6540 files changed, 265832 insertions, 185127 deletions

diff --git a/.clang-format b/.clang-format
index 0bbb1991defe..ccc9b93972a9 100644
--- a/.clang-format
+++ b/.clang-format
@@ -82,11 +82,16 @@ ForEachMacros:
   - '__for_each_thread'
   - '__hlist_for_each_rcu'
   - '__map__for_each_symbol_by_name'
+  - '__pci_bus_for_each_res0'
+  - '__pci_bus_for_each_res1'
+  - '__pci_dev_for_each_res0'
+  - '__pci_dev_for_each_res1'
   - '__perf_evlist__for_each_entry'
   - '__perf_evlist__for_each_entry_reverse'
   - '__perf_evlist__for_each_entry_safe'
   - '__rq_for_each_bio'
   - '__shost_for_each_device'
+  - '__sym_for_each'
   - 'apei_estatus_for_each_section'
   - 'ata_for_each_dev'
   - 'ata_for_each_link'
@@ -105,13 +110,12 @@ ForEachMacros:
   - 'bip_for_each_vec'
   - 'bond_for_each_slave'
   - 'bond_for_each_slave_rcu'
-  - 'bpf__perf_for_each_map'
-  - 'bpf__perf_for_each_map_named'
+  - 'bpf_for_each'
+  - 'bpf_for_each_reg_in_vstate'
+  - 'bpf_for_each_reg_in_vstate_mask'
   - 'bpf_for_each_spilled_reg'
   - 'bpf_object__for_each_map'
   - 'bpf_object__for_each_program'
-  - 'bpf_object__for_each_safe'
-  - 'bpf_perf_object__for_each'
   - 'btree_for_each_safe128'
   - 'btree_for_each_safe32'
   - 'btree_for_each_safe64'
@@ -119,6 +123,7 @@ ForEachMacros:
   - 'card_for_each_dev'
   - 'cgroup_taskset_for_each'
   - 'cgroup_taskset_for_each_leader'
+  - 'cpu_aggr_map__for_each_idx'
   - 'cpufreq_for_each_efficient_entry_idx'
   - 'cpufreq_for_each_entry'
   - 'cpufreq_for_each_entry_idx'
@@ -128,11 +133,14 @@ ForEachMacros:
   - 'css_for_each_descendant_post'
   - 'css_for_each_descendant_pre'
   - 'damon_for_each_region'
+  - 'damon_for_each_region_from'
   - 'damon_for_each_region_safe'
   - 'damon_for_each_scheme'
   - 'damon_for_each_scheme_safe'
   - 'damon_for_each_target'
   - 'damon_for_each_target_safe'
+  - 'damos_for_each_filter'
+  - 'damos_for_each_filter_safe'
   - 'data__for_each_file'
   - 'data__for_each_file_new'
   - 'data__for_each_file_start'
@@ -151,6 +159,8 @@ ForEachMacros:
   - 'drm_client_for_each_connector_iter'
   - 'drm_client_for_each_modeset'
   - 'drm_connector_for_each_possible_encoder'
+  - 'drm_exec_for_each_locked_object'
+  - 'drm_exec_for_each_locked_object_reverse'
   - 'drm_for_each_bridge_in_chain'
   - 'drm_for_each_connector_iter'
   - 'drm_for_each_crtc'
@@ -162,22 +172,32 @@ ForEachMacros:
   - 'drm_for_each_plane'
   - 'drm_for_each_plane_mask'
   - 'drm_for_each_privobj'
+  - 'drm_gem_for_each_gpuva'
+  - 'drm_gem_for_each_gpuva_safe'
+  - 'drm_gpuva_for_each_op'
+  - 'drm_gpuva_for_each_op_from_reverse'
+  - 'drm_gpuva_for_each_op_safe'
+  - 'drm_gpuvm_for_each_va'
+  - 'drm_gpuvm_for_each_va_range'
+  - 'drm_gpuvm_for_each_va_range_safe'
+  - 'drm_gpuvm_for_each_va_safe'
   - 'drm_mm_for_each_hole'
   - 'drm_mm_for_each_node'
   - 'drm_mm_for_each_node_in_range'
   - 'drm_mm_for_each_node_safe'
   - 'dsa_switch_for_each_available_port'
   - 'dsa_switch_for_each_cpu_port'
+  - 'dsa_switch_for_each_cpu_port_continue_reverse'
   - 'dsa_switch_for_each_port'
   - 'dsa_switch_for_each_port_continue_reverse'
   - 'dsa_switch_for_each_port_safe'
   - 'dsa_switch_for_each_user_port'
+  - 'dsa_tree_for_each_cpu_port'
   - 'dsa_tree_for_each_user_port'
+  - 'dsa_tree_for_each_user_port_continue_reverse'
   - 'dso__for_each_symbol'
   - 'dsos__for_each_with_build_id'
   - 'elf_hash_for_each_possible'
-  - 'elf_section__for_each_rel'
-  - 'elf_section__for_each_rela'
   - 'elf_symtab__for_each_symbol'
   - 'evlist__for_each_cpu'
   - 'evlist__for_each_entry'
@@ -186,12 +206,15 @@ ForEachMacros:
   - 'evlist__for_each_entry_reverse'
   - 'evlist__for_each_entry_safe'
   - 'flow_action_for_each'
+  - 'for_each_acpi_consumer_dev'
   - 'for_each_acpi_dev_match'
   - 'for_each_active_dev_scope'
   - 'for_each_active_drhd_unit'
   - 'for_each_active_iommu'
   - 'for_each_active_route'
   - 'for_each_aggr_pgid'
+  - 'for_each_and_bit'
+  - 'for_each_andnot_bit'
   - 'for_each_available_child_of_node'
   - 'for_each_bench'
   - 'for_each_bio'
@@ -222,10 +245,13 @@ ForEachMacros:
   - 'for_each_compatible_node'
   - 'for_each_component_dais'
   - 'for_each_component_dais_safe'
+  - 'for_each_conduit'
   - 'for_each_console'
   - 'for_each_console_srcu'
   - 'for_each_cpu'
   - 'for_each_cpu_and'
+  - 'for_each_cpu_andnot'
+  - 'for_each_cpu_or'
   - 'for_each_cpu_wrap'
   - 'for_each_dapm_widgets'
   - 'for_each_dedup_cand'
@@ -254,9 +280,11 @@ ForEachMacros:
   - 'for_each_free_mem_range'
   - 'for_each_free_mem_range_reverse'
   - 'for_each_func_rsrc'
-  - 'for_each_group_device'
+  - 'for_each_gpiochip_node'
   - 'for_each_group_evsel'
+  - 'for_each_group_evsel_head'
   - 'for_each_group_member'
+  - 'for_each_group_member_head'
   - 'for_each_hstate'
   - 'for_each_if'
   - 'for_each_inject_fn'
@@ -273,6 +301,7 @@ ForEachMacros:
   - 'for_each_lru'
   - 'for_each_matching_node'
   - 'for_each_matching_node_and_match'
+  - 'for_each_media_entity_data_link'
   - 'for_each_mem_pfn_range'
   - 'for_each_mem_range'
   - 'for_each_mem_range_rev'
@@ -281,6 +310,8 @@ ForEachMacros:
   - 'for_each_memory'
   - 'for_each_migratetype_order'
   - 'for_each_missing_reg'
+  - 'for_each_mle_subelement'
+  - 'for_each_mod_mem_type'
   - 'for_each_net'
   - 'for_each_net_continue_reverse'
   - 'for_each_net_rcu'
@@ -288,6 +319,7 @@ ForEachMacros:
   - 'for_each_netdev_continue'
   - 'for_each_netdev_continue_rcu'
   - 'for_each_netdev_continue_reverse'
+  - 'for_each_netdev_dump'
   - 'for_each_netdev_feature'
   - 'for_each_netdev_in_bond_rcu'
   - 'for_each_netdev_rcu'
@@ -308,6 +340,7 @@ ForEachMacros:
   - 'for_each_node_with_cpus'
   - 'for_each_node_with_property'
   - 'for_each_nonreserved_multicast_dest_pgid'
+  - 'for_each_numa_hop_mask'
   - 'for_each_of_allnodes'
   - 'for_each_of_allnodes_from'
   - 'for_each_of_cpu_node'
@@ -326,6 +359,7 @@ ForEachMacros:
   - 'for_each_online_cpu'
   - 'for_each_online_node'
   - 'for_each_online_pgdat'
+  - 'for_each_or_bit'
   - 'for_each_path'
   - 'for_each_pci_bridge'
   - 'for_each_pci_dev'
@@ -333,6 +367,7 @@ ForEachMacros:
   - 'for_each_physmem_range'
   - 'for_each_populated_zone'
   - 'for_each_possible_cpu'
+  - 'for_each_present_blessed_reg'
   - 'for_each_present_cpu'
   - 'for_each_prime_number'
   - 'for_each_prime_number_from'
@@ -348,7 +383,8 @@ ForEachMacros:
   - 'for_each_property_of_node'
   - 'for_each_reg'
   - 'for_each_reg_filtered'
-  - 'for_each_registered_fb'
+  - 'for_each_reloc'
+  - 'for_each_reloc_from'
   - 'for_each_requested_gpio'
   - 'for_each_requested_gpio_in_range'
   - 'for_each_reserved_mem_range'
@@ -357,10 +393,12 @@ ForEachMacros:
   - 'for_each_rtd_components'
   - 'for_each_rtd_cpu_dais'
   - 'for_each_rtd_dais'
+  - 'for_each_sband_iftype_data'
   - 'for_each_script'
   - 'for_each_sec'
   - 'for_each_set_bit'
   - 'for_each_set_bit_from'
+  - 'for_each_set_bit_wrap'
   - 'for_each_set_bitrange'
   - 'for_each_set_bitrange_from'
   - 'for_each_set_clump8'
@@ -371,8 +409,8 @@ ForEachMacros:
   - 'for_each_sgtable_dma_sg'
   - 'for_each_sgtable_page'
   - 'for_each_sgtable_sg'
-  - 'for_each_shell_test'
   - 'for_each_sibling_event'
+  - 'for_each_sta_active_link'
   - 'for_each_subelement'
   - 'for_each_subelement_extid'
   - 'for_each_subelement_id'
@@ -380,10 +418,15 @@ ForEachMacros:
   - 'for_each_subsystem'
   - 'for_each_supported_activate_fn'
   - 'for_each_supported_inject_fn'
+  - 'for_each_sym'
   - 'for_each_test'
   - 'for_each_thread'
   - 'for_each_token'
   - 'for_each_unicast_dest_pgid'
+  - 'for_each_valid_link'
+  - 'for_each_vif_active_link'
+  - 'for_each_vma'
+  - 'for_each_vma_range'
   - 'for_each_vsi'
   - 'for_each_wakeup_source'
   - 'for_each_zone'
@@ -392,10 +435,12 @@ ForEachMacros:
   - 'func_for_each_insn'
   - 'fwnode_for_each_available_child_node'
   - 'fwnode_for_each_child_node'
+  - 'fwnode_for_each_parent_node'
   - 'fwnode_graph_for_each_endpoint'
   - 'gadget_for_each_ep'
   - 'genradix_for_each'
   - 'genradix_for_each_from'
+  - 'genradix_for_each_reverse'
   - 'hash_for_each'
   - 'hash_for_each_possible'
   - 'hash_for_each_possible_rcu'
@@ -439,14 +484,9 @@ ForEachMacros:
   - 'in_dev_for_each_ifa_rcu'
   - 'in_dev_for_each_ifa_rtnl'
   - 'inet_bind_bucket_for_each'
-  - 'inet_lhash2_for_each_icsk'
-  - 'inet_lhash2_for_each_icsk_continue'
-  - 'inet_lhash2_for_each_icsk_rcu'
-  - 'interval_tree_for_each_double_span'
   - 'interval_tree_for_each_span'
   - 'intlist__for_each_entry'
   - 'intlist__for_each_entry_safe'
-  - 'iopt_for_each_contig_area'
   - 'kcore_copy__for_each_phdr'
   - 'key_for_each'
   - 'key_for_each_safe'
@@ -483,28 +523,38 @@ ForEachMacros:
   - 'list_for_each_from'
   - 'list_for_each_prev'
   - 'list_for_each_prev_safe'
+  - 'list_for_each_rcu'
+  - 'list_for_each_reverse'
   - 'list_for_each_safe'
   - 'llist_for_each'
   - 'llist_for_each_entry'
   - 'llist_for_each_entry_safe'
   - 'llist_for_each_safe'
+  - 'lwq_for_each_safe'
   - 'map__for_each_symbol'
   - 'map__for_each_symbol_by_name'
-  - 'map_for_each_event'
-  - 'map_for_each_metric'
   - 'maps__for_each_entry'
   - 'maps__for_each_entry_safe'
+  - 'mas_for_each'
   - 'mci_for_each_dimm'
   - 'media_device_for_each_entity'
   - 'media_device_for_each_intf'
   - 'media_device_for_each_link'
   - 'media_device_for_each_pad'
+  - 'media_entity_for_each_pad'
+  - 'media_pipeline_for_each_entity'
+  - 'media_pipeline_for_each_pad'
+  - 'mlx5_lag_for_each_peer_mdev'
+  - 'msi_domain_for_each_desc'
   - 'msi_for_each_desc'
+  - 'mt_for_each'
   - 'nanddev_io_for_each_page'
   - 'netdev_for_each_lower_dev'
   - 'netdev_for_each_lower_private'
   - 'netdev_for_each_lower_private_rcu'
   - 'netdev_for_each_mc_addr'
+  - 'netdev_for_each_synced_mc_addr'
+  - 'netdev_for_each_synced_uc_addr'
   - 'netdev_for_each_uc_addr'
   - 'netdev_for_each_upper_dev_rcu'
   - 'netdev_hw_addr_list_for_each'
@@ -529,6 +579,7 @@ ForEachMacros:
   - 'perf_config_sections__for_each_entry'
   - 'perf_config_set__for_each_entry'
   - 'perf_cpu_map__for_each_cpu'
+  - 'perf_cpu_map__for_each_idx'
   - 'perf_evlist__for_each_entry'
   - 'perf_evlist__for_each_entry_reverse'
   - 'perf_evlist__for_each_entry_safe'
@@ -538,9 +589,7 @@ ForEachMacros:
   - 'perf_hpp_list__for_each_format_safe'
   - 'perf_hpp_list__for_each_sort_list'
   - 'perf_hpp_list__for_each_sort_list_safe'
-  - 'perf_pmu__for_each_hybrid_pmu'
-  - 'ping_portaddr_for_each_entry'
-  - 'ping_portaddr_for_each_entry_rcu'
+  - 'perf_tool_event__for_each_event'
   - 'plist_for_each'
   - 'plist_for_each_continue'
   - 'plist_for_each_entry'
@@ -577,6 +626,7 @@ ForEachMacros:
   - 'rq_for_each_segment'
   - 'rq_list_for_each'
   - 'rq_list_for_each_safe'
+  - 'sample_read_group__for_each'
   - 'scsi_for_each_prot_sg'
   - 'scsi_for_each_sg'
   - 'sctp_for_each_hentry'
@@ -584,10 +634,12 @@ ForEachMacros:
   - 'sec_for_each_insn'
   - 'sec_for_each_insn_continue'
   - 'sec_for_each_insn_from'
+  - 'sec_for_each_sym'
   - 'shdma_for_each_chan'
   - 'shost_for_each_device'
   - 'sk_for_each'
   - 'sk_for_each_bound'
+  - 'sk_for_each_bound_bhash2'
   - 'sk_for_each_entry_offset_rcu'
   - 'sk_for_each_from'
   - 'sk_for_each_rcu'
@@ -609,6 +661,8 @@ ForEachMacros:
   - 'tb_property_for_each'
   - 'tcf_act_for_each_action'
   - 'tcf_exts_for_each_action'
+  - 'ttm_resource_manager_for_each_res'
+  - 'twsk_for_each_bound_bhash2'
   - 'udp_portaddr_for_each_entry'
   - 'udp_portaddr_for_each_entry_rcu'
   - 'usb_hub_for_each_child'
diff --git a/.mailmap b/.mailmap
index 43031441b2d9..1f6ad79b45e4 100644
--- a/.mailmap
+++ b/.mailmap
@@ -117,6 +117,7 @@ Changbin Du <changbin.du@intel.com> <changbin.du@gmail.com>
 Changbin Du <changbin.du@intel.com> <changbin.du@intel.com>
 Chao Yu <chao@kernel.org> <chao2.yu@samsung.com>
 Chao Yu <chao@kernel.org> <yuchao0@huawei.com>
+Chester Lin <chester62515@gmail.com> <clin@suse.com>
 Chris Chiu <chris.chiu@canonical.com> <chiu@endlessm.com>
 Chris Chiu <chris.chiu@canonical.com> <chiu@endlessos.org>
 Chris Lew <quic_clew@quicinc.com> <clew@codeaurora.org>
@@ -190,6 +191,10 @@ Gao Xiang <xiang@kernel.org> <gaoxiang25@huawei.com>
 Gao Xiang <xiang@kernel.org> <hsiangkao@aol.com>
 Gao Xiang <xiang@kernel.org> <hsiangkao@linux.alibaba.com>
 Gao Xiang <xiang@kernel.org> <hsiangkao@redhat.com>
+Geliang Tang <geliang.tang@linux.dev> <geliang.tang@suse.com>
+Geliang Tang <geliang.tang@linux.dev> <geliangtang@xiaomi.com>
+Geliang Tang <geliang.tang@linux.dev> <geliangtang@gmail.com>
+Geliang Tang <geliang.tang@linux.dev> <geliangtang@163.com>
 Georgi Djakov <djakov@kernel.org> <georgi.djakov@linaro.org>
 Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@de.ibm.com>
 Gerald Schaefer <gerald.schaefer@linux.ibm.com> <gerald.schaefer@de.ibm.com>
@@ -265,6 +270,9 @@ Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
 Jernej Skrabec <jernej.skrabec@gmail.com> <jernej.skrabec@siol.net>
 Jessica Zhang <quic_jesszhan@quicinc.com> <jesszhan@codeaurora.org>
 Jilai Wang <quic_jilaiw@quicinc.com> <jilaiw@codeaurora.org>
+Jiri Kosina <jikos@kernel.org> <jikos@jikos.cz>
+Jiri Kosina <jikos@kernel.org> <jkosina@suse.cz>
+Jiri Kosina <jikos@kernel.org> <jkosina@suse.com>
 Jiri Pirko <jiri@resnulli.us> <jiri@nvidia.com>
 Jiri Pirko <jiri@resnulli.us> <jiri@mellanox.com>
 Jiri Pirko <jiri@resnulli.us> <jpirko@redhat.com>
@@ -369,7 +377,7 @@ Martin Kepplinger <martink@posteo.de> <martin.kepplinger@ginzinger.com>
 Martin Kepplinger <martink@posteo.de> <martin.kepplinger@puri.sm>
 Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com>
 Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com> <martyna.szapar-mudlaw@intel.com>
-Mathieu Othacehe <m.othacehe@gmail.com>
+Mathieu Othacehe <m.othacehe@gmail.com> <othacehe@gnu.org>
 Mat Martineau <martineau@kernel.org> <mathew.j.martineau@linux.intel.com>
 Mat Martineau <martineau@kernel.org> <mathewm@codeaurora.org>
 Matthew Wilcox <willy@infradead.org> <matthew.r.wilcox@intel.com>
@@ -428,6 +436,7 @@ Muna Sinada <quic_msinada@quicinc.com> <msinada@codeaurora.org>
 Murali Nalajala <quic_mnalajal@quicinc.com> <mnalajal@codeaurora.org>
 Mythri P K <mythripk@ti.com>
 Nadia Yvette Chambers <nyc@holomorphy.com> William Lee Irwin III <wli@holomorphy.com>
+Naoya Horiguchi <naoya.horiguchi@nec.com> <n-horiguchi@ah.jp.nec.com>
 Nathan Chancellor <nathan@kernel.org> <natechancellor@gmail.com>
 Neeraj Upadhyay <quic_neeraju@quicinc.com> <neeraju@codeaurora.org>
 Neil Armstrong <neil.armstrong@linaro.org> <narmstrong@baylibre.com>
@@ -469,6 +478,8 @@ Paul E. McKenney <paulmck@kernel.org> <paulmck@linux.vnet.ibm.com>
 Paul E. McKenney <paulmck@kernel.org> <paulmck@us.ibm.com>
 Paul Mackerras <paulus@ozlabs.org> <paulus@samba.org>
 Paul Mackerras <paulus@ozlabs.org> <paulus@au1.ibm.com>
+Paul Moore <paul@paul-moore.com> <paul.moore@hp.com>
+Paul Moore <paul@paul-moore.com> <pmoore@redhat.com>
 Pavankumar Kondeti <quic_pkondeti@quicinc.com> <pkondeti@codeaurora.org>
 Peter A Jonsson <pj@ludd.ltu.se>
 Peter Oruba <peter.oruba@amd.com>
@@ -533,6 +544,8 @@ Sebastian Reichel <sre@kernel.org> <sebastian.reichel@collabora.co.uk>
 Sebastian Reichel <sre@kernel.org> <sre@debian.org>
 Sedat Dilek <sedat.dilek@gmail.com> <sedat.dilek@credativ.de>
 Senthilkumar N L <quic_snlakshm@quicinc.com> <snlakshm@codeaurora.org>
+Serge Hallyn <sergeh@kernel.org> <serge.hallyn@canonical.com>
+Serge Hallyn <sergeh@kernel.org> <serue@us.ibm.com>
 Seth Forshee <sforshee@kernel.org> <seth.forshee@canonical.com>
 Shannon Nelson <shannon.nelson@amd.com> <snelson@pensando.io>
 Shannon Nelson <shannon.nelson@amd.com> <shannon.nelson@intel.com>
@@ -595,6 +608,9 @@ Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
 Uwe Kleine-König <ukleinek@strlen.de>
 Uwe Kleine-König <ukl@pengutronix.de>
 Uwe Kleine-König <Uwe.Kleine-Koenig@digi.com>
+Vadim Fedorenko <vadim.fedorenko@linux.dev> <vadfed@fb.com>
+Vadim Fedorenko <vadim.fedorenko@linux.dev> <vadfed@meta.com>
+Vadim Fedorenko <vadim.fedorenko@linux.dev> <vfedorenko@novek.ru>
 Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
 Vara Reddy <quic_varar@quicinc.com> <varar@codeaurora.org>
 Varadarajan Narayanan <quic_varada@quicinc.com> <varada@codeaurora.org>
@@ -629,4 +645,5 @@ Wolfram Sang <wsa@kernel.org> <w.sang@pengutronix.de>
 Wolfram Sang <wsa@kernel.org> <wsa@the-dreams.de>
 Yakir Yang <kuankuan.y@gmail.com> <ykk@rock-chips.com>
 Yusuke Goda <goda.yusuke@renesas.com>
+Zack Rusin <zack.rusin@broadcom.com> <zackr@vmware.com>
 Zhu Yanjun <zyjzyj2000@gmail.com> <yanjunz@nvidia.com>
diff --git a/CREDITS b/CREDITS
index 6781d4eeb9fb..06b177c6af6a 100644
--- a/CREDITS
+++ b/CREDITS
@@ -9,10 +9,6 @@
 			Linus
 ----------
 
-N: Matt Mackal
-E: mpm@selenic.com
-D: SLOB slab allocator
-
 N: Matti Aarnio
 E: mea@nic.funet.fi
 D: Alpha systems hacking, IPv6 and other network related stuff
@@ -323,6 +319,9 @@ N: Ohad Ben Cohen
 E: ohad@wizery.com
 D: Remote Processor (remoteproc) subsystem
 D: Remote Processor Messaging (rpmsg) subsystem
+D: Hardware spinlock (hwspinlock) subsystem
+D: OMAP hwspinlock driver
+D: OMAP remoteproc driver
 
 N: Krzysztof Benedyczak
 E: golbi@mat.uni.torun.pl
@@ -1425,6 +1424,10 @@ S: University of Stellenbosch
 S: Stellenbosch, Western Cape
 S: South Africa
 
+N: Andy Gross
+E: agross@kernel.org
+D: Qualcomm SoC subsystem and drivers
+
 N: Grant Grundler
 E: grantgrundler@gmail.com
 W: http://obmouse.sourceforge.net/
@@ -1572,6 +1575,10 @@ S: Ampferstr. 50 / 4
 S: 6020 Innsbruck
 S: Austria
 
+N: Mark Hemment
+E: markhe@nextd.demon.co.uk
+D: SLAB allocator implementation
+
 N: Richard Henderson
 E: rth@twiddle.net
 E: rth@cygnus.com
@@ -1862,6 +1869,10 @@ D: Fedora kernel maintenance (2003-2014).
 D: 'Trinity' and similar fuzz testing work.
 D: Misc/Other.
 
+N: Tom Joseph
+E: tjoseph@cadence.com
+D: Cadence PCIe driver
+
 N: Martin Josfsson
 E: gandalf@wlug.westbo.se
 P: 1024D/F6B6D3B1 7610 7CED 5C34 4AA6 DBA2  8BE1 5A6D AF95 F6B6 D3B1
@@ -2133,6 +2144,10 @@ S: 2213 La Terrace Circle
 S: San Jose, CA 95123
 S: USA
 
+N: Mike Kravetz
+E: mike.kravetz@oracle.com
+D: Maintenance and development of the hugetlb subsystem
+
 N: Andreas S. Krebs
 E: akrebs@altavista.net
 D: CYPRESS CY82C693 chipset IDE, Digital's PC-Alpha 164SX boards
@@ -2444,6 +2459,10 @@ D: work on suspend-to-ram/disk, killing duplicates from ioctl32,
 D: Altera SoCFPGA and Nokia N900 support.
 S: Czech Republic
 
+N: Olivia Mackall
+E: olivia@selenic.com
+D: SLOB slab allocator
+
 N: Paul Mackerras
 E: paulus@samba.org
 D: PPP driver
@@ -2951,6 +2970,14 @@ D: IPX development and support
 N: Venkatesh Pallipadi (Venki)
 D: x86/HPET
 
+N: Antti Palosaari
+E: crope@iki.fi
+D: Various DVB drivers
+W: https://palosaari.fi/linux/
+S: Yliopistokatu 1 D 513
+S: FI-90570 Oulu
+S: FINLAND
+
 N: Kyungmin Park
 E: kyungmin.park@samsung.com
 D: Samsung S5Pv210 and Exynos4210 mobile platforms
diff --git a/Documentation/ABI/testing/debugfs-driver-qat_telemetry b/Documentation/ABI/testing/debugfs-driver-qat_telemetry
new file mode 100644
index 000000000000..eacee2072088
--- /dev/null
+++ b/Documentation/ABI/testing/debugfs-driver-qat_telemetry
@@ -0,0 +1,228 @@
+What:		/sys/kernel/debug/qat_<device>_<BDF>/telemetry/control
+Date:		March 2024
+KernelVersion:	6.8
+Contact:	qat-linux@intel.com
+Description:	(RW) Enables/disables the reporting of telemetry metrics.
+
+		Allowed values to write:
+		========================
+		* 0: disable telemetry
+		* 1: enable telemetry
+		* 2, 3, 4: enable telemetry and calculate minimum, maximum
+		  and average for each counter over 2, 3 or 4 samples
+
+		Returned values:
+		================
+		* 1-4: telemetry is enabled and running
+		* 0: telemetry is disabled
+
+		Example.
+
+		Writing '3' to this file starts the collection of
+		telemetry metrics. Samples are collected every second and
+		stored in a circular buffer of size 3. These values are then
+		used to calculate the minimum, maximum and average for each
+		counter. After enabling, counters can be retrieved through
+		the ``device_data`` file::
+
+		  echo 3 > /sys/kernel/debug/qat_4xxx_0000:6b:00.0/telemetry/control
+
+		Writing '0' to this file stops the collection of telemetry
+		metrics::
+
+		  echo 0 > /sys/kernel/debug/qat_4xxx_0000:6b:00.0/telemetry/control
+
+		This attribute is only available for qat_4xxx devices.
+
+What:		/sys/kernel/debug/qat_<device>_<BDF>/telemetry/device_data
+Date:		March 2024
+KernelVersion:	6.8
+Contact:	qat-linux@intel.com
+Description:	(RO) Reports device telemetry counters.
+		Reads report metrics about performance and utilization of
+		a QAT device:
+
+		=======================	========================================
+		Field			Description
+		=======================	========================================
+		sample_cnt		number of acquisitions of telemetry data
+					from the device. Reads are performed
+					every 1000 ms.
+		pci_trans_cnt		number of PCIe partial transactions
+		max_rd_lat		maximum logged read latency [ns] (could
+					be any read operation)
+		rd_lat_acc_avg		average read latency [ns]
+		max_gp_lat		max get to put latency [ns] (only takes
+					samples for AE0)
+		gp_lat_acc_avg		average get to put latency [ns]
+		bw_in			PCIe, write bandwidth [Mbps]
+		bw_out			PCIe, read bandwidth [Mbps]
+		at_page_req_lat_avg	Address Translator(AT), average page
+					request latency [ns]
+		at_trans_lat_avg	AT, average page translation latency [ns]
+		at_max_tlb_used		AT, maximum uTLB used
+		util_cpr<N>		utilization of Compression slice N [%]
+		exec_cpr<N>		execution count of Compression slice N
+		util_xlt<N>		utilization of Translator slice N [%]
+		exec_xlt<N>		execution count of Translator slice N
+		util_dcpr<N>		utilization of Decompression slice N [%]
+		exec_dcpr<N>		execution count of Decompression slice N
+		util_pke<N>		utilization of PKE N [%]
+		exec_pke<N>		execution count of PKE N
+		util_ucs<N>		utilization of UCS slice N [%]
+		exec_ucs<N>		execution count of UCS slice N
+		util_wat<N>		utilization of Wireless Authentication
+					slice N [%]
+		exec_wat<N>		execution count of Wireless Authentication
+					slice N
+		util_wcp<N>		utilization of Wireless Cipher slice N [%]
+		exec_wcp<N>		execution count of Wireless Cipher slice N
+		util_cph<N>		utilization of Cipher slice N [%]
+		exec_cph<N>		execution count of Cipher slice N
+		util_ath<N>		utilization of Authentication slice N [%]
+		exec_ath<N>		execution count of Authentication slice N
+		=======================	========================================
+
+		The telemetry report file can be read with the following command::
+
+		  cat /sys/kernel/debug/qat_4xxx_0000:6b:00.0/telemetry/device_data
+
+		If ``control`` is set to 1, only the current values of the
+		counters are displayed::
+
+		  <counter_name> <current>
+
+		If ``control`` is 2, 3 or 4, counters are displayed in the
+		following format::
+
+		  <counter_name> <current> <min> <max> <avg>
+
+		If a device lacks of a specific accelerator, the corresponding
+		attribute is not reported.
+
+		This attribute is only available for qat_4xxx devices.
+
+What:		/sys/kernel/debug/qat_<device>_<BDF>/telemetry/rp_<A/B/C/D>_data
+Date:		March 2024
+KernelVersion:	6.8
+Contact:	qat-linux@intel.com
+Description:	(RW) Selects up to 4 Ring Pairs (RP) to monitor, one per file,
+		and report telemetry counters related to each.
+
+		Allowed values to write:
+		========================
+		* 0 to ``<num_rps - 1>``:
+		  Ring pair to be monitored. The value of ``num_rps`` can be
+		  retrieved through ``/sys/bus/pci/devices/<BDF>/qat/num_rps``.
+		  See Documentation/ABI/testing/sysfs-driver-qat.
+
+		Reads report metrics about performance and utilization of
+		the selected RP:
+
+		=======================	========================================
+		Field			Description
+		=======================	========================================
+		sample_cnt		number of acquisitions of telemetry data
+					from the device. Reads are performed
+					every 1000 ms
+		rp_num			RP number associated with slot <A/B/C/D>
+		service_type		service associated to the RP
+		pci_trans_cnt		number of PCIe partial transactions
+		gp_lat_acc_avg		average get to put latency [ns]
+		bw_in			PCIe, write bandwidth [Mbps]
+		bw_out			PCIe, read bandwidth [Mbps]
+		at_glob_devtlb_hit	Message descriptor DevTLB hit rate
+		at_glob_devtlb_miss	Message descriptor DevTLB miss rate
+		tl_at_payld_devtlb_hit	Payload DevTLB hit rate
+		tl_at_payld_devtlb_miss	Payload DevTLB miss rate
+		======================= ========================================
+
+		Example.
+
+		Writing the value '32' to the file ``rp_C_data`` starts the
+		collection of telemetry metrics for ring pair 32::
+
+		  echo 32 > /sys/kernel/debug/qat_4xxx_0000:6b:00.0/telemetry/rp_C_data
+
+		Once a ring pair is selected, statistics can be read accessing
+		the file::
+
+		  cat /sys/kernel/debug/qat_4xxx_0000:6b:00.0/telemetry/rp_C_data
+
+		If ``control`` is set to 1, only the current values of the
+		counters are displayed::
+
+		  <counter_name> <current>
+
+		If ``control`` is 2, 3 or 4, counters are displayed in the
+		following format::
+
+		  <counter_name> <current> <min> <max> <avg>
+
+
+		On QAT GEN4 devices there are 64 RPs on a PF, so the allowed
+		values are 0..63. This number is absolute to the device.
+		If Virtual Functions (VF) are used, the ring pair number can
+		be derived from the Bus, Device, Function of the VF:
+
+		============ ====== ====== ====== ======
+		PCI BDF/VF   RP0    RP1    RP2    RP3
+		============ ====== ====== ====== ======
+		0000:6b:0.1  RP  0  RP  1  RP  2  RP  3
+		0000:6b:0.2  RP  4  RP  5  RP  6  RP  7
+		0000:6b:0.3  RP  8  RP  9  RP 10  RP 11
+		0000:6b:0.4  RP 12  RP 13  RP 14  RP 15
+		0000:6b:0.5  RP 16  RP 17  RP 18  RP 19
+		0000:6b:0.6  RP 20  RP 21  RP 22  RP 23
+		0000:6b:0.7  RP 24  RP 25  RP 26  RP 27
+		0000:6b:1.0  RP 28  RP 29  RP 30  RP 31
+		0000:6b:1.1  RP 32  RP 33  RP 34  RP 35
+		0000:6b:1.2  RP 36  RP 37  RP 38  RP 39
+		0000:6b:1.3  RP 40  RP 41  RP 42  RP 43
+		0000:6b:1.4  RP 44  RP 45  RP 46  RP 47
+		0000:6b:1.5  RP 48  RP 49  RP 50  RP 51
+		0000:6b:1.6  RP 52  RP 53  RP 54  RP 55
+		0000:6b:1.7  RP 56  RP 57  RP 58  RP 59
+		0000:6b:2.0  RP 60  RP 61  RP 62  RP 63
+		============ ====== ====== ====== ======
+
+		The mapping is only valid for the BDFs of VFs on the host.
+
+
+		The service provided on a ring-pair varies depending on the
+		configuration. The configuration for a given device can be
+		queried and set using ``cfg_services``.
+		See Documentation/ABI/testing/sysfs-driver-qat for details.
+
+		The following table reports how ring pairs are mapped to VFs
+		on the PF 0000:6b:0.0 configured for `sym;asym` or `asym;sym`:
+
+		=========== ============ =========== ============ ===========
+		PCI BDF/VF  RP0/service  RP1/service RP2/service  RP3/service
+		=========== ============ =========== ============ ===========
+		0000:6b:0.1 RP 0 asym    RP 1 sym    RP 2 asym    RP 3 sym
+		0000:6b:0.2 RP 4 asym    RP 5 sym    RP 6 asym    RP 7 sym
+		0000:6b:0.3 RP 8 asym    RP 9 sym    RP10 asym    RP11 sym
+		...         ...          ...         ...          ...
+		=========== ============ =========== ============ ===========
+
+		All VFs follow the same pattern.
+
+
+		The following table reports how ring pairs are mapped to VFs on
+		the PF 0000:6b:0.0 configured for `dc`:
+
+		=========== ============ =========== ============ ===========
+		PCI BDF/VF  RP0/service  RP1/service RP2/service  RP3/service
+		=========== ============ =========== ============ ===========
+		0000:6b:0.1 RP 0 dc      RP 1 dc     RP 2 dc      RP 3 dc
+		0000:6b:0.2 RP 4 dc      RP 5 dc     RP 6 dc      RP 7 dc
+		0000:6b:0.3 RP 8 dc      RP 9 dc     RP10 dc      RP11 dc
+		...         ...          ...         ...          ...
+		=========== ============ =========== ============ ===========
+
+		The mapping of a RP to a service can be retrieved using
+		``rp2srv`` from sysfs.
+		See Documentation/ABI/testing/sysfs-driver-qat for details.
+
+		This attribute is only available for qat_4xxx devices.
diff --git a/Documentation/ABI/testing/debugfs-hisi-hpre b/Documentation/ABI/testing/debugfs-hisi-hpre
index 82abf92df429..8e8de49c5cc6 100644
--- a/Documentation/ABI/testing/debugfs-hisi-hpre
+++ b/Documentation/ABI/testing/debugfs-hisi-hpre
@@ -101,7 +101,7 @@ What:		/sys/kernel/debug/hisi_hpre/<bdf>/qm/status
 Date:		Apr 2020
 Contact:	linux-crypto@vger.kernel.org
 Description:	Dump the status of the QM.
-		Four states: initiated, started, stopped and closed.
+		Two states: work, stop.
 		Available for both PF and VF, and take no other effect on HPRE.
 
 What:		/sys/kernel/debug/hisi_hpre/<bdf>/qm/diff_regs
diff --git a/Documentation/ABI/testing/debugfs-hisi-sec b/Documentation/ABI/testing/debugfs-hisi-sec
index 93c530d1bf0f..deeefe2c735e 100644
--- a/Documentation/ABI/testing/debugfs-hisi-sec
+++ b/Documentation/ABI/testing/debugfs-hisi-sec
@@ -81,7 +81,7 @@ What:		/sys/kernel/debug/hisi_sec2/<bdf>/qm/status
 Date:		Apr 2020
 Contact:	linux-crypto@vger.kernel.org
 Description:	Dump the status of the QM.
-		Four states: initiated, started, stopped and closed.
+		Two states: work, stop.
 		Available for both PF and VF, and take no other effect on SEC.
 
 What:		/sys/kernel/debug/hisi_sec2/<bdf>/qm/diff_regs
diff --git a/Documentation/ABI/testing/debugfs-hisi-zip b/Documentation/ABI/testing/debugfs-hisi-zip
index fd3f314cf8d1..593714afaed2 100644
--- a/Documentation/ABI/testing/debugfs-hisi-zip
+++ b/Documentation/ABI/testing/debugfs-hisi-zip
@@ -94,7 +94,7 @@ What:		/sys/kernel/debug/hisi_zip/<bdf>/qm/status
 Date:		Apr 2020
 Contact:	linux-crypto@vger.kernel.org
 Description:	Dump the status of the QM.
-		Four states: initiated, started, stopped and closed.
+		Two states: work, stop.
 		Available for both PF and VF, and take no other effect on ZIP.
 
 What:		/sys/kernel/debug/hisi_zip/<bdf>/qm/diff_regs
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-caps b/Documentation/ABI/testing/sysfs-bus-event_source-devices-caps
index 8757dcf41c08..a5f506f7d481 100644
--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-caps
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-caps
@@ -16,3 +16,9 @@ Description:
 		Example output in powerpc:
 		grep . /sys/bus/event_source/devices/cpu/caps/*
 		/sys/bus/event_source/devices/cpu/caps/pmu_name:POWER9
+
+		The "branch_counter_nr" in the supported platform exposes the
+		maximum number of counters which can be shown in the u64 counters
+		of PERF_SAMPLE_BRANCH_COUNTERS, while the "branch_counter_width"
+		exposes the width of each counter. Both of them can be used by
+		the perf tool to parse the logged counters in each branch.
diff --git a/Documentation/ABI/testing/sysfs-bus-optee-devices b/Documentation/ABI/testing/sysfs-bus-optee-devices
index 0f58701367b6..af31e5a22d89 100644
--- a/Documentation/ABI/testing/sysfs-bus-optee-devices
+++ b/Documentation/ABI/testing/sysfs-bus-optee-devices
@@ -6,3 +6,12 @@ Description:
 		OP-TEE bus provides reference to registered drivers under this directory. The <uuid>
 		matches Trusted Application (TA) driver and corresponding TA in secure OS. Drivers
 		are free to create needed API under optee-ta-<uuid> directory.
+
+What:		/sys/bus/tee/devices/optee-ta-<uuid>/need_supplicant
+Date:		November 2023
+KernelVersion:	6.7
+Contact:	op-tee@lists.trustedfirmware.org
+Description:
+		Allows to distinguish whether an OP-TEE based TA/device requires user-space
+		tee-supplicant to function properly or not. This attribute will be present for
+		devices which depend on tee-supplicant to be running.
diff --git a/Documentation/ABI/testing/sysfs-bus-spi-devices-spi-nor b/Documentation/ABI/testing/sysfs-bus-spi-devices-spi-nor
index c800621eff95..9ed5582ddea2 100644
--- a/Documentation/ABI/testing/sysfs-bus-spi-devices-spi-nor
+++ b/Documentation/ABI/testing/sysfs-bus-spi-devices-spi-nor
@@ -25,6 +25,9 @@ KernelVersion:	5.14
 Contact:	linux-mtd@lists.infradead.org
 Description:	(RO) Part name of the SPI NOR flash.
 
+		The attribute is optional. User space should not rely on
+		it to be present or even correct. Instead, user space
+		should read the jedec_id attribute.
 
 What:		/sys/bus/spi/devices/.../spi-nor/sfdp
 Date:		April 2021
diff --git a/Documentation/ABI/testing/sysfs-class-devfreq b/Documentation/ABI/testing/sysfs-class-devfreq
index 5e6b74f30406..1e7e0bb4c14e 100644
--- a/Documentation/ABI/testing/sysfs-class-devfreq
+++ b/Documentation/ABI/testing/sysfs-class-devfreq
@@ -52,6 +52,9 @@ Description:
 
 			echo 0 > /sys/class/devfreq/.../trans_stat
 
+		If the transition table is bigger than PAGE_SIZE, reading
+		this will return an -EFBIG error.
+
 What:		/sys/class/devfreq/.../available_frequencies
 Date:		October 2012
 Contact:	Nishanth Menon <nm@ti.com>
diff --git a/Documentation/ABI/testing/sysfs-class-led b/Documentation/ABI/testing/sysfs-class-led
index b2ff0012c0f2..2e24ac3bd7ef 100644
--- a/Documentation/ABI/testing/sysfs-class-led
+++ b/Documentation/ABI/testing/sysfs-class-led
@@ -59,15 +59,6 @@ Description:
 		brightness. Reading this file when no hw brightness change
 		event has happened will return an ENODATA error.
 
-What:		/sys/class/leds/<led>/color
-Date:		June 2023
-KernelVersion:	6.5
-Description:
-		Color of the LED.
-
-		This is a read-only file. Reading this file returns the color
-		of the LED as a string (e.g: "red", "green", "multicolor").
-
 What:		/sys/class/leds/<led>/trigger
 Date:		March 2006
 KernelVersion:	2.6.17
diff --git a/Documentation/ABI/testing/sysfs-devices-platform-kunpeng_hccs b/Documentation/ABI/testing/sysfs-devices-platform-kunpeng_hccs
index fdb4e36310fb..1666340820f7 100644
--- a/Documentation/ABI/testing/sysfs-devices-platform-kunpeng_hccs
+++ b/Documentation/ABI/testing/sysfs-devices-platform-kunpeng_hccs
@@ -3,7 +3,7 @@ What:		/sys/devices/platform/HISI04Bx:00/chipX/linked_full_lane
 What:		/sys/devices/platform/HISI04Bx:00/chipX/crc_err_cnt
 Date:		November 2023
 KernelVersion:	6.6
-Contact:	Huisong Li <lihuisong@huawei.org>
+Contact:	Huisong Li <lihuisong@huawei.com>
 Description:
 		The /sys/devices/platform/HISI04Bx:00/chipX/ directory
 		contains read-only attributes exposing some summarization
@@ -26,7 +26,7 @@ What:		/sys/devices/platform/HISI04Bx:00/chipX/dieY/linked_full_lane
 What:		/sys/devices/platform/HISI04Bx:00/chipX/dieY/crc_err_cnt
 Date:		November 2023
 KernelVersion:	6.6
-Contact:	Huisong Li <lihuisong@huawei.org>
+Contact:	Huisong Li <lihuisong@huawei.com>
 Description:
 		The /sys/devices/platform/HISI04Bx:00/chipX/dieY/ directory
 		contains read-only attributes exposing some summarization
@@ -54,7 +54,7 @@ What:		/sys/devices/platform/HISI04Bx:00/chipX/dieY/hccsN/lane_mask
 What:		/sys/devices/platform/HISI04Bx:00/chipX/dieY/hccsN/crc_err_cnt
 Date:		November 2023
 KernelVersion:	6.6
-Contact:	Huisong Li <lihuisong@huawei.org>
+Contact:	Huisong Li <lihuisong@huawei.com>
 Description:
 		The /sys/devices/platform/HISI04Bx/chipX/dieX/hccsN/ directory
 		contains read-only attributes exposing information about
diff --git a/Documentation/ABI/testing/sysfs-driver-ufs b/Documentation/ABI/testing/sysfs-driver-ufs
index 0c7efaf62de0..5bf7073b4f75 100644
--- a/Documentation/ABI/testing/sysfs-driver-ufs
+++ b/Documentation/ABI/testing/sysfs-driver-ufs
@@ -1223,6 +1223,55 @@ Description:	This file shows the total latency (in micro seconds) of write
 
 		The file is read only.
 
+What:		/sys/bus/platform/drivers/ufshcd/*/power_info/lane
+What:		/sys/bus/platform/devices/*.ufs/power_info/lane
+Date:		September 2023
+Contact:	Can Guo <quic_cang@quicinc.com>
+Description:	This file shows how many lanes are enabled on the UFS link,
+		i.e., an output 2 means UFS link is operating with 2 lanes.
+
+		The file is read only.
+
+What:		/sys/bus/platform/drivers/ufshcd/*/power_info/mode
+What:		/sys/bus/platform/devices/*.ufs/power_info/mode
+Date:		September 2023
+Contact:	Can Guo <quic_cang@quicinc.com>
+Description:	This file shows the PA power mode of UFS.
+
+		The file is read only.
+
+What:		/sys/bus/platform/drivers/ufshcd/*/power_info/rate
+What:		/sys/bus/platform/devices/*.ufs/power_info/rate
+Date:		September 2023
+Contact:	Can Guo <quic_cang@quicinc.com>
+Description:	This file shows the speed rate of UFS link.
+
+		The file is read only.
+
+What:		/sys/bus/platform/drivers/ufshcd/*/power_info/gear
+What:		/sys/bus/platform/devices/*.ufs/power_info/gear
+Date:		September 2023
+Contact:	Can Guo <quic_cang@quicinc.com>
+Description:	This file shows the gear of UFS link.
+
+		The file is read only.
+
+What:		/sys/bus/platform/drivers/ufshcd/*/power_info/dev_pm
+What:		/sys/bus/platform/devices/*.ufs/power_info/dev_pm
+Date:		September 2023
+Contact:	Can Guo <quic_cang@quicinc.com>
+Description:	This file shows the UFS device power mode.
+
+		The file is read only.
+
+What:		/sys/bus/platform/drivers/ufshcd/*/power_info/link_state
+What:		/sys/bus/platform/devices/*.ufs/power_info/link_state
+Date:		September 2023
+Contact:	Can Guo <quic_cang@quicinc.com>
+Description:	This file shows the state of UFS link.
+
+		The file is read only.
+
 What:		/sys/bus/platform/drivers/ufshcd/*/device_descriptor/wb_presv_us_en
 What:		/sys/bus/platform/devices/*.ufs/device_descriptor/wb_presv_us_en
 Date:		June 2020
@@ -1474,3 +1523,10 @@ Description:	Indicates status of Write Booster.
 
 		The file is read only.
 
+What:		/sys/bus/platform/drivers/ufshcd/*/rtc_update_ms
+What:		/sys/bus/platform/devices/*.ufs/rtc_update_ms
+Date:		November 2023
+Contact:	Bean Huo <beanhuo@micron.com>
+Description:
+		rtc_update_ms indicates how often the host should synchronize or update the
+		UFS RTC. If set to 0, this will disable UFS RTC periodic update.
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-damon b/Documentation/ABI/testing/sysfs-kernel-mm-damon
index b35649a46a2f..bfa5b8288d8d 100644
--- a/Documentation/ABI/testing/sysfs-kernel-mm-damon
+++ b/Documentation/ABI/testing/sysfs-kernel-mm-damon
@@ -25,12 +25,14 @@ Description:	Writing 'on' or 'off' to this file makes the kdamond starts or
 		stops, respectively.  Reading the file returns the keywords
 		based on the current status.  Writing 'commit' to this file
 		makes the kdamond reads the user inputs in the sysfs files
-		except 'state' again.  Writing 'update_schemes_stats' to the
-		file updates contents of schemes stats files of the kdamond.
-		Writing 'update_schemes_tried_regions' to the file updates
-		contents of 'tried_regions' directory of every scheme directory
-		of this kdamond.  Writing 'update_schemes_tried_bytes' to the
-		file updates only '.../tried_regions/total_bytes' files of this
+		except 'state' again.  Writing 'commit_schemes_quota_goals' to
+		this file makes the kdamond reads the quota goal files again.
+		Writing 'update_schemes_stats' to the file updates contents of
+		schemes stats files of the kdamond.  Writing
+		'update_schemes_tried_regions' to the file updates contents of
+		'tried_regions' directory of every scheme directory of this
+		kdamond.  Writing 'update_schemes_tried_bytes' to the file
+		updates only '.../tried_regions/total_bytes' files of this
 		kdamond.  Writing 'clear_schemes_tried_regions' to the file
 		removes contents of the 'tried_regions' directory.
 
@@ -212,6 +214,25 @@ Contact:	SeongJae Park <sj@kernel.org>
 Description:	Writing to and reading from this file sets and gets the quotas
 		charge reset interval of the scheme in milliseconds.
 
+What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/goals/nr_goals
+Date:		Nov 2023
+Contact:	SeongJae Park <sj@kernel.org>
+Description:	Writing a number 'N' to this file creates the number of
+		directories for setting automatic tuning of the scheme's
+		aggressiveness named '0' to 'N-1' under the goals/ directory.
+
+What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/goals/<G>/target_value
+Date:		Nov 2023
+Contact:	SeongJae Park <sj@kernel.org>
+Description:	Writing to and reading from this file sets and gets the target
+		value of the goal metric.
+
+What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/goals/<G>/current_value
+Date:		Nov 2023
+Contact:	SeongJae Park <sj@kernel.org>
+Description:	Writing to and reading from this file sets and gets the current
+		value of the goal metric.
+
 What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/weights/sz_permil
 Date:		Mar 2022
 Contact:	SeongJae Park <sj@kernel.org>
diff --git a/Documentation/ABI/testing/sysfs-platform-silicom b/Documentation/ABI/testing/sysfs-platform-silicom
new file mode 100644
index 000000000000..2288b3665d16
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-platform-silicom
@@ -0,0 +1,29 @@
+What:		/sys/devices/platform/silicom-platform/uc_version
+Date:		November 2023
+KernelVersion:	6.7
+Contact:	Henry Shi <henrys@silicom-usa.com>
+Description:
+		This file allows to read microcontroller firmware
+		version of current platform.
+
+What:		/sys/devices/platform/silicom-platform/power_cycle
+Date:		November 2023
+KernelVersion:	6.7
+Contact:	Henry Shi <henrys@silicom-usa.com>
+		This file allow user to power cycle the platform.
+		Default value is 0; when set to 1, it powers down
+		the platform, waits 5 seconds, then powers on the
+		device. It returns to default value after power cycle.
+
+		0 - default value.
+
+What:		/sys/devices/platform/silicom-platform/efuse_status
+Date:		November 2023
+KernelVersion:	6.7
+Contact:	Henry Shi <henrys@silicom-usa.com>
+Description:
+		This file is read only. It returns the current
+		OTP status:
+
+		0 - not programmed.
+		1 - programmed.
diff --git a/Documentation/Makefile b/Documentation/Makefile
index 2f35793acd2a..3885bbe260eb 100644
--- a/Documentation/Makefile
+++ b/Documentation/Makefile
@@ -97,7 +97,21 @@ quiet_cmd_sphinx = SPHINX  $@ --> file://$(abspath $(BUILDDIR)/$3/$4)
 		cp $(if $(patsubst /%,,$(DOCS_CSS)),$(abspath $(srctree)/$(DOCS_CSS)),$(DOCS_CSS)) $(BUILDDIR)/$3/_static/; \
 	fi
 
-htmldocs:
+YNL_INDEX:=$(srctree)/Documentation/networking/netlink_spec/index.rst
+YNL_RST_DIR:=$(srctree)/Documentation/networking/netlink_spec
+YNL_YAML_DIR:=$(srctree)/Documentation/netlink/specs
+YNL_TOOL:=$(srctree)/tools/net/ynl/ynl-gen-rst.py
+
+YNL_RST_FILES_TMP := $(patsubst %.yaml,%.rst,$(wildcard $(YNL_YAML_DIR)/*.yaml))
+YNL_RST_FILES := $(patsubst $(YNL_YAML_DIR)%,$(YNL_RST_DIR)%, $(YNL_RST_FILES_TMP))
+
+$(YNL_INDEX): $(YNL_RST_FILES)
+	$(Q)$(YNL_TOOL) -o $@ -x
+
+$(YNL_RST_DIR)/%.rst: $(YNL_YAML_DIR)/%.yaml $(YNL_TOOL)
+	$(Q)$(YNL_TOOL) -i $< -o $@
+
+htmldocs: $(YNL_INDEX)
 	@$(srctree)/scripts/sphinx-pre-install --version-check
 	@+$(foreach var,$(SPHINXDIRS),$(call loop_cmd,sphinx,html,$(var),,$(var)))
 
diff --git a/Documentation/RAS/ras.rst b/Documentation/RAS/ras.rst
new file mode 100644
index 000000000000..2556b397cd27
--- /dev/null
+++ b/Documentation/RAS/ras.rst
@@ -0,0 +1,26 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Reliability, Availability and Serviceability features
+=====================================================
+
+This documents different aspects of the RAS functionality present in the
+kernel.
+
+Error decoding
+---------------
+
+* x86
+
+Error decoding on AMD systems should be done using the rasdaemon tool:
+https://github.com/mchehab/rasdaemon/
+
+While the daemon is running, it would automatically log and decode
+errors. If not, one can still decode such errors by supplying the
+hardware information from the error::
+
+        $ rasdaemon -p --status <STATUS> --ipid <IPID> --smca
+
+Also, the user can pass particular family and model to decode the error
+string::
+
+        $ rasdaemon -p --status <STATUS> --ipid <IPID> --smca --family <CPU Family> --model <CPU Model> --bank <BANK_NUM>
diff --git a/Documentation/admin-guide/blockdev/zram.rst b/Documentation/admin-guide/blockdev/zram.rst
index e4551579cb12..ee2b0030d416 100644
--- a/Documentation/admin-guide/blockdev/zram.rst
+++ b/Documentation/admin-guide/blockdev/zram.rst
@@ -328,7 +328,7 @@ as idle::
 From now on, any pages on zram are idle pages. The idle mark
 will be removed until someone requests access of the block.
 IOW, unless there is access request, those pages are still idle pages.
-Additionally, when CONFIG_ZRAM_MEMORY_TRACKING is enabled pages can be
+Additionally, when CONFIG_ZRAM_TRACK_ENTRY_ACTIME is enabled pages can be
 marked as idle based on how long (in seconds) it's been since they were
 last accessed::
 
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 3f85254f3cef..17e6e9565156 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1093,7 +1093,11 @@ All time durations are in microseconds.
 	A read-write single value file which exists on non-root
 	cgroups.  The default is "100".
 
-	The weight in the range [1, 10000].
+	For non idle groups (cpu.idle = 0), the weight is in the
+	range [1, 10000].
+
+	If the cgroup has been configured to be SCHED_IDLE (cpu.idle = 1),
+	then the weight will show as a 0.
 
   cpu.weight.nice
 	A read-write single value file which exists on non-root
@@ -1157,6 +1161,16 @@ All time durations are in microseconds.
         values similar to the sched_setattr(2). This maximum utilization
         value is used to clamp the task specific maximum utilization clamp.
 
+  cpu.idle
+	A read-write single value file which exists on non-root cgroups.
+	The default is 0.
+
+	This is the cgroup analog of the per-task SCHED_IDLE sched policy.
+	Setting this value to a 1 will make the scheduling policy of the
+	cgroup SCHED_IDLE. The threads inside the cgroup will retain their
+	own relative priorities, but the cgroup itself will be treated as
+	very low priority relative to its peers.
+
 
 
 Memory
@@ -1679,6 +1693,21 @@ PAGE_SIZE multiple when read back.
 	limit, it will refuse to take any more stores before existing
 	entries fault back in or are written out to disk.
 
+  memory.zswap.writeback
+	A read-write single value file. The default value is "1". The
+	initial value of the root cgroup is 1, and when a new cgroup is
+	created, it inherits the current value of its parent.
+
+	When this is set to 0, all swapping attempts to swapping devices
+	are disabled. This included both zswap writebacks, and swapping due
+	to zswap store failures. If the zswap store failures are recurring
+	(for e.g if the pages are incompressible), users can observe
+	reclaim inefficiency after disabling writeback (because the same
+	pages might be rejected again and again).
+
+	Note that this is subtly different from setting memory.swap.max to
+	0, as it still allows for pages to be written to the zswap pool.
+
   memory.pressure
 	A read-only nested-keyed file.
 
@@ -2316,6 +2345,13 @@ Cpuset Interface Files
 	treated to have an implicit value of "cpuset.cpus" in the
 	formation of local partition.
 
+  cpuset.cpus.isolated
+	A read-only and root cgroup only multiple values file.
+
+	This file shows the set of all isolated CPUs used in existing
+	isolated partitions. It will be empty if no isolated partition
+	is created.
+
   cpuset.cpus.partition
 	A read-write single value file which exists on non-root
 	cpuset-enabled cgroups.  This flag is owned by the parent cgroup
@@ -2358,11 +2394,11 @@ Cpuset Interface Files
 	partition or scheduling domain.  The set of exclusive CPUs is
 	determined by the value of its "cpuset.cpus.exclusive.effective".
 
-	When set to "isolated", the CPUs in that partition will
-	be in an isolated state without any load balancing from the
-	scheduler.  Tasks placed in such a partition with multiple
-	CPUs should be carefully distributed and bound to each of the
-	individual CPUs for optimal performance.
+	When set to "isolated", the CPUs in that partition will be in
+	an isolated state without any load balancing from the scheduler
+	and excluded from the unbound workqueues.  Tasks placed in such
+	a partition with multiple CPUs should be carefully distributed
+	and bound to each of the individual CPUs for optimal performance.
 
 	A partition root ("root" or "isolated") can be in one of the
 	two possible states - valid or invalid.  An invalid partition
diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst
index 43ea35613dfc..fb40a1f6f79e 100644
--- a/Documentation/admin-guide/index.rst
+++ b/Documentation/admin-guide/index.rst
@@ -119,6 +119,7 @@ configure specific aspects of kernel behavior to your liking.
    parport
    perf-security
    pm/index
+   pmf
    pnp
    rapidio
    ras
diff --git a/Documentation/admin-guide/kdump/vmcoreinfo.rst b/Documentation/admin-guide/kdump/vmcoreinfo.rst
index 78e4d2e7ba14..bced9e4b6e08 100644
--- a/Documentation/admin-guide/kdump/vmcoreinfo.rst
+++ b/Documentation/admin-guide/kdump/vmcoreinfo.rst
@@ -172,7 +172,7 @@ variables.
 Offset of the free_list's member. This value is used to compute the number
 of free pages.
 
-Each zone has a free_area structure array called free_area[MAX_ORDER + 1].
+Each zone has a free_area structure array called free_area[NR_PAGE_ORDERS].
 The free_list represents a linked list of free page blocks.
 
 (list_head, next|prev)
@@ -189,11 +189,11 @@ Offsets of the vmap_area's members. They carry vmalloc-specific
 information. Makedumpfile gets the start address of the vmalloc region
 from this.
 
-(zone.free_area, MAX_ORDER + 1)
--------------------------------
+(zone.free_area, NR_PAGE_ORDERS)
+--------------------------------
 
 Free areas descriptor. User-space tools use this value to iterate the
-free_area ranges. MAX_ORDER is used by the zone buddy allocator.
+free_area ranges. NR_PAGE_ORDERS is used by the zone buddy allocator.
 
 prb
 ---
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 91bd74b2e203..505af40e97bc 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -981,17 +981,17 @@
 			buddy allocator. Bigger value increase the probability
 			of catching random memory corruption, but reduce the
 			amount of memory for normal system use. The maximum
-			possible value is MAX_ORDER/2.  Setting this parameter
-			to 1 or 2 should be enough to identify most random
-			memory corruption problems caused by bugs in kernel or
-			driver code when a CPU writes to (or reads from) a
-			random memory location. Note that there exists a class
-			of memory corruptions problems caused by buggy H/W or
-			F/W or by drivers badly programming DMA (basically when
-			memory is written at bus level and the CPU MMU is
-			bypassed) which are not detectable by
-			CONFIG_DEBUG_PAGEALLOC, hence this option will not help
-			tracking down these problems.
+			possible value is MAX_PAGE_ORDER/2.  Setting this
+			parameter to 1 or 2 should be enough to identify most
+			random memory corruption problems caused by bugs in
+			kernel or driver code when a CPU writes to (or reads
+			from) a random memory location. Note that there exists
+			a class of memory corruptions problems caused by buggy
+			H/W or F/W or by drivers badly programming DMA
+			(basically when memory is written at bus level and the
+			CPU MMU is bypassed) which are not detectable by
+			CONFIG_DEBUG_PAGEALLOC, hence this option will not
+			help tracking down these problems.
 
 	debug_pagealloc=
 			[KNL] When CONFIG_DEBUG_PAGEALLOC is set, this parameter
@@ -4147,7 +4147,7 @@
 			[KNL] Minimal page reporting order
 			Format: <integer>
 			Adjust the minimal page reporting order. The page
-			reporting is disabled when it exceeds MAX_ORDER.
+			reporting is disabled when it exceeds MAX_PAGE_ORDER.
 
 	panic=		[KNL] Kernel behaviour on panic: delay <timeout>
 			timeout > 0: seconds before rebooting
@@ -5555,6 +5555,13 @@
 			print every Nth verbose statement, where N is the value
 			specified.
 
+	regulator_ignore_unused
+			[REGULATOR]
+			Prevents regulator framework from disabling regulators
+			that are unused, due no driver claiming them. This may
+			be useful for debug and development, but should not be
+			needed on a platform with proper driver support.
+
 	relax_domain_level=
 			[KNL, SMP] Set scheduler's default relax_domain_level.
 			See Documentation/admin-guide/cgroup-v1/cpusets.rst.
diff --git a/Documentation/admin-guide/mm/damon/usage.rst b/Documentation/admin-guide/mm/damon/usage.rst
index da94feb97ed1..9d23144bf985 100644
--- a/Documentation/admin-guide/mm/damon/usage.rst
+++ b/Documentation/admin-guide/mm/damon/usage.rst
@@ -59,41 +59,47 @@ Files Hierarchy
 The files hierarchy of DAMON sysfs interface is shown below.  In the below
 figure, parents-children relations are represented with indentations, each
 directory is having ``/`` suffix, and files in each directory are separated by
-comma (","). ::
-
-    /sys/kernel/mm/damon/admin
-    │ kdamonds/nr_kdamonds
-    │ │ 0/state,pid
-    │ │ │ contexts/nr_contexts
-    │ │ │ │ 0/avail_operations,operations
-    │ │ │ │ │ monitoring_attrs/
+comma (",").
+
+.. parsed-literal::
+
+    :ref:`/sys/kernel/mm/damon <sysfs_root>`/admin
+    │ :ref:`kdamonds <sysfs_kdamonds>`/nr_kdamonds
+    │ │ :ref:`0 <sysfs_kdamond>`/state,pid
+    │ │ │ :ref:`contexts <sysfs_contexts>`/nr_contexts
+    │ │ │ │ :ref:`0 <sysfs_context>`/avail_operations,operations
+    │ │ │ │ │ :ref:`monitoring_attrs <sysfs_monitoring_attrs>`/
     │ │ │ │ │ │ intervals/sample_us,aggr_us,update_us
     │ │ │ │ │ │ nr_regions/min,max
-    │ │ │ │ │ targets/nr_targets
-    │ │ │ │ │ │ 0/pid_target
-    │ │ │ │ │ │ │ regions/nr_regions
-    │ │ │ │ │ │ │ │ 0/start,end
+    │ │ │ │ │ :ref:`targets <sysfs_targets>`/nr_targets
+    │ │ │ │ │ │ :ref:`0 <sysfs_target>`/pid_target
+    │ │ │ │ │ │ │ :ref:`regions <sysfs_regions>`/nr_regions
+    │ │ │ │ │ │ │ │ :ref:`0 <sysfs_region>`/start,end
     │ │ │ │ │ │ │ │ ...
     │ │ │ │ │ │ ...
-    │ │ │ │ │ schemes/nr_schemes
-    │ │ │ │ │ │ 0/action,apply_interval_us
-    │ │ │ │ │ │ │ access_pattern/
+    │ │ │ │ │ :ref:`schemes <sysfs_schemes>`/nr_schemes
+    │ │ │ │ │ │ :ref:`0 <sysfs_scheme>`/action,apply_interval_us
+    │ │ │ │ │ │ │ :ref:`access_pattern <sysfs_access_pattern>`/
     │ │ │ │ │ │ │ │ sz/min,max
     │ │ │ │ │ │ │ │ nr_accesses/min,max
     │ │ │ │ │ │ │ │ age/min,max
-    │ │ │ │ │ │ │ quotas/ms,bytes,reset_interval_ms
+    │ │ │ │ │ │ │ :ref:`quotas <sysfs_quotas>`/ms,bytes,reset_interval_ms
     │ │ │ │ │ │ │ │ weights/sz_permil,nr_accesses_permil,age_permil
-    │ │ │ │ │ │ │ watermarks/metric,interval_us,high,mid,low
-    │ │ │ │ │ │ │ filters/nr_filters
+    │ │ │ │ │ │ │ │ :ref:`goals <sysfs_schemes_quota_goals>`/nr_goals
+    │ │ │ │ │ │ │ │ │ 0/target_value,current_value
+    │ │ │ │ │ │ │ :ref:`watermarks <sysfs_watermarks>`/metric,interval_us,high,mid,low
+    │ │ │ │ │ │ │ :ref:`filters <sysfs_filters>`/nr_filters
     │ │ │ │ │ │ │ │ 0/type,matching,memcg_id
-    │ │ │ │ │ │ │ stats/nr_tried,sz_tried,nr_applied,sz_applied,qt_exceeds
-    │ │ │ │ │ │ │ tried_regions/total_bytes
+    │ │ │ │ │ │ │ :ref:`stats <sysfs_schemes_stats>`/nr_tried,sz_tried,nr_applied,sz_applied,qt_exceeds
+    │ │ │ │ │ │ │ :ref:`tried_regions <sysfs_schemes_tried_regions>`/total_bytes
     │ │ │ │ │ │ │ │ 0/start,end,nr_accesses,age
     │ │ │ │ │ │ │ │ ...
     │ │ │ │ │ │ ...
     │ │ │ │ ...
     │ │ ...
 
+.. _sysfs_root:
+
 Root
 ----
 
@@ -102,6 +108,8 @@ has one directory named ``admin``.  The directory contains the files for
 privileged user space programs' control of DAMON.  User space tools or daemons
 having the root permission could use this directory.
 
+.. _sysfs_kdamonds:
+
 kdamonds/
 ---------
 
@@ -113,6 +121,8 @@ details) exists.  In the beginning, this directory has only one file,
 child directories named ``0`` to ``N-1``.  Each directory represents each
 kdamond.
 
+.. _sysfs_kdamond:
+
 kdamonds/<N>/
 -------------
 
@@ -120,29 +130,37 @@ In each kdamond directory, two files (``state`` and ``pid``) and one directory
 (``contexts``) exist.
 
 Reading ``state`` returns ``on`` if the kdamond is currently running, or
-``off`` if it is not running.  Writing ``on`` or ``off`` makes the kdamond be
-in the state.  Writing ``commit`` to the ``state`` file makes kdamond reads the
-user inputs in the sysfs files except ``state`` file again.  Writing
-``update_schemes_stats`` to ``state`` file updates the contents of stats files
-for each DAMON-based operation scheme of the kdamond.  For details of the
-stats, please refer to :ref:`stats section <sysfs_schemes_stats>`.
-
-Writing ``update_schemes_tried_regions`` to ``state`` file updates the
-DAMON-based operation scheme action tried regions directory for each
-DAMON-based operation scheme of the kdamond.  Writing
-``update_schemes_tried_bytes`` to ``state`` file updates only
-``.../tried_regions/total_bytes`` files.  Writing
-``clear_schemes_tried_regions`` to ``state`` file clears the DAMON-based
-operating scheme action tried regions directory for each DAMON-based operation
-scheme of the kdamond.  For details of the DAMON-based operation scheme action
-tried regions directory, please refer to :ref:`tried_regions section
-<sysfs_schemes_tried_regions>`.
+``off`` if it is not running.
+
+Users can write below commands for the kdamond to the ``state`` file.
+
+- ``on``: Start running.
+- ``off``: Stop running.
+- ``commit``: Read the user inputs in the sysfs files except ``state`` file
+  again.
+- ``commit_schemes_quota_goals``: Read the DAMON-based operation schemes'
+  :ref:`quota goals <sysfs_schemes_quota_goals>`.
+- ``update_schemes_stats``: Update the contents of stats files for each
+  DAMON-based operation scheme of the kdamond.  For details of the stats,
+  please refer to :ref:`stats section <sysfs_schemes_stats>`.
+- ``update_schemes_tried_regions``: Update the DAMON-based operation scheme
+  action tried regions directory for each DAMON-based operation scheme of the
+  kdamond.  For details of the DAMON-based operation scheme action tried
+  regions directory, please refer to
+  :ref:`tried_regions section <sysfs_schemes_tried_regions>`.
+- ``update_schemes_tried_bytes``: Update only ``.../tried_regions/total_bytes``
+  files.
+- ``clear_schemes_tried_regions``: Clear the DAMON-based operating scheme
+  action tried regions directory for each DAMON-based operation scheme of the
+  kdamond.
 
 If the state is ``on``, reading ``pid`` shows the pid of the kdamond thread.
 
 ``contexts`` directory contains files for controlling the monitoring contexts
 that this kdamond will execute.
 
+.. _sysfs_contexts:
+
 kdamonds/<N>/contexts/
 ----------------------
 
@@ -153,7 +171,7 @@ number (``N``) to the file creates the number of child directories named as
 details).  At the moment, only one context per kdamond is supported, so only
 ``0`` or ``1`` can be written to the file.
 
-.. _sysfs_contexts:
+.. _sysfs_context:
 
 contexts/<N>/
 -------------
@@ -203,6 +221,8 @@ writing to and rading from the files.
 For more details about the intervals and monitoring regions range, please refer
 to the Design document (:doc:`/mm/damon/design`).
 
+.. _sysfs_targets:
+
 contexts/<N>/targets/
 ---------------------
 
@@ -210,6 +230,8 @@ In the beginning, this directory has only one file, ``nr_targets``.  Writing a
 number (``N``) to the file creates the number of child directories named ``0``
 to ``N-1``.  Each directory represents each monitoring target.
 
+.. _sysfs_target:
+
 targets/<N>/
 ------------
 
@@ -244,6 +266,8 @@ In the beginning, this directory has only one file, ``nr_regions``.  Writing a
 number (``N``) to the file creates the number of child directories named ``0``
 to ``N-1``.  Each directory represents each initial monitoring target region.
 
+.. _sysfs_region:
+
 regions/<N>/
 ------------
 
@@ -254,6 +278,8 @@ region by writing to and reading from the files, respectively.
 Each region should not overlap with others.  ``end`` of directory ``N`` should
 be equal or smaller than ``start`` of directory ``N+1``.
 
+.. _sysfs_schemes:
+
 contexts/<N>/schemes/
 ---------------------
 
@@ -265,6 +291,8 @@ In the beginning, this directory has only one file, ``nr_schemes``.  Writing a
 number (``N``) to the file creates the number of child directories named ``0``
 to ``N-1``.  Each directory represents each DAMON-based operation scheme.
 
+.. _sysfs_scheme:
+
 schemes/<N>/
 ------------
 
@@ -277,7 +305,7 @@ The ``action`` file is for setting and getting the scheme's :ref:`action
 from the file and their meaning are as below.
 
 Note that support of each action depends on the running DAMON operations set
-:ref:`implementation <sysfs_contexts>`.
+:ref:`implementation <sysfs_context>`.
 
  - ``willneed``: Call ``madvise()`` for the region with ``MADV_WILLNEED``.
    Supported by ``vaddr`` and ``fvaddr`` operations set.
@@ -299,6 +327,8 @@ Note that support of each action depends on the running DAMON operations set
 The ``apply_interval_us`` file is for setting and getting the scheme's
 :ref:`apply_interval <damon_design_damos>` in microseconds.
 
+.. _sysfs_access_pattern:
+
 schemes/<N>/access_pattern/
 ---------------------------
 
@@ -312,6 +342,8 @@ to and reading from the ``min`` and ``max`` files under ``sz``,
 ``nr_accesses``, and ``age`` directories, respectively.  Note that the ``min``
 and the ``max`` form a closed interval.
 
+.. _sysfs_quotas:
+
 schemes/<N>/quotas/
 -------------------
 
@@ -319,8 +351,7 @@ The directory for the :ref:`quotas <damon_design_damos_quotas>` of the given
 DAMON-based operation scheme.
 
 Under ``quotas`` directory, three files (``ms``, ``bytes``,
-``reset_interval_ms``) and one directory (``weights``) having three files
-(``sz_permil``, ``nr_accesses_permil``, and ``age_permil``) in it exist.
+``reset_interval_ms``) and two directores (``weights`` and ``goals``) exist.
 
 You can set the ``time quota`` in milliseconds, ``size quota`` in bytes, and
 ``reset interval`` in milliseconds by writing the values to the three files,
@@ -330,11 +361,37 @@ apply the action to only up to ``bytes`` bytes of memory regions within the
 ``reset_interval_ms``.  Setting both ``ms`` and ``bytes`` zero disables the
 quota limits.
 
-You can also set the :ref:`prioritization weights
+Under ``weights`` directory, three files (``sz_permil``,
+``nr_accesses_permil``, and ``age_permil``) exist.
+You can set the :ref:`prioritization weights
 <damon_design_damos_quotas_prioritization>` for size, access frequency, and age
 in per-thousand unit by writing the values to the three files under the
 ``weights`` directory.
 
+.. _sysfs_schemes_quota_goals:
+
+schemes/<N>/quotas/goals/
+-------------------------
+
+The directory for the :ref:`automatic quota tuning goals
+<damon_design_damos_quotas_auto_tuning>` of the given DAMON-based operation
+scheme.
+
+In the beginning, this directory has only one file, ``nr_goals``.  Writing a
+number (``N``) to the file creates the number of child directories named ``0``
+to ``N-1``.  Each directory represents each goal and current achievement.
+Among the multiple feedback, the best one is used.
+
+Each goal directory contains two files, namely ``target_value`` and
+``current_value``.  Users can set and get any number to those files to set the
+feedback.  User space main workload's latency or throughput, system metrics
+like free memory ratio or memory pressure stall time (PSI) could be example
+metrics for the values.  Note that users should write
+``commit_schemes_quota_goals`` to the ``state`` file of the :ref:`kdamond
+directory <sysfs_kdamond>` to pass the feedback to DAMON.
+
+.. _sysfs_watermarks:
+
 schemes/<N>/watermarks/
 -----------------------
 
@@ -354,6 +411,8 @@ as below.
 
 The ``interval`` should written in microseconds unit.
 
+.. _sysfs_filters:
+
 schemes/<N>/filters/
 --------------------
 
@@ -394,7 +453,7 @@ pages of all memory cgroups except ``/having_care_already``.::
     echo N > 1/matching
 
 Note that ``anon`` and ``memcg`` filters are currently supported only when
-``paddr`` :ref:`implementation <sysfs_contexts>` is being used.
+``paddr`` :ref:`implementation <sysfs_context>` is being used.
 
 Also, memory regions that are filtered out by ``addr`` or ``target`` filters
 are not counted as the scheme has tried to those, while regions that filtered
@@ -449,6 +508,8 @@ and query-like efficient data access monitoring results retrievals.  For the
 latter use case, in particular, users can set the ``action`` as ``stat`` and
 set the ``access pattern`` as their interested pattern that they want to query.
 
+.. _sysfs_schemes_tried_region:
+
 tried_regions/<N>/
 ------------------
 
diff --git a/Documentation/admin-guide/mm/ksm.rst b/Documentation/admin-guide/mm/ksm.rst
index e59231ac6bb7..a639cac12477 100644
--- a/Documentation/admin-guide/mm/ksm.rst
+++ b/Documentation/admin-guide/mm/ksm.rst
@@ -80,6 +80,9 @@ pages_to_scan
         how many pages to scan before ksmd goes to sleep
         e.g. ``echo 100 > /sys/kernel/mm/ksm/pages_to_scan``.
 
+        The pages_to_scan value cannot be changed if ``advisor_mode`` has
+        been set to scan-time.
+
         Default: 100 (chosen for demonstration purposes)
 
 sleep_millisecs
@@ -164,6 +167,29 @@ smart_scan
         optimization is enabled.  The ``pages_skipped`` metric shows how
         effective the setting is.
 
+advisor_mode
+        The ``advisor_mode`` selects the current advisor. Two modes are
+        supported: none and scan-time. The default is none. By setting
+        ``advisor_mode`` to scan-time, the scan time advisor is enabled.
+        The section about ``advisor`` explains in detail how the scan time
+        advisor works.
+
+adivsor_max_cpu
+        specifies the upper limit of the cpu percent usage of the ksmd
+        background thread. The default is 70.
+
+advisor_target_scan_time
+        specifies the target scan time in seconds to scan all the candidate
+        pages. The default value is 200 seconds.
+
+advisor_min_pages_to_scan
+        specifies the lower limit of the ``pages_to_scan`` parameter of the
+        scan time advisor. The default is 500.
+
+adivsor_max_pages_to_scan
+        specifies the upper limit of the ``pages_to_scan`` parameter of the
+        scan time advisor. The default is 30000.
+
 The effectiveness of KSM and MADV_MERGEABLE is shown in ``/sys/kernel/mm/ksm/``:
 
 general_profit
@@ -263,6 +289,35 @@ ksm_swpin_copy
 	note that KSM page might be copied when swapping in because do_swap_page()
 	cannot do all the locking needed to reconstitute a cross-anon_vma KSM page.
 
+Advisor
+=======
+
+The number of candidate pages for KSM is dynamic. It can be often observed
+that during the startup of an application more candidate pages need to be
+processed. Without an advisor the ``pages_to_scan`` parameter needs to be
+sized for the maximum number of candidate pages. The scan time advisor can
+changes the ``pages_to_scan`` parameter based on demand.
+
+The advisor can be enabled, so KSM can automatically adapt to changes in the
+number of candidate pages to scan. Two advisors are implemented: none and
+scan-time. With none, no advisor is enabled. The default is none.
+
+The scan time advisor changes the ``pages_to_scan`` parameter based on the
+observed scan times. The possible values for the ``pages_to_scan`` parameter is
+limited by the ``advisor_max_cpu`` parameter. In addition there is also the
+``advisor_target_scan_time`` parameter. This parameter sets the target time to
+scan all the KSM candidate pages. The parameter ``advisor_target_scan_time``
+decides how aggressive the scan time advisor scans candidate pages. Lower
+values make the scan time advisor to scan more aggresively. This is the most
+important parameter for the configuration of the scan time advisor.
+
+The initial value and the maximum value can be changed with
+``advisor_min_pages_to_scan`` and ``advisor_max_pages_to_scan``. The default
+values are sufficient for most workloads and use cases.
+
+The ``pages_to_scan`` parameter is re-calculated after a scan has been completed.
+
+
 --
 Izik Eidus,
 Hugh Dickins, 17 Nov 2009
diff --git a/Documentation/admin-guide/mm/pagemap.rst b/Documentation/admin-guide/mm/pagemap.rst
index fe17cf210426..f5f065c67615 100644
--- a/Documentation/admin-guide/mm/pagemap.rst
+++ b/Documentation/admin-guide/mm/pagemap.rst
@@ -253,6 +253,7 @@ Following flags about pages are currently supported:
 - ``PAGE_IS_SWAPPED`` - Page is in swapped
 - ``PAGE_IS_PFNZERO`` - Page has zero PFN
 - ``PAGE_IS_HUGE`` - Page is THP or Hugetlb backed
+- ``PAGE_IS_SOFT_DIRTY`` - Page is soft-dirty
 
 The ``struct pm_scan_arg`` is used as the argument of the IOCTL.
 
diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
index b0cc8243e093..04eb45a2f940 100644
--- a/Documentation/admin-guide/mm/transhuge.rst
+++ b/Documentation/admin-guide/mm/transhuge.rst
@@ -45,10 +45,25 @@ components:
    the two is using hugepages just because of the fact the TLB miss is
    going to run faster.
 
+Modern kernels support "multi-size THP" (mTHP), which introduces the
+ability to allocate memory in blocks that are bigger than a base page
+but smaller than traditional PMD-size (as described above), in
+increments of a power-of-2 number of pages. mTHP can back anonymous
+memory (for example 16K, 32K, 64K, etc). These THPs continue to be
+PTE-mapped, but in many cases can still provide similar benefits to
+those outlined above: Page faults are significantly reduced (by a
+factor of e.g. 4, 8, 16, etc), but latency spikes are much less
+prominent because the size of each page isn't as huge as the PMD-sized
+variant and there is less memory to clear in each page fault. Some
+architectures also employ TLB compression mechanisms to squeeze more
+entries in when a set of PTEs are virtually and physically contiguous
+and approporiately aligned. In this case, TLB misses will occur less
+often.
+
 THP can be enabled system wide or restricted to certain tasks or even
 memory ranges inside task's address space. Unless THP is completely
 disabled, there is ``khugepaged`` daemon that scans memory and
-collapses sequences of basic pages into huge pages.
+collapses sequences of basic pages into PMD-sized huge pages.
 
 The THP behaviour is controlled via :ref:`sysfs <thp_sysfs>`
 interface and using madvise(2) and prctl(2) system calls.
@@ -95,12 +110,40 @@ Global THP controls
 Transparent Hugepage Support for anonymous memory can be entirely disabled
 (mostly for debugging purposes) or only enabled inside MADV_HUGEPAGE
 regions (to avoid the risk of consuming more memory resources) or enabled
-system wide. This can be achieved with one of::
+system wide. This can be achieved per-supported-THP-size with one of::
+
+	echo always >/sys/kernel/mm/transparent_hugepage/hugepages-<size>kB/enabled
+	echo madvise >/sys/kernel/mm/transparent_hugepage/hugepages-<size>kB/enabled
+	echo never >/sys/kernel/mm/transparent_hugepage/hugepages-<size>kB/enabled
+
+where <size> is the hugepage size being addressed, the available sizes
+for which vary by system.
+
+For example::
+
+	echo always >/sys/kernel/mm/transparent_hugepage/hugepages-2048kB/enabled
+
+Alternatively it is possible to specify that a given hugepage size
+will inherit the top-level "enabled" value::
+
+	echo inherit >/sys/kernel/mm/transparent_hugepage/hugepages-<size>kB/enabled
+
+For example::
+
+	echo inherit >/sys/kernel/mm/transparent_hugepage/hugepages-2048kB/enabled
+
+The top-level setting (for use with "inherit") can be set by issuing
+one of the following commands::
 
 	echo always >/sys/kernel/mm/transparent_hugepage/enabled
 	echo madvise >/sys/kernel/mm/transparent_hugepage/enabled
 	echo never >/sys/kernel/mm/transparent_hugepage/enabled
 
+By default, PMD-sized hugepages have enabled="inherit" and all other
+hugepage sizes have enabled="never". If enabling multiple hugepage
+sizes, the kernel will select the most appropriate enabled size for a
+given allocation.
+
 It's also possible to limit defrag efforts in the VM to generate
 anonymous hugepages in case they're not immediately free to madvise
 regions or to never try to defrag memory and simply fallback to regular
@@ -146,25 +189,34 @@ madvise
 never
 	should be self-explanatory.
 
-By default kernel tries to use huge zero page on read page fault to
-anonymous mapping. It's possible to disable huge zero page by writing 0
-or enable it back by writing 1::
+By default kernel tries to use huge, PMD-mappable zero page on read
+page fault to anonymous mapping. It's possible to disable huge zero
+page by writing 0 or enable it back by writing 1::
 
 	echo 0 >/sys/kernel/mm/transparent_hugepage/use_zero_page
 	echo 1 >/sys/kernel/mm/transparent_hugepage/use_zero_page
 
-Some userspace (such as a test program, or an optimized memory allocation
-library) may want to know the size (in bytes) of a transparent hugepage::
+Some userspace (such as a test program, or an optimized memory
+allocation library) may want to know the size (in bytes) of a
+PMD-mappable transparent hugepage::
 
 	cat /sys/kernel/mm/transparent_hugepage/hpage_pmd_size
 
-khugepaged will be automatically started when
-transparent_hugepage/enabled is set to "always" or "madvise, and it'll
-be automatically shutdown if it's set to "never".
+khugepaged will be automatically started when one or more hugepage
+sizes are enabled (either by directly setting "always" or "madvise",
+or by setting "inherit" while the top-level enabled is set to "always"
+or "madvise"), and it'll be automatically shutdown when the last
+hugepage size is disabled (either by directly setting "never", or by
+setting "inherit" while the top-level enabled is set to "never").
 
 Khugepaged controls
 -------------------
 
+.. note::
+   khugepaged currently only searches for opportunities to collapse to
+   PMD-sized THP and no attempt is made to collapse to other THP
+   sizes.
+
 khugepaged runs usually at low frequency so while one may not want to
 invoke defrag algorithms synchronously during the page faults, it
 should be worth invoking defrag at least in khugepaged. However it's
@@ -282,19 +334,26 @@ force
 Need of application restart
 ===========================
 
-The transparent_hugepage/enabled values and tmpfs mount option only affect
-future behavior. So to make them effective you need to restart any
-application that could have been using hugepages. This also applies to the
-regions registered in khugepaged.
+The transparent_hugepage/enabled and
+transparent_hugepage/hugepages-<size>kB/enabled values and tmpfs mount
+option only affect future behavior. So to make them effective you need
+to restart any application that could have been using hugepages. This
+also applies to the regions registered in khugepaged.
 
 Monitoring usage
 ================
 
-The number of anonymous transparent huge pages currently used by the
+.. note::
+   Currently the below counters only record events relating to
+   PMD-sized THP. Events relating to other THP sizes are not included.
+
+The number of PMD-sized anonymous transparent huge pages currently used by the
 system is available by reading the AnonHugePages field in ``/proc/meminfo``.
-To identify what applications are using anonymous transparent huge pages,
-it is necessary to read ``/proc/PID/smaps`` and count the AnonHugePages fields
-for each mapping.
+To identify what applications are using PMD-sized anonymous transparent huge
+pages, it is necessary to read ``/proc/PID/smaps`` and count the AnonHugePages
+fields for each mapping. (Note that AnonHugePages only applies to traditional
+PMD-sized THP for historical reasons and should have been called
+AnonHugePmdMapped).
 
 The number of file transparent huge pages mapped to userspace is available
 by reading ShmemPmdMapped and ShmemHugePages fields in ``/proc/meminfo``.
@@ -413,7 +472,7 @@ for huge pages.
 Optimizing the applications
 ===========================
 
-To be guaranteed that the kernel will map a 2M page immediately in any
+To be guaranteed that the kernel will map a THP immediately in any
 memory region, the mmap region has to be hugepage naturally
 aligned. posix_memalign() can provide that guarantee.
 
diff --git a/Documentation/admin-guide/mm/userfaultfd.rst b/Documentation/admin-guide/mm/userfaultfd.rst
index 203e26da5f92..e5cc8848dcb3 100644
--- a/Documentation/admin-guide/mm/userfaultfd.rst
+++ b/Documentation/admin-guide/mm/userfaultfd.rst
@@ -113,6 +113,9 @@ events, except page fault notifications, may be generated:
   areas. ``UFFD_FEATURE_MINOR_SHMEM`` is the analogous feature indicating
   support for shmem virtual memory areas.
 
+- ``UFFD_FEATURE_MOVE`` indicates that the kernel supports moving an
+  existing page contents from userspace.
+
 The userland application should set the feature flags it intends to use
 when invoking the ``UFFDIO_API`` ioctl, to request that those features be
 enabled if supported.
diff --git a/Documentation/admin-guide/mm/zswap.rst b/Documentation/admin-guide/mm/zswap.rst
index 45b98390e938..b42132969e31 100644
--- a/Documentation/admin-guide/mm/zswap.rst
+++ b/Documentation/admin-guide/mm/zswap.rst
@@ -153,6 +153,26 @@ attribute, e. g.::
 
 Setting this parameter to 100 will disable the hysteresis.
 
+Some users cannot tolerate the swapping that comes with zswap store failures
+and zswap writebacks. Swapping can be disabled entirely (without disabling
+zswap itself) on a cgroup-basis as follows:
+
+	echo 0 > /sys/fs/cgroup/<cgroup-name>/memory.zswap.writeback
+
+Note that if the store failures are recurring (for e.g if the pages are
+incompressible), users can observe reclaim inefficiency after disabling
+writeback (because the same pages might be rejected again and again).
+
+When there is a sizable amount of cold memory residing in the zswap pool, it
+can be advantageous to proactively write these cold pages to swap and reclaim
+the memory for other use cases. By default, the zswap shrinker is disabled.
+User can enable it as follows:
+
+  echo Y > /sys/module/zswap/parameters/shrinker_enabled
+
+This can be enabled at the boot time if ``CONFIG_ZSWAP_SHRINKER_DEFAULT_ON`` is
+selected.
+
 A debugfs interface is provided for various statistic about pool size, number
 of pages stored, same-value filled pages and various counters for the reasons
 pages are rejected.
diff --git a/Documentation/admin-guide/perf/dwc_pcie_pmu.rst b/Documentation/admin-guide/perf/dwc_pcie_pmu.rst
new file mode 100644
index 000000000000..d47cd229d710
--- /dev/null
+++ b/Documentation/admin-guide/perf/dwc_pcie_pmu.rst
@@ -0,0 +1,94 @@
+======================================================================
+Synopsys DesignWare Cores (DWC) PCIe Performance Monitoring Unit (PMU)
+======================================================================
+
+DesignWare Cores (DWC) PCIe PMU
+===============================
+
+The PMU is a PCIe configuration space register block provided by each PCIe Root
+Port in a Vendor-Specific Extended Capability named RAS D.E.S (Debug, Error
+injection, and Statistics).
+
+As the name indicates, the RAS DES capability supports system level
+debugging, AER error injection, and collection of statistics. To facilitate
+collection of statistics, Synopsys DesignWare Cores PCIe controller
+provides the following two features:
+
+- one 64-bit counter for Time Based Analysis (RX/TX data throughput and
+  time spent in each low-power LTSSM state) and
+- one 32-bit counter for Event Counting (error and non-error events for
+  a specified lane)
+
+Note: There is no interrupt for counter overflow.
+
+Time Based Analysis
+-------------------
+
+Using this feature you can obtain information regarding RX/TX data
+throughput and time spent in each low-power LTSSM state by the controller.
+The PMU measures data in two categories:
+
+- Group#0: Percentage of time the controller stays in LTSSM states.
+- Group#1: Amount of data processed (Units of 16 bytes).
+
+Lane Event counters
+-------------------
+
+Using this feature you can obtain Error and Non-Error information in
+specific lane by the controller. The PMU event is selected by all of:
+
+- Group i
+- Event j within the Group i
+- Lane k
+
+Some of the events only exist for specific configurations.
+
+DesignWare Cores (DWC) PCIe PMU Driver
+=======================================
+
+This driver adds PMU devices for each PCIe Root Port named based on the BDF of
+the Root Port. For example,
+
+    30:03.0 PCI bridge: Device 1ded:8000 (rev 01)
+
+the PMU device name for this Root Port is dwc_rootport_3018.
+
+The DWC PCIe PMU driver registers a perf PMU driver, which provides
+description of available events and configuration options in sysfs, see
+/sys/bus/event_source/devices/dwc_rootport_{bdf}.
+
+The "format" directory describes format of the config fields of the
+perf_event_attr structure. The "events" directory provides configuration
+templates for all documented events.  For example,
+"Rx_PCIe_TLP_Data_Payload" is an equivalent of "eventid=0x22,type=0x1".
+
+The "perf list" command shall list the available events from sysfs, e.g.::
+
+    $# perf list | grep dwc_rootport
+    <...>
+    dwc_rootport_3018/Rx_PCIe_TLP_Data_Payload/        [Kernel PMU event]
+    <...>
+    dwc_rootport_3018/rx_memory_read,lane=?/               [Kernel PMU event]
+
+Time Based Analysis Event Usage
+-------------------------------
+
+Example usage of counting PCIe RX TLP data payload (Units of bytes)::
+
+    $# perf stat -a -e dwc_rootport_3018/Rx_PCIe_TLP_Data_Payload/
+
+The average RX/TX bandwidth can be calculated using the following formula:
+
+    PCIe RX Bandwidth = Rx_PCIe_TLP_Data_Payload / Measure_Time_Window
+    PCIe TX Bandwidth = Tx_PCIe_TLP_Data_Payload / Measure_Time_Window
+
+Lane Event Usage
+-------------------------------
+
+Each lane has the same event set and to avoid generating a list of hundreds
+of events, the user need to specify the lane ID explicitly, e.g.::
+
+    $# perf stat -a -e dwc_rootport_3018/rx_memory_read,lane=4/
+
+The driver does not support sampling, therefore "perf record" will not
+work. Per-task (without "-a") perf sessions are not supported.
diff --git a/Documentation/admin-guide/perf/imx-ddr.rst b/Documentation/admin-guide/perf/imx-ddr.rst
index 90926d0fb8ec..77418ae5a290 100644
--- a/Documentation/admin-guide/perf/imx-ddr.rst
+++ b/Documentation/admin-guide/perf/imx-ddr.rst
@@ -13,8 +13,8 @@ is one register for each counter. Counter 0 is special in that it always counts
 interrupt is raised. If any other counter overflows, it continues counting, and
 no interrupt is raised.
 
-The "format" directory describes format of the config (event ID) and config1
-(AXI filtering) fields of the perf_event_attr structure, see /sys/bus/event_source/
+The "format" directory describes format of the config (event ID) and config1/2
+(AXI filter setting) fields of the perf_event_attr structure, see /sys/bus/event_source/
 devices/imx8_ddr0/format/. The "events" directory describes the events types
 hardware supported that can be used with perf tool, see /sys/bus/event_source/
 devices/imx8_ddr0/events/. The "caps" directory describes filter features implemented
@@ -28,12 +28,11 @@ in DDR PMU, see /sys/bus/events_source/devices/imx8_ddr0/caps/.
 AXI filtering is only used by CSV modes 0x41 (axid-read) and 0x42 (axid-write)
 to count reading or writing matches filter setting. Filter setting is various
 from different DRAM controller implementations, which is distinguished by quirks
-in the driver. You also can dump info from userspace, filter in "caps" directory
-indicates whether PMU supports AXI ID filter or not; enhanced_filter indicates
-whether PMU supports enhanced AXI ID filter or not. Value 0 for un-supported, and
-value 1 for supported.
+in the driver. You also can dump info from userspace, "caps" directory show the
+type of AXI filter (filter, enhanced_filter and super_filter). Value 0 for
+un-supported, and value 1 for supported.
 
-* With DDR_CAP_AXI_ID_FILTER quirk(filter: 1, enhanced_filter: 0).
+* With DDR_CAP_AXI_ID_FILTER quirk(filter: 1, enhanced_filter: 0, super_filter: 0).
   Filter is defined with two configuration parts:
   --AXI_ID defines AxID matching value.
   --AXI_MASKING defines which bits of AxID are meaningful for the matching.
@@ -65,7 +64,37 @@ value 1 for supported.
 
         perf stat -a -e imx8_ddr0/axid-read,axi_id=0x12/ cmd, which will monitor ARID=0x12
 
-* With DDR_CAP_AXI_ID_FILTER_ENHANCED quirk(filter: 1, enhanced_filter: 1).
+* With DDR_CAP_AXI_ID_FILTER_ENHANCED quirk(filter: 1, enhanced_filter: 1, super_filter: 0).
   This is an extension to the DDR_CAP_AXI_ID_FILTER quirk which permits
   counting the number of bytes (as opposed to the number of bursts) from DDR
   read and write transactions concurrently with another set of data counters.
+
+* With DDR_CAP_AXI_ID_PORT_CHANNEL_FILTER quirk(filter: 0, enhanced_filter: 0, super_filter: 1).
+  There is a limitation in previous AXI filter, it cannot filter different IDs
+  at the same time as the filter is shared between counters. This quirk is the
+  extension of AXI ID filter. One improvement is that counter 1-3 has their own
+  filter, means that it supports concurrently filter various IDs. Another
+  improvement is that counter 1-3 supports AXI PORT and CHANNEL selection. Support
+  selecting address channel or data channel.
+
+  Filter is defined with 2 configuration registers per counter 1-3.
+  --Counter N MASK COMP register - including AXI_ID and AXI_MASKING.
+  --Counter N MUX CNTL register - including AXI CHANNEL and AXI PORT.
+
+      - 0: address channel
+      - 1: data channel
+
+  PMU in DDR subsystem, only one single port0 exists, so axi_port is reserved
+  which should be 0.
+
+  .. code-block:: bash
+
+      perf stat -a -e imx8_ddr0/axid-read,axi_mask=0xMMMM,axi_id=0xDDDD,axi_channel=0xH/ cmd
+      perf stat -a -e imx8_ddr0/axid-write,axi_mask=0xMMMM,axi_id=0xDDDD,axi_channel=0xH/ cmd
+
+  .. note::
+
+      axi_channel is inverted in userspace, and it will be reverted in driver
+      automatically. So that users do not need specify axi_channel if want to
+      monitor data channel from DDR transactions, since data channel is more
+      meaningful.
diff --git a/Documentation/admin-guide/perf/index.rst b/Documentation/admin-guide/perf/index.rst
index a2e6f2c81146..f4a4513c526f 100644
--- a/Documentation/admin-guide/perf/index.rst
+++ b/Documentation/admin-guide/perf/index.rst
@@ -19,6 +19,7 @@ Performance monitor support
    arm_dsu_pmu
    thunderx2-pmu
    alibaba_pmu
+   dwc_pcie_pmu
    nvidia-pmu
    meson-ddr-pmu
    cxl
diff --git a/Documentation/admin-guide/pmf.rst b/Documentation/admin-guide/pmf.rst
new file mode 100644
index 000000000000..9ee729ffc19b
--- /dev/null
+++ b/Documentation/admin-guide/pmf.rst
@@ -0,0 +1,24 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Set udev rules for PMF Smart PC Builder
+---------------------------------------
+
+AMD PMF(Platform Management Framework) Smart PC Solution builder has to set the system states
+like S0i3, Screen lock, hibernate etc, based on the output actions provided by the PMF
+TA (Trusted Application).
+
+In order for this to work the PMF driver generates a uevent for userspace to react to. Below are
+sample udev rules that can facilitate this experience when a machine has PMF Smart PC solution builder
+enabled.
+
+Please add the following line(s) to
+``/etc/udev/rules.d/99-local.rules``::
+
+        DRIVERS=="amd-pmf", ACTION=="change", ENV{EVENT_ID}=="0", RUN+="/usr/bin/systemctl suspend"
+        DRIVERS=="amd-pmf", ACTION=="change", ENV{EVENT_ID}=="1", RUN+="/usr/bin/systemctl hibernate"
+        DRIVERS=="amd-pmf", ACTION=="change", ENV{EVENT_ID}=="2", RUN+="/bin/loginctl lock-sessions"
+
+EVENT_ID values:
+0= Put the system to S0i3/S2Idle
+1= Put the system to hibernate
+2= Lock the screen
diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst
index c7525942f12c..396091651955 100644
--- a/Documentation/admin-guide/sysctl/net.rst
+++ b/Documentation/admin-guide/sysctl/net.rst
@@ -345,7 +345,10 @@ optmem_max
 ----------
 
 Maximum ancillary buffer size allowed per socket. Ancillary data is a sequence
-of struct cmsghdr structures with appended data.
+of struct cmsghdr structures with appended data. TCP tx zerocopy also uses
+optmem_max as a limit for its internal structures.
+
+Default : 128 KB
 
 fb_tunnels_only_for_init_net
 ----------------------------
diff --git a/Documentation/arch/arm64/arm-acpi.rst b/Documentation/arch/arm64/arm-acpi.rst
index a46c34fa9604..e59e4505d0d9 100644
--- a/Documentation/arch/arm64/arm-acpi.rst
+++ b/Documentation/arch/arm64/arm-acpi.rst
@@ -130,7 +130,7 @@ When an Arm system boots, it can either have DT information, ACPI tables,
 or in some very unusual cases, both.  If no command line parameters are used,
 the kernel will try to use DT for device enumeration; if there is no DT
 present, the kernel will try to use ACPI tables, but only if they are present.
-In neither is available, the kernel will not boot.  If acpi=force is used
+If neither is available, the kernel will not boot.  If acpi=force is used
 on the command line, the kernel will attempt to use ACPI tables first, but
 fall back to DT if there are no ACPI tables present.  The basic idea is that
 the kernel will not fail to boot unless it absolutely has no other choice.
diff --git a/Documentation/arch/arm64/perf.rst b/Documentation/arch/arm64/perf.rst
index 1f87b57c2332..997fd716b82f 100644
--- a/Documentation/arch/arm64/perf.rst
+++ b/Documentation/arch/arm64/perf.rst
@@ -164,3 +164,75 @@ and should be used to mask the upper bits as needed.
    https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/perf/arch/arm64/tests/user-events.c
 .. _tools/lib/perf/tests/test-evsel.c:
    https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/lib/perf/tests/test-evsel.c
+
+Event Counting Threshold
+==========================================
+
+Overview
+--------
+
+FEAT_PMUv3_TH (Armv8.8) permits a PMU counter to increment only on
+events whose count meets a specified threshold condition. For example if
+threshold_compare is set to 2 ('Greater than or equal'), and the
+threshold is set to 2, then the PMU counter will now only increment by
+when an event would have previously incremented the PMU counter by 2 or
+more on a single processor cycle.
+
+To increment by 1 after passing the threshold condition instead of the
+number of events on that cycle, add the 'threshold_count' option to the
+commandline.
+
+How-to
+------
+
+These are the parameters for controlling the feature:
+
+.. list-table::
+   :header-rows: 1
+
+   * - Parameter
+     - Description
+   * - threshold
+     - Value to threshold the event by. A value of 0 means that
+       thresholding is disabled and the other parameters have no effect.
+   * - threshold_compare
+     - | Comparison function to use, with the following values supported:
+       |
+       | 0: Not-equal
+       | 1: Equals
+       | 2: Greater-than-or-equal
+       | 3: Less-than
+   * - threshold_count
+     - If this is set, count by 1 after passing the threshold condition
+       instead of the value of the event on this cycle.
+
+The threshold, threshold_compare and threshold_count values can be
+provided per event, for example:
+
+.. code-block:: sh
+
+  perf stat -e stall_slot/threshold=2,threshold_compare=2/ \
+            -e dtlb_walk/threshold=10,threshold_compare=3,threshold_count/
+
+In this example the stall_slot event will count by 2 or more on every
+cycle where 2 or more stalls happen. And dtlb_walk will count by 1 on
+every cycle where the number of dtlb walks were less than 10.
+
+The maximum supported threshold value can be read from the caps of each
+PMU, for example:
+
+.. code-block:: sh
+
+  cat /sys/bus/event_source/devices/armv8_pmuv3/caps/threshold_max
+
+  0x000000ff
+
+If a value higher than this is given, then opening the event will result
+in an error. The highest possible maximum is 4095, as the config field
+for threshold is limited to 12 bits, and the Perf tool will refuse to
+parse higher values.
+
+If the PMU doesn't support FEAT_PMUv3_TH, then threshold_max will read
+0, and attempting to set a threshold value will also result in an error.
+threshold_max will also read as 0 on aarch32 guests, even if the host
+is running on hardware with the feature.
diff --git a/Documentation/arch/loongarch/introduction.rst b/Documentation/arch/loongarch/introduction.rst
index 8c568cfc2107..5e6db78abeaf 100644
--- a/Documentation/arch/loongarch/introduction.rst
+++ b/Documentation/arch/loongarch/introduction.rst
@@ -375,9 +375,9 @@ Developer web site of Loongson and LoongArch (Software and Documentation):
 
 Documentation of LoongArch ISA:
 
-  https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.02-CN.pdf (in Chinese)
+  https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.10-CN.pdf (in Chinese)
 
-  https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.02-EN.pdf (in English)
+  https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.10-EN.pdf (in English)
 
 Documentation of LoongArch ELF psABI:
 
diff --git a/Documentation/arch/x86/boot.rst b/Documentation/arch/x86/boot.rst
index 04376280e58f..c513855a54bb 100644
--- a/Documentation/arch/x86/boot.rst
+++ b/Documentation/arch/x86/boot.rst
@@ -77,7 +77,7 @@ Protocol 2.14	BURNT BY INCORRECT COMMIT
 Protocol 2.15	(Kernel 5.5) Added the kernel_info and kernel_info.setup_type_max.
 =============	============================================================
 
-.. note::
+  .. note::
      The protocol version number should be changed only if the setup header
      is changed. There is no need to update the version number if boot_params
      or kernel_info are changed. Additionally, it is recommended to use
diff --git a/Documentation/arch/x86/cpuinfo.rst b/Documentation/arch/x86/cpuinfo.rst
index 08246e8ac835..8895784d4784 100644
--- a/Documentation/arch/x86/cpuinfo.rst
+++ b/Documentation/arch/x86/cpuinfo.rst
@@ -7,27 +7,74 @@ x86 Feature Flags
 Introduction
 ============
 
-On x86, flags appearing in /proc/cpuinfo have an X86_FEATURE definition
-in arch/x86/include/asm/cpufeatures.h. If the kernel cares about a feature
-or KVM want to expose the feature to a KVM guest, it can and should have
-an X86_FEATURE_* defined. These flags represent hardware features as
-well as software features.
-
-If users want to know if a feature is available on a given system, they
-try to find the flag in /proc/cpuinfo. If a given flag is present, it
-means that the kernel supports it and is currently making it available.
-If such flag represents a hardware feature, it also means that the
-hardware supports it.
-
-If the expected flag does not appear in /proc/cpuinfo, things are murkier.
-Users need to find out the reason why the flag is missing and find the way
-how to enable it, which is not always easy. There are several factors that
-can explain missing flags: the expected feature failed to enable, the feature
-is missing in hardware, platform firmware did not enable it, the feature is
-disabled at build or run time, an old kernel is in use, or the kernel does
-not support the feature and thus has not enabled it. In general, /proc/cpuinfo
-shows features which the kernel supports. For a full list of CPUID flags
-which the CPU supports, use tools/arch/x86/kcpuid.
+The list of feature flags in /proc/cpuinfo is not complete and
+represents an ill-fated attempt from long time ago to put feature flags
+in an easy to find place for userspace.
+
+However, the amount of feature flags is growing by the CPU generation,
+leading to unparseable and unwieldy /proc/cpuinfo.
+
+What is more, those feature flags do not even need to be in that file
+because userspace doesn't care about them - glibc et al already use
+CPUID to find out what the target machine supports and what not.
+
+And even if it doesn't show a particular feature flag - although the CPU
+still does have support for the respective hardware functionality and
+said CPU supports CPUID faulting - userspace can simply probe for the
+feature and figure out if it is supported or not, regardless of whether
+it is being advertised somewhere.
+
+Furthermore, those flag strings become an ABI the moment they appear
+there and maintaining them forever when nothing even uses them is a lot
+of wasted effort.
+
+So, the current use of /proc/cpuinfo is to show features which the
+kernel has *enabled* and *supports*. As in: the CPUID feature flag is
+there, there's an additional setup which the kernel has done while
+booting and the functionality is ready to use. A perfect example for
+that is "user_shstk" where additional code enablement is present in the
+kernel to support shadow stack for user programs.
+
+So, if users want to know if a feature is available on a given system,
+they try to find the flag in /proc/cpuinfo. If a given flag is present,
+it means that
+
+* the kernel knows about the feature enough to have an X86_FEATURE bit
+
+* the kernel supports it and is currently making it available either to
+  userspace or some other part of the kernel
+
+* if the flag represents a hardware feature the hardware supports it.
+
+The absence of a flag in /proc/cpuinfo by itself means almost nothing to
+an end user.
+
+On the one hand, a feature like "vaes" might be fully available to user
+applications on a kernel that has not defined X86_FEATURE_VAES and thus
+there is no "vaes" in /proc/cpuinfo.
+
+On the other hand, a new kernel running on non-VAES hardware would also
+have no "vaes" in /proc/cpuinfo.  There's no way for an application or
+user to tell the difference.
+
+The end result is that the flags field in /proc/cpuinfo is marginally
+useful for kernel debugging, but not really for anything else.
+Applications should instead use things like the glibc facilities for
+querying CPU support.  Users should rely on tools like
+tools/arch/x86/kcpuid and cpuid(1).
+
+Regarding implementation, flags appearing in /proc/cpuinfo have an
+X86_FEATURE definition in arch/x86/include/asm/cpufeatures.h. These flags
+represent hardware features as well as software features.
+
+If the kernel cares about a feature or KVM want to expose the feature to
+a KVM guest, it should only then expose it to the guest when the guest
+needs to parse /proc/cpuinfo. Which, as mentioned above, is highly
+unlikely. KVM can synthesize the CPUID bit and the KVM guest can simply
+query CPUID and figure out what the hypervisor supports and what not. As
+already stated, /proc/cpuinfo is not a dumping ground for useless
+feature flags.
+
 
 How are feature flags created?
 ==============================
diff --git a/Documentation/arch/x86/pti.rst b/Documentation/arch/x86/pti.rst
index 4b858a9bad8d..e08d35177bc0 100644
--- a/Documentation/arch/x86/pti.rst
+++ b/Documentation/arch/x86/pti.rst
@@ -81,11 +81,9 @@ this protection comes at a cost:
      and exit (it can be skipped when the kernel is interrupted,
      though.)  Moves to CR3 are on the order of a hundred
      cycles, and are required at every entry and exit.
-  b. A "trampoline" must be used for SYSCALL entry.  This
-     trampoline depends on a smaller set of resources than the
-     non-PTI SYSCALL entry code, so requires mapping fewer
-     things into the userspace page tables.  The downside is
-     that stacks must be switched at entry time.
+  b. Percpu TSS is mapped into the user page tables to allow SYSCALL64 path
+     to work under PTI. This doesn't have a direct runtime cost but it can
+     be argued it opens certain timing attack scenarios.
   c. Global pages are disabled for all kernel structures not
      mapped into both kernel and userspace page tables.  This
      feature of the MMU allows different processes to share TLB
@@ -167,7 +165,7 @@ that are worth noting here.
  * Failures of the selftests/x86 code.  Usually a bug in one of the
    more obscure corners of entry_64.S
  * Crashes in early boot, especially around CPU bringup.  Bugs
-   in the trampoline code or mappings cause these.
+   in the mappings cause these.
  * Crashes at the first interrupt.  Caused by bugs in entry_64.S,
    like screwing up a page table switch.  Also caused by
    incorrectly mapping the IRQ handler entry code.
diff --git a/Documentation/bpf/cpumasks.rst b/Documentation/bpf/cpumasks.rst
index a22b6ad105fb..b5d47a04da5d 100644
--- a/Documentation/bpf/cpumasks.rst
+++ b/Documentation/bpf/cpumasks.rst
@@ -352,7 +352,7 @@ can be used to query the contents of cpumasks.
 
 .. kernel-doc:: kernel/bpf/cpumask.c
    :identifiers: bpf_cpumask_first bpf_cpumask_first_zero bpf_cpumask_first_and
-                 bpf_cpumask_test_cpu
+                 bpf_cpumask_test_cpu bpf_cpumask_weight
 
 .. kernel-doc:: kernel/bpf/cpumask.c
    :identifiers: bpf_cpumask_equal bpf_cpumask_intersects bpf_cpumask_subset
diff --git a/Documentation/bpf/fs_kfuncs.rst b/Documentation/bpf/fs_kfuncs.rst
new file mode 100644
index 000000000000..8762c3233a3d
--- /dev/null
+++ b/Documentation/bpf/fs_kfuncs.rst
@@ -0,0 +1,21 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+.. _fs_kfuncs-header-label:
+
+=====================
+BPF filesystem kfuncs
+=====================
+
+BPF LSM programs need to access filesystem data from LSM hooks. The following
+BPF kfuncs can be used to get these data.
+
+ * ``bpf_get_file_xattr()``
+
+ * ``bpf_get_fsverity_digest()``
+
+To avoid recursions, these kfuncs follow the following rules:
+
+1. These kfuncs are only permitted from BPF LSM function.
+2. These kfuncs should not call into other LSM hooks, i.e. security_*(). For
+   example, ``bpf_get_file_xattr()`` does not use ``vfs_getxattr()``, because
+   the latter calls LSM hook ``security_inode_getxattr``.
diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst
index aeaeb35e6d4a..0bb5cb8157f1 100644
--- a/Documentation/bpf/index.rst
+++ b/Documentation/bpf/index.rst
@@ -21,6 +21,7 @@ that goes into great technical depth about the BPF Architecture.
    helpers
    kfuncs
    cpumasks
+   fs_kfuncs
    programs
    maps
    bpf_prog_run
diff --git a/Documentation/bpf/kfuncs.rst b/Documentation/bpf/kfuncs.rst
index 723408e399ab..7985c6615f3c 100644
--- a/Documentation/bpf/kfuncs.rst
+++ b/Documentation/bpf/kfuncs.rst
@@ -135,6 +135,30 @@ Either way, the returned buffer is either NULL, or of size buffer_szk. Without t
 annotation, the verifier will reject the program if a null pointer is passed in with
 a nonzero size.
 
+2.2.5 __str Annotation
+----------------------------
+This annotation is used to indicate that the argument is a constant string.
+
+An example is given below::
+
+        __bpf_kfunc bpf_get_file_xattr(..., const char *name__str, ...)
+        {
+        ...
+        }
+
+In this case, ``bpf_get_file_xattr()`` can be called as::
+
+        bpf_get_file_xattr(..., "xattr_name", ...);
+
+Or::
+
+        const char name[] = "xattr_name";  /* This need to be global */
+        int BPF_PROG(...)
+        {
+                ...
+                bpf_get_file_xattr(..., name, ...);
+                ...
+        }
 
 .. _BPF_kfunc_nodef:
 
diff --git a/Documentation/core-api/maple_tree.rst b/Documentation/core-api/maple_tree.rst
index 96f3d5f076b5..ccdd1615cf97 100644
--- a/Documentation/core-api/maple_tree.rst
+++ b/Documentation/core-api/maple_tree.rst
@@ -81,6 +81,9 @@ section.
 Sometimes it is necessary to ensure the next call to store to a maple tree does
 not allocate memory, please see :ref:`maple-tree-advanced-api` for this use case.
 
+You can use mtree_dup() to duplicate an entire maple tree. It is a more
+efficient way than inserting all elements one by one into a new tree.
+
 Finally, you can remove all entries from a maple tree by calling
 mtree_destroy().  If the maple tree entries are pointers, you may wish to free
 the entries first.
@@ -112,6 +115,7 @@ Takes ma_lock internally:
  * mtree_insert()
  * mtree_insert_range()
  * mtree_erase()
+ * mtree_dup()
  * mtree_destroy()
  * mt_set_in_rcu()
  * mt_clear_in_rcu()
diff --git a/Documentation/core-api/mm-api.rst b/Documentation/core-api/mm-api.rst
index 2d091c873d1e..af8151db88b2 100644
--- a/Documentation/core-api/mm-api.rst
+++ b/Documentation/core-api/mm-api.rst
@@ -37,7 +37,7 @@ The Slab Cache
 .. kernel-doc:: include/linux/slab.h
    :internal:
 
-.. kernel-doc:: mm/slab.c
+.. kernel-doc:: mm/slub.c
    :export:
 
 .. kernel-doc:: mm/slab_common.c
diff --git a/Documentation/crypto/device_drivers/index.rst b/Documentation/crypto/device_drivers/index.rst
new file mode 100644
index 000000000000..c81d311ac61b
--- /dev/null
+++ b/Documentation/crypto/device_drivers/index.rst
@@ -0,0 +1,9 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Hardware Device Driver Specific Documentation
+---------------------------------------------
+
+.. toctree::
+   :maxdepth: 1
+
+   octeontx2
diff --git a/Documentation/crypto/device_drivers/octeontx2.rst b/Documentation/crypto/device_drivers/octeontx2.rst
new file mode 100644
index 000000000000..7e469b173ac8
--- /dev/null
+++ b/Documentation/crypto/device_drivers/octeontx2.rst
@@ -0,0 +1,25 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=========================
+octeontx2 devlink support
+=========================
+
+This document describes the devlink features implemented by the ``octeontx2 CPT``
+device drivers.
+
+Parameters
+==========
+
+The ``octeontx2`` driver implements the following driver-specific parameters.
+
+.. list-table:: Driver-specific parameters implemented
+   :widths: 5 5 5 85
+
+   * - Name
+     - Type
+     - Mode
+     - Description
+   * - ``t106_mode``
+     - u8
+     - runtime
+     - Used to configure CN10KA B0/CN10KB CPT to work as CN10KA A0/A1.
diff --git a/Documentation/crypto/index.rst b/Documentation/crypto/index.rst
index 10647c5ae2ea..92eec78b5713 100644
--- a/Documentation/crypto/index.rst
+++ b/Documentation/crypto/index.rst
@@ -25,3 +25,4 @@ for cryptographic use cases, as well as programming examples.
    api
    api-samples
    descore-readme
+   device_drivers/index
diff --git a/Documentation/dev-tools/kunit/api/resource.rst b/Documentation/dev-tools/kunit/api/resource.rst
index 0a94f831259e..ec6002a6b0db 100644
--- a/Documentation/dev-tools/kunit/api/resource.rst
+++ b/Documentation/dev-tools/kunit/api/resource.rst
@@ -11,3 +11,12 @@ state on a per-test basis, register custom cleanup actions, and more.
 
 .. kernel-doc:: include/kunit/resource.h
    :internal:
+
+Managed Devices
+---------------
+
+Functions for using KUnit-managed struct device and struct device_driver.
+Include ``kunit/device.h`` to use these.
+
+.. kernel-doc:: include/kunit/device.h
+   :internal:
diff --git a/Documentation/dev-tools/kunit/run_manual.rst b/Documentation/dev-tools/kunit/run_manual.rst
index e7b46421f247..699d92885075 100644
--- a/Documentation/dev-tools/kunit/run_manual.rst
+++ b/Documentation/dev-tools/kunit/run_manual.rst
@@ -49,9 +49,52 @@ loaded.
 
 The results will appear in TAP format in ``dmesg``.
 
+debugfs
+=======
+
+KUnit can be accessed from userspace via the debugfs filesystem (See more
+information about debugfs at Documentation/filesystems/debugfs.rst).
+
+If ``CONFIG_KUNIT_DEBUGFS`` is enabled, the KUnit debugfs filesystem is
+mounted at /sys/kernel/debug/kunit. You can use this filesystem to perform
+the following actions.
+
+Retrieve Test Results
+=====================
+
+You can use debugfs to retrieve KUnit test results. The test results are
+accessible from the debugfs filesystem in the following read-only file:
+
+.. code-block :: bash
+
+	/sys/kernel/debug/kunit/<test_suite>/results
+
+The test results are printed in a KTAP document. Note this document is separate
+to the kernel log and thus, may have different test suite numbering.
+
+Run Tests After Kernel Has Booted
+=================================
+
+You can use the debugfs filesystem to trigger built-in tests to run after
+boot. To run the test suite, you can use the following command to write to
+the ``/sys/kernel/debug/kunit/<test_suite>/run`` file:
+
+.. code-block :: bash
+
+	echo "any string" > /sys/kernel/debugfs/kunit/<test_suite>/run
+
+As a result, the test suite runs and the results are printed to the kernel
+log.
+
+However, this feature is not available with KUnit suites that use init data,
+because init data may have been discarded after the kernel boots. KUnit
+suites that use init data should be defined using the
+kunit_test_init_section_suites() macro.
+
+Also, you cannot use this feature to run tests concurrently. Instead a test
+will wait to run until other tests have completed or failed.
+
 .. note ::
 
-	If ``CONFIG_KUNIT_DEBUGFS`` is enabled, KUnit test results will
-	be accessible from the ``debugfs`` filesystem (if mounted).
-	They will be in ``/sys/kernel/debug/kunit/<test_suite>/results``, in
-	TAP format.
+	For test authors, to use this feature, tests will need to correctly initialise
+	and/or clean up any data, so the test runs correctly a second time.
diff --git a/Documentation/dev-tools/kunit/running_tips.rst b/Documentation/dev-tools/kunit/running_tips.rst
index 766f9cdea0fa..024e9ad1d1e9 100644
--- a/Documentation/dev-tools/kunit/running_tips.rst
+++ b/Documentation/dev-tools/kunit/running_tips.rst
@@ -428,3 +428,10 @@ This attribute indicates the name of the module associated with the test.
 
 This attribute is automatically saved as a string and is printed for each suite.
 Tests can also be filtered using this attribute.
+
+``is_init``
+
+This attribute indicates whether the test uses init data or functions.
+
+This attribute is automatically saved as a boolean and tests can also be
+filtered using this attribute.
diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst
index c27e1646ecd9..a9efab50eed8 100644
--- a/Documentation/dev-tools/kunit/usage.rst
+++ b/Documentation/dev-tools/kunit/usage.rst
@@ -566,13 +566,9 @@ By reusing the same ``cases`` array from above, we can write the test as a
 		},
 	};
 
-	// Need a helper function to generate a name for each test case.
-	static void case_to_desc(const struct sha1_test_case *t, char *desc)
-	{
-		strcpy(desc, t->str);
-	}
-	// Creates `sha1_gen_params()` to iterate over `cases`.
-	KUNIT_ARRAY_PARAM(sha1, cases, case_to_desc);
+	// Creates `sha1_gen_params()` to iterate over `cases` while using
+	// the struct member `str` for the case description.
+	KUNIT_ARRAY_PARAM_DESC(sha1, cases, str);
 
 	// Looks no different from a normal test.
 	static void sha1_test(struct kunit *test)
@@ -588,7 +584,7 @@ By reusing the same ``cases`` array from above, we can write the test as a
 	}
 
 	// Instead of KUNIT_CASE, we use KUNIT_CASE_PARAM and pass in the
-	// function declared by KUNIT_ARRAY_PARAM.
+	// function declared by KUNIT_ARRAY_PARAM or KUNIT_ARRAY_PARAM_DESC.
 	static struct kunit_case sha1_test_cases[] = {
 		KUNIT_CASE_PARAM(sha1_test, sha1_gen_params),
 		{}
@@ -651,12 +647,16 @@ For example:
 	}
 
 Note that, for functions like device_unregister which only accept a single
-pointer-sized argument, it's possible to directly cast that function to
-a ``kunit_action_t`` rather than writing a wrapper function, for example:
+pointer-sized argument, it's possible to automatically generate a wrapper
+with the ``KUNIT_DEFINE_ACTION_WRAPPER()`` macro, for example:
 
 .. code-block:: C
 
-	kunit_add_action(test, (kunit_action_t *)&device_unregister, &dev);
+	KUNIT_DEFINE_ACTION_WRAPPER(device_unregister, device_unregister_wrapper, struct device *);
+	kunit_add_action(test, &device_unregister_wrapper, &dev);
+
+You should do this in preference to manually casting to the ``kunit_action_t`` type,
+as casting function pointers will break Control Flow Integrity (CFI).
 
 ``kunit_add_action`` can fail if, for example, the system is out of memory.
 You can use ``kunit_add_action_or_reset`` instead which runs the action
@@ -793,3 +793,53 @@ structures as shown below:
 KUnit is not enabled, or if no test is running in the current task, it will do
 nothing. This compiles down to either a no-op or a static key check, so will
 have a negligible performance impact when no test is running.
+
+Managing Fake Devices and Drivers
+---------------------------------
+
+When testing drivers or code which interacts with drivers, many functions will
+require a ``struct device`` or ``struct device_driver``. In many cases, setting
+up a real device is not required to test any given function, so a fake device
+can be used instead.
+
+KUnit provides helper functions to create and manage these fake devices, which
+are internally of type ``struct kunit_device``, and are attached to a special
+``kunit_bus``. These devices support managed device resources (devres), as
+described in Documentation/driver-api/driver-model/devres.rst
+
+To create a KUnit-managed ``struct device_driver``, use ``kunit_driver_create()``,
+which will create a driver with the given name, on the ``kunit_bus``. This driver
+will automatically be destroyed when the corresponding test finishes, but can also
+be manually destroyed with ``driver_unregister()``.
+
+To create a fake device, use the ``kunit_device_register()``, which will create
+and register a device, using a new KUnit-managed driver created with ``kunit_driver_create()``.
+To provide a specific, non-KUnit-managed driver, use ``kunit_device_register_with_driver()``
+instead. Like with managed drivers, KUnit-managed fake devices are automatically
+cleaned up when the test finishes, but can be manually cleaned up early with
+``kunit_device_unregister()``.
+
+The KUnit devices should be used in preference to ``root_device_register()``, and
+instead of ``platform_device_register()`` in cases where the device is not otherwise
+a platform device.
+
+For example:
+
+.. code-block:: c
+
+	#include <kunit/device.h>
+
+	static void test_my_device(struct kunit *test)
+	{
+		struct device *fake_device;
+		const char *dev_managed_string;
+
+		// Create a fake device.
+		fake_device = kunit_device_register(test, "my_device");
+		KUNIT_ASSERT_NOT_ERR_OR_NULL(test, fake_device)
+
+		// Pass it to functions which need a device.
+		dev_managed_string = devm_kstrdup(fake_device, "Hello, World!");
+
+		// Everything is cleaned up automatically when the test ends.
+	}
\ No newline at end of file
diff --git a/Documentation/devicetree/bindings/arm/cpus.yaml b/Documentation/devicetree/bindings/arm/cpus.yaml
index ffd526363fda..cc5a21b47e26 100644
--- a/Documentation/devicetree/bindings/arm/cpus.yaml
+++ b/Documentation/devicetree/bindings/arm/cpus.yaml
@@ -198,6 +198,7 @@ properties:
       - qcom,kryo660
       - qcom,kryo685
       - qcom,kryo780
+      - qcom,oryon
       - qcom,scorpion
 
   enable-method:
diff --git a/Documentation/devicetree/bindings/arm/fsl.yaml b/Documentation/devicetree/bindings/arm/fsl.yaml
index 32b195852a75..228dcc5c7d6f 100644
--- a/Documentation/devicetree/bindings/arm/fsl.yaml
+++ b/Documentation/devicetree/bindings/arm/fsl.yaml
@@ -967,6 +967,7 @@ properties:
               - menlo,mx8menlo                       # Verdin iMX8M Mini Module on i.MX8MM Menlo board
               - toradex,verdin-imx8mm-nonwifi-dahlia # Verdin iMX8M Mini Module on Dahlia
               - toradex,verdin-imx8mm-nonwifi-dev    # Verdin iMX8M Mini Module on Verdin Development Board
+              - toradex,verdin-imx8mm-nonwifi-mallow # Verdin iMX8M Mini Module on Mallow
               - toradex,verdin-imx8mm-nonwifi-yavia  # Verdin iMX8M Mini Module on Yavia
           - const: toradex,verdin-imx8mm-nonwifi     # Verdin iMX8M Mini Module without Wi-Fi / BT
           - const: toradex,verdin-imx8mm             # Verdin iMX8M Mini Module
@@ -977,6 +978,7 @@ properties:
           - enum:
               - toradex,verdin-imx8mm-wifi-dahlia # Verdin iMX8M Mini Wi-Fi / BT Module on Dahlia
               - toradex,verdin-imx8mm-wifi-dev    # Verdin iMX8M Mini Wi-Fi / BT M. on Verdin Development B.
+              - toradex,verdin-imx8mm-wifi-mallow # Verdin iMX8M Mini Wi-Fi / BT Module on Mallow
               - toradex,verdin-imx8mm-wifi-yavia  # Verdin iMX8M Mini Wi-Fi / BT Module on Yavia
           - const: toradex,verdin-imx8mm-wifi     # Verdin iMX8M Mini Wi-Fi / BT Module
           - const: toradex,verdin-imx8mm          # Verdin iMX8M Mini Module
@@ -1022,7 +1024,10 @@ properties:
 
       - description: Variscite VAR-SOM-MX8MN based boards
         items:
-          - const: variscite,var-som-mx8mn-symphony
+          - enum:
+              - dimonoff,gateway-evk # i.MX8MN Dimonoff Gateway EVK Board
+              - rve,rve-gateway # i.MX8MN RVE Gateway Board
+              - variscite,var-som-mx8mn-symphony
           - const: variscite,var-som-mx8mn
           - const: fsl,imx8mn
 
@@ -1048,6 +1053,9 @@ properties:
               - gateworks,imx8mp-gw73xx-2x # i.MX8MP Gateworks Board
               - gateworks,imx8mp-gw74xx   # i.MX8MP Gateworks Board
               - gateworks,imx8mp-gw7905-2x # i.MX8MP Gateworks Board
+              - skov,imx8mp-skov-revb-hdmi # SKOV i.MX8MP climate control without panel
+              - skov,imx8mp-skov-revb-lt6 # SKOV i.MX8MP climate control with 7� panel
+              - skov,imx8mp-skov-revb-mi1010ait-1cp1 # SKOV i.MX8MP climate control with 10.1" panel
               - toradex,verdin-imx8mp     # Verdin iMX8M Plus Modules
               - toradex,verdin-imx8mp-nonwifi  # Verdin iMX8M Plus Modules without Wi-Fi / BT
               - toradex,verdin-imx8mp-wifi  # Verdin iMX8M Plus Wi-Fi / BT Modules
@@ -1100,6 +1108,7 @@ properties:
           - enum:
               - toradex,verdin-imx8mp-nonwifi-dahlia # Verdin iMX8M Plus Module on Dahlia
               - toradex,verdin-imx8mp-nonwifi-dev    # Verdin iMX8M Plus Module on Verdin Development Board
+              - toradex,verdin-imx8mp-nonwifi-mallow # Verdin iMX8M Plus Module on Mallow
               - toradex,verdin-imx8mp-nonwifi-yavia  # Verdin iMX8M Plus Module on Yavia
           - const: toradex,verdin-imx8mp-nonwifi     # Verdin iMX8M Plus Module without Wi-Fi / BT
           - const: toradex,verdin-imx8mp             # Verdin iMX8M Plus Module
@@ -1110,6 +1119,7 @@ properties:
           - enum:
               - toradex,verdin-imx8mp-wifi-dahlia # Verdin iMX8M Plus Wi-Fi / BT Module on Dahlia
               - toradex,verdin-imx8mp-wifi-dev    # Verdin iMX8M Plus Wi-Fi / BT M. on Verdin Development B.
+              - toradex,verdin-imx8mp-wifi-mallow # Verdin iMX8M Plus Wi-Fi / BT Module on Mallow
               - toradex,verdin-imx8mp-wifi-yavia  # Verdin iMX8M Plus Wi-Fi / BT Module on Yavia
           - const: toradex,verdin-imx8mp-wifi     # Verdin iMX8M Plus Wi-Fi / BT Module
           - const: toradex,verdin-imx8mp          # Verdin iMX8M Plus Module
@@ -1476,6 +1486,16 @@ properties:
           - const: solidrun,lx2162a-som
           - const: fsl,lx2160a
 
+      - description:
+          TQ-Systems TQMLX2160A is a series of socketable SOM featuring
+          LX2160A system-on-chip variants. MBLX2160A mainboard can be used a
+          starterkit.
+        items:
+          - enum:
+              - tq,lx2160a-tqmlx2160a-mblx2160a
+          - const: tq,lx2160a-tqmlx2160a
+          - const: fsl,lx2160a
+
       - description: S32G2 based Boards
         items:
           - enum:
diff --git a/Documentation/devicetree/bindings/arm/google.yaml b/Documentation/devicetree/bindings/arm/google.yaml
new file mode 100644
index 000000000000..e20b5c9b16bc
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/google.yaml
@@ -0,0 +1,53 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/arm/google.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Google Tensor platforms
+
+maintainers:
+  - Peter Griffin <peter.griffin@linaro.org>
+
+description: |
+  ARM platforms using SoCs designed by Google branded "Tensor" used in Pixel
+  devices.
+
+  Currently upstream this is devices using "gs101" SoC which is found in Pixel
+  6, Pixel 6 Pro and Pixel 6a.
+
+  Google have a few different names for the SoC:
+  - Marketing name ("Tensor")
+  - Codename ("Whitechapel")
+  - SoC ID ("gs101")
+  - Die ID ("S5P9845")
+
+  Likewise there are a couple of names for the actual device
+  - Marketing name ("Pixel 6")
+  - Codename ("Oriole")
+
+  Devicetrees should use the lowercased SoC ID and lowercased board codename,
+  e.g. gs101 and gs101-oriole.
+
+properties:
+  $nodename:
+    const: '/'
+  compatible:
+    oneOf:
+      - description: Google Pixel 6 / Oriole
+        items:
+          - enum:
+              - google,gs101-oriole
+          - const: google,gs101
+
+  # Bootloader requires empty ect node to be present
+  ect:
+    type: object
+    additionalProperties: false
+
+required:
+  - ect
+
+additionalProperties: true
+
+...
diff --git a/Documentation/devicetree/bindings/arm/hisilicon/controller/sysctrl.yaml b/Documentation/devicetree/bindings/arm/hisilicon/controller/sysctrl.yaml
index 5a53d433b6f0..7a221e1c09df 100644
--- a/Documentation/devicetree/bindings/arm/hisilicon/controller/sysctrl.yaml
+++ b/Documentation/devicetree/bindings/arm/hisilicon/controller/sysctrl.yaml
@@ -82,6 +82,23 @@ properties:
 
   ranges: true
 
+patternProperties:
+  '^clock@':
+    type: object
+    additionalProperties: false
+
+    properties:
+      compatible:
+        enum:
+          - hisilicon,hi3620-clock
+          - hisilicon,hi3620-mmc-clock
+
+      reg:
+        maxItems: 1
+
+      '#clock-cells':
+        const: 1
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/arm/marvell/armada-7k-8k.yaml b/Documentation/devicetree/bindings/arm/marvell/armada-7k-8k.yaml
index 52d78521e412..16d2e132d3d1 100644
--- a/Documentation/devicetree/bindings/arm/marvell/armada-7k-8k.yaml
+++ b/Documentation/devicetree/bindings/arm/marvell/armada-7k-8k.yaml
@@ -60,4 +60,26 @@ properties:
           - const: marvell,armada-ap807-quad
           - const: marvell,armada-ap807
 
+      - description:
+          Alleycat5X (98DX35xx) Reference Design as COM Express Carrier plus
+          Armada CN9130 COM Express CPU module
+        items:
+          - const: marvell,cn9130-ac5x-carrier
+          - const: marvell,rd-ac5x-carrier
+          - const: marvell,cn9130-cpu-module
+          - const: marvell,cn9130
+          - const: marvell,armada-ap807-quad
+          - const: marvell,armada-ap807
+
+      - description:
+          Alleycat5X (98DX35xx) Reference Design as COM Express Carrier plus
+          Armada CN9131 COM Express CPU module
+        items:
+          - const: marvell,cn9131-ac5x-carrier
+          - const: marvell,rd-ac5x-carrier
+          - const: marvell,cn9131-cpu-module
+          - const: marvell,cn9131
+          - const: marvell,armada-ap807-quad
+          - const: marvell,armada-ap807
+
 additionalProperties: true
diff --git a/Documentation/devicetree/bindings/arm/mediatek.yaml b/Documentation/devicetree/bindings/arm/mediatek.yaml
index a5999b3afc35..6f2f64ae76fc 100644
--- a/Documentation/devicetree/bindings/arm/mediatek.yaml
+++ b/Documentation/devicetree/bindings/arm/mediatek.yaml
@@ -176,6 +176,10 @@ properties:
           - const: mediatek,mt8186
       - items:
           - enum:
+              - mediatek,mt8188-evb
+          - const: mediatek,mt8188
+      - items:
+          - enum:
               - mediatek,mt8192-evb
           - const: mediatek,mt8192
       - items:
@@ -235,6 +239,13 @@ properties:
         items:
           - const: google,kappa
           - const: mediatek,mt8183
+      - description: Google Katsu (ASUS Chromebook Detachable CZ1)
+        items:
+          - enum:
+              - google,katsu-sku32
+              - google,katsu-sku38
+          - const: google,katsu
+          - const: mediatek,mt8183
       - description: Google Kodama (Lenovo 10e Chromebook Tablet)
         items:
           - enum:
@@ -244,6 +255,20 @@ properties:
               - google,kodama-sku32
           - const: google,kodama
           - const: mediatek,mt8183
+      - description: Google Makomo (Lenovo 100e Chromebook 2nd Gen MTK 2)
+        items:
+          - enum:
+              - google,makomo-sku0
+              - google,makomo-sku1
+          - const: google,makomo
+          - const: mediatek,mt8183
+      - description: Google Pico (Acer Chromebook Spin 311)
+        items:
+          - enum:
+              - google,pico-sku1
+              - google,pico-sku2
+          - const: google,pico
+          - const: mediatek,mt8183
       - description: Google Willow (Acer Chromebook 311 C722/C722T)
         items:
           - enum:
diff --git a/Documentation/devicetree/bindings/arm/mediatek/mediatek,audsys.txt b/Documentation/devicetree/bindings/arm/mediatek/mediatek,audsys.txt
deleted file mode 100644
index 699776be1dd3..000000000000
--- a/Documentation/devicetree/bindings/arm/mediatek/mediatek,audsys.txt
+++ /dev/null
@@ -1,39 +0,0 @@
-MediaTek AUDSYS controller
-============================
-
-The MediaTek AUDSYS controller provides various clocks to the system.
-
-Required Properties:
-
-- compatible: Should be one of:
-	- "mediatek,mt2701-audsys", "syscon"
-	- "mediatek,mt6765-audsys", "syscon"
-	- "mediatek,mt6779-audio", "syscon"
-	- "mediatek,mt7622-audsys", "syscon"
-	- "mediatek,mt7623-audsys", "mediatek,mt2701-audsys", "syscon"
-	- "mediatek,mt8167-audiosys", "syscon"
-	- "mediatek,mt8183-audiosys", "syscon"
-	- "mediatek,mt8192-audsys", "syscon"
-	- "mediatek,mt8516-audsys", "syscon"
-- #clock-cells: Must be 1
-
-The AUDSYS controller uses the common clk binding from
-Documentation/devicetree/bindings/clock/clock-bindings.txt
-The available clocks are defined in dt-bindings/clock/mt*-clk.h.
-
-Required sub-nodes:
--------
-For common binding part and usage, refer to
-../sonud/mt2701-afe-pcm.txt.
-
-Example:
-
-	audsys: clock-controller@11220000 {
-		compatible = "mediatek,mt7622-audsys", "syscon";
-		reg = <0 0x11220000 0 0x2000>;
-		#clock-cells = <1>;
-
-		afe: audio-controller {
-			...
-		};
-	};
diff --git a/Documentation/devicetree/bindings/arm/mediatek/mediatek,audsys.yaml b/Documentation/devicetree/bindings/arm/mediatek/mediatek,audsys.yaml
new file mode 100644
index 000000000000..45d4a6620041
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/mediatek/mediatek,audsys.yaml
@@ -0,0 +1,153 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/arm/mediatek/mediatek,audsys.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: MediaTek AUDSYS controller
+
+maintainers:
+  - Eugen Hristev <eugen.hristev@collabora.com>
+
+description:
+  The MediaTek AUDSYS controller provides various clocks to the system.
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+          - enum:
+              - mediatek,mt2701-audsys
+              - mediatek,mt6765-audsys
+              - mediatek,mt6779-audsys
+              - mediatek,mt7622-audsys
+              - mediatek,mt8167-audsys
+              - mediatek,mt8173-audsys
+              - mediatek,mt8183-audsys
+              - mediatek,mt8186-audsys
+              - mediatek,mt8192-audsys
+              - mediatek,mt8516-audsys
+          - const: syscon
+      - items:
+          # Special case for mt7623 for backward compatibility
+          - const: mediatek,mt7623-audsys
+          - const: mediatek,mt2701-audsys
+          - const: syscon
+
+  reg:
+    maxItems: 1
+
+  '#clock-cells':
+    const: 1
+
+  audio-controller:
+    $ref: /schemas/sound/mediatek,mt2701-audio.yaml#
+    type: object
+
+required:
+  - compatible
+  - '#clock-cells'
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/power/mt2701-power.h>
+    #include <dt-bindings/clock/mt2701-clk.h>
+    soc {
+        #address-cells = <2>;
+        #size-cells = <2>;
+        audsys: clock-controller@11220000 {
+            compatible = "mediatek,mt7622-audsys", "syscon";
+            reg = <0 0x11220000 0 0x2000>;
+            #clock-cells = <1>;
+
+            afe: audio-controller {
+                compatible = "mediatek,mt2701-audio";
+                interrupts = <GIC_SPI 104 IRQ_TYPE_LEVEL_LOW>,
+                             <GIC_SPI 132 IRQ_TYPE_LEVEL_LOW>;
+                interrupt-names = "afe", "asys";
+                power-domains = <&scpsys MT2701_POWER_DOMAIN_IFR_MSC>;
+
+                clocks = <&infracfg CLK_INFRA_AUDIO>,
+                         <&topckgen CLK_TOP_AUD_MUX1_SEL>,
+                         <&topckgen CLK_TOP_AUD_MUX2_SEL>,
+                         <&topckgen CLK_TOP_AUD_48K_TIMING>,
+                         <&topckgen CLK_TOP_AUD_44K_TIMING>,
+                         <&topckgen CLK_TOP_AUD_K1_SRC_SEL>,
+                         <&topckgen CLK_TOP_AUD_K2_SRC_SEL>,
+                         <&topckgen CLK_TOP_AUD_K3_SRC_SEL>,
+                         <&topckgen CLK_TOP_AUD_K4_SRC_SEL>,
+                         <&topckgen CLK_TOP_AUD_K1_SRC_DIV>,
+                         <&topckgen CLK_TOP_AUD_K2_SRC_DIV>,
+                         <&topckgen CLK_TOP_AUD_K3_SRC_DIV>,
+                         <&topckgen CLK_TOP_AUD_K4_SRC_DIV>,
+                         <&topckgen CLK_TOP_AUD_I2S1_MCLK>,
+                         <&topckgen CLK_TOP_AUD_I2S2_MCLK>,
+                         <&topckgen CLK_TOP_AUD_I2S3_MCLK>,
+                         <&topckgen CLK_TOP_AUD_I2S4_MCLK>,
+                         <&audsys CLK_AUD_I2SO1>,
+                         <&audsys CLK_AUD_I2SO2>,
+                         <&audsys CLK_AUD_I2SO3>,
+                         <&audsys CLK_AUD_I2SO4>,
+                         <&audsys CLK_AUD_I2SIN1>,
+                         <&audsys CLK_AUD_I2SIN2>,
+                         <&audsys CLK_AUD_I2SIN3>,
+                         <&audsys CLK_AUD_I2SIN4>,
+                         <&audsys CLK_AUD_ASRCO1>,
+                         <&audsys CLK_AUD_ASRCO2>,
+                         <&audsys CLK_AUD_ASRCO3>,
+                         <&audsys CLK_AUD_ASRCO4>,
+                         <&audsys CLK_AUD_AFE>,
+                         <&audsys CLK_AUD_AFE_CONN>,
+                         <&audsys CLK_AUD_A1SYS>,
+                         <&audsys CLK_AUD_A2SYS>,
+                         <&audsys CLK_AUD_AFE_MRGIF>;
+
+                clock-names = "infra_sys_audio_clk",
+                              "top_audio_mux1_sel",
+                              "top_audio_mux2_sel",
+                              "top_audio_a1sys_hp",
+                              "top_audio_a2sys_hp",
+                              "i2s0_src_sel",
+                              "i2s1_src_sel",
+                              "i2s2_src_sel",
+                              "i2s3_src_sel",
+                              "i2s0_src_div",
+                              "i2s1_src_div",
+                              "i2s2_src_div",
+                              "i2s3_src_div",
+                              "i2s0_mclk_en",
+                              "i2s1_mclk_en",
+                              "i2s2_mclk_en",
+                              "i2s3_mclk_en",
+                              "i2so0_hop_ck",
+                              "i2so1_hop_ck",
+                              "i2so2_hop_ck",
+                              "i2so3_hop_ck",
+                              "i2si0_hop_ck",
+                              "i2si1_hop_ck",
+                              "i2si2_hop_ck",
+                              "i2si3_hop_ck",
+                              "asrc0_out_ck",
+                              "asrc1_out_ck",
+                              "asrc2_out_ck",
+                              "asrc3_out_ck",
+                              "audio_afe_pd",
+                              "audio_afe_conn_pd",
+                              "audio_a1sys_pd",
+                              "audio_a2sys_pd",
+                              "audio_mrgif_pd";
+
+                assigned-clocks = <&topckgen CLK_TOP_AUD_MUX1_SEL>,
+                                  <&topckgen CLK_TOP_AUD_MUX2_SEL>,
+                                  <&topckgen CLK_TOP_AUD_MUX1_DIV>,
+                                  <&topckgen CLK_TOP_AUD_MUX2_DIV>;
+                assigned-clock-parents = <&topckgen CLK_TOP_AUD1PLL_98M>,
+                                         <&topckgen CLK_TOP_AUD2PLL_90M>;
+                assigned-clock-rates = <0>, <0>, <49152000>, <45158400>;
+            };
+        };
+    };
diff --git a/Documentation/devicetree/bindings/arm/mediatek/mediatek,mmsys.yaml b/Documentation/devicetree/bindings/arm/mediatek/mediatek,mmsys.yaml
index 536f5a5ebd24..b3c6888c1457 100644
--- a/Documentation/devicetree/bindings/arm/mediatek/mediatek,mmsys.yaml
+++ b/Documentation/devicetree/bindings/arm/mediatek/mediatek,mmsys.yaml
@@ -32,6 +32,9 @@ properties:
               - mediatek,mt8183-mmsys
               - mediatek,mt8186-mmsys
               - mediatek,mt8188-vdosys0
+              - mediatek,mt8188-vdosys1
+              - mediatek,mt8188-vppsys0
+              - mediatek,mt8188-vppsys1
               - mediatek,mt8192-mmsys
               - mediatek,mt8195-vdosys1
               - mediatek,mt8195-vppsys0
diff --git a/Documentation/devicetree/bindings/arm/mediatek/mediatek,pericfg.yaml b/Documentation/devicetree/bindings/arm/mediatek/mediatek,pericfg.yaml
index 26158d0d72f3..33c94c491828 100644
--- a/Documentation/devicetree/bindings/arm/mediatek/mediatek,pericfg.yaml
+++ b/Documentation/devicetree/bindings/arm/mediatek/mediatek,pericfg.yaml
@@ -28,6 +28,7 @@ properties:
               - mediatek,mt8173-pericfg
               - mediatek,mt8183-pericfg
               - mediatek,mt8186-pericfg
+              - mediatek,mt8188-pericfg
               - mediatek,mt8195-pericfg
               - mediatek,mt8516-pericfg
           - const: syscon
diff --git a/Documentation/devicetree/bindings/arm/qcom-soc.yaml b/Documentation/devicetree/bindings/arm/qcom-soc.yaml
index 97621c92a1ab..d0751a572af3 100644
--- a/Documentation/devicetree/bindings/arm/qcom-soc.yaml
+++ b/Documentation/devicetree/bindings/arm/qcom-soc.yaml
@@ -23,7 +23,7 @@ description: |
 select:
   properties:
     compatible:
-      pattern: "^qcom,.*(apq|ipq|mdm|msm|qcm|qcs|sa|sc|sdm|sdx|sm)[0-9]+.*$"
+      pattern: "^qcom,.*(apq|ipq|mdm|msm|qcm|qcs|q[dr]u|sa|sc|sd[amx]|sm|x1e)[0-9]+.*$"
   required:
     - compatible
 
@@ -31,17 +31,17 @@ properties:
   compatible:
     oneOf:
       # Preferred naming style for compatibles of SoC components:
-      - pattern: "^qcom,(apq|ipq|mdm|msm|qcm|qcs|sa|sc|sdm|sdx|sm)[0-9]+(pro)?-.*$"
+      - pattern: "^qcom,(apq|ipq|mdm|msm|qcm|qcs|q[dr]u|sa|sc|sd[amx]|sm|x1e)[0-9]+(pro)?-.*$"
       - pattern: "^qcom,(sa|sc)8[0-9]+[a-z][a-z]?-.*$"
 
       # Legacy namings - variations of existing patterns/compatibles are OK,
       # but do not add completely new entries to these:
-      - pattern: "^qcom,[ak]pss-wdt-(apq|ipq|mdm|msm|qcm|qcs|sa|sc|sdm|sdx|sm)[0-9]+.*$"
-      - pattern: "^qcom,gcc-(apq|ipq|mdm|msm|qcm|qcs|sa|sc|sdm|sdx|sm)[0-9]+.*$"
-      - pattern: "^qcom,mmcc-(apq|ipq|mdm|msm|qcm|qcs|sa|sc|sdm|sdx|sm)[0-9]+.*$"
-      - pattern: "^qcom,pcie-(apq|ipq|mdm|msm|qcm|qcs|sa|sc|sdm|sdx|sm)[0-9]+.*$"
-      - pattern: "^qcom,rpm-(apq|ipq|mdm|msm|qcm|qcs|sa|sc|sdm|sdx|sm)[0-9]+.*$"
-      - pattern: "^qcom,scm-(apq|ipq|mdm|msm|qcm|qcs|sa|sc|sdm|sdx|sm)[0-9]+.*$"
+      - pattern: "^qcom,[ak]pss-wdt-(apq|ipq|mdm|msm|qcm|qcs|q[dr]u|sa|sc|sd[amx]|sm)[0-9]+.*$"
+      - pattern: "^qcom,gcc-(apq|ipq|mdm|msm|qcm|qcs|q[dr]u|sa|sc|sd[amx]|sm)[0-9]+.*$"
+      - pattern: "^qcom,mmcc-(apq|ipq|mdm|msm|qcm|qcs|q[dr]u|sa|sc|sd[amx]|sm)[0-9]+.*$"
+      - pattern: "^qcom,pcie-(apq|ipq|mdm|msm|qcm|qcs|q[dr]u|sa|sc|sd[amx]|sm|x1e)[0-9]+.*$"
+      - pattern: "^qcom,rpm-(apq|ipq|mdm|msm|qcm|qcs|q[dr]u|sa|sc|sd[amx]|sm)[0-9]+.*$"
+      - pattern: "^qcom,scm-(apq|ipq|mdm|msm|qcm|qcs|q[dr]u|sa|sc|sd[amx]|sm|x1e)[0-9]+.*$"
       - enum:
           - qcom,dsi-ctrl-6g-qcm2290
           - qcom,gpucc-sdm630
diff --git a/Documentation/devicetree/bindings/arm/qcom.yaml b/Documentation/devicetree/bindings/arm/qcom.yaml
index 7f80f48a0954..1a5fb889a444 100644
--- a/Documentation/devicetree/bindings/arm/qcom.yaml
+++ b/Documentation/devicetree/bindings/arm/qcom.yaml
@@ -87,29 +87,18 @@ description: |
         sm8350
         sm8450
         sm8550
+        sm8650
+        x1e80100
 
   The 'board' element must be one of the following strings:
 
         adp
-        ap-al02-c2
-        ap-al02-c6
-        ap-al02-c7
-        ap-al02-c8
-        ap-al02-c9
-        ap-mi01.2
-        ap-mi01.3
-        ap-mi01.6
-        ap-mi01.9
         cdp
-        cp01-c1
         dragonboard
-        hk01
-        hk10-c1
-        hk10-c2
         idp
         liquid
-        rdp432-c2
         mtp
+        qcp
         qrd
         rb2
         ride
@@ -138,7 +127,7 @@ description: |
   There are many devices in the list below that run the standard ChromeOS
   bootloader setup and use the open source depthcharge bootloader to boot the
   OS. These devices do not use the scheme described above. For details, see:
-  https://docs.kernel.org/arm/google/chromebook-boot-flow.html
+  https://docs.kernel.org/arch/arm/google/chromebook-boot-flow.html
 
 properties:
   $nodename:
@@ -186,11 +175,24 @@ properties:
 
       - items:
           - enum:
+              - microsoft,dempsey
+              - microsoft,makepeace
+              - microsoft,moneypenny
               - samsung,s3ve3g
           - const: qcom,msm8226
 
       - items:
           - enum:
+              - htc,memul
+              - microsoft,superman-lte
+              - microsoft,tesla
+              - motorola,peregrine
+          - const: qcom,msm8926
+          - const: qcom,msm8226
+
+      - items:
+          - enum:
+              - huawei,kiwi
               - longcheer,l9100
               - samsung,a7
               - sony,kanuti-tulip
@@ -397,6 +399,8 @@ properties:
       - items:
           - enum:
               - fairphone,fp5
+              - qcom,qcm6490-idp
+              - qcom,qcs6490-rb3gen2
           - const: qcom,qcm6490
 
       - description: Qualcomm Technologies, Inc. Distributed Unit 1000 platform
@@ -1009,6 +1013,7 @@ properties:
               - sony,pdx203-generic
               - sony,pdx206-generic
               - xiaomi,elish
+              - xiaomi,pipa
           - const: qcom,sm8250
 
       - items:
@@ -1034,6 +1039,18 @@ properties:
               - qcom,sm8550-qrd
           - const: qcom,sm8550
 
+      - items:
+          - enum:
+              - qcom,sm8650-mtp
+              - qcom,sm8650-qrd
+          - const: qcom,sm8650
+
+      - items:
+          - enum:
+              - qcom,x1e80100-crd
+              - qcom,x1e80100-qcp
+          - const: qcom,x1e80100
+
   # Board compatibles go above
 
   qcom,msm-id:
diff --git a/Documentation/devicetree/bindings/arm/rockchip.yaml b/Documentation/devicetree/bindings/arm/rockchip.yaml
index 5f7c6c4aad8f..5cf5cbef2cf5 100644
--- a/Documentation/devicetree/bindings/arm/rockchip.yaml
+++ b/Documentation/devicetree/bindings/arm/rockchip.yaml
@@ -30,9 +30,11 @@ properties:
           - const: amarula,vyasa-rk3288
           - const: rockchip,rk3288
 
-      - description: Anbernic RG351M
+      - description: Anbernic RK3326 Handheld Gaming Console
         items:
-          - const: anbernic,rg351m
+          - enum:
+              - anbernic,rg351m
+              - anbernic,rg351v
           - const: rockchip,rk3326
 
       - description: Anbernic RG353P
@@ -95,22 +97,30 @@ properties:
           - const: chipspark,rayeager-px2
           - const: rockchip,rk3066a
 
+      - description: Cool Pi Compute Module 5(CM5) EVB
+        items:
+          - enum:
+              - coolpi,pi-cm5-evb
+          - const: coolpi,pi-cm5
+          - const: rockchip,rk3588
+
+      - description: Cool Pi 4 Model B
+        items:
+          - const: coolpi,pi-4b
+          - const: rockchip,rk3588s
+
       - description: Edgeble Neural Compute Module 2(Neu2) SoM based boards
         items:
           - const: edgeble,neural-compute-module-2-io   # Edgeble Neural Compute Module 2 IO Board
           - const: edgeble,neural-compute-module-2      # Edgeble Neural Compute Module 2 SoM
           - const: rockchip,rv1126
 
-      - description: Edgeble Neural Compute Module 6(Neu6) Model A SoM based boards
-        items:
-          - const: edgeble,neural-compute-module-6a-io  # Edgeble Neural Compute Module 6A IO Board
-          - const: edgeble,neural-compute-module-6a     # Edgeble Neural Compute Module 6A SoM
-          - const: rockchip,rk3588
-
-      - description: Edgeble Neural Compute Module 6(Neu6) Model B SoM based boards
+      - description: Edgeble Neural Compute Module 6(Neu6) SoM based boards
         items:
-          - const: edgeble,neural-compute-module-6b-io  # Edgeble Neural Compute Module 6B IO Board
-          - const: edgeble,neural-compute-module-6b     # Edgeble Neural Compute Module 6B SoM
+          - const: edgeble,neural-compute-module-6a-io  # Edgeble NCM6A-IO Board
+          - enum:
+              - edgeble,neural-compute-module-6a        # Edgeble Neural Compute Module 6A SoM
+              - edgeble,neural-compute-module-6b        # Edgeble Neural Compute Module 6B SoM
           - const: rockchip,rk3588
 
       - description: Elgin RV1108 R1
@@ -237,6 +247,11 @@ properties:
           - const: geekbuying,geekbox
           - const: rockchip,rk3368
 
+      - description: Geniatech XPI-3128
+        items:
+          - const: geniatech,xpi-3128
+          - const: rockchip,rk3128
+
       - description: Google Bob (Asus Chromebook Flip C101PA)
         items:
           - const: google,bob-rev13
@@ -674,9 +689,12 @@ properties:
           - const: pine64,soquartz
           - const: rockchip,rk3566
 
-      - description: Powkiddy RGB30
+      - description: Powkiddy RK3566 Handheld Gaming Console
         items:
-          - const: powkiddy,rgb30
+          - enum:
+              - powkiddy,rgb30
+              - powkiddy,rk2023
+              - powkiddy,x55
           - const: rockchip,rk3566
 
       - description: Radxa Compute Module 3(CM3)
@@ -875,6 +893,11 @@ properties:
           - const: tsd,rk3399-puma-haikou
           - const: rockchip,rk3399
 
+      - description: Theobroma Systems RK3588-SBC Jaguar
+        items:
+          - const: tsd,rk3588-jaguar
+          - const: rockchip,rk3588
+
       - description: Tronsmart Orion R68 Meta
         items:
           - const: tronsmart,orion-r68-meta
@@ -922,6 +945,13 @@ properties:
           - const: rockchip,rk3568-bpi-r2pro
           - const: rockchip,rk3568
 
+      - description: Sonoff iHost Smart Home Hub
+        items:
+          - const: itead,sonoff-ihost
+          - enum:
+              - rockchip,rv1126
+              - rockchip,rv1109
+
 additionalProperties: true
 
 ...
diff --git a/Documentation/devicetree/bindings/arm/samsung/samsung-boards.yaml b/Documentation/devicetree/bindings/arm/samsung/samsung-boards.yaml
index e3ffd8159ab6..01dcbd8aa703 100644
--- a/Documentation/devicetree/bindings/arm/samsung/samsung-boards.yaml
+++ b/Documentation/devicetree/bindings/arm/samsung/samsung-boards.yaml
@@ -230,6 +230,12 @@ properties:
               - samsung,exynosautov9-sadk   # Samsung Exynos Auto v9 SADK
           - const: samsung,exynosautov9
 
+      - description: Exynos Auto v920 based boards
+        items:
+          - enum:
+              - samsung,exynosautov920-sadk   # Samsung Exynos Auto v920 SADK
+          - const: samsung,exynosautov920
+
 required:
   - compatible
 
diff --git a/Documentation/devicetree/bindings/arm/sprd/sprd.yaml b/Documentation/devicetree/bindings/arm/sprd/sprd.yaml
index eaa67b8e0d6c..40fc3c8b9dce 100644
--- a/Documentation/devicetree/bindings/arm/sprd/sprd.yaml
+++ b/Documentation/devicetree/bindings/arm/sprd/sprd.yaml
@@ -35,6 +35,11 @@ properties:
               - sprd,ums512-1h10
           - const: sprd,ums512
 
+      - items:
+          - enum:
+              - sprd,ums9620-2h10
+          - const: sprd,ums9620
+
 additionalProperties: true
 
 ...
diff --git a/Documentation/devicetree/bindings/arm/stm32/stm32.yaml b/Documentation/devicetree/bindings/arm/stm32/stm32.yaml
index df087c81c69e..bc2f43330ae4 100644
--- a/Documentation/devicetree/bindings/arm/stm32/stm32.yaml
+++ b/Documentation/devicetree/bindings/arm/stm32/stm32.yaml
@@ -82,29 +82,19 @@ properties:
               - shiratech,stm32mp157a-iot-box # IoT Box
               - shiratech,stm32mp157a-stinger96 # Stinger96
               - st,stm32mp157c-ed1
+              - st,stm32mp157c-ed1-scmi
               - st,stm32mp157a-dk1
+              - st,stm32mp157a-dk1-scmi
               - st,stm32mp157c-dk2
+              - st,stm32mp157c-dk2-scmi
           - const: st,stm32mp157
 
       - items:
-          - const: st,stm32mp157a-dk1-scmi
-          - const: st,stm32mp157a-dk1
-          - const: st,stm32mp157
-      - items:
-          - const: st,stm32mp157c-dk2-scmi
-          - const: st,stm32mp157c-dk2
-          - const: st,stm32mp157
-      - items:
-          - const: st,stm32mp157c-ed1-scmi
-          - const: st,stm32mp157c-ed1
-          - const: st,stm32mp157
-      - items:
           - const: st,stm32mp157c-ev1
           - const: st,stm32mp157c-ed1
           - const: st,stm32mp157
       - items:
           - const: st,stm32mp157c-ev1-scmi
-          - const: st,stm32mp157c-ev1
           - const: st,stm32mp157c-ed1
           - const: st,stm32mp157
 
diff --git a/Documentation/devicetree/bindings/arm/sunxi.yaml b/Documentation/devicetree/bindings/arm/sunxi.yaml
index 11c5ce941dd7..a9d8e85565b8 100644
--- a/Documentation/devicetree/bindings/arm/sunxi.yaml
+++ b/Documentation/devicetree/bindings/arm/sunxi.yaml
@@ -868,6 +868,11 @@ properties:
           - const: topwise,a721
           - const: allwinner,sun4i-a10
 
+      - description: Transpeed 8K618-T
+        items:
+          - const: transpeed,8k618-t
+          - const: allwinner,sun50i-h618
+
       - description: Utoo P66
         items:
           - const: utoo,p66
@@ -1013,6 +1018,11 @@ properties:
           - const: xunlong,orangepi-zero2
           - const: allwinner,sun50i-h616
 
+      - description: Xunlong OrangePi Zero 2W
+        items:
+          - const: xunlong,orangepi-zero2w
+          - const: allwinner,sun50i-h618
+
       - description: Xunlong OrangePi Zero 3
         items:
           - const: xunlong,orangepi-zero3
diff --git a/Documentation/devicetree/bindings/arm/ti/k3.yaml b/Documentation/devicetree/bindings/arm/ti/k3.yaml
index 03d2a0d79fb0..c6506bccfe88 100644
--- a/Documentation/devicetree/bindings/arm/ti/k3.yaml
+++ b/Documentation/devicetree/bindings/arm/ti/k3.yaml
@@ -50,6 +50,7 @@ properties:
           - enum:
               - toradex,verdin-am62-nonwifi-dahlia # Verdin AM62 Module on Dahlia
               - toradex,verdin-am62-nonwifi-dev    # Verdin AM62 Module on Verdin Development Board
+              - toradex,verdin-am62-nonwifi-mallow # Verdin AM62 Module on Mallow
               - toradex,verdin-am62-nonwifi-yavia  # Verdin AM62 Module on Yavia
           - const: toradex,verdin-am62-nonwifi     # Verdin AM62 Module without Wi-Fi / BT
           - const: toradex,verdin-am62             # Verdin AM62 Module
@@ -60,6 +61,7 @@ properties:
           - enum:
               - toradex,verdin-am62-wifi-dahlia # Verdin AM62 Wi-Fi / BT Module on Dahlia
               - toradex,verdin-am62-wifi-dev    # Verdin AM62 Wi-Fi / BT M. on Verdin Development B.
+              - toradex,verdin-am62-wifi-mallow # Verdin AM62 Wi-Fi / BT Module on Mallow
               - toradex,verdin-am62-wifi-yavia  # Verdin AM62 Wi-Fi / BT Module on Yavia
           - const: toradex,verdin-am62-wifi     # Verdin AM62 Wi-Fi / BT Module
           - const: toradex,verdin-am62          # Verdin AM62 Module
diff --git a/Documentation/devicetree/bindings/arm/ti/omap.yaml b/Documentation/devicetree/bindings/arm/ti/omap.yaml
index b18fc046390a..93e04a109a12 100644
--- a/Documentation/devicetree/bindings/arm/ti/omap.yaml
+++ b/Documentation/devicetree/bindings/arm/ti/omap.yaml
@@ -134,6 +134,8 @@ properties:
               - amazon,omap4-kc1        # Amazon Kindle Fire (first generation)
               - motorola,droid4         # Motorola Droid 4 XT894
               - motorola,droid-bionic   # Motorola Droid Bionic XT875
+              - motorola,xyboard-mz609
+              - motorola,xyboard-mz617
               - ti,omap4-panda
               - ti,omap4-sdp
           - const: ti,omap4430
diff --git a/Documentation/devicetree/bindings/cache/qcom,llcc.yaml b/Documentation/devicetree/bindings/cache/qcom,llcc.yaml
index 580f9a97ddf7..b9a9f2cf32a1 100644
--- a/Documentation/devicetree/bindings/cache/qcom,llcc.yaml
+++ b/Documentation/devicetree/bindings/cache/qcom,llcc.yaml
@@ -33,6 +33,8 @@ properties:
       - qcom,sm8350-llcc
       - qcom,sm8450-llcc
       - qcom,sm8550-llcc
+      - qcom,sm8650-llcc
+      - qcom,x1e80100-llcc
 
   reg:
     minItems: 2
@@ -104,6 +106,7 @@ allOf:
               - qcom,qdu1000-llcc
               - qcom,sc8180x-llcc
               - qcom,sc8280xp-llcc
+              - qcom,x1e80100-llcc
     then:
       properties:
         reg:
diff --git a/Documentation/devicetree/bindings/cache/sifive,ccache0.yaml b/Documentation/devicetree/bindings/cache/sifive,ccache0.yaml
index 8a6a78e1a7ab..7e8cebe21584 100644
--- a/Documentation/devicetree/bindings/cache/sifive,ccache0.yaml
+++ b/Documentation/devicetree/bindings/cache/sifive,ccache0.yaml
@@ -38,7 +38,9 @@ properties:
               - sifive,fu740-c000-ccache
           - const: cache
       - items:
-          - const: starfive,jh7110-ccache
+          - enum:
+              - starfive,jh7100-ccache
+              - starfive,jh7110-ccache
           - const: sifive,ccache0
           - const: cache
       - items:
@@ -88,6 +90,7 @@ allOf:
           contains:
             enum:
               - sifive,fu740-c000-ccache
+              - starfive,jh7100-ccache
               - starfive,jh7110-ccache
               - microchip,mpfs-ccache
 
@@ -111,6 +114,7 @@ allOf:
           contains:
             enum:
               - sifive,fu740-c000-ccache
+              - starfive,jh7100-ccache
               - starfive,jh7110-ccache
 
     then:
diff --git a/Documentation/devicetree/bindings/clock/google,gs101-clock.yaml b/Documentation/devicetree/bindings/clock/google,gs101-clock.yaml
new file mode 100644
index 000000000000..3eebc03a309b
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/google,gs101-clock.yaml
@@ -0,0 +1,106 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/google,gs101-clock.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Google GS101 SoC clock controller
+
+maintainers:
+  - Peter Griffin <peter.griffin@linaro.org>
+
+description: |
+  Google GS101 clock controller is comprised of several CMU units, generating
+  clocks for different domains. Those CMU units are modeled as separate device
+  tree nodes, and might depend on each other. The root clock in that clock tree
+  is OSCCLK (24.576 MHz). That external clock must be defined as a fixed-rate
+  clock in dts.
+
+  CMU_TOP is a top-level CMU, where all base clocks are prepared using PLLs and
+  dividers; all other leaf clocks (other CMUs) are usually derived from CMU_TOP.
+
+  Each clock is assigned an identifier and client nodes can use this identifier
+  to specify the clock which they consume. All clocks available for usage
+  in clock consumer nodes are defined as preprocessor macros in
+  'dt-bindings/clock/gs101.h' header.
+
+properties:
+  compatible:
+    enum:
+      - google,gs101-cmu-top
+      - google,gs101-cmu-apm
+      - google,gs101-cmu-misc
+
+  clocks:
+    minItems: 1
+    maxItems: 2
+
+  clock-names:
+    minItems: 1
+    maxItems: 2
+
+  "#clock-cells":
+    const: 1
+
+  reg:
+    maxItems: 1
+
+required:
+  - compatible
+  - "#clock-cells"
+  - clocks
+  - clock-names
+  - reg
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - google,gs101-cmu-top
+              - google,gs101-cmu-apm
+    then:
+      properties:
+        clocks:
+          items:
+            - description: External reference clock (24.576 MHz)
+
+        clock-names:
+          items:
+            - const: oscclk
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: google,gs101-cmu-misc
+
+    then:
+      properties:
+        clocks:
+          items:
+            - description: Misc bus clock (from CMU_TOP)
+            - description: Misc sss clock (from CMU_TOP)
+
+        clock-names:
+          items:
+            - const: dout_cmu_misc_bus
+            - const: dout_cmu_misc_sss
+
+additionalProperties: false
+
+examples:
+  # Clock controller node for CMU_TOP
+  - |
+    #include <dt-bindings/clock/google,gs101.h>
+
+    cmu_top: clock-controller@1e080000 {
+        compatible = "google,gs101-cmu-top";
+        reg = <0x1e080000 0x8000>;
+        #clock-cells = <1>;
+        clocks = <&ext_24_5m>;
+        clock-names = "oscclk";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/hi3620-clock.txt b/Documentation/devicetree/bindings/clock/hi3620-clock.txt
deleted file mode 100644
index dad6269f52c5..000000000000
--- a/Documentation/devicetree/bindings/clock/hi3620-clock.txt
+++ /dev/null
@@ -1,20 +0,0 @@
-* Hisilicon Hi3620 Clock Controller
-
-The Hi3620 clock controller generates and supplies clock to various
-controllers within the Hi3620 SoC.
-
-Required Properties:
-
-- compatible: should be one of the following.
-  - "hisilicon,hi3620-clock" - controller compatible with Hi3620 SoC.
-  - "hisilicon,hi3620-mmc-clock" - controller specific for Hi3620 mmc.
-
-- reg: physical base address of the controller and length of memory mapped
-  region.
-
-- #clock-cells: should be 1.
-
-Each clock is assigned an identifier and client nodes use this identifier
-to specify the clock which they consume.
-
-All these identifier could be found in <dt-bindings/clock/hi3620-clock.h>.
diff --git a/Documentation/devicetree/bindings/clock/mediatek,mt8188-clock.yaml b/Documentation/devicetree/bindings/clock/mediatek,mt8188-clock.yaml
index d7214d97b2ba..860570320545 100644
--- a/Documentation/devicetree/bindings/clock/mediatek,mt8188-clock.yaml
+++ b/Documentation/devicetree/bindings/clock/mediatek,mt8188-clock.yaml
@@ -43,8 +43,6 @@ properties:
       - mediatek,mt8188-vdecsys
       - mediatek,mt8188-vdecsys-soc
       - mediatek,mt8188-vencsys
-      - mediatek,mt8188-vppsys0
-      - mediatek,mt8188-vppsys1
       - mediatek,mt8188-wpesys
       - mediatek,mt8188-wpesys-vpp0
 
diff --git a/Documentation/devicetree/bindings/clock/qcom,camcc-sm8250.yaml b/Documentation/devicetree/bindings/clock/qcom,camcc-sm8250.yaml
index 426335a2841c..3fd3dc1069fb 100644
--- a/Documentation/devicetree/bindings/clock/qcom,camcc-sm8250.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,camcc-sm8250.yaml
@@ -15,6 +15,9 @@ description: |
 
   See also:: include/dt-bindings/clock/qcom,camcc-sm8250.h
 
+allOf:
+  - $ref: qcom,gcc.yaml#
+
 properties:
   compatible:
     const: qcom,sm8250-camcc
@@ -33,15 +36,6 @@ properties:
       - const: bi_tcxo_ao
       - const: sleep_clk
 
-  '#clock-cells':
-    const: 1
-
-  '#reset-cells':
-    const: 1
-
-  '#power-domain-cells':
-    const: 1
-
   power-domains:
     items:
       - description: MMCX power domain
@@ -56,14 +50,10 @@ properties:
 
 required:
   - compatible
-  - reg
   - clocks
   - clock-names
-  - '#clock-cells'
-  - '#reset-cells'
-  - '#power-domain-cells'
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/clock/qcom,gcc-ipq8074.yaml b/Documentation/devicetree/bindings/clock/qcom,gcc-ipq8074.yaml
index 52e7831a8d6d..2d44ddc45aab 100644
--- a/Documentation/devicetree/bindings/clock/qcom,gcc-ipq8074.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,gcc-ipq8074.yaml
@@ -27,11 +27,15 @@ properties:
     items:
       - description: board XO clock
       - description: sleep clock
+      - description: Gen3 QMP PCIe PHY PIPE clock
+      - description: Gen2 QMP PCIe PHY PIPE clock
 
   clock-names:
     items:
       - const: xo
       - const: sleep_clk
+      - const: pcie0_pipe
+      - const: pcie1_pipe
 
 required:
   - compatible
diff --git a/Documentation/devicetree/bindings/clock/qcom,rpmhcc.yaml b/Documentation/devicetree/bindings/clock/qcom,rpmhcc.yaml
index 4eb5e59f6772..ca857942ed6c 100644
--- a/Documentation/devicetree/bindings/clock/qcom,rpmhcc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,rpmhcc.yaml
@@ -35,6 +35,8 @@ properties:
       - qcom,sm8350-rpmh-clk
       - qcom,sm8450-rpmh-clk
       - qcom,sm8550-rpmh-clk
+      - qcom,sm8650-rpmh-clk
+      - qcom,x1e80100-rpmh-clk
 
   clocks:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/clock/qcom,sc7180-camcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sc7180-camcc.yaml
index 2dfc2a4f1918..c7fe6400ea13 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sc7180-camcc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sc7180-camcc.yaml
@@ -15,6 +15,9 @@ description: |
 
   See also:: include/dt-bindings/clock/qcom,camcc-sc7180.h
 
+allOf:
+  - $ref: qcom,gcc.yaml#
+
 properties:
   compatible:
     const: qcom,sc7180-camcc
@@ -31,28 +34,15 @@ properties:
       - const: iface
       - const: xo
 
-  '#clock-cells':
-    const: 1
-
-  '#reset-cells':
-    const: 1
-
-  '#power-domain-cells':
-    const: 1
-
   reg:
     maxItems: 1
 
 required:
   - compatible
-  - reg
   - clocks
   - clock-names
-  - '#clock-cells'
-  - '#reset-cells'
-  - '#power-domain-cells'
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/clock/qcom,sc7280-camcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sc7280-camcc.yaml
index 01feef1cab0a..dcef8de3a905 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sc7280-camcc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sc7280-camcc.yaml
@@ -15,6 +15,9 @@ description: |
 
   See also:: include/dt-bindings/clock/qcom,camcc-sc7280.h
 
+allOf:
+  - $ref: qcom,gcc.yaml#
+
 properties:
   compatible:
     const: qcom,sc7280-camcc
@@ -31,28 +34,15 @@ properties:
       - const: bi_tcxo_ao
       - const: sleep_clk
 
-  '#clock-cells':
-    const: 1
-
-  '#reset-cells':
-    const: 1
-
-  '#power-domain-cells':
-    const: 1
-
   reg:
     maxItems: 1
 
 required:
   - compatible
-  - reg
   - clocks
   - clock-names
-  - '#clock-cells'
-  - '#reset-cells'
-  - '#power-domain-cells'
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/clock/qcom,sdm845-camcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sdm845-camcc.yaml
index 91d1f7918037..810b852ae371 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sdm845-camcc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sdm845-camcc.yaml
@@ -15,6 +15,9 @@ description: |
 
   See also:: include/dt-bindings/clock/qcom,camcc-sm845.h
 
+allOf:
+  - $ref: qcom,gcc.yaml#
+
 properties:
   compatible:
     const: qcom,sdm845-camcc
@@ -27,28 +30,15 @@ properties:
     items:
       - const: bi_tcxo
 
-  '#clock-cells':
-    const: 1
-
-  '#reset-cells':
-    const: 1
-
-  '#power-domain-cells':
-    const: 1
-
   reg:
     maxItems: 1
 
 required:
   - compatible
-  - reg
   - clocks
   - clock-names
-  - '#clock-cells'
-  - '#reset-cells'
-  - '#power-domain-cells'
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8450-camcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8450-camcc.yaml
index dc3c18e4ead7..48986460f994 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sm8450-camcc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sm8450-camcc.yaml
@@ -16,10 +16,15 @@ description: |
   See also::
     include/dt-bindings/clock/qcom,sm8450-camcc.h
     include/dt-bindings/clock/qcom,sm8550-camcc.h
+    include/dt-bindings/clock/qcom,sc8280xp-camcc.h
+
+allOf:
+  - $ref: qcom,gcc.yaml#
 
 properties:
   compatible:
     enum:
+      - qcom,sc8280xp-camcc
       - qcom,sm8450-camcc
       - qcom,sm8550-camcc
 
@@ -40,29 +45,16 @@ properties:
     description:
       A phandle to an OPP node describing required MMCX performance point.
 
-  '#clock-cells':
-    const: 1
-
-  '#reset-cells':
-    const: 1
-
-  '#power-domain-cells':
-    const: 1
-
   reg:
     maxItems: 1
 
 required:
   - compatible
-  - reg
   - clocks
   - power-domains
   - required-opps
-  - '#clock-cells'
-  - '#reset-cells'
-  - '#power-domain-cells'
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml
index 2320be920a5f..1a384e8532a5 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml
@@ -17,12 +17,14 @@ description: |
     include/dt-bindings/clock/qcom,sm8450-gpucc.h
     include/dt-bindings/clock/qcom,sm8550-gpucc.h
     include/dt-bindings/reset/qcom,sm8450-gpucc.h
+    include/dt-bindings/reset/qcom,sm8650-gpucc.h
 
 properties:
   compatible:
     enum:
       - qcom,sm8450-gpucc
       - qcom,sm8550-gpucc
+      - qcom,sm8650-gpucc
 
   clocks:
     items:
diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8550-tcsr.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8550-tcsr.yaml
index 1bf1a41fd89c..af16b05eac96 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sm8550-tcsr.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sm8550-tcsr.yaml
@@ -13,12 +13,16 @@ description: |
   Qualcomm TCSR clock control module provides the clocks, resets and
   power domains on SM8550
 
-  See also:: include/dt-bindings/clock/qcom,sm8550-tcsr.h
+  See also:
+  - include/dt-bindings/clock/qcom,sm8550-tcsr.h
+  - include/dt-bindings/clock/qcom,sm8650-tcsr.h
 
 properties:
   compatible:
     items:
-      - const: qcom,sm8550-tcsr
+      - enum:
+          - qcom,sm8550-tcsr
+          - qcom,sm8650-tcsr
       - const: syscon
 
   clocks:
diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8650-dispcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8650-dispcc.yaml
new file mode 100644
index 000000000000..5e0c45c380f5
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/qcom,sm8650-dispcc.yaml
@@ -0,0 +1,106 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/qcom,sm8650-dispcc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Display Clock & Reset Controller for SM8650
+
+maintainers:
+  - Bjorn Andersson <andersson@kernel.org>
+  - Neil Armstrong <neil.armstrong@linaro.org>
+
+description: |
+  Qualcomm display clock control module provides the clocks, resets and power
+  domains on SM8650.
+
+  See also:: include/dt-bindings/clock/qcom,sm8650-dispcc.h
+
+properties:
+  compatible:
+    enum:
+      - qcom,sm8650-dispcc
+
+  clocks:
+    items:
+      - description: Board XO source
+      - description: Board Always On XO source
+      - description: Display's AHB clock
+      - description: sleep clock
+      - description: Byte clock from DSI PHY0
+      - description: Pixel clock from DSI PHY0
+      - description: Byte clock from DSI PHY1
+      - description: Pixel clock from DSI PHY1
+      - description: Link clock from DP PHY0
+      - description: VCO DIV clock from DP PHY0
+      - description: Link clock from DP PHY1
+      - description: VCO DIV clock from DP PHY1
+      - description: Link clock from DP PHY2
+      - description: VCO DIV clock from DP PHY2
+      - description: Link clock from DP PHY3
+      - description: VCO DIV clock from DP PHY3
+
+  '#clock-cells':
+    const: 1
+
+  '#reset-cells':
+    const: 1
+
+  '#power-domain-cells':
+    const: 1
+
+  reg:
+    maxItems: 1
+
+  power-domains:
+    description:
+      A phandle and PM domain specifier for the MMCX power domain.
+    maxItems: 1
+
+  required-opps:
+    description:
+      A phandle to an OPP node describing required MMCX performance point.
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - '#clock-cells'
+  - '#reset-cells'
+  - '#power-domain-cells'
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/qcom,sm8650-gcc.h>
+    #include <dt-bindings/clock/qcom,rpmh.h>
+    #include <dt-bindings/power/qcom-rpmpd.h>
+    #include <dt-bindings/power/qcom,rpmhpd.h>
+    clock-controller@af00000 {
+      compatible = "qcom,sm8650-dispcc";
+      reg = <0x0af00000 0x10000>;
+      clocks = <&rpmhcc RPMH_CXO_CLK>,
+               <&rpmhcc RPMH_CXO_CLK_A>,
+               <&gcc GCC_DISP_AHB_CLK>,
+               <&sleep_clk>,
+               <&dsi0_phy 0>,
+               <&dsi0_phy 1>,
+               <&dsi1_phy 0>,
+               <&dsi1_phy 1>,
+               <&dp0_phy 0>,
+               <&dp0_phy 1>,
+               <&dp1_phy 0>,
+               <&dp1_phy 1>,
+               <&dp2_phy 0>,
+               <&dp2_phy 1>,
+               <&dp3_phy 0>,
+               <&dp3_phy 1>;
+      #clock-cells = <1>;
+      #reset-cells = <1>;
+      #power-domain-cells = <1>;
+      power-domains = <&rpmhpd RPMHPD_MMCX>;
+      required-opps = <&rpmhpd_opp_low_svs>;
+    };
+...
diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8650-gcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8650-gcc.yaml
new file mode 100644
index 000000000000..b54761cc8674
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/qcom,sm8650-gcc.yaml
@@ -0,0 +1,65 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/qcom,sm8650-gcc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Global Clock & Reset Controller on SM8650
+
+maintainers:
+  - Bjorn Andersson <andersson@kernel.org>
+
+description: |
+  Qualcomm global clock control module provides the clocks, resets and power
+  domains on SM8650
+
+  See also:: include/dt-bindings/clock/qcom,sm8650-gcc.h
+
+properties:
+  compatible:
+    const: qcom,sm8650-gcc
+
+  clocks:
+    items:
+      - description: Board XO source
+      - description: Board Always On XO source
+      - description: Sleep clock source
+      - description: PCIE 0 Pipe clock source
+      - description: PCIE 1 Pipe clock source
+      - description: PCIE 1 Phy Auxiliary clock source
+      - description: UFS Phy Rx symbol 0 clock source
+      - description: UFS Phy Rx symbol 1 clock source
+      - description: UFS Phy Tx symbol 0 clock source
+      - description: USB3 Phy wrapper pipe clock source
+
+required:
+  - compatible
+  - clocks
+
+allOf:
+  - $ref: qcom,gcc.yaml#
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/qcom,rpmh.h>
+    clock-controller@100000 {
+      compatible = "qcom,sm8650-gcc";
+      reg = <0x00100000 0x001f4200>;
+      clocks = <&rpmhcc RPMH_CXO_CLK>,
+               <&rpmhcc RPMH_CXO_CLK_A>,
+               <&sleep_clk>,
+               <&pcie0_phy>,
+               <&pcie1_phy>,
+               <&pcie_1_phy_aux_clk>,
+               <&ufs_mem_phy 0>,
+               <&ufs_mem_phy 1>,
+               <&ufs_mem_phy 2>,
+               <&usb_1_qmpphy>;
+      #clock-cells = <1>;
+      #reset-cells = <1>;
+      #power-domain-cells = <1>;
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/qcom,x1e80100-gcc.yaml b/Documentation/devicetree/bindings/clock/qcom,x1e80100-gcc.yaml
new file mode 100644
index 000000000000..14a796dbf8bc
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/qcom,x1e80100-gcc.yaml
@@ -0,0 +1,72 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/qcom,x1e80100-gcc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Global Clock & Reset Controller on X1E80100
+
+maintainers:
+  - Rajendra Nayak <quic_rjendra@quicinc.com>
+
+description: |
+  Qualcomm global clock control module provides the clocks, resets and power
+  domains on X1E80100
+
+  See also:: include/dt-bindings/clock/qcom,x1e80100-gcc.h
+
+properties:
+  compatible:
+    const: qcom,x1e80100-gcc
+
+  clocks:
+    items:
+      - description: Board XO source
+      - description: Sleep clock source
+      - description: PCIe 3 pipe clock
+      - description: PCIe 4 pipe clock
+      - description: PCIe 5 pipe clock
+      - description: PCIe 6a pipe clock
+      - description: PCIe 6b pipe clock
+      - description: USB QMP Phy 0 clock source
+      - description: USB QMP Phy 1 clock source
+      - description: USB QMP Phy 2 clock source
+
+  power-domains:
+    description:
+      A phandle and PM domain specifier for the CX power domain.
+    maxItems: 1
+
+required:
+  - compatible
+  - clocks
+  - power-domains
+
+allOf:
+  - $ref: qcom,gcc.yaml#
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/power/qcom,rpmhpd.h>
+    clock-controller@100000 {
+      compatible = "qcom,x1e80100-gcc";
+      reg = <0x00100000 0x200000>;
+      clocks = <&bi_tcxo_div2>,
+               <&sleep_clk>,
+               <&pcie3_phy>,
+               <&pcie4_phy>,
+               <&pcie5_phy>,
+               <&pcie6a_phy>,
+               <&pcie6b_phy>,
+               <&usb_1_ss0_qmpphy 0>,
+               <&usb_1_ss1_qmpphy 1>,
+               <&usb_1_ss2_qmpphy 2>;
+      power-domains = <&rpmhpd RPMHPD_CX>;
+      #clock-cells = <1>;
+      #reset-cells = <1>;
+      #power-domain-cells = <1>;
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/crypto/inside-secure,safexcel.yaml b/Documentation/devicetree/bindings/crypto/inside-secure,safexcel.yaml
new file mode 100644
index 000000000000..ef07258d16c1
--- /dev/null
+++ b/Documentation/devicetree/bindings/crypto/inside-secure,safexcel.yaml
@@ -0,0 +1,86 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/crypto/inside-secure,safexcel.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Inside Secure SafeXcel cryptographic engine
+
+maintainers:
+  - Antoine Tenart <atenart@kernel.org>
+
+properties:
+  compatible:
+    oneOf:
+      - const: inside-secure,safexcel-eip197b
+      - const: inside-secure,safexcel-eip197d
+      - const: inside-secure,safexcel-eip97ies
+      - const: inside-secure,safexcel-eip197
+        description: Equivalent of inside-secure,safexcel-eip197b
+        deprecated: true
+      - const: inside-secure,safexcel-eip97
+        description: Equivalent of inside-secure,safexcel-eip97ies
+        deprecated: true
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 6
+
+  interrupt-names:
+    items:
+      - const: ring0
+      - const: ring1
+      - const: ring2
+      - const: ring3
+      - const: eip
+      - const: mem
+
+  clocks:
+    minItems: 1
+    maxItems: 2
+
+  clock-names:
+    minItems: 1
+    items:
+      - const: core
+      - const: reg
+
+required:
+  - reg
+  - interrupts
+  - interrupt-names
+
+allOf:
+  - if:
+      properties:
+        clocks:
+          minItems: 2
+    then:
+      properties:
+        clock-names:
+          minItems: 2
+      required:
+        - clock-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    crypto@800000 {
+        compatible = "inside-secure,safexcel-eip197b";
+        reg = <0x800000 0x200000>;
+        interrupts = <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
+        interrupt-names = "ring0", "ring1", "ring2", "ring3", "eip", "mem";
+        clocks = <&cpm_syscon0 1 26>;
+        clock-names = "core";
+    };
diff --git a/Documentation/devicetree/bindings/crypto/inside-secure-safexcel.txt b/Documentation/devicetree/bindings/crypto/inside-secure-safexcel.txt
deleted file mode 100644
index 3bbf144c9988..000000000000
--- a/Documentation/devicetree/bindings/crypto/inside-secure-safexcel.txt
+++ /dev/null
@@ -1,40 +0,0 @@
-Inside Secure SafeXcel cryptographic engine
-
-Required properties:
-- compatible: Should be "inside-secure,safexcel-eip197b",
-	      "inside-secure,safexcel-eip197d" or
-              "inside-secure,safexcel-eip97ies".
-- reg: Base physical address of the engine and length of memory mapped region.
-- interrupts: Interrupt numbers for the rings and engine.
-- interrupt-names: Should be "ring0", "ring1", "ring2", "ring3", "eip", "mem".
-
-Optional properties:
-- clocks: Reference to the crypto engine clocks, the second clock is
-          needed for the Armada 7K/8K SoCs.
-- clock-names: mandatory if there is a second clock, in this case the
-               name must be "core" for the first clock and "reg" for
-               the second one.
-
-Backward compatibility:
-Two compatibles are kept for backward compatibility, but shouldn't be used for
-new submissions:
-- "inside-secure,safexcel-eip197" is equivalent to
-  "inside-secure,safexcel-eip197b".
-- "inside-secure,safexcel-eip97" is equivalent to
-  "inside-secure,safexcel-eip97ies".
-
-Example:
-
-	crypto: crypto@800000 {
-		compatible = "inside-secure,safexcel-eip197b";
-		reg = <0x800000 0x200000>;
-		interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>;
-		interrupt-names = "mem", "ring0", "ring1", "ring2", "ring3",
-				  "eip";
-		clocks = <&cpm_syscon0 1 26>;
-	};
diff --git a/Documentation/devicetree/bindings/crypto/qcom,inline-crypto-engine.yaml b/Documentation/devicetree/bindings/crypto/qcom,inline-crypto-engine.yaml
index ca4f7d1cefaa..09e43157cc71 100644
--- a/Documentation/devicetree/bindings/crypto/qcom,inline-crypto-engine.yaml
+++ b/Documentation/devicetree/bindings/crypto/qcom,inline-crypto-engine.yaml
@@ -16,6 +16,7 @@ properties:
           - qcom,sa8775p-inline-crypto-engine
           - qcom,sm8450-inline-crypto-engine
           - qcom,sm8550-inline-crypto-engine
+          - qcom,sm8650-inline-crypto-engine
       - const: qcom,inline-crypto-engine
 
   reg:
diff --git a/Documentation/devicetree/bindings/crypto/qcom,prng.yaml b/Documentation/devicetree/bindings/crypto/qcom,prng.yaml
index 13070db0f70c..89c88004b41b 100644
--- a/Documentation/devicetree/bindings/crypto/qcom,prng.yaml
+++ b/Documentation/devicetree/bindings/crypto/qcom,prng.yaml
@@ -21,6 +21,7 @@ properties:
               - qcom,sc7280-trng
               - qcom,sm8450-trng
               - qcom,sm8550-trng
+              - qcom,sm8650-trng
           - const: qcom,trng
 
   reg:
diff --git a/Documentation/devicetree/bindings/crypto/qcom-qce.yaml b/Documentation/devicetree/bindings/crypto/qcom-qce.yaml
index 8e665d910e6e..a48bd381063a 100644
--- a/Documentation/devicetree/bindings/crypto/qcom-qce.yaml
+++ b/Documentation/devicetree/bindings/crypto/qcom-qce.yaml
@@ -44,10 +44,12 @@ properties:
 
       - items:
           - enum:
+              - qcom,sc7280-qce
               - qcom,sm8250-qce
               - qcom,sm8350-qce
               - qcom,sm8450-qce
               - qcom,sm8550-qce
+              - qcom,sm8650-qce
           - const: qcom,sm8150-qce
           - const: qcom,qce
 
@@ -96,6 +98,7 @@ allOf:
               - qcom,crypto-v5.4
               - qcom,ipq6018-qce
               - qcom,ipq8074-qce
+              - qcom,ipq9574-qce
               - qcom,msm8996-qce
               - qcom,sdm845-qce
     then:
@@ -129,6 +132,17 @@ allOf:
         - clocks
         - clock-names
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,sm8150-qce
+    then:
+      properties:
+        clocks: false
+        clock-names: false
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml b/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml
index 987aa83c2649..df20a3c9c744 100644
--- a/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml
@@ -9,6 +9,9 @@ title: Analog Devices ADV7533/35 HDMI Encoders
 maintainers:
   - Laurent Pinchart <laurent.pinchart@ideasonboard.com>
 
+allOf:
+  - $ref: /schemas/sound/dai-common.yaml#
+
 description: |
   The ADV7533 and ADV7535 are HDMI audio and video transmitters
   compatible with HDMI 1.4 and DVI 1.0. They support color space
@@ -89,6 +92,9 @@ properties:
     $ref: /schemas/types.yaml#/definitions/uint32
     enum: [ 1, 2, 3, 4 ]
 
+  "#sound-dai-cells":
+    const: 0
+
   ports:
     description:
       The ADV7533/35 has two video ports and one audio port.
diff --git a/Documentation/devicetree/bindings/display/fsl,lcdif.yaml b/Documentation/devicetree/bindings/display/fsl,lcdif.yaml
index fc11ab5fc465..1c2be8d6f633 100644
--- a/Documentation/devicetree/bindings/display/fsl,lcdif.yaml
+++ b/Documentation/devicetree/bindings/display/fsl,lcdif.yaml
@@ -51,7 +51,10 @@ properties:
     minItems: 1
 
   interrupts:
-    maxItems: 1
+    items:
+      - description: LCDIF DMA interrupt
+      - description: LCDIF Error interrupt
+    minItems: 1
 
   power-domains:
     maxItems: 1
@@ -131,6 +134,21 @@ allOf:
     then:
       required:
         - power-domains
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - fsl,imx23-lcdif
+    then:
+      properties:
+        interrupts:
+          minItems: 2
+          maxItems: 2
+    else:
+      properties:
+        interrupts:
+          maxItems: 1
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,aal.yaml b/Documentation/devicetree/bindings/display/mediatek/mediatek,aal.yaml
index 7fd42c8fdc32..b4c28e96dd55 100644
--- a/Documentation/devicetree/bindings/display/mediatek/mediatek,aal.yaml
+++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,aal.yaml
@@ -24,6 +24,7 @@ properties:
       - enum:
           - mediatek,mt8173-disp-aal
           - mediatek,mt8183-disp-aal
+          - mediatek,mt8195-mdp3-aal
       - items:
           - enum:
               - mediatek,mt2712-disp-aal
diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,color.yaml b/Documentation/devicetree/bindings/display/mediatek/mediatek,color.yaml
index f21e44092043..b886ca0d89ea 100644
--- a/Documentation/devicetree/bindings/display/mediatek/mediatek,color.yaml
+++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,color.yaml
@@ -26,6 +26,7 @@ properties:
           - mediatek,mt2701-disp-color
           - mediatek,mt8167-disp-color
           - mediatek,mt8173-disp-color
+          - mediatek,mt8195-mdp3-color
       - items:
           - enum:
               - mediatek,mt7623-disp-color
diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,dsi.yaml b/Documentation/devicetree/bindings/display/mediatek/mediatek,dsi.yaml
index 537e5304b730..8611319bed2e 100644
--- a/Documentation/devicetree/bindings/display/mediatek/mediatek,dsi.yaml
+++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,dsi.yaml
@@ -10,7 +10,6 @@ maintainers:
   - Chun-Kuang Hu <chunkuang.hu@kernel.org>
   - Philipp Zabel <p.zabel@pengutronix.de>
   - Jitao Shi <jitao.shi@mediatek.com>
-  - Xinlei Lee <xinlei.lee@mediatek.com>
 
 description: |
   The MediaTek DSI function block is a sink of the display subsystem and can
@@ -35,6 +34,10 @@ properties:
           - enum:
               - mediatek,mt6795-dsi
           - const: mediatek,mt8173-dsi
+      - items:
+          - enum:
+              - mediatek,mt8195-dsi
+          - const: mediatek,mt8183-dsi
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,ethdr.yaml b/Documentation/devicetree/bindings/display/mediatek/mediatek,ethdr.yaml
index 801fa66ae615..677882348ede 100644
--- a/Documentation/devicetree/bindings/display/mediatek/mediatek,ethdr.yaml
+++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,ethdr.yaml
@@ -23,7 +23,11 @@ description:
 
 properties:
   compatible:
-    const: mediatek,mt8195-disp-ethdr
+    oneOf:
+      - const: mediatek,mt8195-disp-ethdr
+      - items:
+          - const: mediatek,mt8188-disp-ethdr
+          - const: mediatek,mt8195-disp-ethdr
 
   reg:
     maxItems: 7
diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,mdp-rdma.yaml b/Documentation/devicetree/bindings/display/mediatek/mediatek,mdp-rdma.yaml
deleted file mode 100644
index dd12e2ff685c..000000000000
--- a/Documentation/devicetree/bindings/display/mediatek/mediatek,mdp-rdma.yaml
+++ /dev/null
@@ -1,88 +0,0 @@
-# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
-%YAML 1.2
----
-$id: http://devicetree.org/schemas/display/mediatek/mediatek,mdp-rdma.yaml#
-$schema: http://devicetree.org/meta-schemas/core.yaml#
-
-title: MediaTek MDP RDMA
-
-maintainers:
-  - Chun-Kuang Hu <chunkuang.hu@kernel.org>
-  - Philipp Zabel <p.zabel@pengutronix.de>
-
-description:
-  The MediaTek MDP RDMA stands for Read Direct Memory Access.
-  It provides real time data to the back-end panel driver, such as DSI,
-  DPI and DP_INTF.
-  It contains one line buffer to store the sufficient pixel data.
-  RDMA device node must be siblings to the central MMSYS_CONFIG node.
-  For a description of the MMSYS_CONFIG binding, see
-  Documentation/devicetree/bindings/arm/mediatek/mediatek,mmsys.yaml for details.
-
-properties:
-  compatible:
-    const: mediatek,mt8195-vdo1-rdma
-
-  reg:
-    maxItems: 1
-
-  interrupts:
-    maxItems: 1
-
-  power-domains:
-    maxItems: 1
-
-  clocks:
-    items:
-      - description: RDMA Clock
-
-  iommus:
-    maxItems: 1
-
-  mediatek,gce-client-reg:
-    description:
-      The register of display function block to be set by gce. There are 4 arguments,
-      such as gce node, subsys id, offset and register size. The subsys id that is
-      mapping to the register of display function blocks is defined in the gce header
-      include/dt-bindings/gce/<chip>-gce.h of each chips.
-    $ref: /schemas/types.yaml#/definitions/phandle-array
-    items:
-      items:
-        - description: phandle of GCE
-        - description: GCE subsys id
-        - description: register offset
-        - description: register size
-    maxItems: 1
-
-required:
-  - compatible
-  - reg
-  - power-domains
-  - clocks
-  - iommus
-  - mediatek,gce-client-reg
-
-additionalProperties: false
-
-examples:
-  - |
-    #include <dt-bindings/interrupt-controller/arm-gic.h>
-    #include <dt-bindings/clock/mt8195-clk.h>
-    #include <dt-bindings/power/mt8195-power.h>
-    #include <dt-bindings/gce/mt8195-gce.h>
-    #include <dt-bindings/memory/mt8195-memory-port.h>
-
-    soc {
-        #address-cells = <2>;
-        #size-cells = <2>;
-
-        rdma@1c104000 {
-            compatible = "mediatek,mt8195-vdo1-rdma";
-            reg = <0 0x1c104000 0 0x1000>;
-            interrupts = <GIC_SPI 495 IRQ_TYPE_LEVEL_HIGH 0>;
-            clocks = <&vdosys1 CLK_VDO1_MDP_RDMA0>;
-            power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
-            iommus = <&iommu_vdo M4U_PORT_L2_MDP_RDMA0>;
-            mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0x4000 0x1000>;
-        };
-    };
diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,merge.yaml b/Documentation/devicetree/bindings/display/mediatek/mediatek,merge.yaml
index eead5cb8636e..dae839279950 100644
--- a/Documentation/devicetree/bindings/display/mediatek/mediatek,merge.yaml
+++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,merge.yaml
@@ -24,9 +24,13 @@ properties:
       - enum:
           - mediatek,mt8173-disp-merge
           - mediatek,mt8195-disp-merge
+          - mediatek,mt8195-mdp3-merge
       - items:
           - const: mediatek,mt6795-disp-merge
           - const: mediatek,mt8173-disp-merge
+      - items:
+          - const: mediatek,mt8188-disp-merge
+          - const: mediatek,mt8195-disp-merge
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,ovl.yaml b/Documentation/devicetree/bindings/display/mediatek/mediatek,ovl.yaml
index 3e1069b00b56..c471a181d125 100644
--- a/Documentation/devicetree/bindings/display/mediatek/mediatek,ovl.yaml
+++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,ovl.yaml
@@ -26,6 +26,7 @@ properties:
           - mediatek,mt8173-disp-ovl
           - mediatek,mt8183-disp-ovl
           - mediatek,mt8192-disp-ovl
+          - mediatek,mt8195-mdp3-ovl
       - items:
           - enum:
               - mediatek,mt7623-disp-ovl
diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,padding.yaml b/Documentation/devicetree/bindings/display/mediatek/mediatek,padding.yaml
new file mode 100644
index 000000000000..be07bbdc54e3
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,padding.yaml
@@ -0,0 +1,83 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/mediatek/mediatek,padding.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: MediaTek Display Padding
+
+maintainers:
+  - Chun-Kuang Hu <chunkuang.hu@kernel.org>
+  - Philipp Zabel <p.zabel@pengutronix.de>
+
+description:
+  Padding provides ability to add pixels to width and height of a layer with
+  specified colors. Due to hardware design, Mixer in VDOSYS1 requires
+  width of a layer to be 2-pixel-align, or 4-pixel-align when ETHDR is enabled,
+  we need Padding to deal with odd width.
+  Please notice that even if the Padding is in bypass mode, settings in
+  register must be cleared to 0, or undefined behaviors could happen.
+
+properties:
+  compatible:
+    enum:
+      - mediatek,mt8188-disp-padding
+      - mediatek,mt8195-mdp3-padding
+
+  reg:
+    maxItems: 1
+
+  power-domains:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: Padding's clocks
+
+  mediatek,gce-client-reg:
+    description:
+      GCE (Global Command Engine) is a multi-core micro processor that helps
+      its clients to execute commands without interrupting CPU. This property
+      describes GCE client's information that is composed by 4 fields.
+      1. Phandle of the GCE (there may be several GCE processors)
+      2. Sub-system ID defined in the dt-binding like a user ID
+         (Please refer to include/dt-bindings/gce/<chip>-gce.h)
+      3. Offset from base address of the subsys you are at
+      4. Size of the register the client needs
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    items:
+      items:
+        - description: Phandle of the GCE
+        - description: Subsys ID defined in the dt-binding
+        - description: Offset from base address of the subsys
+        - description: Size of register
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - power-domains
+  - clocks
+  - mediatek,gce-client-reg
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/mediatek,mt8188-clk.h>
+    #include <dt-bindings/power/mediatek,mt8188-power.h>
+    #include <dt-bindings/gce/mt8195-gce.h>
+
+    soc {
+        #address-cells = <2>;
+        #size-cells = <2>;
+
+        padding0: padding@1c11d000 {
+            compatible = "mediatek,mt8188-disp-padding";
+            reg = <0 0x1c11d000 0 0x1000>;
+            clocks = <&vdosys1 CLK_VDO1_PADDING0>;
+            power-domains = <&spm MT8188_POWER_DOMAIN_VDOSYS1>;
+            mediatek,gce-client-reg = <&gce0 SUBSYS_1c11XXXX 0xd000 0x1000>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,split.yaml b/Documentation/devicetree/bindings/display/mediatek/mediatek,split.yaml
index a8a5c9608598..e4affc854f3d 100644
--- a/Documentation/devicetree/bindings/display/mediatek/mediatek,split.yaml
+++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,split.yaml
@@ -23,6 +23,7 @@ properties:
     oneOf:
       - enum:
           - mediatek,mt8173-disp-split
+          - mediatek,mt8195-mdp3-split
       - items:
           - const: mediatek,mt6795-disp-split
           - const: mediatek,mt8173-disp-split
@@ -38,6 +39,21 @@ properties:
       the power controller specified by phandle. See
       Documentation/devicetree/bindings/power/power-domain.yaml for details.
 
+  mediatek,gce-client-reg:
+    description:
+      The register of display function block to be set by gce. There are 4 arguments,
+      such as gce node, subsys id, offset and register size. The subsys id that is
+      mapping to the register of display function blocks is defined in the gce header
+      include/dt-bindings/gce/<chip>-gce.h of each chips.
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    items:
+      items:
+        - description: phandle of GCE
+        - description: GCE subsys id
+        - description: register offset
+        - description: register size
+    maxItems: 1
+
   clocks:
     items:
       - description: SPLIT Clock
@@ -48,6 +64,17 @@ required:
   - power-domains
   - clocks
 
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: mediatek,mt8195-mdp3-split
+
+    then:
+      required:
+        - mediatek,gce-client-reg
+
 additionalProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/display/panel/panel-simple-dsi.yaml b/Documentation/devicetree/bindings/display/panel/panel-simple-dsi.yaml
index 73674baea75d..f9160d7bac3c 100644
--- a/Documentation/devicetree/bindings/display/panel/panel-simple-dsi.yaml
+++ b/Documentation/devicetree/bindings/display/panel/panel-simple-dsi.yaml
@@ -42,6 +42,8 @@ properties:
       - lg,acx467akm-7
         # LG Corporation 7" WXGA TFT LCD panel
       - lg,ld070wx3-sl01
+        # LG Corporation 5" HD TFT LCD panel
+      - lg,lh500wx1-sd03
         # One Stop Displays OSD101T2587-53TS 10.1" 1920x1200 panel
       - osddisplays,osd101t2587-53ts
         # Panasonic 10" WUXGA TFT LCD panel
diff --git a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml
index 3ec9ee95045f..11422af3477e 100644
--- a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml
+++ b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml
@@ -208,8 +208,6 @@ properties:
       - lemaker,bl035-rgb-002
         # LG 7" (800x480 pixels) TFT LCD panel
       - lg,lb070wv8
-        # LG Corporation 5" HD TFT LCD panel
-      - lg,lh500wx1-sd03
         # LG LP079QX1-SP0V 7.9" (1536x2048 pixels) TFT LCD panel
       - lg,lp079qx1-sp0v
         # LG 9.7" (2048x1536 pixels) TFT LCD panel
diff --git a/Documentation/devicetree/bindings/firmware/qcom,scm.yaml b/Documentation/devicetree/bindings/firmware/qcom,scm.yaml
index 0613a37a851a..47d3d2d52acd 100644
--- a/Documentation/devicetree/bindings/firmware/qcom,scm.yaml
+++ b/Documentation/devicetree/bindings/firmware/qcom,scm.yaml
@@ -63,7 +63,9 @@ properties:
           - qcom,scm-sm8350
           - qcom,scm-sm8450
           - qcom,scm-sm8550
+          - qcom,scm-sm8650
           - qcom,scm-qcs404
+          - qcom,scm-x1e80100
       - const: qcom,scm
 
   clocks:
@@ -178,21 +180,6 @@ allOf:
           minItems: 3
           maxItems: 3
 
-  # Interconnects
-  - if:
-      not:
-        properties:
-          compatible:
-            contains:
-              enum:
-                - qcom,scm-qdu1000
-                - qcom,scm-sc8280xp
-                - qcom,scm-sm8450
-                - qcom,scm-sm8550
-    then:
-      properties:
-        interconnects: false
-
   # Interrupts
   - if:
       not:
@@ -202,6 +189,7 @@ allOf:
               enum:
                 - qcom,scm-sm8450
                 - qcom,scm-sm8550
+                - qcom,scm-sm8650
     then:
       properties:
         interrupts: false
diff --git a/Documentation/devicetree/bindings/gpu/arm,mali-midgard.yaml b/Documentation/devicetree/bindings/gpu/arm,mali-midgard.yaml
index ca02baba5526..0801da33a385 100644
--- a/Documentation/devicetree/bindings/gpu/arm,mali-midgard.yaml
+++ b/Documentation/devicetree/bindings/gpu/arm,mali-midgard.yaml
@@ -42,6 +42,11 @@ properties:
           - const: arm,mali-t760
       - items:
           - enum:
+              - samsung,exynos7-mali
+          - const: samsung,exynos5433-mali
+          - const: arm,mali-t760
+      - items:
+          - enum:
               - rockchip,rk3399-mali
           - const: arm,mali-t860
 
diff --git a/Documentation/devicetree/bindings/hwinfo/samsung,exynos-chipid.yaml b/Documentation/devicetree/bindings/hwinfo/samsung,exynos-chipid.yaml
index 95cbdcb56efe..780ccb5ee9b4 100644
--- a/Documentation/devicetree/bindings/hwinfo/samsung,exynos-chipid.yaml
+++ b/Documentation/devicetree/bindings/hwinfo/samsung,exynos-chipid.yaml
@@ -11,9 +11,21 @@ maintainers:
 
 properties:
   compatible:
-    enum:
-      - samsung,exynos4210-chipid
-      - samsung,exynos850-chipid
+    oneOf:
+      - enum:
+          - samsung,exynos4210-chipid
+          - samsung,exynos850-chipid
+      - items:
+          - enum:
+              - samsung,exynos5433-chipid
+              - samsung,exynos7-chipid
+          - const: samsung,exynos4210-chipid
+      - items:
+          - enum:
+              - samsung,exynos7885-chipid
+              - samsung,exynosautov9-chipid
+              - samsung,exynosautov920-chipid
+          - const: samsung,exynos850-chipid
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml b/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml
index 3e52a0db6c41..df9c57bca2a8 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml
+++ b/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml
@@ -25,7 +25,16 @@ properties:
           - samsung,exynos5250-hsi2c    # Exynos5250 and Exynos5420
           - samsung,exynos5260-hsi2c    # Exynos5260
           - samsung,exynos7-hsi2c       # Exynos7
-          - samsung,exynosautov9-hsi2c  # ExynosAutoV9 and Exynos850
+          - samsung,exynosautov9-hsi2c
+      - items:
+          - enum:
+              - samsung,exynos5433-hsi2c
+              - tesla,fsd-hsi2c
+          - const: samsung,exynos7-hsi2c
+      - items:
+          - enum:
+              - samsung,exynos850-hsi2c
+          - const: samsung,exynosautov9-hsi2c
       - const: samsung,exynos5-hsi2c    # Exynos5250 and Exynos5420
         deprecated: true
 
diff --git a/Documentation/devicetree/bindings/i2c/samsung,s3c2410-i2c.yaml b/Documentation/devicetree/bindings/i2c/samsung,s3c2410-i2c.yaml
index b204e35e4f8d..1303502cf265 100644
--- a/Documentation/devicetree/bindings/i2c/samsung,s3c2410-i2c.yaml
+++ b/Documentation/devicetree/bindings/i2c/samsung,s3c2410-i2c.yaml
@@ -11,14 +11,20 @@ maintainers:
 
 properties:
   compatible:
-    enum:
-      - samsung,s3c2410-i2c
-      - samsung,s3c2440-i2c
-        # For s3c2440-like I2C used inside HDMIPHY block found on several SoCs:
-      - samsung,s3c2440-hdmiphy-i2c
-        # For s3c2440-like I2C used as a host to SATA PHY controller on an
-        # internal bus:
-      - samsung,exynos5-sata-phy-i2c
+    oneOf:
+      - enum:
+          - samsung,s3c2410-i2c
+          - samsung,s3c2440-i2c
+            # For s3c2440-like I2C used inside HDMIPHY block found on several SoCs:
+          - samsung,s3c2440-hdmiphy-i2c
+            # For s3c2440-like I2C used as a host to SATA PHY controller on an
+            # internal bus:
+          - samsung,exynos5-sata-phy-i2c
+      - items:
+          - enum:
+              - samsung,exynos7885-i2c
+              - samsung,exynos850-i2c
+          - const: samsung,s3c2440-i2c
 
   '#address-cells':
     const: 1
diff --git a/Documentation/devicetree/bindings/iio/adc/samsung,exynos-adc.yaml b/Documentation/devicetree/bindings/iio/adc/samsung,exynos-adc.yaml
index 582d0a03b814..4e40f6bed5db 100644
--- a/Documentation/devicetree/bindings/iio/adc/samsung,exynos-adc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/samsung,exynos-adc.yaml
@@ -11,18 +11,23 @@ maintainers:
 
 properties:
   compatible:
-    enum:
-      - samsung,exynos-adc-v1                 # Exynos5250
-      - samsung,exynos-adc-v2
-      - samsung,exynos3250-adc
-      - samsung,exynos4212-adc                # Exynos4212 and Exynos4412
-      - samsung,exynos7-adc
-      - samsung,s3c2410-adc
-      - samsung,s3c2416-adc
-      - samsung,s3c2440-adc
-      - samsung,s3c2443-adc
-      - samsung,s3c6410-adc
-      - samsung,s5pv210-adc
+    oneOf:
+      - enum:
+          - samsung,exynos-adc-v1                 # Exynos5250
+          - samsung,exynos-adc-v2
+          - samsung,exynos3250-adc
+          - samsung,exynos4212-adc                # Exynos4212 and Exynos4412
+          - samsung,exynos7-adc
+          - samsung,s3c2410-adc
+          - samsung,s3c2416-adc
+          - samsung,s3c2440-adc
+          - samsung,s3c2443-adc
+          - samsung,s3c6410-adc
+          - samsung,s5pv210-adc
+      - items:
+          - enum:
+              - samsung,exynos5433-adc
+          - const: samsung,exynos7-adc
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/interconnect/qcom,sm6115.yaml b/Documentation/devicetree/bindings/interconnect/qcom,sm6115.yaml
new file mode 100644
index 000000000000..14b1a0b08e73
--- /dev/null
+++ b/Documentation/devicetree/bindings/interconnect/qcom,sm6115.yaml
@@ -0,0 +1,152 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/interconnect/qcom,sm6115.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm SM6115 Network-On-Chip interconnect
+
+maintainers:
+  - Konrad Dybcio <konradybcio@kernel.org>
+
+description:
+  The Qualcomm SM6115 interconnect providers support adjusting the
+  bandwidth requirements between the various NoC fabrics.
+
+properties:
+  compatible:
+    enum:
+      - qcom,sm6115-bimc
+      - qcom,sm6115-cnoc
+      - qcom,sm6115-snoc
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    minItems: 1
+    maxItems: 4
+
+  clock-names:
+    minItems: 1
+    maxItems: 4
+
+# Child node's properties
+patternProperties:
+  '^interconnect-[a-z0-9]+$':
+    type: object
+    description:
+      The interconnect providers do not have a separate QoS register space,
+      but share parent's space.
+
+    $ref: qcom,rpm-common.yaml#
+
+    properties:
+      compatible:
+        enum:
+          - qcom,sm6115-clk-virt
+          - qcom,sm6115-mmrt-virt
+          - qcom,sm6115-mmnrt-virt
+
+    required:
+      - compatible
+
+    unevaluatedProperties: false
+
+required:
+  - compatible
+  - reg
+
+allOf:
+  - $ref: qcom,rpm-common.yaml#
+  - if:
+      properties:
+        compatible:
+          const: qcom,sm6115-cnoc
+
+    then:
+      properties:
+        clocks:
+          items:
+            - description: USB-NoC AXI clock
+
+        clock-names:
+          items:
+            - const: usb_axi
+
+  - if:
+      properties:
+        compatible:
+          const: qcom,sm6115-snoc
+
+    then:
+      properties:
+        clocks:
+          items:
+            - description: CPU-NoC AXI clock.
+            - description: UFS-NoC AXI clock.
+            - description: USB-NoC AXI clock.
+            - description: IPA clock.
+
+        clock-names:
+          items:
+            - const: cpu_axi
+            - const: ufs_axi
+            - const: usb_axi
+            - const: ipa
+
+  - if:
+      properties:
+        compatible:
+          enum:
+            - qcom,sm6115-bimc
+            - qcom,sm6115-clk-virt
+            - qcom,sm6115-mmrt-virt
+            - qcom,sm6115-mmnrt-virt
+
+    then:
+      properties:
+        clocks: false
+        clock-names: false
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/qcom,gcc-sm6115.h>
+    #include <dt-bindings/clock/qcom,rpmcc.h>
+
+    snoc: interconnect@1880000 {
+        compatible = "qcom,sm6115-snoc";
+        reg = <0x01880000 0x60200>;
+        clocks = <&gcc GCC_SYS_NOC_CPUSS_AHB_CLK>,
+                 <&gcc GCC_SYS_NOC_UFS_PHY_AXI_CLK>,
+                 <&gcc GCC_SYS_NOC_USB3_PRIM_AXI_CLK>,
+                 <&rpmcc RPM_SMD_IPA_CLK>;
+        clock-names = "cpu_axi",
+                      "ufs_axi",
+                      "usb_axi",
+                      "ipa";
+        #interconnect-cells = <1>;
+
+        qup_virt: interconnect-clk {
+            compatible = "qcom,sm6115-clk-virt";
+            #interconnect-cells = <1>;
+        };
+
+        mmnrt_virt: interconnect-mmnrt {
+            compatible = "qcom,sm6115-mmnrt-virt";
+            #interconnect-cells = <1>;
+        };
+
+        mmrt_virt: interconnect-mmrt {
+            compatible = "qcom,sm6115-mmrt-virt";
+            #interconnect-cells = <1>;
+        };
+    };
+
+    cnoc: interconnect@1900000 {
+        compatible = "qcom,sm6115-cnoc";
+        reg = <0x01900000 0x8200>;
+        #interconnect-cells = <1>;
+    };
diff --git a/Documentation/devicetree/bindings/interconnect/qcom,sm8650-rpmh.yaml b/Documentation/devicetree/bindings/interconnect/qcom,sm8650-rpmh.yaml
new file mode 100644
index 000000000000..f9322de7cd61
--- /dev/null
+++ b/Documentation/devicetree/bindings/interconnect/qcom,sm8650-rpmh.yaml
@@ -0,0 +1,136 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/interconnect/qcom,sm8650-rpmh.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm RPMh Network-On-Chip Interconnect on SM8650
+
+maintainers:
+  - Abel Vesa <abel.vesa@linaro.org>
+  - Neil Armstrong <neil.armstrong@linaro.org>
+
+description: |
+  RPMh interconnect providers support system bandwidth requirements through
+  RPMh hardware accelerators known as Bus Clock Manager (BCM). The provider is
+  able to communicate with the BCM through the Resource State Coordinator (RSC)
+  associated with each execution environment. Provider nodes must point to at
+  least one RPMh device child node pertaining to their RSC and each provider
+  can map to multiple RPMh resources.
+
+  See also:: include/dt-bindings/interconnect/qcom,sm8650-rpmh.h
+
+properties:
+  compatible:
+    enum:
+      - qcom,sm8650-aggre1-noc
+      - qcom,sm8650-aggre2-noc
+      - qcom,sm8650-clk-virt
+      - qcom,sm8650-cnoc-main
+      - qcom,sm8650-config-noc
+      - qcom,sm8650-gem-noc
+      - qcom,sm8650-lpass-ag-noc
+      - qcom,sm8650-lpass-lpiaon-noc
+      - qcom,sm8650-lpass-lpicx-noc
+      - qcom,sm8650-mc-virt
+      - qcom,sm8650-mmss-noc
+      - qcom,sm8650-nsp-noc
+      - qcom,sm8650-pcie-anoc
+      - qcom,sm8650-system-noc
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    minItems: 1
+    maxItems: 2
+
+required:
+  - compatible
+
+allOf:
+  - $ref: qcom,rpmh-common.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,sm8650-clk-virt
+              - qcom,sm8650-mc-virt
+    then:
+      properties:
+        reg: false
+    else:
+      required:
+        - reg
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,sm8650-pcie-anoc
+    then:
+      properties:
+        clocks:
+          items:
+            - description: aggre-NOC PCIe AXI clock
+            - description: cfg-NOC PCIe a-NOC AHB clock
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,sm8650-aggre1-noc
+    then:
+      properties:
+        clocks:
+          items:
+            - description: aggre UFS PHY AXI clock
+            - description: aggre USB3 PRIM AXI clock
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,sm8650-aggre2-noc
+    then:
+      properties:
+        clocks:
+          items:
+            - description: RPMH CC IPA clock
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,sm8650-aggre1-noc
+              - qcom,sm8650-aggre2-noc
+              - qcom,sm8650-pcie-anoc
+    then:
+      required:
+        - clocks
+    else:
+      properties:
+        clocks: false
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    clk_virt: interconnect-0 {
+      compatible = "qcom,sm8650-clk-virt";
+      #interconnect-cells = <2>;
+      qcom,bcm-voters = <&apps_bcm_voter>;
+    };
+
+    aggre1_noc: interconnect@16e0000 {
+      compatible = "qcom,sm8650-aggre1-noc";
+      reg = <0x016e0000 0x14400>;
+      #interconnect-cells = <2>;
+      clocks = <&gcc_phy_axi_clk>, <&gcc_prim_axi_clk>;
+      qcom,bcm-voters = <&apps_bcm_voter>;
+    };
diff --git a/Documentation/devicetree/bindings/interconnect/qcom,x1e80100-rpmh.yaml b/Documentation/devicetree/bindings/interconnect/qcom,x1e80100-rpmh.yaml
new file mode 100644
index 000000000000..08b0210e0e59
--- /dev/null
+++ b/Documentation/devicetree/bindings/interconnect/qcom,x1e80100-rpmh.yaml
@@ -0,0 +1,83 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/interconnect/qcom,x1e80100-rpmh.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm RPMh Network-On-Chip Interconnect on X1E80100
+
+maintainers:
+  - Rajendra Nayak <quic_rjendra@quicinc.com>
+  - Abel Vesa <abel.vesa@linaro.org>
+
+description: |
+  RPMh interconnect providers support system bandwidth requirements through
+  RPMh hardware accelerators known as Bus Clock Manager (BCM). The provider is
+  able to communicate with the BCM through the Resource State Coordinator (RSC)
+  associated with each execution environment. Provider nodes must point to at
+  least one RPMh device child node pertaining to their RSC and each provider
+  can map to multiple RPMh resources.
+
+  See also:: include/dt-bindings/interconnect/qcom,x1e80100-rpmh.h
+
+properties:
+  compatible:
+    enum:
+      - qcom,x1e80100-aggre1-noc
+      - qcom,x1e80100-aggre2-noc
+      - qcom,x1e80100-clk-virt
+      - qcom,x1e80100-cnoc-cfg
+      - qcom,x1e80100-cnoc-main
+      - qcom,x1e80100-gem-noc
+      - qcom,x1e80100-lpass-ag-noc
+      - qcom,x1e80100-lpass-lpiaon-noc
+      - qcom,x1e80100-lpass-lpicx-noc
+      - qcom,x1e80100-mc-virt
+      - qcom,x1e80100-mmss-noc
+      - qcom,x1e80100-nsp-noc
+      - qcom,x1e80100-pcie-center-anoc
+      - qcom,x1e80100-pcie-north-anoc
+      - qcom,x1e80100-pcie-south-anoc
+      - qcom,x1e80100-system-noc
+      - qcom,x1e80100-usb-center-anoc
+      - qcom,x1e80100-usb-north-anoc
+      - qcom,x1e80100-usb-south-anoc
+
+  reg:
+    maxItems: 1
+
+required:
+  - compatible
+
+allOf:
+  - $ref: qcom,rpmh-common.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,x1e80100-clk-virt
+              - qcom,x1e80100-mc-virt
+    then:
+      properties:
+        reg: false
+    else:
+      required:
+        - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    clk_virt: interconnect-0 {
+      compatible = "qcom,x1e80100-clk-virt";
+      #interconnect-cells = <2>;
+      qcom,bcm-voters = <&apps_bcm_voter>;
+    };
+
+    aggre1_noc: interconnect@16e0000 {
+      compatible = "qcom,x1e80100-aggre1-noc";
+      reg = <0x016e0000 0x14400>;
+      #interconnect-cells = <2>;
+      qcom,bcm-voters = <&apps_bcm_voter>;
+    };
diff --git a/Documentation/devicetree/bindings/interrupt-controller/qcom,mpm.yaml b/Documentation/devicetree/bindings/interrupt-controller/qcom,mpm.yaml
index 509d20c091af..ebb40c48950a 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/qcom,mpm.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/qcom,mpm.yaml
@@ -29,6 +29,12 @@ properties:
     maxItems: 1
     description:
       Specifies the base address and size of vMPM registers in RPM MSG RAM.
+    deprecated: true
+
+  qcom,rpm-msg-ram:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description:
+      Phandle to the APSS MPM slice of the RPM Message RAM
 
   interrupts:
     maxItems: 1
@@ -62,35 +68,51 @@ properties:
         - description: MPM pin number
         - description: GIC SPI number for the MPM pin
 
+  '#power-domain-cells':
+    const: 0
+
 required:
   - compatible
-  - reg
   - interrupts
   - mboxes
   - interrupt-controller
   - '#interrupt-cells'
   - qcom,mpm-pin-count
   - qcom,mpm-pin-map
+  - qcom,rpm-msg-ram
 
 additionalProperties: false
 
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
-    mpm: interrupt-controller@45f01b8 {
-        compatible = "qcom,mpm";
-        interrupts = <GIC_SPI 197 IRQ_TYPE_EDGE_RISING>;
-        reg = <0x45f01b8 0x1000>;
-        mboxes = <&apcs_glb 1>;
-        interrupt-controller;
-        #interrupt-cells = <2>;
-        interrupt-parent = <&intc>;
-        qcom,mpm-pin-count = <96>;
-        qcom,mpm-pin-map = <2 275>,
-                           <5 296>,
-                           <12 422>,
-                           <24 79>,
-                           <86 183>,
-                           <90 260>,
-                           <91 260>;
+
+    remoteproc-rpm {
+        compatible = "qcom,msm8998-rpm-proc", "qcom,rpm-proc";
+
+        glink-edge {
+            compatible = "qcom,glink-rpm";
+
+            interrupts = <GIC_SPI 168 IRQ_TYPE_EDGE_RISING>;
+            qcom,rpm-msg-ram = <&rpm_msg_ram>;
+            mboxes = <&apcs_glb 0>;
+        };
+
+        mpm: interrupt-controller {
+            compatible = "qcom,mpm";
+            qcom,rpm-msg-ram = <&apss_mpm>;
+            interrupts = <GIC_SPI 197 IRQ_TYPE_EDGE_RISING>;
+            mboxes = <&apcs_glb 1>;
+            interrupt-controller;
+            #interrupt-cells = <2>;
+            interrupt-parent = <&intc>;
+            qcom,mpm-pin-count = <96>;
+            qcom,mpm-pin-map = <2 275>,
+                               <5 296>,
+                               <12 422>,
+                               <24 79>,
+                               <86 183>,
+                               <91 260>;
+            #power-domain-cells = <0>;
+        };
     };
diff --git a/Documentation/devicetree/bindings/interrupt-controller/renesas,rzg2l-irqc.yaml b/Documentation/devicetree/bindings/interrupt-controller/renesas,rzg2l-irqc.yaml
index 2ef3081eaaf3..d3b5aec0a3f7 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/renesas,rzg2l-irqc.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/renesas,rzg2l-irqc.yaml
@@ -26,6 +26,7 @@ properties:
           - renesas,r9a07g043u-irqc   # RZ/G2UL
           - renesas,r9a07g044-irqc    # RZ/G2{L,LC}
           - renesas,r9a07g054-irqc    # RZ/V2L
+          - renesas,r9a08g045-irqc    # RZ/G3S
       - const: renesas,rzg2l-irqc
 
   '#interrupt-cells':
@@ -167,7 +168,9 @@ allOf:
       properties:
         compatible:
           contains:
-            const: renesas,r9a07g043u-irqc
+            enum:
+              - renesas,r9a07g043u-irqc
+              - renesas,r9a08g045-irqc
     then:
       properties:
         interrupts:
diff --git a/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml b/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml
index 0c07e8dda445..709b2211276b 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml
@@ -66,6 +66,7 @@ properties:
           - enum:
               - allwinner,sun20i-d1-plic
               - sophgo,cv1800b-plic
+              - sophgo,cv1812h-plic
               - sophgo,sg2042-plic
               - thead,th1520-plic
           - const: thead,c900-plic
diff --git a/Documentation/devicetree/bindings/media/mediatek,mdp3-fg.yaml b/Documentation/devicetree/bindings/media/mediatek,mdp3-fg.yaml
new file mode 100644
index 000000000000..03f31b009085
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/mediatek,mdp3-fg.yaml
@@ -0,0 +1,61 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/media/mediatek,mdp3-fg.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: MediaTek Media Data Path 3 Film Grain
+
+maintainers:
+  - Matthias Brugger <matthias.bgg@gmail.com>
+  - Moudy Ho <moudy.ho@mediatek.com>
+
+description:
+  Film Grain (FG) is a Media Data Path 3 (MDP3) component used to add
+  the film grain according to the AOMedia Video 1 (AV1) standard.
+
+properties:
+  compatible:
+    enum:
+      - mediatek,mt8195-mdp3-fg
+
+  reg:
+    maxItems: 1
+
+  mediatek,gce-client-reg:
+    description:
+      The register of display function block to be set by gce. There are 4 arguments,
+      such as gce node, subsys id, offset and register size. The subsys id that is
+      mapping to the register of display function blocks is defined in the gce header
+      include/dt-bindings/gce/<chip>-gce.h of each chips.
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    items:
+      items:
+        - description: phandle of GCE
+        - description: GCE subsys id
+        - description: register offset
+        - description: register size
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - mediatek,gce-client-reg
+  - clocks
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/mt8195-clk.h>
+    #include <dt-bindings/gce/mt8195-gce.h>
+
+    display@14002000 {
+        compatible = "mediatek,mt8195-mdp3-fg";
+        reg = <0x14002000 0x1000>;
+        mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0x2000 0x1000>;
+        clocks = <&vppsys0 CLK_VPP0_MDP_FG>;
+    };
diff --git a/Documentation/devicetree/bindings/media/mediatek,mdp3-hdr.yaml b/Documentation/devicetree/bindings/media/mediatek,mdp3-hdr.yaml
new file mode 100644
index 000000000000..d4609bba6578
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/mediatek,mdp3-hdr.yaml
@@ -0,0 +1,61 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/media/mediatek,mdp3-hdr.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: MediaTek Media Data Path 3 HDR
+
+maintainers:
+  - Matthias Brugger <matthias.bgg@gmail.com>
+  - Moudy Ho <moudy.ho@mediatek.com>
+
+description:
+  A Media Data Path 3 (MDP3) component used to perform conversion from
+  High Dynamic Range (HDR) to Standard Dynamic Range (SDR).
+
+properties:
+  compatible:
+    enum:
+      - mediatek,mt8195-mdp3-hdr
+
+  reg:
+    maxItems: 1
+
+  mediatek,gce-client-reg:
+    description:
+      The register of display function block to be set by gce. There are 4 arguments,
+      such as gce node, subsys id, offset and register size. The subsys id that is
+      mapping to the register of display function blocks is defined in the gce header
+      include/dt-bindings/gce/<chip>-gce.h of each chips.
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    items:
+      items:
+        - description: phandle of GCE
+        - description: GCE subsys id
+        - description: register offset
+        - description: register size
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - mediatek,gce-client-reg
+  - clocks
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/mt8195-clk.h>
+    #include <dt-bindings/gce/mt8195-gce.h>
+
+    display@14004000 {
+        compatible = "mediatek,mt8195-mdp3-hdr";
+        reg = <0x14004000 0x1000>;
+        mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0x4000 0x1000>;
+        clocks = <&vppsys0 CLK_VPP0_MDP_HDR>;
+    };
diff --git a/Documentation/devicetree/bindings/media/mediatek,mdp3-rdma.yaml b/Documentation/devicetree/bindings/media/mediatek,mdp3-rdma.yaml
index 7032c7e15039..59db8306485b 100644
--- a/Documentation/devicetree/bindings/media/mediatek,mdp3-rdma.yaml
+++ b/Documentation/devicetree/bindings/media/mediatek,mdp3-rdma.yaml
@@ -20,8 +20,14 @@ description: |
 
 properties:
   compatible:
-    items:
-      - const: mediatek,mt8183-mdp3-rdma
+    oneOf:
+      - enum:
+          - mediatek,mt8183-mdp3-rdma
+          - mediatek,mt8195-mdp3-rdma
+          - mediatek,mt8195-vdo1-rdma
+      - items:
+          - const: mediatek,mt8188-vdo1-rdma
+          - const: mediatek,mt8195-vdo1-rdma
 
   reg:
     maxItems: 1
@@ -45,6 +51,14 @@ properties:
       include/dt-bindings/gce/<chip>-gce.h of each chips.
     $ref: /schemas/types.yaml#/definitions/uint32-array
 
+  mediatek,scp:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description:
+      Phandle to the System Control Processor (SCP) used for initializing
+      and stopping the MDP3, for sending frame data locations to the MDP3's
+      VPU and to install Inter-Processor Interrupt handlers to control
+      processing states.
+
   power-domains:
     maxItems: 1
 
@@ -52,6 +66,7 @@ properties:
     items:
       - description: RDMA clock
       - description: RSZ clock
+    minItems: 1
 
   iommus:
     maxItems: 1
@@ -60,16 +75,72 @@ properties:
     items:
       - description: used for 1st data pipe from RDMA
       - description: used for 2nd data pipe from RDMA
+      - description: used for 3rd data pipe from RDMA
+      - description: used for 4th data pipe from RDMA
+      - description: used for the data pipe from SPLIT
+    minItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  '#dma-cells':
+    const: 1
 
 required:
   - compatible
   - reg
   - mediatek,gce-client-reg
-  - mediatek,gce-events
   - power-domains
   - clocks
   - iommus
-  - mboxes
+  - '#dma-cells'
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: mediatek,mt8183-mdp3-rdma
+
+    then:
+      properties:
+        clocks:
+          minItems: 2
+
+        mboxes:
+          minItems: 2
+
+      required:
+        - mboxes
+        - mediatek,gce-events
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: mediatek,mt8195-mdp3-rdma
+
+    then:
+      properties:
+        clocks:
+          maxItems: 1
+
+        mboxes:
+          minItems: 5
+
+      required:
+        - mediatek,gce-events
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: mediatek,mt8195-vdo1-rdma
+
+    then:
+      properties:
+        clocks:
+          maxItems: 1
 
 additionalProperties: false
 
@@ -80,16 +151,17 @@ examples:
     #include <dt-bindings/power/mt8183-power.h>
     #include <dt-bindings/memory/mt8183-larb-port.h>
 
-    mdp3_rdma0: mdp3-rdma0@14001000 {
-      compatible = "mediatek,mt8183-mdp3-rdma";
-      reg = <0x14001000 0x1000>;
-      mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x1000 0x1000>;
-      mediatek,gce-events = <CMDQ_EVENT_MDP_RDMA0_SOF>,
-                            <CMDQ_EVENT_MDP_RDMA0_EOF>;
-      power-domains = <&spm MT8183_POWER_DOMAIN_DISP>;
-      clocks = <&mmsys CLK_MM_MDP_RDMA0>,
-               <&mmsys CLK_MM_MDP_RSZ1>;
-      iommus = <&iommu>;
-      mboxes = <&gce 20 CMDQ_THR_PRIO_LOWEST>,
-               <&gce 21 CMDQ_THR_PRIO_LOWEST>;
+    dma-controller@14001000 {
+        compatible = "mediatek,mt8183-mdp3-rdma";
+        reg = <0x14001000 0x1000>;
+        mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x1000 0x1000>;
+        mediatek,gce-events = <CMDQ_EVENT_MDP_RDMA0_SOF>,
+                              <CMDQ_EVENT_MDP_RDMA0_EOF>;
+        power-domains = <&spm MT8183_POWER_DOMAIN_DISP>;
+        clocks = <&mmsys CLK_MM_MDP_RDMA0>,
+                 <&mmsys CLK_MM_MDP_RSZ1>;
+        iommus = <&iommu>;
+        mboxes = <&gce 20 CMDQ_THR_PRIO_LOWEST>,
+                 <&gce 21 CMDQ_THR_PRIO_LOWEST>;
+        #dma-cells = <1>;
     };
diff --git a/Documentation/devicetree/bindings/media/mediatek,mdp3-rsz.yaml b/Documentation/devicetree/bindings/media/mediatek,mdp3-rsz.yaml
index 78f9de6192ef..f5676bec4326 100644
--- a/Documentation/devicetree/bindings/media/mediatek,mdp3-rsz.yaml
+++ b/Documentation/devicetree/bindings/media/mediatek,mdp3-rsz.yaml
@@ -15,9 +15,13 @@ description: |
 
 properties:
   compatible:
-    items:
+    oneOf:
       - enum:
           - mediatek,mt8183-mdp3-rsz
+      - items:
+          - enum:
+              - mediatek,mt8195-mdp3-rsz
+          - const: mediatek,mt8183-mdp3-rsz
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/media/mediatek,mdp3-stitch.yaml b/Documentation/devicetree/bindings/media/mediatek,mdp3-stitch.yaml
new file mode 100644
index 000000000000..d815bea29154
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/mediatek,mdp3-stitch.yaml
@@ -0,0 +1,61 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/media/mediatek,mdp3-stitch.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: MediaTek Media Data Path 3 STITCH
+
+maintainers:
+  - Matthias Brugger <matthias.bgg@gmail.com>
+  - Moudy Ho <moudy.ho@mediatek.com>
+
+description:
+  One of Media Data Path 3 (MDP3) components used to combine multiple video frame
+  with overlapping fields of view to produce a segmented panorame.
+
+properties:
+  compatible:
+    enum:
+      - mediatek,mt8195-mdp3-stitch
+
+  reg:
+    maxItems: 1
+
+  mediatek,gce-client-reg:
+    description:
+      The register of display function block to be set by gce. There are 4 arguments,
+      such as gce node, subsys id, offset and register size. The subsys id that is
+      mapping to the register of display function blocks is defined in the gce header
+      include/dt-bindings/gce/<chip>-gce.h of each chips.
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    items:
+      items:
+        - description: phandle of GCE
+        - description: GCE subsys id
+        - description: register offset
+        - description: register size
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - mediatek,gce-client-reg
+  - clocks
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/mt8195-clk.h>
+    #include <dt-bindings/gce/mt8195-gce.h>
+
+    display@14003000 {
+        compatible = "mediatek,mt8195-mdp3-stitch";
+        reg = <0x14003000 0x1000>;
+        mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0x3000 0x1000>;
+        clocks = <&vppsys0 CLK_VPP0_STITCH>;
+    };
diff --git a/Documentation/devicetree/bindings/media/mediatek,mdp3-tcc.yaml b/Documentation/devicetree/bindings/media/mediatek,mdp3-tcc.yaml
new file mode 100644
index 000000000000..14ea556d4f82
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/mediatek,mdp3-tcc.yaml
@@ -0,0 +1,62 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/media/mediatek,mdp3-tcc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: MediaTek Media Data Path 3 Tone Curve Conversion
+
+maintainers:
+  - Matthias Brugger <matthias.bgg@gmail.com>
+
+description:
+  Tone Curve Conversion (TCC) is one of Media Profile Path 3 (MDP3) components.
+  It is used to handle the tone mapping of various gamma curves in order to
+  achieve HDR10 effects. This helps adapt the content to the color and
+  brightness range that standard display devices typically support.
+
+properties:
+  compatible:
+    enum:
+      - mediatek,mt8195-mdp3-tcc
+
+  reg:
+    maxItems: 1
+
+  mediatek,gce-client-reg:
+    description:
+      The register of display function block to be set by gce. There are 4 arguments,
+      such as gce node, subsys id, offset and register size. The subsys id that is
+      mapping to the register of display function blocks is defined in the gce header
+      include/dt-bindings/gce/<chip>-gce.h of each chips.
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    items:
+      items:
+        - description: phandle of GCE
+        - description: GCE subsys id
+        - description: register offset
+        - description: register size
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - mediatek,gce-client-reg
+  - clocks
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/mt8195-clk.h>
+    #include <dt-bindings/gce/mt8195-gce.h>
+
+    display@1400b000 {
+        compatible = "mediatek,mt8195-mdp3-tcc";
+        reg = <0x1400b000 0x1000>;
+        mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0xb000 0x1000>;
+        clocks = <&vppsys0 CLK_VPP0_MDP_TCC>;
+    };
diff --git a/Documentation/devicetree/bindings/media/mediatek,mdp3-tdshp.yaml b/Documentation/devicetree/bindings/media/mediatek,mdp3-tdshp.yaml
new file mode 100644
index 000000000000..8ab7f2d8e148
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/mediatek,mdp3-tdshp.yaml
@@ -0,0 +1,61 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/media/mediatek,mdp3-tdshp.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: MediaTek Media Data Path 3 Two-Dimensional Sharpness
+
+maintainers:
+  - Matthias Brugger <matthias.bgg@gmail.com>
+  - Moudy Ho <moudy.ho@mediatek.com>
+
+description:
+  Two-Dimensional Sharpness (TDSHP) is a Media Profile Path 3 (MDP3) component
+  used to perform image edge sharpening and enhance vividness and contrast.
+
+properties:
+  compatible:
+    enum:
+      - mediatek,mt8195-mdp3-tdshp
+
+  reg:
+    maxItems: 1
+
+  mediatek,gce-client-reg:
+    description:
+      The register of display function block to be set by gce. There are 4 arguments,
+      such as gce node, subsys id, offset and register size. The subsys id that is
+      mapping to the register of display function blocks is defined in the gce header
+      include/dt-bindings/gce/<chip>-gce.h of each chips.
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    items:
+      items:
+        - description: phandle of GCE
+        - description: GCE subsys id
+        - description: register offset
+        - description: register size
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - mediatek,gce-client-reg
+  - clocks
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/mt8195-clk.h>
+    #include <dt-bindings/gce/mt8195-gce.h>
+
+    display@14007000 {
+        compatible = "mediatek,mt8195-mdp3-tdshp";
+        reg = <0x14007000 0x1000>;
+        mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0x7000 0x1000>;
+        clocks = <&vppsys0 CLK_VPP0_MDP_TDSHP>;
+    };
diff --git a/Documentation/devicetree/bindings/media/mediatek,mdp3-wrot.yaml b/Documentation/devicetree/bindings/media/mediatek,mdp3-wrot.yaml
index 0baa77198fa2..53a679338402 100644
--- a/Documentation/devicetree/bindings/media/mediatek,mdp3-wrot.yaml
+++ b/Documentation/devicetree/bindings/media/mediatek,mdp3-wrot.yaml
@@ -15,9 +15,13 @@ description: |
 
 properties:
   compatible:
-    items:
+    oneOf:
       - enum:
           - mediatek,mt8183-mdp3-wrot
+      - items:
+          - enum:
+              - mediatek,mt8195-mdp3-wrot
+          - const: mediatek,mt8183-mdp3-wrot
 
   reg:
     maxItems: 1
@@ -50,6 +54,9 @@ properties:
   iommus:
     maxItems: 1
 
+  '#dma-cells':
+    const: 1
+
 required:
   - compatible
   - reg
@@ -58,6 +65,7 @@ required:
   - power-domains
   - clocks
   - iommus
+  - '#dma-cells'
 
 additionalProperties: false
 
@@ -68,13 +76,14 @@ examples:
     #include <dt-bindings/power/mt8183-power.h>
     #include <dt-bindings/memory/mt8183-larb-port.h>
 
-    mdp3_wrot0: mdp3-wrot0@14005000 {
-      compatible = "mediatek,mt8183-mdp3-wrot";
-      reg = <0x14005000 0x1000>;
-      mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x5000 0x1000>;
-      mediatek,gce-events = <CMDQ_EVENT_MDP_WROT0_SOF>,
-                            <CMDQ_EVENT_MDP_WROT0_EOF>;
-      power-domains = <&spm MT8183_POWER_DOMAIN_DISP>;
-      clocks = <&mmsys CLK_MM_MDP_WROT0>;
-      iommus = <&iommu>;
+    dma-controller@14005000 {
+        compatible = "mediatek,mt8183-mdp3-wrot";
+        reg = <0x14005000 0x1000>;
+        mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x5000 0x1000>;
+        mediatek,gce-events = <CMDQ_EVENT_MDP_WROT0_SOF>,
+                              <CMDQ_EVENT_MDP_WROT0_EOF>;
+        power-domains = <&spm MT8183_POWER_DOMAIN_DISP>;
+        clocks = <&mmsys CLK_MM_MDP_WROT0>;
+        iommus = <&iommu>;
+        #dma-cells = <1>;
     };
diff --git a/Documentation/devicetree/bindings/mfd/samsung,exynos5433-lpass.yaml b/Documentation/devicetree/bindings/mfd/samsung,exynos5433-lpass.yaml
index b97b06848729..f154103f32cc 100644
--- a/Documentation/devicetree/bindings/mfd/samsung,exynos5433-lpass.yaml
+++ b/Documentation/devicetree/bindings/mfd/samsung,exynos5433-lpass.yaml
@@ -85,7 +85,7 @@ examples:
         };
 
         i2s@11440000 {
-            compatible = "samsung,exynos7-i2s";
+            compatible = "samsung,exynos5433-i2s", "samsung,exynos7-i2s";
             reg = <0x11440000 0x100>;
             dmas = <&adma 0>, <&adma 2>;
             dma-names = "tx", "rx";
diff --git a/Documentation/devicetree/bindings/mmc/samsung,exynos-dw-mshc.yaml b/Documentation/devicetree/bindings/mmc/samsung,exynos-dw-mshc.yaml
index 6ee78a38bd74..5fe65795f796 100644
--- a/Documentation/devicetree/bindings/mmc/samsung,exynos-dw-mshc.yaml
+++ b/Documentation/devicetree/bindings/mmc/samsung,exynos-dw-mshc.yaml
@@ -14,15 +14,22 @@ maintainers:
 
 properties:
   compatible:
-    enum:
-      - samsung,exynos4210-dw-mshc
-      - samsung,exynos4412-dw-mshc
-      - samsung,exynos5250-dw-mshc
-      - samsung,exynos5420-dw-mshc
-      - samsung,exynos5420-dw-mshc-smu
-      - samsung,exynos7-dw-mshc
-      - samsung,exynos7-dw-mshc-smu
-      - axis,artpec8-dw-mshc
+    oneOf:
+      - enum:
+          - axis,artpec8-dw-mshc
+          - samsung,exynos4210-dw-mshc
+          - samsung,exynos4412-dw-mshc
+          - samsung,exynos5250-dw-mshc
+          - samsung,exynos5420-dw-mshc
+          - samsung,exynos5420-dw-mshc-smu
+          - samsung,exynos7-dw-mshc
+          - samsung,exynos7-dw-mshc-smu
+      - items:
+          - enum:
+              - samsung,exynos5433-dw-mshc-smu
+              - samsung,exynos7885-dw-mshc-smu
+              - samsung,exynos850-dw-mshc-smu
+          - const: samsung,exynos7-dw-mshc-smu
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/mtd/partitions/u-boot.yaml b/Documentation/devicetree/bindings/mtd/partitions/u-boot.yaml
index 3c56efe48efd..327fa872c001 100644
--- a/Documentation/devicetree/bindings/mtd/partitions/u-boot.yaml
+++ b/Documentation/devicetree/bindings/mtd/partitions/u-boot.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: U-Boot bootloader partition
 
 description: |
-  U-Boot is a bootlodaer commonly used in embedded devices. It's almost always
+  U-Boot is a bootloader commonly used in embedded devices. It's almost always
   located on some kind of flash device.
 
   Device configuration is stored as a set of environment variables that are
diff --git a/Documentation/devicetree/bindings/net/dsa/dsa.yaml b/Documentation/devicetree/bindings/net/dsa/dsa.yaml
index 6107189d276a..2abd036578d1 100644
--- a/Documentation/devicetree/bindings/net/dsa/dsa.yaml
+++ b/Documentation/devicetree/bindings/net/dsa/dsa.yaml
@@ -46,4 +46,10 @@ $defs:
             $ref: dsa-port.yaml#
             unevaluatedProperties: false
 
+oneOf:
+  - required:
+      - ports
+  - required:
+      - ethernet-ports
+
 ...
diff --git a/Documentation/devicetree/bindings/net/dsa/marvell,mv88e6060.yaml b/Documentation/devicetree/bindings/net/dsa/marvell,mv88e6060.yaml
new file mode 100644
index 000000000000..4f1adf00431a
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/dsa/marvell,mv88e6060.yaml
@@ -0,0 +1,88 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/dsa/marvell,mv88e6060.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Marvell MV88E6060 DSA switch
+
+maintainers:
+  - Andrew Lunn <andrew@lunn.ch>
+
+description:
+  The Marvell MV88E6060 switch has been produced and sold by Marvell
+  since at least 2008. The switch has one pin ADDR4 that controls the
+  MDIO address of the switch to be 0x10 or 0x00, and on the MDIO bus
+  connected to the switch, the PHYs inside the switch appear as
+  independent devices on address 0x00-0x04 or 0x10-0x14, so in difference
+  from many other DSA switches this switch does not have an internal
+  MDIO bus for the PHY devices.
+
+properties:
+  compatible:
+    const: marvell,mv88e6060
+    description:
+      The MV88E6060 is the oldest Marvell DSA switch product, and
+      as such a bit limited in features compared to later hardware.
+
+  reg:
+    maxItems: 1
+
+  reset-gpios:
+    description:
+      GPIO to be used to reset the whole device
+    maxItems: 1
+
+allOf:
+  - $ref: dsa.yaml#/$defs/ethernet-ports
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+    mdio {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        ethernet-switch@16 {
+            compatible = "marvell,mv88e6060";
+            reg = <16>;
+
+            ethernet-ports {
+                #address-cells = <1>;
+                #size-cells = <0>;
+
+                ethernet-port@0 {
+                    reg = <0>;
+                    label = "lan1";
+                };
+                ethernet-port@1 {
+                    reg = <1>;
+                    label = "lan2";
+                };
+                ethernet-port@2 {
+                    reg = <2>;
+                    label = "lan3";
+                };
+                ethernet-port@3 {
+                    reg = <3>;
+                    label = "lan4";
+                };
+                ethernet-port@5 {
+                    reg = <5>;
+                    phy-mode = "rev-mii";
+                    ethernet = <&ethc>;
+                    fixed-link {
+                        speed = <100>;
+                        full-duplex;
+                    };
+                };
+            };
+        };
+    };
diff --git a/Documentation/devicetree/bindings/net/dsa/marvell,mv88e6xxx.yaml b/Documentation/devicetree/bindings/net/dsa/marvell,mv88e6xxx.yaml
new file mode 100644
index 000000000000..19f15bdd1c97
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/dsa/marvell,mv88e6xxx.yaml
@@ -0,0 +1,337 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/dsa/marvell,mv88e6xxx.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Marvell MV88E6xxx DSA switch family
+
+maintainers:
+  - Andrew Lunn <andrew@lunn.ch>
+
+description:
+  The Marvell MV88E6xxx switch series has been produced and sold
+  by Marvell since at least 2008. The switch has a few compatibles which
+  just indicate the base address of the switch, then operating systems
+  can investigate switch ID registers to find out which actual version
+  of the switch it is dealing with.
+
+properties:
+  compatible:
+    oneOf:
+      - enum:
+          - marvell,mv88e6085
+          - marvell,mv88e6190
+          - marvell,mv88e6250
+        description: |
+          marvell,mv88e6085: This switch uses base address 0x10.
+            This switch and its siblings will be autodetected from
+            ID registers found in the switch, so only "marvell,mv88e6085" should be
+            specified. This includes the following list of MV88Exxxx switches:
+            6085, 6095, 6097, 6123, 6131, 6141, 6161, 6165, 6171, 6172, 6175, 6176,
+            6185, 6240, 6320, 6321, 6341, 6350, 6351, 6352
+          marvell,mv88e6190: This switch uses base address 0x00.
+            This switch and its siblings will be autodetected from
+            ID registers found in the switch, so only "marvell,mv88e6190" should be
+            specified. This includes the following list of MV88Exxxx switches:
+            6190, 6190X, 6191, 6290, 6361, 6390, 6390X
+          marvell,mv88e6250: This switch uses base address 0x08 or 0x18.
+            This switch and its siblings will be autodetected from
+            ID registers found in the switch, so only "marvell,mv88e6250" should be
+            specified. This includes the following list of MV88Exxxx switches:
+            6220, 6250
+      - items:
+          - const: marvell,turris-mox-mv88e6085
+          - const: marvell,mv88e6085
+      - items:
+          - const: marvell,turris-mox-mv88e6190
+          - const: marvell,mv88e6190
+
+  reg:
+    maxItems: 1
+
+  eeprom-length:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description: Set to the length of an EEPROM connected to the switch. Must be
+      set if the switch can not detect the presence and/or size of a connected
+      EEPROM, otherwise optional.
+
+  reset-gpios:
+    description:
+      GPIO to be used to reset the whole device
+    maxItems: 1
+
+  interrupts:
+    description: The switch provides an external interrupt line, but it is
+      not always used by target systems.
+    maxItems: 1
+
+  interrupt-controller:
+    description: The switch has an internal interrupt controller used by
+      the different sub-blocks.
+
+  '#interrupt-cells':
+    description: The internal interrupt controller only supports triggering
+      on active high level interrupts so the second cell must alway be set to
+      IRQ_TYPE_LEVEL_HIGH.
+    const: 2
+
+  mdio:
+    $ref: /schemas/net/mdio.yaml#
+    unevaluatedProperties: false
+    description: Marvell MV88E6xxx switches have an varying combination of
+      internal and external MDIO buses, in some cases a combined bus that
+      can be used both internally and externally. This node is for the
+      primary bus, used internally and sometimes also externally.
+
+  mdio-external:
+    $ref: /schemas/net/mdio.yaml#
+    unevaluatedProperties: false
+    description: Marvell MV88E6xxx switches that have a separate external
+      MDIO bus use this port to access external components on the MDIO bus.
+
+    properties:
+      compatible:
+        const: marvell,mv88e6xxx-mdio-external
+
+    required:
+      - compatible
+
+allOf:
+  - $ref: dsa.yaml#/$defs/ethernet-ports
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    mdio {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        ethernet-switch@0 {
+            compatible = "marvell,mv88e6085";
+            reg = <0>;
+            reset-gpios = <&gpio5 1 GPIO_ACTIVE_LOW>;
+
+            mdio {
+                #address-cells = <1>;
+                #size-cells = <0>;
+
+                sw_phy0: ethernet-phy@0 {
+                    reg = <0x0>;
+                };
+
+                sw_phy1: ethernet-phy@1 {
+                    reg = <0x1>;
+                };
+
+                sw_phy2: ethernet-phy@2 {
+                    reg = <0x2>;
+                };
+
+                sw_phy3: ethernet-phy@3 {
+                    reg = <0x3>;
+                };
+            };
+
+            ethernet-ports {
+                #address-cells = <1>;
+                #size-cells = <0>;
+
+                ethernet-port@0 {
+                    reg = <0>;
+                    label = "lan4";
+                    phy-handle = <&sw_phy0>;
+                    phy-mode = "internal";
+                };
+
+                ethernet-port@1 {
+                    reg = <1>;
+                    label = "lan3";
+                    phy-handle = <&sw_phy1>;
+                    phy-mode = "internal";
+                };
+
+                ethernet-port@2 {
+                    reg = <2>;
+                    label = "lan2";
+                    phy-handle = <&sw_phy2>;
+                    phy-mode = "internal";
+                };
+
+                ethernet-port@3 {
+                    reg = <3>;
+                    label = "lan1";
+                    phy-handle = <&sw_phy3>;
+                    phy-mode = "internal";
+                };
+
+                ethernet-port@5 {
+                    reg = <5>;
+                    ethernet = <&fec>;
+                    phy-mode = "rgmii-id";
+
+                    fixed-link {
+                        speed = <1000>;
+                        full-duplex;
+                    };
+                };
+            };
+        };
+    };
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    mdio {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        ethernet-switch@0 {
+            compatible = "marvell,mv88e6190";
+            #interrupt-cells = <2>;
+            interrupt-controller;
+            interrupt-parent = <&gpio1>;
+            interrupts = <7 IRQ_TYPE_LEVEL_LOW>;
+            pinctrl-0 = <&switch_interrupt_pins>;
+            pinctrl-names = "default";
+            reg = <0>;
+
+            mdio {
+                #address-cells = <1>;
+                #size-cells = <0>;
+
+                switch0phy1: ethernet-phy@1 {
+                    reg = <0x1>;
+                };
+
+                switch0phy2: ethernet-phy@2 {
+                    reg = <0x2>;
+                };
+
+                switch0phy3: ethernet-phy@3 {
+                    reg = <0x3>;
+                };
+
+                switch0phy4: ethernet-phy@4 {
+                    reg = <0x4>;
+                };
+
+                switch0phy5: ethernet-phy@5 {
+                    reg = <0x5>;
+                };
+
+                switch0phy6: ethernet-phy@6 {
+                    reg = <0x6>;
+                };
+
+                switch0phy7: ethernet-phy@7 {
+                    reg = <0x7>;
+                };
+
+                switch0phy8: ethernet-phy@8 {
+                    reg = <0x8>;
+                };
+            };
+
+            mdio-external {
+                compatible = "marvell,mv88e6xxx-mdio-external";
+                #address-cells = <1>;
+                #size-cells = <0>;
+
+                phy1: ethernet-phy@b {
+                    reg = <0xb>;
+                    compatible = "ethernet-phy-ieee802.3-c45";
+                };
+
+                phy2: ethernet-phy@c {
+                    reg = <0xc>;
+                    compatible = "ethernet-phy-ieee802.3-c45";
+                };
+            };
+
+            ethernet-ports {
+                #address-cells = <1>;
+                #size-cells = <0>;
+
+                ethernet-port@0 {
+                    ethernet = <&eth0>;
+                    phy-mode = "rgmii";
+                    reg = <0>;
+
+                    fixed-link {
+                        full-duplex;
+                        pause;
+                        speed = <1000>;
+                    };
+                };
+
+                ethernet-port@1 {
+                    label = "lan1";
+                    phy-handle = <&switch0phy1>;
+                    reg = <1>;
+                };
+
+                ethernet-port@2 {
+                    label = "lan2";
+                    phy-handle = <&switch0phy2>;
+                    reg = <2>;
+                };
+
+                ethernet-port@3 {
+                    label = "lan3";
+                    phy-handle = <&switch0phy3>;
+                    reg = <3>;
+                };
+
+                ethernet-port@4 {
+                    label = "lan4";
+                    phy-handle = <&switch0phy4>;
+                    reg = <4>;
+                };
+
+                ethernet-port@5 {
+                    label = "lan5";
+                    phy-handle = <&switch0phy5>;
+                    reg = <5>;
+                };
+
+                ethernet-port@6 {
+                    label = "lan6";
+                    phy-handle = <&switch0phy6>;
+                    reg = <6>;
+                };
+
+                ethernet-port@7 {
+                    label = "lan7";
+                    phy-handle = <&switch0phy7>;
+                    reg = <7>;
+                };
+
+                ethernet-port@8 {
+                    label = "lan8";
+                    phy-handle = <&switch0phy8>;
+                    reg = <8>;
+                };
+
+                ethernet-port@9 {
+                    /* 88X3310P external phy */
+                    label = "lan9";
+                    phy-handle = <&phy1>;
+                    phy-mode = "xaui";
+                    reg = <9>;
+                };
+
+                ethernet-port@a {
+                    /* 88X3310P external phy */
+                    label = "lan10";
+                    phy-handle = <&phy2>;
+                    phy-mode = "xaui";
+                    reg = <0xa>;
+                };
+            };
+        };
+    };
diff --git a/Documentation/devicetree/bindings/net/dsa/marvell.txt b/Documentation/devicetree/bindings/net/dsa/marvell.txt
deleted file mode 100644
index 6ec0c181b6db..000000000000
--- a/Documentation/devicetree/bindings/net/dsa/marvell.txt
+++ /dev/null
@@ -1,109 +0,0 @@
-Marvell DSA Switch Device Tree Bindings
----------------------------------------
-
-WARNING: This binding is currently unstable. Do not program it into a
-FLASH never to be changed again. Once this binding is stable, this
-warning will be removed.
-
-If you need a stable binding, use the old dsa.txt binding.
-
-Marvell Switches are MDIO devices. The following properties should be
-placed as a child node of an mdio device.
-
-The properties described here are those specific to Marvell devices.
-Additional required and optional properties can be found in dsa.txt.
-
-The compatibility string is used only to find an identification register,
-which is at a different MDIO base address in different switch families.
-- "marvell,mv88e6085"	: Switch has base address 0x10. Use with models:
-			  6085, 6095, 6097, 6123, 6131, 6141, 6161, 6165,
-			  6171, 6172, 6175, 6176, 6185, 6240, 6320, 6321,
-			  6341, 6350, 6351, 6352
-- "marvell,mv88e6190"	: Switch has base address 0x00. Use with models:
-			  6190, 6190X, 6191, 6290, 6361, 6390, 6390X
-- "marvell,mv88e6250"	: Switch has base address 0x08 or 0x18. Use with model:
-			  6220, 6250
-
-Required properties:
-- compatible		: Should be one of "marvell,mv88e6085",
-			  "marvell,mv88e6190" or "marvell,mv88e6250" as
-			  indicated above
-- reg			: Address on the MII bus for the switch.
-
-Optional properties:
-
-- reset-gpios		: Should be a gpio specifier for a reset line
-- interrupts		: Interrupt from the switch
-- interrupt-controller	: Indicates the switch is itself an interrupt
-			  controller. This is used for the PHY interrupts.
-#interrupt-cells = <2>	: Controller uses two cells, number and flag
-- eeprom-length		: Set to the length of an EEPROM connected to the
-			  switch. Must be set if the switch can not detect
-			  the presence and/or size of a connected EEPROM,
-			  otherwise optional.
-- mdio			: Container of PHY and devices on the switches MDIO
-			  bus.
-- mdio?		: Container of PHYs and devices on the external MDIO
-			  bus. The node must contains a compatible string of
-			  "marvell,mv88e6xxx-mdio-external"
-
-Example:
-
-	mdio {
-		#address-cells = <1>;
-		#size-cells = <0>;
-		interrupt-parent = <&gpio0>;
-		interrupts = <27 IRQ_TYPE_LEVEL_LOW>;
-		interrupt-controller;
-		#interrupt-cells = <2>;
-
-		switch0: switch@0 {
-			compatible = "marvell,mv88e6085";
-			reg = <0>;
-			reset-gpios = <&gpio5 1 GPIO_ACTIVE_LOW>;
-
-			mdio {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				switch1phy0: switch1phy0@0 {
-					reg = <0>;
-					interrupt-parent = <&switch0>;
-					interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
-				};
-			};
-		};
-	};
-
-	mdio {
-		#address-cells = <1>;
-		#size-cells = <0>;
-		interrupt-parent = <&gpio0>;
-		interrupts = <27 IRQ_TYPE_LEVEL_LOW>;
-		interrupt-controller;
-		#interrupt-cells = <2>;
-
-		switch0: switch@0 {
-			compatible = "marvell,mv88e6190";
-			reg = <0>;
-			reset-gpios = <&gpio5 1 GPIO_ACTIVE_LOW>;
-
-			mdio {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				switch1phy0: switch1phy0@0 {
-					reg = <0>;
-					interrupt-parent = <&switch0>;
-					interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
-				};
-			};
-
-			mdio1 {
-				compatible = "marvell,mv88e6xxx-mdio-external";
-				#address-cells = <1>;
-				#size-cells = <0>;
-				switch1phy9: switch1phy0@9 {
-					reg = <9>;
-				};
-			};
-		};
-	};
diff --git a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml
index b3029c64d0d5..c963dc09e8e1 100644
--- a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml
+++ b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml
@@ -11,7 +11,6 @@ maintainers:
   - Woojung Huh <Woojung.Huh@microchip.com>
 
 allOf:
-  - $ref: dsa.yaml#/$defs/ethernet-ports
   - $ref: /schemas/spi/spi-peripheral-props.yaml#
 
 properties:
@@ -78,6 +77,39 @@ required:
   - compatible
   - reg
 
+if:
+  not:
+    properties:
+      compatible:
+        enum:
+          - microchip,ksz8863
+          - microchip,ksz8873
+then:
+  $ref: dsa.yaml#/$defs/ethernet-ports
+else:
+  patternProperties:
+    "^(ethernet-)?ports$":
+      patternProperties:
+        "^(ethernet-)?port@[0-2]$":
+          $ref: dsa-port.yaml#
+          unevaluatedProperties: false
+          properties:
+            microchip,rmii-clk-internal:
+              $ref: /schemas/types.yaml#/definitions/flag
+              description:
+                When ksz88x3 is acting as clock provier (via REFCLKO) it
+                can select between internal and external RMII reference
+                clock. Internal reference clock means that the clock for
+                the RMII of ksz88x3 is provided by the ksz88x3 internally
+                and the REFCLKI pin is unconnected. For the external
+                reference clock, the clock needs to be fed back to ksz88x3
+                via REFCLKI.
+                If microchip,rmii-clk-internal is set, ksz88x3 will provide
+                rmii reference clock internally, otherwise reference clock
+                should be provided externally.
+          dependencies:
+            microchip,rmii-clk-internal: [ethernet]
+
 unevaluatedProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
index 9f6a5ccbcefe..d14d123ad7a0 100644
--- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
@@ -275,12 +275,12 @@ allOf:
       properties:
         rx-internal-delay-ps:
           description:
-            RGMII Receive Clock Delay defined in pico seconds.This is used for
+            RGMII Receive Clock Delay defined in pico seconds. This is used for
             controllers that have configurable RX internal delays. If this
             property is present then the MAC applies the RX delay.
         tx-internal-delay-ps:
           description:
-            RGMII Transmit Clock Delay defined in pico seconds.This is used for
+            RGMII Transmit Clock Delay defined in pico seconds. This is used for
             controllers that have configurable TX internal delays. If this
             property is present then the MAC applies the TX delay.
 
diff --git a/Documentation/devicetree/bindings/net/ethernet-switch.yaml b/Documentation/devicetree/bindings/net/ethernet-switch.yaml
index 72ac67ca3415..b3b7e1a1b127 100644
--- a/Documentation/devicetree/bindings/net/ethernet-switch.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-switch.yaml
@@ -20,9 +20,26 @@ description:
 
 select: false
 
-properties:
-  $nodename:
-    pattern: "^(ethernet-)?switch(@.*)?$"
+allOf:
+  # This condition is here to satisfy the case where certain device
+  # nodes have to preserve non-standard names because of
+  # backward-compatibility with boot loaders inspecting certain
+  # node names.
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - marvell,turris-mox-mv88e6085
+              - marvell,turris-mox-mv88e6190
+    then:
+      properties:
+        $nodename:
+          pattern: "switch[0-3]@[0-3]+$"
+    else:
+      properties:
+        $nodename:
+          pattern: "^(ethernet-)?switch(@.*)?$"
 
 patternProperties:
   "^(ethernet-)?ports$":
diff --git a/Documentation/devicetree/bindings/net/lantiq,pef2256.yaml b/Documentation/devicetree/bindings/net/lantiq,pef2256.yaml
new file mode 100644
index 000000000000..7da8370e2468
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/lantiq,pef2256.yaml
@@ -0,0 +1,213 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/lantiq,pef2256.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Lantiq PEF2256
+
+maintainers:
+  - Herve Codina <herve.codina@bootlin.com>
+
+description:
+  The Lantiq PEF2256, also known as Infineon PEF2256 or FALC56, is a framer and
+  line interface component designed to fulfill all required interfacing between
+  an analog E1/T1/J1 line and the digital PCM system highway/H.100 bus.
+
+properties:
+  compatible:
+    items:
+      - const: lantiq,pef2256
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: Master Clock
+      - description: System Clock Receive
+      - description: System Clock Transmit
+
+  clock-names:
+    items:
+      - const: mclk
+      - const: sclkr
+      - const: sclkx
+
+  interrupts:
+    maxItems: 1
+
+  reset-gpios:
+    description:
+      GPIO used to reset the device.
+    maxItems: 1
+
+  pinctrl:
+    $ref: /schemas/pinctrl/pinctrl.yaml#
+    additionalProperties: false
+
+    patternProperties:
+      '-pins$':
+        type: object
+        $ref: /schemas/pinctrl/pinmux-node.yaml#
+        additionalProperties: false
+
+        properties:
+          pins:
+            enum: [ RPA, RPB, RPC, RPD, XPA, XPB, XPC, XPD ]
+
+          function:
+            enum: [ SYPR, RFM, RFMB, RSIGM, RSIG, DLR, FREEZE, RFSP, LOS,
+                    SYPX, XFMS, XSIG, TCLK, XMFB, XSIGM, DLX, XCLK, XLT,
+                    GPI, GPOH, GPOL ]
+
+        required:
+          - pins
+          - function
+
+  lantiq,data-rate-bps:
+    enum: [2048000, 4096000, 8192000, 16384000]
+    default: 2048000
+    description:
+      Data rate (bit per seconds) on the system highway.
+
+  lantiq,clock-falling-edge:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description:
+      Data is sent on falling edge of the clock (and received on the rising
+      edge). If 'clock-falling-edge' is not present, data is sent on the
+      rising edge (and received on the falling edge).
+
+  lantiq,channel-phase:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum: [0, 1, 2, 3, 4, 5, 6, 7]
+    default: 0
+    description: |
+      The pef2256 delivers a full frame (32 8-bit time-slots in E1 and 24 8-bit
+      time-slots 8 8-bit signaling in E1/J1) every 125us. This lead to a data
+      rate of 2048000 bit/s. When lantiq,data-rate-bps is more than 2048000
+      bit/s, the data (all 32 8-bit) present in the frame are interleave with
+      unused time-slots. The lantiq,channel-phase property allows to set the
+      correct alignment of the interleave mechanism.
+      For instance, suppose lantiq,data-rate-bps = 8192000 (ie 4*2048000), and
+      lantiq,channel-phase = 2, the interleave schema with unused time-slots
+      (nu) and used time-slots (XX) for TSi is
+        nu nu XX nu nu nu XX nu nu nu XX nu
+        <-- TSi --> <- TSi+1 -> <- TSi+2 ->
+      With lantiq,data-rate-bps = 8192000, and lantiq,channel-phase = 1, the
+      interleave schema is
+        nu XX nu nu nu XX nu nu nu XX nu nu
+        <-- TSi --> <- TSi+1 -> <- TSi+2 ->
+      With lantiq,data-rate-bps = 4096000 (ie 2*2048000), and
+      lantiq,channel-phase = 1, the interleave schema is
+        nu    XX    nu    XX    nu    XX
+        <-- TSi --> <- TSi+1 -> <- TSi+2 ->
+
+patternProperties:
+  '^codec(-([0-9]|[1-2][0-9]|3[0-1]))?$':
+    type: object
+    $ref: /schemas/sound/dai-common.yaml
+    unevaluatedProperties: false
+    description:
+      Codec provided by the pef2256. This codec allows to use some of the PCM
+      system highway time-slots as audio channels to transport audio data over
+      the E1/T1/J1 lines.
+      The time-slots used by the codec must be set and so, the properties
+      'dai-tdm-slot-num', 'dai-tdm-slot-width', 'dai-tdm-slot-tx-mask' and
+      'dai-tdm-slot-rx-mask' must be present in the sound card node for
+      sub-nodes that involve the codec. The codec uses 8-bit time-slots.
+      'dai-tdm-tdm-slot-with' must be set to 8.
+      The tx and rx masks define the pef2256 time-slots assigned to the codec.
+
+    properties:
+      compatible:
+        const: lantiq,pef2256-codec
+
+      '#sound-dai-cells':
+        const: 0
+
+    required:
+      - compatible
+      - '#sound-dai-cells'
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - interrupts
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    pef2256: framer@2000000 {
+      compatible = "lantiq,pef2256";
+      reg = <0x2000000 0x100>;
+      interrupts = <8 IRQ_TYPE_LEVEL_LOW>;
+      interrupt-parent = <&intc>;
+      clocks = <&clk_mclk>, <&clk_sclkr>, <&clk_sclkx>;
+      clock-names = "mclk", "sclkr", "sclkx";
+      reset-gpios = <&gpio 11 GPIO_ACTIVE_LOW>;
+      lantiq,data-rate-bps = <4096000>;
+
+      pinctrl {
+        pef2256_rpa_sypr: rpa-pins {
+          pins = "RPA";
+          function = "SYPR";
+        };
+        pef2256_xpa_sypx: xpa-pins {
+          pins = "XPA";
+          function = "SYPX";
+        };
+      };
+
+      pef2256_codec0: codec-0 {
+        compatible = "lantiq,pef2256-codec";
+        #sound-dai-cells = <0>;
+        sound-name-prefix = "PEF2256_0";
+      };
+
+      pef2256_codec1: codec-1 {
+        compatible = "lantiq,pef2256-codec";
+        #sound-dai-cells = <0>;
+        sound-name-prefix = "PEF2256_1";
+      };
+    };
+
+    sound {
+      compatible = "simple-audio-card";
+      #address-cells = <1>;
+      #size-cells = <0>;
+      simple-audio-card,dai-link@0 { /* CPU DAI1 - pef2256 codec 1 */
+        reg = <0>;
+        cpu {
+          sound-dai = <&cpu_dai1>;
+        };
+        codec {
+          sound-dai = <&pef2256_codec0>;
+          dai-tdm-slot-num = <4>;
+          dai-tdm-slot-width = <8>;
+          /* TS 1, 2, 3, 4 */
+          dai-tdm-slot-tx-mask = <0 1 1 1 1>;
+          dai-tdm-slot-rx-mask = <0 1 1 1 1>;
+        };
+      };
+      simple-audio-card,dai-link@1 { /* CPU DAI2 - pef2256 codec 2 */
+        reg = <1>;
+        cpu {
+          sound-dai = <&cpu_dai2>;
+        };
+        codec {
+          sound-dai = <&pef2256_codec1>;
+          dai-tdm-slot-num = <4>;
+          dai-tdm-slot-width = <8>;
+          /* TS 5, 6, 7, 8 */
+          dai-tdm-slot-tx-mask = <0 0 0 0 0 1 1 1 1>;
+          dai-tdm-slot-rx-mask = <0 0 0 0 0 1 1 1 1>;
+        };
+      };
+    };
diff --git a/Documentation/devicetree/bindings/net/marvell,aquantia.yaml b/Documentation/devicetree/bindings/net/marvell,aquantia.yaml
new file mode 100644
index 000000000000..9854fab4c4db
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/marvell,aquantia.yaml
@@ -0,0 +1,116 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/marvell,aquantia.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Marvell Aquantia Ethernet PHY
+
+maintainers:
+  - Christian Marangi <ansuelsmth@gmail.com>
+
+description: |
+  Marvell Aquantia Ethernet PHY require a firmware to be loaded to actually
+  work.
+
+  This can be done and is implemented by OEM in 3 different way:
+    - Attached SPI flash directly to the PHY with the firmware. The PHY
+      will self load the firmware in the presence of this configuration.
+    - Read from a dedicated partition on system NAND declared in an
+      NVMEM cell, and loaded to the PHY using its mailbox interface.
+    - Manually provided firmware loaded from a file in the filesystem.
+
+allOf:
+  - $ref: ethernet-phy.yaml#
+
+select:
+  properties:
+    compatible:
+      contains:
+        enum:
+          - ethernet-phy-id03a1.b445
+          - ethernet-phy-id03a1.b460
+          - ethernet-phy-id03a1.b4a2
+          - ethernet-phy-id03a1.b4d0
+          - ethernet-phy-id03a1.b4e0
+          - ethernet-phy-id03a1.b5c2
+          - ethernet-phy-id03a1.b4b0
+          - ethernet-phy-id03a1.b662
+          - ethernet-phy-id03a1.b712
+          - ethernet-phy-id31c3.1c12
+  required:
+    - compatible
+
+properties:
+  reg:
+    maxItems: 1
+
+  firmware-name:
+    description: specify the name of PHY firmware to load
+
+  nvmem-cells:
+    description: phandle to the firmware nvmem cell
+    maxItems: 1
+
+  nvmem-cell-names:
+    const: firmware
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    mdio {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        ethernet-phy@0 {
+            compatible = "ethernet-phy-id31c3.1c12",
+                         "ethernet-phy-ieee802.3-c45";
+
+            reg = <0>;
+            firmware-name = "AQR-G4_v5.4.C-AQR_CIG_WF-1945_0x8_ID44776_VER1630.cld";
+        };
+
+        ethernet-phy@1 {
+            compatible = "ethernet-phy-id31c3.1c12",
+                         "ethernet-phy-ieee802.3-c45";
+
+            reg = <1>;
+            nvmem-cells = <&aqr_fw>;
+            nvmem-cell-names = "firmware";
+        };
+    };
+
+    flash {
+        compatible = "jedec,spi-nor";
+        #address-cells = <1>;
+        #size-cells = <1>;
+
+        partitions {
+            compatible = "fixed-partitions";
+            #address-cells = <1>;
+            #size-cells = <1>;
+
+            /* ... */
+
+            partition@650000 {
+                compatible = "nvmem-cells";
+                label = "0:ethphyfw";
+                reg = <0x650000 0x80000>;
+                read-only;
+                #address-cells = <1>;
+                #size-cells = <1>;
+
+                aqr_fw: aqr_fw@0 {
+                    reg = <0x0 0x5f42a>;
+                };
+            };
+
+            /* ... */
+
+        };
+    };
diff --git a/Documentation/devicetree/bindings/net/marvell,mvusb.yaml b/Documentation/devicetree/bindings/net/marvell,mvusb.yaml
index 3a3325168048..ab838c1ffeed 100644
--- a/Documentation/devicetree/bindings/net/marvell,mvusb.yaml
+++ b/Documentation/devicetree/bindings/net/marvell,mvusb.yaml
@@ -50,11 +50,14 @@ examples:
                     #address-cells = <1>;
                     #size-cells = <0>;
 
-                    switch@0 {
+                    ethernet-switch@0 {
                             compatible = "marvell,mv88e6190";
                             reg = <0x0>;
 
-                            ports {
+                            ethernet-ports {
+                                    #address-cells = <1>;
+                                    #size-cells = <0>;
+
                                     /* Port definitions */
                             };
 
diff --git a/Documentation/devicetree/bindings/net/marvell,orion-mdio.yaml b/Documentation/devicetree/bindings/net/marvell,orion-mdio.yaml
index e35da8b01dc2..73429855d584 100644
--- a/Documentation/devicetree/bindings/net/marvell,orion-mdio.yaml
+++ b/Documentation/devicetree/bindings/net/marvell,orion-mdio.yaml
@@ -39,28 +39,6 @@ required:
 allOf:
   - $ref: mdio.yaml#
 
-  - if:
-      required:
-        - interrupts
-
-    then:
-      properties:
-        reg:
-          items:
-            - items:
-                - $ref: /schemas/types.yaml#/definitions/cell
-                - const: 0x84
-
-    else:
-      properties:
-        reg:
-          items:
-            - items:
-                - $ref: /schemas/types.yaml#/definitions/cell
-                - enum:
-                    - 0x4
-                    - 0x10
-
 unevaluatedProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/net/qcom,ipa.yaml b/Documentation/devicetree/bindings/net/qcom,ipa.yaml
index 2d5e4ffb2f9e..c30218684cfe 100644
--- a/Documentation/devicetree/bindings/net/qcom,ipa.yaml
+++ b/Documentation/devicetree/bindings/net/qcom,ipa.yaml
@@ -43,15 +43,21 @@ description:
 
 properties:
   compatible:
-    enum:
-      - qcom,msm8998-ipa
-      - qcom,sc7180-ipa
-      - qcom,sc7280-ipa
-      - qcom,sdm845-ipa
-      - qcom,sdx55-ipa
-      - qcom,sdx65-ipa
-      - qcom,sm6350-ipa
-      - qcom,sm8350-ipa
+    oneOf:
+      - enum:
+          - qcom,msm8998-ipa
+          - qcom,sc7180-ipa
+          - qcom,sc7280-ipa
+          - qcom,sdm845-ipa
+          - qcom,sdx55-ipa
+          - qcom,sdx65-ipa
+          - qcom,sm6350-ipa
+          - qcom,sm8350-ipa
+          - qcom,sm8550-ipa
+      - items:
+          - enum:
+              - qcom,sm8650-ipa
+          - const: qcom,sm8550-ipa
 
   reg:
     items:
diff --git a/Documentation/devicetree/bindings/net/renesas,etheravb.yaml b/Documentation/devicetree/bindings/net/renesas,etheravb.yaml
index 5d074f27d462..890f7858d0dc 100644
--- a/Documentation/devicetree/bindings/net/renesas,etheravb.yaml
+++ b/Documentation/devicetree/bindings/net/renesas,etheravb.yaml
@@ -55,9 +55,10 @@ properties:
 
       - items:
           - enum:
-              - renesas,r9a07g043-gbeth # RZ/G2UL
+              - renesas,r9a07g043-gbeth # RZ/G2UL and RZ/Five
               - renesas,r9a07g044-gbeth # RZ/G2{L,LC}
               - renesas,r9a07g054-gbeth # RZ/V2L
+              - renesas,r9a08g045-gbeth # RZ/G3S
           - const: renesas,rzg2l-gbeth  # RZ/{G2L,G2UL,V2L} family
 
   reg: true
diff --git a/Documentation/devicetree/bindings/net/renesas,ethertsn.yaml b/Documentation/devicetree/bindings/net/renesas,ethertsn.yaml
new file mode 100644
index 000000000000..475aff7714d6
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/renesas,ethertsn.yaml
@@ -0,0 +1,133 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/renesas,ethertsn.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Renesas Ethernet TSN End-station
+
+maintainers:
+  - Niklas Söderlund <niklas.soderlund@ragnatech.se>
+
+description:
+  The RTSN device provides Ethernet network using a 10 Mbps, 100 Mbps, or 1
+  Gbps full-duplex link via MII/GMII/RMII/RGMII. Depending on the connected PHY.
+
+allOf:
+  - $ref: ethernet-controller.yaml#
+
+properties:
+  compatible:
+    items:
+      - enum:
+          - renesas,r8a779g0-ethertsn       # R-Car V4H
+      - const: renesas,rcar-gen4-ethertsn
+
+  reg:
+    items:
+      - description: TSN End Station target
+      - description: generalized Precision Time Protocol target
+
+  reg-names:
+    items:
+      - const: tsnes
+      - const: gptp
+
+  interrupts:
+    items:
+      - description: TX data interrupt
+      - description: RX data interrupt
+
+  interrupt-names:
+    items:
+      - const: tx
+      - const: rx
+
+  clocks:
+    maxItems: 1
+
+  power-domains:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+  phy-mode:
+    contains:
+      enum:
+        - mii
+        - rgmii
+
+  phy-handle:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description:
+      Specifies a reference to a node representing a PHY device.
+
+  rx-internal-delay-ps:
+    enum: [0, 1800]
+
+  tx-internal-delay-ps:
+    enum: [0, 2000]
+
+  '#address-cells':
+    const: 1
+
+  '#size-cells':
+    const: 0
+
+patternProperties:
+  "^ethernet-phy@[0-9a-f]$":
+    type: object
+    $ref: ethernet-phy.yaml#
+    unevaluatedProperties: false
+
+required:
+  - compatible
+  - reg
+  - reg-names
+  - interrupts
+  - interrupt-names
+  - clocks
+  - power-domains
+  - resets
+  - phy-mode
+  - phy-handle
+  - '#address-cells'
+  - '#size-cells'
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/r8a779g0-cpg-mssr.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/power/r8a779g0-sysc.h>
+    #include <dt-bindings/gpio/gpio.h>
+
+    tsn0: ethernet@e6460000 {
+        compatible = "renesas,r8a779g0-ethertsn", "renesas,rcar-gen4-ethertsn";
+        reg = <0xe6460000 0x7000>,
+              <0xe6449000 0x500>;
+        reg-names = "tsnes", "gptp";
+        interrupts = <GIC_SPI 429 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 430 IRQ_TYPE_LEVEL_HIGH>;
+        interrupt-names = "tx", "rx";
+        clocks = <&cpg CPG_MOD 2723>;
+        power-domains = <&sysc R8A779G0_PD_ALWAYS_ON>;
+        resets = <&cpg 2723>;
+
+        phy-mode = "rgmii";
+        tx-internal-delay-ps = <2000>;
+        phy-handle = <&phy3>;
+
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        phy3: ethernet-phy@3 {
+            compatible = "ethernet-phy-ieee802.3-c45";
+            reg = <0>;
+            interrupt-parent = <&gpio4>;
+            interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
+            reset-gpios = <&gpio1 23 GPIO_ACTIVE_LOW>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/net/xlnx,axi-ethernet.yaml b/Documentation/devicetree/bindings/net/xlnx,axi-ethernet.yaml
index 1d33d80af11c..bbe89ea9590c 100644
--- a/Documentation/devicetree/bindings/net/xlnx,axi-ethernet.yaml
+++ b/Documentation/devicetree/bindings/net/xlnx,axi-ethernet.yaml
@@ -122,6 +122,20 @@ properties:
       and "phy-handle" should point to an external PHY if exists.
     maxItems: 1
 
+  dmas:
+    minItems: 2
+    maxItems: 32
+    description: TX and RX DMA channel phandle
+
+  dma-names:
+    items:
+      pattern: "^[tr]x_chan([0-9]|1[0-5])$"
+    description:
+      Should be "tx_chan0", "tx_chan1" ... "tx_chan15" for DMA Tx channel
+      Should be "rx_chan0", "rx_chan1" ... "rx_chan15" for DMA Rx channel
+    minItems: 2
+    maxItems: 32
+
 required:
   - compatible
   - interrupts
@@ -143,6 +157,8 @@ examples:
         clocks = <&axi_clk>, <&axi_clk>, <&pl_enet_ref_clk>, <&mgt_clk>;
         phy-mode = "mii";
         reg = <0x40c00000 0x40000>,<0x50c00000 0x40000>;
+        dmas = <&xilinx_dma 0>, <&xilinx_dma 1>;
+        dma-names = "tx_chan0", "rx_chan0";
         xlnx,rxcsum = <0x2>;
         xlnx,rxmem = <0x800>;
         xlnx,txcsum = <0x2>;
diff --git a/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml b/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml
index f43186f98607..d9287be89877 100644
--- a/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml
+++ b/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml
@@ -15,9 +15,11 @@ allOf:
 
 properties:
   compatible:
-    enum:
-      - fsl,imx23-ocotp
-      - fsl,imx28-ocotp
+    items:
+      - enum:
+          - fsl,imx23-ocotp
+          - fsl,imx28-ocotp
+      - const: fsl,ocotp
 
   reg:
     maxItems: 1
@@ -35,7 +37,7 @@ unevaluatedProperties: false
 examples:
   - |
     ocotp: efuse@8002c000 {
-        compatible = "fsl,imx28-ocotp";
+        compatible = "fsl,imx28-ocotp", "fsl,ocotp";
         #address-cells = <1>;
         #size-cells = <1>;
         reg = <0x8002c000 0x2000>;
diff --git a/Documentation/devicetree/bindings/perf/fsl-imx-ddr.yaml b/Documentation/devicetree/bindings/perf/fsl-imx-ddr.yaml
index e9fad4b3de68..6c96a4204e5d 100644
--- a/Documentation/devicetree/bindings/perf/fsl-imx-ddr.yaml
+++ b/Documentation/devicetree/bindings/perf/fsl-imx-ddr.yaml
@@ -27,6 +27,9 @@ properties:
               - fsl,imx8mq-ddr-pmu
               - fsl,imx8mp-ddr-pmu
           - const: fsl,imx8m-ddr-pmu
+      - items:
+          - const: fsl,imx8dxl-ddr-pmu
+          - const: fsl,imx8-ddr-pmu
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/perf/riscv,pmu.yaml b/Documentation/devicetree/bindings/perf/riscv,pmu.yaml
index c8448de2f2a0..d01c677ad3c7 100644
--- a/Documentation/devicetree/bindings/perf/riscv,pmu.yaml
+++ b/Documentation/devicetree/bindings/perf/riscv,pmu.yaml
@@ -90,7 +90,7 @@ properties:
             bitmap of all MHPMCOUNTERx that can monitor the range of events
 
 dependencies:
-  "riscv,event-to-mhpmevent": [ "riscv,event-to-mhpmcounters" ]
+  riscv,event-to-mhpmevent: [ "riscv,event-to-mhpmcounters" ]
 
 required:
   - compatible
diff --git a/Documentation/devicetree/bindings/pinctrl/nxp,s32g2-siul2-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/nxp,s32g2-siul2-pinctrl.yaml
index d49aafd8c5f4..a24286e4def6 100644
--- a/Documentation/devicetree/bindings/pinctrl/nxp,s32g2-siul2-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/nxp,s32g2-siul2-pinctrl.yaml
@@ -9,7 +9,7 @@ title: NXP S32G2 pin controller
 
 maintainers:
   - Ghennadi Procopciuc <Ghennadi.Procopciuc@oss.nxp.com>
-  - Chester Lin <clin@suse.com>
+  - Chester Lin <chester62515@gmail.com>
 
 description: |
   S32G2 pinmux is implemented in SIUL2 (System Integration Unit Lite2),
diff --git a/Documentation/devicetree/bindings/pwm/imx-pwm.yaml b/Documentation/devicetree/bindings/pwm/imx-pwm.yaml
index c01dff3b7f84..a84a240a61dc 100644
--- a/Documentation/devicetree/bindings/pwm/imx-pwm.yaml
+++ b/Documentation/devicetree/bindings/pwm/imx-pwm.yaml
@@ -14,12 +14,10 @@ allOf:
 
 properties:
   "#pwm-cells":
-    description: |
-      Should be 2 for i.MX1 and 3 for i.MX27 and newer SoCs. See pwm.yaml
-      in this directory for a description of the cells format.
-    enum:
-      - 2
-      - 3
+    description:
+      The only third cell flag supported by this binding is
+      PWM_POLARITY_INVERTED. fsl,imx1-pwm does not support this flags.
+    const: 3
 
   compatible:
     oneOf:
diff --git a/Documentation/devicetree/bindings/pwm/pwm-samsung.yaml b/Documentation/devicetree/bindings/pwm/pwm-samsung.yaml
index 2162f661ed5a..17a2b927af33 100644
--- a/Documentation/devicetree/bindings/pwm/pwm-samsung.yaml
+++ b/Documentation/devicetree/bindings/pwm/pwm-samsung.yaml
@@ -29,7 +29,11 @@ properties:
           - samsung,exynos4210-pwm          # 32-bit, Exynos
       - items:
           - enum:
+              - samsung,exynos5433-pwm
+              - samsung,exynos7-pwm
               - samsung,exynosautov9-pwm
+              - samsung,exynosautov920-pwm
+              - tesla,fsd-pwm
           - const: samsung,exynos4210-pwm
 
   reg:
diff --git a/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml b/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml
index ce7751b9129c..9ff9abf2691a 100644
--- a/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml
@@ -105,6 +105,8 @@ properties:
     description:
       Interrupt signaling a critical under-voltage event.
 
+  system-critical-regulator: true
+
 required:
   - compatible
   - regulator-name
diff --git a/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.yaml b/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.yaml
index acd37f28ef53..27c6d5152413 100644
--- a/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.yaml
@@ -42,6 +42,7 @@ description: |
       For PM7325, smps1 - smps8, ldo1 - ldo19
       For PM8005, smps1 - smps4
       For PM8009, smps1 - smps2, ldo1 - ldo7
+      For PM8010, ldo1 - ldo7
       For PM8150, smps1 - smps10, ldo1 - ldo18
       For PM8150L, smps1 - smps8, ldo1 - ldo11, bob, flash, rgb
       For PM8350, smps1 - smps12, ldo1 - ldo10
@@ -68,6 +69,7 @@ properties:
       - qcom,pm8005-rpmh-regulators
       - qcom,pm8009-rpmh-regulators
       - qcom,pm8009-1-rpmh-regulators
+      - qcom,pm8010-rpmh-regulators
       - qcom,pm8150-rpmh-regulators
       - qcom,pm8150l-rpmh-regulators
       - qcom,pm8350-rpmh-regulators
@@ -242,6 +244,18 @@ allOf:
       properties:
         compatible:
           enum:
+            - qcom,pm8010-rpmh-regulators
+    then:
+      properties:
+        vdd-l1-l2-supply: true
+        vdd-l3-l4-supply: true
+      patternProperties:
+        "^vdd-l[5-7]-supply$": true
+
+  - if:
+      properties:
+        compatible:
+          enum:
             - qcom,pm8150-rpmh-regulators
             - qcom,pmc8180-rpmh-regulators
             - qcom,pmm8155au-rpmh-regulators
diff --git a/Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.yaml b/Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.yaml
index 9ea8ac0786ac..f2fd2df68a9e 100644
--- a/Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.yaml
@@ -47,6 +47,9 @@ description:
   For pm8916, s1, s2, s3, s4, l1, l2, l3, l4, l5, l6, l7, l8, l9, l10, l11,
   l12, l13, l14, l15, l16, l17, l18
 
+  For pm8937, s1, s2, s3, s4, l1, l2, l3, l4, l5, l6, l7, l8, l9, l10,
+  l11, l12, l13, l14, l15, l16, l17, l18, l19, l20, l21, l22, l23
+
   For pm8941, s1, s2, s3, s4, l1, l2, l3, l4, l5, l6, l7, l8, l9, l10, l11,
   l12, l13, l14, l15, l16, l17, l18, l19, l20, l21, l22, l23, l24, lvs1, lvs2,
   lvs3, 5vs1, 5vs2
@@ -92,6 +95,7 @@ properties:
       - qcom,rpm-pm8841-regulators
       - qcom,rpm-pm8909-regulators
       - qcom,rpm-pm8916-regulators
+      - qcom,rpm-pm8937-regulators
       - qcom,rpm-pm8941-regulators
       - qcom,rpm-pm8950-regulators
       - qcom,rpm-pm8953-regulators
diff --git a/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.yaml b/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.yaml
index 7a1b7d2abbd4..aea849e8eadf 100644
--- a/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.yaml
@@ -22,6 +22,7 @@ properties:
       - qcom,pm8841-regulators
       - qcom,pm8909-regulators
       - qcom,pm8916-regulators
+      - qcom,pm8937-regulators
       - qcom,pm8941-regulators
       - qcom,pm8950-regulators
       - qcom,pm8994-regulators
@@ -296,6 +297,24 @@ allOf:
         compatible:
           contains:
             enum:
+              - qcom,pm8937-regulators
+    then:
+      properties:
+        vdd_l1_l19-supply: true
+        vdd_l20_l21-supply: true
+        vdd_l2_l23-supply: true
+        vdd_l3-supply: true
+        vdd_l4_l5_l6_l7_l16-supply: true
+        vdd_l8_l11_l12_l17_l22-supply: true
+        vdd_l9_l10_l13_l14_l15_l18-supply: true
+      patternProperties:
+        "^vdd_s[1-6]-supply$": true
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
               - qcom,pm8950-regulators
     then:
       properties:
diff --git a/Documentation/devicetree/bindings/regulator/qcom,usb-vbus-regulator.yaml b/Documentation/devicetree/bindings/regulator/qcom,usb-vbus-regulator.yaml
index 89c564dfa5db..534f87e98716 100644
--- a/Documentation/devicetree/bindings/regulator/qcom,usb-vbus-regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/qcom,usb-vbus-regulator.yaml
@@ -36,10 +36,11 @@ unevaluatedProperties: false
 
 examples:
   - |
-     pm8150b {
+     pmic {
         #address-cells = <1>;
         #size-cells = <0>;
-        pm8150b_vbus: usb-vbus-regulator@1100 {
+
+        usb-vbus-regulator@1100 {
             compatible = "qcom,pm8150b-vbus-reg";
             reg = <0x1100>;
             regulator-min-microamp = <500000>;
diff --git a/Documentation/devicetree/bindings/regulator/regulator.yaml b/Documentation/devicetree/bindings/regulator/regulator.yaml
index 9daf0fc2465f..1ef380d1515e 100644
--- a/Documentation/devicetree/bindings/regulator/regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/regulator.yaml
@@ -114,6 +114,11 @@ properties:
     description: Enable pull down resistor when the regulator is disabled.
     type: boolean
 
+  system-critical-regulator:
+    description: Set if the regulator is critical to system stability or
+      functionality.
+    type: boolean
+
   regulator-over-current-protection:
     description: Enable over current protection.
     type: boolean
@@ -181,6 +186,14 @@ properties:
       be enabled but limit setting can be omitted. Limit is given as microvolt
       offset from voltage set to regulator.
 
+  regulator-uv-less-critical-window-ms:
+    description: Specifies the time window (in milliseconds) following a
+      critical under-voltage event during which the system can continue to
+      operate safely while performing less critical operations. This property
+      provides a defined duration before a more severe reaction to the
+      under-voltage event is needed, allowing for certain non-urgent actions to
+      be carried out in preparation for potential power loss.
+
   regulator-temp-protection-kelvin:
     description: Set over temperature protection limit. This is a limit where
       hardware performs emergency shutdown. Zero can be passed to disable
diff --git a/Documentation/devicetree/bindings/reset/amlogic,meson-reset.yaml b/Documentation/devicetree/bindings/reset/amlogic,meson-reset.yaml
index d3fdee89d4f8..f0c6c0df0ce3 100644
--- a/Documentation/devicetree/bindings/reset/amlogic,meson-reset.yaml
+++ b/Documentation/devicetree/bindings/reset/amlogic,meson-reset.yaml
@@ -18,6 +18,7 @@ properties:
       - amlogic,meson-axg-reset # Reset Controller on AXG and compatible SoCs
       - amlogic,meson-a1-reset # Reset Controller on A1 and compatible SoCs
       - amlogic,meson-s4-reset # Reset Controller on S4 and compatible SoCs
+      - amlogic,c3-reset # Reset Controller on C3 and compatible SoCs
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/reset/fsl,imx-src.yaml b/Documentation/devicetree/bindings/reset/fsl,imx-src.yaml
index b11ac533f914..f5ec1d54aa51 100644
--- a/Documentation/devicetree/bindings/reset/fsl,imx-src.yaml
+++ b/Documentation/devicetree/bindings/reset/fsl,imx-src.yaml
@@ -28,28 +28,17 @@ description: |
 properties:
   compatible:
     oneOf:
-      - const: "fsl,imx51-src"
+      - const: fsl,imx51-src
       - items:
-          - const: "fsl,imx50-src"
-          - const: "fsl,imx51-src"
-      - items:
-          - const: "fsl,imx53-src"
-          - const: "fsl,imx51-src"
-      - items:
-          - const: "fsl,imx6q-src"
-          - const: "fsl,imx51-src"
-      - items:
-          - const: "fsl,imx6sx-src"
-          - const: "fsl,imx51-src"
-      - items:
-          - const: "fsl,imx6sl-src"
-          - const: "fsl,imx51-src"
-      - items:
-          - const: "fsl,imx6ul-src"
-          - const: "fsl,imx51-src"
-      - items:
-          - const: "fsl,imx6sll-src"
-          - const: "fsl,imx51-src"
+          - enum:
+              - fsl,imx50-src
+              - fsl,imx53-src
+              - fsl,imx6q-src
+              - fsl,imx6sx-src
+              - fsl,imx6sl-src
+              - fsl,imx6ul-src
+              - fsl,imx6sll-src
+          - const: fsl,imx51-src
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/reset/hisilicon,hi3660-reset.yaml b/Documentation/devicetree/bindings/reset/hisilicon,hi3660-reset.yaml
index cdfcf32c53fa..e4de002d6903 100644
--- a/Documentation/devicetree/bindings/reset/hisilicon,hi3660-reset.yaml
+++ b/Documentation/devicetree/bindings/reset/hisilicon,hi3660-reset.yaml
@@ -50,32 +50,9 @@ additionalProperties: false
 
 examples:
   - |
-    #include <dt-bindings/interrupt-controller/irq.h>
-    #include <dt-bindings/interrupt-controller/arm-gic.h>
-    #include <dt-bindings/clock/hi3660-clock.h>
-
-    iomcu: iomcu@ffd7e000 {
-        compatible = "hisilicon,hi3660-iomcu", "syscon";
-        reg = <0xffd7e000 0x1000>;
-    };
-
-    iomcu_rst: iomcu_rst_controller {
+    iomcu_rst_controller {
         compatible = "hisilicon,hi3660-reset";
         hisilicon,rst-syscon = <&iomcu>;
         #reset-cells = <2>;
     };
-
-    /* Specifying reset lines connected to IP modules */
-    i2c@ffd71000 {
-        compatible = "snps,designware-i2c";
-        reg = <0xffd71000 0x1000>;
-        interrupts = <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>;
-        #address-cells = <1>;
-        #size-cells = <0>;
-        clock-frequency = <400000>;
-        clocks = <&crg_ctrl HI3660_CLK_GATE_I2C0>;
-        resets = <&iomcu_rst 0x20 3>;
-        pinctrl-names = "default";
-        pinctrl-0 = <&i2c0_pmx_func &i2c0_cfg_func>;
-    };
 ...
diff --git a/Documentation/devicetree/bindings/reset/qcom,aoss-reset.yaml b/Documentation/devicetree/bindings/reset/qcom,aoss-reset.yaml
index d92e2b3cc83f..24beb712b56d 100644
--- a/Documentation/devicetree/bindings/reset/qcom,aoss-reset.yaml
+++ b/Documentation/devicetree/bindings/reset/qcom,aoss-reset.yaml
@@ -18,17 +18,17 @@ properties:
     oneOf:
       - description: on SC7180 SoCs the following compatibles must be specified
         items:
-          - const: "qcom,sc7180-aoss-cc"
-          - const: "qcom,sdm845-aoss-cc"
+          - const: qcom,sc7180-aoss-cc
+          - const: qcom,sdm845-aoss-cc
 
       - description: on SC7280 SoCs the following compatibles must be specified
         items:
-          - const: "qcom,sc7280-aoss-cc"
-          - const: "qcom,sdm845-aoss-cc"
+          - const: qcom,sc7280-aoss-cc
+          - const: qcom,sdm845-aoss-cc
 
       - description: on SDM845 SoCs the following compatibles must be specified
         items:
-          - const: "qcom,sdm845-aoss-cc"
+          - const: qcom,sdm845-aoss-cc
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/reset/qcom,pdc-global.yaml b/Documentation/devicetree/bindings/reset/qcom,pdc-global.yaml
index ca5d79332189..f514363aa474 100644
--- a/Documentation/devicetree/bindings/reset/qcom,pdc-global.yaml
+++ b/Documentation/devicetree/bindings/reset/qcom,pdc-global.yaml
@@ -18,16 +18,16 @@ properties:
     oneOf:
       - description: on SC7180 SoCs the following compatibles must be specified
         items:
-          - const: "qcom,sc7180-pdc-global"
-          - const: "qcom,sdm845-pdc-global"
+          - const: qcom,sc7180-pdc-global
+          - const: qcom,sdm845-pdc-global
 
       - description: on SC7280 SoCs the following compatibles must be specified
         items:
-          - const: "qcom,sc7280-pdc-global"
+          - const: qcom,sc7280-pdc-global
 
       - description: on SDM845 SoCs the following compatibles must be specified
         items:
-          - const: "qcom,sdm845-pdc-global"
+          - const: qcom,sdm845-pdc-global
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/reset/renesas,rzg2l-usbphy-ctrl.yaml b/Documentation/devicetree/bindings/reset/renesas,rzg2l-usbphy-ctrl.yaml
index 731b8ce01525..03c18611e42d 100644
--- a/Documentation/devicetree/bindings/reset/renesas,rzg2l-usbphy-ctrl.yaml
+++ b/Documentation/devicetree/bindings/reset/renesas,rzg2l-usbphy-ctrl.yaml
@@ -17,7 +17,7 @@ properties:
   compatible:
     items:
       - enum:
-          - renesas,r9a07g043-usbphy-ctrl # RZ/G2UL
+          - renesas,r9a07g043-usbphy-ctrl # RZ/G2UL and RZ/Five
           - renesas,r9a07g044-usbphy-ctrl # RZ/G2{L,LC}
           - renesas,r9a07g054-usbphy-ctrl # RZ/V2L
       - const: renesas,rzg2l-usbphy-ctrl
diff --git a/Documentation/devicetree/bindings/riscv/sophgo.yaml b/Documentation/devicetree/bindings/riscv/sophgo.yaml
index 86748c5390be..9bc813dad098 100644
--- a/Documentation/devicetree/bindings/riscv/sophgo.yaml
+++ b/Documentation/devicetree/bindings/riscv/sophgo.yaml
@@ -24,6 +24,10 @@ properties:
           - const: sophgo,cv1800b
       - items:
           - enum:
+              - sophgo,huashan-pi
+          - const: sophgo,cv1812h
+      - items:
+          - enum:
               - milkv,pioneer
           - const: sophgo,sg2042
 
diff --git a/Documentation/devicetree/bindings/rng/starfive,jh7110-trng.yaml b/Documentation/devicetree/bindings/rng/starfive,jh7110-trng.yaml
index 2b76ce25acc4..4639247e9e51 100644
--- a/Documentation/devicetree/bindings/rng/starfive,jh7110-trng.yaml
+++ b/Documentation/devicetree/bindings/rng/starfive,jh7110-trng.yaml
@@ -11,7 +11,11 @@ maintainers:
 
 properties:
   compatible:
-    const: starfive,jh7110-trng
+    oneOf:
+      - items:
+          - const: starfive,jh8100-trng
+          - const: starfive,jh7110-trng
+      - const: starfive,jh7110-trng
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/rtc/s3c-rtc.yaml b/Documentation/devicetree/bindings/rtc/s3c-rtc.yaml
index d51b236939bf..bf4e11d6dffb 100644
--- a/Documentation/devicetree/bindings/rtc/s3c-rtc.yaml
+++ b/Documentation/devicetree/bindings/rtc/s3c-rtc.yaml
@@ -17,6 +17,11 @@ properties:
           - samsung,s3c2416-rtc
           - samsung,s3c2443-rtc
           - samsung,s3c6410-rtc
+      - items:
+          - enum:
+              - samsung,exynos7-rtc
+              - samsung,exynos850-rtc
+          - const: samsung,s3c6410-rtc
       - const: samsung,exynos3250-rtc
         deprecated: true
 
diff --git a/Documentation/devicetree/bindings/serial/samsung_uart.yaml b/Documentation/devicetree/bindings/serial/samsung_uart.yaml
index ac60ab1e35e3..133259ed3a34 100644
--- a/Documentation/devicetree/bindings/serial/samsung_uart.yaml
+++ b/Documentation/devicetree/bindings/serial/samsung_uart.yaml
@@ -18,17 +18,29 @@ description: |+
 properties:
   compatible:
     oneOf:
-      - items:
-          - const: samsung,exynosautov9-uart
-          - const: samsung,exynos850-uart
       - enum:
           - apple,s5l-uart
           - axis,artpec8-uart
+          - google,gs101-uart
           - samsung,s3c6400-uart
           - samsung,s5pv210-uart
           - samsung,exynos4210-uart
           - samsung,exynos5433-uart
           - samsung,exynos850-uart
+      - items:
+          - enum:
+              - samsung,exynos7-uart
+              - tesla,fsd-uart
+          - const: samsung,exynos4210-uart
+      - items:
+          - enum:
+              - samsung,exynos7885-uart
+          - const: samsung,exynos5433-uart
+      - items:
+          - enum:
+              - samsung,exynosautov9-uart
+              - samsung,exynosautov920-uart
+          - const: samsung,exynos850-uart
 
   reg:
     maxItems: 1
@@ -122,6 +134,16 @@ allOf:
             - const: uart
             - const: clk_uart_baud0
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - google,gs101-uart
+    then:
+      required:
+        - samsung,uart-fifosize
+
 unevaluatedProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/soc/amlogic/amlogic,meson-gx-hhi-sysctrl.yaml b/Documentation/devicetree/bindings/soc/amlogic/amlogic,meson-gx-hhi-sysctrl.yaml
index 16977e4e4357..c6bce40946d4 100644
--- a/Documentation/devicetree/bindings/soc/amlogic/amlogic,meson-gx-hhi-sysctrl.yaml
+++ b/Documentation/devicetree/bindings/soc/amlogic/amlogic,meson-gx-hhi-sysctrl.yaml
@@ -158,3 +158,36 @@ examples:
             };
         };
     };
+
+  - |
+    system-controller@ff63c000 {
+        compatible = "amlogic,meson-axg-hhi-sysctrl", "simple-mfd", "syscon";
+        reg = <0xff63c000 0x400>;
+
+        clock-controller {
+            compatible = "amlogic,axg-clkc";
+            #clock-cells = <1>;
+            clocks = <&xtal>;
+            clock-names = "xtal";
+        };
+
+        power-controller {
+           compatible = "amlogic,meson-axg-pwrc";
+           #power-domain-cells = <1>;
+           amlogic,ao-sysctrl = <&sysctrl_AO>;
+
+           resets = <&reset_viu>,
+                    <&reset_venc>,
+                    <&reset_vcbus>,
+                    <&reset_vencl>,
+                    <&reset_vid_lock>;
+           reset-names = "viu", "venc", "vcbus", "vencl", "vid_lock";
+           clocks = <&clk_vpu>, <&clk_vapb>;
+           clock-names = "vpu", "vapb";
+        };
+
+        phy {
+           compatible = "amlogic,axg-mipi-pcie-analog-phy";
+           #phy-cells = <0>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/soc/mediatek/mediatek,pwrap.yaml b/Documentation/devicetree/bindings/soc/mediatek/mediatek,pwrap.yaml
index a06ac2177444..4737e5f45d54 100644
--- a/Documentation/devicetree/bindings/soc/mediatek/mediatek,pwrap.yaml
+++ b/Documentation/devicetree/bindings/soc/mediatek/mediatek,pwrap.yaml
@@ -41,7 +41,6 @@ properties:
               - mediatek,mt8173-pwrap
               - mediatek,mt8183-pwrap
               - mediatek,mt8186-pwrap
-              - mediatek,mt8188-pwrap
               - mediatek,mt8195-pwrap
               - mediatek,mt8365-pwrap
               - mediatek,mt8516-pwrap
@@ -50,6 +49,11 @@ properties:
               - mediatek,mt8186-pwrap
               - mediatek,mt8195-pwrap
           - const: syscon
+      - items:
+          - enum:
+              - mediatek,mt8188-pwrap
+          - const: mediatek,mt8195-pwrap
+          - const: syscon
 
   reg:
     minItems: 1
diff --git a/Documentation/devicetree/bindings/soc/mediatek/mtk-svs.yaml b/Documentation/devicetree/bindings/soc/mediatek/mtk-svs.yaml
index 7eda63d5682f..742b91d1d28e 100644
--- a/Documentation/devicetree/bindings/soc/mediatek/mtk-svs.yaml
+++ b/Documentation/devicetree/bindings/soc/mediatek/mtk-svs.yaml
@@ -22,8 +22,10 @@ properties:
   compatible:
     enum:
       - mediatek,mt8183-svs
+      - mediatek,mt8186-svs
       - mediatek,mt8188-svs
       - mediatek,mt8192-svs
+      - mediatek,mt8195-svs
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/soc/microchip/microchip,mpfs-sys-controller.yaml b/Documentation/devicetree/bindings/soc/microchip/microchip,mpfs-sys-controller.yaml
index 365a9fed5914..a3fa04f3a1bd 100644
--- a/Documentation/devicetree/bindings/soc/microchip/microchip,mpfs-sys-controller.yaml
+++ b/Documentation/devicetree/bindings/soc/microchip/microchip,mpfs-sys-controller.yaml
@@ -26,6 +26,16 @@ properties:
   compatible:
     const: microchip,mpfs-sys-controller
 
+  microchip,bitstream-flash:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description:
+      The SPI flash connected to the system controller's QSPI controller.
+      The system controller may retrieve FPGA bitstreams from this flash to
+      perform In-Application Programming (IAP) or during device initialisation
+      for Auto Update. The MSS and system controller have separate QSPI
+      controllers and this flash is connected to both. Software running in the
+      MSS can write bitstreams to the flash.
+
 required:
   - compatible
   - mboxes
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,aoss-qmp.yaml b/Documentation/devicetree/bindings/soc/qcom/qcom,aoss-qmp.yaml
index d1c7c2be865f..b4478f417edc 100644
--- a/Documentation/devicetree/bindings/soc/qcom/qcom,aoss-qmp.yaml
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,aoss-qmp.yaml
@@ -38,6 +38,8 @@ properties:
           - qcom,sm8350-aoss-qmp
           - qcom,sm8450-aoss-qmp
           - qcom,sm8550-aoss-qmp
+          - qcom,sm8650-aoss-qmp
+          - qcom,x1e80100-aoss-qmp
       - const: qcom,aoss-qmp
 
   reg:
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,pmic-glink.yaml b/Documentation/devicetree/bindings/soc/qcom/qcom,pmic-glink.yaml
index 422921cf1f82..61df97ffe1e4 100644
--- a/Documentation/devicetree/bindings/soc/qcom/qcom,pmic-glink.yaml
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,pmic-glink.yaml
@@ -20,14 +20,20 @@ description:
 
 properties:
   compatible:
-    items:
-      - enum:
-          - qcom,sc8180x-pmic-glink
-          - qcom,sc8280xp-pmic-glink
-          - qcom,sm8350-pmic-glink
-          - qcom,sm8450-pmic-glink
-          - qcom,sm8550-pmic-glink
-      - const: qcom,pmic-glink
+    oneOf:
+      - items:
+          - enum:
+              - qcom,sc8180x-pmic-glink
+              - qcom,sc8280xp-pmic-glink
+              - qcom,sm8350-pmic-glink
+              - qcom,sm8450-pmic-glink
+              - qcom,sm8550-pmic-glink
+          - const: qcom,pmic-glink
+      - items:
+          - enum:
+              - qcom,sm8650-pmic-glink
+          - const: qcom,sm8550-pmic-glink
+          - const: qcom,pmic-glink
 
   '#address-cells':
     const: 1
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom-stats.yaml b/Documentation/devicetree/bindings/soc/qcom/qcom-stats.yaml
index 96a7f1822022..686a7ef2f48a 100644
--- a/Documentation/devicetree/bindings/soc/qcom/qcom-stats.yaml
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom-stats.yaml
@@ -31,10 +31,24 @@ properties:
   reg:
     maxItems: 1
 
+  qcom,qmp:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description: Reference to the AOSS side-channel message RAM
+
 required:
   - compatible
   - reg
 
+allOf:
+  - if:
+      not:
+        properties:
+          compatible:
+            const: qcom,rpmh-stats
+    then:
+      properties:
+        qcom,qmp: false
+
 additionalProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml
index e4fa6a07b4fa..9793ea6f0fe6 100644
--- a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml
+++ b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml
@@ -28,6 +28,8 @@ properties:
               - rockchip,rk3588-sys-grf
               - rockchip,rk3588-pcie3-phy-grf
               - rockchip,rk3588-pcie3-pipe-grf
+              - rockchip,rk3588-vo-grf
+              - rockchip,rk3588-vop-grf
               - rockchip,rv1108-usbgrf
           - const: syscon
       - items:
@@ -233,6 +235,7 @@ allOf:
               - rockchip,rk3399-grf
               - rockchip,rk3399-pmugrf
               - rockchip,rk3568-pmugrf
+              - rockchip,rk3588-pmugrf
               - rockchip,rv1108-grf
               - rockchip,rv1108-pmugrf
 
diff --git a/Documentation/devicetree/bindings/soc/samsung/exynos-pmu.yaml b/Documentation/devicetree/bindings/soc/samsung/exynos-pmu.yaml
index e1d716df5dfa..15fcd8f1d8bc 100644
--- a/Documentation/devicetree/bindings/soc/samsung/exynos-pmu.yaml
+++ b/Documentation/devicetree/bindings/soc/samsung/exynos-pmu.yaml
@@ -15,6 +15,7 @@ select:
     compatible:
       contains:
         enum:
+          - google,gs101-pmu
           - samsung,exynos3250-pmu
           - samsung,exynos4210-pmu
           - samsung,exynos4212-pmu
@@ -35,6 +36,7 @@ properties:
     oneOf:
       - items:
           - enum:
+              - google,gs101-pmu
               - samsung,exynos3250-pmu
               - samsung,exynos4210-pmu
               - samsung,exynos4212-pmu
@@ -50,6 +52,14 @@ properties:
           - const: syscon
       - items:
           - enum:
+              - samsung,exynos7885-pmu
+              - samsung,exynosautov9-pmu
+              - samsung,exynosautov920-pmu
+              - tesla,fsd-pmu
+          - const: samsung,exynos7-pmu
+          - const: syscon
+      - items:
+          - enum:
               - samsung,exynos3250-pmu
               - samsung,exynos4210-pmu
               - samsung,exynos4212-pmu
diff --git a/Documentation/devicetree/bindings/soc/samsung/exynos-usi.yaml b/Documentation/devicetree/bindings/soc/samsung/exynos-usi.yaml
index a6836904a4f8..8b478d6cdc30 100644
--- a/Documentation/devicetree/bindings/soc/samsung/exynos-usi.yaml
+++ b/Documentation/devicetree/bindings/soc/samsung/exynos-usi.yaml
@@ -24,7 +24,10 @@ properties:
   compatible:
     oneOf:
       - items:
-          - const: samsung,exynosautov9-usi
+          - enum:
+              - google,gs101-usi
+              - samsung,exynosautov9-usi
+              - samsung,exynosautov920-usi
           - const: samsung,exynos850-usi
       - enum:
           - samsung,exynos850-usi
@@ -155,7 +158,7 @@ examples:
         };
 
         hsi2c_0: i2c@13820000 {
-            compatible = "samsung,exynosautov9-hsi2c";
+            compatible = "samsung,exynos850-hsi2c", "samsung,exynosautov9-hsi2c";
             reg = <0x13820000 0xc0>;
             interrupts = <GIC_SPI 227 IRQ_TYPE_LEVEL_HIGH>;
             #address-cells = <1>;
diff --git a/Documentation/devicetree/bindings/soc/samsung/samsung,exynos-sysreg.yaml b/Documentation/devicetree/bindings/soc/samsung/samsung,exynos-sysreg.yaml
index 163e912e9cad..1794e3799f21 100644
--- a/Documentation/devicetree/bindings/soc/samsung/samsung,exynos-sysreg.yaml
+++ b/Documentation/devicetree/bindings/soc/samsung/samsung,exynos-sysreg.yaml
@@ -14,9 +14,14 @@ properties:
     oneOf:
       - items:
           - enum:
+              - google,gs101-apm-sysreg
+              - google,gs101-peric0-sysreg
+              - google,gs101-peric1-sysreg
               - samsung,exynos3-sysreg
               - samsung,exynos4-sysreg
               - samsung,exynos5-sysreg
+              - samsung,exynosautov920-peric0-sysreg
+              - samsung,exynosautov920-peric1-sysreg
               - tesla,fsd-cam-sysreg
               - tesla,fsd-fsys0-sysreg
               - tesla,fsd-fsys1-sysreg
diff --git a/Documentation/devicetree/bindings/arm/xilinx.yaml b/Documentation/devicetree/bindings/soc/xilinx/xilinx.yaml
index f57ed0347894..d4c0fe1fe435 100644
--- a/Documentation/devicetree/bindings/arm/xilinx.yaml
+++ b/Documentation/devicetree/bindings/soc/xilinx/xilinx.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/arm/xilinx.yaml#
+$id: http://devicetree.org/schemas/soc/xilinx/xilinx.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: Xilinx Zynq Platforms
@@ -132,6 +132,11 @@ properties:
           - const: xlnx,zynqmp-smk-k26
           - const: xlnx,zynqmp
 
+      - description: AMD MicroBlaze V (QEMU)
+        items:
+          - const: qemu,mbv
+          - const: amd,mbv
+
 additionalProperties: true
 
 ...
diff --git a/Documentation/devicetree/bindings/sound/mediatek,mt2701-audio.yaml b/Documentation/devicetree/bindings/sound/mediatek,mt2701-audio.yaml
new file mode 100644
index 000000000000..45382c4d86aa
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/mediatek,mt2701-audio.yaml
@@ -0,0 +1,116 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/sound/mediatek,mt2701-audio.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: MediaTek Audio Front End (AFE) PCM controller for mt2701
+
+description:
+  The AFE PCM node must be a subnode of the MediaTek audsys device tree node.
+
+maintainers:
+  - Eugen Hristev <eugen.hristev@collabora.com>
+
+properties:
+  compatible:
+    enum:
+      - mediatek,mt2701-audio
+      - mediatek,mt7622-audio
+
+  interrupts:
+    items:
+      - description: AFE interrupt
+      - description: ASYS interrupt
+
+  interrupt-names:
+    items:
+      - const: afe
+      - const: asys
+
+  power-domains:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: audio infra sys clock
+      - description: top audio mux 1
+      - description: top audio mux 2
+      - description: top audio sys a1 clock
+      - description: top audio sys a2 clock
+      - description: i2s0 source selection
+      - description: i2s1 source selection
+      - description: i2s2 source selection
+      - description: i2s3 source selection
+      - description: i2s0 source divider
+      - description: i2s1 source divider
+      - description: i2s2 source divider
+      - description: i2s3 source divider
+      - description: i2s0 master clock
+      - description: i2s1 master clock
+      - description: i2s2 master clock
+      - description: i2s3 master clock
+      - description: i2so0 hopping clock
+      - description: i2so1 hopping clock
+      - description: i2so2 hopping clock
+      - description: i2so3 hopping clock
+      - description: i2si0 hopping clock
+      - description: i2si1 hopping clock
+      - description: i2si2 hopping clock
+      - description: i2si3 hopping clock
+      - description: asrc0 output clock
+      - description: asrc1 output clock
+      - description: asrc2 output clock
+      - description: asrc3 output clock
+      - description: audio front end pd clock
+      - description: audio front end conn pd clock
+      - description: top audio a1 sys pd
+      - description: top audio a2 sys pd
+      - description: audio merge interface pd
+
+  clock-names:
+    items:
+      - const: infra_sys_audio_clk
+      - const: top_audio_mux1_sel
+      - const: top_audio_mux2_sel
+      - const: top_audio_a1sys_hp
+      - const: top_audio_a2sys_hp
+      - const: i2s0_src_sel
+      - const: i2s1_src_sel
+      - const: i2s2_src_sel
+      - const: i2s3_src_sel
+      - const: i2s0_src_div
+      - const: i2s1_src_div
+      - const: i2s2_src_div
+      - const: i2s3_src_div
+      - const: i2s0_mclk_en
+      - const: i2s1_mclk_en
+      - const: i2s2_mclk_en
+      - const: i2s3_mclk_en
+      - const: i2so0_hop_ck
+      - const: i2so1_hop_ck
+      - const: i2so2_hop_ck
+      - const: i2so3_hop_ck
+      - const: i2si0_hop_ck
+      - const: i2si1_hop_ck
+      - const: i2si2_hop_ck
+      - const: i2si3_hop_ck
+      - const: asrc0_out_ck
+      - const: asrc1_out_ck
+      - const: asrc2_out_ck
+      - const: asrc3_out_ck
+      - const: audio_afe_pd
+      - const: audio_afe_conn_pd
+      - const: audio_a1sys_pd
+      - const: audio_a2sys_pd
+      - const: audio_mrgif_pd
+
+required:
+  - compatible
+  - interrupts
+  - interrupt-names
+  - power-domains
+  - clocks
+  - clock-names
+
+additionalProperties: false
diff --git a/Documentation/devicetree/bindings/sound/mt2701-afe-pcm.txt b/Documentation/devicetree/bindings/sound/mt2701-afe-pcm.txt
deleted file mode 100644
index f548e6a58240..000000000000
--- a/Documentation/devicetree/bindings/sound/mt2701-afe-pcm.txt
+++ /dev/null
@@ -1,146 +0,0 @@
-Mediatek AFE PCM controller for mt2701
-
-Required properties:
-- compatible: should be one of the following.
-	      - "mediatek,mt2701-audio"
-	      - "mediatek,mt7622-audio"
-- interrupts: should contain AFE and ASYS interrupts
-- interrupt-names: should be "afe" and "asys"
-- power-domains: should define the power domain
-- clocks: Must contain an entry for each entry in clock-names
-  See ../clocks/clock-bindings.txt for details
-- clock-names: should have these clock names:
-		"infra_sys_audio_clk",
-		"top_audio_mux1_sel",
-		"top_audio_mux2_sel",
-		"top_audio_a1sys_hp",
-		"top_audio_a2sys_hp",
-		"i2s0_src_sel",
-		"i2s1_src_sel",
-		"i2s2_src_sel",
-		"i2s3_src_sel",
-		"i2s0_src_div",
-		"i2s1_src_div",
-		"i2s2_src_div",
-		"i2s3_src_div",
-		"i2s0_mclk_en",
-		"i2s1_mclk_en",
-		"i2s2_mclk_en",
-		"i2s3_mclk_en",
-		"i2so0_hop_ck",
-		"i2so1_hop_ck",
-		"i2so2_hop_ck",
-		"i2so3_hop_ck",
-		"i2si0_hop_ck",
-		"i2si1_hop_ck",
-		"i2si2_hop_ck",
-		"i2si3_hop_ck",
-		"asrc0_out_ck",
-		"asrc1_out_ck",
-		"asrc2_out_ck",
-		"asrc3_out_ck",
-		"audio_afe_pd",
-		"audio_afe_conn_pd",
-		"audio_a1sys_pd",
-		"audio_a2sys_pd",
-		"audio_mrgif_pd";
-- assigned-clocks: list of input clocks and dividers for the audio system.
-		   See ../clocks/clock-bindings.txt for details.
-- assigned-clocks-parents: parent of input clocks of assigned clocks.
-- assigned-clock-rates: list of clock frequencies of assigned clocks.
-
-Must be a subnode of MediaTek audsys device tree node.
-See ../arm/mediatek/mediatek,audsys.txt for details about the parent node.
-
-Example:
-
-	audsys: audio-subsystem@11220000 {
-		compatible = "mediatek,mt2701-audsys", "syscon";
-		...
-
-		afe: audio-controller {
-			compatible = "mediatek,mt2701-audio";
-			interrupts =  <GIC_SPI 104 IRQ_TYPE_LEVEL_LOW>,
-				      <GIC_SPI 132 IRQ_TYPE_LEVEL_LOW>;
-			interrupt-names	= "afe", "asys";
-			power-domains = <&scpsys MT2701_POWER_DOMAIN_IFR_MSC>;
-
-			clocks = <&infracfg CLK_INFRA_AUDIO>,
-				 <&topckgen CLK_TOP_AUD_MUX1_SEL>,
-				 <&topckgen CLK_TOP_AUD_MUX2_SEL>,
-				 <&topckgen CLK_TOP_AUD_48K_TIMING>,
-				 <&topckgen CLK_TOP_AUD_44K_TIMING>,
-				 <&topckgen CLK_TOP_AUD_K1_SRC_SEL>,
-				 <&topckgen CLK_TOP_AUD_K2_SRC_SEL>,
-				 <&topckgen CLK_TOP_AUD_K3_SRC_SEL>,
-				 <&topckgen CLK_TOP_AUD_K4_SRC_SEL>,
-				 <&topckgen CLK_TOP_AUD_K1_SRC_DIV>,
-				 <&topckgen CLK_TOP_AUD_K2_SRC_DIV>,
-				 <&topckgen CLK_TOP_AUD_K3_SRC_DIV>,
-				 <&topckgen CLK_TOP_AUD_K4_SRC_DIV>,
-				 <&topckgen CLK_TOP_AUD_I2S1_MCLK>,
-				 <&topckgen CLK_TOP_AUD_I2S2_MCLK>,
-				 <&topckgen CLK_TOP_AUD_I2S3_MCLK>,
-				 <&topckgen CLK_TOP_AUD_I2S4_MCLK>,
-				 <&audsys CLK_AUD_I2SO1>,
-				 <&audsys CLK_AUD_I2SO2>,
-				 <&audsys CLK_AUD_I2SO3>,
-				 <&audsys CLK_AUD_I2SO4>,
-				 <&audsys CLK_AUD_I2SIN1>,
-				 <&audsys CLK_AUD_I2SIN2>,
-				 <&audsys CLK_AUD_I2SIN3>,
-				 <&audsys CLK_AUD_I2SIN4>,
-				 <&audsys CLK_AUD_ASRCO1>,
-				 <&audsys CLK_AUD_ASRCO2>,
-				 <&audsys CLK_AUD_ASRCO3>,
-				 <&audsys CLK_AUD_ASRCO4>,
-				 <&audsys CLK_AUD_AFE>,
-				 <&audsys CLK_AUD_AFE_CONN>,
-				 <&audsys CLK_AUD_A1SYS>,
-				 <&audsys CLK_AUD_A2SYS>,
-				 <&audsys CLK_AUD_AFE_MRGIF>;
-
-			clock-names = "infra_sys_audio_clk",
-				      "top_audio_mux1_sel",
-				      "top_audio_mux2_sel",
-				      "top_audio_a1sys_hp",
-				      "top_audio_a2sys_hp",
-				      "i2s0_src_sel",
-				      "i2s1_src_sel",
-				      "i2s2_src_sel",
-				      "i2s3_src_sel",
-				      "i2s0_src_div",
-				      "i2s1_src_div",
-				      "i2s2_src_div",
-				      "i2s3_src_div",
-				      "i2s0_mclk_en",
-				      "i2s1_mclk_en",
-				      "i2s2_mclk_en",
-				      "i2s3_mclk_en",
-				      "i2so0_hop_ck",
-				      "i2so1_hop_ck",
-				      "i2so2_hop_ck",
-				      "i2so3_hop_ck",
-				      "i2si0_hop_ck",
-				      "i2si1_hop_ck",
-				      "i2si2_hop_ck",
-				      "i2si3_hop_ck",
-				      "asrc0_out_ck",
-				      "asrc1_out_ck",
-				      "asrc2_out_ck",
-				      "asrc3_out_ck",
-				      "audio_afe_pd",
-				      "audio_afe_conn_pd",
-				      "audio_a1sys_pd",
-				      "audio_a2sys_pd",
-				      "audio_mrgif_pd";
-
-			assigned-clocks = <&topckgen CLK_TOP_AUD_MUX1_SEL>,
-					  <&topckgen CLK_TOP_AUD_MUX2_SEL>,
-					  <&topckgen CLK_TOP_AUD_MUX1_DIV>,
-					  <&topckgen CLK_TOP_AUD_MUX2_DIV>;
-			assigned-clock-parents = <&topckgen CLK_TOP_AUD1PLL_98M>,
-						 <&topckgen CLK_TOP_AUD2PLL_90M>;
-			assigned-clock-rates = <0>, <0>, <49152000>, <45158400>;
-		};
-	};
diff --git a/Documentation/devicetree/bindings/sound/samsung-i2s.yaml b/Documentation/devicetree/bindings/sound/samsung-i2s.yaml
index 30b3b6e9824b..f45f73b5056d 100644
--- a/Documentation/devicetree/bindings/sound/samsung-i2s.yaml
+++ b/Documentation/devicetree/bindings/sound/samsung-i2s.yaml
@@ -44,13 +44,18 @@ properties:
       frequencies supported by Exynos7 I2S and 7.1 channel TDM support
       for playback and capture TDM (Time division multiplexing) to allow
       transfer of multiple channel audio data on single data line.
-    enum:
-      - samsung,s3c6410-i2s
-      - samsung,s5pv210-i2s
-      - samsung,exynos5420-i2s
-      - samsung,exynos7-i2s
-      - samsung,exynos7-i2s1
-      - tesla,fsd-i2s
+    oneOf:
+      - enum:
+          - samsung,s3c6410-i2s
+          - samsung,s5pv210-i2s
+          - samsung,exynos5420-i2s
+          - samsung,exynos7-i2s
+          - samsung,exynos7-i2s1
+          - tesla,fsd-i2s
+      - items:
+          - enum:
+              - samsung,exynos5433-i2s
+          - const: samsung,exynos7-i2s
 
   '#address-cells':
     const: 1
diff --git a/Documentation/devicetree/bindings/spi/adi,axi-spi-engine.txt b/Documentation/devicetree/bindings/spi/adi,axi-spi-engine.txt
deleted file mode 100644
index 8a18d71e6879..000000000000
--- a/Documentation/devicetree/bindings/spi/adi,axi-spi-engine.txt
+++ /dev/null
@@ -1,31 +0,0 @@
-Analog Devices AXI SPI Engine controller Device Tree Bindings
-
-Required properties:
-- compatible		: Must be "adi,axi-spi-engine-1.00.a""
-- reg			: Physical base address and size of the register map.
-- interrupts		: Property with a value describing the interrupt
-			  number.
-- clock-names		: List of input clock names - "s_axi_aclk", "spi_clk"
-- clocks		: Clock phandles and specifiers (See clock bindings for
-			  details on clock-names and clocks).
-- #address-cells	: Must be <1>
-- #size-cells		: Must be <0>
-
-Optional subnodes:
-	Subnodes are use to represent the SPI slave devices connected to the SPI
-	master. They follow the generic SPI bindings as outlined in spi-bus.txt.
-
-Example:
-
-    spi@@44a00000 {
-		compatible = "adi,axi-spi-engine-1.00.a";
-		reg = <0x44a00000 0x1000>;
-		interrupts = <0 56 4>;
-		clocks = <&clkc 15 &clkc 15>;
-		clock-names = "s_axi_aclk", "spi_clk";
-
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		/* SPI devices */
-    };
diff --git a/Documentation/devicetree/bindings/spi/adi,axi-spi-engine.yaml b/Documentation/devicetree/bindings/spi/adi,axi-spi-engine.yaml
new file mode 100644
index 000000000000..d48faa42d025
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/adi,axi-spi-engine.yaml
@@ -0,0 +1,66 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/spi/adi,axi-spi-engine.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Analog Devices AXI SPI Engine Controller
+
+description: |
+  The AXI SPI Engine controller is part of the SPI Engine framework[1] and
+  allows memory mapped access to the SPI Engine control bus. This allows it
+  to be used as a general purpose software driven SPI controller as well as
+  some optional advanced acceleration and offloading capabilities.
+
+  [1] https://wiki.analog.com/resources/fpga/peripherals/spi_engine
+
+maintainers:
+  - Michael Hennerich <Michael.Hennerich@analog.com>
+  - Nuno Sá <nuno.sa@analog.com>
+
+allOf:
+  - $ref: /schemas/spi/spi-controller.yaml#
+
+properties:
+  compatible:
+    const: adi,axi-spi-engine-1.00.a
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: The AXI interconnect clock.
+      - description: The SPI controller clock.
+
+  clock-names:
+    items:
+      - const: s_axi_aclk
+      - const: spi_clk
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    spi@44a00000 {
+        compatible = "adi,axi-spi-engine-1.00.a";
+        reg = <0x44a00000 0x1000>;
+        interrupts = <0 56 4>;
+        clocks = <&clkc 15>, <&clkc 15>;
+        clock-names = "s_axi_aclk", "spi_clk";
+
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        /* SPI devices */
+    };
diff --git a/Documentation/devicetree/bindings/spi/renesas,rspi.yaml b/Documentation/devicetree/bindings/spi/renesas,rspi.yaml
index 4d8ec69214c9..0ef3f8421986 100644
--- a/Documentation/devicetree/bindings/spi/renesas,rspi.yaml
+++ b/Documentation/devicetree/bindings/spi/renesas,rspi.yaml
@@ -21,7 +21,7 @@ properties:
           - enum:
               - renesas,rspi-r7s72100  # RZ/A1H
               - renesas,rspi-r7s9210   # RZ/A2
-              - renesas,r9a07g043-rspi # RZ/G2UL
+              - renesas,r9a07g043-rspi # RZ/G2UL and RZ/Five
               - renesas,r9a07g044-rspi # RZ/G2{L,LC}
               - renesas,r9a07g054-rspi # RZ/V2L
           - const: renesas,rspi-rz
diff --git a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
index 6348a387a21c..fde3776a558b 100644
--- a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
+++ b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
@@ -72,8 +72,6 @@ properties:
           - const: snps,dw-apb-ssi
       - description: Intel Keem Bay SPI Controller
         const: intel,keembay-ssi
-      - description: Intel Thunder Bay SPI Controller
-        const: intel,thunderbay-ssi
       - description: Intel Mount Evans Integrated Management Complex SPI Controller
         const: intel,mountevans-imc-ssi
       - description: AMD Pensando Elba SoC SPI Controller
diff --git a/Documentation/devicetree/bindings/spi/st,stm32-spi.yaml b/Documentation/devicetree/bindings/spi/st,stm32-spi.yaml
index ae0f082bd377..4bd9aeb81208 100644
--- a/Documentation/devicetree/bindings/spi/st,stm32-spi.yaml
+++ b/Documentation/devicetree/bindings/spi/st,stm32-spi.yaml
@@ -23,7 +23,9 @@ properties:
   compatible:
     enum:
       - st,stm32f4-spi
+      - st,stm32f7-spi
       - st,stm32h7-spi
+      - st,stm32mp25-spi
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/thermal/allwinner,sun8i-a83t-ths.yaml b/Documentation/devicetree/bindings/thermal/allwinner,sun8i-a83t-ths.yaml
index fbd4212285e2..9b2272a9ec15 100644
--- a/Documentation/devicetree/bindings/thermal/allwinner,sun8i-a83t-ths.yaml
+++ b/Documentation/devicetree/bindings/thermal/allwinner,sun8i-a83t-ths.yaml
@@ -16,6 +16,7 @@ properties:
       - allwinner,sun8i-a83t-ths
       - allwinner,sun8i-h3-ths
       - allwinner,sun8i-r40-ths
+      - allwinner,sun20i-d1-ths
       - allwinner,sun50i-a64-ths
       - allwinner,sun50i-a100-ths
       - allwinner,sun50i-h5-ths
@@ -61,6 +62,7 @@ allOf:
         compatible:
           contains:
             enum:
+              - allwinner,sun20i-d1-ths
               - allwinner,sun50i-a100-ths
               - allwinner,sun50i-h6-ths
 
@@ -84,7 +86,9 @@ allOf:
       properties:
         compatible:
           contains:
-            const: allwinner,sun8i-h3-ths
+            enum:
+              - allwinner,sun8i-h3-ths
+              - allwinner,sun20i-d1-ths
 
     then:
       properties:
@@ -103,6 +107,7 @@ allOf:
             enum:
               - allwinner,sun8i-h3-ths
               - allwinner,sun8i-r40-ths
+              - allwinner,sun20i-d1-ths
               - allwinner,sun50i-a64-ths
               - allwinner,sun50i-a100-ths
               - allwinner,sun50i-h5-ths
diff --git a/Documentation/devicetree/bindings/thermal/loongson,ls2k-thermal.yaml b/Documentation/devicetree/bindings/thermal/loongson,ls2k-thermal.yaml
index 7538469997f9..b634f57cd011 100644
--- a/Documentation/devicetree/bindings/thermal/loongson,ls2k-thermal.yaml
+++ b/Documentation/devicetree/bindings/thermal/loongson,ls2k-thermal.yaml
@@ -10,6 +10,9 @@ maintainers:
   - zhanghongchen <zhanghongchen@loongson.cn>
   - Yinbo Zhu <zhuyinbo@loongson.cn>
 
+allOf:
+  - $ref: /schemas/thermal/thermal-sensor.yaml#
+
 properties:
   compatible:
     oneOf:
@@ -26,12 +29,16 @@ properties:
   interrupts:
     maxItems: 1
 
+  '#thermal-sensor-cells':
+    const: 1
+
 required:
   - compatible
   - reg
   - interrupts
+  - '#thermal-sensor-cells'
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
@@ -41,4 +48,5 @@ examples:
         reg = <0x1fe01500 0x30>;
         interrupt-parent = <&liointc0>;
         interrupts = <7 IRQ_TYPE_LEVEL_LOW>;
+        #thermal-sensor-cells = <1>;
     };
diff --git a/Documentation/devicetree/bindings/thermal/mediatek,thermal.yaml b/Documentation/devicetree/bindings/thermal/mediatek,thermal.yaml
new file mode 100644
index 000000000000..d96a2e32bd8f
--- /dev/null
+++ b/Documentation/devicetree/bindings/thermal/mediatek,thermal.yaml
@@ -0,0 +1,99 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/thermal/mediatek,thermal.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Mediatek thermal controller for on-SoC temperatures
+
+maintainers:
+  - Sascha Hauer <s.hauer@pengutronix.de>
+
+description:
+  This device does not have its own ADC, instead it directly controls the AUXADC
+  via AHB bus accesses. For this reason it needs phandles to the AUXADC. Also it
+  controls a mux in the apmixedsys register space via AHB bus accesses, so a
+  phandle to the APMIXEDSYS is also needed.
+
+allOf:
+  - $ref: thermal-sensor.yaml#
+
+properties:
+  compatible:
+    enum:
+      - mediatek,mt2701-thermal
+      - mediatek,mt2712-thermal
+      - mediatek,mt7622-thermal
+      - mediatek,mt7981-thermal
+      - mediatek,mt7986-thermal
+      - mediatek,mt8173-thermal
+      - mediatek,mt8183-thermal
+      - mediatek,mt8365-thermal
+      - mediatek,mt8516-thermal
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: Main clock needed for register access
+      - description: The AUXADC clock
+
+  clock-names:
+    items:
+      - const: therm
+      - const: auxadc
+
+  mediatek,auxadc:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description: A phandle to the AUXADC which the thermal controller uses
+
+  mediatek,apmixedsys:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description: A phandle to the APMIXEDSYS controller
+
+  resets:
+    description: Reset controller controlling the thermal controller
+
+  nvmem-cells:
+    items:
+      - description:
+          NVMEM cell with EEPROMA phandle to the calibration data provided by an
+          NVMEM device. If unspecified default values shall be used.
+
+  nvmem-cell-names:
+    items:
+      - const: calibration-data
+
+required:
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - mediatek,auxadc
+  - mediatek,apmixedsys
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/clock/mt8173-clk.h>
+    #include <dt-bindings/reset/mt8173-resets.h>
+
+    thermal@1100b000 {
+        compatible = "mediatek,mt8173-thermal";
+        reg = <0x1100b000 0x1000>;
+        interrupts = <0 70 IRQ_TYPE_LEVEL_LOW>;
+        clocks = <&pericfg CLK_PERI_THERM>, <&pericfg CLK_PERI_AUXADC>;
+        clock-names = "therm", "auxadc";
+        resets = <&pericfg MT8173_PERI_THERM_SW_RST>;
+        mediatek,auxadc = <&auxadc>;
+        mediatek,apmixedsys = <&apmixedsys>;
+        nvmem-cells = <&thermal_calibration_data>;
+        nvmem-cell-names = "calibration-data";
+        #thermal-sensor-cells = <1>;
+    };
diff --git a/Documentation/devicetree/bindings/thermal/mediatek-thermal.txt b/Documentation/devicetree/bindings/thermal/mediatek-thermal.txt
deleted file mode 100644
index ac39c7156fde..000000000000
--- a/Documentation/devicetree/bindings/thermal/mediatek-thermal.txt
+++ /dev/null
@@ -1,52 +0,0 @@
-* Mediatek Thermal
-
-This describes the device tree binding for the Mediatek thermal controller
-which measures the on-SoC temperatures. This device does not have its own ADC,
-instead it directly controls the AUXADC via AHB bus accesses. For this reason
-this device needs phandles to the AUXADC. Also it controls a mux in the
-apmixedsys register space via AHB bus accesses, so a phandle to the APMIXEDSYS
-is also needed.
-
-Required properties:
-- compatible:
-  - "mediatek,mt8173-thermal" : For MT8173 family of SoCs
-  - "mediatek,mt2701-thermal" : For MT2701 family of SoCs
-  - "mediatek,mt2712-thermal" : For MT2712 family of SoCs
-  - "mediatek,mt7622-thermal" : For MT7622 SoC
-  - "mediatek,mt7981-thermal", "mediatek,mt7986-thermal" : For MT7981 SoC
-  - "mediatek,mt7986-thermal" : For MT7986 SoC
-  - "mediatek,mt8183-thermal" : For MT8183 family of SoCs
-  - "mediatek,mt8365-thermal" : For MT8365 family of SoCs
-  - "mediatek,mt8516-thermal", "mediatek,mt2701-thermal : For MT8516 family of SoCs
-- reg: Address range of the thermal controller
-- interrupts: IRQ for the thermal controller
-- clocks, clock-names: Clocks needed for the thermal controller. required
-                       clocks are:
-		       "therm":	 Main clock needed for register access
-		       "auxadc": The AUXADC clock
-- mediatek,auxadc: A phandle to the AUXADC which the thermal controller uses
-- mediatek,apmixedsys: A phandle to the APMIXEDSYS controller.
-- #thermal-sensor-cells : Should be 0. See Documentation/devicetree/bindings/thermal/thermal-sensor.yaml for a description.
-
-Optional properties:
-- resets: Reference to the reset controller controlling the thermal controller.
-- nvmem-cells: A phandle to the calibration data provided by a nvmem device. If
-               unspecified default values shall be used.
-- nvmem-cell-names: Should be "calibration-data"
-
-Example:
-
-	thermal: thermal@1100b000 {
-		#thermal-sensor-cells = <1>;
-		compatible = "mediatek,mt8173-thermal";
-		reg = <0 0x1100b000 0 0x1000>;
-		interrupts = <0 70 IRQ_TYPE_LEVEL_LOW>;
-		clocks = <&pericfg CLK_PERI_THERM>, <&pericfg CLK_PERI_AUXADC>;
-		clock-names = "therm", "auxadc";
-		resets = <&pericfg MT8173_PERI_THERM_SW_RST>;
-		reset-names = "therm";
-		mediatek,auxadc = <&auxadc>;
-		mediatek,apmixedsys = <&apmixedsys>;
-		nvmem-cells = <&thermal_calibration_data>;
-		nvmem-cell-names = "calibration-data";
-	};
diff --git a/Documentation/devicetree/bindings/thermal/qcom-spmi-adc-tm-hc.yaml b/Documentation/devicetree/bindings/thermal/qcom-spmi-adc-tm-hc.yaml
index 01253d58bf9f..7541e27704ca 100644
--- a/Documentation/devicetree/bindings/thermal/qcom-spmi-adc-tm-hc.yaml
+++ b/Documentation/devicetree/bindings/thermal/qcom-spmi-adc-tm-hc.yaml
@@ -114,12 +114,14 @@ examples:
   - |
     #include <dt-bindings/iio/qcom,spmi-vadc.h>
     #include <dt-bindings/interrupt-controller/irq.h>
-    spmi_bus {
+
+    pmic {
         #address-cells = <1>;
         #size-cells = <0>;
+
         pm8998_adc: adc@3100 {
-            reg = <0x3100>;
             compatible = "qcom,spmi-adc-rev2";
+            reg = <0x3100>;
             #address-cells = <1>;
             #size-cells = <0>;
             #io-channel-cells = <1>;
@@ -130,7 +132,7 @@ examples:
             };
         };
 
-        pm8998_adc_tm: adc-tm@3400 {
+        adc-tm@3400 {
             compatible = "qcom,spmi-adc-tm-hc";
             reg = <0x3400>;
             interrupts = <0x2 0x34 0x0 IRQ_TYPE_EDGE_RISING>;
diff --git a/Documentation/devicetree/bindings/thermal/qcom-spmi-adc-tm5.yaml b/Documentation/devicetree/bindings/thermal/qcom-spmi-adc-tm5.yaml
index 3c81def03c84..d9d2657287cb 100644
--- a/Documentation/devicetree/bindings/thermal/qcom-spmi-adc-tm5.yaml
+++ b/Documentation/devicetree/bindings/thermal/qcom-spmi-adc-tm5.yaml
@@ -167,12 +167,14 @@ examples:
   - |
     #include <dt-bindings/iio/qcom,spmi-vadc.h>
     #include <dt-bindings/interrupt-controller/irq.h>
-    spmi_bus {
+
+    pmic {
         #address-cells = <1>;
         #size-cells = <0>;
+
         pm8150b_adc: adc@3100 {
-            reg = <0x3100>;
             compatible = "qcom,spmi-adc5";
+            reg = <0x3100>;
             #address-cells = <1>;
             #size-cells = <0>;
             #io-channel-cells = <1>;
@@ -186,7 +188,7 @@ examples:
             };
         };
 
-        pm8150b_adc_tm: adc-tm@3500 {
+        adc-tm@3500 {
             compatible = "qcom,spmi-adc-tm5";
             reg = <0x3500>;
             interrupts = <0x2 0x35 0x0 IRQ_TYPE_EDGE_RISING>;
@@ -207,12 +209,14 @@ examples:
     #include <dt-bindings/iio/qcom,spmi-adc7-pmk8350.h>
     #include <dt-bindings/iio/qcom,spmi-adc7-pm8350.h>
     #include <dt-bindings/interrupt-controller/irq.h>
-    spmi_bus {
+
+    pmic {
         #address-cells = <1>;
         #size-cells = <0>;
+
         pmk8350_vadc: adc@3100 {
-            reg = <0x3100>;
             compatible = "qcom,spmi-adc7";
+            reg = <0x3100>;
             #address-cells = <1>;
             #size-cells = <0>;
             #io-channel-cells = <1>;
@@ -233,7 +237,7 @@ examples:
             };
         };
 
-        pmk8350_adc_tm: adc-tm@3400 {
+        adc-tm@3400 {
             compatible = "qcom,spmi-adc-tm5-gen2";
             reg = <0x3400>;
             interrupts = <0x0 0x34 0x0 IRQ_TYPE_EDGE_RISING>;
diff --git a/Documentation/devicetree/bindings/thermal/qcom-tsens.yaml b/Documentation/devicetree/bindings/thermal/qcom-tsens.yaml
index 437b74732886..99d9c526c0b6 100644
--- a/Documentation/devicetree/bindings/thermal/qcom-tsens.yaml
+++ b/Documentation/devicetree/bindings/thermal/qcom-tsens.yaml
@@ -66,6 +66,7 @@ properties:
               - qcom,sm8350-tsens
               - qcom,sm8450-tsens
               - qcom,sm8550-tsens
+              - qcom,sm8650-tsens
           - const: qcom,tsens-v2
 
       - description: v2 of TSENS with combined interrupt
diff --git a/Documentation/devicetree/bindings/thermal/thermal-zones.yaml b/Documentation/devicetree/bindings/thermal/thermal-zones.yaml
index 4a8dabc48170..dbd52620d293 100644
--- a/Documentation/devicetree/bindings/thermal/thermal-zones.yaml
+++ b/Documentation/devicetree/bindings/thermal/thermal-zones.yaml
@@ -75,6 +75,22 @@ patternProperties:
           framework and assumes that the thermal sensors in this zone
           support interrupts.
 
+      critical-action:
+        $ref: /schemas/types.yaml#/definitions/string
+        description: |
+          The action the OS should perform after the critical temperature is reached.
+          By default the system will shutdown as a safe action to prevent damage
+          to the hardware, if the property is not set.
+          The shutdown action should be always the default and preferred one.
+          Choose 'reboot' with care, as the hardware may be in thermal stress,
+          thus leading to infinite reboots that may cause damage to the hardware.
+          Make sure the firmware/bootloader will act as the last resort and take
+          over the thermal control.
+
+        enum:
+          - shutdown
+          - reboot
+
       thermal-sensors:
         $ref: /schemas/types.yaml#/definitions/phandle-array
         maxItems: 1
diff --git a/Documentation/devicetree/bindings/timer/sifive,clint.yaml b/Documentation/devicetree/bindings/timer/sifive,clint.yaml
index e8be6c470364..4b6c20fc8194 100644
--- a/Documentation/devicetree/bindings/timer/sifive,clint.yaml
+++ b/Documentation/devicetree/bindings/timer/sifive,clint.yaml
@@ -38,6 +38,7 @@ properties:
           - enum:
               - allwinner,sun20i-d1-clint
               - sophgo,cv1800b-clint
+              - sophgo,cv1812h-clint
               - thead,th1520-clint
           - const: thead,c900-clint
       - items:
diff --git a/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml b/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml
index 462ead5a1cec..10c146424baa 100644
--- a/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml
+++ b/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml
@@ -27,6 +27,7 @@ properties:
           - qcom,msm8996-ufshc
           - qcom,msm8998-ufshc
           - qcom,sa8775p-ufshc
+          - qcom,sc7280-ufshc
           - qcom,sc8280xp-ufshc
           - qcom,sdm845-ufshc
           - qcom,sm6115-ufshc
@@ -36,6 +37,7 @@ properties:
           - qcom,sm8350-ufshc
           - qcom,sm8450-ufshc
           - qcom,sm8550-ufshc
+          - qcom,sm8650-ufshc
       - const: qcom,ufshc
       - const: jedec,ufs-2.0
 
@@ -117,11 +119,13 @@ allOf:
             enum:
               - qcom,msm8998-ufshc
               - qcom,sa8775p-ufshc
+              - qcom,sc7280-ufshc
               - qcom,sc8280xp-ufshc
               - qcom,sm8250-ufshc
               - qcom,sm8350-ufshc
               - qcom,sm8450-ufshc
               - qcom,sm8550-ufshc
+              - qcom,sm8650-ufshc
     then:
       properties:
         clocks:
diff --git a/Documentation/devicetree/bindings/ufs/ufs-common.yaml b/Documentation/devicetree/bindings/ufs/ufs-common.yaml
index 985ea8f64de8..31fe7f30ff5b 100644
--- a/Documentation/devicetree/bindings/ufs/ufs-common.yaml
+++ b/Documentation/devicetree/bindings/ufs/ufs-common.yaml
@@ -87,6 +87,8 @@ properties:
     description:
       Specifies max. load that can be drawn from VCCQ2 supply.
 
+  msi-parent: true
+
 dependencies:
   freq-table-hz: [ clocks ]
   operating-points-v2: [ clocks, clock-names ]
diff --git a/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml b/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml
index ff3a1707ef57..6d4cfd943f58 100644
--- a/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml
+++ b/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml
@@ -36,7 +36,11 @@ properties:
 
   vdd-supply:
     description:
-      VDD power supply to the hub
+      3V3 power supply to the hub
+
+  vdd2-supply:
+    description:
+      1V2 power supply to the hub
 
   peer-hub:
     $ref: /schemas/types.yaml#/definitions/phandle
@@ -62,6 +66,7 @@ allOf:
       properties:
         reset-gpios: false
         vdd-supply: false
+        vdd2-supply: false
         peer-hub: false
         i2c-bus: false
     else:
diff --git a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
index e889158ca205..915c8205623b 100644
--- a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
+++ b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
@@ -521,8 +521,8 @@ examples:
 
             interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
                          <GIC_SPI 486 IRQ_TYPE_LEVEL_HIGH>,
-                         <GIC_SPI 488 IRQ_TYPE_LEVEL_HIGH>,
-                         <GIC_SPI 489 IRQ_TYPE_LEVEL_HIGH>;
+                         <GIC_SPI 488 IRQ_TYPE_EDGE_BOTH>,
+                         <GIC_SPI 489 IRQ_TYPE_EDGE_BOTH>;
             interrupt-names = "hs_phy_irq", "ss_phy_irq",
                           "dm_hs_phy_irq", "dp_hs_phy_irq";
 
diff --git a/Documentation/devicetree/bindings/usb/usb-hcd.yaml b/Documentation/devicetree/bindings/usb/usb-hcd.yaml
index 692dd60e3f73..45a19d4928af 100644
--- a/Documentation/devicetree/bindings/usb/usb-hcd.yaml
+++ b/Documentation/devicetree/bindings/usb/usb-hcd.yaml
@@ -41,7 +41,7 @@ examples:
   - |
     usb {
         phys = <&usb2_phy1>, <&usb3_phy1>;
-        phy-names = "usb";
+        phy-names = "usb2", "usb3";
         #address-cells = <1>;
         #size-cells = <0>;
 
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml
index 309b94c328c8..8f03e85be90a 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.yaml
+++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml
@@ -294,6 +294,8 @@ patternProperties:
     description: CompuLab Ltd.
   "^congatec,.*":
     description: congatec GmbH
+  "^coolpi,.*":
+    description: cool-pi.com
   "^coreriver,.*":
     description: CORERIVER Semiconductor Co.,Ltd.
   "^corpro,.*":
@@ -352,6 +354,8 @@ patternProperties:
     description: Digi International Inc.
   "^digilent,.*":
     description: Diglent, Inc.
+  "^dimonoff,.*":
+    description: Dimonoff inc.
   "^diodes,.*":
     description: Diodes, Inc.
   "^dioo,.*":
@@ -597,6 +601,8 @@ patternProperties:
     description: Hewlett Packard Enterprise
   "^hsg,.*":
     description: HannStar Display Co.
+  "^htc,.*":
+    description: HTC Corporation
   "^huawei,.*":
     description: Huawei Technologies Co., Ltd.
   "^hugsun,.*":
@@ -1179,6 +1185,8 @@ patternProperties:
     description: Shenzhen Roofull Technology Co, Ltd
   "^roseapplepi,.*":
     description: RoseapplePi.org
+  "^rve,.*":
+    description: Recharge Véhicule Électrique (RVE) inc.
   "^saef,.*":
     description: Saef Technology Limited
   "^samsung,.*":
@@ -1434,6 +1442,8 @@ patternProperties:
     description: TPO
   "^tq,.*":
     description: TQ-Systems GmbH
+  "^transpeed,.*":
+    description: Transpeed
   "^traverse,.*":
     description: Traverse Technologies Australia Pty Ltd
   "^tronfy,.*":
diff --git a/Documentation/devicetree/bindings/watchdog/samsung-wdt.yaml b/Documentation/devicetree/bindings/watchdog/samsung-wdt.yaml
index 8fb6656ba0c2..77a5ddd0426e 100644
--- a/Documentation/devicetree/bindings/watchdog/samsung-wdt.yaml
+++ b/Documentation/devicetree/bindings/watchdog/samsung-wdt.yaml
@@ -16,14 +16,20 @@ description: |+
 
 properties:
   compatible:
-    enum:
-      - samsung,s3c2410-wdt                   # for S3C2410
-      - samsung,s3c6410-wdt                   # for S3C6410, S5PV210 and Exynos4
-      - samsung,exynos5250-wdt                # for Exynos5250
-      - samsung,exynos5420-wdt                # for Exynos5420
-      - samsung,exynos7-wdt                   # for Exynos7
-      - samsung,exynos850-wdt                 # for Exynos850
-      - samsung,exynosautov9-wdt              # for Exynosautov9
+    oneOf:
+      - enum:
+          - google,gs101-wdt                      # for Google gs101
+          - samsung,s3c2410-wdt                   # for S3C2410
+          - samsung,s3c6410-wdt                   # for S3C6410, S5PV210 and Exynos4
+          - samsung,exynos5250-wdt                # for Exynos5250
+          - samsung,exynos5420-wdt                # for Exynos5420
+          - samsung,exynos7-wdt                   # for Exynos7
+          - samsung,exynos850-wdt                 # for Exynos850
+          - samsung,exynosautov9-wdt              # for Exynosautov9
+      - items:
+          - enum:
+              - tesla,fsd-wdt
+          - const: samsung,exynos7-wdt
 
   reg:
     maxItems: 1
@@ -42,13 +48,14 @@ properties:
   samsung,cluster-index:
     $ref: /schemas/types.yaml#/definitions/uint32
     description:
-      Index of CPU cluster on which watchdog is running (in case of Exynos850)
+      Index of CPU cluster on which watchdog is running (in case of Exynos850
+      or Google gs101).
 
   samsung,syscon-phandle:
     $ref: /schemas/types.yaml#/definitions/phandle
     description:
       Phandle to the PMU system controller node (in case of Exynos5250,
-      Exynos5420, Exynos7 and Exynos850).
+      Exynos5420, Exynos7, Exynos850 and gs101).
 
 required:
   - compatible
@@ -64,6 +71,7 @@ allOf:
         compatible:
           contains:
             enum:
+              - google,gs101-wdt
               - samsung,exynos5250-wdt
               - samsung,exynos5420-wdt
               - samsung,exynos7-wdt
@@ -77,6 +85,7 @@ allOf:
         compatible:
           contains:
             enum:
+              - google,gs101-wdt
               - samsung,exynos850-wdt
               - samsung,exynosautov9-wdt
     then:
diff --git a/Documentation/driver-api/crypto/iaa/iaa-crypto.rst b/Documentation/driver-api/crypto/iaa/iaa-crypto.rst
new file mode 100644
index 000000000000..de587cf9cbed
--- /dev/null
+++ b/Documentation/driver-api/crypto/iaa/iaa-crypto.rst
@@ -0,0 +1,824 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=========================================
+IAA Compression Accelerator Crypto Driver
+=========================================
+
+Tom Zanussi <tom.zanussi@linux.intel.com>
+
+The IAA crypto driver supports compression/decompression compatible
+with the DEFLATE compression standard described in RFC 1951, which is
+the compression/decompression algorithm exported by this module.
+
+The IAA hardware spec can be found here:
+
+  https://cdrdv2.intel.com/v1/dl/getContent/721858
+
+The iaa_crypto driver is designed to work as a layer underneath
+higher-level compression devices such as zswap.
+
+Users can select IAA compress/decompress acceleration by specifying
+one of the supported IAA compression algorithms in whatever facility
+allows compression algorithms to be selected.
+
+For example, a zswap device can select the IAA 'fixed' mode
+represented by selecting the 'deflate-iaa' crypto compression
+algorithm::
+
+  # echo deflate-iaa > /sys/module/zswap/parameters/compressor
+
+This will tell zswap to use the IAA 'fixed' compression mode for all
+compresses and decompresses.
+
+Currently, there is only one compression modes available, 'fixed'
+mode.
+
+The 'fixed' compression mode implements the compression scheme
+specified by RFC 1951 and is given the crypto algorithm name
+'deflate-iaa'.  (Because the IAA hardware has a 4k history-window
+limitation, only buffers <= 4k, or that have been compressed using a
+<= 4k history window, are technically compliant with the deflate spec,
+which allows for a window of up to 32k.  Because of this limitation,
+the IAA fixed mode deflate algorithm is given its own algorithm name
+rather than simply 'deflate').
+
+
+Config options and other setup
+==============================
+
+The IAA crypto driver is available via menuconfig using the following
+path::
+
+  Cryptographic API -> Hardware crypto devices -> Support for Intel(R) IAA Compression Accelerator
+
+In the configuration file the option called CONFIG_CRYPTO_DEV_IAA_CRYPTO.
+
+The IAA crypto driver also supports statistics, which are available
+via menuconfig using the following path::
+
+  Cryptographic API -> Hardware crypto devices -> Support for Intel(R) IAA Compression -> Enable Intel(R) IAA Compression Accelerator Statistics
+
+In the configuration file the option called CONFIG_CRYPTO_DEV_IAA_CRYPTO_STATS.
+
+The following config options should also be enabled::
+
+  CONFIG_IRQ_REMAP=y
+  CONFIG_INTEL_IOMMU=y
+  CONFIG_INTEL_IOMMU_SVM=y
+  CONFIG_PCI_ATS=y
+  CONFIG_PCI_PRI=y
+  CONFIG_PCI_PASID=y
+  CONFIG_INTEL_IDXD=m
+  CONFIG_INTEL_IDXD_SVM=y
+
+IAA is one of the first Intel accelerator IPs that can work in
+conjunction with the Intel IOMMU.  There are multiple modes that exist
+for testing. Based on IOMMU configuration, there are 3 modes::
+
+  - Scalable
+  - Legacy
+  - No IOMMU
+
+
+Scalable mode
+-------------
+
+Scalable mode supports Shared Virtual Memory (SVM or SVA). It is
+entered when using the kernel boot commandline::
+
+  intel_iommu=on,sm_on
+
+with VT-d turned on in BIOS.
+
+With scalable mode, both shared and dedicated workqueues are available
+for use.
+
+For scalable mode, the following BIOS settings should be enabled::
+
+  Socket Configuration > IIO Configuration > Intel VT for Directed I/O (VT-d) > Intel VT for Directed I/O
+
+  Socket Configuration > IIO Configuration > PCIe ENQCMD > ENQCMDS
+
+
+Legacy mode
+-----------
+
+Legacy mode is entered when using the kernel boot commandline::
+
+  intel_iommu=off
+
+or VT-d is not turned on in BIOS.
+
+If you have booted into Linux and not sure if VT-d is on, do a "dmesg
+| grep -i dmar". If you don't see a number of DMAR devices enumerated,
+most likely VT-d is not on.
+
+With legacy mode, only dedicated workqueues are available for use.
+
+
+No IOMMU mode
+-------------
+
+No IOMMU mode is entered when using the kernel boot commandline::
+
+  iommu=off.
+
+With no IOMMU mode, only dedicated workqueues are available for use.
+
+
+Usage
+=====
+
+accel-config
+------------
+
+When loaded, the iaa_crypto driver automatically creates a default
+configuration and enables it, and assigns default driver attributes.
+If a different configuration or set of driver attributes is required,
+the user must first disable the IAA devices and workqueues, reset the
+configuration, and then re-register the deflate-iaa algorithm with the
+crypto subsystem by removing and reinserting the iaa_crypto module.
+
+The :ref:`iaa_disable_script` in the 'Use Cases'
+section below can be used to disable the default configuration.
+
+See :ref:`iaa_default_config` below for details of the default
+configuration.
+
+More likely than not, however, and because of the complexity and
+configurability of the accelerator devices, the user will want to
+configure the device and manually enable the desired devices and
+workqueues.
+
+The userspace tool to help doing that is called accel-config.  Using
+accel-config to configure device or loading a previously saved config
+is highly recommended.  The device can be controlled via sysfs
+directly but comes with the warning that you should do this ONLY if
+you know exactly what you are doing.  The following sections will not
+cover the sysfs interface but assumes you will be using accel-config.
+
+The :ref:`iaa_sysfs_config` section in the appendix below can be
+consulted for the sysfs interface details if interested.
+
+The accel-config tool along with instructions for building it can be
+found here:
+
+  https://github.com/intel/idxd-config/#readme
+
+Typical usage
+-------------
+
+In order for the iaa_crypto module to actually do any
+compression/decompression work on behalf of a facility, one or more
+IAA workqueues need to be bound to the iaa_crypto driver.
+
+For instance, here's an example of configuring an IAA workqueue and
+binding it to the iaa_crypto driver (note that device names are
+specified as 'iax' rather than 'iaa' - this is because upstream still
+has the old 'iax' device naming in place) ::
+
+  # configure wq1.0
+
+  accel-config config-wq --group-id=0 --mode=dedicated --type=kernel --name="iaa_crypto" --device_name="crypto" iax1/wq1.0
+
+  # enable IAA device iax1
+
+  accel-config enable-device iax1
+
+  # enable wq1.0 on IAX device iax1
+
+  accel-config enable-wq iax1/wq1.0
+
+Whenever a new workqueue is bound to or unbound from the iaa_crypto
+driver, the available workqueues are 'rebalanced' such that work
+submitted from a particular CPU is given to the most appropriate
+workqueue available.  Current best practice is to configure and bind
+at least one workqueue for each IAA device, but as long as there is at
+least one workqueue configured and bound to any IAA device in the
+system, the iaa_crypto driver will work, albeit most likely not as
+efficiently.
+
+The IAA crypto algorigthms is operational and compression and
+decompression operations are fully enabled following the successful
+binding of the first IAA workqueue to the iaa_crypto driver.
+
+Similarly, the IAA crypto algorithm is not operational and compression
+and decompression operations are disabled following the unbinding of
+the last IAA worqueue to the iaa_crypto driver.
+
+As a result, the IAA crypto algorithms and thus the IAA hardware are
+only available when one or more workques are bound to the iaa_crypto
+driver.
+
+When there are no IAA workqueues bound to the driver, the IAA crypto
+algorithms can be unregistered by removing the module.
+
+
+Driver attributes
+-----------------
+
+There are a couple user-configurable driver attributes that can be
+used to configure various modes of operation.  They're listed below,
+along with their default values.  To set any of these attributes, echo
+the appropriate values to the attribute file located under
+/sys/bus/dsa/drivers/crypto/
+
+The attribute settings at the time the IAA algorithms are registered
+are captured in each algorithm's crypto_ctx and used for all compresses
+and decompresses when using that algorithm.
+
+The available attributes are:
+
+  - verify_compress
+
+    Toggle compression verification.  If set, each compress will be
+    internally decompressed and the contents verified, returning error
+    codes if unsuccessful.  This can be toggled with 0/1::
+
+      echo 0 > /sys/bus/dsa/drivers/crypto/verify_compress
+
+    The default setting is '1' - verify all compresses.
+
+  - sync_mode
+
+    Select mode to be used to wait for completion of each compresses
+    and decompress operation.
+
+    The crypto async interface support implemented by iaa_crypto
+    provides an implementation that satisfies the interface but does
+    so in a synchronous manner - it fills and submits the IDXD
+    descriptor and then loops around waiting for it to complete before
+    returning.  This isn't a problem at the moment, since all existing
+    callers (e.g. zswap) wrap any asynchronous callees in a
+    synchronous wrapper anyway.
+
+    The iaa_crypto driver does however provide true asynchronous
+    support for callers that can make use of it.  In this mode, it
+    fills and submits the IDXD descriptor, then returns immediately
+    with -EINPROGRESS.  The caller can then either poll for completion
+    itself, which requires specific code in the caller which currently
+    nothing in the upstream kernel implements, or go to sleep and wait
+    for an interrupt signaling completion.  This latter mode is
+    supported by current users in the kernel such as zswap via
+    synchronous wrappers.  Although it is supported this mode is
+    significantly slower than the synchronous mode that does the
+    polling in the iaa_crypto driver previously mentioned.
+
+    This mode can be enabled by writing 'async_irq' to the sync_mode
+    iaa_crypto driver attribute::
+
+      echo async_irq > /sys/bus/dsa/drivers/crypto/sync_mode
+
+    Async mode without interrupts (caller must poll) can be enabled by
+    writing 'async' to it::
+
+      echo async > /sys/bus/dsa/drivers/crypto/sync_mode
+
+    The mode that does the polling in the iaa_crypto driver can be
+    enabled by writing 'sync' to it::
+
+      echo sync > /sys/bus/dsa/drivers/crypto/sync_mode
+
+    The default mode is 'sync'.
+
+.. _iaa_default_config:
+
+IAA Default Configuration
+-------------------------
+
+When the iaa_crypto driver is loaded, each IAA device has a single
+work queue configured for it, with the following attributes::
+
+          mode              "dedicated"
+          threshold         0
+          size              Total WQ Size from WQCAP
+          priority          10
+          type              IDXD_WQT_KERNEL
+          group             0
+          name              "iaa_crypto"
+          driver_name       "crypto"
+
+The devices and workqueues are also enabled and therefore the driver
+is ready to be used without any additional configuration.
+
+The default driver attributes in effect when the driver is loaded are::
+
+          sync_mode         "sync"
+          verify_compress   1
+
+In order to change either the device/work queue or driver attributes,
+the enabled devices and workqueues must first be disabled.  In order
+to have the new configuration applied to the deflate-iaa crypto
+algorithm, it needs to be re-registered by removing and reinserting
+the iaa_crypto module.  The :ref:`iaa_disable_script` in the 'Use
+Cases' section below can be used to disable the default configuration.
+
+Statistics
+==========
+
+If the optional debugfs statistics support is enabled, the IAA crypto
+driver will generate statistics which can be accessed in debugfs at::
+
+  # ls -al /sys/kernel/debug/iaa-crypto/
+  total 0
+  drwxr-xr-x  2 root root 0 Mar  3 09:35 .
+  drwx------ 47 root root 0 Mar  3 09:35 ..
+  -rw-r--r--  1 root root 0 Mar  3 09:35 max_acomp_delay_ns
+  -rw-r--r--  1 root root 0 Mar  3 09:35 max_adecomp_delay_ns
+  -rw-r--r--  1 root root 0 Mar  3 09:35 max_comp_delay_ns
+  -rw-r--r--  1 root root 0 Mar  3 09:35 max_decomp_delay_ns
+  -rw-r--r--  1 root root 0 Mar  3 09:35 stats_reset
+  -rw-r--r--  1 root root 0 Mar  3 09:35 total_comp_bytes_out
+  -rw-r--r--  1 root root 0 Mar  3 09:35 total_comp_calls
+  -rw-r--r--  1 root root 0 Mar  3 09:35 total_decomp_bytes_in
+  -rw-r--r--  1 root root 0 Mar  3 09:35 total_decomp_calls
+  -rw-r--r--  1 root root 0 Mar  3 09:35 wq_stats
+
+Most of the above statisticss are self-explanatory.  The wq_stats file
+shows per-wq stats, a set for each iaa device and wq in addition to
+some global stats::
+
+  # cat wq_stats
+  global stats:
+    total_comp_calls: 100
+    total_decomp_calls: 100
+    total_comp_bytes_out: 22800
+    total_decomp_bytes_in: 22800
+    total_completion_einval_errors: 0
+    total_completion_timeout_errors: 0
+    total_completion_comp_buf_overflow_errors: 0
+
+  iaa device:
+    id: 1
+    n_wqs: 1
+    comp_calls: 0
+    comp_bytes: 0
+    decomp_calls: 0
+    decomp_bytes: 0
+    wqs:
+      name: iaa_crypto
+      comp_calls: 0
+      comp_bytes: 0
+      decomp_calls: 0
+      decomp_bytes: 0
+
+  iaa device:
+    id: 3
+    n_wqs: 1
+    comp_calls: 0
+    comp_bytes: 0
+    decomp_calls: 0
+    decomp_bytes: 0
+    wqs:
+      name: iaa_crypto
+      comp_calls: 0
+      comp_bytes: 0
+      decomp_calls: 0
+      decomp_bytes: 0
+
+  iaa device:
+    id: 5
+    n_wqs: 1
+    comp_calls: 100
+    comp_bytes: 22800
+    decomp_calls: 100
+    decomp_bytes: 22800
+    wqs:
+      name: iaa_crypto
+      comp_calls: 100
+      comp_bytes: 22800
+      decomp_calls: 100
+      decomp_bytes: 22800
+
+Writing 0 to 'stats_reset' resets all the stats, including the
+per-device and per-wq stats::
+
+  # echo 0 > stats_reset
+  # cat wq_stats
+    global stats:
+    total_comp_calls: 0
+    total_decomp_calls: 0
+    total_comp_bytes_out: 0
+    total_decomp_bytes_in: 0
+    total_completion_einval_errors: 0
+    total_completion_timeout_errors: 0
+    total_completion_comp_buf_overflow_errors: 0
+    ...
+
+
+Use cases
+=========
+
+Simple zswap test
+-----------------
+
+For this example, the kernel should be configured according to the
+dedicated mode options described above, and zswap should be enabled as
+well::
+
+  CONFIG_ZSWAP=y
+
+This is a simple test that uses iaa_compress as the compressor for a
+swap (zswap) device.  It sets up the zswap device and then uses the
+memory_memadvise program listed below to forcibly swap out and in a
+specified number of pages, demonstrating both compress and decompress.
+
+The zswap test expects the work queues for each IAA device on the
+system to be configured properly as a kernel workqueue with a
+workqueue driver_name of "crypto".
+
+The first step is to make sure the iaa_crypto module is loaded::
+
+  modprobe iaa_crypto
+
+If the IAA devices and workqueues haven't previously been disabled and
+reconfigured, then the default configuration should be in place and no
+further IAA configuration is necessary.  See :ref:`iaa_default_config`
+below for details of the default configuration.
+
+If the default configuration is in place, you should see the iaa
+devices and wq0s enabled::
+
+  # cat /sys/bus/dsa/devices/iax1/state
+  enabled
+  # cat /sys/bus/dsa/devices/iax1/wq1.0/state
+  enabled
+
+To demonstrate that the following steps work as expected, these
+commands can be used to enable debug output::
+
+  # echo -n 'module iaa_crypto +p' > /sys/kernel/debug/dynamic_debug/control
+  # echo -n 'module idxd +p' > /sys/kernel/debug/dynamic_debug/control
+
+Use the following commands to enable zswap::
+
+  # echo 0 > /sys/module/zswap/parameters/enabled
+  # echo 50 > /sys/module/zswap/parameters/max_pool_percent
+  # echo deflate-iaa > /sys/module/zswap/parameters/compressor
+  # echo zsmalloc > /sys/module/zswap/parameters/zpool
+  # echo 1 > /sys/module/zswap/parameters/enabled
+  # echo 0 > /sys/module/zswap/parameters/same_filled_pages_enabled
+  # echo 100 > /proc/sys/vm/swappiness
+  # echo never > /sys/kernel/mm/transparent_hugepage/enabled
+  # echo 1 > /proc/sys/vm/overcommit_memory
+
+Now you can now run the zswap workload you want to measure. For
+example, using the memory_memadvise code below, the following command
+will swap in and out 100 pages::
+
+  ./memory_madvise 100
+
+  Allocating 100 pages to swap in/out
+  Swapping out 100 pages
+  Swapping in 100 pages
+  Swapped out and in 100 pages
+
+You should see something like the following in the dmesg output::
+
+  [  404.202972] idxd 0000:e7:02.0: iaa_comp_acompress: dma_map_sg, src_addr 223925c000, nr_sgs 1, req->src 00000000ee7cb5e6, req->slen 4096, sg_dma_len(sg) 4096
+  [  404.202973] idxd 0000:e7:02.0: iaa_comp_acompress: dma_map_sg, dst_addr 21dadf8000, nr_sgs 1, req->dst 000000008d6acea8, req->dlen 4096, sg_dma_len(sg) 8192
+  [  404.202975] idxd 0000:e7:02.0: iaa_compress: desc->src1_addr 223925c000, desc->src1_size 4096, desc->dst_addr 21dadf8000, desc->max_dst_size 4096, desc->src2_addr 2203543000, desc->src2_size 1568
+  [  404.202981] idxd 0000:e7:02.0: iaa_compress_verify: (verify) desc->src1_addr 21dadf8000, desc->src1_size 228, desc->dst_addr 223925c000, desc->max_dst_size 4096, desc->src2_addr 0, desc->src2_size 0
+  ...
+
+Now that basic functionality has been demonstrated, the defaults can
+be erased and replaced with a different configuration.  To do that,
+first disable zswap::
+
+  # echo lzo > /sys/module/zswap/parameters/compressor
+  # swapoff -a
+  # echo 0 > /sys/module/zswap/parameters/accept_threshold_percent
+  # echo 0 > /sys/module/zswap/parameters/max_pool_percent
+  # echo 0 > /sys/module/zswap/parameters/enabled
+  # echo 0 > /sys/module/zswap/parameters/enabled
+
+Then run the :ref:`iaa_disable_script` in the 'Use Cases' section
+below to disable the default configuration.
+
+Finally turn swap back on::
+
+  # swapon -a
+
+Following all that the IAA device(s) can now be re-configured and
+enabled as desired for further testing.  Below is one example.
+
+The zswap test expects the work queues for each IAA device on the
+system to be configured properly as a kernel workqueue with a
+workqueue driver_name of "crypto".
+
+The below script automatically does that::
+
+  #!/bin/bash
+
+  echo "IAA devices:"
+  lspci -d:0cfe
+  echo "# IAA devices:"
+  lspci -d:0cfe | wc -l
+
+  #
+  # count iaa instances
+  #
+  iaa_dev_id="0cfe"
+  num_iaa=$(lspci -d:${iaa_dev_id} | wc -l)
+  echo "Found ${num_iaa} IAA instances"
+
+  #
+  # disable iaa wqs and devices
+  #
+  echo "Disable IAA"
+
+  for ((i = 1; i < ${num_iaa} * 2; i += 2)); do
+      echo disable wq iax${i}/wq${i}.0
+      accel-config disable-wq iax${i}/wq${i}.0
+      echo disable iaa iax${i}
+      accel-config disable-device iax${i}
+  done
+
+  echo "End Disable IAA"
+
+  #
+  # configure iaa wqs and devices
+  #
+  echo "Configure IAA"
+  for ((i = 1; i < ${num_iaa} * 2; i += 2)); do
+      accel-config config-wq --group-id=0 --mode=dedicated --size=128 --priority=10 --type=kernel --name="iaa_crypto" --driver_name="crypto" iax${i}/wq${i}
+  done
+
+  echo "End Configure IAA"
+
+  #
+  # enable iaa wqs and devices
+  #
+  echo "Enable IAA"
+
+  for ((i = 1; i < ${num_iaa} * 2; i += 2)); do
+      echo enable iaa iaa${i}
+      accel-config enable-device iaa${i}
+      echo enable wq iaa${i}/wq${i}.0
+      accel-config enable-wq iaa${i}/wq${i}.0
+  done
+
+  echo "End Enable IAA"
+
+When the workqueues are bound to the iaa_crypto driver, you should
+see something similar to the following in dmesg output if you've
+enabled debug output (echo -n 'module iaa_crypto +p' >
+/sys/kernel/debug/dynamic_debug/control)::
+
+  [   60.752344] idxd 0000:f6:02.0: add_iaa_wq: added wq 000000004068d14d to iaa 00000000c9585ba2, n_wq 1
+  [   60.752346] iaa_crypto: rebalance_wq_table: nr_nodes=2, nr_cpus 160, nr_iaa 8, cpus_per_iaa 20
+  [   60.752347] iaa_crypto: rebalance_wq_table: iaa=0
+  [   60.752349] idxd 0000:6a:02.0: request_iaa_wq: getting wq from iaa_device 0000000042d7bc52 (0)
+  [   60.752350] idxd 0000:6a:02.0: request_iaa_wq: returning unused wq 00000000c8bb4452 (0) from iaa device 0000000042d7bc52 (0)
+  [   60.752352] iaa_crypto: rebalance_wq_table: assigned wq for cpu=0, node=0 = wq 00000000c8bb4452
+  [   60.752354] iaa_crypto: rebalance_wq_table: iaa=0
+  [   60.752355] idxd 0000:6a:02.0: request_iaa_wq: getting wq from iaa_device 0000000042d7bc52 (0)
+  [   60.752356] idxd 0000:6a:02.0: request_iaa_wq: returning unused wq 00000000c8bb4452 (0) from iaa device 0000000042d7bc52 (0)
+  [   60.752358] iaa_crypto: rebalance_wq_table: assigned wq for cpu=1, node=0 = wq 00000000c8bb4452
+  [   60.752359] iaa_crypto: rebalance_wq_table: iaa=0
+  [   60.752360] idxd 0000:6a:02.0: request_iaa_wq: getting wq from iaa_device 0000000042d7bc52 (0)
+  [   60.752361] idxd 0000:6a:02.0: request_iaa_wq: returning unused wq 00000000c8bb4452 (0) from iaa device 0000000042d7bc52 (0)
+  [   60.752362] iaa_crypto: rebalance_wq_table: assigned wq for cpu=2, node=0 = wq 00000000c8bb4452
+  [   60.752364] iaa_crypto: rebalance_wq_table: iaa=0
+  .
+  .
+  .
+
+Once the workqueues and devices have been enabled, the IAA crypto
+algorithms are enabled and available.  When the IAA crypto algorithms
+have been successfully enabled, you should see the following dmesg
+output::
+
+  [   64.893759] iaa_crypto: iaa_crypto_enable: iaa_crypto now ENABLED
+
+Now run the following zswap-specific setup commands to have zswap use
+the 'fixed' compression mode::
+
+  echo 0 > /sys/module/zswap/parameters/enabled
+  echo 50 > /sys/module/zswap/parameters/max_pool_percent
+  echo deflate-iaa > /sys/module/zswap/parameters/compressor
+  echo zsmalloc > /sys/module/zswap/parameters/zpool
+  echo 1 > /sys/module/zswap/parameters/enabled
+  echo 0 > /sys/module/zswap/parameters/same_filled_pages_enabled
+
+  echo 100 > /proc/sys/vm/swappiness
+  echo never > /sys/kernel/mm/transparent_hugepage/enabled
+  echo 1 > /proc/sys/vm/overcommit_memory
+
+Finally, you can now run the zswap workload you want to measure. For
+example, using the code below, the following command will swap in and
+out 100 pages::
+
+  ./memory_madvise 100
+
+  Allocating 100 pages to swap in/out
+  Swapping out 100 pages
+  Swapping in 100 pages
+  Swapped out and in 100 pages
+
+You should see something like the following in the dmesg output if
+you've enabled debug output (echo -n 'module iaa_crypto +p' >
+/sys/kernel/debug/dynamic_debug/control)::
+
+  [  404.202972] idxd 0000:e7:02.0: iaa_comp_acompress: dma_map_sg, src_addr 223925c000, nr_sgs 1, req->src 00000000ee7cb5e6, req->slen 4096, sg_dma_len(sg) 4096
+  [  404.202973] idxd 0000:e7:02.0: iaa_comp_acompress: dma_map_sg, dst_addr 21dadf8000, nr_sgs 1, req->dst 000000008d6acea8, req->dlen 4096, sg_dma_len(sg) 8192
+  [  404.202975] idxd 0000:e7:02.0: iaa_compress: desc->src1_addr 223925c000, desc->src1_size 4096, desc->dst_addr 21dadf8000, desc->max_dst_size 4096, desc->src2_addr 2203543000, desc->src2_size 1568
+  [  404.202981] idxd 0000:e7:02.0: iaa_compress_verify: (verify) desc->src1_addr 21dadf8000, desc->src1_size 228, desc->dst_addr 223925c000, desc->max_dst_size 4096, desc->src2_addr 0, desc->src2_size 0
+  [  409.203227] idxd 0000:e7:02.0: iaa_comp_adecompress: dma_map_sg, src_addr 21ddd8b100, nr_sgs 1, req->src 0000000084adab64, req->slen 228, sg_dma_len(sg) 228
+  [  409.203235] idxd 0000:e7:02.0: iaa_comp_adecompress: dma_map_sg, dst_addr 21ee3dc000, nr_sgs 1, req->dst 000000004e2990d0, req->dlen 4096, sg_dma_len(sg) 4096
+  [  409.203239] idxd 0000:e7:02.0: iaa_decompress: desc->src1_addr 21ddd8b100, desc->src1_size 228, desc->dst_addr 21ee3dc000, desc->max_dst_size 4096, desc->src2_addr 0, desc->src2_size 0
+  [  409.203254] idxd 0000:e7:02.0: iaa_comp_adecompress: dma_map_sg, src_addr 21ddd8b100, nr_sgs 1, req->src 0000000084adab64, req->slen 228, sg_dma_len(sg) 228
+  [  409.203256] idxd 0000:e7:02.0: iaa_comp_adecompress: dma_map_sg, dst_addr 21f1551000, nr_sgs 1, req->dst 000000004e2990d0, req->dlen 4096, sg_dma_len(sg) 4096
+  [  409.203257] idxd 0000:e7:02.0: iaa_decompress: desc->src1_addr 21ddd8b100, desc->src1_size 228, desc->dst_addr 21f1551000, desc->max_dst_size 4096, desc->src2_addr 0, desc->src2_size 0
+
+In order to unregister the IAA crypto algorithms, and register new
+ones using different parameters, any users of the current algorithm
+should be stopped and the IAA workqueues and devices disabled.
+
+In the case of zswap, remove the IAA crypto algorithm as the
+compressor and turn off swap (to remove all references to
+iaa_crypto)::
+
+  echo lzo > /sys/module/zswap/parameters/compressor
+  swapoff -a
+
+  echo 0 > /sys/module/zswap/parameters/accept_threshold_percent
+  echo 0 > /sys/module/zswap/parameters/max_pool_percent
+  echo 0 > /sys/module/zswap/parameters/enabled
+
+Once zswap is disabled and no longer using iaa_crypto, the IAA wqs and
+devices can be disabled.
+
+.. _iaa_disable_script:
+
+IAA disable script
+------------------
+
+The below script automatically does that::
+
+  #!/bin/bash
+
+  echo "IAA devices:"
+  lspci -d:0cfe
+  echo "# IAA devices:"
+  lspci -d:0cfe | wc -l
+
+  #
+  # count iaa instances
+  #
+  iaa_dev_id="0cfe"
+  num_iaa=$(lspci -d:${iaa_dev_id} | wc -l)
+  echo "Found ${num_iaa} IAA instances"
+
+  #
+  # disable iaa wqs and devices
+  #
+  echo "Disable IAA"
+
+  for ((i = 1; i < ${num_iaa} * 2; i += 2)); do
+      echo disable wq iax${i}/wq${i}.0
+      accel-config disable-wq iax${i}/wq${i}.0
+      echo disable iaa iax${i}
+      accel-config disable-device iax${i}
+  done
+
+  echo "End Disable IAA"
+
+Finally, at this point the iaa_crypto module can be removed, which
+will unregister the current IAA crypto algorithms::
+
+  rmmod iaa_crypto
+
+
+memory_madvise.c (gcc -o memory_memadvise memory_madvise.c)::
+
+  #include <stdio.h>
+  #include <stdlib.h>
+  #include <string.h>
+  #include <unistd.h>
+  #include <sys/mman.h>
+  #include <linux/mman.h>
+
+  #ifndef MADV_PAGEOUT
+  #define MADV_PAGEOUT    21      /* force pages out immediately */
+  #endif
+
+  #define PG_SZ           4096
+
+  int main(int argc, char **argv)
+  {
+        int i, nr_pages = 1;
+        int64_t *dump_ptr;
+        char *addr, *a;
+        int loop = 1;
+
+        if (argc > 1)
+                nr_pages = atoi(argv[1]);
+
+        printf("Allocating %d pages to swap in/out\n", nr_pages);
+
+        /* allocate pages */
+        addr = mmap(NULL, nr_pages * PG_SZ, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+        *addr = 1;
+
+        /* initialize data in page to all '*' chars */
+        memset(addr, '*', nr_pages * PG_SZ);
+
+         printf("Swapping out %d pages\n", nr_pages);
+
+        /* Tell kernel to swap it out */
+        madvise(addr, nr_pages * PG_SZ, MADV_PAGEOUT);
+
+        while (loop > 0) {
+                /* Wait for swap out to finish */
+                sleep(5);
+
+                a = addr;
+
+                printf("Swapping in %d pages\n", nr_pages);
+
+                /* Access the page ... this will swap it back in again */
+                for (i = 0; i < nr_pages; i++) {
+                        if (a[0] != '*') {
+                                printf("Bad data from decompress!!!!!\n");
+
+                                dump_ptr = (int64_t *)a;
+                                 for (int j = 0; j < 100; j++) {
+                                        printf("  page %d data: %#llx\n", i, *dump_ptr);
+                                        dump_ptr++;
+                                }
+                        }
+
+                        a += PG_SZ;
+                }
+
+                loop --;
+        }
+
+       printf("Swapped out and in %d pages\n", nr_pages);
+
+Appendix
+========
+
+.. _iaa_sysfs_config:
+
+IAA sysfs config interface
+--------------------------
+
+Below is a description of the IAA sysfs interface, which as mentioned
+in the main document, should only be used if you know exactly what you
+are doing.  Even then, there's no compelling reason to use it directly
+since accel-config can do everything the sysfs interface can and in
+fact accel-config is based on it under the covers.
+
+The 'IAA config path' is /sys/bus/dsa/devices and contains
+subdirectories representing each IAA device, workqueue, engine, and
+group.  Note that in the sysfs interface, the IAA devices are actually
+named using iax e.g. iax1, iax3, etc. (Note that IAA devices are the
+odd-numbered devices; the even-numbered devices are DSA devices and
+can be ignored for IAA).
+
+The 'IAA device bind path' is /sys/bus/dsa/drivers/idxd/bind and is
+the file that is written to enable an IAA device.
+
+The 'IAA workqueue bind path' is /sys/bus/dsa/drivers/crypto/bind and
+is the file that is written to enable an IAA workqueue.
+
+Similarly /sys/bus/dsa/drivers/idxd/unbind and
+/sys/bus/dsa/drivers/crypto/unbind are used to disable IAA devices and
+workqueues.
+
+The basic sequence of commands needed to set up the IAA devices and
+workqueues is:
+
+For each device::
+  1) Disable any workqueues enabled on the device.  For example to
+     disable workques 0 and 1 on IAA device 3::
+
+       # echo wq3.0 > /sys/bus/dsa/drivers/crypto/unbind
+       # echo wq3.1 > /sys/bus/dsa/drivers/crypto/unbind
+
+  2) Disable the device. For example to disable IAA device 3::
+
+       # echo iax3 > /sys/bus/dsa/drivers/idxd/unbind
+
+  3) configure the desired workqueues.  For example, to configure
+     workqueue 3 on IAA device 3::
+
+       # echo dedicated > /sys/bus/dsa/devices/iax3/wq3.3/mode
+       # echo 128 > /sys/bus/dsa/devices/iax3/wq3.3/size
+       # echo 0 > /sys/bus/dsa/devices/iax3/wq3.3/group_id
+       # echo 10 > /sys/bus/dsa/devices/iax3/wq3.3/priority
+       # echo "kernel" > /sys/bus/dsa/devices/iax3/wq3.3/type
+       # echo "iaa_crypto" > /sys/bus/dsa/devices/iax3/wq3.3/name
+       # echo "crypto" > /sys/bus/dsa/devices/iax3/wq3.3/driver_name
+
+  4) Enable the device. For example to enable IAA device 3::
+
+       # echo iax3 > /sys/bus/dsa/drivers/idxd/bind
+
+  5) Enable the desired workqueues on the device.  For example to
+     enable workques 0 and 1 on IAA device 3::
+
+       # echo wq3.0 > /sys/bus/dsa/drivers/crypto/bind
+       # echo wq3.1 > /sys/bus/dsa/drivers/crypto/bind
diff --git a/Documentation/driver-api/crypto/iaa/index.rst b/Documentation/driver-api/crypto/iaa/index.rst
new file mode 100644
index 000000000000..aa6837e27264
--- /dev/null
+++ b/Documentation/driver-api/crypto/iaa/index.rst
@@ -0,0 +1,20 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=================================
+IAA (Intel Analytics Accelerator)
+=================================
+
+IAA provides hardware compression and decompression via the crypto
+API.
+
+.. toctree::
+   :maxdepth: 1
+
+   iaa-crypto
+
+.. only::  subproject and html
+
+   Indices
+   =======
+
+   * :ref:`genindex`
diff --git a/Documentation/driver-api/crypto/index.rst b/Documentation/driver-api/crypto/index.rst
new file mode 100644
index 000000000000..fb9709b98bea
--- /dev/null
+++ b/Documentation/driver-api/crypto/index.rst
@@ -0,0 +1,20 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============
+Crypto Drivers
+==============
+
+Documentation for crypto drivers that may need more involved setup and
+configuration.
+
+.. toctree::
+   :maxdepth: 1
+
+   iaa/index
+
+.. only::  subproject and html
+
+   Indices
+   =======
+
+   * :ref:`genindex`
diff --git a/Documentation/driver-api/device-io.rst b/Documentation/driver-api/device-io.rst
index 2c7abd234f4e..d55384b106bd 100644
--- a/Documentation/driver-api/device-io.rst
+++ b/Documentation/driver-api/device-io.rst
@@ -408,11 +408,12 @@ functions for details on the CPU side of things.
 ioremap_uc()
 ------------
 
-ioremap_uc() behaves like ioremap() except that on the x86 architecture without
-'PAT' mode, it marks memory as uncached even when the MTRR has designated
-it as cacheable, see Documentation/arch/x86/pat.rst.
+ioremap_uc() is only meaningful on old x86-32 systems with the PAT extension,
+and on ia64 with its slightly unconventional ioremap() behavior, everywhere
+elss ioremap_uc() defaults to return NULL.
 
-Portable drivers should avoid the use of ioremap_uc().
+
+Portable drivers should avoid the use of ioremap_uc(), use ioremap() instead.
 
 ioremap_cache()
 ---------------
diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst
index b38f81836118..eba851605388 100644
--- a/Documentation/driver-api/index.rst
+++ b/Documentation/driver-api/index.rst
@@ -110,6 +110,8 @@ available subsections can be seen below.
    hte/index
    wmi
    dpll
+   wbrf
+   crypto/index
    tee
 
 .. only::  subproject and html
diff --git a/Documentation/driver-api/mtd/spi-nor.rst b/Documentation/driver-api/mtd/spi-nor.rst
index c22f8c0f7950..148fa4288760 100644
--- a/Documentation/driver-api/mtd/spi-nor.rst
+++ b/Documentation/driver-api/mtd/spi-nor.rst
@@ -2,64 +2,204 @@
 SPI NOR framework
 =================
 
-Part I - Why do we need this framework?
----------------------------------------
-
-SPI bus controllers (drivers/spi/) only deal with streams of bytes; the bus
-controller operates agnostic of the specific device attached. However, some
-controllers (such as Freescale's QuadSPI controller) cannot easily handle
-arbitrary streams of bytes, but rather are designed specifically for SPI NOR.
-
-In particular, Freescale's QuadSPI controller must know the NOR commands to
-find the right LUT sequence. Unfortunately, the SPI subsystem has no notion of
-opcodes, addresses, or data payloads; a SPI controller simply knows to send or
-receive bytes (Tx and Rx). Therefore, we must define a new layering scheme under
-which the controller driver is aware of the opcodes, addressing, and other
-details of the SPI NOR protocol.
-
-Part II - How does the framework work?
---------------------------------------
-
-This framework just adds a new layer between the MTD and the SPI bus driver.
-With this new layer, the SPI NOR controller driver does not depend on the
-m25p80 code anymore.
-
-Before this framework, the layer is like::
-
-                   MTD
-         ------------------------
-                  m25p80
-         ------------------------
-	       SPI bus driver
-         ------------------------
-	        SPI NOR chip
-
-After this framework, the layer is like::
-
-                   MTD
-         ------------------------
-              SPI NOR framework
-         ------------------------
-                  m25p80
-         ------------------------
-	       SPI bus driver
-         ------------------------
-	       SPI NOR chip
-
-With the SPI NOR controller driver (Freescale QuadSPI), it looks like::
-
-                   MTD
-         ------------------------
-              SPI NOR framework
-         ------------------------
-                fsl-quadSPI
-         ------------------------
-	       SPI NOR chip
-
-Part III - How can drivers use the framework?
----------------------------------------------
-
-The main API is spi_nor_scan(). Before you call the hook, a driver should
-initialize the necessary fields for spi_nor{}. Please see
-drivers/mtd/spi-nor/spi-nor.c for detail. Please also refer to spi-fsl-qspi.c
-when you want to write a new driver for a SPI NOR controller.
+How to propose a new flash addition
+-----------------------------------
+
+Most SPI NOR flashes comply with the JEDEC JESD216
+Serial Flash Discoverable Parameter (SFDP) standard. SFDP describes
+the functional and feature capabilities of serial flash devices in a
+standard set of internal read-only parameter tables.
+
+The SPI NOR driver queries the SFDP tables in order to determine the
+flash's parameters and settings. If the flash defines the SFDP tables
+it's likely that you won't need a flash entry at all, and instead
+rely on the generic flash driver which probes the flash solely based
+on its SFDP data. All one has to do is to specify the "jedec,spi-nor"
+compatible in the device tree.
+
+There are cases however where you need to define an explicit flash
+entry. This typically happens when the flash has settings or support
+that is not covered by the SFDP tables (e.g. Block Protection), or
+when the flash contains mangled SFDP data. If the later, one needs
+to implement the ``spi_nor_fixups`` hooks in order to amend the SFDP
+parameters with the correct values.
+
+Minimum testing requirements
+-----------------------------
+
+Do all the tests from below and paste them in the commit's comments
+section, after the ``---`` marker.
+
+1) Specify the controller that you used to test the flash and specify
+   the frequency at which the flash was operated, e.g.::
+
+    This flash is populated on the X board and was tested at Y
+    frequency using the Z (put compatible) SPI controller.
+
+2) Dump the sysfs entries and print the md5/sha1/sha256 SFDP checksum::
+
+    root@1:~# cat /sys/bus/spi/devices/spi0.0/spi-nor/partname
+    sst26vf064b
+    root@1:~# cat /sys/bus/spi/devices/spi0.0/spi-nor/jedec_id
+    bf2643
+    root@1:~# cat /sys/bus/spi/devices/spi0.0/spi-nor/manufacturer
+    sst
+    root@1:~# xxd -p /sys/bus/spi/devices/spi0.0/spi-nor/sfdp
+    53464450060102ff00060110300000ff81000106000100ffbf0001180002
+    0001fffffffffffffffffffffffffffffffffd20f1ffffffff0344eb086b
+    083b80bbfeffffffffff00ffffff440b0c200dd80fd810d820914824806f
+    1d81ed0f773830b030b0f7ffffff29c25cfff030c080ffffffffffffffff
+    ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
+    ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
+    ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
+    ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
+    ffffffffffffffffffffffffffffffffff0004fff37f0000f57f0000f9ff
+    7d00f57f0000f37f0000ffffffffffffffffffffffffffffffffffffffff
+    ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
+    ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
+    ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
+    ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
+    ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
+    ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
+    ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
+    ffffbf2643ffb95ffdff30f260f332ff0a122346ff0f19320f1919ffffff
+    ffffffff00669938ff05013506040232b03072428de89888a585c09faf5a
+    ffff06ec060c0003080bffffffffff07ffff0202ff060300fdfd040700fc
+    0300fefe0202070e
+    root@1:~# sha256sum /sys/bus/spi/devices/spi0.0/spi-nor/sfdp
+    428f34d0461876f189ac97f93e68a05fa6428c6650b3b7baf736a921e5898ed1  /sys/bus/spi/devices/spi0.0/spi-nor/sfdp
+
+   Please dump the SFDP tables using ``xxd -p``. It enables us to do
+   the reverse operation and convert the hexdump to binary with
+   ``xxd -rp``. Dumping the SFDP data with ``hexdump -Cv`` is accepted,
+   but less desirable.
+
+3) Dump debugfs data::
+
+    root@1:~# cat /sys/kernel/debug/spi-nor/spi0.0/capabilities
+    Supported read modes by the flash
+     1S-1S-1S
+      opcode		0x03
+      mode cycles	0
+      dummy cycles	0
+     1S-1S-1S (fast read)
+      opcode		0x0b
+      mode cycles	0
+      dummy cycles	8
+     1S-1S-2S
+      opcode		0x3b
+      mode cycles	0
+      dummy cycles	8
+     1S-2S-2S
+      opcode		0xbb
+      mode cycles	4
+      dummy cycles	0
+     1S-1S-4S
+      opcode		0x6b
+      mode cycles	0
+      dummy cycles	8
+     1S-4S-4S
+      opcode		0xeb
+      mode cycles	2
+      dummy cycles	4
+     4S-4S-4S
+      opcode		0x0b
+      mode cycles	2
+      dummy cycles	4
+
+    Supported page program modes by the flash
+     1S-1S-1S
+      opcode	0x02
+
+    root@1:~# cat /sys/kernel/debug/spi-nor/spi0.0/params
+    name		sst26vf064b
+    id			bf 26 43 bf 26 43
+    size		8.00 MiB
+    write size		1
+    page size		256
+    address nbytes	3
+    flags		HAS_LOCK | HAS_16BIT_SR | SOFT_RESET | SWP_IS_VOLATILE
+
+    opcodes
+     read		0xeb
+      dummy cycles	6
+     erase		0x20
+     program		0x02
+     8D extension	none
+
+    protocols
+     read		1S-4S-4S
+     write		1S-1S-1S
+     register		1S-1S-1S
+
+    erase commands
+     20 (4.00 KiB) [0]
+     d8 (8.00 KiB) [1]
+     d8 (32.0 KiB) [2]
+     d8 (64.0 KiB) [3]
+     c7 (8.00 MiB)
+
+    sector map
+     region (in hex)   | erase mask | flags
+     ------------------+------------+----------
+     00000000-00007fff |     [01  ] |
+     00008000-0000ffff |     [0 2 ] |
+     00010000-007effff |     [0  3] |
+     007f0000-007f7fff |     [0 2 ] |
+     007f8000-007fffff |     [01  ] |
+
+4) Use `mtd-utils <https://git.infradead.org/mtd-utils.git>`__
+   and verify that erase, read and page program operations work fine::
+
+    root@1:~# dd if=/dev/urandom of=./spi_test bs=1M count=2
+    2+0 records in
+    2+0 records out
+    2097152 bytes (2.1 MB, 2.0 MiB) copied, 0.848566 s, 2.5 MB/s
+
+    root@1:~# mtd_debug erase /dev/mtd0 0 2097152
+    Erased 2097152 bytes from address 0x00000000 in flash
+
+    root@1:~# mtd_debug read /dev/mtd0 0 2097152 spi_read
+    Copied 2097152 bytes from address 0x00000000 in flash to spi_read
+
+    root@1:~# hexdump spi_read
+    0000000 ffff ffff ffff ffff ffff ffff ffff ffff
+    *
+    0200000
+
+    root@1:~# sha256sum spi_read
+    4bda3a28f4ffe603c0ec1258c0034d65a1a0d35ab7bd523a834608adabf03cc5  spi_read
+
+    root@1:~# mtd_debug write /dev/mtd0 0 2097152 spi_test
+    Copied 2097152 bytes from spi_test to address 0x00000000 in flash
+
+    root@1:~# mtd_debug read /dev/mtd0 0 2097152 spi_read
+    Copied 2097152 bytes from address 0x00000000 in flash to spi_read
+
+    root@1:~# sha256sum spi*
+    c444216a6ba2a4a66cccd60a0dd062bce4b865dd52b200ef5e21838c4b899ac8  spi_read
+    c444216a6ba2a4a66cccd60a0dd062bce4b865dd52b200ef5e21838c4b899ac8  spi_test
+
+   If the flash comes erased by default and the previous erase was ignored,
+   we won't catch it, thus test the erase again::
+
+    root@1:~# mtd_debug erase /dev/mtd0 0 2097152
+    Erased 2097152 bytes from address 0x00000000 in flash
+
+    root@1:~# mtd_debug read /dev/mtd0 0 2097152 spi_read
+    Copied 2097152 bytes from address 0x00000000 in flash to spi_read
+
+    root@1:~# sha256sum spi*
+    4bda3a28f4ffe603c0ec1258c0034d65a1a0d35ab7bd523a834608adabf03cc5  spi_read
+    c444216a6ba2a4a66cccd60a0dd062bce4b865dd52b200ef5e21838c4b899ac8  spi_test
+
+   Dump some other relevant data::
+
+    root@1:~# mtd_debug info /dev/mtd0
+    mtd.type = MTD_NORFLASH
+    mtd.flags = MTD_CAP_NORFLASH
+    mtd.size = 8388608 (8M)
+    mtd.erasesize = 4096 (4K)
+    mtd.writesize = 1
+    mtd.oobsize = 0
+    regions = 0
diff --git a/Documentation/driver-api/surface_aggregator/ssh.rst b/Documentation/driver-api/surface_aggregator/ssh.rst
index b955b673838b..58a757319931 100644
--- a/Documentation/driver-api/surface_aggregator/ssh.rst
+++ b/Documentation/driver-api/surface_aggregator/ssh.rst
@@ -39,7 +39,7 @@ Note that the standard disclaimer for this subsystem also applies to this
 document: All of this has been reverse-engineered and may thus be erroneous
 and/or incomplete.
 
-All CRCs used in the following are two-byte ``crc_ccitt_false(0xffff, ...)``.
+All CRCs used in the following are two-byte ``crc_itu_t(0xffff, ...)``.
 All multi-byte values are little-endian, there is no implicit padding between
 values.
 
diff --git a/Documentation/driver-api/wbrf.rst b/Documentation/driver-api/wbrf.rst
new file mode 100644
index 000000000000..f48bfa029813
--- /dev/null
+++ b/Documentation/driver-api/wbrf.rst
@@ -0,0 +1,78 @@
+.. SPDX-License-Identifier: GPL-2.0-or-later
+
+=================================
+WBRF - Wifi Band RFI Mitigations
+=================================
+
+Due to electrical and mechanical constraints in certain platform designs
+there may be likely interference of relatively high-powered harmonics of
+the GPU memory clocks with local radio module frequency bands used by
+certain Wifi bands.
+
+To mitigate possible RFI interference producers can advertise the
+frequencies in use and consumers can use this information to avoid using
+these frequencies for sensitive features.
+
+When a platform is known to have this issue with any contained devices,
+the platform designer will advertise the availability of this feature via
+ACPI devices with a device specific method (_DSM).
+* Producers with this _DSM will be able to advertise the frequencies in use.
+* Consumers with this _DSM will be able to register for notifications of
+frequencies in use.
+
+Some general terms
+==================
+
+Producer: such component who can produce high-powered radio frequency
+Consumer: such component who can adjust its in-use frequency in
+response to the radio frequencies of other components to mitigate the
+possible RFI.
+
+To make the mechanism function, those producers should notify active use
+of their particular frequencies so that other consumers can make relative
+internal adjustments as necessary to avoid this resonance.
+
+ACPI interface
+==============
+
+Although initially used by for wifi + dGPU use cases, the ACPI interface
+can be scaled to any type of device that a platform designer discovers
+can cause interference.
+
+The GUID used for the _DSM is 7B7656CF-DC3D-4C1C-83E9-66E721DE3070.
+
+3 functions are available in this _DSM:
+
+* 0: discover # of functions available
+* 1: record RF bands in use
+* 2: retrieve RF bands in use
+
+Driver programming interface
+============================
+
+.. kernel-doc:: drivers/platform/x86/amd/wbrf.c
+
+Sample Usage
+=============
+
+The expected flow for the producers:
+1. During probe, call `acpi_amd_wbrf_supported_producer` to check if WBRF
+can be enabled for the device.
+2. On using some frequency band, call `acpi_amd_wbrf_add_remove` with 'add'
+param to get other consumers properly notified.
+3. Or on stopping using some frequency band, call
+`acpi_amd_wbrf_add_remove` with 'remove' param to get other consumers notified.
+
+The expected flow for the consumers:
+1. During probe, call `acpi_amd_wbrf_supported_consumer` to check if WBRF
+can be enabled for the device.
+2. Call `amd_wbrf_register_notifier` to register for notification
+of frequency band change(add or remove) from other producers.
+3. Call the `amd_wbrf_retrieve_freq_band` initally to retrieve
+current active frequency bands considering some producers may broadcast
+such information before the consumer is up.
+4. On receiving a notification for frequency band change, run
+`amd_wbrf_retrieve_freq_band` again to retrieve the latest
+active frequency bands.
+5. During driver cleanup, call `amd_wbrf_unregister_notifier` to
+unregister the notifier.
diff --git a/Documentation/filesystems/erofs.rst b/Documentation/filesystems/erofs.rst
index 57c6ae23b3fc..cc4626d6ee4f 100644
--- a/Documentation/filesystems/erofs.rst
+++ b/Documentation/filesystems/erofs.rst
@@ -91,6 +91,10 @@ compatibility checking tool (fsck.erofs), and a debugging tool (dump.erofs):
 
 - git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs-utils.git
 
+For more information, please also refer to the documentation site:
+
+- https://erofs.docs.kernel.org
+
 Bugs and patches are welcome, please kindly help us and send to the following
 linux-erofs mailing list:
 
diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst
index 1b84f818e574..e86b886b64d0 100644
--- a/Documentation/filesystems/fscrypt.rst
+++ b/Documentation/filesystems/fscrypt.rst
@@ -31,15 +31,15 @@ However, except for filenames, fscrypt does not encrypt filesystem
 metadata.
 
 Unlike eCryptfs, which is a stacked filesystem, fscrypt is integrated
-directly into supported filesystems --- currently ext4, F2FS, and
-UBIFS.  This allows encrypted files to be read and written without
-caching both the decrypted and encrypted pages in the pagecache,
-thereby nearly halving the memory used and bringing it in line with
-unencrypted files.  Similarly, half as many dentries and inodes are
-needed.  eCryptfs also limits encrypted filenames to 143 bytes,
-causing application compatibility issues; fscrypt allows the full 255
-bytes (NAME_MAX).  Finally, unlike eCryptfs, the fscrypt API can be
-used by unprivileged users, with no need to mount anything.
+directly into supported filesystems --- currently ext4, F2FS, UBIFS,
+and CephFS.  This allows encrypted files to be read and written
+without caching both the decrypted and encrypted pages in the
+pagecache, thereby nearly halving the memory used and bringing it in
+line with unencrypted files.  Similarly, half as many dentries and
+inodes are needed.  eCryptfs also limits encrypted filenames to 143
+bytes, causing application compatibility issues; fscrypt allows the
+full 255 bytes (NAME_MAX).  Finally, unlike eCryptfs, the fscrypt API
+can be used by unprivileged users, with no need to mount anything.
 
 fscrypt does not support encrypting files in-place.  Instead, it
 supports marking an empty directory as encrypted.  Then, after
@@ -1382,7 +1382,8 @@ directory.)  These structs are defined as follows::
             u8 contents_encryption_mode;
             u8 filenames_encryption_mode;
             u8 flags;
-            u8 __reserved[4];
+            u8 log2_data_unit_size;
+            u8 __reserved[3];
             u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
             u8 nonce[FSCRYPT_FILE_NONCE_SIZE];
     };
diff --git a/Documentation/filesystems/fuse-io.rst b/Documentation/filesystems/fuse-io.rst
index 255a368fe534..6464de4266ad 100644
--- a/Documentation/filesystems/fuse-io.rst
+++ b/Documentation/filesystems/fuse-io.rst
@@ -15,7 +15,8 @@ The direct-io mode can be selected with the FOPEN_DIRECT_IO flag in the
 FUSE_OPEN reply.
 
 In direct-io mode the page cache is completely bypassed for reads and writes.
-No read-ahead takes place. Shared mmap is disabled.
+No read-ahead takes place. Shared mmap is disabled by default. To allow shared
+mmap, the FUSE_DIRECT_IO_ALLOW_MMAP flag may be enabled in the FUSE_INIT reply.
 
 In cached mode reads may be satisfied from the page cache, and data may be
 read-ahead by the kernel to fill the cache.  The cache is always kept consistent
diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst
index 09cade7eaefc..e18bc5ae3b35 100644
--- a/Documentation/filesystems/index.rst
+++ b/Documentation/filesystems/index.rst
@@ -121,8 +121,5 @@ Documentation for filesystem implementations.
    udf
    virtiofs
    vfat
-   xfs-delayed-logging-design
-   xfs-maintainer-entry-profile
-   xfs-self-describing-metadata
-   xfs-online-fsck-design
+   xfs/index
    zonefs
diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index 7be2900806c8..421daf837940 100644
--- a/Documentation/filesystems/locking.rst
+++ b/Documentation/filesystems/locking.rst
@@ -261,7 +261,7 @@ prototypes::
 			struct folio *src, enum migrate_mode);
 	int (*launder_folio)(struct folio *);
 	bool (*is_partially_uptodate)(struct folio *, size_t from, size_t count);
-	int (*error_remove_page)(struct address_space *, struct page *);
+	int (*error_remove_folio)(struct address_space *, struct folio *);
 	int (*swap_activate)(struct swap_info_struct *sis, struct file *f, sector_t *span)
 	int (*swap_deactivate)(struct file *);
 	int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter);
@@ -287,7 +287,7 @@ direct_IO:
 migrate_folio:		yes (both)
 launder_folio:		yes
 is_partially_uptodate:	yes
-error_remove_page:	yes
+error_remove_folio:	yes
 swap_activate:		no
 swap_deactivate:	no
 swap_rw:		yes, unlocks
diff --git a/Documentation/filesystems/overlayfs.rst b/Documentation/filesystems/overlayfs.rst
index 0407f361f32a..1c244866041a 100644
--- a/Documentation/filesystems/overlayfs.rst
+++ b/Documentation/filesystems/overlayfs.rst
@@ -39,7 +39,7 @@ objects in the original filesystem.
 On 64bit systems, even if all overlay layers are not on the same
 underlying filesystem, the same compliant behavior could be achieved
 with the "xino" feature.  The "xino" feature composes a unique object
-identifier from the real object st_ino and an underlying fsid index.
+identifier from the real object st_ino and an underlying fsid number.
 The "xino" feature uses the high inode number bits for fsid, because the
 underlying filesystems rarely use the high inode number bits.  In case
 the underlying inode number does overflow into the high xino bits, overlay
@@ -118,7 +118,7 @@ Where both upper and lower objects are directories, a merged directory
 is formed.
 
 At mount time, the two directories given as mount options "lowerdir" and
-"upperdir" are combined into a merged directory:
+"upperdir" are combined into a merged directory::
 
   mount -t overlay overlay -olowerdir=/lower,upperdir=/upper,\
   workdir=/work /merged
@@ -172,12 +172,12 @@ directory is being read.  This is unlikely to be noticed by many
 programs.
 
 seek offsets are assigned sequentially when the directories are read.
-Thus if
+Thus if:
 
-  - read part of a directory
-  - remember an offset, and close the directory
-  - re-open the directory some time later
-  - seek to the remembered offset
+ - read part of a directory
+ - remember an offset, and close the directory
+ - re-open the directory some time later
+ - seek to the remembered offset
 
 there may be little correlation between the old and new locations in
 the list of filenames, particularly if anything has changed in the
@@ -290,9 +290,9 @@ Permission checking in the overlay filesystem follows these principles:
  2) task creating the overlay mount MUST NOT gain additional privileges
 
  3) non-mounting task MAY gain additional privileges through the overlay,
- compared to direct access on underlying lower or upper filesystems
+    compared to direct access on underlying lower or upper filesystems
 
-This is achieved by performing two permission checks on each access
+This is achieved by performing two permission checks on each access:
 
  a) check if current task is allowed access based on local DAC (owner,
     group, mode and posix acl), as well as MAC checks
@@ -311,11 +311,11 @@ to create setups where the consistency rule (1) does not hold; normally,
 however, the mounting task will have sufficient privileges to perform all
 operations.
 
-Another way to demonstrate this model is drawing parallels between
+Another way to demonstrate this model is drawing parallels between::
 
   mount -t overlay overlay -olowerdir=/lower,upperdir=/upper,... /merged
 
-and
+and::
 
   cp -a /lower /upper
   mount --bind /upper /merged
@@ -328,7 +328,7 @@ Multiple lower layers
 ---------------------
 
 Multiple lower layers can now be given using the colon (":") as a
-separator character between the directory names.  For example:
+separator character between the directory names.  For example::
 
   mount -t overlay overlay -olowerdir=/lower1:/lower2:/lower3 /merged
 
@@ -340,13 +340,13 @@ rightmost one and going left.  In the above example lower1 will be the
 top, lower2 the middle and lower3 the bottom layer.
 
 Note: directory names containing colons can be provided as lower layer by
-escaping the colons with a single backslash.  For example:
+escaping the colons with a single backslash.  For example::
 
   mount -t overlay overlay -olowerdir=/a\:lower\:\:dir /merged
 
 Since kernel version v6.8, directory names containing colons can also
 be configured as lower layer using the "lowerdir+" mount options and the
-fsconfig syscall from new mount api.  For example:
+fsconfig syscall from new mount api.  For example::
 
   fsconfig(fs_fd, FSCONFIG_SET_STRING, "lowerdir+", "/a:lower::dir", 0);
 
@@ -356,7 +356,7 @@ as an octal characters (\072) when displayed in /proc/self/mountinfo.
 Metadata only copy up
 ---------------------
 
-When metadata only copy up feature is enabled, overlayfs will only copy
+When the "metacopy" feature is enabled, overlayfs will only copy
 up metadata (as opposed to whole file), when a metadata specific operation
 like chown/chmod is performed. Full file will be copied up later when
 file is opened for WRITE operation.
@@ -405,7 +405,7 @@ A normal lower layer is not allowed to be below a data-only layer, so single
 colon separators are not allowed to the right of double colon ("::") separators.
 
 
-For example:
+For example::
 
   mount -t overlay overlay -olowerdir=/l1:/l2:/l3::/do1::/do2 /merged
 
@@ -419,7 +419,7 @@ to the absolute path of the "lower data" file in the "data-only" lower layer.
 
 Since kernel version v6.8, "data-only" lower layers can also be added using
 the "datadir+" mount options and the fsconfig syscall from new mount api.
-For example:
+For example::
 
   fsconfig(fs_fd, FSCONFIG_SET_STRING, "lowerdir+", "/l1", 0);
   fsconfig(fs_fd, FSCONFIG_SET_STRING, "lowerdir+", "/l2", 0);
@@ -429,7 +429,7 @@ For example:
 
 
 fs-verity support
-----------------------
+-----------------
 
 During metadata copy up of a lower file, if the source file has
 fs-verity enabled and overlay verity support is enabled, then the
@@ -492,27 +492,27 @@ though it will not result in a crash or deadlock.
 
 Mounting an overlay using an upper layer path, where the upper layer path
 was previously used by another mounted overlay in combination with a
-different lower layer path, is allowed, unless the "inodes index" feature
-or "metadata only copy up" feature is enabled.
+different lower layer path, is allowed, unless the "index" or "metacopy"
+features are enabled.
 
-With the "inodes index" feature, on the first time mount, an NFS file
+With the "index" feature, on the first time mount, an NFS file
 handle of the lower layer root directory, along with the UUID of the lower
 filesystem, are encoded and stored in the "trusted.overlay.origin" extended
 attribute on the upper layer root directory.  On subsequent mount attempts,
 the lower root directory file handle and lower filesystem UUID are compared
 to the stored origin in upper root directory.  On failure to verify the
 lower root origin, mount will fail with ESTALE.  An overlayfs mount with
-"inodes index" enabled will fail with EOPNOTSUPP if the lower filesystem
+"index" enabled will fail with EOPNOTSUPP if the lower filesystem
 does not support NFS export, lower filesystem does not have a valid UUID or
 if the upper filesystem does not support extended attributes.
 
-For "metadata only copy up" feature there is no verification mechanism at
+For the "metacopy" feature, there is no verification mechanism at
 mount time. So if same upper is mounted with different set of lower, mount
 probably will succeed but expect the unexpected later on. So don't do it.
 
 It is quite a common practice to copy overlay layers to a different
 directory tree on the same or different underlying filesystem, and even
-to a different machine.  With the "inodes index" feature, trying to mount
+to a different machine.  With the "index" feature, trying to mount
 the copied layers will fail the verification of the lower root file handle.
 
 Nesting overlayfs mounts
@@ -547,20 +547,21 @@ filesystem.
 
 This is the list of cases that overlayfs doesn't currently handle:
 
-a) POSIX mandates updating st_atime for reads.  This is currently not
-done in the case when the file resides on a lower layer.
+ a) POSIX mandates updating st_atime for reads.  This is currently not
+    done in the case when the file resides on a lower layer.
 
-b) If a file residing on a lower layer is opened for read-only and then
-memory mapped with MAP_SHARED, then subsequent changes to the file are not
-reflected in the memory mapping.
+ b) If a file residing on a lower layer is opened for read-only and then
+    memory mapped with MAP_SHARED, then subsequent changes to the file are not
+    reflected in the memory mapping.
 
-c) If a file residing on a lower layer is being executed, then opening that
-file for write or truncating the file will not be denied with ETXTBSY.
+ c) If a file residing on a lower layer is being executed, then opening that
+    file for write or truncating the file will not be denied with ETXTBSY.
 
 The following options allow overlayfs to act more like a standards
 compliant filesystem:
 
-1) "redirect_dir"
+redirect_dir
+````````````
 
 Enabled with the mount option or module option: "redirect_dir=on" or with
 the kernel config option CONFIG_OVERLAY_FS_REDIRECT_DIR=y.
@@ -568,7 +569,8 @@ the kernel config option CONFIG_OVERLAY_FS_REDIRECT_DIR=y.
 If this feature is disabled, then rename(2) on a lower or merged directory
 will fail with EXDEV ("Invalid cross-device link").
 
-2) "inode index"
+index
+`````
 
 Enabled with the mount option or module option "index=on" or with the
 kernel config option CONFIG_OVERLAY_FS_INDEX=y.
@@ -577,7 +579,8 @@ If this feature is disabled and a file with multiple hard links is copied
 up, then this will "break" the link.  Changes will not be propagated to
 other names referring to the same inode.
 
-3) "xino"
+xino
+````
 
 Enabled with the mount option "xino=auto" or "xino=on", with the module
 option "xino_auto=on" or with the kernel config option
@@ -604,7 +607,7 @@ a crash or deadlock.
 
 Offline changes, when the overlay is not mounted, are allowed to the
 upper tree.  Offline changes to the lower tree are only allowed if the
-"metadata only copy up", "inode index", "xino" and "redirect_dir" features
+"metacopy", "index", "xino" and "redirect_dir" features
 have not been used.  If the lower tree is modified and any of these
 features has been used, the behavior of the overlay is undefined,
 though it will not result in a crash or deadlock.
@@ -644,12 +647,13 @@ directory inode.
 When encoding a file handle from an overlay filesystem object, the
 following rules apply:
 
-1. For a non-upper object, encode a lower file handle from lower inode
-2. For an indexed object, encode a lower file handle from copy_up origin
-3. For a pure-upper object and for an existing non-indexed upper object,
-   encode an upper file handle from upper inode
+ 1. For a non-upper object, encode a lower file handle from lower inode
+ 2. For an indexed object, encode a lower file handle from copy_up origin
+ 3. For a pure-upper object and for an existing non-indexed upper object,
+    encode an upper file handle from upper inode
 
 The encoded overlay file handle includes:
+
  - Header including path type information (e.g. lower/upper)
  - UUID of the underlying filesystem
  - Underlying filesystem encoding of underlying inode
@@ -659,15 +663,15 @@ are stored in extended attribute "trusted.overlay.origin".
 
 When decoding an overlay file handle, the following steps are followed:
 
-1. Find underlying layer by UUID and path type information.
-2. Decode the underlying filesystem file handle to underlying dentry.
-3. For a lower file handle, lookup the handle in index directory by name.
-4. If a whiteout is found in index, return ESTALE. This represents an
-   overlay object that was deleted after its file handle was encoded.
-5. For a non-directory, instantiate a disconnected overlay dentry from the
-   decoded underlying dentry, the path type and index inode, if found.
-6. For a directory, use the connected underlying decoded dentry, path type
-   and index, to lookup a connected overlay dentry.
+ 1. Find underlying layer by UUID and path type information.
+ 2. Decode the underlying filesystem file handle to underlying dentry.
+ 3. For a lower file handle, lookup the handle in index directory by name.
+ 4. If a whiteout is found in index, return ESTALE. This represents an
+    overlay object that was deleted after its file handle was encoded.
+ 5. For a non-directory, instantiate a disconnected overlay dentry from the
+    decoded underlying dentry, the path type and index inode, if found.
+ 6. For a directory, use the connected underlying decoded dentry, path type
+    and index, to lookup a connected overlay dentry.
 
 Decoding a non-directory file handle may return a disconnected dentry.
 copy_up of that disconnected dentry will create an upper index entry with
@@ -770,9 +774,9 @@ Testsuite
 There's a testsuite originally developed by David Howells and currently
 maintained by Amir Goldstein at:
 
-  https://github.com/amir73il/unionmount-testsuite.git
+https://github.com/amir73il/unionmount-testsuite.git
 
-Run as root:
+Run as root::
 
   # cd unionmount-testsuite
   # ./run --ov --verify
diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst
index 878e72b2f8b7..ced3a6761329 100644
--- a/Documentation/filesystems/porting.rst
+++ b/Documentation/filesystems/porting.rst
@@ -1061,3 +1061,15 @@ export_operations ->encode_fh() no longer has a default implementation to
 encode FILEID_INO32_GEN* file handles.
 Filesystems that used the default implementation may use the generic helper
 generic_encode_ino32_fh() explicitly.
+
+---
+
+**recommended**
+
+Block device freezing and thawing have been moved to holder operations.
+
+Before this change, get_active_super() would only be able to find the
+superblock of the main block device, i.e., the one stored in sb->s_bdev. Block
+device freezing now works for any block device owned by a given superblock, not
+just the main block device. The get_active_super() helper and bd_fsfreeze_sb
+pointer are gone.
diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
index 49ef12df631b..104c6d047d9b 100644
--- a/Documentation/filesystems/proc.rst
+++ b/Documentation/filesystems/proc.rst
@@ -528,9 +528,9 @@ replaced by copy-on-write) part of the underlying shmem object out on swap.
 does not take into account swapped out page of underlying shmem objects.
 "Locked" indicates whether the mapping is locked in memory or not.
 
-"THPeligible" indicates whether the mapping is eligible for allocating THP
-pages as well as the THP is PMD mappable or not - 1 if true, 0 otherwise.
-It just shows the current status.
+"THPeligible" indicates whether the mapping is eligible for allocating
+naturally aligned THP pages of any currently enabled size. 1 if true, 0
+otherwise.
 
 "VmFlags" field deserves a separate description. This member represents the
 kernel flags associated with the particular virtual memory area in two letter
diff --git a/Documentation/filesystems/squashfs.rst b/Documentation/filesystems/squashfs.rst
index df42106bae71..4af8d6207509 100644
--- a/Documentation/filesystems/squashfs.rst
+++ b/Documentation/filesystems/squashfs.rst
@@ -64,6 +64,66 @@ obtained from this site also.
 The squashfs-tools development tree is now located on kernel.org
 	git://git.kernel.org/pub/scm/fs/squashfs/squashfs-tools.git
 
+2.1 Mount options
+-----------------
+===================    =========================================================
+errors=%s              Specify whether squashfs errors trigger a kernel panic
+                       or not
+
+		       ==========  =============================================
+                         continue  errors don't trigger a panic (default)
+                            panic  trigger a panic when errors are encountered,
+                                   similar to several other filesystems (e.g.
+                                   btrfs, ext4, f2fs, GFS2, jfs, ntfs, ubifs)
+
+                                   This allows a kernel dump to be saved,
+                                   useful for analyzing and debugging the
+                                   corruption.
+                       ==========  =============================================
+threads=%s             Select the decompression mode or the number of threads
+
+                       If SQUASHFS_CHOICE_DECOMP_BY_MOUNT is set:
+
+		       ==========  =============================================
+                           single  use single-threaded decompression (default)
+
+                                   Only one block (data or metadata) can be
+                                   decompressed at any one time. This limits
+                                   CPU and memory usage to a minimum, but it
+                                   also gives poor performance on parallel I/O
+                                   workloads when using multiple CPU machines
+                                   due to waiting on decompressor availability.
+                            multi  use up to two parallel decompressors per core
+
+                                   If you have a parallel I/O workload and your
+                                   system has enough memory, using this option
+                                   may improve overall I/O performance. It
+                                   dynamically allocates decompressors on a
+                                   demand basis.
+                           percpu  use a maximum of one decompressor per core
+
+                                   It uses percpu variables to ensure
+                                   decompression is load-balanced across the
+                                   cores.
+                        1|2|3|...  configure the number of threads used for
+                                   decompression
+
+                                   The upper limit is num_online_cpus() * 2.
+                       ==========  =============================================
+
+                       If SQUASHFS_CHOICE_DECOMP_BY_MOUNT is **not** set and
+                       SQUASHFS_DECOMP_MULTI, SQUASHFS_MOUNT_DECOMP_THREADS are
+                       both set:
+
+		       ==========  =============================================
+                          2|3|...  configure the number of threads used for
+                                   decompression
+
+                                   The upper limit is num_online_cpus() * 2.
+                       ==========  =============================================
+
+===================    =========================================================
+
 3. Squashfs Filesystem Design
 -----------------------------
 
diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
index 276a219ff8d9..eebcc0f9e2bc 100644
--- a/Documentation/filesystems/vfs.rst
+++ b/Documentation/filesystems/vfs.rst
@@ -823,7 +823,7 @@ cache in your filesystem.  The following members are defined:
 		bool (*is_partially_uptodate) (struct folio *, size_t from,
 					       size_t count);
 		void (*is_dirty_writeback)(struct folio *, bool *, bool *);
-		int (*error_remove_page) (struct mapping *mapping, struct page *page);
+		int (*error_remove_folio)(struct mapping *mapping, struct folio *);
 		int (*swap_activate)(struct swap_info_struct *sis, struct file *f, sector_t *span)
 		int (*swap_deactivate)(struct file *);
 		int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter);
@@ -1034,8 +1034,8 @@ cache in your filesystem.  The following members are defined:
 	VM if a folio should be treated as dirty or writeback for the
 	purposes of stalling.
 
-``error_remove_page``
-	normally set to generic_error_remove_page if truncation is ok
+``error_remove_folio``
+	normally set to generic_error_remove_folio if truncation is ok
 	for this address space.  Used for memory failure handling.
 	Setting this implies you deal with pages going away under you,
 	unless you have them locked or reference counts increased.
diff --git a/Documentation/filesystems/xfs/index.rst b/Documentation/filesystems/xfs/index.rst
new file mode 100644
index 000000000000..ab66c57a5d18
--- /dev/null
+++ b/Documentation/filesystems/xfs/index.rst
@@ -0,0 +1,14 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+============================
+XFS Filesystem Documentation
+============================
+
+.. toctree::
+   :maxdepth: 2
+   :numbered:
+
+   xfs-delayed-logging-design
+   xfs-maintainer-entry-profile
+   xfs-self-describing-metadata
+   xfs-online-fsck-design
diff --git a/Documentation/filesystems/xfs-delayed-logging-design.rst b/Documentation/filesystems/xfs/xfs-delayed-logging-design.rst
index 6402ab8e370c..6402ab8e370c 100644
--- a/Documentation/filesystems/xfs-delayed-logging-design.rst
+++ b/Documentation/filesystems/xfs/xfs-delayed-logging-design.rst
diff --git a/Documentation/filesystems/xfs-maintainer-entry-profile.rst b/Documentation/filesystems/xfs/xfs-maintainer-entry-profile.rst
index 32b6ac4ca9d6..32b6ac4ca9d6 100644
--- a/Documentation/filesystems/xfs-maintainer-entry-profile.rst
+++ b/Documentation/filesystems/xfs/xfs-maintainer-entry-profile.rst
diff --git a/Documentation/filesystems/xfs-online-fsck-design.rst b/Documentation/filesystems/xfs/xfs-online-fsck-design.rst
index a0678101a7d0..352516feef6f 100644
--- a/Documentation/filesystems/xfs-online-fsck-design.rst
+++ b/Documentation/filesystems/xfs/xfs-online-fsck-design.rst
@@ -962,7 +962,7 @@ disk, but these buffer verifiers cannot provide any consistency checking
 between metadata structures.
 
 For more information, please see the documentation for
-Documentation/filesystems/xfs-self-describing-metadata.rst
+Documentation/filesystems/xfs/xfs-self-describing-metadata.rst
 
 Reverse Mapping
 ---------------
diff --git a/Documentation/filesystems/xfs-self-describing-metadata.rst b/Documentation/filesystems/xfs/xfs-self-describing-metadata.rst
index a10c4ae6955e..a10c4ae6955e 100644
--- a/Documentation/filesystems/xfs-self-describing-metadata.rst
+++ b/Documentation/filesystems/xfs/xfs-self-describing-metadata.rst
diff --git a/Documentation/i2c/i2c-address-translators.rst b/Documentation/i2c/i2c-address-translators.rst
index b22ce9f41ecf..6845c114e472 100644
--- a/Documentation/i2c/i2c-address-translators.rst
+++ b/Documentation/i2c/i2c-address-translators.rst
@@ -71,7 +71,7 @@ Transaction:
  - Physical I2C transaction on bus A, slave address 0x20
  - ATR chip detects transaction on address 0x20, finds it in table,
    propagates transaction on bus B with address translated to 0x10,
-   keeps clock streched on bus A waiting for reply
+   keeps clock stretched on bus A waiting for reply
  - Slave X chip (on bus B) detects transaction at its own physical
    address 0x10 and replies normally
  - ATR chip stops clock stretching and forwards reply on bus A,
diff --git a/Documentation/index.rst b/Documentation/index.rst
index 9dfdc826618c..36e61783437c 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -113,6 +113,7 @@ to ReStructured Text format, or are simply too old.
    :maxdepth: 1
 
    staging/index
+   RAS/ras
 
 
 Translations
diff --git a/Documentation/locking/mutex-design.rst b/Documentation/locking/mutex-design.rst
index 78540cd7f54b..7c30b4aa5e28 100644
--- a/Documentation/locking/mutex-design.rst
+++ b/Documentation/locking/mutex-design.rst
@@ -101,6 +101,24 @@ features that make lock debugging easier and faster:
     - Detects multi-task circular deadlocks and prints out all affected
       locks and tasks (and only those tasks).
 
+Mutexes - and most other sleeping locks like rwsems - do not provide an
+implicit reference for the memory they occupy, which reference is released
+with mutex_unlock().
+
+[ This is in contrast with spin_unlock() [or completion_done()], which
+  APIs can be used to guarantee that the memory is not touched by the
+  lock implementation after spin_unlock()/completion_done() releases
+  the lock. ]
+
+mutex_unlock() may access the mutex structure even after it has internally
+released the lock already - so it's not safe for another context to
+acquire the mutex and assume that the mutex_unlock() context is not using
+the structure anymore.
+
+The mutex user must ensure that the mutex is not destroyed while a
+release operation is still in progress - in other words, callers of
+mutex_unlock() must ensure that the mutex stays alive until mutex_unlock()
+has returned.
 
 Interfaces
 ----------
diff --git a/Documentation/maintainer/maintainer-entry-profile.rst b/Documentation/maintainer/maintainer-entry-profile.rst
index 7ad4bfc2cc03..18cee1edaecb 100644
--- a/Documentation/maintainer/maintainer-entry-profile.rst
+++ b/Documentation/maintainer/maintainer-entry-profile.rst
@@ -105,4 +105,4 @@ to do something different in the near future.
    ../driver-api/media/maintainer-entry-profile
    ../driver-api/vfio-pci-device-specific-driver-acceptance
    ../nvme/feature-and-quirk-policy
-   ../filesystems/xfs-maintainer-entry-profile
+   ../filesystems/xfs/xfs-maintainer-entry-profile
diff --git a/Documentation/mm/arch_pgtable_helpers.rst b/Documentation/mm/arch_pgtable_helpers.rst
index c82e3ee20e51..2466d3363af7 100644
--- a/Documentation/mm/arch_pgtable_helpers.rst
+++ b/Documentation/mm/arch_pgtable_helpers.rst
@@ -18,8 +18,6 @@ PTE Page Table Helpers
 +---------------------------+--------------------------------------------------+
 | pte_same                  | Tests whether both PTE entries are the same      |
 +---------------------------+--------------------------------------------------+
-| pte_bad                   | Tests a non-table mapped PTE                     |
-+---------------------------+--------------------------------------------------+
 | pte_present               | Tests a valid mapped PTE                         |
 +---------------------------+--------------------------------------------------+
 | pte_young                 | Tests a young PTE                                |
diff --git a/Documentation/mm/damon/design.rst b/Documentation/mm/damon/design.rst
index 1f7e0586b5fa..1bb69524a62e 100644
--- a/Documentation/mm/damon/design.rst
+++ b/Documentation/mm/damon/design.rst
@@ -5,6 +5,18 @@ Design
 ======
 
 
+.. _damon_design_execution_model_and_data_structures:
+
+Execution Model and Data Structures
+===================================
+
+The monitoring-related information including the monitoring request
+specification and DAMON-based operation schemes are stored in a data structure
+called DAMON ``context``.  DAMON executes each context with a kernel thread
+called ``kdamond``.  Multiple kdamonds could run in parallel, for different
+types of monitoring.
+
+
 Overall Architecture
 ====================
 
@@ -346,6 +358,19 @@ the weight will be respected are up to the underlying prioritization mechanism
 implementation.
 
 
+.. _damon_design_damos_quotas_auto_tuning:
+
+Aim-oriented Feedback-driven Auto-tuning
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Automatic feedback-driven quota tuning.  Instead of setting the absolute quota
+value, users can repeatedly provide numbers representing how much of their goal
+for the scheme is achieved as feedback.  DAMOS then automatically tunes the
+aggressiveness (the quota) of the corresponding scheme.  For example, if DAMOS
+is under achieving the goal, DAMOS automatically increases the quota.  If DAMOS
+is over achieving the goal, it decreases the quota.
+
+
 .. _damon_design_damos_watermarks:
 
 Watermarks
@@ -477,15 +502,3 @@ modules for proactive reclamation and LRU lists manipulation are provided.  For
 more detail, please read the usage documents for those
 (:doc:`/admin-guide/mm/damon/reclaim` and
 :doc:`/admin-guide/mm/damon/lru_sort`).
-
-
-.. _damon_design_execution_model_and_data_structures:
-
-Execution Model and Data Structures
-===================================
-
-The monitoring-related information including the monitoring request
-specification and DAMON-based operation schemes are stored in a data structure
-called DAMON ``context``.  DAMON executes each context with a kernel thread
-called ``kdamond``.  Multiple kdamonds could run in parallel, for different
-types of monitoring.
diff --git a/Documentation/mm/transhuge.rst b/Documentation/mm/transhuge.rst
index 9a607059ea11..93c9239b9ebe 100644
--- a/Documentation/mm/transhuge.rst
+++ b/Documentation/mm/transhuge.rst
@@ -117,7 +117,7 @@ pages:
 
   - map/unmap of a PMD entry for the whole THP increment/decrement
     folio->_entire_mapcount and also increment/decrement
-    folio->_nr_pages_mapped by COMPOUND_MAPPED when _entire_mapcount
+    folio->_nr_pages_mapped by ENTIRELY_MAPPED when _entire_mapcount
     goes from -1 to 0 or 0 to -1.
 
   - map/unmap of individual pages with PTE entry increment/decrement
@@ -156,7 +156,7 @@ Partial unmap and deferred_split_folio()
 
 Unmapping part of THP (with munmap() or other way) is not going to free
 memory immediately. Instead, we detect that a subpage of THP is not in use
-in page_remove_rmap() and queue the THP for splitting if memory pressure
+in folio_remove_rmap_*() and queue the THP for splitting if memory pressure
 comes. Splitting will free up unused subpages.
 
 Splitting the page right away is not an option due to locking context in
diff --git a/Documentation/mm/unevictable-lru.rst b/Documentation/mm/unevictable-lru.rst
index 67f1338440a5..b6a07a26b10d 100644
--- a/Documentation/mm/unevictable-lru.rst
+++ b/Documentation/mm/unevictable-lru.rst
@@ -486,7 +486,7 @@ munlock the pages if we're removing the last VM_LOCKED VMA that maps the pages.
 Before the unevictable/mlock changes, mlocking did not mark the pages in any
 way, so unmapping them required no processing.
 
-For each PTE (or PMD) being unmapped from a VMA, page_remove_rmap() calls
+For each PTE (or PMD) being unmapped from a VMA, folio_remove_rmap_*() calls
 munlock_vma_folio(), which calls munlock_folio() when the VMA is VM_LOCKED
 (unless it was a PTE mapping of a part of a transparent huge page).
 
@@ -511,7 +511,7 @@ userspace; truncation even unmaps and deletes any private anonymous pages
 which had been Copied-On-Write from the file pages now being truncated.
 
 Mlocked pages can be munlocked and deleted in this way: like with munmap(),
-for each PTE (or PMD) being unmapped from a VMA, page_remove_rmap() calls
+for each PTE (or PMD) being unmapped from a VMA, folio_remove_rmap_*() calls
 munlock_vma_folio(), which calls munlock_folio() when the VMA is VM_LOCKED
 (unless it was a PTE mapping of a part of a transparent huge page).
 
diff --git a/Documentation/netlink/netlink-raw.yaml b/Documentation/netlink/netlink-raw.yaml
index 775cce8c548a..04b92f1a5cd6 100644
--- a/Documentation/netlink/netlink-raw.yaml
+++ b/Documentation/netlink/netlink-raw.yaml
@@ -126,8 +126,10 @@ properties:
               name:
                 type: string
               type:
-                description: The netlink attribute type
-                enum: [ u8, u16, u32, u64, s8, s16, s32, s64, string, binary ]
+                description: |
+                  The netlink attribute type. Members of type 'binary' or 'pad'
+                  must also have the 'len' property set.
+                enum: [ u8, u16, u32, u64, s8, s16, s32, s64, string, binary, pad ]
               len:
                 $ref: '#/$defs/len-or-define'
               byte-order:
@@ -150,6 +152,14 @@ properties:
                   the right formatting mechanism when displaying values of this
                   type.
                 enum: [ hex, mac, fddi, ipv4, ipv6, uuid ]
+            if:
+              properties:
+                type:
+                  oneOf:
+                    - const: binary
+                    - const: pad
+            then:
+              required: [ len ]
         # End genetlink-legacy
 
   attribute-sets:
@@ -200,8 +210,10 @@ properties:
                 type: string
               type: &attr-type
                 description: The netlink attribute type
-                enum: [ unused, pad, flag, binary, u8, u16, u32, u64, s32, s64,
-                        string, nest, array-nest, nest-type-value ]
+                enum: [ unused, pad, flag, binary, bitfield32,
+                        u8, u16, u32, u64, s8, s16, s32, s64,
+                        string, nest, array-nest, nest-type-value,
+                        sub-message ]
               doc:
                 description: Documentation of the attribute.
                 type: string
@@ -260,6 +272,17 @@ properties:
                 description: Name of the struct type used for the attribute.
                 type: string
               # End genetlink-legacy
+              # Start netlink-raw
+              sub-message:
+                description: |
+                  Name of the sub-message definition to use for the attribute.
+                type: string
+              selector:
+                description: |
+                  Name of the attribute to use for dynamic selection of sub-message
+                  format specifier.
+                type: string
+              # End netlink-raw
 
       # Make sure name-prefix does not appear in subsets (subsets inherit naming)
       dependencies:
@@ -282,6 +305,43 @@ properties:
             items:
               required: [ type ]
 
+  # Start netlink-raw
+  sub-messages:
+    description: Definition of sub message attributes
+    type: array
+    items:
+      type: object
+      additionalProperties: False
+      required: [ name, formats ]
+      properties:
+        name:
+          description: Name of the sub-message definition
+          type: string
+        formats:
+          description: Dynamically selected format specifiers
+          type: array
+          items:
+            type: object
+            additionalProperties: False
+            required: [ value ]
+            properties:
+              value:
+                description: |
+                  Value to match for dynamic selection of sub-message format
+                  specifier.
+                type: string
+              fixed-header:
+                description: |
+                  Name of the struct definition to use as the fixed header
+                  for the sub message.
+                type: string
+              attribute-set:
+                description: |
+                  Name of the attribute space from which to resolve attributes
+                  in the sub message.
+                type: string
+  # End netlink-raw
+
   operations:
     description: Operations supported by the protocol.
     type: object
diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml
index 572d83a414d0..cf6eaa0da821 100644
--- a/Documentation/netlink/specs/devlink.yaml
+++ b/Documentation/netlink/specs/devlink.yaml
@@ -77,6 +77,14 @@ definitions:
         name: ipsec-packet-bit
   -
     type: enum
+    name: rate-type
+    entries:
+      -
+        name: leaf
+      -
+        name: node
+  -
+    type: enum
     name: sb-threshold-type
     entries:
       -
@@ -113,6 +121,16 @@ definitions:
         name: basic
   -
     type: enum
+    name: dpipe-header-id
+    entries:
+      -
+        name: ethernet
+      -
+        name: ipv4
+      -
+        name: ipv6
+  -
+    type: enum
     name: dpipe-match-type
     entries:
       -
@@ -174,6 +192,16 @@ definitions:
         name: trap
       -
         name: mirror
+  -
+    type: enum
+    name: trap-type
+    entries:
+      -
+        name: drop
+      -
+        name: exception
+      -
+        name: control
 
 attribute-sets:
   -
@@ -194,27 +222,45 @@ attribute-sets:
         name: port-type
         type: u16
         enum: port-type
-
-      # TODO: fill in the attributes in between
-
+      -
+        name: port-desired-type
+        type: u16
+      -
+        name: port-netdev-ifindex
+        type: u32
+      -
+        name: port-netdev-name
+        type: string
+      -
+        name: port-ibdev-name
+        type: string
       -
         name: port-split-count
         type: u32
-        value: 9
-
-      # TODO: fill in the attributes in between
-
+      -
+        name: port-split-group
+        type: u32
       -
         name: sb-index
         type: u32
-        value: 11
-
-      # TODO: fill in the attributes in between
-
+      -
+        name: sb-size
+        type: u32
+      -
+        name: sb-ingress-pool-count
+        type: u16
+      -
+        name: sb-egress-pool-count
+        type: u16
+      -
+        name: sb-ingress-tc-count
+        type: u16
+      -
+        name: sb-egress-tc-count
+        type: u16
       -
         name: sb-pool-index
         type: u16
-        value: 17
       -
         name: sb-pool-type
         type: u8
@@ -232,16 +278,16 @@ attribute-sets:
       -
         name: sb-tc-index
         type: u16
-        value: 22
-
-      # TODO: fill in the attributes in between
-
+      -
+        name: sb-occ-cur
+        type: u32
+      -
+        name: sb-occ-max
+        type: u32
       -
         name: eswitch-mode
         type: u16
-        value: 25
         enum: eswitch-mode
-
       -
         name: eswitch-inline-mode
         type: u16
@@ -347,6 +393,7 @@ attribute-sets:
       -
         name: dpipe-header-id
         type: u32
+        enum: dpipe-header-id
       -
         name: dpipe-header-fields
         type: nest
@@ -381,7 +428,6 @@ attribute-sets:
       -
         name: eswitch-encap-mode
         type: u8
-        value: 62
         enum: eswitch-encap-mode
       -
         name: resource-list
@@ -433,20 +479,25 @@ attribute-sets:
         name: port-flavour
         type: u16
         enum: port-flavour
-
-      # TODO: fill in the attributes in between
-
+      -
+        name: port-number
+        type: u32
+      -
+        name: port-split-subport-number
+        type: u32
+      -
+        name: param
+        type: nest
+        nested-attributes: dl-param
       -
         name: param-name
         type: string
-        value: 81
-
-      # TODO: fill in the attributes in between
-
+      -
+        name: param-generic
+        type: flag
       -
         name: param-type
         type: u8
-        value: 83
 
       # TODO: fill in the attributes in between
 
@@ -458,20 +509,34 @@ attribute-sets:
       -
         name: region-name
         type: string
-
-      # TODO: fill in the attributes in between
-
+      -
+        name: region-size
+        type: u64
+      -
+        name: region-snapshots
+        type: nest
+        nested-attributes: dl-region-snapshots
+      -
+        name: region-snapshot
+        type: nest
+        nested-attributes: dl-region-snapshot
       -
         name: region-snapshot-id
         type: u32
-        value: 92
-
-      # TODO: fill in the attributes in between
-
+      -
+        name: region-chunks
+        type: nest
+        nested-attributes: dl-region-chunks
+      -
+        name: region-chunk
+        type: nest
+        nested-attributes: dl-region-chunk
+      -
+        name: region-chunk-data
+        type: binary
       -
         name: region-chunk-addr
         type: u64
-        value: 96
       -
         name: region-chunk-len
         type: u64
@@ -502,14 +567,13 @@ attribute-sets:
       -
         name: info-version-value
         type: string
-
-      # TODO: fill in the attributes in between
-
+      -
+        name: sb-pool-cell-size
+        type: u32
       -
         name: fmsg
         type: nest
         nested-attributes: dl-fmsg
-        value: 106
       -
         name: fmsg-obj-nest-start
         type: flag
@@ -525,20 +589,35 @@ attribute-sets:
       -
         name: fmsg-obj-name
         type: string
+      -
+        name: fmsg-obj-value-type
+        type: u8
 
       # TODO: fill in the attributes in between
 
       -
+        name: health-reporter
+        type: nest
+        value: 114
+        nested-attributes: dl-health-reporter
+      -
         name: health-reporter-name
         type: string
-        value: 115
-
-      # TODO: fill in the attributes in between
-
+      -
+        name: health-reporter-state
+        type: u8
+      -
+        name: health-reporter-err-count
+        type: u64
+      -
+        name: health-reporter-recover-count
+        type: u64
+      -
+        name: health-reporter-dump-ts
+        type: u64
       -
         name: health-reporter-graceful-period
         type: u64
-        value: 120
       -
         name: health-reporter-auto-recover
         type: u8
@@ -548,55 +627,64 @@ attribute-sets:
       -
         name: flash-update-component
         type: string
-
-      # TODO: fill in the attributes in between
-
+      -
+        name: flash-update-status-msg
+        type: string
+      -
+        name: flash-update-status-done
+        type: u64
+      -
+        name: flash-update-status-total
+        type: u64
       -
         name: port-pci-pf-number
         type: u16
-        value: 127
-
-      # TODO: fill in the attributes in between
-
+      -
+        name: port-pci-vf-number
+        type: u16
+      -
+        name: stats
+        type: nest
+        nested-attributes: dl-attr-stats
       -
         name: trap-name
         type: string
-        value: 130
       -
         name: trap-action
         type: u8
         enum: trap-action
-
-      # TODO: fill in the attributes in between
-
+      -
+        name: trap-type
+        type: u8
+        enum: trap-type
+      -
+        name: trap-generic
+        type: flag
+      -
+        name: trap-metadata
+        type: nest
+        nested-attributes: dl-trap-metadata
       -
         name: trap-group-name
         type: string
-        value: 135
-
       -
         name: reload-failed
         type: u8
-
-      # TODO: fill in the attributes in between
-
+      -
+        name: health-reporter-dump-ts-ns
+        type: u64
       -
         name: netns-fd
         type: u32
-        value: 138
       -
         name: netns-pid
         type: u32
       -
         name: netns-id
         type: u32
-
-      # TODO: fill in the attributes in between
-
       -
         name: health-reporter-auto-dump
         type: u8
-        value: 141
       -
         name: trap-policer-id
         type: u32
@@ -610,22 +698,29 @@ attribute-sets:
         name: port-function
         type: nest
         nested-attributes: dl-port-function
-
-      # TODO: fill in the attributes in between
-
+      -
+        name: info-board-serial-number
+        type: string
+      -
+        name: port-lanes
+        type: u32
+      -
+        name: port-splittable
+        type: u8
+      -
+        name: port-external
+        type: u8
       -
         name: port-controller-number
         type: u32
-        value: 150
-
-      # TODO: fill in the attributes in between
-
+      -
+        name: flash-update-status-timeout
+        type: u64
       -
         name: flash-update-overwrite-mask
         type: bitfield32
         enum: flash-overwrite
         enum-as-flags: True
-        value: 152
       -
         name: reload-action
         type: u8
@@ -673,20 +768,16 @@ attribute-sets:
         type: nest
         multi-attr: true
         nested-attributes: dl-reload-act-stats
-
-      # TODO: fill in the attributes in between
-
       -
         name: port-pci-sf-number
         type: u32
-        value: 164
-
-      # TODO: fill in the attributes in between
-
+      -
+        name: rate-type
+        type: u16
+        enum: rate-type
       -
         name: rate-tx-share
         type: u64
-        value: 166
       -
         name: rate-tx-max
         type: u64
@@ -696,20 +787,22 @@ attribute-sets:
       -
         name: rate-parent-node-name
         type: string
-
-      # TODO: fill in the attributes in between
-
+      -
+         name: region-max-snapshots
+         type: u32
       -
         name: linecard-index
         type: u32
-        value: 171
-
-      # TODO: fill in the attributes in between
-
+      -
+         name: linecard-state
+         type: u8
       -
         name: linecard-type
         type: string
-        value: 173
+      -
+        name: linecard-supported-types
+        type: nest
+        nested-attributes: dl-linecard-supported-types
 
       # TODO: fill in the attributes in between
 
@@ -736,12 +829,14 @@ attribute-sets:
         name: reload-stats
       -
         name: remote-reload-stats
+
   -
     name: dl-reload-stats
     subset-of: devlink
     attributes:
       -
         name: reload-action-info
+
   -
     name: dl-reload-act-info
     subset-of: devlink
@@ -750,12 +845,14 @@ attribute-sets:
         name: reload-action
       -
         name: reload-action-stats
+
   -
     name: dl-reload-act-stats
     subset-of: devlink
     attributes:
       -
         name: reload-stats-entry
+
   -
     name: dl-reload-stats-entry
     subset-of: devlink
@@ -764,6 +861,7 @@ attribute-sets:
         name: reload-stats-limit
       -
         name: reload-stats-value
+
   -
     name: dl-info-version
     subset-of: devlink
@@ -772,6 +870,7 @@ attribute-sets:
         name: info-version-name
       -
         name: info-version-value
+
   -
     name: dl-port-function
     name-prefix: devlink-port-fn-attr-
@@ -1006,6 +1105,49 @@ attribute-sets:
         name: resource
 
   -
+    name: dl-param
+    subset-of: devlink
+    attributes:
+      -
+        name: param-name
+      -
+        name: param-generic
+      -
+        name: param-type
+
+      # TODO: fill in the attribute param-value-list
+
+  -
+    name: dl-region-snapshots
+    subset-of: devlink
+    attributes:
+      -
+        name: region-snapshot
+
+  -
+    name: dl-region-snapshot
+    subset-of: devlink
+    attributes:
+      -
+        name: region-snapshot-id
+
+  -
+    name: dl-region-chunks
+    subset-of: devlink
+    attributes:
+      -
+        name: region-chunk
+
+  -
+    name: dl-region-chunk
+    subset-of: devlink
+    attributes:
+      -
+        name: region-chunk-data
+      -
+        name: region-chunk-addr
+
+  -
     name: dl-fmsg
     subset-of: devlink
     attributes:
@@ -1021,6 +1163,62 @@ attribute-sets:
         name: fmsg-obj-name
 
   -
+    name: dl-health-reporter
+    subset-of: devlink
+    attributes:
+      -
+        name: health-reporter-name
+      -
+        name: health-reporter-state
+      -
+        name: health-reporter-err-count
+      -
+        name: health-reporter-recover-count
+      -
+        name: health-reporter-graceful-period
+      -
+        name: health-reporter-auto-recover
+      -
+        name: health-reporter-dump-ts
+      -
+        name: health-reporter-dump-ts-ns
+      -
+        name: health-reporter-auto-dump
+
+  -
+    name: dl-attr-stats
+    name-prefix: devlink-attr-
+    attributes:
+      - name: stats-rx-packets
+        type: u64
+        value: 0
+      -
+        name: stats-rx-bytes
+        type: u64
+      -
+        name: stats-rx-dropped
+        type: u64
+
+  -
+    name: dl-trap-metadata
+    name-prefix: devlink-attr-
+    attributes:
+      -
+        name: trap-metadata-type-in-port
+        type: flag
+        value: 0
+      -
+        name: trap-metadata-type-fa-cookie
+        type: flag
+
+  -
+    name: dl-linecard-supported-types
+    subset-of: devlink
+    attributes:
+      -
+        name: linecard-type
+
+  -
     name: dl-selftest-id
     name-prefix: devlink-attr-selftest-id-
     attributes:
@@ -1077,6 +1275,7 @@ operations:
         reply:
           value: 3  # due to a bug, port dump returns DEVLINK_CMD_NEW
           attributes: *port-id-attrs
+
     -
       name: port-set
       doc: Set devlink port instances.
@@ -1484,8 +1683,8 @@ operations:
       dont-validate: [ strict ]
       flags: [ admin-perm ]
       do:
-        pre: devlink-nl-pre-doit
-        post: devlink-nl-post-doit
+        pre: devlink-nl-pre-doit-dev-lock
+        post: devlink-nl-post-doit-dev-lock
         request:
           attributes:
             - bus-name
@@ -2055,3 +2254,14 @@ operations:
             - bus-name
             - dev-name
             - selftests
+
+    -
+      name: notify-filter-set
+      doc: Set notification messages socket filter.
+      attribute-set: devlink
+      do:
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - port-index
diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml
index cf8abe1c0550..b14aed18065f 100644
--- a/Documentation/netlink/specs/dpll.yaml
+++ b/Documentation/netlink/specs/dpll.yaml
@@ -296,6 +296,16 @@ attribute-sets:
       -
         name: phase-offset
         type: s64
+      -
+        name: fractional-frequency-offset
+        type: sint
+        doc: |
+          The FFO (Fractional Frequency Offset) between the RX and TX
+          symbol rate on the media associated with the pin:
+          (rx_frequency-tx_frequency)/rx_frequency
+          Value is in PPM (parts per million).
+          This may be implemented for example for pin of type
+          PIN_TYPE_SYNCE_ETH_PORT.
   -
     name: pin-parent-device
     subset-of: pin
@@ -460,6 +470,7 @@ operations:
             - phase-adjust-min
             - phase-adjust-max
             - phase-adjust
+            - fractional-frequency-offset
 
       dump:
         pre: dpll-lock-dumpit
diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 5c7a65b009b4..197208f419dc 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -908,6 +908,9 @@ attribute-sets:
       -
         name: hkey
         type: binary
+      -
+        name: input_xfrm
+        type: u32
   -
     name: plca
     attributes:
@@ -1598,6 +1601,7 @@ operations:
             - hfunc
             - indir
             - hkey
+            - input_xfrm
       dump: *rss-get-op
     -
       name: plca-get-cfg
diff --git a/Documentation/netlink/specs/mptcp.yaml b/Documentation/netlink/specs/mptcp_pm.yaml
index 49f90cfb4698..49f90cfb4698 100644
--- a/Documentation/netlink/specs/mptcp.yaml
+++ b/Documentation/netlink/specs/mptcp_pm.yaml
diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 14511b13f305..3addac970680 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -45,7 +45,6 @@ definitions:
   -
     type: flags
     name: xdp-rx-metadata
-    render-max: true
     entries:
       -
         name: timestamp
@@ -55,6 +54,26 @@ definitions:
         name: hash
         doc:
           Device is capable of exposing receive packet hash via bpf_xdp_metadata_rx_hash().
+      -
+        name: vlan-tag
+        doc:
+          Device is capable of exposing receive packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag().
+  -
+    type: flags
+    name: xsk-flags
+    entries:
+      -
+        name: tx-timestamp
+        doc:
+          HW timestamping egress packets is supported by the driver.
+      -
+        name: tx-checksum
+        doc:
+          L3 checksum HW offload is supported by the driver.
+  -
+    name: queue-type
+    type: enum
+    entries: [ rx, tx ]
 
 attribute-sets:
   -
@@ -86,6 +105,165 @@ attribute-sets:
              See Documentation/networking/xdp-rx-metadata.rst for more details.
         type: u64
         enum: xdp-rx-metadata
+      -
+        name: xsk-features
+        doc: Bitmask of enabled AF_XDP features.
+        type: u64
+        enum: xsk-flags
+  -
+    name: page-pool
+    attributes:
+      -
+        name: id
+        doc: Unique ID of a Page Pool instance.
+        type: uint
+        checks:
+          min: 1
+          max: u32-max
+      -
+        name: ifindex
+        doc: |
+          ifindex of the netdev to which the pool belongs.
+          May be reported as 0 if the page pool was allocated for a netdev
+          which got destroyed already (page pools may outlast their netdevs
+          because they wait for all memory to be returned).
+        type: u32
+        checks:
+          min: 1
+          max: s32-max
+      -
+        name: napi-id
+        doc: Id of NAPI using this Page Pool instance.
+        type: uint
+        checks:
+          min: 1
+          max: u32-max
+      -
+        name: inflight
+        type: uint
+        doc: |
+          Number of outstanding references to this page pool (allocated
+          but yet to be freed pages). Allocated pages may be held in
+          socket receive queues, driver receive ring, page pool recycling
+          ring, the page pool cache, etc.
+      -
+        name: inflight-mem
+        type: uint
+        doc: |
+          Amount of memory held by inflight pages.
+      -
+        name: detach-time
+        type: uint
+        doc: |
+          Seconds in CLOCK_BOOTTIME of when Page Pool was detached by
+          the driver. Once detached Page Pool can no longer be used to
+          allocate memory.
+          Page Pools wait for all the memory allocated from them to be freed
+          before truly disappearing. "Detached" Page Pools cannot be
+          "re-attached", they are just waiting to disappear.
+          Attribute is absent if Page Pool has not been detached, and
+          can still be used to allocate new memory.
+  -
+    name: page-pool-info
+    subset-of: page-pool
+    attributes:
+      -
+        name: id
+      -
+        name: ifindex
+  -
+    name: page-pool-stats
+    doc: |
+      Page pool statistics, see docs for struct page_pool_stats
+      for information about individual statistics.
+    attributes:
+      -
+        name: info
+        doc: Page pool identifying information.
+        type: nest
+        nested-attributes: page-pool-info
+      -
+        name: alloc-fast
+        type: uint
+        value: 8 # reserve some attr ids in case we need more metadata later
+      -
+        name: alloc-slow
+        type: uint
+      -
+        name: alloc-slow-high-order
+        type: uint
+      -
+        name: alloc-empty
+        type: uint
+      -
+        name: alloc-refill
+        type: uint
+      -
+        name: alloc-waive
+        type: uint
+      -
+        name: recycle-cached
+        type: uint
+      -
+        name: recycle-cache-full
+        type: uint
+      -
+        name: recycle-ring
+        type: uint
+      -
+        name: recycle-ring-full
+        type: uint
+      -
+        name: recycle-released-refcnt
+        type: uint
+
+  -
+    name: napi
+    attributes:
+      -
+        name: ifindex
+        doc: ifindex of the netdevice to which NAPI instance belongs.
+        type: u32
+        checks:
+          min: 1
+      -
+        name: id
+        doc: ID of the NAPI instance.
+        type: u32
+      -
+        name: irq
+        doc: The associated interrupt vector number for the napi
+        type: u32
+      -
+        name: pid
+        doc: PID of the napi thread, if NAPI is configured to operate in
+             threaded mode. If NAPI is not in threaded mode (i.e. uses normal
+             softirq context), the attribute will be absent.
+        type: u32
+  -
+    name: queue
+    attributes:
+      -
+        name: id
+        doc: Queue index; most queue types are indexed like a C array, with
+             indexes starting at 0 and ending at queue count - 1. Queue indexes
+             are scoped to an interface and queue type.
+        type: u32
+      -
+        name: ifindex
+        doc: ifindex of the netdevice to which the queue belongs.
+        type: u32
+        checks:
+          min: 1
+      -
+        name: type
+        doc: Queue type as rx, tx. Each queue type defines a separate ID space.
+        type: u32
+        enum: queue-type
+      -
+        name: napi-id
+        doc: ID of the NAPI instance which services this queue.
+        type: u32
 
 operations:
   list:
@@ -103,6 +281,7 @@ operations:
             - xdp-features
             - xdp-zc-max-segs
             - xdp-rx-metadata-features
+            - xsk-features
       dump:
         reply: *dev-all
     -
@@ -120,8 +299,116 @@ operations:
       doc: Notification about device configuration being changed.
       notify: dev-get
       mcgrp: mgmt
+    -
+      name: page-pool-get
+      doc: |
+        Get / dump information about Page Pools.
+        (Only Page Pools associated with a net_device can be listed.)
+      attribute-set: page-pool
+      do:
+        request:
+          attributes:
+            - id
+        reply: &pp-reply
+          attributes:
+            - id
+            - ifindex
+            - napi-id
+            - inflight
+            - inflight-mem
+            - detach-time
+      dump:
+        reply: *pp-reply
+      config-cond: page-pool
+    -
+      name: page-pool-add-ntf
+      doc: Notification about page pool appearing.
+      notify: page-pool-get
+      mcgrp: page-pool
+      config-cond: page-pool
+    -
+      name: page-pool-del-ntf
+      doc: Notification about page pool disappearing.
+      notify: page-pool-get
+      mcgrp: page-pool
+      config-cond: page-pool
+    -
+      name: page-pool-change-ntf
+      doc: Notification about page pool configuration being changed.
+      notify: page-pool-get
+      mcgrp: page-pool
+      config-cond: page-pool
+    -
+      name: page-pool-stats-get
+      doc: Get page pool statistics.
+      attribute-set: page-pool-stats
+      do:
+        request:
+          attributes:
+            - info
+        reply: &pp-stats-reply
+          attributes:
+            - info
+            - alloc-fast
+            - alloc-slow
+            - alloc-slow-high-order
+            - alloc-empty
+            - alloc-refill
+            - alloc-waive
+            - recycle-cached
+            - recycle-cache-full
+            - recycle-ring
+            - recycle-ring-full
+            - recycle-released-refcnt
+      dump:
+        reply: *pp-stats-reply
+      config-cond: page-pool-stats
+    -
+      name: queue-get
+      doc: Get queue information from the kernel.
+           Only configured queues will be reported (as opposed to all available
+           hardware queues).
+      attribute-set: queue
+      do:
+        request:
+          attributes:
+            - ifindex
+            - type
+            - id
+        reply: &queue-get-op
+          attributes:
+            - id
+            - type
+            - napi-id
+            - ifindex
+      dump:
+        request:
+          attributes:
+            - ifindex
+        reply: *queue-get-op
+    -
+      name: napi-get
+      doc: Get information about NAPI instances configured on the system.
+      attribute-set: napi
+      do:
+        request:
+          attributes:
+            - id
+        reply: &napi-get-op
+          attributes:
+            - id
+            - ifindex
+            - irq
+            - pid
+      dump:
+        request:
+          attributes:
+            - ifindex
+        reply: *napi-get-op
 
 mcast-groups:
   list:
     -
       name: mgmt
+    -
+      name: page-pool
diff --git a/Documentation/netlink/specs/ovs_datapath.yaml b/Documentation/netlink/specs/ovs_datapath.yaml
index f709c26c3e92..edc8c95ca6f5 100644
--- a/Documentation/netlink/specs/ovs_datapath.yaml
+++ b/Documentation/netlink/specs/ovs_datapath.yaml
@@ -20,6 +20,7 @@ definitions:
     name: user-features
     type: flags
     name-prefix: ovs-dp-f-
+    enum-name:
     entries:
       -
         name: unaligned
@@ -142,7 +143,6 @@ operations:
       do:
         request:
           attributes:
-            - dp-ifindex
             - name
             - upcall-pid
             - user-features
@@ -154,7 +154,6 @@ operations:
       do:
         request:
           attributes:
-            - dp-ifindex
             - name
 
 mcast-groups:
diff --git a/Documentation/netlink/specs/ovs_flow.yaml b/Documentation/netlink/specs/ovs_flow.yaml
index 109ca1f57b6c..4fdfc6b5cae9 100644
--- a/Documentation/netlink/specs/ovs_flow.yaml
+++ b/Documentation/netlink/specs/ovs_flow.yaml
@@ -124,6 +124,7 @@ definitions:
   -
     name: ovs-frag-type
     name-prefix: ovs-frag-type-
+    enum-name: ovs-frag-type
     type: enum
     entries:
       -
@@ -269,6 +270,7 @@ definitions:
   -
     name: ovs-ufid-flags
     name-prefix: ovs-ufid-f-
+    enum-name:
     type: flags
     entries:
       - omit-key
@@ -288,6 +290,7 @@ definitions:
         doc: Basis used for computing hash.
   -
     name: ovs-hash-alg
+    enum-name: ovs-hash-alg
     type: enum
     doc: |
       Data path hash algorithm for computing Datapath hash. The algorithm type only specifies
@@ -339,6 +342,7 @@ definitions:
           MPLS tunnel attributes.
   -
     name: ct-state-flags
+    enum-name:
     type: flags
     name-prefix: ovs-cs-f-
     entries:
@@ -947,13 +951,11 @@ operations:
       do: &flow-get-op
         request:
           attributes:
-            - dp-ifindex
             - key
             - ufid
             - ufid-flags
         reply:
           attributes:
-            - dp-ifindex
             - key
             - ufid
             - mask
@@ -968,7 +970,6 @@ operations:
       do:
         request:
           attributes:
-            - dp-ifindex
             - key
             - ufid
             - mask
diff --git a/Documentation/netlink/specs/ovs_vport.yaml b/Documentation/netlink/specs/ovs_vport.yaml
index f65ce62cd60d..86ba9ac2a521 100644
--- a/Documentation/netlink/specs/ovs_vport.yaml
+++ b/Documentation/netlink/specs/ovs_vport.yaml
@@ -135,7 +135,6 @@ operations:
             - name
             - type
             - upcall-pid
-            - dp-ifindex
             - ifindex
             - options
     -
@@ -146,7 +145,6 @@ operations:
       do:
         request:
           attributes:
-            - dp-ifindex
             - port-no
             - type
             - name
@@ -158,11 +156,9 @@ operations:
       do: &vport-get-op
         request:
           attributes:
-            - dp-ifindex
             - name
         reply: &dev-all
           attributes:
-            - dp-ifindex
             - port-no
             - type
             - name
diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml
index d86a68f8475c..1ad01d52a863 100644
--- a/Documentation/netlink/specs/rt_link.yaml
+++ b/Documentation/netlink/specs/rt_link.yaml
@@ -66,8 +66,9 @@ definitions:
         name: ifi-family
         type: u8
       -
-        name: padding
-        type: u8
+        name: pad
+        type: pad
+        len: 1
       -
         name: ifi-type
         type: u16
@@ -83,6 +84,18 @@ definitions:
         name: ifi-change
         type: u32
   -
+    name: ifla-bridge-id
+    type: struct
+    members:
+      -
+        name: prio
+        type: u16
+      -
+        name: addr
+        type: binary
+        len: 6
+        display-hint: mac
+  -
     name: ifla-cacheinfo
     type: struct
     members:
@@ -707,11 +720,9 @@ definitions:
         name: family
         type: u8
       -
-        name: pad1
-        type: u8
-      -
-        name: pad2
-        type: u16
+        name: pad
+        type: pad
+        len: 3
       -
         name: ifindex
         type: u32
@@ -966,8 +977,9 @@ attribute-sets:
         type: string
       -
         name: data
-        type: binary
-        # kind specific nest, e.g. linkinfo-bridge-attrs
+        type: sub-message
+        sub-message: linkinfo-data-msg
+        selector: kind
       -
         name: xstats
         type: binary
@@ -976,10 +988,12 @@ attribute-sets:
         type: string
       -
         name: slave-data
-        type: binary
-        # kind specific nest
+        type: sub-message
+        sub-message: linkinfo-member-data-msg
+        selector: slave-kind
   -
     name: linkinfo-bridge-attrs
+    name-prefix: ifla-br-
     attributes:
       -
         name: forward-delay
@@ -1011,9 +1025,11 @@ attribute-sets:
       -
         name: root-id
         type: binary
+        struct: ifla-bridge-id
       -
         name: bridge-id
         type: binary
+        struct: ifla-bridge-id
       -
         name: root-port
         type: u16
@@ -1041,6 +1057,7 @@ attribute-sets:
       -
         name: group-addr
         type: binary
+        display-hint: mac
       -
         name: fdb-flush
         type: binary
@@ -1124,6 +1141,376 @@ attribute-sets:
         name: mcast-querier-state
         type: binary
   -
+    name: linkinfo-brport-attrs
+    name-prefix: ifla-brport-
+    attributes:
+      -
+        name: state
+        type: u8
+      -
+        name: priority
+        type: u16
+      -
+        name: cost
+        type: u32
+      -
+        name: mode
+        type: flag
+      -
+        name: guard
+        type: flag
+      -
+        name: protect
+        type: flag
+      -
+        name: fast-leave
+        type: flag
+      -
+        name: learning
+        type: flag
+      -
+        name: unicast-flood
+        type: flag
+      -
+        name: proxyarp
+        type: flag
+      -
+        name: learning-sync
+        type: flag
+      -
+        name: proxyarp-wifi
+        type: flag
+      -
+        name: root-id
+        type: binary
+        struct: ifla-bridge-id
+      -
+        name: bridge-id
+        type: binary
+        struct: ifla-bridge-id
+      -
+        name: designated-port
+        type: u16
+      -
+        name: designated-cost
+        type: u16
+      -
+        name: id
+        type: u16
+      -
+        name: "no"
+        type: u16
+      -
+        name: topology-change-ack
+        type: u8
+      -
+        name: config-pending
+        type: u8
+      -
+        name: message-age-timer
+        type: u64
+      -
+        name: forward-delay-timer
+        type: u64
+      -
+        name: hold-timer
+        type: u64
+      -
+        name: flush
+        type: flag
+      -
+        name: multicast-router
+        type: u8
+      -
+        name: pad
+        type: pad
+      -
+        name: mcast-flood
+        type: flag
+      -
+        name: mcast-to-ucast
+        type: flag
+      -
+        name: vlan-tunnel
+        type: flag
+      -
+        name: bcast-flood
+        type: flag
+      -
+        name: group-fwd-mask
+        type: u16
+      -
+        name: neigh-suppress
+        type: flag
+      -
+        name: isolated
+        type: flag
+      -
+        name: backup-port
+        type: u32
+      -
+        name: mrp-ring-open
+        type: flag
+      -
+        name: mrp-in-open
+        type: flag
+      -
+        name: mcast-eht-hosts-limit
+        type: u32
+      -
+        name: mcast-eht-hosts-cnt
+        type: u32
+      -
+        name: locked
+        type: flag
+      -
+        name: mab
+        type: flag
+      -
+        name: mcast-n-groups
+        type: u32
+      -
+        name: mcast-max-groups
+        type: u32
+      -
+        name: neigh-vlan-suppress
+        type: flag
+      -
+        name: backup-nhid
+        type: u32
+  -
+    name: linkinfo-gre-attrs
+    name-prefix: ifla-gre-
+    attributes:
+      -
+        name: link
+        type: u32
+      -
+        name: iflags
+        type: u16
+      -
+        name: oflags
+        type: u16
+      -
+        name: ikey
+        type: u32
+      -
+        name: okey
+        type: u32
+      -
+        name: local
+        type: binary
+        display-hint: ipv4
+      -
+        name: remote
+        type: binary
+        display-hint: ipv4
+      -
+        name: ttl
+        type: u8
+      -
+        name: tos
+        type: u8
+      -
+        name: pmtudisc
+        type: u8
+      -
+        name: encap-limit
+        type: u32
+      -
+        name: flowinfo
+        type: u32
+      -
+        name: flags
+        type: u32
+      -
+        name: encap-type
+        type: u16
+      -
+        name: encap-flags
+        type: u16
+      -
+        name: encap-sport
+        type: u16
+      -
+        name: encap-dport
+        type: u16
+      -
+        name: collect-metadata
+        type: flag
+      -
+        name: ignore-df
+        type: u8
+      -
+        name: fwmark
+        type: u32
+      -
+        name: erspan-index
+        type: u32
+      -
+        name: erspan-ver
+        type: u8
+      -
+        name: erspan-dir
+        type: u8
+      -
+        name: erspan-hwid
+        type: u16
+  -
+    name: linkinfo-geneve-attrs
+    name-prefix: ifla-geneve-
+    attributes:
+      -
+        name: id
+        type: u32
+      -
+        name: remote
+        type: binary
+        display-hint: ipv4
+      -
+        name: ttl
+        type: u8
+      -
+        name: tos
+        type: u8
+      -
+        name: port
+        type: u16
+      -
+        name: collect-metadata
+        type: flag
+      -
+        name: remote6
+        type: binary
+        display-hint: ipv6
+      -
+        name: udp-csum
+        type: u8
+      -
+        name: udp-zero-csum6-tx
+        type: u8
+      -
+        name: udp-zero-csum6-rx
+        type: u8
+      -
+        name: label
+        type: u32
+      -
+        name: ttl-inherit
+        type: u8
+      -
+        name: df
+        type: u8
+      -
+        name: inner-proto-inherit
+        type: flag
+  -
+    name: linkinfo-iptun-attrs
+    name-prefix: ifla-iptun-
+    attributes:
+      -
+        name: link
+        type: u32
+      -
+        name: local
+        type: binary
+        display-hint: ipv4
+      -
+        name: remote
+        type: binary
+        display-hint: ipv4
+      -
+        name: ttl
+        type: u8
+      -
+        name: tos
+        type: u8
+      -
+        name: encap-limit
+        type: u8
+      -
+        name: flowinfo
+        type: u32
+      -
+        name: flags
+        type: u16
+      -
+        name: proto
+        type: u8
+      -
+        name: pmtudisc
+        type: u8
+      -
+        name: 6rd-prefix
+        type: binary
+        display-hint: ipv6
+      -
+        name: 6rd-relay-prefix
+        type: binary
+        display-hint: ipv4
+      -
+        name: 6rd-prefixlen
+        type: u16
+      -
+        name: 6rd-relay-prefixlen
+        type: u16
+      -
+        name: encap-type
+        type: u16
+      -
+        name: encap-flags
+        type: u16
+      -
+        name: encap-sport
+        type: u16
+      -
+        name: encap-dport
+        type: u16
+      -
+        name: collect-metadata
+        type: flag
+      -
+        name: fwmark
+        type: u32
+  -
+    name: linkinfo-tun-attrs
+    name-prefix: ifla-tun-
+    attributes:
+      -
+        name: owner
+        type: u32
+      -
+        name: group
+        type: u32
+      -
+        name: type
+        type: u8
+      -
+        name: pi
+        type: u8
+      -
+        name: vnet-hdr
+        type: u8
+      -
+        name: persist
+        type: u8
+      -
+        name: multi-queue
+        type: u8
+      -
+        name: num-queues
+        type: u32
+      -
+        name: num-disabled-queues
+        type: u32
+  -
+    name: linkinfo-vrf-attrs
+    name-prefix: ifla-vrf-
+    attributes:
+      -
+        name: table
+        type: u32
+  -
     name: xdp-attrs
     attributes:
       -
@@ -1241,6 +1628,46 @@ attribute-sets:
         name: used
         type: u8
 
+sub-messages:
+  -
+    name: linkinfo-data-msg
+    formats:
+      -
+        value: bridge
+        attribute-set: linkinfo-bridge-attrs
+      -
+        value: erspan
+        attribute-set: linkinfo-gre-attrs
+      -
+        value: gre
+        attribute-set: linkinfo-gre-attrs
+      -
+        value: gretap
+        attribute-set: linkinfo-gre-attrs
+      -
+        value: geneve
+        attribute-set: linkinfo-geneve-attrs
+      -
+        value: ipip
+        attribute-set: linkinfo-iptun-attrs
+      -
+        value: sit
+        attribute-set: linkinfo-iptun-attrs
+      -
+        value: tun
+        attribute-set: linkinfo-tun-attrs
+      -
+        value: vrf
+        attribute-set: linkinfo-vrf-attrs
+  -
+    name: linkinfo-member-data-msg
+    formats:
+      -
+        value: bridge
+        attribute-set: linkinfo-brport-attrs
+      -
+        value: bond
+
 operations:
   enum-model: directional
   list:
diff --git a/Documentation/netlink/specs/tc.yaml b/Documentation/netlink/specs/tc.yaml
new file mode 100644
index 000000000000..4346fa402fc9
--- /dev/null
+++ b/Documentation/netlink/specs/tc.yaml
@@ -0,0 +1,2031 @@
+# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+
+name: tc
+protocol: netlink-raw
+protonum: 0
+
+doc:
+  Netlink raw family for tc qdisc, chain, class and filter configuration
+  over rtnetlink.
+
+definitions:
+  -
+    name: tcmsg
+    type: struct
+    members:
+      -
+        name: family
+        type: u8
+      -
+        name: pad
+        type: pad
+        len: 3
+      -
+        name: ifindex
+        type: s32
+      -
+        name: handle
+        type: u32
+      -
+        name: parent
+        type: u32
+      -
+        name: info
+        type: u32
+  -
+    name: tc-cls-flags
+    type: flags
+    entries:
+      - skip-hw
+      - skip-sw
+      - in-hw
+      - not-in-nw
+      - verbose
+  -
+    name: tc-stats
+    type: struct
+    members:
+      -
+        name: bytes
+        type: u64
+      -
+        name: packets
+        type: u32
+      -
+        name: drops
+        type: u32
+      -
+        name: overlimits
+        type: u32
+      -
+        name: bps
+        type: u32
+      -
+        name: pps
+        type: u32
+      -
+        name: qlen
+        type: u32
+      -
+        name: backlog
+        type: u32
+  -
+    name: tc-cbs-qopt
+    type: struct
+    members:
+      -
+        name: offload
+        type: u8
+      -
+        name: pad
+        type: pad
+        len: 3
+      -
+        name: hicredit
+        type: s32
+      -
+        name: locredit
+        type: s32
+      -
+        name: idleslope
+        type: s32
+      -
+        name: sendslope
+        type: s32
+  -
+    name: tc-etf-qopt
+    type: struct
+    members:
+      -
+        name: delta
+        type: s32
+      -
+        name: clockid
+        type: s32
+      -
+        name: flags
+        type: s32
+  -
+    name: tc-fifo-qopt
+    type: struct
+    members:
+      -
+        name: limit
+        type: u32
+  -
+    name: tc-htb-opt
+    type: struct
+    members:
+      -
+        name: rate
+        type: binary
+        len: 12
+      -
+        name: ceil
+        type: binary
+        len: 12
+      -
+        name: buffer
+        type: u32
+      -
+        name: cbuffer
+        type: u32
+      -
+        name: quantum
+        type: u32
+      -
+        name: level
+        type: u32
+      -
+        name: prio
+        type: u32
+  -
+    name: tc-htb-glob
+    type: struct
+    members:
+      -
+        name: version
+        type: u32
+      -
+        name: rate2quantum
+        type: u32
+      -
+        name: defcls
+        type: u32
+      -
+        name: debug
+        type: u32
+      -
+        name: direct-pkts
+        type: u32
+  -
+    name: tc-gred-qopt
+    type: struct
+    members:
+      -
+        name: limit
+        type: u32
+      -
+        name: qth-min
+        type: u32
+      -
+        name: qth-max
+        type: u32
+      -
+        name: DP
+        type: u32
+      -
+        name: backlog
+        type: u32
+      -
+        name: qave
+        type: u32
+      -
+        name: forced
+        type: u32
+      -
+        name: early
+        type: u32
+      -
+        name: other
+        type: u32
+      -
+        name: pdrop
+        type: u32
+      -
+        name: Wlog
+        type: u8
+      -
+        name: Plog
+        type: u8
+      -
+        name: Scell_log
+        type: u8
+      -
+        name: prio
+        type: u8
+      -
+        name: packets
+        type: u32
+      -
+        name: bytesin
+        type: u32
+  -
+    name: tc-gred-sopt
+    type: struct
+    members:
+      -
+        name: DPs
+        type: u32
+      -
+        name: def_DP
+        type: u32
+      -
+        name: grio
+        type: u8
+      -
+        name: flags
+        type: u8
+      -
+        name: pad
+        type: pad
+        len: 2
+  -
+    name: tc-hfsc-qopt
+    type: struct
+    members:
+      -
+        name: defcls
+        type: u16
+  -
+    name: tc-mqprio-qopt
+    type: struct
+    members:
+      -
+        name: num-tc
+        type: u8
+      -
+        name: prio-tc-map
+        type: binary
+        len: 16
+      -
+        name: hw
+        type: u8
+      -
+        name: count
+        type: binary
+        len: 32
+      -
+        name: offset
+        type: binary
+        len: 32
+  -
+    name: tc-multiq-qopt
+    type: struct
+    members:
+      -
+        name: bands
+        type: u16
+      -
+        name: max-bands
+        type: u16
+  -
+    name: tc-netem-qopt
+    type: struct
+    members:
+      -
+        name: latency
+        type: u32
+      -
+        name: limit
+        type: u32
+      -
+        name: loss
+        type: u32
+      -
+        name: gap
+        type: u32
+      -
+        name: duplicate
+        type: u32
+      -
+        name: jitter
+        type: u32
+  -
+    name: tc-plug-qopt
+    type: struct
+    members:
+      -
+        name: action
+        type: s32
+      -
+        name: limit
+        type: u32
+  -
+    name: tc-prio-qopt
+    type: struct
+    members:
+      -
+        name: bands
+        type: u16
+      -
+        name: priomap
+        type: binary
+        len: 16
+  -
+    name: tc-red-qopt
+    type: struct
+    members:
+      -
+        name: limit
+        type: u32
+      -
+        name: qth-min
+        type: u32
+      -
+        name: qth-max
+        type: u32
+      -
+        name: Wlog
+        type: u8
+      -
+        name: Plog
+        type: u8
+      -
+        name: Scell-log
+        type: u8
+      -
+        name: flags
+        type: u8
+  -
+    name: tc-sfb-qopt
+    type: struct
+    members:
+      -
+        name: rehash-interval
+        type: u32
+      -
+        name: warmup-time
+        type: u32
+      -
+        name: max
+        type: u32
+      -
+        name: bin-size
+        type: u32
+      -
+        name: increment
+        type: u32
+      -
+        name: decrement
+        type: u32
+      -
+        name: limit
+        type: u32
+      -
+        name: penalty-rate
+        type: u32
+      -
+        name: penalty-burst
+        type: u32
+  -
+    name: tc-sfq-qopt-v1 # TODO nested structs
+    type: struct
+    members:
+      -
+        name: quantum
+        type: u32
+      -
+        name: perturb-period
+        type: s32
+      -
+        name: limit
+        type: u32
+      -
+        name: divisor
+        type: u32
+      -
+        name: flows
+        type: u32
+      -
+        name: depth
+        type: u32
+      -
+        name: headdrop
+        type: u32
+      -
+        name: limit
+        type: u32
+      -
+        name: qth-min
+        type: u32
+      -
+        name: qth-mac
+        type: u32
+      -
+        name: Wlog
+        type: u8
+      -
+        name: Plog
+        type: u8
+      -
+        name: Scell-log
+        type: u8
+      -
+        name: flags
+        type: u8
+      -
+        name: max-P
+        type: u32
+      -
+        name: prob-drop
+        type: u32
+      -
+        name: forced-drop
+        type: u32
+      -
+        name: prob-mark
+        type: u32
+      -
+        name: forced-mark
+        type: u32
+      -
+        name: prob-mark-head
+        type: u32
+      -
+        name: forced-mark-head
+        type: u32
+  -
+    name: tc-tbf-qopt
+    type: struct
+    members:
+      -
+        name: rate
+        type: binary # TODO nested struct tc_ratespec
+        len: 12
+      -
+        name: peakrate
+        type: binary # TODO nested struct tc_ratespec
+        len: 12
+      -
+        name: limit
+        type: u32
+      -
+        name: buffer
+        type: u32
+      -
+        name: mtu
+        type: u32
+  -
+    name: tc-sizespec
+    type: struct
+    members:
+      -
+        name: cell-log
+        type: u8
+      -
+        name: size-log
+        type: u8
+      -
+        name: cell-align
+        type: s16
+      -
+        name: overhead
+        type: s32
+      -
+        name: linklayer
+        type: u32
+      -
+        name: mpu
+        type: u32
+      -
+        name: mtu
+        type: u32
+      -
+        name: tsize
+        type: u32
+  -
+    name: gnet-estimator
+    type: struct
+    members:
+      -
+        name: interval
+        type: s8
+      -
+        name: ewma-log
+        type: u8
+attribute-sets:
+  -
+    name: tc-attrs
+    attributes:
+      -
+        name: kind
+        type: string
+      -
+        name: options
+        type: sub-message
+        sub-message: tc-options-msg
+        selector: kind
+      -
+        name: stats
+        type: binary
+        struct: tc-stats
+      -
+        name: xstats
+        type: binary
+      -
+        name: rate
+        type: binary
+        struct: gnet-estimator
+      -
+        name: fcnt
+        type: u32
+      -
+        name: stats2
+        type: nest
+        nested-attributes: tca-stats-attrs
+      -
+        name: stab
+        type: nest
+        nested-attributes: tca-stab-attrs
+      -
+        name: pad
+        type: pad
+      -
+        name: dump-invisible
+        type: flag
+      -
+        name: chain
+        type: u32
+      -
+        name: hw-offload
+        type: u8
+      -
+        name: ingress-block
+        type: u32
+      -
+        name: egress-block
+        type: u32
+      -
+        name: dump-flags
+        type: bitfield32
+      -
+        name: ext-warn-msg
+        type: string
+  -
+    name: tc-cake-attrs
+    attributes:
+      -
+        name: pad
+        type: pad
+      -
+        name: base-rate64
+        type: u64
+      -
+        name: diffserv-mode
+        type: u32
+      -
+        name: atm
+        type: u32
+      -
+        name: flow-mode
+        type: u32
+      -
+        name: overhead
+        type: u32
+      -
+        name: rtt
+        type: u32
+      -
+        name: target
+        type: u32
+      -
+        name: autorate
+        type: u32
+      -
+        name: memory
+        type: u32
+      -
+        name: nat
+        type: u32
+      -
+        name: raw
+        type: u32
+      -
+        name: wash
+        type: u32
+      -
+        name: mpu
+        type: u32
+      -
+        name: ingress
+        type: u32
+      -
+        name: ack-filter
+        type: u32
+      -
+        name: split-gso
+        type: u32
+      -
+        name: fwmark
+        type: u32
+  -
+    name: tc-cake-stats-attrs
+    attributes:
+      -
+        name: pad
+        type: pad
+      -
+        name: capacity-estimate64
+        type: u64
+      -
+        name: memory-limit
+        type: u32
+      -
+        name: memory-used
+        type: u32
+      -
+        name: avg-netoff
+        type: u32
+      -
+        name: min-netlen
+        type: u32
+      -
+        name: max-netlen
+        type: u32
+      -
+        name: min-adjlen
+        type: u32
+      -
+        name: max-adjlen
+        type: u32
+      -
+        name: tin-stats
+        type: binary
+      -
+        name: deficit
+        type: s32
+      -
+        name: cobalt-count
+        type: u32
+      -
+        name: dropping
+        type: u32
+      -
+        name: drop-next-us
+        type: s32
+      -
+        name: p-drop
+        type: u32
+      -
+        name: blue-timer-us
+        type: s32
+  -
+    name: tc-cbs-attrs
+    attributes:
+      -
+        name: parms
+        type: binary
+        struct: tc-cbs-qopt
+  -
+    name: tc-choke-attrs
+    attributes:
+      -
+        name: parms
+        type: binary
+        struct: tc-red-qopt
+      -
+        name: stab
+        type: binary
+      -
+        name: max-p
+        type: u32
+  -
+    name: tc-codel-attrs
+    attributes:
+      -
+        name: target
+        type: u32
+      -
+        name: limit
+        type: u32
+      -
+        name: interval
+        type: u32
+      -
+        name: ecn
+        type: u32
+      -
+        name: ce-threshold
+        type: u32
+  -
+    name: tc-drr-attrs
+    attributes:
+      -
+        name: quantum
+        type: u32
+  -
+    name: tc-flower-attrs
+    attributes:
+      -
+        name: classid
+        type: u32
+      -
+        name: indev
+        type: string
+      -
+        name: act
+        type: array-nest
+        nested-attributes: tc-act-attrs
+      -
+        name: key-eth-dst
+        type: binary
+        display-hint: mac
+      -
+        name: key-eth-dst-mask
+        type: binary
+        display-hint: mac
+      -
+        name: key-eth-src
+        type: binary
+        display-hint: mac
+      -
+        name: key-eth-src-mask
+        type: binary
+        display-hint: mac
+      -
+        name: key-eth-type
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-ip-proto
+        type: u8
+      -
+        name: key-ipv4-src
+        type: u32
+        byte-order: big-endian
+        display-hint: ipv4
+      -
+        name: key-ipv4-src-mask
+        type: u32
+        byte-order: big-endian
+        display-hint: ipv4
+      -
+        name: key-ipv4-dst
+        type: u32
+        byte-order: big-endian
+        display-hint: ipv4
+      -
+        name: key-ipv4-dst-mask
+        type: u32
+        byte-order: big-endian
+        display-hint: ipv4
+      -
+        name: key-ipv6-src
+        type: binary
+        display-hint: ipv6
+      -
+        name: key-ipv6-src-mask
+        type: binary
+        display-hint: ipv6
+      -
+        name: key-ipv6-dst
+        type: binary
+        display-hint: ipv6
+      -
+        name: key-ipv6-dst-mask
+        type: binary
+        display-hint: ipv6
+      -
+        name: key-tcp-src
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-tcp-dst
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-udp-src
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-udp-dst
+        type: u16
+        byte-order: big-endian
+      -
+        name: flags
+        type: u32
+        enum: tc-cls-flags
+        enum-as-flags: true
+      -
+        name: key-vlan-id
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-vlan-prio
+        type: u8
+      -
+        name: key-vlan-eth-type
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-enc-key-id
+        type: u32
+        byte-order: big-endian
+      -
+        name: key-enc-ipv4-src
+        type: u32
+        byte-order: big-endian
+        display-hint: ipv4
+      -
+        name: key-enc-ipv4-src-mask
+        type: u32
+        byte-order: big-endian
+        display-hint: ipv4
+      -
+        name: key-enc-ipv4-dst
+        type: u32
+        byte-order: big-endian
+        display-hint: ipv4
+      -
+        name: key-enc-ipv4-dst-mask
+        type: u32
+        byte-order: big-endian
+        display-hint: ipv4
+      -
+        name: key-enc-ipv6-src
+        type: binary
+        display-hint: ipv6
+      -
+        name: key-enc-ipv6-src-mask
+        type: binary
+        display-hint: ipv6
+      -
+        name: key-enc-ipv6-dst
+        type: binary
+        display-hint: ipv6
+      -
+        name: key-enc-ipv6-dst-mask
+        type: binary
+        display-hint: ipv6
+      -
+        name: key-tcp-src-mask
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-tcp-dst-mask
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-udp-src-mask
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-udp-dst-mask
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-sctp-src-mask
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-sctp-dst-mask
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-sctp-src
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-sctp-dst
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-enc-udp-src-port
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-enc-udp-src-port-mask
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-enc-udp-dst-port
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-enc-udp-dst-port-mask
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-flags
+        type: u32
+        byte-order: big-endian
+      -
+        name: key-flags-mask
+        type: u32
+        byte-order: big-endian
+      -
+        name: key-icmpv4-code
+        type: u8
+      -
+        name: key-icmpv4-code-mask
+        type: u8
+      -
+        name: key-icmpv4-type
+        type: u8
+      -
+        name: key-icmpv4-type-mask
+        type: u8
+      -
+        name: key-icmpv6-code
+        type: u8
+      -
+        name: key-icmpv6-code-mask
+        type: u8
+      -
+        name: key-icmpv6-type
+        type: u8
+      -
+        name: key-icmpv6-type-mask
+        type: u8
+      -
+        name: key-arp-sip
+        type: u32
+        byte-order: big-endian
+      -
+        name: key-arp-sip-mask
+        type: u32
+        byte-order: big-endian
+      -
+        name: key-arp-tip
+        type: u32
+        byte-order: big-endian
+      -
+        name: key-arp-tip-mask
+        type: u32
+        byte-order: big-endian
+      -
+        name: key-arp-op
+        type: u8
+      -
+        name: key-arp-op-mask
+        type: u8
+      -
+        name: key-arp-sha
+        type: binary
+      -
+        name: key-arp-sha-mask
+        type: binary
+      -
+        name: key-arp-tha
+        type: binary
+      -
+        name: key-arp-tha-mask
+        type: binary
+      -
+        name: key-mpls-ttl
+        type: u8
+      -
+        name: key-mpls-bos
+        type: u8
+      -
+        name: key-mpls-tc
+        type: u8
+      -
+        name: key-mpls-label
+        type: u32
+        byte-order: big-endian
+      -
+        name: key-tcp-flags
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-tcp-flags-mask
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-ip-tos
+        type: u8
+      -
+        name: key-ip-tos-mask
+        type: u8
+      -
+        name: key-ip-ttl
+        type: u8
+      -
+        name: key-ip-ttl-mask
+        type: u8
+      -
+        name: key-cvlan-id
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-cvlan-prio
+        type: u8
+      -
+        name: key-cvlan-eth-type
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-enc-ip-tos
+        type: u8
+      -
+        name: key-enc-ip-tos-mask
+        type: u8
+      -
+        name: key-enc-ip-ttl
+        type: u8
+      -
+        name: key-enc-ip-ttl-mask
+        type: u8
+      -
+        name: key-enc-opts
+        type: binary
+      -
+        name: key-enc-opts-mask
+        type: binary
+      -
+        name: in-hw-count
+        type: u32
+      -
+        name: key-port-src-min
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-port-src-max
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-port-dst-min
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-port-dst-max
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-ct-state
+        type: u16
+      -
+        name: key-ct-state-mask
+        type: u16
+      -
+        name: key-ct-zone
+        type: u16
+      -
+        name: key-ct-zone-mask
+        type: u16
+      -
+        name: key-ct-mark
+        type: u32
+      -
+        name: key-ct-mark-mask
+        type: u32
+      -
+        name: key-ct-labels
+        type: binary
+      -
+        name: key-ct-labels-mask
+        type: binary
+      -
+        name: key-mpls-opts
+        type: binary
+      -
+        name: key-hash
+        type: u32
+      -
+        name: key-hash-mask
+        type: u32
+      -
+        name: key-num-of-vlans
+        type: u8
+      -
+        name: key-pppoe-sid
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-ppp-proto
+        type: u16
+        byte-order: big-endian
+      -
+        name: key-l2-tpv3-sid
+        type: u32
+        byte-order: big-endian
+  -
+    name: tc-gred-attrs
+    attributes:
+      -
+        name: parms
+        type: binary # array of struct: tc-gred-qopt
+      -
+        name: stab
+        type: binary
+        sub-type: u8
+      -
+        name: dps
+        type: binary
+        struct: tc-gred-sopt
+      -
+        name: max-p
+        type: binary
+        sub-type: u32
+      -
+        name: limit
+        type: u32
+      -
+        name: vq-list
+        type: nest
+        nested-attributes: tca-gred-vq-list-attrs
+  -
+    name: tca-gred-vq-list-attrs
+    attributes:
+      -
+        name: entry
+        type: nest
+        nested-attributes: tca-gred-vq-entry-attrs
+        multi-attr: true
+  -
+    name: tca-gred-vq-entry-attrs
+    attributes:
+      -
+        name: pad
+        type: pad
+      -
+        name: dp
+        type: u32
+      -
+        name: stat-bytes
+        type: u32
+      -
+        name: stat-packets
+        type: u32
+      -
+        name: stat-backlog
+        type: u32
+      -
+        name: stat-prob-drop
+        type: u32
+      -
+        name: stat-prob-mark
+        type: u32
+      -
+        name: stat-forced-drop
+        type: u32
+      -
+        name: stat-forced-mark
+        type: u32
+      -
+        name: stat-pdrop
+        type: u32
+      -
+        name: stat-other
+        type: u32
+      -
+        name: flags
+        type: u32
+  -
+    name: tc-hfsc-attrs
+    attributes:
+      -
+        name: rsc
+        type: binary
+      -
+        name: fsc
+        type: binary
+      -
+        name: usc
+        type: binary
+  -
+    name: tc-hhf-attrs
+    attributes:
+      -
+        name: backlog-limit
+        type: u32
+      -
+        name: quantum
+        type: u32
+      -
+        name: hh-flows-limit
+        type: u32
+      -
+        name: reset-timeout
+        type: u32
+      -
+        name: admit-bytes
+        type: u32
+      -
+        name: evict-timeout
+        type: u32
+      -
+        name: non-hh-weight
+        type: u32
+  -
+    name: tc-htb-attrs
+    attributes:
+      -
+        name: parms
+        type: binary
+        struct: tc-htb-opt
+      -
+        name: init
+        type: binary
+        struct: tc-htb-glob
+      -
+        name: ctab
+        type: binary
+      -
+        name: rtab
+        type: binary
+      -
+        name: direct-qlen
+        type: u32
+      -
+        name: rate64
+        type: u64
+      -
+        name: ceil64
+        type: u64
+      -
+        name: pad
+        type: pad
+      -
+        name: offload
+        type: flag
+  -
+    name: tc-act-attrs
+    attributes:
+      -
+        name: kind
+        type: string
+      -
+        name: options
+        type: sub-message
+        sub-message: tc-act-options-msg
+        selector: kind
+      -
+        name: index
+        type: u32
+      -
+        name: stats
+        type: binary
+      -
+        name: pad
+        type: pad
+      -
+        name: cookie
+        type: binary
+      -
+        name: flags
+        type: bitfield32
+      -
+        name: hw-stats
+        type: bitfield32
+      -
+        name: used-hw-stats
+        type: bitfield32
+      -
+        name: in-hw-count
+        type: u32
+  -
+    name: tc-etf-attrs
+    attributes:
+      -
+        name: parms
+        type: binary
+        struct: tc-etf-qopt
+  -
+    name: tc-ets-attrs
+    attributes:
+      -
+        name: nbands
+        type: u8
+      -
+        name: nstrict
+        type: u8
+      -
+        name: quanta
+        type: nest
+        nested-attributes: tc-ets-attrs
+      -
+        name: quanta-band
+        type: u32
+        multi-attr: true
+      -
+        name: priomap
+        type: nest
+        nested-attributes: tc-ets-attrs
+      -
+        name: priomap-band
+        type: u8
+        multi-attr: true
+  -
+    name: tc-fq-attrs
+    attributes:
+      -
+        name: plimit
+        type: u32
+      -
+        name: flow-plimit
+        type: u32
+      -
+        name: quantum
+        type: u32
+      -
+        name: initial-quantum
+        type: u32
+      -
+        name: rate-enable
+        type: u32
+      -
+        name: flow-default-rate
+        type: u32
+      -
+        name: flow-max-rate
+        type: u32
+      -
+        name: buckets-log
+        type: u32
+      -
+        name: flow-refill-delay
+        type: u32
+      -
+        name: orphan-mask
+        type: u32
+      -
+        name: low-rate-threshold
+        type: u32
+      -
+        name: ce-threshold
+        type: u32
+      -
+        name: timer-slack
+        type: u32
+      -
+        name: horizon
+        type: u32
+      -
+        name: horizon-drop
+        type: u8
+  -
+    name: tc-fq-codel-attrs
+    attributes:
+      -
+        name: target
+        type: u32
+      -
+        name: limit
+        type: u32
+      -
+        name: interval
+        type: u32
+      -
+        name: ecn
+        type: u32
+      -
+        name: flows
+        type: u32
+      -
+        name: quantum
+        type: u32
+      -
+        name: ce-threshold
+        type: u32
+      -
+        name: drop-batch-size
+        type: u32
+      -
+        name: memory-limit
+        type: u32
+      -
+        name: ce-threshold-selector
+        type: u8
+      -
+        name: ce-threshold-mask
+        type: u8
+  -
+    name: tc-fq-pie-attrs
+    attributes:
+      -
+        name: limit
+        type: u32
+      -
+        name: flows
+        type: u32
+      -
+        name: target
+        type: u32
+      -
+        name: tupdate
+        type: u32
+      -
+        name: alpha
+        type: u32
+      -
+        name: beta
+        type: u32
+      -
+        name: quantum
+        type: u32
+      -
+        name: memory-limit
+        type: u32
+      -
+        name: ecn-prob
+        type: u32
+      -
+        name: ecn
+        type: u32
+      -
+        name: bytemode
+        type: u32
+      -
+        name: dq-rate-estimator
+        type: u32
+  -
+    name: tc-netem-attrs
+    attributes:
+      -
+        name: corr
+        type: binary
+      -
+        name: delay-dist
+        type: binary
+        sub-type: s16
+      -
+        name: reorder
+        type: binary
+      -
+        name: corrupt
+        type: binary
+      -
+        name: loss
+        type: binary
+      -
+        name: rate
+        type: binary
+      -
+        name: ecn
+        type: u32
+      -
+        name: rate64
+        type: u64
+      -
+        name: pad
+        type: u32
+      -
+        name: latency64
+        type: s64
+      -
+        name: jitter64
+        type: s64
+      -
+        name: slot
+        type: binary
+      -
+        name: slot-dist
+        type: binary
+        sub-type: s16
+  -
+    name: tc-pie-attrs
+    attributes:
+      -
+        name: target
+        type: u32
+      -
+        name: limit
+        type: u32
+      -
+        name: tupdate
+        type: u32
+      -
+        name: alpha
+        type: u32
+      -
+        name: beta
+        type: u32
+      -
+        name: ecn
+        type: u32
+      -
+        name: bytemode
+        type: u32
+      -
+        name: dq-rate-estimator
+        type: u32
+  -
+    name: tc-qfq-attrs
+    attributes:
+      -
+        name: weight
+        type: u32
+      -
+        name: lmax
+        type: u32
+  -
+    name: tc-red-attrs
+    attributes:
+      -
+        name: parms
+        type: binary
+        struct: tc-red-qopt
+      -
+        name: stab
+        type: binary
+      -
+        name: max-p
+        type: u32
+      -
+        name: flags
+        type: binary
+      -
+        name: early-drop-block
+        type: u32
+      -
+        name: mark-block
+        type: u32
+  -
+    name: tc-taprio-attrs
+    attributes:
+      -
+        name: priomap
+        type: binary
+        struct: tc-mqprio-qopt
+      -
+        name: sched-entry-list
+        type: nest
+        nested-attributes: tc-taprio-sched-entry-list
+      -
+        name: sched-base-time
+        type: s64
+      -
+        name: sched-single-entry
+        type: nest
+        nested-attributes: tc-taprio-sched-entry
+      -
+        name: sched-clockid
+        type: s32
+      -
+        name: pad
+        type: pad
+      -
+        name: admin-sched
+        type: binary
+      -
+        name: sched-cycle-time
+        type: s64
+      -
+        name: sched-cycle-time-extension
+        type: s64
+      -
+        name: flags
+        type: u32
+      -
+        name: txtime-delay
+        type: u32
+      -
+        name: tc-entry
+        type: nest
+        nested-attributes: tc-taprio-tc-entry-attrs
+  -
+    name: tc-taprio-sched-entry-list
+    attributes:
+      -
+        name: entry
+        type: nest
+        nested-attributes: tc-taprio-sched-entry
+  -
+    name: tc-taprio-sched-entry
+    attributes:
+      -
+        name: index
+        type: u32
+      -
+        name: cmd
+        type: u8
+      -
+        name: gate-mask
+        type: u32
+      -
+        name: interval
+        type: u32
+  -
+    name: tc-taprio-tc-entry-attrs
+    attributes:
+      -
+        name: index
+        type: u32
+      -
+        name: max-sdu
+        type: u32
+      -
+        name: fp
+        type: u32
+  -
+    name: tc-tbf-attrs
+    attributes:
+      -
+        name: parms
+        type: binary
+        struct: tc-tbf-qopt
+      -
+        name: rtab
+        type: binary
+      -
+        name: ptab
+        type: binary
+      -
+        name: rate64
+        type: u64
+      -
+        name: prate4
+        type: u64
+      -
+        name: burst
+        type: u32
+      -
+        name: pburst
+        type: u32
+      -
+        name: pad
+        type: pad
+  -
+    name: tca-gact-attrs
+    attributes:
+      -
+        name: tm
+        type: binary
+      -
+        name: parms
+        type: binary
+      -
+        name: prob
+        type: binary
+      -
+        name: pad
+        type: pad
+  -
+    name: tca-stab-attrs
+    attributes:
+      -
+        name: base
+        type: binary
+        struct: tc-sizespec
+      -
+        name: data
+        type: binary
+  -
+    name: tca-stats-attrs
+    attributes:
+      -
+        name: basic
+        type: binary
+      -
+        name: rate-est
+        type: binary
+      -
+        name: queue
+        type: binary
+      -
+        name: app
+        type: binary # TODO sub-message needs 2+ level deep lookup
+        sub-message: tca-stats-app-msg
+        selector: kind
+      -
+        name: rate-est64
+        type: binary
+      -
+        name: pad
+        type: pad
+      -
+        name: basic-hw
+        type: binary
+      -
+        name: pkt64
+        type: binary
+
+sub-messages:
+  -
+    name: tc-options-msg
+    formats:
+      -
+        value: bfifo
+        fixed-header: tc-fifo-qopt
+      -
+        value: cake
+        attribute-set: tc-cake-attrs
+      -
+        value: cbs
+        attribute-set: tc-cbs-attrs
+      -
+        value: choke
+        attribute-set: tc-choke-attrs
+      -
+        value: clsact # no content
+      -
+        value: codel
+        attribute-set: tc-codel-attrs
+      -
+        value: drr
+        attribute-set: tc-drr-attrs
+      -
+        value: etf
+        attribute-set: tc-etf-attrs
+      -
+        value: ets
+        attribute-set: tc-ets-attrs
+      -
+        value: fq
+        attribute-set: tc-fq-attrs
+      -
+        value: fq_codel
+        attribute-set: tc-fq-codel-attrs
+      -
+        value: fq_pie
+        attribute-set: tc-fq-pie-attrs
+      -
+        value: flower
+        attribute-set: tc-flower-attrs
+      -
+        value: gred
+        attribute-set: tc-gred-attrs
+      -
+        value: hfsc
+        fixed-header: tc-hfsc-qopt
+      -
+        value: hhf
+        attribute-set: tc-hhf-attrs
+      -
+        value: htb
+        attribute-set: tc-htb-attrs
+      -
+        value: ingress # no content
+      -
+        value: mq # no content
+      -
+        value: mqprio
+        fixed-header: tc-mqprio-qopt
+      -
+        value: multiq
+        fixed-header: tc-multiq-qopt
+      -
+        value: netem
+        fixed-header: tc-netem-qopt
+        attribute-set: tc-netem-attrs
+      -
+        value: pfifo
+        fixed-header: tc-fifo-qopt
+      -
+        value: pfifo_fast
+        fixed-header: tc-prio-qopt
+      -
+        value: pfifo_head_drop
+        fixed-header: tc-fifo-qopt
+      -
+        value: pie
+        attribute-set: tc-pie-attrs
+      -
+        value: plug
+        fixed-header: tc-plug-qopt
+      -
+        value: prio
+        fixed-header: tc-prio-qopt
+      -
+        value: qfq
+        attribute-set: tc-qfq-attrs
+      -
+        value: red
+        attribute-set: tc-red-attrs
+      -
+        value: sfb
+        fixed-header: tc-sfb-qopt
+      -
+        value: sfq
+        fixed-header: tc-sfq-qopt-v1
+      -
+        value: taprio
+        attribute-set: tc-taprio-attrs
+      -
+        value: tbf
+        attribute-set: tc-tbf-attrs
+  -
+    name: tc-act-options-msg
+    formats:
+      -
+        value: gact
+        attribute-set: tca-gact-attrs
+  -
+    name: tca-stats-app-msg
+    formats:
+      -
+        value: bfifo
+      -
+        value: blackhole
+      -
+        value: cake
+        attribute-set: tc-cake-stats-attrs
+      -
+        value: cbs
+      -
+        value: choke
+      -
+        value: clsact
+      -
+        value: codel
+      -
+        value: drr
+      -
+        value: etf
+      -
+        value: ets
+      -
+        value: fq
+      -
+        value: fq_codel
+      -
+        value: fq_pie
+      -
+        value: flower
+      -
+        value: gred
+      -
+        value: hfsc
+      -
+        value: hhf
+      -
+        value: htb
+      -
+        value: ingress
+      -
+        value: mq
+      -
+        value: mqprio
+      -
+        value: multiq
+      -
+        value: netem
+      -
+        value: noqueue
+      -
+        value: pfifo
+      -
+        value: pfifo_fast
+      -
+        value: pfifo_head_drop
+      -
+        value: pie
+      -
+        value: plug
+      -
+        value: prio
+      -
+        value: qfq
+      -
+        value: red
+      -
+        value: sfb
+      -
+        value: sfq
+      -
+        value: taprio
+      -
+        value: tbf
+
+operations:
+  enum-model: directional
+  list:
+    -
+      name: newqdisc
+      doc: Create new tc qdisc.
+      attribute-set: tc-attrs
+      fixed-header: tcmsg
+      do:
+        request:
+          value: 36
+          attributes: &create-params
+            - kind
+            - options
+            - rate
+            - chain
+            - ingress-block
+            - egress-block
+    -
+      name: delqdisc
+      doc: Delete existing tc qdisc.
+      attribute-set: tc-attrs
+      fixed-header: tcmsg
+      do:
+        request:
+          value: 37
+    -
+      name: getqdisc
+      doc: Get / dump tc qdisc information.
+      attribute-set: tc-attrs
+      fixed-header: tcmsg
+      do:
+        request:
+          value: 38
+          attributes:
+            - dump-invisible
+        reply:
+          value: 36
+          attributes: &tc-all
+            - kind
+            - options
+            - stats
+            - xstats
+            - rate
+            - fcnt
+            - stats2
+            - stab
+            - chain
+            - ingress-block
+            - egress-block
+    -
+      name: newtclass
+      doc: Get / dump tc traffic class information.
+      attribute-set: tc-attrs
+      fixed-header: tcmsg
+      do:
+        request:
+          value: 40
+          attributes: *create-params
+    -
+      name: deltclass
+      doc: Get / dump tc traffic class information.
+      attribute-set: tc-attrs
+      fixed-header: tcmsg
+      do:
+        request:
+          value: 41
+    -
+      name: gettclass
+      doc: Get / dump tc traffic class information.
+      attribute-set: tc-attrs
+      fixed-header: tcmsg
+      do:
+        request:
+          value: 42
+        reply:
+          value: 40
+          attributes: *tc-all
+    -
+      name: newtfilter
+      doc: Get / dump tc filter information.
+      attribute-set: tc-attrs
+      fixed-header: tcmsg
+      do:
+        request:
+          value: 44
+          attributes: *create-params
+    -
+      name: deltfilter
+      doc: Get / dump tc filter information.
+      attribute-set: tc-attrs
+      fixed-header: tcmsg
+      do:
+        request:
+          value: 45
+          attributes:
+            - chain
+            - kind
+    -
+      name: gettfilter
+      doc: Get / dump tc filter information.
+      attribute-set: tc-attrs
+      fixed-header: tcmsg
+      do:
+        request:
+          value: 46
+          attributes:
+            - chain
+            - kind
+        reply:
+          value: 44
+          attributes: *tc-all
+      dump:
+        request:
+          value: 46
+          attributes:
+            - chain
+            - dump-flags
+        reply:
+          value: 44
+          attributes: *tc-all
+    -
+      name: newchain
+      doc: Get / dump tc chain information.
+      attribute-set: tc-attrs
+      fixed-header: tcmsg
+      do:
+        request:
+          value: 100
+          attributes: *create-params
+    -
+      name: delchain
+      doc: Get / dump tc chain information.
+      attribute-set: tc-attrs
+      fixed-header: tcmsg
+      do:
+        request:
+          value: 101
+          attributes:
+            - chain
+    -
+      name: getchain
+      doc: Get / dump tc chain information.
+      attribute-set: tc-attrs
+      fixed-header: tcmsg
+      do:
+        request:
+          value: 102
+          attributes:
+            - chain
+        reply:
+          value: 100
+          attributes: *tc-all
+
+mcast-groups:
+  list:
+    -
+      name: rtnlgrp-tc
+      value: 4
diff --git a/Documentation/networking/bridge.rst b/Documentation/networking/bridge.rst
index c859f3c1636e..ba14e7b07869 100644
--- a/Documentation/networking/bridge.rst
+++ b/Documentation/networking/bridge.rst
@@ -4,18 +4,332 @@
 Ethernet Bridging
 =================
 
-In order to use the Ethernet bridging functionality, you'll need the
-userspace tools.
+Introduction
+============
 
-Documentation for Linux bridging is on:
-   https://wiki.linuxfoundation.org/networking/bridge
+The IEEE 802.1Q-2022 (Bridges and Bridged Networks) standard defines the
+operation of bridges in computer networks. A bridge, in the context of this
+standard, is a device that connects two or more network segments and operates
+at the data link layer (Layer 2) of the OSI (Open Systems Interconnection)
+model. The purpose of a bridge is to filter and forward frames between
+different segments based on the destination MAC (Media Access Control) address.
 
-The bridge-utilities are maintained at:
-   git://git.kernel.org/pub/scm/linux/kernel/git/shemminger/bridge-utils.git
+Bridge kAPI
+===========
 
-Additionally, the iproute2 utilities can be used to configure
-bridge devices.
+Here are some core structures of bridge code. Note that the kAPI is *unstable*,
+and can be changed at any time.
 
-If you still have questions, don't hesitate to post to the mailing list 
-(more info https://lists.linux-foundation.org/mailman/listinfo/bridge).
+.. kernel-doc:: net/bridge/br_private.h
+   :identifiers: net_bridge_vlan
 
+Bridge uAPI
+===========
+
+Modern Linux bridge uAPI is accessed via Netlink interface. You can find
+below files where the bridge and bridge port netlink attributes are defined.
+
+Bridge netlink attributes
+-------------------------
+
+.. kernel-doc:: include/uapi/linux/if_link.h
+   :doc: Bridge enum definition
+
+Bridge port netlink attributes
+------------------------------
+
+.. kernel-doc:: include/uapi/linux/if_link.h
+   :doc: Bridge port enum definition
+
+Bridge sysfs
+------------
+
+The sysfs interface is deprecated and should not be extended if new
+options are added.
+
+STP
+===
+
+The STP (Spanning Tree Protocol) implementation in the Linux bridge driver
+is a critical feature that helps prevent loops and broadcast storms in
+Ethernet networks by identifying and disabling redundant links. In a Linux
+bridge context, STP is crucial for network stability and availability.
+
+STP is a Layer 2 protocol that operates at the Data Link Layer of the OSI
+model. It was originally developed as IEEE 802.1D and has since evolved into
+multiple versions, including Rapid Spanning Tree Protocol (RSTP) and
+`Multiple Spanning Tree Protocol (MSTP)
+<https://lore.kernel.org/netdev/20220316150857.2442916-1-tobias@waldekranz.com/>`_.
+
+The 802.1D-2004 removed the original Spanning Tree Protocol, instead
+incorporating the Rapid Spanning Tree Protocol (RSTP). By 2014, all the
+functionality defined by IEEE 802.1D has been incorporated into either
+IEEE 802.1Q (Bridges and Bridged Networks) or IEEE 802.1AC (MAC Service
+Definition). 802.1D has been officially withdrawn in 2022.
+
+Bridge Ports and STP States
+---------------------------
+
+In the context of STP, bridge ports can be in one of the following states:
+  * Blocking: The port is disabled for data traffic and only listens for
+    BPDUs (Bridge Protocol Data Units) from other devices to determine the
+    network topology.
+  * Listening: The port begins to participate in the STP process and listens
+    for BPDUs.
+  * Learning: The port continues to listen for BPDUs and begins to learn MAC
+    addresses from incoming frames but does not forward data frames.
+  * Forwarding: The port is fully operational and forwards both BPDUs and
+    data frames.
+  * Disabled: The port is administratively disabled and does not participate
+    in the STP process. The data frames forwarding are also disabled.
+
+Root Bridge and Convergence
+---------------------------
+
+In the context of networking and Ethernet bridging in Linux, the root bridge
+is a designated switch in a bridged network that serves as a reference point
+for the spanning tree algorithm to create a loop-free topology.
+
+Here's how the STP works and root bridge is chosen:
+  1. Bridge Priority: Each bridge running a spanning tree protocol, has a
+     configurable Bridge Priority value. The lower the value, the higher the
+     priority. By default, the Bridge Priority is set to a standard value
+     (e.g., 32768).
+  2. Bridge ID: The Bridge ID is composed of two components: Bridge Priority
+     and the MAC address of the bridge. It uniquely identifies each bridge
+     in the network. The Bridge ID is used to compare the priorities of
+     different bridges.
+  3. Bridge Election: When the network starts, all bridges initially assume
+     that they are the root bridge. They start advertising Bridge Protocol
+     Data Units (BPDU) to their neighbors, containing their Bridge ID and
+     other information.
+  4. BPDU Comparison: Bridges exchange BPDUs to determine the root bridge.
+     Each bridge examines the received BPDUs, including the Bridge Priority
+     and Bridge ID, to determine if it should adjust its own priorities.
+     The bridge with the lowest Bridge ID will become the root bridge.
+  5. Root Bridge Announcement: Once the root bridge is determined, it sends
+     BPDUs with information about the root bridge to all other bridges in the
+     network. This information is used by other bridges to calculate the
+     shortest path to the root bridge and, in doing so, create a loop-free
+     topology.
+  6. Forwarding Ports: After the root bridge is selected and the spanning tree
+     topology is established, each bridge determines which of its ports should
+     be in the forwarding state (used for data traffic) and which should be in
+     the blocking state (used to prevent loops). The root bridge's ports are
+     all in the forwarding state. while other bridges have some ports in the
+     blocking state to avoid loops.
+  7. Root Ports: After the root bridge is selected and the spanning tree
+     topology is established, each non-root bridge processes incoming
+     BPDUs and determines which of its ports provides the shortest path to the
+     root bridge based on the information in the received BPDUs. This port is
+     designated as the root port. And it is in the Forwarding state, allowing
+     it to actively forward network traffic.
+  8. Designated ports: A designated port is the port through which the non-root
+     bridge will forward traffic towards the designated segment. Designated ports
+     are placed in the Forwarding state. All other ports on the non-root
+     bridge that are not designated for specific segments are placed in the
+     Blocking state to prevent network loops.
+
+STP ensures network convergence by calculating the shortest path and disabling
+redundant links. When network topology changes occur (e.g., a link failure),
+STP recalculates the network topology to restore connectivity while avoiding loops.
+
+Proper configuration of STP parameters, such as the bridge priority, can
+influence network performance, path selection and which bridge becomes the
+Root Bridge.
+
+User space STP helper
+---------------------
+
+The user space STP helper *bridge-stp* is a program to control whether to use
+user mode spanning tree. The ``/sbin/bridge-stp <bridge> <start|stop>`` is
+called by the kernel when STP is enabled/disabled on a bridge
+(via ``brctl stp <bridge> <on|off>`` or ``ip link set <bridge> type bridge
+stp_state <0|1>``).  The kernel enables user_stp mode if that command returns
+0, or enables kernel_stp mode if that command returns any other value.
+
+VLAN
+====
+
+A LAN (Local Area Network) is a network that covers a small geographic area,
+typically within a single building or a campus. LANs are used to connect
+computers, servers, printers, and other networked devices within a localized
+area. LANs can be wired (using Ethernet cables) or wireless (using Wi-Fi).
+
+A VLAN (Virtual Local Area Network) is a logical segmentation of a physical
+network into multiple isolated broadcast domains. VLANs are used to divide
+a single physical LAN into multiple virtual LANs, allowing different groups of
+devices to communicate as if they were on separate physical networks.
+
+Typically there are two VLAN implementations, IEEE 802.1Q and IEEE 802.1ad
+(also known as QinQ). IEEE 802.1Q is a standard for VLAN tagging in Ethernet
+networks. It allows network administrators to create logical VLANs on a
+physical network and tag Ethernet frames with VLAN information, which is
+called *VLAN-tagged frames*. IEEE 802.1ad, commonly known as QinQ or Double
+VLAN, is an extension of the IEEE 802.1Q standard. QinQ allows for the
+stacking of multiple VLAN tags within a single Ethernet frame. The Linux
+bridge supports both the IEEE 802.1Q and `802.1AD
+<https://lore.kernel.org/netdev/1402401565-15423-1-git-send-email-makita.toshiaki@lab.ntt.co.jp/>`_
+protocol for VLAN tagging.
+
+`VLAN filtering <https://lore.kernel.org/netdev/1360792820-14116-1-git-send-email-vyasevic@redhat.com/>`_
+on a bridge is disabled by default. After enabling VLAN filtering on a bridge,
+it will start forwarding frames to appropriate destinations based on their
+destination MAC address and VLAN tag (both must match).
+
+Multicast
+=========
+
+The Linux bridge driver has multicast support allowing it to process Internet
+Group Management Protocol (IGMP) or Multicast Listener Discovery (MLD)
+messages, and to efficiently forward multicast data packets. The bridge
+driver supports IGMPv2/IGMPv3 and MLDv1/MLDv2.
+
+Multicast snooping
+------------------
+
+Multicast snooping is a networking technology that allows network switches
+to intelligently manage multicast traffic within a local area network (LAN).
+
+The switch maintains a multicast group table, which records the association
+between multicast group addresses and the ports where hosts have joined these
+groups. The group table is dynamically updated based on the IGMP/MLD messages
+received. With the multicast group information gathered through snooping, the
+switch optimizes the forwarding of multicast traffic. Instead of blindly
+broadcasting the multicast traffic to all ports, it sends the multicast
+traffic based on the destination MAC address only to ports which have
+subscribed the respective destination multicast group.
+
+When created, the Linux bridge devices have multicast snooping enabled by
+default. It maintains a Multicast forwarding database (MDB) which keeps track
+of port and group relationships.
+
+IGMPv3/MLDv2 EHT support
+------------------------
+
+The Linux bridge supports IGMPv3/MLDv2 EHT (Explicit Host Tracking), which
+was added by `474ddb37fa3a ("net: bridge: multicast: add EHT allow/block handling")
+<https://lore.kernel.org/netdev/20210120145203.1109140-1-razor@blackwall.org/>`_
+
+The explicit host tracking enables the device to keep track of each
+individual host that is joined to a particular group or channel. The main
+benefit of the explicit host tracking in IGMP is to allow minimal leave
+latencies when a host leaves a multicast group or channel.
+
+The length of time between a host wanting to leave and a device stopping
+traffic forwarding is called the IGMP leave latency. A device configured
+with IGMPv3 or MLDv2 and explicit tracking can immediately stop forwarding
+traffic if the last host to request to receive traffic from the device
+indicates that it no longer wants to receive traffic. The leave latency
+is thus bound only by the packet transmission latencies in the multiaccess
+network and the processing time in the device.
+
+Other multicast features
+------------------------
+
+The Linux bridge also supports `per-VLAN multicast snooping
+<https://lore.kernel.org/netdev/20210719170637.435541-1-razor@blackwall.org/>`_,
+which is disabled by default but can be enabled. And `Multicast Router Discovery
+<https://lore.kernel.org/netdev/20190121062628.2710-1-linus.luessing@c0d3.blue/>`_,
+which help identify the location of multicast routers.
+
+Switchdev
+=========
+
+Linux Bridge Switchdev is a feature in the Linux kernel that extends the
+capabilities of the traditional Linux bridge to work more efficiently with
+hardware switches that support switchdev. With Linux Bridge Switchdev, certain
+networking functions like forwarding, filtering, and learning of Ethernet
+frames can be offloaded to a hardware switch. This offloading reduces the
+burden on the Linux kernel and CPU, leading to improved network performance
+and lower latency.
+
+To use Linux Bridge Switchdev, you need hardware switches that support the
+switchdev interface. This means that the switch hardware needs to have the
+necessary drivers and functionality to work in conjunction with the Linux
+kernel.
+
+Please see the :ref:`switchdev` document for more details.
+
+Netfilter
+=========
+
+The bridge netfilter module is a legacy feature that allows to filter bridged
+packets with iptables and ip6tables. Its use is discouraged. Users should
+consider using nftables for packet filtering.
+
+The older ebtables tool is more feature-limited compared to nftables, but
+just like nftables it doesn't need this module either to function.
+
+The br_netfilter module intercepts packets entering the bridge, performs
+minimal sanity tests on ipv4 and ipv6 packets and then pretends that
+these packets are being routed, not bridged. br_netfilter then calls
+the ip and ipv6 netfilter hooks from the bridge layer, i.e. ip(6)tables
+rulesets will also see these packets.
+
+br_netfilter is also the reason for the iptables *physdev* match:
+This match is the only way to reliably tell routed and bridged packets
+apart in an iptables ruleset.
+
+Note that ebtables and nftables will work fine without the br_netfilter module.
+iptables/ip6tables/arptables do not work for bridged traffic because they
+plug in the routing stack. nftables rules in ip/ip6/inet/arp families won't
+see traffic that is forwarded by a bridge either, but that's very much how it
+should be.
+
+Historically the feature set of ebtables was very limited (it still is),
+this module was added to pretend packets are routed and invoke the ipv4/ipv6
+netfilter hooks from the bridge so users had access to the more feature-rich
+iptables matching capabilities (including conntrack). nftables doesn't have
+this limitation, pretty much all features work regardless of the protocol family.
+
+So, br_netfilter is only needed if users, for some reason, need to use
+ip(6)tables to filter packets forwarded by the bridge, or NAT bridged
+traffic. For pure link layer filtering, this module isn't needed.
+
+Other Features
+==============
+
+The Linux bridge also supports `IEEE 802.11 Proxy ARP
+<https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=958501163ddd6ea22a98f94fa0e7ce6d4734e5c4>`_,
+`Media Redundancy Protocol (MRP)
+<https://lore.kernel.org/netdev/20200426132208.3232-1-horatiu.vultur@microchip.com/>`_,
+`Media Redundancy Protocol (MRP) LC mode
+<https://lore.kernel.org/r/20201124082525.273820-1-horatiu.vultur@microchip.com>`_,
+`IEEE 802.1X port authentication
+<https://lore.kernel.org/netdev/20220218155148.2329797-1-schultz.hans+netdev@gmail.com/>`_,
+and `MAC Authentication Bypass (MAB)
+<https://lore.kernel.org/netdev/20221101193922.2125323-2-idosch@nvidia.com/>`_.
+
+FAQ
+===
+
+What does a bridge do?
+----------------------
+
+A bridge transparently forwards traffic between multiple network interfaces.
+In plain English this means that a bridge connects two or more physical
+Ethernet networks, to form one larger (logical) Ethernet network.
+
+Is it L3 protocol independent?
+------------------------------
+
+Yes. The bridge sees all frames, but it *uses* only L2 headers/information.
+As such, the bridging functionality is protocol independent, and there should
+be no trouble forwarding IPX, NetBEUI, IP, IPv6, etc.
+
+Contact Info
+============
+
+The code is currently maintained by Roopa Prabhu <roopa@nvidia.com> and
+Nikolay Aleksandrov <razor@blackwall.org>. Bridge bugs and enhancements
+are discussed on the linux-netdev mailing list netdev@vger.kernel.org and
+bridge@lists.linux-foundation.org.
+
+The list is open to anyone interested: http://vger.kernel.org/vger-lists.html#netdev
+
+External Links
+==============
+
+The old Documentation for Linux bridging is on:
+https://wiki.linuxfoundation.org/networking/bridge
diff --git a/Documentation/networking/device_drivers/ethernet/amazon/ena.rst b/Documentation/networking/device_drivers/ethernet/amazon/ena.rst
index 5eaa3ab6c73e..b842bcb14255 100644
--- a/Documentation/networking/device_drivers/ethernet/amazon/ena.rst
+++ b/Documentation/networking/device_drivers/ethernet/amazon/ena.rst
@@ -54,6 +54,7 @@ ena_common_defs.h   Common definitions for ena_com layer.
 ena_regs_defs.h     Definition of ENA PCI memory-mapped (MMIO) registers.
 ena_netdev.[ch]     Main Linux kernel driver.
 ena_ethtool.c       ethtool callbacks.
+ena_xdp.[ch]        XDP files
 ena_pci_id_tbl.h    Supported device IDs.
 =================   ======================================================
 
diff --git a/Documentation/networking/device_drivers/ethernet/intel/ice.rst b/Documentation/networking/device_drivers/ethernet/intel/ice.rst
index e4d065c55ea8..5038e54586af 100644
--- a/Documentation/networking/device_drivers/ethernet/intel/ice.rst
+++ b/Documentation/networking/device_drivers/ethernet/intel/ice.rst
@@ -895,6 +895,147 @@ driver writes raw bytes by the GNSS object to the receiver through i2c. Please
 refer to the hardware GNSS module documentation for configuration details.
 
 
+Firmware (FW) logging
+---------------------
+The driver supports FW logging via the debugfs interface on PF 0 only. The FW
+running on the NIC must support FW logging; if the FW doesn't support FW logging
+the 'fwlog' file will not get created in the ice debugfs directory.
+
+Module configuration
+~~~~~~~~~~~~~~~~~~~~
+Firmware logging is configured on a per module basis. Each module can be set to
+a value independent of the other modules (unless the module 'all' is specified).
+The modules will be instantiated under the 'fwlog/modules' directory.
+
+The user can set the log level for a module by writing to the module file like
+this::
+
+  # echo <log_level> > /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/modules/<module>
+
+where
+
+* log_level is a name as described below. Each level includes the
+  messages from the previous/lower level
+
+      *	none
+      *	error
+      *	warning
+      *	normal
+      *	verbose
+
+* module is a name that represents the module to receive events for. The
+  module names are
+
+      *	general
+      *	ctrl
+      *	link
+      *	link_topo
+      *	dnl
+      *	i2c
+      *	sdp
+      *	mdio
+      *	adminq
+      *	hdma
+      *	lldp
+      *	dcbx
+      *	dcb
+      *	xlr
+      *	nvm
+      *	auth
+      *	vpd
+      *	iosf
+      *	parser
+      *	sw
+      *	scheduler
+      *	txq
+      *	rsvd
+      *	post
+      *	watchdog
+      *	task_dispatch
+      *	mng
+      *	synce
+      *	health
+      *	tsdrv
+      *	pfreg
+      *	mdlver
+      *	all
+
+The name 'all' is special and allows the user to set all of the modules to the
+specified log_level or to read the log_level of all of the modules.
+
+Example usage to configure the modules
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+To set a single module to 'verbose'::
+
+  # echo verbose > /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/modules/link
+
+To set multiple modules then issue the command multiple times::
+
+  # echo verbose > /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/modules/link
+  # echo warning > /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/modules/ctrl
+  # echo none > /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/modules/dcb
+
+To set all the modules to the same value::
+
+  # echo normal > /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/modules/all
+
+To read the log_level of a specific module (e.g. module 'general')::
+
+  # cat /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/modules/general
+
+To read the log_level of all the modules::
+
+  # cat /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/modules/all
+
+Enabling FW log
+~~~~~~~~~~~~~~~
+Configuring the modules indicates to the FW that the configured modules should
+generate events that the driver is interested in, but it **does not** send the
+events to the driver until the enable message is sent to the FW. To do this
+the user can write a 1 (enable) or 0 (disable) to 'fwlog/enable'. An example
+is::
+
+  # echo 1 > /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/enable
+
+Retrieving FW log data
+~~~~~~~~~~~~~~~~~~~~~~
+The FW log data can be retrieved by reading from 'fwlog/data'. The user can
+write any value to 'fwlog/data' to clear the data. The data can only be cleared
+when FW logging is disabled. The FW log data is a binary file that is sent to
+Intel and used to help debug user issues.
+
+An example to read the data is::
+
+  # cat /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/data > fwlog.bin
+
+An example to clear the data is::
+
+  # echo 0 > /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/data
+
+Changing how often the log events are sent to the driver
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+The driver receives FW log data from the Admin Receive Queue (ARQ). The
+frequency that the FW sends the ARQ events can be configured by writing to
+'fwlog/nr_messages'. The range is 1-128 (1 means push every log message, 128
+means push only when the max AQ command buffer is full). The suggested value is
+10. The user can see what the value is configured to by reading
+'fwlog/nr_messages'. An example to set the value is::
+
+  # echo 50 > /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/nr_messages
+
+Configuring the amount of memory used to store FW log data
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+The driver stores FW log data within the driver. The default size of the memory
+used to store the data is 1MB. Some use cases may require more or less data so
+the user can change the amount of memory that is allocated for FW log data.
+To change the amount of memory then write to 'fwlog/log_size'. The value must be
+one of: 128K, 256K, 512K, 1M, or 2M. FW logging must be disabled to change the
+value. An example of changing the value is::
+
+  # echo 128K > /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/log_size
+
+
 Performance Optimization
 ========================
 Driver defaults are meant to fit a wide variety of workloads, but if further
diff --git a/Documentation/networking/device_drivers/ethernet/marvell/octeon_ep.rst b/Documentation/networking/device_drivers/ethernet/marvell/octeon_ep.rst
index cad96c8d1f97..c96d262b30be 100644
--- a/Documentation/networking/device_drivers/ethernet/marvell/octeon_ep.rst
+++ b/Documentation/networking/device_drivers/ethernet/marvell/octeon_ep.rst
@@ -22,8 +22,13 @@ EndPoint NIC.
 Supported Devices
 =================
 Currently, this driver support following devices:
+ * Network controller: Cavium, Inc. Device b100
  * Network controller: Cavium, Inc. Device b200
  * Network controller: Cavium, Inc. Device b400
+ * Network controller: Cavium, Inc. Device b900
+ * Network controller: Cavium, Inc. Device ba00
+ * Network controller: Cavium, Inc. Device bc00
+ * Network controller: Cavium, Inc. Device bd00
 
 Interface Control
 =================
diff --git a/Documentation/networking/device_drivers/wifi/index.rst b/Documentation/networking/device_drivers/wifi/index.rst
index bf91a87c7acf..fb394f5de4a9 100644
--- a/Documentation/networking/device_drivers/wifi/index.rst
+++ b/Documentation/networking/device_drivers/wifi/index.rst
@@ -10,7 +10,6 @@ Contents:
 
    intel/ipw2100
    intel/ipw2200
-   ray_cs
 
 .. only::  subproject and html
 
diff --git a/Documentation/networking/device_drivers/wifi/ray_cs.rst b/Documentation/networking/device_drivers/wifi/ray_cs.rst
deleted file mode 100644
index 9a46d1ae8f20..000000000000
--- a/Documentation/networking/device_drivers/wifi/ray_cs.rst
+++ /dev/null
@@ -1,165 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0
-
-.. include:: <isonum.txt>
-
-=========================
-Raylink wireless LAN card
-=========================
-
-September 21, 1999
-
-Copyright |copy| 1998  Corey Thomas (corey@world.std.com)
-
-This file is the documentation for the Raylink Wireless LAN card driver for
-Linux.  The Raylink wireless LAN card is a PCMCIA card which provides IEEE
-802.11 compatible wireless network connectivity at 1 and 2 megabits/second.
-See http://www.raytheon.com/micro/raylink/ for more information on the Raylink
-card.  This driver is in early development and does have bugs.  See the known
-bugs and limitations at the end of this document for more information.
-This driver also works with WebGear's Aviator 2.4 and Aviator Pro
-wireless LAN cards.
-
-As of kernel 2.3.18, the ray_cs driver is part of the Linux kernel
-source.  My web page for the development of ray_cs is at
-http://web.ralinktech.com/ralink/Home/Support/Linux.html
-and I can be emailed at corey@world.std.com
-
-The kernel driver is based on ray_cs-1.62.tgz
-
-The driver at my web page is intended to be used as an add on to
-David Hinds pcmcia package.  All the command line parameters are
-available when compiled as a module.  When built into the kernel, only
-the essid= string parameter is available via the kernel command line.
-This will change after the method of sorting out parameters for all
-the PCMCIA drivers is agreed upon.  If you must have a built in driver
-with nondefault parameters, they can be edited in
-/usr/src/linux/drivers/net/pcmcia/ray_cs.c.  Searching for module_param
-will find them all.
-
-Information on card services is available at:
-
-	http://pcmcia-cs.sourceforge.net/
-
-
-Card services user programs are still required for PCMCIA devices.
-pcmcia-cs-3.1.1 or greater is required for the kernel version of
-the driver.
-
-Currently, ray_cs is not part of David Hinds card services package,
-so the following magic is required.
-
-At the end of the /etc/pcmcia/config.opts file, add the line:
-source ./ray_cs.opts
-This will make card services read the ray_cs.opts file
-when starting.  Create the file /etc/pcmcia/ray_cs.opts containing the
-following::
-
-  #### start of /etc/pcmcia/ray_cs.opts ###################
-  # Configuration options for Raylink Wireless LAN PCMCIA card
-  device "ray_cs"
-    class "network" module "misc/ray_cs"
-
-  card "RayLink PC Card WLAN Adapter"
-    manfid 0x01a6, 0x0000
-    bind "ray_cs"
-
-  module "misc/ray_cs" opts ""
-  #### end of /etc/pcmcia/ray_cs.opts #####################
-
-
-To join an existing network with
-different parameters, contact the network administrator for the
-configuration information, and edit /etc/pcmcia/ray_cs.opts.
-Add the parameters below between the empty quotes.
-
-Parameters for ray_cs driver which may be specified in ray_cs.opts:
-
-=============== =============== =============================================
-bc              integer         0 = normal mode (802.11 timing),
-				1 = slow down inter frame timing to allow
-				operation with older breezecom access
-				points.
-
-beacon_period	integer         beacon period in Kilo-microseconds,
-
-				legal values = must be integer multiple
-				of hop dwell
-
-				default = 256
-
-country         integer         1 = USA (default),
-				2 = Europe,
-				3 = Japan,
-				4 = Korea,
-				5 = Spain,
-				6 = France,
-				7 = Israel,
-				8 = Australia
-
-essid		string		ESS ID - network name to join
-
-				string with maximum length of 32 chars
-				default value = "ADHOC_ESSID"
-
-hop_dwell	integer         hop dwell time in Kilo-microseconds
-
-				legal values = 16,32,64,128(default),256
-
-irq_mask	integer         linux standard 16 bit value 1bit/IRQ
-
-				lsb is IRQ 0, bit 1 is IRQ 1 etc.
-				Used to restrict choice of IRQ's to use.
-				Recommended method for controlling
-				interrupts is in /etc/pcmcia/config.opts
-
-net_type	integer		0 (default) = adhoc network,
-				1 = infrastructure
-
-phy_addr	string          string containing new MAC address in
-				hex, must start with x eg
-				x00008f123456
-
-psm		integer         0 = continuously active,
-				1 = power save mode (not useful yet)
-
-pc_debug	integer		(0-5) larger values for more verbose
-				logging.  Replaces ray_debug.
-
-ray_debug	integer		Replaced with pc_debug
-
-ray_mem_speed   integer         defaults to 500
-
-sniffer         integer         0 = not sniffer (default),
-				1 = sniffer which can be used to record all
-				network traffic using tcpdump or similar,
-				but no normal network use is allowed.
-
-translate	integer		0 = no translation (encapsulate frames),
-				1 = translation    (RFC1042/802.1)
-=============== =============== =============================================
-
-More on sniffer mode:
-
-tcpdump does not understand 802.11 headers, so it can't
-interpret the contents, but it can record to a file.  This is only
-useful for debugging 802.11 lowlevel protocols that are not visible to
-linux.  If you want to watch ftp xfers, or do similar things, you
-don't need to use sniffer mode.  Also, some packet types are never
-sent up by the card, so you will never see them (ack, rts, cts, probe
-etc.)  There is a simple program (showcap) included in the ray_cs
-package which parses the 802.11 headers.
-
-Known Problems and missing features
-
-	Does not work with non x86
-
-	Does not work with SMP
-
-	Support for defragmenting frames is not yet debugged, and in
-	fact is known to not work.  I have never encountered a net set
-	up to fragment, but still, it should be fixed.
-
-	The ioctl support is incomplete.  The hardware address cannot be set
-	using ifconfig yet.  If a different hardware address is needed, it may
-	be set using the phy_addr parameter in ray_cs.opts.  This requires
-	a card insertion to take effect.
diff --git a/Documentation/networking/devlink/devlink-reload.rst b/Documentation/networking/devlink/devlink-reload.rst
index 505d22da027d..2fb0269b2054 100644
--- a/Documentation/networking/devlink/devlink-reload.rst
+++ b/Documentation/networking/devlink/devlink-reload.rst
@@ -22,8 +22,17 @@ By default ``driver_reinit`` action is selected.
    * - ``driver-reinit``
      - Devlink driver entities re-initialization, including applying
        new values to devlink entities which are used during driver
-       load such as ``devlink-params`` in configuration mode
-       ``driverinit`` or ``devlink-resources``
+       load which are:
+
+       * ``devlink-params`` in configuration mode ``driverinit``
+       * ``devlink-resources``
+
+       Other devlink entities may stay over the re-initialization:
+
+       * ``devlink-health-reporter``
+       * ``devlink-region``
+
+       The rest of the devlink entities have to be removed and readded.
    * - ``fw_activate``
      - Firmware activate. Activates new firmware if such image is stored and
        pending activation. If no limitation specified this action may involve
diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst
index 2f60e34ab926..7f30ebd5debb 100644
--- a/Documentation/networking/devlink/ice.rst
+++ b/Documentation/networking/devlink/ice.rst
@@ -38,6 +38,10 @@ The ``ice`` driver reports the following versions
       - fixed
       - K65390-000
       - The Product Board Assembly (PBA) identifier of the board.
+    * - ``cgu.id``
+      - fixed
+      - 36
+      - The Clock Generation Unit (CGU) hardware revision identifier.
     * - ``fw.mgmt``
       - running
       - 2.1.7
@@ -104,6 +108,11 @@ The ``ice`` driver reports the following versions
       - running
       - 0xee16ced7
       - The first 4 bytes of the hash of the netlist module contents.
+    * - ``fw.cgu``
+      - running
+      - 8032.16973825.6021
+      - The version of Clock Generation Unit (CGU). Format:
+        <CGU type>.<configuration version>.<firmware version>.
 
 Flash Update
 ============
diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index 2540c70952ff..d583d9abf2f8 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -223,6 +223,9 @@ Userspace to kernel:
   ``ETHTOOL_MSG_PSE_SET``               set PSE parameters
   ``ETHTOOL_MSG_PSE_GET``               get PSE parameters
   ``ETHTOOL_MSG_RSS_GET``               get RSS settings
+  ``ETHTOOL_MSG_PLCA_GET_CFG``          get PLCA RS parameters
+  ``ETHTOOL_MSG_PLCA_SET_CFG``          set PLCA RS parameters
+  ``ETHTOOL_MSG_PLCA_GET_STATUS``       get PLCA RS status
   ``ETHTOOL_MSG_MM_GET``                get MAC merge layer state
   ``ETHTOOL_MSG_MM_SET``                set MAC merge layer parameters
   ===================================== =================================
@@ -267,6 +270,9 @@ Kernel to userspace:
   ``ETHTOOL_MSG_MODULE_GET_REPLY``         transceiver module parameters
   ``ETHTOOL_MSG_PSE_GET_REPLY``            PSE parameters
   ``ETHTOOL_MSG_RSS_GET_REPLY``            RSS settings
+  ``ETHTOOL_MSG_PLCA_GET_CFG_REPLY``       PLCA RS parameters
+  ``ETHTOOL_MSG_PLCA_GET_STATUS_REPLY``    PLCA RS status
+  ``ETHTOOL_MSG_PLCA_NTF``                 PLCA RS parameters
   ``ETHTOOL_MSG_MM_GET_REPLY``             MAC merge layer status
   ======================================== =================================
 
@@ -1768,12 +1774,16 @@ Kernel response contents:
   ``ETHTOOL_A_RSS_HFUNC``              u32     RSS hash func
   ``ETHTOOL_A_RSS_INDIR``              binary  Indir table bytes
   ``ETHTOOL_A_RSS_HKEY``               binary  Hash key bytes
+  ``ETHTOOL_A_RSS_INPUT_XFRM``         u32     RSS input data transformation
 =====================================  ======  ==========================
 
 ETHTOOL_A_RSS_HFUNC attribute is bitmap indicating the hash function
 being used. Current supported options are toeplitz, xor or crc32.
-ETHTOOL_A_RSS_INDIR attribute returns RSS indrection table where each byte
+ETHTOOL_A_RSS_INDIR attribute returns RSS indirection table where each byte
 indicates queue number.
+ETHTOOL_A_RSS_INPUT_XFRM attribute is a bitmap indicating the type of
+transformation applied to the input protocol fields before given to the RSS
+hfunc. Current supported option is symmetric-xor.
 
 PLCA_GET_CFG
 ============
diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index 683eb42309cc..69f3d6dcd9fd 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -55,6 +55,7 @@ Contents:
    filter
    generic-hdlc
    generic_netlink
+   netlink_spec/index
    gen_stats
    gtp
    ila
@@ -74,6 +75,7 @@ Contents:
    mptcp-sysctl
    multiqueue
    napi
+   net_cachelines/index
    netconsole
    netdev-features
    netdevices
@@ -123,6 +125,7 @@ Contents:
    xfrm_sync
    xfrm_sysctl
    xdp-rx-metadata
+   xsk-tx-metadata
 
 .. only::  subproject and html
 
diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 4dfe0d9a57bb..7afff42612e9 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -2511,7 +2511,7 @@ temp_valid_lft - INTEGER
 temp_prefered_lft - INTEGER
 	Preferred lifetime (in seconds) for temporary addresses. If
 	temp_prefered_lft is less than the minimum required lifetime (typically
-	5 seconds), the preferred lifetime is the minimum required. If
+	5 seconds), temporary addresses will not be created. If
 	temp_prefered_lft is greater than temp_valid_lft, the preferred lifetime
 	is temp_valid_lft.
 
diff --git a/Documentation/networking/net_cachelines/index.rst b/Documentation/networking/net_cachelines/index.rst
new file mode 100644
index 000000000000..2669e4cda086
--- /dev/null
+++ b/Documentation/networking/net_cachelines/index.rst
@@ -0,0 +1,16 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. Copyright (C) 2023 Google LLC
+
+===================================
+Common Networking Struct Cachelines
+===================================
+
+.. toctree::
+   :maxdepth: 1
+
+   inet_connection_sock
+   inet_sock
+   net_device
+   netns_ipv4_sysctl
+   snmp
+   tcp_sock
diff --git a/Documentation/networking/net_cachelines/inet_connection_sock.rst b/Documentation/networking/net_cachelines/inet_connection_sock.rst
new file mode 100644
index 000000000000..7a911dc95652
--- /dev/null
+++ b/Documentation/networking/net_cachelines/inet_connection_sock.rst
@@ -0,0 +1,50 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. Copyright (C) 2023 Google LLC
+
+=====================================================
+inet_connection_sock struct fast path usage breakdown
+=====================================================
+
+Type                                Name                   fastpath_tx_access  fastpath_rx_access  comment
+..struct                            ..inet_connection_sock                                         
+struct_inet_sock                    icsk_inet              read_mostly         read_mostly         tcp_init_buffer_space,tcp_init_transfer,tcp_finish_connect,tcp_connect,tcp_send_rcvq,tcp_send_syn_data
+struct_request_sock_queue           icsk_accept_queue      -                   -                   
+struct_inet_bind_bucket             icsk_bind_hash         read_mostly         -                   tcp_set_state
+struct_inet_bind2_bucket            icsk_bind2_hash        read_mostly         -                   tcp_set_state,inet_put_port
+unsigned_long                       icsk_timeout           read_mostly         -                   inet_csk_reset_xmit_timer,tcp_connect
+struct_timer_list                   icsk_retransmit_timer  read_mostly         -                   inet_csk_reset_xmit_timer,tcp_connect
+struct_timer_list                   icsk_delack_timer      read_mostly         -                   inet_csk_reset_xmit_timer,tcp_connect
+u32                                 icsk_rto               read_write          -                   tcp_cwnd_validate,tcp_schedule_loss_probe,tcp_connect_init,tcp_connect,tcp_write_xmit,tcp_push_one
+u32                                 icsk_rto_min           -                   -                   
+u32                                 icsk_delack_max        -                   -                   
+u32                                 icsk_pmtu_cookie       read_write          -                   tcp_sync_mss,tcp_current_mss,tcp_send_syn_data,tcp_connect_init,tcp_connect
+struct_tcp_congestion_ops           icsk_ca_ops            read_write          -                   tcp_cwnd_validate,tcp_tso_segs,tcp_ca_dst_init,tcp_connect_init,tcp_connect,tcp_write_xmit
+struct_inet_connection_sock_af_ops  icsk_af_ops            read_mostly         -                   tcp_finish_connect,tcp_send_syn_data,tcp_mtup_init,tcp_mtu_check_reprobe,tcp_mtu_probe,tcp_connect_init,tcp_connect,__tcp_transmit_skb
+struct_tcp_ulp_ops*                 icsk_ulp_ops           -                   -                   
+void*                               icsk_ulp_data          -                   -                   
+u8:5                                icsk_ca_state          read_write          -                   tcp_cwnd_application_limited,tcp_set_ca_state,tcp_enter_cwr,tcp_tso_should_defer,tcp_mtu_probe,tcp_schedule_loss_probe,tcp_write_xmit,__tcp_transmit_skb
+u8:1                                icsk_ca_initialized    read_write          -                   tcp_init_transfer,tcp_init_congestion_control,tcp_init_transfer,tcp_finish_connect,tcp_connect
+u8:1                                icsk_ca_setsockopt     -                   -                   
+u8:1                                icsk_ca_dst_locked     write_mostly        -                   tcp_ca_dst_init,tcp_connect_init,tcp_connect
+u8                                  icsk_retransmits       write_mostly        -                   tcp_connect_init,tcp_connect
+u8                                  icsk_pending           read_write          -                   inet_csk_reset_xmit_timer,tcp_connect,tcp_check_probe_timer,__tcp_push_pending_frames,tcp_rearm_rto,tcp_event_new_data_sent,tcp_event_new_data_sent
+u8                                  icsk_backoff           write_mostly        -                   tcp_write_queue_purge,tcp_connect_init
+u8                                  icsk_syn_retries       -                   -                   
+u8                                  icsk_probes_out        -                   -                   
+u16                                 icsk_ext_hdr_len       read_mostly         -                   __tcp_mtu_to_mss,tcp_mtu_to_rss,tcp_mtu_probe,tcp_write_xmit,tcp_mtu_to_mss,
+struct_icsk_ack_u8                  pending                read_write          read_write          inet_csk_ack_scheduled,__tcp_cleanup_rbuf,tcp_cleanup_rbuf,inet_csk_clear_xmit_timer,tcp_event_ack-sent,inet_csk_reset_xmit_timer
+struct_icsk_ack_u8                  quick                  read_write          write_mostly        tcp_dec_quickack_mode,tcp_event_ack_sent,__tcp_transmit_skb,__tcp_select_window,__tcp_cleanup_rbuf
+struct_icsk_ack_u8                  pingpong               -                   -                   
+struct_icsk_ack_u8                  retry                  write_mostly        read_write          inet_csk_clear_xmit_timer,tcp_rearm_rto,tcp_event_new_data_sent,tcp_write_xmit,__tcp_send_ack,tcp_send_ack,
+struct_icsk_ack_u8                  ato                    read_mostly         write_mostly        tcp_dec_quickack_mode,tcp_event_ack_sent,__tcp_transmit_skb,__tcp_send_ack,tcp_send_ack
+struct_icsk_ack_unsigned_long       timeout                read_write          read_write          inet_csk_reset_xmit_timer,tcp_connect
+struct_icsk_ack_u32                 lrcvtime               read_write          -                   tcp_finish_connect,tcp_connect,tcp_event_data_sent,__tcp_transmit_skb
+struct_icsk_ack_u16                 rcv_mss                write_mostly        read_mostly         __tcp_select_window,__tcp_cleanup_rbuf,tcp_initialize_rcv_mss,tcp_connect_init
+struct_icsk_mtup_int                search_high            read_write          -                   tcp_mtup_init,tcp_sync_mss,tcp_connect_init,tcp_mtu_check_reprobe,tcp_write_xmit
+struct_icsk_mtup_int                search_low             read_write          -                   tcp_mtu_probe,tcp_mtu_check_reprobe,tcp_write_xmit,tcp_sync_mss,tcp_connect_init,tcp_mtup_init
+struct_icsk_mtup_u32:31             probe_size             read_write          -                   tcp_mtup_init,tcp_connect_init,__tcp_transmit_skb
+struct_icsk_mtup_u32:1              enabled                read_write          -                   tcp_mtup_init,tcp_sync_mss,tcp_connect_init,tcp_mtu_probe,tcp_write_xmit
+struct_icsk_mtup_u32                probe_timestamp        read_write          -                   tcp_mtup_init,tcp_connect_init,tcp_mtu_check_reprobe,tcp_mtu_probe
+u32                                 icsk_probes_tstamp     -                   -                   
+u32                                 icsk_user_timeout      -                   -                   
+u64[104/sizeof(u64)]                icsk_ca_priv           -                   -                   
diff --git a/Documentation/networking/net_cachelines/inet_sock.rst b/Documentation/networking/net_cachelines/inet_sock.rst
new file mode 100644
index 000000000000..a2babd0d7954
--- /dev/null
+++ b/Documentation/networking/net_cachelines/inet_sock.rst
@@ -0,0 +1,44 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. Copyright (C) 2023 Google LLC
+
+=====================================================
+inet_connection_sock struct fast path usage breakdown
+=====================================================
+
+Type                    Name                  fastpath_tx_access  fastpath_rx_access  comment
+..struct                ..inet_sock                                                     
+struct_sock             sk                    read_mostly         read_mostly         tcp_init_buffer_space,tcp_init_transfer,tcp_finish_connect,tcp_connect,tcp_send_rcvq,tcp_send_syn_data
+struct_ipv6_pinfo*      pinet6                -                   -                   
+be16                    inet_sport            read_mostly         -                   __tcp_transmit_skb
+be32                    inet_daddr            read_mostly         -                   ip_select_ident_segs
+be32                    inet_rcv_saddr        -                   -                   
+be16                    inet_dport            read_mostly         -                   __tcp_transmit_skb
+u16                     inet_num              -                   -                   
+be32                    inet_saddr            -                   -                   
+s16                     uc_ttl                read_mostly         -                   __ip_queue_xmit/ip_select_ttl
+u16                     cmsg_flags            -                   -                   
+struct_ip_options_rcu*  inet_opt              read_mostly         -                   __ip_queue_xmit
+u16                     inet_id               read_mostly         -                   ip_select_ident_segs
+u8                      tos                   read_mostly         -                   ip_queue_xmit
+u8                      min_ttl               -                   -                   
+u8                      mc_ttl                -                   -                   
+u8                      pmtudisc              -                   -                   
+u8:1                    recverr               -                   -                   
+u8:1                    is_icsk               -                   -                   
+u8:1                    freebind              -                   -                   
+u8:1                    hdrincl               -                   -                   
+u8:1                    mc_loop               -                   -                   
+u8:1                    transparent           -                   -                   
+u8:1                    mc_all                -                   -                   
+u8:1                    nodefrag              -                   -                   
+u8:1                    bind_address_no_port  -                   -                   
+u8:1                    recverr_rfc4884       -                   -                   
+u8:1                    defer_connect         read_mostly         -                   tcp_sendmsg_fastopen
+u8                      rcv_tos               -                   -                   
+u8                      convert_csum          -                   -                   
+int                     uc_index              -                   -                   
+int                     mc_index              -                   -                   
+be32                    mc_addr               -                   -                   
+struct_ip_mc_socklist*  mc_list               -                   -                   
+struct_inet_cork_full   cork                  read_mostly         -                   __tcp_transmit_skb
+struct                  local_port_range      -                   -                   
diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
new file mode 100644
index 000000000000..e75a53593bb9
--- /dev/null
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -0,0 +1,178 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. Copyright (C) 2023 Google LLC
+
+===========================================
+net_device struct fast path usage breakdown
+===========================================
+
+Type                                Name                    fastpath_tx_access  fastpath_rx_access  Comments
+..struct                            ..net_device                                                    
+char                                name[16]                -                   -                   
+struct_netdev_name_node*            name_node                                                       
+struct_dev_ifalias*                 ifalias                                                         
+unsigned_long                       mem_end                                                         
+unsigned_long                       mem_start                                                       
+unsigned_long                       base_addr                                                       
+unsigned_long                       state                                                           
+struct_list_head                    dev_list                                                        
+struct_list_head                    napi_list                                                       
+struct_list_head                    unreg_list                                                      
+struct_list_head                    close_list                                                      
+struct_list_head                    ptype_all               read_mostly         -                   dev_nit_active(tx)
+struct_list_head                    ptype_specific                              read_mostly         deliver_ptype_list_skb/__netif_receive_skb_core(rx)
+struct                              adj_list                                                        
+unsigned_int                        flags                   read_mostly         read_mostly         __dev_queue_xmit,__dev_xmit_skb,ip6_output,__ip6_finish_output(tx);ip6_rcv_core(rx)
+xdp_features_t                      xdp_features                                                    
+unsigned_long_long                  priv_flags              read_mostly         -                   __dev_queue_xmit(tx)
+struct_net_device_ops*              netdev_ops              read_mostly         -                   netdev_core_pick_tx,netdev_start_xmit(tx)
+struct_xdp_metadata_ops*            xdp_metadata_ops                                                
+int                                 ifindex                 -                   read_mostly         ip6_rcv_core
+unsigned_short                      gflags                                                          
+unsigned_short                      hard_header_len         read_mostly         read_mostly         ip6_xmit(tx);gro_list_prepare(rx)
+unsigned_int                        mtu                     read_mostly         -                   ip_finish_output2
+unsigned_short                      needed_headroom         read_mostly         -                   LL_RESERVED_SPACE/ip_finish_output2
+unsigned_short                      needed_tailroom                                                 
+netdev_features_t                   features                read_mostly         read_mostly         HARD_TX_LOCK,netif_skb_features,sk_setup_caps(tx);netif_elide_gro(rx)
+netdev_features_t                   hw_features                                                     
+netdev_features_t                   wanted_features                                                 
+netdev_features_t                   vlan_features                                                   
+netdev_features_t                   hw_enc_features         -                   -                   netif_skb_features
+netdev_features_t                   mpls_features                                                   
+netdev_features_t                   gso_partial_features    read_mostly                             gso_features_check
+unsigned_int                        min_mtu                                                         
+unsigned_int                        max_mtu                                                         
+unsigned_short                      type                                                            
+unsigned_char                       min_header_len                                                  
+unsigned_char                       name_assign_type                                                
+int                                 group                                                           
+struct_net_device_stats             stats                                                           
+struct_net_device_core_stats*       core_stats                                                      
+atomic_t                            carrier_up_count                                                
+atomic_t                            carrier_down_count                                              
+struct_iw_handler_def*              wireless_handlers                                               
+struct_iw_public_data*              wireless_data                                                   
+struct_ethtool_ops*                 ethtool_ops                                                     
+struct_l3mdev_ops*                  l3mdev_ops                                                      
+struct_ndisc_ops*                   ndisc_ops                                                       
+struct_xfrmdev_ops*                 xfrmdev_ops                                                     
+struct_tlsdev_ops*                  tlsdev_ops                                                      
+struct_header_ops*                  header_ops              read_mostly         -                   ip_finish_output2,ip6_finish_output2(tx)
+unsigned_char                       operstate                                                       
+unsigned_char                       link_mode                                                       
+unsigned_char                       if_port                                                         
+unsigned_char                       dma                                                             
+unsigned_char                       perm_addr[32]                                                   
+unsigned_char                       addr_assign_type                                                
+unsigned_char                       addr_len                                                        
+unsigned_char                       upper_level                                                     
+unsigned_char                       lower_level                                                     
+unsigned_short                      neigh_priv_len                                                  
+unsigned_short                      padded                                                          
+unsigned_short                      dev_id                                                          
+unsigned_short                      dev_port                                                        
+spinlock_t                          addr_list_lock                                                  
+int                                 irq                                                             
+struct_netdev_hw_addr_list          uc                                                              
+struct_netdev_hw_addr_list          mc                                                              
+struct_netdev_hw_addr_list          dev_addrs                                                       
+struct_kset*                        queues_kset                                                     
+struct_list_head                    unlink_list                                                     
+unsigned_int                        promiscuity                                                     
+unsigned_int                        allmulti                                                        
+bool                                uc_promisc                                                      
+unsigned_char                       nested_level                                                    
+struct_in_device*                   ip_ptr                  read_mostly         read_mostly         __in_dev_get
+struct_inet6_dev*                   ip6_ptr                 read_mostly         read_mostly         __in6_dev_get
+struct_vlan_info*                   vlan_info                                                       
+struct_dsa_port*                    dsa_ptr                                                         
+struct_tipc_bearer*                 tipc_ptr                                                        
+void*                               atalk_ptr                                                       
+void*                               ax25_ptr                                                        
+struct_wireless_dev*                ieee80211_ptr                                                   
+struct_wpan_dev*                    ieee802154_ptr                                                  
+struct_mpls_dev*                    mpls_ptr                                                        
+struct_mctp_dev*                    mctp_ptr                                                        
+unsigned_char*                      dev_addr                                                        
+struct_netdev_queue*                _rx                     read_mostly         -                   netdev_get_rx_queue(rx)
+unsigned_int                        num_rx_queues                                                   
+unsigned_int                        real_num_rx_queues      -                   read_mostly         get_rps_cpu
+struct_bpf_prog*                    xdp_prog                -                   read_mostly         netif_elide_gro()
+unsigned_long                       gro_flush_timeout       -                   read_mostly         napi_complete_done
+int                                 napi_defer_hard_irqs    -                   read_mostly         napi_complete_done
+unsigned_int                        gro_max_size            -                   read_mostly         skb_gro_receive
+unsigned_int                        gro_ipv4_max_size       -                   read_mostly         skb_gro_receive
+rx_handler_func_t*                  rx_handler              read_mostly         -                   __netif_receive_skb_core
+void*                               rx_handler_data         read_mostly         -                   
+struct_netdev_queue*                ingress_queue           read_mostly         -                   
+struct_bpf_mprog_entry              tcx_ingress             -                   read_mostly         sch_handle_ingress
+struct_nf_hook_entries*             nf_hooks_ingress                                                
+unsigned_char                       broadcast[32]                                                   
+struct_cpu_rmap*                    rx_cpu_rmap                                                     
+struct_hlist_node                   index_hlist                                                     
+struct_netdev_queue*                _tx                     read_mostly         -                   netdev_get_tx_queue(tx)
+unsigned_int                        num_tx_queues           -                   -                   
+unsigned_int                        real_num_tx_queues      read_mostly         -                   skb_tx_hash,netdev_core_pick_tx(tx)
+unsigned_int                        tx_queue_len                                                    
+spinlock_t                          tx_global_lock                                                  
+struct_xdp_dev_bulk_queue__percpu*  xdp_bulkq                                                       
+struct_xps_dev_maps*                xps_maps[2]             read_mostly         -                   __netif_set_xps_queue
+struct_bpf_mprog_entry              tcx_egress              read_mostly         -                   sch_handle_egress
+struct_nf_hook_entries*             nf_hooks_egress         read_mostly         -                   
+struct_hlist_head                   qdisc_hash[16]                                                  
+struct_timer_list                   watchdog_timer                                                  
+int                                 watchdog_timeo                                                  
+u32                                 proto_down_reason                                               
+struct_list_head                    todo_list                                                       
+int__percpu*                        pcpu_refcnt                                                     
+refcount_t                          dev_refcnt                                                      
+struct_ref_tracker_dir              refcnt_tracker                                                  
+struct_list_head                    link_watch_list                                                 
+enum:8                              reg_state                                                       
+bool                                dismantle                                                       
+enum:16                             rtnl_link_state                                                 
+bool                                needs_free_netdev                                               
+void*priv_destructor                struct_net_device                                               
+struct_netpoll_info*                npinfo                  -                   read_mostly         napi_poll/napi_poll_lock
+possible_net_t                      nd_net                  -                   read_mostly         (dev_net)napi_busy_loop,tcp_v(4/6)_rcv,ip(v6)_rcv,ip(6)_input,ip(6)_input_finish
+void*                               ml_priv                                                         
+enum_netdev_ml_priv_type            ml_priv_type                                                    
+struct_pcpu_lstats__percpu*         lstats                                                          
+struct_pcpu_sw_netstats__percpu*    tstats                                                          
+struct_pcpu_dstats__percpu*         dstats                                                          
+struct_garp_port*                   garp_port                                                       
+struct_mrp_port*                    mrp_port                                                        
+struct_dm_hw_stat_delta*            dm_private                                                      
+struct_device                       dev                     -                   -                   
+struct_attribute_group*             sysfs_groups[4]                                                 
+struct_attribute_group*             sysfs_rx_queue_group                                            
+struct_rtnl_link_ops*               rtnl_link_ops                                                   
+unsigned_int                        gso_max_size            read_mostly         -                   sk_dst_gso_max_size
+unsigned_int                        tso_max_size                                                    
+u16                                 gso_max_segs            read_mostly         -                   gso_max_segs
+u16                                 tso_max_segs                                                    
+unsigned_int                        gso_ipv4_max_size       read_mostly         -                   sk_dst_gso_max_size
+struct_dcbnl_rtnl_ops*              dcbnl_ops                                                       
+s16                                 num_tc                  read_mostly         -                   skb_tx_hash
+struct_netdev_tc_txq                tc_to_txq[16]           read_mostly         -                   skb_tx_hash
+u8                                  prio_tc_map[16]                                                 
+unsigned_int                        fcoe_ddp_xid                                                    
+struct_netprio_map*                 priomap                                                         
+struct_phy_device*                  phydev                                                          
+struct_sfp_bus*                     sfp_bus                                                         
+struct_lock_class_key*              qdisc_tx_busylock                                               
+bool                                proto_down                                                      
+unsigned:1                          wol_enabled                                                     
+unsigned:1                          threaded                -                   -                   napi_poll(napi_enable,dev_set_threaded)
+struct_list_head                    net_notifier_list                                               
+struct_macsec_ops*                  macsec_ops                                                      
+struct_udp_tunnel_nic_info*         udp_tunnel_nic_info                                             
+struct_udp_tunnel_nic*              udp_tunnel_nic                                                  
+unsigned_int                        xdp_zc_max_segs                                                 
+struct_bpf_xdp_entity               xdp_state[3]                                                    
+u8                                  dev_addr_shadow[32]                                             
+netdevice_tracker                   linkwatch_dev_tracker                                           
+netdevice_tracker                   watchdog_dev_tracker                                            
+netdevice_tracker                   dev_registered_tracker                                          
+struct_rtnl_hw_stats64*             offload_xstats_l3                                               
+struct_devlink_port*                devlink_port                                                    
+struct_dpll_pin*                    dpll_pin                                                        
diff --git a/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst b/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst
new file mode 100644
index 000000000000..9b87089a84c6
--- /dev/null
+++ b/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst
@@ -0,0 +1,158 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. Copyright (C) 2023 Google LLC
+
+===========================================
+netns_ipv4 struct fast path usage breakdown
+===========================================
+
+Type                            Name                                         fastpath_tx_access  fastpath_rx_access  comment
+..struct                        ..netns_ipv4                                                                         
+struct_inet_timewait_death_row  tcp_death_row                                                                        
+struct_udp_table*               udp_table                                                                            
+struct_ctl_table_header*        forw_hdr                                                                             
+struct_ctl_table_header*        frags_hdr                                                                            
+struct_ctl_table_header*        ipv4_hdr                                                                             
+struct_ctl_table_header*        route_hdr                                                                            
+struct_ctl_table_header*        xfrm4_hdr                                                                            
+struct_ipv4_devconf*            devconf_all                                                                          
+struct_ipv4_devconf*            devconf_dflt                                                                         
+struct_ip_ra_chain              ra_chain                                                                             
+struct_mutex                    ra_mutex                                                                             
+struct_fib_rules_ops*           rules_ops                                                                            
+struct_fib_table                fib_main                                                                             
+struct_fib_table                fib_default                                                                          
+unsigned_int                    fib_rules_require_fldissect                                                          
+bool                            fib_has_custom_rules                                                                 
+bool                            fib_has_custom_local_routes                                                          
+bool                            fib_offload_disabled                                                                 
+atomic_t                        fib_num_tclassid_users                                                               
+struct_hlist_head*              fib_table_hash                                                                       
+struct_sock*                    fibnl                                                                                
+struct_sock*                    mc_autojoin_sk                                                                       
+struct_inet_peer_base*          peers                                                                                
+struct_fqdir*                   fqdir                                                                                
+u8                              sysctl_icmp_echo_ignore_all                                                          
+u8                              sysctl_icmp_echo_enable_probe                                                        
+u8                              sysctl_icmp_echo_ignore_broadcasts                                                   
+u8                              sysctl_icmp_ignore_bogus_error_responses                                             
+u8                              sysctl_icmp_errors_use_inbound_ifaddr                                                
+int                             sysctl_icmp_ratelimit                                                                
+int                             sysctl_icmp_ratemask                                                                 
+u32                             ip_rt_min_pmtu                               -                   -                   
+int                             ip_rt_mtu_expires                            -                   -                   
+int                             ip_rt_min_advmss                             -                   -                   
+struct_local_ports              ip_local_ports                               -                   -                   
+u8                              sysctl_tcp_ecn                               -                   -                   
+u8                              sysctl_tcp_ecn_fallback                      -                   -                   
+u8                              sysctl_ip_default_ttl                        -                   -                   ip4_dst_hoplimit/ip_select_ttl
+u8                              sysctl_ip_no_pmtu_disc                       -                   -                   
+u8                              sysctl_ip_fwd_use_pmtu                       read_mostly         -                   ip_dst_mtu_maybe_forward/ip_skb_dst_mtu
+u8                              sysctl_ip_fwd_update_priority                -                   -                   ip_forward
+u8                              sysctl_ip_nonlocal_bind                      -                   -                   
+u8                              sysctl_ip_autobind_reuse                     -                   -                   
+u8                              sysctl_ip_dynaddr                            -                   -                   
+u8                              sysctl_ip_early_demux                        -                   read_mostly         ip(6)_rcv_finish_core
+u8                              sysctl_raw_l3mdev_accept                     -                   -                   
+u8                              sysctl_tcp_early_demux                       -                   read_mostly         ip(6)_rcv_finish_core
+u8                              sysctl_udp_early_demux                                                               
+u8                              sysctl_nexthop_compat_mode                   -                   -                   
+u8                              sysctl_fwmark_reflect                        -                   -                   
+u8                              sysctl_tcp_fwmark_accept                     -                   -                   
+u8                              sysctl_tcp_l3mdev_accept                     -                   -                   
+u8                              sysctl_tcp_mtu_probing                       -                   -                   
+int                             sysctl_tcp_mtu_probe_floor                   -                   -                   
+int                             sysctl_tcp_base_mss                          -                   -                   
+int                             sysctl_tcp_min_snd_mss                       read_mostly         -                   __tcp_mtu_to_mss(tcp_write_xmit)
+int                             sysctl_tcp_probe_threshold                   -                   -                   tcp_mtu_probe(tcp_write_xmit)
+u32                             sysctl_tcp_probe_interval                    -                   -                   tcp_mtu_check_reprobe(tcp_write_xmit)
+int                             sysctl_tcp_keepalive_time                    -                   -                   
+int                             sysctl_tcp_keepalive_intvl                   -                   -                   
+u8                              sysctl_tcp_keepalive_probes                  -                   -                   
+u8                              sysctl_tcp_syn_retries                       -                   -                   
+u8                              sysctl_tcp_synack_retries                    -                   -                   
+u8                              sysctl_tcp_syncookies                        -                   -                   generated_on_syn
+u8                              sysctl_tcp_migrate_req                       -                   -                   reuseport
+u8                              sysctl_tcp_comp_sack_nr                      -                   -                   __tcp_ack_snd_check
+int                             sysctl_tcp_reordering                        -                   read_mostly         tcp_may_raise_cwnd/tcp_cong_control
+u8                              sysctl_tcp_retries1                          -                   -                   
+u8                              sysctl_tcp_retries2                          -                   -                   
+u8                              sysctl_tcp_orphan_retries                    -                   -                   
+u8                              sysctl_tcp_tw_reuse                          -                   -                   timewait_sock_ops
+int                             sysctl_tcp_fin_timeout                       -                   -                   TCP_LAST_ACK/tcp_rcv_state_process
+unsigned_int                    sysctl_tcp_notsent_lowat                     read_mostly         -                   tcp_notsent_lowat/tcp_stream_memory_free
+u8                              sysctl_tcp_sack                              -                   -                   tcp_syn_options
+u8                              sysctl_tcp_window_scaling                    -                   -                   tcp_syn_options,tcp_parse_options
+u8                              sysctl_tcp_timestamps                                                                
+u8                              sysctl_tcp_early_retrans                     read_mostly         -                   tcp_schedule_loss_probe(tcp_write_xmit)
+u8                              sysctl_tcp_recovery                          -                   -                   tcp_fastretrans_alert
+u8                              sysctl_tcp_thin_linear_timeouts              -                   -                   tcp_retrans_timer(on_thin_streams)
+u8                              sysctl_tcp_slow_start_after_idle             -                   -                   unlikely(tcp_cwnd_validate-network-not-starved)
+u8                              sysctl_tcp_retrans_collapse                  -                   -                   
+u8                              sysctl_tcp_stdurg                            -                   -                   unlikely(tcp_check_urg)
+u8                              sysctl_tcp_rfc1337                           -                   -                   
+u8                              sysctl_tcp_abort_on_overflow                 -                   -                   
+u8                              sysctl_tcp_fack                              -                   -                   
+int                             sysctl_tcp_max_reordering                    -                   -                   tcp_check_sack_reordering
+int                             sysctl_tcp_adv_win_scale                     -                   -                   tcp_init_buffer_space
+u8                              sysctl_tcp_dsack                             -                   -                   partial_packet_or_retrans_in_tcp_data_queue
+u8                              sysctl_tcp_app_win                           -                   -                   tcp_win_from_space
+u8                              sysctl_tcp_frto                              -                   -                   tcp_enter_loss
+u8                              sysctl_tcp_nometrics_save                    -                   -                   TCP_LAST_ACK/tcp_update_metrics
+u8                              sysctl_tcp_no_ssthresh_metrics_save          -                   -                   TCP_LAST_ACK/tcp_(update/init)_metrics
+u8                              sysctl_tcp_moderate_rcvbuf                   read_mostly         read_mostly         tcp_tso_should_defer(tx);tcp_rcv_space_adjust(rx)
+u8                              sysctl_tcp_tso_win_divisor                   read_mostly         -                   tcp_tso_should_defer(tcp_write_xmit)
+u8                              sysctl_tcp_workaround_signed_windows         -                   -                   tcp_select_window
+int                             sysctl_tcp_limit_output_bytes                read_mostly         -                   tcp_small_queue_check(tcp_write_xmit)
+int                             sysctl_tcp_challenge_ack_limit               -                   -                   
+int                             sysctl_tcp_min_rtt_wlen                      read_mostly         -                   tcp_ack_update_rtt
+u8                              sysctl_tcp_min_tso_segs                      -                   -                   unlikely(icsk_ca_ops-written)
+u8                              sysctl_tcp_tso_rtt_log                       read_mostly         -                   tcp_tso_autosize
+u8                              sysctl_tcp_autocorking                       read_mostly         -                   tcp_push/tcp_should_autocork
+u8                              sysctl_tcp_reflect_tos                       -                   -                   tcp_v(4/6)_send_synack
+int                             sysctl_tcp_invalid_ratelimit                 -                   -                   
+int                             sysctl_tcp_pacing_ss_ratio                   -                   -                   default_cong_cont(tcp_update_pacing_rate)
+int                             sysctl_tcp_pacing_ca_ratio                   -                   -                   default_cong_cont(tcp_update_pacing_rate)
+int                             sysctl_tcp_wmem[3]                           read_mostly         -                   tcp_wmem_schedule(sendmsg/sendpage)
+int                             sysctl_tcp_rmem[3]                           -                   read_mostly         __tcp_grow_window(tx),tcp_rcv_space_adjust(rx)
+unsigned_int                    sysctl_tcp_child_ehash_entries                                                       
+unsigned_long                   sysctl_tcp_comp_sack_delay_ns                -                   -                   __tcp_ack_snd_check
+unsigned_long                   sysctl_tcp_comp_sack_slack_ns                -                   -                   __tcp_ack_snd_check
+int                             sysctl_max_syn_backlog                       -                   -                   
+int                             sysctl_tcp_fastopen                          -                   -                   
+struct_tcp_congestion_ops       tcp_congestion_control                       -                   -                   init_cc
+struct_tcp_fastopen_context     tcp_fastopen_ctx                             -                   -                   
+unsigned_int                    sysctl_tcp_fastopen_blackhole_timeout        -                   -                   
+atomic_t                        tfo_active_disable_times                     -                   -                   
+unsigned_long                   tfo_active_disable_stamp                     -                   -                   
+u32                             tcp_challenge_timestamp                      -                   -                   
+u32                             tcp_challenge_count                          -                   -                   
+u8                              sysctl_tcp_plb_enabled                       -                   -                   
+u8                              sysctl_tcp_plb_idle_rehash_rounds            -                   -                   
+u8                              sysctl_tcp_plb_rehash_rounds                 -                   -                   
+u8                              sysctl_tcp_plb_suspend_rto_sec               -                   -                   
+int                             sysctl_tcp_plb_cong_thresh                   -                   -                   
+int                             sysctl_udp_wmem_min                                                                  
+int                             sysctl_udp_rmem_min                                                                  
+u8                              sysctl_fib_notify_on_flag_change                                                     
+u8                              sysctl_udp_l3mdev_accept                                                             
+u8                              sysctl_igmp_llm_reports                                                              
+int                             sysctl_igmp_max_memberships                                                          
+int                             sysctl_igmp_max_msf                                                                  
+int                             sysctl_igmp_qrv                                                                      
+struct_ping_group_range         ping_group_range                                                                     
+atomic_t                        dev_addr_genid                                                                       
+unsigned_int                    sysctl_udp_child_hash_entries                                                        
+unsigned_long*                  sysctl_local_reserved_ports                                                          
+int                             sysctl_ip_prot_sock                                                                  
+struct_mr_table*                mrt                                                                                  
+struct_list_head                mr_tables                                                                            
+struct_fib_rules_ops*           mr_rules_ops                                                                         
+u32                             sysctl_fib_multipath_hash_fields                                                     
+u8                              sysctl_fib_multipath_use_neigh                                                       
+u8                              sysctl_fib_multipath_hash_policy                                                     
+struct_fib_notifier_ops*        notifier_ops                                                                         
+unsigned_int                    fib_seq                                                                              
+struct_fib_notifier_ops*        ipmr_notifier_ops                                                                    
+unsigned_int                    ipmr_seq                                                                             
+atomic_t                        rt_genid                                                                             
+siphash_key_t                   ip_id_key                                                                                      
diff --git a/Documentation/networking/net_cachelines/snmp.rst b/Documentation/networking/net_cachelines/snmp.rst
new file mode 100644
index 000000000000..6a071538566c
--- /dev/null
+++ b/Documentation/networking/net_cachelines/snmp.rst
@@ -0,0 +1,135 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. Copyright (C) 2023 Google LLC
+
+===========================================
+netns_ipv4 enum fast path usage breakdown
+===========================================
+
+Type           Name                                  fastpath_tx_access  fastpath_rx_access  comment
+..enum                                                                                       
+unsigned_long  LINUX_MIB_TCPKEEPALIVE                write_mostly        -                   tcp_keepalive_timer
+unsigned_long  LINUX_MIB_DELAYEDACKS                 write_mostly        -                   tcp_delack_timer_handler,tcp_delack_timer
+unsigned_long  LINUX_MIB_DELAYEDACKLOCKED            write_mostly        -                   tcp_delack_timer_handler,tcp_delack_timer
+unsigned_long  LINUX_MIB_TCPAUTOCORKING              write_mostly        -                   tcp_push,tcp_sendmsg_locked
+unsigned_long  LINUX_MIB_TCPFROMZEROWINDOWADV        write_mostly        -                   tcp_select_window,tcp_transmit-skb
+unsigned_long  LINUX_MIB_TCPTOZEROWINDOWADV          write_mostly        -                   tcp_select_window,tcp_transmit-skb
+unsigned_long  LINUX_MIB_TCPWANTZEROWINDOWADV        write_mostly        -                   tcp_select_window,tcp_transmit-skb
+unsigned_long  LINUX_MIB_TCPORIGDATASENT             write_mostly        -                   tcp_write_xmit
+unsigned_long  LINUX_MIB_TCPHPHITS                   -                   write_mostly        tcp_rcv_established,tcp_v4_do_rcv,tcp_v6_do_rcv
+unsigned_long  LINUX_MIB_TCPRCVCOALESCE              -                   write_mostly        tcp_try_coalesce,tcp_queue_rcv,tcp_rcv_established
+unsigned_long  LINUX_MIB_TCPPUREACKS                 -                   write_mostly        tcp_ack,tcp_rcv_established
+unsigned_long  LINUX_MIB_TCPHPACKS                   -                   write_mostly        tcp_ack,tcp_rcv_established
+unsigned_long  LINUX_MIB_TCPDELIVERED                -                   write_mostly        tcp_newly_delivered,tcp_ack,tcp_rcv_established
+unsigned_long  LINUX_MIB_SYNCOOKIESSENT                                                      
+unsigned_long  LINUX_MIB_SYNCOOKIESRECV                                                      
+unsigned_long  LINUX_MIB_SYNCOOKIESFAILED                                                    
+unsigned_long  LINUX_MIB_EMBRYONICRSTS                                                       
+unsigned_long  LINUX_MIB_PRUNECALLED                                                         
+unsigned_long  LINUX_MIB_RCVPRUNED                                                           
+unsigned_long  LINUX_MIB_OFOPRUNED                                                           
+unsigned_long  LINUX_MIB_OUTOFWINDOWICMPS                                                    
+unsigned_long  LINUX_MIB_LOCKDROPPEDICMPS                                                    
+unsigned_long  LINUX_MIB_ARPFILTER                                                           
+unsigned_long  LINUX_MIB_TIMEWAITED                                                          
+unsigned_long  LINUX_MIB_TIMEWAITRECYCLED                                                    
+unsigned_long  LINUX_MIB_TIMEWAITKILLED                                                      
+unsigned_long  LINUX_MIB_PAWSACTIVEREJECTED                                                  
+unsigned_long  LINUX_MIB_PAWSESTABREJECTED                                                   
+unsigned_long  LINUX_MIB_DELAYEDACKLOST                                                      
+unsigned_long  LINUX_MIB_LISTENOVERFLOWS                                                     
+unsigned_long  LINUX_MIB_LISTENDROPS                                                         
+unsigned_long  LINUX_MIB_TCPRENORECOVERY                                                     
+unsigned_long  LINUX_MIB_TCPSACKRECOVERY                                                     
+unsigned_long  LINUX_MIB_TCPSACKRENEGING                                                     
+unsigned_long  LINUX_MIB_TCPSACKREORDER                                                      
+unsigned_long  LINUX_MIB_TCPRENOREORDER                                                      
+unsigned_long  LINUX_MIB_TCPTSREORDER                                                        
+unsigned_long  LINUX_MIB_TCPFULLUNDO                                                         
+unsigned_long  LINUX_MIB_TCPPARTIALUNDO                                                      
+unsigned_long  LINUX_MIB_TCPDSACKUNDO                                                        
+unsigned_long  LINUX_MIB_TCPLOSSUNDO                                                         
+unsigned_long  LINUX_MIB_TCPLOSTRETRANSMIT                                                   
+unsigned_long  LINUX_MIB_TCPRENOFAILURES                                                     
+unsigned_long  LINUX_MIB_TCPSACKFAILURES                                                     
+unsigned_long  LINUX_MIB_TCPLOSSFAILURES                                                     
+unsigned_long  LINUX_MIB_TCPFASTRETRANS                                                      
+unsigned_long  LINUX_MIB_TCPSLOWSTARTRETRANS                                                 
+unsigned_long  LINUX_MIB_TCPTIMEOUTS                                                         
+unsigned_long  LINUX_MIB_TCPLOSSPROBES                                                       
+unsigned_long  LINUX_MIB_TCPLOSSPROBERECOVERY                                                
+unsigned_long  LINUX_MIB_TCPRENORECOVERYFAIL                                                 
+unsigned_long  LINUX_MIB_TCPSACKRECOVERYFAIL                                                 
+unsigned_long  LINUX_MIB_TCPRCVCOLLAPSED                                                     
+unsigned_long  LINUX_MIB_TCPDSACKOLDSENT                                                     
+unsigned_long  LINUX_MIB_TCPDSACKOFOSENT                                                     
+unsigned_long  LINUX_MIB_TCPDSACKRECV                                                        
+unsigned_long  LINUX_MIB_TCPDSACKOFORECV                                                     
+unsigned_long  LINUX_MIB_TCPABORTONDATA                                                      
+unsigned_long  LINUX_MIB_TCPABORTONCLOSE                                                     
+unsigned_long  LINUX_MIB_TCPABORTONMEMORY                                                    
+unsigned_long  LINUX_MIB_TCPABORTONTIMEOUT                                                   
+unsigned_long  LINUX_MIB_TCPABORTONLINGER                                                    
+unsigned_long  LINUX_MIB_TCPABORTFAILED                                                      
+unsigned_long  LINUX_MIB_TCPMEMORYPRESSURES                                                  
+unsigned_long  LINUX_MIB_TCPMEMORYPRESSURESCHRONO                                            
+unsigned_long  LINUX_MIB_TCPSACKDISCARD                                                      
+unsigned_long  LINUX_MIB_TCPDSACKIGNOREDOLD                                                  
+unsigned_long  LINUX_MIB_TCPDSACKIGNOREDNOUNDO                                               
+unsigned_long  LINUX_MIB_TCPSPURIOUSRTOS                                                     
+unsigned_long  LINUX_MIB_TCPMD5NOTFOUND                                                      
+unsigned_long  LINUX_MIB_TCPMD5UNEXPECTED                                                    
+unsigned_long  LINUX_MIB_TCPMD5FAILURE                                                       
+unsigned_long  LINUX_MIB_SACKSHIFTED                                                         
+unsigned_long  LINUX_MIB_SACKMERGED                                                          
+unsigned_long  LINUX_MIB_SACKSHIFTFALLBACK                                                   
+unsigned_long  LINUX_MIB_TCPBACKLOGDROP                                                      
+unsigned_long  LINUX_MIB_PFMEMALLOCDROP                                                      
+unsigned_long  LINUX_MIB_TCPMINTTLDROP                                                       
+unsigned_long  LINUX_MIB_TCPDEFERACCEPTDROP                                                  
+unsigned_long  LINUX_MIB_IPRPFILTER                                                          
+unsigned_long  LINUX_MIB_TCPTIMEWAITOVERFLOW                                                 
+unsigned_long  LINUX_MIB_TCPREQQFULLDOCOOKIES                                                
+unsigned_long  LINUX_MIB_TCPREQQFULLDROP                                                     
+unsigned_long  LINUX_MIB_TCPRETRANSFAIL                                                      
+unsigned_long  LINUX_MIB_TCPBACKLOGCOALESCE                                                  
+unsigned_long  LINUX_MIB_TCPOFOQUEUE                                                         
+unsigned_long  LINUX_MIB_TCPOFODROP                                                          
+unsigned_long  LINUX_MIB_TCPOFOMERGE                                                         
+unsigned_long  LINUX_MIB_TCPCHALLENGEACK                                                     
+unsigned_long  LINUX_MIB_TCPSYNCHALLENGE                                                     
+unsigned_long  LINUX_MIB_TCPFASTOPENACTIVE                                                   
+unsigned_long  LINUX_MIB_TCPFASTOPENACTIVEFAIL                                               
+unsigned_long  LINUX_MIB_TCPFASTOPENPASSIVE                                                  
+unsigned_long  LINUX_MIB_TCPFASTOPENPASSIVEFAIL                                              
+unsigned_long  LINUX_MIB_TCPFASTOPENLISTENOVERFLOW                                           
+unsigned_long  LINUX_MIB_TCPFASTOPENCOOKIEREQD                                               
+unsigned_long  LINUX_MIB_TCPFASTOPENBLACKHOLE                                                
+unsigned_long  LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES                                          
+unsigned_long  LINUX_MIB_BUSYPOLLRXPACKETS                                                   
+unsigned_long  LINUX_MIB_TCPSYNRETRANS                                                       
+unsigned_long  LINUX_MIB_TCPHYSTARTTRAINDETECT                                               
+unsigned_long  LINUX_MIB_TCPHYSTARTTRAINCWND                                                 
+unsigned_long  LINUX_MIB_TCPHYSTARTDELAYDETECT                                               
+unsigned_long  LINUX_MIB_TCPHYSTARTDELAYCWND                                                 
+unsigned_long  LINUX_MIB_TCPACKSKIPPEDSYNRECV                                                
+unsigned_long  LINUX_MIB_TCPACKSKIPPEDPAWS                                                   
+unsigned_long  LINUX_MIB_TCPACKSKIPPEDSEQ                                                    
+unsigned_long  LINUX_MIB_TCPACKSKIPPEDFINWAIT2                                               
+unsigned_long  LINUX_MIB_TCPACKSKIPPEDTIMEWAIT                                               
+unsigned_long  LINUX_MIB_TCPACKSKIPPEDCHALLENGE                                              
+unsigned_long  LINUX_MIB_TCPWINPROBE                                                         
+unsigned_long  LINUX_MIB_TCPMTUPFAIL                                                         
+unsigned_long  LINUX_MIB_TCPMTUPSUCCESS                                                      
+unsigned_long  LINUX_MIB_TCPDELIVEREDCE                                                      
+unsigned_long  LINUX_MIB_TCPACKCOMPRESSED                                                    
+unsigned_long  LINUX_MIB_TCPZEROWINDOWDROP                                                   
+unsigned_long  LINUX_MIB_TCPRCVQDROP                                                         
+unsigned_long  LINUX_MIB_TCPWQUEUETOOBIG                                                     
+unsigned_long  LINUX_MIB_TCPFASTOPENPASSIVEALTKEY                                            
+unsigned_long  LINUX_MIB_TCPTIMEOUTREHASH                                                    
+unsigned_long  LINUX_MIB_TCPDUPLICATEDATAREHASH                                              
+unsigned_long  LINUX_MIB_TCPDSACKRECVSEGS                                                    
+unsigned_long  LINUX_MIB_TCPDSACKIGNOREDDUBIOUS                                              
+unsigned_long  LINUX_MIB_TCPMIGRATEREQSUCCESS                                                
+unsigned_long  LINUX_MIB_TCPMIGRATEREQFAILURE                                                
+unsigned_long  __LINUX_MIB_MAX                                                               
diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst
new file mode 100644
index 000000000000..97d7a5c8e01c
--- /dev/null
+++ b/Documentation/networking/net_cachelines/tcp_sock.rst
@@ -0,0 +1,157 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. Copyright (C) 2023 Google LLC
+
+=========================================
+tcp_sock struct fast path usage breakdown
+=========================================
+
+Type                          Name                    fastpath_tx_access  fastpath_rx_access  Comments
+..struct                      ..tcp_sock                                                        
+struct_inet_connection_sock   inet_conn                                                       
+u16                           tcp_header_len          read_mostly         read_mostly         tcp_bound_to_half_wnd,tcp_current_mss(tx);tcp_rcv_established(rx)
+u16                           gso_segs                read_mostly         -                   tcp_xmit_size_goal
+__be32                        pred_flags              read_write          read_mostly         tcp_select_window(tx);tcp_rcv_established(rx)
+u64                           bytes_received          -                   read_write          tcp_rcv_nxt_update(rx)
+u32                           segs_in                 -                   read_write          tcp_v6_rcv(rx)
+u32                           data_segs_in            -                   read_write          tcp_v6_rcv(rx)
+u32                           rcv_nxt                 read_mostly         read_write          tcp_cleanup_rbuf,tcp_send_ack,tcp_inq_hint,tcp_transmit_skb,tcp_receive_window(tx);tcp_v6_do_rcv,tcp_rcv_established,tcp_data_queue,tcp_receive_window,tcp_rcv_nxt_update(write)(rx)
+u32                           copied_seq              -                   read_mostly         tcp_cleanup_rbuf,tcp_rcv_space_adjust,tcp_inq_hint
+u32                           rcv_wup                 -                   read_write          __tcp_cleanup_rbuf,tcp_receive_window,tcp_receive_established
+u32                           snd_nxt                 read_write          read_mostly         tcp_rate_check_app_limited,__tcp_transmit_skb,tcp_event_new_data_sent(write)(tx);tcp_rcv_established,tcp_ack,tcp_clean_rtx_queue(rx)
+u32                           segs_out                read_write          -                   __tcp_transmit_skb
+u32                           data_segs_out           read_write          -                   __tcp_transmit_skb,tcp_update_skb_after_send
+u64                           bytes_sent              read_write          -                   __tcp_transmit_skb
+u64                           bytes_acked             -                   read_write          tcp_snd_una_update/tcp_ack
+u32                           dsack_dups                                                      
+u32                           snd_una                 read_mostly         read_write          tcp_wnd_end,tcp_urg_mode,tcp_minshall_check,tcp_cwnd_validate(tx);tcp_ack,tcp_may_update_window,tcp_clean_rtx_queue(write),tcp_ack_tstamp(rx)
+u32                           snd_sml                 read_write          -                   tcp_minshall_check,tcp_minshall_update
+u32                           rcv_tstamp              -                   read_mostly         tcp_ack
+u32                           lsndtime                read_write          -                   tcp_slow_start_after_idle_check,tcp_event_data_sent
+u32                           last_oow_ack_time                                               
+u32                           compressed_ack_rcv_nxt                                          
+u32                           tsoffset                read_mostly         read_mostly         tcp_established_options(tx);tcp_fast_parse_options(rx)
+struct_list_head              tsq_node                -                   -                   
+struct_list_head              tsorted_sent_queue      read_write          -                   tcp_update_skb_after_send
+u32                           snd_wl1                 -                   read_mostly         tcp_may_update_window
+u32                           snd_wnd                 read_mostly         read_mostly         tcp_wnd_end,tcp_tso_should_defer(tx);tcp_fast_path_on(rx)
+u32                           max_window              read_mostly         -                   tcp_bound_to_half_wnd,forced_push
+u32                           mss_cache               read_mostly         read_mostly         tcp_rate_check_app_limited,tcp_current_mss,tcp_sync_mss,tcp_sndbuf_expand,tcp_tso_should_defer(tx);tcp_update_pacing_rate,tcp_clean_rtx_queue(rx)
+u32                           window_clamp            read_mostly         read_write          tcp_rcv_space_adjust,__tcp_select_window
+u32                           rcv_ssthresh            read_mostly         -                   __tcp_select_window
+u82                           scaling_ratio                                                   
+struct                        tcp_rack                                                        
+u16                           advmss                  -                   read_mostly         tcp_rcv_space_adjust
+u8                            compressed_ack                                                  
+u8:2                          dup_ack_counter                                                 
+u8:1                          tlp_retrans                                                     
+u8:1                          tcp_usec_ts                                                     
+u32                           chrono_start            read_write          -                   tcp_chrono_start/stop(tcp_write_xmit,tcp_cwnd_validate,tcp_send_syn_data)
+u32[3]                        chrono_stat             read_write          -                   tcp_chrono_start/stop(tcp_write_xmit,tcp_cwnd_validate,tcp_send_syn_data)
+u8:2                          chrono_type             read_write          -                   tcp_chrono_start/stop(tcp_write_xmit,tcp_cwnd_validate,tcp_send_syn_data)
+u8:1                          rate_app_limited        -                   read_write          tcp_rate_gen
+u8:1                          fastopen_connect                                                
+u8:1                          fastopen_no_cookie                                              
+u8:1                          is_sack_reneg           -                   read_mostly         tcp_skb_entail,tcp_ack
+u8:2                          fastopen_client_fail                                            
+u8:4                          nonagle                 read_write          -                   tcp_skb_entail,tcp_push_pending_frames
+u8:1                          thin_lto                                                        
+u8:1                          recvmsg_inq                                                     
+u8:1                          repair                  read_mostly         -                   tcp_write_xmit
+u8:1                          frto                                                            
+u8                            repair_queue            -                   -                   
+u8:2                          save_syn                                                        
+u8:1                          syn_data                                                        
+u8:1                          syn_fastopen                                                    
+u8:1                          syn_fastopen_exp                                                
+u8:1                          syn_fastopen_ch                                                 
+u8:1                          syn_data_acked                                                  
+u8:1                          is_cwnd_limited         read_mostly         -                   tcp_cwnd_validate,tcp_is_cwnd_limited
+u32                           tlp_high_seq            -                   read_mostly         tcp_ack
+u32                           tcp_tx_delay                                                    
+u64                           tcp_wstamp_ns           read_write          -                   tcp_pacing_check,tcp_tso_should_defer,tcp_update_skb_after_send
+u64                           tcp_clock_cache         read_write          read_write          tcp_mstamp_refresh(tcp_write_xmit/tcp_rcv_space_adjust),__tcp_transmit_skb,tcp_tso_should_defer;timer
+u64                           tcp_mstamp              read_write          read_write          tcp_mstamp_refresh(tcp_write_xmit/tcp_rcv_space_adjust)(tx);tcp_rcv_space_adjust,tcp_rate_gen,tcp_clean_rtx_queue,tcp_ack_update_rtt/tcp_time_stamp(rx);timer
+u32                           srtt_us                 read_mostly         read_write          tcp_tso_should_defer(tx);tcp_update_pacing_rate,__tcp_set_rto,tcp_rtt_estimator(rx)
+u32                           mdev_us                 read_write          -                   tcp_rtt_estimator
+u32                           mdev_max_us                                                     
+u32                           rttvar_us               -                   read_mostly         __tcp_set_rto
+u32                           rtt_seq                 read_write                              tcp_rtt_estimator
+struct_minmax                 rtt_min                 -                   read_mostly         tcp_min_rtt/tcp_rate_gen,tcp_min_rtttcp_update_rtt_min
+u32                           packets_out             read_write          read_write          tcp_packets_in_flight(tx/rx);tcp_slow_start_after_idle_check,tcp_nagle_check,tcp_rate_skb_sent,tcp_event_new_data_sent,tcp_cwnd_validate,tcp_write_xmit(tx);tcp_ack,tcp_clean_rtx_queue,tcp_update_pacing_rate(rx)
+u32                           retrans_out             -                   read_mostly         tcp_packets_in_flight,tcp_rate_check_app_limited
+u32                           max_packets_out         -                   read_write          tcp_cwnd_validate
+u32                           cwnd_usage_seq          -                   read_write          tcp_cwnd_validate
+u16                           urg_data                -                   read_mostly         tcp_fast_path_check
+u8                            ecn_flags               read_write          -                   tcp_ecn_send
+u8                            keepalive_probes                                                
+u32                           reordering              read_mostly         -                   tcp_sndbuf_expand
+u32                           reord_seen                                                      
+u32                           snd_up                  read_write          read_mostly         tcp_mark_urg,tcp_urg_mode,__tcp_transmit_skb(tx);tcp_clean_rtx_queue(rx)
+struct_tcp_options_received   rx_opt                  read_mostly         read_write          tcp_established_options(tx);tcp_fast_path_on,tcp_ack_update_window,tcp_is_sack,tcp_data_queue,tcp_rcv_established,tcp_ack_update_rtt(rx)
+u32                           snd_ssthresh            -                   read_mostly         tcp_update_pacing_rate
+u32                           snd_cwnd                read_mostly         read_mostly         tcp_snd_cwnd,tcp_rate_check_app_limited,tcp_tso_should_defer(tx);tcp_update_pacing_rate
+u32                           snd_cwnd_cnt                                                    
+u32                           snd_cwnd_clamp                                                  
+u32                           snd_cwnd_used                                                   
+u32                           snd_cwnd_stamp                                                  
+u32                           prior_cwnd                                                      
+u32                           prr_delivered                                                   
+u32                           prr_out                 read_mostly         read_mostly         tcp_rate_skb_sent,tcp_newly_delivered(tx);tcp_ack,tcp_rate_gen,tcp_clean_rtx_queue(rx)
+u32                           delivered               read_mostly         read_write          tcp_rate_skb_sent, tcp_newly_delivered(tx);tcp_ack, tcp_rate_gen, tcp_clean_rtx_queue (rx)
+u32                           delivered_ce            read_mostly         read_write          tcp_rate_skb_sent(tx);tcp_rate_gen(rx)
+u32                           lost                    -                   read_mostly         tcp_ack
+u32                           app_limited             read_write          read_mostly         tcp_rate_check_app_limited,tcp_rate_skb_sent(tx);tcp_rate_gen(rx)
+u64                           first_tx_mstamp         read_write          -                   tcp_rate_skb_sent
+u64                           delivered_mstamp        read_write          -                   tcp_rate_skb_sent
+u32                           rate_delivered          -                   read_mostly         tcp_rate_gen
+u32                           rate_interval_us        -                   read_mostly         rate_delivered,rate_app_limited
+u32                           rcv_wnd                 read_write          read_mostly         tcp_select_window,tcp_receive_window,tcp_fast_path_check
+u32                           write_seq               read_write          -                   tcp_rate_check_app_limited,tcp_write_queue_empty,tcp_skb_entail,forced_push,tcp_mark_push
+u32                           notsent_lowat           read_mostly         -                   tcp_stream_memory_free
+u32                           pushed_seq              read_write          -                   tcp_mark_push,forced_push
+u32                           lost_out                read_mostly         read_mostly         tcp_left_out(tx);tcp_packets_in_flight(tx/rx);tcp_rate_check_app_limited(rx)
+u32                           sacked_out              read_mostly         read_mostly         tcp_left_out(tx);tcp_packets_in_flight(tx/rx);tcp_clean_rtx_queue(rx)
+struct_hrtimer                pacing_timer                                                    
+struct_hrtimer                compressed_ack_timer                                            
+struct_sk_buff*               lost_skb_hint           read_mostly                             tcp_clean_rtx_queue
+struct_sk_buff*               retransmit_skb_hint     read_mostly         -                   tcp_clean_rtx_queue
+struct_rb_root                out_of_order_queue      -                   read_mostly         tcp_data_queue,tcp_fast_path_check
+struct_sk_buff*               ooo_last_skb                                                    
+struct_tcp_sack_block[1]      duplicate_sack                                                  
+struct_tcp_sack_block[4]      selective_acks                                                  
+struct_tcp_sack_block[4]      recv_sack_cache                                                 
+struct_sk_buff*               highest_sack            read_write          -                   tcp_event_new_data_sent
+int                           lost_cnt_hint                                                   
+u32                           prior_ssthresh                                                  
+u32                           high_seq                                                        
+u32                           retrans_stamp                                                   
+u32                           undo_marker                                                     
+int                           undo_retrans                                                    
+u64                           bytes_retrans                                                   
+u32                           total_retrans                                                   
+u32                           rto_stamp                                                       
+u16                           total_rto                                                       
+u16                           total_rto_recoveries                                            
+u32                           total_rto_time                                                  
+u32                           urg_seq                 -                   -                   
+unsigned_int                  keepalive_time                                                  
+unsigned_int                  keepalive_intvl                                                 
+int                           linger2                                                         
+u8                            bpf_sock_ops_cb_flags                                           
+u8:1                          bpf_chg_cc_inprogress                                           
+u16                           timeout_rehash                                                  
+u32                           rcv_ooopack                                                     
+u32                           rcv_rtt_last_tsecr                                              
+struct                        rcv_rtt_est             -                   read_write          tcp_rcv_space_adjust,tcp_rcv_established
+struct                        rcvq_space              -                   read_write          tcp_rcv_space_adjust
+struct                        mtu_probe                                                       
+u32                           plb_rehash                                                      
+u32                           mtu_info                                                        
+bool                          is_mptcp                                                        
+bool                          smc_hs_congested                                                
+bool                          syn_smc                                                         
+struct_tcp_sock_af_ops*       af_specific                                                     
+struct_tcp_md5sig_info*       md5sig_info                                                     
+struct_tcp_fastopen_request*  fastopen_req                                                    
+struct_request_sock*          fastopen_rsk                                                    
+struct_saved_syn*             saved_syn                                                        
\ No newline at end of file
diff --git a/Documentation/networking/netlink_spec/.gitignore b/Documentation/networking/netlink_spec/.gitignore
new file mode 100644
index 000000000000..30d85567b592
--- /dev/null
+++ b/Documentation/networking/netlink_spec/.gitignore
@@ -0,0 +1 @@
+*.rst
diff --git a/Documentation/networking/netlink_spec/readme.txt b/Documentation/networking/netlink_spec/readme.txt
new file mode 100644
index 000000000000..6763f99d216c
--- /dev/null
+++ b/Documentation/networking/netlink_spec/readme.txt
@@ -0,0 +1,4 @@
+SPDX-License-Identifier: GPL-2.0
+
+This file is populated during the build of the documentation (htmldocs) by the
+tools/net/ynl/ynl-gen-rst.py script.
diff --git a/Documentation/networking/packet_mmap.rst b/Documentation/networking/packet_mmap.rst
index 30a3be3c48f3..dca15d15feaf 100644
--- a/Documentation/networking/packet_mmap.rst
+++ b/Documentation/networking/packet_mmap.rst
@@ -263,20 +263,20 @@ the name indicates, this function allocates pages of memory, and the second
 argument is "order" or a power of two number of pages, that is
 (for PAGE_SIZE == 4096) order=0 ==> 4096 bytes, order=1 ==> 8192 bytes,
 order=2 ==> 16384 bytes, etc. The maximum size of a
-region allocated by __get_free_pages is determined by the MAX_ORDER macro. More
-precisely the limit can be calculated as::
+region allocated by __get_free_pages is determined by the MAX_PAGE_ORDER macro.
+More precisely the limit can be calculated as::
 
-   PAGE_SIZE << MAX_ORDER
+   PAGE_SIZE << MAX_PAGE_ORDER
 
    In a i386 architecture PAGE_SIZE is 4096 bytes
-   In a 2.4/i386 kernel MAX_ORDER is 10
-   In a 2.6/i386 kernel MAX_ORDER is 11
+   In a 2.4/i386 kernel MAX_PAGE_ORDER is 10
+   In a 2.6/i386 kernel MAX_PAGE_ORDER is 11
 
 So get_free_pages can allocate as much as 4MB or 8MB in a 2.4/2.6 kernel
 respectively, with an i386 architecture.
 
 User space programs can include /usr/include/sys/user.h and
-/usr/include/linux/mmzone.h to get PAGE_SIZE MAX_ORDER declarations.
+/usr/include/linux/mmzone.h to get PAGE_SIZE MAX_PAGE_ORDER declarations.
 
 The pagesize can also be determined dynamically with the getpagesize (2)
 system call.
@@ -324,7 +324,7 @@ Definitions:
 		(see /proc/slabinfo)
 <pointer size>  depends on the architecture -- ``sizeof(void *)``
 <page size>     depends on the architecture -- PAGE_SIZE or getpagesize (2)
-<max-order>     is the value defined with MAX_ORDER
+<max-order>     is the value defined with MAX_PAGE_ORDER
 <frame size>    it's an upper bound of frame's capture size (more on this later)
 ==============  ================================================================
 
diff --git a/Documentation/networking/page_pool.rst b/Documentation/networking/page_pool.rst
index 60993cb56b32..9d958128a57c 100644
--- a/Documentation/networking/page_pool.rst
+++ b/Documentation/networking/page_pool.rst
@@ -41,6 +41,11 @@ Architecture overview
                           |   Fast cache    |     |  ptr-ring cache  |
                           +-----------------+     +------------------+
 
+Monitoring
+==========
+Information about page pools on the system can be accessed via the netdev
+genetlink family (see Documentation/netlink/specs/netdev.yaml).
+
 API interface
 =============
 The number of pools created **must** match the number of hardware queues
@@ -107,8 +112,9 @@ page_pool_get_stats() and structures described below are available.
 It takes a  pointer to a ``struct page_pool`` and a pointer to a struct
 page_pool_stats allocated by the caller.
 
-The API will fill in the provided struct page_pool_stats with
-statistics about the page_pool.
+Older drivers expose page pool statistics via ethtool or debugfs.
+The same statistics are accessible via the netlink netdev family
+in a driver-independent fashion.
 
 .. kernel-doc:: include/net/page_pool/types.h
    :identifiers: struct page_pool_recycle_stats
diff --git a/Documentation/networking/scaling.rst b/Documentation/networking/scaling.rst
index 03ae19a689fc..4eb50bcb9d42 100644
--- a/Documentation/networking/scaling.rst
+++ b/Documentation/networking/scaling.rst
@@ -44,6 +44,21 @@ by masking out the low order seven bits of the computed hash for the
 packet (usually a Toeplitz hash), taking this number as a key into the
 indirection table and reading the corresponding value.
 
+Some NICs support symmetric RSS hashing where, if the IP (source address,
+destination address) and TCP/UDP (source port, destination port) tuples
+are swapped, the computed hash is the same. This is beneficial in some
+applications that monitor TCP/IP flows (IDS, firewalls, ...etc) and need
+both directions of the flow to land on the same Rx queue (and CPU). The
+"Symmetric-XOR" is a type of RSS algorithms that achieves this hash
+symmetry by XORing the input source and destination fields of the IP
+and/or L4 protocols. This, however, results in reduced input entropy and
+could potentially be exploited. Specifically, the algorithm XORs the input
+as follows::
+
+    # (SRC_IP ^ DST_IP, SRC_IP ^ DST_IP, SRC_PORT ^ DST_PORT, SRC_PORT ^ DST_PORT)
+
+The result is then fed to the underlying RSS algorithm.
+
 Some advanced NICs allow steering packets to queues based on
 programmable filters. For example, webserver bound TCP port 80 packets
 can be directed to their own receive queue. Such “n-tuple� filters can
diff --git a/Documentation/networking/smc-sysctl.rst b/Documentation/networking/smc-sysctl.rst
index 769149d98773..a874d007f2db 100644
--- a/Documentation/networking/smc-sysctl.rst
+++ b/Documentation/networking/smc-sysctl.rst
@@ -57,3 +57,17 @@ rmem - INTEGER
 	only allowed 512KiB for SMC-R and 1MiB for SMC-D.
 
 	Default: 64KiB
+
+smcr_max_links_per_lgr - INTEGER
+	Controls the max number of links can be added to a SMC-R link group. Notice that
+	the actual number of the links added to a SMC-R link group depends on the number
+	of RDMA devices exist in the system. The acceptable value ranges from 1 to 2. Only
+	for SMC-R v2.1 and later.
+
+	Default: 2
+
+smcr_max_conns_per_lgr - INTEGER
+	Controls the max number of connections can be added to a SMC-R link group. The
+	acceptable value ranges from 16 to 255. Only for SMC-R v2.1 and later.
+
+	Default: 255
diff --git a/Documentation/networking/tcp_ao.rst b/Documentation/networking/tcp_ao.rst
index cfa5bf1cc542..8a58321acce7 100644
--- a/Documentation/networking/tcp_ao.rst
+++ b/Documentation/networking/tcp_ao.rst
@@ -99,7 +99,7 @@ also [6.1]::
    when it is no longer considered permitted.
 
 Linux TCP-AO will try its best to prevent you from removing a key that's
-being used, considering it a key management failure. But sine keeping
+being used, considering it a key management failure. But since keeping
 an outdated key may become a security issue and as a peer may
 unintentionally prevent the removal of an old key by always setting
 it as RNextKeyID - a forced key removal mechanism is provided, where
diff --git a/Documentation/networking/timestamping.rst b/Documentation/networking/timestamping.rst
index f17c01834a12..5e93cd71f99f 100644
--- a/Documentation/networking/timestamping.rst
+++ b/Documentation/networking/timestamping.rst
@@ -357,7 +357,8 @@ enabling SOF_TIMESTAMPING_OPT_ID and comparing the byte offset at
 send time with the value returned for each timestamp. It can prevent
 the situation by always flushing the TCP stack in between requests,
 for instance by enabling TCP_NODELAY and disabling TCP_CORK and
-autocork.
+autocork. After linux-4.7, a better way to prevent coalescing is
+to use MSG_EOR flag at sendmsg() time.
 
 These precautions ensure that the timestamp is generated only when all
 bytes have passed a timestamp point, assuming that the network stack
diff --git a/Documentation/networking/xdp-rx-metadata.rst b/Documentation/networking/xdp-rx-metadata.rst
index 205696780b78..a6e0ece18be5 100644
--- a/Documentation/networking/xdp-rx-metadata.rst
+++ b/Documentation/networking/xdp-rx-metadata.rst
@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: GPL-2.0
+
 ===============
 XDP RX Metadata
 ===============
@@ -18,7 +20,13 @@ Currently, the following kfuncs are supported. In the future, as more
 metadata is supported, this set will grow:
 
 .. kernel-doc:: net/core/xdp.c
-   :identifiers: bpf_xdp_metadata_rx_timestamp bpf_xdp_metadata_rx_hash
+   :identifiers: bpf_xdp_metadata_rx_timestamp
+
+.. kernel-doc:: net/core/xdp.c
+   :identifiers: bpf_xdp_metadata_rx_hash
+
+.. kernel-doc:: net/core/xdp.c
+   :identifiers: bpf_xdp_metadata_rx_vlan_tag
 
 An XDP program can use these kfuncs to read the metadata into stack
 variables for its own consumption. Or, to pass the metadata on to other
diff --git a/Documentation/networking/xsk-tx-metadata.rst b/Documentation/networking/xsk-tx-metadata.rst
new file mode 100644
index 000000000000..bd033fe95cca
--- /dev/null
+++ b/Documentation/networking/xsk-tx-metadata.rst
@@ -0,0 +1,81 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==================
+AF_XDP TX Metadata
+==================
+
+This document describes how to enable offloads when transmitting packets
+via :doc:`af_xdp`. Refer to :doc:`xdp-rx-metadata` on how to access similar
+metadata on the receive side.
+
+General Design
+==============
+
+The headroom for the metadata is reserved via ``tx_metadata_len`` in
+``struct xdp_umem_reg``. The metadata length is therefore the same for
+every socket that shares the same umem. The metadata layout is a fixed UAPI,
+refer to ``union xsk_tx_metadata`` in ``include/uapi/linux/if_xdp.h``.
+Thus, generally, the ``tx_metadata_len`` field above should contain
+``sizeof(union xsk_tx_metadata)``.
+
+The headroom and the metadata itself should be located right before
+``xdp_desc->addr`` in the umem frame. Within a frame, the metadata
+layout is as follows::
+
+           tx_metadata_len
+     /                         \
+    +-----------------+---------+----------------------------+
+    | xsk_tx_metadata | padding |          payload           |
+    +-----------------+---------+----------------------------+
+                                ^
+                                |
+                          xdp_desc->addr
+
+An AF_XDP application can request headrooms larger than ``sizeof(struct
+xsk_tx_metadata)``. The kernel will ignore the padding (and will still
+use ``xdp_desc->addr - tx_metadata_len`` to locate
+the ``xsk_tx_metadata``). For the frames that shouldn't carry
+any metadata (i.e., the ones that don't have ``XDP_TX_METADATA`` option),
+the metadata area is ignored by the kernel as well.
+
+The flags field enables the particular offload:
+
+- ``XDP_TXMD_FLAGS_TIMESTAMP``: requests the device to put transmission
+  timestamp into ``tx_timestamp`` field of ``union xsk_tx_metadata``.
+- ``XDP_TXMD_FLAGS_CHECKSUM``: requests the device to calculate L4
+  checksum. ``csum_start`` specifies byte offset of where the checksumming
+  should start and ``csum_offset`` specifies byte offset where the
+  device should store the computed checksum.
+
+Besides the flags above, in order to trigger the offloads, the first
+packet's ``struct xdp_desc`` descriptor should set ``XDP_TX_METADATA``
+bit in the ``options`` field. Also note that in a multi-buffer packet
+only the first chunk should carry the metadata.
+
+Software TX Checksum
+====================
+
+For development and testing purposes its possible to pass
+``XDP_UMEM_TX_SW_CSUM`` flag to ``XDP_UMEM_REG`` UMEM registration call.
+In this case, when running in ``XDK_COPY`` mode, the TX checksum
+is calculated on the CPU. Do not enable this option in production because
+it will negatively affect performance.
+
+Querying Device Capabilities
+============================
+
+Every devices exports its offloads capabilities via netlink netdev family.
+Refer to ``xsk-flags`` features bitmask in
+``Documentation/netlink/specs/netdev.yaml``.
+
+- ``tx-timestamp``: device supports ``XDP_TXMD_FLAGS_TIMESTAMP``
+- ``tx-checksum``: device supports ``XDP_TXMD_FLAGS_CHECKSUM``
+
+See ``tools/net/ynl/samples/netdev.c`` on how to query this information.
+
+Example
+=======
+
+See ``tools/testing/selftests/bpf/xdp_hw_metadata.c`` for an example
+program that handles TX metadata. Also see https://github.com/fomichev/xskgen
+for a more bare-bones example.
diff --git a/Documentation/power/freezing-of-tasks.rst b/Documentation/power/freezing-of-tasks.rst
index 53b6a56c4635..df9755bfbd94 100644
--- a/Documentation/power/freezing-of-tasks.rst
+++ b/Documentation/power/freezing-of-tasks.rst
@@ -14,27 +14,28 @@ architectures).
 II. How does it work?
 =====================
 
-There are three per-task flags used for that, PF_NOFREEZE, PF_FROZEN
-and PF_FREEZER_SKIP (the last one is auxiliary).  The tasks that have
-PF_NOFREEZE unset (all user space processes and some kernel threads) are
-regarded as 'freezable' and treated in a special way before the system enters a
-suspend state as well as before a hibernation image is created (in what follows
-we only consider hibernation, but the description also applies to suspend).
+There is one per-task flag (PF_NOFREEZE) and three per-task states
+(TASK_FROZEN, TASK_FREEZABLE and __TASK_FREEZABLE_UNSAFE) used for that.
+The tasks that have PF_NOFREEZE unset (all user space tasks and some kernel
+threads) are regarded as 'freezable' and treated in a special way before the
+system enters a sleep state as well as before a hibernation image is created
+(hibernation is directly covered by what follows, but the description applies
+to system-wide suspend too).
 
 Namely, as the first step of the hibernation procedure the function
 freeze_processes() (defined in kernel/power/process.c) is called.  A system-wide
-variable system_freezing_cnt (as opposed to a per-task flag) is used to indicate
-whether the system is to undergo a freezing operation. And freeze_processes()
-sets this variable.  After this, it executes try_to_freeze_tasks() that sends a
-fake signal to all user space processes, and wakes up all the kernel threads.
-All freezable tasks must react to that by calling try_to_freeze(), which
-results in a call to __refrigerator() (defined in kernel/freezer.c), which sets
-the task's PF_FROZEN flag, changes its state to TASK_UNINTERRUPTIBLE and makes
-it loop until PF_FROZEN is cleared for it. Then, we say that the task is
-'frozen' and therefore the set of functions handling this mechanism is referred
-to as 'the freezer' (these functions are defined in kernel/power/process.c,
-kernel/freezer.c & include/linux/freezer.h). User space processes are generally
-frozen before kernel threads.
+static key freezer_active (as opposed to a per-task flag or state) is used to
+indicate whether the system is to undergo a freezing operation. And
+freeze_processes() sets this static key.  After this, it executes
+try_to_freeze_tasks() that sends a fake signal to all user space processes, and
+wakes up all the kernel threads. All freezable tasks must react to that by
+calling try_to_freeze(), which results in a call to __refrigerator() (defined
+in kernel/freezer.c), which changes the task's state to TASK_FROZEN, and makes
+it loop until it is woken by an explicit TASK_FROZEN wakeup. Then, that task
+is regarded as 'frozen' and so the set of functions handling this mechanism is
+referred to as 'the freezer' (these functions are defined in
+kernel/power/process.c, kernel/freezer.c & include/linux/freezer.h). User space
+tasks are generally frozen before kernel threads.
 
 __refrigerator() must not be called directly.  Instead, use the
 try_to_freeze() function (defined in include/linux/freezer.h), that checks
@@ -43,31 +44,40 @@ if the task is to be frozen and makes the task enter __refrigerator().
 For user space processes try_to_freeze() is called automatically from the
 signal-handling code, but the freezable kernel threads need to call it
 explicitly in suitable places or use the wait_event_freezable() or
-wait_event_freezable_timeout() macros (defined in include/linux/freezer.h)
-that combine interruptible sleep with checking if the task is to be frozen and
-calling try_to_freeze().  The main loop of a freezable kernel thread may look
+wait_event_freezable_timeout() macros (defined in include/linux/wait.h)
+that put the task to sleep (TASK_INTERRUPTIBLE) or freeze it (TASK_FROZEN) if
+freezer_active is set. The main loop of a freezable kernel thread may look
 like the following one::
 
 	set_freezable();
-	do {
-		hub_events();
-		wait_event_freezable(khubd_wait,
-				!list_empty(&hub_event_list) ||
-				kthread_should_stop());
-	} while (!kthread_should_stop() || !list_empty(&hub_event_list));
-
-(from drivers/usb/core/hub.c::hub_thread()).
-
-If a freezable kernel thread fails to call try_to_freeze() after the freezer has
-initiated a freezing operation, the freezing of tasks will fail and the entire
-hibernation operation will be cancelled.  For this reason, freezable kernel
-threads must call try_to_freeze() somewhere or use one of the
+
+	while (true) {
+		struct task_struct *tsk = NULL;
+
+		wait_event_freezable(oom_reaper_wait, oom_reaper_list != NULL);
+		spin_lock_irq(&oom_reaper_lock);
+		if (oom_reaper_list != NULL) {
+			tsk = oom_reaper_list;
+			oom_reaper_list = tsk->oom_reaper_list;
+		}
+		spin_unlock_irq(&oom_reaper_lock);
+
+		if (tsk)
+			oom_reap_task(tsk);
+	}
+
+(from mm/oom_kill.c::oom_reaper()).
+
+If a freezable kernel thread is not put to the frozen state after the freezer
+has initiated a freezing operation, the freezing of tasks will fail and the
+entire system-wide transition will be cancelled.  For this reason, freezable
+kernel threads must call try_to_freeze() somewhere or use one of the
 wait_event_freezable() and wait_event_freezable_timeout() macros.
 
 After the system memory state has been restored from a hibernation image and
 devices have been reinitialized, the function thaw_processes() is called in
-order to clear the PF_FROZEN flag for each frozen task.  Then, the tasks that
-have been frozen leave __refrigerator() and continue running.
+order to wake up each frozen task.  Then, the tasks that have been frozen leave
+__refrigerator() and continue running.
 
 
 Rationale behind the functions dealing with freezing and thawing of tasks
@@ -96,7 +106,8 @@ III. Which kernel threads are freezable?
 Kernel threads are not freezable by default.  However, a kernel thread may clear
 PF_NOFREEZE for itself by calling set_freezable() (the resetting of PF_NOFREEZE
 directly is not allowed).  From this point it is regarded as freezable
-and must call try_to_freeze() in a suitable place.
+and must call try_to_freeze() or variants of wait_event_freezable() in a
+suitable place.
 
 IV. Why do we do that?
 ======================
diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
index f18cfc01f31a..50b3d1cb1115 100644
--- a/Documentation/process/changes.rst
+++ b/Documentation/process/changes.rst
@@ -31,7 +31,7 @@ you probably needn't concern yourself with pcmciautils.
 ====================== ===============  ========================================
 GNU C                  5.1              gcc --version
 Clang/LLVM (optional)  11.0.0           clang --version
-Rust (optional)        1.73.0           rustc --version
+Rust (optional)        1.74.1           rustc --version
 bindgen (optional)     0.65.1           bindgen --version
 GNU make               3.82             make --version
 bash                   4.2              bash --version
diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst
index 7feacc20835e..84ee60fceef2 100644
--- a/Documentation/process/maintainer-netdev.rst
+++ b/Documentation/process/maintainer-netdev.rst
@@ -193,9 +193,23 @@ Review timelines
 Generally speaking, the patches get triaged quickly (in less than
 48h). But be patient, if your patch is active in patchwork (i.e. it's
 listed on the project's patch list) the chances it was missed are close to zero.
-Asking the maintainer for status updates on your
-patch is a good way to ensure your patch is ignored or pushed to the
-bottom of the priority list.
+
+The high volume of development on netdev makes reviewers move on
+from discussions relatively quickly. New comments and replies
+are very unlikely to arrive after a week of silence. If a patch
+is no longer active in patchwork and the thread went idle for more
+than a week - clarify the next steps and/or post the next version.
+
+For RFC postings specifically, if nobody responded in a week - reviewers
+either missed the posting or have no strong opinions. If the code is ready,
+repost as a PATCH.
+
+Emails saying just "ping" or "bump" are considered rude. If you can't figure
+out the status of the patch from patchwork or where the discussion has
+landed - describe your best guess and ask if it's correct. For example::
+
+  I don't understand what the next steps are. Person X seems to be unhappy
+  with A, should I do B and repost the patches?
 
 .. _Changes requested:
 
diff --git a/Documentation/rust/coding-guidelines.rst b/Documentation/rust/coding-guidelines.rst
index aa8ed082613e..05542840b16c 100644
--- a/Documentation/rust/coding-guidelines.rst
+++ b/Documentation/rust/coding-guidelines.rst
@@ -177,6 +177,19 @@ please take a look at the ``rustdoc`` book at:
 
 	https://doc.rust-lang.org/rustdoc/how-to-write-documentation.html
 
+In addition, the kernel supports creating links relative to the source tree by
+prefixing the link destination with ``srctree/``. For instance:
+
+.. code-block:: rust
+
+	//! C header: [`include/linux/printk.h`](srctree/include/linux/printk.h)
+
+or:
+
+.. code-block:: rust
+
+	/// [`struct mutex`]: srctree/include/linux/mutex.h
+
 
 Naming
 ------
diff --git a/Documentation/rust/general-information.rst b/Documentation/rust/general-information.rst
index 081397827a7e..236c6dd3c647 100644
--- a/Documentation/rust/general-information.rst
+++ b/Documentation/rust/general-information.rst
@@ -77,3 +77,27 @@ configuration:
 	#[cfg(CONFIG_X="y")]   // Enabled as a built-in (`y`)
 	#[cfg(CONFIG_X="m")]   // Enabled as a module   (`m`)
 	#[cfg(not(CONFIG_X))]  // Disabled
+
+
+Testing
+-------
+
+There are the tests that come from the examples in the Rust documentation
+and get transformed into KUnit tests. These can be run via KUnit. For example
+via ``kunit_tool`` (``kunit.py``) on the command line::
+
+	./tools/testing/kunit/kunit.py run --make_options LLVM=1 --arch x86_64 --kconfig_add CONFIG_RUST=y
+
+Alternatively, KUnit can run them as kernel built-in at boot. Refer to
+Documentation/dev-tools/kunit/index.rst for the general KUnit documentation
+and Documentation/dev-tools/kunit/architecture.rst for the details of kernel
+built-in vs. command line testing.
+
+Additionally, there are the ``#[test]`` tests. These can be run using
+the ``rusttest`` Make target::
+
+	make LLVM=1 rusttest
+
+This requires the kernel ``.config`` and downloads external repositories.
+It runs the ``#[test]`` tests on the host (currently) and thus is fairly
+limited in what these tests can test.
diff --git a/Documentation/rust/quick-start.rst b/Documentation/rust/quick-start.rst
index f382914f4191..cc3f11e0d441 100644
--- a/Documentation/rust/quick-start.rst
+++ b/Documentation/rust/quick-start.rst
@@ -33,14 +33,18 @@ A particular version of the Rust compiler is required. Newer versions may or
 may not work because, for the moment, the kernel depends on some unstable
 Rust features.
 
-If ``rustup`` is being used, enter the checked out source code directory
-and run::
+If ``rustup`` is being used, enter the kernel build directory (or use
+``--path=<build-dir>`` argument to the ``set`` sub-command) and run::
 
 	rustup override set $(scripts/min-tool-version.sh rustc)
 
 This will configure your working directory to use the correct version of
-``rustc`` without affecting your default toolchain. If you are not using
-``rustup``, fetch a standalone installer from:
+``rustc`` without affecting your default toolchain.
+
+Note that the override applies to the current working directory (and its
+sub-directories).
+
+If you are not using ``rustup``, fetch a standalone installer from:
 
 	https://forge.rust-lang.org/infra/other-installation-methods.html#standalone
 
@@ -76,7 +80,7 @@ libclang
 
 ``libclang`` (part of LLVM) is used by ``bindgen`` to understand the C code
 in the kernel, which means LLVM needs to be installed; like when the kernel
-is compiled with ``CC=clang`` or ``LLVM=1``.
+is compiled with ``LLVM=1``.
 
 Linux distributions are likely to have a suitable one available, so it is
 best to check that first.
@@ -229,10 +233,6 @@ at the moment. That is::
 
 	make LLVM=1
 
-For architectures that do not support a full LLVM toolchain, use::
-
-	make CC=clang
-
 Using GCC also works for some configurations, but it is very experimental at
 the moment.
 
diff --git a/Documentation/scheduler/sched-design-CFS.rst b/Documentation/scheduler/sched-design-CFS.rst
index f68919800f05..6cffffe26500 100644
--- a/Documentation/scheduler/sched-design-CFS.rst
+++ b/Documentation/scheduler/sched-design-CFS.rst
@@ -180,7 +180,7 @@ This is the (partial) list of the hooks:
    compat_yield sysctl is turned on; in that case, it places the scheduling
    entity at the right-most end of the red-black tree.
 
- - check_preempt_curr(...)
+ - wakeup_preempt(...)
 
    This function checks if a task that entered the runnable state should
    preempt the currently running task.
@@ -189,10 +189,10 @@ This is the (partial) list of the hooks:
 
    This function chooses the most appropriate task eligible to run next.
 
- - set_curr_task(...)
+ - set_next_task(...)
 
-   This function is called when a task changes its scheduling class or changes
-   its task group.
+   This function is called when a task changes its scheduling class, changes
+   its task group or is scheduled.
 
  - task_tick(...)
 
diff --git a/Documentation/scheduler/schedutil.rst b/Documentation/scheduler/schedutil.rst
index 32c7d69fc86c..803fba8fc714 100644
--- a/Documentation/scheduler/schedutil.rst
+++ b/Documentation/scheduler/schedutil.rst
@@ -90,8 +90,8 @@ For more detail see:
  - Documentation/scheduler/sched-capacity.rst:"1. CPU Capacity + 2. Task utilization"
 
 
-UTIL_EST / UTIL_EST_FASTUP
-==========================
+UTIL_EST
+========
 
 Because periodic tasks have their averages decayed while they sleep, even
 though when running their expected utilization will be the same, they suffer a
@@ -99,8 +99,7 @@ though when running their expected utilization will be the same, they suffer a
 
 To alleviate this (a default enabled option) UTIL_EST drives an Infinite
 Impulse Response (IIR) EWMA with the 'running' value on dequeue -- when it is
-highest. A further default enabled option UTIL_EST_FASTUP modifies the IIR
-filter to instantly increase and only decay on decrease.
+highest. UTIL_EST filters to instantly increase and only decay on decrease.
 
 A further runqueue wide sum (of runnable tasks) is maintained of:
 
diff --git a/Documentation/sphinx/requirements.txt b/Documentation/sphinx/requirements.txt
index 335b53df35e2..a8a1aff6445e 100644
--- a/Documentation/sphinx/requirements.txt
+++ b/Documentation/sphinx/requirements.txt
@@ -1,3 +1,4 @@
 # jinja2>=3.1 is not compatible with Sphinx<4.0
 jinja2<3.1
 Sphinx==2.4.4
+pyyaml
diff --git a/Documentation/spi/pxa2xx.rst b/Documentation/spi/pxa2xx.rst
index 04f2a3856c40..19479b801826 100644
--- a/Documentation/spi/pxa2xx.rst
+++ b/Documentation/spi/pxa2xx.rst
@@ -3,13 +3,13 @@ PXA2xx SPI on SSP driver HOWTO
 ==============================
 
 This a mini HOWTO on the pxa2xx_spi driver. The driver turns a PXA2xx
-synchronous serial port into an SPI master controller
+synchronous serial port into an SPI host controller
 (see Documentation/spi/spi-summary.rst). The driver has the following features
 
 - Support for any PXA2xx and compatible SSP.
 - SSP PIO and SSP DMA data transfers.
 - External and Internal (SSPFRM) chip selects.
-- Per slave device (chip) configuration.
+- Per peripheral device (chip) configuration.
 - Full suspend, freeze, resume support.
 
 The driver is built around a &struct spi_message FIFO serviced by kernel
@@ -17,10 +17,10 @@ thread. The kernel thread, spi_pump_messages(), drives message FIFO and
 is responsible for queuing SPI transactions and setting up and launching
 the DMA or interrupt driven transfers.
 
-Declaring PXA2xx Master Controllers
------------------------------------
-Typically, for a legacy platform, an SPI master is defined in the
-arch/.../mach-*/board-*.c as a "platform device". The master configuration
+Declaring PXA2xx host controllers
+---------------------------------
+Typically, for a legacy platform, an SPI host controller is defined in the
+arch/.../mach-*/board-*.c as a "platform device". The host controller configuration
 is passed to the driver via a table found in include/linux/spi/pxa2xx_spi.h::
 
   struct pxa2xx_spi_controller {
@@ -30,7 +30,7 @@ is passed to the driver via a table found in include/linux/spi/pxa2xx_spi.h::
   };
 
 The "pxa2xx_spi_controller.num_chipselect" field is used to determine the number of
-slave device (chips) attached to this SPI master.
+peripheral devices (chips) attached to this SPI host controller.
 
 The "pxa2xx_spi_controller.enable_dma" field informs the driver that SSP DMA should
 be used. This caused the driver to acquire two DMA channels: Rx channel and
@@ -40,8 +40,8 @@ See the "PXA2xx Developer Manual" section "DMA Controller".
 For the new platforms the description of the controller and peripheral devices
 comes from Device Tree or ACPI.
 
-NSSP MASTER SAMPLE
-------------------
+NSSP HOST SAMPLE
+----------------
 Below is a sample configuration using the PXA255 NSSP for a legacy platform::
 
   static struct resource pxa_spi_nssp_resources[] = {
@@ -57,7 +57,7 @@ Below is a sample configuration using the PXA255 NSSP for a legacy platform::
 	},
   };
 
-  static struct pxa2xx_spi_controller pxa_nssp_master_info = {
+  static struct pxa2xx_spi_controller pxa_nssp_controller_info = {
 	.num_chipselect = 1, /* Matches the number of chips attached to NSSP */
 	.enable_dma = 1, /* Enables NSSP DMA */
   };
@@ -68,7 +68,7 @@ Below is a sample configuration using the PXA255 NSSP for a legacy platform::
 	.resource = pxa_spi_nssp_resources,
 	.num_resources = ARRAY_SIZE(pxa_spi_nssp_resources),
 	.dev = {
-		.platform_data = &pxa_nssp_master_info, /* Passed to driver */
+		.platform_data = &pxa_nssp_controller_info, /* Passed to driver */
 	},
   };
 
@@ -81,17 +81,17 @@ Below is a sample configuration using the PXA255 NSSP for a legacy platform::
 	(void)platform_add_device(devices, ARRAY_SIZE(devices));
   }
 
-Declaring Slave Devices
------------------------
-Typically, for a legacy platform, each SPI slave (chip) is defined in the
+Declaring peripheral devices
+----------------------------
+Typically, for a legacy platform, each SPI peripheral device (chip) is defined in the
 arch/.../mach-*/board-*.c using the "spi_board_info" structure found in
 "linux/spi/spi.h". See "Documentation/spi/spi-summary.rst" for additional
 information.
 
-Each slave device attached to the PXA must provide slave specific configuration
+Each peripheral device (chip) attached to the PXA2xx must provide specific chip configuration
 information via the structure "pxa2xx_spi_chip" found in
-"include/linux/spi/pxa2xx_spi.h".  The pxa2xx_spi master controller driver
-will uses the configuration whenever the driver communicates with the slave
+"include/linux/spi/pxa2xx_spi.h". The PXA2xx host controller driver will use
+the configuration whenever the driver communicates with the peripheral
 device. All fields are optional.
 
 ::
@@ -123,7 +123,7 @@ dma_burst_size == 0.
 The "pxa2xx_spi_chip.timeout" fields is used to efficiently handle
 trailing bytes in the SSP receiver FIFO. The correct value for this field is
 dependent on the SPI bus speed ("spi_board_info.max_speed_hz") and the specific
-slave device.  Please note that the PXA2xx SSP 1 does not support trailing byte
+peripheral device. Please note that the PXA2xx SSP 1 does not support trailing byte
 timeouts and must busy-wait any trailing bytes.
 
 NOTE: the SPI driver cannot control the chip select if SSPFRM is used, so the
@@ -132,8 +132,8 @@ asserted around the complete message. Use SSPFRM as a GPIO (through a descriptor
 to accommodate these chips.
 
 
-NSSP SLAVE SAMPLE
------------------
+NSSP PERIPHERAL SAMPLE
+----------------------
 For a legacy platform or in some other cases, the pxa2xx_spi_chip structure
 is passed to the pxa2xx_spi driver in the "spi_board_info.controller_data"
 field. Below is a sample configuration using the PXA255 NSSP.
@@ -161,16 +161,16 @@ field. Below is a sample configuration using the PXA255 NSSP.
 		.bus_num = 2, /* Framework bus number */
 		.chip_select = 0, /* Framework chip select */
 		.platform_data = NULL; /* No spi_driver specific config */
-		.controller_data = &cs8415a_chip_info, /* Master chip config */
-		.irq = STREETRACER_APCI_IRQ, /* Slave device interrupt */
+		.controller_data = &cs8415a_chip_info, /* Host controller config */
+		.irq = STREETRACER_APCI_IRQ, /* Peripheral device interrupt */
 	},
 	{
 		.modalias = "cs8405a", /* Name of spi_driver for this device */
 		.max_speed_hz = 3686400, /* Run SSP as fast a possible */
 		.bus_num = 2, /* Framework bus number */
 		.chip_select = 1, /* Framework chip select */
-		.controller_data = &cs8405a_chip_info, /* Master chip config */
-		.irq = STREETRACER_APCI_IRQ, /* Slave device interrupt */
+		.controller_data = &cs8405a_chip_info, /* Host controller config */
+		.irq = STREETRACER_APCI_IRQ, /* Peripheral device interrupt */
 	},
   };
 
@@ -193,17 +193,14 @@ mode supports both coherent and stream based DMA mappings.
 The following logic is used to determine the type of I/O to be used on
 a per "spi_transfer" basis::
 
-  if !enable_dma then
-	always use PIO transfers
+  if spi_message.len > 65536 then
+	if spi_message.is_dma_mapped or rx_dma_buf != 0 or tx_dma_buf != 0 then
+		reject premapped transfers
 
-  if spi_message.len > 8191 then
 	print "rate limited" warning
 	use PIO transfers
 
-  if spi_message.is_dma_mapped and rx_dma_buf != 0 and tx_dma_buf != 0 then
-	use coherent DMA mode
-
-  if rx_buf and tx_buf are aligned on 8 byte boundary then
+  if enable_dma and the size is in the range [DMA burst size..65536] then
 	use streaming DMA mode
 
   otherwise
diff --git a/Documentation/trace/coresight/coresight.rst b/Documentation/trace/coresight/coresight.rst
index 4a71ea6cb390..826e59a698da 100644
--- a/Documentation/trace/coresight/coresight.rst
+++ b/Documentation/trace/coresight/coresight.rst
@@ -130,7 +130,7 @@ Misc:
 Device Tree Bindings
 --------------------
 
-See Documentation/devicetree/bindings/arm/arm,coresight-\*.yaml for details.
+See ``Documentation/devicetree/bindings/arm/arm,coresight-*.yaml`` for details.
 
 As of this writing drivers for ITM, STMs and CTIs are not provided but are
 expected to be added as the solution matures.
diff --git a/Documentation/translations/ja_JP/SubmitChecklist b/Documentation/translations/ja_JP/SubmitChecklist
index 4429447b0965..1759c6b452d6 100644
--- a/Documentation/translations/ja_JP/SubmitChecklist
+++ b/Documentation/translations/ja_JP/SubmitChecklist
@@ -56,8 +56,8 @@ Linux カー�ルパッ�投稿者���ェックリスト
 
  9: sparseを利用���ゃん���コード�ェックを������。
 
-10: 'make checkstack' � 'make namespacecheck' を利用���題�発見�れ�ら
-    修正������。'make checkstack' �明示的��題を示���ん���れ�
+10: 'make checkstack' を利用���題�発見�れ�ら修正������。
+    'make checkstack' �明示的��題を示���ん���れ�
     １��関数�512�イトより大��スタックを使���れ��修正���候補�
     �り��。
 
diff --git a/Documentation/translations/zh_CN/arch/loongarch/introduction.rst b/Documentation/translations/zh_CN/arch/loongarch/introduction.rst
index 59d6bf33050c..bf463c5a4c51 100644
--- a/Documentation/translations/zh_CN/arch/loongarch/introduction.rst
+++ b/Documentation/translations/zh_CN/arch/loongarch/introduction.rst
@@ -338,9 +338,9 @@ Loongson与LoongArch的开�者网站（软件与文档资�）：
 
 LoongArch指令集架构的文档：
 
-  https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.02-CN.pdf （中文版）
+  https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.10-CN.pdf （中文版）
 
-  https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.02-EN.pdf （英文版）
+  https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.10-EN.pdf （英文版）
 
 LoongArch的ELF psABI文档：
 
diff --git a/Documentation/translations/zh_CN/process/submit-checklist.rst b/Documentation/translations/zh_CN/process/submit-checklist.rst
index 3d6ee21c74ae..10536b74aeec 100644
--- a/Documentation/translations/zh_CN/process/submit-checklist.rst
+++ b/Documentation/translations/zh_CN/process/submit-checklist.rst
@@ -53,8 +53,7 @@ Linux内核补��交检查�
 9) 通过 sparse 清查。
    （�� Documentation/translations/zh_CN/dev-tools/sparse.rst ）
 
-10) 使用 ``make checkstack`` 和 ``make namespacecheck`` 并修�他们�现的任何
-    问题。
+10) 使用 ``make checkstack`` 并修�他们�现的任何问题。
 
     .. note::
 
diff --git a/Documentation/translations/zh_CN/scheduler/sched-design-CFS.rst b/Documentation/translations/zh_CN/scheduler/sched-design-CFS.rst
index 3076402406c4..abc6709ec3b2 100644
--- a/Documentation/translations/zh_CN/scheduler/sched-design-CFS.rst
+++ b/Documentation/translations/zh_CN/scheduler/sched-design-CFS.rst
@@ -80,7 +80,7 @@ p->se.vruntime。一旦p->se.vruntimeå�˜å¾—足够大，其它的任务将æˆ�为æ
 CFS使用纳秒粒度的计时，��赖于任何jiffies或HZ的细节。因此CFS并��之�的调度器那样
 有“时间片�的概念，也没有任何���的设计。唯一�调的�数（你需�打开CONFIG_SCHED_DEBUG）是：
 
-   /sys/kernel/debug/sched/min_granularity_ns
+   /sys/kernel/debug/sched/base_slice_ns
 
 它�以用�将调度器从“桌��模�（也就是低时延）调节为“�务器�（也就是高批处�）模�。
 它的默认设置是适�桌�的工作负载。SCHED_BATCH也被CFS调度器模�处�。
@@ -147,7 +147,7 @@ array）。
    这个函数的行为基本上是出队，紧接�入队，除�compat_yield sysctl被开�。在那�情况下，
    它将调度实体放在红黑树的最�端。
 
- - check_preempt_curr(...)
+ - wakeup_preempt(...)
 
    这个函数检查进入��行状�的任务能�抢�当�正在�行的任务。
 
@@ -155,9 +155,9 @@ array）。
 
    这个函数选择接下�最适��行的任务。
 
- - set_curr_task(...)
+ - set_next_task(...)
 
-   这个函数在任务改�调度类或改�任务组时被调用。
+   这个函数在任务改�调度类，改�任务组时，或者任务被调度时被调用。
 
  - task_tick(...)
 
diff --git a/Documentation/translations/zh_CN/scheduler/schedutil.rst b/Documentation/translations/zh_CN/scheduler/schedutil.rst
index d1ea68007520..7c8d87f21c42 100644
--- a/Documentation/translations/zh_CN/scheduler/schedutil.rst
+++ b/Documentation/translations/zh_CN/scheduler/schedutil.rst
@@ -89,16 +89,15 @@ r_cpu被定义为当�CPU的最高性能水平与系统中任何其它CPU的最
  - Documentation/translations/zh_CN/scheduler/sched-capacity.rst:"1. CPU Capacity + 2. Task utilization"
 
 
-UTIL_EST / UTIL_EST_FASTUP
-==========================
+UTIL_EST
+========
 
 由于周期性任务的平�数在�眠时会衰�，而在�行时其预期利用率会和�眠�相�，
 因此它们在�次�行�会�临（DVFS）的上涨。
 
 为了缓解这个问题，（一个默认使能的编译选项）UTIL_EST驱动一个无�脉冲�应
 （Infinite Impulse Response，IIR）的EWMA，“�行�值在出队时是最高的。
-�一个默认使能的编译选项UTIL_EST_FASTUP修改了IIR滤波器，使其�许立�增加，
-仅在利用率下�时衰�。
+UTIL_EST滤波使其在�到更高值时立刻增加，而�到低值时会缓慢衰�。
 
 进一步，�行队列的（��行任务的）利用率之和由下�计算：
 
diff --git a/Documentation/translations/zh_TW/process/submit-checklist.rst b/Documentation/translations/zh_TW/process/submit-checklist.rst
index e57ef0f99e0c..43f2e3c5b514 100644
--- a/Documentation/translations/zh_TW/process/submit-checklist.rst
+++ b/Documentation/translations/zh_TW/process/submit-checklist.rst
@@ -56,8 +56,7 @@ Linux內核補��交檢查單
 9) 通� sparse 清查。
    （�見 Documentation/translations/zh_CN/dev-tools/sparse.rst ）
 
-10) 使用 ``make checkstack`` 和 ``make namespacecheck`` 並修復他們發�的任何
-    �題。
+10) 使用 ``make checkstack`` 並修復他們發�的任何�題。
 
     .. note::
 
diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst
index 74bc0716432e..09f61bd2ac2e 100644
--- a/Documentation/userspace-api/index.rst
+++ b/Documentation/userspace-api/index.rst
@@ -30,6 +30,7 @@ place where this information is gathered.
    sysfs-platform_profile
    vduse
    futex2
+   lsm
    tee
    isapnp
    dcdbas
diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst
index 4ea5b837399a..d8b6cb1a3636 100644
--- a/Documentation/userspace-api/ioctl/ioctl-number.rst
+++ b/Documentation/userspace-api/ioctl/ioctl-number.rst
@@ -349,6 +349,10 @@ Code  Seq#    Include File                                           Comments
                                                                      <mailto:vgo@ratio.de>
 0xB1  00-1F                                                          PPPoX
                                                                      <mailto:mostrows@styx.uwaterloo.ca>
+0xB2  00     arch/powerpc/include/uapi/asm/papr-vpd.h                powerpc/pseries VPD API
+                                                                     <mailto:linuxppc-dev>
+0xB2  01-02  arch/powerpc/include/uapi/asm/papr-sysparm.h            powerpc/pseries system parameter API
+                                                                     <mailto:linuxppc-dev>
 0xB3  00     linux/mmc/ioctl.h
 0xB4  00-0F  linux/gpio.h                                            <mailto:linux-gpio@vger.kernel.org>
 0xB5  00-0F  uapi/linux/rpmsg.h                                      <mailto:linux-remoteproc@vger.kernel.org>
diff --git a/Documentation/userspace-api/lsm.rst b/Documentation/userspace-api/lsm.rst
new file mode 100644
index 000000000000..a76da373841b
--- /dev/null
+++ b/Documentation/userspace-api/lsm.rst
@@ -0,0 +1,73 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. Copyright (C) 2022 Casey Schaufler <casey@schaufler-ca.com>
+.. Copyright (C) 2022 Intel Corporation
+
+=====================================
+Linux Security Modules
+=====================================
+
+:Author: Casey Schaufler
+:Date: July 2023
+
+Linux security modules (LSM) provide a mechanism to implement
+additional access controls to the Linux security policies.
+
+The various security modules may support any of these attributes:
+
+``LSM_ATTR_CURRENT`` is the current, active security context of the
+process.
+The proc filesystem provides this value in ``/proc/self/attr/current``.
+This is supported by the SELinux, Smack and AppArmor security modules.
+Smack also provides this value in ``/proc/self/attr/smack/current``.
+AppArmor also provides this value in ``/proc/self/attr/apparmor/current``.
+
+``LSM_ATTR_EXEC`` is the security context of the process at the time the
+current image was executed.
+The proc filesystem provides this value in ``/proc/self/attr/exec``.
+This is supported by the SELinux and AppArmor security modules.
+AppArmor also provides this value in ``/proc/self/attr/apparmor/exec``.
+
+``LSM_ATTR_FSCREATE`` is the security context of the process used when
+creating file system objects.
+The proc filesystem provides this value in ``/proc/self/attr/fscreate``.
+This is supported by the SELinux security module.
+
+``LSM_ATTR_KEYCREATE`` is the security context of the process used when
+creating key objects.
+The proc filesystem provides this value in ``/proc/self/attr/keycreate``.
+This is supported by the SELinux security module.
+
+``LSM_ATTR_PREV`` is the security context of the process at the time the
+current security context was set.
+The proc filesystem provides this value in ``/proc/self/attr/prev``.
+This is supported by the SELinux and AppArmor security modules.
+AppArmor also provides this value in ``/proc/self/attr/apparmor/prev``.
+
+``LSM_ATTR_SOCKCREATE`` is the security context of the process used when
+creating socket objects.
+The proc filesystem provides this value in ``/proc/self/attr/sockcreate``.
+This is supported by the SELinux security module.
+
+Kernel interface
+================
+
+Set a security attribute of the current process
+-----------------------------------------------
+
+.. kernel-doc:: security/lsm_syscalls.c
+    :identifiers: sys_lsm_set_self_attr
+
+Get the specified security attributes of the current process
+------------------------------------------------------------
+
+.. kernel-doc:: security/lsm_syscalls.c
+    :identifiers: sys_lsm_get_self_attr
+
+.. kernel-doc:: security/lsm_syscalls.c
+    :identifiers: sys_lsm_list_modules
+
+Additional documentation
+========================
+
+* Documentation/security/lsm.rst
+* Documentation/security/lsm-development.rst
diff --git a/Documentation/userspace-api/netlink/index.rst b/Documentation/userspace-api/netlink/index.rst
index 62725dafbbdb..c1b6765cc963 100644
--- a/Documentation/userspace-api/netlink/index.rst
+++ b/Documentation/userspace-api/netlink/index.rst
@@ -16,4 +16,6 @@ Netlink documentation for users.
    genetlink-legacy
    netlink-raw
 
-See also :ref:`Documentation/core-api/netlink.rst <kernel_netlink>`.
+See also:
+ - :ref:`Documentation/core-api/netlink.rst <kernel_netlink>`
+ - :ref:`Documentation/networking/netlink_spec/index.rst <specs>`
diff --git a/Documentation/userspace-api/netlink/intro.rst b/Documentation/userspace-api/netlink/intro.rst
index 7b1d401210ef..aacffade8f84 100644
--- a/Documentation/userspace-api/netlink/intro.rst
+++ b/Documentation/userspace-api/netlink/intro.rst
@@ -234,6 +234,10 @@ ACK attributes may be present::
   | ** optionally extended ACK                 |
   ----------------------------------------------
 
+Note that some implementations may issue custom ``NLMSG_DONE`` messages
+in reply to ``do`` action requests. In that case the payload is
+implementation-specific and may also be absent.
+
 .. _res_fam:
 
 Resolving the Family ID
diff --git a/Documentation/userspace-api/netlink/netlink-raw.rst b/Documentation/userspace-api/netlink/netlink-raw.rst
index f07fb9b9c101..1e14f5f22b8e 100644
--- a/Documentation/userspace-api/netlink/netlink-raw.rst
+++ b/Documentation/userspace-api/netlink/netlink-raw.rst
@@ -14,7 +14,8 @@ Specification
 The netlink-raw schema extends the :doc:`genetlink-legacy <genetlink-legacy>`
 schema with properties that are needed to specify the protocol numbers and
 multicast IDs used by raw netlink families. See :ref:`classic_netlink` for more
-information.
+information. The raw netlink families also make use of type-specific
+sub-messages.
 
 Globals
 -------
@@ -56,3 +57,96 @@ group registration.
       -
         name: rtnlgrp-mctp-ifaddr
         value: 34
+
+Sub-messages
+------------
+
+Several raw netlink families such as
+:doc:`rt_link<../../networking/netlink_spec/rt_link>` and
+:doc:`tc<../../networking/netlink_spec/tc>` use attribute nesting as an
+abstraction to carry module specific information.
+
+Conceptually it looks as follows::
+
+    [OUTER NEST OR MESSAGE LEVEL]
+      [GENERIC ATTR 1]
+      [GENERIC ATTR 2]
+      [GENERIC ATTR 3]
+      [GENERIC ATTR - wrapper]
+        [MODULE SPECIFIC ATTR 1]
+        [MODULE SPECIFIC ATTR 2]
+
+The ``GENERIC ATTRs`` at the outer level are defined in the core (or rt_link or
+core TC), while specific drivers, TC classifiers, qdiscs etc. can carry their
+own information wrapped in the ``GENERIC ATTR - wrapper``. Even though the
+example above shows attributes nesting inside the wrapper, the modules generally
+have full freedom to define the format of the nest. In practice the payload of
+the wrapper attr has very similar characteristics to a netlink message. It may
+contain a fixed header / structure, netlink attributes, or both. Because of
+those shared characteristics we refer to the payload of the wrapper attribute as
+a sub-message.
+
+A sub-message attribute uses the value of another attribute as a selector key to
+choose the right sub-message format. For example if the following attribute has
+already been decoded:
+
+.. code-block:: json
+
+  { "kind": "gre" }
+
+and we encounter the following attribute spec:
+
+.. code-block:: yaml
+
+  -
+    name: data
+    type: sub-message
+    sub-message: linkinfo-data-msg
+    selector: kind
+
+Then we look for a sub-message definition called ``linkinfo-data-msg`` and use
+the value of the ``kind`` attribute i.e. ``gre`` as the key to choose the
+correct format for the sub-message:
+
+.. code-block:: yaml
+
+  sub-messages:
+    name: linkinfo-data-msg
+    formats:
+      -
+        value: bridge
+        attribute-set: linkinfo-bridge-attrs
+      -
+        value: gre
+        attribute-set: linkinfo-gre-attrs
+      -
+        value: geneve
+        attribute-set: linkinfo-geneve-attrs
+
+This would decode the attribute value as a sub-message with the attribute-set
+called ``linkinfo-gre-attrs`` as the attribute space.
+
+A sub-message can have an optional ``fixed-header`` followed by zero or more
+attributes from an ``attribute-set``. For example the following
+``tc-options-msg`` sub-message defines message formats that use a mixture of
+``fixed-header``, ``attribute-set`` or both together:
+
+.. code-block:: yaml
+
+  sub-messages:
+    -
+      name: tc-options-msg
+      formats:
+        -
+          value: bfifo
+          fixed-header: tc-fifo-qopt
+        -
+          value: cake
+          attribute-set: tc-cake-attrs
+        -
+          value: netem
+          fixed-header: tc-netem-qopt
+          attribute-set: tc-netem-attrs
+
+Note that a selector attribute must appear in a netlink message before any
+sub-message attributes that depend on it.
diff --git a/Documentation/userspace-api/netlink/specs.rst b/Documentation/userspace-api/netlink/specs.rst
index c1b951649113..1b50d97d8d7c 100644
--- a/Documentation/userspace-api/netlink/specs.rst
+++ b/Documentation/userspace-api/netlink/specs.rst
@@ -15,7 +15,7 @@ kernel headers directly.
 Internally kernel uses the YAML specs to generate:
 
  - the C uAPI header
- - documentation of the protocol as a ReST file
+ - documentation of the protocol as a ReST file - see :ref:`Documentation/networking/netlink_spec/index.rst <specs>`
  - policy tables for input attribute validation
  - operation tables
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 894fdcc201f5..c121b5212027 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -171,13 +171,10 @@ S:	Supported
 F:	drivers/soc/fujitsu/a64fx-diag.c
 
 A8293 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/a8293*
 
 AACRAID SCSI RAID DRIVER
@@ -576,23 +573,17 @@ F:	drivers/iio/accel/adxl372_i2c.c
 F:	drivers/iio/accel/adxl372_spi.c
 
 AF9013 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/af9013*
 
 AF9033 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/af9033*
 
 AFFS FILE SYSTEM
@@ -650,13 +641,10 @@ F:	fs/aio.c
 F:	include/linux/*aio*.h
 
 AIRSPY MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/airspy/
 
 ALACRITECH GIGABIT ETHERNET DRIVER
@@ -1943,7 +1931,6 @@ F:	drivers/i2c/busses/i2c-pasemi-platform.c
 F:	drivers/iommu/apple-dart.c
 F:	drivers/iommu/io-pgtable-dart.c
 F:	drivers/irqchip/irq-apple-aic.c
-F:	drivers/mailbox/apple-mailbox.c
 F:	drivers/nvme/host/apple.c
 F:	drivers/nvmem/apple-efuses.c
 F:	drivers/pinctrl/pinctrl-apple-gpio.c
@@ -1952,7 +1939,6 @@ F:	drivers/soc/apple/*
 F:	drivers/watchdog/apple_wdt.c
 F:	include/dt-bindings/interrupt-controller/apple-aic.h
 F:	include/dt-bindings/pinctrl/apple.h
-F:	include/linux/apple-mailbox.h
 F:	include/linux/soc/apple/*
 
 ARM/ARTPEC MACHINE SUPPORT
@@ -2029,11 +2015,6 @@ L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Odd Fixes
 N:	clps711x
 
-ARM/CIRRUS LOGIC EDB9315A MACHINE SUPPORT
-M:	Lennert Buytenhek <kernel@wantstofly.org>
-L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	Maintained
-
 ARM/CIRRUS LOGIC EP93XX ARM ARCHITECTURE
 M:	Hartley Sweeten <hsweeten@visionengravers.com>
 M:	Alexander Sverdlin <alexander.sverdlin@gmail.com>
@@ -2155,6 +2136,7 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git
 F:	arch/arm/boot/dts/nxp/imx/
 F:	arch/arm/boot/dts/nxp/mxs/
+F:	arch/arm64/boot/dts/freescale/
 X:	arch/arm64/boot/dts/freescale/fsl-*
 X:	arch/arm64/boot/dts/freescale/qoriq-*
 X:	drivers/media/i2c/
@@ -2318,6 +2300,7 @@ F:	arch/arm/mach-dove/
 F:	arch/arm/mach-mv78xx0/
 F:	arch/arm/mach-orion5x/
 F:	arch/arm/plat-orion/
+F:	drivers/bus/mvebu-mbus.c
 F:	drivers/soc/dove/
 
 ARM/Marvell Kirkwood and Armada 370, 375, 38x, 39x, XP, 3700, 7K/8K, CN9130 SOC support
@@ -2332,8 +2315,7 @@ F:	arch/arm/boot/dts/marvell/armada*
 F:	arch/arm/boot/dts/marvell/kirkwood*
 F:	arch/arm/configs/mvebu_*_defconfig
 F:	arch/arm/mach-mvebu/
-F:	arch/arm64/boot/dts/marvell/armada*
-F:	arch/arm64/boot/dts/marvell/cn913*
+F:	arch/arm64/boot/dts/marvell/
 F:	drivers/clk/mvebu/
 F:	drivers/cpufreq/armada-37xx-cpufreq.c
 F:	drivers/cpufreq/armada-8k-cpufreq.c
@@ -2405,7 +2387,6 @@ F:	drivers/memory/atmel*
 F:	drivers/watchdog/sama5d4_wdt.c
 F:	include/soc/at91/
 X:	drivers/input/touchscreen/atmel_mxt_ts.c
-X:	drivers/net/wireless/atmel/
 N:	at91
 N:	atmel
 
@@ -2535,7 +2516,7 @@ F:	drivers/*/*/*wpcm*
 F:	drivers/*/*wpcm*
 
 ARM/NXP S32G ARCHITECTURE
-M:	Chester Lin <clin@suse.com>
+M:	Chester Lin <chester62515@gmail.com>
 R:	Andreas Färber <afaerber@suse.de>
 R:	Matthias Brugger <mbrugger@suse.com>
 R:	NXP S32 Linux Team <s32@nxp.com>
@@ -2557,7 +2538,6 @@ F:	arch/arm64/boot/dts/qcom/sc7280*
 F:	arch/arm64/boot/dts/qcom/sdm845-cheza*
 
 ARM/QUALCOMM SUPPORT
-M:	Andy Gross <agross@kernel.org>
 M:	Bjorn Andersson <andersson@kernel.org>
 M:	Konrad Dybcio <konrad.dybcio@linaro.org>
 L:	linux-arm-msm@vger.kernel.org
@@ -2837,7 +2817,6 @@ F:	Documentation/devicetree/bindings/interrupt-controller/sunplus,sp7021-intc.ya
 F:	Documentation/devicetree/bindings/reset/sunplus,reset.yaml
 F:	arch/arm/boot/dts/sunplus/
 F:	arch/arm/configs/sp7021_*defconfig
-F:	arch/arm/mach-sunplus/
 F:	drivers/clk/clk-sp7021.c
 F:	drivers/irqchip/irq-sp7021-intc.c
 F:	drivers/reset/reset-sunplus.c
@@ -2853,11 +2832,6 @@ F:	arch/arm/boot/dts/synaptics/
 F:	arch/arm/mach-berlin/
 F:	arch/arm64/boot/dts/synaptics/
 
-ARM/TECHNOLOGIC SYSTEMS TS7250 MACHINE SUPPORT
-M:	Lennert Buytenhek <kernel@wantstofly.org>
-L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	Maintained
-
 ARM/TEGRA HDMI CEC SUBSYSTEM SUPPORT
 M:	Hans Verkuil <hverkuil-cisco@xs4all.nl>
 L:	linux-tegra@vger.kernel.org
@@ -2874,11 +2848,6 @@ L:	linux-samsung-soc@vger.kernel.org
 S:	Maintained
 F:	arch/arm64/boot/dts/tesla/
 
-ARM/TETON BGA MACHINE SUPPORT
-M:	"Mark F. Brown" <mark.brown314@gmail.com>
-L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	Maintained
-
 ARM/TEXAS INSTRUMENT AEMIF/EMIF DRIVERS
 M:	Santosh Shilimkar <ssantosh@kernel.org>
 L:	linux-kernel@vger.kernel.org
@@ -2957,7 +2926,6 @@ F:	Documentation/devicetree/bindings/pinctrl/socionext,uniphier-pinctrl.yaml
 F:	Documentation/devicetree/bindings/soc/socionext/socionext,uniphier*.yaml
 F:	arch/arm/boot/dts/socionext/uniphier*
 F:	arch/arm/include/asm/hardware/cache-uniphier.h
-F:	arch/arm/mach-uniphier/
 F:	arch/arm/mm/cache-uniphier.c
 F:	arch/arm64/boot/dts/socionext/uniphier*
 F:	drivers/bus/uniphier-system-bus.c
@@ -3020,6 +2988,7 @@ F:	Documentation/devicetree/bindings/i2c/cdns,i2c-r1p10.yaml
 F:	Documentation/devicetree/bindings/i2c/xlnx,xps-iic-2.00.a.yaml
 F:	Documentation/devicetree/bindings/memory-controllers/snps,dw-umctl2-ddrc.yaml
 F:	Documentation/devicetree/bindings/memory-controllers/xlnx,zynq-ddrc-a05.yaml
+F:	Documentation/devicetree/bindings/soc/xilinx/xilinx.yaml
 F:	Documentation/devicetree/bindings/spi/xlnx,zynq-qspi.yaml
 F:	arch/arm/mach-zynq/
 F:	drivers/clocksource/timer-cadence-ttc.c
@@ -3084,6 +3053,14 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/net/asix,ax88796c.yaml
 F:	drivers/net/ethernet/asix/ax88796c_*
 
+ASIX PHY DRIVER [RUST]
+M:	FUJITA Tomonori <fujita.tomonori@gmail.com>
+R:	Trevor Gross <tmgross@umich.edu>
+L:	netdev@vger.kernel.org
+L:	rust-for-linux@vger.kernel.org
+S:	Maintained
+F:	drivers/net/phy/ax88796b_rust.rs
+
 ASPEED CRYPTO DRIVER
 M:	Neal Liu <neal_liu@aspeedtech.com>
 L:	linux-aspeed@lists.ozlabs.org (moderated for non-subscribers)
@@ -3309,13 +3286,6 @@ T:	git git://github.com/ndyer/linux.git
 F:	Documentation/devicetree/bindings/input/atmel,maxtouch.yaml
 F:	drivers/input/touchscreen/atmel_mxt_ts.c
 
-ATMEL WIRELESS DRIVER
-L:	linux-wireless@vger.kernel.org
-S:	Orphan
-W:	http://www.thekelleys.org.uk/atmel
-W:	http://atmelwlandriver.sourceforge.net/
-F:	drivers/net/wireless/atmel/atmel*
-
 ATOMIC INFRASTRUCTURE
 M:	Will Deacon <will@kernel.org>
 M:	Peter Zijlstra <peterz@infradead.org>
@@ -3350,13 +3320,17 @@ M:	Eric Paris <eparis@redhat.com>
 L:	audit@vger.kernel.org
 S:	Supported
 W:	https://github.com/linux-audit
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/audit.git
+Q:	https://patchwork.kernel.org/project/audit/list
+B:	mailto:audit@vger.kernel.org
+P:	https://github.com/linux-audit/audit-kernel/blob/main/README.md
+T:	git https://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/audit.git
 F:	include/asm-generic/audit_*.h
 F:	include/linux/audit.h
 F:	include/linux/audit_arch.h
 F:	include/uapi/linux/audit.h
 F:	kernel/audit*
 F:	lib/*audit.c
+K:	\baudit_[a-z_0-9]\+\b
 
 AUXILIARY BUS DRIVER
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
@@ -3415,6 +3389,16 @@ W:	https://ez.analog.com/linux-software-drivers
 F:	Documentation/devicetree/bindings/hwmon/adi,axi-fan-control.yaml
 F:	drivers/hwmon/axi-fan-control.c
 
+AXI SPI ENGINE
+M:	Michael Hennerich <michael.hennerich@analog.com>
+M:	Nuno Sá <nuno.sa@analog.com>
+R:	David Lechner <dlechner@baylibre.com>
+L:	linux-spi@vger.kernel.org
+S:	Supported
+W:	https://ez.analog.com/linux-software-drivers
+F:	Documentation/devicetree/bindings/spi/adi,axi-spi-engine.yaml
+F:	drivers/spi/spi-axi-spi-engine.c
+
 AXXIA I2C CONTROLLER
 M:	Krzysztof Adamski <krzysztof.adamski@nokia.com>
 L:	linux-i2c@vger.kernel.org
@@ -3499,7 +3483,7 @@ F:	drivers/net/hamradio/baycom*
 
 BCACHE (BLOCK LAYER CACHE)
 M:	Coly Li <colyli@suse.de>
-M:	Kent Overstreet <kent.overstreet@gmail.com>
+M:	Kent Overstreet <kent.overstreet@linux.dev>
 L:	linux-bcache@vger.kernel.org
 S:	Maintained
 W:	http://bcache.evilpiepirate.org
@@ -4138,7 +4122,6 @@ M:	Franky Lin <franky.lin@broadcom.com>
 M:	Hante Meuleman <hante.meuleman@broadcom.com>
 L:	linux-wireless@vger.kernel.org
 L:	brcm80211-dev-list.pdl@broadcom.com
-L:	SHA-cyfmac-dev-list@infineon.com
 S:	Supported
 F:	drivers/net/wireless/broadcom/brcm80211/
 
@@ -5076,7 +5059,6 @@ CLANG CONTROL FLOW INTEGRITY SUPPORT
 M:	Sami Tolvanen <samitolvanen@google.com>
 M:	Kees Cook <keescook@chromium.org>
 R:	Nathan Chancellor <nathan@kernel.org>
-R:	Nick Desaulniers <ndesaulniers@google.com>
 L:	llvm@lists.linux.dev
 S:	Supported
 B:	https://github.com/ClangBuiltLinux/linux/issues
@@ -5091,8 +5073,9 @@ F:	.clang-format
 
 CLANG/LLVM BUILD SUPPORT
 M:	Nathan Chancellor <nathan@kernel.org>
-M:	Nick Desaulniers <ndesaulniers@google.com>
-R:	Tom Rix <trix@redhat.com>
+R:	Nick Desaulniers <ndesaulniers@google.com>
+R:	Bill Wendling <morbo@google.com>
+R:	Justin Stitt <justinstitt@google.com>
 L:	llvm@lists.linux.dev
 S:	Supported
 W:	https://clangbuiltlinux.github.io/
@@ -5242,7 +5225,6 @@ F:	drivers/platform/x86/compal-laptop.c
 
 COMPILER ATTRIBUTES
 M:	Miguel Ojeda <ojeda@kernel.org>
-R:	Nick Desaulniers <ndesaulniers@google.com>
 S:	Maintained
 F:	include/linux/compiler_attributes.h
 
@@ -5352,6 +5334,7 @@ L:	linux-mm@kvack.org
 S:	Maintained
 F:	mm/memcontrol.c
 F:	mm/swap_cgroup.c
+F:	samples/cgroup/*
 F:	tools/testing/selftests/cgroup/memcg_protection.m
 F:	tools/testing/selftests/cgroup/test_hugetlb_memcg.c
 F:	tools/testing/selftests/cgroup/test_kmem.c
@@ -5536,6 +5519,12 @@ F:	include/crypto/
 F:	include/linux/crypto*
 F:	lib/crypto/
 
+CRYPTO SPEED TEST COMPARE
+M:	Wang Jinchao <wangjinchao@xfusion.com>
+L:	linux-crypto@vger.kernel.org
+S:	Maintained
+F:	tools/crypto/tcrypt/tcrypt_speed_compare.py
+
 CRYPTOGRAPHIC RANDOM NUMBER GENERATOR
 M:	Neil Horman <nhorman@tuxdriver.com>
 L:	linux-crypto@vger.kernel.org
@@ -5605,13 +5594,10 @@ F:	Documentation/driver-api/media/drivers/cx88*
 F:	drivers/media/pci/cx88/
 
 CXD2820R MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/cxd2820r*
 
 CXGB3 ETHERNET DRIVER (CXGB3)
@@ -5724,13 +5710,10 @@ F:	Documentation/devicetree/bindings/input/cypress-sf.yaml
 F:	drivers/input/keyboard/cypress-sf.c
 
 CYPRESS_FIRMWARE MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/common/cypress_firmware*
 
 CYTTSP TOUCHSCREEN DRIVER
@@ -6068,10 +6051,8 @@ M:	Mikulas Patocka <mpatocka@redhat.com>
 M:	dm-devel@lists.linux.dev
 L:	dm-devel@lists.linux.dev
 S:	Maintained
-W:	http://sources.redhat.com/dm
 Q:	http://patchwork.kernel.org/project/dm-devel/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm.git
-T:	quilt http://people.redhat.com/agk/patches/linux/editing/
 F:	Documentation/admin-guide/device-mapper/
 F:	drivers/md/Kconfig
 F:	drivers/md/Makefile
@@ -6922,8 +6903,8 @@ T:	git git://anongit.freedesktop.org/drm/drm-misc
 F:	drivers/gpu/drm/vboxvideo/
 
 DRM DRIVER FOR VMWARE VIRTUAL GPU
-M:	Zack Rusin <zackr@vmware.com>
-R:	VMware Graphics Reviewers <linux-graphics-maintainer@vmware.com>
+M:	Zack Rusin <zack.rusin@broadcom.com>
+R:	Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
 L:	dri-devel@lists.freedesktop.org
 S:	Supported
 T:	git git://anongit.freedesktop.org/drm/drm-misc
@@ -7320,53 +7301,38 @@ T:	git git://linuxtv.org/media_tree.git
 F:	drivers/media/pci/dt3155/
 
 DVB_USB_AF9015 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/dvb-usb-v2/af9015*
 
 DVB_USB_AF9035 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/dvb-usb-v2/af9035*
 
 DVB_USB_ANYSEE MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/dvb-usb-v2/anysee*
 
 DVB_USB_AU6610 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/dvb-usb-v2/au6610*
 
 DVB_USB_CE6230 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/dvb-usb-v2/ce6230*
 
 DVB_USB_CXUSB MEDIA DRIVER
@@ -7380,22 +7346,17 @@ T:	git git://linuxtv.org/media_tree.git
 F:	drivers/media/usb/dvb-usb/cxusb*
 
 DVB_USB_EC168 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/dvb-usb-v2/ec168*
 
 DVB_USB_GL861 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/dvb-usb-v2/gl861*
 
 DVB_USB_MXL111SF MEDIA DRIVER
@@ -7409,23 +7370,18 @@ T:	git git://linuxtv.org/mkrufky/mxl111sf.git
 F:	drivers/media/usb/dvb-usb-v2/mxl111sf*
 
 DVB_USB_RTL28XXU MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/dvb-usb-v2/rtl28xxu*
 
 DVB_USB_V2 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/dvb-usb-v2/dvb_usb*
 F:	drivers/media/usb/dvb-usb-v2/usb_urb.c
 
@@ -7467,13 +7423,10 @@ F:	Documentation/devicetree/bindings/input/e3x0-button.txt
 F:	drivers/input/misc/e3x0-button.c
 
 E4000 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/tuners/e4000*
 
 EARTH_PT1 MEDIA DRIVER
@@ -7489,13 +7442,10 @@ S:	Odd Fixes
 F:	drivers/media/pci/pt3/
 
 EC100 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/ec100*
 
 ECRYPT FILE SYSTEM
@@ -7855,6 +7805,7 @@ R:	Yue Hu <huyue2@coolpad.com>
 R:	Jeffle Xu <jefflexu@linux.alibaba.com>
 L:	linux-erofs@lists.ozlabs.org
 S:	Maintained
+W:	https://erofs.docs.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs.git
 F:	Documentation/ABI/testing/sysfs-fs-erofs
 F:	Documentation/filesystems/erofs.rst
@@ -7929,6 +7880,14 @@ F:	include/uapi/linux/mdio.h
 F:	include/uapi/linux/mii.h
 F:	net/core/of_net.c
 
+ETHERNET PHY LIBRARY [RUST]
+M:	FUJITA Tomonori <fujita.tomonori@gmail.com>
+R:	Trevor Gross <tmgross@umich.edu>
+L:	netdev@vger.kernel.org
+L:	rust-for-linux@vger.kernel.org
+S:	Maintained
+F:	rust/kernel/net/phy.rs
+
 EXEC & BINFMT API
 R:	Eric Biederman <ebiederm@xmission.com>
 R:	Kees Cook <keescook@chromium.org>
@@ -7976,6 +7935,7 @@ F:	include/uapi/linux/ext4.h
 
 Extended Verification Module (EVM)
 M:	Mimi Zohar <zohar@linux.ibm.com>
+M:	Roberto Sassu <roberto.sassu@huawei.com>
 L:	linux-integrity@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/zohar/linux-integrity.git
@@ -8112,13 +8072,10 @@ F:	drivers/media/tuners/fc0011.c
 F:	drivers/media/tuners/fc0011.h
 
 FC2580 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/tuners/fc2580*
 
 FCOE SUBSYSTEM (libfc, libfcoe, fcoe)
@@ -8157,6 +8114,7 @@ F:	include/trace/events/fs_dax.h
 FILESYSTEMS (VFS and infrastructure)
 M:	Alexander Viro <viro@zeniv.linux.org.uk>
 M:	Christian Brauner <brauner@kernel.org>
+R:	Jan Kara <jack@suse.cz>
 L:	linux-fsdevel@vger.kernel.org
 S:	Maintained
 F:	fs/*
@@ -8177,6 +8135,16 @@ F:	fs/exportfs/
 F:	fs/fhandle.c
 F:	include/linux/exportfs.h
 
+FILESYSTEMS [IDMAPPED MOUNTS]
+M:	Christian Brauner <brauner@kernel.org>
+M:	Seth Forshee <sforshee@kernel.org>
+L:	linux-fsdevel@vger.kernel.org
+S:	Maintained
+F:	Documentation/filesystems/idmappings.rst
+F:	fs/mnt_idmapping.c
+F:	include/linux/mnt_idmapping.*
+F:	tools/testing/selftests/mount_setattr/
+
 FILESYSTEMS [IOMAP]
 M:	Christian Brauner <brauner@kernel.org>
 R:	Darrick J. Wong <djwong@kernel.org>
@@ -8186,6 +8154,15 @@ S:	Supported
 F:	fs/iomap/
 F:	include/linux/iomap.h
 
+FILESYSTEMS [STACKABLE]
+M:	Miklos Szeredi <miklos@szeredi.hu>
+M:	Amir Goldstein <amir73il@gmail.com>
+L:	linux-fsdevel@vger.kernel.org
+L:	linux-unionfs@vger.kernel.org
+S:	Maintained
+F:	fs/backing-file.c
+F:	include/linux/backing-file.h
+
 FINTEK F75375S HARDWARE MONITOR AND FAN CONTROLLER DRIVER
 M:	Riku Voipio <riku.voipio@iki.fi>
 L:	linux-hwmon@vger.kernel.org
@@ -8950,7 +8927,6 @@ S:	Maintained
 F:	scripts/get_maintainer.pl
 
 GFS2 FILE SYSTEM
-M:	Bob Peterson <rpeterso@redhat.com>
 M:	Andreas Gruenbacher <agruenba@redhat.com>
 L:	gfs2@lists.linux.dev
 S:	Supported
@@ -9006,6 +8982,16 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/chrome-platform/linux.git
 F:	drivers/firmware/google/
 
+GOOGLE TENSOR SoC SUPPORT
+M:	Peter Griffin <peter.griffin@linaro.org>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+L:	linux-samsung-soc@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/clock/google,gs101-clock.yaml
+F:	arch/arm64/boot/dts/exynos/google/
+F:	drivers/clk/samsung/clk-gs101.c
+F:	include/dt-bindings/clock/google,gs101.h
+
 GPD POCKET FAN DRIVER
 M:	Hans de Goede <hdegoede@redhat.com>
 L:	platform-driver-x86@vger.kernel.org
@@ -9045,7 +9031,7 @@ F:	drivers/gpio/gpio-mockup.c
 F:	tools/testing/selftests/gpio/
 
 GPIO REGMAP
-M:	Michael Walle <michael@walle.cc>
+M:	Michael Walle <mwalle@kernel.org>
 S:	Maintained
 F:	drivers/gpio/gpio-regmap.c
 F:	include/linux/gpio/regmap.h
@@ -9054,12 +9040,9 @@ K:	(devm_)?gpio_regmap_(un)?register
 GPIO SUBSYSTEM
 M:	Linus Walleij <linus.walleij@linaro.org>
 M:	Bartosz Golaszewski <brgl@bgdev.pl>
-R:	Andy Shevchenko <andy@kernel.org>
 L:	linux-gpio@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux.git
-F:	Documentation/ABI/obsolete/sysfs-gpio
-F:	Documentation/ABI/testing/gpio-cdev
 F:	Documentation/admin-guide/gpio/
 F:	Documentation/devicetree/bindings/gpio/
 F:	Documentation/driver-api/gpio/
@@ -9068,6 +9051,16 @@ F:	include/dt-bindings/gpio/
 F:	include/linux/gpio.h
 F:	include/linux/gpio/
 F:	include/linux/of_gpio.h
+
+GPIO UAPI
+M:	Bartosz Golaszewski <brgl@bgdev.pl>
+R:	Kent Gibson <warthog618@gmail.com>
+L:	linux-gpio@vger.kernel.org
+S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux.git
+F:	Documentation/ABI/obsolete/sysfs-gpio
+F:	Documentation/ABI/testing/gpio-cdev
+F:	drivers/gpio/gpiolib-cdev.c
 F:	include/uapi/linux/gpio.h
 F:	tools/gpio/
 
@@ -9249,13 +9242,10 @@ F:	include/trace/events/habanalabs.h
 F:	include/uapi/drm/habanalabs_accel.h
 
 HACKRF MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/hackrf/
 
 HANDSHAKE UPCALL FOR TRANSPORT LAYER SECURITY
@@ -9313,7 +9303,6 @@ F:	drivers/char/hw_random/
 F:	include/linux/hw_random.h
 
 HARDWARE SPINLOCK CORE
-M:	Ohad Ben-Cohen <ohad@wizery.com>
 M:	Bjorn Andersson <andersson@kernel.org>
 R:	Baolin Wang <baolin.wang7@gmail.com>
 L:	linux-remoteproc@vger.kernel.org
@@ -9542,6 +9531,7 @@ F:	Documentation/devicetree/bindings/gpio/hisilicon,ascend910-gpio.yaml
 F:	drivers/gpio/gpio-hisi.c
 
 HISILICON HIGH PERFORMANCE RSA ENGINE DRIVER (HPRE)
+M:	Zhiqi Song <songzhiqi1@huawei.com>
 M:	Longfang Liu <liulongfang@huawei.com>
 L:	linux-crypto@vger.kernel.org
 S:	Maintained
@@ -9581,6 +9571,7 @@ F:	drivers/bus/hisi_lpc.c
 HISILICON NETWORK SUBSYSTEM 3 DRIVER (HNS3)
 M:	Yisen Zhuang <yisen.zhuang@huawei.com>
 M:	Salil Mehta <salil.mehta@huawei.com>
+M:	Jijie Shao <shaojijie@huawei.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 W:	http://www.hisilicon.com
@@ -9628,6 +9619,7 @@ F:	drivers/crypto/hisilicon/sgl.c
 F:	include/linux/hisi_acc_qm.h
 
 HISILICON ROCE DRIVER
+M:	Chengchang Tang <tangchengchang@huawei.com>
 M:	Junxian Huang <huangjunxian6@hisilicon.com>
 L:	linux-rdma@vger.kernel.org
 S:	Maintained
@@ -9642,7 +9634,6 @@ F:	Documentation/devicetree/bindings/scsi/hisilicon-sas.txt
 F:	drivers/scsi/hisi_sas/
 
 HISILICON SECURITY ENGINE V2 DRIVER (SEC2)
-M:	Kai Ye <yekai13@huawei.com>
 M:	Longfang Liu <liulongfang@huawei.com>
 L:	linux-crypto@vger.kernel.org
 S:	Maintained
@@ -9709,11 +9700,6 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/iio/pressure/honeywell,mprls0025pa.yaml
 F:	drivers/iio/pressure/mprls0025pa.c
 
-HOST AP DRIVER
-L:	linux-wireless@vger.kernel.org
-S:	Obsolete
-F:	drivers/net/wireless/intersil/hostap/
-
 HP BIOSCFG DRIVER
 M:	Jorge Lopez <jorge.lopez2@hp.com>
 L:	platform-driver-x86@vger.kernel.org
@@ -9816,7 +9802,6 @@ F:	Documentation/networking/device_drivers/ethernet/huawei/hinic.rst
 F:	drivers/net/ethernet/huawei/hinic/
 
 HUGETLB SUBSYSTEM
-M:	Mike Kravetz <mike.kravetz@oracle.com>
 M:	Muchun Song <muchun.song@linux.dev>
 L:	linux-mm@kvack.org
 S:	Maintained
@@ -9840,8 +9825,8 @@ T:	git git://linuxtv.org/media_tree.git
 F:	drivers/media/platform/st/sti/hva
 
 HWPOISON MEMORY FAILURE HANDLING
-M:	Naoya Horiguchi <naoya.horiguchi@nec.com>
-R:	Miaohe Lin <linmiaohe@huawei.com>
+M:	Miaohe Lin <linmiaohe@huawei.com>
+R:	Naoya Horiguchi <naoya.horiguchi@nec.com>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	mm/hwpoison-inject.c
@@ -10252,16 +10237,6 @@ S:	Maintained
 W:	https://github.com/o2genum/ideapad-slidebar
 F:	drivers/input/misc/ideapad_slidebar.c
 
-IDMAPPED MOUNTS
-M:	Christian Brauner <brauner@kernel.org>
-M:	Seth Forshee <sforshee@kernel.org>
-L:	linux-fsdevel@vger.kernel.org
-S:	Maintained
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping.git
-F:	Documentation/filesystems/idmappings.rst
-F:	include/linux/mnt_idmapping.*
-F:	tools/testing/selftests/mount_setattr/
-
 IDT VersaClock 5 CLOCK DRIVER
 M:	Luca Ceresoli <luca@lucaceresoli.net>
 S:	Maintained
@@ -10554,7 +10529,9 @@ F:	drivers/crypto/inside-secure/
 
 INTEGRITY MEASUREMENT ARCHITECTURE (IMA)
 M:	Mimi Zohar <zohar@linux.ibm.com>
+M:	Roberto Sassu <roberto.sassu@huawei.com>
 M:	Dmitry Kasatkin <dmitry.kasatkin@gmail.com>
+R:	Eric Snowberg <eric.snowberg@oracle.com>
 L:	linux-integrity@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/zohar/linux-integrity.git
@@ -10694,6 +10671,7 @@ F:	drivers/gpio/gpio-pch.c
 F:	drivers/gpio/gpio-sch.c
 F:	drivers/gpio/gpio-sodaville.c
 F:	drivers/gpio/gpio-tangier.c
+F:	drivers/gpio/gpio-tangier.h
 
 INTEL GVT-g DRIVERS (Intel GPU Virtualization)
 M:	Zhenyu Wang <zhenyuw@linux.intel.com>
@@ -10719,6 +10697,13 @@ S:	Supported
 Q:	https://patchwork.kernel.org/project/linux-dmaengine/list/
 F:	drivers/dma/ioat*
 
+INTEL IAA CRYPTO DRIVER
+M:	Tom Zanussi <tom.zanussi@linux.intel.com>
+L:	linux-crypto@vger.kernel.org
+S:	Supported
+F:	Documentation/driver-api/crypto/iaa/iaa-crypto.rst
+F:	drivers/crypto/intel/iaa/*
+
 INTEL IDLE DRIVER
 M:	Jacob Pan <jacob.jun.pan@linux.intel.com>
 M:	Len Brown <lenb@kernel.org>
@@ -11017,6 +11002,7 @@ F:	drivers/net/wireless/intel/iwlegacy/
 
 INTEL WIRELESS WIFI LINK (iwlwifi)
 M:	Gregory Greenman <gregory.greenman@intel.com>
+M:	Miri Korenblit <miriam.rachel.korenblit@intel.com>
 L:	linux-wireless@vger.kernel.org
 S:	Supported
 W:	https://wireless.wiki.kernel.org/en/users/drivers/iwlwifi
@@ -11025,7 +11011,6 @@ F:	drivers/net/wireless/intel/iwlwifi/
 
 INTEL WMI SLIM BOOTLOADER (SBL) FIRMWARE UPDATE DRIVER
 M:	Jithu Joseph <jithu.joseph@intel.com>
-R:	Maurice Ma <maurice.ma@intel.com>
 S:	Maintained
 W:	https://slimbootloader.github.io/security/firmware-update.html
 F:	drivers/platform/x86/intel/wmi/sbl-fw-update.c
@@ -11157,6 +11142,7 @@ L:	io-uring@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.dk/linux-block
 T:	git git://git.kernel.dk/liburing
+F:	include/linux/io_uring/
 F:	include/linux/io_uring.h
 F:	include/linux/io_uring_types.h
 F:	include/trace/events/io_uring.h
@@ -11329,13 +11315,10 @@ F:	Documentation/hwmon/it87.rst
 F:	drivers/hwmon/it87.c
 
 IT913X MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/tuners/it913x*
 
 ITE IT66121 HDMI BRIDGE DRIVER
@@ -11517,7 +11500,6 @@ F:	fs/autofs/
 KERNEL BUILD + files below scripts/ (unless maintained elsewhere)
 M:	Masahiro Yamada <masahiroy@kernel.org>
 R:	Nathan Chancellor <nathan@kernel.org>
-R:	Nick Desaulniers <ndesaulniers@google.com>
 R:	Nicolas Schier <nicolas@fjasle.eu>
 L:	linux-kbuild@vger.kernel.org
 S:	Maintained
@@ -11529,6 +11511,7 @@ F:	scripts/*vmlinux*
 F:	scripts/Kbuild*
 F:	scripts/Makefile*
 F:	scripts/basic/
+F:	scripts/clang-tools/
 F:	scripts/dummy-tools/
 F:	scripts/mk*
 F:	scripts/mod/
@@ -12028,6 +12011,14 @@ S:	Maintained
 F:	arch/mips/lantiq
 F:	drivers/soc/lantiq
 
+LANTIQ PEF2256 DRIVER
+M:	Herve Codina <herve.codina@bootlin.com>
+S:	Maintained
+F:	Documentation/devicetree/bindings/net/lantiq,pef2256.yaml
+F:	drivers/net/wan/framer/pef2256/
+F:	drivers/pinctrl/pinctrl-pef2256.c
+F:	include/linux/framer/pef2256.h
+
 LASI 53c700 driver for PARISC
 M:	"James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
 L:	linux-scsi@vger.kernel.org
@@ -12155,9 +12146,10 @@ F:	drivers/ata/sata_promise.*
 
 LIBATA SUBSYSTEM (Serial and Parallel ATA drivers)
 M:	Damien Le Moal <dlemoal@kernel.org>
+M:	Niklas Cassel <cassel@kernel.org>
 L:	linux-ide@vger.kernel.org
 S:	Maintained
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/libata.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/libata/linux.git
 F:	Documentation/ABI/testing/sysfs-ata
 F:	Documentation/devicetree/bindings/ata/
 F:	drivers/ata/
@@ -12209,6 +12201,13 @@ F:	include/linux/nd.h
 F:	include/uapi/linux/ndctl.h
 F:	tools/testing/nvdimm/
 
+LIBRARY CODE
+M:	Andrew Morton <akpm@linux-foundation.org>
+L:	linux-kernel@vger.kernel.org
+S:	Supported
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm.git mm-nonmm-unstable
+F:	lib/*
+
 LICENSES and SPDX stuff
 M:	Thomas Gleixner <tglx@linutronix.de>
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
@@ -12241,6 +12240,8 @@ LINUX FOR POWERPC (32-BIT AND 64-BIT)
 M:	Michael Ellerman <mpe@ellerman.id.au>
 R:	Nicholas Piggin <npiggin@gmail.com>
 R:	Christophe Leroy <christophe.leroy@csgroup.eu>
+R:	Aneesh Kumar K.V <aneesh.kumar@kernel.org>
+R:	Naveen N. Rao <naveen.n.rao@linux.ibm.com>
 L:	linuxppc-dev@lists.ozlabs.org
 S:	Supported
 W:	https://github.com/linuxppc/wiki/wiki
@@ -12286,21 +12287,21 @@ S:	Orphan
 F:	arch/powerpc/platforms/40x/
 F:	arch/powerpc/platforms/44x/
 
-LINUX FOR POWERPC EMBEDDED PPC83XX AND PPC85XX
+LINUX FOR POWERPC EMBEDDED PPC85XX
 M:	Scott Wood <oss@buserror.net>
 L:	linuxppc-dev@lists.ozlabs.org
 S:	Odd fixes
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/scottwood/linux.git
 F:	Documentation/devicetree/bindings/cache/freescale-l2cache.txt
 F:	Documentation/devicetree/bindings/powerpc/fsl/
-F:	arch/powerpc/platforms/83xx/
 F:	arch/powerpc/platforms/85xx/
 
-LINUX FOR POWERPC EMBEDDED PPC8XX
+LINUX FOR POWERPC EMBEDDED PPC8XX AND PPC83XX
 M:	Christophe Leroy <christophe.leroy@csgroup.eu>
 L:	linuxppc-dev@lists.ozlabs.org
 S:	Maintained
 F:	arch/powerpc/platforms/8xx/
+F:	arch/powerpc/platforms/83xx/
 
 LINUX KERNEL DUMP TEST MODULE (LKDTM)
 M:	Kees Cook <keescook@chromium.org>
@@ -12447,6 +12448,12 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/har
 F:	Documentation/admin-guide/LSM/LoadPin.rst
 F:	security/loadpin/
 
+LOCKDOWN SECURITY MODULE
+L:	linux-security-module@vger.kernel.org
+S:	Odd Fixes
+T:	git https://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/lsm.git
+F:	security/lockdown/
+
 LOCKING PRIMITIVES
 M:	Peter Zijlstra <peterz@infradead.org>
 M:	Ingo Molnar <mingo@redhat.com>
@@ -12458,7 +12465,7 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core
 F:	Documentation/locking/
 F:	arch/*/include/asm/spinlock*.h
-F:	include/linux/lockdep.h
+F:	include/linux/lockdep*.h
 F:	include/linux/mutex*.h
 F:	include/linux/rwlock*.h
 F:	include/linux/rwsem*.h
@@ -12688,13 +12695,10 @@ W:	http://www.tazenda.demon.co.uk/phil/linux-hp
 F:	arch/m68k/hp300/
 
 M88DS3103 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/m88ds3103*
 
 M88RS2000 MEDIA DRIVER
@@ -12786,7 +12790,8 @@ MARVELL 88E6XXX ETHERNET SWITCH FABRIC DRIVER
 M:	Andrew Lunn <andrew@lunn.ch>
 L:	netdev@vger.kernel.org
 S:	Maintained
-F:	Documentation/devicetree/bindings/net/dsa/marvell.txt
+F:	Documentation/devicetree/bindings/net/dsa/marvell,mv88e6060.yaml
+F:	Documentation/devicetree/bindings/net/dsa/marvell,mv88e6xxx.yaml
 F:	Documentation/networking/devlink/mv88e6xxx.rst
 F:	drivers/net/dsa/mv88e6xxx/
 F:	include/linux/dsa/mv88e6xxx.h
@@ -12869,7 +12874,7 @@ S:	Maintained
 F:	drivers/net/ethernet/marvell/mvneta.*
 
 MARVELL MVPP2 ETHERNET DRIVER
-M:	Marcin Wojtas <mw@semihalf.com>
+M:	Marcin Wojtas <marcin.s.wojtas@gmail.com>
 M:	Russell King <linux@armlinux.org.uk>
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -13779,7 +13784,6 @@ F:	drivers/net/ethernet/mellanox/mlxfw/
 MELLANOX HARDWARE PLATFORM SUPPORT
 M:	Hans de Goede <hdegoede@redhat.com>
 M:	Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
-M:	Mark Gross <markgross@kernel.org>
 M:	Vadim Pasternak <vadimp@nvidia.com>
 L:	platform-driver-x86@vger.kernel.org
 S:	Supported
@@ -14388,7 +14392,6 @@ F:	drivers/platform/surface/surface_gpe.c
 MICROSOFT SURFACE HARDWARE PLATFORM SUPPORT
 M:	Hans de Goede <hdegoede@redhat.com>
 M:	Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
-M:	Mark Gross <markgross@kernel.org>
 M:	Maximilian Luz <luzmaximilian@gmail.com>
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
@@ -14590,20 +14593,16 @@ F:	include/asm-generic/tlb.h
 F:	mm/mmu_gather.c
 
 MN88472 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 F:	drivers/media/dvb-frontends/mn88472*
 
 MN88473 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 F:	drivers/media/dvb-frontends/mn88473*
 
@@ -14691,23 +14690,17 @@ S:	Orphan
 F:	drivers/platform/x86/msi-wmi.c
 
 MSI001 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/tuners/msi001*
 
 MSI2500 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/msi2500/
 
 MSTAR INTERRUPT CONTROLLER DRIVER
@@ -14995,10 +14988,12 @@ M:	Jakub Kicinski <kuba@kernel.org>
 M:	Paolo Abeni <pabeni@redhat.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
+P:	Documentation/process/maintainer-netdev.rst
 Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
 F:	Documentation/devicetree/bindings/net/
+F:	Documentation/networking/net_cachelines/net_device.rst
 F:	drivers/connector/
 F:	drivers/net/
 F:	include/dt-bindings/net/
@@ -15046,6 +15041,7 @@ M:	Jakub Kicinski <kuba@kernel.org>
 M:	Paolo Abeni <pabeni@redhat.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
+P:	Documentation/process/maintainer-netdev.rst
 Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 B:	mailto:netdev@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
@@ -15053,9 +15049,11 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
 F:	Documentation/core-api/netlink.rst
 F:	Documentation/netlink/
 F:	Documentation/networking/
+F:	Documentation/networking/net_cachelines/
 F:	Documentation/process/maintainer-netdev.rst
 F:	Documentation/userspace-api/netlink/
 F:	include/linux/in.h
+F:	include/linux/indirect_call_wrapper.h
 F:	include/linux/net.h
 F:	include/linux/netdevice.h
 F:	include/net/
@@ -15068,6 +15066,7 @@ F:	lib/random32.c
 F:	net/
 F:	tools/net/
 F:	tools/testing/selftests/net/
+X:	net/9p/
 X:	net/bluetooth/
 
 NETWORKING [IPSEC]
@@ -15140,6 +15139,7 @@ K:	\bmdo_
 NETWORKING [MPTCP]
 M:	Matthieu Baerts <matttbe@kernel.org>
 M:	Mat Martineau <martineau@kernel.org>
+R:	Geliang Tang <geliang.tang@linux.dev>
 L:	netdev@vger.kernel.org
 L:	mptcp@lists.linux.dev
 S:	Maintained
@@ -15147,7 +15147,7 @@ W:	https://github.com/multipath-tcp/mptcp_net-next/wiki
 B:	https://github.com/multipath-tcp/mptcp_net-next/issues
 T:	git https://github.com/multipath-tcp/mptcp_net-next.git export-net
 T:	git https://github.com/multipath-tcp/mptcp_net-next.git export
-F:	Documentation/netlink/specs/mptcp.yaml
+F:	Documentation/netlink/specs/mptcp_pm.yaml
 F:	Documentation/networking/mptcp-sysctl.rst
 F:	include/net/mptcp.h
 F:	include/trace/events/mptcp.h
@@ -15160,6 +15160,7 @@ NETWORKING [TCP]
 M:	Eric Dumazet <edumazet@google.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
+F:	Documentation/networking/net_cachelines/tcp_sock.rst
 F:	include/linux/tcp.h
 F:	include/net/tcp.h
 F:	include/trace/events/tcp.h
@@ -15487,10 +15488,10 @@ F:	Documentation/devicetree/bindings/net/bluetooth/nxp,88w8987-bt.yaml
 F:	drivers/bluetooth/btnxpuart.c
 
 NXP C45 TJA11XX PHY DRIVER
-M:	Radu Pirea <radu-nicolae.pirea@oss.nxp.com>
+M:	Andrei Botila <andrei.botila@oss.nxp.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
-F:	drivers/net/phy/nxp-c45-tja11xx.c
+F:	drivers/net/phy/nxp-c45-tja11xx*
 
 NXP FSPI DRIVER
 M:	Han Xu <han.xu@nxp.com>
@@ -15758,9 +15759,8 @@ F:	Documentation/devicetree/bindings/gpio/ti,omap-gpio.yaml
 F:	drivers/gpio/gpio-omap.c
 
 OMAP HARDWARE SPINLOCK SUPPORT
-M:	Ohad Ben-Cohen <ohad@wizery.com>
 L:	linux-omap@vger.kernel.org
-S:	Maintained
+S:	Orphan
 F:	drivers/hwspinlock/omap_hwspinlock.c
 
 OMAP HS MMC SUPPORT
@@ -15860,6 +15860,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap.git
 F:	Documentation/devicetree/bindings/arm/ti/omap.yaml
 F:	arch/arm/configs/omap2plus_defconfig
 F:	arch/arm/mach-omap2/
+F:	drivers/bus/omap*.[ch]
 F:	drivers/bus/ti-sysc.c
 F:	drivers/gpio/gpio-tps65219.c
 F:	drivers/i2c/busses/i2c-omap.c
@@ -16191,7 +16192,7 @@ F:	include/dt-bindings/
 
 OPENCOMPUTE PTP CLOCK DRIVER
 M:	Jonathan Lemon <jonathan.lemon@gmail.com>
-M:	Vadim Fedorenko <vadfed@fb.com>
+M:	Vadim Fedorenko <vadfed@linux.dev>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/ptp/ptp_ocp.c
@@ -16269,13 +16270,6 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/hubcap/linux.git
 F:	Documentation/filesystems/orangefs.rst
 F:	fs/orangefs/
 
-ORINOCO DRIVER
-L:	linux-wireless@vger.kernel.org
-S:	Orphan
-W:	https://wireless.wiki.kernel.org/en/users/Drivers/orinoco
-W:	http://www.nongnu.org/orinoco/
-F:	drivers/net/wireless/intersil/orinoco/
-
 OV2659 OMNIVISION SENSOR DRIVER
 M:	"Lad, Prabhakar" <prabhakar.csengg@gmail.com>
 L:	linux-media@vger.kernel.org
@@ -16511,11 +16505,10 @@ F:	Documentation/devicetree/bindings/pci/pci-armada8k.txt
 F:	drivers/pci/controller/dwc/pcie-armada8k.c
 
 PCI DRIVER FOR CADENCE PCIE IP
-M:	Tom Joseph <tjoseph@cadence.com>
 L:	linux-pci@vger.kernel.org
-S:	Maintained
+S:	Orphan
 F:	Documentation/devicetree/bindings/pci/cdns,*
-F:	drivers/pci/controller/cadence/
+F:	drivers/pci/controller/cadence/*cadence*
 
 PCI DRIVER FOR FREESCALE LAYERSCAPE
 M:	Minghuan Lian <minghuan.Lian@nxp.com>
@@ -17422,7 +17415,7 @@ F:	tools/testing/selftests/proc/
 PROC SYSCTL
 M:	Luis Chamberlain <mcgrof@kernel.org>
 M:	Kees Cook <keescook@chromium.org>
-M:	Iurii Zaikin <yzaikin@google.com>
+M:	Joel Granados <j.granados@samsung.com>
 L:	linux-kernel@vger.kernel.org
 L:	linux-fsdevel@vger.kernel.org
 S:	Maintained
@@ -17775,13 +17768,10 @@ F:	drivers/bus/fsl-mc/
 F:	include/uapi/linux/fsl_mc.h
 
 QT1010 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/tuners/qt1010*
 
 QUALCOMM ATH12K WIRELESS DRIVER
@@ -17948,6 +17938,8 @@ L:	iommu@lists.linux.dev
 L:	linux-arm-msm@vger.kernel.org
 S:	Maintained
 F:	drivers/iommu/arm/arm-smmu/qcom_iommu.c
+F:	drivers/iommu/arm/arm-smmu/arm-smmu-qcom*
+F:	drivers/iommu/msm_iommu*
 
 QUALCOMM IPC ROUTER (QRTR) DRIVER
 M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
@@ -18169,11 +18161,6 @@ F:	drivers/ras/
 F:	include/linux/ras.h
 F:	include/ras/ras_event.h
 
-RAYLINK/WEBGEAR 802.11 WIRELESS LAN DRIVER
-L:	linux-wireless@vger.kernel.org
-S:	Orphan
-F:	drivers/net/wireless/legacy/ray*
-
 RC-CORE / LIRC FRAMEWORK
 M:	Sean Young <sean@mess.org>
 L:	linux-media@vger.kernel.org
@@ -18641,6 +18628,7 @@ F:	Documentation/devicetree/bindings/usb/microchip,mpfs-musb.yaml
 F:	arch/riscv/boot/dts/microchip/
 F:	drivers/char/hw_random/mpfs-rng.c
 F:	drivers/clk/microchip/clk-mpfs*.c
+F:	drivers/firmware/microchip/mpfs-auto-update.c
 F:	drivers/i2c/busses/i2c-microchip-corei2c.c
 F:	drivers/mailbox/mailbox-mpfs.c
 F:	drivers/pci/controller/pcie-microchip-host.c
@@ -18834,33 +18822,24 @@ S:	Maintained
 F:	drivers/tty/rpmsg_tty.c
 
 RTL2830 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/rtl2830*
 
 RTL2832 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/rtl2832*
 
 RTL2832_SDR MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/rtl2832_sdr*
 
 RTL8180 WIRELESS DRIVER
@@ -19507,22 +19486,29 @@ SECURITY SUBSYSTEM
 M:	Paul Moore <paul@paul-moore.com>
 M:	James Morris <jmorris@namei.org>
 M:	"Serge E. Hallyn" <serge@hallyn.com>
-L:	linux-security-module@vger.kernel.org (suggested Cc:)
+L:	linux-security-module@vger.kernel.org
 S:	Supported
-W:	http://kernsec.org/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/lsm.git
+Q:	https://patchwork.kernel.org/project/linux-security-module/list
+B:	mailto:linux-security-module@vger.kernel.org
+P:	https://github.com/LinuxSecurityModule/kernel/blob/main/README.md
+T:	git https://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/lsm.git
+F:	include/uapi/linux/lsm.h
 F:	security/
+F:	tools/testing/selftests/lsm/
 X:	security/selinux/
+K:	\bsecurity_[a-z_0-9]\+\b
 
 SELINUX SECURITY MODULE
 M:	Paul Moore <paul@paul-moore.com>
 M:	Stephen Smalley <stephen.smalley.work@gmail.com>
-M:	Eric Paris <eparis@parisplace.org>
+R:	Ondrej Mosnacek <omosnace@redhat.com>
 L:	selinux@vger.kernel.org
 S:	Supported
-W:	https://selinuxproject.org
 W:	https://github.com/SELinuxProject
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/selinux.git
+Q:	https://patchwork.kernel.org/project/selinux/list
+B:	mailto:selinux@vger.kernel.org
+P:	https://github.com/SELinuxProject/selinux-kernel/blob/main/README.md
+T:	git https://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/selinux.git
 F:	Documentation/ABI/removed/sysfs-selinux-checkreqprot
 F:	Documentation/ABI/removed/sysfs-selinux-disable
 F:	Documentation/admin-guide/LSM/SELinux.rst
@@ -19637,7 +19623,6 @@ S:	Maintained
 F:	drivers/misc/sgi-xp/
 
 SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS
-M:	Karsten Graul <kgraul@linux.ibm.com>
 M:	Wenjia Zhang <wenjia@linux.ibm.com>
 M:	Jan Karcher <jaka@linux.ibm.com>
 R:	D. Wythe <alibuda@linux.alibaba.com>
@@ -19670,13 +19655,10 @@ F:	drivers/media/platform/renesas/sh_vou.c
 F:	include/media/drv-intf/sh_vou.h
 
 SI2157 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/tuners/si2157*
 
 SI2165 MEDIA DRIVER
@@ -19688,13 +19670,10 @@ Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 F:	drivers/media/dvb-frontends/si2165*
 
 SI2168 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/si2168*
 
 SI470X FM RADIO RECEIVER I2C DRIVER
@@ -19785,6 +19764,13 @@ S:	Supported
 N:	sifive
 K:	[^@]sifive
 
+SIFIVE CACHE DRIVER
+M:	Conor Dooley <conor@kernel.org>
+L:	linux-riscv@lists.infradead.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/cache/sifive,ccache0.yaml
+F:	drivers/cache/sifive_ccache.c
+
 SIFIVE FU540 SYSTEM-ON-CHIP
 M:	Paul Walmsley <paul.walmsley@sifive.com>
 M:	Palmer Dabbelt <palmer@dabbelt.com>
@@ -19800,13 +19786,6 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml
 F:	drivers/dma/sf-pdma/
 
-SIFIVE SOC DRIVERS
-M:	Conor Dooley <conor@kernel.org>
-L:	linux-riscv@lists.infradead.org
-S:	Maintained
-T:	git https://git.kernel.org/pub/scm/linux/kernel/git/conor/linux.git/
-F:	Documentation/devicetree/bindings/cache/sifive,ccache0.yaml
-F:	drivers/soc/sifive/
 
 SILEAD TOUCHSCREEN DRIVER
 M:	Hans de Goede <hdegoede@redhat.com>
@@ -19847,11 +19826,6 @@ F:	Documentation/devicetree/bindings/display/simple-framebuffer.yaml
 F:	drivers/video/fbdev/simplefb.c
 F:	include/linux/platform_data/simplefb.h
 
-SIMTEC EB110ATX (Chalice CATS)
-M:	Simtec Linux Team <linux@simtec.co.uk>
-S:	Supported
-W:	http://www.simtec.co.uk/products/EB110ATX/
-
 SIOX
 M:	Thorsten Scherer <t.scherer@eckelmann.de>
 M:	Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
@@ -19901,7 +19875,7 @@ W:	http://www.winischhofer.at/linuxsisusbvga.shtml
 F:	drivers/usb/misc/sisusbvga/
 
 SL28 CPLD MFD DRIVER
-M:	Michael Walle <michael@walle.cc>
+M:	Michael Walle <mwalle@kernel.org>
 S:	Maintained
 F:	Documentation/devicetree/bindings/gpio/kontron,sl28cpld-gpio.yaml
 F:	Documentation/devicetree/bindings/hwmon/kontron,sl28cpld-hwmon.yaml
@@ -19916,7 +19890,7 @@ F:	drivers/pwm/pwm-sl28cpld.c
 F:	drivers/watchdog/sl28cpld_wdt.c
 
 SL28 VPD NVMEM LAYOUT DRIVER
-M:	Michael Walle <michael@walle.cc>
+M:	Michael Walle <mwalle@kernel.org>
 S:	Maintained
 F:	Documentation/devicetree/bindings/nvmem/layouts/kontron,sl28-vpd.yaml
 F:	drivers/nvmem/layouts/sl28vpd.c
@@ -20106,6 +20080,7 @@ F:	include/linux/property.h
 
 SOFTWARE RAID (Multiple Disks) SUPPORT
 M:	Song Liu <song@kernel.org>
+R:	Yu Kuai <yukuai3@huawei.com>
 L:	linux-raid@vger.kernel.org
 S:	Supported
 Q:	https://patchwork.kernel.org/project/linux-raid/list/
@@ -20427,7 +20402,7 @@ F:	drivers/pinctrl/spear/
 SPI NOR SUBSYSTEM
 M:	Tudor Ambarus <tudor.ambarus@linaro.org>
 M:	Pratyush Yadav <pratyush@kernel.org>
-R:	Michael Walle <michael@walle.cc>
+M:	Michael Walle <mwalle@kernel.org>
 L:	linux-mtd@lists.infradead.org
 S:	Maintained
 W:	http://www.linux-mtd.infradead.org/
@@ -21091,6 +21066,13 @@ L:	linux-mmc@vger.kernel.org
 S:	Maintained
 F:	drivers/mmc/host/dw_mmc*
 
+SYNOPSYS DESIGNWARE PCIE PMU DRIVER
+M:	Shuai Xue <xueshuai@linux.alibaba.com>
+M:	Jing Zhang <renyu.zj@linux.alibaba.com>
+S:	Supported
+F:	Documentation/admin-guide/perf/dwc_pcie_pmu.rst
+F:	drivers/perf/dwc_pcie_pmu.c
+
 SYNOPSYS HSDK RESET CONTROLLER DRIVER
 M:	Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
 S:	Supported
@@ -21197,33 +21179,24 @@ W:	http://tcp-lp-mod.sourceforge.net/
 F:	net/ipv4/tcp_lp.c
 
 TDA10071 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/tda10071*
 
 TDA18212 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/tuners/tda18212*
 
 TDA18218 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/tuners/tda18218*
 
 TDA18250 MEDIA DRIVER
@@ -21772,7 +21745,9 @@ F:	Documentation/devicetree/bindings/counter/ti-eqep.yaml
 F:	drivers/counter/ti-eqep.c
 
 TI ETHERNET SWITCH DRIVER (CPSW)
-R:	Grygorii Strashko <grygorii.strashko@ti.com>
+R:	Siddharth Vadapalli <s-vadapalli@ti.com>
+R:	Ravi Gunasekaran <r-gunasekaran@ti.com>
+R:	Roger Quadros <rogerq@kernel.org>
 L:	linux-omap@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -21796,6 +21771,15 @@ F:	Documentation/devicetree/bindings/media/i2c/ti,ds90*
 F:	drivers/media/i2c/ds90*
 F:	include/media/i2c/ds90*
 
+TI ICSSG ETHERNET DRIVER (ICSSG)
+R:	MD Danish Anwar <danishanwar@ti.com>
+R:	Roger Quadros <rogerq@kernel.org>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/net/ti,icss*.yaml
+F:	drivers/net/ethernet/ti/icssg/*
+
 TI J721E CSI2RX DRIVER
 M:	Jai Luthra <j-luthra@ti.com>
 L:	linux-media@vger.kernel.org
@@ -22071,6 +22055,7 @@ F:	drivers/watchdog/tqmx86_wdt.c
 TRACING
 M:	Steven Rostedt <rostedt@goodmis.org>
 M:	Masami Hiramatsu <mhiramat@kernel.org>
+R:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
 L:	linux-kernel@vger.kernel.org
 L:	linux-trace-kernel@vger.kernel.org
 S:	Maintained
@@ -22149,13 +22134,10 @@ F:	include/uapi/linux/serial_core.h
 F:	include/uapi/linux/tty.h
 
 TUA9001 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/tuners/tua9001*
 
 TULIP NETWORK DRIVERS
@@ -22299,7 +22281,7 @@ F:	drivers/usb/common/ulpi.c
 F:	include/linux/ulpi/
 
 UNICODE SUBSYSTEM
-M:	Gabriel Krisman Bertazi <krisman@collabora.com>
+M:	Gabriel Krisman Bertazi <krisman@kernel.org>
 L:	linux-fsdevel@vger.kernel.org
 S:	Supported
 F:	fs/unicode/
@@ -22341,7 +22323,8 @@ S:	Maintained
 F:	drivers/ufs/host/ufs-exynos*
 
 UNIVERSAL FLASH STORAGE HOST CONTROLLER DRIVER MEDIATEK HOOKS
-M:	Stanley Chu <stanley.chu@mediatek.com>
+M:	Peter Wang <peter.wang@mediatek.com>
+R:	Stanley Jhu <chu.stanley@gmail.com>
 L:	linux-scsi@vger.kernel.org
 L:	linux-mediatek@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
@@ -22672,11 +22655,6 @@ F:	drivers/usb/gadget/function/*uvc*
 F:	drivers/usb/gadget/legacy/webcam.c
 F:	include/uapi/linux/usb/g_uvc.h
 
-USB WIRELESS RNDIS DRIVER (rndis_wlan)
-L:	linux-wireless@vger.kernel.org
-S:	Orphan
-F:	drivers/net/wireless/legacy/rndis_wlan.c
-
 USB XHCI DRIVER
 M:	Mathias Nyman <mathias.nyman@intel.com>
 L:	linux-usb@vger.kernel.org
@@ -22684,12 +22662,6 @@ S:	Supported
 F:	drivers/usb/host/pci-quirks*
 F:	drivers/usb/host/xhci*
 
-USB ZD1201 DRIVER
-L:	linux-wireless@vger.kernel.org
-S:	Orphan
-W:	http://linux-lc100020.sourceforge.net
-F:	drivers/net/wireless/zydas/zd1201.*
-
 USER DATAGRAM PROTOCOL (UDP)
 M:	Willem de Bruijn <willemdebruijn.kernel@gmail.com>
 S:	Maintained
@@ -23289,9 +23261,8 @@ F:	drivers/misc/vmw_vmci/
 F:	include/linux/vmw_vmci*
 
 VMWARE VMMOUSE SUBDRIVER
-M:	Zack Rusin <zackr@vmware.com>
-R:	VMware Graphics Reviewers <linux-graphics-maintainer@vmware.com>
-R:	VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
+M:	Zack Rusin <zack.rusin@broadcom.com>
+R:	Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
 L:	linux-input@vger.kernel.org
 S:	Supported
 F:	drivers/input/mouse/vmmouse.c
@@ -23491,11 +23462,6 @@ M:	Miloslav Trmac <mitr@volny.cz>
 S:	Maintained
 F:	drivers/input/misc/wistron_btns.c
 
-WL3501 WIRELESS PCMCIA CARD DRIVER
-L:	linux-wireless@vger.kernel.org
-S:	Orphan
-F:	drivers/net/wireless/legacy/wl3501*
-
 WMI BINARY MOF DRIVER
 M:	Armin Wolf <W_Armin@gmx.de>
 R:	Thomas Weißschuh <linux@weissschuh.net>
@@ -23657,7 +23623,6 @@ F:	drivers/platform/x86/x86-android-tablets/
 X86 PLATFORM DRIVERS
 M:	Hans de Goede <hdegoede@redhat.com>
 M:	Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
-M:	Mark Gross <markgross@kernel.org>
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
 Q:	https://patchwork.kernel.org/project/platform-driver-x86/list/
@@ -23666,15 +23631,6 @@ F:	drivers/platform/olpc/
 F:	drivers/platform/x86/
 F:	include/linux/platform_data/x86/
 
-X86 PLATFORM DRIVERS - ARCH
-R:	Darren Hart <dvhart@infradead.org>
-R:	Andy Shevchenko <andy@infradead.org>
-L:	platform-driver-x86@vger.kernel.org
-L:	x86@kernel.org
-S:	Maintained
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/core
-F:	arch/x86/platform
-
 X86 PLATFORM UV HPE SUPERDOME FLEX
 M:	Steve Wahl <steve.wahl@hpe.com>
 R:	Justin Ernst <justin.ernst@hpe.com>
@@ -23695,6 +23651,20 @@ F:	arch/x86/kernel/dumpstack.c
 F:	arch/x86/kernel/stacktrace.c
 F:	arch/x86/kernel/unwind_*.c
 
+X86 TRUST DOMAIN EXTENSIONS (TDX)
+M:	Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
+R:	Dave Hansen <dave.hansen@linux.intel.com>
+L:	x86@kernel.org
+L:	linux-coco@lists.linux.dev
+S:	Supported
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/tdx
+F:	arch/x86/boot/compressed/tdx*
+F:	arch/x86/coco/tdx/
+F:	arch/x86/include/asm/shared/tdx.h
+F:	arch/x86/include/asm/tdx.h
+F:	arch/x86/virt/vmx/tdx/
+F:	drivers/virt/coco/tdx-guest
+
 X86 VDSO
 M:	Andy Lutomirski <luto@kernel.org>
 L:	linux-kernel@vger.kernel.org
@@ -23872,11 +23842,10 @@ S:	Supported
 W:	http://xfs.org/
 C:	irc://irc.oftc.net/xfs
 T:	git git://git.kernel.org/pub/scm/fs/xfs/xfs-linux.git
-P:	Documentation/filesystems/xfs-maintainer-entry-profile.rst
+P:	Documentation/filesystems/xfs/xfs-maintainer-entry-profile.rst
 F:	Documentation/ABI/testing/sysfs-fs-xfs
 F:	Documentation/admin-guide/xfs.rst
-F:	Documentation/filesystems/xfs-delayed-logging-design.rst
-F:	Documentation/filesystems/xfs-self-describing-metadata.rst
+F:	Documentation/filesystems/xfs/*
 F:	fs/xfs/
 F:	include/uapi/linux/dqblk_xfs.h
 F:	include/uapi/linux/fsmap.h
@@ -24088,20 +24057,16 @@ S:	Orphan
 F:	drivers/net/wireless/zydas/zd1211rw/
 
 ZD1301 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org/
-W:	http://palosaari.fi/linux/
 Q:	https://patchwork.linuxtv.org/project/linux-media/list/
 F:	drivers/media/usb/dvb-usb-v2/zd1301*
 
 ZD1301_DEMOD MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org/
-W:	http://palosaari.fi/linux/
 Q:	https://patchwork.linuxtv.org/project/linux-media/list/
 F:	drivers/media/dvb-frontends/zd1301_demod*
 
diff --git a/Makefile b/Makefile
index ede0bd241056..f1b2fd977275 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 7
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION =
 NAME = Hurr durr I'ma ninja sloth
 
 # *DOCUMENTATION*
@@ -1576,7 +1576,8 @@ help:
 	 echo  '                    (default: $(INSTALL_HDR_PATH))'; \
 	 echo  ''
 	@echo  'Static analysers:'
-	@echo  '  checkstack      - Generate a list of stack hogs'
+	@echo  '  checkstack      - Generate a list of stack hogs and consider all functions'
+	@echo  '                    with a stack size larger than MINSTACKSIZE (default: 100)'
 	@echo  '  versioncheck    - Sanity check on version.h usage'
 	@echo  '  includecheck    - Check for duplicate included header files'
 	@echo  '  export_report   - List the usages of all exported symbols'
@@ -2016,9 +2017,10 @@ CHECKSTACK_ARCH := $(SUBARCH)
 else
 CHECKSTACK_ARCH := $(ARCH)
 endif
+MINSTACKSIZE	?= 100
 checkstack:
 	$(OBJDUMP) -d vmlinux $$(find . -name '*.ko') | \
-	$(PERL) $(srctree)/scripts/checkstack.pl $(CHECKSTACK_ARCH)
+	$(PERL) $(srctree)/scripts/checkstack.pl $(CHECKSTACK_ARCH) $(MINSTACKSIZE)
 
 kernelrelease:
 	@$(filechk_kernel.release)
diff --git a/arch/Kconfig b/arch/Kconfig
index f4b210ab0612..5ca66aad0d08 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -301,17 +301,8 @@ config ARCH_HAS_DMA_CLEAR_UNCACHED
 config ARCH_HAS_CPU_FINALIZE_INIT
 	bool
 
-# Select if arch init_task must go in the __init_task_data section
-config ARCH_TASK_STRUCT_ON_STACK
-	bool
-
-# Select if arch has its private alloc_task_struct() function
-config ARCH_TASK_STRUCT_ALLOCATOR
-	bool
-
 config HAVE_ARCH_THREAD_STRUCT_WHITELIST
 	bool
-	depends on !ARCH_TASK_STRUCT_ALLOCATOR
 	help
 	  An architecture should select this to provide hardened usercopy
 	  knowledge about what region of the thread_struct should be
@@ -320,10 +311,6 @@ config HAVE_ARCH_THREAD_STRUCT_WHITELIST
 	  should be implemented. Without this, the entire thread_struct
 	  field in task_struct will be left whitelisted.
 
-# Select if arch has its private alloc_thread_stack() function
-config ARCH_THREAD_STACK_ALLOCATOR
-	bool
-
 # Select if arch wants to size task_struct dynamically via arch_task_struct_size:
 config ARCH_WANTS_DYNAMIC_TASK_STRUCT
 	bool
@@ -1470,6 +1457,14 @@ config DYNAMIC_SIGFRAME
 config HAVE_ARCH_NODE_DEV_GROUP
 	bool
 
+config ARCH_HAS_HW_PTE_YOUNG
+	bool
+	help
+	  Architectures that select this option are capable of setting the
+	  accessed bit in PTE entries when using them as part of linear address
+	  translations. Architectures that require runtime check should select
+	  this option and override arch_has_hw_pte_young().
+
 config ARCH_HAS_NONLEAF_PMD_YOUNG
 	bool
 	help
diff --git a/arch/alpha/include/asm/io.h b/arch/alpha/include/asm/io.h
index 7aeaf7c30a6f..4f47a5003fe8 100644
--- a/arch/alpha/include/asm/io.h
+++ b/arch/alpha/include/asm/io.h
@@ -308,7 +308,6 @@ static inline void __iomem *ioremap(unsigned long port, unsigned long size)
 }
 
 #define ioremap_wc ioremap
-#define ioremap_uc ioremap
 
 static inline void iounmap(volatile void __iomem *addr)
 {
@@ -652,12 +651,6 @@ extern void outsl (unsigned long port, const void *src, unsigned long count);
 #define RTC_ALWAYS_BCD	0
 
 /*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p)	__va(p)
-
-/*
  * These get provided from <asm-generic/iomap.h> since alpha does not
  * select GENERIC_IOMAP.
  */
diff --git a/arch/alpha/include/asm/mmu_context.h b/arch/alpha/include/asm/mmu_context.h
index 4eea7c616992..29a3e3a1f02b 100644
--- a/arch/alpha/include/asm/mmu_context.h
+++ b/arch/alpha/include/asm/mmu_context.h
@@ -183,6 +183,8 @@ ev4_switch_mm(struct mm_struct *prev_mm, struct mm_struct *next_mm,
 }
 
 extern void __load_new_mm_context(struct mm_struct *);
+asmlinkage void do_page_fault(unsigned long address, unsigned long mmcsr,
+			      long cause, struct pt_regs *regs);
 
 #ifdef CONFIG_SMP
 #define check_mmu_context()					\
diff --git a/arch/alpha/kernel/asm-offsets.c b/arch/alpha/kernel/asm-offsets.c
index b121294bee26..bf1eedd27cf7 100644
--- a/arch/alpha/kernel/asm-offsets.c
+++ b/arch/alpha/kernel/asm-offsets.c
@@ -12,7 +12,7 @@
 #include <linux/kbuild.h>
 #include <asm/io.h>
 
-void foo(void)
+static void __used foo(void)
 {
 	DEFINE(TI_TASK, offsetof(struct thread_info, task));
 	DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 18c842ca6c32..8ff110826ce2 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -496,3 +496,8 @@
 564	common	futex_wake			sys_futex_wake
 565	common	futex_wait			sys_futex_wait
 566	common	futex_requeue			sys_futex_requeue
+567	common	statmount			sys_statmount
+568	common	listmount			sys_listmount
+569	common	lsm_get_self_attr		sys_lsm_get_self_attr
+570	common	lsm_set_self_attr		sys_lsm_set_self_attr
+571	common	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c
index d9a67b370e04..7fc72aeb7398 100644
--- a/arch/alpha/kernel/traps.c
+++ b/arch/alpha/kernel/traps.c
@@ -9,6 +9,7 @@
  * This file initializes the trap entry points
  */
 
+#include <linux/cpu.h>
 #include <linux/jiffies.h>
 #include <linux/mm.h>
 #include <linux/sched/signal.h>
diff --git a/arch/alpha/lib/Makefile b/arch/alpha/lib/Makefile
index 1cc74f7b50ef..6a779b9018fd 100644
--- a/arch/alpha/lib/Makefile
+++ b/arch/alpha/lib/Makefile
@@ -4,7 +4,6 @@
 #
 
 asflags-y := $(KBUILD_CFLAGS)
-ccflags-y := -Werror
 
 # Many of these routines have implementations tuned for ev6.
 # Choose them iff we're targeting ev6 specifically.
diff --git a/arch/alpha/mm/Makefile b/arch/alpha/mm/Makefile
index bd770302eb82..101dbd06b4ce 100644
--- a/arch/alpha/mm/Makefile
+++ b/arch/alpha/mm/Makefile
@@ -3,6 +3,4 @@
 # Makefile for the linux alpha-specific parts of the memory manager.
 #
 
-ccflags-y := -Werror
-
 obj-y	:= init.o fault.o
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 3162db540ee9..1b0483c51cc1 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -49,7 +49,6 @@ config ARC
 	select OF
 	select OF_EARLY_FLATTREE
 	select PCI_SYSCALL if PCI
-	select PERF_USE_VMALLOC if ARC_CACHE_VIPT_ALIASING
 	select HAVE_ARCH_JUMP_LABEL if ISA_ARCV2 && !CPU_ENDIAN_BE32
 	select TRACE_IRQFLAGS_SUPPORT
 
@@ -232,10 +231,6 @@ config ARC_CACHE_PAGES
 	  Note that Global I/D ENABLE + Per Page DISABLE works but corollary
 	  Global DISABLE + Per Page ENABLE won't work
 
-config ARC_CACHE_VIPT_ALIASING
-	bool "Support VIPT Aliasing D$"
-	depends on ARC_HAS_DCACHE && ISA_ARCOMPACT
-
 endif #ARC_CACHE
 
 config ARC_HAS_ICCM
diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h
index bd5b1a9a0544..563af3e75f01 100644
--- a/arch/arc/include/asm/cacheflush.h
+++ b/arch/arc/include/asm/cacheflush.h
@@ -44,31 +44,10 @@ void dma_cache_wback(phys_addr_t start, unsigned long sz);
 
 #define flush_cache_dup_mm(mm)			/* called on fork (VIVT only) */
 
-#ifndef CONFIG_ARC_CACHE_VIPT_ALIASING
-
 #define flush_cache_mm(mm)			/* called on munmap/exit */
 #define flush_cache_range(mm, u_vstart, u_vend)
 #define flush_cache_page(vma, u_vaddr, pfn)	/* PF handling/COW-break */
 
-#else	/* VIPT aliasing dcache */
-
-/* To clear out stale userspace mappings */
-void flush_cache_mm(struct mm_struct *mm);
-void flush_cache_range(struct vm_area_struct *vma,
-	unsigned long start,unsigned long end);
-void flush_cache_page(struct vm_area_struct *vma,
-	unsigned long user_addr, unsigned long page);
-
-/*
- * To make sure that userspace mapping is flushed to memory before
- * get_user_pages() uses a kernel mapping to access the page
- */
-#define ARCH_HAS_FLUSH_ANON_PAGE
-void flush_anon_page(struct vm_area_struct *vma,
-	struct page *page, unsigned long u_vaddr);
-
-#endif	/* CONFIG_ARC_CACHE_VIPT_ALIASING */
-
 /*
  * A new pagecache page has PG_arch_1 clear - thus dcache dirty by default
  * This works around some PIO based drivers which don't call flush_dcache_page
@@ -76,28 +55,6 @@ void flush_anon_page(struct vm_area_struct *vma,
  */
 #define PG_dc_clean	PG_arch_1
 
-#define CACHE_COLORS_NUM	4
-#define CACHE_COLORS_MSK	(CACHE_COLORS_NUM - 1)
-#define CACHE_COLOR(addr)	(((unsigned long)(addr) >> (PAGE_SHIFT)) & CACHE_COLORS_MSK)
-
-/*
- * Simple wrapper over config option
- * Bootup code ensures that hardware matches kernel configuration
- */
-static inline int cache_is_vipt_aliasing(void)
-{
-	return IS_ENABLED(CONFIG_ARC_CACHE_VIPT_ALIASING);
-}
-
-/*
- * checks if two addresses (after page aligning) index into same cache set
- */
-#define addr_not_cache_congruent(addr1, addr2)				\
-({									\
-	cache_is_vipt_aliasing() ? 					\
-		(CACHE_COLOR(addr1) != CACHE_COLOR(addr2)) : 0;		\
-})
-
 #define copy_to_user_page(vma, page, vaddr, dst, src, len)		\
 do {									\
 	memcpy(dst, src, len);						\
diff --git a/arch/arc/include/asm/entry-arcv2.h b/arch/arc/include/asm/entry-arcv2.h
index 4d13320e0c1b..3802a2daaf86 100644
--- a/arch/arc/include/asm/entry-arcv2.h
+++ b/arch/arc/include/asm/entry-arcv2.h
@@ -291,4 +291,36 @@
 				/* M = 8-1  N = 8 */
 .endm
 
+.macro SAVE_ABI_CALLEE_REGS
+	push	r13
+	push	r14
+	push	r15
+	push	r16
+	push	r17
+	push	r18
+	push	r19
+	push	r20
+	push	r21
+	push	r22
+	push	r23
+	push	r24
+	push	r25
+.endm
+
+.macro RESTORE_ABI_CALLEE_REGS
+	pop	r25
+	pop	r24
+	pop	r23
+	pop	r22
+	pop	r21
+	pop	r20
+	pop	r19
+	pop	r18
+	pop	r17
+	pop	r16
+	pop	r15
+	pop	r14
+	pop	r13
+.endm
+
 #endif
diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h
index a0e760eb35a8..92c3e9f13252 100644
--- a/arch/arc/include/asm/entry-compact.h
+++ b/arch/arc/include/asm/entry-compact.h
@@ -33,6 +33,91 @@
 #include <asm/irqflags-compact.h>
 #include <asm/thread_info.h>	/* For THREAD_SIZE */
 
+/* Note on the LD/ST addr modes with addr reg wback
+ *
+ * LD.a same as LD.aw
+ *
+ * LD.a    reg1, [reg2, x]  => Pre Incr
+ *      Eff Addr for load = [reg2 + x]
+ *
+ * LD.ab   reg1, [reg2, x]  => Post Incr
+ *      Eff Addr for load = [reg2]
+ */
+
+.macro PUSHAX aux
+	lr	r9, [\aux]
+	push	r9
+.endm
+
+.macro POPAX aux
+	pop	r9
+	sr	r9, [\aux]
+.endm
+
+.macro  SAVE_R0_TO_R12
+	push	r0
+	push	r1
+	push	r2
+	push	r3
+	push	r4
+	push	r5
+	push	r6
+	push	r7
+	push	r8
+	push	r9
+	push	r10
+	push	r11
+	push	r12
+.endm
+
+.macro RESTORE_R12_TO_R0
+	pop	r12
+	pop	r11
+	pop	r10
+	pop	r9
+	pop	r8
+	pop	r7
+	pop	r6
+	pop	r5
+	pop	r4
+	pop	r3
+	pop	r2
+	pop	r1
+	pop	r0
+.endm
+
+.macro SAVE_ABI_CALLEE_REGS
+	push	r13
+	push	r14
+	push	r15
+	push	r16
+	push	r17
+	push	r18
+	push	r19
+	push	r20
+	push	r21
+	push	r22
+	push	r23
+	push	r24
+	push	r25
+.endm
+
+.macro RESTORE_ABI_CALLEE_REGS
+	pop	r25
+	pop	r24
+	pop	r23
+	pop	r22
+	pop	r21
+	pop	r20
+	pop	r19
+	pop	r18
+	pop	r17
+	pop	r16
+	pop	r15
+	pop	r14
+	pop	r13
+.endm
+
 /*--------------------------------------------------------------
  * Switch to Kernel Mode stack if SP points to User Mode stack
  *
@@ -235,7 +320,7 @@
 	SWITCH_TO_KERNEL_STK
 
 
-	PUSH	0x003\LVL\()abcd    /* Dummy ECR */
+	st.a	0x003\LVL\()abcd, [sp, -4]	/* Dummy ECR */
 	sub	sp, sp, 8	    /* skip orig_r0 (not needed)
 				       skip pt_regs->sp, already saved above */
 
diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h
index 49c2e090cb5c..cf1ba376e992 100644
--- a/arch/arc/include/asm/entry.h
+++ b/arch/arc/include/asm/entry.h
@@ -21,114 +21,12 @@
 #include <asm/entry-arcv2.h>
 #endif
 
-/* Note on the LD/ST addr modes with addr reg wback
- *
- * LD.a same as LD.aw
- *
- * LD.a    reg1, [reg2, x]  => Pre Incr
- *      Eff Addr for load = [reg2 + x]
- *
- * LD.ab   reg1, [reg2, x]  => Post Incr
- *      Eff Addr for load = [reg2]
- */
-
-.macro PUSH reg
-	st.a	\reg, [sp, -4]
-.endm
-
-.macro PUSHAX aux
-	lr	r9, [\aux]
-	PUSH	r9
-.endm
-
-.macro POP reg
-	ld.ab	\reg, [sp, 4]
-.endm
-
-.macro POPAX aux
-	POP	r9
-	sr	r9, [\aux]
-.endm
-
-/*--------------------------------------------------------------
- * Helpers to save/restore Scratch Regs:
- * used by Interrupt/Exception Prologue/Epilogue
- *-------------------------------------------------------------*/
-.macro  SAVE_R0_TO_R12
-	PUSH	r0
-	PUSH	r1
-	PUSH	r2
-	PUSH	r3
-	PUSH	r4
-	PUSH	r5
-	PUSH	r6
-	PUSH	r7
-	PUSH	r8
-	PUSH	r9
-	PUSH	r10
-	PUSH	r11
-	PUSH	r12
-.endm
-
-.macro RESTORE_R12_TO_R0
-	POP	r12
-	POP	r11
-	POP	r10
-	POP	r9
-	POP	r8
-	POP	r7
-	POP	r6
-	POP	r5
-	POP	r4
-	POP	r3
-	POP	r2
-	POP	r1
-	POP	r0
-
-.endm
-
-/*--------------------------------------------------------------
- * Helpers to save/restore callee-saved regs:
- * used by several macros below
- *-------------------------------------------------------------*/
-.macro SAVE_R13_TO_R25
-	PUSH	r13
-	PUSH	r14
-	PUSH	r15
-	PUSH	r16
-	PUSH	r17
-	PUSH	r18
-	PUSH	r19
-	PUSH	r20
-	PUSH	r21
-	PUSH	r22
-	PUSH	r23
-	PUSH	r24
-	PUSH	r25
-.endm
-
-.macro RESTORE_R25_TO_R13
-	POP	r25
-	POP	r24
-	POP	r23
-	POP	r22
-	POP	r21
-	POP	r20
-	POP	r19
-	POP	r18
-	POP	r17
-	POP	r16
-	POP	r15
-	POP	r14
-	POP	r13
-.endm
-
 /*
  * save user mode callee regs as struct callee_regs
  *  - needed by fork/do_signal/unaligned-access-emulation.
  */
 .macro SAVE_CALLEE_SAVED_USER
-	SAVE_R13_TO_R25
+	SAVE_ABI_CALLEE_REGS
 .endm
 
 /*
@@ -136,18 +34,18 @@
  *  - could have been changed by ptrace tracer or unaligned-access fixup
  */
 .macro RESTORE_CALLEE_SAVED_USER
-	RESTORE_R25_TO_R13
+	RESTORE_ABI_CALLEE_REGS
 .endm
 
 /*
  * save/restore kernel mode callee regs at the time of context switch
  */
 .macro SAVE_CALLEE_SAVED_KERNEL
-	SAVE_R13_TO_R25
+	SAVE_ABI_CALLEE_REGS
 .endm
 
 .macro RESTORE_CALLEE_SAVED_KERNEL
-	RESTORE_R25_TO_R13
+	RESTORE_ABI_CALLEE_REGS
 .endm
 
 /*--------------------------------------------------------------
diff --git a/arch/arc/include/asm/hugepage.h b/arch/arc/include/asm/hugepage.h
index ef8d4166370c..8a2441670a8f 100644
--- a/arch/arc/include/asm/hugepage.h
+++ b/arch/arc/include/asm/hugepage.h
@@ -10,6 +10,13 @@
 #include <linux/types.h>
 #include <asm-generic/pgtable-nopmd.h>
 
+/*
+ * Hugetlb definitions.
+ */
+#define HPAGE_SHIFT		PMD_SHIFT
+#define HPAGE_SIZE		(_AC(1, UL) << HPAGE_SHIFT)
+#define HPAGE_MASK		(~(HPAGE_SIZE - 1))
+
 static inline pte_t pmd_pte(pmd_t pmd)
 {
 	return __pte(pmd_val(pmd));
diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h
index 02b53ad811fb..def0dfb95b43 100644
--- a/arch/arc/include/asm/page.h
+++ b/arch/arc/include/asm/page.h
@@ -85,15 +85,6 @@ typedef struct {
 typedef struct page *pgtable_t;
 
 /*
- * Use virt_to_pfn with caution:
- * If used in pte or paddr related macros, it could cause truncation
- * in PAE40 builds
- * As a rule of thumb, only use it in helpers starting with virt_
- * You have been warned !
- */
-#define virt_to_pfn(kaddr)	(__pa(kaddr) >> PAGE_SHIFT)
-
-/*
  * When HIGHMEM is enabled we have holes in the memory map so we need
  * pfn_valid() that takes into account the actual extents of the physical
  * memory
@@ -122,6 +113,18 @@ extern int pfn_valid(unsigned long pfn);
 #define __pa(vaddr)  		((unsigned long)(vaddr))
 #define __va(paddr)  		((void *)((unsigned long)(paddr)))
 
+/*
+ * Use virt_to_pfn with caution:
+ * If used in pte or paddr related macros, it could cause truncation
+ * in PAE40 builds
+ * As a rule of thumb, only use it in helpers starting with virt_
+ * You have been warned !
+ */
+static inline unsigned long virt_to_pfn(const void *kaddr)
+{
+	return __pa(kaddr) >> PAGE_SHIFT;
+}
+
 #define virt_to_page(kaddr)	pfn_to_page(virt_to_pfn(kaddr))
 #define virt_addr_valid(kaddr)  pfn_valid(virt_to_pfn(kaddr))
 
diff --git a/arch/arc/include/asm/pgtable-levels.h b/arch/arc/include/asm/pgtable-levels.h
index fc417c75c24d..86e148226463 100644
--- a/arch/arc/include/asm/pgtable-levels.h
+++ b/arch/arc/include/asm/pgtable-levels.h
@@ -159,7 +159,7 @@
 #define pmd_clear(xp)		do { pmd_val(*(xp)) = 0; } while (0)
 #define pmd_page_vaddr(pmd)	(pmd_val(pmd) & PAGE_MASK)
 #define pmd_pfn(pmd)		((pmd_val(pmd) & PAGE_MASK) >> PAGE_SHIFT)
-#define pmd_page(pmd)		virt_to_page(pmd_page_vaddr(pmd))
+#define pmd_page(pmd)		virt_to_page((void *)pmd_page_vaddr(pmd))
 #define set_pmd(pmdp, pmd)	(*(pmdp) = pmd)
 #define pmd_pgtable(pmd)	((pgtable_t) pmd_page(pmd))
 
diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h
index 4a2b30fb5a98..00b9318e551e 100644
--- a/arch/arc/include/asm/ptrace.h
+++ b/arch/arc/include/asm/ptrace.h
@@ -54,6 +54,10 @@ struct pt_regs {
 	ecr_reg ecr;
 };
 
+struct callee_regs {
+	unsigned long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
+};
+
 #define MAX_REG_OFFSET offsetof(struct pt_regs, ecr)
 
 #else
@@ -92,16 +96,14 @@ struct pt_regs {
 	unsigned long status32;
 };
 
-#define MAX_REG_OFFSET offsetof(struct pt_regs, status32)
-
-#endif
-
-/* Callee saved registers - need to be saved only when you are scheduled out */
-
 struct callee_regs {
 	unsigned long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
 };
 
+#define MAX_REG_OFFSET offsetof(struct pt_regs, status32)
+
+#endif
+
 #define instruction_pointer(regs)	((regs)->ret)
 #define profile_pc(regs)		instruction_pointer(regs)
 
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 4dcf8589b708..d08a5092c2b4 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -153,7 +153,7 @@ static int arcv2_mumbojumbo(int c, struct cpuinfo_arc *info, char *buf, int len)
 {
 	int n = 0;
 #ifdef CONFIG_ISA_ARCV2
-	const char *release, *cpu_nm, *isa_nm = "ARCv2";
+	const char *release = "", *cpu_nm = "HS38", *isa_nm = "ARCv2";
 	int dual_issue = 0, dual_enb = 0, mpy_opt, present;
 	int bpu_full, bpu_cache, bpu_pred, bpu_ret_stk;
 	char mpy_nm[16], lpb_nm[32];
@@ -172,8 +172,6 @@ static int arcv2_mumbojumbo(int c, struct cpuinfo_arc *info, char *buf, int len)
 	 * releases only update it.
 	 */
 
-	cpu_nm = "HS38";
-
 	if (info->arcver > 0x50 && info->arcver <= 0x53) {
 		release = arc_hs_rel[info->arcver - 0x51].str;
 	} else {
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index 0b3bb529d246..8f6f4a542964 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -62,7 +62,7 @@ struct rt_sigframe {
 	unsigned int sigret_magic;
 };
 
-static int save_arcv2_regs(struct sigcontext *mctx, struct pt_regs *regs)
+static int save_arcv2_regs(struct sigcontext __user *mctx, struct pt_regs *regs)
 {
 	int err = 0;
 #ifndef CONFIG_ISA_ARCOMPACT
@@ -75,12 +75,12 @@ static int save_arcv2_regs(struct sigcontext *mctx, struct pt_regs *regs)
 #else
 	v2abi.r58 = v2abi.r59 = 0;
 #endif
-	err = __copy_to_user(&mctx->v2abi, &v2abi, sizeof(v2abi));
+	err = __copy_to_user(&mctx->v2abi, (void const *)&v2abi, sizeof(v2abi));
 #endif
 	return err;
 }
 
-static int restore_arcv2_regs(struct sigcontext *mctx, struct pt_regs *regs)
+static int restore_arcv2_regs(struct sigcontext __user *mctx, struct pt_regs *regs)
 {
 	int err = 0;
 #ifndef CONFIG_ISA_ARCOMPACT
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index f7e05c146637..9106ceac323c 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -145,10 +145,9 @@ dc_chk:
 	p_dc->sz_k = 1 << (dbcr.sz - 1);
 
 	n += scnprintf(buf + n, len - n,
-			"D-Cache\t\t: %uK, %dway/set, %uB Line, %s%s%s\n",
+			"D-Cache\t\t: %uK, %dway/set, %uB Line, %s%s\n",
 			p_dc->sz_k, assoc, p_dc->line_len,
 			vipt ? "VIPT" : "PIPT",
-			p_dc->colors > 1 ? " aliasing" : "",
 			IS_USED_CFG(CONFIG_ARC_HAS_DCACHE));
 
 slc_chk:
@@ -703,51 +702,10 @@ static inline void arc_slc_enable(void)
  * Exported APIs
  */
 
-/*
- * Handle cache congruency of kernel and userspace mappings of page when kernel
- * writes-to/reads-from
- *
- * The idea is to defer flushing of kernel mapping after a WRITE, possible if:
- *  -dcache is NOT aliasing, hence any U/K-mappings of page are congruent
- *  -U-mapping doesn't exist yet for page (finalised in update_mmu_cache)
- *  -In SMP, if hardware caches are coherent
- *
- * There's a corollary case, where kernel READs from a userspace mapped page.
- * If the U-mapping is not congruent to K-mapping, former needs flushing.
- */
 void flush_dcache_folio(struct folio *folio)
 {
-	struct address_space *mapping;
-
-	if (!cache_is_vipt_aliasing()) {
-		clear_bit(PG_dc_clean, &folio->flags);
-		return;
-	}
-
-	/* don't handle anon pages here */
-	mapping = folio_flush_mapping(folio);
-	if (!mapping)
-		return;
-
-	/*
-	 * pagecache page, file not yet mapped to userspace
-	 * Make a note that K-mapping is dirty
-	 */
-	if (!mapping_mapped(mapping)) {
-		clear_bit(PG_dc_clean, &folio->flags);
-	} else if (folio_mapped(folio)) {
-		/* kernel reading from page with U-mapping */
-		phys_addr_t paddr = (unsigned long)folio_address(folio);
-		unsigned long vaddr = folio_pos(folio);
-
-		/*
-		 * vaddr is not actually the virtual address, but is
-		 * congruent to every user mapping.
-		 */
-		if (addr_not_cache_congruent(paddr, vaddr))
-			__flush_dcache_pages(paddr, vaddr,
-						folio_nr_pages(folio));
-	}
+	clear_bit(PG_dc_clean, &folio->flags);
+	return;
 }
 EXPORT_SYMBOL(flush_dcache_folio);
 
@@ -921,44 +879,6 @@ noinline void flush_cache_all(void)
 
 }
 
-#ifdef CONFIG_ARC_CACHE_VIPT_ALIASING
-
-void flush_cache_mm(struct mm_struct *mm)
-{
-	flush_cache_all();
-}
-
-void flush_cache_page(struct vm_area_struct *vma, unsigned long u_vaddr,
-		      unsigned long pfn)
-{
-	phys_addr_t paddr = pfn << PAGE_SHIFT;
-
-	u_vaddr &= PAGE_MASK;
-
-	__flush_dcache_pages(paddr, u_vaddr, 1);
-
-	if (vma->vm_flags & VM_EXEC)
-		__inv_icache_pages(paddr, u_vaddr, 1);
-}
-
-void flush_cache_range(struct vm_area_struct *vma, unsigned long start,
-		       unsigned long end)
-{
-	flush_cache_all();
-}
-
-void flush_anon_page(struct vm_area_struct *vma, struct page *page,
-		     unsigned long u_vaddr)
-{
-	/* TBD: do we really need to clear the kernel mapping */
-	__flush_dcache_pages((phys_addr_t)page_address(page), u_vaddr, 1);
-	__flush_dcache_pages((phys_addr_t)page_address(page),
-			    (phys_addr_t)page_address(page), 1);
-
-}
-
-#endif
-
 void copy_user_highpage(struct page *to, struct page *from,
 	unsigned long u_vaddr, struct vm_area_struct *vma)
 {
@@ -966,46 +886,11 @@ void copy_user_highpage(struct page *to, struct page *from,
 	struct folio *dst = page_folio(to);
 	void *kfrom = kmap_atomic(from);
 	void *kto = kmap_atomic(to);
-	int clean_src_k_mappings = 0;
-
-	/*
-	 * If SRC page was already mapped in userspace AND it's U-mapping is
-	 * not congruent with K-mapping, sync former to physical page so that
-	 * K-mapping in memcpy below, sees the right data
-	 *
-	 * Note that while @u_vaddr refers to DST page's userspace vaddr, it is
-	 * equally valid for SRC page as well
-	 *
-	 * For !VIPT cache, all of this gets compiled out as
-	 * addr_not_cache_congruent() is 0
-	 */
-	if (page_mapcount(from) && addr_not_cache_congruent(kfrom, u_vaddr)) {
-		__flush_dcache_pages((unsigned long)kfrom, u_vaddr, 1);
-		clean_src_k_mappings = 1;
-	}
 
 	copy_page(kto, kfrom);
 
-	/*
-	 * Mark DST page K-mapping as dirty for a later finalization by
-	 * update_mmu_cache(). Although the finalization could have been done
-	 * here as well (given that both vaddr/paddr are available).
-	 * But update_mmu_cache() already has code to do that for other
-	 * non copied user pages (e.g. read faults which wire in pagecache page
-	 * directly).
-	 */
 	clear_bit(PG_dc_clean, &dst->flags);
-
-	/*
-	 * if SRC was already usermapped and non-congruent to kernel mapping
-	 * sync the kernel mapping back to physical page
-	 */
-	if (clean_src_k_mappings) {
-		__flush_dcache_pages((unsigned long)kfrom,
-					(unsigned long)kfrom, 1);
-	} else {
-		clear_bit(PG_dc_clean, &src->flags);
-	}
+	clear_bit(PG_dc_clean, &src->flags);
 
 	kunmap_atomic(kto);
 	kunmap_atomic(kfrom);
@@ -1140,17 +1025,8 @@ static noinline void __init arc_cache_init_master(void)
 			      dc->line_len, L1_CACHE_BYTES);
 
 		/* check for D-Cache aliasing on ARCompact: ARCv2 has PIPT */
-		if (is_isa_arcompact()) {
-			int handled = IS_ENABLED(CONFIG_ARC_CACHE_VIPT_ALIASING);
-
-			if (dc->colors > 1) {
-				if (!handled)
-					panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
-				if (CACHE_COLORS_NUM != dc->colors)
-					panic("CACHE_COLORS_NUM not optimized for config\n");
-			} else if (handled && dc->colors == 1) {
-				panic("Disable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
-			}
+		if (is_isa_arcompact() && dc->colors > 1) {
+			panic("Aliasing VIPT cache not supported\n");
 		}
 	}
 
diff --git a/arch/arc/mm/mmap.c b/arch/arc/mm/mmap.c
index fce5fa2b4f52..3c1c7ae73292 100644
--- a/arch/arc/mm/mmap.c
+++ b/arch/arc/mm/mmap.c
@@ -14,10 +14,6 @@
 
 #include <asm/cacheflush.h>
 
-#define COLOUR_ALIGN(addr, pgoff)			\
-	((((addr) + SHMLBA - 1) & ~(SHMLBA - 1)) +	\
-	 (((pgoff) << PAGE_SHIFT) & (SHMLBA - 1)))
-
 /*
  * Ensure that shared mappings are correctly aligned to
  * avoid aliasing issues with VIPT caches.
@@ -31,21 +27,13 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
-	int do_align = 0;
-	int aliasing = cache_is_vipt_aliasing();
 	struct vm_unmapped_area_info info;
 
 	/*
-	 * We only need to do colour alignment if D cache aliases.
-	 */
-	if (aliasing)
-		do_align = filp || (flags & MAP_SHARED);
-
-	/*
 	 * We enforce the MAP_FIXED case.
 	 */
 	if (flags & MAP_FIXED) {
-		if (aliasing && flags & MAP_SHARED &&
+		if (flags & MAP_SHARED &&
 		    (addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1))
 			return -EINVAL;
 		return addr;
@@ -55,10 +43,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		return -ENOMEM;
 
 	if (addr) {
-		if (do_align)
-			addr = COLOUR_ALIGN(addr, pgoff);
-		else
-			addr = PAGE_ALIGN(addr);
+		addr = PAGE_ALIGN(addr);
 
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
@@ -70,7 +55,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	info.length = len;
 	info.low_limit = mm->mmap_base;
 	info.high_limit = TASK_SIZE;
-	info.align_mask = do_align ? (PAGE_MASK & (SHMLBA - 1)) : 0;
+	info.align_mask = 0;
 	info.align_offset = pgoff << PAGE_SHIFT;
 	return vm_unmapped_area(&info);
 }
diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c
index e536b2dcd4b0..ad702b49aeb3 100644
--- a/arch/arc/mm/tlb.c
+++ b/arch/arc/mm/tlb.c
@@ -478,21 +478,15 @@ void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma,
 
 	create_tlb(vma, vaddr, ptep);
 
-	if (page == ZERO_PAGE(0)) {
+	if (page == ZERO_PAGE(0))
 		return;
-	}
 
 	/*
-	 * Exec page : Independent of aliasing/page-color considerations,
-	 *	       since icache doesn't snoop dcache on ARC, any dirty
-	 *	       K-mapping of a code page needs to be wback+inv so that
-	 *	       icache fetch by userspace sees code correctly.
-	 * !EXEC page: If K-mapping is NOT congruent to U-mapping, flush it
-	 *	       so userspace sees the right data.
-	 *  (Avoids the flush for Non-exec + congruent mapping case)
+	 * For executable pages, since icache doesn't snoop dcache, any
+	 * dirty K-mapping of a code page needs to be wback+inv so that
+	 * icache fetch by userspace sees code correctly.
 	 */
-	if ((vma->vm_flags & VM_EXEC) ||
-	     addr_not_cache_congruent(paddr, vaddr)) {
+	if (vma->vm_flags & VM_EXEC) {
 		struct folio *folio = page_folio(page);
 		int dirty = !test_and_set_bit(PG_dc_clean, &folio->flags);
 		if (dirty) {
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index f8567e95f98b..b67d05468251 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -340,83 +340,7 @@ config ARCH_MULTIPLATFORM
 	  Selecting N here allows using those options, including
 	  DEBUG_UNCOMPRESS, XIP_KERNEL and ZBOOT_ROM. If unsure, say Y.
 
-menu "Platform selection"
-	depends on MMU
-
-comment "CPU Core family selection"
-
-config ARCH_MULTI_V4
-	bool "ARMv4 based platforms (FA526, StrongARM)"
-	depends on !ARCH_MULTI_V6_V7
-	# https://github.com/llvm/llvm-project/issues/50764
-	depends on !LD_IS_LLD || LLD_VERSION >= 160000
-	select ARCH_MULTI_V4_V5
-	select CPU_FA526 if !(CPU_SA110 || CPU_SA1100)
-
-config ARCH_MULTI_V4T
-	bool "ARMv4T based platforms (ARM720T, ARM920T, ...)"
-	depends on !ARCH_MULTI_V6_V7
-	# https://github.com/llvm/llvm-project/issues/50764
-	depends on !LD_IS_LLD || LLD_VERSION >= 160000
-	select ARCH_MULTI_V4_V5
-	select CPU_ARM920T if !(CPU_ARM7TDMI || CPU_ARM720T || \
-		CPU_ARM740T || CPU_ARM9TDMI || CPU_ARM922T || \
-		CPU_ARM925T || CPU_ARM940T)
-
-config ARCH_MULTI_V5
-	bool "ARMv5 based platforms (ARM926T, XSCALE, PJ1, ...)"
-	depends on !ARCH_MULTI_V6_V7
-	select ARCH_MULTI_V4_V5
-	select CPU_ARM926T if !(CPU_ARM946E || CPU_ARM1020 || \
-		CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || \
-		CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_FEROCEON)
-
-config ARCH_MULTI_V4_V5
-	bool
-
-config ARCH_MULTI_V6
-	bool "ARMv6 based platforms (ARM11)"
-	select ARCH_MULTI_V6_V7
-	select CPU_V6K
-
-config ARCH_MULTI_V7
-	bool "ARMv7 based platforms (Cortex-A, PJ4, Scorpion, Krait)"
-	default y
-	select ARCH_MULTI_V6_V7
-	select CPU_V7
-	select HAVE_SMP
-
-config ARCH_MULTI_V6_V7
-	bool
-	select MIGHT_HAVE_CACHE_L2X0
-
-config ARCH_MULTI_CPU_AUTO
-	def_bool !(ARCH_MULTI_V4 || ARCH_MULTI_V4T || ARCH_MULTI_V6_V7)
-	select ARCH_MULTI_V5
-
-endmenu
-
-config ARCH_VIRT
-	bool "Dummy Virtual Machine"
-	depends on ARCH_MULTI_V7
-	select ARM_AMBA
-	select ARM_GIC
-	select ARM_GIC_V2M if PCI
-	select ARM_GIC_V3
-	select ARM_GIC_V3_ITS if PCI
-	select ARM_PSCI
-	select HAVE_ARM_ARCH_TIMER
-
-config ARCH_AIROHA
-	bool "Airoha SoC Support"
-	depends on ARCH_MULTI_V7
-	select ARM_AMBA
-	select ARM_GIC
-	select ARM_GIC_V3
-	select ARM_PSCI
-	select HAVE_ARM_ARCH_TIMER
-	help
-	  Support for Airoha EN7523 SoCs
+source "arch/arm/Kconfig.platforms"
 
 #
 # This is sorted alphabetically by mach-* pathname.  However, plat-*
@@ -429,8 +353,6 @@ source "arch/arm/mach-alpine/Kconfig"
 
 source "arch/arm/mach-artpec/Kconfig"
 
-source "arch/arm/mach-asm9260/Kconfig"
-
 source "arch/arm/mach-aspeed/Kconfig"
 
 source "arch/arm/mach-at91/Kconfig"
@@ -479,8 +401,6 @@ source "arch/arm/mach-milbeaut/Kconfig"
 
 source "arch/arm/mach-mmp/Kconfig"
 
-source "arch/arm/mach-moxart/Kconfig"
-
 source "arch/arm/mach-mstar/Kconfig"
 
 source "arch/arm/mach-mv78xx0/Kconfig"
@@ -493,8 +413,6 @@ source "arch/arm/mach-nomadik/Kconfig"
 
 source "arch/arm/mach-npcm/Kconfig"
 
-source "arch/arm/mach-nspire/Kconfig"
-
 source "arch/arm/mach-omap1/Kconfig"
 
 source "arch/arm/mach-omap2/Kconfig"
@@ -505,8 +423,6 @@ source "arch/arm/mach-pxa/Kconfig"
 
 source "arch/arm/mach-qcom/Kconfig"
 
-source "arch/arm/mach-rda/Kconfig"
-
 source "arch/arm/mach-realtek/Kconfig"
 
 source "arch/arm/mach-rpc/Kconfig"
@@ -529,14 +445,10 @@ source "arch/arm/mach-sti/Kconfig"
 
 source "arch/arm/mach-stm32/Kconfig"
 
-source "arch/arm/mach-sunplus/Kconfig"
-
 source "arch/arm/mach-sunxi/Kconfig"
 
 source "arch/arm/mach-tegra/Kconfig"
 
-source "arch/arm/mach-uniphier/Kconfig"
-
 source "arch/arm/mach-ux500/Kconfig"
 
 source "arch/arm/mach-versatile/Kconfig"
@@ -1362,7 +1274,7 @@ config ARCH_FORCE_MAX_ORDER
 	default "10"
 	help
 	  The kernel page allocator limits the size of maximal physically
-	  contiguous allocations. The limit is called MAX_ORDER and it
+	  contiguous allocations. The limit is called MAX_PAGE_ORDER and it
 	  defines the maximal power of two of number of pages that can be
 	  allocated as a single contiguous block. This option allows
 	  overriding the default setting when ability to allocate very
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index fc2b41d41447..5fbbac1b708b 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -1809,15 +1809,8 @@ config DEBUG_UNCOMPRESS
 		     (!DEBUG_TEGRA_UART || !ZBOOT_ROM) && \
 		     !DEBUG_BRCMSTB_UART && !DEBUG_SEMIHOSTING
 	help
-	  This option influences the normal decompressor output for
-	  multiplatform kernels.  Normally, multiplatform kernels disable
-	  decompressor output because it is not possible to know where to
-	  send the decompressor output.
-
-	  When this option is set, the selected DEBUG_LL output method
-	  will be re-used for normal decompressor output on multiplatform
-	  kernels.
-	  
+	  Say Y here to enable debug output in the decompressor code, using
+	  the selected DEBUG_LL output method.
 
 config UNCOMPRESS_INCLUDE
 	string
diff --git a/arch/arm/Kconfig.platforms b/arch/arm/Kconfig.platforms
new file mode 100644
index 000000000000..845ab08e20a4
--- /dev/null
+++ b/arch/arm/Kconfig.platforms
@@ -0,0 +1,183 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+menu "Platform selection"
+	depends on MMU
+
+comment "CPU Core family selection"
+
+config ARCH_MULTI_V4
+	bool "ARMv4 based platforms (FA526, StrongARM)"
+	depends on !ARCH_MULTI_V6_V7
+	# https://github.com/llvm/llvm-project/issues/50764
+	depends on !LD_IS_LLD || LLD_VERSION >= 160000
+	select ARCH_MULTI_V4_V5
+	select CPU_FA526 if !(CPU_SA110 || CPU_SA1100)
+
+config ARCH_MULTI_V4T
+	bool "ARMv4T based platforms (ARM720T, ARM920T, ...)"
+	depends on !ARCH_MULTI_V6_V7
+	# https://github.com/llvm/llvm-project/issues/50764
+	depends on !LD_IS_LLD || LLD_VERSION >= 160000
+	select ARCH_MULTI_V4_V5
+	select CPU_ARM920T if !(CPU_ARM7TDMI || CPU_ARM720T || \
+		CPU_ARM740T || CPU_ARM9TDMI || CPU_ARM922T || \
+		CPU_ARM925T || CPU_ARM940T)
+
+config ARCH_MULTI_V5
+	bool "ARMv5 based platforms (ARM926T, XSCALE, PJ1, ...)"
+	depends on !ARCH_MULTI_V6_V7
+	select ARCH_MULTI_V4_V5
+	select CPU_ARM926T if !(CPU_ARM946E || CPU_ARM1020 || \
+		CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || \
+		CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_FEROCEON)
+
+config ARCH_MULTI_V4_V5
+	bool
+
+config ARCH_MULTI_V6
+	bool "ARMv6 based platforms (ARM11)"
+	select ARCH_MULTI_V6_V7
+	select CPU_V6K
+
+config ARCH_MULTI_V7
+	bool "ARMv7 based platforms (Cortex-A, PJ4, Scorpion, Krait)"
+	default y
+	select ARCH_MULTI_V6_V7
+	select CPU_V7
+	select HAVE_SMP
+
+config ARCH_MULTI_V6_V7
+	bool
+	select MIGHT_HAVE_CACHE_L2X0
+
+config ARCH_MULTI_CPU_AUTO
+	def_bool !(ARCH_MULTI_V4 || ARCH_MULTI_V4T || ARCH_MULTI_V6_V7)
+	select ARCH_MULTI_V5
+
+endmenu
+
+config ARCH_VIRT
+	bool "Dummy Virtual Machine"
+	depends on ARCH_MULTI_V7
+	select ARM_AMBA
+	select ARM_GIC
+	select ARM_GIC_V2M if PCI
+	select ARM_GIC_V3
+	select ARM_GIC_V3_ITS if PCI
+	select ARM_PSCI
+	select HAVE_ARM_ARCH_TIMER
+
+config ARCH_AIROHA
+	bool "Airoha SoC Support"
+	depends on ARCH_MULTI_V7
+	select ARM_AMBA
+	select ARM_GIC
+	select ARM_GIC_V3
+	select ARM_PSCI
+	select HAVE_ARM_ARCH_TIMER
+	help
+	  Support for Airoha EN7523 SoCs
+
+config MACH_ASM9260
+	bool "Alphascale ASM9260"
+	depends on ARCH_MULTI_V5
+	depends on CPU_LITTLE_ENDIAN
+	select CPU_ARM926T
+	select ASM9260_TIMER
+	help
+	  Support for Alphascale ASM9260 based platform.
+
+menuconfig ARCH_MOXART
+	bool "MOXA ART SoC"
+	depends on ARCH_MULTI_V4
+	depends on CPU_LITTLE_ENDIAN
+	select CPU_FA526
+	select ARM_DMA_MEM_BUFFERABLE
+	select FARADAY_FTINTC010
+	select FTTMR010_TIMER
+	select GPIOLIB
+	select PHYLIB if NETDEVICES
+	help
+	  Say Y here if you want to run your kernel on hardware with a
+	  MOXA ART SoC.
+	  The MOXA ART SoC is based on a Faraday FA526 ARMv4 32-bit
+	  192 MHz CPU with MMU and 16KB/8KB D/I-cache (UC-7112-LX).
+	  Used on models UC-7101, UC-7112/UC-7110, IA240/IA241, IA3341.
+
+if ARCH_MOXART
+
+config MACH_UC7112LX
+	bool "MOXA UC-7112-LX"
+	depends on ARCH_MOXART
+	help
+	  Say Y here if you intend to run this kernel on a MOXA
+	  UC-7112-LX embedded computer.
+
+endif
+
+config ARCH_NSPIRE
+	bool "TI-NSPIRE based"
+	depends on ARCH_MULTI_V4T
+	depends on CPU_LITTLE_ENDIAN
+	select CPU_ARM926T
+	select GENERIC_IRQ_CHIP
+	select ARM_AMBA
+	select ARM_VIC
+	select ARM_TIMER_SP804
+	select NSPIRE_TIMER
+	select POWER_RESET
+	select POWER_RESET_SYSCON
+	help
+	  This enables support for systems using the TI-NSPIRE CPU
+
+config ARCH_RDA
+	bool "RDA Micro SoCs"
+	depends on ARCH_MULTI_V7
+	select RDA_INTC
+	select RDA_TIMER
+	help
+	  This enables support for the RDA Micro 8810PL SoC family.
+
+menuconfig ARCH_SUNPLUS
+	bool "Sunplus SoCs"
+	depends on ARCH_MULTI_V7
+	help
+	  Support for Sunplus SoC family: SP7021 and succeeding SoC-based systems,
+	  such as the Banana Pi BPI-F2S development board (and derivatives).
+	  (<http://www.sinovoip.com.cn/ecp_view.asp?id=586>)
+	  (<https://tibbo.com/store/plus1.html>)
+
+if ARCH_SUNPLUS
+
+config SOC_SP7021
+	bool "Sunplus SP7021 SoC support"
+	default ARCH_SUNPLUS
+	select HAVE_ARM_ARCH_TIMER
+	select ARM_GIC
+	select ARM_PSCI
+	select PINCTRL
+	select PINCTRL_SPPCTL
+	select SERIAL_SUNPLUS if TTY
+	select SERIAL_SUNPLUS_CONSOLE if TTY
+	help
+	  Support for Sunplus SP7021 SoC. It is based on ARM 4-core
+	  Cortex-A7 with various peripherals (e.g.: I2C, SPI, SDIO,
+	  Ethernet, etc.), FPGA interface,  chip-to-chip bus.
+	  It is designed for industrial control.
+
+endif
+
+config ARCH_UNIPHIER
+	bool "Socionext UniPhier SoCs"
+	depends on ARCH_MULTI_V7
+	select ARCH_HAS_RESET_CONTROLLER
+	select ARM_AMBA
+	select ARM_GLOBAL_TIMER
+	select ARM_GIC
+	select HAVE_ARM_SCU
+	select HAVE_ARM_TWD if SMP
+	select PINCTRL
+	select RESET_CONTROLLER
+	help
+	  Support for UniPhier SoC family developed by Socionext Inc.
+	  (formerly, System LSI Business Division of Panasonic Corporation)
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 5ba42f69f8ce..473280d5adce 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -167,7 +167,6 @@ textofs-$(CONFIG_ARCH_AXXIA) := 0x00308000
 # Machine directory name.  This list is sorted alphanumerically
 # by CONFIG_* macro name.
 machine-$(CONFIG_ARCH_ACTIONS)		+= actions
-machine-$(CONFIG_ARCH_AIROHA)		+= airoha
 machine-$(CONFIG_ARCH_ALPINE)		+= alpine
 machine-$(CONFIG_ARCH_ARTPEC)		+= artpec
 machine-$(CONFIG_ARCH_ASPEED)           += aspeed
@@ -192,7 +191,6 @@ machine-$(CONFIG_ARCH_LPC18XX)		+= lpc18xx
 machine-$(CONFIG_ARCH_LPC32XX)		+= lpc32xx
 machine-$(CONFIG_ARCH_MESON)		+= meson
 machine-$(CONFIG_ARCH_MMP)		+= mmp
-machine-$(CONFIG_ARCH_MOXART)		+= moxart
 machine-$(CONFIG_ARCH_MV78XX0)		+= mv78xx0
 machine-$(CONFIG_ARCH_MVEBU)		+= mvebu
 machine-$(CONFIG_ARCH_MXC)		+= imx
@@ -202,7 +200,6 @@ machine-$(CONFIG_ARCH_MXS)		+= mxs
 machine-$(CONFIG_ARCH_MSTARV7)		+= mstar
 machine-$(CONFIG_ARCH_NOMADIK)		+= nomadik
 machine-$(CONFIG_ARCH_NPCM)		+= npcm
-machine-$(CONFIG_ARCH_NSPIRE)		+= nspire
 machine-$(CONFIG_ARCH_OMAP1)		+= omap1
 machine-$(CONFIG_ARCH_OMAP2PLUS)	+= omap2
 machine-$(CONFIG_ARCH_ORION5X)		+= orion5x
@@ -218,7 +215,6 @@ machine-$(CONFIG_ARCH_RENESAS)	 	+= shmobile
 machine-$(CONFIG_ARCH_INTEL_SOCFPGA)	+= socfpga
 machine-$(CONFIG_ARCH_STI)		+= sti
 machine-$(CONFIG_ARCH_STM32)		+= stm32
-machine-$(CONFIG_ARCH_SUNPLUS)		+= sunplus
 machine-$(CONFIG_ARCH_SUNXI)		+= sunxi
 machine-$(CONFIG_ARCH_TEGRA)		+= tegra
 machine-$(CONFIG_ARCH_U8500)		+= ux500
diff --git a/arch/arm/boot/dts/broadcom/bcm2711-rpi-400.dts b/arch/arm/boot/dts/broadcom/bcm2711-rpi-400.dts
index 1ab8184302db..5a2869a18bd5 100644
--- a/arch/arm/boot/dts/broadcom/bcm2711-rpi-400.dts
+++ b/arch/arm/boot/dts/broadcom/bcm2711-rpi-400.dts
@@ -36,9 +36,7 @@
 	gpios = <&gpio 42 GPIO_ACTIVE_HIGH>;
 };
 
-&leds {
-	/delete-node/ led_act;
-};
+/delete-node/ &led_act;
 
 &pm {
 	/delete-property/ system-power-controller;
diff --git a/arch/arm/boot/dts/broadcom/bcm63138.dtsi b/arch/arm/boot/dts/broadcom/bcm63138.dtsi
index 93281c47c9ba..4ef02283612b 100644
--- a/arch/arm/boot/dts/broadcom/bcm63138.dtsi
+++ b/arch/arm/boot/dts/broadcom/bcm63138.dtsi
@@ -232,6 +232,12 @@
 			interrupt-names = "nand";
 		};
 
+		serial@4400 {
+			compatible = "brcm,bcm63138-hs-uart", "brcm,bcmbca-hs-uart";
+			reg = <0x4400 0x1e0>;
+			interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
 		bootlut: bootlut@8000 {
 			compatible = "brcm,bcm63138-bootlut";
 			reg = <0x8000 0x50>;
diff --git a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-usrobotics-usr8200.dts b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-usrobotics-usr8200.dts
index 90fd51b36e7d..2c89db34c8d8 100644
--- a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-usrobotics-usr8200.dts
+++ b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-usrobotics-usr8200.dts
@@ -165,6 +165,24 @@
 				#address-cells = <1>;
 				#size-cells = <0>;
 
+				/*
+				 * PHY 0..4 are internal to the MV88E6060 switch but appear
+				 * as independent devices.
+				 */
+				phy0: ethernet-phy@0 {
+					reg = <0>;
+				};
+				phy1: ethernet-phy@1 {
+					reg = <1>;
+				};
+				phy2: ethernet-phy@2 {
+					reg = <2>;
+				};
+				phy3: ethernet-phy@3 {
+					reg = <3>;
+				};
+
+				/* Altima AMI101L used by the WAN port */
 				phy9: ethernet-phy@9 {
 					reg = <9>;
 				};
@@ -181,21 +199,25 @@
 						port@0 {
 							reg = <0>;
 							label = "lan1";
+							phy-handle = <&phy0>;
 						};
 
 						port@1 {
 							reg = <1>;
 							label = "lan2";
+							phy-handle = <&phy1>;
 						};
 
 						port@2 {
 							reg = <2>;
 							label = "lan3";
+							phy-handle = <&phy2>;
 						};
 
 						port@3 {
 							reg = <3>;
 							label = "lan4";
+							phy-handle = <&phy3>;
 						};
 
 						port@5 {
diff --git a/arch/arm/boot/dts/intel/socfpga/socfpga.dtsi b/arch/arm/boot/dts/intel/socfpga/socfpga.dtsi
index 4c1d140f40f8..35be14150f41 100644
--- a/arch/arm/boot/dts/intel/socfpga/socfpga.dtsi
+++ b/arch/arm/boot/dts/intel/socfpga/socfpga.dtsi
@@ -768,7 +768,7 @@
 			status = "disabled";
 		};
 
-		nand0: nand@ff900000 {
+		nand0: nand-controller@ff900000 {
 			#address-cells = <0x1>;
 			#size-cells = <0x0>;
 			compatible = "altr,socfpga-denali-nand";
diff --git a/arch/arm/boot/dts/intel/socfpga/socfpga_arria10.dtsi b/arch/arm/boot/dts/intel/socfpga/socfpga_arria10.dtsi
index f36063c57c7f..6b6e77596ffa 100644
--- a/arch/arm/boot/dts/intel/socfpga/socfpga_arria10.dtsi
+++ b/arch/arm/boot/dts/intel/socfpga/socfpga_arria10.dtsi
@@ -669,7 +669,7 @@
 			status = "disabled";
 		};
 
-		nand: nand@ffb90000 {
+		nand: nand-controller@ffb90000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			compatible = "altr,socfpga-denali-nand";
diff --git a/arch/arm/boot/dts/intel/socfpga/socfpga_arria10_socdk_qspi.dts b/arch/arm/boot/dts/intel/socfpga/socfpga_arria10_socdk_qspi.dts
index 11ccdc6c2dc6..0434f1c7b665 100644
--- a/arch/arm/boot/dts/intel/socfpga/socfpga_arria10_socdk_qspi.dts
+++ b/arch/arm/boot/dts/intel/socfpga/socfpga_arria10_socdk_qspi.dts
@@ -17,8 +17,6 @@
 		spi-max-frequency = <100000000>;
 
 		m25p,fast-read;
-		cdns,page-size = <256>;
-		cdns,block-size = <16>;
 		cdns,read-delay = <3>;
 		cdns,tshsl-ns = <50>;
 		cdns,tsd2d-ns = <50>;
diff --git a/arch/arm/boot/dts/intel/socfpga/socfpga_arria5_socdk.dts b/arch/arm/boot/dts/intel/socfpga/socfpga_arria5_socdk.dts
index c48385702a85..7342f5942b0d 100644
--- a/arch/arm/boot/dts/intel/socfpga/socfpga_arria5_socdk.dts
+++ b/arch/arm/boot/dts/intel/socfpga/socfpga_arria5_socdk.dts
@@ -124,8 +124,6 @@
 		spi-max-frequency = <100000000>;
 
 		m25p,fast-read;
-		cdns,page-size = <256>;
-		cdns,block-size = <16>;
 		cdns,read-delay = <4>;
 		cdns,tshsl-ns = <50>;
 		cdns,tsd2d-ns = <50>;
diff --git a/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_socdk.dts b/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_socdk.dts
index c7f5fa0ba0f2..d37a982e8571 100644
--- a/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_socdk.dts
+++ b/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_socdk.dts
@@ -129,8 +129,6 @@
 		spi-max-frequency = <100000000>;
 
 		m25p,fast-read;
-		cdns,page-size = <256>;
-		cdns,block-size = <16>;
 		cdns,read-delay = <4>;
 		cdns,tshsl-ns = <50>;
 		cdns,tsd2d-ns = <50>;
diff --git a/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_sockit.dts b/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_sockit.dts
index 3dd99c7c95e0..9e4db7407f1a 100644
--- a/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_sockit.dts
+++ b/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_sockit.dts
@@ -174,8 +174,6 @@
 		spi-max-frequency = <100000000>;
 
 		m25p,fast-read;
-		cdns,page-size = <256>;
-		cdns,block-size = <16>;
 		cdns,read-delay = <4>;
 		cdns,tshsl-ns = <50>;
 		cdns,tsd2d-ns = <50>;
diff --git a/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_sodia.dts b/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_sodia.dts
index 2564671fc1c6..ce0d6514eeb5 100644
--- a/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_sodia.dts
+++ b/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_sodia.dts
@@ -121,8 +121,6 @@
 		spi-max-frequency = <100000000>;
 
 		m25p,fast-read;
-		cdns,page-size = <256>;
-		cdns,block-size = <16>;
 		cdns,read-delay = <4>;
 		cdns,tshsl-ns = <50>;
 		cdns,tsd2d-ns = <50>;
diff --git a/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_vining_fpga.dts b/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_vining_fpga.dts
index e0630b0eed03..65f390bf8975 100644
--- a/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_vining_fpga.dts
+++ b/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_vining_fpga.dts
@@ -229,8 +229,6 @@
 		spi-max-frequency = <100000000>;
 		m25p,fast-read;
 
-		cdns,page-size = <256>;
-		cdns,block-size = <16>;
 		cdns,read-delay = <4>;
 		cdns,tshsl-ns = <50>;
 		cdns,tsd2d-ns = <50>;
@@ -246,8 +244,6 @@
 		spi-max-frequency = <100000000>;
 		m25p,fast-read;
 
-		cdns,page-size = <256>;
-		cdns,block-size = <16>;
 		cdns,read-delay = <4>;
 		cdns,tshsl-ns = <50>;
 		cdns,tsd2d-ns = <50>;
diff --git a/arch/arm/boot/dts/marvell/armada-370-rd.dts b/arch/arm/boot/dts/marvell/armada-370-rd.dts
index b459a670f615..f23f6b3fc8f3 100644
--- a/arch/arm/boot/dts/marvell/armada-370-rd.dts
+++ b/arch/arm/boot/dts/marvell/armada-370-rd.dts
@@ -95,7 +95,7 @@
 			gpio-fan {
 				compatible = "gpio-fan";
 				gpios = <&gpio0 8 GPIO_ACTIVE_HIGH>;
-				gpio-fan,speed-map = <0 0 3000 1>;
+				gpio-fan,speed-map = <0 0>, <3000 1>;
 				pinctrl-0 = <&fan_pins>;
 				pinctrl-names = "default";
 			};
@@ -149,39 +149,37 @@
 		};
 	};
 
-	switch: switch@10 {
+	switch: ethernet-switch@10 {
 		compatible = "marvell,mv88e6085";
-		#address-cells = <1>;
-		#size-cells = <0>;
 		reg = <0x10>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 
-		ports {
+		ethernet-ports {
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			port@0 {
+			ethernet-port@0 {
 				reg = <0>;
 				label = "lan0";
 			};
 
-			port@1 {
+			ethernet-port@1 {
 				reg = <1>;
 				label = "lan1";
 			};
 
-			port@2 {
+			ethernet-port@2 {
 				reg = <2>;
 				label = "lan2";
 			};
 
-			port@3 {
+			ethernet-port@3 {
 				reg = <3>;
 				label = "lan3";
 			};
 
-			port@5 {
+			ethernet-port@5 {
 				reg = <5>;
 				ethernet = <&eth1>;
 				phy-mode = "rgmii-id";
@@ -196,25 +194,25 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			switchphy0: switchphy@0 {
+			switchphy0: ethernet-phy@0 {
 				reg = <0>;
 				interrupt-parent = <&switch>;
 				interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
 			};
 
-			switchphy1: switchphy@1 {
+			switchphy1: ethernet-phy@1 {
 				reg = <1>;
 				interrupt-parent = <&switch>;
 				interrupts = <1 IRQ_TYPE_LEVEL_HIGH>;
 			};
 
-			switchphy2: switchphy@2 {
+			switchphy2: ethernet-phy@2 {
 				reg = <2>;
 				interrupt-parent = <&switch>;
 				interrupts = <2 IRQ_TYPE_LEVEL_HIGH>;
 			};
 
-			switchphy3: switchphy@3 {
+			switchphy3: ethernet-phy@3 {
 				reg = <3>;
 				interrupt-parent = <&switch>;
 				interrupts = <3 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/boot/dts/marvell/armada-370-seagate-nas-2bay.dts b/arch/arm/boot/dts/marvell/armada-370-seagate-nas-2bay.dts
index 8dd242e668e6..6ec3dd3337f4 100644
--- a/arch/arm/boot/dts/marvell/armada-370-seagate-nas-2bay.dts
+++ b/arch/arm/boot/dts/marvell/armada-370-seagate-nas-2bay.dts
@@ -25,9 +25,9 @@
 
 	gpio-fan {
 		gpio-fan,speed-map =
-			<   0 3
-			  950 2
-			 1400 1
-			 1800 0>;
+			<   0 3>,
+			< 950 2>,
+			<1400 1>,
+			<1800 0>;
 	};
 };
diff --git a/arch/arm/boot/dts/marvell/armada-370-seagate-nas-4bay.dts b/arch/arm/boot/dts/marvell/armada-370-seagate-nas-4bay.dts
index 370ca9c43247..3011578a3124 100644
--- a/arch/arm/boot/dts/marvell/armada-370-seagate-nas-4bay.dts
+++ b/arch/arm/boot/dts/marvell/armada-370-seagate-nas-4bay.dts
@@ -106,10 +106,10 @@
 
 	gpio-fan {
 		gpio-fan,speed-map =
-			<   0 3
-			  800 2
-			  1050 1
-			  1300 0>;
+			<   0 3>,
+			< 800 2>,
+			<1050 1>,
+			<1300 0>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/marvell/armada-370-synology-ds213j.dts b/arch/arm/boot/dts/marvell/armada-370-synology-ds213j.dts
index b07d11d1f124..02599a3e9816 100644
--- a/arch/arm/boot/dts/marvell/armada-370-synology-ds213j.dts
+++ b/arch/arm/boot/dts/marvell/armada-370-synology-ds213j.dts
@@ -113,14 +113,14 @@
 			 &gpio2  0 GPIO_ACTIVE_HIGH
 			 &gpio2  1 GPIO_ACTIVE_HIGH>;
 		alarm-gpios = <&gpio1 6 GPIO_ACTIVE_HIGH>;
-		gpio-fan,speed-map = <    0 0
-				       1000 1
-				       1150 2
-				       1350 4
-				       1500 3
-				       1650 5
-				       1750 6
-				       1900 7 >;
+		gpio-fan,speed-map = <   0 0>,
+				     <1000 1>,
+				     <1150 2>,
+				     <1350 4>,
+				     <1500 3>,
+				     <1650 5>,
+				     <1750 6>,
+				     <1900 7>;
 	};
 
 	gpio-leds {
diff --git a/arch/arm/boot/dts/marvell/armada-381-netgear-gs110emx.dts b/arch/arm/boot/dts/marvell/armada-381-netgear-gs110emx.dts
index f4c4b213ef4e..5baf83e5253d 100644
--- a/arch/arm/boot/dts/marvell/armada-381-netgear-gs110emx.dts
+++ b/arch/arm/boot/dts/marvell/armada-381-netgear-gs110emx.dts
@@ -77,51 +77,49 @@
 	pinctrl-0 = <&mdio_pins>;
 	status = "okay";
 
-	switch@0 {
+	ethernet-switch@0 {
 		compatible = "marvell,mv88e6190";
-		#address-cells = <1>;
 		#interrupt-cells = <2>;
 		interrupt-controller;
 		interrupt-parent = <&gpio1>;
 		interrupts = <7 IRQ_TYPE_LEVEL_LOW>;
 		pinctrl-0 = <&switch_interrupt_pins>;
 		pinctrl-names = "default";
-		#size-cells = <0>;
 		reg = <0>;
 
 		mdio {
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			switch0phy1: switch0phy1@1 {
+			switch0phy1: ethernet-phy@1 {
 				reg = <0x1>;
 			};
 
-			switch0phy2: switch0phy2@2 {
+			switch0phy2: ethernet-phy@2 {
 				reg = <0x2>;
 			};
 
-			switch0phy3: switch0phy3@3 {
+			switch0phy3: ethernet-phy@3 {
 				reg = <0x3>;
 			};
 
-			switch0phy4: switch0phy4@4 {
+			switch0phy4: ethernet-phy@4 {
 				reg = <0x4>;
 			};
 
-			switch0phy5: switch0phy5@5 {
+			switch0phy5: ethernet-phy@5 {
 				reg = <0x5>;
 			};
 
-			switch0phy6: switch0phy6@6 {
+			switch0phy6: ethernet-phy@6 {
 				reg = <0x6>;
 			};
 
-			switch0phy7: switch0phy7@7 {
+			switch0phy7: ethernet-phy@7 {
 				reg = <0x7>;
 			};
 
-			switch0phy8: switch0phy8@8 {
+			switch0phy8: ethernet-phy@8 {
 				reg = <0x8>;
 			};
 		};
@@ -142,11 +140,11 @@
 			};
 		};
 
-		ports {
+		ethernet-ports {
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			port@0 {
+			ethernet-port@0 {
 				ethernet = <&eth0>;
 				phy-mode = "rgmii";
 				reg = <0>;
@@ -158,55 +156,55 @@
 				};
 			};
 
-			port@1 {
+			ethernet-port@1 {
 				label = "lan1";
 				phy-handle = <&switch0phy1>;
 				reg = <1>;
 			};
 
-			port@2 {
+			ethernet-port@2 {
 				label = "lan2";
 				phy-handle = <&switch0phy2>;
 				reg = <2>;
 			};
 
-			port@3 {
+			ethernet-port@3 {
 				label = "lan3";
 				phy-handle = <&switch0phy3>;
 				reg = <3>;
 			};
 
-			port@4 {
+			ethernet-port@4 {
 				label = "lan4";
 				phy-handle = <&switch0phy4>;
 				reg = <4>;
 			};
 
-			port@5 {
+			ethernet-port@5 {
 				label = "lan5";
 				phy-handle = <&switch0phy5>;
 				reg = <5>;
 			};
 
-			port@6 {
+			ethernet-port@6 {
 				label = "lan6";
 				phy-handle = <&switch0phy6>;
 				reg = <6>;
 			};
 
-			port@7 {
+			ethernet-port@7 {
 				label = "lan7";
 				phy-handle = <&switch0phy7>;
 				reg = <7>;
 			};
 
-			port@8 {
+			ethernet-port@8 {
 				label = "lan8";
 				phy-handle = <&switch0phy8>;
 				reg = <8>;
 			};
 
-			port@9 {
+			ethernet-port@9 {
 				/* 88X3310P external phy */
 				label = "lan9";
 				phy-handle = <&phy1>;
@@ -214,7 +212,7 @@
 				reg = <9>;
 			};
 
-			port@a {
+			ethernet-port@a {
 				/* 88X3310P external phy */
 				label = "lan10";
 				phy-handle = <&phy2>;
diff --git a/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr-l8.dts b/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr-l8.dts
index 1990f7d0cc79..1707d1b01545 100644
--- a/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr-l8.dts
+++ b/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr-l8.dts
@@ -7,66 +7,66 @@
 };
 
 &mdio {
-	switch0: switch0@4 {
+	switch0: ethernet-switch@4 {
 		compatible = "marvell,mv88e6190";
 		reg = <4>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&cf_gtr_switch_reset_pins>;
 		reset-gpios = <&gpio0 18 GPIO_ACTIVE_LOW>;
 
-		ports {
+		ethernet-ports {
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			port@1 {
+			ethernet-port@1 {
 				reg = <1>;
 				label = "lan8";
 				phy-handle = <&switch0phy0>;
 			};
 
-			port@2 {
+			ethernet-port@2 {
 				reg = <2>;
 				label = "lan7";
 				phy-handle = <&switch0phy1>;
 			};
 
-			port@3 {
+			ethernet-port@3 {
 				reg = <3>;
 				label = "lan6";
 				phy-handle = <&switch0phy2>;
 			};
 
-			port@4 {
+			ethernet-port@4 {
 				reg = <4>;
 				label = "lan5";
 				phy-handle = <&switch0phy3>;
 			};
 
-			port@5 {
+			ethernet-port@5 {
 				reg = <5>;
 				label = "lan4";
 				phy-handle = <&switch0phy4>;
 			};
 
-			port@6 {
+			ethernet-port@6 {
 				reg = <6>;
 				label = "lan3";
 				phy-handle = <&switch0phy5>;
 			};
 
-			port@7 {
+			ethernet-port@7 {
 				reg = <7>;
 				label = "lan2";
 				phy-handle = <&switch0phy6>;
 			};
 
-			port@8 {
+			ethernet-port@8 {
 				reg = <8>;
 				label = "lan1";
 				phy-handle = <&switch0phy7>;
 			};
 
-			port@10 {
+			ethernet-port@10 {
 				reg = <10>;
 				phy-mode = "2500base-x";
 
@@ -83,35 +83,35 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			switch0phy0: switch0phy0@1 {
+			switch0phy0: ethernet-phy@1 {
 				reg = <0x1>;
 			};
 
-			switch0phy1: switch0phy1@2 {
+			switch0phy1: ethernet-phy@2 {
 				reg = <0x2>;
 			};
 
-			switch0phy2: switch0phy2@3 {
+			switch0phy2: ethernet-phy@3 {
 				reg = <0x3>;
 			};
 
-			switch0phy3: switch0phy3@4 {
+			switch0phy3: ethernet-phy@4 {
 				reg = <0x4>;
 			};
 
-			switch0phy4: switch0phy4@5 {
+			switch0phy4: ethernet-phy@5 {
 				reg = <0x5>;
 			};
 
-			switch0phy5: switch0phy5@6 {
+			switch0phy5: ethernet-phy@6 {
 				reg = <0x6>;
 			};
 
-			switch0phy6: switch0phy6@7 {
+			switch0phy6: ethernet-phy@7 {
 				reg = <0x7>;
 			};
 
-			switch0phy7: switch0phy7@8 {
+			switch0phy7: ethernet-phy@8 {
 				reg = <0x8>;
 			};
 		};
diff --git a/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr-s4.dts b/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr-s4.dts
index b795ad573891..a7678a784c18 100644
--- a/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr-s4.dts
+++ b/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr-s4.dts
@@ -11,42 +11,42 @@
 };
 
 &mdio {
-	switch0: switch0@4 {
+	switch0: ethernet-switch@4 {
 		compatible = "marvell,mv88e6085";
 		reg = <4>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&cf_gtr_switch_reset_pins>;
 		reset-gpios = <&gpio0 18 GPIO_ACTIVE_LOW>;
 
-		ports {
+		ethernet-ports {
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			port@1 {
+			ethernet-port@1 {
 				reg = <1>;
 				label = "lan2";
 				phy-handle = <&switch0phy0>;
 			};
 
-			port@2 {
+			ethernet-port@2 {
 				reg = <2>;
 				label = "lan1";
 				phy-handle = <&switch0phy1>;
 			};
 
-			port@3 {
+			ethernet-port@3 {
 				reg = <3>;
 				label = "lan4";
 				phy-handle = <&switch0phy2>;
 			};
 
-			port@4 {
+			ethernet-port@4 {
 				reg = <4>;
 				label = "lan3";
 				phy-handle = <&switch0phy3>;
 			};
 
-			port@5 {
+			ethernet-port@5 {
 				reg = <5>;
 				phy-mode = "2500base-x";
 				ethernet = <&eth1>;
@@ -63,19 +63,19 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			switch0phy0: switch0phy0@11 {
+			switch0phy0: ethernet-phy@11 {
 				reg = <0x11>;
 			};
 
-			switch0phy1: switch0phy1@12 {
+			switch0phy1: ethernet-phy@12 {
 				reg = <0x12>;
 			};
 
-			switch0phy2: switch0phy2@13 {
+			switch0phy2: ethernet-phy@13 {
 				reg = <0x13>;
 			};
 
-			switch0phy3: switch0phy3@14 {
+			switch0phy3: ethernet-phy@14 {
 				reg = <0x14>;
 			};
 		};
diff --git a/arch/arm/boot/dts/marvell/armada-385-linksys.dtsi b/arch/arm/boot/dts/marvell/armada-385-linksys.dtsi
index fc8216fd9f60..4116ed60f709 100644
--- a/arch/arm/boot/dts/marvell/armada-385-linksys.dtsi
+++ b/arch/arm/boot/dts/marvell/armada-385-linksys.dtsi
@@ -158,42 +158,40 @@
 &mdio {
 	status = "okay";
 
-	switch@0 {
+	ethernet-switch@0 {
 		compatible = "marvell,mv88e6085";
-		#address-cells = <1>;
-		#size-cells = <0>;
 		reg = <0>;
 
-		ports {
+		ethernet-ports {
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			port@0 {
+			ethernet-port@0 {
 				reg = <0>;
 				label = "lan4";
 			};
 
-			port@1 {
+			ethernet-port@1 {
 				reg = <1>;
 				label = "lan3";
 			};
 
-			port@2 {
+			ethernet-port@2 {
 				reg = <2>;
 				label = "lan2";
 			};
 
-			port@3 {
+			ethernet-port@3 {
 				reg = <3>;
 				label = "lan1";
 			};
 
-			port@4 {
+			ethernet-port@4 {
 				reg = <4>;
 				label = "wan";
 			};
 
-			port@5 {
+			ethernet-port@5 {
 				reg = <5>;
 				phy-mode = "sgmii";
 				ethernet = <&eth2>;
diff --git a/arch/arm/boot/dts/marvell/armada-385-synology-ds116.dts b/arch/arm/boot/dts/marvell/armada-385-synology-ds116.dts
index ea91ff964d94..6caa5c50175a 100644
--- a/arch/arm/boot/dts/marvell/armada-385-synology-ds116.dts
+++ b/arch/arm/boot/dts/marvell/armada-385-synology-ds116.dts
@@ -131,14 +131,14 @@
 			gpios = <&gpio1 18 GPIO_ACTIVE_HIGH>,
 				<&gpio1 17 GPIO_ACTIVE_HIGH>,
 				<&gpio1 16 GPIO_ACTIVE_HIGH>;
-			gpio-fan,speed-map = <   0 0
-					      1500 1
-					      2500 2
-					      3000 3
-					      3400 4
-					      3700 5
-					      3900 6
-					      4000 7>;
+			gpio-fan,speed-map = <   0 0>,
+					     <1500 1>,
+					     <2500 2>,
+					     <3000 3>,
+					     <3400 4>,
+					     <3700 5>,
+					     <3900 6>,
+					     <4000 7>;
 			#cooling-cells = <2>;
 		};
 
diff --git a/arch/arm/boot/dts/marvell/armada-385-turris-omnia.dts b/arch/arm/boot/dts/marvell/armada-385-turris-omnia.dts
index 2d8d319bec83..7b755bb4e4e7 100644
--- a/arch/arm/boot/dts/marvell/armada-385-turris-omnia.dts
+++ b/arch/arm/boot/dts/marvell/armada-385-turris-omnia.dts
@@ -435,12 +435,10 @@
 	};
 
 	/* Switch MV88E6176 at address 0x10 */
-	switch@10 {
+	ethernet-switch@10 {
 		pinctrl-names = "default";
 		pinctrl-0 = <&swint_pins>;
 		compatible = "marvell,mv88e6085";
-		#address-cells = <1>;
-		#size-cells = <0>;
 
 		dsa,member = <0 0>;
 		reg = <0x10>;
@@ -448,36 +446,36 @@
 		interrupt-parent = <&gpio1>;
 		interrupts = <13 IRQ_TYPE_LEVEL_LOW>;
 
-		ports {
+		ethernet-ports {
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			ports@0 {
+			ethernet-port@0 {
 				reg = <0>;
 				label = "lan0";
 			};
 
-			ports@1 {
+			ethernet-port@1 {
 				reg = <1>;
 				label = "lan1";
 			};
 
-			ports@2 {
+			ethernet-port@2 {
 				reg = <2>;
 				label = "lan2";
 			};
 
-			ports@3 {
+			ethernet-port@3 {
 				reg = <3>;
 				label = "lan3";
 			};
 
-			ports@4 {
+			ethernet-port@4 {
 				reg = <4>;
 				label = "lan4";
 			};
 
-			ports@5 {
+			ethernet-port@5 {
 				reg = <5>;
 				ethernet = <&eth1>;
 				phy-mode = "rgmii-id";
@@ -488,7 +486,7 @@
 				};
 			};
 
-			ports@6 {
+			ethernet-port@6 {
 				reg = <6>;
 				ethernet = <&eth0>;
 				phy-mode = "rgmii-id";
diff --git a/arch/arm/boot/dts/marvell/armada-388-clearfog.dts b/arch/arm/boot/dts/marvell/armada-388-clearfog.dts
index 32c569df142f..3290ccad2374 100644
--- a/arch/arm/boot/dts/marvell/armada-388-clearfog.dts
+++ b/arch/arm/boot/dts/marvell/armada-388-clearfog.dts
@@ -92,44 +92,42 @@
 &mdio {
 	status = "okay";
 
-	switch@4 {
+	ethernet-switch@4 {
 		compatible = "marvell,mv88e6085";
-		#address-cells = <1>;
-		#size-cells = <0>;
 		reg = <4>;
 		pinctrl-0 = <&clearfog_dsa0_clk_pins &clearfog_dsa0_pins>;
 		pinctrl-names = "default";
 
-		ports {
+		ethernet-ports {
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			port@0 {
+			ethernet-port@0 {
 				reg = <0>;
 				label = "lan5";
 			};
 
-			port@1 {
+			ethernet-port@1 {
 				reg = <1>;
 				label = "lan4";
 			};
 
-			port@2 {
+			ethernet-port@2 {
 				reg = <2>;
 				label = "lan3";
 			};
 
-			port@3 {
+			ethernet-port@3 {
 				reg = <3>;
 				label = "lan2";
 			};
 
-			port@4 {
+			ethernet-port@4 {
 				reg = <4>;
 				label = "lan1";
 			};
 
-			port@5 {
+			ethernet-port@5 {
 				reg = <5>;
 				ethernet = <&eth1>;
 				phy-mode = "1000base-x";
@@ -140,7 +138,7 @@
 				};
 			};
 
-			port@6 {
+			ethernet-port@6 {
 				/* 88E1512 external phy */
 				reg = <6>;
 				label = "lan6";
diff --git a/arch/arm/boot/dts/marvell/armada-388-gp.dts b/arch/arm/boot/dts/marvell/armada-388-gp.dts
index e2ba50520b6b..1de0a172aa5f 100644
--- a/arch/arm/boot/dts/marvell/armada-388-gp.dts
+++ b/arch/arm/boot/dts/marvell/armada-388-gp.dts
@@ -237,8 +237,8 @@
 		gpio-fan {
 			compatible = "gpio-fan";
 			gpios = <&expander1 3 GPIO_ACTIVE_HIGH>;
-			gpio-fan,speed-map = <	 0 0
-					      3000 1>;
+			gpio-fan,speed-map = <	 0 0>,
+					     <3000 1>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/marvell/armada-xp-linksys-mamba.dts b/arch/arm/boot/dts/marvell/armada-xp-linksys-mamba.dts
index 7a0614fd0c93..ea859f7ea042 100644
--- a/arch/arm/boot/dts/marvell/armada-xp-linksys-mamba.dts
+++ b/arch/arm/boot/dts/marvell/armada-xp-linksys-mamba.dts
@@ -265,42 +265,40 @@
 &mdio {
 	status = "okay";
 
-	switch@0 {
+	ethernet-switch@0 {
 		compatible = "marvell,mv88e6085";
-		#address-cells = <1>;
-		#size-cells = <0>;
 		reg = <0>;
 
-		ports {
+		ethernet-ports {
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			port@0 {
+			ethernet-port@0 {
 				reg = <0>;
 				label = "lan4";
 			};
 
-			port@1 {
+			ethernet-port@1 {
 				reg = <1>;
 				label = "lan3";
 			};
 
-			port@2 {
+			ethernet-port@2 {
 				reg = <2>;
 				label = "lan2";
 			};
 
-			port@3 {
+			ethernet-port@3 {
 				reg = <3>;
 				label = "lan1";
 			};
 
-			port@4 {
+			ethernet-port@4 {
 				reg = <4>;
 				label = "internet";
 			};
 
-			port@5 {
+			ethernet-port@5 {
 				reg = <5>;
 				phy-mode = "rgmii-id";
 				ethernet = <&eth0>;
diff --git a/arch/arm/boot/dts/marvell/kirkwood-dnskw.dtsi b/arch/arm/boot/dts/marvell/kirkwood-dnskw.dtsi
index eb917462b219..0738eb679fcd 100644
--- a/arch/arm/boot/dts/marvell/kirkwood-dnskw.dtsi
+++ b/arch/arm/boot/dts/marvell/kirkwood-dnskw.dtsi
@@ -38,9 +38,9 @@
 		pinctrl-names = "default";
 		gpios = <&gpio1 14 GPIO_ACTIVE_HIGH
 			 &gpio1 13 GPIO_ACTIVE_HIGH>;
-		gpio-fan,speed-map = <0    0
-				      3000 1
-				      6000 2>;
+		gpio-fan,speed-map = <0    0>,
+				     <3000 1>,
+				     <6000 2>;
 	};
 
 	gpio_poweroff {
diff --git a/arch/arm/boot/dts/marvell/kirkwood-linkstation-6282.dtsi b/arch/arm/boot/dts/marvell/kirkwood-linkstation-6282.dtsi
index 377b6e970259..dfac2045a1eb 100644
--- a/arch/arm/boot/dts/marvell/kirkwood-linkstation-6282.dtsi
+++ b/arch/arm/boot/dts/marvell/kirkwood-linkstation-6282.dtsi
@@ -118,10 +118,11 @@
 		gpios = <&gpio0 17 GPIO_ACTIVE_LOW
 			 &gpio0 16 GPIO_ACTIVE_LOW>;
 
-		gpio-fan,speed-map = <0 3
-				1500 2
-				3250 1
-				5000 0>;
+		gpio-fan,speed-map =
+				<   0 3>,
+				<1500 2>,
+				<3250 1>,
+				<5000 0>;
 
 		alarm-gpios = <&gpio1 11 GPIO_ACTIVE_HIGH>;
 	};
diff --git a/arch/arm/boot/dts/marvell/kirkwood-linkstation-lswxl.dts b/arch/arm/boot/dts/marvell/kirkwood-linkstation-lswxl.dts
index c6024b569423..0425df8cb91c 100644
--- a/arch/arm/boot/dts/marvell/kirkwood-linkstation-lswxl.dts
+++ b/arch/arm/boot/dts/marvell/kirkwood-linkstation-lswxl.dts
@@ -69,10 +69,11 @@
 		gpios = <&gpio1 16 GPIO_ACTIVE_LOW
 			 &gpio1 15 GPIO_ACTIVE_LOW>;
 
-		gpio-fan,speed-map = <0 3
-				1500 2
-				3250 1
-				5000 0>;
+		gpio-fan,speed-map =
+				<   0 3>,
+				<1500 2>,
+				<3250 1>,
+				<5000 0>;
 
 		alarm-gpios = <&gpio1 8 GPIO_ACTIVE_HIGH>;
 	};
diff --git a/arch/arm/boot/dts/marvell/kirkwood-lsxl.dtsi b/arch/arm/boot/dts/marvell/kirkwood-lsxl.dtsi
index 88b70ba1c8fe..f80af24b9e90 100644
--- a/arch/arm/boot/dts/marvell/kirkwood-lsxl.dtsi
+++ b/arch/arm/boot/dts/marvell/kirkwood-lsxl.dtsi
@@ -172,10 +172,11 @@
 		pinctrl-names = "default";
 		gpios = <&gpio0 19 GPIO_ACTIVE_LOW
 		         &gpio0 18 GPIO_ACTIVE_LOW>;
-		gpio-fan,speed-map = <0    3
-		                      1500 2
-		                      3250 1
-		                      5000 0>;
+		gpio-fan,speed-map =
+				<0    3>,
+				<1500 2>,
+				<3250 1>,
+				<5000 0>;
 		alarm-gpios = <&gpio1 8 GPIO_ACTIVE_HIGH>;
 	};
 
diff --git a/arch/arm/boot/dts/marvell/kirkwood-ns2max.dts b/arch/arm/boot/dts/marvell/kirkwood-ns2max.dts
index c0a087e77408..044958bc55da 100644
--- a/arch/arm/boot/dts/marvell/kirkwood-ns2max.dts
+++ b/arch/arm/boot/dts/marvell/kirkwood-ns2max.dts
@@ -29,15 +29,15 @@
 			 &gpio1  1 GPIO_ACTIVE_LOW
 			 &gpio0 23 GPIO_ACTIVE_LOW>;
 		gpio-fan,speed-map =
-			<   0  0
-			 1500 15
-			 1700 14
-			 1800 13
-			 2100 12
-			 3100 11
-			 3300 10
-			 4300  9
-			 5500  8>;
+			<   0  0>,
+			<1500 15>,
+			<1700 14>,
+			<1800 13>,
+			<2100 12>,
+			<3100 11>,
+			<3300 10>,
+			<4300  9>,
+			<5500  8>;
 		alarm-gpios = <&gpio0 25 GPIO_ACTIVE_LOW>;
 	};
 
diff --git a/arch/arm/boot/dts/marvell/kirkwood-ns2mini.dts b/arch/arm/boot/dts/marvell/kirkwood-ns2mini.dts
index 5b9fa14b6428..3fbe008f9141 100644
--- a/arch/arm/boot/dts/marvell/kirkwood-ns2mini.dts
+++ b/arch/arm/boot/dts/marvell/kirkwood-ns2mini.dts
@@ -30,15 +30,15 @@
 			 &gpio1  1 GPIO_ACTIVE_LOW
 			 &gpio0 23 GPIO_ACTIVE_LOW>;
 		gpio-fan,speed-map =
-			<   0  0
-			 3000 15
-			 3180 14
-			 4140 13
-			 4570 12
-			 6760 11
-			 7140 10
-			 7980  9
-			 9200  8>;
+			<   0  0>,
+			<3000 15>,
+			<3180 14>,
+			<4140 13>,
+			<4570 12>,
+			<6760 11>,
+			<7140 10>,
+			<7980  9>,
+			<9200  8>;
 		alarm-gpios = <&gpio0 25 GPIO_ACTIVE_LOW>;
 	};
 
diff --git a/arch/arm/boot/dts/marvell/kirkwood-synology.dtsi b/arch/arm/boot/dts/marvell/kirkwood-synology.dtsi
index 9b6666020cdd..20964eb48fd7 100644
--- a/arch/arm/boot/dts/marvell/kirkwood-synology.dtsi
+++ b/arch/arm/boot/dts/marvell/kirkwood-synology.dtsi
@@ -286,14 +286,15 @@
 		gpios = <&gpio1 0 GPIO_ACTIVE_HIGH
 			 &gpio1 1 GPIO_ACTIVE_HIGH
 			 &gpio1 2 GPIO_ACTIVE_HIGH>;
-		gpio-fan,speed-map = <    0 0
-				       2200 1
-				       2500 2
-				       3000 4
-				       3300 3
-				       3700 5
-				       3800 6
-				       4200 7 >;
+		gpio-fan,speed-map =
+				<   0 0>,
+				<2200 1>,
+				<2500 2>,
+				<3000 4>,
+				<3300 3>,
+				<3700 5>,
+				<3800 6>,
+				<4200 7>;
 	};
 
 	gpio-fan-150-15-18 {
@@ -306,14 +307,15 @@
 			 &gpio0 16 GPIO_ACTIVE_HIGH
 			 &gpio0 17 GPIO_ACTIVE_HIGH>;
 		alarm-gpios = <&gpio0 18 GPIO_ACTIVE_HIGH>;
-		gpio-fan,speed-map = <    0 0
-				       2200 1
-				       2500 2
-				       3000 4
-				       3300 3
-				       3700 5
-				       3800 6
-				       4200 7 >;
+		gpio-fan,speed-map =
+				<   0 0>,
+				<2200 1>,
+				<2500 2>,
+				<3000 4>,
+				<3300 3>,
+				<3700 5>,
+				<3800 6>,
+				<4200 7>;
 	};
 
 	gpio-fan-100-32-35 {
@@ -326,14 +328,15 @@
 			 &gpio1 1 GPIO_ACTIVE_HIGH
 			 &gpio1 2 GPIO_ACTIVE_HIGH>;
 		alarm-gpios = <&gpio1 3 GPIO_ACTIVE_HIGH>;
-		gpio-fan,speed-map = <    0 0
-				       2500 1
-				       3100 2
-				       3800 3
-				       4600 4
-				       4800 5
-				       4900 6
-				       5000 7 >;
+		gpio-fan,speed-map =
+				<   0 0>,
+				<2500 1>,
+				<3100 2>,
+				<3800 3>,
+				<4600 4>,
+				<4800 5>,
+				<4900 6>,
+				<5000 7>;
 	};
 
 	gpio-fan-100-15-18 {
@@ -346,14 +349,15 @@
 			 &gpio0 16 GPIO_ACTIVE_HIGH
 			 &gpio0 17 GPIO_ACTIVE_HIGH>;
 		alarm-gpios = <&gpio0 18 GPIO_ACTIVE_HIGH>;
-		gpio-fan,speed-map = <    0 0
-				       2500 1
-				       3100 2
-				       3800 3
-				       4600 4
-				       4800 5
-				       4900 6
-				       5000 7 >;
+		gpio-fan,speed-map =
+				<   0 0>,
+				<2500 1>,
+				<3100 2>,
+				<3800 3>,
+				<4600 4>,
+				<4800 5>,
+				<4900 6>,
+				<5000 7>;
 	};
 
 	gpio-fan-100-15-35-1 {
@@ -366,14 +370,15 @@
 			 &gpio0 16 GPIO_ACTIVE_HIGH
 			 &gpio0 17 GPIO_ACTIVE_HIGH>;
 		alarm-gpios = <&gpio1 3 GPIO_ACTIVE_HIGH>;
-		gpio-fan,speed-map = <    0 0
-				       2500 1
-				       3100 2
-				       3800 3
-				       4600 4
-				       4800 5
-				       4900 6
-				       5000 7 >;
+		gpio-fan,speed-map =
+				<   0 0>,
+				<2500 1>,
+				<3100 2>,
+				<3800 3>,
+				<4600 4>,
+				<4800 5>,
+				<4900 6>,
+				<5000 7>;
 	};
 
 	gpio-fan-100-15-35-3 {
@@ -388,14 +393,15 @@
 		alarm-gpios = <&gpio1 3 GPIO_ACTIVE_HIGH
 			       &gpio1 12 GPIO_ACTIVE_HIGH
 			       &gpio1 13 GPIO_ACTIVE_HIGH>;
-		gpio-fan,speed-map = <    0 0
-				       2500 1
-				       3100 2
-				       3800 3
-				       4600 4
-				       4800 5
-				       4900 6
-				       5000 7 >;
+		gpio-fan,speed-map =
+				<   0 0>,
+				<2500 1>,
+				<3100 2>,
+				<3800 3>,
+				<4600 4>,
+				<4800 5>,
+				<4900 6>,
+				<5000 7>;
 	};
 
 	gpio-leds-alarm-12 {
diff --git a/arch/arm/boot/dts/marvell/mvebu-linkstation-fan.dtsi b/arch/arm/boot/dts/marvell/mvebu-linkstation-fan.dtsi
index e172029a0c4d..a260c42dbda3 100644
--- a/arch/arm/boot/dts/marvell/mvebu-linkstation-fan.dtsi
+++ b/arch/arm/boot/dts/marvell/mvebu-linkstation-fan.dtsi
@@ -50,10 +50,10 @@
 		pinctrl-names = "default";
 
 		gpio-fan,speed-map =
-			<0		3
-			1500	2
-			3250	1
-			5000	0>;
+			<   0 3>,
+			<1500 2>,
+			<3250 1>,
+			<5000 0>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/microchip/at91-sam9x60_curiosity.dts b/arch/arm/boot/dts/microchip/at91-sam9x60_curiosity.dts
index 83372c1f291b..c6fbdd29019f 100644
--- a/arch/arm/boot/dts/microchip/at91-sam9x60_curiosity.dts
+++ b/arch/arm/boot/dts/microchip/at91-sam9x60_curiosity.dts
@@ -249,6 +249,8 @@
 
 	ethernet-phy@0 {
 		reg = <0x0>;
+		interrupt-parent = <&pioB>;
+		interrupts = <8 IRQ_TYPE_LEVEL_LOW>;
 	};
 };
 
@@ -353,6 +355,7 @@
 				 AT91_PIOB 5 AT91_PERIPH_A AT91_PINCTRL_NONE	/* PB5 periph A */
 				 AT91_PIOB 6 AT91_PERIPH_A AT91_PINCTRL_NONE	/* PB6 periph A */
 				 AT91_PIOB 7 AT91_PERIPH_A AT91_PINCTRL_NONE	/* PB7 periph A */
+				 AT91_PIOB 8 AT91_PERIPH_GPIO AT91_PINCTRL_NONE	/* PB8 IRQ GPIO */
 				 AT91_PIOB 9 AT91_PERIPH_A AT91_PINCTRL_NONE	/* PB9 periph A */
 				 AT91_PIOB 10 AT91_PERIPH_A AT91_PINCTRL_NONE>;	/* PB10 periph A */
 		};
diff --git a/arch/arm/boot/dts/microchip/at91-sam9x60ek.dts b/arch/arm/boot/dts/microchip/at91-sam9x60ek.dts
index 5cd593028aff..f3cbb675cea4 100644
--- a/arch/arm/boot/dts/microchip/at91-sam9x60ek.dts
+++ b/arch/arm/boot/dts/microchip/at91-sam9x60ek.dts
@@ -292,6 +292,8 @@
 
 	ethernet-phy@0 {
 		reg = <0x0>;
+		interrupt-parent = <&pioB>;
+		interrupts = <8 IRQ_TYPE_LEVEL_LOW>;
 	};
 };
 
@@ -465,6 +467,7 @@
 				 AT91_PIOB 5 AT91_PERIPH_A AT91_PINCTRL_NONE	/* PB5 periph A */
 				 AT91_PIOB 6 AT91_PERIPH_A AT91_PINCTRL_NONE	/* PB6 periph A */
 				 AT91_PIOB 7 AT91_PERIPH_A AT91_PINCTRL_NONE	/* PB7 periph A */
+				 AT91_PIOB 8 AT91_PERIPH_GPIO AT91_PINCTRL_NONE	/* PB8 IRQ GPIO */
 				 AT91_PIOB 9 AT91_PERIPH_A AT91_PINCTRL_NONE	/* PB9 periph A */
 				 AT91_PIOB 10 AT91_PERIPH_A AT91_PINCTRL_NONE>;	/* PB10 periph A */
 		};
diff --git a/arch/arm/boot/dts/microchip/at91-sama5d27_som1_ek.dts b/arch/arm/boot/dts/microchip/at91-sama5d27_som1_ek.dts
index d0a6dbd377df..f3ffb8f01d8a 100644
--- a/arch/arm/boot/dts/microchip/at91-sama5d27_som1_ek.dts
+++ b/arch/arm/boot/dts/microchip/at91-sama5d27_som1_ek.dts
@@ -54,7 +54,6 @@
 
 		sdmmc0: sdio-host@a0000000 {
 			bus-width = <8>;
-			mmc-ddr-3_3v;
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_sdmmc0_default>;
 			status = "okay";
diff --git a/arch/arm/boot/dts/microchip/at91-sama5d27_wlsom1_ek.dts b/arch/arm/boot/dts/microchip/at91-sama5d27_wlsom1_ek.dts
index e055b9e2fe34..15239834d886 100644
--- a/arch/arm/boot/dts/microchip/at91-sama5d27_wlsom1_ek.dts
+++ b/arch/arm/boot/dts/microchip/at91-sama5d27_wlsom1_ek.dts
@@ -197,7 +197,6 @@
 
 &sdmmc0 {
 	bus-width = <4>;
-	mmc-ddr-3_3v;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_sdmmc0_default>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/nxp/imx/imx1-ads.dts b/arch/arm/boot/dts/nxp/imx/imx1-ads.dts
index 5833fb6f15d8..2c817c4a4c68 100644
--- a/arch/arm/boot/dts/nxp/imx/imx1-ads.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx1-ads.dts
@@ -65,7 +65,7 @@
 	pinctrl-0 = <&pinctrl_weim>;
 	status = "okay";
 
-	nor: nor@0,0 {
+	nor: flash@0,0 {
 		compatible = "cfi-flash";
 		reg = <0 0x00000000 0x02000000>;
 		bank-width = <4>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx1-apf9328.dts b/arch/arm/boot/dts/nxp/imx/imx1-apf9328.dts
index 1f11e9542a72..e66eef87a7a4 100644
--- a/arch/arm/boot/dts/nxp/imx/imx1-apf9328.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx1-apf9328.dts
@@ -45,7 +45,7 @@
 	pinctrl-0 = <&pinctrl_weim>;
 	status = "okay";
 
-	nor: nor@0,0 {
+	nor: flash@0,0 {
 		compatible = "cfi-flash";
 		reg = <0 0x00000000 0x02000000>;
 		bank-width = <2>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx1.dtsi b/arch/arm/boot/dts/nxp/imx/imx1.dtsi
index e312f1e74e2f..1ac10965fdfd 100644
--- a/arch/arm/boot/dts/nxp/imx/imx1.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx1.dtsi
@@ -68,7 +68,7 @@
 		interrupt-parent = <&aitc>;
 		ranges;
 
-		aipi@200000 {
+		bus@200000 {
 			compatible = "fsl,aipi-bus", "simple-bus";
 			#address-cells = <1>;
 			#size-cells = <1>;
@@ -155,7 +155,7 @@
 			};
 		};
 
-		aipi@210000 {
+		bus@210000 {
 			compatible = "fsl,aipi-bus", "simple-bus";
 			#address-cells = <1>;
 			#size-cells = <1>;
@@ -268,9 +268,12 @@
 			status = "disabled";
 		};
 
-		esram: esram@300000 {
+		esram: sram@300000 {
 			compatible = "mmio-sram";
 			reg = <0x00300000 0x20000>;
+			ranges = <0 0x00300000 0x20000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/nxp/imx/imx25-eukrea-cpuimx25.dtsi b/arch/arm/boot/dts/nxp/imx/imx25-eukrea-cpuimx25.dtsi
index 0703f62d10d1..93a6e4e680b4 100644
--- a/arch/arm/boot/dts/nxp/imx/imx25-eukrea-cpuimx25.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx25-eukrea-cpuimx25.dtsi
@@ -27,7 +27,7 @@
 	pinctrl-0 = <&pinctrl_i2c1>;
 	status = "okay";
 
-	pcf8563@51 {
+	rtc@51 {
 		compatible = "nxp,pcf8563";
 		reg = <0x51>;
 	};
diff --git a/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-cmo-qvga.dts b/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-cmo-qvga.dts
index fc8a502fc957..6cddb2cc36fe 100644
--- a/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-cmo-qvga.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-cmo-qvga.dts
@@ -16,7 +16,7 @@
 		bus-width = <18>;
 		display-timings {
 			native-mode = <&qvga_timings>;
-			qvga_timings: 320x240 {
+			qvga_timings: timing0 {
 				clock-frequency = <6500000>;
 				hactive = <320>;
 				vactive = <240>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-dvi-svga.dts b/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-dvi-svga.dts
index 80a7f96de4c6..64b2ffac463b 100644
--- a/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-dvi-svga.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-dvi-svga.dts
@@ -16,7 +16,7 @@
 		bus-width = <18>;
 		display-timings {
 			native-mode = <&dvi_svga_timings>;
-			dvi_svga_timings: 800x600 {
+			dvi_svga_timings: timing0 {
 				clock-frequency = <40000000>;
 				hactive = <800>;
 				vactive = <600>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dts b/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dts
index 24027a1fb46d..fb074bfdaa8d 100644
--- a/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dts
@@ -16,7 +16,7 @@
 		bus-width = <18>;
 		display-timings {
 			native-mode = <&dvi_vga_timings>;
-			dvi_vga_timings: 640x480 {
+			dvi_vga_timings: timing0 {
 				clock-frequency = <31250000>;
 				hactive = <640>;
 				vactive = <480>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx25-pdk.dts b/arch/arm/boot/dts/nxp/imx/imx25-pdk.dts
index 04f4b127a172..dd176fb54e58 100644
--- a/arch/arm/boot/dts/nxp/imx/imx25-pdk.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx25-pdk.dts
@@ -68,7 +68,7 @@
 		bus-width = <18>;
 		display-timings {
 			native-mode = <&wvga_timings>;
-			wvga_timings: 640x480 {
+			wvga_timings: timing0 {
 				hactive = <640>;
 				vactive = <480>;
 				hback-porch = <45>;
@@ -122,6 +122,7 @@
 	codec: sgtl5000@a {
 		compatible = "fsl,sgtl5000";
 		reg = <0x0a>;
+		#sound-dai-cells = <0>;
 		clocks = <&clks 129>;
 		VDDA-supply = <&reg_2p5v>;
 		VDDIO-supply = <&reg_3p3v>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx25.dtsi b/arch/arm/boot/dts/nxp/imx/imx25.dtsi
index 534c70b8d79d..9cfff2151b7e 100644
--- a/arch/arm/boot/dts/nxp/imx/imx25.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx25.dtsi
@@ -68,6 +68,16 @@
 		};
 	};
 
+	usbphy0: usb-phy0 {
+		compatible = "usb-nop-xceiv";
+		#phy-cells = <0>;
+	};
+
+	usbphy1: usb-phy1 {
+		compatible = "usb-nop-xceiv";
+		#phy-cells = <0>;
+	};
+
 	soc: soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -93,7 +103,7 @@
 				compatible = "fsl,imx25-i2c", "fsl,imx21-i2c";
 				reg = <0x43f80000 0x4000>;
 				clocks = <&clks 48>;
-				clock-names = "";
+				clock-names = "ipg";
 				interrupts = <3>;
 				status = "disabled";
 			};
@@ -104,7 +114,7 @@
 				compatible = "fsl,imx25-i2c", "fsl,imx21-i2c";
 				reg = <0x43f84000 0x4000>;
 				clocks = <&clks 48>;
-				clock-names = "";
+				clock-names = "ipg";
 				interrupts = <10>;
 				status = "disabled";
 			};
@@ -151,7 +161,7 @@
 				compatible = "fsl,imx25-i2c", "fsl,imx21-i2c";
 				reg = <0x43f98000 0x4000>;
 				clocks = <&clks 48>;
-				clock-names = "";
+				clock-names = "ipg";
 				interrupts = <4>;
 				status = "disabled";
 			};
@@ -178,12 +188,9 @@
 			};
 
 			kpp: kpp@43fa8000 {
-				#address-cells = <1>;
-				#size-cells = <0>;
 				compatible = "fsl,imx25-kpp", "fsl,imx21-kpp";
 				reg = <0x43fa8000 0x4000>;
 				clocks = <&clks 102>;
-				clock-names = "";
 				interrupts = <24>;
 				status = "disabled";
 			};
@@ -542,7 +549,7 @@
 			};
 
 			iim: efuse@53ff0000 {
-				compatible = "fsl,imx25-iim", "fsl,imx27-iim";
+				compatible = "fsl,imx25-iim";
 				reg = <0x53ff0000 0x4000>;
 				interrupts = <19>;
 				clocks = <&clks 99>;
@@ -597,7 +604,7 @@
 			#size-cells = <1>;
 		};
 
-		emi@80000000 {
+		bus@80000000 {
 			compatible = "fsl,emi-bus", "simple-bus";
 			#address-cells = <1>;
 			#size-cells = <1>;
@@ -617,22 +624,4 @@
 			};
 		};
 	};
-
-	usbphy {
-		compatible = "simple-bus";
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		usbphy0: usb-phy@0 {
-			reg = <0>;
-			compatible = "usb-nop-xceiv";
-			#phy-cells = <0>;
-		};
-
-		usbphy1: usb-phy@1 {
-			reg = <1>;
-			compatible = "usb-nop-xceiv";
-			#phy-cells = <0>;
-		};
-	};
 };
diff --git a/arch/arm/boot/dts/nxp/imx/imx27-apf27dev.dts b/arch/arm/boot/dts/nxp/imx/imx27-apf27dev.dts
index a21f1f7c24b8..849306cb4532 100644
--- a/arch/arm/boot/dts/nxp/imx/imx27-apf27dev.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx27-apf27dev.dts
@@ -16,7 +16,7 @@
 		fsl,pcr = <0xfae80083>;	/* non-standard but required */
 		display-timings {
 			native-mode = <&timing0>;
-			timing0: 800x480 {
+			timing0: timing0 {
 				clock-frequency = <33000033>;
 				hactive = <800>;
 				vactive = <480>;
@@ -47,7 +47,7 @@
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_gpio_leds>;
 
-		user {
+		led-user {
 			label = "Heartbeat";
 			gpios = <&gpio6 14 GPIO_ACTIVE_HIGH>;
 			linux,default-trigger = "heartbeat";
diff --git a/arch/arm/boot/dts/nxp/imx/imx27-eukrea-cpuimx27.dtsi b/arch/arm/boot/dts/nxp/imx/imx27-eukrea-cpuimx27.dtsi
index 74110bbcd9d4..c7e923584878 100644
--- a/arch/arm/boot/dts/nxp/imx/imx27-eukrea-cpuimx27.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx27-eukrea-cpuimx27.dtsi
@@ -33,7 +33,7 @@
 	pinctrl-0 = <&pinctrl_i2c1>;
 	status = "okay";
 
-	pcf8563@51 {
+	rtc@51 {
 		compatible = "nxp,pcf8563";
 		reg = <0x51>;
 	};
@@ -90,7 +90,7 @@
 &weim {
 	status = "okay";
 
-	nor: nor@0,0 {
+	nor: flash@0,0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		compatible = "cfi-flash";
diff --git a/arch/arm/boot/dts/nxp/imx/imx27-eukrea-mbimxsd27-baseboard.dts b/arch/arm/boot/dts/nxp/imx/imx27-eukrea-mbimxsd27-baseboard.dts
index 145e459625b3..d78793601306 100644
--- a/arch/arm/boot/dts/nxp/imx/imx27-eukrea-mbimxsd27-baseboard.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx27-eukrea-mbimxsd27-baseboard.dts
@@ -16,7 +16,7 @@
 
 		display-timings {
 			native-mode = <&timing0>;
-			timing0: 320x240 {
+			timing0: timing0 {
 				clock-frequency = <6500000>;
 				hactive = <320>;
 				vactive = <240>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx27-pdk.dts b/arch/arm/boot/dts/nxp/imx/imx27-pdk.dts
index 35123b7cb6b3..21d436972aa4 100644
--- a/arch/arm/boot/dts/nxp/imx/imx27-pdk.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx27-pdk.dts
@@ -14,18 +14,12 @@
 		reg = <0xa0000000 0x08000000>;
 	};
 
-	usbphy {
-		compatible = "simple-bus";
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		usbphy0: usbphy@0 {
-			compatible = "usb-nop-xceiv";
-			reg = <0>;
-			clocks = <&clks IMX27_CLK_DUMMY>;
-			clock-names = "main_clk";
-			#phy-cells = <0>;
-		};
+
+	usbphy0: usbphy {
+		compatible = "usb-nop-xceiv";
+		clocks = <&clks IMX27_CLK_DUMMY>;
+		clock-names = "main_clk";
+		#phy-cells = <0>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycard-s-rdk.dts b/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycard-s-rdk.dts
index 25442eba21c1..27c93b9fe049 100644
--- a/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycard-s-rdk.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycard-s-rdk.dts
@@ -19,7 +19,7 @@
 		fsl,pcr = <0xf0c88080>;	/* non-standard but required */
 		display-timings {
 			native-mode = <&timing0>;
-			timing0: 640x480 {
+			timing0: timing0 {
 				hactive = <640>;
 				vactive = <480>;
 				hback-porch = <112>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-rdk.dts b/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-rdk.dts
index 7f0cd4d3ec2d..b8048e12e3d9 100644
--- a/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-rdk.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-rdk.dts
@@ -19,7 +19,7 @@
 
 		display-timings {
 			native-mode = <&timing0>;
-			timing0: 240x320 {
+			timing0: timing0 {
 				clock-frequency = <5500000>;
 				hactive = <240>;
 				vactive = <320>;
@@ -48,15 +48,12 @@
 		regulator-always-on;
 	};
 
-	usbphy {
-		usbphy2: usbphy@2 {
-			compatible = "usb-nop-xceiv";
-			reg = <2>;
-			vcc-supply = <&reg_5v0>;
-			clocks = <&clks IMX27_CLK_DUMMY>;
-			clock-names = "main_clk";
-			#phy-cells = <0>;
-		};
+	usbphy2: usbphy {
+		compatible = "usb-nop-xceiv";
+		vcc-supply = <&reg_5v0>;
+		clocks = <&clks IMX27_CLK_DUMMY>;
+		clock-names = "main_clk";
+		#phy-cells = <0>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-som.dtsi b/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-som.dtsi
index 7b2ea4cdae58..e958d7286ae9 100644
--- a/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-som.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-som.dtsi
@@ -29,19 +29,13 @@
 		regulator-max-microvolt = <5000000>;
 	};
 
-	usbphy {
-		compatible = "simple-bus";
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		usbphy0: usbphy@0 {
-			compatible = "usb-nop-xceiv";
-			reg = <0>;
-			vcc-supply = <&sw3_reg>;
-			clocks = <&clks IMX27_CLK_DUMMY>;
-			clock-names = "main_clk";
-			#phy-cells = <0>;
-		};
+
+	usbphy0: usbphy {
+		compatible = "usb-nop-xceiv";
+		vcc-supply = <&sw3_reg>;
+		clocks = <&clks IMX27_CLK_DUMMY>;
+		clock-names = "main_clk";
+		#phy-cells = <0>;
 	};
 };
 
@@ -49,12 +43,12 @@
 	status = "okay";
 
 	/* SSI0 <=> PINS_4 (MC13783 Audio) */
-	ssi0 {
+	mux-ssi0 {
 		fsl,audmux-port = <0>;
 		fsl,port-config = <0xcb205000>;
 	};
 
-	pins4 {
+	mux-pins4 {
 		fsl,audmux-port = <2>;
 		fsl,port-config = <0x00001000>;
 	};
@@ -186,7 +180,7 @@
 		reg = <0x52>;
 	};
 
-	pcf8563@51 {
+	rtc@51 {
 		compatible = "nxp,pcf8563";
 		reg = <0x51>;
 	};
@@ -314,7 +308,7 @@
 &weim {
 	status = "okay";
 
-	nor: nor@0,0 {
+	nor: flash@0,0 {
 		compatible = "cfi-flash";
 		reg = <0 0x00000000 0x02000000>;
 		bank-width = <2>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx27.dtsi b/arch/arm/boot/dts/nxp/imx/imx27.dtsi
index faba12ee7465..ec472695c71e 100644
--- a/arch/arm/boot/dts/nxp/imx/imx27.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx27.dtsi
@@ -81,7 +81,7 @@
 		interrupt-parent = <&aitc>;
 		ranges;
 
-		aipi1: aipi@10000000 { /* AIPI1 */
+		aipi1: bus@10000000 { /* AIPI1 */
 			compatible = "fsl,aipi-bus", "simple-bus";
 			#address-cells = <1>;
 			#size-cells = <1>;
@@ -453,7 +453,7 @@
 			};
 		};
 
-		aipi2: aipi@10020000 { /* AIPI2 */
+		aipi2: bus@10020000 { /* AIPI2 */
 			compatible = "fsl,aipi-bus", "simple-bus";
 			#address-cells = <1>;
 			#size-cells = <1>;
@@ -588,6 +588,9 @@
 		iram: sram@ffff4c00 {
 			compatible = "mmio-sram";
 			reg = <0xffff4c00 0xb400>;
+			ranges = <0 0xffff4c00 0xb400>;
+			#address-cells = <1>;
+			#size-cells = <1>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/nxp/imx/imx53-cx9020.dts b/arch/arm/boot/dts/nxp/imx/imx53-cx9020.dts
index 055d23a9aee7..0814f5665a59 100644
--- a/arch/arm/boot/dts/nxp/imx/imx53-cx9020.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx53-cx9020.dts
@@ -22,7 +22,7 @@
 	};
 
 	display-0 {
-		#address-cells =<1>;
+		#address-cells = <1>;
 		#size-cells = <0>;
 		compatible = "fsl,imx-parallel-display";
 		interface-pix-fmt = "rgb24";
diff --git a/arch/arm/boot/dts/nxp/imx/imx6dl-b105pv2.dts b/arch/arm/boot/dts/nxp/imx/imx6dl-b105pv2.dts
index 7d4ae113c381..63cdf24eb397 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6dl-b105pv2.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx6dl-b105pv2.dts
@@ -22,7 +22,7 @@
 		compatible = "ilitek,ili251x";
 		reg = <0x41>;
 		pinctrl-names = "default";
-		pinctrl-0 =<&pinctrl_q7_gpio0>;
+		pinctrl-0 = <&pinctrl_q7_gpio0>;
 		interrupt-parent = <&gpio5>;
 		interrupts = <2 IRQ_TYPE_EDGE_FALLING>;
 		reset-gpios = <&tca6424a 21 GPIO_ACTIVE_LOW>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx6dl-b105v2.dts b/arch/arm/boot/dts/nxp/imx/imx6dl-b105v2.dts
index 9c5938e16d99..2e75d700efdb 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6dl-b105v2.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx6dl-b105v2.dts
@@ -22,7 +22,7 @@
 		compatible = "ilitek,ili251x";
 		reg = <0x41>;
 		pinctrl-names = "default";
-		pinctrl-0 =<&pinctrl_q7_gpio0>;
+		pinctrl-0 = <&pinctrl_q7_gpio0>;
 		interrupt-parent = <&gpio5>;
 		interrupts = <2 IRQ_TYPE_EDGE_FALLING>;
 		reset-gpios = <&tca6424a 21 GPIO_ACTIVE_LOW>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx6dl-b125pv2.dts b/arch/arm/boot/dts/nxp/imx/imx6dl-b125pv2.dts
index 01df7cffcef2..94625d5d5918 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6dl-b125pv2.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx6dl-b125pv2.dts
@@ -22,7 +22,7 @@
 		compatible = "eeti,exc80h60";
 		reg = <0x2a>;
 		pinctrl-names = "default";
-		pinctrl-0 =<&pinctrl_q7_gpio0>;
+		pinctrl-0 = <&pinctrl_q7_gpio0>;
 		interrupt-parent = <&gpio5>;
 		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
 		reset-gpios = <&tca6424a 21 GPIO_ACTIVE_HIGH>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx6dl-b125v2.dts b/arch/arm/boot/dts/nxp/imx/imx6dl-b125v2.dts
index a015453daf10..b3cfa8110ade 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6dl-b125v2.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx6dl-b125v2.dts
@@ -22,7 +22,7 @@
 		compatible = "eeti,exc80h60";
 		reg = <0x2a>;
 		pinctrl-names = "default";
-		pinctrl-0 =<&pinctrl_q7_gpio0>;
+		pinctrl-0 = <&pinctrl_q7_gpio0>;
 		interrupt-parent = <&gpio5>;
 		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
 		reset-gpios = <&tca6424a 21 GPIO_ACTIVE_HIGH>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx6dl-b155v2.dts b/arch/arm/boot/dts/nxp/imx/imx6dl-b155v2.dts
index b71ee6b79208..7edc788bcb8f 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6dl-b155v2.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx6dl-b155v2.dts
@@ -22,7 +22,7 @@
 		compatible = "eeti,exc80h84";
 		reg = <0x2a>;
 		pinctrl-names = "default";
-		pinctrl-0 =<&pinctrl_q7_gpio0>;
+		pinctrl-0 = <&pinctrl_q7_gpio0>;
 		interrupt-parent = <&gpio5>;
 		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
 		touchscreen-inverted-x;
diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-apalis-ixora-v1.2.dts b/arch/arm/boot/dts/nxp/imx/imx6q-apalis-ixora-v1.2.dts
index 717decda0ceb..3ac7a4501620 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6q-apalis-ixora-v1.2.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx6q-apalis-ixora-v1.2.dts
@@ -76,6 +76,7 @@
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_enable_can1_power>;
 		regulator-name = "can1_supply";
+		startup-delay-us = <1000>;
 	};
 
 	reg_can2_supply: regulator-can2-supply {
@@ -85,6 +86,7 @@
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_enable_can2_power>;
 		regulator-name = "can2_supply";
+		startup-delay-us = <1000>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-skov-reve-mi1010ait-1cp1.dts b/arch/arm/boot/dts/nxp/imx/imx6q-skov-reve-mi1010ait-1cp1.dts
index a3f247c722b4..0342a79ccd5d 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6q-skov-reve-mi1010ait-1cp1.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx6q-skov-reve-mi1010ait-1cp1.dts
@@ -37,9 +37,9 @@
 
 &clks {
 	assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>,
-			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>;
+			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>, <&clks IMX6QDL_CLK_ENET_REF_SEL>;
 	assigned-clock-parents = <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>,
-				 <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>;
+				 <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>, <&clk50m_phy>;
 };
 
 &hdmi {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-var-mx6customboard.dts b/arch/arm/boot/dts/nxp/imx/imx6q-var-mx6customboard.dts
index 6f9d094dd6d0..18a620832a2a 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6q-var-mx6customboard.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx6q-var-mx6customboard.dts
@@ -16,7 +16,7 @@
 	compatible = "variscite,mx6customboard", "variscite,var-som-imx6q", "fsl,imx6q";
 
 	panel0: lvds-panel0 {
-		compatible =  "panel-lvds";
+		compatible = "panel-lvds";
 		backlight = <&backlight_lvds>;
 		width-mm = <152>;
 		height-mm = <91>;
@@ -43,7 +43,7 @@
 	};
 
 	panel1: lvds-panel1 {
-		compatible =  "panel-lvds";
+		compatible = "panel-lvds";
 		width-mm = <152>;
 		height-mm = <91>;
 		data-mapping = "jeida-18";
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi
index 4cc965277c52..2ae93f57fe5a 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi
@@ -12,6 +12,13 @@
 	model = "Toradex Apalis iMX6Q/D Module";
 	compatible = "toradex,apalis_imx6q", "fsl,imx6q";
 
+	aliases {
+		mmc0 = &usdhc3; /* eMMC */
+		mmc1 = &usdhc1; /* MMC1 slot */
+		mmc2 = &usdhc2; /* SD1 slot */
+		/delete-property/ mmc3;
+	};
+
 	/* Will be filled by the bootloader */
 	memory@10000000 {
 		device_type = "memory";
@@ -166,7 +173,7 @@
 	reg_usb_host_vbus: regulator-usb-host-vbus {
 		compatible = "regulator-fixed";
 		enable-active-high;
-		gpio =  <&gpio1 0 GPIO_ACTIVE_HIGH>;
+		gpio = <&gpio1 0 GPIO_ACTIVE_HIGH>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_regulator_usbh_pwr>;
 		regulator-max-microvolt = <5000000>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi
index 11d9c7a2dacb..55c90f6393ad 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi
@@ -12,6 +12,13 @@
 	model = "Toradex Colibri iMX6DL/S Module";
 	compatible = "toradex,colibri_imx6dl", "fsl,imx6dl";
 
+	aliases {
+		mmc0 = &usdhc3; /* eMMC */
+		mmc1 = &usdhc1; /* MMC/SD Slot */
+		/delete-property/ mmc2;
+		/delete-property/ mmc3;
+	};
+
 	backlight: backlight {
 		compatible = "pwm-backlight";
 		brightness-levels = <0 45 63 88 119 158 203 255>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-emcon-avari.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-emcon-avari.dtsi
index f1a41c76729c..5587069b6052 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-emcon-avari.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-emcon-avari.dtsi
@@ -54,7 +54,7 @@
 	clk_codec: clock-codec {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
-		clock-frequency  = <12000000>;
+		clock-frequency = <12000000>;
 	};
 
 	sound {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-mba6.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-mba6.dtsi
index da0f8dae1ea8..4d2abcd44eff 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-mba6.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-mba6.dtsi
@@ -500,21 +500,21 @@
 
 	pinctrl_pwm1: pwm1grp {
 		fsl,pins = <
-			/* 100 k PD, DSE 120 OHM, SPPEED LO */
+			/* 100 k PD, DSE 120 OHM, SPEED LO */
 			MX6QDL_PAD_GPIO_9__PWM1_OUT 0x00003050
 		>;
 	};
 
 	pinctrl_pwm3: pwm3grp {
 		fsl,pins = <
-			/* 100 k PD, DSE 120 OHM, SPPEED LO */
+			/* 100 k PD, DSE 120 OHM, SPEED LO */
 			MX6QDL_PAD_SD4_DAT1__PWM3_OUT 0x00003050
 		>;
 	};
 
 	pinctrl_pwm4: pwm4grp {
 		fsl,pins = <
-			/* 100 k PD, DSE 120 OHM, SPPEED LO */
+			/* 100 k PD, DSE 120 OHM, SPEED LO */
 			MX6QDL_PAD_SD4_DAT2__PWM4_OUT 0x00003050
 		>;
 	};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-skov-cpu-revc.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-skov-cpu-revc.dtsi
index b81799d7076a..596b3bb3ddd1 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-skov-cpu-revc.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-skov-cpu-revc.dtsi
@@ -25,7 +25,7 @@
 		compatible = "ti,tsc2046e-adc";
 		reg = <0>;
 		pinctrl-0 = <&pinctrl_touch>;
-		pinctrl-names ="default";
+		pinctrl-names = "default";
 		spi-max-frequency = <1000000>;
 		interrupts-extended = <&gpio3 19 IRQ_TYPE_LEVEL_LOW>;
 		#io-channel-cells = <1>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl.dtsi
index bda182edc589..81142c523fa8 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl.dtsi
@@ -475,7 +475,7 @@
 						<&sdma 20 23 1>, <&sdma 21 23 1>, <&sdma 22 23 1>;
 					dma-names = "rxa", "rxb", "rxc",
 							"txa", "txb", "txc";
-					fsl,asrc-rate  = <48000>;
+					fsl,asrc-rate = <48000>;
 					fsl,asrc-width = <16>;
 					status = "okay";
 				};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6sx.dtsi b/arch/arm/boot/dts/nxp/imx/imx6sx.dtsi
index f6b35923ad83..df3a375f0a3e 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6sx.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6sx.dtsi
@@ -418,7 +418,7 @@
 					       <&sdma 21 23 1>, <&sdma 22 23 1>;
 					dma-names = "rxa", "rxb", "rxc",
 						    "txa", "txb", "txc";
-					fsl,asrc-rate  = <48000>;
+					fsl,asrc-rate = <48000>;
 					fsl,asrc-width = <16>;
 					status = "okay";
 				};
@@ -1010,7 +1010,7 @@
 				clock-names = "ipg", "ahb", "per";
 				bus-width = <4>;
 				fsl,tuning-start-tap = <20>;
-				fsl,tuning-step= <2>;
+				fsl,tuning-step = <2>;
 				status = "disabled";
 			};
 
@@ -1024,7 +1024,7 @@
 				clock-names = "ipg", "ahb", "per";
 				bus-width = <4>;
 				fsl,tuning-start-tap = <20>;
-				fsl,tuning-step= <2>;
+				fsl,tuning-step = <2>;
 				status = "disabled";
 			};
 
@@ -1038,7 +1038,7 @@
 				clock-names = "ipg", "ahb", "per";
 				bus-width = <4>;
 				fsl,tuning-start-tap = <20>;
-				fsl,tuning-step= <2>;
+				fsl,tuning-step = <2>;
 				status = "disabled";
 			};
 
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-pico.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul-pico.dtsi
index 4ffe99ed55ca..07dcecbe485d 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ul-pico.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ul-pico.dtsi
@@ -121,6 +121,8 @@
 			max-speed = <100>;
 			interrupt-parent = <&gpio5>;
 			interrupts = <6 IRQ_TYPE_LEVEL_LOW>;
+			clocks = <&clks IMX6UL_CLK_ENET_REF>;
+			clock-names = "rmii-ref";
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul.dtsi
index 3b87d980e9f4..a27a7554c2e7 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ul.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ul.dtsi
@@ -364,7 +364,7 @@
 						<&sdma 20 23 1>, <&sdma 21 23 1>, <&sdma 22 23 1>;
 					dma-names = "rxa", "rxb", "rxc",
 						    "txa", "txb", "txc";
-					fsl,asrc-rate  = <48000>;
+					fsl,asrc-rate = <48000>;
 					fsl,asrc-width = <16>;
 					status = "okay";
 				};
diff --git a/arch/arm/boot/dts/nxp/imx/imx7-tqma7.dtsi b/arch/arm/boot/dts/nxp/imx/imx7-tqma7.dtsi
index fe42b0a46831..3fc3130f9def 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7-tqma7.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx7-tqma7.dtsi
@@ -128,11 +128,16 @@
 		};
 	};
 
-	/* NXP SE97BTP with temperature sensor + eeprom */
+	/* LM75A temperature sensor, TQMa7x 01xx */
+	lm75a: temperature-sensor@48 {
+		compatible = "national,lm75a";
+		reg = <0x48>;
+	};
+
+	/* NXP SE97BTP with temperature sensor + eeprom, TQMa7x 02xx */
 	se97b: temperature-sensor-eeprom@1e {
 		compatible = "nxp,se97b", "jedec,jc-42.4-temp";
 		reg = <0x1e>;
-		status = "okay";
 	};
 
 	/* ST M24C64 */
diff --git a/arch/arm/boot/dts/nxp/imx/imx7d-colibri-emmc.dtsi b/arch/arm/boot/dts/nxp/imx/imx7d-colibri-emmc.dtsi
index 3740e34ef99f..9670f45eab3b 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7d-colibri-emmc.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx7d-colibri-emmc.dtsi
@@ -11,6 +11,10 @@
 		/* Required to properly pass MAC addresses from bootloader. */
 		ethernet0 = &fec1;
 		ethernet1 = &fec2;
+		mmc0 = &usdhc3; /* eMMC */
+		mmc1 = &usdhc1; /* MMC/SD slot */
+		/delete-property/ mmc2;
+		/delete-property/ mmc3;
 	};
 
 	memory@80000000 {
diff --git a/arch/arm/boot/dts/nxp/imx/imx7d-meerkat96.dts b/arch/arm/boot/dts/nxp/imx/imx7d-meerkat96.dts
index dd8003bd1fc0..f0fda15f3020 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7d-meerkat96.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx7d-meerkat96.dts
@@ -212,7 +212,7 @@
 	keep-power-in-suspend;
 	wakeup-source;
 	vmmc-supply = <&reg_wlreg_on>;
-	vqmmc-supply =<&reg_3p3v>;
+	vqmmc-supply = <&reg_3p3v>;
 	status = "okay";
 
 	brcmf: wifi@1 {
diff --git a/arch/arm/boot/dts/nxp/imx/imx7d-pico.dtsi b/arch/arm/boot/dts/nxp/imx/imx7d-pico.dtsi
index c5eefe89cd99..8d5037ac03c7 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7d-pico.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx7d-pico.dtsi
@@ -108,6 +108,14 @@
 	assigned-clock-rates = <0>, <32768>;
 };
 
+&cpu0 {
+	cpu-supply = <&sw1a_reg>;
+};
+
+&cpu1 {
+	cpu-supply = <&sw1a_reg>;
+};
+
 &ecspi3 {
 	cs-gpios = <&gpio4 11 GPIO_ACTIVE_LOW>;
 	pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/nxp/imx/imx7d-smegw01.dts b/arch/arm/boot/dts/nxp/imx/imx7d-smegw01.dts
index 85b97b5f64e7..7ed27c7ad726 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7d-smegw01.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx7d-smegw01.dts
@@ -149,7 +149,7 @@
 
 &i2c2 {
 	pinctrl-names = "default";
-	pinctrl-0 =<&pinctrl_i2c2>;
+	pinctrl-0 = <&pinctrl_i2c2>;
 	clock-frequency = <100000>;
 	status = "okay";
 
diff --git a/arch/arm/boot/dts/nxp/imx/imx7d.dtsi b/arch/arm/boot/dts/nxp/imx/imx7d.dtsi
index 4b94b8afb55d..0484e349e064 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7d.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx7d.dtsi
@@ -217,9 +217,6 @@
 };
 
 &ca_funnel_in_ports {
-	#address-cells = <1>;
-	#size-cells = <0>;
-
 	port@1 {
 		reg = <1>;
 		ca_funnel_in_port1: endpoint {
diff --git a/arch/arm/boot/dts/nxp/imx/imx7s.dtsi b/arch/arm/boot/dts/nxp/imx/imx7s.dtsi
index 29b8fd03567a..ebf7befcc11e 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7s.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx7s.dtsi
@@ -183,6 +183,15 @@
 		interrupt-parent = <&gpc>;
 		ranges;
 
+		ocram: sram@900000 {
+			compatible = "mmio-sram";
+			reg = <0x00900000 0x20000>;
+			ranges = <0 0x00900000 0x20000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			clocks = <&clks IMX7D_OCRAM_CLK>;
+		};
+
 		funnel@30041000 {
 			compatible = "arm,coresight-dynamic-funnel", "arm,primecell";
 			reg = <0x30041000 0x1000>;
@@ -190,7 +199,11 @@
 			clock-names = "apb_pclk";
 
 			ca_funnel_in_ports: in-ports {
-				port {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
 					ca_funnel_in_port0: endpoint {
 						remote-endpoint = <&etm0_out_port>;
 					};
@@ -454,7 +467,7 @@
 			};
 
 			gpt1: timer@302d0000 {
-				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
+				compatible = "fsl,imx7d-gpt", "fsl,imx6dl-gpt";
 				reg = <0x302d0000 0x10000>;
 				interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX7D_GPT1_ROOT_CLK>,
@@ -463,7 +476,7 @@
 			};
 
 			gpt2: timer@302e0000 {
-				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
+				compatible = "fsl,imx7d-gpt", "fsl,imx6dl-gpt";
 				reg = <0x302e0000 0x10000>;
 				interrupts = <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX7D_GPT2_ROOT_CLK>,
@@ -473,7 +486,7 @@
 			};
 
 			gpt3: timer@302f0000 {
-				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
+				compatible = "fsl,imx7d-gpt", "fsl,imx6dl-gpt";
 				reg = <0x302f0000 0x10000>;
 				interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX7D_GPT3_ROOT_CLK>,
@@ -483,7 +496,7 @@
 			};
 
 			gpt4: timer@30300000 {
-				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
+				compatible = "fsl,imx7d-gpt", "fsl,imx6dl-gpt";
 				reg = <0x30300000 0x10000>;
 				interrupts = <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX7D_GPT4_ROOT_CLK>,
@@ -605,6 +618,7 @@
 					nvmem-cells = <&tempmon_calib>,	<&fuse_grade>;
 					nvmem-cell-names = "calib", "temp_grade";
 					clocks = <&clks IMX7D_PLL_SYS_MAIN_CLK>;
+					#thermal-sensor-cells = <0>;
 				};
 			};
 
@@ -720,6 +734,8 @@
 				clocks = <&clks IMX7D_ECSPI4_ROOT_CLK>,
 					<&clks IMX7D_ECSPI4_ROOT_CLK>;
 				clock-names = "ipg", "per";
+				dma-names = "rx", "tx";
+				dmas = <&sdma 6 7 1>, <&sdma 7 7 2>;
 				status = "disabled";
 			};
 
@@ -811,13 +827,23 @@
 			};
 
 			lcdif: lcdif@30730000 {
-				compatible = "fsl,imx7d-lcdif", "fsl,imx28-lcdif";
+				compatible = "fsl,imx7d-lcdif", "fsl,imx6sx-lcdif";
 				reg = <0x30730000 0x10000>;
 				interrupts = <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX7D_LCDIF_PIXEL_ROOT_CLK>,
 					<&clks IMX7D_LCDIF_PIXEL_ROOT_CLK>;
 				clock-names = "pix", "axi";
 				status = "disabled";
+
+				port {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					lcdif_out_mipi_dsi: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&mipi_dsi_in_lcdif>;
+					};
+				};
 			};
 
 			mipi_csi: mipi-csi@30750000 {
@@ -850,6 +876,42 @@
 					};
 				};
 			};
+
+			mipi_dsi: dsi@30760000 {
+				compatible = "fsl,imx7d-mipi-dsim", "fsl,imx8mm-mipi-dsim";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <0x30760000 0x400>;
+				clocks = <&clks IMX7D_MIPI_DSI_ROOT_CLK>,
+					 <&clks IMX7D_MIPI_DPHY_ROOT_CLK>;
+				clock-names = "bus_clk", "sclk_mipi";
+				assigned-clocks = <&clks IMX7D_MIPI_DSI_ROOT_SRC>,
+						  <&clks IMX7D_PLL_SYS_PFD5_CLK>;
+				assigned-clock-parents = <&clks IMX7D_PLL_SYS_PFD5_CLK>;
+				assigned-clock-rates = <0>, <333000000>;
+				power-domains = <&pgc_mipi_phy>;
+				interrupts = <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>;
+				samsung,burst-clock-frequency = <891000000>;
+				samsung,esc-clock-frequency = <20000000>;
+				samsung,pll-clock-frequency = <24000000>;
+				status = "disabled";
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						mipi_dsi_in_lcdif: endpoint@0 {
+							reg = <0>;
+							remote-endpoint = <&lcdif_out_mipi_dsi>;
+						};
+					};
+				};
+			};
 		};
 
 		aips3: bus@30800000 {
@@ -875,6 +937,8 @@
 					clocks = <&clks IMX7D_ECSPI1_ROOT_CLK>,
 						<&clks IMX7D_ECSPI1_ROOT_CLK>;
 					clock-names = "ipg", "per";
+					dma-names = "rx", "tx";
+					dmas = <&sdma 0 7 1>, <&sdma 1 7 2>;
 					status = "disabled";
 				};
 
@@ -887,6 +951,8 @@
 					clocks = <&clks IMX7D_ECSPI2_ROOT_CLK>,
 						<&clks IMX7D_ECSPI2_ROOT_CLK>;
 					clock-names = "ipg", "per";
+					dma-names = "rx", "tx";
+					dmas = <&sdma 2 7 1>, <&sdma 3 7 2>;
 					status = "disabled";
 				};
 
@@ -899,6 +965,8 @@
 					clocks = <&clks IMX7D_ECSPI3_ROOT_CLK>,
 						<&clks IMX7D_ECSPI3_ROOT_CLK>;
 					clock-names = "ipg", "per";
+					dma-names = "rx", "tx";
+					dmas = <&sdma 4 7 1>, <&sdma 5 7 2>;
 					status = "disabled";
 				};
 
@@ -1275,7 +1343,7 @@
 		gpmi: nand-controller@33002000 {
 			compatible = "fsl,imx7d-gpmi-nand";
 			#address-cells = <1>;
-			#size-cells = <1>;
+			#size-cells = <0>;
 			reg = <0x33002000 0x2000>, <0x33004000 0x4000>;
 			reg-names = "gpmi-nand", "bch";
 			interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/boot/dts/nxp/imx/mba6ulx.dtsi b/arch/arm/boot/dts/nxp/imx/mba6ulx.dtsi
index 5a8b867d7d79..e78d0a7d8cd2 100644
--- a/arch/arm/boot/dts/nxp/imx/mba6ulx.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/mba6ulx.dtsi
@@ -467,7 +467,7 @@
 
 	pinctrl_pwm2: pwm2grp {
 		fsl,pins = <
-			/* 100 k PD, DSE 120 OHM, SPPEED LO */
+			/* 100 k PD, DSE 120 OHM, SPEED LO */
 			MX6UL_PAD_GPIO1_IO09__PWM2_OUT		0x00003050
 		>;
 	};
diff --git a/arch/arm/boot/dts/nxp/lpc/lpc18xx.dtsi b/arch/arm/boot/dts/nxp/lpc/lpc18xx.dtsi
index 9cf09c183b85..6dd73290f0c6 100644
--- a/arch/arm/boot/dts/nxp/lpc/lpc18xx.dtsi
+++ b/arch/arm/boot/dts/nxp/lpc/lpc18xx.dtsi
@@ -74,7 +74,7 @@
 		sct_pwm: pwm@40000000 {
 			compatible = "nxp,lpc1850-sct-pwm";
 			reg = <0x40000000 0x1000>;
-			clocks =<&ccu1 CLK_CPU_SCT>;
+			clocks = <&ccu1 CLK_CPU_SCT>;
 			clock-names = "pwm";
 			resets = <&rgu 37>;
 			#pwm-cells = <3>;
diff --git a/arch/arm/boot/dts/nxp/ls/ls1021a.dtsi b/arch/arm/boot/dts/nxp/ls/ls1021a.dtsi
index 49c78c84cd5d..d471cc5efa94 100644
--- a/arch/arm/boot/dts/nxp/ls/ls1021a.dtsi
+++ b/arch/arm/boot/dts/nxp/ls/ls1021a.dtsi
@@ -112,7 +112,7 @@
 			compatible = "fsl,ls1021a-msi";
 			reg = <0x0 0x1570e00 0x0 0x8>;
 			msi-controller;
-			interrupts =  <GIC_SPI 179 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 179 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
 		msi2: msi-controller@1570e08 {
diff --git a/arch/arm/boot/dts/nxp/mxs/imx23-sansa.dts b/arch/arm/boot/dts/nxp/mxs/imx23-sansa.dts
index 636cf09a2b37..b23e7ada9c80 100644
--- a/arch/arm/boot/dts/nxp/mxs/imx23-sansa.dts
+++ b/arch/arm/boot/dts/nxp/mxs/imx23-sansa.dts
@@ -175,10 +175,8 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 		compatible = "i2c-gpio";
-		gpios = <
-			&gpio1 24 0		/* SDA */
-			&gpio1 22 0		/* SCL */
-		>;
+		sda-gpios = <&gpio1 24 0>;
+		scl-gpios = <&gpio1 22 0>;
 		i2c-gpio,delay-us = <2>;	/* ~100 kHz */
 	};
 
@@ -186,10 +184,8 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 		compatible = "i2c-gpio";
-		gpios = <
-			&gpio0 31 0		/* SDA */
-			&gpio0 30 0		/* SCL */
-		>;
+		sda-gpios = <&gpio0 31 0>;
+		scl-gpios = <&gpio0 30 0>;
 		i2c-gpio,delay-us = <2>;	/* ~100 kHz */
 
 		touch: touch@20 {
diff --git a/arch/arm/boot/dts/nxp/mxs/imx23.dtsi b/arch/arm/boot/dts/nxp/mxs/imx23.dtsi
index fdf18b7cb2f6..0309592af1e1 100644
--- a/arch/arm/boot/dts/nxp/mxs/imx23.dtsi
+++ b/arch/arm/boot/dts/nxp/mxs/imx23.dtsi
@@ -110,7 +110,7 @@
 				reg = <0x80018000 0x2000>;
 
 				gpio0: gpio@0 {
-					compatible = "fsl,imx23-gpio", "fsl,mxs-gpio";
+					compatible = "fsl,imx23-gpio";
 					reg = <0>;
 					interrupts = <16>;
 					gpio-controller;
@@ -120,7 +120,7 @@
 				};
 
 				gpio1: gpio@1 {
-					compatible = "fsl,imx23-gpio", "fsl,mxs-gpio";
+					compatible = "fsl,imx23-gpio";
 					reg = <1>;
 					interrupts = <17>;
 					gpio-controller;
@@ -130,7 +130,7 @@
 				};
 
 				gpio2: gpio@2 {
-					compatible = "fsl,imx23-gpio", "fsl,mxs-gpio";
+					compatible = "fsl,imx23-gpio";
 					reg = <2>;
 					interrupts = <18>;
 					gpio-controller;
@@ -412,7 +412,7 @@
 				status = "disabled";
 			};
 
-			dma_apbx: dma-apbx@80024000 {
+			dma_apbx: dma-controller@80024000 {
 				compatible = "fsl,imx23-dma-apbx";
 				reg = <0x80024000 0x2000>;
 				interrupts = <7>, <5>, <9>, <26>,
@@ -484,7 +484,7 @@
 			ranges;
 
 			clks: clkctrl@80040000 {
-				compatible = "fsl,imx23-clkctrl", "fsl,clkctrl";
+				compatible = "fsl,imx23-clkctrl";
 				reg = <0x80040000 0x2000>;
 				#clock-cells = <1>;
 			};
diff --git a/arch/arm/boot/dts/nxp/mxs/imx28-lwe.dtsi b/arch/arm/boot/dts/nxp/mxs/imx28-lwe.dtsi
index bb971e660db8..69fcb0dde940 100644
--- a/arch/arm/boot/dts/nxp/mxs/imx28-lwe.dtsi
+++ b/arch/arm/boot/dts/nxp/mxs/imx28-lwe.dtsi
@@ -18,6 +18,7 @@
 
 	memory@40000000 {
 		reg = <0x40000000 0x08000000>;
+		device_type = "memory";
 	};
 
 	reg_3v3: regulator-reg-3v3 {
diff --git a/arch/arm/boot/dts/nxp/mxs/imx28-tx28.dts b/arch/arm/boot/dts/nxp/mxs/imx28-tx28.dts
index 153e4017951d..5485fe118dc4 100644
--- a/arch/arm/boot/dts/nxp/mxs/imx28-tx28.dts
+++ b/arch/arm/boot/dts/nxp/mxs/imx28-tx28.dts
@@ -260,6 +260,7 @@
 	sgtl5000: sgtl5000@a {
 		compatible = "fsl,sgtl5000";
 		reg = <0x0a>;
+		#sound-dai-cells = <0>;
 		VDDA-supply = <&reg_2p5v>;
 		VDDIO-supply = <&reg_3p3v>;
 		clocks = <&mclk>;
diff --git a/arch/arm/boot/dts/nxp/mxs/imx28-xea.dts b/arch/arm/boot/dts/nxp/mxs/imx28-xea.dts
index a400c108f66a..6c5e6856648a 100644
--- a/arch/arm/boot/dts/nxp/mxs/imx28-xea.dts
+++ b/arch/arm/boot/dts/nxp/mxs/imx28-xea.dts
@@ -8,6 +8,7 @@
 #include "imx28-lwe.dtsi"
 
 / {
+	model = "Liebherr XEA board";
 	compatible = "lwn,imx28-xea", "fsl,imx28";
 };
 
diff --git a/arch/arm/boot/dts/nxp/mxs/imx28.dtsi b/arch/arm/boot/dts/nxp/mxs/imx28.dtsi
index 6932d23fb29d..4817fba2d938 100644
--- a/arch/arm/boot/dts/nxp/mxs/imx28.dtsi
+++ b/arch/arm/boot/dts/nxp/mxs/imx28.dtsi
@@ -164,7 +164,7 @@
 				reg = <0x80018000 0x2000>;
 
 				gpio0: gpio@0 {
-					compatible = "fsl,imx28-gpio", "fsl,mxs-gpio";
+					compatible = "fsl,imx28-gpio";
 					reg = <0>;
 					interrupts = <127>;
 					gpio-controller;
@@ -174,7 +174,7 @@
 				};
 
 				gpio1: gpio@1 {
-					compatible = "fsl,imx28-gpio", "fsl,mxs-gpio";
+					compatible = "fsl,imx28-gpio";
 					reg = <1>;
 					interrupts = <126>;
 					gpio-controller;
@@ -184,7 +184,7 @@
 				};
 
 				gpio2: gpio@2 {
-					compatible = "fsl,imx28-gpio", "fsl,mxs-gpio";
+					compatible = "fsl,imx28-gpio";
 					reg = <2>;
 					interrupts = <125>;
 					gpio-controller;
@@ -194,7 +194,7 @@
 				};
 
 				gpio3: gpio@3 {
-					compatible = "fsl,imx28-gpio", "fsl,mxs-gpio";
+					compatible = "fsl,imx28-gpio";
 					reg = <3>;
 					interrupts = <124>;
 					gpio-controller;
@@ -204,7 +204,7 @@
 				};
 
 				gpio4: gpio@4 {
-					compatible = "fsl,imx28-gpio", "fsl,mxs-gpio";
+					compatible = "fsl,imx28-gpio";
 					reg = <4>;
 					interrupts = <123>;
 					gpio-controller;
@@ -990,7 +990,7 @@
 				status = "disabled";
 			};
 
-			dma_apbx: dma-apbx@80024000 {
+			dma_apbx: dma-controller@80024000 {
 				compatible = "fsl,imx28-dma-apbx";
 				reg = <0x80024000 0x2000>;
 				interrupts = <78>, <79>, <66>, <0>,
@@ -1100,7 +1100,7 @@
 			ranges;
 
 			clks: clkctrl@80040000 {
-				compatible = "fsl,imx28-clkctrl", "fsl,clkctrl";
+				compatible = "fsl,imx28-clkctrl";
 				reg = <0x80040000 0x2000>;
 				#clock-cells = <1>;
 			};
diff --git a/arch/arm/boot/dts/nxp/vf/vf-colibri-eval-v3.dtsi b/arch/arm/boot/dts/nxp/vf/vf-colibri-eval-v3.dtsi
index 14c411f146f5..5a19da9313ae 100644
--- a/arch/arm/boot/dts/nxp/vf/vf-colibri-eval-v3.dtsi
+++ b/arch/arm/boot/dts/nxp/vf/vf-colibri-eval-v3.dtsi
@@ -55,7 +55,7 @@
 	brightness-levels = <0 4 8 16 32 64 128 255>;
 	default-brightness-level = <6>;
 	power-supply = <&reg_3v3>;
-	status  = "okay";
+	status = "okay";
 };
 
 &dcu0 {
diff --git a/arch/arm/boot/dts/nxp/vf/vf610-bk4.dts b/arch/arm/boot/dts/nxp/vf/vf610-bk4.dts
index e4f691d601cc..722182f5fd17 100644
--- a/arch/arm/boot/dts/nxp/vf/vf610-bk4.dts
+++ b/arch/arm/boot/dts/nxp/vf/vf610-bk4.dts
@@ -68,7 +68,7 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 		/* PTD12 ->RPIO[91] */
-		sck-gpios  = <&gpio2 27 GPIO_ACTIVE_LOW>;
+		sck-gpios = <&gpio2 27 GPIO_ACTIVE_LOW>;
 		/* PTD10 ->RPIO[89] */
 		miso-gpios = <&gpio2 25 GPIO_ACTIVE_HIGH>;
 		num-chipselects = <0>;
@@ -79,7 +79,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			/* PTB18 -> RGPIO[40] */
-			load-gpios  = <&gpio1 8 GPIO_ACTIVE_LOW>;
+			load-gpios = <&gpio1 8 GPIO_ACTIVE_LOW>;
 			spi-max-frequency = <100000>;
 		};
 	};
diff --git a/arch/arm/boot/dts/nxp/vf/vf610-zii-cfu1.dts b/arch/arm/boot/dts/nxp/vf/vf610-zii-cfu1.dts
index 1a19aec8957b..7e72f860c3c5 100644
--- a/arch/arm/boot/dts/nxp/vf/vf610-zii-cfu1.dts
+++ b/arch/arm/boot/dts/nxp/vf/vf610-zii-cfu1.dts
@@ -162,7 +162,7 @@
 		suppress-preamble;
 		status = "okay";
 
-		switch0: switch0@0 {
+		switch0: ethernet-switch@0 {
 			compatible = "marvell,mv88e6085";
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_switch>;
@@ -173,26 +173,26 @@
 			interrupt-controller;
 			#interrupt-cells = <2>;
 
-			ports {
+			ethernet-ports {
 				#address-cells = <1>;
 				#size-cells = <0>;
 
-				port@0 {
+				ethernet-port@0 {
 					reg = <0>;
 					label = "eth_cu_1000_1";
 				};
 
-				port@1 {
+				ethernet-port@1 {
 					reg = <1>;
 					label = "eth_cu_1000_2";
 				};
 
-				port@2 {
+				ethernet-port@2 {
 					reg = <2>;
 					label = "eth_cu_1000_3";
 				};
 
-				port@5 {
+				ethernet-port@5 {
 					reg = <5>;
 					label = "eth_fc_1000_1";
 					phy-mode = "1000base-x";
@@ -200,7 +200,7 @@
 					sfp = <&sff>;
 				};
 
-				port@6 {
+				ethernet-port@6 {
 					reg = <6>;
 					phy-mode = "rmii";
 					ethernet = <&fec1>;
diff --git a/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-b.dts b/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-b.dts
index 16b4e06c4efa..b0ed68af0546 100644
--- a/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-b.dts
+++ b/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-b.dts
@@ -294,11 +294,11 @@
 		pinctrl-names = "default";
 		#address-cells = <1>;
 		#size-cells = <0>;
-		sck-gpios  = <&gpio1 12 GPIO_ACTIVE_HIGH>;
+		sck-gpios = <&gpio1 12 GPIO_ACTIVE_HIGH>;
 		mosi-gpios = <&gpio1 11 GPIO_ACTIVE_HIGH>;
 		miso-gpios = <&gpio1 10 GPIO_ACTIVE_HIGH>;
-		cs-gpios  = <&gpio1  9 GPIO_ACTIVE_LOW
-			     &gpio1  8 GPIO_ACTIVE_HIGH>;
+		cs-gpios = <&gpio1 9 GPIO_ACTIVE_LOW
+			    &gpio1 8 GPIO_ACTIVE_HIGH>;
 		num-chipselects = <2>;
 
 		flash@0 {
diff --git a/arch/arm/boot/dts/nxp/vf/vf610-zii-scu4-aib.dts b/arch/arm/boot/dts/nxp/vf/vf610-zii-scu4-aib.dts
index df1335492a19..77492eeea450 100644
--- a/arch/arm/boot/dts/nxp/vf/vf610-zii-scu4-aib.dts
+++ b/arch/arm/boot/dts/nxp/vf/vf610-zii-scu4-aib.dts
@@ -47,17 +47,17 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			switch0: switch0@0 {
+			switch0: ethernet-switch@0 {
 				compatible = "marvell,mv88e6190";
 				reg = <0>;
 				dsa,member = <0 0>;
 				eeprom-length = <65536>;
 
-				ports {
+				ethernet-ports {
 					#address-cells = <1>;
 					#size-cells = <0>;
 
-					port@0 {
+					ethernet-port@0 {
 						reg = <0>;
 						phy-mode = "rmii";
 						ethernet = <&fec1>;
@@ -68,37 +68,37 @@
 						};
 					};
 
-					port@1 {
+					ethernet-port@1 {
 						reg = <1>;
 						label = "aib2main_1";
 					};
 
-					port@2 {
+					ethernet-port@2 {
 						reg = <2>;
 						label = "aib2main_2";
 					};
 
-					port@3 {
+					ethernet-port@3 {
 						reg = <3>;
 						label = "eth_cu_1000_5";
 					};
 
-					port@4 {
+					ethernet-port@4 {
 						reg = <4>;
 						label = "eth_cu_1000_6";
 					};
 
-					port@5 {
+					ethernet-port@5 {
 						reg = <5>;
 						label = "eth_cu_1000_4";
 					};
 
-					port@6 {
+					ethernet-port@6 {
 						reg = <6>;
 						label = "eth_cu_1000_7";
 					};
 
-					port@7 {
+					ethernet-port@7 {
 						reg = <7>;
 						label = "modem_pic";
 
@@ -108,7 +108,7 @@
 						};
 					};
 
-					switch0port10: port@10 {
+					switch0port10: ethernet-port@10 {
 						reg = <10>;
 						label = "dsa";
 						phy-mode = "xgmii";
@@ -130,32 +130,32 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			switch1: switch1@0 {
+			switch1: ethernet-switch@0 {
 				compatible = "marvell,mv88e6190";
 				reg = <0>;
 				dsa,member = <0 1>;
 				eeprom-length = <65536>;
 
-				ports {
+				ethernet-ports {
 					#address-cells = <1>;
 					#size-cells = <0>;
 
-					port@1 {
+					ethernet-port@1 {
 						reg = <1>;
 						label = "eth_cu_1000_3";
 					};
 
-					port@2 {
+					ethernet-port@2 {
 						reg = <2>;
 						label = "eth_cu_100_2";
 					};
 
-					port@3 {
+					ethernet-port@3 {
 						reg = <3>;
 						label = "eth_cu_100_3";
 					};
 
-					switch1port9: port@9 {
+					switch1port9: ethernet-port@9 {
 						reg = <9>;
 						label = "dsa";
 						phy-mode = "xgmii";
@@ -168,7 +168,7 @@
 						};
 					};
 
-					switch1port10: port@10 {
+					switch1port10: ethernet-port@10 {
 						reg = <10>;
 						label = "dsa";
 						phy-mode = "xgmii";
@@ -188,17 +188,17 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			switch2: switch2@0 {
+			switch2: ethernet-switch@0 {
 				compatible = "marvell,mv88e6190";
 				reg = <0>;
 				dsa,member = <0 2>;
 				eeprom-length = <65536>;
 
-				ports {
+				ethernet-ports {
 					#address-cells = <1>;
 					#size-cells = <0>;
 
-					port@2 {
+					ethernet-port@2 {
 						reg = <2>;
 						label = "eth_fc_1000_2";
 						phy-mode = "1000base-x";
@@ -206,7 +206,7 @@
 						sfp = <&sff1>;
 					};
 
-					port@3 {
+					ethernet-port@3 {
 						reg = <3>;
 						label = "eth_fc_1000_3";
 						phy-mode = "1000base-x";
@@ -214,7 +214,7 @@
 						sfp = <&sff2>;
 					};
 
-					port@4 {
+					ethernet-port@4 {
 						reg = <4>;
 						label = "eth_fc_1000_4";
 						phy-mode = "1000base-x";
@@ -222,7 +222,7 @@
 						sfp = <&sff3>;
 					};
 
-					port@5 {
+					ethernet-port@5 {
 						reg = <5>;
 						label = "eth_fc_1000_5";
 						phy-mode = "1000base-x";
@@ -230,7 +230,7 @@
 						sfp = <&sff4>;
 					};
 
-					port@6 {
+					ethernet-port@6 {
 						reg = <6>;
 						label = "eth_fc_1000_6";
 						phy-mode = "1000base-x";
@@ -238,7 +238,7 @@
 						sfp = <&sff5>;
 					};
 
-					port@7 {
+					ethernet-port@7 {
 						reg = <7>;
 						label = "eth_fc_1000_7";
 						phy-mode = "1000base-x";
@@ -246,7 +246,7 @@
 						sfp = <&sff6>;
 					};
 
-					port@9 {
+					ethernet-port@9 {
 						reg = <9>;
 						label = "eth_fc_1000_1";
 						phy-mode = "1000base-x";
@@ -254,7 +254,7 @@
 						sfp = <&sff0>;
 					};
 
-					switch2port10: port@10 {
+					switch2port10: ethernet-port@10 {
 						reg = <10>;
 						label = "dsa";
 						phy-mode = "2500base-x";
@@ -276,17 +276,17 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			switch3: switch3@0 {
+			switch3: ethernet-switch@0 {
 				compatible = "marvell,mv88e6190";
 				reg = <0>;
 				dsa,member = <0 3>;
 				eeprom-length = <65536>;
 
-				ports {
+				ethernet-ports {
 					#address-cells = <1>;
 					#size-cells = <0>;
 
-					port@2 {
+					ethernet-port@2 {
 						reg = <2>;
 						label = "eth_fc_1000_8";
 						phy-mode = "1000base-x";
@@ -294,7 +294,7 @@
 						sfp = <&sff7>;
 					};
 
-					port@3 {
+					ethernet-port@3 {
 						reg = <3>;
 						label = "eth_fc_1000_9";
 						phy-mode = "1000base-x";
@@ -302,7 +302,7 @@
 						sfp = <&sff8>;
 					};
 
-					port@4 {
+					ethernet-port@4 {
 						reg = <4>;
 						label = "eth_fc_1000_10";
 						phy-mode = "1000base-x";
@@ -310,7 +310,7 @@
 						sfp = <&sff9>;
 					};
 
-					switch3port9: port@9 {
+					switch3port9: ethernet-port@9 {
 						reg = <9>;
 						label = "dsa";
 						phy-mode = "2500base-x";
@@ -322,7 +322,7 @@
 						};
 					};
 
-					switch3port10: port@10 {
+					switch3port10: ethernet-port@10 {
 						reg = <10>;
 						label = "dsa";
 						phy-mode = "xgmii";
diff --git a/arch/arm/boot/dts/nxp/vf/vf610-zii-spb4.dts b/arch/arm/boot/dts/nxp/vf/vf610-zii-spb4.dts
index 1461804ecaea..2a490464660c 100644
--- a/arch/arm/boot/dts/nxp/vf/vf610-zii-spb4.dts
+++ b/arch/arm/boot/dts/nxp/vf/vf610-zii-spb4.dts
@@ -123,7 +123,7 @@
 		suppress-preamble;
 		status = "okay";
 
-		switch0: switch0@0 {
+		switch0: ethernet-switch@0 {
 			compatible = "marvell,mv88e6190";
 			pinctrl-0 = <&pinctrl_gpio_switch0>;
 			pinctrl-names = "default";
@@ -134,11 +134,11 @@
 			interrupt-controller;
 			#interrupt-cells = <2>;
 
-			ports {
+			ethernet-ports {
 				#address-cells = <1>;
 				#size-cells = <0>;
 
-				port@0 {
+				ethernet-port@0 {
 					reg = <0>;
 					phy-mode = "rmii";
 					ethernet = <&fec1>;
@@ -149,32 +149,32 @@
 					};
 				};
 
-				port@1 {
+				ethernet-port@1 {
 					reg = <1>;
 					label = "eth_cu_1000_1";
 				};
 
-				port@2 {
+				ethernet-port@2 {
 					reg = <2>;
 					label = "eth_cu_1000_2";
 				};
 
-				port@3 {
+				ethernet-port@3 {
 					reg = <3>;
 					label = "eth_cu_1000_3";
 				};
 
-				port@4 {
+				ethernet-port@4 {
 					reg = <4>;
 					label = "eth_cu_1000_4";
 				};
 
-				port@5 {
+				ethernet-port@5 {
 					reg = <5>;
 					label = "eth_cu_1000_5";
 				};
 
-				port@6 {
+				ethernet-port@6 {
 					reg = <6>;
 					label = "eth_cu_1000_6";
 				};
diff --git a/arch/arm/boot/dts/nxp/vf/vf610-zii-ssmb-dtu.dts b/arch/arm/boot/dts/nxp/vf/vf610-zii-ssmb-dtu.dts
index 463c2452b9b7..078d8699e16d 100644
--- a/arch/arm/boot/dts/nxp/vf/vf610-zii-ssmb-dtu.dts
+++ b/arch/arm/boot/dts/nxp/vf/vf610-zii-ssmb-dtu.dts
@@ -112,7 +112,7 @@
 		suppress-preamble;
 		status = "okay";
 
-		switch0: switch0@0 {
+		switch0: ethernet-switch@0 {
 			compatible = "marvell,mv88e6190";
 			pinctrl-0 = <&pinctrl_gpio_switch0>;
 			pinctrl-names = "default";
@@ -123,11 +123,11 @@
 			interrupt-controller;
 			#interrupt-cells = <2>;
 
-			ports {
+			ethernet-ports {
 				#address-cells = <1>;
 				#size-cells = <0>;
 
-				port@0 {
+				ethernet-port@0 {
 					reg = <0>;
 					phy-mode = "rmii";
 					ethernet = <&fec1>;
@@ -138,27 +138,27 @@
 					};
 				};
 
-				port@1 {
+				ethernet-port@1 {
 					reg = <1>;
 					label = "eth_cu_100_3";
 				};
 
-				port@5 {
+				ethernet-port@5 {
 					reg = <5>;
 					label = "eth_cu_1000_4";
 				};
 
-				port@6 {
+				ethernet-port@6 {
 					reg = <6>;
 					label = "eth_cu_1000_5";
 				};
 
-				port@8 {
+				ethernet-port@8 {
 					reg = <8>;
 					label = "eth_cu_1000_1";
 				};
 
-				port@9 {
+				ethernet-port@9 {
 					reg = <9>;
 					label = "eth_cu_1000_2";
 					phy-handle = <&phy9>;
@@ -167,12 +167,12 @@
 				};
 			};
 
-			mdio1 {
+			mdio-external {
 				compatible = "marvell,mv88e6xxx-mdio-external";
 				#address-cells = <1>;
 				#size-cells = <0>;
 
-				phy9: phy9@0 {
+				phy9: ethernet-phy@0 {
 					compatible = "ethernet-phy-ieee802.3-c45";
 					pinctrl-0 = <&pinctrl_gpio_phy9>;
 					pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/nxp/vf/vf610-zii-ssmb-spu3.dts b/arch/arm/boot/dts/nxp/vf/vf610-zii-ssmb-spu3.dts
index f5ae0d5de315..22c8f44390a9 100644
--- a/arch/arm/boot/dts/nxp/vf/vf610-zii-ssmb-spu3.dts
+++ b/arch/arm/boot/dts/nxp/vf/vf610-zii-ssmb-spu3.dts
@@ -137,7 +137,7 @@
 		suppress-preamble;
 		status = "okay";
 
-		switch0: switch0@0 {
+		switch0: ethernet-switch@0 {
 			compatible = "marvell,mv88e6190";
 			pinctrl-0 = <&pinctrl_gpio_switch0>;
 			pinctrl-names = "default";
@@ -148,11 +148,11 @@
 			interrupt-controller;
 			#interrupt-cells = <2>;
 
-			ports {
+			ethernet-ports {
 				#address-cells = <1>;
 				#size-cells = <0>;
 
-				port@0 {
+				ethernet-port@0 {
 					reg = <0>;
 					phy-mode = "rmii";
 					ethernet = <&fec1>;
@@ -163,32 +163,32 @@
 					};
 				};
 
-				port@1 {
+				ethernet-port@1 {
 					reg = <1>;
 					label = "eth_cu_1000_1";
 				};
 
-				port@2 {
+				ethernet-port@2 {
 					reg = <2>;
 					label = "eth_cu_1000_2";
 				};
 
-				port@3 {
+				ethernet-port@3 {
 					reg = <3>;
 					label = "eth_cu_1000_3";
 				};
 
-				port@4 {
+				ethernet-port@4 {
 					reg = <4>;
 					label = "eth_cu_1000_4";
 				};
 
-				port@5 {
+				ethernet-port@5 {
 					reg = <5>;
 					label = "eth_cu_1000_5";
 				};
 
-				port@6 {
+				ethernet-port@6 {
 					reg = <6>;
 					label = "eth_cu_1000_6";
 				};
diff --git a/arch/arm/boot/dts/qcom/Makefile b/arch/arm/boot/dts/qcom/Makefile
index 3dfb1c8cefb8..9cc1e14e6cd0 100644
--- a/arch/arm/boot/dts/qcom/Makefile
+++ b/arch/arm/boot/dts/qcom/Makefile
@@ -23,12 +23,19 @@ dtb-$(CONFIG_ARCH_QCOM) += \
 	qcom-ipq4019-ap.dk07.1-c2.dtb \
 	qcom-ipq8064-ap148.dtb \
 	qcom-ipq8064-rb3011.dtb \
+	qcom-msm8226-microsoft-dempsey.dtb \
+	qcom-msm8226-microsoft-makepeace.dtb \
+	qcom-msm8226-microsoft-moneypenny.dtb \
 	qcom-msm8226-samsung-s3ve3g.dtb \
 	qcom-msm8660-surf.dtb \
 	qcom-msm8916-samsung-e5.dtb \
 	qcom-msm8916-samsung-e7.dtb \
 	qcom-msm8916-samsung-grandmax.dtb \
 	qcom-msm8916-samsung-serranove.dtb \
+	qcom-msm8926-htc-memul.dtb \
+	qcom-msm8926-microsoft-superman-lte.dtb \
+	qcom-msm8926-microsoft-tesla.dtb \
+	qcom-msm8926-motorola-peregrine.dtb \
 	qcom-msm8960-cdp.dtb \
 	qcom-msm8960-samsung-expressatt.dtb \
 	qcom-msm8974-lge-nexus5-hammerhead.dtb \
diff --git a/arch/arm/boot/dts/qcom/pm8018.dtsi b/arch/arm/boot/dts/qcom/pm8018.dtsi
new file mode 100644
index 000000000000..22f3c7bac522
--- /dev/null
+++ b/arch/arm/boot/dts/qcom/pm8018.dtsi
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Device Tree Source for Qualcomm PM8018
+ *
+ * Copyright (C) 2016 BayLibre, SAS.
+ * Author : Neil Armstrong <narmstrong@baylibre.com>
+ */
+
+&ssbi {
+	pm8018: pmic {
+		compatible = "qcom,pm8018", "qcom,pm8921";
+		#interrupt-cells = <2>;
+		interrupt-controller;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		pwrkey@1c {
+			compatible = "qcom,pm8018-pwrkey",
+				     "qcom,pm8921-pwrkey";
+			reg = <0x1c>;
+			interrupts-extended = <&pm8018 50 IRQ_TYPE_EDGE_RISING>,
+					      <&pm8018 51 IRQ_TYPE_EDGE_RISING>;
+			debounce = <15625>;
+			pull-up;
+		};
+
+		pm8018_mpps: mpps@50 {
+			compatible = "qcom,pm8018-mpp", "qcom,ssbi-mpp";
+			reg = <0x50>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			gpio-ranges = <&pm8018_mpps 0 0 6>;
+		};
+
+		rtc@11d {
+			compatible = "qcom,pm8018-rtc", "qcom,pm8921-rtc";
+			reg = <0x11d>;
+			interrupts-extended = <&pm8018 39 IRQ_TYPE_EDGE_RISING>;
+			allow-set-time;
+		};
+
+		pm8018_gpio: gpio@150 {
+			compatible = "qcom,pm8058-gpio",
+				     "qcom,ssbi-gpio";
+			reg = <0x150>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			gpio-controller;
+			gpio-ranges = <&pm8018_gpio 0 0 6>;
+			#gpio-cells = <2>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/qcom/pm8058.dtsi b/arch/arm/boot/dts/qcom/pm8058.dtsi
new file mode 100644
index 000000000000..984b79777984
--- /dev/null
+++ b/arch/arm/boot/dts/qcom/pm8058.dtsi
@@ -0,0 +1,159 @@
+// SPDX-License-Identifier: GPL-2.0
+
+&ssbi {
+	pm8058: pmic {
+		compatible = "qcom,pm8058";
+		#interrupt-cells = <2>;
+		interrupt-controller;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		pwrkey@1c {
+			compatible = "qcom,pm8058-pwrkey";
+			reg = <0x1c>;
+			interrupts-extended = <&pm8058 50 IRQ_TYPE_EDGE_RISING>,
+					      <&pm8058 51 IRQ_TYPE_EDGE_RISING>;
+			debounce = <15625>;
+			pull-up;
+		};
+
+		pm8058_led48: led@48 {
+			compatible = "qcom,pm8058-keypad-led";
+			reg = <0x48>;
+			status = "disabled";
+		};
+
+		vibrator@4a {
+			compatible = "qcom,pm8058-vib";
+			reg = <0x4a>;
+		};
+
+		pm8058_mpps: mpps@50 {
+			compatible = "qcom,pm8058-mpp",
+				     "qcom,ssbi-mpp";
+			reg = <0x50>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			gpio-ranges = <&pm8058_mpps 0 0 12>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+		};
+
+		pm8058_led131: led@131 {
+			compatible = "qcom,pm8058-led";
+			reg = <0x131>;
+			status = "disabled";
+		};
+
+		pm8058_led132: led@132 {
+			compatible = "qcom,pm8058-led";
+			reg = <0x132>;
+			status = "disabled";
+		};
+
+		pm8058_led133: led@133 {
+			compatible = "qcom,pm8058-led";
+			reg = <0x133>;
+			status = "disabled";
+		};
+
+		pm8058_keypad: keypad@148 {
+			compatible = "qcom,pm8058-keypad";
+			reg = <0x148>;
+			interrupts-extended = <&pm8058 74 IRQ_TYPE_EDGE_RISING>,
+					      <&pm8058 75 IRQ_TYPE_EDGE_RISING>;
+			debounce = <15>;
+			scan-delay = <32>;
+			row-hold = <91500>;
+		};
+
+		pm8058_gpio: gpio@150 {
+			compatible = "qcom,pm8058-gpio",
+				     "qcom,ssbi-gpio";
+			reg = <0x150>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			gpio-controller;
+			gpio-ranges = <&pm8058_gpio 0 0 44>;
+			#gpio-cells = <2>;
+		};
+
+		pm8058_xoadc: xoadc@197 {
+			compatible = "qcom,pm8058-adc";
+			reg = <0x197>;
+			interrupts-extended = <&pm8058 76 IRQ_TYPE_EDGE_RISING>;
+			#address-cells = <2>;
+			#size-cells = <0>;
+			#io-channel-cells = <2>;
+
+			vcoin: adc-channel@0 {
+				reg = <0x00 0x00>;
+			};
+
+			vbat: adc-channel@1 {
+				reg = <0x00 0x01>;
+			};
+
+			dcin: adc-channel@2 {
+				reg = <0x00 0x02>;
+			};
+
+			ichg: adc-channel@3 {
+				reg = <0x00 0x03>;
+			};
+
+			vph_pwr: adc-channel@4 {
+				reg = <0x00 0x04>;
+			};
+
+			usb_vbus: adc-channel@a {
+				reg = <0x00 0x0a>;
+			};
+
+			die_temp: adc-channel@b {
+				reg = <0x00 0x0b>;
+			};
+
+			ref_625mv: adc-channel@c {
+				reg = <0x00 0x0c>;
+			};
+
+			ref_1250mv: adc-channel@d {
+				reg = <0x00 0x0d>;
+			};
+
+			ref_325mv: adc-channel@e {
+				reg = <0x00 0x0e>;
+			};
+
+			ref_muxoff: adc-channel@f {
+				reg = <0x00 0x0f>;
+			};
+		};
+
+		rtc@1e8 {
+			compatible = "qcom,pm8058-rtc";
+			reg = <0x1e8>;
+			interrupts-extended = <&pm8058 39 IRQ_TYPE_EDGE_RISING>;
+			allow-set-time;
+		};
+	};
+};
+
+/ {
+	/*
+	 * These channels from the ADC are simply hardware monitors.
+	 * That is why the ADC is referred to as "HKADC" - HouseKeeping
+	 * ADC.
+	 */
+	iio-hwmon {
+		compatible = "iio-hwmon";
+		io-channels = <&pm8058_xoadc 0x00 0x01>, /* Battery */
+			      <&pm8058_xoadc 0x00 0x02>, /* DC in (charger) */
+			      <&pm8058_xoadc 0x00 0x04>, /* VPH the main system voltage */
+			      <&pm8058_xoadc 0x00 0x0b>, /* Die temperature */
+			      <&pm8058_xoadc 0x00 0x0c>, /* Reference voltage 1.25V */
+			      <&pm8058_xoadc 0x00 0x0d>, /* Reference voltage 0.625V */
+			      <&pm8058_xoadc 0x00 0x0e>; /* Reference voltage 0.325V */
+	};
+};
diff --git a/arch/arm/boot/dts/qcom/qcom-pm8226.dtsi b/arch/arm/boot/dts/qcom/pm8226.dtsi
index 2413778f3715..2fd4f135ed84 100644
--- a/arch/arm/boot/dts/qcom/qcom-pm8226.dtsi
+++ b/arch/arm/boot/dts/qcom/pm8226.dtsi
@@ -82,6 +82,8 @@
 					  "usb-valid",
 					  "dc-valid";
 
+			status = "disabled";
+
 			chg_otg: otg-vbus { };
 		};
 
diff --git a/arch/arm/boot/dts/qcom/pm8821.dtsi b/arch/arm/boot/dts/qcom/pm8821.dtsi
new file mode 100644
index 000000000000..064e3ba54e18
--- /dev/null
+++ b/arch/arm/boot/dts/qcom/pm8821.dtsi
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* This PMIC is used on a secondary SSBI bus */
+&ssbi2 {
+	pm8821: pmic {
+		compatible = "qcom,pm8821";
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		pm8821_mpps: mpps@50 {
+			compatible = "qcom,pm8821-mpp", "qcom,ssbi-mpp";
+			reg = <0x50>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			gpio-ranges = <&pm8821_mpps 0 0 4>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/qcom/qcom-pm8841.dtsi b/arch/arm/boot/dts/qcom/pm8841.dtsi
index 3bf2ce5c86a6..3bf2ce5c86a6 100644
--- a/arch/arm/boot/dts/qcom/qcom-pm8841.dtsi
+++ b/arch/arm/boot/dts/qcom/pm8841.dtsi
diff --git a/arch/arm/boot/dts/qcom/pm8921.dtsi b/arch/arm/boot/dts/qcom/pm8921.dtsi
new file mode 100644
index 000000000000..058962af3005
--- /dev/null
+++ b/arch/arm/boot/dts/qcom/pm8921.dtsi
@@ -0,0 +1,137 @@
+// SPDX-License-Identifier: GPL-2.0
+
+&ssbi {
+	pm8921: pmic {
+		compatible = "qcom,pm8921";
+		#interrupt-cells = <2>;
+		interrupt-controller;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		pwrkey@1c {
+			compatible = "qcom,pm8921-pwrkey";
+			reg = <0x1c>;
+			interrupts-extended = <&pm8921 50 IRQ_TYPE_EDGE_RISING>,
+					      <&pm8921 51 IRQ_TYPE_EDGE_RISING>;
+			debounce = <15625>;
+			pull-up;
+		};
+
+		pm8921_mpps: mpps@50 {
+			compatible = "qcom,pm8921-mpp",
+				     "qcom,ssbi-mpp";
+			reg = <0x50>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			gpio-ranges = <&pm8921_mpps 0 0 12>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+		};
+
+		rtc@11d {
+			compatible = "qcom,pm8921-rtc";
+			reg = <0x11d>;
+			interrupts-extended = <&pm8921 39 IRQ_TYPE_EDGE_RISING>;
+			allow-set-time;
+		};
+
+		pm8921_keypad: keypad@148 {
+			compatible = "qcom,pm8921-keypad";
+			reg = <0x148>;
+			interrupts-extended = <&pm8921 74 IRQ_TYPE_EDGE_RISING>,
+					      <&pm8921 75 IRQ_TYPE_EDGE_RISING>;
+			debounce = <15>;
+			scan-delay = <32>;
+			row-hold = <91500>;
+			status = "disabled";
+		};
+
+		pm8921_gpio: gpio@150 {
+
+			compatible = "qcom,pm8921-gpio",
+				     "qcom,ssbi-gpio";
+			reg = <0x150>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			gpio-controller;
+			gpio-ranges = <&pm8921_gpio 0 0 44>;
+			#gpio-cells = <2>;
+
+		};
+
+		pm8921_xoadc: xoadc@197 {
+			compatible = "qcom,pm8921-adc";
+			reg = <0x197>;
+			interrupts-extended = <&pm8921 78 IRQ_TYPE_EDGE_RISING>;
+			#address-cells = <2>;
+			#size-cells = <0>;
+			#io-channel-cells = <2>;
+
+			vcoin: adc-channel@0 {
+				reg = <0x00 0x00>;
+			};
+
+			vbat: adc-channel@1 {
+				reg = <0x00 0x01>;
+			};
+
+			dcin: adc-channel@2 {
+				reg = <0x00 0x02>;
+			};
+
+			vph_pwr: adc-channel@4 {
+				reg = <0x00 0x04>;
+			};
+
+			batt_therm: adc-channel@8 {
+				reg = <0x00 0x08>;
+			};
+
+			batt_id: adc-channel@9 {
+				reg = <0x00 0x09>;
+			};
+
+			usb_vbus: adc-channel@a {
+				reg = <0x00 0x0a>;
+			};
+
+			die_temp: adc-channel@b {
+				reg = <0x00 0x0b>;
+			};
+
+			ref_625mv: adc-channel@c {
+				reg = <0x00 0x0c>;
+			};
+
+			ref_1250mv: adc-channel@d {
+				reg = <0x00 0x0d>;
+			};
+
+			chg_temp: adc-channel@e {
+				reg = <0x00 0x0e>;
+			};
+
+			ref_muxoff: adc-channel@f {
+				reg = <0x00 0x0f>;
+			};
+		};
+	};
+};
+
+/ {
+	/*
+	 * These channels from the ADC are simply hardware monitors.
+	 * That is why the ADC is referred to as "HKADC" - HouseKeeping
+	 * ADC.
+	 */
+	iio-hwmon {
+		compatible = "iio-hwmon";
+		io-channels = <&pm8921_xoadc 0x00 0x01>, /* Battery */
+			      <&pm8921_xoadc 0x00 0x02>, /* DC in (charger) */
+			      <&pm8921_xoadc 0x00 0x04>, /* VPH the main system voltage */
+			      <&pm8921_xoadc 0x00 0x0b>, /* Die temperature */
+			      <&pm8921_xoadc 0x00 0x0c>, /* Reference voltage 1.25V */
+			      <&pm8921_xoadc 0x00 0x0d>, /* Reference voltage 0.625V */
+			      <&pm8921_xoadc 0x00 0x0e>; /* Charger temperature */
+	};
+};
diff --git a/arch/arm/boot/dts/qcom/qcom-pm8941.dtsi b/arch/arm/boot/dts/qcom/pm8941.dtsi
index ed0ba591c755..aca0052a02b7 100644
--- a/arch/arm/boot/dts/qcom/qcom-pm8941.dtsi
+++ b/arch/arm/boot/dts/qcom/pm8941.dtsi
@@ -99,6 +99,8 @@
 
 			usb-otg-in-supply = <&pm8941_5vs1>;
 
+			status = "disabled";
+
 			chg_otg: otg-vbus { };
 		};
 
diff --git a/arch/arm/boot/dts/qcom/qcom-pma8084.dtsi b/arch/arm/boot/dts/qcom/pma8084.dtsi
index 2985f4805b93..2985f4805b93 100644
--- a/arch/arm/boot/dts/qcom/qcom-pma8084.dtsi
+++ b/arch/arm/boot/dts/qcom/pma8084.dtsi
diff --git a/arch/arm/boot/dts/qcom/qcom-pmx55.dtsi b/arch/arm/boot/dts/qcom/pmx55.dtsi
index da0851173c69..da0851173c69 100644
--- a/arch/arm/boot/dts/qcom/qcom-pmx55.dtsi
+++ b/arch/arm/boot/dts/qcom/pmx55.dtsi
diff --git a/arch/arm/boot/dts/qcom/qcom-pmx65.dtsi b/arch/arm/boot/dts/qcom/pmx65.dtsi
index 1c7fdf59c1f5..1c7fdf59c1f5 100644
--- a/arch/arm/boot/dts/qcom/qcom-pmx65.dtsi
+++ b/arch/arm/boot/dts/qcom/pmx65.dtsi
diff --git a/arch/arm/boot/dts/qcom/qcom-apq8026-asus-sparrow.dts b/arch/arm/boot/dts/qcom/qcom-apq8026-asus-sparrow.dts
index aa0e0e8d2a97..a2ca456012f1 100644
--- a/arch/arm/boot/dts/qcom/qcom-apq8026-asus-sparrow.dts
+++ b/arch/arm/boot/dts/qcom/qcom-apq8026-asus-sparrow.dts
@@ -6,7 +6,7 @@
 /dts-v1/;
 
 #include "qcom-msm8226.dtsi"
-#include "qcom-pm8226.dtsi"
+#include "pm8226.dtsi"
 
 /delete-node/ &adsp_region;
 
@@ -253,6 +253,8 @@
 	qcom,fast-charge-high-threshold-voltage = <4400000>;
 	qcom,auto-recharge-threshold-voltage = <4300000>;
 	qcom,minimum-input-voltage = <4400000>;
+
+	status = "okay";
 };
 
 &tlmm {
diff --git a/arch/arm/boot/dts/qcom/qcom-apq8026-huawei-sturgeon.dts b/arch/arm/boot/dts/qcom/qcom-apq8026-huawei-sturgeon.dts
index de19640efe55..ac228965a485 100644
--- a/arch/arm/boot/dts/qcom/qcom-apq8026-huawei-sturgeon.dts
+++ b/arch/arm/boot/dts/qcom/qcom-apq8026-huawei-sturgeon.dts
@@ -6,7 +6,7 @@
 /dts-v1/;
 
 #include "qcom-msm8226.dtsi"
-#include "qcom-pm8226.dtsi"
+#include "pm8226.dtsi"
 #include <dt-bindings/input/ti-drv260x.h>
 
 /delete-node/ &adsp_region;
@@ -335,6 +335,8 @@
 	qcom,fast-charge-current-limit = <300000>;
 	qcom,fast-charge-safe-current = <600000>;
 	qcom,auto-recharge-threshold-voltage = <4240000>;
+
+	status = "okay";
 };
 
 &tlmm {
diff --git a/arch/arm/boot/dts/qcom/qcom-apq8026-lg-lenok.dts b/arch/arm/boot/dts/qcom/qcom-apq8026-lg-lenok.dts
index b887e5361ec3..0a1fd5eb3c6d 100644
--- a/arch/arm/boot/dts/qcom/qcom-apq8026-lg-lenok.dts
+++ b/arch/arm/boot/dts/qcom/qcom-apq8026-lg-lenok.dts
@@ -6,7 +6,7 @@
 /dts-v1/;
 
 #include "qcom-msm8226.dtsi"
-#include "qcom-pm8226.dtsi"
+#include "pm8226.dtsi"
 
 /delete-node/ &adsp_region;
 
@@ -292,6 +292,8 @@
 	qcom,fast-charge-high-threshold-voltage = <4350000>;
 	qcom,auto-recharge-threshold-voltage = <4240000>;
 	qcom,minimum-input-voltage = <4450000>;
+
+	status = "okay";
 };
 
 &tlmm {
diff --git a/arch/arm/boot/dts/qcom/qcom-apq8026-samsung-matisse-wifi.dts b/arch/arm/boot/dts/qcom/qcom-apq8026-samsung-matisse-wifi.dts
index f516e0426bb9..cffc069712b2 100644
--- a/arch/arm/boot/dts/qcom/qcom-apq8026-samsung-matisse-wifi.dts
+++ b/arch/arm/boot/dts/qcom/qcom-apq8026-samsung-matisse-wifi.dts
@@ -7,7 +7,7 @@
 
 #include <dt-bindings/input/input.h>
 #include "qcom-msm8226.dtsi"
-#include "qcom-pm8226.dtsi"
+#include "pm8226.dtsi"
 
 /delete-node/ &adsp_region;
 /delete-node/ &smem_region;
diff --git a/arch/arm/boot/dts/qcom/qcom-apq8060-dragonboard.dts b/arch/arm/boot/dts/qcom/qcom-apq8060-dragonboard.dts
index 569cbf0d8df8..009afd8212c2 100644
--- a/arch/arm/boot/dts/qcom/qcom-apq8060-dragonboard.dts
+++ b/arch/arm/boot/dts/qcom/qcom-apq8060-dragonboard.dts
@@ -5,6 +5,7 @@
 #include <dt-bindings/pinctrl/qcom,pmic-gpio.h>
 #include <dt-bindings/pinctrl/qcom,pmic-mpp.h>
 #include "qcom-msm8660.dtsi"
+#include "pm8058.dtsi"
 
 / {
 	model = "Qualcomm APQ8060 Dragonboard";
@@ -71,7 +72,7 @@
 		/* Trig on both edges - getting close or far away */
 		interrupts-extended = <&pm8058_gpio 34 IRQ_TYPE_EDGE_BOTH>;
 		/* MPP05 analog input to the XOADC */
-		io-channels = <&xoadc 0x00 0x05>;
+		io-channels = <&pm8058_xoadc 0x00 0x05>;
 		io-channel-names = "aout";
 		pinctrl-names = "default";
 		pinctrl-0 = <&dragon_cm3605_gpios>, <&dragon_cm3605_mpps>;
@@ -272,6 +273,10 @@
 	};
 };
 
+&pm8058 {
+	interrupts-extended = <&tlmm 88 IRQ_TYPE_LEVEL_LOW>;
+};
+
 &pm8058_gpio {
 	dragon_ethernet_gpios: ethernet-state {
 		pinconf {
@@ -447,6 +452,8 @@
 	 * that means
 	 */
 	regulators-0 {
+		compatible = "qcom,rpm-pm8901-regulators";
+
 		vdd_l0-supply = <&pm8901_s4>;
 		vdd_l1-supply = <&vph>;
 		vdd_l2-supply = <&vph>;
@@ -464,57 +471,63 @@
 		lvs3_in-supply = <&pm8058_s2>;
 		mvs_in-supply = <&pm8058_s3>;
 
-		l0 {
+		pm8901_l0: l0 {
 			regulator-min-microvolt = <1200000>;
 			regulator-max-microvolt = <1200000>;
 			bias-pull-down;
 		};
-		l1 {
+
+		pm8901_l1: l1 {
 			regulator-min-microvolt = <3300000>;
 			regulator-max-microvolt = <3300000>;
 			bias-pull-down;
 		};
-		l2 {
+
+		pm8901_l2: l2 {
 			/* TMA340 requires strictly 3.3V */
 			regulator-min-microvolt = <3300000>;
 			regulator-max-microvolt = <3300000>;
 			bias-pull-down;
 		};
-		l3 {
+
+		pm8901_l3: l3 {
 			regulator-min-microvolt = <3300000>;
 			regulator-max-microvolt = <3300000>;
 			bias-pull-down;
 		};
-		l4 {
+
+		pm8901_l4: l4 {
 			regulator-min-microvolt = <2600000>;
 			regulator-max-microvolt = <2600000>;
 			bias-pull-down;
 		};
-		l5 {
+
+		pm8901_l5: l5 {
 			regulator-min-microvolt = <2850000>;
 			regulator-max-microvolt = <2850000>;
 			bias-pull-down;
 		};
-		l6 {
+
+		pm8901_l6: l6 {
 			regulator-min-microvolt = <2200000>;
 			regulator-max-microvolt = <2200000>;
 			bias-pull-down;
 		};
 
 		/* s0 and s1 are SAW regulators controlled over SPM */
-		s2 {
+		pm8901_s2: s2 {
 			regulator-min-microvolt = <1300000>;
 			regulator-max-microvolt = <1300000>;
 			qcom,switch-mode-frequency = <1600000>;
 			bias-pull-down;
 		};
-		s3 {
+		pm8901_s3: s3 {
 			regulator-min-microvolt = <1100000>;
 			regulator-max-microvolt = <1100000>;
 			qcom,switch-mode-frequency = <1600000>;
 			bias-pull-down;
 		};
-		s4 {
+		pm8901_s4: s4 {
 			regulator-min-microvolt = <1225000>;
 			regulator-max-microvolt = <1225000>;
 			qcom,switch-mode-frequency = <1600000>;
@@ -522,17 +535,22 @@
 		};
 
 		/* LVS0 thru 3 and mvs are just switches */
-		lvs0 {
+		pm8901_lvs0: lvs0 {
 			regulator-always-on;
 		};
-		lvs1 { };
-		lvs2 { };
-		lvs3 { };
-		mvs { };
 
+		pm8901_lvs1: lvs1 { };
+
+		pm8901_lvs2: lvs2 { };
+
+		pm8901_lvs3: lvs3 { };
+
+		pm8901_mvs: mvs { };
 	};
 
 	regulators-1 {
+		compatible = "qcom,rpm-pm8058-regulators";
+
 		vdd_l0_l1_lvs-supply = <&pm8058_s3>;
 		vdd_l2_l11_l12-supply = <&vph>;
 		vdd_l3_l4_l5-supply = <&vph>;
@@ -554,144 +572,169 @@
 		vdd_s4-supply = <&vph>;
 		vdd_ncp-supply = <&vph>;
 
-		l0 {
+		pm8058_l0: l0 {
 			regulator-min-microvolt = <1200000>;
 			regulator-max-microvolt = <1200000>;
 			bias-pull-down;
 		};
-		l1 {
+
+		pm8058_l1: l1 {
 			regulator-min-microvolt = <1200000>;
 			regulator-max-microvolt = <1200000>;
 			bias-pull-down;
 		};
-		l2 {
+
+		pm8058_l2: l2 {
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <2600000>;
 			bias-pull-down;
 		};
-		l3 {
+
+		pm8058_l3: l3 {
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
 			bias-pull-down;
 		};
-		l4 {
+
+		pm8058_l4: l4 {
 			regulator-min-microvolt = <2850000>;
 			regulator-max-microvolt = <2850000>;
 			bias-pull-down;
 		};
-		l5 {
+
+		pm8058_l5: l5 {
 			regulator-min-microvolt = <2850000>;
 			regulator-max-microvolt = <2850000>;
 			bias-pull-down;
 		};
-		l6 {
+
+		pm8058_l6: l6 {
 			regulator-min-microvolt = <3000000>;
 			regulator-max-microvolt = <3600000>;
 			bias-pull-down;
 		};
-		l7 {
+
+		pm8058_l7: l7 {
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
 			bias-pull-down;
 		};
-		l8 {
+
+		pm8058_l8: l8 {
 			regulator-min-microvolt = <2900000>;
 			regulator-max-microvolt = <3050000>;
 			bias-pull-down;
 		};
-		l9 {
+
+		pm8058_l9: l9 {
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
 			bias-pull-down;
 		};
-		l10 {
+
+		pm8058_l10: l10 {
 			regulator-min-microvolt = <2600000>;
 			regulator-max-microvolt = <2600000>;
 			bias-pull-down;
 		};
-		l11 {
+
+		pm8058_l11: l11 {
 			regulator-min-microvolt = <1500000>;
 			regulator-max-microvolt = <1500000>;
 			bias-pull-down;
 		};
-		l12 {
+
+		pm8058_l12: l12 {
 			regulator-min-microvolt = <2900000>;
 			regulator-max-microvolt = <2900000>;
 			bias-pull-down;
 		};
-		l13 {
+
+		pm8058_l13: l13 {
 			regulator-min-microvolt = <2050000>;
 			regulator-max-microvolt = <2050000>;
 			bias-pull-down;
 		};
-		l14 {
+
+		pm8058_l14: l14 {
 			regulator-min-microvolt = <2850000>;
 			regulator-max-microvolt = <2850000>;
 		};
-		l15 {
+
+		pm8058_l15: l15 {
 			regulator-min-microvolt = <2850000>;
 			regulator-max-microvolt = <2850000>;
 			bias-pull-down;
 		};
-		l16 {
+
+		pm8058_l16: l16 {
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
 			bias-pull-down;
 			regulator-always-on;
 		};
-		l17 {
+
+		pm8058_l17: l17 {
 			// 1.5V according to schematic
 			regulator-min-microvolt = <2600000>;
 			regulator-max-microvolt = <2600000>;
 			bias-pull-down;
 		};
-		l18 {
+
+		pm8058_l18: l18 {
 			regulator-min-microvolt = <2200000>;
 			regulator-max-microvolt = <2200000>;
 			bias-pull-down;
 		};
-		l19 {
+
+		pm8058_l19: l19 {
 			regulator-min-microvolt = <2500000>;
 			regulator-max-microvolt = <2500000>;
 			bias-pull-down;
 		};
-		l20 {
+
+		pm8058_l20: l20 {
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
 			bias-pull-down;
 		};
-		l21 {
+
+		pm8058_l21: l21 {
 			// 1.1 V according to schematic
 			regulator-min-microvolt = <1200000>;
 			regulator-max-microvolt = <1200000>;
 			bias-pull-down;
 			regulator-always-on;
 		};
-		l22 {
+
+		pm8058_l22: l22 {
 			// 1.2 V according to schematic
 			regulator-min-microvolt = <1150000>;
 			regulator-max-microvolt = <1150000>;
 			bias-pull-down;
 		};
-		l23 {
+
+		pm8058_l23: l23 {
 			// Unused
 			regulator-min-microvolt = <1200000>;
 			regulator-max-microvolt = <1200000>;
 			bias-pull-down;
 		};
-		l24 {
+
+		pm8058_l24: l24 {
 			// Unused
 			regulator-min-microvolt = <1200000>;
 			regulator-max-microvolt = <1200000>;
 			bias-pull-down;
 		};
-		l25 {
+
+		pm8058_l25: l25 {
 			regulator-min-microvolt = <1200000>;
 			regulator-max-microvolt = <1200000>;
 			bias-pull-down;
 		};
 
-		s0 {
+		pm8058_s0: s0 {
 			// regulator-min-microvolt = <500000>;
 			// regulator-max-microvolt = <1325000>;
 			regulator-min-microvolt = <1100000>;
@@ -699,7 +742,8 @@
 			qcom,switch-mode-frequency = <1600000>;
 			bias-pull-down;
 		};
-		s1 {
+
+		pm8058_s1: s1 {
 			// regulator-min-microvolt = <500000>;
 			// regulator-max-microvolt = <1250000>;
 			regulator-min-microvolt = <1100000>;
@@ -707,21 +751,24 @@
 			qcom,switch-mode-frequency = <1600000>;
 			bias-pull-down;
 		};
-		s2 {
+
+		pm8058_s2: s2 {
 			// 1.3 V according to schematic
 			regulator-min-microvolt = <1200000>;
 			regulator-max-microvolt = <1400000>;
 			qcom,switch-mode-frequency = <1600000>;
 			bias-pull-down;
 		};
-		s3 {
+
+		pm8058_s3: s3 {
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
 			qcom,switch-mode-frequency = <1600000>;
 			regulator-always-on;
 			bias-pull-down;
 		};
-		s4 {
+
+		pm8058_s4: s4 {
 			regulator-min-microvolt = <2200000>;
 			regulator-max-microvolt = <2200000>;
 			qcom,switch-mode-frequency = <1600000>;
@@ -730,14 +777,15 @@
 		};
 
 		/* LVS0 and LVS1 are just switches */
-		lvs0 {
+		pm8058_lvs0: lvs0 {
 			bias-pull-down;
 		};
-		lvs1 {
+
+		pm8058_lvs1: lvs1 {
 			bias-pull-down;
 		};
 
-		ncp {
+		pm8058_ncp: ncp {
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
 			qcom,switch-mode-frequency = <1600000>;
@@ -944,28 +992,32 @@
 	};
 };
 
-&xoadc {
+&pm8058_xoadc {
 	/* Reference voltage 2.2 V */
 	xoadc-ref-supply = <&pm8058_l18>;
 
 	/* Board-specific channels */
-	mpp5@5 {
+	adc-channel@5 {
 		/* Connected to AOUT of ALS sensor */
 		reg = <0x00 0x05>;
 	};
-	mpp6@6 {
+
+	adc-channel@6 {
 		/* Connected to test point TP43 */
 		reg = <0x00 0x06>;
 	};
-	mpp7@7 {
+
+	adc-channel@7 {
 		/* Connected to battery thermistor */
 		reg = <0x00 0x07>;
 	};
-	mpp8@8 {
+
+	adc-channel@8 {
 		/* Connected to battery ID detector */
 		reg = <0x00 0x08>;
 	};
-	mpp9@9 {
+
+	adc-channel@9 {
 		/* Connected to XO thermistor */
 		reg = <0x00 0x09>;
 	};
diff --git a/arch/arm/boot/dts/qcom/qcom-apq8064-asus-nexus7-flo.dts b/arch/arm/boot/dts/qcom/qcom-apq8064-asus-nexus7-flo.dts
index c0dd6399f597..d460743fbb94 100644
--- a/arch/arm/boot/dts/qcom/qcom-apq8064-asus-nexus7-flo.dts
+++ b/arch/arm/boot/dts/qcom/qcom-apq8064-asus-nexus7-flo.dts
@@ -1,8 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "qcom-apq8064-v2.0.dtsi"
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/pinctrl/qcom,pmic-gpio.h>
+
+#include "qcom-apq8064-v2.0.dtsi"
+#include "pm8821.dtsi"
+#include "pm8921.dtsi"
+
 / {
 	model = "Asus Nexus7(flo)";
 	compatible = "asus,nexus7-flo", "qcom,apq8064";
@@ -180,24 +184,26 @@
 	status = "okay";
 };
 
-/* eMMC */
-&sdcc1 {
-	vmmc-supply = <&pm8921_l5>;
-	vqmmc-supply = <&pm8921_s4>;
-	status = "okay";
-};
-
 &mdp_dsi1_out {
 	remote-endpoint = <&dsi0_in>;
 };
 
+&pm8821 {
+	interrupts-extended = <&tlmm_pinmux 76 IRQ_TYPE_LEVEL_LOW>;
+};
+
+&pm8921 {
+	interrupts-extended = <&tlmm_pinmux 74 IRQ_TYPE_LEVEL_LOW>;
+};
+
 &rpm {
 	regulators {
+		compatible = "qcom,rpm-pm8921-regulators";
+
 		vdd_l1_l2_l12_l18-supply = <&pm8921_s4>;
 		vin_lvs1_3_6-supply = <&pm8921_s4>;
 		vin_lvs4_5_7-supply = <&pm8921_s4>;
 
-
 		vdd_l24-supply = <&pm8921_s1>;
 		vdd_l25-supply = <&pm8921_s1>;
 		vin_lvs2-supply = <&pm8921_s1>;
@@ -209,7 +215,7 @@
 		vdd_ncp-supply = <&pm8921_l6>;
 
 		/* Buck SMPS */
-		s1 {
+		pm8921_s1: s1 {
 			regulator-always-on;
 			regulator-min-microvolt = <1225000>;
 			regulator-max-microvolt = <1225000>;
@@ -218,7 +224,7 @@
 		};
 
 		/* msm otg HSUSB_VDDCX */
-		s3 {
+		pm8921_s3: s3 {
 			regulator-min-microvolt = <500000>;
 			regulator-max-microvolt = <1150000>;
 			qcom,switch-mode-frequency = <4800000>;
@@ -231,55 +237,58 @@
 		 * tabla2x-slim-CDC_VDD_CP
 		 * tabla2x-slim-VDDIO_CDC
 		 */
-		s4 {
+		pm8921_s4: s4 {
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
 			qcom,switch-mode-frequency = <3200000>;
 			regulator-always-on;
 		};
 
-		s7 {
+		pm8921_s7: s7 {
 			regulator-min-microvolt = <1300000>;
 			regulator-max-microvolt = <1300000>;
 			qcom,switch-mode-frequency = <3200000>;
 		};
 
 		/* mipi_dsi.1-dsi1_pll_vdda */
-		l2 {
+		pm8921_l2: l2 {
 			regulator-min-microvolt = <1200000>;
 			regulator-max-microvolt = <1200000>;
 			regulator-always-on;
 		};
 
 		/* msm_otg-HSUSB_3p3 */
-		l3 {
+		pm8921_l3: l3 {
 			regulator-min-microvolt = <3075000>;
 			regulator-max-microvolt = <3075000>;
 			bias-pull-down;
 		};
 
 		/* msm_otg-HSUSB_1p8 */
-		l4 {
+		pm8921_l4: l4 {
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
 			bias-pull-down;
 		};
 
 		/* msm_sdcc.1-sdc_vdd */
-		l5 {
+		pm8921_l5: l5 {
 			regulator-min-microvolt = <2950000>;
 			regulator-max-microvolt = <2950000>;
 			regulator-always-on;
 			bias-pull-down;
 		};
 
-		l6 {
+		pm8921_l6: l6 {
 			regulator-min-microvolt = <2950000>;
 			regulator-max-microvolt = <2950000>;
 		};
 
+		pm8921_l8: l8 {
+		};
+
 		/* mipi_dsi.1-dsi1_avdd */
-		l11 {
+		pm8921_l11: l11 {
 			regulator-min-microvolt = <3000000>;
 			regulator-max-microvolt = <3000000>;
 			bias-pull-down;
@@ -287,14 +296,14 @@
 		};
 
 		/* pwm_power for backlight */
-		l17 {
+		pm8921_l17: l17 {
 			regulator-min-microvolt = <3000000>;
 			regulator-max-microvolt = <3000000>;
 			regulator-always-on;
 		};
 
 		/* camera, qdsp6 */
-		l23 {
+		pm8921_l23: l23 {
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
 			bias-pull-down;
@@ -304,37 +313,44 @@
 		 * tabla2x-slim-CDC_VDDA_A_1P2V
 		 * tabla2x-slim-VDDD_CDC_D
 		 */
-		l25 {
+		pm8921_l25: l25 {
 			regulator-min-microvolt = <1250000>;
 			regulator-max-microvolt = <1250000>;
 			bias-pull-down;
 		};
 
-		lvs1 {
+		pm8921_lvs1: lvs1 {
 			bias-pull-down;
 		};
 
-		lvs4 {
+		pm8921_lvs4: lvs4 {
 			bias-pull-down;
 		};
 
-		lvs5 {
+		pm8921_lvs5: lvs5 {
 			bias-pull-down;
 		};
 
-		lvs6 {
+		pm8921_lvs6: lvs6 {
 			bias-pull-down;
 		};
 		/*
 		 * mipi_dsi.1-dsi1_vddio
 		 * pil_riva-pll_vdd
 		 */
-		lvs7 {
+		pm8921_lvs7: lvs7 {
 			bias-pull-down;
 		};
 	};
 };
 
+/* eMMC */
+&sdcc1 {
+	vmmc-supply = <&pm8921_l5>;
+	vqmmc-supply = <&pm8921_s4>;
+	status = "okay";
+};
+
 &usb_hs1_phy {
 	v3p3-supply = <&pm8921_l3>;
 	v1p8-supply = <&pm8921_l4>;
diff --git a/arch/arm/boot/dts/qcom/qcom-apq8064-cm-qs600.dts b/arch/arm/boot/dts/qcom/qcom-apq8064-cm-qs600.dts
index d6ecfd8addb7..671d58cc2741 100644
--- a/arch/arm/boot/dts/qcom/qcom-apq8064-cm-qs600.dts
+++ b/arch/arm/boot/dts/qcom/qcom-apq8064-cm-qs600.dts
@@ -1,8 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "qcom-apq8064-v2.0.dtsi"
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/pinctrl/qcom,pmic-gpio.h>
 
+#include "qcom-apq8064-v2.0.dtsi"
+#include "pm8821.dtsi"
+#include "pm8921.dtsi"
+
 / {
 	model = "CompuLab CM-QS600";
 	compatible = "qcom,apq8064-cm-qs600", "qcom,apq8064";
@@ -69,6 +72,14 @@
 	status = "okay";
 };
 
+&pm8821 {
+	interrupts-extended = <&tlmm_pinmux 76 IRQ_TYPE_LEVEL_LOW>;
+};
+
+&pm8921 {
+	interrupts-extended = <&tlmm_pinmux 74 IRQ_TYPE_LEVEL_LOW>;
+};
+
 &pm8921_gpio {
 	wlan_default_gpios: wlan-gpios-state {
 		pinconf {
@@ -82,6 +93,8 @@
 
 &rpm {
 	regulators {
+		compatible = "qcom,rpm-pm8921-regulators";
+
 		vin_lvs1_3_6-supply = <&pm8921_s4>;
 		vin_lvs2-supply = <&pm8921_s1>;
 		vin_lvs4_5_7-supply = <&pm8921_s4>;
@@ -93,9 +106,8 @@
 		vdd_l27-supply = <&pm8921_s7>;
 		vdd_l28-supply = <&pm8921_s7>;
 
-
 		/* Buck SMPS */
-		s1 {
+		pm8921_s1: s1 {
 			regulator-always-on;
 			regulator-min-microvolt = <1225000>;
 			regulator-max-microvolt = <1225000>;
@@ -103,52 +115,51 @@
 			bias-pull-down;
 		};
 
-		s3 {
+		pm8921_s3: s3 {
 			regulator-min-microvolt = <1000000>;
 			regulator-max-microvolt = <1400000>;
 			qcom,switch-mode-frequency = <4800000>;
 		};
 
-		s4 {
+		pm8921_s4: s4 {
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
 			qcom,switch-mode-frequency = <3200000>;
 		};
 
-		s7 {
+		pm8921_s7: s7 {
 			regulator-min-microvolt = <1300000>;
 			regulator-max-microvolt = <1300000>;
 			qcom,switch-mode-frequency = <3200000>;
 		};
 
-		l3 {
+		pm8921_l3: l3 {
 			regulator-min-microvolt = <3050000>;
 			regulator-max-microvolt = <3300000>;
 			bias-pull-down;
 		};
 
-		l4 {
+		pm8921_l4: l4 {
 			regulator-min-microvolt = <1000000>;
 			regulator-max-microvolt = <1800000>;
 			bias-pull-down;
 		};
 
-		l5 {
+		pm8921_l5: l5 {
 			regulator-min-microvolt = <2750000>;
 			regulator-max-microvolt = <3000000>;
 			bias-pull-down;
 		};
 
-		l23 {
+		pm8921_l23: l23 {
 			regulator-min-microvolt = <1700000>;
 			regulator-max-microvolt = <1900000>;
 			bias-pull-down;
 		};
 
-		lvs6 {
+		pm8921_lvs6: lvs6 {
 			bias-pull-down;
 		};
-
 	};
 };
 
diff --git a/arch/arm/boot/dts/qcom/qcom-apq8064-ifc6410.dts b/arch/arm/boot/dts/qcom/qcom-apq8064-ifc6410.dts
index b0c5e7bd5e74..ed86b24119c9 100644
--- a/arch/arm/boot/dts/qcom/qcom-apq8064-ifc6410.dts
+++ b/arch/arm/boot/dts/qcom/qcom-apq8064-ifc6410.dts
@@ -1,9 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "qcom-apq8064-v2.0.dtsi"
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/leds/common.h>
 #include <dt-bindings/pinctrl/qcom,pmic-gpio.h>
 
+#include "qcom-apq8064-v2.0.dtsi"
+#include "pm8821.dtsi"
+#include "pm8921.dtsi"
+
 / {
 	model = "Qualcomm APQ8064/IFC6410";
 	compatible = "qcom,apq8064-ifc6410", "qcom,apq8064";
@@ -170,6 +173,14 @@
 	perst-gpios = <&tlmm_pinmux 27 GPIO_ACTIVE_LOW>;
 };
 
+&pm8821 {
+	interrupts-extended = <&tlmm_pinmux 76 IRQ_TYPE_LEVEL_LOW>;
+};
+
+&pm8921 {
+	interrupts-extended = <&tlmm_pinmux 74 IRQ_TYPE_LEVEL_LOW>;
+};
+
 &pm8921_gpio {
 	wlan_default_gpios: wlan-gpios-state {
 		pinconf {
@@ -192,6 +203,8 @@
 
 &rpm {
 	regulators {
+		compatible = "qcom,rpm-pm8921-regulators";
+
 		vin_lvs1_3_6-supply = <&pm8921_s4>;
 		vin_lvs2-supply = <&pm8921_s1>;
 		vin_lvs4_5_7-supply = <&pm8921_s4>;
@@ -203,9 +216,8 @@
 		vdd_l27-supply = <&pm8921_s7>;
 		vdd_l28-supply = <&pm8921_s7>;
 
-
 		/* Buck SMPS */
-		s1 {
+		pm8921_s1: s1 {
 			regulator-always-on;
 			regulator-min-microvolt = <1225000>;
 			regulator-max-microvolt = <1225000>;
@@ -213,59 +225,63 @@
 			bias-pull-down;
 		};
 
-		s3 {
+		pm8921_s3: s3 {
 			regulator-min-microvolt = <1000000>;
 			regulator-max-microvolt = <1400000>;
 			qcom,switch-mode-frequency = <4800000>;
 		};
 
-		s4 {
+		pm8921_s4: s4 {
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
 			qcom,switch-mode-frequency = <3200000>;
 		};
 
-		s7 {
+		pm8921_s7: s7 {
 			regulator-min-microvolt = <1300000>;
 			regulator-max-microvolt = <1300000>;
 			qcom,switch-mode-frequency = <3200000>;
 		};
 
-		l3 {
+		pm8921_l3: l3 {
 			regulator-min-microvolt = <3050000>;
 			regulator-max-microvolt = <3300000>;
 			bias-pull-down;
 		};
 
-		l4 {
+		pm8921_l4: l4 {
 			regulator-min-microvolt = <1000000>;
 			regulator-max-microvolt = <1800000>;
 			bias-pull-down;
 		};
 
-		l5 {
+		pm8921_l5: l5 {
 			regulator-min-microvolt = <2750000>;
 			regulator-max-microvolt = <3000000>;
 			bias-pull-down;
 		};
 
-		l6 {
+		pm8921_l6: l6 {
 			regulator-min-microvolt = <2950000>;
 			regulator-max-microvolt = <2950000>;
 			bias-pull-down;
 		};
 
-		l23 {
+		pm8921_l23: l23 {
 			regulator-min-microvolt = <1700000>;
 			regulator-max-microvolt = <1900000>;
 			bias-pull-down;
 		};
 
-		lvs1 {
+		pm8921_lvs1: lvs1 {
+			bias-pull-down;
+		};
+
+		pm8921_lvs6: lvs6 {
 			bias-pull-down;
 		};
 
-		lvs6 {
+		pm8921_hdmi_switch: hdmi-switch {
 			bias-pull-down;
 		};
 	};
diff --git a/arch/arm/boot/dts/qcom/qcom-apq8064-sony-xperia-lagan-yuga.dts b/arch/arm/boot/dts/qcom/qcom-apq8064-sony-xperia-lagan-yuga.dts
index 9244512b74d1..2412aa3e3e8d 100644
--- a/arch/arm/boot/dts/qcom/qcom-apq8064-sony-xperia-lagan-yuga.dts
+++ b/arch/arm/boot/dts/qcom/qcom-apq8064-sony-xperia-lagan-yuga.dts
@@ -1,10 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "qcom-apq8064-v2.0.dtsi"
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/mfd/qcom-rpm.h>
 #include <dt-bindings/pinctrl/qcom,pmic-gpio.h>
 
+#include "qcom-apq8064-v2.0.dtsi"
+#include "pm8821.dtsi"
+#include "pm8921.dtsi"
+
 / {
 	model = "Sony Xperia Z";
 	compatible = "sony,xperia-yuga", "qcom,apq8064";
@@ -65,6 +68,14 @@
 	status = "okay";
 };
 
+&pm8821 {
+	interrupts-extended = <&tlmm_pinmux 76 IRQ_TYPE_LEVEL_LOW>;
+};
+
+&pm8921 {
+	interrupts-extended = <&tlmm_pinmux 74 IRQ_TYPE_LEVEL_LOW>;
+};
+
 &pm8921_gpio {
 	gpio_keys_pin_a: gpio-keys-active-state {
 		pins = "gpio3", "gpio4", "gpio29", "gpio35";
@@ -82,11 +93,25 @@
 &riva {
 	pinctrl-names = "default";
 	pinctrl-0 = <&riva_wlan_pin_a>, <&riva_bt_pin_a>, <&riva_fm_pin_a>;
+
+	vddcx-supply = <&pm8921_s3>;
+	vddmx-supply = <&pm8921_l24>;
+	vddpx-supply = <&pm8921_s4>;
+
 	status = "okay";
+
+	iris {
+		vddxo-supply = <&pm8921_l4>;
+		vddrfa-supply = <&pm8921_s2>;
+		vddpa-supply = <&pm8921_l10>;
+		vdddig-supply = <&pm8921_lvs2>;
+	};
 };
 
 &rpm {
 	regulators {
+		compatible = "qcom,rpm-pm8921-regulators";
+
 		vin_l1_l2_l12_l18-supply = <&pm8921_s4>;
 		vin_lvs_1_3_6-supply = <&pm8921_s4>;
 		vin_lvs_4_5_7-supply = <&pm8921_s4>;
@@ -98,7 +123,7 @@
 		vin_l28-supply = <&pm8921_s7>;
 
 		/* Buck SMPS */
-		s1 {
+		pm8921_s1: s1 {
 			regulator-always-on;
 			regulator-min-microvolt = <1225000>;
 			regulator-max-microvolt = <1225000>;
@@ -106,21 +131,21 @@
 			bias-pull-down;
 		};
 
-		s2 {
+		pm8921_s2: s2 {
 			regulator-min-microvolt = <1300000>;
 			regulator-max-microvolt = <1300000>;
 			qcom,switch-mode-frequency = <1600000>;
 			bias-pull-down;
 		};
 
-		s3 {
+		pm8921_s3: s3 {
 			regulator-min-microvolt = <500000>;
 			regulator-max-microvolt = <1150000>;
 			qcom,switch-mode-frequency = <4800000>;
 			bias-pull-down;
 		};
 
-		s4 {
+		pm8921_s4: s4 {
 			regulator-always-on;
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
@@ -129,205 +154,207 @@
 			qcom,force-mode = <QCOM_RPM_FORCE_MODE_AUTO>;
 		};
 
-		s7 {
+		pm8921_s7: s7 {
 			regulator-min-microvolt = <1300000>;
 			regulator-max-microvolt = <1300000>;
 			qcom,switch-mode-frequency = <3200000>;
 		};
 
-		s8 {
+		pm8921_s8: s8 {
 			regulator-min-microvolt = <2200000>;
 			regulator-max-microvolt = <2200000>;
 			qcom,switch-mode-frequency = <1600000>;
 		};
 
 		/* PMOS LDO */
-		l1 {
+		pm8921_l1: l1 {
 			regulator-always-on;
 			regulator-min-microvolt = <1100000>;
 			regulator-max-microvolt = <1100000>;
 			bias-pull-down;
 		};
 
-		l2 {
+		pm8921_l2: l2 {
 			regulator-min-microvolt = <1200000>;
 			regulator-max-microvolt = <1200000>;
 			bias-pull-down;
 		};
 
-		l3 {
+		pm8921_l3: l3 {
 			regulator-min-microvolt = <3075000>;
 			regulator-max-microvolt = <3075000>;
 			bias-pull-down;
 		};
 
-		l4 {
+		pm8921_l4: l4 {
 			regulator-always-on;
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
 			bias-pull-down;
 		};
 
-		l5 {
+		pm8921_l5: l5 {
 			regulator-min-microvolt = <2950000>;
 			regulator-max-microvolt = <2950000>;
 			bias-pull-down;
 		};
 
-		l6 {
+		pm8921_l6: l6 {
 			regulator-min-microvolt = <2950000>;
 			regulator-max-microvolt = <2950000>;
 			bias-pull-down;
 		};
 
-		l7 {
+		pm8921_l7: l7 {
 			regulator-min-microvolt = <1850000>;
 			regulator-max-microvolt = <2950000>;
 			bias-pull-down;
 		};
 
-		l8 {
+		pm8921_l8: l8 {
 			regulator-min-microvolt = <2800000>;
 			regulator-max-microvolt = <2800000>;
 			bias-pull-down;
 		};
 
-		l9 {
+		pm8921_l9: l9 {
 			regulator-min-microvolt = <3000000>;
 			regulator-max-microvolt = <3000000>;
 			bias-pull-down;
 		};
 
-		l10 {
+		pm8921_l10: l10 {
 			regulator-min-microvolt = <2900000>;
 			regulator-max-microvolt = <2900000>;
 			bias-pull-down;
 		};
 
-		l11 {
+		pm8921_l11: l11 {
 			regulator-min-microvolt = <3000000>;
 			regulator-max-microvolt = <3000000>;
 			bias-pull-down;
 		};
 
-		l12 {
+		pm8921_l12: l12 {
 			regulator-min-microvolt = <1200000>;
 			regulator-max-microvolt = <1200000>;
 			bias-pull-down;
 		};
 
-		l14 {
+		pm8921_l14: l14 {
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
 			bias-pull-down;
 		};
 
-		l15 {
+		pm8921_l15: l15 {
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <2950000>;
 			bias-pull-down;
 		};
 
-		l16 {
+		pm8921_l16: l16 {
 			regulator-min-microvolt = <2800000>;
 			regulator-max-microvolt = <2800000>;
 			bias-pull-down;
 		};
 
-		l17 {
+		pm8921_l17: l17 {
 			regulator-min-microvolt = <2000000>;
 			regulator-max-microvolt = <2000000>;
 			bias-pull-down;
 		};
 
-		l18 {
+		pm8921_l18: l18 {
 			regulator-min-microvolt = <1200000>;
 			regulator-max-microvolt = <1200000>;
 			bias-pull-down;
 		};
 
-		l21 {
+		pm8921_l21: l21 {
 			regulator-min-microvolt = <1050000>;
 			regulator-max-microvolt = <1050000>;
 			bias-pull-down;
 		};
 
-		l22 {
+		pm8921_l22: l22 {
 			regulator-min-microvolt = <2600000>;
 			regulator-max-microvolt = <2600000>;
 			bias-pull-down;
 		};
 
-		l23 {
+		pm8921_l23: l23 {
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
 			bias-pull-down;
 		};
 
-		l24 {
+		pm8921_l24: l24 {
 			regulator-min-microvolt = <750000>;
 			regulator-max-microvolt = <1150000>;
 			bias-pull-down;
 		};
 
-		l25 {
+		pm8921_l25: l25 {
 			regulator-always-on;
 			regulator-min-microvolt = <1250000>;
 			regulator-max-microvolt = <1250000>;
 			bias-pull-down;
 		};
 
-		l27 {
+		pm8921_l27: l27 {
 			regulator-min-microvolt = <1100000>;
 			regulator-max-microvolt = <1100000>;
 		};
 
-		l28 {
+		pm8921_l28: l28 {
 			regulator-min-microvolt = <1050000>;
 			regulator-max-microvolt = <1050000>;
 			bias-pull-down;
 		};
 
-		l29 {
+		pm8921_l29: l29 {
 			regulator-min-microvolt = <2000000>;
 			regulator-max-microvolt = <2000000>;
 			bias-pull-down;
 		};
 
 		/* Low Voltage Switch */
-		lvs1 {
+		pm8921_lvs1: lvs1 {
 			bias-pull-down;
 		};
 
-		lvs2 {
+		pm8921_lvs2: lvs2 {
 			bias-pull-down;
 		};
 
-		lvs3 {
+		pm8921_lvs3: lvs3 {
 			bias-pull-down;
 		};
 
-		lvs4 {
+		pm8921_lvs4: lvs4 {
 			bias-pull-down;
 		};
 
-		lvs5 {
+		pm8921_lvs5: lvs5 {
 			bias-pull-down;
 		};
 
-		lvs6 {
+		pm8921_lvs6: lvs6 {
 			bias-pull-down;
 		};
 
-		lvs7 {
+		pm8921_lvs7: lvs7 {
 			bias-pull-down;
 		};
 
-		usb-switch {};
+		pm8921_usb_switch: usb-switch {};
 
-		hdmi-switch {};
+		pm8921_hdmi_switch: hdmi-switch {
+			bias-pull-down;
+		};
 
-		ncp {
+		pm8921_ncp: ncp {
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
 			qcom,switch-mode-frequency = <1600000>;
diff --git a/arch/arm/boot/dts/qcom/qcom-apq8064.dtsi b/arch/arm/boot/dts/qcom/qcom-apq8064.dtsi
index 59fd86b9fb47..3faf57035d54 100644
--- a/arch/arm/boot/dts/qcom/qcom-apq8064.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-apq8064.dtsi
@@ -284,23 +284,6 @@
 		};
 	};
 
-
-	/*
-	 * These channels from the ADC are simply hardware monitors.
-	 * That is why the ADC is referred to as "HKADC" - HouseKeeping
-	 * ADC.
-	 */
-	iio-hwmon {
-		compatible = "iio-hwmon";
-		io-channels = <&xoadc 0x00 0x01>, /* Battery */
-			    <&xoadc 0x00 0x02>, /* DC in (charger) */
-			    <&xoadc 0x00 0x04>, /* VPH the main system voltage */
-			    <&xoadc 0x00 0x0b>, /* Die temperature */
-			    <&xoadc 0x00 0x0c>, /* Reference voltage 1.25V */
-			    <&xoadc 0x00 0x0d>, /* Reference voltage 0.625V */
-			    <&xoadc 0x00 0x0e>; /* Charger temperature */
-	};
-
 	soc: soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -655,133 +638,16 @@
 			clock-names = "core";
 		};
 
-		ssbi@c00000 {
+		ssbi2: ssbi@c00000 {
 			compatible = "qcom,ssbi";
 			reg = <0x00c00000 0x1000>;
 			qcom,controller-type = "pmic-arbiter";
-
-			pm8821: pmic {
-				compatible = "qcom,pm8821";
-				interrupt-parent = <&tlmm_pinmux>;
-				interrupts = <76 IRQ_TYPE_LEVEL_LOW>;
-				#interrupt-cells = <2>;
-				interrupt-controller;
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				pm8821_mpps: mpps@50 {
-					compatible = "qcom,pm8821-mpp", "qcom,ssbi-mpp";
-					reg = <0x50>;
-					interrupt-controller;
-					#interrupt-cells = <2>;
-					gpio-controller;
-					#gpio-cells = <2>;
-					gpio-ranges = <&pm8821_mpps 0 0 4>;
-				};
-			};
 		};
 
-		ssbi@500000 {
+		ssbi: ssbi@500000 {
 			compatible = "qcom,ssbi";
 			reg = <0x00500000 0x1000>;
 			qcom,controller-type = "pmic-arbiter";
-
-			pmicintc: pmic {
-				compatible = "qcom,pm8921";
-				interrupt-parent = <&tlmm_pinmux>;
-				interrupts = <74 8>;
-				#interrupt-cells = <2>;
-				interrupt-controller;
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				pm8921_gpio: gpio@150 {
-
-					compatible = "qcom,pm8921-gpio",
-						     "qcom,ssbi-gpio";
-					reg = <0x150>;
-					interrupt-controller;
-					#interrupt-cells = <2>;
-					gpio-controller;
-					gpio-ranges = <&pm8921_gpio 0 0 44>;
-					#gpio-cells = <2>;
-
-				};
-
-				pm8921_mpps: mpps@50 {
-					compatible = "qcom,pm8921-mpp",
-						     "qcom,ssbi-mpp";
-					reg = <0x50>;
-					gpio-controller;
-					#gpio-cells = <2>;
-					gpio-ranges = <&pm8921_mpps 0 0 12>;
-					interrupt-controller;
-					#interrupt-cells = <2>;
-				};
-
-				rtc@11d {
-					compatible = "qcom,pm8921-rtc";
-					interrupt-parent = <&pmicintc>;
-					interrupts = <39 1>;
-					reg = <0x11d>;
-					allow-set-time;
-				};
-
-				pwrkey@1c {
-					compatible = "qcom,pm8921-pwrkey";
-					reg = <0x1c>;
-					interrupt-parent = <&pmicintc>;
-					interrupts = <50 1>, <51 1>;
-					debounce = <15625>;
-					pull-up;
-				};
-
-				xoadc: xoadc@197 {
-					compatible = "qcom,pm8921-adc";
-					reg = <197>;
-					interrupts-extended = <&pmicintc 78 IRQ_TYPE_EDGE_RISING>;
-					#address-cells = <2>;
-					#size-cells = <0>;
-					#io-channel-cells = <2>;
-
-					vcoin: adc-channel@0 {
-						reg = <0x00 0x00>;
-					};
-					vbat: adc-channel@1 {
-						reg = <0x00 0x01>;
-					};
-					dcin: adc-channel@2 {
-						reg = <0x00 0x02>;
-					};
-					vph_pwr: adc-channel@4 {
-						reg = <0x00 0x04>;
-					};
-					batt_therm: adc-channel@8 {
-						reg = <0x00 0x08>;
-					};
-					batt_id: adc-channel@9 {
-						reg = <0x00 0x09>;
-					};
-					usb_vbus: adc-channel@a {
-						reg = <0x00 0x0a>;
-					};
-					die_temp: adc-channel@b {
-						reg = <0x00 0x0b>;
-					};
-					ref_625mv: adc-channel@c {
-						reg = <0x00 0x0c>;
-					};
-					ref_1250mv: adc-channel@d {
-						reg = <0x00 0x0d>;
-					};
-					chg_temp: adc-channel@e {
-						reg = <0x00 0x0e>;
-					};
-					ref_muxoff: adc-channel@f {
-						reg = <0x00 0x0f>;
-					};
-				};
-			};
 		};
 
 		qfprom: qfprom@700000 {
@@ -891,60 +757,6 @@
 				clocks = <&pxo_board>, <&cxo_board>;
 				clock-names = "pxo", "cxo";
 			};
-
-			regulators {
-				compatible = "qcom,rpm-pm8921-regulators";
-
-				pm8921_s1: s1 {};
-				pm8921_s2: s2 {};
-				pm8921_s3: s3 {};
-				pm8921_s4: s4 {};
-				pm8921_s7: s7 {};
-				pm8921_s8: s8 {};
-
-				pm8921_l1: l1 {};
-				pm8921_l2: l2 {};
-				pm8921_l3: l3 {};
-				pm8921_l4: l4 {};
-				pm8921_l5: l5 {};
-				pm8921_l6: l6 {};
-				pm8921_l7: l7 {};
-				pm8921_l8: l8 {};
-				pm8921_l9: l9 {};
-				pm8921_l10: l10 {};
-				pm8921_l11: l11 {};
-				pm8921_l12: l12 {};
-				pm8921_l14: l14 {};
-				pm8921_l15: l15 {};
-				pm8921_l16: l16 {};
-				pm8921_l17: l17 {};
-				pm8921_l18: l18 {};
-				pm8921_l21: l21 {};
-				pm8921_l22: l22 {};
-				pm8921_l23: l23 {};
-				pm8921_l24: l24 {};
-				pm8921_l25: l25 {};
-				pm8921_l26: l26 {};
-				pm8921_l27: l27 {};
-				pm8921_l28: l28 {};
-				pm8921_l29: l29 {};
-
-				pm8921_lvs1: lvs1 {};
-				pm8921_lvs2: lvs2 {};
-				pm8921_lvs3: lvs3 {};
-				pm8921_lvs4: lvs4 {};
-				pm8921_lvs5: lvs5 {};
-				pm8921_lvs6: lvs6 {};
-				pm8921_lvs7: lvs7 {};
-
-				pm8921_usb_switch: usb-switch {};
-
-				pm8921_hdmi_switch: hdmi-switch {
-					bias-pull-down;
-				};
-
-				pm8921_ncp: ncp {};
-			};
 		};
 
 		usb1: usb@12500000 {
@@ -1472,7 +1284,7 @@
 			qcom,ncb = <3>;
 		};
 
-		pcie: pci@1b500000 {
+		pcie: pcie@1b500000 {
 			compatible = "qcom,pcie-apq8064";
 			reg = <0x1b500000 0x1000>,
 			      <0x1b502000 0x80>,
@@ -1623,10 +1435,6 @@
 
 			memory-region = <&wcnss_mem>;
 
-			vddcx-supply = <&pm8921_s3>;
-			vddmx-supply = <&pm8921_l24>;
-			vddpx-supply = <&pm8921_s4>;
-
 			status = "disabled";
 
 			iris {
@@ -1634,11 +1442,6 @@
 
 				clocks = <&cxo_board>;
 				clock-names = "xo";
-
-				vddxo-supply = <&pm8921_l4>;
-				vddrfa-supply = <&pm8921_s2>;
-				vddpa-supply = <&pm8921_l10>;
-				vdddig-supply = <&pm8921_lvs2>;
 			};
 
 			smd-edge {
diff --git a/arch/arm/boot/dts/qcom/qcom-apq8074-dragonboard.dts b/arch/arm/boot/dts/qcom/qcom-apq8074-dragonboard.dts
index 6d1b2439ae3a..6fce0112361f 100644
--- a/arch/arm/boot/dts/qcom/qcom-apq8074-dragonboard.dts
+++ b/arch/arm/boot/dts/qcom/qcom-apq8074-dragonboard.dts
@@ -4,8 +4,8 @@
 #include <dt-bindings/leds/common.h>
 #include <dt-bindings/pinctrl/qcom,pmic-gpio.h>
 #include "qcom-msm8974.dtsi"
-#include "qcom-pm8841.dtsi"
-#include "qcom-pm8941.dtsi"
+#include "pm8841.dtsi"
+#include "pm8941.dtsi"
 
 /delete-node/ &mpss_region;
 
@@ -49,6 +49,33 @@
 			no-map;
 		};
 	};
+
+	vreg_boost: vreg-boost {
+		compatible = "regulator-fixed";
+
+		regulator-name = "vreg-boost";
+		regulator-min-microvolt = <3150000>;
+		regulator-max-microvolt = <3150000>;
+
+		regulator-always-on;
+		regulator-boot-on;
+
+		gpio = <&pm8941_gpios 21 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&boost_bypass_n_pin>;
+	};
+
+	vreg_vph_pwr: vreg-vph-pwr {
+		compatible = "regulator-fixed";
+		regulator-name = "vph-pwr";
+
+		regulator-min-microvolt = <3600000>;
+		regulator-max-microvolt = <3600000>;
+
+		regulator-always-on;
+	};
 };
 
 &blsp1_uart2 {
@@ -403,6 +430,10 @@
 	pinctrl-1 = <&sdc2_off>;
 };
 
+&smbb {
+	status = "okay";
+};
+
 &tlmm {
 	sdc1_on: sdc1-on-state {
 		clk-pins {
diff --git a/arch/arm/boot/dts/qcom/qcom-apq8084-ifc6540.dts b/arch/arm/boot/dts/qcom/qcom-apq8084-ifc6540.dts
index 116e59a3b76d..1df24c922be9 100644
--- a/arch/arm/boot/dts/qcom/qcom-apq8084-ifc6540.dts
+++ b/arch/arm/boot/dts/qcom/qcom-apq8084-ifc6540.dts
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "qcom-apq8084.dtsi"
-#include "qcom-pma8084.dtsi"
+#include "pma8084.dtsi"
 
 / {
 	model = "Qualcomm APQ8084/IFC6540";
diff --git a/arch/arm/boot/dts/qcom/qcom-apq8084-mtp.dts b/arch/arm/boot/dts/qcom/qcom-apq8084-mtp.dts
index c6b6680248a6..d4e6aee034af 100644
--- a/arch/arm/boot/dts/qcom/qcom-apq8084-mtp.dts
+++ b/arch/arm/boot/dts/qcom/qcom-apq8084-mtp.dts
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "qcom-apq8084.dtsi"
-#include "qcom-pma8084.dtsi"
+#include "pma8084.dtsi"
 
 / {
 	model = "Qualcomm APQ 8084-MTP";
diff --git a/arch/arm/boot/dts/qcom/qcom-ipq4019-ap.dk04.1.dtsi b/arch/arm/boot/dts/qcom/qcom-ipq4019-ap.dk04.1.dtsi
index 468ebc40d2ad..374af6dd360a 100644
--- a/arch/arm/boot/dts/qcom/qcom-ipq4019-ap.dk04.1.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-ipq4019-ap.dk04.1.dtsi
@@ -98,7 +98,7 @@
 			};
 		};
 
-		pci@40000000 {
+		pcie@40000000 {
 			status = "okay";
 			perst-gpios = <&tlmm 38 GPIO_ACTIVE_LOW>;
 		};
diff --git a/arch/arm/boot/dts/qcom/qcom-ipq4019.dtsi b/arch/arm/boot/dts/qcom/qcom-ipq4019.dtsi
index 9844e0b7cff9..f989bd741cd1 100644
--- a/arch/arm/boot/dts/qcom/qcom-ipq4019.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-ipq4019.dtsi
@@ -224,7 +224,7 @@
 		};
 
 		sdhci: mmc@7824900 {
-			compatible = "qcom,sdhci-msm-v4";
+			compatible = "qcom,ipq4019-sdhci", "qcom,sdhci-msm-v4";
 			reg = <0x7824900 0x11c>, <0x7824000 0x800>;
 			reg-names = "hc", "core";
 			interrupts = <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>;
@@ -417,7 +417,7 @@
 			reg = <0x4ab000 0x4>;
 		};
 
-		pcie0: pci@40000000 {
+		pcie0: pcie@40000000 {
 			compatible = "qcom,pcie-ipq4019";
 			reg = <0x40000000 0xf1d>,
 			      <0x40000f20 0xa8>,
diff --git a/arch/arm/boot/dts/qcom/qcom-ipq8064.dtsi b/arch/arm/boot/dts/qcom/qcom-ipq8064.dtsi
index 6198f42f6a9c..6a7f4dd0f775 100644
--- a/arch/arm/boot/dts/qcom/qcom-ipq8064.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-ipq8064.dtsi
@@ -366,7 +366,7 @@
 			};
 		};
 
-		qcom,ssbi@500000 {
+		ssbi@500000 {
 			compatible = "qcom,ssbi";
 			reg = <0x00500000 0x1000>;
 			qcom,controller-type = "pmic-arbiter";
@@ -1076,7 +1076,7 @@
 			status = "disabled";
 		};
 
-		pcie0: pci@1b500000 {
+		pcie0: pcie@1b500000 {
 			compatible = "qcom,pcie-ipq8064";
 			reg = <0x1b500000 0x1000
 			       0x1b502000 0x80
@@ -1127,7 +1127,7 @@
 			perst-gpios = <&qcom_pinmux 3 GPIO_ACTIVE_LOW>;
 		};
 
-		pcie1: pci@1b700000 {
+		pcie1: pcie@1b700000 {
 			compatible = "qcom,pcie-ipq8064";
 			reg = <0x1b700000 0x1000
 			       0x1b702000 0x80
@@ -1178,7 +1178,7 @@
 			perst-gpios = <&qcom_pinmux 48 GPIO_ACTIVE_LOW>;
 		};
 
-		pcie2: pci@1b900000 {
+		pcie2: pcie@1b900000 {
 			compatible = "qcom,pcie-ipq8064";
 			reg = <0x1b900000 0x1000
 			       0x1b902000 0x80
diff --git a/arch/arm/boot/dts/qcom/qcom-mdm9615-wp8548-mangoh-green.dts b/arch/arm/boot/dts/qcom/qcom-mdm9615-wp8548-mangoh-green.dts
index b269fdca1460..e3b4b93c3d38 100644
--- a/arch/arm/boot/dts/qcom/qcom-mdm9615-wp8548-mangoh-green.dts
+++ b/arch/arm/boot/dts/qcom/qcom-mdm9615-wp8548-mangoh-green.dts
@@ -6,11 +6,11 @@
  * Author : Neil Armstrong <narmstrong@baylibre.com>
  */
 
+#include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
+#include <dt-bindings/interrupt-controller/irq.h>
 
 #include "qcom-mdm9615-wp8548.dtsi"
-#include <dt-bindings/interrupt-controller/irq.h>
-#include <dt-bindings/gpio/gpio.h>
 
 / {
 	model = "MangOH Green with WP8548 Module";
diff --git a/arch/arm/boot/dts/qcom/qcom-mdm9615-wp8548.dtsi b/arch/arm/boot/dts/qcom/qcom-mdm9615-wp8548.dtsi
index 92c8003dac25..0dd52cac0e2e 100644
--- a/arch/arm/boot/dts/qcom/qcom-mdm9615-wp8548.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-mdm9615-wp8548.dtsi
@@ -7,6 +7,7 @@
  */
 
 #include "qcom-mdm9615.dtsi"
+#include "pm8018.dtsi"
 
 / {
 	model = "Sierra Wireless WP8548 Module";
@@ -76,7 +77,11 @@
 	};
 };
 
-&pmicgpio {
+&pm8018 {
+	interrupts-extended = <&intc GIC_PPI 226 IRQ_TYPE_LEVEL_HIGH>;
+};
+
+&pm8018_gpio {
 	usb_vbus_5v_pins: usb-vbus-5v-state {
 		pins = "gpio4";
 		function = "normal";
@@ -129,6 +134,142 @@
 	pinctrl-names = "default";
 };
 
+&rpm {
+	regulators {
+		compatible = "qcom,rpm-pm8018-regulators";
+
+		vin_lvs1-supply = <&pm8018_s3>;
+
+		vdd_l7-supply = <&pm8018_s4>;
+		vdd_l8-supply = <&pm8018_s3>;
+		vdd_l9_l10_l11_l12-supply = <&pm8018_s5>;
+
+		/* Buck SMPS */
+		pm8018_s1: s1 {
+			regulator-min-microvolt = <500000>;
+			regulator-max-microvolt = <1150000>;
+			qcom,switch-mode-frequency = <1600000>;
+			bias-pull-down;
+		};
+
+		pm8018_s2: s2 {
+			regulator-min-microvolt = <1225000>;
+			regulator-max-microvolt = <1300000>;
+			qcom,switch-mode-frequency = <1600000>;
+			bias-pull-down;
+		};
+
+		pm8018_s3: s3 {
+			regulator-always-on;
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			qcom,switch-mode-frequency = <1600000>;
+			bias-pull-down;
+		};
+
+		pm8018_s4: s4 {
+			regulator-min-microvolt = <2100000>;
+			regulator-max-microvolt = <2200000>;
+			qcom,switch-mode-frequency = <1600000>;
+			bias-pull-down;
+		};
+
+		pm8018_s5: s5 {
+			regulator-always-on;
+			regulator-min-microvolt = <1350000>;
+			regulator-max-microvolt = <1350000>;
+			qcom,switch-mode-frequency = <1600000>;
+			bias-pull-down;
+		};
+
+		/* PMOS LDO */
+		pm8018_l2: l2 {
+			regulator-always-on;
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			bias-pull-down;
+		};
+
+		pm8018_l3: l3 {
+			regulator-always-on;
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			bias-pull-down;
+		};
+
+		pm8018_l4: l4 {
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			bias-pull-down;
+		};
+
+		pm8018_l5: l5 {
+			regulator-min-microvolt = <2850000>;
+			regulator-max-microvolt = <2850000>;
+			bias-pull-down;
+		};
+
+		pm8018_l6: l6 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2850000>;
+			bias-pull-down;
+		};
+
+		pm8018_l7: l7 {
+			regulator-min-microvolt = <1850000>;
+			regulator-max-microvolt = <1900000>;
+			bias-pull-down;
+		};
+
+		pm8018_l8: l8 {
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			bias-pull-down;
+		};
+
+		pm8018_l9: l9 {
+			regulator-min-microvolt = <750000>;
+			regulator-max-microvolt = <1150000>;
+			bias-pull-down;
+		};
+
+		pm8018_l10: l10 {
+			regulator-min-microvolt = <1050000>;
+			regulator-max-microvolt = <1050000>;
+			bias-pull-down;
+		};
+
+		pm8018_l11: l11 {
+			regulator-min-microvolt = <1050000>;
+			regulator-max-microvolt = <1050000>;
+			bias-pull-down;
+		};
+
+		pm8018_l12: l12 {
+			regulator-min-microvolt = <1050000>;
+			regulator-max-microvolt = <1050000>;
+			bias-pull-down;
+		};
+
+		pm8018_l13: l13 {
+			regulator-min-microvolt = <1850000>;
+			regulator-max-microvolt = <2950000>;
+			bias-pull-down;
+		};
+
+		pm8018_l14: l14 {
+			regulator-min-microvolt = <2850000>;
+			regulator-max-microvolt = <2850000>;
+			bias-pull-down;
+		};
+
+		/* Low Voltage Switch */
+		pm8018_lvs1: lvs1 {
+			bias-pull-down;
+		};
+	};
+};
+
 &sdcc1 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/qcom/qcom-mdm9615.dtsi b/arch/arm/boot/dts/qcom/qcom-mdm9615.dtsi
index 63e21aa23642..34c60994d026 100644
--- a/arch/arm/boot/dts/qcom/qcom-mdm9615.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-mdm9615.dtsi
@@ -256,57 +256,10 @@
 			};
 		};
 
-		qcom,ssbi@500000 {
+		ssbi: ssbi@500000 {
 			compatible = "qcom,ssbi";
 			reg = <0x500000 0x1000>;
 			qcom,controller-type = "pmic-arbiter";
-
-			pmicintc: pmic {
-				compatible = "qcom,pm8018", "qcom,pm8921";
-				interrupts = <GIC_PPI 226 IRQ_TYPE_LEVEL_HIGH>;
-				#interrupt-cells = <2>;
-				interrupt-controller;
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				pwrkey@1c {
-					compatible = "qcom,pm8018-pwrkey", "qcom,pm8921-pwrkey";
-					reg = <0x1c>;
-					interrupt-parent = <&pmicintc>;
-					interrupts = <50 IRQ_TYPE_EDGE_RISING>,
-						     <51 IRQ_TYPE_EDGE_RISING>;
-					debounce = <15625>;
-					pull-up;
-				};
-
-				pmicmpp: mpps@50 {
-					compatible = "qcom,pm8018-mpp", "qcom,ssbi-mpp";
-					interrupt-controller;
-					#interrupt-cells = <2>;
-					reg = <0x50>;
-					gpio-controller;
-					#gpio-cells = <2>;
-					gpio-ranges = <&pmicmpp 0 0 6>;
-				};
-
-				rtc@11d {
-					compatible = "qcom,pm8018-rtc", "qcom,pm8921-rtc";
-					interrupt-parent = <&pmicintc>;
-					interrupts = <39 IRQ_TYPE_EDGE_RISING>;
-					reg = <0x11d>;
-					allow-set-time;
-				};
-
-				pmicgpio: gpio@150 {
-					compatible = "qcom,pm8018-gpio", "qcom,ssbi-gpio";
-					reg = <0x150>;
-					interrupt-controller;
-					#interrupt-cells = <2>;
-					gpio-controller;
-					gpio-ranges = <&pmicgpio 0 0 6>;
-					#gpio-cells = <2>;
-				};
-			};
 		};
 
 		sdcc1bam: dma-controller@12182000 {
@@ -383,140 +336,6 @@
 				     <GIC_SPI 21 IRQ_TYPE_EDGE_RISING>,
 				     <GIC_SPI 22 IRQ_TYPE_EDGE_RISING>;
 			interrupt-names = "ack", "err", "wakeup";
-
-			regulators {
-				compatible = "qcom,rpm-pm8018-regulators";
-
-				vin_lvs1-supply = <&pm8018_s3>;
-
-				vdd_l7-supply = <&pm8018_s4>;
-				vdd_l8-supply = <&pm8018_s3>;
-				vdd_l9_l10_l11_l12-supply = <&pm8018_s5>;
-
-				/* Buck SMPS */
-				pm8018_s1: s1 {
-					regulator-min-microvolt = <500000>;
-					regulator-max-microvolt = <1150000>;
-					qcom,switch-mode-frequency = <1600000>;
-					bias-pull-down;
-				};
-
-				pm8018_s2: s2 {
-					regulator-min-microvolt = <1225000>;
-					regulator-max-microvolt = <1300000>;
-					qcom,switch-mode-frequency = <1600000>;
-					bias-pull-down;
-				};
-
-				pm8018_s3: s3 {
-					regulator-always-on;
-					regulator-min-microvolt = <1800000>;
-					regulator-max-microvolt = <1800000>;
-					qcom,switch-mode-frequency = <1600000>;
-					bias-pull-down;
-				};
-
-				pm8018_s4: s4 {
-					regulator-min-microvolt = <2100000>;
-					regulator-max-microvolt = <2200000>;
-					qcom,switch-mode-frequency = <1600000>;
-					bias-pull-down;
-				};
-
-				pm8018_s5: s5 {
-					regulator-always-on;
-					regulator-min-microvolt = <1350000>;
-					regulator-max-microvolt = <1350000>;
-					qcom,switch-mode-frequency = <1600000>;
-					bias-pull-down;
-				};
-
-				/* PMOS LDO */
-				pm8018_l2: l2 {
-					regulator-always-on;
-					regulator-min-microvolt = <1800000>;
-					regulator-max-microvolt = <1800000>;
-					bias-pull-down;
-				};
-
-				pm8018_l3: l3 {
-					regulator-always-on;
-					regulator-min-microvolt = <1800000>;
-					regulator-max-microvolt = <1800000>;
-					bias-pull-down;
-				};
-
-				pm8018_l4: l4 {
-					regulator-min-microvolt = <3300000>;
-					regulator-max-microvolt = <3300000>;
-					bias-pull-down;
-				};
-
-				pm8018_l5: l5 {
-					regulator-min-microvolt = <2850000>;
-					regulator-max-microvolt = <2850000>;
-					bias-pull-down;
-				};
-
-				pm8018_l6: l6 {
-					regulator-min-microvolt = <1800000>;
-					regulator-max-microvolt = <2850000>;
-					bias-pull-down;
-				};
-
-				pm8018_l7: l7 {
-					regulator-min-microvolt = <1850000>;
-					regulator-max-microvolt = <1900000>;
-					bias-pull-down;
-				};
-
-				pm8018_l8: l8 {
-					regulator-min-microvolt = <1200000>;
-					regulator-max-microvolt = <1200000>;
-					bias-pull-down;
-				};
-
-				pm8018_l9: l9 {
-					regulator-min-microvolt = <750000>;
-					regulator-max-microvolt = <1150000>;
-					bias-pull-down;
-				};
-
-				pm8018_l10: l10 {
-					regulator-min-microvolt = <1050000>;
-					regulator-max-microvolt = <1050000>;
-					bias-pull-down;
-				};
-
-				pm8018_l11: l11 {
-					regulator-min-microvolt = <1050000>;
-					regulator-max-microvolt = <1050000>;
-					bias-pull-down;
-				};
-
-				pm8018_l12: l12 {
-					regulator-min-microvolt = <1050000>;
-					regulator-max-microvolt = <1050000>;
-					bias-pull-down;
-				};
-
-				pm8018_l13: l13 {
-					regulator-min-microvolt = <1850000>;
-					regulator-max-microvolt = <2950000>;
-					bias-pull-down;
-				};
-
-				pm8018_l14: l14 {
-					regulator-min-microvolt = <2850000>;
-					regulator-max-microvolt = <2850000>;
-					bias-pull-down;
-				};
-
-				/* Low Voltage Switch */
-				pm8018_lvs1: lvs1 {
-					bias-pull-down;
-				};
-			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8226-microsoft-common.dtsi b/arch/arm/boot/dts/qcom/qcom-msm8226-microsoft-common.dtsi
new file mode 100644
index 000000000000..525d8c608b06
--- /dev/null
+++ b/arch/arm/boot/dts/qcom/qcom-msm8226-microsoft-common.dtsi
@@ -0,0 +1,327 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * Common Board Device Tree for Microsoft MSM8x26-based Lumias
+ *
+ * Copyright (c) 2023, Jack Matthews <jm5112356@gmail.com>
+ * Copyright (c) 2023, Ivaylo Ivanov <ivo.ivanov.ivanov1@gmail.com>
+ * Copyright (c) 2023, Dominik Kobinski <dominikkobinski314@gmail.com>
+ * Copyright (c) 2023, Rayyan Ansari <rayyan@ansari.sh>
+ */
+
+#include "qcom-msm8226.dtsi"
+#include "pm8226.dtsi"
+#include <dt-bindings/input/input.h>
+
+/*
+ * Delete all generic (msm8226.dtsi) reserved
+ * memory mappings which are different on these devices.
+ */
+/delete-node/ &smem_region;
+
+/ {
+	aliases {
+		mmc0 = &sdhc_1; /* eMMC */
+		mmc1 = &sdhc_2; /* microSD */
+		display0 = &framebuffer;
+	};
+
+	chosen {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		stdout-path = "display0";
+
+		framebuffer: framebuffer@3200000 {
+			compatible = "simple-framebuffer";
+			reg = <0x3200000 0x800000>;
+			format = "a8r8g8b8";
+			width = <720>;
+			height = <1280>;
+			stride = <(720 * 4)>;
+
+			clocks = <&mmcc MDSS_AHB_CLK>,
+				 <&mmcc MDSS_AXI_CLK>,
+				 <&mmcc MDSS_BYTE0_CLK>,
+				 <&mmcc MDSS_MDP_CLK>,
+				 <&mmcc MDSS_PCLK0_CLK>,
+				 <&mmcc MDSS_VSYNC_CLK>;
+			power-domains = <&mmcc MDSS_GDSC>;
+		};
+	};
+
+	gpio_keys: gpio-keys {
+		compatible = "gpio-keys";
+
+		pinctrl-0 = <&gpio_keys_default>;
+		pinctrl-names = "default";
+
+		label = "GPIO Buttons";
+
+		key-volume-up {
+			label = "Volume Up";
+			gpios = <&tlmm 106 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_VOLUMEUP>;
+		};
+	};
+
+	/*
+	 * This device being a WP platform has a different
+	 * memory layout than other Android based devices.
+	 * This smem memory region is directly copied from
+	 * the original UEFI firmware.
+	 */
+	reserved-memory {
+		display_reserved: framebuffer@3200000 {
+			reg = <0x03200000 0x800000>;
+			no-map;
+		};
+
+		smem_region: smem@fa00000 {
+			reg = <0x0fa00000 0x100000>;
+			no-map;
+		};
+	};
+};
+
+&blsp1_i2c5 {
+	status = "okay";
+
+	touchscreen: touchscreen@4b {
+		compatible = "syna,rmi4-i2c";
+		reg = <0x4b>;
+
+		interrupts-extended = <&tlmm 17 IRQ_TYPE_EDGE_FALLING>;
+		vdd-supply = <&pm8226_l15>;
+		vio-supply = <&pm8226_l6>;
+
+		pinctrl-0 = <&touchscreen_default>;
+		pinctrl-names = "default";
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		rmi4-f01@1 {
+			reg = <0x01>;
+			syna,nosleep-mode = <1>;
+		};
+
+		rmi4-f11@11 {
+			reg = <0x11>;
+			syna,sensor-type = <1>;
+		};
+	};
+};
+
+&blsp1_uart3 {
+	status = "okay";
+};
+
+&pm8226_resin {
+	linux,code = <KEY_VOLUMEDOWN>;
+	status = "okay";
+};
+
+&pm8226_vib {
+	status = "okay";
+};
+
+&rpm_requests {
+	regulators {
+		compatible = "qcom,rpm-pm8226-regulators";
+
+		/* These values were taken from the original firmware DSDT */
+		pm8226_s1: s1 {
+			regulator-min-microvolt = <1050000>;
+			regulator-max-microvolt = <1050000>;
+		};
+
+		pm8226_s3: s3 {
+			regulator-min-microvolt = <1300000>;
+			regulator-max-microvolt = <1300000>;
+		};
+
+		pm8226_s4: s4 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2100000>;
+		};
+
+		pm8226_s5: s5 {
+			regulator-min-microvolt = <1150000>;
+			regulator-max-microvolt = <1150000>;
+		};
+
+		pm8226_l3: l3 {
+			regulator-min-microvolt = <750000>;
+			regulator-max-microvolt = <1150000>;
+		};
+
+		pm8226_l4: l4 {
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+		};
+
+		pm8226_l5: l5 {
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+		};
+
+		pm8226_l6: l6 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+		};
+
+		pm8226_l7: l7 {
+			regulator-min-microvolt = <1850000>;
+			regulator-max-microvolt = <1850000>;
+		};
+
+		pm8226_l8: l8 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-always-on;
+		};
+
+		pm8226_l9: l9 {
+			regulator-min-microvolt = <2050000>;
+			regulator-max-microvolt = <2050000>;
+		};
+
+		pm8226_l10: l10 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+		};
+
+		pm8226_l12: l12 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+		};
+
+		pm8226_l14: l14 {
+			regulator-min-microvolt = <2750000>;
+			regulator-max-microvolt = <2750000>;
+		};
+
+		pm8226_l15: l15 {
+			regulator-min-microvolt = <2850000>;
+			regulator-max-microvolt = <2850000>;
+		};
+
+		pm8226_l16: l16 {
+			regulator-min-microvolt = <3000000>;
+			regulator-max-microvolt = <3000000>;
+		};
+
+		pm8226_l17: l17 {
+			regulator-min-microvolt = <2950000>;
+			regulator-max-microvolt = <2950000>;
+			regulator-system-load = <200000>;
+			regulator-allow-set-load;
+		};
+
+		pm8226_l18: l18 {
+			regulator-min-microvolt = <2950000>;
+			regulator-max-microvolt = <2950000>;
+			regulator-system-load = <200000>;
+			regulator-allow-set-load;
+		};
+
+		pm8226_l19: l19 {
+			regulator-min-microvolt = <2850000>;
+			regulator-max-microvolt = <2850000>;
+		};
+
+		pm8226_l20: l20 {
+			regulator-min-microvolt = <3075000>;
+			regulator-max-microvolt = <3075000>;
+		};
+
+		pm8226_l21: l21 {
+			regulator-min-microvolt = <1850000>;
+			regulator-max-microvolt = <2950000>;
+		};
+
+		pm8226_l22: l22 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+		};
+
+		pm8226_l23: l23 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+		};
+
+		pm8226_l24: l24 {
+			regulator-min-microvolt = <1300000>;
+			regulator-max-microvolt = <1300000>;
+		};
+
+		pm8226_l25: l25 {
+			regulator-min-microvolt = <1775000>;
+			regulator-max-microvolt = <2075000>;
+		};
+
+		pm8226_l27: l27 {
+			regulator-min-microvolt = <2050000>;
+			regulator-max-microvolt = <2050000>;
+		};
+
+		pm8226_l28: l28 {
+			regulator-min-microvolt = <2000000>;
+			regulator-max-microvolt = <3000000>;
+		};
+	};
+};
+
+&sdhc_1 {
+	vmmc-supply = <&pm8226_l17>;
+	vqmmc-supply = <&pm8226_l6>;
+
+	status = "okay";
+};
+
+&sdhc_2 {
+	vmmc-supply = <&pm8226_l18>;
+	vqmmc-supply = <&pm8226_l21>;
+
+	status = "okay";
+};
+
+&usb {
+	extcon = <&smbb>;
+	dr_mode = "peripheral";
+
+	status = "okay";
+};
+
+&usb_hs_phy {
+	extcon = <&smbb>;
+	v1p8-supply = <&pm8226_l10>;
+	v3p3-supply = <&pm8226_l20>;
+};
+
+&tlmm {
+	gpio_keys_default: gpio-keys-default-state {
+		pins = "gpio106", "gpio107", "gpio108";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-pull-up;
+	};
+
+	touchscreen_default: touchscreen-default-state {
+		irq-pins {
+			pins = "gpio17";
+			function = "gpio";
+			drive-strength = <8>;
+			bias-pull-up;
+		};
+
+		reset-pins {
+			pins = "gpio16";
+			function = "gpio";
+			drive-strength = <8>;
+			bias-disable;
+			output-high;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8226-microsoft-dempsey.dts b/arch/arm/boot/dts/qcom/qcom-msm8226-microsoft-dempsey.dts
new file mode 100644
index 000000000000..2c664b5934ec
--- /dev/null
+++ b/arch/arm/boot/dts/qcom/qcom-msm8226-microsoft-dempsey.dts
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * Copyright (c) 2023, Jack Matthews <jm5112356@gmail.com>
+ * Copyright (c) 2023, Ivaylo Ivanov <ivo.ivanov.ivanov1@gmail.com>
+ * Copyright (c) 2023, Dominik Kobinski <dominikkobinski314@gmail.com>
+ * Copyright (c) 2023, Rayyan Ansari <rayyan@ansari.sh>
+ */
+
+/dts-v1/;
+
+#include "qcom-msm8226-microsoft-common.dtsi"
+
+/ {
+	model = "Microsoft Lumia 640";
+	compatible = "microsoft,dempsey", "qcom,msm8226";
+	chassis-type = "handset";
+};
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8226-microsoft-makepeace.dts b/arch/arm/boot/dts/qcom/qcom-msm8226-microsoft-makepeace.dts
new file mode 100644
index 000000000000..731c5c375678
--- /dev/null
+++ b/arch/arm/boot/dts/qcom/qcom-msm8226-microsoft-makepeace.dts
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * Copyright (c) 2023, Jack Matthews <jm5112356@gmail.com>
+ * Copyright (c) 2023, Ivaylo Ivanov <ivo.ivanov.ivanov1@gmail.com>
+ * Copyright (c) 2023, Dominik Kobinski <dominikkobinski314@gmail.com>
+ * Copyright (c) 2023, Rayyan Ansari <rayyan@ansari.sh>
+ */
+
+/dts-v1/;
+
+#include "qcom-msm8226-microsoft-common.dtsi"
+
+/ {
+	model = "Microsoft Lumia 640 XL";
+	compatible = "microsoft,makepeace", "qcom,msm8226";
+	chassis-type = "handset";
+};
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8226-microsoft-moneypenny.dts b/arch/arm/boot/dts/qcom/qcom-msm8226-microsoft-moneypenny.dts
new file mode 100644
index 000000000000..992b7115b5f8
--- /dev/null
+++ b/arch/arm/boot/dts/qcom/qcom-msm8226-microsoft-moneypenny.dts
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * Copyright (c) 2023, Jack Matthews <jm5112356@gmail.com>
+ * Copyright (c) 2023, Ivaylo Ivanov <ivo.ivanov.ivanov1@gmail.com>
+ * Copyright (c) 2023, Dominik Kobinski <dominikkobinski314@gmail.com>
+ * Copyright (c) 2023, Rayyan Ansari <rayyan@ansari.sh>
+ */
+
+/dts-v1/;
+
+#include "qcom-msm8226-microsoft-common.dtsi"
+
+/ {
+	model = "Nokia Lumia 630";
+	compatible = "microsoft,moneypenny", "qcom,msm8226";
+	chassis-type = "handset";
+};
+
+&framebuffer {
+	width = <480>;
+	height = <854>;
+	stride = <(480 * 4)>;
+};
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8226.dtsi b/arch/arm/boot/dts/qcom/qcom-msm8226.dtsi
index 97a377b5a0ec..b492c95e5d30 100644
--- a/arch/arm/boot/dts/qcom/qcom-msm8226.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-msm8226.dtsi
@@ -442,8 +442,8 @@
 				 <&gcc GPLL0_VOTE>,
 				 <&gcc GPLL1_VOTE>,
 				 <&rpmcc RPM_SMD_GFX3D_CLK_SRC>,
-				 <0>,
-				 <0>;
+				 <&mdss_dsi0_phy 1>,
+				 <&mdss_dsi0_phy 0>;
 			clock-names = "xo",
 				      "mmss_gpll0_vote",
 				      "gpll0_vote",
@@ -875,8 +875,8 @@
 				offset = <0x65c>;
 
 				mode-bootloader = <0x77665500>;
-				mode-normal     = <0x77665501>;
-				mode-recovery   = <0x77665502>;
+				mode-normal = <0x77665501>;
+				mode-recovery = <0x77665502>;
 			};
 		};
 
@@ -1006,6 +1006,46 @@
 					      "ref";
 			};
 		};
+
+		gpu: adreno@fdb00000 {
+			compatible = "qcom,adreno-305.18", "qcom,adreno";
+			reg = <0xfdb00000 0x10000>;
+			reg-names = "kgsl_3d0_reg_memory";
+
+			interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "kgsl_3d0_irq";
+
+			clocks = <&mmcc OXILI_GFX3D_CLK>,
+				 <&mmcc OXILICX_AHB_CLK>,
+				 <&mmcc OXILICX_AXI_CLK>;
+			clock-names = "core", "iface", "mem_iface";
+
+			sram = <&gmu_sram>;
+			power-domains = <&mmcc OXILICX_GDSC>;
+			operating-points-v2 = <&gpu_opp_table>;
+
+			status = "disabled";
+
+			gpu_opp_table: opp-table {
+				compatible = "operating-points-v2";
+
+				opp-450000000 {
+					opp-hz = /bits/ 64 <450000000>;
+				};
+
+				opp-320000000 {
+					opp-hz = /bits/ 64 <320000000>;
+				};
+
+				opp-200000000 {
+					opp-hz = /bits/ 64 <200000000>;
+				};
+
+				opp-19000000 {
+					opp-hz = /bits/ 64 <19000000>;
+				};
+			};
+		};
 	};
 
 	thermal-zones {
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8660-surf.dts b/arch/arm/boot/dts/qcom/qcom-msm8660-surf.dts
index be18f1be29a1..69fe651f564d 100644
--- a/arch/arm/boot/dts/qcom/qcom-msm8660-surf.dts
+++ b/arch/arm/boot/dts/qcom/qcom-msm8660-surf.dts
@@ -2,6 +2,7 @@
 #include <dt-bindings/input/input.h>
 
 #include "qcom-msm8660.dtsi"
+#include "pm8058.dtsi"
 
 / {
 	model = "Qualcomm MSM8660 SURF";
@@ -35,30 +36,42 @@
 };
 
 &pm8058 {
-	keypad@148 {
-		linux,keymap = <
-			MATRIX_KEY(0, 0, KEY_FN_F1)
-			MATRIX_KEY(0, 1, KEY_UP)
-			MATRIX_KEY(0, 2, KEY_LEFT)
-			MATRIX_KEY(0, 3, KEY_VOLUMEUP)
-			MATRIX_KEY(1, 0, KEY_FN_F2)
-			MATRIX_KEY(1, 1, KEY_RIGHT)
-			MATRIX_KEY(1, 2, KEY_DOWN)
-			MATRIX_KEY(1, 3, KEY_VOLUMEDOWN)
-			MATRIX_KEY(2, 3, KEY_ENTER)
-			MATRIX_KEY(4, 0, KEY_CAMERA_FOCUS)
-			MATRIX_KEY(4, 1, KEY_UP)
-			MATRIX_KEY(4, 2, KEY_LEFT)
-			MATRIX_KEY(4, 3, KEY_HOME)
-			MATRIX_KEY(4, 4, KEY_FN_F3)
-			MATRIX_KEY(5, 0, KEY_CAMERA)
-			MATRIX_KEY(5, 1, KEY_RIGHT)
-			MATRIX_KEY(5, 2, KEY_DOWN)
-			MATRIX_KEY(5, 3, KEY_BACK)
-			MATRIX_KEY(5, 4, KEY_MENU)
-			>;
-		keypad,num-rows = <6>;
-		keypad,num-columns = <5>;
+	interrupts-extended = <&tlmm 88 IRQ_TYPE_LEVEL_LOW>;
+};
+
+&pm8058_keypad {
+	linux,keymap = <
+		MATRIX_KEY(0, 0, KEY_FN_F1)
+		MATRIX_KEY(0, 1, KEY_UP)
+		MATRIX_KEY(0, 2, KEY_LEFT)
+		MATRIX_KEY(0, 3, KEY_VOLUMEUP)
+		MATRIX_KEY(1, 0, KEY_FN_F2)
+		MATRIX_KEY(1, 1, KEY_RIGHT)
+		MATRIX_KEY(1, 2, KEY_DOWN)
+		MATRIX_KEY(1, 3, KEY_VOLUMEDOWN)
+		MATRIX_KEY(2, 3, KEY_ENTER)
+		MATRIX_KEY(4, 0, KEY_CAMERA_FOCUS)
+		MATRIX_KEY(4, 1, KEY_UP)
+		MATRIX_KEY(4, 2, KEY_LEFT)
+		MATRIX_KEY(4, 3, KEY_HOME)
+		MATRIX_KEY(4, 4, KEY_FN_F3)
+		MATRIX_KEY(5, 0, KEY_CAMERA)
+		MATRIX_KEY(5, 1, KEY_RIGHT)
+		MATRIX_KEY(5, 2, KEY_DOWN)
+		MATRIX_KEY(5, 3, KEY_BACK)
+		MATRIX_KEY(5, 4, KEY_MENU)
+		>;
+	keypad,num-rows = <6>;
+	keypad,num-columns = <5>;
+};
+
+&rpm {
+	regulators-0 {
+		compatible = "qcom,rpm-pm8901-regulators";
+	};
+
+	regulators-1 {
+		compatible = "qcom,rpm-pm8058-regulators";
 	};
 };
 
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8660.dtsi b/arch/arm/boot/dts/qcom/qcom-msm8660.dtsi
index 78023ed2fdf7..a7c245b9c8f9 100644
--- a/arch/arm/boot/dts/qcom/qcom-msm8660.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-msm8660.dtsi
@@ -73,22 +73,6 @@
 		};
 	};
 
-	/*
-	 * These channels from the ADC are simply hardware monitors.
-	 * That is why the ADC is referred to as "HKADC" - HouseKeeping
-	 * ADC.
-	 */
-	iio-hwmon {
-		compatible = "iio-hwmon";
-		io-channels = <&xoadc 0x00 0x01>, /* Battery */
-			    <&xoadc 0x00 0x02>, /* DC in (charger) */
-			    <&xoadc 0x00 0x04>, /* VPH the main system voltage */
-			    <&xoadc 0x00 0x0b>, /* Die temperature */
-			    <&xoadc 0x00 0x0c>, /* Reference voltage 1.25V */
-			    <&xoadc 0x00 0x0d>, /* Reference voltage 0.625V */
-			    <&xoadc 0x00 0x0e>; /* Reference voltage 0.325V */
-	};
-
 	soc: soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -334,143 +318,10 @@
 			status = "disabled";
 		};
 
-		ssbi@500000 {
+		ssbi: ssbi@500000 {
 			compatible = "qcom,ssbi";
 			reg = <0x500000 0x1000>;
 			qcom,controller-type = "pmic-arbiter";
-
-			pm8058: pmic {
-				compatible = "qcom,pm8058";
-				interrupt-parent = <&tlmm>;
-				interrupts = <88 8>;
-				#interrupt-cells = <2>;
-				interrupt-controller;
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				pm8058_gpio: gpio@150 {
-					compatible = "qcom,pm8058-gpio",
-						     "qcom,ssbi-gpio";
-					reg = <0x150>;
-					interrupt-controller;
-					#interrupt-cells = <2>;
-					gpio-controller;
-					gpio-ranges = <&pm8058_gpio 0 0 44>;
-					#gpio-cells = <2>;
-
-				};
-
-				pm8058_mpps: mpps@50 {
-					compatible = "qcom,pm8058-mpp",
-						     "qcom,ssbi-mpp";
-					reg = <0x50>;
-					gpio-controller;
-					#gpio-cells = <2>;
-					gpio-ranges = <&pm8058_mpps 0 0 12>;
-					interrupt-controller;
-					#interrupt-cells = <2>;
-				};
-
-				pwrkey@1c {
-					compatible = "qcom,pm8058-pwrkey";
-					reg = <0x1c>;
-					interrupt-parent = <&pm8058>;
-					interrupts = <50 1>, <51 1>;
-					debounce = <15625>;
-					pull-up;
-				};
-
-				pm8058_keypad: keypad@148 {
-					compatible = "qcom,pm8058-keypad";
-					reg = <0x148>;
-					interrupt-parent = <&pm8058>;
-					interrupts = <74 1>, <75 1>;
-					debounce = <15>;
-					scan-delay = <32>;
-					row-hold = <91500>;
-				};
-
-				xoadc: xoadc@197 {
-					compatible = "qcom,pm8058-adc";
-					reg = <0x197>;
-					interrupts-extended = <&pm8058 76 IRQ_TYPE_EDGE_RISING>;
-					#address-cells = <2>;
-					#size-cells = <0>;
-					#io-channel-cells = <2>;
-
-					vcoin: adc-channel@0 {
-						reg = <0x00 0x00>;
-					};
-					vbat: adc-channel@1 {
-						reg = <0x00 0x01>;
-					};
-					dcin: adc-channel@2 {
-						reg = <0x00 0x02>;
-					};
-					ichg: adc-channel@3 {
-						reg = <0x00 0x03>;
-					};
-					vph_pwr: adc-channel@4 {
-						reg = <0x00 0x04>;
-					};
-					usb_vbus: adc-channel@a {
-						reg = <0x00 0x0a>;
-					};
-					die_temp: adc-channel@b {
-						reg = <0x00 0x0b>;
-					};
-					ref_625mv: adc-channel@c {
-						reg = <0x00 0x0c>;
-					};
-					ref_1250mv: adc-channel@d {
-						reg = <0x00 0x0d>;
-					};
-					ref_325mv: adc-channel@e {
-						reg = <0x00 0x0e>;
-					};
-					ref_muxoff: adc-channel@f {
-						reg = <0x00 0x0f>;
-					};
-				};
-
-				rtc@1e8 {
-					compatible = "qcom,pm8058-rtc";
-					reg = <0x1e8>;
-					interrupt-parent = <&pm8058>;
-					interrupts = <39 1>;
-					allow-set-time;
-				};
-
-				vibrator@4a {
-					compatible = "qcom,pm8058-vib";
-					reg = <0x4a>;
-				};
-
-				pm8058_led48: led@48 {
-					compatible = "qcom,pm8058-keypad-led";
-					reg = <0x48>;
-					status = "disabled";
-				};
-
-				pm8058_led131: led@131 {
-					compatible = "qcom,pm8058-led";
-					reg = <0x131>;
-					status = "disabled";
-				};
-
-				pm8058_led132: led@132 {
-					compatible = "qcom,pm8058-led";
-					reg = <0x132>;
-					status = "disabled";
-				};
-
-				pm8058_led133: led@133 {
-					compatible = "qcom,pm8058-led";
-					reg = <0x133>;
-					status = "disabled";
-				};
-
-			};
 		};
 
 		l2cc: clock-controller@2082000 {
@@ -496,72 +347,6 @@
 				clocks = <&pxo_board>;
 				clock-names = "pxo";
 			};
-
-			regulators-0 {
-				compatible = "qcom,rpm-pm8901-regulators";
-
-				pm8901_l0: l0 {};
-				pm8901_l1: l1 {};
-				pm8901_l2: l2 {};
-				pm8901_l3: l3 {};
-				pm8901_l4: l4 {};
-				pm8901_l5: l5 {};
-				pm8901_l6: l6 {};
-
-				/* S0 and S1 Handled as SAW regulators by SPM */
-				pm8901_s2: s2 {};
-				pm8901_s3: s3 {};
-				pm8901_s4: s4 {};
-
-				pm8901_lvs0: lvs0 {};
-				pm8901_lvs1: lvs1 {};
-				pm8901_lvs2: lvs2 {};
-				pm8901_lvs3: lvs3 {};
-
-				pm8901_mvs: mvs {};
-			};
-
-			regulators-1 {
-				compatible = "qcom,rpm-pm8058-regulators";
-
-				pm8058_l0: l0 {};
-				pm8058_l1: l1 {};
-				pm8058_l2: l2 {};
-				pm8058_l3: l3 {};
-				pm8058_l4: l4 {};
-				pm8058_l5: l5 {};
-				pm8058_l6: l6 {};
-				pm8058_l7: l7 {};
-				pm8058_l8: l8 {};
-				pm8058_l9: l9 {};
-				pm8058_l10: l10 {};
-				pm8058_l11: l11 {};
-				pm8058_l12: l12 {};
-				pm8058_l13: l13 {};
-				pm8058_l14: l14 {};
-				pm8058_l15: l15 {};
-				pm8058_l16: l16 {};
-				pm8058_l17: l17 {};
-				pm8058_l18: l18 {};
-				pm8058_l19: l19 {};
-				pm8058_l20: l20 {};
-				pm8058_l21: l21 {};
-				pm8058_l22: l22 {};
-				pm8058_l23: l23 {};
-				pm8058_l24: l24 {};
-				pm8058_l25: l25 {};
-
-				pm8058_s0: s0 {};
-				pm8058_s1: s1 {};
-				pm8058_s2: s2 {};
-				pm8058_s3: s3 {};
-				pm8058_s4: s4 {};
-
-				pm8058_lvs0: lvs0 {};
-				pm8058_lvs1: lvs1 {};
-
-				pm8058_ncp: ncp {};
-			};
 		};
 
 		amba {
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8926-htc-memul.dts b/arch/arm/boot/dts/qcom/qcom-msm8926-htc-memul.dts
new file mode 100644
index 000000000000..ed328b24335f
--- /dev/null
+++ b/arch/arm/boot/dts/qcom/qcom-msm8926-htc-memul.dts
@@ -0,0 +1,372 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * Copyright (c) 2023, Luca Weiss <luca@z3ntu.xyz>
+ */
+
+/dts-v1/;
+
+#include "qcom-msm8226.dtsi"
+#include "pm8226.dtsi"
+
+/delete-node/ &adsp_region;
+/delete-node/ &smem_region;
+
+/ {
+	model = "HTC One Mini 2";
+	compatible = "htc,memul", "qcom,msm8926", "qcom,msm8226";
+	chassis-type = "handset";
+
+	aliases {
+		mmc1 = &sdhc_2; /* SDC2 SD card slot */
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		key-power {
+			label = "Power";
+			gpios = <&tlmm 106 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_POWER>;
+			debounce-interval = <15>;
+		};
+
+		key-volume-down {
+			label = "Volume Down";
+			gpios = <&tlmm 107 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_VOLUMEDOWN>;
+			debounce-interval = <15>;
+		};
+
+		key-volume-up {
+			label = "Volume Up";
+			gpios = <&tlmm 108 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_VOLUMEUP>;
+			debounce-interval = <15>;
+		};
+	};
+
+	reserved-memory {
+		unknown@5b00000 {
+			reg = <0x05b00000 0x200000>;
+			no-map;
+		};
+
+		unknown@7500000 {
+			reg = <0x07500000 0xb00000>;
+			no-map;
+		};
+
+		mpss_region: mpss@8000000 {
+			reg = <0x08000000 0x4f00000>;
+			no-map;
+		};
+
+		unknown@cf00000 {
+			reg = <0x0cf00000 0x200000>;
+			no-map;
+		};
+
+		mba_region: mba@d100000 {
+			reg = <0x0d100000 0x3a000>;
+			no-map;
+		};
+
+		unknown@d13a000 {
+			reg = <0x0d13a000 0xc6000>;
+			no-map;
+		};
+
+		wcnss_region: wcnss@d200000 {
+			reg = <0x0d200000 0x650000>;
+			no-map;
+		};
+
+		unknown@d850000 {
+			reg = <0x0d850000 0x3b0000>;
+			no-map;
+		};
+
+		adsp_region: adsp@dc00000 {
+			reg = <0x0dc00000 0x1400000>;
+			no-map;
+		};
+
+		unknown@f000000 {
+			reg = <0x0f000000 0x500000>;
+			no-map;
+		};
+
+		venus_region: venus@f500000 {
+			reg = <0x0f500000 0x500000>;
+			no-map;
+		};
+
+		smem_region: smem@fa00000 {
+			reg = <0x0fa00000 0x100000>;
+			no-map;
+		};
+
+		unknown@fb00000 {
+			reg = <0x0fb00000 0x1b00000>;
+			no-map;
+		};
+	};
+};
+
+&adsp {
+	firmware-name = "qcom/msm8926/memul/adsp.mbn";
+	status = "okay";
+};
+
+&blsp1_i2c2 {
+	status = "okay";
+
+	magnetometer@d {
+		compatible = "asahi-kasei,ak8963";
+		reg = <0x0d>;
+		interrupts-extended = <&tlmm 66 IRQ_TYPE_EDGE_RISING>;
+		vdd-supply = <&pm8226_l19>;
+		vid-supply = <&pm8226_l28>;
+	};
+
+	accelerometer@18 {
+		compatible = "bosch,bma250e";
+		reg = <0x18>;
+		interrupts-extended = <&tlmm 63 IRQ_TYPE_EDGE_RISING>;
+		vdd-supply = <&pm8226_l19>;
+		vddio-supply = <&pm8226_l28>;
+	};
+};
+
+&blsp1_i2c4 {
+	status = "okay";
+
+	/* TFA9887 @ 34 */
+	/* TFA9887 @ 35 */
+};
+
+&blsp1_i2c5 {
+	status = "okay";
+
+	touchscreen@20 {
+		compatible = "syna,rmi4-i2c";
+		reg = <0x20>;
+
+		interrupts-extended = <&tlmm 17 IRQ_TYPE_EDGE_FALLING>;
+		vdd-supply = <&pm8226_l19>;
+
+		syna,startup-delay-ms = <160>;
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		rmi4-f01@1 {
+			reg = <0x1>;
+			syna,nosleep-mode = <1>;
+		};
+
+		rmi4-f12@12 {
+			reg = <0x12>;
+			syna,sensor-type = <1>;
+		};
+	};
+};
+
+&blsp1_i2c6 {
+	status = "okay";
+
+	/* NCP6924 Camera Regulators @ 10 */
+	/* PN544 NFC @ 28 */
+	/* TPS61310 Flash/Torch @ 33 */
+};
+
+&pm8226_vib {
+	status = "okay";
+};
+
+&rpm_requests {
+	regulators {
+		compatible = "qcom,rpm-pm8226-regulators";
+
+		pm8226_s3: s3 {
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1350000>;
+		};
+
+		pm8226_s4: s4 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2200000>;
+		};
+
+		pm8226_s5: s5 {
+			regulator-min-microvolt = <1150000>;
+			regulator-max-microvolt = <1150000>;
+		};
+
+		pm8226_l1: l1 {
+			regulator-min-microvolt = <1225000>;
+			regulator-max-microvolt = <1225000>;
+		};
+
+		pm8226_l2: l2 {
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+		};
+
+		pm8226_l3: l3 {
+			regulator-min-microvolt = <750000>;
+			regulator-max-microvolt = <1337500>;
+		};
+
+		pm8226_l4: l4 {
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+		};
+
+		pm8226_l5: l5 {
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+		};
+
+		pm8226_l6: l6 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+		};
+
+		pm8226_l7: l7 {
+			regulator-min-microvolt = <1850000>;
+			regulator-max-microvolt = <1850000>;
+		};
+
+		pm8226_l8: l8 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+		};
+
+		pm8226_l9: l9 {
+			regulator-min-microvolt = <2050000>;
+			regulator-max-microvolt = <2050000>;
+		};
+
+		pm8226_l10: l10 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+		};
+
+		pm8226_l12: l12 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+		};
+
+		pm8226_l14: l14 {
+			regulator-min-microvolt = <2750000>;
+			regulator-max-microvolt = <2750000>;
+		};
+
+		pm8226_l15: l15 {
+			regulator-min-microvolt = <3000000>;
+			regulator-max-microvolt = <3000000>;
+		};
+
+		pm8226_l16: l16 {
+			regulator-min-microvolt = <3000000>;
+			regulator-max-microvolt = <3350000>;
+		};
+
+		pm8226_l17: l17 {
+			regulator-min-microvolt = <2950000>;
+			regulator-max-microvolt = <2950000>;
+		};
+
+		pm8226_l18: l18 {
+			regulator-min-microvolt = <2950000>;
+			regulator-max-microvolt = <2950000>;
+		};
+
+		pm8226_l19: l19 {
+			regulator-min-microvolt = <2850000>;
+			regulator-max-microvolt = <2850000>;
+		};
+
+		pm8226_l20: l20 {
+			regulator-min-microvolt = <3075000>;
+			regulator-max-microvolt = <3075000>;
+		};
+
+		pm8226_l21: l21 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2950000>;
+			regulator-allow-set-load;
+		};
+
+		pm8226_l22: l22 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2950000>;
+		};
+
+		pm8226_l23: l23 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <3000000>;
+		};
+
+		pm8226_l24: l24 {
+			regulator-min-microvolt = <1300000>;
+			regulator-max-microvolt = <1350000>;
+		};
+
+		pm8226_l25: l25 {
+			regulator-min-microvolt = <1775000>;
+			regulator-max-microvolt = <2125000>;
+		};
+
+		pm8226_l26: l26 {
+			regulator-min-microvolt = <1225000>;
+			regulator-max-microvolt = <1225000>;
+		};
+
+		pm8226_l27: l27 {
+			regulator-min-microvolt = <2050000>;
+			regulator-max-microvolt = <2050000>;
+		};
+
+		pm8226_l28: l28 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+		};
+
+		pm8226_lvs1: lvs1 {};
+	};
+};
+
+&sdhc_2 {
+	vmmc-supply = <&pm8226_l18>;
+	vqmmc-supply = <&pm8226_l21>;
+
+	bus-width = <4>;
+	cd-gpios = <&tlmm 38 GPIO_ACTIVE_LOW>;
+
+	status = "okay";
+};
+
+&smbb {
+	qcom,fast-charge-safe-current = <1750000>;
+	qcom,fast-charge-current-limit = <1750000>;
+	qcom,fast-charge-safe-voltage = <4360000>;
+	qcom,fast-charge-high-threshold-voltage = <4350000>;
+	qcom,auto-recharge-threshold-voltage = <4300000>;
+	qcom,minimum-input-voltage = <4300000>;
+
+	status = "okay";
+};
+
+&usb {
+	extcon = <&smbb>;
+	dr_mode = "peripheral";
+	status = "okay";
+};
+
+&usb_hs_phy {
+	extcon = <&smbb>;
+	v1p8-supply = <&pm8226_l10>;
+	v3p3-supply = <&pm8226_l20>;
+};
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8926-microsoft-superman-lte.dts b/arch/arm/boot/dts/qcom/qcom-msm8926-microsoft-superman-lte.dts
new file mode 100644
index 000000000000..9b48661d69c5
--- /dev/null
+++ b/arch/arm/boot/dts/qcom/qcom-msm8926-microsoft-superman-lte.dts
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * Copyright (c) 2023, Jack Matthews <jm5112356@gmail.com>
+ * Copyright (c) 2023, Ivaylo Ivanov <ivo.ivanov.ivanov1@gmail.com>
+ * Copyright (c) 2023, Dominik Kobinski <dominikkobinski314@gmail.com>
+ * Copyright (c) 2023, Rayyan Ansari <rayyan@ansari.sh>
+ */
+
+/dts-v1/;
+
+#include "qcom-msm8226-microsoft-common.dtsi"
+
+/* This device has touchscreen on i2c3 instead */
+/delete-node/ &touchscreen;
+
+/ {
+	model = "Nokia Lumia 735";
+	compatible = "microsoft,superman-lte", "qcom,msm8926", "qcom,msm8226";
+	chassis-type = "handset";
+};
+
+&blsp1_i2c3 {
+	status = "okay";
+
+	touchscreen: touchscreen@4b {
+		compatible = "syna,rmi4-i2c";
+		reg = <0x4b>;
+
+		interrupts-extended = <&tlmm 17 IRQ_TYPE_EDGE_FALLING>;
+		vdd-supply = <&pm8226_l15>;
+		vio-supply = <&pm8226_l6>;
+
+		pinctrl-0 = <&touchscreen_default>;
+		pinctrl-names = "default";
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		rmi4-f01@1 {
+			reg = <0x01>;
+			syna,nosleep-mode = <1>;
+		};
+
+		rmi4-f11@11 {
+			reg = <0x11>;
+			syna,sensor-type = <1>;
+		};
+	};
+};
+
+&blsp1_i2c5 {
+	status = "disabled";
+};
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8926-microsoft-tesla.dts b/arch/arm/boot/dts/qcom/qcom-msm8926-microsoft-tesla.dts
new file mode 100644
index 000000000000..53a6d4e85959
--- /dev/null
+++ b/arch/arm/boot/dts/qcom/qcom-msm8926-microsoft-tesla.dts
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * Copyright (c) 2023, Jack Matthews <jm5112356@gmail.com>
+ * Copyright (c) 2023, Ivaylo Ivanov <ivo.ivanov.ivanov1@gmail.com>
+ * Copyright (c) 2023, Dominik Kobinski <dominikkobinski314@gmail.com>
+ * Copyright (c) 2023, Rayyan Ansari <rayyan@ansari.sh>
+ */
+
+/dts-v1/;
+
+#include "qcom-msm8226-microsoft-common.dtsi"
+
+/* This device has touchscreen on i2c1 instead */
+/delete-node/ &touchscreen;
+
+/ {
+	model = "Nokia Lumia 830";
+	compatible = "microsoft,tesla", "qcom,msm8926", "qcom,msm8226";
+	chassis-type = "handset";
+};
+
+&blsp1_i2c1 {
+	status = "okay";
+
+	touchscreen: touchscreen@4b {
+		compatible = "syna,rmi4-i2c";
+		reg = <0x4b>;
+
+		interrupts-extended = <&tlmm 17 IRQ_TYPE_EDGE_FALLING>;
+		vdd-supply = <&pm8226_l15>;
+		vio-supply = <&pm8226_l6>;
+
+		pinctrl-0 = <&touchscreen_default>;
+		pinctrl-names = "default";
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		rmi4-f01@1 {
+			reg = <0x01>;
+			syna,nosleep-mode = <1>;
+		};
+
+		rmi4-f12@12 {
+			reg = <0x12>;
+			syna,sensor-type = <1>;
+		};
+	};
+};
+
+&blsp1_i2c5 {
+	status = "disabled";
+};
+
+&gpio_keys {
+	key-camera-snapshot {
+		label = "Camera Snapshot";
+		gpios = <&tlmm 107 GPIO_ACTIVE_LOW>;
+		linux,code = <KEY_CAMERA>;
+	};
+
+	key-camera-focus {
+		label = "Camera Focus";
+		gpios = <&tlmm 108 GPIO_ACTIVE_LOW>;
+		linux,code = <KEY_CAMERA_FOCUS>;
+	};
+};
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8926-motorola-peregrine.dts b/arch/arm/boot/dts/qcom/qcom-msm8926-motorola-peregrine.dts
new file mode 100644
index 000000000000..0cbe2d2fbbb1
--- /dev/null
+++ b/arch/arm/boot/dts/qcom/qcom-msm8926-motorola-peregrine.dts
@@ -0,0 +1,291 @@
+// SPDX-License-Identifier: BSD-3-Clause
+
+/dts-v1/;
+
+#include "qcom-msm8226.dtsi"
+#include "pm8226.dtsi"
+
+/delete-node/ &smem_region;
+
+/ {
+	model = "Motorola Moto G 4G (2013)";
+	compatible = "motorola,peregrine", "qcom,msm8926", "qcom,msm8226";
+	chassis-type = "handset";
+
+	aliases {
+		mmc0 = &sdhc_1; /* SDC1 eMMC slot */
+		mmc1 = &sdhc_2; /* SDC2 SD card slot */
+	};
+
+	chosen {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		framebuffer0: framebuffer@3200000 {
+			compatible = "simple-framebuffer";
+			reg = <0x03200000 0x800000>;
+			width = <720>;
+			height = <1280>;
+			stride = <(720 * 3)>;
+			format = "r8g8b8";
+		};
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		event-hall-sensor {
+			label = "Hall Effect Sensor";
+			gpios = <&tlmm 51 GPIO_ACTIVE_LOW>;
+			linux,input-type = <EV_SW>;
+			linux,code = <SW_LID>;
+			linux,can-disable;
+		};
+
+		key-volume-up {
+			label = "Volume Up";
+			gpios = <&tlmm 106 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_VOLUMEUP>;
+			debounce-interval = <15>;
+		};
+	};
+
+	reserved-memory {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		framebuffer@3200000 {
+			reg = <0x03200000 0x800000>;
+			no-map;
+		};
+
+		smem_region: smem@fa00000 {
+			reg = <0x0fa00000 0x100000>;
+			no-map;
+		};
+	};
+};
+
+&blsp1_i2c3 {
+	status = "okay";
+
+	sensor@48 {
+		compatible = "ti,tmp108";
+		reg = <0x48>;
+	};
+};
+
+&blsp1_uart3 {
+	status = "okay";
+};
+
+&pm8226_resin {
+	linux,code = <KEY_VOLUMEDOWN>;
+	status = "okay";
+};
+
+&pm8226_vib {
+	status = "okay";
+};
+
+&rpm_requests {
+	regulators {
+		compatible = "qcom,rpm-pm8226-regulators";
+
+		pm8226_s3: s3 {
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1300000>;
+		};
+
+		pm8226_s4: s4 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2200000>;
+		};
+
+		pm8226_s5: s5 {
+			regulator-min-microvolt = <1150000>;
+			regulator-max-microvolt = <1150000>;
+		};
+
+		pm8226_l1: l1 {
+			regulator-min-microvolt = <1225000>;
+			regulator-max-microvolt = <1225000>;
+		};
+
+		pm8226_l2: l2 {
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+		};
+
+		pm8226_l3: l3 {
+			regulator-min-microvolt = <750000>;
+			regulator-max-microvolt = <1337500>;
+		};
+
+		pm8226_l4: l4 {
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+		};
+
+		pm8226_l5: l5 {
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+		};
+
+		pm8226_l6: l6 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-allow-set-load;
+		};
+
+		pm8226_l7: l7 {
+			regulator-min-microvolt = <1850000>;
+			regulator-max-microvolt = <1850000>;
+		};
+
+		pm8226_l8: l8 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+		};
+
+		pm8226_l9: l9 {
+			regulator-min-microvolt = <2050000>;
+			regulator-max-microvolt = <2050000>;
+		};
+
+		pm8226_l10: l10 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+		};
+
+		pm8226_l12: l12 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+		};
+
+		pm8226_l14: l14 {
+			regulator-min-microvolt = <2750000>;
+			regulator-max-microvolt = <2750000>;
+		};
+
+		pm8226_l15: l15 {
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+		};
+
+		pm8226_l16: l16 {
+			regulator-min-microvolt = <3000000>;
+			regulator-max-microvolt = <3350000>;
+		};
+
+		pm8226_l17: l17 {
+			regulator-min-microvolt = <2950000>;
+			regulator-max-microvolt = <2950000>;
+		};
+
+		pm8226_l18: l18 {
+			regulator-min-microvolt = <2950000>;
+			regulator-max-microvolt = <2950000>;
+		};
+
+		pm8226_l19: l19 {
+			regulator-min-microvolt = <2850000>;
+			regulator-max-microvolt = <2850000>;
+		};
+
+		pm8226_l20: l20 {
+			regulator-min-microvolt = <3075000>;
+			regulator-max-microvolt = <3075000>;
+		};
+
+		pm8226_l21: l21 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2950000>;
+			regulator-allow-set-load;
+		};
+
+		pm8226_l22: l22 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2950000>;
+		};
+
+		pm8226_l23: l23 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2950000>;
+		};
+
+		pm8226_l24: l24 {
+			regulator-min-microvolt = <1300000>;
+			regulator-max-microvolt = <1350000>;
+		};
+
+		pm8226_l25: l25 {
+			regulator-min-microvolt = <1775000>;
+			regulator-max-microvolt = <2125000>;
+		};
+
+		pm8226_l26: l26 {
+			regulator-min-microvolt = <1225000>;
+			regulator-max-microvolt = <1225000>;
+		};
+
+		pm8226_l27: l27 {
+			regulator-min-microvolt = <2050000>;
+			regulator-max-microvolt = <2050000>;
+		};
+
+		pm8226_l28: l28 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <3400000>;
+			regulator-boot-on;
+		};
+
+		pm8226_lvs1: lvs1 {
+			/* Pull-up for I2C lines */
+			regulator-always-on;
+		};
+	};
+};
+
+&sdhc_1 {
+	vmmc-supply = <&pm8226_l17>;
+	vqmmc-supply = <&pm8226_l6>;
+
+	bus-width = <8>;
+	non-removable;
+
+	status = "okay";
+};
+
+&sdhc_2 {
+	vmmc-supply = <&pm8226_l18>;
+	vqmmc-supply = <&pm8226_l21>;
+
+	bus-width = <4>;
+	cd-gpios = <&tlmm 115 GPIO_ACTIVE_HIGH>;
+
+	status = "okay";
+};
+
+&smbb {
+	qcom,fast-charge-safe-current = <2000000>;
+	qcom,fast-charge-current-limit = <1900000>;
+	qcom,fast-charge-safe-voltage = <4400000>;
+	qcom,minimum-input-voltage = <4300000>;
+
+	status = "okay";
+};
+
+&usb {
+	extcon = <&smbb>;
+	dr_mode = "peripheral";
+	status = "okay";
+};
+
+&usb_hs_phy {
+	extcon = <&smbb>;
+	v1p8-supply = <&pm8226_l10>;
+	v3p3-supply = <&pm8226_l20>;
+};
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8960-cdp.dts b/arch/arm/boot/dts/qcom/qcom-msm8960-cdp.dts
index 6c1bc3818883..36f4c997b0b3 100644
--- a/arch/arm/boot/dts/qcom/qcom-msm8960-cdp.dts
+++ b/arch/arm/boot/dts/qcom/qcom-msm8960-cdp.dts
@@ -2,6 +2,7 @@
 #include <dt-bindings/input/input.h>
 
 #include "qcom-msm8960.dtsi"
+#include "pm8921.dtsi"
 
 / {
 	model = "Qualcomm MSM8960 CDP";
@@ -88,17 +89,21 @@
 	};
 };
 
-&pmicintc {
-	keypad@148 {
-		linux,keymap = <
-			MATRIX_KEY(0, 0, KEY_VOLUMEUP)
-			MATRIX_KEY(0, 1, KEY_VOLUMEDOWN)
-			MATRIX_KEY(0, 2, KEY_CAMERA_FOCUS)
-			MATRIX_KEY(0, 3, KEY_CAMERA)
-			>;
-		keypad,num-rows = <1>;
-		keypad,num-columns = <5>;
-	};
+&pm8921 {
+	interrupts-extended = <&msmgpio 104 IRQ_TYPE_LEVEL_LOW>;
+};
+
+&pm8921_keypad {
+	linux,keymap = <
+		MATRIX_KEY(0, 0, KEY_VOLUMEUP)
+		MATRIX_KEY(0, 1, KEY_VOLUMEDOWN)
+		MATRIX_KEY(0, 2, KEY_CAMERA_FOCUS)
+		MATRIX_KEY(0, 3, KEY_CAMERA)
+		>;
+	keypad,num-rows = <1>;
+	keypad,num-columns = <5>;
+
+	status = "okay";
 };
 
 &rpm {
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8960-samsung-expressatt.dts b/arch/arm/boot/dts/qcom/qcom-msm8960-samsung-expressatt.dts
index 13e85c287498..1a5116336ff0 100644
--- a/arch/arm/boot/dts/qcom/qcom-msm8960-samsung-expressatt.dts
+++ b/arch/arm/boot/dts/qcom/qcom-msm8960-samsung-expressatt.dts
@@ -1,8 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <dt-bindings/input/input.h>
+#include <dt-bindings/reset/qcom,gcc-msm8960.h>
 
 #include "qcom-msm8960.dtsi"
-#include <dt-bindings/reset/qcom,gcc-msm8960.h>
+#include "pm8921.dtsi"
 
 / {
 	model = "Samsung Galaxy Express SGH-I437";
@@ -84,6 +85,10 @@
 	};
 };
 
+&pm8921 {
+	interrupts-extended = <&msmgpio 104 IRQ_TYPE_LEVEL_LOW>;
+};
+
 &rpm {
 	regulators {
 		compatible = "qcom,rpm-pm8921-regulators";
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8960.dtsi b/arch/arm/boot/dts/qcom/qcom-msm8960.dtsi
index d13080fcbeea..f420740e068e 100644
--- a/arch/arm/boot/dts/qcom/qcom-msm8960.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-msm8960.dtsi
@@ -200,10 +200,6 @@
 				     <GIC_SPI 21 IRQ_TYPE_EDGE_RISING>,
 				     <GIC_SPI 22 IRQ_TYPE_EDGE_RISING>;
 			interrupt-names = "ack", "err", "wakeup";
-
-			regulators {
-				compatible = "qcom,rpm-pm8921-regulators";
-			};
 		};
 
 		acc0: clock-controller@2088000 {
@@ -259,49 +255,10 @@
 			};
 		};
 
-		ssbi@500000 {
+		ssbi: ssbi@500000 {
 			compatible = "qcom,ssbi";
 			reg = <0x500000 0x1000>;
 			qcom,controller-type = "pmic-arbiter";
-
-			pmicintc: pmic {
-				compatible = "qcom,pm8921";
-				interrupt-parent = <&msmgpio>;
-				interrupts = <104 IRQ_TYPE_LEVEL_LOW>;
-				#interrupt-cells = <2>;
-				interrupt-controller;
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				pwrkey@1c {
-					compatible = "qcom,pm8921-pwrkey";
-					reg = <0x1c>;
-					interrupt-parent = <&pmicintc>;
-					interrupts = <50 IRQ_TYPE_EDGE_RISING>,
-						     <51 IRQ_TYPE_EDGE_RISING>;
-					debounce = <15625>;
-					pull-up;
-				};
-
-				keypad@148 {
-					compatible = "qcom,pm8921-keypad";
-					reg = <0x148>;
-					interrupt-parent = <&pmicintc>;
-					interrupts = <74 IRQ_TYPE_EDGE_RISING>,
-						     <75 IRQ_TYPE_EDGE_RISING>;
-					debounce = <15>;
-					scan-delay = <32>;
-					row-hold = <91500>;
-				};
-
-				rtc@11d {
-					compatible = "qcom,pm8921-rtc";
-					interrupt-parent = <&pmicintc>;
-					interrupts = <39 IRQ_TYPE_EDGE_RISING>;
-					reg = <0x11d>;
-					allow-set-time;
-				};
-			};
 		};
 
 		rng@1a500000 {
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8974-lge-nexus5-hammerhead.dts b/arch/arm/boot/dts/qcom/qcom-msm8974-lge-nexus5-hammerhead.dts
index 60bdfddeae69..4aaae8537a3f 100644
--- a/arch/arm/boot/dts/qcom/qcom-msm8974-lge-nexus5-hammerhead.dts
+++ b/arch/arm/boot/dts/qcom/qcom-msm8974-lge-nexus5-hammerhead.dts
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "qcom-msm8974.dtsi"
-#include "qcom-pm8841.dtsi"
-#include "qcom-pm8941.dtsi"
+#include "pm8841.dtsi"
+#include "pm8941.dtsi"
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/leds/common.h>
 #include <dt-bindings/pinctrl/qcom,pmic-gpio.h>
@@ -60,6 +60,33 @@
 		enable-gpios = <&tlmm 60 GPIO_ACTIVE_HIGH>;
 	};
 
+	vreg_boost: vreg-boost {
+		compatible = "regulator-fixed";
+
+		regulator-name = "vreg-boost";
+		regulator-min-microvolt = <3150000>;
+		regulator-max-microvolt = <3150000>;
+
+		regulator-always-on;
+		regulator-boot-on;
+
+		gpio = <&pm8941_gpios 21 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&boost_bypass_n_pin>;
+	};
+
+	vreg_vph_pwr: vreg-vph-pwr {
+		compatible = "regulator-fixed";
+		regulator-name = "vph-pwr";
+
+		regulator-min-microvolt = <3600000>;
+		regulator-max-microvolt = <3600000>;
+
+		regulator-always-on;
+	};
+
 	vreg_wlan: wlan-regulator {
 		compatible = "regulator-fixed";
 
@@ -340,6 +367,7 @@
 
 &remoteproc_adsp {
 	cx-supply = <&pm8841_s2>;
+	status = "okay";
 };
 
 &remoteproc_mss {
@@ -347,6 +375,7 @@
 	mss-supply = <&pm8841_s3>;
 	mx-supply = <&pm8841_s1>;
 	pll-supply = <&pm8941_l12>;
+	status = "okay";
 };
 
 &rpm_requests {
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8974-sony-xperia-rhine.dtsi b/arch/arm/boot/dts/qcom/qcom-msm8974-sony-xperia-rhine.dtsi
index 68a2f9094e53..d34659ebac22 100644
--- a/arch/arm/boot/dts/qcom/qcom-msm8974-sony-xperia-rhine.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-msm8974-sony-xperia-rhine.dtsi
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "qcom-msm8974.dtsi"
-#include "qcom-pm8841.dtsi"
-#include "qcom-pm8941.dtsi"
+#include "pm8841.dtsi"
+#include "pm8941.dtsi"
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/leds/common.h>
 #include <dt-bindings/pinctrl/qcom,pmic-gpio.h>
@@ -65,6 +65,33 @@
 			pmsg-size = <0x80000>;
 		};
 	};
+
+	vreg_boost: vreg-boost {
+		compatible = "regulator-fixed";
+
+		regulator-name = "vreg-boost";
+		regulator-min-microvolt = <3150000>;
+		regulator-max-microvolt = <3150000>;
+
+		regulator-always-on;
+		regulator-boot-on;
+
+		gpio = <&pm8941_gpios 21 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&boost_bypass_n_pin>;
+	};
+
+	vreg_vph_pwr: vreg-vph-pwr {
+		compatible = "regulator-fixed";
+		regulator-name = "vph-pwr";
+
+		regulator-min-microvolt = <3600000>;
+		regulator-max-microvolt = <3600000>;
+
+		regulator-always-on;
+	};
 };
 
 &blsp1_i2c2 {
@@ -190,6 +217,7 @@
 
 &remoteproc_adsp {
 	cx-supply = <&pm8841_s2>;
+	status = "okay";
 };
 
 &remoteproc_mss {
@@ -197,6 +225,7 @@
 	mss-supply = <&pm8841_s3>;
 	mx-supply = <&pm8841_s1>;
 	pll-supply = <&pm8941_l12>;
+	status = "okay";
 };
 
 &rpm_requests {
@@ -425,6 +454,8 @@
 	qcom,fast-charge-low-threshold-voltage = <3400000>;
 	qcom,auto-recharge-threshold-voltage = <4200000>;
 	qcom,minimum-input-voltage = <4300000>;
+
+	status = "okay";
 };
 
 &tlmm {
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8974.dtsi b/arch/arm/boot/dts/qcom/qcom-msm8974.dtsi
index 0bc2e66d15b1..b1413983787c 100644
--- a/arch/arm/boot/dts/qcom/qcom-msm8974.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-msm8974.dtsi
@@ -346,6 +346,20 @@
 			reg = <0xf9011000 0x1000>;
 		};
 
+		saw_l2: power-controller@f9012000 {
+			compatible = "qcom,saw2";
+			reg = <0xf9012000 0x1000>;
+			regulator;
+		};
+
+		watchdog@f9017000 {
+			compatible = "qcom,apss-wdt-msm8974", "qcom,kpss-wdt";
+			reg = <0xf9017000 0x1000>;
+			interrupts = <GIC_SPI 3 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 4 IRQ_TYPE_EDGE_RISING>;
+			clocks = <&sleep_clk>;
+		};
+
 		timer@f9020000 {
 			#address-cells = <1>;
 			#size-cells = <1>;
@@ -405,52 +419,46 @@
 			};
 		};
 
-		saw0: power-controller@f9089000 {
-			compatible = "qcom,msm8974-saw2-v2.1-cpu", "qcom,saw2";
-			reg = <0xf9089000 0x1000>, <0xf9009000 0x1000>;
-		};
-
-		saw1: power-controller@f9099000 {
-			compatible = "qcom,msm8974-saw2-v2.1-cpu", "qcom,saw2";
-			reg = <0xf9099000 0x1000>, <0xf9009000 0x1000>;
-		};
-
-		saw2: power-controller@f90a9000 {
-			compatible = "qcom,msm8974-saw2-v2.1-cpu", "qcom,saw2";
-			reg = <0xf90a9000 0x1000>, <0xf9009000 0x1000>;
-		};
-
-		saw3: power-controller@f90b9000 {
-			compatible = "qcom,msm8974-saw2-v2.1-cpu", "qcom,saw2";
-			reg = <0xf90b9000 0x1000>, <0xf9009000 0x1000>;
-		};
-
-		saw_l2: power-controller@f9012000 {
-			compatible = "qcom,saw2";
-			reg = <0xf9012000 0x1000>;
-			regulator;
-		};
-
 		acc0: power-manager@f9088000 {
 			compatible = "qcom,kpss-acc-v2";
 			reg = <0xf9088000 0x1000>, <0xf9008000 0x1000>;
 		};
 
+		saw0: power-controller@f9089000 {
+			compatible = "qcom,msm8974-saw2-v2.1-cpu", "qcom,saw2";
+			reg = <0xf9089000 0x1000>, <0xf9009000 0x1000>;
+		};
+
 		acc1: power-manager@f9098000 {
 			compatible = "qcom,kpss-acc-v2";
 			reg = <0xf9098000 0x1000>, <0xf9008000 0x1000>;
 		};
 
+		saw1: power-controller@f9099000 {
+			compatible = "qcom,msm8974-saw2-v2.1-cpu", "qcom,saw2";
+			reg = <0xf9099000 0x1000>, <0xf9009000 0x1000>;
+		};
+
 		acc2: power-manager@f90a8000 {
 			compatible = "qcom,kpss-acc-v2";
 			reg = <0xf90a8000 0x1000>, <0xf9008000 0x1000>;
 		};
 
+		saw2: power-controller@f90a9000 {
+			compatible = "qcom,msm8974-saw2-v2.1-cpu", "qcom,saw2";
+			reg = <0xf90a9000 0x1000>, <0xf9009000 0x1000>;
+		};
+
 		acc3: power-manager@f90b8000 {
 			compatible = "qcom,kpss-acc-v2";
 			reg = <0xf90b8000 0x1000>, <0xf9008000 0x1000>;
 		};
 
+		saw3: power-controller@f90b9000 {
+			compatible = "qcom,msm8974-saw2-v2.1-cpu", "qcom,saw2";
+			reg = <0xf90b9000 0x1000>, <0xf9009000 0x1000>;
+		};
+
 		sdhc_1: mmc@f9824900 {
 			compatible = "qcom,msm8974-sdhci", "qcom,sdhci-msm-v4";
 			reg = <0xf9824900 0x11c>, <0xf9824000 0x800>;
@@ -1063,6 +1071,15 @@
 			};
 		};
 
+		bimc: interconnect@fc380000 {
+			reg = <0xfc380000 0x6a000>;
+			compatible = "qcom,msm8974-bimc";
+			#interconnect-cells = <1>;
+			clock-names = "bus", "bus_a";
+			clocks = <&rpmcc RPM_SMD_BIMC_CLK>,
+				 <&rpmcc RPM_SMD_BIMC_A_CLK>;
+		};
+
 		gcc: clock-controller@fc400000 {
 			compatible = "qcom,gcc-msm8974";
 			#clock-cells = <1>;
@@ -1101,22 +1118,13 @@
 			};
 		};
 
-		bimc: interconnect@fc380000 {
-			reg = <0xfc380000 0x6a000>;
-			compatible = "qcom,msm8974-bimc";
-			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_BIMC_CLK>,
-			         <&rpmcc RPM_SMD_BIMC_A_CLK>;
-		};
-
 		snoc: interconnect@fc460000 {
 			reg = <0xfc460000 0x4000>;
 			compatible = "qcom,msm8974-snoc";
 			#interconnect-cells = <1>;
 			clock-names = "bus", "bus_a";
 			clocks = <&rpmcc RPM_SMD_SNOC_CLK>,
-			         <&rpmcc RPM_SMD_SNOC_A_CLK>;
+				 <&rpmcc RPM_SMD_SNOC_A_CLK>;
 		};
 
 		pnoc: interconnect@fc468000 {
@@ -1125,7 +1133,7 @@
 			#interconnect-cells = <1>;
 			clock-names = "bus", "bus_a";
 			clocks = <&rpmcc RPM_SMD_PNOC_CLK>,
-			         <&rpmcc RPM_SMD_PNOC_A_CLK>;
+				 <&rpmcc RPM_SMD_PNOC_A_CLK>;
 		};
 
 		ocmemnoc: interconnect@fc470000 {
@@ -1134,7 +1142,7 @@
 			#interconnect-cells = <1>;
 			clock-names = "bus", "bus_a";
 			clocks = <&rpmcc RPM_SMD_OCMEMGX_CLK>,
-			         <&rpmcc RPM_SMD_OCMEMGX_A_CLK>;
+				 <&rpmcc RPM_SMD_OCMEMGX_A_CLK>;
 		};
 
 		mmssnoc: interconnect@fc478000 {
@@ -1143,7 +1151,7 @@
 			#interconnect-cells = <1>;
 			clock-names = "bus", "bus_a";
 			clocks = <&mmcc MMSS_S0_AXI_CLK>,
-			         <&mmcc MMSS_S0_AXI_CLK>;
+				 <&mmcc MMSS_S0_AXI_CLK>;
 		};
 
 		cnoc: interconnect@fc480000 {
@@ -1152,7 +1160,7 @@
 			#interconnect-cells = <1>;
 			clock-names = "bus", "bus_a";
 			clocks = <&rpmcc RPM_SMD_CNOC_CLK>,
-			         <&rpmcc RPM_SMD_CNOC_A_CLK>;
+				 <&rpmcc RPM_SMD_CNOC_A_CLK>;
 		};
 
 		tsens: thermal-sensor@fc4a9000 {
@@ -1633,13 +1641,6 @@
 					bias-pull-up;
 					drive-strength = <2>;
 				};
-
-				cd-pins {
-					pins = "gpio54";
-					function = "gpio";
-					bias-disable;
-					drive-strength = <2>;
-				};
 			};
 
 			blsp1_uart2_default: blsp1-uart2-default-state {
@@ -2408,31 +2409,4 @@
 			     <GIC_PPI 1 0xf08>;
 		clock-frequency = <19200000>;
 	};
-
-	vreg_boost: vreg-boost {
-		compatible = "regulator-fixed";
-
-		regulator-name = "vreg-boost";
-		regulator-min-microvolt = <3150000>;
-		regulator-max-microvolt = <3150000>;
-
-		regulator-always-on;
-		regulator-boot-on;
-
-		gpio = <&pm8941_gpios 21 GPIO_ACTIVE_HIGH>;
-		enable-active-high;
-
-		pinctrl-names = "default";
-		pinctrl-0 = <&boost_bypass_n_pin>;
-	};
-
-	vreg_vph_pwr: vreg-vph-pwr {
-		compatible = "regulator-fixed";
-		regulator-name = "vph-pwr";
-
-		regulator-min-microvolt = <3600000>;
-		regulator-max-microvolt = <3600000>;
-
-		regulator-always-on;
-	};
 };
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8974pro-fairphone-fp2.dts b/arch/arm/boot/dts/qcom/qcom-msm8974pro-fairphone-fp2.dts
index 42d253b75dad..fe227fd3f908 100644
--- a/arch/arm/boot/dts/qcom/qcom-msm8974pro-fairphone-fp2.dts
+++ b/arch/arm/boot/dts/qcom/qcom-msm8974pro-fairphone-fp2.dts
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "qcom-msm8974pro.dtsi"
-#include "qcom-pm8841.dtsi"
-#include "qcom-pm8941.dtsi"
+#include "pm8841.dtsi"
+#include "pm8941.dtsi"
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/leds/common.h>
 #include <dt-bindings/pinctrl/qcom,pmic-gpio.h>
@@ -57,6 +57,33 @@
 		enable-gpios = <&tlmm 86 GPIO_ACTIVE_HIGH>;
 		vcc-supply = <&pm8941_l18>;
 	};
+
+	vreg_boost: vreg-boost {
+		compatible = "regulator-fixed";
+
+		regulator-name = "vreg-boost";
+		regulator-min-microvolt = <3150000>;
+		regulator-max-microvolt = <3150000>;
+
+		regulator-always-on;
+		regulator-boot-on;
+
+		gpio = <&pm8941_gpios 21 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&boost_bypass_n_pin>;
+	};
+
+	vreg_vph_pwr: vreg-vph-pwr {
+		compatible = "regulator-fixed";
+		regulator-name = "vph-pwr";
+
+		regulator-min-microvolt = <3600000>;
+		regulator-max-microvolt = <3600000>;
+
+		regulator-always-on;
+	};
 };
 
 &blsp1_i2c2 {
@@ -381,6 +408,8 @@
 	qcom,fast-charge-high-threshold-voltage = <4350000>;
 	qcom,auto-recharge-threshold-voltage = <4240000>;
 	qcom,minimum-input-voltage = <4450000>;
+
+	status = "okay";
 };
 
 &tlmm {
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8974pro-oneplus-bacon.dts b/arch/arm/boot/dts/qcom/qcom-msm8974pro-oneplus-bacon.dts
index 8230d0e1d95d..4c8edadea0ac 100644
--- a/arch/arm/boot/dts/qcom/qcom-msm8974pro-oneplus-bacon.dts
+++ b/arch/arm/boot/dts/qcom/qcom-msm8974pro-oneplus-bacon.dts
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "qcom-msm8974pro.dtsi"
-#include "qcom-pm8841.dtsi"
-#include "qcom-pm8941.dtsi"
+#include "pm8841.dtsi"
+#include "pm8941.dtsi"
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/pinctrl/qcom,pmic-gpio.h>
 
@@ -51,6 +51,33 @@
 			debounce-interval = <150>;
 		};
 	};
+
+	vreg_boost: vreg-boost {
+		compatible = "regulator-fixed";
+
+		regulator-name = "vreg-boost";
+		regulator-min-microvolt = <3150000>;
+		regulator-max-microvolt = <3150000>;
+
+		regulator-always-on;
+		regulator-boot-on;
+
+		gpio = <&pm8941_gpios 21 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&boost_bypass_n_pin>;
+	};
+
+	vreg_vph_pwr: vreg-vph-pwr {
+		compatible = "regulator-fixed";
+		regulator-name = "vph-pwr";
+
+		regulator-min-microvolt = <3600000>;
+		regulator-max-microvolt = <3600000>;
+
+		regulator-always-on;
+	};
 };
 
 &blsp1_i2c1 {
@@ -433,6 +460,10 @@
 	status = "okay";
 };
 
+&smbb {
+	status = "okay";
+};
+
 &tlmm {
 	gpio_hall_sensor_default: gpio-hall-sensor-default-state {
 		pins = "gpio68";
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8974pro-samsung-klte.dts b/arch/arm/boot/dts/qcom/qcom-msm8974pro-samsung-klte.dts
index 3e2c86591ee2..b93539e2b87e 100644
--- a/arch/arm/boot/dts/qcom/qcom-msm8974pro-samsung-klte.dts
+++ b/arch/arm/boot/dts/qcom/qcom-msm8974pro-samsung-klte.dts
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "qcom-msm8974pro.dtsi"
-#include "qcom-pma8084.dtsi"
+#include "pma8084.dtsi"
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/pinctrl/qcom,pmic-gpio.h>
 #include <dt-bindings/leds/common.h>
@@ -155,7 +155,15 @@
 		enable-active-high;
 	};
 
-	/delete-node/ vreg-boost;
+	vreg_vph_pwr: vreg-vph-pwr {
+		compatible = "regulator-fixed";
+		regulator-name = "vph-pwr";
+
+		regulator-min-microvolt = <3600000>;
+		regulator-max-microvolt = <3600000>;
+
+		regulator-always-on;
+	};
 };
 
 &blsp1_i2c2 {
@@ -355,7 +363,6 @@
 		vddr-supply = <&vreg_panel>;
 
 		reset-gpios = <&pma8084_gpios 17 GPIO_ACTIVE_LOW>;
-		te-gpios = <&tlmm 12 GPIO_ACTIVE_HIGH>;
 
 		port {
 			panel_in: endpoint {
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8974pro-sony-xperia-shinano-castor.dts b/arch/arm/boot/dts/qcom/qcom-msm8974pro-sony-xperia-shinano-castor.dts
index 11468d1409f7..ee94741a26ed 100644
--- a/arch/arm/boot/dts/qcom/qcom-msm8974pro-sony-xperia-shinano-castor.dts
+++ b/arch/arm/boot/dts/qcom/qcom-msm8974pro-sony-xperia-shinano-castor.dts
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "qcom-msm8974pro.dtsi"
-#include "qcom-pm8841.dtsi"
-#include "qcom-pm8941.dtsi"
+#include "pm8841.dtsi"
+#include "pm8941.dtsi"
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/leds/common.h>
 #include <dt-bindings/pinctrl/qcom,pmic-gpio.h>
@@ -84,6 +84,33 @@
 		pinctrl-0 = <&lcd_dcdc_en_pin_a>;
 	};
 
+	vreg_boost: vreg-boost {
+		compatible = "regulator-fixed";
+
+		regulator-name = "vreg-boost";
+		regulator-min-microvolt = <3150000>;
+		regulator-max-microvolt = <3150000>;
+
+		regulator-always-on;
+		regulator-boot-on;
+
+		gpio = <&pm8941_gpios 21 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&boost_bypass_n_pin>;
+	};
+
+	vreg_vph_pwr: vreg-vph-pwr {
+		compatible = "regulator-fixed";
+		regulator-name = "vph-pwr";
+
+		regulator-min-microvolt = <3600000>;
+		regulator-max-microvolt = <3600000>;
+
+		regulator-always-on;
+	};
+
 	vreg_wlan: wlan-regulator {
 		compatible = "regulator-fixed";
 
@@ -297,6 +324,7 @@
 
 &remoteproc_adsp {
 	cx-supply = <&pm8841_s2>;
+	status = "okay";
 };
 
 &remoteproc_mss {
@@ -304,6 +332,7 @@
 	mss-supply = <&pm8841_s3>;
 	mx-supply = <&pm8841_s1>;
 	pll-supply = <&pm8941_l12>;
+	status = "okay";
 };
 
 &rpm_requests {
@@ -558,6 +587,8 @@
 	qcom,fast-charge-low-threshold-voltage = <3400000>;
 	qcom,auto-recharge-threshold-voltage = <4200000>;
 	qcom,minimum-input-voltage = <4300000>;
+
+	status = "okay";
 };
 
 &tlmm {
diff --git a/arch/arm/boot/dts/qcom/qcom-sdx55-mtp.dts b/arch/arm/boot/dts/qcom/qcom-sdx55-mtp.dts
index 7e97ad5803d8..247069361909 100644
--- a/arch/arm/boot/dts/qcom/qcom-sdx55-mtp.dts
+++ b/arch/arm/boot/dts/qcom/qcom-sdx55-mtp.dts
@@ -9,7 +9,7 @@
 #include "qcom-sdx55.dtsi"
 #include <dt-bindings/regulator/qcom,rpmh-regulator.h>
 #include <arm64/qcom/pm8150b.dtsi>
-#include "qcom-pmx55.dtsi"
+#include "pmx55.dtsi"
 
 / {
 	model = "Qualcomm Technologies, Inc. SDX55 MTP";
diff --git a/arch/arm/boot/dts/qcom/qcom-sdx55-t55.dts b/arch/arm/boot/dts/qcom/qcom-sdx55-t55.dts
index 51058b065279..082f7ed1a01f 100644
--- a/arch/arm/boot/dts/qcom/qcom-sdx55-t55.dts
+++ b/arch/arm/boot/dts/qcom/qcom-sdx55-t55.dts
@@ -8,7 +8,7 @@
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/regulator/qcom,rpmh-regulator.h>
 #include "qcom-sdx55.dtsi"
-#include "qcom-pmx55.dtsi"
+#include "pmx55.dtsi"
 
 / {
 	model = "Thundercomm T55 Development Kit";
diff --git a/arch/arm/boot/dts/qcom/qcom-sdx55-telit-fn980-tlb.dts b/arch/arm/boot/dts/qcom/qcom-sdx55-telit-fn980-tlb.dts
index 8fadc6e70692..e336a15b45c4 100644
--- a/arch/arm/boot/dts/qcom/qcom-sdx55-telit-fn980-tlb.dts
+++ b/arch/arm/boot/dts/qcom/qcom-sdx55-telit-fn980-tlb.dts
@@ -8,7 +8,7 @@
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/regulator/qcom,rpmh-regulator.h>
 #include "qcom-sdx55.dtsi"
-#include "qcom-pmx55.dtsi"
+#include "pmx55.dtsi"
 
 / {
 	model = "Telit FN980 TLB";
diff --git a/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi b/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi
index 2aa5089a8513..2045fc779f88 100644
--- a/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi
@@ -228,31 +228,26 @@
 
 		usb_qmpphy: phy@ff6000 {
 			compatible = "qcom,sdx55-qmp-usb3-uni-phy";
-			reg = <0x00ff6000 0x1c0>;
-			status = "disabled";
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges;
+			reg = <0x00ff6000 0x1000>;
 
 			clocks = <&gcc GCC_USB3_PHY_AUX_CLK>,
+				 <&gcc GCC_USB3_PRIM_CLKREF_CLK>,
 				 <&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>,
-				 <&gcc GCC_USB3_PRIM_CLKREF_CLK>;
-			clock-names = "aux", "cfg_ahb", "ref";
-
-			resets = <&gcc GCC_USB3PHY_PHY_BCR>,
-				 <&gcc GCC_USB3_PHY_BCR>;
-			reset-names = "phy", "common";
-
-			usb_ssphy: phy@ff6200 {
-				reg = <0x00ff6200 0x170>,
-				      <0x00ff6400 0x200>,
-				      <0x00ff6800 0x800>;
-				#phy-cells = <0>;
-				#clock-cells = <0>;
-				clocks = <&gcc GCC_USB3_PHY_PIPE_CLK>;
-				clock-names = "pipe0";
-				clock-output-names = "usb3_uni_phy_pipe_clk_src";
-			};
+				 <&gcc GCC_USB3_PHY_PIPE_CLK>;
+			clock-names = "aux",
+				      "ref",
+				      "cfg_ahb",
+				      "pipe";
+			clock-output-names = "usb3_uni_phy_pipe_clk_src";
+			#clock-cells = <0>;
+			#phy-cells = <0>;
+
+			resets = <&gcc GCC_USB3_PHY_BCR>,
+				 <&gcc GCC_USB3PHY_PHY_BCR>;
+			reset-names = "phy",
+				      "phy_phy";
+
+			status = "disabled";
 		};
 
 		mc_virt: interconnect@1100000 {
@@ -436,9 +431,9 @@
 			status = "disabled";
 		};
 
-		pcie_phy: phy@1c07000 {
+		pcie_phy: phy@1c06000 {
 			compatible = "qcom,sdx55-qmp-pcie-phy";
-			reg = <0x01c07000 0x2000>;
+			reg = <0x01c06000 0x2000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges;
@@ -585,10 +580,10 @@
 					  <&gcc GCC_USB30_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <200000000>;
 
-			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 198 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 158 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 157 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 51 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 11 IRQ_TYPE_EDGE_BOTH>,
+					      <&pdc 10 IRQ_TYPE_EDGE_BOTH>;
 			interrupt-names = "hs_phy_irq", "ss_phy_irq",
 					  "dm_hs_phy_irq", "dp_hs_phy_irq";
 
@@ -603,7 +598,7 @@
 				iommus = <&apps_smmu 0x1a0 0x0>;
 				snps,dis_u2_susphy_quirk;
 				snps,dis_enblslpm_quirk;
-				phys = <&usb_hsphy>, <&usb_ssphy>;
+				phys = <&usb_hsphy>, <&usb_qmpphy>;
 				phy-names = "usb2-phy", "usb3-phy";
 			};
 		};
@@ -612,7 +607,7 @@
 			compatible = "qcom,sdx55-pdc", "qcom,pdc";
 			reg = <0x0b210000 0x30000>;
 			qcom,pdc-ranges = <0 179 52>;
-			#interrupt-cells = <3>;
+			#interrupt-cells = <2>;
 			interrupt-parent = <&intc>;
 			interrupt-controller;
 		};
diff --git a/arch/arm/boot/dts/qcom/qcom-sdx65-mtp.dts b/arch/arm/boot/dts/qcom/qcom-sdx65-mtp.dts
index 9649c859a2c3..07c10c84eefa 100644
--- a/arch/arm/boot/dts/qcom/qcom-sdx65-mtp.dts
+++ b/arch/arm/boot/dts/qcom/qcom-sdx65-mtp.dts
@@ -12,7 +12,7 @@
 #include <dt-bindings/regulator/qcom,rpmh-regulator.h>
 #include <arm64/qcom/pmk8350.dtsi>
 #include <arm64/qcom/pm7250b.dtsi>
-#include "qcom-pmx65.dtsi"
+#include "pmx65.dtsi"
 
 / {
 	model = "Qualcomm Technologies, Inc. SDX65 MTP";
diff --git a/arch/arm/boot/dts/qcom/qcom-sdx65.dtsi b/arch/arm/boot/dts/qcom/qcom-sdx65.dtsi
index e559adaaeee7..40591a4da6a4 100644
--- a/arch/arm/boot/dts/qcom/qcom-sdx65.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-sdx65.dtsi
@@ -204,8 +204,16 @@
 		gcc: clock-controller@100000 {
 			compatible = "qcom,gcc-sdx65";
 			reg = <0x00100000 0x001f7400>;
-			clocks = <&rpmhcc RPMH_CXO_CLK>, <&rpmhcc RPMH_CXO_CLK_A>, <&sleep_clk>;
-			clock-names = "bi_tcxo", "bi_tcxo_ao", "sleep_clk";
+			clocks = <&rpmhcc RPMH_CXO_CLK>,
+				 <&rpmhcc RPMH_CXO_CLK_A>,
+				 <&sleep_clk>,
+				 <&pcie_phy>,
+				 <0>;
+			clock-names = "bi_tcxo",
+				      "bi_tcxo_ao",
+				      "sleep_clk",
+				      "pcie_pipe_clk",
+				      "usb3_phy_wrapper_gcc_usb30_pipe_clk";
 			#power-domain-cells = <1>;
 			#clock-cells = <1>;
 			#reset-cells = <1>;
@@ -233,32 +241,27 @@
 
 		usb_qmpphy: phy@ff6000 {
 			compatible = "qcom,sdx65-qmp-usb3-uni-phy";
-			reg = <0x00ff6000 0x1c8>;
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges;
+			reg = <0x00ff6000 0x2000>;
 
 			clocks = <&gcc GCC_USB3_PHY_AUX_CLK>,
+				 <&gcc GCC_USB3_PRIM_CLKREF_EN>,
 				 <&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>,
-				 <&gcc GCC_USB3_PRIM_CLKREF_EN>;
-			clock-names = "aux", "cfg_ahb", "ref";
+				 <&gcc GCC_USB3_PHY_PIPE_CLK>;
+			clock-names = "aux",
+				      "ref",
+				      "cfg_ahb",
+				      "pipe";
+			clock-output-names = "usb3_uni_phy_pipe_clk_src";
+			#clock-cells = <0>;
+			#phy-cells = <0>;
 
-			resets = <&gcc GCC_USB3PHY_PHY_BCR>,
-				 <&gcc GCC_USB3_PHY_BCR>;
-			reset-names = "phy", "common";
+			resets = <&gcc GCC_USB3_PHY_BCR>,
+				 <&gcc GCC_USB3PHY_PHY_BCR>;
+			reset-names = "phy",
+				      "phy_phy";
 
 			status = "disabled";
 
-			usb_ssphy: phy@ff6200 {
-				reg = <0x00ff6e00 0x160>,
-				      <0x00ff7000 0x1ec>,
-				      <0x00ff6200 0x1e00>;
-				#phy-cells = <0>;
-				#clock-cells = <0>;
-				clocks = <&gcc GCC_USB3_PHY_PIPE_CLK>;
-				clock-names = "pipe0";
-				clock-output-names = "usb3_uni_phy_pipe_clk_src";
-			};
 		};
 
 		system_noc: interconnect@1620000 {
@@ -338,7 +341,7 @@
 			power-domains = <&gcc PCIE_GDSC>;
 
 			phys = <&pcie_phy>;
-			phy-names = "pcie-phy";
+			phy-names = "pciephy";
 
 			max-link-speed = <3>;
 			num-lanes = <2>;
@@ -520,7 +523,7 @@
 				iommus = <&apps_smmu 0x1a0 0x0>;
 				snps,dis_u2_susphy_quirk;
 				snps,dis_enblslpm_quirk;
-				phys = <&usb_hsphy>, <&usb_ssphy>;
+				phys = <&usb_hsphy>, <&usb_qmpphy>;
 				phy-names = "usb2-phy", "usb3-phy";
 			};
 		};
@@ -530,7 +533,7 @@
 			reg = <0x0c264000 0x1000>;
 		};
 
-		spmi_bus: qcom,spmi@c440000 {
+		spmi_bus: spmi@c440000 {
 			compatible = "qcom,spmi-pmic-arb";
 			reg = <0xc440000 0xd00>,
 				<0xc600000 0x2000000>,
diff --git a/arch/arm/boot/dts/renesas/iwg20d-q7-dbcm-ca.dtsi b/arch/arm/boot/dts/renesas/iwg20d-q7-dbcm-ca.dtsi
index e10f99278c77..de52218ceaa4 100644
--- a/arch/arm/boot/dts/renesas/iwg20d-q7-dbcm-ca.dtsi
+++ b/arch/arm/boot/dts/renesas/iwg20d-q7-dbcm-ca.dtsi
@@ -27,6 +27,15 @@
 			};
 		};
 	};
+
+	reg_1p8v: regulator-1p8v {
+		compatible = "regulator-fixed";
+		regulator-name = "1P8V";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
 };
 
 &can1 {
@@ -69,6 +78,12 @@
 		clocks = <&cec_clock>;
 		clock-names = "cec";
 
+		avdd-supply = <&reg_1p8v>;
+		dvdd-supply = <&reg_1p8v>;
+		pvdd-supply = <&reg_1p8v>;
+		dvdd-3v-supply = <&reg_3p3v>;
+		bgvdd-supply = <&reg_1p8v>;
+
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
 		adi,input-clock = "1x";
diff --git a/arch/arm/boot/dts/renesas/r8a7740-armadillo800eva.dts b/arch/arm/boot/dts/renesas/r8a7740-armadillo800eva.dts
index d21e00e1f401..e1ac2c161e73 100644
--- a/arch/arm/boot/dts/renesas/r8a7740-armadillo800eva.dts
+++ b/arch/arm/boot/dts/renesas/r8a7740-armadillo800eva.dts
@@ -132,7 +132,7 @@
 		i2c-gpio,delay-us = <5>;
 	};
 
-	backlight {
+	backlight: backlight {
 		compatible = "pwm-backlight";
 		pwms = <&tpu 2 33333 PWM_POLARITY_INVERTED>;
 		brightness-levels = <0 1 2 4 8 16 32 64 128 255>;
@@ -143,6 +143,18 @@
 		enable-gpios = <&pfc 61 GPIO_ACTIVE_HIGH>;
 	};
 
+	panel {
+		compatible = "ampire,am-800480l1tmqw-t00h";
+		backlight = <&backlight>;
+		power-supply = <&reg_5p0v>;
+
+		port {
+			panel_in: endpoint {
+				remote-endpoint = <&lcdc0_rgb>;
+			};
+		};
+	};
+
 	sound {
 		compatible = "simple-audio-card";
 
@@ -228,10 +240,22 @@
 	};
 };
 
-&pfc {
+&lcdc0 {
 	pinctrl-0 = <&lcd0_pins>;
 	pinctrl-names = "default";
 
+	status = "okay";
+
+	ports {
+		port@0 {
+			endpoint {
+				remote-endpoint = <&panel_in>;
+			};
+		};
+	};
+};
+
+&pfc {
 	ether_pins: ether {
 		groups = "gether_mii", "gether_int";
 		function = "gether";
diff --git a/arch/arm/boot/dts/renesas/r8a7740.dtsi b/arch/arm/boot/dts/renesas/r8a7740.dtsi
index 1b2cf5fa322b..55884ec701f8 100644
--- a/arch/arm/boot/dts/renesas/r8a7740.dtsi
+++ b/arch/arm/boot/dts/renesas/r8a7740.dtsi
@@ -398,6 +398,61 @@
 		status = "disabled";
 	};
 
+	lcdc0: lcd-controller@fe940000 {
+		compatible = "renesas,r8a7740-lcdc";
+		reg = <0xfe940000 0x4000>;
+		interrupts = <GIC_SPI 177 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp1_clks R8A7740_CLK_LCDC0>,
+			 <&cpg_clocks R8A7740_CLK_M3>, <&lcdlclk0_clk>,
+			 <&vou_clk>;
+		clock-names = "fck", "media", "lclk", "video";
+		power-domains = <&pd_a4lc>;
+		status = "disabled";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				lcdc0_rgb: endpoint {
+				};
+			};
+		};
+	};
+
+	lcdc1: lcd-controller@fe944000 {
+		compatible = "renesas,r8a7740-lcdc";
+		reg = <0xfe944000 0x4000>;
+		interrupts = <GIC_SPI 178 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp1_clks R8A7740_CLK_LCDC1>,
+			 <&cpg_clocks R8A7740_CLK_M3>, <&lcdlclk1_clk>,
+			 <&vou_clk>;
+		clock-names = "fck", "media", "lclk", "video";
+		power-domains = <&pd_a4lc>;
+		status = "disabled";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				lcdc1_rgb: endpoint {
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				lcdc1_hdmi: endpoint {
+				};
+			};
+		};
+	};
+
 	tmu0: timer@fff80000 {
 		compatible = "renesas,tmu-r8a7740", "renesas,tmu";
 		reg = <0xfff80000 0x2c>;
@@ -474,6 +529,16 @@
 			#clock-cells = <0>;
 			clock-frequency = <0>;
 		};
+		lcdlclk0_clk: lcdlclk0 {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <0>;
+		};
+		lcdlclk1_clk: lcdlclk1 {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <0>;
+		};
 
 		/* Special CPG clocks */
 		cpg_clocks: cpg_clocks@e6150000 {
diff --git a/arch/arm/boot/dts/renesas/r8a7745-iwg22d-sodimm-dbhd-ca.dts b/arch/arm/boot/dts/renesas/r8a7745-iwg22d-sodimm-dbhd-ca.dts
index b1f679da36b2..a0b574398055 100644
--- a/arch/arm/boot/dts/renesas/r8a7745-iwg22d-sodimm-dbhd-ca.dts
+++ b/arch/arm/boot/dts/renesas/r8a7745-iwg22d-sodimm-dbhd-ca.dts
@@ -34,6 +34,15 @@
 			};
 		};
 	};
+
+	reg_1p8v: regulator-1p8v {
+		compatible = "regulator-fixed";
+		regulator-name = "1P8V";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
 };
 
 &du {
@@ -81,6 +90,12 @@
 		clock-names = "cec";
 		pd-gpios = <&gpio2 24 GPIO_ACTIVE_HIGH>;
 
+		avdd-supply = <&reg_1p8v>;
+		dvdd-supply = <&reg_1p8v>;
+		pvdd-supply = <&reg_1p8v>;
+		dvdd-3v-supply = <&reg_3p3v>;
+		bgvdd-supply = <&reg_1p8v>;
+
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
 		adi,input-clock = "1x";
diff --git a/arch/arm/boot/dts/renesas/r8a7745-iwg22d-sodimm.dts b/arch/arm/boot/dts/renesas/r8a7745-iwg22d-sodimm.dts
index c105932f642e..24411044ef6c 100644
--- a/arch/arm/boot/dts/renesas/r8a7745-iwg22d-sodimm.dts
+++ b/arch/arm/boot/dts/renesas/r8a7745-iwg22d-sodimm.dts
@@ -182,7 +182,7 @@
 		VDDIO-supply = <&reg_3p3v>;
 	};
 
-	stmpe811@44 {
+	port-expander@44 {
 		compatible = "st,stmpe811";
 		reg = <0x44>;
 		interrupt-parent = <&gpio4>;
@@ -197,7 +197,7 @@
 		/* internal ADC reference */
 		st,ref-sel = <0>;
 
-		stmpe_touchscreen {
+		touchscreen {
 			compatible = "st,stmpe-ts";
 			/* 8 sample average control */
 			st,ave-ctrl = <3>;
diff --git a/arch/arm/boot/dts/renesas/r8a7779-marzen.dts b/arch/arm/boot/dts/renesas/r8a7779-marzen.dts
index 08ea149b1ee6..9b13e8d1538b 100644
--- a/arch/arm/boot/dts/renesas/r8a7779-marzen.dts
+++ b/arch/arm/boot/dts/renesas/r8a7779-marzen.dts
@@ -52,10 +52,10 @@
 		states = <3300000 1>, <1800000 0>;
 	};
 
-	keyboard-irq {
+	keypad-0 {
 		compatible = "gpio-keys";
 
-		pinctrl-0 = <&keyboard_irq_pins>;
+		pinctrl-0 = <&keypad0_pins>;
 		pinctrl-names = "default";
 
 		interrupt-parent = <&gpio0>;
@@ -76,11 +76,11 @@
 		};
 	};
 
-	keyboard-gpio {
+	keypad-1 {
 		compatible = "gpio-keys-polled";
 		poll-interval = <50>;
 
-		pinctrl-0 = <&keyboard_gpio_pins>;
+		pinctrl-0 = <&keypad1_pins>;
 		pinctrl-names = "default";
 
 		key-3 {
@@ -193,7 +193,7 @@
 };
 
 &gpio0 {
-	keyboard-irq-hog {
+	keypad0-hog {
 		gpio-hog;
 		gpios = <17 GPIO_ACTIVE_LOW>, <18 GPIO_ACTIVE_LOW>;
 		input;
@@ -215,6 +215,35 @@
 };
 
 &lbsc {
+	flash@0 {
+		compatible = "cfi-flash";
+		reg = <0x0 0x04000000>;
+		pinctrl-0 = <&flash_pins>;
+		pinctrl-names = "default";
+		bank-width = <2>;
+
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			partition@0 {
+				label = "uboot";
+				reg = <0x00000000 0x00040000>;
+				read-only;
+			};
+			partition@40000 {
+				label = "uboot-env";
+				reg = <0x00040000 0x00040000>;
+				read-only;
+			};
+			partition@80000 {
+				label = "flash";
+				reg = <0x00080000 0x03f80000>;
+			};
+		};
+	};
+
 	ethernet@18000000 {
 		compatible = "smsc,lan89218", "smsc,lan9115";
 		reg = <0x18000000 0x100>;
@@ -266,6 +295,11 @@
 		};
 	};
 
+	flash_pins: flash {
+		groups = "lbsc_cs0";
+		function = "lbsc";
+	};
+
 	scif2_pins: scif2 {
 		groups = "scif2_data_c";
 		function = "scif2";
@@ -286,11 +320,11 @@
 		function = "hspi0";
 	};
 
-	keyboard_irq_pins: keyboard-irq {
+	keypad0_pins: keypad-0 {
 		pins = "GP_0_17", "GP_0_18";
 		bias-pull-up;
 	};
-	keyboard_gpio_pins: keyboard-gpio {
+	keypad1_pins: keypad-1 {
 		pins = "GP_0_19", "GP_0_20";
 		bias-pull-up;
 	};
diff --git a/arch/arm/boot/dts/renesas/r8a7790-lager.dts b/arch/arm/boot/dts/renesas/r8a7790-lager.dts
index 4d666ad8b114..2fba4d084001 100644
--- a/arch/arm/boot/dts/renesas/r8a7790-lager.dts
+++ b/arch/arm/boot/dts/renesas/r8a7790-lager.dts
@@ -122,6 +122,15 @@
 		};
 	};
 
+	fixedregulator1v8: regulator-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-1.8V";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+
 	fixedregulator3v3: regulator-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "fixed-3.3V";
@@ -303,7 +312,7 @@
 	 *
 	 * IIC0/I2C0 does not appear to support fallback to GPIO.
 	 */
-	i2cexio0: i2c-10 {
+	i2cexio0: i2c-mux1 {
 		compatible = "i2c-demux-pinctrl";
 		i2c-parent = <&iic0>, <&i2c0>;
 		i2c-bus-name = "i2c-exio0";
@@ -316,7 +325,7 @@
 	 * This is similar to the arangement described for i2cexio0 (above)
 	 * with a fallback to GPIO also provided.
 	 */
-	i2cexio1: i2c-11 {
+	i2cexio1: i2c-mux2 {
 		compatible = "i2c-demux-pinctrl";
 		i2c-parent = <&iic1>, <&i2c1>, <&gpioi2c1>;
 		i2c-bus-name = "i2c-exio1";
@@ -328,7 +337,7 @@
 	 * IIC2 and I2C2 may be switched using pinmux.
 	 * A fallback to GPIO is also provided.
 	 */
-	i2chdmi: i2c-12 {
+	i2chdmi: i2c-mux3 {
 		compatible = "i2c-demux-pinctrl";
 		i2c-parent = <&iic2>, <&i2c2>, <&gpioi2c2>;
 		i2c-bus-name = "i2c-hdmi";
@@ -361,6 +370,12 @@
 			clocks = <&cec_clock>;
 			clock-names = "cec";
 
+			avdd-supply = <&fixedregulator1v8>;
+			dvdd-supply = <&fixedregulator1v8>;
+			pvdd-supply = <&fixedregulator1v8>;
+			dvdd-3v-supply = <&fixedregulator3v3>;
+			bgvdd-supply = <&fixedregulator1v8>;
+
 			adi,input-depth = <8>;
 			adi,input-colorspace = "rgb";
 			adi,input-clock = "1x";
@@ -417,7 +432,7 @@
 	 * IIC3 and I2C3 may be switched using pinmux.
 	 * IIC3/I2C3 does not appear to support fallback to GPIO.
 	 */
-	i2cpwr: i2c-13 {
+	i2cpwr: i2c-mux4 {
 		compatible = "i2c-demux-pinctrl";
 		pinctrl-names = "default";
 		pinctrl-0 = <&pmic_irq_pins>;
diff --git a/arch/arm/boot/dts/renesas/r8a7790-stout.dts b/arch/arm/boot/dts/renesas/r8a7790-stout.dts
index fe14727eefe1..f9bc5b4f019d 100644
--- a/arch/arm/boot/dts/renesas/r8a7790-stout.dts
+++ b/arch/arm/boot/dts/renesas/r8a7790-stout.dts
@@ -44,6 +44,15 @@
 		};
 	};
 
+	fixedregulator1v8: regulator-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-1.8V";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+
 	fixedregulator3v3: regulator-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "fixed-3.3V";
@@ -296,6 +305,12 @@
 		clocks = <&osc4_clk>;
 		clock-names = "cec";
 
+		avdd-supply = <&fixedregulator1v8>;
+		dvdd-supply = <&fixedregulator1v8>;
+		pvdd-supply = <&fixedregulator1v8>;
+		dvdd-3v-supply = <&fixedregulator3v3>;
+		bgvdd-supply = <&fixedregulator1v8>;
+
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
 		adi,input-clock = "1x";
diff --git a/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts b/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts
index 545515b41ea3..e9c13bb03772 100644
--- a/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts
+++ b/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts
@@ -174,6 +174,24 @@
 		};
 	};
 
+	reg_1p8v: regulator-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-1.8V";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+
+	reg_3p3v: regulator-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-3.3V";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+
 	vcc_sdhi0: regulator-vcc-sdhi0 {
 		compatible = "regulator-fixed";
 
@@ -340,7 +358,7 @@
 	 * I2C1 is routed to EXIO connector B, pins 64 (SCL) + 66 (SDA).
 	 * A fallback to GPIO is provided.
 	 */
-	i2cexio1: i2c-12 {
+	i2cexio1: i2c-mux1 {
 		compatible = "i2c-demux-pinctrl";
 		i2c-parent = <&i2c1>, <&gpioi2c1>;
 		i2c-bus-name = "i2c-exio1";
@@ -351,7 +369,7 @@
 	/*
 	 * A fallback to GPIO is provided for I2C2.
 	 */
-	i2chdmi: i2c-13 {
+	i2chdmi: i2c-mux2 {
 		compatible = "i2c-demux-pinctrl";
 		i2c-parent = <&i2c2>, <&gpioi2c2>;
 		i2c-bus-name = "i2c-hdmi";
@@ -384,6 +402,12 @@
 			clocks = <&cec_clock>;
 			clock-names = "cec";
 
+			avdd-supply = <&reg_1p8v>;
+			dvdd-supply = <&reg_1p8v>;
+			pvdd-supply = <&reg_1p8v>;
+			dvdd-3v-supply = <&reg_3p3v>;
+			bgvdd-supply = <&reg_1p8v>;
+
 			adi,input-depth = <8>;
 			adi,input-colorspace = "rgb";
 			adi,input-clock = "1x";
@@ -446,7 +470,7 @@
 	 * I2C4 is routed to EXIO connector E, pins 37 (SCL) + 39 (SDA).
 	 * A fallback to GPIO is provided.
 	 */
-	i2cexio4: i2c-14 {
+	i2cexio4: i2c-mux3 {
 		compatible = "i2c-demux-pinctrl";
 		i2c-parent = <&i2c4>, <&gpioi2c4>;
 		i2c-bus-name = "i2c-exio4";
diff --git a/arch/arm/boot/dts/renesas/r8a7791-porter.dts b/arch/arm/boot/dts/renesas/r8a7791-porter.dts
index ec0a20d5130d..7e8bc06715f6 100644
--- a/arch/arm/boot/dts/renesas/r8a7791-porter.dts
+++ b/arch/arm/boot/dts/renesas/r8a7791-porter.dts
@@ -47,6 +47,24 @@
 		reg = <2 0x00000000 0 0x40000000>;
 	};
 
+	reg_1p8v: regulator-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-1.8V";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+
+	reg_3p3v: regulator-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-3.3V";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+
 	vcc_sdhi0: regulator-vcc-sdhi0 {
 		compatible = "regulator-fixed";
 
@@ -148,7 +166,7 @@
 	/*
 	 * A fallback to GPIO is provided for I2C2.
 	 */
-	i2chdmi: i2c-10 {
+	i2chdmi: i2c-mux1 {
 		compatible = "i2c-demux-pinctrl";
 		i2c-parent = <&i2c2>, <&gpioi2c2>;
 		i2c-bus-name = "i2c-hdmi";
@@ -179,6 +197,12 @@
 			interrupt-parent = <&gpio3>;
 			interrupts = <29 IRQ_TYPE_LEVEL_LOW>;
 
+			avdd-supply = <&reg_1p8v>;
+			dvdd-supply = <&reg_1p8v>;
+			pvdd-supply = <&reg_1p8v>;
+			dvdd-3v-supply = <&reg_3p3v>;
+			bgvdd-supply = <&reg_1p8v>;
+
 			adi,input-depth = <8>;
 			adi,input-colorspace = "rgb";
 			adi,input-clock = "1x";
diff --git a/arch/arm/boot/dts/renesas/r8a7792-blanche.dts b/arch/arm/boot/dts/renesas/r8a7792-blanche.dts
index e793134f32a3..4f9838cf97ee 100644
--- a/arch/arm/boot/dts/renesas/r8a7792-blanche.dts
+++ b/arch/arm/boot/dts/renesas/r8a7792-blanche.dts
@@ -30,6 +30,15 @@
 		reg = <0 0x40000000 0 0x40000000>;
 	};
 
+	d1_8v: regulator-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "D1.8V";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+
 	d3_3v: regulator-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "D3.3V";
@@ -182,6 +191,35 @@
 };
 
 &lbsc {
+	flash@0 {
+		compatible = "cfi-flash";
+		reg = <0x00000000 0x04000000>;
+		pinctrl-0 = <&flash_pins>;
+		pinctrl-names = "default";
+		bank-width = <2>;
+
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			partition@0 {
+				label = "uboot";
+				reg = <0x00000000 0x00040000>;
+				read-only;
+			};
+			partition@40000 {
+				label = "uboot-env";
+				reg = <0x00040000 0x00040000>;
+				read-only;
+			};
+			partition@80000 {
+				label = "flash";
+				reg = <0x00080000 0x03f80000>;
+			};
+		};
+	};
+
 	ethernet@18000000 {
 		compatible = "smsc,lan89218", "smsc,lan9115";
 		reg = <0x18000000 0x100>;
@@ -240,6 +278,11 @@
 		function = "du1";
 	};
 
+	flash_pins: flash {
+		groups = "lbsc_cs0";
+		function = "lbsc";
+	};
+
 	keyboard_pins: keyboard {
 		pins = "GP_3_10", "GP_3_11", "GP_3_12", "GP_3_15", "GP_11_2";
 		bias-pull-up;
@@ -296,6 +339,12 @@
 		interrupt-parent = <&irqc>;
 		interrupts = <3 IRQ_TYPE_EDGE_FALLING>;
 
+		avdd-supply = <&d1_8v>;
+		dvdd-supply = <&d1_8v>;
+		pvdd-supply = <&d1_8v>;
+		dvdd-3v-supply = <&d3_3v>;
+		bgvdd-supply = <&d1_8v>;
+
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
 		adi,input-clock = "1x";
diff --git a/arch/arm/boot/dts/renesas/r8a7792-wheat.dts b/arch/arm/boot/dts/renesas/r8a7792-wheat.dts
index f87e78fe3f6e..000f21a2a863 100644
--- a/arch/arm/boot/dts/renesas/r8a7792-wheat.dts
+++ b/arch/arm/boot/dts/renesas/r8a7792-wheat.dts
@@ -29,6 +29,15 @@
 		reg = <0 0x40000000 0 0x40000000>;
 	};
 
+	d1_8v: regulator-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "D1.8V";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+
 	d3_3v: regulator-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "D3.3V";
@@ -254,6 +263,12 @@
 		reg = <0x3d>, <0x4d>, <0x2d>, <0x5d>;
 		reg-names = "main", "edid", "cec", "packet";
 
+		avdd-supply = <&d1_8v>;
+		dvdd-supply = <&d1_8v>;
+		pvdd-supply = <&d1_8v>;
+		dvdd-3v-supply = <&d3_3v>;
+		bgvdd-supply = <&d1_8v>;
+
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
 		adi,input-clock = "1x";
@@ -283,6 +298,12 @@
 		reg = <0x39>, <0x49>, <0x29>, <0x59>;
 		reg-names = "main", "edid", "cec", "packet";
 
+		avdd-supply = <&d1_8v>;
+		dvdd-supply = <&d1_8v>;
+		pvdd-supply = <&d1_8v>;
+		dvdd-3v-supply = <&d3_3v>;
+		bgvdd-supply = <&d1_8v>;
+
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
 		adi,input-clock = "1x";
diff --git a/arch/arm/boot/dts/renesas/r8a7793-gose.dts b/arch/arm/boot/dts/renesas/r8a7793-gose.dts
index 79b537b24642..1744fdbf9e0c 100644
--- a/arch/arm/boot/dts/renesas/r8a7793-gose.dts
+++ b/arch/arm/boot/dts/renesas/r8a7793-gose.dts
@@ -165,6 +165,24 @@
 		};
 	};
 
+	reg_1p8v: regulator-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-1.8V";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+
+	reg_3p3v: regulator-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-3.3V";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+
 	vcc_sdhi0: regulator-vcc-sdhi0 {
 		compatible = "regulator-fixed";
 
@@ -324,7 +342,7 @@
 	/*
 	 * A fallback to GPIO is provided for I2C2.
 	 */
-	i2chdmi: i2c-11 {
+	i2chdmi: i2c-mux1 {
 		compatible = "i2c-demux-pinctrl";
 		i2c-parent = <&i2c2>, <&gpioi2c2>;
 		i2c-bus-name = "i2c-hdmi";
@@ -368,6 +386,12 @@
 			interrupt-parent = <&gpio3>;
 			interrupts = <29 IRQ_TYPE_LEVEL_LOW>;
 
+			avdd-supply = <&reg_1p8v>;
+			dvdd-supply = <&reg_1p8v>;
+			pvdd-supply = <&reg_1p8v>;
+			dvdd-3v-supply = <&reg_3p3v>;
+			bgvdd-supply = <&reg_1p8v>;
+
 			adi,input-depth = <8>;
 			adi,input-colorspace = "rgb";
 			adi,input-clock = "1x";
@@ -430,7 +454,7 @@
 	 * I2C4 is routed to EXIO connector E, pins 37 (SCL) + 39 (SDA).
 	 * A fallback to GPIO is provided.
 	 */
-	i2cexio4: i2c-12 {
+	i2cexio4: i2c-mux2 {
 		compatible = "i2c-demux-pinctrl";
 		i2c-parent = <&i2c4>, <&gpioi2c4>;
 		i2c-bus-name = "i2c-exio4";
diff --git a/arch/arm/boot/dts/renesas/r8a7794-alt.dts b/arch/arm/boot/dts/renesas/r8a7794-alt.dts
index 08df031bc27c..c0d067df22a0 100644
--- a/arch/arm/boot/dts/renesas/r8a7794-alt.dts
+++ b/arch/arm/boot/dts/renesas/r8a7794-alt.dts
@@ -192,7 +192,7 @@
 	/*
 	 * A fallback to GPIO is provided for I2C1.
 	 */
-	i2chdmi: i2c-11 {
+	i2chdmi: i2c-mux1 {
 		compatible = "i2c-demux-pinctrl";
 		i2c-parent = <&i2c1>, <&gpioi2c1>;
 		i2c-bus-name = "i2c-hdmi";
@@ -222,7 +222,7 @@
 	 * I2C4 is routed to EXIO connector B, pins 73 (SCL) + 74 (SDA).
 	 * A fallback to GPIO is provided.
 	 */
-	i2cexio4: i2c-14 {
+	i2cexio4: i2c-mux2 {
 		compatible = "i2c-demux-pinctrl";
 		i2c-parent = <&i2c4>, <&gpioi2c4>;
 		i2c-bus-name = "i2c-exio4";
diff --git a/arch/arm/boot/dts/renesas/r8a7794-silk.dts b/arch/arm/boot/dts/renesas/r8a7794-silk.dts
index b7af1befa126..43d480a7f3ea 100644
--- a/arch/arm/boot/dts/renesas/r8a7794-silk.dts
+++ b/arch/arm/boot/dts/renesas/r8a7794-silk.dts
@@ -102,6 +102,15 @@
 		};
 	};
 
+	d1_8v: regulator-d1-8v {
+		compatible = "regulator-fixed";
+		regulator-name = "D1.8V";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+
 	d3_3v: regulator-d3-3v {
 		compatible = "regulator-fixed";
 		regulator-name = "D3.3V";
@@ -225,7 +234,7 @@
 	/*
 	 * A fallback to GPIO is provided for I2C1.
 	 */
-	i2chdmi: i2c-10 {
+	i2chdmi: i2c-mux1 {
 		compatible = "i2c-demux-pinctrl";
 		i2c-parent = <&i2c1>, <&gpioi2c1>;
 		i2c-bus-name = "i2c-hdmi";
@@ -256,6 +265,12 @@
 			interrupt-parent = <&gpio5>;
 			interrupts = <23 IRQ_TYPE_LEVEL_LOW>;
 
+			avdd-supply = <&d1_8v>;
+			dvdd-supply = <&d1_8v>;
+			pvdd-supply = <&d1_8v>;
+			dvdd-3v-supply = <&d3_3v>;
+			bgvdd-supply = <&d1_8v>;
+
 			adi,input-depth = <8>;
 			adi,input-colorspace = "rgb";
 			adi,input-clock = "1x";
diff --git a/arch/arm/boot/dts/renesas/r9a06g032.dtsi b/arch/arm/boot/dts/renesas/r9a06g032.dtsi
index 0fa565a1c3ad..fa63e1afc4ef 100644
--- a/arch/arm/boot/dts/renesas/r9a06g032.dtsi
+++ b/arch/arm/boot/dts/renesas/r9a06g032.dtsi
@@ -437,7 +437,7 @@
 		};
 
 		can0: can@52104000 {
-			compatible = "renesas,r9a06g032-sja1000","renesas,rzn1-sja1000";
+			compatible = "renesas,r9a06g032-sja1000", "renesas,rzn1-sja1000";
 			reg = <0x52104000 0x800>;
 			reg-io-width = <4>;
 			interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/boot/dts/rockchip/Makefile b/arch/arm/boot/dts/rockchip/Makefile
index 0f46e18fe275..ab4cd9aab722 100644
--- a/arch/arm/boot/dts/rockchip/Makefile
+++ b/arch/arm/boot/dts/rockchip/Makefile
@@ -2,7 +2,9 @@
 dtb-$(CONFIG_ARCH_ROCKCHIP) += \
 	rv1108-elgin-r1.dtb \
 	rv1108-evb.dtb \
+	rv1109-sonoff-ihost.dtb \
 	rv1126-edgeble-neu2-io.dtb \
+	rv1126-sonoff-ihost.dtb \
 	rk3036-evb.dtb \
 	rk3036-kylin.dtb \
 	rk3066a-bqcurie2.dtb \
@@ -10,6 +12,7 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += \
 	rk3066a-mk808.dtb \
 	rk3066a-rayeager.dtb \
 	rk3128-evb.dtb \
+	rk3128-xpi-3128.dtb \
 	rk3188-bqedison2qc.dtb \
 	rk3188-px3-evb.dtb \
 	rk3188-radxarock.dtb \
diff --git a/arch/arm/boot/dts/rockchip/rk3036-kylin.dts b/arch/arm/boot/dts/rockchip/rk3036-kylin.dts
index 67e1e04139e7..e32c73d32f0a 100644
--- a/arch/arm/boot/dts/rockchip/rk3036-kylin.dts
+++ b/arch/arm/boot/dts/rockchip/rk3036-kylin.dts
@@ -8,11 +8,26 @@
 	model = "Rockchip RK3036 KylinBoard";
 	compatible = "rockchip,rk3036-kylin", "rockchip,rk3036";
 
+	chosen {
+		stdout-path = "serial2:115200n8";
+	};
+
 	memory@60000000 {
 		device_type = "memory";
 		reg = <0x60000000 0x20000000>;
 	};
 
+	hdmi_con: hdmi-con {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi_con_in: endpoint {
+				remote-endpoint = <&hdmi_out_con>;
+			};
+		};
+	};
+
 	leds: gpio-leds {
 		compatible = "gpio-leds";
 
@@ -110,6 +125,12 @@
 	status = "okay";
 };
 
+&hdmi_out {
+	hdmi_out_con: endpoint {
+		remote-endpoint = <&hdmi_con_in>;
+	};
+};
+
 &i2c1 {
 	clock-frequency = <400000>;
 
diff --git a/arch/arm/boot/dts/rockchip/rk3036.dtsi b/arch/arm/boot/dts/rockchip/rk3036.dtsi
index 78686fc72ce6..04af224005f8 100644
--- a/arch/arm/boot/dts/rockchip/rk3036.dtsi
+++ b/arch/arm/boot/dts/rockchip/rk3036.dtsi
@@ -17,6 +17,9 @@
 	interrupt-parent = <&gic>;
 
 	aliases {
+		gpio0 = &gpio0;
+		gpio1 = &gpio1;
+		gpio2 = &gpio2;
 		i2c0 = &i2c0;
 		i2c1 = &i2c1;
 		i2c2 = &i2c2;
@@ -282,7 +285,6 @@
 		clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>,
 			 <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>;
 		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
-		rockchip,default-sample-phase = <158>;
 		disable-wp;
 		dmas = <&pdma 12>;
 		dma-names = "rx-tx";
@@ -402,12 +404,20 @@
 		pinctrl-0 = <&hdmi_ctl>;
 		status = "disabled";
 
-		hdmi_in: port {
+		ports {
 			#address-cells = <1>;
 			#size-cells = <0>;
-			hdmi_in_vop: endpoint@0 {
+
+			hdmi_in: port@0 {
 				reg = <0>;
-				remote-endpoint = <&vop_out_hdmi>;
+
+				hdmi_in_vop: endpoint {
+					remote-endpoint = <&vop_out_hdmi>;
+				};
+			};
+
+			hdmi_out: port@1 {
+				reg = <1>;
 			};
 		};
 	};
diff --git a/arch/arm/boot/dts/rockchip/rk3066a.dtsi b/arch/arm/boot/dts/rockchip/rk3066a.dtsi
index de9915d946f7..30139f21de64 100644
--- a/arch/arm/boot/dts/rockchip/rk3066a.dtsi
+++ b/arch/arm/boot/dts/rockchip/rk3066a.dtsi
@@ -13,6 +13,11 @@
 / {
 	compatible = "rockchip,rk3066a";
 
+	aliases {
+		gpio4 = &gpio4;
+		gpio6 = &gpio6;
+	};
+
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
diff --git a/arch/arm/boot/dts/rockchip/rk3128-evb.dts b/arch/arm/boot/dts/rockchip/rk3128-evb.dts
index c38f42497cbd..c7ab7fcdb436 100644
--- a/arch/arm/boot/dts/rockchip/rk3128-evb.dts
+++ b/arch/arm/boot/dts/rockchip/rk3128-evb.dts
@@ -12,11 +12,6 @@
 	compatible = "rockchip,rk3128-evb", "rockchip,rk3128";
 
 	aliases {
-		gpio0 = &gpio0;
-		gpio1 = &gpio1;
-		gpio2 = &gpio2;
-		gpio3 = &gpio3;
-		i2c1 = &i2c1;
 		mmc0 = &emmc;
 	};
 
diff --git a/arch/arm/boot/dts/rockchip/rk3128-xpi-3128.dts b/arch/arm/boot/dts/rockchip/rk3128-xpi-3128.dts
new file mode 100644
index 000000000000..03a97881519a
--- /dev/null
+++ b/arch/arm/boot/dts/rockchip/rk3128-xpi-3128.dts
@@ -0,0 +1,425 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+/dts-v1/;
+
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
+#include "rk3128.dtsi"
+
+/ {
+	model = "Geniatech XPI-3128";
+	compatible = "geniatech,xpi-3128", "rockchip,rk3128";
+
+	aliases {
+		ethernet0 = &gmac;
+		mmc0 = &emmc;
+		mmc1 = &sdmmc;
+	};
+
+	memory@60000000 {
+		device_type = "memory";
+		reg = <0x60000000 0x40000000>;
+	};
+
+	chosen {
+		stdout-path = &uart1;
+	};
+
+	adc-keys {
+		compatible = "adc-keys";
+		io-channels = <&saradc 1>;
+		io-channel-names = "buttons";
+		keyup-threshold-microvolt = <3300000>;
+
+		button-recovery {
+			label = "Recovery";
+			linux,code = <KEY_VENDOR>;
+			press-threshold-microvolt = <0>;
+		};
+	};
+
+	dc_5v: dc-5v-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "DC_5V";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	/*
+	 * This is a vbus-supply, which also supplies the GL852G usb hub,
+	 * thus has to be always-on
+	 */
+	host_pwr_5v: host-pwr-5v-regulator {
+		compatible = "regulator-fixed";
+		gpio = <&gpio3 RK_PC4 GPIO_ACTIVE_HIGH>;
+		startup-delay-us = <1500>;
+		regulator-name = "HOST_PWR_5V";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&dc_5v>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&host_drv>;
+		enable-active-high;
+		regulator-always-on;
+	};
+
+	ir-receiver {
+		compatible = "gpio-ir-receiver";
+		gpios = <&gpio3 RK_PD2 GPIO_ACTIVE_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&ir_int>;
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		led-power {
+			gpios = <&gpio0 RK_PD2 GPIO_ACTIVE_HIGH>;
+			function = LED_FUNCTION_POWER;
+			color = <LED_COLOR_ID_BLUE>;
+			default-state = "on";
+			pinctrl-names = "default";
+			pinctrl-0 = <&power_led>;
+		};
+
+		led-spd {
+			gpios = <&gpio3 RK_PB3 GPIO_ACTIVE_LOW>;
+			function = LED_FUNCTION_LAN;
+			color = <LED_COLOR_ID_GREEN>;
+			/*
+			 * currently not allowed to be set as per
+			 * https://www.kernel.org/doc/Documentation/devicetree/bindings/leds/common.yaml
+			 * and needs to set in userspace:
+			 *
+			 * linux,default-trigger = "netdev";
+			 */
+			pinctrl-names = "default";
+			pinctrl-0 = <&spd_led>;
+		};
+	};
+
+	mcu3v3: mcu3v3-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "MCU3V3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcc_io>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	vcc_ddr: vcc-ddr-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "VCC_DDR";
+		regulator-min-microvolt = <1500000>;
+		regulator-max-microvolt = <1500000>;
+		vin-supply = <&vcc_sys>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	vcc_io: vcc-io-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "VCC_IO";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcc_sys>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	vcc_lan: vcc-lan-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "VCC_LAN";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcc_io>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	vcc_sd: vcc-sd-regulator {
+		compatible = "regulator-fixed";
+		gpio = <&gpio1 RK_PB6 GPIO_ACTIVE_LOW>;
+		startup-delay-us = <500>;
+		regulator-name = "VCC_SD";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcc_io>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&sdmmc_pwren>;
+	};
+
+	vcc_sys: vcc-sys-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "VCC_SYS";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&dc_5v>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	vcc33_hdmi: vcc33-hdmi-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "VCC33_HDMI";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcca_33>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	vcca_33: vcca-33-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "VCCA_33";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcc_sys>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	vdd_11: vdd-11-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "VDD_11";
+		regulator-min-microvolt = <1100000>;
+		regulator-max-microvolt = <1100000>;
+		vin-supply = <&vcc_sys>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	vdd11_hdmi: vdd11-hdmi-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "VDD11_HDMI";
+		regulator-min-microvolt = <1100000>;
+		regulator-max-microvolt = <1100000>;
+		vin-supply = <&vdd_11>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	vdd_arm: vdd-arm-regulator {
+		compatible = "pwm-regulator";
+		regulator-name = "VDD_ARM";
+		pwms = <&pwm1 0 25000 1>;
+		pwm-supply = <&vcc_sys>;
+		regulator-min-microvolt = <900000>;
+		regulator-max-microvolt = <1400000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	/*
+	 * As per schematics vdd_log is minimum 900 mV, maximum 1400 mV.
+	 * Since there are HW blocks in PD_LOGIC (which are all driven by
+	 * this supply), that either do not have a driver at all or the
+	 * driver does not implement regulator support we have to make
+	 * sure here that the voltage never drops below 1050 mV.
+	 */
+	vdd_log: vdd-log-regulator {
+		compatible = "pwm-regulator";
+		regulator-name = "VDD_LOG";
+		pwms = <&pwm2 0 25000 1>;
+		pwm-dutycycle-range = <30 100>;
+		pwm-supply = <&vcc_sys>;
+		regulator-min-microvolt = <1050000>;
+		regulator-max-microvolt = <1400000>;
+		regulator-ramp-delay = <4000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+};
+
+&cpu0 {
+	cpu-supply = <&vdd_arm>;
+};
+
+&emmc {
+	bus-width = <8>;
+	vmmc-supply = <&vcc_io>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&emmc_clk &emmc_cmd &emmc_bus8>;
+	cap-mmc-highspeed;
+	mmc-ddr-3_3v;
+	no-sd;
+	no-sdio;
+	status = "okay";
+};
+
+&gmac {
+	clock_in_out = "output";
+	phy-supply = <&vcc_lan>;
+	phy-mode = "rmii";
+	phy-handle = <&phy0>;
+	assigned-clocks = <&cru SCLK_MAC_SRC>;
+	assigned-clock-rates= <50000000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&rmii_pins>;
+	status = "okay";
+};
+
+&gpio0 {
+	gpio-line-names = /* GPIO0 A0-A7 */
+			  "", "", "HEADER_5", "HEADER_3",
+			  "", "", "", "",
+			  /* GPIO0 B0-B7 */
+			  "HEADER_22", "HEADER_23", "", "HEADER_19",
+			  "HEADER_26", "HEADER_21", "HEADER_24", "",
+			  /* GPIO0 C0-C7 */
+			  "", "HEADER_18", "", "",
+			  "", "", "", "",
+			  /* GPIO0 D0-D7 */
+			  "HEADER_36", "", "", "",
+			  "", "", "HEADER_13", "";
+};
+
+&gpio1 {
+	gpio-line-names = /* GPIO1 A0-A7 */
+			  "HEADER_7", "HEADER_35", "HEADER_33", "HEADER_37",
+			  "HEADER_40", "HEADER_38", "", "",
+			  /* GPIO1 B0-B7 */
+			  "HEADER_11", "", "", "HEADER_29",
+			  "HEADER_31", "", "", "",
+			  /* GPIO1 C0-C7 */
+			  "", "", "", "",
+			  "", "", "", "",
+			  /* GPIO1 D0-D7 */
+			  "", "", "", "",
+			  "", "", "", "";
+};
+
+&gpio2 {
+	gpio-line-names = /* GPIO2 A0-A7 */
+			  "", "", "", "",
+			  "", "", "", "",
+			  /* GPIO2 B0-B7 */
+			  "", "", "", "",
+			  "", "", "", "",
+			  /* GPIO2 C0-C7 */
+			  "", "", "", "",
+			  "HEADER_27", "", "", "",
+			  /* GPIO2 D0-D7 */
+			  "", "", "HEADER_8", "HEADER_10",
+			  "", "", "", "";
+};
+
+&gpio3 {
+	gpio-line-names = /* GPIO3 A0-A7 */
+			  "", "", "", "",
+			  "", "", "", "",
+			  /* GPIO3 B0-B7 */
+			  "", "", "", "",
+			  "", "", "", "",
+			  /* GPIO3 C0-C7 */
+			  "", "HEADER_32", "", "",
+			  "", "", "", "HEADER_12",
+			  /* GPIO3 D0-D7 */
+			  "", "", "", "HEADER_15",
+			  "", "", "", "";
+};
+
+&gpu {
+	mali-supply = <&vdd_log>;
+	status = "okay";
+};
+
+&mdio {
+	phy0: ethernet-phy@1 {
+		compatible = "ethernet-phy-ieee802.3-c22";
+		reg = <1>;
+		max-speed = <100>;
+		/* T2.2.4 min. 1 us */
+		reset-assert-us = <10>;
+		/* T2.2.1 + T2.2.2 + T2.2.3 min. 6.05 us */
+		reset-deassert-us = <20>;
+		reset-gpios = <&gpio2 RK_PD0 GPIO_ACTIVE_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&dp83848c_rst>;
+	};
+};
+
+&pinctrl {
+	dp83848c {
+		dp83848c_rst: dp83848c-rst {
+			rockchip,pins = <2 RK_PD0 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	ir-receiver {
+		ir_int: ir-int {
+			rockchip,pins = <3 RK_PD2 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	leds {
+		power_led: power-led {
+			rockchip,pins = <0 RK_PD2 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		spd_led: spd-led {
+			rockchip,pins = <3 RK_PB3 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	usb2 {
+		host_drv: host-drv {
+			rockchip,pins = <3 RK_PC4 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&pwm1 {
+	status = "okay";
+};
+
+&pwm2 {
+	status = "okay";
+};
+
+&saradc {
+	vref-supply = <&vcc_io>;
+	status = "okay";
+};
+
+&sdmmc {
+	bus-width = <4>;
+	vmmc-supply = <&vcc_sd>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&sdmmc_bus4 &sdmmc_clk &sdmmc_cmd &sdmmc_det>;
+	disable-wp;
+	cap-sd-highspeed;
+	no-mmc;
+	no-sdio;
+	status = "okay";
+};
+
+&uart1 {
+	status = "okay";
+};
+
+&usb_host_ehci {
+	status = "okay";
+};
+
+&usb_otg {
+	vusb_a-supply = <&vcc_io>;
+	vusb_d-supply = <&vdd_11>;
+	status = "okay";
+};
+
+&usb2phy {
+	status = "okay";
+};
+
+&usb2phy_host {
+	status = "okay";
+};
+
+&usb2phy_otg {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/rockchip/rk3128.dtsi b/arch/arm/boot/dts/rockchip/rk3128.dtsi
index 7bf557c99561..e2264c40b924 100644
--- a/arch/arm/boot/dts/rockchip/rk3128.dtsi
+++ b/arch/arm/boot/dts/rockchip/rk3128.dtsi
@@ -8,6 +8,7 @@
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/pinctrl/rockchip.h>
+#include <dt-bindings/power/rk3128-power.h>
 
 / {
 	compatible = "rockchip,rk3128";
@@ -15,6 +16,20 @@
 	#address-cells = <1>;
 	#size-cells = <1>;
 
+	aliases {
+		gpio0 = &gpio0;
+		gpio1 = &gpio1;
+		gpio2 = &gpio2;
+		gpio3 = &gpio3;
+		i2c0 = &i2c0;
+		i2c1 = &i2c1;
+		i2c2 = &i2c2;
+		i2c3 = &i2c3;
+		serial0 = &uart0;
+		serial1 = &uart1;
+		serial2 = &uart2;
+	};
+
 	arm-pmu {
 		compatible = "arm,cortex-a7-pmu";
 		interrupts = <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>,
@@ -100,6 +115,27 @@
 		};
 	};
 
+	gpu_opp_table: opp-table-1 {
+		compatible = "operating-points-v2";
+
+		opp-200000000 {
+			opp-hz = /bits/ 64 <200000000>;
+			opp-microvolt = <975000 975000 1250000>;
+		};
+		opp-300000000 {
+			opp-hz = /bits/ 64 <300000000>;
+			opp-microvolt = <1050000 1050000 1250000>;
+		};
+		opp-400000000 {
+			opp-hz = /bits/ 64 <400000000>;
+			opp-microvolt = <1150000 1150000 1250000>;
+		};
+		opp-480000000 {
+			opp-hz = /bits/ 64 <480000000>;
+			opp-microvolt = <1250000 1250000 1250000>;
+		};
+	};
+
 	timer {
 		compatible = "arm,armv7-timer";
 		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>,
@@ -130,9 +166,119 @@
 		};
 	};
 
+	gpu: gpu@10090000 {
+		compatible = "rockchip,rk3128-mali", "arm,mali-400";
+		reg = <0x10090000 0x10000>;
+		interrupts = <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "gp",
+				  "gpmmu",
+				  "pp0",
+				  "ppmmu0",
+				  "pp1",
+				  "ppmmu1";
+		clocks = <&cru ACLK_GPU>, <&cru ACLK_GPU>;
+		clock-names = "bus", "core";
+		operating-points-v2 = <&gpu_opp_table>;
+		resets = <&cru SRST_GPU>;
+		power-domains = <&power RK3128_PD_GPU>;
+		status = "disabled";
+	};
+
 	pmu: syscon@100a0000 {
 		compatible = "rockchip,rk3128-pmu", "syscon", "simple-mfd";
 		reg = <0x100a0000 0x1000>;
+
+		power: power-controller {
+			compatible = "rockchip,rk3128-power-controller";
+			#power-domain-cells = <1>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			power-domain@RK3128_PD_VIO {
+				reg = <RK3128_PD_VIO>;
+				clocks = <&cru ACLK_CIF>,
+					 <&cru HCLK_CIF>,
+					 <&cru DCLK_EBC>,
+					 <&cru HCLK_EBC>,
+					 <&cru ACLK_IEP>,
+					 <&cru HCLK_IEP>,
+					 <&cru ACLK_LCDC0>,
+					 <&cru HCLK_LCDC0>,
+					 <&cru PCLK_MIPI>,
+					 <&cru ACLK_RGA>,
+					 <&cru HCLK_RGA>,
+					 <&cru ACLK_VIO0>,
+					 <&cru ACLK_VIO1>,
+					 <&cru HCLK_VIO>,
+					 <&cru HCLK_VIO_H2P>,
+					 <&cru DCLK_VOP>,
+					 <&cru SCLK_VOP>;
+				pm_qos = <&qos_ebc>,
+					 <&qos_iep>,
+					 <&qos_lcdc>,
+					 <&qos_rga>,
+					 <&qos_vip>;
+				#power-domain-cells = <0>;
+			};
+
+			power-domain@RK3128_PD_VIDEO {
+				reg = <RK3128_PD_VIDEO>;
+				clocks = <&cru ACLK_VDPU>,
+					 <&cru HCLK_VDPU>,
+					 <&cru ACLK_VEPU>,
+					 <&cru HCLK_VEPU>,
+					 <&cru SCLK_HEVC_CORE>;
+				pm_qos = <&qos_vpu>;
+				#power-domain-cells = <0>;
+			};
+
+			power-domain@RK3128_PD_GPU {
+				reg = <RK3128_PD_GPU>;
+				clocks = <&cru ACLK_GPU>;
+				pm_qos = <&qos_gpu>;
+				#power-domain-cells = <0>;
+			};
+		};
+	};
+
+	qos_gpu: qos@1012d000 {
+		compatible = "rockchip,rk3128-qos", "syscon";
+		reg = <0x1012d000 0x20>;
+	};
+
+	qos_vpu: qos@1012e000 {
+		compatible = "rockchip,rk3128-qos", "syscon";
+		reg = <0x1012e000 0x20>;
+	};
+
+	qos_rga: qos@1012f000 {
+		compatible = "rockchip,rk3128-qos", "syscon";
+		reg = <0x1012f000 0x20>;
+	};
+
+	qos_ebc: qos@1012f080 {
+		compatible = "rockchip,rk3128-qos", "syscon";
+		reg = <0x1012f080 0x20>;
+	};
+
+	qos_iep: qos@1012f100 {
+		compatible = "rockchip,rk3128-qos", "syscon";
+		reg = <0x1012f100 0x20>;
+	};
+
+	qos_lcdc: qos@1012f180 {
+		compatible = "rockchip,rk3128-qos", "syscon";
+		reg = <0x1012f180 0x20>;
+	};
+
+	qos_vip: qos@1012f200 {
+		compatible = "rockchip,rk3128-qos", "syscon";
+		reg = <0x1012f200 0x20>;
 	};
 
 	gic: interrupt-controller@10139000 {
@@ -154,6 +300,9 @@
 		clocks = <&cru HCLK_OTG>;
 		clock-names = "otg";
 		dr_mode = "otg";
+		g-np-tx-fifo-size = <16>;
+		g-rx-fifo-size = <280>;
+		g-tx-fifo-size = <256 128 128 64 32 16>;
 		phys = <&usb2phy_otg>;
 		phy-names = "usb2-phy";
 		status = "disabled";
@@ -163,6 +312,7 @@
 		compatible = "generic-ehci";
 		reg = <0x101c0000 0x20000>;
 		interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&cru HCLK_HOST2>;
 		phys = <&usb2phy_host>;
 		phy-names = "usb";
 		status = "disabled";
@@ -172,6 +322,7 @@
 		compatible = "generic-ohci";
 		reg = <0x101e0000 0x20000>;
 		interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&cru HCLK_HOST2>;
 		phys = <&usb2phy_host>;
 		phy-names = "usb";
 		status = "disabled";
@@ -261,6 +412,8 @@
 			clocks = <&cru SCLK_OTGPHY0>;
 			clock-names = "phyclk";
 			clock-output-names = "usb480m_phy";
+			assigned-clocks = <&cru SCLK_USB480M>;
+			assigned-clock-parents = <&usb2phy>;
 			#clock-cells = <0>;
 			status = "disabled";
 
@@ -518,6 +671,34 @@
 		#dma-cells = <1>;
 	};
 
+	gmac: ethernet@2008c000 {
+		compatible = "rockchip,rk3128-gmac";
+		reg = <0x2008c000 0x4000>;
+		interrupts = <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "macirq", "eth_wake_irq";
+		clocks = <&cru SCLK_MAC>,
+			 <&cru SCLK_MAC_RX>, <&cru SCLK_MAC_TX>,
+			 <&cru SCLK_MAC_REF>, <&cru SCLK_MAC_REFOUT>,
+			 <&cru ACLK_GMAC>, <&cru PCLK_GMAC>;
+		clock-names = "stmmaceth",
+			      "mac_clk_rx", "mac_clk_tx",
+			      "clk_mac_ref", "clk_mac_refout",
+			      "aclk_mac", "pclk_mac";
+		resets = <&cru SRST_GMAC>;
+		reset-names = "stmmaceth";
+		rockchip,grf = <&grf>;
+		rx-fifo-depth = <4096>;
+		tx-fifo-depth = <2048>;
+		status = "disabled";
+
+		mdio: mdio {
+			compatible = "snps,dwmac-mdio";
+			#address-cells = <0x1>;
+			#size-cells = <0x0>;
+		};
+	};
+
 	pinctrl: pinctrl {
 		compatible = "rockchip,rk3128-pinctrl";
 		rockchip,grf = <&grf>;
@@ -843,12 +1024,16 @@
 				rockchip,pins = <1 RK_PB7 1 &pcfg_pull_default>;
 			};
 
+			sdmmc_det: sdmmc-det {
+				rockchip,pins = <1 RK_PC1 1 &pcfg_pull_default>;
+			};
+
 			sdmmc_wp: sdmmc-wp {
 				rockchip,pins = <1 RK_PA7 1 &pcfg_pull_default>;
 			};
 
 			sdmmc_pwren: sdmmc-pwren {
-				rockchip,pins = <1 RK_PB6 1 &pcfg_pull_default>;
+				rockchip,pins = <1 RK_PB6 RK_FUNC_GPIO &pcfg_pull_default>;
 			};
 
 			sdmmc_bus4: sdmmc-bus4 {
diff --git a/arch/arm/boot/dts/rockchip/rk322x.dtsi b/arch/arm/boot/dts/rockchip/rk322x.dtsi
index ffc16d6b97e1..831561fc1814 100644
--- a/arch/arm/boot/dts/rockchip/rk322x.dtsi
+++ b/arch/arm/boot/dts/rockchip/rk322x.dtsi
@@ -15,6 +15,10 @@
 	interrupt-parent = <&gic>;
 
 	aliases {
+		gpio0 = &gpio0;
+		gpio1 = &gpio1;
+		gpio2 = &gpio2;
+		gpio3 = &gpio3;
 		serial0 = &uart0;
 		serial1 = &uart1;
 		serial2 = &uart2;
@@ -215,9 +219,9 @@
 
 			power-domain@RK3228_PD_VOP {
 				reg = <RK3228_PD_VOP>;
-				clocks =<&cru ACLK_VOP>,
-					<&cru DCLK_VOP>,
-					<&cru HCLK_VOP>;
+				clocks = <&cru ACLK_VOP>,
+					 <&cru DCLK_VOP>,
+					 <&cru HCLK_VOP>;
 				pm_qos = <&qos_vop>;
 				#power-domain-cells = <0>;
 			};
diff --git a/arch/arm/boot/dts/rockchip/rk3288.dtsi b/arch/arm/boot/dts/rockchip/rk3288.dtsi
index cb9cdaddffd4..ead343dc3df1 100644
--- a/arch/arm/boot/dts/rockchip/rk3288.dtsi
+++ b/arch/arm/boot/dts/rockchip/rk3288.dtsi
@@ -19,6 +19,15 @@
 
 	aliases {
 		ethernet0 = &gmac;
+		gpio0 = &gpio0;
+		gpio1 = &gpio1;
+		gpio2 = &gpio2;
+		gpio3 = &gpio3;
+		gpio4 = &gpio4;
+		gpio5 = &gpio5;
+		gpio6 = &gpio6;
+		gpio7 = &gpio7;
+		gpio8 = &gpio8;
 		i2c0 = &i2c0;
 		i2c1 = &i2c1;
 		i2c2 = &i2c2;
diff --git a/arch/arm/boot/dts/rockchip/rk3xxx.dtsi b/arch/arm/boot/dts/rockchip/rk3xxx.dtsi
index cb4e42ede56a..f37137f298d5 100644
--- a/arch/arm/boot/dts/rockchip/rk3xxx.dtsi
+++ b/arch/arm/boot/dts/rockchip/rk3xxx.dtsi
@@ -16,6 +16,10 @@
 
 	aliases {
 		ethernet0 = &emac;
+		gpio0 = &gpio0;
+		gpio1 = &gpio1;
+		gpio2 = &gpio2;
+		gpio3 = &gpio3;
 		i2c0 = &i2c0;
 		i2c1 = &i2c1;
 		i2c2 = &i2c2;
diff --git a/arch/arm/boot/dts/rockchip/rv1109-sonoff-ihost.dts b/arch/arm/boot/dts/rockchip/rv1109-sonoff-ihost.dts
new file mode 100644
index 000000000000..45dced8087a3
--- /dev/null
+++ b/arch/arm/boot/dts/rockchip/rv1109-sonoff-ihost.dts
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2020 Rockchip Electronics Co., Ltd.
+ */
+
+/dts-v1/;
+#include "rv1109.dtsi"
+#include "rv1126-sonoff-ihost.dtsi"
+
+/ {
+	model = "Sonoff iHost 2G";
+	compatible = "itead,sonoff-ihost", "rockchip,rv1109";
+};
+
+&cpu0 {
+	cpu-supply = <&vdd_arm>;
+};
+
+&cpu1 {
+	cpu-supply = <&vdd_arm>;
+};
diff --git a/arch/arm/boot/dts/rockchip/rv1109.dtsi b/arch/arm/boot/dts/rockchip/rv1109.dtsi
new file mode 100644
index 000000000000..9cbaa08ab1b8
--- /dev/null
+++ b/arch/arm/boot/dts/rockchip/rv1109.dtsi
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2019 Fuzhou Rockchip Electronics Co., Ltd.
+ */
+
+/dts-v1/;
+
+#include "rv1126.dtsi"
+
+/ {
+	compatible = "rockchip,rv1109";
+
+	cpus {
+		/delete-node/ cpu@f02;
+		/delete-node/ cpu@f03;
+	};
+
+	arm-pmu {
+		interrupts = <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&cpu0>, <&cpu1>;
+	};
+};
diff --git a/arch/arm/boot/dts/rockchip/rv1126-edgeble-neu2-io.dts b/arch/arm/boot/dts/rockchip/rv1126-edgeble-neu2-io.dts
index f09be8405964..0c2396b8f8db 100644
--- a/arch/arm/boot/dts/rockchip/rv1126-edgeble-neu2-io.dts
+++ b/arch/arm/boot/dts/rockchip/rv1126-edgeble-neu2-io.dts
@@ -61,7 +61,7 @@
 	phy-mode = "rgmii";
 	phy-supply = <&vcc_3v3>;
 	pinctrl-names = "default";
-	pinctrl-0 = <&rgmiim1_pins &clk_out_ethernetm1_pins>;
+	pinctrl-0 = <&rgmiim1_miim &rgmiim1_bus2 &rgmiim1_bus4 &clk_out_ethernetm1_pins>;
 	tx_delay = <0x2a>;
 	rx_delay = <0x1a>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/rockchip/rv1126-pinctrl.dtsi b/arch/arm/boot/dts/rockchip/rv1126-pinctrl.dtsi
index bb34b0c9cb4a..06b1d7f2d858 100644
--- a/arch/arm/boot/dts/rockchip/rv1126-pinctrl.dtsi
+++ b/arch/arm/boot/dts/rockchip/rv1126-pinctrl.dtsi
@@ -87,6 +87,16 @@
 				<0 RK_PB5 1 &pcfg_pull_none_drv_level_0_smt>;
 		};
 	};
+	i2c2 {
+		/omit-if-no-ref/
+		i2c2_xfer: i2c2-xfer {
+			rockchip,pins =
+				/* i2c2_scl */
+				<0 RK_PC2 1 &pcfg_pull_none_drv_level_0_smt>,
+				/* i2c2_sda */
+				<0 RK_PC3 1 &pcfg_pull_none_drv_level_0_smt>;
+		};
+	};
 	pwm2 {
 		/omit-if-no-ref/
 		pwm2m0_pins: pwm2m0-pins {
@@ -105,36 +115,56 @@
 	};
 	rgmii {
 		/omit-if-no-ref/
-		rgmiim1_pins: rgmiim1-pins {
+		rgmiim1_miim: rgmiim1-miim {
 			rockchip,pins =
 				/* rgmii_mdc_m1 */
 				<2 RK_PC2 2 &pcfg_pull_none>,
 				/* rgmii_mdio_m1 */
-				<2 RK_PC1 2 &pcfg_pull_none>,
-				/* rgmii_rxclk_m1 */
-				<2 RK_PD3 2 &pcfg_pull_none>,
+				<2 RK_PC1 2 &pcfg_pull_none>;
+		};
+		/omit-if-no-ref/
+		rgmiim1_rxer: rgmiim1-rxer {
+			rockchip,pins =
+				/* rgmii_rxer_m1 */
+				<2 RK_PC0 2 &pcfg_pull_none>;
+		};
+		/omit-if-no-ref/
+		rgmiim1_bus2: rgmiim1-bus2 {
+			rockchip,pins =
 				/* rgmii_rxd0_m1 */
 				<2 RK_PB5 2 &pcfg_pull_none>,
 				/* rgmii_rxd1_m1 */
 				<2 RK_PB6 2 &pcfg_pull_none>,
-				/* rgmii_rxd2_m1 */
-				<2 RK_PC7 2 &pcfg_pull_none>,
-				/* rgmii_rxd3_m1 */
-				<2 RK_PD0 2 &pcfg_pull_none>,
 				/* rgmii_rxdv_m1 */
 				<2 RK_PB4 2 &pcfg_pull_none>,
-				/* rgmii_txclk_m1 */
-				<2 RK_PD2 2 &pcfg_pull_none_drv_level_3>,
 				/* rgmii_txd0_m1 */
 				<2 RK_PC3 2 &pcfg_pull_none_drv_level_3>,
 				/* rgmii_txd1_m1 */
 				<2 RK_PC4 2 &pcfg_pull_none_drv_level_3>,
+				/* rgmii_txen_m1 */
+				<2 RK_PC6 2 &pcfg_pull_none_drv_level_3>;
+		};
+		/omit-if-no-ref/
+		rgmiim1_bus4: rgmiim1-bus4 {
+			rockchip,pins =
+				/* rgmii_rxclk_m1 */
+				<2 RK_PD3 2 &pcfg_pull_none>,
+				/* rgmii_rxd2_m1 */
+				<2 RK_PC7 2 &pcfg_pull_none>,
+				/* rgmii_rxd3_m1 */
+				<2 RK_PD0 2 &pcfg_pull_none>,
+				/* rgmii_txclk_m1 */
+				<2 RK_PD2 2 &pcfg_pull_none_drv_level_3>,
 				/* rgmii_txd2_m1 */
 				<2 RK_PD1 2 &pcfg_pull_none_drv_level_3>,
 				/* rgmii_txd3_m1 */
-				<2 RK_PA4 2 &pcfg_pull_none_drv_level_3>,
-				/* rgmii_txen_m1 */
-				<2 RK_PC6 2 &pcfg_pull_none_drv_level_3>;
+				<2 RK_PA4 2 &pcfg_pull_none_drv_level_3>;
+		};
+		/omit-if-no-ref/
+		rgmiim1_mclkinout: rgmiim1-mclkinout {
+			rockchip,pins =
+				/* rgmii_clk_m1 */
+				<2 RK_PB7 2 &pcfg_pull_none>;
 		};
 	};
 	sdmmc0 {
@@ -263,6 +293,14 @@
 				/* uart3_tx_m0 */
 				<3 RK_PC6 4 &pcfg_pull_up>;
 		};
+		/omit-if-no-ref/
+		uart3m2_xfer: uart3m2-xfer {
+			rockchip,pins =
+				/* uart3_rx_m2 */
+				<3 RK_PA1 4 &pcfg_pull_up>,
+				/* uart3_tx_m2 */
+				<3 RK_PA0 4 &pcfg_pull_up>;
+		};
 	};
 	uart4 {
 		/omit-if-no-ref/
@@ -273,6 +311,14 @@
 				/* uart4_tx_m0 */
 				<3 RK_PA4 4 &pcfg_pull_up>;
 		};
+		/omit-if-no-ref/
+		uart4m2_xfer: uart4m2-xfer {
+			rockchip,pins =
+				/* uart4_rx_m2 */
+				<1 RK_PD4 3 &pcfg_pull_up>,
+				/* uart4_tx_m2 */
+				<1 RK_PD5 3 &pcfg_pull_up>;
+		};
 	};
 	uart5 {
 		/omit-if-no-ref/
diff --git a/arch/arm/boot/dts/rockchip/rv1126-sonoff-ihost.dts b/arch/arm/boot/dts/rockchip/rv1126-sonoff-ihost.dts
new file mode 100644
index 000000000000..77386a48d81e
--- /dev/null
+++ b/arch/arm/boot/dts/rockchip/rv1126-sonoff-ihost.dts
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2020 Rockchip Electronics Co., Ltd.
+ */
+
+/dts-v1/;
+#include "rv1126.dtsi"
+#include "rv1126-sonoff-ihost.dtsi"
+
+/ {
+	model = "Sonoff iHost 4G";
+	compatible = "itead,sonoff-ihost", "rockchip,rv1126";
+};
+
+&cpu0 {
+	cpu-supply = <&vdd_arm>;
+};
+
+&cpu1 {
+	cpu-supply = <&vdd_arm>;
+};
+
+&cpu2 {
+	cpu-supply = <&vdd_arm>;
+};
+
+&cpu3 {
+	cpu-supply = <&vdd_arm>;
+};
diff --git a/arch/arm/boot/dts/rockchip/rv1126-sonoff-ihost.dtsi b/arch/arm/boot/dts/rockchip/rv1126-sonoff-ihost.dtsi
new file mode 100644
index 000000000000..32b329e87a0c
--- /dev/null
+++ b/arch/arm/boot/dts/rockchip/rv1126-sonoff-ihost.dtsi
@@ -0,0 +1,404 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2020 Rockchip Electronics Co., Ltd.
+ * Copyright (c) 2022 Edgeble AI Technologies Pvt. Ltd.
+ */
+
+/ {
+	aliases {
+		ethernet0 = &gmac;
+		mmc0 = &emmc;
+	};
+
+	chosen {
+		stdout-path = "serial2:1500000n8";
+	};
+
+	vcc5v0_sys: regulator-vcc5v0-sys {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0_sys";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
+	sdio_pwrseq: pwrseq-sdio {
+		compatible = "mmc-pwrseq-simple";
+		clocks = <&rk809 1>;
+		clock-names = "ext_clock";
+		pinctrl-names = "default";
+		pinctrl-0 = <&wifi_enable_h>;
+		reset-gpios = <&gpio1 RK_PD0 GPIO_ACTIVE_LOW>;
+	};
+};
+
+&emmc {
+	bus-width = <8>;
+	cap-mmc-highspeed;
+	mmc-hs200-1_8v;
+	non-removable;
+	pinctrl-names = "default";
+	pinctrl-0 = <&emmc_bus8 &emmc_cmd &emmc_clk &emmc_rstnout>;
+	rockchip,default-sample-phase = <90>;
+	vmmc-supply = <&vcc_3v3>;
+	vqmmc-supply = <&vcc_1v8>;
+	status = "okay";
+};
+
+&i2c0 {
+	clock-frequency = <400000>;
+	status = "okay";
+
+	rk809: pmic@20 {
+		compatible = "rockchip,rk809";
+		reg = <0x20>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <RK_PB1 IRQ_TYPE_LEVEL_LOW>;
+		#clock-cells = <1>;
+		clock-output-names = "rk808-clkout1", "rk808-clkout2";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_int_l>;
+		rockchip,system-power-controller;
+		wakeup-source;
+
+		vcc1-supply = <&vcc5v0_sys>;
+		vcc2-supply = <&vcc5v0_sys>;
+		vcc3-supply = <&vcc5v0_sys>;
+		vcc4-supply = <&vcc5v0_sys>;
+		vcc5-supply = <&vcc_buck5>;
+		vcc6-supply = <&vcc_buck5>;
+		vcc7-supply = <&vcc5v0_sys>;
+		vcc8-supply = <&vcc3v3_sys>;
+		vcc9-supply = <&vcc5v0_sys>;
+
+		regulators {
+			vdd_npu_vepu: DCDC_REG1 {
+				regulator-name = "vdd_npu_vepu";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-initial-mode = <0x2>;
+				regulator-min-microvolt = <650000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <6001>;
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_arm: DCDC_REG2 {
+				regulator-name = "vdd_arm";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-initial-mode = <0x2>;
+				regulator-min-microvolt = <725000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <6001>;
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_ddr: DCDC_REG3 {
+				regulator-name = "vcc_ddr";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-initial-mode = <0x2>;
+				regulator-state-mem {
+					regulator-on-in-suspend;
+				};
+			};
+
+			vcc3v3_sys: DCDC_REG4 {
+				regulator-name = "vcc3v3_sys";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-initial-mode = <0x2>;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			vcc_buck5: DCDC_REG5 {
+				regulator-name = "vcc_buck5";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <2200000>;
+				regulator-max-microvolt = <2200000>;
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <2200000>;
+				};
+			};
+
+			vcc_0v8: LDO_REG1 {
+				regulator-name = "vcc_0v8";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <800000>;
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc1v8_pmu: LDO_REG2 {
+				regulator-name = "vcc1v8_pmu";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vdd0v8_pmu: LDO_REG3 {
+				regulator-name = "vcc0v8_pmu";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <800000>;
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <800000>;
+				};
+			};
+
+			vcc_1v8: LDO_REG4 {
+				regulator-name = "vcc_1v8";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vcc_dovdd: LDO_REG5 {
+				regulator-name = "vcc_dovdd";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_dvdd: LDO_REG6 {
+				regulator-name = "vcc_dvdd";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_avdd: LDO_REG7 {
+				regulator-name = "vcc_avdd";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vccio_sd: LDO_REG8 {
+				regulator-name = "vccio_sd";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc3v3_sd: LDO_REG9 {
+				regulator-name = "vcc3v3_sd";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_5v0: SWITCH_REG1 {
+				regulator-name = "vcc_5v0";
+			};
+
+			vcc_3v3: SWITCH_REG2 {
+				regulator-name = "vcc_3v3";
+				regulator-always-on;
+				regulator-boot-on;
+			};
+		};
+	};
+};
+
+&i2c2 {
+	status = "okay";
+	clock-frequency = <400000>;
+
+	pcf8563: rtc@51 {
+		compatible = "nxp,pcf8563";
+		reg = <0x51>;
+		#clock-cells = <0>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <RK_PA2 IRQ_TYPE_LEVEL_LOW>;
+		clock-output-names = "xin32k";
+	};
+};
+
+&gmac {
+	assigned-clocks = <&cru CLK_GMAC_SRC_M1>, <&cru CLK_GMAC_SRC>,
+			  <&cru CLK_GMAC_TX_RX>;
+	assigned-clock-parents = <&cru CLK_GMAC_RGMII_M1>, <&cru CLK_GMAC_SRC_M1>,
+				 <&cru RMII_MODE_CLK>;
+	assigned-clock-rates = <0>, <50000000>;
+	clock_in_out = "output";
+	phy-handle = <&phy>;
+	phy-mode = "rmii";
+	phy-supply = <&vcc_3v3>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&rgmiim1_miim &rgmiim1_rxer &rgmiim1_bus2 &rgmiim1_mclkinout>;
+	status = "okay";
+};
+
+&mdio {
+	phy: ethernet-phy@0 {
+		compatible = "ethernet-phy-ieee802.3-c22";
+		reg = <0x0>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&eth_phy_rst>;
+		reset-active-low;
+		reset-assert-us = <50000>;
+		reset-deassert-us = <10000>;
+		reset-gpios = <&gpio2 RK_PA6 GPIO_ACTIVE_LOW>;
+	};
+};
+
+&pinctrl {
+	ethernet {
+		eth_phy_rst: eth-phy-rst {
+			rockchip,pins = <2 RK_PA6 RK_FUNC_GPIO &pcfg_pull_down>;
+		};
+	};
+	bt {
+		bt_enable: bt-enable {
+			rockchip,pins = <1 RK_PC6 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		bt_wake_dev: bt-wake-dev {
+			rockchip,pins = <1 RK_PC7 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		bt_wake_host: bt-wake-host {
+			rockchip,pins = <1 RK_PC5 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	pmic {
+		pmic_int_l: pmic-int-l {
+			rockchip,pins = <0 RK_PB1 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	wifi {
+		wifi_enable_h: wifi-enable-h {
+			rockchip,pins = <1 RK_PD0 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&pmu_io_domains {
+	pmuio0-supply = <&vcc1v8_pmu>;
+	pmuio1-supply = <&vcc3v3_sys>;
+	vccio1-supply = <&vcc_1v8>;
+	vccio2-supply = <&vccio_sd>;
+	vccio3-supply = <&vcc_1v8>;
+	vccio4-supply = <&vcc_dovdd>;
+	vccio5-supply = <&vcc_1v8>;
+	vccio6-supply = <&vcc_1v8>;
+	vccio7-supply = <&vcc_dovdd>;
+	status = "okay";
+};
+
+&saradc {
+	vref-supply = <&vcc_1v8>;
+	status = "okay";
+};
+
+&sdio {
+	bus-width = <4>;
+	cap-sd-highspeed;
+	cap-sdio-irq;
+	keep-power-in-suspend;
+	max-frequency = <100000000>;
+	mmc-pwrseq = <&sdio_pwrseq>;
+	non-removable;
+	pinctrl-names = "default";
+	pinctrl-0 = <&sdmmc1_clk &sdmmc1_cmd &sdmmc1_bus4>;
+	rockchip,default-sample-phase = <90>;
+	sd-uhs-sdr104;
+	vmmc-supply = <&vcc3v3_sys>;
+	vqmmc-supply = <&vcc_1v8>;
+	status = "okay";
+};
+
+&sdmmc {
+	bus-width = <4>;
+	cap-mmc-highspeed;
+	cap-sd-highspeed;
+	card-detect-delay = <200>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&sdmmc0_clk &sdmmc0_cmd &sdmmc0_bus4 &sdmmc0_det>;
+	rockchip,default-sample-phase = <90>;
+	sd-uhs-sdr12;
+	sd-uhs-sdr25;
+	sd-uhs-sdr104;
+	vqmmc-supply = <&vccio_sd>;
+	status = "okay";
+};
+
+&uart0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart0_xfer &uart0_ctsn &uart0_rtsn>;
+	uart-has-rtscts;
+	status = "okay";
+
+	bluetooth {
+		compatible = "realtek,rtl8723ds-bt";
+		device-wake-gpios = <&gpio1 RK_PC7 GPIO_ACTIVE_HIGH>; /* BT_WAKE */
+		enable-gpios = <&gpio1 RK_PC6 GPIO_ACTIVE_HIGH>; /* BT_RST */
+		host-wake-gpios = <&gpio1 RK_PC5 GPIO_ACTIVE_HIGH>; /* BT_WAKE_HOST */
+		max-speed = <2000000>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&bt_enable>, <&bt_wake_dev>, <&bt_wake_host>;
+	};
+};
+
+&uart2 {
+	status = "okay";
+};
+
+&uart3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart3m2_xfer>;
+	status = "okay";
+};
+
+&uart4 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart4m2_xfer>;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/rockchip/rv1126.dtsi b/arch/arm/boot/dts/rockchip/rv1126.dtsi
index 9ccd1bad6229..bb603cae13df 100644
--- a/arch/arm/boot/dts/rockchip/rv1126.dtsi
+++ b/arch/arm/boot/dts/rockchip/rv1126.dtsi
@@ -21,6 +21,13 @@
 
 	aliases {
 		i2c0 = &i2c0;
+		i2c2 = &i2c2;
+		serial0 = &uart0;
+		serial1 = &uart1;
+		serial2 = &uart2;
+		serial3 = &uart3;
+		serial4 = &uart4;
+		serial5 = &uart5;
 	};
 
 	cpus {
@@ -231,6 +238,20 @@
 		status = "disabled";
 	};
 
+	i2c2: i2c@ff400000 {
+		compatible = "rockchip,rv1126-i2c", "rockchip,rk3399-i2c";
+		reg = <0xff400000 0x1000>;
+		interrupts = <GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>;
+		rockchip,grf = <&pmugrf>;
+		clocks = <&pmucru CLK_I2C2>, <&pmucru PCLK_I2C2>;
+		clock-names = "i2c", "pclk";
+		pinctrl-names = "default";
+		pinctrl-0 = <&i2c2_xfer>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
 	uart1: serial@ff410000 {
 		compatible = "rockchip,rv1126-uart", "snps,dw-apb-uart";
 		reg = <0xff410000 0x100>;
diff --git a/arch/arm/boot/dts/samsung/exynos4.dtsi b/arch/arm/boot/dts/samsung/exynos4.dtsi
index f775b9377a38..7f981b5c0d64 100644
--- a/arch/arm/boot/dts/samsung/exynos4.dtsi
+++ b/arch/arm/boot/dts/samsung/exynos4.dtsi
@@ -203,16 +203,16 @@
 
 		camera: camera@11800000 {
 			compatible = "samsung,fimc";
+			ranges = <0x0 0x11800000 0xa0000>;
 			status = "disabled";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			#clock-cells = <1>;
 			clock-output-names = "cam_a_clkout", "cam_b_clkout";
-			ranges;
 
-			fimc_0: fimc@11800000 {
+			fimc_0: fimc@0 {
 				compatible = "samsung,exynos4210-fimc";
-				reg = <0x11800000 0x1000>;
+				reg = <0x0 0x1000>;
 				interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clock CLK_FIMC0>,
 					 <&clock CLK_SCLK_FIMC0>;
@@ -223,9 +223,9 @@
 				status = "disabled";
 			};
 
-			fimc_1: fimc@11810000 {
+			fimc_1: fimc@10000 {
 				compatible = "samsung,exynos4210-fimc";
-				reg = <0x11810000 0x1000>;
+				reg = <0x00010000 0x1000>;
 				interrupts = <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clock CLK_FIMC1>,
 					 <&clock CLK_SCLK_FIMC1>;
@@ -236,9 +236,9 @@
 				status = "disabled";
 			};
 
-			fimc_2: fimc@11820000 {
+			fimc_2: fimc@20000 {
 				compatible = "samsung,exynos4210-fimc";
-				reg = <0x11820000 0x1000>;
+				reg = <0x00020000 0x1000>;
 				interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clock CLK_FIMC2>,
 					 <&clock CLK_SCLK_FIMC2>;
@@ -249,9 +249,9 @@
 				status = "disabled";
 			};
 
-			fimc_3: fimc@11830000 {
+			fimc_3: fimc@30000 {
 				compatible = "samsung,exynos4210-fimc";
-				reg = <0x11830000 0x1000>;
+				reg = <0x00030000 0x1000>;
 				interrupts = <GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clock CLK_FIMC3>,
 					 <&clock CLK_SCLK_FIMC3>;
@@ -262,9 +262,9 @@
 				status = "disabled";
 			};
 
-			csis_0: csis@11880000 {
+			csis_0: csis@80000 {
 				compatible = "samsung,exynos4210-csis";
-				reg = <0x11880000 0x4000>;
+				reg = <0x00080000 0x4000>;
 				interrupts = <GIC_SPI 78 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clock CLK_CSIS0>,
 					 <&clock CLK_SCLK_CSIS0>;
@@ -278,9 +278,9 @@
 				#size-cells = <0>;
 			};
 
-			csis_1: csis@11890000 {
+			csis_1: csis@90000 {
 				compatible = "samsung,exynos4210-csis";
-				reg = <0x11890000 0x4000>;
+				reg = <0x00090000 0x4000>;
 				interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clock CLK_CSIS1>,
 					 <&clock CLK_SCLK_CSIS1>;
diff --git a/arch/arm/boot/dts/samsung/exynos4210-i9100.dts b/arch/arm/boot/dts/samsung/exynos4210-i9100.dts
index a9ec1f6c1dea..0d8495792a70 100644
--- a/arch/arm/boot/dts/samsung/exynos4210-i9100.dts
+++ b/arch/arm/boot/dts/samsung/exynos4210-i9100.dts
@@ -184,6 +184,28 @@
 		};
 	};
 
+	i2c-gpio-2 {
+		compatible = "i2c-gpio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		sda-gpios = <&gpk1 2 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+		scl-gpios = <&gpk1 0 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+		i2c-gpio,delay-us = <2>;
+
+		touchscreen@20 {
+			compatible = "cypress,aries-touchkey";
+			reg = <0x20>;
+
+			interrupt-parent = <&gpl0>;
+			interrupts = <5 IRQ_TYPE_EDGE_FALLING>;
+
+			vdd-supply = <&vtouchled_reg>;
+			vcc-supply = <&vtouch_reg>;
+			linux,keycodes = <KEY_MENU>, <KEY_BACK>;
+		};
+	};
+
 	spi-3 {
 		compatible = "spi-gpio";
 		#address-cells = <1>;
@@ -380,6 +402,23 @@
 	vusb_a-supply = <&vusbdac_reg>;
 };
 
+&i2c_1 {
+	status = "okay";
+
+	samsung,i2c-sda-delay = <100>;
+	samsung,i2c-slave-addr = <0x10>;
+	samsung,i2c-max-bus-freq = <100000>;
+
+	lis3dh: accelerometer@19 {
+		compatible = "st,lis3dh-accel";
+		reg = <0x19>;
+
+		mount-matrix = "0", "-1", "0",
+			       "1", "0", "0",
+			       "0", "0", "1";
+	};
+};
+
 &i2c_3 {
 	status = "okay";
 
@@ -513,7 +552,6 @@
 				regulator-name = "TOUCH_2.8V";
 				regulator-min-microvolt = <2800000>;
 				regulator-max-microvolt = <2800000>;
-				regulator-always-on;
 			};
 
 			vpll_reg: LDO10 {
@@ -527,6 +565,14 @@
 				regulator-name = "VT_CAM_1.8V";
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <1800000>;
+
+				/*
+				 * Force-enable this regulator; otherwise the
+				 * kernel hangs very early in the boot process
+				 * for about 12 seconds, without apparent
+				 * reason.
+				 */
+				regulator-always-on;
 			};
 
 			vcclcd_reg: LDO13 {
diff --git a/arch/arm/boot/dts/samsung/exynos4x12.dtsi b/arch/arm/boot/dts/samsung/exynos4x12.dtsi
index 84c1db221c98..b4b5e769145b 100644
--- a/arch/arm/boot/dts/samsung/exynos4x12.dtsi
+++ b/arch/arm/boot/dts/samsung/exynos4x12.dtsi
@@ -451,14 +451,15 @@
 };
 
 &camera {
+	ranges = <0x0 0x11800000 0xba1000>;
 	clocks = <&clock CLK_SCLK_CAM0>, <&clock CLK_SCLK_CAM1>,
 		 <&clock CLK_PIXELASYNCM0>, <&clock CLK_PIXELASYNCM1>;
 	clock-names = "sclk_cam0", "sclk_cam1", "pxl_async0", "pxl_async1";
 
 	/* fimc_[0-3] are configured outside, under phandles */
-	fimc_lite_0: fimc-lite@12390000 {
+	fimc_lite_0: fimc-lite@b90000 {
 		compatible = "samsung,exynos4212-fimc-lite";
-		reg = <0x12390000 0x1000>;
+		reg = <0x00b90000 0x1000>;
 		interrupts = <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH>;
 		power-domains = <&pd_isp>;
 		clocks = <&isp_clock CLK_ISP_FIMC_LITE0>;
@@ -467,9 +468,9 @@
 		status = "disabled";
 	};
 
-	fimc_lite_1: fimc-lite@123a0000 {
+	fimc_lite_1: fimc-lite@ba0000 {
 		compatible = "samsung,exynos4212-fimc-lite";
-		reg = <0x123a0000 0x1000>;
+		reg = <0x00ba0000 0x1000>;
 		interrupts = <GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>;
 		power-domains = <&pd_isp>;
 		clocks = <&isp_clock CLK_ISP_FIMC_LITE1>;
@@ -478,9 +479,9 @@
 		status = "disabled";
 	};
 
-	fimc_is: fimc-is@12000000 {
+	fimc_is: fimc-is@800000 {
 		compatible = "samsung,exynos4212-fimc-is";
-		reg = <0x12000000 0x260000>;
+		reg = <0x00800000 0x260000>;
 		interrupts = <GIC_SPI 90 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>;
 		power-domains = <&pd_isp>;
@@ -516,18 +517,15 @@
 		iommus = <&sysmmu_fimc_isp>, <&sysmmu_fimc_drc>,
 			 <&sysmmu_fimc_fd>, <&sysmmu_fimc_mcuctl>;
 		iommu-names = "isp", "drc", "fd", "mcuctl";
+		samsung,pmu-syscon = <&pmu_system_controller>;
 		#address-cells = <1>;
 		#size-cells = <1>;
 		ranges;
 		status = "disabled";
 
-		pmu@10020000 {
-			reg = <0x10020000 0x3000>;
-		};
-
-		i2c1_isp: i2c-isp@12140000 {
+		i2c1_isp: i2c-isp@940000 {
 			compatible = "samsung,exynos4212-i2c-isp";
-			reg = <0x12140000 0x100>;
+			reg = <0x00940000 0x100>;
 			clocks = <&isp_clock CLK_ISP_I2C1_ISP>;
 			clock-names = "i2c_isp";
 			#address-cells = <1>;
diff --git a/arch/arm/boot/dts/samsung/s5pv210.dtsi b/arch/arm/boot/dts/samsung/s5pv210.dtsi
index f7de5b5f2f38..ed560c9a3aa1 100644
--- a/arch/arm/boot/dts/samsung/s5pv210.dtsi
+++ b/arch/arm/boot/dts/samsung/s5pv210.dtsi
@@ -549,17 +549,17 @@
 
 		camera: camera@fa600000 {
 			compatible = "samsung,fimc";
+			ranges = <0x0 0xfa600000 0xe01000>;
 			clocks = <&clocks SCLK_CAM0>, <&clocks SCLK_CAM1>;
 			clock-names = "sclk_cam0", "sclk_cam1";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			#clock-cells = <1>;
 			clock-output-names = "cam_a_clkout", "cam_b_clkout";
-			ranges;
 
-			csis0: csis@fa600000 {
+			csis0: csis@0 {
 				compatible = "samsung,s5pv210-csis";
-				reg = <0xfa600000 0x4000>;
+				reg = <0x00000000 0x4000>;
 				interrupt-parent = <&vic2>;
 				interrupts = <29>;
 				clocks = <&clocks CLK_CSIS>,
@@ -572,9 +572,9 @@
 				#size-cells = <0>;
 			};
 
-			fimc0: fimc@fb200000 {
+			fimc0: fimc@c00000 {
 				compatible = "samsung,s5pv210-fimc";
-				reg = <0xfb200000 0x1000>;
+				reg = <0x00c00000 0x1000>;
 				interrupts = <5>;
 				interrupt-parent = <&vic2>;
 				clocks = <&clocks CLK_FIMC0>,
@@ -586,9 +586,9 @@
 				samsung,cam-if;
 			};
 
-			fimc1: fimc@fb300000 {
+			fimc1: fimc@d00000 {
 				compatible = "samsung,s5pv210-fimc";
-				reg = <0xfb300000 0x1000>;
+				reg = <0x00d00000 0x1000>;
 				interrupt-parent = <&vic2>;
 				interrupts = <6>;
 				clocks = <&clocks CLK_FIMC1>,
@@ -602,9 +602,9 @@
 				samsung,lcd-wb;
 			};
 
-			fimc2: fimc@fb400000 {
+			fimc2: fimc@e00000 {
 				compatible = "samsung,s5pv210-fimc";
-				reg = <0xfb400000 0x1000>;
+				reg = <0x00e00000 0x1000>;
 				interrupt-parent = <&vic2>;
 				interrupts = <7>;
 				clocks = <&clocks CLK_FIMC2>,
diff --git a/arch/arm/boot/dts/st/ste-dbx5x0.dtsi b/arch/arm/boot/dts/st/ste-dbx5x0.dtsi
index d5d88771ef97..0f87abeddc33 100644
--- a/arch/arm/boot/dts/st/ste-dbx5x0.dtsi
+++ b/arch/arm/boot/dts/st/ste-dbx5x0.dtsi
@@ -425,7 +425,7 @@
 		gpio0: gpio@8012e000 {
 			compatible = "stericsson,db8500-gpio",
 				"st,nomadik-gpio";
-			reg =  <0x8012e000 0x80>;
+			reg = <0x8012e000 0x80>;
 			interrupts = <GIC_SPI 119 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -440,7 +440,7 @@
 		gpio1: gpio@8012e080 {
 			compatible = "stericsson,db8500-gpio",
 				"st,nomadik-gpio";
-			reg =  <0x8012e080 0x80>;
+			reg = <0x8012e080 0x80>;
 			interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -455,7 +455,7 @@
 		gpio2: gpio@8000e000 {
 			compatible = "stericsson,db8500-gpio",
 				"st,nomadik-gpio";
-			reg =  <0x8000e000 0x80>;
+			reg = <0x8000e000 0x80>;
 			interrupts = <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -470,7 +470,7 @@
 		gpio3: gpio@8000e080 {
 			compatible = "stericsson,db8500-gpio",
 				"st,nomadik-gpio";
-			reg =  <0x8000e080 0x80>;
+			reg = <0x8000e080 0x80>;
 			interrupts = <GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -485,7 +485,7 @@
 		gpio4: gpio@8000e100 {
 			compatible = "stericsson,db8500-gpio",
 				"st,nomadik-gpio";
-			reg =  <0x8000e100 0x80>;
+			reg = <0x8000e100 0x80>;
 			interrupts = <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -500,7 +500,7 @@
 		gpio5: gpio@8000e180 {
 			compatible = "stericsson,db8500-gpio",
 				"st,nomadik-gpio";
-			reg =  <0x8000e180 0x80>;
+			reg = <0x8000e180 0x80>;
 			interrupts = <GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -515,7 +515,7 @@
 		gpio6: gpio@8011e000 {
 			compatible = "stericsson,db8500-gpio",
 				"st,nomadik-gpio";
-			reg =  <0x8011e000 0x80>;
+			reg = <0x8011e000 0x80>;
 			interrupts = <GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -530,7 +530,7 @@
 		gpio7: gpio@8011e080 {
 			compatible = "stericsson,db8500-gpio",
 				"st,nomadik-gpio";
-			reg =  <0x8011e080 0x80>;
+			reg = <0x8011e080 0x80>;
 			interrupts = <GIC_SPI 126 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -545,7 +545,7 @@
 		gpio8: gpio@a03fe000 {
 			compatible = "stericsson,db8500-gpio",
 				"st,nomadik-gpio";
-			reg =  <0xa03fe000 0x80>;
+			reg = <0xa03fe000 0x80>;
 			interrupts = <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
diff --git a/arch/arm/boot/dts/st/ste-href-ab8500.dtsi b/arch/arm/boot/dts/st/ste-href-ab8500.dtsi
index e1de9d389a01..5eeb44c5e932 100644
--- a/arch/arm/boot/dts/st/ste-href-ab8500.dtsi
+++ b/arch/arm/boot/dts/st/ste-href-ab8500.dtsi
@@ -9,6 +9,54 @@
 	soc {
 		prcmu@80157000 {
 			ab8500 {
+				phy {
+					pinctrl-names = "default", "sleep";
+					pinctrl-0 = <&usb_a_1_default>;
+					pinctrl-1 = <&usb_a_1_sleep>;
+				};
+
+				regulator {
+					ab8500_ldo_aux1_reg: ab8500_ldo_aux1 {
+						regulator-name = "V-DISPLAY";
+					};
+
+					ab8500_ldo_aux2_reg: ab8500_ldo_aux2 {
+						regulator-name = "V-eMMC1";
+					};
+
+					ab8500_ldo_aux3_reg: ab8500_ldo_aux3 {
+						regulator-name = "V-MMC-SD";
+					};
+
+					ab8500_ldo_intcore_reg: ab8500_ldo_intcore {
+						regulator-name = "V-INTCORE";
+					};
+
+					ab8500_ldo_tvout_reg: ab8500_ldo_tvout {
+						regulator-name = "V-TVOUT";
+					};
+
+					ab8500_ldo_audio_reg: ab8500_ldo_audio {
+						regulator-name = "V-AUD";
+					};
+
+					ab8500_ldo_anamic1_reg: ab8500_ldo_anamic1 {
+						regulator-name = "V-AMIC1";
+					};
+
+					ab8500_ldo_anamic2_reg: ab8500_ldo_anamic2 {
+						regulator-name = "V-AMIC2";
+					};
+
+					ab8500_ldo_dmic_reg: ab8500_ldo_dmic {
+						regulator-name = "V-DMIC";
+					};
+
+					ab8500_ldo_ana_reg: ab8500_ldo_ana {
+						regulator-name = "V-CSI/DSI";
+					};
+				};
+
 				gpio {
 					/* Hog a few default settings */
 					pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/st/ste-href-ab8505.dtsi b/arch/arm/boot/dts/st/ste-href-ab8505.dtsi
new file mode 100644
index 000000000000..268db68ccf87
--- /dev/null
+++ b/arch/arm/boot/dts/st/ste-href-ab8505.dtsi
@@ -0,0 +1,490 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2023 Linus Walleij <linus.walleij@linaro.org>
+ */
+
+#include "ste-ab8505.dtsi"
+
+/ {
+	soc {
+		prcmu@80157000 {
+			ab8505 {
+				phy {
+					pinctrl-names = "default", "sleep";
+					pinctrl-0 = <&usb_a_1_default>;
+					pinctrl-1 = <&usb_a_1_sleep>;
+				};
+
+				regulator {
+					ab8500_ldo_aux1_reg: ab8500_ldo_aux1 {
+						regulator-name = "V-DISPLAY";
+					};
+
+					ab8500_ldo_aux2_reg: ab8500_ldo_aux2 {
+						regulator-name = "V-eMMC1";
+					};
+
+					ab8500_ldo_aux3_reg: ab8500_ldo_aux3 {
+						regulator-name = "V-MMC-SD";
+					};
+
+					ab8500_ldo_intcore_reg: ab8500_ldo_intcore {
+						regulator-name = "V-INTCORE";
+					};
+
+					ab8500_ldo_tvout_reg: ab8500_ldo_tvout {
+						regulator-name = "V-TVOUT";
+					};
+
+					ab8500_ldo_audio_reg: ab8500_ldo_audio {
+						regulator-name = "V-AUD";
+					};
+
+					ab8500_ldo_anamic1_reg: ab8500_ldo_anamic1 {
+						regulator-name = "V-AMIC1";
+					};
+
+					ab8500_ldo_anamic2_reg: ab8500_ldo_anamic2 {
+						regulator-name = "V-AMIC2";
+					};
+
+					ab8500_ldo_dmic_reg: ab8500_ldo_dmic {
+						regulator-name = "V-DMIC";
+					};
+
+					ab8500_ldo_ana_reg: ab8500_ldo_ana {
+						regulator-name = "V-CSI/DSI";
+					};
+				};
+
+				gpio {
+					/* Hog a few default settings */
+					pinctrl-names = "default";
+					pinctrl-0 = <&gpio2_default_mode>,
+						    <&gpio4_default_mode>,
+						    <&gpio10_default_mode>,
+						    <&gpio11_default_mode>,
+						    <&gpio12_default_mode>,
+						    <&gpio13_default_mode>,
+						    <&gpio16_default_mode>,
+						    <&gpio24_default_mode>,
+						    <&gpio25_default_mode>,
+						    <&gpio36_default_mode>,
+						    <&gpio37_default_mode>,
+						    <&gpio38_default_mode>,
+						    <&gpio39_default_mode>,
+						    <&gpio42_default_mode>,
+						    <&gpio26_default_mode>,
+						    <&gpio35_default_mode>,
+						    <&ycbcr_default_mode>,
+						    <&pwm_default_mode>,
+						    <&adi1_default_mode>,
+						    <&usbuicc_default_mode>,
+						    <&dmic_default_mode>,
+						    <&extcpena_default_mode>,
+						    <&modsclsda_default_mode>;
+
+					/*
+					 * Pins 2, 4, 10, 11, 12, 13, 16, 24, 25, 36, 37, 38, 39 and 42
+					 * are muxed in as GPIO, and configured as INPUT PULL DOWN
+					 */
+					gpio2 {
+						gpio2_default_mode: gpio2_default {
+							default_mux {
+								function = "gpio";
+								groups = "gpio2_a_1";
+							};
+							default_cfg {
+								pins = "GPIO2_T9";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+					gpio4 {
+						gpio4_default_mode: gpio4_default {
+							default_mux {
+								function = "gpio";
+								groups = "gpio4_a_1";
+							};
+							default_cfg {
+								pins = "GPIO4_W2";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+					gpio10 {
+						gpio10_default_mode: gpio10_default {
+							default_mux {
+								function = "gpio";
+								groups = "gpio10_d_1";
+							};
+							default_cfg {
+								pins = "GPIO10_U17";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+					gpio11 {
+						gpio11_default_mode: gpio11_default {
+							default_mux {
+								function = "gpio";
+								groups = "gpio11_d_1";
+							};
+							default_cfg {
+								pins = "GPIO11_AA18";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+					gpio12 {
+						gpio12_default_mode: gpio12_default {
+							default_mux {
+								function = "gpio";
+								groups = "gpio12_d_1";
+							};
+							default_cfg {
+								pins = "GPIO12_U16";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+					gpio13 {
+						gpio13_default_mode: gpio13_default {
+							default_mux {
+								function = "gpio";
+								groups = "gpio13_d_1";
+							};
+							default_cfg {
+								pins = "GPIO13_W17";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+					gpio16 {
+						gpio16_default_mode: gpio16_default {
+							default_mux {
+								function = "gpio";
+								groups = "gpio16_a_1";
+							};
+							default_cfg {
+								pins = "GPIO16_F15";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+					gpio24 {
+						gpio24_default_mode: gpio24_default {
+							default_mux {
+								function = "gpio";
+								groups = "gpio24_a_1";
+							};
+							default_cfg {
+								pins = "GPIO24_T14";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+					gpio25 {
+						gpio25_default_mode: gpio25_default {
+							default_mux {
+								function = "gpio";
+								groups = "gpio25_a_1";
+							};
+							default_cfg {
+								pins = "GPIO25_R16";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+					gpio36 {
+						gpio36_default_mode: gpio36_default {
+							default_mux {
+								function = "gpio";
+								groups = "gpio36_a_1";
+							};
+							default_cfg {
+								pins = "GPIO36_A17";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+					gpio37 {
+						gpio37_default_mode: gpio37_default {
+							default_mux {
+								function = "gpio";
+								groups = "gpio37_a_1";
+							};
+							default_cfg {
+								pins = "GPIO37_E15";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+					gpio38 {
+						gpio38_default_mode: gpio38_default {
+							default_mux {
+								function = "gpio";
+								groups = "gpio38_a_1";
+							};
+							default_cfg {
+								pins = "GPIO38_C17";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+					gpio39 {
+						gpio39_default_mode: gpio39_default {
+							default_mux {
+								function = "gpio";
+								groups = "gpio39_a_1";
+							};
+							default_cfg {
+								pins = "GPIO39_E16";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+					gpio42 {
+						gpio42_default_mode: gpio42_default {
+							default_mux {
+								function = "gpio";
+								groups = "gpio42_a_1";
+							};
+							default_cfg {
+								pins = "GPIO42_U2";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+					/*
+					 * Pins 26 and 35 muxed in as GPIO, and configured as OUTPUT LOW
+					 */
+					gpio26 {
+						gpio26_default_mode: gpio26_default {
+							default_mux {
+								function = "gpio";
+								groups = "gpio26_d_1";
+							};
+							default_cfg {
+								pins = "GPIO26_M16";
+								output-low;
+							};
+						};
+					};
+					gpio35 {
+						gpio35_default_mode: gpio35_default {
+							default_mux {
+								function = "gpio";
+								groups = "gpio35_d_1";
+							};
+							default_cfg {
+								pins = "GPIO35_W15";
+								output-low;
+							};
+						};
+					};
+					/*
+					 * This sets up the YCBCR connector pins, i.e. analog video out.
+					 * Set as input with no bias.
+					 */
+					ycbcr {
+						ycbcr_default_mode: ycbcr_default {
+							default_mux {
+								function = "ycbcr";
+								groups = "ycbcr0123_d_1";
+							};
+							default_cfg {
+								pins = "GPIO6_Y18",
+									 "GPIO7_AA20",
+									 "GPIO8_W18",
+									 "GPIO9_AA19";
+								input-enable;
+								bias-disable;
+							};
+						};
+					};
+					/* This sets up the PWM pins 14 and 15 */
+					pwm {
+						pwm_default_mode: pwm_default {
+							default_mux {
+								function = "pwmout";
+								groups = "pwmout1_d_1", "pwmout2_d_1";
+							};
+							default_cfg {
+								pins = "GPIO14_F14",
+									 "GPIO15_B17";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+					/* This sets up audio interface 1 */
+					adi1 {
+						adi1_default_mode: adi1_default {
+							default_mux {
+								function = "adi1";
+								groups = "adi1_d_1";
+							};
+							default_cfg {
+								pins = "GPIO17_P5",
+									 "GPIO18_R5",
+									 "GPIO19_U5",
+									 "GPIO20_T5";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+					/* This sets up the USB UICC pins */
+					usbuicc {
+						usbuicc_default_mode: usbuicc_default {
+							default_mux {
+								function = "usbuicc";
+								groups = "usbuicc_d_1";
+							};
+							default_cfg {
+								pins = "GPIO21_H19",
+									 "GPIO22_G20",
+									 "GPIO23_G19";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+					/* This sets up the microphone pins */
+					dmic {
+						dmic_default_mode: dmic_default {
+							default_mux {
+								function = "dmic";
+								groups = "dmic12_d_1",
+									 "dmic34_d_1",
+									 "dmic56_d_1";
+							};
+							default_cfg {
+								pins = "GPIO27_J6",
+									 "GPIO28_K6",
+									 "GPIO29_G6",
+									 "GPIO30_H6",
+									 "GPIO31_F5",
+									 "GPIO32_G5";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+					extcpena {
+						extcpena_default_mode: extcpena_default {
+							default_mux {
+								function = "extcpena";
+								groups = "extcpena_d_1";
+							};
+							default_cfg {
+								pins = "GPIO34_R17";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+					/* Modem I2C setup (SCL and SDA pins) */
+					modsclsda {
+						modsclsda_default_mode: modsclsda_default {
+							default_mux {
+								function = "modsclsda";
+								groups = "modsclsda_d_1";
+							};
+							default_cfg {
+								pins = "GPIO40_T19",
+									"GPIO41_U19";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+					/*
+					 * Clock output pins associated with regulators.
+					 */
+					sysclkreq2 {
+						sysclkreq2_default_mode: sysclkreq2_default {
+							default_mux {
+								function = "sysclkreq";
+								groups = "sysclkreq2_d_1";
+							};
+							default_cfg {
+								pins = "GPIO1_T10";
+								input-enable;
+								bias-disable;
+							};
+						};
+						sysclkreq2_sleep_mode: sysclkreq2_sleep {
+							default_mux {
+								function = "gpio";
+								groups = "gpio1_a_1";
+							};
+							default_cfg {
+								pins = "GPIO1_T10";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+					sysclkreq4 {
+						sysclkreq4_default_mode: sysclkreq4_default {
+							default_mux {
+								function = "sysclkreq";
+								groups = "sysclkreq4_d_1";
+							};
+							default_cfg {
+								pins = "GPIO3_U9";
+								input-enable;
+								bias-disable;
+							};
+						};
+						sysclkreq4_sleep_mode: sysclkreq4_sleep {
+							default_mux {
+								function = "gpio";
+								groups = "gpio3_a_1";
+							};
+							default_cfg {
+								pins = "GPIO3_U9";
+								input-enable;
+								bias-pull-down;
+							};
+						};
+					};
+				};
+				/*
+				 * Charging is not working on the HREF unless an actual battery is
+				 * mounted, most HREFs have a DC cable in to the "battery power"
+				 * which means this will only be cofusing. So do not enable charging
+				 * of the HREFs.
+				 */
+				ab8500_fg {
+					status = "disabled";
+				};
+				ab8500_btemp {
+					status = "disabled";
+				};
+				ab8500_charger {
+					status = "disabled";
+				};
+				ab8500_chargalg {
+					status = "disabled";
+				};
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/st/ste-href.dtsi b/arch/arm/boot/dts/st/ste-href.dtsi
index 13b11dbeba1c..fbf0309e108f 100644
--- a/arch/arm/boot/dts/st/ste-href.dtsi
+++ b/arch/arm/boot/dts/st/ste-href.dtsi
@@ -242,61 +242,6 @@
 			status = "okay";
 		};
 
-		prcmu@80157000 {
-			ab8500 {
-				gpio {
-				};
-
-				phy {
-					pinctrl-names = "default", "sleep";
-					pinctrl-0 = <&usb_a_1_default>;
-					pinctrl-1 = <&usb_a_1_sleep>;
-				};
-
-				regulator {
-					ab8500_ldo_aux1_reg: ab8500_ldo_aux1 {
-						regulator-name = "V-DISPLAY";
-					};
-
-					ab8500_ldo_aux2_reg: ab8500_ldo_aux2 {
-						regulator-name = "V-eMMC1";
-					};
-
-					ab8500_ldo_aux3_reg: ab8500_ldo_aux3 {
-						regulator-name = "V-MMC-SD";
-					};
-
-					ab8500_ldo_intcore_reg: ab8500_ldo_intcore {
-						regulator-name = "V-INTCORE";
-					};
-
-					ab8500_ldo_tvout_reg: ab8500_ldo_tvout {
-						regulator-name = "V-TVOUT";
-					};
-
-					ab8500_ldo_audio_reg: ab8500_ldo_audio {
-						regulator-name = "V-AUD";
-					};
-
-					ab8500_ldo_anamic1_reg: ab8500_ldo_anamic1 {
-						regulator-name = "V-AMIC1";
-					};
-
-					ab8500_ldo_anamic2_reg: ab8500_ldo_anamic2 {
-						regulator-name = "V-AMIC2";
-					};
-
-					ab8500_ldo_dmic_reg: ab8500_ldo_dmic {
-						regulator-name = "V-DMIC";
-					};
-
-					ab8500_ldo_ana_reg: ab8500_ldo_ana {
-						regulator-name = "V-CSI/DSI";
-					};
-				};
-			};
-		};
-
 		pinctrl {
 			sdi0 {
 				sdi0_default_mode: sdi0_default {
diff --git a/arch/arm/boot/dts/st/ste-href520-tvk.dts b/arch/arm/boot/dts/st/ste-href520-tvk.dts
index 7f661f8f13ad..5677df43c3ac 100644
--- a/arch/arm/boot/dts/st/ste-href520-tvk.dts
+++ b/arch/arm/boot/dts/st/ste-href520-tvk.dts
@@ -5,6 +5,7 @@
 
 /dts-v1/;
 #include "ste-db8520.dtsi"
+#include "ste-href-ab8505.dtsi"
 #include "ste-hrefv60plus.dtsi"
 #include "ste-href-tvk1281618-r3.dtsi"
 
diff --git a/arch/arm/boot/dts/st/ste-hrefprev60-stuib.dts b/arch/arm/boot/dts/st/ste-hrefprev60-stuib.dts
index a29e345a43d3..b142bb2d38d8 100644
--- a/arch/arm/boot/dts/st/ste-hrefprev60-stuib.dts
+++ b/arch/arm/boot/dts/st/ste-hrefprev60-stuib.dts
@@ -5,6 +5,7 @@
 
 /dts-v1/;
 #include "ste-db8500.dtsi"
+#include "ste-href-ab8500.dtsi"
 #include "ste-hrefprev60.dtsi"
 #include "ste-href-stuib.dtsi"
 
diff --git a/arch/arm/boot/dts/st/ste-hrefprev60-tvk.dts b/arch/arm/boot/dts/st/ste-hrefprev60-tvk.dts
index 1968bd143114..5da1ff41b00e 100644
--- a/arch/arm/boot/dts/st/ste-hrefprev60-tvk.dts
+++ b/arch/arm/boot/dts/st/ste-hrefprev60-tvk.dts
@@ -5,6 +5,7 @@
 
 /dts-v1/;
 #include "ste-db8500.dtsi"
+#include "ste-href-ab8500.dtsi"
 #include "ste-hrefprev60.dtsi"
 #include "ste-href-tvk1281618-r2.dtsi"
 
diff --git a/arch/arm/boot/dts/st/ste-hrefprev60.dtsi b/arch/arm/boot/dts/st/ste-hrefprev60.dtsi
index 9859ee91a15e..c87fd27b4434 100644
--- a/arch/arm/boot/dts/st/ste-hrefprev60.dtsi
+++ b/arch/arm/boot/dts/st/ste-hrefprev60.dtsi
@@ -62,7 +62,7 @@
 
 		// External Micro SD slot
 		mmc@80126000 {
-			cd-gpios  = <&tc3589x_gpio 3 GPIO_ACTIVE_HIGH>;
+			cd-gpios = <&tc3589x_gpio 3 GPIO_ACTIVE_HIGH>;
 		};
 
 		pinctrl {
diff --git a/arch/arm/boot/dts/st/ste-hrefv60plus-stuib.dts b/arch/arm/boot/dts/st/ste-hrefv60plus-stuib.dts
index 7a5b6aa1db5b..c4abe24a7cd0 100644
--- a/arch/arm/boot/dts/st/ste-hrefv60plus-stuib.dts
+++ b/arch/arm/boot/dts/st/ste-hrefv60plus-stuib.dts
@@ -7,6 +7,7 @@
 
 /dts-v1/;
 #include "ste-db8500.dtsi"
+#include "ste-href-ab8500.dtsi"
 #include "ste-hrefv60plus.dtsi"
 #include "ste-href-stuib.dtsi"
 
diff --git a/arch/arm/boot/dts/st/ste-hrefv60plus-tvk.dts b/arch/arm/boot/dts/st/ste-hrefv60plus-tvk.dts
index d5af3f375161..f55e8de2b516 100644
--- a/arch/arm/boot/dts/st/ste-hrefv60plus-tvk.dts
+++ b/arch/arm/boot/dts/st/ste-hrefv60plus-tvk.dts
@@ -7,6 +7,7 @@
 
 /dts-v1/;
 #include "ste-db8500.dtsi"
+#include "ste-href-ab8500.dtsi"
 #include "ste-hrefv60plus.dtsi"
 #include "ste-href-tvk1281618-r2.dtsi"
 
diff --git a/arch/arm/boot/dts/st/ste-hrefv60plus.dtsi b/arch/arm/boot/dts/st/ste-hrefv60plus.dtsi
index e66fa59c2de6..b23966c16a32 100644
--- a/arch/arm/boot/dts/st/ste-hrefv60plus.dtsi
+++ b/arch/arm/boot/dts/st/ste-hrefv60plus.dtsi
@@ -3,7 +3,6 @@
  * Copyright 2012 ST-Ericsson AB
  */
 
-#include "ste-href-ab8500.dtsi"
 #include "ste-href.dtsi"
 
 / {
@@ -191,7 +190,7 @@
 
 		// External Micro SD slot
 		mmc@80126000 {
-			cd-gpios  = <&gpio2 31 GPIO_ACTIVE_HIGH>; // 95
+			cd-gpios = <&gpio2 31 GPIO_ACTIVE_HIGH>; // 95
 		};
 
 		pinctrl {
diff --git a/arch/arm/boot/dts/st/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/st/ste-nomadik-stn8815.dtsi
index 6816eef39d45..4d37c5fb553c 100644
--- a/arch/arm/boot/dts/st/ste-nomadik-stn8815.dtsi
+++ b/arch/arm/boot/dts/st/ste-nomadik-stn8815.dtsi
@@ -52,7 +52,7 @@
 
 	gpio0: gpio@101e4000 {
 		compatible = "st,nomadik-gpio";
-		reg =  <0x101e4000 0x80>;
+		reg = <0x101e4000 0x80>;
 		interrupt-parent = <&vica>;
 		interrupts = <6>;
 		interrupt-controller;
@@ -66,7 +66,7 @@
 
 	gpio1: gpio@101e5000 {
 		compatible = "st,nomadik-gpio";
-		reg =  <0x101e5000 0x80>;
+		reg = <0x101e5000 0x80>;
 		interrupt-parent = <&vica>;
 		interrupts = <7>;
 		interrupt-controller;
@@ -80,7 +80,7 @@
 
 	gpio2: gpio@101e6000 {
 		compatible = "st,nomadik-gpio";
-		reg =  <0x101e6000 0x80>;
+		reg = <0x101e6000 0x80>;
 		interrupt-parent = <&vica>;
 		interrupts = <8>;
 		interrupt-controller;
@@ -94,7 +94,7 @@
 
 	gpio3: gpio@101e7000 {
 		compatible = "st,nomadik-gpio";
-		reg =  <0x101e7000 0x80>;
+		reg = <0x101e7000 0x80>;
 		ngpio = <28>;
 		interrupt-parent = <&vica>;
 		interrupts = <9>;
diff --git a/arch/arm/boot/dts/st/ste-snowball.dts b/arch/arm/boot/dts/st/ste-snowball.dts
index 27c2ec51e732..1322abfc7acf 100644
--- a/arch/arm/boot/dts/st/ste-snowball.dts
+++ b/arch/arm/boot/dts/st/ste-snowball.dts
@@ -266,7 +266,7 @@
 			pinctrl-1 = <&mc0_a_1_sleep>;
 
 			/* GPIO218 MMC_CD */
-			cd-gpios  = <&gpio6 26 GPIO_ACTIVE_LOW>;
+			cd-gpios = <&gpio6 26 GPIO_ACTIVE_LOW>;
 
 			status = "okay";
 		};
diff --git a/arch/arm/boot/dts/st/ste-ux500-samsung-codina-tmo.dts b/arch/arm/boot/dts/st/ste-ux500-samsung-codina-tmo.dts
index 463942ae755e..c623cc35c5ea 100644
--- a/arch/arm/boot/dts/st/ste-ux500-samsung-codina-tmo.dts
+++ b/arch/arm/boot/dts/st/ste-ux500-samsung-codina-tmo.dts
@@ -310,7 +310,7 @@
 			pinctrl-names = "default", "sleep";
 			pinctrl-0 = <&mc0_a_2_default>;
 			pinctrl-1 = <&mc0_a_2_sleep>;
-			cd-gpios  = <&gpio6 25 GPIO_ACTIVE_LOW>; // GPIO217
+			cd-gpios = <&gpio6 25 GPIO_ACTIVE_LOW>; // GPIO217
 			status = "okay";
 		};
 
diff --git a/arch/arm/boot/dts/st/ste-ux500-samsung-codina.dts b/arch/arm/boot/dts/st/ste-ux500-samsung-codina.dts
index c1ae0e23fe45..2355ca6e9ad6 100644
--- a/arch/arm/boot/dts/st/ste-ux500-samsung-codina.dts
+++ b/arch/arm/boot/dts/st/ste-ux500-samsung-codina.dts
@@ -402,7 +402,7 @@
 			pinctrl-names = "default", "sleep";
 			pinctrl-0 = <&mc0_a_2_default>;
 			pinctrl-1 = <&mc0_a_2_sleep>;
-			cd-gpios  = <&gpio6 25 GPIO_ACTIVE_LOW>; // GPIO217
+			cd-gpios = <&gpio6 25 GPIO_ACTIVE_LOW>; // GPIO217
 			status = "okay";
 		};
 
diff --git a/arch/arm/boot/dts/st/ste-ux500-samsung-gavini.dts b/arch/arm/boot/dts/st/ste-ux500-samsung-gavini.dts
index b21e40da3dfd..ad9a20ccaaeb 100644
--- a/arch/arm/boot/dts/st/ste-ux500-samsung-gavini.dts
+++ b/arch/arm/boot/dts/st/ste-ux500-samsung-gavini.dts
@@ -362,7 +362,7 @@
 			pinctrl-0 = <&mc0_a_2_default>;
 			pinctrl-1 = <&mc0_a_2_sleep>;
 			/* "flash detect" actually card detect */
-			cd-gpios  = <&gpio6 25 GPIO_ACTIVE_LOW>;
+			cd-gpios = <&gpio6 25 GPIO_ACTIVE_LOW>;
 			status = "okay";
 		};
 
diff --git a/arch/arm/boot/dts/st/ste-ux500-samsung-janice.dts b/arch/arm/boot/dts/st/ste-ux500-samsung-janice.dts
index 6e586e875565..229f7c32103c 100644
--- a/arch/arm/boot/dts/st/ste-ux500-samsung-janice.dts
+++ b/arch/arm/boot/dts/st/ste-ux500-samsung-janice.dts
@@ -412,7 +412,7 @@
 			pinctrl-names = "default", "sleep";
 			pinctrl-0 = <&mc0_a_2_default>;
 			pinctrl-1 = <&mc0_a_2_sleep>;
-			cd-gpios  = <&gpio6 25 GPIO_ACTIVE_LOW>; // GPIO217
+			cd-gpios = <&gpio6 25 GPIO_ACTIVE_LOW>; // GPIO217
 			status = "okay";
 		};
 
diff --git a/arch/arm/boot/dts/st/ste-ux500-samsung-kyle.dts b/arch/arm/boot/dts/st/ste-ux500-samsung-kyle.dts
index ba4421080b2a..cdb147dcc1db 100644
--- a/arch/arm/boot/dts/st/ste-ux500-samsung-kyle.dts
+++ b/arch/arm/boot/dts/st/ste-ux500-samsung-kyle.dts
@@ -238,7 +238,7 @@
 			pinctrl-names = "default", "sleep";
 			pinctrl-0 = <&mc0_a_1_default>;
 			pinctrl-1 = <&mc0_a_1_sleep>;
-			cd-gpios  = <&gpio6 25 GPIO_ACTIVE_LOW>; // GPIO217
+			cd-gpios = <&gpio6 25 GPIO_ACTIVE_LOW>; // GPIO217
 			status = "okay";
 		};
 
diff --git a/arch/arm/boot/dts/st/stm32f469-disco.dts b/arch/arm/boot/dts/st/stm32f469-disco.dts
index cbbd521bf010..8a4f8ddd083d 100644
--- a/arch/arm/boot/dts/st/stm32f469-disco.dts
+++ b/arch/arm/boot/dts/st/stm32f469-disco.dts
@@ -69,16 +69,9 @@
 		serial0 = &usart3;
 	};
 
-	mmc_vcard: mmc_vcard {
+	vcc_3v3: vcc-3v3 {
 		compatible = "regulator-fixed";
-		regulator-name = "mmc_vcard";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-	};
-
-	vdd_dsi: vdd-dsi {
-		compatible = "regulator-fixed";
-		regulator-name = "vdd_dsi";
+		regulator-name = "vcc_3v3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 	};
@@ -164,7 +157,7 @@
 		compatible = "orisetech,otm8009a";
 		reg = <0>; /* dsi virtual channel (0..3) */
 		reset-gpios = <&gpioh 7 GPIO_ACTIVE_LOW>;
-		power-supply = <&vdd_dsi>;
+		power-supply = <&vcc_3v3>;
 		status = "okay";
 
 		port {
@@ -219,7 +212,7 @@
 
 &sdio {
 	status = "okay";
-	vmmc-supply = <&mmc_vcard>;
+	vmmc-supply = <&vcc_3v3>;
 	cd-gpios = <&gpiog 2 GPIO_ACTIVE_LOW>;
 	broken-cd;
 	pinctrl-names = "default", "opendrain";
diff --git a/arch/arm/boot/dts/st/stm32f746.dtsi b/arch/arm/boot/dts/st/stm32f746.dtsi
index 53a8e2dec9a4..65c72b6fcc83 100644
--- a/arch/arm/boot/dts/st/stm32f746.dtsi
+++ b/arch/arm/boot/dts/st/stm32f746.dtsi
@@ -274,6 +274,26 @@
 			clocks = <&rcc 0 STM32F7_APB1_CLOCK(CAN3)>;
 		};
 
+		spi2: spi@40003800 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "st,stm32f7-spi";
+			reg = <0x40003800 0x400>;
+			interrupts = <36>;
+			clocks = <&rcc 0 STM32F7_APB1_CLOCK(SPI2)>;
+			status = "disabled";
+		};
+
+		spi3: spi@40003c00 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "st,stm32f7-spi";
+			reg = <0x40003c00 0x400>;
+			interrupts = <51>;
+			clocks = <&rcc 0 STM32F7_APB1_CLOCK(SPI3)>;
+			status = "disabled";
+		};
+
 		usart2: serial@40004400 {
 			compatible = "st,stm32f7-uart";
 			reg = <0x40004400 0x400>;
@@ -491,9 +511,30 @@
 			status = "disabled";
 		};
 
+		spi1: spi@40013000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "st,stm32f7-spi";
+			reg = <0x40013000 0x400>;
+			interrupts = <35>;
+			clocks = <&rcc 0 STM32F7_APB2_CLOCK(SPI1)>;
+			status = "disabled";
+		};
+
+		spi4: spi@40013400 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "st,stm32f7-spi";
+			reg = <0x40013400 0x400>;
+			interrupts = <84>;
+			clocks = <&rcc 0 STM32F7_APB2_CLOCK(SPI4)>;
+			status = "disabled";
+		};
+
 		syscfg: syscon@40013800 {
 			compatible = "st,stm32-syscfg", "syscon";
 			reg = <0x40013800 0x400>;
+			clocks = <&rcc 0 STM32F7_APB2_CLOCK(SYSCFG)>;
 		};
 
 		exti: interrupt-controller@40013c00 {
@@ -554,6 +595,26 @@
 			};
 		};
 
+		spi5: spi@40015000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "st,stm32f7-spi";
+			reg = <0x40015000 0x400>;
+			interrupts = <85>;
+			clocks = <&rcc 0 STM32F7_APB2_CLOCK(SPI5)>;
+			status = "disabled";
+		};
+
+		spi6: spi@40015400 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "st,stm32f7-spi";
+			reg = <0x40015400 0x400>;
+			interrupts = <86>;
+			clocks = <&rcc 0 STM32F7_APB2_CLOCK(SPI6)>;
+			status = "disabled";
+		};
+
 		ltdc: display-controller@40016800 {
 			compatible = "st,stm32-ltdc";
 			reg = <0x40016800 0x200>;
diff --git a/arch/arm/boot/dts/st/stm32mp135.dtsi b/arch/arm/boot/dts/st/stm32mp135.dtsi
index abf2acd37b4e..68d32f9f5314 100644
--- a/arch/arm/boot/dts/st/stm32mp135.dtsi
+++ b/arch/arm/boot/dts/st/stm32mp135.dtsi
@@ -8,5 +8,16 @@
 
 / {
 	soc {
+		dcmipp: dcmipp@5a000000 {
+			compatible = "st,stm32mp13-dcmipp";
+			reg = <0x5a000000 0x400>;
+			interrupts = <GIC_SPI 79 IRQ_TYPE_LEVEL_HIGH>;
+			resets = <&rcc DCMIPP_R>;
+			clocks = <&rcc DCMIPP_K>;
+			status = "disabled";
+
+			port {
+			};
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/st/stm32mp151.dtsi b/arch/arm/boot/dts/st/stm32mp151.dtsi
index 61508917521c..fa4cbd312e5a 100644
--- a/arch/arm/boot/dts/st/stm32mp151.dtsi
+++ b/arch/arm/boot/dts/st/stm32mp151.dtsi
@@ -1521,6 +1521,8 @@
 			clocks = <&usbphyc>, <&rcc USBH>;
 			resets = <&rcc USBH_R>;
 			interrupts = <GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH>;
+			phys = <&usbphyc_port0>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -1531,6 +1533,8 @@
 			resets = <&rcc USBH_R>;
 			interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
 			companion = <&usbh_ohci>;
+			phys = <&usbphyc_port0>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/st/stm32mp151a-prtt1l.dtsi b/arch/arm/boot/dts/st/stm32mp151a-prtt1l.dtsi
index dd23de85100c..3938d357e198 100644
--- a/arch/arm/boot/dts/st/stm32mp151a-prtt1l.dtsi
+++ b/arch/arm/boot/dts/st/stm32mp151a-prtt1l.dtsi
@@ -206,8 +206,6 @@
 };
 
 &usbh_ehci {
-	phys = <&usbphyc_port0>;
-	phy-names = "usb";
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/st/stm32mp157a-dk1-scmi.dts b/arch/arm/boot/dts/st/stm32mp157a-dk1-scmi.dts
index afcd6285890c..ce5937270aa1 100644
--- a/arch/arm/boot/dts/st/stm32mp157a-dk1-scmi.dts
+++ b/arch/arm/boot/dts/st/stm32mp157a-dk1-scmi.dts
@@ -11,7 +11,7 @@
 
 / {
 	model = "STMicroelectronics STM32MP157A-DK1 SCMI Discovery Board";
-	compatible = "st,stm32mp157a-dk1-scmi", "st,stm32mp157a-dk1", "st,stm32mp157";
+	compatible = "st,stm32mp157a-dk1-scmi", "st,stm32mp157";
 
 	reserved-memory {
 		optee@de000000 {
@@ -59,7 +59,7 @@
 	/delete-property/ st,syscfg-holdboot;
 	resets = <&scmi_reset RST_SCMI_MCU>,
 		 <&scmi_reset RST_SCMI_MCU_HOLD_BOOT>;
-	reset-names =  "mcu_rst", "hold_boot";
+	reset-names = "mcu_rst", "hold_boot";
 };
 
 &rcc {
diff --git a/arch/arm/boot/dts/st/stm32mp157a-stinger96.dtsi b/arch/arm/boot/dts/st/stm32mp157a-stinger96.dtsi
index 5f85598cc7c6..5c1cc48e5199 100644
--- a/arch/arm/boot/dts/st/stm32mp157a-stinger96.dtsi
+++ b/arch/arm/boot/dts/st/stm32mp157a-stinger96.dtsi
@@ -313,8 +313,6 @@
 };
 
 &usbh_ehci {
-	phys = <&usbphyc_port0>;
-	phy-names = "usb";
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/st/stm32mp157c-dk2-scmi.dts b/arch/arm/boot/dts/st/stm32mp157c-dk2-scmi.dts
index 39358d902000..c20a73841c1f 100644
--- a/arch/arm/boot/dts/st/stm32mp157c-dk2-scmi.dts
+++ b/arch/arm/boot/dts/st/stm32mp157c-dk2-scmi.dts
@@ -11,7 +11,7 @@
 
 / {
 	model = "STMicroelectronics STM32MP157C-DK2 SCMI Discovery Board";
-	compatible = "st,stm32mp157c-dk2-scmi", "st,stm32mp157c-dk2", "st,stm32mp157";
+	compatible = "st,stm32mp157c-dk2-scmi", "st,stm32mp157";
 
 	reserved-memory {
 		optee@de000000 {
@@ -65,7 +65,7 @@
 	/delete-property/ st,syscfg-holdboot;
 	resets = <&scmi_reset RST_SCMI_MCU>,
 		 <&scmi_reset RST_SCMI_MCU_HOLD_BOOT>;
-	reset-names =  "mcu_rst", "hold_boot";
+	reset-names = "mcu_rst", "hold_boot";
 };
 
 &rcc {
diff --git a/arch/arm/boot/dts/st/stm32mp157c-ed1-scmi.dts b/arch/arm/boot/dts/st/stm32mp157c-ed1-scmi.dts
index 07ea765a4553..5e2eaf57ce22 100644
--- a/arch/arm/boot/dts/st/stm32mp157c-ed1-scmi.dts
+++ b/arch/arm/boot/dts/st/stm32mp157c-ed1-scmi.dts
@@ -11,7 +11,7 @@
 
 / {
 	model = "STMicroelectronics STM32MP157C-ED1 SCMI eval daughter";
-	compatible = "st,stm32mp157c-ed1-scmi", "st,stm32mp157c-ed1", "st,stm32mp157";
+	compatible = "st,stm32mp157c-ed1-scmi", "st,stm32mp157";
 
 	reserved-memory {
 		optee@fe000000 {
@@ -64,7 +64,7 @@
 	/delete-property/ st,syscfg-holdboot;
 	resets = <&scmi_reset RST_SCMI_MCU>,
 		 <&scmi_reset RST_SCMI_MCU_HOLD_BOOT>;
-	reset-names =  "mcu_rst", "hold_boot";
+	reset-names = "mcu_rst", "hold_boot";
 };
 
 &rcc {
diff --git a/arch/arm/boot/dts/st/stm32mp157c-emstamp-argon.dtsi b/arch/arm/boot/dts/st/stm32mp157c-emstamp-argon.dtsi
index f928cfb80b87..4792004cab0c 100644
--- a/arch/arm/boot/dts/st/stm32mp157c-emstamp-argon.dtsi
+++ b/arch/arm/boot/dts/st/stm32mp157c-emstamp-argon.dtsi
@@ -500,14 +500,10 @@
 };
 
 &usbh_ehci {
-	phys = <&usbphyc_port0>;
-	phy-names = "usb";
 	status = "okay";
 };
 
 &usbh_ohci {
-	phys = <&usbphyc_port0>;
-	phy-names = "usb";
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/st/stm32mp157c-ev1-scmi.dts b/arch/arm/boot/dts/st/stm32mp157c-ev1-scmi.dts
index 813086ec2489..3226fb945a8e 100644
--- a/arch/arm/boot/dts/st/stm32mp157c-ev1-scmi.dts
+++ b/arch/arm/boot/dts/st/stm32mp157c-ev1-scmi.dts
@@ -11,8 +11,7 @@
 
 / {
 	model = "STMicroelectronics STM32MP157C-EV1 SCMI eval daughter on eval mother";
-	compatible = "st,stm32mp157c-ev1-scmi", "st,stm32mp157c-ev1", "st,stm32mp157c-ed1",
-		     "st,stm32mp157";
+	compatible = "st,stm32mp157c-ev1-scmi", "st,stm32mp157c-ed1", "st,stm32mp157";
 
 	reserved-memory {
 		optee@fe000000 {
@@ -70,7 +69,7 @@
 	/delete-property/ st,syscfg-holdboot;
 	resets = <&scmi_reset RST_SCMI_MCU>,
 		 <&scmi_reset RST_SCMI_MCU_HOLD_BOOT>;
-	reset-names =  "mcu_rst", "hold_boot";
+	reset-names = "mcu_rst", "hold_boot";
 };
 
 &rcc {
diff --git a/arch/arm/boot/dts/st/stm32mp157c-ev1.dts b/arch/arm/boot/dts/st/stm32mp157c-ev1.dts
index cd9c3ff5378b..9eb9a1bf4f2c 100644
--- a/arch/arm/boot/dts/st/stm32mp157c-ev1.dts
+++ b/arch/arm/boot/dts/st/stm32mp157c-ev1.dts
@@ -362,7 +362,6 @@
 };
 
 &usbh_ehci {
-	phys = <&usbphyc_port0>;
 	status = "okay";
 	#address-cells = <1>;
 	#size-cells = <0>;
diff --git a/arch/arm/boot/dts/st/stm32mp157c-osd32mp1-red.dts b/arch/arm/boot/dts/st/stm32mp157c-osd32mp1-red.dts
index bd67a1db9122..527c33be66cc 100644
--- a/arch/arm/boot/dts/st/stm32mp157c-osd32mp1-red.dts
+++ b/arch/arm/boot/dts/st/stm32mp157c-osd32mp1-red.dts
@@ -197,14 +197,10 @@
 };
 
 &usbh_ehci {
-	phys = <&usbphyc_port0>;
-	phy-names = "usb";
 	status = "okay";
 };
 
 &usbh_ohci {
-	phys = <&usbphyc_port0>;
-	phy-names = "usb";
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/st/stm32mp157c-phycore-stm32mp15-som.dtsi b/arch/arm/boot/dts/st/stm32mp157c-phycore-stm32mp15-som.dtsi
index 4e8b2d2b30c7..bf0c32027baf 100644
--- a/arch/arm/boot/dts/st/stm32mp157c-phycore-stm32mp15-som.dtsi
+++ b/arch/arm/boot/dts/st/stm32mp157c-phycore-stm32mp15-som.dtsi
@@ -547,14 +547,10 @@
 };
 
 &usbh_ehci {
-	phys = <&usbphyc_port0>;
-	phy-names = "usb";
 	status = "okay";
 };
 
 &usbh_ohci {
-	phys = <&usbphyc_port0>;
-	phy-names = "usb";
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/st/stm32mp15xc-lxa-tac.dtsi b/arch/arm/boot/dts/st/stm32mp15xc-lxa-tac.dtsi
index f09b7c384bd9..fc3a2386dbb9 100644
--- a/arch/arm/boot/dts/st/stm32mp15xc-lxa-tac.dtsi
+++ b/arch/arm/boot/dts/st/stm32mp15xc-lxa-tac.dtsi
@@ -567,9 +567,6 @@ baseboard_eeprom: &sip_eeprom {
 };
 
 &usbh_ehci {
-	phys = <&usbphyc_port0>;
-	phy-names = "usb";
-
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/st/stm32mp15xx-dhcom-drc02.dtsi b/arch/arm/boot/dts/st/stm32mp15xx-dhcom-drc02.dtsi
index 35b1034aa3cf..bb4f8a0b937f 100644
--- a/arch/arm/boot/dts/st/stm32mp15xx-dhcom-drc02.dtsi
+++ b/arch/arm/boot/dts/st/stm32mp15xx-dhcom-drc02.dtsi
@@ -152,7 +152,6 @@
 };
 
 &usbh_ehci {
-	phys = <&usbphyc_port0>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/st/stm32mp15xx-dhcom-pdk2.dtsi b/arch/arm/boot/dts/st/stm32mp15xx-dhcom-pdk2.dtsi
index 46b87a27d8b3..466d9701add0 100644
--- a/arch/arm/boot/dts/st/stm32mp15xx-dhcom-pdk2.dtsi
+++ b/arch/arm/boot/dts/st/stm32mp15xx-dhcom-pdk2.dtsi
@@ -305,7 +305,6 @@
 };
 
 &usbh_ehci {
-	phys = <&usbphyc_port0>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/st/stm32mp15xx-dhcom-picoitx.dtsi b/arch/arm/boot/dts/st/stm32mp15xx-dhcom-picoitx.dtsi
index abc595350e71..b5bc53accd6b 100644
--- a/arch/arm/boot/dts/st/stm32mp15xx-dhcom-picoitx.dtsi
+++ b/arch/arm/boot/dts/st/stm32mp15xx-dhcom-picoitx.dtsi
@@ -119,12 +119,10 @@
 };
 
 &usbh_ehci {
-	phys = <&usbphyc_port0>;
 	status = "okay";
 };
 
 &usbh_ohci {
-	phys = <&usbphyc_port0>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/st/stm32mp15xx-dhcor-avenger96.dtsi b/arch/arm/boot/dts/st/stm32mp15xx-dhcor-avenger96.dtsi
index 0069ad75d55e..343a4613dfca 100644
--- a/arch/arm/boot/dts/st/stm32mp15xx-dhcor-avenger96.dtsi
+++ b/arch/arm/boot/dts/st/stm32mp15xx-dhcor-avenger96.dtsi
@@ -489,8 +489,6 @@
 };
 
 &usbh_ehci {
-	phys = <&usbphyc_port0>;
-	phy-names = "usb";
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/st/stm32mp15xx-dhcor-drc-compact.dtsi b/arch/arm/boot/dts/st/stm32mp15xx-dhcor-drc-compact.dtsi
index 92d906bfd5d7..bc4ddcbdd5cf 100644
--- a/arch/arm/boot/dts/st/stm32mp15xx-dhcor-drc-compact.dtsi
+++ b/arch/arm/boot/dts/st/stm32mp15xx-dhcor-drc-compact.dtsi
@@ -312,12 +312,10 @@
 };
 
 &usbh_ehci {
-	phys = <&usbphyc_port0>;
 	status = "okay";
 };
 
 &usbh_ohci {
-	phys = <&usbphyc_port0>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/st/stm32mp15xx-dhcor-testbench.dtsi b/arch/arm/boot/dts/st/stm32mp15xx-dhcor-testbench.dtsi
index ab7f0ba49639..6e79c4b6fe32 100644
--- a/arch/arm/boot/dts/st/stm32mp15xx-dhcor-testbench.dtsi
+++ b/arch/arm/boot/dts/st/stm32mp15xx-dhcor-testbench.dtsi
@@ -168,12 +168,10 @@
 };
 
 &usbh_ehci {
-	phys = <&usbphyc_port0>;
 	status = "okay";
 };
 
 &usbh_ohci {
-	phys = <&usbphyc_port0>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/st/stm32mp15xx-dkx.dtsi b/arch/arm/boot/dts/st/stm32mp15xx-dkx.dtsi
index 511113f2e399..f7634c51efb2 100644
--- a/arch/arm/boot/dts/st/stm32mp15xx-dkx.dtsi
+++ b/arch/arm/boot/dts/st/stm32mp15xx-dkx.dtsi
@@ -680,7 +680,6 @@
 };
 
 &usbh_ehci {
-	phys = <&usbphyc_port0>;
 	status = "okay";
 	#address-cells = <1>;
 	#size-cells = <0>;
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2e-netcp.dtsi b/arch/arm/boot/dts/ti/keystone/keystone-k2e-netcp.dtsi
index bff73a0ed10b..5c88a90903b8 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2e-netcp.dtsi
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2e-netcp.dtsi
@@ -36,9 +36,9 @@ qmss: qmss@2a40000 {
 		qpend {
 			qpend-0 {
 				qrange = <658 8>;
-				interrupts =<0 40 0xf04 0 41 0xf04 0 42 0xf04
-					     0 43 0xf04 0 44 0xf04 0 45 0xf04
-					     0 46 0xf04 0 47 0xf04>;
+				interrupts = <0 40 0xf04 0 41 0xf04 0 42 0xf04
+					      0 43 0xf04 0 44 0xf04 0 45 0xf04
+					      0 46 0xf04 0 47 0xf04>;
 			};
 			qpend-1 {
 				qrange = <528 16>;
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2g-evm.dts b/arch/arm/boot/dts/ti/keystone/keystone-k2g-evm.dts
index 7bfc80f1af26..f0ddbbcdc972 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2g-evm.dts
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2g-evm.dts
@@ -9,7 +9,7 @@
 #include "keystone-k2g.dtsi"
 
 / {
-	compatible =  "ti,k2g-evm", "ti,k2g", "ti,keystone";
+	compatible = "ti,k2g-evm", "ti,k2g", "ti,keystone";
 	model = "Texas Instruments K2G General Purpose EVM";
 
 	memory@800000000 {
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2g-netcp.dtsi b/arch/arm/boot/dts/ti/keystone/keystone-k2g-netcp.dtsi
index f6306933ff42..7109ca031617 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2g-netcp.dtsi
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2g-netcp.dtsi
@@ -37,9 +37,9 @@ qmss: qmss@4020000 {
 		qpend {
 			qpend-0 {
 				qrange = <77 8>;
-				interrupts =<0 308 0xf04 0 309 0xf04 0 310 0xf04
-					     0 311 0xf04 0 312 0xf04 0 313 0xf04
-					     0 314 0xf04 0 315 0xf04>;
+				interrupts = <0 308 0xf04 0 309 0xf04 0 310 0xf04
+					      0 311 0xf04 0 312 0xf04 0 313 0xf04
+					      0 314 0xf04 0 315 0xf04>;
 				qalloc-by-id;
 			};
 		};
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2hk-evm.dts b/arch/arm/boot/dts/ti/keystone/keystone-k2hk-evm.dts
index 206df8a8d9dd..8dfb54295027 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2hk-evm.dts
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2hk-evm.dts
@@ -10,7 +10,7 @@
 #include "keystone-k2hk.dtsi"
 
 / {
-	compatible =  "ti,k2hk-evm", "ti,k2hk", "ti,keystone";
+	compatible = "ti,k2hk-evm", "ti,k2hk", "ti,keystone";
 	model = "Texas Instruments Keystone 2 Kepler/Hawking EVM";
 
 	reserved-memory {
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2hk-netcp.dtsi b/arch/arm/boot/dts/ti/keystone/keystone-k2hk-netcp.dtsi
index 8a421c65f920..c2ee775eab6a 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2hk-netcp.dtsi
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2hk-netcp.dtsi
@@ -49,9 +49,9 @@ qmss: qmss@2a40000 {
 		qpend {
 			qpend-0 {
 				qrange = <658 8>;
-				interrupts =<0 40 0xf04 0 41 0xf04 0 42 0xf04
-					     0 43 0xf04 0 44 0xf04 0 45 0xf04
-					     0 46 0xf04 0 47 0xf04>;
+				interrupts = <0 40 0xf04 0 41 0xf04 0 42 0xf04
+					      0 43 0xf04 0 44 0xf04 0 45 0xf04
+					      0 46 0xf04 0 47 0xf04>;
 			};
 			qpend-1 {
 				qrange = <8704 16>;
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2l-netcp.dtsi b/arch/arm/boot/dts/ti/keystone/keystone-k2l-netcp.dtsi
index 5ec6680a533d..1afebd7458c1 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2l-netcp.dtsi
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2l-netcp.dtsi
@@ -36,9 +36,9 @@ qmss: qmss@2a40000 {
 		qpend {
 			qpend-0 {
 				qrange = <658 8>;
-				interrupts =<0 40 0xf04 0 41 0xf04 0 42 0xf04
-					     0 43 0xf04 0 44 0xf04 0 45 0xf04
-					     0 46 0xf04 0 47 0xf04>;
+				interrupts = <0 40 0xf04 0 41 0xf04 0 42 0xf04
+					      0 43 0xf04 0 44 0xf04 0 45 0xf04
+					      0 46 0xf04 0 47 0xf04>;
 			};
 			qpend-1 {
 				qrange = <528 16>;
diff --git a/arch/arm/boot/dts/ti/omap/Makefile b/arch/arm/boot/dts/ti/omap/Makefile
index d2b590004fed..95c68135dd0c 100644
--- a/arch/arm/boot/dts/ti/omap/Makefile
+++ b/arch/arm/boot/dts/ti/omap/Makefile
@@ -79,7 +79,9 @@ dtb-$(CONFIG_ARCH_OMAP4) += \
 	omap4-sdp.dtb \
 	omap4-sdp-es23plus.dtb \
 	omap4-var-dvk-om44.dtb \
-	omap4-var-stk-om44.dtb
+	omap4-var-stk-om44.dtb \
+	omap4-xyboard-mz609.dtb \
+	omap4-xyboard-mz617.dtb
 dtb-$(CONFIG_SOC_AM33XX) += \
 	am335x-baltos-ir2110.dtb \
 	am335x-baltos-ir3220.dtb \
@@ -129,6 +131,16 @@ dtb-$(CONFIG_SOC_AM43XX) += \
 am57xx-evm-dtbs := am57xx-beagle-x15.dtb am57xx-evm.dtbo
 am57xx-evm-reva3-dtbs := am57xx-beagle-x15-revc.dtb am57xx-evm.dtbo
 
+am571x-idk-overlays-dtbs := am571x-idk.dtb \
+	am571x-idk-touchscreen.dtbo am57xx-idk-lcd-osd101t2587.dtbo
+am572x-idk-overlays-dtbs := am572x-idk.dtb \
+	am572x-idk-touchscreen.dtbo am57xx-idk-lcd-osd101t2045.dtbo
+
+# Build time test only, enabled by CONFIG_OF_ALL_DTBS
+dtb- += \
+	am571x-idk-overlays.dtb \
+	am572x-idk-overlays.dtb
+
 dtb-$(CONFIG_SOC_DRA7XX) += \
 	am57xx-beagle-x15.dtb \
 	am57xx-beagle-x15-revb1.dtb \
diff --git a/arch/arm/boot/dts/ti/omap/am33xx.dtsi b/arch/arm/boot/dts/ti/omap/am33xx.dtsi
index 1a2cd5baf402..5b9e01a8aa5d 100644
--- a/arch/arm/boot/dts/ti/omap/am33xx.dtsi
+++ b/arch/arm/boot/dts/ti/omap/am33xx.dtsi
@@ -359,6 +359,7 @@
 					<SYSC_IDLE_NO>,
 					<SYSC_IDLE_SMART>,
 					<SYSC_IDLE_SMART_WKUP>;
+			ti,sysc-delay-us = <2>;
 			clocks = <&l3s_clkctrl AM3_L3S_USB_OTG_HS_CLKCTRL 0>;
 			clock-names = "fck";
 			#address-cells = <1>;
diff --git a/arch/arm/boot/dts/ti/omap/am571x-idk.dts b/arch/arm/boot/dts/ti/omap/am571x-idk.dts
index 48425020281a..322cf79d22e9 100644
--- a/arch/arm/boot/dts/ti/omap/am571x-idk.dts
+++ b/arch/arm/boot/dts/ti/omap/am571x-idk.dts
@@ -168,8 +168,8 @@
 };
 
 &extcon_usb2 {
-	id-gpio = <&gpio5 7 GPIO_ACTIVE_HIGH>;
-	vbus-gpio = <&gpio7 22 GPIO_ACTIVE_HIGH>;
+	id-gpios = <&gpio5 7 GPIO_ACTIVE_HIGH>;
+	vbus-gpios = <&gpio7 22 GPIO_ACTIVE_HIGH>;
 };
 
 &sn65hvs882 {
diff --git a/arch/arm/boot/dts/ti/omap/am5729-beagleboneai.dts b/arch/arm/boot/dts/ti/omap/am5729-beagleboneai.dts
index 9a234dc1431d..c8e55642f9c6 100644
--- a/arch/arm/boot/dts/ti/omap/am5729-beagleboneai.dts
+++ b/arch/arm/boot/dts/ti/omap/am5729-beagleboneai.dts
@@ -197,7 +197,7 @@
 	extcon_usb1: extcon_usb1 {
 		compatible = "linux,extcon-usb-gpio";
 		ti,enable-id-detection;
-		id-gpio = <&gpio3 13 GPIO_ACTIVE_HIGH>;
+		id-gpios = <&gpio3 13 GPIO_ACTIVE_HIGH>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/ti/omap/am572x-idk-common.dtsi b/arch/arm/boot/dts/ti/omap/am572x-idk-common.dtsi
index 1d66278c3a72..3fca84819dc0 100644
--- a/arch/arm/boot/dts/ti/omap/am572x-idk-common.dtsi
+++ b/arch/arm/boot/dts/ti/omap/am572x-idk-common.dtsi
@@ -169,8 +169,8 @@
 };
 
 &extcon_usb2 {
-	id-gpio = <&gpio3 16 GPIO_ACTIVE_HIGH>;
-	vbus-gpio = <&gpio3 26 GPIO_ACTIVE_HIGH>;
+	id-gpios = <&gpio3 16 GPIO_ACTIVE_HIGH>;
+	vbus-gpios = <&gpio3 26 GPIO_ACTIVE_HIGH>;
 };
 
 &sn65hvs882 {
diff --git a/arch/arm/boot/dts/ti/omap/dra7-evm-common.dtsi b/arch/arm/boot/dts/ti/omap/dra7-evm-common.dtsi
index 4cdffd6db740..ed5199d7acd8 100644
--- a/arch/arm/boot/dts/ti/omap/dra7-evm-common.dtsi
+++ b/arch/arm/boot/dts/ti/omap/dra7-evm-common.dtsi
@@ -15,12 +15,12 @@
 
 	extcon_usb1: extcon_usb1 {
 		compatible = "linux,extcon-usb-gpio";
-		id-gpio = <&pcf_gpio_21 1 GPIO_ACTIVE_HIGH>;
+		id-gpios = <&pcf_gpio_21 1 GPIO_ACTIVE_HIGH>;
 	};
 
 	extcon_usb2: extcon_usb2 {
 		compatible = "linux,extcon-usb-gpio";
-		id-gpio = <&pcf_gpio_21 2 GPIO_ACTIVE_HIGH>;
+		id-gpios = <&pcf_gpio_21 2 GPIO_ACTIVE_HIGH>;
 	};
 
 	sound0: sound0 {
diff --git a/arch/arm/boot/dts/ti/omap/dra7.dtsi b/arch/arm/boot/dts/ti/omap/dra7.dtsi
index 3f3e52e3b375..6509c742fb58 100644
--- a/arch/arm/boot/dts/ti/omap/dra7.dtsi
+++ b/arch/arm/boot/dts/ti/omap/dra7.dtsi
@@ -147,7 +147,7 @@
 
 		l3-noc@44000000 {
 			compatible = "ti,dra7-l3-noc";
-			reg = <0x44000000 0x1000>,
+			reg = <0x44000000 0x1000000>,
 			      <0x45000000 0x1000>;
 			interrupts-extended = <&crossbar_mpu GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>,
 					      <&wakeupgen GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/boot/dts/ti/omap/dra71-evm.dts b/arch/arm/boot/dts/ti/omap/dra71-evm.dts
index a64364443031..f747ac56eb92 100644
--- a/arch/arm/boot/dts/ti/omap/dra71-evm.dts
+++ b/arch/arm/boot/dts/ti/omap/dra71-evm.dts
@@ -293,11 +293,11 @@
 };
 
 &extcon_usb1 {
-	vbus-gpio = <&pcf_lcd 14 GPIO_ACTIVE_HIGH>;
+	vbus-gpios = <&pcf_lcd 14 GPIO_ACTIVE_HIGH>;
 };
 
 &extcon_usb2 {
-	vbus-gpio = <&pcf_lcd 15 GPIO_ACTIVE_HIGH>;
+	vbus-gpios = <&pcf_lcd 15 GPIO_ACTIVE_HIGH>;
 };
 
 &ipu2 {
diff --git a/arch/arm/boot/dts/ti/omap/dra72-evm-common.dtsi b/arch/arm/boot/dts/ti/omap/dra72-evm-common.dtsi
index 31ab0c60ca75..f8151c61488e 100644
--- a/arch/arm/boot/dts/ti/omap/dra72-evm-common.dtsi
+++ b/arch/arm/boot/dts/ti/omap/dra72-evm-common.dtsi
@@ -96,12 +96,12 @@
 
 	extcon_usb1: extcon_usb1 {
 		compatible = "linux,extcon-usb-gpio";
-		id-gpio = <&pcf_gpio_21 1 GPIO_ACTIVE_HIGH>;
+		id-gpios = <&pcf_gpio_21 1 GPIO_ACTIVE_HIGH>;
 	};
 
 	extcon_usb2: extcon_usb2 {
 		compatible = "linux,extcon-usb-gpio";
-		id-gpio = <&pcf_gpio_21 2 GPIO_ACTIVE_HIGH>;
+		id-gpios = <&pcf_gpio_21 2 GPIO_ACTIVE_HIGH>;
 	};
 
 	hdmi0: connector {
diff --git a/arch/arm/boot/dts/ti/omap/dra76-evm.dts b/arch/arm/boot/dts/ti/omap/dra76-evm.dts
index 57868ac60d29..cf9c3d35b049 100644
--- a/arch/arm/boot/dts/ti/omap/dra76-evm.dts
+++ b/arch/arm/boot/dts/ti/omap/dra76-evm.dts
@@ -533,11 +533,11 @@
 };
 
 &extcon_usb1 {
-	vbus-gpio = <&pcf_lcd 14 GPIO_ACTIVE_HIGH>;
+	vbus-gpios = <&pcf_lcd 14 GPIO_ACTIVE_HIGH>;
 };
 
 &extcon_usb2 {
-	vbus-gpio = <&pcf_lcd 15 GPIO_ACTIVE_HIGH>;
+	vbus-gpios = <&pcf_lcd 15 GPIO_ACTIVE_HIGH>;
 };
 
 &m_can0 {
diff --git a/arch/arm/boot/dts/ti/omap/logicpd-torpedo-37xx-devkit.dts b/arch/arm/boot/dts/ti/omap/logicpd-torpedo-37xx-devkit.dts
index 533ce7ce387a..fbff15a0a0fe 100644
--- a/arch/arm/boot/dts/ti/omap/logicpd-torpedo-37xx-devkit.dts
+++ b/arch/arm/boot/dts/ti/omap/logicpd-torpedo-37xx-devkit.dts
@@ -52,7 +52,7 @@
 
 &uart2 {
 	/delete-property/dma-names;
-	bluetooth {
+	bluetooth-gnss {
 		compatible = "ti,wl1283-st";
 		enable-gpios = <&gpio6 2 GPIO_ACTIVE_HIGH>; /* gpio 162 */
 		max-speed = <3000000>;
diff --git a/arch/arm/boot/dts/ti/omap/motorola-mapphone-common.dtsi b/arch/arm/boot/dts/ti/omap/motorola-mapphone-common.dtsi
index a2bb3609c94f..a0c53d9c2625 100644
--- a/arch/arm/boot/dts/ti/omap/motorola-mapphone-common.dtsi
+++ b/arch/arm/boot/dts/ti/omap/motorola-mapphone-common.dtsi
@@ -6,15 +6,6 @@
 #include "motorola-cpcap-mapphone.dtsi"
 
 / {
-	chosen {
-		stdout-path = &uart3;
-	};
-
-	aliases {
-		display0 = &lcd0;
-		display1 = &hdmi0;
-	};
-
 	/*
 	 * We seem to have only 1021 MB accessible, 1021 - 1022 is locked,
 	 * then 1023 - 1024 seems to contain mbm.
@@ -63,46 +54,6 @@
 		regulator-always-on;
 	};
 
-	/* FS USB Host PHY on port 1 for mdm6600 */
-	fsusb1_phy: usb-phy@1 {
-		compatible = "motorola,mapphone-mdm6600";
-		pinctrl-0 = <&usb_mdm6600_pins>;
-		pinctrl-1 = <&usb_mdm6600_sleep_pins>;
-		pinctrl-names = "default", "sleep";
-		enable-gpios = <&gpio3 31 GPIO_ACTIVE_LOW>;     /* gpio_95 */
-		power-gpios = <&gpio2 22 GPIO_ACTIVE_HIGH>;	/* gpio_54 */
-		reset-gpios = <&gpio2 17 GPIO_ACTIVE_HIGH>;	/* gpio_49 */
-		/* mode: gpio_148 gpio_149 */
-		motorola,mode-gpios = <&gpio5 20 GPIO_ACTIVE_HIGH>,
-				      <&gpio5 21 GPIO_ACTIVE_HIGH>;
-		/* cmd: gpio_103 gpio_104 gpio_142 */
-		motorola,cmd-gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>,
-				     <&gpio4 8 GPIO_ACTIVE_HIGH>,
-				     <&gpio5 14 GPIO_ACTIVE_HIGH>;
-		/* status: gpio_52 gpio_53 gpio_55 */
-		motorola,status-gpios = <&gpio2 20 GPIO_ACTIVE_HIGH>,
-					<&gpio2 21 GPIO_ACTIVE_HIGH>,
-					<&gpio2 23 GPIO_ACTIVE_HIGH>;
-		#phy-cells = <0>;
-	};
-
-	/* HS USB host TLL nop-phy on port 2 for w3glte */
-	hsusb2_phy: usb-phy@2 {
-		compatible = "usb-nop-xceiv";
-		#phy-cells = <0>;
-	};
-
-	/* LCD regulator from sw5 source */
-	lcd_regulator: regulator-lcd {
-		compatible = "regulator-fixed";
-		regulator-name = "lcd";
-		regulator-min-microvolt = <5050000>;
-		regulator-max-microvolt = <5050000>;
-		gpio = <&gpio4 0 GPIO_ACTIVE_HIGH>;	/* gpio96 */
-		enable-active-high;
-		vin-supply = <&sw5>;
-	};
-
 	/* This is probably coming straight from the battery.. */
 	wl12xx_vmmc: regulator-wl12xx {
 		compatible = "regulator-fixed";
@@ -133,41 +84,6 @@
 
 		dais = <&mcbsp2_port>, <&mcbsp3_port>;
 	};
-
-	pwm8: pwm-8 {
-		pinctrl-names = "default";
-		pinctrl-0 = <&vibrator_direction_pin>;
-
-		compatible = "ti,omap-dmtimer-pwm";
-		#pwm-cells = <3>;
-		ti,timers = <&timer8>;
-		ti,clock-source = <0x01>;
-	};
-
-	pwm9: pwm-9 {
-		pinctrl-names = "default";
-		pinctrl-0 = <&vibrator_enable_pin>;
-
-		compatible = "ti,omap-dmtimer-pwm";
-		#pwm-cells = <3>;
-		ti,timers = <&timer9>;
-		ti,clock-source = <0x01>;
-	};
-
-	vibrator {
-		compatible = "pwm-vibrator";
-		pwms = <&pwm9 0 10000000 0>, <&pwm8 0 10000000 0>;
-		pwm-names = "enable", "direction";
-		direction-duty-cycle-ns = <10000000>;
-	};
-
-	backlight: backlight {
-		compatible = "led-backlight";
-
-		leds = <&backlight_led>;
-		brightness-levels = <31 63 95 127 159 191 223 255>;
-		default-brightness-level = <6>;
-	};
 };
 
 &cpu_thermal {
@@ -197,57 +113,6 @@
 	status = "okay";
 };
 
-&dsi1 {
-	status = "okay";
-	vdd-supply = <&vcsi>;
-
-	port {
-		dsi1_out_ep: endpoint {
-			remote-endpoint = <&lcd0_in>;
-			lanes = <0 1 2 3 4 5>;
-		};
-	};
-
-	lcd0: panel@0 {
-		compatible = "motorola,droid4-panel", "panel-dsi-cm";
-		reg = <0>;
-		label = "lcd0";
-		vddi-supply = <&lcd_regulator>;
-		reset-gpios = <&gpio4 5 GPIO_ACTIVE_HIGH>;	/* gpio101 */
-
-		backlight = <&backlight>;
-
-		width-mm = <50>;
-		height-mm = <89>;
-		rotation = <90>;
-
-		panel-timing {
-			clock-frequency = <0>;		/* Calculated by dsi */
-
-			hback-porch = <2>;
-			hactive = <540>;
-			hfront-porch = <0>;
-			hsync-len = <2>;
-
-			vback-porch = <1>;
-			vactive = <960>;
-			vfront-porch = <0>;
-			vsync-len = <1>;
-
-			hsync-active = <0>;
-			vsync-active = <0>;
-			de-active = <1>;
-			pixelclk-active = <1>;
-		};
-
-		port {
-			lcd0_in: endpoint {
-				remote-endpoint = <&dsi1_out_ep>;
-			};
-		};
-	};
-};
-
 &hdmi {
 	status = "okay";
 	pinctrl-0 = <&dss_hdmi_pins>;
@@ -262,13 +127,6 @@
 	};
 };
 
-/* Battery NVRAM on 1-wire handled by w1_ds250x driver */
-&hdqw1w {
-	pinctrl-0 = <&hdq_pins>;
-	pinctrl-names = "default";
-	ti,mode = "1w";
-};
-
 &i2c1 {
 	tmp105@48 {
 		compatible = "ti,tmp105";
@@ -322,34 +180,6 @@
 	};
 };
 
-&i2c2 {
-	touchscreen@4a {
-		compatible = "atmel,maxtouch";
-		reg = <0x4a>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&touchscreen_pins>;
-
-		reset-gpios = <&gpio6 13 GPIO_ACTIVE_LOW>; /* gpio173 */
-
-		/* gpio_183 with sys_nirq2 pad as wakeup */
-		interrupts-extended = <&gpio6 23 IRQ_TYPE_LEVEL_LOW>,
-				      <&omap4_pmx_core 0x160>;
-		interrupt-names = "irq", "wakeup";
-		wakeup-source;
-	};
-
-	isl29030@44 {
-		compatible = "isil,isl29030";
-		reg = <0x44>;
-
-		pinctrl-names = "default";
-		pinctrl-0 = <&als_proximity_pins>;
-
-		interrupt-parent = <&gpio6>;
-		interrupts = <17 IRQ_TYPE_LEVEL_LOW>; /* gpio177 */
-	};
-};
-
 &omap4_pmx_core {
 
 	/* hdmi_hpd.gpio_63 */
@@ -359,13 +189,6 @@
 		>;
 	};
 
-	hdq_pins: hdq-pins {
-		pinctrl-single,pins = <
-		/* 0x4a100120 hdq_sio.hdq_sio aa27 */
-		OMAP4_IOPAD(0x120, PIN_INPUT | MUX_MODE0)
-		>;
-	};
-
 	/* hdmi_cec.hdmi_cec, hdmi_scl.hdmi_scl, hdmi_sda.hdmi_sda */
 	dss_hdmi_pins: dss-hdmi-pins {
 		pinctrl-single,pins = <
@@ -427,73 +250,6 @@
 		>;
 	};
 
-	touchscreen_pins: touchscreen-pins {
-		pinctrl-single,pins = <
-		OMAP4_IOPAD(0x180, PIN_OUTPUT | MUX_MODE3)
-		OMAP4_IOPAD(0x1a0, PIN_INPUT_PULLUP | MUX_MODE3)
-		>;
-	};
-
-	als_proximity_pins: als-proximity-pins {
-		pinctrl-single,pins = <
-		OMAP4_IOPAD(0x18c, PIN_INPUT_PULLUP | MUX_MODE3)
-		>;
-	};
-
-	usb_mdm6600_pins: usb-mdm6600-pins {
-		pinctrl-single,pins = <
-		/* enable 0x4a1000d8 usbb1_ulpitll_dat7.gpio_95 ag16 */
-		OMAP4_IOPAD(0x0d8, PIN_INPUT | MUX_MODE3)
-
-		/* power 0x4a10007c gpmc_nwp.gpio_54 c25 */
-		OMAP4_IOPAD(0x07c, PIN_OUTPUT | MUX_MODE3)
-
-		/* reset 0x4a100072 gpmc_a25.gpio_49 d20 */
-		OMAP4_IOPAD(0x072, PIN_OUTPUT | MUX_MODE3)
-
-		/* mode0/bpwake 0x4a10014e sdmmc5_dat1.gpio_148 af4 */
-		OMAP4_IOPAD(0x14e, PIN_OUTPUT | MUX_MODE3)
-
-		/* mode1/apwake 0x4a100150 sdmmc5_dat2.gpio_149 ag3 */
-		OMAP4_IOPAD(0x150, PIN_OFF_OUTPUT_LOW | PIN_INPUT | MUX_MODE3)
-
-		/* status0 0x4a10007e gpmc_clk.gpio_55 b22 */
-		OMAP4_IOPAD(0x07e, PIN_INPUT | MUX_MODE3)
-
-		/* status1 0x4a10007a gpmc_ncs3.gpio_53 c22 */
-		OMAP4_IOPAD(0x07a, PIN_INPUT | MUX_MODE3)
-
-		/* status2 0x4a100078 gpmc_ncs2.gpio_52 d21 */
-		OMAP4_IOPAD(0x078, PIN_INPUT | MUX_MODE3)
-
-		/* cmd0 0x4a100094 gpmc_ncs6.gpio_103 c24 */
-		OMAP4_IOPAD(0x094, PIN_OUTPUT | MUX_MODE3)
-
-		/* cmd1 0x4a100096 gpmc_ncs7.gpio_104 d24 */
-		OMAP4_IOPAD(0x096, PIN_OUTPUT | MUX_MODE3)
-
-		/* cmd2 0x4a100142 uart3_rts_sd.gpio_142 f28 */
-		OMAP4_IOPAD(0x142, PIN_OUTPUT | MUX_MODE3)
-		>;
-	};
-
-	/* Modem sleep pins to keep gpio_49 high with internal pull */
-	usb_mdm6600_sleep_pins: usb-mdm6600-sleep-pins {
-		pinctrl-single,pins = <
-		OMAP4_IOPAD(0x0d8, PIN_INPUT | MUX_MODE3)
-		OMAP4_IOPAD(0x07c, PIN_OUTPUT | MUX_MODE3)
-		OMAP4_IOPAD(0x072, PIN_INPUT_PULLUP | MUX_MODE7) /* Keep gpio_49 reset high */
-		OMAP4_IOPAD(0x14e, PIN_OUTPUT | MUX_MODE3)
-		OMAP4_IOPAD(0x150, PIN_OFF_OUTPUT_LOW | PIN_INPUT | MUX_MODE3)
-		OMAP4_IOPAD(0x07e, PIN_INPUT | MUX_MODE3)
-		OMAP4_IOPAD(0x07a, PIN_INPUT | MUX_MODE3)
-		OMAP4_IOPAD(0x078, PIN_INPUT | MUX_MODE3)
-		OMAP4_IOPAD(0x094, PIN_OUTPUT | MUX_MODE3)
-		OMAP4_IOPAD(0x096, PIN_OUTPUT | MUX_MODE3)
-		OMAP4_IOPAD(0x142, PIN_OUTPUT | MUX_MODE3)
-		>;
-	};
-
 	usb_ulpi_pins: usb-ulpi-pins {
 		pinctrl-single,pins = <
 		OMAP4_IOPAD(0x196, MUX_MODE7)
@@ -601,18 +357,6 @@
 		OMAP4_IOPAD(0x10c, PIN_INPUT | MUX_MODE1)	/* abe_mcbsp3_fsx */
 		>;
 	};
-
-	vibrator_direction_pin: vibrator-direction-pins {
-		pinctrl-single,pins = <
-		OMAP4_IOPAD(0x1ce, PIN_OUTPUT | MUX_MODE1)	/* dmtimer8_pwm_evt (gpio_27) */
-		>;
-	};
-
-	vibrator_enable_pin: vibrator-enable-pins {
-		pinctrl-single,pins = <
-		OMAP4_IOPAD(0X1d0, PIN_OUTPUT | MUX_MODE1)	/* dmtimer9_pwm_evt (gpio_28) */
-		>;
-	};
 };
 
 &omap4_pmx_wkup {
@@ -629,17 +373,6 @@
 	status = "disabled";
 };
 
-/* Configure pwm clock source for timers 8 & 9 */
-&timer8 {
-	assigned-clocks = <&abe_clkctrl OMAP4_TIMER8_CLKCTRL 24>;
-	assigned-clock-parents = <&sys_32k_ck>;
-};
-
-&timer9 {
-	assigned-clocks = <&l4_per_clkctrl OMAP4_TIMER9_CLKCTRL 24>;
-	assigned-clock-parents = <&sys_32k_ck>;
-};
-
 /*
  * The uart1 port is wired to mdm6600 with rts and cts. The modem uses gpio_149
  * for wake-up events for both the USB PHY and the UART. We can use gpio_149
@@ -672,20 +405,6 @@
 	};
 };
 
-&usbhsohci {
-	phys = <&fsusb1_phy>;
-	phy-names = "usb";
-};
-
-&usbhsehci {
-	phys = <&hsusb2_phy>;
-};
-
-&usbhshost {
-	port1-mode = "ohci-phy-4pin-dpdm";
-	port2-mode = "ehci-tll";
-};
-
 /* Internal UTMI+ PHY used for OTG, CPCAP ULPI PHY for detection and charger */
 &usb_otg_hs {
 	interface-type = <1>;
@@ -698,23 +417,6 @@
 	power = <150>;
 };
 
-&i2c4 {
-	ak8975: magnetometer@c {
-		compatible = "asahi-kasei,ak8975";
-		reg = <0x0c>;
-
-		vdd-supply = <&vhvio>;
-
-		interrupt-parent = <&gpio6>;
-		interrupts = <15 IRQ_TYPE_EDGE_RISING>; /* gpio175 */
-
-		rotation-matrix = "-1", "0", "0",
-				  "0", "1", "0",
-				  "0", "0", "-1";
-
-	};
-};
-
 &mcbsp2 {
 	#sound-dai-cells = <0>;
 	pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/ti/omap/motorola-mapphone-handset.dtsi b/arch/arm/boot/dts/ti/omap/motorola-mapphone-handset.dtsi
new file mode 100644
index 000000000000..f3f9ff02b35f
--- /dev/null
+++ b/arch/arm/boot/dts/ti/omap/motorola-mapphone-handset.dtsi
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/dts-v1/;
+
+#include "motorola-mapphone-common.dtsi"
+
+/ {
+	/* FS USB Host PHY on port 1 for mdm6600 */
+	fsusb1_phy: usb-phy@1 {
+		compatible = "motorola,mapphone-mdm6600";
+		pinctrl-0 = <&usb_mdm6600_pins>;
+		pinctrl-1 = <&usb_mdm6600_sleep_pins>;
+		pinctrl-names = "default", "sleep";
+		enable-gpios = <&gpio3 31 GPIO_ACTIVE_LOW>;     /* gpio_95 */
+		power-gpios = <&gpio2 22 GPIO_ACTIVE_HIGH>;	/* gpio_54 */
+		reset-gpios = <&gpio2 17 GPIO_ACTIVE_HIGH>;	/* gpio_49 */
+		/* mode: gpio_148 gpio_149 */
+		motorola,mode-gpios = <&gpio5 20 GPIO_ACTIVE_HIGH>,
+				      <&gpio5 21 GPIO_ACTIVE_HIGH>;
+		/* cmd: gpio_103 gpio_104 gpio_142 */
+		motorola,cmd-gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>,
+				     <&gpio4 8 GPIO_ACTIVE_HIGH>,
+				     <&gpio5 14 GPIO_ACTIVE_HIGH>;
+		/* status: gpio_52 gpio_53 gpio_55 */
+		motorola,status-gpios = <&gpio2 20 GPIO_ACTIVE_HIGH>,
+					<&gpio2 21 GPIO_ACTIVE_HIGH>,
+					<&gpio2 23 GPIO_ACTIVE_HIGH>;
+		#phy-cells = <0>;
+	};
+
+	/* HS USB host TLL nop-phy on port 2 for w3glte */
+	hsusb2_phy: usb-phy@2 {
+		compatible = "usb-nop-xceiv";
+		#phy-cells = <0>;
+	};
+
+	pwm8: pwm-8 {
+		pinctrl-names = "default";
+		pinctrl-0 = <&vibrator_direction_pin>;
+
+		compatible = "ti,omap-dmtimer-pwm";
+		#pwm-cells = <3>;
+		ti,timers = <&timer8>;
+		ti,clock-source = <0x01>;
+	};
+
+	pwm9: pwm-9 {
+		pinctrl-names = "default";
+		pinctrl-0 = <&vibrator_enable_pin>;
+
+		compatible = "ti,omap-dmtimer-pwm";
+		#pwm-cells = <3>;
+		ti,timers = <&timer9>;
+		ti,clock-source = <0x01>;
+	};
+
+	vibrator {
+		compatible = "pwm-vibrator";
+		pwms = <&pwm9 0 10000000 0>, <&pwm8 0 10000000 0>;
+		pwm-names = "enable", "direction";
+		direction-duty-cycle-ns = <10000000>;
+	};
+};
+
+/* Battery NVRAM on 1-wire handled by w1_ds250x driver */
+&hdqw1w {
+	pinctrl-0 = <&hdq_pins>;
+	pinctrl-names = "default";
+	ti,mode = "1w";
+};
+
+&i2c2 {
+	touchscreen@4a {
+		compatible = "atmel,maxtouch";
+		reg = <0x4a>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&touchscreen_pins>;
+
+		reset-gpios = <&gpio6 13 GPIO_ACTIVE_LOW>; /* gpio173 */
+
+		/* gpio_183 with sys_nirq2 pad as wakeup */
+		interrupts-extended = <&gpio6 23 IRQ_TYPE_LEVEL_LOW>,
+				      <&omap4_pmx_core 0x160>;
+		interrupt-names = "irq", "wakeup";
+		wakeup-source;
+	};
+
+	isl29030@44 {
+		compatible = "isil,isl29030";
+		reg = <0x44>;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&als_proximity_pins>;
+
+		interrupt-parent = <&gpio6>;
+		interrupts = <17 IRQ_TYPE_LEVEL_LOW>; /* gpio177 */
+	};
+};
+
+&omap4_pmx_core {
+	hdq_pins: hdq-pins {
+		pinctrl-single,pins = <
+		/* 0x4a100120 hdq_sio.hdq_sio aa27 */
+		OMAP4_IOPAD(0x120, PIN_INPUT | MUX_MODE0)
+		>;
+	};
+
+	/* kpd_row0.gpio_178 */
+	tmp105_irq: tmp105-irq-pins {
+		pinctrl-single,pins = <
+		OMAP4_IOPAD(0x18e, PIN_INPUT_PULLUP | MUX_MODE3)
+		>;
+	};
+
+	touchscreen_pins: touchscreen-pins {
+		pinctrl-single,pins = <
+		OMAP4_IOPAD(0x180, PIN_OUTPUT | MUX_MODE3)
+		OMAP4_IOPAD(0x1a0, PIN_INPUT_PULLUP | MUX_MODE3)
+		>;
+	};
+
+	usb_mdm6600_pins: usb-mdm6600-pins {
+		pinctrl-single,pins = <
+		/* enable 0x4a1000d8 usbb1_ulpitll_dat7.gpio_95 ag16 */
+		OMAP4_IOPAD(0x0d8, PIN_INPUT | MUX_MODE3)
+
+		/* power 0x4a10007c gpmc_nwp.gpio_54 c25 */
+		OMAP4_IOPAD(0x07c, PIN_OUTPUT | MUX_MODE3)
+
+		/* reset 0x4a100072 gpmc_a25.gpio_49 d20 */
+		OMAP4_IOPAD(0x072, PIN_OUTPUT | MUX_MODE3)
+
+		/* mode0/bpwake 0x4a10014e sdmmc5_dat1.gpio_148 af4 */
+		OMAP4_IOPAD(0x14e, PIN_OUTPUT | MUX_MODE3)
+
+		/* mode1/apwake 0x4a100150 sdmmc5_dat2.gpio_149 ag3 */
+		OMAP4_IOPAD(0x150, PIN_OFF_OUTPUT_LOW | PIN_INPUT | MUX_MODE3)
+
+		/* status0 0x4a10007e gpmc_clk.gpio_55 b22 */
+		OMAP4_IOPAD(0x07e, PIN_INPUT | MUX_MODE3)
+
+		/* status1 0x4a10007a gpmc_ncs3.gpio_53 c22 */
+		OMAP4_IOPAD(0x07a, PIN_INPUT | MUX_MODE3)
+
+		/* status2 0x4a100078 gpmc_ncs2.gpio_52 d21 */
+		OMAP4_IOPAD(0x078, PIN_INPUT | MUX_MODE3)
+
+		/* cmd0 0x4a100094 gpmc_ncs6.gpio_103 c24 */
+		OMAP4_IOPAD(0x094, PIN_OUTPUT | MUX_MODE3)
+
+		/* cmd1 0x4a100096 gpmc_ncs7.gpio_104 d24 */
+		OMAP4_IOPAD(0x096, PIN_OUTPUT | MUX_MODE3)
+
+		/* cmd2 0x4a100142 uart3_rts_sd.gpio_142 f28 */
+		OMAP4_IOPAD(0x142, PIN_OUTPUT | MUX_MODE3)
+		>;
+	};
+
+	/* Modem sleep pins to keep gpio_49 high with internal pull */
+	usb_mdm6600_sleep_pins: usb-mdm6600-sleep-pins {
+		pinctrl-single,pins = <
+		OMAP4_IOPAD(0x0d8, PIN_INPUT | MUX_MODE3)
+		OMAP4_IOPAD(0x07c, PIN_OUTPUT | MUX_MODE3)
+		OMAP4_IOPAD(0x072, PIN_INPUT_PULLUP | MUX_MODE7) /* Keep gpio_49 reset high */
+		OMAP4_IOPAD(0x14e, PIN_OUTPUT | MUX_MODE3)
+		OMAP4_IOPAD(0x150, PIN_OFF_OUTPUT_LOW | PIN_INPUT | MUX_MODE3)
+		OMAP4_IOPAD(0x07e, PIN_INPUT | MUX_MODE3)
+		OMAP4_IOPAD(0x07a, PIN_INPUT | MUX_MODE3)
+		OMAP4_IOPAD(0x078, PIN_INPUT | MUX_MODE3)
+		OMAP4_IOPAD(0x094, PIN_OUTPUT | MUX_MODE3)
+		OMAP4_IOPAD(0x096, PIN_OUTPUT | MUX_MODE3)
+		OMAP4_IOPAD(0x142, PIN_OUTPUT | MUX_MODE3)
+		>;
+	};
+
+	als_proximity_pins: als-proximity-pins {
+		pinctrl-single,pins = <
+		OMAP4_IOPAD(0x18c, PIN_INPUT_PULLUP | MUX_MODE3)
+		>;
+	};
+
+	vibrator_direction_pin: vibrator-direction-pins {
+		pinctrl-single,pins = <
+		OMAP4_IOPAD(0x1ce, PIN_OUTPUT | MUX_MODE1)	/* dmtimer8_pwm_evt (gpio_27) */
+		>;
+	};
+
+	vibrator_enable_pin: vibrator-enable-pins {
+		pinctrl-single,pins = <
+		OMAP4_IOPAD(0X1d0, PIN_OUTPUT | MUX_MODE1)	/* dmtimer9_pwm_evt (gpio_28) */
+		>;
+	};
+};
+
+/* Configure pwm clock source for timers 8 & 9 */
+&timer8 {
+	assigned-clocks = <&abe_clkctrl OMAP4_TIMER8_CLKCTRL 24>;
+	assigned-clock-parents = <&sys_32k_ck>;
+};
+
+&timer9 {
+	assigned-clocks = <&l4_per_clkctrl OMAP4_TIMER9_CLKCTRL 24>;
+	assigned-clock-parents = <&sys_32k_ck>;
+};
+
+&usbhsohci {
+	phys = <&fsusb1_phy>;
+	phy-names = "usb";
+};
+
+&usbhsehci {
+	phys = <&hsusb2_phy>;
+};
+
+&usbhshost {
+	port1-mode = "ohci-phy-4pin-dpdm";
+	port2-mode = "ehci-tll";
+};
+
+&i2c4 {
+	ak8975: magnetometer@c {
+		compatible = "asahi-kasei,ak8975";
+		reg = <0x0c>;
+
+		vdd-supply = <&vhvio>;
+
+		interrupt-parent = <&gpio6>;
+		interrupts = <15 IRQ_TYPE_EDGE_RISING>; /* gpio175 */
+
+		rotation-matrix = "-1", "0", "0",
+				  "0", "1", "0",
+				  "0", "0", "-1";
+
+	};
+};
diff --git a/arch/arm/boot/dts/ti/omap/motorola-mapphone-mz607-mz617.dtsi b/arch/arm/boot/dts/ti/omap/motorola-mapphone-mz607-mz617.dtsi
new file mode 100644
index 000000000000..a356b3a2f24e
--- /dev/null
+++ b/arch/arm/boot/dts/ti/omap/motorola-mapphone-mz607-mz617.dtsi
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/dts-v1/;
+
+#include "motorola-mapphone-common.dtsi"
+
+&keypad {
+	keypad,num-rows = <8>;
+	keypad,num-columns = <8>;
+	linux,keymap = <MATRIX_KEY(5, 0, KEY_VOLUMEUP)>,
+		       <MATRIX_KEY(3, 0, KEY_VOLUMEDOWN)>;
+};
+
+/*
+ * On tablets, mmc1 regulator is vsimcard instead of vwlan2 in the stock kernel
+ * dtb. The regulator may not be wired even if a MMC cage is added though.
+ */
+&mmc1 {
+	vmmc-supply = <&vsimcard>;
+	bus-width = <4>;
+	cd-gpios = <&gpio6 16 GPIO_ACTIVE_LOW>;	/* gpio_176 */
+};
diff --git a/arch/arm/boot/dts/ti/omap/motorola-mapphone-xt8xx.dtsi b/arch/arm/boot/dts/ti/omap/motorola-mapphone-xt8xx.dtsi
new file mode 100644
index 000000000000..8b8de92b5424
--- /dev/null
+++ b/arch/arm/boot/dts/ti/omap/motorola-mapphone-xt8xx.dtsi
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/dts-v1/;
+
+#include "motorola-mapphone-handset.dtsi"
+
+/ {
+	backlight: backlight {
+		compatible = "led-backlight";
+
+		leds = <&backlight_led>;
+		brightness-levels = <31 63 95 127 159 191 223 255>;
+		default-brightness-level = <6>;
+	};
+
+	/* LCD regulator from sw5 source */
+	lcd_regulator: regulator-lcd {
+		compatible = "regulator-fixed";
+		regulator-name = "lcd";
+		regulator-min-microvolt = <5050000>;
+		regulator-max-microvolt = <5050000>;
+		gpio = <&gpio4 0 GPIO_ACTIVE_HIGH>;	/* gpio96 */
+		enable-active-high;
+		vin-supply = <&sw5>;
+	};
+};
+
+&dsi1 {
+	status = "okay";
+	vdd-supply = <&vcsi>;
+
+	port {
+		dsi1_out_ep: endpoint {
+			remote-endpoint = <&lcd0_in>;
+			lanes = <0 1 2 3 4 5>;
+		};
+	};
+
+	lcd0: panel@0 {
+		compatible = "motorola,droid4-panel", "panel-dsi-cm";
+		reg = <0>;
+		label = "lcd0";
+		vddi-supply = <&lcd_regulator>;
+		reset-gpios = <&gpio4 5 GPIO_ACTIVE_HIGH>;	/* gpio101 */
+		backlight = <&backlight>;
+
+		width-mm = <50>;
+		height-mm = <89>;
+		rotation = <90>;
+
+		panel-timing {
+			clock-frequency = <0>;		/* Calculated by dsi */
+
+			hback-porch = <2>;
+			hactive = <540>;
+			hfront-porch = <0>;
+			hsync-len = <2>;
+
+			vback-porch = <1>;
+			vactive = <960>;
+			vfront-porch = <0>;
+			vsync-len = <1>;
+
+			hsync-active = <0>;
+			vsync-active = <0>;
+			de-active = <1>;
+			pixelclk-active = <1>;
+		};
+
+		port {
+			lcd0_in: endpoint {
+				remote-endpoint = <&dsi1_out_ep>;
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/ti/omap/omap4-droid-bionic-xt875.dts b/arch/arm/boot/dts/ti/omap/omap4-droid-bionic-xt875.dts
index ccf03a743678..1d9000f84f1b 100644
--- a/arch/arm/boot/dts/ti/omap/omap4-droid-bionic-xt875.dts
+++ b/arch/arm/boot/dts/ti/omap/omap4-droid-bionic-xt875.dts
@@ -1,11 +1,20 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /dts-v1/;
 
-#include "motorola-mapphone-common.dtsi"
+#include "motorola-mapphone-xt8xx.dtsi"
 
 / {
 	model = "Motorola Droid Bionic XT875";
 	compatible = "motorola,droid-bionic", "ti,omap4430", "ti,omap4";
+
+	chosen {
+		stdout-path = &uart3;
+	};
+
+	aliases {
+		display0 = &lcd0;
+		display1 = &hdmi0;
+	};
 };
 
 &keypad {
diff --git a/arch/arm/boot/dts/ti/omap/omap4-droid4-xt894.dts b/arch/arm/boot/dts/ti/omap/omap4-droid4-xt894.dts
index e833c21f1c01..cc3f3e1b65ea 100644
--- a/arch/arm/boot/dts/ti/omap/omap4-droid4-xt894.dts
+++ b/arch/arm/boot/dts/ti/omap/omap4-droid4-xt894.dts
@@ -1,9 +1,21 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /dts-v1/;
 
-#include "motorola-mapphone-common.dtsi"
+#include "motorola-mapphone-xt8xx.dtsi"
 
 / {
+	model = "Motorola Droid 4 XT894";
+	compatible = "motorola,droid4", "ti,omap4430", "ti,omap4";
+
+	chosen {
+		stdout-path = &uart3;
+	};
+
+	aliases {
+		display0 = &lcd0;
+		display1 = &hdmi0;
+	};
+
 	gpio_keys {
 		compatible = "gpio-keys";
 
@@ -33,11 +45,6 @@
 	};
 };
 
-/ {
-	model = "Motorola Droid 4 XT894";
-	compatible = "motorola,droid4", "ti,omap4430", "ti,omap4";
-};
-
 &keypad {
 	keypad,num-rows = <8>;
 	keypad,num-columns = <8>;
diff --git a/arch/arm/boot/dts/ti/omap/omap4-epson-embt2ws.dts b/arch/arm/boot/dts/ti/omap/omap4-epson-embt2ws.dts
index 01d783826d5f..24f7d0285f79 100644
--- a/arch/arm/boot/dts/ti/omap/omap4-epson-embt2ws.dts
+++ b/arch/arm/boot/dts/ti/omap/omap4-epson-embt2ws.dts
@@ -51,6 +51,12 @@
 		regulator-name = "unknown";
 	};
 
+	wl12xx_pwrseq: wl12xx-pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		clocks = <&twl 1>;
+		clock-names = "ext_clock";
+	};
+
        /* regulator for wl12xx on sdio2 */
 	wl12xx_vmmc: wl12xx-vmmc {
 		pinctrl-names = "default";
@@ -74,6 +80,7 @@
 	twl: pmic@48 {
 		compatible = "ti,twl6032";
 		reg = <0x48>;
+		#clock-cells = <1>;
 		/* IRQ# = 7 */
 		interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>; /* IRQ_SYS_1N cascaded to gic */
 		interrupt-controller;
@@ -294,6 +301,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&wl12xx_pins>;
 	vmmc-supply = <&wl12xx_vmmc>;
+	mmc-pwrseq = <&wl12xx_pwrseq>;
 	interrupts-extended = <&wakeupgen GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH
 			       &omap4_pmx_core 0x12e>;
 	non-removable;
@@ -454,10 +462,12 @@
 	interrupts-extended = <&wakeupgen GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH
 			       &omap4_pmx_core OMAP4_UART2_RX>;
 
-	/*
-	 * BT + GPS in WL1283 in WG7500 requiring CLK32KAUDIO of pmic
-	 * which does not have a driver
-	 */
+	bluetooth-gnss {
+		compatible = "ti,wl1283-st";
+		enable-gpios = <&gpio1 25 GPIO_ACTIVE_HIGH>;	/* GPIO_25 */
+		clocks = <&twl 1>;
+		clock-names = "ext_clock";
+	};
 };
 
 &uart3 {
diff --git a/arch/arm/boot/dts/ti/omap/omap4-xyboard-mz609.dts b/arch/arm/boot/dts/ti/omap/omap4-xyboard-mz609.dts
new file mode 100644
index 000000000000..762934e2d075
--- /dev/null
+++ b/arch/arm/boot/dts/ti/omap/omap4-xyboard-mz609.dts
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/dts-v1/;
+
+#include "motorola-mapphone-mz607-mz617.dtsi"
+
+/ {
+	model = "Motorola Xyboard MZ609";
+	compatible = "motorola,xyboard-mz609", "ti,omap4430", "ti,omap4";
+
+	chosen {
+		stdout-path = &uart3;
+	};
+
+	aliases {
+		display1 = &hdmi0;
+	};
+
+	backlight: backlight {
+		compatible = "led-backlight";
+
+		leds = <&backlight_led>;
+		brightness-levels = <31 63 95 127 159 191 223 255>;
+		default-brightness-level = <6>;
+	};
+};
+
+&i2c1 {
+	led-controller@38 {
+		compatible = "ti,lm3532";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0x38>;
+
+		enable-gpios = <&gpio6 12 GPIO_ACTIVE_HIGH>;
+
+		ramp-up-us = <1024>;
+		ramp-down-us = <8193>;
+
+		backlight_led: led@0 {
+			reg = <0>;
+			led-sources = <2>;
+			ti,led-mode = <0>;
+			label = ":backlight";
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/ti/omap/omap4-xyboard-mz617.dts b/arch/arm/boot/dts/ti/omap/omap4-xyboard-mz617.dts
new file mode 100644
index 000000000000..b9caea3b7f9d
--- /dev/null
+++ b/arch/arm/boot/dts/ti/omap/omap4-xyboard-mz617.dts
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/dts-v1/;
+
+#include "motorola-mapphone-mz607-mz617.dtsi"
+
+/ {
+	model = "Motorola Xyboard MZ617";
+	compatible = "motorola,xyboard-mz617", "ti,omap4430", "ti,omap4";
+
+	chosen {
+		stdout-path = &uart3;
+	};
+
+	aliases {
+		display1 = &hdmi0;
+	};
+};
diff --git a/arch/arm/configs/am200epdkit_defconfig b/arch/arm/configs/am200epdkit_defconfig
index a25834e4c901..134a559aba3d 100644
--- a/arch/arm/configs/am200epdkit_defconfig
+++ b/arch/arm/configs/am200epdkit_defconfig
@@ -1,6 +1,5 @@
 CONFIG_LOCALVERSION="gum"
 CONFIG_SYSVIPC=y
-CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_PREEMPT=y
 CONFIG_EXPERT=y
 # CONFIG_EPOLL is not set
@@ -49,7 +48,6 @@ CONFIG_BLK_DEV_SD=m
 CONFIG_ATA=m
 CONFIG_PATA_PCMCIA=m
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_SMC91X=m
 # CONFIG_LEGACY_PTYS is not set
 CONFIG_SERIAL_PXA=y
diff --git a/arch/arm/configs/aspeed_g4_defconfig b/arch/arm/configs/aspeed_g4_defconfig
index 9d1b297c432e..b3dc0465796f 100644
--- a/arch/arm/configs/aspeed_g4_defconfig
+++ b/arch/arm/configs/aspeed_g4_defconfig
@@ -12,11 +12,12 @@ CONFIG_BLK_DEV_INITRD=y
 # CONFIG_RD_BZIP2 is not set
 # CONFIG_RD_LZO is not set
 # CONFIG_RD_LZ4 is not set
+CONFIG_EXPERT=y
 # CONFIG_UID16 is not set
 # CONFIG_SYSFS_SYSCALL is not set
 # CONFIG_AIO is not set
-CONFIG_EXPERT=y
 CONFIG_PERF_EVENTS=y
+CONFIG_KEXEC=y
 # CONFIG_ARCH_MULTI_V7 is not set
 CONFIG_ARCH_ASPEED=y
 CONFIG_MACH_ASPEED_G4=y
@@ -24,7 +25,6 @@ CONFIG_VMSPLIT_2G=y
 CONFIG_AEABI=y
 CONFIG_UACCESS_WITH_MEMCPY=y
 # CONFIG_ATAGS is not set
-CONFIG_KEXEC=y
 CONFIG_JUMP_LABEL=y
 CONFIG_STRICT_KERNEL_RWX=y
 # CONFIG_BLK_DEBUG_FS is not set
diff --git a/arch/arm/configs/aspeed_g5_defconfig b/arch/arm/configs/aspeed_g5_defconfig
index b55f8f539c5f..3fdf4dbfdea5 100644
--- a/arch/arm/configs/aspeed_g5_defconfig
+++ b/arch/arm/configs/aspeed_g5_defconfig
@@ -12,11 +12,12 @@ CONFIG_BLK_DEV_INITRD=y
 # CONFIG_RD_BZIP2 is not set
 # CONFIG_RD_LZO is not set
 # CONFIG_RD_LZ4 is not set
+CONFIG_EXPERT=y
 # CONFIG_UID16 is not set
 # CONFIG_SYSFS_SYSCALL is not set
 # CONFIG_AIO is not set
-CONFIG_EXPERT=y
 CONFIG_PERF_EVENTS=y
+CONFIG_KEXEC=y
 CONFIG_ARCH_MULTI_V6=y
 CONFIG_ARCH_ASPEED=y
 CONFIG_MACH_ASPEED_G5=y
@@ -29,7 +30,6 @@ CONFIG_NR_CPUS=2
 CONFIG_HIGHMEM=y
 CONFIG_UACCESS_WITH_MEMCPY=y
 # CONFIG_ATAGS is not set
-CONFIG_KEXEC=y
 CONFIG_VFP=y
 CONFIG_NEON=y
 CONFIG_KERNEL_MODE_NEON=y
diff --git a/arch/arm/configs/assabet_defconfig b/arch/arm/configs/assabet_defconfig
index 8ba8eb7a4adf..07ab9eaac4af 100644
--- a/arch/arm/configs/assabet_defconfig
+++ b/arch/arm/configs/assabet_defconfig
@@ -28,7 +28,6 @@ CONFIG_MTD_SA1100=y
 CONFIG_BLK_DEV_LOOP=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_NET_PCMCIA=y
 CONFIG_PCMCIA_PCNET=y
 CONFIG_INPUT_EVDEV=y
diff --git a/arch/arm/configs/at91_dt_defconfig b/arch/arm/configs/at91_dt_defconfig
index 71b5acc78187..1d53aec4c836 100644
--- a/arch/arm/configs/at91_dt_defconfig
+++ b/arch/arm/configs/at91_dt_defconfig
@@ -6,8 +6,9 @@ CONFIG_LOG_BUF_SHIFT=14
 CONFIG_CGROUPS=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-CONFIG_KALLSYMS_ALL=y
 CONFIG_EXPERT=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_KEXEC=y
 CONFIG_ARCH_MULTI_V4T=y
 CONFIG_ARCH_MULTI_V5=y
 # CONFIG_ARCH_MULTI_V7 is not set
@@ -22,7 +23,6 @@ CONFIG_UACCESS_WITH_MEMCPY=y
 CONFIG_ARM_APPENDED_DTB=y
 CONFIG_ARM_ATAG_DTB_COMPAT=y
 CONFIG_CMDLINE="console=ttyS0,115200 initrd=0x21100000,25165824 root=/dev/ram0 rw"
-CONFIG_KEXEC=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
diff --git a/arch/arm/configs/bcm2835_defconfig b/arch/arm/configs/bcm2835_defconfig
index 225a16c0323c..b5f0bd8dd536 100644
--- a/arch/arm/configs/bcm2835_defconfig
+++ b/arch/arm/configs/bcm2835_defconfig
@@ -18,17 +18,17 @@ CONFIG_SCHED_AUTOGROUP=y
 CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-CONFIG_KALLSYMS_ALL=y
 CONFIG_EXPERT=y
+CONFIG_KALLSYMS_ALL=y
 CONFIG_PROFILING=y
 CONFIG_CC_STACKPROTECTOR_REGULAR=y
+CONFIG_CRASH_DUMP=y
 CONFIG_ARCH_MULTI_V6=y
 CONFIG_ARCH_BCM=y
 CONFIG_ARCH_BCM2835=y
 CONFIG_AEABI=y
 CONFIG_SECCOMP=y
 CONFIG_KEXEC=y
-CONFIG_CRASH_DUMP=y
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_STAT=y
 CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE=y
diff --git a/arch/arm/configs/clps711x_defconfig b/arch/arm/configs/clps711x_defconfig
index d7ed1e7c6a90..6fa3477e6b02 100644
--- a/arch/arm/configs/clps711x_defconfig
+++ b/arch/arm/configs/clps711x_defconfig
@@ -6,15 +6,8 @@ CONFIG_RD_LZMA=y
 CONFIG_EXPERT=y
 CONFIG_JUMP_LABEL=y
 CONFIG_PARTITION_ADVANCED=y
-CONFIG_ARCH_CLPS711X=y
-CONFIG_ARCH_AUTCPU12=y
-CONFIG_ARCH_CDB89712=y
-CONFIG_ARCH_CLEP7312=y
-CONFIG_ARCH_EDB7211=y
-CONFIG_ARCH_P720T=y
 CONFIG_AEABI=y
 # CONFIG_COREDUMP is not set
-CONFIG_SLUB=y
 CONFIG_SLUB_TINY=y
 CONFIG_NET=y
 CONFIG_PACKET=y
diff --git a/arch/arm/configs/collie_defconfig b/arch/arm/configs/collie_defconfig
index 69341c33e0cc..01b5a5a73f03 100644
--- a/arch/arm/configs/collie_defconfig
+++ b/arch/arm/configs/collie_defconfig
@@ -13,7 +13,6 @@ CONFIG_CMDLINE="noinitrd root=/dev/mtdblock2 rootfstype=jffs2 fbcon=rotate:1"
 CONFIG_FPE_NWFPE=y
 CONFIG_PM=y
 # CONFIG_SWAP is not set
-CONFIG_SLUB=y
 CONFIG_SLUB_TINY=y
 CONFIG_NET=y
 CONFIG_PACKET=y
@@ -60,9 +59,9 @@ CONFIG_MCP_SA11X0=y
 CONFIG_MCP_UCB1200=y
 CONFIG_MCP_UCB1200_TS=y
 CONFIG_FB=y
-CONFIG_FB_MODE_HELPERS=y
 CONFIG_FB_SA1100=y
 # CONFIG_VGA_CONSOLE is not set
+CONFIG_FB_MODE_HELPERS=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y
 CONFIG_NEW_LEDS=y
diff --git a/arch/arm/configs/davinci_all_defconfig b/arch/arm/configs/davinci_all_defconfig
index 05ea71778ef8..3474e475373a 100644
--- a/arch/arm/configs/davinci_all_defconfig
+++ b/arch/arm/configs/davinci_all_defconfig
@@ -148,8 +148,8 @@ CONFIG_DRM_SIMPLE_BRIDGE=m
 CONFIG_DRM_TINYDRM=m
 CONFIG_TINYDRM_ST7586=m
 CONFIG_FB=y
-CONFIG_FIRMWARE_EDID=y
 CONFIG_FB_DA8XX=y
+CONFIG_FIRMWARE_EDID=y
 CONFIG_BACKLIGHT_PWM=m
 CONFIG_BACKLIGHT_GPIO=m
 CONFIG_FRAMEBUFFER_CONSOLE=y
diff --git a/arch/arm/configs/dove_defconfig b/arch/arm/configs/dove_defconfig
index 46859e6fee5b..2849d17f5856 100644
--- a/arch/arm/configs/dove_defconfig
+++ b/arch/arm/configs/dove_defconfig
@@ -6,9 +6,7 @@ CONFIG_EXPERT=y
 # CONFIG_ARCH_MULTI_V6 is not set
 CONFIG_ARCH_MULTI_V7=y
 CONFIG_ARCH_DOVE=y
-CONFIG_MACH_DOVE_DB=y
 CONFIG_MACH_CM_A510=y
-CONFIG_MACH_DOVE_DT=y
 CONFIG_AEABI=y
 CONFIG_HIGHMEM=y
 CONFIG_ARM_APPENDED_DTB=y
diff --git a/arch/arm/configs/ep93xx_defconfig b/arch/arm/configs/ep93xx_defconfig
index 44e89a980d29..7dece9d98828 100644
--- a/arch/arm/configs/ep93xx_defconfig
+++ b/arch/arm/configs/ep93xx_defconfig
@@ -78,8 +78,8 @@ CONFIG_SPI_EP93XX=y
 CONFIG_WATCHDOG=y
 CONFIG_EP93XX_WATCHDOG=y
 CONFIG_FB=y
-CONFIG_FB_MODE_HELPERS=y
 CONFIG_FB_EP93XX=y
+CONFIG_FB_MODE_HELPERS=y
 CONFIG_LOGO=y
 CONFIG_USB=y
 CONFIG_USB_DYNAMIC_MINORS=y
diff --git a/arch/arm/configs/footbridge_defconfig b/arch/arm/configs/footbridge_defconfig
index c9f4594b7ca9..5f6963687ee4 100644
--- a/arch/arm/configs/footbridge_defconfig
+++ b/arch/arm/configs/footbridge_defconfig
@@ -55,7 +55,6 @@ CONFIG_BLK_DEV_LOOP=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_NET_VENDOR_3COM=y
 CONFIG_VORTEX=y
 CONFIG_NET_PCI=y
diff --git a/arch/arm/configs/gemini_defconfig b/arch/arm/configs/gemini_defconfig
index 592a6e6024d4..7b1daec630cb 100644
--- a/arch/arm/configs/gemini_defconfig
+++ b/arch/arm/configs/gemini_defconfig
@@ -7,13 +7,13 @@ CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_USER_NS=y
 CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_KEXEC=y
 CONFIG_ARCH_MULTI_V4=y
 # CONFIG_ARCH_MULTI_V7 is not set
 CONFIG_ARCH_GEMINI=y
 CONFIG_AEABI=y
 CONFIG_HIGHMEM=y
 CONFIG_CMDLINE="console=ttyS0,115200n8"
-CONFIG_KEXEC=y
 CONFIG_PM=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_BINFMT_MISC=y
diff --git a/arch/arm/configs/imx_v4_v5_defconfig b/arch/arm/configs/imx_v4_v5_defconfig
index ec45e6225225..875c8cdbada7 100644
--- a/arch/arm/configs/imx_v4_v5_defconfig
+++ b/arch/arm/configs/imx_v4_v5_defconfig
@@ -12,11 +12,6 @@ CONFIG_ARCH_MULTI_V4T=y
 CONFIG_ARCH_MULTI_V5=y
 # CONFIG_ARCH_MULTI_V7 is not set
 CONFIG_ARCH_MXC=y
-CONFIG_MACH_MX21ADS=y
-CONFIG_MACH_MX27ADS=y
-CONFIG_MACH_MX27_3DS=y
-CONFIG_MACH_IMX27_VISSTRIM_M10=y
-CONFIG_MACH_PCA100=y
 CONFIG_SOC_IMX1=y
 CONFIG_SOC_IMX25=y
 CONFIG_SOC_IMX27=y
diff --git a/arch/arm/configs/jornada720_defconfig b/arch/arm/configs/jornada720_defconfig
index 91bdcc095884..e6ec768f42e2 100644
--- a/arch/arm/configs/jornada720_defconfig
+++ b/arch/arm/configs/jornada720_defconfig
@@ -1,6 +1,5 @@
 CONFIG_SYSVIPC=y
 CONFIG_LOG_BUF_SHIFT=14
-CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_ARCH_MULTI_V4=y
 # CONFIG_ARCH_MULTI_V7 is not set
 CONFIG_ARCH_SA1100=y
@@ -26,7 +25,6 @@ CONFIG_ATA=y
 CONFIG_PATA_PCMCIA=y
 CONFIG_NETDEVICES=y
 CONFIG_DUMMY=y
-CONFIG_NET_ETHERNET=y
 CONFIG_NET_PCMCIA=y
 CONFIG_INPUT_MOUSEDEV_SCREEN_X=640
 CONFIG_INPUT_MOUSEDEV_SCREEN_Y=240
diff --git a/arch/arm/configs/lpc32xx_defconfig b/arch/arm/configs/lpc32xx_defconfig
index 42053e45f730..98e267213b21 100644
--- a/arch/arm/configs/lpc32xx_defconfig
+++ b/arch/arm/configs/lpc32xx_defconfig
@@ -5,8 +5,6 @@ CONFIG_PREEMPT=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=16
-CONFIG_SYSFS_DEPRECATED=y
-CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_EXPERT=y
diff --git a/arch/arm/configs/mmp2_defconfig b/arch/arm/configs/mmp2_defconfig
index 3d1d6f3b592a..f6f9e135353e 100644
--- a/arch/arm/configs/mmp2_defconfig
+++ b/arch/arm/configs/mmp2_defconfig
@@ -2,7 +2,6 @@ CONFIG_SYSVIPC=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_PREEMPT=y
 CONFIG_LOG_BUF_SHIFT=14
-CONFIG_SYSFS_DEPRECATED_V2=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_ARCH_MMP=y
 CONFIG_AEABI=y
@@ -28,7 +27,6 @@ CONFIG_MTD_ONENAND_GENERIC=y
 CONFIG_MTD_RAW_NAND=y
 # CONFIG_BLK_DEV is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_SMC91X=y
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 # CONFIG_INPUT_KEYBOARD is not set
diff --git a/arch/arm/configs/moxart_defconfig b/arch/arm/configs/moxart_defconfig
index bb6a5222e42f..1d41e73f4903 100644
--- a/arch/arm/configs/moxart_defconfig
+++ b/arch/arm/configs/moxart_defconfig
@@ -4,13 +4,13 @@ CONFIG_NO_HZ_IDLE=y
 CONFIG_PREEMPT=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
+CONFIG_EXPERT=y
 # CONFIG_ELF_CORE is not set
 # CONFIG_BASE_FULL is not set
 # CONFIG_SIGNALFD is not set
 # CONFIG_TIMERFD is not set
 # CONFIG_EVENTFD is not set
 # CONFIG_AIO is not set
-CONFIG_EXPERT=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_ARCH_MULTI_V4=y
 # CONFIG_ARCH_MULTI_V7 is not set
@@ -126,8 +126,8 @@ CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_KGDB=y
 CONFIG_DEBUG_PAGEALLOC=y
 # CONFIG_SLUB_DEBUG is not set
-CONFIG_DEBUG_OBJECTS=y
 CONFIG_DEBUG_KMEMLEAK=y
+CONFIG_DEBUG_OBJECTS=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_MEMORY_INIT=y
 CONFIG_DEBUG_SHIRQ=y
diff --git a/arch/arm/configs/multi_v4t_defconfig b/arch/arm/configs/multi_v4t_defconfig
index a7fabf1d88ff..27d650635d9b 100644
--- a/arch/arm/configs/multi_v4t_defconfig
+++ b/arch/arm/configs/multi_v4t_defconfig
@@ -5,12 +5,12 @@ CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 CONFIG_ARCH_MULTI_V4T=y
 # CONFIG_ARCH_MULTI_V7 is not set
+CONFIG_ARCH_NSPIRE=y
 CONFIG_ARCH_AT91=y
 CONFIG_SOC_AT91RM9200=y
 CONFIG_ARCH_CLPS711X=y
 CONFIG_ARCH_MXC=y
 CONFIG_SOC_IMX1=y
-CONFIG_ARCH_NSPIRE=y
 CONFIG_ARCH_INTEGRATOR=y
 CONFIG_ARCH_INTEGRATOR_AP=y
 CONFIG_INTEGRATOR_IMPD1=y
@@ -25,7 +25,6 @@ CONFIG_ARM_CLPS711X_CPUIDLE=y
 CONFIG_JUMP_LABEL=y
 CONFIG_PARTITION_ADVANCED=y
 # CONFIG_COREDUMP is not set
-CONFIG_SLUB=y
 CONFIG_SLUB_TINY=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
diff --git a/arch/arm/configs/multi_v5_defconfig b/arch/arm/configs/multi_v5_defconfig
index 52bb1a5e25fc..3f4ddcf49ec7 100644
--- a/arch/arm/configs/multi_v5_defconfig
+++ b/arch/arm/configs/multi_v5_defconfig
@@ -62,8 +62,8 @@ CONFIG_NET_DSA=y
 CONFIG_NET_PKTGEN=m
 CONFIG_CFG80211=y
 CONFIG_MAC80211=y
-CONFIG_PCI_MVEBU=y
 CONFIG_PCI_VERSATILE=y
+CONFIG_PCI_MVEBU=y
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_IMX_WEIM=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 10fd74bf85f9..ecb3e286107a 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -5,8 +5,11 @@ CONFIG_CGROUPS=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 CONFIG_PERF_EVENTS=y
+CONFIG_KEXEC=y
 CONFIG_ARCH_VIRT=y
 CONFIG_ARCH_AIROHA=y
+CONFIG_ARCH_SUNPLUS=y
+CONFIG_ARCH_UNIPHIER=y
 CONFIG_ARCH_ACTIONS=y
 CONFIG_ARCH_ALPINE=y
 CONFIG_ARCH_ARTPEC=y
@@ -96,10 +99,8 @@ CONFIG_MACH_SPEAR1310=y
 CONFIG_MACH_SPEAR1340=y
 CONFIG_ARCH_STI=y
 CONFIG_ARCH_STM32=y
-CONFIG_ARCH_SUNPLUS=y
 CONFIG_ARCH_SUNXI=y
 CONFIG_ARCH_TEGRA=y
-CONFIG_ARCH_UNIPHIER=y
 CONFIG_ARCH_U8500=y
 CONFIG_ARCH_VEXPRESS=y
 CONFIG_ARCH_VEXPRESS_TC2_PM=y
@@ -109,7 +110,6 @@ CONFIG_SMP=y
 CONFIG_NR_CPUS=16
 CONFIG_ARM_APPENDED_DTB=y
 CONFIG_ARM_ATAG_DTB_COMPAT=y
-CONFIG_KEXEC=y
 CONFIG_EFI=y
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_STAT=y
@@ -179,10 +179,10 @@ CONFIG_NFC_S3FWRN5_I2C=m
 CONFIG_PCIEPORTBUS=y
 CONFIG_PCI_MVEBU=y
 CONFIG_PCI_TEGRA=y
-CONFIG_PCI_RCAR_GEN2=y
 CONFIG_PCIE_RCAR_HOST=y
-CONFIG_PCI_DRA7XX_EP=y
+CONFIG_PCI_RCAR_GEN2=y
 CONFIG_PCI_LAYERSCAPE=y
+CONFIG_PCI_DRA7XX_EP=y
 CONFIG_PCI_ENDPOINT=y
 CONFIG_PCI_ENDPOINT_CONFIGFS=y
 CONFIG_PCI_EPF_TEST=m
@@ -272,6 +272,7 @@ CONFIG_KS8851=y
 CONFIG_LAN966X_SWITCH=m
 CONFIG_R8169=y
 CONFIG_SH_ETH=y
+CONFIG_RAVB=y
 CONFIG_SMSC911X=y
 CONFIG_SNI_AVE=y
 CONFIG_STMMAC_ETH=y
@@ -523,6 +524,7 @@ CONFIG_CHARGER_TPS65090=y
 CONFIG_BATTERY_ACER_A500=m
 CONFIG_SENSORS_ARM_SCMI=y
 CONFIG_SENSORS_ASPEED=m
+CONFIG_SENSORS_GXP_FAN_CTRL=m
 CONFIG_SENSORS_IIO_HWMON=y
 CONFIG_SENSORS_LAN966X=m
 CONFIG_SENSORS_LM90=y
@@ -531,7 +533,6 @@ CONFIG_SENSORS_NTC_THERMISTOR=m
 CONFIG_SENSORS_PWM_FAN=m
 CONFIG_SENSORS_RASPBERRYPI_HWMON=m
 CONFIG_SENSORS_INA2XX=m
-CONFIG_SENSORS_GXP_FAN_CTRL=m
 CONFIG_CPU_THERMAL=y
 CONFIG_DEVFREQ_THERMAL=y
 CONFIG_IMX_THERMAL=y
@@ -691,6 +692,7 @@ CONFIG_VIDEO_STI_BDISP=m
 CONFIG_VIDEO_STI_DELTA=m
 CONFIG_VIDEO_STI_HVA=m
 CONFIG_VIDEO_STM32_DCMI=m
+CONFIG_VIDEO_STM32_DCMIPP=m
 CONFIG_V4L_TEST_DRIVERS=y
 CONFIG_VIDEO_VIVID=m
 CONFIG_VIDEO_S5C73M3=m
@@ -1072,6 +1074,7 @@ CONFIG_HWSPINLOCK_QCOM=y
 CONFIG_OMAP2PLUS_MBOX=y
 CONFIG_BCM2835_MBOX=y
 CONFIG_QCOM_APCS_IPC=y
+CONFIG_STM32_IPCC=m
 CONFIG_QCOM_IPCC=y
 CONFIG_OMAP_IOMMU=y
 CONFIG_OMAP_IOMMU_DEBUG=y
@@ -1087,20 +1090,18 @@ CONFIG_QCOM_Q6V5_MSS=m
 CONFIG_QCOM_SYSMON=m
 CONFIG_QCOM_WCNSS_PIL=m
 CONFIG_ST_REMOTEPROC=m
+CONFIG_RPMSG_CHAR=m
+CONFIG_RPMSG_CTRL=m
 CONFIG_RPMSG_QCOM_SMD=y
 CONFIG_RPMSG_VIRTIO=m
 CONFIG_ASPEED_LPC_CTRL=m
 CONFIG_ASPEED_LPC_SNOOP=m
 CONFIG_ASPEED_P2A_CTRL=m
-CONFIG_RASPBERRYPI_POWER=y
 CONFIG_QCOM_COMMAND_DB=m
-CONFIG_QCOM_CPR=y
 CONFIG_QCOM_GSBI=y
 CONFIG_QCOM_OCMEM=m
 CONFIG_QCOM_RMTFS_MEM=m
 CONFIG_QCOM_RPMH=y
-CONFIG_QCOM_RPMHPD=y
-CONFIG_QCOM_RPMPD=y
 CONFIG_QCOM_SMEM=y
 CONFIG_QCOM_SMD_RPM=y
 CONFIG_QCOM_SMP2P=y
@@ -1128,11 +1129,15 @@ CONFIG_ARCH_R8A7744=y
 CONFIG_ARCH_R9A06G032=y
 CONFIG_ARCH_SH73A0=y
 CONFIG_ROCKCHIP_IODOMAIN=y
-CONFIG_ROCKCHIP_PM_DOMAINS=y
 CONFIG_ARCH_TEGRA_2x_SOC=y
 CONFIG_ARCH_TEGRA_3x_SOC=y
 CONFIG_ARCH_TEGRA_114_SOC=y
 CONFIG_ARCH_TEGRA_124_SOC=y
+CONFIG_RASPBERRYPI_POWER=y
+CONFIG_QCOM_CPR=y
+CONFIG_QCOM_RPMHPD=y
+CONFIG_QCOM_RPMPD=y
+CONFIG_ROCKCHIP_PM_DOMAINS=y
 CONFIG_ARM_EXYNOS_BUS_DEVFREQ=m
 CONFIG_ARM_TEGRA_DEVFREQ=m
 CONFIG_DEVFREQ_EVENT_EXYNOS_NOCP=m
@@ -1191,6 +1196,7 @@ CONFIG_PWM_TEGRA=y
 CONFIG_PWM_VT8500=y
 CONFIG_KEYSTONE_IRQ=y
 CONFIG_RESET_MCHP_SPARX5=y
+CONFIG_RESET_SCMI=y
 CONFIG_PHY_SUN4I_USB=y
 CONFIG_PHY_SUN9I_USB=y
 CONFIG_PHY_BRCM_USB=m
@@ -1240,8 +1246,8 @@ CONFIG_OPTEE=y
 CONFIG_INTERCONNECT_QCOM=y
 CONFIG_INTERCONNECT_QCOM_MSM8916=y
 CONFIG_COUNTER=m
-CONFIG_STM32_TIMER_CNT=m
 CONFIG_STM32_LPTIMER_CNT=m
+CONFIG_STM32_TIMER_CNT=m
 CONFIG_EXT4_FS=y
 CONFIG_AUTOFS_FS=y
 CONFIG_MSDOS_FS=y
diff --git a/arch/arm/configs/mv78xx0_defconfig b/arch/arm/configs/mv78xx0_defconfig
index 4ed6e8c8e164..3343f72de7ea 100644
--- a/arch/arm/configs/mv78xx0_defconfig
+++ b/arch/arm/configs/mv78xx0_defconfig
@@ -3,7 +3,6 @@ CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_PREEMPT=y
 CONFIG_LOG_BUF_SHIFT=14
-CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_EXPERT=y
 CONFIG_KALLSYMS_ALL=y
 CONFIG_PROFILING=y
@@ -52,7 +51,6 @@ CONFIG_CHR_DEV_SG=m
 CONFIG_ATA=y
 CONFIG_SATA_MV=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_MII=y
 CONFIG_NET_PCI=y
 CONFIG_MV643XX_ETH=y
diff --git a/arch/arm/configs/neponset_defconfig b/arch/arm/configs/neponset_defconfig
index c333406ce5e3..2227f86100ad 100644
--- a/arch/arm/configs/neponset_defconfig
+++ b/arch/arm/configs/neponset_defconfig
@@ -38,7 +38,6 @@ CONFIG_BLK_DEV_RAM_SIZE=8192
 CONFIG_SCSI=m
 CONFIG_BLK_DEV_SD=m
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_NET_VENDOR_SMC=y
 CONFIG_PCMCIA_PCNET=y
 CONFIG_SMC9194=y
diff --git a/arch/arm/configs/netwinder_defconfig b/arch/arm/configs/netwinder_defconfig
index 30ff6fbce5a3..e639e6ad02cb 100644
--- a/arch/arm/configs/netwinder_defconfig
+++ b/arch/arm/configs/netwinder_defconfig
@@ -27,7 +27,6 @@ CONFIG_BLK_DEV_SD=y
 CONFIG_ATA=y
 CONFIG_PATA_WINBOND=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_MII=y
 CONFIG_NET_TULIP=y
 CONFIG_TULIP=y
diff --git a/arch/arm/configs/omap1_defconfig b/arch/arm/configs/omap1_defconfig
index 7c2cc7a89511..729ea8157e2a 100644
--- a/arch/arm/configs/omap1_defconfig
+++ b/arch/arm/configs/omap1_defconfig
@@ -28,7 +28,6 @@ CONFIG_MACH_OMAP_PALMTE=y
 CONFIG_MACH_SX1=y
 CONFIG_MACH_NOKIA770=y
 CONFIG_MACH_AMS_DELTA=y
-CONFIG_MACH_OMAP_GENERIC=y
 CONFIG_AEABI=y
 CONFIG_CMDLINE="root=1f03 rootfstype=jffs2"
 CONFIG_FPE_NWFPE=y
@@ -40,7 +39,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_BINFMT_MISC=y
 # CONFIG_SWAP is not set
-CONFIG_SLUB=y
 CONFIG_SLUB_TINY=y
 # CONFIG_VM_EVENT_COUNTERS is not set
 CONFIG_NET=y
@@ -132,14 +130,14 @@ CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_OMAP_WATCHDOG=y
 CONFIG_FB=y
-CONFIG_FIRMWARE_EDID=y
-CONFIG_FB_MODE_HELPERS=y
 CONFIG_FB_VIRTUAL=y
 CONFIG_FB_OMAP=y
 CONFIG_FB_OMAP_LCDC_EXTERNAL=y
 CONFIG_FB_OMAP_LCDC_HWA742=y
 CONFIG_FB_OMAP_MANUAL_UPDATE=y
 CONFIG_FB_OMAP_LCD_MIPID=y
+CONFIG_FIRMWARE_EDID=y
+CONFIG_FB_MODE_HELPERS=y
 CONFIG_LCD_CLASS_DEVICE=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 7b1b41b4b160..3a166c2f02bd 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -607,6 +607,7 @@ CONFIG_LEDS_LP55XX_COMMON=m
 CONFIG_LEDS_LP5523=m
 CONFIG_LEDS_PCA963X=m
 CONFIG_LEDS_PWM=m
+CONFIG_LEDS_BD2606MVV=m
 CONFIG_LEDS_TRIGGERS=y
 CONFIG_LEDS_TRIGGER_TIMER=m
 CONFIG_LEDS_TRIGGER_ONESHOT=m
@@ -624,6 +625,7 @@ CONFIG_RTC_DRV_PALMAS=m
 CONFIG_RTC_DRV_OMAP=m
 CONFIG_RTC_DRV_CPCAP=m
 CONFIG_DMADEVICES=y
+CONFIG_CLK_TWL=m
 CONFIG_CLK_TWL6040=m
 CONFIG_COMMON_CLK_PALMAS=m
 CONFIG_OMAP_IOMMU=y
@@ -646,6 +648,9 @@ CONFIG_CPCAP_ADC=m
 CONFIG_INA2XX_ADC=m
 CONFIG_TI_AM335X_ADC=m
 CONFIG_TWL4030_MADC=m
+CONFIG_TWL6030_GPADC=m
+CONFIG_MPU3050_I2C=m
+CONFIG_INV_MPU6050_I2C=m
 CONFIG_SENSORS_ISL29028=m
 CONFIG_AK8975=m
 CONFIG_BMP280=m
diff --git a/arch/arm/configs/pxa168_defconfig b/arch/arm/configs/pxa168_defconfig
index ec3a43f9c85e..ce10fe2104bf 100644
--- a/arch/arm/configs/pxa168_defconfig
+++ b/arch/arm/configs/pxa168_defconfig
@@ -1,5 +1,4 @@
 CONFIG_SYSVIPC=y
-CONFIG_SYSFS_DEPRECATED_V2=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
@@ -22,7 +21,6 @@ CONFIG_IP_PNP=y
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
 # CONFIG_BLK_DEV is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_SMC91X=y
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 # CONFIG_INPUT_KEYBOARD is not set
diff --git a/arch/arm/configs/pxa3xx_defconfig b/arch/arm/configs/pxa3xx_defconfig
index 7f95fa273a7d..381356faf382 100644
--- a/arch/arm/configs/pxa3xx_defconfig
+++ b/arch/arm/configs/pxa3xx_defconfig
@@ -1,7 +1,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_PREEMPT=y
 CONFIG_LOG_BUF_SHIFT=18
-CONFIG_SYSFS_DEPRECATED_V2=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_KALLSYMS_ALL=y
 # CONFIG_BLK_DEV_BSG is not set
@@ -34,7 +33,6 @@ CONFIG_MTD_NAND_MARVELL=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_SMC91X=y
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 # CONFIG_KEYBOARD_ATKBD is not set
diff --git a/arch/arm/configs/pxa910_defconfig b/arch/arm/configs/pxa910_defconfig
index 958d958377dc..1f28aea86014 100644
--- a/arch/arm/configs/pxa910_defconfig
+++ b/arch/arm/configs/pxa910_defconfig
@@ -3,7 +3,6 @@ CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_PREEMPT=y
 CONFIG_LOG_BUF_SHIFT=14
-CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_ARCH_MMP=y
 CONFIG_CMDLINE="root=/dev/nfs rootfstype=nfs nfsroot=192.168.2.100:/nfsroot/ ip=192.168.2.101:192.168.2.100::255.255.255.0::eth0:on console=ttyS0,115200 mem=128M earlyprintk"
@@ -23,7 +22,6 @@ CONFIG_IP_PNP=y
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
 # CONFIG_BLK_DEV is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_SMC91X=y
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 # CONFIG_INPUT_KEYBOARD is not set
diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig
index 9e81b1849e4c..f2ca5c9131b5 100644
--- a/arch/arm/configs/pxa_defconfig
+++ b/arch/arm/configs/pxa_defconfig
@@ -10,9 +10,10 @@ CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=13
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_KALLSYMS_ALL=y
 CONFIG_EXPERT=y
+CONFIG_KALLSYMS_ALL=y
 CONFIG_PROFILING=y
+CONFIG_KEXEC=y
 # CONFIG_ARCH_MULTI_V7 is not set
 CONFIG_ARCH_PXA=y
 CONFIG_ARCH_GUMSTIX=y
@@ -22,7 +23,6 @@ CONFIG_MACH_BORZOI=y
 CONFIG_AEABI=y
 CONFIG_ARCH_FORCE_MAX_ORDER=8
 CONFIG_CMDLINE="root=/dev/ram0 ro"
-CONFIG_KEXEC=y
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_STAT=y
 CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
@@ -44,7 +44,6 @@ CONFIG_PARTITION_ADVANCED=y
 CONFIG_LDM_PARTITION=y
 CONFIG_CMDLINE_PARTITION=y
 CONFIG_BINFMT_MISC=y
-CONFIG_SLUB=y
 CONFIG_SLUB_TINY=y
 # CONFIG_COMPACTION is not set
 CONFIG_NET=y
@@ -380,8 +379,6 @@ CONFIG_V4L_MEM2MEM_DRIVERS=y
 CONFIG_VIDEO_PXA27x=m
 CONFIG_DRM=m
 CONFIG_FB=y
-CONFIG_FIRMWARE_EDID=y
-CONFIG_FB_TILEBLITTING=y
 CONFIG_FB_PXA=y
 CONFIG_FB_PXA_OVERLAY=y
 CONFIG_FB_PXA_PARAMETERS=y
@@ -393,6 +390,8 @@ CONFIG_LCD_CORGI=m
 CONFIG_LCD_PLATFORM=m
 CONFIG_BACKLIGHT_PWM=m
 CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FIRMWARE_EDID=y
+CONFIG_FB_TILEBLITTING=y
 CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y
 CONFIG_LOGO=y
 CONFIG_SOUND=m
diff --git a/arch/arm/configs/qcom_defconfig b/arch/arm/configs/qcom_defconfig
index 737d51412eb2..ec52ccece0ca 100644
--- a/arch/arm/configs/qcom_defconfig
+++ b/arch/arm/configs/qcom_defconfig
@@ -6,8 +6,8 @@ CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_CGROUPS=y
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_KALLSYMS_ALL=y
 CONFIG_EXPERT=y
+CONFIG_KALLSYMS_ALL=y
 CONFIG_PROFILING=y
 CONFIG_ARCH_QCOM=y
 CONFIG_ARCH_MSM8X60=y
@@ -139,11 +139,11 @@ CONFIG_PINCTRL_MDM9615=y
 CONFIG_PINCTRL_MSM8X74=y
 CONFIG_PINCTRL_MSM8909=y
 CONFIG_PINCTRL_MSM8916=y
-CONFIG_PINCTRL_QCOM_SPMI_PMIC=y
-CONFIG_PINCTRL_QCOM_SSBI_PMIC=y
 CONFIG_GPIOLIB=y
 CONFIG_PINCTRL_SDX55=y
 CONFIG_PINCTRL_SDX65=y
+CONFIG_PINCTRL_QCOM_SPMI_PMIC=y
+CONFIG_PINCTRL_QCOM_SSBI_PMIC=y
 CONFIG_GPIO_SYSFS=y
 CONFIG_POWER_RESET=y
 CONFIG_POWER_RESET_MSM=y
@@ -259,8 +259,6 @@ CONFIG_QCOM_OCMEM=y
 CONFIG_QCOM_PM=y
 CONFIG_QCOM_RMTFS_MEM=y
 CONFIG_QCOM_RPMH=y
-CONFIG_QCOM_RPMHPD=y
-CONFIG_QCOM_RPMPD=y
 CONFIG_QCOM_SMEM=y
 CONFIG_QCOM_SMD_RPM=y
 CONFIG_QCOM_SMP2P=y
@@ -268,6 +266,8 @@ CONFIG_QCOM_SMSM=y
 CONFIG_QCOM_SOCINFO=y
 CONFIG_QCOM_STATS=y
 CONFIG_QCOM_WCNSS_CTRL=y
+CONFIG_QCOM_RPMHPD=y
+CONFIG_QCOM_RPMPD=y
 CONFIG_EXTCON_QCOM_SPMI_MISC=y
 CONFIG_IIO=y
 CONFIG_IIO_BUFFER_CB=y
diff --git a/arch/arm/configs/realview_defconfig b/arch/arm/configs/realview_defconfig
index a221a99f6472..febea5cf7aaa 100644
--- a/arch/arm/configs/realview_defconfig
+++ b/arch/arm/configs/realview_defconfig
@@ -9,8 +9,6 @@ CONFIG_MACH_REALVIEW_EB=y
 CONFIG_REALVIEW_EB_ARM1136=y
 CONFIG_REALVIEW_EB_ARM1176=y
 CONFIG_REALVIEW_EB_A9MP=y
-CONFIG_REALVIEW_EB_ARM11MP=y
-CONFIG_MACH_REALVIEW_PB11MP=y
 CONFIG_MACH_REALVIEW_PB1176=y
 CONFIG_MACH_REALVIEW_PBA8=y
 CONFIG_MACH_REALVIEW_PBX=y
@@ -58,6 +56,8 @@ CONFIG_GPIOLIB=y
 # CONFIG_HWMON is not set
 CONFIG_REGULATOR=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
+CONFIG_AUXDISPLAY=y
+CONFIG_ARM_CHARLCD=y
 CONFIG_DRM=y
 CONFIG_DRM_PANEL_SIMPLE=y
 CONFIG_DRM_PANEL_EDP=y
@@ -85,8 +85,6 @@ CONFIG_LEDS_TRIGGER_CPU=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_DS1307=y
 CONFIG_RTC_DRV_PL031=y
-CONFIG_AUXDISPLAY=y
-CONFIG_ARM_CHARLCD=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
diff --git a/arch/arm/configs/rpc_defconfig b/arch/arm/configs/rpc_defconfig
index b1d12a2c2ef8..24f1fa868230 100644
--- a/arch/arm/configs/rpc_defconfig
+++ b/arch/arm/configs/rpc_defconfig
@@ -2,13 +2,13 @@
 CONFIG_SYSVIPC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
 CONFIG_ARCH_MULTI_V4=y
 # CONFIG_ARCH_MULTI_V7 is not set
 CONFIG_ARCH_RPC=y
 CONFIG_CPU_SA110=y
 CONFIG_FPE_NWFPE=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_BSD_DISKLABEL=y
 CONFIG_NET=y
@@ -45,7 +45,6 @@ CONFIG_ATA=y
 CONFIG_PATA_ICSIDE=y
 CONFIG_PATA_PLATFORM=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_ARM_ETHER1=y
 CONFIG_ARM_ETHER3=y
 CONFIG_ARM_ETHERH=y
diff --git a/arch/arm/configs/s3c6400_defconfig b/arch/arm/configs/s3c6400_defconfig
index 93258d5b57ff..a37e6ac40825 100644
--- a/arch/arm/configs/s3c6400_defconfig
+++ b/arch/arm/configs/s3c6400_defconfig
@@ -1,5 +1,3 @@
-CONFIG_SYSFS_DEPRECATED=y
-CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_KALLSYMS_ALL=y
 CONFIG_ARCH_MULTI_V6=y
diff --git a/arch/arm/configs/s5pv210_defconfig b/arch/arm/configs/s5pv210_defconfig
index d280169081bd..5dbe85c263de 100644
--- a/arch/arm/configs/s5pv210_defconfig
+++ b/arch/arm/configs/s5pv210_defconfig
@@ -3,8 +3,6 @@ CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_PREEMPT=y
 CONFIG_CGROUPS=y
-CONFIG_SYSFS_DEPRECATED=y
-CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_KALLSYMS_ALL=y
 CONFIG_ARCH_S5PV210=y
diff --git a/arch/arm/configs/sama5_defconfig b/arch/arm/configs/sama5_defconfig
index 0e030063130f..9096a99b5abd 100644
--- a/arch/arm/configs/sama5_defconfig
+++ b/arch/arm/configs/sama5_defconfig
@@ -6,6 +6,7 @@ CONFIG_LOG_BUF_SHIFT=14
 CONFIG_CGROUPS=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
+CONFIG_KEXEC=y
 CONFIG_ARCH_AT91=y
 CONFIG_SOC_SAMA5D2=y
 CONFIG_SOC_SAMA5D3=y
@@ -14,7 +15,6 @@ CONFIG_SOC_SAMA5D4=y
 CONFIG_UACCESS_WITH_MEMCPY=y
 # CONFIG_ATAGS is not set
 CONFIG_CMDLINE="console=ttyS0,115200 initrd=0x21100000,25165824 root=/dev/ram0 rw"
-CONFIG_KEXEC=y
 CONFIG_VFP=y
 CONFIG_NEON=y
 CONFIG_KERNEL_MODE_NEON=y
diff --git a/arch/arm/configs/sama7_defconfig b/arch/arm/configs/sama7_defconfig
index be0cfed4ecf1..7fa5d251ced2 100644
--- a/arch/arm/configs/sama7_defconfig
+++ b/arch/arm/configs/sama7_defconfig
@@ -6,13 +6,11 @@ CONFIG_LOG_BUF_SHIFT=16
 CONFIG_CGROUPS=y
 CONFIG_CGROUP_DEBUG=y
 CONFIG_NAMESPACES=y
-CONFIG_SYSFS_DEPRECATED=y
-CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_EXPERT=y
 # CONFIG_FHANDLE is not set
 # CONFIG_IO_URING is not set
 CONFIG_KALLSYMS_ALL=y
-CONFIG_EXPERT=y
 CONFIG_ARCH_AT91=y
 CONFIG_SOC_SAMA7G5=y
 CONFIG_ATMEL_CLOCKSOURCE_TCB=y
diff --git a/arch/arm/configs/shmobile_defconfig b/arch/arm/configs/shmobile_defconfig
index dfdea295c4af..c47a638172a8 100644
--- a/arch/arm/configs/shmobile_defconfig
+++ b/arch/arm/configs/shmobile_defconfig
@@ -75,6 +75,7 @@ CONFIG_SERIAL_8250=y
 # CONFIG_SERIAL_8250_16550A_VARIANTS is not set
 CONFIG_SERIAL_8250_CONSOLE=y
 # CONFIG_SERIAL_8250_PCI is not set
+# CONFIG_SERIAL_8250_EXAR is not set
 CONFIG_SERIAL_8250_DW=y
 CONFIG_SERIAL_8250_EM=y
 # CONFIG_SERIAL_8250_PERICOM is not set
@@ -134,8 +135,10 @@ CONFIG_VIDEO_ADV7604=y
 CONFIG_VIDEO_ADV7604_CEC=y
 CONFIG_VIDEO_ML86V7667=y
 CONFIG_DRM=y
+CONFIG_DRM_FBDEV_EMULATION=y
 CONFIG_DRM_RCAR_DU=y
 # CONFIG_DRM_RCAR_USE_MIPI_DSI is not set
+CONFIG_DRM_SHMOBILE=y
 CONFIG_DRM_PANEL_SIMPLE=y
 CONFIG_DRM_PANEL_EDP=y
 CONFIG_DRM_DISPLAY_CONNECTOR=y
@@ -144,8 +147,7 @@ CONFIG_DRM_SII902X=y
 CONFIG_DRM_SIMPLE_BRIDGE=y
 CONFIG_DRM_I2C_ADV7511=y
 CONFIG_DRM_I2C_ADV7511_AUDIO=y
-CONFIG_FB=y
-CONFIG_FB_SH_MOBILE_LCDC=y
+CONFIG_FB_DEVICE=y
 CONFIG_BACKLIGHT_PWM=y
 CONFIG_BACKLIGHT_AS3711=y
 CONFIG_SOUND=y
diff --git a/arch/arm/configs/spitz_defconfig b/arch/arm/configs/spitz_defconfig
index 10108b4a978e..294d16ddeb18 100644
--- a/arch/arm/configs/spitz_defconfig
+++ b/arch/arm/configs/spitz_defconfig
@@ -2,7 +2,6 @@ CONFIG_SYSVIPC=y
 CONFIG_PREEMPT=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_LOG_BUF_SHIFT=14
-CONFIG_SYSFS_DEPRECATED_V2=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 CONFIG_PROFILING=y
@@ -87,7 +86,6 @@ CONFIG_CHR_DEV_SG=m
 CONFIG_ATA=y
 CONFIG_PATA_PCMCIA=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_PCMCIA_PCNET=m
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
diff --git a/arch/arm/configs/stm32_defconfig b/arch/arm/configs/stm32_defconfig
index e95aba916547..b9fe3fbed5ae 100644
--- a/arch/arm/configs/stm32_defconfig
+++ b/arch/arm/configs/stm32_defconfig
@@ -4,6 +4,7 @@ CONFIG_PREEMPT=y
 CONFIG_LOG_BUF_SHIFT=16
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_EXPERT=y
 # CONFIG_UID16 is not set
 # CONFIG_BASE_FULL is not set
 # CONFIG_FUTEX is not set
@@ -11,7 +12,6 @@ CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 # CONFIG_SIGNALFD is not set
 # CONFIG_EVENTFD is not set
 # CONFIG_AIO is not set
-CONFIG_EXPERT=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_MMU is not set
 CONFIG_ARCH_STM32=y
diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig
index 8635b7216bfc..d2a094ad360c 100644
--- a/arch/arm/configs/tegra_defconfig
+++ b/arch/arm/configs/tegra_defconfig
@@ -13,13 +13,13 @@ CONFIG_CGROUP_DEBUG=y
 CONFIG_NAMESPACES=y
 CONFIG_USER_NS=y
 CONFIG_BLK_DEV_INITRD=y
-# CONFIG_ELF_CORE is not set
 CONFIG_EXPERT=y
+# CONFIG_ELF_CORE is not set
 CONFIG_PERF_EVENTS=y
+CONFIG_KEXEC=y
 CONFIG_ARCH_TEGRA=y
 CONFIG_SMP=y
 CONFIG_HIGHMEM=y
-CONFIG_KEXEC=y
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
diff --git a/arch/arm/configs/vf610m4_defconfig b/arch/arm/configs/vf610m4_defconfig
index 963ff0a03311..a5609cbfdfb3 100644
--- a/arch/arm/configs/vf610m4_defconfig
+++ b/arch/arm/configs/vf610m4_defconfig
@@ -4,8 +4,8 @@ CONFIG_BLK_DEV_INITRD=y
 # CONFIG_RD_LZMA is not set
 # CONFIG_RD_XZ is not set
 # CONFIG_RD_LZ4 is not set
-CONFIG_KALLSYMS_ALL=y
 CONFIG_EXPERT=y
+CONFIG_KALLSYMS_ALL=y
 # CONFIG_MMU is not set
 CONFIG_ARCH_MXC=y
 CONFIG_SOC_VF610=y
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 56b08ed6cc3b..1815748f5d2a 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -407,12 +407,6 @@ struct pci_dev;
 #define pci_iounmap pci_iounmap
 extern void pci_iounmap(struct pci_dev *dev, void __iomem *addr);
 
-/*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p)	__va(p)
-
 #include <asm-generic/io.h>
 
 #ifdef CONFIG_MMU
diff --git a/arch/arm/include/asm/irq_work.h b/arch/arm/include/asm/irq_work.h
index 3149e4dc1b54..8895999834cc 100644
--- a/arch/arm/include/asm/irq_work.h
+++ b/arch/arm/include/asm/irq_work.h
@@ -9,6 +9,4 @@ static inline bool arch_irq_work_has_interrupt(void)
 	return is_smp();
 }
 
-extern void arch_irq_work_raise(void);
-
 #endif /* _ASM_ARM_IRQ_WORK_H */
diff --git a/arch/arm/include/asm/kexec.h b/arch/arm/include/asm/kexec.h
index e62832dcba76..a8287e7ab9d4 100644
--- a/arch/arm/include/asm/kexec.h
+++ b/arch/arm/include/asm/kexec.h
@@ -2,8 +2,6 @@
 #ifndef _ARM_KEXEC_H
 #define _ARM_KEXEC_H
 
-#ifdef CONFIG_KEXEC
-
 /* Maximum physical address we can use pages from */
 #define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
 /* Maximum address we can reach in physical address mode */
@@ -82,6 +80,4 @@ static inline struct page *boot_pfn_to_page(unsigned long boot_pfn)
 
 #endif /* __ASSEMBLY__ */
 
-#endif /* CONFIG_KEXEC */
-
 #endif /* _ARM_KEXEC_H */
diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index c7d2510e5a78..853c4f81ba4a 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -13,6 +13,7 @@
 #define arch_set_freq_scale topology_set_freq_scale
 #define arch_scale_freq_capacity topology_get_freq_scale
 #define arch_scale_freq_invariant topology_scale_freq_invariant
+#define arch_scale_freq_ref topology_get_freq_ref
 #endif
 
 /* Replace task scheduler's default cpu-invariant accounting */
diff --git a/arch/arm/include/asm/vdso.h b/arch/arm/include/asm/vdso.h
index 422c3afa806a..5b85889f82ee 100644
--- a/arch/arm/include/asm/vdso.h
+++ b/arch/arm/include/asm/vdso.h
@@ -24,11 +24,6 @@ static inline void arm_install_vdso(struct mm_struct *mm, unsigned long addr)
 
 #endif /* CONFIG_VDSO */
 
-int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts);
-int __vdso_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts);
-int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
-int __vdso_clock_getres(clockid_t clock_id, struct old_timespec32 *res);
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index d53f56d6f840..771264d4726a 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -59,7 +59,7 @@ obj-$(CONFIG_FUNCTION_TRACER)	+= entry-ftrace.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o insn.o patch.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o insn.o patch.o
 obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o insn.o patch.o
-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
+obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec.o relocate_kernel.o
 # Main staffs in KPROBES are in arch/arm/probes/ .
 obj-$(CONFIG_KPROBES)		+= patch.o insn.o
 obj-$(CONFIG_OABI_COMPAT)	+= sys_oabi-compat.o
diff --git a/arch/arm/kernel/atags_proc.c b/arch/arm/kernel/atags_proc.c
index 3ec2afe78423..cd09f8ab93e3 100644
--- a/arch/arm/kernel/atags_proc.c
+++ b/arch/arm/kernel/atags_proc.c
@@ -7,7 +7,7 @@
 
 struct buffer {
 	size_t size;
-	char data[];
+	char data[] __counted_by(size);
 };
 
 static ssize_t atags_read(struct file *file, char __user *buf,
@@ -54,7 +54,7 @@ static int __init init_atags_procfs(void)
 
 	WARN_ON(tag->hdr.tag != ATAG_NONE);
 
-	b = kmalloc(sizeof(*b) + size, GFP_KERNEL);
+	b = kmalloc(struct_size(b, data, size), GFP_KERNEL);
 	if (!b)
 		goto nomem;
 
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index 1ae99deeec54..d9fd53841591 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -113,69 +113,6 @@ static const unsigned armv6_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 	[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV6_PERFCTR_ITLB_MISS,
 };
 
-enum armv6mpcore_perf_types {
-	ARMV6MPCORE_PERFCTR_ICACHE_MISS	    = 0x0,
-	ARMV6MPCORE_PERFCTR_IBUF_STALL	    = 0x1,
-	ARMV6MPCORE_PERFCTR_DDEP_STALL	    = 0x2,
-	ARMV6MPCORE_PERFCTR_ITLB_MISS	    = 0x3,
-	ARMV6MPCORE_PERFCTR_DTLB_MISS	    = 0x4,
-	ARMV6MPCORE_PERFCTR_BR_EXEC	    = 0x5,
-	ARMV6MPCORE_PERFCTR_BR_NOTPREDICT   = 0x6,
-	ARMV6MPCORE_PERFCTR_BR_MISPREDICT   = 0x7,
-	ARMV6MPCORE_PERFCTR_INSTR_EXEC	    = 0x8,
-	ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS = 0xA,
-	ARMV6MPCORE_PERFCTR_DCACHE_RDMISS   = 0xB,
-	ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS = 0xC,
-	ARMV6MPCORE_PERFCTR_DCACHE_WRMISS   = 0xD,
-	ARMV6MPCORE_PERFCTR_DCACHE_EVICTION = 0xE,
-	ARMV6MPCORE_PERFCTR_SW_PC_CHANGE    = 0xF,
-	ARMV6MPCORE_PERFCTR_MAIN_TLB_MISS   = 0x10,
-	ARMV6MPCORE_PERFCTR_EXPL_MEM_ACCESS = 0x11,
-	ARMV6MPCORE_PERFCTR_LSU_FULL_STALL  = 0x12,
-	ARMV6MPCORE_PERFCTR_WBUF_DRAINED    = 0x13,
-	ARMV6MPCORE_PERFCTR_CPU_CYCLES	    = 0xFF,
-};
-
-/*
- * The hardware events that we support. We do support cache operations but
- * we have harvard caches and no way to combine instruction and data
- * accesses/misses in hardware.
- */
-static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = {
-	PERF_MAP_ALL_UNSUPPORTED,
-	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV6MPCORE_PERFCTR_CPU_CYCLES,
-	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV6MPCORE_PERFCTR_INSTR_EXEC,
-	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV6MPCORE_PERFCTR_BR_EXEC,
-	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV6MPCORE_PERFCTR_BR_MISPREDICT,
-	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= ARMV6MPCORE_PERFCTR_IBUF_STALL,
-	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= ARMV6MPCORE_PERFCTR_LSU_FULL_STALL,
-};
-
-static const unsigned armv6mpcore_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
-					[PERF_COUNT_HW_CACHE_OP_MAX]
-					[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-	PERF_CACHE_MAP_ALL_UNSUPPORTED,
-
-	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS,
-	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV6MPCORE_PERFCTR_DCACHE_RDMISS,
-	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS,
-	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV6MPCORE_PERFCTR_DCACHE_WRMISS,
-
-	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV6MPCORE_PERFCTR_ICACHE_MISS,
-
-	/*
-	 * The ARM performance counters can count micro DTLB misses, micro ITLB
-	 * misses and main TLB misses. There isn't an event for TLB misses, so
-	 * use the micro misses here and if users want the main TLB misses they
-	 * can use a raw counter.
-	 */
-	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV6MPCORE_PERFCTR_DTLB_MISS,
-	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV6MPCORE_PERFCTR_DTLB_MISS,
-
-	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV6MPCORE_PERFCTR_ITLB_MISS,
-	[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV6MPCORE_PERFCTR_ITLB_MISS,
-};
-
 static inline unsigned long
 armv6_pmcr_read(void)
 {
@@ -268,10 +205,8 @@ static inline void armv6pmu_write_counter(struct perf_event *event, u64 value)
 
 static void armv6pmu_enable_event(struct perf_event *event)
 {
-	unsigned long val, mask, evt, flags;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+	unsigned long val, mask, evt;
 	struct hw_perf_event *hwc = &event->hw;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	if (ARMV6_CYCLE_COUNTER == idx) {
@@ -294,12 +229,10 @@ static void armv6pmu_enable_event(struct perf_event *event)
 	 * Mask out the current event and set the counter to count the event
 	 * that we're interested in.
 	 */
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val &= ~mask;
 	val |= evt;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static irqreturn_t
@@ -362,26 +295,20 @@ armv6pmu_handle_irq(struct arm_pmu *cpu_pmu)
 
 static void armv6pmu_start(struct arm_pmu *cpu_pmu)
 {
-	unsigned long flags, val;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+	unsigned long val;
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val |= ARMV6_PMCR_ENABLE;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void armv6pmu_stop(struct arm_pmu *cpu_pmu)
 {
-	unsigned long flags, val;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+	unsigned long val;
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val &= ~ARMV6_PMCR_ENABLE;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static int
@@ -419,10 +346,8 @@ static void armv6pmu_clear_event_idx(struct pmu_hw_events *cpuc,
 
 static void armv6pmu_disable_event(struct perf_event *event)
 {
-	unsigned long val, mask, evt, flags;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+	unsigned long val, mask, evt;
 	struct hw_perf_event *hwc = &event->hw;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	if (ARMV6_CYCLE_COUNTER == idx) {
@@ -444,43 +369,10 @@ static void armv6pmu_disable_event(struct perf_event *event)
 	 * of ETM bus signal assertion cycles. The external reporting should
 	 * be disabled and so this should never increment.
 	 */
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
-	val = armv6_pmcr_read();
-	val &= ~mask;
-	val |= evt;
-	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
-}
-
-static void armv6mpcore_pmu_disable_event(struct perf_event *event)
-{
-	unsigned long val, mask, flags, evt = 0;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
-	struct hw_perf_event *hwc = &event->hw;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
-	int idx = hwc->idx;
-
-	if (ARMV6_CYCLE_COUNTER == idx) {
-		mask	= ARMV6_PMCR_CCOUNT_IEN;
-	} else if (ARMV6_COUNTER0 == idx) {
-		mask	= ARMV6_PMCR_COUNT0_IEN;
-	} else if (ARMV6_COUNTER1 == idx) {
-		mask	= ARMV6_PMCR_COUNT1_IEN;
-	} else {
-		WARN_ONCE(1, "invalid counter number (%d)\n", idx);
-		return;
-	}
-
-	/*
-	 * Unlike UP ARMv6, we don't have a way of stopping the counters. We
-	 * simply disable the interrupt reporting.
-	 */
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val &= ~mask;
 	val |= evt;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static int armv6_map_event(struct perf_event *event)
@@ -525,40 +417,7 @@ static int armv6_1176_pmu_init(struct arm_pmu *cpu_pmu)
 	return 0;
 }
 
-/*
- * ARMv6mpcore is almost identical to single core ARMv6 with the exception
- * that some of the events have different enumerations and that there is no
- * *hack* to stop the programmable counters. To stop the counters we simply
- * disable the interrupt reporting and update the event. When unthrottling we
- * reset the period and enable the interrupt reporting.
- */
-
-static int armv6mpcore_map_event(struct perf_event *event)
-{
-	return armpmu_map_event(event, &armv6mpcore_perf_map,
-				&armv6mpcore_perf_cache_map, 0xFF);
-}
-
-static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu)
-{
-	cpu_pmu->name		= "armv6_11mpcore";
-	cpu_pmu->handle_irq	= armv6pmu_handle_irq;
-	cpu_pmu->enable		= armv6pmu_enable_event;
-	cpu_pmu->disable	= armv6mpcore_pmu_disable_event;
-	cpu_pmu->read_counter	= armv6pmu_read_counter;
-	cpu_pmu->write_counter	= armv6pmu_write_counter;
-	cpu_pmu->get_event_idx	= armv6pmu_get_event_idx;
-	cpu_pmu->clear_event_idx = armv6pmu_clear_event_idx;
-	cpu_pmu->start		= armv6pmu_start;
-	cpu_pmu->stop		= armv6pmu_stop;
-	cpu_pmu->map_event	= armv6mpcore_map_event;
-	cpu_pmu->num_events	= 3;
-
-	return 0;
-}
-
 static const struct of_device_id armv6_pmu_of_device_ids[] = {
-	{.compatible = "arm,arm11mpcore-pmu",	.data = armv6mpcore_pmu_init},
 	{.compatible = "arm,arm1176-pmu",	.data = armv6_1176_pmu_init},
 	{.compatible = "arm,arm1136-pmu",	.data = armv6_1136_pmu_init},
 	{ /* sentinel value */ }
@@ -568,7 +427,6 @@ static const struct pmu_probe_info armv6_pmu_probe_table[] = {
 	ARM_PMU_PROBE(ARM_CPU_PART_ARM1136, armv6_1136_pmu_init),
 	ARM_PMU_PROBE(ARM_CPU_PART_ARM1156, armv6_1156_pmu_init),
 	ARM_PMU_PROBE(ARM_CPU_PART_ARM1176, armv6_1176_pmu_init),
-	ARM_PMU_PROBE(ARM_CPU_PART_ARM11MPCORE, armv6mpcore_pmu_init),
 	{ /* sentinel value */ }
 };
 
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index eb2190477da1..a3322e2b3ea4 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -870,10 +870,8 @@ static void armv7_pmnc_dump_regs(struct arm_pmu *cpu_pmu)
 
 static void armv7pmu_enable_event(struct perf_event *event)
 {
-	unsigned long flags;
 	struct hw_perf_event *hwc = &event->hw;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	if (!armv7_pmnc_counter_valid(cpu_pmu, idx)) {
@@ -886,7 +884,6 @@ static void armv7pmu_enable_event(struct perf_event *event)
 	 * Enable counter and interrupt, and set the counter to count
 	 * the event that we're interested in.
 	 */
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 
 	/*
 	 * Disable counter
@@ -910,16 +907,12 @@ static void armv7pmu_enable_event(struct perf_event *event)
 	 * Enable counter
 	 */
 	armv7_pmnc_enable_counter(idx);
-
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void armv7pmu_disable_event(struct perf_event *event)
 {
-	unsigned long flags;
 	struct hw_perf_event *hwc = &event->hw;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	if (!armv7_pmnc_counter_valid(cpu_pmu, idx)) {
@@ -931,7 +924,6 @@ static void armv7pmu_disable_event(struct perf_event *event)
 	/*
 	 * Disable counter and interrupt
 	 */
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 
 	/*
 	 * Disable counter
@@ -942,8 +934,6 @@ static void armv7pmu_disable_event(struct perf_event *event)
 	 * Disable interrupt for this counter
 	 */
 	armv7_pmnc_disable_intens(idx);
-
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static irqreturn_t armv7pmu_handle_irq(struct arm_pmu *cpu_pmu)
@@ -1009,24 +999,14 @@ static irqreturn_t armv7pmu_handle_irq(struct arm_pmu *cpu_pmu)
 
 static void armv7pmu_start(struct arm_pmu *cpu_pmu)
 {
-	unsigned long flags;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
-
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	/* Enable all counters */
 	armv7_pmnc_write(armv7_pmnc_read() | ARMV7_PMNC_E);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void armv7pmu_stop(struct arm_pmu *cpu_pmu)
 {
-	unsigned long flags;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
-
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	/* Disable all counters */
 	armv7_pmnc_write(armv7_pmnc_read() & ~ARMV7_PMNC_E);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static int armv7pmu_get_event_idx(struct pmu_hw_events *cpuc,
@@ -1072,8 +1052,10 @@ static int armv7pmu_set_event_filter(struct hw_perf_event *event,
 {
 	unsigned long config_base = 0;
 
-	if (attr->exclude_idle)
-		return -EPERM;
+	if (attr->exclude_idle) {
+		pr_debug("ARM performance counters do not support mode exclusion\n");
+		return -EOPNOTSUPP;
+	}
 	if (attr->exclude_user)
 		config_base |= ARMV7_EXCLUDE_USER;
 	if (attr->exclude_kernel)
@@ -1492,14 +1474,10 @@ static void krait_clearpmu(u32 config_base)
 
 static void krait_pmu_disable_event(struct perf_event *event)
 {
-	unsigned long flags;
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 
 	/* Disable counter and interrupt */
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 
 	/* Disable counter */
 	armv7_pmnc_disable_counter(idx);
@@ -1512,23 +1490,17 @@ static void krait_pmu_disable_event(struct perf_event *event)
 
 	/* Disable interrupt for this counter */
 	armv7_pmnc_disable_intens(idx);
-
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void krait_pmu_enable_event(struct perf_event *event)
 {
-	unsigned long flags;
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 
 	/*
 	 * Enable counter and interrupt, and set the counter to count
 	 * the event that we're interested in.
 	 */
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 
 	/* Disable counter */
 	armv7_pmnc_disable_counter(idx);
@@ -1548,8 +1520,6 @@ static void krait_pmu_enable_event(struct perf_event *event)
 
 	/* Enable counter */
 	armv7_pmnc_enable_counter(idx);
-
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void krait_pmu_reset(void *info)
@@ -1825,14 +1795,10 @@ static void scorpion_clearpmu(u32 config_base)
 
 static void scorpion_pmu_disable_event(struct perf_event *event)
 {
-	unsigned long flags;
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 
 	/* Disable counter and interrupt */
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 
 	/* Disable counter */
 	armv7_pmnc_disable_counter(idx);
@@ -1845,23 +1811,17 @@ static void scorpion_pmu_disable_event(struct perf_event *event)
 
 	/* Disable interrupt for this counter */
 	armv7_pmnc_disable_intens(idx);
-
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void scorpion_pmu_enable_event(struct perf_event *event)
 {
-	unsigned long flags;
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 
 	/*
 	 * Enable counter and interrupt, and set the counter to count
 	 * the event that we're interested in.
 	 */
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 
 	/* Disable counter */
 	armv7_pmnc_disable_counter(idx);
@@ -1881,8 +1841,6 @@ static void scorpion_pmu_enable_event(struct perf_event *event)
 
 	/* Enable counter */
 	armv7_pmnc_enable_counter(idx);
-
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void scorpion_pmu_reset(void *info)
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index f6cdcacfb96d..7a2ba1c689a7 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -203,10 +203,8 @@ xscale1pmu_handle_irq(struct arm_pmu *cpu_pmu)
 
 static void xscale1pmu_enable_event(struct perf_event *event)
 {
-	unsigned long val, mask, evt, flags;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+	unsigned long val, mask, evt;
 	struct hw_perf_event *hwc = &event->hw;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	switch (idx) {
@@ -229,20 +227,16 @@ static void xscale1pmu_enable_event(struct perf_event *event)
 		return;
 	}
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
 	val &= ~mask;
 	val |= evt;
 	xscale1pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void xscale1pmu_disable_event(struct perf_event *event)
 {
-	unsigned long val, mask, evt, flags;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+	unsigned long val, mask, evt;
 	struct hw_perf_event *hwc = &event->hw;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	switch (idx) {
@@ -263,12 +257,10 @@ static void xscale1pmu_disable_event(struct perf_event *event)
 		return;
 	}
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
 	val &= ~mask;
 	val |= evt;
 	xscale1pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static int
@@ -300,26 +292,20 @@ static void xscalepmu_clear_event_idx(struct pmu_hw_events *cpuc,
 
 static void xscale1pmu_start(struct arm_pmu *cpu_pmu)
 {
-	unsigned long flags, val;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+	unsigned long val;
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
 	val |= XSCALE_PMU_ENABLE;
 	xscale1pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void xscale1pmu_stop(struct arm_pmu *cpu_pmu)
 {
-	unsigned long flags, val;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+	unsigned long val;
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
 	val &= ~XSCALE_PMU_ENABLE;
 	xscale1pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static inline u64 xscale1pmu_read_counter(struct perf_event *event)
@@ -549,10 +535,8 @@ xscale2pmu_handle_irq(struct arm_pmu *cpu_pmu)
 
 static void xscale2pmu_enable_event(struct perf_event *event)
 {
-	unsigned long flags, ien, evtsel;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+	unsigned long ien, evtsel;
 	struct hw_perf_event *hwc = &event->hw;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	ien = xscale2pmu_read_int_enable();
@@ -587,18 +571,14 @@ static void xscale2pmu_enable_event(struct perf_event *event)
 		return;
 	}
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	xscale2pmu_write_event_select(evtsel);
 	xscale2pmu_write_int_enable(ien);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void xscale2pmu_disable_event(struct perf_event *event)
 {
-	unsigned long flags, ien, evtsel, of_flags;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+	unsigned long ien, evtsel, of_flags;
 	struct hw_perf_event *hwc = &event->hw;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	ien = xscale2pmu_read_int_enable();
@@ -638,11 +618,9 @@ static void xscale2pmu_disable_event(struct perf_event *event)
 		return;
 	}
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	xscale2pmu_write_event_select(evtsel);
 	xscale2pmu_write_int_enable(ien);
 	xscale2pmu_write_overflow_flags(of_flags);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static int
@@ -663,26 +641,20 @@ out:
 
 static void xscale2pmu_start(struct arm_pmu *cpu_pmu)
 {
-	unsigned long flags, val;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+	unsigned long val;
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale2pmu_read_pmnc() & ~XSCALE_PMU_CNT64;
 	val |= XSCALE_PMU_ENABLE;
 	xscale2pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void xscale2pmu_stop(struct arm_pmu *cpu_pmu)
 {
-	unsigned long flags, val;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+	unsigned long val;
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale2pmu_read_pmnc();
 	val &= ~XSCALE_PMU_ENABLE;
 	xscale2pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static inline u64 xscale2pmu_read_counter(struct perf_event *event)
diff --git a/arch/arm/mach-airoha/airoha.c b/arch/arm/mach-airoha/airoha.c
deleted file mode 100644
index ea23b5abb478..000000000000
--- a/arch/arm/mach-airoha/airoha.c
+++ /dev/null
@@ -1,16 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Device Tree support for Airoha SoCs
- *
- * Copyright (c) 2022 Felix Fietkau <nbd@nbd.name>
- */
-#include <asm/mach/arch.h>
-
-static const char * const airoha_board_dt_compat[] = {
-	"airoha,en7523",
-	NULL,
-};
-
-DT_MACHINE_START(MEDIATEK_DT, "Airoha Cortex-A53 (Device Tree)")
-	.dt_compat	= airoha_board_dt_compat,
-MACHINE_END
diff --git a/arch/arm/mach-asm9260/Kconfig b/arch/arm/mach-asm9260/Kconfig
deleted file mode 100644
index 74e0f61c74c8..000000000000
--- a/arch/arm/mach-asm9260/Kconfig
+++ /dev/null
@@ -1,9 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-config MACH_ASM9260
-	bool "Alphascale ASM9260"
-	depends on ARCH_MULTI_V5
-	depends on CPU_LITTLE_ENDIAN
-	select CPU_ARM926T
-	select ASM9260_TIMER
-	help
-	  Support for Alphascale ASM9260 based platform.
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index 1a26af0fabc7..345b91dc6627 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -1103,6 +1103,7 @@ static void __init at91_pm_secure_init(void)
 	if (res.a0 == 0) {
 		pr_info("AT91: Secure PM: suspend mode set to %s\n",
 			pm_modes[suspend_mode].pattern);
+		soc_pm.data.mode = suspend_mode;
 		return;
 	}
 
@@ -1112,6 +1113,7 @@ static void __init at91_pm_secure_init(void)
 	res = sam_smccc_call(SAMA5_SMC_SIP_GET_SUSPEND_MODE, 0, 0);
 	if (res.a0 == 0) {
 		pr_warn("AT91: Secure PM: failed to get default mode\n");
+		soc_pm.data.mode = -1;
 		return;
 	}
 
@@ -1119,6 +1121,7 @@ static void __init at91_pm_secure_init(void)
 		pm_modes[suspend_mode].pattern);
 
 	soc_pm.data.suspend_mode = res.a1;
+	soc_pm.data.mode = soc_pm.data.suspend_mode;
 }
 static const struct of_device_id atmel_shdwc_ids[] = {
 	{ .compatible = "atmel,sama5d2-shdwc" },
diff --git a/arch/arm/mach-davinci/Kconfig b/arch/arm/mach-davinci/Kconfig
index 4316e1370627..59de137c6f53 100644
--- a/arch/arm/mach-davinci/Kconfig
+++ b/arch/arm/mach-davinci/Kconfig
@@ -4,6 +4,7 @@ menuconfig ARCH_DAVINCI
 	bool "TI DaVinci"
 	depends on ARCH_MULTI_V5
 	depends on CPU_LITTLE_ENDIAN
+	select CPU_ARM926T
 	select DAVINCI_TIMER
 	select ZONE_DMA
 	select PM_GENERIC_DOMAINS if PM
diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c
index 2157493b78a9..444a7eaa320c 100644
--- a/arch/arm/mach-imx/mmdc.c
+++ b/arch/arm/mach-imx/mmdc.c
@@ -13,7 +13,8 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/perf_event.h>
 #include <linux/slab.h>
 
@@ -103,7 +104,7 @@ struct mmdc_pmu {
 	struct device *dev;
 	struct perf_event *mmdc_events[MMDC_NUM_COUNTERS];
 	struct hlist_node node;
-	struct fsl_mmdc_devtype_data *devtype_data;
+	const struct fsl_mmdc_devtype_data *devtype_data;
 	struct clk *mmdc_ipg_clk;
 };
 
@@ -474,8 +475,6 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b
 	struct mmdc_pmu *pmu_mmdc;
 	char *name;
 	int ret;
-	const struct of_device_id *of_id =
-		of_match_device(imx_mmdc_dt_ids, &pdev->dev);
 
 	pmu_mmdc = kzalloc(sizeof(*pmu_mmdc), GFP_KERNEL);
 	if (!pmu_mmdc) {
@@ -501,9 +500,13 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b
 
 	name = devm_kasprintf(&pdev->dev,
 				GFP_KERNEL, "mmdc%d", ret);
+	if (!name) {
+		ret = -ENOMEM;
+		goto pmu_release_id;
+	}
 
 	pmu_mmdc->mmdc_ipg_clk = mmdc_ipg_clk;
-	pmu_mmdc->devtype_data = (struct fsl_mmdc_devtype_data *)of_id->data;
+	pmu_mmdc->devtype_data = device_get_match_data(&pdev->dev);
 
 	hrtimer_init(&pmu_mmdc->hrtimer, CLOCK_MONOTONIC,
 			HRTIMER_MODE_REL);
@@ -523,9 +526,10 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b
 
 pmu_register_err:
 	pr_warn("MMDC Perf PMU failed (%d), disabled\n", ret);
-	ida_simple_remove(&mmdc_ida, pmu_mmdc->id);
 	cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node);
 	hrtimer_cancel(&pmu_mmdc->hrtimer);
+pmu_release_id:
+	ida_simple_remove(&mmdc_ida, pmu_mmdc->id);
 pmu_free:
 	kfree(pmu_mmdc);
 	return ret;
diff --git a/arch/arm/mach-moxart/Kconfig b/arch/arm/mach-moxart/Kconfig
deleted file mode 100644
index 909c6573ba8b..000000000000
--- a/arch/arm/mach-moxart/Kconfig
+++ /dev/null
@@ -1,28 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-menuconfig ARCH_MOXART
-	bool "MOXA ART SoC"
-	depends on ARCH_MULTI_V4
-	depends on CPU_LITTLE_ENDIAN
-	select CPU_FA526
-	select ARM_DMA_MEM_BUFFERABLE
-	select FARADAY_FTINTC010
-	select FTTMR010_TIMER
-	select GPIOLIB
-	select PHYLIB if NETDEVICES
-	help
-	  Say Y here if you want to run your kernel on hardware with a
-	  MOXA ART SoC.
-	  The MOXA ART SoC is based on a Faraday FA526 ARMv4 32-bit
-	  192 MHz CPU with MMU and 16KB/8KB D/I-cache (UC-7112-LX).
-	  Used on models UC-7101, UC-7112/UC-7110, IA240/IA241, IA3341.
-
-if ARCH_MOXART
-
-config MACH_UC7112LX
-	bool "MOXA UC-7112-LX"
-	depends on ARCH_MOXART
-	help
-	  Say Y here if you intend to run this kernel on a MOXA
-	  UC-7112-LX embedded computer.
-
-endif
diff --git a/arch/arm/mach-moxart/Makefile b/arch/arm/mach-moxart/Makefile
deleted file mode 100644
index ded3e38fb98d..000000000000
--- a/arch/arm/mach-moxart/Makefile
+++ /dev/null
@@ -1,4 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-# Object file lists.
-
-obj-$(CONFIG_MACH_UC7112LX)	+= moxart.o
diff --git a/arch/arm/mach-moxart/moxart.c b/arch/arm/mach-moxart/moxart.c
deleted file mode 100644
index f1f58c0c0fa1..000000000000
--- a/arch/arm/mach-moxart/moxart.c
+++ /dev/null
@@ -1,6 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * arch/arm/mach-moxart/moxart.c
- *
- * (C) Copyright 2013, Jonas Jensen <jonas.jensen@gmail.com>
- */
diff --git a/arch/arm/mach-mxs/mach-mxs.c b/arch/arm/mach-mxs/mach-mxs.c
index 3faf9a1e3e36..6e017fa306c8 100644
--- a/arch/arm/mach-mxs/mach-mxs.c
+++ b/arch/arm/mach-mxs/mach-mxs.c
@@ -356,7 +356,9 @@ static int __init mxs_restart_init(void)
 {
 	struct device_node *np;
 
-	np = of_find_compatible_node(NULL, NULL, "fsl,clkctrl");
+	np = of_find_compatible_node(NULL, NULL, "fsl,imx23-clkctrl");
+	if (!np)
+		np = of_find_compatible_node(NULL, NULL, "fsl,imx28-clkctrl");
 	reset_addr = of_iomap(np, 0);
 	if (!reset_addr)
 		return -ENODEV;
diff --git a/arch/arm/mach-nspire/Kconfig b/arch/arm/mach-nspire/Kconfig
deleted file mode 100644
index 0ffdcaca1e6b..000000000000
--- a/arch/arm/mach-nspire/Kconfig
+++ /dev/null
@@ -1,15 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-config ARCH_NSPIRE
-	bool "TI-NSPIRE based"
-	depends on ARCH_MULTI_V4T
-	depends on CPU_LITTLE_ENDIAN
-	select CPU_ARM926T
-	select GENERIC_IRQ_CHIP
-	select ARM_AMBA
-	select ARM_VIC
-	select ARM_TIMER_SP804
-	select NSPIRE_TIMER
-	select POWER_RESET
-	select POWER_RESET_SYSCON
-	help
-	  This enables support for systems using the TI-NSPIRE CPU
diff --git a/arch/arm/mach-nspire/Makefile b/arch/arm/mach-nspire/Makefile
deleted file mode 100644
index 4716b9b9aa7b..000000000000
--- a/arch/arm/mach-nspire/Makefile
+++ /dev/null
@@ -1,2 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-obj-y				+= nspire.o
diff --git a/arch/arm/mach-nspire/nspire.c b/arch/arm/mach-nspire/nspire.c
deleted file mode 100644
index 2fbfc23237ff..000000000000
--- a/arch/arm/mach-nspire/nspire.c
+++ /dev/null
@@ -1,18 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *	Copyright (C) 2013 Daniel Tang <tangrs@tangrs.id.au>
- */
-
-#include <asm/mach/arch.h>
-
-static const char *const nspire_dt_match[] __initconst = {
-	"ti,nspire",
-	"ti,nspire-cx",
-	"ti,nspire-tp",
-	"ti,nspire-clp",
-	NULL,
-};
-
-DT_MACHINE_START(NSPIRE, "TI-NSPIRE")
-	.dt_compat	= nspire_dt_match,
-MACHINE_END
diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c
index 98999aa8cc0c..7f387706368a 100644
--- a/arch/arm/mach-omap2/id.c
+++ b/arch/arm/mach-omap2/id.c
@@ -793,11 +793,16 @@ void __init omap_soc_device_init(void)
 
 	soc_dev_attr->machine  = soc_name;
 	soc_dev_attr->family   = omap_get_family();
+	if (!soc_dev_attr->family) {
+		kfree(soc_dev_attr);
+		return;
+	}
 	soc_dev_attr->revision = soc_rev;
 	soc_dev_attr->custom_attr_group = omap_soc_groups[0];
 
 	soc_dev = soc_device_register(soc_dev_attr);
 	if (IS_ERR(soc_dev)) {
+		kfree(soc_dev_attr->family);
 		kfree(soc_dev_attr);
 		return;
 	}
diff --git a/arch/arm/mach-rda/Kconfig b/arch/arm/mach-rda/Kconfig
deleted file mode 100644
index 4d2e4e046cb3..000000000000
--- a/arch/arm/mach-rda/Kconfig
+++ /dev/null
@@ -1,8 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-menuconfig ARCH_RDA
-	bool "RDA Micro SoCs"
-	depends on ARCH_MULTI_V7
-	select RDA_INTC
-	select RDA_TIMER
-	help
-	  This enables support for the RDA Micro 8810PL SoC family.
diff --git a/arch/arm/mach-sunplus/Kconfig b/arch/arm/mach-sunplus/Kconfig
deleted file mode 100644
index d0c2416e6f24..000000000000
--- a/arch/arm/mach-sunplus/Kconfig
+++ /dev/null
@@ -1,27 +0,0 @@
-# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
-
-menuconfig ARCH_SUNPLUS
-	bool "Sunplus SoCs"
-	depends on ARCH_MULTI_V7
-	help
-	  Support for Sunplus SoC family: SP7021 and succeeding SoC-based systems,
-	  such as the Banana Pi BPI-F2S development board (and derivatives).
-	  (<http://www.sinovoip.com.cn/ecp_view.asp?id=586>)
-	  (<https://tibbo.com/store/plus1.html>)
-
-config SOC_SP7021
-	bool "Sunplus SP7021 SoC support"
-	depends on ARCH_SUNPLUS
-	default ARCH_SUNPLUS
-	select HAVE_ARM_ARCH_TIMER
-	select ARM_GIC
-	select ARM_PSCI
-	select PINCTRL
-	select PINCTRL_SPPCTL
-	select SERIAL_SUNPLUS if TTY
-	select SERIAL_SUNPLUS_CONSOLE if TTY
-	help
-	  Support for Sunplus SP7021 SoC. It is based on ARM 4-core
-	  Cortex-A7 with various peripherals (e.g.: I2C, SPI, SDIO,
-	  Ethernet, etc.), FPGA interface,  chip-to-chip bus.
-	  It is designed for industrial control.
diff --git a/arch/arm/mach-sunplus/Makefile b/arch/arm/mach-sunplus/Makefile
deleted file mode 100644
index d211de6af2db..000000000000
--- a/arch/arm/mach-sunplus/Makefile
+++ /dev/null
@@ -1,8 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile for the linux kernel.
-#
-
-# Object file lists.
-
-obj-$(CONFIG_SOC_SP7021)	+= sp7021.o
diff --git a/arch/arm/mach-sunplus/sp7021.c b/arch/arm/mach-sunplus/sp7021.c
deleted file mode 100644
index 774d0a5bd4eb..000000000000
--- a/arch/arm/mach-sunplus/sp7021.c
+++ /dev/null
@@ -1,16 +0,0 @@
-// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
-/*
- * Copyright (C) Sunplus Technology Co., Ltd.
- *       All rights reserved.
- */
-#include <linux/kernel.h>
-#include <asm/mach/arch.h>
-
-static const char *sp7021_compat[] __initconst = {
-	"sunplus,sp7021",
-	NULL
-};
-
-DT_MACHINE_START(SP7021_DT, "SP7021")
-	.dt_compat	= sp7021_compat,
-MACHINE_END
diff --git a/arch/arm/mach-sunxi/mc_smp.c b/arch/arm/mach-sunxi/mc_smp.c
index cb63921232a6..277f6aa8e6c2 100644
--- a/arch/arm/mach-sunxi/mc_smp.c
+++ b/arch/arm/mach-sunxi/mc_smp.c
@@ -803,16 +803,16 @@ static int __init sunxi_mc_smp_init(void)
 	for (i = 0; i < ARRAY_SIZE(sunxi_mc_smp_data); i++) {
 		ret = of_property_match_string(node, "enable-method",
 					       sunxi_mc_smp_data[i].enable_method);
-		if (!ret)
+		if (ret >= 0)
 			break;
 	}
 
-	is_a83t = sunxi_mc_smp_data[i].is_a83t;
-
 	of_node_put(node);
-	if (ret)
+	if (ret < 0)
 		return -ENODEV;
 
+	is_a83t = sunxi_mc_smp_data[i].is_a83t;
+
 	if (!sunxi_mc_smp_cpu_table_init())
 		return -EINVAL;
 
diff --git a/arch/arm/mach-uniphier/Kconfig b/arch/arm/mach-uniphier/Kconfig
deleted file mode 100644
index e661d2626675..000000000000
--- a/arch/arm/mach-uniphier/Kconfig
+++ /dev/null
@@ -1,15 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-config ARCH_UNIPHIER
-	bool "Socionext UniPhier SoCs"
-	depends on ARCH_MULTI_V7
-	select ARCH_HAS_RESET_CONTROLLER
-	select ARM_AMBA
-	select ARM_GLOBAL_TIMER
-	select ARM_GIC
-	select HAVE_ARM_SCU
-	select HAVE_ARM_TWD if SMP
-	select PINCTRL
-	select RESET_CONTROLLER
-	help
-	  Support for UniPhier SoC family developed by Socionext Inc.
-	  (formerly, System LSI Business Division of Panasonic Corporation)
diff --git a/arch/arm/mach-versatile/Kconfig b/arch/arm/mach-versatile/Kconfig
index b1519b4dc03a..e029270c2687 100644
--- a/arch/arm/mach-versatile/Kconfig
+++ b/arch/arm/mach-versatile/Kconfig
@@ -201,23 +201,6 @@ config REALVIEW_EB_A9MP
 	  Enable support for the Cortex-A9MPCore tile fitted to the
 	  Realview(R) Emulation Baseboard platform.
 
-config REALVIEW_EB_ARM11MP
-	bool "Support ARM11MPCore Tile"
-	depends on MACH_REALVIEW_EB && ARCH_MULTI_V6
-	select HAVE_SMP
-	help
-	  Enable support for the ARM11MPCore tile fitted to the Realview(R)
-	  Emulation Baseboard platform.
-
-config MACH_REALVIEW_PB11MP
-	bool "Support RealView(R) Platform Baseboard for ARM11MPCore"
-	depends on ARCH_MULTI_V6
-	select HAVE_SMP
-	help
-	  Include support for the ARM(R) RealView(R) Platform Baseboard for
-	  the ARM11MPCore.  This platform has an on-board ARM11MPCore and has
-	  support for PCI-E and Compact Flash.
-
 # ARMv6 CPU without K extensions, but does have the new exclusive ops
 config MACH_REALVIEW_PB1176
 	bool "Support RealView(R) Platform Baseboard for ARM1176JZF-S"
diff --git a/arch/arm/mach-versatile/platsmp-realview.c b/arch/arm/mach-versatile/platsmp-realview.c
index 5d363385c801..6965a1de727b 100644
--- a/arch/arm/mach-versatile/platsmp-realview.c
+++ b/arch/arm/mach-versatile/platsmp-realview.c
@@ -18,6 +18,11 @@
 #define REALVIEW_SYS_FLAGSSET_OFFSET	0x30
 
 static const struct of_device_id realview_scu_match[] = {
+	/*
+	 * The ARM11MP SCU compatible is only provided as fallback for
+	 * old RealView EB Cortex-A9 device trees that were using this
+	 * compatible by mistake.
+	 */
 	{ .compatible = "arm,arm11mp-scu", },
 	{ .compatible = "arm,cortex-a9-scu", },
 	{ .compatible = "arm,cortex-a5-scu", },
@@ -27,7 +32,6 @@ static const struct of_device_id realview_scu_match[] = {
 static const struct of_device_id realview_syscon_match[] = {
         { .compatible = "arm,core-module-integrator", },
         { .compatible = "arm,realview-eb-syscon", },
-        { .compatible = "arm,realview-pb11mp-syscon", },
         { .compatible = "arm,realview-pbx-syscon", },
         { },
 };
diff --git a/arch/arm/mach-versatile/realview.c b/arch/arm/mach-versatile/realview.c
index a3933e2373d5..36a6f6bc4fdd 100644
--- a/arch/arm/mach-versatile/realview.c
+++ b/arch/arm/mach-versatile/realview.c
@@ -9,7 +9,6 @@
 static const char *const realview_dt_platform_compat[] __initconst = {
 	"arm,realview-eb",
 	"arm,realview-pb1176",
-	"arm,realview-pb11mp",
 	"arm,realview-pba8",
 	"arm,realview-pbx",
 	NULL,
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index c164cde50243..2b6f50dd5478 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -937,24 +937,6 @@ config VDSO
 	  You must have glibc 2.22 or later for programs to seamlessly
 	  take advantage of this.
 
-config DMA_CACHE_RWFO
-	bool "Enable read/write for ownership DMA cache maintenance"
-	depends on CPU_V6K && SMP
-	default y
-	help
-	  The Snoop Control Unit on ARM11MPCore does not detect the
-	  cache maintenance operations and the dma_{map,unmap}_area()
-	  functions may leave stale cache entries on other CPUs. By
-	  enabling this option, Read or Write For Ownership in the ARMv6
-	  DMA cache maintenance functions is performed. These LDR/STR
-	  instructions change the cache line state to shared or modified
-	  so that the cache operation has the desired effect.
-
-	  Note that the workaround is only valid on processors that do
-	  not perform speculative loads into the D-cache. For such
-	  processors, if cache maintenance operations are not broadcast
-	  in hardware, other workarounds are needed (e.g. cache
-	  maintenance broadcasting in software via FIQ).
 
 config OUTER_CACHE
 	bool
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index 250c83bf7158..44211d8a296f 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -201,10 +201,6 @@ ENTRY(v6_flush_kern_dcache_area)
  *	- end     - virtual end address of region
  */
 v6_dma_inv_range:
-#ifdef CONFIG_DMA_CACHE_RWFO
-	ldrb	r2, [r0]			@ read for ownership
-	strb	r2, [r0]			@ write for ownership
-#endif
 	tst	r0, #D_CACHE_LINE_SIZE - 1
 	bic	r0, r0, #D_CACHE_LINE_SIZE - 1
 #ifdef HARVARD_CACHE
@@ -213,10 +209,6 @@ v6_dma_inv_range:
 	mcrne	p15, 0, r0, c7, c11, 1		@ clean unified line
 #endif
 	tst	r1, #D_CACHE_LINE_SIZE - 1
-#ifdef CONFIG_DMA_CACHE_RWFO
-	ldrbne	r2, [r1, #-1]			@ read for ownership
-	strbne	r2, [r1, #-1]			@ write for ownership
-#endif
 	bic	r1, r1, #D_CACHE_LINE_SIZE - 1
 #ifdef HARVARD_CACHE
 	mcrne	p15, 0, r1, c7, c14, 1		@ clean & invalidate D line
@@ -231,10 +223,6 @@ v6_dma_inv_range:
 #endif
 	add	r0, r0, #D_CACHE_LINE_SIZE
 	cmp	r0, r1
-#ifdef CONFIG_DMA_CACHE_RWFO
-	ldrlo	r2, [r0]			@ read for ownership
-	strlo	r2, [r0]			@ write for ownership
-#endif
 	blo	1b
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c10, 4		@ drain write buffer
@@ -248,9 +236,6 @@ v6_dma_inv_range:
 v6_dma_clean_range:
 	bic	r0, r0, #D_CACHE_LINE_SIZE - 1
 1:
-#ifdef CONFIG_DMA_CACHE_RWFO
-	ldr	r2, [r0]			@ read for ownership
-#endif
 #ifdef HARVARD_CACHE
 	mcr	p15, 0, r0, c7, c10, 1		@ clean D line
 #else
@@ -269,10 +254,6 @@ v6_dma_clean_range:
  *	- end     - virtual end address of region
  */
 ENTRY(v6_dma_flush_range)
-#ifdef CONFIG_DMA_CACHE_RWFO
-	ldrb	r2, [r0]		@ read for ownership
-	strb	r2, [r0]		@ write for ownership
-#endif
 	bic	r0, r0, #D_CACHE_LINE_SIZE - 1
 1:
 #ifdef HARVARD_CACHE
@@ -282,10 +263,6 @@ ENTRY(v6_dma_flush_range)
 #endif
 	add	r0, r0, #D_CACHE_LINE_SIZE
 	cmp	r0, r1
-#ifdef CONFIG_DMA_CACHE_RWFO
-	ldrblo	r2, [r0]			@ read for ownership
-	strblo	r2, [r0]			@ write for ownership
-#endif
 	blo	1b
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c10, 4		@ drain write buffer
@@ -301,13 +278,7 @@ ENTRY(v6_dma_map_area)
 	add	r1, r1, r0
 	teq	r2, #DMA_FROM_DEVICE
 	beq	v6_dma_inv_range
-#ifndef CONFIG_DMA_CACHE_RWFO
 	b	v6_dma_clean_range
-#else
-	teq	r2, #DMA_TO_DEVICE
-	beq	v6_dma_clean_range
-	b	v6_dma_flush_range
-#endif
 ENDPROC(v6_dma_map_area)
 
 /*
@@ -317,11 +288,9 @@ ENDPROC(v6_dma_map_area)
  *	- dir	- DMA direction
  */
 ENTRY(v6_dma_unmap_area)
-#ifndef CONFIG_DMA_CACHE_RWFO
 	add	r1, r1, r0
 	teq	r2, #DMA_TO_DEVICE
 	bne	v6_dma_inv_range
-#endif
 	ret	lr
 ENDPROC(v6_dma_unmap_area)
 
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 584f9528c996..b6c9e01e14f5 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -470,3 +470,8 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount
+459	common	lsm_get_self_attr		sys_lsm_get_self_attr
+460	common	lsm_set_self_attr		sys_lsm_set_self_attr
+461	common	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/arm/vdso/vgettimeofday.c b/arch/arm/vdso/vgettimeofday.c
index a003beacac76..3554aa35f1ba 100644
--- a/arch/arm/vdso/vgettimeofday.c
+++ b/arch/arm/vdso/vgettimeofday.c
@@ -8,6 +8,7 @@
 #include <linux/types.h>
 #include <asm/vdso.h>
 #include <asm/unwind.h>
+#include <vdso/gettime.h>
 
 int __vdso_clock_gettime(clockid_t clock,
 			 struct old_timespec32 *ts)
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 9afdc4c4a5dc..a395b6c0aae2 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -484,7 +484,8 @@ static int __init xen_guest_init(void)
 	 * for secondary CPUs as they are brought up.
 	 * For uniformity we use VCPUOP_register_vcpu_info even on cpu0.
 	 */
-	xen_vcpu_info = alloc_percpu(struct vcpu_info);
+	xen_vcpu_info = __alloc_percpu(sizeof(struct vcpu_info),
+				       1 << fls(sizeof(struct vcpu_info) - 1));
 	if (xen_vcpu_info == NULL)
 		return -ENOMEM;
 
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 7b071a00425d..8f6cf1221b6a 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -36,6 +36,7 @@ config ARM64
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PTE_DEVMAP
 	select ARCH_HAS_PTE_SPECIAL
+	select ARCH_HAS_HW_PTE_YOUNG
 	select ARCH_HAS_SETUP_DMA_OPS
 	select ARCH_HAS_SET_DIRECT_MAP
 	select ARCH_HAS_SET_MEMORY
@@ -154,7 +155,7 @@ config ARM64
 	select HAVE_MOVE_PUD
 	select HAVE_PCI
 	select HAVE_ACPI_APEI if (ACPI && EFI)
-	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
+	select HAVE_ALIGNED_STRUCT_PAGE
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_BITREVERSE
 	select HAVE_ARCH_COMPILER_H
@@ -1519,15 +1520,15 @@ config XEN
 
 # include/linux/mmzone.h requires the following to be true:
 #
-#   MAX_ORDER + PAGE_SHIFT <= SECTION_SIZE_BITS
+#   MAX_PAGE_ORDER + PAGE_SHIFT <= SECTION_SIZE_BITS
 #
-# so the maximum value of MAX_ORDER is SECTION_SIZE_BITS - PAGE_SHIFT:
+# so the maximum value of MAX_PAGE_ORDER is SECTION_SIZE_BITS - PAGE_SHIFT:
 #
-#     | SECTION_SIZE_BITS |  PAGE_SHIFT  |  max MAX_ORDER  |  default MAX_ORDER |
-# ----+-------------------+--------------+-----------------+--------------------+
-# 4K  |       27          |      12      |       15        |         10         |
-# 16K |       27          |      14      |       13        |         11         |
-# 64K |       29          |      16      |       13        |         13         |
+#     | SECTION_SIZE_BITS |  PAGE_SHIFT  |  max MAX_PAGE_ORDER  |  default MAX_PAGE_ORDER |
+# ----+-------------------+--------------+----------------------+-------------------------+
+# 4K  |       27          |      12      |       15             |         10              |
+# 16K |       27          |      14      |       13             |         11              |
+# 64K |       29          |      16      |       13             |         13              |
 config ARCH_FORCE_MAX_ORDER
 	int
 	default "13" if ARM64_64K_PAGES
@@ -1535,21 +1536,21 @@ config ARCH_FORCE_MAX_ORDER
 	default "10"
 	help
 	  The kernel page allocator limits the size of maximal physically
-	  contiguous allocations. The limit is called MAX_ORDER and it
+	  contiguous allocations. The limit is called MAX_PAGE_ORDER and it
 	  defines the maximal power of two of number of pages that can be
 	  allocated as a single contiguous block. This option allows
 	  overriding the default setting when ability to allocate very
 	  large blocks of physically contiguous memory is required.
 
 	  The maximal size of allocation cannot exceed the size of the
-	  section, so the value of MAX_ORDER should satisfy
+	  section, so the value of MAX_PAGE_ORDER should satisfy
 
-	    MAX_ORDER + PAGE_SHIFT <= SECTION_SIZE_BITS
+	    MAX_PAGE_ORDER + PAGE_SHIFT <= SECTION_SIZE_BITS
 
 	  Don't change if unsure.
 
 config UNMAP_KERNEL_AT_EL0
-	bool "Unmap kernel when running in userspace (aka \"KAISER\")" if EXPERT
+	bool "Unmap kernel when running in userspace (KPTI)" if EXPERT
 	default y
 	help
 	  Speculation attacks against some high-performance processors can
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 4bd85cc0d32b..47ecc4cff9d2 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -158,7 +158,7 @@ endif
 
 all:	$(notdir $(KBUILD_IMAGE))
 
-
+vmlinuz.efi: Image
 Image vmlinuz.efi: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
@@ -200,7 +200,7 @@ endif
 endif
 
 vdso-install-y				+= arch/arm64/kernel/vdso/vdso.so.dbg
-vdso-install-$(CONFIG_COMPAT_VDSO)	+= arch/arm64/kernel/vdso32/vdso.so.dbg:vdso32.so
+vdso-install-$(CONFIG_COMPAT_VDSO)	+= arch/arm64/kernel/vdso32/vdso32.so.dbg
 
 include $(srctree)/scripts/Makefile.defconf
 
diff --git a/arch/arm64/boot/Makefile b/arch/arm64/boot/Makefile
index 1761f5972443..a5a787371117 100644
--- a/arch/arm64/boot/Makefile
+++ b/arch/arm64/boot/Makefile
@@ -44,7 +44,7 @@ EFI_ZBOOT_BFD_TARGET	:= elf64-littleaarch64
 EFI_ZBOOT_MACH_TYPE	:= ARM64
 EFI_ZBOOT_FORWARD_CFI	:= $(CONFIG_ARM64_BTI_KERNEL)
 
-EFI_ZBOOT_OBJCOPY_FLAGS	= --add-symbol zboot_code_size=0x$(shell \
+EFI_ZBOOT_OBJCOPY_FLAGS	= --add-symbol zboot_code_size=0x$$( \
 				$(NM) vmlinux|grep _kernel_codesize|cut -d' ' -f1)
 
 include $(srctree)/drivers/firmware/efi/libstub/Makefile.zboot
diff --git a/arch/arm64/boot/dts/allwinner/Makefile b/arch/arm64/boot/dts/allwinner/Makefile
index 3aca6787a167..91d505b385de 100644
--- a/arch/arm64/boot/dts/allwinner/Makefile
+++ b/arch/arm64/boot/dts/allwinner/Makefile
@@ -43,3 +43,4 @@ dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-bigtreetech-pi.dtb
 dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-orangepi-zero2.dtb
 dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-x96-mate.dtb
 dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h618-orangepi-zero3.dtb
+dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h618-transpeed-8k618-t.dtb
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero.dtsi
index 15290e6892fc..fc7315b94406 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero.dtsi
@@ -68,10 +68,7 @@
 &emac0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&ext_rgmii_pins>;
-	phy-mode = "rgmii";
 	phy-handle = <&ext_rgmii_phy>;
-	allwinner,rx-delay-ps = <3100>;
-	allwinner,tx-delay-ps = <700>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero2.dts
index d83852e72f06..b5d713926a34 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero2.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero2.dts
@@ -13,6 +13,9 @@
 };
 
 &emac0 {
+	allwinner,rx-delay-ps = <3100>;
+	allwinner,tx-delay-ps = <700>;
+	phy-mode = "rgmii";
 	phy-supply = <&reg_dcdce>;
 };
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero2w.dts b/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero2w.dts
new file mode 100644
index 000000000000..21ca1977055d
--- /dev/null
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero2w.dts
@@ -0,0 +1,176 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (C) 2023 Arm Ltd.
+ */
+
+/dts-v1/;
+
+#include "sun50i-h616.dtsi"
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/leds/common.h>
+
+/ {
+	model = "OrangePi Zero 2W";
+	compatible = "xunlong,orangepi-zero2w", "allwinner,sun50i-h618";
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		led-0 {
+			function = LED_FUNCTION_STATUS;
+			color = <LED_COLOR_ID_GREEN>;
+			gpios = <&pio 2 13 GPIO_ACTIVE_HIGH>; /* PC13 */
+		};
+	};
+
+	reg_vcc5v: vcc5v {
+		/* board wide 5V supply directly from the USB-C socket */
+		compatible = "regulator-fixed";
+		regulator-name = "vcc-5v";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-always-on;
+	};
+
+	reg_vcc3v3: vcc3v3 {
+		/* SY8089 DC/DC converter */
+		compatible = "regulator-fixed";
+		regulator-name = "vcc-3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&reg_vcc5v>;
+		regulator-always-on;
+	};
+};
+
+&ehci1 {
+	status = "okay";
+};
+
+/* USB 2 & 3 are on the FPC connector (or the exansion board) */
+
+&mmc0 {
+	cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>;	/* PF6 */
+	bus-width = <4>;
+	vmmc-supply = <&reg_vcc3v3>;
+	status = "okay";
+};
+
+&ohci1 {
+	status = "okay";
+};
+
+&pio {
+	vcc-pc-supply = <&reg_dldo1>;
+	vcc-pf-supply = <&reg_dldo1>;	/* internally via VCC-IO */
+	vcc-pg-supply = <&reg_aldo1>;
+	vcc-ph-supply = <&reg_dldo1>;	/* internally via VCC-IO */
+	vcc-pi-supply = <&reg_dldo1>;
+};
+
+&r_i2c {
+	status = "okay";
+
+	axp313: pmic@36 {
+		compatible = "x-powers,axp313a";
+		reg = <0x36>;
+		#interrupt-cells = <1>;
+		interrupt-controller;
+		interrupt-parent = <&pio>;
+		interrupts = <2 9 IRQ_TYPE_LEVEL_LOW>;	/* PC9 */
+
+		vin1-supply = <&reg_vcc5v>;
+		vin2-supply = <&reg_vcc5v>;
+		vin3-supply = <&reg_vcc5v>;
+
+		regulators {
+			/* Supplies VCC-PLL and DRAM */
+			reg_aldo1: aldo1 {
+				regulator-always-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc1v8";
+			};
+
+			/* Supplies VCC-IO, so needs to be always on. */
+			reg_dldo1: dldo1 {
+				regulator-always-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcc3v3";
+			};
+
+			reg_dcdc1: dcdc1 {
+				regulator-always-on;
+				regulator-min-microvolt = <810000>;
+				regulator-max-microvolt = <990000>;
+				regulator-name = "vdd-gpu-sys";
+			};
+
+			reg_dcdc2: dcdc2 {
+				regulator-always-on;
+				regulator-min-microvolt = <810000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-name = "vdd-cpu";
+			};
+
+			reg_dcdc3: dcdc3 {
+				regulator-always-on;
+				regulator-min-microvolt = <1100000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-name = "vdd-dram";
+			};
+		};
+	};
+};
+
+&spi0  {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&spi0_pins>, <&spi0_cs0_pin>;
+
+	flash@0 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "jedec,spi-nor";
+		reg = <0>;
+		spi-max-frequency = <40000000>;
+	};
+};
+
+&uart0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart0_ph_pins>;
+	status = "okay";
+};
+
+&usbotg {
+	/*
+	 * PHY0 pins are connected to a USB-C socket, but a role switch
+	 * is not implemented: both CC pins are pulled to GND.
+	 * The VBUS pins power the device, so a fixed peripheral mode
+	 * is the best choice.
+	 * The board can be powered via GPIOs, in this case port0 *can*
+	 * act as a host (with a cable/adapter ignoring CC), as VBUS is
+	 * then provided by the GPIOs. Any user of this setup would
+	 * need to adjust the DT accordingly: dr_mode set to "host",
+	 * enabling OHCI0 and EHCI0.
+	 */
+	dr_mode = "peripheral";
+	status = "okay";
+};
+
+&usbphy {
+	usb1_vbus-supply = <&reg_vcc5v>;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero3.dts b/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero3.dts
index 00fe28caac93..b3b1b8692125 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero3.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero3.dts
@@ -13,6 +13,8 @@
 };
 
 &emac0 {
+	allwinner,tx-delay-ps = <700>;
+	phy-mode = "rgmii-rxid";
 	phy-supply = <&reg_dldo1>;
 };
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h618-transpeed-8k618-t.dts b/arch/arm64/boot/dts/allwinner/sun50i-h618-transpeed-8k618-t.dts
new file mode 100644
index 000000000000..8ea1fd41aeba
--- /dev/null
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h618-transpeed-8k618-t.dts
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (C) 2023 Arm Ltd.
+ */
+
+/dts-v1/;
+
+#include "sun50i-h616.dtsi"
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/ {
+	model = "Transpeed 8K618-T";
+	compatible = "transpeed,8k618-t", "allwinner,sun50i-h618";
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	reg_vcc5v: vcc5v {
+		/* board wide 5V supply directly from the DC input */
+		compatible = "regulator-fixed";
+		regulator-name = "vcc-5v";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-always-on;
+	};
+
+	reg_vcc3v3: vcc3v3 {
+		/* discrete 3.3V regulator */
+		compatible = "regulator-fixed";
+		regulator-name = "vcc-3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+	};
+};
+
+&ehci0 {
+	status = "okay";
+};
+
+&ehci1 {
+	status = "okay";
+};
+
+&ir {
+	status = "okay";
+};
+
+&mmc0 {
+	vmmc-supply = <&reg_dldo1>;
+	cd-gpios = <&pio 8 16 GPIO_ACTIVE_LOW>;	/* PI16 */
+	bus-width = <4>;
+	status = "okay";
+};
+
+&mmc2 {
+	vmmc-supply = <&reg_dldo1>;
+	vqmmc-supply = <&reg_aldo1>;
+	bus-width = <8>;
+	non-removable;
+	cap-mmc-hw-reset;
+	mmc-ddr-1_8v;
+	mmc-hs200-1_8v;
+	status = "okay";
+};
+
+&ohci0 {
+	status = "okay";
+};
+
+&ohci1 {
+	status = "okay";
+};
+
+&r_i2c {
+	status = "okay";
+
+	axp313: pmic@36 {
+		compatible = "x-powers,axp313a";
+		reg = <0x36>;
+		#interrupt-cells = <1>;
+		interrupt-controller;
+
+		vin1-supply = <&reg_vcc5v>;
+		vin2-supply = <&reg_vcc5v>;
+		vin3-supply = <&reg_vcc5v>;
+
+		regulators {
+			reg_aldo1: aldo1 {
+				regulator-always-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc-1v8-pll";
+			};
+
+			reg_dldo1: dldo1 {
+				regulator-always-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcc-3v3-io-mmc";
+			};
+
+			reg_dcdc1: dcdc1 {
+				regulator-always-on;
+				regulator-min-microvolt = <810000>;
+				regulator-max-microvolt = <990000>;
+				regulator-name = "vdd-gpu-sys";
+			};
+
+			reg_dcdc2: dcdc2 {
+				regulator-always-on;
+				regulator-min-microvolt = <810000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-name = "vdd-cpu";
+			};
+
+			reg_dcdc3: dcdc3 {
+				regulator-always-on;
+				regulator-min-microvolt = <1360000>;
+				regulator-max-microvolt = <1360000>;
+				regulator-name = "vdd-dram";
+			};
+		};
+	};
+};
+
+&pio {
+	vcc-pc-supply = <&reg_aldo1>;
+	vcc-pg-supply = <&reg_dldo1>;
+	vcc-ph-supply = <&reg_dldo1>;
+	vcc-pi-supply = <&reg_dldo1>;
+};
+
+&uart0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart0_ph_pins>;
+	status = "okay";
+};
+
+&uart1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart1_pins>, <&uart1_rts_cts_pins>;
+	uart-has-rtscts;
+	status = "okay";
+};
+
+&usbotg {
+	dr_mode = "host";	/* USB A type receptable */
+	status = "okay";
+};
+
+&usbphy {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
index 439497ab967d..072fe20cfca0 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
@@ -59,6 +59,25 @@
 		};
 	};
 
+	firmware {
+		svc {
+			compatible = "intel,stratix10-svc";
+			method = "smc";
+			memory-region = <&service_reserved>;
+
+			fpga_mgr: fpga-mgr {
+				compatible = "intel,stratix10-soc-fpga-mgr";
+			};
+		};
+	};
+
+	fpga-region {
+		compatible = "fpga-region";
+		#address-cells = <0x2>;
+		#size-cells = <0x2>;
+		fpga-mgr = <&fpga_mgr>;
+	};
+
 	pmu {
 		compatible = "arm,armv8-pmuv3";
 		interrupts = <0 170 4>,
@@ -125,7 +144,7 @@
 		};
 	};
 
-	soc {
+	soc@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		compatible = "simple-bus";
@@ -133,13 +152,6 @@
 		interrupt-parent = <&intc>;
 		ranges = <0 0 0 0xffffffff>;
 
-		base_fpga_region {
-			#address-cells = <0x2>;
-			#size-cells = <0x2>;
-			compatible = "fpga-region";
-			fpga-mgr = <&fpga_mgr>;
-		};
-
 		clkmgr: clock-controller@ffd10000 {
 			compatible = "intel,stratix10-clkmgr";
 			reg = <0xffd10000 0x1000>;
@@ -510,6 +522,7 @@
 			resets = <&rst USB1_RESET>, <&rst USB1_OCP_RESET>;
 			reset-names = "dwc2", "dwc2-ecc";
 			clocks = <&clkmgr STRATIX10_USB_CLK>;
+			clock-names = "otg";
 			iommus = <&smmu 7>;
 			status = "disabled";
 		};
@@ -620,18 +633,6 @@
 
 			status = "disabled";
 		};
-
-		firmware {
-			svc {
-				compatible = "intel,stratix10-svc";
-				method = "smc";
-				memory-region = <&service_reserved>;
-
-				fpga_mgr: fpga-mgr {
-					compatible = "intel,stratix10-soc-fpga-mgr";
-				};
-			};
-		};
 	};
 
 	usbphy0: usbphy0 {
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
index 468fcc7da066..26173f0b0051 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
@@ -51,7 +51,7 @@
 		regulator-max-microvolt = <330000>;
 	};
 
-	soc {
+	soc@0 {
 		eccmgr {
 			sdmmca-ecc@ff8c8c00 {
 				compatible = "altr,socfpga-s10-sdmmc-ecc",
@@ -66,14 +66,14 @@
 };
 
 &pinctrl0 {
-	i2c1_pmx_func: i2c1-pmx-func {
+	i2c1_pmx_func: i2c1-pmx-func-pins {
 		pinctrl-single,pins = <
 			0x78   0x4   /* I2C1_SDA (IO6-B) PIN30SEL) */
 			0x7c   0x4   /* I2C1_SCL (IO7-B) PIN31SEL */
 		>;
 	};
 
-	i2c1_pmx_func_gpio: i2c1-pmx-func-gpio {
+	i2c1_pmx_func_gpio: i2c1-pmx-func-gpio-pins {
 		pinctrl-single,pins = <
 			0x78   0x8   /* I2C1_SDA (IO6-B) PIN30SEL) */
 			0x7c   0x8   /* I2C1_SCL (IO7-B) PIN31SEL */
@@ -187,8 +187,6 @@
 		spi-max-frequency = <100000000>;
 
 		m25p,fast-read;
-		cdns,page-size = <256>;
-		cdns,block-size = <16>;
 		cdns,read-delay = <1>;
 		cdns,tshsl-ns = <50>;
 		cdns,tsd2d-ns = <50>;
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts
index 532164a6354c..81d0e914a77c 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts
@@ -51,7 +51,7 @@
 		regulator-max-microvolt = <330000>;
 	};
 
-	soc {
+	soc@0 {
 		eccmgr {
 			sdmmca-ecc@ff8c8c00 {
 				compatible = "altr,socfpga-s10-sdmmc-ecc",
@@ -102,7 +102,7 @@
 &nand {
 	status = "okay";
 
-	flash@0 {
+	nand@0 {
 		reg = <0>;
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -176,8 +176,6 @@
 		spi-max-frequency = <100000000>;
 
 		m25p,fast-read;
-		cdns,page-size = <256>;
-		cdns,block-size = <16>;
 		cdns,read-delay = <1>;
 		cdns,tshsl-ns = <50>;
 		cdns,tsd2d-ns = <50>;
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_swvp.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_swvp.dts
index ff413f8e3b07..0d837d3e65a5 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10_swvp.dts
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_swvp.dts
@@ -80,8 +80,6 @@
 
 &mmc {
 	status = "okay";
-	altr,dw-mshc-ciu-div = <0x3>;
-	altr,dw-mshc-sdr-timing = <0x0 0x3>;
 	cap-sd-highspeed;
 	cap-mmc-highspeed;
 	broken-cd;
diff --git a/arch/arm64/boot/dts/amlogic/amlogic-c3.dtsi b/arch/arm64/boot/dts/amlogic/amlogic-c3.dtsi
index 998f5050795c..2ad1f8eef199 100644
--- a/arch/arm64/boot/dts/amlogic/amlogic-c3.dtsi
+++ b/arch/arm64/boot/dts/amlogic/amlogic-c3.dtsi
@@ -81,6 +81,12 @@
 			#size-cells = <2>;
 			ranges = <0x0 0x0 0x0 0xfe000000 0x0 0x480000>;
 
+			watchdog@2100 {
+				compatible = "amlogic,c3-wdt", "amlogic,t7-wdt";
+				reg = <0x0 0x2100 0x0 0x10>;
+				clocks = <&xtal>;
+			};
+
 			periphs_pinctrl: pinctrl@4000 {
 				compatible = "amlogic,c3-periphs-pinctrl";
 				#address-cells = <2>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j110-rev-2.dts b/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j110-rev-2.dts
index 0062667c4f65..8a18ce948450 100644
--- a/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j110-rev-2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j110-rev-2.dts
@@ -30,8 +30,20 @@
 &uart_B {
 	bluetooth {
 		compatible = "realtek,rtl8822cs-bt";
-		enable-gpios  = <&gpio GPIOZ_7 GPIO_ACTIVE_HIGH>;
+		enable-gpios = <&gpio GPIOZ_7 GPIO_ACTIVE_HIGH>;
 		host-wake-gpios = <&gpio GPIOZ_8 GPIO_ACTIVE_HIGH>;
 		device-wake-gpios = <&gpio GPIOZ_6 GPIO_ACTIVE_HIGH>;
 	};
 };
+
+&i2c_AO {
+	/* EEPROM on base board */
+	eeprompd: eeprom@56 {
+		compatible = "atmel,24c64";
+		reg = <0x56>;
+		pagesize = <0x20>;
+		label = "eeprompd";
+		address-width = <0x10>;
+		vcc-supply = <&vddao_3v3>;
+	};
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j110-rev-3.dts b/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j110-rev-3.dts
index c2d22b00c1cd..c356bd2cc63a 100644
--- a/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j110-rev-3.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j110-rev-3.dts
@@ -25,3 +25,15 @@
 &sd_emmc_b {
 	broken-cd;/* cd-gpios = <&gpio_ao GPIOAO_3 GPIO_ACTIVE_LOW>;*/
 };
+
+&i2c_AO {
+	/* EEPROM on base board */
+	eeprompd: eeprom@56 {
+		compatible = "atmel,24c64";
+		reg = <0x56>;
+		pagesize = <0x20>;
+		label = "eeprompd";
+		address-width = <0x10>;
+		vcc-supply = <&vddao_3v3>;
+	};
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts b/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts
index df16eead2c80..c8905663bc75 100644
--- a/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts
@@ -66,7 +66,6 @@
 		VDDA-supply = <&vcc_3v3>;
 		VDDP-supply = <&vcc_3v3>;
 		VDDD-supply = <&vcc_3v3>;
-		status = "okay";
 		sound-name-prefix = "Linein";
 	};
 
@@ -75,14 +74,12 @@
 		compatible = "everest,es7154";
 		VDD-supply = <&vcc_3v3>;
 		PVDD-supply = <&vcc_5v>;
-		status = "okay";
 		sound-name-prefix = "Lineout";
 	};
 
 	spdif_dit: audio-codec-2 {
 		#sound-dai-cells = <0>;
 		compatible = "linux,spdif-dit";
-		status = "okay";
 		sound-name-prefix = "DIT";
 	};
 
@@ -91,14 +88,12 @@
 		compatible = "dmic-codec";
 		num-channels = <7>;
 		wakeup-delay-ms = <50>;
-		status = "okay";
 		sound-name-prefix = "MIC";
 	};
 
 	spdif_dir: audio-codec-4 {
 		#sound-dai-cells = <0>;
 		compatible = "linux,spdif-dir";
-		status = "okay";
 		sound-name-prefix = "DIR";
 	};
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
index a49aa62e3f9f..7e5ac9db93f8 100644
--- a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
@@ -432,6 +432,27 @@
 					};
 				};
 
+				nand_all_pins: nand-all-pins {
+					mux {
+						groups = "emmc_nand_d0",
+							 "emmc_nand_d1",
+							 "emmc_nand_d2",
+							 "emmc_nand_d3",
+							 "emmc_nand_d4",
+							 "emmc_nand_d5",
+							 "emmc_nand_d6",
+							 "emmc_nand_d7",
+							 "nand_ce0",
+							 "nand_ale",
+							 "nand_cle",
+							 "nand_wen_clk",
+							 "nand_ren_wr";
+						function = "nand";
+						input-enable;
+						bias-pull-up;
+					};
+				};
+
 				emmc_ds_pins: emmc_ds {
 					mux {
 						groups = "emmc_ds";
@@ -1913,6 +1934,8 @@
 				reg = <0x0 0x7800 0x0 0x100>,
 				      <0x0 0x7000 0x0 0x800>;
 				reg-names = "nfc", "emmc";
+				pinctrl-0 = <&nand_all_pins>;
+				pinctrl-names = "default";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				interrupts = <GIC_SPI 34 IRQ_TYPE_EDGE_RISING>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12a-sei510.dts b/arch/arm64/boot/dts/amlogic/meson-g12a-sei510.dts
index 0ad0c2b7dfef..4c4550dd4711 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12a-sei510.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-g12a-sei510.dts
@@ -45,7 +45,6 @@
 		compatible = "dmic-codec";
 		num-channels = <2>;
 		wakeup-delay-ms = <50>;
-		status = "okay";
 		sound-name-prefix = "MIC";
 	};
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12a-x96-max.dts b/arch/arm64/boot/dts/amlogic/meson-g12a-x96-max.dts
index 4969a76460fa..9b55982b6a6b 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12a-x96-max.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-g12a-x96-max.dts
@@ -22,7 +22,6 @@
 	spdif_dit: audio-codec-1 {
 		#sound-dai-cells = <0>;
 		compatible = "linux,spdif-dit";
-		status = "okay";
 		sound-name-prefix = "DIT";
 	};
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-bananapi-cm4.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-bananapi-cm4.dtsi
index 995ce10d5c81..08c33ec7e9f1 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12b-bananapi-cm4.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12b-bananapi-cm4.dtsi
@@ -369,7 +369,7 @@
 
 	bluetooth {
 		compatible = "realtek,rtl8822cs-bt";
-		enable-gpios  = <&gpio GPIOX_17 GPIO_ACTIVE_HIGH>;
+		enable-gpios = <&gpio GPIOX_17 GPIO_ACTIVE_HIGH>;
 		host-wake-gpios = <&gpio GPIOX_19 GPIO_ACTIVE_HIGH>;
 		device-wake-gpios = <&gpio GPIOX_18 GPIO_ACTIVE_HIGH>;
 	};
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-bananapi.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-bananapi.dtsi
index 0a6a12808568..4b8db872bbf3 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12b-bananapi.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12b-bananapi.dtsi
@@ -487,7 +487,7 @@
 
 	bluetooth {
 		compatible = "realtek,rtl8822cs-bt";
-		enable-gpios  = <&gpio GPIOX_17 GPIO_ACTIVE_HIGH>;
+		enable-gpios = <&gpio GPIOX_17 GPIO_ACTIVE_HIGH>;
 		host-wake-gpios = <&gpio GPIOX_19 GPIO_ACTIVE_HIGH>;
 		device-wake-gpios = <&gpio GPIOX_18 GPIO_ACTIVE_HIGH>;
 	};
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-gtking.dts b/arch/arm64/boot/dts/amlogic/meson-g12b-gtking.dts
index 8fc2e143cb54..0da386cabe1a 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12b-gtking.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-g12b-gtking.dts
@@ -22,7 +22,6 @@
 	spdif_dit: audio-codec-1 {
 		#sound-dai-cells = <0>;
 		compatible = "linux,spdif-dit";
-		status = "okay";
 		sound-name-prefix = "DIT";
 	};
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-ugoos-am6.dts b/arch/arm64/boot/dts/amlogic/meson-g12b-ugoos-am6.dts
index ce548b373296..6396f190d703 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12b-ugoos-am6.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-g12b-ugoos-am6.dts
@@ -17,7 +17,6 @@
 	spdif_dit: audio-codec-1 {
 		#sound-dai-cells = <0>;
 		compatible = "linux,spdif-dit";
-		status = "okay";
 		sound-name-prefix = "DIT";
 	};
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
index 18f7b730289e..e59c3c92b1e7 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
@@ -26,7 +26,6 @@
 	spdif_dit: audio-codec-0 {
 		#sound-dai-cells = <0>;
 		compatible = "linux,spdif-dit";
-		status = "okay";
 		sound-name-prefix = "DIT";
 	};
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-kii-pro.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-kii-pro.dts
index e238f1f10124..f28452b9f00f 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-kii-pro.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-kii-pro.dts
@@ -18,7 +18,6 @@
 	spdif_dit: audio-codec-0 {
 		#sound-dai-cells = <0>;
 		compatible = "linux,spdif-dit";
-		status = "okay";
 		sound-name-prefix = "DIT";
 	};
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-p200.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-p200.dts
index 292c718ee19c..591455c50e88 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-p200.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-p200.dts
@@ -18,7 +18,6 @@
 	spdif_dit: audio-codec-0 {
 		#sound-dai-cells = <0>;
 		compatible = "linux,spdif-dit";
-		status = "okay";
 		sound-name-prefix = "DIT";
 	};
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi
index e8303089bff6..74df32534231 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi
@@ -21,7 +21,6 @@
 	spdif_dit: audio-codec-0 {
 		#sound-dai-cells = <0>;
 		compatible = "linux,spdif-dit";
-		status = "okay";
 		sound-name-prefix = "DIT";
 	};
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek-play2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek-play2.dts
index e1b74b174915..376760d86766 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek-play2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek-play2.dts
@@ -17,7 +17,6 @@
 	spdif_dit: audio-codec-0 {
 		#sound-dai-cells = <0>;
 		compatible = "linux,spdif-dit";
-		status = "okay";
 		sound-name-prefix = "DIT";
 	};
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts
index 7d525bdb0e06..ad2dd4ad0a31 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts
@@ -28,7 +28,6 @@
 	spdif_dit: audio-codec-0 {
 		#sound-dai-cells = <0>;
 		compatible = "linux,spdif-dit";
-		status = "okay";
 		sound-name-prefix = "DIT";
 	};
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts
index 50d49aec41bd..d05dde8da5c5 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts
@@ -37,7 +37,6 @@
 	spdif_dit: audio-codec-0 {
 		#sound-dai-cells = <0>;
 		compatible = "linux,spdif-dit";
-		status = "okay";
 		sound-name-prefix = "DIT";
 	};
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-s4-s805x2-aq222.dts b/arch/arm64/boot/dts/amlogic/meson-s4-s805x2-aq222.dts
index c1f322c73982..983caddc409c 100644
--- a/arch/arm64/boot/dts/amlogic/meson-s4-s805x2-aq222.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-s4-s805x2-aq222.dts
@@ -15,7 +15,7 @@
 	#size-cells = <2>;
 
 	aliases {
-		serial0 = &uart_B;
+		serial0 = &uart_b;
 	};
 
 	memory@0 {
@@ -23,9 +23,20 @@
 		reg = <0x0 0x0 0x0 0x40000000>;
 	};
 
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		/* 52 MiB reserved for ARM Trusted Firmware */
+		secmon_reserved: secmon@5000000 {
+			reg = <0x0 0x05000000 0x0 0x3400000>;
+			no-map;
+		};
+	};
 };
 
-&uart_B {
+&uart_b {
 	status = "okay";
 };
 
@@ -34,3 +45,48 @@
 	pinctrl-0 = <&remote_pins>;
 	pinctrl-names = "default";
 };
+
+&nand {
+	status = "okay";
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	pinctrl-0 = <&nand_pins>;
+	pinctrl-names = "default";
+
+	nand@0 {
+		reg = <0>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		nand-on-flash-bbt;
+
+		partition@0 {
+			label = "boot";
+			reg = <0x0 0x00200000>;
+		};
+		partition@200000 {
+			label = "env";
+			reg = <0x00200000 0x00400000>;
+		};
+		partition@600000 {
+			label = "system";
+			reg = <0x00600000 0x00a00000>;
+		};
+		partition@1000000 {
+			label = "rootfs";
+			reg = <0x01000000 0x03000000>;
+		};
+		partition@4000000 {
+			label = "media";
+			reg = <0x04000000 0x8000000>;
+		};
+	};
+};
+
+&spicc0 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&spicc0_pins_x>;
+	cs-gpios = <&gpio GPIOX_10 GPIO_ACTIVE_LOW>;
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-s4.dtsi b/arch/arm64/boot/dts/amlogic/meson-s4.dtsi
index e0cfc54ebccb..ce90b35686a2 100644
--- a/arch/arm64/boot/dts/amlogic/meson-s4.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-s4.dtsi
@@ -6,6 +6,10 @@
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/gpio/meson-s4-gpio.h>
+#include <dt-bindings/clock/amlogic,s4-pll-clkc.h>
+#include <dt-bindings/clock/amlogic,s4-peripherals-clkc.h>
+#include <dt-bindings/power/meson-s4-power.h>
 
 / {
 	cpus {
@@ -92,6 +96,44 @@
 			#size-cells = <2>;
 			ranges = <0x0 0x0 0x0 0xfe000000 0x0 0x480000>;
 
+			clkc_periphs: clock-controller@0 {
+				compatible = "amlogic,s4-peripherals-clkc";
+				reg = <0x0 0x0 0x0 0x49c>;
+				clocks = <&clkc_pll CLKID_FCLK_DIV2>,
+					<&clkc_pll CLKID_FCLK_DIV2P5>,
+					<&clkc_pll CLKID_FCLK_DIV3>,
+					<&clkc_pll CLKID_FCLK_DIV4>,
+					<&clkc_pll CLKID_FCLK_DIV5>,
+					<&clkc_pll CLKID_FCLK_DIV7>,
+					<&clkc_pll CLKID_HIFI_PLL>,
+					<&clkc_pll CLKID_GP0_PLL>,
+					<&clkc_pll CLKID_MPLL0>,
+					<&clkc_pll CLKID_MPLL1>,
+					<&clkc_pll CLKID_MPLL2>,
+					<&clkc_pll CLKID_MPLL3>,
+					<&clkc_pll CLKID_HDMI_PLL>,
+					<&xtal>;
+				clock-names = "fclk_div2", "fclk_div2p5", "fclk_div3",
+						"fclk_div4", "fclk_div5", "fclk_div7",
+						"hifi_pll", "gp0_pll", "mpll0", "mpll1",
+						"mpll2", "mpll3", "hdmi_pll", "xtal";
+				#clock-cells = <1>;
+			};
+
+			clkc_pll: clock-controller@8000 {
+				compatible = "amlogic,s4-pll-clkc";
+				reg = <0x0 0x8000 0x0 0x1e8>;
+				clocks = <&xtal>;
+				clock-names = "xtal";
+				#clock-cells = <1>;
+			};
+
+			watchdog@2100 {
+				compatible = "amlogic,s4-wdt", "amlogic,t7-wdt";
+				reg = <0x0 0x2100 0x0 0x10>;
+				clocks = <&xtal>;
+			};
+
 			periphs_pinctrl: pinctrl@4000 {
 				compatible = "amlogic,meson-s4-periphs-pinctrl";
 				#address-cells = <2>;
@@ -114,6 +156,187 @@
 						bias-disable;
 					};
 				};
+
+				i2c0_pins1: i2c0-pins1 {
+					mux {
+						groups = "i2c0_sda",
+						       "i2c0_scl";
+						function = "i2c0";
+						drive-strength-microamp = <3000>;
+						bias-disable;
+					};
+				};
+
+				i2c1_pins1: i2c1-pins1 {
+					mux {
+						groups = "i2c1_sda_c",
+						       "i2c1_scl_c";
+						function = "i2c1";
+						drive-strength-microamp = <3000>;
+						bias-disable;
+					};
+				};
+
+				i2c1_pins2: i2c1-pins2 {
+					mux {
+						groups = "i2c1_sda_d",
+						       "i2c1_scl_d";
+						function = "i2c1";
+						drive-strength-microamp = <3000>;
+						bias-disable;
+					};
+				};
+
+				i2c1_pins3: i2c1-pins3 {
+					mux {
+						groups = "i2c1_sda_h",
+						       "i2c1_scl_h";
+						function = "i2c1";
+						drive-strength-microamp = <3000>;
+						bias-disable;
+					};
+				};
+
+				i2c1_pins4: i2c1-pins4 {
+					mux {
+						groups = "i2c1_sda_x",
+						       "i2c1_scl_x";
+						function = "i2c1";
+						drive-strength-microamp = <3000>;
+						bias-disable;
+					};
+				};
+
+				i2c2_pins1: i2c2-pins1 {
+					mux {
+						groups = "i2c2_sda_d",
+						       "i2c2_scl_d";
+						function = "i2c2";
+						drive-strength-microamp = <3000>;
+						bias-disable;
+					};
+				};
+
+				i2c2_pins2: i2c2-pins2 {
+					mux {
+						groups = "i2c2_sda_h8",
+						       "i2c2_scl_h9";
+						function = "i2c2";
+						drive-strength-microamp = <3000>;
+						bias-disable;
+					};
+				};
+
+				i2c2_pins3: i2c2-pins3 {
+					mux {
+						groups = "i2c2_sda_h0",
+						       "i2c2_scl_h1";
+						function = "i2c2";
+						drive-strength-microamp = <3000>;
+						bias-disable;
+					};
+				};
+
+				i2c3_pins1: i2c3-pins1 {
+					mux {
+						groups = "i2c3_sda_x",
+						       "i2c3_scl_x";
+						function = "i2c3";
+						drive-strength-microamp = <3000>;
+						bias-disable;
+					};
+				};
+
+				i2c3_pins2: i2c3-pins2 {
+					mux {
+						groups = "i2c3_sda_z",
+						       "i2c3_scl_z";
+						function = "i2c3";
+						drive-strength-microamp = <3000>;
+						bias-disable;
+					};
+				};
+
+				i2c4_pins1: i2c4-pins1 {
+					mux {
+						groups = "i2c4_sda_c",
+						       "i2c4_scl_c";
+						function = "i2c4";
+						drive-strength-microamp = <3000>;
+						bias-disable;
+					};
+				};
+
+				i2c4_pins2: i2c4-pins2 {
+					mux {
+						groups = "i2c4_sda_d",
+						       "i2c4_scl_d";
+						function = "i2c4";
+						drive-strength-microamp = <3000>;
+						bias-disable;
+					};
+				};
+
+				i2c4_pins3: i2c4-pins3 {
+					mux {
+						groups = "i2c4_sda_z",
+						       "i2c4_scl_z";
+						function = "i2c4";
+						drive-strength-microamp = <3000>;
+						bias-disable;
+					};
+				};
+
+				nand_pins: nand-pins {
+					mux {
+						groups = "emmc_nand_d0",
+						       "emmc_nand_d1",
+						       "emmc_nand_d2",
+						       "emmc_nand_d3",
+						       "emmc_nand_d4",
+						       "emmc_nand_d5",
+						       "emmc_nand_d6",
+						       "emmc_nand_d7",
+						       "nand_ce0",
+						       "nand_ale",
+						       "nand_cle",
+						       "nand_wen_clk",
+						       "nand_ren_wr";
+						function = "nand";
+						input-enable;
+					};
+				};
+
+				spicc0_pins_x: spicc0-pins_x {
+					mux {
+						groups = "spi_a_mosi_x",
+						       "spi_a_miso_x",
+						       "spi_a_clk_x";
+						function = "spi_a";
+						drive-strength-microamp = <3000>;
+					};
+				};
+
+				spicc0_pins_h: spicc0-pins-h {
+					mux {
+						groups = "spi_a_mosi_h",
+						       "spi_a_miso_h",
+						       "spi_a_clk_h";
+						function = "spi_a";
+						drive-strength-microamp = <3000>;
+					};
+				};
+
+				spicc0_pins_z: spicc0-pins-z {
+					mux {
+						groups = "spi_a_mosi_z",
+						       "spi_a_miso_z",
+						       "spi_a_clk_z";
+						function = "spi_a";
+						drive-strength-microamp = <3000>;
+					};
+				};
+
 			};
 
 			gpio_intc: interrupt-controller@4080 {
@@ -126,14 +349,120 @@
 					<10 11 12 13 14 15 16 17 18 19 20 21>;
 			};
 
-			uart_B: serial@7a000 {
+			eth_phy: mdio-multiplexer@28000 {
+				compatible = "amlogic,g12a-mdio-mux";
+				reg = <0x0 0x28000 0x0 0xa4>;
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+				clocks = <&clkc_periphs CLKID_ETHPHY>,
+					 <&xtal>,
+					 <&clkc_pll CLKID_MPLL_50M>;
+				clock-names = "pclk", "clkin0", "clkin1";
+				mdio-parent-bus = <&mdio0>;
+
+				ext_mdio: mdio@0 {
+					reg = <0>;
+					#address-cells = <1>;
+					#size-cells = <0>;
+				};
+
+				int_mdio: mdio@1 {
+					reg = <1>;
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					internal_ephy: ethernet-phy@8 {
+						compatible = "ethernet-phy-id0180.3301",
+							     "ethernet-phy-ieee802.3-c22";
+						interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
+						reg = <8>;
+						max-speed = <100>;
+					};
+				};
+			};
+
+			spicc0: spi@50000 {
+				compatible = "amlogic,meson-g12a-spicc";
+				reg = <0x0 0x50000 0x0 0x44>;
+				interrupts = <GIC_SPI 183 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clkc_periphs CLKID_SPICC0>,
+					 <&clkc_periphs CLKID_SPICC0_EN>;
+				clock-names = "core", "pclk";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			i2c0: i2c@66000 {
+				compatible = "amlogic,meson-axg-i2c";
+				reg = <0x0 0x66000 0x0 0x20>;
+				interrupts = <GIC_SPI 160 IRQ_TYPE_EDGE_RISING>;
+				clocks = <&clkc_periphs CLKID_I2C_M_A>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			i2c1: i2c@68000 {
+				compatible = "amlogic,meson-axg-i2c";
+				reg = <0x0 0x68000 0x0 0x20>;
+				interrupts = <GIC_SPI 161 IRQ_TYPE_EDGE_RISING>;
+				clocks = <&clkc_periphs CLKID_I2C_M_B>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			i2c2: i2c@6a000 {
+				compatible = "amlogic,meson-axg-i2c";
+				reg = <0x0 0x6a000 0x0 0x20>;
+				interrupts = <GIC_SPI 162 IRQ_TYPE_EDGE_RISING>;
+				clocks = <&clkc_periphs CLKID_I2C_M_C>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			i2c3: i2c@6c000 {
+				compatible = "amlogic,meson-axg-i2c";
+				reg = <0x0 0x6c000 0x0 0x20>;
+				interrupts = <GIC_SPI 163 IRQ_TYPE_EDGE_RISING>;
+				clocks = <&clkc_periphs CLKID_I2C_M_D>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			i2c4: i2c@6e000 {
+				compatible = "amlogic,meson-axg-i2c";
+				reg = <0x0 0x6e000 0x0 0x20>;
+				interrupts = <GIC_SPI 164 IRQ_TYPE_EDGE_RISING>;
+				clocks = <&clkc_periphs CLKID_I2C_M_E>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			nand: nand-controller@8c800 {
+				compatible = "amlogic,meson-axg-nfc";
+				reg = <0x0 0x8c800 0x0 0x100>, <0x0 0x8c000 0x0 0x4>;
+				reg-names = "nfc", "emmc";
+				interrupts = <GIC_SPI 175 IRQ_TYPE_EDGE_RISING>;
+				clocks = <&clkc_periphs CLKID_SD_EMMC_C>,
+					<&clkc_pll CLKID_FCLK_DIV2>;
+				clock-names = "core", "device";
+				status = "disabled";
+			};
+
+			uart_b: serial@7a000 {
 				compatible = "amlogic,meson-s4-uart",
 					     "amlogic,meson-ao-uart";
 				reg = <0x0 0x7a000 0x0 0x18>;
 				interrupts = <GIC_SPI 169 IRQ_TYPE_EDGE_RISING>;
-				status = "disabled";
-				clocks = <&xtal>, <&xtal>, <&xtal>;
+				clocks = <&xtal>, <&clkc_periphs CLKID_UART_B>, <&xtal>;
 				clock-names = "xtal", "pclk", "baud";
+				status = "disabled";
 			};
 
 			reset: reset-controller@2000 {
@@ -154,5 +483,30 @@
 				reg = <0x0 0x440788 0x0 0x0c>;
 			};
 		};
+
+		ethmac: ethernet@fdc00000 {
+			compatible = "amlogic,meson-axg-dwmac",
+				     "snps,dwmac-3.70a",
+				     "snps,dwmac";
+			reg = <0x0 0xfdc00000 0x0 0x10000>,
+			      <0x0 0xfe024000 0x0 0x8>;
+
+			interrupts = <GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "macirq";
+			power-domains = <&pwrc PWRC_S4_ETH_ID>;
+			clocks = <&clkc_periphs CLKID_ETH>,
+				 <&clkc_pll CLKID_FCLK_DIV2>,
+				 <&clkc_pll CLKID_MPLL2>;
+			clock-names = "stmmaceth", "clkin0", "clkin1";
+			rx-fifo-depth = <4096>;
+			tx-fifo-depth = <2048>;
+			status = "disabled";
+
+			mdio0: mdio {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "snps,dwmac-mdio";
+			};
+		};
 	};
 };
diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts b/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts
index 095579c55f18..109932068dbe 100644
--- a/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts
@@ -32,7 +32,6 @@
 		compatible = "dmic-codec";
 		num-channels = <2>;
 		wakeup-delay-ms = <50>;
-		status = "okay";
 		sound-name-prefix = "MIC";
 	};
 
diff --git a/arch/arm64/boot/dts/arm/juno-base.dtsi b/arch/arm64/boot/dts/arm/juno-base.dtsi
index 8b4d280b1e7e..b897f5542c0a 100644
--- a/arch/arm64/boot/dts/arm/juno-base.dtsi
+++ b/arch/arm64/boot/dts/arm/juno-base.dtsi
@@ -747,7 +747,7 @@
 	};
 
 	thermal-zones {
-		pmic {
+		pmic-thermal {
 			polling-delay = <1000>;
 			polling-delay-passive = <100>;
 			thermal-sensors = <&scpi_sensors0 0>;
@@ -760,7 +760,7 @@
 			};
 		};
 
-		soc {
+		soc-thermal {
 			polling-delay = <1000>;
 			polling-delay-passive = <100>;
 			thermal-sensors = <&scpi_sensors0 3>;
@@ -773,28 +773,28 @@
 			};
 		};
 
-		big_cluster_thermal_zone: big-cluster {
+		big_cluster_thermal_zone: big-cluster-thermal {
 			polling-delay = <1000>;
 			polling-delay-passive = <100>;
 			thermal-sensors = <&scpi_sensors0 21>;
 			status = "disabled";
 		};
 
-		little_cluster_thermal_zone: little-cluster {
+		little_cluster_thermal_zone: little-cluster-thermal {
 			polling-delay = <1000>;
 			polling-delay-passive = <100>;
 			thermal-sensors = <&scpi_sensors0 22>;
 			status = "disabled";
 		};
 
-		gpu0_thermal_zone: gpu0 {
+		gpu0_thermal_zone: gpu0-thermal {
 			polling-delay = <1000>;
 			polling-delay-passive = <100>;
 			thermal-sensors = <&scpi_sensors0 23>;
 			status = "disabled";
 		};
 
-		gpu1_thermal_zone: gpu1 {
+		gpu1_thermal_zone: gpu1-thermal {
 			polling-delay = <1000>;
 			polling-delay-passive = <100>;
 			thermal-sensors = <&scpi_sensors0 24>;
diff --git a/arch/arm64/boot/dts/arm/juno-scmi.dtsi b/arch/arm64/boot/dts/arm/juno-scmi.dtsi
index ec85cd2c733c..31929e2377d8 100644
--- a/arch/arm64/boot/dts/arm/juno-scmi.dtsi
+++ b/arch/arm64/boot/dts/arm/juno-scmi.dtsi
@@ -76,27 +76,27 @@
 	};
 
 	thermal-zones {
-		pmic {
+		pmic-thermal {
 			thermal-sensors = <&scmi_sensors0 0>;
 		};
 
-		soc {
+		soc-thermal {
 			thermal-sensors = <&scmi_sensors0 3>;
 		};
 
-		big-cluster {
+		big-cluster-thermal {
 			thermal-sensors = <&scmi_sensors0 21>;
 		};
 
-		little-cluster {
+		little-cluster-thermal {
 			thermal-sensors = <&scmi_sensors0 22>;
 		};
 
-		gpu0 {
+		gpu0-thermal {
 			thermal-sensors = <&scmi_sensors0 23>;
 		};
 
-		gpu1 {
+		gpu1-thermal {
 			thermal-sensors = <&scmi_sensors0 24>;
 		};
 	};
diff --git a/arch/arm64/boot/dts/exynos/Makefile b/arch/arm64/boot/dts/exynos/Makefile
index 6e4ba69268e5..d7f2191c2cdb 100644
--- a/arch/arm64/boot/dts/exynos/Makefile
+++ b/arch/arm64/boot/dts/exynos/Makefile
@@ -1,8 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0
+subdir-y += google
+
 dtb-$(CONFIG_ARCH_EXYNOS) += \
 	exynos5433-tm2.dtb		\
 	exynos5433-tm2e.dtb		\
 	exynos7-espresso.dtb		\
 	exynos7885-jackpotlte.dtb	\
 	exynos850-e850-96.dtb		\
-	exynosautov9-sadk.dtb
+	exynosautov9-sadk.dtb		\
+	exynosautov920-sadk.dtb
diff --git a/arch/arm64/boot/dts/exynos/exynos5433.dtsi b/arch/arm64/boot/dts/exynos/exynos5433.dtsi
index 91ae0462a706..7fbbec04bff0 100644
--- a/arch/arm64/boot/dts/exynos/exynos5433.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos5433.dtsi
@@ -361,7 +361,8 @@
 		ranges = <0x0 0x0 0x0 0x18000000>;
 
 		chipid@10000000 {
-			compatible = "samsung,exynos4210-chipid";
+			compatible = "samsung,exynos5433-chipid",
+				     "samsung,exynos4210-chipid";
 			reg = <0x10000000 0x100>;
 		};
 
@@ -850,7 +851,8 @@
 			reg = <0x10580000 0x1a20>, <0x11090000 0x100>;
 
 			wakeup-interrupt-controller {
-				compatible = "samsung,exynos7-wakeup-eint";
+				compatible = "samsung,exynos5433-wakeup-eint",
+					     "samsung,exynos7-wakeup-eint";
 				interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
 			};
 		};
@@ -1546,7 +1548,7 @@
 		};
 
 		adc: adc@14d10000 {
-			compatible = "samsung,exynos7-adc";
+			compatible = "samsung,exynos5433-adc", "samsung,exynos7-adc";
 			reg = <0x14d10000 0x100>;
 			interrupts = <GIC_SPI 438 IRQ_TYPE_LEVEL_HIGH>;
 			clock-names = "adc";
@@ -1556,7 +1558,7 @@
 		};
 
 		i2s1: i2s@14d60000 {
-			compatible = "samsung,exynos7-i2s";
+			compatible = "samsung,exynos5433-i2s", "samsung,exynos7-i2s";
 			reg = <0x14d60000 0x100>;
 			dmas = <&pdma0 31>, <&pdma0 30>;
 			dma-names = "tx", "rx";
@@ -1571,7 +1573,7 @@
 		};
 
 		pwm: pwm@14dd0000 {
-			compatible = "samsung,exynos4210-pwm";
+			compatible = "samsung,exynos5433-pwm", "samsung,exynos4210-pwm";
 			reg = <0x14dd0000 0x100>;
 			interrupts = <GIC_SPI 416 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 417 IRQ_TYPE_LEVEL_HIGH>,
@@ -1586,7 +1588,8 @@
 		};
 
 		hsi2c_0: i2c@14e40000 {
-			compatible = "samsung,exynos7-hsi2c";
+			compatible = "samsung,exynos5433-hsi2c",
+				     "samsung,exynos7-hsi2c";
 			reg = <0x14e40000 0x1000>;
 			interrupts = <GIC_SPI 428 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -1599,7 +1602,8 @@
 		};
 
 		hsi2c_1: i2c@14e50000 {
-			compatible = "samsung,exynos7-hsi2c";
+			compatible = "samsung,exynos5433-hsi2c",
+				     "samsung,exynos7-hsi2c";
 			reg = <0x14e50000 0x1000>;
 			interrupts = <GIC_SPI 429 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -1612,7 +1616,8 @@
 		};
 
 		hsi2c_2: i2c@14e60000 {
-			compatible = "samsung,exynos7-hsi2c";
+			compatible = "samsung,exynos5433-hsi2c",
+				     "samsung,exynos7-hsi2c";
 			reg = <0x14e60000 0x1000>;
 			interrupts = <GIC_SPI 430 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -1625,7 +1630,8 @@
 		};
 
 		hsi2c_3: i2c@14e70000 {
-			compatible = "samsung,exynos7-hsi2c";
+			compatible = "samsung,exynos5433-hsi2c",
+				     "samsung,exynos7-hsi2c";
 			reg = <0x14e70000 0x1000>;
 			interrupts = <GIC_SPI 431 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -1638,7 +1644,8 @@
 		};
 
 		hsi2c_4: i2c@14ec0000 {
-			compatible = "samsung,exynos7-hsi2c";
+			compatible = "samsung,exynos5433-hsi2c",
+				     "samsung,exynos7-hsi2c";
 			reg = <0x14ec0000 0x1000>;
 			interrupts = <GIC_SPI 424 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -1651,7 +1658,8 @@
 		};
 
 		hsi2c_5: i2c@14ed0000 {
-			compatible = "samsung,exynos7-hsi2c";
+			compatible = "samsung,exynos5433-hsi2c",
+				     "samsung,exynos7-hsi2c";
 			reg = <0x14ed0000 0x1000>;
 			interrupts = <GIC_SPI 425 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -1664,7 +1672,8 @@
 		};
 
 		hsi2c_6: i2c@14ee0000 {
-			compatible = "samsung,exynos7-hsi2c";
+			compatible = "samsung,exynos5433-hsi2c",
+				     "samsung,exynos7-hsi2c";
 			reg = <0x14ee0000 0x1000>;
 			interrupts = <GIC_SPI 426 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -1677,7 +1686,8 @@
 		};
 
 		hsi2c_7: i2c@14ef0000 {
-			compatible = "samsung,exynos7-hsi2c";
+			compatible = "samsung,exynos5433-hsi2c",
+				     "samsung,exynos7-hsi2c";
 			reg = <0x14ef0000 0x1000>;
 			interrupts = <GIC_SPI 427 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -1690,7 +1700,8 @@
 		};
 
 		hsi2c_8: i2c@14d90000 {
-			compatible = "samsung,exynos7-hsi2c";
+			compatible = "samsung,exynos5433-hsi2c",
+				     "samsung,exynos7-hsi2c";
 			reg = <0x14d90000 0x1000>;
 			interrupts = <GIC_SPI 443 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -1703,7 +1714,8 @@
 		};
 
 		hsi2c_9: i2c@14da0000 {
-			compatible = "samsung,exynos7-hsi2c";
+			compatible = "samsung,exynos5433-hsi2c",
+				     "samsung,exynos7-hsi2c";
 			reg = <0x14da0000 0x1000>;
 			interrupts = <GIC_SPI 444 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -1716,7 +1728,8 @@
 		};
 
 		hsi2c_10: i2c@14de0000 {
-			compatible = "samsung,exynos7-hsi2c";
+			compatible = "samsung,exynos5433-hsi2c",
+				     "samsung,exynos7-hsi2c";
 			reg = <0x14de0000 0x1000>;
 			interrupts = <GIC_SPI 445 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -1729,7 +1742,8 @@
 		};
 
 		hsi2c_11: i2c@14df0000 {
-			compatible = "samsung,exynos7-hsi2c";
+			compatible = "samsung,exynos5433-hsi2c",
+				     "samsung,exynos7-hsi2c";
 			reg = <0x14df0000 0x1000>;
 			interrupts = <GIC_SPI 446 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -1820,7 +1834,8 @@
 		};
 
 		mshc_0: mmc@15540000 {
-			compatible = "samsung,exynos7-dw-mshc-smu";
+			compatible = "samsung,exynos5433-dw-mshc-smu",
+				     "samsung,exynos7-dw-mshc-smu";
 			interrupts = <GIC_SPI 225 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -1833,7 +1848,8 @@
 		};
 
 		mshc_1: mmc@15550000 {
-			compatible = "samsung,exynos7-dw-mshc-smu";
+			compatible = "samsung,exynos5433-dw-mshc-smu",
+				     "samsung,exynos7-dw-mshc-smu";
 			interrupts = <GIC_SPI 226 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -1846,7 +1862,8 @@
 		};
 
 		mshc_2: mmc@15560000 {
-			compatible = "samsung,exynos7-dw-mshc-smu";
+			compatible = "samsung,exynos5433-dw-mshc-smu",
+				     "samsung,exynos7-dw-mshc-smu";
 			interrupts = <GIC_SPI 227 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -1897,7 +1914,8 @@
 			};
 
 			i2s0: i2s@11440000 {
-				compatible = "samsung,exynos7-i2s";
+				compatible = "samsung,exynos5433-i2s",
+					     "samsung,exynos7-i2s";
 				reg = <0x11440000 0x100>;
 				dmas = <&adma 0>, <&adma 2>;
 				dma-names = "tx", "rx";
diff --git a/arch/arm64/boot/dts/exynos/exynos7.dtsi b/arch/arm64/boot/dts/exynos/exynos7.dtsi
index 6ed80ddf3369..9cb6bd61262e 100644
--- a/arch/arm64/boot/dts/exynos/exynos7.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos7.dtsi
@@ -128,7 +128,8 @@
 		ranges = <0 0 0 0x18000000>;
 
 		chipid@10000000 {
-			compatible = "samsung,exynos4210-chipid";
+			compatible = "samsung,exynos7-chipid",
+				     "samsung,exynos4210-chipid";
 			reg = <0x10000000 0x100>;
 		};
 
@@ -279,7 +280,7 @@
 		};
 
 		serial_0: serial@13630000 {
-			compatible = "samsung,exynos4210-uart";
+			compatible = "samsung,exynos7-uart", "samsung,exynos4210-uart";
 			reg = <0x13630000 0x100>;
 			interrupts = <GIC_SPI 440 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&clock_peric0 PCLK_UART0>,
@@ -289,7 +290,7 @@
 		};
 
 		serial_1: serial@14c20000 {
-			compatible = "samsung,exynos4210-uart";
+			compatible = "samsung,exynos7-uart", "samsung,exynos4210-uart";
 			reg = <0x14c20000 0x100>;
 			interrupts = <GIC_SPI 456 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&clock_peric1 PCLK_UART1>,
@@ -299,7 +300,7 @@
 		};
 
 		serial_2: serial@14c30000 {
-			compatible = "samsung,exynos4210-uart";
+			compatible = "samsung,exynos7-uart", "samsung,exynos4210-uart";
 			reg = <0x14c30000 0x100>;
 			interrupts = <GIC_SPI 457 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&clock_peric1 PCLK_UART2>,
@@ -309,7 +310,7 @@
 		};
 
 		serial_3: serial@14c40000 {
-			compatible = "samsung,exynos4210-uart";
+			compatible = "samsung,exynos7-uart", "samsung,exynos4210-uart";
 			reg = <0x14c40000 0x100>;
 			interrupts = <GIC_SPI 458 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&clock_peric1 PCLK_UART3>,
@@ -539,7 +540,7 @@
 		};
 
 		rtc: rtc@10590000 {
-			compatible = "samsung,s3c6410-rtc";
+			compatible = "samsung,exynos7-rtc", "samsung,s3c6410-rtc";
 			reg = <0x10590000 0x100>;
 			interrupts = <GIC_SPI 355 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 356 IRQ_TYPE_LEVEL_HIGH>;
@@ -559,7 +560,8 @@
 		};
 
 		gpu: gpu@14ac0000 {
-			compatible = "samsung,exynos5433-mali", "arm,mali-t760";
+			compatible = "samsung,exynos7-mali",
+				     "samsung,exynos5433-mali", "arm,mali-t760";
 			reg = <0x14ac0000 0x5000>;
 			interrupts = <GIC_SPI 241 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 242 IRQ_TYPE_LEVEL_HIGH>,
@@ -619,7 +621,7 @@
 		};
 
 		pwm: pwm@136c0000 {
-			compatible = "samsung,exynos4210-pwm";
+			compatible = "samsung,exynos7-pwm", "samsung,exynos4210-pwm";
 			reg = <0x136c0000 0x100>;
 			interrupts = <GIC_SPI 449 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 450 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/arm64/boot/dts/exynos/exynos7885.dtsi b/arch/arm64/boot/dts/exynos/exynos7885.dtsi
index d69fc2392bd0..008228fb319a 100644
--- a/arch/arm64/boot/dts/exynos/exynos7885.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos7885.dtsi
@@ -172,7 +172,8 @@
 		ranges = <0x0 0x0 0x0 0x20000000>;
 
 		chipid@10000000 {
-			compatible = "samsung,exynos850-chipid";
+			compatible = "samsung,exynos7885-chipid",
+				     "samsung,exynos850-chipid";
 			reg = <0x10000000 0x24>;
 		};
 
@@ -264,7 +265,8 @@
 			reg = <0x11cb0000 0x1000>;
 
 			wakeup-interrupt-controller {
-				compatible = "samsung,exynos7-wakeup-eint";
+				compatible = "samsung,exynos7885-wakeup-eint",
+					     "samsung,exynos7-wakeup-eint";
 				interrupt-parent = <&gic>;
 				interrupts = <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>;
 			};
@@ -289,12 +291,14 @@
 		};
 
 		pmu_system_controller: system-controller@11c80000 {
-			compatible = "samsung,exynos7-pmu", "syscon";
+			compatible = "samsung,exynos7885-pmu",
+				     "samsung,exynos7-pmu", "syscon";
 			reg = <0x11c80000 0x10000>;
 		};
 
 		mmc_0: mmc@13500000 {
-			compatible = "samsung,exynos7-dw-mshc-smu";
+			compatible = "samsung,exynos7885-dw-mshc-smu",
+				     "samsung,exynos7-dw-mshc-smu";
 			reg = <0x13500000 0x2000>;
 			interrupts = <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -307,7 +311,8 @@
 		};
 
 		serial_0: serial@13800000 {
-			compatible = "samsung,exynos5433-uart";
+			compatible = "samsung,exynos7885-uart",
+				     "samsung,exynos5433-uart";
 			reg = <0x13800000 0x100>;
 			interrupts = <GIC_SPI 246 IRQ_TYPE_LEVEL_HIGH>;
 			pinctrl-names = "default";
@@ -320,7 +325,8 @@
 		};
 
 		serial_1: serial@13810000 {
-			compatible = "samsung,exynos5433-uart";
+			compatible = "samsung,exynos7885-uart",
+				     "samsung,exynos5433-uart";
 			reg = <0x13810000 0x100>;
 			interrupts = <GIC_SPI 247 IRQ_TYPE_LEVEL_HIGH>;
 			pinctrl-names = "default";
@@ -333,7 +339,8 @@
 		};
 
 		serial_2: serial@13820000 {
-			compatible = "samsung,exynos5433-uart";
+			compatible = "samsung,exynos7885-uart",
+				     "samsung,exynos5433-uart";
 			reg = <0x13820000 0x100>;
 			interrupts = <GIC_SPI 279 IRQ_TYPE_LEVEL_HIGH>;
 			pinctrl-names = "default";
@@ -346,7 +353,8 @@
 		};
 
 		i2c_0: i2c@13830000 {
-			compatible = "samsung,s3c2440-i2c";
+			compatible = "samsung,exynos7885-i2c",
+				     "samsung,s3c2440-i2c";
 			reg = <0x13830000 0x100>;
 			interrupts = <GIC_SPI 248 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -359,7 +367,8 @@
 		};
 
 		i2c_1: i2c@13840000 {
-			compatible = "samsung,s3c2440-i2c";
+			compatible = "samsung,exynos7885-i2c",
+				     "samsung,s3c2440-i2c";
 			reg = <0x13840000 0x100>;
 			interrupts = <GIC_SPI 249 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -372,7 +381,8 @@
 		};
 
 		i2c_2: i2c@13850000 {
-			compatible = "samsung,s3c2440-i2c";
+			compatible = "samsung,exynos7885-i2c",
+				     "samsung,s3c2440-i2c";
 			reg = <0x13850000 0x100>;
 			interrupts = <GIC_SPI 250 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -385,7 +395,8 @@
 		};
 
 		i2c_3: i2c@13860000 {
-			compatible = "samsung,s3c2440-i2c";
+			compatible = "samsung,exynos7885-i2c",
+				     "samsung,s3c2440-i2c";
 			reg = <0x13860000 0x100>;
 			interrupts = <GIC_SPI 251 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -398,7 +409,8 @@
 		};
 
 		i2c_4: i2c@13870000 {
-			compatible = "samsung,s3c2440-i2c";
+			compatible = "samsung,exynos7885-i2c",
+				     "samsung,s3c2440-i2c";
 			reg = <0x13870000 0x100>;
 			interrupts = <GIC_SPI 252 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -411,7 +423,8 @@
 		};
 
 		i2c_5: i2c@13880000 {
-			compatible = "samsung,s3c2440-i2c";
+			compatible = "samsung,exynos7885-i2c",
+				     "samsung,s3c2440-i2c";
 			reg = <0x13880000 0x100>;
 			interrupts = <GIC_SPI 253 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -424,7 +437,8 @@
 		};
 
 		i2c_6: i2c@13890000 {
-			compatible = "samsung,s3c2440-i2c";
+			compatible = "samsung,exynos7885-i2c",
+				     "samsung,s3c2440-i2c";
 			reg = <0x13890000 0x100>;
 			interrupts = <GIC_SPI 254 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -437,7 +451,8 @@
 		};
 
 		i2c_7: i2c@11cd0000 {
-			compatible = "samsung,s3c2440-i2c";
+			compatible = "samsung,exynos7885-i2c",
+				     "samsung,s3c2440-i2c";
 			reg = <0x11cd0000 0x100>;
 			interrupts = <GIC_SPI 255 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/exynos/exynos850.dtsi b/arch/arm64/boot/dts/exynos/exynos850.dtsi
index 53104e65b9c6..da3f4a791e68 100644
--- a/arch/arm64/boot/dts/exynos/exynos850.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos850.dtsi
@@ -359,7 +359,8 @@
 			reg = <0x11850000 0x1000>;
 
 			wakeup-interrupt-controller {
-				compatible = "samsung,exynos850-wakeup-eint";
+				compatible = "samsung,exynos850-wakeup-eint",
+					     "samsung,exynos7-wakeup-eint";
 			};
 		};
 
@@ -368,7 +369,8 @@
 			reg = <0x11c30000 0x1000>;
 
 			wakeup-interrupt-controller {
-				compatible = "samsung,exynos850-wakeup-eint";
+				compatible = "samsung,exynos850-wakeup-eint",
+					     "samsung,exynos7-wakeup-eint";
 			};
 		};
 
@@ -396,7 +398,7 @@
 		};
 
 		rtc: rtc@11a30000 {
-			compatible = "samsung,s3c6410-rtc";
+			compatible = "samsung,exynos850-rtc", "samsung,s3c6410-rtc";
 			reg = <0x11a30000 0x100>;
 			interrupts = <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>;
@@ -406,7 +408,8 @@
 		};
 
 		mmc_0: mmc@12100000 {
-			compatible = "samsung,exynos7-dw-mshc-smu";
+			compatible = "samsung,exynos850-dw-mshc-smu",
+				     "samsung,exynos7-dw-mshc-smu";
 			reg = <0x12100000 0x2000>;
 			interrupts = <GIC_SPI 452 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -419,7 +422,7 @@
 		};
 
 		i2c_0: i2c@13830000 {
-			compatible = "samsung,s3c2440-i2c";
+			compatible = "samsung,exynos850-i2c", "samsung,s3c2440-i2c";
 			reg = <0x13830000 0x100>;
 			interrupts = <GIC_SPI 196 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -432,7 +435,7 @@
 		};
 
 		i2c_1: i2c@13840000 {
-			compatible = "samsung,s3c2440-i2c";
+			compatible = "samsung,exynos850-i2c", "samsung,s3c2440-i2c";
 			reg = <0x13840000 0x100>;
 			interrupts = <GIC_SPI 197 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -445,7 +448,7 @@
 		};
 
 		i2c_2: i2c@13850000 {
-			compatible = "samsung,s3c2440-i2c";
+			compatible = "samsung,exynos850-i2c", "samsung,s3c2440-i2c";
 			reg = <0x13850000 0x100>;
 			interrupts = <GIC_SPI 198 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -458,7 +461,7 @@
 		};
 
 		i2c_3: i2c@13860000 {
-			compatible = "samsung,s3c2440-i2c";
+			compatible = "samsung,exynos850-i2c", "samsung,s3c2440-i2c";
 			reg = <0x13860000 0x100>;
 			interrupts = <GIC_SPI 199 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -471,7 +474,7 @@
 		};
 
 		i2c_4: i2c@13870000 {
-			compatible = "samsung,s3c2440-i2c";
+			compatible = "samsung,exynos850-i2c", "samsung,s3c2440-i2c";
 			reg = <0x13870000 0x100>;
 			interrupts = <GIC_SPI 200 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -485,7 +488,7 @@
 
 		/* I2C_5 (also called CAM_PMIC_I2C in TRM) */
 		i2c_5: i2c@13880000 {
-			compatible = "samsung,s3c2440-i2c";
+			compatible = "samsung,exynos850-i2c", "samsung,s3c2440-i2c";
 			reg = <0x13880000 0x100>;
 			interrupts = <GIC_SPI 201 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -499,7 +502,7 @@
 
 		/* I2C_6 (also called MOTOR_I2C in TRM) */
 		i2c_6: i2c@13890000 {
-			compatible = "samsung,s3c2440-i2c";
+			compatible = "samsung,exynos850-i2c", "samsung,s3c2440-i2c";
 			reg = <0x13890000 0x100>;
 			interrupts = <GIC_SPI 202 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -640,7 +643,8 @@
 			status = "disabled";
 
 			hsi2c_0: i2c@138a0000 {
-				compatible = "samsung,exynosautov9-hsi2c";
+				compatible = "samsung,exynos850-hsi2c",
+					     "samsung,exynosautov9-hsi2c";
 				reg = <0x138a0000 0xc0>;
 				interrupts = <GIC_SPI 193 IRQ_TYPE_LEVEL_HIGH>;
 				#address-cells = <1>;
@@ -668,7 +672,8 @@
 			status = "disabled";
 
 			hsi2c_1: i2c@138b0000 {
-				compatible = "samsung,exynosautov9-hsi2c";
+				compatible = "samsung,exynos850-hsi2c",
+					     "samsung,exynosautov9-hsi2c";
 				reg = <0x138b0000 0xc0>;
 				interrupts = <GIC_SPI 194 IRQ_TYPE_LEVEL_HIGH>;
 				#address-cells = <1>;
@@ -696,7 +701,8 @@
 			status = "disabled";
 
 			hsi2c_2: i2c@138c0000 {
-				compatible = "samsung,exynosautov9-hsi2c";
+				compatible = "samsung,exynos850-hsi2c",
+					     "samsung,exynosautov9-hsi2c";
 				reg = <0x138c0000 0xc0>;
 				interrupts = <GIC_SPI 195 IRQ_TYPE_LEVEL_HIGH>;
 				#address-cells = <1>;
@@ -738,7 +744,8 @@
 			status = "disabled";
 
 			hsi2c_3: i2c@11d00000 {
-				compatible = "samsung,exynosautov9-hsi2c";
+				compatible = "samsung,exynos850-hsi2c",
+					     "samsung,exynosautov9-hsi2c";
 				reg = <0x11d00000 0xc0>;
 				interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>;
 				#address-cells = <1>;
@@ -778,7 +785,8 @@
 			status = "disabled";
 
 			hsi2c_4: i2c@11d20000 {
-				compatible = "samsung,exynosautov9-hsi2c";
+				compatible = "samsung,exynos850-hsi2c",
+					     "samsung,exynosautov9-hsi2c";
 				reg = <0x11d20000 0xc0>;
 				interrupts = <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>;
 				#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/exynos/exynosautov9-sadk.dts b/arch/arm64/boot/dts/exynos/exynosautov9-sadk.dts
index bc1815f6ada2..de2c1de51a76 100644
--- a/arch/arm64/boot/dts/exynos/exynosautov9-sadk.dts
+++ b/arch/arm64/boot/dts/exynos/exynosautov9-sadk.dts
@@ -9,6 +9,7 @@
 /dts-v1/;
 #include "exynosautov9.dtsi"
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
 
 / {
 	model = "Samsung ExynosAuto v9 SADK board";
@@ -32,6 +33,31 @@
 		      <0xa 0x00000000 0x2 0x00000000>;
 	};
 
+	gpio-keys {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&key_wakeup &key_volup &key_voldown>;
+
+		key-wakeup {
+			label = "Wakeup";
+			linux,code = <KEY_WAKEUP>;
+			gpios = <&gpa0 0 GPIO_ACTIVE_LOW>;
+			wakeup-source;
+		};
+
+		key-volume-down {
+			label = "Volume Down";
+			linux,code = <KEY_VOLUMEDOWN>;
+			gpios = <&gpg2 0 GPIO_ACTIVE_LOW>;
+		};
+
+		key-volume-up {
+			label = "Volume Up";
+			linux,code = <KEY_VOLUMEUP>;
+			gpios = <&gpg1 5 GPIO_ACTIVE_LOW>;
+		};
+	};
+
 	ufs_0_fixed_vcc_reg: regulator-0 {
 		compatible = "regulator-fixed";
 		regulator-name = "ufs-vcc";
@@ -49,6 +75,31 @@
 	};
 };
 
+&pinctrl_alive {
+	key_wakeup: key-wakeup-pins {
+		samsung,pins = "gpa0-0";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_EINT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS5420_PIN_DRV_LV1>;
+	};
+};
+
+&pinctrl_peric1 {
+	key_voldown: key-voldown-pins {
+		samsung,pins = "gpg2-0";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_EINT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS5420_PIN_DRV_LV1>;
+	};
+
+	key_volup: key-volup-pins {
+		samsung,pins = "gpg1-5";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_EINT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS5420_PIN_DRV_LV1>;
+	};
+};
+
 &pwm {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pwm_tout3>;
diff --git a/arch/arm64/boot/dts/exynos/exynosautov9.dtsi b/arch/arm64/boot/dts/exynos/exynosautov9.dtsi
index b228cd7e351e..c871a2f49fda 100644
--- a/arch/arm64/boot/dts/exynos/exynosautov9.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynosautov9.dtsi
@@ -166,7 +166,8 @@
 		ranges = <0x0 0x0 0x0 0x20000000>;
 
 		chipid@10000000 {
-			compatible = "samsung,exynos850-chipid";
+			compatible = "samsung,exynosautov9-chipid",
+				     "samsung,exynos850-chipid";
 			reg = <0x10000000 0x24>;
 		};
 
@@ -309,7 +310,9 @@
 			reg = <0x10450000 0x1000>;
 
 			wakeup-interrupt-controller {
-				compatible = "samsung,exynosautov9-wakeup-eint";
+				compatible = "samsung,exynosautov9-wakeup-eint",
+					     "samsung,exynos850-wakeup-eint",
+					     "samsung,exynos7-wakeup-eint";
 			};
 		};
 
@@ -349,7 +352,8 @@
 		};
 
 		pmu_system_controller: system-controller@10460000 {
-			compatible = "samsung,exynos7-pmu", "syscon";
+			compatible = "samsung,exynosautov9-pmu",
+				     "samsung,exynos7-pmu", "syscon";
 			reg = <0x10460000 0x10000>;
 
 			reboot: syscon-reboot {
diff --git a/arch/arm64/boot/dts/exynos/exynosautov920-pinctrl.dtsi b/arch/arm64/boot/dts/exynos/exynosautov920-pinctrl.dtsi
new file mode 100644
index 000000000000..663e8265cbf5
--- /dev/null
+++ b/arch/arm64/boot/dts/exynos/exynosautov920-pinctrl.dtsi
@@ -0,0 +1,1266 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Samsung's ExynosAutov920 SoC pin-mux and pin-config device tree source
+ *
+ * Copyright (c) 2023 Samsung Electronics Co., Ltd.
+ *
+ * Samsung's ExynosAutov920 SoC pin-mux and pin-config options are listed as
+ * device tree nodes in this file.
+ */
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+#include "exynos-pinctrl.h"
+
+&pinctrl_alive {
+	gpa0: gpa0-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
+	gpa1: gpa1-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
+	gpq0: gpq0-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+};
+
+&pinctrl_aud {
+	gpb0: gpb0-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpb1: gpb1-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpb2: gpb2-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpb3: gpb3-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpb4: gpb4-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpb5: gpb5-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpb6: gpb6-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+};
+
+&pinctrl_hsi0 {
+	gph0: gph0-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gph1: gph1-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+};
+
+&pinctrl_hsi1 {
+	gph8: gph8-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+};
+
+&pinctrl_hsi2 {
+	gph3: gph3-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gph4: gph4-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gph5: gph5-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gph6: gph6-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+};
+
+&pinctrl_hsi2ufs {
+	gph2: gph2-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	ufs_refclk_out: ufs-refclk-out-pins {
+		samsung,pins = "gph2-0";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-con-pdn = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	ufs_rst_n: ufs-rst-n-pins {
+		samsung,pins = "gph2-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-con-pdn = <EXYNOS_PIN_PULL_DOWN>;
+	};
+
+	ufs_refclk_out_1: ufs-refclk-out-1-pins {
+		samsung,pins = "gph2-2";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-con-pdn = <EXYNOS_PIN_PULL_DOWN>;
+	};
+
+	ufs_rst_n_1: ufs-rst-n-1-pins {
+		samsung,pins = "gph2-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-con-pdn = <EXYNOS_PIN_PULL_DOWN>;
+	};
+};
+
+&pinctrl_peric0 {
+	gpg0: gpg0-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpg2: gpg2-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpg3: gpg3-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpg4: gpg4-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpg5: gpg5-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp0: gpp0-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp1: gpp1-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp2: gpp2-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp3: gpp3-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp4: gpp4-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	/* PWM PERIC0 */
+	pwm_tout0: pwm-tout0-pins {
+		samsung,pins = "gpg0-0";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_4>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	pwm_tout1: pwm-tout1-pins {
+		samsung,pins = "gpg0-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_4>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	pwm_tout2: pwm-tout2-pins {
+		samsung,pins = "gpg0-2";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_4>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	pwm_tout3: pwm-tout3-pins {
+		samsung,pins = "gpg0-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_4>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* UART PERIC0_USI00 */
+	uart0_bus: uart0-bus-pins {
+		samsung,pins = "gpp0-0", "gpp0-1", "gpp0-2", "gpp0-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	uart0_bus_dual: uart0-bus-dual-pins {
+		samsung,pins = "gpp0-0", "gpp0-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* UART PERIC0_USI01 */
+	uart1_bus: uart1-bus-pins {
+		samsung,pins = "gpp0-4", "gpp0-5", "gpp0-6", "gpp0-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	uart1_bus_dual: uart1-bus-dual-pins {
+		samsung,pins = "gpp0-4", "gpp0-5";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* UART PERIC0_USI02 */
+	uart2_bus: uart2-bus-pins {
+		samsung,pins = "gpp1-0", "gpp1-1", "gpp1-2", "gpp1-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	uart2_bus_dual: uart2-bus-dual-pins {
+		samsung,pins = "gpp1-0", "gpp1-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* UART PERIC0_USI03 */
+	uart3_bus: uart3-bus-pins {
+		samsung,pins = "gpp1-4", "gpp1-5", "gpp1-6", "gpp1-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	uart3_bus_dual: uart3-bus-dual-pins {
+		samsung,pins = "gpp1-4", "gpp1-5";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* UART PERIC0_USI04 */
+	uart4_bus: uart4-bus-pins {
+		samsung,pins = "gpp2-0", "gpp2-1", "gpp2-2", "gpp2-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	uart4_bus_dual: uart4-bus-dual-pins {
+		samsung,pins = "gpp2-0", "gpp2-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* UART PERIC0_USI05 */
+	uart5_bus: uart5-bus-pins {
+		samsung,pins = "gpp2-4", "gpp2-5", "gpp2-6", "gpp2-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	uart5_bus_dual: uart5-bus-dual-pins {
+		samsung,pins = "gpp2-4", "gpp2-5";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* UART PERIC0_USI06 */
+	uart6_bus: uart6-bus-pins {
+		samsung,pins = "gpp3-0", "gpp3-1", "gpp3-2", "gpp3-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	uart6_bus_dual: uart6-bus-dual-pins {
+		samsung,pins = "gpp3-0", "gpp3-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* UART PERIC0_USI07 */
+	uart7_bus: uart7-bus-pins {
+		samsung,pins = "gpp3-4", "gpp3-5", "gpp3-6", "gpp3-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	uart7_bus_dual: uart7-bus-dual-pins {
+		samsung,pins = "gpp3-4", "gpp3-5";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* UART PERIC0_USI08 */
+	uart8_bus: uart8-bus-pins {
+		samsung,pins = "gpp4-0", "gpp4-1", "gpp4-2", "gpp4-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	uart8_bus_dual: uart8-bus-dual-pins {
+		samsung,pins = "gpp4-0", "gpp4-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC0 USI00  */
+	hsi2c0_bus: hsi2c0-bus-pins {
+		samsung,pins = "gpp0-0", "gpp0-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC0 USI00_I2C */
+	hsi2c1_bus: hsi2c1-bus-pins {
+		samsung,pins = "gpp0-2", "gpp0-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC0 USI01 */
+	hsi2c2_bus: hsi2c2-bus-pins {
+		samsung,pins = "gpp0-4", "gpp0-5";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC0 USI01_I2C */
+	hsi2c3_bus: hsi2c3-bus-pins {
+		samsung,pins = "gpp0-6", "gpp0-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC0 USI02 */
+	hsi2c4_bus: hsi2c4-bus-pins {
+		samsung,pins = "gpp1-0", "gpp1-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC0 USI02_I2C */
+	hsi2c5_bus: hsi2c5-bus-pins {
+		samsung,pins = "gpp1-2", "gpp1-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC0 USI03 */
+	hsi2c6_bus: hsi2c6-bus-pins {
+		samsung,pins = "gpp1-4", "gpp1-5";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC0 USI03_I2C */
+	hsi2c7_bus: hsi2c7-bus-pins {
+		samsung,pins = "gpp1-6", "gpp1-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC0 USI04 */
+	hsi2c8_bus: hsi2c8-bus-pins {
+		samsung,pins = "gpp2-0", "gpp2-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC0 USI04_I2C */
+	hsi2c9_bus: hsi2c9-bus-pins {
+		samsung,pins = "gpp2-2", "gpp2-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC0 USI05 */
+	hsi2c10_bus: hsi2c10-bus-pins {
+		samsung,pins = "gpp2-4", "gpp2-5";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC0 USI05_I2C */
+	hsi2c11_bus: hsi2c11-bus-pins {
+		samsung,pins = "gpp2-6", "gpp2-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC0 USI06 */
+	hsi2c12_bus: hsi2c12-bus-pins {
+		samsung,pins = "gpp3-0", "gpp3-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC0 USI06_I2C */
+	hsi2c13_bus: hsi2c13-bus-pins {
+		samsung,pins = "gpp3-2", "gpp3-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC0 USI07 */
+	hsi2c14_bus: hsi2c14-bus-pins {
+		samsung,pins = "gpp3-4", "gpp3-5";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC0 USI07_I2C */
+	hsi2c15_bus: hsi2c15-bus-pins {
+		samsung,pins = "gpp3-6", "gpp3-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC0 USI08 */
+	hsi2c16_bus: hsi2c16-bus-pins {
+		samsung,pins = "gpp4-0", "gpp4-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC0 USI08_I2C */
+	hsi2c17_bus: hsi2c17-bus-pins {
+		samsung,pins = "gpp4-2", "gpp4-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* SPI PERIC0 USI00 */
+	spi0_bus: spi0-bus-pins {
+		samsung,pins = "gpp0-0", "gpp0-1", "gpp0-2";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi0_cs: spi0-cs-pins {
+		samsung,pins = "gpp0-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi0_cs_func: spi0-cs-func-pins {
+		samsung,pins = "gpp0-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* SPI PERIC0 USI01 */
+	spi1_bus: spi1-bus-pins {
+		samsung,pins = "gpp0-4", "gpp0-5", "gpp0-6";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi1_cs: spi1-cs-pins {
+		samsung,pins = "gpp0-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi1_cs_func: spi1-cs-func-pins {
+		samsung,pins = "gpp0-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* SPI PERIC0 USI02 */
+	spi2_bus: spi2-bus-pins {
+		samsung,pins = "gpp1-0", "gpp1-1", "gpp1-2";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi2_cs: spi2-cs-pins {
+		samsung,pins = "gpp1-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi2_cs_func: spi2-cs-func-pins {
+		samsung,pins = "gpp1-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* SPI PERIC0 USI03 */
+	spi3_bus: spi3-bus-pins {
+		samsung,pins = "gpp1-4", "gpp1-5", "gpp1-6";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi3_cs: spi3-cs-pins {
+		samsung,pins = "gpp1-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi3_cs_func: spi3-cs-func-pins {
+		samsung,pins = "gpp1-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* SPI PERIC0 USI04 */
+	spi4_bus: spi4-bus-pins {
+		samsung,pins = "gpp2-0", "gpp2-1", "gpp2-2";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi4_cs: spi4-cs-pins {
+		samsung,pins = "gpp2-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi4_cs_func: spi4-cs-func-pins {
+		samsung,pins = "gpp2-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* SPI PERIC0 USI05 */
+	spi5_bus: spi5-bus-pins {
+		samsung,pins = "gpp2-4", "gpp2-5", "gpp2-6";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi5_cs: spi5-cs-pins {
+		samsung,pins = "gpp2-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi5_cs_func: spi5-cs-func-pins {
+		samsung,pins = "gpp2-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* SPI PERIC0 USI06 */
+	spi6_bus: spi6-bus-pins {
+		samsung,pins = "gpp3-0", "gpp3-1", "gpp3-2";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi6_cs: spi6-cs-pins {
+		samsung,pins = "gpp3-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi6_cs_func: spi6-cs-func-pins {
+		samsung,pins = "gpp3-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* SPI PERIC0 USI07 */
+	spi7_bus: spi7-bus-pins {
+		samsung,pins = "gpp3-4", "gpp3-5", "gpp3-6";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi7_cs: spi7-cs-pins {
+		samsung,pins = "gpp3-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi7_cs_func: spi7-cs-func-pins {
+		samsung,pins = "gpp3-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* SPI PERIC0 USI08 */
+	spi8_bus: spi8-bus-pins {
+		samsung,pins = "gpp4-0", "gpp4-1", "gpp4-2";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi8_cs: spi8-cs-pins {
+		samsung,pins = "gpp4-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi8_cs_func: spi8-cs-func-pins {
+		samsung,pins = "gpp4-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I3C PERIC0 */
+	i3c0_bus: i3c0-bus-pins {
+		samsung,pins = "gpp2-6", "gpp2-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_4>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	i3c1_bus: i3c1-bus-pins {
+		samsung,pins = "gpp3-2", "gpp3-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_4>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	i3c2_bus: i3c2-bus-pins {
+		samsung,pins = "gpp3-6", "gpp3-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_4>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	i3c3_bus: i3c3-bus-pins {
+		samsung,pins = "gpp4-2", "gpp4-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_4>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+};
+
+&pinctrl_peric1 {
+	gpg1: gpg1-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp5: gpp5-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp6: gpp6-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp7: gpp7-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp8: gpp8-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp9: gpp9-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp10: gpp10-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp11: gpp11-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp12: gpp12-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	/* UART PERIC1 USI09 */
+	uart9_bus: uart9-bus-pins {
+		samsung,pins = "gpp5-0", "gpp5-1", "gpp5-2", "gpp5-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	uart9_bus_dual: uart9-bus-dual-pins {
+		samsung,pins = "gpp5-0", "gpp5-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* UART PERIC1 USI10 */
+	uart10_bus: uart10-bus-pins {
+		samsung,pins = "gpp5-4", "gpp5-5", "gpp5-6", "gpp5-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	uart10_bus_dual: uart10-bus-dual-pins {
+		samsung,pins = "gpp5-4", "gpp5-5";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* UART PERIC1 USI11 */
+	uart11_bus: uart11-bus-pins {
+		samsung,pins = "gpp10-0", "gpp10-1", "gpp10-2", "gpp10-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	uart11_bus_dual: uart11-bus-dual-pins {
+		samsung,pins = "gpp10-0", "gpp10-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* UART PERIC1_USI12 */
+	uart12_bus: uart12-bus-pins {
+		samsung,pins = "gpp7-0", "gpp7-1", "gpp7-2", "gpp7-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	uart12_bus_dual: uart12-bus-dual-pins {
+		samsung,pins = "gpp7-0", "gpp7-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* UART PERIC1_USI13 */
+	uart13_bus: uart13-bus-pins {
+		samsung,pins = "gpp7-4", "gpp7-5", "gpp7-6", "gpp7-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	uart13_bus_dual: uart13-bus-dual-pins {
+		samsung,pins = "gpp7-4", "gpp7-5";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* UART PERIC1 USI14 */
+	uart14_bus: uart14-bus-pins {
+		samsung,pins = "gpp8-0", "gpp8-1", "gpp8-2", "gpp8-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	uart14_bus_dual: uart14-bus-dual-pins {
+		samsung,pins = "gpp8-0", "gpp8-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* UART PERIC1 USI15 */
+	uart15_bus: uart15-bus-pins {
+		samsung,pins = "gpp11-0", "gpp11-1", "gpp11-2", "gpp11-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	uart15_bus_dual: uart15-bus-dual-pins {
+		samsung,pins = "gpp11-0", "gpp11-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* UART PERIC1 USI16 */
+	uart16_bus: uart16-bus-pins {
+		samsung,pins = "gpp9-0", "gpp9-1", "gpp9-2", "gpp9-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	uart16_bus_dual: uart16-bus-dual-pins {
+		samsung,pins = "gpp9-0", "gpp9-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* UART PERIC1 USI17 */
+	uart17_bus: uart17-bus-pins {
+		samsung,pins = "gpp12-0", "gpp12-1", "gpp12-2", "gpp12-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	uart17_bus_dual: uart17-bus-dual-pins {
+		samsung,pins = "gpp12-0", "gpp12-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC1 USI09 */
+	hsi2c18_bus: hsi2c18-bus-pins {
+		samsung,pins = "gpp5-0", "gpp5-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC1 USI09_I2C */
+	hsi2c19_bus: hsi2c19-bus-pins {
+		samsung,pins = "gpp5-2", "gpp5-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC1 USI10 */
+	hsi2c20_bus: hsi2c20-bus-pins {
+		samsung,pins = "gpp5-4", "gpp5-5";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC1 USI10_I2C */
+	hsi2c21_bus: hsi2c21-bus-pins {
+		samsung,pins = "gpp5-6", "gpp5-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC1 USI11 */
+	hsi2c22_bus: hsi2c22-bus-pins {
+		samsung,pins = "gpp10-0", "gpp10-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC1 USI11_I2C */
+	hsi2c23_bus: hsi2c23-bus-pins {
+		samsung,pins = "gpp10-2", "gpp10-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC1 USI12 */
+	hsi2c24_bus: hsi2c24-bus-pins {
+		samsung,pins = "gpp7-0", "gpp7-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC1 USI12_I2C */
+	hsi2c25_bus: hsi2c25-bus-pins {
+		samsung,pins = "gpp7-2", "gpp7-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC1 USI13 */
+	hsi2c26_bus: hsi2c26-bus-pins {
+		samsung,pins = "gpp7-4", "gpp7-5";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC1 USI13_I2C */
+	hsi2c27_bus: hsi2c27-bus-pins {
+		samsung,pins = "gpp7-6", "gpp7-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC1 USI14 */
+	hsi2c28_bus: hsi2c28-bus-pins {
+		samsung,pins = "gpp8-0", "gpp8-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC1 USI14_I2C */
+	hsi2c29_bus: hsi2c29-bus-pins {
+		samsung,pins = "gpp8-2", "gpp8-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC1 USI15 */
+	hsi2c30_bus: hsi2c30-bus-pins {
+		samsung,pins = "gpp11-0", "gpp11-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC1 USI15_I2C */
+	hsi2c31_bus: hsi2c31-bus-pins {
+		samsung,pins = "gpp11-2", "gpp11-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC1 USI16 */
+	hsi2c32_bus: hsi2c32-bus-pins {
+		samsung,pins = "gpp9-0", "gpp9-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC1 USI16_I2C */
+	hsi2c33_bus: hsi2c33-bus-pins {
+		samsung,pins = "gpp9-2", "gpp9-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC1 USI17 */
+	hsi2c34_bus: hsi2c34-bus-pins {
+		samsung,pins = "gpp12-0", "gpp12-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I2C PERIC1 USI17_I2C */
+	hsi2c35_bus: hsi2c35-bus-pins {
+		samsung,pins = "gpp12-2", "gpp12-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* SPI PERIC1 USI09 */
+	spi9_bus: spi9-bus-pins {
+		samsung,pins = "gpp5-0", "gpp5-1", "gpp5-2";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi9_cs: spi9-cs-pins {
+		samsung,pins = "gpp5-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi9_cs_func: spi9-cs-func-pins {
+		samsung,pins = "gpp5-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* SPI PERIC1 USI10 */
+	spi10_bus: spi10-bus-pins {
+		samsung,pins = "gpp5-4", "gpp5-5", "gpp5-6";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi10_cs: spi10-cs-pins {
+		samsung,pins = "gpp5-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi10_cs_func: spi10-cs-func-pins {
+		samsung,pins = "gpp5-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* SPI PERIC1 USI11 */
+	spi11_bus: spi11-bus-pins {
+		samsung,pins = "gpp10-0", "gpp10-1", "gpp10-2";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi11_cs: spi11-cs-pins {
+		samsung,pins = "gpp10-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi11_cs_func: spi11-cs-func-pins {
+		samsung,pins = "gpp10-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* SPI PERIC1 USI12 */
+	spi12_bus: spi12-bus-pins {
+		samsung,pins = "gpp7-0", "gpp7-1", "gpp7-2";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi12_cs: spi12-cs-pins {
+		samsung,pins = "gpp7-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi12_cs_func: spi12-cs-func-pins {
+		samsung,pins = "gpp7-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* SPI PERIC1 USI13 */
+	spi13_bus: spi13-bus-pins {
+		samsung,pins = "gpp7-4", "gpp7-5", "gpp7-6";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi13_cs: spi13-cs-pins {
+		samsung,pins = "gpp7-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi13_cs_func: spi13-cs-func-pins {
+		samsung,pins = "gpp7-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* SPI PERIC1 USI14 */
+	spi14_bus: spi14-bus-pins {
+		samsung,pins = "gpp8-0", "gpp8-1", "gpp8-2";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi14_cs: spi14-cs-pins {
+		samsung,pins = "gpp8-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi14_cs_func: spi14-cs-func-pins {
+		samsung,pins = "gpp8-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* SPI PERIC1 USI15 */
+	spi15_bus: spi15-bus-pins {
+		samsung,pins = "gpp11-0", "gpp11-1", "gpp11-2";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi15_cs: spi15-cs-pins {
+		samsung,pins = "gpp11-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi15_cs_func: spi15-cs-func-pins {
+		samsung,pins = "gpp11-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* SPI PERIC1 USI16 */
+	spi16_bus: spi16-bus-pins {
+		samsung,pins = "gpp9-0", "gpp9-1", "gpp9-2";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi16_cs: spi16-cs-pins {
+		samsung,pins = "gpp9-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi16_cs_func: spi16-cs-func-pins {
+		samsung,pins = "gpp9-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* SPI PERIC1 USI17 */
+	spi17_bus: spi17-bus-pins {
+		samsung,pins = "gpp12-0", "gpp12-1", "gpp12-2";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi17_cs: spi17-cs-pins {
+		samsung,pins = "gpp12-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	spi17_cs_func: spi17-cs-func-pins {
+		samsung,pins = "gpp12-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	/* I3C PERIC1 */
+	i3c4_bus: i3c4-bus-pins {
+		samsung,pins = "gpp7-2", "gpp7-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_4>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	i3c5_bus: i3c5-bus-pins {
+		samsung,pins = "gpp7-6", "gpp7-7";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_4>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	i3c6_bus: i3c6-bus-pins {
+		samsung,pins = "gpp8-2", "gpp8-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_4>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
+	i3c7_bus: i3c7-bus-pins {
+		samsung,pins = "gpp11-2", "gpp11-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_4>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+};
diff --git a/arch/arm64/boot/dts/exynos/exynosautov920-sadk.dts b/arch/arm64/boot/dts/exynos/exynosautov920-sadk.dts
new file mode 100644
index 000000000000..a397f068ed53
--- /dev/null
+++ b/arch/arm64/boot/dts/exynos/exynosautov920-sadk.dts
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Samsung's ExynosAutov920 SADK board device tree source
+ *
+ * Copyright (c) 2023 Samsung Electronics Co., Ltd.
+ *
+ */
+
+/dts-v1/;
+#include "exynosautov920.dtsi"
+#include "exynos-pinctrl.h"
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+
+/ {
+	model = "Samsung ExynosAutov920 SADK board";
+	compatible = "samsung,exynosautov920-sadk", "samsung,exynosautov920";
+
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	aliases {
+		serial0 = &serial_0;
+	};
+
+	chosen {
+		stdout-path = &serial_0;
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&key_wakeup &key_back>;
+
+		key-wakeup {
+			label = "KEY_WAKEUP";
+			linux,code = <KEY_WAKEUP>;
+			gpios = <&gpa0 0 GPIO_ACTIVE_LOW>;
+			wakeup-source;
+		};
+
+		key-back {
+			label = "KEY_BACK";
+			linux,code = <KEY_BACK>;
+			gpios = <&gpp6 3 GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x0 0x80000000 0x0 0x70000000>,
+		      <0x8 0x80000000 0x1 0xfba00000>,
+		      <0xa 0x00000000 0x2 0x00000000>;
+	};
+};
+
+&pinctrl_alive {
+	key_wakeup: key-wakeup-pins {
+		samsung,pins = "gpa0-0";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_EINT>;
+	};
+};
+
+&pinctrl_peric1 {
+	key_back: key-back-pins {
+		samsung,pins = "gpp6-3";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_EINT>;
+	};
+};
+
+&pwm {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pwm_tout0>;
+	status = "okay";
+};
+
+&serial_0 {
+	status = "okay";
+};
+
+&usi_0 {
+	samsung,clkreq-on; /* needed for UART mode */
+	status = "okay";
+};
+
+&xtcxo {
+	clock-frequency = <38400000>;
+};
diff --git a/arch/arm64/boot/dts/exynos/exynosautov920.dtsi b/arch/arm64/boot/dts/exynos/exynosautov920.dtsi
new file mode 100644
index 000000000000..c1c8566d74f5
--- /dev/null
+++ b/arch/arm64/boot/dts/exynos/exynosautov920.dtsi
@@ -0,0 +1,312 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Samsung's ExynosAutov920 SoC device tree source
+ *
+ * Copyright (c) 2023 Samsung Electronics Co., Ltd.
+ *
+ */
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/soc/samsung,exynos-usi.h>
+
+/ {
+	compatible = "samsung,exynosautov920";
+	#address-cells = <2>;
+	#size-cells = <1>;
+
+	interrupt-parent = <&gic>;
+
+	aliases {
+		pinctrl0 = &pinctrl_alive;
+		pinctrl1 = &pinctrl_aud;
+		pinctrl2 = &pinctrl_hsi0;
+		pinctrl3 = &pinctrl_hsi1;
+		pinctrl4 = &pinctrl_hsi2;
+		pinctrl5 = &pinctrl_hsi2ufs;
+		pinctrl6 = &pinctrl_peric0;
+		pinctrl7 = &pinctrl_peric1;
+	};
+
+	arm-pmu {
+		compatible = "arm,cortex-a78-pmu";
+		interrupts = <GIC_PPI 7 IRQ_TYPE_LEVEL_LOW>;
+	};
+
+	xtcxo: clock {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-output-names = "oscclk";
+	};
+
+	/*
+	 * FIXME: Keep the stub clock for serial driver, until proper clock
+	 * driver is implemented.
+	 */
+	clock_usi: clock-usi {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <200000000>;
+		clock-output-names = "usi";
+	};
+
+	cpus: cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&cpu0>;
+				};
+				core1 {
+					cpu = <&cpu1>;
+				};
+				core2 {
+					cpu = <&cpu2>;
+				};
+				core3 {
+					cpu = <&cpu3>;
+				};
+			};
+
+			cluster1 {
+				core0 {
+					cpu = <&cpu4>;
+				};
+				core1 {
+					cpu = <&cpu5>;
+				};
+				core2 {
+					cpu = <&cpu6>;
+				};
+				core3 {
+					cpu = <&cpu7>;
+				};
+			};
+
+			cluster2 {
+				core0 {
+					cpu = <&cpu8>;
+				};
+				core1 {
+					cpu = <&cpu9>;
+				};
+			};
+		};
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a78ae";
+			reg = <0x0 0x0>;
+			enable-method = "psci";
+		};
+
+		cpu1: cpu@100 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a78ae";
+			reg = <0x0 0x100>;
+			enable-method = "psci";
+		};
+
+		cpu2: cpu@200 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a78ae";
+			reg = <0x0 0x200>;
+			enable-method = "psci";
+		};
+
+		cpu3: cpu@300 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a78ae";
+			reg = <0x0 0x300>;
+			enable-method = "psci";
+		};
+
+		cpu4: cpu@10000 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a78ae";
+			reg = <0x0 0x10000>;
+			enable-method = "psci";
+		};
+
+		cpu5: cpu@10100 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a78ae";
+			reg = <0x0 0x10100>;
+			enable-method = "psci";
+		};
+
+		cpu6: cpu@10200 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a78ae";
+			reg = <0x0 0x10200>;
+			enable-method = "psci";
+		};
+
+		cpu7: cpu@10300 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a78ae";
+			reg = <0x0 0x10300>;
+			enable-method = "psci";
+		};
+
+		cpu8: cpu@20000 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a78ae";
+			reg = <0x0 0x20000>;
+			enable-method = "psci";
+		};
+
+		cpu9: cpu@20100 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a78ae";
+			reg = <0x0 0x20100>;
+			enable-method = "psci";
+		};
+	};
+
+	psci {
+		compatible = "arm,psci-1.0";
+		method = "smc";
+	};
+
+	soc: soc@0 {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x0 0x0 0x0 0x20000000>;
+
+		chipid@10000000 {
+			compatible = "samsung,exynosautov920-chipid",
+				     "samsung,exynos850-chipid";
+			reg = <0x10000000 0x24>;
+		};
+
+		gic: interrupt-controller@10400000 {
+			compatible = "arm,gic-v3";
+			#interrupt-cells = <3>;
+			#address-cells = <0>;
+			interrupt-controller;
+			reg = <0x10400000 0x10000>,
+			      <0x10460000 0x140000>;
+			interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		syscon_peric0: syscon@10820000 {
+			compatible = "samsung,exynosautov920-peric0-sysreg",
+				     "syscon";
+			reg = <0x10820000 0x2000>;
+		};
+
+		pinctrl_peric0: pinctrl@10830000 {
+			compatible = "samsung,exynosautov920-pinctrl";
+			reg = <0x10830000 0x10000>;
+			interrupts = <GIC_SPI 753 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		usi_0: usi@108800c0 {
+			compatible = "samsung,exynosautov920-usi",
+				     "samsung,exynos850-usi";
+			reg = <0x108800c0 0x20>;
+			samsung,sysreg = <&syscon_peric0 0x1000>;
+			samsung,mode = <USI_V2_UART>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges;
+			clocks = <&clock_usi>, <&clock_usi>;
+			clock-names = "pclk", "ipclk";
+			status = "disabled";
+
+			serial_0: serial@10880000 {
+				compatible = "samsung,exynosautov920-uart",
+					     "samsung,exynos850-uart";
+				reg = <0x10880000 0xc0>;
+				interrupts = <GIC_SPI 764 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-names = "default";
+				pinctrl-0 = <&uart0_bus>;
+				clocks = <&clock_usi>, <&clock_usi>;
+				clock-names = "uart", "clk_uart_baud0";
+				samsung,uart-fifosize = <256>;
+				status = "disabled";
+			};
+		};
+
+		pwm: pwm@109b0000 {
+			compatible = "samsung,exynosautov920-pwm",
+				     "samsung,exynos4210-pwm";
+			reg = <0x109b0000 0x100>;
+			samsung,pwm-outputs = <0>, <1>, <2>, <3>;
+			#pwm-cells = <3>;
+			clocks = <&xtcxo>;
+			clock-names = "timers";
+			status = "disabled";
+		};
+
+		syscon_peric1: syscon@10c20000 {
+			compatible = "samsung,exynosautov920-peric1-sysreg",
+				     "syscon";
+			reg = <0x10c20000 0x2000>;
+		};
+
+		pinctrl_peric1: pinctrl@10c30000 {
+			compatible = "samsung,exynosautov920-pinctrl";
+			reg = <0x10c30000 0x10000>;
+			interrupts = <GIC_SPI 781 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		pinctrl_alive: pinctrl@11850000 {
+			compatible = "samsung,exynosautov920-pinctrl";
+			reg = <0x11850000 0x10000>;
+
+			wakeup-interrupt-controller {
+				compatible = "samsung,exynosautov920-wakeup-eint";
+			};
+		};
+
+		pmu_system_controller: system-controller@11860000 {
+			compatible = "samsung,exynosautov920-pmu",
+				     "samsung,exynos7-pmu","syscon";
+			reg = <0x11860000 0x10000>;
+		};
+
+		pinctrl_hsi0: pinctrl@16040000 {
+			compatible = "samsung,exynosautov920-pinctrl";
+			reg = <0x16040000 0x10000>;
+			interrupts = <GIC_SPI 442 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		pinctrl_hsi1: pinctrl@16450000 {
+			compatible = "samsung,exynosautov920-pinctrl";
+			reg = <0x16450000 0x10000>;
+			interrupts = <GIC_SPI 456 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		pinctrl_hsi2: pinctrl@16c10000 {
+			compatible = "samsung,exynosautov920-pinctrl";
+			reg = <0x16c10000 0x10000>;
+			interrupts = <GIC_SPI 602 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		pinctrl_hsi2ufs: pinctrl@16d20000 {
+			compatible = "samsung,exynosautov920-pinctrl";
+			reg = <0x16d20000 0x10000>;
+			interrupts = <GIC_SPI 603 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		pinctrl_aud: pinctrl@1a460000 {
+			compatible = "samsung,exynosautov920-pinctrl";
+			reg = <0x1a460000 0x10000>;
+		};
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>;
+	};
+};
+
+#include "exynosautov920-pinctrl.dtsi"
diff --git a/arch/arm64/boot/dts/exynos/google/Makefile b/arch/arm64/boot/dts/exynos/google/Makefile
new file mode 100644
index 000000000000..0a6d5e1fe4ee
--- /dev/null
+++ b/arch/arm64/boot/dts/exynos/google/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+
+dtb-$(CONFIG_ARCH_EXYNOS) += \
+	gs101-oriole.dtb \
diff --git a/arch/arm64/boot/dts/exynos/google/gs101-oriole.dts b/arch/arm64/boot/dts/exynos/google/gs101-oriole.dts
new file mode 100644
index 000000000000..4a71f752200d
--- /dev/null
+++ b/arch/arm64/boot/dts/exynos/google/gs101-oriole.dts
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Oriole Device Tree
+ *
+ * Copyright 2021-2023 Google LLC
+ * Copyright 2023 Linaro Ltd - <peter.griffin@linaro.org>
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include "gs101-pinctrl.h"
+#include "gs101.dtsi"
+
+/ {
+	model = "Oriole";
+	compatible = "google,gs101-oriole", "google,gs101";
+
+	aliases {
+		serial0 = &serial_0;
+	};
+
+	chosen {
+		/* Bootloader expects bootargs specified otherwise it crashes */
+		bootargs = "";
+		stdout-path = &serial_0;
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&key_voldown>, <&key_volup>, <&key_power>;
+
+		button-vol-down {
+			label = "KEY_VOLUMEDOWN";
+			linux,code = <KEY_VOLUMEDOWN>;
+			gpios = <&gpa7 3 GPIO_ACTIVE_LOW>;
+			wakeup-source;
+		};
+
+		button-vol-up {
+			label = "KEY_VOLUMEUP";
+			linux,code = <KEY_VOLUMEUP>;
+			gpios = <&gpa8 1 GPIO_ACTIVE_LOW>;
+			wakeup-source;
+		};
+
+		button-power {
+			label = "KEY_POWER";
+			linux,code = <KEY_POWER>;
+			gpios = <&gpa10 1 GPIO_ACTIVE_LOW>;
+			wakeup-source;
+		};
+	};
+};
+
+&ext_24_5m {
+	clock-frequency = <24576000>;
+};
+
+&ext_200m {
+	clock-frequency = <200000000>;
+};
+
+&pinctrl_far_alive {
+	key_voldown: key-voldown-pins {
+		samsung,pins = "gpa7-3";
+		samsung,pin-function = <GS101_PIN_FUNC_EINT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	key_volup: key-volup-pins {
+		samsung,pins = "gpa8-1";
+		samsung,pin-function = <GS101_PIN_FUNC_EINT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+};
+
+&pinctrl_gpio_alive {
+	key_power: key-power-pins {
+		samsung,pins = "gpa10-1";
+		samsung,pin-function = <GS101_PIN_FUNC_EINT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+};
+
+&serial_0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart0_bus>;
+	status = "okay";
+};
+
+&usi_uart {
+	samsung,clkreq-on; /* needed for UART mode */
+	status = "okay";
+};
+
+&watchdog_cl0 {
+	timeout-sec = <30>;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/exynos/google/gs101-pinctrl.dtsi b/arch/arm64/boot/dts/exynos/google/gs101-pinctrl.dtsi
new file mode 100644
index 000000000000..e6a9776d4d62
--- /dev/null
+++ b/arch/arm64/boot/dts/exynos/google/gs101-pinctrl.dtsi
@@ -0,0 +1,1249 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * GS101 SoC pin-mux and pin-config device tree source
+ *
+ * Copyright 2019-2023 Google LLC
+ * Copyright 2023 Linaro Ltd - <peter.griffin@linaro.org>
+ */
+
+#include "gs101-pinctrl.h"
+
+&pinctrl_gpio_alive {
+	gpa0: gpa0-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 1 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH 0>;
+	};
+
+	gpa1: gpa1-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH 0>;
+	};
+
+	gpa2: gpa2-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH 0>;
+	};
+
+	gpa3: gpa3-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH 0>;
+	};
+
+	gpa4: gpa4-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH 0>;
+	};
+
+	gpa5: gpa5-gpio-bank  {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		interrupts = <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH 0>;
+	};
+
+	gpa9: gpa9-gpio-bank  {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		interrupts = <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH 0>;
+	};
+
+	gpa10: gpa10-gpio-bank  {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		interrupts = <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH 0>;
+	};
+
+	uart15_bus: uart15-bus-pins {
+		samsung,pins = "gpa2-3", "gpa2-4";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+	};
+
+	uart16_bus: uart16-bus-pins {
+		samsung,pins = "gpa3-0", "gpa3-1", "gpa3-2", "gpa3-3";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+	};
+
+	uart17_bus: uart17-bus-pins {
+		samsung,pins = "gpa4-0", "gpa4-1", "gpa4-2", "gpa4-3";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+	};
+
+	spi15_bus: spi15-bus-pins {
+		samsung,pins = "gpa4-0", "gpa4-1", "gpa4-2";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi15_cs: spi15-cs-pins {
+		samsung,pins = "gpa4-3";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+};
+
+&pinctrl_far_alive {
+	gpa6: gpa6-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 46 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 48 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH 0>;
+	};
+
+	gpa7: gpa7-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH 0>;
+	};
+
+	gpa8: gpa8-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 59 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 60 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 61 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH 0>;
+	};
+
+	gpa11: gpa11-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 66 IRQ_TYPE_LEVEL_HIGH 0>;
+	};
+};
+
+&pinctrl_gsacore {
+	gps0: gps0-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gps1: gps1-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gps2: gps2-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+};
+
+&pinctrl_gsactrl {
+	gps3: gps3-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+};
+
+&pinctrl_hsi1 {
+	gph0: gph0-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gph1: gph1-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	pcie0_clkreq: pcie0-clkreq-pins{
+		samsung,pins = "gph0-1";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_UP>;
+		samsung,pin-drv = <GS101_PIN_DRV_10_MA>;
+		samsung,pin-con-pdn = <GS101_PIN_PDN_PREV>;
+		samsung,pin-pud-pdn = <GS101_PIN_PULL_UP>;
+	};
+
+	pcie0_perst: pcie0-perst-pins {
+		samsung,pins = "gph0-0";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-drv = <GS101_PIN_DRV_10_MA>;
+		samsung,pin-con-pdn = <GS101_PIN_PDN_PREV>;
+	};
+};
+
+&pinctrl_hsi2 {
+	gph2: gph2-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gph3: gph3-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gph4: gph4-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	sd2_clk: sd2-clk-pins {
+		samsung,pins = "gph4-0";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_7_5_MA>;
+	};
+
+	sd2_cmd: sd2-cmd-pins {
+		samsung,pins = "gph4-1";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_UP>;
+		samsung,pin-drv = <GS101_PIN_DRV_7_5_MA>;
+	};
+
+	sd2_bus1: sd2-bus-width1-pins {
+		samsung,pins = "gph4-2";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_UP>;
+		samsung,pin-drv = <GS101_PIN_DRV_7_5_MA>;
+	};
+
+	sd2_bus4: sd2-bus-width4-pins {
+		samsung,pins = "gph4-3", "gph4-4", "gph4-5";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_UP>;
+		samsung,pin-drv = <GS101_PIN_DRV_7_5_MA>;
+	};
+
+	sd2_clk_fast_slew_rate_1x: sd2-clk-fast-slew-rate-1x-pins {
+		samsung,pins = "gph4-0";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	sd2_clk_fast_slew_rate_2x: sd2-clk-fast-slew-rate-2x-pins {
+		samsung,pins = "gph4-0";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_5_MA>;
+	};
+
+	sd2_clk_fast_slew_rate_3x: sd2-clk-fast-slew-rate-3x-pins {
+		samsung,pins = "gph4-0";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_7_5_MA>;
+	};
+
+	sd2_clk_fast_slew_rate_4x: sd2-clk-fast-slew-rate-4x-pins {
+		samsung,pins = "gph4-0";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_10_MA>;
+	};
+
+	ufs_rst_n: ufs-rst-n-pins {
+		samsung,pins = "gph3-1";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-con-pdn = <GS101_PIN_PDN_PREV>;
+		samsung,pin-pud-pdn = <GS101_PIN_PULL_NONE>;
+	};
+
+	ufs_refclk_out: ufs-refclk-out-pins {
+		samsung,pins = "gph3-0";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-con-pdn = <GS101_PIN_PDN_PREV>;
+		samsung,pin-pud-pdn = <GS101_PIN_PULL_NONE>;
+	};
+
+	pcie1_clkreq: pcie1-clkreq-pins {
+		samsung,pins = "gph2-1";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_UP>;
+		samsung,pin-drv = <GS101_PIN_DRV_10_MA>;
+		samsung,pin-con-pdn = <GS101_PIN_PDN_PREV>;
+		samsung,pin-pud-pdn = <GS101_PIN_PULL_UP>;
+	};
+
+	pcie1_perst: pcie1-perst-pins {
+		samsung,pins = "gph2-0";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-drv = <GS101_PIN_DRV_10_MA>;
+		samsung,pin-con-pdn = <GS101_PIN_PDN_PREV>;
+	};
+};
+
+&pinctrl_peric0 {
+	gpp0: gpp0-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp1: gpp1-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp2: gpp2-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp3: gpp3-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp4: gpp4-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp5: gpp5-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp6: gpp6-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp7: gpp7-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp8: gpp8-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp9: gpp9-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp10: gpp10-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp11: gpp11-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp12: gpp12-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp13: gpp13-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp14: gpp14-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp15: gpp15-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp16: gpp16-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp17: gpp17-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp18: gpp18-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp19: gpp19-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	/* USI_PERIC0_UART_DBG */
+	uart0_bus: uart0-bus-pins {
+		samsung,pins = "gpp1-2", "gpp1-3";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+	};
+
+	disp_te_pri_on: disp-te-pri-on-pins {
+		samsung,pins = "gpp0-3";
+		samsung,pin-function = <GS101_PIN_FUNC_EINT>;
+	};
+
+	disp_te_pri_off: disp-te-pri-off-pins {
+		samsung,pins = "gpp0-3";
+		samsung,pin-function = <GS101_PIN_FUNC_INPUT>;
+	};
+
+	disp_te_sec_on: disp-te-sec-on-pins {
+		samsung,pins = "gpp0-4";
+		samsung,pin-function = <GS101_PIN_FUNC_EINT>;
+	};
+
+	disp_te_sec_off: disp-te-sec-off-pins {
+		samsung,pins = "gpp0-4";
+		samsung,pin-function = <GS101_PIN_FUNC_INPUT>;
+	};
+
+	sensor_mclk1_out: sensor-mclk1-out-pins {
+		samsung,pins = "gpp3-0";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_DOWN>;
+		samsung,pin-drv = <GS101_PIN_DRV_5_MA>;
+	};
+
+	sensor_mclk1_fn: sensor-mclk1-fn-pins {
+		samsung,pins = "gpp3-0";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_5_MA>;
+	};
+
+	sensor_mclk2_out: sensor-mclk2-out-pins {
+		samsung,pins = "gpp5-0";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_DOWN>;
+		samsung,pin-drv = <GS101_PIN_DRV_5_MA>;
+	};
+
+	sensor_mclk2_fn: sensor-mclk2-fn-pins {
+		samsung,pins = "gpp5-0";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_5_MA>;
+	};
+
+	sensor_mclk3_out: sensor-mclk3-out-pins {
+		samsung,pins = "gpp7-0";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_DOWN>;
+		samsung,pin-drv = <GS101_PIN_DRV_5_MA>;
+	};
+
+	sensor_mclk3_fn: sensor-mclk3-fn-pins {
+		samsung,pins = "gpp7-0";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_5_MA>;
+	};
+
+	sensor_mclk4_out: sensor-mclk4-out-pins {
+		samsung,pins = "gpp9-0";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_DOWN>;
+		samsung,pin-drv = <GS101_PIN_DRV_5_MA>;
+	};
+
+	sensor_mclk4_fn: sensor-mclk4-fn-pins {
+		samsung,pins = "gpp9-0";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_5_MA>;
+	};
+
+	sensor_mclk5_out: sensor-mclk5-out-pins {
+		samsung,pins = "gpp11-0";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_DOWN>;
+		samsung,pin-drv = <GS101_PIN_DRV_5_MA>;
+	};
+
+	sensor_mclk5_fn: sensor-mclk5-fn-pins {
+		samsung,pins = "gpp11-0";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_5_MA>;
+	};
+
+	sensor_mclk6_out: sensor-mclk6-out-pins {
+		samsung,pins = "gpp13-0";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_DOWN>;
+		samsung,pin-drv = <GS101_PIN_DRV_5_MA>;
+	};
+
+	sensor_mclk6_fn: sensor-mclk6-fn-pins {
+		samsung,pins = "gpp13-0";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_5_MA>;
+	};
+
+	sensor_mclk7_out: sensor-mclk7-out-pins {
+		samsung,pins = "gpp15-0";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_DOWN>;
+		samsung,pin-drv = <GS101_PIN_DRV_5_MA>;
+	};
+
+	sensor_mclk7_fn: sensor-mclk7-fn-pins {
+		samsung,pins = "gpp15-0";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_5_MA>;
+	};
+
+	sensor_mclk8_out: sensor-mclk8-out-pins {
+		samsung,pins = "gpp17-0";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_DOWN>;
+		samsung,pin-drv = <GS101_PIN_DRV_5_MA>;
+	};
+
+	sensor_mclk8_fn: sensor-mclk8-fn-pins {
+		samsung,pins = "gpp17-0";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_5_MA>;
+	};
+
+	hsi2c14_bus: hsi2c14-bus-pins {
+		samsung,pins = "gpp18-0", "gpp18-1";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	uart14_bus_single: uart14-bus-pins {
+		samsung,pins = "gpp18-0", "gpp18-1",
+			       "gpp18-2", "gpp18-3";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+	};
+
+	spi14_bus: spi14-bus-pins {
+		samsung,pins = "gpp18-0", "gpp18-1", "gpp18-2";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi14_cs: spi14-cs-pins {
+		samsung,pins = "gpp18-3";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi14_cs_func: spi14-cs-func-pins {
+		samsung,pins = "gpp18-3";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	hsi2c8_bus: hsi2c8-bus-pins {
+		samsung,pins = "gpp16-0", "gpp16-1";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+		samsung,pin-pud-pdn = <GS101_PIN_PDN_OUT0>;
+	};
+
+	uart8_bus_single: uart8-bus-pins {
+		samsung,pins = "gpp16-0", "gpp16-1", "gpp16-2",
+			       "gpp16-3";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+	};
+
+	spi8_bus: spi8-bus-pins {
+		samsung,pins = "gpp16-0", "gpp16-1", "gpp16-2";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi8_cs: spi8-cs-pins {
+		samsung,pins = "gpp16-3";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi8_cs_func: spi8-cs-func-pins {
+		samsung,pins = "gpp16-3";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	hsi2c7_bus: hsi2c7-bus-pins {
+		samsung,pins = "gpp14-0", "gpp14-1";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	uart7_bus_single: uart7-bus-pins {
+		samsung,pins = "gpp14-0", "gpp14-1",
+			       "gpp14-2", "gpp14-3";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+	};
+
+	spi7_bus: spi7-bus-pins {
+		samsung,pins = "gpp14-0", "gpp14-1", "gpp14-2";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi7_cs: spi7-cs-pins {
+		samsung,pins = "gpp14-3";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi7_cs_func: spi7-cs-func-pins {
+		samsung,pins = "gpp14-3";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	hsi2c6_bus: hsi2c6-bus-pins {
+		samsung,pins = "gpp12-0", "gpp12-1";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	uart6_bus_single: uart6-bus-pins {
+		samsung,pins = "gpp12-0", "gpp12-1",
+			       "gpp12-2", "gpp12-3";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+	};
+
+	spi6_bus: spi6-bus-pins {
+		samsung,pins = "gpp12-0", "gpp12-1", "gpp12-2";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi6_cs: spi6-cs-pins {
+		samsung,pins = "gpp12-3";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi6_cs_func: spi6-cs-func-pins {
+		samsung,pins = "gpp12-3";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	hsi2c5_bus: hsi2c5-bus-pins {
+		samsung,pins = "gpp10-0", "gpp10-1";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	uart5_bus_single: uart5-bus-pins {
+		samsung,pins = "gpp10-0", "gpp10-1",
+			       "gpp10-2", "gpp10-3";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+	};
+
+	spi5_bus: spi5-bus-pins {
+		samsung,pins = "gpp10-0", "gpp10-1", "gpp10-2";
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-con-pdn = <GS101_PIN_PDN_PREV>;
+		samsung,pin-pud-pdn = <GS101_PIN_PULL_NONE>;
+	};
+
+	spi5_cs_func: spi5-cs-func-pins {
+		samsung,pins = "gpp10-3";
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-con-pdn = <GS101_PIN_PDN_PREV>;
+		samsung,pin-pud-pdn = <GS101_PIN_PULL_NONE>;
+	};
+
+	hsi2c4_bus: hsi2c4-bus-pins {
+		samsung,pins = "gpp8-0", "gpp8-1";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	uart4_bus_single: uart4-bus-pins {
+		samsung,pins = "gpp8-0", "gpp8-1",
+			       "gpp8-2", "gpp8-3";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+	};
+
+	spi4_bus: spi4-bus-pins {
+		samsung,pins = "gpp8-0", "gpp8-1", "gpp8-2";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi4_cs: spi4-cs-pins {
+		samsung,pins = "gpp8-3";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi4_cs_func: spi4-cs-func-pins {
+		samsung,pins = "gpp8-3";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	hsi2c3_bus: hsi2c3-bus-pins {
+		samsung,pins = "gpp6-0", "gpp6-1";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	uart3_bus_single: uart3-bus-pins {
+		samsung,pins = "gpp6-0", "gpp6-1",
+			       "gpp6-2", "gpp6-3";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+	};
+
+	spi3_bus: spi3-bus-pins {
+		samsung,pins = "gpp6-0", "gpp6-1", "gpp6-2";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi3_cs: spi3-cs-pins {
+		samsung,pins = "gpp6-3";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi3_cs_func: spi3-cs-func-pins {
+		samsung,pins = "gpp6-3";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	hsi2c2_bus: hsi2c2-bus-pins {
+		samsung,pins = "gpp4-0", "gpp4-1";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	uart2_bus_single: uart2-bus-pins {
+		samsung,pins = "gpp4-0", "gpp4-1",
+			       "gpp4-2", "gpp4-3";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+	};
+
+	spi2_bus: spi2-bus-pins {
+		samsung,pins = "gpp4-0", "gpp4-1", "gpp4-2";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi2_cs: spi2-cs-pins {
+		samsung,pins = "gpp4-3";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi2_cs_func: spi2-cs-func-pins {
+		samsung,pins = "gpp4-3";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	hsi2c1_bus: hsi2c1-bus-pins {
+		samsung,pins = "gpp2-0", "gpp2-1";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	uart1_bus_single: uart1-bus-pins {
+		samsung,pins = "gpp2-0", "gpp2-1",
+			       "gpp2-2", "gpp2-3";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+	};
+
+	spi1_bus: spi1-bus-pins {
+		samsung,pins = "gpp2-0", "gpp2-1", "gpp2-2";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi1_cs: spi1-cs-pins {
+		samsung,pins = "gpp2-3";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi1_cs_func: spi1-cs-func-pins {
+		samsung,pins = "gpp2-3";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+};
+
+&pinctrl_peric1 {
+	gpp20: gpp20-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp21: gpp21-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp22: gpp22-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp23: gpp23-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp24: gpp24-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp25: gpp25-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp26: gpp26-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpp27: gpp27-gpio-bank {
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	hsi2c13_bus: hsi2c13-bus-pins  {
+		samsung,pins = "gpp25-0", "gpp25-1";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	uart13_bus_single: uart13-bus-pins {
+		samsung,pins = "gpp25-0", "gpp25-1",
+			       "gpp25-2", "gpp25-3";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+	};
+
+	spi13_bus: spi13-bus-pins {
+		samsung,pins = "gpp25-0", "gpp25-1", "gpp25-2";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi13_cs: spi13-cs-pins {
+		samsung,pins = "gpp25-3";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi13_cs_func: spi13-cs-func-pins {
+		samsung,pins = "gpp25-3";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	hsi2c12_bus: hsi2c12-bus-pins {
+		samsung,pins = "gpp23-4", "gpp23-5";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	uart12_bus_single: uart12-bus-pins {
+		samsung,pins = "gpp23-4", "gpp23-5",
+			       "gpp23-6", "gpp23-7";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+	};
+
+	spi12_bus: spi12-bus-pins {
+		samsung,pins = "gpp23-4", "gpp23-5", "gpp23-6";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi14_cs2: spi14-cs2-pins {
+		samsung,pins = "gpp23-6";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi12_cs: spi12-cs-pins {
+		samsung,pins = "gpp23-7";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi12_cs_func: spi12-cs-func-pins {
+		samsung,pins = "gpp23-7";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	hsi2c11_bus: hsi2c11-bus-pins {
+		samsung,pins = "gpp23-0", "gpp23-1";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	uart11_bus_single: uart11-bus-pins {
+		samsung,pins = "gpp23-0", "gpp23-1",
+			       "gpp23-2", "gpp23-3";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+	};
+
+	spi11_bus: spi11-bus-pins {
+		samsung,pins = "gpp23-0", "gpp23-1", "gpp23-2";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi11_cs: spi11-cs-pins {
+		samsung,pins = "gpp23-3";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi11_cs_func: spi11-cs-func-pins {
+		samsung,pins = "gpp23-3";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	hsi2c10_bus: hsi2c10-bus-pins {
+		samsung,pins = "gpp21-0", "gpp21-1";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	uart10_bus_single: uart10-bus-pins {
+		samsung,pins = "gpp21-0", "gpp21-1",
+			       "gpp21-2", "gpp21-3";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+	};
+
+	spi10_bus: spi10-bus-pins {
+		samsung,pins = "gpp21-0", "gpp21-1", "gpp21-2";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi10_cs: spi10-cs-pins {
+		samsung,pins = "gpp21-3";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi10_cs_func: spi10-cs-func-pins {
+		samsung,pins = "gpp21-3";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	hsi2c9_bus: hsi2c9-bus-pins {
+		samsung,pins = "gpp20-4", "gpp20-5";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	uart9_bus_single: uart9-bus-pins {
+		samsung,pins = "gpp20-4", "gpp20-5",
+			       "gpp20-6", "gpp20-7";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+	};
+
+	spi9_bus: spi9-bus-pins {
+		samsung,pins = "gpp20-4", "gpp20-5", "gpp20-6";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi9_cs: spi9-cs-pins {
+		samsung,pins = "gpp20-7";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi9_cs_func: spi9-cs-func-pins {
+		samsung,pins = "gpp20-7";
+		samsung,pin-function = <GS101_PIN_FUNC_2>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	hsi2c0_bus: hsi2c0-bus-pins {
+		samsung,pins = "gpp20-0", "gpp20-1";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	uart0_bus_single: uart0-bus-pins {
+		samsung,pins = "gpp20-0", "gpp20-1",
+			       "gpp20-2", "gpp20-3";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+	};
+
+	spi0_bus: spi0-bus-pins {
+		samsung,pins = "gpp20-0", "gpp20-1", "gpp20-2";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi0_cs: spi0-cs-pins {
+		samsung,pins = "gpp20-3";
+		samsung,pin-function = <GS101_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	spi0_cs_func: spi0-cs-func-pins {
+		samsung,pins = "gpp20-3";
+		samsung,pin-function = <GS101_PIN_FUNC_3>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+};
diff --git a/arch/arm64/boot/dts/exynos/google/gs101-pinctrl.h b/arch/arm64/boot/dts/exynos/google/gs101-pinctrl.h
new file mode 100644
index 000000000000..b7d276b1e25a
--- /dev/null
+++ b/arch/arm64/boot/dts/exynos/google/gs101-pinctrl.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Pinctrl binding constants for GS101
+ *
+ * Copyright 2020-2023 Google LLC
+ */
+
+#ifndef __DTS_ARM64_SAMSUNG_EXYNOS_GOOGLE_PINCTRL_GS101_H__
+#define __DTS_ARM64_SAMSUNG_EXYNOS_GOOGLE_PINCTRL_GS101_H__
+
+#define GS101_PIN_PULL_NONE		0
+#define GS101_PIN_PULL_DOWN		1
+#define GS101_PIN_PULL_UP		3
+
+/* Pin function in power down mode */
+#define GS101_PIN_PDN_OUT0		0
+#define GS101_PIN_PDN_OUT1		1
+#define GS101_PIN_PDN_INPUT		2
+#define GS101_PIN_PDN_PREV		3
+
+/* GS101 drive strengths */
+#define GS101_PIN_DRV_2_5_MA		0
+#define GS101_PIN_DRV_5_MA		1
+#define GS101_PIN_DRV_7_5_MA		2
+#define GS101_PIN_DRV_10_MA		3
+
+#define GS101_PIN_FUNC_INPUT		0
+#define GS101_PIN_FUNC_OUTPUT		1
+#define GS101_PIN_FUNC_2		2
+#define GS101_PIN_FUNC_3		3
+#define GS101_PIN_FUNC_EINT		0xf
+
+#endif /* __DTS_ARM64_SAMSUNG_EXYNOS_GOOGLE_PINCTRL_GS101_H__ */
diff --git a/arch/arm64/boot/dts/exynos/google/gs101.dtsi b/arch/arm64/boot/dts/exynos/google/gs101.dtsi
new file mode 100644
index 000000000000..9747cb3fa03a
--- /dev/null
+++ b/arch/arm64/boot/dts/exynos/google/gs101.dtsi
@@ -0,0 +1,473 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * GS101 SoC
+ *
+ * Copyright 2019-2023 Google LLC
+ * Copyright 2023 Linaro Ltd - <peter.griffin@linaro.org>
+ */
+
+#include <dt-bindings/clock/google,gs101.h>
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/soc/samsung,exynos-usi.h>
+
+/ {
+	compatible = "google,gs101";
+	#address-cells = <2>;
+	#size-cells = <1>;
+
+	interrupt-parent = <&gic>;
+
+	aliases {
+		pinctrl0 = &pinctrl_gpio_alive;
+		pinctrl1 = &pinctrl_far_alive;
+		pinctrl2 = &pinctrl_gsacore;
+		pinctrl3 = &pinctrl_gsactrl;
+		pinctrl4 = &pinctrl_peric0;
+		pinctrl5 = &pinctrl_peric1;
+		pinctrl6 = &pinctrl_hsi1;
+		pinctrl7 = &pinctrl_hsi2;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&cpu0>;
+				};
+				core1 {
+					cpu = <&cpu1>;
+				};
+				core2 {
+					cpu = <&cpu2>;
+				};
+				core3 {
+					cpu = <&cpu3>;
+				};
+			};
+
+			cluster1 {
+				core0 {
+					cpu = <&cpu4>;
+				};
+				core1 {
+					cpu = <&cpu5>;
+				};
+			};
+
+			cluster2 {
+				core0 {
+					cpu = <&cpu6>;
+				};
+				core1 {
+					cpu = <&cpu7>;
+				};
+			};
+		};
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a55";
+			reg = <0x0000>;
+			enable-method = "psci";
+			cpu-idle-states =  <&ANANKE_CPU_SLEEP>;
+			capacity-dmips-mhz = <250>;
+			dynamic-power-coefficient = <70>;
+		};
+
+		cpu1: cpu@100 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a55";
+			reg = <0x0100>;
+			enable-method = "psci";
+			cpu-idle-states =  <&ANANKE_CPU_SLEEP>;
+			capacity-dmips-mhz = <250>;
+			dynamic-power-coefficient = <70>;
+		};
+
+		cpu2: cpu@200 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a55";
+			reg = <0x0200>;
+			enable-method = "psci";
+			cpu-idle-states =  <&ANANKE_CPU_SLEEP>;
+			capacity-dmips-mhz = <250>;
+			dynamic-power-coefficient = <70>;
+		};
+
+		cpu3: cpu@300 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a55";
+			reg = <0x0300>;
+			enable-method = "psci";
+			cpu-idle-states =  <&ANANKE_CPU_SLEEP>;
+			capacity-dmips-mhz = <250>;
+			dynamic-power-coefficient = <70>;
+		};
+
+		cpu4: cpu@400 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a76";
+			reg = <0x0400>;
+			enable-method = "psci";
+			cpu-idle-states =  <&ENYO_CPU_SLEEP>;
+			capacity-dmips-mhz = <620>;
+			dynamic-power-coefficient = <284>;
+		};
+
+		cpu5: cpu@500 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a76";
+			reg = <0x0500>;
+			enable-method = "psci";
+			cpu-idle-states =  <&ENYO_CPU_SLEEP>;
+			capacity-dmips-mhz = <620>;
+			dynamic-power-coefficient = <284>;
+		};
+
+		cpu6: cpu@600 {
+			device_type = "cpu";
+			compatible = "arm,cortex-x1";
+			reg = <0x0600>;
+			enable-method = "psci";
+			cpu-idle-states =  <&HERA_CPU_SLEEP>;
+			capacity-dmips-mhz = <1024>;
+			dynamic-power-coefficient = <650>;
+		};
+
+		cpu7: cpu@700 {
+			device_type = "cpu";
+			compatible = "arm,cortex-x1";
+			reg = <0x0700>;
+			enable-method = "psci";
+			cpu-idle-states =  <&HERA_CPU_SLEEP>;
+			capacity-dmips-mhz = <1024>;
+			dynamic-power-coefficient = <650>;
+		};
+
+		idle-states {
+			entry-method = "psci";
+
+			ANANKE_CPU_SLEEP: cpu-ananke-sleep {
+				idle-state-name = "c2";
+				compatible = "arm,idle-state";
+				arm,psci-suspend-param = <0x0010000>;
+				entry-latency-us = <70>;
+				exit-latency-us = <160>;
+				min-residency-us = <2000>;
+			};
+
+			ENYO_CPU_SLEEP: cpu-enyo-sleep {
+				idle-state-name = "c2";
+				compatible = "arm,idle-state";
+				arm,psci-suspend-param = <0x0010000>;
+				entry-latency-us = <150>;
+				exit-latency-us = <190>;
+				min-residency-us = <2500>;
+			};
+
+			HERA_CPU_SLEEP: cpu-hera-sleep {
+				idle-state-name = "c2";
+				compatible = "arm,idle-state";
+				arm,psci-suspend-param = <0x0010000>;
+				entry-latency-us = <235>;
+				exit-latency-us = <220>;
+				min-residency-us = <3500>;
+			};
+		};
+	};
+
+	/* TODO replace with CCF clock */
+	dummy_clk: clock-3 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <12345>;
+		clock-output-names = "pclk";
+	};
+
+	/* ect node is required to be present by bootloader */
+	ect {
+	};
+
+	ext_24_5m: clock-1 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-output-names = "oscclk";
+	};
+
+	ext_200m: clock-2 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-output-names = "ext-200m";
+	};
+
+	pmu-0 {
+		compatible = "arm,cortex-a55-pmu";
+		interrupts = <GIC_PPI 7 IRQ_TYPE_LEVEL_HIGH &ppi_cluster0>;
+	};
+
+	pmu-1 {
+		compatible = "arm,cortex-a76-pmu";
+		interrupts = <GIC_PPI 7 IRQ_TYPE_LEVEL_HIGH &ppi_cluster1>;
+	};
+
+	pmu-2 {
+		compatible = "arm,cortex-x1-pmu";
+		interrupts = <GIC_PPI 7 IRQ_TYPE_LEVEL_HIGH &ppi_cluster2>;
+	};
+
+	pmu-3 {
+		compatible = "arm,dsu-pmu";
+		interrupts = <GIC_SPI 257 IRQ_TYPE_LEVEL_HIGH 0>;
+		cpus = <&cpu0>, <&cpu1>, <&cpu2>, <&cpu3>,
+		       <&cpu4>, <&cpu5>, <&cpu6>, <&cpu7>;
+	};
+
+	psci {
+		compatible = "arm,psci-1.0";
+		method = "smc";
+	};
+
+	reserved_memory: reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges;
+
+		gsa_reserved_protected: gsa@90200000 {
+			reg = <0x0 0x90200000 0x400000>;
+			no-map;
+		};
+
+		tpu_fw_reserved: tpu-fw@93000000 {
+			reg = <0x0 0x93000000 0x1000000>;
+			no-map;
+		};
+
+		aoc_reserve: aoc@94000000 {
+			reg = <0x0 0x94000000 0x03000000>;
+			no-map;
+		};
+
+		abl_reserved: abl@f8800000 {
+			reg = <0x0 0xf8800000 0x02000000>;
+			no-map;
+		};
+
+		dss_log_reserved: dss-log-reserved@fd3f0000 {
+			reg = <0x0 0xfd3f0000 0x0000e000>;
+			no-map;
+		};
+
+		debug_kinfo_reserved: debug-kinfo-reserved@fd3fe000 {
+			reg = <0x0 0xfd3fe000 0x00001000>;
+			no-map;
+		};
+
+		bldr_log_reserved: bldr-log-reserved@fd800000 {
+			reg = <0x0 0xfd800000 0x00100000>;
+			no-map;
+		};
+
+		bldr_log_hist_reserved: bldr-log-hist-reserved@fd900000 {
+			reg = <0x0 0xfd900000 0x00002000>;
+			no-map;
+		};
+	};
+
+	soc: soc@0 {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x0 0x0 0x0 0x40000000>;
+
+		cmu_misc: clock-controller@10010000 {
+			compatible = "google,gs101-cmu-misc";
+			reg = <0x10010000 0x8000>;
+			#clock-cells = <1>;
+			clocks = <&cmu_top CLK_DOUT_CMU_MISC_BUS>,
+				 <&cmu_top CLK_DOUT_CMU_MISC_SSS>;
+			clock-names = "dout_cmu_misc_bus", "dout_cmu_misc_sss";
+		};
+
+		watchdog_cl0: watchdog@10060000 {
+			compatible = "google,gs101-wdt";
+			reg = <0x10060000 0x100>;
+			interrupts = <GIC_SPI 765 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&cmu_misc CLK_GOUT_MISC_WDT_CLUSTER0_PCLK>,
+				 <&ext_24_5m>;
+			clock-names = "watchdog", "watchdog_src";
+			samsung,syscon-phandle = <&pmu_system_controller>;
+			samsung,cluster-index = <0>;
+			status = "disabled";
+		};
+
+		watchdog_cl1: watchdog@10070000 {
+			compatible = "google,gs101-wdt";
+			reg = <0x10070000 0x100>;
+			interrupts = <GIC_SPI 766 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&cmu_misc CLK_GOUT_MISC_WDT_CLUSTER1_PCLK>,
+				 <&ext_24_5m>;
+			clock-names = "watchdog", "watchdog_src";
+			samsung,syscon-phandle = <&pmu_system_controller>;
+			samsung,cluster-index = <1>;
+			status = "disabled";
+		};
+
+		gic: interrupt-controller@10400000 {
+			compatible = "arm,gic-v3";
+			#interrupt-cells = <4>;
+			interrupt-controller;
+			reg = <0x10400000 0x10000>, /* GICD */
+			      <0x10440000 0x100000>;/* GICR * 8 */
+			interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH 0>;
+
+			ppi-partitions {
+				ppi_cluster0: interrupt-partition-0 {
+					affinity = <&cpu0 &cpu1 &cpu2 &cpu3>;
+				};
+
+				ppi_cluster1: interrupt-partition-1 {
+					affinity = <&cpu4 &cpu5>;
+				};
+
+				ppi_cluster2: interrupt-partition-2 {
+					affinity = <&cpu6 &cpu7>;
+				};
+			};
+		};
+
+		sysreg_peric0: syscon@10820000 {
+			compatible = "google,gs101-peric0-sysreg", "syscon";
+			reg = <0x10820000 0x10000>;
+		};
+
+		pinctrl_peric0: pinctrl@10840000 {
+			compatible = "google,gs101-pinctrl";
+			reg = <0x10840000 0x00001000>;
+			interrupts = <GIC_SPI 625 IRQ_TYPE_LEVEL_HIGH 0>;
+		};
+
+		usi_uart: usi@10a000c0 {
+			compatible = "google,gs101-usi",
+				     "samsung,exynos850-usi";
+			reg = <0x10a000c0 0x20>;
+			ranges;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			clocks = <&dummy_clk>, <&dummy_clk>;
+			clock-names = "pclk", "ipclk";
+			samsung,sysreg = <&sysreg_peric0 0x1020>;
+			samsung,mode = <USI_V2_UART>;
+			status = "disabled";
+
+			serial_0: serial@10a00000 {
+				compatible = "google,gs101-uart";
+				reg = <0x10a00000 0xc0>;
+				reg-io-width = <4>;
+				interrupts = <GIC_SPI 634
+					      IRQ_TYPE_LEVEL_HIGH 0>;
+				clocks = <&dummy_clk 0>, <&dummy_clk 0>;
+				clock-names = "uart", "clk_uart_baud0";
+				samsung,uart-fifosize = <256>;
+				status = "disabled";
+			};
+		};
+
+		sysreg_peric1: syscon@10c20000 {
+			compatible = "google,gs101-peric1-sysreg", "syscon";
+			reg = <0x10c20000 0x10000>;
+		};
+
+		pinctrl_peric1: pinctrl@10c40000 {
+			compatible = "google,gs101-pinctrl";
+			reg = <0x10c40000 0x00001000>;
+			interrupts = <GIC_SPI 644 IRQ_TYPE_LEVEL_HIGH 0>;
+		};
+
+		pinctrl_hsi1: pinctrl@11840000 {
+			compatible = "google,gs101-pinctrl";
+			reg = <0x11840000 0x00001000>;
+			interrupts = <GIC_SPI 471 IRQ_TYPE_LEVEL_HIGH 0>;
+		};
+
+		pinctrl_hsi2: pinctrl@14440000 {
+			compatible = "google,gs101-pinctrl";
+			reg = <0x14440000 0x00001000>;
+			interrupts = <GIC_SPI 503 IRQ_TYPE_LEVEL_HIGH 0>;
+		};
+
+		cmu_apm: clock-controller@17400000 {
+			compatible = "google,gs101-cmu-apm";
+			reg = <0x17400000 0x8000>;
+			#clock-cells = <1>;
+
+			clocks = <&ext_24_5m>;
+			clock-names = "oscclk";
+		};
+
+		sysreg_apm: syscon@174204e0 {
+			compatible = "google,gs101-apm-sysreg", "syscon";
+			reg = <0x174204e0 0x1000>;
+		};
+
+		pmu_system_controller: system-controller@17460000 {
+			compatible = "google,gs101-pmu", "syscon";
+			reg = <0x17460000 0x10000>;
+		};
+
+		pinctrl_gpio_alive: pinctrl@174d0000 {
+			compatible = "google,gs101-pinctrl";
+			reg = <0x174d0000 0x00001000>;
+
+			wakeup-interrupt-controller {
+				compatible = "google,gs101-wakeup-eint",
+					     "samsung,exynos850-wakeup-eint",
+					     "samsung,exynos7-wakeup-eint";
+			};
+		};
+
+		pinctrl_far_alive: pinctrl@174e0000 {
+			compatible = "google,gs101-pinctrl";
+			reg = <0x174e0000 0x00001000>;
+
+			wakeup-interrupt-controller {
+				compatible = "google,gs101-wakeup-eint",
+					     "samsung,exynos850-wakeup-eint",
+					     "samsung,exynos7-wakeup-eint";
+			};
+		};
+
+		pinctrl_gsactrl: pinctrl@17940000 {
+			compatible = "google,gs101-pinctrl";
+			reg = <0x17940000 0x00001000>;
+		};
+
+		pinctrl_gsacore: pinctrl@17a80000 {
+			compatible = "google,gs101-pinctrl";
+			reg = <0x17a80000 0x00001000>;
+		};
+
+		cmu_top: clock-controller@1e080000 {
+			compatible = "google,gs101-cmu-top";
+			reg = <0x1e080000 0x8000>;
+			#clock-cells = <1>;
+
+			clocks = <&ext_24_5m>;
+			clock-names = "oscclk";
+		};
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts =
+		   <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW) 0>,
+		   <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW) 0>,
+		   <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW) 0>,
+		   <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW) 0>;
+	};
+};
+
+#include "gs101-pinctrl.dtsi"
diff --git a/arch/arm64/boot/dts/freescale/Makefile b/arch/arm64/boot/dts/freescale/Makefile
index 300049037eb0..2e027675d7bb 100644
--- a/arch/arm64/boot/dts/freescale/Makefile
+++ b/arch/arm64/boot/dts/freescale/Makefile
@@ -53,6 +53,32 @@ dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1028a-qds-85bb.dtb
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1028a-qds-899b.dtb
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1028a-qds-9999.dtb
 
+fsl-lx2160a-tqmlx2160a-mblx2160a-12-11-x-dtbs := fsl-lx2160a-tqmlx2160a-mblx2160a.dtb \
+	fsl-lx2160a-tqmlx2160a-mblx2160a_12_x_x.dtbo \
+	fsl-lx2160a-tqmlx2160a-mblx2160a_x_11_x.dtbo
+fsl-lx2160a-tqmlx2160a-mblx2160a-12-7-x-dtbs := fsl-lx2160a-tqmlx2160a-mblx2160a.dtb \
+	fsl-lx2160a-tqmlx2160a-mblx2160a_12_x_x.dtbo \
+	fsl-lx2160a-tqmlx2160a-mblx2160a_x_7_x.dtbo
+fsl-lx2160a-tqmlx2160a-mblx2160a-12-8-x-dtbs := fsl-lx2160a-tqmlx2160a-mblx2160a.dtb \
+	fsl-lx2160a-tqmlx2160a-mblx2160a_12_x_x.dtbo \
+	fsl-lx2160a-tqmlx2160a-mblx2160a_x_8_x.dtbo
+fsl-lx2160a-tqmlx2160a-mblx2160a-14-7-x-dtbs := fsl-lx2160a-tqmlx2160a-mblx2160a.dtb \
+	fsl-lx2160a-tqmlx2160a-mblx2160a_14_x_x.dtbo \
+	fsl-lx2160a-tqmlx2160a-mblx2160a_x_7_x.dtbo
+fsl-lx2160a-tqmlx2160a-mblx2160a-14-8-x-dtbs := fsl-lx2160a-tqmlx2160a-mblx2160a.dtb \
+	fsl-lx2160a-tqmlx2160a-mblx2160a_14_x_x.dtbo \
+	fsl-lx2160a-tqmlx2160a-mblx2160a_x_8_x.dtbo
+fsl-lx2160a-tqmlx2160a-mblx2160a-14-11-x-dtbs := fsl-lx2160a-tqmlx2160a-mblx2160a.dtb \
+	fsl-lx2160a-tqmlx2160a-mblx2160a_14_x_x.dtbo \
+	fsl-lx2160a-tqmlx2160a-mblx2160a_x_11_x.dtbo
+
+dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-tqmlx2160a-mblx2160a-12-11-x.dtb
+dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-tqmlx2160a-mblx2160a-12-8-x.dtb
+dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-tqmlx2160a-mblx2160a-12-7-x.dtb
+dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-tqmlx2160a-mblx2160a-14-11-x.dtb
+dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-tqmlx2160a-mblx2160a-14-8-x.dtb
+dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-tqmlx2160a-mblx2160a-14-7-x.dtb
+
 dtb-$(CONFIG_ARCH_MXC) += imx8dxl-evk.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mm-beacon-kit.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mm-data-modul-edm-sbc.dtb
@@ -84,9 +110,11 @@ dtb-$(CONFIG_ARCH_MXC) += imx8mm-venice-gw7904.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mm-venice-gw7905-0x.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mm-verdin-nonwifi-dahlia.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mm-verdin-nonwifi-dev.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8mm-verdin-nonwifi-mallow.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mm-verdin-nonwifi-yavia.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mm-verdin-wifi-dahlia.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mm-verdin-wifi-dev.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8mm-verdin-wifi-mallow.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mm-verdin-wifi-yavia.dtb
 
 imx8mm-tqma8mqml-mba8mx-lvds-tm070jvhg33-dtbs += imx8mm-tqma8mqml-mba8mx.dtb imx8mm-tqma8mqml-mba8mx-lvds-tm070jvhg33.dtbo
@@ -95,9 +123,11 @@ dtb-$(CONFIG_ARCH_MXC) += imx8mm-tqma8mqml-mba8mx-lvds-tm070jvhg33.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mn-beacon-kit.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mn-bsh-smm-s2.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mn-bsh-smm-s2pro.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8mn-dimonoff-gateway-evk.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mn-evk.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mn-ddr3l-evk.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mn-ddr4-evk.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8mn-rve-gateway.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mn-tqma8mqnl-mba8mx.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mn-var-som-symphony.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mn-venice-gw7902.dtb
@@ -115,6 +145,9 @@ dtb-$(CONFIG_ARCH_MXC) += imx8mp-evk.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-icore-mx8mp-edimm2.2.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-msc-sm2s-ep1.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-phyboard-pollux-rdk.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8mp-skov-revb-hdmi.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8mp-skov-revb-lt6.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8mp-skov-revb-mi1010ait-1cp1.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-tqma8mpql-mba8mpxl.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-venice-gw71xx-2x.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-venice-gw72xx-2x.dtb
@@ -123,13 +156,17 @@ dtb-$(CONFIG_ARCH_MXC) += imx8mp-venice-gw74xx.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-venice-gw7905-2x.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-verdin-nonwifi-dahlia.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-verdin-nonwifi-dev.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8mp-verdin-nonwifi-mallow.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-verdin-nonwifi-yavia.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-verdin-wifi-dahlia.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-verdin-wifi-dev.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8mp-verdin-wifi-mallow.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-verdin-wifi-yavia.dtb
 
 imx8mp-tqma8mpql-mba8mpxl-lvds-dtbs += imx8mp-tqma8mpql-mba8mpxl.dtb imx8mp-tqma8mpql-mba8mpxl-lvds.dtbo
+imx8mp-tqma8mpql-mba8mpxl-lvds-g133han01-dtbs += imx8mp-tqma8mpql-mba8mpxl.dtb imx8mp-tqma8mpql-mba8mpxl-lvds-g133han01.dtbo
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-tqma8mpql-mba8mpxl-lvds.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8mp-tqma8mpql-mba8mpxl-lvds-g133han01.dtb
 
 dtb-$(CONFIG_ARCH_MXC) += imx8mq-evk.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mq-hummingboard-pulse.dtb
@@ -164,6 +201,7 @@ dtb-$(CONFIG_ARCH_MXC) += imx8qxp-colibri-iris-v2.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8qxp-mek.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8ulp-evk.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx93-11x11-evk.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx93-tqma9352-mba93xxca.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx93-tqma9352-mba93xxla.dtb
 
 imx8mm-venice-gw72xx-0x-imx219-dtbs	:= imx8mm-venice-gw72xx-0x.dtb imx8mm-venice-gw72xx-0x-imx219.dtbo
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi
index a863022529ac..1e3fe3897b52 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi
@@ -307,46 +307,46 @@
 			reg = <0x0 0x1f00000 0x0 0x10000>;
 			interrupts = <0 33 0x4>;
 			fsl,tmu-range = <0xb0000 0x9002a 0x6004c 0x60062>;
-			fsl,tmu-calibration = <0x00000000 0x00000025
-					       0x00000001 0x0000002c
-					       0x00000002 0x00000032
-					       0x00000003 0x00000039
-					       0x00000004 0x0000003f
-					       0x00000005 0x00000046
-					       0x00000006 0x0000004c
-					       0x00000007 0x00000053
-					       0x00000008 0x00000059
-					       0x00000009 0x0000005f
-					       0x0000000a 0x00000066
-					       0x0000000b 0x0000006c
-
-					       0x00010000 0x00000026
-					       0x00010001 0x0000002d
-					       0x00010002 0x00000035
-					       0x00010003 0x0000003d
-					       0x00010004 0x00000045
-					       0x00010005 0x0000004d
-					       0x00010006 0x00000055
-					       0x00010007 0x0000005d
-					       0x00010008 0x00000065
-					       0x00010009 0x0000006d
-
-					       0x00020000 0x00000026
-					       0x00020001 0x00000030
-					       0x00020002 0x0000003a
-					       0x00020003 0x00000044
-					       0x00020004 0x0000004e
-					       0x00020005 0x00000059
-					       0x00020006 0x00000063
-
-					       0x00030000 0x00000014
-					       0x00030001 0x00000021
-					       0x00030002 0x0000002e
-					       0x00030003 0x0000003a
-					       0x00030004 0x00000047
-					       0x00030005 0x00000053
-					       0x00030006 0x00000060>;
-			big-endian;
+			fsl,tmu-calibration =
+					<0x00000000 0x00000025>,
+					<0x00000001 0x0000002c>,
+					<0x00000002 0x00000032>,
+					<0x00000003 0x00000039>,
+					<0x00000004 0x0000003f>,
+					<0x00000005 0x00000046>,
+					<0x00000006 0x0000004c>,
+					<0x00000007 0x00000053>,
+					<0x00000008 0x00000059>,
+					<0x00000009 0x0000005f>,
+					<0x0000000a 0x00000066>,
+					<0x0000000b 0x0000006c>,
+
+					<0x00010000 0x00000026>,
+					<0x00010001 0x0000002d>,
+					<0x00010002 0x00000035>,
+					<0x00010003 0x0000003d>,
+					<0x00010004 0x00000045>,
+					<0x00010005 0x0000004d>,
+					<0x00010006 0x00000055>,
+					<0x00010007 0x0000005d>,
+					<0x00010008 0x00000065>,
+					<0x00010009 0x0000006d>,
+
+					<0x00020000 0x00000026>,
+					<0x00020001 0x00000030>,
+					<0x00020002 0x0000003a>,
+					<0x00020003 0x00000044>,
+					<0x00020004 0x0000004e>,
+					<0x00020005 0x00000059>,
+					<0x00020006 0x00000063>,
+
+					<0x00030000 0x00000014>,
+					<0x00030001 0x00000021>,
+					<0x00030002 0x0000002e>,
+					<0x00030003 0x0000003a>,
+					<0x00030004 0x00000047>,
+					<0x00030005 0x00000053>,
+					<0x00030006 0x00000060>;
 			#thermal-sensor-cells = <1>;
 		};
 
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
index eefe3577d94e..ae534c23b970 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
@@ -1026,49 +1026,50 @@
 			reg = <0x0 0x1f80000 0x0 0x10000>;
 			interrupts = <0 23 0x4>;
 			fsl,tmu-range = <0xb0000 0xa0026 0x80048 0x70061>;
-			fsl,tmu-calibration = <0x00000000 0x00000024
-					       0x00000001 0x0000002b
-					       0x00000002 0x00000031
-					       0x00000003 0x00000038
-					       0x00000004 0x0000003f
-					       0x00000005 0x00000045
-					       0x00000006 0x0000004c
-					       0x00000007 0x00000053
-					       0x00000008 0x00000059
-					       0x00000009 0x00000060
-					       0x0000000a 0x00000066
-					       0x0000000b 0x0000006d
-
-					       0x00010000 0x0000001c
-					       0x00010001 0x00000024
-					       0x00010002 0x0000002c
-					       0x00010003 0x00000035
-					       0x00010004 0x0000003d
-					       0x00010005 0x00000045
-					       0x00010006 0x0000004d
-					       0x00010007 0x00000055
-					       0x00010008 0x0000005e
-					       0x00010009 0x00000066
-					       0x0001000a 0x0000006e
-
-					       0x00020000 0x00000018
-					       0x00020001 0x00000022
-					       0x00020002 0x0000002d
-					       0x00020003 0x00000038
-					       0x00020004 0x00000043
-					       0x00020005 0x0000004d
-					       0x00020006 0x00000058
-					       0x00020007 0x00000063
-					       0x00020008 0x0000006e
-
-					       0x00030000 0x00000010
-					       0x00030001 0x0000001c
-					       0x00030002 0x00000029
-					       0x00030003 0x00000036
-					       0x00030004 0x00000042
-					       0x00030005 0x0000004f
-					       0x00030006 0x0000005b
-					       0x00030007 0x00000068>;
+			fsl,tmu-calibration =
+					<0x00000000 0x00000024>,
+					<0x00000001 0x0000002b>,
+					<0x00000002 0x00000031>,
+					<0x00000003 0x00000038>,
+					<0x00000004 0x0000003f>,
+					<0x00000005 0x00000045>,
+					<0x00000006 0x0000004c>,
+					<0x00000007 0x00000053>,
+					<0x00000008 0x00000059>,
+					<0x00000009 0x00000060>,
+					<0x0000000a 0x00000066>,
+					<0x0000000b 0x0000006d>,
+
+					<0x00010000 0x0000001c>,
+					<0x00010001 0x00000024>,
+					<0x00010002 0x0000002c>,
+					<0x00010003 0x00000035>,
+					<0x00010004 0x0000003d>,
+					<0x00010005 0x00000045>,
+					<0x00010006 0x0000004d>,
+					<0x00010007 0x00000055>,
+					<0x00010008 0x0000005e>,
+					<0x00010009 0x00000066>,
+					<0x0001000a 0x0000006e>,
+
+					<0x00020000 0x00000018>,
+					<0x00020001 0x00000022>,
+					<0x00020002 0x0000002d>,
+					<0x00020003 0x00000038>,
+					<0x00020004 0x00000043>,
+					<0x00020005 0x0000004d>,
+					<0x00020006 0x00000058>,
+					<0x00020007 0x00000063>,
+					<0x00020008 0x0000006e>,
+
+					<0x00030000 0x00000010>,
+					<0x00030001 0x0000001c>,
+					<0x00030002 0x00000029>,
+					<0x00030003 0x00000036>,
+					<0x00030004 0x00000042>,
+					<0x00030005 0x0000004f>,
+					<0x00030006 0x0000005b>,
+					<0x00030007 0x00000068>;
 			little-endian;
 			#thermal-sensor-cells = <1>;
 		};
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
index 229bb4bebe42..d333b773bc45 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
@@ -447,46 +447,47 @@
 			reg = <0x0 0x1f00000 0x0 0x10000>;
 			interrupts = <0 33 0x4>;
 			fsl,tmu-range = <0xb0000 0x9002a 0x6004c 0x70062>;
-			fsl,tmu-calibration = <0x00000000 0x00000023
-					       0x00000001 0x0000002a
-					       0x00000002 0x00000031
-					       0x00000003 0x00000037
-					       0x00000004 0x0000003e
-					       0x00000005 0x00000044
-					       0x00000006 0x0000004b
-					       0x00000007 0x00000051
-					       0x00000008 0x00000058
-					       0x00000009 0x0000005e
-					       0x0000000a 0x00000065
-					       0x0000000b 0x0000006b
-
-					       0x00010000 0x00000023
-					       0x00010001 0x0000002b
-					       0x00010002 0x00000033
-					       0x00010003 0x0000003b
-					       0x00010004 0x00000043
-					       0x00010005 0x0000004b
-					       0x00010006 0x00000054
-					       0x00010007 0x0000005c
-					       0x00010008 0x00000064
-					       0x00010009 0x0000006c
-
-					       0x00020000 0x00000021
-					       0x00020001 0x0000002c
-					       0x00020002 0x00000036
-					       0x00020003 0x00000040
-					       0x00020004 0x0000004b
-					       0x00020005 0x00000055
-					       0x00020006 0x0000005f
-
-					       0x00030000 0x00000013
-					       0x00030001 0x0000001d
-					       0x00030002 0x00000028
-					       0x00030003 0x00000032
-					       0x00030004 0x0000003d
-					       0x00030005 0x00000047
-					       0x00030006 0x00000052
-					       0x00030007 0x0000005c>;
+			fsl,tmu-calibration =
+					<0x00000000 0x00000023>,
+					<0x00000001 0x0000002a>,
+					<0x00000002 0x00000031>,
+					<0x00000003 0x00000037>,
+					<0x00000004 0x0000003e>,
+					<0x00000005 0x00000044>,
+					<0x00000006 0x0000004b>,
+					<0x00000007 0x00000051>,
+					<0x00000008 0x00000058>,
+					<0x00000009 0x0000005e>,
+					<0x0000000a 0x00000065>,
+					<0x0000000b 0x0000006b>,
+
+					<0x00010000 0x00000023>,
+					<0x00010001 0x0000002b>,
+					<0x00010002 0x00000033>,
+					<0x00010003 0x0000003b>,
+					<0x00010004 0x00000043>,
+					<0x00010005 0x0000004b>,
+					<0x00010006 0x00000054>,
+					<0x00010007 0x0000005c>,
+					<0x00010008 0x00000064>,
+					<0x00010009 0x0000006c>,
+
+					<0x00020000 0x00000021>,
+					<0x00020001 0x0000002c>,
+					<0x00020002 0x00000036>,
+					<0x00020003 0x00000040>,
+					<0x00020004 0x0000004b>,
+					<0x00020005 0x00000055>,
+					<0x00020006 0x0000005f>,
+
+					<0x00030000 0x00000013>,
+					<0x00030001 0x0000001d>,
+					<0x00030002 0x00000028>,
+					<0x00030003 0x00000032>,
+					<0x00030004 0x0000003d>,
+					<0x00030005 0x00000047>,
+					<0x00030006 0x00000052>,
+					<0x00030007 0x0000005c>;
 			#thermal-sensor-cells = <1>;
 		};
 
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
index 50f68ca5a9af..1515cec23147 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
@@ -445,46 +445,46 @@
 			fsl,tmu-range = <0xb0000 0x9002a 0x6004c 0x70062>;
 			fsl,tmu-calibration =
 				/* Calibration data group 1 */
-				<0x00000000 0x00000023
-				0x00000001 0x00000029
-				0x00000002 0x0000002f
-				0x00000003 0x00000036
-				0x00000004 0x0000003c
-				0x00000005 0x00000042
-				0x00000006 0x00000049
-				0x00000007 0x0000004f
-				0x00000008 0x00000055
-				0x00000009 0x0000005c
-				0x0000000a 0x00000062
-				0x0000000b 0x00000068
+				<0x00000000 0x00000023>,
+				<0x00000001 0x00000029>,
+				<0x00000002 0x0000002f>,
+				<0x00000003 0x00000036>,
+				<0x00000004 0x0000003c>,
+				<0x00000005 0x00000042>,
+				<0x00000006 0x00000049>,
+				<0x00000007 0x0000004f>,
+				<0x00000008 0x00000055>,
+				<0x00000009 0x0000005c>,
+				<0x0000000a 0x00000062>,
+				<0x0000000b 0x00000068>,
 				/* Calibration data group 2 */
-				0x00010000 0x00000022
-				0x00010001 0x0000002a
-				0x00010002 0x00000032
-				0x00010003 0x0000003a
-				0x00010004 0x00000042
-				0x00010005 0x0000004a
-				0x00010006 0x00000052
-				0x00010007 0x0000005a
-				0x00010008 0x00000062
-				0x00010009 0x0000006a
+				<0x00010000 0x00000022>,
+				<0x00010001 0x0000002a>,
+				<0x00010002 0x00000032>,
+				<0x00010003 0x0000003a>,
+				<0x00010004 0x00000042>,
+				<0x00010005 0x0000004a>,
+				<0x00010006 0x00000052>,
+				<0x00010007 0x0000005a>,
+				<0x00010008 0x00000062>,
+				<0x00010009 0x0000006a>,
 				/* Calibration data group 3 */
-				0x00020000 0x00000021
-				0x00020001 0x0000002b
-				0x00020002 0x00000035
-				0x00020003 0x0000003e
-				0x00020004 0x00000048
-				0x00020005 0x00000052
-				0x00020006 0x0000005c
+				<0x00020000 0x00000021>,
+				<0x00020001 0x0000002b>,
+				<0x00020002 0x00000035>,
+				<0x00020003 0x0000003e>,
+				<0x00020004 0x00000048>,
+				<0x00020005 0x00000052>,
+				<0x00020006 0x0000005c>,
 				/* Calibration data group 4 */
-				0x00030000 0x00000011
-				0x00030001 0x0000001a
-				0x00030002 0x00000024
-				0x00030003 0x0000002e
-				0x00030004 0x00000038
-				0x00030005 0x00000042
-				0x00030006 0x0000004c
-				0x00030007 0x00000056>;
+				<0x00030000 0x00000011>,
+				<0x00030001 0x0000001a>,
+				<0x00030002 0x00000024>,
+				<0x00030003 0x0000002e>,
+				<0x00030004 0x00000038>,
+				<0x00030005 0x00000042>,
+				<0x00030006 0x0000004c>,
+				<0x00030007 0x00000056>;
 			big-endian;
 			#thermal-sensor-cells = <1>;
 		};
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
index 8f6090a9aef2..8616d5e0c388 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
@@ -284,46 +284,46 @@
 			fsl,tmu-range = <0xb0000 0x9002a 0x6004c 0x70062>;
 			fsl,tmu-calibration =
 				/* Calibration data group 1 */
-				<0x00000000 0x00000023
-				0x00000001 0x0000002a
-				0x00000002 0x00000030
-				0x00000003 0x00000037
-				0x00000004 0x0000003d
-				0x00000005 0x00000044
-				0x00000006 0x0000004a
-				0x00000007 0x00000051
-				0x00000008 0x00000057
-				0x00000009 0x0000005e
-				0x0000000a 0x00000064
-				0x0000000b 0x0000006b
+				<0x00000000 0x00000023>,
+				<0x00000001 0x0000002a>,
+				<0x00000002 0x00000030>,
+				<0x00000003 0x00000037>,
+				<0x00000004 0x0000003d>,
+				<0x00000005 0x00000044>,
+				<0x00000006 0x0000004a>,
+				<0x00000007 0x00000051>,
+				<0x00000008 0x00000057>,
+				<0x00000009 0x0000005e>,
+				<0x0000000a 0x00000064>,
+				<0x0000000b 0x0000006b>,
 				/* Calibration data group 2 */
-				0x00010000 0x00000022
-				0x00010001 0x0000002a
-				0x00010002 0x00000032
-				0x00010003 0x0000003a
-				0x00010004 0x00000042
-				0x00010005 0x0000004a
-				0x00010006 0x00000052
-				0x00010007 0x0000005a
-				0x00010008 0x00000062
-				0x00010009 0x0000006a
+				<0x00010000 0x00000022>,
+				<0x00010001 0x0000002a>,
+				<0x00010002 0x00000032>,
+				<0x00010003 0x0000003a>,
+				<0x00010004 0x00000042>,
+				<0x00010005 0x0000004a>,
+				<0x00010006 0x00000052>,
+				<0x00010007 0x0000005a>,
+				<0x00010008 0x00000062>,
+				<0x00010009 0x0000006a>,
 				/* Calibration data group 3 */
-				0x00020000 0x00000021
-				0x00020001 0x0000002b
-				0x00020002 0x00000035
-				0x00020003 0x00000040
-				0x00020004 0x0000004a
-				0x00020005 0x00000054
-				0x00020006 0x0000005e
+				<0x00020000 0x00000021>,
+				<0x00020001 0x0000002b>,
+				<0x00020002 0x00000035>,
+				<0x00020003 0x00000040>,
+				<0x00020004 0x0000004a>,
+				<0x00020005 0x00000054>,
+				<0x00020006 0x0000005e>,
 				/* Calibration data group 4 */
-				0x00030000 0x00000010
-				0x00030001 0x0000001c
-				0x00030002 0x00000027
-				0x00030003 0x00000032
-				0x00030004 0x0000003e
-				0x00030005 0x00000049
-				0x00030006 0x00000054
-				0x00030007 0x00000060>;
+				<0x00030000 0x00000010>,
+				<0x00030001 0x0000001c>,
+				<0x00030002 0x00000027>,
+				<0x00030003 0x00000032>,
+				<0x00030004 0x0000003e>,
+				<0x00030005 0x00000049>,
+				<0x00030006 0x00000054>,
+				<0x00030007 0x00000060>;
 			little-endian;
 			#thermal-sensor-cells = <1>;
 		};
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
index 717288bbdb8b..0b7292835906 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
@@ -321,42 +321,43 @@
 			reg = <0x0 0x1f80000 0x0 0x10000>;
 			interrupts = <0 23 0x4>;
 			fsl,tmu-range = <0xb0000 0x9002a 0x6004c 0x30062>;
-			fsl,tmu-calibration = <0x00000000 0x00000026
-					       0x00000001 0x0000002d
-					       0x00000002 0x00000032
-					       0x00000003 0x00000039
-					       0x00000004 0x0000003f
-					       0x00000005 0x00000046
-					       0x00000006 0x0000004d
-					       0x00000007 0x00000054
-					       0x00000008 0x0000005a
-					       0x00000009 0x00000061
-					       0x0000000a 0x0000006a
-					       0x0000000b 0x00000071
-
-					       0x00010000 0x00000025
-					       0x00010001 0x0000002c
-					       0x00010002 0x00000035
-					       0x00010003 0x0000003d
-					       0x00010004 0x00000045
-					       0x00010005 0x0000004e
-					       0x00010006 0x00000057
-					       0x00010007 0x00000061
-					       0x00010008 0x0000006b
-					       0x00010009 0x00000076
-
-					       0x00020000 0x00000029
-					       0x00020001 0x00000033
-					       0x00020002 0x0000003d
-					       0x00020003 0x00000049
-					       0x00020004 0x00000056
-					       0x00020005 0x00000061
-					       0x00020006 0x0000006d
-
-					       0x00030000 0x00000021
-					       0x00030001 0x0000002a
-					       0x00030002 0x0000003c
-					       0x00030003 0x0000004e>;
+			fsl,tmu-calibration =
+					<0x00000000 0x00000026>,
+					<0x00000001 0x0000002d>,
+					<0x00000002 0x00000032>,
+					<0x00000003 0x00000039>,
+					<0x00000004 0x0000003f>,
+					<0x00000005 0x00000046>,
+					<0x00000006 0x0000004d>,
+					<0x00000007 0x00000054>,
+					<0x00000008 0x0000005a>,
+					<0x00000009 0x00000061>,
+					<0x0000000a 0x0000006a>,
+					<0x0000000b 0x00000071>,
+
+					<0x00010000 0x00000025>,
+					<0x00010001 0x0000002c>,
+					<0x00010002 0x00000035>,
+					<0x00010003 0x0000003d>,
+					<0x00010004 0x00000045>,
+					<0x00010005 0x0000004e>,
+					<0x00010006 0x00000057>,
+					<0x00010007 0x00000061>,
+					<0x00010008 0x0000006b>,
+					<0x00010009 0x00000076>,
+
+					<0x00020000 0x00000029>,
+					<0x00020001 0x00000033>,
+					<0x00020002 0x0000003d>,
+					<0x00020003 0x00000049>,
+					<0x00020004 0x00000056>,
+					<0x00020005 0x00000061>,
+					<0x00020006 0x0000006d>,
+
+					<0x00030000 0x00000021>,
+					<0x00030001 0x0000002a>,
+					<0x00030002 0x0000003c>,
+					<0x00030003 0x0000004e>;
 			little-endian;
 			#thermal-sensor-cells = <1>;
 		};
diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a-tqmlx2160a-mblx2160a.dts b/arch/arm64/boot/dts/freescale/fsl-lx2160a-tqmlx2160a-mblx2160a.dts
new file mode 100644
index 000000000000..da0f58e26b9a
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a-tqmlx2160a-mblx2160a.dts
@@ -0,0 +1,338 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright (c) 2020-2023 TQ-Systems GmbH <linux@ew.tq-group.com>,
+ * D-82229 Seefeld, Germany.
+ * Author: Gregor Herburger
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/net/ti-dp83867.h>
+
+#include "fsl-lx2160a-tqmlx2160a.dtsi"
+
+/ {
+	model = "TQ Systems GmbH MBLX2160A Starterkit";
+	compatible = "tq,lx2160a-tqmlx2160a-mblx2160a", "tq,lx2160a-tqmlx2160a",
+		     "fsl,lx2160a";
+
+	aliases {
+		mmc0 = &esdhc0;
+		mmc1 = &esdhc1;
+		serial0 = &uart0;
+		serial1 = &uart1;
+		serial2 = &uart2;
+		serial3 = &uart3;
+	};
+
+	chosen {
+		stdout-path = &uart0;
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		button-user1 {
+			label = "button:user1";
+			gpios = <&gpio2 9 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_F1>;
+		};
+
+		button-user2 {
+			label = "button:user2";
+			gpios = <&gpio2 10 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_F2>;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		led-user1 {
+			gpios = <&gpioex1 15 GPIO_ACTIVE_LOW>;
+			color = <LED_COLOR_ID_BLUE>;
+			function = LED_FUNCTION_HEARTBEAT;
+			function-enumerator = <0>;
+			linux,default-trigger = "heartbeat";
+		};
+
+		led-user2 {
+			gpios = <&gpio2 8 GPIO_ACTIVE_LOW>;
+			color = <LED_COLOR_ID_BLUE>;
+			function = LED_FUNCTION_HEARTBEAT;
+			function-enumerator = <1>;
+			linux,default-trigger = "heartbeat";
+		};
+	};
+
+	sfp_xfi1: sfp-xfi1 {
+		compatible = "sff,sfp";
+		i2c-bus = <&xfi1_i2c>;
+		mod-def0-gpios = <&gpioex2 2 GPIO_ACTIVE_LOW>;
+		los-gpios = <&gpioex2 3 GPIO_ACTIVE_HIGH>;
+		tx-fault-gpios = <&gpioex2 0 GPIO_ACTIVE_HIGH>;
+		tx-disable-gpios = <&gpioex2 1 GPIO_ACTIVE_HIGH>;
+		status = "disabled";
+	};
+
+	sfp_xfi2: sfp-xfi2 {
+		compatible = "sff,sfp";
+		i2c-bus = <&xfi2_i2c>;
+		mod-def0-gpios = <&gpioex2 6 GPIO_ACTIVE_LOW>;
+		los-gpios = <&gpioex2 7 GPIO_ACTIVE_HIGH>;
+		tx-fault-gpios = <&gpioex2 4 GPIO_ACTIVE_HIGH>;
+		tx-disable-gpios = <&gpioex2 5 GPIO_ACTIVE_HIGH>;
+		status = "disabled";
+	};
+};
+
+&can0 {
+	status = "okay";
+};
+
+&can1 {
+	status = "okay";
+};
+
+&dpmac17 {
+	phy-handle = <&dp83867_2_3>;
+	phy-connection-type = "rgmii-id";
+};
+
+&dpmac18 {
+	phy-handle = <&dp83867_2_4>;
+	phy-connection-type = "rgmii-id";
+};
+
+&emdio1 {
+	status = "okay";
+
+	dp83867_1_1: ethernet-phy@1 {
+		reg = <1>;
+		ti,clk-output-sel = <DP83867_CLK_O_SEL_OFF>;
+	};
+
+	dp83867_1_2: ethernet-phy@2 {
+		reg = <2>;
+		ti,clk-output-sel = <DP83867_CLK_O_SEL_OFF>;
+	};
+
+	dp83867_1_3: ethernet-phy@3 {
+		reg = <3>;
+		ti,clk-output-sel = <DP83867_CLK_O_SEL_OFF>;
+	};
+
+	dp83867_1_4: ethernet-phy@4 {
+		reg = <4>;
+		ti,clk-output-sel = <DP83867_CLK_O_SEL_OFF>;
+	};
+
+	dp83867_1_5: ethernet-phy@5 {
+		reg = <5>;
+		ti,clk-output-sel = <DP83867_CLK_O_SEL_OFF>;
+	};
+
+	dp83867_1_6: ethernet-phy@6 {
+		reg = <6>;
+		ti,clk-output-sel = <DP83867_CLK_O_SEL_OFF>;
+	};
+};
+
+&emdio2 {
+	status = "okay";
+
+	dp83867_2_1: ethernet-phy@1 {
+		reg = <1>;
+		ti,clk-output-sel = <DP83867_CLK_O_SEL_OFF>;
+	};
+
+	dp83867_2_2: ethernet-phy@2 {
+		reg = <2>;
+		ti,clk-output-sel = <DP83867_CLK_O_SEL_OFF>;
+	};
+
+	dp83867_2_3: ethernet-phy@3 {
+		reg = <3>;
+		ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_25_NS>;
+		ti,tx-internal-delay = <DP83867_RGMIIDCTL_2_25_NS>;
+		ti,clk-output-sel = <DP83867_CLK_O_SEL_OFF>;
+	};
+
+	dp83867_2_4: ethernet-phy@4 {
+		reg = <4>;
+		ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_25_NS>;
+		ti,tx-internal-delay = <DP83867_RGMIIDCTL_2_25_NS>;
+		ti,clk-output-sel = <DP83867_CLK_O_SEL_OFF>;
+	};
+};
+
+&esdhc0 {
+	sd-uhs-sdr104;
+	sd-uhs-sdr50;
+	sd-uhs-sdr25;
+	sd-uhs-sdr12;
+	no-mmc;
+	no-sdio;
+	wp-gpios = <&gpio0 30 GPIO_ACTIVE_LOW>;
+	cd-gpios = <&gpio0 31 GPIO_ACTIVE_LOW>;
+	status = "okay";
+};
+
+&i2c0 {
+	gpioex3: gpio@20 {
+		compatible = "nxp,pca9555";
+		reg = <0x20>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		vcc-supply = <&reg_vcc3v3>;
+	};
+};
+
+&i2c4 {
+	status = "okay";
+
+	mux@70 {
+		compatible = "nxp,pca9544";
+		reg = <0x70>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		vdd-supply = <&reg_vcc3v3>;
+
+		i2c@0 {
+			reg = <0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
+		i2c@1 {
+			reg = <1>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
+		i2c@2 {
+			reg = <2>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			gpioex0: gpio@20 {
+				compatible = "nxp,pca9555";
+				reg = <0x20>;
+				#gpio-cells = <2>;
+				gpio-controller;
+				vcc-supply = <&reg_vcc3v3>;
+			};
+
+			gpioex1: gpio@21 {
+				compatible = "nxp,pca9555";
+				reg = <0x21>;
+				#gpio-cells = <2>;
+				gpio-controller;
+				vcc-supply = <&reg_vcc3v3>;
+			};
+
+			gpioex2: gpio@22 {
+				compatible = "nxp,pca9555";
+				reg = <0x22>;
+				#gpio-cells = <2>;
+				gpio-controller;
+				vcc-supply = <&reg_vcc3v3>;
+			};
+		};
+
+		i2c@3 {
+			reg = <3>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+	};
+};
+
+&i2c5 {
+	status = "okay";
+
+	mux@70 {
+		compatible = "nxp,pca9544";
+		reg = <0x70>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		vdd-supply = <&reg_vcc3v3>;
+
+		i2c@0 {
+			reg = <0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
+		xfi1_i2c: i2c@1 {
+			reg = <1>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
+		xfi2_i2c: i2c@2 {
+			reg = <2>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
+		i2c@3 {
+			reg = <3>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+	};
+};
+
+&pcs_mdio17 {
+	status = "okay";
+};
+
+&pcs_mdio18 {
+	status = "okay";
+};
+
+&uart0 {
+	status = "okay";
+};
+
+&uart1 {
+	status = "okay";
+};
+
+&uart2 {
+	status = "okay";
+};
+
+&uart3 {
+	status = "okay";
+};
+
+&usb0 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+
+	hub_2_0: hub@1 {
+		compatible = "usb451,8142";
+		reg = <1>;
+		peer-hub = <&hub_3_0>;
+		reset-gpios = <&gpioex1 0 GPIO_ACTIVE_LOW>;
+		vcc-supply = <&reg_vcc3v3>;
+	};
+
+	hub_3_0: hub@2 {
+		compatible = "usb451,8140";
+		reg = <2>;
+		peer-hub = <&hub_2_0>;
+		reset-gpios = <&gpioex1 0 GPIO_ACTIVE_LOW>;
+		vcc-supply = <&reg_vcc3v3>;
+	};
+};
+
+&usb1 {
+	dr_mode = "otg";
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a-tqmlx2160a-mblx2160a_12_x_x.dtso b/arch/arm64/boot/dts/freescale/fsl-lx2160a-tqmlx2160a-mblx2160a_12_x_x.dtso
new file mode 100644
index 000000000000..8284a564e20d
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a-tqmlx2160a-mblx2160a_12_x_x.dtso
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright (c) 2020-2023 TQ-Systems GmbH <linux@ew.tq-group.com>,
+ * D-82229 Seefeld, Germany.
+ * Author: Gregor Herburger
+ */
+
+/dts-v1/;
+/plugin/;
+
+&dpmac9 {
+	phy-handle = <&dp83867_2_1>;
+	phy-connection-type = "sgmii";
+	managed = "in-band-status";
+};
+
+&dpmac10 {
+	phy-handle = <&dp83867_2_2>;
+	phy-connection-type = "sgmii";
+	managed = "in-band-status";
+};
+
+&pcs_mdio9 {
+	status = "okay";
+};
+
+&pcs_mdio10 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a-tqmlx2160a-mblx2160a_14_x_x.dtso b/arch/arm64/boot/dts/freescale/fsl-lx2160a-tqmlx2160a-mblx2160a_14_x_x.dtso
new file mode 100644
index 000000000000..636b17a383ed
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a-tqmlx2160a-mblx2160a_14_x_x.dtso
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright (c) 2020-2023 TQ-Systems GmbH <linux@ew.tq-group.com>,
+ * D-82229 Seefeld, Germany.
+ * Author: Gregor Herburger
+ */
+
+/dts-v1/;
+/plugin/;
+
+&dpmac1 {
+	managed = "in-band-status";
+};
+
+&pcs_mdio1 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a-tqmlx2160a-mblx2160a_x_11_x.dtso b/arch/arm64/boot/dts/freescale/fsl-lx2160a-tqmlx2160a-mblx2160a_x_11_x.dtso
new file mode 100644
index 000000000000..6d0c808cd840
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a-tqmlx2160a-mblx2160a_x_11_x.dtso
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright (c) 2020-2023 TQ-Systems GmbH <linux@ew.tq-group.com>,
+ * D-82229 Seefeld, Germany.
+ * Author: Gregor Herburger
+ */
+
+/dts-v1/;
+/plugin/;
+
+&dpmac12 {
+	phy-handle = <&dp83867_1_1>;
+	phy-connection-type = "sgmii";
+	managed = "in-band-status";
+};
+
+&dpmac13 {
+	phy-handle = <&dp83867_1_5>;
+	phy-connection-type = "sgmii";
+	managed = "in-band-status";
+};
+
+&dpmac14 {
+	phy-handle = <&dp83867_1_6>;
+	phy-connection-type = "sgmii";
+	managed = "in-band-status";
+};
+
+&dpmac16 {
+	phy-handle = <&dp83867_1_4>;
+	phy-connection-type = "sgmii";
+	managed = "in-band-status";
+};
+
+&pcs_mdio12 {
+	status = "okay";
+};
+
+&pcs_mdio13 {
+	status = "okay";
+};
+
+&pcs_mdio14 {
+	status = "okay";
+};
+
+&pcs_mdio16 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a-tqmlx2160a-mblx2160a_x_7_x.dtso b/arch/arm64/boot/dts/freescale/fsl-lx2160a-tqmlx2160a-mblx2160a_x_7_x.dtso
new file mode 100644
index 000000000000..db88a86ff69c
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a-tqmlx2160a-mblx2160a_x_7_x.dtso
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright (c) 2020-2023 TQ-Systems GmbH <linux@ew.tq-group.com>,
+ * D-82229 Seefeld, Germany.
+ * Author: Gregor Herburger
+ */
+
+/dts-v1/;
+/plugin/;
+
+&dpmac12 {
+	phy-handle = <&dp83867_1_1>;
+	phy-connection-type = "sgmii";
+	managed = "in-band-status";
+};
+
+&dpmac13 {
+	sfp = <&sfp_xfi1>;
+	managed = "in-band-status";
+};
+
+&dpmac14 {
+	sfp = <&sfp_xfi2>;
+	managed = "in-band-status";
+};
+
+&dpmac16 {
+	phy-handle = <&dp83867_1_4>;
+	phy-connection-type = "sgmii";
+	managed = "in-band-status";
+};
+
+&pcs_mdio12 {
+	status = "okay";
+};
+
+&pcs_mdio13 {
+	status = "okay";
+};
+
+&pcs_mdio14 {
+	status = "okay";
+};
+
+&pcs_mdio16 {
+	status = "okay";
+};
+
+&sfp_xfi1 {
+	status = "okay";
+};
+
+&sfp_xfi2 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a-tqmlx2160a-mblx2160a_x_8_x.dtso b/arch/arm64/boot/dts/freescale/fsl-lx2160a-tqmlx2160a-mblx2160a_x_8_x.dtso
new file mode 100644
index 000000000000..f6dfa76aa0e7
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a-tqmlx2160a-mblx2160a_x_8_x.dtso
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright (c) 2020-2023 TQ-Systems GmbH <linux@ew.tq-group.com>,
+ * D-82229 Seefeld, Germany.
+ * Author: Gregor Herburger
+ */
+
+/dts-v1/;
+/plugin/;
+
+&dpmac13 {
+	sfp = <&sfp_xfi1>;
+	managed = "in-band-status";
+};
+
+&dpmac14 {
+	sfp = <&sfp_xfi2>;
+	managed = "in-band-status";
+};
+
+&pcs_mdio13 {
+	status = "okay";
+};
+
+&pcs_mdio14 {
+	status = "okay";
+};
+
+&sata0 {
+	status = "okay";
+};
+
+&sata1 {
+	status = "okay";
+};
+
+&sata2 {
+	status = "okay";
+};
+
+&sfp_xfi1 {
+	status = "okay";
+};
+
+&sfp_xfi2 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a-tqmlx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a-tqmlx2160a.dtsi
new file mode 100644
index 000000000000..89a4765737b4
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a-tqmlx2160a.dtsi
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright (c) 2020-2023 TQ-Systems GmbH <linux@ew.tq-group.com>,
+ * D-82229 Seefeld, Germany.
+ * Author: Gregor Herburger
+ */
+
+#include "fsl-lx2160a.dtsi"
+
+/ {
+	reg_vcc3v3: regulator-vcc3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "VCC3V3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+	};
+};
+
+
+&emdio1 {
+	status = "okay";
+};
+
+&emdio2 {
+	status = "okay";
+};
+
+&esdhc1 {
+	bus-width = <8>;
+	no-sd;
+	no-sdio;
+	non-removable;
+	mmc-hs200-1_8v;
+	status = "okay";
+};
+
+&fspi {
+	status = "okay";
+
+	flash0: flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		spi-max-frequency = <10000000>;
+		spi-rx-bus-width = <1>;
+		spi-tx-bus-width = <1>;
+
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+		};
+	};
+
+	flash1: flash@1 {
+		compatible = "jedec,spi-nor";
+		reg = <1>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		spi-max-frequency = <10000000>;
+		spi-rx-bus-width = <1>;
+		spi-tx-bus-width = <1>;
+	};
+};
+
+&i2c0 {
+	scl-gpios = <&gpio2 11 GPIO_ACTIVE_HIGH>;
+	status = "okay";
+
+	sensor0: temperature-sensor@1f {
+		compatible = "nxp,se97", "jedec,jc-42.4-temp";
+		reg = <0x1f>;
+	};
+
+	eeprom1: eeprom@57 {
+		compatible = "atmel,24c02";
+		reg = <0x57>;
+		pagesize = <16>;
+		read-only;
+		vcc-supply = <&reg_vcc3v3>;
+	};
+
+	rtc: rtc@51 {
+		compatible = "nxp,pcf85063a";
+		reg = <0x51>;
+		quartz-load-femtofarads = <12500>;
+	};
+
+	eeprom2: eeprom@50 {
+		compatible = "atmel,24c64";
+		reg = <0x50>;
+		pagesize = <32>;
+		vcc-supply = <&reg_vcc3v3>;
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
index f176ca2e244e..6640b49670ae 100644
--- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
@@ -732,9 +732,9 @@
 			fsl,tmu-range = <0x800000e6 0x8001017d>;
 			fsl,tmu-calibration =
 				/* Calibration data group 1 */
-				<0x00000000 0x00000035
+				<0x00000000 0x00000035>,
 				/* Calibration data group 2 */
-				0x00000001 0x00000154>;
+				<0x00000001 0x00000154>;
 			little-endian;
 			#thermal-sensor-cells = <1>;
 		};
diff --git a/arch/arm64/boot/dts/freescale/imx8-apalis-ixora-v1.2.dtsi b/arch/arm64/boot/dts/freescale/imx8-apalis-ixora-v1.2.dtsi
index 72136c436a70..f6654fdcb147 100644
--- a/arch/arm64/boot/dts/freescale/imx8-apalis-ixora-v1.2.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8-apalis-ixora-v1.2.dtsi
@@ -68,6 +68,7 @@
 		gpio = <&lsio_gpio5 22 GPIO_ACTIVE_HIGH>;
 		enable-active-high;
 		regulator-name = "can1_supply";
+		startup-delay-us = <1000>;
 	};
 
 	reg_can2_supply: regulator-can2-supply {
@@ -77,6 +78,7 @@
 		gpio = <&lsio_gpio2 8 GPIO_ACTIVE_HIGH>;
 		enable-active-high;
 		regulator-name = "can2_supply";
+		startup-delay-us = <1000>;
 	};
 
 	reg_usb_host_vbus: regulator-usb-host-vbus {
diff --git a/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi b/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi
index 5ce5fbf2b38e..f69b0c17560a 100644
--- a/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi
@@ -82,12 +82,9 @@
 		pinctrl-0 = <&pinctrl_wifi_pdn>;
 		gpio = <&lsio_gpio1 28 GPIO_ACTIVE_HIGH>;
 		enable-active-high;
+		regulator-always-on;
 		regulator-name = "wifi_pwrdn_fake_regulator";
 		regulator-settling-time-us = <100>;
-
-		regulator-state-mem {
-			regulator-off-in-suspend;
-		};
 	};
 
 	reg_pcie_switch: regulator-pcie-switch {
diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi
index 9d75ce467569..f057c6b21b30 100644
--- a/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi
@@ -24,7 +24,6 @@ audio_subsys: bus@59000000 {
 		compatible = "fsl,imx8qm-edma";
 		reg = <0x591f0000 0x190000>;
 		#dma-cells = <3>;
-		shared-interrupt;
 		dma-channels = <24>;
 		dma-channel-mask = <0x5c0c00>;
 		interrupts = <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH>, /* 0 asrc 0 */
@@ -127,7 +126,6 @@ audio_subsys: bus@59000000 {
 		compatible = "fsl,imx8qm-edma";
 		reg = <0x599f0000 0xc0000>;
 		#dma-cells = <3>;
-		shared-interrupt;
 		dma-channels = <11>;
 		dma-channel-mask = <0xc0>;
 		interrupts = <GIC_SPI 382 IRQ_TYPE_LEVEL_HIGH>, /* 0 asrc 1 */
diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi
index ce66d30a4839..b0bb77150adc 100644
--- a/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi
@@ -149,7 +149,7 @@ dma_subsys: bus@5a000000 {
 		clock-names = "ipg", "per";
 		assigned-clocks = <&clk IMX_SC_R_LCD_0_PWM_0 IMX_SC_PM_CLK_PER>;
 		assigned-clock-rates = <24000000>;
-		#pwm-cells = <2>;
+		#pwm-cells = <3>;
 		power-domains = <&pd IMX_SC_R_LCD_0_PWM_0>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi
index 49ad3413db94..7e510b21bbac 100644
--- a/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi
@@ -29,7 +29,7 @@ lsio_subsys: bus@5d000000 {
 			 <&pwm0_lpcg 1>;
 		assigned-clocks = <&clk IMX_SC_R_PWM_0 IMX_SC_PM_CLK_PER>;
 		assigned-clock-rates = <24000000>;
-		#pwm-cells = <2>;
+		#pwm-cells = <3>;
 		interrupts = <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>;
 		status = "disabled";
 	};
@@ -42,7 +42,7 @@ lsio_subsys: bus@5d000000 {
 			 <&pwm1_lpcg 1>;
 		assigned-clocks = <&clk IMX_SC_R_PWM_1 IMX_SC_PM_CLK_PER>;
 		assigned-clock-rates = <24000000>;
-		#pwm-cells = <2>;
+		#pwm-cells = <3>;
 		interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>;
 		status = "disabled";
 	};
@@ -55,7 +55,7 @@ lsio_subsys: bus@5d000000 {
 			 <&pwm2_lpcg 1>;
 		assigned-clocks = <&clk IMX_SC_R_PWM_2 IMX_SC_PM_CLK_PER>;
 		assigned-clock-rates = <24000000>;
-		#pwm-cells = <2>;
+		#pwm-cells = <3>;
 		interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>;
 		status = "disabled";
 	};
@@ -68,7 +68,7 @@ lsio_subsys: bus@5d000000 {
 			 <&pwm3_lpcg 1>;
 		assigned-clocks = <&clk IMX_SC_R_PWM_3 IMX_SC_PM_CLK_PER>;
 		assigned-clock-rates = <24000000>;
-		#pwm-cells = <2>;
+		#pwm-cells = <3>;
 		interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>;
 		status = "disabled";
 	};
diff --git a/arch/arm64/boot/dts/freescale/imx8dxl-ss-conn.dtsi b/arch/arm64/boot/dts/freescale/imx8dxl-ss-conn.dtsi
index a414df645351..6d13e4fafb76 100644
--- a/arch/arm64/boot/dts/freescale/imx8dxl-ss-conn.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8dxl-ss-conn.dtsi
@@ -13,6 +13,13 @@
 		clock-frequency = <250000000>;
 		clock-output-names = "conn_enet0_root_clk";
 	};
+
+	clk_dummy: clock-dummy {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+		clock-output-names = "clk_dummy";
+	};
 };
 
 &conn_subsys {
@@ -22,7 +29,7 @@
 		interrupt-parent = <&gic>;
 		interrupts = <GIC_SPI 163 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 162 IRQ_TYPE_LEVEL_HIGH>;
-		interrupt-names = "eth_wake_irq", "macirq";
+		interrupt-names = "macirq", "eth_wake_irq";
 		clocks = <&eqos_lpcg IMX_LPCG_CLK_4>,
 			 <&eqos_lpcg IMX_LPCG_CLK_6>,
 			 <&eqos_lpcg IMX_LPCG_CLK_0>,
@@ -53,13 +60,6 @@
 		rx-burst-size-dword = <0x10>;
 		power-domains = <&pd IMX_SC_R_USB_1>;
 		status = "disabled";
-
-		clk_dummy: clock-dummy {
-			compatible = "fixed-clock";
-			#clock-cells = <0>;
-			clock-frequency = <0>;
-			clock-output-names = "clk_dummy";
-		};
 	};
 
 	usbmisc2: usbmisc@5b0e0200 {
diff --git a/arch/arm64/boot/dts/freescale/imx8dxl-ss-ddr.dtsi b/arch/arm64/boot/dts/freescale/imx8dxl-ss-ddr.dtsi
index 550f513708d8..3569abb5bb9b 100644
--- a/arch/arm64/boot/dts/freescale/imx8dxl-ss-ddr.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8dxl-ss-ddr.dtsi
@@ -4,6 +4,6 @@
  */
 
 &ddr_pmu0 {
-	compatible = "fsl,imx8-ddr-pmu";
+	compatible = "fsl,imx8dxl-ddr-pmu", "fsl,imx8-ddr-pmu";
 	interrupts = <GIC_SPI 71 IRQ_TYPE_LEVEL_HIGH>;
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi
index f264102bdb27..62ed64663f49 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi
@@ -3,6 +3,8 @@
  * Copyright 2020 Compass Electronics Group, LLC
  */
 
+#include "imx8mm-overdrive.dtsi"
+
 / {
 	aliases {
 		rtc0 = &rtc;
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-emcon-avari.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-emcon-avari.dtsi
index d897a8527335..44c2cba41a1f 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-emcon-avari.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-emcon-avari.dtsi
@@ -104,7 +104,7 @@
 		compatible = "nxp,pca8574";
 		reg = <0x3a>;
 		gpio-controller;
-		#gpio-cells = <1>;
+		#gpio-cells = <2>;
 	};
 };
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi
index a882c86ec313..b53104ed8919 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi
@@ -367,12 +367,6 @@
 		interrupts = <11 8>;
 		status = "okay";
 
-		port {
-			typec1_dr_sw: endpoint {
-				remote-endpoint = <&usb1_drd_sw>;
-			};
-		};
-
 		typec1_con: connector {
 			compatible = "usb-c-connector";
 			label = "USB-C";
@@ -384,6 +378,12 @@
 				     PDO_VAR(5000, 20000, 3000)>;
 			op-sink-microwatt = <15000000>;
 			self-powered;
+
+			port {
+				typec1_dr_sw: endpoint {
+					remote-endpoint = <&usb1_drd_sw>;
+				};
+			};
 		};
 	};
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-nitrogen-r2.dts b/arch/arm64/boot/dts/freescale/imx8mm-nitrogen-r2.dts
index 0e8f0d7161ad..12fb79d20b29 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-nitrogen-r2.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-nitrogen-r2.dts
@@ -220,7 +220,7 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		i2c3@0 {
+		i2c@0 {
 			reg = <0>;
 			#address-cells = <1>;
 			#size-cells = <0>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-overdrive.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-overdrive.dtsi
new file mode 100644
index 000000000000..b31436b5e9b7
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mm-overdrive.dtsi
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+&gpu_2d {
+	assigned-clocks = <&clk IMX8MM_CLK_GPU2D_CORE>,
+			  <&clk IMX8MM_GPU_PLL_OUT>;
+	assigned-clock-parents = <&clk IMX8MM_GPU_PLL_OUT>;
+	assigned-clock-rates = <0>, <1000000000>;
+};
+
+&gpu_3d {
+	assigned-clocks = <&clk IMX8MM_CLK_GPU3D_CORE>,
+			  <&clk IMX8MM_GPU_PLL_OUT>;
+	assigned-clock-parents = <&clk IMX8MM_GPU_PLL_OUT>;
+	assigned-clock-rates = <0>, <1000000000>;
+};
+
+&vpu_blk_ctrl {
+	assigned-clocks = <&clk IMX8MM_CLK_VPU_G1>,
+			  <&clk IMX8MM_CLK_VPU_G2>,
+			  <&clk IMX8MM_CLK_VPU_H1>,
+			  <&clk IMX8MM_VPU_PLL_OUT>;
+	assigned-clock-parents = <&clk IMX8MM_SYS_PLL3_OUT>,
+				 <&clk IMX8MM_VPU_PLL_OUT>,
+				 <&clk IMX8MM_SYS_PLL3_OUT>;
+	assigned-clock-rates = <750000000>,
+			       <700000000>,
+			       <750000000>,
+			       <700000000>;
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml-mba8mx.dts b/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml-mba8mx.dts
index 156d793a0c97..ea6e8b85169f 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml-mba8mx.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml-mba8mx.dts
@@ -11,6 +11,7 @@
 / {
 	model = "TQ-Systems GmbH i.MX8MM TQMa8MxML on MBa8Mx";
 	compatible = "tq,imx8mm-tqma8mqml-mba8mx", "tq,imx8mm-tqma8mqml", "fsl,imx8mm";
+	chassis-type = "embedded";
 
 	aliases {
 		eeprom0 = &eeprom3;
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi
index 3a0a10e835a2..3f3f2a2c89cd 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi
@@ -84,8 +84,15 @@
 &ecspi2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_spi2>;
-	cs-gpios = <&gpio5 13 GPIO_ACTIVE_LOW>;
+	cs-gpios = <&gpio5 13 GPIO_ACTIVE_LOW>,
+		   <&gpio1 10 GPIO_ACTIVE_LOW>;
 	status = "okay";
+
+	tpm@1 {
+		compatible = "tcg,tpm_tis-spi";
+		reg = <0x1>;
+		spi-max-frequency = <36000000>;
+	};
 };
 
 &gpio1 {
@@ -152,23 +159,30 @@
 
 	pcie@0,0 {
 		reg = <0x0000 0 0 0 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
+		device_type = "pci";
+		#address-cells = <3>;
+		#size-cells = <2>;
+		ranges;
 
-		pcie@1,0 {
+		pcie@0,0 {
 			reg = <0x0000 0 0 0 0>;
-			#address-cells = <1>;
-			#size-cells = <0>;
+			device_type = "pci";
+			#address-cells = <3>;
+			#size-cells = <2>;
+			ranges;
 
-			pcie@2,3 {
+			pcie@3,0 {
 				reg = <0x1800 0 0 0 0>;
-				#address-cells = <1>;
-				#size-cells = <0>;
+				device_type = "pci";
+				#address-cells = <3>;
+				#size-cells = <2>;
+				ranges;
 
-				eth1: pcie@5,0 {
+				eth1: ethernet@0,0 {
 					reg = <0x0000 0 0 0 0>;
-					#address-cells = <1>;
-					#size-cells = <0>;
+					#address-cells = <3>;
+					#size-cells = <2>;
+					ranges;
 
 					local-mac-address = [00 00 00 00 00 00];
 				};
@@ -312,6 +326,7 @@
 			MX8MM_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI	0xd6
 			MX8MM_IOMUXC_ECSPI2_MISO_ECSPI2_MISO	0xd6
 			MX8MM_IOMUXC_ECSPI2_SS0_GPIO5_IO13	0xd6
+			MX8MM_IOMUXC_GPIO1_IO10_GPIO1_IO10	0xd6
 		>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi
index d79fe9f62b95..06fed9376996 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi
@@ -179,23 +179,30 @@
 
 	pcie@0,0 {
 		reg = <0x0000 0 0 0 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
+		device_type = "pci";
+		#address-cells = <3>;
+		#size-cells = <2>;
+		ranges;
 
-		pcie@1,0 {
+		pcie@0,0 {
 			reg = <0x0000 0 0 0 0>;
-			#address-cells = <1>;
-			#size-cells = <0>;
+			device_type = "pci";
+			#address-cells = <3>;
+			#size-cells = <2>;
+			ranges;
 
-			pcie@2,4 {
+			pcie@4,0 {
 				reg = <0x2000 0 0 0 0>;
-				#address-cells = <1>;
-				#size-cells = <0>;
+				device_type = "pci";
+				#address-cells = <3>;
+				#size-cells = <2>;
+				ranges;
 
-				eth1: pcie@6,0 {
+				eth1: ethernet@0,0 {
 					reg = <0x0000 0 0 0 0>;
-					#address-cells = <1>;
-					#size-cells = <0>;
+					#address-cells = <3>;
+					#size-cells = <2>;
+					ranges;
 
 					local-mac-address = [00 00 00 00 00 00];
 				};
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7902.dts b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7902.dts
index 06a394a41d7c..c11260c26d0b 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7902.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7902.dts
@@ -635,13 +635,16 @@
 
 	pcie@0,0 {
 		reg = <0x0000 0 0 0 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
+		device_type = "pci";
+		#address-cells = <3>;
+		#size-cells = <2>;
+		ranges;
 
-		eth1: pcie@1,0 {
+		eth1: ethernet@0,0 {
 			reg = <0x0000 0 0 0 0>;
-			#address-cells = <1>;
-			#size-cells = <0>;
+			#address-cells = <3>;
+			#size-cells = <2>;
+			ranges;
 
 			local-mac-address = [00 00 00 00 00 00];
 		};
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin-mallow.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin-mallow.dtsi
new file mode 100644
index 000000000000..4a0799d63446
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin-mallow.dtsi
@@ -0,0 +1,173 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright 2023 Toradex
+ *
+ * Common dtsi for Verdin IMX8MM SoM on Mallow carrier board
+ *
+ * https://www.toradex.com/computer-on-modules/verdin-arm-family/nxp-imx-8m-mini-nano
+ * https://www.toradex.com/products/carrier-board/mallow-carrier-board
+ */
+
+#include <dt-bindings/leds/common.h>
+
+/ {
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_leds>;
+
+		/* SODIMM 52 - USER_LED_1_RED */
+		led-0 {
+			color = <LED_COLOR_ID_RED>;
+			function = LED_FUNCTION_DEBUG;
+			function-enumerator = <1>;
+			gpios = <&gpio3 0 GPIO_ACTIVE_HIGH>;
+		};
+
+		/* SODIMM 54 - USER_LED_1_GREEN */
+		led-1 {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_DEBUG;
+			function-enumerator = <1>;
+			gpios = <&gpio3 1 GPIO_ACTIVE_HIGH>;
+		};
+
+		/* SODIMM 56 - USER_LED_2_RED */
+		led-2 {
+			color = <LED_COLOR_ID_RED>;
+			function = LED_FUNCTION_DEBUG;
+			function-enumerator = <2>;
+			gpios = <&gpio3 6 GPIO_ACTIVE_HIGH>;
+		};
+
+		/* SODIMM 58 - USER_LED_2_GREEN */
+		led-3 {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_DEBUG;
+			function-enumerator = <2>;
+			gpios = <&gpio3 7 GPIO_ACTIVE_HIGH>;
+		};
+	};
+};
+
+/* Verdin SPI_1 */
+&ecspi2 {
+	pinctrl-0 = <&pinctrl_ecspi2>, <&pinctrl_tpm_cs>;
+	cs-gpios = <&gpio5 13 GPIO_ACTIVE_LOW>, <&gpio3 2 GPIO_ACTIVE_LOW>;
+	status = "okay";
+
+	tpm@1 {
+		compatible = "infineon,slb9670", "tcg,tpm_tis-spi";
+		reg = <1>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_tpm_irq>;
+		interrupt-parent = <&gpio3>;
+		interrupts = <14 IRQ_TYPE_LEVEL_LOW>;
+		spi-max-frequency = <18500000>;
+	};
+};
+
+/* EEPROM on Mallow */
+&eeprom_carrier_board {
+	status = "okay";
+};
+
+/* Verdin ETH_1 */
+&fec1 {
+	status = "okay";
+};
+
+/* Temperature sensor on Mallow */
+&hwmon_temp {
+	compatible = "ti,tmp1075";
+	status = "okay";
+};
+
+/* Verdin I2C_2_DSI */
+&i2c2 {
+	status = "okay";
+};
+
+/* Verdin I2C_4_CSI */
+&i2c3 {
+	status = "okay";
+};
+
+/* Verdin I2C_1 */
+&i2c4 {
+	status = "okay";
+};
+
+/* Verdin PCIE_1 */
+&pcie0 {
+	status = "okay";
+};
+
+&pcie_phy {
+	status = "okay";
+};
+
+/* Verdin PWM_3_DSI */
+&pwm1 {
+	status = "okay";
+};
+
+/* Verdin PWM_1 */
+&pwm2 {
+	status = "okay";
+};
+
+/* Verdin PWM_2 */
+&pwm3 {
+	status = "okay";
+};
+
+/* Verdin UART_3 */
+&uart1 {
+	status = "okay";
+};
+
+/* Verdin UART_1 */
+&uart2 {
+	status = "okay";
+};
+
+/* Verdin UART_2 */
+&uart3 {
+	status = "okay";
+};
+
+/* Verdin USB_1 */
+&usbotg1 {
+	status = "okay";
+};
+
+/* Verdin USB_2 */
+&usbotg2 {
+	status = "okay";
+};
+
+/* Verdin SD_1 */
+&usdhc2 {
+	status = "okay";
+};
+
+&iomuxc {
+	pinctrl_leds: ledsgrp {
+		fsl,pins =
+			<MX8MM_IOMUXC_NAND_ALE_GPIO3_IO0	0x106>, /* SODIMM 52 */
+			<MX8MM_IOMUXC_NAND_CE0_B_GPIO3_IO1	0x106>, /* SODIMM 54 */
+			<MX8MM_IOMUXC_NAND_DATA00_GPIO3_IO6	0x106>, /* SODIMM 56 */
+			<MX8MM_IOMUXC_NAND_DATA01_GPIO3_IO7	0x106>; /* SODIMM 58 */
+	};
+
+	pinctrl_tpm_cs: tpmcsgrp {
+		fsl,pins =
+			<MX8MM_IOMUXC_NAND_CE1_B_GPIO3_IO2	0x146>; /* SODIMM 64 */
+	};
+
+	pinctrl_tpm_irq: tpmirqgrp {
+		fsl,pins =
+			<MX8MM_IOMUXC_NAND_DQS_GPIO3_IO14	0x141>; /* SODIMM 66 */
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin-nonwifi-mallow.dts b/arch/arm64/boot/dts/freescale/imx8mm-verdin-nonwifi-mallow.dts
new file mode 100644
index 000000000000..1b1999f3a80e
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin-nonwifi-mallow.dts
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright 2023 Toradex
+ */
+
+/dts-v1/;
+
+#include "imx8mm-verdin.dtsi"
+#include "imx8mm-verdin-nonwifi.dtsi"
+#include "imx8mm-verdin-mallow.dtsi"
+
+/ {
+	model = "Toradex Verdin iMX8M Mini on Mallow";
+	compatible = "toradex,verdin-imx8mm-nonwifi-mallow",
+		     "toradex,verdin-imx8mm-nonwifi",
+		     "toradex,verdin-imx8mm",
+		     "fsl,imx8mm";
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin-wifi-mallow.dts b/arch/arm64/boot/dts/freescale/imx8mm-verdin-wifi-mallow.dts
new file mode 100644
index 000000000000..2916145f31bb
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin-wifi-mallow.dts
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright 2023 Toradex
+ */
+
+/dts-v1/;
+
+#include "imx8mm-verdin.dtsi"
+#include "imx8mm-verdin-wifi.dtsi"
+#include "imx8mm-verdin-mallow.dtsi"
+
+/ {
+	model = "Toradex Verdin iMX8M Mini WB on Mallow";
+	compatible = "toradex,verdin-imx8mm-wifi-mallow",
+		     "toradex,verdin-imx8mm-wifi",
+		     "toradex,verdin-imx8mm",
+		     "fsl,imx8mm";
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi
index 738024baaa57..8a1b42b94dce 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi
@@ -636,6 +636,8 @@
 			clk: clock-controller@30380000 {
 				compatible = "fsl,imx8mm-ccm";
 				reg = <0x30380000 0x10000>;
+				interrupts = <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
 				#clock-cells = <1>;
 				clocks = <&osc_32k>, <&osc_24m>, <&clk_ext1>, <&clk_ext2>,
 					 <&clk_ext3>, <&clk_ext4>;
@@ -647,7 +649,6 @@
 						<&clk IMX8MM_CLK_AUDIO_AHB>,
 						<&clk IMX8MM_CLK_IPG_AUDIO_ROOT>,
 						<&clk IMX8MM_SYS_PLL3>,
-						<&clk IMX8MM_VIDEO_PLL1>,
 						<&clk IMX8MM_AUDIO_PLL1>;
 				assigned-clock-parents = <&clk IMX8MM_SYS_PLL1_800M>,
 							 <&clk IMX8MM_ARM_PLL_OUT>,
@@ -657,7 +658,6 @@
 							<400000000>,
 							<400000000>,
 							<750000000>,
-							<594000000>,
 							<393216000>;
 			};
 
@@ -1133,7 +1133,7 @@
 				assigned-clock-parents = <&clk IMX8MM_VIDEO_PLL1_OUT>,
 							 <&clk IMX8MM_SYS_PLL2_1000M>,
 							 <&clk IMX8MM_SYS_PLL1_800M>;
-				assigned-clock-rates = <594000000>, <500000000>, <200000000>;
+				assigned-clock-rates = <24000000>, <500000000>, <200000000>;
 				interrupts = <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>;
 				power-domains = <&disp_blk_ctrl IMX8MM_DISPBLK_PD_LCDIF>;
 				status = "disabled";
@@ -1151,12 +1151,8 @@
 				clocks = <&clk IMX8MM_CLK_DSI_CORE>,
 					 <&clk IMX8MM_CLK_DSI_PHY_REF>;
 				clock-names = "bus_clk", "sclk_mipi";
-				assigned-clocks = <&clk IMX8MM_CLK_DSI_CORE>,
-						  <&clk IMX8MM_CLK_DSI_PHY_REF>;
-				assigned-clock-parents = <&clk IMX8MM_SYS_PLL1_266M>,
-							 <&clk IMX8MM_CLK_24M>;
-				assigned-clock-rates = <266000000>, <24000000>;
-				samsung,pll-clock-frequency = <24000000>;
+				assigned-clocks = <&clk IMX8MM_CLK_DSI_CORE>;
+				assigned-clock-parents = <&clk IMX8MM_SYS_PLL1_266M>;
 				interrupts = <GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH>;
 				power-domains = <&disp_blk_ctrl IMX8MM_DISPBLK_PD_MIPI_DSI>;
 				status = "disabled";
@@ -1408,7 +1404,7 @@
 			assigned-clocks = <&clk IMX8MM_CLK_GPU3D_CORE>,
 					  <&clk IMX8MM_GPU_PLL_OUT>;
 			assigned-clock-parents = <&clk IMX8MM_GPU_PLL_OUT>;
-			assigned-clock-rates = <0>, <1000000000>;
+			assigned-clock-rates = <0>, <800000000>;
 			power-domains = <&pgc_gpu>;
 		};
 
@@ -1423,7 +1419,7 @@
 			assigned-clocks = <&clk IMX8MM_CLK_GPU2D_CORE>,
 					  <&clk IMX8MM_GPU_PLL_OUT>;
 			assigned-clock-parents = <&clk IMX8MM_GPU_PLL_OUT>;
-			assigned-clock-rates = <0>, <1000000000>;
+			assigned-clock-rates = <0>, <800000000>;
 			power-domains = <&pgc_gpu>;
 		};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-beacon-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-beacon-som.dtsi
index 90073b16536f..2a64115eebf1 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-beacon-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mn-beacon-som.dtsi
@@ -3,6 +3,8 @@
  * Copyright 2020 Compass Electronics Group, LLC
  */
 
+#include "imx8mn-overdrive.dtsi"
+
 / {
 	aliases {
 		rtc0 = &rtc;
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-bsh-smm-s2-common.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-bsh-smm-s2-common.dtsi
index 22a754d438f1..bbb07c650da9 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-bsh-smm-s2-common.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mn-bsh-smm-s2-common.dtsi
@@ -7,6 +7,7 @@
 /dts-v1/;
 
 #include "imx8mn.dtsi"
+#include "imx8mn-bsh-smm-s2-display.dtsi"
 
 / {
 	chosen {
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-bsh-smm-s2-display.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-bsh-smm-s2-display.dtsi
new file mode 100644
index 000000000000..7675583a6b67
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mn-bsh-smm-s2-display.dtsi
@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright 2021 BSH
+ */
+
+/ {
+	backlight: backlight {
+		compatible = "pwm-backlight";
+		pwms = <&pwm1 0 700000 0>;	/* 700000 ns = 1337Hz */
+		brightness-levels = <0 100>;
+		num-interpolated-steps = <100>;
+		default-brightness-level = <50>;
+		status = "okay";
+	};
+
+	reg_3v3_dvdd: regulator-3v3-O3 {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_dvdd>;
+		regulator-name = "3v3-dvdd-supply";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio1 7 GPIO_ACTIVE_LOW>;
+	};
+
+	reg_v3v3_avdd: regulator-3v3-O2 {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_avdd>;
+		regulator-name = "3v3-avdd-supply";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio1 5 GPIO_ACTIVE_LOW>;
+	};
+};
+
+&pwm1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_bl>;
+	status = "okay";
+};
+
+&lcdif {
+	assigned-clocks = <&clk IMX8MN_VIDEO_PLL1>;
+	assigned-clock-rates = <594000000>;
+	status = "okay";
+};
+
+&pgc_dispmix {
+	assigned-clocks = <&clk IMX8MN_CLK_DISP_AXI>, <&clk IMX8MN_CLK_DISP_APB>;
+	assigned-clock-parents = <&clk IMX8MN_SYS_PLL2_1000M>, <&clk IMX8MN_SYS_PLL1_800M>;
+	assigned-clock-rates = <500000000>, <200000000>;
+};
+
+&mipi_dsi {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	samsung,esc-clock-frequency = <20000000>;
+	samsung,pll-clock-frequency = <12000000>;
+	status = "okay";
+
+	panel@0 {
+		compatible = "sharp,ls068b3sx02", "syna,r63353";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_panel>;
+		reg = <0>;
+
+		backlight = <&backlight>;
+		dvdd-supply = <&reg_3v3_dvdd>;
+		avdd-supply = <&reg_v3v3_avdd>;
+		reset-gpios = <&gpio4 29 GPIO_ACTIVE_HIGH>;
+
+		port {
+			panel_in: endpoint {
+				remote-endpoint = <&mipi_dsi_out>;
+			};
+		};
+
+	};
+
+	ports {
+		port@1 {
+			reg = <1>;
+
+			mipi_dsi_out: endpoint {
+				remote-endpoint = <&panel_in>;
+			};
+		};
+	};
+};
+
+&gpu {
+	status = "okay";
+};
+
+&iomuxc {
+	pinctrl_avdd: avddgrp {
+		fsl,pins = <
+			MX8MN_IOMUXC_GPIO1_IO05_GPIO1_IO5	0x16	/* VDD 3V3_VO2 */
+		>;
+	};
+
+	/* This is for both PWM and voltage regulators for display */
+	pinctrl_bl: blgrp {
+		fsl,pins = <
+			MX8MN_IOMUXC_GPIO1_IO01_PWM1_OUT	0x16
+		>;
+	};
+
+	pinctrl_dvdd: dvddgrp {
+		fsl,pins = <
+			MX8MN_IOMUXC_GPIO1_IO07_GPIO1_IO7	0x16	/* VDD 3V3_VO3 */
+		>;
+	};
+
+	pinctrl_panel: panelgrp {
+		fsl,pins = <
+			MX8MN_IOMUXC_SAI3_RXC_GPIO4_IO29	0x16	/* panel reset */
+		>;
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-dimonoff-gateway-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-dimonoff-gateway-evk.dts
new file mode 100644
index 000000000000..6f9b82958b96
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mn-dimonoff-gateway-evk.dts
@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright 2022 DimOnOff
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/usb/pd.h>
+#include "imx8mn-var-som-symphony.dts"
+
+/ {
+	model = "DimOnOff Gateway EVK board";
+	compatible = "dimonoff,gateway-evk", "variscite,var-som-mx8mn",
+		     "fsl,imx8mn";
+
+	/*
+	 * U30 FPF2193 regulator.
+	 * Source = BASE_PER_3V3 = SOM_3V3 (COM pin 49).
+	 */
+	reg_disp_3v3: regulator-disp-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "Display 3V3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_gpio_keys>;
+
+		key-enter {
+			label = "enter";
+			gpios = <&gpio1 8 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_ENTER>;
+			wakeup-source;
+		};
+	};
+
+	/* Bourns PEC12R rotary encoder, 24 steps. */
+	rotary: rotary-encoder {
+		compatible = "rotary-encoder";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_rotary>;
+		gpios = <&gpio5 12 GPIO_ACTIVE_LOW>, /* A */
+			<&gpio5 13 GPIO_ACTIVE_LOW>; /* B */
+		linux,axis = <0>; /* REL_X */
+		rotary-encoder,encoding = "gray";
+		rotary-encoder,relative-axis;
+	};
+};
+
+/* Disable Asynchronous Sample Rate Converter (audio) */
+&easrc {
+	status = "disabled";
+};
+
+&ecspi1 {
+	/* Resistive touch controller */
+	/delete-node/ touchscreen@0;
+};
+
+&gpu {
+	status = "disabled";
+};
+
+&i2c2 {
+	adc@48 {
+		compatible = "ti,ads7924";
+		reg = <0x48>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_adc>;
+		vref-supply = <&reg_disp_3v3>;
+		reset-gpios = <&gpio5 5 GPIO_ACTIVE_LOW>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		channel@0 {
+			reg = <0>;
+			label = "Pot0";
+		};
+		channel@1 {
+			reg = <1>;
+			label = "Pot1";
+		};
+		channel@2 {
+			reg = <2>;
+			label = "Pot2";
+		};
+		channel@3 {
+			reg = <3>;
+			label = "Pot3";
+		};
+	};
+
+	rtc@51 {
+		compatible = "nxp,pcf2129";
+		reg = <0x51>;
+		reset-source; /* For watchdog. */
+	};
+
+	rtc@53 {
+		compatible = "nxp,pcf2131";
+		reg = <0x53>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_rtc>;
+		reset-source; /* For watchdog. */
+		interrupt-parent = <&gpio5>;
+		interrupts = <10 IRQ_TYPE_EDGE_FALLING>; /* J17.6 on EVK */
+	};
+};
+
+&i2c3 {
+	touchscreen@38 {
+		status = "disabled";
+	};
+
+	codec@1a {
+		status = "disabled";
+	};
+
+	/* DS1337 RTC module */
+	rtc@68 {
+		status = "disabled";
+	};
+};
+
+&sai5 {
+	status = "disabled";
+};
+
+&iomuxc {
+	pinctrl_gpio_keys: gpiokeysgrp {
+		fsl,pins = <
+			MX8MN_IOMUXC_GPIO1_IO08_GPIO1_IO8	0xc6
+		>;
+	};
+
+	pinctrl_rotary: rotarygrp {
+		fsl,pins = <
+			MX8MN_IOMUXC_ECSPI2_MISO_GPIO5_IO12	0x00000156
+			MX8MN_IOMUXC_ECSPI2_SS0_GPIO5_IO13	0x00000156
+		>;
+	};
+
+	pinctrl_adc: adcgrp {
+		fsl,pins = <
+			MX8MN_IOMUXC_SPDIF_EXT_CLK_GPIO5_IO5	0x00000156
+		>;
+	};
+
+	pinctrl_rtc: rtcgrp {
+		fsl,pins = <
+			MX8MN_IOMUXC_ECSPI2_SCLK_GPIO5_IO10	0x00000156
+			MX8MN_IOMUXC_ECSPI2_MOSI_GPIO5_IO11	0x00000156
+		>;
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-evk.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-evk.dtsi
index 3f6a19839c9e..a0e13d3324ed 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-evk.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mn-evk.dtsi
@@ -221,12 +221,6 @@
 		interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
 		status = "okay";
 
-		port {
-			typec1_dr_sw: endpoint {
-				remote-endpoint = <&usb1_drd_sw>;
-			};
-		};
-
 		typec1_con: connector {
 			compatible = "usb-c-connector";
 			label = "USB-C";
@@ -238,6 +232,12 @@
 				     PDO_VAR(5000, 20000, 3000)>;
 			op-sink-microwatt = <15000000>;
 			self-powered;
+
+			port {
+				typec1_dr_sw: endpoint {
+					remote-endpoint = <&usb1_drd_sw>;
+				};
+			};
 		};
 	};
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-overdrive.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-overdrive.dtsi
new file mode 100644
index 000000000000..5d03fb893e90
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mn-overdrive.dtsi
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+&gpu {
+	assigned-clocks = <&clk IMX8MN_CLK_GPU_CORE>,
+			  <&clk IMX8MN_CLK_GPU_SHADER>,
+			  <&clk IMX8MN_CLK_GPU_AXI>,
+			  <&clk IMX8MN_CLK_GPU_AHB>,
+			  <&clk IMX8MN_GPU_PLL>;
+	assigned-clock-parents = <&clk IMX8MN_GPU_PLL_OUT>,
+				  <&clk IMX8MN_GPU_PLL_OUT>,
+				  <&clk IMX8MN_SYS_PLL1_800M>,
+				  <&clk IMX8MN_SYS_PLL1_800M>;
+	assigned-clock-rates = <600000000>,
+			       <600000000>,
+			       <800000000>,
+			       <400000000>,
+			       <1200000000>;
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-rve-gateway.dts b/arch/arm64/boot/dts/freescale/imx8mn-rve-gateway.dts
new file mode 100644
index 000000000000..1b633bd1ebb6
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mn-rve-gateway.dts
@@ -0,0 +1,285 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright 2023 DimOnOff
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/usb/pd.h>
+#include "imx8mn-var-som.dtsi"
+
+/ {
+	model = "RVE gateway";
+	compatible = "rve,rve-gateway", "variscite,var-som-mx8mn", "fsl,imx8mn";
+
+	crystal_duart_24m: crystal-duart-24m {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <24000000>;
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_gpio_keys>;
+
+		key-enter {
+			label = "enter";
+			gpios = <&gpio1 1 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_ENTER>;
+		};
+
+		key-exit {
+			label = "exit";
+			gpios = <&gpio3 23 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_ESC>;
+		};
+	};
+
+	lcd {
+		compatible = "hit,hd44780";
+		display-height-chars = <2>;
+		display-width-chars = <20>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_lcd>;
+		data-gpios = <&gpio5  1 GPIO_ACTIVE_HIGH>,
+			     <&gpio1  6 GPIO_ACTIVE_HIGH>,
+			     <&gpio1 14 GPIO_ACTIVE_HIGH>,
+			     <&gpio4 28 GPIO_ACTIVE_HIGH>,
+			     <&gpio5 24 GPIO_ACTIVE_HIGH>,
+			     <&gpio5  2 GPIO_ACTIVE_HIGH>,
+			     <&gpio1 12 GPIO_ACTIVE_HIGH>,
+			     <&gpio5 25 GPIO_ACTIVE_HIGH>;
+		enable-gpios = <&gpio5 23 GPIO_ACTIVE_HIGH>;
+		rs-gpios = <&gpio1 7 GPIO_ACTIVE_HIGH>;
+		rw-gpios = <&gpio4 27 GPIO_ACTIVE_HIGH>;
+	};
+
+	reg_3p3v: regulator-3p3v {
+		compatible = "regulator-fixed";
+		regulator-name = "3P3V";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+	};
+
+	/* Bourns PEC12R rotary encoder, 24 steps. */
+	rotary: rotary-encoder {
+		compatible = "rotary-encoder";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_rotary>;
+		gpios = <&gpio1  5 GPIO_ACTIVE_LOW>, /* A */
+			<&gpio3 21 GPIO_ACTIVE_LOW>; /* B */
+		linux,axis = <0>; /* REL_X */
+		rotary-encoder,encoding = "gray";
+		rotary-encoder,relative-axis;
+	};
+};
+
+&ecspi1 {
+	cs-gpios = <&gpio5 9 GPIO_ACTIVE_LOW>;
+
+	duart1: serial@0 {
+		compatible = "nxp,sc16is752";
+		reg = <0>;
+		spi-rx-bus-width = <1>;
+		spi-tx-bus-width = <1>;
+		spi-max-frequency = <4000000>;
+		clocks = <&crystal_duart_24m>;
+		interrupt-parent = <&gpio3>;
+		interrupts = <22 IRQ_TYPE_EDGE_FALLING>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		gpio-line-names = "RADIO0", "RADIO1", "RADIO2", "RADIO3",
+				  "RADIO4", "RADIO_RESET", "TP12", "TP11";
+		linux,rs485-enabled-at-boot-time;
+		rs485-rts-active-low;
+	};
+
+	/delete-node/ touchscreen@0;
+};
+
+&ecspi2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_ecspi2>;
+	cs-gpios = <&gpio5 13 GPIO_ACTIVE_LOW>;
+	/delete-property/ dmas;
+	/delete-property/ dma-names;
+	status = "okay";
+
+	duart2: serial@0 {
+		compatible = "nxp,sc16is752";
+		reg = <0>;
+		spi-rx-bus-width = <1>;
+		spi-tx-bus-width = <1>;
+		spi-max-frequency = <4000000>;
+		clocks = <&crystal_duart_24m>;
+		interrupt-parent = <&gpio3>;
+		interrupts = <20 IRQ_TYPE_EDGE_FALLING>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		gpio-line-names = "LED_B_USER", "LED_R_USER", "LED_G_USER",
+				  "GPIO_EXT3", "GPIO_EXT2", "GPIO_EXT1",
+				  "GPIO_EXT0", "TP13";
+		linux,rs485-enabled-at-boot-time;
+		rs485-rts-active-low;
+	};
+};
+
+/* Configure PWM pins in GPIO mode: */
+&gpio5 {
+	gpio-line-names = "", "", "", "PWM3", "PWM2", "PWM1";
+};
+
+&gpu {
+	status = "disabled";
+};
+
+&i2c2 {
+	clock-frequency = <400000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c2>;
+	status = "okay";
+
+	/* Carrier board EEPROM */
+	eeprom_cb: eeprom@56 {
+		compatible = "atmel,24c04";
+		reg = <0x56>;
+		pagesize = <16>;
+		vcc-supply = <&reg_3p3v>;
+	};
+
+	lm75: sensor@48 {
+		compatible = "st,stlm75";
+		reg = <0x48>;
+		vs-supply = <&reg_3p3v>;
+	};
+
+	mcp7940: rtc@6f {
+		compatible = "microchip,mcp7940x";
+		reg = <0x6f>;
+	};
+};
+
+&i2c3 {
+	codec@1a {
+		status = "disabled";
+	};
+};
+
+&i2c4 {
+	clock-frequency = <400000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c4>;
+	status = "okay";
+
+	pcf8574_1: gpio@38 {
+		compatible = "nxp,pcf8574";
+		reg = <0x38>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		gpio-line-names = "LED_B_COMM3", "LED_R_COMM3", "LED_G_COMM3",
+				  "TP14", "TP15", "LED_G_COMM4", "LED_R_COMM4",
+				  "LED_B_COMM4";
+	};
+
+	pcf8574_2: gpio@39 {
+		compatible = "nxp,pcf8574";
+		reg = <0x39>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		gpio-line-names = "LED_B_COMM2", "LED_G_COMM2", "LED_B_COMM1",
+				  "LED_R_COMM2", "LED_R_COMM1", "LED_G_COMM1",
+				  "TP16", "TP17";
+	};
+};
+
+/* Bluetooth */
+&uart2 {
+	status = "disabled";
+};
+
+&usbotg1 {
+	dr_mode = "host";
+	disable-over-current;
+	status = "okay";
+};
+
+/* SD interface on expansion connector. */
+&usdhc2 {
+	vmmc-supply = <&reg_3p3v>;
+	cd-gpios = <&gpio1 13 GPIO_ACTIVE_LOW>;
+};
+
+&iomuxc {
+	pinctrl_ecspi1: ecspi1grp {
+		fsl,pins = <
+			MX8MN_IOMUXC_ECSPI1_SCLK_ECSPI1_SCLK	0x13
+			MX8MN_IOMUXC_ECSPI1_MOSI_ECSPI1_MOSI	0x13
+			MX8MN_IOMUXC_ECSPI1_MISO_ECSPI1_MISO	0x13
+			MX8MN_IOMUXC_ECSPI1_SS0_GPIO5_IO9	0x13 /* SS0 */
+			MX8MN_IOMUXC_SAI5_RXD1_GPIO3_IO22	0x13 /* SC16 IRQ */
+		>;
+	};
+
+	pinctrl_ecspi2: ecspi2grp {
+		fsl,pins = <
+			MX8MN_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK	0x13
+			MX8MN_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI	0x13
+			MX8MN_IOMUXC_ECSPI2_MISO_ECSPI2_MISO	0x13
+			MX8MN_IOMUXC_ECSPI2_SS0_GPIO5_IO13	0x13 /* SS0 */
+			MX8MN_IOMUXC_SAI5_RXC_GPIO3_IO20	0x13 /* SC16 IRQ */
+		>;
+	};
+
+	pinctrl_gpio_keys: gpiokeysgrp {
+		fsl,pins = <
+			MX8MN_IOMUXC_GPIO1_IO01_GPIO1_IO1	0xc6 /* Enter */
+			MX8MN_IOMUXC_SAI5_RXD2_GPIO3_IO23	0xc6 /* Exit */
+		>;
+	};
+
+	pinctrl_i2c2: i2c2grp {
+		fsl,pins = <
+			MX8MN_IOMUXC_I2C2_SCL_I2C2_SCL		0x400001c3
+			MX8MN_IOMUXC_I2C2_SDA_I2C2_SDA		0x400001c3
+		>;
+	};
+
+	pinctrl_i2c4: i2c4grp {
+		fsl,pins = <
+			MX8MN_IOMUXC_I2C4_SCL_I2C4_SCL		0x400001c3
+			MX8MN_IOMUXC_I2C4_SDA_I2C4_SDA		0x400001c3
+		>;
+	};
+
+	pinctrl_lcd: lcdgrp {
+		fsl,pins = <
+			MX8MN_IOMUXC_SAI3_TXD_GPIO5_IO1		0x00000156 /* D0 */
+			MX8MN_IOMUXC_GPIO1_IO06_GPIO1_IO6	0x00000156 /* D1 */
+			MX8MN_IOMUXC_GPIO1_IO14_GPIO1_IO14	0x00000156 /* D2 */
+			MX8MN_IOMUXC_SAI3_RXFS_GPIO4_IO28	0x00000156 /* D3 */
+			MX8MN_IOMUXC_UART2_RXD_GPIO5_IO24	0x00000156 /* D4 */
+			MX8MN_IOMUXC_SAI3_MCLK_GPIO5_IO2	0x00000156 /* D5 */
+			MX8MN_IOMUXC_GPIO1_IO12_GPIO1_IO12	0x00000156 /* D6 */
+			MX8MN_IOMUXC_UART2_TXD_GPIO5_IO25	0x00000156 /* D7 */
+			MX8MN_IOMUXC_UART1_TXD_GPIO5_IO23	0x00000156 /* E */
+			MX8MN_IOMUXC_GPIO1_IO07_GPIO1_IO7	0x00000156 /* RS */
+			MX8MN_IOMUXC_SAI2_MCLK_GPIO4_IO27	0x00000156 /* R/W */
+		>;
+	};
+
+	pinctrl_rotary: rotarygrp {
+		fsl,pins = <
+			MX8MN_IOMUXC_GPIO1_IO05_GPIO1_IO5	0x00000156 /* A */
+			MX8MN_IOMUXC_SAI5_RXD0_GPIO3_IO21	0x00000156 /* B */
+		>;
+	};
+
+	/* Override Card Detect function GPIO value (GPIO1_IO10) from SOM: */
+	pinctrl_usdhc2_gpio: usdhc2gpiogrp {
+		fsl,pins = <
+			MX8MN_IOMUXC_GPIO1_IO13_GPIO1_IO13	0x41
+		>;
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-tqma8mqnl-mba8mx.dts b/arch/arm64/boot/dts/freescale/imx8mn-tqma8mqnl-mba8mx.dts
index 3f1e49bfe38f..c07d59147ab5 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-tqma8mqnl-mba8mx.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mn-tqma8mqnl-mba8mx.dts
@@ -11,6 +11,7 @@
 / {
 	model = "TQ-Systems GmbH i.MX8MN TQMa8MxNL on MBa8Mx";
 	compatible = "tq,imx8mn-tqma8mqnl-mba8mx", "tq,imx8mn-tqma8mqnl", "fsl,imx8mn";
+	chassis-type = "embedded";
 
 	aliases {
 		eeprom0 = &eeprom3;
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som-symphony.dts b/arch/arm64/boot/dts/freescale/imx8mn-var-som-symphony.dts
index a7a57442cb81..f38ee2266b25 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-var-som-symphony.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som-symphony.dts
@@ -57,6 +57,15 @@
 			linux,default-trigger = "heartbeat";
 		};
 	};
+
+	/* Peripherals supply, enabled by Q2 after SOM_3V3 rises. */
+	reg_per_3v3: regulator-peripheral-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "per_3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+	};
 };
 
 &ethphy {
@@ -79,6 +88,7 @@
 		interrupts = <7 IRQ_TYPE_EDGE_FALLING>;
 		#gpio-cells = <2>;
 		wakeup-source;
+		vcc-supply = <&reg_per_3v3>;
 
 		/* USB 3.0 OTG (usbotg1) / SATA port switch, set to USB 3.0 */
 		usb3-sata-sel-hog {
@@ -118,9 +128,14 @@
 		pinctrl-0 = <&pinctrl_ptn5150>;
 		status = "okay";
 
-		port {
-			typec1_dr_sw: endpoint {
-				remote-endpoint = <&usb1_drd_sw>;
+		connector {
+			compatible = "usb-c-connector";
+			label = "USB-C";
+
+			port {
+				typec1_dr_sw: endpoint {
+					remote-endpoint = <&usb1_drd_sw>;
+				};
 			};
 		};
 	};
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi
index b8946edf317b..b364307868f2 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi
@@ -31,6 +31,14 @@
 		gpio = <&gpio2 9 GPIO_ACTIVE_HIGH>;
 		enable-active-high;
 	};
+
+	reg_3v3_fixed: regulator-3v3-fixed {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed_3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+	};
 };
 
 &A53_0 {
@@ -234,6 +242,7 @@
 		compatible = "atmel,24c04";
 		reg = <0x52>;
 		pagesize = <16>;
+		vcc-supply = <&reg_3v3_fixed>;
 	};
 };
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi
index 1bb1d0c1bae4..136e75c51251 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi
@@ -637,6 +637,8 @@
 			clk: clock-controller@30380000 {
 				compatible = "fsl,imx8mn-ccm";
 				reg = <0x30380000 0x10000>;
+				interrupts = <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
 				#clock-cells = <1>;
 				clocks = <&osc_32k>, <&osc_24m>, <&clk_ext1>, <&clk_ext2>,
 					 <&clk_ext3>, <&clk_ext4>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts b/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts
index 0bea0798d2db..feae77e03835 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts
@@ -94,6 +94,17 @@
 		};
 	};
 
+	bridge-connector {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi_con: endpoint {
+				remote-endpoint = <&adv7535_out>;
+			};
+		};
+	};
+
 	leds {
 		compatible = "gpio-leds";
 		pinctrl-names = "default";
@@ -153,6 +164,21 @@
 		enable-active-high;
 	};
 
+	sound-adv7535 {
+		compatible = "simple-audio-card";
+		simple-audio-card,name = "sound-adv7535";
+		simple-audio-card,format = "i2s";
+
+		simple-audio-card,cpu {
+			sound-dai = <&sai5>;
+			system-clock-direction-out;
+		};
+
+		simple-audio-card,codec {
+			sound-dai = <&adv_bridge>;
+		};
+	};
+
 	sound-dmic {
 		compatible = "simple-audio-card";
 		simple-audio-card,name = "sound-pdm";
@@ -274,6 +300,35 @@
 		#interrupt-cells = <2>;
 	};
 
+	adv_bridge: hdmi@3d {
+		compatible = "adi,adv7535";
+		reg = <0x3d>, <0x3c>, <0x3e>, <0x3f>;
+		reg-names = "main", "cec", "edid", "packet";
+		adi,dsi-lanes = <4>;
+		#sound-dai-cells = <0>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				adv7535_in: endpoint {
+					remote-endpoint = <&dsi_out>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				adv7535_out: endpoint {
+					remote-endpoint = <&hdmi_con>;
+				};
+			};
+		};
+	};
+
 	pcieclk: clock-generator@68 {
 		compatible = "renesas,9fgv0241";
 		reg = <0x68>;
@@ -398,6 +453,10 @@
 	};
 };
 
+&lcdif1 {
+	status = "okay";
+};
+
 &micfil {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_pdm>;
@@ -407,6 +466,21 @@
 	status = "okay";
 };
 
+&mipi_dsi {
+	samsung,esc-clock-frequency = <10000000>;
+	status = "okay";
+
+	ports {
+		port@1 {
+			reg = <1>;
+
+			dsi_out: endpoint {
+				remote-endpoint = <&adv7535_in>;
+			};
+		};
+	};
+};
+
 &pcie {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_pcie>;
@@ -433,6 +507,16 @@
 	status = "okay";
 };
 
+&sai5 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_sai5>;
+	assigned-clocks = <&clk IMX8MP_CLK_SAI5>;
+	assigned-clock-parents = <&clk IMX8MP_AUDIO_PLL1_OUT>;
+	assigned-clock-rates = <12288000>;
+	fsl,sai-mclk-direction-output;
+	status = "okay";
+};
+
 &snvs_pwrkey {
 	status = "okay";
 };
@@ -612,6 +696,14 @@
 		>;
 	};
 
+	pinctrl_sai5: sai5grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SAI5_RXD3__AUDIOMIX_SAI5_TX_DATA00	0xd6
+			MX8MP_IOMUXC_SAI5_RXD2__AUDIOMIX_SAI5_TX_BCLK	0xd6
+			MX8MP_IOMUXC_SAI5_RXD1__AUDIOMIX_SAI5_TX_SYNC	0xd6
+		>;
+	};
+
 	pinctrl_tpm: tpmgrp {
 		fsl,pins = <
 			MX8MP_IOMUXC_SAI1_RXFS__GPIO4_IO00	0x19 /* Reset */
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-debix-model-a.dts b/arch/arm64/boot/dts/freescale/imx8mp-debix-model-a.dts
index 267ceffc02d8..2c19766ebf09 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-debix-model-a.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-debix-model-a.dts
@@ -75,7 +75,7 @@
 &eqos {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_eqos>;
-	phy-connection-type = "rgmii-id";
+	phy-mode = "rgmii-id";
 	phy-handle = <&ethphy0>;
 	status = "okay";
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-debix-som-a-bmb-08.dts b/arch/arm64/boot/dts/freescale/imx8mp-debix-som-a-bmb-08.dts
index 0afd90224a59..b11d694b98e1 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-debix-som-a-bmb-08.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-debix-som-a-bmb-08.dts
@@ -63,6 +63,50 @@
 		regulator-always-on;
 	};
 
+	reg_csi1_1v8: regulator-csi1-vdd1v8 {
+		compatible = "regulator-fixed";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-name = "CSI1_VDD1V8";
+		gpio = <&expander0 13 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&reg_baseboard_vdd3v3>;
+	};
+
+	reg_csi1_3v3: regulator-csi1-vdd3v3 {
+		compatible = "regulator-fixed";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-name = "CSI1_VDD3V3";
+		gpio = <&expander0 14 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&reg_vdd5v0>;
+	};
+
+	reg_csi2_1v8: regulator-csi2-vdd1v8 {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_reg_csi2_1v8>;
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-name = "CSI2_VDD1V8";
+		gpio = <&gpio3 21 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&reg_baseboard_vdd3v3>;
+	};
+
+	reg_csi2_3v3: regulator-csi2-vdd3v3 {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_reg_csi2_3v3>;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-name = "CSI2_VDD3V3";
+		gpio = <&gpio4 25 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&reg_vdd5v0>;
+	};
+
 	regulator-vbus-usb20 {
 		compatible = "regulator-fixed";
 		regulator-min-microvolt = <5000000>;
@@ -413,6 +457,18 @@
 		>;
 	};
 
+	pinctrl_reg_csi2_1v8: regcsi21v8grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SAI5_RXD0__GPIO3_IO21		0x19
+		>;
+	};
+
+	pinctrl_reg_csi2_3v3: regcsi23v3grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SAI2_TXC__GPIO4_IO25		0x19
+		>;
+	};
+
 	pinctrl_uart2: uart2grp {
 		fsl,pins = <
 			MX8MP_IOMUXC_UART2_RXD__UART2_DCE_RX		0x14f
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-debix-som-a.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-debix-som-a.dtsi
index bc312aa1bfc8..91094c227744 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-debix-som-a.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-debix-som-a.dtsi
@@ -6,6 +6,8 @@
 
 #include "imx8mp.dtsi"
 
+#include <dt-bindings/leds/common.h>
+
 / {
 	model = "Polyhex i.MX8MPlus Debix SOM A";
 	compatible = "polyhex,imx8mp-debix-som-a", "fsl,imx8mp";
@@ -20,6 +22,20 @@
 		gpio = <&gpio2 19 GPIO_ACTIVE_HIGH>;
 		enable-active-high;
 	};
+
+	gpio-leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_gpio_led>;
+
+		led-0 {
+			gpios = <&gpio3 16 GPIO_ACTIVE_HIGH>;
+			default-state = "on";
+			linux,default-trigger = "heartbeat";
+			function = LED_FUNCTION_STATUS;
+			color = <LED_COLOR_ID_GREEN>;
+		};
+	};
 };
 
 &A53_0 {
@@ -203,6 +219,12 @@
 };
 
 &iomuxc {
+	pinctrl_gpio_led: gpioledgrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_NAND_READY_B__GPIO3_IO16		0x19
+		>;
+	};
+
 	pinctrl_i2c1: i2c1grp {
 		fsl,pins = <
 			MX8MP_IOMUXC_I2C1_SCL__I2C1_SCL			0x400001c2
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-pdk3.dts b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-pdk3.dts
index b749e28e5ede..fea67a9282f0 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-pdk3.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-pdk3.dts
@@ -175,10 +175,14 @@
 				pinctrl-names = "default";
 				pinctrl-0 = <&pinctrl_ptn5150>;
 
-				port {
-
-					ptn5150_out_ep: endpoint {
-						remote-endpoint = <&dwc3_0_ep>;
+				connector {
+					compatible = "usb-c-connector";
+					label = "USB-C";
+
+					port {
+						ptn5150_out_ep: endpoint {
+							remote-endpoint = <&dwc3_0_ep>;
+						};
 					};
 				};
 			};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi
index d8963f32ec84..4ae4fdab461e 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi
@@ -420,6 +420,18 @@
 		reg = <0x53>;
 	};
 
+	eeprom0wl: eeprom@58 {
+		compatible = "atmel,24c32d-wl";	/* M24C32-D WL page of 0x50 */
+		pagesize = <32>;
+		reg = <0x58>;
+	};
+
+	eeprom1wl: eeprom@5b {
+		compatible = "atmel,24c32d-wl";	/* M24C32-D WL page of 0x53 */
+		pagesize = <32>;
+		reg = <0x5b>;
+	};
+
 	ioexp: gpio@74 {
 		compatible = "nxp,pca9539";
 		reg = <0x74>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-msc-sm2s-ep1.dts b/arch/arm64/boot/dts/freescale/imx8mp-msc-sm2s-ep1.dts
index e4215c83ee0f..da4b1807c275 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-msc-sm2s-ep1.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-msc-sm2s-ep1.dts
@@ -57,8 +57,8 @@
 		clocks = <&clk IMX8MP_CLK_CLKOUT1>;
 		#sound-dai-cells = <0>;
 
-		VDDA-supply  = <&reg_vcc_3v3_audio>;
-		VDDD-supply  = <&reg_vcc_1v8_audio>;
+		VDDA-supply = <&reg_vcc_3v3_audio>;
+		VDDD-supply = <&reg_vcc_1v8_audio>;
 		VDDIO-supply = <&reg_vcc_1v8_audio>;
 	};
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-skov-reva.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-skov-reva.dtsi
new file mode 100644
index 000000000000..59813ef8e2bb
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mp-skov-reva.dtsi
@@ -0,0 +1,711 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+
+#include "imx8mp.dtsi"
+
+#include <dt-bindings/leds/common.h>
+
+/ {
+	aliases {
+		/* some of this aliases like backlight0, ethernetX and switch0
+		 * are needed for the bootloader.
+		 */
+		backlight0 = &backlight;
+		ethernet0 = &eqos;
+		ethernet1 = &lan1;
+		ethernet2 = &lan2;
+		rtc0 = &i2c_rtc;
+		rtc1 = &snvs_rtc;
+		switch0 = &switch;
+	};
+
+	/*
+	 * Backlight is present only on some of boards, so it is disabled by
+	 * default.
+	 */
+	backlight: backlight {
+		compatible = "pwm-backlight";
+		pinctrl-0 = <&pinctrl_backlight>;
+		pwms = <&pwm1 0 20000 0>;
+		power-supply = <&reg_24v>;
+		enable-gpios = <&gpio4 24 GPIO_ACTIVE_HIGH>;
+		brightness-levels = <0 255>;
+		num-interpolated-steps = <17>;
+		default-brightness-level = <8>;
+		status = "disabled";
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_gpio_led>;
+
+		led-0 {
+			label = "D1";
+			color = <LED_COLOR_ID_GREEN>;
+			gpios = <&gpio1 5 GPIO_ACTIVE_HIGH>;
+			function = LED_FUNCTION_STATUS;
+			default-state = "on";
+			linux,default-trigger = "heartbeat";
+		};
+
+		led-1 {
+			label = "D2";
+			color = <LED_COLOR_ID_GREEN>;
+			gpios = <&gpio1 6 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		led-2 {
+			label = "D3";
+			color = <LED_COLOR_ID_GREEN>;
+			gpios = <&gpio1 7 GPIO_ACTIVE_HIGH>;
+			default-state = "on";
+		};
+	};
+
+	reg_1v2: regulator-1v2 {
+		compatible = "regulator-fixed";
+		vin-supply = <&reg_5v_p>;
+		regulator-name = "1V2";
+		regulator-min-microvolt = <1200000>;
+		regulator-max-microvolt = <1200000>;
+	};
+
+	reg_2v5: regulator-2v5 {
+		compatible = "regulator-fixed";
+		vin-supply = <&reg_5v_s>;
+		regulator-name = "2V5";
+		regulator-min-microvolt = <2500000>;
+		regulator-max-microvolt = <2500000>;
+	};
+
+	reg_3v3: regulator-3v3 {
+		compatible = "regulator-fixed";
+		vin-supply = <&reg_5v_s>;
+		regulator-name = "3V3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
+	/*
+	 * This regulator will provide power as long as possible even if
+	 * undervoltage is detected.
+	 */
+	reg_5v_p: regulator-5v-p {
+		compatible = "regulator-fixed";
+		regulator-name = "5V_P";
+		vin-supply = <&reg_24v>;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
+	/*
+	 * This regulator will be automatically shutdown if undervoltage is
+	 * detected.
+	 */
+	reg_5v_s: regulator-5v-s {
+		compatible = "regulator-fixed";
+		regulator-name = "5V_S";
+		vin-supply = <&reg_24v>;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
+	reg_24v: regulator-24v {
+		compatible = "regulator-fixed";
+		regulator-name = "24V";
+		regulator-min-microvolt = <24000000>;
+		regulator-max-microvolt = <24000000>;
+	};
+
+	reg_can2rs: regulator-can2rs {
+		compatible = "regulator-fixed";
+		regulator-name = "CAN2RS";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_can2rs>;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio4 22 GPIO_ACTIVE_LOW>;
+	};
+
+	reg_canrs: regulator-canrs {
+		compatible = "regulator-fixed";
+		regulator-name = "CANRS";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_canrs>;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio4 21 GPIO_ACTIVE_LOW>;
+	};
+
+	reg_tft_vcom: regulator-tft-vcom {
+		compatible = "pwm-regulator";
+		pwms = <&pwm4 0 20000 0>;
+		regulator-name = "VCOM";
+		vin-supply = <&reg_5v_s>;
+		regulator-min-microvolt = <3600000>;
+		regulator-max-microvolt = <3600000>;
+		regulator-always-on;
+		voltage-table = <3600000 26>;
+		status = "disabled";
+	};
+
+	reg_vsd_3v3: regulator-vsd-3v3 {
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_reg_vsd_3v3>;
+		vin-supply = <&reg_vdd_3v3>;
+		compatible = "regulator-fixed";
+		regulator-name = "VSD_3V3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio2 19 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+};
+
+&A53_0 {
+	cpu-supply = <&reg_vdd_arm>;
+};
+
+&A53_1 {
+	cpu-supply = <&reg_vdd_arm>;
+};
+
+&A53_2 {
+	cpu-supply = <&reg_vdd_arm>;
+};
+
+&A53_3 {
+	cpu-supply = <&reg_vdd_arm>;
+};
+
+&ecspi2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_ecspi2>;
+	cs-gpios = <&gpio5 13 GPIO_ACTIVE_LOW>;
+	status = "okay";
+
+	adc: adc@0 {
+		compatible = "microchip,mcp3002";
+		reg = <0>;
+		vref-supply = <&reg_vdd_3v3>;
+		spi-max-frequency = <1000000>;
+		#io-channel-cells = <1>;
+	};
+};
+
+&eqos {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_eqos>;
+	phy-mode = "rgmii-txid";
+	status = "okay";
+
+	fixed-link {
+		speed = <1000>;
+		full-duplex;
+	};
+};
+
+&flexcan1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_flexcan1>;
+	xceiver-supply = <&reg_canrs>;
+	status = "okay";
+};
+
+&flexcan2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_flexcan2>;
+	xceiver-supply = <&reg_can2rs>;
+	status = "okay";
+};
+
+&i2c1 {
+	clock-frequency = <100000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c1>;
+	status = "okay";
+
+	pmic@25 {
+		compatible = "nxp,pca9450c";
+		reg = <0x25>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_pmic>;
+		interrupts-extended = <&gpio1 3 IRQ_TYPE_EDGE_RISING>;
+		sd-vsel-gpios = <&gpio1 4 GPIO_ACTIVE_HIGH>;
+
+		regulators {
+			reg_vdd_soc: BUCK1 {
+				regulator-name = "VDD_SOC";
+				regulator-min-microvolt = <600000>;
+				regulator-max-microvolt = <2187500>;
+				vin-supply = <&reg_5v_p>;
+				regulator-boot-on;
+				regulator-always-on;
+				regulator-ramp-delay = <3125>;
+			};
+
+			reg_vdd_arm: BUCK2 {
+				regulator-name = "VDD_ARM";
+				regulator-min-microvolt = <600000>;
+				regulator-max-microvolt = <2187500>;
+				vin-supply = <&reg_5v_p>;
+				regulator-boot-on;
+				regulator-always-on;
+				regulator-ramp-delay = <3125>;
+				nxp,dvs-run-voltage = <950000>;
+				nxp,dvs-standby-voltage = <850000>;
+			};
+
+			reg_vdd_3v3: BUCK4 {
+				regulator-name = "VDD_3V3";
+				regulator-min-microvolt = <600000>;
+				regulator-max-microvolt = <3400000>;
+				vin-supply = <&reg_5v_p>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			reg_vdd_1v8: BUCK5 {
+				regulator-name = "VDD_1V8";
+				regulator-min-microvolt = <600000>;
+				regulator-max-microvolt = <3400000>;
+				vin-supply = <&reg_5v_p>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			reg_nvcc_dram_1v1: BUCK6 {
+				regulator-name = "NVCC_DRAM_1V1";
+				regulator-min-microvolt = <600000>;
+				regulator-max-microvolt = <3400000>;
+				vin-supply = <&reg_5v_p>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			reg_nvcc_snvs_1v8: LDO1 {
+				regulator-name = "NVCC_SNVS_1V8";
+				regulator-min-microvolt = <1600000>;
+				regulator-max-microvolt = <3300000>;
+				vin-supply = <&reg_5v_p>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			reg_vdda_1v8: LDO3 {
+				regulator-name = "VDDA_1V8";
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <3300000>;
+				vin-supply = <&reg_5v_p>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			reg_nvcc_sd2: LDO5 {
+				regulator-name = "NVCC_SD2";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				vin-supply = <&reg_5v_p>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+		};
+	};
+};
+
+&i2c3 {
+	clock-frequency = <100000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c3>;
+	status = "okay";
+
+	i2c_rtc: rtc@51 {
+		compatible = "nxp,pcf85063tp";
+		reg = <0x51>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_rtc>;
+		interrupts-extended = <&gpio4 31 IRQ_TYPE_EDGE_FALLING>;
+		quartz-load-femtofarads = <12500>;
+	};
+};
+
+&i2c4 {
+	clock-frequency = <380000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c4>;
+	status = "okay";
+
+	switch: switch@5f {
+		compatible = "microchip,ksz9893";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_switch>;
+		reset-gpios = <&gpio5 1 GPIO_ACTIVE_LOW>;
+		reg = <0x5f>;
+
+		ethernet-ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			lan1: port@0 {
+				reg = <0>;
+				phy-mode = "internal";
+				label = "lan1";
+			};
+
+			lan2: port@1 {
+				reg = <1>;
+				phy-mode = "internal";
+				label = "lan2";
+			};
+
+			port@2 {
+				reg = <2>;
+				label = "cpu";
+				ethernet = <&eqos>;
+				phy-mode = "rgmii";
+				/* 2ns RX delay is implemented on PCB */
+				tx-internal-delay-ps = <2000>;
+				rx-internal-delay-ps = <0>;
+
+				fixed-link {
+					speed = <1000>;
+					full-duplex;
+				};
+			};
+		};
+	};
+};
+
+&pwm1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pwm1>;
+};
+
+&pwm4 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pwm4>;
+};
+
+&uart1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart1>;
+	status = "okay";
+};
+
+&uart2 {
+	/* console */
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart2>;
+	status = "okay";
+};
+
+&usb3_0 {
+	status = "okay";
+};
+
+&usb3_1 {
+	status = "okay";
+};
+
+&usb3_phy0 {
+	vbus-supply = <&reg_3v3>;
+	status = "okay";
+};
+
+&usb3_phy1 {
+	vbus-supply = <&reg_3v3>;
+	status = "okay";
+};
+
+&usb_dwc3_0 {
+	dr_mode = "host";
+};
+
+&usb_dwc3_1 {
+	dr_mode = "host";
+};
+
+/* SD Card */
+&usdhc2 {
+	pinctrl-names = "default", "state_100mhz", "state_200mhz";
+	pinctrl-0 = <&pinctrl_usdhc2>, <&pinctrl_usdhc2_gpio>;
+	pinctrl-1 = <&pinctrl_usdhc2_100mhz>, <&pinctrl_usdhc2_gpio>;
+	pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_gpio>;
+	vmmc-supply = <&reg_vsd_3v3>;
+	vqmmc-supply = <&reg_nvcc_sd2>;
+	cd-gpios = <&gpio2 12 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio2 20 GPIO_ACTIVE_HIGH>;
+	bus-width = <4>;
+	status = "okay";
+};
+
+/* eMMC */
+&usdhc3 {
+	assigned-clocks = <&clk IMX8MP_CLK_USDHC3>;
+	assigned-clock-rates = <400000000>;
+	pinctrl-names = "default", "state_100mhz", "state_200mhz";
+	pinctrl-0 = <&pinctrl_usdhc3>;
+	pinctrl-1 = <&pinctrl_usdhc3_100mhz>;
+	pinctrl-2 = <&pinctrl_usdhc3_200mhz>;
+	vmmc-supply = <&reg_vdd_3v3>;
+	vqmmc-supply = <&reg_vdd_1v8>;
+	bus-width = <8>;
+	no-sd;
+	no-sdio;
+	non-removable;
+	status = "okay";
+};
+
+&wdog1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_wdog>;
+	fsl,ext-reset-output;
+	status = "okay";
+};
+
+&iomuxc {
+	pinctrl_backlight: backlightgrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SAI2_TXFS__GPIO4_IO24			0x0100
+		>;
+	};
+
+	pinctrl_can2rs: can2rsgrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SAI2_RXC__GPIO4_IO22			0x154
+		>;
+	};
+
+	pinctrl_canrs: canrsgrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SAI2_RXFS__GPIO4_IO21			0x154
+		>;
+	};
+
+	pinctrl_ecspi2: ecspi2grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_ECSPI2_SCLK__ECSPI2_SCLK			0x44
+			MX8MP_IOMUXC_ECSPI2_MOSI__ECSPI2_MOSI			0x44
+			MX8MP_IOMUXC_ECSPI2_MISO__ECSPI2_MISO			0x44
+			MX8MP_IOMUXC_ECSPI2_SS0__GPIO5_IO13			0x40
+		>;
+	};
+
+	pinctrl_eqos: eqosgrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_ENET_RD0__ENET_QOS_RGMII_RD0			0x91
+			MX8MP_IOMUXC_ENET_RD1__ENET_QOS_RGMII_RD1			0x91
+			MX8MP_IOMUXC_ENET_RD2__ENET_QOS_RGMII_RD2			0x91
+			MX8MP_IOMUXC_ENET_RD3__ENET_QOS_RGMII_RD3			0x91
+			MX8MP_IOMUXC_ENET_RXC__CCM_ENET_QOS_CLOCK_GENERATE_RX_CLK	0x91
+			MX8MP_IOMUXC_ENET_RX_CTL__ENET_QOS_RGMII_RX_CTL			0x91
+			MX8MP_IOMUXC_ENET_TD0__ENET_QOS_RGMII_TD0			0x1f
+			MX8MP_IOMUXC_ENET_TD1__ENET_QOS_RGMII_TD1			0x1f
+			MX8MP_IOMUXC_ENET_TD2__ENET_QOS_RGMII_TD2			0x1f
+			MX8MP_IOMUXC_ENET_TD3__ENET_QOS_RGMII_TD3			0x1f
+			MX8MP_IOMUXC_ENET_TX_CTL__ENET_QOS_RGMII_TX_CTL			0x1f
+			MX8MP_IOMUXC_ENET_TXC__CCM_ENET_QOS_CLOCK_GENERATE_TX_CLK	0x1f
+		>;
+	};
+
+	pinctrl_flexcan1: flexcan1grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SPDIF_RX__CAN1_RX				0x154
+			MX8MP_IOMUXC_SPDIF_TX__CAN1_TX				0x154
+		>;
+	};
+
+	pinctrl_flexcan2: flexcan2grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SAI2_MCLK__CAN2_RX				0x154
+			MX8MP_IOMUXC_SAI2_TXD0__CAN2_TX				0x154
+		>;
+	};
+
+	pinctrl_gpio_led: gpioledgrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_GPIO1_IO05__GPIO1_IO05			0x19
+			MX8MP_IOMUXC_GPIO1_IO06__GPIO1_IO06			0x19
+			MX8MP_IOMUXC_GPIO1_IO07__GPIO1_IO07			0x19
+		>;
+	};
+
+	pinctrl_i2c1: i2c1grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_I2C1_SCL__I2C1_SCL				0x400001c2
+			MX8MP_IOMUXC_I2C1_SDA__I2C1_SDA				0x400001c2
+		>;
+	};
+
+	pinctrl_i2c3: i2c3grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_I2C3_SCL__I2C3_SCL				0x400001c2
+			MX8MP_IOMUXC_I2C3_SDA__I2C3_SDA				0x400001c2
+		>;
+	};
+
+	pinctrl_i2c4: i2c4grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_I2C4_SCL__I2C4_SCL				0x400001c3
+			MX8MP_IOMUXC_I2C4_SDA__I2C4_SDA				0x400001c3
+		>;
+	};
+
+	pinctrl_pmic: pmicirqgrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03			0x41
+			MX8MP_IOMUXC_GPIO1_IO04__GPIO1_IO04			0x41
+		>;
+	};
+
+	pinctrl_pwm1: pwm1grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SPDIF_EXT_CLK__PWM1_OUT			0x116
+		>;
+	};
+
+	pinctrl_pwm4: pwm4grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SAI3_MCLK__PWM4_OUT			0x116
+		>;
+	};
+
+	pinctrl_reg_vsd_3v3: regvsd3v3grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SD2_RESET_B__GPIO2_IO19	0x40
+		>;
+	};
+
+	pinctrl_rtc: rtcgrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SAI3_TXFS__GPIO4_IO31			0x41
+		>;
+	};
+
+	pinctrl_switch: switchgrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SAI3_TXC__GPIO5_IO00			0x41
+			MX8MP_IOMUXC_SAI3_TXD__GPIO5_IO01			0x41
+		>;
+	};
+
+	pinctrl_touchscreen: touchscreengrp {
+		fsl,pins = <
+			/* external 10 k pull up */
+			/* CTP_INT */
+			MX8MP_IOMUXC_SAI3_RXFS__GPIO4_IO28			0x41
+			/* CTP_RST */
+			MX8MP_IOMUXC_SAI3_RXC__GPIO4_IO29			0x41
+		>;
+	};
+
+	pinctrl_uart1: uart1grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_UART1_RXD__UART1_DCE_RX			0x140
+			MX8MP_IOMUXC_UART1_TXD__UART1_DCE_TX			0x140
+			MX8MP_IOMUXC_UART3_RXD__UART1_DTE_RTS			0x140
+		>;
+	};
+
+	pinctrl_uart2: uart2grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_UART2_RXD__UART2_DCE_RX			0x14f
+			MX8MP_IOMUXC_UART2_TXD__UART2_DCE_TX			0x14f
+		>;
+	};
+
+	pinctrl_usdhc2: usdhc2grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SD2_CLK__USDHC2_CLK			0x190
+			MX8MP_IOMUXC_SD2_CMD__USDHC2_CMD			0x1d0
+			MX8MP_IOMUXC_SD2_DATA0__USDHC2_DATA0			0x1d0
+			MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1			0x1d0
+			MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2			0x1d0
+			MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3			0x1d0
+		>;
+	};
+
+	pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SD2_CLK__USDHC2_CLK			0x194
+			MX8MP_IOMUXC_SD2_CMD__USDHC2_CMD			0x1d4
+			MX8MP_IOMUXC_SD2_DATA0__USDHC2_DATA0			0x1d4
+			MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1			0x1d4
+			MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2			0x1d4
+			MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3			0x1d4
+		>;
+	};
+
+	pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SD2_CLK__USDHC2_CLK			0x196
+			MX8MP_IOMUXC_SD2_CMD__USDHC2_CMD			0x1d6
+			MX8MP_IOMUXC_SD2_DATA0__USDHC2_DATA0			0x1d6
+			MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1			0x1d6
+			MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2			0x1d6
+			MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3			0x1d6
+		>;
+	};
+
+	pinctrl_usdhc2_gpio: usdhc2gpiogrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SD2_CD_B__GPIO2_IO12			0x1c4
+			MX8MP_IOMUXC_SD2_WP__GPIO2_IO20				0x1c4
+		>;
+	};
+
+	pinctrl_usdhc3: usdhc3grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_NAND_WE_B__USDHC3_CLK			0x190
+			MX8MP_IOMUXC_NAND_WP_B__USDHC3_CMD			0x1d0
+			MX8MP_IOMUXC_NAND_DATA04__USDHC3_DATA0			0x1d0
+			MX8MP_IOMUXC_NAND_DATA05__USDHC3_DATA1			0x1d0
+			MX8MP_IOMUXC_NAND_DATA06__USDHC3_DATA2			0x1d0
+			MX8MP_IOMUXC_NAND_DATA07__USDHC3_DATA3			0x1d0
+			MX8MP_IOMUXC_NAND_RE_B__USDHC3_DATA4			0x1d0
+			MX8MP_IOMUXC_NAND_CE2_B__USDHC3_DATA5			0x1d0
+			MX8MP_IOMUXC_NAND_CE3_B__USDHC3_DATA6			0x1d0
+			MX8MP_IOMUXC_NAND_CLE__USDHC3_DATA7			0x1d0
+			MX8MP_IOMUXC_NAND_CE1_B__USDHC3_STROBE			0x190
+		>;
+	};
+
+	pinctrl_usdhc3_100mhz: usdhc3-100mhzgrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_NAND_WE_B__USDHC3_CLK			0x194
+			MX8MP_IOMUXC_NAND_WP_B__USDHC3_CMD			0x1d4
+			MX8MP_IOMUXC_NAND_DATA04__USDHC3_DATA0			0x1d4
+			MX8MP_IOMUXC_NAND_DATA05__USDHC3_DATA1			0x1d4
+			MX8MP_IOMUXC_NAND_DATA06__USDHC3_DATA2			0x1d4
+			MX8MP_IOMUXC_NAND_DATA07__USDHC3_DATA3			0x1d4
+			MX8MP_IOMUXC_NAND_RE_B__USDHC3_DATA4			0x1d4
+			MX8MP_IOMUXC_NAND_CE2_B__USDHC3_DATA5			0x1d4
+			MX8MP_IOMUXC_NAND_CE3_B__USDHC3_DATA6			0x1d4
+			MX8MP_IOMUXC_NAND_CLE__USDHC3_DATA7			0x1d4
+			MX8MP_IOMUXC_NAND_CE1_B__USDHC3_STROBE			0x194
+		>;
+	};
+
+	pinctrl_usdhc3_200mhz: usdhc3-200mhzgrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_NAND_WE_B__USDHC3_CLK			0x196
+			MX8MP_IOMUXC_NAND_WP_B__USDHC3_CMD			0x1d6
+			MX8MP_IOMUXC_NAND_DATA04__USDHC3_DATA0			0x1d6
+			MX8MP_IOMUXC_NAND_DATA05__USDHC3_DATA1			0x1d6
+			MX8MP_IOMUXC_NAND_DATA06__USDHC3_DATA2			0x1d6
+			MX8MP_IOMUXC_NAND_DATA07__USDHC3_DATA3			0x1d6
+			MX8MP_IOMUXC_NAND_RE_B__USDHC3_DATA4			0x1d6
+			MX8MP_IOMUXC_NAND_CE2_B__USDHC3_DATA5			0x1d6
+			MX8MP_IOMUXC_NAND_CE3_B__USDHC3_DATA6			0x1d6
+			MX8MP_IOMUXC_NAND_CLE__USDHC3_DATA7			0x1d6
+			MX8MP_IOMUXC_NAND_CE1_B__USDHC3_STROBE			0x196
+		>;
+	};
+
+	pinctrl_wdog: wdoggrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_GPIO1_IO02__WDOG1_WDOG_B			0xc6
+		>;
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-hdmi.dts b/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-hdmi.dts
new file mode 100644
index 000000000000..c1ca69da3cb8
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-hdmi.dts
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+
+/dts-v1/;
+
+#include "imx8mp-skov-reva.dtsi"
+
+/ {
+	model = "SKOV IMX8MP CPU revB - HDMI";
+	compatible = "skov,imx8mp-skov-revb-hdmi", "fsl,imx8mp";
+};
+
+&iomuxc {
+	pinctrl_hdmi: hdmigrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_HDMI_DDC_SCL__HDMIMIX_HDMI_SCL		0x1c3
+			MX8MP_IOMUXC_HDMI_DDC_SDA__HDMIMIX_HDMI_SDA		0x1c3
+			MX8MP_IOMUXC_HDMI_HPD__HDMIMIX_HDMI_HPD			0x19
+		>;
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-lt6.dts b/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-lt6.dts
new file mode 100644
index 000000000000..ccbd3abedd69
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-lt6.dts
@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+
+/dts-v1/;
+
+#include "imx8mp-skov-reva.dtsi"
+
+/ {
+	model = "SKOV IMX8MP CPU revB - LT6";
+	compatible = "skov,imx8mp-skov-revb-lt6", "fsl,imx8mp";
+
+	touchscreen {
+		compatible = "resistive-adc-touch";
+		io-channels = <&adc_ts 1>, <&adc_ts 3>, <&adc_ts 4>, <&adc_ts 5>;
+		io-channel-names = "y", "z1", "z2", "x";
+		touchscreen-min-pressure = <65000>;
+		touchscreen-inverted-y;
+		touchscreen-swapped-x-y;
+		touchscreen-x-plate-ohms = <300>;
+	};
+};
+
+&reg_tft_vcom {
+	regulator-min-microvolt = <3600000>;
+	regulator-max-microvolt = <3600000>;
+	voltage-table = <3600000 26>;
+	status = "okay";
+};
+
+&pwm4 {
+	status = "okay";
+};
+
+&backlight {
+	status = "okay";
+};
+
+&ecspi1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_ecspi1>;
+	cs-gpios = <&gpio5 9 GPIO_ACTIVE_LOW>;
+	status = "okay";
+
+	adc_ts: adc@0 {
+		compatible = "ti,tsc2046e-adc";
+		reg = <0>;
+		pinctrl-0 = <&pinctrl_touch>;
+		pinctrl-names ="default";
+		spi-max-frequency = <1000000>;
+		interrupts-extended = <&gpio4 25 IRQ_TYPE_LEVEL_LOW>;
+		#io-channel-cells = <1>;
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		channel@1 {
+			reg = <1>;
+			settling-time-us = <700>;
+			oversampling-ratio = <5>;
+		};
+
+		channel@3 {
+			reg = <3>;
+			settling-time-us = <700>;
+			oversampling-ratio = <5>;
+		};
+
+		channel@4 {
+			reg = <4>;
+			settling-time-us = <700>;
+			oversampling-ratio = <5>;
+		};
+
+		channel@5 {
+			reg = <5>;
+			settling-time-us = <700>;
+			oversampling-ratio = <5>;
+		};
+	};
+};
+
+&pwm1 {
+	status = "okay";
+};
+
+&iomuxc {
+	pinctrl_ecspi1: ecspi1grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_ECSPI1_SCLK__ECSPI1_SCLK			0x44
+			MX8MP_IOMUXC_ECSPI1_MOSI__ECSPI1_MOSI			0x44
+			MX8MP_IOMUXC_ECSPI1_MISO__ECSPI1_MISO			0x44
+			MX8MP_IOMUXC_ECSPI1_SS0__GPIO5_IO09			0x40
+		>;
+	};
+
+	pinctrl_touch: touchgrp {
+		fsl,pins = <
+			/* external pull up */
+			MX8MP_IOMUXC_SAI2_TXC__GPIO4_IO25			0x40
+		>;
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-mi1010ait-1cp1.dts b/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-mi1010ait-1cp1.dts
new file mode 100644
index 000000000000..3c2efdc59bfa
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-mi1010ait-1cp1.dts
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+
+/dts-v1/;
+
+#include "imx8mp-skov-reva.dtsi"
+
+/ {
+	model = "SKOV IMX8MP CPU revB - MI1010AIT-1CP1";
+	compatible = "skov,imx8mp-skov-revb-mi1010ait-1cp1", "fsl,imx8mp";
+
+	panel {
+		compatible = "multi-inno,mi1010ait-1cp";
+		backlight = <&backlight>;
+		power-supply = <&reg_tft_vcom>;
+
+		port {
+			in_lvds0: endpoint {
+				remote-endpoint = <&ldb_lvds_ch0>;
+			};
+		};
+	};
+};
+
+&backlight {
+	status = "okay";
+};
+
+&i2c2 {
+	clock-frequency = <100000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c2>;
+	status = "okay";
+
+	touchscreen@38 {
+		compatible = "edt,edt-ft5406";
+		reg = <0x38>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_touchscreen>;
+		interrupts-extended = <&gpio4 28 IRQ_TYPE_EDGE_FALLING>;
+		reset-gpios = <&gpio4 29 GPIO_ACTIVE_LOW>;
+		touchscreen-size-x = <1280>;
+		touchscreen-size-y = <800>;
+		vcc-supply = <&reg_vdd_3v3>;
+		iovcc-supply = <&reg_vdd_3v3>;
+		wakeup-source;
+	};
+};
+
+&lcdif2 {
+	status = "okay";
+};
+
+&lvds_bridge {
+	/* IMX8MP_CLK_MEDIA_LDB = IMX8MP_CLK_MEDIA_DISP2_PIX * 7 */
+	assigned-clock-rates = <482300000>;
+	status = "okay";
+
+	ports {
+		port@1 {
+			ldb_lvds_ch0: endpoint {
+				remote-endpoint = <&in_lvds0>;
+			};
+		};
+	};
+};
+
+&media_blk_ctrl {
+	/* currently it is not possible to let display clocks confugure
+	 * automatically, so we need to set them manually
+	 */
+	assigned-clock-rates = <500000000>, <200000000>, <0>,
+		/* IMX8MP_CLK_MEDIA_DISP2_PIX = pixelclk of lvds panel */
+		<68900000>,
+		/* IMX8MP_VIDEO_PLL1 = IMX8MP_CLK_MEDIA_LDB * 2 */
+		<964600000>;
+};
+
+&pwm4 {
+	status = "okay";
+};
+
+&pwm1 {
+	status = "okay";
+};
+
+&reg_tft_vcom {
+	regulator-min-microvolt = <3160000>;
+	regulator-max-microvolt = <3160000>;
+	voltage-table = <3160000 73>;
+	status = "okay";
+};
+
+&iomuxc {
+	pinctrl_i2c2: i2c2grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_I2C2_SCL__I2C2_SCL				0x400001c2
+			MX8MP_IOMUXC_I2C2_SDA__I2C2_SDA				0x400001c2
+		>;
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl-lvds-g133han01.dtso b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl-lvds-g133han01.dtso
new file mode 100644
index 000000000000..5058cd9409c7
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl-lvds-g133han01.dtso
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR MIT)
+/*
+ * Copyright (c) 2023 TQ-Systems GmbH <linux@ew.tq-group.com>,
+ * D-82229 Seefeld, Germany.
+ * Author: Alexander Stein
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/clock/imx8mp-clock.h>
+
+&{/} {
+	compatible = "tq,imx8mp-tqma8mpql-mba8mpxl", "tq,imx8mp-tqma8mpql", "fsl,imx8mp";
+};
+
+&backlight_lvds {
+	status = "okay";
+};
+
+&display {
+	compatible = "auo,g133han01";
+	status = "okay";
+
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			reg = <0>;
+			dual-lvds-odd-pixels;
+
+			panel_in_lvds0: endpoint {
+				remote-endpoint = <&ldb_lvds_ch0>;
+			};
+		};
+
+		port@1 {
+			reg = <1>;
+			dual-lvds-even-pixels;
+
+			panel_in_lvds1: endpoint {
+				remote-endpoint = <&ldb_lvds_ch1>;
+			};
+		};
+	};
+};
+
+&lcdif2 {
+	status = "okay";
+};
+
+&lvds_bridge {
+	assigned-clocks = <&clk IMX8MP_CLK_MEDIA_LDB>,
+				 <&clk IMX8MP_VIDEO_PLL1>;
+	assigned-clock-parents = <&clk IMX8MP_VIDEO_PLL1_OUT>;
+	assigned-clock-rates = <0>, <988400000>;
+	status = "okay";
+
+	ports {
+		port@1 {
+			ldb_lvds_ch0: endpoint {
+				remote-endpoint = <&panel_in_lvds0>;
+			};
+		};
+
+		port@2 {
+			ldb_lvds_ch1: endpoint {
+				remote-endpoint = <&panel_in_lvds1>;
+			};
+		};
+	};
+};
+
+&pwm2 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts
index 4240e20d38ac..a2d5d19b2de0 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts
@@ -15,6 +15,7 @@
 / {
 	model = "TQ-Systems i.MX8MPlus TQMa8MPxL on MBa8MPxL";
 	compatible = "tq,imx8mp-tqma8mpql-mba8mpxl", "tq,imx8mp-tqma8mpql", "fsl,imx8mp";
+	chassis-type = "embedded";
 
 	chosen {
 		stdout-path = &uart4;
@@ -55,6 +56,21 @@
 		clock-frequency = <25000000>;
 	};
 
+	connector {
+		compatible = "gpio-usb-b-connector", "usb-b-connector";
+		type = "micro";
+		label = "X29";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_usbcon0>;
+		id-gpios = <&gpio1 10 GPIO_ACTIVE_HIGH>;
+
+		port {
+			usb_dr_connector: endpoint {
+				remote-endpoint = <&usb3_dwc>;
+			};
+		};
+	};
+
 	fan0: pwm-fan {
 		compatible = "pwm-fan";
 		pinctrl-names = "default";
@@ -602,7 +618,6 @@
 &usb3_1 {
 	fsl,disable-port-power-control;
 	fsl,permanently-attached;
-	dr_mode = "host";
 	status = "okay";
 };
 
@@ -626,13 +641,10 @@
 	role-switch-default-mode = "peripheral";
 	status = "okay";
 
-	connector {
-		compatible = "gpio-usb-b-connector", "usb-b-connector";
-		type = "micro";
-		label = "X29";
-		pinctrl-names = "default";
-		pinctrl-0 = <&pinctrl_usbcon0>;
-		id-gpios = <&gpio1 10 GPIO_ACTIVE_HIGH>;
+	port {
+		usb3_dwc: endpoint {
+			remote-endpoint = <&usb_dr_connector>;
+		};
 	};
 };
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw71xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw71xx.dtsi
index bf47b5e9dd8c..0e8d0f3c7ea8 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw71xx.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw71xx.dtsi
@@ -8,6 +8,21 @@
 #include <dt-bindings/phy/phy-imx8-pcie.h>
 
 / {
+	connector {
+		compatible = "gpio-usb-b-connector", "usb-b-connector";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_usbcon1>;
+		type = "micro";
+		label = "Type-C";
+		id-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>;
+
+		port {
+			usb_dr_connector: endpoint {
+				remote-endpoint = <&usb3_dwc>;
+			};
+		};
+	};
+
 	led-controller {
 		compatible = "gpio-leds";
 		pinctrl-names = "default";
@@ -132,13 +147,10 @@
 	role-switch-default-mode = "peripheral";
 	status = "okay";
 
-	connector {
-		compatible = "gpio-usb-b-connector", "usb-b-connector";
-		pinctrl-names = "default";
-		pinctrl-0 = <&pinctrl_usbcon1>;
-		type = "micro";
-		label = "Type-C";
-		id-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>;
+	port {
+		usb3_dwc: endpoint {
+			remote-endpoint = <&usb_dr_connector>;
+		};
 	};
 };
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi
index f942e949084b..c24587c895e1 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi
@@ -8,6 +8,21 @@
 #include <dt-bindings/phy/phy-imx8-pcie.h>
 
 / {
+	connector {
+		compatible = "gpio-usb-b-connector", "usb-b-connector";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_usbcon1>;
+		type = "micro";
+		label = "otg";
+		id-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>;
+
+		port {
+			usb_dr_connector: endpoint {
+				remote-endpoint = <&usb3_dwc>;
+			};
+		};
+	};
+
 	led-controller {
 		compatible = "gpio-leds";
 		pinctrl-names = "default";
@@ -83,8 +98,15 @@
 &ecspi2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_spi2>;
-	cs-gpios = <&gpio5 13 GPIO_ACTIVE_LOW>;
+	cs-gpios = <&gpio5 13 GPIO_ACTIVE_LOW>,
+		   <&gpio1 10 GPIO_ACTIVE_LOW>;
 	status = "okay";
+
+	tpm@1 {
+		compatible = "tcg,tpm_tis-spi";
+		reg = <0x1>;
+		spi-max-frequency = <36000000>;
+	};
 };
 
 &gpio4 {
@@ -175,13 +197,10 @@
 	role-switch-default-mode = "peripheral";
 	status = "okay";
 
-	connector {
-		compatible = "gpio-usb-b-connector", "usb-b-connector";
-		pinctrl-names = "default";
-		pinctrl-0 = <&pinctrl_usbcon1>;
-		type = "micro";
-		label = "otg";
-		id-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>;
+	port {
+		usb3_dwc: endpoint {
+			remote-endpoint = <&usb_dr_connector>;
+		};
 	};
 };
 
@@ -285,6 +304,7 @@
 			MX8MP_IOMUXC_ECSPI2_MOSI__ECSPI2_MOSI	0x140
 			MX8MP_IOMUXC_ECSPI2_MISO__ECSPI2_MISO	0x140
 			MX8MP_IOMUXC_ECSPI2_SS0__GPIO5_IO13	0x140
+			MX8MP_IOMUXC_GPIO1_IO10__GPIO1_IO10	0x140
 		>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi
index b0d42b18c5ce..628ffba69862 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi
@@ -8,6 +8,21 @@
 #include <dt-bindings/phy/phy-imx8-pcie.h>
 
 / {
+	connector {
+		compatible = "gpio-usb-b-connector", "usb-b-connector";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_usbcon1>;
+		type = "micro";
+		label = "otg";
+		id-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>;
+
+		port {
+			usb_dr_connector: endpoint {
+				remote-endpoint = <&usb3_dwc>;
+			};
+		};
+	};
+
 	led-controller {
 		compatible = "gpio-leds";
 		pinctrl-names = "default";
@@ -201,13 +216,10 @@
 	role-switch-default-mode = "peripheral";
 	status = "okay";
 
-	connector {
-		compatible = "gpio-usb-b-connector", "usb-b-connector";
-		pinctrl-names = "default";
-		pinctrl-0 = <&pinctrl_usbcon1>;
-		type = "micro";
-		label = "otg";
-		id-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>;
+	port {
+		usb3_dwc: endpoint {
+			remote-endpoint = <&usb_dr_connector>;
+		};
 	};
 };
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts
index 2ab9f4cc12cc..9caf7ca25444 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts
@@ -35,6 +35,21 @@
 		reg = <0x0 0x40000000 0 0x80000000>;
 	};
 
+	connector {
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_usbcon1>;
+		compatible = "gpio-usb-b-connector", "usb-b-connector";
+		type = "micro";
+		label = "Type-C";
+		id-gpios = <&gpio1 10 GPIO_ACTIVE_HIGH>;
+
+		port {
+			usb_dr_connector: endpoint {
+				remote-endpoint = <&usb3_dwc>;
+			};
+		};
+	};
+
 	gpio-keys {
 		compatible = "gpio-keys";
 
@@ -182,8 +197,6 @@
 
 	tpm@0 {
 		compatible = "tcg,tpm_tis-spi";
-		#address-cells = <0x1>;
-		#size-cells = <0x1>;
 		reg = <0x0>;
 		spi-max-frequency = <36000000>;
 	};
@@ -694,13 +707,10 @@
 	role-switch-default-mode = "peripheral";
 	status = "okay";
 
-	connector {
-		pinctrl-names = "default";
-		pinctrl-0 = <&pinctrl_usbcon1>;
-		compatible = "gpio-usb-b-connector", "usb-b-connector";
-		type = "micro";
-		label = "Type-C";
-		id-gpios = <&gpio1 10 GPIO_ACTIVE_HIGH>;
+	port {
+		usb3_dwc: endpoint {
+			remote-endpoint = <&usb_dr_connector>;
+		};
 	};
 };
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-verdin-mallow.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-verdin-mallow.dtsi
new file mode 100644
index 000000000000..8482393f3cac
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mp-verdin-mallow.dtsi
@@ -0,0 +1,199 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright 2023 Toradex
+ *
+ * Common dtsi for Verdin IMX8MP SoM on Mallow carrier board
+ *
+ * https://www.toradex.com/computer-on-modules/verdin-arm-family/nxp-imx-8m-plus
+ * https://www.toradex.com/products/carrier-board/mallow-carrier-board
+ */
+
+#include <dt-bindings/leds/common.h>
+
+/ {
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_leds>;
+
+		/* SODIMM 52 - USER_LED_1_RED */
+		led-0 {
+			color = <LED_COLOR_ID_RED>;
+			function = LED_FUNCTION_DEBUG;
+			function-enumerator = <1>;
+			gpios = <&gpio3 0 GPIO_ACTIVE_HIGH>;
+		};
+
+		/* SODIMM 54 - USER_LED_1_GREEN */
+		led-1 {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_DEBUG;
+			function-enumerator = <1>;
+			gpios = <&gpio3 1 GPIO_ACTIVE_HIGH>;
+		};
+
+		/* SODIMM 56 - USER_LED_2_RED */
+		led-2 {
+			color = <LED_COLOR_ID_RED>;
+			function = LED_FUNCTION_DEBUG;
+			function-enumerator = <2>;
+			gpios = <&gpio3 6 GPIO_ACTIVE_HIGH>;
+		};
+
+		/* SODIMM 58 - USER_LED_2_GREEN */
+		led-3 {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_DEBUG;
+			function-enumerator = <2>;
+			gpios = <&gpio3 7 GPIO_ACTIVE_HIGH>;
+		};
+	};
+};
+
+&backlight {
+	power-supply = <&reg_3p3v>;
+};
+
+/* Verdin SPI_1 */
+&ecspi1 {
+	pinctrl-0 = <&pinctrl_ecspi1>, <&pinctrl_tpm_cs>;
+	cs-gpios = <&gpio5 9 GPIO_ACTIVE_LOW>, <&gpio3 16 GPIO_ACTIVE_LOW>;
+	status = "okay";
+
+	tpm@1 {
+		compatible = "infineon,slb9670", "tcg,tpm_tis-spi";
+		reg = <1>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_tpm_irq>;
+		interrupt-parent = <&gpio3>;
+		interrupts = <14 IRQ_TYPE_LEVEL_LOW>;
+		spi-max-frequency = <18500000>;
+	};
+};
+
+/* EEPROM on Mallow */
+&eeprom_carrier_board {
+	status = "okay";
+};
+
+/* Verdin ETH_1 */
+&eqos {
+	status = "okay";
+};
+
+/* Verdin CAN_1 */
+&flexcan1 {
+	status = "okay";
+};
+
+/* Verdin CAN_2 */
+&flexcan2 {
+	status = "okay";
+};
+
+/* Temperature sensor on Mallow */
+&hwmon_temp {
+	compatible = "ti,tmp1075";
+	status = "okay";
+};
+
+/* Verdin I2C_2_DSI */
+&i2c2 {
+	status = "okay";
+};
+
+/* Verdin I2C_4_CSI */
+&i2c3 {
+	status = "okay";
+};
+
+/* Verdin I2C_1 */
+&i2c4 {
+	status = "okay";
+};
+
+/* Verdin PCIE_1 */
+&pcie {
+	status = "okay";
+};
+
+&pcie_phy {
+	status = "okay";
+};
+
+/* Verdin PWM_1 */
+&pwm1 {
+	status = "okay";
+};
+
+/* Verdin PWM_2 */
+&pwm2 {
+	status = "okay";
+};
+
+/* Verdin PWM_3_DSI */
+&pwm3 {
+	status = "okay";
+};
+
+&reg_usdhc2_vmmc {
+	vin-supply = <&reg_3p3v>;
+};
+
+/* Verdin UART_1 */
+&uart1 {
+	status = "okay";
+};
+
+/* Verdin UART_2 */
+&uart2 {
+	status = "okay";
+};
+
+/* Verdin UART_3 */
+&uart3 {
+	status = "okay";
+};
+
+/* Verdin USB_1 */
+&usb3_0 {
+	status = "okay";
+};
+
+&usb3_phy0 {
+	status = "okay";
+};
+
+/* Verdin USB_2 */
+&usb3_1 {
+	status = "okay";
+};
+
+&usb3_phy1 {
+	status = "okay";
+};
+
+/* Verdin SD_1 */
+&usdhc2 {
+	status = "okay";
+};
+
+&iomuxc {
+	pinctrl_leds: ledsgrp {
+		fsl,pins =
+			<MX8MP_IOMUXC_NAND_ALE__GPIO3_IO00	0x106>, /* SODIMM 52 */
+			<MX8MP_IOMUXC_NAND_CE0_B__GPIO3_IO01	0x106>, /* SODIMM 54 */
+			<MX8MP_IOMUXC_NAND_DATA00__GPIO3_IO06	0x106>, /* SODIMM 56 */
+			<MX8MP_IOMUXC_NAND_DATA01__GPIO3_IO07	0x106>; /* SODIMM 58 */
+	};
+
+	pinctrl_tpm_cs: tpmcsgrp {
+		fsl,pins =
+			<MX8MP_IOMUXC_NAND_READY_B__GPIO3_IO16	0x82>; /* SODIMM 64 */
+	};
+
+	pinctrl_tpm_irq: tpmirqgrp {
+		fsl,pins =
+			<MX8MP_IOMUXC_NAND_DQS__GPIO3_IO14	0x16>; /* SODIMM 66 */
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-verdin-nonwifi-mallow.dts b/arch/arm64/boot/dts/freescale/imx8mp-verdin-nonwifi-mallow.dts
new file mode 100644
index 000000000000..6a536a4964bb
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mp-verdin-nonwifi-mallow.dts
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright 2023 Toradex
+ */
+
+/dts-v1/;
+
+#include "imx8mp-verdin.dtsi"
+#include "imx8mp-verdin-nonwifi.dtsi"
+#include "imx8mp-verdin-mallow.dtsi"
+
+/ {
+	model = "Toradex Verdin iMX8M Plus on Mallow Board";
+	compatible = "toradex,verdin-imx8mp-nonwifi-mallow",
+		     "toradex,verdin-imx8mp-nonwifi",
+		     "toradex,verdin-imx8mp",
+		     "fsl,imx8mp";
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-verdin-wifi-mallow.dts b/arch/arm64/boot/dts/freescale/imx8mp-verdin-wifi-mallow.dts
new file mode 100644
index 000000000000..08b7aef3fdde
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mp-verdin-wifi-mallow.dts
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright 2023 Toradex
+ */
+
+/dts-v1/;
+
+#include "imx8mp-verdin.dtsi"
+#include "imx8mp-verdin-wifi.dtsi"
+#include "imx8mp-verdin-mallow.dtsi"
+
+/ {
+	model = "Toradex Verdin iMX8M Plus WB on Mallow Board";
+	compatible = "toradex,verdin-imx8mp-wifi-mallow",
+		     "toradex,verdin-imx8mp-wifi",
+		     "toradex,verdin-imx8mp",
+		     "fsl,imx8mp";
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi
index 04f2083c4ab2..c3305f0d4001 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi
@@ -45,6 +45,23 @@
 		status = "disabled";
 	};
 
+	connector {
+		compatible = "gpio-usb-b-connector", "usb-b-connector";
+		id-gpios = <&gpio2 10 GPIO_ACTIVE_HIGH>;
+		label = "Type-C";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_usb_1_id>;
+		self-powered;
+		type = "micro";
+		vbus-supply = <&reg_usb1_vbus>;
+
+		port {
+			usb_dr_connector: endpoint {
+				remote-endpoint = <&usb3_dwc>;
+			};
+		};
+	};
+
 	gpio-keys {
 		compatible = "gpio-keys";
 		pinctrl-names = "default";
@@ -835,15 +852,10 @@
 	srp-disable;
 	usb-role-switch;
 
-	connector {
-		compatible = "gpio-usb-b-connector", "usb-b-connector";
-		id-gpios = <&gpio2 10 GPIO_ACTIVE_HIGH>;
-		label = "Type-C";
-		pinctrl-names = "default";
-		pinctrl-0 = <&pinctrl_usb_1_id>;
-		self-powered;
-		type = "micro";
-		vbus-supply = <&reg_usb1_vbus>;
+	port {
+		usb3_dwc: endpoint {
+			remote-endpoint = <&usb_dr_connector>;
+		};
 	};
 };
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index c9a610ba4836..76c73daf546b 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -264,6 +264,7 @@
 		dsp_reserved: dsp@92400000 {
 			reg = <0 0x92400000 0 0x2000000>;
 			no-map;
+			status = "disabled";
 		};
 	};
 
@@ -726,6 +727,8 @@
 			clk: clock-controller@30380000 {
 				compatible = "fsl,imx8mp-ccm";
 				reg = <0x30380000 0x10000>;
+				interrupts = <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
 				#clock-cells = <1>;
 				clocks = <&osc_32k>, <&osc_24m>, <&clk_ext1>, <&clk_ext2>,
 					 <&clk_ext3>, <&clk_ext4>;
@@ -793,8 +796,8 @@
 							 <&clk IMX8MP_CLK_AUDIO_AXI>;
 						assigned-clocks = <&clk IMX8MP_CLK_AUDIO_AHB>,
 								  <&clk IMX8MP_CLK_AUDIO_AXI_SRC>;
-						assigned-clock-parents =  <&clk IMX8MP_SYS_PLL1_800M>,
-									  <&clk IMX8MP_SYS_PLL1_800M>;
+						assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>,
+									 <&clk IMX8MP_SYS_PLL1_800M>;
 						assigned-clock-rates = <400000000>,
 								       <600000000>;
 					};
@@ -887,6 +890,15 @@
 						clocks = <&clk IMX8MP_CLK_ML_AXI>,
 							 <&clk IMX8MP_CLK_ML_AHB>,
 							 <&clk IMX8MP_CLK_NPU_ROOT>;
+						assigned-clocks = <&clk IMX8MP_CLK_ML_CORE>,
+								  <&clk IMX8MP_CLK_ML_AXI>,
+								  <&clk IMX8MP_CLK_ML_AHB>;
+						assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>,
+									 <&clk IMX8MP_SYS_PLL1_800M>,
+									 <&clk IMX8MP_SYS_PLL1_800M>;
+						assigned-clock-rates = <800000000>,
+								       <800000000>,
+								       <300000000>;
 					};
 				};
 			};
@@ -2012,6 +2024,18 @@
 			interconnect-names = "g1", "g2", "vc8000e";
 		};
 
+		npu: npu@38500000 {
+			compatible = "vivante,gc";
+			reg = <0x38500000 0x200000>;
+			interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk IMX8MP_CLK_NPU_ROOT>,
+				 <&clk IMX8MP_CLK_NPU_ROOT>,
+				 <&clk IMX8MP_CLK_ML_AXI>,
+				 <&clk IMX8MP_CLK_ML_AHB>;
+			clock-names = "core", "shader", "bus", "reg";
+			power-domains = <&pgc_mlmix>;
+		};
+
 		gic: interrupt-controller@38800000 {
 			compatible = "arm,gic-v3";
 			reg = <0x38800000 0x10000>,
@@ -2072,6 +2096,7 @@
 				phys = <&usb3_phy0>, <&usb3_phy0>;
 				phy-names = "usb2-phy", "usb3-phy";
 				snps,gfladj-refclk-lpm-sel-quirk;
+				snps,parkmode-disable-ss-quirk;
 			};
 
 		};
@@ -2114,6 +2139,7 @@
 				phys = <&usb3_phy1>, <&usb3_phy1>;
 				phy-names = "usb2-phy", "usb3-phy";
 				snps,gfladj-refclk-lpm-sel-quirk;
+				snps,parkmode-disable-ss-quirk;
 			};
 		};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mq-phanbell.dts b/arch/arm64/boot/dts/freescale/imx8mq-phanbell.dts
index a3b9d615a3b4..e34045d10a12 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq-phanbell.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mq-phanbell.dts
@@ -39,7 +39,7 @@
 
 	fan: gpio-fan {
 		compatible = "gpio-fan";
-		gpio-fan,speed-map = <0 0 8600 1>;
+		gpio-fan,speed-map = <0 0>, <8600 1>;
 		gpios = <&gpio3 5 GPIO_ACTIVE_HIGH>;
 		#cooling-cells = <2>;
 		pinctrl-names = "default";
diff --git a/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq-mba8mx.dts b/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq-mba8mx.dts
index 0d8def2766f5..b302daca4ce6 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq-mba8mx.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq-mba8mx.dts
@@ -11,6 +11,7 @@
 / {
 	model = "TQ-Systems GmbH i.MX8MQ TQMa8MQ on MBa8Mx";
 	compatible = "tq,imx8mq-tqma8mq-mba8mx", "tq,imx8mq-tqma8mq", "fsl,imx8mq";
+	chassis-type = "embedded";
 
 	aliases {
 		eeprom0 = &eeprom3;
diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
index 4b1ce9fc1758..c6dc3ba0d43b 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
@@ -1649,6 +1649,7 @@
 			phys = <&usb3_phy0>, <&usb3_phy0>;
 			phy-names = "usb2-phy", "usb3-phy";
 			power-domains = <&pgc_otg1>;
+			snps,parkmode-disable-ss-quirk;
 			status = "disabled";
 		};
 
@@ -1680,6 +1681,7 @@
 			phys = <&usb3_phy1>, <&usb3_phy1>;
 			phy-names = "usb2-phy", "usb3-phy";
 			power-domains = <&pgc_otg2>;
+			snps,parkmode-disable-ss-quirk;
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi b/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi
index 01539df335f8..69cb8676732e 100644
--- a/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi
@@ -96,6 +96,17 @@
 	status = "okay";
 };
 
+&edma3 {
+	power-domains = <&pd IMX_SC_R_DMA_1_CH0>,
+		     <&pd IMX_SC_R_DMA_1_CH1>,
+		     <&pd IMX_SC_R_DMA_1_CH2>,
+		     <&pd IMX_SC_R_DMA_1_CH3>,
+		     <&pd IMX_SC_R_DMA_1_CH4>,
+		     <&pd IMX_SC_R_DMA_1_CH5>,
+		     <&pd IMX_SC_R_DMA_1_CH6>,
+		     <&pd IMX_SC_R_DMA_1_CH7>;
+};
+
 &flexcan1 {
 	fsl,clk-source = /bits/ 8 <1>;
 };
@@ -117,21 +128,25 @@
 &lpuart0 {
 	compatible = "fsl,imx8qm-lpuart", "fsl,imx8qxp-lpuart";
 	dmas = <&edma2 13 0 0>, <&edma2 12 0 1>;
+	dma-names = "rx","tx";
 };
 
 &lpuart1 {
 	compatible = "fsl,imx8qm-lpuart", "fsl,imx8qxp-lpuart";
 	dmas = <&edma2 15 0 0>, <&edma2 14 0 1>;
+	dma-names = "rx","tx";
 };
 
 &lpuart2 {
 	compatible = "fsl,imx8qm-lpuart", "fsl,imx8qxp-lpuart";
 	dmas = <&edma2 17 0 0>, <&edma2 16 0 1>;
+	dma-names = "rx","tx";
 };
 
 &lpuart3 {
 	compatible = "fsl,imx8qm-lpuart", "fsl,imx8qxp-lpuart";
 	dmas = <&edma2 19 0 0>, <&edma2 18 0 1>;
+	dma-names = "rx","tx";
 };
 
 &i2c0 {
diff --git a/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts b/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts
index 99611729943c..8360bb851ac0 100644
--- a/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts
+++ b/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts
@@ -31,7 +31,7 @@
 	};
 
 	gpio-sbu-mux {
-		compatible = "gpio-sbu-mux";
+		compatible = "nxp,cbdtu02043", "gpio-sbu-mux";
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_typec_mux>;
 		select-gpios = <&lsio_gpio5 9 GPIO_ACTIVE_HIGH>;
@@ -50,6 +50,10 @@
 	status = "okay";
 };
 
+&dsp_reserved {
+	status = "okay";
+};
+
 &fec1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_fec1>;
@@ -152,12 +156,6 @@
 		interrupt-parent = <&lsio_gpio1>;
 		interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
 
-		port {
-			typec_dr_sw: endpoint {
-				remote-endpoint = <&usb3_drd_sw>;
-			};
-		};
-
 		usb_con1: connector {
 			compatible = "usb-c-connector";
 			label = "USB-C";
@@ -169,8 +167,17 @@
 				#address-cells = <1>;
 				#size-cells = <0>;
 
+				port@0 {
+					reg = <0>;
+
+					typec_dr_sw: endpoint {
+						remote-endpoint = <&usb3_drd_sw>;
+					};
+				};
+
 				port@1 {
 					reg = <1>;
+
 					typec_con_ss: endpoint {
 						remote-endpoint = <&usb3_data_ss>;
 					};
diff --git a/arch/arm64/boot/dts/freescale/imx8qxp-ss-vpu.dtsi b/arch/arm64/boot/dts/freescale/imx8qxp-ss-vpu.dtsi
new file mode 100644
index 000000000000..7894a3ab26d6
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8qxp-ss-vpu.dtsi
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR X11)
+/*
+ * Copyright 2023 TQ-Systems GmbH <linux@ew.tq-group.com>,
+ * D-82229 Seefeld, Germany.
+ * Author: Alexander Stein
+ */
+
+&vpu_core0 {
+	reg = <0x2d040000 0x10000>;
+};
+
+&vpu_core1 {
+	reg = <0x2d050000 0x10000>;
+};
+
+/delete-node/ &mu2_m0;
+/delete-node/ &vpu_core2;
diff --git a/arch/arm64/boot/dts/freescale/imx8qxp.dtsi b/arch/arm64/boot/dts/freescale/imx8qxp.dtsi
index c80c85a4b405..958267b33340 100644
--- a/arch/arm64/boot/dts/freescale/imx8qxp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8qxp.dtsi
@@ -48,7 +48,6 @@
 		serial3 = &lpuart3;
 		vpu-core0 = &vpu_core0;
 		vpu-core1 = &vpu_core1;
-		vpu-core2 = &vpu_core2;
 	};
 
 	cpus {
@@ -184,6 +183,7 @@
 		dsp_reserved: dsp@92400000 {
 			reg = <0 0x92400000 0 0x2000000>;
 			no-map;
+			status = "disabled";
 		};
 
 		encoder_rpc: encoder-rpc@94400000 {
@@ -317,6 +317,7 @@
 };
 
 #include "imx8qxp-ss-img.dtsi"
+#include "imx8qxp-ss-vpu.dtsi"
 #include "imx8qxp-ss-adma.dtsi"
 #include "imx8qxp-ss-conn.dtsi"
 #include "imx8qxp-ss-lsio.dtsi"
diff --git a/arch/arm64/boot/dts/freescale/imx8ulp.dtsi b/arch/arm64/boot/dts/freescale/imx8ulp.dtsi
index f22c1ac391c9..c4a0082f30d3 100644
--- a/arch/arm64/boot/dts/freescale/imx8ulp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8ulp.dtsi
@@ -483,7 +483,7 @@
 			};
 		};
 
-		gpioe: gpio@2d000080 {
+		gpioe: gpio@2d000000 {
 				compatible = "fsl,imx8ulp-gpio";
 				reg = <0x2d000000 0x1000>;
 				gpio-controller;
@@ -498,7 +498,7 @@
 				gpio-ranges = <&iomuxc1 0 32 24>;
 		};
 
-		gpiof: gpio@2d010080 {
+		gpiof: gpio@2d010000 {
 				compatible = "fsl,imx8ulp-gpio";
 				reg = <0x2d010000 0x1000>;
 				gpio-controller;
@@ -534,7 +534,7 @@
 			};
 		};
 
-		gpiod: gpio@2e200080 {
+		gpiod: gpio@2e200000 {
 			compatible = "fsl,imx8ulp-gpio";
 			reg = <0x2e200000 0x1000>;
 			gpio-controller;
diff --git a/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts b/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts
index 2b9d47716f75..9921ea13ab48 100644
--- a/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts
@@ -76,6 +76,7 @@
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 		gpio = <&gpio3 7 GPIO_ACTIVE_HIGH>;
+		off-on-delay-us = <12000>;
 		enable-active-high;
 	};
 };
@@ -237,18 +238,19 @@
 		>;
 	};
 
+	/* need to config the SION for data and cmd pad, refer to ERR052021 */
 	pinctrl_usdhc1: usdhc1grp {
 		fsl,pins = <
 			MX93_PAD_SD1_CLK__USDHC1_CLK		0x15fe
-			MX93_PAD_SD1_CMD__USDHC1_CMD		0x13fe
-			MX93_PAD_SD1_DATA0__USDHC1_DATA0	0x13fe
-			MX93_PAD_SD1_DATA1__USDHC1_DATA1	0x13fe
-			MX93_PAD_SD1_DATA2__USDHC1_DATA2	0x13fe
-			MX93_PAD_SD1_DATA3__USDHC1_DATA3	0x13fe
-			MX93_PAD_SD1_DATA4__USDHC1_DATA4	0x13fe
-			MX93_PAD_SD1_DATA5__USDHC1_DATA5	0x13fe
-			MX93_PAD_SD1_DATA6__USDHC1_DATA6	0x13fe
-			MX93_PAD_SD1_DATA7__USDHC1_DATA7	0x13fe
+			MX93_PAD_SD1_CMD__USDHC1_CMD		0x400013fe
+			MX93_PAD_SD1_DATA0__USDHC1_DATA0	0x400013fe
+			MX93_PAD_SD1_DATA1__USDHC1_DATA1	0x400013fe
+			MX93_PAD_SD1_DATA2__USDHC1_DATA2	0x400013fe
+			MX93_PAD_SD1_DATA3__USDHC1_DATA3	0x400013fe
+			MX93_PAD_SD1_DATA4__USDHC1_DATA4	0x400013fe
+			MX93_PAD_SD1_DATA5__USDHC1_DATA5	0x400013fe
+			MX93_PAD_SD1_DATA6__USDHC1_DATA6	0x400013fe
+			MX93_PAD_SD1_DATA7__USDHC1_DATA7	0x400013fe
 			MX93_PAD_SD1_STROBE__USDHC1_STROBE	0x15fe
 		>;
 	};
@@ -265,14 +267,15 @@
 		>;
 	};
 
+	/* need to config the SION for data and cmd pad, refer to ERR052021 */
 	pinctrl_usdhc2: usdhc2grp {
 		fsl,pins = <
 			MX93_PAD_SD2_CLK__USDHC2_CLK		0x15fe
-			MX93_PAD_SD2_CMD__USDHC2_CMD		0x13fe
-			MX93_PAD_SD2_DATA0__USDHC2_DATA0	0x13fe
-			MX93_PAD_SD2_DATA1__USDHC2_DATA1	0x13fe
-			MX93_PAD_SD2_DATA2__USDHC2_DATA2	0x13fe
-			MX93_PAD_SD2_DATA3__USDHC2_DATA3	0x13fe
+			MX93_PAD_SD2_CMD__USDHC2_CMD		0x400013fe
+			MX93_PAD_SD2_DATA0__USDHC2_DATA0	0x400013fe
+			MX93_PAD_SD2_DATA1__USDHC2_DATA1	0x400013fe
+			MX93_PAD_SD2_DATA2__USDHC2_DATA2	0x400013fe
+			MX93_PAD_SD2_DATA3__USDHC2_DATA3	0x400013fe
 			MX93_PAD_SD2_VSELECT__USDHC2_VSELECT	0x51e
 		>;
 	};
diff --git a/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxca.dts b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxca.dts
new file mode 100644
index 000000000000..af795ecf678b
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxca.dts
@@ -0,0 +1,709 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR MIT)
+/*
+ * Copyright (c) 2022-2023 TQ-Systems GmbH <linux@ew.tq-group.com>,
+ * D-82229 Seefeld, Germany.
+ * Author: Markus Niebel
+ * Author: Alexander Stein
+ */
+/dts-v1/;
+
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/net/ti-dp83867.h>
+#include <dt-bindings/pwm/pwm.h>
+
+#include "imx93-tqma9352.dtsi"
+
+/{
+	model = "TQ-Systems i.MX93 TQMa93xxLA/TQMa93xxCA on MBa93xxCA starter kit";
+	compatible = "tq,imx93-tqma9352-mba93xxca",
+		     "tq,imx93-tqma9352", "fsl,imx93";
+	chassis-type = "embedded";
+
+	chosen {
+		stdout-path = &lpuart1;
+	};
+
+	aliases {
+		eeprom0 = &eeprom0;
+		rtc0 = &pcf85063;
+		rtc1 = &bbnsm_rtc;
+	};
+
+	backlight_lvds: backlight {
+		compatible = "pwm-backlight";
+		pwms = <&tpm5 0 5000000 0>;
+		brightness-levels = <0 4 8 16 32 64 128 255>;
+		default-brightness-level = <7>;
+		power-supply = <&reg_12v0>;
+		enable-gpios = <&expander2 2 GPIO_ACTIVE_HIGH>;
+		status = "disabled";
+	};
+
+	fan0: pwm-fan {
+		compatible = "pwm-fan";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_pwmfan>;
+		fan-supply = <&reg_pwm_fan>;
+		#cooling-cells = <2>;
+		/* typical 25 kHz -> 40.000 nsec */
+		pwms = <&tpm6 0 40000 PWM_POLARITY_INVERTED>;
+		cooling-levels = <0 32 64 128 196 240>;
+		pulses-per-revolution = <2>;
+		interrupt-parent = <&gpio2>;
+		interrupts = <9 IRQ_TYPE_EDGE_FALLING>;
+		status = "disabled";
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		autorepeat;
+
+		switch-a {
+			label = "switcha";
+			linux,code = <BTN_0>;
+			gpios = <&expander0 6 GPIO_ACTIVE_LOW>;
+			wakeup-source;
+		};
+
+		switch-b {
+			label = "switchb";
+			linux,code = <BTN_1>;
+			gpios = <&expander0 7 GPIO_ACTIVE_LOW>;
+			wakeup-source;
+		};
+	};
+
+	gpio-leds {
+		compatible = "gpio-leds";
+
+		led-1 {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_STATUS;
+			gpios = <&expander2 6 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "default-on";
+		};
+
+		led-2 {
+			color = <LED_COLOR_ID_AMBER>;
+			function = LED_FUNCTION_HEARTBEAT;
+			gpios = <&expander2 7 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "heartbeat";
+		};
+	};
+
+	iio-hwmon {
+		compatible = "iio-hwmon";
+		io-channels = <&adc1 0>, <&adc1 1>, <&adc1 2>, <&adc1 3>;
+	};
+
+	reg_3v3: regulator-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "V_3V3_MB";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
+	reg_5v0: regulator-5v0 {
+		compatible = "regulator-fixed";
+		regulator-name = "V_5V0_MB";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
+	reg_12v0: regulator-12v0 {
+		compatible = "regulator-fixed";
+		regulator-name = "V_12V";
+		regulator-min-microvolt = <12000000>;
+		regulator-max-microvolt = <12000000>;
+		gpio = <&expander1 7 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	reg_mpcie_1v5: regulator-mpcie-1v5 {
+		compatible = "regulator-fixed";
+		regulator-name = "V_1V5_MPCIE";
+		regulator-min-microvolt = <1500000>;
+		regulator-max-microvolt = <1500000>;
+		gpio = <&expander0 2 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	reg_mpcie_3v3: regulator-mpcie-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "V_3V3_MPCIE";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&expander0 3 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	reg_pwm_fan: regulator-pwm-fan {
+		compatible = "regulator-fixed";
+		regulator-name = "FAN_PWR";
+		regulator-min-microvolt = <12000000>;
+		regulator-max-microvolt = <12000000>;
+		gpio = <&expander0 0 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&reg_12v0>;
+	};
+
+	thermal-zones {
+		cpu-thermal {
+			trips {
+				cpu_active0: trip-active0 {
+					temperature = <40000>;
+					hysteresis = <5000>;
+					type = "active";
+				};
+
+				cpu_active1: trip-active1 {
+					temperature = <48000>;
+					hysteresis = <3000>;
+					type = "active";
+				};
+
+				cpu_active2: trip-active2 {
+					temperature = <60000>;
+					hysteresis = <10000>;
+					type = "active";
+				};
+			};
+
+			cooling-maps {
+				map1 {
+					trip = <&cpu_active0>;
+					cooling-device = <&fan0 1 1>;
+				};
+
+				map2 {
+					trip = <&cpu_active1>;
+					cooling-device = <&fan0 2 2>;
+				};
+
+				map3 {
+					trip = <&cpu_active2>;
+					cooling-device = <&fan0 3 3>;
+				};
+			};
+		};
+	};
+};
+
+&adc1 {
+	status = "okay";
+};
+
+&eqos {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_eqos>;
+	phy-mode = "rgmii-id";
+	phy-handle = <&ethphy_eqos>;
+	status = "okay";
+
+	mdio {
+		compatible = "snps,dwmac-mdio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		ethphy_eqos: ethernet-phy@0 {
+			compatible = "ethernet-phy-ieee802.3-c22";
+			reg = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_eqos_phy>;
+			reset-gpios = <&expander1 0 GPIO_ACTIVE_LOW>;
+			reset-assert-us = <500000>;
+			reset-deassert-us = <50000>;
+			interrupt-parent = <&gpio3>;
+			interrupts = <26 IRQ_TYPE_EDGE_FALLING>;
+			enet-phy-lane-no-swap;
+			ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_25_NS>;
+			ti,tx-internal-delay = <DP83867_RGMIIDCTL_2_25_NS>;
+			ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_4_B_NIB>;
+			ti,dp83867-rxctrl-strap-quirk;
+			ti,clk-output-sel = <DP83867_CLK_O_SEL_OFF>;
+		};
+	};
+};
+
+&fec {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_fec>;
+	phy-mode = "rgmii-id";
+	phy-handle = <&ethphy_fec>;
+	fsl,magic-packet;
+	status = "okay";
+
+	mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		clock-frequency = <5000000>;
+
+		ethphy_fec: ethernet-phy@0 {
+			compatible = "ethernet-phy-ieee802.3-c22";
+			reg = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_fec_phy>;
+			reset-gpios = <&expander1 1 GPIO_ACTIVE_LOW>;
+			reset-assert-us = <500000>;
+			reset-deassert-us = <50000>;
+			interrupt-parent = <&gpio3>;
+			interrupts = <27 IRQ_TYPE_EDGE_FALLING>;
+			enet-phy-lane-no-swap;
+			ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_25_NS>;
+			ti,tx-internal-delay = <DP83867_RGMIIDCTL_2_25_NS>;
+			ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_4_B_NIB>;
+			ti,dp83867-rxctrl-strap-quirk;
+			ti,clk-output-sel = <DP83867_CLK_O_SEL_OFF>;
+		};
+	};
+};
+
+&flexcan1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_flexcan1>;
+	xceiver-supply = <&reg_3v3>;
+	status = "okay";
+};
+
+&flexcan2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_flexcan2>;
+	xceiver-supply = <&reg_3v3>;
+	status = "okay";
+};
+
+&gpio1 {
+	expander-irq-hog {
+		gpio-hog;
+		gpios = <12 GPIO_ACTIVE_LOW>;
+		input;
+		line-name = "PEX_INT#";
+	};
+
+	tcpc-irq-hog {
+		gpio-hog;
+		gpios = <2 GPIO_ACTIVE_LOW>;
+		input;
+		line-name = "USB_C_ALERT#";
+	};
+};
+
+&lpi2c3 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	clock-frequency = <400000>;
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&pinctrl_lpi2c3>;
+	pinctrl-1 = <&pinctrl_lpi2c3>;
+	status = "okay";
+
+	temperature-sensor@1c {
+		compatible = "nxp,se97b", "jedec,jc-42.4-temp";
+		reg = <0x1c>;
+	};
+
+	eeprom2: eeprom@54 {
+		compatible = "nxp,se97b", "atmel,24c02";
+		reg = <0x54>;
+		pagesize = <16>;
+		vcc-supply = <&reg_3v3>;
+	};
+
+	expander0: gpio@70 {
+		compatible = "nxp,pca9538";
+		reg = <0x70>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_pexp_irq>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		interrupt-parent = <&gpio1>;
+		interrupts = <12 IRQ_TYPE_LEVEL_LOW>;
+		vcc-supply = <&reg_3v3>;
+		gpio-line-names = "FAN_PWR_EN", "MPCIE_WAKE#",
+				  "MPCIE_1V5_EN", "MPCIE_3V3_EN",
+				  "MPCIE_PERST#", "MPCIE_WDISABLE#",
+				  "BUTTON_A#", "BUTTON_B#";
+
+		mpcie-wake-hog {
+			gpio-hog;
+			gpios = <1 GPIO_ACTIVE_LOW>;
+			input;
+			line-name = "MPCIE_WAKE#";
+		};
+
+		/*
+		 * Controls the mPCIE slot reset which is low active as
+		 * reset signal. The output-low states, the signal is
+		 * inactive, e.g. not in reset
+		 */
+		mpcie_rst_hog: mpcie-rst-hog {
+			gpio-hog;
+			gpios = <4 GPIO_ACTIVE_LOW>;
+			output-low;
+			line-name = "MPCIE_PERST#";
+		};
+
+		/*
+		 * Controls the mPCIE slot WDISABLE pin which is low active
+		 * as disable signal. The output-low states, the signal is
+		 * inactive, e.g. not disabled
+		 */
+		mpcie_wdisable_hog: mpcie-wdisable-hog {
+			gpio-hog;
+			gpios = <5 GPIO_ACTIVE_LOW>;
+			output-low;
+			line-name = "MPCIE_WDISABLE#";
+		};
+	};
+
+	expander1: gpio@71 {
+		compatible = "nxp,pca9538";
+		reg = <0x71>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		vcc-supply = <&reg_3v3>;
+		gpio-line-names = "ENET1_RESET#", "ENET2_RESET#",
+				  "USB_RESET#", "",
+				  "WLAN_PD#", "WLAN_W_DISABLE#",
+				  "WLAN_PERST#", "12V_EN";
+
+		/*
+		 * Controls the on board USB Hub reset which is low
+		 * active as reset signal. The output-low states, the
+		 * signal is inactive, e.g. no reset
+		 */
+		usb-reset-hog {
+			gpio-hog;
+			gpios = <2 GPIO_ACTIVE_LOW>;
+			output-low;
+			line-name = "USB_RESET#";
+		};
+
+		/*
+		 * Controls the WiFi card PD pin which is low active
+		 * as power down signal. The output-high states, the signal
+		 * is active, e.g. card is powered down
+		 */
+		wlan-pd-hog {
+			gpio-hog;
+			gpios = <4 GPIO_ACTIVE_LOW>;
+			output-high;
+			line-name = "WLAN_PD#";
+		};
+
+		/*
+		 * Controls the WiFi card disable pin which is low active
+		 * as disable signal. The output-high states, the signal
+		 * is active, e.g. card is disabled
+		 */
+		wlan-wdisable-hog {
+			gpio-hog;
+			gpios = <5 GPIO_ACTIVE_LOW>;
+			output-high;
+			line-name = "WLAN_W_DISABLE#";
+		};
+
+		/*
+		 * Controls the WiFi card reset pin which is low active
+		 * as reset signal. The output-high states, the signal
+		 * is active, e.g. card in reset
+		 */
+		wlan-perst-hog {
+			gpio-hog;
+			gpios = <6 GPIO_ACTIVE_LOW>;
+			output-high;
+			line-name = "WLAN_PERST#";
+		};
+	};
+
+	expander2: gpio@72 {
+		compatible = "nxp,pca9538";
+		reg = <0x72>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		vcc-supply = <&reg_3v3>;
+		gpio-line-names = "LCD_RESET#", "LCD_PWR_EN",
+				  "LCD_BLT_EN", "DP_EN",
+				  "MIPI_CSI_EN", "MIPI_CSI_RST#",
+				  "USER_LED1", "USER_LED2";
+	};
+};
+
+&lpi2c5 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	clock-frequency = <400000>;
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&pinctrl_lpi2c5>;
+	pinctrl-1 = <&pinctrl_lpi2c5>;
+	status = "okay";
+};
+
+&lpspi6 {
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&pinctrl_lpspi6>;
+	pinctrl-1 = <&pinctrl_lpspi6>;
+	status = "okay";
+};
+
+&lpuart1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart1>;
+	status = "okay";
+};
+
+&lpuart2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart2>;
+	linux,rs485-enabled-at-boot-time;
+	status = "okay";
+};
+
+/* disabled per default, console for M33 */
+&lpuart3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart3>;
+	status = "disabled";
+};
+
+&lpuart6 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart6>;
+	status = "okay";
+};
+
+&lpuart8 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart8>;
+	status = "okay";
+};
+
+&tpm5 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_tpm5>;
+};
+
+&tpm6 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_tpm6>;
+	status = "okay";
+};
+
+&usdhc2 {
+	pinctrl-names = "default", "state_100mhz", "state_200mhz";
+	pinctrl-0 = <&pinctrl_usdhc2_hs>, <&pinctrl_usdhc2_gpio>;
+	pinctrl-1 = <&pinctrl_usdhc2_uhs>, <&pinctrl_usdhc2_gpio>;
+	pinctrl-2 = <&pinctrl_usdhc2_uhs>, <&pinctrl_usdhc2_gpio>;
+	cd-gpios = <&gpio3 0 GPIO_ACTIVE_LOW>;
+	vmmc-supply = <&reg_usdhc2_vmmc>;
+	bus-width = <4>;
+	no-sdio;
+	no-mmc;
+	disable-wp;
+	status = "okay";
+};
+
+&iomuxc {
+	pinctrl_eqos: eqosgrp {
+		fsl,pins = <
+			/* PD | FSEL_2 | DSE X4 */
+			MX93_PAD_ENET1_MDC__ENET_QOS_MDC		0x51e
+			MX93_PAD_ENET1_MDIO__ENET_QOS_MDIO		0x4000051e
+			/* PD | FSEL_2 | DSE X6 */
+			MX93_PAD_ENET1_RD0__ENET_QOS_RGMII_RD0		0x57e
+			MX93_PAD_ENET1_RD1__ENET_QOS_RGMII_RD1		0x57e
+			MX93_PAD_ENET1_RD2__ENET_QOS_RGMII_RD2		0x57e
+			MX93_PAD_ENET1_RD3__ENET_QOS_RGMII_RD3		0x57e
+			/* PD | FSEL_3 | DSE X6 */
+			MX93_PAD_ENET1_RXC__CCM_ENET_QOS_CLOCK_GENERATE_RX_CLK	0x5fe
+			MX93_PAD_ENET1_RX_CTL__ENET_QOS_RGMII_RX_CTL	0x57e
+			/* PD | FSEL_2 | DSE X4 */
+			MX93_PAD_ENET1_TD0__ENET_QOS_RGMII_TD0		0x51e
+			MX93_PAD_ENET1_TD1__ENET_QOS_RGMII_TD1		0x51e
+			MX93_PAD_ENET1_TD2__ENET_QOS_RGMII_TD2		0x51e
+			MX93_PAD_ENET1_TD3__ENET_QOS_RGMII_TD3		0x51e
+			MX93_PAD_ENET1_TX_CTL__ENET_QOS_RGMII_TX_CTL	0x51e
+			/* PD | FSEL_3 | DSE X3 */
+			MX93_PAD_ENET1_TXC__CCM_ENET_QOS_CLOCK_GENERATE_TX_CLK	0x58e
+		>;
+	};
+
+	pinctrl_eqos_phy: eqosphygrp {
+		fsl,pins = <
+			MX93_PAD_CCM_CLKO1__GPIO3_IO26		0x1306
+		>;
+	};
+
+	pinctrl_fec: fecgrp {
+		fsl,pins = <
+			/* PD | FSEL_2 | DSE X4 */
+			MX93_PAD_ENET2_MDC__ENET1_MDC			0x51e
+			MX93_PAD_ENET2_MDIO__ENET1_MDIO			0x4000051e
+			/* PD | FSEL_2 | DSE X6 */
+			MX93_PAD_ENET2_RD0__ENET1_RGMII_RD0		0x57e
+			MX93_PAD_ENET2_RD1__ENET1_RGMII_RD1		0x57e
+			MX93_PAD_ENET2_RD2__ENET1_RGMII_RD2		0x57e
+			MX93_PAD_ENET2_RD3__ENET1_RGMII_RD3		0x57e
+			/* PD | FSEL_3 | DSE X6 */
+			MX93_PAD_ENET2_RXC__ENET1_RGMII_RXC		0x5fe
+			MX93_PAD_ENET2_RX_CTL__ENET1_RGMII_RX_CTL	0x57e
+			/* PD | FSEL_2 | DSE X4 */
+			MX93_PAD_ENET2_TD0__ENET1_RGMII_TD0		0x51e
+			MX93_PAD_ENET2_TD1__ENET1_RGMII_TD1		0x51e
+			MX93_PAD_ENET2_TD2__ENET1_RGMII_TD2		0x51e
+			MX93_PAD_ENET2_TD3__ENET1_RGMII_TD3		0x51e
+			MX93_PAD_ENET2_TX_CTL__ENET1_RGMII_TX_CTL	0x51e
+			/* PD | FSEL_3 | DSE X3 */
+			MX93_PAD_ENET2_TXC__ENET1_RGMII_TXC		0x58e
+		>;
+	};
+
+	pinctrl_fec_phy: fecphygrp {
+		fsl,pins = <
+			MX93_PAD_CCM_CLKO2__GPIO3_IO27		0x1306
+		>;
+	};
+
+	pinctrl_flexcan1: flexcan1grp {
+		fsl,pins = <
+			MX93_PAD_PDM_BIT_STREAM0__CAN1_RX	0x139e
+			MX93_PAD_PDM_CLK__CAN1_TX		0x139e
+		>;
+	};
+
+	pinctrl_flexcan2: flexcan2grp {
+		fsl,pins = <
+			MX93_PAD_GPIO_IO25__CAN2_TX		0x139e
+			MX93_PAD_GPIO_IO27__CAN2_RX		0x139e
+		>;
+	};
+
+	pinctrl_lpi2c3: lpi2c3grp {
+		fsl,pins = <
+			MX93_PAD_GPIO_IO28__LPI2C3_SDA		0x40000b9e
+			MX93_PAD_GPIO_IO29__LPI2C3_SCL		0x40000b9e
+		>;
+	};
+
+	pinctrl_lpi2c5: lpi2c5grp {
+		fsl,pins = <
+			MX93_PAD_GPIO_IO22__LPI2C5_SDA		0x40000b9e
+			MX93_PAD_GPIO_IO23__LPI2C5_SCL		0x40000b9e
+		>;
+	};
+
+	pinctrl_lpspi6: lpspi6grp {
+		fsl,pins = <
+			MX93_PAD_GPIO_IO00__LPSPI6_PCS0		0x3fe
+			MX93_PAD_GPIO_IO01__LPSPI6_SIN		0x3fe
+			MX93_PAD_GPIO_IO02__LPSPI6_SOUT		0x3fe
+			MX93_PAD_GPIO_IO03__LPSPI6_SCK		0x3fe
+		>;
+	};
+
+	pinctrl_pexp_irq: pexpirqgrp {
+		fsl,pins = <
+			MX93_PAD_SAI1_TXC__GPIO1_IO12		0x1306
+		>;
+	};
+
+	pinctrl_pwmfan: pwmfangrp {
+		fsl,pins = <
+			MX93_PAD_GPIO_IO09__GPIO2_IO09		0x1306
+		>;
+	};
+
+	pinctrl_tpm5: tpm5grp {
+		fsl,pins = <
+			MX93_PAD_GPIO_IO06__TPM5_CH0		0x57e
+		>;
+	};
+
+	pinctrl_tpm6: tpm6grp {
+		fsl,pins = <
+			MX93_PAD_GPIO_IO08__TPM6_CH0		0x57e
+		>;
+	};
+
+	pinctrl_typec: typecgrp {
+		fsl,pins = <
+			MX93_PAD_I2C2_SCL__GPIO1_IO02		0x1306
+		>;
+	};
+
+	pinctrl_uart1: uart1grp {
+		fsl,pins = <
+			MX93_PAD_UART1_RXD__LPUART1_RX		0x31e
+			MX93_PAD_UART1_TXD__LPUART1_TX		0x31e
+		>;
+	};
+
+	pinctrl_uart2: uart2grp {
+		fsl,pins = <
+			MX93_PAD_UART2_TXD__LPUART2_TX		0x31e
+			MX93_PAD_UART2_RXD__LPUART2_RX		0x31e
+			MX93_PAD_SAI1_TXD0__LPUART2_RTS_B   0x51e
+		>;
+	};
+
+	pinctrl_uart3: uart3grp {
+		fsl,pins = <
+			MX93_PAD_GPIO_IO14__LPUART3_TX		0x31e
+			MX93_PAD_GPIO_IO15__LPUART3_RX		0x31e
+		>;
+	};
+
+	pinctrl_uart6: uart6grp {
+		fsl,pins = <
+			MX93_PAD_GPIO_IO04__LPUART6_TX		0x31e
+			MX93_PAD_GPIO_IO05__LPUART6_RX		0x31e
+		>;
+	};
+
+	pinctrl_uart8: uart8grp {
+		fsl,pins = <
+			MX93_PAD_GPIO_IO12__LPUART8_TX		0x31e
+			MX93_PAD_GPIO_IO13__LPUART8_RX		0x31e
+		>;
+	};
+
+	pinctrl_usdhc2_gpio: usdhc2gpiogrp {
+		fsl,pins = <
+			MX93_PAD_SD2_CD_B__GPIO3_IO00		0x31e
+		>;
+	};
+
+	pinctrl_usdhc2_hs: usdhc2hsgrp {
+		fsl,pins = <
+			/* HYS | PD | PU | FSEL_3 | DSE X5 */
+			MX93_PAD_SD2_CLK__USDHC2_CLK		0x17be
+			/* HYS | PD | PU | FSEL_3 | DSE X4 */
+			MX93_PAD_SD2_CMD__USDHC2_CMD		0x139e
+			/* HYS | PD | PU | FSEL_3 | DSE X3 */
+			MX93_PAD_SD2_DATA0__USDHC2_DATA0	0x138e
+			MX93_PAD_SD2_DATA1__USDHC2_DATA1	0x138e
+			MX93_PAD_SD2_DATA2__USDHC2_DATA2	0x138e
+			MX93_PAD_SD2_DATA3__USDHC2_DATA3	0x138e
+			/* PD | PU | FSEL_2 | DSE X3 */
+			MX93_PAD_SD2_VSELECT__USDHC2_VSELECT	0x50e
+		>;
+	};
+
+	pinctrl_usdhc2_uhs: usdhc2uhsgrp {
+		fsl,pins = <
+			/* HYS | PD | PU | FSEL_3 | DSE X6 */
+			MX93_PAD_SD2_CLK__USDHC2_CLK		0x17fe
+			/* HYS | PD | PU | FSEL_3 | DSE X4 */
+			MX93_PAD_SD2_CMD__USDHC2_CMD		0x139e
+			MX93_PAD_SD2_DATA0__USDHC2_DATA0	0x139e
+			MX93_PAD_SD2_DATA1__USDHC2_DATA1	0x139e
+			MX93_PAD_SD2_DATA2__USDHC2_DATA2	0x139e
+			MX93_PAD_SD2_DATA3__USDHC2_DATA3	0x139e
+			/* PD | PU | FSEL_2 | DSE X3 */
+			MX93_PAD_SD2_VSELECT__USDHC2_VSELECT	0x50e
+		>;
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts
index f06139bdff97..eb3f4cfb6986 100644
--- a/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts
+++ b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts
@@ -18,6 +18,7 @@
 	model = "TQ-Systems i.MX93 TQMa93xxLA on MBa93xxLA SBC";
 	compatible = "tq,imx93-tqma9352-mba93xxla",
 		     "tq,imx93-tqma9352", "fsl,imx93";
+	chassis-type = "embedded";
 
 	chosen {
 		stdout-path = &lpuart1;
@@ -577,7 +578,7 @@
 		fsl,pins = <
 			MX93_PAD_UART2_TXD__LPUART2_TX		0x31e
 			MX93_PAD_UART2_RXD__LPUART2_RX		0x31e
-			MX93_PAD_SAI1_TXD0__LPUART2_RTS_B	0x31e
+			MX93_PAD_SAI1_TXD0__LPUART2_RTS_B	0x51e
 		>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx93.dtsi b/arch/arm64/boot/dts/freescale/imx93.dtsi
index ceccf4766440..8f2e7c42ad6e 100644
--- a/arch/arm64/boot/dts/freescale/imx93.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx93.dtsi
@@ -171,6 +171,18 @@
 		status = "disabled";
 	};
 
+	mqs1: mqs1 {
+		compatible = "fsl,imx93-mqs";
+		gpr = <&aonmix_ns_gpr>;
+		status = "disabled";
+	};
+
+	mqs2: mqs2 {
+		compatible = "fsl,imx93-mqs";
+		gpr = <&wakeupmix_gpr>;
+		status = "disabled";
+	};
+
 	soc@0 {
 		compatible = "simple-bus";
 		#address-cells = <1>;
@@ -282,6 +294,19 @@
 				status = "disabled";
 			};
 
+			i3c1: i3c-master@44330000 {
+				compatible = "silvaco,i3c-master-v1";
+				reg = <0x44330000 0x10000>;
+				interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>;
+				#address-cells = <3>;
+				#size-cells = <0>;
+				clocks = <&clk IMX93_CLK_BUS_AON>,
+					 <&clk IMX93_CLK_I3C1_GATE>,
+					 <&clk IMX93_CLK_I3C1_SLOW>;
+				clock-names = "pclk", "fast_clk", "slow_clk";
+				status = "disabled";
+			};
+
 			lpi2c1: i2c@44340000 {
 				compatible = "fsl,imx93-lpi2c", "fsl,imx7ulp-lpi2c";
 				reg = <0x44340000 0x10000>;
@@ -367,6 +392,19 @@
 				status = "disabled";
 			};
 
+			sai1: sai@443b0000 {
+				compatible = "fsl,imx93-sai";
+				reg = <0x443b0000 0x10000>;
+				interrupts = <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clk IMX93_CLK_SAI1_IPG>, <&clk IMX93_CLK_DUMMY>,
+					 <&clk IMX93_CLK_SAI1_GATE>, <&clk IMX93_CLK_DUMMY>,
+					 <&clk IMX93_CLK_DUMMY>;
+				clock-names = "bus", "mclk0", "mclk1", "mclk2", "mclk3";
+				dmas = <&edma1 22 0 1>, <&edma1 21 0 0>;
+				dma-names = "rx", "tx";
+				status = "disabled";
+			};
+
 			iomuxc: pinctrl@443c0000 {
 				compatible = "fsl,imx93-iomuxc";
 				reg = <0x443c0000 0x10000>;
@@ -395,6 +433,8 @@
 				#clock-cells = <1>;
 				clocks = <&osc_32k>, <&osc_24m>, <&clk_ext1>;
 				clock-names = "osc_32k", "osc_24m", "clk_ext1";
+				assigned-clocks = <&clk IMX93_CLK_AUDIO_PLL>;
+				assigned-clock-rates = <393216000>;
 				status = "okay";
 			};
 
@@ -417,14 +457,15 @@
 					compatible = "fsl,imx93-src-slice";
 					reg = <0x44462400 0x400>, <0x44465800 0x400>;
 					#power-domain-cells = <0>;
-					clocks = <&clk IMX93_CLK_MEDIA_AXI>,
+					clocks = <&clk IMX93_CLK_NIC_MEDIA_GATE>,
 						 <&clk IMX93_CLK_MEDIA_APB>;
 				};
 			};
 
-			anatop: anatop@44480000 {
-				compatible = "fsl,imx93-anatop", "syscon";
+			clock-controller@44480000 {
+				compatible = "fsl,imx93-anatop";
 				reg = <0x44480000 0x2000>;
+				#clock-cells = <1>;
 			};
 
 			tmu: tmu@44482000 {
@@ -447,6 +488,21 @@
 				#thermal-sensor-cells = <1>;
 			};
 
+			micfil: micfil@44520000 {
+				compatible = "fsl,imx93-micfil";
+				reg = <0x44520000 0x10000>;
+				interrupts = <GIC_SPI 202 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 201 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 200 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 199 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clk IMX93_CLK_PDM_IPG>,
+					 <&clk IMX93_CLK_PDM_GATE>,
+					 <&clk IMX93_CLK_AUDIO_PLL>;
+				clock-names = "ipg_clk", "ipg_clk_app", "pll8k";
+				dmas = <&edma1 29 0 5>;
+				dma-names = "rx";
+				status = "disabled";
+			};
 
 			adc1: adc@44530000 {
 				compatible = "nxp,imx93-adc";
@@ -473,7 +529,6 @@
 				compatible = "fsl,imx93-edma4";
 				reg = <0x42000000 0x210000>;
 				#dma-cells = <3>;
-				shared-interrupt;
 				dma-channels = <64>;
 				interrupts = <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>,
@@ -616,6 +671,19 @@
 				status = "disabled";
 			};
 
+			i3c2: i3c-master@42520000 {
+				compatible = "silvaco,i3c-master-v1";
+				reg = <0x42520000 0x10000>;
+				interrupts = <GIC_SPI 61 IRQ_TYPE_LEVEL_HIGH>;
+				#address-cells = <3>;
+				#size-cells = <0>;
+				clocks = <&clk IMX93_CLK_BUS_WAKEUP>,
+					 <&clk IMX93_CLK_I3C2_GATE>,
+					 <&clk IMX93_CLK_I3C2_SLOW>;
+				clock-names = "pclk", "fast_clk", "slow_clk";
+				status = "disabled";
+			};
+
 			lpi2c3: i2c@42530000 {
 				compatible = "fsl,imx93-lpi2c", "fsl,imx7ulp-lpi2c";
 				reg = <0x42530000 0x10000>;
@@ -738,6 +806,51 @@
 				status = "disabled";
 			};
 
+			sai2: sai@42650000 {
+				compatible = "fsl,imx93-sai";
+				reg = <0x42650000 0x10000>;
+				interrupts = <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clk IMX93_CLK_SAI2_IPG>, <&clk IMX93_CLK_DUMMY>,
+					 <&clk IMX93_CLK_SAI2_GATE>, <&clk IMX93_CLK_DUMMY>,
+					 <&clk IMX93_CLK_DUMMY>;
+				clock-names = "bus", "mclk0", "mclk1", "mclk2", "mclk3";
+				dmas = <&edma2 59 0 1>, <&edma2 58 0 0>;
+				dma-names = "rx", "tx";
+				status = "disabled";
+			};
+
+			sai3: sai@42660000 {
+				compatible = "fsl,imx93-sai";
+				reg = <0x42660000 0x10000>;
+				interrupts = <GIC_SPI 171 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clk IMX93_CLK_SAI3_IPG>, <&clk IMX93_CLK_DUMMY>,
+					 <&clk IMX93_CLK_SAI3_GATE>, <&clk IMX93_CLK_DUMMY>,
+					 <&clk IMX93_CLK_DUMMY>;
+				clock-names = "bus", "mclk0", "mclk1", "mclk2", "mclk3";
+				dmas = <&edma2 61 0 1>, <&edma2 60 0 0>;
+				dma-names = "rx", "tx";
+				status = "disabled";
+			};
+
+			xcvr: xcvr@42680000 {
+				compatible = "fsl,imx93-xcvr";
+				reg = <0x42680000 0x800>,
+				      <0x42680800 0x400>,
+				      <0x42680c00 0x080>,
+				      <0x42680e00 0x080>;
+				reg-names = "ram", "regs", "rxfifo", "txfifo";
+				interrupts = <GIC_SPI 203 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 204 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clk IMX93_CLK_BUS_WAKEUP>,
+					 <&clk IMX93_CLK_SPDIF_GATE>,
+					 <&clk IMX93_CLK_DUMMY>,
+					 <&clk IMX93_CLK_AUD_XCVR_GATE>;
+				clock-names = "ipg", "phy", "spba", "pll_ipg";
+				dmas = <&edma2 65 0 1>, <&edma2 66 0 0>;
+				dma-names = "rx", "tx";
+				status = "disabled";
+			};
+
 			lpuart7: serial@42690000 {
 				compatible = "fsl,imx93-lpuart", "fsl,imx8ulp-lpuart", "fsl,imx7ulp-lpuart";
 				reg = <0x42690000 0x1000>;
@@ -755,7 +868,7 @@
 				interrupts = <GIC_SPI 211 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX93_CLK_LPUART8_GATE>;
 				clock-names = "ipg";
-				dmas =  <&edma2 90 0 1>, <&edma2 89 0 0>;
+				dmas = <&edma2 90 0 1>, <&edma2 89 0 0>;
 				dma-names = "rx", "tx";
 				status = "disabled";
 			};
@@ -874,7 +987,7 @@
 					 <&clk IMX93_CLK_USDHC1_GATE>;
 				clock-names = "ipg", "ahb", "per";
 				bus-width = <8>;
-				fsl,tuning-start-tap = <20>;
+				fsl,tuning-start-tap = <1>;
 				fsl,tuning-step = <2>;
 				status = "disabled";
 			};
@@ -888,7 +1001,7 @@
 					 <&clk IMX93_CLK_USDHC2_GATE>;
 				clock-names = "ipg", "ahb", "per";
 				bus-width = <4>;
-				fsl,tuning-start-tap = <20>;
+				fsl,tuning-start-tap = <1>;
 				fsl,tuning-step = <2>;
 				status = "disabled";
 			};
@@ -951,13 +1064,13 @@
 					 <&clk IMX93_CLK_USDHC3_GATE>;
 				clock-names = "ipg", "ahb", "per";
 				bus-width = <4>;
-				fsl,tuning-start-tap = <20>;
+				fsl,tuning-start-tap = <1>;
 				fsl,tuning-step = <2>;
 				status = "disabled";
 			};
 		};
 
-		gpio2: gpio@43810080 {
+		gpio2: gpio@43810000 {
 			compatible = "fsl,imx93-gpio", "fsl,imx8ulp-gpio";
 			reg = <0x43810000 0x1000>;
 			gpio-controller;
@@ -972,7 +1085,7 @@
 			gpio-ranges = <&iomuxc 0 4 30>;
 		};
 
-		gpio3: gpio@43820080 {
+		gpio3: gpio@43820000 {
 			compatible = "fsl,imx93-gpio", "fsl,imx8ulp-gpio";
 			reg = <0x43820000 0x1000>;
 			gpio-controller;
@@ -988,7 +1101,7 @@
 				      <&iomuxc 26 34 2>, <&iomuxc 28 0 4>;
 		};
 
-		gpio4: gpio@43830080 {
+		gpio4: gpio@43830000 {
 			compatible = "fsl,imx93-gpio", "fsl,imx8ulp-gpio";
 			reg = <0x43830000 0x1000>;
 			gpio-controller;
@@ -1003,7 +1116,7 @@
 			gpio-ranges = <&iomuxc 0 38 28>, <&iomuxc 28 36 2>;
 		};
 
-		gpio1: gpio@47400080 {
+		gpio1: gpio@47400000 {
 			compatible = "fsl,imx93-gpio", "fsl,imx8ulp-gpio";
 			reg = <0x47400000 0x1000>;
 			gpio-controller;
diff --git a/arch/arm64/boot/dts/hisilicon/hikey970-pmic.dtsi b/arch/arm64/boot/dts/hisilicon/hikey970-pmic.dtsi
index 970047f2dabd..299c4ab630e8 100644
--- a/arch/arm64/boot/dts/hisilicon/hikey970-pmic.dtsi
+++ b/arch/arm64/boot/dts/hisilicon/hikey970-pmic.dtsi
@@ -10,10 +10,9 @@
 / {
 	spmi: spmi@fff24000 {
 		compatible = "hisilicon,kirin970-spmi-controller";
+		reg = <0x0 0xfff24000 0x0 0x1000>;
 		#address-cells = <2>;
 		#size-cells = <0>;
-		status = "okay";
-		reg = <0x0 0xfff24000 0x0 0x1000>;
 		hisilicon,spmi-channel = <2>;
 
 		pmic: pmic@0 {
@@ -25,9 +24,6 @@
 			gpios = <&gpio28 0 0>;
 
 			regulators {
-				#address-cells = <1>;
-				#size-cells = <0>;
-
 				ldo3: ldo3 { /* HDMI */
 					regulator-name = "ldo3";
 					regulator-min-microvolt = <1500000>;
diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi b/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi
index d3adb6a130ae..76aafa172eb0 100644
--- a/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi
+++ b/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi
@@ -60,6 +60,25 @@
 		};
 	};
 
+	firmware {
+		svc {
+			compatible = "intel,agilex-svc";
+			method = "smc";
+			memory-region = <&service_reserved>;
+
+			fpga_mgr: fpga-mgr {
+				compatible = "intel,agilex-soc-fpga-mgr";
+			};
+		};
+	};
+
+	fpga-region {
+		compatible = "fpga-region";
+		#address-cells = <0x2>;
+		#size-cells = <0x2>;
+		fpga-mgr = <&fpga_mgr>;
+	};
+
 	pmu {
 		compatible = "arm,armv8-pmuv3";
 		interrupts = <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
@@ -130,7 +149,7 @@
 		compatible = "usb-nop-xceiv";
 	};
 
-	soc {
+	soc@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		compatible = "simple-bus";
@@ -138,13 +157,6 @@
 		interrupt-parent = <&intc>;
 		ranges = <0 0 0 0xffffffff>;
 
-		base_fpga_region {
-			#address-cells = <0x2>;
-			#size-cells = <0x2>;
-			compatible = "fpga-region";
-			fpga-mgr = <&fpga_mgr>;
-		};
-
 		clkmgr: clock-controller@ffd10000 {
 			compatible = "intel,agilex-clkmgr";
 			reg = <0xffd10000 0x1000>;
@@ -368,7 +380,7 @@
 			pinctrl-single,function-mask = <0x0000000f>;
 		};
 
-		pinctrl1: pinconf@ffd13100 {
+		pinctrl1: pinctrl@ffd13100 {
 			compatible = "pinctrl-single";
 			#pinctrl-cells = <1>;
 			reg = <0xffd13100 0x20>;
@@ -659,17 +671,5 @@
 
 			status = "disabled";
 		};
-
-		firmware {
-			svc {
-				compatible = "intel,agilex-svc";
-				method = "smc";
-				memory-region = <&service_reserved>;
-
-				fpga_mgr: fpga-mgr {
-					compatible = "intel,agilex-soc-fpga-mgr";
-				};
-			};
-		};
 	};
 };
diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex5.dtsi b/arch/arm64/boot/dts/intel/socfpga_agilex5.dtsi
index dcdaf7064953..d66d425e45b7 100644
--- a/arch/arm64/boot/dts/intel/socfpga_agilex5.dtsi
+++ b/arch/arm64/boot/dts/intel/socfpga_agilex5.dtsi
@@ -73,7 +73,7 @@
 		ranges;
 		#interrupt-cells = <3>;
 		#address-cells = <2>;
-		#size-cells =<2>;
+		#size-cells = <2>;
 		interrupt-controller;
 		#redistributor-regions = <1>;
 		redistributor-stride = <0x0 0x20000>;
@@ -315,7 +315,7 @@
 			num-cs = <4>;
 			clocks = <&clkmgr AGILEX5_L4_MAIN_CLK>;
 			dmas = <&dmac0 2>, <&dmac0 3>;
-			dma-names ="tx", "rx";
+			dma-names = "tx", "rx";
 			status = "disabled";
 
 		};
diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex_n6000.dts b/arch/arm64/boot/dts/intel/socfpga_agilex_n6000.dts
index 1a32840c74e0..d22de06e9839 100644
--- a/arch/arm64/boot/dts/intel/socfpga_agilex_n6000.dts
+++ b/arch/arm64/boot/dts/intel/socfpga_agilex_n6000.dts
@@ -26,7 +26,7 @@
 		reg = <0 0x80000000 0 0>;
 	};
 
-	soc {
+	soc@0 {
 		bus@80000000 {
 			compatible = "simple-bus";
 			reg = <0x80000000 0x60000000>,
diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts b/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts
index 053690657675..ad99aefeb185 100644
--- a/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts
+++ b/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts
@@ -113,8 +113,6 @@
 		spi-max-frequency = <100000000>;
 
 		m25p,fast-read;
-		cdns,page-size = <256>;
-		cdns,block-size = <16>;
 		cdns,read-delay = <2>;
 		cdns,tshsl-ns = <50>;
 		cdns,tsd2d-ns = <50>;
diff --git a/arch/arm64/boot/dts/intel/socfpga_n5x_socdk.dts b/arch/arm64/boot/dts/intel/socfpga_n5x_socdk.dts
index 5ddfdff37c25..2d70a92c2090 100644
--- a/arch/arm64/boot/dts/intel/socfpga_n5x_socdk.dts
+++ b/arch/arm64/boot/dts/intel/socfpga_n5x_socdk.dts
@@ -25,12 +25,11 @@
 		reg = <0 0x80000000 0 0>;
 	};
 
-	soc {
+	soc@0 {
 		sdram_edac: memory-controller@f87f8000 {
 			compatible = "snps,ddrc-3.80a";
 			reg = <0xf87f8000 0x400>;
 			interrupts = <0 175 4>;
-			status = "okay";
 		};
 	};
 };
@@ -91,8 +90,6 @@
 		spi-max-frequency = <100000000>;
 
 		m25p,fast-read;
-		cdns,page-size = <256>;
-		cdns,block-size = <16>;
 		cdns,read-delay = <2>;
 		cdns,tshsl-ns = <50>;
 		cdns,tsd2d-ns = <50>;
diff --git a/arch/arm64/boot/dts/marvell/Makefile b/arch/arm64/boot/dts/marvell/Makefile
index 79ac09b58a89..99b8cb3c49e1 100644
--- a/arch/arm64/boot/dts/marvell/Makefile
+++ b/arch/arm64/boot/dts/marvell/Makefile
@@ -26,4 +26,5 @@ dtb-$(CONFIG_ARCH_MVEBU) += cn9132-db.dtb
 dtb-$(CONFIG_ARCH_MVEBU) += cn9132-db-B.dtb
 dtb-$(CONFIG_ARCH_MVEBU) += cn9130-crb-A.dtb
 dtb-$(CONFIG_ARCH_MVEBU) += cn9130-crb-B.dtb
+dtb-$(CONFIG_ARCH_MVEBU) += ac5x-rd-carrier-cn9131.dtb
 dtb-$(CONFIG_ARCH_MVEBU) += ac5-98dx35xx-rd.dtb
diff --git a/arch/arm64/boot/dts/marvell/ac5x-rd-carrier-cn9131.dts b/arch/arm64/boot/dts/marvell/ac5x-rd-carrier-cn9131.dts
new file mode 100644
index 000000000000..2a0b07000089
--- /dev/null
+++ b/arch/arm64/boot/dts/marvell/ac5x-rd-carrier-cn9131.dts
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (C) 2023 Marvell International Ltd.
+ *
+ * Device tree for the AC5X RD Type 7 Com Express carrier board,
+ * Utilizing the CN913x COM Express CPU module board.
+ * This specific carrier board in this mode of operation (external)
+ * only maintains a PCIe link with the CPU module,
+ * which does not require any special DTS definitions.
+ *
+ * AC5X RD works here in external mode (switch selectable at the back of the
+ * board), and connect via an external cable a kit
+ * which would allow it to use an external CN9131 CPU COM Express module,
+ * mounted on top of an interposer kit.
+ *
+ * So in this case, once the switch is set to external mode as explained above,
+ * the AC5X RD becomes part of the carrier solution.
+ *
+ * When the board boots in the external CPU mode, the internal CPU is disabled,
+ * and only the switch portion of the SOC acts as a PCIe end-point, Hence there
+ * is no need to describe this internal (disabled CPU) in the device tree.
+ *
+ * There is no CPU booting in this mode on the carrier, only on the
+ * CN9131 COM Express CPU module.
+ * What runs the Linux is the CN9131 on the COM Express CPU module,
+ * And it accesses the switch end-point on the AC5X RD portion of the carrier
+ * via PCIe.
+ */
+
+#include "cn9131-db-comexpress.dtsi"
+#include "ac5x-rd-carrier.dtsi"
+
+/ {
+	model = "Marvell Armada AC5X RD COM EXPRESS type 7 carrier board with CN9131 CPU module";
+	compatible = "marvell,cn9131-ac5x-carrier", "marvell,rd-ac5x-carrier",
+			"marvell,cn9131-cpu-module", "marvell,cn9131",
+			"marvell,armada-ap807-quad", "marvell,armada-ap807";
+
+	memory@0 {
+		device_type = "memory";
+		reg = <0x0 0x0 0x2 0x00000000>;
+	};
+
+};
diff --git a/arch/arm64/boot/dts/marvell/ac5x-rd-carrier.dtsi b/arch/arm64/boot/dts/marvell/ac5x-rd-carrier.dtsi
new file mode 100644
index 000000000000..f98629abb58b
--- /dev/null
+++ b/arch/arm64/boot/dts/marvell/ac5x-rd-carrier.dtsi
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (C) 2023 Marvell International Ltd.
+ *
+ * Device tree for the AC5X RD Type 7 Com Express carrier board,
+ * This specific board in external mode (see below) only maintains
+ * a PCIe link with the COM Express CPU module, which does not
+ * require any special DTS definitions.
+ *
+ * AC5X RD can either work as you would expect, as a complete standalone
+ * box using the internal CPU, or you can move the switch on the back of
+ * the box to "external" mode, and connect via an external cable a kit
+ * which would allow it to use an external CPU COM Express module,
+ * mounted on top of an interposer kit.
+ *
+ * So in this case, once the switch is set to external mode as explained above,
+ * the AC5X RD becomes part of the carrier solution.
+ * This is a development/reference solution, not a full commercial solution,
+ * hence it was designed with the flexibility to be configured in different
+ * modes of operation.
+ *
+ * When the board boots in the external CPU mode, the internal CPU is disabled,
+ * and only the switch portion of the SOC acts as a PCIe end-point, Hence there
+ * is no need to describe this internal (disabled CPU) in the device tree.
+ *
+ * There is no CPU booting in this mode on the carrier,
+ * only on the COM Express CPU module.
+ */
+
+/ {
+	model = "Marvell Armada AC5X RD COM EXPRESS type 7 carrier board";
+	compatible = "marvell,rd-ac5x-carrier";
+
+};
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-espressobin-ultra.dts b/arch/arm64/boot/dts/marvell/armada-3720-espressobin-ultra.dts
index f9abef8dcc94..870bb380a40a 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-espressobin-ultra.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-espressobin-ultra.dts
@@ -126,32 +126,32 @@
 
 	reset-gpios = <&gpiosb 23 GPIO_ACTIVE_LOW>;
 
-	ports {
-		switch0port1: port@1 {
+	ethernet-ports {
+		switch0port1: ethernet-port@1 {
 			reg = <1>;
 			label = "lan0";
 			phy-handle = <&switch0phy0>;
 		};
 
-		switch0port2: port@2 {
+		switch0port2: ethernet-port@2 {
 			reg = <2>;
 			label = "lan1";
 			phy-handle = <&switch0phy1>;
 		};
 
-		switch0port3: port@3 {
+		switch0port3: ethernet-port@3 {
 			reg = <3>;
 			label = "lan2";
 			phy-handle = <&switch0phy2>;
 		};
 
-		switch0port4: port@4 {
+		switch0port4: ethernet-port@4 {
 			reg = <4>;
 			label = "lan3";
 			phy-handle = <&switch0phy3>;
 		};
 
-		switch0port5: port@5 {
+		switch0port5: ethernet-port@5 {
 			reg = <5>;
 			label = "wan";
 			phy-handle = <&extphy>;
@@ -160,7 +160,7 @@
 	};
 
 	mdio {
-		switch0phy3: switch0phy3@14 {
+		switch0phy3: ethernet-phy@14 {
 			reg = <0x14>;
 		};
 	};
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtsi b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtsi
index 49cbdb55b4b3..fed2dcecb323 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtsi
@@ -145,19 +145,17 @@
 };
 
 &mdio {
-	switch0: switch0@1 {
+	switch0: ethernet-switch@1 {
 		compatible = "marvell,mv88e6085";
-		#address-cells = <1>;
-		#size-cells = <0>;
 		reg = <1>;
 
 		dsa,member = <0 0>;
 
-		ports {
+		ethernet-ports {
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			switch0port0: port@0 {
+			switch0port0: ethernet-port@0 {
 				reg = <0>;
 				label = "cpu";
 				ethernet = <&eth0>;
@@ -168,19 +166,19 @@
 				};
 			};
 
-			switch0port1: port@1 {
+			switch0port1: ethernet-port@1 {
 				reg = <1>;
 				label = "wan";
 				phy-handle = <&switch0phy0>;
 			};
 
-			switch0port2: port@2 {
+			switch0port2: ethernet-port@2 {
 				reg = <2>;
 				label = "lan0";
 				phy-handle = <&switch0phy1>;
 			};
 
-			switch0port3: port@3 {
+			switch0port3: ethernet-port@3 {
 				reg = <3>;
 				label = "lan1";
 				phy-handle = <&switch0phy2>;
@@ -192,13 +190,13 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			switch0phy0: switch0phy0@11 {
+			switch0phy0: ethernet-phy@11 {
 				reg = <0x11>;
 			};
-			switch0phy1: switch0phy1@12 {
+			switch0phy1: ethernet-phy@12 {
 				reg = <0x12>;
 			};
-			switch0phy2: switch0phy2@13 {
+			switch0phy2: ethernet-phy@13 {
 				reg = <0x13>;
 			};
 		};
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-gl-mv1000.dts b/arch/arm64/boot/dts/marvell/armada-3720-gl-mv1000.dts
index b1b45b4fa9d4..63fbc8352161 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-gl-mv1000.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-gl-mv1000.dts
@@ -152,31 +152,29 @@
 };
 
 &mdio {
-	switch0: switch0@1 {
+	switch0: ethernet-switch@1 {
 		compatible = "marvell,mv88e6085";
-		#address-cells = <1>;
-		#size-cells = <0>;
 		reg = <1>;
 
 		dsa,member = <0 0>;
 
-		ports: ports {
+		ports: ethernet-ports {
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			port@0 {
+			ethernet-port@0 {
 				reg = <0>;
 				label = "cpu";
 				ethernet = <&eth0>;
 			};
 
-			port@1 {
+			ethernet-port@1 {
 				reg = <1>;
 				label = "wan";
 				phy-handle = <&switch0phy0>;
 			};
 
-			port@2 {
+			ethernet-port@2 {
 				reg = <2>;
 				label = "lan0";
 				phy-handle = <&switch0phy1>;
@@ -185,7 +183,7 @@
 				nvmem-cell-names = "mac-address";
 			};
 
-			port@3 {
+			ethernet-port@3 {
 				reg = <3>;
 				label = "lan1";
 				phy-handle = <&switch0phy2>;
@@ -199,13 +197,13 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			switch0phy0: switch0phy0@11 {
+			switch0phy0: ethernet-phy@11 {
 				reg = <0x11>;
 			};
-			switch0phy1: switch0phy1@12 {
+			switch0phy1: ethernet-phy@12 {
 				reg = <0x12>;
 			};
-			switch0phy2: switch0phy2@13 {
+			switch0phy2: ethernet-phy@13 {
 				reg = <0x13>;
 			};
 		};
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
index 9eab2bb22134..f1a9f2234359 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
@@ -130,7 +130,7 @@
 		compatible = "microchip,mcp7940x";
 		reg = <0x6f>;
 		interrupt-parent = <&gpiosb>;
-		interrupts = <5 0>; /* GPIO2_5 */
+		interrupts = <5 IRQ_TYPE_EDGE_FALLING>; /* GPIO2_5 */
 	};
 };
 
@@ -304,9 +304,15 @@
 		reg = <1>;
 	};
 
-	/* switch nodes are enabled by U-Boot if modules are present */
+	/*
+	 * NOTE: switch nodes are enabled by U-Boot if modules are present
+	 * DO NOT change this node name (switch0@10) even if it is not following
+	 * conventions! Deployed U-Boot binaries are explicitly looking for
+	 * this node in order to augment the device tree!
+	 * Also do not touch the "ports" or "port@n" nodes. These are also ABI.
+	 */
 	switch0@10 {
-		compatible = "marvell,mv88e6190";
+		compatible = "marvell,turris-mox-mv88e6190", "marvell,mv88e6190";
 		reg = <0x10>;
 		dsa,member = <0 0>;
 		interrupt-parent = <&moxtet>;
@@ -317,35 +323,35 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			switch0phy1: switch0phy1@1 {
+			switch0phy1: ethernet-phy@1 {
 				reg = <0x1>;
 			};
 
-			switch0phy2: switch0phy2@2 {
+			switch0phy2: ethernet-phy@2 {
 				reg = <0x2>;
 			};
 
-			switch0phy3: switch0phy3@3 {
+			switch0phy3: ethernet-phy@3 {
 				reg = <0x3>;
 			};
 
-			switch0phy4: switch0phy4@4 {
+			switch0phy4: ethernet-phy@4 {
 				reg = <0x4>;
 			};
 
-			switch0phy5: switch0phy5@5 {
+			switch0phy5: ethernet-phy@5 {
 				reg = <0x5>;
 			};
 
-			switch0phy6: switch0phy6@6 {
+			switch0phy6: ethernet-phy@6 {
 				reg = <0x6>;
 			};
 
-			switch0phy7: switch0phy7@7 {
+			switch0phy7: ethernet-phy@7 {
 				reg = <0x7>;
 			};
 
-			switch0phy8: switch0phy8@8 {
+			switch0phy8: ethernet-phy@8 {
 				reg = <0x8>;
 			};
 		};
@@ -430,8 +436,9 @@
 		};
 	};
 
+	/* NOTE: this node name is ABI, don't change it! */
 	switch0@2 {
-		compatible = "marvell,mv88e6085";
+		compatible = "marvell,turris-mox-mv88e6085", "marvell,mv88e6085";
 		reg = <0x2>;
 		dsa,member = <0 0>;
 		interrupt-parent = <&moxtet>;
@@ -442,19 +449,19 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			switch0phy1_topaz: switch0phy1@11 {
+			switch0phy1_topaz: ethernet-phy@11 {
 				reg = <0x11>;
 			};
 
-			switch0phy2_topaz: switch0phy2@12 {
+			switch0phy2_topaz: ethernet-phy@12 {
 				reg = <0x12>;
 			};
 
-			switch0phy3_topaz: switch0phy3@13 {
+			switch0phy3_topaz: ethernet-phy@13 {
 				reg = <0x13>;
 			};
 
-			switch0phy4_topaz: switch0phy4@14 {
+			switch0phy4_topaz: ethernet-phy@14 {
 				reg = <0x14>;
 			};
 		};
@@ -497,8 +504,9 @@
 		};
 	};
 
+	/* NOTE: this node name is ABI, don't change it! */
 	switch1@11 {
-		compatible = "marvell,mv88e6190";
+		compatible = "marvell,turris-mox-mv88e6190", "marvell,mv88e6190";
 		reg = <0x11>;
 		dsa,member = <0 1>;
 		interrupt-parent = <&moxtet>;
@@ -509,35 +517,35 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			switch1phy1: switch1phy1@1 {
+			switch1phy1: ethernet-phy@1 {
 				reg = <0x1>;
 			};
 
-			switch1phy2: switch1phy2@2 {
+			switch1phy2: ethernet-phy@2 {
 				reg = <0x2>;
 			};
 
-			switch1phy3: switch1phy3@3 {
+			switch1phy3: ethernet-phy@3 {
 				reg = <0x3>;
 			};
 
-			switch1phy4: switch1phy4@4 {
+			switch1phy4: ethernet-phy@4 {
 				reg = <0x4>;
 			};
 
-			switch1phy5: switch1phy5@5 {
+			switch1phy5: ethernet-phy@5 {
 				reg = <0x5>;
 			};
 
-			switch1phy6: switch1phy6@6 {
+			switch1phy6: ethernet-phy@6 {
 				reg = <0x6>;
 			};
 
-			switch1phy7: switch1phy7@7 {
+			switch1phy7: ethernet-phy@7 {
 				reg = <0x7>;
 			};
 
-			switch1phy8: switch1phy8@8 {
+			switch1phy8: ethernet-phy@8 {
 				reg = <0x8>;
 			};
 		};
@@ -622,8 +630,9 @@
 		};
 	};
 
+	/* NOTE: this node name is ABI, don't change it! */
 	switch1@2 {
-		compatible = "marvell,mv88e6085";
+		compatible = "marvell,turris-mox-mv88e6085", "marvell,mv88e6085";
 		reg = <0x2>;
 		dsa,member = <0 1>;
 		interrupt-parent = <&moxtet>;
@@ -634,19 +643,19 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			switch1phy1_topaz: switch1phy1@11 {
+			switch1phy1_topaz: ethernet-phy@11 {
 				reg = <0x11>;
 			};
 
-			switch1phy2_topaz: switch1phy2@12 {
+			switch1phy2_topaz: ethernet-phy@12 {
 				reg = <0x12>;
 			};
 
-			switch1phy3_topaz: switch1phy3@13 {
+			switch1phy3_topaz: ethernet-phy@13 {
 				reg = <0x13>;
 			};
 
-			switch1phy4_topaz: switch1phy4@14 {
+			switch1phy4_topaz: ethernet-phy@14 {
 				reg = <0x14>;
 			};
 		};
@@ -689,8 +698,9 @@
 		};
 	};
 
+	/* NOTE: this node name is ABI, don't change it! */
 	switch2@12 {
-		compatible = "marvell,mv88e6190";
+		compatible = "marvell,turris-mox-mv88e6190", "marvell,mv88e6190";
 		reg = <0x12>;
 		dsa,member = <0 2>;
 		interrupt-parent = <&moxtet>;
@@ -701,35 +711,35 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			switch2phy1: switch2phy1@1 {
+			switch2phy1: ethernet-phy@1 {
 				reg = <0x1>;
 			};
 
-			switch2phy2: switch2phy2@2 {
+			switch2phy2: ethernet-phy@2 {
 				reg = <0x2>;
 			};
 
-			switch2phy3: switch2phy3@3 {
+			switch2phy3: ethernet-phy@3 {
 				reg = <0x3>;
 			};
 
-			switch2phy4: switch2phy4@4 {
+			switch2phy4: ethernet-phy@4 {
 				reg = <0x4>;
 			};
 
-			switch2phy5: switch2phy5@5 {
+			switch2phy5: ethernet-phy@5 {
 				reg = <0x5>;
 			};
 
-			switch2phy6: switch2phy6@6 {
+			switch2phy6: ethernet-phy@6 {
 				reg = <0x6>;
 			};
 
-			switch2phy7: switch2phy7@7 {
+			switch2phy7: ethernet-phy@7 {
 				reg = <0x7>;
 			};
 
-			switch2phy8: switch2phy8@8 {
+			switch2phy8: ethernet-phy@8 {
 				reg = <0x8>;
 			};
 		};
@@ -805,8 +815,9 @@
 		};
 	};
 
+	/* NOTE: this node name is ABI, don't change it! */
 	switch2@2 {
-		compatible = "marvell,mv88e6085";
+		compatible = "marvell,turris-mox-mv88e6085", "marvell,mv88e6085";
 		reg = <0x2>;
 		dsa,member = <0 2>;
 		interrupt-parent = <&moxtet>;
@@ -817,19 +828,19 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			switch2phy1_topaz: switch2phy1@11 {
+			switch2phy1_topaz: ethernet-phy@11 {
 				reg = <0x11>;
 			};
 
-			switch2phy2_topaz: switch2phy2@12 {
+			switch2phy2_topaz: ethernet-phy@12 {
 				reg = <0x12>;
 			};
 
-			switch2phy3_topaz: switch2phy3@13 {
+			switch2phy3_topaz: ethernet-phy@13 {
 				reg = <0x13>;
 			};
 
-			switch2phy4_topaz: switch2phy4@14 {
+			switch2phy4_topaz: ethernet-phy@14 {
 				reg = <0x14>;
 			};
 		};
diff --git a/arch/arm64/boot/dts/marvell/armada-7040-mochabin.dts b/arch/arm64/boot/dts/marvell/armada-7040-mochabin.dts
index 48202810bf78..40b7ee7ead72 100644
--- a/arch/arm64/boot/dts/marvell/armada-7040-mochabin.dts
+++ b/arch/arm64/boot/dts/marvell/armada-7040-mochabin.dts
@@ -301,10 +301,8 @@
 	};
 
 	/* 88E6141 Topaz switch */
-	switch: switch@3 {
+	switch: ethernet-switch@3 {
 		compatible = "marvell,mv88e6085";
-		#address-cells = <1>;
-		#size-cells = <0>;
 		reg = <3>;
 
 		pinctrl-names = "default";
@@ -314,35 +312,35 @@
 		interrupt-parent = <&cp0_gpio1>;
 		interrupts = <1 IRQ_TYPE_LEVEL_LOW>;
 
-		ports {
+		ethernet-ports {
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			swport1: port@1 {
+			swport1: ethernet-port@1 {
 				reg = <1>;
 				label = "lan0";
 				phy-handle = <&swphy1>;
 			};
 
-			swport2: port@2 {
+			swport2: ethernet-port@2 {
 				reg = <2>;
 				label = "lan1";
 				phy-handle = <&swphy2>;
 			};
 
-			swport3: port@3 {
+			swport3: ethernet-port@3 {
 				reg = <3>;
 				label = "lan2";
 				phy-handle = <&swphy3>;
 			};
 
-			swport4: port@4 {
+			swport4: ethernet-port@4 {
 				reg = <4>;
 				label = "lan3";
 				phy-handle = <&swphy4>;
 			};
 
-			port@5 {
+			ethernet-port@5 {
 				reg = <5>;
 				label = "cpu";
 				ethernet = <&cp0_eth1>;
@@ -355,19 +353,19 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			swphy1: swphy1@17 {
+			swphy1: ethernet-phy@17 {
 				reg = <17>;
 			};
 
-			swphy2: swphy2@18 {
+			swphy2: ethernet-phy@18 {
 				reg = <18>;
 			};
 
-			swphy3: swphy3@19 {
+			swphy3: ethernet-phy@19 {
 				reg = <19>;
 			};
 
-			swphy4: swphy4@20 {
+			swphy4: ethernet-phy@20 {
 				reg = <20>;
 			};
 		};
diff --git a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
index 4125202028c8..67892f0d2863 100644
--- a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
+++ b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
@@ -497,42 +497,42 @@
 		reset-deassert-us = <10000>;
 	};
 
-	switch0: switch0@4 {
+	switch0: ethernet-switch@4 {
 		compatible = "marvell,mv88e6085";
 		reg = <4>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&cp1_switch_reset_pins>;
 		reset-gpios = <&cp1_gpio1 24 GPIO_ACTIVE_LOW>;
 
-		ports {
+		ethernet-ports {
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			port@1 {
+			ethernet-port@1 {
 				reg = <1>;
 				label = "lan2";
 				phy-handle = <&switch0phy0>;
 			};
 
-			port@2 {
+			ethernet-port@2 {
 				reg = <2>;
 				label = "lan1";
 				phy-handle = <&switch0phy1>;
 			};
 
-			port@3 {
+			ethernet-port@3 {
 				reg = <3>;
 				label = "lan4";
 				phy-handle = <&switch0phy2>;
 			};
 
-			port@4 {
+			ethernet-port@4 {
 				reg = <4>;
 				label = "lan3";
 				phy-handle = <&switch0phy3>;
 			};
 
-			port@5 {
+			ethernet-port@5 {
 				reg = <5>;
 				label = "cpu";
 				ethernet = <&cp1_eth2>;
@@ -545,19 +545,19 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			switch0phy0: switch0phy0@11 {
+			switch0phy0: ethernet-phy@11 {
 				reg = <0x11>;
 			};
 
-			switch0phy1: switch0phy1@12 {
+			switch0phy1: ethernet-phy@12 {
 				reg = <0x12>;
 			};
 
-			switch0phy2: switch0phy2@13 {
+			switch0phy2: ethernet-phy@13 {
 				reg = <0x13>;
 			};
 
-			switch0phy3: switch0phy3@14 {
+			switch0phy3: ethernet-phy@14 {
 				reg = <0x14>;
 			};
 		};
diff --git a/arch/arm64/boot/dts/marvell/cn9130-crb.dtsi b/arch/arm64/boot/dts/marvell/cn9130-crb.dtsi
index 47d45ff3d6f5..6fcc34f7b464 100644
--- a/arch/arm64/boot/dts/marvell/cn9130-crb.dtsi
+++ b/arch/arm64/boot/dts/marvell/cn9130-crb.dtsi
@@ -207,11 +207,9 @@
 		reg = <0>;
 	};
 
-	switch6: switch0@6 {
+	switch6: ethernet-switch@6 {
 		/* Actual device is MV88E6393X */
 		compatible = "marvell,mv88e6190";
-		#address-cells = <1>;
-		#size-cells = <0>;
 		reg = <6>;
 		interrupt-parent = <&cp0_gpio1>;
 		interrupts = <28 IRQ_TYPE_LEVEL_LOW>;
@@ -220,59 +218,59 @@
 
 		dsa,member = <0 0>;
 
-		ports {
+		ethernet-ports {
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			port@1 {
+			ethernet-port@1 {
 				reg = <1>;
 				label = "p1";
 				phy-handle = <&switch0phy1>;
 			};
 
-			port@2 {
+			ethernet-port@2 {
 				reg = <2>;
 				label = "p2";
 				phy-handle = <&switch0phy2>;
 			};
 
-			port@3 {
+			ethernet-port@3 {
 				reg = <3>;
 				label = "p3";
 				phy-handle = <&switch0phy3>;
 			};
 
-			port@4 {
+			ethernet-port@4 {
 				reg = <4>;
 				label = "p4";
 				phy-handle = <&switch0phy4>;
 			};
 
-			port@5 {
+			ethernet-port@5 {
 				reg = <5>;
 				label = "p5";
 				phy-handle = <&switch0phy5>;
 			};
 
-			port@6 {
+			ethernet-port@6 {
 				reg = <6>;
 				label = "p6";
 				phy-handle = <&switch0phy6>;
 			};
 
-			port@7 {
+			ethernet-port@7 {
 				reg = <7>;
 				label = "p7";
 				phy-handle = <&switch0phy7>;
 			};
 
-			port@8 {
+			ethernet-port@8 {
 				reg = <8>;
 				label = "p8";
 				phy-handle = <&switch0phy8>;
 			};
 
-			port@9 {
+			ethernet-port@9 {
 				reg = <9>;
 				label = "p9";
 				phy-mode = "10gbase-r";
@@ -280,7 +278,7 @@
 				managed = "in-band-status";
 			};
 
-			port@a {
+			ethernet-port@a {
 				reg = <10>;
 				ethernet = <&cp0_eth0>;
 				phy-mode = "10gbase-r";
@@ -293,35 +291,35 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			switch0phy1: switch0phy1@1 {
+			switch0phy1: ethernet-phy@1 {
 				reg = <0x1>;
 			};
 
-			switch0phy2: switch0phy2@2 {
+			switch0phy2: ethernet-phy@2 {
 				reg = <0x2>;
 			};
 
-			switch0phy3: switch0phy3@3 {
+			switch0phy3: ethernet-phy@3 {
 				reg = <0x3>;
 			};
 
-			switch0phy4: switch0phy4@4 {
+			switch0phy4: ethernet-phy@4 {
 				reg = <0x4>;
 			};
 
-			switch0phy5: switch0phy5@5 {
+			switch0phy5: ethernet-phy@5 {
 				reg = <0x5>;
 			};
 
-			switch0phy6: switch0phy6@6 {
+			switch0phy6: ethernet-phy@6 {
 				reg = <0x6>;
 			};
 
-			switch0phy7: switch0phy7@7 {
+			switch0phy7: ethernet-phy@7 {
 				reg = <0x7>;
 			};
 
-			switch0phy8: switch0phy8@8 {
+			switch0phy8: ethernet-phy@8 {
 				reg = <0x8>;
 			};
 		};
diff --git a/arch/arm64/boot/dts/marvell/cn9130-db-comexpress.dtsi b/arch/arm64/boot/dts/marvell/cn9130-db-comexpress.dtsi
new file mode 100644
index 000000000000..028496ebc473
--- /dev/null
+++ b/arch/arm64/boot/dts/marvell/cn9130-db-comexpress.dtsi
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (C) 2023 Marvell International Ltd.
+ *
+ * Device tree for the CN9130-DB Com Express CPU module board.
+ */
+
+#include "cn9130-db.dtsi"
+
+/ {
+	model = "Marvell Armada CN9130-DB COM EXPRESS type 7 CPU module board";
+	compatible = "marvell,cn9130-cpu-module", "marvell,cn9130",
+		     "marvell,armada-ap807-quad", "marvell,armada-ap807";
+
+};
+
+&ap0_reg_sd_vccq {
+	regulator-max-microvolt = <1800000>;
+	states = <1800000 0x1 1800000 0x0>;
+	/delete-property/ gpios;
+};
+
+&cp0_reg_usb3_vbus0 {
+	/delete-property/ gpio;
+};
+
+&cp0_reg_usb3_vbus1 {
+	/delete-property/ gpio;
+};
+
+&cp0_reg_sd_vcc {
+	status = "disabled";
+};
+
+&cp0_reg_sd_vccq {
+	status = "disabled";
+};
+
+&cp0_sdhci0 {
+	status = "disabled";
+};
+
+&cp0_eth0 {
+	status = "disabled";
+};
+
+&cp0_eth1 {
+	status = "okay";
+	phy = <&phy0>;
+	phy-mode = "rgmii-id";
+};
+
+&cp0_eth2 {
+	status = "disabled";
+};
+
+&cp0_mdio {
+	status = "okay";
+	pinctrl-0 = <&cp0_ge_mdio_pins>;
+	phy0: ethernet-phy@0 {
+		status = "okay";
+	};
+};
+
+&cp0_syscon0 {
+	cp0_pinctrl: pinctrl {
+		compatible = "marvell,cp115-standalone-pinctrl";
+
+		cp0_ge_mdio_pins: ge-mdio-pins {
+			marvell,pins = "mpp40", "mpp41";
+			marvell,function = "ge";
+		};
+	};
+};
+
+&cp0_sdhci0 {
+	status = "disabled";
+};
+
+&cp0_spi1 {
+	status = "okay";
+};
+
+&cp0_usb3_0 {
+	status = "okay";
+	usb-phy = <&cp0_usb3_0_phy0>;
+	phy-names = "usb";
+	/delete-property/ phys;
+};
+
+&cp0_usb3_1 {
+	status = "okay";
+	usb-phy = <&cp0_usb3_0_phy1>;
+	phy-names = "usb";
+	/delete-property/ phys;
+};
diff --git a/arch/arm64/boot/dts/marvell/cn9131-db-comexpress.dtsi b/arch/arm64/boot/dts/marvell/cn9131-db-comexpress.dtsi
new file mode 100644
index 000000000000..6f3914bcfd01
--- /dev/null
+++ b/arch/arm64/boot/dts/marvell/cn9131-db-comexpress.dtsi
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (C) 2023 Marvell International Ltd.
+ *
+ * Device tree for the CN9131-DB Com Express CPU module board.
+ */
+
+#include "cn9131-db.dtsi"
+
+/ {
+	model = "Marvell Armada CN9131-DB COM EXPRESS type 7 CPU module board";
+	compatible = "marvell,cn9131-cpu-module", "marvell,cn9131", "marvell,cn9130",
+		     "marvell,armada-ap807-quad", "marvell,armada-ap807";
+
+};
+
+&ap0_reg_sd_vccq {
+	regulator-max-microvolt = <1800000>;
+	states = <1800000 0x1 1800000 0x0>;
+	/delete-property/ gpios;
+};
+
+&cp0_reg_usb3_vbus0 {
+	/delete-property/ gpio;
+};
+
+&cp0_reg_usb3_vbus1 {
+	/delete-property/ gpio;
+};
+
+&cp1_reg_usb3_vbus0 {
+	/delete-property/ gpio;
+};
+
+&cp0_reg_sd_vcc {
+	status = "disabled";
+};
+
+&cp0_reg_sd_vccq {
+	status = "disabled";
+};
+
+&cp0_sdhci0 {
+	status = "disabled";
+};
+
+&cp0_eth0 {
+	status = "disabled";
+};
+
+&cp0_eth1 {
+	status = "okay";
+	phy = <&phy0>;
+	phy-mode = "rgmii-id";
+};
+
+&cp0_eth2 {
+	status = "disabled";
+};
+
+&cp0_mdio {
+	status = "okay";
+	pinctrl-0 = <&cp0_ge_mdio_pins>;
+	phy0: ethernet-phy@0 {
+		status = "okay";
+	};
+};
+
+&cp0_syscon0 {
+	cp0_pinctrl: pinctrl {
+		compatible = "marvell,cp115-standalone-pinctrl";
+
+		cp0_ge_mdio_pins: ge-mdio-pins {
+			marvell,pins = "mpp40", "mpp41";
+			marvell,function = "ge";
+		};
+	};
+};
+
+&cp0_sdhci0 {
+	status = "disabled";
+};
+
+&cp0_spi1 {
+	status = "okay";
+};
+
+&cp0_usb3_0 {
+	status = "okay";
+	usb-phy = <&cp0_usb3_0_phy0>;
+	phy-names = "usb";
+	/delete-property/ phys;
+};
+
+&cp0_usb3_1 {
+	status = "okay";
+	usb-phy = <&cp0_usb3_0_phy1>;
+	phy-names = "usb";
+	/delete-property/ phys;
+};
+
+&cp1_usb3_1 {
+	status = "okay";
+	usb-phy = <&cp1_usb3_0_phy0>;
+	/* Generic PHY, providing serdes lanes */
+	phys = <&cp1_comphy3 1>;
+	phy-names = "usb";
+};
diff --git a/arch/arm64/boot/dts/mediatek/Makefile b/arch/arm64/boot/dts/mediatek/Makefile
index e6e7592a3645..1e6f91731e92 100644
--- a/arch/arm64/boot/dts/mediatek/Makefile
+++ b/arch/arm64/boot/dts/mediatek/Makefile
@@ -32,10 +32,16 @@ dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-jacuzzi-fennel14-sku2.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-jacuzzi-juniper-sku16.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-jacuzzi-kappa.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-jacuzzi-kenzo.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-jacuzzi-makomo-sku0.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-jacuzzi-makomo-sku1.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-jacuzzi-pico.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-jacuzzi-pico6.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-jacuzzi-willow-sku0.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-jacuzzi-willow-sku1.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-kakadu.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-kakadu-sku22.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-katsu-sku32.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-katsu-sku38.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-kodama-sku16.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-kodama-sku272.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-kodama-sku288.dtb
@@ -44,6 +50,7 @@ dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-krane-sku0.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-krane-sku176.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-pumpkin.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-evb.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt8188-evb.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8192-asurada-hayato-r1.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8192-asurada-hayato-r5-sku2.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8192-asurada-spherion-r0.dtb
diff --git a/arch/arm64/boot/dts/mediatek/mt6358.dtsi b/arch/arm64/boot/dts/mediatek/mt6358.dtsi
index b605313bed99..a1b96013f814 100644
--- a/arch/arm64/boot/dts/mediatek/mt6358.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt6358.dtsi
@@ -8,8 +8,6 @@
 	pmic: pmic {
 		compatible = "mediatek,mt6358";
 		interrupt-controller;
-		interrupt-parent = <&pio>;
-		interrupts = <182 IRQ_TYPE_LEVEL_HIGH>;
 		#interrupt-cells = <2>;
 
 		mt6358codec: mt6358codec {
@@ -128,7 +126,6 @@
 			};
 
 			mt6358_vrf12_reg: ldo_vrf12 {
-				compatible = "regulator-fixed";
 				regulator-name = "vrf12";
 				regulator-min-microvolt = <1200000>;
 				regulator-max-microvolt = <1200000>;
@@ -136,7 +133,6 @@
 			};
 
 			mt6358_vio18_reg: ldo_vio18 {
-				compatible = "regulator-fixed";
 				regulator-name = "vio18";
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <1800000>;
@@ -153,7 +149,6 @@
 			};
 
 			mt6358_vcamio_reg: ldo_vcamio {
-				compatible = "regulator-fixed";
 				regulator-name = "vcamio";
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <1800000>;
@@ -168,7 +163,6 @@
 			};
 
 			mt6358_vcn18_reg: ldo_vcn18 {
-				compatible = "regulator-fixed";
 				regulator-name = "vcn18";
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <1800000>;
@@ -176,7 +170,6 @@
 			};
 
 			mt6358_vfe28_reg: ldo_vfe28 {
-				compatible = "regulator-fixed";
 				regulator-name = "vfe28";
 				regulator-min-microvolt = <2800000>;
 				regulator-max-microvolt = <2800000>;
@@ -193,7 +186,6 @@
 			};
 
 			mt6358_vcn28_reg: ldo_vcn28 {
-				compatible = "regulator-fixed";
 				regulator-name = "vcn28";
 				regulator-min-microvolt = <2800000>;
 				regulator-max-microvolt = <2800000>;
@@ -218,7 +210,6 @@
 			};
 
 			mt6358_vxo22_reg: ldo_vxo22 {
-				compatible = "regulator-fixed";
 				regulator-name = "vxo22";
 				regulator-min-microvolt = <2200000>;
 				regulator-max-microvolt = <2200000>;
@@ -234,7 +225,6 @@
 			};
 
 			mt6358_vaux18_reg: ldo_vaux18 {
-				compatible = "regulator-fixed";
 				regulator-name = "vaux18";
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <1800000>;
@@ -249,7 +239,6 @@
 			};
 
 			mt6358_vbif28_reg: ldo_vbif28 {
-				compatible = "regulator-fixed";
 				regulator-name = "vbif28";
 				regulator-min-microvolt = <2800000>;
 				regulator-max-microvolt = <2800000>;
@@ -280,7 +269,6 @@
 			};
 
 			mt6358_vio28_reg: ldo_vio28 {
-				compatible = "regulator-fixed";
 				regulator-name = "vio28";
 				regulator-min-microvolt = <2800000>;
 				regulator-max-microvolt = <2800000>;
@@ -288,7 +276,6 @@
 			};
 
 			mt6358_va12_reg: ldo_va12 {
-				compatible = "regulator-fixed";
 				regulator-name = "va12";
 				regulator-min-microvolt = <1200000>;
 				regulator-max-microvolt = <1200000>;
@@ -297,22 +284,14 @@
 			};
 
 			mt6358_vrf18_reg: ldo_vrf18 {
-				compatible = "regulator-fixed";
 				regulator-name = "vrf18";
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <1800000>;
 				regulator-enable-ramp-delay = <120>;
 			};
 
-			mt6358_vcn33_bt_reg: ldo_vcn33_bt {
-				regulator-name = "vcn33_bt";
-				regulator-min-microvolt = <3300000>;
-				regulator-max-microvolt = <3500000>;
-				regulator-enable-ramp-delay = <270>;
-			};
-
-			mt6358_vcn33_wifi_reg: ldo_vcn33_wifi {
-				regulator-name = "vcn33_wifi";
+			mt6358_vcn33_reg: ldo_vcn33 {
+				regulator-name = "vcn33";
 				regulator-min-microvolt = <3300000>;
 				regulator-max-microvolt = <3500000>;
 				regulator-enable-ramp-delay = <270>;
@@ -340,7 +319,6 @@
 			};
 
 			mt6358_vaud28_reg: ldo_vaud28 {
-				compatible = "regulator-fixed";
 				regulator-name = "vaud28";
 				regulator-min-microvolt = <2800000>;
 				regulator-max-microvolt = <2800000>;
diff --git a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts
index 3b7a176b7904..a1f42048dcc7 100644
--- a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts
+++ b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts
@@ -73,7 +73,7 @@
 		};
 	};
 
-	memory {
+	memory@40000000 {
 		reg = <0 0x40000000 0 0x40000000>;
 	};
 
@@ -153,8 +153,7 @@
 			reg = <0>;
 			interrupt-controller;
 			#interrupt-cells = <1>;
-			interrupt-parent = <&pio>;
-			interrupts = <53 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts-extended = <&pio 53 IRQ_TYPE_LEVEL_HIGH>;
 			reset-gpios = <&pio 54 0>;
 
 			ports {
diff --git a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts
index a885a3fbe456..2dc1bdc74e21 100644
--- a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts
+++ b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts
@@ -55,7 +55,7 @@
 		};
 	};
 
-	memory {
+	memory@40000000 {
 		reg = <0 0x40000000 0 0x20000000>;
 	};
 
diff --git a/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts
index af4a4309bda4..d06d4af43cbf 100644
--- a/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts
+++ b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts
@@ -126,6 +126,7 @@
 		compatible = "sff,sfp";
 		i2c-bus = <&i2c_sfp1>;
 		los-gpios = <&pio 46 GPIO_ACTIVE_HIGH>;
+		maximum-power-milliwatt = <3000>;
 		mod-def0-gpios = <&pio 49 GPIO_ACTIVE_LOW>;
 		tx-disable-gpios = <&pio 20 GPIO_ACTIVE_HIGH>;
 		tx-fault-gpios = <&pio 7 GPIO_ACTIVE_HIGH>;
@@ -137,6 +138,7 @@
 		i2c-bus = <&i2c_sfp2>;
 		los-gpios = <&pio 31 GPIO_ACTIVE_HIGH>;
 		mod-def0-gpios = <&pio 47 GPIO_ACTIVE_LOW>;
+		maximum-power-milliwatt = <3000>;
 		tx-disable-gpios = <&pio 15 GPIO_ACTIVE_HIGH>;
 		tx-fault-gpios = <&pio 48 GPIO_ACTIVE_HIGH>;
 	};
@@ -150,16 +152,16 @@
 			trip = <&cpu_trip_active_high>;
 		};
 
-		cpu-active-low {
+		cpu-active-med {
 			/* active: set fan to cooling level 1 */
 			cooling-device = <&fan 1 1>;
-			trip = <&cpu_trip_active_low>;
+			trip = <&cpu_trip_active_med>;
 		};
 
-		cpu-passive {
-			/* passive: set fan to cooling level 0 */
+		cpu-active-low {
+			/* active: set fan to cooling level 0 */
 			cooling-device = <&fan 0 0>;
-			trip = <&cpu_trip_passive>;
+			trip = <&cpu_trip_active_low>;
 		};
 	};
 };
@@ -203,8 +205,7 @@
 		reg = <31>;
 		interrupt-controller;
 		#interrupt-cells = <1>;
-		interrupt-parent = <&pio>;
-		interrupts = <66 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts-extended = <&pio 66 IRQ_TYPE_LEVEL_HIGH>;
 		reset-gpios = <&pio 5 GPIO_ACTIVE_HIGH>;
 	};
 };
diff --git a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi
index 24eda00e320d..fc751e049953 100644
--- a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi
@@ -374,6 +374,10 @@
 			reg = <0 0x11230000 0 0x1000>,
 			      <0 0x11c20000 0 0x1000>;
 			interrupts = <GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>;
+			assigned-clocks = <&topckgen CLK_TOP_EMMC_416M_SEL>,
+					  <&topckgen CLK_TOP_EMMC_250M_SEL>;
+			assigned-clock-parents = <&apmixedsys CLK_APMIXED_MPLL>,
+						 <&topckgen CLK_TOP_NET1PLL_D5_D2>;
 			clocks = <&topckgen CLK_TOP_EMMC_416M_SEL>,
 				 <&infracfg CLK_INFRA_MSDC_HCK_CK>,
 				 <&infracfg CLK_INFRA_MSDC_CK>,
@@ -610,22 +614,34 @@
 			thermal-sensors = <&thermal 0>;
 
 			trips {
+				cpu_trip_crit: crit {
+					temperature = <125000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+
+				cpu_trip_hot: hot {
+					temperature = <120000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
 				cpu_trip_active_high: active-high {
 					temperature = <115000>;
 					hysteresis = <2000>;
 					type = "active";
 				};
 
-				cpu_trip_active_low: active-low {
+				cpu_trip_active_med: active-med {
 					temperature = <85000>;
 					hysteresis = <2000>;
 					type = "active";
 				};
 
-				cpu_trip_passive: passive {
-					temperature = <40000>;
+				cpu_trip_active_low: active-low {
+					temperature = <60000>;
 					hysteresis = <2000>;
-					type = "passive";
+					type = "active";
 				};
 			};
 		};
diff --git a/arch/arm64/boot/dts/mediatek/mt8173-elm-hana.dtsi b/arch/arm64/boot/dts/mediatek/mt8173-elm-hana.dtsi
index bdcd35cecad9..90cbbc18a483 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173-elm-hana.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8173-elm-hana.dtsi
@@ -13,8 +13,7 @@
 	touchscreen2: touchscreen@34 {
 		compatible = "melfas,mip4_ts";
 		reg = <0x34>;
-		interrupt-parent = <&pio>;
-		interrupts = <88 IRQ_TYPE_LEVEL_LOW>;
+		interrupts-extended = <&pio 88 IRQ_TYPE_LEVEL_LOW>;
 	};
 
 	/*
@@ -26,8 +25,7 @@
 		compatible = "hid-over-i2c";
 		reg = <0x20>;
 		hid-descr-addr = <0x0020>;
-		interrupt-parent = <&pio>;
-		interrupts = <88 IRQ_TYPE_LEVEL_LOW>;
+		interrupts-extended = <&pio 88 IRQ_TYPE_LEVEL_LOW>;
 	};
 };
 
@@ -39,8 +37,7 @@
 	 */
 	trackpad2: trackpad@2c {
 		compatible = "hid-over-i2c";
-		interrupt-parent = <&pio>;
-		interrupts = <117 IRQ_TYPE_LEVEL_LOW>;
+		interrupts-extended = <&pio 117 IRQ_TYPE_LEVEL_LOW>;
 		reg = <0x2c>;
 		hid-descr-addr = <0x0020>;
 		wakeup-source;
diff --git a/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi b/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi
index 111495622cac..8d614ac2c58e 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi
@@ -245,8 +245,7 @@
 		reg = <0x1a>;
 		avdd-supply = <&mt6397_vgp1_reg>;
 		cpvdd-supply = <&mt6397_vcama_reg>;
-		interrupt-parent = <&pio>;
-		interrupts = <3 IRQ_TYPE_EDGE_BOTH>;
+		interrupts-extended = <&pio 3 IRQ_TYPE_EDGE_BOTH>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&rt5650_irq>;
 		#sound-dai-cells = <1>;
@@ -308,8 +307,7 @@
 	da9211: da9211@68 {
 		compatible = "dlg,da9211";
 		reg = <0x68>;
-		interrupt-parent = <&pio>;
-		interrupts = <15 IRQ_TYPE_LEVEL_LOW>;
+		interrupts-extended = <&pio 15 IRQ_TYPE_LEVEL_LOW>;
 
 		regulators {
 			da9211_vcpu_reg: BUCKA {
@@ -353,8 +351,7 @@
 	touchscreen: touchscreen@10 {
 		compatible = "elan,ekth3500";
 		reg = <0x10>;
-		interrupt-parent = <&pio>;
-		interrupts = <88 IRQ_TYPE_LEVEL_LOW>;
+		interrupts-extended = <&pio 88 IRQ_TYPE_LEVEL_LOW>;
 	};
 };
 
@@ -366,8 +363,7 @@
 
 	trackpad: trackpad@15 {
 		compatible = "elan,ekth3000";
-		interrupt-parent = <&pio>;
-		interrupts = <117 IRQ_TYPE_LEVEL_LOW>;
+		interrupts-extended = <&pio 117 IRQ_TYPE_LEVEL_LOW>;
 		reg = <0x15>;
 		vcc-supply = <&mt6397_vgp6_reg>;
 		wakeup-source;
@@ -439,8 +435,7 @@
 	btmrvl: btmrvl@2 {
 		compatible = "marvell,sd8897-bt";
 		reg = <2>;
-		interrupt-parent = <&pio>;
-		interrupts = <119 IRQ_TYPE_LEVEL_LOW>;
+		interrupts-extended = <&pio 119 IRQ_TYPE_LEVEL_LOW>;
 		marvell,wakeup-pin = /bits/ 16 <0x0d>;
 		marvell,wakeup-gap-ms = /bits/ 16 <0x64>;
 	};
@@ -448,8 +443,7 @@
 	mwifiex: mwifiex@1 {
 		compatible = "marvell,sd8897";
 		reg = <1>;
-		interrupt-parent = <&pio>;
-		interrupts = <38 IRQ_TYPE_LEVEL_LOW>;
+		interrupts-extended = <&pio 38 IRQ_TYPE_LEVEL_LOW>;
 		marvell,wakeup-pin = <3>;
 	};
 };
@@ -933,8 +927,7 @@
 		compatible = "mediatek,mt6397";
 		#address-cells = <1>;
 		#size-cells = <1>;
-		interrupt-parent = <&pio>;
-		interrupts = <11 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts-extended = <&pio 11 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 
@@ -1160,8 +1153,7 @@
 		compatible = "google,cros-ec-spi";
 		reg = <0x0>;
 		spi-max-frequency = <12000000>;
-		interrupt-parent = <&pio>;
-		interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
+		interrupts-extended = <&pio 0 IRQ_TYPE_LEVEL_LOW>;
 		google,cros-ec-spi-msg-delay = <500>;
 
 		i2c_tunnel: i2c-tunnel0 {
diff --git a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
index 5122963d8743..0e5c628d1ec3 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
@@ -44,7 +44,7 @@
 		id-gpio = <&pio 16 GPIO_ACTIVE_HIGH>;
 	};
 
-	usb_p1_vbus: regulator@0 {
+	usb_p1_vbus: regulator-usb-p1 {
 		compatible = "regulator-fixed";
 		regulator-name = "usb_vbus";
 		regulator-min-microvolt = <5000000>;
@@ -53,7 +53,7 @@
 		enable-active-high;
 	};
 
-	usb_p0_vbus: regulator@1 {
+	usb_p0_vbus: regulator-usb-p0 {
 		compatible = "regulator-fixed";
 		regulator-name = "vbus";
 		regulator-min-microvolt = <5000000>;
@@ -303,8 +303,7 @@
 
 	pmic: pmic {
 		compatible = "mediatek,mt6397";
-		interrupt-parent = <&pio>;
-		interrupts = <11 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts-extended = <&pio 11 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 
diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
index c47d7d900f28..cac4cd0a0320 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
@@ -1368,10 +1368,9 @@
 			#clock-cells = <1>;
 		};
 
-		vcodec_dec: vcodec@16000000 {
+		vcodec_dec: vcodec@16020000 {
 			compatible = "mediatek,mt8173-vcodec-dec";
-			reg = <0 0x16000000 0 0x100>,	/* VDEC_SYS */
-			      <0 0x16020000 0 0x1000>,	/* VDEC_MISC */
+			reg = <0 0x16020000 0 0x1000>,	/* VDEC_MISC */
 			      <0 0x16021000 0 0x800>,	/* VDEC_LD */
 			      <0 0x16021800 0 0x800>,	/* VDEC_TOP */
 			      <0 0x16022000 0 0x1000>,	/* VDEC_CM */
@@ -1382,6 +1381,8 @@
 			      <0 0x16027000 0 0x800>,	/* VDEC_HWQ */
 			      <0 0x16027800 0 0x800>,	/* VDEC_HWB */
 			      <0 0x16028400 0 0x400>;	/* VDEC_HWG */
+			reg-names = "misc", "ld", "top", "cm", "ad", "av", "pp",
+				    "hwd", "hwq", "hwb", "hwg";
 			interrupts = <GIC_SPI 204 IRQ_TYPE_LEVEL_LOW>;
 			iommus = <&iommu M4U_PORT_HW_VDEC_MC_EXT>,
 				 <&iommu M4U_PORT_HW_VDEC_PP_EXT>,
@@ -1392,6 +1393,7 @@
 				 <&iommu M4U_PORT_HW_VDEC_VLD_EXT>,
 				 <&iommu M4U_PORT_HW_VDEC_VLD2_EXT>;
 			mediatek,vpu = <&vpu>;
+			mediatek,vdecsys = <&vdecsys>;
 			power-domains = <&spm MT8173_POWER_DOMAIN_VDEC>;
 			clocks = <&apmixedsys CLK_APMIXED_VCODECPLL>,
 				 <&topckgen CLK_TOP_UNIVPLL_D2>,
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-evb.dts b/arch/arm64/boot/dts/mediatek/mt8183-evb.dts
index ce336a48c897..681deddffc2a 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-evb.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8183-evb.dts
@@ -31,14 +31,14 @@
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
-		scp_mem_reserved: scp_mem_region {
+		scp_mem_reserved: memory@50000000 {
 			compatible = "shared-dma-pool";
 			reg = <0 0x50000000 0 0x2900000>;
 			no-map;
 		};
 	};
 
-	ntc@0 {
+	thermal-sensor {
 		compatible = "murata,ncp03wf104";
 		pullup-uv = <1800000>;
 		pullup-ohm = <390000>;
@@ -381,6 +381,10 @@
 	};
 };
 
+&pmic {
+	interrupts-extended = <&pio 182 IRQ_TYPE_LEVEL_HIGH>;
+};
+
 &mfg {
 	domain-supply = <&mt6358_vgpu_reg>;
 };
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-audio-da7219.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-audio-da7219.dtsi
index 2c69e7658dba..8b57706ac814 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-audio-da7219.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-audio-da7219.dtsi
@@ -11,8 +11,7 @@
 		pinctrl-0 = <&da7219_pins>;
 		compatible = "dlg,da7219";
 		reg = <0x1a>;
-		interrupt-parent = <&pio>;
-		interrupts = <165 IRQ_TYPE_LEVEL_LOW 165 0>;
+		interrupts-extended = <&pio 165 IRQ_TYPE_LEVEL_LOW>;
 
 		dlg,micbias-lvl = <2600>;
 		dlg,mic-amp-in-sel = "diff";
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-audio-ts3a227e.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-audio-ts3a227e.dtsi
index 0799c48ade19..548e22c194a2 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-audio-ts3a227e.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-audio-ts3a227e.dtsi
@@ -11,8 +11,7 @@
 		pinctrl-0 = <&ts3a227e_pins>;
 		compatible = "ti,ts3a227e";
 		reg = <0x3b>;
-		interrupt-parent = <&pio>;
-		interrupts = <157 IRQ_TYPE_LEVEL_LOW>;
+		interrupts-extended = <&pio 157 IRQ_TYPE_LEVEL_LOW>;
 		status = "okay";
 	};
 };
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-damu.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-damu.dts
index 552bfc726999..0b45aee2e299 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-damu.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-damu.dts
@@ -18,8 +18,7 @@
 
 	compatible = "hid-over-i2c";
 	reg = <0x10>;
-	interrupt-parent = <&pio>;
-	interrupts = <155 IRQ_TYPE_LEVEL_LOW>;
+	interrupts-extended = <&pio 155 IRQ_TYPE_LEVEL_LOW>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&touchscreen_pins>;
 
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku1.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku1.dts
index 77b96ddf648e..b595622e7bee 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku1.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku1.dts
@@ -30,8 +30,7 @@
 
 	compatible = "hid-over-i2c";
 	reg = <0x10>;
-	interrupt-parent = <&pio>;
-	interrupts = <155 IRQ_TYPE_LEVEL_LOW>;
+	interrupts-extended = <&pio 155 IRQ_TYPE_LEVEL_LOW>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&touchscreen_pins>;
 
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku6.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku6.dts
index 37e6e58f63b7..5a1c39318a6c 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku6.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku6.dts
@@ -17,8 +17,7 @@
 
 	compatible = "hid-over-i2c";
 	reg = <0x10>;
-	interrupt-parent = <&pio>;
-	interrupts = <155 IRQ_TYPE_LEVEL_LOW>;
+	interrupts-extended = <&pio 155 IRQ_TYPE_LEVEL_LOW>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&touchscreen_pins>;
 
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku7.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku7.dts
index 0e09604004d5..3ea4fdb40118 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku7.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku7.dts
@@ -17,8 +17,7 @@
 
 	compatible = "hid-over-i2c";
 	reg = <0x10>;
-	interrupt-parent = <&pio>;
-	interrupts = <155 IRQ_TYPE_LEVEL_LOW>;
+	interrupts-extended = <&pio 155 IRQ_TYPE_LEVEL_LOW>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&touchscreen_pins>;
 
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-makomo-sku0.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-makomo-sku0.dts
new file mode 100644
index 000000000000..4eb2a0d571af
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-makomo-sku0.dts
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright 2023 Google LLC
+ */
+
+/dts-v1/;
+#include "mt8183-kukui-jacuzzi-fennel.dtsi"
+#include "mt8183-kukui-audio-da7219-rt1015p.dtsi"
+
+/ {
+	model = "Google makomo sku0 board";
+	chassis-type = "laptop";
+	compatible = "google,makomo-sku0", "google,makomo", "mediatek,mt8183";
+};
+
+&qca_wifi {
+	qcom,ath10k-calibration-variant = "GO_FENNEL14";
+};
+
+&mmc1_pins_uhs {
+	pins-clk {
+		drive-strength = <MTK_DRIVE_6mA>;
+	};
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-makomo-sku1.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-makomo-sku1.dts
new file mode 100644
index 000000000000..6a733361e8ae
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-makomo-sku1.dts
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright 2023 Google LLC
+ */
+
+/dts-v1/;
+#include "mt8183-kukui-jacuzzi-fennel.dtsi"
+#include "mt8183-kukui-audio-ts3a227e-rt1015p.dtsi"
+
+/ {
+	model = "Google makomo sku1 board";
+	chassis-type = "laptop";
+	compatible = "google,makomo-sku1", "google,makomo", "mediatek,mt8183";
+};
+
+&qca_wifi {
+	qcom,ath10k-calibration-variant = "GO_FENNEL14";
+};
+
+&mmc1_pins_uhs {
+	pins-clk {
+		drive-strength = <MTK_DRIVE_6mA>;
+	};
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico.dts
new file mode 100644
index 000000000000..8ce9568fee95
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico.dts
@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright 2023 Google LLC
+ */
+
+/dts-v1/;
+#include "mt8183-kukui-jacuzzi.dtsi"
+#include "mt8183-kukui-audio-ts3a227e-max98357a.dtsi"
+
+/ {
+	model = "Google pico board";
+	chassis-type = "convertible";
+	compatible = "google,pico-sku1", "google,pico", "mediatek,mt8183";
+};
+
+&i2c_tunnel {
+	google,remote-bus = <0>;
+};
+
+&i2c2 {
+	i2c-scl-internal-delay-ns = <25000>;
+
+	trackpad@2c {
+		compatible = "hid-over-i2c";
+		reg = <0x2c>;
+		hid-descr-addr = <0x20>;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&trackpad_pins>;
+
+		interrupts-extended = <&pio 7 IRQ_TYPE_LEVEL_LOW>;
+
+		wakeup-source;
+	};
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico6.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico6.dts
new file mode 100644
index 000000000000..a2e74b829320
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico6.dts
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright 2023 Google LLC
+ */
+
+/dts-v1/;
+#include "mt8183-kukui-jacuzzi.dtsi"
+#include "mt8183-kukui-audio-ts3a227e-max98357a.dtsi"
+
+/ {
+	model = "Google pico6 board";
+	chassis-type = "convertible";
+	compatible = "google,pico-sku2", "google,pico", "mediatek,mt8183";
+
+	bt_wakeup: bt-wakeup {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&bt_pins_wakeup>;
+
+		wobt {
+			label = "Wake on BT";
+			gpios = <&pio 42 GPIO_ACTIVE_HIGH>;
+			linux,code = <KEY_WAKEUP>;
+			wakeup-source;
+		};
+	};
+};
+
+&i2c_tunnel {
+	google,remote-bus = <0>;
+};
+
+&i2c2 {
+	i2c-scl-internal-delay-ns = <25000>;
+
+	trackpad@2c {
+		compatible = "hid-over-i2c";
+		reg = <0x2c>;
+		hid-descr-addr = <0x20>;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&trackpad_pins>;
+
+		interrupts-extended = <&pio 7 IRQ_TYPE_LEVEL_LOW>;
+
+		wakeup-source;
+	};
+};
+
+&wifi_wakeup {
+	wowlan {
+		gpios = <&pio 113 GPIO_ACTIVE_LOW>;
+	};
+};
+
+&wifi_pwrseq {
+	post-power-on-delay-ms = <50>;
+
+	/* Toggle WIFI_ENABLE to reset the chip. */
+	reset-gpios = <&pio 8 GPIO_ACTIVE_LOW>;
+};
+
+&wifi_pins_pwrseq {
+	pins-wifi-enable {
+		pinmux = <PINMUX_GPIO8__FUNC_GPIO8>;
+	};
+};
+
+&mmc1_pins_default {
+	pins-cmd-dat {
+		drive-strength = <MTK_DRIVE_6mA>;
+	};
+	pins-clk {
+		drive-strength = <MTK_DRIVE_6mA>;
+	};
+};
+
+&mmc1_pins_uhs {
+	pins-clk {
+		drive-strength = <MTK_DRIVE_6mA>;
+	};
+};
+
+&mmc1 {
+	bt_reset: bt-reset {
+		compatible = "mediatek,mt7921s-bluetooth";
+		pinctrl-names = "default";
+		pinctrl-0 = <&bt_pins_reset>;
+		reset-gpios = <&pio 120 GPIO_ACTIVE_LOW>;
+	};
+};
+
+&pio {
+	bt_pins_wakeup: bt-pins-wakeup {
+		piins-bt-wakeup {
+			pinmux = <PINMUX_GPIO42__FUNC_GPIO42>;
+			input-enable;
+		};
+	};
+
+	bt_pins_reset: bt-pins-reset {
+		pins-bt-reset {
+			pinmux = <PINMUX_GPIO120__FUNC_GPIO120>;
+			output-high;
+		};
+	};
+};
+
+/delete-node/ &bluetooth;
+/delete-node/ &bt_pins;
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi
index bf97b60ae4d1..7592e3b86037 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi
@@ -91,6 +91,8 @@
 
 &dsi0 {
 	status = "okay";
+	/delete-property/#size-cells;
+	/delete-property/#address-cells;
 	/delete-node/panel@0;
 	ports {
 		port {
@@ -147,7 +149,6 @@
 		reg = <0x58>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&anx7625_pins>;
-		panel_flags = <1>;
 		enable-gpios = <&pio 45 GPIO_ACTIVE_HIGH>;
 		reset-gpios = <&pio 73 GPIO_ACTIVE_HIGH>;
 		vdd10-supply = <&pp1200_mipibrdg>;
@@ -441,20 +442,20 @@
 	};
 
 	touchscreen_pins: touchscreen-pins {
-		touch_int_odl {
+		touch-int-odl {
 			pinmux = <PINMUX_GPIO155__FUNC_GPIO155>;
 			input-enable;
 			bias-pull-up;
 		};
 
-		touch_rst_l {
+		touch-rst-l {
 			pinmux = <PINMUX_GPIO156__FUNC_GPIO156>;
 			output-high;
 		};
 	};
 
 	trackpad_pins: trackpad-pins {
-		trackpad_int {
+		trackpad-int {
 			pinmux = <PINMUX_GPIO7__FUNC_GPIO7>;
 			input-enable;
 			bias-disable; /* pulled externally */
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu-sku22.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu-sku22.dts
index fcce8ea1232e..1ecf39458d93 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu-sku22.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu-sku22.dts
@@ -14,6 +14,24 @@
 		     "google,kakadu", "mediatek,mt8183";
 };
 
+&i2c0 {
+	touchscreen: touchscreen@10 {
+		compatible = "hid-over-i2c";
+		reg = <0x10>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&open_touch>;
+
+		interrupts-extended = <&pio 155 IRQ_TYPE_EDGE_FALLING>;
+
+		post-power-on-delay-ms = <10>;
+		hid-descr-addr = <0x0001>;
+	};
+};
+
+&panel {
+	compatible = "boe,tv105wum-nw0";
+};
+
 &sound {
 	compatible = "mediatek,mt8183_mt6358_ts3a227_rt1015p";
 };
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dts
index ebfabba72507..ba74109a4909 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dts
@@ -13,3 +13,21 @@
 	compatible = "google,kakadu-rev3", "google,kakadu-rev2",
 			"google,kakadu", "mediatek,mt8183";
 };
+
+&i2c0 {
+	touchscreen: touchscreen@10 {
+		compatible = "hid-over-i2c";
+		reg = <0x10>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&open_touch>;
+
+		interrupts-extended = <&pio 155 IRQ_TYPE_EDGE_FALLING>;
+
+		post-power-on-delay-ms = <10>;
+		hid-descr-addr = <0x0001>;
+	};
+};
+
+&panel {
+	compatible = "boe,tv105wum-nw0";
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dtsi
index a11adeb29b1f..b6a9830af269 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dtsi
@@ -63,19 +63,6 @@
 
 &i2c0 {
 	status = "okay";
-
-	touchscreen: touchscreen@10 {
-		compatible = "hid-over-i2c";
-		reg = <0x10>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&open_touch>;
-
-		interrupt-parent = <&pio>;
-		interrupts = <155 IRQ_TYPE_EDGE_FALLING>;
-
-		post-power-on-delay-ms = <10>;
-		hid-descr-addr = <0x0001>;
-	};
 };
 
 &mt6358_vcama2_reg {
@@ -384,5 +371,5 @@
 
 &panel {
 	status = "okay";
-	compatible = "boe,tv105wum-nw0";
+	/* compatible will be set in board dts */
 };
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-katsu-sku32.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-katsu-sku32.dts
new file mode 100644
index 000000000000..05361008e8ac
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-katsu-sku32.dts
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright 2023 Google LLC
+ */
+
+/dts-v1/;
+#include "mt8183-kukui-kakadu.dtsi"
+#include "mt8183-kukui-audio-da7219-rt1015p.dtsi"
+
+/ {
+	model = "Google katsu board";
+	chassis-type = "tablet";
+	compatible = "google,katsu-sku32", "google,katsu", "mediatek,mt8183";
+};
+
+&i2c0 {
+	touchscreen1: touchscreen@5d {
+		compatible = "goodix,gt7375p";
+		reg = <0x5d>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&open_touch>;
+
+		interrupts-extended = <&pio 155 IRQ_TYPE_LEVEL_LOW>;
+
+		reset-gpios = <&pio 156 GPIO_ACTIVE_LOW>;
+		vdd-supply = <&lcd_pp3300>;
+	};
+};
+
+&panel {
+	compatible = "starry,2081101qfh032011-53g";
+};
+
+&qca_wifi {
+	qcom,ath10k-calibration-variant = "GO_KATSU";
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-katsu-sku38.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-katsu-sku38.dts
new file mode 100644
index 000000000000..cf008ed82878
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-katsu-sku38.dts
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright 2023 Google LLC
+ */
+
+/dts-v1/;
+#include "mt8183-kukui-kakadu.dtsi"
+#include "mt8183-kukui-audio-rt1015p.dtsi"
+
+/ {
+	model = "Google katsu sku38 board";
+	chassis-type = "tablet";
+	compatible = "google,katsu-sku38", "google,katsu", "mediatek,mt8183";
+};
+
+&i2c0 {
+	touchscreen1: touchscreen@5d {
+		compatible = "goodix,gt7375p";
+		reg = <0x5d>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&open_touch>;
+
+		interrupts-extended = <&pio 155 IRQ_TYPE_LEVEL_LOW>;
+
+		reset-gpios = <&pio 156 GPIO_ACTIVE_LOW>;
+		vdd-supply = <&lcd_pp3300>;
+	};
+};
+
+&panel {
+	compatible = "starry,2081101qfh032011-53g";
+};
+
+&qca_wifi {
+	qcom,ath10k-calibration-variant = "GO_KATSU";
+};
+
+&sound {
+	compatible = "mediatek,mt8183_mt6358_ts3a227_rt1015p";
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kodama.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kodama.dtsi
index 4864c39e53a4..306c95166f3f 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kodama.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kodama.dtsi
@@ -48,8 +48,7 @@
 	touchscreen: touchscreen@10 {
 		compatible = "hid-over-i2c";
 		reg = <0x10>;
-		interrupt-parent = <&pio>;
-		interrupts = <155 IRQ_TYPE_LEVEL_LOW>;
+		interrupts-extended = <&pio 155 IRQ_TYPE_LEVEL_LOW>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&touch_default>;
 
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-krane.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-krane.dtsi
index d5f41c6c9881..382e4c6d7191 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-krane.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-krane.dtsi
@@ -54,8 +54,7 @@
 		pinctrl-names = "default";
 		pinctrl-0 = <&open_touch>;
 
-		interrupt-parent = <&pio>;
-		interrupts = <155 IRQ_TYPE_EDGE_FALLING>;
+		interrupts-extended = <&pio 155 IRQ_TYPE_EDGE_FALLING>;
 
 		post-power-on-delay-ms = <10>;
 		hid-descr-addr = <0x0001>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi
index bf7de35ffcbc..5506de83f61d 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi
@@ -116,7 +116,7 @@
 		#size-cells = <2>;
 		ranges;
 
-		scp_mem_reserved: scp_mem_region {
+		scp_mem_reserved: memory@50000000 {
 			compatible = "shared-dma-pool";
 			reg = <0 0x50000000 0 0x2900000>;
 			no-map;
@@ -460,7 +460,7 @@
 
 &pio {
 	aud_pins_default: audiopins {
-		pins_bus {
+		pins-bus {
 			pinmux = <PINMUX_GPIO97__FUNC_I2S2_MCK>,
 				<PINMUX_GPIO98__FUNC_I2S2_BCK>,
 				<PINMUX_GPIO101__FUNC_I2S2_LRCK>,
@@ -482,7 +482,7 @@
 	};
 
 	aud_pins_tdm_out_on: audiotdmouton {
-		pins_bus {
+		pins-bus {
 			pinmux = <PINMUX_GPIO169__FUNC_TDM_BCK_2ND>,
 				<PINMUX_GPIO170__FUNC_TDM_LRCK_2ND>,
 				<PINMUX_GPIO171__FUNC_TDM_DATA0_2ND>,
@@ -494,7 +494,7 @@
 	};
 
 	aud_pins_tdm_out_off: audiotdmoutoff {
-		pins_bus {
+		pins-bus {
 			pinmux = <PINMUX_GPIO169__FUNC_GPIO169>,
 				<PINMUX_GPIO170__FUNC_GPIO170>,
 				<PINMUX_GPIO171__FUNC_GPIO171>,
@@ -508,13 +508,13 @@
 	};
 
 	bt_pins: bt-pins {
-		pins_bt_en {
+		pins-bt-en {
 			pinmux = <PINMUX_GPIO120__FUNC_GPIO120>;
 			output-low;
 		};
 	};
 
-	ec_ap_int_odl: ec_ap_int_odl {
+	ec_ap_int_odl: ec-ap-int-odl {
 		pins1 {
 			pinmux = <PINMUX_GPIO151__FUNC_GPIO151>;
 			input-enable;
@@ -522,7 +522,7 @@
 		};
 	};
 
-	h1_int_od_l: h1_int_od_l {
+	h1_int_od_l: h1-int-od-l {
 		pins1 {
 			pinmux = <PINMUX_GPIO153__FUNC_GPIO153>;
 			input-enable;
@@ -530,7 +530,7 @@
 	};
 
 	i2c0_pins: i2c0 {
-		pins_bus {
+		pins-bus {
 			pinmux = <PINMUX_GPIO82__FUNC_SDA0>,
 				 <PINMUX_GPIO83__FUNC_SCL0>;
 			mediatek,pull-up-adv = <3>;
@@ -539,7 +539,7 @@
 	};
 
 	i2c1_pins: i2c1 {
-		pins_bus {
+		pins-bus {
 			pinmux = <PINMUX_GPIO81__FUNC_SDA1>,
 				 <PINMUX_GPIO84__FUNC_SCL1>;
 			mediatek,pull-up-adv = <3>;
@@ -548,7 +548,7 @@
 	};
 
 	i2c2_pins: i2c2 {
-		pins_bus {
+		pins-bus {
 			pinmux = <PINMUX_GPIO103__FUNC_SCL2>,
 				 <PINMUX_GPIO104__FUNC_SDA2>;
 			bias-disable;
@@ -557,7 +557,7 @@
 	};
 
 	i2c3_pins: i2c3 {
-		pins_bus {
+		pins-bus {
 			pinmux = <PINMUX_GPIO50__FUNC_SCL3>,
 				 <PINMUX_GPIO51__FUNC_SDA3>;
 			mediatek,pull-up-adv = <3>;
@@ -566,7 +566,7 @@
 	};
 
 	i2c4_pins: i2c4 {
-		pins_bus {
+		pins-bus {
 			pinmux = <PINMUX_GPIO105__FUNC_SCL4>,
 				 <PINMUX_GPIO106__FUNC_SDA4>;
 			bias-disable;
@@ -575,7 +575,7 @@
 	};
 
 	i2c5_pins: i2c5 {
-		pins_bus {
+		pins-bus {
 			pinmux = <PINMUX_GPIO48__FUNC_SCL5>,
 				 <PINMUX_GPIO49__FUNC_SDA5>;
 			mediatek,pull-up-adv = <3>;
@@ -584,7 +584,7 @@
 	};
 
 	i2c6_pins: i2c6 {
-		pins_bus {
+		pins-bus {
 			pinmux = <PINMUX_GPIO11__FUNC_SCL6>,
 				 <PINMUX_GPIO12__FUNC_SDA6>;
 			bias-disable;
@@ -592,7 +592,7 @@
 	};
 
 	mmc0_pins_default: mmc0-pins-default {
-		pins_cmd_dat {
+		pins-cmd-dat {
 			pinmux = <PINMUX_GPIO123__FUNC_MSDC0_DAT0>,
 				 <PINMUX_GPIO128__FUNC_MSDC0_DAT1>,
 				 <PINMUX_GPIO125__FUNC_MSDC0_DAT2>,
@@ -607,13 +607,13 @@
 			mediatek,pull-up-adv = <01>;
 		};
 
-		pins_clk {
+		pins-clk {
 			pinmux = <PINMUX_GPIO124__FUNC_MSDC0_CLK>;
 			drive-strength = <MTK_DRIVE_14mA>;
 			mediatek,pull-down-adv = <10>;
 		};
 
-		pins_rst {
+		pins-rst {
 			pinmux = <PINMUX_GPIO133__FUNC_MSDC0_RSTB>;
 			drive-strength = <MTK_DRIVE_14mA>;
 			mediatek,pull-down-adv = <01>;
@@ -621,7 +621,7 @@
 	};
 
 	mmc0_pins_uhs: mmc0-pins-uhs {
-		pins_cmd_dat {
+		pins-cmd-dat {
 			pinmux = <PINMUX_GPIO123__FUNC_MSDC0_DAT0>,
 				 <PINMUX_GPIO128__FUNC_MSDC0_DAT1>,
 				 <PINMUX_GPIO125__FUNC_MSDC0_DAT2>,
@@ -636,19 +636,19 @@
 			mediatek,pull-up-adv = <01>;
 		};
 
-		pins_clk {
+		pins-clk {
 			pinmux = <PINMUX_GPIO124__FUNC_MSDC0_CLK>;
 			drive-strength = <MTK_DRIVE_14mA>;
 			mediatek,pull-down-adv = <10>;
 		};
 
-		pins_ds {
+		pins-ds {
 			pinmux = <PINMUX_GPIO131__FUNC_MSDC0_DSL>;
 			drive-strength = <MTK_DRIVE_14mA>;
 			mediatek,pull-down-adv = <10>;
 		};
 
-		pins_rst {
+		pins-rst {
 			pinmux = <PINMUX_GPIO133__FUNC_MSDC0_RSTB>;
 			drive-strength = <MTK_DRIVE_14mA>;
 			mediatek,pull-up-adv = <01>;
@@ -656,7 +656,7 @@
 	};
 
 	mmc1_pins_default: mmc1-pins-default {
-		pins_cmd_dat {
+		pins-cmd-dat {
 			pinmux = <PINMUX_GPIO31__FUNC_MSDC1_CMD>,
 				 <PINMUX_GPIO32__FUNC_MSDC1_DAT0>,
 				 <PINMUX_GPIO34__FUNC_MSDC1_DAT1>,
@@ -666,7 +666,7 @@
 			mediatek,pull-up-adv = <10>;
 		};
 
-		pins_clk {
+		pins-clk {
 			pinmux = <PINMUX_GPIO29__FUNC_MSDC1_CLK>;
 			input-enable;
 			mediatek,pull-down-adv = <10>;
@@ -674,7 +674,7 @@
 	};
 
 	mmc1_pins_uhs: mmc1-pins-uhs {
-		pins_cmd_dat {
+		pins-cmd-dat {
 			pinmux = <PINMUX_GPIO31__FUNC_MSDC1_CMD>,
 				 <PINMUX_GPIO32__FUNC_MSDC1_DAT0>,
 				 <PINMUX_GPIO34__FUNC_MSDC1_DAT1>,
@@ -685,7 +685,7 @@
 			mediatek,pull-up-adv = <10>;
 		};
 
-		pins_clk {
+		pins-clk {
 			pinmux = <PINMUX_GPIO29__FUNC_MSDC1_CLK>;
 			drive-strength = <MTK_DRIVE_8mA>;
 			mediatek,pull-down-adv = <10>;
@@ -693,15 +693,15 @@
 		};
 	};
 
-	panel_pins_default: panel_pins_default {
-		panel_reset {
+	panel_pins_default: panel-pins-default {
+		panel-reset {
 			pinmux = <PINMUX_GPIO45__FUNC_GPIO45>;
 			output-low;
 			bias-pull-up;
 		};
 	};
 
-	pwm0_pin_default: pwm0_pin_default {
+	pwm0_pin_default: pwm0-pin-default {
 		pins1 {
 			pinmux = <PINMUX_GPIO176__FUNC_GPIO176>;
 			output-high;
@@ -713,14 +713,14 @@
 	};
 
 	scp_pins: scp {
-		pins_scp_uart {
+		pins-scp-uart {
 			pinmux = <PINMUX_GPIO110__FUNC_TP_URXD1_AO>,
 				 <PINMUX_GPIO112__FUNC_TP_UTXD1_AO>;
 		};
 	};
 
 	spi0_pins: spi0 {
-		pins_spi {
+		pins-spi {
 			pinmux = <PINMUX_GPIO85__FUNC_SPI0_MI>,
 				 <PINMUX_GPIO86__FUNC_GPIO86>,
 				 <PINMUX_GPIO87__FUNC_SPI0_MO>,
@@ -730,7 +730,7 @@
 	};
 
 	spi1_pins: spi1 {
-		pins_spi {
+		pins-spi {
 			pinmux = <PINMUX_GPIO161__FUNC_SPI1_A_MI>,
 				 <PINMUX_GPIO162__FUNC_SPI1_A_CSB>,
 				 <PINMUX_GPIO163__FUNC_SPI1_A_MO>,
@@ -740,20 +740,20 @@
 	};
 
 	spi2_pins: spi2 {
-		pins_spi {
+		pins-spi {
 			pinmux = <PINMUX_GPIO0__FUNC_SPI2_CSB>,
 				 <PINMUX_GPIO1__FUNC_SPI2_MO>,
 				 <PINMUX_GPIO2__FUNC_SPI2_CLK>;
 			bias-disable;
 		};
-		pins_spi_mi {
+		pins-spi-mi {
 			pinmux = <PINMUX_GPIO94__FUNC_SPI2_MI>;
 			mediatek,pull-down-adv = <00>;
 		};
 	};
 
 	spi3_pins: spi3 {
-		pins_spi {
+		pins-spi {
 			pinmux = <PINMUX_GPIO21__FUNC_SPI3_MI>,
 				 <PINMUX_GPIO22__FUNC_SPI3_CSB>,
 				 <PINMUX_GPIO23__FUNC_SPI3_MO>,
@@ -763,7 +763,7 @@
 	};
 
 	spi4_pins: spi4 {
-		pins_spi {
+		pins-spi {
 			pinmux = <PINMUX_GPIO17__FUNC_SPI4_MI>,
 				 <PINMUX_GPIO18__FUNC_SPI4_CSB>,
 				 <PINMUX_GPIO19__FUNC_SPI4_MO>,
@@ -773,7 +773,7 @@
 	};
 
 	spi5_pins: spi5 {
-		pins_spi {
+		pins-spi {
 			pinmux = <PINMUX_GPIO13__FUNC_SPI5_MI>,
 				 <PINMUX_GPIO14__FUNC_SPI5_CSB>,
 				 <PINMUX_GPIO15__FUNC_SPI5_MO>,
@@ -783,69 +783,73 @@
 	};
 
 	uart0_pins_default: uart0-pins-default {
-		pins_rx {
+		pins-rx {
 			pinmux = <PINMUX_GPIO95__FUNC_URXD0>;
 			input-enable;
 			bias-pull-up;
 		};
-		pins_tx {
+		pins-tx {
 			pinmux = <PINMUX_GPIO96__FUNC_UTXD0>;
 		};
 	};
 
 	uart1_pins_default: uart1-pins-default {
-		pins_rx {
+		pins-rx {
 			pinmux = <PINMUX_GPIO121__FUNC_URXD1>;
 			input-enable;
 			bias-pull-up;
 		};
-		pins_tx {
+		pins-tx {
 			pinmux = <PINMUX_GPIO115__FUNC_UTXD1>;
 		};
-		pins_rts {
+		pins-rts {
 			pinmux = <PINMUX_GPIO47__FUNC_URTS1>;
 			output-enable;
 		};
-		pins_cts {
+		pins-cts {
 			pinmux = <PINMUX_GPIO46__FUNC_UCTS1>;
 			input-enable;
 		};
 	};
 
 	uart1_pins_sleep: uart1-pins-sleep {
-		pins_rx {
+		pins-rx {
 			pinmux = <PINMUX_GPIO121__FUNC_GPIO121>;
 			input-enable;
 			bias-pull-up;
 		};
-		pins_tx {
+		pins-tx {
 			pinmux = <PINMUX_GPIO115__FUNC_UTXD1>;
 		};
-		pins_rts {
+		pins-rts {
 			pinmux = <PINMUX_GPIO47__FUNC_URTS1>;
 			output-enable;
 		};
-		pins_cts {
+		pins-cts {
 			pinmux = <PINMUX_GPIO46__FUNC_UCTS1>;
 			input-enable;
 		};
 	};
 
 	wifi_pins_pwrseq: wifi-pins-pwrseq {
-		pins_wifi_enable {
+		pins-wifi-enable {
 			pinmux = <PINMUX_GPIO119__FUNC_GPIO119>;
 			output-low;
 		};
 	};
 
 	wifi_pins_wakeup: wifi-pins-wakeup {
-		pins_wifi_wakeup {
+		pins-wifi-wakeup {
 			pinmux = <PINMUX_GPIO113__FUNC_GPIO113>;
 			input-enable;
 		};
 	};
 };
 
+&pmic {
+	interrupts-extended = <&pio 182 IRQ_TYPE_LEVEL_HIGH>;
+};
+
 &pwm0 {
 	status = "okay";
 	pinctrl-names = "default";
@@ -890,8 +894,7 @@
 		spi-max-frequency = <1000000>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&h1_int_od_l>;
-		interrupt-parent = <&pio>;
-		interrupts = <153 IRQ_TYPE_EDGE_RISING>;
+		interrupts-extended = <&pio 153 IRQ_TYPE_EDGE_RISING>;
 	};
 };
 
@@ -918,8 +921,7 @@
 		compatible = "google,cros-ec-spi";
 		reg = <0>;
 		spi-max-frequency = <3000000>;
-		interrupt-parent = <&pio>;
-		interrupts = <151 IRQ_TYPE_LEVEL_LOW>;
+		interrupts-extended = <&pio 151 IRQ_TYPE_LEVEL_LOW>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&ec_ap_int_odl>;
 
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-pumpkin.dts b/arch/arm64/boot/dts/mediatek/mt8183-pumpkin.dts
index b5784a60c315..76449b4cf236 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-pumpkin.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8183-pumpkin.dts
@@ -370,6 +370,10 @@
 	};
 };
 
+&pmic {
+	interrupts-extended = <&pio 182 IRQ_TYPE_LEVEL_HIGH>;
+};
+
 &mfg {
 	domain-supply = <&mt6358_vgpu_reg>;
 };
diff --git a/arch/arm64/boot/dts/mediatek/mt8183.dtsi b/arch/arm64/boot/dts/mediatek/mt8183.dtsi
index 5169779d01df..920ee415ef5f 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8183.dtsi
@@ -1183,22 +1183,10 @@
 			status = "disabled";
 		};
 
-		svs: svs@1100b000 {
-			compatible = "mediatek,mt8183-svs";
-			reg = <0 0x1100b000 0 0x1000>;
-			interrupts = <GIC_SPI 127 IRQ_TYPE_LEVEL_LOW>;
-			clocks = <&infracfg CLK_INFRA_THERM>;
-			clock-names = "main";
-			nvmem-cells = <&svs_calibration>,
-				      <&thermal_calibration>;
-			nvmem-cell-names = "svs-calibration-data",
-					   "t-calibration-data";
-		};
-
 		thermal: thermal@1100b000 {
 			#thermal-sensor-cells = <1>;
 			compatible = "mediatek,mt8183-thermal";
-			reg = <0 0x1100b000 0 0x1000>;
+			reg = <0 0x1100b000 0 0xc00>;
 			clocks = <&infracfg CLK_INFRA_THERM>,
 				 <&infracfg CLK_INFRA_AUXADC>;
 			clock-names = "therm", "auxadc";
@@ -1210,125 +1198,16 @@
 			nvmem-cell-names = "calibration-data";
 		};
 
-		thermal_zones: thermal-zones {
-			cpu_thermal: cpu-thermal {
-				polling-delay-passive = <100>;
-				polling-delay = <500>;
-				thermal-sensors = <&thermal 0>;
-				sustainable-power = <5000>;
-
-				trips {
-					threshold: trip-point0 {
-						temperature = <68000>;
-						hysteresis = <2000>;
-						type = "passive";
-					};
-
-					target: trip-point1 {
-						temperature = <80000>;
-						hysteresis = <2000>;
-						type = "passive";
-					};
-
-					cpu_crit: cpu-crit {
-						temperature = <115000>;
-						hysteresis = <2000>;
-						type = "critical";
-					};
-				};
-
-				cooling-maps {
-					map0 {
-						trip = <&target>;
-						cooling-device = <&cpu0
-							THERMAL_NO_LIMIT
-							THERMAL_NO_LIMIT>,
-								 <&cpu1
-							THERMAL_NO_LIMIT
-							THERMAL_NO_LIMIT>,
-								 <&cpu2
-							THERMAL_NO_LIMIT
-							THERMAL_NO_LIMIT>,
-								 <&cpu3
-							THERMAL_NO_LIMIT
-							THERMAL_NO_LIMIT>;
-						contribution = <3072>;
-					};
-					map1 {
-						trip = <&target>;
-						cooling-device = <&cpu4
-							THERMAL_NO_LIMIT
-							THERMAL_NO_LIMIT>,
-								 <&cpu5
-							THERMAL_NO_LIMIT
-							THERMAL_NO_LIMIT>,
-								 <&cpu6
-							THERMAL_NO_LIMIT
-							THERMAL_NO_LIMIT>,
-								 <&cpu7
-							THERMAL_NO_LIMIT
-							THERMAL_NO_LIMIT>;
-						contribution = <1024>;
-					};
-				};
-			};
-
-			/* The tzts1 ~ tzts6 don't need to polling */
-			/* The tzts1 ~ tzts6 don't need to thermal throttle */
-
-			tzts1: tzts1 {
-				polling-delay-passive = <0>;
-				polling-delay = <0>;
-				thermal-sensors = <&thermal 1>;
-				sustainable-power = <5000>;
-				trips {};
-				cooling-maps {};
-			};
-
-			tzts2: tzts2 {
-				polling-delay-passive = <0>;
-				polling-delay = <0>;
-				thermal-sensors = <&thermal 2>;
-				sustainable-power = <5000>;
-				trips {};
-				cooling-maps {};
-			};
-
-			tzts3: tzts3 {
-				polling-delay-passive = <0>;
-				polling-delay = <0>;
-				thermal-sensors = <&thermal 3>;
-				sustainable-power = <5000>;
-				trips {};
-				cooling-maps {};
-			};
-
-			tzts4: tzts4 {
-				polling-delay-passive = <0>;
-				polling-delay = <0>;
-				thermal-sensors = <&thermal 4>;
-				sustainable-power = <5000>;
-				trips {};
-				cooling-maps {};
-			};
-
-			tzts5: tzts5 {
-				polling-delay-passive = <0>;
-				polling-delay = <0>;
-				thermal-sensors = <&thermal 5>;
-				sustainable-power = <5000>;
-				trips {};
-				cooling-maps {};
-			};
-
-			tztsABB: tztsABB {
-				polling-delay-passive = <0>;
-				polling-delay = <0>;
-				thermal-sensors = <&thermal 6>;
-				sustainable-power = <5000>;
-				trips {};
-				cooling-maps {};
-			};
+		svs: svs@1100bc00 {
+			compatible = "mediatek,mt8183-svs";
+			reg = <0 0x1100bc00 0 0x400>;
+			interrupts = <GIC_SPI 127 IRQ_TYPE_LEVEL_LOW>;
+			clocks = <&infracfg CLK_INFRA_THERM>;
+			clock-names = "main";
+			nvmem-cells = <&svs_calibration>,
+				      <&thermal_calibration>;
+			nvmem-cell-names = "svs-calibration-data",
+					   "t-calibration-data";
 		};
 
 		pwm0: pwm@1100e000 {
@@ -1781,7 +1660,7 @@
 			mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0 0x1000>;
 		};
 
-		mdp3-rdma0@14001000 {
+		dma-controller0@14001000 {
 			compatible = "mediatek,mt8183-mdp3-rdma";
 			reg = <0 0x14001000 0 0x1000>;
 			mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x1000 0x1000>;
@@ -1793,6 +1672,7 @@
 			iommus = <&iommu M4U_PORT_MDP_RDMA0>;
 			mboxes = <&gce 20 CMDQ_THR_PRIO_LOWEST 0>,
 				 <&gce 21 CMDQ_THR_PRIO_LOWEST 0>;
+			#dma-cells = <1>;
 		};
 
 		mdp3-rsz0@14003000 {
@@ -1813,7 +1693,7 @@
 			clocks = <&mmsys CLK_MM_MDP_RSZ1>;
 		};
 
-		mdp3-wrot0@14005000 {
+		dma-controller@14005000 {
 			compatible = "mediatek,mt8183-mdp3-wrot";
 			reg = <0 0x14005000 0 0x1000>;
 			mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x5000 0x1000>;
@@ -1822,6 +1702,7 @@
 			power-domains = <&spm MT8183_POWER_DOMAIN_DISP>;
 			clocks = <&mmsys CLK_MM_MDP_WROT0>;
 			iommus = <&iommu M4U_PORT_MDP_WROT0>;
+			#dma-cells = <1>;
 		};
 
 		mdp3-wdma@14006000 {
@@ -2019,6 +1900,36 @@
 			#clock-cells = <1>;
 		};
 
+		vcodec_dec: video-codec@16020000 {
+			compatible = "mediatek,mt8183-vcodec-dec";
+			reg = <0 0x16020000 0 0x1000>,		/* VDEC_MISC */
+			      <0 0x16021000 0 0x800>,		/* VDEC_VLD */
+			      <0 0x16021800 0 0x800>,		/* VDEC_TOP */
+			      <0 0x16022000 0 0x1000>,		/* VDEC_MC */
+			      <0 0x16023000 0 0x1000>,		/* VDEC_AVCVLD */
+			      <0 0x16024000 0 0x1000>,		/* VDEC_AVCMV */
+			      <0 0x16025000 0 0x1000>,		/* VDEC_PP */
+			      <0 0x16026800 0 0x800>,		/* VP8_VD */
+			      <0 0x16027000 0 0x800>,		/* VP6_VD */
+			      <0 0x16027800 0 0x800>,		/* VP8_VL */
+			      <0 0x16028400 0 0x400>;		/* VP9_VD */
+			reg-names = "misc", "ld", "top", "cm", "ad", "av", "pp",
+				    "hwd", "hwq", "hwb", "hwg";
+			interrupts = <GIC_SPI 250 IRQ_TYPE_LEVEL_LOW>;
+			iommus = <&iommu M4U_PORT_HW_VDEC_MC_EXT>,
+				 <&iommu M4U_PORT_HW_VDEC_PP_EXT>,
+				 <&iommu M4U_PORT_HW_VDEC_VLD_EXT>,
+				 <&iommu M4U_PORT_HW_VDEC_AVC_MV_EXT>,
+				 <&iommu M4U_PORT_HW_VDEC_PRED_RD_EXT>,
+				 <&iommu M4U_PORT_HW_VDEC_PRED_WR_EXT>,
+				 <&iommu M4U_PORT_HW_VDEC_PPWRAP_EXT>;
+			mediatek,scp = <&scp>;
+			mediatek,vdecsys = <&vdecsys>;
+			power-domains = <&spm MT8183_POWER_DOMAIN_VDEC>;
+			clocks = <&vdecsys CLK_VDEC_VDEC>;
+			clock-names = "vdec";
+		};
+
 		larb1: larb@16010000 {
 			compatible = "mediatek,mt8183-smi-larb";
 			reg = <0 0x16010000 0 0x1000>;
@@ -2105,4 +2016,125 @@
 			power-domains = <&spm MT8183_POWER_DOMAIN_CAM>;
 		};
 	};
+
+	thermal_zones: thermal-zones {
+		cpu_thermal: cpu-thermal {
+			polling-delay-passive = <100>;
+			polling-delay = <500>;
+			thermal-sensors = <&thermal 0>;
+			sustainable-power = <5000>;
+
+			trips {
+				threshold: trip-point0 {
+					temperature = <68000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				target: trip-point1 {
+					temperature = <80000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu_crit: cpu-crit {
+					temperature = <115000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&target>;
+					cooling-device = <&cpu0
+						THERMAL_NO_LIMIT
+						THERMAL_NO_LIMIT>,
+							 <&cpu1
+						THERMAL_NO_LIMIT
+						THERMAL_NO_LIMIT>,
+							 <&cpu2
+						THERMAL_NO_LIMIT
+						THERMAL_NO_LIMIT>,
+							 <&cpu3
+						THERMAL_NO_LIMIT
+						THERMAL_NO_LIMIT>;
+					contribution = <3072>;
+				};
+				map1 {
+					trip = <&target>;
+					cooling-device = <&cpu4
+						THERMAL_NO_LIMIT
+						THERMAL_NO_LIMIT>,
+							 <&cpu5
+						THERMAL_NO_LIMIT
+						THERMAL_NO_LIMIT>,
+							 <&cpu6
+						THERMAL_NO_LIMIT
+						THERMAL_NO_LIMIT>,
+							 <&cpu7
+						THERMAL_NO_LIMIT
+						THERMAL_NO_LIMIT>;
+					contribution = <1024>;
+				};
+			};
+		};
+
+		/* The tzts1 ~ tzts6 don't need to polling */
+		/* The tzts1 ~ tzts6 don't need to thermal throttle */
+
+		tzts1: tzts1 {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&thermal 1>;
+			sustainable-power = <5000>;
+			trips {};
+			cooling-maps {};
+		};
+
+		tzts2: tzts2 {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&thermal 2>;
+			sustainable-power = <5000>;
+			trips {};
+			cooling-maps {};
+		};
+
+		tzts3: tzts3 {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&thermal 3>;
+			sustainable-power = <5000>;
+			trips {};
+			cooling-maps {};
+		};
+
+		tzts4: tzts4 {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&thermal 4>;
+			sustainable-power = <5000>;
+			trips {};
+			cooling-maps {};
+		};
+
+		tzts5: tzts5 {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&thermal 5>;
+			sustainable-power = <5000>;
+			trips {};
+			cooling-maps {};
+		};
+
+		tztsABB: tztsABB {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&thermal 6>;
+			sustainable-power = <5000>;
+			trips {};
+			cooling-maps {};
+		};
+	};
 };
diff --git a/arch/arm64/boot/dts/mediatek/mt8186.dtsi b/arch/arm64/boot/dts/mediatek/mt8186.dtsi
index f04ae70c470a..2fec6fd1c1a7 100644
--- a/arch/arm64/boot/dts/mediatek/mt8186.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8186.dtsi
@@ -22,7 +22,7 @@
 
 	aliases {
 		ovl0 = &ovl0;
-		ovl_2l0 = &ovl_2l0;
+		ovl-2l0 = &ovl_2l0;
 		rdma0 = &rdma0;
 		rdma1 = &rdma1;
 	};
@@ -924,7 +924,8 @@
 					reg = <MT8186_POWER_DOMAIN_CSIRX_TOP>;
 					clocks = <&topckgen CLK_TOP_SENINF>,
 						 <&topckgen CLK_TOP_SENINF1>;
-					clock-names = "csirx_top0", "csirx_top1";
+					clock-names = "subsys-csirx-top0",
+						      "subsys-csirx-top1";
 					#power-domain-cells = <0>;
 				};
 
@@ -942,7 +943,8 @@
 					reg = <MT8186_POWER_DOMAIN_ADSP_AO>;
 					clocks = <&topckgen CLK_TOP_AUDIODSP>,
 						 <&topckgen CLK_TOP_ADSP_BUS>;
-					clock-names = "audioadsp", "adsp_bus";
+					clock-names = "audioadsp",
+						      "subsys-adsp-bus";
 					#address-cells = <1>;
 					#size-cells = <0>;
 					#power-domain-cells = <1>;
@@ -975,8 +977,11 @@
 						 <&mmsys CLK_MM_SMI_COMMON>,
 						 <&mmsys CLK_MM_SMI_GALS>,
 						 <&mmsys CLK_MM_SMI_IOMMU>;
-					clock-names = "disp", "mdp", "smi_infra", "smi_common",
-						     "smi_gals", "smi_iommu";
+					clock-names = "disp", "mdp",
+						      "subsys-smi-infra",
+						      "subsys-smi-common",
+						      "subsys-smi-gals",
+						      "subsys-smi-iommu";
 					mediatek,infracfg = <&infracfg_ao>;
 					#address-cells = <1>;
 					#size-cells = <0>;
@@ -993,15 +998,17 @@
 
 					power-domain@MT8186_POWER_DOMAIN_CAM {
 						reg = <MT8186_POWER_DOMAIN_CAM>;
-						clocks = <&topckgen CLK_TOP_CAM>,
-							 <&topckgen CLK_TOP_SENINF>,
+						clocks = <&topckgen CLK_TOP_SENINF>,
 							 <&topckgen CLK_TOP_SENINF1>,
 							 <&topckgen CLK_TOP_SENINF2>,
 							 <&topckgen CLK_TOP_SENINF3>,
+							 <&camsys CLK_CAM2MM_GALS>,
 							 <&topckgen CLK_TOP_CAMTM>,
-							 <&camsys CLK_CAM2MM_GALS>;
-						clock-names = "cam-top", "cam0", "cam1", "cam2",
-							     "cam3", "cam-tm", "gals";
+							 <&topckgen CLK_TOP_CAM>;
+						clock-names = "cam0", "cam1", "cam2",
+							      "cam3", "gals",
+							      "subsys-cam-tm",
+							      "subsys-cam-top";
 						mediatek,infracfg = <&infracfg_ao>;
 						#address-cells = <1>;
 						#size-cells = <0>;
@@ -1020,9 +1027,9 @@
 
 					power-domain@MT8186_POWER_DOMAIN_IMG {
 						reg = <MT8186_POWER_DOMAIN_IMG>;
-						clocks = <&topckgen CLK_TOP_IMG1>,
-							 <&imgsys1 CLK_IMG1_GALS_IMG1>;
-						clock-names = "img-top", "gals";
+						clocks = <&imgsys1 CLK_IMG1_GALS_IMG1>,
+							 <&topckgen CLK_TOP_IMG1>;
+						clock-names = "gals", "subsys-img-top";
 						mediatek,infracfg = <&infracfg_ao>;
 						#address-cells = <1>;
 						#size-cells = <0>;
@@ -1041,8 +1048,11 @@
 							 <&ipesys CLK_IPE_LARB20>,
 							 <&ipesys CLK_IPE_SMI_SUBCOM>,
 							 <&ipesys CLK_IPE_GALS_IPE>;
-						clock-names = "ipe-top", "ipe-larb0", "ipe-larb1",
-							      "ipe-smi", "ipe-gals";
+						clock-names = "subsys-ipe-top",
+							      "subsys-ipe-larb0",
+							      "subsys-ipe-larb1",
+							      "subsys-ipe-smi",
+							      "subsys-ipe-gals";
 						mediatek,infracfg = <&infracfg_ao>;
 						#power-domain-cells = <0>;
 					};
@@ -1061,7 +1071,9 @@
 						clocks = <&topckgen CLK_TOP_WPE>,
 							 <&wpesys CLK_WPE_SMI_LARB8_CK_EN>,
 							 <&wpesys CLK_WPE_SMI_LARB8_PCLK_EN>;
-						clock-names = "wpe0", "larb-ck", "larb-pclk";
+						clock-names = "wpe0",
+							      "subsys-larb-ck",
+							      "subsys-larb-pclk";
 						mediatek,infracfg = <&infracfg_ao>;
 						#power-domain-cells = <0>;
 					};
@@ -1148,14 +1160,14 @@
 			status = "disabled";
 		};
 
-		adsp_mailbox0: mailbox@10686000 {
+		adsp_mailbox0: mailbox@10686100 {
 			compatible = "mediatek,mt8186-adsp-mbox";
 			#mbox-cells = <0>;
 			reg = <0 0x10686100 0 0x1000>;
 			interrupts = <GIC_SPI 361 IRQ_TYPE_LEVEL_HIGH 0>;
 		};
 
-		adsp_mailbox1: mailbox@10687000 {
+		adsp_mailbox1: mailbox@10687100 {
 			compatible = "mediatek,mt8186-adsp-mbox";
 			#mbox-cells = <0>;
 			reg = <0 0x10687100 0 0x1000>;
@@ -1656,7 +1668,7 @@
 			#address-cells = <1>;
 			#size-cells = <1>;
 
-			gpu_speedbin: gpu-speed-bin@59c {
+			gpu_speedbin: gpu-speedbin@59c {
 				reg = <0x59c 0x4>;
 				bits = <0 3>;
 			};
diff --git a/arch/arm64/boot/dts/mediatek/mt8188-evb.dts b/arch/arm64/boot/dts/mediatek/mt8188-evb.dts
new file mode 100644
index 000000000000..68a82b49f7a3
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8188-evb.dts
@@ -0,0 +1,387 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (C) 2023 MediaTek Inc.
+ */
+/dts-v1/;
+#include "mt8188.dtsi"
+#include "mt6359.dtsi"
+
+/ {
+	model = "MediaTek MT8188 evaluation board";
+	compatible = "mediatek,mt8188-evb", "mediatek,mt8188";
+
+	aliases {
+		serial0 = &uart0;
+		i2c0 = &i2c0;
+		i2c1 = &i2c1;
+		i2c2 = &i2c2;
+		i2c3 = &i2c3;
+		i2c4 = &i2c4;
+		i2c5 = &i2c5;
+		i2c6 = &i2c6;
+		mmc0 = &mmc0;
+	};
+
+	chosen: chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory@40000000 {
+		device_type = "memory";
+		reg = <0 0x40000000 0 0x80000000>;
+	};
+
+	reserved_memory: reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		scp_mem_reserved: memory@50000000 {
+			compatible = "shared-dma-pool";
+			reg = <0 0x50000000 0 0x2900000>;
+			no-map;
+		};
+	};
+};
+
+&auxadc {
+	status = "okay";
+};
+
+&i2c0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c0_pins>;
+	clock-frequency = <400000>;
+	status = "okay";
+};
+
+&i2c1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c1_pins>;
+	clock-frequency = <400000>;
+	status = "okay";
+};
+
+&i2c2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c2_pins>;
+	clock-frequency = <400000>;
+	status = "okay";
+};
+
+&i2c3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c3_pins>;
+	clock-frequency = <400000>;
+	status = "okay";
+};
+
+&i2c4 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c4_pins>;
+	clock-frequency = <400000>;
+	status = "okay";
+};
+
+&i2c5 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c5_pins>;
+	clock-frequency = <400000>;
+	status = "okay";
+};
+
+&i2c6 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c6_pins>;
+	clock-frequency = <400000>;
+	status = "okay";
+};
+
+&mmc0 {
+	bus-width = <8>;
+	hs400-ds-delay = <0x1481b>;
+	max-frequency = <200000000>;
+
+	cap-mmc-highspeed;
+	mmc-hs200-1_8v;
+	mmc-hs400-1_8v;
+	supports-cqe;
+	cap-mmc-hw-reset;
+	no-sdio;
+	no-sd;
+	non-removable;
+
+	vmmc-supply = <&mt6359_vemc_1_ldo_reg>;
+	vqmmc-supply = <&mt6359_vufs_ldo_reg>;
+
+	pinctrl-names = "default", "state_uhs";
+	pinctrl-0 = <&mmc0_default_pins>;
+	pinctrl-1 = <&mmc0_uhs_pins>;
+
+	status = "okay";
+};
+
+&mt6359_vcore_buck_reg {
+	regulator-always-on;
+};
+
+&mt6359_vgpu11_buck_reg {
+	regulator-always-on;
+};
+
+&mt6359_vpu_buck_reg {
+	regulator-always-on;
+};
+
+&mt6359_vrf12_ldo_reg {
+	regulator-always-on;
+};
+
+&nor_flash {
+	pinctrl-names = "default";
+	pinctrl-0 = <&nor_pins_default>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0>;
+		spi-max-frequency = <52000000>;
+	};
+};
+
+&pio {
+	adsp_uart_pins: adsp-uart-pins {
+		pins-tx-rx {
+			pinmux = <PINMUX_GPIO35__FUNC_O_ADSP_UTXD0>,
+				 <PINMUX_GPIO36__FUNC_I1_ADSP_URXD0>;
+		};
+	};
+
+	i2c0_pins: i2c0-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO56__FUNC_B1_SDA0>,
+				 <PINMUX_GPIO55__FUNC_B1_SCL0>;
+			bias-pull-up = <MTK_PULL_SET_RSEL_011>;
+		};
+	};
+
+	i2c1_pins: i2c1-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO58__FUNC_B1_SDA1>,
+				 <PINMUX_GPIO57__FUNC_B1_SCL1>;
+			bias-pull-up = <MTK_PULL_SET_RSEL_011>;
+		};
+	};
+
+	i2c2_pins: i2c2-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO60__FUNC_B1_SDA2>,
+				 <PINMUX_GPIO59__FUNC_B1_SCL2>;
+			bias-pull-up = <MTK_PULL_SET_RSEL_011>;
+		};
+	};
+
+	i2c3_pins: i2c3-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO62__FUNC_B1_SDA3>,
+				 <PINMUX_GPIO61__FUNC_B1_SCL3>;
+			bias-pull-up = <MTK_PULL_SET_RSEL_011>;
+		};
+	};
+
+	i2c4_pins: i2c4-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO64__FUNC_B1_SDA4>,
+				 <PINMUX_GPIO63__FUNC_B1_SCL4>;
+			bias-pull-up = <MTK_PULL_SET_RSEL_011>;
+		};
+	};
+
+	i2c5_pins: i2c5-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO66__FUNC_B1_SDA5>,
+				 <PINMUX_GPIO65__FUNC_B1_SCL5>;
+			bias-pull-up = <MTK_PULL_SET_RSEL_011>;
+		};
+	};
+
+	i2c6_pins: i2c6-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO68__FUNC_B1_SDA6>,
+				 <PINMUX_GPIO67__FUNC_B1_SCL6>;
+			bias-pull-up = <MTK_PULL_SET_RSEL_011>;
+		};
+	};
+
+	mmc0_default_pins: mmc0-default-pins {
+		pins-cmd-dat {
+			pinmux = <PINMUX_GPIO161__FUNC_B1_MSDC0_DAT0>,
+				 <PINMUX_GPIO160__FUNC_B1_MSDC0_DAT1>,
+				 <PINMUX_GPIO159__FUNC_B1_MSDC0_DAT2>,
+				 <PINMUX_GPIO158__FUNC_B1_MSDC0_DAT3>,
+				 <PINMUX_GPIO154__FUNC_B1_MSDC0_DAT4>,
+				 <PINMUX_GPIO153__FUNC_B1_MSDC0_DAT5>,
+				 <PINMUX_GPIO152__FUNC_B1_MSDC0_DAT6>,
+				 <PINMUX_GPIO151__FUNC_B1_MSDC0_DAT7>,
+				 <PINMUX_GPIO156__FUNC_B1_MSDC0_CMD>;
+			input-enable;
+			drive-strength = <6>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+
+		pins-clk {
+			pinmux = <PINMUX_GPIO157__FUNC_B1_MSDC0_CLK>;
+			drive-strength = <6>;
+			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
+		};
+
+		pins-rst {
+			pinmux = <PINMUX_GPIO155__FUNC_O_MSDC0_RSTB>;
+			drive-strength = <6>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+	};
+
+	mmc0_uhs_pins: mmc0-uhs-pins {
+		pins-cmd-dat {
+			pinmux = <PINMUX_GPIO161__FUNC_B1_MSDC0_DAT0>,
+				 <PINMUX_GPIO160__FUNC_B1_MSDC0_DAT1>,
+				 <PINMUX_GPIO159__FUNC_B1_MSDC0_DAT2>,
+				 <PINMUX_GPIO158__FUNC_B1_MSDC0_DAT3>,
+				 <PINMUX_GPIO154__FUNC_B1_MSDC0_DAT4>,
+				 <PINMUX_GPIO153__FUNC_B1_MSDC0_DAT5>,
+				 <PINMUX_GPIO152__FUNC_B1_MSDC0_DAT6>,
+				 <PINMUX_GPIO151__FUNC_B1_MSDC0_DAT7>,
+				 <PINMUX_GPIO156__FUNC_B1_MSDC0_CMD>;
+			input-enable;
+			drive-strength = <8>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+
+		pins-clk-ds {
+			pinmux = <PINMUX_GPIO157__FUNC_B1_MSDC0_CLK>,
+				 <PINMUX_GPIO162__FUNC_B0_MSDC0_DSL>;
+			drive-strength = <8>;
+			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
+		};
+
+		pins-rst {
+			pinmux = <PINMUX_GPIO155__FUNC_O_MSDC0_RSTB>;
+			drive-strength = <8>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+	};
+
+	nor_pins_default: nor-pins {
+		pins-io-ck {
+			pinmux = <PINMUX_GPIO127__FUNC_B0_SPINOR_IO0>,
+				 <PINMUX_GPIO125__FUNC_O_SPINOR_CK>,
+				 <PINMUX_GPIO128__FUNC_B0_SPINOR_IO1>;
+			bias-pull-down;
+		};
+
+		pins-io-cs {
+			pinmux = <PINMUX_GPIO126__FUNC_O_SPINOR_CS>,
+				 <PINMUX_GPIO129__FUNC_B0_SPINOR_IO2>,
+				 <PINMUX_GPIO130__FUNC_B0_SPINOR_IO3>;
+			bias-pull-up;
+		};
+	};
+
+	spi0_pins: spi0-pins {
+		pins-spi {
+			pinmux = <PINMUX_GPIO69__FUNC_O_SPIM0_CSB>,
+				 <PINMUX_GPIO70__FUNC_O_SPIM0_CLK>,
+				 <PINMUX_GPIO71__FUNC_B0_SPIM0_MOSI>,
+				 <PINMUX_GPIO72__FUNC_B0_SPIM0_MISO>;
+			bias-disable;
+		};
+	};
+
+	spi1_pins: spi1-pins {
+		pins-spi {
+			pinmux = <PINMUX_GPIO75__FUNC_O_SPIM1_CSB>,
+				 <PINMUX_GPIO76__FUNC_O_SPIM1_CLK>,
+				 <PINMUX_GPIO77__FUNC_B0_SPIM1_MOSI>,
+				 <PINMUX_GPIO78__FUNC_B0_SPIM1_MISO>;
+			bias-disable;
+		};
+	};
+
+	spi2_pins: spi2-pins {
+		pins-spi {
+			pinmux = <PINMUX_GPIO79__FUNC_O_SPIM2_CSB>,
+				 <PINMUX_GPIO80__FUNC_O_SPIM2_CLK>,
+				 <PINMUX_GPIO81__FUNC_B0_SPIM2_MOSI>,
+				 <PINMUX_GPIO82__FUNC_B0_SPIM2_MISO>;
+			bias-disable;
+		};
+	};
+
+	uart0_pins: uart0-pins {
+		pins-rx-tx {
+			pinmux = <PINMUX_GPIO31__FUNC_O_UTXD0>,
+				 <PINMUX_GPIO32__FUNC_I1_URXD0>;
+			bias-pull-up;
+		};
+	};
+};
+
+&pmic {
+	interrupts-extended = <&pio 222 IRQ_TYPE_LEVEL_HIGH>;
+};
+
+&scp {
+	memory-region = <&scp_mem_reserved>;
+	status = "okay";
+};
+
+&spi0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&spi0_pins>;
+	status = "okay";
+};
+
+&spi1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&spi1_pins>;
+	status = "okay";
+};
+
+&spi2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&spi2_pins>;
+	status = "okay";
+};
+
+&u3phy0 {
+	status = "okay";
+};
+
+&u3phy1 {
+	status = "okay";
+};
+
+&u3phy2 {
+	status = "okay";
+};
+
+&uart0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart0_pins>;
+	status = "okay";
+};
+
+&xhci0 {
+	status = "okay";
+};
+
+&xhci1 {
+	status = "okay";
+};
+
+&xhci2 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8188.dtsi b/arch/arm64/boot/dts/mediatek/mt8188.dtsi
new file mode 100644
index 000000000000..b4315c9214dc
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8188.dtsi
@@ -0,0 +1,956 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (c) 2023 MediaTek Inc.
+ *
+ */
+
+/dts-v1/;
+#include <dt-bindings/clock/mediatek,mt8188-clk.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/phy/phy.h>
+#include <dt-bindings/pinctrl/mediatek,mt8188-pinfunc.h>
+#include <dt-bindings/power/mediatek,mt8188-power.h>
+
+/ {
+	compatible = "mediatek,mt8188";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a55";
+			reg = <0x000>;
+			enable-method = "psci";
+			clock-frequency = <2000000000>;
+			capacity-dmips-mhz = <282>;
+			cpu-idle-states = <&cpu_off_l &cluster_off_l>;
+			i-cache-size = <32768>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <128>;
+			d-cache-size = <32768>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <128>;
+			next-level-cache = <&l2_0>;
+			#cooling-cells = <2>;
+		};
+
+		cpu1: cpu@100 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a55";
+			reg = <0x100>;
+			enable-method = "psci";
+			clock-frequency = <2000000000>;
+			capacity-dmips-mhz = <282>;
+			cpu-idle-states = <&cpu_off_l &cluster_off_l>;
+			i-cache-size = <32768>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <128>;
+			d-cache-size = <32768>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <128>;
+			next-level-cache = <&l2_0>;
+			#cooling-cells = <2>;
+		};
+
+		cpu2: cpu@200 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a55";
+			reg = <0x200>;
+			enable-method = "psci";
+			clock-frequency = <2000000000>;
+			capacity-dmips-mhz = <282>;
+			cpu-idle-states = <&cpu_off_l &cluster_off_l>;
+			i-cache-size = <32768>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <128>;
+			d-cache-size = <32768>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <128>;
+			next-level-cache = <&l2_0>;
+			#cooling-cells = <2>;
+		};
+
+		cpu3: cpu@300 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a55";
+			reg = <0x300>;
+			enable-method = "psci";
+			clock-frequency = <2000000000>;
+			capacity-dmips-mhz = <282>;
+			cpu-idle-states = <&cpu_off_l &cluster_off_l>;
+			i-cache-size = <32768>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <128>;
+			d-cache-size = <32768>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <128>;
+			next-level-cache = <&l2_0>;
+			#cooling-cells = <2>;
+		};
+
+		cpu4: cpu@400 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a55";
+			reg = <0x400>;
+			enable-method = "psci";
+			clock-frequency = <2000000000>;
+			capacity-dmips-mhz = <282>;
+			cpu-idle-states = <&cpu_off_l &cluster_off_l>;
+			i-cache-size = <32768>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <128>;
+			d-cache-size = <32768>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <128>;
+			next-level-cache = <&l2_0>;
+			#cooling-cells = <2>;
+		};
+
+		cpu5: cpu@500 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a55";
+			reg = <0x500>;
+			enable-method = "psci";
+			clock-frequency = <2000000000>;
+			capacity-dmips-mhz = <282>;
+			cpu-idle-states = <&cpu_off_l &cluster_off_l>;
+			i-cache-size = <32768>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <128>;
+			d-cache-size = <32768>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <128>;
+			next-level-cache = <&l2_0>;
+			#cooling-cells = <2>;
+		};
+
+		cpu6: cpu@600 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a78";
+			reg = <0x600>;
+			enable-method = "psci";
+			clock-frequency = <2600000000>;
+			capacity-dmips-mhz = <1024>;
+			cpu-idle-states = <&cpu_off_b &cluster_off_b>;
+			i-cache-size = <65536>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>;
+			d-cache-size = <65536>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <256>;
+			next-level-cache = <&l2_1>;
+			#cooling-cells = <2>;
+		};
+
+		cpu7: cpu@700 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a78";
+			reg = <0x700>;
+			enable-method = "psci";
+			clock-frequency = <2600000000>;
+			capacity-dmips-mhz = <1024>;
+			cpu-idle-states = <&cpu_off_b &cluster_off_b>;
+			i-cache-size = <65536>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>;
+			d-cache-size = <65536>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <256>;
+			next-level-cache = <&l2_1>;
+			#cooling-cells = <2>;
+		};
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&cpu0>;
+				};
+
+				core1 {
+					cpu = <&cpu1>;
+				};
+
+				core2 {
+					cpu = <&cpu2>;
+				};
+
+				core3 {
+					cpu = <&cpu3>;
+				};
+
+				core4 {
+					cpu = <&cpu4>;
+				};
+
+				core5 {
+					cpu = <&cpu5>;
+				};
+
+				core6 {
+					cpu = <&cpu6>;
+				};
+
+				core7 {
+					cpu = <&cpu7>;
+				};
+			};
+		};
+
+		idle-states {
+			entry-method = "psci";
+
+			cpu_off_l: cpu-off-l {
+				compatible = "arm,idle-state";
+				arm,psci-suspend-param = <0x00010000>;
+				local-timer-stop;
+				entry-latency-us = <50>;
+				exit-latency-us = <95>;
+				min-residency-us = <580>;
+			};
+
+			cpu_off_b: cpu-off-b {
+				compatible = "arm,idle-state";
+				arm,psci-suspend-param = <0x00010000>;
+				local-timer-stop;
+				entry-latency-us = <45>;
+				exit-latency-us = <140>;
+				min-residency-us = <740>;
+			};
+
+			cluster_off_l: cluster-off-l {
+				compatible = "arm,idle-state";
+				arm,psci-suspend-param = <0x01010010>;
+				local-timer-stop;
+				entry-latency-us = <55>;
+				exit-latency-us = <155>;
+				min-residency-us = <840>;
+			};
+
+			cluster_off_b: cluster-off-b {
+				compatible = "arm,idle-state";
+				arm,psci-suspend-param = <0x01010010>;
+				local-timer-stop;
+				entry-latency-us = <50>;
+				exit-latency-us = <200>;
+				min-residency-us = <1000>;
+			};
+		};
+
+		l2_0: l2-cache0 {
+			compatible = "cache";
+			cache-level = <2>;
+			cache-size = <131072>;
+			cache-line-size = <64>;
+			cache-sets = <512>;
+			next-level-cache = <&l3_0>;
+			cache-unified;
+		};
+
+		l2_1: l2-cache1 {
+			compatible = "cache";
+			cache-level = <2>;
+			cache-size = <262144>;
+			cache-line-size = <64>;
+			cache-sets = <512>;
+			next-level-cache = <&l3_0>;
+			cache-unified;
+		};
+
+		l3_0: l3-cache {
+			compatible = "cache";
+			cache-level = <3>;
+			cache-size = <2097152>;
+			cache-line-size = <64>;
+			cache-sets = <2048>;
+			cache-unified;
+		};
+	};
+
+	clk13m: oscillator-13m {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <13000000>;
+		clock-output-names = "clk13m";
+	};
+
+	clk26m: oscillator-26m {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <26000000>;
+		clock-output-names = "clk26m";
+	};
+
+	clk32k: oscillator-32k {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <32768>;
+		clock-output-names = "clk32k";
+	};
+
+	pmu-a55 {
+		compatible = "arm,cortex-a55-pmu";
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_PPI 7 IRQ_TYPE_LEVEL_HIGH &ppi_cluster0>;
+	};
+
+	pmu-a78 {
+		compatible = "arm,cortex-a78-pmu";
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_PPI 7 IRQ_TYPE_LEVEL_HIGH &ppi_cluster1>;
+	};
+
+	psci {
+		compatible = "arm,psci-1.0";
+		method = "smc";
+	};
+
+	timer: timer {
+		compatible = "arm,armv8-timer";
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_PPI 14 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_PPI 10 IRQ_TYPE_LEVEL_HIGH 0>;
+		clock-frequency = <13000000>;
+	};
+
+	soc {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		compatible = "simple-bus";
+		ranges;
+
+		gic: interrupt-controller@c000000 {
+			compatible = "arm,gic-v3";
+			#interrupt-cells = <4>;
+			#redistributor-regions = <1>;
+			interrupt-parent = <&gic>;
+			interrupt-controller;
+			reg = <0 0x0c000000 0 0x40000>,
+			      <0 0x0c040000 0 0x200000>;
+			interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH 0>;
+
+			ppi-partitions {
+				ppi_cluster0: interrupt-partition-0 {
+					affinity = <&cpu0 &cpu1 &cpu2 &cpu3 &cpu4 &cpu5>;
+				};
+
+				ppi_cluster1: interrupt-partition-1 {
+					affinity = <&cpu6 &cpu7>;
+				};
+			};
+		};
+
+		topckgen: syscon@10000000 {
+			compatible = "mediatek,mt8188-topckgen", "syscon";
+			reg = <0 0x10000000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		infracfg_ao: syscon@10001000 {
+			compatible = "mediatek,mt8188-infracfg-ao", "syscon";
+			reg = <0 0x10001000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		pericfg: syscon@10003000 {
+			compatible = "mediatek,mt8188-pericfg", "syscon";
+			reg = <0 0x10003000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		pio: pinctrl@10005000 {
+			compatible = "mediatek,mt8188-pinctrl";
+			reg = <0 0x10005000 0 0x1000>,
+			      <0 0x11c00000 0 0x1000>,
+			      <0 0x11e10000 0 0x1000>,
+			      <0 0x11e20000 0 0x1000>,
+			      <0 0x11ea0000 0 0x1000>,
+			      <0 0x1000b000 0 0x1000>;
+			reg-names = "iocfg0", "iocfg_rm", "iocfg_lt",
+				    "iocfg_lm", "iocfg_rt", "eint";
+			gpio-controller;
+			#gpio-cells = <2>;
+			gpio-ranges = <&pio 0 0 176>;
+			interrupt-controller;
+			interrupts = <GIC_SPI 235 IRQ_TYPE_LEVEL_HIGH 0>;
+			#interrupt-cells = <2>;
+		};
+
+		watchdog: watchdog@10007000 {
+			compatible = "mediatek,mt8188-wdt";
+			reg = <0 0x10007000 0 0x100>;
+			mediatek,disable-extrst;
+			#reset-cells = <1>;
+		};
+
+		apmixedsys: syscon@1000c000 {
+			compatible = "mediatek,mt8188-apmixedsys", "syscon";
+			reg = <0 0x1000c000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		systimer: timer@10017000 {
+			compatible = "mediatek,mt8188-timer", "mediatek,mt6765-timer";
+			reg = <0 0x10017000 0 0x1000>;
+			interrupts = <GIC_SPI 265 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&clk13m>;
+		};
+
+		pwrap: pwrap@10024000 {
+			compatible = "mediatek,mt8188-pwrap", "mediatek,mt8195-pwrap", "syscon";
+			reg = <0 0x10024000 0 0x1000>;
+			reg-names = "pwrap";
+			interrupts = <GIC_SPI 243 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&infracfg_ao CLK_INFRA_AO_PMIC_AP>,
+				 <&infracfg_ao CLK_INFRA_AO_PMIC_TMR>;
+			clock-names = "spi", "wrap";
+		};
+
+		scp: scp@10500000 {
+			compatible = "mediatek,mt8188-scp";
+			reg = <0 0x10500000 0 0x100000>,
+			      <0 0x10720000 0 0xe0000>;
+			reg-names = "sram", "cfg";
+			interrupts = <GIC_SPI 462 IRQ_TYPE_LEVEL_HIGH 0>;
+		};
+
+		adsp_audio26m: clock-controller@10b91100 {
+			compatible = "mediatek,mt8188-adsp-audio26m";
+			reg = <0 0x10b91100 0 0x100>;
+			#clock-cells = <1>;
+		};
+
+		uart0: serial@11001100 {
+			compatible = "mediatek,mt8188-uart", "mediatek,mt6577-uart";
+			reg = <0 0x11001100 0 0x100>;
+			interrupts = <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&clk26m>, <&infracfg_ao CLK_INFRA_AO_UART0>;
+			clock-names = "baud", "bus";
+			status = "disabled";
+		};
+
+		uart1: serial@11001200 {
+			compatible = "mediatek,mt8188-uart", "mediatek,mt6577-uart";
+			reg = <0 0x11001200 0 0x100>;
+			interrupts = <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&clk26m>, <&infracfg_ao CLK_INFRA_AO_UART1>;
+			clock-names = "baud", "bus";
+			status = "disabled";
+		};
+
+		uart2: serial@11001300 {
+			compatible = "mediatek,mt8188-uart", "mediatek,mt6577-uart";
+			reg = <0 0x11001300 0 0x100>;
+			interrupts = <GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&clk26m>, <&infracfg_ao CLK_INFRA_AO_UART2>;
+			clock-names = "baud", "bus";
+			status = "disabled";
+		};
+
+		uart3: serial@11001400 {
+			compatible = "mediatek,mt8188-uart", "mediatek,mt6577-uart";
+			reg = <0 0x11001400 0 0x100>;
+			interrupts = <GIC_SPI 723 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&clk26m>, <&infracfg_ao CLK_INFRA_AO_UART3>;
+			clock-names = "baud", "bus";
+			status = "disabled";
+		};
+
+		auxadc: adc@11002000 {
+			compatible = "mediatek,mt8188-auxadc", "mediatek,mt8173-auxadc";
+			reg = <0 0x11002000 0 0x1000>;
+			clocks = <&infracfg_ao CLK_INFRA_AO_AUXADC>;
+			clock-names = "main";
+			#io-channel-cells = <1>;
+			status = "disabled";
+		};
+
+		pericfg_ao: syscon@11003000 {
+			compatible = "mediatek,mt8188-pericfg-ao", "syscon";
+			reg = <0 0x11003000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		spi0: spi@1100a000 {
+			compatible = "mediatek,mt8188-spi-ipm", "mediatek,spi-ipm";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0 0x1100a000 0 0x1000>;
+			interrupts = <GIC_SPI 191 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&topckgen CLK_TOP_UNIVPLL_D6_D2>,
+				 <&topckgen CLK_TOP_SPI>,
+				 <&infracfg_ao CLK_INFRA_AO_SPI0>;
+			clock-names = "parent-clk", "sel-clk", "spi-clk";
+			status = "disabled";
+		};
+
+		spi1: spi@11010000 {
+			compatible = "mediatek,mt8188-spi-ipm", "mediatek,spi-ipm";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0 0x11010000 0 0x1000>;
+			interrupts = <GIC_SPI 192 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&topckgen CLK_TOP_UNIVPLL_D6_D2>,
+				 <&topckgen CLK_TOP_SPI>,
+				 <&infracfg_ao CLK_INFRA_AO_SPI1>;
+			clock-names = "parent-clk", "sel-clk", "spi-clk";
+			status = "disabled";
+		};
+
+		spi2: spi@11012000 {
+			compatible = "mediatek,mt8188-spi-ipm", "mediatek,spi-ipm";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0 0x11012000 0 0x1000>;
+			interrupts = <GIC_SPI 193 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&topckgen CLK_TOP_UNIVPLL_D6_D2>,
+				 <&topckgen CLK_TOP_SPI>,
+				 <&infracfg_ao CLK_INFRA_AO_SPI2>;
+			clock-names = "parent-clk", "sel-clk", "spi-clk";
+			status = "disabled";
+		};
+
+		spi3: spi@11013000 {
+			compatible = "mediatek,mt8188-spi-ipm", "mediatek,spi-ipm";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0 0x11013000 0 0x1000>;
+			interrupts = <GIC_SPI 194 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&topckgen CLK_TOP_UNIVPLL_D6_D2>,
+				 <&topckgen CLK_TOP_SPI>,
+				 <&infracfg_ao CLK_INFRA_AO_SPI3>;
+			clock-names = "parent-clk", "sel-clk", "spi-clk";
+			status = "disabled";
+		};
+
+		spi4: spi@11018000 {
+			compatible = "mediatek,mt8188-spi-ipm", "mediatek,spi-ipm";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0 0x11018000 0 0x1000>;
+			interrupts = <GIC_SPI 195 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&topckgen CLK_TOP_UNIVPLL_D6_D2>,
+				 <&topckgen CLK_TOP_SPI>,
+				 <&infracfg_ao CLK_INFRA_AO_SPI4>;
+			clock-names = "parent-clk", "sel-clk", "spi-clk";
+			status = "disabled";
+		};
+
+		spi5: spi@11019000 {
+			compatible = "mediatek,mt8188-spi-ipm", "mediatek,spi-ipm";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0 0x11019000 0 0x1000>;
+			interrupts = <GIC_SPI 196 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&topckgen CLK_TOP_UNIVPLL_D6_D2>,
+				 <&topckgen CLK_TOP_SPI>,
+				 <&infracfg_ao CLK_INFRA_AO_SPI5>;
+			clock-names = "parent-clk", "sel-clk", "spi-clk";
+			status = "disabled";
+		};
+
+		xhci1: usb@11200000 {
+			compatible = "mediatek,mt8188-xhci", "mediatek,mtk-xhci";
+			reg = <0 0x11200000 0 0x1000>,
+			      <0 0x11203e00 0 0x0100>;
+			reg-names = "mac", "ippc";
+			interrupts = <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH 0>;
+			phys = <&u2port1 PHY_TYPE_USB2>,
+			       <&u3port1 PHY_TYPE_USB3>;
+			assigned-clocks = <&topckgen CLK_TOP_USB_TOP>,
+					  <&topckgen CLK_TOP_SSUSB_XHCI>;
+			assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D5_D4>,
+						 <&topckgen CLK_TOP_UNIVPLL_D5_D4>;
+			clocks = <&pericfg_ao CLK_PERI_AO_SSUSB_BUS>,
+				 <&topckgen CLK_TOP_SSUSB_TOP_REF>,
+				 <&pericfg_ao CLK_PERI_AO_SSUSB_XHCI>;
+			clock-names = "sys_ck", "ref_ck", "mcu_ck";
+			mediatek,syscon-wakeup = <&pericfg 0x468 2>;
+			wakeup-source;
+			status = "disabled";
+		};
+
+		mmc0: mmc@11230000 {
+			compatible = "mediatek,mt8188-mmc", "mediatek,mt8183-mmc";
+			reg = <0 0x11230000 0 0x10000>,
+			      <0 0x11f50000 0 0x1000>;
+			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&topckgen CLK_TOP_MSDC50_0>,
+				 <&infracfg_ao CLK_INFRA_AO_MSDC0>,
+				 <&infracfg_ao CLK_INFRA_AO_MSDC0_SRC>,
+				 <&infracfg_ao CLK_INFRA_AO_RG_AES_MSDCFDE_CK_0P>;
+			clock-names = "source", "hclk", "source_cg", "crypto_clk";
+			status = "disabled";
+		};
+
+		mmc1: mmc@11240000 {
+			compatible = "mediatek,mt8188-mmc", "mediatek,mt8183-mmc";
+			reg = <0 0x11240000 0 0x1000>,
+			      <0 0x11eb0000 0 0x1000>;
+			interrupts = <GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&topckgen CLK_TOP_MSDC30_1>,
+				 <&infracfg_ao CLK_INFRA_AO_MSDC1>,
+				 <&infracfg_ao CLK_INFRA_AO_MSDC1_SRC>;
+			clock-names = "source", "hclk", "source_cg";
+			assigned-clocks = <&topckgen CLK_TOP_MSDC30_1>;
+			assigned-clock-parents = <&topckgen CLK_TOP_MSDCPLL_D2>;
+			status = "disabled";
+		};
+
+		i2c0: i2c@11280000 {
+			compatible = "mediatek,mt8188-i2c";
+			reg = <0 0x11280000 0 0x1000>,
+			      <0 0x10220080 0 0x80>;
+			interrupts = <GIC_SPI 151 IRQ_TYPE_LEVEL_HIGH 0>;
+			clock-div = <1>;
+			clocks = <&imp_iic_wrap_c CLK_IMP_IIC_WRAP_C_AP_CLOCK_I2C0>,
+				 <&infracfg_ao CLK_INFRA_AO_APDMA_BCLK>;
+			clock-names = "main", "dma";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		i2c2: i2c@11281000 {
+			compatible = "mediatek,mt8188-i2c";
+			reg = <0 0x11281000 0 0x1000>,
+			      <0 0x10220180 0 0x80>;
+			interrupts = <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH 0>;
+			clock-div = <1>;
+			clocks = <&imp_iic_wrap_c CLK_IMP_IIC_WRAP_C_AP_CLOCK_I2C2>,
+				 <&infracfg_ao CLK_INFRA_AO_APDMA_BCLK>;
+			clock-names = "main", "dma";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		i2c3: i2c@11282000 {
+			compatible = "mediatek,mt8188-i2c";
+			reg = <0 0x11282000 0 0x1000>,
+			      <0 0x10220280 0 0x80>;
+			interrupts = <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH 0>;
+			clock-div = <1>;
+			clocks = <&imp_iic_wrap_c CLK_IMP_IIC_WRAP_C_AP_CLOCK_I2C3>,
+				 <&infracfg_ao CLK_INFRA_AO_APDMA_BCLK>;
+			clock-names = "main", "dma";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		imp_iic_wrap_c: clock-controller@11283000 {
+			compatible = "mediatek,mt8188-imp-iic-wrap-c";
+			reg = <0 0x11283000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		xhci2: usb@112a0000 {
+			compatible = "mediatek,mt8188-xhci", "mediatek,mtk-xhci";
+			reg = <0 0x112a0000 0 0x1000>,
+			      <0 0x112a3e00 0 0x0100>;
+			reg-names = "mac", "ippc";
+			interrupts = <GIC_SPI 536 IRQ_TYPE_LEVEL_HIGH 0>;
+			phys = <&u2port2 PHY_TYPE_USB2>;
+			assigned-clocks = <&topckgen CLK_TOP_SSUSB_XHCI_3P>,
+					  <&topckgen CLK_TOP_USB_TOP_3P>;
+			assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D5_D4>,
+						 <&topckgen CLK_TOP_UNIVPLL_D5_D4>;
+			clocks = <&pericfg_ao CLK_PERI_AO_SSUSB_3P_BUS>,
+				 <&topckgen CLK_TOP_SSUSB_TOP_P3_REF>,
+				 <&pericfg_ao CLK_PERI_AO_SSUSB_3P_XHCI>;
+			clock-names = "sys_ck", "ref_ck", "mcu_ck";
+			status = "disabled";
+		};
+
+		xhci0: usb@112b0000 {
+			compatible = "mediatek,mt8188-xhci", "mediatek,mtk-xhci";
+			reg = <0 0x112b0000 0 0x1000>,
+			      <0 0x112b3e00 0 0x0100>;
+			reg-names = "mac", "ippc";
+			interrupts = <GIC_SPI 533 IRQ_TYPE_LEVEL_HIGH 0>;
+			phys = <&u2port0 PHY_TYPE_USB2>;
+			assigned-clocks = <&topckgen CLK_TOP_SSUSB_XHCI_2P>,
+					  <&topckgen CLK_TOP_USB_TOP_2P>;
+			assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D5_D4>,
+						 <&topckgen CLK_TOP_UNIVPLL_D5_D4>;
+			clocks = <&pericfg_ao CLK_PERI_AO_SSUSB_2P_BUS>,
+				 <&topckgen CLK_TOP_SSUSB_TOP_P2_REF>,
+				 <&pericfg_ao CLK_PERI_AO_SSUSB_2P_XHCI>;
+			clock-names = "sys_ck", "ref_ck", "mcu_ck";
+			mediatek,syscon-wakeup = <&pericfg 0x460 2>;
+			wakeup-source;
+			status = "disabled";
+		};
+
+		nor_flash: spi@1132c000 {
+			compatible = "mediatek,mt8188-nor", "mediatek,mt8186-nor";
+			reg = <0 0x1132c000 0 0x1000>;
+			clocks = <&topckgen CLK_TOP_SPINOR>,
+				 <&pericfg_ao CLK_PERI_AO_FLASHIFLASHCK>,
+				 <&pericfg_ao CLK_PERI_AO_FLASHIF_BUS>;
+			clock-names = "spi", "sf", "axi";
+			assigned-clocks = <&topckgen CLK_TOP_SPINOR>;
+			interrupts = <GIC_SPI 825 IRQ_TYPE_LEVEL_HIGH 0>;
+			status = "disabled";
+		};
+
+		i2c1: i2c@11e00000 {
+			compatible = "mediatek,mt8188-i2c";
+			reg = <0 0x11e00000 0 0x1000>,
+			      <0 0x10220100 0 0x80>;
+			interrupts = <GIC_SPI 152 IRQ_TYPE_LEVEL_HIGH 0>;
+			clock-div = <1>;
+			clocks = <&imp_iic_wrap_w CLK_IMP_IIC_WRAP_W_AP_CLOCK_I2C1>,
+				 <&infracfg_ao CLK_INFRA_AO_APDMA_BCLK>;
+			clock-names = "main", "dma";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		i2c4: i2c@11e01000 {
+			compatible = "mediatek,mt8188-i2c";
+			reg = <0 0x11e01000 0 0x1000>,
+			      <0 0x10220380 0 0x80>;
+			interrupts = <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH 0>;
+			clock-div = <1>;
+			clocks = <&imp_iic_wrap_w CLK_IMP_IIC_WRAP_W_AP_CLOCK_I2C4>,
+				 <&infracfg_ao CLK_INFRA_AO_APDMA_BCLK>;
+			clock-names = "main", "dma";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		imp_iic_wrap_w: clock-controller@11e02000 {
+			compatible = "mediatek,mt8188-imp-iic-wrap-w";
+			reg = <0 0x11e02000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		u3phy0: t-phy@11e30000 {
+			compatible = "mediatek,mt8188-tphy", "mediatek,generic-tphy-v3";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0x0 0x0 0x11e30000 0x1000>;
+			status = "disabled";
+
+			u2port0: usb-phy@0 {
+				reg = <0x0 0x700>;
+				clocks = <&topckgen CLK_TOP_SSUSB_PHY_P2_REF>,
+					 <&apmixedsys CLK_APMIXED_PLL_SSUSB26M_EN>;
+				clock-names = "ref", "da_ref";
+				#phy-cells = <1>;
+			};
+		};
+
+		u3phy1: t-phy@11e40000 {
+			compatible = "mediatek,mt8188-tphy", "mediatek,generic-tphy-v3";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0x0 0x0 0x11e40000 0x1000>;
+			status = "disabled";
+
+			u2port1: usb-phy@0 {
+				reg = <0x0 0x700>;
+				clocks = <&topckgen CLK_TOP_SSUSB_PHY_REF>,
+					 <&apmixedsys CLK_APMIXED_PLL_SSUSB26M_EN>;
+				clock-names = "ref", "da_ref";
+				#phy-cells = <1>;
+			};
+
+			u3port1: usb-phy@700 {
+				reg = <0x700 0x700>;
+				clocks = <&apmixedsys CLK_APMIXED_PLL_SSUSB26M_EN>,
+					 <&clk26m>;
+				clock-names = "ref", "da_ref";
+				#phy-cells = <1>;
+				status = "disabled";
+			};
+		};
+
+		u3phy2: t-phy@11e80000 {
+			compatible = "mediatek,mt8188-tphy", "mediatek,generic-tphy-v3";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0x0 0x0 0x11e80000 0x1000>;
+			status = "disabled";
+
+			u2port2: usb-phy@0 {
+				reg = <0x0 0x700>;
+				clocks = <&topckgen CLK_TOP_SSUSB_PHY_P3_REF>,
+					 <&apmixedsys CLK_APMIXED_PLL_SSUSB26M_EN>;
+				clock-names = "ref", "da_ref";
+				#phy-cells = <1>;
+			};
+		};
+
+		i2c5: i2c@11ec0000 {
+			compatible = "mediatek,mt8188-i2c";
+			reg = <0 0x11ec0000 0 0x1000>,
+			      <0 0x10220480 0 0x80>;
+			interrupts = <GIC_SPI 149 IRQ_TYPE_LEVEL_HIGH 0>;
+			clock-div = <1>;
+			clocks = <&imp_iic_wrap_en CLK_IMP_IIC_WRAP_EN_AP_CLOCK_I2C5>,
+				 <&infracfg_ao CLK_INFRA_AO_APDMA_BCLK>;
+			clock-names = "main", "dma";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		i2c6: i2c@11ec1000 {
+			compatible = "mediatek,mt8188-i2c";
+			reg = <0 0x11ec1000 0 0x1000>,
+			      <0 0x10220600 0 0x80>;
+			interrupts = <GIC_SPI 150 IRQ_TYPE_LEVEL_HIGH 0>;
+			clock-div = <1>;
+			clocks = <&imp_iic_wrap_en CLK_IMP_IIC_WRAP_EN_AP_CLOCK_I2C6>,
+				 <&infracfg_ao CLK_INFRA_AO_APDMA_BCLK>;
+			clock-names = "main", "dma";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		imp_iic_wrap_en: clock-controller@11ec2000 {
+			compatible = "mediatek,mt8188-imp-iic-wrap-en";
+			reg = <0 0x11ec2000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		mfgcfg: clock-controller@13fbf000 {
+			compatible = "mediatek,mt8188-mfgcfg";
+			reg = <0 0x13fbf000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		vppsys0: clock-controller@14000000 {
+			compatible = "mediatek,mt8188-vppsys0";
+			reg = <0 0x14000000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		wpesys: clock-controller@14e00000 {
+			compatible = "mediatek,mt8188-wpesys";
+			reg = <0 0x14e00000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		wpesys_vpp0: clock-controller@14e02000 {
+			compatible = "mediatek,mt8188-wpesys-vpp0";
+			reg = <0 0x14e02000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		vppsys1: clock-controller@14f00000 {
+			compatible = "mediatek,mt8188-vppsys1";
+			reg = <0 0x14f00000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		imgsys: clock-controller@15000000 {
+			compatible = "mediatek,mt8188-imgsys";
+			reg = <0 0x15000000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		imgsys1_dip_top: clock-controller@15110000 {
+			compatible = "mediatek,mt8188-imgsys1-dip-top";
+			reg = <0 0x15110000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		imgsys1_dip_nr: clock-controller@15130000 {
+			compatible = "mediatek,mt8188-imgsys1-dip-nr";
+			reg = <0 0x15130000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		imgsys_wpe1: clock-controller@15220000 {
+			compatible = "mediatek,mt8188-imgsys-wpe1";
+			reg = <0 0x15220000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		ipesys: clock-controller@15330000 {
+			compatible = "mediatek,mt8188-ipesys";
+			reg = <0 0x15330000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		imgsys_wpe2: clock-controller@15520000 {
+			compatible = "mediatek,mt8188-imgsys-wpe2";
+			reg = <0 0x15520000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		imgsys_wpe3: clock-controller@15620000 {
+			compatible = "mediatek,mt8188-imgsys-wpe3";
+			reg = <0 0x15620000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		camsys: clock-controller@16000000 {
+			compatible = "mediatek,mt8188-camsys";
+			reg = <0 0x16000000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		camsys_rawa: clock-controller@1604f000 {
+			compatible = "mediatek,mt8188-camsys-rawa";
+			reg = <0 0x1604f000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		camsys_yuva: clock-controller@1606f000 {
+			compatible = "mediatek,mt8188-camsys-yuva";
+			reg = <0 0x1606f000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		camsys_rawb: clock-controller@1608f000 {
+			compatible = "mediatek,mt8188-camsys-rawb";
+			reg = <0 0x1608f000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		camsys_yuvb: clock-controller@160af000 {
+			compatible = "mediatek,mt8188-camsys-yuvb";
+			reg = <0 0x160af000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		ccusys: clock-controller@17200000 {
+			compatible = "mediatek,mt8188-ccusys";
+			reg = <0 0x17200000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		vdecsys_soc: clock-controller@1800f000 {
+			compatible = "mediatek,mt8188-vdecsys-soc";
+			reg = <0 0x1800f000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		vdecsys: clock-controller@1802f000 {
+			compatible = "mediatek,mt8188-vdecsys";
+			reg = <0 0x1802f000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		vencsys: clock-controller@1a000000 {
+			compatible = "mediatek,mt8188-vencsys";
+			reg = <0 0x1a000000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8192.dtsi b/arch/arm64/boot/dts/mediatek/mt8192.dtsi
index 69f4cded5dbb..6dd32dbfb832 100644
--- a/arch/arm64/boot/dts/mediatek/mt8192.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8192.dtsi
@@ -14,6 +14,8 @@
 #include <dt-bindings/phy/phy.h>
 #include <dt-bindings/power/mt8192-power.h>
 #include <dt-bindings/reset/mt8192-resets.h>
+#include <dt-bindings/thermal/thermal.h>
+#include <dt-bindings/thermal/mediatek,lvts-thermal.h>
 
 / {
 	compatible = "mediatek,mt8192";
@@ -72,6 +74,7 @@
 			next-level-cache = <&l2_0>;
 			performance-domains = <&performance 0>;
 			capacity-dmips-mhz = <427>;
+			#cooling-cells = <2>;
 		};
 
 		cpu1: cpu@100 {
@@ -90,6 +93,7 @@
 			next-level-cache = <&l2_0>;
 			performance-domains = <&performance 0>;
 			capacity-dmips-mhz = <427>;
+			#cooling-cells = <2>;
 		};
 
 		cpu2: cpu@200 {
@@ -108,6 +112,7 @@
 			next-level-cache = <&l2_0>;
 			performance-domains = <&performance 0>;
 			capacity-dmips-mhz = <427>;
+			#cooling-cells = <2>;
 		};
 
 		cpu3: cpu@300 {
@@ -126,6 +131,7 @@
 			next-level-cache = <&l2_0>;
 			performance-domains = <&performance 0>;
 			capacity-dmips-mhz = <427>;
+			#cooling-cells = <2>;
 		};
 
 		cpu4: cpu@400 {
@@ -144,6 +150,7 @@
 			next-level-cache = <&l2_1>;
 			performance-domains = <&performance 1>;
 			capacity-dmips-mhz = <1024>;
+			#cooling-cells = <2>;
 		};
 
 		cpu5: cpu@500 {
@@ -162,6 +169,7 @@
 			next-level-cache = <&l2_1>;
 			performance-domains = <&performance 1>;
 			capacity-dmips-mhz = <1024>;
+			#cooling-cells = <2>;
 		};
 
 		cpu6: cpu@600 {
@@ -180,6 +188,7 @@
 			next-level-cache = <&l2_1>;
 			performance-domains = <&performance 1>;
 			capacity-dmips-mhz = <1024>;
+			#cooling-cells = <2>;
 		};
 
 		cpu7: cpu@700 {
@@ -198,6 +207,7 @@
 			next-level-cache = <&l2_1>;
 			performance-domains = <&performance 1>;
 			capacity-dmips-mhz = <1024>;
+			#cooling-cells = <2>;
 		};
 
 		cpu-map {
@@ -788,6 +798,29 @@
 			status = "disabled";
 		};
 
+		lvts_ap: thermal-sensor@1100b000 {
+			compatible = "mediatek,mt8192-lvts-ap";
+			reg = <0 0x1100b000 0 0xc00>;
+			interrupts = <GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&infracfg CLK_INFRA_THERM>;
+			resets = <&infracfg MT8192_INFRA_RST0_THERM_CTRL_SWRST>;
+			nvmem-cells = <&lvts_e_data1>;
+			nvmem-cell-names = "lvts-calib-data-1";
+			#thermal-sensor-cells = <1>;
+		};
+
+		svs: svs@1100bc00 {
+			compatible = "mediatek,mt8192-svs";
+			reg = <0 0x1100bc00 0 0x400>;
+			interrupts = <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&infracfg CLK_INFRA_THERM>;
+			clock-names = "main";
+			nvmem-cells = <&svs_calibration>, <&lvts_e_data1>;
+			nvmem-cell-names = "svs-calibration-data", "t-calibration-data";
+			resets = <&infracfg MT8192_INFRA_RST3_THERM_CTRL_PTP_SWRST>;
+			reset-names = "svs_rst";
+		};
+
 		pwm0: pwm@1100e000 {
 			compatible = "mediatek,mt8183-disp-pwm";
 			reg = <0 0x1100e000 0 0x1000>;
@@ -1114,6 +1147,17 @@
 			status = "disabled";
 		};
 
+		lvts_mcu: thermal-sensor@11278000 {
+			compatible = "mediatek,mt8192-lvts-mcu";
+			reg = <0 0x11278000 0 0x1000>;
+			interrupts = <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&infracfg CLK_INFRA_THERM>;
+			resets = <&infracfg MT8192_INFRA_RST4_THERM_CTRL_MCU_SWRST>;
+			nvmem-cells = <&lvts_e_data1>;
+			nvmem-cell-names = "lvts-calib-data-1";
+			#thermal-sensor-cells = <1>;
+		};
+
 		efuse: efuse@11c10000 {
 			compatible = "mediatek,mt8192-efuse", "mediatek,efuse";
 			reg = <0 0x11c10000 0 0x1000>;
@@ -1899,4 +1943,426 @@
 			power-domains = <&spm MT8192_POWER_DOMAIN_MDP>;
 		};
 	};
+
+	thermal_zones: thermal-zones {
+		cpu0-thermal {
+			polling-delay = <1000>;
+			polling-delay-passive = <250>;
+			thermal-sensors = <&lvts_mcu MT8192_MCU_LITTLE_CPU0>;
+
+			trips {
+				cpu0_alert: trip-alert {
+					temperature = <85000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu0_crit: trip-crit {
+					temperature = <100000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu0_alert>;
+					cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		cpu1-thermal {
+			polling-delay = <1000>;
+			polling-delay-passive = <250>;
+			thermal-sensors = <&lvts_mcu MT8192_MCU_LITTLE_CPU1>;
+
+			trips {
+				cpu1_alert: trip-alert {
+					temperature = <85000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu1_crit: trip-crit {
+					temperature = <100000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu1_alert>;
+					cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		cpu2-thermal {
+			polling-delay = <1000>;
+			polling-delay-passive = <250>;
+			thermal-sensors = <&lvts_mcu MT8192_MCU_LITTLE_CPU2>;
+
+			trips {
+				cpu2_alert: trip-alert {
+					temperature = <85000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu2_crit: trip-crit {
+					temperature = <100000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu2_alert>;
+					cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		cpu3-thermal {
+			polling-delay = <1000>;
+			polling-delay-passive = <250>;
+			thermal-sensors = <&lvts_mcu MT8192_MCU_LITTLE_CPU3>;
+
+			trips {
+				cpu3_alert: trip-alert {
+					temperature = <85000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu3_crit: trip-crit {
+					temperature = <100000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu3_alert>;
+					cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		cpu4-thermal {
+			polling-delay = <1000>;
+			polling-delay-passive = <250>;
+			thermal-sensors = <&lvts_mcu MT8192_MCU_BIG_CPU0>;
+
+			trips {
+				cpu4_alert: trip-alert {
+					temperature = <85000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu4_crit: trip-crit {
+					temperature = <100000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu4_alert>;
+					cooling-device = <&cpu4 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu5 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu6 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu7 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		cpu5-thermal {
+			polling-delay = <1000>;
+			polling-delay-passive = <250>;
+			thermal-sensors = <&lvts_mcu MT8192_MCU_BIG_CPU1>;
+
+			trips {
+				cpu5_alert: trip-alert {
+					temperature = <85000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu5_crit: trip-crit {
+					temperature = <100000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu5_alert>;
+					cooling-device = <&cpu4 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu5 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu6 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu7 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		cpu6-thermal {
+			polling-delay = <1000>;
+			polling-delay-passive = <250>;
+			thermal-sensors = <&lvts_mcu MT8192_MCU_BIG_CPU2>;
+
+			trips {
+				cpu6_alert: trip-alert {
+					temperature = <85000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu6_crit: trip-crit {
+					temperature = <100000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu6_alert>;
+					cooling-device = <&cpu4 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu5 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu6 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu7 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		cpu7-thermal {
+			polling-delay = <1000>;
+			polling-delay-passive = <250>;
+			thermal-sensors = <&lvts_mcu MT8192_MCU_BIG_CPU3>;
+
+			trips {
+				cpu7_alert: trip-alert {
+					temperature = <85000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu7_crit: trip-crit {
+					temperature = <100000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu7_alert>;
+					cooling-device = <&cpu4 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu5 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu6 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu7 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		vpu0-thermal {
+			polling-delay = <1000>;
+			polling-delay-passive = <250>;
+			thermal-sensors = <&lvts_ap MT8192_AP_VPU0>;
+
+			trips {
+				vpu0_alert: trip-alert {
+					temperature = <85000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				vpu0_crit: trip-crit {
+					temperature = <100000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+		};
+
+		vpu1-thermal {
+			polling-delay = <1000>;
+			polling-delay-passive = <250>;
+			thermal-sensors = <&lvts_ap MT8192_AP_VPU1>;
+
+			trips {
+				vpu1_alert: trip-alert {
+					temperature = <85000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				vpu1_crit: trip-crit {
+					temperature = <100000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+		};
+
+		gpu0-thermal {
+			polling-delay = <1000>;
+			polling-delay-passive = <250>;
+			thermal-sensors = <&lvts_ap MT8192_AP_GPU0>;
+
+			trips {
+				gpu0_alert: trip-alert {
+					temperature = <85000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				gpu0_crit: trip-crit {
+					temperature = <100000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+		};
+
+		gpu1-thermal {
+			polling-delay = <1000>;
+			polling-delay-passive = <250>;
+			thermal-sensors = <&lvts_ap MT8192_AP_GPU1>;
+
+			trips {
+				gpu1_alert: trip-alert {
+					temperature = <85000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				gpu1_crit: trip-crit {
+					temperature = <100000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+		};
+
+		infra-thermal {
+			polling-delay = <1000>;
+			polling-delay-passive = <250>;
+			thermal-sensors = <&lvts_ap MT8192_AP_INFRA>;
+
+			trips {
+				infra_alert: trip-alert {
+					temperature = <85000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				infra_crit: trip-crit {
+					temperature = <100000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+		};
+
+		cam-thermal {
+			polling-delay = <1000>;
+			polling-delay-passive = <250>;
+			thermal-sensors = <&lvts_ap MT8192_AP_CAM>;
+
+			trips {
+				cam_alert: trip-alert {
+					temperature = <85000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cam_crit: trip-crit {
+					temperature = <100000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+		};
+
+		md0-thermal {
+			polling-delay = <1000>;
+			polling-delay-passive = <250>;
+			thermal-sensors = <&lvts_ap MT8192_AP_MD0>;
+
+			trips {
+				md0_alert: trip-alert {
+					temperature = <85000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				md0_crit: trip-crit {
+					temperature = <100000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+		};
+
+		md1-thermal {
+			polling-delay = <1000>;
+			polling-delay-passive = <250>;
+			thermal-sensors = <&lvts_ap MT8192_AP_MD1>;
+
+			trips {
+				md1_alert: trip-alert {
+					temperature = <85000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				md1_crit: trip-crit {
+					temperature = <100000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+		};
+
+		md2-thermal {
+			polling-delay = <1000>;
+			polling-delay-passive = <250>;
+			thermal-sensors = <&lvts_ap MT8192_AP_MD2>;
+
+			trips {
+				md2_alert: trip-alert {
+					temperature = <85000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				md2_crit: trip-crit {
+					temperature = <100000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+		};
+	};
 };
diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
index dd5b89b73190..bbdcd441c049 100644
--- a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
@@ -127,6 +127,77 @@
 		regulator-boot-on;
 	};
 
+	/* Murata NCP03WF104F05RL */
+	tboard_thermistor1: thermal-sensor-t1 {
+		compatible = "generic-adc-thermal";
+		#thermal-sensor-cells = <0>;
+		io-channels = <&auxadc 0>;
+		io-channel-names = "sensor-channel";
+		temperature-lookup-table = <	(-10000) 1553
+						(-5000) 1485
+						0 1406
+						5000 1317
+						10000 1219
+						15000 1115
+						20000 1007
+						25000 900
+						30000 796
+						35000 697
+						40000 605
+						45000 523
+						50000 449
+						55000 384
+						60000 327
+						65000 279
+						70000 237
+						75000 202
+						80000 172
+						85000 147
+						90000 125
+						95000 107
+						100000 92
+						105000 79
+						110000 68
+						115000 59
+						120000 51
+						125000 44>;
+	};
+
+	tboard_thermistor2: thermal-sensor-t2 {
+		compatible = "generic-adc-thermal";
+		#thermal-sensor-cells = <0>;
+		io-channels = <&auxadc 1>;
+		io-channel-names = "sensor-channel";
+		temperature-lookup-table = <	(-10000) 1553
+						(-5000) 1485
+						0 1406
+						5000 1317
+						10000 1219
+						15000 1115
+						20000 1007
+						25000 900
+						30000 796
+						35000 697
+						40000 605
+						45000 523
+						50000 449
+						55000 384
+						60000 327
+						65000 279
+						70000 237
+						75000 202
+						80000 172
+						85000 147
+						90000 125
+						95000 107
+						100000 92
+						105000 79
+						110000 68
+						115000 59
+						120000 51
+						125000 44>;
+	};
+
 	usb_vbus: regulator-5v0-usb-vbus {
 		compatible = "regulator-fixed";
 		regulator-name = "usb-vbus";
@@ -189,6 +260,10 @@
 	memory-region = <&afe_mem>;
 };
 
+&auxadc {
+	status = "okay";
+};
+
 &dp_intf0 {
 	status = "okay";
 
@@ -389,7 +464,7 @@
 	pinctrl-0 = <&i2c7_pins>;
 
 	pmic@34 {
-		#interrupt-cells = <1>;
+		#interrupt-cells = <2>;
 		compatible = "mediatek,mt6360";
 		reg = <0x34>;
 		interrupt-controller;
@@ -401,6 +476,14 @@
 	};
 };
 
+&mfg0 {
+	domain-supply = <&mt6315_7_vbuck1>;
+};
+
+&mfg1 {
+	domain-supply = <&mt6359_vsram_others_ldo_reg>;
+};
+
 &mmc0 {
 	status = "okay";
 
@@ -471,7 +554,6 @@
 
 /* for GPU SRAM */
 &mt6359_vsram_others_ldo_reg {
-	regulator-always-on;
 	regulator-min-microvolt = <750000>;
 	regulator-max-microvolt = <750000>;
 };
@@ -1154,7 +1236,36 @@
 				regulator-enable-ramp-delay = <256>;
 				regulator-ramp-delay = <6250>;
 				regulator-allowed-modes = <0 1 2>;
-				regulator-always-on;
+			};
+		};
+	};
+};
+
+&thermal_zones {
+	soc-area-thermal {
+		polling-delay = <1000>;
+		polling-delay-passive = <250>;
+		thermal-sensors = <&tboard_thermistor1>;
+
+		trips {
+			trip-crit {
+				temperature = <84000>;
+				hysteresis = <1000>;
+				type = "critical";
+			};
+		};
+	};
+
+	pmic-area-thermal {
+		polling-delay = <1000>;
+		polling-delay-passive = <0>;
+		thermal-sensors = <&tboard_thermistor2>;
+
+		trips {
+			trip-crit {
+				temperature = <84000>;
+				hysteresis = <1000>;
+				type = "critical";
 			};
 		};
 	};
diff --git a/arch/arm64/boot/dts/mediatek/mt8195.dtsi b/arch/arm64/boot/dts/mediatek/mt8195.dtsi
index 54c674c45b49..b9101662ce40 100644
--- a/arch/arm64/boot/dts/mediatek/mt8195.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8195.dtsi
@@ -538,7 +538,7 @@
 					#size-cells = <0>;
 					#power-domain-cells = <1>;
 
-					power-domain@MT8195_POWER_DOMAIN_MFG1 {
+					mfg1: power-domain@MT8195_POWER_DOMAIN_MFG1 {
 						reg = <MT8195_POWER_DOMAIN_MFG1>;
 						clocks = <&apmixedsys CLK_APMIXED_MFGPLL>,
 							 <&topckgen CLK_TOP_MFG_CORE_TMP>;
@@ -627,6 +627,8 @@
 
 					power-domain@MT8195_POWER_DOMAIN_VENC_CORE1 {
 						reg = <MT8195_POWER_DOMAIN_VENC_CORE1>;
+						clocks = <&vencsys_core1 CLK_VENC_CORE1_LARB>;
+						clock-names = "venc1-larb";
 						mediatek,infracfg = <&infracfg_ao>;
 						#power-domain-cells = <0>;
 					};
@@ -689,6 +691,8 @@
 
 						power-domain@MT8195_POWER_DOMAIN_VENC {
 							reg = <MT8195_POWER_DOMAIN_VENC>;
+							clocks = <&vencsys CLK_VENC_LARB>;
+							clock-names = "venc0-larb";
 							mediatek,infracfg = <&infracfg_ao>;
 							#power-domain-cells = <0>;
 						};
@@ -1115,7 +1119,7 @@
 
 		lvts_ap: thermal-sensor@1100b000 {
 			compatible = "mediatek,mt8195-lvts-ap";
-			reg = <0 0x1100b000 0 0x1000>;
+			reg = <0 0x1100b000 0 0xc00>;
 			interrupts = <GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH 0>;
 			clocks = <&infracfg_ao CLK_INFRA_AO_THERM>;
 			resets = <&infracfg_ao MT8195_INFRA_RST0_THERM_CTRL_SWRST>;
@@ -1124,6 +1128,18 @@
 			#thermal-sensor-cells = <1>;
 		};
 
+		svs: svs@1100bc00 {
+			compatible = "mediatek,mt8195-svs";
+			reg = <0 0x1100bc00 0 0x400>;
+			interrupts = <GIC_SPI 199 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&infracfg_ao CLK_INFRA_AO_THERM>;
+			clock-names = "main";
+			nvmem-cells = <&svs_calib_data &lvts_efuse_data1>;
+			nvmem-cell-names = "svs-calibration-data", "t-calibration-data";
+			resets = <&infracfg_ao MT8195_INFRA_RST3_THERM_CTRL_PTP_SWRST>;
+			reset-names = "svs_rst";
+		};
+
 		disp_pwm0: pwm@1100e000 {
 			compatible = "mediatek,mt8195-disp-pwm", "mediatek,mt8183-disp-pwm";
 			reg = <0 0x1100e000 0 0x1000>;
@@ -1682,6 +1698,9 @@
 			lvts_efuse_data2: lvts2-calib@1d0 {
 				reg = <0x1d0 0x38>;
 			};
+			svs_calib_data: svs-calib@580 {
+				reg = <0x580 0x64>;
+			};
 		};
 
 		u3phy2: t-phy@11c40000 {
@@ -1714,6 +1733,26 @@
 			};
 		};
 
+		mipi_tx0: dsi-phy@11c80000 {
+			compatible = "mediatek,mt8195-mipi-tx", "mediatek,mt8183-mipi-tx";
+			reg = <0 0x11c80000 0 0x1000>;
+			clocks = <&clk26m>;
+			clock-output-names = "mipi_tx0_pll";
+			#clock-cells = <0>;
+			#phy-cells = <0>;
+			status = "disabled";
+		};
+
+		mipi_tx1: dsi-phy@11c90000 {
+			compatible = "mediatek,mt8195-mipi-tx", "mediatek,mt8183-mipi-tx";
+			reg = <0 0x11c90000 0 0x1000>;
+			clocks = <&clk26m>;
+			clock-output-names = "mipi_tx1_pll";
+			#clock-cells = <0>;
+			#phy-cells = <0>;
+			status = "disabled";
+		};
+
 		i2c5: i2c@11d00000 {
 			compatible = "mediatek,mt8195-i2c",
 				     "mediatek,mt8192-i2c";
@@ -1961,6 +2000,115 @@
 			#clock-cells = <1>;
 		};
 
+		dma-controller@14001000 {
+			compatible = "mediatek,mt8195-mdp3-rdma";
+			reg = <0 0x14001000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0x1000 0x1000>;
+			mediatek,gce-events = <CMDQ_EVENT_VPP0_MDP_RDMA_SOF>,
+					      <CMDQ_EVENT_VPP0_MDP_RDMA_FRAME_DONE>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS0>;
+			iommus = <&iommu_vpp M4U_PORT_L4_MDP_RDMA>;
+			clocks = <&vppsys0 CLK_VPP0_MDP_RDMA>;
+			mboxes = <&gce1 12 CMDQ_THR_PRIO_1>,
+				 <&gce1 13 CMDQ_THR_PRIO_1>,
+				 <&gce1 14 CMDQ_THR_PRIO_1>,
+				 <&gce1 21 CMDQ_THR_PRIO_1>,
+				 <&gce1 22 CMDQ_THR_PRIO_1>;
+			#dma-cells = <1>;
+		};
+
+		display@14002000 {
+			compatible = "mediatek,mt8195-mdp3-fg";
+			reg = <0 0x14002000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0x2000 0x1000>;
+			clocks = <&vppsys0 CLK_VPP0_MDP_FG>;
+		};
+
+		display@14003000 {
+			compatible = "mediatek,mt8195-mdp3-stitch";
+			reg = <0 0x14003000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0x3000 0x1000>;
+			clocks = <&vppsys0 CLK_VPP0_STITCH>;
+		};
+
+		display@14004000 {
+			compatible = "mediatek,mt8195-mdp3-hdr";
+			reg = <0 0x14004000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0x4000 0x1000>;
+			clocks = <&vppsys0 CLK_VPP0_MDP_HDR>;
+		};
+
+		display@14005000 {
+			compatible = "mediatek,mt8195-mdp3-aal";
+			reg = <0 0x14005000 0 0x1000>;
+			interrupts = <GIC_SPI 582 IRQ_TYPE_LEVEL_HIGH 0>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0x5000 0x1000>;
+			clocks = <&vppsys0 CLK_VPP0_MDP_AAL>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS0>;
+		};
+
+		display@14006000 {
+			compatible = "mediatek,mt8195-mdp3-rsz", "mediatek,mt8183-mdp3-rsz";
+			reg = <0 0x14006000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0x6000 0x1000>;
+			mediatek,gce-events = <CMDQ_EVENT_VPP0_MDP_RSZ_IN_RSZ_SOF>,
+					      <CMDQ_EVENT_VPP0_MDP_RSZ_FRAME_DONE>;
+			clocks = <&vppsys0 CLK_VPP0_MDP_RSZ>;
+		};
+
+		display@14007000 {
+			compatible = "mediatek,mt8195-mdp3-tdshp";
+			reg = <0 0x14007000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0x7000 0x1000>;
+			clocks = <&vppsys0 CLK_VPP0_MDP_TDSHP>;
+		};
+
+		display@14008000 {
+			compatible = "mediatek,mt8195-mdp3-color";
+			reg = <0 0x14008000 0 0x1000>;
+			interrupts = <GIC_SPI 585 IRQ_TYPE_LEVEL_HIGH 0>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0x8000 0x1000>;
+			clocks = <&vppsys0 CLK_VPP0_MDP_COLOR>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS0>;
+		};
+
+		display@14009000 {
+			compatible = "mediatek,mt8195-mdp3-ovl";
+			reg = <0 0x14009000 0 0x1000>;
+			interrupts = <GIC_SPI 586 IRQ_TYPE_LEVEL_HIGH 0>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0x9000 0x1000>;
+			clocks = <&vppsys0 CLK_VPP0_MDP_OVL>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS0>;
+			iommus = <&iommu_vpp M4U_PORT_L4_MDP_OVL>;
+		};
+
+		display@1400a000 {
+			compatible = "mediatek,mt8195-mdp3-padding";
+			reg = <0 0x1400a000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0xa000 0x1000>;
+			clocks = <&vppsys0 CLK_VPP0_PADDING>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS0>;
+		};
+
+		display@1400b000 {
+			compatible = "mediatek,mt8195-mdp3-tcc";
+			reg = <0 0x1400b000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0xb000 0x1000>;
+			clocks = <&vppsys0 CLK_VPP0_MDP_TCC>;
+		};
+
+		dma-controller@1400c000 {
+			compatible = "mediatek,mt8195-mdp3-wrot", "mediatek,mt8183-mdp3-wrot";
+			reg = <0 0x1400c000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0xc000 0x1000>;
+			mediatek,gce-events = <CMDQ_EVENT_VPP0_MDP_WROT_SOF>,
+					      <CMDQ_EVENT_VPP0_MDP_WROT_VIDO_WDONE>;
+			clocks = <&vppsys0 CLK_VPP0_MDP_WROT>;
+			iommus = <&iommu_vpp M4U_PORT_L4_MDP_WROT>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS0>;
+			#dma-cells = <1>;
+		};
+
 		mutex@1400f000 {
 			compatible = "mediatek,mt8195-vpp-mutex";
 			reg = <0 0x1400f000 0 0x1000>;
@@ -2108,6 +2256,289 @@
 			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS1>;
 		};
 
+		display@14f06000 {
+			compatible = "mediatek,mt8195-mdp3-split";
+			reg = <0 0x14f06000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f0XXXX 0x6000 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_VPP_SPLIT>,
+				 <&vppsys1 CLK_VPP1_HDMI_META>,
+				 <&vppsys1 CLK_VPP1_VPP_SPLIT_HDMI>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS1>;
+		};
+
+		display@14f07000 {
+			compatible = "mediatek,mt8195-mdp3-tcc";
+			reg = <0 0x14f07000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f0XXXX 0x7000 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP1_MDP_TCC>;
+		};
+
+		dma-controller@14f08000 {
+			compatible = "mediatek,mt8195-mdp3-rdma";
+			reg = <0 0x14f08000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f0XXXX 0x8000 0x1000>;
+			mediatek,gce-events = <CMDQ_EVENT_VPP1_SVPP1_MDP_RDMA_SOF>,
+					      <CMDQ_EVENT_VPP1_SVPP1_MDP_RDMA_FRAME_DONE>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP1_MDP_RDMA>;
+			iommus = <&iommu_vdo M4U_PORT_L5_SVPP1_MDP_RDMA>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS1>;
+			#dma-cells = <1>;
+		};
+
+		dma-controller@14f09000 {
+			compatible = "mediatek,mt8195-mdp3-rdma";
+			reg = <0 0x14f09000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f0XXXX 0x9000 0x1000>;
+			mediatek,gce-events = <CMDQ_EVENT_VPP1_SVPP2_MDP_RDMA_SOF>,
+					      <CMDQ_EVENT_VPP1_SVPP2_MDP_RDMA_FRAME_DONE>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP2_MDP_RDMA>;
+			iommus = <&iommu_vdo M4U_PORT_L5_SVPP2_MDP_RDMA>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS1>;
+			#dma-cells = <1>;
+		};
+
+		dma-controller@14f0a000 {
+			compatible = "mediatek,mt8195-mdp3-rdma";
+			reg = <0 0x14f0a000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f0XXXX 0xa000 0x1000>;
+			mediatek,gce-events = <CMDQ_EVENT_VPP1_SVPP3_MDP_RDMA_SOF>,
+					      <CMDQ_EVENT_VPP1_SVPP3_MDP_RDMA_FRAME_DONE>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP3_MDP_RDMA>;
+			iommus = <&iommu_vpp M4U_PORT_L6_SVPP3_MDP_RDMA>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS1>;
+			#dma-cells = <1>;
+		};
+
+		display@14f0b000 {
+			compatible = "mediatek,mt8195-mdp3-fg";
+			reg = <0 0x14f0b000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f0XXXX 0xb000 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP1_MDP_FG>;
+		};
+
+		display@14f0c000 {
+			compatible = "mediatek,mt8195-mdp3-fg";
+			reg = <0 0x14f0c000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f0XXXX 0xc000 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP2_MDP_FG>;
+		};
+
+		display@14f0d000 {
+			compatible = "mediatek,mt8195-mdp3-fg";
+			reg = <0 0x14f0d000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f0XXXX 0xd000 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP3_MDP_FG>;
+		};
+
+		display@14f0e000 {
+			compatible = "mediatek,mt8195-mdp3-hdr";
+			reg = <0 0x14f0e000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f0XXXX 0xe000 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP1_MDP_HDR>;
+		};
+
+		display@14f0f000 {
+			compatible = "mediatek,mt8195-mdp3-hdr";
+			reg = <0 0x14f0f000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f0XXXX 0xf000 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP2_MDP_HDR>;
+		};
+
+		display@14f10000 {
+			compatible = "mediatek,mt8195-mdp3-hdr";
+			reg = <0 0x14f10000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f1XXXX 0 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP3_MDP_HDR>;
+		};
+
+		display@14f11000 {
+			compatible = "mediatek,mt8195-mdp3-aal";
+			reg = <0 0x14f11000 0 0x1000>;
+			interrupts = <GIC_SPI 617 IRQ_TYPE_LEVEL_HIGH 0>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f1XXXX 0x1000 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP1_MDP_AAL>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS1>;
+		};
+
+		display@14f12000 {
+			compatible = "mediatek,mt8195-mdp3-aal";
+			reg = <0 0x14f12000 0 0x1000>;
+			interrupts = <GIC_SPI 618 IRQ_TYPE_LEVEL_HIGH 0>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f1XXXX 0x2000 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP2_MDP_AAL>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS1>;
+		};
+
+		display@14f13000 {
+			compatible = "mediatek,mt8195-mdp3-aal";
+			reg = <0 0x14f13000 0 0x1000>;
+			interrupts = <GIC_SPI 619 IRQ_TYPE_LEVEL_HIGH 0>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f1XXXX 0x3000 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP3_MDP_AAL>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS1>;
+		};
+
+		display@14f14000 {
+			compatible = "mediatek,mt8195-mdp3-rsz", "mediatek,mt8183-mdp3-rsz";
+			reg = <0 0x14f14000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f1XXXX 0x4000 0x1000>;
+			mediatek,gce-events = <CMDQ_EVENT_VPP1_SVPP1_MDP_RSZ_SOF>,
+					      <CMDQ_EVENT_VPP1_SVPP1_MDP_RSZ_FRAME_DONE>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP1_MDP_RSZ>;
+		};
+
+		display@14f15000 {
+			compatible = "mediatek,mt8195-mdp3-rsz", "mediatek,mt8183-mdp3-rsz";
+			reg = <0 0x14f15000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f1XXXX 0x5000 0x1000>;
+			mediatek,gce-events = <CMDQ_EVENT_VPP1_SVPP2_MDP_RSZ_SOF>,
+					      <CMDQ_EVENT_VPP1_SVPP2_MDP_RSZ_FRAME_DONE>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP2_MDP_RSZ>;
+		};
+
+		display@14f16000 {
+			compatible = "mediatek,mt8195-mdp3-rsz", "mediatek,mt8183-mdp3-rsz";
+			reg = <0 0x14f16000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f1XXXX 0x6000 0x1000>;
+			mediatek,gce-events = <CMDQ_EVENT_VPP1_SVPP3_MDP_RSZ_SOF>,
+					      <CMDQ_EVENT_VPP1_SVPP3_MDP_RSZ_FRAME_DONE>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP3_MDP_RSZ>;
+		};
+
+		display@14f17000 {
+			compatible = "mediatek,mt8195-mdp3-tdshp";
+			reg = <0 0x14f17000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f1XXXX 0x7000 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP1_MDP_TDSHP>;
+		};
+
+		display@14f18000 {
+			compatible = "mediatek,mt8195-mdp3-tdshp";
+			reg = <0 0x14f18000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f1XXXX 0x8000 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP2_MDP_TDSHP>;
+		};
+
+		display@14f19000 {
+			compatible = "mediatek,mt8195-mdp3-tdshp";
+			reg = <0 0x14f19000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f1XXXX 0x9000 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP3_MDP_TDSHP>;
+		};
+
+		display@14f1a000 {
+			compatible = "mediatek,mt8195-mdp3-merge";
+			reg = <0 0x14f1a000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f1XXXX 0xa000 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP2_VPP_MERGE>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS1>;
+		};
+
+		display@14f1b000 {
+			compatible = "mediatek,mt8195-mdp3-merge";
+			reg = <0 0x14f1b000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f1XXXX 0xb000 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP3_VPP_MERGE>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS1>;
+		};
+
+		display@14f1c000 {
+			compatible = "mediatek,mt8195-mdp3-color";
+			reg = <0 0x14f1c000 0 0x1000>;
+			interrupts = <GIC_SPI 628 IRQ_TYPE_LEVEL_HIGH 0>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f1XXXX 0xc000 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP1_MDP_COLOR>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS1>;
+		};
+
+		display@14f1d000 {
+			compatible = "mediatek,mt8195-mdp3-color";
+			reg = <0 0x14f1d000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f1XXXX 0xd000 0x1000>;
+			interrupts = <GIC_SPI 629 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP2_MDP_COLOR>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS1>;
+		};
+
+		display@14f1e000 {
+			compatible = "mediatek,mt8195-mdp3-color";
+			reg = <0 0x14f1e000 0 0x1000>;
+			interrupts = <GIC_SPI 630 IRQ_TYPE_LEVEL_HIGH 0>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f1XXXX 0xe000 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP3_MDP_COLOR>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS1>;
+		};
+
+		display@14f1f000 {
+			compatible = "mediatek,mt8195-mdp3-ovl";
+			reg = <0 0x14f1f000 0 0x1000>;
+			interrupts = <GIC_SPI 631 IRQ_TYPE_LEVEL_HIGH 0>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f1XXXX 0xf000 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP1_MDP_OVL>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS1>;
+			iommus = <&iommu_vdo M4U_PORT_L5_SVPP1_MDP_OVL>;
+		};
+
+		display@14f20000 {
+			compatible = "mediatek,mt8195-mdp3-padding";
+			reg = <0 0x14f20000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f2XXXX 0 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP1_VPP_PAD>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS1>;
+		};
+
+		display@14f21000 {
+			compatible = "mediatek,mt8195-mdp3-padding";
+			reg = <0 0x14f21000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f2XXXX 0x1000 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP2_VPP_PAD>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS1>;
+		};
+
+		display@14f22000 {
+			compatible = "mediatek,mt8195-mdp3-padding";
+			reg = <0 0x14f22000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f2XXXX 0x2000 0x1000>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP3_VPP_PAD>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS1>;
+		};
+
+		dma-controller@14f23000 {
+			compatible = "mediatek,mt8195-mdp3-wrot", "mediatek,mt8183-mdp3-wrot";
+			reg = <0 0x14f23000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f2XXXX 0x3000 0x1000>;
+			mediatek,gce-events = <CMDQ_EVENT_VPP1_SVPP1_MDP_WROT_SOF>,
+					      <CMDQ_EVENT_VPP1_SVPP1_MDP_WROT_FRAME_DONE>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP1_MDP_WROT>;
+			iommus = <&iommu_vdo M4U_PORT_L5_SVPP1_MDP_WROT>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS1>;
+			#dma-cells = <1>;
+		};
+
+		dma-controller@14f24000 {
+			compatible = "mediatek,mt8195-mdp3-wrot", "mediatek,mt8183-mdp3-wrot";
+			reg = <0 0x14f24000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f2XXXX 0x4000 0x1000>;
+			mediatek,gce-events = <CMDQ_EVENT_VPP1_SVPP2_MDP_WROT_SOF>,
+					<CMDQ_EVENT_VPP1_SVPP2_MDP_WROT_FRAME_DONE>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP2_MDP_WROT>;
+			iommus = <&iommu_vdo M4U_PORT_L5_SVPP2_MDP_WROT>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS1>;
+			#dma-cells = <1>;
+		};
+
+		dma-controller@14f25000 {
+			compatible = "mediatek,mt8195-mdp3-wrot", "mediatek,mt8183-mdp3-wrot";
+			reg = <0 0x14f25000 0 0x1000>;
+			mediatek,gce-client-reg = <&gce1 SUBSYS_14f2XXXX 0x5000 0x1000>;
+			mediatek,gce-events = <CMDQ_EVENT_VPP1_SVPP3_MDP_WROT_SOF>,
+					<CMDQ_EVENT_VPP1_SVPP3_MDP_WROT_FRAME_DONE>;
+			clocks = <&vppsys1 CLK_VPP1_SVPP3_MDP_WROT>;
+			iommus = <&iommu_vpp M4U_PORT_L6_SVPP3_MDP_WROT>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VPPSYS1>;
+			#dma-cells = <1>;
+		};
+
 		imgsys: clock-controller@15000000 {
 			compatible = "mediatek,mt8195-imgsys";
 			reg = <0 0x15000000 0 0x1000>;
@@ -2665,7 +3096,7 @@
 			reg = <0 0x1b010000 0 0x1000>;
 			mediatek,larb-id = <20>;
 			mediatek,smi = <&smi_common_vpp>;
-			clocks = <&vencsys_core1 CLK_VENC_CORE1_LARB>,
+			clocks = <&vencsys_core1 CLK_VENC_CORE1_VENC>,
 				 <&vencsys_core1 CLK_VENC_CORE1_GALS>,
 				 <&vppsys0 CLK_VPP0_GALS_VDO0_VDO1_VENCSYS_CORE1>;
 			clock-names = "apb", "smi", "gals";
@@ -2737,6 +3168,20 @@
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c00XXXX 0x7000 0x1000>;
 		};
 
+		dsi0: dsi@1c008000 {
+			compatible = "mediatek,mt8195-dsi", "mediatek,mt8183-dsi";
+			reg = <0 0x1c008000 0 0x1000>;
+			interrupts = <GIC_SPI 644 IRQ_TYPE_LEVEL_HIGH 0>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS0>;
+			clocks = <&vdosys0 CLK_VDO0_DSI0>,
+				 <&vdosys0 CLK_VDO0_DSI0_DSI>,
+				 <&mipi_tx0>;
+			clock-names = "engine", "digital", "hs";
+			phys = <&mipi_tx0>;
+			phy-names = "dphy";
+			status = "disabled";
+		};
+
 		dsc0: dsc@1c009000 {
 			compatible = "mediatek,mt8195-disp-dsc";
 			reg = <0 0x1c009000 0 0x1000>;
@@ -2746,6 +3191,20 @@
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c00XXXX 0x9000 0x1000>;
 		};
 
+		dsi1: dsi@1c012000 {
+			compatible = "mediatek,mt8195-dsi", "mediatek,mt8183-dsi";
+			reg = <0 0x1c012000 0 0x1000>;
+			interrupts = <GIC_SPI 654 IRQ_TYPE_LEVEL_HIGH 0>;
+			power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS0>;
+			clocks = <&vdosys0 CLK_VDO0_DSI1>,
+				 <&vdosys0 CLK_VDO0_DSI1_DSI>,
+				 <&mipi_tx1>;
+			clock-names = "engine", "digital", "hs";
+			phys = <&mipi_tx1>;
+			phy-names = "dphy";
+			status = "disabled";
+		};
+
 		merge0: merge@1c014000 {
 			compatible = "mediatek,mt8195-disp-merge";
 			reg = <0 0x1c014000 0 0x1000>;
@@ -2869,7 +3328,7 @@
 			power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
 		};
 
-		vdo1_rdma0: rdma@1c104000 {
+		vdo1_rdma0: dma-controller@1c104000 {
 			compatible = "mediatek,mt8195-vdo1-rdma";
 			reg = <0 0x1c104000 0 0x1000>;
 			interrupts = <GIC_SPI 495 IRQ_TYPE_LEVEL_HIGH 0>;
@@ -2877,9 +3336,10 @@
 			power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
 			iommus = <&iommu_vdo M4U_PORT_L2_MDP_RDMA0>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0x4000 0x1000>;
+			#dma-cells = <1>;
 		};
 
-		vdo1_rdma1: rdma@1c105000 {
+		vdo1_rdma1: dma-controller@1c105000 {
 			compatible = "mediatek,mt8195-vdo1-rdma";
 			reg = <0 0x1c105000 0 0x1000>;
 			interrupts = <GIC_SPI 496 IRQ_TYPE_LEVEL_HIGH 0>;
@@ -2887,9 +3347,10 @@
 			power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
 			iommus = <&iommu_vpp M4U_PORT_L3_MDP_RDMA1>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0x5000 0x1000>;
+			#dma-cells = <1>;
 		};
 
-		vdo1_rdma2: rdma@1c106000 {
+		vdo1_rdma2: dma-controller@1c106000 {
 			compatible = "mediatek,mt8195-vdo1-rdma";
 			reg = <0 0x1c106000 0 0x1000>;
 			interrupts = <GIC_SPI 497 IRQ_TYPE_LEVEL_HIGH 0>;
@@ -2897,9 +3358,10 @@
 			power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
 			iommus = <&iommu_vdo M4U_PORT_L2_MDP_RDMA2>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0x6000 0x1000>;
+			#dma-cells = <1>;
 		};
 
-		vdo1_rdma3: rdma@1c107000 {
+		vdo1_rdma3: dma-controller@1c107000 {
 			compatible = "mediatek,mt8195-vdo1-rdma";
 			reg = <0 0x1c107000 0 0x1000>;
 			interrupts = <GIC_SPI 498 IRQ_TYPE_LEVEL_HIGH 0>;
@@ -2907,9 +3369,10 @@
 			power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
 			iommus = <&iommu_vpp M4U_PORT_L3_MDP_RDMA3>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0x7000 0x1000>;
+			#dma-cells = <1>;
 		};
 
-		vdo1_rdma4: rdma@1c108000 {
+		vdo1_rdma4: dma-controller@1c108000 {
 			compatible = "mediatek,mt8195-vdo1-rdma";
 			reg = <0 0x1c108000 0 0x1000>;
 			interrupts = <GIC_SPI 499 IRQ_TYPE_LEVEL_HIGH 0>;
@@ -2917,9 +3380,10 @@
 			power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
 			iommus = <&iommu_vdo M4U_PORT_L2_MDP_RDMA4>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0x8000 0x1000>;
+			#dma-cells = <1>;
 		};
 
-		vdo1_rdma5: rdma@1c109000 {
+		vdo1_rdma5: dma-controller@1c109000 {
 			compatible = "mediatek,mt8195-vdo1-rdma";
 			reg = <0 0x1c109000 0 0x1000>;
 			interrupts = <GIC_SPI 500 IRQ_TYPE_LEVEL_HIGH 0>;
@@ -2927,9 +3391,10 @@
 			power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
 			iommus = <&iommu_vpp M4U_PORT_L3_MDP_RDMA5>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0x9000 0x1000>;
+			#dma-cells = <1>;
 		};
 
-		vdo1_rdma6: rdma@1c10a000 {
+		vdo1_rdma6: dma-controller@1c10a000 {
 			compatible = "mediatek,mt8195-vdo1-rdma";
 			reg = <0 0x1c10a000 0 0x1000>;
 			interrupts = <GIC_SPI 501 IRQ_TYPE_LEVEL_HIGH 0>;
@@ -2937,9 +3402,10 @@
 			power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
 			iommus = <&iommu_vdo M4U_PORT_L2_MDP_RDMA6>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0xa000 0x1000>;
+			#dma-cells = <1>;
 		};
 
-		vdo1_rdma7: rdma@1c10b000 {
+		vdo1_rdma7: dma-controller@1c10b000 {
 			compatible = "mediatek,mt8195-vdo1-rdma";
 			reg = <0 0x1c10b000 0 0x1000>;
 			interrupts = <GIC_SPI 502 IRQ_TYPE_LEVEL_HIGH 0>;
@@ -2947,6 +3413,7 @@
 			power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
 			iommus = <&iommu_vpp M4U_PORT_L3_MDP_RDMA7>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0xb000 0x1000>;
+			#dma-cells = <1>;
 		};
 
 		merge1: vpp-merge@1c10c000 {
diff --git a/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts b/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts
index 70b465f7c6a7..7fc515a07c65 100644
--- a/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts
@@ -210,8 +210,7 @@
 	touchscreen@5d {
 		compatible = "goodix,gt9271";
 		reg = <0x5d>;
-		interrupt-parent = <&pio>;
-		interrupts = <132 IRQ_TYPE_EDGE_RISING>;
+		interrupts-extended = <&pio 132 IRQ_TYPE_EDGE_RISING>;
 		irq-gpios = <&pio 132 GPIO_ACTIVE_HIGH>;
 		reset-gpios = <&pio 133 GPIO_ACTIVE_HIGH>;
 		AVDD28-supply = <&mt6360_ldo1>;
@@ -238,6 +237,7 @@
 	mt6360: pmic@34 {
 		compatible = "mediatek,mt6360";
 		reg = <0x34>;
+		interrupt-parent = <&pio>;
 		interrupts = <128 IRQ_TYPE_EDGE_FALLING>;
 		interrupt-names = "IRQB";
 		interrupt-controller;
@@ -773,8 +773,7 @@
 };
 
 &pmic {
-	interrupt-parent = <&pio>;
-	interrupts = <222 IRQ_TYPE_LEVEL_HIGH>;
+	interrupts-extended = <&pio 222 IRQ_TYPE_LEVEL_HIGH>;
 };
 
 &scp {
diff --git a/arch/arm64/boot/dts/qcom/Makefile b/arch/arm64/boot/dts/qcom/Makefile
index d6cb840b7050..39889d5f8e12 100644
--- a/arch/arm64/boot/dts/qcom/Makefile
+++ b/arch/arm64/boot/dts/qcom/Makefile
@@ -45,6 +45,7 @@ dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-thwc-uf896.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-thwc-ufi001c.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-wingtech-wt88047.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-yiming-uz801v3.dtb
+dtb-$(CONFIG_ARCH_QCOM)	+= msm8939-huawei-kiwi.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8939-longcheer-l9100.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8939-samsung-a7.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8939-sony-xperia-kanuti-tulip.dtb
@@ -87,8 +88,10 @@ dtb-$(CONFIG_ARCH_QCOM)	+= msm8998-sony-xperia-yoshino-maple.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8998-sony-xperia-yoshino-poplar.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8998-xiaomi-sagit.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= qcm6490-fairphone-fp5.dtb
+dtb-$(CONFIG_ARCH_QCOM)	+= qcm6490-idp.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= qcs404-evb-1000.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= qcs404-evb-4000.dtb
+dtb-$(CONFIG_ARCH_QCOM)	+= qcs6490-rb3gen2.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= qdu1000-idp.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= qrb2210-rb1.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= qrb4210-rb2.dtb
@@ -220,6 +223,7 @@ dtb-$(CONFIG_ARCH_QCOM)	+= sm8250-sony-xperia-edo-pdx203.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= sm8250-sony-xperia-edo-pdx206.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= sm8250-xiaomi-elish-boe.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= sm8250-xiaomi-elish-csot.dtb
+dtb-$(CONFIG_ARCH_QCOM)	+= sm8250-xiaomi-pipa.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= sm8350-hdk.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= sm8350-microsoft-surface-duo2.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= sm8350-mtp.dtb
@@ -231,3 +235,7 @@ dtb-$(CONFIG_ARCH_QCOM)	+= sm8450-sony-xperia-nagara-pdx223.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= sm8450-sony-xperia-nagara-pdx224.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= sm8550-mtp.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= sm8550-qrd.dtb
+dtb-$(CONFIG_ARCH_QCOM)	+= sm8650-mtp.dtb
+dtb-$(CONFIG_ARCH_QCOM)	+= sm8650-qrd.dtb
+dtb-$(CONFIG_ARCH_QCOM)	+= x1e80100-crd.dtb
+dtb-$(CONFIG_ARCH_QCOM)	+= x1e80100-qcp.dtb
diff --git a/arch/arm64/boot/dts/qcom/ipq5018-rdp432-c2.dts b/arch/arm64/boot/dts/qcom/ipq5018-rdp432-c2.dts
index e636a1cb9b77..8460b538eb6a 100644
--- a/arch/arm64/boot/dts/qcom/ipq5018-rdp432-c2.dts
+++ b/arch/arm64/boot/dts/qcom/ipq5018-rdp432-c2.dts
@@ -67,6 +67,18 @@
 	};
 };
 
+&usb {
+	status = "okay";
+};
+
+&usb_dwc {
+	dr_mode = "host";
+};
+
+&usbphy0 {
+	status = "okay";
+};
+
 &xo_board_clk {
 	clock-frequency = <24000000>;
 };
diff --git a/arch/arm64/boot/dts/qcom/ipq5018.dtsi b/arch/arm64/boot/dts/qcom/ipq5018.dtsi
index 38ffdc3cbdcd..32b178b639f0 100644
--- a/arch/arm64/boot/dts/qcom/ipq5018.dtsi
+++ b/arch/arm64/boot/dts/qcom/ipq5018.dtsi
@@ -5,6 +5,7 @@
  * Copyright (c) 2023 The Linux Foundation. All rights reserved.
  */
 
+#include <dt-bindings/clock/qcom,apss-ipq.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/clock/qcom,gcc-ipq5018.h>
 #include <dt-bindings/reset/qcom,gcc-ipq5018.h>
@@ -36,6 +37,8 @@
 			reg = <0x0>;
 			enable-method = "psci";
 			next-level-cache = <&L2_0>;
+			clocks = <&apcs_glb APCS_ALIAS0_CORE_CLK>;
+			operating-points-v2 = <&cpu_opp_table>;
 		};
 
 		CPU1: cpu@1 {
@@ -44,6 +47,8 @@
 			reg = <0x1>;
 			enable-method = "psci";
 			next-level-cache = <&L2_0>;
+			clocks = <&apcs_glb APCS_ALIAS0_CORE_CLK>;
+			operating-points-v2 = <&cpu_opp_table>;
 		};
 
 		L2_0: l2-cache {
@@ -54,6 +59,23 @@
 		};
 	};
 
+	cpu_opp_table: opp-table-cpu {
+		compatible = "operating-points-v2";
+		opp-shared;
+
+		opp-800000000 {
+			opp-hz = /bits/ 64 <800000000>;
+			opp-microvolt = <1100000>;
+			clock-latency-ns = <200000>;
+		};
+
+		opp-1008000000 {
+			opp-hz = /bits/ 64 <1008000000>;
+			opp-microvolt = <1100000>;
+			clock-latency-ns = <200000>;
+		};
+	};
+
 	firmware {
 		scm {
 			compatible = "qcom,scm-ipq5018", "qcom,scm";
@@ -82,6 +104,24 @@
 		#size-cells = <2>;
 		ranges;
 
+		bootloader@4a800000 {
+			reg = <0x0 0x4a800000 0x0 0x200000>;
+			no-map;
+		};
+
+		sbl@4aa00000 {
+			reg = <0x0 0x4aa00000 0x0 0x100000>;
+			no-map;
+		};
+
+		smem@4ab00000 {
+			compatible = "qcom,smem";
+			reg = <0x0 0x4ab00000 0x0 0x100000>;
+			no-map;
+
+			hwlocks = <&tcsr_mutex 3>;
+		};
+
 		tz_region: tz@4ac00000 {
 			reg = <0x0 0x4ac00000 0x0 0x200000>;
 			no-map;
@@ -94,6 +134,19 @@
 		#size-cells = <1>;
 		ranges = <0 0 0 0xffffffff>;
 
+		usbphy0: phy@5b000 {
+			compatible = "qcom,ipq5018-usb-hsphy";
+			reg = <0x0005b000 0x120>;
+
+			clocks = <&gcc GCC_USB0_PHY_CFG_AHB_CLK>;
+
+			resets = <&gcc GCC_QUSB2_0_PHY_BCR>;
+
+			#phy-cells = <0>;
+
+			status = "disabled";
+		};
+
 		tlmm: pinctrl@1000000 {
 			compatible = "qcom,ipq5018-tlmm";
 			reg = <0x01000000 0x300000>;
@@ -129,6 +182,12 @@
 			#power-domain-cells = <1>;
 		};
 
+		tcsr_mutex: hwlock@1905000 {
+			compatible = "qcom,tcsr-mutex";
+			reg = <0x01905000 0x20000>;
+			#hwlock-cells = <1>;
+		};
+
 		sdhc_1: mmc@7804000 {
 			compatible = "qcom,ipq5018-sdhci", "qcom,sdhci-msm-v5";
 			reg = <0x7804000 0x1000>;
@@ -146,6 +205,16 @@
 			status = "disabled";
 		};
 
+		blsp_dma: dma-controller@7884000 {
+			compatible = "qcom,bam-v1.7.0";
+			reg = <0x07884000 0x1d000>;
+			interrupts = <GIC_SPI 238 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP1_AHB_CLK>;
+			clock-names = "bam_clk";
+			#dma-cells = <1>;
+			qcom,ee = <0>;
+		};
+
 		blsp1_uart1: serial@78af000 {
 			compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm";
 			reg = <0x078af000 0x200>;
@@ -156,6 +225,61 @@
 			status = "disabled";
 		};
 
+		blsp1_spi1: spi@78b5000 {
+			compatible = "qcom,spi-qup-v2.2.1";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x078b5000 0x600>;
+			interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP1_QUP1_SPI_APPS_CLK>,
+				 <&gcc GCC_BLSP1_AHB_CLK>;
+			clock-names = "core", "iface";
+			dmas = <&blsp_dma 4>, <&blsp_dma 5>;
+			dma-names = "tx", "rx";
+			status = "disabled";
+		};
+
+		usb: usb@8af8800 {
+			compatible = "qcom,ipq5018-dwc3", "qcom,dwc3";
+			reg = <0x08af8800 0x400>;
+
+			interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "hs_phy_irq";
+
+			clocks = <&gcc GCC_USB0_MASTER_CLK>,
+				 <&gcc GCC_SYS_NOC_USB0_AXI_CLK>,
+				 <&gcc GCC_USB0_SLEEP_CLK>,
+				 <&gcc GCC_USB0_MOCK_UTMI_CLK>;
+			clock-names = "core",
+				      "iface",
+				      "sleep",
+				      "mock_utmi";
+
+			resets = <&gcc GCC_USB0_BCR>;
+
+			qcom,select-utmi-as-pipe-clk;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges;
+
+			status = "disabled";
+
+			usb_dwc: usb@8a00000 {
+				compatible = "snps,dwc3";
+				reg = <0x08a00000 0xe000>;
+				clocks = <&gcc GCC_USB0_MOCK_UTMI_CLK>;
+				clock-names = "ref";
+				interrupts = <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>;
+				phy-names = "usb2-phy";
+				phys = <&usbphy0>;
+				tx-fifo-resize;
+				snps,is-utmi-l1-suspend;
+				snps,hird-threshold = /bits/ 8 <0x0>;
+				snps,dis_u2_susphy_quirk;
+				snps,dis_u3_susphy_quirk;
+			};
+		};
+
 		intc: interrupt-controller@b000000 {
 			compatible = "qcom,msm-qgic2";
 			reg = <0x0b000000 0x1000>,  /* GICD */
@@ -189,6 +313,24 @@
 			clocks = <&sleep_clk>;
 		};
 
+		apcs_glb: mailbox@b111000 {
+			compatible = "qcom,ipq5018-apcs-apps-global",
+				     "qcom,ipq6018-apcs-apps-global";
+			reg = <0x0b111000 0x1000>;
+			#clock-cells = <1>;
+			clocks = <&a53pll>, <&xo_board_clk>, <&gcc GPLL0>;
+			clock-names = "pll", "xo", "gpll0";
+			#mbox-cells = <1>;
+		};
+
+		a53pll: clock@b116000 {
+			compatible = "qcom,ipq5018-a53pll";
+			reg = <0x0b116000 0x40>;
+			#clock-cells = <0>;
+			clocks = <&xo_board_clk>;
+			clock-names = "xo";
+		};
+
 		timer@b120000 {
 			compatible = "arm,armv7-timer-mem";
 			reg = <0x0b120000 0x1000>;
diff --git a/arch/arm64/boot/dts/qcom/ipq5332-rdp-common.dtsi b/arch/arm64/boot/dts/qcom/ipq5332-rdp-common.dtsi
index 4870cdb764d0..b37ae7749083 100644
--- a/arch/arm64/boot/dts/qcom/ipq5332-rdp-common.dtsi
+++ b/arch/arm64/boot/dts/qcom/ipq5332-rdp-common.dtsi
@@ -9,6 +9,7 @@
 
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
 #include "ipq5332.dtsi"
 
 / {
@@ -39,6 +40,8 @@
 		pinctrl-names = "default";
 
 		led-0 {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_WLAN;
 			gpios = <&tlmm 36 GPIO_ACTIVE_HIGH>;
 			linux,default-trigger = "phy0tx";
 			default-state = "off";
diff --git a/arch/arm64/boot/dts/qcom/ipq5332-rdp441.dts b/arch/arm64/boot/dts/qcom/ipq5332-rdp441.dts
index e89e2e948603..846413817e9a 100644
--- a/arch/arm64/boot/dts/qcom/ipq5332-rdp441.dts
+++ b/arch/arm64/boot/dts/qcom/ipq5332-rdp441.dts
@@ -15,7 +15,7 @@
 };
 
 &blsp1_i2c1 {
-	clock-frequency  = <400000>;
+	clock-frequency = <400000>;
 	pinctrl-0 = <&i2c_1_pins>;
 	pinctrl-names = "default";
 	status = "okay";
diff --git a/arch/arm64/boot/dts/qcom/ipq5332-rdp442.dts b/arch/arm64/boot/dts/qcom/ipq5332-rdp442.dts
index efd480a7afdf..ed8a54eb95c0 100644
--- a/arch/arm64/boot/dts/qcom/ipq5332-rdp442.dts
+++ b/arch/arm64/boot/dts/qcom/ipq5332-rdp442.dts
@@ -15,7 +15,7 @@
 };
 
 &blsp1_i2c1 {
-	clock-frequency  = <400000>;
+	clock-frequency = <400000>;
 	pinctrl-0 = <&i2c_1_pins>;
 	pinctrl-names = "default";
 	status = "okay";
diff --git a/arch/arm64/boot/dts/qcom/ipq5332-rdp474.dts b/arch/arm64/boot/dts/qcom/ipq5332-rdp474.dts
index eb1fa33d6fe4..d5f99e741ae5 100644
--- a/arch/arm64/boot/dts/qcom/ipq5332-rdp474.dts
+++ b/arch/arm64/boot/dts/qcom/ipq5332-rdp474.dts
@@ -15,7 +15,7 @@
 };
 
 &blsp1_i2c1 {
-	clock-frequency  = <400000>;
+	clock-frequency = <400000>;
 	pinctrl-0 = <&i2c_1_pins>;
 	pinctrl-names = "default";
 	status = "okay";
diff --git a/arch/arm64/boot/dts/qcom/ipq5332.dtsi b/arch/arm64/boot/dts/qcom/ipq5332.dtsi
index d3fef2f80a81..42e2e48b2bc3 100644
--- a/arch/arm64/boot/dts/qcom/ipq5332.dtsi
+++ b/arch/arm64/boot/dts/qcom/ipq5332.dtsi
@@ -91,11 +91,19 @@
 	};
 
 	cpu_opp_table: opp-table-cpu {
-		compatible = "operating-points-v2";
+		compatible = "operating-points-v2-kryo-cpu";
 		opp-shared;
+		nvmem-cells = <&cpu_speed_bin>;
 
-		opp-1488000000 {
-			opp-hz = /bits/ 64 <1488000000>;
+		opp-1100000000 {
+			opp-hz = /bits/ 64 <1100000000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+
+		opp-1500000000 {
+			opp-hz = /bits/ 64 <1500000000>;
+			opp-supported-hw = <0x3>;
 			clock-latency-ns = <200000>;
 		};
 	};
@@ -163,6 +171,11 @@
 			reg = <0x000a4000 0x721>;
 			#address-cells = <1>;
 			#size-cells = <1>;
+
+			cpu_speed_bin: cpu-speed-bin@1d {
+				reg = <0x1d 0x2>;
+				bits = <7 2>;
+			};
 		};
 
 		rng: rng@e3000 {
@@ -390,8 +403,8 @@
 				     "qcom,ipq6018-apcs-apps-global";
 			reg = <0x0b111000 0x1000>;
 			#clock-cells = <1>;
-			clocks = <&a53pll>, <&xo_board>;
-			clock-names = "pll", "xo";
+			clocks = <&a53pll>, <&xo_board>, <&gcc GPLL0>;
+			clock-names = "pll", "xo", "gpll0";
 			#mbox-cells = <1>;
 		};
 
diff --git a/arch/arm64/boot/dts/qcom/ipq6018.dtsi b/arch/arm64/boot/dts/qcom/ipq6018.dtsi
index e59b9df96c7e..5e1277fea725 100644
--- a/arch/arm64/boot/dts/qcom/ipq6018.dtsi
+++ b/arch/arm64/boot/dts/qcom/ipq6018.dtsi
@@ -96,42 +96,49 @@
 	};
 
 	cpu_opp_table: opp-table-cpu {
-		compatible = "operating-points-v2";
+		compatible = "operating-points-v2-kryo-cpu";
+		nvmem-cells = <&cpu_speed_bin>;
 		opp-shared;
 
 		opp-864000000 {
 			opp-hz = /bits/ 64 <864000000>;
 			opp-microvolt = <725000>;
+			opp-supported-hw = <0xf>;
 			clock-latency-ns = <200000>;
 		};
 
 		opp-1056000000 {
 			opp-hz = /bits/ 64 <1056000000>;
 			opp-microvolt = <787500>;
+			opp-supported-hw = <0xf>;
 			clock-latency-ns = <200000>;
 		};
 
 		opp-1320000000 {
 			opp-hz = /bits/ 64 <1320000000>;
 			opp-microvolt = <862500>;
+			opp-supported-hw = <0x3>;
 			clock-latency-ns = <200000>;
 		};
 
 		opp-1440000000 {
 			opp-hz = /bits/ 64 <1440000000>;
 			opp-microvolt = <925000>;
+			opp-supported-hw = <0x3>;
 			clock-latency-ns = <200000>;
 		};
 
 		opp-1608000000 {
 			opp-hz = /bits/ 64 <1608000000>;
 			opp-microvolt = <987500>;
+			opp-supported-hw = <0x1>;
 			clock-latency-ns = <200000>;
 		};
 
 		opp-1800000000 {
 			opp-hz = /bits/ 64 <1800000000>;
 			opp-microvolt = <1062500>;
+			opp-supported-hw = <0x1>;
 			clock-latency-ns = <200000>;
 		};
 	};
@@ -236,31 +243,26 @@
 
 		ssphy_0: ssphy@78000 {
 			compatible = "qcom,ipq6018-qmp-usb3-phy";
-			reg = <0x0 0x00078000 0x0 0x1c4>;
-			#address-cells = <2>;
-			#size-cells = <2>;
-			ranges;
+			reg = <0x0 0x00078000 0x0 0x1000>;
 
 			clocks = <&gcc GCC_USB0_AUX_CLK>,
-				 <&gcc GCC_USB0_PHY_CFG_AHB_CLK>, <&xo>;
-			clock-names = "aux", "cfg_ahb", "ref";
+				 <&xo>,
+				 <&gcc GCC_USB0_PHY_CFG_AHB_CLK>,
+				 <&gcc GCC_USB0_PIPE_CLK>;
+			clock-names = "aux",
+				      "ref",
+				      "cfg_ahb",
+				      "pipe";
+			clock-output-names = "gcc_usb0_pipe_clk_src";
+			#clock-cells = <0>;
+			#phy-cells = <0>;
 
 			resets = <&gcc GCC_USB0_PHY_BCR>,
 				 <&gcc GCC_USB3PHY_0_PHY_BCR>;
-			reset-names = "phy","common";
-			status = "disabled";
+			reset-names = "phy",
+				      "phy_phy";
 
-			usb0_ssphy: phy@78200 {
-				reg = <0x0 0x00078200 0x0 0x130>, /* Tx */
-				      <0x0 0x00078400 0x0 0x200>, /* Rx */
-				      <0x0 0x00078800 0x0 0x1f8>, /* PCS */
-				      <0x0 0x00078600 0x0 0x044>; /* PCS misc */
-				#phy-cells = <0>;
-				#clock-cells = <0>;
-				clocks = <&gcc GCC_USB0_PIPE_CLK>;
-				clock-names = "pipe0";
-				clock-output-names = "gcc_usb0_pipe_clk_src";
-			};
+			status = "disabled";
 		};
 
 		qusb_phy_0: qusb@79000 {
@@ -314,6 +316,11 @@
 			reg = <0x0 0x000a4000 0x0 0x2000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
+
+			cpu_speed_bin: cpu-speed-bin@135 {
+				reg = <0x135 0x1>;
+				bits = <7 1>;
+			};
 		};
 
 		prng: qrng@e3000 {
@@ -439,6 +446,26 @@
 			qcom,ee = <0>;
 		};
 
+		blsp1_uart1: serial@78af000 {
+			compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm";
+			reg = <0x0 0x78af000 0x0 0x200>;
+			interrupts = <GIC_SPI 107 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP1_UART1_APPS_CLK>,
+				 <&gcc GCC_BLSP1_AHB_CLK>;
+			clock-names = "core", "iface";
+			status = "disabled";
+		};
+
+		blsp1_uart2: serial@78b0000 {
+			compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm";
+			reg = <0x0 0x78b0000 0x0 0x200>;
+			interrupts = <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP1_UART2_APPS_CLK>,
+				 <&gcc GCC_BLSP1_AHB_CLK>;
+			clock-names = "core", "iface";
+			status = "disabled";
+		};
+
 		blsp1_uart3: serial@78b1000 {
 			compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm";
 			reg = <0x0 0x078b1000 0x0 0x200>;
@@ -449,6 +476,36 @@
 			status = "disabled";
 		};
 
+		blsp1_uart4: serial@78b2000 {
+			compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm";
+			reg = <0x0 0x078b2000 0x0 0x200>;
+			interrupts = <GIC_SPI 307 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP1_UART4_APPS_CLK>,
+				 <&gcc GCC_BLSP1_AHB_CLK>;
+			clock-names = "core", "iface";
+			status = "disabled";
+		};
+
+		blsp1_uart5: serial@78b3000 {
+			compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm";
+			reg = <0x0 0x78b3000 0x0 0x200>;
+			interrupts = <GIC_SPI 308 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP1_UART5_APPS_CLK>,
+				 <&gcc GCC_BLSP1_AHB_CLK>;
+			clock-names = "core", "iface";
+			status = "disabled";
+		};
+
+		blsp1_uart6: serial@78b4000 {
+			compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm";
+			reg = <0x0 0x078b4000 0x0 0x200>;
+			interrupts = <GIC_SPI 309 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP1_UART6_APPS_CLK>,
+				 <&gcc GCC_BLSP1_AHB_CLK>;
+			clock-names = "core", "iface";
+			status = "disabled";
+		};
+
 		blsp1_spi1: spi@78b5000 {
 			compatible = "qcom,spi-qup-v2.2.1";
 			#address-cells = <1>;
@@ -477,6 +534,20 @@
 			status = "disabled";
 		};
 
+		blsp1_spi5: spi@78b9000 {
+			compatible = "qcom,spi-qup-v2.2.1";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x0 0x078b9000 0x0 0x600>;
+			interrupts = <GIC_SPI 299 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP1_QUP5_SPI_APPS_CLK>,
+				 <&gcc GCC_BLSP1_AHB_CLK>;
+			clock-names = "core", "iface";
+			dmas = <&blsp_dma 20>, <&blsp_dma 21>;
+			dma-names = "tx", "rx";
+			status = "disabled";
+		};
+
 		blsp1_i2c2: i2c@78b6000 {
 			compatible = "qcom,i2c-qup-v2.2.1";
 			#address-cells = <1>;
@@ -557,7 +628,7 @@
 					  <&gcc GCC_USB0_MOCK_UTMI_CLK>;
 			assigned-clock-rates = <133330000>,
 					       <133330000>,
-					       <20000000>;
+					       <24000000>;
 
 			resets = <&gcc GCC_USB0_BCR>;
 			status = "disabled";
@@ -566,7 +637,7 @@
 				compatible = "snps,dwc3";
 				reg = <0x0 0x08a00000 0x0 0xcd00>;
 				interrupts = <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>;
-				phys = <&qusb_phy_0>, <&usb0_ssphy>;
+				phys = <&qusb_phy_0>, <&ssphy_0>;
 				phy-names = "usb2-phy", "usb3-phy";
 				clocks = <&xo>;
 				clock-names = "ref";
@@ -611,8 +682,8 @@
 			compatible = "qcom,ipq6018-apcs-apps-global";
 			reg = <0x0 0x0b111000 0x0 0x1000>;
 			#clock-cells = <1>;
-			clocks = <&a53pll>, <&xo>;
-			clock-names = "pll", "xo";
+			clocks = <&a53pll>, <&xo>, <&gcc GPLL0>;
+			clock-names = "pll", "xo", "gpll0";
 			#mbox-cells = <1>;
 		};
 
@@ -731,7 +802,7 @@
 			};
 		};
 
-		pcie0: pci@20000000 {
+		pcie0: pcie@20000000 {
 			compatible = "qcom,pcie-ipq6018";
 			reg = <0x0 0x20000000 0x0 0xf1d>,
 			      <0x0 0x20000f20 0x0 0xa8>,
diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi
index 2f275c84e566..cf295bed3299 100644
--- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi
+++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi
@@ -125,32 +125,26 @@
 
 		ssphy_1: phy@58000 {
 			compatible = "qcom,ipq8074-qmp-usb3-phy";
-			reg = <0x00058000 0x1c4>;
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges;
+			reg = <0x00058000 0x1000>;
 
 			clocks = <&gcc GCC_USB1_AUX_CLK>,
-				<&gcc GCC_USB1_PHY_CFG_AHB_CLK>,
-				<&xo>;
-			clock-names = "aux", "cfg_ahb", "ref";
+				 <&xo>,
+				 <&gcc GCC_USB1_PHY_CFG_AHB_CLK>,
+				 <&gcc GCC_USB1_PIPE_CLK>;
+			clock-names = "aux",
+				      "ref",
+				      "cfg_ahb",
+				      "pipe";
+			clock-output-names = "usb3phy_1_cc_pipe_clk";
+			#clock-cells = <0>;
+			#phy-cells = <0>;
 
 			resets = <&gcc GCC_USB1_PHY_BCR>,
-				<&gcc GCC_USB3PHY_1_PHY_BCR>;
-			reset-names = "phy","common";
-			status = "disabled";
+				 <&gcc GCC_USB3PHY_1_PHY_BCR>;
+			reset-names = "phy",
+				      "phy_phy";
 
-			usb1_ssphy: phy@58200 {
-				reg = <0x00058200 0x130>,     /* Tx */
-				      <0x00058400 0x200>,     /* Rx */
-				      <0x00058800 0x1f8>,     /* PCS */
-				      <0x00058600 0x044>;     /* PCS misc */
-				#phy-cells = <0>;
-				#clock-cells = <0>;
-				clocks = <&gcc GCC_USB1_PIPE_CLK>;
-				clock-names = "pipe0";
-				clock-output-names = "usb3phy_1_cc_pipe_clk";
-			};
+			status = "disabled";
 		};
 
 		qusb_phy_1: phy@59000 {
@@ -168,32 +162,26 @@
 
 		ssphy_0: phy@78000 {
 			compatible = "qcom,ipq8074-qmp-usb3-phy";
-			reg = <0x00078000 0x1c4>;
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges;
+			reg = <0x00078000 0x1000>;
 
 			clocks = <&gcc GCC_USB0_AUX_CLK>,
-				<&gcc GCC_USB0_PHY_CFG_AHB_CLK>,
-				<&xo>;
-			clock-names = "aux", "cfg_ahb", "ref";
+				 <&xo>,
+				 <&gcc GCC_USB0_PHY_CFG_AHB_CLK>,
+				 <&gcc GCC_USB0_PIPE_CLK>;
+			clock-names = "aux",
+				      "ref",
+				      "cfg_ahb",
+				      "pipe";
+			clock-output-names = "usb3phy_0_cc_pipe_clk";
+			#clock-cells = <0>;
+			#phy-cells = <0>;
 
 			resets = <&gcc GCC_USB0_PHY_BCR>,
-				<&gcc GCC_USB3PHY_0_PHY_BCR>;
-			reset-names = "phy","common";
-			status = "disabled";
+				 <&gcc GCC_USB3PHY_0_PHY_BCR>;
+			reset-names = "phy",
+				      "phy_phy";
 
-			usb0_ssphy: phy@78200 {
-				reg = <0x00078200 0x130>,     /* Tx */
-				      <0x00078400 0x200>,     /* Rx */
-				      <0x00078800 0x1f8>,     /* PCS */
-				      <0x00078600 0x044>;     /* PCS misc */
-				#phy-cells = <0>;
-				#clock-cells = <0>;
-				clocks = <&gcc GCC_USB0_PIPE_CLK>;
-				clock-names = "pipe0";
-				clock-output-names = "usb3phy_0_cc_pipe_clk";
-			};
+			status = "disabled";
 		};
 
 		qusb_phy_0: phy@79000 {
@@ -369,8 +357,14 @@
 		gcc: gcc@1800000 {
 			compatible = "qcom,gcc-ipq8074";
 			reg = <0x01800000 0x80000>;
-			clocks = <&xo>, <&sleep_clk>;
-			clock-names = "xo", "sleep_clk";
+			clocks = <&xo>,
+				 <&sleep_clk>,
+				 <&pcie_qmp0>,
+				 <&pcie_qmp1>;
+			clock-names = "xo",
+				      "sleep_clk",
+				      "pcie0_pipe",
+				      "pcie1_pipe";
 			#clock-cells = <1>;
 			#power-domain-cells = <1>;
 			#reset-cells = <1>;
@@ -406,7 +400,7 @@
 		};
 
 		sdhc_1: mmc@7824900 {
-			compatible = "qcom,sdhci-msm-v4";
+			compatible = "qcom,ipq8074-sdhci", "qcom,sdhci-msm-v4";
 			reg = <0x7824900 0x500>, <0x7824000 0x800>;
 			reg-names = "hc", "core";
 
@@ -523,6 +517,20 @@
 			status = "disabled";
 		};
 
+		blsp1_spi4: spi@78b8000 {
+			compatible = "qcom,spi-qup-v2.2.1";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x78b8000 0x600>;
+			interrupts = <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP1_QUP4_SPI_APPS_CLK>,
+				 <&gcc GCC_BLSP1_AHB_CLK>;
+			clock-names = "core", "iface";
+			dmas = <&blsp_dma 18>, <&blsp_dma 19>;
+			dma-names = "tx", "rx";
+			status = "disabled";
+		};
+
 		blsp1_i2c5: i2c@78b9000 {
 			compatible = "qcom,i2c-qup-v2.2.1";
 			#address-cells = <1>;
@@ -628,7 +636,7 @@
 				compatible = "snps,dwc3";
 				reg = <0x8a00000 0xcd00>;
 				interrupts = <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>;
-				phys = <&qusb_phy_0>, <&usb0_ssphy>;
+				phys = <&qusb_phy_0>, <&ssphy_0>;
 				phy-names = "usb2-phy", "usb3-phy";
 				snps,is-utmi-l1-suspend;
 				snps,hird-threshold = /bits/ 8 <0x0>;
@@ -670,7 +678,7 @@
 				compatible = "snps,dwc3";
 				reg = <0x8c00000 0xcd00>;
 				interrupts = <GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>;
-				phys = <&qusb_phy_1>, <&usb1_ssphy>;
+				phys = <&qusb_phy_1>, <&ssphy_1>;
 				phy-names = "usb2-phy", "usb3-phy";
 				snps,is-utmi-l1-suspend;
 				snps,hird-threshold = /bits/ 8 <0x0>;
@@ -708,8 +716,8 @@
 			compatible = "qcom,ipq8074-apcs-apps-global",
 				     "qcom,ipq6018-apcs-apps-global";
 			reg = <0x0b111000 0x1000>;
-			clocks = <&a53pll>, <&xo>;
-			clock-names = "pll", "xo";
+			clocks = <&a53pll>, <&xo>, <&gcc GPLL0>;
+			clock-names = "pll", "xo", "gpll0";
 
 			#clock-cells = <1>;
 			#mbox-cells = <1>;
@@ -781,7 +789,7 @@
 			};
 		};
 
-		pcie1: pci@10000000 {
+		pcie1: pcie@10000000 {
 			compatible = "qcom,pcie-ipq8074";
 			reg = <0x10000000 0xf1d>,
 			      <0x10000f20 0xa8>,
@@ -842,7 +850,7 @@
 			status = "disabled";
 		};
 
-		pcie0: pci@20000000 {
+		pcie0: pcie@20000000 {
 			compatible = "qcom,pcie-ipq8074-gen3";
 			reg = <0x20000000 0xf1d>,
 			      <0x20000f20 0xa8>,
diff --git a/arch/arm64/boot/dts/qcom/ipq9574-rdp-common.dtsi b/arch/arm64/boot/dts/qcom/ipq9574-rdp-common.dtsi
new file mode 100644
index 000000000000..91e104b0f865
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/ipq9574-rdp-common.dtsi
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/*
+ * IPQ9574 RDP board common device tree source
+ *
+ * Copyright (c) 2020-2021 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2023, Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
+#include "ipq9574.dtsi"
+
+/ {
+	aliases {
+		serial0 = &blsp1_uart2;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	regulator_fixed_3p3: s3300 {
+		compatible = "regulator-fixed";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-boot-on;
+		regulator-always-on;
+		regulator-name = "fixed_3p3";
+	};
+
+	regulator_fixed_0p925: s0925 {
+		compatible = "regulator-fixed";
+		regulator-min-microvolt = <925000>;
+		regulator-max-microvolt = <925000>;
+		regulator-boot-on;
+		regulator-always-on;
+		regulator-name = "fixed_0p925";
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		pinctrl-0 = <&gpio_keys_default>;
+		pinctrl-names = "default";
+
+		button-wps {
+			label = "wps";
+			linux,code = <KEY_WPS_BUTTON>;
+			gpios = <&tlmm 37 GPIO_ACTIVE_LOW>;
+			debounce-interval = <60>;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-0 = <&gpio_leds_default>;
+		pinctrl-names = "default";
+
+		led-0 {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_WLAN;
+			gpios = <&tlmm 64 GPIO_ACTIVE_LOW>;
+			linux,default-trigger = "phy0tx";
+			default-state = "off";
+		};
+	};
+};
+
+&blsp1_spi0 {
+	pinctrl-0 = <&spi_0_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	flash@0 {
+		compatible = "micron,n25q128a11", "jedec,spi-nor";
+		reg = <0>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		spi-max-frequency = <50000000>;
+	};
+};
+
+&blsp1_uart2 {
+	pinctrl-0 = <&uart2_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&rpm_requests {
+	regulators {
+		compatible = "qcom,rpm-mp5496-regulators";
+
+		ipq9574_s1: s1 {
+		/*
+		 * During kernel bootup, the SoC runs at 800MHz with 875mV set by the bootloaders.
+		 * During regulator registration, kernel not knowing the initial voltage,
+		 * considers it as zero and brings up the regulators with minimum supported voltage.
+		 * Update the regulator-min-microvolt with SVS voltage of 725mV so that
+		 * the regulators are brought up with 725mV which is sufficient for all the
+		 * corner parts to operate at 800MHz
+		 */
+			regulator-min-microvolt = <725000>;
+			regulator-max-microvolt = <1075000>;
+		};
+
+		mp5496_l2: l2 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-always-on;
+			regulator-boot-on;
+		};
+	};
+};
+
+&sleep_clk {
+	clock-frequency = <32000>;
+};
+
+&tlmm {
+	spi_0_pins: spi-0-state {
+		pins = "gpio11", "gpio12", "gpio13", "gpio14";
+		function = "blsp0_spi";
+		drive-strength = <8>;
+		bias-disable;
+	};
+
+	gpio_keys_default: gpio-keys-default-state {
+		pins = "gpio37";
+		function = "gpio";
+		drive-strength = <8>;
+		bias-pull-up;
+	};
+
+	gpio_leds_default: gpio-leds-default-state {
+		pins = "gpio64";
+		function = "gpio";
+		drive-strength = <8>;
+		bias-pull-up;
+	};
+};
+
+&usb_0_dwc3 {
+	dr_mode = "host";
+};
+
+&usb_0_qmpphy {
+	vdda-pll-supply = <&mp5496_l2>;
+	vdda-phy-supply = <&regulator_fixed_0p925>;
+
+	status = "okay";
+};
+
+&usb_0_qusbphy {
+	vdd-supply = <&regulator_fixed_0p925>;
+	vdda-pll-supply = <&mp5496_l2>;
+	vdda-phy-dpdm-supply = <&regulator_fixed_3p3>;
+
+	status = "okay";
+};
+
+&usb3 {
+	status = "okay";
+};
+
+&xo_board_clk {
+	clock-frequency = <24000000>;
+};
diff --git a/arch/arm64/boot/dts/qcom/ipq9574-rdp418.dts b/arch/arm64/boot/dts/qcom/ipq9574-rdp418.dts
index 2b093e02637b..f4f9199d4ab1 100644
--- a/arch/arm64/boot/dts/qcom/ipq9574-rdp418.dts
+++ b/arch/arm64/boot/dts/qcom/ipq9574-rdp418.dts
@@ -8,58 +8,12 @@
 
 /dts-v1/;
 
-#include "ipq9574.dtsi"
+#include "ipq9574-rdp-common.dtsi"
 
 / {
 	model = "Qualcomm Technologies, Inc. IPQ9574/AP-AL02-C2";
 	compatible = "qcom,ipq9574-ap-al02-c2", "qcom,ipq9574";
 
-	aliases {
-		serial0 = &blsp1_uart2;
-	};
-
-	chosen {
-		stdout-path = "serial0:115200n8";
-	};
-};
-
-&blsp1_spi0 {
-	pinctrl-0 = <&spi_0_pins>;
-	pinctrl-names = "default";
-	status = "okay";
-
-	flash@0 {
-		compatible = "micron,n25q128a11", "jedec,spi-nor";
-		reg = <0>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-		spi-max-frequency = <50000000>;
-	};
-};
-
-&blsp1_uart2 {
-	pinctrl-0 = <&uart2_pins>;
-	pinctrl-names = "default";
-	status = "okay";
-};
-
-&rpm_requests {
-	regulators {
-		compatible = "qcom,rpm-mp5496-regulators";
-
-		ipq9574_s1: s1 {
-		/*
-		 * During kernel bootup, the SoC runs at 800MHz with 875mV set by the bootloaders.
-		 * During regulator registration, kernel not knowing the initial voltage,
-		 * considers it as zero and brings up the regulators with minimum supported voltage.
-		 * Update the regulator-min-microvolt with SVS voltage of 725mV so that
-		 * the regulators are brought up with 725mV which is sufficient for all the
-		 * corner parts to operate at 800MHz
-		 */
-			regulator-min-microvolt = <725000>;
-			regulator-max-microvolt = <1075000>;
-		};
-	};
 };
 
 &sdhc_1 {
@@ -74,10 +28,6 @@
 	status = "okay";
 };
 
-&sleep_clk {
-	clock-frequency = <32000>;
-};
-
 &tlmm {
 	sdc_default_state: sdc-default-state {
 		clk-pins {
@@ -110,15 +60,4 @@
 			bias-pull-down;
 		};
 	};
-
-	spi_0_pins: spi-0-state {
-		pins = "gpio11", "gpio12", "gpio13", "gpio14";
-		function = "blsp0_spi";
-		drive-strength = <8>;
-		bias-disable;
-	};
-};
-
-&xo_board_clk {
-	clock-frequency = <24000000>;
 };
diff --git a/arch/arm64/boot/dts/qcom/ipq9574-rdp433.dts b/arch/arm64/boot/dts/qcom/ipq9574-rdp433.dts
index 877026ccc6e2..1bb8d96c9a82 100644
--- a/arch/arm64/boot/dts/qcom/ipq9574-rdp433.dts
+++ b/arch/arm64/boot/dts/qcom/ipq9574-rdp433.dts
@@ -8,69 +8,11 @@
 
 /dts-v1/;
 
-#include "ipq9574.dtsi"
+#include "ipq9574-rdp-common.dtsi"
 
 / {
 	model = "Qualcomm Technologies, Inc. IPQ9574/AP-AL02-C7";
 	compatible = "qcom,ipq9574-ap-al02-c7", "qcom,ipq9574";
-
-	aliases {
-		serial0 = &blsp1_uart2;
-	};
-
-	chosen {
-		stdout-path = "serial0:115200n8";
-	};
-
-	regulator_fixed_3p3: s3300 {
-		compatible = "regulator-fixed";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-		regulator-boot-on;
-		regulator-always-on;
-		regulator-name = "fixed_3p3";
-	};
-
-	regulator_fixed_0p925: s0925 {
-		compatible = "regulator-fixed";
-		regulator-min-microvolt = <925000>;
-		regulator-max-microvolt = <925000>;
-		regulator-boot-on;
-		regulator-always-on;
-		regulator-name = "fixed_0p925";
-	};
-};
-
-&blsp1_uart2 {
-	pinctrl-0 = <&uart2_pins>;
-	pinctrl-names = "default";
-	status = "okay";
-};
-
-&rpm_requests {
-	regulators {
-		compatible = "qcom,rpm-mp5496-regulators";
-
-		ipq9574_s1: s1 {
-		/*
-		 * During kernel bootup, the SoC runs at 800MHz with 875mV set by the bootloaders.
-		 * During regulator registration, kernel not knowing the initial voltage,
-		 * considers it as zero and brings up the regulators with minimum supported voltage.
-		 * Update the regulator-min-microvolt with SVS voltage of 725mV so that
-		 * the regulators are brought up with 725mV which is sufficient for all the
-		 * corner parts to operate at 800MHz
-		 */
-			regulator-min-microvolt = <725000>;
-			regulator-max-microvolt = <1075000>;
-		};
-
-		mp5496_l2: l2 {
-			regulator-min-microvolt = <1800000>;
-			regulator-max-microvolt = <1800000>;
-			regulator-always-on;
-			regulator-boot-on;
-		};
-	};
 };
 
 &sdhc_1 {
@@ -85,10 +27,6 @@
 	status = "okay";
 };
 
-&sleep_clk {
-	clock-frequency = <32000>;
-};
-
 &tlmm {
 	sdc_default_state: sdc-default-state {
 		clk-pins {
@@ -122,30 +60,3 @@
 		};
 	};
 };
-
-&usb_0_dwc3 {
-	dr_mode = "host";
-};
-
-&usb_0_qmpphy {
-	vdda-pll-supply = <&mp5496_l2>;
-	vdda-phy-supply = <&regulator_fixed_0p925>;
-
-	status = "okay";
-};
-
-&usb_0_qusbphy {
-	vdd-supply = <&regulator_fixed_0p925>;
-	vdda-pll-supply = <&mp5496_l2>;
-	vdda-phy-dpdm-supply = <&regulator_fixed_3p3>;
-
-	status = "okay";
-};
-
-&usb3 {
-	status = "okay";
-};
-
-&xo_board_clk {
-	clock-frequency = <24000000>;
-};
diff --git a/arch/arm64/boot/dts/qcom/ipq9574-rdp449.dts b/arch/arm64/boot/dts/qcom/ipq9574-rdp449.dts
index c8fa54e1a62c..d36d1078763e 100644
--- a/arch/arm64/boot/dts/qcom/ipq9574-rdp449.dts
+++ b/arch/arm64/boot/dts/qcom/ipq9574-rdp449.dts
@@ -8,73 +8,10 @@
 
 /dts-v1/;
 
-#include "ipq9574.dtsi"
+#include "ipq9574-rdp-common.dtsi"
 
 / {
 	model = "Qualcomm Technologies, Inc. IPQ9574/AP-AL02-C6";
 	compatible = "qcom,ipq9574-ap-al02-c6", "qcom,ipq9574";
 
-	aliases {
-		serial0 = &blsp1_uart2;
-	};
-
-	chosen {
-		stdout-path = "serial0:115200n8";
-	};
-};
-
-&blsp1_spi0 {
-	pinctrl-0 = <&spi_0_pins>;
-	pinctrl-names = "default";
-	status = "okay";
-
-	flash@0 {
-		compatible = "micron,n25q128a11", "jedec,spi-nor";
-		reg = <0>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-		spi-max-frequency = <50000000>;
-	};
-};
-
-&blsp1_uart2 {
-	pinctrl-0 = <&uart2_pins>;
-	pinctrl-names = "default";
-	status = "okay";
-};
-
-&rpm_requests {
-	regulators {
-		compatible = "qcom,rpm-mp5496-regulators";
-
-		ipq9574_s1: s1 {
-		/*
-		 * During kernel bootup, the SoC runs at 800MHz with 875mV set by the bootloaders.
-		 * During regulator registration, kernel not knowing the initial voltage,
-		 * considers it as zero and brings up the regulators with minimum supported voltage.
-		 * Update the regulator-min-microvolt with SVS voltage of 725mV so that
-		 * the regulators are brought up with 725mV which is sufficient for all the
-		 * corner parts to operate at 800MHz
-		 */
-			regulator-min-microvolt = <725000>;
-			regulator-max-microvolt = <1075000>;
-		};
-	};
-};
-
-&sleep_clk {
-	clock-frequency = <32000>;
-};
-
-&tlmm {
-	spi_0_pins: spi-0-state {
-		pins = "gpio11", "gpio12", "gpio13", "gpio14";
-		function = "blsp0_spi";
-		drive-strength = <8>;
-		bias-disable;
-	};
-};
-
-&xo_board_clk {
-	clock-frequency = <24000000>;
 };
diff --git a/arch/arm64/boot/dts/qcom/ipq9574-rdp453.dts b/arch/arm64/boot/dts/qcom/ipq9574-rdp453.dts
index f01de6628c3b..c30c9fbedf26 100644
--- a/arch/arm64/boot/dts/qcom/ipq9574-rdp453.dts
+++ b/arch/arm64/boot/dts/qcom/ipq9574-rdp453.dts
@@ -8,73 +8,10 @@
 
 /dts-v1/;
 
-#include "ipq9574.dtsi"
+#include "ipq9574-rdp-common.dtsi"
 
 / {
 	model = "Qualcomm Technologies, Inc. IPQ9574/AP-AL02-C8";
 	compatible = "qcom,ipq9574-ap-al02-c8", "qcom,ipq9574";
 
-	aliases {
-		serial0 = &blsp1_uart2;
-	};
-
-	chosen {
-		stdout-path = "serial0:115200n8";
-	};
-};
-
-&blsp1_spi0 {
-	pinctrl-0 = <&spi_0_pins>;
-	pinctrl-names = "default";
-	status = "okay";
-
-	flash@0 {
-		compatible = "micron,n25q128a11", "jedec,spi-nor";
-		reg = <0>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-		spi-max-frequency = <50000000>;
-	};
-};
-
-&blsp1_uart2 {
-	pinctrl-0 = <&uart2_pins>;
-	pinctrl-names = "default";
-	status = "okay";
-};
-
-&rpm_requests {
-	regulators {
-		compatible = "qcom,rpm-mp5496-regulators";
-
-		ipq9574_s1: s1 {
-		/*
-		 * During kernel bootup, the SoC runs at 800MHz with 875mV set by the bootloaders.
-		 * During regulator registration, kernel not knowing the initial voltage,
-		 * considers it as zero and brings up the regulators with minimum supported voltage.
-		 * Update the regulator-min-microvolt with SVS voltage of 725mV so that
-		 * the regulators are brought up with 725mV which is sufficient for all the
-		 * corner parts to operate at 800MHz
-		 */
-			regulator-min-microvolt = <725000>;
-			regulator-max-microvolt = <1075000>;
-		};
-	};
-};
-
-&sleep_clk {
-	clock-frequency = <32000>;
-};
-
-&tlmm {
-	spi_0_pins: spi-0-state {
-		pins = "gpio11", "gpio12", "gpio13", "gpio14";
-		function = "blsp0_spi";
-		drive-strength = <8>;
-		bias-disable;
-	};
-};
-
-&xo_board_clk {
-	clock-frequency = <24000000>;
 };
diff --git a/arch/arm64/boot/dts/qcom/ipq9574-rdp454.dts b/arch/arm64/boot/dts/qcom/ipq9574-rdp454.dts
index 6efae3426cb8..0dc382f5d5ec 100644
--- a/arch/arm64/boot/dts/qcom/ipq9574-rdp454.dts
+++ b/arch/arm64/boot/dts/qcom/ipq9574-rdp454.dts
@@ -8,73 +8,9 @@
 
 /dts-v1/;
 
-#include "ipq9574.dtsi"
+#include "ipq9574-rdp-common.dtsi"
 
 / {
 	model = "Qualcomm Technologies, Inc. IPQ9574/AP-AL02-C9";
 	compatible = "qcom,ipq9574-ap-al02-c9", "qcom,ipq9574";
-
-	aliases {
-		serial0 = &blsp1_uart2;
-	};
-
-	chosen {
-		stdout-path = "serial0:115200n8";
-	};
-};
-
-&blsp1_spi0 {
-	pinctrl-0 = <&spi_0_pins>;
-	pinctrl-names = "default";
-	status = "okay";
-
-	flash@0 {
-		compatible = "micron,n25q128a11", "jedec,spi-nor";
-		reg = <0>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-		spi-max-frequency = <50000000>;
-	};
-};
-
-&blsp1_uart2 {
-	pinctrl-0 = <&uart2_pins>;
-	pinctrl-names = "default";
-	status = "okay";
-};
-
-&rpm_requests {
-	regulators {
-		compatible = "qcom,rpm-mp5496-regulators";
-
-		ipq9574_s1: s1 {
-		/*
-		 * During kernel bootup, the SoC runs at 800MHz with 875mV set by the bootloaders.
-		 * During regulator registration, kernel not knowing the initial voltage,
-		 * considers it as zero and brings up the regulators with minimum supported voltage.
-		 * Update the regulator-min-microvolt with SVS voltage of 725mV so that
-		 * the regulators are brought up with 725mV which is sufficient for all the
-		 * corner parts to operate at 800MHz
-		 */
-			regulator-min-microvolt = <725000>;
-			regulator-max-microvolt = <1075000>;
-		};
-	};
-};
-
-&sleep_clk {
-	clock-frequency = <32000>;
-};
-
-&tlmm {
-	spi_0_pins: spi-0-state {
-		pins = "gpio11", "gpio12", "gpio13", "gpio14";
-		function = "blsp0_spi";
-		drive-strength = <8>;
-		bias-disable;
-	};
-};
-
-&xo_board_clk {
-	clock-frequency = <24000000>;
 };
diff --git a/arch/arm64/boot/dts/qcom/ipq9574.dtsi b/arch/arm64/boot/dts/qcom/ipq9574.dtsi
index 8a72ad4afd03..5f83ee42a719 100644
--- a/arch/arm64/boot/dts/qcom/ipq9574.dtsi
+++ b/arch/arm64/boot/dts/qcom/ipq9574.dtsi
@@ -106,42 +106,56 @@
 	};
 
 	cpu_opp_table: opp-table-cpu {
-		compatible = "operating-points-v2";
+		compatible = "operating-points-v2-kryo-cpu";
 		opp-shared;
+		nvmem-cells = <&cpu_speed_bin>;
 
 		opp-936000000 {
 			opp-hz = /bits/ 64 <936000000>;
 			opp-microvolt = <725000>;
+			opp-supported-hw = <0xf>;
 			clock-latency-ns = <200000>;
 		};
 
 		opp-1104000000 {
 			opp-hz = /bits/ 64 <1104000000>;
 			opp-microvolt = <787500>;
+			opp-supported-hw = <0xf>;
+			clock-latency-ns = <200000>;
+		};
+
+		opp-1200000000 {
+			opp-hz = /bits/ 64 <1200000000>;
+			opp-microvolt = <862500>;
+			opp-supported-hw = <0xf>;
 			clock-latency-ns = <200000>;
 		};
 
 		opp-1416000000 {
 			opp-hz = /bits/ 64 <1416000000>;
 			opp-microvolt = <862500>;
+			opp-supported-hw = <0x7>;
 			clock-latency-ns = <200000>;
 		};
 
 		opp-1488000000 {
 			opp-hz = /bits/ 64 <1488000000>;
 			opp-microvolt = <925000>;
+			opp-supported-hw = <0x7>;
 			clock-latency-ns = <200000>;
 		};
 
 		opp-1800000000 {
 			opp-hz = /bits/ 64 <1800000000>;
 			opp-microvolt = <987500>;
+			opp-supported-hw = <0x5>;
 			clock-latency-ns = <200000>;
 		};
 
 		opp-2208000000 {
 			opp-hz = /bits/ 64 <2208000000>;
 			opp-microvolt = <1062500>;
+			opp-supported-hw = <0x1>;
 			clock-latency-ns = <200000>;
 		};
 	};
@@ -223,6 +237,11 @@
 			reg = <0x000a4000 0x5a1>;
 			#address-cells = <1>;
 			#size-cells = <1>;
+
+			cpu_speed_bin: cpu-speed-bin@15 {
+				reg = <0x15 0x2>;
+				bits = <7 2>;
+			};
 		};
 
 		cryptobam: dma-controller@704000 {
@@ -652,8 +671,8 @@
 				     "qcom,ipq6018-apcs-apps-global";
 			reg = <0x0b111000 0x1000>;
 			#clock-cells = <1>;
-			clocks = <&a73pll>, <&xo_board_clk>;
-			clock-names = "pll", "xo";
+			clocks = <&a73pll>, <&xo_board_clk>, <&gcc GPLL0>;
+			clock-names = "pll", "xo", "gpll0";
 			#mbox-cells = <1>;
 		};
 
diff --git a/arch/arm64/boot/dts/qcom/msm8916-acer-a1-724.dts b/arch/arm64/boot/dts/qcom/msm8916-acer-a1-724.dts
index 57a74eea1005..b32c7a97394d 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-acer-a1-724.dts
+++ b/arch/arm64/boot/dts/qcom/msm8916-acer-a1-724.dts
@@ -7,6 +7,7 @@
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/leds/common.h>
 
 /*
  * NOTE: The original firmware from Acer can only boot 32-bit kernels.
@@ -83,6 +84,29 @@
 	};
 };
 
+&blsp_i2c4 {
+	status = "okay";
+
+	led-controller@30 {
+		compatible = "kinetic,ktd2026";
+		reg = <0x30>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		led@0 {
+			reg = <0>;
+			function = LED_FUNCTION_STATUS;
+			color = <LED_COLOR_ID_RED>;
+		};
+
+		led@1 {
+			reg = <1>;
+			function = LED_FUNCTION_STATUS;
+			color = <LED_COLOR_ID_GREEN>;
+		};
+	};
+};
+
 &blsp_i2c5 {
 	status = "okay";
 
diff --git a/arch/arm64/boot/dts/qcom/msm8916-alcatel-idol347.dts b/arch/arm64/boot/dts/qcom/msm8916-alcatel-idol347.dts
index aa4c1ab1e673..3459145516a1 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-alcatel-idol347.dts
+++ b/arch/arm64/boot/dts/qcom/msm8916-alcatel-idol347.dts
@@ -3,6 +3,8 @@
 /dts-v1/;
 
 #include "msm8916-pm8916.dtsi"
+#include "msm8916-modem-qdsp6.dtsi"
+
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/leds/common.h>
@@ -22,6 +24,19 @@
 		stdout-path = "serial0";
 	};
 
+	reserved-memory {
+		/delete-node/ reserved@86680000;
+		/delete-node/ rmtfs@86700000;
+
+		rmtfs: rmtfs@86680000 {
+			compatible = "qcom,rmtfs-mem";
+			reg = <0x0 0x86680000 0x0 0x160000>;
+			no-map;
+
+			qcom,client-id = <1>;
+		};
+	};
+
 	gpio-keys {
 		compatible = "gpio-keys";
 
@@ -50,6 +65,17 @@
 		};
 	};
 
+	reg_headphones_avdd: regulator-headphones-avdd {
+		compatible = "regulator-fixed";
+		regulator-name = "headphones_avdd";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		gpio = <&tlmm 121 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		pinctrl-0 = <&headphones_avdd_default>;
+		pinctrl-names = "default";
+	};
+
 	usb_id: usb-id {
 		compatible = "linux,extcon-usb-gpio";
 		id-gpios = <&tlmm 69 GPIO_ACTIVE_HIGH>;
@@ -58,8 +84,41 @@
 	};
 };
 
-&blsp_uart2 {
+&blsp_i2c3 {
 	status = "okay";
+
+	headphones: audio-codec@10 {
+		compatible = "asahi-kasei,ak4375";
+		reg = <0x10>;
+		avdd-supply = <&reg_headphones_avdd>;
+		tvdd-supply = <&pm8916_l6>;
+		pdn-gpios = <&tlmm 114 GPIO_ACTIVE_HIGH>;
+		pinctrl-0 = <&headphones_pdn_default>;
+		pinctrl-names = "default";
+		#sound-dai-cells = <0>;
+	};
+
+	speaker_codec_top: audio-codec@34 {
+		compatible = "nxp,tfa9897";
+		reg = <0x34>;
+		vddd-supply = <&pm8916_l6>;
+		rcv-gpios = <&tlmm 50 GPIO_ACTIVE_HIGH>;
+		pinctrl-0 = <&speaker_top_default>;
+		pinctrl-names = "default";
+		sound-name-prefix = "Speaker Top";
+		#sound-dai-cells = <0>;
+	};
+
+	speaker_codec_bottom: audio-codec@36 {
+		compatible = "nxp,tfa9897";
+		reg = <0x36>;
+		vddd-supply = <&pm8916_l6>;
+		rcv-gpios = <&tlmm 111 GPIO_ACTIVE_HIGH>;
+		pinctrl-0 = <&speaker_bottom_default>;
+		pinctrl-names = "default";
+		sound-name-prefix = "Speaker Bottom";
+		#sound-dai-cells = <0>;
+	};
 };
 
 &blsp_i2c4 {
@@ -153,6 +212,22 @@
 	};
 };
 
+&blsp_uart2 {
+	status = "okay";
+};
+
+&mpss_mem {
+	reg = <0x0 0x86800000 0x0 0x5000000>;
+};
+
+&pm8916_codec {
+	qcom,micbias1-ext-cap;
+	qcom,micbias-lvl = <2800>;
+	qcom,mbhc-vthreshold-low = <75 100 120 180 500>;
+	qcom,mbhc-vthreshold-high = <75 100 120 180 500>;
+	qcom,hphl-jack-type-normally-open;
+};
+
 &pm8916_resin {
 	status = "okay";
 	linux,code = <KEY_VOLUMEDOWN>;
@@ -169,6 +244,17 @@
 	status = "okay";
 };
 
+&q6afedai {
+	dai@18 {
+		reg = <SECONDARY_MI2S_RX>;
+		qcom,sd-lines = <0>;
+	};
+	dai@22 {
+		reg = <QUATERNARY_MI2S_RX>;
+		qcom,sd-lines = <0>;
+	};
+};
+
 &sdhc_1 {
 	status = "okay";
 };
@@ -183,6 +269,54 @@
 	cd-gpios = <&tlmm 38 GPIO_ACTIVE_LOW>;
 };
 
+&sound {
+	/* Add pin switches for speakers to allow disabling them individually */
+	model = "alcatel-idol3";
+	widgets =
+		"Speaker", "Speaker Top",
+		"Speaker", "Speaker Bottom";
+	pin-switches = "Speaker Top", "Speaker Bottom";
+	audio-routing =
+		"Speaker Top", "Speaker Top OUT",
+		"Speaker Bottom", "Speaker Bottom OUT",
+		"AMIC1", "MIC BIAS External1",
+		"AMIC2", "MIC BIAS Internal2",
+		"AMIC3", "MIC BIAS External1";
+
+	pinctrl-0 = <&cdc_pdm_default &pri_mi2s_default &pri_mi2s_ws_default &sec_mi2s_default>;
+	pinctrl-1 = <&cdc_pdm_sleep &pri_mi2s_sleep &pri_mi2s_ws_sleep &sec_mi2s_sleep>;
+	pinctrl-names = "default", "sleep";
+
+	sound_link_backend2: backend2-dai-link {
+		link-name = "Quaternary MI2S";
+
+		cpu {
+			sound-dai = <&q6afedai QUATERNARY_MI2S_RX>;
+		};
+		platform {
+			sound-dai = <&q6routing>;
+		};
+		codec {
+			sound-dai = <&speaker_codec_top>, <&speaker_codec_bottom>;
+		};
+	};
+};
+
+&sound_link_backend0 {
+	/* Primary MI2S is not used, replace with Secondary MI2S for headphones */
+	link-name = "Secondary MI2S";
+
+	cpu {
+		sound-dai = <&q6afedai SECONDARY_MI2S_RX>;
+	};
+	platform {
+		sound-dai = <&q6routing>;
+	};
+	codec {
+		sound-dai = <&headphones>;
+	};
+};
+
 &usb {
 	status = "okay";
 	extcon = <&usb_id>, <&usb_id>;
@@ -212,6 +346,15 @@
 	status = "okay";
 };
 
+/* Only some of the pins are used */
+&pri_mi2s_default {
+	pins = "gpio113", "gpio115";
+};
+
+&pri_mi2s_sleep {
+	pins = "gpio113", "gpio115";
+};
+
 &tlmm {
 	accel_int_default: accel-int-default-state {
 		pins = "gpio31";
@@ -245,6 +388,20 @@
 		bias-disable;
 	};
 
+	headphones_avdd_default: headphones-avdd-default-state {
+		pins = "gpio121";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
+	headphones_pdn_default: headphones-pdn-default-state {
+		pins = "gpio114";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
 	/*
 	 * The OEM wired an additional GPIO to be asserted so that
 	 * the si-en,sn3190 LED IC works. Since this GPIO is not
@@ -291,6 +448,20 @@
 		bias-disable;
 	};
 
+	speaker_bottom_default: speaker-bottom-default-state {
+		pins = "gpio111";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
+	speaker_top_default: speaker-top-default-state {
+		pins = "gpio50";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
 	ts_int_reset_default: ts-int-reset-default-state {
 		pins = "gpio13", "gpio100";
 		function = "gpio";
diff --git a/arch/arm64/boot/dts/qcom/msm8916-asus-z00l.dts b/arch/arm64/boot/dts/qcom/msm8916-asus-z00l.dts
index a8be6ff66893..77618c7374df 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-asus-z00l.dts
+++ b/arch/arm64/boot/dts/qcom/msm8916-asus-z00l.dts
@@ -3,6 +3,8 @@
 /dts-v1/;
 
 #include "msm8916-pm8916.dtsi"
+#include "msm8916-modem-qdsp6.dtsi"
+
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/interrupt-controller/irq.h>
@@ -130,6 +132,18 @@
 	status = "okay";
 };
 
+&mpss_mem {
+	reg = <0x0 0x86800000 0x0 0x5500000>;
+};
+
+&pm8916_codec {
+	qcom,micbias-lvl = <2800>;
+	qcom,mbhc-vthreshold-low = <75 150 237 450 500>;
+	qcom,mbhc-vthreshold-high = <75 150 237 450 500>;
+	qcom,micbias1-ext-cap;
+	qcom,hphl-jack-type-normally-open;
+};
+
 &pm8916_rpm_regulators {
 	pm8916_l17: l17 {
 		regulator-min-microvolt = <2850000>;
@@ -151,6 +165,13 @@
 	cd-gpios = <&tlmm 38 GPIO_ACTIVE_LOW>;
 };
 
+&sound {
+	audio-routing =
+		"AMIC1", "MIC BIAS External1",
+		"AMIC2", "MIC BIAS Internal2",
+		"AMIC3", "MIC BIAS External1";
+};
+
 &usb {
 	status = "okay";
 	extcon = <&usb_id>, <&usb_id>;
diff --git a/arch/arm64/boot/dts/qcom/msm8916-longcheer-l8150.dts b/arch/arm64/boot/dts/qcom/msm8916-longcheer-l8150.dts
index 47d1c5cb13f4..3a3e794c022f 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-longcheer-l8150.dts
+++ b/arch/arm64/boot/dts/qcom/msm8916-longcheer-l8150.dts
@@ -3,6 +3,8 @@
 /dts-v1/;
 
 #include "msm8916-pm8916.dtsi"
+#include "msm8916-modem-qdsp6.dtsi"
+
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/interrupt-controller/irq.h>
@@ -25,17 +27,45 @@
 
 	/*
 	 * For some reason, the signed wcnss firmware is not relocatable.
-	 * It must be loaded at 0x8b600000. All other firmware is relocatable,
-	 * so place wcnss at the fixed address and then all other firmware
-	 * regions will be automatically allocated at a fitting place.
+	 * It must be loaded at 0x8b600000. Unfortunately, this also means that
+	 * mpss_mem does not fit when loaded to the typical address at 0x86800000.
+	 *
+	 * Load wcnss_mem to the fixed address and relocate mpss_mem to the next
+	 * working higher address. For some reason the modem firmware does not
+	 * boot when placed at 0x8a800000 to 0x8e800000.
 	 */
 	reserved-memory {
+		/delete-node/ mpss@86800000;
 		/delete-node/ wcnss;
 
 		wcnss_mem: wcnss@8b600000 {
 			reg = <0x0 0x8b600000 0x0 0x600000>;
 			no-map;
 		};
+
+		mpss_mem: mpss@8e800000 {
+			reg = <0x0 0x8e800000 0x0 0x5000000>;
+			no-map;
+		};
+	};
+
+	battery: battery {
+		compatible = "simple-battery";
+		voltage-min-design-microvolt = <3400000>;
+		voltage-max-design-microvolt = <4350000>;
+		energy-full-design-microwatt-hours = <9500000>;
+		charge-full-design-microamp-hours = <2500000>;
+
+		ocv-capacity-celsius = <25>;
+		ocv-capacity-table-0 = <4330000 100>, <4265000 95>,
+			<4208000 90>, <4153000 85>, <4100000 80>, <4049000 75>,
+			<4001000 70>, <3962000 65>, <3919000 60>, <3872000 55>,
+			<3839000 50>, <3817000 45>, <3798000 40>, <3783000 35>,
+			<3767000 30>, <3747000 25>, <3729000 20>, <3709000 16>,
+			<3688000 13>, <3681000 11>, <3680000 10>, <3679000 9>,
+			<3677000 8>, <3674000 7>, <3666000 6>, <3641000 5>,
+			<3597000 4>, <3537000 3>, <3457000 2>, <3336000 1>,
+			<3000000 0>;
 	};
 
 	gpio-keys {
@@ -93,6 +123,7 @@
 		#size-cells = <0>;
 
 		vcc-supply = <&pm8916_l17>;
+		vio-supply = <&pm8916_l6>;
 
 		led@0 {
 			reg = <0>;
@@ -225,6 +256,29 @@
 	status = "okay";
 };
 
+&pm8916_bms {
+	status = "okay";
+
+	monitored-battery = <&battery>;
+	power-supplies = <&pm8916_charger>;
+};
+
+&pm8916_charger {
+	status = "okay";
+
+	monitored-battery = <&battery>;
+
+	qcom,fast-charge-safe-current = <900000>;
+	qcom,fast-charge-safe-voltage = <4300000>;
+};
+
+&pm8916_codec {
+	qcom,micbias-lvl = <2800>;
+	qcom,mbhc-vthreshold-low = <75 150 237 450 500>;
+	qcom,mbhc-vthreshold-high = <75 150 237 450 500>;
+	qcom,hphl-jack-type-normally-open;
+};
+
 &pm8916_resin {
 	status = "okay";
 	linux,code = <KEY_VOLUMEDOWN>;
@@ -237,10 +291,6 @@
 	};
 };
 
-&pm8916_usbin {
-	status = "okay";
-};
-
 &pm8916_vib {
 	status = "okay";
 };
@@ -254,14 +304,21 @@
 	non-removable;
 };
 
+&sound {
+	audio-routing =
+		"AMIC1", "MIC BIAS Internal1",
+		"AMIC2", "MIC BIAS Internal2",
+		"AMIC3", "MIC BIAS Internal3";
+};
+
 &usb {
 	status = "okay";
 	dr_mode = "peripheral";
-	extcon = <&pm8916_usbin>;
+	extcon = <&pm8916_charger>;
 };
 
 &usb_hs_phy {
-	extcon = <&pm8916_usbin>;
+	extcon = <&pm8916_charger>;
 };
 
 &venus {
diff --git a/arch/arm64/boot/dts/qcom/msm8916-longcheer-l8910.dts b/arch/arm64/boot/dts/qcom/msm8916-longcheer-l8910.dts
index 41cadb906b98..3b7fdb6797a9 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-longcheer-l8910.dts
+++ b/arch/arm64/boot/dts/qcom/msm8916-longcheer-l8910.dts
@@ -3,9 +3,12 @@
 /dts-v1/;
 
 #include "msm8916-pm8916.dtsi"
+#include "msm8916-modem-qdsp6.dtsi"
+
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/leds/common.h>
+#include <dt-bindings/pinctrl/qcom,pmic-gpio.h>
 
 / {
 	model = "BQ Aquaris X5 (Longcheer L8910)";
@@ -22,6 +25,16 @@
 		stdout-path = "serial0";
 	};
 
+	speaker_amp: audio-amplifier {
+		compatible = "awinic,aw8738";
+		mode-gpios = <&tlmm 114 GPIO_ACTIVE_HIGH>;
+		awinic,mode = <5>;
+		sound-name-prefix = "Speaker Amp";
+
+		pinctrl-0 = <&spk_ext_pa_default>;
+		pinctrl-names = "default";
+	};
+
 	flash-led-controller {
 		compatible = "ocs,ocp8110";
 		enable-gpios = <&tlmm 49 GPIO_ACTIVE_HIGH>;
@@ -74,6 +87,46 @@
 	};
 };
 
+&blsp_i2c2 {
+	status = "okay";
+
+	led-controller@30 {
+		compatible = "kinetic,ktd2026";
+		reg = <0x30>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		vin-supply = <&pm8916_l17>;
+		vio-supply = <&pm8916_l6>;
+
+		pinctrl-0 = <&status_led_default>;
+		pinctrl-names = "default";
+
+		multi-led {
+			color = <LED_COLOR_ID_RGB>;
+			function = LED_FUNCTION_STATUS;
+
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			led@0 {
+				reg = <0>;
+				color = <LED_COLOR_ID_RED>;
+			};
+
+			led@1 {
+				reg = <1>;
+				color = <LED_COLOR_ID_GREEN>;
+			};
+
+			led@2 {
+				reg = <2>;
+				color = <LED_COLOR_ID_BLUE>;
+			};
+		};
+	};
+};
+
 &blsp_i2c3 {
 	status = "okay";
 
@@ -107,6 +160,27 @@
 	status = "okay";
 };
 
+&mpss_mem {
+	reg = <0x0 0x86800000 0x0 0x5000000>;
+};
+
+&pm8916_codec {
+	qcom,micbias-lvl = <2800>;
+	qcom,mbhc-vthreshold-low = <75 100 120 180 500>;
+	qcom,mbhc-vthreshold-high = <75 100 120 180 500>;
+	qcom,hphl-jack-type-normally-open;
+};
+
+&pm8916_gpios {
+	status_led_default: status-led-default-state {
+		pins = "gpio3";
+		function = PMIC_GPIO_FUNC_NORMAL;
+		power-source = <PM8916_GPIO_VPH>;
+		bias-disable;
+		output-high;
+	};
+};
+
 &pm8916_resin {
 	status = "okay";
 	linux,code = <KEY_VOLUMEDOWN>;
@@ -137,6 +211,28 @@
 	cd-gpios = <&tlmm 38 GPIO_ACTIVE_LOW>;
 };
 
+&sound {
+	/*
+	 * Provide widgets/pin-switches to allow enabling speaker separately.
+	 * The hardware does not provide a way to disable the output via the
+	 * headphone jack when the speaker is enabled.
+	 */
+	model = "bq-paella";
+	widgets =
+		"Speaker", "Speaker",
+		"Headphone", "Headphones";
+	pin-switches = "Speaker";
+	audio-routing =
+		"Speaker", "Speaker Amp OUT",
+		"Speaker Amp IN", "HPH_R",
+		"Headphones", "HPH_L",
+		"Headphones", "HPH_R",
+		"AMIC1", "MIC BIAS External1",
+		"AMIC2", "MIC BIAS Internal2",
+		"AMIC3", "MIC BIAS External1";
+	aux-devs = <&speaker_amp>;
+};
+
 &usb {
 	status = "okay";
 	extcon = <&usb_id>, <&usb_id>;
@@ -205,6 +301,13 @@
 		bias-disable;
 	};
 
+	spk_ext_pa_default: spk-ext-pa-default-state {
+		pins = "gpio114";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
 	usb_id_default: usb-id-default-state {
 		pins = "gpio110";
 		function = "gpio";
diff --git a/arch/arm64/boot/dts/qcom/msm8916-modem-qdsp6.dtsi b/arch/arm64/boot/dts/qcom/msm8916-modem-qdsp6.dtsi
new file mode 100644
index 000000000000..039961622633
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/msm8916-modem-qdsp6.dtsi
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/*
+ * msm8916-modem-qdsp6.dtsi describes the typical modem setup on MSM8916 devices
+ * (or similar SoCs) with audio routed via the QDSP6 services provided by the
+ * modem firmware. The digital/analog codec in the SoC/PMIC is used by default,
+ * but boards can define additional codecs by adding additional backend DAI links.
+ */
+
+#include <dt-bindings/sound/qcom,q6afe.h>
+#include <dt-bindings/sound/qcom,q6asm.h>
+
+&apr {
+	status = "okay";
+};
+
+&bam_dmux {
+	status = "okay";
+};
+
+&bam_dmux_dma {
+	status = "okay";
+};
+
+&lpass {
+	status = "reserved"; /* Controlled by QDSP6 */
+};
+
+&lpass_codec {
+	status = "okay";
+};
+
+&mba_mem {
+	status = "okay";
+};
+
+&mpss {
+	status = "okay";
+};
+
+&mpss_mem {
+	status = "okay";
+};
+
+&pm8916_codec {
+	status = "okay";
+};
+
+&q6afedai {
+	dai@16 {
+		reg = <PRIMARY_MI2S_RX>;
+		qcom,sd-lines = <0 1>;
+	};
+	dai@20 {
+		reg = <TERTIARY_MI2S_TX>;
+		qcom,sd-lines = <0 1>;
+	};
+};
+
+&q6asmdai {
+	dai@0 {
+		reg = <0>;
+		direction = <Q6ASM_DAI_RX>;
+	};
+	dai@1 {
+		reg = <1>;
+		direction = <Q6ASM_DAI_TX>;
+	};
+	dai@2 {
+		reg = <2>;
+		direction = <Q6ASM_DAI_RX>;
+	};
+	dai@3 {
+		reg = <3>;
+		direction = <Q6ASM_DAI_RX>;
+		is-compress-dai;
+	};
+};
+
+&sound {
+	compatible = "qcom,msm8916-qdsp6-sndcard";
+	model = "msm8916";
+
+	pinctrl-0 = <&cdc_pdm_default>;
+	pinctrl-1 = <&cdc_pdm_sleep>;
+	pinctrl-names = "default", "sleep";
+
+	status = "okay";
+
+	frontend0-dai-link {
+		link-name = "MultiMedia1";
+
+		cpu {
+			sound-dai = <&q6asmdai MSM_FRONTEND_DAI_MULTIMEDIA1>;
+		};
+	};
+
+	frontend1-dai-link {
+		link-name = "MultiMedia2";
+
+		cpu {
+			sound-dai = <&q6asmdai MSM_FRONTEND_DAI_MULTIMEDIA2>;
+		};
+	};
+
+	frontend2-dai-link {
+		link-name = "MultiMedia3";
+
+		cpu {
+			sound-dai = <&q6asmdai MSM_FRONTEND_DAI_MULTIMEDIA3>;
+		};
+	};
+
+	frontend3-dai-link {
+		link-name = "MultiMedia4";
+
+		cpu {
+			sound-dai = <&q6asmdai MSM_FRONTEND_DAI_MULTIMEDIA4>;
+		};
+	};
+
+	sound_link_backend0: backend0-dai-link {
+		link-name = "Primary MI2S";
+
+		cpu {
+			sound-dai = <&q6afedai PRIMARY_MI2S_RX>;
+		};
+		platform {
+			sound-dai = <&q6routing>;
+		};
+		codec {
+			sound-dai = <&lpass_codec 0>, <&pm8916_codec 0>;
+		};
+	};
+
+	sound_link_backend1: backend1-dai-link {
+		link-name = "Tertiary MI2S";
+
+		cpu {
+			sound-dai = <&q6afedai TERTIARY_MI2S_TX>;
+		};
+		platform {
+			sound-dai = <&q6routing>;
+		};
+		codec {
+			sound-dai = <&lpass_codec 1>, <&pm8916_codec 1>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/qcom/msm8916-samsung-a2015-common.dtsi b/arch/arm64/boot/dts/qcom/msm8916-samsung-a2015-common.dtsi
index 0b29132b74e1..2937495940ea 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-samsung-a2015-common.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8916-samsung-a2015-common.dtsi
@@ -1,10 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0-only
 
 #include "msm8916-pm8916.dtsi"
+#include "msm8916-modem-qdsp6.dtsi"
+
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/pinctrl/qcom,pmic-gpio.h>
+#include <dt-bindings/sound/apq8016-lpass.h>
 
 / {
 	aliases {
@@ -196,6 +199,18 @@
 	};
 };
 
+&blsp_i2c1 {
+	status = "okay";
+
+	speaker_codec: audio-codec@34 {
+		compatible = "nxp,tfa9895";
+		reg = <0x34>;
+		vddd-supply = <&pm8916_l5>;
+		sound-name-prefix = "Speaker";
+		#sound-dai-cells = <0>;
+	};
+};
+
 &blsp_i2c2 {
 	status = "okay";
 
@@ -243,6 +258,25 @@
 	status = "okay";
 };
 
+/*
+ * For some reason the speaker amplifier is connected to the second SD line
+ * (MI2S_2_D1) instead of the first (MI2S_2_D0). This must be configured in the
+ * device tree, otherwise audio will seemingly play fine on the wrong SD line
+ * but the speaker stays silent.
+ *
+ * When routing audio via QDSP6 (the default) the &lpass node is reserved and
+ * the definitions from &q6afedai are used. When the modem is disabled audio can
+ * be alternatively routed directly to the LPASS hardware with reduced latency.
+ * The definitions for &lpass are here for completeness to simplify changing the
+ * setup with minor changes to the DT (either manually or with DT overlays).
+ */
+&lpass {
+	dai-link@3 {
+		reg = <MI2S_QUATERNARY>;
+		qcom,playback-sd-lines = <1>;
+	};
+};
+
 &mdss {
 	status = "okay";
 };
@@ -253,6 +287,10 @@
 	pinctrl-1 = <&mdss_sleep>;
 };
 
+&mpss_mem {
+	reg = <0x0 0x86800000 0x0 0x5400000>;
+};
+
 &pm8916_resin {
 	status = "okay";
 	linux,code = <KEY_VOLUMEDOWN>;
@@ -265,6 +303,13 @@
 	};
 };
 
+&q6afedai {
+	dai@22 {
+		reg = <QUATERNARY_MI2S_RX>;
+		qcom,sd-lines = <1>;
+	};
+};
+
 &sdhc_1 {
 	status = "okay";
 };
@@ -279,6 +324,32 @@
 	cd-gpios = <&tlmm 38 GPIO_ACTIVE_LOW>;
 };
 
+&sound {
+	model = "samsung-a2015";
+	audio-routing =
+		"AMIC1", "MIC BIAS External1",
+		"AMIC2", "MIC BIAS Internal2",
+		"AMIC3", "MIC BIAS External1";
+
+	pinctrl-0 = <&cdc_pdm_default &sec_mi2s_default>;
+	pinctrl-1 = <&cdc_pdm_sleep &sec_mi2s_sleep>;
+	pinctrl-names = "default", "sleep";
+
+	sound_link_backend2: backend2-dai-link {
+		link-name = "Quaternary MI2S";
+
+		cpu {
+			sound-dai = <&q6afedai QUATERNARY_MI2S_RX>;
+		};
+		platform {
+			sound-dai = <&q6routing>;
+		};
+		codec {
+			sound-dai = <&speaker_codec>;
+		};
+	};
+};
+
 &usb {
 	status = "okay";
 	extcon = <&muic>, <&muic>;
diff --git a/arch/arm64/boot/dts/qcom/msm8916-samsung-a3u-eur.dts b/arch/arm64/boot/dts/qcom/msm8916-samsung-a3u-eur.dts
index f5a808369518..3b934f5eba47 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-samsung-a3u-eur.dts
+++ b/arch/arm64/boot/dts/qcom/msm8916-samsung-a3u-eur.dts
@@ -49,11 +49,6 @@
 	};
 };
 
-&touchkey {
-	vcc-supply = <&reg_touch_key>;
-	vdd-supply = <&reg_key_led>;
-};
-
 &accelerometer {
 	mount-matrix = "0", "1", "0",
 		       "1", "0", "0",
@@ -108,6 +103,11 @@
 	remote-endpoint = <&panel_in>;
 };
 
+&touchkey {
+	vcc-supply = <&reg_touch_key>;
+	vdd-supply = <&reg_key_led>;
+};
+
 &vibrator {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/qcom/msm8916-samsung-e2015-common.dtsi b/arch/arm64/boot/dts/qcom/msm8916-samsung-e2015-common.dtsi
index 0824ab041d80..3c49dac92d2d 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-samsung-e2015-common.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8916-samsung-e2015-common.dtsi
@@ -65,6 +65,10 @@
 	};
 };
 
+&mpss_mem {
+	reg = <0x0 0x86800000 0x0 0x5a00000>;
+};
+
 &reg_motor_vdd {
 	regulator-min-microvolt = <3300000>;
 	regulator-max-microvolt = <3300000>;
diff --git a/arch/arm64/boot/dts/qcom/msm8916-samsung-grandmax.dts b/arch/arm64/boot/dts/qcom/msm8916-samsung-grandmax.dts
index 3f145dde4059..5882b3a593b8 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-samsung-grandmax.dts
+++ b/arch/arm64/boot/dts/qcom/msm8916-samsung-grandmax.dts
@@ -49,6 +49,10 @@
 	status = "disabled";
 };
 
+&sound {
+	model = "samsung-gmax"; /* No secondary microphone */
+};
+
 &tlmm {
 	gpio_leds_default: gpio-led-default-state {
 		pins = "gpio60";
diff --git a/arch/arm64/boot/dts/qcom/msm8916-samsung-gt5-common.dtsi b/arch/arm64/boot/dts/qcom/msm8916-samsung-gt5-common.dtsi
index c19cf20d7427..fbd2caf405d5 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-samsung-gt5-common.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8916-samsung-gt5-common.dtsi
@@ -3,9 +3,12 @@
 /dts-v1/;
 
 #include "msm8916-pm8916.dtsi"
+#include "msm8916-modem-qdsp6.dtsi"
+
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/sound/apq8016-lpass.h>
 
 / {
 	aliases {
@@ -65,25 +68,6 @@
 	};
 };
 
-&blsp_i2c4 {
-	status = "okay";
-
-	fuelgauge@36 {
-		compatible = "maxim,max77849-battery";
-		reg = <0x36>;
-
-		maxim,rsns-microohm = <10000>;
-		maxim,over-heat-temp = <600>;
-		maxim,over-volt = <4400>;
-
-		interrupt-parent = <&tlmm>;
-		interrupts = <121 IRQ_TYPE_EDGE_FALLING>;
-
-		pinctrl-0 = <&fuelgauge_int_default>;
-		pinctrl-names = "default";
-	};
-};
-
 &blsp_i2c2 {
 	status = "okay";
 
@@ -112,10 +96,52 @@
 	};
 };
 
+&blsp_i2c4 {
+	status = "okay";
+
+	fuelgauge@36 {
+		compatible = "maxim,max77849-battery";
+		reg = <0x36>;
+
+		maxim,rsns-microohm = <10000>;
+		maxim,over-heat-temp = <600>;
+		maxim,over-volt = <4400>;
+
+		interrupt-parent = <&tlmm>;
+		interrupts = <121 IRQ_TYPE_EDGE_FALLING>;
+
+		pinctrl-0 = <&fuelgauge_int_default>;
+		pinctrl-names = "default";
+	};
+};
+
 &blsp_uart2 {
 	status = "okay";
 };
 
+/*
+ * For some reason the speaker amplifier is connected to the second SD line
+ * (MI2S_2_D1) instead of the first (MI2S_2_D0). This must be configured in the
+ * device tree, otherwise audio will seemingly play fine on the wrong SD line
+ * but the speaker stays silent.
+ *
+ * When routing audio via QDSP6 (the default) the &lpass node is reserved and
+ * the definitions from &q6afedai are used. When the modem is disabled audio can
+ * be alternatively routed directly to the LPASS hardware with reduced latency.
+ * The definitions for &lpass are here for completeness to simplify changing the
+ * setup with minor changes to the DT (either manually or with DT overlays).
+ */
+&lpass {
+	dai-link@3 {
+		reg = <MI2S_QUATERNARY>;
+		qcom,playback-sd-lines = <1>;
+	};
+};
+
+&mpss_mem {
+	reg = <0x0 0x86800000 0x0 0x5400000>;
+};
+
 &pm8916_resin {
 	linux,code = <KEY_VOLUMEDOWN>;
 	status = "okay";
@@ -133,6 +159,13 @@
 	status = "okay";
 };
 
+&q6afedai {
+	dai@22 {
+		reg = <QUATERNARY_MI2S_RX>;
+		qcom,sd-lines = <1>;
+	};
+};
+
 &sdhc_1 {
 	status = "okay";
 };
@@ -147,6 +180,27 @@
 	status = "okay";
 };
 
+&sound {
+	audio-routing =
+		"AMIC1", "MIC BIAS External1",
+		"AMIC2", "MIC BIAS Internal2",
+		"AMIC3", "MIC BIAS External1";
+
+	sound_link_backend2: backend2-dai-link {
+		link-name = "Quaternary MI2S";
+
+		cpu {
+			sound-dai = <&q6afedai QUATERNARY_MI2S_RX>;
+		};
+		platform {
+			sound-dai = <&q6routing>;
+		};
+		codec {
+			sound-dai = <&speaker_codec>;
+		};
+	};
+};
+
 &usb {
 	dr_mode = "peripheral";
 	extcon = <&pm8916_usbin>;
diff --git a/arch/arm64/boot/dts/qcom/msm8916-samsung-gt510.dts b/arch/arm64/boot/dts/qcom/msm8916-samsung-gt510.dts
index 75c4854ecd64..5b34529b816c 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-samsung-gt510.dts
+++ b/arch/arm64/boot/dts/qcom/msm8916-samsung-gt510.dts
@@ -9,6 +9,14 @@
 	compatible = "samsung,gt510", "qcom,msm8916";
 	chassis-type = "tablet";
 
+	speaker_codec: audio-codec {
+		compatible = "maxim,max98357a";
+		sdmode-gpios = <&tlmm 55 GPIO_ACTIVE_HIGH>;
+		#sound-dai-cells = <0>;
+		pinctrl-0 = <&audio_sdmode_default>;
+		pinctrl-names = "default";
+	};
+
 	clk_pwm: pwm {
 		compatible = "clk-pwm";
 		#pwm-cells = <2>;
@@ -112,6 +120,10 @@
 	};
 };
 
+&gpu {
+	status = "okay";
+};
+
 &mdss {
 	status = "okay";
 };
@@ -142,7 +154,21 @@
 	remote-endpoint = <&panel_in>;
 };
 
+&sound {
+	model = "samsung-gt510";
+	pinctrl-0 = <&cdc_pdm_default &sec_mi2s_default>;
+	pinctrl-1 = <&cdc_pdm_sleep &sec_mi2s_sleep>;
+	pinctrl-names = "default", "sleep";
+};
+
 &tlmm {
+	audio_sdmode_default: audio-sdmode-default-state {
+		pins = "gpio55";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
 	buckbooster_en_default: buckbooster-en-default-state {
 		pins = "gpio51";
 		function = "gpio";
diff --git a/arch/arm64/boot/dts/qcom/msm8916-samsung-gt58.dts b/arch/arm64/boot/dts/qcom/msm8916-samsung-gt58.dts
index 11359bcc27b3..579312ed53ce 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-samsung-gt58.dts
+++ b/arch/arm64/boot/dts/qcom/msm8916-samsung-gt58.dts
@@ -35,6 +35,26 @@
 		pinctrl-names = "default";
 	};
 
+	i2c-amplifier {
+		compatible = "i2c-gpio";
+		sda-gpios = <&tlmm 55 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+		scl-gpios = <&tlmm 56 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+
+		pinctrl-0 = <&amp_i2c_default>;
+		pinctrl-names = "default";
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		speaker_codec: audio-codec@34 {
+			compatible = "nxp,tfa9895";
+			reg = <0x34>;
+			vddd-supply = <&pm8916_l5>;
+			sound-name-prefix = "Speaker";
+			#sound-dai-cells = <0>;
+		};
+	};
+
 	vibrator {
 		compatible = "gpio-vibrator";
 		enable-gpios = <&tlmm 76 GPIO_ACTIVE_HIGH>;
@@ -64,6 +84,10 @@
 	};
 };
 
+&gpu {
+	status = "okay";
+};
+
 &mdss {
 	status = "okay";
 };
@@ -94,7 +118,21 @@
 	remote-endpoint = <&panel_in>;
 };
 
+&sound {
+	model = "samsung-a2015";
+	pinctrl-0 = <&cdc_pdm_default &sec_mi2s_default &secondary_mic_default>;
+	pinctrl-1 = <&cdc_pdm_sleep &sec_mi2s_sleep &secondary_mic_default>;
+	pinctrl-names = "default", "sleep";
+};
+
 &tlmm {
+	amp_i2c_default: amp-i2c-default-state {
+		pins = "gpio55", "gpio56";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
 	buckbooster_en_default: buckbooster-en-default-state {
 		pins = "gpio8";
 		function = "gpio";
@@ -123,6 +161,14 @@
 		bias-disable;
 	};
 
+	secondary_mic_default: secondary-mic-default-state {
+		pins = "gpio98";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+		output-high;
+	};
+
 	tsp_int_default: tsp-int-default-state {
 		pins = "gpio13";
 		function = "gpio";
diff --git a/arch/arm64/boot/dts/qcom/msm8916-samsung-j5-common.dtsi b/arch/arm64/boot/dts/qcom/msm8916-samsung-j5-common.dtsi
index fe59be3505fe..5ca2ada266f4 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-samsung-j5-common.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8916-samsung-j5-common.dtsi
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0-only
 
 #include "msm8916-pm8916.dtsi"
+#include "msm8916-modem-qdsp6.dtsi"
+
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/interrupt-controller/irq.h>
@@ -135,6 +137,10 @@
 	status = "okay";
 };
 
+&mpss_mem {
+	reg = <0x0 0x86800000 0x0 0x5800000>;
+};
+
 &pm8916_resin {
 	status = "okay";
 	linux,code = <KEY_VOLUMEDOWN>;
@@ -154,6 +160,14 @@
 	cd-gpios = <&tlmm 38 GPIO_ACTIVE_LOW>;
 };
 
+&sound {
+	model = "msm8916-1mic";
+	audio-routing =
+		"AMIC1", "MIC BIAS External1",
+		"AMIC2", "MIC BIAS Internal2",
+		"AMIC3", "MIC BIAS External1";
+};
+
 &usb {
 	extcon = <&muic>, <&muic>;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/qcom/msm8916-samsung-j5.dts b/arch/arm64/boot/dts/qcom/msm8916-samsung-j5.dts
index 58c2f5a70e78..ba8650971d6a 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-samsung-j5.dts
+++ b/arch/arm64/boot/dts/qcom/msm8916-samsung-j5.dts
@@ -19,6 +19,10 @@
 	status = "disabled";
 };
 
+&pm8916_codec {
+	qcom,micbias1-ext-cap;
+};
+
 &touchscreen {
 	/* FIXME: Missing sm5703-mfd driver to power up vdd-supply */
 };
diff --git a/arch/arm64/boot/dts/qcom/msm8916-samsung-serranove.dts b/arch/arm64/boot/dts/qcom/msm8916-samsung-serranove.dts
index 68da2a2d3077..5ce8f1350abc 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-samsung-serranove.dts
+++ b/arch/arm64/boot/dts/qcom/msm8916-samsung-serranove.dts
@@ -6,6 +6,8 @@
 /dts-v1/;
 
 #include "msm8916-pm8916.dtsi"
+#include "msm8916-modem-qdsp6.dtsi"
+
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/interrupt-controller/irq.h>
@@ -319,6 +321,10 @@
 	status = "okay";
 };
 
+&mpss_mem {
+	reg = <0x0 0x86800000 0x0 0x5a00000>;
+};
+
 &pm8916_resin {
 	status = "okay";
 	linux,code = <KEY_VOLUMEDOWN>;
@@ -350,6 +356,13 @@
 	no-1-8-v;
 };
 
+&sound {
+	audio-routing =
+		"AMIC1", "MIC BIAS External1",
+		"AMIC2", "MIC BIAS Internal2",
+		"AMIC3", "MIC BIAS External1";
+};
+
 &usb {
 	status = "okay";
 	extcon = <&muic>, <&muic>;
diff --git a/arch/arm64/boot/dts/qcom/msm8916-thwc-uf896.dts b/arch/arm64/boot/dts/qcom/msm8916-thwc-uf896.dts
index 6fe1850ba20e..f34997500891 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-thwc-uf896.dts
+++ b/arch/arm64/boot/dts/qcom/msm8916-thwc-uf896.dts
@@ -13,16 +13,16 @@
 	gpios = <&tlmm 35 GPIO_ACTIVE_LOW>;
 };
 
-&led_r {
-	gpios = <&tlmm 82 GPIO_ACTIVE_HIGH>;
+&led_b {
+	gpios = <&tlmm 81 GPIO_ACTIVE_HIGH>;
 };
 
 &led_g {
 	gpios = <&tlmm 83 GPIO_ACTIVE_HIGH>;
 };
 
-&led_b {
-	gpios = <&tlmm 81 GPIO_ACTIVE_HIGH>;
+&led_r {
+	gpios = <&tlmm 82 GPIO_ACTIVE_HIGH>;
 };
 
 &button_default {
diff --git a/arch/arm64/boot/dts/qcom/msm8916-thwc-ufi001c.dts b/arch/arm64/boot/dts/qcom/msm8916-thwc-ufi001c.dts
index 16d4a91022be..6cb3911ba1c9 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-thwc-ufi001c.dts
+++ b/arch/arm64/boot/dts/qcom/msm8916-thwc-ufi001c.dts
@@ -13,16 +13,16 @@
 	gpios = <&tlmm 37 GPIO_ACTIVE_HIGH>;
 };
 
-&led_r {
-	gpios = <&tlmm 22 GPIO_ACTIVE_HIGH>;
+&led_b {
+	gpios = <&tlmm 20 GPIO_ACTIVE_HIGH>;
 };
 
 &led_g {
 	gpios = <&tlmm 21 GPIO_ACTIVE_HIGH>;
 };
 
-&led_b {
-	gpios = <&tlmm 20 GPIO_ACTIVE_HIGH>;
+&led_r {
+	gpios = <&tlmm 22 GPIO_ACTIVE_HIGH>;
 };
 
 &mpss {
diff --git a/arch/arm64/boot/dts/qcom/msm8916-wingtech-wt88047.dts b/arch/arm64/boot/dts/qcom/msm8916-wingtech-wt88047.dts
index 419f35c1fc92..510b3b3c4e3c 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-wingtech-wt88047.dts
+++ b/arch/arm64/boot/dts/qcom/msm8916-wingtech-wt88047.dts
@@ -6,6 +6,8 @@
 /dts-v1/;
 
 #include "msm8916-pm8916.dtsi"
+#include "msm8916-modem-qdsp6.dtsi"
+
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/leds/common.h>
@@ -25,6 +27,28 @@
 		stdout-path = "serial0";
 	};
 
+	speaker_amp: audio-amplifier {
+		compatible = "simple-audio-amplifier";
+		enable-gpios = <&tlmm 117 GPIO_ACTIVE_HIGH>;
+		sound-name-prefix = "Speaker Amp";
+		pinctrl-0 = <&speaker_amp_default>;
+		pinctrl-names = "default";
+	};
+
+	/*
+	 * This seems to be actually an analog switch that either routes audio
+	 * to the headphone jack or nowhere. Given that we need to enable a GPIO
+	 * to get sound on headphones, modelling it as simple-audio-amplifier
+	 * works just fine.
+	 */
+	headphones_switch: audio-switch {
+		compatible = "simple-audio-amplifier";
+		enable-gpios = <&tlmm 8 GPIO_ACTIVE_HIGH>;
+		sound-name-prefix = "Headphones Switch";
+		pinctrl-0 = <&headphones_switch_default>;
+		pinctrl-names = "default";
+	};
+
 	flash-led-controller {
 		compatible = "ocs,ocp8110";
 		enable-gpios = <&tlmm 31 GPIO_ACTIVE_HIGH>;
@@ -118,6 +142,7 @@
 		#size-cells = <0>;
 
 		vcc-supply = <&pm8916_l16>;
+		vio-supply = <&pm8916_l5>;
 
 		led@0 {
 			reg = <0>;
@@ -146,6 +171,18 @@
 	status = "okay";
 };
 
+&mpss_mem {
+	reg = <0x0 0x86800000 0x0 0x5100000>;
+};
+
+&pm8916_codec {
+	qcom,micbias1-ext-cap;
+	qcom,micbias-lvl = <2800>;
+	qcom,mbhc-vthreshold-low = <75 100 120 180 500>;
+	qcom,mbhc-vthreshold-high = <75 100 120 180 500>;
+	qcom,hphl-jack-type-normally-open;
+};
+
 &pm8916_resin {
 	status = "okay";
 	linux,code = <KEY_VOLUMEDOWN>;
@@ -180,6 +217,30 @@
 	non-removable;
 };
 
+&sound {
+	/*
+	 * Provide widgets/pin-switches to allow enabling speaker and headphones
+	 * separately. Both are routed via the HPH_L/HPH_R pins of the codec.
+	 */
+	model = "wt88047";
+	widgets =
+		"Speaker", "Speaker",
+		"Headphone", "Headphones";
+	pin-switches = "Speaker", "Headphones";
+	audio-routing =
+		"Speaker", "Speaker Amp OUTL",
+		"Speaker", "Speaker Amp OUTR",
+		"Speaker Amp INL", "HPH_R",
+		"Speaker Amp INR", "HPH_R",
+		"Headphones", "Headphones Switch OUTL",
+		"Headphones", "Headphones Switch OUTR",
+		"Headphones Switch INL", "HPH_L",
+		"Headphones Switch INR", "HPH_R",
+		"AMIC1", "MIC BIAS External1",
+		"AMIC2", "MIC BIAS Internal2";
+	aux-devs = <&speaker_amp>, <&headphones_switch>;
+};
+
 &usb {
 	status = "okay";
 	extcon = <&usb_id>, <&usb_id>;
@@ -226,6 +287,13 @@
 		bias-pull-up;
 	};
 
+	headphones_switch_default: headphones-switch-default-state {
+		pins = "gpio8";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
 	imu_default: imu-default-state {
 		pins = "gpio115";
 		function = "gpio";
@@ -234,6 +302,13 @@
 		bias-disable;
 	};
 
+	speaker_amp_default: speaker-amp-default-state {
+		pins = "gpio117";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
 	touchscreen_default: touchscreen-default-state {
 		touchscreen-pins {
 			pins = "gpio13";
diff --git a/arch/arm64/boot/dts/qcom/msm8916-yiming-uz801v3.dts b/arch/arm64/boot/dts/qcom/msm8916-yiming-uz801v3.dts
index 5e6ba8c58bb5..a98efcfe78b7 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-yiming-uz801v3.dts
+++ b/arch/arm64/boot/dts/qcom/msm8916-yiming-uz801v3.dts
@@ -13,16 +13,16 @@
 	gpios = <&tlmm 23 GPIO_ACTIVE_LOW>;
 };
 
-&led_r {
-	gpios = <&tlmm 7 GPIO_ACTIVE_HIGH>;
+&led_b {
+	gpios = <&tlmm 6 GPIO_ACTIVE_HIGH>;
 };
 
 &led_g {
 	gpios = <&tlmm 8 GPIO_ACTIVE_HIGH>;
 };
 
-&led_b {
-	gpios = <&tlmm 6 GPIO_ACTIVE_HIGH>;
+&led_r {
+	gpios = <&tlmm 7 GPIO_ACTIVE_HIGH>;
 };
 
 &button_default {
diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi
index 4f799b536a92..7f8327b0dbdb 100644
--- a/arch/arm64/boot/dts/qcom/msm8916.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi
@@ -10,6 +10,7 @@
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/power/qcom-rpmpd.h>
 #include <dt-bindings/reset/qcom,gcc-msm8916.h>
+#include <dt-bindings/soc/qcom,apr.h>
 #include <dt-bindings/thermal/thermal.h>
 
 / {
@@ -1989,6 +1990,54 @@
 
 				label = "hexagon";
 
+				apr: apr {
+					compatible = "qcom,apr-v2";
+					qcom,smd-channels = "apr_audio_svc";
+					qcom,domain = <APR_DOMAIN_ADSP>;
+					#address-cells = <1>;
+					#size-cells = <0>;
+					status = "disabled";
+
+					q6core: service@3 {
+						compatible = "qcom,q6core";
+						reg = <APR_SVC_ADSP_CORE>;
+					};
+
+					q6afe: service@4 {
+						compatible = "qcom,q6afe";
+						reg = <APR_SVC_AFE>;
+
+						q6afedai: dais {
+							compatible = "qcom,q6afe-dais";
+							#address-cells = <1>;
+							#size-cells = <0>;
+							#sound-dai-cells = <1>;
+						};
+					};
+
+					q6asm: service@7 {
+						compatible = "qcom,q6asm";
+						reg = <APR_SVC_ASM>;
+
+						q6asmdai: dais {
+							compatible = "qcom,q6asm-dais";
+							#address-cells = <1>;
+							#size-cells = <0>;
+							#sound-dai-cells = <1>;
+						};
+					};
+
+					q6adm: service@8 {
+						compatible = "qcom,q6adm";
+						reg = <APR_SVC_ADM>;
+
+						q6routing: routing {
+							compatible = "qcom,q6adm-routing";
+							#sound-dai-cells = <0>;
+						};
+					};
+				};
+
 				fastrpc {
 					compatible = "qcom,fastrpc";
 					qcom,smd-channels = "fastrpcsmd-apps-dsp";
@@ -2106,6 +2155,7 @@
 			clock-names = "bam_clk";
 			#dma-cells = <1>;
 			qcom,ee = <0>;
+			qcom,controlled-remotely;
 		};
 
 		blsp_uart1: serial@78af000 {
diff --git a/arch/arm64/boot/dts/qcom/msm8939-huawei-kiwi.dts b/arch/arm64/boot/dts/qcom/msm8939-huawei-kiwi.dts
new file mode 100644
index 000000000000..3cec51891aed
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/msm8939-huawei-kiwi.dts
@@ -0,0 +1,242 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/dts-v1/;
+
+#include "msm8939-pm8916.dtsi"
+#include <dt-bindings/gpio/gpio.h>
+
+/ {
+	model = "Huawei Honor 5X / GR5 (2016)";
+	compatible = "huawei,kiwi", "qcom,msm8939";
+	chassis-type = "handset";
+
+	aliases {
+		mmc0 = &sdhc_1; /* SDC1 eMMC slot */
+		mmc1 = &sdhc_2; /* SDC2 SD card slot */
+		serial0 = &blsp_uart2;
+	};
+
+	chosen {
+		stdout-path = "serial0";
+	};
+
+	reserved-memory {
+		qseecom_mem: qseecom@84a00000 {
+			reg = <0x0 0x84a00000 0x0 0x1600000>;
+			no-map;
+		};
+	};
+
+	gpio-hall-sensor {
+		compatible = "gpio-keys";
+
+		pinctrl-0 = <&gpio_hall_sensor_default>;
+		pinctrl-names = "default";
+
+		label = "GPIO Hall Effect Sensor";
+
+		event-hall-sensor {
+			label = "Hall Effect Sensor";
+			gpios = <&tlmm 69 GPIO_ACTIVE_LOW>;
+			linux,input-type = <EV_SW>;
+			linux,code = <SW_LID>;
+			linux,can-disable;
+		};
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		pinctrl-0 = <&gpio_keys_default>;
+		pinctrl-names = "default";
+
+		label = "GPIO Buttons";
+
+		button-volume-up {
+			label = "Volume Up";
+			gpios = <&tlmm 107 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_VOLUMEUP>;
+		};
+	};
+
+	usb_id: usb-id {
+		compatible = "linux,extcon-usb-gpio";
+		id-gpios = <&tlmm 110 GPIO_ACTIVE_HIGH>;
+		pinctrl-0 = <&usb_id_default>;
+		pinctrl-names = "default";
+	};
+};
+
+&blsp_i2c2 {
+	status = "okay";
+
+	accelerometer@1e {
+		compatible = "kionix,kx023-1025";
+		reg = <0x1e>;
+
+		vdd-supply = <&pm8916_l17>;
+		vddio-supply = <&pm8916_l6>;
+		pinctrl-0 = <&accel_int_default>;
+		pinctrl-names = "default";
+		mount-matrix = "-1", "0", "0",
+			       "0", "1", "0",
+			       "0", "0", "1";
+	};
+
+	proximity@39 {
+		compatible = "avago,apds9930";
+		reg = <0x39>;
+
+		interrupt-parent = <&tlmm>;
+		interrupts = <113 IRQ_TYPE_EDGE_FALLING>;
+
+		vdd-supply = <&pm8916_l17>;
+		vddio-supply = <&pm8916_l6>;
+
+		led-max-microamp = <25000>;
+		amstaos,proximity-diodes = <0>;
+
+		pinctrl-0 = <&prox_irq_default>;
+		pinctrl-names = "default";
+	};
+};
+
+&blsp_i2c5 {
+	status = "okay";
+
+	touchscreen@1c {
+		compatible = "cypress,tt21000";
+
+		reg = <0x1c>;
+		interrupt-parent = <&tlmm>;
+		interrupts = <13 IRQ_TYPE_EDGE_FALLING>;
+
+		reset-gpios = <&tlmm 12 GPIO_ACTIVE_LOW>;
+
+		/*
+		 * NOTE: vdd is not directly supplied by pm8916_l16, it seems to be a
+		 * fixed regulator that is automatically enabled by pm8916_l16.
+		 */
+		vdd-supply = <&pm8916_l16>;
+		vddio-supply = <&pm8916_l16>;
+
+		pinctrl-0 = <&touchscreen_default>;
+		pinctrl-names = "default";
+	};
+};
+
+&blsp_uart2 {
+	status = "okay";
+};
+
+&pm8916_l8 {
+	regulator-min-microvolt = <2950000>;
+	regulator-max-microvolt = <2950000>;
+};
+
+&pm8916_resin {
+	linux,code = <KEY_VOLUMEDOWN>;
+	status = "okay";
+};
+
+&pm8916_rpm_regulators {
+	pm8916_l16: l16 {
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+	};
+
+	pm8916_l17: l17 {
+		regulator-min-microvolt = <2850000>;
+		regulator-max-microvolt = <2850000>;
+	};
+};
+
+&pm8916_vib {
+	status = "okay";
+};
+
+&sdhc_1 {
+	status = "okay";
+};
+
+&sdhc_2 {
+	pinctrl-0 = <&sdc2_default &sdc2_cd_default>;
+	pinctrl-1 = <&sdc2_sleep &sdc2_cd_default>;
+	pinctrl-names = "default", "sleep";
+
+	cd-gpios = <&tlmm 38 GPIO_ACTIVE_HIGH>;
+
+	status = "okay";
+};
+
+&usb {
+	extcon = <&usb_id>, <&usb_id>;
+	status = "okay";
+};
+
+&usb_hs_phy {
+	extcon = <&usb_id>;
+};
+
+&wcnss {
+	status = "okay";
+};
+
+&wcnss_iris {
+	compatible = "qcom,wcn3620";
+};
+
+&wcnss_mem {
+	status = "okay";
+};
+
+&tlmm {
+	accel_int_default: accel-int-default-state {
+		pins = "gpio115";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
+	gpio_hall_sensor_default: gpio-hall-sensor-default-state {
+		pins = "gpio69";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
+	gpio_keys_default: gpio-keys-default-state {
+		pins = "gpio107";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-pull-up;
+	};
+
+	prox_irq_default: prox-irq-default-state {
+		pins = "gpio113";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
+	sdc2_cd_default: sdc2-cd-default-state {
+		pins = "gpio38";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
+	touchscreen_default: touchscreen-default-state {
+		pins = "gpio12", "gpio13";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
+	usb_id_default: usb-id-default-state {
+		pins = "gpio110";
+		function = "gpio";
+		drive-strength = <8>;
+		bias-pull-up;
+	};
+};
diff --git a/arch/arm64/boot/dts/qcom/msm8939-longcheer-l9100.dts b/arch/arm64/boot/dts/qcom/msm8939-longcheer-l9100.dts
index 6802714fda3f..e3404c4455cf 100644
--- a/arch/arm64/boot/dts/qcom/msm8939-longcheer-l9100.dts
+++ b/arch/arm64/boot/dts/qcom/msm8939-longcheer-l9100.dts
@@ -8,6 +8,7 @@
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/leds/common.h>
+#include <dt-bindings/pinctrl/qcom,pmic-gpio.h>
 #include <dt-bindings/pinctrl/qcom,pmic-mpp.h>
 
 / {
@@ -120,6 +121,46 @@
 
 };
 
+&blsp_i2c2 {
+	status = "okay";
+
+	led-controller@30 {
+		compatible = "kinetic,ktd2026";
+		reg = <0x30>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		vin-supply = <&pm8916_l17>;
+		vio-supply = <&pm8916_l6>;
+
+		pinctrl-0 = <&status_led_default>;
+		pinctrl-names = "default";
+
+		multi-led {
+			color = <LED_COLOR_ID_RGB>;
+			function = LED_FUNCTION_STATUS;
+
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			led@0 {
+				reg = <0>;
+				color = <LED_COLOR_ID_RED>;
+			};
+
+			led@1 {
+				reg = <1>;
+				color = <LED_COLOR_ID_GREEN>;
+			};
+
+			led@2 {
+				reg = <2>;
+				color = <LED_COLOR_ID_BLUE>;
+			};
+		};
+	};
+};
+
 &blsp_i2c3 {
 	status = "okay";
 
@@ -139,6 +180,7 @@
 	light-sensor@23 {
 		compatible = "liteon,ltr559";
 		reg = <0x23>;
+		proximity-near-level = <75>;
 
 		vdd-supply = <&pm8916_l17>;
 		vddio-supply = <&pm8916_l5>;
@@ -184,6 +226,16 @@
 	status = "okay";
 };
 
+&pm8916_gpios {
+	status_led_default: status-led-default-state {
+		pins = "gpio3";
+		function = PMIC_GPIO_FUNC_NORMAL;
+		power-source = <PM8916_GPIO_VPH>;
+		bias-disable;
+		output-high;
+	};
+};
+
 &pm8916_mpps {
 	pwm_out: mpp4-state {
 		pins = "mpp4";
@@ -247,6 +299,10 @@
 	compatible = "qcom,wcn3620";
 };
 
+&wcnss_mem {
+	status = "okay";
+};
+
 &tlmm {
 	button_backlight_default: button-backlight-default-state {
 		pins = "gpio17";
diff --git a/arch/arm64/boot/dts/qcom/msm8939-samsung-a7.dts b/arch/arm64/boot/dts/qcom/msm8939-samsung-a7.dts
index fccd8fec8b8f..aa6c39482a2f 100644
--- a/arch/arm64/boot/dts/qcom/msm8939-samsung-a7.dts
+++ b/arch/arm64/boot/dts/qcom/msm8939-samsung-a7.dts
@@ -3,10 +3,12 @@
 /dts-v1/;
 
 #include "msm8939-pm8916.dtsi"
+#include "msm8916-modem-qdsp6.dtsi"
 
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/sound/apq8016-lpass.h>
 
 / {
 	model = "Samsung Galaxy A7 (2015)";
@@ -287,6 +289,18 @@
 	};
 };
 
+&blsp_i2c2 {
+	status = "okay";
+
+	speaker_codec: audio-codec@34 {
+		compatible = "nxp,tfa9895";
+		reg = <0x34>;
+		vddd-supply = <&pm8916_l5>;
+		sound-name-prefix = "Speaker";
+		#sound-dai-cells = <0>;
+	};
+};
+
 &blsp_i2c5 {
 	status = "okay";
 
@@ -309,6 +323,29 @@
 	status = "okay";
 };
 
+/*
+ * For some reason the speaker amplifier is connected to the second SD line
+ * (MI2S_2_D1) instead of the first (MI2S_2_D0). This must be configured in the
+ * device tree, otherwise audio will seemingly play fine on the wrong SD line
+ * but the speaker stays silent.
+ *
+ * When routing audio via QDSP6 (the default) the &lpass node is reserved and
+ * the definitions from &q6afedai are used. When the modem is disabled audio can
+ * be alternatively routed directly to the LPASS hardware with reduced latency.
+ * The definitions for &lpass are here for completeness to simplify changing the
+ * setup with minor changes to the DT (either manually or with DT overlays).
+ */
+&lpass {
+	dai-link@3 {
+		reg = <MI2S_QUATERNARY>;
+		qcom,playback-sd-lines = <1>;
+	};
+};
+
+&mpss_mem {
+	reg = <0x0 0x86800000 0x0 0x5800000>;
+};
+
 &pm8916_resin {
 	linux,code = <KEY_VOLUMEDOWN>;
 	status = "okay";
@@ -321,6 +358,13 @@
 	};
 };
 
+&q6afedai {
+	dai@22 {
+		reg = <QUATERNARY_MI2S_RX>;
+		qcom,sd-lines = <1>;
+	};
+};
+
 &sdhc_1 {
 	status = "okay";
 };
@@ -335,6 +379,32 @@
 	status = "okay";
 };
 
+&sound {
+	model = "samsung-a2015";
+	audio-routing =
+		"AMIC1", "MIC BIAS External1",
+		"AMIC2", "MIC BIAS Internal2",
+		"AMIC3", "MIC BIAS External1";
+
+	pinctrl-0 = <&cdc_pdm_default &sec_mi2s_default>;
+	pinctrl-1 = <&cdc_pdm_sleep &sec_mi2s_sleep>;
+	pinctrl-names = "default", "sleep";
+
+	sound_link_backend2: backend2-dai-link {
+		link-name = "Quaternary MI2S";
+
+		cpu {
+			sound-dai = <&q6afedai QUATERNARY_MI2S_RX>;
+		};
+		platform {
+			sound-dai = <&q6routing>;
+		};
+		codec {
+			sound-dai = <&speaker_codec>;
+		};
+	};
+};
+
 &usb {
 	extcon = <&muic>, <&muic>;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/qcom/msm8939.dtsi b/arch/arm64/boot/dts/qcom/msm8939.dtsi
index 324b5d26db40..29f6bd9df2eb 100644
--- a/arch/arm64/boot/dts/qcom/msm8939.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8939.dtsi
@@ -10,6 +10,7 @@
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/power/qcom-rpmpd.h>
 #include <dt-bindings/reset/qcom,gcc-msm8939.h>
+#include <dt-bindings/soc/qcom,apr.h>
 #include <dt-bindings/thermal/thermal.h>
 
 / {
@@ -1537,6 +1538,20 @@
 			#interrupt-cells = <4>;
 		};
 
+		bam_dmux_dma: dma-controller@4044000 {
+			compatible = "qcom,bam-v1.7.0";
+			reg = <0x04044000 0x19000>;
+			interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
+			#dma-cells = <1>;
+			qcom,ee = <0>;
+
+			num-channels = <6>;
+			qcom,num-ees = <1>;
+			qcom,powered-remotely;
+
+			status = "disabled";
+		};
+
 		mpss: remoteproc@4080000 {
 			compatible = "qcom,msm8916-mss-pil";
 			reg = <0x04080000 0x100>, <0x04020000 0x040>;
@@ -1569,6 +1584,22 @@
 			qcom,halt-regs = <&tcsr 0x18000 0x19000 0x1a000>;
 			status = "disabled";
 
+			bam_dmux: bam-dmux {
+				compatible = "qcom,bam-dmux";
+
+				interrupt-parent = <&hexagon_smsm>;
+				interrupts = <1 IRQ_TYPE_EDGE_BOTH>, <11 IRQ_TYPE_EDGE_BOTH>;
+				interrupt-names = "pc", "pc-ack";
+
+				qcom,smem-states = <&apps_smsm 1>, <&apps_smsm 11>;
+				qcom,smem-state-names = "pc", "pc-ack";
+
+				dmas = <&bam_dmux_dma 4>, <&bam_dmux_dma 5>;
+				dma-names = "tx", "rx";
+
+				status = "disabled";
+			};
+
 			mba {
 				memory-region = <&mba_mem>;
 			};
@@ -1585,6 +1616,54 @@
 				qcom,remote-pid = <1>;
 
 				label = "hexagon";
+
+				apr: apr {
+					compatible = "qcom,apr-v2";
+					qcom,smd-channels = "apr_audio_svc";
+					qcom,domain = <APR_DOMAIN_ADSP>;
+					#address-cells = <1>;
+					#size-cells = <0>;
+					status = "disabled";
+
+					q6core: service@3 {
+						compatible = "qcom,q6core";
+						reg = <APR_SVC_ADSP_CORE>;
+					};
+
+					q6afe: service@4 {
+						compatible = "qcom,q6afe";
+						reg = <APR_SVC_AFE>;
+
+						q6afedai: dais {
+							compatible = "qcom,q6afe-dais";
+							#address-cells = <1>;
+							#size-cells = <0>;
+							#sound-dai-cells = <1>;
+						};
+					};
+
+					q6asm: service@7 {
+						compatible = "qcom,q6asm";
+						reg = <APR_SVC_ASM>;
+
+						q6asmdai: dais {
+							compatible = "qcom,q6asm-dais";
+							#address-cells = <1>;
+							#size-cells = <0>;
+							#sound-dai-cells = <1>;
+						};
+					};
+
+					q6adm: service@8 {
+						compatible = "qcom,q6adm";
+						reg = <APR_SVC_ADM>;
+
+						q6routing: routing {
+							compatible = "qcom,q6adm-routing";
+							#sound-dai-cells = <0>;
+						};
+					};
+				};
 			};
 		};
 
@@ -1682,6 +1761,7 @@
 			clock-names = "bam_clk";
 			#dma-cells = <1>;
 			qcom,ee = <0>;
+			qcom,controlled-remotely;
 		};
 
 		blsp_uart1: serial@78af000 {
@@ -2116,6 +2196,8 @@
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges;
+			/* Necessary because firmware does not configure this correctly */
+			clock-frequency = <19200000>;
 
 			frame@b121000 {
 				reg = <0x0b121000 0x1000>,
diff --git a/arch/arm64/boot/dts/qcom/msm8953-xiaomi-mido.dts b/arch/arm64/boot/dts/qcom/msm8953-xiaomi-mido.dts
index ed95d09cedb1..6b9245cd8b0c 100644
--- a/arch/arm64/boot/dts/qcom/msm8953-xiaomi-mido.dts
+++ b/arch/arm64/boot/dts/qcom/msm8953-xiaomi-mido.dts
@@ -111,6 +111,7 @@
 		reg = <0x45>;
 
 		vcc-supply = <&pm8953_l10>;
+		vio-supply = <&pm8953_l5>;
 
 		#address-cells = <1>;
 		#size-cells = <0>;
diff --git a/arch/arm64/boot/dts/qcom/msm8953-xiaomi-tissot.dts b/arch/arm64/boot/dts/qcom/msm8953-xiaomi-tissot.dts
index 61ff629c9bf3..9ac4f507e321 100644
--- a/arch/arm64/boot/dts/qcom/msm8953-xiaomi-tissot.dts
+++ b/arch/arm64/boot/dts/qcom/msm8953-xiaomi-tissot.dts
@@ -104,6 +104,7 @@
 		reg = <0x45>;
 
 		vcc-supply = <&pm8953_l10>;
+		vio-supply = <&pm8953_l5>;
 
 		#address-cells = <1>;
 		#size-cells = <0>;
diff --git a/arch/arm64/boot/dts/qcom/msm8953-xiaomi-vince.dts b/arch/arm64/boot/dts/qcom/msm8953-xiaomi-vince.dts
index 1a1d3f92a511..b0588f30f8f1 100644
--- a/arch/arm64/boot/dts/qcom/msm8953-xiaomi-vince.dts
+++ b/arch/arm64/boot/dts/qcom/msm8953-xiaomi-vince.dts
@@ -113,6 +113,7 @@
 		reg = <0x45>;
 
 		vcc-supply = <&pm8953_l10>;
+		vio-supply = <&pm8953_l5>;
 
 		#address-cells = <1>;
 		#size-cells = <0>;
diff --git a/arch/arm64/boot/dts/qcom/msm8953.dtsi b/arch/arm64/boot/dts/qcom/msm8953.dtsi
index e7de7632669a..ad2f8cf9c966 100644
--- a/arch/arm64/boot/dts/qcom/msm8953.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8953.dtsi
@@ -174,10 +174,10 @@
 		};
 	};
 
-	memory {
+	memory@10000000 {
 		device_type = "memory";
 		/* We expect the bootloader to fill in the reg */
-		reg = <0 0 0 0>;
+		reg = <0 0x10000000 0 0>;
 	};
 
 	pmu {
@@ -726,6 +726,48 @@
 				bias-disable;
 			};
 
+			spi_3_default: spi-3-default-state {
+				pins = "gpio10", "gpio11";
+				function = "blsp_spi3";
+				drive-strength = <2>;
+				bias-disable;
+			};
+
+			spi_3_sleep: spi-3-sleep-state {
+				pins = "gpio10", "gpio11";
+				function = "gpio";
+				drive-strength = <2>;
+				bias-disable;
+			};
+
+			spi_5_default: spi-5-default-state {
+				pins = "gpio18", "gpio19";
+				function = "blsp_spi5";
+				drive-strength = <2>;
+				bias-disable;
+			};
+
+			spi_5_sleep: spi-5-sleep-state {
+				pins = "gpio18", "gpio19";
+				function = "gpio";
+				drive-strength = <2>;
+				bias-disable;
+			};
+
+			spi_6_default: spi-6-default-state {
+				pins = "gpio22", "gpio23";
+				function = "blsp_spi6";
+				drive-strength = <2>;
+				bias-disable;
+			};
+
+			spi_6_sleep: spi-6-sleep-state {
+				pins = "gpio22", "gpio23";
+				function = "gpio";
+				drive-strength = <2>;
+				bias-disable;
+			};
+
 			wcnss_pin_a: wcnss-active-state {
 
 				wcss-wlan2-pins {
@@ -1004,7 +1046,7 @@
 
 		apps_iommu: iommu@1e20000 {
 			compatible = "qcom,msm8953-iommu", "qcom,msm-iommu-v1";
-			ranges  = <0 0x01e20000 0x20000>;
+			ranges = <0 0x01e20000 0x20000>;
 
 			clocks = <&gcc GCC_SMMU_CFG_CLK>,
 				 <&gcc GCC_APSS_TCU_ASYNC_CLK>;
@@ -1360,6 +1402,26 @@
 			status = "disabled";
 		};
 
+		spi_3: spi@78b7000 {
+			compatible = "qcom,spi-qup-v2.2.1";
+			reg = <0x078b7000 0x600>;
+			interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>;
+			clock-names = "core", "iface";
+			clocks = <&gcc GCC_BLSP1_QUP3_I2C_APPS_CLK>,
+				 <&gcc GCC_BLSP1_AHB_CLK>;
+			dmas = <&blsp1_dma 8>, <&blsp1_dma 9>;
+			dma-names = "tx", "rx";
+
+			pinctrl-names = "default", "sleep";
+			pinctrl-0 = <&spi_3_default>;
+			pinctrl-1 = <&spi_3_sleep>;
+
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			status = "disabled";
+		};
+
 		i2c_4: i2c@78b8000 {
 			compatible = "qcom,i2c-qup-v2.2.1";
 			reg = <0x078b8000 0x600>;
@@ -1413,6 +1475,26 @@
 			status = "disabled";
 		};
 
+		spi_5: spi@7af5000 {
+			compatible = "qcom,spi-qup-v2.2.1";
+			reg = <0x07af5000 0x600>;
+			interrupts = <GIC_SPI 299 IRQ_TYPE_LEVEL_HIGH>;
+			clock-names = "core", "iface";
+			clocks = <&gcc GCC_BLSP2_QUP1_I2C_APPS_CLK>,
+				<&gcc GCC_BLSP2_AHB_CLK>;
+			dmas = <&blsp2_dma 4>, <&blsp2_dma 5>;
+			dma-names = "tx", "rx";
+
+			pinctrl-names = "default", "sleep";
+			pinctrl-0 = <&spi_5_default>;
+			pinctrl-1 = <&spi_5_sleep>;
+
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			status = "disabled";
+		};
+
 		i2c_6: i2c@7af6000 {
 			compatible = "qcom,i2c-qup-v2.2.1";
 			reg = <0x07af6000 0x600>;
@@ -1433,6 +1515,26 @@
 			status = "disabled";
 		};
 
+		spi_6: spi@7af6000 {
+			compatible = "qcom,spi-qup-v2.2.1";
+			reg = <0x07af6000 0x600>;
+			interrupts = <GIC_SPI 300 IRQ_TYPE_LEVEL_HIGH>;
+			clock-names = "core", "iface";
+			clocks = <&gcc GCC_BLSP2_QUP2_I2C_APPS_CLK>,
+				 <&gcc GCC_BLSP2_AHB_CLK>;
+			dmas = <&blsp2_dma 6>, <&blsp2_dma 7>;
+			dma-names = "tx", "rx";
+
+			pinctrl-names = "default", "sleep";
+			pinctrl-0 = <&spi_6_default>;
+			pinctrl-1 = <&spi_6_sleep>;
+
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			status = "disabled";
+		};
+
 		i2c_7: i2c@7af7000 {
 			compatible = "qcom,i2c-qup-v2.2.1";
 			reg = <0x07af7000 0x600>;
@@ -1645,7 +1747,7 @@
 				apr {
 					compatible = "qcom,apr-v2";
 					qcom,smd-channels = "apr_audio_svc";
-					qcom,apr-domain = <APR_DOMAIN_ADSP>;
+					qcom,domain = <APR_DOMAIN_ADSP>;
 					#address-cells = <1>;
 					#size-cells = <0>;
 
diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi
index 6ba9da9e6a8b..8c6a7efa90c4 100644
--- a/arch/arm64/boot/dts/qcom/msm8996.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi
@@ -444,6 +444,38 @@
 		reg = <0x0 0x80000000 0x0 0x0>;
 	};
 
+	etm {
+		compatible = "qcom,coresight-remote-etm";
+
+		out-ports {
+			port {
+				modem_etm_out_funnel_in2: endpoint {
+					remote-endpoint =
+					  <&funnel_in2_in_modem_etm>;
+				};
+			};
+		};
+	};
+
+	mpm: interrupt-controller {
+		compatible = "qcom,mpm";
+		qcom,rpm-msg-ram = <&apss_mpm>;
+		interrupts = <GIC_SPI 171 IRQ_TYPE_EDGE_RISING>;
+		mboxes = <&apcs_glb 1>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		#power-domain-cells = <0>;
+		interrupt-parent = <&intc>;
+		qcom,mpm-pin-count = <96>;
+		qcom,mpm-pin-map = <2 184>,  /* TSENS1 upper_lower_int */
+				   <52 243>, /* DWC3_PRI ss_phy_irq */
+				   <79 347>, /* DWC3_PRI hs_phy_irq */
+				   <80 352>, /* DWC3_SEC hs_phy_irq */
+				   <81 347>, /* QUSB2_PHY_PRI DP+DM */
+				   <82 352>, /* QUSB2_PHY_SEC DP+DM */
+				   <87 326>; /* SPMI */
+	};
+
 	psci {
 		compatible = "arm,psci-1.0";
 		method = "smc";
@@ -733,8 +765,15 @@
 		};
 
 		rpm_msg_ram: sram@68000 {
-			compatible = "qcom,rpm-msg-ram";
+			compatible = "qcom,rpm-msg-ram", "mmio-sram";
 			reg = <0x00068000 0x6000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0x00068000 0x7000>;
+
+			apss_mpm: sram@1b8 {
+				reg = <0x1b8 0x48>;
+			};
 		};
 
 		qfprom@74000 {
@@ -779,10 +818,10 @@
 				 <&pciephy_0>,
 				 <&pciephy_1>,
 				 <&pciephy_2>,
-				 <&ssusb_phy_0>,
-				 <&ufsphy_lane 0>,
-				 <&ufsphy_lane 1>,
-				 <&ufsphy_lane 2>;
+				 <&usb3phy>,
+				 <&ufsphy 0>,
+				 <&ufsphy 1>,
+				 <&ufsphy 2>;
 			clock-names = "cxo",
 				      "cxo2",
 				      "sleep_clk",
@@ -820,8 +859,8 @@
 			reg = <0x004ad000 0x1000>, /* TM */
 			      <0x004ac000 0x1000>; /* SROT */
 			#qcom,sensors = <8>;
-			interrupts = <GIC_SPI 184 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 430 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts-extended = <&mpm 2 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 430 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "uplow", "critical";
 			#thermal-sensor-cells = <1>;
 		};
@@ -1343,6 +1382,7 @@
 			interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
 			gpio-controller;
 			gpio-ranges = <&tlmm 0 0 150>;
+			wakeup-parent = <&mpm>;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -1870,7 +1910,7 @@
 			      <0x0400a000 0x002100>;
 			reg-names = "core", "chnls", "obsrvr", "intr", "cnfg";
 			interrupt-names = "periph_irq";
-			interrupts = <GIC_SPI 326 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts-extended = <&mpm 87 IRQ_TYPE_LEVEL_HIGH>;
 			qcom,ee = <0>;
 			qcom,channel = <0>;
 			#address-cells = <2>;
@@ -2047,7 +2087,7 @@
 			reg = <0x00624000 0x2500>;
 			interrupts = <GIC_SPI 265 IRQ_TYPE_LEVEL_HIGH>;
 
-			phys = <&ufsphy_lane>;
+			phys = <&ufsphy>;
 			phy-names = "ufsphy";
 
 			power-domains = <&gcc UFS_GDSC>;
@@ -2100,25 +2140,18 @@
 
 		ufsphy: phy@627000 {
 			compatible = "qcom,msm8996-qmp-ufs-phy";
-			reg = <0x00627000 0x1c4>;
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges;
+			reg = <0x00627000 0x1000>;
 
 			clocks = <&gcc GCC_UFS_CLKREF_CLK>;
 			clock-names = "ref";
 
 			resets = <&ufshc 0>;
 			reset-names = "ufsphy";
-			status = "disabled";
 
-			ufsphy_lane: phy@627400 {
-				reg = <0x627400 0x12c>,
-				      <0x627600 0x200>,
-				      <0x627c00 0x1b4>;
-				#clock-cells = <1>;
-				#phy-cells = <0>;
-			};
+			#clock-cells = <1>;
+			#phy-cells = <0>;
+
+			status = "disabled";
 		};
 
 		camss: camss@a34000 {
@@ -2644,6 +2677,14 @@
 			clocks = <&rpmcc RPM_QDSS_CLK>, <&rpmcc RPM_QDSS_A_CLK>;
 			clock-names = "apb_pclk", "atclk";
 
+			in-ports {
+				port {
+					funnel_in2_in_modem_etm: endpoint {
+						remote-endpoint =
+						  <&modem_etm_out_funnel_in2>;
+					};
+				};
+			};
 
 			out-ports {
 				port {
@@ -3026,8 +3067,8 @@
 			#size-cells = <1>;
 			ranges;
 
-			interrupts = <GIC_SPI 347 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 243 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts-extended = <&mpm 79 IRQ_TYPE_LEVEL_HIGH>,
+					      <&mpm 52 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "hs_phy_irq", "ss_phy_irq";
 
 			clocks = <&gcc GCC_SYS_NOC_USB3_AXI_CLK>,
@@ -3056,7 +3097,7 @@
 				compatible = "snps,dwc3";
 				reg = <0x06a00000 0xcc00>;
 				interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>;
-				phys = <&hsusb_phy1>, <&ssusb_phy_0>;
+				phys = <&hsusb_phy1>, <&usb3phy>;
 				phy-names = "usb2-phy", "usb3-phy";
 				snps,hird-threshold = /bits/ 8 <0>;
 				snps,dis_u2_susphy_quirk;
@@ -3068,32 +3109,26 @@
 
 		usb3phy: phy@7410000 {
 			compatible = "qcom,msm8996-qmp-usb3-phy";
-			reg = <0x07410000 0x1c4>;
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges;
+			reg = <0x07410000 0x1000>;
 
 			clocks = <&gcc GCC_USB3_PHY_AUX_CLK>,
-				<&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>,
-				<&gcc GCC_USB3_CLKREF_CLK>;
-			clock-names = "aux", "cfg_ahb", "ref";
+				 <&gcc GCC_USB3_CLKREF_CLK>,
+				 <&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>,
+				 <&gcc GCC_USB3_PHY_PIPE_CLK>;
+			clock-names = "aux",
+				      "ref",
+				      "cfg_ahb",
+				      "pipe";
+			clock-output-names = "usb3_phy_pipe_clk_src";
+			#clock-cells = <0>;
+			#phy-cells = <0>;
 
 			resets = <&gcc GCC_USB3_PHY_BCR>,
-				<&gcc GCC_USB3PHY_PHY_BCR>;
-			reset-names = "phy", "common";
-			status = "disabled";
-
-			ssusb_phy_0: phy@7410200 {
-				reg = <0x07410200 0x200>,
-				      <0x07410400 0x130>,
-				      <0x07410600 0x1a8>;
-				#phy-cells = <0>;
+				 <&gcc GCC_USB3PHY_PHY_BCR>;
+			reset-names = "phy",
+				      "phy_phy";
 
-				#clock-cells = <0>;
-				clock-output-names = "usb3_phy_pipe_clk_src";
-				clocks = <&gcc GCC_USB3_PHY_PIPE_CLK>;
-				clock-names = "pipe0";
-			};
+			status = "disabled";
 		};
 
 		hsusb_phy1: phy@7411000 {
diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi
index b485bf925ce6..bb591c6bf573 100644
--- a/arch/arm64/boot/dts/qcom/msm8998.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi
@@ -933,7 +933,7 @@
 				<GIC_SPI 465 IRQ_TYPE_EDGE_RISING>;
 		};
 
-		pcie0: pci@1c00000 {
+		pcie0: pcie@1c00000 {
 			compatible = "qcom,pcie-msm8998", "qcom,pcie-msm8996";
 			reg = <0x01c00000 0x2000>,
 			      <0x1b000000 0xf1d>,
@@ -1004,7 +1004,7 @@
 			compatible = "qcom,msm8998-ufshc", "qcom,ufshc", "jedec,ufs-2.0";
 			reg = <0x01da4000 0x2500>;
 			interrupts = <GIC_SPI 265 IRQ_TYPE_LEVEL_HIGH>;
-			phys = <&ufsphy_lanes>;
+			phys = <&ufsphy>;
 			phy-names = "ufsphy";
 			lanes-per-direction = <2>;
 			power-domains = <&gcc UFS_GDSC>;
@@ -1045,11 +1045,7 @@
 
 		ufsphy: phy@1da7000 {
 			compatible = "qcom,msm8998-qmp-ufs-phy";
-			reg = <0x01da7000 0x18c>;
-			#address-cells = <1>;
-			#size-cells = <1>;
-			status = "disabled";
-			ranges;
+			reg = <0x01da7000 0x1000>;
 
 			clock-names =
 				"ref",
@@ -1061,14 +1057,8 @@
 			reset-names = "ufsphy";
 			resets = <&ufshc 0>;
 
-			ufsphy_lanes: phy@1da7400 {
-				reg = <0x01da7400 0x128>,
-				      <0x01da7600 0x1fc>,
-				      <0x01da7c00 0x1dc>,
-				      <0x01da7800 0x128>,
-				      <0x01da7a00 0x1fc>;
-				#phy-cells = <0>;
-			};
+			#phy-cells = <0>;
+			status = "disabled";
 		};
 
 		tcsr_mutex: hwlock@1f40000 {
@@ -2031,9 +2021,11 @@
 
 			cpu = <&CPU4>;
 
-			port {
-				etm4_out: endpoint {
-					remote-endpoint = <&apss_funnel_in4>;
+			out-ports {
+				port {
+					etm4_out: endpoint {
+						remote-endpoint = <&apss_funnel_in4>;
+					};
 				};
 			};
 		};
@@ -2048,9 +2040,11 @@
 
 			cpu = <&CPU5>;
 
-			port {
-				etm5_out: endpoint {
-					remote-endpoint = <&apss_funnel_in5>;
+			out-ports {
+				port {
+					etm5_out: endpoint {
+						remote-endpoint = <&apss_funnel_in5>;
+					};
 				};
 			};
 		};
@@ -2065,9 +2059,11 @@
 
 			cpu = <&CPU6>;
 
-			port {
-				etm6_out: endpoint {
-					remote-endpoint = <&apss_funnel_in6>;
+			out-ports {
+				port {
+					etm6_out: endpoint {
+						remote-endpoint = <&apss_funnel_in6>;
+					};
 				};
 			};
 		};
@@ -2082,9 +2078,11 @@
 
 			cpu = <&CPU7>;
 
-			port {
-				etm7_out: endpoint {
-					remote-endpoint = <&apss_funnel_in7>;
+			out-ports {
+				port {
+					etm7_out: endpoint {
+						remote-endpoint = <&apss_funnel_in7>;
+					};
 				};
 			};
 		};
@@ -2149,7 +2147,7 @@
 				interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>;
 				snps,dis_u2_susphy_quirk;
 				snps,dis_enblslpm_quirk;
-				phys = <&qusb2phy>, <&usb1_ssphy>;
+				phys = <&qusb2phy>, <&usb3phy>;
 				phy-names = "usb2-phy", "usb3-phy";
 				snps,has-lpm-erratum;
 				snps,hird-threshold = /bits/ 8 <0x10>;
@@ -2158,33 +2156,26 @@
 
 		usb3phy: phy@c010000 {
 			compatible = "qcom,msm8998-qmp-usb3-phy";
-			reg = <0x0c010000 0x18c>;
-			status = "disabled";
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges;
+			reg = <0x0c010000 0x1000>;
 
 			clocks = <&gcc GCC_USB3_PHY_AUX_CLK>,
+				 <&gcc GCC_USB3_CLKREF_CLK>,
 				 <&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>,
-				 <&gcc GCC_USB3_CLKREF_CLK>;
-			clock-names = "aux", "cfg_ahb", "ref";
+				 <&gcc GCC_USB3_PHY_PIPE_CLK>;
+			clock-names = "aux",
+				      "ref",
+				      "cfg_ahb",
+				      "pipe";
+			clock-output-names = "usb3_phy_pipe_clk_src";
+			#clock-cells = <0>;
+			#phy-cells = <0>;
 
 			resets = <&gcc GCC_USB3_PHY_BCR>,
 				 <&gcc GCC_USB3PHY_PHY_BCR>;
-			reset-names = "phy", "common";
+			reset-names = "phy",
+				      "phy_phy";
 
-			usb1_ssphy: phy@c010200 {
-				reg = <0xc010200 0x128>,
-				      <0xc010400 0x200>,
-				      <0xc010c00 0x20c>,
-				      <0xc010600 0x128>,
-				      <0xc010800 0x200>;
-				#phy-cells = <0>;
-				#clock-cells = <0>;
-				clocks = <&gcc GCC_USB3_PHY_PIPE_CLK>;
-				clock-names = "pipe0";
-				clock-output-names = "usb3_phy_pipe_clk_src";
-			};
+			status = "disabled";
 		};
 
 		qusb2phy: phy@c012000 {
diff --git a/arch/arm64/boot/dts/qcom/pm7250b.dtsi b/arch/arm64/boot/dts/qcom/pm7250b.dtsi
index df0afe82f250..3bf7cf5d1700 100644
--- a/arch/arm64/boot/dts/qcom/pm7250b.dtsi
+++ b/arch/arm64/boot/dts/qcom/pm7250b.dtsi
@@ -148,7 +148,7 @@
 			status = "disabled";
 		};
 
-		pm7250b_gpios: pinctrl@c000 {
+		pm7250b_gpios: gpio@c000 {
 			compatible = "qcom,pm7250b-gpio", "qcom,spmi-gpio";
 			reg = <0xc000>;
 			gpio-controller;
diff --git a/arch/arm64/boot/dts/qcom/pm8550.dtsi b/arch/arm64/boot/dts/qcom/pm8550.dtsi
index db3d5c17a77d..797a18c249a4 100644
--- a/arch/arm64/boot/dts/qcom/pm8550.dtsi
+++ b/arch/arm64/boot/dts/qcom/pm8550.dtsi
@@ -64,9 +64,6 @@
 
 		pm8550_pwm: pwm {
 			compatible = "qcom,pm8550-pwm", "qcom,pm8350c-pwm";
-
-			#address-cells = <1>;
-			#size-cells = <0>;
 			#pwm-cells = <2>;
 
 			status = "disabled";
diff --git a/arch/arm64/boot/dts/qcom/pm8550ve.dtsi b/arch/arm64/boot/dts/qcom/pm8550ve.dtsi
index c47646a467be..4dc1f03ab2c7 100644
--- a/arch/arm64/boot/dts/qcom/pm8550ve.dtsi
+++ b/arch/arm64/boot/dts/qcom/pm8550ve.dtsi
@@ -33,16 +33,16 @@
 
 
 &spmi_bus {
-	pm8550ve: pmic@5 {
+	pm8550ve: pmic@PMK8550VE_SID {
 		compatible = "qcom,pm8550", "qcom,spmi-pmic";
-		reg = <0x5 SPMI_USID>;
+		reg = <PMK8550VE_SID SPMI_USID>;
 		#address-cells = <1>;
 		#size-cells = <0>;
 
 		pm8550ve_temp_alarm: temp-alarm@a00 {
 			compatible = "qcom,spmi-temp-alarm";
 			reg = <0xa00>;
-			interrupts = <0x5 0xa 0x0 IRQ_TYPE_EDGE_BOTH>;
+			interrupts = <PMK8550VE_SID 0xa 0x0 IRQ_TYPE_EDGE_BOTH>;
 			#thermal-sensor-cells = <0>;
 		};
 
diff --git a/arch/arm64/boot/dts/qcom/pm8916.dtsi b/arch/arm64/boot/dts/qcom/pm8916.dtsi
index f4de86787743..4b2e8fb47d2d 100644
--- a/arch/arm64/boot/dts/qcom/pm8916.dtsi
+++ b/arch/arm64/boot/dts/qcom/pm8916.dtsi
@@ -41,6 +41,35 @@
 			};
 		};
 
+		pm8916_charger: charger@1000 {
+			compatible = "qcom,pm8916-lbc";
+			reg = <0x1000>, <0x1200>, <0x1300>, <0x1600>;
+			reg-names = "chgr", "bat_if", "usb", "misc";
+
+			interrupts = <0x0 0x10 0 IRQ_TYPE_EDGE_BOTH>,
+				     <0x0 0x10 5 IRQ_TYPE_EDGE_BOTH>,
+				     <0x0 0x10 6 IRQ_TYPE_EDGE_BOTH>,
+				     <0x0 0x10 7 IRQ_TYPE_EDGE_BOTH>,
+				     <0x0 0x12 0 IRQ_TYPE_EDGE_BOTH>,
+				     <0x0 0x12 1 IRQ_TYPE_EDGE_BOTH>,
+				     <0x0 0x13 0 IRQ_TYPE_EDGE_BOTH>,
+				     <0x0 0x13 1 IRQ_TYPE_EDGE_BOTH>,
+				     <0x0 0x13 2 IRQ_TYPE_EDGE_BOTH>,
+				     <0x0 0x13 4 IRQ_TYPE_EDGE_BOTH>;
+			interrupt-names = "vbat_det",
+					  "fast_chg",
+					  "chg_fail",
+					  "chg_done",
+					  "bat_pres",
+					  "temp_ok",
+					  "coarse_det",
+					  "usb_vbus",
+					  "chg_gone",
+					  "overtemp";
+
+			status = "disabled";
+		};
+
 		pm8916_usbin: usb-detect@1300 {
 			compatible = "qcom,pm8941-misc";
 			reg = <0x1300>;
@@ -91,6 +120,25 @@
 			};
 		};
 
+		pm8916_bms: battery@4000 {
+			compatible = "qcom,pm8916-bms-vm";
+			reg = <0x4000>;
+			interrupts = <0x0 0x40 0 IRQ_TYPE_EDGE_RISING>,
+				     <0x0 0x40 1 IRQ_TYPE_EDGE_RISING>,
+				     <0x0 0x40 2 IRQ_TYPE_EDGE_RISING>,
+				     <0x0 0x40 3 IRQ_TYPE_EDGE_RISING>,
+				     <0x0 0x40 4 IRQ_TYPE_EDGE_RISING>,
+				     <0x0 0x40 5 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "cv_leave",
+					  "cv_enter",
+					  "ocv_good",
+					  "ocv_thr",
+					  "fifo",
+					  "state_chg";
+
+			status = "disabled";
+		};
+
 		rtc@6000 {
 			compatible = "qcom,pm8941-rtc";
 			reg = <0x6000>, <0x6100>;
diff --git a/arch/arm64/boot/dts/qcom/pmk8350.dtsi b/arch/arm64/boot/dts/qcom/pmk8350.dtsi
index 1eb74017062d..f0ed15458dd7 100644
--- a/arch/arm64/boot/dts/qcom/pmk8350.dtsi
+++ b/arch/arm64/boot/dts/qcom/pmk8350.dtsi
@@ -22,7 +22,7 @@
 		mode-bootloader = <0x02>;
 	};
 };
-	
+
 &spmi_bus {
 	pmk8350: pmic@PMK8350_SID {
 		compatible = "qcom,pmk8350", "qcom,spmi-pmic";
diff --git a/arch/arm64/boot/dts/qcom/qcm2290.dtsi b/arch/arm64/boot/dts/qcom/qcm2290.dtsi
index d46e591e72b5..0911fb08ed63 100644
--- a/arch/arm64/boot/dts/qcom/qcm2290.dtsi
+++ b/arch/arm64/boot/dts/qcom/qcm2290.dtsi
@@ -5,12 +5,15 @@
  * Based on sm6115.dtsi and previous efforts by Shawn Guo & Loic Poulain.
  */
 
+#include <dt-bindings/clock/qcom,dispcc-qcm2290.h>
 #include <dt-bindings/clock/qcom,gcc-qcm2290.h>
 #include <dt-bindings/clock/qcom,rpmcc.h>
 #include <dt-bindings/dma/qcom-gpi.h>
 #include <dt-bindings/firmware/qcom,scm.h>
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/interconnect/qcom,qcm2290.h>
+#include <dt-bindings/interconnect/qcom,rpm-icc.h>
 #include <dt-bindings/power/qcom-rpmpd.h>
 
 / {
@@ -150,6 +153,8 @@
 			clocks = <&rpmcc RPM_SMD_CE1_CLK>;
 			clock-names = "core";
 			#reset-cells = <1>;
+			interconnects = <&system_noc MASTER_CRYPTO_CORE0 RPM_ALWAYS_TAG
+					 &bimc SLAVE_EBI1 RPM_ALWAYS_TAG>;
 		};
 	};
 
@@ -194,6 +199,7 @@
 
 		CLUSTER_PD: power-domain-cpu-cluster {
 			#power-domain-cells = <0>;
+			power-domains = <&mpm>;
 			domain-idle-states = <&CLUSTER_SLEEP>;
 		};
 	};
@@ -261,6 +267,24 @@
 				};
 			};
 		};
+
+		mpm: interrupt-controller {
+			compatible = "qcom,mpm";
+			qcom,rpm-msg-ram = <&apss_mpm>;
+			interrupts = <GIC_SPI 197 IRQ_TYPE_EDGE_RISING>;
+			mboxes = <&apcs_glb 1>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			#power-domain-cells = <0>;
+			interrupt-parent = <&intc>;
+			qcom,mpm-pin-count = <96>;
+			qcom,mpm-pin-map = <2 275>,  /* TSENS0 uplow */
+					   <5 296>,  /* Soundwire master_irq */
+					   <12 422>, /* DWC3 ss_phy_irq */
+					   <24 79>,  /* Soundwire wake_irq */
+					   <86 183>, /* MPM wake, SPMI */
+					   <90 260>; /* QUSB2_PHY DP+DM */
+		};
 	};
 
 	reserved_memory: reserved-memory {
@@ -424,6 +448,7 @@
 			interrupts = <GIC_SPI 227 IRQ_TYPE_LEVEL_HIGH>;
 			gpio-controller;
 			gpio-ranges = <&tlmm 0 0 127>;
+			wakeup-parent = <&mpm>;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -668,6 +693,33 @@
 			status = "disabled";
 		};
 
+		system_noc: interconnect@1880000 {
+			compatible = "qcom,qcm2290-snoc";
+			reg = <0x0 0x01880000 0x0 0x60200>;
+			#interconnect-cells = <2>;
+
+			qup_virt: interconnect-qup {
+				compatible = "qcom,qcm2290-qup-virt";
+				#interconnect-cells = <2>;
+			};
+
+			mmnrt_virt: interconnect-mmnrt {
+				compatible = "qcom,qcm2290-mmnrt-virt";
+				#interconnect-cells = <2>;
+			};
+
+			mmrt_virt: interconnect-mmrt {
+				compatible = "qcom,qcm2290-mmrt-virt";
+				#interconnect-cells = <2>;
+			};
+		};
+
+		config_noc: interconnect@1900000 {
+			compatible = "qcom,qcm2290-cnoc";
+			reg = <0x0 0x01900000 0x0 0x8200>;
+			#interconnect-cells = <2>;
+		};
+
 		qfprom@1b44000 {
 			compatible = "qcom,qcm2290-qfprom", "qcom,qfprom";
 			reg = <0x0 0x01b44000 0x0 0x3000>;
@@ -680,6 +732,60 @@
 			};
 		};
 
+		pmu@1b8e300 {
+			compatible = "qcom,qcm2290-cpu-bwmon", "qcom,sdm845-bwmon";
+			reg = <0x0 0x01b8e300 0x0 0x600>;
+			interrupts = <GIC_SPI 421 IRQ_TYPE_LEVEL_HIGH>;
+
+			operating-points-v2 = <&cpu_bwmon_opp_table>;
+			interconnects = <&bimc MASTER_APPSS_PROC RPM_ACTIVE_TAG
+					 &bimc SLAVE_EBI1 RPM_ACTIVE_TAG>;
+
+			cpu_bwmon_opp_table: opp-table {
+				compatible = "operating-points-v2";
+
+				opp-0 {
+					opp-peak-kBps = <(200 * 4 * 1000)>;
+				};
+
+				opp-1 {
+					opp-peak-kBps = <(300 * 4 * 1000)>;
+				};
+
+				opp-2 {
+					opp-peak-kBps = <(451 * 4 * 1000)>;
+				};
+
+				opp-3 {
+					opp-peak-kBps = <(547 * 4 * 1000)>;
+				};
+
+				opp-4 {
+					opp-peak-kBps = <(681 * 4 * 1000)>;
+				};
+
+				opp-5 {
+					opp-peak-kBps = <(768 * 4 * 1000)>;
+				};
+
+				opp-6 {
+					opp-peak-kBps = <(1017 * 4 * 1000)>;
+				};
+
+				opp-7 {
+					opp-peak-kBps = <(1353 * 4 * 1000)>;
+				};
+
+				opp-8 {
+					opp-peak-kBps = <(1555 * 4 * 1000)>;
+				};
+
+				opp-9 {
+					opp-peak-kBps = <(1804 * 4 * 1000)>;
+				};
+			};
+		};
+
 		spmi_bus: spmi@1c40000 {
 			compatible = "qcom,spmi-pmic-arb";
 			reg = <0x0 0x01c40000 0x0 0x1100>,
@@ -692,7 +798,7 @@
 				    "obsrvr",
 				    "intr",
 				    "cnfg";
-			interrupts = <GIC_SPI 183 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts-extended = <&mpm 86 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "periph_irq";
 			qcom,ee = <0>;
 			qcom,channel = <0>;
@@ -707,8 +813,8 @@
 			reg = <0x0 0x04411000 0x0 0x1ff>,
 			      <0x0 0x04410000 0x0 0x8>;
 			#qcom,sensors = <10>;
-			interrupts = <GIC_SPI 275 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 190 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts-extended = <&mpm 2 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 190 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "uplow", "critical";
 			#thermal-sensor-cells = <1>;
 		};
@@ -720,9 +826,22 @@
 			clock-names = "core";
 		};
 
+		bimc: interconnect@4480000 {
+			compatible = "qcom,qcm2290-bimc";
+			reg = <0x0 0x04480000 0x0 0x80000>;
+			#interconnect-cells = <2>;
+		};
+
 		rpm_msg_ram: sram@45f0000 {
-			compatible = "qcom,rpm-msg-ram";
+			compatible = "qcom,rpm-msg-ram", "mmio-sram";
 			reg = <0x0 0x045f0000 0x0 0x7000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0x0 0x045f0000 0x7000>;
+
+			apss_mpm: sram@1b8 {
+				reg = <0x1b8 0x48>;
+			};
 		};
 
 		sram@4690000 {
@@ -755,13 +874,45 @@
 			resets = <&gcc GCC_SDCC1_BCR>;
 
 			power-domains = <&rpmpd QCM2290_VDDCX>;
+			operating-points-v2 = <&sdhc1_opp_table>;
 			iommus = <&apps_smmu 0xc0 0x0>;
+			interconnects = <&system_noc MASTER_SDCC_1 RPM_ALWAYS_TAG
+					 &bimc SLAVE_EBI1 RPM_ALWAYS_TAG>,
+					<&bimc MASTER_APPSS_PROC RPM_ALWAYS_TAG
+					 &config_noc SLAVE_SDCC_1 RPM_ALWAYS_TAG>;
+			interconnect-names = "sdhc-ddr",
+					     "cpu-sdhc";
 
 			qcom,dll-config = <0x000f642c>;
 			qcom,ddr-config = <0x80040868>;
 			bus-width = <8>;
 
 			status = "disabled";
+
+			sdhc1_opp_table: opp-table {
+				compatible = "operating-points-v2";
+
+				opp-100000000 {
+					opp-hz = /bits/ 64 <100000000>;
+					required-opps = <&rpmpd_opp_low_svs>;
+					opp-peak-kBps = <250000 133320>;
+					opp-avg-kBps = <102400 65000>;
+				};
+
+				opp-192000000 {
+					opp-hz = /bits/ 64 <192000000>;
+					required-opps = <&rpmpd_opp_low_svs>;
+					opp-peak-kBps = <800000 300000>;
+					opp-avg-kBps = <204800 200000>;
+				};
+
+				opp-384000000 {
+					opp-hz = /bits/ 64 <384000000>;
+					required-opps = <&rpmpd_opp_svs_plus>;
+					opp-peak-kBps = <800000 300000>;
+					opp-avg-kBps = <204800 200000>;
+				};
+			};
 		};
 
 		sdhc_2: mmc@4784000 {
@@ -785,6 +936,12 @@
 			power-domains = <&rpmpd QCM2290_VDDCX>;
 			operating-points-v2 = <&sdhc2_opp_table>;
 			iommus = <&apps_smmu 0xa0 0x0>;
+			interconnects = <&system_noc MASTER_SDCC_2 RPM_ALWAYS_TAG
+					 &bimc SLAVE_EBI1 RPM_ALWAYS_TAG>,
+					<&bimc MASTER_APPSS_PROC RPM_ALWAYS_TAG
+					 &config_noc SLAVE_SDCC_2 RPM_ALWAYS_TAG>;
+			interconnect-names = "sdhc-ddr",
+					     "cpu-sdhc";
 
 			qcom,dll-config = <0x0007642c>;
 			qcom,ddr-config = <0x80040868>;
@@ -798,11 +955,15 @@
 				opp-100000000 {
 					opp-hz = /bits/ 64 <100000000>;
 					required-opps = <&rpmpd_opp_low_svs>;
+					opp-peak-kBps = <250000 133320>;
+					opp-avg-kBps = <261438 150000>;
 				};
 
 				opp-202000000 {
 					opp-hz = /bits/ 64 <202000000>;
 					required-opps = <&rpmpd_opp_svs_plus>;
+					opp-peak-kBps = <800000 300000>;
+					opp-avg-kBps = <261438 300000>;
 				};
 			};
 		};
@@ -850,6 +1011,15 @@
 				dmas = <&gpi_dma0 0 0 QCOM_GPI_I2C>,
 				       <&gpi_dma0 1 0 QCOM_GPI_I2C>;
 				dma-names = "tx", "rx";
+				interconnects = <&qup_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &qup_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_APPSS_PROC RPM_ALWAYS_TAG
+						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>,
+						<&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG
+						 &bimc SLAVE_EBI1 RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -866,6 +1036,12 @@
 				dmas = <&gpi_dma0 0 0 QCOM_GPI_SPI>,
 				       <&gpi_dma0 1 0 QCOM_GPI_SPI>;
 				dma-names = "tx", "rx";
+				interconnects = <&qup_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &qup_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_APPSS_PROC RPM_ALWAYS_TAG
+						 &config_noc MASTER_APPSS_PROC RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -879,6 +1055,12 @@
 				clock-names = "se";
 				pinctrl-0 = <&qup_uart0_default>;
 				pinctrl-names = "default";
+				interconnects = <&qup_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &qup_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_APPSS_PROC RPM_ALWAYS_TAG
+						 &config_noc MASTER_APPSS_PROC RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config";
 				status = "disabled";
 			};
 
@@ -893,6 +1075,15 @@
 				dmas = <&gpi_dma0 0 1 QCOM_GPI_I2C>,
 				       <&gpi_dma0 1 1 QCOM_GPI_I2C>;
 				dma-names = "tx", "rx";
+				interconnects = <&qup_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &qup_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_APPSS_PROC RPM_ALWAYS_TAG
+						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>,
+						<&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG
+						 &bimc SLAVE_EBI1 RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -909,6 +1100,12 @@
 				dmas = <&gpi_dma0 0 1 QCOM_GPI_SPI>,
 				       <&gpi_dma0 1 1 QCOM_GPI_SPI>;
 				dma-names = "tx", "rx";
+				interconnects = <&qup_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &qup_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_APPSS_PROC RPM_ALWAYS_TAG
+						 &config_noc MASTER_APPSS_PROC RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -925,6 +1122,15 @@
 				dmas = <&gpi_dma0 0 2 QCOM_GPI_I2C>,
 				       <&gpi_dma0 1 2 QCOM_GPI_I2C>;
 				dma-names = "tx", "rx";
+				interconnects = <&qup_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &qup_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_APPSS_PROC RPM_ALWAYS_TAG
+						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>,
+						<&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG
+						 &bimc SLAVE_EBI1 RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -941,6 +1147,12 @@
 				dmas = <&gpi_dma0 0 2 QCOM_GPI_SPI>,
 				       <&gpi_dma0 1 2 QCOM_GPI_SPI>;
 				dma-names = "tx", "rx";
+				interconnects = <&qup_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &qup_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_APPSS_PROC RPM_ALWAYS_TAG
+						 &config_noc MASTER_APPSS_PROC RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -957,6 +1169,15 @@
 				dmas = <&gpi_dma0 0 3 QCOM_GPI_I2C>,
 				       <&gpi_dma0 1 3 QCOM_GPI_I2C>;
 				dma-names = "tx", "rx";
+				interconnects = <&qup_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &qup_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_APPSS_PROC RPM_ALWAYS_TAG
+						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>,
+						<&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG
+						 &bimc SLAVE_EBI1 RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -973,6 +1194,12 @@
 				dmas = <&gpi_dma0 0 3 QCOM_GPI_SPI>,
 				       <&gpi_dma0 1 3 QCOM_GPI_SPI>;
 				dma-names = "tx", "rx";
+				interconnects = <&qup_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &qup_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_APPSS_PROC RPM_ALWAYS_TAG
+						 &config_noc MASTER_APPSS_PROC RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -989,6 +1216,15 @@
 				dmas = <&gpi_dma0 0 4 QCOM_GPI_I2C>,
 				       <&gpi_dma0 1 4 QCOM_GPI_I2C>;
 				dma-names = "tx", "rx";
+				interconnects = <&qup_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &qup_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_APPSS_PROC RPM_ALWAYS_TAG
+						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>,
+						<&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG
+						 &bimc SLAVE_EBI1 RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -1005,6 +1241,12 @@
 				dmas = <&gpi_dma0 0 4 QCOM_GPI_SPI>,
 				       <&gpi_dma0 1 4 QCOM_GPI_SPI>;
 				dma-names = "tx", "rx";
+				interconnects = <&qup_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &qup_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_APPSS_PROC RPM_ALWAYS_TAG
+						 &config_noc MASTER_APPSS_PROC RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -1018,6 +1260,12 @@
 				clock-names = "se";
 				pinctrl-0 = <&qup_uart4_default>;
 				pinctrl-names = "default";
+				interconnects = <&qup_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &qup_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_APPSS_PROC RPM_ALWAYS_TAG
+						 &config_noc MASTER_APPSS_PROC RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config";
 				status = "disabled";
 			};
 
@@ -1032,6 +1280,15 @@
 				dmas = <&gpi_dma0 0 5 QCOM_GPI_I2C>,
 				       <&gpi_dma0 1 5 QCOM_GPI_I2C>;
 				dma-names = "tx", "rx";
+				interconnects = <&qup_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &qup_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_APPSS_PROC RPM_ALWAYS_TAG
+						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>,
+						<&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG
+						 &bimc SLAVE_EBI1 RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -1048,6 +1305,12 @@
 				dmas = <&gpi_dma0 0 5 QCOM_GPI_SPI>,
 				       <&gpi_dma0 1 5 QCOM_GPI_SPI>;
 				dma-names = "tx", "rx";
+				interconnects = <&qup_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &qup_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_APPSS_PROC RPM_ALWAYS_TAG
+						 &config_noc MASTER_APPSS_PROC RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -1057,9 +1320,10 @@
 		usb: usb@4ef8800 {
 			compatible = "qcom,qcm2290-dwc3", "qcom,dwc3";
 			reg = <0x0 0x04ef8800 0x0 0x400>;
-			interrupts = <GIC_SPI 260 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 422 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "hs_phy_irq", "ss_phy_irq";
+			interrupts-extended = <&intc GIC_SPI 260 IRQ_TYPE_LEVEL_HIGH>,
+					      <&mpm 12 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "hs_phy_irq",
+					  "ss_phy_irq";
 
 			clocks = <&gcc GCC_CFG_NOC_USB3_PRIM_AXI_CLK>,
 				 <&gcc GCC_USB30_PRIM_MASTER_CLK>,
@@ -1080,6 +1344,13 @@
 
 			resets = <&gcc GCC_USB30_PRIM_BCR>;
 			power-domains = <&gcc GCC_USB30_PRIM_GDSC>;
+			/* TODO: USB<->IPA path */
+			interconnects = <&system_noc MASTER_USB3_0 RPM_ALWAYS_TAG
+					 &bimc SLAVE_EBI1 RPM_ALWAYS_TAG>,
+					<&bimc MASTER_APPSS_PROC RPM_ALWAYS_TAG
+					 &config_noc SLAVE_USB3 RPM_ALWAYS_TAG>;
+			interconnect-names = "usb-ddr",
+					     "apps-usb";
 			wakeup-source;
 
 			#address-cells = <2>;
@@ -1105,6 +1376,225 @@
 			};
 		};
 
+		mdss: display-subsystem@5e00000 {
+			compatible = "qcom,qcm2290-mdss";
+			reg = <0x0 0x05e00000 0x0 0x1000>;
+			reg-names = "mdss";
+			interrupts = <GIC_SPI 186 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+
+			clocks = <&gcc GCC_DISP_AHB_CLK>,
+				 <&gcc GCC_DISP_HF_AXI_CLK>,
+				 <&dispcc DISP_CC_MDSS_MDP_CLK>;
+			clock-names = "iface",
+				      "bus",
+				      "core";
+
+			resets = <&dispcc DISP_CC_MDSS_CORE_BCR>;
+
+			power-domains = <&dispcc MDSS_GDSC>;
+
+			iommus = <&apps_smmu 0x420 0x2>,
+				 <&apps_smmu 0x421 0x0>;
+			interconnects = <&mmrt_virt MASTER_MDP0 RPM_ALWAYS_TAG
+					 &bimc SLAVE_EBI1 RPM_ALWAYS_TAG>,
+					<&bimc MASTER_APPSS_PROC RPM_ALWAYS_TAG
+					 &config_noc SLAVE_DISPLAY_CFG RPM_ALWAYS_TAG>;
+			interconnect-names = "mdp0-mem",
+					     "cpu-cfg";
+
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+
+			status = "disabled";
+
+			mdp: display-controller@5e01000 {
+				compatible = "qcom,qcm2290-dpu";
+				reg = <0x0 0x05e01000 0x0 0x8f000>,
+				      <0x0 0x05eb0000 0x0 0x2008>;
+				reg-names = "mdp",
+					    "vbif";
+
+				interrupt-parent = <&mdss>;
+				interrupts = <0>;
+
+				clocks = <&gcc GCC_DISP_HF_AXI_CLK>,
+					 <&dispcc DISP_CC_MDSS_AHB_CLK>,
+					 <&dispcc DISP_CC_MDSS_MDP_CLK>,
+					 <&dispcc DISP_CC_MDSS_MDP_LUT_CLK>,
+					 <&dispcc DISP_CC_MDSS_VSYNC_CLK>;
+				clock-names = "bus",
+					      "iface",
+					      "core",
+					      "lut",
+					      "vsync";
+
+				operating-points-v2 = <&mdp_opp_table>;
+				power-domains = <&rpmpd QCM2290_VDDCX>;
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+						dpu_intf1_out: endpoint {
+							remote-endpoint = <&mdss_dsi0_in>;
+						};
+					};
+				};
+
+				mdp_opp_table: opp-table {
+					compatible = "operating-points-v2";
+
+					opp-19200000 {
+						opp-hz = /bits/ 64 <19200000>;
+						required-opps = <&rpmpd_opp_min_svs>;
+					};
+
+					opp-192000000 {
+						opp-hz = /bits/ 64 <192000000>;
+						required-opps = <&rpmpd_opp_low_svs>;
+					};
+
+					opp-256000000 {
+						opp-hz = /bits/ 64 <256000000>;
+						required-opps = <&rpmpd_opp_svs>;
+					};
+
+					opp-307200000 {
+						opp-hz = /bits/ 64 <307200000>;
+						required-opps = <&rpmpd_opp_svs_plus>;
+					};
+
+					opp-384000000 {
+						opp-hz = /bits/ 64 <384000000>;
+						required-opps = <&rpmpd_opp_nom>;
+					};
+				};
+			};
+
+			mdss_dsi0: dsi@5e94000 {
+				compatible = "qcom,qcm2290-dsi-ctrl", "qcom,mdss-dsi-ctrl";
+				reg = <0x0 0x05e94000 0x0 0x400>;
+				reg-names = "dsi_ctrl";
+
+				interrupt-parent = <&mdss>;
+				interrupts = <4>;
+
+				clocks = <&dispcc DISP_CC_MDSS_BYTE0_CLK>,
+					 <&dispcc DISP_CC_MDSS_BYTE0_INTF_CLK>,
+					 <&dispcc DISP_CC_MDSS_PCLK0_CLK>,
+					 <&dispcc DISP_CC_MDSS_ESC0_CLK>,
+					 <&dispcc DISP_CC_MDSS_AHB_CLK>,
+					 <&gcc GCC_DISP_HF_AXI_CLK>;
+				clock-names = "byte",
+					      "byte_intf",
+					      "pixel",
+					      "core",
+					      "iface",
+					      "bus";
+
+				assigned-clocks = <&dispcc DISP_CC_MDSS_BYTE0_CLK_SRC>,
+						  <&dispcc DISP_CC_MDSS_PCLK0_CLK_SRC>;
+				assigned-clock-parents = <&mdss_dsi0_phy 0>,
+							 <&mdss_dsi0_phy 1>;
+
+				operating-points-v2 = <&dsi_opp_table>;
+				power-domains = <&rpmpd QCM2290_VDDCX>;
+				phys = <&mdss_dsi0_phy>;
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+
+				dsi_opp_table: opp-table {
+					compatible = "operating-points-v2";
+
+					opp-19200000 {
+						opp-hz = /bits/ 64 <19200000>;
+						required-opps = <&rpmpd_opp_min_svs>;
+					};
+
+					opp-164000000 {
+						opp-hz = /bits/ 64 <164000000>;
+						required-opps = <&rpmpd_opp_low_svs>;
+					};
+
+					opp-187500000 {
+						opp-hz = /bits/ 64 <187500000>;
+						required-opps = <&rpmpd_opp_svs>;
+					};
+				};
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+
+						mdss_dsi0_in: endpoint {
+							remote-endpoint = <&dpu_intf1_out>;
+						};
+					};
+
+					port@1 {
+						reg = <1>;
+
+						mdss_dsi0_out: endpoint {
+						};
+					};
+				};
+			};
+
+			mdss_dsi0_phy: phy@5e94400 {
+				compatible = "qcom,dsi-phy-14nm-2290";
+				reg = <0x0 0x05e94400 0x0 0x100>,
+				      <0x0 0x05e94500 0x0 0x300>,
+				      <0x0 0x05e94800 0x0 0x188>;
+				reg-names = "dsi_phy",
+					    "dsi_phy_lane",
+					    "dsi_pll";
+
+				clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
+					 <&rpmcc RPM_SMD_XO_CLK_SRC>;
+				clock-names = "iface",
+					      "ref";
+
+				power-domains = <&rpmpd QCM2290_VDDMX>;
+				required-opps = <&rpmpd_opp_nom>;
+
+				#clock-cells = <1>;
+				#phy-cells = <0>;
+
+				status = "disabled";
+			};
+		};
+
+		dispcc: clock-controller@5f00000 {
+			compatible = "qcom,qcm2290-dispcc";
+			reg = <0x0 0x05f00000 0x0 0x20000>;
+			clocks = <&rpmcc RPM_SMD_XO_CLK_SRC>,
+				 <&rpmcc RPM_SMD_XO_A_CLK_SRC>,
+				 <&gcc GCC_DISP_GPLL0_CLK_SRC>,
+				 <&gcc GCC_DISP_GPLL0_DIV_CLK_SRC>,
+				 <&mdss_dsi0_phy 0>,
+				 <&mdss_dsi0_phy 1>;
+			clock-names = "bi_tcxo",
+				      "bi_tcxo_ao",
+				      "gcc_disp_gpll0_clk_src",
+				      "gcc_disp_gpll0_div_clk_src",
+				      "dsi0_phy_pll_out_byteclk",
+				      "dsi0_phy_pll_out_dsiclk";
+			#power-domain-cells = <1>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+		};
+
 		remoteproc_mpss: remoteproc@6080000 {
 			compatible = "qcom,qcm2290-mpss-pas", "qcom,sm6115-mpss-pas";
 			reg = <0x0 0x06080000 0x0 0x100>;
diff --git a/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts b/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts
index 2de0b8c26c35..176898c9dbbd 100644
--- a/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts
+++ b/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts
@@ -9,6 +9,8 @@
 #define PM7250B_SID 8
 #define PM7250B_SID1 9
 
+#include <dt-bindings/iio/qcom,spmi-adc7-pm7325.h>
+#include <dt-bindings/iio/qcom,spmi-adc7-pmk8350.h>
 #include <dt-bindings/leds/common.h>
 #include <dt-bindings/pinctrl/qcom,pmic-gpio.h>
 #include <dt-bindings/regulator/qcom,rpmh-regulator.h>
@@ -75,26 +77,11 @@
 			no-map;
 		};
 
-		adsp_mem: adsp@86700000 {
-			reg = <0x0 0x86700000 0x0 0x2800000>;
-			no-map;
-		};
-
 		cdsp_mem: cdsp@88f00000 {
 			reg = <0x0 0x88f00000 0x0 0x1e00000>;
 			no-map;
 		};
 
-		mpss_mem: mpss@8b800000 {
-			reg = <0x0 0x8b800000 0x0 0xf600000>;
-			no-map;
-		};
-
-		wpss_mem: wpss@9ae00000 {
-			reg = <0x0 0x9ae00000 0x0 0x1900000>;
-			no-map;
-		};
-
 		rmtfs_mem: memory@f8500000 {
 			compatible = "qcom,rmtfs-mem";
 			reg = <0x0 0xf8500000 0x0 0x600000>;
@@ -134,6 +121,106 @@
 		enable-active-high;
 		vin-supply = <&vreg_bob>;
 	};
+
+	thermal-zones {
+		camera-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&pmk8350_adc_tm 2>;
+
+			trips {
+				active-config0 {
+					temperature = <125000>;
+					hysteresis = <1000>;
+					type = "passive";
+				};
+			};
+		};
+
+		chg-skin-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&pm7250b_adc_tm 0>;
+
+			trips {
+				active-config0 {
+					temperature = <125000>;
+					hysteresis = <1000>;
+					type = "passive";
+				};
+			};
+		};
+
+		conn-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&pm7250b_adc_tm 1>;
+
+			trips {
+				active-config0 {
+					temperature = <125000>;
+					hysteresis = <1000>;
+					type = "passive";
+				};
+			};
+		};
+
+		quiet-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&pmk8350_adc_tm 1>;
+
+			trips {
+				active-config0 {
+					temperature = <125000>;
+					hysteresis = <1000>;
+					type = "passive";
+				};
+			};
+		};
+
+		rear-cam-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&pmk8350_adc_tm 4>;
+
+			trips {
+				active-config0 {
+					temperature = <125000>;
+					hysteresis = <1000>;
+					type = "passive";
+				};
+			};
+		};
+
+		sdm-skin-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&pmk8350_adc_tm 3>;
+
+			trips {
+				active-config0 {
+					temperature = <125000>;
+					hysteresis = <1000>;
+					type = "passive";
+				};
+			};
+		};
+
+		xo-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&pmk8350_adc_tm 0>;
+
+			trips {
+				active-config0 {
+					temperature = <125000>;
+					hysteresis = <1000>;
+					type = "passive";
+				};
+			};
+		};
+	};
 };
 
 &apps_rsc {
@@ -182,8 +269,9 @@
 		};
 
 		vreg_l7b: ldo7 {
-			regulator-min-microvolt = <2400000>;
-			regulator-max-microvolt = <3544000>;
+			/* Constrained for UFS VCC, at least until UFS driver scales voltage */
+			regulator-min-microvolt = <2952000>;
+			regulator-max-microvolt = <2952000>;
 			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
 		};
 
@@ -425,6 +513,42 @@
 	status = "okay";
 };
 
+&pm7250b_adc {
+	channel@4d {
+		reg = <ADC5_AMUX_THM1_100K_PU>;
+		qcom,ratiometric;
+		qcom,hw-settle-time = <200>;
+		qcom,pre-scaling = <1 1>;
+		label = "charger_skin_therm";
+	};
+
+	channel@4f {
+		reg = <ADC5_AMUX_THM3_100K_PU>;
+		qcom,ratiometric;
+		qcom,hw-settle-time = <200>;
+		qcom,pre-scaling = <1 1>;
+		label = "conn_therm";
+	};
+};
+
+&pm7250b_adc_tm {
+	status = "okay";
+
+	charger-skin-therm@0 {
+		reg = <0>;
+		io-channels = <&pm7250b_adc ADC5_AMUX_THM1_100K_PU>;
+		qcom,ratiometric;
+		qcom,hw-settle-time-us = <200>;
+	};
+
+	conn-therm@1 {
+		reg = <1>;
+		io-channels = <&pm7250b_adc ADC5_AMUX_THM3_100K_PU>;
+		qcom,ratiometric;
+		qcom,hw-settle-time-us = <200>;
+	};
+};
+
 &pm7325_gpios {
 	volume_down_default: volume-down-default-state {
 		pins = "gpio6";
@@ -448,10 +572,93 @@
 	};
 };
 
+&pmk8350_adc_tm {
+	status = "okay";
+
+	xo-therm@0 {
+		reg = <0>;
+		io-channels = <&pmk8350_vadc PMK8350_ADC7_AMUX_THM1_100K_PU>;
+		qcom,ratiometric;
+		qcom,hw-settle-time-us = <200>;
+	};
+
+	quiet-therm@1 {
+		reg = <1>;
+		io-channels = <&pmk8350_vadc PM7325_ADC7_AMUX_THM1_100K_PU>;
+		qcom,ratiometric;
+		qcom,hw-settle-time-us = <200>;
+	};
+
+	cam-flash-therm@2 {
+		reg = <2>;
+		io-channels = <&pmk8350_vadc PM7325_ADC7_AMUX_THM2_100K_PU>;
+		qcom,ratiometric;
+		qcom,hw-settle-time-us = <200>;
+	};
+
+	sdm-skin-therm@3 {
+		reg = <3>;
+		io-channels = <&pmk8350_vadc PM7325_ADC7_AMUX_THM3_100K_PU>;
+		qcom,ratiometric;
+		qcom,hw-settle-time-us = <200>;
+	};
+
+	wide-rfc-therm@4 {
+		reg = <4>;
+		io-channels = <&pmk8350_vadc PM7325_ADC7_AMUX_THM4_100K_PU>;
+		qcom,ratiometric;
+		qcom,hw-settle-time-us = <200>;
+	};
+};
+
 &pmk8350_rtc {
 	status = "okay";
 };
 
+&pmk8350_vadc {
+	status = "okay";
+
+	channel@44 {
+		reg = <PMK8350_ADC7_AMUX_THM1_100K_PU>;
+		qcom,ratiometric;
+		qcom,hw-settle-time = <200>;
+		qcom,pre-scaling = <1 1>;
+		label = "pmk8350_xo_therm";
+	};
+
+	channel@144 {
+		reg = <PM7325_ADC7_AMUX_THM1_100K_PU>;
+		qcom,ratiometric;
+		qcom,hw-settle-time = <200>;
+		qcom,pre-scaling = <1 1>;
+		label = "pm7325_quiet_therm";
+	};
+
+	channel@145 {
+		reg = <PM7325_ADC7_AMUX_THM2_100K_PU>;
+		qcom,ratiometric;
+		qcom,hw-settle-time = <200>;
+		qcom,pre-scaling = <1 1>;
+		label = "pm7325_cam_flash_therm";
+	};
+
+	channel@146 {
+		reg = <PM7325_ADC7_AMUX_THM3_100K_PU>;
+		qcom,ratiometric;
+		qcom,hw-settle-time = <200>;
+		qcom,pre-scaling = <1 1>;
+		label = "pm7325_sdm_skin_therm";
+	};
+
+	channel@147 {
+		reg = <PM7325_ADC7_AMUX_THM4_100K_PU>;
+		qcom,ratiometric;
+		qcom,hw-settle-time = <200>;
+		qcom,pre-scaling = <1 1>;
+		label = "pm7325_wide_rfc_therm";
+	};
+};
+
 &pon_pwrkey {
 	status = "okay";
 };
@@ -489,6 +696,26 @@
 	status = "okay";
 };
 
+&remoteproc_adsp {
+	firmware-name = "qcom/qcm6490/fairphone5/adsp.mbn";
+	status = "okay";
+};
+
+&remoteproc_cdsp {
+	firmware-name = "qcom/qcm6490/fairphone5/cdsp.mbn";
+	status = "okay";
+};
+
+&remoteproc_mpss {
+	firmware-name = "qcom/qcm6490/fairphone5/modem.mbn";
+	status = "okay";
+};
+
+&remoteproc_wpss {
+	firmware-name = "qcom/qcm6490/fairphone5/wpss.mbn";
+	status = "okay";
+};
+
 &sdc2_clk {
 	drive-strength = <16>;
 	bias-disable;
@@ -632,6 +859,28 @@
 	};
 };
 
+&ufs_mem_hc {
+	reset-gpios = <&tlmm 175 GPIO_ACTIVE_LOW>;
+
+	vcc-supply = <&vreg_l7b>;
+	vcc-max-microamp = <800000>;
+	/*
+	 * Technically l9b enables an eLDO (supplied by s1b) which then powers
+	 * VCCQ2 of the UFS.
+	 */
+	vccq-supply = <&vreg_l9b>;
+	vccq-max-microamp = <900000>;
+
+	status = "okay";
+};
+
+&ufs_mem_phy {
+	vdda-phy-supply = <&vreg_l10c>;
+	vdda-pll-supply = <&vreg_l6b>;
+
+	status = "okay";
+};
+
 &usb_1 {
 	status = "okay";
 };
@@ -665,3 +914,8 @@
 
 	status = "okay";
 };
+
+&wifi {
+	qcom,ath11k-calibration-variant = "Fairphone_5";
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/qcom/qcm6490-idp.dts b/arch/arm64/boot/dts/qcom/qcm6490-idp.dts
new file mode 100644
index 000000000000..03e97e27d16d
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/qcm6490-idp.dts
@@ -0,0 +1,468 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/regulator/qcom,rpmh-regulator.h>
+#include "sc7280.dtsi"
+#include "pm7325.dtsi"
+#include "pm8350c.dtsi"
+#include "pmk8350.dtsi"
+
+/delete-node/ &ipa_fw_mem;
+/delete-node/ &rmtfs_mem;
+/delete-node/ &adsp_mem;
+/delete-node/ &cdsp_mem;
+/delete-node/ &video_mem;
+/delete-node/ &wlan_ce_mem;
+/delete-node/ &wpss_mem;
+/delete-node/ &xbl_mem;
+
+/ {
+	model = "Qualcomm Technologies, Inc. QCM6490 IDP";
+	compatible = "qcom,qcm6490-idp", "qcom,qcm6490";
+	chassis-type = "embedded";
+
+	aliases {
+		serial0 = &uart5;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	reserved-memory {
+		xbl_mem: xbl@80700000 {
+			reg = <0x0 0x80700000 0x0 0x100000>;
+			no-map;
+		};
+
+		cdsp_secure_heap_mem: cdsp-secure-heap@81800000 {
+			reg = <0x0 0x81800000 0x0 0x1e00000>;
+			no-map;
+		};
+
+		camera_mem: camera@84300000 {
+			reg = <0x0 0x84300000 0x0 0x500000>;
+			no-map;
+		};
+
+		wpss_mem: wpss@84800000 {
+			reg = <0x0 0x84800000 0x0 0x1900000>;
+			no-map;
+		};
+
+		adsp_mem: adsp@86100000 {
+			reg = <0x0 0x86100000 0x0 0x2800000>;
+			no-map;
+		};
+
+		cdsp_mem: cdsp@88900000 {
+			reg = <0x0 0x88900000 0x0 0x1e00000>;
+			no-map;
+		};
+
+		video_mem: video@8a700000 {
+			reg = <0x0 0x8a700000 0x0 0x700000>;
+			no-map;
+		};
+
+		cvp_mem: cvp@8ae00000 {
+			reg = <0x0 0x8ae00000 0x0 0x500000>;
+			no-map;
+		};
+
+		ipa_fw_mem: ipa-fw@8b300000 {
+			reg = <0x0 0x8b300000 0x0 0x10000>;
+			no-map;
+		};
+
+		ipa_gsi_mem: ipa-gsi@8b310000 {
+			reg = <0x0 0x8b310000 0x0 0xa000>;
+			no-map;
+		};
+
+		gpu_microcode_mem: gpu-microcode@8b31a000 {
+			reg = <0x0 0x8b31a000 0x0 0x2000>;
+			no-map;
+		};
+
+		mpss_mem: mpss@8b800000 {
+			reg = <0x0 0x8b800000 0x0 0xf600000>;
+			no-map;
+		};
+
+		tz_stat_mem: tz-stat@c0000000 {
+			reg = <0x0 0xc0000000 0x0 0x100000>;
+			no-map;
+		};
+
+		tags_mem: tags@c0100000 {
+			reg = <0x0 0xc0100000 0x0 0x1200000>;
+			no-map;
+		};
+
+		qtee_mem: qtee@c1300000 {
+			reg = <0x0 0xc1300000 0x0 0x500000>;
+			no-map;
+		};
+
+		trusted_apps_mem: trusted_apps@c1800000 {
+			reg = <0x0 0xc1800000 0x0 0x1c00000>;
+			no-map;
+		};
+
+		debug_vm_mem: debug-vm@d0600000 {
+			reg = <0x0 0xd0600000 0x0 0x100000>;
+			no-map;
+		};
+	};
+
+	vph_pwr: vph-pwr-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vph_pwr";
+		regulator-min-microvolt = <2500000>;
+		regulator-max-microvolt = <4350000>;
+	};
+};
+
+&apps_rsc {
+	regulators-0 {
+		compatible = "qcom,pm7325-rpmh-regulators";
+		qcom,pmic-id = "b";
+
+		vdd-s1-supply = <&vph_pwr>;
+		vdd-s2-supply = <&vph_pwr>;
+		vdd-s3-supply = <&vph_pwr>;
+		vdd-s4-supply = <&vph_pwr>;
+		vdd-s5-supply = <&vph_pwr>;
+		vdd-s6-supply = <&vph_pwr>;
+		vdd-s7-supply = <&vph_pwr>;
+		vdd-s8-supply = <&vph_pwr>;
+		vdd-l1-l4-l12-l15-supply = <&vreg_s7b_0p972>;
+		vdd-l2-l7-supply = <&vreg_bob_3p296>;
+		vdd-l3-supply = <&vreg_s2b_0p876>;
+		vdd-l5-supply = <&vreg_s2b_0p876>;
+		vdd-l6-l9-l10-supply = <&vreg_s8b_1p272>;
+		vdd-l8-supply = <&vreg_s7b_0p972>;
+		vdd-l11-l17-l18-l19-supply = <&vreg_s1b_1p872>;
+		vdd-l13-supply = <&vreg_s7b_0p972>;
+		vdd-l14-l16-supply = <&vreg_s8b_1p272>;
+
+		vreg_s1b_1p872: smps1 {
+			regulator-min-microvolt = <1840000>;
+			regulator-max-microvolt = <2040000>;
+		};
+
+		vreg_s2b_0p876: smps2 {
+			regulator-min-microvolt = <570070>;
+			regulator-max-microvolt = <1050000>;
+		};
+
+		vreg_s7b_0p972: smps7 {
+			regulator-min-microvolt = <535000>;
+			regulator-max-microvolt = <1120000>;
+		};
+
+		vreg_s8b_1p272: smps8 {
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1500000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_RET>;
+		};
+
+		vreg_l1b_0p912: ldo1 {
+			regulator-min-microvolt = <825000>;
+			regulator-max-microvolt = <925000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2b_3p072: ldo2 {
+			regulator-min-microvolt = <2700000>;
+			regulator-max-microvolt = <3544000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3b_0p504: ldo3 {
+			regulator-min-microvolt = <312000>;
+			regulator-max-microvolt = <910000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l4b_0p752: ldo4 {
+			regulator-min-microvolt = <752000>;
+			regulator-max-microvolt = <820000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		reg_l5b_0p752: ldo5 {
+			regulator-min-microvolt = <552000>;
+			regulator-max-microvolt = <832000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6b_1p2: ldo6 {
+			regulator-min-microvolt = <1140000>;
+			regulator-max-microvolt = <1260000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l7b_2p952: ldo7 {
+			regulator-min-microvolt = <2400000>;
+			regulator-max-microvolt = <3544000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l8b_0p904: ldo8 {
+			regulator-min-microvolt = <870000>;
+			regulator-max-microvolt = <970000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l9b_1p2: ldo9 {
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1304000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l11b_1p504: ldo11 {
+			regulator-min-microvolt = <1504000>;
+			regulator-max-microvolt = <2000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l12b_0p751: ldo12 {
+			regulator-min-microvolt = <751000>;
+			regulator-max-microvolt = <824000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l13b_0p53: ldo13 {
+			regulator-min-microvolt = <530000>;
+			regulator-max-microvolt = <824000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l14b_1p08: ldo14 {
+			regulator-min-microvolt = <1080000>;
+			regulator-max-microvolt = <1304000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l15b_0p765: ldo15 {
+			regulator-min-microvolt = <765000>;
+			regulator-max-microvolt = <1020000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l16b_1p1: ldo16 {
+			regulator-min-microvolt = <1100000>;
+			regulator-max-microvolt = <1300000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l17b_1p7: ldo17 {
+			regulator-min-microvolt = <1700000>;
+			regulator-max-microvolt = <1900000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l18b_1p8: ldo18 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l19b_1p8: ldo19 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-1 {
+		compatible = "qcom,pm8350c-rpmh-regulators";
+		qcom,pmic-id = "c";
+
+		vdd-s1-supply = <&vph_pwr>;
+		vdd-s2-supply = <&vph_pwr>;
+		vdd-s3-supply = <&vph_pwr>;
+		vdd-s4-supply = <&vph_pwr>;
+		vdd-s5-supply = <&vph_pwr>;
+		vdd-s6-supply = <&vph_pwr>;
+		vdd-s7-supply = <&vph_pwr>;
+		vdd-s8-supply = <&vph_pwr>;
+		vdd-s9-supply = <&vph_pwr>;
+		vdd-s10-supply = <&vph_pwr>;
+		vdd-l1-l12-supply = <&vreg_s1b_1p872>;
+		vdd-l2-l8-supply = <&vreg_s1b_1p872>;
+		vdd-l3-l4-l5-l7-l13-supply = <&vreg_bob_3p296>;
+		vdd-l6-l9-l11-supply = <&vreg_bob_3p296>;
+		vdd-l10-supply = <&vreg_s7b_0p972>;
+		vdd-bob-supply = <&vph_pwr>;
+
+		vreg_s1c_2p19: smps1 {
+			regulator-min-microvolt = <2190000>;
+			regulator-max-microvolt = <2210000>;
+		};
+
+		vreg_s2c_0p752: smps2 {
+			regulator-min-microvolt = <750000>;
+			regulator-max-microvolt = <800000>;
+		};
+
+		vreg_s5c_0p752: smps5 {
+			regulator-min-microvolt = <465000>;
+			regulator-max-microvolt = <1050000>;
+		};
+
+		vreg_s7c_0p752: smps7 {
+			regulator-min-microvolt = <465000>;
+			regulator-max-microvolt = <800000>;
+		};
+
+		vreg_s9c_1p084: smps9 {
+			regulator-min-microvolt = <1010000>;
+			regulator-max-microvolt = <1170000>;
+		};
+
+		vreg_l1c_1p8: ldo1 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1980000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2c_1p62: ldo2 {
+			regulator-min-microvolt = <1620000>;
+			regulator-max-microvolt = <1980000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3c_2p8: ldo3 {
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <3540000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l4c_1p62: ldo4 {
+			regulator-min-microvolt = <1620000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l5c_1p62: ldo5 {
+			regulator-min-microvolt = <1620000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6c_2p96: ldo6 {
+			regulator-min-microvolt = <1650000>;
+			regulator-max-microvolt = <3544000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l7c_3p0: ldo7 {
+			regulator-min-microvolt = <3000000>;
+			regulator-max-microvolt = <3544000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l8c_1p62: ldo8 {
+			regulator-min-microvolt = <1620000>;
+			regulator-max-microvolt = <2000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l9c_2p96: ldo9 {
+			regulator-min-microvolt = <2700000>;
+			regulator-max-microvolt = <35440000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l10c_0p88: ldo10 {
+			regulator-min-microvolt = <720000>;
+			regulator-max-microvolt = <1050000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l11c_2p8: ldo11 {
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <3544000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l12c_1p65: ldo12 {
+			regulator-min-microvolt = <1650000>;
+			regulator-max-microvolt = <2000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l13c_2p7: ldo13 {
+			regulator-min-microvolt = <2700000>;
+			regulator-max-microvolt = <3544000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_bob_3p296: bob {
+			regulator-min-microvolt = <3008000>;
+			regulator-max-microvolt = <3960000>;
+		};
+	};
+};
+
+&qupv3_id_0 {
+	status = "okay";
+};
+
+&sdhc_1 {
+	non-removable;
+	no-sd;
+	no-sdio;
+
+	vmmc-supply = <&vreg_l7b_2p952>;
+	vqmmc-supply = <&vreg_l19b_1p8>;
+
+	status = "okay";
+};
+
+&tlmm {
+	gpio-reserved-ranges = <32 2>, /* ADSP */
+			       <48 4>; /* NFC */
+};
+
+&uart5 {
+	compatible = "qcom,geni-debug-uart";
+	status = "okay";
+};
+
+&usb_1 {
+	status = "okay";
+};
+
+&usb_1_dwc3 {
+	dr_mode = "peripheral";
+};
+
+&usb_1_hsphy {
+	vdda-pll-supply = <&vreg_l10c_0p88>;
+	vdda33-supply = <&vreg_l2b_3p072>;
+	vdda18-supply = <&vreg_l1c_1p8>;
+
+	status = "okay";
+};
+
+&usb_1_qmpphy {
+	vdda-phy-supply = <&vreg_l6b_1p2>;
+	vdda-pll-supply = <&vreg_l1b_0p912>;
+
+	status = "okay";
+};
+
+&wifi {
+	memory-region = <&wlan_fw_mem>;
+};
diff --git a/arch/arm64/boot/dts/qcom/qcs404.dtsi b/arch/arm64/boot/dts/qcom/qcs404.dtsi
index 2721f32dfb71..6ac64ce9bb68 100644
--- a/arch/arm64/boot/dts/qcom/qcs404.dtsi
+++ b/arch/arm64/boot/dts/qcom/qcs404.dtsi
@@ -1461,7 +1461,7 @@
 			};
 		};
 
-		pcie: pci@10000000 {
+		pcie: pcie@10000000 {
 			compatible = "qcom,pcie-qcs404";
 			reg = <0x10000000 0xf1d>,
 			      <0x10000f20 0xa8>,
diff --git a/arch/arm64/boot/dts/qcom/qcs6490-rb3gen2.dts b/arch/arm64/boot/dts/qcom/qcs6490-rb3gen2.dts
new file mode 100644
index 000000000000..8bb7d13d85f6
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/qcs6490-rb3gen2.dts
@@ -0,0 +1,455 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+/dts-v1/;
+
+/* PM7250B is configured to use SID8/9 */
+#define PM7250B_SID 8
+#define PM7250B_SID1 9
+
+#include <dt-bindings/regulator/qcom,rpmh-regulator.h>
+#include "sc7280.dtsi"
+#include "pm7250b.dtsi"
+#include "pm7325.dtsi"
+#include "pm8350c.dtsi"
+#include "pmk8350.dtsi"
+
+/delete-node/ &ipa_fw_mem;
+/delete-node/ &remoteproc_mpss;
+/delete-node/ &rmtfs_mem;
+/delete-node/ &adsp_mem;
+/delete-node/ &cdsp_mem;
+/delete-node/ &video_mem;
+/delete-node/ &wlan_ce_mem;
+/delete-node/ &wpss_mem;
+/delete-node/ &xbl_mem;
+
+/ {
+	model = "Qualcomm Technologies, Inc. Robotics RB3gen2";
+	compatible = "qcom,qcs6490-rb3gen2", "qcom,qcm6490";
+	chassis-type = "embedded";
+
+	aliases {
+		serial0 = &uart5;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	reserved-memory {
+		xbl_mem: xbl@80700000 {
+			reg = <0x0 0x80700000 0x0 0x100000>;
+			no-map;
+		};
+
+		cdsp_secure_heap_mem: cdsp-secure-heap@81800000 {
+			reg = <0x0 0x81800000 0x0 0x1e00000>;
+			no-map;
+		};
+
+		camera_mem: camera@84300000 {
+			reg = <0x0 0x84300000 0x0 0x500000>;
+			no-map;
+		};
+
+		wpss_mem: wpss@84800000 {
+			reg = <0x0 0x84800000 0x0 0x1900000>;
+			no-map;
+		};
+
+		adsp_mem: adsp@86100000 {
+			reg = <0x0 0x86100000 0x0 0x2800000>;
+			no-map;
+		};
+
+		cdsp_mem: cdsp@88900000 {
+			reg = <0x0 0x88900000 0x0 0x1e00000>;
+			no-map;
+		};
+
+		video_mem: video@8a700000 {
+			reg = <0x0 0x8a700000 0x0 0x700000>;
+			no-map;
+		};
+
+		cvp_mem: cvp@8ae00000 {
+			reg = <0x0 0x8ae00000 0x0 0x500000>;
+			no-map;
+		};
+
+		ipa_fw_mem: ipa-fw@8b300000 {
+			reg = <0x0 0x8b300000 0x0 0x10000>;
+			no-map;
+		};
+
+		ipa_gsi_mem: ipa-gsi@8b310000 {
+			reg = <0x0 0x8b310000 0x0 0xa000>;
+			no-map;
+		};
+
+		gpu_microcode_mem: gpu-microcode@8b31a000 {
+			reg = <0x0 0x8b31a000 0x0 0x2000>;
+			no-map;
+		};
+
+		tz_stat_mem: tz-stat@c0000000 {
+			reg = <0x0 0xc0000000 0x0 0x100000>;
+			no-map;
+		};
+
+		tags_mem: tags@c0100000 {
+			reg = <0x0 0xc0100000 0x0 0x1200000>;
+			no-map;
+		};
+
+		qtee_mem: qtee@c1300000 {
+			reg = <0x0 0xc1300000 0x0 0x500000>;
+			no-map;
+		};
+
+		trusted_apps_mem: trusted_apps@c1800000 {
+			reg = <0x0 0xc1800000 0x0 0x1c00000>;
+			no-map;
+		};
+
+		debug_vm_mem: debug-vm@d0600000 {
+			reg = <0x0 0xd0600000 0x0 0x100000>;
+			no-map;
+		};
+	};
+
+	vph_pwr: vph-pwr-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vph_pwr";
+		regulator-min-microvolt = <2500000>;
+		regulator-max-microvolt = <4350000>;
+	};
+};
+
+&apps_rsc {
+	regulators-0 {
+		compatible = "qcom,pm7325-rpmh-regulators";
+		qcom,pmic-id = "b";
+
+		vdd-s1-supply = <&vph_pwr>;
+		vdd-s2-supply = <&vph_pwr>;
+		vdd-s3-supply = <&vph_pwr>;
+		vdd-s4-supply = <&vph_pwr>;
+		vdd-s5-supply = <&vph_pwr>;
+		vdd-s6-supply = <&vph_pwr>;
+		vdd-s7-supply = <&vph_pwr>;
+		vdd-s8-supply = <&vph_pwr>;
+		vdd-l1-l4-l12-l15-supply = <&vreg_s7b_0p972>;
+		vdd-l2-l7-supply = <&vreg_bob_3p296>;
+		vdd-l3-supply = <&vreg_s2b_0p876>;
+		vdd-l5-supply = <&vreg_s2b_0p876>;
+		vdd-l6-l9-l10-supply = <&vreg_s8b_1p272>;
+		vdd-l8-supply = <&vreg_s7b_0p972>;
+		vdd-l11-l17-l18-l19-supply = <&vreg_s1b_1p872>;
+		vdd-l13-supply = <&vreg_s7b_0p972>;
+		vdd-l14-l16-supply = <&vreg_s8b_1p272>;
+
+		vreg_s1b_1p872: smps1 {
+			regulator-min-microvolt = <1840000>;
+			regulator-max-microvolt = <2040000>;
+		};
+
+		vreg_s2b_0p876: smps2 {
+			regulator-min-microvolt = <570070>;
+			regulator-max-microvolt = <1050000>;
+		};
+
+		vreg_s7b_0p972: smps7 {
+			regulator-min-microvolt = <535000>;
+			regulator-max-microvolt = <1120000>;
+		};
+
+		vreg_s8b_1p272: smps8 {
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1500000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_RET>;
+		};
+
+		vreg_l1b_0p912: ldo1 {
+			regulator-min-microvolt = <825000>;
+			regulator-max-microvolt = <925000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2b_3p072: ldo2 {
+			regulator-min-microvolt = <2700000>;
+			regulator-max-microvolt = <3544000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3b_0p504: ldo3 {
+			regulator-min-microvolt = <312000>;
+			regulator-max-microvolt = <910000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l4b_0p752: ldo4 {
+			regulator-min-microvolt = <752000>;
+			regulator-max-microvolt = <820000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		reg_l5b_0p752: ldo5 {
+			regulator-min-microvolt = <552000>;
+			regulator-max-microvolt = <832000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6b_1p2: ldo6 {
+			regulator-min-microvolt = <1140000>;
+			regulator-max-microvolt = <1260000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l7b_2p952: ldo7 {
+			regulator-min-microvolt = <2400000>;
+			regulator-max-microvolt = <3544000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l8b_0p904: ldo8 {
+			regulator-min-microvolt = <870000>;
+			regulator-max-microvolt = <970000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l9b_1p2: ldo9 {
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1304000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l11b_1p504: ldo11 {
+			regulator-min-microvolt = <1504000>;
+			regulator-max-microvolt = <2000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l12b_0p751: ldo12 {
+			regulator-min-microvolt = <751000>;
+			regulator-max-microvolt = <824000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l13b_0p53: ldo13 {
+			regulator-min-microvolt = <530000>;
+			regulator-max-microvolt = <824000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l14b_1p08: ldo14 {
+			regulator-min-microvolt = <1080000>;
+			regulator-max-microvolt = <1304000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l15b_0p765: ldo15 {
+			regulator-min-microvolt = <765000>;
+			regulator-max-microvolt = <1020000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l16b_1p1: ldo16 {
+			regulator-min-microvolt = <1100000>;
+			regulator-max-microvolt = <1300000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l17b_1p7: ldo17 {
+			regulator-min-microvolt = <1700000>;
+			regulator-max-microvolt = <1900000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l18b_1p8: ldo18 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l19b_1p8: ldo19 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-1 {
+		compatible = "qcom,pm8350c-rpmh-regulators";
+		qcom,pmic-id = "c";
+
+		vdd-s1-supply = <&vph_pwr>;
+		vdd-s2-supply = <&vph_pwr>;
+		vdd-s3-supply = <&vph_pwr>;
+		vdd-s4-supply = <&vph_pwr>;
+		vdd-s5-supply = <&vph_pwr>;
+		vdd-s6-supply = <&vph_pwr>;
+		vdd-s7-supply = <&vph_pwr>;
+		vdd-s8-supply = <&vph_pwr>;
+		vdd-s9-supply = <&vph_pwr>;
+		vdd-s10-supply = <&vph_pwr>;
+		vdd-l1-l12-supply = <&vreg_s1b_1p872>;
+		vdd-l2-l8-supply = <&vreg_s1b_1p872>;
+		vdd-l3-l4-l5-l7-l13-supply = <&vreg_bob_3p296>;
+		vdd-l6-l9-l11-supply = <&vreg_bob_3p296>;
+		vdd-l10-supply = <&vreg_s7b_0p972>;
+		vdd-bob-supply = <&vph_pwr>;
+
+		vreg_s1c_2p19: smps1 {
+			regulator-min-microvolt = <2190000>;
+			regulator-max-microvolt = <2210000>;
+		};
+
+		vreg_s2c_0p752: smps2 {
+			regulator-min-microvolt = <750000>;
+			regulator-max-microvolt = <800000>;
+		};
+
+		vreg_s5c_0p752: smps5 {
+			regulator-min-microvolt = <465000>;
+			regulator-max-microvolt = <1050000>;
+		};
+
+		vreg_s7c_0p752: smps7 {
+			regulator-min-microvolt = <465000>;
+			regulator-max-microvolt = <800000>;
+		};
+
+		vreg_s9c_1p084: smps9 {
+			regulator-min-microvolt = <1010000>;
+			regulator-max-microvolt = <1170000>;
+		};
+
+		vreg_l1c_1p8: ldo1 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1980000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2c_1p62: ldo2 {
+			regulator-min-microvolt = <1620000>;
+			regulator-max-microvolt = <1980000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3c_2p8: ldo3 {
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <3540000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l4c_1p62: ldo4 {
+			regulator-min-microvolt = <1620000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l5c_1p62: ldo5 {
+			regulator-min-microvolt = <1620000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6c_2p96: ldo6 {
+			regulator-min-microvolt = <1650000>;
+			regulator-max-microvolt = <3544000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l7c_3p0: ldo7 {
+			regulator-min-microvolt = <3000000>;
+			regulator-max-microvolt = <3544000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l8c_1p62: ldo8 {
+			regulator-min-microvolt = <1620000>;
+			regulator-max-microvolt = <2000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l9c_2p96: ldo9 {
+			regulator-min-microvolt = <2700000>;
+			regulator-max-microvolt = <35440000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l10c_0p88: ldo10 {
+			regulator-min-microvolt = <720000>;
+			regulator-max-microvolt = <1050000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l11c_2p8: ldo11 {
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <3544000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l12c_1p65: ldo12 {
+			regulator-min-microvolt = <1650000>;
+			regulator-max-microvolt = <2000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l13c_2p7: ldo13 {
+			regulator-min-microvolt = <2700000>;
+			regulator-max-microvolt = <3544000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_bob_3p296: bob {
+			regulator-min-microvolt = <3008000>;
+			regulator-max-microvolt = <3960000>;
+		};
+	};
+};
+
+&qupv3_id_0 {
+	status = "okay";
+};
+
+&tlmm {
+	gpio-reserved-ranges = <32 2>, /* ADSP */
+			       <48 4>; /* NFC */
+};
+
+&uart5 {
+	compatible = "qcom,geni-debug-uart";
+	status = "okay";
+};
+
+&usb_1 {
+	status = "okay";
+};
+
+&usb_1_dwc3 {
+	dr_mode = "peripheral";
+};
+
+&usb_1_hsphy {
+	vdda-pll-supply = <&vreg_l10c_0p88>;
+	vdda33-supply = <&vreg_l2b_3p072>;
+	vdda18-supply = <&vreg_l1c_1p8>;
+
+	status = "okay";
+};
+
+&usb_1_qmpphy {
+	vdda-phy-supply = <&vreg_l6b_1p2>;
+	vdda-pll-supply = <&vreg_l1b_0p912>;
+
+	status = "okay";
+};
+
+&wifi {
+	memory-region = <&wlan_fw_mem>;
+};
diff --git a/arch/arm64/boot/dts/qcom/qdu1000.dtsi b/arch/arm64/boot/dts/qcom/qdu1000.dtsi
index 1c0e5d271e91..832f472c4b7a 100644
--- a/arch/arm64/boot/dts/qcom/qdu1000.dtsi
+++ b/arch/arm64/boot/dts/qcom/qdu1000.dtsi
@@ -381,6 +381,20 @@
 			#power-domain-cells = <1>;
 		};
 
+		ecpricc: clock-controller@280000 {
+			compatible = "qcom,qdu1000-ecpricc";
+			reg = <0x0 0x00280000 0x0 0x31c00>;
+			clocks = <&rpmhcc RPMH_CXO_CLK>,
+				 <&gcc GCC_ECPRI_CC_GPLL0_CLK_SRC>,
+				 <&gcc GCC_ECPRI_CC_GPLL1_EVEN_CLK_SRC>,
+				 <&gcc GCC_ECPRI_CC_GPLL2_EVEN_CLK_SRC>,
+				 <&gcc GCC_ECPRI_CC_GPLL3_CLK_SRC>,
+				 <&gcc GCC_ECPRI_CC_GPLL4_CLK_SRC>,
+				 <&gcc GCC_ECPRI_CC_GPLL5_EVEN_CLK_SRC>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+		};
+
 		gpi_dma0: dma-controller@900000  {
 			compatible = "qcom,qdu1000-gpi-dma", "qcom,sm6350-gpi-dma";
 			reg = <0x0 0x900000 0x0 0x60000>;
@@ -1446,13 +1460,10 @@
 		system-cache-controller@19200000 {
 			compatible = "qcom,qdu1000-llcc";
 			reg = <0 0x19200000 0 0xd80000>,
-			      <0 0x1a200000 0 0x80000>,
-			      <0 0x221c8128 0 0x4>;
-			reg-names = "llcc_base",
-				    "llcc_broadcast_base",
-				    "multi_channel_register";
+			      <0 0x1a200000 0 0x80000>;
+			reg-names = "llcc0_base",
+				    "llcc_broadcast_base";
 			interrupts = <GIC_SPI 266 IRQ_TYPE_LEVEL_HIGH>;
-			multi-ch-bit-off = <24 2>;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts b/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts
index 94885b9c21c8..aa53b6af6d9c 100644
--- a/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts
+++ b/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts
@@ -23,6 +23,14 @@
 		stdout-path = "serial0:115200n8";
 	};
 
+	clocks {
+		clk40M: can-clk {
+			compatible = "fixed-clock";
+			clock-frequency = <40000000>;
+			#clock-cells = <0>;
+		};
+	};
+
 	gpio-keys {
 		compatible = "gpio-keys";
 		label = "gpio-keys";
@@ -40,6 +48,17 @@
 		};
 	};
 
+	hdmi-connector {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi_con: endpoint {
+				remote-endpoint = <&lt9611_out>;
+			};
+		};
+	};
+
 	leds {
 		compatible = "gpio-leds";
 
@@ -158,6 +177,68 @@
 	};
 };
 
+&gpi_dma0 {
+	status = "okay";
+};
+
+&i2c2 {
+	clock-frequency = <400000>;
+	status = "okay";
+
+	lt9611_codec: hdmi-bridge@2b {
+		compatible = "lontium,lt9611uxc";
+		reg = <0x2b>;
+		interrupts-extended = <&tlmm 46 IRQ_TYPE_EDGE_FALLING>;
+		reset-gpios = <&tlmm 41 GPIO_ACTIVE_HIGH>;
+
+		vdd-supply = <&vreg_hdmi_out_1p2>;
+		vcc-supply = <&lt9611_3v3>;
+
+		pinctrl-0 = <&lt9611_irq_pin &lt9611_rst_pin>;
+		pinctrl-names = "default";
+		#sound-dai-cells = <1>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				lt9611_a: endpoint {
+					remote-endpoint = <&mdss_dsi0_out>;
+				};
+			};
+
+			port@2 {
+				reg = <2>;
+
+				lt9611_out: endpoint {
+					remote-endpoint = <&hdmi_con>;
+				};
+			};
+		};
+	};
+};
+
+&mdss {
+	status = "okay";
+};
+
+&mdss_dsi0 {
+	vdda-supply = <&pm2250_l5>;
+	status = "okay";
+};
+
+&mdss_dsi0_out {
+	remote-endpoint = <&lt9611_a>;
+	data-lanes = <0 1 2 3>;
+};
+
+&mdss_dsi0_phy {
+	status = "okay";
+};
+
 &pm2250_resin {
 	linux,code = <KEY_VOLUMEDOWN>;
 	status = "okay";
@@ -376,7 +457,34 @@
 	status = "okay";
 };
 
+&spi5 {
+	status = "okay";
+
+	can@0 {
+		compatible = "microchip,mcp2518fd";
+		reg = <0>;
+		interrupts-extended = <&tlmm 39 IRQ_TYPE_LEVEL_LOW>;
+		clocks = <&clk40M>;
+		spi-max-frequency = <10000000>;
+		vdd-supply = <&vdc_5v>;
+		xceiver-supply = <&vdc_5v>;
+	};
+};
+
 &tlmm {
+	lt9611_rst_pin: lt9611-rst-state {
+		pins = "gpio41";
+		function = "gpio";
+		input-disable;
+		output-high;
+	};
+
+	lt9611_irq_pin: lt9611-irq-state {
+		pins = "gpio46";
+		function = "gpio";
+		bias-disable;
+	};
+
 	sd_det_in_on: sd-det-in-on-state {
 		pins = "gpio88";
 		function = "gpio";
@@ -415,6 +523,10 @@
 	status = "okay";
 };
 
+&usb_dwc3 {
+	dr_mode = "host";
+};
+
 &usb_hsphy {
 	vdd-supply = <&pm2250_l12>;
 	vdda-pll-supply = <&pm2250_l13>;
@@ -427,6 +539,7 @@
 	vdd-1.8-xo-supply = <&pm2250_l13>;
 	vdd-1.3-rfa-supply = <&pm2250_l10>;
 	vdd-3.3-ch0-supply = <&pm2250_l22>;
+	qcom,ath10k-calibration-variant = "Thundercomm_RB1";
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts b/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts
index a7278a9472ed..7c19f874fa71 100644
--- a/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts
+++ b/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts
@@ -15,6 +15,7 @@
 
 	aliases {
 		serial0 = &uart4;
+		serial1 = &uart3;
 	};
 
 	chosen {
@@ -280,6 +281,12 @@
 	status = "okay";
 };
 
+&remoteproc_mpss {
+	firmware-name = "qcom/qrb4210/modem.mbn";
+
+	status = "okay";
+};
+
 &rpm_requests {
 	regulators {
 		compatible = "qcom,rpm-pm6125-regulators";
@@ -346,13 +353,14 @@
 		};
 
 		vreg_l8a_0p664: l8 {
-			regulator-min-microvolt = <400000>;
-			regulator-max-microvolt = <728000>;
+			regulator-min-microvolt = <640000>;
+			regulator-max-microvolt = <640000>;
 		};
 
 		vreg_l9a_1p8: l9 {
 			regulator-min-microvolt = <1800000>;
-			regulator-max-microvolt = <2000000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-allow-set-load;
 		};
 
 		vreg_l10a_1p8: l10 {
@@ -389,11 +397,13 @@
 		vreg_l16a_1p3: l16 {
 			regulator-min-microvolt = <1704000>;
 			regulator-max-microvolt = <1904000>;
+			regulator-allow-set-load;
 		};
 
 		vreg_l17a_1p3: l17 {
 			regulator-min-microvolt = <1152000>;
 			regulator-max-microvolt = <1384000>;
+			regulator-allow-set-load;
 		};
 
 		vreg_l18a_1p232: l18 {
@@ -424,8 +434,9 @@
 		};
 
 		vreg_l23a_3p3: l23 {
-			regulator-min-microvolt = <3200000>;
-			regulator-max-microvolt = <3400000>;
+			regulator-min-microvolt = <3312000>;
+			regulator-max-microvolt = <3312000>;
+			regulator-allow-set-load;
 		};
 
 		vreg_l24a_2p96: l24 {
@@ -487,6 +498,66 @@
 			       <56 3>, <61 2>, <64 1>,
 			       <68 1>, <72 8>, <96 1>;
 
+	uart3_default: uart3-default-state {
+		cts-pins {
+			pins = "gpio8";
+			function = "qup3";
+			drive-strength = <2>;
+			bias-bus-hold;
+		};
+
+		rts-pins {
+			pins = "gpio9";
+			function = "qup3";
+			drive-strength = <2>;
+			bias-disable;
+		};
+
+		tx-pins {
+			pins = "gpio10";
+			function = "qup3";
+			drive-strength = <2>;
+			bias-disable;
+		};
+
+		rx-pins {
+			pins = "gpio11";
+			function = "qup3";
+			drive-strength = <2>;
+			bias-pull-up;
+		};
+	};
+
+	uart3_sleep: uart3-sleep-state {
+		cts-pins {
+			pins = "gpio8";
+			function = "gpio";
+			drive-strength = <2>;
+			bias-bus-hold;
+		};
+
+		rts-pins {
+			pins = "gpio9";
+			function = "gpio";
+			drive-strength = <2>;
+			bias-pull-down;
+		};
+
+		tx-pins {
+			pins = "gpio10";
+			function = "gpio";
+			drive-strength = <2>;
+			bias-pull-up;
+		};
+
+		rx-pins {
+			pins = "gpio11";
+			function = "gpio";
+			drive-strength = <2>;
+			bias-pull-up;
+		};
+	};
+
 	lt9611_rst_pin: lt9611-rst-state {
 		pins = "gpio41";
 		function = "gpio";
@@ -508,6 +579,26 @@
 	};
 };
 
+&uart3 {
+	interrupts-extended = <&intc GIC_SPI 330 IRQ_TYPE_LEVEL_HIGH>,
+			      <&tlmm 11 IRQ_TYPE_LEVEL_HIGH>;
+	pinctrl-0 = <&uart3_default>;
+	pinctrl-1 = <&uart3_sleep>;
+	pinctrl-names = "default", "sleep";
+	status = "okay";
+
+	bluetooth {
+		compatible = "qcom,wcn3988-bt";
+
+		vddio-supply = <&vreg_l9a_1p8>;
+		vddxo-supply = <&vreg_l16a_1p3>;
+		vddrf-supply = <&vreg_l17a_1p3>;
+		vddch0-supply = <&vreg_l23a_3p3>;
+		enable-gpios = <&tlmm 87 GPIO_ACTIVE_HIGH>;
+		max-speed = <3200000>;
+	};
+};
+
 &uart4 {
 	status = "okay";
 };
@@ -518,7 +609,6 @@
 
 &usb_dwc3 {
 	maximum-speed = "super-speed";
-	dr_mode = "peripheral";
 };
 
 &usb_hsphy {
@@ -536,6 +626,16 @@
 	status = "okay";
 };
 
+&wifi {
+	vdd-0.8-cx-mx-supply = <&vreg_l8a_0p664>;
+	vdd-1.8-xo-supply = <&vreg_l16a_1p3>;
+	vdd-1.3-rfa-supply = <&vreg_l17a_1p3>;
+	vdd-3.3-ch0-supply = <&vreg_l23a_3p3>;
+	qcom,ath10k-calibration-variant = "Thundercomm_RB2";
+
+	status = "okay";
+};
+
 &xo_board {
 	clock-frequency = <19200000>;
 };
diff --git a/arch/arm64/boot/dts/qcom/qrb5165-rb5-vision-mezzanine.dts b/arch/arm64/boot/dts/qcom/qrb5165-rb5-vision-mezzanine.dts
index bb149e577914..edc0e42ee017 100644
--- a/arch/arm64/boot/dts/qcom/qrb5165-rb5-vision-mezzanine.dts
+++ b/arch/arm64/boot/dts/qcom/qrb5165-rb5-vision-mezzanine.dts
@@ -46,7 +46,7 @@
 		assigned-clocks = <&camcc CAM_CC_MCLK2_CLK>;
 		assigned-clock-rates = <24000000>;
 
-		dovdd-supply  = <&vreg_l7f_1p8>;
+		dovdd-supply = <&vreg_l7f_1p8>;
 		avdd-supply = <&vdc_5v>;
 		dvdd-supply = <&vdc_5v>;
 
diff --git a/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts b/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts
index c8cd40a462a3..043184557873 100644
--- a/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts
+++ b/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts
@@ -23,6 +23,7 @@
 
 	aliases {
 		serial0 = &uart12;
+		serial1 = &uart6;
 		sdhc2 = &sdhc_2;
 	};
 
@@ -64,8 +65,8 @@
 			function = LED_FUNCTION_INDICATOR;
 			color = <LED_COLOR_ID_GREEN>;
 			gpios = <&pm8150_gpios 10 GPIO_ACTIVE_HIGH>;
-			linux,default-trigger = "panic-indicator";
 			default-state = "off";
+			panic-indicator;
 		};
 
 		led-wlan {
@@ -1263,6 +1264,14 @@
 		"HST_WLAN_UART_TX",
 		"HST_WLAN_UART_RX";
 
+	bt_en_state: bt-default-state {
+		pins = "gpio21";
+		function = "gpio";
+		drive-strength = <16>;
+		output-low;
+		bias-pull-up;
+	};
+
 	lt9611_irq_pin: lt9611-irq-state {
 		pins = "gpio63";
 		function = "gpio";
@@ -1296,6 +1305,26 @@
 	};
 };
 
+&uart6 {
+	status = "okay";
+
+	bluetooth {
+		compatible = "qcom,qca6390-bt";
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&bt_en_state>;
+
+		enable-gpios = <&tlmm 21 GPIO_ACTIVE_HIGH>;
+
+		vddio-supply = <&vreg_s4a_1p8>;
+		vddpmu-supply = <&vreg_s2f_0p95>;
+		vddaon-supply = <&vreg_s6a_0p95>;
+		vddrfa0p9-supply = <&vreg_s2f_0p95>;
+		vddrfa1p3-supply = <&vreg_s8c_1p3>;
+		vddrfa1p9-supply = <&vreg_s5a_1p9>;
+	};
+};
+
 &uart12 {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/qcom/sa8775p-ride.dts b/arch/arm64/boot/dts/qcom/sa8775p-ride.dts
index 9760bb4b468c..26ad05bd3b3f 100644
--- a/arch/arm64/boot/dts/qcom/sa8775p-ride.dts
+++ b/arch/arm64/boot/dts/qcom/sa8775p-ride.dts
@@ -461,6 +461,11 @@
 			  "ANALOG_PON_OPT";
 };
 
+&pmm8654au_0_pon_resin {
+	linux,code = <KEY_VOLUMEDOWN>;
+	status = "okay";
+};
+
 &pmm8654au_1_gpios {
 	gpio-line-names = "PMIC_C_ID0",
 			  "PMIC_C_ID1",
diff --git a/arch/arm64/boot/dts/qcom/sa8775p.dtsi b/arch/arm64/boot/dts/qcom/sa8775p.dtsi
index b6a93b11cbbd..a7eaca33d326 100644
--- a/arch/arm64/boot/dts/qcom/sa8775p.dtsi
+++ b/arch/arm64/boot/dts/qcom/sa8775p.dtsi
@@ -1487,6 +1487,11 @@
 			};
 		};
 
+		rng: rng@10d2000 {
+			compatible = "qcom,sa8775p-trng", "qcom,trng";
+			reg = <0 0x010d2000 0 0x1000>;
+		};
+
 		ufs_mem_hc: ufs@1d84000 {
 			compatible = "qcom,sa8775p-ufshc", "qcom,ufshc", "jedec,ufs-2.0";
 			reg = <0x0 0x01d84000 0x0 0x3000>;
@@ -1610,8 +1615,8 @@
 			assigned-clock-rates = <19200000>, <200000000>;
 
 			interrupts-extended = <&intc GIC_SPI 287 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc 14 IRQ_TYPE_EDGE_RISING>,
-					      <&pdc 15 IRQ_TYPE_EDGE_RISING>,
+					      <&pdc 14 IRQ_TYPE_EDGE_BOTH>,
+					      <&pdc 15 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 12 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "pwr_event",
 					  "dp_hs_phy_irq",
@@ -1697,8 +1702,8 @@
 			assigned-clock-rates = <19200000>, <200000000>;
 
 			interrupts-extended = <&intc GIC_SPI 352 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc 8 IRQ_TYPE_EDGE_RISING>,
-					      <&pdc 7 IRQ_TYPE_EDGE_RISING>,
+					      <&pdc 8 IRQ_TYPE_EDGE_BOTH>,
+					      <&pdc 7 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 13 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "pwr_event",
 					  "dp_hs_phy_irq",
@@ -1760,8 +1765,8 @@
 			assigned-clock-rates = <19200000>, <200000000>;
 
 			interrupts-extended = <&intc GIC_SPI 444 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc 10 IRQ_TYPE_EDGE_RISING>,
-					      <&pdc 9 IRQ_TYPE_EDGE_RISING>;
+					      <&pdc 10 IRQ_TYPE_EDGE_BOTH>,
+					      <&pdc 9 IRQ_TYPE_EDGE_BOTH>;
 			interrupt-names = "pwr_event",
 					  "dp_hs_phy_irq",
 					  "dm_hs_phy_irq";
@@ -1910,6 +1915,50 @@
 			interrupt-controller;
 		};
 
+		tsens2: thermal-sensor@c251000 {
+			compatible = "qcom,sa8775p-tsens", "qcom,tsens-v2";
+			reg = <0x0 0x0c251000 0x0 0x1ff>,
+			      <0x0 0x0c224000 0x0 0x8>;
+			interrupts = <GIC_SPI 572 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 609 IRQ_TYPE_LEVEL_HIGH>;
+			#qcom,sensors = <13>;
+			interrupt-names = "uplow", "critical";
+			#thermal-sensor-cells = <1>;
+		};
+
+		tsens3: thermal-sensor@c252000 {
+			compatible = "qcom,sa8775p-tsens", "qcom,tsens-v2";
+			reg = <0x0 0x0c252000 0x0 0x1ff>,
+			      <0x0 0x0c225000 0x0 0x8>;
+			interrupts = <GIC_SPI 573 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 610 IRQ_TYPE_LEVEL_HIGH>;
+			#qcom,sensors = <13>;
+			interrupt-names = "uplow", "critical";
+			#thermal-sensor-cells = <1>;
+		};
+
+		tsens0: thermal-sensor@c263000 {
+			compatible = "qcom,sa8775p-tsens", "qcom,tsens-v2";
+			reg = <0x0 0x0c263000 0x0 0x1ff>,
+			      <0x0 0x0c222000 0x0 0x8>;
+			interrupts = <GIC_SPI 506 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 508 IRQ_TYPE_LEVEL_HIGH>;
+			#qcom,sensors = <12>;
+			interrupt-names = "uplow", "critical";
+			#thermal-sensor-cells = <1>;
+		};
+
+		tsens1: thermal-sensor@c265000 {
+			compatible = "qcom,sa8775p-tsens", "qcom,tsens-v2";
+			reg = <0x0 0x0c265000 0x0 0x1ff>,
+			      <0x0 0x0c223000 0x0 0x8>;
+			interrupts = <GIC_SPI 507 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 509 IRQ_TYPE_LEVEL_HIGH>;
+			#qcom,sensors = <12>;
+			interrupt-names = "uplow", "critical";
+			#thermal-sensor-cells = <1>;
+		};
+
 		aoss_qmp: power-management@c300000 {
 			compatible = "qcom,sa8775p-aoss-qmp", "qcom,aoss-qmp";
 			reg = <0x0 0x0c300000 0x0 0x400>;
@@ -1920,6 +1969,11 @@
 			#clock-cells = <0>;
 		};
 
+		sram@c3f0000 {
+			compatible = "qcom,rpmh-stats";
+			reg = <0x0 0x0c3f0000 0x0 0x400>;
+		};
+
 		spmi_bus: spmi@c440000 {
 			compatible = "qcom,spmi-pmic-arb";
 			reg = <0x0 0x0c440000 0x0 0x1100>,
@@ -2181,7 +2235,7 @@
 			compatible = "qcom,apss-wdt-sa8775p", "qcom,kpss-wdt";
 			reg = <0x0 0x17c10000 0x0 0x1000>;
 			clocks = <&sleep_clk>;
-			interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 0 IRQ_TYPE_EDGE_RISING>;
 		};
 
 		memtimer: timer@17c20000 {
@@ -2401,6 +2455,1058 @@
 		};
 	};
 
+	thermal-zones {
+		aoss-0-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 0>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		cpu-0-0-0-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 1>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		cpu-0-1-0-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 2>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		cpu-0-2-0-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 3>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		cpu-0-3-0-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 4>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		gpuss-0-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 5>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		gpuss-1-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 6>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		gpuss-2-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 7>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		audio-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 8>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		camss-0-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 9>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		pcie-0-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 10>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		cpuss-0-0-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 11>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		aoss-1-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 0>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		cpu-0-0-1-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 1>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		cpu-0-1-1-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 2>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		cpu-0-2-1-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 3>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		cpu-0-3-1-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 4>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		gpuss-3-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 5>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		gpuss-4-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 6>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		gpuss-5-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 7>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		video-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 8>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		camss-1-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 9>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		pcie-1-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 10>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		cpuss-0-1-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 11>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		aoss-2-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens2 0>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		cpu-1-0-0-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens2 1>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		cpu-1-1-0-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens2 2>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		cpu-1-2-0-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens2 3>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		cpu-1-3-0-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens2 4>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		nsp-0-0-0-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens2 5>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		nsp-0-1-0-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens2 6>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		nsp-0-2-0-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens2 7>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		nsp-1-0-0-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens2 8>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		nsp-1-1-0-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens2 9>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		nsp-1-2-0-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens2 10>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		ddrss-0-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens2 11>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		cpuss-1-0-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens2 12>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		aoss-3-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens3 0>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		cpu-1-0-1-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens3 1>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		cpu-1-1-1-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens3 2>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		cpu-1-2-1-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens3 3>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		cpu-1-3-1-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens3 4>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		nsp-0-0-1-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens3 5>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		nsp-0-1-1-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens3 6>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		nsp-0-2-1-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens3 7>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		nsp-1-0-1-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens3 8>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		nsp-1-1-1-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens3 9>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		nsp-1-2-1-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens3 10>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		ddrss-1-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens3 11>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+
+		cpuss-1-1-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens3 12>;
+
+			trips {
+				trip-point0 {
+					temperature = <105000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <115000>;
+					hysteresis = <5000>;
+					type = "passive";
+				};
+			};
+		};
+	};
+
 	arch_timer: timer {
 		compatible = "arm,armv8-timer";
 		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>,
@@ -2409,7 +3515,7 @@
 			     <GIC_PPI 12 (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>;
 	};
 
-	pcie0: pci@1c00000{
+	pcie0: pcie@1c00000 {
 		compatible = "qcom,pcie-sa8775p";
 		reg = <0x0 0x01c00000 0x0 0x3000>,
 		      <0x0 0x40000000 0x0 0xf20>,
@@ -2509,7 +3615,7 @@
 		status = "disabled";
 	};
 
-	pcie1: pci@1c10000{
+	pcie1: pcie@1c10000 {
 		compatible = "qcom,pcie-sa8775p";
 		reg = <0x0 0x01c10000 0x0 0x3000>,
 		      <0x0 0x60000000 0x0 0xf20>,
diff --git a/arch/arm64/boot/dts/qcom/sc7180-acer-aspire1.dts b/arch/arm64/boot/dts/qcom/sc7180-acer-aspire1.dts
index dbb48934d499..5afcb8212f49 100644
--- a/arch/arm64/boot/dts/qcom/sc7180-acer-aspire1.dts
+++ b/arch/arm64/boot/dts/qcom/sc7180-acer-aspire1.dts
@@ -3,6 +3,7 @@
 /dts-v1/;
 
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/sound/qcom,q6asm.h>
 #include <dt-bindings/regulator/qcom,rpmh-regulator.h>
 
 #include "sc7180.dtsi"
@@ -129,6 +130,113 @@
 		pinctrl-names = "default";
 	};
 
+	sound: sound {
+		compatible = "qcom,sc7180-qdsp6-sndcard";
+		pinctrl-0 = <&pri_mi2s_active>, <&pri_mi2s_mclk_active>, <&ter_mi2s_active>;
+		pinctrl-names = "default";
+		model = "Acer-Aspire-1";
+
+		audio-routing =
+			"Headphone Jack", "HPOL",
+			"Headphone Jack", "HPOR";
+
+		multimedia1-dai-link {
+			link-name = "MultiMedia1";
+
+			cpu {
+				sound-dai = <&q6asmdai MSM_FRONTEND_DAI_MULTIMEDIA1>;
+			};
+		};
+
+		multimedia2-dai-link {
+			link-name = "MultiMedia2";
+
+			cpu {
+				sound-dai = <&q6asmdai MSM_FRONTEND_DAI_MULTIMEDIA2>;
+			};
+		};
+
+		multimedia3-dai-link {
+			link-name = "MultiMedia3";
+
+			cpu {
+				sound-dai = <&q6asmdai MSM_FRONTEND_DAI_MULTIMEDIA3>;
+			};
+		};
+
+		multimedia4-dai-link {
+			link-name = "MultiMedia4";
+
+			cpu {
+				sound-dai = <&q6asmdai MSM_FRONTEND_DAI_MULTIMEDIA4>;
+			};
+		};
+
+		primary-rx-dai-link {
+			link-name = "Primary MI2S Playback";
+
+			cpu {
+				sound-dai = <&q6afedai PRIMARY_MI2S_RX>;
+			};
+
+			platform {
+				sound-dai = <&q6routing>;
+			};
+
+			codec {
+				sound-dai = <&alc5682 0>;
+			};
+		};
+
+		primary-tx-dai-link {
+			link-name = "Primary MI2S Capture";
+
+			cpu {
+				sound-dai = <&q6afedai PRIMARY_MI2S_TX>;
+			};
+
+			platform {
+				sound-dai = <&q6routing>;
+			};
+
+			codec {
+				sound-dai = <&alc5682 0>;
+			};
+		};
+
+		tertiary-rx-dai-link {
+			link-name = "Tertiary MI2S Playback";
+
+			cpu {
+				sound-dai = <&q6afedai TERTIARY_MI2S_RX>;
+			};
+
+			platform {
+				sound-dai = <&q6routing>;
+			};
+
+			codec {
+				sound-dai = <&max98357a>;
+			};
+		};
+
+		displayport-rx-dai-link {
+			link-name = "DisplayPort Playback";
+
+			cpu {
+				sound-dai = <&q6afedai DISPLAY_PORT_RX>;
+			};
+
+			platform {
+				sound-dai = <&q6routing>;
+			};
+
+			codec {
+				sound-dai = <&mdss_dp>;
+			};
+		};
+	};
+
 	reg_tp_3p3: touchpad-regulator {
 		compatible = "regulator-fixed";
 		regulator-name = "tp_3p3";
@@ -209,9 +317,22 @@
 		AVDD-supply = <&vreg_l15a_1p8>;
 		MICVDD-supply = <&reg_codec_3p3>;
 		VBAT-supply = <&reg_codec_3p3>;
+		DBVDD-supply = <&vreg_l15a_1p8>;
+		LDO1-IN-supply = <&vreg_l15a_1p8>;
+
+		/*
+		 * NOTE: The board has a path from this codec to the
+		 * DMIC microphones in the lid, however some of the option
+		 * resistors are absent and the microphones are connected
+		 * to the SoC instead.
+		 *
+		 * If the resistors were to be changed by the user to
+		 * connect the codec, the following could be used:
+		 *
+		 * realtek,dmic1-data-pin = <1>;
+		 * realtek,dmic1-clk-pin = <1>;
+		 */
 
-		realtek,dmic1-data-pin = <1>;
-		realtek,dmic1-clk-pin = <1>;
 		realtek,jd-src = <1>;
 	};
 };
@@ -351,6 +472,49 @@
 	status = "disabled";
 };
 
+&pm6150_rtc {
+	status = "okay";
+};
+
+&q6afedai {
+	dai@16 {
+		reg = <PRIMARY_MI2S_RX>;
+		qcom,sd-lines = <1>;
+	};
+
+	dai@17 {
+		reg = <PRIMARY_MI2S_TX>;
+		qcom,sd-lines = <0>;
+	};
+
+	dai@20 {
+		reg = <TERTIARY_MI2S_RX>;
+		qcom,sd-lines = <0>;
+	};
+
+	dai@104 {
+		reg = <DISPLAY_PORT_RX>;
+	};
+};
+
+&q6asmdai {
+	dai@0 {
+		reg = <0>;
+	};
+
+	dai@1 {
+		reg = <1>;
+	};
+
+	dai@2 {
+		reg = <2>;
+	};
+
+	dai@3 {
+		reg = <3>;
+	};
+};
+
 &qupv3_id_0 {
 	status = "okay";
 };
@@ -359,6 +523,12 @@
 	status = "okay";
 };
 
+&remoteproc_adsp {
+	memory-region = <&adsp_mem>;
+	firmware-name = "qcom/sc7180/acer/aspire1/qcadsp7180.mbn";
+	status = "okay";
+};
+
 &remoteproc_mpss {
 	firmware-name = "qcom/sc7180/acer/aspire1/qcmpss7180_nm.mbn";
 	status = "okay";
diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi
index 0be62331f982..067813f5f437 100644
--- a/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi
@@ -141,7 +141,7 @@ ap_ts_pen_1v8: &i2c4 {
 };
 
 &panel {
-	compatible = "kingdisplay,kd116n21-30nv-a010";
+	compatible = "edp-panel";
 };
 
 &pen_insert {
diff --git a/arch/arm64/boot/dts/qcom/sc7180.dtsi b/arch/arm64/boot/dts/qcom/sc7180.dtsi
index 11f353d416b4..4dcaa15caef2 100644
--- a/arch/arm64/boot/dts/qcom/sc7180.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7180.dtsi
@@ -2966,8 +2966,8 @@
 
 			interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
 					      <&pdc 6 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc 8 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc 9 IRQ_TYPE_LEVEL_HIGH>;
+					      <&pdc 8 IRQ_TYPE_EDGE_BOTH>,
+					      <&pdc 9 IRQ_TYPE_EDGE_BOTH>;
 			interrupt-names = "hs_phy_irq", "ss_phy_irq",
 					  "dm_hs_phy_irq", "dp_hs_phy_irq";
 
@@ -3100,8 +3100,12 @@
 			interrupt-controller;
 			#interrupt-cells = <1>;
 
-			interconnects = <&mmss_noc MASTER_MDP0 0 &mc_virt SLAVE_EBI1 0>;
-			interconnect-names = "mdp0-mem";
+			interconnects = <&mmss_noc MASTER_MDP0 QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
+					<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+					 &config_noc SLAVE_DISPLAY_CFG QCOM_ICC_TAG_ALWAYS>;
+			interconnect-names = "mdp0-mem",
+					     "cpu-cfg";
 
 			iommus = <&apps_smmu 0x800 0x2>;
 
@@ -3576,7 +3580,7 @@
 			compatible = "qcom,apss-wdt-sc7180", "qcom,kpss-wdt";
 			reg = <0 0x17c10000 0 0x1000>;
 			clocks = <&sleep_clk>;
-			interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 0 IRQ_TYPE_EDGE_RISING>;
 		};
 
 		timer@17c20000 {
diff --git a/arch/arm64/boot/dts/qcom/sc7280-chrome-common.dtsi b/arch/arm64/boot/dts/qcom/sc7280-chrome-common.dtsi
index 5d462ae14ba1..c4d00a81da39 100644
--- a/arch/arm64/boot/dts/qcom/sc7280-chrome-common.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7280-chrome-common.dtsi
@@ -17,6 +17,9 @@
  * required by the setup for Chrome boards.
  */
 
+/delete-node/ &cdsp_mem;
+/delete-node/ &gpu_zap_mem;
+/delete-node/ &gpu_zap_shader;
 /delete-node/ &hyp_mem;
 /delete-node/ &xbl_mem;
 /delete-node/ &reserved_xbl_uefi_log;
@@ -24,11 +27,6 @@
 
 / {
 	reserved-memory {
-		adsp_mem: memory@86700000 {
-			reg = <0x0 0x86700000 0x0 0x2800000>;
-			no-map;
-		};
-
 		camera_mem: memory@8ad00000 {
 			reg = <0x0 0x8ad00000 0x0 0x500000>;
 			no-map;
@@ -38,11 +36,6 @@
 			reg = <0x0 0x8b200000 0x0 0x500000>;
 			no-map;
 		};
-
-		wpss_mem: memory@9ae00000 {
-			reg = <0x0 0x9ae00000 0x0 0x1900000>;
-			no-map;
-		};
 	};
 };
 
@@ -94,9 +87,31 @@
 	};
 };
 
+/* Currently not used */
+&remoteproc_cdsp {
+	/delete-property/ memory-region;
+};
+
 &remoteproc_wpss {
-	status = "okay";
+	compatible = "qcom,sc7280-wpss-pil";
+	clocks = <&gcc GCC_WPSS_AHB_BDG_MST_CLK>,
+		 <&gcc GCC_WPSS_AHB_CLK>,
+		 <&gcc GCC_WPSS_RSCP_CLK>,
+		 <&rpmhcc RPMH_CXO_CLK>;
+	clock-names = "ahb_bdg",
+		      "ahb",
+		      "rscp",
+		      "xo";
+
+	resets = <&aoss_reset AOSS_CC_WCSS_RESTART>,
+		 <&pdc_reset PDC_WPSS_SYNC_RESET>;
+	reset-names = "restart", "pdc_sync";
+
+	qcom,halt-regs = <&tcsr_1 0x17000>;
+
 	firmware-name = "ath11k/WCN6750/hw1.0/wpss.mdt";
+
+	status = "okay";
 };
 
 &scm {
diff --git a/arch/arm64/boot/dts/qcom/sc7280-herobrine-lte-sku.dtsi b/arch/arm64/boot/dts/qcom/sc7280-herobrine-lte-sku.dtsi
index 95505549adcc..b721a8546800 100644
--- a/arch/arm64/boot/dts/qcom/sc7280-herobrine-lte-sku.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7280-herobrine-lte-sku.dtsi
@@ -8,11 +8,6 @@
 
 / {
 	reserved-memory {
-		mpss_mem: memory@8b800000 {
-			reg = <0x0 0x8b800000 0x0 0xf600000>;
-			no-map;
-		};
-
 		mba_mem: memory@9c700000 {
 			reg = <0x0 0x9c700000 0x0 0x200000>;
 			no-map;
@@ -33,6 +28,8 @@
 
 &remoteproc_mpss {
 	compatible = "qcom,sc7280-mss-pil";
+	reg = <0 0x04080000 0 0x10000>, <0 0x04180000 0 0x48>;
+	reg-names = "qdsp6", "rmb";
 
 	clocks = <&gcc GCC_MSS_CFG_AHB_CLK>,
 		 <&gcc GCC_MSS_OFFLINE_AXI_CLK>,
diff --git a/arch/arm64/boot/dts/qcom/sc7280-herobrine-wifi-sku.dtsi b/arch/arm64/boot/dts/qcom/sc7280-herobrine-wifi-sku.dtsi
index 2febd6126d4c..3ebc915f0dc2 100644
--- a/arch/arm64/boot/dts/qcom/sc7280-herobrine-wifi-sku.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7280-herobrine-wifi-sku.dtsi
@@ -7,5 +7,6 @@
 
 /* WIFI SKUs save 256M by not having modem/mba/rmtfs memory regions defined. */
 
+/delete-node/ &mpss_mem;
 /delete-node/ &remoteproc_mpss;
 /delete-node/ &rmtfs_mem;
diff --git a/arch/arm64/boot/dts/qcom/sc7280-idp.dtsi b/arch/arm64/boot/dts/qcom/sc7280-idp.dtsi
index 2ff549f4dc7a..a0059527d9e4 100644
--- a/arch/arm64/boot/dts/qcom/sc7280-idp.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7280-idp.dtsi
@@ -499,6 +499,25 @@
 	status = "okay";
 };
 
+&ufs_mem_hc {
+	reset-gpios = <&tlmm 175 GPIO_ACTIVE_LOW>;
+	vcc-supply = <&vreg_l7b_2p9>;
+	vcc-max-microamp = <800000>;
+	vccq-supply = <&vreg_l9b_1p2>;
+	vccq-max-microamp = <900000>;
+	vccq2-supply = <&vreg_l9b_1p2>;
+	vccq2-max-microamp = <900000>;
+
+	status = "okay";
+};
+
+&ufs_mem_phy {
+	vdda-phy-supply = <&vreg_l10c_0p8>;
+	vdda-pll-supply = <&vreg_l6b_1p2>;
+
+	status = "okay";
+};
+
 &usb_1 {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/qcom/sc7280.dtsi b/arch/arm64/boot/dts/qcom/sc7280.dtsi
index 66f1eb83cca7..83b5b76ba179 100644
--- a/arch/arm64/boot/dts/qcom/sc7280.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7280.dtsi
@@ -15,6 +15,7 @@
 #include <dt-bindings/dma/qcom-gpi.h>
 #include <dt-bindings/firmware/qcom,scm.h>
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interconnect/qcom,icc.h>
 #include <dt-bindings/interconnect/qcom,osm-l3.h>
 #include <dt-bindings/interconnect/qcom,sc7280.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
@@ -91,68 +92,93 @@
 		#size-cells = <2>;
 		ranges;
 
-		wlan_ce_mem: memory@4cd000 {
+		wlan_ce_mem: wlan-ce@4cd000 {
 			no-map;
 			reg = <0x0 0x004cd000 0x0 0x1000>;
 		};
 
-		hyp_mem: memory@80000000 {
+		hyp_mem: hyp@80000000 {
 			reg = <0x0 0x80000000 0x0 0x600000>;
 			no-map;
 		};
 
-		xbl_mem: memory@80600000 {
+		xbl_mem: xbl@80600000 {
 			reg = <0x0 0x80600000 0x0 0x200000>;
 			no-map;
 		};
 
-		aop_mem: memory@80800000 {
+		aop_mem: aop@80800000 {
 			reg = <0x0 0x80800000 0x0 0x60000>;
 			no-map;
 		};
 
-		aop_cmd_db_mem: memory@80860000 {
+		aop_cmd_db_mem: aop-cmd-db@80860000 {
 			reg = <0x0 0x80860000 0x0 0x20000>;
 			compatible = "qcom,cmd-db";
 			no-map;
 		};
 
-		reserved_xbl_uefi_log: memory@80880000 {
+		reserved_xbl_uefi_log: xbl-uefi-res@80880000 {
 			reg = <0x0 0x80884000 0x0 0x10000>;
 			no-map;
 		};
 
-		sec_apps_mem: memory@808ff000 {
+		sec_apps_mem: sec-apps@808ff000 {
 			reg = <0x0 0x808ff000 0x0 0x1000>;
 			no-map;
 		};
 
-		smem_mem: memory@80900000 {
+		smem_mem: smem@80900000 {
 			reg = <0x0 0x80900000 0x0 0x200000>;
 			no-map;
 		};
 
-		cpucp_mem: memory@80b00000 {
+		cpucp_mem: cpucp@80b00000 {
 			no-map;
 			reg = <0x0 0x80b00000 0x0 0x100000>;
 		};
 
-		wlan_fw_mem: memory@80c00000 {
+		wlan_fw_mem: wlan-fw@80c00000 {
 			reg = <0x0 0x80c00000 0x0 0xc00000>;
 			no-map;
 		};
 
-		video_mem: memory@8b200000 {
+		adsp_mem: adsp@86700000 {
+			reg = <0x0 0x86700000 0x0 0x2800000>;
+			no-map;
+		};
+
+		video_mem: video@8b200000 {
 			reg = <0x0 0x8b200000 0x0 0x500000>;
 			no-map;
 		};
 
-		ipa_fw_mem: memory@8b700000 {
+		cdsp_mem: cdsp@88f00000 {
+			reg = <0x0 0x88f00000 0x0 0x1e00000>;
+			no-map;
+		};
+
+		ipa_fw_mem: ipa-fw@8b700000 {
 			reg = <0 0x8b700000 0 0x10000>;
 			no-map;
 		};
 
-		rmtfs_mem: memory@9c900000 {
+		gpu_zap_mem: zap@8b71a000 {
+			reg = <0 0x8b71a000 0 0x2000>;
+			no-map;
+		};
+
+		mpss_mem: mpss@8b800000 {
+			reg = <0x0 0x8b800000 0x0 0xf600000>;
+			no-map;
+		};
+
+		wpss_mem: wpss@9ae00000 {
+			reg = <0x0 0x9ae00000 0x0 0x1900000>;
+			no-map;
+		};
+
+		rmtfs_mem: rmtfs@9c900000 {
 			compatible = "qcom,rmtfs-mem";
 			reg = <0x0 0x9c900000 0x0 0x280000>;
 			no-map;
@@ -906,7 +932,7 @@
 			clocks = <&rpmhcc RPMH_CXO_CLK>,
 				 <&rpmhcc RPMH_CXO_CLK_A>, <&sleep_clk>,
 				 <0>, <&pcie1_phy>,
-				 <0>, <0>, <0>,
+				 <&ufs_mem_phy 0>, <&ufs_mem_phy 1>, <&ufs_mem_phy 2>,
 				 <&usb_1_qmpphy QMP_USB43DP_USB3_PIPE_CLK>;
 			clock-names = "bi_tcxo", "bi_tcxo_ao", "sleep_clk",
 				      "pcie_0_pipe_clk", "pcie_1_pipe_clk",
@@ -974,6 +1000,7 @@
 
 			bus-width = <8>;
 			supports-cqe;
+			dma-coherent;
 
 			qcom,dll-config = <0x0007642c>;
 			qcom,ddr-config = <0x80040868>;
@@ -2034,6 +2061,11 @@
 			};
 		};
 
+		rng: rng@10d3000 {
+			compatible = "qcom,sc7280-trng", "qcom,trng";
+			reg = <0 0x010d3000 0 0x1000>;
+		};
+
 		cnoc2: interconnect@1500000 {
 			reg = <0 0x01500000 0 0x1000>;
 			compatible = "qcom,sc7280-cnoc2";
@@ -2126,7 +2158,7 @@
 			qcom,smem-state-names = "wlan-smp2p-out";
 		};
 
-		pcie1: pci@1c08000 {
+		pcie1: pcie@1c08000 {
 			compatible = "qcom,pcie-sc7280";
 			reg = <0 0x01c08000 0 0x3000>,
 			      <0 0x40000000 0 0xf1d>,
@@ -2233,6 +2265,99 @@
 			status = "disabled";
 		};
 
+		ufs_mem_hc: ufs@1d84000 {
+			compatible = "qcom,sc7280-ufshc", "qcom,ufshc",
+				     "jedec,ufs-2.0";
+			reg = <0x0 0x01d84000 0x0 0x3000>;
+			interrupts = <GIC_SPI 265 IRQ_TYPE_LEVEL_HIGH>;
+			phys = <&ufs_mem_phy>;
+			phy-names = "ufsphy";
+			lanes-per-direction = <2>;
+			#reset-cells = <1>;
+			resets = <&gcc GCC_UFS_PHY_BCR>;
+			reset-names = "rst";
+
+			power-domains = <&gcc GCC_UFS_PHY_GDSC>;
+			required-opps = <&rpmhpd_opp_nom>;
+
+			iommus = <&apps_smmu 0x80 0x0>;
+			dma-coherent;
+
+			interconnects = <&aggre1_noc MASTER_UFS_MEM QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
+					<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+					 &cnoc2 SLAVE_UFS_MEM_CFG QCOM_ICC_TAG_ALWAYS>;
+			interconnect-names = "ufs-ddr", "cpu-ufs";
+
+			clocks = <&gcc GCC_UFS_PHY_AXI_CLK>,
+				 <&gcc GCC_AGGRE_UFS_PHY_AXI_CLK>,
+				 <&gcc GCC_UFS_PHY_AHB_CLK>,
+				 <&gcc GCC_UFS_PHY_UNIPRO_CORE_CLK>,
+				 <&rpmhcc RPMH_CXO_CLK>,
+				 <&gcc GCC_UFS_PHY_TX_SYMBOL_0_CLK>,
+				 <&gcc GCC_UFS_PHY_RX_SYMBOL_0_CLK>,
+				 <&gcc GCC_UFS_PHY_RX_SYMBOL_1_CLK>;
+			clock-names = "core_clk",
+				      "bus_aggr_clk",
+				      "iface_clk",
+				      "core_clk_unipro",
+				      "ref_clk",
+				      "tx_lane0_sync_clk",
+				      "rx_lane0_sync_clk",
+				      "rx_lane1_sync_clk";
+			freq-table-hz =
+				<75000000 300000000>,
+				<0 0>,
+				<0 0>,
+				<75000000 300000000>,
+				<0 0>,
+				<0 0>,
+				<0 0>,
+				<0 0>;
+			status = "disabled";
+		};
+
+		ufs_mem_phy: phy@1d87000 {
+			compatible = "qcom,sc7280-qmp-ufs-phy";
+			reg = <0x0 0x01d87000 0x0 0xe00>;
+			clocks = <&rpmhcc RPMH_CXO_CLK>,
+				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>,
+				 <&gcc GCC_UFS_1_CLKREF_EN>;
+			clock-names = "ref", "ref_aux", "qref";
+
+			power-domains = <&rpmhpd SC7280_MX>;
+
+			resets = <&ufs_mem_hc 0>;
+			reset-names = "ufsphy";
+
+			#clock-cells = <1>;
+			#phy-cells = <0>;
+
+			status = "disabled";
+		};
+
+		cryptobam: dma-controller@1dc4000 {
+			compatible = "qcom,bam-v1.7.4", "qcom,bam-v1.7.0";
+			reg = <0x0 0x01dc4000 0x0 0x28000>;
+			interrupts = <GIC_SPI 272 IRQ_TYPE_LEVEL_HIGH>;
+			#dma-cells = <1>;
+			iommus = <&apps_smmu 0x4e4 0x0011>,
+				 <&apps_smmu 0x4e6 0x0011>;
+			qcom,ee = <0>;
+			qcom,controlled-remotely;
+		};
+
+		crypto: crypto@1dfa000 {
+			compatible = "qcom,sc7280-qce", "qcom,sm8150-qce", "qcom,qce";
+			reg = <0x0 0x01dfa000 0x0 0x6000>;
+			dmas = <&cryptobam 4>, <&cryptobam 5>;
+			dma-names = "rx", "tx";
+			iommus = <&apps_smmu 0x4e4 0x0011>,
+				 <&apps_smmu 0x4e4 0x0011>;
+			interconnects = <&aggre2_noc MASTER_CRYPTO 0 &mc_virt SLAVE_EBI1 0>;
+			interconnect-names = "memory";
+		};
+
 		ipa: ipa@1e40000 {
 			compatible = "qcom,sc7280-ipa";
 
@@ -2598,7 +2723,8 @@
 				    "cx_mem",
 				    "cx_dbgc";
 			interrupts = <GIC_SPI 300 IRQ_TYPE_LEVEL_HIGH>;
-			iommus = <&adreno_smmu 0 0x401>;
+			iommus = <&adreno_smmu 0 0x400>,
+				 <&adreno_smmu 1 0x400>;
 			operating-points-v2 = <&gpu_opp_table>;
 			qcom,gmu = <&gmu>;
 			interconnects = <&gem_noc MASTER_GFX3D 0 &mc_virt SLAVE_EBI1 0>;
@@ -2608,6 +2734,10 @@
 			nvmem-cells = <&gpu_speed_bin>;
 			nvmem-cell-names = "speed_bin";
 
+			gpu_zap_shader: zap-shader {
+				memory-region = <&gpu_zap_mem>;
+			};
+
 			gpu_opp_table: opp-table {
 				compatible = "operating-points-v2";
 
@@ -2615,14 +2745,14 @@
 					opp-hz = /bits/ 64 <315000000>;
 					opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS>;
 					opp-peak-kBps = <1804000>;
-					opp-supported-hw = <0x03>;
+					opp-supported-hw = <0x07>;
 				};
 
 				opp-450000000 {
 					opp-hz = /bits/ 64 <450000000>;
 					opp-level = <RPMH_REGULATOR_LEVEL_SVS>;
 					opp-peak-kBps = <4068000>;
-					opp-supported-hw = <0x03>;
+					opp-supported-hw = <0x07>;
 				};
 
 				/* Only applicable for SKUs which has 550Mhz as Fmax */
@@ -2637,28 +2767,28 @@
 					opp-hz = /bits/ 64 <550000000>;
 					opp-level = <RPMH_REGULATOR_LEVEL_SVS_L1>;
 					opp-peak-kBps = <6832000>;
-					opp-supported-hw = <0x02>;
+					opp-supported-hw = <0x06>;
 				};
 
 				opp-608000000 {
 					opp-hz = /bits/ 64 <608000000>;
 					opp-level = <RPMH_REGULATOR_LEVEL_SVS_L2>;
 					opp-peak-kBps = <8368000>;
-					opp-supported-hw = <0x02>;
+					opp-supported-hw = <0x06>;
 				};
 
 				opp-700000000 {
 					opp-hz = /bits/ 64 <700000000>;
 					opp-level = <RPMH_REGULATOR_LEVEL_NOM>;
 					opp-peak-kBps = <8532000>;
-					opp-supported-hw = <0x02>;
+					opp-supported-hw = <0x06>;
 				};
 
 				opp-812000000 {
 					opp-hz = /bits/ 64 <812000000>;
 					opp-level = <RPMH_REGULATOR_LEVEL_NOM_L1>;
 					opp-peak-kBps = <8532000>;
-					opp-supported-hw = <0x02>;
+					opp-supported-hw = <0x06>;
 				};
 
 				opp-840000000 {
@@ -2772,12 +2902,12 @@
 					"gpu_cc_hub_aon_clk";
 
 			power-domains = <&gpucc GPU_CC_CX_GDSC>;
+			dma-coherent;
 		};
 
 		remoteproc_mpss: remoteproc@4080000 {
 			compatible = "qcom,sc7280-mpss-pas";
-			reg = <0 0x04080000 0 0x10000>, <0 0x04180000 0 0x48>;
-			reg-names = "qdsp6", "rmb";
+			reg = <0 0x04080000 0 0x10000>;
 
 			interrupts-extended = <&intc GIC_SPI 264 IRQ_TYPE_EDGE_RISING>,
 					      <&modem_smp2p_in 0 IRQ_TYPE_EDGE_RISING>,
@@ -3329,6 +3459,7 @@
 			operating-points-v2 = <&sdhc2_opp_table>;
 
 			bus-width = <4>;
+			dma-coherent;
 
 			qcom,dll-config = <0x0007642c>;
 
@@ -3399,6 +3530,32 @@
 
 			#clock-cells = <1>;
 			#phy-cells = <1>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+
+					usb_dp_qmpphy_out: endpoint {
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+
+					usb_dp_qmpphy_usb_ss_in: endpoint {
+					};
+				};
+
+				port@2 {
+					reg = <2>;
+
+					usb_dp_qmpphy_dp_in: endpoint {
+					};
+				};
+			};
 		};
 
 		usb_2: usb@8cf8800 {
@@ -3426,8 +3583,8 @@
 			assigned-clock-rates = <19200000>, <200000000>;
 
 			interrupts-extended = <&intc GIC_SPI 240 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc 12 IRQ_TYPE_EDGE_RISING>,
-					      <&pdc 13 IRQ_TYPE_EDGE_RISING>;
+					      <&pdc 12 IRQ_TYPE_EDGE_BOTH>,
+					      <&pdc 13 IRQ_TYPE_EDGE_BOTH>;
 			interrupt-names = "hs_phy_irq",
 					  "dp_hs_phy_irq",
 					  "dm_hs_phy_irq";
@@ -3479,8 +3636,77 @@
 			status = "disabled";
 		};
 
+		remoteproc_adsp: remoteproc@3700000 {
+			compatible = "qcom,sc7280-adsp-pas";
+			reg = <0 0x03700000 0 0x100>;
+
+			interrupts-extended = <&pdc 6 IRQ_TYPE_LEVEL_HIGH>,
+					      <&adsp_smp2p_in 0 IRQ_TYPE_EDGE_RISING>,
+					      <&adsp_smp2p_in 1 IRQ_TYPE_EDGE_RISING>,
+					      <&adsp_smp2p_in 2 IRQ_TYPE_EDGE_RISING>,
+					      <&adsp_smp2p_in 3 IRQ_TYPE_EDGE_RISING>,
+					      <&adsp_smp2p_in 7 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "wdog", "fatal", "ready", "handover",
+					  "stop-ack", "shutdown-ack";
+
+			clocks = <&rpmhcc RPMH_CXO_CLK>;
+			clock-names = "xo";
+
+			power-domains = <&rpmhpd SC7280_LCX>,
+					<&rpmhpd SC7280_LMX>;
+			power-domain-names = "lcx", "lmx";
+
+			memory-region = <&adsp_mem>;
+
+			qcom,qmp = <&aoss_qmp>;
+
+			qcom,smem-states = <&adsp_smp2p_out 0>;
+			qcom,smem-state-names = "stop";
+
+			status = "disabled";
+
+			glink-edge {
+				interrupts-extended = <&ipcc IPCC_CLIENT_LPASS
+							     IPCC_MPROC_SIGNAL_GLINK_QMP
+							     IRQ_TYPE_EDGE_RISING>;
+
+				mboxes = <&ipcc IPCC_CLIENT_LPASS
+						IPCC_MPROC_SIGNAL_GLINK_QMP>;
+
+				label = "lpass";
+				qcom,remote-pid = <2>;
+
+				fastrpc {
+					compatible = "qcom,fastrpc";
+					qcom,glink-channels = "fastrpcglink-apps-dsp";
+					label = "adsp";
+					qcom,non-secure-domain;
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					compute-cb@3 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <3>;
+						iommus = <&apps_smmu 0x1803 0x0>;
+					};
+
+					compute-cb@4 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <4>;
+						iommus = <&apps_smmu 0x1804 0x0>;
+					};
+
+					compute-cb@5 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <5>;
+						iommus = <&apps_smmu 0x1805 0x0>;
+					};
+				};
+			};
+		};
+
 		remoteproc_wpss: remoteproc@8a00000 {
-			compatible = "qcom,sc7280-wpss-pil";
+			compatible = "qcom,sc7280-wpss-pas";
 			reg = <0 0x08a00000 0 0x10000>;
 
 			interrupts-extended = <&intc GIC_SPI 587 IRQ_TYPE_EDGE_RISING>,
@@ -3492,12 +3718,8 @@
 			interrupt-names = "wdog", "fatal", "ready", "handover",
 					  "stop-ack", "shutdown-ack";
 
-			clocks = <&gcc GCC_WPSS_AHB_BDG_MST_CLK>,
-				 <&gcc GCC_WPSS_AHB_CLK>,
-				 <&gcc GCC_WPSS_RSCP_CLK>,
-				 <&rpmhcc RPMH_CXO_CLK>;
-			clock-names = "ahb_bdg", "ahb",
-				      "rscp", "xo";
+			clocks = <&rpmhcc RPMH_CXO_CLK>;
+			clock-names = "xo";
 
 			power-domains = <&rpmhpd SC7280_CX>,
 					<&rpmhpd SC7280_MX>;
@@ -3510,11 +3732,6 @@
 			qcom,smem-states = <&wpss_smp2p_out 0>;
 			qcom,smem-state-names = "stop";
 
-			resets = <&aoss_reset AOSS_CC_WCSS_RESTART>,
-				 <&pdc_reset PDC_WPSS_SYNC_RESET>;
-			reset-names = "restart", "pdc_sync";
-
-			qcom,halt-regs = <&tcsr_1 0x17000>;
 
 			status = "disabled";
 
@@ -3656,6 +3873,144 @@
 			qcom,bcm-voters = <&apps_bcm_voter>;
 		};
 
+		remoteproc_cdsp: remoteproc@a300000 {
+			compatible = "qcom,sc7280-cdsp-pas";
+			reg = <0 0x0a300000 0 0x10000>;
+
+			interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_LEVEL_HIGH>,
+					      <&cdsp_smp2p_in 0 IRQ_TYPE_EDGE_RISING>,
+					      <&cdsp_smp2p_in 1 IRQ_TYPE_EDGE_RISING>,
+					      <&cdsp_smp2p_in 2 IRQ_TYPE_EDGE_RISING>,
+					      <&cdsp_smp2p_in 3 IRQ_TYPE_EDGE_RISING>,
+					      <&cdsp_smp2p_in 7 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "wdog", "fatal", "ready", "handover",
+					  "stop-ack", "shutdown-ack";
+
+			clocks = <&rpmhcc RPMH_CXO_CLK>;
+			clock-names = "xo";
+
+			power-domains = <&rpmhpd SC7280_CX>,
+					<&rpmhpd SC7280_MX>;
+			power-domain-names = "cx", "mx";
+
+			interconnects = <&nsp_noc MASTER_CDSP_PROC 0 &mc_virt SLAVE_EBI1 0>;
+
+			memory-region = <&cdsp_mem>;
+
+			qcom,qmp = <&aoss_qmp>;
+
+			qcom,smem-states = <&cdsp_smp2p_out 0>;
+			qcom,smem-state-names = "stop";
+
+			status = "disabled";
+
+			glink-edge {
+				interrupts-extended = <&ipcc IPCC_CLIENT_CDSP
+							     IPCC_MPROC_SIGNAL_GLINK_QMP
+							     IRQ_TYPE_EDGE_RISING>;
+				mboxes = <&ipcc IPCC_CLIENT_CDSP
+						IPCC_MPROC_SIGNAL_GLINK_QMP>;
+
+				label = "cdsp";
+				qcom,remote-pid = <5>;
+
+				fastrpc {
+					compatible = "qcom,fastrpc";
+					qcom,glink-channels = "fastrpcglink-apps-dsp";
+					label = "cdsp";
+					qcom,non-secure-domain;
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					compute-cb@1 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <1>;
+						iommus = <&apps_smmu 0x11a1 0x0420>,
+							 <&apps_smmu 0x1181 0x0420>;
+					};
+
+					compute-cb@2 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <2>;
+						iommus = <&apps_smmu 0x11a2 0x0420>,
+							 <&apps_smmu 0x1182 0x0420>;
+					};
+
+					compute-cb@3 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <3>;
+						iommus = <&apps_smmu 0x11a3 0x0420>,
+							 <&apps_smmu 0x1183 0x0420>;
+					};
+
+					compute-cb@4 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <4>;
+						iommus = <&apps_smmu 0x11a4 0x0420>,
+							 <&apps_smmu 0x1184 0x0420>;
+					};
+
+					compute-cb@5 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <5>;
+						iommus = <&apps_smmu 0x11a5 0x0420>,
+							 <&apps_smmu 0x1185 0x0420>;
+					};
+
+					compute-cb@6 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <6>;
+						iommus = <&apps_smmu 0x11a6 0x0420>,
+							 <&apps_smmu 0x1186 0x0420>;
+					};
+
+					compute-cb@7 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <7>;
+						iommus = <&apps_smmu 0x11a7 0x0420>,
+							 <&apps_smmu 0x1187 0x0420>;
+					};
+
+					compute-cb@8 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <8>;
+						iommus = <&apps_smmu 0x11a8 0x0420>,
+							 <&apps_smmu 0x1188 0x0420>;
+					};
+
+					/* note: secure cb9 in downstream */
+
+					compute-cb@11 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <11>;
+						iommus = <&apps_smmu 0x11ab 0x0420>,
+							 <&apps_smmu 0x118b 0x0420>;
+					};
+
+					compute-cb@12 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <12>;
+						iommus = <&apps_smmu 0x11ac 0x0420>,
+							 <&apps_smmu 0x118c 0x0420>;
+					};
+
+					compute-cb@13 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <13>;
+						iommus = <&apps_smmu 0x11ad 0x0420>,
+							 <&apps_smmu 0x118d 0x0420>;
+					};
+
+					compute-cb@14 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <14>;
+						iommus = <&apps_smmu 0x11ae 0x0420>,
+							 <&apps_smmu 0x118e 0x0420>;
+					};
+				};
+			};
+		};
+
 		usb_1: usb@a6f8800 {
 			compatible = "qcom,sc7280-dwc3", "qcom,dwc3";
 			reg = <0 0x0a6f8800 0 0x400>;
@@ -3681,9 +4036,9 @@
 			assigned-clock-rates = <19200000>, <200000000>;
 
 			interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc 14 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 14 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 15 IRQ_TYPE_EDGE_BOTH>,
-					      <&pdc 17 IRQ_TYPE_EDGE_BOTH>;
+					      <&pdc 17 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "hs_phy_irq",
 					  "dp_hs_phy_irq",
 					  "dm_hs_phy_irq",
@@ -3793,6 +4148,86 @@
 			#power-domain-cells = <1>;
 		};
 
+		cci0: cci@ac4a000 {
+			compatible = "qcom,sc7280-cci", "qcom,msm8996-cci";
+			reg = <0 0x0ac4a000 0 0x1000>;
+			interrupts = <GIC_SPI 460 IRQ_TYPE_EDGE_RISING>;
+			power-domains = <&camcc CAM_CC_TITAN_TOP_GDSC>;
+
+			clocks = <&camcc CAM_CC_CAMNOC_AXI_CLK>,
+				 <&camcc CAM_CC_SLOW_AHB_CLK_SRC>,
+				 <&camcc CAM_CC_CPAS_AHB_CLK>,
+				 <&camcc CAM_CC_CCI_0_CLK>,
+				 <&camcc CAM_CC_CCI_0_CLK_SRC>;
+			clock-names = "camnoc_axi",
+				      "slow_ahb_src",
+				      "cpas_ahb",
+				      "cci",
+				      "cci_src";
+			pinctrl-0 = <&cci0_default &cci1_default>;
+			pinctrl-1 = <&cci0_sleep &cci1_sleep>;
+			pinctrl-names = "default", "sleep";
+
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			status = "disabled";
+
+			cci0_i2c0: i2c-bus@0 {
+				reg = <0>;
+				clock-frequency = <1000000>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+
+			cci0_i2c1: i2c-bus@1 {
+				reg = <1>;
+				clock-frequency = <1000000>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+		};
+
+		cci1: cci@ac4b000 {
+			compatible = "qcom,sc7280-cci", "qcom,msm8996-cci";
+			reg = <0 0x0ac4b000 0 0x1000>;
+			interrupts = <GIC_SPI 271 IRQ_TYPE_EDGE_RISING>;
+			power-domains = <&camcc CAM_CC_TITAN_TOP_GDSC>;
+
+			clocks = <&camcc CAM_CC_CAMNOC_AXI_CLK>,
+				 <&camcc CAM_CC_SLOW_AHB_CLK_SRC>,
+				 <&camcc CAM_CC_CPAS_AHB_CLK>,
+				 <&camcc CAM_CC_CCI_1_CLK>,
+				 <&camcc CAM_CC_CCI_1_CLK_SRC>;
+			clock-names = "camnoc_axi",
+				      "slow_ahb_src",
+				      "cpas_ahb",
+				      "cci",
+				      "cci_src";
+			pinctrl-0 = <&cci2_default &cci3_default>;
+			pinctrl-1 = <&cci2_sleep &cci3_sleep>;
+			pinctrl-names = "default", "sleep";
+
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			status = "disabled";
+
+			cci1_i2c0: i2c-bus@0 {
+				reg = <0>;
+				clock-frequency = <1000000>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+
+			cci1_i2c1: i2c-bus@1 {
+				reg = <1>;
+				clock-frequency = <1000000>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+		};
+
 		camcc: clock-controller@ad00000 {
 			compatible = "qcom,sc7280-camcc";
 			reg = <0 0x0ad00000 0 0x10000>;
@@ -3847,8 +4282,12 @@
 			interrupt-controller;
 			#interrupt-cells = <1>;
 
-			interconnects = <&mmss_noc MASTER_MDP0 0 &mc_virt SLAVE_EBI1 0>;
-			interconnect-names = "mdp0-mem";
+			interconnects = <&mmss_noc MASTER_MDP0 QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
+					<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+					 &cnoc2 SLAVE_DISPLAY_CFG QCOM_ICC_TAG_ALWAYS>;
+			interconnect-names = "mdp0-mem",
+					     "cpu-cfg";
 
 			iommus = <&apps_smmu 0x900 0x402>;
 
@@ -4298,6 +4737,62 @@
 			gpio-ranges = <&tlmm 0 0 175>;
 			wakeup-parent = <&pdc>;
 
+			cci0_default: cci0-default-state {
+				pins = "gpio69", "gpio70";
+				function = "cci_i2c";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			cci0_sleep: cci0-sleep-state {
+				pins = "gpio69", "gpio70";
+				function = "cci_i2c";
+				drive-strength = <2>;
+				bias-pull-down;
+			};
+
+			cci1_default: cci1-default-state {
+				pins = "gpio71", "gpio72";
+				function = "cci_i2c";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			cci1_sleep: cci1-sleep-state {
+				pins = "gpio71", "gpio72";
+				function = "cci_i2c";
+				drive-strength = <2>;
+				bias-pull-down;
+			};
+
+			cci2_default: cci2-default-state {
+				pins = "gpio73", "gpio74";
+				function = "cci_i2c";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			cci2_sleep: cci2-sleep-state {
+				pins = "gpio73", "gpio74";
+				function = "cci_i2c";
+				drive-strength = <2>;
+				bias-pull-down;
+			};
+
+			cci3_default: cci3-default-state {
+				pins = "gpio75", "gpio76";
+				function = "cci_i2c";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			cci3_sleep: cci3-sleep-state {
+				pins = "gpio75", "gpio76";
+				function = "cci_i2c";
+				drive-strength = <2>;
+				bias-pull-down;
+			};
+
 			dp_hot_plug_det: dp-hot-plug-det-state {
 				pins = "gpio47";
 				function = "dp_hot";
@@ -5222,7 +5717,7 @@
 			compatible = "qcom,apss-wdt-sc7280", "qcom,kpss-wdt";
 			reg = <0 0x17c10000 0 0x1000>;
 			clocks = <&sleep_clk>;
-			interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 0 IRQ_TYPE_EDGE_RISING>;
 			status = "reserved"; /* Owned by Gunyah hyp */
 		};
 
diff --git a/arch/arm64/boot/dts/qcom/sc8180x-lenovo-flex-5g.dts b/arch/arm64/boot/dts/qcom/sc8180x-lenovo-flex-5g.dts
index 3ea07d094b60..0c22f3efec20 100644
--- a/arch/arm64/boot/dts/qcom/sc8180x-lenovo-flex-5g.dts
+++ b/arch/arm64/boot/dts/qcom/sc8180x-lenovo-flex-5g.dts
@@ -452,8 +452,8 @@
 };
 
 &pcie3 {
-	perst-gpio = <&tlmm 178 GPIO_ACTIVE_LOW>;
-	wake-gpio = <&tlmm 180 GPIO_ACTIVE_HIGH>;
+	perst-gpios = <&tlmm 178 GPIO_ACTIVE_LOW>;
+	wake-gpios = <&tlmm 180 GPIO_ACTIVE_HIGH>;
 	pinctrl-0 = <&pcie3_default_state>;
 	pinctrl-names = "default";
 
diff --git a/arch/arm64/boot/dts/qcom/sc8180x-primus.dts b/arch/arm64/boot/dts/qcom/sc8180x-primus.dts
index fd2fab4895b3..bfee60c93ccc 100644
--- a/arch/arm64/boot/dts/qcom/sc8180x-primus.dts
+++ b/arch/arm64/boot/dts/qcom/sc8180x-primus.dts
@@ -43,7 +43,7 @@
 		pinctrl-0 = <&hall_int_active_state>;
 
 		lid-switch {
-			gpios = <&tlmm 121 GPIO_ACTIVE_HIGH>;
+			gpios = <&tlmm 121 GPIO_ACTIVE_LOW>;
 			linux,input-type = <EV_SW>;
 			linux,code = <SW_LID>;
 			wakeup-source;
@@ -386,12 +386,18 @@
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
 			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
 		};
 
 		vreg_l10e_2p9: ldo10 {
 			regulator-min-microvolt = <2904000>;
 			regulator-max-microvolt = <2904000>;
 			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
 		};
 
 		vreg_l12e: ldo12 {
@@ -531,8 +537,8 @@
 };
 
 &pcie1 {
-	perst-gpio = <&tlmm 175 GPIO_ACTIVE_LOW>;
-	wake-gpio = <&tlmm 177 GPIO_ACTIVE_HIGH>;
+	perst-gpios = <&tlmm 175 GPIO_ACTIVE_LOW>;
+	wake-gpios = <&tlmm 177 GPIO_ACTIVE_HIGH>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pcie2_default_state>;
 
diff --git a/arch/arm64/boot/dts/qcom/sc8180x.dtsi b/arch/arm64/boot/dts/qcom/sc8180x.dtsi
index a34f438ef2d9..0430d99091e3 100644
--- a/arch/arm64/boot/dts/qcom/sc8180x.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc8180x.dtsi
@@ -8,6 +8,7 @@
 #include <dt-bindings/clock/qcom,gcc-sc8180x.h>
 #include <dt-bindings/clock/qcom,gpucc-sm8150.h>
 #include <dt-bindings/clock/qcom,rpmh.h>
+#include <dt-bindings/interconnect/qcom,icc.h>
 #include <dt-bindings/interconnect/qcom,osm-l3.h>
 #include <dt-bindings/interconnect/qcom,sc8180x.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
@@ -1684,7 +1685,7 @@
 			qcom,bcm-voters = <&apps_bcm_voter>;
 		};
 
-		pcie0: pci@1c00000 {
+		pcie0: pcie@1c00000 {
 			compatible = "qcom,pcie-sc8180x";
 			reg = <0 0x01c00000 0 0x3000>,
 			      <0 0x60000000 0 0xf1d>,
@@ -1736,7 +1737,6 @@
 			assigned-clocks = <&gcc GCC_PCIE_0_AUX_CLK>;
 			assigned-clock-rates = <19200000>;
 
-			iommus = <&apps_smmu 0x1d80 0x7f>;
 			iommu-map = <0x0   &apps_smmu 0x1d80 0x1>,
 				    <0x100 &apps_smmu 0x1d81 0x1>;
 
@@ -1751,6 +1751,7 @@
 
 			phys = <&pcie0_phy>;
 			phy-names = "pciephy";
+			dma-coherent;
 
 			status = "disabled";
 		};
@@ -1761,7 +1762,7 @@
 			clocks = <&gcc GCC_PCIE_PHY_AUX_CLK>,
 				 <&gcc GCC_PCIE_0_CFG_AHB_CLK>,
 				 <&gcc GCC_PCIE_0_CLKREF_CLK>,
-				 <&gcc GCC_PCIE1_PHY_REFGEN_CLK>,
+				 <&gcc GCC_PCIE0_PHY_REFGEN_CLK>,
 				 <&gcc GCC_PCIE_0_PIPE_CLK>;
 			clock-names = "aux",
 				      "cfg_ahb",
@@ -1781,7 +1782,7 @@
 			status = "disabled";
 		};
 
-		pcie3: pci@1c08000 {
+		pcie3: pcie@1c08000 {
 			compatible = "qcom,pcie-sc8180x";
 			reg = <0 0x01c08000 0 0x3000>,
 			      <0 0x40000000 0 0xf1d>,
@@ -1833,7 +1834,6 @@
 			assigned-clocks = <&gcc GCC_PCIE_3_AUX_CLK>;
 			assigned-clock-rates = <19200000>;
 
-			iommus = <&apps_smmu 0x1e00 0x7f>;
 			iommu-map = <0x0   &apps_smmu 0x1e00 0x1>,
 				    <0x100 &apps_smmu 0x1e01 0x1>;
 
@@ -1848,6 +1848,7 @@
 
 			phys = <&pcie3_phy>;
 			phy-names = "pciephy";
+			dma-coherent;
 
 			status = "disabled";
 		};
@@ -1858,7 +1859,7 @@
 			clocks = <&gcc GCC_PCIE_PHY_AUX_CLK>,
 				 <&gcc GCC_PCIE_3_CFG_AHB_CLK>,
 				 <&gcc GCC_PCIE_3_CLKREF_CLK>,
-				 <&gcc GCC_PCIE2_PHY_REFGEN_CLK>,
+				 <&gcc GCC_PCIE3_PHY_REFGEN_CLK>,
 				 <&gcc GCC_PCIE_3_PIPE_CLK>;
 			clock-names = "aux",
 				      "cfg_ahb",
@@ -1879,7 +1880,7 @@
 			status = "disabled";
 		};
 
-		pcie1: pci@1c10000 {
+		pcie1: pcie@1c10000 {
 			compatible = "qcom,pcie-sc8180x";
 			reg = <0 0x01c10000 0 0x3000>,
 			      <0 0x68000000 0 0xf1d>,
@@ -1931,7 +1932,6 @@
 			assigned-clocks = <&gcc GCC_PCIE_1_AUX_CLK>;
 			assigned-clock-rates = <19200000>;
 
-			iommus = <&apps_smmu 0x1c80 0x7f>;
 			iommu-map = <0x0   &apps_smmu 0x1c80 0x1>,
 				    <0x100 &apps_smmu 0x1c81 0x1>;
 
@@ -1946,6 +1946,7 @@
 
 			phys = <&pcie1_phy>;
 			phy-names = "pciephy";
+			dma-coherent;
 
 			status = "disabled";
 		};
@@ -1977,7 +1978,7 @@
 			status = "disabled";
 		};
 
-		pcie2: pci@1c18000 {
+		pcie2: pcie@1c18000 {
 			compatible = "qcom,pcie-sc8180x";
 			reg = <0 0x01c18000 0 0x3000>,
 			      <0 0x70000000 0 0xf1d>,
@@ -2029,7 +2030,6 @@
 			assigned-clocks = <&gcc GCC_PCIE_2_AUX_CLK>;
 			assigned-clock-rates = <19200000>;
 
-			iommus = <&apps_smmu 0x1d00 0x7f>;
 			iommu-map = <0x0   &apps_smmu 0x1d00 0x1>,
 				    <0x100 &apps_smmu 0x1d01 0x1>;
 
@@ -2044,6 +2044,7 @@
 
 			phys = <&pcie2_phy>;
 			phy-names = "pciephy";
+			dma-coherent;
 
 			status = "disabled";
 		};
@@ -2062,7 +2063,7 @@
 				      "refgen",
 				      "pipe";
 			#clock-cells = <0>;
-			clock-output-names = "pcie_3_pipe_clk";
+			clock-output-names = "pcie_2_pipe_clk";
 
 			#phy-cells = <0>;
 
@@ -2114,6 +2115,14 @@
 					<0 0>,
 					<0 0>;
 
+			power-domains = <&gcc UFS_PHY_GDSC>;
+
+			interconnects = <&aggre1_noc MASTER_UFS_MEM QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI_CH0 QCOM_ICC_TAG_ALWAYS>,
+					<&gem_noc MASTER_AMPSS_M0 QCOM_ICC_TAG_ALWAYS
+					 &config_noc SLAVE_UFS_MEM_0_CFG QCOM_ICC_TAG_ALWAYS>;
+			interconnect-names = "ufs-ddr", "cpu-ufs";
+
 			status = "disabled";
 		};
 
@@ -2548,10 +2557,10 @@
 		usb_prim: usb@a6f8800 {
 			compatible = "qcom,sc8180x-dwc3", "qcom,dwc3";
 			reg = <0 0x0a6f8800 0 0x400>;
-			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 486 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 488 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 489 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 6 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 8 IRQ_TYPE_EDGE_BOTH>,
+					      <&pdc 9 IRQ_TYPE_EDGE_BOTH>;
 			interrupt-names = "hs_phy_irq",
 					  "ss_phy_irq",
 					  "dm_hs_phy_irq",
@@ -2622,10 +2631,10 @@
 				      "xo";
 			resets = <&gcc GCC_USB30_SEC_BCR>;
 			power-domains = <&gcc USB30_SEC_GDSC>;
-			interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 487 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 490 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 491 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts-extended = <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 7 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 10 IRQ_TYPE_EDGE_BOTH>,
+					      <&pdc 11 IRQ_TYPE_EDGE_BOTH>;
 			interrupt-names = "hs_phy_irq", "ss_phy_irq",
 					  "dm_hs_phy_irq", "dp_hs_phy_irq";
 
@@ -2704,11 +2713,15 @@
 				clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
 					 <&gcc GCC_DISP_HF_AXI_CLK>,
 					 <&dispcc DISP_CC_MDSS_MDP_CLK>,
-					 <&dispcc DISP_CC_MDSS_VSYNC_CLK>;
+					 <&dispcc DISP_CC_MDSS_VSYNC_CLK>,
+					 <&dispcc DISP_CC_MDSS_ROT_CLK>,
+					 <&dispcc DISP_CC_MDSS_MDP_LUT_CLK>;
 				clock-names = "iface",
 					      "bus",
 					      "core",
-					      "vsync";
+					      "vsync",
+					      "rot",
+					      "lut";
 
 				assigned-clocks = <&dispcc DISP_CC_MDSS_MDP_CLK>,
 						  <&dispcc DISP_CC_MDSS_VSYNC_CLK>;
@@ -3117,8 +3130,6 @@
 				phys = <&edp_phy>;
 				phy-names = "dp";
 
-				#sound-dai-cells = <0>;
-
 				operating-points-v2 = <&edp_opp_table>;
 				power-domains = <&rpmhpd SC8180X_MMCX>;
 
@@ -3418,10 +3429,12 @@
 			reg = <0x0 0x17a00000 0x0 0x10000>,	/* GICD */
 			      <0x0 0x17a60000 0x0 0x100000>;	/* GICR * 8 */
 			interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH>;
+			#redistributor-regions = <1>;
+			redistributor-stride = <0 0x20000>;
 		};
 
 		apss_shared: mailbox@17c00000 {
-			compatible = "qcom,sc8180x-apss-shared";
+			compatible = "qcom,sc8180x-apss-shared", "qcom,sdm845-apss-shared";
 			reg = <0x0 0x17c00000 0x0 0x1000>;
 			#mbox-cells = <1>;
 		};
diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts b/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts
index e4861c61a65b..ffc4406422ae 100644
--- a/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts
+++ b/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts
@@ -458,6 +458,8 @@
 };
 
 &mdss0_dp3_phy {
+	compatible = "qcom,sc8280xp-edp-phy";
+
 	vdda-phy-supply = <&vreg_l6b>;
 	vdda-pll-supply = <&vreg_l3b>;
 
diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts
index 38edaf51aa34..def3976bd5bb 100644
--- a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts
+++ b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts
@@ -82,6 +82,9 @@
 	leds {
 		compatible = "gpio-leds";
 
+		pinctrl-names = "default";
+		pinctrl-0 = <&cam_indicator_en>;
+
 		led-camera-indicator {
 			label = "white:camera-indicator";
 			function = LED_FUNCTION_INDICATOR;
@@ -570,6 +573,7 @@
 
 &mdss0_dp3 {
 	compatible = "qcom,sc8280xp-edp";
+	/delete-property/ #sound-dai-cells;
 
 	data-lanes = <0 1 2 3>;
 
@@ -601,6 +605,7 @@
 };
 
 &mdss0_dp3_phy {
+	compatible = "qcom,sc8280xp-edp-phy";
 	vdda-phy-supply = <&vreg_l6b>;
 	vdda-pll-supply = <&vreg_l3b>;
 
@@ -1277,6 +1282,13 @@
 		};
 	};
 
+	cam_indicator_en: cam-indicator-en-state {
+		pins = "gpio28";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
 	edp_reg_en: edp-reg-en-state {
 		pins = "gpio25";
 		function = "gpio";
diff --git a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi
index cad59af7ccef..febf28356ff8 100644
--- a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi
@@ -8,6 +8,7 @@
 #include <dt-bindings/clock/qcom,gcc-sc8280xp.h>
 #include <dt-bindings/clock/qcom,gpucc-sc8280xp.h>
 #include <dt-bindings/clock/qcom,rpmh.h>
+#include <dt-bindings/clock/qcom,sc8280xp-camcc.h>
 #include <dt-bindings/clock/qcom,sc8280xp-lpasscc.h>
 #include <dt-bindings/interconnect/qcom,osm-l3.h>
 #include <dt-bindings/interconnect/qcom,sc8280xp.h>
@@ -2731,7 +2732,7 @@
 			status = "disabled";
 		};
 
-		swr1: soundwire-controller@3210000 {
+		swr1: soundwire@3210000 {
 			compatible = "qcom,soundwire-v1.6.0";
 			reg = <0 0x03210000 0 0x2000>;
 			interrupts = <GIC_SPI 155 IRQ_TYPE_LEVEL_HIGH>;
@@ -2807,7 +2808,7 @@
 			status = "disabled";
 		};
 
-		swr0: soundwire-controller@3250000 {
+		swr0: soundwire@3250000 {
 			reg = <0 0x03250000 0 0x2000>;
 			compatible = "qcom,soundwire-v1.6.0";
 			interrupts = <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>;
@@ -2844,7 +2845,7 @@
 			#reset-cells = <1>;
 		};
 
-		swr2: soundwire-controller@3330000 {
+		swr2: soundwire@3330000 {
 			compatible = "qcom,soundwire-v1.6.0";
 			reg = <0 0x03330000 0 0x2000>;
 			interrupts = <GIC_SPI 959 IRQ_TYPE_LEVEL_HIGH>,
@@ -3450,6 +3451,20 @@
 			};
 		};
 
+		camcc: clock-controller@ad00000 {
+			compatible = "qcom,sc8280xp-camcc";
+			reg = <0 0x0ad00000 0 0x20000>;
+			clocks = <&gcc GCC_CAMERA_AHB_CLK>,
+				 <&rpmhcc RPMH_CXO_CLK>,
+				 <&rpmhcc RPMH_CXO_CLK_A>,
+				 <&sleep_clk>;
+			power-domains = <&rpmhpd SC8280XP_MMCX>;
+			required-opps = <&rpmhpd_opp_low_svs>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+			#power-domain-cells = <1>;
+		};
+
 		mdss0: display-subsystem@ae00000 {
 			compatible = "qcom,sc8280xp-mdss";
 			reg = <0 0x0ae00000 0 0x1000>;
@@ -4030,6 +4045,7 @@
 		sram@c3f0000 {
 			compatible = "qcom,rpmh-stats";
 			reg = <0 0x0c3f0000 0 0x400>;
+			qcom,qmp = <&aoss_qmp>;
 		};
 
 		spmi_bus: spmi@c440000 {
@@ -4225,7 +4241,7 @@
 			compatible = "qcom,apss-wdt-sc8280xp", "qcom,kpss-wdt";
 			reg = <0 0x17c10000 0 0x1000>;
 			clocks = <&sleep_clk>;
-			interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 0 IRQ_TYPE_EDGE_RISING>;
 		};
 
 		timer@17c20000 {
diff --git a/arch/arm64/boot/dts/qcom/sdm632-fairphone-fp3.dts b/arch/arm64/boot/dts/qcom/sdm632-fairphone-fp3.dts
index 301eca9a4f31..057579ae3013 100644
--- a/arch/arm64/boot/dts/qcom/sdm632-fairphone-fp3.dts
+++ b/arch/arm64/boot/dts/qcom/sdm632-fairphone-fp3.dts
@@ -80,6 +80,10 @@
 	};
 };
 
+&lpass {
+	status = "okay";
+};
+
 &pm8953_resin {
 	status = "okay";
 	linux,code = <KEY_VOLUMEDOWN>;
@@ -239,3 +243,18 @@
 &usb3_dwc3 {
 	dr_mode = "peripheral";
 };
+
+&wcnss {
+	status = "okay";
+
+	vddpx-supply = <&pm8953_l5>;
+};
+
+&wcnss_iris {
+	compatible = "qcom,wcn3680";
+
+	vddxo-supply = <&pm8953_l7>;
+	vddrfa-supply = <&pm8953_l19>;
+	vddpa-supply = <&pm8953_l9>;
+	vdddig-supply = <&pm8953_l5>;
+};
diff --git a/arch/arm64/boot/dts/qcom/sdm670.dtsi b/arch/arm64/boot/dts/qcom/sdm670.dtsi
index ba2043d67370..4d7b77a23159 100644
--- a/arch/arm64/boot/dts/qcom/sdm670.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm670.dtsi
@@ -6,6 +6,7 @@
  * Copyright (c) 2022, Richard Acayan. All rights reserved.
  */
 
+#include <dt-bindings/clock/qcom,dispcc-sdm845.h>
 #include <dt-bindings/clock/qcom,gcc-sdm845.h>
 #include <dt-bindings/clock/qcom,rpmh.h>
 #include <dt-bindings/dma/qcom-gpi.h>
@@ -400,6 +401,30 @@
 		};
 	};
 
+	dsi_opp_table: opp-table-dsi {
+		compatible = "operating-points-v2";
+
+		opp-19200000 {
+			opp-hz = /bits/ 64 <19200000>;
+			required-opps = <&rpmhpd_opp_min_svs>;
+		};
+
+		opp-180000000 {
+			opp-hz = /bits/ 64 <180000000>;
+			required-opps = <&rpmhpd_opp_low_svs>;
+		};
+
+		opp-275000000 {
+			opp-hz = /bits/ 64 <275000000>;
+			required-opps = <&rpmhpd_opp_svs>;
+		};
+
+		opp-358000000 {
+			opp-hz = /bits/ 64 <358000000>;
+			required-opps = <&rpmhpd_opp_svs_l1>;
+		};
+	};
+
 	psci {
 		compatible = "arm,psci-1.0";
 		method = "smc";
@@ -1295,10 +1320,10 @@
 					  <&gcc GCC_USB30_PRIM_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <150000000>;
 
-			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 486 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 488 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 489 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 6 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 8 IRQ_TYPE_EDGE_BOTH>,
+					      <&pdc 9 IRQ_TYPE_EDGE_BOTH>;
 			interrupt-names = "hs_phy_irq", "ss_phy_irq",
 					  "dm_hs_phy_irq", "dp_hs_phy_irq";
 
@@ -1353,6 +1378,273 @@
 			#interrupt-cells = <4>;
 		};
 
+		mdss: display-subsystem@ae00000 {
+			compatible = "qcom,sdm670-mdss";
+			reg = <0 0x0ae00000 0 0x1000>;
+			reg-names = "mdss";
+
+			power-domains = <&dispcc MDSS_GDSC>;
+
+			clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
+				 <&dispcc DISP_CC_MDSS_MDP_CLK>;
+			clock-names = "iface", "core";
+
+			interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+
+			interconnects = <&mmss_noc MASTER_MDP_PORT0 0 &mem_noc SLAVE_EBI_CH0 0>,
+					<&mmss_noc MASTER_MDP_PORT1 0 &mem_noc SLAVE_EBI_CH0 0>;
+			interconnect-names = "mdp0-mem", "mdp1-mem";
+
+			iommus = <&apps_smmu 0x880 0x8>,
+				 <&apps_smmu 0xc80 0x8>;
+
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+
+			status = "disabled";
+
+			mdss_mdp: display-controller@ae01000 {
+				compatible = "qcom,sdm670-dpu";
+				reg = <0 0x0ae01000 0 0x8f000>,
+				      <0 0x0aeb0000 0 0x2008>;
+				reg-names = "mdp", "vbif";
+
+				clocks = <&gcc GCC_DISP_AXI_CLK>,
+					 <&dispcc DISP_CC_MDSS_AHB_CLK>,
+					 <&dispcc DISP_CC_MDSS_AXI_CLK>,
+					 <&dispcc DISP_CC_MDSS_MDP_CLK>,
+					 <&dispcc DISP_CC_MDSS_VSYNC_CLK>;
+				clock-names = "gcc-bus", "iface", "bus", "core", "vsync";
+
+				assigned-clocks = <&dispcc DISP_CC_MDSS_VSYNC_CLK>;
+				assigned-clock-rates = <19200000>;
+				operating-points-v2 = <&mdp_opp_table>;
+				power-domains = <&rpmhpd SDM670_CX>;
+
+				interrupt-parent = <&mdss>;
+				interrupts = <0>;
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+						dpu_intf0_out: endpoint {
+							remote-endpoint = <&mdss_dsi0_in>;
+						};
+					};
+
+					port@1 {
+						reg = <1>;
+						dpu_intf1_out: endpoint {
+							remote-endpoint = <&mdss_dsi1_in>;
+						};
+					};
+				};
+
+				mdp_opp_table: opp-table {
+					compatible = "operating-points-v2";
+
+					opp-19200000 {
+						opp-hz = /bits/ 64 <19200000>;
+						required-opps = <&rpmhpd_opp_min_svs>;
+					};
+
+					opp-171428571 {
+						opp-hz = /bits/ 64 <171428571>;
+						required-opps = <&rpmhpd_opp_low_svs>;
+					};
+
+					opp-358000000 {
+						opp-hz = /bits/ 64 <358000000>;
+						required-opps = <&rpmhpd_opp_svs_l1>;
+					};
+
+					opp-430000000 {
+						opp-hz = /bits/ 64 <430000000>;
+						required-opps = <&rpmhpd_opp_nom>;
+					};
+				};
+			};
+
+			mdss_dsi0: dsi@ae94000 {
+				compatible = "qcom,sdm670-dsi-ctrl",
+					     "qcom,mdss-dsi-ctrl";
+				reg = <0 0x0ae94000 0 0x400>;
+				reg-names = "dsi_ctrl";
+
+				interrupt-parent = <&mdss>;
+				interrupts = <4>;
+
+				clocks = <&dispcc DISP_CC_MDSS_BYTE0_CLK>,
+					 <&dispcc DISP_CC_MDSS_BYTE0_INTF_CLK>,
+					 <&dispcc DISP_CC_MDSS_PCLK0_CLK>,
+					 <&dispcc DISP_CC_MDSS_ESC0_CLK>,
+					 <&dispcc DISP_CC_MDSS_AHB_CLK>,
+					 <&dispcc DISP_CC_MDSS_AXI_CLK>;
+				clock-names = "byte",
+					      "byte_intf",
+					      "pixel",
+					      "core",
+					      "iface",
+					      "bus";
+				assigned-clocks = <&dispcc DISP_CC_MDSS_BYTE0_CLK_SRC>,
+						  <&dispcc DISP_CC_MDSS_PCLK0_CLK_SRC>;
+				assigned-clock-parents = <&mdss_dsi0_phy 0>,
+							 <&mdss_dsi0_phy 1>;
+
+				operating-points-v2 = <&dsi_opp_table>;
+				power-domains = <&rpmhpd SDM670_CX>;
+
+				phys = <&mdss_dsi0_phy>;
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+						mdss_dsi0_in: endpoint {
+							remote-endpoint = <&dpu_intf0_out>;
+						};
+					};
+
+					port@1 {
+						reg = <1>;
+						mdss_dsi0_out: endpoint {
+						};
+					};
+				};
+			};
+
+			mdss_dsi0_phy: phy@ae94400 {
+				compatible = "qcom,dsi-phy-10nm";
+				reg = <0 0x0ae94400 0 0x200>,
+				      <0 0x0ae94600 0 0x280>,
+				      <0 0x0ae94a00 0 0x1e0>;
+				reg-names = "dsi_phy",
+					    "dsi_phy_lane",
+					    "dsi_pll";
+
+				#clock-cells = <1>;
+				#phy-cells = <0>;
+
+				clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
+					 <&rpmhcc RPMH_CXO_CLK>;
+				clock-names = "iface", "ref";
+
+				status = "disabled";
+			};
+
+			mdss_dsi1: dsi@ae96000 {
+				compatible = "qcom,sdm670-dsi-ctrl",
+					     "qcom,mdss-dsi-ctrl";
+				reg = <0 0x0ae96000 0 0x400>;
+				reg-names = "dsi_ctrl";
+
+				interrupt-parent = <&mdss>;
+				interrupts = <5>;
+
+				clocks = <&dispcc DISP_CC_MDSS_BYTE1_CLK>,
+					 <&dispcc DISP_CC_MDSS_BYTE1_INTF_CLK>,
+					 <&dispcc DISP_CC_MDSS_PCLK1_CLK>,
+					 <&dispcc DISP_CC_MDSS_ESC1_CLK>,
+					 <&dispcc DISP_CC_MDSS_AHB_CLK>,
+					 <&dispcc DISP_CC_MDSS_AXI_CLK>;
+				clock-names = "byte",
+					      "byte_intf",
+					      "pixel",
+					      "core",
+					      "iface",
+					      "bus";
+				assigned-clocks = <&dispcc DISP_CC_MDSS_BYTE1_CLK_SRC>,
+						  <&dispcc DISP_CC_MDSS_PCLK1_CLK_SRC>;
+				assigned-clock-parents = <&mdss_dsi1_phy 0>, <&mdss_dsi1_phy 1>;
+
+				operating-points-v2 = <&dsi_opp_table>;
+				power-domains = <&rpmhpd SDM670_CX>;
+
+				phys = <&mdss_dsi1_phy>;
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+						mdss_dsi1_in: endpoint {
+							remote-endpoint = <&dpu_intf1_out>;
+						};
+					};
+
+					port@1 {
+						reg = <1>;
+						mdss_dsi1_out: endpoint {
+						};
+					};
+				};
+			};
+
+			mdss_dsi1_phy: phy@ae96400 {
+				compatible = "qcom,dsi-phy-10nm";
+				reg = <0 0x0ae96400 0 0x200>,
+				      <0 0x0ae96600 0 0x280>,
+				      <0 0x0ae96a00 0 0x10e>;
+				reg-names = "dsi_phy",
+					    "dsi_phy_lane",
+					    "dsi_pll";
+
+				#clock-cells = <1>;
+				#phy-cells = <0>;
+
+				clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
+					 <&rpmhcc RPMH_CXO_CLK>;
+				clock-names = "iface", "ref";
+
+				status = "disabled";
+			};
+		};
+
+		dispcc: clock-controller@af00000 {
+			compatible = "qcom,sdm845-dispcc";
+			reg = <0 0x0af00000 0 0x10000>;
+			clocks = <&rpmhcc RPMH_CXO_CLK>,
+				 <&gcc GCC_DISP_GPLL0_CLK_SRC>,
+				 <&gcc GCC_DISP_GPLL0_DIV_CLK_SRC>,
+				 <&mdss_dsi0_phy 0>,
+				 <&mdss_dsi0_phy 1>,
+				 <&mdss_dsi1_phy 0>,
+				 <&mdss_dsi1_phy 1>,
+				 <0>,
+				 <0>;
+			clock-names = "bi_tcxo",
+				      "gcc_disp_gpll0_clk_src",
+				      "gcc_disp_gpll0_div_clk_src",
+				      "dsi0_phy_pll_out_byteclk",
+				      "dsi0_phy_pll_out_dsiclk",
+				      "dsi1_phy_pll_out_byteclk",
+				      "dsi1_phy_pll_out_dsiclk",
+				      "dp_link_clk_divsel_ten",
+				      "dp_vco_divided_clk_src_mux";
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+			#power-domain-cells = <1>;
+		};
+
 		apps_smmu: iommu@15000000 {
 			compatible = "qcom,sdm670-smmu-500", "qcom,smmu-500", "arm,mmu-500";
 			reg = <0 0x15000000 0 0x80000>;
@@ -1532,7 +1824,7 @@
 		};
 
 		cpufreq_hw: cpufreq@17d43000 {
-			compatible = "qcom,cpufreq-hw";
+			compatible = "qcom,sdm670-cpufreq-hw", "qcom,cpufreq-hw";
 			reg = <0 0x17d43000 0 0x1400>, <0 0x17d45800 0 0x1400>;
 			reg-names = "freq-domain0", "freq-domain1";
 
diff --git a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts
index c7eba6c491be..ab6220456513 100644
--- a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts
+++ b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts
@@ -67,8 +67,8 @@
 			function = LED_FUNCTION_INDICATOR;
 			color = <LED_COLOR_ID_GREEN>;
 			gpios = <&pm8998_gpios 13 GPIO_ACTIVE_HIGH>;
-			linux,default-trigger = "panic-indicator";
 			default-state = "off";
+			panic-indicator;
 		};
 
 		led-1 {
@@ -1130,7 +1130,7 @@
 	vdd-rx-supply = <&vreg_s4a_1p8>;
 	vdd-io-supply = <&vreg_s4a_1p8>;
 
-	swm: swm@c85 {
+	swm: soundwire@c85 {
 		left_spkr: speaker@0,1 {
 			compatible = "sdw10217201000";
 			reg = <0 1>;
diff --git a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi
index b523b5fff702..e821103d49c0 100644
--- a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi
@@ -8,6 +8,7 @@
 /dts-v1/;
 
 #include <dt-bindings/input/linux-event-codes.h>
+#include <dt-bindings/leds/common.h>
 #include <dt-bindings/regulator/qcom,rpmh-regulator.h>
 #include <dt-bindings/sound/qcom,q6afe.h>
 #include <dt-bindings/sound/qcom,q6asm.h>
@@ -484,6 +485,28 @@
 	status = "okay";
 };
 
+&pmi8998_flash {
+	status = "okay";
+
+	led-0 {
+		function = LED_FUNCTION_FLASH;
+		color = <LED_COLOR_ID_WHITE>;
+		led-sources = <1>;
+		led-max-microamp = <500000>;
+		flash-max-microamp = <1500000>;
+		flash-max-timeout-us = <1280000>;
+	};
+
+	led-1 {
+		function = LED_FUNCTION_FLASH;
+		color = <LED_COLOR_ID_YELLOW>;
+		led-sources = <2>;
+		led-max-microamp = <500000>;
+		flash-max-microamp = <1500000>;
+		flash-max-timeout-us = <1280000>;
+	};
+};
+
 &q6afedai {
 	qi2s@22 {
 		reg = <22>;
diff --git a/arch/arm64/boot/dts/qcom/sdm845-wcd9340.dtsi b/arch/arm64/boot/dts/qcom/sdm845-wcd9340.dtsi
index c15d48860646..6172cd1539e6 100644
--- a/arch/arm64/boot/dts/qcom/sdm845-wcd9340.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm845-wcd9340.dtsi
@@ -54,7 +54,7 @@
 				reg = <0x42 0x2>;
 			};
 
-			swm: swm@c85 {
+			swm: soundwire@c85 {
 				compatible = "qcom,soundwire-v1.3.0";
 				reg = <0xc85 0x40>;
 				interrupts-extended = <&wcd9340 20>;
diff --git a/arch/arm64/boot/dts/qcom/sdm845-xiaomi-beryllium-common.dtsi b/arch/arm64/boot/dts/qcom/sdm845-xiaomi-beryllium-common.dtsi
index 93b1582e807d..617b17b2d7d9 100644
--- a/arch/arm64/boot/dts/qcom/sdm845-xiaomi-beryllium-common.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm845-xiaomi-beryllium-common.dtsi
@@ -355,6 +355,28 @@
 	status = "okay";
 };
 
+&pmi8998_flash {
+	status = "okay";
+
+	led-0 {
+		function = LED_FUNCTION_FLASH;
+		color = <LED_COLOR_ID_WHITE>;
+		led-sources = <1>;
+		led-max-microamp = <500000>;
+		flash-max-microamp = <1500000>;
+		flash-max-timeout-us = <1280000>;
+	};
+
+	led-1 {
+		function = LED_FUNCTION_FLASH;
+		color = <LED_COLOR_ID_YELLOW>;
+		led-sources = <2>;
+		led-max-microamp = <500000>;
+		flash-max-microamp = <1500000>;
+		flash-max-timeout-us = <1280000>;
+	};
+};
+
 &pm8998_resin {
 	linux,code = <KEY_VOLUMEDOWN>;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi
index bf5e6eb9d313..c2244824355a 100644
--- a/arch/arm64/boot/dts/qcom/sdm845.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi
@@ -2306,7 +2306,7 @@
 			};
 		};
 
-		pcie0: pci@1c00000 {
+		pcie0: pcie@1c00000 {
 			compatible = "qcom,pcie-sdm845";
 			reg = <0 0x01c00000 0 0x2000>,
 			      <0 0x60000000 0 0xf1d>,
@@ -2405,7 +2405,7 @@
 			status = "disabled";
 		};
 
-		pcie1: pci@1c08000 {
+		pcie1: pcie@1c08000 {
 			compatible = "qcom,pcie-sdm845";
 			reg = <0 0x01c08000 0 0x2000>,
 			      <0 0x40000000 0 0xf1d>,
@@ -2565,7 +2565,7 @@
 			      <0 0x01d90000 0 0x8000>;
 			reg-names = "std", "ice";
 			interrupts = <GIC_SPI 265 IRQ_TYPE_LEVEL_HIGH>;
-			phys = <&ufs_mem_phy_lanes>;
+			phys = <&ufs_mem_phy>;
 			phy-names = "ufsphy";
 			lanes-per-direction = <2>;
 			power-domains = <&gcc UFS_PHY_GDSC>;
@@ -2595,30 +2595,50 @@
 				<&gcc GCC_UFS_PHY_RX_SYMBOL_0_CLK>,
 				<&gcc GCC_UFS_PHY_RX_SYMBOL_1_CLK>,
 				<&gcc GCC_UFS_PHY_ICE_CORE_CLK>;
-			freq-table-hz =
-				<50000000 200000000>,
-				<0 0>,
-				<0 0>,
-				<37500000 150000000>,
-				<0 0>,
-				<0 0>,
-				<0 0>,
-				<0 0>,
-				<75000000 300000000>;
+
+			operating-points-v2 = <&ufs_opp_table>;
 
 			interconnects = <&aggre1_noc MASTER_UFS_MEM 0 &mem_noc SLAVE_EBI1 0>,
 					<&gladiator_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_UFS_MEM_CFG 0>;
 			interconnect-names = "ufs-ddr", "cpu-ufs";
 
 			status = "disabled";
+
+			ufs_opp_table: opp-table {
+				compatible = "operating-points-v2";
+
+				opp-50000000 {
+					opp-hz = /bits/ 64 <50000000>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <37500000>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <75000000>;
+					required-opps = <&rpmhpd_opp_low_svs>;
+				};
+
+				opp-200000000 {
+					opp-hz = /bits/ 64 <200000000>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <150000000>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <300000000>;
+					required-opps = <&rpmhpd_opp_nom>;
+				};
+			};
 		};
 
 		ufs_mem_phy: phy@1d87000 {
 			compatible = "qcom,sdm845-qmp-ufs-phy";
-			reg = <0 0x01d87000 0 0x18c>;
-			#address-cells = <2>;
-			#size-cells = <2>;
-			ranges;
+			reg = <0 0x01d87000 0 0x1000>;
+
 			clock-names = "ref",
 				      "ref_aux";
 			clocks = <&gcc GCC_UFS_MEM_CLKREF_CLK>,
@@ -2626,16 +2646,9 @@
 
 			resets = <&ufs_mem_hc 0>;
 			reset-names = "ufsphy";
-			status = "disabled";
 
-			ufs_mem_phy_lanes: phy@1d87400 {
-				reg = <0 0x01d87400 0 0x108>,
-				      <0 0x01d87600 0 0x1e0>,
-				      <0 0x01d87c00 0 0x1dc>,
-				      <0 0x01d87800 0 0x108>,
-				      <0 0x01d87a00 0 0x1e0>;
-				#phy-cells = <0>;
-			};
+			#phy-cells = <0>;
+			status = "disabled";
 		};
 
 		cryptobam: dma-controller@1dc4000 {
@@ -3545,11 +3558,8 @@
 			};
 
 			in-ports {
-				#address-cells = <1>;
-				#size-cells = <0>;
 
-				port@1 {
-					reg = <1>;
+				port {
 					etf_in: endpoint {
 						remote-endpoint =
 						  <&merge_funnel_out>;
@@ -4000,33 +4010,28 @@
 
 		usb_2_qmpphy: phy@88eb000 {
 			compatible = "qcom,sdm845-qmp-usb3-uni-phy";
-			reg = <0 0x088eb000 0 0x18c>;
-			status = "disabled";
-			#address-cells = <2>;
-			#size-cells = <2>;
-			ranges;
+			reg = <0 0x088eb000 0 0x1000>;
 
 			clocks = <&gcc GCC_USB3_SEC_PHY_AUX_CLK>,
 				 <&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>,
 				 <&gcc GCC_USB3_SEC_CLKREF_CLK>,
-				 <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>;
-			clock-names = "aux", "cfg_ahb", "ref", "com_aux";
+				 <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>,
+				 <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>;
+			clock-names = "aux",
+				      "cfg_ahb",
+				      "ref",
+				      "com_aux",
+				      "pipe";
+			clock-output-names = "usb3_uni_phy_pipe_clk_src";
+			#clock-cells = <0>;
+			#phy-cells = <0>;
 
-			resets = <&gcc GCC_USB3PHY_PHY_SEC_BCR>,
-				 <&gcc GCC_USB3_PHY_SEC_BCR>;
-			reset-names = "phy", "common";
+			resets = <&gcc GCC_USB3_PHY_SEC_BCR>,
+				 <&gcc GCC_USB3PHY_PHY_SEC_BCR>;
+			reset-names = "phy",
+				      "phy_phy";
 
-			usb_2_ssphy: phy@88eb200 {
-				reg = <0 0x088eb200 0 0x128>,
-				      <0 0x088eb400 0 0x1fc>,
-				      <0 0x088eb800 0 0x218>,
-				      <0 0x088eb600 0 0x70>;
-				#clock-cells = <0>;
-				#phy-cells = <0>;
-				clocks = <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>;
-				clock-names = "pipe0";
-				clock-output-names = "usb3_uni_phy_pipe_clk_src";
-			};
+			status = "disabled";
 		};
 
 		usb_1: usb@a6f8800 {
@@ -4053,10 +4058,10 @@
 					  <&gcc GCC_USB30_PRIM_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <150000000>;
 
-			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 486 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 488 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 489 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc_intc 6 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc_intc 8 IRQ_TYPE_EDGE_BOTH>,
+					      <&pdc_intc 9 IRQ_TYPE_EDGE_BOTH>;
 			interrupt-names = "hs_phy_irq", "ss_phy_irq",
 					  "dm_hs_phy_irq", "dp_hs_phy_irq";
 
@@ -4104,10 +4109,10 @@
 					  <&gcc GCC_USB30_SEC_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <150000000>;
 
-			interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 487 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 490 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 491 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts-extended = <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc_intc 7 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc_intc 10 IRQ_TYPE_EDGE_BOTH>,
+					      <&pdc_intc 11 IRQ_TYPE_EDGE_BOTH>;
 			interrupt-names = "hs_phy_irq", "ss_phy_irq",
 					  "dm_hs_phy_irq", "dp_hs_phy_irq";
 
@@ -4126,7 +4131,7 @@
 				iommus = <&apps_smmu 0x760 0>;
 				snps,dis_u2_susphy_quirk;
 				snps,dis_enblslpm_quirk;
-				phys = <&usb_2_hsphy>, <&usb_2_ssphy>;
+				phys = <&usb_2_hsphy>, <&usb_2_qmpphy>;
 				phy-names = "usb2-phy", "usb3-phy";
 			};
 		};
@@ -5088,7 +5093,7 @@
 			compatible = "qcom,apss-wdt-sdm845", "qcom,kpss-wdt";
 			reg = <0 0x17980000 0 0x1000>;
 			clocks = <&sleep_clk>;
-			interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 0 IRQ_TYPE_EDGE_RISING>;
 		};
 
 		apss_shared: mailbox@17990000 {
diff --git a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts
index 92a812b5f423..47dc42f6e936 100644
--- a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts
+++ b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts
@@ -392,6 +392,8 @@
 		hid-descr-addr = <0x20>;
 
 		interrupts-extended = <&tlmm 37 IRQ_TYPE_LEVEL_HIGH>;
+
+		wakeup-source;
 	};
 };
 
@@ -408,6 +410,8 @@
 
 		pinctrl-names = "default";
 		pinctrl-0 = <&i2c5_hid_active>;
+
+		wakeup-source;
 	};
 };
 
@@ -482,6 +486,8 @@
 
 		pinctrl-names = "default";
 		pinctrl-0 = <&i2c11_hid_active>;
+
+		wakeup-source;
 	};
 };
 
@@ -797,7 +803,7 @@
 	qcom,mbhc-headset-vthreshold-microvolt = <1700000>;
 	qcom,mbhc-headphone-vthreshold-microvolt = <50000>;
 
-	swm: swm@c85 {
+	swm: soundwire@c85 {
 		left_spkr: speaker@0,3 {
 			compatible = "sdw10217211000";
 			reg = <0 3>;
diff --git a/arch/arm64/boot/dts/qcom/sdm850-samsung-w737.dts b/arch/arm64/boot/dts/qcom/sdm850-samsung-w737.dts
index 543837316001..26217836c270 100644
--- a/arch/arm64/boot/dts/qcom/sdm850-samsung-w737.dts
+++ b/arch/arm64/boot/dts/qcom/sdm850-samsung-w737.dts
@@ -658,7 +658,7 @@
 	qcom,mbhc-headset-vthreshold-microvolt = <1700000>;
 	qcom,mbhc-headphone-vthreshold-microvolt = <50000>;
 
-	swm: swm@c85 {
+	swm: soundwire@c85 {
 		left_spkr: speaker@0,3 {
 			compatible = "sdw10217211000";
 			reg = <0 3>;
diff --git a/arch/arm64/boot/dts/qcom/sdx75-idp.dts b/arch/arm64/boot/dts/qcom/sdx75-idp.dts
index a14e0650c4a8..f76e72fb2072 100644
--- a/arch/arm64/boot/dts/qcom/sdx75-idp.dts
+++ b/arch/arm64/boot/dts/qcom/sdx75-idp.dts
@@ -250,6 +250,11 @@
 	stdout-path = "serial0:115200n8";
 };
 
+&pm7550ba_eusb2_repeater {
+	vdd18-supply = <&vreg_l5b_1p776>;
+	vdd3-supply = <&vreg_l10b_3p08>;
+};
+
 &qupv3_id_0 {
 	status = "okay";
 };
@@ -261,3 +266,27 @@
 &uart1 {
 	status = "okay";
 };
+
+&usb {
+	status = "okay";
+};
+
+&usb_dwc3 {
+	dr_mode = "peripheral";
+};
+
+&usb_hsphy {
+	vdd-supply = <&vreg_l4b_0p88>;
+	vdda12-supply = <&vreg_l1b_1p2>;
+
+	phys = <&pm7550ba_eusb2_repeater>;
+
+	status = "okay";
+};
+
+&usb_qmpphy {
+	vdda-phy-supply = <&vreg_l4b_0p88>;
+	vdda-pll-supply = <&vreg_l1b_1p2>;
+
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/qcom/sdx75.dtsi b/arch/arm64/boot/dts/qcom/sdx75.dtsi
index e180aa4023ec..7dbdf8ca6de6 100644
--- a/arch/arm64/boot/dts/qcom/sdx75.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdx75.dtsi
@@ -8,6 +8,8 @@
 
 #include <dt-bindings/clock/qcom,rpmh.h>
 #include <dt-bindings/clock/qcom,sdx75-gcc.h>
+#include <dt-bindings/interconnect/qcom,icc.h>
+#include <dt-bindings/interconnect/qcom,sdx75.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/power/qcom,rpmhpd.h>
 #include <dt-bindings/power/qcom-rpmpd.h>
@@ -203,6 +205,19 @@
 		};
 	};
 
+	clk_virt: interconnect-0 {
+		compatible = "qcom,sdx75-clk-virt";
+		#interconnect-cells = <2>;
+		qcom,bcm-voters = <&apps_bcm_voter>;
+		clocks = <&rpmhcc RPMH_QPIC_CLK>;
+	};
+
+	mc_virt: interconnect-1 {
+		compatible = "qcom,sdx75-mc-virt";
+		#interconnect-cells = <2>;
+		qcom,bcm-voters = <&apps_bcm_voter>;
+	};
+
 	memory@80000000 {
 		device_type = "memory";
 		reg = <0x0 0x80000000 0x0 0x0>;
@@ -434,6 +449,9 @@
 			clock-names = "m-ahb",
 				      "s-ahb";
 			iommus = <&apps_smmu 0xe3 0x0>;
+			interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+					 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>;
+			interconnect-names = "qup-core";
 			#address-cells = <2>;
 			#size-cells = <2>;
 			ranges;
@@ -444,6 +462,12 @@
 				reg = <0x0 0x00984000 0x0 0x4000>;
 				clocks = <&gcc GCC_QUPV3_WRAP0_S1_CLK>;
 				clock-names = "se";
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &system_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config";
 				interrupts = <GIC_SPI 338 IRQ_TYPE_LEVEL_HIGH>;
 				pinctrl-0 = <&qupv3_se1_2uart_active>;
 				pinctrl-1 = <&qupv3_se1_2uart_sleep>;
@@ -453,12 +477,144 @@
 			};
 		};
 
+		usb_hsphy: phy@ff4000 {
+			compatible = "qcom,sdx75-snps-eusb2-phy", "qcom,sm8550-snps-eusb2-phy";
+			reg = <0x0 0x00ff4000 0x0 0x154>;
+			#phy-cells = <0>;
+
+			clocks = <&rpmhcc RPMH_CXO_CLK>;
+			clock-names = "ref";
+
+			resets = <&gcc GCC_QUSB2PHY_BCR>;
+
+			status = "disabled";
+		};
+
+		usb_qmpphy: phy@ff6000 {
+			compatible = "qcom,sdx75-qmp-usb3-uni-phy";
+			reg = <0x0 0x00ff6000 0x0 0x2000>;
+
+			clocks = <&gcc GCC_USB3_PHY_AUX_CLK>,
+				 <&gcc GCC_USB2_CLKREF_EN>,
+				 <&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>,
+				 <&gcc GCC_USB3_PHY_PIPE_CLK>;
+			clock-names = "aux",
+				      "ref",
+				      "cfg_ahb",
+				      "pipe";
+
+			power-domains = <&gcc GCC_USB3_PHY_GDSC>;
+
+			resets = <&gcc GCC_USB3_PHY_BCR>,
+				 <&gcc GCC_USB3PHY_PHY_BCR>;
+			reset-names = "phy",
+				      "phy_phy";
+
+			#clock-cells = <0>;
+			clock-output-names = "usb3_uni_phy_pipe_clk_src";
+
+			#phy-cells = <0>;
+
+			status = "disabled";
+		};
+
+		system_noc: interconnect@1640000 {
+			compatible = "qcom,sdx75-system-noc";
+			reg = <0x0 0x01640000 0x0 0x4b400>;
+			#interconnect-cells = <2>;
+			qcom,bcm-voters = <&apps_bcm_voter>;
+		};
+
+		pcie_anoc: interconnect@16c0000 {
+			compatible = "qcom,sdx75-pcie-anoc";
+			reg = <0x0 0x016c0000 0x0 0x14200>;
+			#interconnect-cells = <2>;
+			qcom,bcm-voters = <&apps_bcm_voter>;
+		};
+
 		tcsr_mutex: hwlock@1f40000 {
 			compatible = "qcom,tcsr-mutex";
 			reg = <0x0 0x01f40000 0x0 0x40000>;
 			#hwlock-cells = <1>;
 		};
 
+		usb: usb@a6f8800 {
+			compatible = "qcom,sdx75-dwc3", "qcom,dwc3";
+			reg = <0x0 0x0a6f8800 0x0 0x400>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+
+			clocks = <&gcc GCC_USB30_SLV_AHB_CLK>,
+				 <&gcc GCC_USB30_MASTER_CLK>,
+				 <&gcc GCC_USB30_MSTR_AXI_CLK>,
+				 <&gcc GCC_USB30_SLEEP_CLK>,
+				 <&gcc GCC_USB30_MOCK_UTMI_CLK>;
+			clock-names = "cfg_noc",
+				      "core",
+				      "iface",
+				      "sleep",
+				      "mock_utmi";
+
+			assigned-clocks = <&gcc GCC_USB30_MOCK_UTMI_CLK>,
+					  <&gcc GCC_USB30_MASTER_CLK>;
+			assigned-clock-rates = <19200000>, <200000000>;
+
+			interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 17 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 9 IRQ_TYPE_EDGE_RISING>,
+					      <&pdc 10 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "hs_phy_irq",
+					  "ss_phy_irq",
+					  "dm_hs_phy_irq",
+					  "dp_hs_phy_irq";
+
+			power-domains = <&gcc GCC_USB30_GDSC>;
+
+			resets = <&gcc GCC_USB30_BCR>;
+
+			interconnects = <&system_noc MASTER_USB3_0 QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
+					<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+					 &system_noc SLAVE_USB3 QCOM_ICC_TAG_ALWAYS>;
+			interconnect-names = "usb-ddr",
+					     "apps-usb";
+
+			status = "disabled";
+
+			usb_dwc3: usb@a600000 {
+				compatible = "snps,dwc3";
+				reg = <0x0 0x0a600000 0x0 0xcd00>;
+				interrupts = <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
+				iommus = <&apps_smmu 0x80 0x0>;
+				snps,dis_u2_susphy_quirk;
+				snps,dis_enblslpm_quirk;
+				phys = <&usb_hsphy>,
+				       <&usb_qmpphy>;
+				phy-names = "usb2-phy",
+					    "usb3-phy";
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+
+						usb_1_dwc3_hs: endpoint {
+						};
+					};
+
+					port@1 {
+						reg = <1>;
+
+						usb_1_dwc3_ss: endpoint {
+						};
+					};
+				};
+			};
+		};
+
 		pdc: interrupt-controller@b220000 {
 			compatible = "qcom,sdx75-pdc", "qcom,pdc";
 			reg = <0x0 0xb220000 0x0 0x30000>,
@@ -733,6 +889,20 @@
 			#freq-domain-cells = <1>;
 			#clock-cells = <1>;
 		};
+
+		dc_noc: interconnect@190e0000 {
+			compatible = "qcom,sdx75-dc-noc";
+			reg = <0x0 0x190e0000 0x0 0x8200>;
+			#interconnect-cells = <2>;
+			qcom,bcm-voters = <&apps_bcm_voter>;
+		};
+
+		gem_noc: interconnect@19100000 {
+			compatible = "qcom,sdx75-gem-noc";
+			reg = <0x0 0x19100000 0x0 0x34080>;
+			#interconnect-cells = <2>;
+			qcom,bcm-voters = <&apps_bcm_voter>;
+		};
 	};
 
 	timer {
diff --git a/arch/arm64/boot/dts/qcom/sm4450-qrd.dts b/arch/arm64/boot/dts/qcom/sm4450-qrd.dts
index 00a1c81ca397..866e93783590 100644
--- a/arch/arm64/boot/dts/qcom/sm4450-qrd.dts
+++ b/arch/arm64/boot/dts/qcom/sm4450-qrd.dts
@@ -10,9 +10,23 @@
 	model = "Qualcomm Technologies, Inc. SM4450 QRD";
 	compatible = "qcom,sm4450-qrd", "qcom,sm4450";
 
-	aliases { };
+	aliases {
+		serial0 = &uart7;
+	};
 
 	chosen {
-		bootargs = "console=hvc0";
+		stdout-path = "serial0:115200n8";
 	};
 };
+
+&qupv3_id_0 {
+	status = "okay";
+};
+
+&tlmm {
+	gpio-reserved-ranges = <0 4>; /* NFC eSE SPI */
+};
+
+&uart7 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/qcom/sm4450.dtsi b/arch/arm64/boot/dts/qcom/sm4450.dtsi
index c4e5b33f5169..3e7ae3bebbe0 100644
--- a/arch/arm64/boot/dts/qcom/sm4450.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm4450.dtsi
@@ -3,8 +3,11 @@
  * Copyright (c) 2023, Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
+#include <dt-bindings/clock/qcom,rpmh.h>
+#include <dt-bindings/clock/qcom,sm4450-gcc.h>
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/soc/qcom,rpmh-rsc.h>
 
 / {
 	interrupt-parent = <&intc>;
@@ -328,6 +331,18 @@
 		};
 	};
 
+	reserved_memory: reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		aop_cmd_db_mem: cmd-db@80860000 {
+			compatible = "qcom,cmd-db";
+			reg = <0x0 0x80860000 0x0 0x20000>;
+			no-map;
+		};
+	};
+
 	soc: soc@0 {
 		#address-cells = <2>;
 		#size-cells = <2>;
@@ -335,6 +350,43 @@
 		dma-ranges = <0 0 0 0 0x10 0>;
 		compatible = "simple-bus";
 
+		gcc: clock-controller@100000 {
+			compatible = "qcom,sm4450-gcc";
+			reg = <0x0 0x00100000 0x0 0x1f4200>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+			#power-domain-cells = <1>;
+			clocks = <&rpmhcc RPMH_CXO_CLK>,
+				 <&sleep_clk>,
+				 <0>,
+				 <0>,
+				 <0>,
+				 <0>;
+		};
+
+		qupv3_id_0: geniqup@ac0000 {
+			compatible = "qcom,geni-se-qup";
+			reg = <0x0 0x00ac0000 0x0 0x2000>;
+			ranges;
+			clocks = <&gcc GCC_QUPV3_WRAP_0_M_AHB_CLK>,
+				 <&gcc GCC_QUPV3_WRAP_0_S_AHB_CLK>;
+			clock-names = "m-ahb", "s-ahb";
+			#address-cells = <2>;
+			#size-cells = <2>;
+			status = "disabled";
+
+			uart7: serial@a88000 {
+				compatible = "qcom,geni-debug-uart";
+				reg = <0x0 0x00a88000 0x0 0x4000>;
+				clocks = <&gcc GCC_QUPV3_WRAP1_S2_CLK>;
+				clock-names = "se";
+				interrupts = <GIC_SPI 355 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&qup_uart7_tx>, <&qup_uart7_rx>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+		};
+
 		tcsr_mutex: hwlock@1f40000 {
 			compatible = "qcom,tcsr-mutex";
 			reg = <0x0 0x01f40000 0x0 0x40000>;
@@ -351,6 +403,32 @@
 			interrupt-controller;
 		};
 
+		tlmm: pinctrl@f100000 {
+			compatible = "qcom,sm4450-tlmm";
+			reg = <0x0 0x0f100000 0x0 0x300000>;
+			interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			gpio-ranges = <&tlmm 0 0 137>;
+			wakeup-parent = <&pdc>;
+
+			qup_uart7_rx: qup-uart7-rx-state {
+				pins = "gpio23";
+				function = "qup1_se2_l2";
+				drive-strength = <2>;
+				bias-disable;
+			};
+
+			qup_uart7_tx: qup-uart7-tx-state {
+				pins = "gpio22";
+				function = "qup1_se2_l2";
+				drive-strength = <2>;
+				bias-disable;
+			};
+		};
+
 		intc: interrupt-controller@17200000 {
 			compatible = "arm,gic-v3";
 			reg = <0x0 0x17200000 0x0 0x10000>,     /* GICD */
@@ -419,6 +497,35 @@
 				status = "disabled";
 			};
 		};
+
+		apps_rsc: rsc@17a00000 {
+			compatible = "qcom,rpmh-rsc";
+			reg = <0x0 0x17a00000 0x0 0x10000>,
+			      <0x0 0x17a10000 0x0 0x10000>,
+			      <0x0 0x17a20000 0x0 0x10000>;
+			reg-names = "drv-0", "drv-1", "drv-2";
+			interrupts = <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>;
+			label = "apps_rsc";
+			qcom,tcs-offset = <0xd00>;
+			qcom,drv-id = <2>;
+			qcom,tcs-config = <ACTIVE_TCS    2>, <SLEEP_TCS     3>,
+					  <WAKE_TCS      3>, <CONTROL_TCS   0>;
+			power-domains = <&CLUSTER_PD>;
+
+			apps_bcm_voter: bcm-voter {
+				compatible = "qcom,bcm-voter";
+			};
+
+			rpmhcc: clock-controller {
+				compatible = "qcom,sm4450-rpmh-clk";
+				#clock-cells = <1>;
+				clocks = <&xo_board>;
+				clock-names = "xo";
+			};
+		};
+
 	};
 
 	timer {
diff --git a/arch/arm64/boot/dts/qcom/sm6115.dtsi b/arch/arm64/boot/dts/qcom/sm6115.dtsi
index 839c60351240..160e098f1075 100644
--- a/arch/arm64/boot/dts/qcom/sm6115.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm6115.dtsi
@@ -10,6 +10,8 @@
 #include <dt-bindings/dma/qcom-gpi.h>
 #include <dt-bindings/firmware/qcom,scm.h>
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interconnect/qcom,rpm-icc.h>
+#include <dt-bindings/interconnect/qcom,sm6115.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/power/qcom-rpmpd.h>
 
@@ -264,6 +266,8 @@
 		scm: scm {
 			compatible = "qcom,scm-sm6115", "qcom,scm";
 			#reset-cells = <1>;
+			interconnects = <&system_noc MASTER_CRYPTO_CORE0 RPM_ALWAYS_TAG
+					 &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>;
 		};
 	};
 
@@ -273,6 +277,25 @@
 		reg = <0 0x80000000 0 0>;
 	};
 
+	qup_opp_table: opp-table-qup {
+		compatible = "operating-points-v2";
+
+		opp-75000000 {
+			opp-hz = /bits/ 64 <75000000>;
+			required-opps = <&rpmpd_opp_low_svs>;
+		};
+
+		opp-100000000 {
+			opp-hz = /bits/ 64 <100000000>;
+			required-opps = <&rpmpd_opp_svs>;
+		};
+
+		opp-128000000 {
+			opp-hz = /bits/ 64 <128000000>;
+			required-opps = <&rpmpd_opp_nom>;
+		};
+	};
+
 	pmu {
 		compatible = "arm,armv8-pmuv3";
 		interrupts = <GIC_PPI 6 IRQ_TYPE_LEVEL_HIGH>;
@@ -859,6 +882,43 @@
 			status = "disabled";
 		};
 
+		system_noc: interconnect@1880000 {
+			compatible = "qcom,sm6115-snoc";
+			reg = <0x0 0x01880000 0x0 0x5f080>;
+			clocks = <&gcc GCC_SYS_NOC_CPUSS_AHB_CLK>,
+				 <&gcc GCC_SYS_NOC_UFS_PHY_AXI_CLK>,
+				 <&gcc GCC_SYS_NOC_USB3_PRIM_AXI_CLK>,
+				 <&rpmcc RPM_SMD_IPA_CLK>;
+			clock-names = "cpu_axi",
+				      "ufs_axi",
+				      "usb_axi",
+				      "ipa";
+			#interconnect-cells = <2>;
+
+			clk_virt: interconnect-clk {
+				compatible = "qcom,sm6115-clk-virt";
+				#interconnect-cells = <2>;
+			};
+
+			mmrt_virt: interconnect-mmrt {
+				compatible = "qcom,sm6115-mmrt-virt";
+				#interconnect-cells = <2>;
+			};
+
+			mmnrt_virt: interconnect-mmnrt {
+				compatible = "qcom,sm6115-mmnrt-virt";
+				#interconnect-cells = <2>;
+			};
+		};
+
+		config_noc: interconnect@1900000 {
+			compatible = "qcom,sm6115-cnoc";
+			reg = <0x0 0x01900000 0x0 0x6200>;
+			clocks = <&gcc GCC_CFG_NOC_USB3_PRIM_AXI_CLK>;
+			clock-names = "usb_axi";
+			#interconnect-cells = <2>;
+		};
+
 		qfprom@1b40000 {
 			compatible = "qcom,sm6115-qfprom", "qcom,qfprom";
 			reg = <0x0 0x01b40000 0x0 0x7000>;
@@ -883,6 +943,60 @@
 			clock-names = "core";
 		};
 
+		pmu@1b8e300 {
+			compatible = "qcom,sm6115-cpu-bwmon", "qcom,sdm845-bwmon";
+			reg = <0x0 0x01b8e300 0x0 0x600>;
+			interrupts = <GIC_SPI 421 IRQ_TYPE_LEVEL_HIGH>;
+
+			operating-points-v2 = <&cpu_bwmon_opp_table>;
+			interconnects = <&bimc MASTER_AMPSS_M0 RPM_ACTIVE_TAG
+					 &bimc SLAVE_EBI_CH0 RPM_ACTIVE_TAG>;
+
+			cpu_bwmon_opp_table: opp-table {
+				compatible = "operating-points-v2";
+
+				opp-0 {
+					opp-peak-kBps = <(200 * 4 * 1000)>;
+				};
+
+				opp-1 {
+					opp-peak-kBps = <(300 * 4 * 1000)>;
+				};
+
+				opp-2 {
+					opp-peak-kBps = <(451 * 4 * 1000)>;
+				};
+
+				opp-3 {
+					opp-peak-kBps = <(547 * 4 * 1000)>;
+				};
+
+				opp-4 {
+					opp-peak-kBps = <(681 * 4 * 1000)>;
+				};
+
+				opp-5 {
+					opp-peak-kBps = <(768 * 4 * 1000)>;
+				};
+
+				opp-6 {
+					opp-peak-kBps = <(1017 * 4 * 1000)>;
+				};
+
+				opp-7 {
+					opp-peak-kBps = <(1353 * 4 * 1000)>;
+				};
+
+				opp-8 {
+					opp-peak-kBps = <(1555 * 4 * 1000)>;
+				};
+
+				opp-9 {
+					opp-peak-kBps = <(1804 * 4 * 1000)>;
+				};
+			};
+		};
+
 		spmi_bus: spmi@1c40000 {
 			compatible = "qcom,spmi-pmic-arb";
 			reg = <0x0 0x01c40000 0x0 0x1100>,
@@ -912,6 +1026,12 @@
 			#thermal-sensor-cells = <1>;
 		};
 
+		bimc: interconnect@4480000 {
+			compatible = "qcom,sm6115-bimc";
+			reg = <0x0 0x04480000 0x0 0x80000>;
+			#interconnect-cells = <2>;
+		};
+
 		rpm_msg_ram: sram@45f0000 {
 			compatible = "qcom,rpm-msg-ram";
 			reg = <0x0 0x045f0000 0x0 0x7000>;
@@ -939,8 +1059,42 @@
 				 <&gcc GCC_SDCC1_ICE_CORE_CLK>;
 			clock-names = "iface", "core", "xo", "ice";
 
+			power-domains = <&rpmpd SM6115_VDDCX>;
+			operating-points-v2 = <&sdhc1_opp_table>;
+			interconnects = <&system_noc MASTER_SDCC_1 RPM_ALWAYS_TAG
+					 &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>,
+					<&bimc MASTER_AMPSS_M0 RPM_ALWAYS_TAG
+					 &config_noc SLAVE_SDCC_1 RPM_ALWAYS_TAG>;
+			interconnect-names = "sdhc-ddr",
+					     "cpu-sdhc";
+
 			bus-width = <8>;
 			status = "disabled";
+
+			sdhc1_opp_table: opp-table {
+				compatible = "operating-points-v2";
+
+				opp-100000000 {
+					opp-hz = /bits/ 64 <100000000>;
+					required-opps = <&rpmpd_opp_low_svs>;
+					opp-peak-kBps = <250000 133320>;
+					opp-avg-kBps = <102400 65000>;
+				};
+
+				opp-192000000 {
+					opp-hz = /bits/ 64 <192000000>;
+					required-opps = <&rpmpd_opp_low_svs>;
+					opp-peak-kBps = <800000 300000>;
+					opp-avg-kBps = <204800 200000>;
+				};
+
+				opp-384000000 {
+					opp-hz = /bits/ 64 <384000000>;
+					required-opps = <&rpmpd_opp_svs_plus>;
+					opp-peak-kBps = <800000 300000>;
+					opp-avg-kBps = <204800 200000>;
+				};
+			};
 		};
 
 		sdhc_2: mmc@4784000 {
@@ -961,6 +1115,12 @@
 			operating-points-v2 = <&sdhc2_opp_table>;
 			iommus = <&apps_smmu 0x00a0 0x0>;
 			resets = <&gcc GCC_SDCC2_BCR>;
+			interconnects = <&system_noc MASTER_SDCC_2 RPM_ALWAYS_TAG
+					 &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>,
+					<&bimc MASTER_AMPSS_M0 RPM_ALWAYS_TAG
+					 &config_noc SLAVE_SDCC_2 RPM_ALWAYS_TAG>;
+			interconnect-names = "sdhc-ddr",
+					     "cpu-sdhc";
 
 			bus-width = <4>;
 			qcom,dll-config = <0x0007642c>;
@@ -973,11 +1133,15 @@
 				opp-100000000 {
 					opp-hz = /bits/ 64 <100000000>;
 					required-opps = <&rpmpd_opp_low_svs>;
+					opp-peak-kBps = <250000 133320>;
+					opp-avg-kBps = <261438 150000>;
 				};
 
 				opp-202000000 {
 					opp-hz = /bits/ 64 <202000000>;
 					required-opps = <&rpmpd_opp_nom>;
+					opp-peak-kBps = <800000 300000>;
+					opp-avg-kBps = <261438 300000>;
 				};
 			};
 		};
@@ -987,7 +1151,7 @@
 			reg = <0x0 0x04804000 0x0 0x3000>, <0x0 0x04810000 0x0 0x8000>;
 			reg-names = "std", "ice";
 			interrupts = <GIC_SPI 356 IRQ_TYPE_LEVEL_HIGH>;
-			phys = <&ufs_mem_phy_lanes>;
+			phys = <&ufs_mem_phy>;
 			phy-names = "ufsphy";
 			lanes-per-direction = <1>;
 			#reset-cells = <1>;
@@ -1028,24 +1192,17 @@
 
 		ufs_mem_phy: phy@4807000 {
 			compatible = "qcom,sm6115-qmp-ufs-phy";
-			reg = <0x0 0x04807000 0x0 0x1c4>;
-			#address-cells = <2>;
-			#size-cells = <2>;
-			ranges;
+			reg = <0x0 0x04807000 0x0 0x1000>;
 
 			clocks = <&gcc GCC_UFS_CLKREF_CLK>, <&gcc GCC_UFS_PHY_PHY_AUX_CLK>;
 			clock-names = "ref", "ref_aux";
 
 			resets = <&ufs_mem_hc 0>;
 			reset-names = "ufsphy";
-			status = "disabled";
 
-			ufs_mem_phy_lanes: phy@4807400 {
-				reg = <0x0 0x04807400 0x0 0x098>,
-				      <0x0 0x04807600 0x0 0x130>,
-				      <0x0 0x04807c00 0x0 0x16c>;
-				#phy-cells = <0>;
-			};
+			#phy-cells = <0>;
+
+			status = "disabled";
 		};
 
 		gpi_dma0: dma-controller@4a00000 {
@@ -1091,6 +1248,15 @@
 				dmas = <&gpi_dma0 0 0 QCOM_GPI_I2C>,
 				       <&gpi_dma0 1 0 QCOM_GPI_I2C>;
 				dma-names = "tx", "rx";
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &clk_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_AMPSS_M0 RPM_ALWAYS_TAG
+						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>,
+						<&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG
+						 &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -1107,6 +1273,15 @@
 				dmas = <&gpi_dma0 0 0 QCOM_GPI_SPI>,
 				       <&gpi_dma0 1 0 QCOM_GPI_SPI>;
 				dma-names = "tx", "rx";
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &clk_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_AMPSS_M0 RPM_ALWAYS_TAG
+						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>,
+						<&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG
+						 &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -1123,6 +1298,12 @@
 				dmas = <&gpi_dma0 0 1 QCOM_GPI_I2C>,
 				       <&gpi_dma0 1 1 QCOM_GPI_I2C>;
 				dma-names = "tx", "rx";
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &clk_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_AMPSS_M0 RPM_ALWAYS_TAG
+						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>,
+						<&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG
+						 &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>;
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -1139,6 +1320,15 @@
 				dmas = <&gpi_dma0 0 1 QCOM_GPI_SPI>,
 				       <&gpi_dma0 1 1 QCOM_GPI_SPI>;
 				dma-names = "tx", "rx";
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &clk_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_AMPSS_M0 RPM_ALWAYS_TAG
+						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>,
+						<&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG
+						 &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -1155,6 +1345,15 @@
 				dmas = <&gpi_dma0 0 2 QCOM_GPI_I2C>,
 				       <&gpi_dma0 1 2 QCOM_GPI_I2C>;
 				dma-names = "tx", "rx";
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &clk_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_AMPSS_M0 RPM_ALWAYS_TAG
+						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>,
+						<&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG
+						 &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -1171,6 +1370,15 @@
 				dmas = <&gpi_dma0 0 2 QCOM_GPI_SPI>,
 				       <&gpi_dma0 1 2 QCOM_GPI_SPI>;
 				dma-names = "tx", "rx";
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &clk_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_AMPSS_M0 RPM_ALWAYS_TAG
+						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>,
+						<&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG
+						 &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -1187,6 +1395,15 @@
 				dmas = <&gpi_dma0 0 3 QCOM_GPI_I2C>,
 				       <&gpi_dma0 1 3 QCOM_GPI_I2C>;
 				dma-names = "tx", "rx";
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &clk_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_AMPSS_M0 RPM_ALWAYS_TAG
+						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>,
+						<&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG
+						 &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -1203,11 +1420,37 @@
 				dmas = <&gpi_dma0 0 3 QCOM_GPI_SPI>,
 				       <&gpi_dma0 1 3 QCOM_GPI_SPI>;
 				dma-names = "tx", "rx";
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &clk_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_AMPSS_M0 RPM_ALWAYS_TAG
+						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>,
+						<&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG
+						 &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
 			};
 
+			uart3: serial@4a8c000 {
+				compatible = "qcom,geni-uart";
+				reg = <0x0 0x04a8c000 0x0 0x4000>;
+				interrupts-extended = <&intc GIC_SPI 330 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&gcc GCC_QUPV3_WRAP0_S3_CLK>;
+				clock-names = "se";
+				power-domains = <&rpmpd SM6115_VDDCX>;
+				operating-points-v2 = <&qup_opp_table>;
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &clk_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_AMPSS_M0 RPM_ALWAYS_TAG
+						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config";
+				status = "disabled";
+			};
+
 			i2c4: i2c@4a90000 {
 				compatible = "qcom,geni-i2c";
 				reg = <0x0 0x04a90000 0x0 0x4000>;
@@ -1219,6 +1462,15 @@
 				dmas = <&gpi_dma0 0 4 QCOM_GPI_I2C>,
 				       <&gpi_dma0 1 4 QCOM_GPI_I2C>;
 				dma-names = "tx", "rx";
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &clk_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_AMPSS_M0 RPM_ALWAYS_TAG
+						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>,
+						<&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG
+						 &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -1235,6 +1487,15 @@
 				dmas = <&gpi_dma0 0 4 QCOM_GPI_SPI>,
 				       <&gpi_dma0 1 4 QCOM_GPI_SPI>;
 				dma-names = "tx", "rx";
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &clk_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_AMPSS_M0 RPM_ALWAYS_TAG
+						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>,
+						<&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG
+						 &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -1246,6 +1507,12 @@
 				clock-names = "se";
 				clocks = <&gcc GCC_QUPV3_WRAP0_S4_CLK>;
 				interrupts = <GIC_SPI 331 IRQ_TYPE_LEVEL_HIGH>;
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &clk_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_AMPSS_M0 RPM_ALWAYS_TAG
+						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config";
 				status = "disabled";
 			};
 
@@ -1260,6 +1527,15 @@
 				dmas = <&gpi_dma0 0 5 QCOM_GPI_I2C>,
 				       <&gpi_dma0 1 5 QCOM_GPI_I2C>;
 				dma-names = "tx", "rx";
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &clk_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_AMPSS_M0 RPM_ALWAYS_TAG
+						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>,
+						<&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG
+						 &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -1276,6 +1552,15 @@
 				dmas = <&gpi_dma0 0 5 QCOM_GPI_SPI>,
 				       <&gpi_dma0 1 5 QCOM_GPI_SPI>;
 				dma-names = "tx", "rx";
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 RPM_ALWAYS_TAG
+						 &clk_virt SLAVE_QUP_CORE_0 RPM_ALWAYS_TAG>,
+						<&bimc MASTER_AMPSS_M0 RPM_ALWAYS_TAG
+						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>,
+						<&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG
+						 &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -1307,6 +1592,14 @@
 
 			resets = <&gcc GCC_USB30_PRIM_BCR>;
 			power-domains = <&gcc GCC_USB30_PRIM_GDSC>;
+			 /* TODO: USB<->IPA path */
+			interconnects = <&system_noc MASTER_USB3 RPM_ALWAYS_TAG
+					 &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>,
+					<&bimc MASTER_AMPSS_M0 RPM_ALWAYS_TAG
+					 &config_noc SLAVE_USB3 RPM_ALWAYS_TAG>;
+			interconnect-names = "usb-ddr",
+					     "apps-usb";
+
 			qcom,select-utmi-as-pipe-clk;
 			status = "disabled";
 
@@ -1478,6 +1771,13 @@
 			iommus = <&apps_smmu 0x420 0x2>,
 				 <&apps_smmu 0x421 0x0>;
 
+			interconnects = <&mmrt_virt MASTER_MDP_PORT0 RPM_ALWAYS_TAG
+					 &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>,
+					<&bimc MASTER_AMPSS_M0 RPM_ALWAYS_TAG
+					 &config_noc SLAVE_DISPLAY_CFG RPM_ALWAYS_TAG>;
+			interconnect-names = "mdp0-mem",
+					     "cpu-cfg";
+
 			#address-cells = <2>;
 			#size-cells = <2>;
 			ranges;
@@ -2566,54 +2866,54 @@
 			compatible = "arm,armv7-timer-mem";
 			reg = <0x0 0x0f120000 0x0 0x1000>;
 			#address-cells = <2>;
-			#size-cells = <2>;
-			ranges;
+			#size-cells = <1>;
+			ranges = <0x0 0x0 0x0 0x0 0x20000000>;
 			clock-frequency = <19200000>;
 
 			frame@f121000 {
-				reg = <0x0 0x0f121000 0x0 0x1000>, <0x0 0x0f122000 0x0 0x1000>;
+				reg = <0x0 0x0f121000 0x1000>, <0x0 0x0f122000 0x1000>;
 				frame-number = <0>;
 				interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>;
 			};
 
 			frame@f123000 {
-				reg = <0x0 0x0f123000 0x0 0x1000>;
+				reg = <0x0 0x0f123000 0x1000>;
 				frame-number = <1>;
 				interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
 			};
 
 			frame@f124000 {
-				reg = <0x0 0x0f124000 0x0 0x1000>;
+				reg = <0x0 0x0f124000 0x1000>;
 				frame-number = <2>;
 				interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
 			};
 
 			frame@f125000 {
-				reg = <0x0 0x0f125000 0x0 0x1000>;
+				reg = <0x0 0x0f125000 0x1000>;
 				frame-number = <3>;
 				interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
 			};
 
 			frame@f126000 {
-				reg = <0x0 0x0f126000 0x0 0x1000>;
+				reg = <0x0 0x0f126000 0x1000>;
 				frame-number = <4>;
 				interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
 			};
 
 			frame@f127000 {
-				reg = <0x0 0x0f127000 0x0 0x1000>;
+				reg = <0x0 0x0f127000 0x1000>;
 				frame-number = <5>;
 				interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
 			};
 
 			frame@f128000 {
-				reg = <0x0 0x0f128000 0x0 0x1000>;
+				reg = <0x0 0x0f128000 0x1000>;
 				frame-number = <6>;
 				interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
diff --git a/arch/arm64/boot/dts/qcom/sm6125.dtsi b/arch/arm64/boot/dts/qcom/sm6125.dtsi
index eb07eca3a48d..1dd3a4056e26 100644
--- a/arch/arm64/boot/dts/qcom/sm6125.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm6125.dtsi
@@ -1185,6 +1185,10 @@
 					  <&gcc GCC_USB30_PRIM_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <66666667>;
 
+			interrupts = <GIC_SPI 260 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 422 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "hs_phy_irq", "ss_phy_irq";
+
 			power-domains = <&gcc USB30_PRIM_GDSC>;
 			qcom,select-utmi-as-pipe-clk;
 			status = "disabled";
diff --git a/arch/arm64/boot/dts/qcom/sm6350.dtsi b/arch/arm64/boot/dts/qcom/sm6350.dtsi
index 8fd6f4d03490..43cffe8e1247 100644
--- a/arch/arm64/boot/dts/qcom/sm6350.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm6350.dtsi
@@ -1142,7 +1142,7 @@
 			      <0 0x01d90000 0 0x8000>;
 			reg-names = "std", "ice";
 			interrupts = <GIC_SPI 265 IRQ_TYPE_LEVEL_HIGH>;
-			phys = <&ufs_mem_phy_lanes>;
+			phys = <&ufs_mem_phy>;
 			phy-names = "ufsphy";
 			lanes-per-direction = <2>;
 			#reset-cells = <1>;
@@ -1187,10 +1187,7 @@
 
 		ufs_mem_phy: phy@1d87000 {
 			compatible = "qcom,sm6350-qmp-ufs-phy";
-			reg = <0 0x01d87000 0 0x18c>;
-			#address-cells = <2>;
-			#size-cells = <2>;
-			ranges;
+			reg = <0 0x01d87000 0 0x1000>;
 
 			clock-names = "ref",
 				      "ref_aux";
@@ -1200,16 +1197,9 @@
 			resets = <&ufs_mem_hc 0>;
 			reset-names = "ufsphy";
 
-			status = "disabled";
+			#phy-cells = <0>;
 
-			ufs_mem_phy_lanes: phy@1d87400 {
-				reg = <0 0x01d87400 0 0x128>,
-				      <0 0x01d87600 0 0x1fc>,
-				      <0 0x01d87c00 0 0x1dc>,
-				      <0 0x01d87800 0 0x128>,
-				      <0 0x01d87a00 0 0x1fc>;
-				#phy-cells = <0>;
-			};
+			status = "disabled";
 		};
 
 		ipa: ipa@1e40000 {
@@ -2524,7 +2514,7 @@
 			compatible = "qcom,apss-wdt-sm6350", "qcom,kpss-wdt";
 			reg = <0 0x17c10000 0 0x1000>;
 			clocks = <&sleep_clk>;
-			interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 0 IRQ_TYPE_EDGE_RISING>;
 		};
 
 		timer@17c20000 {
diff --git a/arch/arm64/boot/dts/qcom/sm6375-sony-xperia-murray-pdx225.dts b/arch/arm64/boot/dts/qcom/sm6375-sony-xperia-murray-pdx225.dts
index b2f1bb1d58e9..cca2c2eb88ad 100644
--- a/arch/arm64/boot/dts/qcom/sm6375-sony-xperia-murray-pdx225.dts
+++ b/arch/arm64/boot/dts/qcom/sm6375-sony-xperia-murray-pdx225.dts
@@ -80,6 +80,15 @@
 		};
 	};
 
+	touch_avdd: touch-avdd-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "touch_avdd";
+		gpio = <&tlmm 59 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&ts_avdd_default>;
+		enable-active-high;
+	};
+
 	vph_pwr: vph-pwr-regulator {
 		compatible = "regulator-fixed";
 		regulator-name = "vph_pwr";
@@ -136,9 +145,10 @@
 		interrupts = <22 0x2008>;
 
 		vdd-supply = <&pm6125_l13>;
+		avdd-supply = <&touch_avdd>;
 
 		pinctrl-names = "default";
-		pinctrl-0 = <&ts_int_default &ts_avdd_default>;
+		pinctrl-0 = <&ts_int_default>;
 	};
 };
 
@@ -187,6 +197,11 @@
 	status = "okay";
 };
 
+&remoteproc_mss {
+	firmware-name = "qcom/sm6375/Sony/murray/modem.mbn";
+	status = "okay";
+};
+
 &rpm_requests {
 	regulators-0 {
 		compatible = "qcom,rpm-pm6125-regulators";
@@ -238,8 +253,8 @@
 		};
 
 		pm6125_l7: l7 {
-			regulator-min-microvolt = <720000>;
-			regulator-max-microvolt = <1050000>;
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <880000>;
 		};
 
 		pm6125_l8: l8 {
@@ -306,7 +321,7 @@
 
 		pm6125_l21: l21 {
 			regulator-min-microvolt = <3000000>;
-			regulator-max-microvolt = <3400000>;
+			regulator-max-microvolt = <3312000>;
 		};
 
 		pm6125_l22: l22 {
@@ -317,7 +332,7 @@
 
 		pm6125_l23: l23 {
 			regulator-min-microvolt = <3000000>;
-			regulator-max-microvolt = <3400000>;
+			regulator-max-microvolt = <3312000>;
 		};
 
 		pm6125_l24: l24 {
@@ -340,8 +355,8 @@
 		};
 
 		pmr735a_l2: l2 {
-			regulator-min-microvolt = <352000>;
-			regulator-max-microvolt = <796000>;
+			regulator-min-microvolt = <640000>;
+			regulator-max-microvolt = <640000>;
 		};
 
 		pmr735a_l3: l3 {
@@ -412,7 +427,7 @@
 		pins = "gpio59";
 		function = "gpio";
 		drive-strength = <8>;
-		output-high;
+		output-low;
 	};
 };
 
@@ -425,6 +440,18 @@
 };
 
 &usb_1_hsphy {
+	vdda-pll-supply = <&pm6125_l7>;
+	vdda18-supply = <&pm6125_l10>;
+	vdda33-supply = <&pmr735a_l7>;
+	status = "okay";
+};
+
+&wifi {
+	vdd-0.8-cx-mx-supply = <&pmr735a_l2>;
+	vdd-1.8-xo-supply = <&pm6125_l16>;
+	vdd-1.3-rfa-supply = <&pm6125_l2>;
+	vdd-3.3-ch0-supply = <&pm6125_l23>;
+	vdd-3.3-ch1-supply = <&pm6125_l21>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/qcom/sm6375.dtsi b/arch/arm64/boot/dts/qcom/sm6375.dtsi
index e7ff55443da7..7ac8bf26dda3 100644
--- a/arch/arm64/boot/dts/qcom/sm6375.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm6375.dtsi
@@ -311,6 +311,25 @@
 		};
 	};
 
+	mpm: interrupt-controller {
+		compatible = "qcom,mpm";
+		qcom,rpm-msg-ram = <&apss_mpm>;
+		interrupts = <GIC_SPI 197 IRQ_TYPE_EDGE_RISING>;
+		mboxes = <&ipcc IPCC_CLIENT_AOP IPCC_MPROC_SIGNAL_SMP2P>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		#power-domain-cells = <0>;
+		interrupt-parent = <&intc>;
+		qcom,mpm-pin-count = <96>;
+		qcom,mpm-pin-map = <5 296>,  /* Soundwire wake_irq */
+				   <12 422>, /* DWC3 ss_phy_irq */
+				   <86 183>, /* MPM wake, SPMI */
+				   <89 314>, /* TSENS0 0C */
+				   <90 315>, /* TSENS1 0C */
+				   <93 164>, /* DWC3 dm_hs_phy_irq */
+				   <94 165>; /* DWC3 dp_hs_phy_irq */
+	};
+
 	memory@80000000 {
 		device_type = "memory";
 		/* We expect the bootloader to fill in the size */
@@ -486,6 +505,7 @@
 
 		CLUSTER_PD: power-domain-cpu-cluster0 {
 			#power-domain-cells = <0>;
+			power-domains = <&mpm>;
 			domain-idle-states = <&CLUSTER_SLEEP_0>;
 		};
 	};
@@ -808,7 +828,7 @@
 			reg = <0 0x00500000 0 0x800000>;
 			interrupts = <GIC_SPI 227 IRQ_TYPE_LEVEL_HIGH>;
 			gpio-ranges = <&tlmm 0 0 157>;
-			/* TODO: Hook up MPM as wakeup-parent when it's there */
+			wakeup-parent = <&mpm>;
 			interrupt-controller;
 			gpio-controller;
 			#interrupt-cells = <2>;
@@ -896,6 +916,36 @@
 				drive-strength = <6>;
 				bias-disable;
 			};
+
+			qup_uart1_default: qup-uart1-default-state {
+				cts-pins {
+					pins = "gpio61";
+					function = "qup01";
+					drive-strength = <2>;
+					bias-pull-down;
+				};
+
+				rts-pins {
+					pins = "gpio62";
+					function = "qup01";
+					drive-strength = <2>;
+					bias-disable;
+				};
+
+				tx-pins {
+					pins = "gpio63";
+					function = "qup01";
+					drive-strength = <2>;
+					bias-disable;
+				};
+
+				rx-pins {
+					pins = "gpio64";
+					function = "qup01";
+					drive-strength = <2>;
+					bias-pull-up;
+				};
+			};
 		};
 
 		gcc: clock-controller@1400000 {
@@ -930,7 +980,7 @@
 			      <0 0x01c0a000 0 0x26000>;
 			reg-names = "core", "chnls", "obsrvr", "intr", "cnfg";
 			interrupt-names = "periph_irq";
-			interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts-extended = <&mpm 86 IRQ_TYPE_LEVEL_HIGH>;
 			qcom,ee = <0>;
 			qcom,channel = <0>;
 			#address-cells = <2>;
@@ -962,8 +1012,15 @@
 		};
 
 		rpm_msg_ram: sram@45f0000 {
-			compatible = "qcom,rpm-msg-ram";
+			compatible = "qcom,rpm-msg-ram", "mmio-sram";
 			reg = <0 0x045f0000 0 0x7000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0x0 0x045f0000 0x7000>;
+
+			apss_mpm: sram@1b8 {
+				reg = <0x1b8 0x48>;
+			};
 		};
 
 		sram@4690000 {
@@ -1111,6 +1168,19 @@
 				status = "disabled";
 			};
 
+			uart1: serial@4a84000 {
+				compatible = "qcom,geni-uart";
+				reg = <0x0 0x04a84000 0x0 0x4000>;
+				interrupts = <GIC_SPI 328 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&gcc GCC_QUPV3_WRAP0_S1_CLK>;
+				clock-names = "se";
+				power-domains = <&rpmpd SM6375_VDDCX>;
+				operating-points-v2 = <&qup_opp_table>;
+				pinctrl-0 = <&qup_uart1_default>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+
 			i2c2: i2c@4a88000 {
 				compatible = "qcom,geni-i2c";
 				reg = <0x0 0x04a88000 0x0 0x4000>;
@@ -1360,10 +1430,10 @@
 					  <&gcc GCC_USB30_PRIM_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <133333333>;
 
-			interrupts = <GIC_SPI 302 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 93 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts-extended = <&intc GIC_SPI 302 IRQ_TYPE_LEVEL_HIGH>,
+					      <&mpm 12 IRQ_TYPE_LEVEL_HIGH>,
+					      <&mpm 93 IRQ_TYPE_EDGE_BOTH>,
+					      <&mpm 94 IRQ_TYPE_EDGE_BOTH>;
 			interrupt-names = "hs_phy_irq",
 					  "ss_phy_irq",
 					  "dm_hs_phy_irq",
diff --git a/arch/arm64/boot/dts/qcom/sm8150-hdk.dts b/arch/arm64/boot/dts/qcom/sm8150-hdk.dts
index bb161b536da4..de670b407ef1 100644
--- a/arch/arm64/boot/dts/qcom/sm8150-hdk.dts
+++ b/arch/arm64/boot/dts/qcom/sm8150-hdk.dts
@@ -7,6 +7,7 @@
 
 #include <dt-bindings/regulator/qcom,rpmh-regulator.h>
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/usb/pd.h>
 #include "sm8150.dtsi"
 #include "pm8150.dtsi"
 #include "pm8150b.dtsi"
@@ -54,6 +55,17 @@
 			gpios = <&pm8150_gpios 6 GPIO_ACTIVE_LOW>;
 		};
 	};
+
+	hdmi-out {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi_con: endpoint {
+				remote-endpoint = <&lt9611_out>;
+			};
+		};
+	};
 };
 
 &apps_rsc {
@@ -127,8 +139,6 @@
 		vdda_sp_sensor:
 		vdda_ufs_2ln_core_1:
 		vdda_ufs_2ln_core_2:
-		vdda_usb_ss_dp_core_1:
-		vdda_usb_ss_dp_core_2:
 		vdda_qlink_lv:
 		vdda_qlink_lv_ck:
 		vreg_l5a_0p875: ldo5 {
@@ -210,6 +220,12 @@
 			regulator-max-microvolt = <3008000>;
 			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
 		};
+
+		vreg_l18a_0p8: ldo18 {
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <880000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
 	};
 
 	regulators-1 {
@@ -359,15 +375,210 @@
 	status = "okay";
 };
 
+&gpi_dma0 {
+	status = "okay";
+};
+
+&gpi_dma1 {
+	status = "okay";
+};
+
 &gpu {
-	/*
-	 * NOTE: "amd,imageon" makes Adreno start in headless mode, remove it
-	 * after display support is added on this board.
-	 */
-	compatible = "qcom,adreno-640.1", "qcom,adreno", "amd,imageon";
 	status = "okay";
 };
 
+&i2c4 {
+	clock-frequency = <100000>;
+
+	status = "okay";
+
+	typec-mux@42 {
+		compatible = "fcs,fsa4480";
+		reg = <0x42>;
+
+		interrupts-extended = <&tlmm 152 IRQ_TYPE_LEVEL_LOW>;
+
+		vcc-supply = <&vreg_bob>;
+		mode-switch;
+		orientation-switch;
+
+		port {
+			fsa4480_sbu_mux: endpoint {
+				remote-endpoint = <&pm8150b_typec_sbu_out>;
+			};
+		};
+	};
+};
+
+&i2c9 {
+	status = "okay";
+	clock-frequency = <400000>;
+
+	lt9611_codec: hdmi-bridge@3b {
+		compatible = "lontium,lt9611";
+		reg = <0x3b>;
+		#sound-dai-cells = <1>;
+
+		interrupts-extended = <&tlmm 9 IRQ_TYPE_EDGE_FALLING>;
+
+		reset-gpios = <&tlmm 7 GPIO_ACTIVE_HIGH>;
+
+		vdd-supply = <&vreg_s4a_1p8>;
+		vcc-supply = <&vreg_bob>;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&lt9611_irq_pin>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				lt9611_a: endpoint {
+					remote-endpoint = <&mdss_dsi0_out>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				lt9611_b: endpoint {
+					remote-endpoint = <&mdss_dsi1_out>;
+				};
+			};
+
+			port@2 {
+				reg = <2>;
+
+				lt9611_out: endpoint {
+					remote-endpoint = <&hdmi_con>;
+				};
+			};
+		};
+	};
+};
+
+&mdss {
+	status = "okay";
+};
+
+&mdss_dp {
+	status = "okay";
+};
+
+&mdss_dp_out {
+	data-lanes = <0 1>;
+	remote-endpoint = <&usb_1_qmpphy_dp_in>;
+};
+
+&mdss_dsi0 {
+	status = "okay";
+	vdda-supply = <&vreg_l3c_1p2>;
+
+	qcom,dual-dsi-mode;
+	qcom,master-dsi;
+
+	ports {
+		port@1 {
+			endpoint {
+				remote-endpoint = <&lt9611_a>;
+				data-lanes = <0 1 2 3>;
+			};
+		};
+	};
+};
+
+&mdss_dsi0_phy {
+	status = "okay";
+	vdds-supply = <&vreg_l5a_0p875>;
+};
+
+&mdss_dsi1 {
+	vdda-supply = <&vreg_l3c_1p2>;
+
+	qcom,dual-dsi-mode;
+
+	/* DSI1 is slave, so use DSI0 clocks */
+	assigned-clock-parents = <&mdss_dsi0_phy 0>, <&mdss_dsi0_phy 1>;
+
+	status = "okay";
+
+	ports {
+		port@1 {
+			endpoint {
+				remote-endpoint = <&lt9611_b>;
+				data-lanes = <0 1 2 3>;
+			};
+		};
+	};
+};
+
+&mdss_dsi1_phy {
+	vdds-supply = <&vreg_l5a_0p875>;
+	status = "okay";
+};
+
+&pm8150b_vbus {
+	regulator-min-microamp = <500000>;
+	regulator-max-microamp = <3000000>;
+	status = "okay";
+};
+
+&pm8150b_typec {
+	status = "okay";
+
+	vdd-pdphy-supply = <&vreg_l2a_3p1>;
+
+	connector {
+		compatible = "usb-c-connector";
+
+		power-role = "source";
+		data-role = "dual";
+		self-powered;
+
+		source-pdos = <PDO_FIXED(5000, 3000,
+					 PDO_FIXED_DUAL_ROLE |
+					 PDO_FIXED_USB_COMM |
+					 PDO_FIXED_DATA_SWAP)>;
+
+		altmodes {
+			displayport {
+				svid = /bits/ 16 <0xff01>;
+				vdo = <0x00001c46>;
+			};
+		};
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+				pm8150b_role_switch_in: endpoint {
+					remote-endpoint = <&usb_1_dwc3_hs>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				pm8150b_typec_mux_in: endpoint {
+					remote-endpoint = <&usb_1_qmpphy_out>;
+				};
+			};
+
+			port@2 {
+				reg = <2>;
+
+				pm8150b_typec_sbu_out: endpoint {
+					remote-endpoint = <&fsa4480_sbu_mux>;
+				};
+			};
+		};
+	};
+};
+
 &pon_pwrkey {
 	status = "okay";
 };
@@ -378,6 +589,10 @@
 	linux,code = <KEY_VOLUMEDOWN>;
 };
 
+&qupv3_id_0 {
+	status = "okay";
+};
+
 &qupv3_id_1 {
 	status = "okay";
 };
@@ -402,6 +617,13 @@
 
 &tlmm {
 	gpio-reserved-ranges = <0 4>, <126 4>;
+
+	lt9611_irq_pin: lt9611-irq-state {
+		pins = "gpio9";
+		function = "gpio";
+		bias-disable;
+	};
+
 };
 
 &uart2 {
@@ -445,13 +667,26 @@
 &usb_1_qmpphy {
 	status = "okay";
 	vdda-phy-supply = <&vreg_l3c_1p2>;
-	vdda-pll-supply = <&vdda_usb_ss_dp_core_1>;
+	vdda-pll-supply = <&vreg_l18a_0p8>;
+	orientation-switch;
+};
+
+&usb_1_qmpphy_dp_in {
+	remote-endpoint = <&mdss_dp_out>;
+};
+
+&usb_1_qmpphy_out {
+	remote-endpoint = <&pm8150b_typec_mux_in>;
+};
+
+&usb_1_qmpphy_usb_ss_in {
+	remote-endpoint = <&usb_1_dwc3_ss>;
 };
 
 &usb_2_qmpphy {
 	status = "okay";
 	vdda-phy-supply = <&vreg_l3c_1p2>;
-	vdda-pll-supply = <&vdda_usb_ss_dp_core_1>;
+	vdda-pll-supply = <&vreg_l5a_0p875>;
 };
 
 &usb_1 {
@@ -463,7 +698,16 @@
 };
 
 &usb_1_dwc3 {
-	dr_mode = "peripheral";
+	dr_mode = "otg";
+	usb-role-switch;
+};
+
+&usb_1_dwc3_hs {
+	remote-endpoint = <&pm8150b_role_switch_in>;
+};
+
+&usb_1_dwc3_ss {
+	remote-endpoint = <&usb_1_qmpphy_usb_ss_in>;
 };
 
 &usb_2_dwc3 {
diff --git a/arch/arm64/boot/dts/qcom/sm8150.dtsi b/arch/arm64/boot/dts/qcom/sm8150.dtsi
index 97623af13464..761a6757dc26 100644
--- a/arch/arm64/boot/dts/qcom/sm8150.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8150.dtsi
@@ -1824,7 +1824,7 @@
 			      <0x0 0x010ad000 0x0 0x3000>;
 		};
 
-		pcie0: pci@1c00000 {
+		pcie0: pcie@1c00000 {
 			compatible = "qcom,pcie-sm8150";
 			reg = <0 0x01c00000 0 0x3000>,
 			      <0 0x60000000 0 0xf1d>,
@@ -1878,7 +1878,7 @@
 			phys = <&pcie0_phy>;
 			phy-names = "pciephy";
 
-			perst-gpio = <&tlmm 35 GPIO_ACTIVE_HIGH>;
+			perst-gpios = <&tlmm 35 GPIO_ACTIVE_HIGH>;
 			enable-gpio = <&tlmm 37 GPIO_ACTIVE_HIGH>;
 
 			pinctrl-names = "default";
@@ -1915,7 +1915,7 @@
 			status = "disabled";
 		};
 
-		pcie1: pci@1c08000 {
+		pcie1: pcie@1c08000 {
 			compatible = "qcom,pcie-sm8150";
 			reg = <0 0x01c08000 0 0x3000>,
 			      <0 0x40000000 0 0xf1d>,
@@ -1972,7 +1972,7 @@
 			phys = <&pcie1_phy>;
 			phy-names = "pciephy";
 
-			perst-gpio = <&tlmm 102 GPIO_ACTIVE_HIGH>;
+			perst-gpios = <&tlmm 102 GPIO_ACTIVE_HIGH>;
 			enable-gpio = <&tlmm 104 GPIO_ACTIVE_HIGH>;
 
 			pinctrl-names = "default";
@@ -2016,7 +2016,7 @@
 			      <0 0x01d90000 0 0x8000>;
 			reg-names = "std", "ice";
 			interrupts = <GIC_SPI 265 IRQ_TYPE_LEVEL_HIGH>;
-			phys = <&ufs_mem_phy_lanes>;
+			phys = <&ufs_mem_phy>;
 			phy-names = "ufsphy";
 			lanes-per-direction = <2>;
 			#reset-cells = <1>;
@@ -2061,10 +2061,8 @@
 
 		ufs_mem_phy: phy@1d87000 {
 			compatible = "qcom,sm8150-qmp-ufs-phy";
-			reg = <0 0x01d87000 0 0x1c0>;
-			#address-cells = <2>;
-			#size-cells = <2>;
-			ranges;
+			reg = <0 0x01d87000 0 0x1000>;
+
 			clock-names = "ref",
 				      "ref_aux";
 			clocks = <&gcc GCC_UFS_MEM_CLKREF_CLK>,
@@ -2074,16 +2072,10 @@
 
 			resets = <&ufs_mem_hc 0>;
 			reset-names = "ufsphy";
-			status = "disabled";
 
-			ufs_mem_phy_lanes: phy@1d87400 {
-				reg = <0 0x01d87400 0 0x16c>,
-				      <0 0x01d87600 0 0x200>,
-				      <0 0x01d87c00 0 0x200>,
-				      <0 0x01d87800 0 0x16c>,
-				      <0 0x01d87a00 0 0x200>;
-				#phy-cells = <0>;
-			};
+			#phy-cells = <0>;
+
+			status = "disabled";
 		};
 
 		cryptobam: dma-controller@1dc4000 {
@@ -2957,11 +2949,8 @@
 			};
 
 			in-ports {
-				#address-cells = <1>;
-				#size-cells = <0>;
 
-				port@1 {
-					reg = <1>;
+				port {
 					replicator1_in: endpoint {
 						remote-endpoint = <&replicator_out1>;
 					};
@@ -3447,37 +3436,56 @@
 			#phy-cells = <1>;
 
 			status = "disabled";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+
+					usb_1_qmpphy_out: endpoint {
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+
+					usb_1_qmpphy_usb_ss_in: endpoint {
+					};
+				};
+
+				port@2 {
+					reg = <2>;
+
+					usb_1_qmpphy_dp_in: endpoint {
+					};
+				};
+			};
 		};
 
 		usb_2_qmpphy: phy@88eb000 {
 			compatible = "qcom,sm8150-qmp-usb3-uni-phy";
-			reg = <0 0x088eb000 0 0x200>;
-			status = "disabled";
-			#address-cells = <2>;
-			#size-cells = <2>;
-			ranges;
+			reg = <0 0x088eb000 0 0x1000>;
 
 			clocks = <&gcc GCC_USB3_SEC_PHY_AUX_CLK>,
-				 <&rpmhcc RPMH_CXO_CLK>,
 				 <&gcc GCC_USB3_SEC_CLKREF_CLK>,
-				 <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>;
-			clock-names = "aux", "ref_clk_src", "ref", "com_aux";
+				 <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>,
+				 <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>;
+			clock-names = "aux",
+				      "ref",
+				      "com_aux",
+				      "pipe";
+			clock-output-names = "usb3_uni_phy_pipe_clk_src";
+			#clock-cells = <0>;
+			#phy-cells = <0>;
 
-			resets = <&gcc GCC_USB3PHY_PHY_SEC_BCR>,
-				 <&gcc GCC_USB3_PHY_SEC_BCR>;
-			reset-names = "phy", "common";
+			resets = <&gcc GCC_USB3_PHY_SEC_BCR>,
+				 <&gcc GCC_USB3PHY_PHY_SEC_BCR>;
+			reset-names = "phy",
+				      "phy_phy";
 
-			usb_2_ssphy: phy@88eb200 {
-				reg = <0 0x088eb200 0 0x200>,
-				      <0 0x088eb400 0 0x200>,
-				      <0 0x088eb800 0 0x800>,
-				      <0 0x088eb600 0 0x200>;
-				#clock-cells = <0>;
-				#phy-cells = <0>;
-				clocks = <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>;
-				clock-names = "pipe0";
-				clock-output-names = "usb3_uni_phy_pipe_clk_src";
-			};
+			status = "disabled";
 		};
 
 		sdhc_2: mmc@8804000 {
@@ -3565,10 +3573,10 @@
 					  <&gcc GCC_USB30_PRIM_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <200000000>;
 
-			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 486 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 488 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 489 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 6 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 8 IRQ_TYPE_EDGE_BOTH>,
+					      <&pdc 9 IRQ_TYPE_EDGE_BOTH>;
 			interrupt-names = "hs_phy_irq", "ss_phy_irq",
 					  "dm_hs_phy_irq", "dp_hs_phy_irq";
 
@@ -3589,6 +3597,25 @@
 				snps,dis_enblslpm_quirk;
 				phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>;
 				phy-names = "usb2-phy", "usb3-phy";
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+
+						usb_1_dwc3_hs: endpoint {
+						};
+					};
+
+					port@1 {
+						reg = <1>;
+
+						usb_1_dwc3_ss: endpoint {
+						};
+					};
+				};
 			};
 		};
 
@@ -3618,10 +3645,10 @@
 					  <&gcc GCC_USB30_SEC_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <200000000>;
 
-			interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 487 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 490 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 491 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts-extended = <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 7 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 10 IRQ_TYPE_EDGE_BOTH>,
+					      <&pdc 11 IRQ_TYPE_EDGE_BOTH>;
 			interrupt-names = "hs_phy_irq", "ss_phy_irq",
 					  "dm_hs_phy_irq", "dp_hs_phy_irq";
 
@@ -3640,7 +3667,7 @@
 				iommus = <&apps_smmu 0x160 0>;
 				snps,dis_u2_susphy_quirk;
 				snps,dis_enblslpm_quirk;
-				phys = <&usb_2_hsphy>, <&usb_2_ssphy>;
+				phys = <&usb_2_hsphy>, <&usb_2_qmpphy>;
 				phy-names = "usb2-phy", "usb3-phy";
 			};
 		};
@@ -3719,6 +3746,13 @@
 							remote-endpoint = <&mdss_dsi1_in>;
 						};
 					};
+
+					port@2 {
+						reg = <2>;
+						dpu_intf0_out: endpoint {
+							remote-endpoint = <&mdss_dp_in>;
+						};
+					};
 				};
 
 				mdp_opp_table: opp-table {
@@ -3746,6 +3780,86 @@
 				};
 			};
 
+			mdss_dp: displayport-controller@ae90000 {
+				compatible = "qcom,sm8150-dp", "qcom,sm8350-dp";
+				reg = <0 0xae90000 0 0x200>,
+				      <0 0xae90200 0 0x200>,
+				      <0 0xae90400 0 0x600>,
+				      <0 0x0ae90a00 0 0x600>,
+				      <0 0x0ae91000 0 0x600>;
+
+				interrupt-parent = <&mdss>;
+				interrupts = <12>;
+				clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
+					 <&dispcc DISP_CC_MDSS_DP_AUX_CLK>,
+					 <&dispcc DISP_CC_MDSS_DP_LINK_CLK>,
+					 <&dispcc DISP_CC_MDSS_DP_LINK_INTF_CLK>,
+					 <&dispcc DISP_CC_MDSS_DP_PIXEL_CLK>;
+				clock-names = "core_iface",
+					      "core_aux",
+					      "ctrl_link",
+					      "ctrl_link_iface",
+					      "stream_pixel";
+
+				assigned-clocks = <&dispcc DISP_CC_MDSS_DP_LINK_CLK_SRC>,
+						  <&dispcc DISP_CC_MDSS_DP_PIXEL_CLK_SRC>;
+				assigned-clock-parents = <&usb_1_qmpphy QMP_USB43DP_DP_LINK_CLK>,
+							 <&usb_1_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>;
+
+				phys = <&usb_1_qmpphy QMP_USB43DP_DP_PHY>;
+				phy-names = "dp";
+
+				#sound-dai-cells = <0>;
+
+				operating-points-v2 = <&dp_opp_table>;
+				power-domains = <&rpmhpd SM8250_MMCX>;
+
+				status = "disabled";
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+						mdss_dp_in: endpoint {
+							remote-endpoint = <&dpu_intf0_out>;
+						};
+					};
+
+					port@1 {
+						reg = <1>;
+
+						mdss_dp_out: endpoint {
+						};
+					};
+				};
+
+				dp_opp_table: opp-table {
+					compatible = "operating-points-v2";
+
+					opp-160000000 {
+						opp-hz = /bits/ 64 <160000000>;
+						required-opps = <&rpmhpd_opp_low_svs>;
+					};
+
+					opp-270000000 {
+						opp-hz = /bits/ 64 <270000000>;
+						required-opps = <&rpmhpd_opp_svs>;
+					};
+
+					opp-540000000 {
+						opp-hz = /bits/ 64 <540000000>;
+						required-opps = <&rpmhpd_opp_svs_l1>;
+					};
+
+					opp-810000000 {
+						opp-hz = /bits/ 64 <810000000>;
+						required-opps = <&rpmhpd_opp_nom>;
+					};
+				};
+			};
+
 			mdss_dsi0: dsi@ae94000 {
 				compatible = "qcom,sm8150-dsi-ctrl", "qcom,mdss-dsi-ctrl";
 				reg = <0 0x0ae94000 0 0x400>;
@@ -3932,6 +4046,7 @@
 				      "dp_phy_pll_link_clk",
 				      "dp_phy_pll_vco_div_clk";
 			power-domains = <&rpmhpd SM8150_MMCX>;
+			required-opps = <&rpmhpd_opp_low_svs>;
 			#clock-cells = <1>;
 			#reset-cells = <1>;
 			#power-domain-cells = <1>;
@@ -4170,7 +4285,7 @@
 			compatible = "qcom,apss-wdt-sm8150", "qcom,kpss-wdt";
 			reg = <0 0x17c10000 0 0x1000>;
 			clocks = <&sleep_clk>;
-			interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 0 IRQ_TYPE_EDGE_RISING>;
 		};
 
 		timer@17c20000 {
diff --git a/arch/arm64/boot/dts/qcom/sm8250-xiaomi-elish-common.dtsi b/arch/arm64/boot/dts/qcom/sm8250-xiaomi-elish-common.dtsi
index 85e5cf3dc91e..946365f15a59 100644
--- a/arch/arm64/boot/dts/qcom/sm8250-xiaomi-elish-common.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8250-xiaomi-elish-common.dtsi
@@ -6,6 +6,7 @@
 #include <dt-bindings/arm/qcom,ids.h>
 #include <dt-bindings/phy/phy.h>
 #include <dt-bindings/regulator/qcom,rpmh-regulator.h>
+#include <dt-bindings/usb/pd.h>
 #include "sm8250.dtsi"
 #include "pm8150.dtsi"
 #include "pm8150b.dtsi"
@@ -23,7 +24,7 @@
 /delete-node/ &xbl_aop_mem;
 
 / {
-	classis-type = "tablet";
+	chassis-type = "tablet";
 
 	/* required for bootloader to select correct board */
 	qcom,msm-id = <QCOM_ID_SM8250 0x20001>; /* SM8250 v2.1 */
@@ -114,7 +115,7 @@
 	};
 
 	reserved-memory {
-		xbl_aop_mem: xbl-aop@80700000 {
+		xbl_aop_mem: xbl-aop@80600000 {
 			reg = <0x0 0x80600000 0x0 0x260000>;
 			no-map;
 		};
@@ -627,6 +628,41 @@
 	};
 };
 
+&pm8150b_typec {
+	vdd-pdphy-supply = <&vreg_l2a_3p1>;
+	status = "okay";
+
+	connector {
+		compatible = "usb-c-connector";
+
+		power-role = "source";
+		data-role = "dual";
+		self-powered;
+
+		source-pdos = <PDO_FIXED(5000, 3000,
+					 PDO_FIXED_DUAL_ROLE |
+					 PDO_FIXED_USB_COMM |
+					 PDO_FIXED_DATA_SWAP)>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				pm8150b_role_switch_in: endpoint {
+					remote-endpoint = <&usb_1_role_switch_out>;
+				};
+			};
+		};
+	};
+};
+
+&pm8150b_vbus {
+	status = "okay";
+};
+
 &pon_pwrkey {
 	status = "okay";
 };
@@ -664,11 +700,12 @@
 };
 
 &usb_1_dwc3 {
-	dr_mode = "peripheral";
+	dr_mode = "otg";
 	maximum-speed = "high-speed";
 	/* Remove USB3 phy */
 	phys = <&usb_1_hsphy>;
 	phy-names = "usb2-phy";
+	usb-role-switch;
 };
 
 &usb_1_hsphy {
@@ -678,6 +715,10 @@
 	status = "okay";
 };
 
+&usb_1_role_switch_out {
+	remote-endpoint = <&pm8150b_role_switch_in>;
+};
+
 &ufs_mem_hc {
 	vcc-supply = <&vreg_l17a_3p0>;
 	vcc-max-microamp = <800000>;
diff --git a/arch/arm64/boot/dts/qcom/sm8250-xiaomi-pipa.dts b/arch/arm64/boot/dts/qcom/sm8250-xiaomi-pipa.dts
new file mode 100644
index 000000000000..86e1f7fd1c20
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/sm8250-xiaomi-pipa.dts
@@ -0,0 +1,623 @@
+// SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+/*
+ * Copyright (c) 2023 Luka Panio <lukapanio@gmail.com>
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/arm/qcom,ids.h>
+#include <dt-bindings/phy/phy.h>
+#include <dt-bindings/regulator/qcom,rpmh-regulator.h>
+#include "sm8250.dtsi"
+#include "pm8150.dtsi"
+#include "pm8150b.dtsi"
+#include "pm8150l.dtsi"
+#include "pm8009.dtsi"
+
+/*
+ * Delete following upstream (sm8250.dtsi) reserved
+ * memory mappings which are different on this device.
+ */
+/delete-node/ &adsp_mem;
+/delete-node/ &cdsp_secure_heap;
+/delete-node/ &slpi_mem;
+/delete-node/ &spss_mem;
+/delete-node/ &xbl_aop_mem;
+
+/ {
+
+	model = "Xiaomi Pad 6";
+	compatible = "xiaomi,pipa", "qcom,sm8250";
+
+	chassis-type = "tablet";
+
+	/* required for bootloader to select correct board */
+	qcom,msm-id = <QCOM_ID_SM8250 0x20001>; /* SM8250 v2.1 */
+	qcom,board-id = <0x34 0>;
+
+	chosen {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		framebuffer: framebuffer@9c000000 {
+			compatible = "simple-framebuffer";
+			reg = <0x0 0x9c000000 0x0 0x2300000>;
+			width = <1800>;
+			height = <2880>;
+			stride = <(1800 * 4)>;
+			format = "a8r8g8b8";
+		};
+	};
+
+	battery_l: battery-l {
+		compatible = "simple-battery";
+		voltage-min-design-microvolt = <3870000>;
+		energy-full-design-microwatt-hours = <16700000>;
+		charge-full-design-microamp-hours = <4420000>;
+	};
+
+	battery_r: battery-r {
+		compatible = "simple-battery";
+		voltage-min-design-microvolt = <3870000>;
+		energy-full-design-microwatt-hours = <16700000>;
+		charge-full-design-microamp-hours = <4420000>;
+	};
+
+	bl_vddpos_5p5: bl-vddpos-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "bl_vddpos_5p5";
+		regulator-min-microvolt = <5500000>;
+		regulator-max-microvolt = <5500000>;
+		regulator-enable-ramp-delay = <233>;
+		gpio = <&tlmm 130 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		regulator-boot-on;
+	};
+
+	bl_vddneg_5p5: bl-vddneg-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "bl_vddneg_5p5";
+		regulator-min-microvolt = <5500000>;
+		regulator-max-microvolt = <5500000>;
+		regulator-enable-ramp-delay = <233>;
+		gpio = <&tlmm 131 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		regulator-boot-on;
+	};
+
+	gpio_keys: gpio-keys {
+		compatible = "gpio-keys";
+
+		pinctrl-0 = <&vol_up_n>;
+		pinctrl-names = "default";
+
+		key-vol-up {
+			label = "Volume Up";
+			gpios = <&pm8150_gpios 6 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_VOLUMEUP>;
+			debounce-interval = <15>;
+			linux,can-disable;
+			wakeup-source;
+		};
+	};
+
+	vph_pwr: vph-pwr-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vph_pwr";
+		regulator-min-microvolt = <3700000>;
+		regulator-max-microvolt = <3700000>;
+	};
+
+	/* S6c is really ebi.lvl but it's there for supply map completeness sake. */
+	vreg_s6c_0p88: smpc6-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vreg_s6c_0p88";
+		regulator-min-microvolt = <880000>;
+		regulator-max-microvolt = <880000>;
+		regulator-always-on;
+		vin-supply = <&vph_pwr>;
+	};
+
+	reserved-memory {
+		xbl_aop_mem: xbl-aop@80700000 {
+			reg = <0x0 0x80600000 0x0 0x260000>;
+			no-map;
+		};
+
+		slpi_mem: slpi@88c00000 {
+			reg = <0x0 0x88c00000 0x0 0x2f00000>;
+			no-map;
+		};
+
+		adsp_mem: adsp@8bb00000 {
+			reg = <0x0 0x8bb00000 0x0 0x2500000>;
+			no-map;
+		};
+
+		spss_mem: spss@8e000000 {
+			reg = <0x0 0x8e000000 0x0 0x100000>;
+			no-map;
+		};
+
+		cdsp_secure_heap: cdsp-secure-heap@8e100000 {
+			reg = <0x0 0x8e100000 0x0 0x4600000>;
+			no-map;
+		};
+
+		cont_splash_mem: cont-splash@9c000000 {
+			reg = <0x0 0x9c000000 0x0 0x2300000>;
+			no-map;
+		};
+
+		ramoops@b0000000 {
+			compatible = "ramoops";
+			reg = <0x0 0xb0000000 0x0 0x400000>;
+			record-size = <0x1000>;
+			console-size = <0x200000>;
+			ecc-size = <16>;
+			no-map;
+		};
+	};
+};
+
+&adsp {
+	firmware-name = "qcom/sm8250/xiaomi/pipa/adsp.mbn";
+	status = "okay";
+};
+
+&apps_rsc {
+	regulators-0 {
+		compatible = "qcom,pm8150-rpmh-regulators";
+		qcom,pmic-id = "a";
+
+		vdd-s1-supply = <&vph_pwr>;
+		vdd-s2-supply = <&vph_pwr>;
+		vdd-s3-supply = <&vph_pwr>;
+		vdd-s4-supply = <&vph_pwr>;
+		vdd-s5-supply = <&vph_pwr>;
+		vdd-s6-supply = <&vph_pwr>;
+		vdd-s7-supply = <&vph_pwr>;
+		vdd-s8-supply = <&vph_pwr>;
+		vdd-s9-supply = <&vph_pwr>;
+		vdd-s10-supply = <&vph_pwr>;
+		vdd-l1-l8-l11-supply = <&vreg_s6c_0p88>;
+		vdd-l2-l10-supply = <&vreg_bob>;
+		vdd-l3-l4-l5-l18-supply = <&vreg_s6a_0p95>;
+		vdd-l6-l9-supply = <&vreg_s8c_1p35>;
+		vdd-l7-l12-l14-l15-supply = <&vreg_s5a_1p9>;
+		vdd-l13-l16-l17-supply = <&vreg_bob>;
+
+		/* (S1+S2+S3) - cx.lvl (ARC) */
+
+		vreg_s4a_1p8: smps4 {
+			regulator-name = "vreg_s4a_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s5a_1p9: smps5 {
+			regulator-name = "vreg_s5a_1p9";
+			regulator-min-microvolt = <1900000>;
+			regulator-max-microvolt = <2040000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s6a_0p95: smps6 {
+			regulator-name = "vreg_s6a_0p95";
+			regulator-min-microvolt = <600000>;
+			regulator-max-microvolt = <1128000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2a_3p1: ldo2 {
+			regulator-name = "vreg_l2a_3p1";
+			regulator-min-microvolt = <3072000>;
+			regulator-max-microvolt = <3072000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3a_0p9: ldo3 {
+			regulator-name = "vreg_l3a_0p9";
+			regulator-min-microvolt = <928000>;
+			regulator-max-microvolt = <932000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		/* L4 - lmx.lvl (ARC) */
+
+		vreg_l5a_0p88: ldo5 {
+			regulator-name = "vreg_l5a_0p88";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <880000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6a_1p2: ldo6 {
+			regulator-name = "vreg_l6a_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		/* L7 is unused. */
+
+		vreg_l9a_1p2: ldo9 {
+			regulator-name = "vreg_l9a_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		/* L10 is unused, L11 - lcx.lvl (ARC) */
+
+		vreg_l12a_1p8: ldo12 {
+			regulator-name = "vreg_l12a_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		/* L13 is unused. */
+
+		vreg_l14a_1p88: ldo14 {
+			regulator-name = "vreg_l14a_1p88";
+			regulator-min-microvolt = <1880000>;
+			regulator-max-microvolt = <1880000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		/* L15 & L16 are unused. */
+
+		vreg_l17a_3p0: ldo17 {
+			regulator-name = "vreg_l17a_3p0";
+			regulator-min-microvolt = <2496000>;
+			regulator-max-microvolt = <3008000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l18a_0p9: ldo18 {
+			regulator-name = "vreg_l18a_0p9";
+			regulator-min-microvolt = <800000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-1 {
+		compatible = "qcom,pm8150l-rpmh-regulators";
+		qcom,pmic-id = "c";
+
+		vdd-s1-supply = <&vph_pwr>;
+		vdd-s2-supply = <&vph_pwr>;
+		vdd-s3-supply = <&vph_pwr>;
+		vdd-s4-supply = <&vph_pwr>;
+		vdd-s5-supply = <&vph_pwr>;
+		vdd-s6-supply = <&vph_pwr>;
+		vdd-s7-supply = <&vph_pwr>;
+		vdd-s8-supply = <&vph_pwr>;
+		vdd-l1-l8-supply = <&vreg_s4a_1p8>;
+		vdd-l2-l3-supply = <&vreg_s8c_1p35>;
+		vdd-l4-l5-l6-supply = <&vreg_bob>;
+		vdd-l7-l11-supply = <&vreg_bob>;
+		vdd-l9-l10-supply = <&vreg_bob>;
+		vdd-bob-supply = <&vph_pwr>;
+
+		vreg_bob: bob {
+			regulator-name = "vreg_bob";
+			regulator-min-microvolt = <3350000>;
+			regulator-max-microvolt = <3960000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_AUTO>;
+		};
+
+		/*
+		 * S1-S6 are ARCs:
+		 * (S1+S2) - gfx.lvl,
+		 * S3 - mx.lvl,
+		 * (S4+S5) - mmcx.lvl,
+		 * S6 - ebi.lvl
+		 */
+
+		vreg_s7c_0p35: smps7 {
+			regulator-name = "vreg_s7c_0p35";
+			regulator-min-microvolt = <348000>;
+			regulator-max-microvolt = <1000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s8c_1p35: smps8 {
+			regulator-name = "vreg_s8c_1p35";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1400000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l1c_1p8: ldo1 {
+			regulator-name = "vreg_l1c_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		/* L2-4 are unused. */
+
+		vreg_l5c_1p8: ldo5 {
+			regulator-name = "vreg_l5c_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6c_2p9: ldo6 {
+			regulator-name = "vreg_l6c_2p9";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2960000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l7c_2p85: ldo7 {
+			regulator-name = "vreg_l7c_2p85";
+			regulator-min-microvolt = <2856000>;
+			regulator-max-microvolt = <3104000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l8c_1p8: ldo8 {
+			regulator-name = "vreg_l8c_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l9c_2p9: ldo9 {
+			regulator-name = "vreg_l9c_2p9";
+			regulator-min-microvolt = <2704000>;
+			regulator-max-microvolt = <2960000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l10c_3p3: ldo10 {
+			regulator-name = "vreg_l10c_3p3";
+			regulator-min-microvolt = <3000000>;
+			regulator-max-microvolt = <3312000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l11c_3p0: ldo11 {
+			regulator-name = "vreg_l11c_3p0";
+			regulator-min-microvolt = <3104000>;
+			regulator-max-microvolt = <3304000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-2 {
+		compatible = "qcom,pm8009-rpmh-regulators";
+		qcom,pmic-id = "f";
+
+		vdd-s1-supply = <&vph_pwr>;
+		vdd-s2-supply = <&vreg_bob>;
+		vdd-l2-supply = <&vreg_s8c_1p35>;
+		vdd-l5-l6-supply = <&vreg_bob>;
+		vdd-l7-supply = <&vreg_s4a_1p8>;
+
+		vreg_s1f_1p2: smps1 {
+			regulator-name = "vreg_s1f_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1300000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s2f_0p5: smps2 {
+			regulator-name = "vreg_s2f_0p5";
+			regulator-min-microvolt = <512000>;
+			regulator-max-microvolt = <1100000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		/* L1 is unused. */
+
+		vreg_l2f_1p3: ldo2 {
+			regulator-name = "vreg_l2f_1p3";
+			regulator-min-microvolt = <1056000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		/* L3 & L4 are unused. */
+
+		vreg_l5f_2p8: ldo5 {
+			regulator-name = "vreg_l5f_2p85";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <3000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6f_2p8: ldo6 {
+			regulator-name = "vreg_l6f_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <3000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l7f_1p8: ldo7 {
+			regulator-name = "vreg_l7f_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+};
+
+&cdsp {
+	firmware-name = "qcom/sm8250/xiaomi/pipa/cdsp.mbn";
+	status = "okay";
+};
+
+&gmu {
+	status = "okay";
+};
+
+&gpi_dma0 {
+	status = "okay";
+};
+
+&gpi_dma1 {
+	status = "okay";
+};
+
+&gpi_dma2 {
+	status = "okay";
+};
+
+&gpu {
+	status = "okay";
+
+	zap-shader {
+		memory-region = <&gpu_mem>;
+		firmware-name = "qcom/sm8250/xiaomi/pipa/a650_zap.mbn";
+	};
+};
+
+&i2c0 {
+	clock-frequency = <400000>;
+	status = "okay";
+
+	fuel-gauge@55 {
+		compatible = "ti,bq27z561";
+		reg = <0x55>;
+		monitored-battery = <&battery_r>;
+	};
+};
+
+&i2c11 {
+	clock-frequency = <400000>;
+	status = "okay";
+
+	backlight: backlight@11 {
+		compatible = "kinetic,ktz8866";
+		reg = <0x11>;
+		vddpos-supply = <&bl_vddpos_5p5>;
+		vddneg-supply = <&bl_vddneg_5p5>;
+		enable-gpios = <&tlmm 139 GPIO_ACTIVE_HIGH>;
+		current-num-sinks = <5>;
+		kinetic,current-ramp-delay-ms = <128>;
+		kinetic,led-enable-ramp-delay-ms = <1>;
+		kinetic,enable-lcd-bias;
+	};
+};
+
+&i2c13 {
+	clock-frequency = <400000>;
+	status = "okay";
+
+	fuel-gauge@55 {
+		compatible = "ti,bq27z561";
+		reg = <0x55>;
+		monitored-battery = <&battery_l>;
+	};
+};
+
+&pcie0 {
+	status = "okay";
+};
+
+&pcie0_phy {
+	vdda-phy-supply = <&vreg_l5a_0p88>;
+	vdda-pll-supply = <&vreg_l9a_1p2>;
+	status = "okay";
+};
+
+&pm8150_gpios {
+	vol_up_n: vol-up-n-state {
+		pins = "gpio6";
+		function = "normal";
+		power-source = <1>;
+		input-enable;
+		bias-pull-up;
+	};
+};
+
+&pon_pwrkey {
+	status = "okay";
+};
+
+&pon_resin {
+	linux,code = <KEY_VOLUMEDOWN>;
+	status = "okay";
+};
+
+&qupv3_id_0 {
+	status = "okay";
+};
+
+&qupv3_id_1 {
+	status = "okay";
+};
+
+&qupv3_id_2 {
+	status = "okay";
+};
+
+&slpi {
+	firmware-name = "qcom/sm8250/xiaomi/pipa/slpi.mbn";
+	status = "okay";
+};
+
+&usb_1 {
+	status = "okay";
+};
+
+&usb_1_dwc3 {
+	dr_mode = "peripheral";
+};
+
+&usb_1_hsphy {
+	vdda-pll-supply = <&vreg_l5a_0p88>;
+	vdda18-supply = <&vreg_l12a_1p8>;
+	vdda33-supply = <&vreg_l2a_3p1>;
+	status = "okay";
+};
+
+&usb_1_qmpphy {
+	status = "okay";
+	vdda-phy-supply = <&vreg_l9a_1p2>;
+	vdda-pll-supply = <&vreg_l18a_0p9>;
+};
+
+&ufs_mem_hc {
+	vcc-supply = <&vreg_l17a_3p0>;
+	vcc-max-microamp = <800000>;
+	vccq-supply = <&vreg_l6a_1p2>;
+	vccq-max-microamp = <800000>;
+	vccq2-supply = <&vreg_s4a_1p8>;
+	vccq2-max-microamp = <800000>;
+	status = "okay";
+};
+
+&ufs_mem_phy {
+	vdda-phy-supply = <&vreg_l5a_0p88>;
+	vdda-pll-supply = <&vreg_l9a_1p2>;
+	status = "okay";
+};
+
+&venus {
+	firmware-name = "qcom/sm8250/xiaomi/pipa/venus.mbn";
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi
index be970472f6c4..760501c1301a 100644
--- a/arch/arm64/boot/dts/qcom/sm8250.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi
@@ -671,6 +671,7 @@
 	firmware {
 		scm: scm {
 			compatible = "qcom,scm-sm8250", "qcom,scm";
+			qcom,dload-mode = <&tcsr 0x13000>;
 			#reset-cells = <1>;
 		};
 	};
@@ -2123,7 +2124,7 @@
 			qcom,bcm-voters = <&apps_bcm_voter>;
 		};
 
-		pcie0: pci@1c00000 {
+		pcie0: pcie@1c00000 {
 			compatible = "qcom,pcie-sm8250";
 			reg = <0 0x01c00000 0 0x3000>,
 			      <0 0x60000000 0 0xf1d>,
@@ -2227,7 +2228,7 @@
 			status = "disabled";
 		};
 
-		pcie1: pci@1c08000 {
+		pcie1: pcie@1c08000 {
 			compatible = "qcom,pcie-sm8250";
 			reg = <0 0x01c08000 0 0x3000>,
 			      <0 0x40000000 0 0xf1d>,
@@ -2328,7 +2329,7 @@
 			status = "disabled";
 		};
 
-		pcie2: pci@1c10000 {
+		pcie2: pcie@1c10000 {
 			compatible = "qcom,pcie-sm8250";
 			reg = <0 0x01c10000 0 0x3000>,
 			      <0 0x64000000 0 0xf1d>,
@@ -2434,7 +2435,7 @@
 				     "jedec,ufs-2.0";
 			reg = <0 0x01d84000 0 0x3000>;
 			interrupts = <GIC_SPI 265 IRQ_TYPE_LEVEL_HIGH>;
-			phys = <&ufs_mem_phy_lanes>;
+			phys = <&ufs_mem_phy>;
 			phy-names = "ufsphy";
 			lanes-per-direction = <2>;
 			#reset-cells = <1>;
@@ -2463,29 +2464,48 @@
 				<&gcc GCC_UFS_PHY_TX_SYMBOL_0_CLK>,
 				<&gcc GCC_UFS_PHY_RX_SYMBOL_0_CLK>,
 				<&gcc GCC_UFS_PHY_RX_SYMBOL_1_CLK>;
-			freq-table-hz =
-				<37500000 300000000>,
-				<0 0>,
-				<0 0>,
-				<37500000 300000000>,
-				<0 0>,
-				<0 0>,
-				<0 0>,
-				<0 0>;
+
+			operating-points-v2 = <&ufs_opp_table>;
 
 			interconnects = <&aggre1_noc MASTER_UFS_MEM 0 &mc_virt SLAVE_EBI_CH0 0>,
 					<&gem_noc MASTER_AMPSS_M0 0 &config_noc SLAVE_UFS_MEM_CFG 0>;
 			interconnect-names = "ufs-ddr", "cpu-ufs";
 
 			status = "disabled";
+
+			ufs_opp_table: opp-table {
+				compatible = "operating-points-v2";
+
+				opp-37500000 {
+					opp-hz = /bits/ 64 <37500000>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <37500000>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>;
+					required-opps = <&rpmhpd_opp_low_svs>;
+				};
+
+				opp-300000000 {
+					opp-hz = /bits/ 64 <300000000>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <300000000>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>;
+					required-opps = <&rpmhpd_opp_nom>;
+				};
+			};
 		};
 
 		ufs_mem_phy: phy@1d87000 {
 			compatible = "qcom,sm8250-qmp-ufs-phy";
-			reg = <0 0x01d87000 0 0x1c0>;
-			#address-cells = <2>;
-			#size-cells = <2>;
-			ranges;
+			reg = <0 0x01d87000 0 0x1000>;
+
 			clock-names = "ref",
 				      "ref_aux";
 			clocks = <&rpmhcc RPMH_CXO_CLK>,
@@ -2493,16 +2513,10 @@
 
 			resets = <&ufs_mem_hc 0>;
 			reset-names = "ufsphy";
-			status = "disabled";
 
-			ufs_mem_phy_lanes: phy@1d87400 {
-				reg = <0 0x01d87400 0 0x16c>,
-				      <0 0x01d87600 0 0x200>,
-				      <0 0x01d87c00 0 0x200>,
-				      <0 0x01d87800 0 0x16c>,
-				      <0 0x01d87a00 0 0x200>;
-				#phy-cells = <0>;
-			};
+			#phy-cells = <0>;
+
+			status = "disabled";
 		};
 
 		cryptobam: dma-controller@1dc4000 {
@@ -2543,6 +2557,11 @@
 			#hwlock-cells = <1>;
 		};
 
+		tcsr: syscon@1fc0000 {
+			compatible = "qcom,sm8250-tcsr", "syscon";
+			reg = <0x0 0x1fc0000 0x0 0x30000>;
+		};
+
 		wsamacro: codec@3240000 {
 			compatible = "qcom,sm8250-lpass-wsa-macro";
 			reg = <0 0x03240000 0 0x1000>;
@@ -2565,7 +2584,7 @@
 			status = "disabled";
 		};
 
-		swr0: soundwire-controller@3250000 {
+		swr0: soundwire@3250000 {
 			reg = <0 0x03250000 0 0x2000>;
 			compatible = "qcom,soundwire-v1.5.1";
 			interrupts = <GIC_SPI 202 IRQ_TYPE_LEVEL_HIGH>;
@@ -2631,7 +2650,7 @@
 			#sound-dai-cells = <1>;
 		};
 
-		swr1: soundwire-controller@3210000 {
+		swr1: soundwire@3210000 {
 			reg = <0 0x03210000 0 0x2000>;
 			compatible = "qcom,soundwire-v1.5.1";
 			status = "disabled";
@@ -2678,7 +2697,7 @@
 		};
 
 		/* tx macro */
-		swr2: soundwire-controller@3230000 {
+		swr2: soundwire@3230000 {
 			reg = <0 0x03230000 0 0x2000>;
 			compatible = "qcom,soundwire-v1.5.1";
 			interrupts = <GIC_SPI 297 IRQ_TYPE_LEVEL_HIGH>;
@@ -3095,11 +3114,8 @@
 			clock-names = "apb_pclk";
 
 			out-ports {
-				#address-cells = <1>;
-				#size-cells = <0>;
 
-				port@0 {
-					reg = <0>;
+				port {
 					tpda_out_funnel_qatb: endpoint {
 						remote-endpoint = <&funnel_qatb_in_tpda>;
 					};
@@ -3142,11 +3158,7 @@
 			};
 
 			in-ports {
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				port@0 {
-					reg = <0>;
+				port {
 					funnel_qatb_in_tpda: endpoint {
 						remote-endpoint = <&tpda_out_funnel_qatb>;
 					};
@@ -3355,11 +3367,8 @@
 			};
 
 			in-ports {
-				#address-cells = <1>;
-				#size-cells = <0>;
 
-				port@0 {
-					reg = <0>;
+				port {
 					etf_in_funnel_swao_out: endpoint {
 						remote-endpoint = <&funnel_swao_out_etf>;
 					};
@@ -3443,8 +3452,6 @@
 			clock-names = "apb_pclk";
 
 			out-ports {
-				#address-cells = <1>;
-				#size-cells = <0>;
 				port {
 					tpdm_mm_out_tpda9: endpoint {
 						remote-endpoint = <&tpda_9_in_tpdm_mm>;
@@ -3710,11 +3717,7 @@
 			};
 
 			in-ports {
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				port@0 {
-					reg = <0>;
+				port {
 					funnel_apss_merg_in_funnel_apss: endpoint {
 					remote-endpoint = <&funnel_apss_out_funnel_apss_merg>;
 					};
@@ -3889,32 +3892,26 @@
 
 		usb_2_qmpphy: phy@88eb000 {
 			compatible = "qcom,sm8250-qmp-usb3-uni-phy";
-			reg = <0 0x088eb000 0 0x200>;
-			status = "disabled";
-			#address-cells = <2>;
-			#size-cells = <2>;
-			ranges;
+			reg = <0 0x088eb000 0 0x1000>;
 
 			clocks = <&gcc GCC_USB3_SEC_PHY_AUX_CLK>,
-				 <&rpmhcc RPMH_CXO_CLK>,
 				 <&gcc GCC_USB3_SEC_CLKREF_EN>,
-				 <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>;
-			clock-names = "aux", "ref_clk_src", "ref", "com_aux";
+				 <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>,
+				 <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>;
+			clock-names = "aux",
+				      "ref",
+				      "com_aux",
+				      "pipe";
+			clock-output-names = "usb3_uni_phy_pipe_clk_src";
+			#clock-cells = <0>;
+			#phy-cells = <0>;
 
-			resets = <&gcc GCC_USB3PHY_PHY_SEC_BCR>,
-				 <&gcc GCC_USB3_PHY_SEC_BCR>;
-			reset-names = "phy", "common";
+			resets = <&gcc GCC_USB3_PHY_SEC_BCR>,
+				 <&gcc GCC_USB3PHY_PHY_SEC_BCR>;
+			reset-names = "phy",
+				      "phy_phy";
 
-			usb_2_ssphy: phy@88eb200 {
-				reg = <0 0x088eb200 0 0x200>,
-				      <0 0x088eb400 0 0x200>,
-				      <0 0x088eb800 0 0x800>;
-				#clock-cells = <0>;
-				#phy-cells = <0>;
-				clocks = <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>;
-				clock-names = "pipe0";
-				clock-output-names = "usb3_uni_phy_pipe_clk_src";
-			};
+			status = "disabled";
 		};
 
 		sdhc_2: mmc@8804000 {
@@ -4141,6 +4138,7 @@
 					  "dp_hs_phy_irq";
 
 			power-domains = <&gcc USB30_PRIM_GDSC>;
+			wakeup-source;
 
 			resets = <&gcc GCC_USB30_PRIM_BCR>;
 
@@ -4209,6 +4207,7 @@
 					  "dp_hs_phy_irq";
 
 			power-domains = <&gcc USB30_SEC_GDSC>;
+			wakeup-source;
 
 			resets = <&gcc GCC_USB30_SEC_BCR>;
 
@@ -4223,7 +4222,7 @@
 				iommus = <&apps_smmu 0x20 0>;
 				snps,dis_u2_susphy_quirk;
 				snps,dis_enblslpm_quirk;
-				phys = <&usb_2_hsphy>, <&usb_2_ssphy>;
+				phys = <&usb_2_hsphy>, <&usb_2_qmpphy>;
 				phy-names = "usb2-phy", "usb3-phy";
 			};
 		};
@@ -6018,7 +6017,7 @@
 			compatible = "qcom,apss-wdt-sm8250", "qcom,kpss-wdt";
 			reg = <0 0x17c10000 0 0x1000>;
 			clocks = <&sleep_clk>;
-			interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 0 IRQ_TYPE_EDGE_RISING>;
 		};
 
 		timer@17c20000 {
diff --git a/arch/arm64/boot/dts/qcom/sm8350.dtsi b/arch/arm64/boot/dts/qcom/sm8350.dtsi
index b46236235b7f..e78c83a897c2 100644
--- a/arch/arm64/boot/dts/qcom/sm8350.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8350.dtsi
@@ -289,6 +289,7 @@
 	firmware {
 		scm: scm {
 			compatible = "qcom,scm-sm8350", "qcom,scm";
+			qcom,dload-mode = <&tcsr 0x13000>;
 			#reset-cells = <1>;
 		};
 	};
@@ -677,9 +678,9 @@
 				 <0>,
 				 <0>,
 				 <0>,
-				 <&ufs_mem_phy_lanes 0>,
-				 <&ufs_mem_phy_lanes 1>,
-				 <&ufs_mem_phy_lanes 2>,
+				 <&ufs_mem_phy 0>,
+				 <&ufs_mem_phy 1>,
+				 <&ufs_mem_phy 2>,
 				 <&usb_1_qmpphy QMP_USB43DP_USB3_PIPE_CLK>,
 				 <0>;
 		};
@@ -919,9 +920,9 @@
 			};
 		};
 
-		gpi_dma0: dma-controller@9800000 {
+		gpi_dma0: dma-controller@900000 {
 			compatible = "qcom,sm8350-gpi-dma", "qcom,sm6350-gpi-dma";
-			reg = <0 0x09800000 0 0x60000>;
+			reg = <0 0x00900000 0 0x60000>;
 			interrupts = <GIC_SPI 244 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 245 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 246 IRQ_TYPE_LEVEL_HIGH>,
@@ -1498,7 +1499,7 @@
 			qcom,bcm-voters = <&apps_bcm_voter>;
 		};
 
-		pcie0: pci@1c00000 {
+		pcie0: pcie@1c00000 {
 			compatible = "qcom,pcie-sm8350";
 			reg = <0 0x01c00000 0 0x3000>,
 			      <0 0x60000000 0 0xf1d>,
@@ -1591,7 +1592,7 @@
 			status = "disabled";
 		};
 
-		pcie1: pci@1c08000 {
+		pcie1: pcie@1c08000 {
 			compatible = "qcom,pcie-sm8350";
 			reg = <0 0x01c08000 0 0x3000>,
 			      <0 0x40000000 0 0xf1d>,
@@ -1679,7 +1680,7 @@
 				     "jedec,ufs-2.0";
 			reg = <0 0x01d84000 0 0x3000>;
 			interrupts = <GIC_SPI 265 IRQ_TYPE_LEVEL_HIGH>;
-			phys = <&ufs_mem_phy_lanes>;
+			phys = <&ufs_mem_phy>;
 			phy-names = "ufsphy";
 			lanes-per-direction = <2>;
 			#reset-cells = <1>;
@@ -1723,10 +1724,8 @@
 
 		ufs_mem_phy: phy@1d87000 {
 			compatible = "qcom,sm8350-qmp-ufs-phy";
-			reg = <0 0x01d87000 0 0x1c4>;
-			#address-cells = <2>;
-			#size-cells = <2>;
-			ranges;
+			reg = <0 0x01d87000 0 0x1000>;
+
 			clock-names = "ref",
 				      "ref_aux";
 			clocks = <&rpmhcc RPMH_CXO_CLK>,
@@ -1734,17 +1733,11 @@
 
 			resets = <&ufs_mem_hc 0>;
 			reset-names = "ufsphy";
-			status = "disabled";
 
-			ufs_mem_phy_lanes: phy@1d87400 {
-				reg = <0 0x01d87400 0 0x188>,
-				      <0 0x01d87600 0 0x200>,
-				      <0 0x01d87c00 0 0x200>,
-				      <0 0x01d87800 0 0x188>,
-				      <0 0x01d87a00 0 0x200>;
-				#clock-cells = <1>;
-				#phy-cells = <0>;
-			};
+			#clock-cells = <1>;
+			#phy-cells = <0>;
+
+			status = "disabled";
 		};
 
 		cryptobam: dma-controller@1dc4000 {
@@ -1818,6 +1811,11 @@
 			#hwlock-cells = <1>;
 		};
 
+		tcsr: syscon@1fc0000 {
+			compatible = "qcom,sm8350-tcsr", "syscon";
+			reg = <0x0 0x1fc0000 0x0 0x30000>;
+		};
+
 		lpass_tlmm: pinctrl@33c0000 {
 			compatible = "qcom,sm8350-lpass-lpi-pinctrl";
 			reg = <0 0x033c0000 0 0x20000>,
@@ -2021,7 +2019,7 @@
 			compatible = "qcom,sm8350-mpss-pas";
 			reg = <0x0 0x04080000 0x0 0x4040>;
 
-			interrupts-extended = <&intc GIC_SPI 264 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts-extended = <&intc GIC_SPI 264 IRQ_TYPE_EDGE_RISING>,
 					      <&smp2p_modem_in 0 IRQ_TYPE_EDGE_RISING>,
 					      <&smp2p_modem_in 1 IRQ_TYPE_EDGE_RISING>,
 					      <&smp2p_modem_in 2 IRQ_TYPE_EDGE_RISING>,
@@ -2063,7 +2061,7 @@
 			compatible = "qcom,sm8350-slpi-pas";
 			reg = <0 0x05c00000 0 0x4000>;
 
-			interrupts-extended = <&pdc 9 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts-extended = <&pdc 9 IRQ_TYPE_EDGE_RISING>,
 					      <&smp2p_slpi_in 0 IRQ_TYPE_EDGE_RISING>,
 					      <&smp2p_slpi_in 1 IRQ_TYPE_EDGE_RISING>,
 					      <&smp2p_slpi_in 2 IRQ_TYPE_EDGE_RISING>,
@@ -2238,34 +2236,27 @@
 			};
 		};
 
-		usb_2_qmpphy: phy-wrapper@88eb000 {
+		usb_2_qmpphy: phy@88eb000 {
 			compatible = "qcom,sm8350-qmp-usb3-uni-phy";
-			reg = <0 0x088eb000 0 0x200>;
+			reg = <0 0x088eb000 0 0x2000>;
 			status = "disabled";
-			#address-cells = <2>;
-			#size-cells = <2>;
-			ranges;
 
 			clocks = <&gcc GCC_USB3_SEC_PHY_AUX_CLK>,
-				 <&rpmhcc RPMH_CXO_CLK>,
 				 <&gcc GCC_USB3_SEC_CLKREF_EN>,
-				 <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>;
-			clock-names = "aux", "ref_clk_src", "ref", "com_aux";
-
-			resets = <&gcc GCC_USB3PHY_PHY_SEC_BCR>,
-				 <&gcc GCC_USB3_PHY_SEC_BCR>;
-			reset-names = "phy", "common";
+				 <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>,
+				 <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>;
+			clock-names = "aux",
+				      "ref",
+				      "com_aux",
+				      "pipe";
+			clock-output-names = "usb3_uni_phy_pipe_clk_src";
+			#clock-cells = <0>;
+			#phy-cells = <0>;
 
-			usb_2_ssphy: phy@88ebe00 {
-				reg = <0 0x088ebe00 0 0x200>,
-				      <0 0x088ec000 0 0x200>,
-				      <0 0x088eb200 0 0x1100>;
-				#phy-cells = <0>;
-				#clock-cells = <0>;
-				clocks = <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>;
-				clock-names = "pipe0";
-				clock-output-names = "usb3_uni_phy_pipe_clk_src";
-			};
+			resets = <&gcc GCC_USB3_PHY_SEC_BCR>,
+				 <&gcc GCC_USB3PHY_PHY_SEC_BCR>;
+			reset-names = "phy",
+				      "phy_phy";
 		};
 
 		dc_noc: interconnect@90c0000 {
@@ -2418,7 +2409,7 @@
 				iommus = <&apps_smmu 0x20 0x0>;
 				snps,dis_u2_susphy_quirk;
 				snps,dis_enblslpm_quirk;
-				phys = <&usb_2_hsphy>, <&usb_2_ssphy>;
+				phys = <&usb_2_hsphy>, <&usb_2_qmpphy>;
 				phy-names = "usb2-phy", "usb3-phy";
 			};
 		};
@@ -2453,35 +2444,6 @@
 			#size-cells = <2>;
 			ranges;
 
-			dpu_opp_table: opp-table {
-				compatible = "operating-points-v2";
-
-				/* TODO: opp-200000000 should work with
-				 * &rpmhpd_opp_low_svs, but one some of
-				 * sm8350_hdk boards reboot using this
-				 * opp.
-				 */
-				opp-200000000 {
-					opp-hz = /bits/ 64 <200000000>;
-					required-opps = <&rpmhpd_opp_svs>;
-				};
-
-				opp-300000000 {
-					opp-hz = /bits/ 64 <300000000>;
-					required-opps = <&rpmhpd_opp_svs>;
-				};
-
-				opp-345000000 {
-					opp-hz = /bits/ 64 <345000000>;
-					required-opps = <&rpmhpd_opp_svs_l1>;
-				};
-
-				opp-460000000 {
-					opp-hz = /bits/ 64 <460000000>;
-					required-opps = <&rpmhpd_opp_nom>;
-				};
-			};
-
 			mdss_mdp: display-controller@ae01000 {
 				compatible = "qcom,sm8350-dpu";
 				reg = <0 0x0ae01000 0 0x8f000>,
@@ -2510,6 +2472,35 @@
 				interrupt-parent = <&mdss>;
 				interrupts = <0>;
 
+				dpu_opp_table: opp-table {
+					compatible = "operating-points-v2";
+
+					/* TODO: opp-200000000 should work with
+					 * &rpmhpd_opp_low_svs, but one some of
+					 * sm8350_hdk boards reboot using this
+					 * opp.
+					 */
+					opp-200000000 {
+						opp-hz = /bits/ 64 <200000000>;
+						required-opps = <&rpmhpd_opp_svs>;
+					};
+
+					opp-300000000 {
+						opp-hz = /bits/ 64 <300000000>;
+						required-opps = <&rpmhpd_opp_svs>;
+					};
+
+					opp-345000000 {
+						opp-hz = /bits/ 64 <345000000>;
+						required-opps = <&rpmhpd_opp_svs_l1>;
+					};
+
+					opp-460000000 {
+						opp-hz = /bits/ 64 <460000000>;
+						required-opps = <&rpmhpd_opp_nom>;
+					};
+				};
+
 				ports {
 					#address-cells = <1>;
 					#size-cells = <0>;
@@ -3207,7 +3198,7 @@
 			compatible = "qcom,sm8350-adsp-pas";
 			reg = <0 0x17300000 0 0x100>;
 
-			interrupts-extended = <&pdc 6 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>,
 					      <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>,
 					      <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>,
 					      <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>,
@@ -3512,7 +3503,7 @@
 			compatible = "qcom,sm8350-cdsp-pas";
 			reg = <0 0x98900000 0 0x1400000>;
 
-			interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>,
 					      <&smp2p_cdsp_in 0 IRQ_TYPE_EDGE_RISING>,
 					      <&smp2p_cdsp_in 1 IRQ_TYPE_EDGE_RISING>,
 					      <&smp2p_cdsp_in 2 IRQ_TYPE_EDGE_RISING>,
diff --git a/arch/arm64/boot/dts/qcom/sm8450-hdk.dts b/arch/arm64/boot/dts/qcom/sm8450-hdk.dts
index 20153d08edde..a20d5d76af35 100644
--- a/arch/arm64/boot/dts/qcom/sm8450-hdk.dts
+++ b/arch/arm64/boot/dts/qcom/sm8450-hdk.dts
@@ -580,6 +580,14 @@
 	status = "okay";
 };
 
+&gpu {
+	status = "okay";
+
+	zap-shader {
+		firmware-name = "qcom/sm8450/a730_zap.mbn";
+	};
+};
+
 &i2c9 {
 	clock-frequency = <400000>;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/qcom/sm8450.dtsi b/arch/arm64/boot/dts/qcom/sm8450.dtsi
index 1783fa78bdbc..01e4dfc4babd 100644
--- a/arch/arm64/boot/dts/qcom/sm8450.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8450.dtsi
@@ -8,6 +8,7 @@
 #include <dt-bindings/clock/qcom,rpmh.h>
 #include <dt-bindings/clock/qcom,sm8450-camcc.h>
 #include <dt-bindings/clock/qcom,sm8450-dispcc.h>
+#include <dt-bindings/clock/qcom,sm8450-gpucc.h>
 #include <dt-bindings/clock/qcom,sm8450-videocc.h>
 #include <dt-bindings/dma/qcom-gpi.h>
 #include <dt-bindings/firmware/qcom,scm.h>
@@ -18,6 +19,7 @@
 #include <dt-bindings/power/qcom-rpmpd.h>
 #include <dt-bindings/interconnect/qcom,icc.h>
 #include <dt-bindings/interconnect/qcom,sm8450.h>
+#include <dt-bindings/reset/qcom,sm8450-gpucc.h>
 #include <dt-bindings/soc/qcom,gpr.h>
 #include <dt-bindings/soc/qcom,rpmh-rsc.h>
 #include <dt-bindings/sound/qcom,q6dsp-lpass-ports.h>
@@ -754,9 +756,9 @@
 				 <&pcie0_phy>,
 				 <&pcie1_phy>,
 				 <0>,
-				 <&ufs_mem_phy_lanes 0>,
-				 <&ufs_mem_phy_lanes 1>,
-				 <&ufs_mem_phy_lanes 2>,
+				 <&ufs_mem_phy 0>,
+				 <&ufs_mem_phy 1>,
+				 <&ufs_mem_phy 2>,
 				 <&usb_1_qmpphy QMP_USB43DP_USB3_PIPE_CLK>;
 			clock-names = "bi_tcxo",
 				      "sleep_clk",
@@ -1739,7 +1741,12 @@
 			};
 		};
 
-		pcie0: pci@1c00000 {
+		rng: rng@10c3000 {
+			compatible = "qcom,sm8450-trng", "qcom,trng";
+			reg = <0 0x010c3000 0 0x1000>;
+		};
+
+		pcie0: pcie@1c00000 {
 			compatible = "qcom,pcie-sm8450-pcie0";
 			reg = <0 0x01c00000 0 0x3000>,
 			      <0 0x60000000 0 0xf1d>,
@@ -1848,7 +1855,7 @@
 			status = "disabled";
 		};
 
-		pcie1: pci@1c08000 {
+		pcie1: pcie@1c08000 {
 			compatible = "qcom,pcie-sm8450-pcie1";
 			reg = <0 0x01c08000 0 0x3000>,
 			      <0 0x40000000 0 0xf1d>,
@@ -2014,6 +2021,206 @@
 			reg = <0x0 0x1fc0000 0x0 0x30000>;
 		};
 
+		gpu: gpu@3d00000 {
+			compatible = "qcom,adreno-730.1", "qcom,adreno";
+			reg = <0x0 0x03d00000 0x0 0x40000>,
+			      <0x0 0x03d9e000 0x0 0x1000>,
+			      <0x0 0x03d61000 0x0 0x800>;
+			reg-names = "kgsl_3d0_reg_memory",
+				    "cx_mem",
+				    "cx_dbgc";
+
+			interrupts = <GIC_SPI 300 IRQ_TYPE_LEVEL_HIGH>;
+
+			iommus = <&adreno_smmu 0 0x400>,
+				 <&adreno_smmu 1 0x400>;
+
+			operating-points-v2 = <&gpu_opp_table>;
+
+			qcom,gmu = <&gmu>;
+
+			status = "disabled";
+
+			zap-shader {
+				memory-region = <&gpu_micro_code_mem>;
+			};
+
+			gpu_opp_table: opp-table {
+				compatible = "operating-points-v2";
+
+				opp-818000000 {
+					opp-hz = /bits/ 64 <818000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_TURBO>;
+				};
+
+				opp-791000000 {
+					opp-hz = /bits/ 64 <791000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_NOM_L1>;
+				};
+
+				opp-734000000 {
+					opp-hz = /bits/ 64 <734000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_NOM>;
+				};
+
+				opp-640000000 {
+					opp-hz = /bits/ 64 <640000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_SVS_L2>;
+				};
+
+				opp-599000000 {
+					opp-hz = /bits/ 64 <599000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_SVS_L1>;
+				};
+
+				opp-545000000 {
+					opp-hz = /bits/ 64 <545000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_SVS_L0>;
+				};
+
+				opp-492000000 {
+					opp-hz = /bits/ 64 <492000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_SVS>;
+				};
+
+				opp-421000000 {
+					opp-hz = /bits/ 64 <421000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS_L1>;
+				};
+
+				opp-350000000 {
+					opp-hz = /bits/ 64 <350000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS>;
+				};
+
+				opp-317000000 {
+					opp-hz = /bits/ 64 <317000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS>;
+				};
+
+				opp-285000000 {
+					opp-hz = /bits/ 64 <285000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS_D1>;
+				};
+
+				opp-220000000 {
+					opp-hz = /bits/ 64 <220000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS_D1>;
+				};
+			};
+		};
+
+		gmu: gmu@3d6a000 {
+			compatible = "qcom,adreno-gmu-730.1", "qcom,adreno-gmu";
+			reg = <0x0 0x03d6a000 0x0 0x35000>,
+			      <0x0 0x03d50000 0x0 0x10000>,
+			      <0x0 0x0b290000 0x0 0x10000>;
+			reg-names = "gmu", "rscc", "gmu_pdc";
+
+			interrupts = <GIC_SPI 304 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "hfi", "gmu";
+
+			clocks = <&gpucc GPU_CC_AHB_CLK>,
+				 <&gpucc GPU_CC_CX_GMU_CLK>,
+				 <&gpucc GPU_CC_CXO_CLK>,
+				 <&gcc GCC_DDRSS_GPU_AXI_CLK>,
+				 <&gcc GCC_GPU_MEMNOC_GFX_CLK>,
+				 <&gpucc GPU_CC_HUB_CX_INT_CLK>,
+				 <&gpucc GPU_CC_DEMET_CLK>;
+			clock-names = "ahb",
+				      "gmu",
+				      "cxo",
+				      "axi",
+				      "memnoc",
+				      "hub",
+				      "demet";
+
+			power-domains = <&gpucc GPU_CX_GDSC>,
+					<&gpucc GPU_GX_GDSC>;
+			power-domain-names = "cx",
+					     "gx";
+
+			iommus = <&adreno_smmu 5 0x400>;
+
+			qcom,qmp = <&aoss_qmp>;
+
+			operating-points-v2 = <&gmu_opp_table>;
+
+			gmu_opp_table: opp-table {
+				compatible = "operating-points-v2";
+
+				opp-500000000 {
+					opp-hz = /bits/ 64 <500000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_SVS>;
+				};
+
+				opp-200000000 {
+					opp-hz = /bits/ 64 <200000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS>;
+				};
+			};
+		};
+
+		gpucc: clock-controller@3d90000 {
+			compatible = "qcom,sm8450-gpucc";
+			reg = <0x0 0x03d90000 0x0 0xa000>;
+			clocks = <&rpmhcc RPMH_CXO_CLK>,
+				 <&gcc GCC_GPU_GPLL0_CLK_SRC>,
+				 <&gcc GCC_GPU_GPLL0_DIV_CLK_SRC>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+			#power-domain-cells = <1>;
+		};
+
+		adreno_smmu: iommu@3da0000 {
+			compatible = "qcom,sm8450-smmu-500", "qcom,adreno-smmu",
+				     "qcom,smmu-500", "arm,mmu-500";
+			reg = <0x0 0x03da0000 0x0 0x40000>;
+			#iommu-cells = <2>;
+			#global-interrupts = <1>;
+			interrupts = <GIC_SPI 673 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 678 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 679 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 680 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 681 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 682 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 683 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 684 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 685 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 686 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 687 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 422 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 476 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 574 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 575 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 576 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 577 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 659 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 661 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 664 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 665 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 666 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 668 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 669 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 699 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 700 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gpucc GPU_CC_CX_GMU_CLK>,
+				 <&gpucc GPU_CC_HUB_CX_INT_CLK>,
+				 <&gpucc GPU_CC_HLOS1_VOTE_GPU_SMMU_CLK>,
+				 <&gcc GCC_GPU_MEMNOC_GFX_CLK>,
+				 <&gcc GCC_GPU_SNOC_DVM_GFX_CLK>,
+				 <&gpucc GPU_CC_AHB_CLK>;
+			clock-names = "gmu",
+				      "hub",
+				      "hlos",
+				      "bus",
+				      "iface",
+				      "ahb";
+			power-domains = <&gpucc GPU_CX_GDSC>;
+			dma-coherent;
+		};
+
 		usb_1_hsphy: phy@88e3000 {
 			compatible = "qcom,sm8450-usb-hs-phy",
 				     "qcom,usb-snps-hs-7nm-phy";
@@ -2149,18 +2356,13 @@
 				 <&q6prmcc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
 				 <&vamacro>;
 			clock-names = "mclk", "npl", "macro", "dcodec", "fsgen";
-			assigned-clocks = <&q6prmcc LPASS_CLK_ID_WSA2_CORE_TX_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
-					  <&q6prmcc LPASS_CLK_ID_WSA2_CORE_TX_2X_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>;
-			assigned-clock-rates = <19200000>, <19200000>;
 
 			#clock-cells = <0>;
 			clock-output-names = "wsa2-mclk";
-			pinctrl-names = "default";
-			pinctrl-0 = <&wsa2_swr_active>;
 			#sound-dai-cells = <1>;
 		};
 
-		swr4: soundwire-controller@31f0000 {
+		swr4: soundwire@31f0000 {
 			compatible = "qcom,soundwire-v1.7.0";
 			reg = <0 0x031f0000 0 0x2000>;
 			interrupts = <GIC_SPI 171 IRQ_TYPE_LEVEL_HIGH>;
@@ -2168,6 +2370,9 @@
 			clock-names = "iface";
 			label = "WSA2";
 
+			pinctrl-0 = <&wsa2_swr_active>;
+			pinctrl-names = "default";
+
 			qcom,din-ports = <2>;
 			qcom,dout-ports = <6>;
 
@@ -2197,18 +2402,12 @@
 				 <&vamacro>;
 			clock-names = "mclk", "npl", "macro", "dcodec", "fsgen";
 
-			assigned-clocks = <&q6prmcc LPASS_CLK_ID_RX_CORE_TX_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
-					  <&q6prmcc LPASS_CLK_ID_RX_CORE_MCLK2_2X_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>;
-			assigned-clock-rates = <19200000>, <19200000>;
-
 			#clock-cells = <0>;
 			clock-output-names = "mclk";
-			pinctrl-names = "default";
-			pinctrl-0 = <&rx_swr_active>;
 			#sound-dai-cells = <1>;
 		};
 
-		swr1: soundwire-controller@3210000 {
+		swr1: soundwire@3210000 {
 			compatible = "qcom,soundwire-v1.7.0";
 			reg = <0 0x03210000 0 0x2000>;
 			interrupts = <GIC_SPI 155 IRQ_TYPE_LEVEL_HIGH>;
@@ -2218,6 +2417,9 @@
 			qcom,din-ports = <0>;
 			qcom,dout-ports = <5>;
 
+			pinctrl-0 = <&rx_swr_active>;
+			pinctrl-names = "default";
+
 			qcom,ports-sinterval-low =	/bits/ 8 <0x03 0x1f 0x1f 0x07 0x00>;
 			qcom,ports-offset1 =		/bits/ 8 <0x00 0x00 0x0b 0x01 0x00>;
 			qcom,ports-offset2 =		/bits/ 8 <0x00 0x00 0x0b 0x00 0x00>;
@@ -2243,14 +2445,9 @@
 				 <&q6prmcc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
 				 <&vamacro>;
 			clock-names = "mclk", "npl", "macro", "dcodec", "fsgen";
-			assigned-clocks = <&q6prmcc LPASS_CLK_ID_RX_CORE_TX_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
-					  <&q6prmcc LPASS_CLK_ID_RX_CORE_MCLK2_2X_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>;
-			assigned-clock-rates = <19200000>, <19200000>;
 
 			#clock-cells = <0>;
 			clock-output-names = "mclk";
-			pinctrl-names = "default";
-			pinctrl-0 = <&tx_swr_active>;
 			#sound-dai-cells = <1>;
 		};
 
@@ -2264,18 +2461,12 @@
 				 <&vamacro>;
 			clock-names = "mclk", "npl", "macro", "dcodec", "fsgen";
 
-			assigned-clocks = <&q6prmcc LPASS_CLK_ID_WSA_CORE_TX_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
-					  <&q6prmcc LPASS_CLK_ID_WSA_CORE_TX_2X_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>;
-			assigned-clock-rates = <19200000>, <19200000>;
-
 			#clock-cells = <0>;
 			clock-output-names = "mclk";
-			pinctrl-names = "default";
-			pinctrl-0 = <&wsa_swr_active>;
 			#sound-dai-cells = <1>;
 		};
 
-		swr0: soundwire-controller@3250000 {
+		swr0: soundwire@3250000 {
 			compatible = "qcom,soundwire-v1.7.0";
 			reg = <0 0x03250000 0 0x2000>;
 			interrupts = <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>;
@@ -2283,6 +2474,9 @@
 			clock-names = "iface";
 			label = "WSA";
 
+			pinctrl-0 = <&wsa_swr_active>;
+			pinctrl-names = "default";
+
 			qcom,din-ports = <2>;
 			qcom,dout-ports = <6>;
 
@@ -2302,17 +2496,20 @@
 			status = "disabled";
 		};
 
-		swr2: soundwire-controller@33b0000 {
+		swr2: soundwire@33b0000 {
 			compatible = "qcom,soundwire-v1.7.0";
 			reg = <0 0x033b0000 0 0x2000>;
 			interrupts = <GIC_SPI 496 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 520 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "core", "wakeup";
 
-			clocks = <&vamacro>;
+			clocks = <&txmacro>;
 			clock-names = "iface";
 			label = "TX";
 
+			pinctrl-0 = <&tx_swr_active>;
+			pinctrl-names = "default";
+
 			qcom,din-ports = <4>;
 			qcom,dout-ports = <0>;
 			qcom,ports-sinterval-low =	/bits/ 8 <0x01 0x01 0x03 0x03>;
@@ -2339,8 +2536,6 @@
 				 <&q6prmcc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
 				 <&q6prmcc LPASS_CLK_ID_RX_CORE_MCLK2_2X_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>;
 			clock-names = "mclk", "macro", "dcodec", "npl";
-			assigned-clocks = <&q6prmcc LPASS_CLK_ID_TX_CORE_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>;
-			assigned-clock-rates = <19200000>;
 
 			#clock-cells = <0>;
 			clock-output-names = "fsgen";
@@ -4122,7 +4317,7 @@
 				     "jedec,ufs-2.0";
 			reg = <0 0x01d84000 0 0x3000>;
 			interrupts = <GIC_SPI 265 IRQ_TYPE_LEVEL_HIGH>;
-			phys = <&ufs_mem_phy_lanes>;
+			phys = <&ufs_mem_phy>;
 			phy-names = "ufsphy";
 			lanes-per-direction = <2>;
 			#reset-cells = <1>;
@@ -4171,10 +4366,8 @@
 
 		ufs_mem_phy: phy@1d87000 {
 			compatible = "qcom,sm8450-qmp-ufs-phy";
-			reg = <0 0x01d87000 0 0x1c4>;
-			#address-cells = <2>;
-			#size-cells = <2>;
-			ranges;
+			reg = <0 0x01d87000 0 0x1000>;
+
 			clock-names = "ref", "ref_aux", "qref";
 			clocks = <&rpmhcc RPMH_CXO_CLK>,
 				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>,
@@ -4182,17 +4375,11 @@
 
 			resets = <&ufs_mem_hc 0>;
 			reset-names = "ufsphy";
-			status = "disabled";
 
-			ufs_mem_phy_lanes: phy@1d87400 {
-				reg = <0 0x01d87400 0 0x188>,
-				      <0 0x01d87600 0 0x200>,
-				      <0 0x01d87c00 0 0x200>,
-				      <0 0x01d87800 0 0x188>,
-				      <0 0x01d87a00 0 0x200>;
-				#clock-cells = <1>;
-				#phy-cells = <0>;
-			};
+			#clock-cells = <1>;
+			#phy-cells = <0>;
+
+			status = "disabled";
 		};
 
 		ice: crypto@1d88000 {
diff --git a/arch/arm64/boot/dts/qcom/sm8550-mtp.dts b/arch/arm64/boot/dts/qcom/sm8550-mtp.dts
index 9a70875028b7..c1135ad5fa69 100644
--- a/arch/arm64/boot/dts/qcom/sm8550-mtp.dts
+++ b/arch/arm64/boot/dts/qcom/sm8550-mtp.dts
@@ -10,6 +10,7 @@
 #include "pm8010.dtsi"
 #include "pm8550.dtsi"
 #include "pm8550b.dtsi"
+#define PMK8550VE_SID 5
 #include "pm8550ve.dtsi"
 #include "pm8550vs.dtsi"
 #include "pmk8550.dtsi"
@@ -510,6 +511,134 @@
 			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
 		};
 	};
+
+	regulators-6 {
+		compatible = "qcom,pm8010-rpmh-regulators";
+		qcom,pmic-id = "m";
+
+		vdd-l1-l2-supply = <&vreg_s4g_1p3>;
+		vdd-l3-l4-supply = <&vreg_bob2>;
+		vdd-l5-supply = <&vreg_s6g_1p8>;
+		vdd-l6-supply = <&vreg_s6g_1p8>;
+		vdd-l7-supply = <&vreg_bob1>;
+
+		vreg_l1m_1p056: ldo1 {
+			regulator-name = "vreg_l1m_1p056";
+			regulator-min-microvolt = <1056000>;
+			regulator-max-microvolt = <1056000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2m_1p056: ldo2 {
+			regulator-name = "vreg_l2m_1p056";
+			regulator-min-microvolt = <1056000>;
+			regulator-max-microvolt = <1056000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3m_2p8: ldo3 {
+			regulator-name = "vreg_l3m_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l4m_2p8: ldo4 {
+			regulator-name = "vreg_l4m_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l5m_1p8: ldo5 {
+			regulator-name = "vreg_l5m_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6m_1p8: ldo6 {
+			regulator-name = "vreg_l6m_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l7m_2p9: ldo7 {
+			regulator-name = "vreg_l7m_2p9";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2904000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-7 {
+		compatible = "qcom,pm8010-rpmh-regulators";
+		qcom,pmic-id = "n";
+
+		vdd-l1-l2-supply = <&vreg_s4g_1p3>;
+		vdd-l3-l4-supply = <&vreg_bob2>;
+		vdd-l5-supply = <&vreg_s6g_1p8>;
+		vdd-l6-supply = <&vreg_bob1>;
+		vdd-l7-supply = <&vreg_bob1>;
+
+		vreg_l1n_1p1: ldo1 {
+			regulator-name = "vreg_l1n_1p1";
+			regulator-min-microvolt = <1104000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2n_1p1: ldo2 {
+			regulator-name = "vreg_l2n_1p1";
+			regulator-min-microvolt = <1104000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3n_2p8: ldo3 {
+			regulator-name = "vreg_l3n_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <3000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l4n_2p8: ldo4 {
+			regulator-name = "vreg_l4n_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l5n_1p8: ldo5 {
+			regulator-name = "vreg_l5n_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6n_3p3: ldo6 {
+			regulator-name = "vreg_l6n_3p3";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <3304000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l7n_2p96: ldo7 {
+			regulator-name = "vreg_l7n_2p96";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2960000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+};
+
+&gpu {
+	status = "okay";
+
+	zap-shader {
+		firmware-name = "qcom/sm8550/a740_zap.mbn";
+	};
 };
 
 &i2c_master_hub_0 {
diff --git a/arch/arm64/boot/dts/qcom/sm8550-qrd.dts b/arch/arm64/boot/dts/qcom/sm8550-qrd.dts
index eef811def39b..d401d63e5c4d 100644
--- a/arch/arm64/boot/dts/qcom/sm8550-qrd.dts
+++ b/arch/arm64/boot/dts/qcom/sm8550-qrd.dts
@@ -11,6 +11,7 @@
 #include "pm8010.dtsi"
 #include "pm8550.dtsi"
 #include "pm8550b.dtsi"
+#define PMK8550VE_SID 5
 #include "pm8550ve.dtsi"
 #include "pm8550vs.dtsi"
 #include "pmk8550.dtsi"
@@ -527,6 +528,126 @@
 			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
 		};
 	};
+
+	regulators-6 {
+		compatible = "qcom,pm8010-rpmh-regulators";
+		qcom,pmic-id = "m";
+
+		vdd-l1-l2-supply = <&vreg_s4g_1p25>;
+		vdd-l3-l4-supply = <&vreg_bob2>;
+		vdd-l5-supply = <&vreg_s6g_1p86>;
+		vdd-l6-supply = <&vreg_s6g_1p86>;
+		vdd-l7-supply = <&vreg_bob1>;
+
+		vreg_l1m_1p056: ldo1 {
+			regulator-name = "vreg_l1m_1p056";
+			regulator-min-microvolt = <1056000>;
+			regulator-max-microvolt = <1056000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2m_1p056: ldo2 {
+			regulator-name = "vreg_l2m_1p056";
+			regulator-min-microvolt = <1056000>;
+			regulator-max-microvolt = <1056000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3m_2p8: ldo3 {
+			regulator-name = "vreg_l3m_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l4m_2p8: ldo4 {
+			regulator-name = "vreg_l4m_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l5m_1p8: ldo5 {
+			regulator-name = "vreg_l5m_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6m_1p8: ldo6 {
+			regulator-name = "vreg_l6m_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l7m_2p9: ldo7 {
+			regulator-name = "vreg_l7m_2p9";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2904000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-7 {
+		compatible = "qcom,pm8010-rpmh-regulators";
+		qcom,pmic-id = "n";
+
+		vdd-l1-l2-supply = <&vreg_s4g_1p25>;
+		vdd-l3-l4-supply = <&vreg_bob2>;
+		vdd-l5-supply = <&vreg_s6g_1p86>;
+		vdd-l6-supply = <&vreg_bob1>;
+		vdd-l7-supply = <&vreg_bob1>;
+
+		vreg_l1n_1p1: ldo1 {
+			regulator-name = "vreg_l1n_1p1";
+			regulator-min-microvolt = <1104000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2n_1p1: ldo2 {
+			regulator-name = "vreg_l2n_1p1";
+			regulator-min-microvolt = <1104000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3n_2p8: ldo3 {
+			regulator-name = "vreg_l3n_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <3000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l4n_2p8: ldo4 {
+			regulator-name = "vreg_l4n_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l5n_1p8: ldo5 {
+			regulator-name = "vreg_l5n_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6n_3p3: ldo6 {
+			regulator-name = "vreg_l6n_3p3";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <3304000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l7n_2p96: ldo7 {
+			regulator-name = "vreg_l7n_2p96";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2960000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
 };
 
 &i2c_master_hub_0 {
@@ -585,6 +706,13 @@
 	};
 };
 
+&ipa {
+	qcom,gsi-loader = "self";
+	memory-region = <&ipa_fw_mem>;
+	firmware-name = "qcom/sm8550/ipa_fws.mbn";
+	status = "okay";
+};
+
 &gcc {
 	clocks = <&bi_tcxo_div2>, <&sleep_clk>,
 		 <&pcie0_phy>,
@@ -596,6 +724,14 @@
 		 <&usb_dp_qmpphy QMP_USB43DP_USB3_PIPE_CLK>;
 };
 
+&gpu {
+	status = "okay";
+
+	zap-shader {
+		firmware-name = "qcom/sm8550/a740_zap.mbn";
+	};
+};
+
 &lpass_tlmm {
 	spkr_1_sd_n_active: spkr-1-sd-n-active-state {
 		pins = "gpio17";
diff --git a/arch/arm64/boot/dts/qcom/sm8550.dtsi b/arch/arm64/boot/dts/qcom/sm8550.dtsi
index 7b9ddde0b2c9..ee1ba5a8c8fc 100644
--- a/arch/arm64/boot/dts/qcom/sm8550.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8550.dtsi
@@ -285,9 +285,9 @@
 				compatible = "arm,idle-state";
 				idle-state-name = "silver-rail-power-collapse";
 				arm,psci-suspend-param = <0x40000004>;
-				entry-latency-us = <800>;
+				entry-latency-us = <550>;
 				exit-latency-us = <750>;
-				min-residency-us = <4090>;
+				min-residency-us = <6700>;
 				local-timer-stop;
 			};
 
@@ -296,8 +296,18 @@
 				idle-state-name = "gold-rail-power-collapse";
 				arm,psci-suspend-param = <0x40000004>;
 				entry-latency-us = <600>;
-				exit-latency-us = <1550>;
-				min-residency-us = <4791>;
+				exit-latency-us = <1300>;
+				min-residency-us = <8136>;
+				local-timer-stop;
+			};
+
+			PRIME_CPU_SLEEP_0: cpu-sleep-2-0 {
+				compatible = "arm,idle-state";
+				idle-state-name = "goldplus-rail-power-collapse";
+				arm,psci-suspend-param = <0x40000004>;
+				entry-latency-us = <500>;
+				exit-latency-us = <1350>;
+				min-residency-us = <7480>;
 				local-timer-stop;
 			};
 		};
@@ -306,17 +316,17 @@
 			CLUSTER_SLEEP_0: cluster-sleep-0 {
 				compatible = "domain-idle-state";
 				arm,psci-suspend-param = <0x41000044>;
-				entry-latency-us = <1050>;
-				exit-latency-us = <2500>;
-				min-residency-us = <5309>;
+				entry-latency-us = <750>;
+				exit-latency-us = <2350>;
+				min-residency-us = <9144>;
 			};
 
 			CLUSTER_SLEEP_1: cluster-sleep-1 {
 				compatible = "domain-idle-state";
 				arm,psci-suspend-param = <0x4100c344>;
-				entry-latency-us = <2700>;
-				exit-latency-us = <3500>;
-				min-residency-us = <13959>;
+				entry-latency-us = <2800>;
+				exit-latency-us = <4400>;
+				min-residency-us = <10150>;
 			};
 		};
 	};
@@ -324,6 +334,7 @@
 	firmware {
 		scm: scm {
 			compatible = "qcom,scm-sm8550", "qcom,scm";
+			qcom,dload-mode = <&tcsr 0x19000>;
 			interconnects = <&aggre2_noc MASTER_CRYPTO 0 &mc_virt SLAVE_EBI1 0>;
 		};
 	};
@@ -400,7 +411,7 @@
 		CPU_PD7: power-domain-cpu7 {
 			#power-domain-cells = <0>;
 			power-domains = <&CLUSTER_PD>;
-			domain-idle-states = <&BIG_CPU_SLEEP_0>;
+			domain-idle-states = <&PRIME_CPU_SLEEP_0>;
 		};
 
 		CLUSTER_PD: power-domain-cluster {
@@ -1677,7 +1688,12 @@
 			qcom,bcm-voters = <&apps_bcm_voter>;
 		};
 
-		pcie0: pci@1c00000 {
+		rng: rng@10c3000 {
+			compatible = "qcom,sm8550-trng", "qcom,trng";
+			reg = <0 0x010c3000 0 0x1000>;
+		};
+
+		pcie0: pcie@1c00000 {
 			device_type = "pci";
 			compatible = "qcom,pcie-sm8550";
 			reg = <0 0x01c00000 0 0x3000>,
@@ -1768,7 +1784,7 @@
 			status = "disabled";
 		};
 
-		pcie1: pci@1c08000 {
+		pcie1: pcie@1c08000 {
 			device_type = "pci";
 			compatible = "qcom,pcie-sm8550";
 			reg = <0x0 0x01c08000 0x0 0x3000>,
@@ -1979,6 +1995,128 @@
 			#reset-cells = <1>;
 		};
 
+		gpu: gpu@3d00000 {
+			compatible = "qcom,adreno-43050a01", "qcom,adreno";
+			reg = <0x0 0x03d00000 0x0 0x40000>,
+			      <0x0 0x03d9e000 0x0 0x1000>,
+			      <0x0 0x03d61000 0x0 0x800>;
+			reg-names = "kgsl_3d0_reg_memory",
+				    "cx_mem",
+				    "cx_dbgc";
+
+			interrupts = <GIC_SPI 300 IRQ_TYPE_LEVEL_HIGH>;
+
+			iommus = <&adreno_smmu 0 0x0>,
+				 <&adreno_smmu 1 0x0>;
+
+			operating-points-v2 = <&gpu_opp_table>;
+
+			qcom,gmu = <&gmu>;
+
+			status = "disabled";
+
+			zap-shader {
+				memory-region = <&gpu_micro_code_mem>;
+			};
+
+			/* Speedbin needs more work on A740+, keep only lower freqs */
+			gpu_opp_table: opp-table {
+				compatible = "operating-points-v2";
+
+				opp-680000000 {
+					opp-hz = /bits/ 64 <680000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_SVS_L1>;
+				};
+
+				opp-615000000 {
+					opp-hz = /bits/ 64 <615000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_SVS_L0>;
+				};
+
+				opp-550000000 {
+					opp-hz = /bits/ 64 <550000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_SVS>;
+				};
+
+				opp-475000000 {
+					opp-hz = /bits/ 64 <475000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS_L1>;
+				};
+
+				opp-401000000 {
+					opp-hz = /bits/ 64 <401000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS>;
+				};
+
+				opp-348000000 {
+					opp-hz = /bits/ 64 <348000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS_D0>;
+				};
+
+				opp-295000000 {
+					opp-hz = /bits/ 64 <295000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS_D1>;
+				};
+
+				opp-220000000 {
+					opp-hz = /bits/ 64 <220000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS_D2>;
+				};
+			};
+		};
+
+		gmu: gmu@3d6a000 {
+			compatible = "qcom,adreno-gmu-740.1", "qcom,adreno-gmu";
+			reg = <0x0 0x03d6a000 0x0 0x35000>,
+			      <0x0 0x03d50000 0x0 0x10000>,
+			      <0x0 0x0b280000 0x0 0x10000>;
+			reg-names = "gmu", "rscc", "gmu_pdc";
+
+			interrupts = <GIC_SPI 304 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "hfi", "gmu";
+
+			clocks = <&gpucc GPU_CC_AHB_CLK>,
+				 <&gpucc GPU_CC_CX_GMU_CLK>,
+				 <&gpucc GPU_CC_CXO_CLK>,
+				 <&gcc GCC_DDRSS_GPU_AXI_CLK>,
+				 <&gcc GCC_GPU_MEMNOC_GFX_CLK>,
+				 <&gpucc GPU_CC_HUB_CX_INT_CLK>,
+				 <&gpucc GPU_CC_DEMET_CLK>;
+			clock-names = "ahb",
+				      "gmu",
+				      "cxo",
+				      "axi",
+				      "memnoc",
+				      "hub",
+				      "demet";
+
+			power-domains = <&gpucc GPU_CC_CX_GDSC>,
+					<&gpucc GPU_CC_GX_GDSC>;
+			power-domain-names = "cx",
+					     "gx";
+
+			iommus = <&adreno_smmu 5 0x0>;
+
+			qcom,qmp = <&aoss_qmp>;
+
+			operating-points-v2 = <&gmu_opp_table>;
+
+			gmu_opp_table: opp-table {
+				compatible = "operating-points-v2";
+
+				opp-500000000 {
+					opp-hz = /bits/ 64 <500000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_SVS>;
+				};
+
+				opp-200000000 {
+					opp-hz = /bits/ 64 <200000000>;
+					opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS>;
+				};
+			};
+		};
+
 		gpucc: clock-controller@3d90000 {
 			compatible = "qcom,sm8550-gpucc";
 			reg = <0 0x03d90000 0 0xa000>;
@@ -1990,6 +2128,89 @@
 			#power-domain-cells = <1>;
 		};
 
+		adreno_smmu: iommu@3da0000 {
+			compatible = "qcom,sm8550-smmu-500", "qcom,adreno-smmu",
+				     "qcom,smmu-500", "arm,mmu-500";
+			reg = <0x0 0x03da0000 0x0 0x40000>;
+			#iommu-cells = <2>;
+			#global-interrupts = <1>;
+			interrupts = <GIC_SPI 673 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 677 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 678 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 679 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 680 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 681 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 682 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 683 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 684 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 685 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 686 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 687 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 422 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 476 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 574 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 575 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 576 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 577 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 659 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 661 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 664 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 665 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 666 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 668 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 669 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 699 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gpucc GPU_CC_HLOS1_VOTE_GPU_SMMU_CLK>,
+				 <&gcc GCC_GPU_MEMNOC_GFX_CLK>,
+				 <&gcc GCC_GPU_SNOC_DVM_GFX_CLK>,
+				 <&gpucc GPU_CC_AHB_CLK>;
+			clock-names = "hlos",
+				      "bus",
+				      "iface",
+				      "ahb";
+			power-domains = <&gpucc GPU_CC_CX_GDSC>;
+			dma-coherent;
+		};
+
+		ipa: ipa@3f40000 {
+			compatible = "qcom,sm8550-ipa";
+
+			iommus = <&apps_smmu 0x4a0 0x0>,
+				 <&apps_smmu 0x4a2 0x0>;
+			reg = <0 0x3f40000 0 0x10000>,
+			      <0 0x3f50000 0 0x5000>,
+			      <0 0x3e04000 0 0xfc000>;
+			reg-names = "ipa-reg",
+				    "ipa-shared",
+				    "gsi";
+
+			interrupts-extended = <&intc GIC_SPI 654 IRQ_TYPE_EDGE_RISING>,
+					      <&intc GIC_SPI 432 IRQ_TYPE_LEVEL_HIGH>,
+					      <&ipa_smp2p_in 0 IRQ_TYPE_EDGE_RISING>,
+					      <&ipa_smp2p_in 1 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "ipa",
+					  "gsi",
+					  "ipa-clock-query",
+					  "ipa-setup-ready";
+
+			clocks = <&rpmhcc RPMH_IPA_CLK>;
+			clock-names = "core";
+
+			interconnects = <&aggre2_noc MASTER_IPA 0 &mc_virt SLAVE_EBI1 0>,
+					<&gem_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_IPA_CFG 0>;
+			interconnect-names = "memory",
+					     "config";
+
+			qcom,qmp = <&aoss_qmp>;
+
+			qcom,smem-states = <&ipa_smp2p_out 0>,
+					   <&ipa_smp2p_out 1>;
+			qcom,smem-state-names = "ipa-clock-enabled-valid",
+						"ipa-clock-enabled";
+
+			status = "disabled";
+		};
+
 		remoteproc_mpss: remoteproc@4080000 {
 			compatible = "qcom,sm8550-mpss-pas";
 			reg = <0x0 0x04080000 0x0 0x4040>;
@@ -2040,17 +2261,13 @@
 				 <&q6prmcc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
 				 <&lpass_vamacro>;
 			clock-names = "mclk", "macro", "dcodec", "fsgen";
-			assigned-clocks = <&q6prmcc LPASS_CLK_ID_WSA2_CORE_TX_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>;
-			assigned-clock-rates = <19200000>;
 
 			#clock-cells = <0>;
 			clock-output-names = "wsa2-mclk";
-			pinctrl-names = "default";
-			pinctrl-0 = <&wsa2_swr_active>;
 			#sound-dai-cells = <1>;
 		};
 
-		swr3: soundwire-controller@6ab0000 {
+		swr3: soundwire@6ab0000 {
 			compatible = "qcom,soundwire-v2.0.0";
 			reg = <0 0x06ab0000 0 0x10000>;
 			interrupts = <GIC_SPI 171 IRQ_TYPE_LEVEL_HIGH>;
@@ -2058,6 +2275,9 @@
 			clock-names = "iface";
 			label = "WSA2";
 
+			pinctrl-0 = <&wsa2_swr_active>;
+			pinctrl-names = "default";
+
 			qcom,din-ports = <4>;
 			qcom,dout-ports = <9>;
 
@@ -2086,17 +2306,12 @@
 				 <&lpass_vamacro>;
 			clock-names = "mclk", "macro", "dcodec", "fsgen";
 
-			assigned-clocks = <&q6prmcc LPASS_CLK_ID_RX_CORE_TX_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>;
-			assigned-clock-rates = <19200000>;
-
 			#clock-cells = <0>;
 			clock-output-names = "mclk";
-			pinctrl-names = "default";
-			pinctrl-0 = <&rx_swr_active>;
 			#sound-dai-cells = <1>;
 		};
 
-		swr1: soundwire-controller@6ad0000 {
+		swr1: soundwire@6ad0000 {
 			compatible = "qcom,soundwire-v2.0.0";
 			reg = <0 0x06ad0000 0 0x10000>;
 			interrupts = <GIC_SPI 155 IRQ_TYPE_LEVEL_HIGH>;
@@ -2104,18 +2319,21 @@
 			clock-names = "iface";
 			label = "RX";
 
-			qcom,din-ports = <0>;
-			qcom,dout-ports = <10>;
+			pinctrl-0 = <&rx_swr_active>;
+			pinctrl-names = "default";
+
+			qcom,din-ports = <1>;
+			qcom,dout-ports = <11>;
 
-			qcom,ports-sinterval =		/bits/ 16 <0x03 0x3f 0x1f 0x07 0x00 0x18f 0xff 0xff 0xff 0xff>;
-			qcom,ports-offset1 =		/bits/ 8 <0x00 0x00 0x0b 0x01 0x00 0x00 0xff 0xff 0xff 0xff>;
-			qcom,ports-offset2 =		/bits/ 8 <0x00 0x00 0x0b 0x00 0x00 0x00 0xff 0xff 0xff 0xff>;
-			qcom,ports-hstart =		/bits/ 8 <0xff 0x03 0xff 0xff 0xff 0x08 0xff 0xff 0xff 0xff>;
-			qcom,ports-hstop =		/bits/ 8 <0xff 0x06 0xff 0xff 0xff 0x08 0xff 0xff 0xff 0xff>;
-			qcom,ports-word-length =	/bits/ 8 <0x01 0x07 0x04 0xff 0xff 0x0f 0xff 0xff 0xff 0xff>;
-			qcom,ports-block-pack-mode =	/bits/ 8 <0xff 0x00 0x01 0xff 0xff 0x00 0xff 0xff 0xff 0xff>;
-			qcom,ports-block-group-count =	/bits/ 8 <0xff 0xff 0xff 0xff 0x00 0x00 0xff 0xff 0xff 0xff>;
-			qcom,ports-lane-control =	/bits/ 8 <0x01 0x00 0x00 0x00 0x00 0x00 0xff 0xff 0xff 0xff>;
+			qcom,ports-sinterval =		/bits/ 16 <0x03 0x3f 0x1f 0x07 0x00 0x18f 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-offset1 =		/bits/ 8 <0x00 0x00 0x0b 0x01 0x00 0x00 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-offset2 =		/bits/ 8 <0x00 0x00 0x0b 0x00 0x00 0x00 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-hstart =		/bits/ 8 <0xff 0x03 0xff 0xff 0xff 0x08 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-hstop =		/bits/ 8 <0xff 0x06 0xff 0xff 0xff 0x08 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-word-length =	/bits/ 8 <0x01 0x07 0x04 0xff 0xff 0x0f 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-block-pack-mode =	/bits/ 8 <0xff 0x00 0x01 0xff 0xff 0x00 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-block-group-count =	/bits/ 8 <0xff 0xff 0xff 0xff 0x00 0x00 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-lane-control =	/bits/ 8 <0x01 0x00 0x00 0x00 0x00 0x00 0xff 0xff 0xff 0xff 0xff 0xff>;
 
 			#address-cells = <2>;
 			#size-cells = <0>;
@@ -2131,14 +2349,9 @@
 				 <&q6prmcc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
 				 <&lpass_vamacro>;
 			clock-names = "mclk", "macro", "dcodec", "fsgen";
-			assigned-clocks = <&q6prmcc LPASS_CLK_ID_TX_CORE_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>;
-
-			assigned-clock-rates = <19200000>;
 
 			#clock-cells = <0>;
 			clock-output-names = "mclk";
-			pinctrl-names = "default";
-			pinctrl-0 = <&tx_swr_active>;
 			#sound-dai-cells = <1>;
 		};
 
@@ -2151,17 +2364,12 @@
 				 <&lpass_vamacro>;
 			clock-names = "mclk", "macro", "dcodec", "fsgen";
 
-			assigned-clocks = <&q6prmcc LPASS_CLK_ID_WSA_CORE_TX_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>;
-			assigned-clock-rates = <19200000>;
-
 			#clock-cells = <0>;
 			clock-output-names = "mclk";
-			pinctrl-names = "default";
-			pinctrl-0 = <&wsa_swr_active>;
 			#sound-dai-cells = <1>;
 		};
 
-		swr0: soundwire-controller@6b10000 {
+		swr0: soundwire@6b10000 {
 			compatible = "qcom,soundwire-v2.0.0";
 			reg = <0 0x06b10000 0 0x10000>;
 			interrupts = <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>;
@@ -2169,6 +2377,9 @@
 			clock-names = "iface";
 			label = "WSA";
 
+			pinctrl-0 = <&wsa_swr_active>;
+			pinctrl-names = "default";
+
 			qcom,din-ports = <4>;
 			qcom,dout-ports = <9>;
 
@@ -2188,16 +2399,19 @@
 			status = "disabled";
 		};
 
-		swr2: soundwire-controller@6d30000 {
+		swr2: soundwire@6d30000 {
 			compatible = "qcom,soundwire-v2.0.0";
 			reg = <0 0x06d30000 0 0x10000>;
 			interrupts = <GIC_SPI 496 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 520 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "core", "wakeup";
-			clocks = <&lpass_vamacro>;
+			clocks = <&lpass_txmacro>;
 			clock-names = "iface";
 			label = "TX";
 
+			pinctrl-0 = <&tx_swr_active>;
+			pinctrl-names = "default";
+
 			qcom,din-ports = <4>;
 			qcom,dout-ports = <0>;
 			qcom,ports-sinterval-low =	/bits/ 8 <0x01 0x01 0x03 0x03>;
@@ -2224,9 +2438,6 @@
 				 <&q6prmcc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>;
 			clock-names = "mclk", "macro", "dcodec";
 
-			assigned-clocks = <&q6prmcc LPASS_CLK_ID_TX_CORE_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>;
-			assigned-clock-rates = <19200000>;
-
 			#clock-cells = <0>;
 			clock-output-names = "fsgen";
 			#sound-dai-cells = <1>;
@@ -2923,8 +3134,8 @@
 
 			interrupts-extended = <&intc GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
 					      <&pdc 17 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc 15 IRQ_TYPE_EDGE_RISING>,
-					      <&pdc 14 IRQ_TYPE_EDGE_RISING>;
+					      <&pdc 15 IRQ_TYPE_EDGE_BOTH>,
+					      <&pdc 14 IRQ_TYPE_EDGE_BOTH>;
 			interrupt-names = "hs_phy_irq",
 					  "ss_phy_irq",
 					  "dm_hs_phy_irq",
diff --git a/arch/arm64/boot/dts/qcom/sm8650-mtp.dts b/arch/arm64/boot/dts/qcom/sm8650-mtp.dts
new file mode 100644
index 000000000000..9d916edb1c73
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/sm8650-mtp.dts
@@ -0,0 +1,727 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/regulator/qcom,rpmh-regulator.h>
+#include "sm8650.dtsi"
+#include "pm8010.dtsi"
+#include "pm8550.dtsi"
+#include "pm8550b.dtsi"
+#define PMK8550VE_SID 8
+#include "pm8550ve.dtsi"
+#include "pm8550vs.dtsi"
+#include "pmk8550.dtsi"
+#include "pmr735d_a.dtsi"
+
+/ {
+	model = "Qualcomm Technologies, Inc. SM8650 MTP";
+	compatible = "qcom,sm8650-mtp", "qcom,sm8650";
+
+	aliases {
+		serial0 = &uart15;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	pmic-glink {
+		compatible = "qcom,sm8650-pmic-glink",
+			     "qcom,sm8550-pmic-glink",
+			     "qcom,pmic-glink";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		orientation-gpios = <&tlmm 29 GPIO_ACTIVE_HIGH>;
+
+		connector@0 {
+			compatible = "usb-c-connector";
+			reg = <0>;
+
+			power-role = "dual";
+			data-role = "dual";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+
+					pmic_glink_hs_in: endpoint {
+						remote-endpoint = <&usb_1_dwc3_hs>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+
+					pmic_glink_ss_in: endpoint {
+						remote-endpoint = <&usb_1_dwc3_ss>;
+					};
+				};
+			};
+		};
+	};
+
+	vph_pwr: vph-pwr-regulator {
+		compatible = "regulator-fixed";
+
+		regulator-name = "vph_pwr";
+		regulator-min-microvolt = <3700000>;
+		regulator-max-microvolt = <3700000>;
+
+		regulator-always-on;
+		regulator-boot-on;
+	};
+};
+
+&apps_rsc {
+	regulators-0 {
+		compatible = "qcom,pm8550-rpmh-regulators";
+
+		vdd-bob1-supply = <&vph_pwr>;
+		vdd-bob2-supply = <&vph_pwr>;
+		vdd-l2-l13-l14-supply = <&vreg_bob1>;
+		vdd-l3-supply = <&vreg_s1c_1p2>;
+		vdd-l5-l16-supply = <&vreg_bob1>;
+		vdd-l6-l7-supply = <&vreg_bob1>;
+		vdd-l8-l9-supply = <&vreg_bob1>;
+		vdd-l11-supply = <&vreg_s1c_1p2>;
+		vdd-l12-supply = <&vreg_s6c_1p8>;
+		vdd-l15-supply = <&vreg_s6c_1p8>;
+		vdd-l17-supply = <&vreg_bob2>;
+
+		qcom,pmic-id = "b";
+
+		vreg_bob1: bob1 {
+			regulator-name = "vreg_bob1";
+			regulator-min-microvolt = <3296000>;
+			regulator-max-microvolt = <3960000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_bob2: bob2 {
+			regulator-name = "vreg_bob2";
+			regulator-min-microvolt = <2720000>;
+			regulator-max-microvolt = <3008000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2b_3p0: ldo2 {
+			regulator-name = "vreg_l2b_3p0";
+			regulator-min-microvolt = <3008000>;
+			regulator-max-microvolt = <3008000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l5b_3p1: ldo5 {
+			regulator-name = "vreg_l5b_3p1";
+			regulator-min-microvolt = <3104000>;
+			regulator-max-microvolt = <3104000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6b_1p8: ldo6 {
+			regulator-name = "vreg_l6b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <3008000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l7b_1p8: ldo7 {
+			regulator-name = "vreg_l7b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <3008000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l8b_1p8: ldo8 {
+			regulator-name = "vreg_l8b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <3008000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l9b_2p9: ldo9 {
+			regulator-name = "vreg_l9b_2p9";
+			regulator-min-microvolt = <2960000>;
+			regulator-max-microvolt = <3008000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l11b_1p2: ldo11 {
+			regulator-name = "vreg_l11b_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1504000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l12b_1p8: ldo12 {
+			regulator-name = "vreg_l12b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l13b_3p0: ldo13 {
+			regulator-name = "vreg_l13b_3p0";
+			regulator-min-microvolt = <3000000>;
+			regulator-max-microvolt = <3000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l14b_3p2: ldo14 {
+			regulator-name = "vreg_l14b_3p2";
+			regulator-min-microvolt = <3200000>;
+			regulator-max-microvolt = <3200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l15b_1p8: ldo15 {
+			regulator-name = "vreg_l15b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l16b_2p8: ldo16 {
+			regulator-name = "vreg_l16b_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l17b_2p5: ldo17 {
+			regulator-name = "vreg_l17b_2p5";
+			regulator-min-microvolt = <2504000>;
+			regulator-max-microvolt = <2504000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-1 {
+		compatible = "qcom,pm8550vs-rpmh-regulators";
+
+		vdd-l1-supply = <&vreg_s1c_1p2>;
+		vdd-l2-supply = <&vreg_s1c_1p2>;
+		vdd-l3-supply = <&vreg_s1c_1p2>;
+		vdd-s1-supply = <&vph_pwr>;
+		vdd-s2-supply = <&vph_pwr>;
+		vdd-s3-supply = <&vph_pwr>;
+		vdd-s4-supply = <&vph_pwr>;
+		vdd-s5-supply = <&vph_pwr>;
+		vdd-s6-supply = <&vph_pwr>;
+
+		qcom,pmic-id = "c";
+
+		vreg_s1c_1p2: smps1 {
+			regulator-name = "vreg_s1c_1p2";
+			regulator-min-microvolt = <1256000>;
+			regulator-max-microvolt = <1348000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s2c_0p8: smps2 {
+			regulator-name = "vreg_s2c_0p8";
+			regulator-min-microvolt = <852000>;
+			regulator-max-microvolt = <1036000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s3c_0p9: smps3 {
+			regulator-name = "vreg_s3c_0p9";
+			regulator-min-microvolt = <976000>;
+			regulator-max-microvolt = <1064000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s4c_1p2: smps4 {
+			regulator-name = "vreg_s4c_1p2";
+			regulator-min-microvolt = <1224000>;
+			regulator-max-microvolt = <1280000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s5c_0p7: smps5 {
+			regulator-name = "vreg_s5c_0p7";
+			regulator-min-microvolt = <752000>;
+			regulator-max-microvolt = <900000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s6c_1p8: smps6 {
+			regulator-name = "vreg_s6c_1p8";
+			regulator-min-microvolt = <1856000>;
+			regulator-max-microvolt = <2000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l1c_1p2: ldo1 {
+			regulator-name = "vreg_l1c_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3c_1p2: ldo3 {
+			regulator-name = "vreg_l3c_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-2 {
+		compatible = "qcom,pm8550vs-rpmh-regulators";
+
+		vdd-l1-supply = <&vreg_s3c_0p9>;
+
+		qcom,pmic-id = "d";
+
+		vreg_l1d_0p88: ldo1 {
+			regulator-name = "vreg_l1d_0p88";
+			regulator-min-microvolt = <912000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-3 {
+		compatible = "qcom,pm8550vs-rpmh-regulators";
+
+		vdd-l3-supply = <&vreg_s3c_0p9>;
+
+		qcom,pmic-id = "e";
+
+		vreg_l3e_0p9: ldo3 {
+			regulator-name = "vreg_l3e_0p9";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-4 {
+		compatible = "qcom,pm8550vs-rpmh-regulators";
+
+		vdd-l1-supply = <&vreg_s3c_0p9>;
+		vdd-l3-supply = <&vreg_s3c_0p9>;
+
+		qcom,pmic-id = "g";
+
+		vreg_l1g_0p91: ldo1 {
+			regulator-name = "vreg_l1g_0p91";
+			regulator-min-microvolt = <912000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3g_0p91: ldo3 {
+			regulator-name = "vreg_l3g_0p91";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <912000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-5 {
+		compatible = "qcom,pm8550ve-rpmh-regulators";
+
+		vdd-l1-supply = <&vreg_s3c_0p9>;
+		vdd-l2-supply = <&vreg_s3c_0p9>;
+		vdd-l3-supply = <&vreg_s1c_1p2>;
+		vdd-s4-supply = <&vph_pwr>;
+
+		qcom,pmic-id = "i";
+
+		vreg_s4i_0p85: smps4 {
+			regulator-name = "vreg_s4i_0p85";
+			regulator-min-microvolt = <852000>;
+			regulator-max-microvolt = <1004000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l1i_0p88: ldo1 {
+			regulator-name = "vreg_l1i_0p88";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <912000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2i_0p88: ldo2 {
+			regulator-name = "vreg_l2i_0p88";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <912000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3i_1p2: ldo3 {
+			regulator-name = "vreg_l3i_0p91";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+};
+
+&dispcc {
+	status = "okay";
+};
+
+&lpass_tlmm {
+	spkr_1_sd_n_active: spkr-1-sd-n-active-state {
+		pins = "gpio21";
+		function = "gpio";
+		drive-strength = <16>;
+		bias-disable;
+		output-low;
+	};
+};
+
+&mdss {
+	status = "okay";
+};
+
+&mdss_dsi0 {
+	vdda-supply = <&vreg_l3i_1p2>;
+
+	status = "okay";
+
+	panel@0 {
+		compatible = "visionox,vtdr6130";
+		reg = <0>;
+
+		reset-gpios = <&tlmm 133 GPIO_ACTIVE_LOW>;
+
+		vddio-supply = <&vreg_l12b_1p8>;
+		vci-supply = <&vreg_l13b_3p0>;
+		vdd-supply = <&vreg_l11b_1p2>;
+
+		pinctrl-0 = <&disp0_reset_n_active>, <&mdp_vsync_active>;
+		pinctrl-1 = <&disp0_reset_n_suspend>, <&mdp_vsync_suspend>;
+		pinctrl-names = "default", "sleep";
+
+		port {
+			panel0_in: endpoint {
+				remote-endpoint = <&mdss_dsi0_out>;
+			};
+		};
+	};
+};
+
+&mdss_dsi0_out {
+	remote-endpoint = <&panel0_in>;
+	data-lanes = <0 1 2 3>;
+};
+
+&mdss_dsi0_phy {
+	vdds-supply = <&vreg_l1i_0p88>;
+
+	status = "okay";
+};
+
+&mdss_mdp {
+	status = "okay";
+};
+
+&pcie_1_phy_aux_clk {
+	clock-frequency = <1000>;
+};
+
+&pcie0 {
+	wake-gpios = <&tlmm 96 GPIO_ACTIVE_HIGH>;
+	perst-gpios = <&tlmm 94 GPIO_ACTIVE_LOW>;
+
+	pinctrl-0 = <&pcie0_default_state>;
+	pinctrl-names = "default";
+
+	status = "okay";
+};
+
+&pcie0_phy {
+	vdda-phy-supply = <&vreg_l1i_0p88>;
+	vdda-pll-supply = <&vreg_l3i_1p2>;
+
+	status = "okay";
+};
+
+&pcie1 {
+	wake-gpios = <&tlmm 99 GPIO_ACTIVE_HIGH>;
+	perst-gpios = <&tlmm 97 GPIO_ACTIVE_LOW>;
+
+	pinctrl-0 = <&pcie1_default_state>;
+	pinctrl-names = "default";
+
+	status = "okay";
+};
+
+&pcie1_phy {
+	vdda-phy-supply = <&vreg_l3e_0p9>;
+	vdda-pll-supply = <&vreg_l3i_1p2>;
+	vdda-qref-supply = <&vreg_l1i_0p88>;
+
+	status = "okay";
+};
+
+&pm8550_gpios {
+	sdc2_card_det_n: sdc2-card-det-state {
+		pins = "gpio12";
+		function = "normal";
+		bias-pull-up;
+		input-enable;
+		output-disable;
+		power-source = <1>; /* 1.8 V */
+	};
+};
+
+&pm8550b_eusb2_repeater {
+	vdd18-supply = <&vreg_l15b_1p8>;
+	vdd3-supply = <&vreg_l5b_3p1>;
+};
+
+&qupv3_id_1 {
+	status = "okay";
+};
+
+&remoteproc_adsp {
+	firmware-name = "qcom/sm8650/adsp.mbn",
+			"qcom/sm8650/adsp_dtb.mbn";
+
+	status = "okay";
+};
+
+&remoteproc_cdsp {
+	firmware-name = "qcom/sm8650/cdsp.mbn",
+			"qcom/sm8650/cdsp_dtb.mbn";
+
+	status = "okay";
+};
+
+&remoteproc_mpss {
+	firmware-name = "qcom/sm8650/modem.mbn",
+			"qcom/sm8650/modem_dtb.mbn";
+
+	status = "okay";
+};
+
+&sdhc_2 {
+	cd-gpios = <&pm8550_gpios 12 GPIO_ACTIVE_LOW>;
+
+	vmmc-supply = <&vreg_l9b_2p9>;
+	vqmmc-supply = <&vreg_l8b_1p8>;
+	bus-width = <4>;
+	no-sdio;
+	no-mmc;
+
+	pinctrl-0 = <&sdc2_default>, <&sdc2_card_det_n>;
+	pinctrl-1 = <&sdc2_sleep>, <&sdc2_card_det_n>;
+	pinctrl-names = "default", "sleep";
+
+	status = "okay";
+};
+
+&sleep_clk {
+	clock-frequency = <32000>;
+};
+
+&swr0 {
+	status = "okay";
+
+	/* WSA8845, Speaker Left */
+	left_spkr: speaker@0,0 {
+		compatible = "sdw20217020400";
+		reg = <0 0>;
+		pinctrl-0 = <&spkr_1_sd_n_active>;
+		pinctrl-names = "default";
+		powerdown-gpios = <&lpass_tlmm 21 GPIO_ACTIVE_LOW>;
+		#sound-dai-cells = <0>;
+		sound-name-prefix = "SpkrLeft";
+		vdd-1p8-supply = <&vreg_l15b_1p8>;
+		vdd-io-supply = <&vreg_l3c_1p2>;
+	};
+
+	/* WSA8845, Speaker Right */
+	right_spkr: speaker@0,1 {
+		compatible = "sdw20217020400";
+		reg = <0 1>;
+		pinctrl-0 = <&spkr_2_sd_n_active>;
+		pinctrl-names = "default";
+		powerdown-gpios = <&tlmm 77 GPIO_ACTIVE_LOW>;
+		#sound-dai-cells = <0>;
+		sound-name-prefix = "SpkrRight";
+		vdd-1p8-supply = <&vreg_l15b_1p8>;
+		vdd-io-supply = <&vreg_l3c_1p2>;
+	};
+};
+
+&tlmm {
+	/* Reserved I/Os for NFC */
+	gpio-reserved-ranges = <32 8>;
+
+	disp0_reset_n_active: disp0-reset-n-active-state {
+		pins = "gpio133";
+		function = "gpio";
+		drive-strength = <8>;
+		bias-disable;
+	};
+
+	disp0_reset_n_suspend: disp0-reset-n-suspend-state {
+		pins = "gpio133";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-pull-down;
+	};
+
+	mdp_vsync_active: mdp-vsync-active-state {
+		pins = "gpio86";
+		function = "mdp_vsync";
+		drive-strength = <2>;
+		bias-pull-down;
+	};
+
+	mdp_vsync_suspend: mdp-vsync-suspend-state {
+		pins = "gpio86";
+		function = "mdp_vsync";
+		drive-strength = <2>;
+		bias-pull-down;
+	};
+
+	spkr_2_sd_n_active: spkr-2-sd-n-active-state {
+		pins = "gpio77";
+		function = "gpio";
+		drive-strength = <16>;
+		bias-disable;
+		output-low;
+	};
+};
+
+&uart15 {
+	status = "okay";
+};
+
+&ufs_mem_hc {
+	reset-gpios = <&tlmm 210 GPIO_ACTIVE_LOW>;
+
+	vcc-supply = <&vreg_l17b_2p5>;
+	vcc-max-microamp = <1300000>;
+	vccq-supply = <&vreg_l1c_1p2>;
+	vccq-max-microamp = <1200000>;
+
+	status = "okay";
+};
+
+&ufs_mem_phy {
+	vdda-phy-supply = <&vreg_l1d_0p88>;
+	vdda-pll-supply = <&vreg_l3i_1p2>;
+
+	status = "okay";
+};
+
+/*
+ * DPAUX -> WCD9395 -> USB_SBU -> USB-C
+ * eUSB2 DP/DM -> PM85550HS -> eUSB2 DP/DM -> USB-C
+ * USB SS -> USB-C
+ */
+
+&usb_1 {
+	status = "okay";
+};
+
+&usb_1_dwc3 {
+	dr_mode = "otg";
+	usb-role-switch;
+};
+
+&usb_1_dwc3_hs {
+	remote-endpoint = <&pmic_glink_hs_in>;
+};
+
+&usb_1_dwc3_ss {
+	remote-endpoint = <&pmic_glink_ss_in>;
+};
+
+&usb_1_hsphy {
+	vdd-supply = <&vreg_l1i_0p88>;
+	vdda12-supply = <&vreg_l3i_1p2>;
+
+	phys = <&pm8550b_eusb2_repeater>;
+
+	status = "okay";
+};
+
+&usb_dp_qmpphy {
+	vdda-phy-supply = <&vreg_l3i_1p2>;
+	vdda-pll-supply = <&vreg_l3g_0p91>;
+
+	status = "okay";
+};
+
+&xo_board {
+	clock-frequency = <76800000>;
+};
diff --git a/arch/arm64/boot/dts/qcom/sm8650-qrd.dts b/arch/arm64/boot/dts/qcom/sm8650-qrd.dts
new file mode 100644
index 000000000000..592a67a47c78
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/sm8650-qrd.dts
@@ -0,0 +1,811 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/regulator/qcom,rpmh-regulator.h>
+#include "sm8650.dtsi"
+#include "pm8010.dtsi"
+#include "pm8550.dtsi"
+#include "pm8550b.dtsi"
+#define PMK8550VE_SID 8
+#include "pm8550ve.dtsi"
+#include "pm8550vs.dtsi"
+#include "pmk8550.dtsi"
+#include "pmr735d_a.dtsi"
+
+/ {
+	model = "Qualcomm Technologies, Inc. SM8650 QRD";
+	compatible = "qcom,sm8650-qrd", "qcom,sm8650";
+
+	aliases {
+		serial0 = &uart15;
+		serial1 = &uart14;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		pinctrl-0 = <&volume_up_n>;
+		pinctrl-names = "default";
+
+		key-volume-up {
+			label = "Volume Up";
+			linux,code = <KEY_VOLUMEUP>;
+			gpios = <&pm8550_gpios 6 GPIO_ACTIVE_LOW>;
+			debounce-interval = <15>;
+			linux,can-disable;
+			wakeup-source;
+		};
+	};
+
+	pmic-glink {
+		compatible = "qcom,sm8650-pmic-glink",
+			     "qcom,sm8550-pmic-glink",
+			     "qcom,pmic-glink";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		orientation-gpios = <&tlmm 29 GPIO_ACTIVE_HIGH>;
+
+		connector@0 {
+			compatible = "usb-c-connector";
+			reg = <0>;
+
+			power-role = "dual";
+			data-role = "dual";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+
+					pmic_glink_hs_in: endpoint {
+						remote-endpoint = <&usb_1_dwc3_hs>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+
+					pmic_glink_ss_in: endpoint {
+						remote-endpoint = <&usb_1_dwc3_ss>;
+					};
+				};
+			};
+		};
+	};
+
+	vph_pwr: vph-pwr-regulator {
+		compatible = "regulator-fixed";
+
+		regulator-name = "vph_pwr";
+		regulator-min-microvolt = <3700000>;
+		regulator-max-microvolt = <3700000>;
+
+		regulator-always-on;
+		regulator-boot-on;
+	};
+};
+
+&apps_rsc {
+	regulators-0 {
+		compatible = "qcom,pm8550-rpmh-regulators";
+
+		vdd-bob1-supply = <&vph_pwr>;
+		vdd-bob2-supply = <&vph_pwr>;
+		vdd-l2-l13-l14-supply = <&vreg_bob1>;
+		vdd-l3-supply = <&vreg_s1c_1p2>;
+		vdd-l5-l16-supply = <&vreg_bob1>;
+		vdd-l6-l7-supply = <&vreg_bob1>;
+		vdd-l8-l9-supply = <&vreg_bob1>;
+		vdd-l11-supply = <&vreg_s1c_1p2>;
+		vdd-l12-supply = <&vreg_s6c_1p8>;
+		vdd-l15-supply = <&vreg_s6c_1p8>;
+		vdd-l17-supply = <&vreg_bob2>;
+
+		qcom,pmic-id = "b";
+
+		vreg_bob1: bob1 {
+			regulator-name = "vreg_bob1";
+			regulator-min-microvolt = <3296000>;
+			regulator-max-microvolt = <3960000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_bob2: bob2 {
+			regulator-name = "vreg_bob2";
+			regulator-min-microvolt = <2720000>;
+			regulator-max-microvolt = <3008000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2b_3p0: ldo2 {
+			regulator-name = "vreg_l2b_3p0";
+			regulator-min-microvolt = <3008000>;
+			regulator-max-microvolt = <3008000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l5b_3p1: ldo5 {
+			regulator-name = "vreg_l5b_3p1";
+			regulator-min-microvolt = <3104000>;
+			regulator-max-microvolt = <3104000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6b_1p8: ldo6 {
+			regulator-name = "vreg_l6b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <3008000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l7b_1p8: ldo7 {
+			regulator-name = "vreg_l7b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <3008000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l8b_1p8: ldo8 {
+			regulator-name = "vreg_l8b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <3008000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l11b_1p2: ldo11 {
+			regulator-name = "vreg_l11b_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1504000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l12b_1p8: ldo12 {
+			regulator-name = "vreg_l12b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l13b_3p0: ldo13 {
+			regulator-name = "vreg_l13b_3p0";
+			regulator-min-microvolt = <3000000>;
+			regulator-max-microvolt = <3000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l14b_3p2: ldo14 {
+			regulator-name = "vreg_l14b_3p2";
+			regulator-min-microvolt = <3200000>;
+			regulator-max-microvolt = <3200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l15b_1p8: ldo15 {
+			regulator-name = "vreg_l15b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l16b_2p8: ldo16 {
+			regulator-name = "vreg_l16b_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l17b_2p5: ldo17 {
+			regulator-name = "vreg_l17b_2p5";
+			regulator-min-microvolt = <2504000>;
+			regulator-max-microvolt = <2504000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-1 {
+		compatible = "qcom,pm8550vs-rpmh-regulators";
+
+		vdd-l1-supply = <&vreg_s1c_1p2>;
+		vdd-l2-supply = <&vreg_s1c_1p2>;
+		vdd-l3-supply = <&vreg_s1c_1p2>;
+		vdd-s1-supply = <&vph_pwr>;
+		vdd-s2-supply = <&vph_pwr>;
+		vdd-s3-supply = <&vph_pwr>;
+		vdd-s4-supply = <&vph_pwr>;
+		vdd-s5-supply = <&vph_pwr>;
+		vdd-s6-supply = <&vph_pwr>;
+
+		qcom,pmic-id = "c";
+
+		vreg_s1c_1p2: smps1 {
+			regulator-name = "vreg_s1c_1p2";
+			regulator-min-microvolt = <1256000>;
+			regulator-max-microvolt = <1348000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s2c_0p8: smps2 {
+			regulator-name = "vreg_s2c_0p8";
+			regulator-min-microvolt = <852000>;
+			regulator-max-microvolt = <1036000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s3c_0p9: smps3 {
+			regulator-name = "vreg_s3c_0p9";
+			regulator-min-microvolt = <976000>;
+			regulator-max-microvolt = <1064000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s4c_1p2: smps4 {
+			regulator-name = "vreg_s4c_1p2";
+			regulator-min-microvolt = <1224000>;
+			regulator-max-microvolt = <1280000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s5c_0p7: smps5 {
+			regulator-name = "vreg_s5c_0p7";
+			regulator-min-microvolt = <752000>;
+			regulator-max-microvolt = <900000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s6c_1p8: smps6 {
+			regulator-name = "vreg_s6c_1p8";
+			regulator-min-microvolt = <1856000>;
+			regulator-max-microvolt = <2000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l1c_1p2: ldo1 {
+			regulator-name = "vreg_l1c_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3c_1p2: ldo3 {
+			regulator-name = "vreg_l3c_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-2 {
+		compatible = "qcom,pm8550vs-rpmh-regulators";
+
+		vdd-l1-supply = <&vreg_s3c_0p9>;
+
+		qcom,pmic-id = "d";
+
+		vreg_l1d_0p88: ldo1 {
+			regulator-name = "vreg_l1d_0p88";
+			regulator-min-microvolt = <912000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-3 {
+		compatible = "qcom,pm8550vs-rpmh-regulators";
+
+		vdd-l3-supply = <&vreg_s3c_0p9>;
+
+		qcom,pmic-id = "e";
+
+		vreg_l3e_0p9: ldo3 {
+			regulator-name = "vreg_l3e_0p9";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-4 {
+		compatible = "qcom,pm8550vs-rpmh-regulators";
+
+		vdd-l1-supply = <&vreg_s3c_0p9>;
+		vdd-l3-supply = <&vreg_s3c_0p9>;
+
+		qcom,pmic-id = "g";
+
+		vreg_l1g_0p91: ldo1 {
+			regulator-name = "vreg_l1g_0p91";
+			regulator-min-microvolt = <912000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3g_0p91: ldo3 {
+			regulator-name = "vreg_l3g_0p91";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <912000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-5 {
+		compatible = "qcom,pm8550ve-rpmh-regulators";
+
+		vdd-l1-supply = <&vreg_s3c_0p9>;
+		vdd-l2-supply = <&vreg_s3c_0p9>;
+		vdd-l3-supply = <&vreg_s1c_1p2>;
+		vdd-s4-supply = <&vph_pwr>;
+
+		qcom,pmic-id = "i";
+
+		vreg_s4i_0p85: smps4 {
+			regulator-name = "vreg_s4i_0p85";
+			regulator-min-microvolt = <852000>;
+			regulator-max-microvolt = <1004000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l1i_0p88: ldo1 {
+			regulator-name = "vreg_l1i_0p88";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <912000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2i_0p88: ldo2 {
+			regulator-name = "vreg_l2i_0p88";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <912000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3i_1p2: ldo3 {
+			regulator-name = "vreg_l3i_0p91";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+};
+
+&dispcc {
+	status = "okay";
+};
+
+&gpi_dma1 {
+	status = "okay";
+};
+
+&ipa {
+	qcom,gsi-loader = "self";
+	memory-region = <&ipa_fw_mem>;
+	firmware-name = "qcom/sm8650/ipa_fws.mbn";
+	status = "okay";
+};
+
+&mdss {
+	status = "okay";
+};
+
+&mdss_dsi0 {
+	vdda-supply = <&vreg_l3i_1p2>;
+
+	status = "okay";
+
+	panel@0 {
+		compatible = "visionox,vtdr6130";
+		reg = <0>;
+
+		reset-gpios = <&tlmm 133 GPIO_ACTIVE_LOW>;
+
+		vddio-supply = <&vreg_l12b_1p8>;
+		vci-supply = <&vreg_l13b_3p0>;
+		vdd-supply = <&vreg_l11b_1p2>;
+
+		pinctrl-0 = <&disp0_reset_n_active>, <&mdp_vsync_active>;
+		pinctrl-1 = <&disp0_reset_n_suspend>, <&mdp_vsync_suspend>;
+		pinctrl-names = "default", "sleep";
+
+		port {
+			panel0_in: endpoint {
+				remote-endpoint = <&mdss_dsi0_out>;
+			};
+		};
+	};
+};
+
+&mdss_dsi0_out {
+	remote-endpoint = <&panel0_in>;
+	data-lanes = <0 1 2 3>;
+};
+
+&mdss_dsi0_phy {
+	vdds-supply = <&vreg_l1i_0p88>;
+
+	status = "okay";
+};
+
+&mdss_mdp {
+	status = "okay";
+};
+
+&pcie_1_phy_aux_clk {
+	clock-frequency = <1000>;
+};
+
+&pcie0 {
+	wake-gpios = <&tlmm 96 GPIO_ACTIVE_HIGH>;
+	perst-gpios = <&tlmm 94 GPIO_ACTIVE_LOW>;
+
+	pinctrl-0 = <&pcie0_default_state>;
+	pinctrl-names = "default";
+
+	status = "okay";
+};
+
+&pcie0_phy {
+	vdda-phy-supply = <&vreg_l1i_0p88>;
+	vdda-pll-supply = <&vreg_l3i_1p2>;
+
+	status = "okay";
+};
+
+&pon_pwrkey {
+	status = "okay";
+};
+
+&pon_resin {
+	linux,code = <KEY_VOLUMEDOWN>;
+
+	status = "okay";
+};
+
+&pm8550_flash {
+	status = "okay";
+
+	led-0 {
+		function = LED_FUNCTION_FLASH;
+		color = <LED_COLOR_ID_YELLOW>;
+		led-sources = <1>, <4>;
+		led-max-microamp = <500000>;
+		flash-max-microamp = <2000000>;
+		flash-max-timeout-us = <1280000>;
+		function-enumerator = <0>;
+	};
+
+	led-1 {
+		function = LED_FUNCTION_FLASH;
+		color = <LED_COLOR_ID_WHITE>;
+		led-sources = <2>, <3>;
+		led-max-microamp = <500000>;
+		flash-max-microamp = <2000000>;
+		flash-max-timeout-us = <1280000>;
+		function-enumerator = <1>;
+	};
+};
+
+&pm8550_gpios {
+	volume_up_n: volume-up-n-state {
+		pins = "gpio6";
+		function = "normal";
+		bias-pull-up;
+		input-enable;
+		power-source = <1>;
+	};
+};
+
+&pm8550_pwm {
+	status = "okay";
+
+	multi-led {
+		color = <LED_COLOR_ID_RGB>;
+		function = LED_FUNCTION_STATUS;
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		led@1 {
+			reg = <1>;
+			color = <LED_COLOR_ID_RED>;
+		};
+
+		led@2 {
+			reg = <2>;
+			color = <LED_COLOR_ID_GREEN>;
+		};
+
+		led@3 {
+			reg = <3>;
+			color = <LED_COLOR_ID_BLUE>;
+		};
+	};
+};
+
+&pm8550b_eusb2_repeater {
+	vdd18-supply = <&vreg_l15b_1p8>;
+	vdd3-supply = <&vreg_l5b_3p1>;
+};
+
+&pmk8550_rtc {
+	status = "okay";
+};
+
+&qupv3_id_0 {
+	status = "okay";
+};
+
+&qupv3_id_1 {
+	status = "okay";
+};
+
+&remoteproc_adsp {
+	firmware-name = "qcom/sm8650/adsp.mbn",
+			"qcom/sm8650/adsp_dtb.mbn";
+
+	status = "okay";
+};
+
+&remoteproc_cdsp {
+	firmware-name = "qcom/sm8650/cdsp.mbn",
+			"qcom/sm8650/cdsp_dtb.mbn";
+
+	status = "okay";
+};
+
+&remoteproc_mpss {
+	firmware-name = "qcom/sm8650/modem.mbn",
+			"qcom/sm8650/modem_dtb.mbn";
+
+	status = "okay";
+};
+
+&sleep_clk {
+	clock-frequency = <32000>;
+};
+
+&spi4 {
+	status = "okay";
+
+	touchscreen@0 {
+		compatible = "goodix,gt9916";
+		reg = <0>;
+
+		interrupt-parent = <&tlmm>;
+		interrupts = <162 IRQ_TYPE_LEVEL_LOW>;
+
+		reset-gpios = <&tlmm 161 GPIO_ACTIVE_LOW>;
+
+		avdd-supply = <&vreg_l14b_3p2>;
+
+		spi-max-frequency = <1000000>;
+
+		touchscreen-size-x = <1080>;
+		touchscreen-size-y = <2400>;
+
+		pinctrl-0 = <&ts_irq>, <&ts_reset>;
+		pinctrl-names = "default";
+	};
+};
+
+&tlmm {
+	/* Reserved I/Os for NFC */
+	gpio-reserved-ranges = <32 8>;
+
+	bt_default: bt-default-state {
+		bt-en-pins {
+			pins = "gpio17";
+			function = "gpio";
+			drive-strength = <16>;
+			bias-disable;
+		};
+
+		sw-ctrl-pins {
+			pins = "gpio18";
+			function = "gpio";
+			bias-pull-down;
+		};
+	};
+
+	disp0_reset_n_active: disp0-reset-n-active-state {
+		pins = "gpio133";
+		function = "gpio";
+		drive-strength = <8>;
+		bias-disable;
+	};
+
+	disp0_reset_n_suspend: disp0-reset-n-suspend-state {
+		pins = "gpio133";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-pull-down;
+	};
+
+	mdp_vsync_active: mdp-vsync-active-state {
+		pins = "gpio86";
+		function = "mdp_vsync";
+		drive-strength = <2>;
+		bias-pull-down;
+	};
+
+	mdp_vsync_suspend: mdp-vsync-suspend-state {
+		pins = "gpio86";
+		function = "mdp_vsync";
+		drive-strength = <2>;
+		bias-pull-down;
+	};
+
+	ts_irq: ts-irq-state {
+		pins = "gpio161";
+		function = "gpio";
+		drive-strength = <8>;
+		bias-pull-up;
+		output-disable;
+	};
+
+	ts_reset: ts-reset-state {
+		pins = "gpio162";
+		function = "gpio";
+		drive-strength = <8>;
+		bias-pull-up;
+	};
+};
+
+&uart14 {
+	status = "okay";
+
+	bluetooth {
+		compatible = "qcom,wcn7850-bt";
+
+		clocks = <&rpmhcc RPMH_RF_CLK1>;
+
+		vddio-supply = <&vreg_l3c_1p2>;
+		vddaon-supply = <&vreg_l15b_1p8>;
+		vdddig-supply = <&vreg_s3c_0p9>;
+		vddrfa0p8-supply = <&vreg_s3c_0p9>;
+		vddrfa1p2-supply = <&vreg_s1c_1p2>;
+		vddrfa1p9-supply = <&vreg_s6c_1p8>;
+
+		max-speed = <3200000>;
+
+		enable-gpios = <&tlmm 17 GPIO_ACTIVE_HIGH>;
+		swctrl-gpios = <&tlmm 18 GPIO_ACTIVE_HIGH>;
+
+		pinctrl-0 = <&bt_default>;
+		pinctrl-names = "default";
+	};
+};
+
+&uart15 {
+	status = "okay";
+};
+
+&ufs_mem_hc {
+	reset-gpios = <&tlmm 210 GPIO_ACTIVE_LOW>;
+
+	vcc-supply = <&vreg_l17b_2p5>;
+	vcc-max-microamp = <1300000>;
+	vccq-supply = <&vreg_l1c_1p2>;
+	vccq-max-microamp = <1200000>;
+
+	status = "okay";
+};
+
+&ufs_mem_phy {
+	vdda-phy-supply = <&vreg_l1d_0p88>;
+	vdda-pll-supply = <&vreg_l3i_1p2>;
+
+	status = "okay";
+};
+
+/*
+ * DPAUX -> WCD9395 -> USB_SBU -> USB-C
+ * eUSB2 DP/DM -> PM85550HS -> eUSB2 DP/DM -> WCD9395 -> USB-C
+ * USB SS -> NB7VPQ904MMUTWG -> USB-C
+ */
+
+&usb_1 {
+	status = "okay";
+};
+
+&usb_1_dwc3 {
+	dr_mode = "otg";
+	usb-role-switch;
+};
+
+&usb_1_dwc3_hs {
+	remote-endpoint = <&pmic_glink_hs_in>;
+};
+
+&usb_1_dwc3_ss {
+	remote-endpoint = <&pmic_glink_ss_in>;
+};
+
+&usb_1_hsphy {
+	vdd-supply = <&vreg_l1i_0p88>;
+	vdda12-supply = <&vreg_l3i_1p2>;
+
+	phys = <&pm8550b_eusb2_repeater>;
+
+	status = "okay";
+};
+
+&usb_dp_qmpphy {
+	vdda-phy-supply = <&vreg_l3i_1p2>;
+	vdda-pll-supply = <&vreg_l3g_0p91>;
+
+	status = "okay";
+};
+
+&xo_board {
+	clock-frequency = <76800000>;
+};
diff --git a/arch/arm64/boot/dts/qcom/sm8650.dtsi b/arch/arm64/boot/dts/qcom/sm8650.dtsi
new file mode 100644
index 000000000000..2df77123a8c7
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/sm8650.dtsi
@@ -0,0 +1,6013 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#include <dt-bindings/clock/qcom,rpmh.h>
+#include <dt-bindings/clock/qcom,sm8650-dispcc.h>
+#include <dt-bindings/clock/qcom,sm8650-gcc.h>
+#include <dt-bindings/clock/qcom,sm8650-gpucc.h>
+#include <dt-bindings/clock/qcom,sm8650-tcsr.h>
+#include <dt-bindings/dma/qcom-gpi.h>
+#include <dt-bindings/firmware/qcom,scm.h>
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interconnect/qcom,icc.h>
+#include <dt-bindings/interconnect/qcom,sm8650-rpmh.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/mailbox/qcom-ipcc.h>
+#include <dt-bindings/phy/phy-qcom-qmp.h>
+#include <dt-bindings/power/qcom,rpmhpd.h>
+#include <dt-bindings/power/qcom-rpmpd.h>
+#include <dt-bindings/reset/qcom,sm8650-gpucc.h>
+#include <dt-bindings/soc/qcom,gpr.h>
+#include <dt-bindings/soc/qcom,rpmh-rsc.h>
+#include <dt-bindings/sound/qcom,q6dsp-lpass-ports.h>
+#include <dt-bindings/thermal/thermal.h>
+
+/ {
+	interrupt-parent = <&intc>;
+
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen { };
+
+	clocks {
+		xo_board: xo-board {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+		};
+
+		sleep_clk: sleep-clk {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+		};
+
+		bi_tcxo_div2: bi-tcxo-div2-clk {
+			compatible = "fixed-factor-clock";
+			#clock-cells = <0>;
+
+			clocks = <&rpmhcc RPMH_CXO_CLK>;
+			clock-mult = <1>;
+			clock-div = <2>;
+		};
+
+		bi_tcxo_ao_div2: bi-tcxo-ao-div2-clk {
+			compatible = "fixed-factor-clock";
+			#clock-cells = <0>;
+
+			clocks = <&rpmhcc RPMH_CXO_CLK_A>;
+			clock-mult = <1>;
+			clock-div = <2>;
+		};
+
+		pcie_1_phy_aux_clk: pcie-1-phy-aux-clk {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+		};
+	};
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		CPU0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a520";
+			reg = <0 0>;
+
+			clocks = <&cpufreq_hw 0>;
+
+			power-domains = <&CPU_PD0>;
+			power-domain-names = "psci";
+
+			enable-method = "psci";
+			next-level-cache = <&L2_0>;
+			capacity-dmips-mhz = <1024>;
+			dynamic-power-coefficient = <100>;
+
+			qcom,freq-domain = <&cpufreq_hw 0>;
+
+			#cooling-cells = <2>;
+
+			L2_0: l2-cache {
+				compatible = "cache";
+				cache-level = <2>;
+				cache-unified;
+				next-level-cache = <&L3_0>;
+
+				L3_0: l3-cache {
+					compatible = "cache";
+					cache-level = <3>;
+					cache-unified;
+				};
+			};
+		};
+
+		CPU1: cpu@100 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a520";
+			reg = <0 0x100>;
+
+			clocks = <&cpufreq_hw 0>;
+
+			power-domains = <&CPU_PD1>;
+			power-domain-names = "psci";
+
+			enable-method = "psci";
+			next-level-cache = <&L2_0>;
+			capacity-dmips-mhz = <1024>;
+			dynamic-power-coefficient = <100>;
+
+			qcom,freq-domain = <&cpufreq_hw 0>;
+
+			#cooling-cells = <2>;
+		};
+
+		CPU2: cpu@200 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a720";
+			reg = <0 0x200>;
+
+			clocks = <&cpufreq_hw 3>;
+
+			power-domains = <&CPU_PD2>;
+			power-domain-names = "psci";
+
+			enable-method = "psci";
+			next-level-cache = <&L2_200>;
+			capacity-dmips-mhz = <1792>;
+			dynamic-power-coefficient = <238>;
+
+			qcom,freq-domain = <&cpufreq_hw 3>;
+
+			#cooling-cells = <2>;
+
+			L2_200: l2-cache {
+				compatible = "cache";
+				cache-level = <2>;
+				cache-unified;
+				next-level-cache = <&L3_0>;
+			};
+		};
+
+		CPU3: cpu@300 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a720";
+			reg = <0 0x300>;
+
+			clocks = <&cpufreq_hw 3>;
+
+			power-domains = <&CPU_PD3>;
+			power-domain-names = "psci";
+
+			enable-method = "psci";
+			next-level-cache = <&L2_200>;
+			capacity-dmips-mhz = <1792>;
+			dynamic-power-coefficient = <238>;
+
+			qcom,freq-domain = <&cpufreq_hw 3>;
+
+			#cooling-cells = <2>;
+		};
+
+		CPU4: cpu@400 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a720";
+			reg = <0 0x400>;
+
+			clocks = <&cpufreq_hw 3>;
+
+			power-domains = <&CPU_PD4>;
+			power-domain-names = "psci";
+
+			enable-method = "psci";
+			next-level-cache = <&L2_400>;
+			capacity-dmips-mhz = <1792>;
+			dynamic-power-coefficient = <238>;
+
+			qcom,freq-domain = <&cpufreq_hw 3>;
+
+			#cooling-cells = <2>;
+
+			L2_400: l2-cache {
+				compatible = "cache";
+				cache-level = <2>;
+				cache-unified;
+				next-level-cache = <&L3_0>;
+			};
+		};
+
+		CPU5: cpu@500 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a720";
+			reg = <0 0x500>;
+
+			clocks = <&cpufreq_hw 1>;
+
+			power-domains = <&CPU_PD5>;
+			power-domain-names = "psci";
+
+			enable-method = "psci";
+			next-level-cache = <&L2_500>;
+			capacity-dmips-mhz = <1792>;
+			dynamic-power-coefficient = <238>;
+
+			qcom,freq-domain = <&cpufreq_hw 1>;
+
+			#cooling-cells = <2>;
+
+			L2_500: l2-cache {
+				compatible = "cache";
+				cache-level = <2>;
+				cache-unified;
+				next-level-cache = <&L3_0>;
+			};
+		};
+
+		CPU6: cpu@600 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a720";
+			reg = <0 0x600>;
+
+			clocks = <&cpufreq_hw 1>;
+
+			power-domains = <&CPU_PD6>;
+			power-domain-names = "psci";
+
+			enable-method = "psci";
+			next-level-cache = <&L2_600>;
+			capacity-dmips-mhz = <1792>;
+			dynamic-power-coefficient = <238>;
+
+			qcom,freq-domain = <&cpufreq_hw 1>;
+
+			#cooling-cells = <2>;
+
+			L2_600: l2-cache {
+				compatible = "cache";
+				cache-level = <2>;
+				cache-unified;
+				next-level-cache = <&L3_0>;
+			};
+		};
+
+		CPU7: cpu@700 {
+			device_type = "cpu";
+			compatible = "arm,cortex-x4";
+			reg = <0 0x700>;
+
+			clocks = <&cpufreq_hw 2>;
+
+			power-domains = <&CPU_PD7>;
+			power-domain-names = "psci";
+
+			enable-method = "psci";
+			next-level-cache = <&L2_700>;
+			capacity-dmips-mhz = <1894>;
+			dynamic-power-coefficient = <588>;
+
+			qcom,freq-domain = <&cpufreq_hw 2>;
+
+			#cooling-cells = <2>;
+
+			L2_700: l2-cache {
+				compatible = "cache";
+				cache-level = <2>;
+				cache-unified;
+				next-level-cache = <&L3_0>;
+			};
+		};
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&CPU0>;
+				};
+
+				core1 {
+					cpu = <&CPU1>;
+				};
+
+				core2 {
+					cpu = <&CPU2>;
+				};
+
+				core3 {
+					cpu = <&CPU3>;
+				};
+
+				core4 {
+					cpu = <&CPU4>;
+				};
+
+				core5 {
+					cpu = <&CPU5>;
+				};
+
+				core6 {
+					cpu = <&CPU6>;
+				};
+
+				core7 {
+					cpu = <&CPU7>;
+				};
+			};
+		};
+
+		idle-states {
+			entry-method = "psci";
+
+			SILVER_CPU_SLEEP_0: cpu-sleep-0-0 {
+				compatible = "arm,idle-state";
+				idle-state-name = "silver-rail-power-collapse";
+				arm,psci-suspend-param = <0x40000004>;
+				entry-latency-us = <550>;
+				exit-latency-us = <750>;
+				min-residency-us = <6700>;
+				local-timer-stop;
+			};
+
+			GOLD_CPU_SLEEP_0: cpu-sleep-1-0 {
+				compatible = "arm,idle-state";
+				idle-state-name = "gold-rail-power-collapse";
+				arm,psci-suspend-param = <0x40000004>;
+				entry-latency-us = <600>;
+				exit-latency-us = <1300>;
+				min-residency-us = <8136>;
+				local-timer-stop;
+			};
+
+			GOLD_PLUS_CPU_SLEEP_0: cpu-sleep-2-0 {
+				compatible = "arm,idle-state";
+				idle-state-name = "gold-plus-rail-power-collapse";
+				arm,psci-suspend-param = <0x40000004>;
+				entry-latency-us = <500>;
+				exit-latency-us = <1350>;
+				min-residency-us = <7480>;
+				local-timer-stop;
+			};
+		};
+
+		domain-idle-states {
+			CLUSTER_SLEEP_0: cluster-sleep-0 {
+				compatible = "domain-idle-state";
+				arm,psci-suspend-param = <0x41000044>;
+				entry-latency-us = <750>;
+				exit-latency-us = <2350>;
+				min-residency-us = <9144>;
+			};
+
+			CLUSTER_SLEEP_1: cluster-sleep-1 {
+				compatible = "domain-idle-state";
+				arm,psci-suspend-param = <0x4100c344>;
+				entry-latency-us = <2800>;
+				exit-latency-us = <4400>;
+				min-residency-us = <10150>;
+			};
+		};
+	};
+
+	firmware {
+		scm: scm {
+			compatible = "qcom,scm-sm8650", "qcom,scm";
+			interconnects = <&aggre2_noc MASTER_CRYPTO QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+		};
+	};
+
+	clk_virt: interconnect-0 {
+		compatible = "qcom,sm8650-clk-virt";
+		#interconnect-cells = <2>;
+		qcom,bcm-voters = <&apps_bcm_voter>;
+	};
+
+	mc_virt: interconnect-1 {
+		compatible = "qcom,sm8650-mc-virt";
+		#interconnect-cells = <2>;
+		qcom,bcm-voters = <&apps_bcm_voter>;
+	};
+
+	memory@a0000000 {
+		device_type = "memory";
+		/* We expect the bootloader to fill in the size */
+		reg = <0 0xa0000000 0 0>;
+	};
+
+	pmu {
+		compatible = "arm,armv8-pmuv3";
+		interrupts = <GIC_PPI 7 IRQ_TYPE_LEVEL_LOW>;
+	};
+
+	psci {
+		compatible = "arm,psci-1.0";
+		method = "smc";
+
+		CPU_PD0: power-domain-cpu0 {
+			#power-domain-cells = <0>;
+			power-domains = <&CLUSTER_PD>;
+			domain-idle-states = <&SILVER_CPU_SLEEP_0>;
+		};
+
+		CPU_PD1: power-domain-cpu1 {
+			#power-domain-cells = <0>;
+			power-domains = <&CLUSTER_PD>;
+			domain-idle-states = <&SILVER_CPU_SLEEP_0>;
+		};
+
+		CPU_PD2: power-domain-cpu2 {
+			#power-domain-cells = <0>;
+			power-domains = <&CLUSTER_PD>;
+			domain-idle-states = <&SILVER_CPU_SLEEP_0>;
+		};
+
+		CPU_PD3: power-domain-cpu3 {
+			#power-domain-cells = <0>;
+			power-domains = <&CLUSTER_PD>;
+			domain-idle-states = <&GOLD_CPU_SLEEP_0>;
+		};
+
+		CPU_PD4: power-domain-cpu4 {
+			#power-domain-cells = <0>;
+			power-domains = <&CLUSTER_PD>;
+			domain-idle-states = <&GOLD_CPU_SLEEP_0>;
+		};
+
+		CPU_PD5: power-domain-cpu5 {
+			#power-domain-cells = <0>;
+			power-domains = <&CLUSTER_PD>;
+			domain-idle-states = <&GOLD_CPU_SLEEP_0>;
+		};
+
+		CPU_PD6: power-domain-cpu6 {
+			#power-domain-cells = <0>;
+			power-domains = <&CLUSTER_PD>;
+			domain-idle-states = <&GOLD_CPU_SLEEP_0>;
+		};
+
+		CPU_PD7: power-domain-cpu7 {
+			#power-domain-cells = <0>;
+			power-domains = <&CLUSTER_PD>;
+			domain-idle-states = <&GOLD_PLUS_CPU_SLEEP_0>;
+		};
+
+		CLUSTER_PD: power-domain-cluster {
+			#power-domain-cells = <0>;
+			domain-idle-states = <&CLUSTER_SLEEP_0>,
+					     <&CLUSTER_SLEEP_1>;
+		};
+	};
+
+	reserved_memory: reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		hyp_mem: hyp@80000000 {
+			reg = <0 0x80000000 0 0xe00000>;
+			no-map;
+		};
+
+		cpusys_vm_mem: cpusys-vm@80e00000 {
+			reg = <0 0x80e00000 0 0x400000>;
+			no-map;
+		};
+
+		/* Merged xbl_dtlog, xbl_ramdump and aop_image regions */
+		xbl_dt_log_merged_mem: xbl-dt-log-merged@81a00000 {
+			reg = <0 0x81a00000 0 0x260000>;
+			no-map;
+		};
+
+		aop_cmd_db_mem: aop-cmd-db@81c60000 {
+			compatible = "qcom,cmd-db";
+			reg = <0 0x81c60000 0 0x20000>;
+			no-map;
+		};
+
+		/* Merged aop_config, tme_crash_dump, tme_log and uefi_log regions */
+		aop_tme_uefi_merged_mem: aop-tme-uefi-merged@81c80000 {
+			reg = <0 0x81c80000 0 0x74000>;
+			no-map;
+		};
+
+		/* Secdata region can be reused by apps */
+
+		smem: smem@81d00000 {
+			compatible = "qcom,smem";
+			reg = <0 0x81d00000 0 0x200000>;
+			hwlocks = <&tcsr_mutex 3>;
+			no-map;
+		};
+
+		adsp_mhi_mem: adsp-mhi@81f00000 {
+			reg = <0 0x81f00000 0 0x20000>;
+			no-map;
+		};
+
+		pvmfw_mem: pvmfw@824a0000 {
+			reg = <0 0x824a0000 0 0x100000>;
+			no-map;
+		};
+
+		global_sync_mem: global-sync@82600000 {
+			reg = <0 0x82600000 0 0x100000>;
+			no-map;
+		};
+
+		tz_stat_mem: tz-stat@82700000 {
+			reg = <0 0x82700000 0 0x100000>;
+			no-map;
+		};
+
+		qdss_mem: qdss@82800000 {
+			reg = <0 0x82800000 0 0x2000000>;
+			no-map;
+		};
+
+		mpss_dsm_mem: mpss-dsm@86b00000 {
+			reg = <0 0x86b00000 0 0x4900000>;
+			no-map;
+		};
+
+		mpss_dsm_mem_2: mpss-dsm-2@8b400000 {
+			reg = <0 0x8b400000 0 0x800000>;
+			no-map;
+		};
+
+		mpss_mem: mpss@8bc00000 {
+			reg = <0 0x8bc00000 0 0xf400000>;
+			no-map;
+		};
+
+		q6_mpss_dtb_mem: q6-mpss-dtb@9b000000 {
+			reg = <0 0x9b000000 0 0x80000>;
+			no-map;
+		};
+
+		ipa_fw_mem: ipa-fw@9b080000 {
+			reg = <0 0x9b080000 0 0x10000>;
+			no-map;
+		};
+
+		ipa_gsi_mem: ipa-gsi@9b090000 {
+			reg = <0 0x9b090000 0 0xa000>;
+			no-map;
+		};
+
+		gpu_micro_code_mem: gpu-micro-code@9b09a000 {
+			reg = <0 0x9b09a000 0 0x2000>;
+			no-map;
+		};
+
+		spss_region_mem: spss@9b0a0000 {
+			reg = <0 0x9b0a0000 0 0x1e0000>;
+			no-map;
+		};
+
+		/* First part of the "SPU secure shared memory" region */
+		spu_tz_shared_mem: spu-tz-shared@9b280000 {
+			reg = <0 0x9b280000 0 0x60000>;
+			no-map;
+		};
+
+		/* Second part of the "SPU secure shared memory" region */
+		spu_modem_shared_mem: spu-modem-shared@9b2e0000 {
+			reg = <0 0x9b2e0000 0 0x20000>;
+			no-map;
+		};
+
+		camera_mem: camera@9b300000 {
+			reg = <0 0x9b300000 0 0x800000>;
+			no-map;
+		};
+
+		video_mem: video@9bb00000 {
+			reg = <0 0x9bb00000 0 0x800000>;
+			no-map;
+		};
+
+		cvp_mem: cvp@9c300000 {
+			reg = <0 0x9c300000 0 0x700000>;
+			no-map;
+		};
+
+		cdsp_mem: cdsp@9ca00000 {
+			reg = <0 0x9ca00000 0 0x1400000>;
+			no-map;
+		};
+
+		q6_cdsp_dtb_mem: q6-cdsp-dtb@9de00000 {
+			reg = <0 0x9de00000 0 0x80000>;
+			no-map;
+		};
+
+		q6_adsp_dtb_mem: q6-adsp-dtb@9de80000 {
+			reg = <0 0x9de80000 0 0x80000>;
+			no-map;
+		};
+
+		adspslpi_mem: adspslpi@9df00000 {
+			reg = <0 0x9df00000 0 0x4080000>;
+			no-map;
+		};
+
+		rmtfs_mem: rmtfs@d7c00000 {
+			compatible = "qcom,rmtfs-mem";
+			reg = <0 0xd7c00000 0 0x400000>;
+			no-map;
+
+			qcom,client-id = <1>;
+			qcom,vmid = <QCOM_SCM_VMID_MSS_MSA>;
+		};
+
+		/* Merged tz_reserved, xbl_sc, cpucp_fw and qtee regions */
+		tz_merged_mem: tz-merged@d8000000 {
+			reg = <0 0xd8000000 0 0x800000>;
+			no-map;
+		};
+
+		hwfence_shbuf: hwfence-shbuf@e6440000 {
+			reg = <0 0xe6440000 0 0x2dd000>;
+			no-map;
+		};
+
+		trust_ui_vm_mem: trust-ui-vm@f3800000 {
+			reg = <0 0xf3800000 0 0x4400000>;
+			no-map;
+		};
+
+		oem_vm_mem: oem-vm@f7c00000 {
+			reg = <0 0xf7c00000 0 0x4c00000>;
+			no-map;
+		};
+
+		llcc_lpi_mem: llcc-lpi@ff800000 {
+			reg = <0 0xff800000 0 0x600000>;
+			no-map;
+		};
+	};
+
+	smp2p-adsp {
+		compatible = "qcom,smp2p";
+
+		interrupts-extended = <&ipcc IPCC_CLIENT_LPASS
+					     IPCC_MPROC_SIGNAL_SMP2P
+					     IRQ_TYPE_EDGE_RISING>;
+
+		mboxes = <&ipcc IPCC_CLIENT_LPASS
+				IPCC_MPROC_SIGNAL_SMP2P>;
+
+		qcom,smem = <443>, <429>;
+		qcom,local-pid = <0>;
+		qcom,remote-pid = <2>;
+
+		smp2p_adsp_out: master-kernel {
+			qcom,entry-name = "master-kernel";
+			#qcom,smem-state-cells = <1>;
+		};
+
+		smp2p_adsp_in: slave-kernel {
+			qcom,entry-name = "slave-kernel";
+			interrupt-controller;
+			#interrupt-cells = <2>;
+		};
+	};
+
+	smp2p-cdsp {
+		compatible = "qcom,smp2p";
+
+		interrupts-extended = <&ipcc IPCC_CLIENT_CDSP
+					     IPCC_MPROC_SIGNAL_SMP2P
+					     IRQ_TYPE_EDGE_RISING>;
+
+		mboxes = <&ipcc IPCC_CLIENT_CDSP
+				IPCC_MPROC_SIGNAL_SMP2P>;
+
+		qcom,smem = <94>, <432>;
+		qcom,local-pid = <0>;
+		qcom,remote-pid = <5>;
+
+		smp2p_cdsp_out: master-kernel {
+			qcom,entry-name = "master-kernel";
+			#qcom,smem-state-cells = <1>;
+		};
+
+		smp2p_cdsp_in: slave-kernel {
+			qcom,entry-name = "slave-kernel";
+			interrupt-controller;
+			#interrupt-cells = <2>;
+		};
+	};
+
+	smp2p-modem {
+		compatible = "qcom,smp2p";
+
+		interrupts-extended = <&ipcc IPCC_CLIENT_MPSS
+					     IPCC_MPROC_SIGNAL_SMP2P
+					     IRQ_TYPE_EDGE_RISING>;
+
+		mboxes = <&ipcc IPCC_CLIENT_MPSS
+				IPCC_MPROC_SIGNAL_SMP2P>;
+
+		qcom,smem = <435>, <428>;
+		qcom,local-pid = <0>;
+		qcom,remote-pid = <1>;
+
+		smp2p_modem_out: master-kernel {
+			qcom,entry-name = "master-kernel";
+			#qcom,smem-state-cells = <1>;
+		};
+
+		smp2p_modem_in: slave-kernel {
+			qcom,entry-name = "slave-kernel";
+			interrupt-controller;
+			#interrupt-cells = <2>;
+		};
+
+		ipa_smp2p_out: ipa-ap-to-modem {
+			qcom,entry-name = "ipa";
+			#qcom,smem-state-cells = <1>;
+		};
+
+		ipa_smp2p_in: ipa-modem-to-ap {
+			qcom,entry-name = "ipa";
+			interrupt-controller;
+			#interrupt-cells = <2>;
+		};
+	};
+
+	soc: soc@0 {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <2>;
+		dma-ranges = <0 0 0 0 0x10 0>;
+		ranges = <0 0 0 0 0x10 0>;
+
+		gcc: clock-controller@100000 {
+			compatible = "qcom,sm8650-gcc";
+			reg = <0 0x00100000 0 0x1f4200>;
+
+			clocks = <&bi_tcxo_div2>,
+				 <&bi_tcxo_ao_div2>,
+				 <&sleep_clk>,
+				 <&pcie0_phy>,
+				 <&pcie1_phy>,
+				 <&pcie_1_phy_aux_clk>,
+				 <&ufs_mem_phy 0>,
+				 <&ufs_mem_phy 1>,
+				 <&ufs_mem_phy 2>,
+				 <&usb_dp_qmpphy QMP_USB43DP_USB3_PIPE_CLK>;
+
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+			#power-domain-cells = <1>;
+		};
+
+		ipcc: mailbox@406000 {
+			compatible = "qcom,sm8650-ipcc", "qcom,ipcc";
+			reg = <0 0x00406000 0 0x1000>;
+
+			interrupts = <GIC_SPI 229 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-controller;
+			#interrupt-cells = <3>;
+
+			#mbox-cells = <2>;
+		};
+
+		gpi_dma2: dma-controller@800000 {
+			compatible = "qcom,sm8650-gpi-dma", "qcom,sm6350-gpi-dma";
+			reg = <0 0x00800000 0 0x60000>;
+
+			interrupts = <GIC_SPI 588 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 589 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 590 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 591 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 592 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 593 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 594 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 595 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 596 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 597 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 598 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 599 IRQ_TYPE_LEVEL_HIGH>;
+
+			dma-channels = <12>;
+			dma-channel-mask = <0x3f>;
+			#dma-cells = <3>;
+
+			iommus = <&apps_smmu 0x436 0>;
+
+			dma-coherent;
+
+			status = "disabled";
+		};
+
+		qupv3_id_1: geniqup@8c0000 {
+			compatible = "qcom,geni-se-qup";
+			reg = <0 0x008c0000 0 0x2000>;
+
+			clocks = <&gcc GCC_QUPV3_WRAP_2_M_AHB_CLK>,
+				 <&gcc GCC_QUPV3_WRAP_2_S_AHB_CLK>;
+			clock-names = "m-ahb",
+				      "s-ahb";
+
+			iommus = <&apps_smmu 0x423 0>;
+
+			dma-coherent;
+
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+
+			status = "disabled";
+
+			i2c8: i2c@880000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00880000 0 0x4000>;
+
+				interrupts = <GIC_SPI 373 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S0_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 0 QCOM_GPI_I2C>,
+				       <&gpi_dma2 1 0 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c8_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi8: spi@880000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00880000 0 0x4000>;
+
+				interrupts = <GIC_SPI 373 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S0_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 0 QCOM_GPI_SPI>,
+				       <&gpi_dma2 1 0 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi8_data_clk>, <&qup_spi8_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c9: i2c@884000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00884000 0 0x4000>;
+
+				interrupts = <GIC_SPI 583 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S1_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 1 QCOM_GPI_I2C>,
+				       <&gpi_dma2 1 1 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c9_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi9: spi@884000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00884000 0 0x4000>;
+
+				interrupts = <GIC_SPI 583 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S1_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 1 QCOM_GPI_SPI>,
+				       <&gpi_dma2 1 1 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi9_data_clk>, <&qup_spi9_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c10: i2c@888000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00888000 0 0x4000>;
+
+				interrupts = <GIC_SPI 584 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S2_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 2 QCOM_GPI_I2C>,
+				       <&gpi_dma2 1 2 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c10_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi10: spi@888000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00888000 0 0x4000>;
+
+				interrupts = <GIC_SPI 584 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S2_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 2 QCOM_GPI_SPI>,
+				       <&gpi_dma2 1 2 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi10_data_clk>, <&qup_spi10_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c11: i2c@88c000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x0088c000 0 0x4000>;
+
+				interrupts = <GIC_SPI 585 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S3_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 3 QCOM_GPI_I2C>,
+				       <&gpi_dma2 1 3 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c11_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi11: spi@88c000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x0088c000 0 0x4000>;
+
+				interrupts = <GIC_SPI 585 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S3_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 3 QCOM_GPI_SPI>,
+				       <&gpi_dma2 1 3 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi11_data_clk>, <&qup_spi11_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c12: i2c@890000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00890000 0 0x4000>;
+
+				interrupts = <GIC_SPI 586 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S4_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 4 QCOM_GPI_I2C>,
+				       <&gpi_dma2 1 4 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c12_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi12: spi@890000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00890000 0 0x4000>;
+
+				interrupts = <GIC_SPI 586 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S4_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 4 QCOM_GPI_SPI>,
+				       <&gpi_dma2 1 4 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi12_data_clk>, <&qup_spi12_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c13: i2c@894000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00894000 0 0x4000>;
+
+				interrupts = <GIC_SPI 587 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S5_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 5 QCOM_GPI_I2C>,
+				       <&gpi_dma2 1 5 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c13_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi13: spi@894000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00894000 0 0x4000>;
+
+				interrupts = <GIC_SPI 587 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S5_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 5 QCOM_GPI_SPI>,
+				       <&gpi_dma2 1 5 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi13_data_clk>, <&qup_spi13_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			uart14: serial@898000 {
+				compatible = "qcom,geni-uart";
+				reg = <0 0x00898000 0 0x4000>;
+
+				interrupts = <GIC_SPI 461 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S6_CLK>;
+				clock-names = "se";
+
+				interconnects =	<&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config";
+
+				pinctrl-0 = <&qup_uart14_default>, <&qup_uart14_cts_rts>;
+				pinctrl-names = "default";
+
+				status = "disabled";
+			};
+
+			uart15: serial@89c000 {
+				compatible = "qcom,geni-debug-uart";
+				reg = <0 0x0089c000 0 0x4000>;
+
+				interrupts = <GIC_SPI 462 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S7_CLK>;
+				clock-names = "se";
+
+				interconnects =	<&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config";
+
+				pinctrl-0 = <&qup_uart15_default>;
+				pinctrl-names = "default";
+
+				status = "disabled";
+			};
+		};
+
+		i2c_master_hub_0: geniqup@9c0000 {
+			compatible = "qcom,geni-se-i2c-master-hub";
+			reg = <0 0x009c0000 0 0x2000>;
+
+			clocks = <&gcc GCC_QUPV3_I2C_S_AHB_CLK>;
+			clock-names = "s-ahb";
+
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+
+			status = "disabled";
+
+			i2c_hub_0: i2c@980000 {
+				compatible = "qcom,geni-i2c-master-hub";
+				reg = <0 0x00980000 0 0x4000>;
+
+				interrupts = <GIC_SPI 464 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_I2C_S0_CLK>,
+					 <&gcc GCC_QUPV3_I2C_CORE_CLK>;
+				clock-names = "se",
+					      "core";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_I2C QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config";
+
+				pinctrl-0 = <&hub_i2c0_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c_hub_1: i2c@984000 {
+				compatible = "qcom,geni-i2c-master-hub";
+				reg = <0 0x00984000 0 0x4000>;
+
+				interrupts = <GIC_SPI 465 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_I2C_S1_CLK>,
+					 <&gcc GCC_QUPV3_I2C_CORE_CLK>;
+				clock-names = "se",
+					      "core";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_I2C QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config";
+
+				pinctrl-0 = <&hub_i2c1_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c_hub_2: i2c@988000 {
+				compatible = "qcom,geni-i2c-master-hub";
+				reg = <0 0x00988000 0 0x4000>;
+
+				interrupts = <GIC_SPI 466 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_I2C_S2_CLK>,
+					 <&gcc GCC_QUPV3_I2C_CORE_CLK>;
+				clock-names = "se",
+					      "core";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_I2C QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config";
+
+				pinctrl-0 = <&hub_i2c2_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c_hub_3: i2c@98c000 {
+				compatible = "qcom,geni-i2c-master-hub";
+				reg = <0 0x0098c000 0 0x4000>;
+
+				interrupts = <GIC_SPI 467 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_I2C_S3_CLK>,
+					 <&gcc GCC_QUPV3_I2C_CORE_CLK>;
+				clock-names = "se",
+					      "core";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_I2C QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config";
+
+				pinctrl-0 = <&hub_i2c3_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c_hub_4: i2c@990000 {
+				compatible = "qcom,geni-i2c-master-hub";
+				reg = <0 0x00990000 0 0x4000>;
+
+				interrupts = <GIC_SPI 468 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_I2C_S4_CLK>,
+					 <&gcc GCC_QUPV3_I2C_CORE_CLK>;
+				clock-names = "se",
+					      "core";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_I2C QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config";
+
+				pinctrl-0 = <&hub_i2c4_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c_hub_5: i2c@994000 {
+				compatible = "qcom,geni-i2c-master-hub";
+				reg = <0 0x00994000 0 0x4000>;
+
+				interrupts = <GIC_SPI 469 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_I2C_S5_CLK>,
+					 <&gcc GCC_QUPV3_I2C_CORE_CLK>;
+				clock-names = "se",
+					      "core";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_I2C QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config";
+
+				pinctrl-0 = <&hub_i2c5_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c_hub_6: i2c@998000 {
+				compatible = "qcom,geni-i2c-master-hub";
+				reg = <0 0x00998000 0 0x4000>;
+
+				interrupts = <GIC_SPI 470 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_I2C_S6_CLK>,
+					 <&gcc GCC_QUPV3_I2C_CORE_CLK>;
+				clock-names = "se",
+					      "core";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_I2C QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config";
+
+				pinctrl-0 = <&hub_i2c6_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c_hub_7: i2c@99c000 {
+				compatible = "qcom,geni-i2c-master-hub";
+				reg = <0 0x0099c000 0 0x4000>;
+
+				interrupts = <GIC_SPI 471 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_I2C_S7_CLK>,
+					 <&gcc GCC_QUPV3_I2C_CORE_CLK>;
+				clock-names = "se",
+					      "core";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_I2C QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config";
+
+				pinctrl-0 = <&hub_i2c7_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c_hub_8: i2c@9a0000 {
+				compatible = "qcom,geni-i2c-master-hub";
+				reg = <0 0x009a0000 0 0x4000>;
+
+				interrupts = <GIC_SPI 472 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_I2C_S8_CLK>,
+					 <&gcc GCC_QUPV3_I2C_CORE_CLK>;
+				clock-names = "se",
+					      "core";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_I2C QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config";
+
+				pinctrl-0 = <&hub_i2c8_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c_hub_9: i2c@9a4000 {
+				compatible = "qcom,geni-i2c-master-hub";
+				reg = <0 0x009a4000 0 0x4000>;
+
+				interrupts = <GIC_SPI 473 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_I2C_S9_CLK>,
+					 <&gcc GCC_QUPV3_I2C_CORE_CLK>;
+				clock-names = "se",
+					      "core";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_I2C QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config";
+
+				pinctrl-0 = <&hub_i2c9_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+		};
+
+		gpi_dma1: dma-controller@a00000 {
+			compatible = "qcom,sm8650-gpi-dma", "qcom,sm6350-gpi-dma";
+			reg = <0 0x00a00000 0 0x60000>;
+
+			interrupts = <GIC_SPI 279 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 280 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 281 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 282 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 283 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 284 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 293 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 294 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 295 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 296 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 297 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 298 IRQ_TYPE_LEVEL_HIGH>;
+
+			dma-channels = <12>;
+			dma-channel-mask = <0xc>;
+			#dma-cells = <3>;
+
+			iommus = <&apps_smmu 0xb6 0>;
+			dma-coherent;
+
+			status = "disabled";
+		};
+
+		qupv3_id_0: geniqup@ac0000 {
+			compatible = "qcom,geni-se-qup";
+			reg = <0 0x00ac0000 0 0x2000>;
+
+			clocks = <&gcc GCC_QUPV3_WRAP_1_M_AHB_CLK>,
+				 <&gcc GCC_QUPV3_WRAP_1_S_AHB_CLK>;
+			clock-names = "m-ahb",
+				      "s-ahb";
+
+			interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+					 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>;
+			interconnect-names = "qup-core";
+
+			iommus = <&apps_smmu 0xa3 0>;
+
+			dma-coherent;
+
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+
+			status = "disabled";
+
+			i2c0: i2c@a80000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00a80000 0 0x4000>;
+
+				interrupts = <GIC_SPI 353 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S0_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 0 QCOM_GPI_I2C>,
+				       <&gpi_dma1 1 0 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c0_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi0: spi@a80000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00a80000 0 0x4000>;
+
+				interrupts = <GIC_SPI 353 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S0_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 0 QCOM_GPI_SPI>,
+				       <&gpi_dma1 1 0 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi0_data_clk>, <&qup_spi0_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c1: i2c@a84000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00a84000 0 0x4000>;
+
+				interrupts = <GIC_SPI 354 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S1_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 1 QCOM_GPI_I2C>,
+				       <&gpi_dma1 1 1 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c1_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi1: spi@a84000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00a84000 0 0x4000>;
+
+				interrupts = <GIC_SPI 354 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S1_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 1 QCOM_GPI_SPI>,
+				       <&gpi_dma1 1 1 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi1_data_clk>, <&qup_spi1_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c2: i2c@a88000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00a88000 0 0x4000>;
+
+				interrupts = <GIC_SPI 355 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S2_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 2 QCOM_GPI_I2C>,
+				       <&gpi_dma1 1 2 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c2_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi2: spi@a88000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00a88000 0 0x4000>;
+
+				interrupts = <GIC_SPI 355 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S2_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 2 QCOM_GPI_SPI>,
+				       <&gpi_dma1 1 2 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi2_data_clk>, <&qup_spi2_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c3: i2c@a8c000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00a8c000 0 0x4000>;
+
+				interrupts = <GIC_SPI 356 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S3_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 3 QCOM_GPI_I2C>,
+				       <&gpi_dma1 1 3 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c3_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi3: spi@a8c000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00a8c000 0 0x4000>;
+
+				interrupts = <GIC_SPI 356 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S3_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 3 QCOM_GPI_SPI>,
+				       <&gpi_dma1 1 3 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi3_data_clk>, <&qup_spi3_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c4: i2c@a90000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00a90000 0 0x4000>;
+
+				interrupts = <GIC_SPI 357 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S4_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 4 QCOM_GPI_I2C>,
+				       <&gpi_dma1 1 4 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c4_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi4: spi@a90000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00a90000 0 0x4000>;
+
+				interrupts = <GIC_SPI 357 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S4_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 4 QCOM_GPI_SPI>,
+				       <&gpi_dma1 1 4 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi4_data_clk>, <&qup_spi4_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c5: i2c@a94000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00a94000 0 0x4000>;
+
+				interrupts = <GIC_SPI 358 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S5_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 5 QCOM_GPI_I2C>,
+				       <&gpi_dma1 1 5 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c5_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi5: spi@a94000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00a94000 0 0x4000>;
+
+				interrupts = <GIC_SPI 358 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S5_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 5 QCOM_GPI_SPI>,
+				       <&gpi_dma1 1 5 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi5_data_clk>, <&qup_spi5_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c6: i2c@a98000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00a98000 0 0x4000>;
+
+				interrupts = <GIC_SPI 363 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S6_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 6 QCOM_GPI_I2C>,
+				       <&gpi_dma1 1 6 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c6_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi6: spi@a98000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00a98000 0 0x4000>;
+
+				interrupts = <GIC_SPI 363 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S6_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 6 QCOM_GPI_SPI>,
+				       <&gpi_dma1 1 6 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi6_data_clk>, <&qup_spi6_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c7: i2c@a9c000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00a9c000 0 0x4000>;
+
+				interrupts = <GIC_SPI 579 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S7_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 7 QCOM_GPI_I2C>,
+				       <&gpi_dma1 1 7 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c7_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi7: spi@a9c000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00a9c000 0 0x4000>;
+
+				interrupts = <GIC_SPI 579 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S7_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt  SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 7 QCOM_GPI_SPI>,
+				       <&gpi_dma1 1 7 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi7_data_clk>, <&qup_spi7_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+		};
+
+		cnoc_main: interconnect@1500000 {
+			compatible = "qcom,sm8650-cnoc-main";
+			reg = <0 0x01500000 0 0x14080>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		config_noc: interconnect@1600000 {
+			compatible = "qcom,sm8650-config-noc";
+			reg = <0 0x01600000 0 0x6200>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		system_noc: interconnect@1680000 {
+			compatible = "qcom,sm8650-system-noc";
+			reg = <0 0x01680000 0 0x1d080>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		pcie_noc: interconnect@16c0000 {
+			compatible = "qcom,sm8650-pcie-anoc";
+			reg = <0 0x016c0000 0 0x12200>;
+
+			clocks = <&gcc GCC_AGGRE_NOC_PCIE_AXI_CLK>,
+				 <&gcc GCC_CFG_NOC_PCIE_ANOC_AHB_CLK>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		aggre1_noc: interconnect@16e0000 {
+			compatible = "qcom,sm8650-aggre1-noc";
+			reg = <0 0x016e0000 0 0x16400>;
+
+			clocks = <&gcc GCC_AGGRE_UFS_PHY_AXI_CLK>,
+				 <&gcc GCC_AGGRE_USB3_PRIM_AXI_CLK>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		aggre2_noc: interconnect@1700000 {
+			compatible = "qcom,sm8650-aggre2-noc";
+			reg = <0 0x01700000 0 0x1e400>;
+
+			clocks = <&rpmhcc RPMH_IPA_CLK>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		mmss_noc: interconnect@1780000 {
+			compatible = "qcom,sm8650-mmss-noc";
+			reg = <0 0x01780000 0 0x5b800>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		rng: rng@10c3000 {
+			compatible = "qcom,sm8650-trng", "qcom,trng";
+			reg = <0 0x010c3000 0 0x1000>;
+		};
+
+		pcie0: pci@1c00000 {
+			device_type = "pci";
+			compatible = "qcom,pcie-sm8650", "qcom,pcie-sm8550";
+			reg = <0 0x01c00000 0 0x3000>,
+			      <0 0x60000000 0 0xf1d>,
+			      <0 0x60000f20 0 0xa8>,
+			      <0 0x60001000 0 0x1000>,
+			      <0 0x60100000 0 0x100000>;
+			reg-names = "parf", "dbi", "elbi", "atu", "config";
+
+			interrupts = <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "msi";
+
+			clocks = <&gcc GCC_PCIE_0_AUX_CLK>,
+				 <&gcc GCC_PCIE_0_CFG_AHB_CLK>,
+				 <&gcc GCC_PCIE_0_MSTR_AXI_CLK>,
+				 <&gcc GCC_PCIE_0_SLV_AXI_CLK>,
+				 <&gcc GCC_PCIE_0_SLV_Q2A_AXI_CLK>,
+				 <&gcc GCC_DDRSS_PCIE_SF_QTB_CLK>,
+				 <&gcc GCC_AGGRE_NOC_PCIE_AXI_CLK>,
+				 <&gcc GCC_CNOC_PCIE_SF_AXI_CLK>;
+			clock-names = "aux",
+				      "cfg",
+				      "bus_master",
+				      "bus_slave",
+				      "slave_q2a",
+				      "ddrss_sf_tbu",
+				      "noc_aggr",
+				      "cnoc_sf_axi";
+
+			resets = <&gcc GCC_PCIE_0_BCR>;
+			reset-names = "pci";
+
+			interconnects = <&pcie_noc MASTER_PCIE_0 QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
+					<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+					 &cnoc_main SLAVE_PCIE_0 QCOM_ICC_TAG_ALWAYS>;
+			interconnect-names = "pcie-mem",
+					     "cpu-pcie";
+
+			power-domains = <&gcc PCIE_0_GDSC>;
+
+			iommu-map = <0     &apps_smmu 0x1400 0x1>,
+				    <0x100 &apps_smmu 0x1401 0x1>;
+
+			interrupt-map = <0 0 0 1 &intc 0 0 0 149 IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 2 &intc 0 0 0 150 IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 3 &intc 0 0 0 151 IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 4 &intc 0 0 0 152 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-map-mask = <0 0 0 0x7>;
+			#interrupt-cells = <1>;
+
+			linux,pci-domain = <0>;
+			num-lanes = <2>;
+			bus-range = <0 0xff>;
+
+			phys = <&pcie0_phy>;
+			phy-names = "pciephy";
+
+			#address-cells = <3>;
+			#size-cells = <2>;
+			ranges = <0x01000000 0 0x00000000 0 0x60200000 0 0x100000>,
+				 <0x02000000 0 0x60300000 0 0x60300000 0 0x3d00000>;
+
+			dma-coherent;
+
+			status = "disabled";
+		};
+
+		pcie0_phy: phy@1c06000 {
+			compatible = "qcom,sm8650-qmp-gen3x2-pcie-phy";
+			reg = <0 0x01c06000 0 0x2000>;
+
+			clocks = <&gcc GCC_PCIE_0_AUX_CLK>,
+				 <&gcc GCC_PCIE_0_CFG_AHB_CLK>,
+				 <&tcsr TCSR_PCIE_0_CLKREF_EN>,
+				 <&gcc GCC_PCIE_0_PHY_RCHNG_CLK>,
+				 <&gcc GCC_PCIE_0_PIPE_CLK>;
+			clock-names = "aux",
+				      "cfg_ahb",
+				      "ref",
+				      "rchng",
+				      "pipe";
+
+			assigned-clocks = <&gcc GCC_PCIE_0_PHY_RCHNG_CLK>;
+			assigned-clock-rates = <100000000>;
+
+			resets = <&gcc GCC_PCIE_0_PHY_BCR>;
+			reset-names = "phy";
+
+			power-domains = <&gcc PCIE_0_PHY_GDSC>;
+
+			#clock-cells = <0>;
+			clock-output-names = "pcie0_pipe_clk";
+
+			#phy-cells = <0>;
+
+			status = "disabled";
+		};
+
+		pcie1: pci@1c08000 {
+			device_type = "pci";
+			compatible = "qcom,pcie-sm8650", "qcom,pcie-sm8550";
+			reg = <0 0x01c08000 0 0x3000>,
+			      <0 0x40000000 0 0xf1d>,
+			      <0 0x40000f20 0 0xa8>,
+			      <0 0x40001000 0 0x1000>,
+			      <0 0x40100000 0 0x100000>;
+			reg-names = "parf",
+				    "dbi",
+				    "elbi",
+				    "atu",
+				    "config";
+
+			interrupts = <GIC_SPI 307 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "msi";
+
+			clocks = <&gcc GCC_PCIE_1_AUX_CLK>,
+				 <&gcc GCC_PCIE_1_CFG_AHB_CLK>,
+				 <&gcc GCC_PCIE_1_MSTR_AXI_CLK>,
+				 <&gcc GCC_PCIE_1_SLV_AXI_CLK>,
+				 <&gcc GCC_PCIE_1_SLV_Q2A_AXI_CLK>,
+				 <&gcc GCC_DDRSS_PCIE_SF_QTB_CLK>,
+				 <&gcc GCC_AGGRE_NOC_PCIE_AXI_CLK>,
+				 <&gcc GCC_CNOC_PCIE_SF_AXI_CLK>;
+			clock-names = "aux",
+				      "cfg",
+				      "bus_master",
+				      "bus_slave",
+				      "slave_q2a",
+				      "ddrss_sf_tbu",
+				      "noc_aggr",
+				      "cnoc_sf_axi";
+
+			assigned-clocks = <&gcc GCC_PCIE_1_AUX_CLK>;
+			assigned-clock-rates = <19200000>;
+
+			resets = <&gcc GCC_PCIE_1_BCR>,
+				 <&gcc GCC_PCIE_1_LINK_DOWN_BCR>;
+			reset-names = "pci",
+				      "link_down";
+
+			interconnects = <&pcie_noc MASTER_PCIE_1 QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
+					<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+					 &cnoc_main SLAVE_PCIE_1 QCOM_ICC_TAG_ALWAYS>;
+			interconnect-names = "pcie-mem",
+					     "cpu-pcie";
+
+			power-domains = <&gcc PCIE_1_GDSC>;
+
+			iommu-map = <0     &apps_smmu 0x1480 0x1>,
+				    <0x100 &apps_smmu 0x1481 0x1>;
+
+			interrupt-map = <0 0 0 1 &intc 0 0 0 434 IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 2 &intc 0 0 0 435 IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 3 &intc 0 0 0 438 IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 4 &intc 0 0 0 439 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-map-mask = <0 0 0 0x7>;
+			#interrupt-cells = <1>;
+
+			linux,pci-domain = <1>;
+			num-lanes = <2>;
+			bus-range = <0 0xff>;
+
+			phys = <&pcie1_phy>;
+			phy-names = "pciephy";
+
+			dma-coherent;
+
+			#address-cells = <3>;
+			#size-cells = <2>;
+			ranges = <0x01000000 0 0x00000000 0 0x40200000 0 0x100000>,
+				 <0x02000000 0 0x40300000 0 0x40300000 0 0x1fd00000>;
+
+			status = "disabled";
+		};
+
+		pcie1_phy: phy@1c0e000 {
+			compatible = "qcom,sm8650-qmp-gen4x2-pcie-phy";
+			reg = <0 0x01c0e000 0 0x2000>;
+
+			clocks = <&gcc GCC_PCIE_1_PHY_AUX_CLK>,
+				 <&gcc GCC_PCIE_1_CFG_AHB_CLK>,
+				 <&tcsr TCSR_PCIE_1_CLKREF_EN>,
+				 <&gcc GCC_PCIE_1_PHY_RCHNG_CLK>,
+				 <&gcc GCC_PCIE_1_PIPE_CLK>;
+			clock-names = "aux",
+				      "cfg_ahb",
+				      "ref",
+				      "rchng",
+				      "pipe";
+
+			assigned-clocks = <&gcc GCC_PCIE_1_PHY_RCHNG_CLK>;
+			assigned-clock-rates = <100000000>;
+
+			resets = <&gcc GCC_PCIE_1_PHY_BCR>,
+				 <&gcc GCC_PCIE_1_NOCSR_COM_PHY_BCR>;
+			reset-names = "phy",
+				      "phy_nocsr";
+
+			power-domains = <&gcc PCIE_1_PHY_GDSC>;
+
+			#clock-cells = <0>;
+			clock-output-names = "pcie1_pipe_clk";
+
+			#phy-cells = <0>;
+
+			status = "disabled";
+		};
+
+		cryptobam: dma-controller@1dc4000 {
+			compatible = "qcom,bam-v1.7.0";
+			reg = <0 0x01dc4000 0 0x28000>;
+
+			interrupts = <GIC_SPI 272 IRQ_TYPE_LEVEL_HIGH>;
+
+			#dma-cells = <1>;
+
+			iommus = <&apps_smmu 0x480 0>,
+				 <&apps_smmu 0x481 0>;
+
+			qcom,ee = <0>;
+			qcom,controlled-remotely;
+		};
+
+		crypto: crypto@1dfa000 {
+			compatible = "qcom,sm8650-qce", "qcom,sm8150-qce", "qcom,qce";
+			reg = <0 0x01dfa000 0 0x6000>;
+
+			interconnects = <&aggre2_noc MASTER_CRYPTO QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+			interconnect-names = "memory";
+
+			dmas = <&cryptobam 4>, <&cryptobam 5>;
+			dma-names = "rx", "tx";
+
+			iommus = <&apps_smmu 0x480 0>,
+				 <&apps_smmu 0x481 0>;
+		};
+
+		ufs_mem_phy: phy@1d80000 {
+			compatible = "qcom,sm8650-qmp-ufs-phy";
+			reg = <0 0x01d80000 0 0x2000>;
+
+			clocks = <&tcsr TCSR_UFS_CLKREF_EN>,
+				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>;
+			clock-names = "ref",
+				      "ref_aux";
+
+			resets = <&ufs_mem_hc 0>;
+			reset-names = "ufsphy";
+
+			power-domains = <&gcc UFS_MEM_PHY_GDSC>;
+
+			#clock-cells = <1>;
+			#phy-cells = <0>;
+
+			status = "disabled";
+		};
+
+		ufs_mem_hc: ufs@1d84000 {
+			compatible = "qcom,sm8650-ufshc", "qcom,ufshc", "jedec,ufs-2.0";
+			reg = <0 0x01d84000 0 0x3000>;
+
+			interrupts = <GIC_SPI 265 IRQ_TYPE_LEVEL_HIGH>;
+
+			clocks = <&gcc GCC_UFS_PHY_AXI_CLK>,
+				 <&gcc GCC_AGGRE_UFS_PHY_AXI_CLK>,
+				 <&gcc GCC_UFS_PHY_AHB_CLK>,
+				 <&gcc GCC_UFS_PHY_UNIPRO_CORE_CLK>,
+				 <&tcsr TCSR_UFS_PAD_CLKREF_EN>,
+				 <&gcc GCC_UFS_PHY_TX_SYMBOL_0_CLK>,
+				 <&gcc GCC_UFS_PHY_RX_SYMBOL_0_CLK>,
+				 <&gcc GCC_UFS_PHY_RX_SYMBOL_1_CLK>;
+			clock-names = "core_clk",
+				      "bus_aggr_clk",
+				      "iface_clk",
+				      "core_clk_unipro",
+				      "ref_clk",
+				      "tx_lane0_sync_clk",
+				      "rx_lane0_sync_clk",
+				      "rx_lane1_sync_clk";
+			freq-table-hz = <100000000 403000000>,
+					<0 0>,
+					<0 0>,
+					<100000000 403000000>,
+					<100000000 403000000>,
+					<0 0>,
+					<0 0>,
+					<0 0>;
+
+			resets = <&gcc GCC_UFS_PHY_BCR>;
+			reset-names = "rst";
+
+			interconnects = <&aggre1_noc MASTER_UFS_MEM QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
+					<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+					 &config_noc SLAVE_UFS_MEM_CFG QCOM_ICC_TAG_ALWAYS>;
+			interconnect-names = "ufs-ddr",
+					     "cpu-ufs";
+
+			power-domains = <&gcc UFS_PHY_GDSC>;
+			required-opps = <&rpmhpd_opp_nom>;
+
+			iommus = <&apps_smmu 0x60 0>;
+
+			lanes-per-direction = <2>;
+			qcom,ice = <&ice>;
+
+			phys = <&ufs_mem_phy>;
+			phy-names = "ufsphy";
+
+			#reset-cells = <1>;
+
+			status = "disabled";
+		};
+
+		ice: crypto@1d88000 {
+			compatible = "qcom,sm8650-inline-crypto-engine",
+				     "qcom,inline-crypto-engine";
+			reg = <0 0x01d88000 0 0x8000>;
+
+			clocks = <&gcc GCC_UFS_PHY_ICE_CORE_CLK>;
+		};
+
+		tcsr_mutex: hwlock@1f40000 {
+			compatible = "qcom,tcsr-mutex";
+			reg = <0 0x01f40000 0 0x20000>;
+
+			#hwlock-cells = <1>;
+		};
+
+		tcsr: clock-controller@1fc0000 {
+			compatible = "qcom,sm8650-tcsr", "syscon";
+			reg = <0 0x01fc0000 0 0xa0000>;
+
+			clocks = <&rpmhcc RPMH_CXO_CLK>;
+
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+		};
+
+		gpucc: clock-controller@3d90000 {
+			compatible = "qcom,sm8650-gpucc";
+			reg = <0 0x03d90000 0 0xa000>;
+
+			clocks = <&bi_tcxo_div2>,
+				 <&gcc GCC_GPU_GPLL0_CLK_SRC>,
+				 <&gcc GCC_GPU_GPLL0_DIV_CLK_SRC>;
+
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+			#power-domain-cells = <1>;
+		};
+
+		ipa: ipa@3f40000 {
+			compatible = "qcom,sm8650-ipa", "qcom,sm8550-ipa";
+
+			iommus = <&apps_smmu 0x4a0 0x0>,
+				 <&apps_smmu 0x4a2 0x0>;
+			reg = <0 0x3f40000 0 0x10000>,
+			      <0 0x3f50000 0 0x5000>,
+			      <0 0x3e04000 0 0xfc000>;
+			reg-names = "ipa-reg",
+				    "ipa-shared",
+				    "gsi";
+
+			interrupts-extended = <&intc GIC_SPI 654 IRQ_TYPE_EDGE_RISING>,
+					      <&intc GIC_SPI 432 IRQ_TYPE_LEVEL_HIGH>,
+					      <&ipa_smp2p_in 0 IRQ_TYPE_EDGE_RISING>,
+					      <&ipa_smp2p_in 1 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "ipa",
+					  "gsi",
+					  "ipa-clock-query",
+					  "ipa-setup-ready";
+
+			clocks = <&rpmhcc RPMH_IPA_CLK>;
+			clock-names = "core";
+
+			interconnects = <&aggre2_noc MASTER_IPA 0 &mc_virt SLAVE_EBI1 0>,
+					<&gem_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_IPA_CFG 0>;
+			interconnect-names = "memory",
+					     "config";
+
+			qcom,qmp = <&aoss_qmp>;
+
+			qcom,smem-states = <&ipa_smp2p_out 0>,
+					   <&ipa_smp2p_out 1>;
+			qcom,smem-state-names = "ipa-clock-enabled-valid",
+						"ipa-clock-enabled";
+
+			status = "disabled";
+		};
+
+		remoteproc_mpss: remoteproc@4080000 {
+			compatible = "qcom,sm8650-mpss-pas";
+			reg = <0 0x04080000 0 0x4040>;
+
+			interrupts-extended = <&intc GIC_SPI 264 IRQ_TYPE_EDGE_RISING>,
+					      <&smp2p_modem_in 0 IRQ_TYPE_EDGE_RISING>,
+					      <&smp2p_modem_in 1 IRQ_TYPE_EDGE_RISING>,
+					      <&smp2p_modem_in 2 IRQ_TYPE_EDGE_RISING>,
+					      <&smp2p_modem_in 3 IRQ_TYPE_EDGE_RISING>,
+					      <&smp2p_modem_in 7 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "wdog",
+					  "fatal",
+					  "ready",
+					  "handover",
+					  "stop-ack",
+					  "shutdown-ack";
+
+			clocks = <&rpmhcc RPMH_CXO_CLK>;
+			clock-names = "xo";
+
+			interconnects = <&mc_virt MASTER_LLCC QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+
+			power-domains = <&rpmhpd RPMHPD_CX>,
+					<&rpmhpd RPMHPD_MSS>;
+			power-domain-names = "cx",
+					     "mss";
+
+			memory-region = <&mpss_mem>, <&q6_mpss_dtb_mem>,
+					<&mpss_dsm_mem>, <&mpss_dsm_mem_2>;
+
+			qcom,qmp = <&aoss_qmp>;
+
+			qcom,smem-states = <&smp2p_modem_out 0>;
+			qcom,smem-state-names = "stop";
+
+			status = "disabled";
+
+			glink-edge {
+				interrupts-extended = <&ipcc IPCC_CLIENT_MPSS
+							     IPCC_MPROC_SIGNAL_GLINK_QMP
+							     IRQ_TYPE_EDGE_RISING>;
+
+				mboxes = <&ipcc IPCC_CLIENT_MPSS
+						IPCC_MPROC_SIGNAL_GLINK_QMP>;
+
+				qcom,remote-pid = <1>;
+
+				label = "mpss";
+			};
+		};
+
+		lpass_wsa2macro: codec@6aa0000 {
+			compatible = "qcom,sm8650-lpass-wsa-macro", "qcom,sm8550-lpass-wsa-macro";
+			reg = <0 0x06aa0000 0 0x1000>;
+			clocks = <&q6prmcc LPASS_CLK_ID_WSA2_CORE_TX_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_MACRO_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&lpass_vamacro>;
+			clock-names = "mclk",
+				      "macro",
+				      "dcodec",
+				      "fsgen";
+
+			#clock-cells = <0>;
+			clock-output-names = "wsa2-mclk";
+			#sound-dai-cells = <1>;
+		};
+
+		swr3: soundwire@6ab0000 {
+			compatible = "qcom,soundwire-v2.0.0";
+			reg = <0 0x06ab0000 0 0x10000>;
+			interrupts = <GIC_SPI 171 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&lpass_wsa2macro>;
+			clock-names = "iface";
+			label = "WSA2";
+
+			pinctrl-0 = <&wsa2_swr_active>;
+			pinctrl-names = "default";
+
+			qcom,din-ports = <4>;
+			qcom,dout-ports = <9>;
+
+			qcom,ports-sinterval =		/bits/ 16 <0x07 0x1f 0x3f 0x07 0x1f 0x3f 0x18f 0xff 0xff 0x0f 0x0f 0xff 0x31f>;
+			qcom,ports-offset1 =		/bits/ 8 <0x01 0x03 0x05 0x02 0x04 0x15 0x00 0xff 0xff 0x06 0x0d 0xff 0x00>;
+			qcom,ports-offset2 =		/bits/ 8 <0xff 0x07 0x1f 0xff 0x07 0x1f 0xff 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-hstart =		/bits/ 8 <0xff 0xff 0xff 0xff 0xff 0xff 0x08 0xff 0xff 0xff 0xff 0xff 0x0f>;
+			qcom,ports-hstop =		/bits/ 8 <0xff 0xff 0xff 0xff 0xff 0xff 0x08 0xff 0xff 0xff 0xff 0xff 0x0f>;
+			qcom,ports-word-length =	/bits/ 8 <0xff 0xff 0xff 0xff 0xff 0xff 0x08 0xff 0xff 0xff 0xff 0xff 0x18>;
+			qcom,ports-block-pack-mode =	/bits/ 8 <0x00 0x01 0x01 0x00 0x01 0x01 0x00 0x00 0x00 0x01 0x01 0x00 0x00>;
+			qcom,ports-block-group-count =	/bits/ 8 <0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-lane-control =	/bits/ 8 <0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff>;
+
+			#address-cells = <2>;
+			#size-cells = <0>;
+			#sound-dai-cells = <1>;
+			status = "disabled";
+		};
+
+		lpass_rxmacro: codec@6ac0000 {
+			compatible = "qcom,sm8650-lpass-rx-macro", "qcom,sm8550-lpass-rx-macro";
+			reg = <0 0x06ac0000 0 0x1000>;
+			clocks = <&q6prmcc LPASS_CLK_ID_RX_CORE_TX_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_MACRO_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&lpass_vamacro>;
+			clock-names = "mclk",
+				      "macro",
+				      "dcodec",
+				      "fsgen";
+
+			#clock-cells = <0>;
+			clock-output-names = "mclk";
+			#sound-dai-cells = <1>;
+		};
+
+		swr1: soundwire@6ad0000 {
+			compatible = "qcom,soundwire-v2.0.0";
+			reg = <0 0x06ad0000 0 0x10000>;
+			interrupts = <GIC_SPI 155 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&lpass_rxmacro>;
+			clock-names = "iface";
+			label = "RX";
+
+			pinctrl-0 = <&rx_swr_active>;
+			pinctrl-names = "default";
+
+			qcom,din-ports = <0>;
+			qcom,dout-ports = <11>;
+
+			qcom,ports-sinterval =		/bits/ 16 <0x03 0x1f 0x1f 0x07 0x03 0xff 0xff 0x31 0xff 0xff 0xff>;
+			qcom,ports-offset1 =		/bits/ 8 <0x00 0x00 0x0b 0x09 0x01 0xff 0xff 0x00 0xff 0xff 0xff>;
+			qcom,ports-offset2 =		/bits/ 8 <0x00 0x00 0x0b 0x00 0x00 0xff 0xff 0x00 0xff 0xff 0xff>;
+			qcom,ports-hstart =		/bits/ 8 <0xff 0x03 0xff 0xff 0xff 0xff 0xff 0x00 0xff 0xff 0xff>;
+			qcom,ports-hstop =		/bits/ 8 <0xff 0x06 0xff 0xff 0xff 0xff 0xff 0x0f 0xff 0xff 0xff>;
+			qcom,ports-word-length =	/bits/ 8 <0x01 0x07 0x04 0xff 0xff 0xff 0xff 0x18 0xff 0xff 0xff>;
+			qcom,ports-block-pack-mode =	/bits/ 8 <0xff 0x00 0x01 0xff 0xff 0xff 0xff 0x01 0xff 0xff 0xff>;
+			qcom,ports-block-group-count =	/bits/ 8 <0xff 0xff 0xff 0x01 0x03 0xff 0xff 0x00 0xff 0xff 0xff>;
+			qcom,ports-lane-control =	/bits/ 8 <0x01 0x00 0x00 0x00 0x00 0xff 0xff 0x01 0xff 0xff 0xff>;
+
+			#address-cells = <2>;
+			#size-cells = <0>;
+			#sound-dai-cells = <1>;
+			status = "disabled";
+		};
+
+		lpass_txmacro: codec@6ae0000 {
+			compatible = "qcom,sm8650-lpass-tx-macro", "qcom,sm8550-lpass-tx-macro";
+			reg = <0 0x06ae0000 0 0x1000>;
+			clocks = <&q6prmcc LPASS_CLK_ID_TX_CORE_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_MACRO_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&lpass_vamacro>;
+			clock-names = "mclk",
+				      "macro",
+				      "dcodec",
+				      "fsgen";
+
+			#clock-cells = <0>;
+			clock-output-names = "mclk";
+			#sound-dai-cells = <1>;
+		};
+
+		lpass_wsamacro: codec@6b00000 {
+			compatible = "qcom,sm8650-lpass-wsa-macro", "qcom,sm8550-lpass-wsa-macro";
+			reg = <0 0x06b00000 0 0x1000>;
+			clocks = <&q6prmcc LPASS_CLK_ID_WSA_CORE_TX_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_MACRO_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&lpass_vamacro>;
+			clock-names = "mclk",
+				      "macro",
+				      "dcodec",
+				      "fsgen";
+
+			#clock-cells = <0>;
+			clock-output-names = "mclk";
+			#sound-dai-cells = <1>;
+		};
+
+		swr0: soundwire@6b10000 {
+			compatible = "qcom,soundwire-v2.0.0";
+			reg = <0 0x06b10000 0 0x10000>;
+			interrupts = <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&lpass_wsamacro>;
+			clock-names = "iface";
+			label = "WSA";
+
+			pinctrl-0 = <&wsa_swr_active>;
+			pinctrl-names = "default";
+
+			qcom,din-ports = <4>;
+			qcom,dout-ports = <9>;
+
+			qcom,ports-sinterval =		/bits/ 16 <0x07 0x1f 0x3f 0x07 0x1f 0x3f 0x18f 0xff 0xff 0x0f 0x0f 0xff 0x31f>;
+			qcom,ports-offset1 =		/bits/ 8 <0x01 0x03 0x05 0x02 0x04 0x15 0x00 0xff 0xff 0x06 0x0d 0xff 0x00>;
+			qcom,ports-offset2 =		/bits/ 8 <0xff 0x07 0x1f 0xff 0x07 0x1f 0xff 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-hstart =		/bits/ 8 <0xff 0xff 0xff 0xff 0xff 0xff 0x08 0xff 0xff 0xff 0xff 0xff 0x0f>;
+			qcom,ports-hstop =		/bits/ 8 <0xff 0xff 0xff 0xff 0xff 0xff 0x08 0xff 0xff 0xff 0xff 0xff 0x0f>;
+			qcom,ports-word-length =	/bits/ 8 <0xff 0xff 0xff 0xff 0xff 0xff 0x08 0xff 0xff 0xff 0xff 0xff 0x18>;
+			qcom,ports-block-pack-mode =	/bits/ 8 <0x00 0x01 0x01 0x00 0x01 0x01 0x00 0x00 0x00 0x01 0x01 0x00 0x00>;
+			qcom,ports-block-group-count =	/bits/ 8 <0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-lane-control =	/bits/ 8 <0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff>;
+
+			#address-cells = <2>;
+			#size-cells = <0>;
+			#sound-dai-cells = <1>;
+			status = "disabled";
+		};
+
+		swr2: soundwire@6d30000 {
+			compatible = "qcom,soundwire-v2.0.0";
+			reg = <0 0x06d30000 0 0x10000>;
+			interrupts = <GIC_SPI 496 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 520 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "core", "wakeup";
+			clocks = <&lpass_txmacro>;
+			clock-names = "iface";
+			label = "TX";
+
+			pinctrl-0 = <&tx_swr_active>;
+			pinctrl-names = "default";
+
+			qcom,din-ports = <4>;
+			qcom,dout-ports = <0>;
+
+			qcom,ports-sinterval-low =	/bits/ 8 <0x01 0x01 0x03 0x03>;
+			qcom,ports-offset1 =		/bits/ 8 <0x00 0x00 0x01 0x01>;
+			qcom,ports-offset2 =		/bits/ 8 <0x00 0x00 0x00 0x00>;
+			qcom,ports-hstart =		/bits/ 8 <0xff 0xff 0xff 0xff>;
+			qcom,ports-hstop =		/bits/ 8 <0xff 0xff 0xff 0xff>;
+			qcom,ports-word-length =	/bits/ 8 <0xff 0xff 0xff 0xff>;
+			qcom,ports-block-pack-mode =	/bits/ 8 <0xff 0xff 0xff 0xff>;
+			qcom,ports-block-group-count =	/bits/ 8 <0xff 0xff 0xff 0xff>;
+			qcom,ports-lane-control =	/bits/ 8 <0x01 0x02 0x00 0x00>;
+
+			#address-cells = <2>;
+			#size-cells = <0>;
+			#sound-dai-cells = <1>;
+			status = "disabled";
+		};
+
+		lpass_vamacro: codec@6d44000 {
+			compatible = "qcom,sm8650-lpass-va-macro", "qcom,sm8550-lpass-va-macro";
+			reg = <0 0x06d44000 0 0x1000>;
+			clocks = <&q6prmcc LPASS_CLK_ID_TX_CORE_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_MACRO_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>;
+			clock-names = "mclk",
+				      "macro",
+				      "dcodec";
+
+			#clock-cells = <0>;
+			clock-output-names = "fsgen";
+			#sound-dai-cells = <1>;
+		};
+
+		lpass_tlmm: pinctrl@6e80000 {
+			compatible = "qcom,sm8650-lpass-lpi-pinctrl";
+			reg = <0 0x06e80000 0 0x20000>;
+
+			clocks = <&q6prmcc LPASS_HW_MACRO_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>;
+			clock-names = "core", "audio";
+
+			gpio-controller;
+			#gpio-cells = <2>;
+			gpio-ranges = <&lpass_tlmm 0 0 23>;
+
+			tx_swr_active: tx-swr-active-state {
+				clk-pins {
+					pins = "gpio0";
+					function = "swr_tx_clk";
+					drive-strength = <2>;
+					slew-rate = <1>;
+					bias-disable;
+				};
+
+				data-pins {
+					pins = "gpio1", "gpio2", "gpio14";
+					function = "swr_tx_data";
+					drive-strength = <2>;
+					slew-rate = <1>;
+					bias-bus-hold;
+				};
+			};
+
+			rx_swr_active: rx-swr-active-state {
+				clk-pins {
+					pins = "gpio3";
+					function = "swr_rx_clk";
+					drive-strength = <2>;
+					slew-rate = <1>;
+					bias-disable;
+				};
+
+				data-pins {
+					pins = "gpio4", "gpio5";
+					function = "swr_rx_data";
+					drive-strength = <2>;
+					slew-rate = <1>;
+					bias-bus-hold;
+				};
+			};
+
+			dmic01_default: dmic01-default-state {
+				clk-pins {
+					pins = "gpio6";
+					function = "dmic1_clk";
+					drive-strength = <8>;
+					output-high;
+				};
+
+				data-pins {
+					pins = "gpio7";
+					function = "dmic1_data";
+					drive-strength = <8>;
+					input-enable;
+				};
+			};
+
+			dmic02_default: dmic02-default-state {
+				clk-pins {
+					pins = "gpio8";
+					function = "dmic2_clk";
+					drive-strength = <8>;
+					output-high;
+				};
+
+				data-pins {
+					pins = "gpio9";
+					function = "dmic2_data";
+					drive-strength = <8>;
+					input-enable;
+				};
+			};
+
+			wsa_swr_active: wsa-swr-active-state {
+				clk-pins {
+					pins = "gpio10";
+					function = "wsa_swr_clk";
+					drive-strength = <2>;
+					slew-rate = <1>;
+					bias-disable;
+				};
+
+				data-pins {
+					pins = "gpio11";
+					function = "wsa_swr_data";
+					drive-strength = <2>;
+					slew-rate = <1>;
+					bias-bus-hold;
+				};
+			};
+
+			wsa2_swr_active: wsa2-swr-active-state {
+				clk-pins {
+					pins = "gpio15";
+					function = "wsa2_swr_clk";
+					drive-strength = <2>;
+					slew-rate = <1>;
+					bias-disable;
+				};
+
+				data-pins {
+					pins = "gpio16";
+					function = "wsa2_swr_data";
+					drive-strength = <2>;
+					slew-rate = <1>;
+					bias-bus-hold;
+				};
+			};
+		};
+
+		lpass_lpiaon_noc: interconnect@7400000 {
+			compatible = "qcom,sm8650-lpass-lpiaon-noc";
+			reg = <0 0x07400000 0 0x19080>;
+
+			#interconnect-cells = <2>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+		};
+
+		lpass_lpicx_noc: interconnect@7430000 {
+			compatible = "qcom,sm8650-lpass-lpicx-noc";
+			reg = <0 0x07430000 0 0x3a200>;
+
+			#interconnect-cells = <2>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+		};
+
+		lpass_ag_noc: interconnect@7e40000 {
+			compatible = "qcom,sm8650-lpass-ag-noc";
+			reg = <0 0x07e40000 0 0xe080>;
+
+			#interconnect-cells = <2>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+		};
+
+		sdhc_2: mmc@8804000 {
+			compatible = "qcom,sm8650-sdhci", "qcom,sdhci-msm-v5";
+			reg = <0 0x08804000 0 0x1000>;
+
+			interrupts = <GIC_SPI 207 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 223 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "hc_irq",
+					  "pwr_irq";
+
+			clocks = <&gcc GCC_SDCC2_AHB_CLK>,
+				 <&gcc GCC_SDCC2_APPS_CLK>,
+				 <&rpmhcc RPMH_CXO_CLK>;
+			clock-names = "iface",
+				      "core",
+				      "xo";
+
+			interconnects = <&aggre2_noc MASTER_SDCC_2 QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
+					<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+					 &config_noc SLAVE_SDCC_2 QCOM_ICC_TAG_ALWAYS>;
+			interconnect-names = "sdhc-ddr",
+					     "cpu-sdhc";
+
+			power-domains = <&rpmhpd RPMHPD_CX>;
+			operating-points-v2 = <&sdhc2_opp_table>;
+
+			iommus = <&apps_smmu 0x540 0>;
+
+			bus-width = <4>;
+
+			/* Forbid SDR104/SDR50 - broken hw! */
+			sdhci-caps-mask = <0x3 0>;
+
+			qcom,dll-config = <0x0007642c>;
+			qcom,ddr-config = <0x80040868>;
+
+			dma-coherent;
+
+			status = "disabled";
+
+			sdhc2_opp_table: opp-table {
+				compatible = "operating-points-v2";
+
+				opp-19200000 {
+					opp-hz = /bits/ 64 <19200000>;
+					required-opps = <&rpmhpd_opp_min_svs>;
+				};
+
+				opp-50000000 {
+					opp-hz = /bits/ 64 <50000000>;
+					required-opps = <&rpmhpd_opp_low_svs>;
+				};
+
+				opp-100000000 {
+					opp-hz = /bits/ 64 <100000000>;
+					required-opps = <&rpmhpd_opp_svs>;
+				};
+
+				opp-202000000 {
+					opp-hz = /bits/ 64 <202000000>;
+					required-opps = <&rpmhpd_opp_svs_l1>;
+				};
+			};
+		};
+
+		mdss: display-subsystem@ae00000 {
+			compatible = "qcom,sm8650-mdss";
+			reg = <0 0x0ae00000 0 0x1000>;
+			reg-names = "mdss";
+
+			interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>;
+
+			clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
+				 <&gcc GCC_DISP_HF_AXI_CLK>,
+				 <&dispcc DISP_CC_MDSS_MDP_CLK>;
+
+			resets = <&dispcc DISP_CC_MDSS_CORE_BCR>;
+
+			interconnects = <&mmss_noc MASTER_MDP QCOM_ICC_TAG_ALWAYS
+					 &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>,
+					<&mc_virt MASTER_LLCC QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+			interconnect-names = "mdp0-mem",
+					     "mdp1-mem";
+
+			power-domains = <&dispcc MDSS_GDSC>;
+
+			iommus = <&apps_smmu 0x1c00 0x2>;
+
+			interrupt-controller;
+			#interrupt-cells = <1>;
+
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+
+			status = "disabled";
+
+			mdss_mdp: display-controller@ae01000 {
+				compatible = "qcom,sm8650-dpu";
+				reg = <0 0x0ae01000 0 0x8f000>,
+				      <0 0x0aeb0000 0 0x2008>;
+				reg-names = "mdp",
+					    "vbif";
+
+				interrupts-extended = <&mdss 0>;
+
+				clocks = <&gcc GCC_DISP_HF_AXI_CLK>,
+					 <&dispcc DISP_CC_MDSS_AHB_CLK>,
+					 <&dispcc DISP_CC_MDSS_MDP_LUT_CLK>,
+					 <&dispcc DISP_CC_MDSS_MDP_CLK>,
+					 <&dispcc DISP_CC_MDSS_VSYNC_CLK>;
+				clock-names = "nrt_bus",
+					      "iface",
+					      "lut",
+					      "core",
+					      "vsync";
+
+				assigned-clocks = <&dispcc DISP_CC_MDSS_VSYNC_CLK>;
+				assigned-clock-rates = <19200000>;
+
+				operating-points-v2 = <&mdp_opp_table>;
+
+				power-domains = <&rpmhpd RPMHPD_MMCX>;
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+
+						dpu_intf1_out: endpoint {
+							remote-endpoint = <&mdss_dsi0_in>;
+						};
+					};
+
+					port@1 {
+						reg = <1>;
+
+						dpu_intf2_out: endpoint {
+							remote-endpoint = <&mdss_dsi1_in>;
+						};
+					};
+
+					port@2 {
+						reg = <2>;
+
+						dpu_intf0_out: endpoint {
+							remote-endpoint = <&mdss_dp0_in>;
+						};
+					};
+				};
+
+				mdp_opp_table: opp-table {
+					compatible = "operating-points-v2";
+
+					opp-200000000 {
+						opp-hz = /bits/ 64 <200000000>;
+						required-opps = <&rpmhpd_opp_low_svs>;
+					};
+
+					opp-325000000 {
+						opp-hz = /bits/ 64 <325000000>;
+						required-opps = <&rpmhpd_opp_svs>;
+					};
+
+					opp-375000000 {
+						opp-hz = /bits/ 64 <375000000>;
+						required-opps = <&rpmhpd_opp_svs_l1>;
+					};
+
+					opp-514000000 {
+						opp-hz = /bits/ 64 <514000000>;
+						required-opps = <&rpmhpd_opp_nom>;
+					};
+				};
+			};
+
+			mdss_dsi0: dsi@ae94000 {
+				compatible = "qcom,sm8650-dsi-ctrl", "qcom,mdss-dsi-ctrl";
+				reg = <0 0x0ae94000 0 0x400>;
+				reg-names = "dsi_ctrl";
+
+				interrupts-extended = <&mdss 4>;
+
+				clocks = <&dispcc DISP_CC_MDSS_BYTE0_CLK>,
+					 <&dispcc DISP_CC_MDSS_BYTE0_INTF_CLK>,
+					 <&dispcc DISP_CC_MDSS_PCLK0_CLK>,
+					 <&dispcc DISP_CC_MDSS_ESC0_CLK>,
+					 <&dispcc DISP_CC_MDSS_AHB_CLK>,
+					 <&gcc GCC_DISP_HF_AXI_CLK>;
+				clock-names = "byte",
+					      "byte_intf",
+					      "pixel",
+					      "core",
+					      "iface",
+					      "bus";
+
+				assigned-clocks = <&dispcc DISP_CC_MDSS_BYTE0_CLK_SRC>,
+						  <&dispcc DISP_CC_MDSS_PCLK0_CLK_SRC>;
+				assigned-clock-parents = <&mdss_dsi0_phy 0>,
+							 <&mdss_dsi0_phy 1>;
+
+				operating-points-v2 = <&mdss_dsi_opp_table>;
+
+				power-domains = <&rpmhpd RPMHPD_MMCX>;
+
+				phys = <&mdss_dsi0_phy>;
+				phy-names = "dsi";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+
+						mdss_dsi0_in: endpoint {
+							remote-endpoint = <&dpu_intf1_out>;
+						};
+					};
+
+					port@1 {
+						reg = <1>;
+
+						mdss_dsi0_out: endpoint {
+						};
+					};
+				};
+
+				mdss_dsi_opp_table: opp-table {
+					compatible = "operating-points-v2";
+
+					opp-187500000 {
+						opp-hz = /bits/ 64 <187500000>;
+						required-opps = <&rpmhpd_opp_low_svs>;
+					};
+
+					opp-300000000 {
+						opp-hz = /bits/ 64 <300000000>;
+						required-opps = <&rpmhpd_opp_svs>;
+					};
+
+					opp-358000000 {
+						opp-hz = /bits/ 64 <358000000>;
+						required-opps = <&rpmhpd_opp_svs_l1>;
+					};
+				};
+			};
+
+			mdss_dsi0_phy: phy@ae95000 {
+				compatible = "qcom,sm8650-dsi-phy-4nm";
+				reg = <0 0x0ae95000 0 0x200>,
+				      <0 0x0ae95200 0 0x280>,
+				      <0 0x0ae95500 0 0x400>;
+				reg-names = "dsi_phy",
+					    "dsi_phy_lane",
+					    "dsi_pll";
+
+				clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
+					 <&rpmhcc RPMH_CXO_CLK>;
+				clock-names = "iface",
+					      "ref";
+
+				#clock-cells = <1>;
+				#phy-cells = <0>;
+
+				status = "disabled";
+			};
+
+			mdss_dsi1: dsi@ae96000 {
+				compatible = "qcom,sm8650-dsi-ctrl", "qcom,mdss-dsi-ctrl";
+				reg = <0 0x0ae96000 0 0x400>;
+				reg-names = "dsi_ctrl";
+
+				interrupts-extended = <&mdss 5>;
+
+				clocks = <&dispcc DISP_CC_MDSS_BYTE1_CLK>,
+					 <&dispcc DISP_CC_MDSS_BYTE1_INTF_CLK>,
+					 <&dispcc DISP_CC_MDSS_PCLK1_CLK>,
+					 <&dispcc DISP_CC_MDSS_ESC1_CLK>,
+					 <&dispcc DISP_CC_MDSS_AHB_CLK>,
+					 <&gcc GCC_DISP_HF_AXI_CLK>;
+				clock-names = "byte",
+					      "byte_intf",
+					      "pixel",
+					      "core",
+					      "iface",
+					      "bus";
+
+				assigned-clocks = <&dispcc DISP_CC_MDSS_BYTE1_CLK_SRC>,
+						  <&dispcc DISP_CC_MDSS_PCLK1_CLK_SRC>;
+				assigned-clock-parents = <&mdss_dsi1_phy 0>,
+							 <&mdss_dsi1_phy 1>;
+
+				operating-points-v2 = <&mdss_dsi_opp_table>;
+
+				power-domains = <&rpmhpd RPMHPD_MMCX>;
+
+				phys = <&mdss_dsi1_phy>;
+				phy-names = "dsi";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+
+						mdss_dsi1_in: endpoint {
+							remote-endpoint = <&dpu_intf2_out>;
+						};
+					};
+
+					port@1 {
+						reg = <1>;
+
+						mdss_dsi1_out: endpoint {
+						};
+					};
+				};
+			};
+
+			mdss_dsi1_phy: phy@ae97000 {
+				compatible = "qcom,sm8650-dsi-phy-4nm";
+				reg = <0 0x0ae97000 0 0x200>,
+				      <0 0x0ae97200 0 0x280>,
+				      <0 0x0ae97500 0 0x400>;
+				reg-names = "dsi_phy",
+					    "dsi_phy_lane",
+					    "dsi_pll";
+
+				clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
+					 <&rpmhcc RPMH_CXO_CLK>;
+				clock-names = "iface",
+					      "ref";
+
+				#clock-cells = <1>;
+				#phy-cells = <0>;
+
+				status = "disabled";
+			};
+
+			mdss_dp0: displayport-controller@af54000 {
+				compatible = "qcom,sm8650-dp";
+				reg = <0 0xaf54000 0 0x104>,
+				      <0 0xaf54200 0 0xc0>,
+				      <0 0xaf55000 0 0x770>,
+				      <0 0xaf56000 0 0x9c>,
+				      <0 0xaf57000 0 0x9c>;
+
+				interrupts-extended = <&mdss 12>;
+
+				clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
+					 <&dispcc DISP_CC_MDSS_DPTX0_AUX_CLK>,
+					 <&dispcc DISP_CC_MDSS_DPTX0_LINK_CLK>,
+					 <&dispcc DISP_CC_MDSS_DPTX0_LINK_INTF_CLK>,
+					 <&dispcc DISP_CC_MDSS_DPTX0_PIXEL0_CLK>;
+				clock-names = "core_iface",
+					      "core_aux",
+					      "ctrl_link",
+					      "ctrl_link_iface",
+					      "stream_pixel";
+
+				assigned-clocks = <&dispcc DISP_CC_MDSS_DPTX0_LINK_CLK_SRC>,
+						  <&dispcc DISP_CC_MDSS_DPTX0_PIXEL0_CLK_SRC>;
+				assigned-clock-parents = <&usb_dp_qmpphy QMP_USB43DP_DP_LINK_CLK>,
+							 <&usb_dp_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>;
+
+				operating-points-v2 = <&dp_opp_table>;
+
+				power-domains = <&rpmhpd RPMHPD_MMCX>;
+
+				phys = <&usb_dp_qmpphy QMP_USB43DP_DP_PHY>;
+				phy-names = "dp";
+
+				#sound-dai-cells = <0>;
+
+				status = "disabled";
+
+				dp_opp_table: opp-table {
+					compatible = "operating-points-v2";
+
+					opp-162000000 {
+						opp-hz = /bits/ 64 <162000000>;
+						required-opps = <&rpmhpd_opp_low_svs_d1>;
+					};
+
+					opp-270000000 {
+						opp-hz = /bits/ 64 <270000000>;
+						required-opps = <&rpmhpd_opp_low_svs>;
+					};
+
+					opp-540000000 {
+						opp-hz = /bits/ 64 <540000000>;
+						required-opps = <&rpmhpd_opp_svs_l1>;
+					};
+
+					opp-810000000 {
+						opp-hz = /bits/ 64 <810000000>;
+						required-opps = <&rpmhpd_opp_nom>;
+					};
+				};
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+
+						mdss_dp0_in: endpoint {
+							remote-endpoint = <&dpu_intf0_out>;
+						};
+					};
+
+					port@1 {
+						reg = <1>;
+
+						mdss_dp0_out: endpoint {
+						};
+					};
+				};
+			};
+		};
+
+		dispcc: clock-controller@af00000 {
+			compatible = "qcom,sm8650-dispcc";
+			reg = <0 0x0af00000 0 0x20000>;
+
+			clocks = <&bi_tcxo_div2>,
+				 <&bi_tcxo_ao_div2>,
+				 <&gcc GCC_DISP_AHB_CLK>,
+				 <&sleep_clk>,
+				 <&mdss_dsi0_phy 0>,
+				 <&mdss_dsi0_phy 1>,
+				 <&mdss_dsi1_phy 0>,
+				 <&mdss_dsi1_phy 1>,
+				 <&usb_dp_qmpphy QMP_USB43DP_DP_LINK_CLK>,
+				 <&usb_dp_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>,
+				 <0>, /* dp1 */
+				 <0>,
+				 <0>, /* dp2 */
+				 <0>,
+				 <0>, /* dp3 */
+				 <0>;
+
+			power-domains = <&rpmhpd RPMHPD_MMCX>;
+			required-opps = <&rpmhpd_opp_low_svs>;
+
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+			#power-domain-cells = <1>;
+
+			status = "disabled";
+		};
+
+		usb_1_hsphy: phy@88e3000 {
+			compatible = "qcom,sm8650-snps-eusb2-phy",
+				     "qcom,sm8550-snps-eusb2-phy";
+			reg = <0 0x088e3000 0 0x154>;
+
+			clocks = <&tcsr TCSR_USB2_CLKREF_EN>;
+			clock-names = "ref";
+
+			resets = <&gcc GCC_QUSB2PHY_PRIM_BCR>;
+
+			#phy-cells = <0>;
+
+			status = "disabled";
+		};
+
+		usb_dp_qmpphy: phy@88e8000 {
+			compatible = "qcom,sm8650-qmp-usb3-dp-phy";
+			reg = <0 0x088e8000 0 0x3000>;
+
+			clocks = <&gcc GCC_USB3_PRIM_PHY_AUX_CLK>,
+				 <&rpmhcc RPMH_CXO_CLK>,
+				 <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>,
+				 <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>;
+			clock-names = "aux",
+				      "ref",
+				      "com_aux",
+				      "usb3_pipe";
+
+			resets = <&gcc GCC_USB3_PHY_PRIM_BCR>,
+				 <&gcc GCC_USB3_DP_PHY_PRIM_BCR>;
+			reset-names = "phy",
+				      "common";
+
+			power-domains = <&gcc USB3_PHY_GDSC>;
+
+			#clock-cells = <1>;
+			#phy-cells = <1>;
+
+			status = "disabled";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+
+					usb_dp_qmpphy_out: endpoint {
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+
+					usb_dp_qmpphy_usb_ss_in: endpoint {
+					};
+				};
+
+				port@2 {
+					reg = <2>;
+
+					usb_dp_qmpphy_dp_in: endpoint {
+					};
+				};
+			};
+		};
+
+		usb_1: usb@a6f8800 {
+			compatible = "qcom,sm8650-dwc3", "qcom,dwc3";
+			reg = <0 0x0a6f8800 0 0x400>;
+
+			interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 17 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 15 IRQ_TYPE_EDGE_RISING>,
+					      <&pdc 14 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "hs_phy_irq",
+					  "ss_phy_irq",
+					  "dm_hs_phy_irq",
+					  "dp_hs_phy_irq";
+
+			clocks = <&gcc GCC_CFG_NOC_USB3_PRIM_AXI_CLK>,
+				 <&gcc GCC_USB30_PRIM_MASTER_CLK>,
+				 <&gcc GCC_AGGRE_USB3_PRIM_AXI_CLK>,
+				 <&gcc GCC_USB30_PRIM_SLEEP_CLK>,
+				 <&gcc GCC_USB30_PRIM_MOCK_UTMI_CLK>,
+				 <&tcsr TCSR_USB3_CLKREF_EN>;
+			clock-names = "cfg_noc",
+				      "core",
+				      "iface",
+				      "sleep",
+				      "mock_utmi",
+				      "xo";
+
+			assigned-clocks = <&gcc GCC_USB30_PRIM_MOCK_UTMI_CLK>,
+					  <&gcc GCC_USB30_PRIM_MASTER_CLK>;
+			assigned-clock-rates = <19200000>, <200000000>;
+
+			resets = <&gcc GCC_USB30_PRIM_BCR>;
+
+			power-domains = <&gcc USB30_PRIM_GDSC>;
+			required-opps = <&rpmhpd_opp_nom>;
+
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+
+			status = "disabled";
+
+			usb_1_dwc3: usb@a600000 {
+				compatible = "snps,dwc3";
+				reg = <0 0x0a600000 0 0xcd00>;
+
+				interrupts = <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
+
+				iommus = <&apps_smmu 0x40 0>;
+
+				phys = <&usb_1_hsphy>,
+				       <&usb_dp_qmpphy QMP_USB43DP_USB3_PHY>;
+				phy-names = "usb2-phy",
+					    "usb3-phy";
+
+				snps,hird-threshold = /bits/ 8 <0x0>;
+				snps,usb2-gadget-lpm-disable;
+				snps,dis_u2_susphy_quirk;
+				snps,dis_enblslpm_quirk;
+				snps,dis-u1-entry-quirk;
+				snps,dis-u2-entry-quirk;
+				snps,is-utmi-l1-suspend;
+				snps,usb3_lpm_capable;
+				snps,usb2-lpm-disable;
+				snps,has-lpm-erratum;
+				tx-fifo-resize;
+
+				dma-coherent;
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+
+						usb_1_dwc3_hs: endpoint {
+						};
+					};
+
+					port@1 {
+						reg = <1>;
+
+						usb_1_dwc3_ss: endpoint {
+						};
+					};
+				};
+			};
+		};
+
+		pdc: interrupt-controller@b220000 {
+			compatible = "qcom,sm8650-pdc", "qcom,pdc";
+			reg = <0 0x0b220000 0 0x30000>, <0 0x174000f0 0 0x64>;
+
+			interrupt-parent = <&intc>;
+
+			qcom,pdc-ranges = <0 480 94>, <94 609 31>,
+					  <125 63 1>, <126 716 12>,
+					  <138 251 5>, <143 244 4>;
+
+			#interrupt-cells = <2>;
+			interrupt-controller;
+		};
+
+		tsens0: thermal-sensor@c228000 {
+			compatible = "qcom,sm8650-tsens", "qcom,tsens-v2";
+			reg = <0 0x0c228000 0 0x1000>, /* TM */
+			      <0 0x0c222000 0 0x1000>; /* SROT */
+
+			interrupts = <GIC_SPI 506 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 640 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "uplow",
+					  "critical";
+
+			#qcom,sensors = <15>;
+
+			#thermal-sensor-cells = <1>;
+		};
+
+		tsens1: thermal-sensor@c229000 {
+			compatible = "qcom,sm8650-tsens", "qcom,tsens-v2";
+			reg = <0 0x0c229000 0 0x1000>, /* TM */
+			      <0 0x0c223000 0 0x1000>; /* SROT */
+
+			interrupts = <GIC_SPI 507 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 641 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "uplow",
+					  "critical";
+
+			#qcom,sensors = <16>;
+
+			#thermal-sensor-cells = <1>;
+		};
+
+		tsens2: thermal-sensor@c22a000 {
+			compatible = "qcom,sm8650-tsens", "qcom,tsens-v2";
+			reg = <0 0x0c22a000 0 0x1000>, /* TM */
+			      <0 0x0c224000 0 0x1000>; /* SROT */
+
+			interrupts = <GIC_SPI 508 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 642 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "uplow",
+					  "critical";
+
+			#qcom,sensors = <13>;
+
+			#thermal-sensor-cells = <1>;
+		};
+
+		aoss_qmp: power-management@c300000 {
+			compatible = "qcom,sm8650-aoss-qmp", "qcom,aoss-qmp";
+			reg = <0 0x0c300000 0 0x400>;
+
+			interrupt-parent = <&ipcc>;
+			interrupts-extended = <&ipcc IPCC_CLIENT_AOP IPCC_MPROC_SIGNAL_GLINK_QMP
+						     IRQ_TYPE_EDGE_RISING>;
+
+			mboxes = <&ipcc IPCC_CLIENT_AOP IPCC_MPROC_SIGNAL_GLINK_QMP>;
+
+			#clock-cells = <0>;
+		};
+
+		sram@c3f0000 {
+			compatible = "qcom,rpmh-stats";
+			reg = <0 0x0c3f0000 0 0x400>;
+		};
+
+		spmi_bus: spmi@c400000 {
+			compatible = "qcom,spmi-pmic-arb";
+			reg = <0 0x0c400000 0 0x3000>,
+			      <0 0x0c500000 0 0x4000000>,
+			      <0 0x0c440000 0 0x80000>,
+			      <0 0x0c4c0000 0 0x20000>,
+			      <0 0x0c42d000 0 0x4000>;
+			reg-names = "core",
+				    "chnls",
+				    "obsrvr",
+				    "intr",
+				    "cnfg";
+
+			interrupts-extended = <&pdc 1 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "periph_irq";
+
+			qcom,ee = <0>;
+			qcom,channel = <0>;
+			qcom,bus-id = <0>;
+
+			interrupt-controller;
+			#interrupt-cells = <4>;
+
+			#address-cells = <2>;
+			#size-cells = <0>;
+		};
+
+		tlmm: pinctrl@f100000 {
+			compatible = "qcom,sm8650-tlmm";
+			reg = <0 0x0f100000 0 0x300000>;
+
+			interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
+
+			gpio-controller;
+			#gpio-cells = <2>;
+
+			interrupt-controller;
+			#interrupt-cells = <2>;
+
+			gpio-ranges = <&tlmm 0 0 211>;
+
+			wakeup-parent = <&pdc>;
+
+			hub_i2c0_data_clk: hub-i2c0-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio64", "gpio65";
+				function = "i2chub0_se0";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			hub_i2c1_data_clk: hub-i2c1-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio66", "gpio67";
+				function = "i2chub0_se1";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			hub_i2c2_data_clk: hub-i2c2-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio68", "gpio69";
+				function = "i2chub0_se2";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			hub_i2c3_data_clk: hub-i2c3-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio70", "gpio71";
+				function = "i2chub0_se3";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			hub_i2c4_data_clk: hub-i2c4-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio72", "gpio73";
+				function = "i2chub0_se4";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			hub_i2c5_data_clk: hub-i2c5-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio74", "gpio75";
+				function = "i2chub0_se5";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			hub_i2c6_data_clk: hub-i2c6-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio76", "gpio77";
+				function = "i2chub0_se6";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			hub_i2c7_data_clk: hub-i2c7-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio78", "gpio79";
+				function = "i2chub0_se7";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			hub_i2c8_data_clk: hub-i2c8-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio206", "gpio207";
+				function = "i2chub0_se8";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			hub_i2c9_data_clk: hub-i2c9-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio80", "gpio81";
+				function = "i2chub0_se9";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			pcie0_default_state: pcie0-default-state {
+				perst-pins {
+					pins = "gpio94";
+					function = "gpio";
+					drive-strength = <2>;
+					bias-pull-down;
+				};
+
+				clkreq-pins {
+					pins = "gpio95";
+					function = "pcie0_clk_req_n";
+					drive-strength = <2>;
+					bias-pull-up;
+				};
+
+				wake-pins {
+					pins = "gpio96";
+					function = "gpio";
+					drive-strength = <2>;
+					bias-pull-up;
+				};
+			};
+
+			pcie1_default_state: pcie1-default-state {
+				perst-pins {
+					pins = "gpio97";
+					function = "gpio";
+					drive-strength = <2>;
+					bias-pull-down;
+				};
+
+				clkreq-pins {
+					pins = "gpio98";
+					function = "pcie1_clk_req_n";
+					drive-strength = <2>;
+					bias-pull-up;
+				};
+
+				wake-pins {
+					pins = "gpio99";
+					function = "gpio";
+					drive-strength = <2>;
+					bias-pull-up;
+				};
+			};
+
+			qup_i2c0_data_clk: qup-i2c0-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio32", "gpio33";
+				function = "qup1_se0";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			qup_i2c1_data_clk: qup-i2c1-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio36", "gpio37";
+				function = "qup1_se1";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			qup_i2c2_data_clk: qup-i2c2-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio40", "gpio41";
+				function = "qup1_se2";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			qup_i2c3_data_clk: qup-i2c3-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio44", "gpio45";
+				function = "qup1_se3";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			qup_i2c4_data_clk: qup-i2c4-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio48", "gpio49";
+				function = "qup1_se4";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			qup_i2c5_data_clk: qup-i2c5-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio52", "gpio53";
+				function = "qup1_se5";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			qup_i2c6_data_clk: qup-i2c6-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio56", "gpio57";
+				function = "qup1_se6";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			qup_i2c7_data_clk: qup-i2c7-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio60", "gpio61";
+				function = "qup1_se7";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			qup_i2c8_data_clk: qup-i2c8-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio0", "gpio1";
+				function = "qup2_se0";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			qup_i2c9_data_clk: qup-i2c9-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio4", "gpio5";
+				function = "qup2_se1";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			qup_i2c10_data_clk: qup-i2c10-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio8", "gpio9";
+				function = "qup2_se2";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			qup_i2c11_data_clk: qup-i2c11-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio12", "gpio13";
+				function = "qup2_se3";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			qup_i2c12_data_clk: qup-i2c12-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio16", "gpio17";
+				function = "qup2_se4";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			qup_i2c13_data_clk: qup-i2c13-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio20", "gpio21";
+				function = "qup2_se5";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			qup_i2c14_data_clk: qup-i2c14-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio24", "gpio25";
+				function = "qup2_se6";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			qup_spi0_cs: qup-spi0-cs-state {
+				pins = "gpio35";
+				function = "qup1_se0";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi0_data_clk: qup-spi0-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio32", "gpio33", "gpio34";
+				function = "qup1_se0";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi1_cs: qup-spi1-cs-state {
+				pins = "gpio39";
+				function = "qup1_se1";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi1_data_clk: qup-spi1-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio36", "gpio37", "gpio38";
+				function = "qup1_se1";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi2_cs: qup-spi2-cs-state {
+				pins = "gpio43";
+				function = "qup1_se2";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi2_data_clk: qup-spi2-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio40", "gpio41", "gpio42";
+				function = "qup1_se2";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi3_cs: qup-spi3-cs-state {
+				pins = "gpio47";
+				function = "qup1_se3";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi3_data_clk: qup-spi3-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio44", "gpio45", "gpio46";
+				function = "qup1_se3";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi4_cs: qup-spi4-cs-state {
+				pins = "gpio51";
+				function = "qup1_se4";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi4_data_clk: qup-spi4-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio48", "gpio49", "gpio50";
+				function = "qup1_se4";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi5_cs: qup-spi5-cs-state {
+				pins = "gpio55";
+				function = "qup1_se5";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi5_data_clk: qup-spi5-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio52", "gpio53", "gpio54";
+				function = "qup1_se5";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi6_cs: qup-spi6-cs-state {
+				pins = "gpio59";
+				function = "qup1_se6";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi6_data_clk: qup-spi6-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio56", "gpio57", "gpio58";
+				function = "qup1_se6";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi7_cs: qup-spi7-cs-state {
+				pins = "gpio63";
+				function = "qup1_se7";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi7_data_clk: qup-spi7-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio60", "gpio61", "gpio62";
+				function = "qup1_se7";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi8_cs: qup-spi8-cs-state {
+				pins = "gpio3";
+				function = "qup2_se0";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi8_data_clk: qup-spi8-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio0", "gpio1", "gpio2";
+				function = "qup2_se0";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi9_cs: qup-spi9-cs-state {
+				pins = "gpio7";
+				function = "qup2_se1";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi9_data_clk: qup-spi9-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio4", "gpio5", "gpio6";
+				function = "qup2_se1";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi10_cs: qup-spi10-cs-state {
+				pins = "gpio11";
+				function = "qup2_se2";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi10_data_clk: qup-spi10-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio8", "gpio9", "gpio10";
+				function = "qup2_se2";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi11_cs: qup-spi11-cs-state {
+				pins = "gpio15";
+				function = "qup2_se3";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi11_data_clk: qup-spi11-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio12", "gpio13", "gpio14";
+				function = "qup2_se3";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi12_cs: qup-spi12-cs-state {
+				pins = "gpio19";
+				function = "qup2_se4";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi12_data_clk: qup-spi12-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio16", "gpio17", "gpio18";
+				function = "qup2_se4";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi13_cs: qup-spi13-cs-state {
+				pins = "gpio23";
+				function = "qup2_se5";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi13_data_clk: qup-spi13-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio20", "gpio21", "gpio22";
+				function = "qup2_se5";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi14_cs: qup-spi14-cs-state {
+				pins = "gpio27";
+				function = "qup2_se6";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi14_data_clk: qup-spi14-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio24", "gpio25", "gpio26";
+				function = "qup2_se6";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_uart14_default: qup-uart14-default-state {
+				/* TX, RX */
+				pins = "gpio26", "gpio27";
+				function = "qup2_se6";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+
+			qup_uart14_cts_rts: qup-uart14-cts-rts-state {
+				/* CTS, RTS */
+				pins = "gpio24", "gpio25";
+				function = "qup2_se6";
+				drive-strength = <2>;
+				bias-pull-down;
+			};
+
+			qup_uart15_default: qup-uart15-default-state {
+				/* TX, RX */
+				pins = "gpio30", "gpio31";
+				function = "qup2_se7";
+				drive-strength = <2>;
+				bias-disable;
+			};
+
+			sdc2_sleep: sdc2-sleep-state {
+				clk-pins {
+					pins = "sdc2_clk";
+					drive-strength = <2>;
+					bias-disable;
+				};
+
+				cmd-pins {
+					pins = "sdc2_cmd";
+					drive-strength = <2>;
+					bias-pull-up;
+				};
+
+				data-pins {
+					pins = "sdc2_data";
+					drive-strength = <2>;
+					bias-pull-up;
+				};
+			};
+
+			sdc2_default: sdc2-default-state {
+				clk-pins {
+					pins = "sdc2_clk";
+					drive-strength = <16>;
+					bias-disable;
+				};
+
+				cmd-pins {
+					pins = "sdc2_cmd";
+					drive-strength = <10>;
+					bias-pull-up;
+				};
+
+				data-pins {
+					pins = "sdc2_data";
+					drive-strength = <10>;
+					bias-pull-up;
+				};
+			};
+		};
+
+		apps_smmu: iommu@15000000 {
+			compatible = "qcom,sm8650-smmu-500", "qcom,smmu-500", "arm,mmu-500";
+			reg = <0 0x15000000 0 0x100000>;
+
+			interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 104 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 107 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 112 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 113 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 114 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 115 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 181 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 182 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 183 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 184 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 185 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 186 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 187 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 188 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 189 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 190 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 191 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 192 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 315 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 316 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 317 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 318 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 319 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 320 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 321 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 322 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 323 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 324 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 325 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 326 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 327 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 328 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 329 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 330 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 331 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 332 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 333 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 334 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 335 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 336 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 337 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 338 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 339 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 340 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 341 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 342 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 343 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 344 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 345 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 395 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 396 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 397 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 398 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 399 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 400 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 401 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 402 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 403 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 404 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 405 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 406 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 407 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 408 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 409 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 418 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 419 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 412 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 421 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 706 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 423 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 424 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 425 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 689 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 690 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 691 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 692 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 693 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 694 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 695 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 696 IRQ_TYPE_LEVEL_HIGH>;
+
+			#iommu-cells = <2>;
+			#global-interrupts = <1>;
+
+			dma-coherent;
+		};
+
+		intc: interrupt-controller@17100000 {
+			compatible = "arm,gic-v3";
+			reg = <0 0x17100000 0 0x10000>,		/* GICD */
+			      <0 0x17180000 0 0x200000>;	/* GICR * 8 */
+
+			interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_LOW>;
+
+			#interrupt-cells = <3>;
+			interrupt-controller;
+
+			#redistributor-regions = <1>;
+			redistributor-stride = <0 0x40000>;
+
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+
+			gic_its: msi-controller@17140000 {
+				compatible = "arm,gic-v3-its";
+				reg = <0 0x17140000 0 0x20000>;
+
+				msi-controller;
+				#msi-cells = <1>;
+			};
+		};
+
+		timer@17420000 {
+			compatible = "arm,armv7-timer-mem";
+			reg = <0 0x17420000 0 0x1000>;
+
+			ranges = <0 0 0 0x20000000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			frame@17421000 {
+				reg = <0x17421000 0x1000>,
+				      <0x17422000 0x1000>;
+
+				interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>;
+
+				frame-number = <0>;
+			};
+
+			frame@17423000 {
+				reg = <0x17423000 0x1000>;
+
+				interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>;
+
+				frame-number = <1>;
+
+				status = "disabled";
+			};
+
+			frame@17425000 {
+				reg = <0x17425000 0x1000>;
+
+				interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>;
+
+				frame-number = <2>;
+
+				status = "disabled";
+			};
+
+			frame@17427000 {
+				reg = <0x17427000 0x1000>;
+
+				interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>;
+
+				frame-number = <3>;
+
+				status = "disabled";
+			};
+
+			frame@17429000 {
+				reg = <0x17429000 0x1000>;
+
+				interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>;
+
+				frame-number = <4>;
+
+				status = "disabled";
+			};
+
+			frame@1742b000 {
+				reg = <0x1742b000 0x1000>;
+
+				interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>;
+
+				frame-number = <5>;
+
+				status = "disabled";
+			};
+
+			frame@1742d000 {
+				reg = <0x1742d000 0x1000>;
+
+				interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
+
+				frame-number = <6>;
+
+				status = "disabled";
+			};
+		};
+
+		apps_rsc: rsc@17a00000 {
+			compatible = "qcom,rpmh-rsc";
+			reg = <0 0x17a00000 0 0x10000>,
+			      <0 0x17a10000 0 0x10000>,
+			      <0 0x17a20000 0 0x10000>,
+			      <0 0x17a30000 0 0x10000>;
+			reg-names = "drv-0",
+				    "drv-1",
+				    "drv-2";
+
+			interrupts = <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>;
+
+			power-domains = <&CLUSTER_PD>;
+
+			qcom,tcs-offset = <0xd00>;
+			qcom,drv-id = <2>;
+			qcom,tcs-config = <ACTIVE_TCS    3>, <SLEEP_TCS     2>,
+					  <WAKE_TCS      2>, <CONTROL_TCS   0>;
+
+			label = "apps_rsc";
+
+			apps_bcm_voter: bcm-voter {
+				compatible = "qcom,bcm-voter";
+			};
+
+			rpmhcc: clock-controller {
+				compatible = "qcom,sm8650-rpmh-clk";
+
+				clocks = <&xo_board>;
+				clock-names = "xo";
+
+				#clock-cells = <1>;
+			};
+
+			rpmhpd: power-controller {
+				compatible = "qcom,sm8650-rpmhpd";
+
+				operating-points-v2 = <&rpmhpd_opp_table>;
+
+				#power-domain-cells = <1>;
+
+				rpmhpd_opp_table: opp-table {
+					compatible = "operating-points-v2";
+
+					rpmhpd_opp_ret: opp-16 {
+						opp-level = <RPMH_REGULATOR_LEVEL_RETENTION>;
+					};
+
+					rpmhpd_opp_min_svs: opp-48 {
+						opp-level = <RPMH_REGULATOR_LEVEL_MIN_SVS>;
+					};
+
+					rpmhpd_opp_low_svs_d2: opp-52 {
+						opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS_D2>;
+					};
+
+					rpmhpd_opp_low_svs_d1: opp-56 {
+						opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS_D1>;
+					};
+
+					rpmhpd_opp_low_svs_d0: opp-60 {
+						opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS_D0>;
+					};
+
+					rpmhpd_opp_low_svs: opp-64 {
+						opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS>;
+					};
+
+					rpmhpd_opp_low_svs_l1: opp-80 {
+						opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS_L1>;
+					};
+
+					rpmhpd_opp_svs: opp-128 {
+						opp-level = <RPMH_REGULATOR_LEVEL_SVS>;
+					};
+
+					rpmhpd_opp_svs_l0: opp-144 {
+						opp-level = <RPMH_REGULATOR_LEVEL_SVS_L0>;
+					};
+
+					rpmhpd_opp_svs_l1: opp-192 {
+						opp-level = <RPMH_REGULATOR_LEVEL_SVS_L1>;
+					};
+
+					rpmhpd_opp_nom: opp-256 {
+						opp-level = <RPMH_REGULATOR_LEVEL_NOM>;
+					};
+
+					rpmhpd_opp_nom_l1: opp-320 {
+						opp-level = <RPMH_REGULATOR_LEVEL_NOM_L1>;
+					};
+
+					rpmhpd_opp_nom_l2: opp-336 {
+						opp-level = <RPMH_REGULATOR_LEVEL_NOM_L2>;
+					};
+
+					rpmhpd_opp_turbo: opp-384 {
+						opp-level = <RPMH_REGULATOR_LEVEL_TURBO>;
+					};
+
+					rpmhpd_opp_turbo_l1: opp-416 {
+						opp-level = <RPMH_REGULATOR_LEVEL_TURBO_L1>;
+					};
+				};
+			};
+		};
+
+		cpufreq_hw: cpufreq@17d91000 {
+			compatible = "qcom,sm8650-cpufreq-epss", "qcom,cpufreq-epss";
+			reg = <0 0x17d91000 0 0x1000>,
+			      <0 0x17d92000 0 0x1000>,
+			      <0 0x17d93000 0 0x1000>,
+			      <0 0x17d94000 0 0x1000>;
+			reg-names = "freq-domain0",
+				    "freq-domain1",
+				    "freq-domain2",
+				    "freq-domain3";
+
+			interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 738 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "dcvsh-irq-0",
+					  "dcvsh-irq-1",
+					  "dcvsh-irq-2",
+					  "dcvsh-irq-3";
+
+			clocks = <&bi_tcxo_div2>, <&gcc GCC_GPLL0>;
+			clock-names = "xo", "alternate";
+
+			#freq-domain-cells = <1>;
+			#clock-cells = <1>;
+		};
+
+		pmu@24091000 {
+			compatible = "qcom,sm8650-llcc-bwmon", "qcom,sc7280-llcc-bwmon";
+			reg = <0 0x24091000 0 0x1000>;
+
+			interrupts = <GIC_SPI 81 IRQ_TYPE_LEVEL_HIGH>;
+
+			interconnects = <&mc_virt MASTER_LLCC QCOM_ICC_TAG_ACTIVE_ONLY
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ACTIVE_ONLY>;
+
+			operating-points-v2 = <&llcc_bwmon_opp_table>;
+
+			llcc_bwmon_opp_table: opp-table {
+				compatible = "operating-points-v2";
+
+				opp-0 {
+					opp-peak-kBps = <2086000>;
+				};
+
+				opp-1 {
+					opp-peak-kBps = <2929000>;
+				};
+
+				opp-2 {
+					opp-peak-kBps = <5931000>;
+				};
+
+				opp-3 {
+					opp-peak-kBps = <6515000>;
+				};
+
+				opp-4 {
+					opp-peak-kBps = <7980000>;
+				};
+
+				opp-5 {
+					opp-peak-kBps = <10437000>;
+				};
+
+				opp-6 {
+					opp-peak-kBps = <12157000>;
+				};
+
+				opp-7 {
+					opp-peak-kBps = <14060000>;
+				};
+
+				opp-8 {
+					opp-peak-kBps = <16113000>;
+				};
+			};
+		};
+
+		pmu@240b7400 {
+			compatible = "qcom,sm8650-cpu-bwmon", "qcom,sdm845-bwmon";
+			reg = <0 0x240b7400 0 0x600>;
+
+			interrupts = <GIC_SPI 581 IRQ_TYPE_LEVEL_HIGH>;
+
+			interconnects = <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ACTIVE_ONLY
+					 &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ACTIVE_ONLY>;
+
+			operating-points-v2 = <&cpu_bwmon_opp_table>;
+
+			cpu_bwmon_opp_table: opp-table {
+				compatible = "operating-points-v2";
+
+				opp-0 {
+					opp-peak-kBps = <4577000>;
+				};
+
+				opp-1 {
+					opp-peak-kBps = <7110000>;
+				};
+
+				opp-2 {
+					opp-peak-kBps = <9155000>;
+				};
+
+				opp-3 {
+					opp-peak-kBps = <12298000>;
+				};
+
+				opp-4 {
+					opp-peak-kBps = <14236000>;
+				};
+
+				opp-5 {
+					opp-peak-kBps = <16265000>;
+				};
+			};
+		};
+
+		gem_noc: interconnect@24100000 {
+			compatible = "qcom,sm8650-gem-noc";
+			reg = <0 0x24100000 0 0xc5080>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		system-cache-controller@25000000 {
+			compatible = "qcom,sm8650-llcc";
+			reg = <0 0x25000000 0 0x200000>,
+			      <0 0x25400000 0 0x200000>,
+			      <0 0x25200000 0 0x200000>,
+			      <0 0x25600000 0 0x200000>,
+			      <0 0x25800000 0 0x200000>;
+			reg-names = "llcc0_base",
+				    "llcc1_base",
+				    "llcc2_base",
+				    "llcc3_base",
+				    "llcc_broadcast_base";
+
+			interrupts = <GIC_SPI 266 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		remoteproc_adsp: remoteproc@30000000 {
+			compatible = "qcom,sm8650-adsp-pas";
+			reg = <0 0x30000000 0 0x100>;
+
+			interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>,
+					      <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>,
+					      <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>,
+					      <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>,
+					      <&smp2p_adsp_in 3 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "wdog",
+					  "fatal",
+					  "ready",
+					  "handover",
+					  "stop-ack";
+
+			clocks = <&rpmhcc RPMH_CXO_CLK>;
+			clock-names = "xo";
+
+			interconnects = <&lpass_lpicx_noc MASTER_LPASS_PROC QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+
+			power-domains = <&rpmhpd RPMHPD_LCX>,
+					<&rpmhpd RPMHPD_LMX>;
+			power-domain-names = "lcx",
+					     "lmx";
+
+			memory-region = <&adspslpi_mem>, <&q6_adsp_dtb_mem>;
+
+			qcom,qmp = <&aoss_qmp>;
+
+			qcom,smem-states = <&smp2p_adsp_out 0>;
+			qcom,smem-state-names = "stop";
+
+			status = "disabled";
+
+			remoteproc_adsp_glink: glink-edge {
+				interrupts-extended = <&ipcc IPCC_CLIENT_LPASS
+							     IPCC_MPROC_SIGNAL_GLINK_QMP
+							     IRQ_TYPE_EDGE_RISING>;
+
+				mboxes = <&ipcc IPCC_CLIENT_LPASS
+						IPCC_MPROC_SIGNAL_GLINK_QMP>;
+
+				qcom,remote-pid = <2>;
+
+				label = "lpass";
+
+				fastrpc {
+					compatible = "qcom,fastrpc";
+
+					qcom,glink-channels = "fastrpcglink-apps-dsp";
+
+					label = "adsp";
+
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					compute-cb@3 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <3>;
+
+						iommus = <&apps_smmu 0x1003 0x80>,
+							 <&apps_smmu 0x1043 0x20>;
+					};
+
+					compute-cb@4 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <4>;
+
+						iommus = <&apps_smmu 0x1004 0x80>,
+							 <&apps_smmu 0x1044 0x20>;
+					};
+
+					compute-cb@5 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <5>;
+
+						iommus = <&apps_smmu 0x1005 0x80>,
+							 <&apps_smmu 0x1045 0x20>;
+					};
+
+					compute-cb@6 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <6>;
+
+						iommus = <&apps_smmu 0x1006 0x80>,
+							 <&apps_smmu 0x1046 0x20>;
+					};
+
+					compute-cb@7 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <7>;
+
+						iommus = <&apps_smmu 0x1007 0x40>,
+							 <&apps_smmu 0x1067 0x0>,
+							 <&apps_smmu 0x1087 0x0>;
+					};
+				};
+
+				gpr {
+					compatible = "qcom,gpr";
+					qcom,glink-channels = "adsp_apps";
+					qcom,domain = <GPR_DOMAIN_ID_ADSP>;
+					qcom,intents = <512 20>;
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					q6apm: service@1 {
+						compatible = "qcom,q6apm";
+						reg = <GPR_APM_MODULE_IID>;
+						#sound-dai-cells = <0>;
+						qcom,protection-domain = "avs/audio",
+									 "msm/adsp/audio_pd";
+
+						q6apmbedai: bedais {
+							compatible = "qcom,q6apm-lpass-dais";
+							#sound-dai-cells = <1>;
+						};
+
+						q6apmdai: dais {
+							compatible = "qcom,q6apm-dais";
+							iommus = <&apps_smmu 0x1001 0x80>,
+								 <&apps_smmu 0x1061 0x0>;
+						};
+					};
+
+					q6prm: service@2 {
+						compatible = "qcom,q6prm";
+						reg = <GPR_PRM_MODULE_IID>;
+						qcom,protection-domain = "avs/audio",
+									 "msm/adsp/audio_pd";
+
+						q6prmcc: clock-controller {
+							compatible = "qcom,q6prm-lpass-clocks";
+							#clock-cells = <2>;
+						};
+					};
+				};
+			};
+		};
+
+		nsp_noc: interconnect@320c0000 {
+			compatible = "qcom,sm8650-nsp-noc";
+			reg = <0 0x320c0000 0 0xf080>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		remoteproc_cdsp: remoteproc@32300000 {
+			compatible = "qcom,sm8650-cdsp-pas";
+			reg = <0 0x32300000 0 0x1400000>;
+
+			interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>,
+					      <&smp2p_cdsp_in 0 IRQ_TYPE_EDGE_RISING>,
+					      <&smp2p_cdsp_in 1 IRQ_TYPE_EDGE_RISING>,
+					      <&smp2p_cdsp_in 2 IRQ_TYPE_EDGE_RISING>,
+					      <&smp2p_cdsp_in 3 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "wdog",
+					  "fatal",
+					  "ready",
+					  "handover",
+					  "stop-ack";
+
+			clocks = <&rpmhcc RPMH_CXO_CLK>;
+			clock-names = "xo";
+
+			interconnects = <&nsp_noc MASTER_CDSP_PROC QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+
+			power-domains = <&rpmhpd RPMHPD_CX>,
+					<&rpmhpd RPMHPD_MXC>,
+					<&rpmhpd RPMHPD_NSP>;
+			power-domain-names = "cx",
+					     "mxc",
+					     "nsp";
+
+			memory-region = <&cdsp_mem>, <&q6_cdsp_dtb_mem>, <&global_sync_mem>;
+
+			qcom,qmp = <&aoss_qmp>;
+
+			qcom,smem-states = <&smp2p_cdsp_out 0>;
+			qcom,smem-state-names = "stop";
+
+			status = "disabled";
+
+			glink-edge {
+				interrupts-extended = <&ipcc IPCC_CLIENT_CDSP
+							     IPCC_MPROC_SIGNAL_GLINK_QMP
+							     IRQ_TYPE_EDGE_RISING>;
+
+				mboxes = <&ipcc IPCC_CLIENT_CDSP
+						IPCC_MPROC_SIGNAL_GLINK_QMP>;
+
+				qcom,remote-pid = <5>;
+
+				label = "cdsp";
+
+				fastrpc {
+					compatible = "qcom,fastrpc";
+
+					qcom,glink-channels = "fastrpcglink-apps-dsp";
+
+					label = "cdsp";
+
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					compute-cb@1 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <1>;
+
+						iommus = <&apps_smmu 0x1961 0x0>,
+							 <&apps_smmu 0x0c01 0x20>,
+							 <&apps_smmu 0x19c1 0x0>;
+					};
+
+					compute-cb@2 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <2>;
+
+						iommus = <&apps_smmu 0x1962 0x0>,
+							 <&apps_smmu 0x0c02 0x20>,
+							 <&apps_smmu 0x19c2 0x0>;
+					};
+
+					compute-cb@3 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <3>;
+
+						iommus = <&apps_smmu 0x1963 0x0>,
+							 <&apps_smmu 0x0c03 0x20>,
+							 <&apps_smmu 0x19c3 0x0>;
+					};
+
+					compute-cb@4 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <4>;
+
+						iommus = <&apps_smmu 0x1964 0x0>,
+							 <&apps_smmu 0x0c04 0x20>,
+							 <&apps_smmu 0x19c4 0x0>;
+					};
+
+					compute-cb@5 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <5>;
+
+						iommus = <&apps_smmu 0x1965 0x0>,
+							 <&apps_smmu 0x0c05 0x20>,
+							 <&apps_smmu 0x19c5 0x0>;
+					};
+
+					compute-cb@6 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <6>;
+
+						iommus = <&apps_smmu 0x1966 0x0>,
+							 <&apps_smmu 0x0c06 0x20>,
+							 <&apps_smmu 0x19c6 0x0>;
+					};
+
+					compute-cb@7 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <7>;
+
+						iommus = <&apps_smmu 0x1967 0x0>,
+							 <&apps_smmu 0x0c07 0x20>,
+							 <&apps_smmu 0x19c7 0x0>;
+					};
+
+					compute-cb@8 {
+						compatible = "qcom,fastrpc-compute-cb";
+						reg = <8>;
+
+						iommus = <&apps_smmu 0x1968 0x0>,
+							 <&apps_smmu 0x0c08 0x20>,
+							 <&apps_smmu 0x19c8 0x0>;
+					};
+				};
+			};
+		};
+	};
+
+	thermal-zones {
+		aoss0-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens0 0>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				aoss0-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpuss0-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens0 1>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				cpuss0-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpuss1-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens0 2>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				cpuss1-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpuss2-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens0 3>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				cpuss2-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpuss3-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens0 4>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				cpuss3-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpu2-top-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens0 5>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu2-critical {
+					temperature = <110000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpu2-bottom-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens0 6>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu2-critical {
+					temperature = <110000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpu3-top-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens0 7>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu3-critical {
+					temperature = <110000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpu3-bottom-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens0 8>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu3-critical {
+					temperature = <110000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpu4-top-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens0 9>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu4-critical {
+					temperature = <110000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpu4-bottom-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens0 10>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu4-critical {
+					temperature = <110000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpu5-top-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens0 11>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu5-critical {
+					temperature = <110000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpu5-bottom-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens0 12>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu5-critical {
+					temperature = <110000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpu6-top-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens0 13>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu6-critical {
+					temperature = <110000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpu6-bottom-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens0 14>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu6-critical {
+					temperature = <110000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+
+		aoss1-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens1 0>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				aoss1-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpu7-top-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens1 1>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu7-critical {
+					temperature = <110000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpu7-middle-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens1 2>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu7-critical {
+					temperature = <110000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpu7-bottom-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens1 3>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu7-critical {
+					temperature = <110000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpu0-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens1 4>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu0-critical {
+					temperature = <110000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpu1-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens1 5>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				trip-point1 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu1-critical {
+					temperature = <110000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+
+		nsphvx0-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens2 6>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				nsphvx1-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		nsphvx1-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens2 7>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				nsphvx1-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		nsphmx0-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens2 8>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				nsphmx0-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		nsphmx1-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens2 9>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				nsphmx1-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		nsphmx2-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens2 10>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				nsphmx2-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		nsphmx3-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens2 11>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				nsphmx3-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		video-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens1 12>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				video-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		ddr-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens1 13>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				ddr-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		camera0-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens1 14>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				camera0-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		camera1-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens1 15>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				camera1-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		aoss2-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens2 0>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				aoss2-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		gpuss0-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens2 1>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				gpuss0-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		gpuss1-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens2 2>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				gpuss1-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		gpuss2-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens2 3>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				gpuss2-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		gpuss3-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens2 4>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				gpuss3-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		gpuss4-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens2 5>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				gpuss4-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		gpuss5-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens2 6>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				gpuss5-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		gpuss6-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens2 7>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				gpuss6-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		gpuss7-thermal {
+			polling-delay-passive = <10>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens2 8>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				gpuss7-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		modem0-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens2 9>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				modem0-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		modem1-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens2 10>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				modem1-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		modem2-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens2 11>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				modem2-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		modem3-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tsens2 12>;
+
+			trips {
+				trip-point0 {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
+				modem3-critical {
+					temperature = <110000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+
+		interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>;
+	};
+};
diff --git a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
new file mode 100644
index 000000000000..7532d8eca2de
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
@@ -0,0 +1,424 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/regulator/qcom,rpmh-regulator.h>
+
+#include "x1e80100.dtsi"
+
+/ {
+	model = "Qualcomm Technologies, Inc. X1E80100 CRD";
+	compatible = "qcom,x1e80100-crd", "qcom,x1e80100";
+
+	aliases {
+		serial0 = &uart21;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	vph_pwr: vph-pwr-regulator {
+		compatible = "regulator-fixed";
+
+		regulator-name = "vph_pwr";
+		regulator-min-microvolt = <3700000>;
+		regulator-max-microvolt = <3700000>;
+
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	vreg_edp_3p3: regulator-edp-3p3 {
+		compatible = "regulator-fixed";
+
+		regulator-name = "VREG_EDP_3P3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+
+		gpio = <&tlmm 70 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+
+		pinctrl-0 = <&edp_reg_en>;
+		pinctrl-names = "default";
+
+		regulator-always-on;
+		regulator-boot-on;
+	};
+};
+
+&apps_rsc {
+	regulators-0 {
+		compatible = "qcom,pm8550-rpmh-regulators";
+		qcom,pmic-id = "b";
+
+		vdd-bob1-supply = <&vph_pwr>;
+		vdd-bob2-supply = <&vph_pwr>;
+		vdd-l1-l4-l10-supply = <&vreg_s4c_1p8>;
+		vdd-l2-l13-l14-supply = <&vreg_bob1>;
+		vdd-l5-l16-supply = <&vreg_bob1>;
+		vdd-l6-l7-supply = <&vreg_bob2>;
+		vdd-l8-l9-supply = <&vreg_bob1>;
+		vdd-l12-supply = <&vreg_s5j_1p2>;
+		vdd-l15-supply = <&vreg_s4c_1p8>;
+		vdd-l17-supply = <&vreg_bob2>;
+
+		vreg_bob1: bob1 {
+			regulator-name = "vreg_bob1";
+			regulator-min-microvolt = <3008000>;
+			regulator-max-microvolt = <3960000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_bob2: bob2 {
+			regulator-name = "vreg_bob2";
+			regulator-min-microvolt = <2504000>;
+			regulator-max-microvolt = <3008000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l1b_1p8: ldo1 {
+			regulator-name = "vreg_l1b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2b_3p0: ldo2 {
+			regulator-name = "vreg_l2b_3p0";
+			regulator-min-microvolt = <3072000>;
+			regulator-max-microvolt = <3100000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l4b_1p8: ldo4 {
+			regulator-name = "vreg_l4b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l5b_3p0: ldo5 {
+			regulator-name = "vreg_l5b_3p0";
+			regulator-min-microvolt = <3000000>;
+			regulator-max-microvolt = <3000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6b_1p8: ldo6 {
+			regulator-name = "vreg_l6b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2960000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l7b_2p8: ldo7 {
+			regulator-name = "vreg_l7b_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l8b_3p0: ldo8 {
+			regulator-name = "vreg_l8b_3p0";
+			regulator-min-microvolt = <3072000>;
+			regulator-max-microvolt = <3072000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l9b_2p9: ldo9 {
+			regulator-name = "vreg_l9b_2p9";
+			regulator-min-microvolt = <2960000>;
+			regulator-max-microvolt = <2960000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l10b_1p8: ldo10 {
+			regulator-name = "vreg_l10b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l12b_1p2: ldo12 {
+			regulator-name = "vreg_l12b_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l13b_3p0: ldo13 {
+			regulator-name = "vreg_l13b_3p0";
+			regulator-min-microvolt = <3072000>;
+			regulator-max-microvolt = <3100000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l14b_3p0: ldo14 {
+			regulator-name = "vreg_l14b_3p0";
+			regulator-min-microvolt = <3072000>;
+			regulator-max-microvolt = <3072000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l15b_1p8: ldo15 {
+			regulator-name = "vreg_l15b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l16b_2p9: ldo16 {
+			regulator-name = "vreg_l16b_2p9";
+			regulator-min-microvolt = <2912000>;
+			regulator-max-microvolt = <2912000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l17b_2p5: ldo17 {
+			regulator-name = "vreg_l17b_2p5";
+			regulator-min-microvolt = <2504000>;
+			regulator-max-microvolt = <2504000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-1 {
+		compatible = "qcom,pm8550ve-rpmh-regulators";
+		qcom,pmic-id = "c";
+
+		vdd-l1-supply = <&vreg_s5j_1p2>;
+		vdd-l2-supply = <&vreg_s1f_0p7>;
+		vdd-l3-supply = <&vreg_s1f_0p7>;
+		vdd-s4-supply = <&vph_pwr>;
+
+		vreg_s4c_1p8: smps4 {
+			regulator-name = "vreg_s4c_1p8";
+			regulator-min-microvolt = <1856000>;
+			regulator-max-microvolt = <2000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l1c_1p2: ldo1 {
+			regulator-name = "vreg_l1c_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2c_0p8: ldo2 {
+			regulator-name = "vreg_l2c_0p8";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3c_0p8: ldo3 {
+			regulator-name = "vreg_l3c_0p8";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-2 {
+		compatible = "qcom,pmc8380-rpmh-regulators";
+		qcom,pmic-id = "d";
+
+		vdd-l1-supply = <&vreg_s1f_0p7>;
+		vdd-l2-supply = <&vreg_s1f_0p7>;
+		vdd-l3-supply = <&vreg_s4c_1p8>;
+		vdd-s1-supply = <&vph_pwr>;
+
+		vreg_l1d_0p8: ldo1 {
+			regulator-name = "vreg_l1d_0p8";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2d_0p9: ldo2 {
+			regulator-name = "vreg_l2d_0p9";
+			regulator-min-microvolt = <912000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3d_1p8: ldo3 {
+			regulator-name = "vreg_l3d_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-3 {
+		compatible = "qcom,pmc8380-rpmh-regulators";
+		qcom,pmic-id = "e";
+
+		vdd-l2-supply = <&vreg_s1f_0p7>;
+		vdd-l3-supply = <&vreg_s5j_1p2>;
+
+		vreg_l2e_0p8: ldo2 {
+			regulator-name = "vreg_l2e_0p8";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3e_1p2: ldo3 {
+			regulator-name = "vreg_l3e_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-4 {
+		compatible = "qcom,pmc8380-rpmh-regulators";
+		qcom,pmic-id = "f";
+
+		vdd-l1-supply = <&vreg_s5j_1p2>;
+		vdd-l2-supply = <&vreg_s5j_1p2>;
+		vdd-l3-supply = <&vreg_s5j_1p2>;
+		vdd-s1-supply = <&vph_pwr>;
+
+		vreg_s1f_0p7: smps1 {
+			regulator-name = "vreg_s1f_0p7";
+			regulator-min-microvolt = <700000>;
+			regulator-max-microvolt = <1100000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l1f_1p0: ldo1 {
+			regulator-name = "vreg_l1f_1p0";
+			regulator-min-microvolt = <1024000>;
+			regulator-max-microvolt = <1024000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2f_1p0: ldo2 {
+			regulator-name = "vreg_l2f_1p0";
+			regulator-min-microvolt = <1024000>;
+			regulator-max-microvolt = <1024000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3f_1p0: ldo3 {
+			regulator-name = "vreg_l3f_1p0";
+			regulator-min-microvolt = <1024000>;
+			regulator-max-microvolt = <1024000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-6 {
+		compatible = "qcom,pm8550ve-rpmh-regulators";
+		qcom,pmic-id = "i";
+
+		vdd-l1-supply = <&vreg_s4c_1p8>;
+		vdd-l2-supply = <&vreg_s5j_1p2>;
+		vdd-l3-supply = <&vreg_s1f_0p7>;
+		vdd-s1-supply = <&vph_pwr>;
+		vdd-s2-supply = <&vph_pwr>;
+
+		vreg_s1i_0p9: smps1 {
+			regulator-name = "vreg_s1i_0p9";
+			regulator-min-microvolt = <900000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s2i_1p0: smps2 {
+			regulator-name = "vreg_s2i_1p0";
+			regulator-min-microvolt = <1000000>;
+			regulator-max-microvolt = <1100000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l1i_1p8: ldo1 {
+			regulator-name = "vreg_l1i_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2i_1p2: ldo2 {
+			regulator-name = "vreg_l2i_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3i_0p8: ldo3 {
+			regulator-name = "vreg_l3i_0p8";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-7 {
+		compatible = "qcom,pm8550ve-rpmh-regulators";
+		qcom,pmic-id = "j";
+
+		vdd-l1-supply = <&vreg_s1f_0p7>;
+		vdd-l2-supply = <&vreg_s5j_1p2>;
+		vdd-l3-supply = <&vreg_s1f_0p7>;
+		vdd-s5-supply = <&vph_pwr>;
+
+		vreg_s5j_1p2: smps5 {
+			regulator-name = "vreg_s5j_1p2";
+			regulator-min-microvolt = <1256000>;
+			regulator-max-microvolt = <1304000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l1j_0p8: ldo1 {
+			regulator-name = "vreg_l1j_0p8";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2j_1p2: ldo2 {
+			regulator-name = "vreg_l2j_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3j_0p8: ldo3 {
+			regulator-name = "vreg_l3j_0p8";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+};
+
+&qupv3_2 {
+	status = "okay";
+};
+
+&tlmm {
+	gpio-reserved-ranges = <34 2>, /* Unused */
+			       <44 4>, /* SPI (TPM) */
+			       <238 1>; /* UFS Reset */
+
+	edp_reg_en: edp-reg-en-state {
+		pins = "gpio70";
+		function = "gpio";
+		drive-strength = <16>;
+		bias-disable;
+	};
+};
+
+&uart21 {
+	compatible = "qcom,geni-debug-uart";
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
new file mode 100644
index 000000000000..a37ad9475c90
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
@@ -0,0 +1,399 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/regulator/qcom,rpmh-regulator.h>
+
+#include "x1e80100.dtsi"
+
+/ {
+	model = "Qualcomm Technologies, Inc. X1E80100 QCP";
+	compatible = "qcom,x1e80100-qcp", "qcom,x1e80100";
+
+	aliases {
+		serial0 = &uart21;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	vph_pwr: vph-pwr-regulator {
+		compatible = "regulator-fixed";
+
+		regulator-name = "vph_pwr";
+		regulator-min-microvolt = <3700000>;
+		regulator-max-microvolt = <3700000>;
+
+		regulator-always-on;
+		regulator-boot-on;
+	};
+};
+
+&apps_rsc {
+	regulators-0 {
+		compatible = "qcom,pm8550-rpmh-regulators";
+		qcom,pmic-id = "b";
+
+		vdd-bob1-supply = <&vph_pwr>;
+		vdd-bob2-supply = <&vph_pwr>;
+		vdd-l1-l4-l10-supply = <&vreg_s4c_1p8>;
+		vdd-l2-l13-l14-supply = <&vreg_bob1>;
+		vdd-l5-l16-supply = <&vreg_bob1>;
+		vdd-l6-l7-supply = <&vreg_bob2>;
+		vdd-l8-l9-supply = <&vreg_bob1>;
+		vdd-l12-supply = <&vreg_s5j_1p2>;
+		vdd-l15-supply = <&vreg_s4c_1p8>;
+		vdd-l17-supply = <&vreg_bob2>;
+
+		vreg_bob1: bob1 {
+			regulator-name = "vreg_bob1";
+			regulator-min-microvolt = <3008000>;
+			regulator-max-microvolt = <3960000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_bob2: bob2 {
+			regulator-name = "vreg_bob2";
+			regulator-min-microvolt = <2504000>;
+			regulator-max-microvolt = <3008000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l1b_1p8: ldo1 {
+			regulator-name = "vreg_l1b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2b_3p0: ldo2 {
+			regulator-name = "vreg_l2b_3p0";
+			regulator-min-microvolt = <3072000>;
+			regulator-max-microvolt = <3100000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l4b_1p8: ldo4 {
+			regulator-name = "vreg_l4b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l5b_3p0: ldo5 {
+			regulator-name = "vreg_l5b_3p0";
+			regulator-min-microvolt = <3000000>;
+			regulator-max-microvolt = <3000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6b_1p8: ldo6 {
+			regulator-name = "vreg_l6b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2960000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l7b_2p8: ldo7 {
+			regulator-name = "vreg_l7b_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l8b_3p0: ldo8 {
+			regulator-name = "vreg_l8b_3p0";
+			regulator-min-microvolt = <3072000>;
+			regulator-max-microvolt = <3072000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l9b_2p9: ldo9 {
+			regulator-name = "vreg_l9b_2p9";
+			regulator-min-microvolt = <2960000>;
+			regulator-max-microvolt = <2960000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l10b_1p8: ldo10 {
+			regulator-name = "vreg_l10b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l12b_1p2: ldo12 {
+			regulator-name = "vreg_l12b_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l13b_3p0: ldo13 {
+			regulator-name = "vreg_l13b_3p0";
+			regulator-min-microvolt = <3072000>;
+			regulator-max-microvolt = <3100000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l14b_3p0: ldo14 {
+			regulator-name = "vreg_l14b_3p0";
+			regulator-min-microvolt = <3072000>;
+			regulator-max-microvolt = <3072000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l15b_1p8: ldo15 {
+			regulator-name = "vreg_l15b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l16b_2p9: ldo16 {
+			regulator-name = "vreg_l16b_2p9";
+			regulator-min-microvolt = <2912000>;
+			regulator-max-microvolt = <2912000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l17b_2p5: ldo17 {
+			regulator-name = "vreg_l17b_2p5";
+			regulator-min-microvolt = <2504000>;
+			regulator-max-microvolt = <2504000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-1 {
+		compatible = "qcom,pm8550ve-rpmh-regulators";
+		qcom,pmic-id = "c";
+
+		vdd-l1-supply = <&vreg_s5j_1p2>;
+		vdd-l2-supply = <&vreg_s1f_0p7>;
+		vdd-l3-supply = <&vreg_s1f_0p7>;
+		vdd-s4-supply = <&vph_pwr>;
+
+		vreg_s4c_1p8: smps4 {
+			regulator-name = "vreg_s4c_1p8";
+			regulator-min-microvolt = <1856000>;
+			regulator-max-microvolt = <2000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l1c_1p2: ldo1 {
+			regulator-name = "vreg_l1c_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2c_0p8: ldo2 {
+			regulator-name = "vreg_l2c_0p8";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3c_0p8: ldo3 {
+			regulator-name = "vreg_l3c_0p8";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-2 {
+		compatible = "qcom,pmc8380-rpmh-regulators";
+		qcom,pmic-id = "d";
+
+		vdd-l1-supply = <&vreg_s1f_0p7>;
+		vdd-l2-supply = <&vreg_s1f_0p7>;
+		vdd-l3-supply = <&vreg_s4c_1p8>;
+		vdd-s1-supply = <&vph_pwr>;
+
+		vreg_l1d_0p8: ldo1 {
+			regulator-name = "vreg_l1d_0p8";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2d_0p9: ldo2 {
+			regulator-name = "vreg_l2d_0p9";
+			regulator-min-microvolt = <912000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3d_1p8: ldo3 {
+			regulator-name = "vreg_l3d_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-3 {
+		compatible = "qcom,pmc8380-rpmh-regulators";
+		qcom,pmic-id = "e";
+
+		vdd-l2-supply = <&vreg_s1f_0p7>;
+		vdd-l3-supply = <&vph_pwr>;
+
+		vreg_l2e_0p8: ldo2 {
+			regulator-name = "vreg_l2e_0p8";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3e_1p2: ldo3 {
+			regulator-name = "vreg_l3e_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-4 {
+		compatible = "qcom,pmc8380-rpmh-regulators";
+		qcom,pmic-id = "f";
+
+		vdd-l1-supply = <&vreg_s5j_1p2>;
+		vdd-l2-supply = <&vreg_s5j_1p2>;
+		vdd-l3-supply = <&vreg_s5j_1p2>;
+		vdd-s1-supply = <&vph_pwr>;
+
+		vreg_s1f_0p7: smps1 {
+			regulator-name = "vreg_s1f_0p7";
+			regulator-min-microvolt = <700000>;
+			regulator-max-microvolt = <1100000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l1f_1p0: ldo1 {
+			regulator-name = "vreg_l1f_1p0";
+			regulator-min-microvolt = <1024000>;
+			regulator-max-microvolt = <1024000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2f_1p0: ldo2 {
+			regulator-name = "vreg_l2f_1p0";
+			regulator-min-microvolt = <1024000>;
+			regulator-max-microvolt = <1024000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3f_1p0: ldo3 {
+			regulator-name = "vreg_l3f_1p0";
+			regulator-min-microvolt = <1024000>;
+			regulator-max-microvolt = <1024000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-6 {
+		compatible = "qcom,pm8550ve-rpmh-regulators";
+		qcom,pmic-id = "i";
+
+		vdd-l1-supply = <&vreg_s4c_1p8>;
+		vdd-l2-supply = <&vreg_s5j_1p2>;
+		vdd-l3-supply = <&vreg_s1f_0p7>;
+		vdd-s1-supply = <&vph_pwr>;
+		vdd-s2-supply = <&vph_pwr>;
+
+		vreg_s1i_0p9: smps1 {
+			regulator-name = "vreg_s1i_0p9";
+			regulator-min-microvolt = <900000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s2i_1p0: smps2 {
+			regulator-name = "vreg_s2i_1p0";
+			regulator-min-microvolt = <1000000>;
+			regulator-max-microvolt = <1100000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l1i_1p8: ldo1 {
+			regulator-name = "vreg_l1i_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2i_1p2: ldo2 {
+			regulator-name = "vreg_l2i_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3i_0p8: ldo3 {
+			regulator-name = "vreg_l3i_0p8";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-7 {
+		compatible = "qcom,pm8550ve-rpmh-regulators";
+		qcom,pmic-id = "j";
+
+		vdd-l1-supply = <&vreg_s1f_0p7>;
+		vdd-l2-supply = <&vph_pwr>;
+		vdd-l3-supply = <&vreg_s1f_0p7>;
+		vdd-s5-supply = <&vph_pwr>;
+
+		vreg_s5j_1p2: smps5 {
+			regulator-name = "vreg_s5j_1p2";
+			regulator-min-microvolt = <1256000>;
+			regulator-max-microvolt = <1304000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l1j_0p8: ldo1 {
+			regulator-name = "vreg_l1j_0p8";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2j_1p2: ldo2 {
+			regulator-name = "vreg_l2j_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3j_0p8: ldo3 {
+			regulator-name = "vreg_l3j_0p8";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+};
+
+&qupv3_2 {
+	status = "okay";
+};
+
+&tlmm {
+	gpio-reserved-ranges = <33 3>, /* Unused */
+			       <44 4>, /* SPI (TPM) */
+			       <238 1>; /* UFS Reset */
+};
+
+&uart21 {
+	compatible = "qcom,geni-debug-uart";
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/qcom/x1e80100.dtsi b/arch/arm64/boot/dts/qcom/x1e80100.dtsi
new file mode 100644
index 000000000000..6f75fc342ceb
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/x1e80100.dtsi
@@ -0,0 +1,3527 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include <dt-bindings/clock/qcom,rpmh.h>
+#include <dt-bindings/clock/qcom,x1e80100-gcc.h>
+#include <dt-bindings/dma/qcom-gpi.h>
+#include <dt-bindings/interconnect/qcom,icc.h>
+#include <dt-bindings/interconnect/qcom,x1e80100-rpmh.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/power/qcom,rpmhpd.h>
+#include <dt-bindings/power/qcom-rpmpd.h>
+#include <dt-bindings/soc/qcom,rpmh-rsc.h>
+
+/ {
+	interrupt-parent = <&intc>;
+
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen { };
+
+	clocks {
+		xo_board: xo-board {
+			compatible = "fixed-clock";
+			clock-frequency = <76800000>;
+			#clock-cells = <0>;
+		};
+
+		sleep_clk: sleep-clk {
+			compatible = "fixed-clock";
+			clock-frequency = <32000>;
+			#clock-cells = <0>;
+		};
+
+		bi_tcxo_div2: bi-tcxo-div2-clk {
+			compatible = "fixed-factor-clock";
+			#clock-cells = <0>;
+
+			clocks = <&rpmhcc RPMH_CXO_CLK>;
+			clock-mult = <1>;
+			clock-div = <2>;
+		};
+
+		bi_tcxo_ao_div2: bi-tcxo-ao-div2-clk {
+			compatible = "fixed-factor-clock";
+			#clock-cells = <0>;
+
+			clocks = <&rpmhcc RPMH_CXO_CLK_A>;
+			clock-mult = <1>;
+			clock-div = <2>;
+		};
+	};
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		CPU0: cpu@0 {
+			device_type = "cpu";
+			compatible = "qcom,oryon";
+			reg = <0x0 0x0>;
+			enable-method = "psci";
+			next-level-cache = <&L2_0>;
+			power-domains = <&CPU_PD0>;
+			power-domain-names = "psci";
+			cpu-idle-states = <&CLUSTER_C4>;
+
+			L2_0: l2-cache {
+				compatible = "cache";
+				cache-level = <2>;
+				cache-unified;
+			};
+		};
+
+		CPU1: cpu@100 {
+			device_type = "cpu";
+			compatible = "qcom,oryon";
+			reg = <0x0 0x100>;
+			enable-method = "psci";
+			next-level-cache = <&L2_0>;
+			power-domains = <&CPU_PD1>;
+			power-domain-names = "psci";
+			cpu-idle-states = <&CLUSTER_C4>;
+		};
+
+		CPU2: cpu@200 {
+			device_type = "cpu";
+			compatible = "qcom,oryon";
+			reg = <0x0 0x200>;
+			enable-method = "psci";
+			next-level-cache = <&L2_0>;
+			power-domains = <&CPU_PD2>;
+			power-domain-names = "psci";
+			cpu-idle-states = <&CLUSTER_C4>;
+		};
+
+		CPU3: cpu@300 {
+			device_type = "cpu";
+			compatible = "qcom,oryon";
+			reg = <0x0 0x300>;
+			enable-method = "psci";
+			next-level-cache = <&L2_0>;
+			power-domains = <&CPU_PD3>;
+			power-domain-names = "psci";
+			cpu-idle-states = <&CLUSTER_C4>;
+		};
+
+		CPU4: cpu@10000 {
+			device_type = "cpu";
+			compatible = "qcom,oryon";
+			reg = <0x0 0x10000>;
+			enable-method = "psci";
+			next-level-cache = <&L2_1>;
+			power-domains = <&CPU_PD4>;
+			power-domain-names = "psci";
+			cpu-idle-states = <&CLUSTER_C4>;
+
+			L2_1: l2-cache {
+				compatible = "cache";
+				cache-level = <2>;
+				cache-unified;
+			};
+		};
+
+		CPU5: cpu@10100 {
+			device_type = "cpu";
+			compatible = "qcom,oryon";
+			reg = <0x0 0x10100>;
+			enable-method = "psci";
+			next-level-cache = <&L2_1>;
+			power-domains = <&CPU_PD5>;
+			power-domain-names = "psci";
+			cpu-idle-states = <&CLUSTER_C4>;
+		};
+
+		CPU6: cpu@10200 {
+			device_type = "cpu";
+			compatible = "qcom,oryon";
+			reg = <0x0 0x10200>;
+			enable-method = "psci";
+			next-level-cache = <&L2_1>;
+			power-domains = <&CPU_PD6>;
+			power-domain-names = "psci";
+			cpu-idle-states = <&CLUSTER_C4>;
+		};
+
+		CPU7: cpu@10300 {
+			device_type = "cpu";
+			compatible = "qcom,oryon";
+			reg = <0x0 0x10300>;
+			enable-method = "psci";
+			next-level-cache = <&L2_1>;
+			power-domains = <&CPU_PD7>;
+			power-domain-names = "psci";
+			cpu-idle-states = <&CLUSTER_C4>;
+		};
+
+		CPU8: cpu@20000 {
+			device_type = "cpu";
+			compatible = "qcom,oryon";
+			reg = <0x0 0x20000>;
+			enable-method = "psci";
+			next-level-cache = <&L2_2>;
+			power-domains = <&CPU_PD8>;
+			power-domain-names = "psci";
+			cpu-idle-states = <&CLUSTER_C4>;
+
+			L2_2: l2-cache {
+				compatible = "cache";
+				cache-level = <2>;
+				cache-unified;
+			};
+		};
+
+		CPU9: cpu@20100 {
+			device_type = "cpu";
+			compatible = "qcom,oryon";
+			reg = <0x0 0x20100>;
+			enable-method = "psci";
+			next-level-cache = <&L2_2>;
+			power-domains = <&CPU_PD9>;
+			power-domain-names = "psci";
+			cpu-idle-states = <&CLUSTER_C4>;
+		};
+
+		CPU10: cpu@20200 {
+			device_type = "cpu";
+			compatible = "qcom,oryon";
+			reg = <0x0 0x20200>;
+			enable-method = "psci";
+			next-level-cache = <&L2_2>;
+			power-domains = <&CPU_PD10>;
+			power-domain-names = "psci";
+			cpu-idle-states = <&CLUSTER_C4>;
+		};
+
+		CPU11: cpu@20300 {
+			device_type = "cpu";
+			compatible = "qcom,oryon";
+			reg = <0x0 0x20300>;
+			enable-method = "psci";
+			next-level-cache = <&L2_2>;
+			power-domains = <&CPU_PD11>;
+			power-domain-names = "psci";
+			cpu-idle-states = <&CLUSTER_C4>;
+		};
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&CPU0>;
+				};
+
+				core1 {
+					cpu = <&CPU1>;
+				};
+
+				core2 {
+					cpu = <&CPU2>;
+				};
+
+				core3 {
+					cpu = <&CPU3>;
+				};
+			};
+
+			cluster1 {
+				core0 {
+					cpu = <&CPU4>;
+				};
+
+				core1 {
+					cpu = <&CPU5>;
+				};
+
+				core2 {
+					cpu = <&CPU6>;
+				};
+
+				core3 {
+					cpu = <&CPU7>;
+				};
+			};
+
+			cluster2 {
+				core0 {
+					cpu = <&CPU8>;
+				};
+
+				core1 {
+					cpu = <&CPU9>;
+				};
+
+				core2 {
+					cpu = <&CPU10>;
+				};
+
+				core3 {
+					cpu = <&CPU11>;
+				};
+			};
+		};
+
+		idle-states {
+			entry-method = "psci";
+
+			CLUSTER_C4: cpu-sleep-0 {
+				compatible = "arm,idle-state";
+				idle-state-name = "ret";
+				arm,psci-suspend-param = <0x00000004>;
+				entry-latency-us = <180>;
+				exit-latency-us = <320>;
+				min-residency-us = <1000>;
+			};
+		};
+
+		domain-idle-states {
+			CLUSTER_CL4: cluster-sleep-0 {
+				compatible = "arm,idle-state";
+				idle-state-name = "l2-ret";
+				arm,psci-suspend-param = <0x01000044>;
+				entry-latency-us = <350>;
+				exit-latency-us = <500>;
+				min-residency-us = <2500>;
+			};
+
+			CLUSTER_CL5: cluster-sleep-1 {
+				compatible = "arm,idle-state";
+				idle-state-name = "ret-pll-off";
+				arm,psci-suspend-param = <0x01000054>;
+				entry-latency-us = <2200>;
+				exit-latency-us = <2500>;
+				min-residency-us = <7000>;
+			};
+		};
+	};
+
+	firmware {
+		scm: scm {
+			compatible = "qcom,scm-x1e80100", "qcom,scm";
+			interconnects = <&aggre2_noc MASTER_CRYPTO QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+		};
+	};
+
+	clk_virt: interconnect-0 {
+		compatible = "qcom,x1e80100-clk-virt";
+		#interconnect-cells = <2>;
+		qcom,bcm-voters = <&apps_bcm_voter>;
+	};
+
+	mc_virt: interconnect-1 {
+		compatible = "qcom,x1e80100-mc-virt";
+		#interconnect-cells = <2>;
+		qcom,bcm-voters = <&apps_bcm_voter>;
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		/* We expect the bootloader to fill in the size */
+		reg = <0 0x80000000 0 0>;
+	};
+
+	pmu {
+		compatible = "arm,armv8-pmuv3";
+		interrupts = <GIC_PPI 7 IRQ_TYPE_LEVEL_LOW>;
+	};
+
+	psci {
+		compatible = "arm,psci-1.0";
+		method = "smc";
+
+		CPU_PD0: power-domain-cpu0 {
+			#power-domain-cells = <0>;
+			power-domains = <&CLUSTER_PD0>;
+		};
+
+		CPU_PD1: power-domain-cpu1 {
+			#power-domain-cells = <0>;
+			power-domains = <&CLUSTER_PD0>;
+		};
+
+		CPU_PD2: power-domain-cpu2 {
+			#power-domain-cells = <0>;
+			power-domains = <&CLUSTER_PD0>;
+		};
+
+		CPU_PD3: power-domain-cpu3 {
+			#power-domain-cells = <0>;
+			power-domains = <&CLUSTER_PD0>;
+		};
+
+		CPU_PD4: power-domain-cpu4 {
+			#power-domain-cells = <0>;
+			power-domains = <&CLUSTER_PD1>;
+		};
+
+		CPU_PD5: power-domain-cpu5 {
+			#power-domain-cells = <0>;
+			power-domains = <&CLUSTER_PD1>;
+		};
+
+		CPU_PD6: power-domain-cpu6 {
+			#power-domain-cells = <0>;
+			power-domains = <&CLUSTER_PD1>;
+		};
+
+		CPU_PD7: power-domain-cpu7 {
+			#power-domain-cells = <0>;
+			power-domains = <&CLUSTER_PD1>;
+		};
+
+		CPU_PD8: power-domain-cpu8 {
+			#power-domain-cells = <0>;
+			power-domains = <&CLUSTER_PD2>;
+		};
+
+		CPU_PD9: power-domain-cpu9 {
+			#power-domain-cells = <0>;
+			power-domains = <&CLUSTER_PD2>;
+		};
+
+		CPU_PD10: power-domain-cpu10 {
+			#power-domain-cells = <0>;
+			power-domains = <&CLUSTER_PD2>;
+		};
+
+		CPU_PD11: power-domain-cpu11 {
+			#power-domain-cells = <0>;
+			power-domains = <&CLUSTER_PD2>;
+		};
+
+		CLUSTER_PD0: power-domain-cpu-cluster0 {
+			#power-domain-cells = <0>;
+			domain-idle-states = <&CLUSTER_CL4>, <&CLUSTER_CL5>;
+		};
+
+		CLUSTER_PD1: power-domain-cpu-cluster1 {
+			#power-domain-cells = <0>;
+			domain-idle-states = <&CLUSTER_CL4>, <&CLUSTER_CL5>;
+		};
+
+		CLUSTER_PD2: power-domain-cpu-cluster2 {
+			#power-domain-cells = <0>;
+			domain-idle-states = <&CLUSTER_CL4>, <&CLUSTER_CL5>;
+		};
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		gunyah_hyp_mem: gunyah-hyp@80000000 {
+			reg = <0x0 0x80000000 0x0 0x800000>;
+			no-map;
+		};
+
+		hyp_elf_package_mem: hyp-elf-package@80800000 {
+			reg = <0x0 0x80800000 0x0 0x200000>;
+			no-map;
+		};
+
+		ncc_mem: ncc@80a00000 {
+			reg = <0x0 0x80a00000 0x0 0x400000>;
+			no-map;
+		};
+
+		cpucp_log_mem: cpucp-log@80e00000 {
+			reg = <0x0 0x80e00000 0x0 0x40000>;
+			no-map;
+		};
+
+		cpucp_mem: cpucp@80e40000 {
+			reg = <0x0 0x80e40000 0x0 0x540000>;
+			no-map;
+		};
+
+		reserved-region@81380000 {
+			reg = <0x0 0x81380000 0x0 0x80000>;
+			no-map;
+		};
+
+		tags_mem: tags-region@81400000 {
+			reg = <0x0 0x81400000 0x0 0x1a0000>;
+			no-map;
+		};
+
+		xbl_dtlog_mem: xbl-dtlog@81a00000 {
+			reg = <0x0 0x81a00000 0x0 0x40000>;
+			no-map;
+		};
+
+		xbl_ramdump_mem: xbl-ramdump@81a40000 {
+			reg = <0x0 0x81a40000 0x0 0x1c0000>;
+			no-map;
+		};
+
+		aop_image_mem: aop-image@81c00000 {
+			reg = <0x0 0x81c00000 0x0 0x60000>;
+			no-map;
+		};
+
+		aop_cmd_db_mem: aop-cmd-db@81c60000 {
+			compatible = "qcom,cmd-db";
+			reg = <0x0 0x81c60000 0x0 0x20000>;
+			no-map;
+		};
+
+		aop_config_mem: aop-config@81c80000 {
+			reg = <0x0 0x81c80000 0x0 0x20000>;
+			no-map;
+		};
+
+		tme_crash_dump_mem: tme-crash-dump@81ca0000 {
+			reg = <0x0 0x81ca0000 0x0 0x40000>;
+			no-map;
+		};
+
+		tme_log_mem: tme-log@81ce0000 {
+			reg = <0x0 0x81ce0000 0x0 0x4000>;
+			no-map;
+		};
+
+		uefi_log_mem: uefi-log@81ce4000 {
+			reg = <0x0 0x81ce4000 0x0 0x10000>;
+			no-map;
+		};
+
+		secdata_apss_mem: secdata-apss@81cff000 {
+			reg = <0x0 0x81cff000 0x0 0x1000>;
+			no-map;
+		};
+
+		pdp_ns_shared_mem: pdp-ns-shared@81e00000 {
+			reg = <0x0 0x81e00000 0x0 0x100000>;
+			no-map;
+		};
+
+		gpu_prr_mem: gpu-prr@81f00000 {
+			reg = <0x0 0x81f00000 0x0 0x10000>;
+			no-map;
+		};
+
+		tpm_control_mem: tpm-control@81f10000 {
+			reg = <0x0 0x81f10000 0x0 0x10000>;
+			no-map;
+		};
+
+		usb_ucsi_shared_mem: usb-ucsi-shared@81f20000 {
+			reg = <0x0 0x81f20000 0x0 0x10000>;
+			no-map;
+		};
+
+		pld_pep_mem: pld-pep@81f30000 {
+			reg = <0x0 0x81f30000 0x0 0x6000>;
+			no-map;
+		};
+
+		pld_gmu_mem: pld-gmu@81f36000 {
+			reg = <0x0 0x81f36000 0x0 0x1000>;
+			no-map;
+		};
+
+		pld_pdp_mem: pld-pdp@81f37000 {
+			reg = <0x0 0x81f37000 0x0 0x1000>;
+			no-map;
+		};
+
+		tz_stat_mem: tz-stat@82700000 {
+			reg = <0x0 0x82700000 0x0 0x100000>;
+			no-map;
+		};
+
+		xbl_tmp_buffer_mem: xbl-tmp-buffer@82800000 {
+			reg = <0x0 0x82800000 0x0 0xc00000>;
+			no-map;
+		};
+
+		adsp_rpc_remote_heap_mem: adsp-rpc-remote-heap@84b00000 {
+			reg = <0x0 0x84b00000 0x0 0x800000>;
+			no-map;
+		};
+
+		spu_secure_shared_memory_mem: spu-secure-shared-memory@85300000 {
+			reg = <0x0 0x85300000 0x0 0x80000>;
+			no-map;
+		};
+
+		adsp_boot_dtb_mem: adsp-boot-dtb@866c0000 {
+			reg = <0x0 0x866c0000 0x0 0x40000>;
+			no-map;
+		};
+
+		spss_region_mem: spss-region@86700000 {
+			reg = <0x0 0x86700000 0x0 0x400000>;
+			no-map;
+		};
+
+		adsp_boot_mem: adsp-boot@86b00000 {
+			reg = <0x0 0x86b00000 0x0 0xc00000>;
+			no-map;
+		};
+
+		video_mem: video@87700000 {
+			reg = <0x0 0x87700000 0x0 0x700000>;
+			no-map;
+		};
+
+		adspslpi_mem: adspslpi@87e00000 {
+			reg = <0x0 0x87e00000 0x0 0x3a00000>;
+			no-map;
+		};
+
+		q6_adsp_dtb_mem: q6-adsp-dtb@8b800000 {
+			reg = <0x0 0x8b800000 0x0 0x80000>;
+			no-map;
+		};
+
+		cdsp_mem: cdsp@8b900000 {
+			reg = <0x0 0x8b900000 0x0 0x2000000>;
+			no-map;
+		};
+
+		q6_cdsp_dtb_mem: q6-cdsp-dtb@8d900000 {
+			reg = <0x0 0x8d900000 0x0 0x80000>;
+			no-map;
+		};
+
+		gpu_microcode_mem: gpu-microcode@8d9fe000 {
+			reg = <0x0 0x8d9fe000 0x0 0x2000>;
+			no-map;
+		};
+
+		cvp_mem: cvp@8da00000 {
+			reg = <0x0 0x8da00000 0x0 0x700000>;
+			no-map;
+		};
+
+		camera_mem: camera@8e100000 {
+			reg = <0x0 0x8e100000 0x0 0x800000>;
+			no-map;
+		};
+
+		av1_encoder_mem: av1-encoder@8e900000 {
+			reg = <0x0 0x8e900000 0x0 0x700000>;
+			no-map;
+		};
+
+		reserved-region@8f000000 {
+			reg = <0x0 0x8f000000 0x0 0xa00000>;
+			no-map;
+		};
+
+		wpss_mem: wpss@8fa00000 {
+			reg = <0x0 0x8fa00000 0x0 0x1900000>;
+			no-map;
+		};
+
+		q6_wpss_dtb_mem: q6-wpss-dtb@91300000 {
+			reg = <0x0 0x91300000 0x0 0x80000>;
+			no-map;
+		};
+
+		xbl_sc_mem: xbl-sc@d8000000 {
+			reg = <0x0 0xd8000000 0x0 0x40000>;
+			no-map;
+		};
+
+		reserved-region@d8040000 {
+			reg = <0x0 0xd8040000 0x0 0xa0000>;
+			no-map;
+		};
+
+		qtee_mem: qtee@d80e0000 {
+			reg = <0x0 0xd80e0000 0x0 0x520000>;
+			no-map;
+		};
+
+		ta_mem: ta@d8600000 {
+			reg = <0x0 0xd8600000 0x0 0x8a00000>;
+			no-map;
+		};
+
+		tags_mem1: tags@e1000000 {
+			reg = <0x0 0xe1000000 0x0 0x26a0000>;
+			no-map;
+		};
+
+		llcc_lpi_mem: llcc-lpi@ff800000 {
+			reg = <0x0 0xff800000 0x0 0x600000>;
+			no-map;
+		};
+
+		smem_mem: smem@ffe00000 {
+			compatible = "qcom,smem";
+			reg = <0x0 0xffe00000 0x0 0x200000>;
+			hwlocks = <&tcsr_mutex 3>;
+			no-map;
+		};
+	};
+
+	soc: soc@0 {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <2>;
+		dma-ranges = <0 0 0 0 0x10 0>;
+		ranges = <0 0 0 0 0x10 0>;
+
+		gcc: clock-controller@100000 {
+			compatible = "qcom,x1e80100-gcc";
+			reg = <0 0x00100000 0 0x200000>;
+
+			clocks = <&bi_tcxo_div2>,
+				 <&sleep_clk>,
+				 <0>,
+				 <0>,
+				 <0>,
+				 <0>,
+				 <0>,
+				 <0>,
+				 <0>,
+				 <0>;
+
+			power-domains = <&rpmhpd RPMHPD_CX>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+			#power-domain-cells = <1>;
+		};
+
+		gpi_dma2: dma-controller@800000 {
+			compatible = "qcom,x1e80100-gpi-dma", "qcom,sm6350-gpi-dma";
+			reg = <0 0x00800000 0 0x60000>;
+
+			interrupts = <GIC_SPI 788 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 789 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 790 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 791 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 792 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 793 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 794 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 795 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 796 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 797 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 798 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 799 IRQ_TYPE_LEVEL_HIGH>;
+
+			dma-channels = <12>;
+			dma-channel-mask = <0x3e>;
+			#dma-cells = <3>;
+
+			iommus = <&apps_smmu 0x436 0x0>;
+
+			status = "disabled";
+		};
+
+		qupv3_2: geniqup@8c0000 {
+			compatible = "qcom,geni-se-qup";
+			reg = <0 0x008c0000 0 0x2000>;
+
+			clocks = <&gcc GCC_QUPV3_WRAP_2_M_AHB_CLK>,
+				 <&gcc GCC_QUPV3_WRAP_2_S_AHB_CLK>;
+			clock-names = "m-ahb",
+				      "s-ahb";
+
+			iommus = <&apps_smmu 0x423 0x0>;
+
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+
+			status = "disabled";
+
+			i2c16: i2c@880000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00880000 0 0x4000>;
+
+				interrupts = <GIC_SPI 808 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S0_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 0 QCOM_GPI_I2C>,
+				       <&gpi_dma2 1 0 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c16_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi16: spi@880000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00880000 0 0x4000>;
+
+				interrupts = <GIC_SPI 808 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S0_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 0 QCOM_GPI_SPI>,
+				       <&gpi_dma2 1 0 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi16_data_clk>, <&qup_spi16_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c17: i2c@884000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00884000 0 0x4000>;
+
+				interrupts = <GIC_SPI 809 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S1_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 1 QCOM_GPI_I2C>,
+				       <&gpi_dma2 1 1 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c17_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi17: spi@884000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00884000 0 0x4000>;
+
+				interrupts = <GIC_SPI 809 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S1_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 1 QCOM_GPI_SPI>,
+				       <&gpi_dma2 1 1 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi17_data_clk>, <&qup_spi17_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c18: i2c@888000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00888000 0 0x4000>;
+
+				interrupts = <GIC_SPI 810 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S2_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 2 QCOM_GPI_I2C>,
+				       <&gpi_dma2 1 2 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c18_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi18: spi@888000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00888000 0 0x4000>;
+
+				interrupts = <GIC_SPI 810 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S2_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 2 QCOM_GPI_SPI>,
+				       <&gpi_dma2 1 2 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi18_data_clk>, <&qup_spi18_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c19: i2c@88c000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x0088c000 0 0x4000>;
+
+				interrupts = <GIC_SPI 811 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S3_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 3 QCOM_GPI_I2C>,
+				       <&gpi_dma2 1 3 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c19_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi19: spi@88c000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x0088c000 0 0x4000>;
+
+				interrupts = <GIC_SPI 811 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S3_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 3 QCOM_GPI_SPI>,
+				       <&gpi_dma2 1 3 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi19_data_clk>, <&qup_spi19_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c20: i2c@890000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00890000 0 0x4000>;
+
+				interrupts = <GIC_SPI 812 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S4_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 4 QCOM_GPI_I2C>,
+				       <&gpi_dma2 1 4 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c20_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi20: spi@890000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00890000 0 0x4000>;
+
+				interrupts = <GIC_SPI 812 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S4_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 4 QCOM_GPI_SPI>,
+				       <&gpi_dma2 1 4 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi20_data_clk>, <&qup_spi20_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c21: i2c@894000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00894000 0 0x4000>;
+
+				interrupts = <GIC_SPI 813 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S5_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 5 QCOM_GPI_I2C>,
+				       <&gpi_dma2 1 5 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c21_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi21: spi@894000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00894000 0 0x4000>;
+
+				interrupts = <GIC_SPI 813 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S5_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 5 QCOM_GPI_SPI>,
+				       <&gpi_dma2 1 5 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi21_data_clk>, <&qup_spi21_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			uart21: serial@894000 {
+				compatible = "qcom,geni-uart";
+				reg = <0 0x00894000 0 0x4000>;
+
+				interrupts = <GIC_SPI 813 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S5_CLK>;
+				clock-names = "se";
+
+				interconnects =	<&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config";
+
+				pinctrl-0 = <&qup_uart21_default>;
+				pinctrl-names = "default";
+
+				status = "disabled";
+			};
+
+			i2c22: i2c@898000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00898000 0 0x4000>;
+
+				interrupts = <GIC_SPI 461 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S6_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 6 QCOM_GPI_I2C>,
+				       <&gpi_dma2 1 6 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c22_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi22: spi@898000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00898000 0 0x4000>;
+
+				interrupts = <GIC_SPI 461 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S6_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 6 QCOM_GPI_SPI>,
+				       <&gpi_dma2 1 6 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi22_data_clk>, <&qup_spi22_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c23: i2c@89c000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x0089c000 0 0x4000>;
+
+				interrupts = <GIC_SPI 462 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S7_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 7 QCOM_GPI_I2C>,
+				       <&gpi_dma2 1 7 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c23_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi23: spi@89c000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x0089c000 0 0x4000>;
+
+				interrupts = <GIC_SPI 462 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP2_S7_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma2 0 7 QCOM_GPI_SPI>,
+				       <&gpi_dma2 1 7 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi23_data_clk>, <&qup_spi23_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+		};
+
+		gpi_dma1: dma-controller@a00000 {
+			compatible = "qcom,x1e80100-gpi-dma", "qcom,sm6350-gpi-dma";
+			reg = <0 0x00a00000 0 0x60000>;
+
+			interrupts = <GIC_SPI 776 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 777 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 778 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 779 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 780 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 781 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 782 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 783 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 784 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 785 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 786 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 787 IRQ_TYPE_LEVEL_HIGH>;
+
+			dma-channels = <12>;
+			dma-channel-mask = <0x3e>;
+			#dma-cells = <3>;
+
+			iommus = <&apps_smmu 0x136 0x0>;
+
+			status = "disabled";
+		};
+
+		qupv3_1: geniqup@ac0000 {
+			compatible = "qcom,geni-se-qup";
+			reg = <0 0x00ac0000 0 0x2000>;
+
+			clocks = <&gcc GCC_QUPV3_WRAP_1_M_AHB_CLK>,
+				 <&gcc GCC_QUPV3_WRAP_1_S_AHB_CLK>;
+			clock-names = "m-ahb",
+				      "s-ahb";
+
+			iommus = <&apps_smmu 0x123 0x0>;
+
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+
+			status = "disabled";
+
+			i2c8: i2c@a80000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00a80000 0 0x4000>;
+
+				interrupts = <GIC_SPI 800 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S0_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 0 QCOM_GPI_I2C>,
+				       <&gpi_dma1 1 0 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c8_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi8: spi@a80000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00a80000 0 0x4000>;
+
+				interrupts = <GIC_SPI 800 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S0_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 0 QCOM_GPI_SPI>,
+				       <&gpi_dma1 1 0 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi8_data_clk>, <&qup_spi8_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c9: i2c@a84000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00a84000 0 0x4000>;
+
+				interrupts = <GIC_SPI 801 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S1_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 1 QCOM_GPI_I2C>,
+				       <&gpi_dma1 1 1 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c9_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi9: spi@a84000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00a84000 0 0x4000>;
+
+				interrupts = <GIC_SPI 801 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S1_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 1 QCOM_GPI_SPI>,
+				       <&gpi_dma1 1 1 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi9_data_clk>, <&qup_spi9_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c10: i2c@a88000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00a88000 0 0x4000>;
+
+				interrupts = <GIC_SPI 802 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S2_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 2 QCOM_GPI_I2C>,
+				       <&gpi_dma1 1 2 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c10_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi10: spi@a88000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00a88000 0 0x4000>;
+
+				interrupts = <GIC_SPI 802 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S2_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 2 QCOM_GPI_SPI>,
+				       <&gpi_dma1 1 2 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi10_data_clk>, <&qup_spi10_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c11: i2c@a8c000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00a8c000 0 0x4000>;
+
+				interrupts = <GIC_SPI 803 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S3_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 3 QCOM_GPI_I2C>,
+				       <&gpi_dma1 1 3 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c11_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi11: spi@a8c000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00a8c000 0 0x4000>;
+
+				interrupts = <GIC_SPI 803 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S3_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 3 QCOM_GPI_SPI>,
+				       <&gpi_dma1 1 3 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi11_data_clk>, <&qup_spi11_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c12: i2c@a90000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00a90000 0 0x4000>;
+
+				interrupts = <GIC_SPI 804 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S4_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 4 QCOM_GPI_I2C>,
+				       <&gpi_dma1 1 4 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c12_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi12: spi@a90000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00a90000 0 0x4000>;
+
+				interrupts = <GIC_SPI 804 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S4_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 4 QCOM_GPI_SPI>,
+				       <&gpi_dma1 1 4 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi12_data_clk>, <&qup_spi12_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c13: i2c@a94000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00a94000 0 0x4000>;
+
+				interrupts = <GIC_SPI 805 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S5_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 5 QCOM_GPI_I2C>,
+				       <&gpi_dma1 1 5 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c13_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi13: spi@a94000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00a94000 0 0x4000>;
+
+				interrupts = <GIC_SPI 805 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S5_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 5 QCOM_GPI_SPI>,
+				       <&gpi_dma1 1 5 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi13_data_clk>, <&qup_spi13_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c14: i2c@a98000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00a98000 0 0x4000>;
+
+				interrupts = <GIC_SPI 806 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S6_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 6 QCOM_GPI_I2C>,
+				       <&gpi_dma1 1 6 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c14_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi14: spi@a98000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00a98000 0 0x4000>;
+
+				interrupts = <GIC_SPI 806 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S6_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 6 QCOM_GPI_SPI>,
+				       <&gpi_dma1 1 6 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi14_data_clk>, <&qup_spi14_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c15: i2c@a9c000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00a9c000 0 0x4000>;
+
+				interrupts = <GIC_SPI 807 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S7_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 7 QCOM_GPI_I2C>,
+				       <&gpi_dma1 1 7 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c15_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi15: spi@a9c000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00a9c000 0 0x4000>;
+
+				interrupts = <GIC_SPI 807 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP1_S7_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma1 0 7 QCOM_GPI_SPI>,
+				       <&gpi_dma1 1 7 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi15_data_clk>, <&qup_spi15_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+		};
+
+		gpi_dma0: dma-controller@b00000  {
+			compatible = "qcom,x1e80100-gpi-dma", "qcom,sm6350-gpi-dma";
+			reg = <0 0x00b00000 0 0x60000>;
+
+			interrupts = <GIC_SPI 588 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 589 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 590 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 591 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 592 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 593 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 594 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 595 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 596 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 597 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 598 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 599 IRQ_TYPE_LEVEL_HIGH>;
+
+			dma-channels = <12>;
+			dma-channel-mask = <0x3e>;
+			#dma-cells = <3>;
+
+			iommus = <&apps_smmu 0x456 0x0>;
+
+			status = "disabled";
+		};
+
+		qupv3_0: geniqup@bc0000 {
+			compatible = "qcom,geni-se-qup";
+			reg = <0 0x00bc0000 0 0x2000>;
+
+			clocks = <&gcc GCC_QUPV3_WRAP_0_M_AHB_CLK>,
+				 <&gcc GCC_QUPV3_WRAP_0_S_AHB_CLK>;
+			clock-names = "m-ahb",
+				      "s-ahb";
+
+			iommus = <&apps_smmu 0x443 0x0>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+
+			status = "disabled";
+
+			i2c0: i2c@b80000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0xb80000 0 0x4000>;
+
+				interrupts = <GIC_SPI 373 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP0_S0_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma0 0 0 QCOM_GPI_I2C>,
+				       <&gpi_dma0 1 0 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c0_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi0: spi@b80000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00b80000 0 0x4000>;
+
+				interrupts = <GIC_SPI 373 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP0_S0_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma0 0 0 QCOM_GPI_SPI>,
+				       <&gpi_dma0 1 0 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi0_data_clk>, <&qup_spi0_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c1: i2c@b84000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00b84000 0 0x4000>;
+
+				interrupts = <GIC_SPI 583 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP0_S1_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma0 0 1 QCOM_GPI_I2C>,
+				       <&gpi_dma0 1 1 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c1_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi1: spi@b84000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00b84000 0 0x4000>;
+
+				interrupts = <GIC_SPI 583 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP0_S1_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma0 0 1 QCOM_GPI_SPI>,
+				       <&gpi_dma0 1 1 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi1_data_clk>, <&qup_spi1_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c2: i2c@b88000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00b88000 0 0x4000>;
+
+				interrupts = <GIC_SPI 584 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP0_S2_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma0 0 2 QCOM_GPI_I2C>,
+				       <&gpi_dma0 1 2 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c2_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi2: spi@b88000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0xb88000 0 0x4000>;
+
+				interrupts = <GIC_SPI 584 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP0_S2_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma0 0 2 QCOM_GPI_SPI>,
+				       <&gpi_dma0 1 2 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi2_data_clk>, <&qup_spi2_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c3: i2c@b8c000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00b8c000 0 0x4000>;
+
+				interrupts = <GIC_SPI 585 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP0_S3_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma0 0 3 QCOM_GPI_I2C>,
+				       <&gpi_dma0 1 3 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c3_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi3: spi@b8c000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00b8c000 0 0x4000>;
+
+				interrupts = <GIC_SPI 585 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP0_S3_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma0 0 3 QCOM_GPI_SPI>,
+				       <&gpi_dma0 1 3 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi3_data_clk>, <&qup_spi3_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c4: i2c@b90000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0xb90000 0 0x4000>;
+
+				interrupts = <GIC_SPI 586 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP0_S4_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma0 0 4 QCOM_GPI_I2C>,
+				       <&gpi_dma0 1 4 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c4_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi4: spi@b90000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00b90000 0 0x4000>;
+
+				interrupts = <GIC_SPI 586 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP0_S4_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma0 0 4 QCOM_GPI_SPI>,
+				       <&gpi_dma0 1 4 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi4_data_clk>, <&qup_spi4_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c5: i2c@b94000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00b94000 0 0x4000>;
+
+				interrupts = <GIC_SPI 587 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP0_S5_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma0 0 5 QCOM_GPI_I2C>,
+				       <&gpi_dma0 1 5 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c5_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi5: spi@b94000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00b94000 0 0x4000>;
+
+				interrupts = <GIC_SPI 587 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP0_S5_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma0 0 5 QCOM_GPI_SPI>,
+				       <&gpi_dma0 1 5 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi5_data_clk>, <&qup_spi5_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c6: i2c@b98000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00b98000 0 0x4000>;
+
+				interrupts = <GIC_SPI 461 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP0_S6_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma0 0 6 QCOM_GPI_I2C>,
+				       <&gpi_dma0 1 6 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c6_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi6: spi@b98000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00b98000 0 0x4000>;
+
+				interrupts = <GIC_SPI 461 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP0_S6_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma0 0 6 QCOM_GPI_SPI>,
+				       <&gpi_dma0 1 6 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi6_data_clk>, <&qup_spi6_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			i2c7: i2c@b9c000 {
+				compatible = "qcom,geni-i2c";
+				reg = <0 0x00b9c000 0 0x4000>;
+
+				interrupts = <GIC_SPI 462 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP0_S7_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma0 0 7 QCOM_GPI_I2C>,
+				       <&gpi_dma0 1 7 QCOM_GPI_I2C>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_i2c7_data_clk>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+
+			spi7: spi@b9c000 {
+				compatible = "qcom,geni-spi";
+				reg = <0 0x00b9c000 0 0x4000>;
+
+				interrupts = <GIC_SPI 462 IRQ_TYPE_LEVEL_HIGH>;
+
+				clocks = <&gcc GCC_QUPV3_WRAP0_S7_CLK>;
+				clock-names = "se";
+
+				interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>,
+						<&aggre2_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS
+						 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
+
+				dmas = <&gpi_dma0 0 7 QCOM_GPI_SPI>,
+				       <&gpi_dma0 1 7 QCOM_GPI_SPI>;
+				dma-names = "tx",
+					    "rx";
+
+				pinctrl-0 = <&qup_spi7_data_clk>, <&qup_spi7_cs>;
+				pinctrl-names = "default";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				status = "disabled";
+			};
+		};
+
+		cnoc_main: interconnect@1500000 {
+			compatible = "qcom,x1e80100-cnoc-main";
+			reg = <0 0x1500000 0 0x14400>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		config_noc: interconnect@1600000 {
+			compatible = "qcom,x1e80100-cnoc-cfg";
+			reg = <0 0x1600000 0 0x6600>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		system_noc: interconnect@1680000 {
+			compatible = "qcom,x1e80100-system-noc";
+			reg = <0 0x1680000 0 0x1c080>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		pcie_south_anoc: interconnect@16c0000 {
+			compatible = "qcom,x1e80100-pcie-south-anoc";
+			reg = <0 0x16c0000 0 0xd080>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		pcie_center_anoc: interconnect@16d0000 {
+			compatible = "qcom,x1e80100-pcie-center-anoc";
+			reg = <0 0x16d0000 0 0x7000>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		aggre1_noc: interconnect@16e0000 {
+			compatible = "qcom,x1e80100-aggre1-noc";
+			reg = <0 0x16E0000 0 0x14400>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		aggre2_noc: interconnect@1700000 {
+			compatible = "qcom,x1e80100-aggre2-noc";
+			reg = <0 0x1700000 0 0x1c400>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		pcie_north_anoc: interconnect@1740000 {
+			compatible = "qcom,x1e80100-pcie-north-anoc";
+			reg = <0 0x1740000 0 0x9080>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		usb_center_anoc: interconnect@1750000 {
+			compatible = "qcom,x1e80100-usb-center-anoc";
+			reg = <0 0x1750000 0 0x8800>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		usb_north_anoc: interconnect@1760000 {
+			compatible = "qcom,x1e80100-usb-north-anoc";
+			reg = <0 0x1760000 0 0x7080>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		usb_south_anoc: interconnect@1770000 {
+			compatible = "qcom,x1e80100-usb-south-anoc";
+			reg = <0 0x1770000 0 0xf080>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		mmss_noc: interconnect@1780000 {
+			compatible = "qcom,x1e80100-mmss-noc";
+			reg = <0 0x1780000 0 0x5B800>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		tcsr_mutex: hwlock@1f40000 {
+			compatible = "qcom,tcsr-mutex";
+			reg = <0 0x01f40000 0 0x20000>;
+			#hwlock-cells = <1>;
+		};
+
+		gem_noc: interconnect@26400000 {
+			compatible = "qcom,x1e80100-gem-noc";
+			reg = <0 0x26400000 0 0x311200>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		nsp_noc: interconnect@320c0000 {
+			compatible = "qcom,x1e80100-nsp-noc";
+			reg = <0 0x320C0000 0 0xE080>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		lpass_ag_noc: interconnect@7e40000 {
+			compatible = "qcom,x1e80100-lpass-ag-noc";
+			reg = <0 0x7e40000 0 0xE080>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		lpass_lpiaon_noc: interconnect@7400000 {
+			compatible = "qcom,x1e80100-lpass-lpiaon-noc";
+			reg = <0 0x7400000 0 0x19080>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		lpass_lpicx_noc: interconnect@7430000 {
+			compatible = "qcom,x1e80100-lpass-lpicx-noc";
+			reg = <0 0x7430000 0 0x3A200>;
+
+			qcom,bcm-voters = <&apps_bcm_voter>;
+
+			#interconnect-cells = <2>;
+		};
+
+		pdc: interrupt-controller@b220000 {
+			compatible = "qcom,x1e80100-pdc", "qcom,pdc";
+			reg = <0 0x0b220000 0 0x30000>, <0 0x174000f0 0 0x64>;
+
+			qcom,pdc-ranges = <0 480 42>, <42 251 5>,
+					  <47 522 52>, <99 609 32>,
+					  <131 717 12>, <143 816 19>;
+			#interrupt-cells = <2>;
+			interrupt-parent = <&intc>;
+			interrupt-controller;
+		};
+
+		tlmm: pinctrl@f100000 {
+			compatible = "qcom,x1e80100-tlmm";
+			reg = <0 0x0f100000 0 0xf00000>;
+
+			interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
+
+			gpio-controller;
+			#gpio-cells = <2>;
+
+			interrupt-controller;
+			#interrupt-cells = <2>;
+
+			gpio-ranges = <&tlmm 0 0 239>;
+			wakeup-parent = <&pdc>;
+
+			qup_i2c0_data_clk: qup-i2c0-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio0", "gpio1";
+				function = "qup0_se0";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c1_data_clk: qup-i2c1-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio4", "gpio5";
+				function = "qup0_se1";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c2_data_clk: qup-i2c2-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio8", "gpio9";
+				function = "qup0_se2";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c3_data_clk: qup-i2c3-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio12", "gpio13";
+				function = "qup0_se3";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c4_data_clk: qup-i2c4-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio16", "gpio17";
+				function = "qup0_se4";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c5_data_clk: qup-i2c5-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio20", "gpio21";
+				function = "qup0_se5";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c6_data_clk: qup-i2c6-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio24", "gpio25";
+				function = "qup0_se6";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c7_data_clk: qup-i2c7-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio14", "gpio15";
+				function = "qup0_se7";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c8_data_clk: qup-i2c8-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio32", "gpio33";
+				function = "qup1_se0";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c9_data_clk: qup-i2c9-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio36", "gpio37";
+				function = "qup1_se1";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c10_data_clk: qup-i2c10-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio40", "gpio41";
+				function = "qup1_se2";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c11_data_clk: qup-i2c11-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio44", "gpio45";
+				function = "qup1_se3";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c12_data_clk: qup-i2c12-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio48", "gpio49";
+				function = "qup1_se4";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c13_data_clk: qup-i2c13-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio52", "gpio53";
+				function = "qup1_se5";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c14_data_clk: qup-i2c14-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio56", "gpio57";
+				function = "qup1_se6";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c15_data_clk: qup-i2c15-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio54", "gpio55";
+				function = "qup1_se7";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c16_data_clk: qup-i2c16-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio64", "gpio65";
+				function = "qup2_se0";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c17_data_clk: qup-i2c17-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio68", "gpio69";
+				function = "qup2_se1";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c18_data_clk: qup-i2c18-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio72", "gpio73";
+				function = "qup2_se2";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c19_data_clk: qup-i2c19-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio76", "gpio77";
+				function = "qup2_se3";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c20_data_clk: qup-i2c20-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio80", "gpio81";
+				function = "qup2_se4";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c21_data_clk: qup-i2c21-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio84", "gpio85";
+				function = "qup2_se5";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c22_data_clk: qup-i2c22-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio88", "gpio89";
+				function = "qup2_se6";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_i2c23_data_clk: qup-i2c23-data-clk-state {
+				/* SDA, SCL */
+				pins = "gpio86", "gpio87";
+				function = "qup2_se7";
+				drive-strength = <2>;
+				bias-pull-up = <2200>;
+			};
+
+			qup_spi0_cs: qup-spi0-cs-state {
+				pins = "gpio3";
+				function = "qup0_se0";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi0_data_clk: qup-spi0-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio0", "gpio1", "gpio2";
+				function = "qup0_se0";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi1_cs: qup-spi1-cs-state {
+				pins = "gpio7";
+				function = "qup0_se1";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi1_data_clk: qup-spi1-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio4", "gpio5", "gpio6";
+				function = "qup0_se1";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi2_cs: qup-spi2-cs-state {
+				pins = "gpio11";
+				function = "qup0_se2";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi2_data_clk: qup-spi2-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio8", "gpio9", "gpio10";
+				function = "qup0_se2";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi3_cs: qup-spi3-cs-state {
+				pins = "gpio15";
+				function = "qup0_se3";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi3_data_clk: qup-spi3-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio12", "gpio13", "gpio14";
+				function = "qup0_se3";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi4_cs: qup-spi4-cs-state {
+				pins = "gpio19";
+				function = "qup0_se4";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi4_data_clk: qup-spi4-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio16", "gpio17", "gpio18";
+				function = "qup0_se4";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi5_cs: qup-spi5-cs-state {
+				pins = "gpio23";
+				function = "qup0_se5";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi5_data_clk: qup-spi5-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio20", "gpio21", "gpio22";
+				function = "qup0_se5";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi6_cs: qup-spi6-cs-state {
+				pins = "gpio27";
+				function = "qup0_se6";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi6_data_clk: qup-spi6-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio24", "gpio25", "gpio26";
+				function = "qup0_se6";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi7_cs: qup-spi7-cs-state {
+				pins = "gpio13";
+				function = "qup0_se7";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi7_data_clk: qup-spi7-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio14", "gpio15", "gpio12";
+				function = "qup0_se7";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi8_cs: qup-spi8-cs-state {
+				pins = "gpio35";
+				function = "qup1_se0";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi8_data_clk: qup-spi8-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio32", "gpio33", "gpio34";
+				function = "qup1_se0";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi9_cs: qup-spi9-cs-state {
+				pins = "gpio39";
+				function = "qup1_se1";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi9_data_clk: qup-spi9-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio36", "gpio37", "gpio38";
+				function = "qup1_se1";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi10_cs: qup-spi10-cs-state {
+				pins = "gpio43";
+				function = "qup1_se2";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi10_data_clk: qup-spi10-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio40", "gpio41", "gpio42";
+				function = "qup1_se2";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi11_cs: qup-spi11-cs-state {
+				pins = "gpio47";
+				function = "qup1_se3";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi11_data_clk: qup-spi11-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio44", "gpio45", "gpio46";
+				function = "qup1_se3";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi12_cs: qup-spi12-cs-state {
+				pins = "gpio51";
+				function = "qup1_se4";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi12_data_clk: qup-spi12-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio48", "gpio49", "gpio50";
+				function = "qup1_se4";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi13_cs: qup-spi13-cs-state {
+				pins = "gpio55";
+				function = "qup1_se5";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi13_data_clk: qup-spi13-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio52", "gpio53", "gpio54";
+				function = "qup1_se5";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi14_cs: qup-spi14-cs-state {
+				pins = "gpio59";
+				function = "qup1_se6";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi14_data_clk: qup-spi14-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio56", "gpio57", "gpio58";
+				function = "qup1_se6";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi15_cs: qup-spi15-cs-state {
+				pins = "gpio53";
+				function = "qup1_se7";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi15_data_clk: qup-spi15-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio54", "gpio55", "gpio52";
+				function = "qup1_se7";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi16_cs: qup-spi16-cs-state {
+				pins = "gpio67";
+				function = "qup2_se0";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi16_data_clk: qup-spi16-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio64", "gpio65", "gpio66";
+				function = "qup2_se0";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi17_cs: qup-spi17-cs-state {
+				pins = "gpio71";
+				function = "qup2_se1";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi17_data_clk: qup-spi17-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio68", "gpio69", "gpio70";
+				function = "qup2_se1";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi18_cs: qup-spi18-cs-state {
+				pins = "gpio75";
+				function = "qup2_se2";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi18_data_clk: qup-spi18-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio72", "gpio73", "gpio74";
+				function = "qup2_se2";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi19_cs: qup-spi19-cs-state {
+				pins = "gpio79";
+				function = "qup2_se3";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi19_data_clk: qup-spi19-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio76", "gpio77", "gpio78";
+				function = "qup2_se3";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi20_cs: qup-spi20-cs-state {
+				pins = "gpio83";
+				function = "qup2_se4";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi20_data_clk: qup-spi20-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio80", "gpio81", "gpio82";
+				function = "qup2_se4";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi21_cs: qup-spi21-cs-state {
+				pins = "gpio87";
+				function = "qup2_se5";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi21_data_clk: qup-spi21-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio84", "gpio85", "gpio86";
+				function = "qup2_se5";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi22_cs: qup-spi22-cs-state {
+				pins = "gpio91";
+				function = "qup2_se6";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi22_data_clk: qup-spi22-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio88", "gpio89", "gpio90";
+				function = "qup2_se6";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi23_cs: qup-spi23-cs-state {
+				pins = "gpio85";
+				function = "qup2_se7";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_spi23_data_clk: qup-spi23-data-clk-state {
+				/* MISO, MOSI, CLK */
+				pins = "gpio86", "gpio87", "gpio84";
+				function = "qup2_se7";
+				drive-strength = <6>;
+				bias-disable;
+			};
+
+			qup_uart21_default: qup-uart21-default-state {
+				/* TX, RX */
+				pins = "gpio86", "gpio87";
+				function = "qup2_se5";
+				drive-strength= <2>;
+				bias-disable;
+			};
+		};
+
+		apps_smmu: iommu@15000000 {
+			compatible = "qcom,x1e80100-smmu-500", "qcom,smmu-500", "arm,mmu-500";
+			reg = <0 0x15000000 0 0x100000>;
+
+			interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 104 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 107 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 112 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 113 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 114 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 115 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 181 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 182 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 183 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 184 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 185 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 186 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 187 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 188 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 189 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 190 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 191 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 192 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 315 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 316 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 317 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 318 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 319 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 320 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 321 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 322 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 323 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 324 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 325 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 326 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 327 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 328 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 329 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 330 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 331 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 332 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 333 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 334 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 335 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 336 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 337 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 338 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 339 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 340 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 341 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 342 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 343 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 344 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 345 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 395 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 396 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 397 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 398 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 399 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 400 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 401 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 402 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 403 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 404 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 405 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 406 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 407 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 408 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 409 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 418 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 419 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 412 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 421 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 707 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 423 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 424 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 425 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 690 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 691 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 692 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 693 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 694 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 695 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 696 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 697 IRQ_TYPE_LEVEL_HIGH>;
+
+			#iommu-cells = <2>;
+			#global-interrupts = <1>;
+		};
+
+		intc: interrupt-controller@17000000 {
+			compatible = "arm,gic-v3";
+			reg = <0 0x17000000 0 0x10000>,     /* GICD */
+			      <0 0x17080000 0 0x480000>;    /* GICR * 12 */
+
+			interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH>;
+
+			#interrupt-cells = <3>;
+			interrupt-controller;
+
+			#redistributor-regions = <1>;
+			redistributor-stride = <0x0 0x40000>;
+
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+
+			gic_its: msi-controller@17040000 {
+				compatible = "arm,gic-v3-its";
+				reg = <0 0x17040000 0 0x40000>;
+
+				msi-controller;
+				#msi-cells = <1>;
+
+				status = "disabled";
+			};
+		};
+
+		apps_rsc: rsc@17500000 {
+			compatible = "qcom,rpmh-rsc";
+			reg = <0 0x17500000 0 0x10000>,
+			      <0 0x17510000 0 0x10000>,
+			      <0 0x17520000 0 0x10000>;
+			reg-names = "drv-0", "drv-1", "drv-2";
+			qcom,drv-count = <3>;
+
+			interrupts = <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>;
+			qcom,tcs-offset = <0xd00>;
+			qcom,drv-id = <2>;
+			qcom,tcs-config = <ACTIVE_TCS    3>, <SLEEP_TCS     2>,
+					  <WAKE_TCS      2>, <CONTROL_TCS   0>;
+
+			label = "apps_rsc";
+
+			apps_bcm_voter: bcm-voter {
+				compatible = "qcom,bcm-voter";
+			};
+
+			rpmhcc: clock-controller {
+				compatible = "qcom,x1e80100-rpmh-clk";
+
+				clocks = <&xo_board>;
+				clock-names = "xo";
+
+				#clock-cells = <1>;
+			};
+
+			rpmhpd: power-controller {
+				compatible = "qcom,x1e80100-rpmhpd";
+
+				operating-points-v2 = <&rpmhpd_opp_table>;
+
+				#power-domain-cells = <1>;
+
+				rpmhpd_opp_table: opp-table {
+					compatible = "operating-points-v2";
+
+					rpmhpd_opp_ret: opp-16 {
+						opp-level = <RPMH_REGULATOR_LEVEL_RETENTION>;
+					};
+
+					rpmhpd_opp_min_svs: opp-48 {
+						opp-level = <RPMH_REGULATOR_LEVEL_MIN_SVS>;
+					};
+
+					rpmhpd_opp_low_svs_d2: opp-52 {
+						opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS_D2>;
+					};
+
+					rpmhpd_opp_low_svs_d1: opp-56 {
+						opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS_D1>;
+					};
+
+					rpmhpd_opp_low_svs_d0: opp-60 {
+						opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS_D0>;
+					};
+
+					rpmhpd_opp_low_svs: opp-64 {
+						opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS>;
+					};
+
+					rpmhpd_opp_low_svs_l1: opp-80 {
+						opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS_L1>;
+					};
+
+					rpmhpd_opp_svs: opp-128 {
+						opp-level = <RPMH_REGULATOR_LEVEL_SVS>;
+					};
+
+					rpmhpd_opp_svs_l0: opp-144 {
+						opp-level = <RPMH_REGULATOR_LEVEL_SVS_L0>;
+					};
+
+					rpmhpd_opp_svs_l1: opp-192 {
+						opp-level = <RPMH_REGULATOR_LEVEL_SVS_L1>;
+					};
+
+					rpmhpd_opp_nom: opp-256 {
+						opp-level = <RPMH_REGULATOR_LEVEL_NOM>;
+					};
+
+					rpmhpd_opp_nom_l1: opp-320 {
+						opp-level = <RPMH_REGULATOR_LEVEL_NOM_L1>;
+					};
+
+					rpmhpd_opp_nom_l2: opp-336 {
+						opp-level = <RPMH_REGULATOR_LEVEL_NOM_L2>;
+					};
+
+					rpmhpd_opp_turbo: opp-384 {
+						opp-level = <RPMH_REGULATOR_LEVEL_TURBO>;
+					};
+
+					rpmhpd_opp_turbo_l1: opp-416 {
+						opp-level = <RPMH_REGULATOR_LEVEL_TURBO_L1>;
+					};
+				};
+			};
+		};
+
+		timer@17800000 {
+			compatible = "arm,armv7-timer-mem";
+			reg = <0 0x17800000 0 0x1000>;
+
+			#address-cells = <2>;
+			#size-cells = <1>;
+			ranges = <0 0 0 0 0x20000000>;
+
+			frame@17801000 {
+				reg = <0 0x17801000 0x1000>,
+				      <0 0x17802000 0x1000>;
+
+				interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>;
+
+				frame-number = <0>;
+			};
+
+			frame@17803000 {
+				reg = <0 0x17803000 0x1000>;
+
+				interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>;
+
+				frame-number = <1>;
+
+				status = "disabled";
+			};
+
+			frame@17805000 {
+				reg = <0 0x17805000 0x1000>;
+
+				interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>;
+
+				frame-number = <2>;
+
+				status = "disabled";
+			};
+
+			frame@17807000 {
+				reg = <0 0x17807000 0x1000>;
+
+				interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>;
+
+				frame-number = <3>;
+
+				status = "disabled";
+			};
+
+			frame@17809000 {
+				reg = <0 0x17809000 0x1000>;
+
+				interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>;
+
+				frame-number = <4>;
+
+				status = "disabled";
+			};
+
+			frame@1780b000 {
+				reg = <0 0x1780b000 0x1000>;
+
+				interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>;
+
+				frame-number = <5>;
+
+				status = "disabled";
+			};
+
+			frame@1780d000 {
+				reg = <0 0x1780d000 0x1000>;
+
+				interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
+
+				frame-number = <6>;
+
+				status = "disabled";
+			};
+		};
+
+		system-cache-controller@25000000 {
+			compatible = "qcom,x1e80100-llcc";
+			reg = <0 0x25000000 0 0x200000>,
+			      <0 0x25200000 0 0x200000>,
+			      <0 0x25400000 0 0x200000>,
+			      <0 0x25600000 0 0x200000>,
+			      <0 0x25800000 0 0x200000>,
+			      <0 0x25a00000 0 0x200000>,
+			      <0 0x25c00000 0 0x200000>,
+			      <0 0x25e00000 0 0x200000>,
+			      <0 0x26000000 0 0x200000>;
+			reg-names = "llcc0_base",
+				    "llcc1_base",
+				    "llcc2_base",
+				    "llcc3_base",
+				    "llcc4_base",
+				    "llcc5_base",
+				    "llcc6_base",
+				    "llcc7_base",
+				    "llcc_broadcast_base";
+			interrupts = <GIC_SPI 266 IRQ_TYPE_LEVEL_HIGH>;
+		};
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+
+		interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>;
+	};
+};
diff --git a/arch/arm64/boot/dts/renesas/draak.dtsi b/arch/arm64/boot/dts/renesas/draak.dtsi
index ef3bb835d5c0..6f133f54ded5 100644
--- a/arch/arm64/boot/dts/renesas/draak.dtsi
+++ b/arch/arm64/boot/dts/renesas/draak.dtsi
@@ -356,12 +356,9 @@
 				 * CVBS and HDMI inputs through SW[49-53]
 				 * switches.
 				 *
-				 * CVBS is the default selection, link it to
-				 * VIN4 here.
+				 * HDMI is the default selection, leave CVBS
+				 * not connected here.
 				 */
-				adv7180_out: endpoint {
-					remote-endpoint = <&vin4_in>;
-				};
 			};
 		};
 
@@ -374,6 +371,12 @@
 		interrupt-parent = <&gpio1>;
 		interrupts = <28 IRQ_TYPE_LEVEL_LOW>;
 
+		avdd-supply = <&reg_1p8v>;
+		dvdd-supply = <&reg_1p8v>;
+		pvdd-supply = <&reg_1p8v>;
+		dvdd-3v-supply = <&reg_3p3v>;
+		bgvdd-supply = <&reg_1p8v>;
+
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
 		adi,input-clock = "1x";
@@ -423,13 +426,11 @@
 				 * CVBS and HDMI inputs through SW[49-53]
 				 * switches.
 				 *
-				 * CVBS is the default selection, leave HDMI
-				 * not connected here.
+				 * HDMI is the default selection, link it to
+				 * VIN4 here.
 				 */
 				adv7612_out: endpoint {
-					pclk-sample = <0>;
-					hsync-active = <0>;
-					vsync-active = <0>;
+					remote-endpoint = <&vin4_in>;
 				};
 			};
 		};
@@ -580,8 +581,8 @@
 		function = "usb0";
 	};
 
-	vin4_pins_cvbs: vin4 {
-		groups = "vin4_data8", "vin4_sync", "vin4_clk";
+	vin4_pins: vin4 {
+		groups = "vin4_data24", "vin4_sync", "vin4_clk";
 		function = "vin4";
 	};
 };
@@ -729,7 +730,7 @@
 };
 
 &vin4 {
-	pinctrl-0 = <&vin4_pins_cvbs>;
+	pinctrl-0 = <&vin4_pins>;
 	pinctrl-names = "default";
 
 	status = "okay";
@@ -737,7 +738,10 @@
 	ports {
 		port {
 			vin4_in: endpoint {
-				remote-endpoint = <&adv7180_out>;
+				pclk-sample = <0>;
+				hsync-active = <0>;
+				vsync-active = <0>;
+				remote-endpoint = <&adv7612_out>;
 			};
 		};
 	};
diff --git a/arch/arm64/boot/dts/renesas/ebisu.dtsi b/arch/arm64/boot/dts/renesas/ebisu.dtsi
index f1a5778ef115..cba2fde9dd36 100644
--- a/arch/arm64/boot/dts/renesas/ebisu.dtsi
+++ b/arch/arm64/boot/dts/renesas/ebisu.dtsi
@@ -403,6 +403,12 @@
 		interrupt-parent = <&gpio1>;
 		interrupts = <1 IRQ_TYPE_LEVEL_LOW>;
 
+		avdd-supply = <&reg_1p8v>;
+		dvdd-supply = <&reg_1p8v>;
+		pvdd-supply = <&reg_1p8v>;
+		dvdd-3v-supply = <&reg_3p3v>;
+		bgvdd-supply = <&reg_1p8v>;
+
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
 		adi,input-clock = "1x";
diff --git a/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts b/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts
index 405404c0843d..0608dce92e40 100644
--- a/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts
+++ b/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts
@@ -29,6 +29,15 @@
 		stdout-path = "serial0:115200n8";
 	};
 
+	d1p8: regulator-fixed {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-1.8V";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+
 	d3p3: regulator-fixed {
 		compatible = "regulator-fixed";
 		regulator-name = "fixed-3.3V";
@@ -166,6 +175,12 @@
 		interrupt-parent = <&gpio1>;
 		interrupts = <20 IRQ_TYPE_LEVEL_LOW>;
 
+		avdd-supply = <&d1p8>;
+		dvdd-supply = <&d1p8>;
+		pvdd-supply = <&d1p8>;
+		dvdd-3v-supply = <&d3p3>;
+		bgvdd-supply = <&d1p8>;
+
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
 		adi,input-clock = "1x";
diff --git a/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-cpu.dtsi b/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-cpu.dtsi
index bb4a5270f71b..913f70fe6c5c 100644
--- a/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-cpu.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-cpu.dtsi
@@ -187,6 +187,9 @@
 };
 
 &hscif0 {
+	pinctrl-0 = <&hscif0_pins>;
+	pinctrl-names = "default";
+
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/renesas/r9a08g045.dtsi b/arch/arm64/boot/dts/renesas/r9a08g045.dtsi
index 6c7b29b69d0e..5facfad96158 100644
--- a/arch/arm64/boot/dts/renesas/r9a08g045.dtsi
+++ b/arch/arm64/boot/dts/renesas/r9a08g045.dtsi
@@ -96,6 +96,7 @@
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
+			interrupt-parent = <&irqc>;
 			gpio-ranges = <&pinctrl 0 0 152>;
 			clocks = <&cpg CPG_MOD R9A08G045_GPIO_HCLK>;
 			power-domains = <&cpg>;
@@ -104,6 +105,73 @@
 				 <&cpg R9A08G045_GPIO_SPARE_RESETN>;
 		};
 
+		irqc: interrupt-controller@11050000 {
+			compatible = "renesas,r9a08g045-irqc", "renesas,rzg2l-irqc";
+			#interrupt-cells = <2>;
+			#address-cells = <0>;
+			interrupt-controller;
+			reg = <0 0x11050000 0 0x10000>;
+			interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 1 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 429 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 430 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 431 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 432 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 433 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 434 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 435 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 436 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 437 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 438 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 439 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 440 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 441 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 442 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 443 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 444 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 445 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 446 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 447 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 448 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 449 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 450 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 451 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 452 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 453 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 454 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 455 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 456 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 457 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 458 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 459 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 460 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "nmi",
+					  "irq0", "irq1", "irq2", "irq3",
+					  "irq4", "irq5", "irq6", "irq7",
+					  "tint0", "tint1", "tint2", "tint3",
+					  "tint4", "tint5", "tint6", "tint7",
+					  "tint8", "tint9", "tint10", "tint11",
+					  "tint12", "tint13", "tint14", "tint15",
+					  "tint16", "tint17", "tint18", "tint19",
+					  "tint20", "tint21", "tint22", "tint23",
+					  "tint24", "tint25", "tint26", "tint27",
+					  "tint28", "tint29", "tint30", "tint31",
+					  "bus-err";
+			clocks = <&cpg CPG_MOD R9A08G045_IA55_CLK>,
+				 <&cpg CPG_MOD R9A08G045_IA55_PCLK>;
+			clock-names = "clk", "pclk";
+			power-domains = <&cpg>;
+			resets = <&cpg R9A08G045_IA55_RESETN>;
+		};
+
 		sdhi0: mmc@11c00000  {
 			compatible = "renesas,sdhi-r9a08g045", "renesas,rcar-gen3-sdhi";
 			reg = <0x0 0x11c00000 0 0x10000>;
@@ -149,6 +217,44 @@
 			status = "disabled";
 		};
 
+		eth0: ethernet@11c30000 {
+			compatible = "renesas,r9a08g045-gbeth", "renesas,rzg2l-gbeth";
+			reg = <0 0x11c30000 0 0x10000>;
+			interrupts = <GIC_SPI 68 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 69 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 70 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "mux", "fil", "arp_ns";
+			phy-mode = "rgmii";
+			clocks = <&cpg CPG_MOD R9A08G045_ETH0_CLK_AXI>,
+				 <&cpg CPG_MOD R9A08G045_ETH0_CLK_CHI>,
+				 <&cpg CPG_MOD R9A08G045_ETH0_REFCLK>;
+			clock-names = "axi", "chi", "refclk";
+			resets = <&cpg R9A08G045_ETH0_RST_HW_N>;
+			power-domains = <&cpg>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		eth1: ethernet@11c40000 {
+			compatible = "renesas,r9a08g045-gbeth", "renesas,rzg2l-gbeth";
+			reg = <0 0x11c40000 0 0x10000>;
+			interrupts = <GIC_SPI 71 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "mux", "fil", "arp_ns";
+			phy-mode = "rgmii";
+			clocks = <&cpg CPG_MOD R9A08G045_ETH1_CLK_AXI>,
+				 <&cpg CPG_MOD R9A08G045_ETH1_CLK_CHI>,
+				 <&cpg CPG_MOD R9A08G045_ETH1_REFCLK>;
+			clock-names = "axi", "chi", "refclk";
+			resets = <&cpg R9A08G045_ETH1_RST_HW_N>;
+			power-domains = <&cpg>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
 		gic: interrupt-controller@12400000 {
 			compatible = "arm,gic-v3";
 			#interrupt-cells = <3>;
diff --git a/arch/arm64/boot/dts/renesas/r9a09g011.dtsi b/arch/arm64/boot/dts/renesas/r9a09g011.dtsi
index 33f2ecf42441..50ed66d42a24 100644
--- a/arch/arm64/boot/dts/renesas/r9a09g011.dtsi
+++ b/arch/arm64/boot/dts/renesas/r9a09g011.dtsi
@@ -163,7 +163,7 @@
 		};
 
 		avb: ethernet@a3300000 {
-			compatible = "renesas,etheravb-r9a09g011","renesas,etheravb-rzv2m";
+			compatible = "renesas,etheravb-r9a09g011", "renesas,etheravb-rzv2m";
 			reg = <0 0xa3300000 0 0x800>;
 			interrupts = <GIC_SPI 251 IRQ_TYPE_LEVEL_HIGH>, /* ch0: Rx0 BE */
 				     <GIC_SPI 252 IRQ_TYPE_LEVEL_HIGH>, /* ch1: Rx1 NC */
diff --git a/arch/arm64/boot/dts/renesas/rzg2l-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg2l-smarc-som.dtsi
index 547859c388ce..4409c47239b9 100644
--- a/arch/arm64/boot/dts/renesas/rzg2l-smarc-som.dtsi
+++ b/arch/arm64/boot/dts/renesas/rzg2l-smarc-som.dtsi
@@ -312,6 +312,7 @@
 		m25p,fast-read;
 		spi-max-frequency = <50000000>;
 		spi-rx-bus-width = <4>;
+		spi-tx-bus-width = <4>;
 
 		partitions {
 			compatible = "fixed-partitions";
diff --git a/arch/arm64/boot/dts/renesas/rzg2lc-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg2lc-smarc-som.dtsi
index 56ff92453976..5e4209d6fb42 100644
--- a/arch/arm64/boot/dts/renesas/rzg2lc-smarc-som.dtsi
+++ b/arch/arm64/boot/dts/renesas/rzg2lc-smarc-som.dtsi
@@ -241,6 +241,7 @@
 		m25p,fast-read;
 		spi-max-frequency = <50000000>;
 		spi-rx-bus-width = <4>;
+		spi-tx-bus-width = <4>;
 
 		partitions {
 			compatible = "fixed-partitions";
diff --git a/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi
index a199de8f8b02..f062d4ad78b7 100644
--- a/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi
+++ b/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi
@@ -9,18 +9,36 @@
 #include <dt-bindings/pinctrl/rzg2l-pinctrl.h>
 
 /*
- * Signals of SW_CONFIG switches:
- * @SW_SD0_DEV_SEL:
- *	0 - SD0 is connected to eMMC
- *	1 - SD0 is connected to uSD0 card
+ * On-board switches' states:
+ * @SW_OFF: switch's state is OFF
+ * @SW_ON:  switch's state is ON
  */
-#define SW_SD0_DEV_SEL	1
+#define SW_OFF		0
+#define SW_ON		1
+
+/*
+ * SW_CONFIG[x] switches' states:
+ * @SW_CONFIG2:
+ *	SW_OFF - SD0 is connected to eMMC
+ *	SW_ON  - SD0 is connected to uSD0 card
+ * @SW_CONFIG3:
+ *	SW_OFF - SD2 is connected to SoC
+ *	SW_ON  - SCIF1, SSI0, IRQ0, IRQ1 connected to SoC
+ */
+#define SW_CONFIG2	SW_ON
+#define SW_CONFIG3	SW_ON
 
 / {
 	compatible = "renesas,rzg3s-smarcm", "renesas,r9a08g045s33", "renesas,r9a08g045";
 
 	aliases {
 		mmc0 = &sdhi0;
+#if SW_CONFIG3 == SW_OFF
+		mmc2 = &sdhi2;
+#else
+		eth0 = &eth0;
+		eth1 = &eth1;
+#endif
 	};
 
 	chosen {
@@ -43,7 +61,7 @@
 		enable-active-high;
 	};
 
-#if SW_SD0_DEV_SEL
+#if SW_CONFIG2 == SW_ON
 	vccq_sdhi0: regulator1 {
 		compatible = "regulator-gpio";
 		regulator-name = "SDHI0 VccQ";
@@ -63,13 +81,76 @@
 		regulator-always-on;
 	};
 #endif
+
+	vcc_sdhi2: regulator2 {
+		compatible = "regulator-fixed";
+		regulator-name = "SDHI2 Vcc";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpios = <&pinctrl RZG2L_GPIO(8, 1) GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+};
+
+#if SW_CONFIG3 == SW_ON
+&eth0 {
+	pinctrl-0 = <&eth0_pins>;
+	pinctrl-names = "default";
+	phy-handle = <&phy0>;
+	phy-mode = "rgmii-id";
+	status = "okay";
+
+	phy0: ethernet-phy@7 {
+		reg = <7>;
+		interrupt-parent = <&pinctrl>;
+		interrupts = <RZG2L_GPIO(12, 0) IRQ_TYPE_EDGE_FALLING>;
+		rxc-skew-psec = <0>;
+		txc-skew-psec = <0>;
+		rxdv-skew-psec = <0>;
+		txen-skew-psec = <0>;
+		rxd0-skew-psec = <0>;
+		rxd1-skew-psec = <0>;
+		rxd2-skew-psec = <0>;
+		rxd3-skew-psec = <0>;
+		txd0-skew-psec = <0>;
+		txd1-skew-psec = <0>;
+		txd2-skew-psec = <0>;
+		txd3-skew-psec = <0>;
+	};
+};
+
+&eth1 {
+	pinctrl-0 = <&eth1_pins>;
+	pinctrl-names = "default";
+	phy-handle = <&phy1>;
+	phy-mode = "rgmii-id";
+	status = "okay";
+
+	phy1: ethernet-phy@7 {
+		reg = <7>;
+		interrupt-parent = <&pinctrl>;
+		interrupts = <RZG2L_GPIO(12, 1) IRQ_TYPE_EDGE_FALLING>;
+		rxc-skew-psec = <0>;
+		txc-skew-psec = <0>;
+		rxdv-skew-psec = <0>;
+		txen-skew-psec = <0>;
+		rxd0-skew-psec = <0>;
+		rxd1-skew-psec = <0>;
+		rxd2-skew-psec = <0>;
+		rxd3-skew-psec = <0>;
+		txd0-skew-psec = <0>;
+		txd1-skew-psec = <0>;
+		txd2-skew-psec = <0>;
+		txd3-skew-psec = <0>;
+	};
 };
+#endif
 
 &extal_clk {
 	clock-frequency = <24000000>;
 };
 
-#if SW_SD0_DEV_SEL
+#if SW_CONFIG2 == SW_ON
 /* SD0 slot */
 &sdhi0 {
 	pinctrl-0 = <&sdhi0_pins>;
@@ -100,7 +181,100 @@
 };
 #endif
 
+#if SW_CONFIG3 == SW_OFF
+&sdhi2 {
+	pinctrl-0 = <&sdhi2_pins>;
+	pinctrl-names = "default";
+	vmmc-supply = <&vcc_sdhi2>;
+	bus-width = <4>;
+	max-frequency = <50000000>;
+	status = "okay";
+};
+#endif
+
 &pinctrl {
+	eth0-phy-irq-hog {
+		gpio-hog;
+		gpios = <RZG2L_GPIO(12, 0) GPIO_ACTIVE_LOW>;
+		input;
+		line-name = "eth0-phy-irq";
+	};
+
+	eth0_pins: eth0 {
+		txc {
+			pinmux = <RZG2L_PORT_PINMUX(1, 0, 1)>;  /* ET0_TXC */
+			power-source = <1800>;
+			output-enable;
+			input-enable;
+			drive-strength-microamp = <5200>;
+		};
+
+		tx_ctl {
+			pinmux = <RZG2L_PORT_PINMUX(1, 1, 1)>;  /* ET0_TX_CTL */
+			power-source = <1800>;
+			output-enable;
+			drive-strength-microamp = <5200>;
+		};
+
+		mux {
+			pinmux = <RZG2L_PORT_PINMUX(1, 2, 1)>,	/* ET0_TXD0 */
+				 <RZG2L_PORT_PINMUX(1, 3, 1)>,	/* ET0_TXD1 */
+				 <RZG2L_PORT_PINMUX(1, 4, 1)>,	/* ET0_TXD2 */
+				 <RZG2L_PORT_PINMUX(2, 0, 1)>,	/* ET0_TXD3 */
+				 <RZG2L_PORT_PINMUX(3, 0, 1)>,	/* ET0_RXC */
+				 <RZG2L_PORT_PINMUX(3, 1, 1)>,	/* ET0_RX_CTL */
+				 <RZG2L_PORT_PINMUX(3, 2, 1)>,	/* ET0_RXD0 */
+				 <RZG2L_PORT_PINMUX(3, 3, 1)>,	/* ET0_RXD1 */
+				 <RZG2L_PORT_PINMUX(4, 0, 1)>,	/* ET0_RXD2 */
+				 <RZG2L_PORT_PINMUX(4, 1, 1)>,	/* ET0_RXD3 */
+				 <RZG2L_PORT_PINMUX(4, 3, 1)>,	/* ET0_MDC */
+				 <RZG2L_PORT_PINMUX(4, 4, 1)>,	/* ET0_MDIO */
+				 <RZG2L_PORT_PINMUX(4, 5, 1)>;	/* ET0_LINKSTA */
+			power-source = <1800>;
+		};
+	};
+
+	eth1-phy-irq-hog {
+		gpio-hog;
+		gpios = <RZG2L_GPIO(12, 1) GPIO_ACTIVE_LOW>;
+		input;
+		line-name = "eth1-phy-irq";
+	};
+
+	eth1_pins: eth1 {
+		txc {
+			pinmux = <RZG2L_PORT_PINMUX(7, 0, 1)>;	/* ET1_TXC */
+			power-source = <1800>;
+			output-enable;
+			input-enable;
+			drive-strength-microamp = <5200>;
+		};
+
+		tx_ctl {
+			pinmux = <RZG2L_PORT_PINMUX(7, 1, 1)>;	/* ET1_TX_CTL */
+			power-source = <1800>;
+			output-enable;
+			drive-strength-microamp = <5200>;
+		};
+
+		mux {
+			pinmux = <RZG2L_PORT_PINMUX(7, 2, 1)>,	/* ET1_TXD0 */
+				 <RZG2L_PORT_PINMUX(7, 3, 1)>,	/* ET1_TXD1 */
+				 <RZG2L_PORT_PINMUX(7, 4, 1)>,	/* ET1_TXD2 */
+				 <RZG2L_PORT_PINMUX(8, 0, 1)>,	/* ET1_TXD3 */
+				 <RZG2L_PORT_PINMUX(8, 4, 1)>,	/* ET1_RXC */
+				 <RZG2L_PORT_PINMUX(9, 0, 1)>,	/* ET1_RX_CTL */
+				 <RZG2L_PORT_PINMUX(9, 1, 1)>,	/* ET1_RXD0 */
+				 <RZG2L_PORT_PINMUX(9, 2, 1)>,	/* ET1_RXD1 */
+				 <RZG2L_PORT_PINMUX(9, 3, 1)>,	/* ET1_RXD2 */
+				 <RZG2L_PORT_PINMUX(10, 0, 1)>,	/* ET1_RXD3 */
+				 <RZG2L_PORT_PINMUX(10, 2, 1)>,	/* ET1_MDC */
+				 <RZG2L_PORT_PINMUX(10, 3, 1)>,	/* ET1_MDIO */
+				 <RZG2L_PORT_PINMUX(10, 4, 1)>;	/* ET1_LINKSTA */
+			power-source = <1800>;
+		};
+	};
+
 	sdhi0_pins: sd0 {
 		data {
 			pins = "SD0_DATA0", "SD0_DATA1", "SD0_DATA2", "SD0_DATA3";
@@ -139,4 +313,26 @@
 		       "SD0_CLK", "SD0_CMD", "SD0_RST#";
 		power-source = <1800>;
 	};
+
+	sdhi2_pins: sd2 {
+		data {
+			pins = "P11_2", "P11_3", "P12_0", "P12_1";
+			input-enable;
+		};
+
+		ctrl {
+			pins = "P11_1";
+			input-enable;
+		};
+
+		mux {
+			pinmux = <RZG2L_PORT_PINMUX(11, 0, 8)>, /* SD2_CLK */
+				 <RZG2L_PORT_PINMUX(11, 1, 8)>, /* SD2_CMD */
+				 <RZG2L_PORT_PINMUX(11, 2, 8)>, /* SD2_DATA0 */
+				 <RZG2L_PORT_PINMUX(11, 3, 8)>, /* SD2_DATA1 */
+				 <RZG2L_PORT_PINMUX(12, 0, 8)>, /* SD2_DATA2 */
+				 <RZG2L_PORT_PINMUX(12, 1, 8)>, /* SD2_DATA3 */
+				 <RZG2L_PORT_PINMUX(14, 1, 7)>; /* SD2_CD# */
+		};
+	};
 };
diff --git a/arch/arm64/boot/dts/renesas/rzg3s-smarc.dtsi b/arch/arm64/boot/dts/renesas/rzg3s-smarc.dtsi
index e7073a09ed2e..214520137230 100644
--- a/arch/arm64/boot/dts/renesas/rzg3s-smarc.dtsi
+++ b/arch/arm64/boot/dts/renesas/rzg3s-smarc.dtsi
@@ -11,6 +11,26 @@
 / {
 	aliases {
 		serial0 = &scif0;
+		mmc1 = &sdhi1;
+	};
+
+	vcc_sdhi1: regulator-vcc-sdhi1 {
+		compatible = "regulator-fixed";
+		regulator-name = "SDHI1 Vcc";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpios = <&pinctrl RZG2L_GPIO(2, 3) GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	vccq_sdhi1: regulator-vccq-sdhi1 {
+		compatible = "regulator-gpio";
+		regulator-name = "SDHI1 VccQ";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <3300000>;
+		gpios = <&pinctrl RZG2L_GPIO(4, 2) GPIO_ACTIVE_HIGH>;
+		gpios-states = <1>;
+		states = <3300000 1>, <1800000 0>;
 	};
 };
 
@@ -19,6 +39,38 @@
 		pinmux = <RZG2L_PORT_PINMUX(6, 3, 1)>, /* RXD */
 			 <RZG2L_PORT_PINMUX(6, 4, 1)>; /* TXD */
 	};
+
+	sdhi1_pins: sd1 {
+		data {
+			pins = "SD1_DATA0", "SD1_DATA1", "SD1_DATA2", "SD1_DATA3";
+			power-source = <3300>;
+		};
+
+		ctrl {
+			pins = "SD1_CLK", "SD1_CMD";
+			power-source = <3300>;
+		};
+
+		cd {
+			pinmux = <RZG2L_PORT_PINMUX(0, 2, 1)>; /* SD1_CD */
+		};
+	};
+
+	sdhi1_pins_uhs: sd1-uhs {
+		data {
+			pins = "SD1_DATA0", "SD1_DATA1", "SD1_DATA2", "SD1_DATA3";
+			power-source = <1800>;
+		};
+
+		ctrl {
+			pins = "SD1_CLK", "SD1_CMD";
+			power-source = <1800>;
+		};
+
+		cd {
+			pinmux = <RZG2L_PORT_PINMUX(0, 2, 1)>; /* SD1_CD */
+		};
+	};
 };
 
 &scif0 {
@@ -26,3 +78,16 @@
 	pinctrl-0 = <&scif0_pins>;
 	status = "okay";
 };
+
+&sdhi1 {
+	pinctrl-0 = <&sdhi1_pins>;
+	pinctrl-1 = <&sdhi1_pins_uhs>;
+	pinctrl-names = "default", "state_uhs";
+	vmmc-supply = <&vcc_sdhi1>;
+	vqmmc-supply = <&vccq_sdhi1>;
+	bus-width = <4>;
+	sd-uhs-sdr50;
+	sd-uhs-sdr104;
+	max-frequency = <125000000>;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/rockchip/Makefile b/arch/arm64/boot/dts/rockchip/Makefile
index a18f33bf0c0e..a7b30e11beaf 100644
--- a/arch/arm64/boot/dts/rockchip/Makefile
+++ b/arch/arm64/boot/dts/rockchip/Makefile
@@ -9,6 +9,7 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3308-roc-cc.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3308-rock-pi-s.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3318-a95x-z2.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3326-anbernic-rg351m.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3326-anbernic-rg351v.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3326-odroid-go2.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3326-odroid-go2-v11.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3326-odroid-go3.dtb
@@ -78,6 +79,8 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-anbernic-rg503.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-pinenote-v1.1.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-pinenote-v1.2.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-powkiddy-rgb30.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-powkiddy-rk2023.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-powkiddy-x55.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-quartz64-a.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-quartz64-b.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-radxa-cm3-io.dtb
@@ -98,14 +101,17 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-odroid-m1.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-radxa-e25.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-roc-pc.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-rock-3a.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-coolpi-cm5-evb.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-edgeble-neu6a-io.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-edgeble-neu6b-io.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-evb1-v10.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-jaguar.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-nanopc-t6.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-orangepi-5-plus.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-quartzpro64.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-rock-5b.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-turing-rk1.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588s-coolpi-4b.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588s-indiedroid-nova.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588s-khadas-edge2.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588s-rock-5a.dtb
diff --git a/arch/arm64/boot/dts/rockchip/px30-engicam-common.dtsi b/arch/arm64/boot/dts/rockchip/px30-engicam-common.dtsi
index 3429e124d95a..5b4e22385165 100644
--- a/arch/arm64/boot/dts/rockchip/px30-engicam-common.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30-engicam-common.dtsi
@@ -7,6 +7,7 @@
 
 / {
 	aliases {
+		ethernet0 = &gmac;
 		mmc1 = &sdmmc;
 		mmc2 = &sdio;
 	};
diff --git a/arch/arm64/boot/dts/rockchip/px30-evb.dts b/arch/arm64/boot/dts/rockchip/px30-evb.dts
index c1bbd555f5f5..0a90a88fc664 100644
--- a/arch/arm64/boot/dts/rockchip/px30-evb.dts
+++ b/arch/arm64/boot/dts/rockchip/px30-evb.dts
@@ -14,6 +14,7 @@
 	compatible = "rockchip,px30-evb", "rockchip,px30";
 
 	aliases {
+		ethernet0 = &gmac;
 		mmc0 = &sdmmc;
 		mmc1 = &sdio;
 		mmc2 = &emmc;
diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
index de0a1f2af983..16798eb77077 100644
--- a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
+++ b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
@@ -13,6 +13,7 @@
 	compatible = "tsd,px30-ringneck-haikou", "rockchip,px30";
 
 	aliases {
+		ethernet0 = &gmac;
 		mmc2 = &sdmmc;
 	};
 
@@ -86,7 +87,7 @@
 	sgtl5000_clk: sgtl5000-oscillator {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
-		clock-frequency  = <24576000>;
+		clock-frequency = <24576000>;
 	};
 
 	dc_12v: dc-12v-regulator {
diff --git a/arch/arm64/boot/dts/rockchip/px30.dtsi b/arch/arm64/boot/dts/rockchip/px30.dtsi
index 42ce78beb413..d0905515399b 100644
--- a/arch/arm64/boot/dts/rockchip/px30.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30.dtsi
@@ -20,7 +20,6 @@
 	#size-cells = <2>;
 
 	aliases {
-		ethernet0 = &gmac;
 		i2c0 = &i2c0;
 		i2c1 = &i2c1;
 		i2c2 = &i2c2;
diff --git a/arch/arm64/boot/dts/rockchip/rk3308-rock-pi-s.dts b/arch/arm64/boot/dts/rockchip/rk3308-rock-pi-s.dts
index e9810d2f0407..b47fe02c33fb 100644
--- a/arch/arm64/boot/dts/rockchip/rk3308-rock-pi-s.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3308-rock-pi-s.dts
@@ -143,6 +143,68 @@
 	status = "okay";
 };
 
+&gpio0 {
+	gpio-line-names =
+		/* GPIO0_A0 - A7 */
+		"", "", "", "", "", "", "", "",
+		/* GPIO0_B0 - B7 */
+		"", "", "", "header1-pin3 [GPIO0_B3]",
+		"header1-pin5 [GPIO0_B4]", "", "",
+		"header1-pin11 [GPIO0_B7]",
+		/* GPIO0_C0 - C7 */
+		"header1-pin13 [GPIO0_C0]",
+		"header1-pin15 [GPIO0_C1]", "", "", "",
+		"", "", "",
+		/* GPIO0_D0 - D7 */
+		"", "", "", "", "", "", "", "";
+};
+
+&gpio1 {
+	gpio-line-names =
+		/* GPIO1_A0 - A7 */
+		"", "", "", "", "", "", "", "",
+		/* GPIO1_B0 - B7 */
+		"", "", "", "", "", "", "", "",
+		/* GPIO1_C0 - C7 */
+		"", "", "", "", "", "", "header1-pin21 [GPIO1_C6]",
+		"header1-pin19 [GPIO1_C7]",
+		/* GPIO1_D0 - D7 */
+		"header1-pin23 [GPIO1_D0]", "header1-pin24 [GPIO1_D1]",
+		"", "", "", "", "", "";
+};
+
+&gpio2 {
+	gpio-line-names =
+		/* GPIO2_A0 - A7 */
+		"header1-pin10 [GPIO2_A0]", "header1-pin8 [GPIO2_A1]",
+		"", "",
+		"header1-pin7 [GPIO2_A4]", "header1-pin12 [GPIO2_A5]",
+		"header2-pin46 [GPIO2_A6]", "header1-pin22 [GPIO1_A7]",
+		/* GPIO2_B0 - B7 */
+		"header2-pin45 [GPIO2_B0]", "header1-pin18 [GPIO2_B1]",
+		"header1-pin16 [GPIO2_B2]", "header2-pin44 [GPIO2_B3]",
+		"header2-pin43 [GPIO2_B4]", "header2-pin28 [GPIO2_B5]",
+		"header2-pin30 [GPIO2_B6]", "header2-pin32 [GPIO2_B7]",
+		/* GPIO2_C0 - C7 */
+		"header2-pin34 [GPIO2_C0]", "", "", "", "", "", "", "",
+		/* GPIO2_D0 - D7 */
+		"", "", "", "", "", "", "", "";
+};
+
+&gpio3 {
+	gpio-line-names =
+		/* GPIO3_A0 - A7 */
+		"", "", "", "", "", "", "", "",
+		/* GPIO3_B0 - B7 */
+		"", "", "header2-pin42 [GPIO3_B2]",
+		"header2-pin41 [GPIO3_B3]", "header2-pin40 [GPIO3_B4]",
+		"header2-pin39 [GPIO3_B5]", "", "",
+		/* GPIO3_C0 - C7 */
+		"", "", "", "", "", "", "", "",
+		/* GPIO3_D0 - D7 */
+		"", "", "", "", "", "", "", "";
+};
+
 &i2c1 {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/rockchip/rk3308.dtsi b/arch/arm64/boot/dts/rockchip/rk3308.dtsi
index 2ae4bb7d5e62..cfc0a87b5195 100644
--- a/arch/arm64/boot/dts/rockchip/rk3308.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3308.dtsi
@@ -20,6 +20,11 @@
 	#size-cells = <2>;
 
 	aliases {
+		gpio0 = &gpio0;
+		gpio1 = &gpio1;
+		gpio2 = &gpio2;
+		gpio3 = &gpio3;
+		gpio4 = &gpio4;
 		i2c0 = &i2c0;
 		i2c1 = &i2c1;
 		i2c2 = &i2c2;
diff --git a/arch/arm64/boot/dts/rockchip/rk3318-a95x-z2.dts b/arch/arm64/boot/dts/rockchip/rk3318-a95x-z2.dts
index 1deef53a4c94..c7b1862fca6a 100644
--- a/arch/arm64/boot/dts/rockchip/rk3318-a95x-z2.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3318-a95x-z2.dts
@@ -9,6 +9,7 @@
 	compatible = "zkmagic,a95x-z2", "rockchip,rk3318";
 
 	aliases {
+		ethernet0 = &gmac2phy;
 		mmc0 = &sdmmc;
 		mmc1 = &sdio;
 		mmc2 = &emmc;
diff --git a/arch/arm64/boot/dts/rockchip/rk3326-anbernic-rg351m.dts b/arch/arm64/boot/dts/rockchip/rk3326-anbernic-rg351m.dts
index ce318e05f0a6..f4d20f29c1b4 100644
--- a/arch/arm64/boot/dts/rockchip/rk3326-anbernic-rg351m.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3326-anbernic-rg351m.dts
@@ -6,30 +6,16 @@
  */
 
 /dts-v1/;
-#include "rk3326-odroid-go.dtsi"
+#include "rk3326-anbernic-rg351m.dtsi"
 
 / {
 	model = "Anbernic RG351M";
 	compatible = "anbernic,rg351m", "rockchip,rk3326";
-
-	vibrator {
-		compatible = "pwm-vibrator";
-		pwms = <&pwm0 0 1000000 0>;
-		pwm-names = "enable";
-	};
 };
 
-/delete-node/ &builtin_gamepad;
-/delete-node/ &vcc_host; /* conflicts with pwm vibration motor */
-
 &internal_display {
 	compatible = "elida,kd35t133";
 	iovcc-supply = <&vcc_lcd>;
+	rotation = <270>;
 	vdd-supply = <&vcc_lcd>;
 };
-
-&pwm0 {
-	status = "okay";
-};
-
-/delete-node/ &rk817_charger;
diff --git a/arch/arm64/boot/dts/rockchip/rk3326-anbernic-rg351m.dtsi b/arch/arm64/boot/dts/rockchip/rk3326-anbernic-rg351m.dtsi
new file mode 100644
index 000000000000..b6d041dbed94
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3326-anbernic-rg351m.dtsi
@@ -0,0 +1,478 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2019 Hardkernel Co., Ltd
+ * Copyright (c) 2020 Theobroma Systems Design und Consulting GmbH
+ * Copyright (c) 2022 Maya Matuszczyk <maccraft123mc@gmail.com>
+ */
+
+/dts-v1/;
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+#include "rk3326.dtsi"
+
+/ {
+	aliases {
+		mmc0 = &sdmmc;
+	};
+
+	chosen {
+		stdout-path = "serial2:115200n8";
+	};
+
+	backlight: backlight {
+		compatible = "pwm-backlight";
+		power-supply = <&vcc_bl>;
+		pwms = <&pwm1 0 25000 0>;
+	};
+
+	/*
+	 * LED is a tri-state. Driven high it is red, driven low it is
+	 * green, and not driven at all (pin set to input) it is amber.
+	 * Additionally, there is a 2nd LED that is not controllable
+	 * that is on (red) when plugged in to power.
+	 */
+	gpio_led: gpio-leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&led_pin>;
+
+		red_green_led: led-0 {
+			color = <LED_COLOR_ID_RED>;
+			gpios = <&gpio2 RK_PB5 GPIO_ACTIVE_HIGH>;
+			function = LED_FUNCTION_CHARGING;
+		};
+	};
+
+	rk817-sound {
+		compatible = "simple-audio-card";
+		simple-audio-card,name = "rk817_int";
+		simple-audio-card,format = "i2s";
+		simple-audio-card,hp-det-gpio = <&gpio2 RK_PC6 GPIO_ACTIVE_HIGH>;
+		simple-audio-card,mclk-fs = <256>;
+		simple-audio-card,widgets =
+			"Microphone", "Mic Jack",
+			"Headphone", "Headphones",
+			"Speaker", "Speaker";
+		simple-audio-card,routing =
+			"MICL", "Mic Jack",
+			"Headphones", "HPOL",
+			"Headphones", "HPOR",
+			"Speaker", "SPKO";
+
+		simple-audio-card,codec {
+			sound-dai = <&rk817>;
+		};
+
+		simple-audio-card,cpu {
+			sound-dai = <&i2s1_2ch>;
+		};
+	};
+
+	vccsys: vccsys {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc3v8_sys";
+		regulator-always-on;
+		regulator-min-microvolt = <3800000>;
+		regulator-max-microvolt = <3800000>;
+	};
+
+	vibrator {
+		compatible = "pwm-vibrator";
+		pwms = <&pwm0 0 1000000 0>;
+		pwm-names = "enable";
+	};
+};
+
+&cpu0 {
+	cpu-supply = <&vdd_arm>;
+};
+
+&cpu1 {
+	cpu-supply = <&vdd_arm>;
+};
+
+&cpu2 {
+	cpu-supply = <&vdd_arm>;
+};
+
+&cpu3 {
+	cpu-supply = <&vdd_arm>;
+};
+
+&cru {
+	assigned-clocks = <&cru PLL_NPLL>,
+		<&cru ACLK_BUS_PRE>, <&cru ACLK_PERI_PRE>,
+		<&cru HCLK_BUS_PRE>, <&cru HCLK_PERI_PRE>,
+		<&cru PCLK_BUS_PRE>, <&cru SCLK_GPU>;
+
+	assigned-clock-rates = <1188000000>,
+		<200000000>, <200000000>,
+		<150000000>, <150000000>,
+		<100000000>, <200000000>;
+};
+
+&display_subsystem {
+	status = "okay";
+};
+
+&dsi {
+	status = "okay";
+
+	ports {
+		mipi_out: port@1 {
+			reg = <1>;
+
+			mipi_out_panel: endpoint {
+				remote-endpoint = <&mipi_in_panel>;
+			};
+		};
+	};
+
+	internal_display: panel@0 {
+		reg = <0>;
+		backlight = <&backlight>;
+		reset-gpios = <&gpio3 RK_PC0 GPIO_ACTIVE_LOW>;
+
+		port {
+			mipi_in_panel: endpoint {
+				remote-endpoint = <&mipi_out_panel>;
+			};
+		};
+	};
+};
+
+&dsi_dphy {
+	status = "okay";
+};
+
+&gpu {
+	mali-supply = <&vdd_logic>;
+	status = "okay";
+};
+
+&i2c0 {
+	clock-frequency = <400000>;
+	i2c-scl-falling-time-ns = <16>;
+	i2c-scl-rising-time-ns = <280>;
+	status = "okay";
+
+	rk817: pmic@20 {
+		compatible = "rockchip,rk817";
+		reg = <0x20>;
+		#clock-cells = <1>;
+		clock-names = "mclk";
+		clock-output-names = "rk808-clkout1", "xin32k";
+		clocks = <&cru SCLK_I2S1_OUT>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <RK_PB2 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-0 = <&pmic_int>, <&i2s1_2ch_mclk>;
+		pinctrl-names = "default";
+		#sound-dai-cells = <0>;
+		wakeup-source;
+
+		vcc1-supply = <&vccsys>;
+		vcc2-supply = <&vccsys>;
+		vcc3-supply = <&vccsys>;
+		vcc4-supply = <&vccsys>;
+		vcc5-supply = <&vccsys>;
+		vcc6-supply = <&vccsys>;
+		vcc7-supply = <&vccsys>;
+		vcc8-supply = <&vccsys>;
+
+		regulators {
+			vdd_logic: DCDC_REG1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-max-microvolt = <1150000>;
+				regulator-min-microvolt = <950000>;
+				regulator-name = "vdd_logic";
+				regulator-ramp-delay = <6001>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <950000>;
+				};
+			};
+
+			vdd_arm: DCDC_REG2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-max-microvolt = <1350000>;
+				regulator-min-microvolt = <950000>;
+				regulator-name = "vdd_arm";
+				regulator-ramp-delay = <6001>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <950000>;
+				};
+			};
+
+			vcc_ddr: DCDC_REG3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-name = "vcc_ddr";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+				};
+			};
+
+			vcc_3v3: DCDC_REG4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-max-microvolt = <3300000>;
+				regulator-min-microvolt = <3300000>;
+				regulator-name = "vcc_3v3";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			vcc_1v8: LDO_REG2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-max-microvolt = <1800000>;
+				regulator-min-microvolt = <1800000>;
+				regulator-name = "vcc_1v8";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vdd_1v0: LDO_REG3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-max-microvolt = <1000000>;
+				regulator-min-microvolt = <1000000>;
+				regulator-name = "vdd_1v0";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1000000>;
+				};
+			};
+
+			vcc3v3_pmu: LDO_REG4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-max-microvolt = <3300000>;
+				regulator-min-microvolt = <3300000>;
+				regulator-name = "vcc3v3_pmu";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			vccio_sd: LDO_REG5 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-max-microvolt = <3300000>;
+				regulator-min-microvolt = <1800000>;
+				regulator-name = "vccio_sd";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			vcc_sd: LDO_REG6 {
+				regulator-boot-on;
+				regulator-max-microvolt = <3300000>;
+				regulator-min-microvolt = <3300000>;
+				regulator-name = "vcc_sd";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			vcc_bl: LDO_REG7 {
+				regulator-max-microvolt = <3300000>;
+				regulator-min-microvolt = <3300000>;
+				regulator-name = "vcc_bl";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			vcc_lcd: LDO_REG8 {
+				regulator-max-microvolt = <2800000>;
+				regulator-min-microvolt = <2800000>;
+				regulator-name = "vcc_lcd";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <2800000>;
+				};
+			};
+
+			vcc_wifi: LDO_REG9 {
+				regulator-max-microvolt = <3300000>;
+				regulator-min-microvolt = <3300000>;
+				regulator-name = "vcc_wifi";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			usb_midu: BOOST {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-max-microvolt = <5400000>;
+				regulator-min-microvolt = <5000000>;
+				regulator-name = "usb_midu";
+			};
+		};
+
+		rk817_codec: codec {
+			rockchip,mic-in-differential;
+		};
+	};
+};
+
+&i2s1_2ch {
+	status = "okay";
+};
+
+&io_domains {
+	vccio1-supply = <&vcc_3v3>;
+	vccio2-supply = <&vccio_sd>;
+	vccio3-supply = <&vcc_3v3>;
+	vccio4-supply = <&vcc_3v3>;
+	vccio5-supply = <&vcc_3v3>;
+	vccio6-supply = <&vcc_3v3>;
+	status = "okay";
+};
+
+&pmu_io_domains {
+	pmuio1-supply = <&vcc3v3_pmu>;
+	pmuio2-supply = <&vcc3v3_pmu>;
+	status = "okay";
+};
+
+&pwm0 {
+	status = "okay";
+};
+
+&pwm1 {
+	status = "okay";
+};
+
+&saradc {
+	vref-supply = <&vcc_1v8>;
+	status = "okay";
+};
+
+&sdmmc {
+	cap-sd-highspeed;
+	card-detect-delay = <200>;
+	cd-gpios = <&gpio0 RK_PA3 GPIO_ACTIVE_LOW>;
+	sd-uhs-sdr12;
+	sd-uhs-sdr25;
+	sd-uhs-sdr50;
+	sd-uhs-sdr104;
+	vmmc-supply = <&vcc_sd>;
+	vqmmc-supply = <&vccio_sd>;
+	status = "okay";
+};
+
+&sfc {
+	#address-cells = <1>;
+	pinctrl-0 = <&sfc_clk &sfc_cs0 &sfc_bus2>;
+	pinctrl-names = "default";
+	#size-cells = <0>;
+	status = "okay";
+
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0>;
+		spi-max-frequency = <108000000>;
+		spi-rx-bus-width = <2>;
+		spi-tx-bus-width = <1>;
+	};
+};
+
+&tsadc {
+	status = "okay";
+};
+
+&u2phy {
+	status = "okay";
+
+	u2phy_host: host-port {
+		status = "okay";
+	};
+
+	u2phy_otg: otg-port {
+		status = "disabled";
+	};
+};
+
+&usb20_otg {
+	status = "okay";
+};
+
+&uart2 {
+	pinctrl-0 = <&uart2m1_xfer>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&vopb {
+	status = "okay";
+};
+
+&vopb_mmu {
+	status = "okay";
+};
+
+&pinctrl {
+	headphone {
+		hp_det: hp-det {
+			rockchip,pins = <2 RK_PC6 RK_FUNC_GPIO &pcfg_pull_down>;
+		};
+	};
+
+	leds {
+		led_pin: led-pin {
+			rockchip,pins = <2 RK_PB5 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	pmic {
+		dc_det: dc-det {
+			rockchip,pins = <0 RK_PB3 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		pmic_int: pmic-int {
+			rockchip,pins = <0 RK_PB2 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+
+		soc_slppin_gpio: soc_slppin_gpio {
+			rockchip,pins = <0 RK_PA4 RK_FUNC_GPIO &pcfg_output_low>;
+		};
+
+		soc_slppin_rst: soc_slppin_rst {
+			rockchip,pins = <0 RK_PA4 2 &pcfg_pull_none>;
+		};
+
+		soc_slppin_slp: soc_slppin_slp {
+			rockchip,pins = <0 RK_PA4 1 &pcfg_pull_none>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3326-anbernic-rg351v.dts b/arch/arm64/boot/dts/rockchip/rk3326-anbernic-rg351v.dts
new file mode 100644
index 000000000000..c79f7a7b38cb
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3326-anbernic-rg351v.dts
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+/dts-v1/;
+#include "rk3326-anbernic-rg351m.dtsi"
+
+/ {
+	model = "Anbernic RG351V";
+	compatible = "anbernic,rg351v", "rockchip,rk3326";
+
+	gpio_keys_vol: gpio-keys-vol {
+		compatible = "gpio-keys";
+		autorepeat;
+
+		button-vol-down {
+			gpios = <&gpio2 RK_PA1 GPIO_ACTIVE_LOW>;
+			label = "VOLUMEDOWN";
+			linux,code = <KEY_VOLUMEDOWN>;
+		};
+
+		button-vol-up {
+			gpios = <&gpio2 RK_PA0 GPIO_ACTIVE_LOW>;
+			label = "VOLUMEUP";
+			linux,code = <KEY_VOLUMEUP>;
+		};
+	};
+};
+
+&internal_display {
+	compatible = "anbernic,rg351v-panel", "newvision,nv3051d";
+	vdd-supply = <&vcc_lcd>;
+};
+
+&io_domains {
+	vccio1-supply = <&vccio_sd>;
+};
+
+&vcc_sd {
+	regulator-max-microvolt = <3000000>;
+	regulator-min-microvolt = <1800000>;
+};
+
+&vccio_sd {
+	regulator-max-microvolt = <1800000>;
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-a1.dts b/arch/arm64/boot/dts/rockchip/rk3328-a1.dts
index 40bf808642b9..824183e515da 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-a1.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-a1.dts
@@ -9,6 +9,7 @@
 	compatible = "azw,beelink-a1", "rockchip,rk3328";
 
 	aliases {
+		ethernet0 = &gmac2io;
 		mmc0 = &sdmmc;
 		mmc1 = &emmc;
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-evb.dts b/arch/arm64/boot/dts/rockchip/rk3328-evb.dts
index ff6b466e0e07..1eef5504445f 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-evb.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-evb.dts
@@ -11,6 +11,7 @@
 	compatible = "rockchip,rk3328-evb", "rockchip,rk3328";
 
 	aliases {
+		ethernet0 = &gmac2phy;
 		mmc0 = &sdmmc;
 		mmc1 = &sdio;
 		mmc2 = &emmc;
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts b/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts
index 1445b879ac7a..a4399da7d8b1 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts
@@ -14,6 +14,7 @@
 	compatible = "friendlyarm,nanopi-r2s", "rockchip,rk3328";
 
 	aliases {
+		ethernet0 = &gmac2io;
 		ethernet1 = &rtl8153;
 		mmc0 = &sdmmc;
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts
index 5d7d567283e5..4237f2ee8fee 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts
@@ -26,9 +26,11 @@
 			compatible = "ethernet-phy-ieee802.3-c22";
 			reg = <0>;
 
+			motorcomm,auto-sleep-disabled;
 			motorcomm,clk-out-frequency-hz = <125000000>;
 			motorcomm,keep-pll-enabled;
-			motorcomm,auto-sleep-disabled;
+			motorcomm,rx-clk-drv-microamp = <5020>;
+			motorcomm,rx-data-drv-microamp = <5020>;
 
 			pinctrl-0 = <&eth_phy_reset_pin>;
 			pinctrl-names = "default";
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dts b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dts
index dc83d74045a3..f20662929c77 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dts
@@ -15,6 +15,7 @@
 	compatible = "xunlong,orangepi-r1-plus", "rockchip,rk3328";
 
 	aliases {
+		ethernet0 = &gmac2io;
 		ethernet1 = &rtl8153;
 		mmc0 = &sdmmc;
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts b/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts
index 5d5d9574088c..414897a57e75 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts
@@ -11,6 +11,7 @@
 	compatible = "firefly,roc-rk3328-cc", "rockchip,rk3328";
 
 	aliases {
+		ethernet0 = &gmac2io;
 		mmc0 = &sdmmc;
 		mmc1 = &emmc;
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts
index 018a3a5075c7..3cda6c627b68 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts
@@ -21,6 +21,8 @@
 	compatible = "radxa,rockpi-e", "rockchip,rk3328";
 
 	aliases {
+		ethernet0 = &gmac2io;
+		ethernet1 = &gmac2phy;
 		mmc0 = &sdmmc;
 		mmc1 = &emmc;
 	};
@@ -180,6 +182,59 @@
 	status = "okay";
 };
 
+&gpio0 {
+	gpio-line-names =
+		/* GPIO0_A0 - A7 */
+		"", "", "", "", "", "", "", "",
+		/* GPIO0_B0 - B7 */
+		"", "", "", "", "", "", "", "",
+		/* GPIO0_C0 - C7 */
+		"", "", "", "", "", "", "", "",
+		/* GPIO0_D0 - D7 */
+		"", "", "", "pin-15 [GPIO0_D3]", "", "", "", "";
+};
+
+&gpio1 {
+	gpio-line-names =
+		/* GPIO1_A0 - A7 */
+		"", "", "", "", "", "", "", "",
+		/* GPIO1_B0 - B7 */
+		"", "", "", "", "", "", "", "",
+		/* GPIO1_C0 - C7 */
+		"", "", "", "", "", "", "", "",
+		/* GPIO1_D0 - D7 */
+		"", "", "", "", "pin-07 [GPIO1_D4]", "", "", "";
+};
+
+&gpio2 {
+	gpio-line-names =
+		/* GPIO2_A0 - A7 */
+		"pin-08 [GPIO2_A0]", "pin-10 [GPIO2_A1]", "pin-11 [GPIO2_A2]",
+		"pin-13 [GPIO2-A3]", "pin-27 [GPIO2_A4]", "pin-28 [GPIO2_A5]",
+		"pin-33 [GPIO2_A6]", "",
+		/* GPIO2_B0 - B7 */
+		"", "", "", "", "pin-26 [GPIO2_B4]", "", "", "pin-36 [GPIO2_B7]",
+		/* GPIO2_C0 - C7 */
+		"pin-32 [GPIO2_C0]", "pin-35 [GPIO2_C1]", "pin-12 [GPIO2_C2]",
+		"pin-38 [GPIO2_C3]", "pin-29 [GPIO2_C4]", "pin-31 [GPIO2_C5]",
+		"pin-37 [GPIO2_C6]", "pin-40 [GPIO2_C7]",
+		/* GPIO2_D0 - D7 */
+		"", "", "", "", "", "", "", "";
+};
+
+&gpio3 {
+	gpio-line-names =
+		/* GPIO3_A0 - A7 */
+		"pin-23 [GPIO3_A0]", "pin-19 [GPIO3_A1]", "pin-21 [GPIO3_A2]",
+		"", "pin-03 [GPIO3_A4]", "", "pin-05 [GPIO3_A6]", "",
+		/* GPIO3_B0 - B7 */
+		"pin-24 [GPIO3_B0]", "", "", "", "", "", "", "",
+		/* GPIO3_C0 - C7 */
+		"", "", "", "", "", "", "", "",
+		/* GPIO3_D0 - D7 */
+		"", "", "", "", "", "", "", "";
+};
+
 &i2c1 {
 	status = "okay";
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
index 0a27fa5271f5..229fe9da9c2d 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
@@ -11,6 +11,7 @@
 	compatible = "pine64,rock64", "rockchip,rk3328";
 
 	aliases {
+		ethernet0 = &gmac2io;
 		mmc0 = &sdmmc;
 		mmc1 = &emmc;
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
index e729e7a22b23..fb5dcf6e9327 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
@@ -20,6 +20,10 @@
 	#size-cells = <2>;
 
 	aliases {
+		gpio0 = &gpio0;
+		gpio1 = &gpio1;
+		gpio2 = &gpio2;
+		gpio3 = &gpio3;
 		serial0 = &uart0;
 		serial1 = &uart1;
 		serial2 = &uart2;
@@ -27,8 +31,6 @@
 		i2c1 = &i2c1;
 		i2c2 = &i2c2;
 		i2c3 = &i2c3;
-		ethernet0 = &gmac2io;
-		ethernet1 = &gmac2phy;
 	};
 
 	cpus {
@@ -668,7 +670,7 @@
 
 	vdec: video-codec@ff360000 {
 		compatible = "rockchip,rk3328-vdec", "rockchip,rk3399-vdec";
-		reg = <0x0 0xff360000 0x0 0x400>;
+		reg = <0x0 0xff360000 0x0 0x480>;
 		interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru ACLK_RKVDEC>, <&cru HCLK_RKVDEC>,
 			 <&cru SCLK_VDEC_CABAC>, <&cru SCLK_VDEC_CORE>;
@@ -916,6 +918,8 @@
 		resets = <&cru SRST_GMAC2IO_A>;
 		reset-names = "stmmaceth";
 		rockchip,grf = <&grf>;
+		tx-fifo-depth = <2048>;
+		rx-fifo-depth = <4096>;
 		snps,txpbl = <0x4>;
 		status = "disabled";
 	};
@@ -938,6 +942,8 @@
 		reset-names = "stmmaceth";
 		phy-mode = "rmii";
 		phy-handle = <&phy>;
+		tx-fifo-depth = <2048>;
+		rx-fifo-depth = <4096>;
 		snps,txpbl = <0x4>;
 		clock_in_out = "output";
 		status = "disabled";
diff --git a/arch/arm64/boot/dts/rockchip/rk3368-evb.dtsi b/arch/arm64/boot/dts/rockchip/rk3368-evb.dtsi
index e47d1398aeca..b48b98c13705 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368-evb.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3368-evb.dtsi
@@ -9,6 +9,7 @@
 
 / {
 	aliases {
+		ethernet0 = &gmac;
 		mmc0 = &emmc;
 	};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3368-geekbox.dts b/arch/arm64/boot/dts/rockchip/rk3368-geekbox.dts
index be06e6e64d18..029b8e22e709 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368-geekbox.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3368-geekbox.dts
@@ -12,6 +12,7 @@
 	compatible = "geekbuying,geekbox", "rockchip,rk3368";
 
 	aliases {
+		ethernet0 = &gmac;
 		mmc0 = &emmc;
 	};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi b/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi
index 5753e57fd716..8ac8acf4082d 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi
@@ -8,6 +8,7 @@
 
 / {
 	aliases {
+		ethernet0 = &gmac;
 		mmc0 = &emmc;
 	};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3368-orion-r68-meta.dts b/arch/arm64/boot/dts/rockchip/rk3368-orion-r68-meta.dts
index 81d1064fdb21..dcee2e28916f 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368-orion-r68-meta.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3368-orion-r68-meta.dts
@@ -12,6 +12,7 @@
 	compatible = "tronsmart,orion-r68-meta", "rockchip,rk3368";
 
 	aliases {
+		ethernet0 = &gmac;
 		mmc0 = &sdmmc;
 		mmc1 = &emmc;
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3368-r88.dts b/arch/arm64/boot/dts/rockchip/rk3368-r88.dts
index 5589f3db6b36..b16b7ca02379 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368-r88.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3368-r88.dts
@@ -12,6 +12,7 @@
 	compatible = "rockchip,r88", "rockchip,rk3368";
 
 	aliases {
+		ethernet0 = &gmac;
 		mmc0 = &sdio0;
 		mmc1 = &emmc;
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
index a4c5aaf1f457..62af0cb94839 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
@@ -19,7 +19,10 @@
 	#size-cells = <2>;
 
 	aliases {
-		ethernet0 = &gmac;
+		gpio0 = &gpio0;
+		gpio1 = &gpio1;
+		gpio2 = &gpio2;
+		gpio3 = &gpio3;
 		i2c0 = &i2c0;
 		i2c1 = &i2c1;
 		i2c2 = &i2c2;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-eaidk-610.dts b/arch/arm64/boot/dts/rockchip/rk3399-eaidk-610.dts
index 6464ef4d113d..173da81fc231 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-eaidk-610.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-eaidk-610.dts
@@ -15,6 +15,7 @@
 	compatible = "openailab,eaidk-610", "rockchip,rk3399";
 
 	aliases {
+		ethernet0 = &gmac;
 		mmc0 = &sdio0;
 		mmc1 = &sdmmc;
 		mmc2 = &sdhci;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-evb.dts b/arch/arm64/boot/dts/rockchip/rk3399-evb.dts
index 3d1e126b553f..55eca7a50a1f 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-evb.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-evb.dts
@@ -12,6 +12,7 @@
 	compatible = "rockchip,rk3399-evb", "rockchip,rk3399";
 
 	aliases {
+		ethernet0 = &gmac;
 		mmc0 = &sdhci;
 	};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-ficus.dts b/arch/arm64/boot/dts/rockchip/rk3399-ficus.dts
index 1ce85a5816e4..30e4879f322c 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-ficus.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-ficus.dts
@@ -13,6 +13,10 @@
 	model = "96boards RK3399 Ficus";
 	compatible = "vamrs,ficus", "rockchip,rk3399";
 
+	aliases {
+		ethernet0 = &gmac;
+	};
+
 	chosen {
 		stdout-path = "serial2:1500000n8";
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts b/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts
index c5db64f3e124..260415d99aeb 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts
@@ -16,6 +16,7 @@
 	compatible = "firefly,firefly-rk3399", "rockchip,rk3399";
 
 	aliases {
+		ethernet0 = &gmac;
 		mmc0 = &sdio0;
 		mmc1 = &sdmmc;
 		mmc2 = &sdhci;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi
index 5c1929d41cc0..cacbad35cfc8 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi
@@ -509,8 +509,7 @@ ap_i2c_tp: &i2c5 {
 &pci_rootport {
 	mvl_wifi: wifi@0,0 {
 		compatible = "pci1b4b,2b42";
-		reg = <0x83010000 0x0 0x00000000 0x0 0x00100000
-		       0x83010000 0x0 0x00100000 0x0 0x00100000>;
+		reg = <0x0000 0x0 0x0 0x0 0x0>;
 		interrupt-parent = <&gpio0>;
 		interrupts = <8 IRQ_TYPE_LEVEL_LOW>;
 		pinctrl-names = "default";
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet-dumo.dts b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet-dumo.dts
index 853e88455e75..9e4b12ed62cb 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet-dumo.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet-dumo.dts
@@ -34,8 +34,8 @@
 &pci_rootport {
 	wifi@0,0 {
 		compatible = "qcom,ath10k";
-		reg = <0x00010000 0x0 0x00000000 0x0 0x00000000>,
-		      <0x03010010 0x0 0x00000000 0x0 0x00200000>;
+		reg = <0x00000000 0x0 0x00000000 0x0 0x00000000>,
+		      <0x03000010 0x0 0x00000000 0x0 0x00200000>;
 		qcom,ath10k-calibration-variant = "GO_DUMO";
 	};
 };
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
index c9bf1d5c3a42..789fd0dcc88b 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
@@ -489,6 +489,7 @@ ap_i2c_audio: &i2c8 {
 		#address-cells = <3>;
 		#size-cells = <2>;
 		ranges;
+		device_type = "pci";
 	};
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-hugsun-x99.dts b/arch/arm64/boot/dts/rockchip/rk3399-hugsun-x99.dts
index 7af27e8216f1..4a6ab6c2e24c 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-hugsun-x99.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-hugsun-x99.dts
@@ -11,6 +11,7 @@
 	compatible = "hugsun,x99", "rockchip,rk3399";
 
 	aliases {
+		ethernet0 = &gmac;
 		mmc0 = &sdio0;
 		mmc1 = &sdmmc;
 		mmc2 = &sdhci;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge-captain.dts b/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge-captain.dts
index 8302e51def52..99ac4ed0f13f 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge-captain.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge-captain.dts
@@ -10,6 +10,10 @@
 / {
 	model = "Khadas Edge-Captain";
 	compatible = "khadas,edge-captain", "rockchip,rk3399";
+
+	aliases {
+		ethernet0 = &gmac;
+	};
 };
 
 &gmac {
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge-v.dts b/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge-v.dts
index f5dcb99dc349..e12e7b4d64ca 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge-v.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge-v.dts
@@ -10,6 +10,10 @@
 / {
 	model = "Khadas Edge-V";
 	compatible = "khadas,edge-v", "rockchip,rk3399";
+
+	aliases {
+		ethernet0 = &gmac;
+	};
 };
 
 &gmac {
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts b/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts
index 1eb287a3f8c0..9e3aec4440bd 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts
@@ -19,6 +19,7 @@
 	compatible = "kobol,helios64", "rockchip,rk3399";
 
 	aliases {
+		ethernet0 = &gmac;
 		mmc0 = &sdmmc;
 		mmc1 = &sdhci;
 		spi1 = &spi1;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-leez-p710.dts b/arch/arm64/boot/dts/rockchip/rk3399-leez-p710.dts
index a21ac319f809..cb69e2145fa9 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-leez-p710.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-leez-p710.dts
@@ -15,6 +15,7 @@
 	compatible = "leez,p710", "rockchip,rk3399";
 
 	aliases {
+		ethernet0 = &gmac;
 		mmc0 = &sdio0;
 		mmc1 = &sdmmc;
 		mmc2 = &sdhci;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-nanopi4.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-nanopi4.dtsi
index 7c5f441a2219..b7f1e47978a6 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-nanopi4.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-nanopi4.dtsi
@@ -18,6 +18,7 @@
 
 / {
 	aliases {
+		ethernet0 = &gmac;
 		mmc0 = &sdio0;
 		mmc1 = &sdmmc;
 		mmc2 = &sdhci;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-orangepi.dts b/arch/arm64/boot/dts/rockchip/rk3399-orangepi.dts
index dba4d03bfc2b..e7551449e718 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-orangepi.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-orangepi.dts
@@ -17,6 +17,7 @@
 	compatible = "rockchip,rk3399-orangepi", "rockchip,rk3399";
 
 	aliases {
+		ethernet0 = &gmac;
 		mmc0 = &sdio0;
 		mmc1 = &sdmmc;
 		mmc2 = &sdhci;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts
index 115c14c0a3c6..18a98c4648ea 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts
@@ -5,6 +5,7 @@
 
 /dts-v1/;
 #include "rk3399-puma.dtsi"
+#include <dt-bindings/input/input.h>
 
 / {
 	model = "Theobroma Systems RK3399-Q7 SoM";
@@ -18,6 +19,38 @@
 		stdout-path = "serial0:115200n8";
 	};
 
+	gpio-keys {
+		compatible = "gpio-keys";
+		pinctrl-0 = <&haikou_keys_pin>;
+		pinctrl-names = "default";
+
+		button-batlow-n {
+			gpios = <&gpio0 RK_PB2 GPIO_ACTIVE_LOW>;
+			label = "BATLOW#";
+			linux,code = <KEY_BATTERY>;
+		};
+
+		button-slp-btn-n {
+			gpios = <&gpio0 RK_PB3 GPIO_ACTIVE_LOW>;
+			label = "SLP_BTN#";
+			linux,code = <KEY_SLEEP>;
+		};
+
+		button-wake-n {
+			gpios = <&gpio0 RK_PB1 GPIO_ACTIVE_LOW>;
+			label = "WAKE#";
+			linux,code = <KEY_WAKEUP>;
+			wakeup-source;
+		};
+
+		switch-lid-btn-n {
+			gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>;
+			label = "LID_BTN#";
+			linux,code = <SW_LID>;
+			linux,input-type = <EV_SW>;
+		};
+	};
+
 	leds {
 		pinctrl-0 = <&module_led_pin>, <&sd_card_led_pin>;
 
@@ -165,11 +198,8 @@
 };
 
 &pinctrl {
-	pinctrl-names = "default";
-	pinctrl-0 = <&haikou_pin_hog>;
-
-	hog {
-		haikou_pin_hog: haikou-pin-hog {
+	buttons {
+		haikou_keys_pin: haikou-keys-pin {
 			rockchip,pins =
 			  /* LID_BTN */
 			  <0 RK_PA4 RK_FUNC_GPIO &pcfg_pull_up>,
@@ -177,7 +207,7 @@
 			  <0 RK_PB2 RK_FUNC_GPIO &pcfg_pull_up>,
 			  /* SLP_BTN# */
 			  <0 RK_PB3 RK_FUNC_GPIO &pcfg_pull_up>,
-			  /* BIOS_DISABLE# */
+			  /* WAKE# */
 			  <0 RK_PB1 RK_FUNC_GPIO &pcfg_pull_up>;
 		};
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
index 20e3f41efe97..c08e69391c01 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
@@ -9,6 +9,7 @@
 
 / {
 	aliases {
+		ethernet0 = &gmac;
 		mmc0 = &sdhci;
 	};
 
@@ -119,6 +120,20 @@
 	drive-impedance-ohm = <33>;
 };
 
+&gpio0 {
+	/*
+	 * The BIOS_DISABLE hog is a feedback pin for the actual status of the
+	 * signal. This usually represents the state of a switch on the baseboard.
+	 * The pin has a 10k pull-up resistor connected, so no pull-up setting is needed.
+	 */
+	bios-disable-hog {
+		gpios = <RK_PB0 GPIO_ACTIVE_HIGH>;
+		gpio-hog;
+		input;
+		line-name = "bios_disable";
+	};
+};
+
 &gmac {
 	assigned-clocks = <&cru SCLK_RMII_SRC>;
 	assigned-clock-parents = <&clkin_gmac>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi
index c32913df93c3..ca7a446b6568 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi
@@ -14,6 +14,7 @@
 	compatible = "firefly,roc-rk3399-pc", "rockchip,rk3399";
 
 	aliases {
+		ethernet0 = &gmac;
 		mmc0 = &sdmmc;
 		mmc1 = &sdhci;
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-4c-plus.dts b/arch/arm64/boot/dts/rockchip/rk3399-rock-4c-plus.dts
index 8bfd5f88d1ef..7baf9d1b22fd 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-rock-4c-plus.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-4c-plus.dts
@@ -15,6 +15,7 @@
 	compatible = "radxa,rock-4c-plus", "rockchip,rk3399";
 
 	aliases {
+		ethernet0 = &gmac;
 		mmc0 = &sdhci;
 		mmc1 = &sdmmc;
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi
index f2279aa6ca9e..281a12180703 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi
@@ -12,6 +12,7 @@
 
 / {
 	aliases {
+		ethernet0 = &gmac;
 		mmc0 = &sdhci;
 		mmc1 = &sdmmc;
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi
index bca2b50e0a93..f30b82a10ca3 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi
@@ -11,6 +11,7 @@
 
 / {
 	aliases {
+		ethernet0 = &gmac;
 		mmc0 = &sdio0;
 		mmc1 = &sdmmc;
 		mmc2 = &sdhci;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi
index e6ac292ce645..b3ef1c85e754 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi
@@ -12,6 +12,7 @@
 	compatible = "rockchip,rk3399-sapphire", "rockchip,rk3399";
 
 	aliases {
+		ethernet0 = &gmac;
 		mmc0 = &sdmmc;
 		mmc1 = &sdhci;
 	};
@@ -44,7 +45,7 @@
 	fan0: gpio-fan {
 		#cooling-cells = <2>;
 		compatible = "gpio-fan";
-		gpio-fan,speed-map = <0 0 3000 1>;
+		gpio-fan,speed-map = <0 0>, <3000 1>;
 		gpios = <&gpio1 RK_PC2 GPIO_ACTIVE_HIGH>;
 		status = "okay";
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index faf02e59d6c7..6e12c5a920ca 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -19,7 +19,11 @@
 	#size-cells = <2>;
 
 	aliases {
-		ethernet0 = &gmac;
+		gpio0 = &gpio0;
+		gpio1 = &gpio1;
+		gpio2 = &gpio2;
+		gpio3 = &gpio3;
+		gpio4 = &gpio4;
 		i2c0 = &i2c0;
 		i2c1 = &i2c1;
 		i2c2 = &i2c2;
@@ -1109,7 +1113,9 @@
 			power-domain@RK3399_PD_VDU {
 				reg = <RK3399_PD_VDU>;
 				clocks = <&cru ACLK_VDU>,
-					 <&cru HCLK_VDU>;
+					 <&cru HCLK_VDU>,
+					 <&cru SCLK_VDU_CA>,
+					 <&cru SCLK_VDU_CORE>;
 				pm_qos = <&qos_video_m1_r>,
 					 <&qos_video_m1_w>;
 				#power-domain-cells = <0>;
@@ -1384,7 +1390,7 @@
 
 	vdec: video-codec@ff660000 {
 		compatible = "rockchip,rk3399-vdec";
-		reg = <0x0 0xff660000 0x0 0x400>;
+		reg = <0x0 0xff660000 0x0 0x480>;
 		interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH 0>;
 		clocks = <&cru ACLK_VDU>, <&cru HCLK_VDU>,
 			 <&cru SCLK_VDU_CA>, <&cru SCLK_VDU_CORE>;
@@ -2112,6 +2118,7 @@
 		interrupt-names = "job", "mmu", "gpu";
 		clocks = <&cru ACLK_GPU>;
 		#cooling-cells = <2>;
+		dynamic-power-coefficient = <2640>;
 		power-domains = <&power RK3399_PD_GPU>;
 		status = "disabled";
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3399pro-vmarc-som.dtsi b/arch/arm64/boot/dts/rockchip/rk3399pro-vmarc-som.dtsi
index 8b8992a8e9c0..8823c924dc1d 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399pro-vmarc-som.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399pro-vmarc-som.dtsi
@@ -13,6 +13,7 @@
 	compatible = "vamrs,rk3399pro-vmarc-som", "rockchip,rk3399pro";
 
 	aliases {
+		ethernet0 = &gmac;
 		mmc0 = &sdhci;
 		mmc1 = &sdmmc;
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts b/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts
index 1c6d83b47cd2..6ecdf5d28339 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts
@@ -455,7 +455,7 @@
 &pinctrl {
 	leds {
 		sys_led_pin: sys-status-led-pin {
-			rockchip,pins = <0 RK_PC7 RK_FUNC_GPIO &pcfg_pull_none>;
+			rockchip,pins = <0 RK_PC5 RK_FUNC_GPIO &pcfg_pull_none>;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rgb30.dts b/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rgb30.dts
index 1ead3c5c24b3..0ac64f043b80 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rgb30.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rgb30.dts
@@ -5,67 +5,11 @@
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/linux-event-codes.h>
 #include <dt-bindings/pinctrl/rockchip.h>
-#include "rk3566-anbernic-rg353x.dtsi"
+#include "rk3566-powkiddy-rk2023.dtsi"
 
 / {
 	model = "RGB30";
 	compatible = "powkiddy,rgb30", "rockchip,rk3566";
-
-	aliases {
-		mmc1 = &sdmmc0;
-		mmc2 = &sdmmc1;
-		mmc3 = &sdmmc2;
-	};
-
-	battery: battery {
-		compatible = "simple-battery";
-		charge-full-design-microamp-hours = <3151000>;
-		charge-term-current-microamp = <300000>;
-		constant-charge-current-max-microamp = <2000000>;
-		constant-charge-voltage-max-microvolt = <4250000>;
-		factory-internal-resistance-micro-ohms = <117000>;
-		voltage-max-design-microvolt = <4172000>;
-		voltage-min-design-microvolt = <3400000>;
-
-		ocv-capacity-celsius = <20>;
-		ocv-capacity-table-0 =  <4172000 100>, <4092000 95>, <4035000 90>, <3990000 85>,
-					<3939000 80>, <3895000 75>, <3852000 70>, <3807000 65>,
-					<3762000 60>, <3713000 55>, <3672000 50>, <3647000 45>,
-					<3629000 40>, <3613000 35>, <3598000 30>, <3578000 25>,
-					<3550000 20>, <3519000 15>, <3479000 10>, <3438000 5>,
-					<3400000 0>;
-	};
-
-	/*
-	 * Channels reversed for speakers. Headphones automatically switch via hardware when
-	 * detected with no ability to control output in software. Headphones appear to be mono
-	 * (each output channel receives all audio). No microphone support on 3.5mm jack.
-	 */
-	sound {
-		compatible = "simple-audio-card";
-		simple-audio-card,name = "rk817_ext";
-		simple-audio-card,format = "i2s";
-		simple-audio-card,mclk-fs = <256>;
-		simple-audio-card,widgets =
-			"Headphone", "Headphones";
-		simple-audio-card,routing =
-			"Headphones", "HPOL",
-			"Headphones", "HPOR";
-
-		simple-audio-card,codec {
-			sound-dai = <&rk817>;
-		};
-
-		simple-audio-card,cpu {
-			sound-dai = <&i2s1_8ch>;
-		};
-	};
-};
-
-/delete-node/ &adc_keys;
-
-&chosen {
-	/delete-property/ stdout-path;
 };
 
 &cru {
@@ -75,87 +19,21 @@
 			       <200000000>, <292500000>;
 };
 
-&gpio_keys_control {
-	button-r1 {
-		gpios = <&gpio3 RK_PB3 GPIO_ACTIVE_LOW>;
-		label = "TR";
-		linux,code = <BTN_TR>;
-	};
-
-	button-r2 {
-		gpios = <&gpio3 RK_PB4 GPIO_ACTIVE_LOW>;
-		label = "TR2";
-		linux,code = <BTN_TR2>;
-	};
-};
-
-/delete-node/ &{/i2c@fdd40000/regulator@40};
-
-&i2c0 {
-	vdd_cpu: regulator@1c {
-		compatible = "tcs,tcs4525";
-		reg = <0x1c>;
-		fcs,suspend-voltage-selector = <1>;
-		regulator-always-on;
-		regulator-boot-on;
-		regulator-min-microvolt = <712500>;
-		regulator-max-microvolt = <1390000>;
-		regulator-name = "vdd_cpu";
-		regulator-ramp-delay = <2300>;
-		vin-supply = <&vcc_sys>;
-		regulator-state-mem {
-			regulator-off-in-suspend;
+&dsi0 {
+	panel: panel@0 {
+		compatible = "powkiddy,rgb30-panel";
+		reg = <0>;
+		backlight = <&backlight>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&lcd_rst>;
+		reset-gpios = <&gpio4 RK_PA0 GPIO_ACTIVE_LOW>;
+		vcc-supply = <&vcc3v3_lcd0_n>;
+		iovcc-supply = <&vcc3v3_lcd0_n>;
+
+		port {
+			mipi_in_panel: endpoint {
+				remote-endpoint = <&mipi_out_panel>;
+			};
 		};
 	};
 };
-
-/*
- * Device has 2 red LEDs instead of an amber and a red. Relabel LEDs as
- * red_led0 and red_led1.
- */
-/delete-node/ &{/pwm-leds/led-1};
-/delete-node/ &{/pwm-leds/led-2};
-
-&leds {
-	red_led0: led-1 {
-		color = <LED_COLOR_ID_RED>;
-		function = LED_FUNCTION_CHARGING;
-		max-brightness = <255>;
-		pwms = <&pwm7 0 25000 0>;
-	};
-
-	red_led1: led-2 {
-		color = <LED_COLOR_ID_RED>;
-		default-state = "off";
-		function = LED_FUNCTION_STATUS;
-		max-brightness = <255>;
-		pwms = <&pwm0 0 25000 0>;
-	};
-};
-
-&panel {
-	compatible = "powkiddy,rgb30-panel";
-	vcc-supply = <&vcc3v3_lcd0_n>;
-	iovcc-supply = <&vcc3v3_lcd0_n>;
-	/delete-property/ vdd-supply;
-};
-
-&pwm5 {
-	status = "disabled";
-};
-
-&rk817 {
-	rk817_charger: charger {
-		monitored-battery = <&battery>;
-		rockchip,resistor-sense-micro-ohms = <10000>;
-		rockchip,sleep-enter-current-microamp = <300000>;
-		rockchip,sleep-filter-current-microamp = <100000>;
-	};
-};
-
-/* There is no UART header visible on the board for this device. */
-&uart2 {
-	status = "disabled";
-};
-
-/delete-node/ &vibrator;
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rk2023.dts b/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rk2023.dts
new file mode 100644
index 000000000000..ba32d0793dca
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rk2023.dts
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/linux-event-codes.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+#include "rk3566-powkiddy-rk2023.dtsi"
+
+/ {
+	model = "RK2023";
+	compatible = "powkiddy,rk2023", "rockchip,rk3566";
+};
+
+&cru {
+	assigned-clocks = <&pmucru CLK_RTC_32K>, <&cru PLL_GPLL>,
+			  <&pmucru PLL_PPLL>, <&cru PLL_VPLL>;
+	assigned-clock-rates = <32768>, <1200000000>,
+			  <200000000>, <115200000>;
+};
+
+&dsi0 {
+	panel: panel@0 {
+		compatible = "powkiddy,rk2023-panel", "newvision,nv3051d";
+		reg = <0>;
+		backlight = <&backlight>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&lcd_rst>;
+		reset-gpios = <&gpio4 RK_PA0 GPIO_ACTIVE_LOW>;
+		vdd-supply = <&vcc3v3_lcd0_n>;
+
+		port {
+			mipi_in_panel: endpoint {
+				remote-endpoint = <&mipi_out_panel>;
+			};
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rk2023.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rk2023.dtsi
new file mode 100644
index 000000000000..0fa8f06f94cd
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rk2023.dtsi
@@ -0,0 +1,875 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/linux-event-codes.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+#include <dt-bindings/soc/rockchip,vop2.h>
+#include "rk3566.dtsi"
+
+/ {
+	aliases {
+		mmc1 = &sdmmc0;
+		mmc2 = &sdmmc1;
+		mmc3 = &sdmmc2;
+	};
+
+	adc-joystick {
+		compatible = "adc-joystick";
+		io-channels = <&adc_mux 0>,
+			      <&adc_mux 1>,
+			      <&adc_mux 2>,
+			      <&adc_mux 3>;
+		pinctrl-0 = <&joy_mux_en>;
+		pinctrl-names = "default";
+		poll-interval = <60>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		axis@0 {
+			reg = <0>;
+			abs-flat = <32>;
+			abs-fuzz = <32>;
+			abs-range = <1023 15>;
+			linux,code = <ABS_X>;
+		};
+
+		axis@1 {
+			reg = <1>;
+			abs-flat = <32>;
+			abs-fuzz = <32>;
+			abs-range = <15 1023>;
+			linux,code = <ABS_RX>;
+		};
+
+		axis@2 {
+			reg = <2>;
+			abs-flat = <32>;
+			abs-fuzz = <32>;
+			abs-range = <15 1023>;
+			linux,code = <ABS_Y>;
+		};
+
+		axis@3 {
+			reg = <3>;
+			abs-flat = <32>;
+			abs-fuzz = <32>;
+			abs-range = <1023 15>;
+			linux,code = <ABS_RY>;
+		};
+	};
+
+	adc_mux: adc-mux {
+		compatible = "io-channel-mux";
+		channels = "left_x", "right_x", "left_y", "right_y";
+		#io-channel-cells = <1>;
+		io-channels = <&saradc 3>;
+		io-channel-names = "parent";
+		mux-controls = <&gpio_mux>;
+		settle-time-us = <100>;
+	};
+
+	backlight: backlight {
+		compatible = "pwm-backlight";
+		power-supply = <&vcc_sys>;
+		pwms = <&pwm4 0 25000 0>;
+	};
+
+	battery: battery {
+		compatible = "simple-battery";
+		charge-full-design-microamp-hours = <3151000>;
+		charge-term-current-microamp = <300000>;
+		constant-charge-current-max-microamp = <2000000>;
+		constant-charge-voltage-max-microvolt = <4250000>;
+		factory-internal-resistance-micro-ohms = <117000>;
+		voltage-max-design-microvolt = <4172000>;
+		voltage-min-design-microvolt = <3400000>;
+
+		ocv-capacity-celsius = <20>;
+		ocv-capacity-table-0 =  <4172000 100>, <4092000 95>, <4035000 90>, <3990000 85>,
+					<3939000 80>, <3895000 75>, <3852000 70>, <3807000 65>,
+					<3762000 60>, <3713000 55>, <3672000 50>, <3647000 45>,
+					<3629000 40>, <3613000 35>, <3598000 30>, <3578000 25>,
+					<3550000 20>, <3519000 15>, <3479000 10>, <3438000 5>,
+					<3400000 0>;
+	};
+
+	gpio_keys_control: gpio-keys-control {
+		compatible = "gpio-keys";
+		pinctrl-0 = <&btn_pins_ctrl>;
+		pinctrl-names = "default";
+
+		button-a {
+			gpios = <&gpio3 RK_PC2 GPIO_ACTIVE_LOW>;
+			label = "EAST";
+			linux,code = <BTN_EAST>;
+		};
+
+		button-b {
+			gpios = <&gpio3 RK_PC3 GPIO_ACTIVE_LOW>;
+			label = "SOUTH";
+			linux,code = <BTN_SOUTH>;
+		};
+
+		button-down {
+			gpios = <&gpio3 RK_PA4 GPIO_ACTIVE_LOW>;
+			label = "DPAD-DOWN";
+			linux,code = <BTN_DPAD_DOWN>;
+		};
+
+		button-l1 {
+			gpios = <&gpio3 RK_PB1 GPIO_ACTIVE_LOW>;
+			label = "TL";
+			linux,code = <BTN_TL>;
+		};
+
+		button-l2 {
+			gpios = <&gpio3 RK_PB2 GPIO_ACTIVE_LOW>;
+			label = "TL2";
+			linux,code = <BTN_TL2>;
+		};
+
+		button-left {
+			gpios = <&gpio3 RK_PA6 GPIO_ACTIVE_LOW>;
+			label = "DPAD-LEFT";
+			linux,code = <BTN_DPAD_LEFT>;
+		};
+
+		button-r1 {
+			gpios = <&gpio3 RK_PB3 GPIO_ACTIVE_LOW>;
+			label = "TR";
+			linux,code = <BTN_TR>;
+		};
+
+		button-r2 {
+			gpios = <&gpio3 RK_PB4 GPIO_ACTIVE_LOW>;
+			label = "TR2";
+			linux,code = <BTN_TR2>;
+		};
+
+		button-right {
+			gpios = <&gpio3 RK_PA5 GPIO_ACTIVE_LOW>;
+			label = "DPAD-RIGHT";
+			linux,code = <BTN_DPAD_RIGHT>;
+		};
+
+		button-select {
+			gpios = <&gpio3 RK_PB6 GPIO_ACTIVE_LOW>;
+			label = "SELECT";
+			linux,code = <BTN_SELECT>;
+		};
+
+		button-start {
+			gpios = <&gpio3 RK_PB5 GPIO_ACTIVE_LOW>;
+			label = "START";
+			linux,code = <BTN_START>;
+		};
+
+		button-thumbl {
+			gpios = <&gpio3 RK_PA1 GPIO_ACTIVE_LOW>;
+			label = "THUMBL";
+			linux,code = <BTN_THUMBL>;
+		};
+
+		button-thumbr {
+			gpios = <&gpio3 RK_PA2 GPIO_ACTIVE_LOW>;
+			label = "THUMBR";
+			linux,code = <BTN_THUMBR>;
+		};
+
+		button-up {
+			gpios = <&gpio3 RK_PA3 GPIO_ACTIVE_LOW>;
+			label = "DPAD-UP";
+			linux,code = <BTN_DPAD_UP>;
+		};
+
+		button-x {
+			gpios = <&gpio3 RK_PC0 GPIO_ACTIVE_LOW>;
+			label = "NORTH";
+			linux,code = <BTN_NORTH>;
+		};
+
+		button-y {
+			gpios = <&gpio3 RK_PC1 GPIO_ACTIVE_LOW>;
+			label = "WEST";
+			linux,code = <BTN_WEST>;
+		};
+	};
+
+	gpio_keys_vol: gpio-keys-vol {
+		compatible = "gpio-keys";
+		autorepeat;
+		pinctrl-0 = <&btn_pins_vol>;
+		pinctrl-names = "default";
+
+		button-vol-down {
+			gpios = <&gpio3 RK_PB0 GPIO_ACTIVE_LOW>;
+			label = "VOLUMEDOWN";
+			linux,code = <KEY_VOLUMEDOWN>;
+		};
+
+		button-vol-up {
+			gpios = <&gpio3 RK_PA7 GPIO_ACTIVE_LOW>;
+			label = "VOLUMEUP";
+			linux,code = <KEY_VOLUMEUP>;
+		};
+	};
+
+	gpio_mux: mux-controller {
+		compatible = "gpio-mux";
+		mux-gpios = <&gpio0 RK_PB6 GPIO_ACTIVE_LOW>,
+			    <&gpio0 RK_PB7 GPIO_ACTIVE_LOW>;
+		#mux-control-cells = <0>;
+	};
+
+	hdmi-con {
+		compatible = "hdmi-connector";
+		ddc-i2c-bus = <&i2c5>;
+		type = "c";
+
+		port {
+			hdmi_con_in: endpoint {
+				remote-endpoint = <&hdmi_out_con>;
+			};
+		};
+	};
+
+	/*
+	 * Device also includes an always on LED that is wired to the 5V input
+	 * voltage and is on when the device is plugged in.
+	 */
+	leds: pwm-leds {
+		compatible = "pwm-leds";
+
+		green_led: led-0 {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_STATUS;
+			max-brightness = <255>;
+			pwms = <&pwm6 0 25000 0>;
+		};
+
+		red_led: led-1 {
+			color = <LED_COLOR_ID_RED>;
+			function = LED_FUNCTION_CHARGING;
+			max-brightness = <255>;
+			pwms = <&pwm7 0 25000 0>;
+		};
+	};
+
+	sdio_pwrseq: sdio-pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		clocks = <&rk817 1>;
+		clock-names = "ext_clock";
+		pinctrl-0 = <&wifi_enable_h>;
+		pinctrl-names = "default";
+		post-power-on-delay-ms = <200>;
+		reset-gpios = <&gpio4 RK_PA2 GPIO_ACTIVE_LOW>;
+	};
+
+	/*
+	 * Channels reversed for speakers. Headphones automatically switch via hardware when
+	 * detected with no ability to control output in software. Headphones appear to be mono
+	 * (each output channel receives all audio). No microphone support on 3.5mm jack.
+	 */
+	sound {
+		compatible = "simple-audio-card";
+		simple-audio-card,name = "rk817_ext";
+		simple-audio-card,format = "i2s";
+		simple-audio-card,mclk-fs = <256>;
+		simple-audio-card,widgets =
+			"Headphone", "Headphones";
+		simple-audio-card,routing =
+			"Headphones", "HPOL",
+			"Headphones", "HPOR";
+
+		simple-audio-card,codec {
+			sound-dai = <&rk817>;
+		};
+
+		simple-audio-card,cpu {
+			sound-dai = <&i2s1_8ch>;
+		};
+	};
+
+	vcc3v3_lcd0_n: regulator-vcc3v3-lcd0 {
+		compatible = "regulator-fixed";
+		gpio = <&gpio0 RK_PC2 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		pinctrl-0 = <&vcc_lcd_h>;
+		pinctrl-names = "default";
+		regulator-boot-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-name = "vcc3v3_lcd0_n";
+		vin-supply = <&vcc_3v3>;
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+
+	vcc_sys: regulator-vcc-sys {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <3800000>;
+		regulator-max-microvolt = <3800000>;
+		regulator-name = "vcc_sys";
+	};
+
+	vcc_wifi: regulator-vcc-wifi {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio0 RK_PA0 GPIO_ACTIVE_HIGH>;
+		pinctrl-0 = <&vcc_wifi_h>;
+		pinctrl-names = "default";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-name = "vcc_wifi";
+	};
+};
+
+&combphy1 {
+	status = "okay";
+};
+
+&cpu0 {
+	cpu-supply = <&vdd_cpu>;
+};
+
+&cpu1 {
+	cpu-supply = <&vdd_cpu>;
+};
+
+&cpu2 {
+	cpu-supply = <&vdd_cpu>;
+};
+
+&cpu3 {
+	cpu-supply = <&vdd_cpu>;
+};
+
+&dsi0 {
+	status = "okay";
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	ports {
+		dsi0_in: port@0 {
+			reg = <0>;
+			dsi0_in_vp1: endpoint {
+				remote-endpoint = <&vp1_out_dsi0>;
+			};
+		};
+
+		dsi0_out: port@1 {
+			reg = <1>;
+			mipi_out_panel: endpoint {
+				remote-endpoint = <&mipi_in_panel>;
+			};
+		};
+	};
+};
+
+&dsi_dphy0 {
+	status = "okay";
+};
+
+&gpu {
+	mali-supply = <&vdd_gpu>;
+	status = "okay";
+};
+
+&hdmi {
+	ddc-i2c-bus = <&i2c5>;
+	pinctrl-0 = <&hdmitxm0_cec>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&hdmi_in {
+	hdmi_in_vp0: endpoint {
+		remote-endpoint = <&vp0_out_hdmi>;
+	};
+};
+
+&hdmi_out {
+	hdmi_out_con: endpoint {
+		remote-endpoint = <&hdmi_con_in>;
+	};
+};
+
+&hdmi_sound {
+	status = "okay";
+};
+
+&i2c0 {
+	status = "okay";
+
+	rk817: pmic@20 {
+		compatible = "rockchip,rk817";
+		reg = <0x20>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <RK_PA3 IRQ_TYPE_LEVEL_LOW>;
+		clock-output-names = "rk808-clkout1", "rk808-clkout2";
+		clock-names = "mclk";
+		clocks = <&cru I2S1_MCLKOUT_TX>;
+		assigned-clocks = <&cru I2S1_MCLKOUT_TX>;
+		assigned-clock-parents = <&cru CLK_I2S1_8CH_TX>;
+		#clock-cells = <1>;
+		#sound-dai-cells = <0>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&i2s1m0_mclk>, <&pmic_int_l>;
+		wakeup-source;
+
+		vcc1-supply = <&vcc_sys>;
+		vcc2-supply = <&vcc_sys>;
+		vcc3-supply = <&vcc_sys>;
+		vcc4-supply = <&vcc_sys>;
+		vcc5-supply = <&vcc_sys>;
+		vcc6-supply = <&vcc_sys>;
+		vcc7-supply = <&vcc_sys>;
+		vcc8-supply = <&vcc_sys>;
+		vcc9-supply = <&dcdc_boost>;
+
+		regulators {
+			vdd_logic: DCDC_REG1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <500000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <6001>;
+				regulator-initial-mode = <0x2>;
+				regulator-name = "vdd_logic";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <900000>;
+				};
+			};
+
+			vdd_gpu: DCDC_REG2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <500000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <6001>;
+				regulator-initial-mode = <0x2>;
+				regulator-name = "vdd_gpu";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_ddr: DCDC_REG3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-initial-mode = <0x2>;
+				regulator-name = "vcc_ddr";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+				};
+			};
+
+			vcc_3v3: DCDC_REG4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-initial-mode = <0x2>;
+				regulator-name = "vcc_3v3";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			vcca1v8_pmu: LDO_REG1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcca1v8_pmu";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vdda_0v9: LDO_REG2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <900000>;
+				regulator-max-microvolt = <900000>;
+				regulator-name = "vdda_0v9";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdda0v9_pmu: LDO_REG3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <900000>;
+				regulator-max-microvolt = <900000>;
+				regulator-name = "vdda0v9_pmu";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <900000>;
+				};
+			};
+
+			vccio_acodec: LDO_REG4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vccio_acodec";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vccio_sd: LDO_REG5 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vccio_sd";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc3v3_pmu: LDO_REG6 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcc3v3_pmu";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			vcc_1v8: LDO_REG7 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc_1v8";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc1v8_dvp: LDO_REG8 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcc1v8_dvp";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc2v8_dvp: LDO_REG9 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-name = "vcc2v8_dvp";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			dcdc_boost: BOOST {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <4700000>;
+				regulator-max-microvolt = <5400000>;
+				regulator-name = "boost";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			otg_switch: OTG_SWITCH {
+				regulator-name = "otg_switch";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+		};
+
+		rk817_charger: charger {
+			monitored-battery = <&battery>;
+			rockchip,resistor-sense-micro-ohms = <10000>;
+			rockchip,sleep-enter-current-microamp = <300000>;
+			rockchip,sleep-filter-current-microamp = <100000>;
+		};
+	};
+
+	vdd_cpu: regulator@1c {
+		compatible = "tcs,tcs4525";
+		reg = <0x1c>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <712500>;
+		regulator-max-microvolt = <1390000>;
+		regulator-name = "vdd_cpu";
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc_sys>;
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+};
+
+&i2c5 {
+	pinctrl-0 = <&i2c5m1_xfer>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&i2s0_8ch {
+	status = "okay";
+};
+
+&i2s1_8ch {
+	pinctrl-0 = <&i2s1m0_sclktx
+		     &i2s1m0_lrcktx
+		     &i2s1m0_sdi0
+		     &i2s1m0_sdo0>;
+	pinctrl-names = "default";
+	rockchip,trcm-sync-tx-only;
+	status = "okay";
+};
+
+&pinctrl {
+	gpio-btns {
+		btn_pins_ctrl: btn-pins-ctrl {
+			rockchip,pins =
+				<3 RK_PA1 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PA2 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PA3 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PA4 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PA5 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PA6 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PB1 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PB2 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PB3 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PB4 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PB5 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PB6 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PC0 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PC1 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PC2 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PC3 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+
+		btn_pins_vol: btn-pins-vol {
+			rockchip,pins =
+				<3 RK_PA7 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PB0 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	joy-mux {
+		joy_mux_en: joy-mux-en {
+			rockchip,pins =
+				<0 RK_PB5 RK_FUNC_GPIO &pcfg_output_low>;
+		};
+	};
+
+	gpio-lcd {
+		lcd_rst: lcd-rst {
+			rockchip,pins =
+				<4 RK_PA0 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	pmic {
+		pmic_int_l: pmic-int-l {
+			rockchip,pins =
+				<0 RK_PA3 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	sdio-pwrseq {
+		wifi_enable_h: wifi-enable-h {
+			rockchip,pins =
+				<4 RK_PA2 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	vcc3v3-lcd {
+		vcc_lcd_h: vcc-lcd-h {
+			rockchip,pins =
+				<0 RK_PC2 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	vcc-wifi {
+		vcc_wifi_h: vcc-wifi-h {
+			rockchip,pins =
+				<0 RK_PA0 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&pmu_io_domains {
+	status = "okay";
+	pmuio1-supply = <&vcc3v3_pmu>;
+	pmuio2-supply = <&vcc3v3_pmu>;
+	vccio1-supply = <&vccio_acodec>;
+	vccio3-supply = <&vccio_sd>;
+	vccio4-supply = <&vcc_1v8>;
+	vccio5-supply = <&vcc_3v3>;
+	vccio6-supply = <&vcc1v8_dvp>;
+	vccio7-supply = <&vcc_3v3>;
+};
+
+&pwm4 {
+	status = "okay";
+};
+
+&pwm6 {
+	status = "okay";
+};
+
+&pwm7 {
+	status = "okay";
+};
+
+&saradc {
+	vref-supply = <&vcc_1v8>;
+	status = "okay";
+};
+
+&sdmmc0 {
+	bus-width = <4>;
+	cap-sd-highspeed;
+	cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>;
+	disable-wp;
+	pinctrl-0 = <&sdmmc0_bus4 &sdmmc0_clk &sdmmc0_cmd &sdmmc0_det>;
+	pinctrl-names = "default";
+	sd-uhs-sdr104;
+	vmmc-supply = <&vcc_3v3>;
+	vqmmc-supply = <&vccio_sd>;
+	status = "okay";
+};
+
+&sdmmc1 {
+	bus-width = <4>;
+	cap-sd-highspeed;
+	cd-gpios = <&gpio2 RK_PB2 GPIO_ACTIVE_LOW>;
+	disable-wp;
+	pinctrl-0 = <&sdmmc1_bus4 &sdmmc1_cmd &sdmmc1_clk &sdmmc1_det>;
+	pinctrl-names = "default";
+	sd-uhs-sdr104;
+	vmmc-supply = <&vcc_3v3>;
+	vqmmc-supply = <&vcc1v8_dvp>;
+	status = "okay";
+};
+
+&sdmmc2 {
+	bus-width = <4>;
+	cap-sd-highspeed;
+	cap-sdio-irq;
+	keep-power-in-suspend;
+	mmc-pwrseq = <&sdio_pwrseq>;
+	non-removable;
+	pinctrl-0 = <&sdmmc2m0_bus4 &sdmmc2m0_cmd &sdmmc2m0_clk>;
+	pinctrl-names = "default";
+	vmmc-supply = <&vcc_wifi>;
+	vqmmc-supply = <&vcca1v8_pmu>;
+	status = "okay";
+};
+
+&tsadc {
+	rockchip,hw-tshut-mode = <1>;
+	rockchip,hw-tshut-polarity = <0>;
+	status = "okay";
+};
+
+&uart1 {
+	pinctrl-0 = <&uart1m1_xfer &uart1m1_ctsn &uart1m1_rtsn>;
+	pinctrl-names = "default";
+	uart-has-rtscts;
+	status = "okay";
+
+	bluetooth {
+		compatible = "realtek,rtl8821cs-bt", "realtek,rtl8723bs-bt";
+		device-wake-gpios = <&gpio4 4 GPIO_ACTIVE_HIGH>;
+		enable-gpios = <&gpio4 3 GPIO_ACTIVE_HIGH>;
+		host-wake-gpios = <&gpio4 5 GPIO_ACTIVE_HIGH>;
+	};
+};
+
+&usb_host0_xhci {
+	dr_mode = "peripheral";
+	phys = <&usb2phy0_otg>;
+	phy-names = "usb2-phy";
+	status = "okay";
+};
+
+&usb_host1_ehci {
+	status = "okay";
+};
+
+&usb_host1_ohci {
+	status = "okay";
+};
+
+&usb_host1_xhci {
+	phy-names = "usb2-phy", "usb3-phy";
+	phys = <&usb2phy1_host>, <&combphy1 PHY_TYPE_USB3>;
+	status = "okay";
+};
+
+&usb2phy0 {
+	status = "okay";
+};
+
+&usb2phy0_otg {
+	status = "okay";
+};
+
+&usb2phy1 {
+	status = "okay";
+};
+
+&usb2phy1_host {
+	status = "okay";
+};
+
+&vop {
+	assigned-clocks = <&cru DCLK_VOP0>, <&cru DCLK_VOP1>;
+	assigned-clock-parents = <&pmucru PLL_HPLL>, <&cru PLL_VPLL>;
+	status = "okay";
+};
+
+&vop_mmu {
+	status = "okay";
+};
+
+&vp0 {
+	vp0_out_hdmi: endpoint@ROCKCHIP_VOP2_EP_HDMI0 {
+		reg = <ROCKCHIP_VOP2_EP_HDMI0>;
+		remote-endpoint = <&hdmi_in_vp0>;
+	};
+};
+
+&vp1 {
+	vp1_out_dsi0: endpoint@ROCKCHIP_VOP2_EP_MIPI0 {
+		reg = <ROCKCHIP_VOP2_EP_MIPI0>;
+		remote-endpoint = <&dsi0_in_vp1>;
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-x55.dts b/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-x55.dts
new file mode 100644
index 000000000000..4786b19fd017
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-x55.dts
@@ -0,0 +1,926 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/linux-event-codes.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+#include <dt-bindings/soc/rockchip,vop2.h>
+#include "rk3566.dtsi"
+
+/ {
+	model = "Powkiddy x55";
+	compatible = "powkiddy,x55", "rockchip,rk3566";
+
+	aliases {
+		mmc0 = &sdhci;
+		mmc1 = &sdmmc0;
+		mmc2 = &sdmmc2;
+		mmc3 = &sdmmc1;
+	};
+
+	chosen: chosen {
+		stdout-path = "serial2:1500000n8";
+	};
+
+	adc_joystick: adc-joystick {
+		compatible = "adc-joystick";
+		io-channels = <&saradc 0>, <&saradc 1>,
+			      <&saradc 2>, <&saradc 3>;
+		poll-interval = <60>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		axis@0 {
+			reg = <0>;
+			abs-flat = <30>;
+			abs-fuzz = <20>;
+			abs-range = <15 1023>;
+			linux,code = <ABS_X>;
+		};
+
+		axis@1 {
+			reg = <1>;
+			abs-flat = <30>;
+			abs-fuzz = <20>;
+			abs-range = <1023 15>;
+			linux,code = <ABS_Y>;
+		};
+
+		axis@2 {
+			reg = <2>;
+			abs-flat = <30>;
+			abs-fuzz = <20>;
+			abs-range = <15 1023>;
+			linux,code = <ABS_RX>;
+		};
+
+		axis@3 {
+			reg = <3>;
+			abs-flat = <30>;
+			abs-fuzz = <20>;
+			abs-range = <1023 15>;
+			linux,code = <ABS_RY>;
+		};
+	};
+
+	backlight: backlight {
+		compatible = "pwm-backlight";
+		power-supply = <&vcc_sys>;
+		pwms = <&pwm4 0 25000 0>;
+	};
+
+	battery: battery {
+		compatible = "simple-battery";
+		charge-full-design-microamp-hours = <4000000>;
+		charge-term-current-microamp = <300000>;
+		constant-charge-current-max-microamp = <2000000>;
+		constant-charge-voltage-max-microvolt = <4300000>;
+		factory-internal-resistance-micro-ohms = <91000>;
+		voltage-max-design-microvolt = <4138000>;
+		voltage-min-design-microvolt = <3400000>;
+
+		ocv-capacity-celsius = <20>;
+		ocv-capacity-table-0 =  <4138000 100>, <4083000 95>, <4059000 90>, <4044000 85>,
+					<4030000 80>, <4020000 75>, <4006000 70>, <3972000 65>,
+					<3934000 60>, <3904000 55>, <3878000 50>, <3857000 45>,
+					<3843000 40>, <3826000 35>, <3801000 30>, <3768000 25>,
+					<3735000 20>, <3688000 15>, <3621000 10>, <3553000 5>,
+					<3400000 0>;
+	};
+
+	gpio_keys_control: gpio-keys-control {
+		compatible = "gpio-keys";
+		pinctrl-0 = <&btn_pins_ctrl>;
+		pinctrl-names = "default";
+
+		button-a {
+			gpios = <&gpio3 RK_PD3 GPIO_ACTIVE_LOW>;
+			label = "EAST";
+			linux,code = <BTN_EAST>;
+		};
+
+		button-b {
+			gpios = <&gpio3 RK_PD2 GPIO_ACTIVE_LOW>;
+			label = "SOUTH";
+			linux,code = <BTN_SOUTH>;
+		};
+
+		button-down {
+			gpios = <&gpio4 RK_PA1 GPIO_ACTIVE_LOW>;
+			label = "DPAD-DOWN";
+			linux,code = <BTN_DPAD_DOWN>;
+		};
+
+		button-l1 {
+			gpios = <&gpio3 RK_PD0 GPIO_ACTIVE_LOW>;
+			label = "TL";
+			linux,code = <BTN_TL>;
+		};
+
+		button-l2 {
+			gpios = <&gpio3 RK_PD1 GPIO_ACTIVE_LOW>;
+			label = "TL2";
+			linux,code = <BTN_TL2>;
+		};
+
+		button-left {
+			gpios = <&gpio3 RK_PD6 GPIO_ACTIVE_LOW>;
+			label = "DPAD-LEFT";
+			linux,code = <BTN_DPAD_LEFT>;
+		};
+
+		button-right {
+			gpios = <&gpio3 RK_PD7 GPIO_ACTIVE_LOW>;
+			label = "DPAD-RIGHT";
+			linux,code = <BTN_DPAD_RIGHT>;
+		};
+
+		button-select {
+			gpios = <&gpio4 RK_PA4 GPIO_ACTIVE_LOW>;
+			label = "SELECT";
+			linux,code = <BTN_SELECT>;
+		};
+
+		button-start {
+			gpios = <&gpio4 RK_PA2 GPIO_ACTIVE_LOW>;
+			label = "START";
+			linux,code = <BTN_START>;
+		};
+
+		button-thumbl {
+			gpios = <&gpio4 RK_PA7 GPIO_ACTIVE_LOW>;
+			label = "THUMBL";
+			linux,code = <BTN_THUMBL>;
+		};
+
+		button-thumbr {
+			gpios = <&gpio4 RK_PB0 GPIO_ACTIVE_LOW>;
+			label = "THUMBR";
+			linux,code = <BTN_THUMBR>;
+		};
+
+		button-r1 {
+			gpios = <&gpio3 RK_PC6 GPIO_ACTIVE_LOW>;
+			label = "TR";
+			linux,code = <BTN_TR>;
+		};
+
+		button-r2 {
+			gpios = <&gpio3 RK_PC7 GPIO_ACTIVE_LOW>;
+			label = "TR2";
+			linux,code = <BTN_TR2>;
+		};
+
+		button-up {
+			gpios = <&gpio4 RK_PA0 GPIO_ACTIVE_LOW>;
+			label = "DPAD-UP";
+			linux,code = <BTN_DPAD_UP>;
+		};
+
+		button-x {
+			gpios = <&gpio3 RK_PD5 GPIO_ACTIVE_LOW>;
+			label = "NORTH";
+			linux,code = <BTN_NORTH>;
+		};
+
+		button-y {
+			gpios = <&gpio3 RK_PD4 GPIO_ACTIVE_LOW>;
+			label = "WEST";
+			linux,code = <BTN_WEST>;
+		};
+	};
+
+	gpio_keys_vol: gpio-keys-vol {
+		compatible = "gpio-keys";
+		autorepeat;
+		pinctrl-0 = <&btn_pins_vol>;
+		pinctrl-names = "default";
+
+		button-voldown {
+			gpios = <&gpio4 RK_PA3 GPIO_ACTIVE_LOW>;
+			label = "VOLUMEDOWN";
+			linux,code = <KEY_VOLUMEDOWN>;
+		};
+
+		button-volup {
+			gpios = <&gpio4 RK_PA5 GPIO_ACTIVE_LOW>;
+			label = "VOLUMEUP";
+			linux,code = <KEY_VOLUMEUP>;
+		};
+	};
+
+	gpio_leds: gpio-leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&led_pins>;
+
+		red_led: led-0 {
+			color = <LED_COLOR_ID_RED>;
+			default-state = "off";
+			gpios = <&gpio4 RK_PB4 GPIO_ACTIVE_HIGH>;
+			function = LED_FUNCTION_STATUS;
+		};
+
+		green_led: led-1 {
+			color = <LED_COLOR_ID_GREEN>;
+			default-state = "on";
+			gpios = <&gpio4 RK_PB5 GPIO_ACTIVE_HIGH>;
+			function = LED_FUNCTION_POWER;
+		};
+
+		amber_led: led-2 {
+			color = <LED_COLOR_ID_AMBER>;
+			gpios = <&gpio4 RK_PB6 GPIO_ACTIVE_HIGH>;
+			function = LED_FUNCTION_CHARGING;
+		};
+
+	};
+
+	hdmi-con {
+		compatible = "hdmi-connector";
+		ddc-i2c-bus = <&i2c5>;
+		type = "c";
+
+		port {
+			hdmi_con_in: endpoint {
+				remote-endpoint = <&hdmi_out_con>;
+			};
+		};
+	};
+
+	sdio_pwrseq: sdio-pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		clocks = <&rk817 1>;
+		clock-names = "ext_clock";
+		pinctrl-0 = <&wifi_enable_h>;
+		pinctrl-names = "default";
+		post-power-on-delay-ms = <200>;
+		reset-gpios = <&gpio0 RK_PC0 GPIO_ACTIVE_LOW>;
+	};
+
+	/* Channels reversed for both headphones and speakers. */
+	sound {
+		compatible = "simple-audio-card";
+		pinctrl-0 = <&hp_det>;
+		pinctrl-names = "default";
+		simple-audio-card,name = "rk817_ext";
+		simple-audio-card,aux-devs = <&spk_amp>;
+		simple-audio-card,format = "i2s";
+		simple-audio-card,hp-det-gpio = <&gpio4 RK_PC6 GPIO_ACTIVE_HIGH>;
+		simple-audio-card,mclk-fs = <256>;
+		simple-audio-card,widgets =
+			"Microphone", "Mic Jack",
+			"Headphone", "Headphones",
+			"Speaker", "Internal Speakers";
+		simple-audio-card,routing =
+			"MICL", "Mic Jack",
+			"Headphones", "HPOL",
+			"Headphones", "HPOR",
+			"Internal Speakers", "Speaker Amp OUTL",
+			"Internal Speakers", "Speaker Amp OUTR",
+			"Speaker Amp INL", "HPOL",
+			"Speaker Amp INR", "HPOR";
+		simple-audio-card,pin-switches = "Internal Speakers";
+
+		simple-audio-card,codec {
+			sound-dai = <&rk817>;
+		};
+
+		simple-audio-card,cpu {
+			sound-dai = <&i2s1_8ch>;
+		};
+	};
+
+	spk_amp: audio-amplifier {
+		compatible = "simple-audio-amplifier";
+		enable-gpios = <&gpio4 RK_PC2 GPIO_ACTIVE_HIGH>;
+		pinctrl-0 = <&spk_amp_enable_h>;
+		pinctrl-names = "default";
+		sound-name-prefix = "Speaker Amp";
+	};
+
+	vcc5v0_host: regulator-vcc5v0-host {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio4 RK_PC4 GPIO_ACTIVE_HIGH>;
+		pinctrl-0 = <&vcc5v0_host_en>;
+		pinctrl-names = "default";
+		regulator-name = "vcc5v0_host";
+		vin-supply = <&dcdc_boost>;
+	};
+
+	vcc_lcd: regulator-vcc-lcd {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio0 RK_PC7 GPIO_ACTIVE_HIGH>;
+		pinctrl-0 = <&vcc_lcd_en>;
+		pinctrl-names = "default";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-name = "vcc_lcd";
+	};
+
+	vcc_sys: regulator-vcc-sys {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <3800000>;
+		regulator-max-microvolt = <3800000>;
+		regulator-name = "vcc_sys";
+	};
+
+	vcc_wifi: regulator-vcc-wifi {
+		compatible = "regulator-fixed";
+		gpio = <&gpio0 RK_PA0 GPIO_ACTIVE_LOW>;
+		pinctrl-0 = <&vcc_wifi_h>;
+		pinctrl-names = "default";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-name = "vcc_wifi";
+	};
+};
+
+&combphy1 {
+	status = "okay";
+};
+
+&cru {
+	assigned-clocks = <&pmucru CLK_RTC_32K>, <&cru PLL_GPLL>,
+			  <&pmucru PLL_PPLL>, <&cru PLL_VPLL>;
+	assigned-clock-rates = <32768>, <1200000000>,
+			       <200000000>, <126400000>;
+};
+
+&cpu0 {
+	cpu-supply = <&vdd_cpu>;
+};
+
+&cpu1 {
+	cpu-supply = <&vdd_cpu>;
+};
+
+&cpu2 {
+	cpu-supply = <&vdd_cpu>;
+};
+
+&cpu3 {
+	cpu-supply = <&vdd_cpu>;
+};
+
+&dsi_dphy0 {
+	status = "okay";
+};
+
+&dsi0 {
+	status = "okay";
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	ports {
+		dsi0_in: port@0 {
+			reg = <0>;
+			dsi0_in_vp1: endpoint {
+				remote-endpoint = <&vp1_out_dsi0>;
+			};
+		};
+
+		dsi0_out: port@1 {
+			reg = <1>;
+			mipi_out_panel: endpoint {
+				remote-endpoint = <&mipi_in_panel>;
+			};
+		};
+	};
+
+	panel: panel@0 {
+		compatible = "powkiddy,x55-panel", "himax,hx8394";
+		reg = <0>;
+		backlight = <&backlight>;
+		iovcc-supply = <&vcc_lcd>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&lcd_rst>;
+		reset-gpios = <&gpio0 RK_PD5 GPIO_ACTIVE_LOW>;
+		rotation = <270>;
+		vcc-supply = <&vcc_lcd>;
+
+		port {
+			mipi_in_panel: endpoint {
+				remote-endpoint = <&mipi_out_panel>;
+			};
+		};
+	};
+};
+
+&gpu {
+	mali-supply = <&vdd_gpu>;
+	status = "okay";
+};
+
+&hdmi {
+	ddc-i2c-bus = <&i2c5>;
+	pinctrl-0 = <&hdmitxm0_cec>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&hdmi_in {
+	hdmi_in_vp0: endpoint {
+		remote-endpoint = <&vp0_out_hdmi>;
+	};
+};
+
+&hdmi_out {
+	hdmi_out_con: endpoint {
+		remote-endpoint = <&hdmi_con_in>;
+	};
+};
+
+&hdmi_sound {
+	status = "okay";
+};
+
+&i2c0 {
+	status = "okay";
+
+	rk817: pmic@20 {
+		compatible = "rockchip,rk817";
+		reg = <0x20>;
+		assigned-clocks = <&cru I2S1_MCLKOUT_TX>;
+		assigned-clock-parents = <&cru CLK_I2S1_8CH_TX>;
+		clock-names = "mclk";
+		clock-output-names = "rk808-clkout1", "rk808-clkout2";
+		clocks = <&cru I2S1_MCLKOUT_TX>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <RK_PA3 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&i2s1m0_mclk>, <&pmic_int_l>;
+		wakeup-source;
+		#clock-cells = <1>;
+		#sound-dai-cells = <0>;
+
+		vcc1-supply = <&vcc_sys>;
+		vcc2-supply = <&vcc_sys>;
+		vcc3-supply = <&vcc_sys>;
+		vcc4-supply = <&vcc_sys>;
+		vcc5-supply = <&vcc_sys>;
+		vcc6-supply = <&vcc_sys>;
+		vcc7-supply = <&vcc_sys>;
+		vcc8-supply = <&vcc_sys>;
+		vcc9-supply = <&dcdc_boost>;
+
+		regulators {
+			vdd_logic: DCDC_REG1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <500000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <6001>;
+				regulator-initial-mode = <0x2>;
+				regulator-name = "vdd_logic";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <900000>;
+				};
+			};
+
+			vdd_gpu: DCDC_REG2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <500000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <6001>;
+				regulator-initial-mode = <0x2>;
+				regulator-name = "vdd_gpu";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_ddr: DCDC_REG3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-initial-mode = <0x2>;
+				regulator-name = "vcc_ddr";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+				};
+			};
+
+			vcc_3v3: DCDC_REG4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-initial-mode = <0x2>;
+				regulator-name = "vcc_3v3";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			vcca1v8_pmu: LDO_REG1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcca1v8_pmu";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vdda_0v9: LDO_REG2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <900000>;
+				regulator-max-microvolt = <900000>;
+				regulator-name = "vdda_0v9";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdda0v9_pmu: LDO_REG3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <900000>;
+				regulator-max-microvolt = <900000>;
+				regulator-name = "vdda0v9_pmu";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <900000>;
+				};
+			};
+
+			vccio_acodec: LDO_REG4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vccio_acodec";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vccio_sd: LDO_REG5 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vccio_sd";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc3v3_pmu: LDO_REG6 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcc3v3_pmu";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			vcc_1v8: LDO_REG7 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc_1v8";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc1v8_dvp: LDO_REG8 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc1v8_dvp";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+				};
+			};
+
+			vcc2v8_dvp: LDO_REG9 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcc2v8_dvp";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			dcdc_boost: BOOST {
+				regulator-min-microvolt = <4700000>;
+				regulator-max-microvolt = <5400000>;
+				regulator-name = "boost";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			otg_switch: OTG_SWITCH {
+				regulator-name = "otg_switch";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+		};
+
+		rk817_charger: charger {
+			monitored-battery = <&battery>;
+			rockchip,resistor-sense-micro-ohms = <10000>;
+			rockchip,sleep-enter-current-microamp = <150000>;
+			rockchip,sleep-filter-current-microamp = <100000>;
+		};
+
+	};
+
+	vdd_cpu: regulator@1c {
+		compatible = "tcs,tcs4525";
+		reg = <0x1c>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <712500>;
+		regulator-max-microvolt = <1390000>;
+		regulator-name = "vdd_cpu";
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc_sys>;
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+};
+
+&i2c5 {
+	pinctrl-0 = <&i2c5m1_xfer>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&i2s0_8ch {
+	status = "okay";
+};
+
+&i2s1_8ch {
+	pinctrl-0 = <&i2s1m0_sclktx>, <&i2s1m0_lrcktx>, <&i2s1m0_sdi0>,
+		    <&i2s1m0_sdo0>;
+	pinctrl-names = "default";
+	rockchip,trcm-sync-tx-only;
+	status = "okay";
+};
+
+&pinctrl {
+	audio-amplifier {
+		spk_amp_enable_h: spk-amp-enable-h {
+			rockchip,pins =
+				<4 RK_PC2 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	gpio-control {
+		btn_pins_ctrl: btn-pins-ctrl {
+			rockchip,pins =
+				<3 RK_PC6 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PC7 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PD0 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PD1 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PD2 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PD3 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PD4 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PD5 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PD6 RK_FUNC_GPIO &pcfg_pull_up>,
+				<3 RK_PD7 RK_FUNC_GPIO &pcfg_pull_up>,
+				<4 RK_PA0 RK_FUNC_GPIO &pcfg_pull_up>,
+				<4 RK_PA1 RK_FUNC_GPIO &pcfg_pull_up>,
+				<4 RK_PA2 RK_FUNC_GPIO &pcfg_pull_up>,
+				<4 RK_PA4 RK_FUNC_GPIO &pcfg_pull_up>,
+				<4 RK_PA7 RK_FUNC_GPIO &pcfg_pull_up>,
+				<4 RK_PB0 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+
+		btn_pins_vol: btn-pins-vol {
+			rockchip,pins =
+				<4 RK_PA3 RK_FUNC_GPIO &pcfg_pull_up>,
+				<4 RK_PA5 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	gpio-lcd {
+		lcd_rst: lcd-rst {
+			rockchip,pins =
+				<0 RK_PD5 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	gpio-leds {
+		led_pins: led-pins {
+			rockchip,pins =
+				<4 RK_PB4 RK_FUNC_GPIO &pcfg_pull_none>,
+				<4 RK_PB5 RK_FUNC_GPIO &pcfg_pull_none>,
+				<4 RK_PB6 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	hp-detect {
+		hp_det: hp-det {
+			rockchip,pins =
+				<4 RK_PC6 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	pmic {
+		pmic_int_l: pmic-int-l {
+			rockchip,pins =
+				<0 RK_PA3 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	sdio-pwrseq {
+		wifi_enable_h: wifi-enable-h {
+			rockchip,pins =
+				<0 RK_PC0 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	usb {
+		vcc5v0_host_en: vcc5v0-host-en {
+			rockchip,pins =
+				<4 RK_PC4 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+
+		vcc5v0_otg_en: vcc5v0-otg-en {
+			rockchip,pins =
+				<4 RK_PC5 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	vcc-lcd {
+		vcc_lcd_en: vcc-lcd-en {
+			rockchip,pins =
+				<0 RK_PC7 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	vcc-wifi {
+		vcc_wifi_h: vcc-wifi-h {
+			rockchip,pins =
+				<0 RK_PA0 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&pmu_io_domains {
+	status = "okay";
+	pmuio1-supply = <&vcc3v3_pmu>;
+	pmuio2-supply = <&vcca1v8_pmu>;
+	vccio1-supply = <&vccio_acodec>;
+	vccio3-supply = <&vccio_sd>;
+	vccio4-supply = <&vcca1v8_pmu>;
+	vccio5-supply = <&vcc2v8_dvp>;
+	vccio6-supply = <&vcc1v8_dvp>;
+	vccio7-supply = <&vcc_3v3>;
+};
+
+&pwm4 {
+	status = "okay";
+};
+
+&saradc {
+	vref-supply = <&vcc_1v8>;
+	status = "okay";
+};
+
+&sdhci {
+	bus-width = <8>;
+	mmc-hs200-1_8v;
+	non-removable;
+	pinctrl-0 = <&emmc_bus8>, <&emmc_clk>, <&emmc_cmd>,
+		    <&emmc_datastrobe>, <&emmc_rstnout>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&sdmmc0 {
+	bus-width = <4>;
+	cap-mmc-highspeed;
+	cap-sd-highspeed;
+	disable-wp;
+	pinctrl-0 = <&sdmmc0_bus4>, <&sdmmc0_clk>, <&sdmmc0_cmd>,
+		    <&sdmmc0_det>;
+	pinctrl-names = "default";
+	sd-uhs-sdr104;
+	vqmmc-supply = <&vccio_sd>;
+	status = "okay";
+};
+
+&sdmmc1 {
+	bus-width = <4>;
+	cap-sd-highspeed;
+	cap-sdio-irq;
+	keep-power-in-suspend;
+	mmc-pwrseq = <&sdio_pwrseq>;
+	non-removable;
+	pinctrl-0 = <&sdmmc1_bus4>, <&sdmmc1_cmd>, <&sdmmc1_clk>;
+	pinctrl-names = "default";
+	vmmc-supply = <&vcc_wifi>;
+	status = "okay";
+};
+
+&sdmmc2 {
+	bus-width = <4>;
+	cap-mmc-highspeed;
+	cap-sd-highspeed;
+	disable-wp;
+	pinctrl-0 = <&sdmmc2m1_bus4>, <&sdmmc2m1_cmd>, <&sdmmc2m1_clk>,
+		    <&sdmmc2m1_det>;
+	pinctrl-names = "default";
+	sd-uhs-sdr104;
+	vqmmc-supply = <&vcc2v8_dvp>;
+	status = "okay";
+};
+
+&tsadc {
+	rockchip,hw-tshut-mode = <1>;
+	rockchip,hw-tshut-polarity = <0>;
+	status = "okay";
+};
+
+&uart1 {
+	pinctrl-0 = <&uart1m0_xfer>, <&uart1m0_ctsn>, <&uart1m0_rtsn>;
+	pinctrl-names = "default";
+	uart-has-rtscts;
+	status = "okay";
+
+	bluetooth {
+		compatible = "realtek,rtl8821cs-bt", "realtek,rtl8723bs-bt";
+		device-wake-gpios = <&gpio0 RK_PB6 GPIO_ACTIVE_HIGH>;
+		enable-gpios = <&gpio0 RK_PC1 GPIO_ACTIVE_HIGH>;
+		host-wake-gpios = <&gpio0 RK_PB5 GPIO_ACTIVE_HIGH>;
+	};
+};
+
+&uart2 {
+	status = "okay";
+};
+
+&usb_host0_xhci {
+	phys = <&usb2phy0_otg>;
+	phy-names = "usb2-phy";
+	status = "okay";
+};
+
+&usb_host1_xhci {
+	status = "okay";
+};
+
+&usb2phy0 {
+	status = "okay";
+};
+
+&usb2phy0_otg {
+	status = "okay";
+};
+
+&usb2phy0_host {
+	phy-supply = <&vcc5v0_host>;
+	status = "okay";
+};
+
+&vop {
+	assigned-clocks = <&cru DCLK_VOP0>, <&cru DCLK_VOP1>;
+	assigned-clock-parents = <&pmucru PLL_HPLL>, <&cru PLL_VPLL>;
+	status = "okay";
+};
+
+&vop_mmu {
+	status = "okay";
+};
+
+&vp0 {
+	vp0_out_hdmi: endpoint@ROCKCHIP_VOP2_EP_HDMI0 {
+		reg = <ROCKCHIP_VOP2_EP_HDMI0>;
+		remote-endpoint = <&hdmi_in_vp0>;
+	};
+};
+
+&vp1 {
+	vp1_out_dsi0: endpoint@ROCKCHIP_VOP2_EP_MIPI0 {
+		reg = <ROCKCHIP_VOP2_EP_MIPI0>;
+		remote-endpoint = <&dsi0_in_vp1>;
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts
index 854d02b46e6f..59843a7a199c 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts
@@ -31,8 +31,9 @@
 	fan: gpio_fan {
 		compatible = "gpio-fan";
 		gpios = <&gpio0 RK_PD5 GPIO_ACTIVE_HIGH>;
-		gpio-fan,speed-map = <0    0
-				      4500 1>;
+		gpio-fan,speed-map =
+				<   0 0>,
+				<4500 1>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&fan_en_h>;
 		#cooling-cells = <2>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-radxa-cm3-io.dts b/arch/arm64/boot/dts/rockchip/rk3566-radxa-cm3-io.dts
index 1b1c67d5b1ef..3ae24e39450a 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-radxa-cm3-io.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-radxa-cm3-io.dts
@@ -14,6 +14,7 @@
 	compatible = "radxa,cm3-io", "radxa,cm3", "rockchip,rk3566";
 
 	aliases {
+		ethernet0 = &gmac1;
 		mmc1 = &sdmmc0;
 	};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-roc-pc.dts b/arch/arm64/boot/dts/rockchip/rk3566-roc-pc.dts
index 938092fce186..63eea27293fe 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-roc-pc.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-roc-pc.dts
@@ -12,6 +12,7 @@
 	compatible = "firefly,rk3566-roc-pc", "rockchip,rk3566";
 
 	aliases {
+		ethernet0 = &gmac1;
 		mmc0 = &sdmmc0;
 		mmc1 = &sdhci;
 		mmc2 = &sdmmc1;
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-soquartz-blade.dts b/arch/arm64/boot/dts/rockchip/rk3566-soquartz-blade.dts
index 4e49bebf548b..fdbf1c783242 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-soquartz-blade.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-soquartz-blade.dts
@@ -13,6 +13,10 @@
 	model = "PINE64 RK3566 SOQuartz on Blade carrier board";
 	compatible = "pine64,soquartz-blade", "pine64,soquartz", "rockchip,rk3566";
 
+	aliases {
+		ethernet0 = &gmac1;
+	};
+
 	/* labeled VCC3V0_SD in schematic to not conflict with PMIC regulator */
 	vcc3v0_sd: vcc3v0-sd-regulator {
 		compatible = "regulator-fixed";
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-soquartz-cm4.dts b/arch/arm64/boot/dts/rockchip/rk3566-soquartz-cm4.dts
index cddf6cd2fecb..6ed3fa4aee34 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-soquartz-cm4.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-soquartz-cm4.dts
@@ -8,6 +8,10 @@
 	model = "Pine64 RK3566 SoQuartz with CM4-IO Carrier Board";
 	compatible = "pine64,soquartz-cm4io", "pine64,soquartz", "rockchip,rk3566";
 
+	aliases {
+		ethernet0 = &gmac1;
+	};
+
 	/* labeled +12v in schematic */
 	vcc12v_dcin: vcc12v-dcin-regulator {
 		compatible = "regulator-fixed";
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-soquartz-model-a.dts b/arch/arm64/boot/dts/rockchip/rk3566-soquartz-model-a.dts
index 2208dbfb7f0a..f2095dfa4eaf 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-soquartz-model-a.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-soquartz-model-a.dts
@@ -8,6 +8,10 @@
 	model = "PINE64 RK3566 SOQuartz on Model A carrier board";
 	compatible = "pine64,soquartz-model-a", "pine64,soquartz", "rockchip,rk3566";
 
+	aliases {
+		ethernet0 = &gmac1;
+	};
+
 	/* labeled DCIN_12V in schematic */
 	vcc12v_dcin: vcc12v-dcin-regulator {
 		compatible = "regulator-fixed";
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi
index 63bae36b8f7e..bfb7b952f4c5 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi
@@ -12,7 +12,6 @@
 	compatible = "pine64,soquartz", "rockchip,rk3566";
 
 	aliases {
-		ethernet0 = &gmac1;
 		mmc0 = &sdmmc0;
 		mmc1 = &sdhci;
 		mmc2 = &sdmmc1;
diff --git a/arch/arm64/boot/dts/rockchip/rk356x.dtsi b/arch/arm64/boot/dts/rockchip/rk356x.dtsi
index 0964761e3ce9..c19c0f1b3778 100644
--- a/arch/arm64/boot/dts/rockchip/rk356x.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk356x.dtsi
@@ -977,7 +977,7 @@
 			     <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 71 IRQ_TYPE_LEVEL_HIGH>;
-		interrupt-names = "sys", "pmc", "msi", "legacy", "err";
+		interrupt-names = "sys", "pmc", "msg", "legacy", "err";
 		bus-range = <0x0 0xf>;
 		clocks = <&cru ACLK_PCIE20_MST>, <&cru ACLK_PCIE20_SLV>,
 			 <&cru ACLK_PCIE20_DBI>, <&cru PCLK_PCIE20>,
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-evb.dts b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-evb.dts
new file mode 100644
index 000000000000..d4c70835e0fe
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-evb.dts
@@ -0,0 +1,214 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2023 Rockchip Electronics Co., Ltd.
+ *
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/leds/common.h>
+#include "rk3588-coolpi-cm5.dtsi"
+
+/ {
+	model = "RK3588 CoolPi CM5 EVB";
+	compatible = "coolpi,pi-cm5-evb", "coolpi,pi-cm5", "rockchip,rk3588";
+
+	backlight: backlight {
+		compatible = "pwm-backlight";
+		enable-gpios = <&gpio4 RK_PA3 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&bl_en>;
+		power-supply = <&vcc12v_dcin>;
+		pwms = <&pwm2 0 25000 0>;
+	};
+
+	leds: leds {
+		compatible = "gpio-leds";
+
+		green_led: led-0 {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_STATUS;
+			gpios = <&gpio3 RK_PB7 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "heartbeat";
+		};
+	};
+
+	vcc12v_dcin: vcc12v-dcin-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc12v_dcin";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <12000000>;
+		regulator-max-microvolt = <12000000>;
+	};
+
+	vcc5v0_sys: vcc5v0-sys-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0_sys";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc12v_dcin>;
+	};
+
+	vcc3v3_sys: vcc3v3-sys-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc3v3_sys";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcc12v_dcin>;
+	};
+
+	vcc3v3_lcd: vcc3v3-lcd-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc3v3_lcd";
+		enable-active-high;
+		gpio = <&gpio1 RK_PC4 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&lcdpwr_en>;
+		vin-supply = <&vcc3v3_sys>;
+	};
+
+	vcc5v0_usb30_host: vcc5v0-usb30-host-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0_host";
+		regulator-boot-on;
+		regulator-always-on;
+		enable-active-high;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&gpio1 RK_PD5 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&usb_host_pwren>;
+		vin-supply = <&vcc5v0_sys>;
+	};
+
+	vcc5v0_usb30_otg: vcc5v0-usb30-otg-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0_otg";
+		regulator-boot-on;
+		regulator-always-on;
+		enable-active-high;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpios = <&gpio0 RK_PA0 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&usb_otg_pwren>;
+		vin-supply = <&vcc5v0_sys>;
+	};
+};
+
+/* M.2 E-Key */
+&pcie2x1l1 {
+	reset-gpios = <&gpio4 RK_PA2 GPIO_ACTIVE_HIGH>;
+	vpcie3v3-supply = <&vcc3v3_sys>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pcie_clkreq &pcie_wake &pcie_rst &wifi_pwron &bt_pwron>;
+	status = "okay";
+};
+
+&pcie30phy {
+	status = "okay";
+};
+
+&pcie3x2 {
+	reset-gpios = <&gpio3 RK_PB0 GPIO_ACTIVE_HIGH>;
+	vpcie3v3-supply = <&vcc3v3_sys>;
+	status = "okay";
+};
+
+/* M.2 M-Key ssd */
+&pcie3x4 {
+	reset-gpios = <&gpio4 RK_PB6 GPIO_ACTIVE_HIGH>;
+	vpcie3v3-supply = <&vcc3v3_sys>;
+	status = "okay";
+};
+
+&pinctrl {
+	lcd {
+		lcdpwr_en: lcdpwr-en {
+			rockchip,pins = <1 RK_PC4 RK_FUNC_GPIO &pcfg_pull_down>;
+		};
+
+		bl_en: bl-en {
+			rockchip,pins = <4 RK_PA3 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	usb {
+		usb_host_pwren: usb-host-pwren {
+			rockchip,pins = <1 RK_PD5 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+
+		usb_otg_pwren: usb-otg-pwren {
+			rockchip,pins = <0 RK_PA0 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	wifi {
+		bt_pwron: bt-pwron {
+			rockchip,pins = <3 RK_PA6 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+
+		pcie_clkreq: pcie-clkreq {
+			rockchip,pins = <4 RK_PA0 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+
+		pcie_rst: pcie-rst {
+			rockchip,pins = <4 RK_PA2 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+
+		wifi_pwron: wifi-pwron {
+			rockchip,pins = <3 RK_PB1 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+
+		pcie_wake: pcie-wake {
+			rockchip,pins = <4 RK_PA1 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+};
+
+&pwm2 {
+	status = "okay";
+};
+
+&sata1 {
+	status = "okay";
+};
+
+&u2phy2 {
+	status = "okay";
+};
+
+&u2phy3 {
+	status = "okay";
+};
+
+&u2phy2_host {
+	phy-supply = <&vcc5v0_usb30_host>;
+	status = "okay";
+};
+
+&u2phy3_host {
+	phy-supply = <&vcc5v0_usb30_host>;
+	status = "okay";
+};
+
+&usb_host0_ehci {
+	status = "okay";
+};
+
+&usb_host0_ohci {
+	status = "okay";
+};
+
+&usb_host1_ehci {
+	status = "okay";
+};
+
+&usb_host1_ohci {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi
new file mode 100644
index 000000000000..0b02f4d6e003
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi
@@ -0,0 +1,650 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2023 Rockchip Electronics Co., Ltd.
+ *
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/pwm/pwm.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+#include "rk3588.dtsi"
+
+/ {
+	compatible = "coolpi,pi-cm5", "rockchip,rk3588";
+
+	aliases {
+		mmc0 = &sdhci;
+		mmc1 = &sdio;
+		mmc2 = &sdmmc;
+		serial2 = &uart2;
+	};
+
+	analog-sound {
+		compatible = "audio-graph-card";
+		dais = <&i2s0_8ch_p0>;
+		label = "rk3588-es8316";
+		routing = "MIC2", "Mic Jack",
+			  "Headphones", "HPOL",
+			  "Headphones", "HPOR";
+		widgets = "Microphone", "Mic Jack",
+			  "Headphone", "Headphones";
+	};
+
+	chosen {
+		stdout-path = "serial2:1500000n8";
+	};
+
+	avdd0v85_pcie20: avdd0v85-pcie20-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "avdd0v85_pcie20";
+		regulator-boot-on;
+		regulator-always-on;
+		regulator-min-microvolt = <850000>;
+		regulator-max-microvolt = <850000>;
+		vin-supply = <&vdd_0v85_s0>;
+	};
+
+	avdd1v8_pcie20: avdd1v8-pcie20-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "avdd1v8_pcie20";
+		regulator-boot-on;
+		regulator-always-on;
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		vin-supply = <&avcc_1v8_s0>;
+	};
+
+	avdd0v75_pcie30: avdd0v75-pcie30-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "avdd0v75_pcie30";
+		regulator-boot-on;
+		regulator-always-on;
+		regulator-min-microvolt = <750000>;
+		regulator-max-microvolt = <750000>;
+		vin-supply = <&avdd_0v75_s0>;
+	};
+
+	pcie30_avdd1v8: avdd1v8-pcie30-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "pcie30_avdd1v8";
+		regulator-boot-on;
+		regulator-always-on;
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		vin-supply = <&avcc_1v8_s0>;
+	};
+};
+
+&combphy0_ps {
+	status = "okay";
+};
+
+&combphy1_ps {
+	status = "okay";
+};
+
+&combphy2_psu {
+	status = "okay";
+};
+
+&cpu_b0 {
+	cpu-supply = <&vdd_cpu_big0_s0>;
+};
+
+&cpu_b1 {
+	cpu-supply = <&vdd_cpu_big0_s0>;
+};
+
+&cpu_b2 {
+	cpu-supply = <&vdd_cpu_big1_s0>;
+};
+
+&cpu_b3 {
+	cpu-supply = <&vdd_cpu_big1_s0>;
+};
+
+&cpu_l0 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l1 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l2 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l3 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&gmac0 {
+	clock_in_out = "output";
+	phy-handle = <&rgmii_phy>;
+	phy-mode = "rgmii-rxid";
+	pinctrl-0 = <&gmac0_miim
+		     &gmac0_tx_bus2
+		     &gmac0_rx_bus2
+		     &gmac0_rgmii_clk
+		     &gmac0_rgmii_bus>;
+	pinctrl-names = "default";
+	rx_delay = <0x00>;
+	tx_delay = <0x43>;
+	status = "okay";
+};
+
+&i2c0 {
+	pinctrl-0 = <&i2c0m2_xfer>;
+	status = "okay";
+
+	vdd_cpu_big0_s0: regulator@42 {
+		compatible = "rockchip,rk8602";
+		reg = <0x42>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_cpu_big0_s0";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <1050000>;
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+
+	vdd_cpu_big1_s0: regulator@43 {
+		compatible = "rockchip,rk8603", "rockchip,rk8602";
+		reg = <0x43>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_cpu_big1_s0";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <1050000>;
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+};
+
+&i2c2 {
+	status = "okay";
+
+	vdd_npu_s0: regulator@42 {
+		compatible = "rockchip,rk8602";
+		reg = <0x42>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_npu_s0";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <950000>;
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+};
+
+&i2c6 {
+	status = "okay";
+
+	hym8563: rtc@51 {
+		compatible = "haoyu,hym8563";
+		reg = <0x51>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <RK_PD4 IRQ_TYPE_LEVEL_LOW>;
+		#clock-cells = <0>;
+		clock-output-names = "hym8563";
+		pinctrl-names = "default";
+		pinctrl-0 = <&hym8563_int>;
+		wakeup-source;
+	};
+};
+
+&i2c7 {
+	pinctrl-0 = <&i2c7m0_xfer>;
+	status = "okay";
+
+	es8316: audio-codec@11 {
+		compatible = "everest,es8316";
+		reg = <0x11>;
+		assigned-clocks = <&cru I2S0_8CH_MCLKOUT>;
+		assigned-clock-rates = <12288000>;
+		clocks = <&cru I2S0_8CH_MCLKOUT>;
+		clock-names = "mclk";
+		#sound-dai-cells = <0>;
+
+		port {
+			es8316_p0_0: endpoint {
+				remote-endpoint = <&i2s0_8ch_p0_0>;
+			};
+		};
+	};
+};
+
+&i2s0_8ch {
+	pinctrl-0 = <&i2s0_lrck
+		     &i2s0_mclk
+		     &i2s0_sclk
+		     &i2s0_sdi0
+		     &i2s0_sdo0>;
+	status = "okay";
+
+	i2s0_8ch_p0: port {
+		i2s0_8ch_p0_0: endpoint {
+			dai-format = "i2s";
+			mclk-fs = <256>;
+			remote-endpoint = <&es8316_p0_0>;
+		};
+	};
+};
+
+&mdio0 {
+	rgmii_phy: ethernet-phy@1 {
+		/* YT8531C/H */
+		compatible = "ethernet-phy-ieee802.3-c22";
+		reg = <0x1>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&yt8531_rst>;
+		reset-assert-us = <20000>;
+		reset-deassert-us = <100000>;
+		reset-gpios = <&gpio4 RK_PB3 GPIO_ACTIVE_LOW>;
+	};
+};
+
+/* ethernet */
+&pcie2x1l2 {
+	reset-gpios = <&gpio3 RK_PD1 GPIO_ACTIVE_HIGH>;
+	vpcie3v3-supply = <&vcc3v3_sys>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&yt6801_isolate>;
+	status = "okay";
+};
+
+&pinctrl {
+	hym8563 {
+		hym8563_int: hym8563-int {
+			rockchip,pins = <0 RK_PD4 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	yt6801 {
+		yt6801_isolate: yt6801-isolate {
+			rockchip,pins = <1 RK_PA4 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	yt8531 {
+		yt8531_rst: yt8531-rst {
+			rockchip,pins = <4 RK_PB3 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&saradc {
+	vref-supply = <&vcc_1v8_s0>;
+	status = "okay";
+};
+
+&sdhci {
+	bus-width = <8>;
+	max-frequency = <200000000>;
+	mmc-hs400-1_8v;
+	mmc-hs400-enhanced-strobe;
+	no-sdio;
+	no-sd;
+	non-removable;
+	status = "okay";
+};
+
+&sdmmc {
+	bus-width = <4>;
+	cap-mmc-highspeed;
+	cap-sd-highspeed;
+	disable-wp;
+	max-frequency = <150000000>;
+	no-sdio;
+	no-mmc;
+	sd-uhs-sdr104;
+	vqmmc-supply = <&vccio_sd_s0>;
+	status = "okay";
+};
+
+&spi2 {
+	assigned-clocks = <&cru CLK_SPI2>;
+	assigned-clock-rates = <200000000>;
+	num-cs = <1>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&spi2m2_cs0 &spi2m2_pins>;
+	status = "okay";
+
+	pmic@0 {
+		compatible = "rockchip,rk806";
+		reg = <0x0>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <7 IRQ_TYPE_LEVEL_LOW>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>,
+			    <&rk806_dvs2_null>, <&rk806_dvs3_null>;
+		spi-max-frequency = <1000000>;
+		vcc1-supply = <&vcc5v0_sys>;
+		vcc2-supply = <&vcc5v0_sys>;
+		vcc3-supply = <&vcc5v0_sys>;
+		vcc4-supply = <&vcc5v0_sys>;
+		vcc5-supply = <&vcc5v0_sys>;
+		vcc6-supply = <&vcc5v0_sys>;
+		vcc7-supply = <&vcc5v0_sys>;
+		vcc8-supply = <&vcc5v0_sys>;
+		vcc9-supply = <&vcc5v0_sys>;
+		vcc10-supply = <&vcc5v0_sys>;
+		vcc11-supply = <&vcc_2v0_pldo_s3>;
+		vcc12-supply = <&vcc5v0_sys>;
+		vcc13-supply = <&vcc_2v0_pldo_s3>;
+		vcc14-supply = <&vcc_2v0_pldo_s3>;
+		vcca-supply = <&vcc5v0_sys>;
+
+		rk806_dvs1_null: dvs1-null-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs2_null: dvs2-null-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs3_null: dvs3-null-pins {
+			pins = "gpio_pwrctrl3";
+			function = "pin_fun0";
+		};
+
+		regulators {
+			vdd_gpu_s0: vdd_gpu_mem_s0: dcdc-reg1 {
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_gpu_s0";
+				regulator-enable-ramp-delay = <400>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_cpu_lit_s0: vdd_cpu_lit_mem_s0: dcdc-reg2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_cpu_lit_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_log_s0: dcdc-reg3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <675000>;
+				regulator-max-microvolt = <750000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_log_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <750000>;
+				};
+			};
+
+			vdd_vdenc_s0: vdd_vdenc_mem_s0: dcdc-reg4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_vdenc_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_ddr_s0: dcdc-reg5 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <675000>;
+				regulator-max-microvolt = <900000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_ddr_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <850000>;
+				};
+			};
+
+			vdd2_ddr_s3: dcdc-reg6 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-name = "vdd2_ddr_s3";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+				};
+			};
+
+			vcc_2v0_pldo_s3: dcdc-reg7 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <2000000>;
+				regulator-max-microvolt = <2000000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_2v0_pldo_s3";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <2000000>;
+				};
+			};
+
+			vcc_3v3_s3: dcdc-reg8 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcc_3v3_s3";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			vddq_ddr_s0: dcdc-reg9 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-name = "vddq_ddr_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_1v8_s3: dcdc-reg10 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc_1v8_s3";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			avcc_1v8_s0: pldo-reg1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "avcc_1v8_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_1v8_s0: pldo-reg2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc_1v8_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			avdd_1v2_s0: pldo-reg3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-name = "avdd_1v2_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_3v3_s0: pldo-reg4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vcc_3v3_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vccio_sd_s0: pldo-reg5 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vccio_sd_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			pldo6_s3: pldo-reg6 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "pldo6_s3";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vdd_0v75_s3: nldo-reg1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+				regulator-name = "vdd_0v75_s3";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <750000>;
+				};
+			};
+
+			vdd_ddr_pll_s0: nldo-reg2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-name = "vdd_ddr_pll_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <850000>;
+				};
+			};
+
+			avdd_0v75_s0: nldo-reg3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+				regulator-name = "avdd_0v75_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_0v85_s0: nldo-reg4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-name = "vdd_0v85_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_0v75_s0: nldo-reg5 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+				regulator-name = "vdd_0v75_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+		};
+	};
+};
+
+&tsadc {
+	status = "okay";
+};
+
+&uart2 {
+	pinctrl-0 = <&uart2m0_xfer>;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-io.dts b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-io.dts
index b51543892078..be6a4f4f90f6 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-io.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-io.dts
@@ -12,10 +12,6 @@
 	compatible = "edgeble,neural-compute-module-6a-io",
 		     "edgeble,neural-compute-module-6a", "rockchip,rk3588";
 
-	aliases {
-		serial2 = &uart2;
-	};
-
 	chosen {
 		stdout-path = "serial2:1500000n8";
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6b-io.dts b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6b-io.dts
index 9933765e4097..070baeb63431 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6b-io.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6b-io.dts
@@ -9,13 +9,9 @@
 
 / {
 	model = "Edgeble Neu6B IO Board";
-	compatible = "edgeble,neural-compute-module-6b-io",
+	compatible = "edgeble,neural-compute-module-6a-io",
 		     "edgeble,neural-compute-module-6b", "rockchip,rk3588";
 
-	aliases {
-		serial2 = &uart2;
-	};
-
 	chosen {
 		stdout-path = "serial2:1500000n8";
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts b/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts
index b9d789d57862..ac7c677b0fb9 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts
@@ -16,8 +16,8 @@
 	compatible = "rockchip,rk3588-evb1-v10", "rockchip,rk3588";
 
 	aliases {
+		ethernet0 = &gmac0;
 		mmc0 = &sdhci;
-		serial2 = &uart2;
 	};
 
 	chosen {
@@ -56,6 +56,63 @@
 		};
 	};
 
+	analog-sound {
+		compatible = "simple-audio-card";
+		pinctrl-names = "default";
+		pinctrl-0 = <&hp_detect>;
+		simple-audio-card,name = "RK3588 EVB1 Audio";
+		simple-audio-card,aux-devs = <&amp_headphone>, <&amp_speaker>;
+		simple-audio-card,bitclock-master = <&masterdai>;
+		simple-audio-card,format = "i2s";
+		simple-audio-card,frame-master = <&masterdai>;
+		simple-audio-card,hp-det-gpio = <&gpio1 RK_PD5 GPIO_ACTIVE_LOW>;
+		simple-audio-card,mclk-fs = <256>;
+		simple-audio-card,pin-switches = "Headphones", "Speaker";
+		simple-audio-card,routing =
+			"Speaker Amplifier INL", "LOUT2",
+			"Speaker Amplifier INR", "ROUT2",
+			"Speaker", "Speaker Amplifier OUTL",
+			"Speaker", "Speaker Amplifier OUTR",
+			"Headphones Amplifier INL", "LOUT1",
+			"Headphones Amplifier INR", "ROUT1",
+			"Headphones", "Headphones Amplifier OUTL",
+			"Headphones", "Headphones Amplifier OUTR",
+			"LINPUT1", "Onboard Microphone",
+			"RINPUT1", "Onboard Microphone",
+			"LINPUT2", "Microphone Jack",
+			"RINPUT2", "Microphone Jack";
+		simple-audio-card,widgets =
+			"Microphone", "Microphone Jack",
+			"Microphone", "Onboard Microphone",
+			"Headphone", "Headphones",
+			"Speaker", "Speaker";
+
+		simple-audio-card,cpu {
+			sound-dai = <&i2s0_8ch>;
+		};
+
+		masterdai: simple-audio-card,codec {
+			sound-dai = <&es8388>;
+			system-clock-frequency = <12288000>;
+		};
+	};
+
+	amp_headphone: headphone-amplifier {
+		compatible = "simple-audio-amplifier";
+		enable-gpios = <&gpio1 RK_PD2 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&headphone_amplifier_en>;
+		sound-name-prefix = "Headphones Amplifier";
+	};
+
+	amp_speaker: speaker-amplifier {
+		compatible = "simple-audio-amplifier";
+		enable-gpios = <&gpio1 RK_PD3 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&speaker_amplifier_en>;
+		sound-name-prefix = "Speaker Amplifier";
+	};
+
 	backlight: backlight {
 		compatible = "pwm-backlight";
 		power-supply = <&vcc12v_dcin>;
@@ -240,6 +297,32 @@
 	};
 };
 
+&i2c7 {
+	status = "okay";
+
+	es8388: audio-codec@11 {
+		compatible = "everest,es8388";
+		reg = <0x11>;
+		clocks = <&cru I2S0_8CH_MCLKOUT>;
+		assigned-clocks = <&cru I2S0_8CH_MCLKOUT>;
+		assigned-clock-rates = <12288000>;
+		AVDD-supply = <&avcc_1v8_codec_s0>;
+		DVDD-supply = <&avcc_1v8_codec_s0>;
+		HPVDD-supply = <&vcc_3v3_s0>;
+		PVDD-supply = <&vcc_3v3_s0>;
+		#sound-dai-cells = <0>;
+	};
+};
+
+&i2s0_8ch {
+	pinctrl-0 = <&i2s0_lrck
+		     &i2s0_mclk
+		     &i2s0_sclk
+		     &i2s0_sdi0
+		     &i2s0_sdo0>;
+	status = "okay";
+};
+
 &mdio0 {
 	rgmii_phy: ethernet-phy@1 {
 		/* RTL8211F */
@@ -273,6 +356,20 @@
 };
 
 &pinctrl {
+	audio {
+		hp_detect: headphone-detect {
+			rockchip,pins = <1 RK_PD5 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		headphone_amplifier_en: headphone-amplifier-en {
+			rockchip,pins = <1 RK_PD2 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		speaker_amplifier_en: speaker-amplifier-en {
+			rockchip,pins = <1 RK_PD3 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
 	rtl8111 {
 		rtl8111_isolate: rtl8111-isolate {
 			rockchip,pins = <1 RK_PA4 RK_FUNC_GPIO &pcfg_pull_up>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts b/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts
new file mode 100644
index 000000000000..4ce70fb75a30
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts
@@ -0,0 +1,803 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2023 Theobroma Systems Design und Consulting GmbH
+ */
+
+/dts-v1/;
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+#include <dt-bindings/usb/pd.h>
+#include "rk3588.dtsi"
+
+/ {
+	model = "Theobroma Systems RK3588-SBC Jaguar";
+	compatible = "tsd,rk3588-jaguar", "rockchip,rk3588";
+
+	adc-keys {
+		compatible = "adc-keys";
+		io-channels = <&saradc 0>;
+		io-channel-names = "buttons";
+		keyup-threshold-microvolt = <1800000>;
+		poll-interval = <100>;
+
+		/* Can be controlled through SW2 but also GPIO1 on CP2102 on P20 */
+		button-bios-disable {
+			label = "BIOS_DISABLE";
+			linux,code = <KEY_VENDOR>;
+			press-threshold-microvolt = <0>;
+		};
+	};
+
+	aliases {
+		ethernet0 = &gmac0;
+		mmc0 = &sdhci;
+		mmc1 = &sdmmc;
+		rtc0 = &rtc_twi;
+	};
+
+	chosen {
+		stdout-path = "serial2:115200n8";
+	};
+
+	/* DCIN is 12-24V but standard is 12V */
+	dc_12v: dc-12v-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "dc_12v";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <12000000>;
+		regulator-max-microvolt = <12000000>;
+	};
+
+	emmc_pwrseq: emmc-pwrseq {
+		compatible = "mmc-pwrseq-emmc";
+		pinctrl-0 = <&emmc_reset>;
+		pinctrl-names = "default";
+		reset-gpios = <&gpio2 RK_PA3 GPIO_ACTIVE_HIGH>;
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&led1_pin>;
+		status = "okay";
+
+		/* LED1 on PCB */
+		led-1 {
+			gpios = <&gpio1 RK_PD4 GPIO_ACTIVE_HIGH>;
+			function = LED_FUNCTION_HEARTBEAT;
+			linux,default-trigger = "heartbeat";
+			color = <LED_COLOR_ID_AMBER>;
+		};
+	};
+
+	pps {
+		compatible = "pps-gpio";
+		gpios = <&gpio0 RK_PD5 GPIO_ACTIVE_HIGH>;
+	};
+
+	vcc_1v1_nldo_s3: vcc-1v1-nldo-s3-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_1v1_nldo_s3";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <1100000>;
+		regulator-max-microvolt = <1100000>;
+		vin-supply = <&vcc5v0_sys>;
+	};
+
+	vcc_1v2_s3: vcc-1v2-s3-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_1v2_s3";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <1200000>;
+		regulator-max-microvolt = <1200000>;
+		vin-supply = <&vcc5v0_sys>;
+	};
+
+	/* Exposed on P14 and P15 */
+	vcc_2v8_s3: vcc-2v8-s3-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_2v8_s3";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <2800000>;
+		regulator-max-microvolt = <2800000>;
+		vin-supply = <&vcc_3v3_s3>;
+	};
+
+	vcc_5v0_usb_a: vcc-5v0-usb-a-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "usb_a_vcc";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc5v0_sys>;
+		gpio = <&gpio1 RK_PB4 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	vcc_5v0_usb_c1: vcc-5v0-usb-c1-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "5v_usbc1";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc5v0_usb>;
+		gpio = <&gpio4 RK_PB5 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	vcc_5v0_usb_c2: vcc-5v0-usb-c2-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "5v_usbc2";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc5v0_usb>;
+		gpio = <&gpio4 RK_PB6 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	vcc3v3_mdot2: vcc3v3-mdot2-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc3v3_mdot2";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&dc_12v>;
+	};
+
+	vcc5v0_sys: vcc5v0-sys-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0_sys";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&dc_12v>;
+	};
+
+	vcc5v0_usb: vcc5v0-usb-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0_usb";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc5v0_sys>;
+	};
+};
+
+&combphy1_ps {
+	status = "okay";
+};
+
+&cpu_b0 {
+	cpu-supply = <&vdd_cpu_big0_s0>;
+};
+
+&cpu_b1 {
+	cpu-supply = <&vdd_cpu_big0_s0>;
+};
+
+&cpu_b2 {
+	cpu-supply = <&vdd_cpu_big1_s0>;
+};
+
+&cpu_b3 {
+	cpu-supply = <&vdd_cpu_big1_s0>;
+};
+
+&cpu_l0 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l1 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l2 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l3 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&gmac0 {
+	clock_in_out = "output";
+	phy-handle = <&rgmii_phy>;
+	phy-mode = "rgmii";
+	phy-supply = <&vcc_1v2_s3>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&gmac0_miim
+		     &gmac0_rx_bus2
+		     &gmac0_tx_bus2
+		     &gmac0_rgmii_clk
+		     &gmac0_rgmii_bus
+		     &eth0_pins
+		     &eth_reset>;
+	tx_delay = <0x10>;
+	rx_delay = <0x10>;
+	snps,reset-gpio = <&gpio4 RK_PC3 GPIO_ACTIVE_LOW>;
+	snps,reset-active-low;
+	snps,reset-delays-us = <0 10000 100000>;
+
+	status = "okay";
+};
+
+&gpio1 {
+	mdot2e-w-disable1-n-hog {
+		gpios = <RK_PB1 GPIO_ACTIVE_LOW>;
+		output-low;
+		line-name = "m.2 E-key W_DISABLE1#";
+		gpio-hog;
+	};
+};
+
+&gpio4 {
+	mdot2e-w-disable2-n-hog {
+		gpios = <RK_PC1 GPIO_ACTIVE_LOW>;
+		output-low;
+		line-name = "m.2 E-key W_DISABLE2#";
+		gpio-hog;
+	};
+};
+
+&i2c0 {
+	pinctrl-0 = <&i2c0m2_xfer>;
+	status = "okay";
+
+	fan@18 {
+		compatible = "ti,amc6821";
+		reg = <0x18>;
+	};
+
+	vdd_npu_s0: regulator@42 {
+		compatible = "rockchip,rk8602";
+		reg = <0x42>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_npu_s0";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <950000>;
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+
+	vdd_cpu_big1_s0: regulator@43 {
+		compatible = "rockchip,rk8603", "rockchip,rk8602";
+		reg = <0x43>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_cpu_big1_s0";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <1050000>;
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+
+	rtc_twi: rtc@6f {
+		compatible = "isil,isl1208";
+		reg = <0x6f>;
+	};
+};
+
+&i2c1 {
+	pinctrl-0 = <&i2c1m4_xfer>;
+};
+
+&i2c6 {
+	pinctrl-0 = <&i2c6m4_xfer>;
+};
+
+&i2c7 {
+	status = "okay";
+
+	/* SE050 Secure Element at 0x48; GPIO1_A4 for enable pin */
+
+	/* Also on 0x55 */
+	eeprom@54 {
+		compatible = "st,24c04", "atmel,24c04";
+		reg = <0x54>;
+		pagesize = <16>;
+		vcc-supply = <&vcc_3v3_s3>;
+	};
+};
+
+&i2c8 {
+	pinctrl-0 = <&i2c8m2_xfer>;
+	status = "okay";
+
+	vdd_cpu_big0_s0: regulator@42 {
+		compatible = "rockchip,rk8602";
+		reg = <0x42>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_cpu_big0_s0";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <1050000>;
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+};
+
+&mdio0 {
+	rgmii_phy: ethernet-phy@6 {
+		/* KSZ9031 or KSZ9131 */
+		compatible = "ethernet-phy-ieee802.3-c22";
+		reg = <0x6>;
+		clocks = <&cru REFCLKO25M_ETH0_OUT>;
+	};
+};
+
+&pcie2x1l0 {
+	reset-gpios = <&gpio4 RK_PB3 GPIO_ACTIVE_HIGH>; /* WIFI_PERST0# */
+	vpcie3v3-supply = <&vcc3v3_mdot2>;
+	status = "okay";
+};
+
+&pinctrl {
+	emmc {
+		emmc_reset: emmc-reset {
+			rockchip,pins = <2 RK_PA3 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	ethernet {
+		eth_reset: eth-reset {
+			rockchip,pins = <4 RK_PC3 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	leds {
+		led1_pin: led1-pin {
+			rockchip,pins = <1 RK_PD4 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&saradc {
+	vref-supply = <&vcc_1v8_s0>;
+	status = "okay";
+};
+
+&sdhci {
+	bus-width = <8>;
+	cap-mmc-highspeed;
+	mmc-ddr-1_8v;
+	mmc-hs200-1_8v;
+	mmc-hs400-1_8v;
+	mmc-hs400-enhanced-strobe;
+	mmc-pwrseq = <&emmc_pwrseq>;
+	no-sdio;
+	no-sd;
+	non-removable;
+	pinctrl-names = "default";
+	pinctrl-0 = <&emmc_bus8 &emmc_cmd &emmc_clk &emmc_data_strobe>;
+	supports-cqe;
+	vmmc-supply = <&vcc_3v3_s3>;
+	vqmmc-supply = <&vcc_1v8_s3>;
+	status = "okay";
+};
+
+&sdmmc {
+	broken-cd;
+	bus-width = <4>;
+	cap-sd-highspeed;
+	disable-wp;
+	max-frequency = <150000000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&sdmmc_bus4 &sdmmc_cmd &sdmmc_clk>;
+	sd-uhs-sdr12;
+	sd-uhs-sdr25;
+	sd-uhs-sdr50;
+	sd-uhs-ddr50;
+	sd-uhs-sdr104;
+	vmmc-supply = <&vcc_3v3_s3>;
+	vqmmc-supply = <&vccio_sd_s0>;
+	status = "okay";
+};
+
+&spi2 {
+	assigned-clocks = <&cru CLK_SPI2>;
+	assigned-clock-rates = <200000000>;
+	num-cs = <1>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&spi2m2_cs0 &spi2m2_pins>;
+	status = "okay";
+
+	pmic@0 {
+		compatible = "rockchip,rk806";
+		reg = <0x0>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <7 IRQ_TYPE_LEVEL_LOW>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>,
+			    <&rk806_dvs2_null>, <&rk806_dvs3_null>;
+		spi-max-frequency = <1000000>;
+		system-power-controller;
+		vcc1-supply = <&vcc5v0_sys>;
+		vcc2-supply = <&vcc5v0_sys>;
+		vcc3-supply = <&vcc5v0_sys>;
+		vcc4-supply = <&vcc5v0_sys>;
+		vcc5-supply = <&vcc5v0_sys>;
+		vcc6-supply = <&vcc5v0_sys>;
+		vcc7-supply = <&vcc5v0_sys>;
+		vcc8-supply = <&vcc5v0_sys>;
+		vcc9-supply = <&vcc5v0_sys>;
+		vcc10-supply = <&vcc5v0_sys>;
+		vcc11-supply = <&vcc_2v0_pldo_s3>;
+		vcc12-supply = <&vcc5v0_sys>;
+		vcc13-supply = <&vcc_1v1_nldo_s3>;
+		vcc14-supply = <&vcc_1v1_nldo_s3>;
+		vcca-supply = <&vcc5v0_sys>;
+
+		rk806_dvs1_null: dvs1-null-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs2_null: dvs2-null-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs3_null: dvs3-null-pins {
+			pins = "gpio_pwrctrl3";
+			function = "pin_fun0";
+		};
+
+		regulators {
+			vdd_gpu_s0: dcdc-reg1 {
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_gpu_s0";
+				regulator-enable-ramp-delay = <400>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_cpu_lit_s0: dcdc-reg2 {
+				regulator-name = "vdd_cpu_lit_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_log_s0: dcdc-reg3 {
+				regulator-name = "vdd_log_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <675000>;
+				regulator-max-microvolt = <750000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <750000>;
+				};
+			};
+
+			vdd_vdenc_s0: dcdc-reg4 {
+				regulator-name = "vdd_vdenc_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_ddr_s0: dcdc-reg5 {
+				regulator-name = "vdd_ddr_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <675000>;
+				regulator-max-microvolt = <900000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <850000>;
+				};
+			};
+
+			vdd2_ddr_s3: dcdc-reg6 {
+				regulator-name = "vdd2_ddr_s3";
+				regulator-always-on;
+				regulator-boot-on;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+				};
+			};
+
+			vcc_2v0_pldo_s3: dcdc-reg7 {
+				regulator-name = "vdd_2v0_pldo_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <2000000>;
+				regulator-max-microvolt = <2000000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <2000000>;
+				};
+			};
+
+			vcc_3v3_s3: dcdc-reg8 {
+				regulator-name = "vcc_3v3_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			vddq_ddr_s0: dcdc-reg9 {
+				regulator-name = "vddq_ddr_s0";
+				regulator-always-on;
+				regulator-boot-on;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_1v8_s3: dcdc-reg10 {
+				regulator-name = "vcc_1v8_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vcca_1v8_s0: pldo-reg1 {
+				regulator-name = "vcca_1v8_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_1v8_s0: pldo-reg2 {
+				regulator-name = "vcc_1v8_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vdda_1v2_s0: pldo-reg3 {
+				regulator-name = "vdda_1v2_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcca_3v3_s0: pldo-reg4 {
+				regulator-name = "vcca_3v3_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vccio_sd_s0: pldo-reg5 {
+				regulator-name = "vccio_sd_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			pldo6_s3: pldo-reg6 {
+				regulator-name = "pldo6_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vdd_0v75_s3: nldo-reg1 {
+				regulator-name = "vdd_0v75_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <750000>;
+				};
+			};
+
+			vdda_ddr_pll_s0: nldo-reg2 {
+				regulator-name = "vdda_ddr_pll_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <850000>;
+				};
+			};
+
+			vdda_0v75_s0: nldo-reg3 {
+				regulator-name = "vdda_0v75_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdda_0v85_s0: nldo-reg4 {
+				regulator-name = "vdda_0v85_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_0v75_s0: nldo-reg5 {
+				regulator-name = "vdd_0v75_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+		};
+	};
+};
+
+&tsadc {
+	status = "okay";
+};
+
+&u2phy2 {
+	status = "okay";
+};
+
+&u2phy2_host {
+	phy-supply = <&vcc_5v0_usb_a>;
+	status = "okay";
+};
+
+&u2phy3 {
+	status = "okay";
+};
+
+&u2phy3_host {
+	status = "okay";
+};
+
+/* Mule-ATtiny debug UART; typically baudrate 9600 */
+&uart0 {
+	pinctrl-0 = <&uart0m0_xfer>;
+	status = "okay";
+};
+
+/* Main debug interface on P20 micro-USB B port and P21 header */
+&uart2 {
+	pinctrl-0 = <&uart2m0_xfer>;
+	status = "okay";
+};
+
+/* RS485 on P19 */
+&uart3 {
+	pinctrl-0 = <&uart3m2_xfer &uart3_rtsn>;
+	linux,rs485-enabled-at-boot-time;
+	status = "okay";
+};
+
+/* Mule-ATtiny UPDI flashing UART */
+&uart7 {
+	pinctrl-0 = <&uart7m0_xfer>;
+	status = "okay";
+};
+
+/* host0 on P10 USB-A */
+&usb_host0_ehci {
+	status = "okay";
+};
+
+/* host0 on P10 USB-A */
+&usb_host0_ohci {
+	status = "okay";
+};
+
+/* host1 on M.2 E-key */
+&usb_host1_ehci {
+	status = "okay";
+};
+
+/* host1 on M.2 E-key */
+&usb_host1_ohci {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts b/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts
index 97af4f912828..d7722772ecd8 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts
@@ -19,7 +19,6 @@
 	aliases {
 		mmc0 = &sdhci;
 		mmc1 = &sdmmc;
-		serial2 = &uart2;
 	};
 
 	chosen {
@@ -537,13 +536,12 @@
 };
 
 &sdmmc {
-	max-frequency = <200000000>;
-	no-sdio;
-	no-mmc;
 	bus-width = <4>;
 	cap-mmc-highspeed;
 	cap-sd-highspeed;
 	disable-wp;
+	no-mmc;
+	no-sdio;
 	sd-uhs-sdr104;
 	vmmc-supply = <&vcc_3v3_s3>;
 	vqmmc-supply = <&vccio_sd_s0>;
@@ -570,6 +568,8 @@
 		pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>,
 			    <&rk806_dvs2_null>, <&rk806_dvs3_null>;
 
+		system-power-controller;
+
 		vcc1-supply = <&vcc4v0_sys>;
 		vcc2-supply = <&vcc4v0_sys>;
 		vcc3-supply = <&vcc4v0_sys>;
@@ -590,7 +590,7 @@
 		#gpio-cells = <2>;
 
 		rk806_dvs1_null: dvs1-null-pins {
-			pins = "gpio_pwrctrl2";
+			pins = "gpio_pwrctrl1";
 			function = "pin_fun0";
 		};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts
index 298c183d6f4f..3e660ff6cd5f 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts
@@ -19,7 +19,6 @@
 	aliases {
 		mmc0 = &sdhci;
 		mmc1 = &sdmmc;
-		serial2 = &uart2;
 	};
 
 	chosen {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts b/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts
index 5c59f9571dce..87a0abf95f7d 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts
@@ -17,9 +17,9 @@
 	compatible = "pine64,quartzpro64", "rockchip,rk3588";
 
 	aliases {
+		ethernet0 = &gmac0;
 		mmc0 = &sdhci;
 		mmc1 = &sdmmc;
-		serial2 = &uart2;
 	};
 
 	chosen {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts
index 741f631db345..a0e303c3a1dc 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts
@@ -14,7 +14,6 @@
 		mmc0 = &sdhci;
 		mmc1 = &sdmmc;
 		mmc2 = &sdio;
-		serial2 = &uart2;
 	};
 
 	chosen {
@@ -138,6 +137,10 @@
 	status = "okay";
 };
 
+&combphy2_psu {
+	status = "okay";
+};
+
 &cpu_b0 {
 	cpu-supply = <&vdd_cpu_big0_s0>;
 };
@@ -423,6 +426,8 @@
 		pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>,
 			    <&rk806_dvs2_null>, <&rk806_dvs3_null>;
 
+		system-power-controller;
+
 		vcc1-supply = <&vcc5v0_sys>;
 		vcc2-supply = <&vcc5v0_sys>;
 		vcc3-supply = <&vcc5v0_sys>;
@@ -443,7 +448,7 @@
 		#gpio-cells = <2>;
 
 		rk806_dvs1_null: dvs1-null-pins {
-			pins = "gpio_pwrctrl2";
+			pins = "gpio_pwrctrl1";
 			function = "pin_fun0";
 		};
 
@@ -765,3 +770,7 @@
 &usb_host1_ohci {
 	status = "okay";
 };
+
+&usb_host2_xhci {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi
index 9570b34aca2e..dc08da518a76 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi
@@ -19,8 +19,6 @@
 	aliases {
 		ethernet0 = &gmac1;
 		mmc0 = &sdhci;
-		serial2 = &uart2;
-		serial9 = &uart9;
 	};
 
 	fan: pwm-fan {
@@ -235,13 +233,13 @@
 &pinctrl {
 	fan {
 		fan_int: fan-int {
-			rockchip,pins = <0 RK_PA4 RK_FUNC_GPIO &pcfg_pull_none>;
+			rockchip,pins = <0 RK_PA4 RK_FUNC_GPIO &pcfg_pull_up>;
 		};
 	};
 
 	hym8563 {
 		hym8563_int: hym8563-int {
-			rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_none>;
+			rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_up>;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts b/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts
new file mode 100644
index 000000000000..ef4f058c20ff
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts
@@ -0,0 +1,812 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2023 Rockchip Electronics Co., Ltd.
+ *
+ * https://cool-pi.com/topic/130/coolpi-4b-product-spec-introduction
+ *
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+#include "rk3588s.dtsi"
+
+/ {
+	model = "RK3588S CoolPi 4 Model B";
+	compatible = "coolpi,pi-4b", "rockchip,rk3588s";
+
+	aliases {
+		mmc0 = &sdhci;
+		mmc1 = &sdio;
+		mmc2 = &sdmmc;
+	};
+
+	analog-sound {
+		compatible = "audio-graph-card";
+		dais = <&i2s0_8ch_p0>;
+		label = "rk3588-es8316";
+		routing = "MIC2", "Mic Jack",
+			  "Headphones", "HPOL",
+			  "Headphones", "HPOR";
+		widgets = "Microphone", "Mic Jack",
+			  "Headphone", "Headphones";
+	};
+
+	chosen {
+		stdout-path = "serial2:1500000n8";
+	};
+
+	leds: leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&gpio_leds>;
+
+		led0: led-green {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_STATUS;
+			gpios = <&gpio0 RK_PD0 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "heartbeat";
+		};
+
+		led1: led-red {
+			color = <LED_COLOR_ID_RED>;
+			default-state = "off";
+			function = LED_FUNCTION_WLAN;
+			gpios = <&gpio0 RK_PC4 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "phy0tx";
+		};
+	};
+
+	sdio_pwrseq: sdio-pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		clocks = <&hym8563>;
+		clock-names = "ext_clock";
+		pinctrl-names = "default";
+		pinctrl-0 = <&wifi_enable_h>;
+		/*
+		 * On the module itself this is one of these (depending
+		 * on the actual card populated):
+		 * - SDIO_RESET_L_WL_REG_ON
+		 * - PDN (power down when low)
+		 */
+		post-power-on-delay-ms = <200>;
+		reset-gpios = <&gpio0 RK_PC7 GPIO_ACTIVE_LOW>;
+	};
+
+	vcc12v_dcin: vcc12v-dcin-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc12v_dcin";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <12000000>;
+		regulator-max-microvolt = <12000000>;
+	};
+
+	vcc5v0_sys: vcc5v0-sys-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0_sys";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc12v_dcin>;
+	};
+
+	vcc5v0_usbdcin: vcc5v0-usbdcin-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0_usbdcin";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc12v_dcin>;
+	};
+
+	vcc5v0_usb: vcc5v0-usb-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0_usb";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc5v0_usbdcin>;
+	};
+
+	avdd0v85_pcie20: avdd0v85-pcie20-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "avdd0v85_pcie20";
+		regulator-boot-on;
+		regulator-always-on;
+		regulator-min-microvolt = <850000>;
+		regulator-max-microvolt = <850000>;
+		vin-supply = <&vdd_0v85_s0>;
+	};
+
+	avdd1v8_pcie20: avdd1v8-pcie20-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "avdd1v8_pcie20";
+		regulator-boot-on;
+		regulator-always-on;
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		vin-supply = <&avcc_1v8_s0>;
+	};
+
+	vcc3v3_mipi: vcc3v3-mipi-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio3 RK_PC2 GPIO_ACTIVE_HIGH>;
+		regulator-name = "vcc3v3_mipi";
+		regulator-boot-on;
+		regulator-always-on;
+		vin-supply = <&vcc_3v3_s3>;
+	};
+
+	vcc5v0_host: vcc5v0-host-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio3 RK_PC0 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&vcc5v0_host_en>;
+		regulator-name = "vcc5v0_host";
+		regulator-boot-on;
+		regulator-always-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc5v0_sys>;
+	};
+
+	vcc5v0_otg: vcc5v0-otg-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio3 RK_PC1 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&vcc5v0_u3host_en>;
+		regulator-name = "vcc5v0_otg";
+		regulator-boot-on;
+		regulator-always-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc5v0_sys>;
+	};
+
+	vcc_1v1_nldo_s3: vcc-1v1-nldo-s3-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_1v1_nldo_s3";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <1100000>;
+		regulator-max-microvolt = <1100000>;
+		vin-supply = <&vcc5v0_sys>;
+	};
+};
+
+&combphy0_ps {
+	status = "okay";
+};
+
+&combphy2_psu {
+	status = "okay";
+};
+
+&cpu_l0 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_b0 {
+	cpu-supply = <&vdd_cpu_big0_s0>;
+};
+
+&cpu_b2 {
+	cpu-supply = <&vdd_cpu_big1_s0>;
+};
+
+&i2c0 {
+	pinctrl-0 = <&i2c0m2_xfer>;
+	status = "okay";
+
+	vdd_cpu_big0_s0: regulator@42 {
+		compatible = "rockchip,rk8602";
+		reg = <0x42>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_cpu_big0_s0";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <1050000>;
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+
+	vdd_cpu_big1_s0: regulator@43 {
+		compatible = "rockchip,rk8603", "rockchip,rk8602";
+		reg = <0x43>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_cpu_big1_s0";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <1050000>;
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+};
+
+&i2c2 {
+	status = "okay";
+
+	vdd_npu_s0: regulator@42 {
+		compatible = "rockchip,rk8602";
+		reg = <0x42>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_npu_s0";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <950000>;
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+};
+
+&i2c6 {
+	pinctrl-0 = <&i2c6m3_xfer>;
+	status = "okay";
+
+	hym8563: rtc@51 {
+		compatible = "haoyu,hym8563";
+		reg = <0x51>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <RK_PB0 IRQ_TYPE_LEVEL_LOW>;
+		#clock-cells = <0>;
+		clock-output-names = "hym8563";
+		pinctrl-names = "default";
+		pinctrl-0 = <&hym8563_int>;
+	};
+};
+
+&i2c7 {
+	pinctrl-0 = <&i2c7m0_xfer>;
+	status = "okay";
+
+	es8316: audio-codec@11 {
+		compatible = "everest,es8316";
+		reg = <0x11>;
+		assigned-clocks = <&cru I2S0_8CH_MCLKOUT>;
+		assigned-clock-rates = <12288000>;
+		clocks = <&cru I2S0_8CH_MCLKOUT>;
+		clock-names = "mclk";
+		#sound-dai-cells = <0>;
+
+		port {
+			es8316_p0_0: endpoint {
+				remote-endpoint = <&i2s0_8ch_p0_0>;
+			};
+		};
+	};
+};
+
+&i2s0_8ch {
+	pinctrl-0 = <&i2s0_lrck
+		     &i2s0_mclk
+		     &i2s0_sclk
+		     &i2s0_sdi0
+		     &i2s0_sdo0>;
+	status = "okay";
+
+	i2s0_8ch_p0: port {
+		i2s0_8ch_p0_0: endpoint {
+			dai-format = "i2s";
+			mclk-fs = <256>;
+			remote-endpoint = <&es8316_p0_0>;
+		};
+	};
+};
+
+&pcie2x1l2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&rtl8111_isolate>;
+	reset-gpios = <&gpio3 RK_PD1 GPIO_ACTIVE_HIGH>;
+	status = "okay";
+};
+
+&pinctrl {
+	hym8563 {
+		hym8563_int: hym8563-int {
+			rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	led {
+		gpio_leds: gpio-leds {
+			rockchip,pins = <0 RK_PC4 RK_FUNC_GPIO &pcfg_pull_down>,
+					<0 RK_PD0 RK_FUNC_GPIO &pcfg_pull_down>;
+		};
+	};
+
+	rtl8111 {
+		rtl8111_isolate: rtl8111-isolate {
+			rockchip,pins = <1 RK_PA4 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	sdio-pwrseq {
+		wifi_enable_h: wifi-enable-h {
+			rockchip,pins = <0 RK_PC7 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	usb {
+		vcc5v0_host_en: vcc5v0-host-en {
+			rockchip,pins = <3 RK_PC0 RK_FUNC_GPIO &pcfg_pull_none>,
+					<4 RK_PB5 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+
+		vcc5v0_u3host_en: vcc5v0-u3host-en {
+			rockchip,pins = <3 RK_PC1 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	wireless-bluetooth {
+		bt_reset_gpio: bt-reset-pin {
+			rockchip,pins = <0 RK_PD3 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		bt_wake_gpio: bt-wake-pin {
+			rockchip,pins = <0 RK_PC6 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		bt_wake_host_irq: bt-wake-host-irq {
+			rockchip,pins = <0 RK_PC5 RK_FUNC_GPIO &pcfg_pull_down>;
+		};
+	};
+
+	wireless-wlan {
+		wifi_host_wake_irq: wifi-host-wake-irq {
+			rockchip,pins = <0 RK_PA0 RK_FUNC_GPIO &pcfg_pull_down>;
+		};
+
+		wifi_poweren_pin: wifi-poweren-pin {
+			rockchip,pins = <1 RK_PD3 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+};
+
+&pwm2 {
+	pinctrl-0 = <&pwm2m1_pins>;
+	status = "okay";
+};
+
+&pwm13 {
+	pinctrl-names = "active";
+	pinctrl-0 = <&pwm13m2_pins>;
+	status = "okay";
+};
+
+&saradc {
+	vref-supply = <&vcc_1v8_s0>;
+	status = "okay";
+};
+
+&sdhci {
+	bus-width = <8>;
+	max-frequency = <200000000>;
+	mmc-hs400-1_8v;
+	mmc-hs400-enhanced-strobe;
+	no-sdio;
+	no-sd;
+	non-removable;
+	status = "okay";
+};
+
+&sdio {
+	bus-width = <4>;
+	cap-sd-highspeed;
+	cap-sdio-irq;
+	disable-wp;
+	keep-power-in-suspend;
+	max-frequency = <150000000>;
+	mmc-pwrseq = <&sdio_pwrseq>;
+	no-sd;
+	no-mmc;
+	non-removable;
+	pinctrl-names = "default";
+	pinctrl-0 = <&sdiom1_pins>,<&wifi_poweren_pin>;
+	status = "okay";
+};
+
+&sdmmc {
+	bus-width = <4>;
+	cap-mmc-highspeed;
+	cap-sd-highspeed;
+	disable-wp;
+	max-frequency = <150000000>;
+	no-sdio;
+	no-mmc;
+	sd-uhs-sdr104;
+	vmmc-supply = <&vcc_3v3_s3>;
+	vqmmc-supply = <&vccio_sd_s0>;
+	status = "okay";
+};
+
+&spi2 {
+	assigned-clocks = <&cru CLK_SPI2>;
+	assigned-clock-rates = <200000000>;
+	num-cs = <1>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&spi2m2_cs0 &spi2m2_pins>;
+	status = "okay";
+
+	pmic@0 {
+		compatible = "rockchip,rk806";
+		reg = <0x0>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <7 IRQ_TYPE_LEVEL_LOW>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>,
+			    <&rk806_dvs2_null>, <&rk806_dvs3_null>;
+		spi-max-frequency = <1000000>;
+		vcc1-supply = <&vcc5v0_sys>;
+		vcc2-supply = <&vcc5v0_sys>;
+		vcc3-supply = <&vcc5v0_sys>;
+		vcc4-supply = <&vcc5v0_sys>;
+		vcc5-supply = <&vcc5v0_sys>;
+		vcc6-supply = <&vcc5v0_sys>;
+		vcc7-supply = <&vcc5v0_sys>;
+		vcc8-supply = <&vcc5v0_sys>;
+		vcc9-supply = <&vcc5v0_sys>;
+		vcc10-supply = <&vcc5v0_sys>;
+		vcc11-supply = <&vcc_2v0_pldo_s3>;
+		vcc12-supply = <&vcc5v0_sys>;
+		vcc13-supply = <&vcc_1v1_nldo_s3>;
+		vcc14-supply = <&vcc_1v1_nldo_s3>;
+		vcca-supply = <&vcc5v0_sys>;
+
+		rk806_dvs1_null: dvs1-null-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs2_null: dvs2-null-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs3_null: dvs3-null-pins {
+			pins = "gpio_pwrctrl3";
+			function = "pin_fun0";
+		};
+
+		regulators {
+			vdd_gpu_s0: vdd_gpu_mem_s0: dcdc-reg1 {
+				regulator-name = "vdd_gpu_s0";
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+				regulator-enable-ramp-delay = <400>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_cpu_lit_s0: vdd_cpu_lit_mem_s0: dcdc-reg2 {
+				regulator-name = "vdd_cpu_lit_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_log_s0: dcdc-reg3 {
+				regulator-name = "vdd_log_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <675000>;
+				regulator-max-microvolt = <750000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <750000>;
+				};
+			};
+
+			vdd_vdenc_s0: vdd_vdenc_mem_s0: dcdc-reg4 {
+				regulator-name = "vdd_vdenc_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_ddr_s0: dcdc-reg5 {
+				regulator-name = "vdd_ddr_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <675000>;
+				regulator-max-microvolt = <900000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <850000>;
+				};
+			};
+
+			vdd2_ddr_s3: dcdc-reg6 {
+				regulator-name = "vdd2_ddr_s3";
+				regulator-always-on;
+				regulator-boot-on;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+				};
+			};
+
+			vcc_2v0_pldo_s3: dcdc-reg7 {
+				regulator-name = "vdd_2v0_pldo_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <2000000>;
+				regulator-max-microvolt = <2000000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <2000000>;
+				};
+			};
+
+			vcc_3v3_s3: dcdc-reg8 {
+				regulator-name = "vcc_3v3_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			vddq_ddr_s0: dcdc-reg9 {
+				regulator-name = "vddq_ddr_s0";
+				regulator-always-on;
+				regulator-boot-on;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_1v8_s3: dcdc-reg10 {
+				regulator-name = "vcc_1v8_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			avcc_1v8_s0: pldo-reg1 {
+				regulator-name = "avcc_1v8_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_1v8_s0: pldo-reg2 {
+				regulator-name = "vcc_1v8_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			avdd_1v2_s0: pldo-reg3 {
+				regulator-name = "avdd_1v2_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_3v3_s0: pldo-reg4 {
+				regulator-name = "vcc_3v3_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vccio_sd_s0: pldo-reg5 {
+				regulator-name = "vccio_sd_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			pldo6_s3: pldo-reg6 {
+				regulator-name = "pldo6_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vdd_0v75_s3: nldo-reg1 {
+				regulator-name = "vdd_0v75_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <750000>;
+				};
+			};
+
+			vdd_ddr_pll_s0: nldo-reg2 {
+				regulator-name = "vdd_ddr_pll_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <850000>;
+				};
+			};
+
+			avdd_0v75_s0: nldo-reg3 {
+				regulator-name = "avdd_0v75_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_0v85_s0: nldo-reg4 {
+				regulator-name = "vdd_0v85_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_0v75_s0: nldo-reg5 {
+				regulator-name = "vdd_0v75_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+		};
+	};
+};
+
+&tsadc {
+	status = "okay";
+};
+
+&u2phy2 {
+	status = "okay";
+};
+
+&u2phy3 {
+	status = "okay";
+};
+
+&u2phy2_host {
+	phy-supply = <&vcc5v0_host>;
+	status = "okay";
+};
+
+&u2phy3_host {
+	status = "okay";
+};
+
+&uart2 {
+	pinctrl-0 = <&uart2m0_xfer>;
+	status = "okay";
+};
+
+/* bt */
+&uart9 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart9m2_xfer &uart9m2_ctsn>;
+};
+
+&usb_host0_ehci {
+	status = "okay";
+};
+
+&usb_host0_ohci {
+	status = "okay";
+};
+
+&usb_host1_ehci {
+	status = "okay";
+};
+
+&usb_host1_ohci {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts b/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts
index 60f00ceb630e..dc677f29a9c7 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts
@@ -44,7 +44,6 @@
 		mmc0 = &sdhci;
 		mmc1 = &sdmmc;
 		mmc2 = &sdio;
-		serial2 = &uart2;
 	};
 
 	chosen {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-khadas-edge2.dts b/arch/arm64/boot/dts/rockchip/rk3588s-khadas-edge2.dts
index 82478a452533..f53e993c785e 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-khadas-edge2.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-khadas-edge2.dts
@@ -12,7 +12,6 @@
 
 	aliases {
 		mmc0 = &sdhci;
-		serial2 = &uart2;
 	};
 
 	chosen {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-orangepi-5.dts b/arch/arm64/boot/dts/rockchip/rk3588s-orangepi-5.dts
index 8f399c4317bd..25de4362af38 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-orangepi-5.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-orangepi-5.dts
@@ -13,8 +13,8 @@
 	compatible = "xunlong,orangepi-5", "rockchip,rk3588s";
 
 	aliases {
+		ethernet0 = &gmac1;
 		mmc0 = &sdmmc;
-		serial2 = &uart2;
 	};
 
 	chosen {
@@ -38,7 +38,7 @@
 	leds {
 		compatible = "gpio-leds";
 		pinctrl-names = "default";
-		pinctrl-0 =<&leds_gpio>;
+		pinctrl-0 = <&leds_gpio>;
 
 		led-1 {
 			gpios = <&gpio1 RK_PA2 GPIO_ACTIVE_HIGH>;
@@ -314,6 +314,7 @@
 		pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>,
 				<&rk806_dvs2_null>, <&rk806_dvs3_null>;
 		spi-max-frequency = <1000000>;
+		system-power-controller;
 
 		vcc1-supply = <&vcc5v0_sys>;
 		vcc2-supply = <&vcc5v0_sys>;
@@ -660,3 +661,7 @@
 &usb_host1_ohci {
 	status = "okay";
 };
+
+&usb_host2_xhci {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-pinctrl.dtsi b/arch/arm64/boot/dts/rockchip/rk3588s-pinctrl.dtsi
index 63151d9d2377..30db12c4fc82 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-pinctrl.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-pinctrl.dtsi
@@ -369,7 +369,7 @@
 		emmc_data_strobe: emmc-data-strobe {
 			rockchip,pins =
 				/* emmc_data_strobe */
-				<2 RK_PA2 1 &pcfg_pull_none>;
+				<2 RK_PA2 1 &pcfg_pull_down>;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts b/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts
index 8347adcbd003..2002fd0221fa 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts
@@ -12,9 +12,9 @@
 	compatible = "radxa,rock-5a", "rockchip,rk3588s";
 
 	aliases {
+		ethernet0 = &gmac1;
 		mmc0 = &sdhci;
 		mmc1 = &sdmmc;
-		serial2 = &uart2;
 	};
 
 	analog-sound {
@@ -114,6 +114,10 @@
 	};
 };
 
+&combphy2_psu {
+	status = "okay";
+};
+
 &cpu_b0 {
 	cpu-supply = <&vdd_cpu_big0_s0>;
 };
@@ -734,3 +738,7 @@
 &usb_host1_ohci {
 	status = "okay";
 };
+
+&usb_host2_xhci {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s.dtsi b/arch/arm64/boot/dts/rockchip/rk3588s.dtsi
index 7064c0e9179f..36b1b7acfe6a 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588s.dtsi
@@ -18,6 +18,38 @@
 	#address-cells = <2>;
 	#size-cells = <2>;
 
+	aliases {
+		gpio0 = &gpio0;
+		gpio1 = &gpio1;
+		gpio2 = &gpio2;
+		gpio3 = &gpio3;
+		gpio4 = &gpio4;
+		i2c0 = &i2c0;
+		i2c1 = &i2c1;
+		i2c2 = &i2c2;
+		i2c3 = &i2c3;
+		i2c4 = &i2c4;
+		i2c5 = &i2c5;
+		i2c6 = &i2c6;
+		i2c7 = &i2c7;
+		i2c8 = &i2c8;
+		serial0 = &uart0;
+		serial1 = &uart1;
+		serial2 = &uart2;
+		serial3 = &uart3;
+		serial4 = &uart4;
+		serial5 = &uart5;
+		serial6 = &uart6;
+		serial7 = &uart7;
+		serial8 = &uart8;
+		serial9 = &uart9;
+		spi0 = &spi0;
+		spi1 = &spi1;
+		spi2 = &spi2;
+		spi3 = &spi3;
+		spi4 = &spi4;
+	};
+
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -362,6 +394,11 @@
 		#clock-cells = <0>;
 	};
 
+	display_subsystem: display-subsystem {
+		compatible = "rockchip,display-subsystem";
+		ports = <&vop_out>;
+	};
+
 	timer {
 		compatible = "arm,armv8-timer";
 		interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH 0>,
@@ -474,6 +511,16 @@
 		reg = <0x0 0xfd58c000 0x0 0x1000>;
 	};
 
+	vop_grf: syscon@fd5a4000 {
+		compatible = "rockchip,rk3588-vop-grf", "syscon";
+		reg = <0x0 0xfd5a4000 0x0 0x2000>;
+	};
+
+	vo1_grf: syscon@fd5a8000 {
+		compatible = "rockchip,rk3588-vo-grf", "syscon";
+		reg = <0x0 0xfd5a8000 0x0 0x100>;
+	};
+
 	php_grf: syscon@fd5b0000 {
 		compatible = "rockchip,rk3588-php-grf", "syscon";
 		reg = <0x0 0xfd5b0000 0x0 0x1000>;
@@ -593,6 +640,74 @@
 		status = "disabled";
 	};
 
+	vop: vop@fdd90000 {
+		compatible = "rockchip,rk3588-vop";
+		reg = <0x0 0xfdd90000 0x0 0x4200>, <0x0 0xfdd95000 0x0 0x1000>;
+		reg-names = "vop", "gamma-lut";
+		interrupts = <GIC_SPI 156 IRQ_TYPE_LEVEL_HIGH 0>;
+		clocks = <&cru ACLK_VOP>,
+			 <&cru HCLK_VOP>,
+			 <&cru DCLK_VOP0>,
+			 <&cru DCLK_VOP1>,
+			 <&cru DCLK_VOP2>,
+			 <&cru DCLK_VOP3>,
+			 <&cru PCLK_VOP_ROOT>;
+		clock-names = "aclk",
+			      "hclk",
+			      "dclk_vp0",
+			      "dclk_vp1",
+			      "dclk_vp2",
+			      "dclk_vp3",
+			      "pclk_vop";
+		iommus = <&vop_mmu>;
+		power-domains = <&power RK3588_PD_VOP>;
+		rockchip,grf = <&sys_grf>;
+		rockchip,vop-grf = <&vop_grf>;
+		rockchip,vo1-grf = <&vo1_grf>;
+		rockchip,pmu = <&pmu>;
+		status = "disabled";
+
+		vop_out: ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			vp0: port@0 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <0>;
+			};
+
+			vp1: port@1 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <1>;
+			};
+
+			vp2: port@2 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <2>;
+			};
+
+			vp3: port@3 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <3>;
+			};
+		};
+	};
+
+	vop_mmu: iommu@fdd97e00 {
+		compatible = "rockchip,rk3588-iommu", "rockchip,rk3568-iommu";
+		reg = <0x0 0xfdd97e00 0x0 0x100>, <0x0 0xfdd97f00 0x0 0x100>;
+		interrupts = <GIC_SPI 156 IRQ_TYPE_LEVEL_HIGH 0>;
+		clocks = <&cru ACLK_VOP>, <&cru HCLK_VOP>;
+		clock-names = "aclk", "iface";
+		#iommu-cells = <0>;
+		power-domains = <&power RK3588_PD_VOP>;
+		status = "disabled";
+	};
+
 	uart0: serial@fd890000 {
 		compatible = "rockchip,rk3588-uart", "snps,dw-apb-uart";
 		reg = <0x0 0xfd890000 0x0 0x100>;
@@ -916,6 +1031,7 @@
 				reg = <RK3588_PD_USB>;
 				clocks = <&cru PCLK_PHP_ROOT>,
 					 <&cru ACLK_USB_ROOT>,
+					 <&cru ACLK_USB>,
 					 <&cru HCLK_USB_ROOT>,
 					 <&cru HCLK_HOST0>,
 					 <&cru HCLK_HOST_ARB0>,
@@ -1362,7 +1478,6 @@
 			     <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH 0>,
 			     <GIC_SPI 48 IRQ_TYPE_LEVEL_HIGH 0>,
 			     <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH 0>;
-		interrupt-names = "ch0", "ch1", "ch2", "ch3";
 		rockchip,pmu = <&pmu1grf>;
 	};
 
diff --git a/arch/arm64/boot/dts/sprd/Makefile b/arch/arm64/boot/dts/sprd/Makefile
index 97522fb0bf66..3ce81ad7116f 100644
--- a/arch/arm64/boot/dts/sprd/Makefile
+++ b/arch/arm64/boot/dts/sprd/Makefile
@@ -2,4 +2,5 @@
 dtb-$(CONFIG_ARCH_SPRD) += sc9836-openphone.dtb \
 			sp9860g-1h10.dtb	\
 			sp9863a-1h10.dtb	\
-			ums512-1h10.dtb
+			ums512-1h10.dtb		\
+			ums9620-2h10.dtb
diff --git a/arch/arm64/boot/dts/sprd/ums512.dtsi b/arch/arm64/boot/dts/sprd/ums512.dtsi
index 024be594c47d..dbdb79f8e959 100644
--- a/arch/arm64/boot/dts/sprd/ums512.dtsi
+++ b/arch/arm64/boot/dts/sprd/ums512.dtsi
@@ -96,7 +96,7 @@
 
 		CPU6: cpu@600 {
 			device_type = "cpu";
-			compatible = "arm,cortex-a55";
+			compatible = "arm,cortex-a75";
 			reg = <0x0 0x600>;
 			enable-method = "psci";
 			cpu-idle-states = <&CORE_PD>;
@@ -104,7 +104,7 @@
 
 		CPU7: cpu@700 {
 			device_type = "cpu";
-			compatible = "arm,cortex-a55";
+			compatible = "arm,cortex-a75";
 			reg = <0x0 0x700>;
 			enable-method = "psci";
 			cpu-idle-states = <&CORE_PD>;
@@ -113,7 +113,7 @@
 
 	idle-states {
 		entry-method = "psci";
-		CORE_PD: core-pd {
+		CORE_PD: cpu-pd {
 			compatible = "arm,idle-state";
 			entry-latency-us = <4000>;
 			exit-latency-us = <4000>;
@@ -291,6 +291,7 @@
 			pll2: clock-controller@0 {
 				compatible = "sprd,ums512-gc-pll";
 				reg = <0x0 0x100>;
+				clocks = <&ext_26m>;
 				clock-names = "ext-26m";
 				#clock-cells = <1>;
 			};
@@ -682,8 +683,8 @@
 			compatible = "arm,coresight-etm4x", "arm,primecell";
 			reg = <0 0x3f040000 0 0x1000>;
 			cpu = <&CPU0>;
-			clocks = <&ext_26m>, <&aon_clk CLK_CSSYS>, <&pll2 CLK_TWPLL_512M>;
-			clock-names = "apb_pclk", "clk_cs", "cs_src";
+			clocks = <&ext_26m>;
+			clock-names = "apb_pclk";
 
 			out-ports {
 				port {
@@ -699,8 +700,8 @@
 			compatible = "arm,coresight-etm4x", "arm,primecell";
 			reg = <0 0x3f140000 0 0x1000>;
 			cpu = <&CPU1>;
-			clocks = <&ext_26m>, <&aon_clk CLK_CSSYS>, <&pll2 CLK_TWPLL_512M>;
-			clock-names = "apb_pclk", "clk_cs", "cs_src";
+			clocks = <&ext_26m>;
+			clock-names = "apb_pclk";
 
 			out-ports {
 				port {
@@ -716,8 +717,8 @@
 			compatible = "arm,coresight-etm4x", "arm,primecell";
 			reg = <0 0x3f240000 0 0x1000>;
 			cpu = <&CPU2>;
-			clocks = <&ext_26m>, <&aon_clk CLK_CSSYS>, <&pll2 CLK_TWPLL_512M>;
-			clock-names = "apb_pclk", "clk_cs", "cs_src";
+			clocks = <&ext_26m>;
+			clock-names = "apb_pclk";
 
 			out-ports {
 				port {
@@ -733,8 +734,8 @@
 			compatible = "arm,coresight-etm4x", "arm,primecell";
 			reg = <0 0x3f340000 0 0x1000>;
 			cpu = <&CPU3>;
-			clocks = <&ext_26m>, <&aon_clk CLK_CSSYS>, <&pll2 CLK_TWPLL_512M>;
-			clock-names = "apb_pclk", "clk_cs", "cs_src";
+			clocks = <&ext_26m>;
+			clock-names = "apb_pclk";
 
 			out-ports {
 				port {
@@ -750,8 +751,8 @@
 			compatible = "arm,coresight-etm4x", "arm,primecell";
 			reg = <0 0x3f440000 0 0x1000>;
 			cpu = <&CPU4>;
-			clocks = <&ext_26m>, <&aon_clk CLK_CSSYS>, <&pll2 CLK_TWPLL_512M>;
-			clock-names = "apb_pclk", "clk_cs", "cs_src";
+			clocks = <&ext_26m>;
+			clock-names = "apb_pclk";
 
 			out-ports {
 				port {
@@ -767,8 +768,8 @@
 			compatible = "arm,coresight-etm4x", "arm,primecell";
 			reg = <0 0x3f540000 0 0x1000>;
 			cpu = <&CPU5>;
-			clocks = <&ext_26m>, <&aon_clk CLK_CSSYS>, <&pll2 CLK_TWPLL_512M>;
-			clock-names = "apb_pclk", "clk_cs", "cs_src";
+			clocks = <&ext_26m>;
+			clock-names = "apb_pclk";
 
 			out-ports {
 				port {
@@ -784,8 +785,8 @@
 			compatible = "arm,coresight-etm4x", "arm,primecell";
 			reg = <0 0x3f640000 0 0x1000>;
 			cpu = <&CPU6>;
-			clocks = <&ext_26m>, <&aon_clk CLK_CSSYS>, <&pll2 CLK_TWPLL_512M>;
-			clock-names = "apb_pclk", "clk_cs", "cs_src";
+			clocks = <&ext_26m>;
+			clock-names = "apb_pclk";
 
 			out-ports {
 				port {
@@ -801,8 +802,8 @@
 			compatible = "arm,coresight-etm4x", "arm,primecell";
 			reg = <0 0x3f740000 0 0x1000>;
 			cpu = <&CPU7>;
-			clocks = <&ext_26m>, <&aon_clk CLK_CSSYS>, <&pll2 CLK_TWPLL_512M>;
-			clock-names = "apb_pclk", "clk_cs", "cs_src";
+			clocks = <&ext_26m>;
+			clock-names = "apb_pclk";
 
 			out-ports {
 				port {
diff --git a/arch/arm64/boot/dts/sprd/ums9620-2h10.dts b/arch/arm64/boot/dts/sprd/ums9620-2h10.dts
new file mode 100644
index 000000000000..b35671192a72
--- /dev/null
+++ b/arch/arm64/boot/dts/sprd/ums9620-2h10.dts
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Unisoc UMS9620-2h10 board DTS file
+ *
+ * Copyright (C) 2023, Unisoc Inc.
+ */
+
+/dts-v1/;
+
+#include "ums9620.dtsi"
+
+/ {
+	model = "Unisoc UMS9620-2H10 Board";
+
+	compatible = "sprd,ums9620-2h10", "sprd,ums9620";
+
+	aliases {
+		serial0 = &uart0;
+		serial1 = &uart1;
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x0 0x80000000 0x2 0x00000000>;
+	};
+
+	chosen {
+		stdout-path = "serial1:921600n8";
+	};
+};
+
+&uart0 {
+	status = "okay";
+};
+
+&uart1 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/sprd/ums9620.dtsi b/arch/arm64/boot/dts/sprd/ums9620.dtsi
new file mode 100644
index 000000000000..2191f0a4811b
--- /dev/null
+++ b/arch/arm64/boot/dts/sprd/ums9620.dtsi
@@ -0,0 +1,245 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Unisoc UMS9620 DTS file
+ *
+ * Copyright (C) 2023, Unisoc Inc.
+ */
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/ {
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&CPU0>;
+				};
+				core1 {
+					cpu = <&CPU1>;
+				};
+				core2 {
+					cpu = <&CPU2>;
+				};
+				core3 {
+					cpu = <&CPU3>;
+				};
+				core4 {
+					cpu = <&CPU4>;
+				};
+				core5 {
+					cpu = <&CPU5>;
+				};
+				core6 {
+					cpu = <&CPU6>;
+				};
+				core7 {
+					cpu = <&CPU7>;
+				};
+			};
+		};
+
+		CPU0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a55";
+			reg = <0x0 0x0>;
+			enable-method = "psci";
+			cpu-idle-states = <&LIT_CORE_PD>;
+		};
+
+		CPU1: cpu@100 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a55";
+			reg = <0x0 0x100>;
+			enable-method = "psci";
+			cpu-idle-states = <&LIT_CORE_PD>;
+		};
+
+		CPU2: cpu@200 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a55";
+			reg = <0x0 0x200>;
+			enable-method = "psci";
+			cpu-idle-states = <&LIT_CORE_PD>;
+		};
+
+		CPU3: cpu@300 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a55";
+			reg = <0x0 0x300>;
+			enable-method = "psci";
+			cpu-idle-states = <&LIT_CORE_PD>;
+		};
+
+		CPU4: cpu@400 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a76";
+			reg = <0x0 0x400>;
+			enable-method = "psci";
+			cpu-idle-states = <&BIG_CORE_PD>;
+		};
+
+		CPU5: cpu@500 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a76";
+			reg = <0x0 0x500>;
+			enable-method = "psci";
+			cpu-idle-states = <&BIG_CORE_PD>;
+		};
+
+		CPU6: cpu@600 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a76";
+			reg = <0x0 0x600>;
+			enable-method = "psci";
+			cpu-idle-states = <&BIG_CORE_PD>;
+		};
+
+		CPU7: cpu@700 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a76";
+			reg = <0x0 0x700>;
+			enable-method = "psci";
+			cpu-idle-states = <&BIG_CORE_PD>;
+		};
+	};
+
+	idle-states {
+		entry-method = "psci";
+		LIT_CORE_PD: cpu-pd-lit {
+			compatible = "arm,idle-state";
+			entry-latency-us = <1000>;
+			exit-latency-us = <500>;
+			min-residency-us = <2500>;
+			local-timer-stop;
+			arm,psci-suspend-param = <0x00010000>;
+		};
+
+		BIG_CORE_PD: cpu-pd-big {
+			compatible = "arm,idle-state";
+			entry-latency-us = <4000>;
+			exit-latency-us = <4000>;
+			min-residency-us = <10000>;
+			local-timer-stop;
+			arm,psci-suspend-param = <0x00010000>;
+		};
+	};
+
+	psci {
+		compatible = "arm,psci-0.2";
+		method = "smc";
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>, /* Physical Secure PPI */
+			     <GIC_PPI 14 IRQ_TYPE_LEVEL_HIGH>, /* Physical Non-Secure PPI */
+			     <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>, /* Virtual PPI */
+			     <GIC_PPI 10 IRQ_TYPE_LEVEL_HIGH>; /* Hipervisor PPI */
+	};
+
+	pmu {
+		compatible = "arm,armv8-pmuv3";
+		interrupts = <GIC_SPI 177 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 178 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 179 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 180 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 181 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 182 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 183 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 184 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
+	soc: soc {
+		compatible = "simple-bus";
+		ranges;
+		#address-cells = <2>;
+		#size-cells = <2>;
+
+		gic: interrupt-controller@12000000 {
+			compatible = "arm,gic-v3";
+			reg = <0x0 0x12000000 0 0x20000>,	/* GICD */
+			      <0x0 0x12040000 0 0x100000>;	/* GICR */
+			#interrupt-cells = <3>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			redistributor-stride = <0x0 0x20000>;	/* 128KB stride */
+			#redistributor-regions = <1>;
+			interrupt-controller;
+			interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		apb@20200000 {
+			compatible = "simple-bus";
+			ranges = <0 0 0x20200000 0x100000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			uart0: serial@0 {
+				compatible = "sprd,ums9620-uart",
+					     "sprd,sc9836-uart";
+				reg = <0 0x100>;
+				interrupts = <GIC_SPI 196 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&ext_26m>;
+				status = "disabled";
+			};
+
+			uart1: serial@10000 {
+				compatible = "sprd,ums9620-uart",
+					     "sprd,sc9836-uart";
+				reg = <0x10000 0x100>;
+				interrupts = <GIC_SPI 195 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&ext_26m>;
+				status = "disabled";
+			};
+		};
+	};
+
+	ext_26m: clk-26m {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <26000000>;
+		clock-output-names = "ext-26m";
+	};
+
+	ext_4m: clk-4m {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <4000000>;
+		clock-output-names = "ext-4m";
+	};
+
+	ext_32k: clk-32k {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <32768>;
+		clock-output-names = "ext-32k";
+	};
+
+	rco_100m: clk-100m {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <100000000>;
+		clock-output-names = "rco-100m";
+	};
+
+	dphy_312m5: dphy-312m5 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <312500000>;
+		clock-output-names = "dphy-312m5";
+	};
+
+	dphy_416m7: dphy-416m7 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <416700000>;
+		clock-output-names = "dphy-416m7";
+	};
+};
diff --git a/arch/arm64/boot/dts/st/stm32mp251.dtsi b/arch/arm64/boot/dts/st/stm32mp251.dtsi
index 124403f5f1f4..96859d098ef8 100644
--- a/arch/arm64/boot/dts/st/stm32mp251.dtsi
+++ b/arch/arm64/boot/dts/st/stm32mp251.dtsi
@@ -140,6 +140,22 @@
 			};
 		};
 
+		bsec: efuse@44000000 {
+			compatible = "st,stm32mp25-bsec";
+			reg = <0x44000000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			part_number_otp@24 {
+				reg = <0x24 0x4>;
+			};
+
+			package_otp@1e8 {
+				reg = <0x1e8 0x1>;
+				bits = <0 3>;
+			};
+		};
+
 		syscfg: syscon@44230000 {
 			compatible = "st,stm32mp25-syscfg", "syscon";
 			reg = <0x44230000 0x10000>;
diff --git a/arch/arm64/boot/dts/tesla/fsd.dtsi b/arch/arm64/boot/dts/tesla/fsd.dtsi
index bb50a9f7db4a..aaffb50b8b60 100644
--- a/arch/arm64/boot/dts/tesla/fsd.dtsi
+++ b/arch/arm64/boot/dts/tesla/fsd.dtsi
@@ -342,6 +342,18 @@
 		#clock-cells = <0>;
 	};
 
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		mfc_left: region@84000000 {
+			compatible = "shared-dma-pool";
+			no-map;
+			reg = <0 0x84000000 0 0x8000000>;
+		};
+	};
+
 	soc: soc@0 {
 		compatible = "simple-bus";
 		#address-cells = <2>;
@@ -581,7 +593,7 @@
 		};
 
 		serial_0: serial@14180000 {
-			compatible = "samsung,exynos4210-uart";
+			compatible = "tesla,fsd-uart", "samsung,exynos4210-uart";
 			reg = <0x0 0x14180000 0x0 0x100>;
 			interrupts = <GIC_SPI 171 IRQ_TYPE_LEVEL_HIGH>;
 			dmas = <&pdma1 1>, <&pdma1 0>;
@@ -593,7 +605,7 @@
 		};
 
 		serial_1: serial@14190000 {
-			compatible = "samsung,exynos4210-uart";
+			compatible = "tesla,fsd-uart", "samsung,exynos4210-uart";
 			reg = <0x0 0x14190000 0x0 0x100>;
 			interrupts = <GIC_SPI 172 IRQ_TYPE_LEVEL_HIGH>;
 			dmas = <&pdma1 3>, <&pdma1 2>;
@@ -605,12 +617,12 @@
 		};
 
 		pmu_system_controller: system-controller@11400000 {
-			compatible = "samsung,exynos7-pmu", "syscon";
+			compatible = "tesla,fsd-pmu", "samsung,exynos7-pmu", "syscon";
 			reg = <0x0 0x11400000 0x0 0x5000>;
 		};
 
 		watchdog_0: watchdog@100a0000 {
-			compatible = "samsung,exynos7-wdt";
+			compatible = "tesla,fsd-wdt", "samsung,exynos7-wdt";
 			reg = <0x0 0x100a0000 0x0 0x100>;
 			interrupts = <GIC_SPI 471 IRQ_TYPE_LEVEL_HIGH>;
 			samsung,syscon-phandle = <&pmu_system_controller>;
@@ -619,7 +631,7 @@
 		};
 
 		watchdog_1: watchdog@100b0000 {
-			compatible = "samsung,exynos7-wdt";
+			compatible = "tesla,fsd-wdt", "samsung,exynos7-wdt";
 			reg = <0x0 0x100b0000 0x0 0x100>;
 			interrupts = <GIC_SPI 472 IRQ_TYPE_LEVEL_HIGH>;
 			samsung,syscon-phandle = <&pmu_system_controller>;
@@ -628,7 +640,7 @@
 		};
 
 		watchdog_2: watchdog@100c0000 {
-			compatible = "samsung,exynos7-wdt";
+			compatible = "tesla,fsd-wdt", "samsung,exynos7-wdt";
 			reg = <0x0 0x100c0000 0x0 0x100>;
 			interrupts = <GIC_SPI 473 IRQ_TYPE_LEVEL_HIGH>;
 			samsung,syscon-phandle = <&pmu_system_controller>;
@@ -637,7 +649,7 @@
 		};
 
 		pwm_0: pwm@14100000 {
-			compatible = "samsung,exynos4210-pwm";
+			compatible = "tesla,fsd-pwm", "samsung,exynos4210-pwm";
 			reg = <0x0 0x14100000 0x0 0x100>;
 			samsung,pwm-outputs = <0>, <1>, <2>, <3>;
 			#pwm-cells = <3>;
@@ -647,7 +659,7 @@
 		};
 
 		pwm_1: pwm@14110000 {
-			compatible = "samsung,exynos4210-pwm";
+			compatible = "tesla,fsd-pwm", "samsung,exynos4210-pwm";
 			reg = <0x0 0x14110000 0x0 0x100>;
 			samsung,pwm-outputs = <0>, <1>, <2>, <3>;
 			#pwm-cells = <3>;
@@ -657,7 +669,7 @@
 		};
 
 		hsi2c_0: i2c@14200000 {
-			compatible = "samsung,exynos7-hsi2c";
+			compatible = "tesla,fsd-hsi2c", "samsung,exynos7-hsi2c";
 			reg = <0x0 0x14200000 0x0 0x1000>;
 			interrupts = <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -670,7 +682,7 @@
 		};
 
 		hsi2c_1: i2c@14210000 {
-			compatible = "samsung,exynos7-hsi2c";
+			compatible = "tesla,fsd-hsi2c", "samsung,exynos7-hsi2c";
 			reg = <0x0 0x14210000 0x0 0x1000>;
 			interrupts = <GIC_SPI 149 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -683,7 +695,7 @@
 		};
 
 		hsi2c_2: i2c@14220000 {
-			compatible = "samsung,exynos7-hsi2c";
+			compatible = "tesla,fsd-hsi2c", "samsung,exynos7-hsi2c";
 			reg = <0x0 0x14220000 0x0 0x1000>;
 			interrupts = <GIC_SPI 150 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -696,7 +708,7 @@
 		};
 
 		hsi2c_3: i2c@14230000 {
-			compatible = "samsung,exynos7-hsi2c";
+			compatible = "tesla,fsd-hsi2c", "samsung,exynos7-hsi2c";
 			reg = <0x0 0x14230000 0x0 0x1000>;
 			interrupts = <GIC_SPI 151 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -709,7 +721,7 @@
 		};
 
 		hsi2c_4: i2c@14240000 {
-			compatible = "samsung,exynos7-hsi2c";
+			compatible = "tesla,fsd-hsi2c", "samsung,exynos7-hsi2c";
 			reg = <0x0 0x14240000 0x0 0x1000>;
 			interrupts = <GIC_SPI 152 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -722,7 +734,7 @@
 		};
 
 		hsi2c_5: i2c@14250000 {
-			compatible = "samsung,exynos7-hsi2c";
+			compatible = "tesla,fsd-hsi2c", "samsung,exynos7-hsi2c";
 			reg = <0x0 0x14250000 0x0 0x1000>;
 			interrupts = <GIC_SPI 153 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -735,7 +747,7 @@
 		};
 
 		hsi2c_6: i2c@14260000 {
-			compatible = "samsung,exynos7-hsi2c";
+			compatible = "tesla,fsd-hsi2c", "samsung,exynos7-hsi2c";
 			reg = <0x0 0x14260000 0x0 0x1000>;
 			interrupts = <GIC_SPI 154 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -748,7 +760,7 @@
 		};
 
 		hsi2c_7: i2c@14270000 {
-			compatible = "samsung,exynos7-hsi2c";
+			compatible = "tesla,fsd-hsi2c", "samsung,exynos7-hsi2c";
 			reg = <0x0 0x14270000 0x0 0x1000>;
 			interrupts = <GIC_SPI 155 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -956,6 +968,15 @@
 			clock-names = "fin_pll", "mct";
 		};
 
+		mfc: mfc@12880000 {
+			compatible = "tesla,fsd-mfc";
+			reg = <0x0 0x12880000 0x0 0x10000>;
+			interrupts = <GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>;
+			clock-names = "mfc";
+			clocks = <&clock_mfc MFC_MFC_IPCLKPORT_ACLK>;
+			memory-region = <&mfc_left>;
+		};
+
 		ufs: ufs@15120000 {
 			compatible = "tesla,fsd-ufs";
 			reg = <0x0 0x15120000 0x0 0x200>,  /* 0: HCI standard */
diff --git a/arch/arm64/boot/dts/ti/Makefile b/arch/arm64/boot/dts/ti/Makefile
index 77a347f9f47d..52c1dc910308 100644
--- a/arch/arm64/boot/dts/ti/Makefile
+++ b/arch/arm64/boot/dts/ti/Makefile
@@ -9,20 +9,20 @@
 # alphabetically.
 
 # Boards with AM62x SoC
-k3-am625-sk-hdmi-audio-dtbs := k3-am625-sk.dtb k3-am62x-sk-hdmi-audio.dtbo
-k3-am62-lp-sk-hdmi-audio-dtbs := k3-am62-lp-sk.dtb k3-am62x-sk-hdmi-audio.dtbo
 dtb-$(CONFIG_ARCH_K3) += k3-am625-beagleplay.dtb
+dtb-$(CONFIG_ARCH_K3) += k3-am625-beagleplay-csi2-ov5640.dtbo
+dtb-$(CONFIG_ARCH_K3) += k3-am625-beagleplay-csi2-tevi-ov5640.dtbo
 dtb-$(CONFIG_ARCH_K3) += k3-am625-phyboard-lyra-rdk.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am625-sk.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am625-verdin-nonwifi-dahlia.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am625-verdin-nonwifi-dev.dtb
+dtb-$(CONFIG_ARCH_K3) += k3-am625-verdin-nonwifi-mallow.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am625-verdin-nonwifi-yavia.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am625-verdin-wifi-dahlia.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am625-verdin-wifi-dev.dtb
+dtb-$(CONFIG_ARCH_K3) += k3-am625-verdin-wifi-mallow.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am625-verdin-wifi-yavia.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am62-lp-sk.dtb
-dtb-$(CONFIG_ARCH_K3) += k3-am625-sk-hdmi-audio.dtb
-dtb-$(CONFIG_ARCH_K3) += k3-am62-lp-sk-hdmi-audio.dtb
 
 # Boards with AM62Ax SoC
 dtb-$(CONFIG_ARCH_K3) += k3-am62a7-sk.dtb
@@ -30,19 +30,19 @@ dtb-$(CONFIG_ARCH_K3) += k3-am62a7-sk.dtb
 # Boards with AM62Px SoC
 dtb-$(CONFIG_ARCH_K3) += k3-am62p5-sk.dtb
 
+# Common overlays for SK-AM62* family of boards
+dtb-$(CONFIG_ARCH_K3) += k3-am62x-sk-csi2-ov5640.dtbo
+dtb-$(CONFIG_ARCH_K3) += k3-am62x-sk-csi2-tevi-ov5640.dtbo
+dtb-$(CONFIG_ARCH_K3) += k3-am62x-sk-csi2-imx219.dtbo
+dtb-$(CONFIG_ARCH_K3) += k3-am62x-sk-hdmi-audio.dtbo
+
 # Boards with AM64x SoC
 dtb-$(CONFIG_ARCH_K3) += k3-am642-evm.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am642-phyboard-electra-rdk.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am642-sk.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am642-tqma64xxl-mbax4xxl.dtb
-
-k3-am642-tqma64xxl-mbax4xxl-sdcard-dtbs := \
-	k3-am642-tqma64xxl-mbax4xxl.dtb k3-am64-tqma64xxl-mbax4xxl-sdcard.dtbo
-k3-am642-tqma64xxl-mbax4xxl-wlan-dtbs := \
-	k3-am642-tqma64xxl-mbax4xxl.dtb k3-am64-tqma64xxl-mbax4xxl-wlan.dtbo
-
-dtb-$(CONFIG_ARCH_K3) += k3-am642-tqma64xxl-mbax4xxl-sdcard.dtb
-dtb-$(CONFIG_ARCH_K3) += k3-am642-tqma64xxl-mbax4xxl-wlan.dtb
+dtb-$(CONFIG_ARCH_K3) += k3-am64-tqma64xxl-mbax4xxl-sdcard.dtbo
+dtb-$(CONFIG_ARCH_K3) += k3-am64-tqma64xxl-mbax4xxl-wlan.dtbo
 
 # Boards with AM65x SoC
 k3-am654-gp-evm-dtbs := k3-am654-base-board.dtb k3-am654-base-board-rocktech-rk101-panel.dtbo
@@ -67,6 +67,7 @@ k3-j721e-evm-dtbs := k3-j721e-common-proc-board.dtb k3-j721e-evm-quad-port-eth-e
 dtb-$(CONFIG_ARCH_K3) += k3-j721e-beagleboneai64.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-j721e-evm.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-j721e-evm-gesi-exp-board.dtbo
+dtb-$(CONFIG_ARCH_K3) += k3-j721e-evm-pcie0-ep.dtbo
 dtb-$(CONFIG_ARCH_K3) += k3-j721e-sk.dtb
 
 # Boards with J721s2 SoC
@@ -75,14 +76,59 @@ dtb-$(CONFIG_ARCH_K3) += k3-j721s2-common-proc-board.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-j721s2-evm-gesi-exp-board.dtbo
 k3-j721s2-evm-dtbs := k3-j721s2-common-proc-board.dtb k3-j721s2-evm-gesi-exp-board.dtbo
 dtb-$(CONFIG_ARCH_K3) += k3-j721s2-evm.dtb
+dtb-$(CONFIG_ARCH_K3) += k3-j721s2-evm-pcie1-ep.dtbo
 
 # Boards with J784s4 SoC
 dtb-$(CONFIG_ARCH_K3) += k3-am69-sk.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-j784s4-evm.dtb
 
+# Build time test only, enabled by CONFIG_OF_ALL_DTBS
+k3-am625-beagleplay-csi2-ov5640-dtbs := k3-am625-beagleplay.dtb \
+	k3-am625-beagleplay-csi2-ov5640.dtbo
+k3-am625-beagleplay-csi2-tevi-ov5640-dtbs := k3-am625-beagleplay.dtb \
+	k3-am625-beagleplay-csi2-tevi-ov5640.dtbo
+k3-am625-sk-csi2-imx219-dtbs := k3-am625-sk.dtb \
+	k3-am62x-sk-csi2-imx219.dtbo
+k3-am625-sk-csi2-ov5640-dtbs := k3-am625-sk.dtb \
+	k3-am62x-sk-csi2-ov5640.dtbo
+k3-am625-sk-csi2-tevi-ov5640-dtbs := k3-am625-sk.dtb \
+	k3-am62x-sk-csi2-tevi-ov5640.dtbo
+k3-am625-sk-hdmi-audio-dtbs := k3-am625-sk.dtb k3-am62x-sk-hdmi-audio.dtbo
+k3-am62-lp-sk-hdmi-audio-dtbs := k3-am62-lp-sk.dtb k3-am62x-sk-hdmi-audio.dtbo
+k3-am62a7-sk-csi2-imx219-dtbs := k3-am62a7-sk.dtb \
+	k3-am62x-sk-csi2-imx219.dtbo
+k3-am62a7-sk-csi2-ov5640-dtbs := k3-am62a7-sk.dtb \
+	k3-am62x-sk-csi2-ov5640.dtbo
+k3-am62a7-sk-csi2-tevi-ov5640-dtbs := k3-am62a7-sk.dtb \
+	k3-am62x-sk-csi2-tevi-ov5640.dtbo
+k3-am642-tqma64xxl-mbax4xxl-sdcard-dtbs := \
+	k3-am642-tqma64xxl-mbax4xxl.dtb k3-am64-tqma64xxl-mbax4xxl-sdcard.dtbo
+k3-am642-tqma64xxl-mbax4xxl-wlan-dtbs := \
+	k3-am642-tqma64xxl-mbax4xxl.dtb k3-am64-tqma64xxl-mbax4xxl-wlan.dtbo
+k3-j721e-evm-pcie0-ep-dtbs := k3-j721e-common-proc-board.dtb \
+	k3-j721e-evm-pcie0-ep.dtbo
+k3-j721s2-evm-pcie1-ep-dtbs := k3-j721s2-common-proc-board.dtb \
+	k3-j721s2-evm-pcie1-ep.dtbo
+dtb- += k3-am625-beagleplay-csi2-ov5640.dtb \
+	k3-am625-beagleplay-csi2-tevi-ov5640.dtb \
+	k3-am625-sk-csi2-imx219.dtb \
+	k3-am625-sk-csi2-ov5640.dtb \
+	k3-am625-sk-csi2-tevi-ov5640.dtb \
+	k3-am625-sk-hdmi-audio.dtb \
+	k3-am62-lp-sk-hdmi-audio.dtb \
+	k3-am62a7-sk-csi2-imx219.dtb \
+	k3-am62a7-sk-csi2-ov5640.dtb \
+	k3-am642-tqma64xxl-mbax4xxl-sdcard.dtb \
+	k3-am642-tqma64xxl-mbax4xxl-wlan.dtb \
+	k3-j721e-evm-pcie0-ep.dtb \
+	k3-j721s2-evm-pcie1-ep.dtb
+
 # Enable support for device-tree overlays
+DTC_FLAGS_k3-am625-beagleplay += -@
 DTC_FLAGS_k3-am625-sk += -@
 DTC_FLAGS_k3-am62-lp-sk += -@
+DTC_FLAGS_k3-am62a7-sk += -@
+DTC_FLAGS_k3-am642-tqma64xxl-mbax4xxl += -@
 DTC_FLAGS_k3-am6548-iot2050-advanced-m2 += -@
 DTC_FLAGS_k3-j721e-common-proc-board += -@
 DTC_FLAGS_k3-j721s2-common-proc-board += -@
diff --git a/arch/arm64/boot/dts/ti/k3-am62-main.dtsi b/arch/arm64/boot/dts/ti/k3-am62-main.dtsi
index e5c64c86d1d5..464b7565d085 100644
--- a/arch/arm64/boot/dts/ti/k3-am62-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62-main.dtsi
@@ -121,8 +121,13 @@
 			      <0x00 0x4c000000 0x00 0x20000>,
 			      <0x00 0x4a820000 0x00 0x20000>,
 			      <0x00 0x4aa40000 0x00 0x20000>,
-			      <0x00 0x4bc00000 0x00 0x100000>;
-			reg-names = "gcfg", "bchanrt", "rchanrt", "tchanrt", "ringrt";
+			      <0x00 0x4bc00000 0x00 0x100000>,
+			      <0x00 0x48600000 0x00 0x8000>,
+			      <0x00 0x484a4000 0x00 0x2000>,
+			      <0x00 0x484c2000 0x00 0x2000>,
+			      <0x00 0x48420000 0x00 0x2000>;
+			reg-names = "gcfg", "bchanrt", "rchanrt", "tchanrt", "ringrt",
+				    "ring", "tchan", "rchan", "bchan";
 			msi-parent = <&inta_main_dmss>;
 			#dma-cells = <3>;
 
@@ -138,8 +143,13 @@
 			reg = <0x00 0x485c0000 0x00 0x100>,
 			      <0x00 0x4a800000 0x00 0x20000>,
 			      <0x00 0x4aa00000 0x00 0x40000>,
-			      <0x00 0x4b800000 0x00 0x400000>;
-			reg-names = "gcfg", "rchanrt", "tchanrt", "ringrt";
+			      <0x00 0x4b800000 0x00 0x400000>,
+			      <0x00 0x485e0000 0x00 0x10000>,
+			      <0x00 0x484a0000 0x00 0x2000>,
+			      <0x00 0x484c0000 0x00 0x2000>,
+			      <0x00 0x48430000 0x00 0x1000>;
+			reg-names = "gcfg", "rchanrt", "tchanrt", "ringrt",
+				    "ring", "tchan", "rchan", "rflow";
 			msi-parent = <&inta_main_dmss>;
 			#dma-cells = <2>;
 
@@ -502,6 +512,9 @@
 	main_gpio0: gpio@600000 {
 		compatible = "ti,am64-gpio", "ti,keystone-gpio";
 		reg = <0x0 0x00600000 0x0 0x100>;
+		gpio-ranges = <&main_pmx0  0  0 32>,
+			      <&main_pmx0 32 33 38>,
+			      <&main_pmx0 70 72 22>;
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&main_gpio_intr>;
@@ -520,6 +533,10 @@
 		compatible = "ti,am64-gpio", "ti,keystone-gpio";
 		reg = <0x0 0x00601000 0x0 0x100>;
 		gpio-controller;
+		gpio-ranges = <&main_pmx0  0  94 41>,
+			      <&main_pmx0 41 136  6>,
+			      <&main_pmx0 47 143  3>,
+			      <&main_pmx0 50 149  2>;
 		#gpio-cells = <2>;
 		interrupt-parent = <&main_gpio_intr>;
 		interrupts = <180>, <181>, <182>,
@@ -675,6 +692,15 @@
 		};
 	};
 
+	gpu: gpu@fd00000 {
+		compatible = "ti,am62-gpu", "img,img-axe";
+		reg = <0x00 0x0fd00000 0x00 0x20000>;
+		clocks = <&k3_clks 187 0>;
+		clock-names = "core";
+		interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
+		power-domains = <&k3_pds 187 TI_SCI_PD_EXCLUSIVE>;
+	};
+
 	cpsw3g: ethernet@8000000 {
 		compatible = "ti,am642-cpsw-nuss";
 		#address-cells = <2>;
@@ -965,4 +991,66 @@
 		power-domains = <&k3_pds 192 TI_SCI_PD_EXCLUSIVE>;
 		status = "disabled";
 	};
+
+	ti_csi2rx0: ticsi2rx@30102000 {
+		compatible = "ti,j721e-csi2rx-shim";
+		dmas = <&main_bcdma 0 0x4700 0>;
+		dma-names = "rx0";
+		reg = <0x00 0x30102000 0x00 0x1000>;
+		power-domains = <&k3_pds 182 TI_SCI_PD_EXCLUSIVE>;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+		status = "disabled";
+
+		cdns_csi2rx0: csi-bridge@30101000 {
+			compatible = "ti,j721e-csi2rx", "cdns,csi2rx";
+			reg = <0x00 0x30101000 0x00 0x1000>;
+			clocks = <&k3_clks 182 0>, <&k3_clks 182 3>, <&k3_clks 182 0>,
+				<&k3_clks 182 0>, <&k3_clks 182 4>, <&k3_clks 182 4>;
+			clock-names = "sys_clk", "p_clk", "pixel_if0_clk",
+				"pixel_if1_clk", "pixel_if2_clk", "pixel_if3_clk";
+			phys = <&dphy0>;
+			phy-names = "dphy";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				csi0_port0: port@0 {
+					reg = <0>;
+					status = "disabled";
+				};
+
+				csi0_port1: port@1 {
+					reg = <1>;
+					status = "disabled";
+				};
+
+				csi0_port2: port@2 {
+					reg = <2>;
+					status = "disabled";
+				};
+
+				csi0_port3: port@3 {
+					reg = <3>;
+					status = "disabled";
+				};
+
+				csi0_port4: port@4 {
+					reg = <4>;
+					status = "disabled";
+				};
+			};
+		};
+	};
+
+	dphy0: phy@30110000 {
+		compatible = "cdns,dphy-rx";
+		reg = <0x00 0x30110000 0x00 0x1100>;
+		#phy-cells = <0>;
+		power-domains = <&k3_pds 185 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+	};
+
 };
diff --git a/arch/arm64/boot/dts/ti/k3-am62-verdin-dahlia.dtsi b/arch/arm64/boot/dts/ti/k3-am62-verdin-dahlia.dtsi
index 013357d17d48..bf6d27e70bc4 100644
--- a/arch/arm64/boot/dts/ti/k3-am62-verdin-dahlia.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62-verdin-dahlia.dtsi
@@ -214,6 +214,5 @@
 
 /* Verdin UART_2 */
 &wkup_uart0 {
-	/* FIXME: WKUP UART0 is used by DM firmware */
-	status = "reserved";
+	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/ti/k3-am62-verdin-dev.dtsi b/arch/arm64/boot/dts/ti/k3-am62-verdin-dev.dtsi
index 6701cb8974bb..680071688dcb 100644
--- a/arch/arm64/boot/dts/ti/k3-am62-verdin-dev.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62-verdin-dev.dtsi
@@ -235,6 +235,5 @@
 
 /* Verdin UART_2 */
 &wkup_uart0 {
-	/* FIXME: WKUP UART0 is used by DM firmware */
-	status = "reserved";
+	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/ti/k3-am62-verdin-mallow.dtsi b/arch/arm64/boot/dts/ti/k3-am62-verdin-mallow.dtsi
new file mode 100644
index 000000000000..17b93534f658
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am62-verdin-mallow.dtsi
@@ -0,0 +1,188 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright 2023 Toradex
+ *
+ * Common dtsi for Verdin AM62 SoM on Mallow carrier board
+ *
+ * https://www.toradex.com/computer-on-modules/verdin-arm-family/ti-am62
+ * https://www.toradex.com/products/carrier-board/mallow-carrier-board
+ */
+
+#include <dt-bindings/leds/common.h>
+
+/ {
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_qspi1_clk_gpio>,
+			    <&pinctrl_qspi1_cs_gpio>,
+			    <&pinctrl_qspi1_io0_gpio>,
+			    <&pinctrl_qspi1_io1_gpio>;
+
+		/* SODIMM 52 - USER_LED_1_RED */
+		led-0 {
+			color = <LED_COLOR_ID_RED>;
+			function = LED_FUNCTION_DEBUG;
+			function-enumerator = <1>;
+			gpios = <&main_gpio0 0 GPIO_ACTIVE_HIGH>;
+		};
+
+		/* SODIMM 54 - USER_LED_1_GREEN */
+		led-1 {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_DEBUG;
+			function-enumerator = <1>;
+			gpios = <&main_gpio0 11 GPIO_ACTIVE_HIGH>;
+		};
+
+		/* SODIMM 56 - USER_LED_2_RED */
+		led-2 {
+			color = <LED_COLOR_ID_RED>;
+			function = LED_FUNCTION_DEBUG;
+			function-enumerator = <2>;
+			gpios = <&main_gpio0 3 GPIO_ACTIVE_HIGH>;
+		};
+
+		/* SODIMM 58 - USER_LED_2_GREEN */
+		led-3 {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_DEBUG;
+			function-enumerator = <2>;
+			gpios = <&main_gpio0 4 GPIO_ACTIVE_HIGH>;
+		};
+	};
+};
+
+/* Verdin ETH */
+&cpsw3g {
+	status = "okay";
+};
+
+/* Verdin MDIO */
+&cpsw3g_mdio {
+	status = "okay";
+};
+
+/* Verdin ETH_1*/
+&cpsw_port1 {
+	status = "okay";
+};
+
+/* Verdin PWM_1 and PWM_2*/
+&epwm0 {
+	status = "okay";
+};
+
+/* Verdin PWM_3 DSI */
+&epwm1 {
+	status = "okay";
+};
+
+&main_gpio0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_ctrl_sleep_moci>,
+		    <&pinctrl_gpio_1>,
+		    <&pinctrl_gpio_2>,
+		    <&pinctrl_gpio_3>,
+		    <&pinctrl_gpio_4>;
+};
+
+/* Verdin I2C_1 */
+&main_i2c1 {
+	status = "okay";
+
+	/* Temperature sensor */
+	sensor@4f {
+		compatible = "ti,tmp1075";
+		reg = <0x4f>;
+	};
+
+	/* EEPROM */
+	eeprom@57 {
+		compatible = "st,24c02", "atmel,24c02";
+		reg = <0x57>;
+		pagesize = <16>;
+	};
+};
+
+/* Verdin I2C_2 DSI */
+&main_i2c2 {
+	status = "okay";
+};
+
+/* Verdin I2C_4 CSI */
+&main_i2c3 {
+	status = "okay";
+};
+
+/* Verdin CAN_1 */
+&main_mcan0 {
+	status = "okay";
+};
+
+/* Verdin SPI_1 */
+&main_spi1 {
+	pinctrl-0 = <&pinctrl_spi1>,
+		    <&pinctrl_spi1_cs0>,
+		    <&pinctrl_qspi1_cs2_gpio>;
+	cs-gpios = <0>, <&main_gpio0 12 GPIO_ACTIVE_LOW>;
+	status = "okay";
+};
+
+/* Verdin UART_3 */
+&main_uart0 {
+	status = "okay";
+};
+
+/* Verdin UART_1 */
+&main_uart1 {
+	status = "okay";
+};
+
+/* Verdin I2C_3_HDMI */
+&mcu_i2c0 {
+	status = "okay";
+};
+
+/* Verdin CAN_2 */
+&mcu_mcan0 {
+	status = "okay";
+};
+
+/* Verdin UART_4 */
+&mcu_uart0 {
+	status = "okay";
+};
+
+/* Verdin SD_1 */
+&sdhci1 {
+	status = "okay";
+};
+
+/* Verdin USB_1 */
+&usbss0 {
+	status = "okay";
+};
+
+&usb0 {
+	status = "okay";
+};
+
+/* Verdin USB_2 */
+&usbss1 {
+	status = "okay";
+};
+
+&usb1 {
+	status = "okay";
+};
+
+/* Verdin CTRL_WAKE1_MICO# */
+&verdin_gpio_keys {
+	status = "okay";
+};
+
+/* Verdin UART_2 */
+&wkup_uart0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am62-verdin-yavia.dtsi b/arch/arm64/boot/dts/ti/k3-am62-verdin-yavia.dtsi
index c685df7deaee..997dfafd27eb 100644
--- a/arch/arm64/boot/dts/ti/k3-am62-verdin-yavia.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62-verdin-yavia.dtsi
@@ -207,6 +207,5 @@
 
 /* Verdin UART_2 */
 &wkup_uart0 {
-	/* FIXME: WKUP UART0 is used by DM firmware */
-	status = "reserved";
+	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi b/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi
index 5db52f237253..6a06724b6d16 100644
--- a/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi
@@ -233,6 +233,13 @@
 		>;
 	};
 
+	/* Verdin SPI_1 CS as GPIO */
+	pinctrl_qspi1_io4_gpio: main-gpio0-7-default-pins {
+		pinctrl-single,pins = <
+			AM62X_IOPAD(0x001c, PIN_INPUT, 7) /* (J23) OSPI0_D4.GPIO0_7 */ /* SODIMM 202 */
+		>;
+	};
+
 	/* Verdin QSPI_1_CS# as GPIO (conflict with Verdin QSPI_1 interface) */
 	pinctrl_qspi1_cs_gpio: main-gpio0-11-default-pins {
 		pinctrl-single,pins = <
@@ -599,12 +606,18 @@
 	pinctrl_spi1: main-spi1-default-pins {
 		pinctrl-single,pins = <
 			AM62X_IOPAD(0x0020, PIN_INPUT, 1) /* (J25) OSPI0_D5.SPI1_CLK */ /* SODIMM 196 */
-			AM62X_IOPAD(0x001c, PIN_INPUT, 1) /* (J23) OSPI0_D4.SPI1_CS0 */ /* SODIMM 202 */
 			AM62X_IOPAD(0x0024, PIN_INPUT, 1) /* (H25) OSPI0_D6.SPI1_D0  */ /* SODIMM 200 */
 			AM62X_IOPAD(0x0028, PIN_INPUT, 1) /* (J22) OSPI0_D7.SPI1_D1  */ /* SODIMM 198 */
 		>;
 	};
 
+	/* Verdin SPI_1 CS */
+	pinctrl_spi1_cs0: main-spi1-cs0-default-pins {
+		pinctrl-single,pins = <
+			AM62X_IOPAD(0x001c, PIN_INPUT, 1) /* (J23) OSPI0_D4.SPI1_CS0 */ /* SODIMM 202 */
+		>;
+	};
+
 	/* ETH_25MHz_CLK */
 	pinctrl_eth_clock: main-system-clkout0-default-pins {
 		pinctrl-single,pins = <
@@ -1278,7 +1291,7 @@
 /* Verdin SPI_1 */
 &main_spi1 {
 	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_spi1>;
+	pinctrl-0 = <&pinctrl_spi1>, <&pinctrl_spi1_cs0>;
 	ti,pindir-d0-out-d1-in;
 	status = "disabled";
 };
diff --git a/arch/arm64/boot/dts/ti/k3-am625-beagleplay-csi2-ov5640.dtso b/arch/arm64/boot/dts/ti/k3-am625-beagleplay-csi2-ov5640.dtso
new file mode 100644
index 000000000000..5e80ca7033ba
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am625-beagleplay-csi2-ov5640.dtso
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ALINX AN5641 & Digilent PCam 5C - OV5640 camera module
+ * Copyright (C) 2022-2023 Texas Instruments Incorporated - https://www.ti.com/
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/gpio/gpio.h>
+
+&{/} {
+	clk_ov5640_fixed: ov5640-xclk {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <12000000>;
+	};
+};
+
+&main_gpio0 {
+	p11-hog {
+		/* P11 - CSI2_CAMERA_GPIO1 */
+		gpio-hog;
+		gpios = <11 GPIO_ACTIVE_HIGH>;
+		output-high;
+		line-name = "CSI2_CAMERA_GPIO1";
+	};
+};
+
+&wkup_i2c0 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+
+	ov5640: camera@3c {
+		compatible = "ovti,ov5640";
+		reg = <0x3c>;
+
+		clocks = <&clk_ov5640_fixed>;
+		clock-names = "xclk";
+
+		port {
+			csi2_cam0: endpoint {
+				remote-endpoint = <&csi2rx0_in_sensor>;
+				clock-lanes = <0>;
+				data-lanes = <1 2>;
+			};
+		};
+	};
+};
+
+&cdns_csi2rx0 {
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		csi0_port0: port@0 {
+			reg = <0>;
+			status = "okay";
+
+			csi2rx0_in_sensor: endpoint {
+				remote-endpoint = <&csi2_cam0>;
+				bus-type = <4>; /* CSI2 DPHY. */
+				clock-lanes = <0>;
+				data-lanes = <1 2>;
+			};
+		};
+	};
+};
+
+&dphy0 {
+	status = "okay";
+};
+
+&ti_csi2rx0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am625-beagleplay-csi2-tevi-ov5640.dtso b/arch/arm64/boot/dts/ti/k3-am625-beagleplay-csi2-tevi-ov5640.dtso
new file mode 100644
index 000000000000..5e1cbbc27c8f
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am625-beagleplay-csi2-tevi-ov5640.dtso
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Technexion TEVI-OV5640-*-RPI - OV5640 camera module
+ * Copyright (C) 2022-2023 Texas Instruments Incorporated - https://www.ti.com/
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/gpio/gpio.h>
+
+&{/} {
+	clk_ov5640_fixed: ov5640-xclk {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <24000000>;
+	};
+};
+
+&main_gpio0 {
+	p11-hog {
+		/* P11 - CSI2_CAMERA_GPIO1 */
+		gpio-hog;
+		gpios = <11 GPIO_ACTIVE_HIGH>;
+		output-high;
+		line-name = "CSI2_CAMERA_GPIO1";
+	};
+};
+
+&wkup_i2c0 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+
+	ov5640: camera@3c {
+		compatible = "ovti,ov5640";
+		reg = <0x3c>;
+
+		clocks = <&clk_ov5640_fixed>;
+		clock-names = "xclk";
+
+		port {
+			csi2_cam0: endpoint {
+				remote-endpoint = <&csi2rx0_in_sensor>;
+				clock-lanes = <0>;
+				data-lanes = <1 2>;
+			};
+		};
+	};
+};
+
+&cdns_csi2rx0 {
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		csi0_port0: port@0 {
+			reg = <0>;
+			status = "okay";
+
+			csi2rx0_in_sensor: endpoint {
+				remote-endpoint = <&csi2_cam0>;
+				bus-type = <4>; /* CSI2 DPHY. */
+				clock-lanes = <0>;
+				data-lanes = <1 2>;
+			};
+		};
+	};
+};
+
+&dphy0 {
+	status = "okay";
+};
+
+&ti_csi2rx0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts b/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts
index 9a6bd0a3c94f..eadbdd9ffe37 100644
--- a/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts
+++ b/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts
@@ -443,7 +443,7 @@
 		>;
 	};
 
-	console_pins_default: console-default-pins {
+	main_uart0_pins_default: main-uart0-default-pins {
 		bootph-all;
 		pinctrl-single,pins = <
 			AM62X_IOPAD(0x01c8, PIN_INPUT, 0) /* (D14) UART0_RXD */
@@ -877,7 +877,7 @@
 &main_uart0 {
 	bootph-all;
 	pinctrl-names = "default";
-	pinctrl-0 = <&console_pins_default>;
+	pinctrl-0 = <&main_uart0_pins_default>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/ti/k3-am625-phyboard-lyra-rdk.dts b/arch/arm64/boot/dts/ti/k3-am625-phyboard-lyra-rdk.dts
index a438baf542c2..4bc0134c987d 100644
--- a/arch/arm64/boot/dts/ti/k3-am625-phyboard-lyra-rdk.dts
+++ b/arch/arm64/boot/dts/ti/k3-am625-phyboard-lyra-rdk.dts
@@ -35,6 +35,18 @@
 		standby-gpios = <&gpio_exp 1 GPIO_ACTIVE_HIGH>;
 	};
 
+	hdmi0: connector-hdmi {
+		compatible = "hdmi-connector";
+		label = "hdmi";
+		type = "a";
+
+		port {
+			hdmi_connector_in: endpoint {
+				remote-endpoint = <&sii9022_out>;
+			};
+		};
+	};
+
 	keys {
 		compatible = "gpio-keys";
 		autorepeat;
@@ -93,6 +105,37 @@
 		>;
 	};
 
+	hdmi_int_pins_default: hdmi-int-default-pins {
+		pinctrl-single,pins = <
+			AM62X_IOPAD(0x040, PIN_INPUT, 7) /* (N23) GPMC0_AD1.GPIO0_16 */
+		>;
+	};
+
+	main_dss0_pins_default: main-dss0-default-pins {
+		pinctrl-single,pins = <
+			AM62X_IOPAD(0x0b8, PIN_OUTPUT, 0) /* (U22) VOUT0_DATA0 */
+			AM62X_IOPAD(0x0bc, PIN_OUTPUT, 0) /* (V24) VOUT0_DATA1 */
+			AM62X_IOPAD(0x0e0, PIN_OUTPUT, 0) /* (V20) VOUT0_DATA10 */
+			AM62X_IOPAD(0x0e4, PIN_OUTPUT, 0) /* (AA23) VOUT0_DATA11 */
+			AM62X_IOPAD(0x0e8, PIN_OUTPUT, 0) /* (AB25) VOUT0_DATA12 */
+			AM62X_IOPAD(0x0ec, PIN_OUTPUT, 0) /* (AA24) VOUT0_DATA13 */
+			AM62X_IOPAD(0x0f0, PIN_OUTPUT, 0) /* (Y22) VOUT0_DATA14 */
+			AM62X_IOPAD(0x0f4, PIN_OUTPUT, 0) /* (AA21) VOUT0_DATA15 */
+			AM62X_IOPAD(0x0c0, PIN_OUTPUT, 0) /* (W25) VOUT0_DATA2 */
+			AM62X_IOPAD(0x0c4, PIN_OUTPUT, 0) /* (W24) VOUT0_DATA3 */
+			AM62X_IOPAD(0x0c8, PIN_OUTPUT, 0) /* (Y25) VOUT0_DATA4 */
+			AM62X_IOPAD(0x0cc, PIN_OUTPUT, 0) /* (Y24) VOUT0_DATA5 */
+			AM62X_IOPAD(0x0d0, PIN_OUTPUT, 0) /* (Y23) VOUT0_DATA6 */
+			AM62X_IOPAD(0x0d4, PIN_OUTPUT, 0) /* (AA25) VOUT0_DATA7 */
+			AM62X_IOPAD(0x0d8, PIN_OUTPUT, 0) /* (V21) VOUT0_DATA8 */
+			AM62X_IOPAD(0x0dc, PIN_OUTPUT, 0) /* (W21) VOUT0_DATA9 */
+			AM62X_IOPAD(0x0fc, PIN_OUTPUT, 0) /* (Y20) VOUT0_DE */
+			AM62X_IOPAD(0x0f8, PIN_OUTPUT, 0) /* (AB24) VOUT0_HSYNC */
+			AM62X_IOPAD(0x104, PIN_OUTPUT, 0) /* (AC24) VOUT0_PCLK */
+			AM62X_IOPAD(0x100, PIN_OUTPUT, 0) /* (AC25) VOUT0_VSYNC */
+		>;
+	};
+
 	main_i2c1_pins_default: main-i2c1-default-pins {
 		pinctrl-single,pins = <
 			AM62X_IOPAD(0x1e8, PIN_INPUT_PULLUP, 0) /* (B17) I2C1_SCL */
@@ -184,10 +227,30 @@
 	};
 };
 
+&dss {
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_dss0_pins_default>;
+	status = "okay";
+};
+
+&dss_ports {
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	/* VP2: DPI/HDMI Output */
+	port@1 {
+		reg = <1>;
+
+		dpi1_out: endpoint {
+			remote-endpoint = <&sii9022_in>;
+		};
+	};
+};
+
 &main_i2c1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_i2c1_pins_default>;
-	clock-frequency = <400000>;
+	clock-frequency = <100000>;
 	status = "okay";
 
 	gpio_exp: gpio-expander@21 {
@@ -201,12 +264,43 @@
 		gpio-controller;
 		interrupt-controller;
 		#interrupt-cells = <2>;
-		gpio-line-names = "GPIO0_HDMI_RST", "GPIO1_CAN0_nEN",
+		gpio-line-names = "", "GPIO1_CAN0_nEN",
 				  "GPIO2_LED2", "GPIO3_LVDS_GPIO",
 				  "GPIO4_BUT2", "GPIO5_LVDS_BKLT_EN",
 				  "GPIO6_ETH1_USER_RESET", "GPIO7_AUDIO_USER_RESET";
 	};
 
+	sii9022: bridge-hdmi@39 {
+		compatible = "sil,sii9022";
+		reg = <0x39>;
+
+		interrupt-parent = <&main_gpio0>;
+		interrupts = <16 IRQ_TYPE_EDGE_FALLING>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&hdmi_int_pins_default>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				sii9022_in: endpoint {
+					remote-endpoint = <&dpi1_out>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				sii9022_out: endpoint {
+					remote-endpoint = <&hdmi_connector_in>;
+				};
+			};
+		};
+	};
+
 	eeprom@51 {
 		compatible = "atmel,24c02";
 		pagesize = <16>;
diff --git a/arch/arm64/boot/dts/ti/k3-am625-verdin-nonwifi-mallow.dts b/arch/arm64/boot/dts/ti/k3-am625-verdin-nonwifi-mallow.dts
new file mode 100644
index 000000000000..9cae12106e0e
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am625-verdin-nonwifi-mallow.dts
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright 2023 Toradex
+ *
+ * https://www.toradex.com/computer-on-modules/verdin-arm-family/ti-am62
+ * https://www.toradex.com/products/carrier-board/mallow-carrier-board
+ */
+
+/dts-v1/;
+
+#include "k3-am625.dtsi"
+#include "k3-am62-verdin.dtsi"
+#include "k3-am62-verdin-nonwifi.dtsi"
+#include "k3-am62-verdin-mallow.dtsi"
+
+/ {
+	model = "Toradex Verdin AM62 on Mallow Board";
+	compatible = "toradex,verdin-am62-nonwifi-mallow",
+		     "toradex,verdin-am62-nonwifi",
+		     "toradex,verdin-am62",
+		     "ti,am625";
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am625-verdin-wifi-mallow.dts b/arch/arm64/boot/dts/ti/k3-am625-verdin-wifi-mallow.dts
new file mode 100644
index 000000000000..81d834b22649
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am625-verdin-wifi-mallow.dts
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright 2023 Toradex
+ *
+ * https://www.toradex.com/computer-on-modules/verdin-arm-family/ti-am62
+ * https://www.toradex.com/products/carrier-board/mallow-carrier-board
+ */
+
+/dts-v1/;
+
+#include "k3-am625.dtsi"
+#include "k3-am62-verdin.dtsi"
+#include "k3-am62-verdin-wifi.dtsi"
+#include "k3-am62-verdin-mallow.dtsi"
+
+/ {
+	model = "Toradex Verdin AM62 WB on Mallow Board";
+	compatible = "toradex,verdin-am62-wifi-mallow",
+		     "toradex,verdin-am62-wifi",
+		     "toradex,verdin-am62",
+		     "ti,am625";
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am62a-main.dtsi b/arch/arm64/boot/dts/ti/k3-am62a-main.dtsi
index 4ae7fdc5221b..f0b8c9ab1459 100644
--- a/arch/arm64/boot/dts/ti/k3-am62a-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62a-main.dtsi
@@ -101,8 +101,13 @@
 			      <0x00 0x4c000000 0x00 0x20000>,
 			      <0x00 0x4a820000 0x00 0x20000>,
 			      <0x00 0x4aa40000 0x00 0x20000>,
-			      <0x00 0x4bc00000 0x00 0x100000>;
-			reg-names = "gcfg", "bchanrt", "rchanrt", "tchanrt", "ringrt";
+			      <0x00 0x4bc00000 0x00 0x100000>,
+			      <0x00 0x48600000 0x00 0x8000>,
+			      <0x00 0x484a4000 0x00 0x2000>,
+			      <0x00 0x484c2000 0x00 0x2000>,
+			      <0x00 0x48420000 0x00 0x2000>;
+			reg-names = "gcfg", "bchanrt", "rchanrt", "tchanrt", "ringrt",
+				    "ring", "tchan", "rchan", "bchan";
 			msi-parent = <&inta_main_dmss>;
 			#dma-cells = <3>;
 			ti,sci = <&dmsc>;
@@ -117,8 +122,13 @@
 			reg = <0x00 0x485c0000 0x00 0x100>,
 			      <0x00 0x4a800000 0x00 0x20000>,
 			      <0x00 0x4aa00000 0x00 0x40000>,
-			      <0x00 0x4b800000 0x00 0x400000>;
-			reg-names = "gcfg", "rchanrt", "tchanrt", "ringrt";
+			      <0x00 0x4b800000 0x00 0x400000>,
+			      <0x00 0x485e0000 0x00 0x10000>,
+			      <0x00 0x484a0000 0x00 0x2000>,
+			      <0x00 0x484c0000 0x00 0x2000>,
+			      <0x00 0x48430000 0x00 0x1000>;
+			reg-names = "gcfg", "rchanrt", "tchanrt", "ringrt",
+				    "ring", "tchan", "rchan", "rflow";
 			msi-parent = <&inta_main_dmss>;
 			#dma-cells = <2>;
 			ti,sci = <&dmsc>;
@@ -144,6 +154,44 @@
 		};
 	};
 
+	dmss_csi: bus@4e000000 {
+		compatible = "simple-bus";
+		#address-cells = <2>;
+		#size-cells = <2>;
+		dma-ranges;
+		ranges = <0x00 0x4e000000 0x00 0x4e000000 0x00 0x300000>;
+
+		ti,sci-dev-id = <198>;
+
+		inta_main_dmss_csi: interrupt-controller@4e0a0000 {
+			compatible = "ti,sci-inta";
+			reg = <0x00 0x4e0a0000 0x00 0x8000>;
+			#interrupt-cells = <0>;
+			interrupt-controller;
+			interrupt-parent = <&gic500>;
+			msi-controller;
+			ti,sci = <&dmsc>;
+			ti,sci-dev-id = <200>;
+			ti,interrupt-ranges = <0 237 8>;
+			ti,unmapped-event-sources = <&main_bcdma_csi>;
+			power-domains = <&k3_pds 182 TI_SCI_PD_EXCLUSIVE>;
+		};
+
+		main_bcdma_csi: dma-controller@4e230000 {
+			compatible = "ti,am62a-dmss-bcdma-csirx";
+			reg = <0x00 0x4e230000 0x00 0x100>,
+			      <0x00 0x4e180000 0x00 0x8000>,
+			      <0x00 0x4e100000 0x00 0x10000>;
+			reg-names = "gcfg", "rchanrt", "ringrt";
+			msi-parent = <&inta_main_dmss_csi>;
+			#dma-cells = <3>;
+			ti,sci = <&dmsc>;
+			ti,sci-dev-id = <199>;
+			ti,sci-rm-range-rchan = <0x21>;
+			power-domains = <&k3_pds 182 TI_SCI_PD_EXCLUSIVE>;
+		};
+	};
+
 	dmsc: system-controller@44043000 {
 		compatible = "ti,k2g-sci";
 		reg = <0x00 0x44043000 0x00 0xfe0>;
@@ -462,7 +510,7 @@
 			     <193>, <194>, <195>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
-		ti,ngpio = <87>;
+		ti,ngpio = <92>;
 		ti,davinci-gpio-unbanked = <0>;
 		power-domains = <&k3_pds 77 TI_SCI_PD_EXCLUSIVE>;
 		clocks = <&k3_clks 77 0>;
@@ -480,7 +528,7 @@
 			     <183>, <184>, <185>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
-		ti,ngpio = <88>;
+		ti,ngpio = <52>;
 		ti,davinci-gpio-unbanked = <0>;
 		power-domains = <&k3_pds 78 TI_SCI_PD_EXCLUSIVE>;
 		clocks = <&k3_clks 78 0>;
@@ -876,4 +924,65 @@
 		power-domains = <&k3_pds 192 TI_SCI_PD_EXCLUSIVE>;
 		status = "disabled";
 	};
+
+	ti_csi2rx0: ticsi2rx@30102000 {
+		compatible = "ti,j721e-csi2rx-shim";
+		dmas = <&main_bcdma_csi 0 0x5000 0>;
+		dma-names = "rx0";
+		reg = <0x00 0x30102000 0x00 0x1000>;
+		power-domains = <&k3_pds 182 TI_SCI_PD_EXCLUSIVE>;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+		status = "disabled";
+
+		cdns_csi2rx0: csi-bridge@30101000 {
+			compatible = "ti,j721e-csi2rx", "cdns,csi2rx";
+			reg = <0x00 0x30101000 0x00 0x1000>;
+			clocks = <&k3_clks 182 0>, <&k3_clks 182 3>, <&k3_clks 182 0>,
+				<&k3_clks 182 0>, <&k3_clks 182 4>, <&k3_clks 182 4>;
+			clock-names = "sys_clk", "p_clk", "pixel_if0_clk",
+				"pixel_if1_clk", "pixel_if2_clk", "pixel_if3_clk";
+			phys = <&dphy0>;
+			phy-names = "dphy";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				csi0_port0: port@0 {
+					reg = <0>;
+					status = "disabled";
+				};
+
+				csi0_port1: port@1 {
+					reg = <1>;
+					status = "disabled";
+				};
+
+				csi0_port2: port@2 {
+					reg = <2>;
+					status = "disabled";
+				};
+
+				csi0_port3: port@3 {
+					reg = <3>;
+					status = "disabled";
+				};
+
+				csi0_port4: port@4 {
+					reg = <4>;
+					status = "disabled";
+				};
+			};
+		};
+	};
+
+	dphy0: phy@30110000 {
+		compatible = "cdns,dphy-rx";
+		reg = <0x00 0x30110000 0x00 0x1100>;
+		#phy-cells = <0>;
+		power-domains = <&k3_pds 185 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+	};
 };
diff --git a/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts b/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts
index 8f64ac2c7568..7b7142586295 100644
--- a/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts
+++ b/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts
@@ -274,6 +274,12 @@
 			AM62AX_IOPAD(0x084, PIN_INPUT, 2) /* (L18) GPMC0_ADVn_ALE.MCASP1_AXR2 */
 		>;
 	};
+
+	main_gpio1_ioexp_intr_pins_default: main-gpio1-ioexp-intr-default-pins {
+		pinctrl-single,pins = <
+			AM62AX_IOPAD(0x01d4, PIN_INPUT, 7) /* (C15) UART0_RTSn.GPIO1_23 */
+		>;
+	};
 };
 
 &mcu_pmx0 {
@@ -407,6 +413,12 @@
 		reg = <0x22>;
 		gpio-controller;
 		#gpio-cells = <2>;
+		interrupt-parent = <&main_gpio1>;
+		interrupts = <23 IRQ_TYPE_EDGE_FALLING>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&main_gpio1_ioexp_intr_pins_default>;
 
 		gpio-line-names = "GPIO_CPSW2_RST", "GPIO_CPSW1_RST",
 				   "BT_EN_SOC", "MMC1_SD_EN",
@@ -434,6 +446,33 @@
 		DRVDD-supply = <&vcc_3v3_sys>;
 		DVDD-supply = <&buck5>;
 	};
+
+	exp2: gpio@23 {
+		compatible = "ti,tca6424";
+		reg = <0x23>;
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		gpio-line-names = "", "",
+				  "", "",
+				  "", "",
+				  "", "",
+				  "WL_LT_EN", "CSI_RSTz",
+				  "", "",
+				  "", "",
+				  "", "",
+				  "SPI0_FET_SEL", "SPI0_FET_OE",
+				  "RGMII2_BRD_CONN_DET", "CSI_SEL2",
+				  "CSI_EN", "AUTO_100M_1000M_CONFIG",
+				  "CSI_VLDO_SEL", "SoC_WLAN_SDIO_RST";
+	};
+};
+
+&main_i2c2 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_i2c2_pins_default>;
+	clock-frequency = <400000>;
 };
 
 &sdhci1 {
diff --git a/arch/arm64/boot/dts/ti/k3-am62p-main.dtsi b/arch/arm64/boot/dts/ti/k3-am62p-main.dtsi
index 963758c7d377..4c51bae06b57 100644
--- a/arch/arm64/boot/dts/ti/k3-am62p-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62p-main.dtsi
@@ -101,8 +101,13 @@
 			      <0x00 0x4c000000 0x00 0x20000>,
 			      <0x00 0x4a820000 0x00 0x20000>,
 			      <0x00 0x4aa40000 0x00 0x20000>,
-			      <0x00 0x4bc00000 0x00 0x100000>;
-			reg-names = "gcfg", "bchanrt", "rchanrt", "tchanrt", "ringrt";
+			      <0x00 0x4bc00000 0x00 0x100000>,
+			      <0x00 0x48600000 0x00 0x8000>,
+			      <0x00 0x484a4000 0x00 0x2000>,
+			      <0x00 0x484c2000 0x00 0x2000>,
+			      <0x00 0x48420000 0x00 0x2000>;
+			reg-names = "gcfg", "bchanrt", "rchanrt", "tchanrt", "ringrt",
+				    "ring", "tchan", "rchan", "bchan";
 			msi-parent = <&inta_main_dmss>;
 			#dma-cells = <3>;
 
@@ -119,8 +124,13 @@
 			reg = <0x00 0x485c0000 0x00 0x100>,
 			      <0x00 0x4a800000 0x00 0x20000>,
 			      <0x00 0x4aa00000 0x00 0x40000>,
-			      <0x00 0x4b800000 0x00 0x400000>;
-			reg-names = "gcfg", "rchanrt", "tchanrt", "ringrt";
+			      <0x00 0x4b800000 0x00 0x400000>,
+			      <0x00 0x485e0000 0x00 0x10000>,
+			      <0x00 0x484a0000 0x00 0x2000>,
+			      <0x00 0x484c0000 0x00 0x2000>,
+			      <0x00 0x48430000 0x00 0x1000>;
+			reg-names = "gcfg", "rchanrt", "tchanrt", "ringrt",
+				    "ring", "tchan", "rchan", "rflow";
 			msi-parent = <&inta_main_dmss>;
 			#dma-cells = <2>;
 			bootph-all;
diff --git a/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts b/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts
index f377eadef0c1..1773c05f752c 100644
--- a/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts
+++ b/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts
@@ -598,3 +598,12 @@
 	status = "reserved";
 	bootph-all;
 };
+
+/* mcu_gpio0 and mcu_gpio_intr are reserved for mcu firmware usage */
+&mcu_gpio0 {
+	status = "reserved";
+};
+
+&mcu_gpio_intr {
+	status = "reserved";
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi b/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi
index 19f57ead4ebd..33768c02d8eb 100644
--- a/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi
@@ -399,6 +399,13 @@
 	};
 };
 
+&main_i2c2 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_i2c2_pins_default>;
+	clock-frequency = <400000>;
+};
+
 &sdhci0 {
 	bootph-all;
 	status = "okay";
@@ -517,3 +524,12 @@
 		};
 	};
 };
+
+/* mcu_gpio0 and mcu_gpio_intr are reserved for mcu firmware usage */
+&mcu_gpio0 {
+	status = "reserved";
+};
+
+&mcu_gpio_intr {
+	status = "reserved";
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am62x-sk-csi2-imx219.dtso b/arch/arm64/boot/dts/ti/k3-am62x-sk-csi2-imx219.dtso
new file mode 100644
index 000000000000..6f4cd73c2f43
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am62x-sk-csi2-imx219.dtso
@@ -0,0 +1,84 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * IMX219 (RPi v2) Camera Module
+ * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/gpio/gpio.h>
+
+&{/} {
+	clk_imx219_fixed: imx219-xclk {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <24000000>;
+	};
+};
+
+&main_i2c2 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+
+	i2c-switch@71 {
+		compatible = "nxp,pca9543";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0x71>;
+
+		/* CAM port */
+		i2c@1 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <1>;
+
+			ov5640: camera@10 {
+				compatible = "sony,imx219";
+				reg = <0x10>;
+
+				clocks = <&clk_imx219_fixed>;
+				clock-names = "xclk";
+
+				reset-gpios = <&exp1 13 GPIO_ACTIVE_HIGH>;
+
+				port {
+					csi2_cam0: endpoint {
+						remote-endpoint = <&csi2rx0_in_sensor>;
+						link-frequencies = /bits/ 64 <456000000>;
+						clock-lanes = <0>;
+						data-lanes = <1 2>;
+					};
+				};
+			};
+		};
+	};
+};
+
+&cdns_csi2rx0 {
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		csi0_port0: port@0 {
+			reg = <0>;
+			status = "okay";
+
+			csi2rx0_in_sensor: endpoint {
+				remote-endpoint = <&csi2_cam0>;
+				bus-type = <4>; /* CSI2 DPHY. */
+				clock-lanes = <0>;
+				data-lanes = <1 2>;
+			};
+		};
+	};
+};
+
+&ti_csi2rx0 {
+	status = "okay";
+};
+
+&dphy0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am62x-sk-csi2-ov5640.dtso b/arch/arm64/boot/dts/ti/k3-am62x-sk-csi2-ov5640.dtso
new file mode 100644
index 000000000000..9323a4b38389
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am62x-sk-csi2-ov5640.dtso
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ALINX AN5641 & Digilent PCam 5C - OV5640 camera module
+ * Copyright (C) 2022-2023 Texas Instruments Incorporated - https://www.ti.com/
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/gpio/gpio.h>
+
+&{/} {
+	clk_ov5640_fixed: ov5640-xclk {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <12000000>;
+	};
+};
+
+&main_i2c2 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+
+	i2c-switch@71 {
+		compatible = "nxp,pca9543";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0x71>;
+
+		/* CAM port */
+		i2c@1 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <1>;
+
+			ov5640: camera@3c {
+				compatible = "ovti,ov5640";
+				reg = <0x3c>;
+
+				clocks = <&clk_ov5640_fixed>;
+				clock-names = "xclk";
+				powerdown-gpios = <&exp1 13 GPIO_ACTIVE_LOW>;
+
+				port {
+					csi2_cam0: endpoint {
+						remote-endpoint = <&csi2rx0_in_sensor>;
+						clock-lanes = <0>;
+						data-lanes = <1 2>;
+					};
+				};
+			};
+		};
+	};
+};
+
+&cdns_csi2rx0 {
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		csi0_port0: port@0 {
+			reg = <0>;
+			status = "okay";
+
+			csi2rx0_in_sensor: endpoint {
+				remote-endpoint = <&csi2_cam0>;
+				bus-type = <4>; /* CSI2 DPHY. */
+				clock-lanes = <0>;
+				data-lanes = <1 2>;
+			};
+		};
+	};
+};
+
+&ti_csi2rx0 {
+	status = "okay";
+};
+
+&dphy0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am62x-sk-csi2-tevi-ov5640.dtso b/arch/arm64/boot/dts/ti/k3-am62x-sk-csi2-tevi-ov5640.dtso
new file mode 100644
index 000000000000..dcaa33a4c8d3
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am62x-sk-csi2-tevi-ov5640.dtso
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Technexion TEVI-OV5640-*-RPI - OV5640 camera module
+ * Copyright (C) 2022-2023 Texas Instruments Incorporated - https://www.ti.com/
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/gpio/gpio.h>
+
+&{/} {
+	clk_ov5640_fixed: ov5640-xclk {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <24000000>;
+	};
+};
+
+&main_i2c2 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+
+	i2c-switch@71 {
+		compatible = "nxp,pca9543";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0x71>;
+
+		/* CAM port */
+		i2c@1 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <1>;
+
+			ov5640: camera@3c {
+				compatible = "ovti,ov5640";
+				reg = <0x3c>;
+
+				clocks = <&clk_ov5640_fixed>;
+				clock-names = "xclk";
+				powerdown-gpios = <&exp1 13 GPIO_ACTIVE_LOW>;
+
+				port {
+					csi2_cam0: endpoint {
+						remote-endpoint = <&csi2rx0_in_sensor>;
+						clock-lanes = <0>;
+						data-lanes = <1 2>;
+					};
+				};
+			};
+		};
+	};
+};
+
+&cdns_csi2rx0 {
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		csi0_port0: port@0 {
+			reg = <0>;
+			status = "okay";
+
+			csi2rx0_in_sensor: endpoint {
+				remote-endpoint = <&csi2_cam0>;
+				bus-type = <4>; /* CSI2 DPHY. */
+				clock-lanes = <0>;
+				data-lanes = <1 2>;
+			};
+		};
+	};
+};
+
+&ti_csi2rx0 {
+	status = "okay";
+};
+
+&dphy0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am64-main.dtsi b/arch/arm64/boot/dts/ti/k3-am64-main.dtsi
index 0be642bc1b86..e348114f42e0 100644
--- a/arch/arm64/boot/dts/ti/k3-am64-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am64-main.dtsi
@@ -63,7 +63,7 @@
 			#phy-cells = <1>;
 		};
 
-		epwm_tbclk: clock-controller@4140 {
+		epwm_tbclk: clock-controller@4130 {
 			compatible = "ti,am64-epwm-tbclk";
 			reg = <0x4130 0x4>;
 			#clock-cells = <1>;
@@ -138,8 +138,13 @@
 			      <0x00 0x4c000000 0x00 0x20000>,
 			      <0x00 0x4a820000 0x00 0x20000>,
 			      <0x00 0x4aa40000 0x00 0x20000>,
-			      <0x00 0x4bc00000 0x00 0x100000>;
-			reg-names = "gcfg", "bchanrt", "rchanrt", "tchanrt", "ringrt";
+			      <0x00 0x4bc00000 0x00 0x100000>,
+			      <0x00 0x48600000 0x00 0x8000>,
+			      <0x00 0x484a4000 0x00 0x2000>,
+			      <0x00 0x484c2000 0x00 0x2000>,
+			      <0x00 0x48420000 0x00 0x2000>;
+			reg-names = "gcfg", "bchanrt", "rchanrt", "tchanrt", "ringrt",
+				    "ring", "tchan", "rchan", "bchan";
 			msi-parent = <&inta_main_dmss>;
 			#dma-cells = <3>;
 
@@ -155,8 +160,13 @@
 			reg = <0x00 0x485c0000 0x00 0x100>,
 			      <0x00 0x4a800000 0x00 0x20000>,
 			      <0x00 0x4aa00000 0x00 0x40000>,
-			      <0x00 0x4b800000 0x00 0x400000>;
-			reg-names = "gcfg", "rchanrt", "tchanrt", "ringrt";
+			      <0x00 0x4b800000 0x00 0x400000>,
+			      <0x00 0x485e0000 0x00 0x20000>,
+			      <0x00 0x484a0000 0x00 0x4000>,
+			      <0x00 0x484c0000 0x00 0x2000>,
+			      <0x00 0x48430000 0x00 0x4000>;
+			reg-names = "gcfg", "rchanrt", "tchanrt", "ringrt",
+				    "ring", "tchan", "rchan", "rflow";
 			msi-parent = <&inta_main_dmss>;
 			#dma-cells = <2>;
 
@@ -623,6 +633,7 @@
 		ti,otap-del-sel-mmc-hs = <0x0>;
 		ti,otap-del-sel-ddr52 = <0x6>;
 		ti,otap-del-sel-hs200 = <0x7>;
+		status = "disabled";
 	};
 
 	sdhci1: mmc@fa00000 {
@@ -641,6 +652,7 @@
 		ti,otap-del-sel-sdr104 = <0x6>;
 		ti,otap-del-sel-ddr50 = <0x9>;
 		ti,clkbuf-sel = <0x7>;
+		status = "disabled";
 	};
 
 	cpsw3g: ethernet@8000000 {
diff --git a/arch/arm64/boot/dts/ti/k3-am64-phycore-som.dtsi b/arch/arm64/boot/dts/ti/k3-am64-phycore-som.dtsi
index f87f09d83c95..1678e74cb750 100644
--- a/arch/arm64/boot/dts/ti/k3-am64-phycore-som.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am64-phycore-som.dtsi
@@ -29,7 +29,7 @@
 		reg = <0x00000000 0x80000000 0x00000000 0x80000000>;
 	};
 
-	reserved-memory {
+	reserved_memory: reserved-memory {
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
@@ -39,6 +39,54 @@
 			alignment = <0x1000>;
 			no-map;
 		};
+
+		main_r5fss0_core0_dma_memory_region: r5f-dma-memory@a0000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa0000000 0x00 0x100000>;
+			no-map;
+		};
+
+		main_r5fss0_core0_memory_region: r5f-memory@a0100000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa0100000 0x00 0xf00000>;
+			no-map;
+		};
+
+		main_r5fss0_core1_dma_memory_region: r5f-dma-memory@a1000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa1000000 0x00 0x100000>;
+			no-map;
+		};
+
+		main_r5fss0_core1_memory_region: r5f-memory@a1100000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa1100000 0x00 0xf00000>;
+			no-map;
+		};
+
+		main_r5fss1_core0_dma_memory_region: r5f-dma-memory@a2000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa2000000 0x00 0x100000>;
+			no-map;
+		};
+
+		main_r5fss1_core0_memory_region: r5f-memory@a2100000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa2100000 0x00 0xf00000>;
+			no-map;
+		};
+
+		main_r5fss1_core1_dma_memory_region: r5f-dma-memory@a3000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa3000000 0x00 0x100000>;
+			no-map;
+		};
+
+		main_r5fss1_core1_memory_region: r5f-memory@a3100000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa3100000 0x00 0xf00000>;
+			no-map;
+		};
 	};
 
 	leds {
@@ -166,6 +214,34 @@
 	status = "disabled";
 };
 
+&mailbox0_cluster2 {
+	status = "okay";
+
+	mbox_main_r5fss0_core0: mbox-main-r5fss0-core0 {
+		ti,mbox-rx = <0 0 2>;
+		ti,mbox-tx = <1 0 2>;
+	};
+
+	mbox_main_r5fss0_core1: mbox-main-r5fss0-core1 {
+		ti,mbox-rx = <2 0 2>;
+		ti,mbox-tx = <3 0 2>;
+	};
+};
+
+&mailbox0_cluster4 {
+	status = "okay";
+
+	mbox_main_r5fss1_core0: mbox-main-r5fss1-core0 {
+		ti,mbox-rx = <0 0 2>;
+		ti,mbox-tx = <1 0 2>;
+	};
+
+	mbox_main_r5fss1_core1: mbox-main-r5fss1-core1 {
+		ti,mbox-rx = <2 0 2>;
+		ti,mbox-tx = <3 0 2>;
+	};
+};
+
 &main_i2c0 {
 	status = "okay";
 	pinctrl-names = "default";
@@ -191,6 +267,30 @@
 	};
 };
 
+&main_r5fss0_core0 {
+	mboxes = <&mailbox0_cluster2 &mbox_main_r5fss0_core0>;
+	memory-region = <&main_r5fss0_core0_dma_memory_region>,
+			<&main_r5fss0_core0_memory_region>;
+};
+
+&main_r5fss0_core1 {
+	mboxes = <&mailbox0_cluster2 &mbox_main_r5fss0_core1>;
+	memory-region = <&main_r5fss0_core1_dma_memory_region>,
+			<&main_r5fss0_core1_memory_region>;
+};
+
+&main_r5fss1_core0 {
+	mboxes = <&mailbox0_cluster4 &mbox_main_r5fss1_core0>;
+	memory-region = <&main_r5fss1_core0_dma_memory_region>,
+			<&main_r5fss1_core0_memory_region>;
+};
+
+&main_r5fss1_core1 {
+	mboxes = <&mailbox0_cluster4 &mbox_main_r5fss1_core1>;
+	memory-region = <&main_r5fss1_core1_dma_memory_region>,
+			<&main_r5fss1_core1_memory_region>;
+};
+
 &ospi0 {
 	status = "okay";
 	pinctrl-names = "default";
@@ -211,6 +311,7 @@
 };
 
 &sdhci0 {
+	status = "okay";
 	bus-width = <8>;
 	non-removable;
 	ti,driver-strength-ohm = <50>;
diff --git a/arch/arm64/boot/dts/ti/k3-am642-evm.dts b/arch/arm64/boot/dts/ti/k3-am642-evm.dts
index 4dba18941015..8c5651d2cf5d 100644
--- a/arch/arm64/boot/dts/ti/k3-am642-evm.dts
+++ b/arch/arm64/boot/dts/ti/k3-am642-evm.dts
@@ -468,11 +468,15 @@
 	bootph-all;
 };
 
-/* mcu_gpio0 is reserved for mcu firmware usage */
+/* mcu_gpio0 and mcu_gpio_intr are reserved for mcu firmware usage */
 &mcu_gpio0 {
 	status = "reserved";
 };
 
+&mcu_gpio_intr {
+	status = "reserved";
+};
+
 &main_spi0 {
 	status = "okay";
 	pinctrl-names = "default";
@@ -487,17 +491,19 @@
 	};
 };
 
+/* eMMC */
 &sdhci0 {
-	/* emmc */
+	status = "okay";
 	bus-width = <8>;
 	non-removable;
 	ti,driver-strength-ohm = <50>;
 	disable-wp;
 };
 
+/* SD/MMC */
 &sdhci1 {
-	/* SD/MMC */
 	bootph-all;
+	status = "okay";
 	vmmc-supply = <&vdd_mmc1>;
 	pinctrl-names = "default";
 	bus-width = <4>;
diff --git a/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-rdk.dts b/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-rdk.dts
index 9175e96842d8..53b64e55413f 100644
--- a/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-rdk.dts
+++ b/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-rdk.dts
@@ -264,6 +264,7 @@
 };
 
 &sdhci1 {
+	status = "okay";
 	vmmc-supply = <&vcc_3v3_mmc>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_mmc1_pins_default>;
diff --git a/arch/arm64/boot/dts/ti/k3-am642-sk.dts b/arch/arm64/boot/dts/ti/k3-am642-sk.dts
index f29c8a9b59ba..1dddd6fc1a0d 100644
--- a/arch/arm64/boot/dts/ti/k3-am642-sk.dts
+++ b/arch/arm64/boot/dts/ti/k3-am642-sk.dts
@@ -433,12 +433,17 @@
 	};
 };
 
-/* mcu_gpio0 is reserved for mcu firmware usage */
+/* mcu_gpio0 and mcu_gpio_intr are reserved for mcu firmware usage */
 &mcu_gpio0 {
 	status = "reserved";
 };
 
+&mcu_gpio_intr {
+	status = "reserved";
+};
+
 &sdhci0 {
+	status = "okay";
 	vmmc-supply = <&wlan_en>;
 	bus-width = <4>;
 	non-removable;
@@ -458,9 +463,10 @@
 	};
 };
 
+/* SD/MMC */
 &sdhci1 {
-	/* SD/MMC */
 	bootph-all;
+	status = "okay";
 	vmmc-supply = <&vdd_mmc1>;
 	pinctrl-names = "default";
 	bus-width = <4>;
diff --git a/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl-mbax4xxl.dts b/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl-mbax4xxl.dts
index d95d80076a42..55102d35cecc 100644
--- a/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl-mbax4xxl.dts
+++ b/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl-mbax4xxl.dts
@@ -425,7 +425,6 @@
 	ti,driver-strength-ohm = <50>;
 	ti,fails-without-test-cd;
 	/* Enabled by overlay */
-	status = "disabled";
 };
 
 &tscadc0 {
diff --git a/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl.dtsi b/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl.dtsi
index d82d4a98306a..6c785eff7d2f 100644
--- a/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl.dtsi
@@ -219,6 +219,7 @@
 };
 
 &sdhci0 {
+	status = "okay";
 	non-removable;
 	disable-wp;
 	no-sdio;
diff --git a/arch/arm64/boot/dts/ti/k3-am65-iot2050-common-pg1.dtsi b/arch/arm64/boot/dts/ti/k3-am65-iot2050-common-pg1.dtsi
index 51f902fa35a7..1d1979859583 100644
--- a/arch/arm64/boot/dts/ti/k3-am65-iot2050-common-pg1.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65-iot2050-common-pg1.dtsi
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (c) Siemens AG, 2021
+ * Copyright (c) Siemens AG, 2021-2023
  *
  * Authors:
  *   Jan Kiszka <jan.kiszka@siemens.com>
@@ -44,3 +44,11 @@
 &tx_pru2_1 {
 	status = "disabled";
 };
+
+&icssg0_eth {
+	status = "disabled";
+};
+
+&icssg0_mdio {
+	status = "disabled";
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am65-iot2050-common-pg2.dtsi b/arch/arm64/boot/dts/ti/k3-am65-iot2050-common-pg2.dtsi
index e9419c4fe605..e9b57b87e42e 100644
--- a/arch/arm64/boot/dts/ti/k3-am65-iot2050-common-pg2.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65-iot2050-common-pg2.dtsi
@@ -20,7 +20,9 @@
 
 &main_gpio1 {
 	pinctrl-names = "default";
-	pinctrl-0 = <&cp2102n_reset_pin_default>;
+	pinctrl-0 =
+		<&main_pcie_enable_pins_default>,
+		<&cp2102n_reset_pin_default>;
 	gpio-line-names =
 		"", "", "", "", "", "", "", "", "", "",
 		"", "", "", "", "", "", "", "", "", "",
diff --git a/arch/arm64/boot/dts/ti/k3-am65-iot2050-common.dtsi b/arch/arm64/boot/dts/ti/k3-am65-iot2050-common.dtsi
index ba1c14a54acf..61a634afaa4f 100644
--- a/arch/arm64/boot/dts/ti/k3-am65-iot2050-common.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65-iot2050-common.dtsi
@@ -9,14 +9,26 @@
  * Common bits of the IOT2050 Basic and Advanced variants, PG1 and PG2
  */
 
-#include "k3-am654.dtsi"
 #include <dt-bindings/phy/phy.h>
+#include <dt-bindings/net/ti-dp83867.h>
 
 / {
 	aliases {
+		serial0 = &wkup_uart0;
+		serial1 = &mcu_uart0;
+		serial2 = &main_uart0;
+		serial3 = &main_uart1;
+		i2c0 = &wkup_i2c0;
+		i2c1 = &mcu_i2c0;
+		i2c2 = &main_i2c0;
+		i2c3 = &main_i2c1;
+		i2c4 = &main_i2c2;
+		i2c5 = &main_i2c3;
 		spi0 = &mcu_spi0;
 		mmc0 = &sdhci1;
 		mmc1 = &sdhci0;
+		ethernet1 = &icssg0_emac0;
+		ethernet2 = &icssg0_emac1;
 	};
 
 	chosen {
@@ -101,9 +113,498 @@
 		#clock-cells = <0>;
 		clock-frequency = <19200000>;
 	};
+
+	/* Dual Ethernet application node on PRU-ICSSG0 */
+	icssg0_eth: icssg0-eth {
+		compatible = "ti,am654-icssg-prueth";
+		pinctrl-names = "default";
+		pinctrl-0 = <&icssg0_rgmii_pins_default>;
+		sram = <&msmc_ram>;
+
+		ti,prus = <&pru0_0>, <&rtu0_0>, <&tx_pru0_0>,
+			<&pru0_1>, <&rtu0_1>, <&tx_pru0_1>;
+		firmware-name = "ti-pruss/am65x-sr2-pru0-prueth-fw.elf",
+				"ti-pruss/am65x-sr2-rtu0-prueth-fw.elf",
+				"ti-pruss/am65x-sr2-txpru0-prueth-fw.elf",
+				"ti-pruss/am65x-sr2-pru1-prueth-fw.elf",
+				"ti-pruss/am65x-sr2-rtu1-prueth-fw.elf",
+				"ti-pruss/am65x-sr2-txpru1-prueth-fw.elf";
+
+		ti,pruss-gp-mux-sel = <2>,      /* MII mode */
+				      <2>,
+				      <2>,
+				      <2>,	/* MII mode */
+				      <2>,
+				      <2>;
+
+		ti,mii-g-rt = <&icssg0_mii_g_rt>;
+		ti,mii-rt = <&icssg0_mii_rt>;
+		ti,iep = <&icssg0_iep0>,  <&icssg0_iep1>;
+
+		interrupt-parent = <&icssg0_intc>;
+		interrupts = <24 0 2>, <25 1 3>;
+		interrupt-names = "tx_ts0", "tx_ts1";
+
+		dmas = <&main_udmap 0xc100>, /* egress slice 0 */
+		       <&main_udmap 0xc101>, /* egress slice 0 */
+		       <&main_udmap 0xc102>, /* egress slice 0 */
+		       <&main_udmap 0xc103>, /* egress slice 0 */
+		       <&main_udmap 0xc104>, /* egress slice 1 */
+		       <&main_udmap 0xc105>, /* egress slice 1 */
+		       <&main_udmap 0xc106>, /* egress slice 1 */
+		       <&main_udmap 0xc107>, /* egress slice 1 */
+		       <&main_udmap 0x4100>, /* ingress slice 0 */
+		       <&main_udmap 0x4101>; /* ingress slice 1 */
+		dma-names = "tx0-0", "tx0-1", "tx0-2", "tx0-3",
+			    "tx1-0", "tx1-1", "tx1-2", "tx1-3",
+			    "rx0", "rx1";
+
+		ethernet-ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			icssg0_emac0: port@0 {
+				reg = <0>;
+				phy-handle = <&icssg0_eth0_phy>;
+				phy-mode = "rgmii-id";
+				ti,syscon-rgmii-delay = <&scm_conf 0x4100>;
+				ti,half-duplex-capable;
+				/* Filled in by bootloader */
+				local-mac-address = [00 00 00 00 00 00];
+			};
+
+			icssg0_emac1: port@1 {
+				reg = <1>;
+				phy-handle = <&icssg0_eth1_phy>;
+				phy-mode = "rgmii-id";
+				ti,syscon-rgmii-delay = <&scm_conf 0x4104>;
+				ti,half-duplex-capable;
+				/* Filled in by bootloader */
+				local-mac-address = [00 00 00 00 00 00];
+			};
+		};
+	};
 };
 
 &wkup_pmx0 {
+	pinctrl-names =
+		"default",
+		"d0-uart0-rxd",  "d0-gpio",  "d0-gpio-pullup",  "d0-gpio-pulldown",
+		"d1-uart0-txd",  "d1-gpio",  "d1-gpio-pullup",  "d1-gpio-pulldown",
+		"d2-uart0-ctsn", "d2-gpio",  "d2-gpio-pullup",  "d2-gpio-pulldown",
+		"d3-uart0-rtsn", "d3-gpio",  "d3-gpio-pullup",  "d3-gpio-pulldown",
+		"d10-spi0-cs0",  "d10-gpio", "d10-gpio-pullup", "d10-gpio-pulldown",
+		"d11-spi0-d0",   "d11-gpio", "d11-gpio-pullup", "d11-gpio-pulldown",
+		"d12-spi0-d1",   "d12-gpio", "d12-gpio-pullup", "d12-gpio-pulldown",
+		"d13-spi0-clk",  "d13-gpio", "d13-gpio-pullup", "d13-gpio-pulldown",
+		"a0-gpio", "a0-gpio-pullup", "a0-gpio-pulldown",
+		"a1-gpio", "a1-gpio-pullup", "a1-gpio-pulldown",
+		"a2-gpio", "a2-gpio-pullup", "a2-gpio-pulldown",
+		"a3-gpio", "a3-gpio-pullup", "a3-gpio-pulldown",
+		"a4-gpio", "a4-gpio-pullup", "a4-gpio-pulldown",
+		"a5-gpio", "a5-gpio-pullup", "a5-gpio-pulldown";
+
+	pinctrl-0 = <&d0_uart0_rxd>;
+	pinctrl-1 = <&d0_uart0_rxd>;
+	pinctrl-2 = <&d0_gpio>;
+	pinctrl-3 = <&d0_gpio_pullup>;
+	pinctrl-4 = <&d0_gpio_pulldown>;
+	pinctrl-5 = <&d1_uart0_txd>;
+	pinctrl-6 = <&d1_gpio>;
+	pinctrl-7 = <&d1_gpio_pullup>;
+	pinctrl-8 = <&d1_gpio_pulldown>;
+	pinctrl-9 = <&d2_uart0_ctsn>;
+	pinctrl-10 = <&d2_gpio>;
+	pinctrl-11 = <&d2_gpio_pullup>;
+	pinctrl-12 = <&d2_gpio_pulldown>;
+	pinctrl-13 = <&d3_uart0_rtsn>;
+	pinctrl-14 = <&d3_gpio>;
+	pinctrl-15 = <&d3_gpio_pullup>;
+	pinctrl-16 = <&d3_gpio_pulldown>;
+	pinctrl-17 = <&d10_spi0_cs0>;
+	pinctrl-18 = <&d10_gpio>;
+	pinctrl-19 = <&d10_gpio_pullup>;
+	pinctrl-20 = <&d10_gpio_pulldown>;
+	pinctrl-21 = <&d11_spi0_d0>;
+	pinctrl-22 = <&d11_gpio>;
+	pinctrl-23 = <&d11_gpio_pullup>;
+	pinctrl-24 = <&d11_gpio_pulldown>;
+	pinctrl-25 = <&d12_spi0_d1>;
+	pinctrl-26 = <&d12_gpio>;
+	pinctrl-27 = <&d12_gpio_pullup>;
+	pinctrl-28 = <&d12_gpio_pulldown>;
+	pinctrl-29 = <&d13_spi0_clk>;
+	pinctrl-30 = <&d13_gpio>;
+	pinctrl-31 = <&d13_gpio_pullup>;
+	pinctrl-32 = <&d13_gpio_pulldown>;
+	pinctrl-33 = <&a0_gpio>;
+	pinctrl-34 = <&a0_gpio_pullup>;
+	pinctrl-35 = <&a0_gpio_pulldown>;
+	pinctrl-36 = <&a1_gpio>;
+	pinctrl-37 = <&a1_gpio_pullup>;
+	pinctrl-38 = <&a1_gpio_pulldown>;
+	pinctrl-39 = <&a2_gpio>;
+	pinctrl-40 = <&a2_gpio_pullup>;
+	pinctrl-41 = <&a2_gpio_pulldown>;
+	pinctrl-42 = <&a3_gpio>;
+	pinctrl-43 = <&a3_gpio_pullup>;
+	pinctrl-44 = <&a3_gpio_pulldown>;
+	pinctrl-45 = <&a4_gpio>;
+	pinctrl-46 = <&a4_gpio_pullup>;
+	pinctrl-47 = <&a4_gpio_pulldown>;
+	pinctrl-48 = <&a5_gpio>;
+	pinctrl-49 = <&a5_gpio_pullup>;
+	pinctrl-50 = <&a5_gpio_pulldown>;
+
+	d0_uart0_rxd: d0-uart0-rxd-pins {
+		pinctrl-single,pins = <
+			/* (P4) MCU_UART0_RXD */
+			AM65X_WKUP_IOPAD(0x0044, PIN_INPUT, 4)
+		>;
+	};
+
+	d0_gpio: d0-gpio-pins {
+		pinctrl-single,pins = <
+			/* (P4) WKUP_GPIO0_29 */
+			AM65X_WKUP_IOPAD(0x0044, PIN_INPUT, 7)
+		>;
+	};
+
+	d0_gpio_pullup: d0-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (P4) WKUP_GPIO0_29 */
+			AM65X_WKUP_IOPAD(0x0044, PIN_INPUT_PULLUP, 7)
+		>;
+	};
+
+	d0_gpio_pulldown: d0-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (P4) WKUP_GPIO0_29 */
+			AM65X_WKUP_IOPAD(0x0044, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d1_uart0_txd: d1-uart0-txd-pins {
+		pinctrl-single,pins = <
+			/* (P5) MCU_UART0_TXD */
+			AM65X_WKUP_IOPAD(0x0048, PIN_OUTPUT, 4)
+		>;
+	};
+
+	d1_gpio: d1-gpio-pins {
+		pinctrl-single,pins = <
+			/* (P5) WKUP_GPIO0_30 */
+			AM65X_WKUP_IOPAD(0x0048, PIN_INPUT, 7)
+		>;
+	};
+
+	d1_gpio_pullup: d1-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (P5) WKUP_GPIO0_30 */
+			AM65X_WKUP_IOPAD(0x0048, PIN_INPUT, 7)
+		>;
+	};
+
+	d1_gpio_pulldown: d1-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (P5) WKUP_GPIO0_30 */
+			AM65X_WKUP_IOPAD(0x0048, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d2_uart0_ctsn: d2-uart0-ctsn-pins {
+		pinctrl-single,pins = <
+			/* (P1) MCU_UART0_CTSn */
+			AM65X_WKUP_IOPAD(0x004C, PIN_INPUT, 4)
+		>;
+	};
+
+	d2_gpio: d2-gpio-pins {
+		pinctrl-single,pins = <
+			/* (P5) WKUP_GPIO0_31 */
+			AM65X_WKUP_IOPAD(0x004C, PIN_INPUT, 7)
+		>;
+	};
+
+	d2_gpio_pullup: d2-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (P5) WKUP_GPIO0_31 */
+			AM65X_WKUP_IOPAD(0x004C, PIN_INPUT, 7)
+		>;
+	};
+
+	d2_gpio_pulldown: d2-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (P5) WKUP_GPIO0_31 */
+			AM65X_WKUP_IOPAD(0x004C, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d3_uart0_rtsn: d3-uart0-rtsn-pins {
+		pinctrl-single,pins = <
+			/* (N3) MCU_UART0_RTSn */
+			AM65X_WKUP_IOPAD(0x0054, PIN_OUTPUT, 4)
+		>;
+	};
+
+	d3_gpio: d3-gpio-pins {
+		pinctrl-single,pins = <
+			/* (N3) WKUP_GPIO0_33 */
+			AM65X_WKUP_IOPAD(0x0054, PIN_INPUT, 7)
+		>;
+	};
+
+	d3_gpio_pullup: d3-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (N3) WKUP_GPIO0_33 */
+			AM65X_WKUP_IOPAD(0x0054, PIN_INPUT, 7)
+		>;
+	};
+
+	d3_gpio_pulldown: d3-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (N3) WKUP_GPIO0_33 */
+			AM65X_WKUP_IOPAD(0x0054, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d10_spi0_cs0: d10-spi0-cs0-pins {
+		pinctrl-single,pins = <
+			/* (Y4) MCU_SPI0_CS0 */
+			AM65X_WKUP_IOPAD(0x009c, PIN_OUTPUT, 0)
+		>;
+	};
+
+	d10_gpio: d10-gpio-pins {
+		pinctrl-single,pins = <
+			/* (Y4) WKUP_GPIO0_51 */
+			AM65X_WKUP_IOPAD(0x009c, PIN_INPUT, 7)
+		>;
+	};
+
+	d10_gpio_pullup: d10-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (Y4) WKUP_GPIO0_51 */
+			AM65X_WKUP_IOPAD(0x009c, PIN_INPUT, 7)
+		>;
+	};
+
+	d10_gpio_pulldown: d10-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (Y4) WKUP_GPIO0_51 */
+			AM65X_WKUP_IOPAD(0x009c, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d11_spi0_d0: d11-spi0-d0-pins {
+		pinctrl-single,pins = <
+			/* (Y3) MCU_SPI0_D0 */
+			AM65X_WKUP_IOPAD(0x0094, PIN_INPUT, 0)
+		>;
+	};
+
+	d11_gpio: d11-gpio-pins {
+		pinctrl-single,pins = <
+			/* (Y3) WKUP_GPIO0_49 */
+			AM65X_WKUP_IOPAD(0x0094, PIN_INPUT, 7)
+		>;
+	};
+
+	d11_gpio_pullup: d11-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (Y3) WKUP_GPIO0_49 */
+			AM65X_WKUP_IOPAD(0x0094, PIN_INPUT, 7)
+		>;
+	};
+
+	d11_gpio_pulldown: d11-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (Y3) WKUP_GPIO0_49 */
+			AM65X_WKUP_IOPAD(0x0094, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d12_spi0_d1: d12-spi0-d1-pins {
+		pinctrl-single,pins = <
+			/* (Y2) MCU_SPI0_D1 */
+			AM65X_WKUP_IOPAD(0x0098, PIN_INPUT, 0)
+		>;
+	};
+
+	d12_gpio: d12-gpio-pins {
+		pinctrl-single,pins = <
+			/* (Y2) WKUP_GPIO0_50 */
+			AM65X_WKUP_IOPAD(0x0098, PIN_INPUT, 7)
+		>;
+	};
+
+	d12_gpio_pullup: d12-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (Y2) WKUP_GPIO0_50 */
+			AM65X_WKUP_IOPAD(0x0098, PIN_INPUT, 7)
+		>;
+	};
+
+	d12_gpio_pulldown: d12-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (Y2) WKUP_GPIO0_50 */
+			AM65X_WKUP_IOPAD(0x0098, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d13_spi0_clk: d13-spi0-clk-pins {
+		pinctrl-single,pins = <
+			/* (Y1) MCU_SPI0_CLK */
+			AM65X_WKUP_IOPAD(0x0090, PIN_INPUT, 0)
+		>;
+	};
+
+	d13_gpio: d13-gpio-pins {
+		pinctrl-single,pins = <
+			/* (Y1) WKUP_GPIO0_48 */
+			AM65X_WKUP_IOPAD(0x0090, PIN_INPUT, 7)
+		>;
+	};
+
+	d13_gpio_pullup: d13-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (Y1) WKUP_GPIO0_48 */
+			AM65X_WKUP_IOPAD(0x0090, PIN_INPUT, 7)
+		>;
+	};
+
+	d13_gpio_pulldown: d13-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (Y1) WKUP_GPIO0_48 */
+			AM65X_WKUP_IOPAD(0x0090, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	a0_gpio: a0-gpio-pins {
+		pinctrl-single,pins = <
+			/* (L6) WKUP_GPIO0_45 */
+			AM65X_WKUP_IOPAD(0x0084, PIN_INPUT, 7)
+		>;
+	};
+
+	a0_gpio_pullup: a0-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (L6) WKUP_GPIO0_45 */
+			AM65X_WKUP_IOPAD(0x0084, PIN_INPUT, 7)
+		>;
+	};
+
+	a0_gpio_pulldown: a0-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (L6) WKUP_GPIO0_45 */
+			AM65X_WKUP_IOPAD(0x0084, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	a1_gpio: a1-gpio-pins {
+		pinctrl-single,pins = <
+			/* (M6) WKUP_GPIO0_44 */
+			AM65X_WKUP_IOPAD(0x0080, PIN_INPUT, 7)
+		>;
+	};
+
+	a1_gpio_pullup: a1-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (M6) WKUP_GPIO0_44 */
+			AM65X_WKUP_IOPAD(0x0080, PIN_INPUT, 7)
+		>;
+	};
+
+	a1_gpio_pulldown: a1-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (M6) WKUP_GPIO0_44 */
+			AM65X_WKUP_IOPAD(0x0080, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	a2_gpio: a2-gpio-pins {
+		pinctrl-single,pins = <
+			/* (L5) WKUP_GPIO0_43 */
+			AM65X_WKUP_IOPAD(0x007C, PIN_INPUT, 7)
+		>;
+	};
+
+	a2_gpio_pullup: a2-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (L5) WKUP_GPIO0_43 */
+			AM65X_WKUP_IOPAD(0x007C, PIN_INPUT, 7)
+		>;
+	};
+
+	a2_gpio_pulldown: a2-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (L5) WKUP_GPIO0_43 */
+			AM65X_WKUP_IOPAD(0x007C, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	a3_gpio: a3-gpio-pins {
+		pinctrl-single,pins = <
+			/* (M5) WKUP_GPIO0_39 */
+			AM65X_WKUP_IOPAD(0x006C, PIN_INPUT, 7)
+		>;
+	};
+
+	a3_gpio_pullup: a3-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (M5) WKUP_GPIO0_39 */
+			AM65X_WKUP_IOPAD(0x006C, PIN_INPUT, 7)
+		>;
+	};
+
+	a3_gpio_pulldown: a3-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (M5) WKUP_GPIO0_39 */
+			AM65X_WKUP_IOPAD(0x006C, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	a4_gpio: a4-gpio-pins {
+		pinctrl-single,pins = <
+			/* (L2) WKUP_GPIO0_42 */
+			AM65X_WKUP_IOPAD(0x0078, PIN_INPUT, 7)
+		>;
+	};
+
+	a4_gpio_pullup: a4-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (L2) WKUP_GPIO0_42 */
+			AM65X_WKUP_IOPAD(0x0078, PIN_INPUT, 7)
+		>;
+	};
+
+	a4_gpio_pulldown: a4-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (L2) WKUP_GPIO0_42 */
+			AM65X_WKUP_IOPAD(0x0078, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	a5_gpio: a5-gpio-pins {
+		pinctrl-single,pins = <
+			/* (N5) WKUP_GPIO0_35 */
+			AM65X_WKUP_IOPAD(0x005C, PIN_INPUT, 7)
+		>;
+	};
+
+	a5_gpio_pullup: a5-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (N5) WKUP_GPIO0_35 */
+			AM65X_WKUP_IOPAD(0x005C, PIN_INPUT_PULLUP, 7)
+		>;
+	};
+
+	a5_gpio_pulldown: a5-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (N5) WKUP_GPIO0_35 */
+			AM65X_WKUP_IOPAD(0x005C, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
 	wkup_i2c0_pins_default: wkup-i2c0-default-pins {
 		pinctrl-single,pins = <
 			/* (AC7) WKUP_I2C0_SCL */
@@ -136,23 +637,6 @@
 		>;
 	};
 
-	arduino_uart_pins_default: arduino-uart-default-pins {
-		pinctrl-single,pins = <
-			/* (P4) MCU_UART0_RXD */
-			AM65X_WKUP_IOPAD(0x0044, PIN_INPUT,  4)
-			/* (P5) MCU_UART0_TXD */
-			AM65X_WKUP_IOPAD(0x0048, PIN_OUTPUT, 4)
-		>;
-	};
-
-	arduino_io_d2_to_d3_pins_default: arduino-io-d2-to-d3-default-pins {
-		pinctrl-single,pins = <
-			/* (P1) WKUP_GPIO0_31 */
-			AM65X_WKUP_IOPAD(0x004C, PIN_OUTPUT, 7)
-			/* (N3) WKUP_GPIO0_33 */
-			AM65X_WKUP_IOPAD(0x0054, PIN_OUTPUT, 7)
-		>;
-	};
 
 	arduino_io_oe_pins_default: arduino-io-oe-default-pins {
 		pinctrl-single,pins = <
@@ -232,6 +716,220 @@
 };
 
 &main_pmx0 {
+	pinctrl-names =
+		"default",
+		"d4-ehrpwm0-a", "d4-gpio", "d4-gpio-pullup", "d4-gpio-pulldown",
+		"d5-ehrpwm1-a", "d5-gpio", "d5-gpio-pullup", "d5-gpio-pulldown",
+		"d6-ehrpwm2-a", "d6-gpio", "d6-gpio-pullup", "d6-gpio-pulldown",
+		"d7-ehrpwm3-a", "d7-gpio", "d7-gpio-pullup", "d7-gpio-pulldown",
+		"d8-ehrpwm4-a", "d8-gpio", "d8-gpio-pullup", "d8-gpio-pulldown",
+		"d9-ehrpwm5-a", "d9-gpio", "d9-gpio-pullup", "d9-gpio-pulldown";
+
+	pinctrl-0 = <&d4_ehrpwm0_a>;
+	pinctrl-1 = <&d4_ehrpwm0_a>;
+	pinctrl-2 = <&d4_gpio>;
+	pinctrl-3 = <&d4_gpio_pullup>;
+	pinctrl-4 = <&d4_gpio_pulldown>;
+
+	pinctrl-5 = <&d5_ehrpwm1_a>;
+	pinctrl-6 = <&d5_gpio>;
+	pinctrl-7 = <&d5_gpio_pullup>;
+	pinctrl-8 = <&d5_gpio_pulldown>;
+
+	pinctrl-9 = <&d6_ehrpwm2_a>;
+	pinctrl-10 = <&d6_gpio>;
+	pinctrl-11 = <&d6_gpio_pullup>;
+	pinctrl-12 = <&d6_gpio_pulldown>;
+
+	pinctrl-13 = <&d7_ehrpwm3_a>;
+	pinctrl-14 = <&d7_gpio>;
+	pinctrl-15 = <&d7_gpio_pullup>;
+	pinctrl-16 = <&d7_gpio_pulldown>;
+
+	pinctrl-17 = <&d8_ehrpwm4_a>;
+	pinctrl-18 = <&d8_gpio>;
+	pinctrl-19 = <&d8_gpio_pullup>;
+	pinctrl-20 = <&d8_gpio_pulldown>;
+
+	pinctrl-21 = <&d9_ehrpwm5_a>;
+	pinctrl-22 = <&d9_gpio>;
+	pinctrl-23 = <&d9_gpio_pullup>;
+	pinctrl-24 = <&d9_gpio_pulldown>;
+
+	d4_ehrpwm0_a: d4-ehrpwm0-a-pins {
+		pinctrl-single,pins = <
+			/* (AG18) EHRPWM0_A */
+			AM65X_IOPAD(0x0084, PIN_OUTPUT, 5)
+		>;
+	};
+
+	d4_gpio: d4-gpio-pins {
+		pinctrl-single,pins = <
+			/* (AG18) GPIO0_33 */
+			AM65X_IOPAD(0x0084, PIN_INPUT, 7)
+		>;
+	};
+
+	d4_gpio_pullup: d4-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (AG18) GPIO0_33 */
+			AM65X_IOPAD(0x0084, PIN_INPUT_PULLUP, 7)
+		>;
+	};
+
+	d4_gpio_pulldown: d4-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (AG18) GPIO0_33 */
+			AM65X_IOPAD(0x0084, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d5_ehrpwm1_a: d5-ehrpwm1-a-pins {
+		pinctrl-single,pins = <
+			/* (AF17) EHRPWM1_A */
+			AM65X_IOPAD(0x008C, PIN_OUTPUT, 5)
+		>;
+	};
+
+	d5_gpio: d5-gpio-pins {
+		pinctrl-single,pins = <
+			/* (AF17) GPIO0_35 */
+			AM65X_IOPAD(0x008C, PIN_INPUT, 7)
+		>;
+	};
+
+	d5_gpio_pullup: d5-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (AF17) GPIO0_35 */
+			AM65X_IOPAD(0x008C, PIN_INPUT_PULLUP, 7)
+		>;
+	};
+
+	d5_gpio_pulldown: d5-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (AF17) GPIO0_35 */
+			AM65X_IOPAD(0x008C, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d6_ehrpwm2_a: d6-ehrpwm2-a-pins {
+		pinctrl-single,pins = <
+			/* (AH16) EHRPWM2_A */
+			AM65X_IOPAD(0x0098, PIN_OUTPUT, 5)
+		>;
+	};
+
+	d6_gpio: d6-gpio-pins {
+		pinctrl-single,pins = <
+			/* (AH16) GPIO0_38 */
+			AM65X_IOPAD(0x0098, PIN_INPUT, 7)
+		>;
+	};
+
+	d6_gpio_pullup: d6-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (AH16) GPIO0_38 */
+			AM65X_IOPAD(0x0098, PIN_INPUT_PULLUP, 7)
+		>;
+	};
+
+	d6_gpio_pulldown: d6-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (AH16) GPIO0_38 */
+			AM65X_IOPAD(0x0098, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d7_ehrpwm3_a: d7-ehrpwm3-a-pins {
+		pinctrl-single,pins = <
+			/* (AH15) EHRPWM3_A */
+			AM65X_IOPAD(0x00AC, PIN_OUTPUT, 5)
+		>;
+	};
+
+	d7_gpio: d7-gpio-pins {
+		pinctrl-single,pins = <
+			/* (AH15) GPIO0_43 */
+			AM65X_IOPAD(0x00AC, PIN_INPUT, 7)
+		>;
+	};
+
+	d7_gpio_pullup: d7-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (AH15) GPIO0_43 */
+			AM65X_IOPAD(0x00AC, PIN_INPUT_PULLUP, 7)
+		>;
+	};
+
+	d7_gpio_pulldown: d7-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (AH15) GPIO0_43 */
+			AM65X_IOPAD(0x00AC, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d8_ehrpwm4_a: d8-ehrpwm4-a-pins {
+		pinctrl-single,pins = <
+			/* (AG15) EHRPWM4_A */
+			AM65X_IOPAD(0x00C0, PIN_OUTPUT, 5)
+		>;
+	};
+
+	d8_gpio: d8-gpio-pins {
+		pinctrl-single,pins = <
+			/* (AG15) GPIO0_48 */
+			AM65X_IOPAD(0x00C0, PIN_INPUT, 7)
+		>;
+	};
+
+	d8_gpio_pullup: d8-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (AG15) GPIO0_48 */
+			AM65X_IOPAD(0x00C0, PIN_INPUT_PULLUP, 7)
+		>;
+	};
+
+	d8_gpio_pulldown: d8-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (AG15) GPIO0_48 */
+			AM65X_IOPAD(0x00C0, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d9_ehrpwm5_a: d9-ehrpwm5-a-pins {
+		pinctrl-single,pins = <
+			/* (AD15) EHRPWM5_A */
+			AM65X_IOPAD(0x00CC, PIN_OUTPUT, 5)
+		>;
+	};
+
+	d9_gpio: d9-gpio-pins {
+		pinctrl-single,pins = <
+			/* (AD15) GPIO0_51 */
+			AM65X_IOPAD(0x00CC, PIN_INPUT, 7)
+		>;
+	};
+
+	d9_gpio_pullup: d9-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (AD15) GPIO0_51 */
+			AM65X_IOPAD(0x00CC, PIN_INPUT_PULLUP, 7)
+		>;
+	};
+
+	d9_gpio_pulldown: d9-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (AD15) GPIO0_51 */
+			AM65X_IOPAD(0x00CC, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	main_pcie_enable_pins_default: main-pcie-enable-default-pins {
+		pinctrl-single,pins = <
+			AM65X_IOPAD(0x01c4, PIN_INPUT_PULLUP, 7)  /* (AH13) GPIO1_17 */
+		>;
+	};
+
 	main_uart1_pins_default: main-uart1-default-pins {
 		pinctrl-single,pins = <
 			AM65X_IOPAD(0x0174, PIN_INPUT,  6)  /* (AE23) UART1_RXD */
@@ -273,17 +971,6 @@
 		>;
 	};
 
-	arduino_io_d4_to_d9_pins_default: arduino-io-d4-to-d9-default-pins {
-		pinctrl-single,pins = <
-			AM65X_IOPAD(0x0084, PIN_OUTPUT, 7)  /* (AG18) GPIO0_33 */
-			AM65X_IOPAD(0x008C, PIN_OUTPUT, 7)  /* (AF17) GPIO0_35 */
-			AM65X_IOPAD(0x0098, PIN_OUTPUT, 7)  /* (AH16) GPIO0_38 */
-			AM65X_IOPAD(0x00AC, PIN_OUTPUT, 7)  /* (AH15) GPIO0_43 */
-			AM65X_IOPAD(0x00C0, PIN_OUTPUT, 7)  /* (AG15) GPIO0_48 */
-			AM65X_IOPAD(0x00CC, PIN_OUTPUT, 7)  /* (AD15) GPIO0_51 */
-		>;
-	};
-
 	dss_vout1_pins_default: dss-vout1-default-pins {
 		pinctrl-single,pins = <
 			AM65X_IOPAD(0x0000, PIN_OUTPUT, 1)  /* VOUT1_DATA0 */
@@ -329,6 +1016,43 @@
 			AM65X_IOPAD(0x0070, PIN_INPUT,  5)  /* (R25) I2C2_SDA */
 		>;
 	};
+
+	icssg0_mdio_pins_default: icssg0-mdio-default-pins {
+		pinctrl-single,pins = <
+			AM65X_IOPAD(0x0294, PIN_INPUT, 0) /* (AE26) PRG0_MDIO0_MDIO */
+			AM65X_IOPAD(0x0298, PIN_OUTPUT, 0) /* (AE28) PRG0_MDIO0_MDC */
+		>;
+	};
+
+	icssg0_rgmii_pins_default: icssg0-rgmii-default-pins {
+		pinctrl-single,pins = <
+			AM65X_IOPAD(0x0244, PIN_INPUT, 2) /* (AB28) PRG0_PRU1_GPO0.PRG0_RGMII2_RD0 */
+			AM65X_IOPAD(0x0248, PIN_INPUT, 2) /* (AC28) PRG0_PRU1_GPO1.PRG0_RGMII2_RD1 */
+			AM65X_IOPAD(0x024c, PIN_INPUT, 2) /* (AC27) PRG0_PRU1_GPO2.PRG0_RGMII2_RD2 */
+			AM65X_IOPAD(0x0250, PIN_INPUT, 2) /* (AB26) PRG0_PRU1_GPO3.PRG0_RGMII2_RD3 */
+			AM65X_IOPAD(0x0274, PIN_OUTPUT, 2) /* (AC25) PRG0_PRU1_GPO12.PRG0_RGMII2_TD0 */
+			AM65X_IOPAD(0x0278, PIN_OUTPUT, 2) /* (AD25) PRG0_PRU1_GPO13.PRG0_RGMII2_TD1 */
+			AM65X_IOPAD(0x027c, PIN_OUTPUT, 2) /* (AD24) PRG0_PRU1_GPO14.PRG0_RGMII2_TD2 */
+			AM65X_IOPAD(0x0280, PIN_OUTPUT, 2) /* (AE27) PRG0_PRU1_GPO15.PRG0_RGMII2_TD3 */
+			AM65X_IOPAD(0x0284, PIN_INPUT, 2) /* (AC24) PRG0_PRU1_GPO16.PRG0_RGMII2_TXC */
+			AM65X_IOPAD(0x0270, PIN_OUTPUT, 2) /* (AB24) PRG0_PRU1_GPO11.PRG0_RGMII2_TX_CTL */
+			AM65X_IOPAD(0x025c, PIN_INPUT, 2) /* (AB27) PRG0_PRU1_GPO6.PRG0_RGMII2_RXC */
+			AM65X_IOPAD(0x0254, PIN_INPUT, 2) /* (AA25) PRG0_PRU1_GPO4.PRG0_RGMII2_RX_CTL */
+
+			AM65X_IOPAD(0x01f4, PIN_INPUT, 2) /* (V24) PRG0_PRU0_GPO0.PRG0_RGMII1_RD0 */
+			AM65X_IOPAD(0x01f8, PIN_INPUT, 2) /* (W25) PRG0_PRU0_GPO1.PRG0_RGMII1_RD1 */
+			AM65X_IOPAD(0x01fc, PIN_INPUT, 2) /* (W24) PRG0_PRU0_GPO2.PRG0_RGMII1_RD2 */
+			AM65X_IOPAD(0x0200, PIN_INPUT, 2) /* (AA27) PRG0_PRU0_GPO3.PRG0_RGMII1_RD3 */
+			AM65X_IOPAD(0x0224, PIN_OUTPUT, 2) /* (AD27) PRG0_PRU0_GPO12.PRG0_RGMII1_TD0 */
+			AM65X_IOPAD(0x0228, PIN_OUTPUT, 2) /* (AC26) PRG0_PRU0_GPO13.PRG0_RGMII1_TD1 */
+			AM65X_IOPAD(0x022c, PIN_OUTPUT, 2) /* (AD26) PRG0_PRU0_GPO14.PRG0_RGMII1_TD2 */
+			AM65X_IOPAD(0x0230, PIN_OUTPUT, 2) /* (AA24) PRG0_PRU0_GPO15.PRG0_RGMII1_TD3 */
+			AM65X_IOPAD(0x0234, PIN_INPUT, 2) /* (AD28) PRG0_PRU0_GPO16.PRG0_RGMII1_TXC */
+			AM65X_IOPAD(0x0220, PIN_OUTPUT, 2) /* (AB25) PRG0_PRU0_GPO11.PRG0_RGMII1_TX_CTL */
+			AM65X_IOPAD(0x020c, PIN_INPUT, 2) /* (Y25) PRG0_PRU0_GPO6.PRG0_RGMII1_RXC */
+			AM65X_IOPAD(0x0204, PIN_INPUT, 2) /* (Y24) PRG0_PRU0_GPO4.PRG0_RGMII1_RX_CTL */
+		>;
+	};
 };
 
 &main_pmx1 {
@@ -345,12 +1069,6 @@
 			AM65X_IOPAD(0x000c, PIN_INPUT,  0)  /* (E21) I2C1_SDA */
 		>;
 	};
-
-	ecap0_pins_default: ecap0-default-pins {
-		pinctrl-single,pins = <
-			AM65X_IOPAD(0x0010, PIN_INPUT,  0)  /* (D21) ECAP0_IN_APWM_OUT */
-		>;
-	};
 };
 
 &wkup_uart0 {
@@ -366,13 +1084,9 @@
 
 &mcu_uart0 {
 	status = "okay";
-	pinctrl-names = "default";
-	pinctrl-0 = <&arduino_uart_pins_default>;
 };
 
 &main_gpio0 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&arduino_io_d4_to_d9_pins_default>;
 	gpio-line-names =
 		"main_gpio0-base", "", "", "", "", "", "", "", "", "",
 		"", "", "", "", "", "", "", "", "", "",
@@ -382,10 +1096,14 @@
 		"", "IO9";
 };
 
+&main_gpio1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_pcie_enable_pins_default>;
+};
+
 &wkup_gpio0 {
 	pinctrl-names = "default";
 	pinctrl-0 =
-		<&arduino_io_d2_to_d3_pins_default>,
 		<&arduino_i2c_aio_switch_pins_default>,
 		<&arduino_io_oe_pins_default>,
 		<&push_button_pins_default>,
@@ -547,13 +1265,8 @@
 	status = "disabled";
 };
 
-&ecap0 {
-	status = "okay";
-	pinctrl-names = "default";
-	pinctrl-0 = <&ecap0_pins_default>;
-};
-
 &sdhci1 {
+	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_mmc1_pins_default>;
 	ti,driver-strength-ohm = <50>;
@@ -574,9 +1287,6 @@
 
 &mcu_spi0 {
 	status = "okay";
-	pinctrl-names = "default";
-	pinctrl-0 = <&mcu_spi0_pins_default>;
-
 	#address-cells = <1>;
 	#size-cells = <0>;
 	ti,pindir-d0-out-d1-in;
@@ -716,3 +1426,21 @@
 			<&mcu_r5fss0_core1_memory_region>;
 	mboxes = <&mailbox0_cluster1>, <&mbox_mcu_r5fss0_core1>;
 };
+
+&icssg0_mdio {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&icssg0_mdio_pins_default>;
+
+	icssg0_eth0_phy: ethernet-phy@0 {
+		reg = <0>;
+		ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_00_NS>;
+		ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_4_B_NIB>;
+	};
+
+	icssg0_eth1_phy: ethernet-phy@1 {
+		reg = <1>;
+		ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_00_NS>;
+		ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_4_B_NIB>;
+	};
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi
index 5ebb87f467de..fcea54465636 100644
--- a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi
@@ -449,6 +449,7 @@
 		ti,otap-del-sel-hs400 = <0x0>;
 		ti,trm-icp = <0x8>;
 		dma-coherent;
+		status = "disabled";
 	};
 
 	sdhci1: mmc@4fa0000 {
@@ -471,6 +472,7 @@
 		ti,clkbuf-sel = <0x7>;
 		ti,trm-icp = <0x8>;
 		dma-coherent;
+		status = "disabled";
 	};
 
 	scm_conf: scm-conf@100000 {
@@ -498,8 +500,8 @@
 		};
 
 		dss_oldi_io_ctrl: dss-oldi-io-ctrl@41e0 {
-			compatible = "syscon";
-			reg = <0x000041e0 0x14>;
+			compatible = "ti,am654-dss-oldi-io-ctrl", "syscon";
+			reg = <0x41e0 0x14>;
 		};
 
 		ehrpwm_tbclk: clock-controller@4140 {
@@ -790,8 +792,12 @@
 			compatible = "ti,am654-navss-main-udmap";
 			reg = <0x0 0x31150000 0x0 0x100>,
 			      <0x0 0x34000000 0x0 0x100000>,
-			      <0x0 0x35000000 0x0 0x100000>;
-			reg-names = "gcfg", "rchanrt", "tchanrt";
+			      <0x0 0x35000000 0x0 0x100000>,
+			      <0x0 0x30b00000 0x0 0x10000>,
+			      <0x0 0x30c00000 0x0 0x10000>,
+			      <0x0 0x30d00000 0x0 0x8000>;
+			reg-names = "gcfg", "rchanrt", "tchanrt",
+				    "tchan", "rchan", "rflow";
 			msi-parent = <&inta_main_udmass>;
 			#dma-cells = <1>;
 
@@ -1034,7 +1040,7 @@
 		assigned-clocks = <&k3_clks 67 2>;
 		assigned-clock-parents = <&k3_clks 67 5>;
 
-		interrupts = <GIC_SPI 166 IRQ_TYPE_EDGE_RISING>;
+		interrupts = <GIC_SPI 166 IRQ_TYPE_LEVEL_HIGH>;
 
 		dma-coherent;
 
diff --git a/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi b/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi
index edd5cfbec40e..ecd7356f3315 100644
--- a/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi
@@ -214,8 +214,12 @@
 			compatible = "ti,am654-navss-mcu-udmap";
 			reg = <0x0 0x285c0000 0x0 0x100>,
 			      <0x0 0x2a800000 0x0 0x40000>,
-			      <0x0 0x2aa00000 0x0 0x40000>;
-			reg-names = "gcfg", "rchanrt", "tchanrt";
+			      <0x0 0x2aa00000 0x0 0x40000>,
+			      <0x0 0x284a0000 0x0 0x4000>,
+			      <0x0 0x284c0000 0x0 0x4000>,
+			      <0x0 0x28400000 0x0 0x2000>;
+			reg-names = "gcfg", "rchanrt", "tchanrt",
+				    "tchan", "rchan", "rflow";
 			msi-parent = <&inta_main_udmass>;
 			#dma-cells = <1>;
 
diff --git a/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi
index fd2b998ebddc..f037b36243ce 100644
--- a/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi
@@ -34,9 +34,16 @@
 		};
 	};
 
-	chipid@43000014 {
-		compatible = "ti,am654-chipid";
-		reg = <0x43000014 0x4>;
+	wkup_conf: bus@43000000 {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x0 0x43000000 0x20000>;
+
+		chipid: chipid@14 {
+			compatible = "ti,am654-chipid";
+			reg = <0x14 0x4>;
+		};
 	};
 
 	wkup_pmx0: pinctrl@4301c000 {
diff --git a/arch/arm64/boot/dts/ti/k3-am652.dtsi b/arch/arm64/boot/dts/ti/k3-am652.dtsi
new file mode 100644
index 000000000000..0f22e00faa90
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am652.dtsi
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Device Tree Source for AM65 SoC family in Dual core configuration
+ *
+ * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ */
+
+#include "k3-am65.dtsi"
+
+/ {
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		cpu-map {
+			cluster0: cluster0 {
+				core0 {
+					cpu = <&cpu0>;
+				};
+
+				core1 {
+					cpu = <&cpu1>;
+				};
+			};
+		};
+
+		cpu0: cpu@0 {
+			compatible = "arm,cortex-a53";
+			reg = <0x000>;
+			device_type = "cpu";
+			enable-method = "psci";
+			i-cache-size = <0x8000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>;
+			d-cache-size = <0x8000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <128>;
+			next-level-cache = <&L2_0>;
+		};
+
+		cpu1: cpu@1 {
+			compatible = "arm,cortex-a53";
+			reg = <0x001>;
+			device_type = "cpu";
+			enable-method = "psci";
+			i-cache-size = <0x8000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>;
+			d-cache-size = <0x8000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <128>;
+			next-level-cache = <&L2_0>;
+		};
+	};
+
+	L2_0: l2-cache0 {
+		compatible = "cache";
+		cache-level = <2>;
+		cache-unified;
+		cache-size = <0x80000>;
+		cache-line-size = <64>;
+		cache-sets = <512>;
+		next-level-cache = <&msmc_l3>;
+	};
+
+	msmc_l3: l3-cache0 {
+		compatible = "cache";
+		cache-level = <3>;
+		cache-unified;
+	};
+
+	thermal_zones: thermal-zones {
+		#include "k3-am654-industrial-thermal.dtsi"
+	};
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am6528-iot2050-basic-common.dtsi b/arch/arm64/boot/dts/ti/k3-am6528-iot2050-basic-common.dtsi
index 5ab434c02ab6..1d6cddb11991 100644
--- a/arch/arm64/boot/dts/ti/k3-am6528-iot2050-basic-common.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am6528-iot2050-basic-common.dtsi
@@ -9,6 +9,7 @@
  * Common bits of the IOT2050 Basic variant, PG1 and PG2
  */
 
+#include "k3-am652.dtsi"
 #include "k3-am65-iot2050-common.dtsi"
 
 / {
@@ -17,21 +18,6 @@
 		/* 1G RAM */
 		reg = <0x00000000 0x80000000 0x00000000 0x40000000>;
 	};
-
-	cpus {
-		cpu-map {
-			/delete-node/ cluster1;
-		};
-		/delete-node/ cpu@100;
-		/delete-node/ cpu@101;
-	};
-
-	/delete-node/ l2-cache1;
-};
-
-/* eMMC */
-&sdhci0 {
-	status = "disabled";
 };
 
 &main_pmx0 {
diff --git a/arch/arm64/boot/dts/ti/k3-am654-base-board.dts b/arch/arm64/boot/dts/ti/k3-am654-base-board.dts
index 1637ec5ab5ed..822c288d2797 100644
--- a/arch/arm64/boot/dts/ti/k3-am654-base-board.dts
+++ b/arch/arm64/boot/dts/ti/k3-am654-base-board.dts
@@ -449,6 +449,7 @@
 };
 
 &sdhci0 {
+	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_mmc0_pins_default>;
 	bus-width = <8>;
@@ -463,6 +464,7 @@
  * disable sdhci1
  */
 &sdhci1 {
+	status = "okay";
 	vmmc-supply = <&vdd_mmc1_sd>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_mmc1_pins_default>;
diff --git a/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-common.dtsi b/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-common.dtsi
index be55494b1f3f..3864ec54e371 100644
--- a/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-common.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-common.dtsi
@@ -11,6 +11,7 @@
 
 /dts-v1/;
 
+#include "k3-am654.dtsi"
 #include "k3-am65-iot2050-common.dtsi"
 
 / {
@@ -43,6 +44,7 @@
 
 /* eMMC */
 &sdhci0 {
+	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_mmc0_pins_default>;
 	bus-width = <8>;
diff --git a/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-m2.dts b/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-m2.dts
index 774eb14ac907..bd6f2e696e94 100644
--- a/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-m2.dts
+++ b/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-m2.dts
@@ -27,12 +27,6 @@
 };
 
 &main_pmx0 {
-	main_m2_enable_pins_default: main-m2-enable-default-pins {
-		pinctrl-single,pins = <
-			AM65X_IOPAD(0x01c4, PIN_INPUT_PULLUP, 7)  /* (AH13) GPIO1_17 */
-		>;
-	};
-
 	main_bkey_pcie_reset: main-bkey-pcie-reset-default-pins {
 		pinctrl-single,pins = <
 			AM65X_IOPAD(0x01bc, PIN_OUTPUT_PULLUP, 7)  /* (AG13) GPIO1_15 */
@@ -66,15 +60,13 @@
 
 &main_gpio0 {
 	pinctrl-names = "default";
-	pinctrl-0 =
-		<&main_m2_pcie_mux_control>,
-		<&arduino_io_d4_to_d9_pins_default>;
+	pinctrl-0 = <&main_m2_pcie_mux_control>;
 };
 
 &main_gpio1 {
 	pinctrl-names = "default";
 	pinctrl-0 =
-		<&main_m2_enable_pins_default>,
+		<&main_pcie_enable_pins_default>,
 		<&main_pmx0_m2_config_pins_default>,
 		<&main_pmx1_m2_config_pins_default>,
 		<&cp2102n_reset_pin_default>;
diff --git a/arch/arm64/boot/dts/ti/k3-am68-sk-base-board.dts b/arch/arm64/boot/dts/ti/k3-am68-sk-base-board.dts
index 1e1a82f9d2b8..d0cfdeac21fb 100644
--- a/arch/arm64/boot/dts/ti/k3-am68-sk-base-board.dts
+++ b/arch/arm64/boot/dts/ti/k3-am68-sk-base-board.dts
@@ -31,6 +31,7 @@
 		can1 = &mcu_mcan1;
 		can2 = &main_mcan6;
 		can3 = &main_mcan7;
+		ethernet0 = &cpsw_port1;
 	};
 
 	vusb_main: regulator-vusb-main5v0 {
diff --git a/arch/arm64/boot/dts/ti/k3-am69-sk.dts b/arch/arm64/boot/dts/ti/k3-am69-sk.dts
index 9868c7049bfb..8da591579868 100644
--- a/arch/arm64/boot/dts/ti/k3-am69-sk.dts
+++ b/arch/arm64/boot/dts/ti/k3-am69-sk.dts
@@ -433,6 +433,13 @@
 
 &wkup_pmx2 {
 	bootph-all;
+	pmic_irq_pins_default: pmic-irq-default-pins {
+		pinctrl-single,pins = <
+			/* (AA37) MCU_ADC1_AIN4.WKUP_GPIO0_83 */
+			J784S4_WKUP_IOPAD(0x0fc, PIN_INPUT, 7)
+		>;
+	};
+
 	wkup_uart0_pins_default: wkup-uart0-default-pins {
 		bootph-all;
 		pinctrl-single,pins = <
@@ -631,6 +638,93 @@
 		compatible = "atmel,24c512";
 		reg = <0x51>;
 	};
+
+	tps659413: pmic@48 {
+		compatible = "ti,tps6594-q1";
+		reg = <0x48>;
+		system-power-controller;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_irq_pins_default>;
+		interrupt-parent = <&wkup_gpio0>;
+		interrupts = <39 IRQ_TYPE_EDGE_FALLING>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		ti,primary-pmic;
+		buck12-supply = <&vsys_3v3>;
+		buck3-supply = <&vsys_3v3>;
+		buck4-supply = <&vsys_3v3>;
+		buck5-supply = <&vsys_3v3>;
+		ldo1-supply = <&vsys_3v3>;
+		ldo2-supply = <&vsys_3v3>;
+		ldo3-supply = <&vsys_3v3>;
+		ldo4-supply = <&vsys_3v3>;
+
+		regulators {
+			bucka12: buck12 {
+				regulator-name = "vdd_ddr_1v1";
+				regulator-min-microvolt = <1100000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			bucka3: buck3 {
+				regulator-name = "vdd_ram_0v85";
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			bucka4: buck4 {
+				regulator-name = "vdd_io_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			bucka5: buck5 {
+				regulator-name = "vdd_mcu_0v85";
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa1: ldo1 {
+				regulator-name = "vdd_mcuio_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa2: ldo2 {
+				regulator-name = "vdd_mcuio_3v3";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa3: ldo3 {
+				regulator-name = "vds_dll_0v8";
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa4: ldo4 {
+				regulator-name = "vda_mcu_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+		};
+	};
 };
 
 &wkup_gpio0 {
@@ -671,7 +765,7 @@
 		reg = <0x21>;
 		gpio-controller;
 		#gpio-cells = <2>;
-		gpio-line-names	= "BOARDID_EEPROM_WP", "CAN_STB", "GPIO_uSD_PWR_EN",
+		gpio-line-names = "BOARDID_EEPROM_WP", "CAN_STB", "GPIO_uSD_PWR_EN",
 				"IO_EXP_MCU_RGMII_RST#", "IO_EXP_PCIe0_4L_PERST#",
 				"IO_EXP_PCIe1_M.2_RTSz", "IO_EXP_PCIe3_M.2_RTSz",
 				"PM_INA_BUS_EN", "ENET1_EXP_PWRDN", "EXP1_ENET_RSTz",
diff --git a/arch/arm64/boot/dts/ti/k3-j7200-main.dtsi b/arch/arm64/boot/dts/ti/k3-j7200-main.dtsi
index 264913f83287..da67bf8fe703 100644
--- a/arch/arm64/boot/dts/ti/k3-j7200-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j7200-main.dtsi
@@ -281,8 +281,12 @@
 			compatible = "ti,j721e-navss-main-udmap";
 			reg = <0x00 0x31150000 0x00 0x100>,
 			      <0x00 0x34000000 0x00 0x100000>,
-			      <0x00 0x35000000 0x00 0x100000>;
-			reg-names = "gcfg", "rchanrt", "tchanrt";
+			      <0x00 0x35000000 0x00 0x100000>,
+			      <0x00 0x30b00000 0x00 0x4000>,
+			      <0x00 0x30c00000 0x00 0x4000>,
+			      <0x00 0x30d00000 0x00 0x4000>;
+			reg-names = "gcfg", "rchanrt", "tchanrt",
+				    "tchan", "rchan", "rflow";
 			msi-parent = <&main_udmass_inta>;
 			#dma-cells = <1>;
 
@@ -647,6 +651,7 @@
 		ti,otap-del-sel-hs400 = <0x5>;
 		ti,itap-del-sel-legacy = <0x10>;
 		ti,itap-del-sel-mmc-hs = <0xa>;
+		ti,itap-del-sel-ddr52 = <0x3>;
 		ti,strobe-sel = <0x77>;
 		ti,clkbuf-sel = <0x7>;
 		ti,trm-icp = <0x8>;
diff --git a/arch/arm64/boot/dts/ti/k3-j7200-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j7200-mcu-wakeup.dtsi
index 3fc588b848c6..60b26374ae0c 100644
--- a/arch/arm64/boot/dts/ti/k3-j7200-mcu-wakeup.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j7200-mcu-wakeup.dtsi
@@ -178,9 +178,16 @@
 		};
 	};
 
-	chipid@43000014 {
-		compatible = "ti,am654-chipid";
-		reg = <0x00 0x43000014 0x00 0x4>;
+	wkup_conf: bus@43000000 {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x0 0x00 0x43000000 0x20000>;
+
+		chipid: chipid@14 {
+			compatible = "ti,am654-chipid";
+			reg = <0x14 0x4>;
+		};
 	};
 
 	/* MCU_TIMERIO pad input CTRLMMR_MCU_TIMER*_CTRL registers */
@@ -346,8 +353,12 @@
 			compatible = "ti,j721e-navss-mcu-udmap";
 			reg = <0x00 0x285c0000 0x00 0x100>,
 			      <0x00 0x2a800000 0x00 0x40000>,
-			      <0x00 0x2aa00000 0x00 0x40000>;
-			reg-names = "gcfg", "rchanrt", "tchanrt";
+			      <0x00 0x2aa00000 0x00 0x40000>,
+			      <0x00 0x284a0000 0x00 0x4000>,
+			      <0x00 0x284c0000 0x00 0x4000>,
+			      <0x00 0x28400000 0x00 0x2000>;
+			reg-names = "gcfg", "rchanrt", "tchanrt",
+				    "tchan", "rchan", "rflow";
 			msi-parent = <&main_udmass_inta>;
 			#dma-cells = <1>;
 
diff --git a/arch/arm64/boot/dts/ti/k3-j7200-som-p0.dtsi b/arch/arm64/boot/dts/ti/k3-j7200-som-p0.dtsi
index 5a300d4c8ba0..ea47f10d393a 100644
--- a/arch/arm64/boot/dts/ti/k3-j7200-som-p0.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j7200-som-p0.dtsi
@@ -127,6 +127,14 @@
 	};
 };
 
+&wkup_pmx3 {
+	pmic_irq_pins_default: pmic-irq-default-pins {
+		pinctrl-single,pins = <
+			J721E_WKUP_IOPAD(0x01c, PIN_INPUT, 7) /* (E18) WKUP_GPIO0_84 */
+		>;
+	};
+};
+
 &main_pmx0 {
 	main_i2c0_pins_default: main-i2c0-default-pins {
 		pinctrl-single,pins = <
@@ -264,6 +272,151 @@
 		compatible = "atmel,24c256";
 		reg = <0x50>;
 	};
+
+	tps659414: pmic@48 {
+		compatible = "ti,tps6594-q1";
+		reg = <0x48>;
+		system-power-controller;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_irq_pins_default>;
+		interrupt-parent = <&wkup_gpio0>;
+		interrupts = <84 IRQ_TYPE_EDGE_FALLING>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		ti,primary-pmic;
+		buck1-supply = <&vsys_3v3>;
+		buck2-supply = <&vsys_3v3>;
+		buck3-supply = <&vsys_3v3>;
+		buck4-supply = <&vsys_3v3>;
+		buck5-supply = <&vsys_3v3>;
+		ldo1-supply = <&vsys_3v3>;
+		ldo2-supply = <&vsys_3v3>;
+		ldo3-supply = <&vsys_3v3>;
+		ldo4-supply = <&vsys_3v3>;
+
+		regulators {
+			bucka1: buck1 {
+				regulator-name = "vda_mcu_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			bucka2: buck2 {
+				regulator-name = "vdd_mcuio_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			bucka3: buck3 {
+				regulator-name = "vdd_mcu_0v85";
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			bucka4: buck4 {
+				regulator-name = "vdd_ddr_1v1";
+				regulator-min-microvolt = <1100000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			bucka5: buck5 {
+				regulator-name = "vdd_phyio_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa1: ldo1 {
+				regulator-name = "vdd1_lpddr4_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa2: ldo2 {
+				regulator-name = "vda_dll_0v8";
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa3: ldo3 {
+				regulator-name = "vdd_wk_0v8";
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa4: ldo4 {
+				regulator-name = "vda_pll_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+		};
+	};
+
+	lp876441: pmic@4c {
+		compatible = "ti,lp8764-q1";
+		reg = <0x4c>;
+		system-power-controller;
+		interrupt-parent = <&wkup_gpio0>;
+		interrupts = <84 IRQ_TYPE_EDGE_FALLING>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		buck1-supply = <&vsys_3v3>;
+		buck2-supply = <&vsys_3v3>;
+		buck3-supply = <&vsys_3v3>;
+		buck4-supply = <&vsys_3v3>;
+
+		regulators: regulators {
+			buckb1: buck1 {
+				regulator-name = "vdd_cpu_avs";
+				regulator-min-microvolt = <600000>;
+				regulator-max-microvolt = <900000>;
+				regulator-always-on;
+				regulator-boot-on;
+				bootph-pre-ram;
+			};
+
+			buckb2: buck2 {
+				regulator-name = "vdd_ram_0v85";
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			buckb3: buck3 {
+				regulator-name = "vdd_core_0v85";
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			buckb4: buck4 {
+				regulator-name = "vdd_io_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+		};
+	};
 };
 
 &ospi0 {
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-evm-pcie0-ep.dtso b/arch/arm64/boot/dts/ti/k3-j721e-evm-pcie0-ep.dtso
new file mode 100644
index 000000000000..0c82a13b65a4
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-j721e-evm-pcie0-ep.dtso
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+/**
+ * DT Overlay for enabling PCIE0 instance in Endpoint Configuration with the
+ * J7 common processor board.
+ *
+ * J7 Common Processor Board Product Link: https://www.ti.com/tool/J721EXCPXEVM
+ *
+ * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/soc/ti,sci_pm_domain.h>
+
+#include "k3-pinctrl.h"
+
+/*
+ * Since Root Complex and Endpoint modes are mutually exclusive
+ * disable Root Complex mode.
+ */
+&pcie0_rc {
+	status = "disabled";
+};
+
+&cbass_main {
+	#address-cells = <2>;
+	#size-cells = <2>;
+	interrupt-parent = <&gic500>;
+
+	pcie0_ep: pcie-ep@2900000 {
+		compatible = "ti,j721e-pcie-ep";
+		reg = <0x00 0x02900000 0x00 0x1000>,
+		      <0x00 0x02907000 0x00 0x400>,
+		      <0x00 0x0d000000 0x00 0x00800000>,
+		      <0x00 0x10000000 0x00 0x08000000>;
+		reg-names = "intd_cfg", "user_cfg", "reg", "mem";
+		interrupt-names = "link_state";
+		interrupts = <GIC_SPI 318 IRQ_TYPE_EDGE_RISING>;
+		ti,syscon-pcie-ctrl = <&scm_conf 0x4070>;
+		max-link-speed = <3>;
+		num-lanes = <1>;
+		power-domains = <&k3_pds 239 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 239 1>;
+		clock-names = "fck";
+		max-functions = /bits/ 8 <6>;
+		max-virtual-functions = /bits/ 8 <4 4 4 4 0 0>;
+		dma-coherent;
+		phys = <&serdes0_pcie_link>;
+		phy-names = "pcie-phy";
+	};
+};
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi
index 746b9f8b1c64..2569b4c08ffb 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi
@@ -382,8 +382,12 @@
 			compatible = "ti,j721e-navss-main-udmap";
 			reg = <0x0 0x31150000 0x0 0x100>,
 			      <0x0 0x34000000 0x0 0x100000>,
-			      <0x0 0x35000000 0x0 0x100000>;
-			reg-names = "gcfg", "rchanrt", "tchanrt";
+			      <0x0 0x35000000 0x0 0x100000>,
+			      <0x0 0x30b00000 0x0 0x20000>,
+			      <0x0 0x30c00000 0x0 0x10000>,
+			      <0x0 0x30d00000 0x0 0x8000>;
+			reg-names = "gcfg", "rchanrt", "tchanrt",
+				    "tchan", "rchan", "rflow";
 			msi-parent = <&main_udmass_inta>;
 			#dma-cells = <1>;
 
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi
index f7ab7719fc07..a74912d9e4da 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi
@@ -48,9 +48,16 @@
 		};
 	};
 
-	chipid@43000014 {
-		compatible = "ti,am654-chipid";
-		reg = <0x0 0x43000014 0x0 0x4>;
+	wkup_conf: bus@43000000 {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x0 0x00 0x43000000 0x20000>;
+
+		chipid: chipid@14 {
+			compatible = "ti,am654-chipid";
+			reg = <0x14 0x4>;
+		};
 	};
 
 	wkup_pmx0: pinctrl@4301c000 {
@@ -468,8 +475,12 @@
 			compatible = "ti,j721e-navss-mcu-udmap";
 			reg = <0x0 0x285c0000 0x0 0x100>,
 			      <0x0 0x2a800000 0x0 0x40000>,
-			      <0x0 0x2aa00000 0x0 0x40000>;
-			reg-names = "gcfg", "rchanrt", "tchanrt";
+			      <0x0 0x2aa00000 0x0 0x40000>,
+			      <0x0 0x284a0000 0x0 0x4000>,
+			      <0x0 0x284c0000 0x0 0x4000>,
+			      <0x0 0x28400000 0x0 0x2000>;
+			reg-names = "gcfg", "rchanrt", "tchanrt",
+				    "tchan", "rchan", "rflow";
 			msi-parent = <&main_udmass_inta>;
 			#dma-cells = <1>;
 
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-sk.dts b/arch/arm64/boot/dts/ti/k3-j721e-sk.dts
index 42fe8eee9ec8..188dfe291a32 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-sk.dts
+++ b/arch/arm64/boot/dts/ti/k3-j721e-sk.dts
@@ -459,6 +459,12 @@
 };
 
 &wkup_pmx0 {
+	pmic_irq_pins_default: pmic-irq-default-pins {
+		pinctrl-single,pins = <
+			J721E_WKUP_IOPAD(0x0cc, PIN_INPUT, 7) /* (G28) WKUP_GPIO0_7 */
+		>;
+	};
+
 	mcu_cpsw_pins_default: mcu-cpsw-default-pins {
 		pinctrl-single,pins = <
 			J721E_WKUP_IOPAD(0x84, PIN_INPUT, 0) /* (B24) MCU_RGMII1_RD0 */
@@ -560,6 +566,151 @@
 		compatible = "atmel,24c512";
 		reg = <0x51>;
 	};
+
+	tps659413: pmic@48 {
+		compatible = "ti,tps6594-q1";
+		reg = <0x48>;
+		system-power-controller;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_irq_pins_default>;
+		interrupt-parent = <&wkup_gpio0>;
+		interrupts = <9 IRQ_TYPE_EDGE_FALLING>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		ti,primary-pmic;
+		buck123-supply = <&vsys_3v3>;
+		buck4-supply = <&vsys_3v3>;
+		buck5-supply = <&vsys_3v3>;
+		ldo1-supply = <&vsys_3v3>;
+		ldo2-supply = <&vsys_3v3>;
+		ldo3-supply = <&vsys_3v3>;
+		ldo4-supply = <&vsys_3v3>;
+
+		regulators {
+			bucka123: buck123 {
+				regulator-name = "vdd_cpu_avs";
+				regulator-min-microvolt = <600000>;
+				regulator-max-microvolt = <900000>;
+				regulator-boot-on;
+				regulator-always-on;
+				bootph-pre-ram;
+			};
+
+			bucka4: buck4 {
+				regulator-name = "vdd_mcu_0v85";
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			bucka5: buck5 {
+				regulator-name = "vdd_phyio_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa1: ldo1 {
+				regulator-name = "vdd1_lpddr4_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa2: ldo2 {
+				regulator-name = "vdd_mcuio_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa3: ldo3 {
+				regulator-name = "vdda_dll_0v8";
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa4: ldo4 {
+				regulator-name = "vda_mcu_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+		};
+	};
+
+	tps659411: pmic@4c {
+		compatible = "ti,tps6594-q1";
+		reg = <0x4c>;
+		system-power-controller;
+		interrupt-parent = <&wkup_gpio0>;
+		interrupts = <9 IRQ_TYPE_EDGE_FALLING>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		buck1234-supply = <&vsys_3v3>;
+		buck5-supply = <&vsys_3v3>;
+		ldo1-supply = <&vsys_3v3>;
+		ldo2-supply = <&vsys_3v3>;
+		ldo3-supply = <&vsys_3v3>;
+		ldo4-supply = <&vsys_3v3>;
+
+		regulators {
+			buckb1234: buck1234 {
+				regulator-name = "vdd_core_0v8";
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			buckb5: buck5 {
+				regulator-name = "vdd_ram_0v85";
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldob1: ldo1 {
+				regulator-name = "vdd_sd_dv";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldob2: ldo2 {
+				regulator-name = "vdd_usb_3v3";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldob3: ldo3 {
+				regulator-name = "vdd_io_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldob4: ldo4 {
+				regulator-name = "vda_pll_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+		};
+	};
 };
 
 &mcu_uart0 {
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-som-p0.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-som-p0.dtsi
index 7f0686c2ce37..a75611eec791 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-som-p0.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721e-som-p0.dtsi
@@ -152,6 +152,12 @@
 		>;
 	};
 
+	pmic_irq_pins_default: pmic-irq-default-pins {
+		pinctrl-single,pins = <
+			J721E_WKUP_IOPAD(0x0d4, PIN_INPUT, 7) /* (G26) WKUP_GPIO0_9 */
+		>;
+	};
+
 	mcu_fss0_ospi0_pins_default: mcu-fss0-ospi0-default-pins {
 		pinctrl-single,pins = <
 			J721E_WKUP_IOPAD(0x0000, PIN_OUTPUT, 0) /* MCU_OSPI0_CLK */
@@ -199,6 +205,160 @@
 		compatible = "atmel,24c256";
 		reg = <0x50>;
 	};
+
+	tps659413: pmic@48 {
+		compatible = "ti,tps6594-q1";
+		reg = <0x48>;
+		system-power-controller;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_irq_pins_default>;
+		interrupt-parent = <&wkup_gpio0>;
+		interrupts = <9 IRQ_TYPE_EDGE_FALLING>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		ti,primary-pmic;
+		buck12-supply = <&vsys_3v3>;
+		buck3-supply = <&vsys_3v3>;
+		buck4-supply = <&vsys_3v3>;
+		buck5-supply = <&vsys_3v3>;
+		ldo1-supply = <&vsys_3v3>;
+		ldo2-supply = <&vsys_3v3>;
+		ldo3-supply = <&vsys_3v3>;
+		ldo4-supply = <&vsys_3v3>;
+
+		regulators {
+			bucka12: buck12 {
+				regulator-name = "vdd_cpu_avs";
+				regulator-min-microvolt = <600000>;
+				regulator-max-microvolt = <900000>;
+				regulator-boot-on;
+				regulator-always-on;
+				bootph-pre-ram;
+			};
+
+			bucka3: buck3 {
+				regulator-name = "vdd_mcu_0v85";
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			bucka4: buck4 {
+				regulator-name = "vdd_ddr_1v1";
+				regulator-min-microvolt = <1100000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			bucka5: buck5 {
+				regulator-name = "vdd_phyio_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa1: ldo1 {
+				regulator-name = "vdd1_lpddr4_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa2: ldo2 {
+				regulator-name = "vdd_mcuio_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa3: ldo3 {
+				regulator-name = "vdda_dll_0v8";
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa4: ldo4 {
+				regulator-name = "vda_mcu_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+		};
+	};
+
+	tps659411: pmic@4c {
+		compatible = "ti,tps6594-q1";
+		reg = <0x4c>;
+		system-power-controller;
+		interrupt-parent = <&wkup_gpio0>;
+		interrupts = <9 IRQ_TYPE_EDGE_FALLING>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		buck1234-supply = <&vsys_3v3>;
+		buck5-supply = <&vsys_3v3>;
+		ldo1-supply = <&vsys_3v3>;
+		ldo2-supply = <&vsys_3v3>;
+		ldo3-supply = <&vsys_3v3>;
+		ldo4-supply = <&vsys_3v3>;
+
+		regulators {
+			buckb1234: buck1234 {
+				regulator-name = "vdd_core_0v8";
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			buckb5: buck5 {
+				regulator-name = "vdd_ram_0v85";
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldob1: ldo1 {
+				regulator-name = "vdd_sd_dv";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldob2: ldo2 {
+				regulator-name = "vdd_usb_3v3";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldob3: ldo3 {
+				regulator-name = "vdd_io_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldob4: ldo4 {
+				regulator-name = "vda_pll_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+		};
+	};
 };
 
 &ospi0 {
diff --git a/arch/arm64/boot/dts/ti/k3-j721s2-evm-pcie1-ep.dtso b/arch/arm64/boot/dts/ti/k3-j721s2-evm-pcie1-ep.dtso
new file mode 100644
index 000000000000..43568eb67d93
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-j721s2-evm-pcie1-ep.dtso
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+/**
+ * DT Overlay for enabling PCIE1 instance in Endpoint Configuration with the
+ * J7 common processor board.
+ *
+ * J7 Common Processor Board Product Link: https://www.ti.com/tool/J721EXCPXEVM
+ *
+ * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/soc/ti,sci_pm_domain.h>
+
+#include "k3-pinctrl.h"
+
+/*
+ * Since Root Complex and Endpoint modes are mutually exclusive
+ * disable Root Complex mode.
+ */
+&pcie1_rc {
+	status = "disabled";
+};
+
+&cbass_main {
+	#address-cells = <2>;
+	#size-cells = <2>;
+	interrupt-parent = <&gic500>;
+
+	pcie1_ep: pcie-ep@2910000 {
+		compatible = "ti,j7200-pcie-ep", "ti,j721e-pcie-ep";
+		reg = <0x00 0x02910000 0x00 0x1000>,
+		      <0x00 0x02917000 0x00 0x400>,
+		      <0x00 0x0d800000 0x00 0x00800000>,
+		      <0x00 0x18000000 0x00 0x08000000>;
+		reg-names = "intd_cfg", "user_cfg", "reg", "mem";
+		interrupt-names = "link_state";
+		interrupts = <GIC_SPI 330 IRQ_TYPE_EDGE_RISING>;
+		ti,syscon-pcie-ctrl = <&scm_conf 0x074>;
+		max-link-speed = <3>;
+		num-lanes = <1>;
+		power-domains = <&k3_pds 276 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 276 41>;
+		clock-names = "fck";
+		max-functions = /bits/ 8 <6>;
+		max-virtual-functions = /bits/ 8 <4 4 4 4 0 0>;
+		dma-coherent;
+		phys = <&serdes0_pcie_link>;
+		phy-names = "pcie-phy";
+	};
+};
diff --git a/arch/arm64/boot/dts/ti/k3-j721s2-main.dtsi b/arch/arm64/boot/dts/ti/k3-j721s2-main.dtsi
index b03731b53a26..ea7f2b2ab165 100644
--- a/arch/arm64/boot/dts/ti/k3-j721s2-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721s2-main.dtsi
@@ -766,6 +766,7 @@
 		ti,itap-del-sel-sd-hs = <0x0>;
 		ti,itap-del-sel-sdr12 = <0x0>;
 		ti,itap-del-sel-sdr25 = <0x0>;
+		ti,itap-del-sel-ddr50 = <0x2>;
 		ti,clkbuf-sel = <0x7>;
 		ti,trm-icp = <0x8>;
 		dma-coherent;
@@ -1086,8 +1087,12 @@
 			compatible = "ti,j721e-navss-main-udmap";
 			reg = <0x0 0x31150000 0x0 0x100>,
 			      <0x0 0x34000000 0x0 0x80000>,
-			      <0x0 0x35000000 0x0 0x200000>;
-			reg-names = "gcfg", "rchanrt", "tchanrt";
+			      <0x0 0x35000000 0x0 0x200000>,
+			      <0x0 0x30b00000 0x0 0x20000>,
+			      <0x0 0x30c00000 0x0 0x8000>,
+			      <0x0 0x30d00000 0x0 0x4000>;
+			reg-names = "gcfg", "rchanrt", "tchanrt",
+				    "tchan", "rchan", "rflow";
 			msi-parent = <&main_udmass_inta>;
 			#dma-cells = <1>;
 
diff --git a/arch/arm64/boot/dts/ti/k3-j721s2-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j721s2-mcu-wakeup.dtsi
index 7254f3bd3634..80aa33c58a45 100644
--- a/arch/arm64/boot/dts/ti/k3-j721s2-mcu-wakeup.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721s2-mcu-wakeup.dtsi
@@ -34,9 +34,16 @@
 		};
 	};
 
-	chipid@43000014 {
-		compatible = "ti,am654-chipid";
-		reg = <0x00 0x43000014 0x00 0x4>;
+	wkup_conf: bus@43000000 {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x0 0x00 0x43000000 0x20000>;
+
+		chipid: chipid@14 {
+			compatible = "ti,am654-chipid";
+			reg = <0x14 0x4>;
+		};
 	};
 
 	secure_proxy_sa3: mailbox@43600000 {
@@ -471,8 +478,12 @@
 			compatible = "ti,j721e-navss-mcu-udmap";
 			reg = <0x0 0x285c0000 0x0 0x100>,
 			      <0x0 0x2a800000 0x0 0x40000>,
-			      <0x0 0x2aa00000 0x0 0x40000>;
-			reg-names = "gcfg", "rchanrt", "tchanrt";
+			      <0x0 0x2aa00000 0x0 0x40000>,
+			      <0x0 0x284a0000 0x0 0x4000>,
+			      <0x0 0x284c0000 0x0 0x4000>,
+			      <0x0 0x28400000 0x0 0x2000>;
+			reg-names = "gcfg", "rchanrt", "tchanrt",
+				    "tchan", "rchan", "rflow";
 			msi-parent = <&main_udmass_inta>;
 			#dma-cells = <1>;
 
diff --git a/arch/arm64/boot/dts/ti/k3-j721s2-som-p0.dtsi b/arch/arm64/boot/dts/ti/k3-j721s2-som-p0.dtsi
index dcad372620b1..da3237b23b63 100644
--- a/arch/arm64/boot/dts/ti/k3-j721s2-som-p0.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721s2-som-p0.dtsi
@@ -172,6 +172,15 @@
 	};
 };
 
+&wkup_pmx1 {
+	pmic_irq_pins_default: pmic-irq-default-pins {
+		pinctrl-single,pins = <
+			/* (C21) MCU_OSPI1_CSn1.WKUP_GPIO0_39 */
+			J721S2_WKUP_IOPAD(0x028, PIN_INPUT, 7)
+		>;
+	};
+};
+
 &wkup_pmx2 {
 	wkup_i2c0_pins_default: wkup-i2c0-default-pins {
 		pinctrl-single,pins = <
@@ -208,6 +217,190 @@
 		compatible = "atmel,24c256";
 		reg = <0x50>;
 	};
+
+	tps659411: pmic@48 {
+		compatible = "ti,tps6594-q1";
+		reg = <0x48>;
+		system-power-controller;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_irq_pins_default>;
+		interrupt-parent = <&wkup_gpio0>;
+		interrupts = <39 IRQ_TYPE_EDGE_FALLING>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		ti,primary-pmic;
+		buck1234-supply = <&vsys_3v3>;
+		buck5-supply = <&vsys_3v3>;
+		ldo1-supply = <&vsys_3v3>;
+		ldo2-supply = <&vsys_3v3>;
+		ldo3-supply = <&vsys_3v3>;
+		ldo4-supply = <&vsys_3v3>;
+
+		regulators {
+			bucka1234: buck1234 {
+				regulator-name = "vdd_cpu_avs";
+				regulator-min-microvolt = <600000>;
+				regulator-max-microvolt = <900000>;
+				regulator-boot-on;
+				regulator-always-on;
+				bootph-pre-ram;
+			};
+
+			bucka5: buck5 {
+				regulator-name = "vdd_mcu_0v85";
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa1: ldo1 {
+				regulator-name = "vdd_mcuwk_0v8";
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa2: ldo2 {
+				regulator-name = "vdd_mcu_gpioret_3v3";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa3: ldo3 {
+				regulator-name = "vdd_mcuio_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa4: ldo4 {
+				regulator-name = "vda_mcu_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+		};
+	};
+
+	tps659414: pmic@4c {
+		compatible = "ti,tps6594-q1";
+		reg = <0x4c>;
+		system-power-controller;
+		interrupt-parent = <&wkup_gpio0>;
+		interrupts = <39 IRQ_TYPE_EDGE_FALLING>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		buck1-supply = <&vsys_3v3>;
+		buck2-supply = <&vsys_3v3>;
+		buck3-supply = <&vsys_3v3>;
+		buck4-supply = <&vsys_3v3>;
+		buck5-supply = <&vsys_3v3>;
+		ldo1-supply = <&vsys_3v3>;
+		ldo2-supply = <&vsys_3v3>;
+		ldo3-supply = <&vsys_3v3>;
+		ldo4-supply = <&vsys_3v3>;
+
+		regulators {
+			buckb1: buck1 {
+				regulator-name = "vdd_io_1v8_reg";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			buckb2: buck2 {
+				regulator-name = "vdd_fpd_1v1";
+				regulator-min-microvolt = <1100000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			buckb3: buck3 {
+				regulator-name = "vdd_phy_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			buckb4: buck4 {
+				regulator-name = "vdd_ddr_1v1";
+				regulator-min-microvolt = <1100000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			buckb5: buck5 {
+				regulator-name = "vdd_ram_0v85";
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldob1: ldo1 {
+				regulator-name = "vdd_wk_0v8";
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldob2: ldo2 {
+				regulator-name = "vdd_gpioret_3v3";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldob3: ldo3 {
+				regulator-name = "vda_dll_0v8";
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldob4: ldo4 {
+				regulator-name = "vda_pll_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+		};
+	};
+
+	lp876411: pmic@58 {
+		compatible = "ti,lp8764-q1";
+		reg = <0x58>;
+		system-power-controller;
+		interrupt-parent = <&wkup_gpio0>;
+		interrupts = <39 IRQ_TYPE_EDGE_FALLING>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		buck1234-supply = <&vsys_3v3>;
+
+		regulators {
+			buckc1234: buck1234 {
+				regulator-name = "vdd_core_0v8";
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+		};
+	};
 };
 
 &main_i2c0 {
diff --git a/arch/arm64/boot/dts/ti/k3-j784s4-evm.dts b/arch/arm64/boot/dts/ti/k3-j784s4-evm.dts
index f1f4c8634ab6..f34b92acc56d 100644
--- a/arch/arm64/boot/dts/ti/k3-j784s4-evm.dts
+++ b/arch/arm64/boot/dts/ti/k3-j784s4-evm.dts
@@ -273,6 +273,10 @@
 	};
 };
 
+&wkup_gpio0 {
+	status = "okay";
+};
+
 &main_pmx0 {
 	bootph-all;
 	main_uart8_pins_default: main-uart8-default-pins {
@@ -407,6 +411,17 @@
 	};
 };
 
+&wkup_pmx1 {
+	status = "okay";
+
+	pmic_irq_pins_default: pmic-irq-default-pins {
+		pinctrl-single,pins = <
+			/* (G33) MCU_OSPI1_CSn1.WKUP_GPIO0_39 */
+			J784S4_WKUP_IOPAD(0x028, PIN_INPUT, 7)
+		>;
+	};
+};
+
 &wkup_pmx0 {
 	bootph-all;
 	mcu_fss0_ospi0_pins_default: mcu-fss0-ospi0-default-pins {
@@ -471,6 +486,93 @@
 		compatible = "atmel,24c256";
 		reg = <0x50>;
 	};
+
+	tps659413: pmic@48 {
+		compatible = "ti,tps6594-q1";
+		reg = <0x48>;
+		system-power-controller;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_irq_pins_default>;
+		interrupt-parent = <&wkup_gpio0>;
+		interrupts = <39 IRQ_TYPE_EDGE_FALLING>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		ti,primary-pmic;
+		buck12-supply = <&vsys_3v3>;
+		buck3-supply = <&vsys_3v3>;
+		buck4-supply = <&vsys_3v3>;
+		buck5-supply = <&vsys_3v3>;
+		ldo1-supply = <&vsys_3v3>;
+		ldo2-supply = <&vsys_3v3>;
+		ldo3-supply = <&vsys_3v3>;
+		ldo4-supply = <&vsys_3v3>;
+
+		regulators {
+			bucka12: buck12 {
+				regulator-name = "vdd_ddr_1v1";
+				regulator-min-microvolt = <1100000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			bucka3: buck3 {
+				regulator-name = "vdd_ram_0v85";
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			bucka4: buck4 {
+				regulator-name = "vdd_io_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			bucka5: buck5 {
+				regulator-name = "vdd_mcu_0v85";
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa1: ldo1 {
+				regulator-name = "vdd_mcuio_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa2: ldo2 {
+				regulator-name = "vdd_mcuio_3v3";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa3: ldo3 {
+				regulator-name = "vds_dll_0v8";
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			ldoa4: ldo4 {
+				regulator-name = "vda_mcu_1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+		};
+	};
 };
 
 &mcu_uart0 {
diff --git a/arch/arm64/boot/dts/ti/k3-j784s4-main.dtsi b/arch/arm64/boot/dts/ti/k3-j784s4-main.dtsi
index d89bcddcfe3d..f2b720ed1e4f 100644
--- a/arch/arm64/boot/dts/ti/k3-j784s4-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j784s4-main.dtsi
@@ -712,6 +712,7 @@
 		ti,itap-del-sel-sd-hs = <0x0>;
 		ti,itap-del-sel-sdr12 = <0x0>;
 		ti,itap-del-sel-sdr25 = <0x0>;
+		ti,itap-del-sel-ddr50 = <0x2>;
 		ti,clkbuf-sel = <0x7>;
 		ti,trm-icp = <0x8>;
 		dma-coherent;
@@ -1188,8 +1189,12 @@
 			compatible = "ti,j721e-navss-main-udmap";
 			reg = <0x00 0x31150000 0x00 0x100>,
 			      <0x00 0x34000000 0x00 0x80000>,
-			      <0x00 0x35000000 0x00 0x200000>;
-			reg-names = "gcfg", "rchanrt", "tchanrt";
+			      <0x00 0x35000000 0x00 0x200000>,
+			      <0x00 0x30b00000 0x00 0x20000>,
+			      <0x00 0x30c00000 0x00 0x8000>,
+			      <0x00 0x30d00000 0x00 0x4000>;
+			reg-names = "gcfg", "rchanrt", "tchanrt",
+				    "tchan", "rchan", "rflow";
 			msi-parent = <&main_udmass_inta>;
 			#dma-cells = <1>;
 
diff --git a/arch/arm64/boot/dts/ti/k3-j784s4-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j784s4-mcu-wakeup.dtsi
index adb5ea6b9732..3902a921d7e5 100644
--- a/arch/arm64/boot/dts/ti/k3-j784s4-mcu-wakeup.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j784s4-mcu-wakeup.dtsi
@@ -38,10 +38,18 @@
 		};
 	};
 
-	chipid@43000014 {
+	wkup_conf: bus@43000000 {
 		bootph-all;
-		compatible = "ti,am654-chipid";
-		reg = <0x00 0x43000014 0x00 0x4>;
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x0 0x00 0x43000000 0x20000>;
+
+		chipid: chipid@14 {
+			bootph-all;
+			compatible = "ti,am654-chipid";
+			reg = <0x14 0x4>;
+		};
 	};
 
 	secure_proxy_sa3: mailbox@43600000 {
@@ -478,8 +486,12 @@
 			compatible = "ti,j721e-navss-mcu-udmap";
 			reg = <0x00 0x285c0000 0x00 0x100>,
 			      <0x00 0x2a800000 0x00 0x40000>,
-			      <0x00 0x2aa00000 0x00 0x40000>;
-			reg-names = "gcfg", "rchanrt", "tchanrt";
+			      <0x00 0x2aa00000 0x00 0x40000>,
+			      <0x00 0x284a0000 0x00 0x4000>,
+			      <0x00 0x284c0000 0x00 0x4000>,
+			      <0x00 0x28400000 0x00 0x2000>;
+			reg-names = "gcfg", "rchanrt", "tchanrt",
+				    "tchan", "rchan", "rflow";
 			msi-parent = <&main_udmass_inta>;
 			#dma-cells = <1>;
 
diff --git a/arch/arm64/boot/dts/xilinx/Makefile b/arch/arm64/boot/dts/xilinx/Makefile
index 5e40c0b4fa0a..1068b0fa8e98 100644
--- a/arch/arm64/boot/dts/xilinx/Makefile
+++ b/arch/arm64/boot/dts/xilinx/Makefile
@@ -22,11 +22,10 @@ dtb-$(CONFIG_ARCH_ZYNQMP) += zynqmp-sm-k26-revA.dtb
 dtb-$(CONFIG_ARCH_ZYNQMP) += zynqmp-smk-k26-revA.dtb
 
 zynqmp-sm-k26-revA-sck-kv-g-revA-dtbs := zynqmp-sm-k26-revA.dtb zynqmp-sck-kv-g-revA.dtbo
+dtb-$(CONFIG_ARCH_ZYNQMP) += zynqmp-sm-k26-revA-sck-kv-g-revA.dtb
 zynqmp-sm-k26-revA-sck-kv-g-revB-dtbs := zynqmp-sm-k26-revA.dtb zynqmp-sck-kv-g-revB.dtbo
+dtb-$(CONFIG_ARCH_ZYNQMP) += zynqmp-sm-k26-revA-sck-kv-g-revB.dtb
 zynqmp-smk-k26-revA-sck-kv-g-revA-dtbs := zynqmp-smk-k26-revA.dtb zynqmp-sck-kv-g-revA.dtbo
+dtb-$(CONFIG_ARCH_ZYNQMP) += zynqmp-smk-k26-revA-sck-kv-g-revA.dtb
 zynqmp-smk-k26-revA-sck-kv-g-revB-dtbs := zynqmp-smk-k26-revA.dtb zynqmp-sck-kv-g-revB.dtbo
-
-zynqmp-sm-k26-revA-sck-kr-g-revA-dtbs := zynqmp-sm-k26-revA.dtb zynqmp-sck-kr-g-revA.dtbo
-zynqmp-sm-k26-revA-sck-kr-g-revB-dtbs := zynqmp-sm-k26-revA.dtb zynqmp-sck-kr-g-revB.dtbo
-zynqmp-smk-k26-revA-sck-kr-g-revA-dtbs := zynqmp-smk-k26-revA.dtb zynqmp-sck-kr-g-revA.dtbo
-zynqmp-smk-k26-revA-sck-kr-g-revB-dtbs := zynqmp-smk-k26-revA.dtb zynqmp-sck-kr-g-revB.dtbo
+dtb-$(CONFIG_ARCH_ZYNQMP) += zynqmp-smk-k26-revA-sck-kv-g-revB.dtb
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revA.dtso b/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revA.dtso
index ae1b9b2bdbee..92f4190d564d 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revA.dtso
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revA.dtso
@@ -21,57 +21,57 @@
 /dts-v1/;
 /plugin/;
 
-&i2c1 { /* I2C_SCK C23/C24 - MIO from SOM */
-	#address-cells = <1>;
-	#size-cells = <0>;
-	pinctrl-names = "default", "gpio";
-	pinctrl-0 = <&pinctrl_i2c1_default>;
-	pinctrl-1 = <&pinctrl_i2c1_gpio>;
-	scl-gpios = <&gpio 24 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
-	sda-gpios = <&gpio 25 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
-
-	/* u14 - 0x40 - ina260 */
-	/* u27 - 0xe0 - STDP4320 DP/HDMI splitter */
-};
-
-&amba {
-	si5332_0: si5332_0 { /* u17 */
+&{/} {
+	si5332_0: si5332-0 { /* u17 */
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <125000000>;
 	};
 
-	si5332_1: si5332_1 { /* u17 */
+	si5332_1: si5332-1 { /* u17 */
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <25000000>;
 	};
 
-	si5332_2: si5332_2 { /* u17 */
+	si5332_2: si5332-2 { /* u17 */
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <48000000>;
 	};
 
-	si5332_3: si5332_3 { /* u17 */
+	si5332_3: si5332-3 { /* u17 */
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <24000000>;
 	};
 
-	si5332_4: si5332_4 { /* u17 */
+	si5332_4: si5332-4 { /* u17 */
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <26000000>;
 	};
 
-	si5332_5: si5332_5 { /* u17 */
+	si5332_5: si5332-5 { /* u17 */
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <27000000>;
 	};
 };
 
+&i2c1 { /* I2C_SCK C23/C24 - MIO from SOM */
+	#address-cells = <1>;
+	#size-cells = <0>;
+	pinctrl-names = "default", "gpio";
+	pinctrl-0 = <&pinctrl_i2c1_default>;
+	pinctrl-1 = <&pinctrl_i2c1_gpio>;
+	scl-gpios = <&gpio 24 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+	sda-gpios = <&gpio 25 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+
+	/* u14 - 0x40 - ina260 */
+	/* u27 - 0xe0 - STDP4320 DP/HDMI splitter */
+};
+
 /* DP/USB 3.0 and SATA */
 &psgtr {
 	status = "okay";
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revB.dtso b/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revB.dtso
index b59e48be6465..f88b71f5b07a 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revB.dtso
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revB.dtso
@@ -16,58 +16,58 @@
 /dts-v1/;
 /plugin/;
 
-&i2c1 { /* I2C_SCK C23/C24 - MIO from SOM */
-	#address-cells = <1>;
-	#size-cells = <0>;
-	pinctrl-names = "default", "gpio";
-	pinctrl-0 = <&pinctrl_i2c1_default>;
-	pinctrl-1 = <&pinctrl_i2c1_gpio>;
-	scl-gpios = <&gpio 24 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
-	sda-gpios = <&gpio 25 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
-
-	/* u14 - 0x40 - ina260 */
-	/* u43 - 0x2d - usb5744 */
-	/* u27 - 0xe0 - STDP4320 DP/HDMI splitter */
-};
-
-&amba {
-	si5332_0: si5332_0 { /* u17 */
+&{/} {
+	si5332_0: si5332-0 { /* u17 */
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <125000000>;
 	};
 
-	si5332_1: si5332_1 { /* u17 */
+	si5332_1: si5332-1 { /* u17 */
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <25000000>;
 	};
 
-	si5332_2: si5332_2 { /* u17 */
+	si5332_2: si5332-2 { /* u17 */
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <48000000>;
 	};
 
-	si5332_3: si5332_3 { /* u17 */
+	si5332_3: si5332-3 { /* u17 */
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <24000000>;
 	};
 
-	si5332_4: si5332_4 { /* u17 */
+	si5332_4: si5332-4 { /* u17 */
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <26000000>;
 	};
 
-	si5332_5: si5332_5 { /* u17 */
+	si5332_5: si5332-5 { /* u17 */
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <27000000>;
 	};
 };
 
+&i2c1 { /* I2C_SCK C23/C24 - MIO from SOM */
+	#address-cells = <1>;
+	#size-cells = <0>;
+	pinctrl-names = "default", "gpio";
+	pinctrl-0 = <&pinctrl_i2c1_default>;
+	pinctrl-1 = <&pinctrl_i2c1_gpio>;
+	scl-gpios = <&gpio 24 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+	sda-gpios = <&gpio 25 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+
+	/* u14 - 0x40 - ina260 */
+	/* u43 - 0x2d - usb5744 */
+	/* u27 - 0xe0 - STDP4320 DP/HDMI splitter */
+};
+
 /* DP/USB 3.0 */
 &psgtr {
 	status = "okay";
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-sm-k26-revA.dts b/arch/arm64/boot/dts/xilinx/zynqmp-sm-k26-revA.dts
index c4774a42d5fc..51622896b1b1 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-sm-k26-revA.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-sm-k26-revA.dts
@@ -131,9 +131,7 @@
 &qspi { /* MIO 0-5 - U143 */
 	status = "okay";
 	spi_flash: flash@0 { /* MT25QU512A */
-		compatible = "mt25qu512a", "jedec,spi-nor"; /* 64MB */
-		#address-cells = <1>;
-		#size-cells = <1>;
+		compatible = "jedec,spi-nor"; /* 64MB */
 		reg = <0>;
 		spi-tx-bus-width = <4>;
 		spi-rx-bus-width = <4>;
@@ -222,9 +220,9 @@
 				label = "Secure OS Storage";
 				reg = <0x2280000 0x20000>; /* 128KB */
 			};
-			partition@22A0000 {
+			partition@22a0000 {
 				label = "User";
-				reg = <0x22A0000 0x1d60000>; /* 29.375 MB */
+				reg = <0x22a0000 0x1d60000>; /* 29.375 MB */
 			};
 		};
 	};
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm015-dc1.dts b/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm015-dc1.dts
index e821d55d8d5a..73491626e01e 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm015-dc1.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm015-dc1.dts
@@ -98,8 +98,12 @@
 	phy-mode = "rgmii-id";
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_gem3_default>;
-	phy0: ethernet-phy@0 {
-		reg = <0>;
+	mdio: mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		phy0: ethernet-phy@0 {
+			reg = <0>;
+		};
 	};
 };
 
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm016-dc2.dts b/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm016-dc2.dts
index b59e11316b4b..f767708fb50d 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm016-dc2.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm016-dc2.dts
@@ -91,12 +91,16 @@
 	phy-mode = "rgmii-id";
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_gem2_default>;
-	phy0: ethernet-phy@5 {
-		reg = <5>;
-		ti,rx-internal-delay = <0x8>;
-		ti,tx-internal-delay = <0xa>;
-		ti,fifo-depth = <0x1>;
-		ti,dp83867-rxctrl-strap-quirk;
+	mdio: mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		phy0: ethernet-phy@5 {
+			reg = <5>;
+			ti,rx-internal-delay = <0x8>;
+			ti,tx-internal-delay = <0xa>;
+			ti,fifo-depth = <0x1>;
+			ti,dp83867-rxctrl-strap-quirk;
+		};
 	};
 };
 
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm017-dc3.dts b/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm017-dc3.dts
index 38b0a312171b..f553b317e6b2 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm017-dc3.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm017-dc3.dts
@@ -88,8 +88,12 @@
 	status = "okay";
 	phy-handle = <&phy0>;
 	phy-mode = "rgmii-id";
-	phy0: ethernet-phy@0 { /* VSC8211 */
-		reg = <0>;
+	mdio: mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		phy0: ethernet-phy@0 { /* VSC8211 */
+			reg = <0>;
+		};
 	};
 };
 
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm018-dc4.dts b/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm018-dc4.dts
index 6636e76545a5..6ec1d9813973 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm018-dc4.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm018-dc4.dts
@@ -116,17 +116,21 @@
 	status = "okay";
 	phy-mode = "rgmii-id";
 	phy-handle = <&ethernet_phy0>;
-	ethernet_phy0: ethernet-phy@0 { /* Marvell 88e1512 */
-		reg = <0>;
-	};
-	ethernet_phy7: ethernet-phy@7 { /* Vitesse VSC8211 */
-		reg = <7>;
-	};
-	ethernet_phy3: ethernet-phy@3 { /* Realtek RTL8211DN */
-		reg = <3>;
-	};
-	ethernet_phy8: ethernet-phy@8 { /* Vitesse VSC8211 */
-		reg = <8>;
+	mdio: mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		ethernet_phy0: ethernet-phy@0 { /* Marvell 88e1512 */
+			reg = <0>;
+		};
+		ethernet_phy7: ethernet-phy@7 { /* Vitesse VSC8211 */
+			reg = <7>;
+		};
+		ethernet_phy3: ethernet-phy@3 { /* Realtek RTL8211DN */
+			reg = <3>;
+		};
+		ethernet_phy8: ethernet-phy@8 { /* Vitesse VSC8211 */
+			reg = <8>;
+		};
 	};
 };
 
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm019-dc5.dts b/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm019-dc5.dts
index 0d2ea9c09a0a..b1857e17ab7e 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm019-dc5.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm019-dc5.dts
@@ -77,8 +77,12 @@
 	phy-mode = "rgmii-id";
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_gem1_default>;
-	phy0: ethernet-phy@0 {
-		reg = <0>;
+	mdio: mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		phy0: ethernet-phy@0 {
+			reg = <0>;
+		};
 	};
 };
 
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-zcu100-revC.dts b/arch/arm64/boot/dts/xilinx/zynqmp-zcu100-revC.dts
index d0091d3cb764..52f998c22538 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-zcu100-revC.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-zcu100-revC.dts
@@ -123,13 +123,13 @@
 		io-channels = <&u35 0>, <&u35 1>, <&u35 2>, <&u35 3>;
 	};
 
-	si5335_0: si5335_0 { /* clk0_usb - u23 */
+	si5335_0: si5335-0 { /* clk0_usb - u23 */
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <26000000>;
 	};
 
-	si5335_1: si5335_1 { /* clk1_dp - u23 */
+	si5335_1: si5335-1 { /* clk1_dp - u23 */
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <27000000>;
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
index b61fc99cd911..eaba466804bc 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
+++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
@@ -129,7 +129,7 @@
 		};
 	};
 
-	zynqmp_ipi: zynqmp_ipi {
+	zynqmp_ipi: zynqmp-ipi {
 		bootph-all;
 		compatible = "xlnx,zynqmp-ipi-mailbox";
 		interrupt-parent = <&gic>;
@@ -141,6 +141,7 @@
 
 		ipi_mailbox_pmu1: mailbox@ff9905c0 {
 			bootph-all;
+			compatible = "xlnx,zynqmp-ipi-dest-mailbox";
 			reg = <0x0 0xff9905c0 0x0 0x20>,
 			      <0x0 0xff9905e0 0x0 0x20>,
 			      <0x0 0xff990e80 0x0 0x20>,
@@ -194,12 +195,12 @@
 				mbox-names = "tx", "rx";
 			};
 
-			nvmem_firmware {
+			nvmem-firmware {
 				compatible = "xlnx,zynqmp-nvmem-fw";
 				#address-cells = <1>;
 				#size-cells = <1>;
 
-				soc_revision: soc_revision@0 {
+				soc_revision: soc-revision@0 {
 					reg = <0x0 0x4>;
 				};
 			};
@@ -584,8 +585,6 @@
 				     <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>;
 			reg = <0x0 0xff0b0000 0x0 0x1000>;
 			clock-names = "pclk", "hclk", "tx_clk", "rx_clk", "tsu_clk";
-			#address-cells = <1>;
-			#size-cells = <0>;
 			iommus = <&smmu 0x874>;
 			power-domains = <&zynqmp_firmware PD_ETH_0>;
 			resets = <&zynqmp_reset ZYNQMP_RESET_GEM0>;
@@ -600,8 +599,6 @@
 				     <GIC_SPI 59 IRQ_TYPE_LEVEL_HIGH>;
 			reg = <0x0 0xff0c0000 0x0 0x1000>;
 			clock-names = "pclk", "hclk", "tx_clk", "rx_clk", "tsu_clk";
-			#address-cells = <1>;
-			#size-cells = <0>;
 			iommus = <&smmu 0x875>;
 			power-domains = <&zynqmp_firmware PD_ETH_1>;
 			resets = <&zynqmp_reset ZYNQMP_RESET_GEM1>;
@@ -616,8 +613,6 @@
 				     <GIC_SPI 61 IRQ_TYPE_LEVEL_HIGH>;
 			reg = <0x0 0xff0d0000 0x0 0x1000>;
 			clock-names = "pclk", "hclk", "tx_clk", "rx_clk", "tsu_clk";
-			#address-cells = <1>;
-			#size-cells = <0>;
 			iommus = <&smmu 0x876>;
 			power-domains = <&zynqmp_firmware PD_ETH_2>;
 			resets = <&zynqmp_reset ZYNQMP_RESET_GEM2>;
@@ -632,8 +627,6 @@
 				     <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>;
 			reg = <0x0 0xff0e0000 0x0 0x1000>;
 			clock-names = "pclk", "hclk", "tx_clk", "rx_clk", "tsu_clk";
-			#address-cells = <1>;
-			#size-cells = <0>;
 			iommus = <&smmu 0x877>;
 			power-domains = <&zynqmp_firmware PD_ETH_3>;
 			resets = <&zynqmp_reset ZYNQMP_RESET_GEM3>;
diff --git a/arch/arm64/boot/install.sh b/arch/arm64/boot/install.sh
index 7399d706967a..9b7a09808a3d 100755
--- a/arch/arm64/boot/install.sh
+++ b/arch/arm64/boot/install.sh
@@ -17,7 +17,8 @@
 #   $3 - kernel map file
 #   $4 - default install path (blank if root directory)
 
-if [ "$(basename $2)" = "Image.gz" ]; then
+if [ "$(basename $2)" = "Image.gz" ] || [ "$(basename $2)" = "vmlinuz.efi" ]
+then
 # Compressed install
   echo "Installing compressed kernel"
   base=vmlinuz
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index b60aa1f89343..e6cf3e5d63c3 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -30,6 +30,9 @@ CONFIG_SCHED_AUTOGROUP=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_KALLSYMS_ALL=y
 CONFIG_PROFILING=y
+CONFIG_KEXEC=y
+CONFIG_KEXEC_FILE=y
+CONFIG_CRASH_DUMP=y
 CONFIG_ARCH_ACTIONS=y
 CONFIG_ARCH_SUNXI=y
 CONFIG_ARCH_ALPINE=y
@@ -77,9 +80,6 @@ CONFIG_ARM64_VA_BITS_48=y
 CONFIG_SCHED_MC=y
 CONFIG_SCHED_SMT=y
 CONFIG_NUMA=y
-CONFIG_KEXEC=y
-CONFIG_KEXEC_FILE=y
-CONFIG_CRASH_DUMP=y
 CONFIG_XEN=y
 CONFIG_COMPAT=y
 CONFIG_RANDOMIZE_BASE=y
@@ -180,8 +180,6 @@ CONFIG_NET_ACT_GATE=m
 CONFIG_QRTR_SMD=m
 CONFIG_QRTR_TUN=m
 CONFIG_CAN=m
-CONFIG_CAN_M_CAN=m
-CONFIG_CAN_M_CAN_PLATFORM=m
 CONFIG_BT=m
 CONFIG_BT_HIDP=m
 # CONFIG_BT_LE is not set
@@ -215,27 +213,27 @@ CONFIG_PCI_PASID=y
 CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_ACPI=y
 CONFIG_PCI_AARDVARK=y
-CONFIG_PCI_TEGRA=y
-CONFIG_PCIE_RCAR_HOST=y
-CONFIG_PCIE_RCAR_EP=y
-CONFIG_PCI_HOST_GENERIC=y
-CONFIG_PCI_XGENE=y
 CONFIG_PCIE_ALTERA=y
 CONFIG_PCIE_ALTERA_MSI=y
+CONFIG_PCIE_BRCMSTB=m
 CONFIG_PCI_HOST_THUNDER_PEM=y
 CONFIG_PCI_HOST_THUNDER_ECAM=y
-CONFIG_PCIE_ROCKCHIP_HOST=m
+CONFIG_PCI_HOST_GENERIC=y
 CONFIG_PCIE_MEDIATEK_GEN3=m
-CONFIG_PCIE_BRCMSTB=m
+CONFIG_PCI_TEGRA=y
+CONFIG_PCIE_RCAR_HOST=y
+CONFIG_PCIE_RCAR_EP=y
+CONFIG_PCIE_ROCKCHIP_HOST=m
+CONFIG_PCI_XGENE=y
 CONFIG_PCI_IMX6_HOST=y
 CONFIG_PCI_LAYERSCAPE=y
 CONFIG_PCI_HISI=y
-CONFIG_PCIE_QCOM=y
-CONFIG_PCIE_ARMADA_8K=y
-CONFIG_PCIE_ROCKCHIP_DW_HOST=y
 CONFIG_PCIE_KIRIN=y
 CONFIG_PCIE_HISI_STB=y
+CONFIG_PCIE_ARMADA_8K=y
 CONFIG_PCIE_TEGRA194_HOST=m
+CONFIG_PCIE_QCOM=y
+CONFIG_PCIE_ROCKCHIP_DW_HOST=y
 CONFIG_PCIE_VISCONTI_HOST=y
 CONFIG_PCIE_LAYERSCAPE_GEN4=y
 CONFIG_PCI_ENDPOINT=y
@@ -252,9 +250,11 @@ CONFIG_ARM_SCPI_PROTOCOL=y
 CONFIG_RASPBERRYPI_FIRMWARE=y
 CONFIG_INTEL_STRATIX10_SERVICE=y
 CONFIG_INTEL_STRATIX10_RSU=m
+CONFIG_MTK_ADSP_IPC=m
 CONFIG_EFI_CAPSULE_LOADER=y
 CONFIG_IMX_SCU=y
-CONFIG_IMX_SCU_PD=y
+CONFIG_QCOM_QSEECOM=y
+CONFIG_QCOM_QSEECOM_UEFISECAPP=y
 CONFIG_GNSS=m
 CONFIG_GNSS_MTK_SERIAL=m
 CONFIG_MTD=y
@@ -276,15 +276,12 @@ CONFIG_MTD_NAND_FSL_IFC=y
 CONFIG_MTD_NAND_QCOM=y
 CONFIG_MTD_SPI_NOR=y
 CONFIG_MTD_UBI=m
-CONFIG_UBIFS_FS=m
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_NBD=m
 CONFIG_VIRTIO_BLK=y
 CONFIG_BLK_DEV_NVME=m
 CONFIG_QCOM_COINCELL=m
 CONFIG_QCOM_FASTRPC=m
-CONFIG_BATTERY_QCOM_BATTMGR=m
-CONFIG_UCSI_PMIC_GLINK=m
 CONFIG_SRAM=y
 CONFIG_PCI_ENDPOINT_TEST=m
 CONFIG_EEPROM_AT24=m
@@ -368,6 +365,7 @@ CONFIG_SNI_NETSEC=y
 CONFIG_STMMAC_ETH=m
 CONFIG_DWMAC_TEGRA=m
 CONFIG_TI_K3_AM65_CPSW_NUSS=y
+CONFIG_TI_ICSSG_PRUETH=m
 CONFIG_QCOM_IPA=m
 CONFIG_MESON_GXL_PHY=m
 CONFIG_AQUANTIA_PHY=y
@@ -384,6 +382,8 @@ CONFIG_DP83869_PHY=m
 CONFIG_DP83TD510_PHY=y
 CONFIG_VITESSE_PHY=y
 CONFIG_CAN_FLEXCAN=m
+CONFIG_CAN_M_CAN=m
+CONFIG_CAN_M_CAN_PLATFORM=m
 CONFIG_CAN_RCAR=m
 CONFIG_CAN_RCAR_CANFD=m
 CONFIG_CAN_MCP251XFD=m
@@ -448,6 +448,7 @@ CONFIG_SERIO_AMBAKMI=y
 CONFIG_LEGACY_PTY_COUNT=16
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=8
 CONFIG_SERIAL_8250_EXTENDED=y
 CONFIG_SERIAL_8250_SHARE_IRQ=y
 CONFIG_SERIAL_8250_BCM2835AUX=y
@@ -574,9 +575,9 @@ CONFIG_PINCTRL_IMX8DXL=y
 CONFIG_PINCTRL_IMX8ULP=y
 CONFIG_PINCTRL_IMX93=y
 CONFIG_PINCTRL_MSM=y
-CONFIG_PINCTRL_IPQ8074=y
 CONFIG_PINCTRL_IPQ5018=y
 CONFIG_PINCTRL_IPQ5332=y
+CONFIG_PINCTRL_IPQ8074=y
 CONFIG_PINCTRL_IPQ6018=y
 CONFIG_PINCTRL_IPQ9574=y
 CONFIG_PINCTRL_MSM8916=y
@@ -588,34 +589,37 @@ CONFIG_PINCTRL_MSM8998=y
 CONFIG_PINCTRL_QCM2290=y
 CONFIG_PINCTRL_QCS404=y
 CONFIG_PINCTRL_QDF2XXX=y
-CONFIG_PINCTRL_QCOM_SPMI_PMIC=y
 CONFIG_PINCTRL_QDU1000=y
 CONFIG_PINCTRL_SA8775P=y
 CONFIG_PINCTRL_SC7180=y
 CONFIG_PINCTRL_SC7280=y
-CONFIG_PINCTRL_SC7280_LPASS_LPI=m
 CONFIG_PINCTRL_SC8180X=y
 CONFIG_PINCTRL_SC8280XP=y
 CONFIG_PINCTRL_SDM660=y
 CONFIG_PINCTRL_SDM670=y
 CONFIG_PINCTRL_SDM845=y
+CONFIG_PINCTRL_SDX75=y
+CONFIG_PINCTRL_SM4450=y
 CONFIG_PINCTRL_SM6115=y
-CONFIG_PINCTRL_SM6115_LPASS_LPI=m
 CONFIG_PINCTRL_SM6125=y
 CONFIG_PINCTRL_SM6350=y
 CONFIG_PINCTRL_SM6375=y
 CONFIG_PINCTRL_SM8150=y
 CONFIG_PINCTRL_SM8250=y
-CONFIG_PINCTRL_SM8250_LPASS_LPI=m
 CONFIG_PINCTRL_SM8350=y
-CONFIG_PINCTRL_SM8350_LPASS_LPI=m
 CONFIG_PINCTRL_SM8450=y
+CONFIG_PINCTRL_SM8550=y
+CONFIG_PINCTRL_SM8650=y
+CONFIG_PINCTRL_X1E80100=y
+CONFIG_PINCTRL_QCOM_SPMI_PMIC=y
+CONFIG_PINCTRL_LPASS_LPI=m
+CONFIG_PINCTRL_SC7280_LPASS_LPI=m
+CONFIG_PINCTRL_SM6115_LPASS_LPI=m
+CONFIG_PINCTRL_SM8250_LPASS_LPI=m
+CONFIG_PINCTRL_SM8350_LPASS_LPI=m
 CONFIG_PINCTRL_SM8450_LPASS_LPI=m
 CONFIG_PINCTRL_SC8280XP_LPASS_LPI=m
-CONFIG_PINCTRL_SM8550=y
 CONFIG_PINCTRL_SM8550_LPASS_LPI=m
-CONFIG_PINCTRL_LPASS_LPI=m
-CONFIG_GPIO_AGGREGATOR=m
 CONFIG_GPIO_ALTERA=m
 CONFIG_GPIO_DAVINCI=y
 CONFIG_GPIO_DWAPB=y
@@ -624,6 +628,7 @@ CONFIG_GPIO_MPC8XXX=y
 CONFIG_GPIO_MXC=y
 CONFIG_GPIO_PL061=y
 CONFIG_GPIO_RCAR=y
+CONFIG_GPIO_SYSCON=y
 CONFIG_GPIO_UNIPHIER=y
 CONFIG_GPIO_VISCONTI=y
 CONFIG_GPIO_WCD934X=m
@@ -635,7 +640,7 @@ CONFIG_GPIO_PCA953X_IRQ=y
 CONFIG_GPIO_BD9571MWV=m
 CONFIG_GPIO_MAX77620=y
 CONFIG_GPIO_SL28CPLD=m
-CONFIG_GPIO_SYSCON=y
+CONFIG_GPIO_AGGREGATOR=m
 CONFIG_POWER_RESET_MSM=y
 CONFIG_POWER_RESET_QCOM_PON=m
 CONFIG_POWER_RESET_XGENE=y
@@ -643,6 +648,7 @@ CONFIG_POWER_RESET_SYSCON=y
 CONFIG_POWER_RESET_SYSCON_POWEROFF=y
 CONFIG_SYSCON_REBOOT_MODE=y
 CONFIG_NVMEM_REBOOT_MODE=m
+CONFIG_BATTERY_QCOM_BATTMGR=m
 CONFIG_BATTERY_SBS=m
 CONFIG_BATTERY_BQ27XXX=y
 CONFIG_BATTERY_MAX17042=m
@@ -667,14 +673,16 @@ CONFIG_DEVFREQ_THERMAL=y
 CONFIG_THERMAL_EMULATION=y
 CONFIG_IMX_SC_THERMAL=m
 CONFIG_IMX8MM_THERMAL=m
-CONFIG_QORIQ_THERMAL=m
 CONFIG_K3_THERMAL=m
+CONFIG_QORIQ_THERMAL=m
 CONFIG_SUN8I_THERMAL=y
 CONFIG_ROCKCHIP_THERMAL=m
 CONFIG_RCAR_THERMAL=y
 CONFIG_RCAR_GEN3_THERMAL=y
 CONFIG_RZG2L_THERMAL=y
 CONFIG_ARMADA_THERMAL=y
+CONFIG_MTK_THERMAL=m
+CONFIG_MTK_LVTS_THERMAL=m
 CONFIG_BCM2711_THERMAL=m
 CONFIG_BCM2835_THERMAL=m
 CONFIG_BRCMSTB_THERMAL=m
@@ -694,6 +702,7 @@ CONFIG_ARM_SP805_WATCHDOG=y
 CONFIG_ARM_SBSA_WATCHDOG=y
 CONFIG_S3C2410_WATCHDOG=y
 CONFIG_DW_WATCHDOG=y
+CONFIG_K3_RTI_WATCHDOG=m
 CONFIG_SUNXI_WATCHDOG=m
 CONFIG_NPCM7XX_WATCHDOG=y
 CONFIG_IMX2_WDT=y
@@ -709,7 +718,6 @@ CONFIG_UNIPHIER_WATCHDOG=y
 CONFIG_PM8916_WATCHDOG=m
 CONFIG_BCM2835_WDT=y
 CONFIG_BCM7038_WDT=m
-CONFIG_K3_RTI_WATCHDOG=m
 CONFIG_MFD_ALTERA_SYSMGR=y
 CONFIG_MFD_BD9571MWV=y
 CONFIG_MFD_AXP20X_I2C=y
@@ -726,9 +734,9 @@ CONFIG_MFD_RK8XX_SPI=y
 CONFIG_MFD_SEC_CORE=y
 CONFIG_MFD_SL28CPLD=y
 CONFIG_RZ_MTU3=y
+CONFIG_MFD_TI_AM335X_TSCADC=m
 CONFIG_MFD_TPS65219=y
 CONFIG_MFD_TPS6594_I2C=m
-CONFIG_MFD_TI_AM335X_TSCADC=m
 CONFIG_MFD_ROHM_BD718XX=y
 CONFIG_MFD_WCD934X=m
 CONFIG_MFD_KHADAS_MCU=m
@@ -737,6 +745,7 @@ CONFIG_REGULATOR_AXP20X=y
 CONFIG_REGULATOR_BD718XX=y
 CONFIG_REGULATOR_BD9571MWV=y
 CONFIG_REGULATOR_CROS_EC=y
+CONFIG_REGULATOR_DA9211=m
 CONFIG_REGULATOR_FAN53555=y
 CONFIG_REGULATOR_GPIO=y
 CONFIG_REGULATOR_HI6421V530=y
@@ -783,6 +792,7 @@ CONFIG_USB_VIDEO_CLASS=m
 CONFIG_V4L_PLATFORM_DRIVERS=y
 CONFIG_SDR_PLATFORM_DRIVERS=y
 CONFIG_V4L_MEM2MEM_DRIVERS=y
+CONFIG_VIDEO_CADENCE_CSI2RX=m
 CONFIG_VIDEO_MEDIATEK_JPEG=m
 CONFIG_VIDEO_MEDIATEK_VCODEC=m
 CONFIG_VIDEO_IMX7_CSI=m
@@ -804,6 +814,7 @@ CONFIG_VIDEO_SAMSUNG_EXYNOS_GSC=m
 CONFIG_VIDEO_SAMSUNG_S5P_JPEG=m
 CONFIG_VIDEO_SAMSUNG_S5P_MFC=m
 CONFIG_VIDEO_SUN6I_CSI=m
+CONFIG_VIDEO_TI_J721E_CSI2RX=m
 CONFIG_VIDEO_HANTRO=m
 CONFIG_VIDEO_IMX219=m
 CONFIG_VIDEO_IMX412=m
@@ -860,6 +871,7 @@ CONFIG_DRM_SAMSUNG_DSIM=m
 CONFIG_DRM_SII902X=m
 CONFIG_DRM_SIMPLE_BRIDGE=m
 CONFIG_DRM_THINE_THC63LVD1024=m
+CONFIG_DRM_TOSHIBA_TC358767=m
 CONFIG_DRM_TOSHIBA_TC358768=m
 CONFIG_DRM_TI_TFP410=m
 CONFIG_DRM_TI_SN65DSI83=m
@@ -877,17 +889,19 @@ CONFIG_DRM_ETNAVIV=m
 CONFIG_DRM_HISI_HIBMC=m
 CONFIG_DRM_HISI_KIRIN=m
 CONFIG_DRM_MEDIATEK=m
+CONFIG_DRM_MEDIATEK_DP=m
 CONFIG_DRM_MEDIATEK_HDMI=m
 CONFIG_DRM_MXSFB=m
-CONFIG_DRM_MESON=m
 CONFIG_DRM_IMX_LCDIF=m
+CONFIG_DRM_MESON=m
 CONFIG_DRM_PL111=m
 CONFIG_DRM_LIMA=m
 CONFIG_DRM_PANFROST=m
 CONFIG_DRM_TIDSS=m
+CONFIG_DRM_POWERVR=m
 CONFIG_FB=y
-CONFIG_FB_MODE_HELPERS=y
 CONFIG_FB_EFI=y
+CONFIG_FB_MODE_HELPERS=y
 CONFIG_BACKLIGHT_PWM=m
 CONFIG_BACKLIGHT_LP855X=m
 CONFIG_LOGO=y
@@ -913,6 +927,8 @@ CONFIG_SND_SOC_MT8183_MT6358_TS3A227E_MAX98357A=m
 CONFIG_SND_SOC_MT8183_DA7219_MAX98357A=m
 CONFIG_SND_SOC_MT8192=m
 CONFIG_SND_SOC_MT8192_MT6359_RT1015_RT5682=m
+CONFIG_SND_SOC_MT8195=m
+CONFIG_SND_SOC_MT8195_MT6359=m
 CONFIG_SND_MESON_AXG_SOUND_CARD=m
 CONFIG_SND_MESON_GX_SOUND_CARD=m
 CONFIG_SND_SOC_QCOM=m
@@ -920,6 +936,7 @@ CONFIG_SND_SOC_APQ8016_SBC=m
 CONFIG_SND_SOC_MSM8996=m
 CONFIG_SND_SOC_SDM845=m
 CONFIG_SND_SOC_SM8250=m
+CONFIG_SND_SOC_SC8280XP=m
 CONFIG_SND_SOC_SC7180=m
 CONFIG_SND_SOC_SC7280=m
 CONFIG_SND_SOC_ROCKCHIP=m
@@ -930,6 +947,10 @@ CONFIG_SND_SOC_RK3399_GRU_SOUND=m
 CONFIG_SND_SOC_SAMSUNG=y
 CONFIG_SND_SOC_RCAR=m
 CONFIG_SND_SOC_RZ=m
+CONFIG_SND_SOC_SOF_TOPLEVEL=y
+CONFIG_SND_SOC_SOF_OF=y
+CONFIG_SND_SOC_SOF_MTK_TOPLEVEL=y
+CONFIG_SND_SOC_SOF_MT8195=m
 CONFIG_SND_SUN8I_CODEC=m
 CONFIG_SND_SUN8I_CODEC_ANALOG=m
 CONFIG_SND_SUN50I_CODEC_ANALOG=m
@@ -950,6 +971,7 @@ CONFIG_SND_SOC_TEGRA210_ADX=m
 CONFIG_SND_SOC_TEGRA210_MIXER=m
 CONFIG_SND_SOC_TEGRA_AUDIO_GRAPH_CARD=m
 CONFIG_SND_SOC_DAVINCI_MCASP=m
+CONFIG_SND_SOC_J721E_EVM=m
 CONFIG_SND_SOC_AK4613=m
 CONFIG_SND_SOC_DA7213=m
 CONFIG_SND_SOC_ES7134=m
@@ -961,7 +983,6 @@ CONFIG_SND_SOC_MSM8916_WCD_DIGITAL=m
 CONFIG_SND_SOC_PCM3168A_I2C=m
 CONFIG_SND_SOC_RK817=m
 CONFIG_SND_SOC_RT5640=m
-CONFIG_SND_SOC_J721E_EVM=m
 CONFIG_SND_SOC_RT5659=m
 CONFIG_SND_SOC_SIMPLE_AMPLIFIER=m
 CONFIG_SND_SOC_SIMPLE_MUX=m
@@ -977,6 +998,8 @@ CONFIG_SND_SOC_WM8960=m
 CONFIG_SND_SOC_WM8962=m
 CONFIG_SND_SOC_WM8978=m
 CONFIG_SND_SOC_WSA881X=m
+CONFIG_SND_SOC_WSA883X=m
+CONFIG_SND_SOC_WSA884X=m
 CONFIG_SND_SOC_NAU8822=m
 CONFIG_SND_SOC_LPASS_WSA_MACRO=m
 CONFIG_SND_SOC_LPASS_VA_MACRO=m
@@ -1047,14 +1070,15 @@ CONFIG_TYPEC=m
 CONFIG_TYPEC_TCPM=m
 CONFIG_TYPEC_TCPCI=m
 CONFIG_TYPEC_FUSB302=m
-CONFIG_TYPEC_TPS6598X=m
-CONFIG_TYPEC_HD3SS3220=m
 CONFIG_TYPEC_QCOM_PMIC=m
 CONFIG_TYPEC_UCSI=m
-CONFIG_TYPEC_MUX_FSA4480=m
-CONFIG_TYPEC_MUX_NB7VPQ904M=m
 CONFIG_UCSI_CCG=m
+CONFIG_UCSI_PMIC_GLINK=m
+CONFIG_TYPEC_TPS6598X=m
+CONFIG_TYPEC_HD3SS3220=m
+CONFIG_TYPEC_MUX_FSA4480=m
 CONFIG_TYPEC_MUX_GPIO_SBU=m
+CONFIG_TYPEC_MUX_NB7VPQ904M=m
 CONFIG_TYPEC_DP_ALTMODE=m
 CONFIG_MMC=y
 CONFIG_MMC_BLOCK_MINORS=32
@@ -1183,6 +1207,7 @@ CONFIG_CROS_EC=y
 CONFIG_CROS_EC_I2C=y
 CONFIG_CROS_EC_RPMSG=m
 CONFIG_CROS_EC_SPI=y
+CONFIG_CROS_KBD_LED_BACKLIGHT=m
 CONFIG_CROS_EC_CHARDEV=m
 CONFIG_COMMON_CLK_RK808=y
 CONFIG_COMMON_CLK_SCMI=y
@@ -1192,6 +1217,7 @@ CONFIG_COMMON_CLK_FSL_SAI=y
 CONFIG_COMMON_CLK_S2MPS11=y
 CONFIG_COMMON_CLK_PWM=y
 CONFIG_COMMON_CLK_RS9_PCIE=y
+CONFIG_COMMON_CLK_VC3=y
 CONFIG_COMMON_CLK_VC5=y
 CONFIG_COMMON_CLK_BD718XX=m
 CONFIG_CLK_RASPBERRYPI=m
@@ -1216,30 +1242,32 @@ CONFIG_COMMON_CLK_MT8192_SCP_ADSP=y
 CONFIG_COMMON_CLK_MT8192_VDECSYS=y
 CONFIG_COMMON_CLK_MT8192_VENCSYS=y
 CONFIG_COMMON_CLK_QCOM=y
+CONFIG_CLK_X1E80100_GCC=y
 CONFIG_QCOM_A53PLL=y
 CONFIG_QCOM_CLK_APCS_MSM8916=y
 CONFIG_QCOM_CLK_APCC_MSM8996=y
 CONFIG_QCOM_CLK_SMD_RPM=y
 CONFIG_QCOM_CLK_RPMH=y
 CONFIG_IPQ_APSS_6018=y
-CONFIG_IPQ_GCC_5332=y
 CONFIG_IPQ_APSS_5018=y
 CONFIG_IPQ_GCC_5018=y
+CONFIG_IPQ_GCC_5332=y
 CONFIG_IPQ_GCC_6018=y
 CONFIG_IPQ_GCC_8074=y
 CONFIG_IPQ_GCC_9574=y
 CONFIG_MSM_GCC_8916=y
+CONFIG_MSM_MMCC_8994=m
 CONFIG_MSM_GCC_8994=y
 CONFIG_MSM_GCC_8996=y
-CONFIG_MSM_MMCC_8994=m
 CONFIG_MSM_MMCC_8996=m
-CONFIG_MSM_MMCC_8998=m
 CONFIG_MSM_GCC_8998=y
+CONFIG_MSM_MMCC_8998=m
 CONFIG_QCM_GCC_2290=y
 CONFIG_QCM_DISPCC_2290=m
 CONFIG_QCS_GCC_404=y
-CONFIG_SA_GCC_8775P=y
+CONFIG_SC_CAMCC_8280XP=m
 CONFIG_SC_DISPCC_8280XP=m
+CONFIG_SA_GCC_8775P=y
 CONFIG_SA_GPUCC_8775P=m
 CONFIG_SC_GCC_7180=y
 CONFIG_SC_GCC_7280=y
@@ -1252,19 +1280,27 @@ CONFIG_SDM_GPUCC_845=y
 CONFIG_SDM_VIDEOCC_845=y
 CONFIG_SDM_DISPCC_845=y
 CONFIG_SDM_LPASSCC_845=m
+CONFIG_SDX_GCC_75=y
 CONFIG_SM_CAMCC_8250=m
 CONFIG_SM_DISPCC_6115=m
 CONFIG_SM_DISPCC_8250=y
 CONFIG_SM_DISPCC_8450=m
 CONFIG_SM_DISPCC_8550=m
+CONFIG_SM_DISPCC_8650=m
+CONFIG_SM_GCC_4450=y
 CONFIG_SM_GCC_6115=y
 CONFIG_SM_GCC_8350=y
 CONFIG_SM_GCC_8450=y
 CONFIG_SM_GCC_8550=y
-CONFIG_SM_TCSRCC_8550=y
+CONFIG_SM_GCC_8650=y
 CONFIG_SM_GPUCC_6115=m
 CONFIG_SM_GPUCC_8150=y
 CONFIG_SM_GPUCC_8250=y
+CONFIG_SM_GPUCC_8450=m
+CONFIG_SM_GPUCC_8550=m
+CONFIG_SM_GPUCC_8650=m
+CONFIG_SM_TCSRCC_8550=y
+CONFIG_SM_TCSRCC_8650=y
 CONFIG_SM_VIDEOCC_8250=y
 CONFIG_QCOM_HFPLL=y
 CONFIG_CLK_GFM_LPASS_SM8250=m
@@ -1279,6 +1315,7 @@ CONFIG_OMAP2PLUS_MBOX=m
 CONFIG_PLATFORM_MHU=y
 CONFIG_BCM2835_MBOX=y
 CONFIG_QCOM_APCS_IPC=y
+CONFIG_MTK_ADSP_MBOX=m
 CONFIG_QCOM_IPCC=y
 CONFIG_ROCKCHIP_IOMMU=y
 CONFIG_TEGRA_IOMMU_SMMU=y
@@ -1288,14 +1325,14 @@ CONFIG_MTK_IOMMU=y
 CONFIG_QCOM_IOMMU=y
 CONFIG_REMOTEPROC=y
 CONFIG_IMX_REMOTEPROC=y
-CONFIG_TI_K3_R5_REMOTEPROC=m
-CONFIG_TI_K3_DSP_REMOTEPROC=m
 CONFIG_MTK_SCP=m
 CONFIG_QCOM_Q6V5_ADSP=m
 CONFIG_QCOM_Q6V5_MSS=m
 CONFIG_QCOM_Q6V5_PAS=m
 CONFIG_QCOM_SYSMON=m
 CONFIG_QCOM_WCNSS_PIL=m
+CONFIG_TI_K3_DSP_REMOTEPROC=m
+CONFIG_TI_K3_R5_REMOTEPROC=m
 CONFIG_RPMSG_CHAR=m
 CONFIG_RPMSG_CTRL=m
 CONFIG_RPMSG_QCOM_GLINK_RPM=y
@@ -1304,8 +1341,6 @@ CONFIG_RPMSG_QCOM_SMD=y
 CONFIG_RPMSG_VIRTIO=y
 CONFIG_SOUNDWIRE=m
 CONFIG_SOUNDWIRE_QCOM=m
-CONFIG_OWL_PM_DOMAINS=y
-CONFIG_RASPBERRYPI_POWER=y
 CONFIG_FSL_DPAA=y
 CONFIG_FSL_MC_DPIO=y
 CONFIG_FSL_RCPM=y
@@ -1315,15 +1350,12 @@ CONFIG_MTK_PMIC_WRAP=y
 CONFIG_MTK_SVS=m
 CONFIG_QCOM_AOSS_QMP=y
 CONFIG_QCOM_COMMAND_DB=y
-CONFIG_QCOM_CPR=y
 CONFIG_QCOM_GENI_SE=y
 CONFIG_QCOM_LLCC=m
 CONFIG_QCOM_OCMEM=m
 CONFIG_QCOM_PMIC_GLINK=m
 CONFIG_QCOM_RMTFS_MEM=m
 CONFIG_QCOM_RPMH=y
-CONFIG_QCOM_RPMHPD=y
-CONFIG_QCOM_RPMPD=y
 CONFIG_QCOM_SMEM=y
 CONFIG_QCOM_SMD_RPM=y
 CONFIG_QCOM_SMP2P=y
@@ -1355,14 +1387,20 @@ CONFIG_ARCH_R9A07G054=y
 CONFIG_ARCH_R9A08G045=y
 CONFIG_ARCH_R9A09G011=y
 CONFIG_ROCKCHIP_IODOMAIN=y
-CONFIG_ROCKCHIP_PM_DOMAINS=y
 CONFIG_ARCH_TEGRA_132_SOC=y
 CONFIG_ARCH_TEGRA_210_SOC=y
 CONFIG_ARCH_TEGRA_186_SOC=y
 CONFIG_ARCH_TEGRA_194_SOC=y
 CONFIG_ARCH_TEGRA_234_SOC=y
-CONFIG_TI_SCI_PM_DOMAINS=y
 CONFIG_TI_PRUSS=m
+CONFIG_OWL_PM_DOMAINS=y
+CONFIG_RASPBERRYPI_POWER=y
+CONFIG_IMX_SCU_PD=y
+CONFIG_QCOM_CPR=y
+CONFIG_QCOM_RPMHPD=y
+CONFIG_QCOM_RPMPD=y
+CONFIG_ROCKCHIP_PM_DOMAINS=y
+CONFIG_TI_SCI_PM_DOMAINS=y
 CONFIG_ARM_IMX_BUS_DEVFREQ=y
 CONFIG_ARM_IMX8M_DDRC_DEVFREQ=m
 CONFIG_ARM_MEDIATEK_CCI_DEVFREQ=m
@@ -1421,6 +1459,7 @@ CONFIG_PHY_XGENE=y
 CONFIG_PHY_CAN_TRANSCEIVER=m
 CONFIG_PHY_SUN4I_USB=y
 CONFIG_PHY_CADENCE_TORRENT=m
+CONFIG_PHY_CADENCE_DPHY_RX=m
 CONFIG_PHY_CADENCE_SIERRA=m
 CONFIG_PHY_MIXEL_MIPI_DPHY=m
 CONFIG_PHY_FSL_IMX8M_PCIE=y
@@ -1430,17 +1469,17 @@ CONFIG_PHY_HISI_INNO_USB2=y
 CONFIG_PHY_MVEBU_CP110_COMPHY=y
 CONFIG_PHY_MTK_TPHY=y
 CONFIG_PHY_QCOM_EDP=m
-CONFIG_PHY_QCOM_EUSB2_REPEATER=m
 CONFIG_PHY_QCOM_PCIE2=m
 CONFIG_PHY_QCOM_QMP=m
 CONFIG_PHY_QCOM_QUSB2=m
 CONFIG_PHY_QCOM_SNPS_EUSB2=m
+CONFIG_PHY_QCOM_EUSB2_REPEATER=m
+CONFIG_PHY_QCOM_M31_USB=m
 CONFIG_PHY_QCOM_USB_HS=m
 CONFIG_PHY_QCOM_USB_SNPS_FEMTO_V2=m
 CONFIG_PHY_QCOM_USB_HS_28NM=m
 CONFIG_PHY_QCOM_USB_SS=m
 CONFIG_PHY_QCOM_SGMII_ETH=m
-CONFIG_PHY_QCOM_M31_USB=m
 CONFIG_PHY_R8A779F0_ETHERNET_SERDES=y
 CONFIG_PHY_RCAR_GEN3_PCIE=y
 CONFIG_PHY_RCAR_GEN3_USB2=y
@@ -1462,7 +1501,6 @@ CONFIG_PHY_J721E_WIZ=m
 CONFIG_ARM_CCI_PMU=m
 CONFIG_ARM_CCN=m
 CONFIG_ARM_CMN=m
-CONFIG_ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU=m
 CONFIG_ARM_SMMU_V3_PMU=m
 CONFIG_ARM_DSU_PMU=m
 CONFIG_FSL_IMX8_DDR_PMU=m
@@ -1471,6 +1509,7 @@ CONFIG_QCOM_L3_PMU=y
 CONFIG_ARM_SPE_PMU=m
 CONFIG_ARM_DMC620_PMU=m
 CONFIG_HISI_PMU=y
+CONFIG_ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU=m
 CONFIG_MESON_DDR_PMU=m
 CONFIG_NVMEM_LAYOUT_SL28_VPD=m
 CONFIG_NVMEM_IMX_OCOTP=y
@@ -1519,11 +1558,14 @@ CONFIG_INTERCONNECT_QCOM_SC7280=y
 CONFIG_INTERCONNECT_QCOM_SC8180X=y
 CONFIG_INTERCONNECT_QCOM_SC8280XP=y
 CONFIG_INTERCONNECT_QCOM_SDM845=y
+CONFIG_INTERCONNECT_QCOM_SDX75=y
 CONFIG_INTERCONNECT_QCOM_SM8150=m
 CONFIG_INTERCONNECT_QCOM_SM8250=m
 CONFIG_INTERCONNECT_QCOM_SM8350=m
 CONFIG_INTERCONNECT_QCOM_SM8450=y
 CONFIG_INTERCONNECT_QCOM_SM8550=y
+CONFIG_INTERCONNECT_QCOM_SM8650=y
+CONFIG_INTERCONNECT_QCOM_X1E80100=y
 CONFIG_COUNTER=m
 CONFIG_RZ_MTU3_CNT=m
 CONFIG_HTE=y
@@ -1546,6 +1588,7 @@ CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_HUGETLBFS=y
 CONFIG_CONFIGFS_FS=y
 CONFIG_EFIVAR_FS=y
+CONFIG_UBIFS_FS=m
 CONFIG_SQUASHFS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=y
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index 6d06b448a66e..eb7b423ba463 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -231,7 +231,7 @@ config CRYPTO_SM4_ARM64_CE
 	  - NEON (Advanced SIMD) extensions
 
 config CRYPTO_SM4_ARM64_CE_BLK
-	tristate "Ciphers: SM4, modes: ECB/CBC/CFB/CTR/XTS (ARMv8 Crypto Extensions)"
+	tristate "Ciphers: SM4, modes: ECB/CBC/CTR/XTS (ARMv8 Crypto Extensions)"
 	depends on KERNEL_MODE_NEON
 	select CRYPTO_SKCIPHER
 	select CRYPTO_SM4
@@ -240,7 +240,6 @@ config CRYPTO_SM4_ARM64_CE_BLK
 	  with block cipher modes:
 	  - ECB (Electronic Codebook) mode (NIST SP800-38A)
 	  - CBC (Cipher Block Chaining) mode (NIST SP800-38A)
-	  - CFB (Cipher Feedback) mode (NIST SP800-38A)
 	  - CTR (Counter) mode (NIST SP800-38A)
 	  - XTS (XOR Encrypt XOR with ciphertext stealing) mode (NIST SP800-38E
 	    and IEEE 1619)
@@ -250,7 +249,7 @@ config CRYPTO_SM4_ARM64_CE_BLK
 	  - NEON (Advanced SIMD) extensions
 
 config CRYPTO_SM4_ARM64_NEON_BLK
-	tristate "Ciphers: SM4, modes: ECB/CBC/CFB/CTR (NEON)"
+	tristate "Ciphers: SM4, modes: ECB/CBC/CTR (NEON)"
 	depends on KERNEL_MODE_NEON
 	select CRYPTO_SKCIPHER
 	select CRYPTO_SM4
@@ -259,7 +258,6 @@ config CRYPTO_SM4_ARM64_NEON_BLK
 	  with block cipher modes:
 	  - ECB (Electronic Codebook) mode (NIST SP800-38A)
 	  - CBC (Cipher Block Chaining) mode (NIST SP800-38A)
-	  - CFB (Cipher Feedback) mode (NIST SP800-38A)
 	  - CTR (Counter) mode (NIST SP800-38A)
 
 	  Architecture: arm64 using:
diff --git a/arch/arm64/crypto/sm4-ce-core.S b/arch/arm64/crypto/sm4-ce-core.S
index 877b80c54a0d..1f3625c2c67e 100644
--- a/arch/arm64/crypto/sm4-ce-core.S
+++ b/arch/arm64/crypto/sm4-ce-core.S
@@ -403,164 +403,6 @@ SYM_FUNC_START(sm4_ce_cbc_cts_dec)
 SYM_FUNC_END(sm4_ce_cbc_cts_dec)
 
 .align 3
-SYM_FUNC_START(sm4_ce_cfb_enc)
-	/* input:
-	 *   x0: round key array, CTX
-	 *   x1: dst
-	 *   x2: src
-	 *   x3: iv (big endian, 128 bit)
-	 *   w4: nblocks
-	 */
-	SM4_PREPARE(x0)
-
-	ld1		{RIV.16b}, [x3]
-
-.Lcfb_enc_loop_4x:
-	cmp		w4, #4
-	blt		.Lcfb_enc_loop_1x
-
-	sub		w4, w4, #4
-
-	ld1		{v0.16b-v3.16b}, [x2], #64
-
-	rev32		v8.16b, RIV.16b
-	SM4_CRYPT_BLK_BE(v8)
-	eor		v0.16b, v0.16b, v8.16b
-
-	rev32		v8.16b, v0.16b
-	SM4_CRYPT_BLK_BE(v8)
-	eor		v1.16b, v1.16b, v8.16b
-
-	rev32		v8.16b, v1.16b
-	SM4_CRYPT_BLK_BE(v8)
-	eor		v2.16b, v2.16b, v8.16b
-
-	rev32		v8.16b, v2.16b
-	SM4_CRYPT_BLK_BE(v8)
-	eor		v3.16b, v3.16b, v8.16b
-
-	st1		{v0.16b-v3.16b}, [x1], #64
-	mov		RIV.16b, v3.16b
-
-	cbz		w4, .Lcfb_enc_end
-	b		.Lcfb_enc_loop_4x
-
-.Lcfb_enc_loop_1x:
-	sub		w4, w4, #1
-
-	ld1		{v0.16b}, [x2], #16
-
-	SM4_CRYPT_BLK(RIV)
-	eor		RIV.16b, RIV.16b, v0.16b
-
-	st1		{RIV.16b}, [x1], #16
-
-	cbnz		w4, .Lcfb_enc_loop_1x
-
-.Lcfb_enc_end:
-	/* store new IV */
-	st1		{RIV.16b}, [x3]
-
-	ret
-SYM_FUNC_END(sm4_ce_cfb_enc)
-
-.align 3
-SYM_FUNC_START(sm4_ce_cfb_dec)
-	/* input:
-	 *   x0: round key array, CTX
-	 *   x1: dst
-	 *   x2: src
-	 *   x3: iv (big endian, 128 bit)
-	 *   w4: nblocks
-	 */
-	SM4_PREPARE(x0)
-
-	ld1		{RIV.16b}, [x3]
-
-.Lcfb_dec_loop_8x:
-	sub		w4, w4, #8
-	tbnz		w4, #31, .Lcfb_dec_4x
-
-	ld1		{v0.16b-v3.16b}, [x2], #64
-	ld1		{v4.16b-v7.16b}, [x2], #64
-
-	rev32		v8.16b, RIV.16b
-	rev32		v9.16b, v0.16b
-	rev32		v10.16b, v1.16b
-	rev32		v11.16b, v2.16b
-	rev32		v12.16b, v3.16b
-	rev32		v13.16b, v4.16b
-	rev32		v14.16b, v5.16b
-	rev32		v15.16b, v6.16b
-
-	SM4_CRYPT_BLK8_BE(v8, v9, v10, v11, v12, v13, v14, v15)
-
-	mov		RIV.16b, v7.16b
-
-	eor		v0.16b, v0.16b, v8.16b
-	eor		v1.16b, v1.16b, v9.16b
-	eor		v2.16b, v2.16b, v10.16b
-	eor		v3.16b, v3.16b, v11.16b
-	eor		v4.16b, v4.16b, v12.16b
-	eor		v5.16b, v5.16b, v13.16b
-	eor		v6.16b, v6.16b, v14.16b
-	eor		v7.16b, v7.16b, v15.16b
-
-	st1		{v0.16b-v3.16b}, [x1], #64
-	st1		{v4.16b-v7.16b}, [x1], #64
-
-	cbz		w4, .Lcfb_dec_end
-	b		.Lcfb_dec_loop_8x
-
-.Lcfb_dec_4x:
-	add		w4, w4, #8
-	cmp		w4, #4
-	blt		.Lcfb_dec_loop_1x
-
-	sub		w4, w4, #4
-
-	ld1		{v0.16b-v3.16b}, [x2], #64
-
-	rev32		v8.16b, RIV.16b
-	rev32		v9.16b, v0.16b
-	rev32		v10.16b, v1.16b
-	rev32		v11.16b, v2.16b
-
-	SM4_CRYPT_BLK4_BE(v8, v9, v10, v11)
-
-	mov		RIV.16b, v3.16b
-
-	eor		v0.16b, v0.16b, v8.16b
-	eor		v1.16b, v1.16b, v9.16b
-	eor		v2.16b, v2.16b, v10.16b
-	eor		v3.16b, v3.16b, v11.16b
-
-	st1		{v0.16b-v3.16b}, [x1], #64
-
-	cbz		w4, .Lcfb_dec_end
-
-.Lcfb_dec_loop_1x:
-	sub		w4, w4, #1
-
-	ld1		{v0.16b}, [x2], #16
-
-	SM4_CRYPT_BLK(RIV)
-
-	eor		RIV.16b, RIV.16b, v0.16b
-	st1		{RIV.16b}, [x1], #16
-
-	mov		RIV.16b, v0.16b
-
-	cbnz		w4, .Lcfb_dec_loop_1x
-
-.Lcfb_dec_end:
-	/* store new IV */
-	st1		{RIV.16b}, [x3]
-
-	ret
-SYM_FUNC_END(sm4_ce_cfb_dec)
-
-.align 3
 SYM_FUNC_START(sm4_ce_ctr_enc)
 	/* input:
 	 *   x0: round key array, CTX
diff --git a/arch/arm64/crypto/sm4-ce-glue.c b/arch/arm64/crypto/sm4-ce-glue.c
index 0a2d32ed3bde..43741bed874e 100644
--- a/arch/arm64/crypto/sm4-ce-glue.c
+++ b/arch/arm64/crypto/sm4-ce-glue.c
@@ -37,10 +37,6 @@ asmlinkage void sm4_ce_cbc_cts_enc(const u32 *rkey, u8 *dst, const u8 *src,
 				   u8 *iv, unsigned int nbytes);
 asmlinkage void sm4_ce_cbc_cts_dec(const u32 *rkey, u8 *dst, const u8 *src,
 				   u8 *iv, unsigned int nbytes);
-asmlinkage void sm4_ce_cfb_enc(const u32 *rkey, u8 *dst, const u8 *src,
-			       u8 *iv, unsigned int nblks);
-asmlinkage void sm4_ce_cfb_dec(const u32 *rkey, u8 *dst, const u8 *src,
-			       u8 *iv, unsigned int nblks);
 asmlinkage void sm4_ce_ctr_enc(const u32 *rkey, u8 *dst, const u8 *src,
 			       u8 *iv, unsigned int nblks);
 asmlinkage void sm4_ce_xts_enc(const u32 *rkey1, u8 *dst, const u8 *src,
@@ -56,7 +52,6 @@ asmlinkage void sm4_ce_mac_update(const u32 *rkey_enc, u8 *digest,
 EXPORT_SYMBOL(sm4_ce_expand_key);
 EXPORT_SYMBOL(sm4_ce_crypt_block);
 EXPORT_SYMBOL(sm4_ce_cbc_enc);
-EXPORT_SYMBOL(sm4_ce_cfb_enc);
 
 struct sm4_xts_ctx {
 	struct sm4_ctx key1;
@@ -280,90 +275,6 @@ static int sm4_cbc_cts_decrypt(struct skcipher_request *req)
 	return sm4_cbc_cts_crypt(req, false);
 }
 
-static int sm4_cfb_encrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct skcipher_walk walk;
-	unsigned int nbytes;
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	while ((nbytes = walk.nbytes) > 0) {
-		const u8 *src = walk.src.virt.addr;
-		u8 *dst = walk.dst.virt.addr;
-		unsigned int nblks;
-
-		kernel_neon_begin();
-
-		nblks = BYTES2BLKS(nbytes);
-		if (nblks) {
-			sm4_ce_cfb_enc(ctx->rkey_enc, dst, src, walk.iv, nblks);
-			dst += nblks * SM4_BLOCK_SIZE;
-			src += nblks * SM4_BLOCK_SIZE;
-			nbytes -= nblks * SM4_BLOCK_SIZE;
-		}
-
-		/* tail */
-		if (walk.nbytes == walk.total && nbytes > 0) {
-			u8 keystream[SM4_BLOCK_SIZE];
-
-			sm4_ce_crypt_block(ctx->rkey_enc, keystream, walk.iv);
-			crypto_xor_cpy(dst, src, keystream, nbytes);
-			nbytes = 0;
-		}
-
-		kernel_neon_end();
-
-		err = skcipher_walk_done(&walk, nbytes);
-	}
-
-	return err;
-}
-
-static int sm4_cfb_decrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct skcipher_walk walk;
-	unsigned int nbytes;
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	while ((nbytes = walk.nbytes) > 0) {
-		const u8 *src = walk.src.virt.addr;
-		u8 *dst = walk.dst.virt.addr;
-		unsigned int nblks;
-
-		kernel_neon_begin();
-
-		nblks = BYTES2BLKS(nbytes);
-		if (nblks) {
-			sm4_ce_cfb_dec(ctx->rkey_enc, dst, src, walk.iv, nblks);
-			dst += nblks * SM4_BLOCK_SIZE;
-			src += nblks * SM4_BLOCK_SIZE;
-			nbytes -= nblks * SM4_BLOCK_SIZE;
-		}
-
-		/* tail */
-		if (walk.nbytes == walk.total && nbytes > 0) {
-			u8 keystream[SM4_BLOCK_SIZE];
-
-			sm4_ce_crypt_block(ctx->rkey_enc, keystream, walk.iv);
-			crypto_xor_cpy(dst, src, keystream, nbytes);
-			nbytes = 0;
-		}
-
-		kernel_neon_end();
-
-		err = skcipher_walk_done(&walk, nbytes);
-	}
-
-	return err;
-}
-
 static int sm4_ctr_crypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
@@ -544,22 +455,6 @@ static struct skcipher_alg sm4_algs[] = {
 		.decrypt	= sm4_cbc_decrypt,
 	}, {
 		.base = {
-			.cra_name		= "cfb(sm4)",
-			.cra_driver_name	= "cfb-sm4-ce",
-			.cra_priority		= 400,
-			.cra_blocksize		= 1,
-			.cra_ctxsize		= sizeof(struct sm4_ctx),
-			.cra_module		= THIS_MODULE,
-		},
-		.min_keysize	= SM4_KEY_SIZE,
-		.max_keysize	= SM4_KEY_SIZE,
-		.ivsize		= SM4_BLOCK_SIZE,
-		.chunksize	= SM4_BLOCK_SIZE,
-		.setkey		= sm4_setkey,
-		.encrypt	= sm4_cfb_encrypt,
-		.decrypt	= sm4_cfb_decrypt,
-	}, {
-		.base = {
 			.cra_name		= "ctr(sm4)",
 			.cra_driver_name	= "ctr-sm4-ce",
 			.cra_priority		= 400,
@@ -869,12 +764,11 @@ static void __exit sm4_exit(void)
 module_cpu_feature_match(SM4, sm4_init);
 module_exit(sm4_exit);
 
-MODULE_DESCRIPTION("SM4 ECB/CBC/CFB/CTR/XTS using ARMv8 Crypto Extensions");
+MODULE_DESCRIPTION("SM4 ECB/CBC/CTR/XTS using ARMv8 Crypto Extensions");
 MODULE_ALIAS_CRYPTO("sm4-ce");
 MODULE_ALIAS_CRYPTO("sm4");
 MODULE_ALIAS_CRYPTO("ecb(sm4)");
 MODULE_ALIAS_CRYPTO("cbc(sm4)");
-MODULE_ALIAS_CRYPTO("cfb(sm4)");
 MODULE_ALIAS_CRYPTO("ctr(sm4)");
 MODULE_ALIAS_CRYPTO("cts(cbc(sm4))");
 MODULE_ALIAS_CRYPTO("xts(sm4)");
diff --git a/arch/arm64/crypto/sm4-ce.h b/arch/arm64/crypto/sm4-ce.h
index 109c21b37590..1e235c4371eb 100644
--- a/arch/arm64/crypto/sm4-ce.h
+++ b/arch/arm64/crypto/sm4-ce.h
@@ -11,6 +11,3 @@ void sm4_ce_crypt_block(const u32 *rkey, u8 *dst, const u8 *src);
 
 void sm4_ce_cbc_enc(const u32 *rkey_enc, u8 *dst, const u8 *src,
 		    u8 *iv, unsigned int nblocks);
-
-void sm4_ce_cfb_enc(const u32 *rkey_enc, u8 *dst, const u8 *src,
-		    u8 *iv, unsigned int nblocks);
diff --git a/arch/arm64/crypto/sm4-neon-core.S b/arch/arm64/crypto/sm4-neon-core.S
index f295b4b7d70a..734dc7193610 100644
--- a/arch/arm64/crypto/sm4-neon-core.S
+++ b/arch/arm64/crypto/sm4-neon-core.S
@@ -438,119 +438,6 @@ SYM_FUNC_START(sm4_neon_cbc_dec)
 SYM_FUNC_END(sm4_neon_cbc_dec)
 
 .align 3
-SYM_FUNC_START(sm4_neon_cfb_dec)
-	/* input:
-	 *   x0: round key array, CTX
-	 *   x1: dst
-	 *   x2: src
-	 *   x3: iv (big endian, 128 bit)
-	 *   w4: nblocks
-	 */
-	SM4_PREPARE()
-
-	ld1		{v0.16b}, [x3]
-
-.Lcfb_dec_loop_8x:
-	sub		w4, w4, #8
-	tbnz		w4, #31, .Lcfb_dec_4x
-
-	ld1		{v1.16b-v3.16b}, [x2], #48
-	ld4		{v4.4s-v7.4s}, [x2]
-
-	transpose_4x4(v0, v1, v2, v3)
-
-	SM4_CRYPT_BLK8(v0, v1, v2, v3, v4, v5, v6, v7)
-
-	sub		x2, x2, #48
-	ld1		{RTMP0.16b-RTMP3.16b}, [x2], #64
-	ld1		{RTMP4.16b-RTMP7.16b}, [x2], #64
-
-	eor		v0.16b, v0.16b, RTMP0.16b
-	eor		v1.16b, v1.16b, RTMP1.16b
-	eor		v2.16b, v2.16b, RTMP2.16b
-	eor		v3.16b, v3.16b, RTMP3.16b
-	eor		v4.16b, v4.16b, RTMP4.16b
-	eor		v5.16b, v5.16b, RTMP5.16b
-	eor		v6.16b, v6.16b, RTMP6.16b
-	eor		v7.16b, v7.16b, RTMP7.16b
-
-	st1		{v0.16b-v3.16b}, [x1], #64
-	st1		{v4.16b-v7.16b}, [x1], #64
-
-	mov		v0.16b, RTMP7.16b
-
-	cbz		w4, .Lcfb_dec_end
-	b		.Lcfb_dec_loop_8x
-
-.Lcfb_dec_4x:
-	add		w4, w4, #8
-	cmp		w4, #4
-	blt		.Lcfb_dec_tail
-
-	sub		w4, w4, #4
-
-	ld1		{v4.16b-v7.16b}, [x2], #64
-
-	rev32		v0.16b, v0.16b		/* v0 is IV register */
-	rev32		v1.16b, v4.16b
-	rev32		v2.16b, v5.16b
-	rev32		v3.16b, v6.16b
-
-	transpose_4x4(v0, v1, v2, v3)
-
-	SM4_CRYPT_BLK4_BE(v0, v1, v2, v3)
-
-	eor		v0.16b, v0.16b, v4.16b
-	eor		v1.16b, v1.16b, v5.16b
-	eor		v2.16b, v2.16b, v6.16b
-	eor		v3.16b, v3.16b, v7.16b
-
-	st1		{v0.16b-v3.16b}, [x1], #64
-
-	mov		v0.16b, v7.16b
-
-	cbz		w4, .Lcfb_dec_end
-
-.Lcfb_dec_tail:
-	cmp		w4, #2
-	ld1		{v4.16b}, [x2], #16
-	blt		.Lcfb_dec_tail_load_done
-	ld1		{v5.16b}, [x2], #16
-	beq		.Lcfb_dec_tail_load_done
-	ld1		{v6.16b}, [x2], #16
-
-.Lcfb_dec_tail_load_done:
-	rev32		v0.16b, v0.16b		/* v0 is IV register */
-	rev32		v1.16b, v4.16b
-	rev32		v2.16b, v5.16b
-
-	transpose_4x4(v0, v1, v2, v3)
-
-	SM4_CRYPT_BLK4_BE(v0, v1, v2, v3)
-
-	cmp		w4, #2
-	eor		v0.16b, v0.16b, v4.16b
-	st1		{v0.16b}, [x1], #16
-	mov		v0.16b, v4.16b
-	blt		.Lcfb_dec_end
-
-	eor		v1.16b, v1.16b, v5.16b
-	st1		{v1.16b}, [x1], #16
-	mov		v0.16b, v5.16b
-	beq		.Lcfb_dec_end
-
-	eor		v2.16b, v2.16b, v6.16b
-	st1		{v2.16b}, [x1], #16
-	mov		v0.16b, v6.16b
-
-.Lcfb_dec_end:
-	/* store new IV */
-	st1		{v0.16b}, [x3]
-
-	ret
-SYM_FUNC_END(sm4_neon_cfb_dec)
-
-.align 3
 SYM_FUNC_START(sm4_neon_ctr_crypt)
 	/* input:
 	 *   x0: round key array, CTX
diff --git a/arch/arm64/crypto/sm4-neon-glue.c b/arch/arm64/crypto/sm4-neon-glue.c
index 7b19accf5c03..e3500aca2d18 100644
--- a/arch/arm64/crypto/sm4-neon-glue.c
+++ b/arch/arm64/crypto/sm4-neon-glue.c
@@ -22,8 +22,6 @@ asmlinkage void sm4_neon_crypt(const u32 *rkey, u8 *dst, const u8 *src,
 			       unsigned int nblocks);
 asmlinkage void sm4_neon_cbc_dec(const u32 *rkey_dec, u8 *dst, const u8 *src,
 				 u8 *iv, unsigned int nblocks);
-asmlinkage void sm4_neon_cfb_dec(const u32 *rkey_enc, u8 *dst, const u8 *src,
-				 u8 *iv, unsigned int nblocks);
 asmlinkage void sm4_neon_ctr_crypt(const u32 *rkey_enc, u8 *dst, const u8 *src,
 				   u8 *iv, unsigned int nblocks);
 
@@ -142,90 +140,6 @@ static int sm4_cbc_decrypt(struct skcipher_request *req)
 	return err;
 }
 
-static int sm4_cfb_encrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct skcipher_walk walk;
-	unsigned int nbytes;
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	while ((nbytes = walk.nbytes) > 0) {
-		u8 keystream[SM4_BLOCK_SIZE];
-		const u8 *iv = walk.iv;
-		const u8 *src = walk.src.virt.addr;
-		u8 *dst = walk.dst.virt.addr;
-
-		while (nbytes >= SM4_BLOCK_SIZE) {
-			sm4_crypt_block(ctx->rkey_enc, keystream, iv);
-			crypto_xor_cpy(dst, src, keystream, SM4_BLOCK_SIZE);
-			iv = dst;
-			src += SM4_BLOCK_SIZE;
-			dst += SM4_BLOCK_SIZE;
-			nbytes -= SM4_BLOCK_SIZE;
-		}
-		if (iv != walk.iv)
-			memcpy(walk.iv, iv, SM4_BLOCK_SIZE);
-
-		/* tail */
-		if (walk.nbytes == walk.total && nbytes > 0) {
-			sm4_crypt_block(ctx->rkey_enc, keystream, walk.iv);
-			crypto_xor_cpy(dst, src, keystream, nbytes);
-			nbytes = 0;
-		}
-
-		err = skcipher_walk_done(&walk, nbytes);
-	}
-
-	return err;
-}
-
-static int sm4_cfb_decrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct skcipher_walk walk;
-	unsigned int nbytes;
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	while ((nbytes = walk.nbytes) > 0) {
-		const u8 *src = walk.src.virt.addr;
-		u8 *dst = walk.dst.virt.addr;
-		unsigned int nblocks;
-
-		nblocks = nbytes / SM4_BLOCK_SIZE;
-		if (nblocks) {
-			kernel_neon_begin();
-
-			sm4_neon_cfb_dec(ctx->rkey_enc, dst, src,
-					 walk.iv, nblocks);
-
-			kernel_neon_end();
-
-			dst += nblocks * SM4_BLOCK_SIZE;
-			src += nblocks * SM4_BLOCK_SIZE;
-			nbytes -= nblocks * SM4_BLOCK_SIZE;
-		}
-
-		/* tail */
-		if (walk.nbytes == walk.total && nbytes > 0) {
-			u8 keystream[SM4_BLOCK_SIZE];
-
-			sm4_crypt_block(ctx->rkey_enc, keystream, walk.iv);
-			crypto_xor_cpy(dst, src, keystream, nbytes);
-			nbytes = 0;
-		}
-
-		err = skcipher_walk_done(&walk, nbytes);
-	}
-
-	return err;
-}
-
 static int sm4_ctr_crypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
@@ -303,22 +217,6 @@ static struct skcipher_alg sm4_algs[] = {
 		.decrypt	= sm4_cbc_decrypt,
 	}, {
 		.base = {
-			.cra_name		= "cfb(sm4)",
-			.cra_driver_name	= "cfb-sm4-neon",
-			.cra_priority		= 200,
-			.cra_blocksize		= 1,
-			.cra_ctxsize		= sizeof(struct sm4_ctx),
-			.cra_module		= THIS_MODULE,
-		},
-		.min_keysize	= SM4_KEY_SIZE,
-		.max_keysize	= SM4_KEY_SIZE,
-		.ivsize		= SM4_BLOCK_SIZE,
-		.chunksize	= SM4_BLOCK_SIZE,
-		.setkey		= sm4_setkey,
-		.encrypt	= sm4_cfb_encrypt,
-		.decrypt	= sm4_cfb_decrypt,
-	}, {
-		.base = {
 			.cra_name		= "ctr(sm4)",
 			.cra_driver_name	= "ctr-sm4-neon",
 			.cra_priority		= 200,
@@ -349,12 +247,11 @@ static void __exit sm4_exit(void)
 module_init(sm4_init);
 module_exit(sm4_exit);
 
-MODULE_DESCRIPTION("SM4 ECB/CBC/CFB/CTR using ARMv8 NEON");
+MODULE_DESCRIPTION("SM4 ECB/CBC/CTR using ARMv8 NEON");
 MODULE_ALIAS_CRYPTO("sm4-neon");
 MODULE_ALIAS_CRYPTO("sm4");
 MODULE_ALIAS_CRYPTO("ecb(sm4)");
 MODULE_ALIAS_CRYPTO("cbc(sm4)");
-MODULE_ALIAS_CRYPTO("cfb(sm4)");
 MODULE_ALIAS_CRYPTO("ctr(sm4)");
 MODULE_AUTHOR("Tianjia Zhang <tianjia.zhang@linux.alibaba.com>");
 MODULE_LICENSE("GPL v2");
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 376a980f2bad..7b1975bf4b90 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -12,7 +12,7 @@
 #ifndef __ASM_ASSEMBLER_H
 #define __ASM_ASSEMBLER_H
 
-#include <asm-generic/export.h>
+#include <linux/export.h>
 
 #include <asm/alternative.h>
 #include <asm/asm-bug.h>
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index ceb368d33bf4..06a4670bdb0b 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -58,7 +58,6 @@ static inline unsigned int arch_slab_minalign(void)
 #define CTR_L1IP(ctr)		SYS_FIELD_GET(CTR_EL0, L1Ip, ctr)
 
 #define ICACHEF_ALIASING	0
-#define ICACHEF_VPIPT		1
 extern unsigned long __icache_flags;
 
 /*
@@ -70,11 +69,6 @@ static inline int icache_is_aliasing(void)
 	return test_bit(ICACHEF_ALIASING, &__icache_flags);
 }
 
-static __always_inline int icache_is_vpipt(void)
-{
-	return test_bit(ICACHEF_VPIPT, &__icache_flags);
-}
-
 static inline u32 cache_type_cwg(void)
 {
 	return SYS_FIELD_GET(CTR_EL0, CWG, read_cpuid_cachetype());
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index f6d416fe49b0..21c824edf8ce 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -617,6 +617,7 @@ static inline bool id_aa64pfr1_mte(u64 pfr1)
 	return val >= ID_AA64PFR1_EL1_MTE_MTE2;
 }
 
+void __init setup_boot_cpu_features(void);
 void __init setup_system_features(void);
 void __init setup_user_features(void);
 
@@ -819,6 +820,11 @@ static inline bool system_supports_tlb_range(void)
 	return alternative_has_cap_unlikely(ARM64_HAS_TLB_RANGE);
 }
 
+static inline bool system_supports_lpa2(void)
+{
+	return cpus_have_final_cap(ARM64_HAS_LPA2);
+}
+
 int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
 bool try_emulate_mrs(struct pt_regs *regs, u32 isn);
 
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index cdf6a35e3994..cda81d009c9b 100644
--- a/arch/arm64/include/asm/fpsimdmacros.h
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -242,14 +242,6 @@
 		| (\nx << 5)
 .endm
 
-/*
- * Zero the entire ZA array
- *	ZERO ZA
- */
-.macro zero_za
-	.inst 0xc00800ff
-.endm
-
 .macro __for from:req, to:req
 	.if (\from) == (\to)
 		_for__body %\from
diff --git a/arch/arm64/include/asm/irq_work.h b/arch/arm64/include/asm/irq_work.h
index 81bbfa3a035b..a1020285ea75 100644
--- a/arch/arm64/include/asm/irq_work.h
+++ b/arch/arm64/include/asm/irq_work.h
@@ -2,8 +2,6 @@
 #ifndef __ASM_IRQ_WORK_H
 #define __ASM_IRQ_WORK_H
 
-extern void arch_irq_work_raise(void);
-
 static inline bool arch_irq_work_has_interrupt(void)
 {
 	return true;
diff --git a/arch/arm64/include/asm/kasan.h b/arch/arm64/include/asm/kasan.h
index 12d5f47f7dbe..7eefc525a9df 100644
--- a/arch/arm64/include/asm/kasan.h
+++ b/arch/arm64/include/asm/kasan.h
@@ -15,29 +15,9 @@
 
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 
+asmlinkage void kasan_early_init(void);
 void kasan_init(void);
-
-/*
- * KASAN_SHADOW_START: beginning of the kernel virtual addresses.
- * KASAN_SHADOW_END: KASAN_SHADOW_START + 1/N of kernel virtual addresses,
- * where N = (1 << KASAN_SHADOW_SCALE_SHIFT).
- *
- * KASAN_SHADOW_OFFSET:
- * This value is used to map an address to the corresponding shadow
- * address by the following formula:
- *     shadow_addr = (address >> KASAN_SHADOW_SCALE_SHIFT) + KASAN_SHADOW_OFFSET
- *
- * (1 << (64 - KASAN_SHADOW_SCALE_SHIFT)) shadow addresses that lie in range
- * [KASAN_SHADOW_OFFSET, KASAN_SHADOW_END) cover all 64-bits of virtual
- * addresses. So KASAN_SHADOW_OFFSET should satisfy the following equation:
- *      KASAN_SHADOW_OFFSET = KASAN_SHADOW_END -
- *				(1ULL << (64 - KASAN_SHADOW_SCALE_SHIFT))
- */
-#define _KASAN_SHADOW_START(va)	(KASAN_SHADOW_END - (1UL << ((va) - KASAN_SHADOW_SCALE_SHIFT)))
-#define KASAN_SHADOW_START      _KASAN_SHADOW_START(vabits_actual)
-
 void kasan_copy_shadow(pgd_t *pgdir);
-asmlinkage void kasan_early_init(void);
 
 #else
 static inline void kasan_init(void) { }
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index 85d26143faa5..83ddb14b95a5 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -37,27 +37,12 @@
 
 
 /*
- * If KASLR is enabled, then an offset K is added to the kernel address
- * space. The bottom 21 bits of this offset are zero to guarantee 2MB
- * alignment for PA and VA.
- *
- * For each pagetable level of the swapper, we know that the shift will
- * be larger than 21 (for the 4KB granule case we use section maps thus
- * the smallest shift is actually 30) thus there is the possibility that
- * KASLR can increase the number of pagetable entries by 1, so we make
- * room for this extra entry.
- *
- * Note KASLR cannot increase the number of required entries for a level
- * by more than one because it increments both the virtual start and end
- * addresses equally (the extra entry comes from the case where the end
- * address is just pushed over a boundary and the start address isn't).
+ * A relocatable kernel may execute from an address that differs from the one at
+ * which it was linked. In the worst case, its runtime placement may intersect
+ * with two adjacent PGDIR entries, which means that an additional page table
+ * may be needed at each subordinate level.
  */
-
-#ifdef CONFIG_RANDOMIZE_BASE
-#define EARLY_KASLR	(1)
-#else
-#define EARLY_KASLR	(0)
-#endif
+#define EXTRA_PAGE	__is_defined(CONFIG_RELOCATABLE)
 
 #define SPAN_NR_ENTRIES(vstart, vend, shift) \
 	((((vend) - 1) >> (shift)) - ((vstart) >> (shift)) + 1)
@@ -83,7 +68,7 @@
 			+ EARLY_PGDS((vstart), (vend), add) 	/* each PGDIR needs a next level page table */	\
 			+ EARLY_PUDS((vstart), (vend), add)	/* each PUD needs a next level page table */	\
 			+ EARLY_PMDS((vstart), (vend), add))	/* each PMD needs a next level page table */
-#define INIT_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR, _end, EARLY_KASLR))
+#define INIT_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR, _end, EXTRA_PAGE))
 
 /* the initial ID map may need two extra pages if it needs to be extended */
 #if VA_BITS < 48
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 49e0d4b36bd0..e3e793d0ec30 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -244,13 +244,6 @@ static inline size_t __invalidate_icache_max_range(void)
 static inline void __invalidate_icache_guest_page(void *va, size_t size)
 {
 	/*
-	 * VPIPT I-cache maintenance must be done from EL2. See comment in the
-	 * nVHE flavor of __kvm_tlb_flush_vmid_ipa().
-	 */
-	if (icache_is_vpipt() && read_sysreg(CurrentEL) != CurrentEL_EL2)
-		return;
-
-	/*
 	 * Blow the whole I-cache if it is aliasing (i.e. VIPT) or the
 	 * invalidation range exceeds our arbitrary limit on invadations by
 	 * cache line.
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index d3e354bb8351..10068500d601 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -25,6 +25,8 @@
 #define KVM_PGTABLE_MIN_BLOCK_LEVEL	2U
 #endif
 
+#define kvm_lpa2_is_enabled()		false
+
 static inline u64 kvm_get_parange(u64 mmfr0)
 {
 	u64 parange = cpuid_feature_extract_unsigned_field(mmfr0,
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index fde4186cc387..d82305ab420f 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -65,15 +65,41 @@
 #define KERNEL_END		_end
 
 /*
- * Generic and tag-based KASAN require 1/8th and 1/16th of the kernel virtual
- * address space for the shadow region respectively. They can bloat the stack
- * significantly, so double the (minimum) stack size when they are in use.
+ * Generic and Software Tag-Based KASAN modes require 1/8th and 1/16th of the
+ * kernel virtual address space for storing the shadow memory respectively.
+ *
+ * The mapping between a virtual memory address and its corresponding shadow
+ * memory address is defined based on the formula:
+ *
+ *     shadow_addr = (addr >> KASAN_SHADOW_SCALE_SHIFT) + KASAN_SHADOW_OFFSET
+ *
+ * where KASAN_SHADOW_SCALE_SHIFT is the order of the number of bits that map
+ * to a single shadow byte and KASAN_SHADOW_OFFSET is a constant that offsets
+ * the mapping. Note that KASAN_SHADOW_OFFSET does not point to the start of
+ * the shadow memory region.
+ *
+ * Based on this mapping, we define two constants:
+ *
+ *     KASAN_SHADOW_START: the start of the shadow memory region;
+ *     KASAN_SHADOW_END: the end of the shadow memory region.
+ *
+ * KASAN_SHADOW_END is defined first as the shadow address that corresponds to
+ * the upper bound of possible virtual kernel memory addresses UL(1) << 64
+ * according to the mapping formula.
+ *
+ * KASAN_SHADOW_START is defined second based on KASAN_SHADOW_END. The shadow
+ * memory start must map to the lowest possible kernel virtual memory address
+ * and thus it depends on the actual bitness of the address space.
+ *
+ * As KASAN inserts redzones between stack variables, this increases the stack
+ * memory usage significantly. Thus, we double the (minimum) stack size.
  */
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 #define KASAN_SHADOW_OFFSET	_AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
-#define KASAN_SHADOW_END	((UL(1) << (64 - KASAN_SHADOW_SCALE_SHIFT)) \
-					+ KASAN_SHADOW_OFFSET)
-#define PAGE_END		(KASAN_SHADOW_END - (1UL << (vabits_actual - KASAN_SHADOW_SCALE_SHIFT)))
+#define KASAN_SHADOW_END	((UL(1) << (64 - KASAN_SHADOW_SCALE_SHIFT)) + KASAN_SHADOW_OFFSET)
+#define _KASAN_SHADOW_START(va)	(KASAN_SHADOW_END - (UL(1) << ((va) - KASAN_SHADOW_SCALE_SHIFT)))
+#define KASAN_SHADOW_START	_KASAN_SHADOW_START(vabits_actual)
+#define PAGE_END		KASAN_SHADOW_START
 #define KASAN_THREAD_SHIFT	1
 #else
 #define KASAN_THREAD_SHIFT	0
@@ -182,6 +208,7 @@
 #include <linux/types.h>
 #include <asm/boot.h>
 #include <asm/bug.h>
+#include <asm/sections.h>
 
 #if VA_BITS > 48
 extern u64			vabits_actual;
@@ -193,15 +220,12 @@ extern s64			memstart_addr;
 /* PHYS_OFFSET - the physical address of the start of memory. */
 #define PHYS_OFFSET		({ VM_BUG_ON(memstart_addr & 1); memstart_addr; })
 
-/* the virtual base of the kernel image */
-extern u64			kimage_vaddr;
-
 /* the offset between the kernel virtual and physical mappings */
 extern u64			kimage_voffset;
 
 static inline unsigned long kaslr_offset(void)
 {
-	return kimage_vaddr - KIMAGE_VADDR;
+	return (u64)&_text - KIMAGE_VADDR;
 }
 
 #ifdef CONFIG_RANDOMIZE_BASE
@@ -407,6 +431,5 @@ void dump_mem_limit(void);
 #define INIT_MEMBLOCK_MEMORY_REGIONS	(INIT_MEMBLOCK_REGIONS * 8)
 #endif
 
-#include <asm-generic/memory_model.h>
 
 #endif /* __ASM_MEMORY_H */
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index e9624f6326dd..483dbfa39c4c 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -71,6 +71,8 @@ extern bool arm64_use_ng_mappings;
 #define PTE_MAYBE_NG		(arm64_use_ng_mappings ? PTE_NG : 0)
 #define PMD_MAYBE_NG		(arm64_use_ng_mappings ? PMD_SECT_NG : 0)
 
+#define lpa2_is_enabled()	false
+
 /*
  * If we have userspace only BTI we don't want to mark kernel pages
  * guarded even if the system does support BTI.
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index b19a8aee684c..79ce70fbb751 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -834,6 +834,12 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 		pte = set_pte_bit(pte, __pgprot(PTE_DIRTY));
 
 	pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
+	/*
+	 * If we end up clearing hw dirtiness for a sw-dirty PTE, set hardware
+	 * dirtiness again.
+	 */
+	if (pte_sw_dirty(pte))
+		pte = pte_mkdirty(pte);
 	return pte;
 }
 
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index e5bc54522e71..5b0a04810b23 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -167,6 +167,9 @@ struct thread_struct {
 	unsigned long		fault_address;	/* fault info */
 	unsigned long		fault_code;	/* ESR_EL1 value */
 	struct debug_info	debug;		/* debugging */
+
+	struct user_fpsimd_state	kernel_fpsimd_state;
+	unsigned int			kernel_fpsimd_cpu;
 #ifdef CONFIG_ARM64_PTR_AUTH
 	struct ptrauth_keys_user	keys_user;
 #ifdef CONFIG_ARM64_PTR_AUTH_KERNEL
diff --git a/arch/arm64/include/asm/setup.h b/arch/arm64/include/asm/setup.h
index f4af547ef54c..2e4d7da74fb8 100644
--- a/arch/arm64/include/asm/setup.h
+++ b/arch/arm64/include/asm/setup.h
@@ -21,9 +21,22 @@ static inline bool arch_parse_debug_rodata(char *arg)
 	extern bool rodata_enabled;
 	extern bool rodata_full;
 
-	if (arg && !strcmp(arg, "full")) {
+	if (!arg)
+		return false;
+
+	if (!strcmp(arg, "full")) {
+		rodata_enabled = rodata_full = true;
+		return true;
+	}
+
+	if (!strcmp(arg, "off")) {
+		rodata_enabled = rodata_full = false;
+		return true;
+	}
+
+	if (!strcmp(arg, "on")) {
 		rodata_enabled = true;
-		rodata_full = true;
+		rodata_full = false;
 		return true;
 	}
 
diff --git a/arch/arm64/include/asm/simd.h b/arch/arm64/include/asm/simd.h
index 6a75d7ecdcaa..8e86c9e70e48 100644
--- a/arch/arm64/include/asm/simd.h
+++ b/arch/arm64/include/asm/simd.h
@@ -12,8 +12,6 @@
 #include <linux/preempt.h>
 #include <linux/types.h>
 
-DECLARE_PER_CPU(bool, fpsimd_context_busy);
-
 #ifdef CONFIG_KERNEL_MODE_NEON
 
 /*
@@ -28,17 +26,10 @@ static __must_check inline bool may_use_simd(void)
 	/*
 	 * We must make sure that the SVE has been initialized properly
 	 * before using the SIMD in kernel.
-	 * fpsimd_context_busy is only set while preemption is disabled,
-	 * and is clear whenever preemption is enabled. Since
-	 * this_cpu_read() is atomic w.r.t. preemption, fpsimd_context_busy
-	 * cannot change under our feet -- if it's set we cannot be
-	 * migrated, and if it's clear we cannot be migrated to a CPU
-	 * where it is set.
 	 */
 	return !WARN_ON(!system_capabilities_finalized()) &&
 	       system_supports_fpsimd() &&
-	       !in_hardirq() && !irqs_disabled() && !in_nmi() &&
-	       !this_cpu_read(fpsimd_context_busy);
+	       !in_hardirq() && !irqs_disabled() && !in_nmi();
 }
 
 #else /* ! CONFIG_KERNEL_MODE_NEON */
diff --git a/arch/arm64/include/asm/sparsemem.h b/arch/arm64/include/asm/sparsemem.h
index 5f5437621029..8a8acc220371 100644
--- a/arch/arm64/include/asm/sparsemem.h
+++ b/arch/arm64/include/asm/sparsemem.h
@@ -10,7 +10,7 @@
 /*
  * Section size must be at least 512MB for 64K base
  * page size config. Otherwise it will be less than
- * MAX_ORDER and the build process will fail.
+ * MAX_PAGE_ORDER and the build process will fail.
  */
 #ifdef CONFIG_ARM64_64K_PAGES
 #define SECTION_SIZE_BITS 29
diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h
index 06c357d83b13..0c4d9045c31f 100644
--- a/arch/arm64/include/asm/spectre.h
+++ b/arch/arm64/include/asm/spectre.h
@@ -13,8 +13,8 @@
 #define __BP_HARDEN_HYP_VECS_SZ	((BP_HARDEN_EL2_SLOTS - 1) * SZ_2K)
 
 #ifndef __ASSEMBLY__
-
-#include <linux/percpu.h>
+#include <linux/smp.h>
+#include <asm/percpu.h>
 
 #include <asm/cpufeature.h>
 #include <asm/virt.h>
diff --git a/arch/arm64/include/asm/stacktrace/common.h b/arch/arm64/include/asm/stacktrace/common.h
index 508f734de46e..f63dc654e545 100644
--- a/arch/arm64/include/asm/stacktrace/common.h
+++ b/arch/arm64/include/asm/stacktrace/common.h
@@ -9,7 +9,6 @@
 #ifndef __ASM_STACKTRACE_COMMON_H
 #define __ASM_STACKTRACE_COMMON_H
 
-#include <linux/kprobes.h>
 #include <linux/types.h>
 
 struct stack_info {
@@ -23,12 +22,6 @@ struct stack_info {
  * @fp:          The fp value in the frame record (or the real fp)
  * @pc:          The lr value in the frame record (or the real lr)
  *
- * @kr_cur:      When KRETPROBES is selected, holds the kretprobe instance
- *               associated with the most recently encountered replacement lr
- *               value.
- *
- * @task:        The task being unwound.
- *
  * @stack:       The stack currently being unwound.
  * @stacks:      An array of stacks which can be unwound.
  * @nr_stacks:   The number of stacks in @stacks.
@@ -36,10 +29,6 @@ struct stack_info {
 struct unwind_state {
 	unsigned long fp;
 	unsigned long pc;
-#ifdef CONFIG_KRETPROBES
-	struct llist_node *kr_cur;
-#endif
-	struct task_struct *task;
 
 	struct stack_info stack;
 	struct stack_info *stacks;
@@ -66,14 +55,8 @@ static inline bool stackinfo_on_stack(const struct stack_info *info,
 	return true;
 }
 
-static inline void unwind_init_common(struct unwind_state *state,
-				      struct task_struct *task)
+static inline void unwind_init_common(struct unwind_state *state)
 {
-	state->task = task;
-#ifdef CONFIG_KRETPROBES
-	state->kr_cur = NULL;
-#endif
-
 	state->stack = stackinfo_get_unknown();
 }
 
diff --git a/arch/arm64/include/asm/stacktrace/nvhe.h b/arch/arm64/include/asm/stacktrace/nvhe.h
index 25ab83a315a7..44759281d0d4 100644
--- a/arch/arm64/include/asm/stacktrace/nvhe.h
+++ b/arch/arm64/include/asm/stacktrace/nvhe.h
@@ -31,7 +31,7 @@ static inline void kvm_nvhe_unwind_init(struct unwind_state *state,
 					unsigned long fp,
 					unsigned long pc)
 {
-	unwind_init_common(state, NULL);
+	unwind_init_common(state);
 
 	state->fp = fp;
 	state->pc = pc;
diff --git a/arch/arm64/include/asm/syscall_wrapper.h b/arch/arm64/include/asm/syscall_wrapper.h
index d977713ec0ba..abb57bc54305 100644
--- a/arch/arm64/include/asm/syscall_wrapper.h
+++ b/arch/arm64/include/asm/syscall_wrapper.h
@@ -44,9 +44,6 @@
 		return sys_ni_syscall();						\
 	}
 
-#define COMPAT_SYS_NI(name) \
-	SYSCALL_ALIAS(__arm64_compat_sys_##name, sys_ni_posix_timers);
-
 #endif /* CONFIG_COMPAT */
 
 #define __SYSCALL_DEFINEx(x, name, ...)						\
@@ -81,6 +78,5 @@
 	}
 
 asmlinkage long __arm64_sys_ni_syscall(const struct pt_regs *__unused);
-#define SYS_NI(name) SYSCALL_ALIAS(__arm64_sys_##name, sys_ni_posix_timers);
 
 #endif /* __ASM_SYSCALL_WRAPPER_H */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 5e65f51c10d2..c3b19b376c86 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -645,6 +645,7 @@
 #define OP_AT_S1E0W	sys_insn(AT_Op0, 0, AT_CRn, 8, 3)
 #define OP_AT_S1E1RP	sys_insn(AT_Op0, 0, AT_CRn, 9, 0)
 #define OP_AT_S1E1WP	sys_insn(AT_Op0, 0, AT_CRn, 9, 1)
+#define OP_AT_S1E1A	sys_insn(AT_Op0, 0, AT_CRn, 9, 2)
 #define OP_AT_S1E2R	sys_insn(AT_Op0, 4, AT_CRn, 8, 0)
 #define OP_AT_S1E2W	sys_insn(AT_Op0, 4, AT_CRn, 8, 1)
 #define OP_AT_S12E1R	sys_insn(AT_Op0, 4, AT_CRn, 8, 4)
@@ -781,10 +782,16 @@
 #define OP_TLBI_VMALLS12E1NXS		sys_insn(1, 4, 9, 7, 6)
 
 /* Misc instructions */
+#define OP_GCSPUSHX			sys_insn(1, 0, 7, 7, 4)
+#define OP_GCSPOPCX			sys_insn(1, 0, 7, 7, 5)
+#define OP_GCSPOPX			sys_insn(1, 0, 7, 7, 6)
+#define OP_GCSPUSHM			sys_insn(1, 3, 7, 7, 0)
+
 #define OP_BRB_IALL			sys_insn(1, 1, 7, 2, 4)
 #define OP_BRB_INJ			sys_insn(1, 1, 7, 2, 5)
 #define OP_CFP_RCTX			sys_insn(1, 3, 7, 3, 4)
 #define OP_DVP_RCTX			sys_insn(1, 3, 7, 3, 5)
+#define OP_COSP_RCTX			sys_insn(1, 3, 7, 3, 6)
 #define OP_CPP_RCTX			sys_insn(1, 3, 7, 3, 7)
 
 /* Common SCTLR_ELx flags. */
@@ -871,10 +878,12 @@
 
 /* id_aa64mmfr0 */
 #define ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN	0x0
+#define ID_AA64MMFR0_EL1_TGRAN4_LPA2		ID_AA64MMFR0_EL1_TGRAN4_52_BIT
 #define ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX	0x7
 #define ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MIN	0x0
 #define ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MAX	0x7
 #define ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN	0x1
+#define ID_AA64MMFR0_EL1_TGRAN16_LPA2		ID_AA64MMFR0_EL1_TGRAN16_52_BIT
 #define ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX	0xf
 
 #define ARM64_MIN_PARANGE_BITS		32
@@ -882,6 +891,7 @@
 #define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_DEFAULT	0x0
 #define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_NONE		0x1
 #define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MIN		0x2
+#define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_LPA2		0x3
 #define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MAX		0x7
 
 #ifdef CONFIG_ARM64_PA_BITS_52
@@ -892,11 +902,13 @@
 
 #if defined(CONFIG_ARM64_4K_PAGES)
 #define ID_AA64MMFR0_EL1_TGRAN_SHIFT		ID_AA64MMFR0_EL1_TGRAN4_SHIFT
+#define ID_AA64MMFR0_EL1_TGRAN_LPA2		ID_AA64MMFR0_EL1_TGRAN4_52_BIT
 #define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MIN	ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN
 #define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MAX	ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX
 #define ID_AA64MMFR0_EL1_TGRAN_2_SHIFT		ID_AA64MMFR0_EL1_TGRAN4_2_SHIFT
 #elif defined(CONFIG_ARM64_16K_PAGES)
 #define ID_AA64MMFR0_EL1_TGRAN_SHIFT		ID_AA64MMFR0_EL1_TGRAN16_SHIFT
+#define ID_AA64MMFR0_EL1_TGRAN_LPA2		ID_AA64MMFR0_EL1_TGRAN16_52_BIT
 #define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MIN	ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN
 #define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MAX	ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX
 #define ID_AA64MMFR0_EL1_TGRAN_2_SHIFT		ID_AA64MMFR0_EL1_TGRAN16_2_SHIFT
@@ -1039,6 +1051,19 @@
 
 #define PIRx_ELx_PERM(idx, perm)	((perm) << ((idx) * 4))
 
+/*
+ * Permission Overlay Extension (POE) permission encodings.
+ */
+#define POE_NONE	UL(0x0)
+#define POE_R		UL(0x1)
+#define POE_X		UL(0x2)
+#define POE_RX		UL(0x3)
+#define POE_W		UL(0x4)
+#define POE_RW		UL(0x5)
+#define POE_XW		UL(0x6)
+#define POE_RXW		UL(0x7)
+#define POE_MASK	UL(0xf)
+
 #define ARM64_FEATURE_FIELD_BITS	4
 
 /* Defined for compatibility only, do not add new users. */
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 553d1bc559c6..e72a3bf9e563 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -80,6 +80,7 @@ void arch_setup_new_exec(void);
 #define TIF_TAGGED_ADDR		26	/* Allow tagged user addresses */
 #define TIF_SME			27	/* SME in use */
 #define TIF_SME_VL_INHERIT	28	/* Inherit SME vl_onexec across exec */
+#define TIF_KERNEL_FPSTATE	29	/* Task is in a kernel mode FPSIMD section */
 
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 846c563689a8..0150deb332af 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -22,15 +22,15 @@ static void tlb_flush(struct mmu_gather *tlb);
 #include <asm-generic/tlb.h>
 
 /*
- * get the tlbi levels in arm64.  Default value is 0 if more than one
- * of cleared_* is set or neither is set.
- * Arm64 doesn't support p4ds now.
+ * get the tlbi levels in arm64.  Default value is TLBI_TTL_UNKNOWN if more than
+ * one of cleared_* is set or neither is set - this elides the level hinting to
+ * the hardware.
  */
 static inline int tlb_get_level(struct mmu_gather *tlb)
 {
 	/* The TTL field is only valid for the leaf entry. */
 	if (tlb->freed_tables)
-		return 0;
+		return TLBI_TTL_UNKNOWN;
 
 	if (tlb->cleared_ptes && !(tlb->cleared_pmds ||
 				   tlb->cleared_puds ||
@@ -47,7 +47,12 @@ static inline int tlb_get_level(struct mmu_gather *tlb)
 				   tlb->cleared_p4ds))
 		return 1;
 
-	return 0;
+	if (tlb->cleared_p4ds && !(tlb->cleared_ptes ||
+				   tlb->cleared_pmds ||
+				   tlb->cleared_puds))
+		return 0;
+
+	return TLBI_TTL_UNKNOWN;
 }
 
 static inline void tlb_flush(struct mmu_gather *tlb)
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index bb2c2833a987..1deb5d789c2e 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -94,19 +94,22 @@ static inline unsigned long get_trans_granule(void)
  * When ARMv8.4-TTL exists, TLBI operations take an additional hint for
  * the level at which the invalidation must take place. If the level is
  * wrong, no invalidation may take place. In the case where the level
- * cannot be easily determined, a 0 value for the level parameter will
- * perform a non-hinted invalidation.
+ * cannot be easily determined, the value TLBI_TTL_UNKNOWN will perform
+ * a non-hinted invalidation. Any provided level outside the hint range
+ * will also cause fall-back to non-hinted invalidation.
  *
  * For Stage-2 invalidation, use the level values provided to that effect
  * in asm/stage2_pgtable.h.
  */
 #define TLBI_TTL_MASK		GENMASK_ULL(47, 44)
 
+#define TLBI_TTL_UNKNOWN	INT_MAX
+
 #define __tlbi_level(op, addr, level) do {				\
 	u64 arg = addr;							\
 									\
 	if (alternative_has_cap_unlikely(ARM64_HAS_ARMv8_4_TTL) &&	\
-	    level) {							\
+	    level >= 0 && level <= 3) {					\
 		u64 ttl = level & 3;					\
 		ttl |= get_trans_granule() << 2;			\
 		arg &= ~TLBI_TTL_MASK;					\
@@ -122,28 +125,34 @@ static inline unsigned long get_trans_granule(void)
 } while (0)
 
 /*
- * This macro creates a properly formatted VA operand for the TLB RANGE.
- * The value bit assignments are:
+ * This macro creates a properly formatted VA operand for the TLB RANGE. The
+ * value bit assignments are:
  *
  * +----------+------+-------+-------+-------+----------------------+
  * |   ASID   |  TG  | SCALE |  NUM  |  TTL  |        BADDR         |
  * +-----------------+-------+-------+-------+----------------------+
  * |63      48|47  46|45   44|43   39|38   37|36                   0|
  *
- * The address range is determined by below formula:
- * [BADDR, BADDR + (NUM + 1) * 2^(5*SCALE + 1) * PAGESIZE)
+ * The address range is determined by below formula: [BADDR, BADDR + (NUM + 1) *
+ * 2^(5*SCALE + 1) * PAGESIZE)
+ *
+ * Note that the first argument, baddr, is pre-shifted; If LPA2 is in use, BADDR
+ * holds addr[52:16]. Else BADDR holds page number. See for example ARM DDI
+ * 0487J.a section C5.5.60 "TLBI VAE1IS, TLBI VAE1ISNXS, TLB Invalidate by VA,
+ * EL1, Inner Shareable".
  *
  */
-#define __TLBI_VADDR_RANGE(addr, asid, scale, num, ttl)		\
-	({							\
-		unsigned long __ta = (addr) >> PAGE_SHIFT;	\
-		__ta &= GENMASK_ULL(36, 0);			\
-		__ta |= (unsigned long)(ttl) << 37;		\
-		__ta |= (unsigned long)(num) << 39;		\
-		__ta |= (unsigned long)(scale) << 44;		\
-		__ta |= get_trans_granule() << 46;		\
-		__ta |= (unsigned long)(asid) << 48;		\
-		__ta;						\
+#define __TLBI_VADDR_RANGE(baddr, asid, scale, num, ttl)			\
+	({									\
+		unsigned long __ta = (baddr);					\
+		unsigned long __ttl = (ttl >= 1 && ttl <= 3) ? ttl : 0;		\
+		__ta &= GENMASK_ULL(36, 0);					\
+		__ta |= __ttl << 37;						\
+		__ta |= (unsigned long)(num) << 39;				\
+		__ta |= (unsigned long)(scale) << 44;				\
+		__ta |= get_trans_granule() << 46;				\
+		__ta |= (unsigned long)(asid) << 48;				\
+		__ta;								\
 	})
 
 /* These macros are used by the TLBI RANGE feature. */
@@ -216,12 +225,16 @@ static inline unsigned long get_trans_granule(void)
  *		CPUs, ensuring that any walk-cache entries associated with the
  *		translation are also invalidated.
  *
- *	__flush_tlb_range(vma, start, end, stride, last_level)
+ *	__flush_tlb_range(vma, start, end, stride, last_level, tlb_level)
  *		Invalidate the virtual-address range '[start, end)' on all
  *		CPUs for the user address space corresponding to 'vma->mm'.
  *		The invalidation operations are issued at a granularity
  *		determined by 'stride' and only affect any walk-cache entries
- *		if 'last_level' is equal to false.
+ *		if 'last_level' is equal to false. tlb_level is the level at
+ *		which the invalidation must take place. If the level is wrong,
+ *		no invalidation may take place. In the case where the level
+ *		cannot be easily determined, the value TLBI_TTL_UNKNOWN will
+ *		perform a non-hinted invalidation.
  *
  *
  *	Finally, take a look at asm/tlb.h to see how tlb_flush() is implemented
@@ -345,34 +358,44 @@ static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
  * @tlb_level:	Translation Table level hint, if known
  * @tlbi_user:	If 'true', call an additional __tlbi_user()
  *              (typically for user ASIDs). 'flase' for IPA instructions
+ * @lpa2:	If 'true', the lpa2 scheme is used as set out below
  *
  * When the CPU does not support TLB range operations, flush the TLB
  * entries one by one at the granularity of 'stride'. If the TLB
  * range ops are supported, then:
  *
- * 1. If 'pages' is odd, flush the first page through non-range
- *    operations;
+ * 1. If FEAT_LPA2 is in use, the start address of a range operation must be
+ *    64KB aligned, so flush pages one by one until the alignment is reached
+ *    using the non-range operations. This step is skipped if LPA2 is not in
+ *    use.
+ *
+ * 2. The minimum range granularity is decided by 'scale', so multiple range
+ *    TLBI operations may be required. Start from scale = 3, flush the largest
+ *    possible number of pages ((num+1)*2^(5*scale+1)) that fit into the
+ *    requested range, then decrement scale and continue until one or zero pages
+ *    are left. We must start from highest scale to ensure 64KB start alignment
+ *    is maintained in the LPA2 case.
  *
- * 2. For remaining pages: the minimum range granularity is decided
- *    by 'scale', so multiple range TLBI operations may be required.
- *    Start from scale = 0, flush the corresponding number of pages
- *    ((num+1)*2^(5*scale+1) starting from 'addr'), then increase it
- *    until no pages left.
+ * 3. If there is 1 page remaining, flush it through non-range operations. Range
+ *    operations can only span an even number of pages. We save this for last to
+ *    ensure 64KB start alignment is maintained for the LPA2 case.
  *
  * Note that certain ranges can be represented by either num = 31 and
  * scale or num = 0 and scale + 1. The loop below favours the latter
  * since num is limited to 30 by the __TLBI_RANGE_NUM() macro.
  */
 #define __flush_tlb_range_op(op, start, pages, stride,			\
-				asid, tlb_level, tlbi_user)		\
+				asid, tlb_level, tlbi_user, lpa2)	\
 do {									\
 	int num = 0;							\
-	int scale = 0;							\
+	int scale = 3;							\
+	int shift = lpa2 ? 16 : PAGE_SHIFT;				\
 	unsigned long addr;						\
 									\
 	while (pages > 0) {						\
 		if (!system_supports_tlb_range() ||			\
-		    pages % 2 == 1) {					\
+		    pages == 1 ||					\
+		    (lpa2 && start != ALIGN(start, SZ_64K))) {		\
 			addr = __TLBI_VADDR(start, asid);		\
 			__tlbi_level(op, addr, tlb_level);		\
 			if (tlbi_user)					\
@@ -384,20 +407,20 @@ do {									\
 									\
 		num = __TLBI_RANGE_NUM(pages, scale);			\
 		if (num >= 0) {						\
-			addr = __TLBI_VADDR_RANGE(start, asid, scale,	\
-						  num, tlb_level);	\
+			addr = __TLBI_VADDR_RANGE(start >> shift, asid, \
+						scale, num, tlb_level);	\
 			__tlbi(r##op, addr);				\
 			if (tlbi_user)					\
 				__tlbi_user(r##op, addr);		\
 			start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT; \
 			pages -= __TLBI_RANGE_PAGES(num, scale);	\
 		}							\
-		scale++;						\
+		scale--;						\
 	}								\
 } while (0)
 
 #define __flush_s2_tlb_range_op(op, start, pages, stride, tlb_level) \
-	__flush_tlb_range_op(op, start, pages, stride, 0, tlb_level, false)
+	__flush_tlb_range_op(op, start, pages, stride, 0, tlb_level, false, kvm_lpa2_is_enabled());
 
 static inline void __flush_tlb_range(struct vm_area_struct *vma,
 				     unsigned long start, unsigned long end,
@@ -427,9 +450,11 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
 	asid = ASID(vma->vm_mm);
 
 	if (last_level)
-		__flush_tlb_range_op(vale1is, start, pages, stride, asid, tlb_level, true);
+		__flush_tlb_range_op(vale1is, start, pages, stride, asid,
+				     tlb_level, true, lpa2_is_enabled());
 	else
-		__flush_tlb_range_op(vae1is, start, pages, stride, asid, tlb_level, true);
+		__flush_tlb_range_op(vae1is, start, pages, stride, asid,
+				     tlb_level, true, lpa2_is_enabled());
 
 	dsb(ish);
 	mmu_notifier_arch_invalidate_secondary_tlbs(vma->vm_mm, start, end);
@@ -441,9 +466,10 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 	/*
 	 * We cannot use leaf-only invalidation here, since we may be invalidating
 	 * table entries as part of collapsing hugepages or moving page tables.
-	 * Set the tlb_level to 0 because we can not get enough information here.
+	 * Set the tlb_level to TLBI_TTL_UNKNOWN because we can not get enough
+	 * information here.
 	 */
-	__flush_tlb_range(vma, start, end, PAGE_SIZE, false, 0);
+	__flush_tlb_range(vma, start, end, PAGE_SIZE, false, TLBI_TTL_UNKNOWN);
 }
 
 static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index 9fab663dd2de..a323b109b9c4 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -23,6 +23,7 @@ void update_freq_counters_refs(void);
 #define arch_set_freq_scale topology_set_freq_scale
 #define arch_scale_freq_capacity topology_get_freq_scale
 #define arch_scale_freq_invariant topology_scale_freq_invariant
+#define arch_scale_freq_ref topology_get_freq_ref
 
 #ifdef CONFIG_ACPI_CPPC_LIB
 #define arch_init_invariance_cppc topology_init_cpu_capacity_cppc
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 531effca5f1f..491b2b9bd553 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -39,7 +39,7 @@
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE + 5)
 #define __ARM_NR_COMPAT_END		(__ARM_NR_COMPAT_BASE + 0x800)
 
-#define __NR_compat_syscalls		457
+#define __NR_compat_syscalls		462
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 9f7c1bf99526..7118282d1c79 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -919,6 +919,16 @@ __SYSCALL(__NR_futex_wake, sys_futex_wake)
 __SYSCALL(__NR_futex_wait, sys_futex_wait)
 #define __NR_futex_requeue 456
 __SYSCALL(__NR_futex_requeue, sys_futex_requeue)
+#define __NR_statmount 457
+__SYSCALL(__NR_statmount, sys_statmount)
+#define __NR_listmount 458
+__SYSCALL(__NR_listmount, sys_listmount)
+#define __NR_lsm_get_self_attr 459
+__SYSCALL(__NR_lsm_get_self_attr, sys_lsm_get_self_attr)
+#define __NR_lsm_set_self_attr 460
+__SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr)
+#define __NR_lsm_list_modules 461
+__SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules)
 
 /*
  * Please add new compat syscalls above this comment and update
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 646591c67e7a..01a4c1d7fc09 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1081,25 +1081,6 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 
 	if (id_aa64pfr1_mte(info->reg_id_aa64pfr1))
 		init_cpu_ftr_reg(SYS_GMID_EL1, info->reg_gmid);
-
-	/*
-	 * Initialize the indirect array of CPU capabilities pointers before we
-	 * handle the boot CPU below.
-	 */
-	init_cpucap_indirect_list();
-
-	/*
-	 * Detect broken pseudo-NMI. Must be called _before_ the call to
-	 * setup_boot_cpu_capabilities() since it interacts with
-	 * can_use_gic_priorities().
-	 */
-	detect_system_supports_pseudo_nmi();
-
-	/*
-	 * Detect and enable early CPU capabilities based on the boot CPU,
-	 * after we have initialised the CPU feature infrastructure.
-	 */
-	setup_boot_cpu_capabilities();
 }
 
 static void update_cpu_ftr_reg(struct arm64_ftr_reg *reg, u64 new)
@@ -1584,16 +1565,6 @@ static bool has_useable_gicv3_cpuif(const struct arm64_cpu_capabilities *entry,
 	return has_sre;
 }
 
-static bool has_no_hw_prefetch(const struct arm64_cpu_capabilities *entry, int __unused)
-{
-	u32 midr = read_cpuid_id();
-
-	/* Cavium ThunderX pass 1.x and 2.x */
-	return midr_is_cpu_model_range(midr, MIDR_THUNDERX,
-		MIDR_CPU_VAR_REV(0, 0),
-		MIDR_CPU_VAR_REV(1, MIDR_REVISION_MASK));
-}
-
 static bool has_cache_idc(const struct arm64_cpu_capabilities *entry,
 			  int scope)
 {
@@ -1768,6 +1739,39 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 	return !meltdown_safe;
 }
 
+#if defined(ID_AA64MMFR0_EL1_TGRAN_LPA2) && defined(ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_LPA2)
+static bool has_lpa2_at_stage1(u64 mmfr0)
+{
+	unsigned int tgran;
+
+	tgran = cpuid_feature_extract_unsigned_field(mmfr0,
+					ID_AA64MMFR0_EL1_TGRAN_SHIFT);
+	return tgran == ID_AA64MMFR0_EL1_TGRAN_LPA2;
+}
+
+static bool has_lpa2_at_stage2(u64 mmfr0)
+{
+	unsigned int tgran;
+
+	tgran = cpuid_feature_extract_unsigned_field(mmfr0,
+					ID_AA64MMFR0_EL1_TGRAN_2_SHIFT);
+	return tgran == ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_LPA2;
+}
+
+static bool has_lpa2(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	u64 mmfr0;
+
+	mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+	return has_lpa2_at_stage1(mmfr0) && has_lpa2_at_stage2(mmfr0);
+}
+#else
+static bool has_lpa2(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	return false;
+}
+#endif
+
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 #define KPTI_NG_TEMP_VA		(-(1UL << PMD_SHIFT))
 
@@ -1839,6 +1843,10 @@ static int __init __kpti_install_ng_mappings(void *__unused)
 
 static void __init kpti_install_ng_mappings(void)
 {
+	/* Check whether KPTI is going to be used */
+	if (!arm64_kernel_unmapped_at_el0())
+		return;
+
 	/*
 	 * We don't need to rewrite the page-tables if either we've done
 	 * it already or we have KASLR enabled and therefore have not
@@ -2322,12 +2330,6 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 	},
 #endif /* CONFIG_ARM64_LSE_ATOMICS */
 	{
-		.desc = "Software prefetching using PRFM",
-		.capability = ARM64_HAS_NO_HW_PREFETCH,
-		.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
-		.matches = has_no_hw_prefetch,
-	},
-	{
 		.desc = "Virtualization Host Extensions",
 		.capability = ARM64_HAS_VIRT_HOST_EXTN,
 		.type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE,
@@ -2731,6 +2733,12 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_cpuid_feature,
 		ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, EVT, IMP)
 	},
+	{
+		.desc = "52-bit Virtual Addressing for KVM (LPA2)",
+		.capability = ARM64_HAS_LPA2,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_lpa2,
+	},
 	{},
 };
 
@@ -3271,14 +3279,6 @@ void check_local_cpu_capabilities(void)
 		verify_local_cpu_capabilities();
 }
 
-static void __init setup_boot_cpu_capabilities(void)
-{
-	/* Detect capabilities with either SCOPE_BOOT_CPU or SCOPE_LOCAL_CPU */
-	update_cpu_capabilities(SCOPE_BOOT_CPU | SCOPE_LOCAL_CPU);
-	/* Enable the SCOPE_BOOT_CPU capabilities alone right away */
-	enable_cpu_capabilities(SCOPE_BOOT_CPU);
-}
-
 bool this_cpu_has_cap(unsigned int n)
 {
 	if (!WARN_ON(preemptible()) && n < ARM64_NCAPS) {
@@ -3334,37 +3334,52 @@ unsigned long cpu_get_elf_hwcap2(void)
 	return elf_hwcap[1];
 }
 
-void __init setup_system_features(void)
+static void __init setup_boot_cpu_capabilities(void)
 {
-	int i;
 	/*
-	 * The system-wide safe feature feature register values have been
-	 * finalized. Finalize and log the available system capabilities.
+	 * The boot CPU's feature register values have been recorded. Detect
+	 * boot cpucaps and local cpucaps for the boot CPU, then enable and
+	 * patch alternatives for the available boot cpucaps.
 	 */
-	update_cpu_capabilities(SCOPE_SYSTEM);
-	if (IS_ENABLED(CONFIG_ARM64_SW_TTBR0_PAN) &&
-	    !cpus_have_cap(ARM64_HAS_PAN))
-		pr_info("emulated: Privileged Access Never (PAN) using TTBR0_EL1 switching\n");
+	update_cpu_capabilities(SCOPE_BOOT_CPU | SCOPE_LOCAL_CPU);
+	enable_cpu_capabilities(SCOPE_BOOT_CPU);
+	apply_boot_alternatives();
+}
 
+void __init setup_boot_cpu_features(void)
+{
 	/*
-	 * Enable all the available capabilities which have not been enabled
-	 * already.
+	 * Initialize the indirect array of CPU capabilities pointers before we
+	 * handle the boot CPU.
 	 */
-	enable_cpu_capabilities(SCOPE_ALL & ~SCOPE_BOOT_CPU);
+	init_cpucap_indirect_list();
 
-	kpti_install_ng_mappings();
+	/*
+	 * Detect broken pseudo-NMI. Must be called _before_ the call to
+	 * setup_boot_cpu_capabilities() since it interacts with
+	 * can_use_gic_priorities().
+	 */
+	detect_system_supports_pseudo_nmi();
 
-	sve_setup();
-	sme_setup();
+	setup_boot_cpu_capabilities();
+}
 
+static void __init setup_system_capabilities(void)
+{
 	/*
-	 * Check for sane CTR_EL0.CWG value.
+	 * The system-wide safe feature register values have been finalized.
+	 * Detect, enable, and patch alternatives for the available system
+	 * cpucaps.
 	 */
-	if (!cache_type_cwg())
-		pr_warn("No Cache Writeback Granule information, assuming %d\n",
-			ARCH_DMA_MINALIGN);
+	update_cpu_capabilities(SCOPE_SYSTEM);
+	enable_cpu_capabilities(SCOPE_ALL & ~SCOPE_BOOT_CPU);
+	apply_alternatives_all();
 
-	for (i = 0; i < ARM64_NCAPS; i++) {
+	/*
+	 * Log any cpucaps with a cpumask as these aren't logged by
+	 * update_cpu_capabilities().
+	 */
+	for (int i = 0; i < ARM64_NCAPS; i++) {
 		const struct arm64_cpu_capabilities *caps = cpucap_ptrs[i];
 
 		if (caps && caps->cpus && caps->desc &&
@@ -3372,6 +3387,29 @@ void __init setup_system_features(void)
 			pr_info("detected: %s on CPU%*pbl\n",
 				caps->desc, cpumask_pr_args(caps->cpus));
 	}
+
+	/*
+	 * TTBR0 PAN doesn't have its own cpucap, so log it manually.
+	 */
+	if (system_uses_ttbr0_pan())
+		pr_info("emulated: Privileged Access Never (PAN) using TTBR0_EL1 switching\n");
+}
+
+void __init setup_system_features(void)
+{
+	setup_system_capabilities();
+
+	kpti_install_ng_mappings();
+
+	sve_setup();
+	sme_setup();
+
+	/*
+	 * Check for sane CTR_EL0.CWG value.
+	 */
+	if (!cache_type_cwg())
+		pr_warn("No Cache Writeback Granule information, assuming %d\n",
+			ARCH_DMA_MINALIGN);
 }
 
 void __init setup_user_features(void)
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index a257da7b56fe..47043c0d95ec 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -36,8 +36,6 @@ static struct cpuinfo_arm64 boot_cpu_data;
 static inline const char *icache_policy_str(int l1ip)
 {
 	switch (l1ip) {
-	case CTR_EL0_L1Ip_VPIPT:
-		return "VPIPT";
 	case CTR_EL0_L1Ip_VIPT:
 		return "VIPT";
 	case CTR_EL0_L1Ip_PIPT:
@@ -388,9 +386,6 @@ static void cpuinfo_detect_icache_policy(struct cpuinfo_arm64 *info)
 	switch (l1ip) {
 	case CTR_EL0_L1Ip_PIPT:
 		break;
-	case CTR_EL0_L1Ip_VPIPT:
-		set_bit(ICACHEF_VPIPT, &__icache_flags);
-		break;
 	case CTR_EL0_L1Ip_VIPT:
 	default:
 		/* Assume aliasing */
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 1559c706d32d..505f389be3e0 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -85,13 +85,13 @@
  * softirq kicks in. Upon vcpu_put(), KVM will save the vcpu FP state and
  * flag the register state as invalid.
  *
- * In order to allow softirq handlers to use FPSIMD, kernel_neon_begin() may
- * save the task's FPSIMD context back to task_struct from softirq context.
- * To prevent this from racing with the manipulation of the task's FPSIMD state
- * from task context and thereby corrupting the state, it is necessary to
- * protect any manipulation of a task's fpsimd_state or TIF_FOREIGN_FPSTATE
- * flag with {, __}get_cpu_fpsimd_context(). This will still allow softirqs to
- * run but prevent them to use FPSIMD.
+ * In order to allow softirq handlers to use FPSIMD, kernel_neon_begin() may be
+ * called from softirq context, which will save the task's FPSIMD context back
+ * to task_struct. To prevent this from racing with the manipulation of the
+ * task's FPSIMD state from task context and thereby corrupting the state, it
+ * is necessary to protect any manipulation of a task's fpsimd_state or
+ * TIF_FOREIGN_FPSTATE flag with get_cpu_fpsimd_context(), which will suspend
+ * softirq servicing entirely until put_cpu_fpsimd_context() is called.
  *
  * For a certain task, the sequence may look something like this:
  * - the task gets scheduled in; if both the task's fpsimd_cpu field
@@ -209,27 +209,14 @@ static inline void sme_free(struct task_struct *t) { }
 
 #endif
 
-DEFINE_PER_CPU(bool, fpsimd_context_busy);
-EXPORT_PER_CPU_SYMBOL(fpsimd_context_busy);
-
 static void fpsimd_bind_task_to_cpu(void);
 
-static void __get_cpu_fpsimd_context(void)
-{
-	bool busy = __this_cpu_xchg(fpsimd_context_busy, true);
-
-	WARN_ON(busy);
-}
-
 /*
  * Claim ownership of the CPU FPSIMD context for use by the calling context.
  *
  * The caller may freely manipulate the FPSIMD context metadata until
  * put_cpu_fpsimd_context() is called.
  *
- * The double-underscore version must only be called if you know the task
- * can't be preempted.
- *
  * On RT kernels local_bh_disable() is not sufficient because it only
  * serializes soft interrupt related sections via a local lock, but stays
  * preemptible. Disabling preemption is the right choice here as bottom
@@ -242,14 +229,6 @@ static void get_cpu_fpsimd_context(void)
 		local_bh_disable();
 	else
 		preempt_disable();
-	__get_cpu_fpsimd_context();
-}
-
-static void __put_cpu_fpsimd_context(void)
-{
-	bool busy = __this_cpu_xchg(fpsimd_context_busy, false);
-
-	WARN_ON(!busy); /* No matching get_cpu_fpsimd_context()? */
 }
 
 /*
@@ -261,18 +240,12 @@ static void __put_cpu_fpsimd_context(void)
  */
 static void put_cpu_fpsimd_context(void)
 {
-	__put_cpu_fpsimd_context();
 	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
 		local_bh_enable();
 	else
 		preempt_enable();
 }
 
-static bool have_cpu_fpsimd_context(void)
-{
-	return !preemptible() && __this_cpu_read(fpsimd_context_busy);
-}
-
 unsigned int task_get_vl(const struct task_struct *task, enum vec_type type)
 {
 	return task->thread.vl[type];
@@ -383,7 +356,8 @@ static void task_fpsimd_load(void)
 	bool restore_ffr;
 
 	WARN_ON(!system_supports_fpsimd());
-	WARN_ON(!have_cpu_fpsimd_context());
+	WARN_ON(preemptible());
+	WARN_ON(test_thread_flag(TIF_KERNEL_FPSTATE));
 
 	if (system_supports_sve() || system_supports_sme()) {
 		switch (current->thread.fp_type) {
@@ -406,7 +380,7 @@ static void task_fpsimd_load(void)
 		default:
 			/*
 			 * This indicates either a bug in
-			 * fpsimd_save() or memory corruption, we
+			 * fpsimd_save_user_state() or memory corruption, we
 			 * should always record an explicit format
 			 * when we save. We always at least have the
 			 * memory allocated for FPSMID registers so
@@ -457,7 +431,7 @@ static void task_fpsimd_load(void)
  * than via current, if we are saving KVM state then it will have
  * ensured that the type of registers to save is set in last->to_save.
  */
-static void fpsimd_save(void)
+static void fpsimd_save_user_state(void)
 {
 	struct cpu_fp_state const *last =
 		this_cpu_ptr(&fpsimd_last_state);
@@ -467,7 +441,7 @@ static void fpsimd_save(void)
 	unsigned int vl;
 
 	WARN_ON(!system_supports_fpsimd());
-	WARN_ON(!have_cpu_fpsimd_context());
+	WARN_ON(preemptible());
 
 	if (test_thread_flag(TIF_FOREIGN_FPSTATE))
 		return;
@@ -888,7 +862,7 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 	if (task == current) {
 		get_cpu_fpsimd_context();
 
-		fpsimd_save();
+		fpsimd_save_user_state();
 	}
 
 	fpsimd_flush_task_state(task);
@@ -1171,7 +1145,7 @@ void __init sve_setup(void)
 	unsigned long b;
 	int max_bit;
 
-	if (!cpus_have_cap(ARM64_SVE))
+	if (!system_supports_sve())
 		return;
 
 	/*
@@ -1301,7 +1275,7 @@ void __init sme_setup(void)
 	struct vl_info *info = &vl_info[ARM64_VEC_SME];
 	int min_bit, max_bit;
 
-	if (!cpus_have_cap(ARM64_SME))
+	if (!system_supports_sme())
 		return;
 
 	/*
@@ -1500,6 +1474,34 @@ void do_fpsimd_exc(unsigned long esr, struct pt_regs *regs)
 		       current);
 }
 
+static void fpsimd_load_kernel_state(struct task_struct *task)
+{
+	struct cpu_fp_state *last = this_cpu_ptr(&fpsimd_last_state);
+
+	/*
+	 * Elide the load if this CPU holds the most recent kernel mode
+	 * FPSIMD context of the current task.
+	 */
+	if (last->st == &task->thread.kernel_fpsimd_state &&
+	    task->thread.kernel_fpsimd_cpu == smp_processor_id())
+		return;
+
+	fpsimd_load_state(&task->thread.kernel_fpsimd_state);
+}
+
+static void fpsimd_save_kernel_state(struct task_struct *task)
+{
+	struct cpu_fp_state cpu_fp_state = {
+		.st		= &task->thread.kernel_fpsimd_state,
+		.to_save	= FP_STATE_FPSIMD,
+	};
+
+	fpsimd_save_state(&task->thread.kernel_fpsimd_state);
+	fpsimd_bind_state_to_cpu(&cpu_fp_state);
+
+	task->thread.kernel_fpsimd_cpu = smp_processor_id();
+}
+
 void fpsimd_thread_switch(struct task_struct *next)
 {
 	bool wrong_task, wrong_cpu;
@@ -1507,24 +1509,31 @@ void fpsimd_thread_switch(struct task_struct *next)
 	if (!system_supports_fpsimd())
 		return;
 
-	__get_cpu_fpsimd_context();
+	WARN_ON_ONCE(!irqs_disabled());
 
 	/* Save unsaved fpsimd state, if any: */
-	fpsimd_save();
-
-	/*
-	 * Fix up TIF_FOREIGN_FPSTATE to correctly describe next's
-	 * state.  For kernel threads, FPSIMD registers are never loaded
-	 * and wrong_task and wrong_cpu will always be true.
-	 */
-	wrong_task = __this_cpu_read(fpsimd_last_state.st) !=
-					&next->thread.uw.fpsimd_state;
-	wrong_cpu = next->thread.fpsimd_cpu != smp_processor_id();
+	if (test_thread_flag(TIF_KERNEL_FPSTATE))
+		fpsimd_save_kernel_state(current);
+	else
+		fpsimd_save_user_state();
 
-	update_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE,
-			       wrong_task || wrong_cpu);
+	if (test_tsk_thread_flag(next, TIF_KERNEL_FPSTATE)) {
+		fpsimd_load_kernel_state(next);
+		set_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE);
+	} else {
+		/*
+		 * Fix up TIF_FOREIGN_FPSTATE to correctly describe next's
+		 * state.  For kernel threads, FPSIMD registers are never
+		 * loaded with user mode FPSIMD state and so wrong_task and
+		 * wrong_cpu will always be true.
+		 */
+		wrong_task = __this_cpu_read(fpsimd_last_state.st) !=
+			&next->thread.uw.fpsimd_state;
+		wrong_cpu = next->thread.fpsimd_cpu != smp_processor_id();
 
-	__put_cpu_fpsimd_context();
+		update_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE,
+				       wrong_task || wrong_cpu);
+	}
 }
 
 static void fpsimd_flush_thread_vl(enum vec_type type)
@@ -1614,7 +1623,7 @@ void fpsimd_preserve_current_state(void)
 		return;
 
 	get_cpu_fpsimd_context();
-	fpsimd_save();
+	fpsimd_save_user_state();
 	put_cpu_fpsimd_context();
 }
 
@@ -1826,13 +1835,15 @@ static void fpsimd_flush_cpu_state(void)
  */
 void fpsimd_save_and_flush_cpu_state(void)
 {
+	unsigned long flags;
+
 	if (!system_supports_fpsimd())
 		return;
 	WARN_ON(preemptible());
-	__get_cpu_fpsimd_context();
-	fpsimd_save();
+	local_irq_save(flags);
+	fpsimd_save_user_state();
 	fpsimd_flush_cpu_state();
-	__put_cpu_fpsimd_context();
+	local_irq_restore(flags);
 }
 
 #ifdef CONFIG_KERNEL_MODE_NEON
@@ -1864,10 +1875,37 @@ void kernel_neon_begin(void)
 	get_cpu_fpsimd_context();
 
 	/* Save unsaved fpsimd state, if any: */
-	fpsimd_save();
+	if (test_thread_flag(TIF_KERNEL_FPSTATE)) {
+		BUG_ON(IS_ENABLED(CONFIG_PREEMPT_RT) || !in_serving_softirq());
+		fpsimd_save_kernel_state(current);
+	} else {
+		fpsimd_save_user_state();
+
+		/*
+		 * Set the thread flag so that the kernel mode FPSIMD state
+		 * will be context switched along with the rest of the task
+		 * state.
+		 *
+		 * On non-PREEMPT_RT, softirqs may interrupt task level kernel
+		 * mode FPSIMD, but the task will not be preemptible so setting
+		 * TIF_KERNEL_FPSTATE for those would be both wrong (as it
+		 * would mark the task context FPSIMD state as requiring a
+		 * context switch) and unnecessary.
+		 *
+		 * On PREEMPT_RT, softirqs are serviced from a separate thread,
+		 * which is scheduled as usual, and this guarantees that these
+		 * softirqs are not interrupting use of the FPSIMD in kernel
+		 * mode in task context. So in this case, setting the flag here
+		 * is always appropriate.
+		 */
+		if (IS_ENABLED(CONFIG_PREEMPT_RT) || !in_serving_softirq())
+			set_thread_flag(TIF_KERNEL_FPSTATE);
+	}
 
 	/* Invalidate any task state remaining in the fpsimd regs: */
 	fpsimd_flush_cpu_state();
+
+	put_cpu_fpsimd_context();
 }
 EXPORT_SYMBOL_GPL(kernel_neon_begin);
 
@@ -1885,7 +1923,16 @@ void kernel_neon_end(void)
 	if (!system_supports_fpsimd())
 		return;
 
-	put_cpu_fpsimd_context();
+	/*
+	 * If we are returning from a nested use of kernel mode FPSIMD, restore
+	 * the task context kernel mode FPSIMD state. This can only happen when
+	 * running in softirq context on non-PREEMPT_RT.
+	 */
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT) && in_serving_softirq() &&
+	    test_thread_flag(TIF_KERNEL_FPSTATE))
+		fpsimd_load_kernel_state(current);
+	else
+		clear_thread_flag(TIF_KERNEL_FPSTATE);
 }
 EXPORT_SYMBOL_GPL(kernel_neon_end);
 
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 7b236994f0e1..cab7f91949d8 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -482,7 +482,7 @@ SYM_FUNC_START_LOCAL(__primary_switched)
 
 	str_l	x21, __fdt_pointer, x5		// Save FDT pointer
 
-	ldr_l	x4, kimage_vaddr		// Save the offset between
+	adrp	x4, _text			// Save the offset between
 	sub	x4, x4, x0			// the kernel virtual and
 	str_l	x4, kimage_voffset, x5		// physical mappings
 
diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c
index 3addc09f8746..e30fd9e32ef3 100644
--- a/arch/arm64/kernel/idreg-override.c
+++ b/arch/arm64/kernel/idreg-override.c
@@ -21,14 +21,25 @@
 
 static u64 __boot_status __initdata;
 
+// temporary __prel64 related definitions
+// to be removed when this code is moved under pi/
+
+#define __prel64_initconst	__initconst
+
+#define PREL64(type, name)	union { type *name; }
+
+#define prel64_pointer(__d)	(__d)
+
+typedef bool filter_t(u64 val);
+
 struct ftr_set_desc {
 	char 				name[FTR_DESC_NAME_LEN];
-	struct arm64_ftr_override	*override;
+	PREL64(struct arm64_ftr_override, override);
 	struct {
 		char			name[FTR_DESC_FIELD_LEN];
 		u8			shift;
 		u8			width;
-		bool			(*filter)(u64 val);
+		PREL64(filter_t,	filter);
 	} 				fields[];
 };
 
@@ -46,7 +57,7 @@ static bool __init mmfr1_vh_filter(u64 val)
 		 val == 0);
 }
 
-static const struct ftr_set_desc mmfr1 __initconst = {
+static const struct ftr_set_desc mmfr1 __prel64_initconst = {
 	.name		= "id_aa64mmfr1",
 	.override	= &id_aa64mmfr1_override,
 	.fields		= {
@@ -70,7 +81,7 @@ static bool __init pfr0_sve_filter(u64 val)
 	return true;
 }
 
-static const struct ftr_set_desc pfr0 __initconst = {
+static const struct ftr_set_desc pfr0 __prel64_initconst = {
 	.name		= "id_aa64pfr0",
 	.override	= &id_aa64pfr0_override,
 	.fields		= {
@@ -94,7 +105,7 @@ static bool __init pfr1_sme_filter(u64 val)
 	return true;
 }
 
-static const struct ftr_set_desc pfr1 __initconst = {
+static const struct ftr_set_desc pfr1 __prel64_initconst = {
 	.name		= "id_aa64pfr1",
 	.override	= &id_aa64pfr1_override,
 	.fields		= {
@@ -105,7 +116,7 @@ static const struct ftr_set_desc pfr1 __initconst = {
 	},
 };
 
-static const struct ftr_set_desc isar1 __initconst = {
+static const struct ftr_set_desc isar1 __prel64_initconst = {
 	.name		= "id_aa64isar1",
 	.override	= &id_aa64isar1_override,
 	.fields		= {
@@ -117,7 +128,7 @@ static const struct ftr_set_desc isar1 __initconst = {
 	},
 };
 
-static const struct ftr_set_desc isar2 __initconst = {
+static const struct ftr_set_desc isar2 __prel64_initconst = {
 	.name		= "id_aa64isar2",
 	.override	= &id_aa64isar2_override,
 	.fields		= {
@@ -128,7 +139,7 @@ static const struct ftr_set_desc isar2 __initconst = {
 	},
 };
 
-static const struct ftr_set_desc smfr0 __initconst = {
+static const struct ftr_set_desc smfr0 __prel64_initconst = {
 	.name		= "id_aa64smfr0",
 	.override	= &id_aa64smfr0_override,
 	.fields		= {
@@ -149,7 +160,7 @@ static bool __init hvhe_filter(u64 val)
 						     ID_AA64MMFR1_EL1_VH_SHIFT));
 }
 
-static const struct ftr_set_desc sw_features __initconst = {
+static const struct ftr_set_desc sw_features __prel64_initconst = {
 	.name		= "arm64_sw",
 	.override	= &arm64_sw_feature_override,
 	.fields		= {
@@ -159,22 +170,23 @@ static const struct ftr_set_desc sw_features __initconst = {
 	},
 };
 
-static const struct ftr_set_desc * const regs[] __initconst = {
-	&mmfr1,
-	&pfr0,
-	&pfr1,
-	&isar1,
-	&isar2,
-	&smfr0,
-	&sw_features,
+static const
+PREL64(const struct ftr_set_desc, reg) regs[] __prel64_initconst = {
+	{ &mmfr1	},
+	{ &pfr0 	},
+	{ &pfr1 	},
+	{ &isar1	},
+	{ &isar2	},
+	{ &smfr0	},
+	{ &sw_features	},
 };
 
 static const struct {
 	char	alias[FTR_ALIAS_NAME_LEN];
 	char	feature[FTR_ALIAS_OPTION_LEN];
 } aliases[] __initconst = {
-	{ "kvm-arm.mode=nvhe",		"id_aa64mmfr1.vh=0" },
-	{ "kvm-arm.mode=protected",	"id_aa64mmfr1.vh=0" },
+	{ "kvm_arm.mode=nvhe",		"id_aa64mmfr1.vh=0" },
+	{ "kvm_arm.mode=protected",	"id_aa64mmfr1.vh=0" },
 	{ "arm64.nosve",		"id_aa64pfr0.sve=0" },
 	{ "arm64.nosme",		"id_aa64pfr1.sme=0" },
 	{ "arm64.nobti",		"id_aa64pfr1.bt=0" },
@@ -187,45 +199,61 @@ static const struct {
 	{ "nokaslr",			"arm64_sw.nokaslr=1" },
 };
 
-static int __init parse_nokaslr(char *unused)
+static int __init parse_hexdigit(const char *p, u64 *v)
 {
-	/* nokaslr param handling is done by early cpufeature code */
+	// skip "0x" if it comes next
+	if (p[0] == '0' && tolower(p[1]) == 'x')
+		p += 2;
+
+	// check whether the RHS is a single hex digit
+	if (!isxdigit(p[0]) || (p[1] && !isspace(p[1])))
+		return -EINVAL;
+
+	*v = tolower(*p) - (isdigit(*p) ? '0' : 'a' - 10);
 	return 0;
 }
-early_param("nokaslr", parse_nokaslr);
 
-static int __init find_field(const char *cmdline,
+static int __init find_field(const char *cmdline, char *opt, int len,
 			     const struct ftr_set_desc *reg, int f, u64 *v)
 {
-	char opt[FTR_DESC_NAME_LEN + FTR_DESC_FIELD_LEN + 2];
-	int len;
+	int flen = strlen(reg->fields[f].name);
 
-	len = snprintf(opt, ARRAY_SIZE(opt), "%s.%s=",
-		       reg->name, reg->fields[f].name);
+	// append '<fieldname>=' to obtain '<name>.<fieldname>='
+	memcpy(opt + len, reg->fields[f].name, flen);
+	len += flen;
+	opt[len++] = '=';
 
-	if (!parameqn(cmdline, opt, len))
+	if (memcmp(cmdline, opt, len))
 		return -1;
 
-	return kstrtou64(cmdline + len, 0, v);
+	return parse_hexdigit(cmdline + len, v);
 }
 
 static void __init match_options(const char *cmdline)
 {
+	char opt[FTR_DESC_NAME_LEN + FTR_DESC_FIELD_LEN + 2];
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(regs); i++) {
+		const struct ftr_set_desc *reg = prel64_pointer(regs[i].reg);
+		struct arm64_ftr_override *override;
+		int len = strlen(reg->name);
 		int f;
 
-		if (!regs[i]->override)
-			continue;
+		override = prel64_pointer(reg->override);
 
-		for (f = 0; strlen(regs[i]->fields[f].name); f++) {
-			u64 shift = regs[i]->fields[f].shift;
-			u64 width = regs[i]->fields[f].width ?: 4;
+		// set opt[] to '<name>.'
+		memcpy(opt, reg->name, len);
+		opt[len++] = '.';
+
+		for (f = 0; reg->fields[f].name[0] != '\0'; f++) {
+			u64 shift = reg->fields[f].shift;
+			u64 width = reg->fields[f].width ?: 4;
 			u64 mask = GENMASK_ULL(shift + width - 1, shift);
+			bool (*filter)(u64 val);
 			u64 v;
 
-			if (find_field(cmdline, regs[i], f, &v))
+			if (find_field(cmdline, opt, len, reg, f, &v))
 				continue;
 
 			/*
@@ -233,16 +261,16 @@ static void __init match_options(const char *cmdline)
 			 * it by setting the value to the all-ones while
 			 * clearing the mask... Yes, this is fragile.
 			 */
-			if (regs[i]->fields[f].filter &&
-			    !regs[i]->fields[f].filter(v)) {
-				regs[i]->override->val  |= mask;
-				regs[i]->override->mask &= ~mask;
+			filter = prel64_pointer(reg->fields[f].filter);
+			if (filter && !filter(v)) {
+				override->val  |= mask;
+				override->mask &= ~mask;
 				continue;
 			}
 
-			regs[i]->override->val  &= ~mask;
-			regs[i]->override->val  |= (v << shift) & mask;
-			regs[i]->override->mask |= mask;
+			override->val  &= ~mask;
+			override->val  |= (v << shift) & mask;
+			override->mask |= mask;
 
 			return;
 		}
@@ -258,23 +286,29 @@ static __init void __parse_cmdline(const char *cmdline, bool parse_aliases)
 
 		cmdline = skip_spaces(cmdline);
 
-		for (len = 0; cmdline[len] && !isspace(cmdline[len]); len++);
-		if (!len)
+		/* terminate on "--" appearing on the command line by itself */
+		if (cmdline[0] == '-' && cmdline[1] == '-' && isspace(cmdline[2]))
 			return;
 
-		len = min(len, ARRAY_SIZE(buf) - 1);
-		memcpy(buf, cmdline, len);
-		buf[len] = '\0';
-
-		if (strcmp(buf, "--") == 0)
+		for (len = 0; cmdline[len] && !isspace(cmdline[len]); len++) {
+			if (len >= sizeof(buf) - 1)
+				break;
+			if (cmdline[len] == '-')
+				buf[len] = '_';
+			else
+				buf[len] = cmdline[len];
+		}
+		if (!len)
 			return;
 
+		buf[len] = 0;
+
 		cmdline += len;
 
 		match_options(buf);
 
 		for (i = 0; parse_aliases && i < ARRAY_SIZE(aliases); i++)
-			if (parameq(buf, aliases[i].alias))
+			if (!memcmp(buf, aliases[i].alias, len + 1))
 				__parse_cmdline(aliases[i].feature, false);
 	} while (1);
 }
@@ -316,13 +350,16 @@ void init_feature_override(u64 boot_status);
 
 asmlinkage void __init init_feature_override(u64 boot_status)
 {
+	struct arm64_ftr_override *override;
+	const struct ftr_set_desc *reg;
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(regs); i++) {
-		if (regs[i]->override) {
-			regs[i]->override->val  = 0;
-			regs[i]->override->mask = 0;
-		}
+		reg = prel64_pointer(regs[i].reg);
+		override = prel64_pointer(reg->override);
+
+		override->val  = 0;
+		override->mask = 0;
 	}
 
 	__boot_status = boot_status;
@@ -330,9 +367,9 @@ asmlinkage void __init init_feature_override(u64 boot_status)
 	parse_cmdline();
 
 	for (i = 0; i < ARRAY_SIZE(regs); i++) {
-		if (regs[i]->override)
-			dcache_clean_inval_poc((unsigned long)regs[i]->override,
-					    (unsigned long)regs[i]->override +
-					    sizeof(*regs[i]->override));
+		reg = prel64_pointer(regs[i].reg);
+		override = prel64_pointer(reg->override);
+		dcache_clean_inval_poc((unsigned long)override,
+				       (unsigned long)(override + 1));
 	}
 }
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 6ad5c6ef5329..85087e2df564 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -22,6 +22,7 @@
 #include <linux/vmalloc.h>
 #include <asm/daifflags.h>
 #include <asm/exception.h>
+#include <asm/numa.h>
 #include <asm/softirq_stack.h>
 #include <asm/stacktrace.h>
 #include <asm/vmap_stack.h>
@@ -47,17 +48,17 @@ static void init_irq_scs(void)
 
 	for_each_possible_cpu(cpu)
 		per_cpu(irq_shadow_call_stack_ptr, cpu) =
-			scs_alloc(cpu_to_node(cpu));
+			scs_alloc(early_cpu_to_node(cpu));
 }
 
 #ifdef CONFIG_VMAP_STACK
-static void init_irq_stacks(void)
+static void __init init_irq_stacks(void)
 {
 	int cpu;
 	unsigned long *p;
 
 	for_each_possible_cpu(cpu) {
-		p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, cpu_to_node(cpu));
+		p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, early_cpu_to_node(cpu));
 		per_cpu(irq_stack_ptr, cpu) = p;
 	}
 }
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index 94a269cd1f07..12c7f3c8ba76 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -36,3 +36,10 @@ void __init kaslr_init(void)
 	pr_info("KASLR enabled\n");
 	__kaslr_is_enabled = true;
 }
+
+static int __init parse_nokaslr(char *unused)
+{
+	/* nokaslr param handling is done by early cpufeature code */
+	return 0;
+}
+early_param("nokaslr", parse_nokaslr);
diff --git a/arch/arm64/kernel/kexec_image.c b/arch/arm64/kernel/kexec_image.c
index 636be6715155..532d72ea42ee 100644
--- a/arch/arm64/kernel/kexec_image.c
+++ b/arch/arm64/kernel/kexec_image.c
@@ -122,9 +122,9 @@ static void *image_load(struct kimage *image,
 	kernel_segment->memsz -= text_offset;
 	image->start = kernel_segment->mem;
 
-	pr_debug("Loaded kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
-				kernel_segment->mem, kbuf.bufsz,
-				kernel_segment->memsz);
+	kexec_dprintk("Loaded kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+		      kernel_segment->mem, kbuf.bufsz,
+		      kernel_segment->memsz);
 
 	return NULL;
 }
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index 078910db77a4..b38aae5b488d 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -32,26 +32,12 @@
 static void _kexec_image_info(const char *func, int line,
 	const struct kimage *kimage)
 {
-	unsigned long i;
-
-	pr_debug("%s:%d:\n", func, line);
-	pr_debug("  kexec kimage info:\n");
-	pr_debug("    type:        %d\n", kimage->type);
-	pr_debug("    start:       %lx\n", kimage->start);
-	pr_debug("    head:        %lx\n", kimage->head);
-	pr_debug("    nr_segments: %lu\n", kimage->nr_segments);
-	pr_debug("    dtb_mem: %pa\n", &kimage->arch.dtb_mem);
-	pr_debug("    kern_reloc: %pa\n", &kimage->arch.kern_reloc);
-	pr_debug("    el2_vectors: %pa\n", &kimage->arch.el2_vectors);
-
-	for (i = 0; i < kimage->nr_segments; i++) {
-		pr_debug("      segment[%lu]: %016lx - %016lx, 0x%lx bytes, %lu pages\n",
-			i,
-			kimage->segment[i].mem,
-			kimage->segment[i].mem + kimage->segment[i].memsz,
-			kimage->segment[i].memsz,
-			kimage->segment[i].memsz /  PAGE_SIZE);
-	}
+	kexec_dprintk("%s:%d:\n", func, line);
+	kexec_dprintk("  kexec kimage info:\n");
+	kexec_dprintk("    type:        %d\n", kimage->type);
+	kexec_dprintk("    head:        %lx\n", kimage->head);
+	kexec_dprintk("    kern_reloc: %pa\n", &kimage->arch.kern_reloc);
+	kexec_dprintk("    el2_vectors: %pa\n", &kimage->arch.el2_vectors);
 }
 
 void machine_kexec_cleanup(struct kimage *kimage)
diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
index a11a6e14ba89..0e017358f4ba 100644
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -127,8 +127,8 @@ int load_other_segments(struct kimage *image,
 		image->elf_load_addr = kbuf.mem;
 		image->elf_headers_sz = headers_sz;
 
-		pr_debug("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
-			 image->elf_load_addr, kbuf.bufsz, kbuf.memsz);
+		kexec_dprintk("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+			      image->elf_load_addr, kbuf.bufsz, kbuf.memsz);
 	}
 
 	/* load initrd */
@@ -148,8 +148,8 @@ int load_other_segments(struct kimage *image,
 			goto out_err;
 		initrd_load_addr = kbuf.mem;
 
-		pr_debug("Loaded initrd at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
-				initrd_load_addr, kbuf.bufsz, kbuf.memsz);
+		kexec_dprintk("Loaded initrd at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+			      initrd_load_addr, kbuf.bufsz, kbuf.memsz);
 	}
 
 	/* load dtb */
@@ -179,8 +179,8 @@ int load_other_segments(struct kimage *image,
 	image->arch.dtb = dtb;
 	image->arch.dtb_mem = kbuf.mem;
 
-	pr_debug("Loaded dtb at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
-			kbuf.mem, kbuf.bufsz, kbuf.memsz);
+	kexec_dprintk("Loaded dtb at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+		      kbuf.mem, kbuf.bufsz, kbuf.memsz);
 
 	return 0;
 
diff --git a/arch/arm64/kernel/pi/Makefile b/arch/arm64/kernel/pi/Makefile
index 4c0ea3cd4ea4..c844a0546d7f 100644
--- a/arch/arm64/kernel/pi/Makefile
+++ b/arch/arm64/kernel/pi/Makefile
@@ -3,6 +3,7 @@
 
 KBUILD_CFLAGS	:= $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) -fpie \
 		   -Os -DDISABLE_BRANCH_PROFILING $(DISABLE_STACKLEAK_PLUGIN) \
+		   $(DISABLE_LATENT_ENTROPY_PLUGIN) \
 		   $(call cc-option,-mbranch-protection=none) \
 		   -I$(srctree)/scripts/dtc/libfdt -fno-stack-protector \
 		   -include $(srctree)/include/linux/hidden.h \
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 20d7ef82de90..09bb7fc7d3c2 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -28,6 +28,7 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/regset.h>
 #include <linux/elf.h>
+#include <linux/rseq.h>
 
 #include <asm/compat.h>
 #include <asm/cpufeature.h>
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index defbab84e9e5..4ced34f62dab 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -439,9 +439,8 @@ static void __init hyp_mode_check(void)
 void __init smp_cpus_done(unsigned int max_cpus)
 {
 	pr_info("SMP: Total of %d processors activated.\n", num_online_cpus());
-	setup_system_features();
 	hyp_mode_check();
-	apply_alternatives_all();
+	setup_system_features();
 	setup_user_features();
 	mark_linear_text_alias_ro();
 }
@@ -454,14 +453,9 @@ void __init smp_prepare_boot_cpu(void)
 	 * freed shortly, so we must move over to the runtime per-cpu area.
 	 */
 	set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
-	cpuinfo_store_boot_cpu();
 
-	/*
-	 * We now know enough about the boot CPU to apply the
-	 * alternatives that cannot wait until interrupt handling
-	 * and/or scheduling is enabled.
-	 */
-	apply_boot_alternatives();
+	cpuinfo_store_boot_cpu();
+	setup_boot_cpu_features();
 
 	/* Conditionally switch to GIC PMR for interrupt masking */
 	if (system_uses_irq_prio_masking())
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 17f66a74c745..7f88028a00c0 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -8,6 +8,7 @@
 #include <linux/efi.h>
 #include <linux/export.h>
 #include <linux/ftrace.h>
+#include <linux/kprobes.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task_stack.h>
@@ -19,6 +20,31 @@
 #include <asm/stacktrace.h>
 
 /*
+ * Kernel unwind state
+ *
+ * @common:      Common unwind state.
+ * @task:        The task being unwound.
+ * @kr_cur:      When KRETPROBES is selected, holds the kretprobe instance
+ *               associated with the most recently encountered replacement lr
+ *               value.
+ */
+struct kunwind_state {
+	struct unwind_state common;
+	struct task_struct *task;
+#ifdef CONFIG_KRETPROBES
+	struct llist_node *kr_cur;
+#endif
+};
+
+static __always_inline void
+kunwind_init(struct kunwind_state *state,
+	     struct task_struct *task)
+{
+	unwind_init_common(&state->common);
+	state->task = task;
+}
+
+/*
  * Start an unwind from a pt_regs.
  *
  * The unwind will begin at the PC within the regs.
@@ -26,13 +52,13 @@
  * The regs must be on a stack currently owned by the calling task.
  */
 static __always_inline void
-unwind_init_from_regs(struct unwind_state *state,
-		      struct pt_regs *regs)
+kunwind_init_from_regs(struct kunwind_state *state,
+		       struct pt_regs *regs)
 {
-	unwind_init_common(state, current);
+	kunwind_init(state, current);
 
-	state->fp = regs->regs[29];
-	state->pc = regs->pc;
+	state->common.fp = regs->regs[29];
+	state->common.pc = regs->pc;
 }
 
 /*
@@ -44,12 +70,12 @@ unwind_init_from_regs(struct unwind_state *state,
  * The function which invokes this must be noinline.
  */
 static __always_inline void
-unwind_init_from_caller(struct unwind_state *state)
+kunwind_init_from_caller(struct kunwind_state *state)
 {
-	unwind_init_common(state, current);
+	kunwind_init(state, current);
 
-	state->fp = (unsigned long)__builtin_frame_address(1);
-	state->pc = (unsigned long)__builtin_return_address(0);
+	state->common.fp = (unsigned long)__builtin_frame_address(1);
+	state->common.pc = (unsigned long)__builtin_return_address(0);
 }
 
 /*
@@ -63,35 +89,38 @@ unwind_init_from_caller(struct unwind_state *state)
  * call this for the current task.
  */
 static __always_inline void
-unwind_init_from_task(struct unwind_state *state,
-		      struct task_struct *task)
+kunwind_init_from_task(struct kunwind_state *state,
+		       struct task_struct *task)
 {
-	unwind_init_common(state, task);
+	kunwind_init(state, task);
 
-	state->fp = thread_saved_fp(task);
-	state->pc = thread_saved_pc(task);
+	state->common.fp = thread_saved_fp(task);
+	state->common.pc = thread_saved_pc(task);
 }
 
 static __always_inline int
-unwind_recover_return_address(struct unwind_state *state)
+kunwind_recover_return_address(struct kunwind_state *state)
 {
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	if (state->task->ret_stack &&
-	    (state->pc == (unsigned long)return_to_handler)) {
+	    (state->common.pc == (unsigned long)return_to_handler)) {
 		unsigned long orig_pc;
-		orig_pc = ftrace_graph_ret_addr(state->task, NULL, state->pc,
-						(void *)state->fp);
-		if (WARN_ON_ONCE(state->pc == orig_pc))
+		orig_pc = ftrace_graph_ret_addr(state->task, NULL,
+						state->common.pc,
+						(void *)state->common.fp);
+		if (WARN_ON_ONCE(state->common.pc == orig_pc))
 			return -EINVAL;
-		state->pc = orig_pc;
+		state->common.pc = orig_pc;
 	}
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
 #ifdef CONFIG_KRETPROBES
-	if (is_kretprobe_trampoline(state->pc)) {
-		state->pc = kretprobe_find_ret_addr(state->task,
-						    (void *)state->fp,
-						    &state->kr_cur);
+	if (is_kretprobe_trampoline(state->common.pc)) {
+		unsigned long orig_pc;
+		orig_pc = kretprobe_find_ret_addr(state->task,
+						  (void *)state->common.fp,
+						  &state->kr_cur);
+		state->common.pc = orig_pc;
 	}
 #endif /* CONFIG_KRETPROBES */
 
@@ -106,38 +135,40 @@ unwind_recover_return_address(struct unwind_state *state)
  * and the location (but not the fp value) of B.
  */
 static __always_inline int
-unwind_next(struct unwind_state *state)
+kunwind_next(struct kunwind_state *state)
 {
 	struct task_struct *tsk = state->task;
-	unsigned long fp = state->fp;
+	unsigned long fp = state->common.fp;
 	int err;
 
 	/* Final frame; nothing to unwind */
 	if (fp == (unsigned long)task_pt_regs(tsk)->stackframe)
 		return -ENOENT;
 
-	err = unwind_next_frame_record(state);
+	err = unwind_next_frame_record(&state->common);
 	if (err)
 		return err;
 
-	state->pc = ptrauth_strip_kernel_insn_pac(state->pc);
+	state->common.pc = ptrauth_strip_kernel_insn_pac(state->common.pc);
 
-	return unwind_recover_return_address(state);
+	return kunwind_recover_return_address(state);
 }
 
+typedef bool (*kunwind_consume_fn)(const struct kunwind_state *state, void *cookie);
+
 static __always_inline void
-unwind(struct unwind_state *state, stack_trace_consume_fn consume_entry,
-       void *cookie)
+do_kunwind(struct kunwind_state *state, kunwind_consume_fn consume_state,
+	   void *cookie)
 {
-	if (unwind_recover_return_address(state))
+	if (kunwind_recover_return_address(state))
 		return;
 
 	while (1) {
 		int ret;
 
-		if (!consume_entry(cookie, state->pc))
+		if (!consume_state(state, cookie))
 			break;
-		ret = unwind_next(state);
+		ret = kunwind_next(state);
 		if (ret < 0)
 			break;
 	}
@@ -172,9 +203,10 @@ unwind(struct unwind_state *state, stack_trace_consume_fn consume_entry,
 			: stackinfo_get_unknown();		\
 	})
 
-noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry,
-			      void *cookie, struct task_struct *task,
-			      struct pt_regs *regs)
+static __always_inline void
+kunwind_stack_walk(kunwind_consume_fn consume_state,
+		   void *cookie, struct task_struct *task,
+		   struct pt_regs *regs)
 {
 	struct stack_info stacks[] = {
 		stackinfo_get_task(task),
@@ -190,22 +222,48 @@ noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry,
 		STACKINFO_EFI,
 #endif
 	};
-	struct unwind_state state = {
-		.stacks = stacks,
-		.nr_stacks = ARRAY_SIZE(stacks),
+	struct kunwind_state state = {
+		.common = {
+			.stacks = stacks,
+			.nr_stacks = ARRAY_SIZE(stacks),
+		},
 	};
 
 	if (regs) {
 		if (task != current)
 			return;
-		unwind_init_from_regs(&state, regs);
+		kunwind_init_from_regs(&state, regs);
 	} else if (task == current) {
-		unwind_init_from_caller(&state);
+		kunwind_init_from_caller(&state);
 	} else {
-		unwind_init_from_task(&state, task);
+		kunwind_init_from_task(&state, task);
 	}
 
-	unwind(&state, consume_entry, cookie);
+	do_kunwind(&state, consume_state, cookie);
+}
+
+struct kunwind_consume_entry_data {
+	stack_trace_consume_fn consume_entry;
+	void *cookie;
+};
+
+static bool
+arch_kunwind_consume_entry(const struct kunwind_state *state, void *cookie)
+{
+	struct kunwind_consume_entry_data *data = cookie;
+	return data->consume_entry(data->cookie, state->common.pc);
+}
+
+noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry,
+			      void *cookie, struct task_struct *task,
+			      struct pt_regs *regs)
+{
+	struct kunwind_consume_entry_data data = {
+		.consume_entry = consume_entry,
+		.cookie = cookie,
+	};
+
+	kunwind_stack_walk(arch_kunwind_consume_entry, &data, task, regs);
 }
 
 static bool dump_backtrace_entry(void *arg, unsigned long where)
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 817d788cd866..1a2c72f3e7f8 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -82,7 +82,12 @@ int __init parse_acpi_topology(void)
 #undef pr_fmt
 #define pr_fmt(fmt) "AMU: " fmt
 
-static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale);
+/*
+ * Ensure that amu_scale_freq_tick() will return SCHED_CAPACITY_SCALE until
+ * the CPU capacity and its associated frequency have been correctly
+ * initialized.
+ */
+static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale) =  1UL << (2 * SCHED_CAPACITY_SHIFT);
 static DEFINE_PER_CPU(u64, arch_const_cycles_prev);
 static DEFINE_PER_CPU(u64, arch_core_cycles_prev);
 static cpumask_var_t amu_fie_cpus;
@@ -112,14 +117,14 @@ static inline bool freq_counters_valid(int cpu)
 	return true;
 }
 
-static int freq_inv_set_max_ratio(int cpu, u64 max_rate, u64 ref_rate)
+void freq_inv_set_max_ratio(int cpu, u64 max_rate)
 {
-	u64 ratio;
+	u64 ratio, ref_rate = arch_timer_get_rate();
 
 	if (unlikely(!max_rate || !ref_rate)) {
-		pr_debug("CPU%d: invalid maximum or reference frequency.\n",
+		WARN_ONCE(1, "CPU%d: invalid maximum or reference frequency.\n",
 			 cpu);
-		return -EINVAL;
+		return;
 	}
 
 	/*
@@ -139,12 +144,10 @@ static int freq_inv_set_max_ratio(int cpu, u64 max_rate, u64 ref_rate)
 	ratio = div64_u64(ratio, max_rate);
 	if (!ratio) {
 		WARN_ONCE(1, "Reference frequency too low.\n");
-		return -EINVAL;
+		return;
 	}
 
-	per_cpu(arch_max_freq_scale, cpu) = (unsigned long)ratio;
-
-	return 0;
+	WRITE_ONCE(per_cpu(arch_max_freq_scale, cpu), (unsigned long)ratio);
 }
 
 static void amu_scale_freq_tick(void)
@@ -195,10 +198,7 @@ static void amu_fie_setup(const struct cpumask *cpus)
 		return;
 
 	for_each_cpu(cpu, cpus) {
-		if (!freq_counters_valid(cpu) ||
-		    freq_inv_set_max_ratio(cpu,
-					   cpufreq_get_hw_max_freq(cpu) * 1000ULL,
-					   arch_timer_get_rate()))
+		if (!freq_counters_valid(cpu))
 			return;
 	}
 
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index 1f911a76c5af..2266fcdff78a 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -118,7 +118,7 @@ endif
 VDSO_CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os
 
 # Build rules
-targets := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso) vdso.so vdso.so.dbg vdso.so.raw
+targets := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso) vdso.so vdso32.so.dbg vdso.so.raw
 c-obj-vdso := $(addprefix $(obj)/, $(c-obj-vdso))
 c-obj-vdso-gettimeofday := $(addprefix $(obj)/, $(c-obj-vdso-gettimeofday))
 asm-obj-vdso := $(addprefix $(obj)/, $(asm-obj-vdso))
@@ -127,15 +127,15 @@ obj-vdso := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso)
 targets += vdso.lds
 CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
 
-include/generated/vdso32-offsets.h: $(obj)/vdso.so.dbg FORCE
+include/generated/vdso32-offsets.h: $(obj)/vdso32.so.dbg FORCE
 	$(call if_changed,vdsosym)
 
 # Strip rule for vdso.so
 $(obj)/vdso.so: OBJCOPYFLAGS := -S
-$(obj)/vdso.so: $(obj)/vdso.so.dbg FORCE
+$(obj)/vdso.so: $(obj)/vdso32.so.dbg FORCE
 	$(call if_changed,objcopy)
 
-$(obj)/vdso.so.dbg: $(obj)/vdso.so.raw $(obj)/$(munge) FORCE
+$(obj)/vdso32.so.dbg: $(obj)/vdso.so.raw $(obj)/$(munge) FORCE
 	$(call if_changed,vdsomunge)
 
 # Link rule for the .so file, .lds has to be first
diff --git a/arch/arm64/kernel/vdso32/vgettimeofday.c b/arch/arm64/kernel/vdso32/vgettimeofday.c
index 5acff29c5991..29b4d8f61e39 100644
--- a/arch/arm64/kernel/vdso32/vgettimeofday.c
+++ b/arch/arm64/kernel/vdso32/vgettimeofday.c
@@ -5,6 +5,8 @@
  * Copyright (C) 2018 ARM Limited
  *
  */
+#define BUILD_VDSO32_64
+#include <vdso/gettime.h>
 
 int __vdso_clock_gettime(clockid_t clock,
 			 struct old_timespec32 *ts)
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index e5f75f1f1085..4796104c4471 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -410,7 +410,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
 	kvm_timer_vcpu_terminate(vcpu);
 	kvm_pmu_vcpu_destroy(vcpu);
-
+	kvm_vgic_vcpu_destroy(vcpu);
 	kvm_arm_vcpu_destroy(vcpu);
 }
 
diff --git a/arch/arm64/kvm/hyp/include/nvhe/gfp.h b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
index fe5472a184a3..97c527ef53c2 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/gfp.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
@@ -16,7 +16,7 @@ struct hyp_pool {
 	 * API at EL2.
 	 */
 	hyp_spinlock_t lock;
-	struct list_head free_area[MAX_ORDER + 1];
+	struct list_head free_area[NR_PAGE_ORDERS];
 	phys_addr_t range_start;
 	phys_addr_t range_end;
 	unsigned short max_order;
diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
index b1e392186a0f..e691290d3765 100644
--- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c
+++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
@@ -228,7 +228,8 @@ int hyp_pool_init(struct hyp_pool *pool, u64 pfn, unsigned int nr_pages,
 	int i;
 
 	hyp_spin_lock_init(&pool->lock);
-	pool->max_order = min(MAX_ORDER, get_order(nr_pages << PAGE_SHIFT));
+	pool->max_order = min(MAX_PAGE_ORDER,
+			      get_order(nr_pages << PAGE_SHIFT));
 	for (i = 0; i <= pool->max_order; i++)
 		INIT_LIST_HEAD(&pool->free_area[i]);
 	pool->range_start = phys;
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index 9d23a51d7f75..b29f15418c0a 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -12,7 +12,7 @@
 #include <nvhe/pkvm.h>
 #include <nvhe/trap_handler.h>
 
-/* Used by icache_is_vpipt(). */
+/* Used by icache_is_aliasing(). */
 unsigned long __icache_flags;
 
 /* Used by kvm_get_vttbr(). */
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index 1b265713d6be..a60fb13e2192 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -105,28 +105,6 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
 	dsb(ish);
 	isb();
 
-	/*
-	 * If the host is running at EL1 and we have a VPIPT I-cache,
-	 * then we must perform I-cache maintenance at EL2 in order for
-	 * it to have an effect on the guest. Since the guest cannot hit
-	 * I-cache lines allocated with a different VMID, we don't need
-	 * to worry about junk out of guest reset (we nuke the I-cache on
-	 * VMID rollover), but we do need to be careful when remapping
-	 * executable pages for the same guest. This can happen when KSM
-	 * takes a CoW fault on an executable page, copies the page into
-	 * a page that was previously mapped in the guest and then needs
-	 * to invalidate the guest view of the I-cache for that page
-	 * from EL1. To solve this, we invalidate the entire I-cache when
-	 * unmapping a page from a guest if we have a VPIPT I-cache but
-	 * the host is running at EL1. As above, we could do better if
-	 * we had the VA.
-	 *
-	 * The moral of this story is: if you have a VPIPT I-cache, then
-	 * you should be running with VHE enabled.
-	 */
-	if (icache_is_vpipt())
-		icache_inval_all_pou();
-
 	__tlb_switch_to_host(&cxt);
 }
 
@@ -157,28 +135,6 @@ void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
 	dsb(nsh);
 	isb();
 
-	/*
-	 * If the host is running at EL1 and we have a VPIPT I-cache,
-	 * then we must perform I-cache maintenance at EL2 in order for
-	 * it to have an effect on the guest. Since the guest cannot hit
-	 * I-cache lines allocated with a different VMID, we don't need
-	 * to worry about junk out of guest reset (we nuke the I-cache on
-	 * VMID rollover), but we do need to be careful when remapping
-	 * executable pages for the same guest. This can happen when KSM
-	 * takes a CoW fault on an executable page, copies the page into
-	 * a page that was previously mapped in the guest and then needs
-	 * to invalidate the guest view of the I-cache for that page
-	 * from EL1. To solve this, we invalidate the entire I-cache when
-	 * unmapping a page from a guest if we have a VPIPT I-cache but
-	 * the host is running at EL1. As above, we could do better if
-	 * we had the VA.
-	 *
-	 * The moral of this story is: if you have a VPIPT I-cache, then
-	 * you should be running with VHE enabled.
-	 */
-	if (icache_is_vpipt())
-		icache_inval_all_pou();
-
 	__tlb_switch_to_host(&cxt);
 }
 
@@ -205,10 +161,6 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
 	dsb(ish);
 	isb();
 
-	/* See the comment in __kvm_tlb_flush_vmid_ipa() */
-	if (icache_is_vpipt())
-		icache_inval_all_pou();
-
 	__tlb_switch_to_host(&cxt);
 }
 
@@ -246,18 +198,5 @@ void __kvm_flush_vm_context(void)
 	/* Same remark as in __tlb_switch_to_guest() */
 	dsb(ish);
 	__tlbi(alle1is);
-
-	/*
-	 * VIPT and PIPT caches are not affected by VMID, so no maintenance
-	 * is necessary across a VMID rollover.
-	 *
-	 * VPIPT caches constrain lookup and maintenance to the active VMID,
-	 * so we need to invalidate lines with a stale VMID to avoid an ABA
-	 * race after multiple rollovers.
-	 *
-	 */
-	if (icache_is_vpipt())
-		asm volatile("ic ialluis");
-
 	dsb(ish);
 }
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index b636b4111dbf..b32e2940df7d 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -216,18 +216,5 @@ void __kvm_flush_vm_context(void)
 {
 	dsb(ishst);
 	__tlbi(alle1is);
-
-	/*
-	 * VIPT and PIPT caches are not affected by VMID, so no maintenance
-	 * is necessary across a VMID rollover.
-	 *
-	 * VPIPT caches constrain lookup and maintenance to the active VMID,
-	 * so we need to invalidate lines with a stale VMID to avoid an ABA
-	 * race after multiple rollovers.
-	 *
-	 */
-	if (icache_is_vpipt())
-		asm volatile("ic ialluis");
-
 	dsb(ish);
 }
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index fe99b3dab6ce..3d9467ff73bc 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -267,9 +267,8 @@ void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu)
 
 u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
 {
-	u64 val = kvm_vcpu_read_pmcr(vcpu) >> ARMV8_PMU_PMCR_N_SHIFT;
+	u64 val = FIELD_GET(ARMV8_PMU_PMCR_N, kvm_vcpu_read_pmcr(vcpu));
 
-	val &= ARMV8_PMU_PMCR_N_MASK;
 	if (val == 0)
 		return BIT(ARMV8_PMU_CYCLE_IDX);
 	else
@@ -1136,8 +1135,7 @@ u8 kvm_arm_pmu_get_pmuver_limit(void)
  */
 u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu)
 {
-	u64 pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0) &
-			~(ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT);
+	u64 pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0);
 
-	return pmcr | ((u64)vcpu->kvm->arch.pmcr_n << ARMV8_PMU_PMCR_N_SHIFT);
+	return u64_replace_bits(pmcr, vcpu->kvm->arch.pmcr_n, ARMV8_PMU_PMCR_N);
 }
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 4735e1b37fb3..ff45d688bd7d 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -877,7 +877,7 @@ static bool pmu_counter_idx_valid(struct kvm_vcpu *vcpu, u64 idx)
 	u64 pmcr, val;
 
 	pmcr = kvm_vcpu_read_pmcr(vcpu);
-	val = (pmcr >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK;
+	val = FIELD_GET(ARMV8_PMU_PMCR_N, pmcr);
 	if (idx >= val && idx != ARMV8_PMU_CYCLE_IDX) {
 		kvm_inject_undefined(vcpu);
 		return false;
@@ -1143,7 +1143,7 @@ static int get_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 static int set_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 		    u64 val)
 {
-	u8 new_n = (val >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK;
+	u8 new_n = FIELD_GET(ARMV8_PMU_PMCR_N, val);
 	struct kvm *kvm = vcpu->kvm;
 
 	mutex_lock(&kvm->arch.config_lock);
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index c8c3cb812783..e949e1d0fd9f 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -368,7 +368,7 @@ static void kvm_vgic_dist_destroy(struct kvm *kvm)
 		vgic_v4_teardown(kvm);
 }
 
-void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
+static void __kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 
@@ -379,29 +379,39 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
 	vgic_flush_pending_lpis(vcpu);
 
 	INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
-	vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;
+	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
+		vgic_unregister_redist_iodev(vcpu);
+		vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;
+	}
 }
 
-static void __kvm_vgic_destroy(struct kvm *kvm)
+void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+
+	mutex_lock(&kvm->slots_lock);
+	__kvm_vgic_vcpu_destroy(vcpu);
+	mutex_unlock(&kvm->slots_lock);
+}
+
+void kvm_vgic_destroy(struct kvm *kvm)
 {
 	struct kvm_vcpu *vcpu;
 	unsigned long i;
 
-	lockdep_assert_held(&kvm->arch.config_lock);
+	mutex_lock(&kvm->slots_lock);
 
 	vgic_debug_destroy(kvm);
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
-		kvm_vgic_vcpu_destroy(vcpu);
+		__kvm_vgic_vcpu_destroy(vcpu);
+
+	mutex_lock(&kvm->arch.config_lock);
 
 	kvm_vgic_dist_destroy(kvm);
-}
 
-void kvm_vgic_destroy(struct kvm *kvm)
-{
-	mutex_lock(&kvm->arch.config_lock);
-	__kvm_vgic_destroy(kvm);
 	mutex_unlock(&kvm->arch.config_lock);
+	mutex_unlock(&kvm->slots_lock);
 }
 
 /**
@@ -469,25 +479,26 @@ int kvm_vgic_map_resources(struct kvm *kvm)
 		type = VGIC_V3;
 	}
 
-	if (ret) {
-		__kvm_vgic_destroy(kvm);
+	if (ret)
 		goto out;
-	}
+
 	dist->ready = true;
 	dist_base = dist->vgic_dist_base;
 	mutex_unlock(&kvm->arch.config_lock);
 
 	ret = vgic_register_dist_iodev(kvm, dist_base, type);
-	if (ret) {
+	if (ret)
 		kvm_err("Unable to register VGIC dist MMIO regions\n");
-		kvm_vgic_destroy(kvm);
-	}
-	mutex_unlock(&kvm->slots_lock);
-	return ret;
 
+	goto out_slots;
 out:
 	mutex_unlock(&kvm->arch.config_lock);
+out_slots:
 	mutex_unlock(&kvm->slots_lock);
+
+	if (ret)
+		kvm_vgic_destroy(kvm);
+
 	return ret;
 }
 
diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
index 89117ba2528a..a764b0ab8bf9 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
@@ -820,7 +820,7 @@ out_unlock:
 	return ret;
 }
 
-static void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu)
+void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu)
 {
 	struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev;
 
@@ -833,6 +833,8 @@ static int vgic_register_all_redist_iodevs(struct kvm *kvm)
 	unsigned long c;
 	int ret = 0;
 
+	lockdep_assert_held(&kvm->slots_lock);
+
 	kvm_for_each_vcpu(c, vcpu, kvm) {
 		ret = vgic_register_redist_iodev(vcpu);
 		if (ret)
diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c
index 339a55194b2c..74a67ad87f29 100644
--- a/arch/arm64/kvm/vgic/vgic-v4.c
+++ b/arch/arm64/kvm/vgic/vgic-v4.c
@@ -436,6 +436,10 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq,
 	if (ret)
 		goto out;
 
+	/* Silently exit if the vLPI is already mapped */
+	if (irq->hw)
+		goto out;
+
 	/*
 	 * Emit the mapping request. If it fails, the ITS probably
 	 * isn't v4 compatible, so let's silently bail out. Holding
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index 0ab09b0d4440..8d134569d0a1 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -241,6 +241,7 @@ int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq);
 int vgic_v3_save_pending_tables(struct kvm *kvm);
 int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count);
 int vgic_register_redist_iodev(struct kvm_vcpu *vcpu);
+void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu);
 bool vgic_v3_check_base(struct kvm *kvm);
 
 void vgic_v3_load(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/lib/copy_page.S b/arch/arm64/lib/copy_page.S
index c336d2ffdec5..6a56d7cf309d 100644
--- a/arch/arm64/lib/copy_page.S
+++ b/arch/arm64/lib/copy_page.S
@@ -18,13 +18,6 @@
  *	x1 - src
  */
 SYM_FUNC_START(__pi_copy_page)
-alternative_if ARM64_HAS_NO_HW_PREFETCH
-	// Prefetch three cache lines ahead.
-	prfm	pldl1strm, [x1, #128]
-	prfm	pldl1strm, [x1, #256]
-	prfm	pldl1strm, [x1, #384]
-alternative_else_nop_endif
-
 	ldp	x2, x3, [x1]
 	ldp	x4, x5, [x1, #16]
 	ldp	x6, x7, [x1, #32]
@@ -39,10 +32,6 @@ alternative_else_nop_endif
 1:
 	tst	x0, #(PAGE_SIZE - 1)
 
-alternative_if ARM64_HAS_NO_HW_PREFETCH
-	prfm	pldl1strm, [x1, #384]
-alternative_else_nop_endif
-
 	stnp	x2, x3, [x0, #-256]
 	ldp	x2, x3, [x1]
 	stnp	x4, x5, [x0, #16 - 256]
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 460d799e1296..55f6455a8284 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -607,6 +607,8 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
 		goto done;
 	}
 	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+	if (fault & VM_FAULT_MAJOR)
+		mm_flags |= FAULT_FLAG_TRIED;
 
 	/* Quick path to respond to signals */
 	if (fault_signal_pending(fault, regs)) {
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index f5aae342632c..8116ac599f80 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -51,7 +51,7 @@ void __init arm64_hugetlb_cma_reserve(void)
 	 * page allocator. Just warn if there is any change
 	 * breaking this assumption.
 	 */
-	WARN_ON(order <= MAX_ORDER);
+	WARN_ON(order <= MAX_PAGE_ORDER);
 	hugetlb_cma_reserve(order);
 }
 #endif /* CONFIG_CMA */
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index 555285ebd5af..4c7ad574b946 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -170,6 +170,11 @@ asmlinkage void __init kasan_early_init(void)
 {
 	BUILD_BUG_ON(KASAN_SHADOW_OFFSET !=
 		KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT)));
+	/*
+	 * We cannot check the actual value of KASAN_SHADOW_START during build,
+	 * as it depends on vabits_actual. As a best-effort approach, check
+	 * potential values calculated based on VA_BITS and VA_BITS_MIN.
+	 */
 	BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS), PGDIR_SIZE));
 	BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS_MIN), PGDIR_SIZE));
 	BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PGDIR_SIZE));
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 15f6347d23b6..1ac7467d34c9 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -52,9 +52,6 @@ u64 vabits_actual __ro_after_init = VA_BITS_MIN;
 EXPORT_SYMBOL(vabits_actual);
 #endif
 
-u64 kimage_vaddr __ro_after_init = (u64)&_text;
-EXPORT_SYMBOL(kimage_vaddr);
-
 u64 kimage_voffset __ro_after_init;
 EXPORT_SYMBOL(kimage_voffset);
 
@@ -674,6 +671,9 @@ static int __init map_entry_trampoline(void)
 {
 	int i;
 
+	if (!arm64_kernel_unmapped_at_el0())
+		return 0;
+
 	pgprot_t prot = kernel_exec_prot();
 	phys_addr_t pa_start = __pa_symbol(__entry_tramp_text_start);
 
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index 8e2017ba5f1b..924843f1f661 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -29,8 +29,8 @@ bool can_set_direct_map(void)
 	 *
 	 * KFENCE pool requires page-granular mapping if initialized late.
 	 */
-	return (rodata_enabled && rodata_full) || debug_pagealloc_enabled() ||
-		arm64_kfence_can_set_direct_map();
+	return rodata_full || debug_pagealloc_enabled() ||
+	       arm64_kfence_can_set_direct_map();
 }
 
 static int change_page_range(pte_t *ptep, unsigned long addr, void *data)
@@ -105,8 +105,7 @@ static int change_memory_common(unsigned long addr, int numpages,
 	 * If we are manipulating read-only permissions, apply the same
 	 * change to the linear mapping of the pages that back this VM area.
 	 */
-	if (rodata_enabled &&
-	    rodata_full && (pgprot_val(set_mask) == PTE_RDONLY ||
+	if (rodata_full && (pgprot_val(set_mask) == PTE_RDONLY ||
 			    pgprot_val(clear_mask) == PTE_RDONLY)) {
 		for (i = 0; i < area->nr_pages; i++) {
 			__change_memory_common((u64)page_address(area->pages[i]),
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 7d4af64e3982..8955da5c47cf 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -1828,7 +1828,7 @@ static void restore_args(struct jit_ctx *ctx, int args_off, int nregs)
  *
  */
 static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
-			      struct bpf_tramp_links *tlinks, void *orig_call,
+			      struct bpf_tramp_links *tlinks, void *func_addr,
 			      int nregs, u32 flags)
 {
 	int i;
@@ -1926,7 +1926,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
 
 	if (flags & BPF_TRAMP_F_IP_ARG) {
 		/* save ip address of the traced function */
-		emit_addr_mov_i64(A64_R(10), (const u64)orig_call, ctx);
+		emit_addr_mov_i64(A64_R(10), (const u64)func_addr, ctx);
 		emit(A64_STR64I(A64_R(10), A64_SP, ip_off), ctx);
 	}
 
@@ -2026,18 +2026,10 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
 	return ctx->idx;
 }
 
-int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
-				void *image_end, const struct btf_func_model *m,
-				u32 flags, struct bpf_tramp_links *tlinks,
-				void *orig_call)
+static int btf_func_model_nregs(const struct btf_func_model *m)
 {
-	int i, ret;
 	int nregs = m->nr_args;
-	int max_insns = ((long)image_end - (long)image) / AARCH64_INSN_SIZE;
-	struct jit_ctx ctx = {
-		.image = NULL,
-		.idx = 0,
-	};
+	int i;
 
 	/* extra registers needed for struct argument */
 	for (i = 0; i < MAX_BPF_FUNC_ARGS; i++) {
@@ -2046,22 +2038,49 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
 			nregs += (m->arg_size[i] + 7) / 8 - 1;
 	}
 
+	return nregs;
+}
+
+int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
+			     struct bpf_tramp_links *tlinks, void *func_addr)
+{
+	struct jit_ctx ctx = {
+		.image = NULL,
+		.idx = 0,
+	};
+	struct bpf_tramp_image im;
+	int nregs, ret;
+
+	nregs = btf_func_model_nregs(m);
 	/* the first 8 registers are used for arguments */
 	if (nregs > 8)
 		return -ENOTSUPP;
 
-	ret = prepare_trampoline(&ctx, im, tlinks, orig_call, nregs, flags);
+	ret = prepare_trampoline(&ctx, &im, tlinks, func_addr, nregs, flags);
 	if (ret < 0)
 		return ret;
 
-	if (ret > max_insns)
-		return -EFBIG;
+	return ret < 0 ? ret : ret * AARCH64_INSN_SIZE;
+}
 
-	ctx.image = image;
-	ctx.idx = 0;
+int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
+				void *image_end, const struct btf_func_model *m,
+				u32 flags, struct bpf_tramp_links *tlinks,
+				void *func_addr)
+{
+	int ret, nregs;
+	struct jit_ctx ctx = {
+		.image = image,
+		.idx = 0,
+	};
+
+	nregs = btf_func_model_nregs(m);
+	/* the first 8 registers are used for arguments */
+	if (nregs > 8)
+		return -ENOTSUPP;
 
 	jit_fill_hole(image, (unsigned int)(image_end - image));
-	ret = prepare_trampoline(&ctx, im, tlinks, orig_call, nregs, flags);
+	ret = prepare_trampoline(&ctx, im, tlinks, func_addr, nregs, flags);
 
 	if (ret > 0 && validate_code(&ctx) < 0)
 		ret = -EINVAL;
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index b98c38288a9d..1e07d74d7a6c 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -37,10 +37,10 @@ HAS_GIC_PRIO_MASKING
 HAS_GIC_PRIO_RELAXED_SYNC
 HAS_HCX
 HAS_LDAPR
+HAS_LPA2
 HAS_LSE_ATOMICS
 HAS_MOPS
 HAS_NESTED_VIRT
-HAS_NO_HW_PREFETCH
 HAS_PAN
 HAS_S1PIE
 HAS_RAS_EXTN
diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg
index 96cbeeab4eec..4c9b67934367 100644
--- a/arch/arm64/tools/sysreg
+++ b/arch/arm64/tools/sysreg
@@ -1002,6 +1002,27 @@ UnsignedEnum	3:0	BT
 EndEnum
 EndSysreg
 
+Sysreg	ID_AA64PFR2_EL1	3	0	0	4	2
+Res0	63:36
+UnsignedEnum	35:32	FPMR
+	0b0000	NI
+	0b0001	IMP
+EndEnum
+Res0	31:12
+UnsignedEnum	11:8	MTEFAR
+	0b0000	NI
+	0b0001	IMP
+EndEnum
+UnsignedEnum	7:4	MTESTOREONLY
+	0b0000	NI
+	0b0001	IMP
+EndEnum
+UnsignedEnum	3:0	MTEPERM
+	0b0000	NI
+	0b0001	IMP
+EndEnum
+EndSysreg
+
 Sysreg	ID_AA64ZFR0_EL1	3	0	0	4	4
 Res0	63:60
 UnsignedEnum	59:56	F64MM
@@ -1058,7 +1079,11 @@ UnsignedEnum	63	FA64
 	0b0	NI
 	0b1	IMP
 EndEnum
-Res0	62:60
+Res0	62:61
+UnsignedEnum	60	LUTv2
+	0b0	NI
+	0b1	IMP
+EndEnum
 UnsignedEnum	59:56	SMEver
 	0b0000	SME
 	0b0001	SME2
@@ -1086,7 +1111,14 @@ UnsignedEnum	42	F16F16
 	0b0	NI
 	0b1	IMP
 EndEnum
-Res0	41:40
+UnsignedEnum	41	F8F16
+	0b0	NI
+	0b1	IMP
+EndEnum
+UnsignedEnum	40	F8F32
+	0b0	NI
+	0b1	IMP
+EndEnum
 UnsignedEnum	39:36	I8I32
 	0b0000	NI
 	0b1111	IMP
@@ -1107,7 +1139,49 @@ UnsignedEnum	32	F32F32
 	0b0	NI
 	0b1	IMP
 EndEnum
-Res0	31:0
+Res0	31
+UnsignedEnum	30	SF8FMA
+	0b0	NI
+	0b1	IMP
+EndEnum
+UnsignedEnum	29	SF8DP4
+	0b0	NI
+	0b1	IMP
+EndEnum
+UnsignedEnum	28	SF8DP2
+	0b0	NI
+	0b1	IMP
+EndEnum
+Res0	27:0
+EndSysreg
+
+Sysreg	ID_AA64FPFR0_EL1	3	0	0	4	7
+Res0	63:32
+UnsignedEnum	31	F8CVT
+	0b0	NI
+	0b1	IMP
+EndEnum
+UnsignedEnum	30	F8FMA
+	0b0	NI
+	0b1	IMP
+EndEnum
+UnsignedEnum	29	F8DP4
+	0b0	NI
+	0b1	IMP
+EndEnum
+UnsignedEnum	28	F8DP2
+	0b0	NI
+	0b1	IMP
+EndEnum
+Res0	27:2
+UnsignedEnum	1	F8E4M3
+	0b0	NI
+	0b1	IMP
+EndEnum
+UnsignedEnum	0	F8E5M2
+	0b0	NI
+	0b1	IMP
+EndEnum
 EndSysreg
 
 Sysreg	ID_AA64DFR0_EL1	3	0	0	5	0
@@ -1115,7 +1189,10 @@ Enum	63:60	HPMN0
 	0b0000	UNPREDICTABLE
 	0b0001	DEF
 EndEnum
-Res0	59:56
+UnsignedEnum	59:56	ExtTrcBuff
+	0b0000	NI
+	0b0001	IMP
+EndEnum
 UnsignedEnum	55:52	BRBE
 	0b0000	NI
 	0b0001	IMP
@@ -1327,6 +1404,7 @@ UnsignedEnum	11:8	API
 	0b0011	PAuth2
 	0b0100	FPAC
 	0b0101	FPACCOMBINE
+	0b0110	PAuth_LR
 EndEnum
 UnsignedEnum	7:4	APA
 	0b0000	NI
@@ -1335,6 +1413,7 @@ UnsignedEnum	7:4	APA
 	0b0011	PAuth2
 	0b0100	FPAC
 	0b0101	FPACCOMBINE
+	0b0110	PAuth_LR
 EndEnum
 UnsignedEnum	3:0	DPB
 	0b0000	NI
@@ -1344,7 +1423,14 @@ EndEnum
 EndSysreg
 
 Sysreg	ID_AA64ISAR2_EL1	3	0	0	6	2
-Res0	63:56
+UnsignedEnum	63:60	ATS1A
+	0b0000	NI
+	0b0001	IMP
+EndEnum
+UnsignedEnum	59:56	LUT
+	0b0000	NI
+	0b0001	IMP
+EndEnum
 UnsignedEnum	55:52	CSSC
 	0b0000	NI
 	0b0001	IMP
@@ -1353,7 +1439,19 @@ UnsignedEnum	51:48	RPRFM
 	0b0000	NI
 	0b0001	IMP
 EndEnum
-Res0	47:32
+Res0	47:44
+UnsignedEnum	43:40	PRFMSLC
+	0b0000	NI
+	0b0001	IMP
+EndEnum
+UnsignedEnum	39:36	SYSINSTR_128
+	0b0000	NI
+	0b0001	IMP
+EndEnum
+UnsignedEnum	35:32	SYSREG_128
+	0b0000	NI
+	0b0001	IMP
+EndEnum
 UnsignedEnum	31:28	CLRBHB
 	0b0000	NI
 	0b0001	IMP
@@ -1377,6 +1475,7 @@ UnsignedEnum	15:12	APA3
 	0b0011	PAuth2
 	0b0100	FPAC
 	0b0101	FPACCOMBINE
+	0b0110	PAuth_LR
 EndEnum
 UnsignedEnum	11:8	GPA3
 	0b0000	NI
@@ -1392,6 +1491,23 @@ UnsignedEnum	3:0	WFxT
 EndEnum
 EndSysreg
 
+Sysreg	ID_AA64ISAR3_EL1	3	0	0	6	3
+Res0	63:12
+UnsignedEnum	11:8	TLBIW
+	0b0000	NI
+	0b0001	IMP
+EndEnum
+UnsignedEnum	7:4	FAMINMAX
+	0b0000	NI
+	0b0001	IMP
+EndEnum
+UnsignedEnum	3:0	CPA
+	0b0000	NI
+	0b0001	IMP
+	0b0010	CPA2
+EndEnum
+EndSysreg
+
 Sysreg	ID_AA64MMFR0_EL1	3	0	0	7	0
 UnsignedEnum	63:60	ECV
 	0b0000	NI
@@ -1680,7 +1796,8 @@ Field	63	TIDCP
 Field	62	SPINTMASK
 Field	61	NMI
 Field	60	EnTP2
-Res0	59:58
+Field	59	TCSO
+Field	58	TCSO0
 Field	57	EPAN
 Field	56	EnALS
 Field	55	EnAS0
@@ -1709,7 +1826,7 @@ EndEnum
 Field	37	ITFSB
 Field	36	BT1
 Field	35	BT0
-Res0	34
+Field	34	EnFPM
 Field	33	MSCEn
 Field	32	CMOW
 Field	31	EnIA
@@ -1747,7 +1864,8 @@ Field	0	M
 EndSysreg
 
 SysregFields	CPACR_ELx
-Res0	63:29
+Res0	63:30
+Field	29	E0POE
 Field	28	TTA
 Res0	27:26
 Field	25:24	SMEN
@@ -1790,6 +1908,41 @@ Sysreg	SMCR_EL1	3	0	1	2	6
 Fields	SMCR_ELx
 EndSysreg
 
+SysregFields	GCSCR_ELx
+Res0	63:10
+Field	9	STREn
+Field	8	PUSHMEn
+Res0	7
+Field	6	EXLOCKEN
+Field	5	RVCHKEN
+Res0	4:1
+Field	0	PCRSEL
+EndSysregFields
+
+Sysreg	GCSCR_EL1	3	0	2	5	0
+Fields	GCSCR_ELx
+EndSysreg
+
+SysregFields	GCSPR_ELx
+Field	63:3	PTR
+Res0	2:0
+EndSysregFields
+
+Sysreg	GCSPR_EL1	3	0	2	5	1
+Fields	GCSPR_ELx
+EndSysreg
+
+Sysreg	GCSCRE0_EL1	3	0	2	5	2
+Res0	63:11
+Field	10	nTR
+Field	9	STREn
+Field	8	PUSHMEn
+Res0	7:6
+Field	5	RVCHKEN
+Res0	4:1
+Field	0	PCRSEL
+EndSysreg
+
 Sysreg	ALLINT	3	0	4	3	0
 Res0	63:14
 Field	13	ALLINT
@@ -1933,10 +2086,18 @@ Sysreg	CONTEXTIDR_EL1	3	0	13	0	1
 Fields	CONTEXTIDR_ELx
 EndSysreg
 
+Sysreg	RCWSMASK_EL1	3	0	13	0	3
+Field	63:0	RCWSMASK
+EndSysreg
+
 Sysreg	TPIDR_EL1	3	0	13	0	4
 Field	63:0	ThreadID
 EndSysreg
 
+Sysreg	RCWMASK_EL1	3	0	13	0	6
+Field	63:0	RCWMASK
+EndSysreg
+
 Sysreg	SCXTNUM_EL1	3	0	13	0	7
 Field	63:0	SoftwareContextNumber
 EndSysreg
@@ -2004,9 +2165,10 @@ Field	27:24	CWG
 Field	23:20	ERG
 Field	19:16	DminLine
 Enum	15:14	L1Ip
-	0b00	VPIPT
+	# This was named as VPIPT in the ARM but now documented as reserved
+	0b00	RESERVED_VPIPT
 	# This is named as AIVIVT in the ARM but documented as reserved
-	0b01	RESERVED
+	0b01	RESERVED_AIVIVT
 	0b10	VIPT
 	0b11	PIPT
 EndEnum
@@ -2020,12 +2182,39 @@ Field	4	DZP
 Field	3:0	BS
 EndSysreg
 
+Sysreg	GCSPR_EL0	3	3	2	5	1
+Fields	GCSPR_ELx
+EndSysreg
+
 Sysreg	SVCR	3	3	4	2	2
 Res0	63:2
 Field	1	ZA
 Field	0	SM
 EndSysreg
 
+Sysreg	FPMR	3	3	4	4	2
+Res0	63:38
+Field	37:32	LSCALE2
+Field	31:24	NSCALE
+Res0	23
+Field	22:16	LSCALE
+Field	15	OSC
+Field	14	OSM
+Res0	13:9
+UnsignedEnum	8:6	F8D
+	0b000	E5M2
+	0b001	E4M3
+EndEnum
+UnsignedEnum	5:3	F8S2
+	0b000	E5M2
+	0b001	E4M3
+EndEnum
+UnsignedEnum	2:0	F8S1
+	0b000	E5M2
+	0b001	E4M3
+EndEnum
+EndSysreg
+
 SysregFields	HFGxTR_EL2
 Field	63	nAMAIR2_EL1
 Field	62	nMAIR2_EL1
@@ -2102,7 +2291,9 @@ Fields	HFGxTR_EL2
 EndSysreg
 
 Sysreg HFGITR_EL2	3	4	1	1	6
-Res0	63:61
+Res0	63
+Field	62	ATS1E1A
+Res0	61
 Field	60	COSPRCTX
 Field	59	nGCSEPP
 Field	58	nGCSSTR_EL1
@@ -2295,12 +2486,57 @@ Field	1	DBGBVRn_EL1
 Field	0	DBGBCRn_EL1
 EndSysreg
 
+Sysreg HAFGRTR_EL2	3	4	3	1	6
+Res0	63:50
+Field	49	AMEVTYPER115_EL0
+Field	48	AMEVCNTR115_EL0
+Field	47	AMEVTYPER114_EL0
+Field	46	AMEVCNTR114_EL0
+Field	45	AMEVTYPER113_EL0
+Field	44	AMEVCNTR113_EL0
+Field	43	AMEVTYPER112_EL0
+Field	42	AMEVCNTR112_EL0
+Field	41	AMEVTYPER111_EL0
+Field	40	AMEVCNTR111_EL0
+Field	39	AMEVTYPER110_EL0
+Field	38	AMEVCNTR110_EL0
+Field	37	AMEVTYPER19_EL0
+Field	36	AMEVCNTR19_EL0
+Field	35	AMEVTYPER18_EL0
+Field	34	AMEVCNTR18_EL0
+Field	33	AMEVTYPER17_EL0
+Field	32	AMEVCNTR17_EL0
+Field	31	AMEVTYPER16_EL0
+Field	30	AMEVCNTR16_EL0
+Field	29	AMEVTYPER15_EL0
+Field	28	AMEVCNTR15_EL0
+Field	27	AMEVTYPER14_EL0
+Field	26	AMEVCNTR14_EL0
+Field	25	AMEVTYPER13_EL0
+Field	24	AMEVCNTR13_EL0
+Field	23	AMEVTYPER12_EL0
+Field	22	AMEVCNTR12_EL0
+Field	21	AMEVTYPER11_EL0
+Field	20	AMEVCNTR11_EL0
+Field	19	AMEVTYPER10_EL0
+Field	18	AMEVCNTR10_EL0
+Field	17	AMCNTEN1
+Res0	16:5
+Field	4	AMEVCNTR03_EL0
+Field	3	AMEVCNTR02_EL0
+Field	2	AMEVCNTR01_EL0
+Field	1	AMEVCNTR00_EL0
+Field	0	AMCNTEN0
+EndSysreg
+
 Sysreg	ZCR_EL2	3	4	1	2	0
 Fields	ZCR_ELx
 EndSysreg
 
 Sysreg	HCRX_EL2	3	4	1	2	2
-Res0	63:23
+Res0	63:25
+Field	24	PACMEn
+Field	23	EnFPM
 Field	22	GCSEn
 Field	21	EnIDCP128
 Field	20	EnSDERR
@@ -2348,6 +2584,14 @@ Sysreg	SMCR_EL2	3	4	1	2	6
 Fields	SMCR_ELx
 EndSysreg
 
+Sysreg	GCSCR_EL2	3	4	2	5	0
+Fields	GCSCR_ELx
+EndSysreg
+
+Sysreg	GCSPR_EL2	3	4	2	5	1
+Fields	GCSPR_ELx
+EndSysreg
+
 Sysreg	DACR32_EL2	3	4	3	0	0
 Res0	63:32
 Field	31:30	D15
@@ -2407,6 +2651,14 @@ Sysreg	SMCR_EL12	3	5	1	2	6
 Fields	SMCR_ELx
 EndSysreg
 
+Sysreg	GCSCR_EL12	3	5	2	5	0
+Fields	GCSCR_ELx
+EndSysreg
+
+Sysreg	GCSPR_EL12	3	5	2	5	1
+Fields	GCSPR_ELx
+EndSysreg
+
 Sysreg	FAR_EL12	3	5	6	0	0
 Field	63:0	ADDR
 EndSysreg
@@ -2471,6 +2723,33 @@ Field	1	PIE
 Field	0	PnCH
 EndSysreg
 
+SysregFields MAIR2_ELx
+Field	63:56	Attr7
+Field	55:48	Attr6
+Field	47:40	Attr5
+Field	39:32	Attr4
+Field	31:24	Attr3
+Field	23:16	Attr2
+Field	15:8	Attr1
+Field	7:0	Attr0
+EndSysregFields
+
+Sysreg	MAIR2_EL1	3	0	10	2	1
+Fields	MAIR2_ELx
+EndSysreg
+
+Sysreg	MAIR2_EL2	3	4	10	1	1
+Fields	MAIR2_ELx
+EndSysreg
+
+Sysreg	AMAIR2_EL1	3	0	10	3	1
+Field	63:0	ImpDef
+EndSysreg
+
+Sysreg	AMAIR2_EL2	3	4	10	3	1
+Field	63:0	ImpDef
+EndSysreg
+
 SysregFields PIRx_ELx
 Field	63:60	Perm15
 Field	59:56	Perm14
@@ -2510,6 +2789,26 @@ Sysreg	PIR_EL2		3	4	10	2	3
 Fields	PIRx_ELx
 EndSysreg
 
+Sysreg	POR_EL0		3	3	10	2	4
+Fields	PIRx_ELx
+EndSysreg
+
+Sysreg	POR_EL1		3	0	10	2	4
+Fields	PIRx_ELx
+EndSysreg
+
+Sysreg	POR_EL12	3	5	10	2	4
+Fields	PIRx_ELx
+EndSysreg
+
+Sysreg	S2POR_EL1	3	0	10	2	5
+Fields	PIRx_ELx
+EndSysreg
+
+Sysreg	S2PIR_EL2	3	4	10	2	5
+Fields	PIRx_ELx
+EndSysreg
+
 Sysreg	LORSA_EL1	3	0	10	4	0
 Res0	63:52
 Field	51:16	SA
diff --git a/arch/csky/include/asm/ftrace.h b/arch/csky/include/asm/ftrace.h
index 9b86341731b6..fd215c38ef27 100644
--- a/arch/csky/include/asm/ftrace.h
+++ b/arch/csky/include/asm/ftrace.h
@@ -26,5 +26,9 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 
 struct dyn_arch_ftrace {
 };
+
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+			   unsigned long frame_pointer);
+
 #endif /* !__ASSEMBLY__ */
 #endif /* __ASM_CSKY_FTRACE_H */
diff --git a/arch/csky/include/asm/irq_work.h b/arch/csky/include/asm/irq_work.h
index 33aaf39d6f94..d39fcc1f5395 100644
--- a/arch/csky/include/asm/irq_work.h
+++ b/arch/csky/include/asm/irq_work.h
@@ -7,5 +7,5 @@ static inline bool arch_irq_work_has_interrupt(void)
 {
 	return true;
 }
-extern void arch_irq_work_raise(void);
+
 #endif /* __ASM_CSKY_IRQ_WORK_H */
diff --git a/arch/csky/include/asm/jump_label.h b/arch/csky/include/asm/jump_label.h
index d488ba6084bc..98a3f4b168bd 100644
--- a/arch/csky/include/asm/jump_label.h
+++ b/arch/csky/include/asm/jump_label.h
@@ -43,5 +43,10 @@ label:
 	return true;
 }
 
+enum jump_label_type;
+void arch_jump_label_transform_static(struct jump_entry *entry,
+				      enum jump_label_type type);
+#define arch_jump_label_transform_static arch_jump_label_transform_static
+
 #endif  /* __ASSEMBLY__ */
 #endif	/* __ASM_CSKY_JUMP_LABEL_H */
diff --git a/arch/csky/include/asm/traps.h b/arch/csky/include/asm/traps.h
index 732c4aaa2e26..6bbbbe43165f 100644
--- a/arch/csky/include/asm/traps.h
+++ b/arch/csky/include/asm/traps.h
@@ -55,6 +55,6 @@ asmlinkage void trap_c(struct pt_regs *regs);
 asmlinkage void do_notify_resume(struct pt_regs *regs,
 			unsigned long thread_info_flags);
 
-void trap_init(void);
+asmlinkage void do_page_fault(struct pt_regs *regs);
 
 #endif /* __ASM_CSKY_TRAPS_H */
diff --git a/arch/csky/kernel/traps.c b/arch/csky/kernel/traps.c
index 6e426fba0119..c2246b07cc9c 100644
--- a/arch/csky/kernel/traps.c
+++ b/arch/csky/kernel/traps.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
 
+#include <linux/cpu.h>
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/kernel.h>
diff --git a/arch/csky/kernel/vdso/vgettimeofday.c b/arch/csky/kernel/vdso/vgettimeofday.c
index c4831145eed5..55af30e83752 100644
--- a/arch/csky/kernel/vdso/vgettimeofday.c
+++ b/arch/csky/kernel/vdso/vgettimeofday.c
@@ -2,36 +2,27 @@
 
 #include <linux/time.h>
 #include <linux/types.h>
+#include <vdso/gettime.h>
 
 extern
 int __vdso_clock_gettime(clockid_t clock,
-			 struct old_timespec32 *ts);
-int __vdso_clock_gettime(clockid_t clock,
 			 struct old_timespec32 *ts)
 {
 	return __cvdso_clock_gettime32(clock, ts);
 }
 
 int __vdso_clock_gettime64(clockid_t clock,
-			   struct __kernel_timespec *ts);
-int __vdso_clock_gettime64(clockid_t clock,
 			   struct __kernel_timespec *ts)
 {
 	return __cvdso_clock_gettime(clock, ts);
 }
 
-extern
-int __vdso_gettimeofday(struct __kernel_old_timeval *tv,
-			struct timezone *tz);
 int __vdso_gettimeofday(struct __kernel_old_timeval *tv,
 			struct timezone *tz)
 {
 	return __cvdso_gettimeofday(tv, tz);
 }
 
-extern
-int __vdso_clock_getres(clockid_t clock_id,
-			struct old_timespec32 *res);
 int __vdso_clock_getres(clockid_t clock_id,
 			struct old_timespec32 *res)
 {
diff --git a/arch/hexagon/include/asm/io.h b/arch/hexagon/include/asm/io.h
index e2b308e32a37..522d321ea85a 100644
--- a/arch/hexagon/include/asm/io.h
+++ b/arch/hexagon/include/asm/io.h
@@ -59,12 +59,6 @@ static inline void *phys_to_virt(unsigned long address)
 }
 
 /*
- * convert a physical pointer to a virtual kernel pointer for
- * /dev/mem access.
- */
-#define xlate_dev_mem_ptr(p)    __va(p)
-
-/*
  * IO port access primitives.  Hexagon doesn't have special IO access
  * instructions; all I/O is memory mapped.
  *
@@ -174,9 +168,6 @@ static inline void writel(u32 data, volatile void __iomem *addr)
 #define _PAGE_IOREMAP (_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
 		       (__HEXAGON_C_DEV << 6))
 
-#define ioremap_uc(addr, size) ioremap((addr), (size))
-
-
 #define __raw_writel writel
 
 static inline void memcpy_fromio(void *dst, const volatile void __iomem *src,
diff --git a/arch/hexagon/include/asm/irq.h b/arch/hexagon/include/asm/irq.h
index 1f7f1292f701..a60d26754caa 100644
--- a/arch/hexagon/include/asm/irq.h
+++ b/arch/hexagon/include/asm/irq.h
@@ -20,4 +20,7 @@
 
 #include <asm-generic/irq.h>
 
+struct pt_regs;
+void arch_do_IRQ(struct pt_regs *);
+
 #endif
diff --git a/arch/hexagon/include/asm/page.h b/arch/hexagon/include/asm/page.h
index 9c03b9965f07..10f1bc07423c 100644
--- a/arch/hexagon/include/asm/page.h
+++ b/arch/hexagon/include/asm/page.h
@@ -78,6 +78,9 @@ typedef struct page *pgtable_t;
 #define __pgd(x)       ((pgd_t) { (x) })
 #define __pgprot(x)    ((pgprot_t) { (x) })
 
+/* Needed for PAGE_OFFSET used in the macro right below */
+#include <asm/mem-layout.h>
+
 /*
  * We need a __pa and a __va routine for kernel space.
  * MIPS says they're only used during mem_init.
@@ -125,8 +128,16 @@ static inline void clear_page(void *page)
  */
 #define page_to_phys(page)      (page_to_pfn(page) << PAGE_SHIFT)
 
-#define virt_to_pfn(kaddr)      (__pa(kaddr) >> PAGE_SHIFT)
-#define pfn_to_virt(pfn)        __va((pfn) << PAGE_SHIFT)
+static inline unsigned long virt_to_pfn(const void *kaddr)
+{
+	return __pa(kaddr) >> PAGE_SHIFT;
+}
+
+static inline void *pfn_to_virt(unsigned long pfn)
+{
+	return (void *)((unsigned long)__va(pfn) << PAGE_SHIFT);
+}
+
 
 #define page_to_virt(page)	__va(page_to_phys(page))
 
diff --git a/arch/hexagon/include/uapi/asm/user.h b/arch/hexagon/include/uapi/asm/user.h
index 7327ec59b22f..abae6a4b5813 100644
--- a/arch/hexagon/include/uapi/asm/user.h
+++ b/arch/hexagon/include/uapi/asm/user.h
@@ -56,15 +56,10 @@ struct user_regs_struct {
 	unsigned long pc;
 	unsigned long cause;
 	unsigned long badva;
-#if CONFIG_HEXAGON_ARCH_VERSION < 4
-	unsigned long pad1;  /* pad out to 48 words total */
-	unsigned long pad2;  /* pad out to 48 words total */
-	unsigned long pad3;  /* pad out to 48 words total */
-#else
+	/* cs0 and cs1 are only available with HEXAGON_ARCH_VERSION >= 4 */
 	unsigned long cs0;
 	unsigned long cs1;
 	unsigned long pad1;  /* pad out to 48 words total */
-#endif
 };
 
 #endif
diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c
index dd7f74ea2c20..2a77bfd75694 100644
--- a/arch/hexagon/kernel/process.c
+++ b/arch/hexagon/kernel/process.c
@@ -5,6 +5,7 @@
  * Copyright (c) 2010-2012, The Linux Foundation. All rights reserved.
  */
 
+#include <linux/cpu.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
@@ -152,6 +153,7 @@ unsigned long __get_wchan(struct task_struct *p)
  * Returns 0 if there's no need to re-check for more work.
  */
 
+int do_work_pending(struct pt_regs *regs, u32 thread_info_flags);
 int do_work_pending(struct pt_regs *regs, u32 thread_info_flags)
 {
 	if (!(thread_info_flags & _TIF_WORK_MASK)) {
diff --git a/arch/hexagon/kernel/ptrace.c b/arch/hexagon/kernel/ptrace.c
index 125f19995b76..905b06790ab7 100644
--- a/arch/hexagon/kernel/ptrace.c
+++ b/arch/hexagon/kernel/ptrace.c
@@ -74,7 +74,7 @@ static int genregs_set(struct task_struct *target,
 		   unsigned int pos, unsigned int count,
 		   const void *kbuf, const void __user *ubuf)
 {
-	int ret;
+	int ret, ignore_offset;
 	unsigned long bucket;
 	struct pt_regs *regs = task_pt_regs(target);
 
@@ -111,12 +111,15 @@ static int genregs_set(struct task_struct *target,
 #if CONFIG_HEXAGON_ARCH_VERSION >=4
 	INEXT(&regs->cs0, cs0);
 	INEXT(&regs->cs1, cs1);
+	ignore_offset = offsetof(struct user_regs_struct, pad1);
+#else
+	ignore_offset = offsetof(struct user_regs_struct, cs0);
 #endif
 
 	/* Ignore the rest, if needed */
 	if (!ret)
 		user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
-			offsetof(struct user_regs_struct, pad1), -1);
+					  ignore_offset, -1);
 	else
 		return ret;
 
diff --git a/arch/hexagon/kernel/reset.c b/arch/hexagon/kernel/reset.c
index da36114d928f..efd70a8d2526 100644
--- a/arch/hexagon/kernel/reset.c
+++ b/arch/hexagon/kernel/reset.c
@@ -3,6 +3,7 @@
  * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
  */
 
+#include <linux/reboot.h>
 #include <linux/smp.h>
 #include <asm/hexagon_vm.h>
 
diff --git a/arch/hexagon/kernel/signal.c b/arch/hexagon/kernel/signal.c
index bcba31e9e0ae..d301f4621553 100644
--- a/arch/hexagon/kernel/signal.c
+++ b/arch/hexagon/kernel/signal.c
@@ -220,7 +220,7 @@ no_restart:
  * Architecture-specific wrappers for signal-related system calls
  */
 
-asmlinkage int sys_rt_sigreturn(void)
+SYSCALL_DEFINE0(rt_sigreturn)
 {
 	struct pt_regs *regs = current_pt_regs();
 	struct rt_sigframe __user *frame;
diff --git a/arch/hexagon/kernel/smp.c b/arch/hexagon/kernel/smp.c
index 4e8bee25b8c6..608884bc3396 100644
--- a/arch/hexagon/kernel/smp.c
+++ b/arch/hexagon/kernel/smp.c
@@ -79,7 +79,7 @@ void smp_vm_unmask_irq(void *info)
  * Specifically, first arg is irq, second is the irq_desc.
  */
 
-irqreturn_t handle_ipi(int irq, void *desc)
+static irqreturn_t handle_ipi(int irq, void *desc)
 {
 	int cpu = smp_processor_id();
 	struct ipi_data *ipi = &per_cpu(ipi_data, cpu);
@@ -124,7 +124,7 @@ void __init smp_prepare_boot_cpu(void)
  * to point to current thread info
  */
 
-void start_secondary(void)
+static void start_secondary(void)
 {
 	unsigned long thread_ptr;
 	unsigned int cpu, irq;
diff --git a/arch/hexagon/kernel/time.c b/arch/hexagon/kernel/time.c
index febc95714d75..f0f207e2a694 100644
--- a/arch/hexagon/kernel/time.c
+++ b/arch/hexagon/kernel/time.c
@@ -17,7 +17,9 @@
 #include <linux/of_irq.h>
 #include <linux/module.h>
 
+#include <asm/delay.h>
 #include <asm/hexagon_vm.h>
+#include <asm/time.h>
 
 #define TIMER_ENABLE		BIT(0)
 
@@ -160,7 +162,7 @@ static irqreturn_t timer_interrupt(int irq, void *devid)
  * This runs just before the delay loop is calibrated, and
  * is used for delay calibration.
  */
-void __init time_init_deferred(void)
+static void __init time_init_deferred(void)
 {
 	struct resource *resource = NULL;
 	struct clock_event_device *ce_dev = &hexagon_clockevent_dev;
diff --git a/arch/hexagon/kernel/traps.c b/arch/hexagon/kernel/traps.c
index 6447763ce5a9..75e062722d28 100644
--- a/arch/hexagon/kernel/traps.c
+++ b/arch/hexagon/kernel/traps.c
@@ -281,6 +281,7 @@ static void cache_error(struct pt_regs *regs)
 /*
  * General exception handler
  */
+void do_genex(struct pt_regs *regs);
 void do_genex(struct pt_regs *regs)
 {
 	/*
@@ -331,13 +332,7 @@ void do_genex(struct pt_regs *regs)
 	}
 }
 
-/* Indirect system call dispatch */
-long sys_syscall(void)
-{
-	printk(KERN_ERR "sys_syscall invoked!\n");
-	return -ENOSYS;
-}
-
+void do_trap0(struct pt_regs *regs);
 void do_trap0(struct pt_regs *regs)
 {
 	syscall_fn syscall;
@@ -415,6 +410,7 @@ void do_trap0(struct pt_regs *regs)
 /*
  * Machine check exception handler
  */
+void do_machcheck(struct pt_regs *regs);
 void do_machcheck(struct pt_regs *regs)
 {
 	/* Halt and catch fire */
@@ -425,6 +421,7 @@ void do_machcheck(struct pt_regs *regs)
  * Treat this like the old 0xdb trap.
  */
 
+void do_debug_exception(struct pt_regs *regs);
 void do_debug_exception(struct pt_regs *regs)
 {
 	regs->hvmer.vmest &= ~HVM_VMEST_CAUSE_MSK;
diff --git a/arch/hexagon/kernel/vdso.c b/arch/hexagon/kernel/vdso.c
index b70970ac809f..2e4872d62124 100644
--- a/arch/hexagon/kernel/vdso.c
+++ b/arch/hexagon/kernel/vdso.c
@@ -10,6 +10,7 @@
 #include <linux/vmalloc.h>
 #include <linux/binfmts.h>
 
+#include <asm/elf.h>
 #include <asm/vdso.h>
 
 static struct page *vdso_page;
diff --git a/arch/hexagon/kernel/vm_events.c b/arch/hexagon/kernel/vm_events.c
index 59ef72e4a4e5..2b881a89b206 100644
--- a/arch/hexagon/kernel/vm_events.c
+++ b/arch/hexagon/kernel/vm_events.c
@@ -73,13 +73,6 @@ void show_regs(struct pt_regs *regs)
 		pt_psp(regs), pt_badva(regs), ints_enabled(regs));
 }
 
-void dummy_handler(struct pt_regs *regs)
-{
-	unsigned int elr = pt_elr(regs);
-	printk(KERN_ERR "Unimplemented handler; ELR=0x%08x\n", elr);
-}
-
-
 void arch_do_IRQ(struct pt_regs *regs)
 {
 	int irq = pt_cause(regs);
diff --git a/arch/hexagon/mm/init.c b/arch/hexagon/mm/init.c
index 146115c9de61..3458f39ca2ac 100644
--- a/arch/hexagon/mm/init.c
+++ b/arch/hexagon/mm/init.c
@@ -12,6 +12,7 @@
 #include <linux/highmem.h>
 #include <asm/tlb.h>
 #include <asm/sections.h>
+#include <asm/setup.h>
 #include <asm/vm_mmu.h>
 
 /*
@@ -86,7 +87,7 @@ void sync_icache_dcache(pte_t pte)
  * In this mode, we only have one pg_data_t
  * structure: contig_mem_data.
  */
-void __init paging_init(void)
+static void __init paging_init(void)
 {
 	unsigned long max_zone_pfn[MAX_NR_ZONES] = {0, };
 
diff --git a/arch/hexagon/mm/uaccess.c b/arch/hexagon/mm/uaccess.c
index 650bca92f0b7..3204e9ba6d6f 100644
--- a/arch/hexagon/mm/uaccess.c
+++ b/arch/hexagon/mm/uaccess.c
@@ -35,11 +35,3 @@ __kernel_size_t __clear_user_hexagon(void __user *dest, unsigned long count)
 
 	return count;
 }
-
-unsigned long clear_user_hexagon(void __user *dest, unsigned long count)
-{
-	if (!access_ok(dest, count))
-		return count;
-	else
-		return __clear_user_hexagon(dest, count);
-}
diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c
index 7295ea3f8cc8..3771fb453898 100644
--- a/arch/hexagon/mm/vm_fault.c
+++ b/arch/hexagon/mm/vm_fault.c
@@ -12,6 +12,7 @@
  */
 
 #include <asm/traps.h>
+#include <asm/vm_fault.h>
 #include <linux/uaccess.h>
 #include <linux/mm.h>
 #include <linux/sched/signal.h>
@@ -33,7 +34,7 @@
 /*
  * Canonical page fault handler
  */
-void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
+static void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
 {
 	struct vm_area_struct *vma;
 	struct mm_struct *mm = current->mm;
diff --git a/arch/hexagon/mm/vm_tlb.c b/arch/hexagon/mm/vm_tlb.c
index 53482f2a9ff9..8b6405e2234b 100644
--- a/arch/hexagon/mm/vm_tlb.c
+++ b/arch/hexagon/mm/vm_tlb.c
@@ -14,6 +14,7 @@
 #include <linux/sched.h>
 #include <asm/page.h>
 #include <asm/hexagon_vm.h>
+#include <asm/tlbflush.h>
 
 /*
  * Initial VM implementation has only one map active at a time, with
diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile
index 9eeb0c05f3f4..4ba8d67ddb09 100644
--- a/arch/loongarch/Makefile
+++ b/arch/loongarch/Makefile
@@ -68,6 +68,7 @@ LDFLAGS_vmlinux			+= -static -n -nostdlib
 ifdef CONFIG_AS_HAS_EXPLICIT_RELOCS
 cflags-y			+= $(call cc-option,-mexplicit-relocs)
 KBUILD_CFLAGS_KERNEL		+= $(call cc-option,-mdirect-extern-access)
+KBUILD_CFLAGS_KERNEL		+= $(call cc-option,-fdirect-access-external-data)
 KBUILD_AFLAGS_MODULE		+= $(call cc-option,-fno-direct-access-external-data)
 KBUILD_CFLAGS_MODULE		+= $(call cc-option,-fno-direct-access-external-data)
 KBUILD_AFLAGS_MODULE		+= $(call cc-option,-mno-relax) $(call cc-option,-Wa$(comma)-mno-relax)
@@ -82,7 +83,7 @@ endif
 
 ifeq ($(CONFIG_RELOCATABLE),y)
 KBUILD_CFLAGS_KERNEL		+= -fPIE
-LDFLAGS_vmlinux			+= -static -pie --no-dynamic-linker -z notext
+LDFLAGS_vmlinux			+= -static -pie --no-dynamic-linker -z notext $(call ld-option, --apply-dynamic-relocs)
 endif
 
 cflags-y += $(call cc-option, -mno-check-zero-division)
@@ -142,6 +143,8 @@ vdso-install-y += arch/loongarch/vdso/vdso.so.dbg
 
 all:	$(notdir $(KBUILD_IMAGE))
 
+vmlinuz.efi: vmlinux.efi
+
 vmlinux.elf vmlinux.efi vmlinuz.efi: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(bootvars-y) $(boot)/$@
 
diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig
index 33795e4a5bd6..60e331af9839 100644
--- a/arch/loongarch/configs/loongson3_defconfig
+++ b/arch/loongarch/configs/loongson3_defconfig
@@ -276,7 +276,6 @@ CONFIG_BRIDGE_EBT_T_NAT=m
 CONFIG_BRIDGE_EBT_ARP=m
 CONFIG_BRIDGE_EBT_IP=m
 CONFIG_BRIDGE_EBT_IP6=m
-CONFIG_BPFILTER=y
 CONFIG_IP_SCTP=m
 CONFIG_RDS=y
 CONFIG_L2TP=m
@@ -304,7 +303,6 @@ CONFIG_NET_CLS_ACT=y
 CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
 CONFIG_NET_ACT_MIRRED=m
-CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_BPF=m
 CONFIG_OPENVSWITCH=m
diff --git a/arch/loongarch/include/asm/asmmacro.h b/arch/loongarch/include/asm/asmmacro.h
index c9544f358c33..655db7d7a427 100644
--- a/arch/loongarch/include/asm/asmmacro.h
+++ b/arch/loongarch/include/asm/asmmacro.h
@@ -609,8 +609,7 @@
 	lu32i.d	\reg, 0
 	lu52i.d	\reg, \reg, 0
 	.pushsection ".la_abs", "aw", %progbits
-	768:
-	.dword	768b-766b
+	.dword	766b
 	.dword	\sym
 	.popsection
 #endif
diff --git a/arch/loongarch/include/asm/efi.h b/arch/loongarch/include/asm/efi.h
index 091897d40b03..eddc8e79b3fa 100644
--- a/arch/loongarch/include/asm/efi.h
+++ b/arch/loongarch/include/asm/efi.h
@@ -32,6 +32,4 @@ static inline unsigned long efi_get_kimg_min_align(void)
 
 #define EFI_KIMG_PREFERRED_ADDRESS	PHYSADDR(VMLINUX_LOAD_ADDRESS)
 
-unsigned long kernel_entry_address(void);
-
 #endif /* _ASM_LOONGARCH_EFI_H */
diff --git a/arch/loongarch/include/asm/elf.h b/arch/loongarch/include/asm/elf.h
index b9a4ab54285c..9b16a3b8e706 100644
--- a/arch/loongarch/include/asm/elf.h
+++ b/arch/loongarch/include/asm/elf.h
@@ -293,7 +293,7 @@ extern const char *__elf_platform;
 #define ELF_PLAT_INIT(_r, load_addr)	do { \
 	_r->regs[1] = _r->regs[2] = _r->regs[3] = _r->regs[4] = 0;	\
 	_r->regs[5] = _r->regs[6] = _r->regs[7] = _r->regs[8] = 0;	\
-	_r->regs[9] = _r->regs[10] = _r->regs[11] = _r->regs[12] = 0;	\
+	_r->regs[9] = _r->regs[10] /* syscall n */ = _r->regs[12] = 0;	\
 	_r->regs[13] = _r->regs[14] = _r->regs[15] = _r->regs[16] = 0;	\
 	_r->regs[17] = _r->regs[18] = _r->regs[19] = _r->regs[20] = 0;	\
 	_r->regs[21] = _r->regs[22] = _r->regs[23] = _r->regs[24] = 0;	\
diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h
index 9b4957cefa8a..46366e783c84 100644
--- a/arch/loongarch/include/asm/loongarch.h
+++ b/arch/loongarch/include/asm/loongarch.h
@@ -1098,12 +1098,11 @@
 
 static __always_inline u64 drdtime(void)
 {
-	int rID = 0;
 	u64 val = 0;
 
 	__asm__ __volatile__(
-		"rdtime.d %0, %1 \n\t"
-		: "=r"(val), "=r"(rID)
+		"rdtime.d %0, $zero\n\t"
+		: "=r"(val)
 		:
 		);
 	return val;
diff --git a/arch/loongarch/include/asm/percpu.h b/arch/loongarch/include/asm/percpu.h
index ed5da02b1cf6..9b36ac003f89 100644
--- a/arch/loongarch/include/asm/percpu.h
+++ b/arch/loongarch/include/asm/percpu.h
@@ -40,13 +40,13 @@ static __always_inline unsigned long __percpu_##op(void *ptr,		\
 	switch (size) {							\
 	case 4:								\
 		__asm__ __volatile__(					\
-		"am"#asm_op".w"	" %[ret], %[val], %[ptr]	\n"		\
+		"am"#asm_op".w"	" %[ret], %[val], %[ptr]	\n"	\
 		: [ret] "=&r" (ret), [ptr] "+ZB"(*(u32 *)ptr)		\
 		: [val] "r" (val));					\
 		break;							\
 	case 8:								\
 		__asm__ __volatile__(					\
-		"am"#asm_op".d" " %[ret], %[val], %[ptr]	\n"		\
+		"am"#asm_op".d" " %[ret], %[val], %[ptr]	\n"	\
 		: [ret] "=&r" (ret), [ptr] "+ZB"(*(u64 *)ptr)		\
 		: [val] "r" (val));					\
 		break;							\
@@ -63,7 +63,7 @@ PERCPU_OP(and, and, &)
 PERCPU_OP(or, or, |)
 #undef PERCPU_OP
 
-static __always_inline unsigned long __percpu_read(void *ptr, int size)
+static __always_inline unsigned long __percpu_read(void __percpu *ptr, int size)
 {
 	unsigned long ret;
 
@@ -100,7 +100,7 @@ static __always_inline unsigned long __percpu_read(void *ptr, int size)
 	return ret;
 }
 
-static __always_inline void __percpu_write(void *ptr, unsigned long val, int size)
+static __always_inline void __percpu_write(void __percpu *ptr, unsigned long val, int size)
 {
 	switch (size) {
 	case 1:
@@ -132,8 +132,7 @@ static __always_inline void __percpu_write(void *ptr, unsigned long val, int siz
 	}
 }
 
-static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
-						   int size)
+static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val, int size)
 {
 	switch (size) {
 	case 1:
diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index 29d9b12298bc..8b5df1bbf9e9 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -523,6 +523,7 @@ static inline pmd_t pmd_wrprotect(pmd_t pmd)
 	return pmd;
 }
 
+#define pmd_dirty pmd_dirty
 static inline int pmd_dirty(pmd_t pmd)
 {
 	return !!(pmd_val(pmd) & (_PAGE_DIRTY | _PAGE_MODIFIED));
diff --git a/arch/loongarch/include/asm/setup.h b/arch/loongarch/include/asm/setup.h
index a0bc159ce8bd..ee52fb1e9963 100644
--- a/arch/loongarch/include/asm/setup.h
+++ b/arch/loongarch/include/asm/setup.h
@@ -25,7 +25,7 @@ extern void set_merr_handler(unsigned long offset, void *addr, unsigned long len
 #ifdef CONFIG_RELOCATABLE
 
 struct rela_la_abs {
-	long offset;
+	long pc;
 	long symvalue;
 };
 
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index 4fcc168f0732..3c808c680370 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -57,7 +57,7 @@ obj-$(CONFIG_MAGIC_SYSRQ)	+= sysrq.o
 
 obj-$(CONFIG_RELOCATABLE)	+= relocate.o
 
-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
+obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec.o relocate_kernel.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 
 obj-$(CONFIG_UNWINDER_GUESS)	+= unwind_guess.o
diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c
index 173fe514fc9e..bee9f7a3108f 100644
--- a/arch/loongarch/kernel/asm-offsets.c
+++ b/arch/loongarch/kernel/asm-offsets.c
@@ -15,7 +15,7 @@
 #include <asm/processor.h>
 #include <asm/ftrace.h>
 
-void output_ptreg_defines(void)
+static void __used output_ptreg_defines(void)
 {
 	COMMENT("LoongArch pt_regs offsets.");
 	OFFSET(PT_R0, pt_regs, regs[0]);
@@ -62,7 +62,7 @@ void output_ptreg_defines(void)
 	BLANK();
 }
 
-void output_task_defines(void)
+static void __used output_task_defines(void)
 {
 	COMMENT("LoongArch task_struct offsets.");
 	OFFSET(TASK_STATE, task_struct, __state);
@@ -77,7 +77,7 @@ void output_task_defines(void)
 	BLANK();
 }
 
-void output_thread_info_defines(void)
+static void __used output_thread_info_defines(void)
 {
 	COMMENT("LoongArch thread_info offsets.");
 	OFFSET(TI_TASK, thread_info, task);
@@ -93,7 +93,7 @@ void output_thread_info_defines(void)
 	BLANK();
 }
 
-void output_thread_defines(void)
+static void __used output_thread_defines(void)
 {
 	COMMENT("LoongArch specific thread_struct offsets.");
 	OFFSET(THREAD_REG01, task_struct, thread.reg01);
@@ -129,7 +129,7 @@ void output_thread_defines(void)
 	BLANK();
 }
 
-void output_thread_fpu_defines(void)
+static void __used output_thread_fpu_defines(void)
 {
 	OFFSET(THREAD_FPR0, loongarch_fpu, fpr[0]);
 	OFFSET(THREAD_FPR1, loongarch_fpu, fpr[1]);
@@ -170,7 +170,7 @@ void output_thread_fpu_defines(void)
 	BLANK();
 }
 
-void output_thread_lbt_defines(void)
+static void __used output_thread_lbt_defines(void)
 {
 	OFFSET(THREAD_SCR0,  loongarch_lbt, scr0);
 	OFFSET(THREAD_SCR1,  loongarch_lbt, scr1);
@@ -180,7 +180,7 @@ void output_thread_lbt_defines(void)
 	BLANK();
 }
 
-void output_mm_defines(void)
+static void __used output_mm_defines(void)
 {
 	COMMENT("Size of struct page");
 	DEFINE(STRUCT_PAGE_SIZE, sizeof(struct page));
@@ -212,7 +212,7 @@ void output_mm_defines(void)
 	BLANK();
 }
 
-void output_sc_defines(void)
+static void __used output_sc_defines(void)
 {
 	COMMENT("Linux sigcontext offsets.");
 	OFFSET(SC_REGS, sigcontext, sc_regs);
@@ -220,7 +220,7 @@ void output_sc_defines(void)
 	BLANK();
 }
 
-void output_signal_defines(void)
+static void __used output_signal_defines(void)
 {
 	COMMENT("Linux signal numbers.");
 	DEFINE(_SIGHUP, SIGHUP);
@@ -258,7 +258,7 @@ void output_signal_defines(void)
 }
 
 #ifdef CONFIG_SMP
-void output_smpboot_defines(void)
+static void __used output_smpboot_defines(void)
 {
 	COMMENT("Linux smp cpu boot offsets.");
 	OFFSET(CPU_BOOT_STACK, secondary_data, stack);
@@ -268,7 +268,7 @@ void output_smpboot_defines(void)
 #endif
 
 #ifdef CONFIG_HIBERNATION
-void output_pbe_defines(void)
+static void __used output_pbe_defines(void)
 {
 	COMMENT("Linux struct pbe offsets.");
 	OFFSET(PBE_ADDRESS, pbe, address);
@@ -280,7 +280,7 @@ void output_pbe_defines(void)
 #endif
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-void output_fgraph_ret_regs_defines(void)
+static void __used output_fgraph_ret_regs_defines(void)
 {
 	COMMENT("LoongArch fgraph_ret_regs offsets.");
 	OFFSET(FGRET_REGS_A0, fgraph_ret_regs, regs[0]);
@@ -291,7 +291,7 @@ void output_fgraph_ret_regs_defines(void)
 }
 #endif
 
-void output_kvm_defines(void)
+static void __used output_kvm_defines(void)
 {
 	COMMENT("KVM/LoongArch Specific offsets.");
 
diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S
index 53b883db0786..0ecab4216392 100644
--- a/arch/loongarch/kernel/head.S
+++ b/arch/loongarch/kernel/head.S
@@ -34,7 +34,6 @@ pe_header:
 
 SYM_DATA(kernel_asize, .long _kernel_asize);
 SYM_DATA(kernel_fsize, .long _kernel_fsize);
-SYM_DATA(kernel_offset, .long _kernel_offset);
 
 #endif
 
diff --git a/arch/loongarch/kernel/image-vars.h b/arch/loongarch/kernel/image-vars.h
index 5087416b9678..41ddcf56d21c 100644
--- a/arch/loongarch/kernel/image-vars.h
+++ b/arch/loongarch/kernel/image-vars.h
@@ -11,7 +11,6 @@ __efistub_strcmp		= strcmp;
 __efistub_kernel_entry		= kernel_entry;
 __efistub_kernel_asize		= kernel_asize;
 __efistub_kernel_fsize		= kernel_fsize;
-__efistub_kernel_offset		= kernel_offset;
 #if defined(CONFIG_EFI_EARLYCON) || defined(CONFIG_SYSFB)
 __efistub_screen_info		= screen_info;
 #endif
diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c
index 6e65ff12d5c7..8fe21f868f72 100644
--- a/arch/loongarch/kernel/numa.c
+++ b/arch/loongarch/kernel/numa.c
@@ -226,32 +226,6 @@ static void __init node_mem_init(unsigned int node)
 
 #ifdef CONFIG_ACPI_NUMA
 
-/*
- * Sanity check to catch more bad NUMA configurations (they are amazingly
- * common).  Make sure the nodes cover all memory.
- */
-static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
-{
-	int i;
-	u64 numaram, biosram;
-
-	numaram = 0;
-	for (i = 0; i < mi->nr_blks; i++) {
-		u64 s = mi->blk[i].start >> PAGE_SHIFT;
-		u64 e = mi->blk[i].end >> PAGE_SHIFT;
-
-		numaram += e - s;
-		numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e);
-		if ((s64)numaram < 0)
-			numaram = 0;
-	}
-	max_pfn = max_low_pfn;
-	biosram = max_pfn - absent_pages_in_range(0, max_pfn);
-
-	BUG_ON((s64)(biosram - numaram) >= (1 << (20 - PAGE_SHIFT)));
-	return true;
-}
-
 static void __init add_node_intersection(u32 node, u64 start, u64 size, u32 type)
 {
 	static unsigned long num_physpages;
@@ -396,7 +370,7 @@ int __init init_numa_memory(void)
 		return -EINVAL;
 
 	init_node_memblock();
-	if (numa_meminfo_cover_memory(&numa_meminfo) == false)
+	if (!memblock_validate_numa_coverage(SZ_1M))
 		return -EINVAL;
 
 	for_each_node_mask(node, node_possible_map) {
diff --git a/arch/loongarch/kernel/relocate.c b/arch/loongarch/kernel/relocate.c
index 6c3eff9af9fb..1acfa704c8d0 100644
--- a/arch/loongarch/kernel/relocate.c
+++ b/arch/loongarch/kernel/relocate.c
@@ -52,7 +52,7 @@ static inline void __init relocate_absolute(long random_offset)
 	for (p = begin; (void *)p < end; p++) {
 		long v = p->symvalue;
 		uint32_t lu12iw, ori, lu32id, lu52id;
-		union loongarch_instruction *insn = (void *)p - p->offset;
+		union loongarch_instruction *insn = (void *)p->pc;
 
 		lu12iw = (v >> 12) & 0xfffff;
 		ori    = v & 0xfff;
@@ -102,6 +102,14 @@ static inline __init unsigned long get_random_boot(void)
 	return hash;
 }
 
+static int __init nokaslr(char *p)
+{
+	pr_info("KASLR is disabled.\n");
+
+	return 0; /* Print a notice and silence the boot warning */
+}
+early_param("nokaslr", nokaslr);
+
 static inline __init bool kaslr_disabled(void)
 {
 	char *str;
diff --git a/arch/loongarch/kernel/signal.c b/arch/loongarch/kernel/signal.c
index 4a3686d13349..7a555b600171 100644
--- a/arch/loongarch/kernel/signal.c
+++ b/arch/loongarch/kernel/signal.c
@@ -15,6 +15,7 @@
 #include <linux/context_tracking.h>
 #include <linux/entry-common.h>
 #include <linux/irqflags.h>
+#include <linux/rseq.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/personality.h>
diff --git a/arch/loongarch/kernel/stacktrace.c b/arch/loongarch/kernel/stacktrace.c
index 92270f14db94..f623feb2129f 100644
--- a/arch/loongarch/kernel/stacktrace.c
+++ b/arch/loongarch/kernel/stacktrace.c
@@ -32,7 +32,7 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
 	}
 
 	for (unwind_start(&state, task, regs);
-	     !unwind_done(&state) && !unwind_error(&state); unwind_next_frame(&state)) {
+	     !unwind_done(&state); unwind_next_frame(&state)) {
 		addr = unwind_get_return_address(&state);
 		if (!addr || !consume_entry(cookie, addr))
 			break;
diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c
index 3064af94db9c..e7015f7b70e3 100644
--- a/arch/loongarch/kernel/time.c
+++ b/arch/loongarch/kernel/time.c
@@ -58,14 +58,16 @@ static int constant_set_state_oneshot(struct clock_event_device *evt)
 	return 0;
 }
 
-static int constant_set_state_oneshot_stopped(struct clock_event_device *evt)
+static int constant_set_state_periodic(struct clock_event_device *evt)
 {
+	unsigned long period;
 	unsigned long timer_config;
 
 	raw_spin_lock(&state_lock);
 
-	timer_config = csr_read64(LOONGARCH_CSR_TCFG);
-	timer_config &= ~CSR_TCFG_EN;
+	period = const_clock_freq / HZ;
+	timer_config = period & CSR_TCFG_VAL;
+	timer_config |= (CSR_TCFG_PERIOD | CSR_TCFG_EN);
 	csr_write64(timer_config, LOONGARCH_CSR_TCFG);
 
 	raw_spin_unlock(&state_lock);
@@ -73,16 +75,14 @@ static int constant_set_state_oneshot_stopped(struct clock_event_device *evt)
 	return 0;
 }
 
-static int constant_set_state_periodic(struct clock_event_device *evt)
+static int constant_set_state_shutdown(struct clock_event_device *evt)
 {
-	unsigned long period;
 	unsigned long timer_config;
 
 	raw_spin_lock(&state_lock);
 
-	period = const_clock_freq / HZ;
-	timer_config = period & CSR_TCFG_VAL;
-	timer_config |= (CSR_TCFG_PERIOD | CSR_TCFG_EN);
+	timer_config = csr_read64(LOONGARCH_CSR_TCFG);
+	timer_config &= ~CSR_TCFG_EN;
 	csr_write64(timer_config, LOONGARCH_CSR_TCFG);
 
 	raw_spin_unlock(&state_lock);
@@ -90,11 +90,6 @@ static int constant_set_state_periodic(struct clock_event_device *evt)
 	return 0;
 }
 
-static int constant_set_state_shutdown(struct clock_event_device *evt)
-{
-	return 0;
-}
-
 static int constant_timer_next_event(unsigned long delta, struct clock_event_device *evt)
 {
 	unsigned long timer_config;
@@ -161,7 +156,7 @@ int constant_clockevent_init(void)
 	cd->rating = 320;
 	cd->cpumask = cpumask_of(cpu);
 	cd->set_state_oneshot = constant_set_state_oneshot;
-	cd->set_state_oneshot_stopped = constant_set_state_oneshot_stopped;
+	cd->set_state_oneshot_stopped = constant_set_state_shutdown;
 	cd->set_state_periodic = constant_set_state_periodic;
 	cd->set_state_shutdown = constant_set_state_shutdown;
 	cd->set_next_event = constant_timer_next_event;
diff --git a/arch/loongarch/kernel/unwind.c b/arch/loongarch/kernel/unwind.c
index ba324ba76fa1..a463d6961344 100644
--- a/arch/loongarch/kernel/unwind.c
+++ b/arch/loongarch/kernel/unwind.c
@@ -28,6 +28,5 @@ bool default_next_frame(struct unwind_state *state)
 
 	} while (!get_stack_info(state->sp, state->task, info));
 
-	state->error = true;
 	return false;
 }
diff --git a/arch/loongarch/kernel/unwind_prologue.c b/arch/loongarch/kernel/unwind_prologue.c
index 55afc27320e1..929ae240280a 100644
--- a/arch/loongarch/kernel/unwind_prologue.c
+++ b/arch/loongarch/kernel/unwind_prologue.c
@@ -227,7 +227,7 @@ static bool next_frame(struct unwind_state *state)
 	} while (!get_stack_info(state->sp, state->task, info));
 
 out:
-	state->error = true;
+	state->stack_info.type = STACK_TYPE_UNKNOWN;
 	return false;
 }
 
diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S
index bb2ec86f37a8..a5d0cd2035da 100644
--- a/arch/loongarch/kernel/vmlinux.lds.S
+++ b/arch/loongarch/kernel/vmlinux.lds.S
@@ -143,7 +143,6 @@ SECTIONS
 	_kernel_fsize = _edata - _text;
 	_kernel_vsize = _end - __initdata_begin;
 	_kernel_rsize = _edata - __initdata_begin;
-	_kernel_offset = kernel_offset - _text;
 #endif
 
 	.gptab.sdata : {
diff --git a/arch/loongarch/mm/pgtable.c b/arch/loongarch/mm/pgtable.c
index 71d0539e2d0b..2aae72e63871 100644
--- a/arch/loongarch/mm/pgtable.c
+++ b/arch/loongarch/mm/pgtable.c
@@ -13,13 +13,13 @@ struct page *dmw_virt_to_page(unsigned long kaddr)
 {
 	return pfn_to_page(virt_to_pfn(kaddr));
 }
-EXPORT_SYMBOL_GPL(dmw_virt_to_page);
+EXPORT_SYMBOL(dmw_virt_to_page);
 
 struct page *tlb_virt_to_page(unsigned long kaddr)
 {
 	return pfn_to_page(pte_pfn(*virt_to_kpte(kaddr)));
 }
-EXPORT_SYMBOL_GPL(tlb_virt_to_page);
+EXPORT_SYMBOL(tlb_virt_to_page);
 
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c
index 169ff8b3915e..4fcd6cd6da23 100644
--- a/arch/loongarch/net/bpf_jit.c
+++ b/arch/loongarch/net/bpf_jit.c
@@ -480,10 +480,12 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 		case 8:
 			move_reg(ctx, t1, src);
 			emit_insn(ctx, extwb, dst, t1);
+			emit_zext_32(ctx, dst, is32);
 			break;
 		case 16:
 			move_reg(ctx, t1, src);
 			emit_insn(ctx, extwh, dst, t1);
+			emit_zext_32(ctx, dst, is32);
 			break;
 		case 32:
 			emit_insn(ctx, addw, dst, src, LOONGARCH_GPR_ZERO);
@@ -772,8 +774,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 			break;
 		case 32:
 			emit_insn(ctx, revb2w, dst, dst);
-			/* zero-extend 32 bits into 64 bits */
-			emit_zext_32(ctx, dst, is32);
+			/* clear the upper 32 bits */
+			emit_zext_32(ctx, dst, true);
 			break;
 		case 64:
 			emit_insn(ctx, revbd, dst, dst);
@@ -911,8 +913,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 
 	/* function return */
 	case BPF_JMP | BPF_EXIT:
-		emit_sext_32(ctx, regmap[BPF_REG_0], true);
-
 		if (i == ctx->prog->len - 1)
 			break;
 
@@ -988,14 +988,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 			}
 			break;
 		case BPF_DW:
-			if (is_signed_imm12(off)) {
-				emit_insn(ctx, ldd, dst, src, off);
-			} else if (is_signed_imm14(off)) {
-				emit_insn(ctx, ldptrd, dst, src, off);
-			} else {
-				move_imm(ctx, t1, off, is32);
-				emit_insn(ctx, ldxd, dst, src, t1);
-			}
+			move_imm(ctx, t1, off, is32);
+			emit_insn(ctx, ldxd, dst, src, t1);
 			break;
 		}
 
diff --git a/arch/loongarch/vdso/vgettimeofday.c b/arch/loongarch/vdso/vgettimeofday.c
index 8f22863bd7ea..0885c1f3a89d 100644
--- a/arch/loongarch/vdso/vgettimeofday.c
+++ b/arch/loongarch/vdso/vgettimeofday.c
@@ -5,23 +5,18 @@
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
 #include <linux/types.h>
+#include <vdso/gettime.h>
 
-extern
-int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
 int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
 {
 	return __cvdso_clock_gettime(clock, ts);
 }
 
-extern
-int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
 int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 {
 	return __cvdso_gettimeofday(tv, tz);
 }
 
-extern
-int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res);
 int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res)
 {
 	return __cvdso_clock_getres(clock_id, res);
diff --git a/arch/m68k/Kconfig.cpu b/arch/m68k/Kconfig.cpu
index ad69b466a08b..9dcf245c9cbf 100644
--- a/arch/m68k/Kconfig.cpu
+++ b/arch/m68k/Kconfig.cpu
@@ -402,7 +402,7 @@ config ARCH_FORCE_MAX_ORDER
 	default "10"
 	help
 	  The kernel page allocator limits the size of maximal physically
-	  contiguous allocations. The limit is called MAX_ORDER and it
+	  contiguous allocations. The limit is called MAX_PAGE_ORDER and it
 	  defines the maximal power of two of number of pages that can be
 	  allocated as a single contiguous block. This option allows
 	  overriding the default setting when ability to allocate very
diff --git a/arch/m68k/coldfire/vectors.c b/arch/m68k/coldfire/vectors.c
index c26c255b530d..4321fd89d83e 100644
--- a/arch/m68k/coldfire/vectors.c
+++ b/arch/m68k/coldfire/vectors.c
@@ -12,14 +12,13 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/irq.h>
+#include <linux/cpu.h>
 #include <asm/traps.h>
 #include <asm/machdep.h>
 #include <asm/coldfire.h>
 #include <asm/mcfsim.h>
 #include <asm/mcfwdebug.h>
 
-#include "vectors.h"
-
 /***************************************************************************/
 
 #ifdef TRAP_DBG_INTERRUPT
diff --git a/arch/m68k/coldfire/vectors.h b/arch/m68k/coldfire/vectors.h
deleted file mode 100644
index 0b01450a4353..000000000000
--- a/arch/m68k/coldfire/vectors.h
+++ /dev/null
@@ -1,3 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-
-void trap_init(void);
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 7e6b74b6eecd..b4d71fea558f 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -453,6 +453,7 @@ CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
+CONFIG_BCACHEFS_FS=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 CONFIG_AUTOFS_FS=m
@@ -550,7 +551,6 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
-CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 0b403e2efcd5..682d8cd3dd3c 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -410,6 +410,7 @@ CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
+CONFIG_BCACHEFS_FS=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 CONFIG_AUTOFS_FS=m
@@ -507,7 +508,6 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
-CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 57aac3f4b001..15259ced8463 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -430,6 +430,7 @@ CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
+CONFIG_BCACHEFS_FS=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 CONFIG_AUTOFS_FS=m
@@ -527,7 +528,6 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
-CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 3c160636a2e9..7395c12caef6 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -402,6 +402,7 @@ CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
+CONFIG_BCACHEFS_FS=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 CONFIG_AUTOFS_FS=m
@@ -499,7 +500,6 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
-CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 23cf07c49d14..92506bc7f78d 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -412,6 +412,7 @@ CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
+CONFIG_BCACHEFS_FS=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 CONFIG_AUTOFS_FS=m
@@ -509,7 +510,6 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
-CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 619a0d93ce5b..144bc8c0d8b5 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -269,9 +269,6 @@ CONFIG_RDS_TCP=m
 CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
-CONFIG_DEV_APPLETALK=m
-CONFIG_IPDDP=m
-CONFIG_IPDDP_ENCAP=y
 CONFIG_6LOWPAN=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
 CONFIG_6LOWPAN_GHC_UDP=m
@@ -432,6 +429,7 @@ CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
+CONFIG_BCACHEFS_FS=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 CONFIG_AUTOFS_FS=m
@@ -529,7 +527,6 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
-CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index d9430bc2b2de..07594c729497 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -289,9 +289,6 @@ CONFIG_RDS_TCP=m
 CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
-CONFIG_DEV_APPLETALK=m
-CONFIG_IPDDP=m
-CONFIG_IPDDP_ENCAP=y
 CONFIG_6LOWPAN=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
 CONFIG_6LOWPAN_GHC_UDP=m
@@ -518,6 +515,7 @@ CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
+CONFIG_BCACHEFS_FS=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 CONFIG_AUTOFS_FS=m
@@ -615,7 +613,6 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
-CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index eb6132f29bf5..c34de6c1de20 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -401,6 +401,7 @@ CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
+CONFIG_BCACHEFS_FS=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 CONFIG_AUTOFS_FS=m
@@ -498,7 +499,6 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
-CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index d0bad674cbb7..83bc029d1f33 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -402,6 +402,7 @@ CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
+CONFIG_BCACHEFS_FS=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 CONFIG_AUTOFS_FS=m
@@ -499,7 +500,6 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
-CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index dad6bcfcaeed..4f551dac2ed7 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -419,6 +419,7 @@ CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
+CONFIG_BCACHEFS_FS=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 CONFIG_AUTOFS_FS=m
@@ -516,7 +517,6 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
-CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index eb1b489b3139..b1bf01182bd3 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -400,6 +400,7 @@ CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
+CONFIG_BCACHEFS_FS=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 CONFIG_AUTOFS_FS=m
@@ -497,7 +498,6 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
-CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 939589826546..5c9a3f71f036 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -400,6 +400,7 @@ CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
+CONFIG_BCACHEFS_FS=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 CONFIG_AUTOFS_FS=m
@@ -497,7 +498,6 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
-CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
diff --git a/arch/m68k/include/asm/io_mm.h b/arch/m68k/include/asm/io_mm.h
index 47525f2a57e1..090aec54b8fa 100644
--- a/arch/m68k/include/asm/io_mm.h
+++ b/arch/m68k/include/asm/io_mm.h
@@ -389,12 +389,6 @@ static inline void isa_delay(void)
 
 #define __ARCH_HAS_NO_PAGE_ZERO_MAPPED		1
 
-/*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p)	__va(p)
-
 #define readb_relaxed(addr)	readb(addr)
 #define readw_relaxed(addr)	readw(addr)
 #define readl_relaxed(addr)	readl(addr)
diff --git a/arch/m68k/include/asm/kexec.h b/arch/m68k/include/asm/kexec.h
index f5a8b2defa4b..3b0b64f0a353 100644
--- a/arch/m68k/include/asm/kexec.h
+++ b/arch/m68k/include/asm/kexec.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_M68K_KEXEC_H
 #define _ASM_M68K_KEXEC_H
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 
 /* Maximum physical address we can use pages from */
 #define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
@@ -25,6 +25,6 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
 
 #endif /* __ASSEMBLY__ */
 
-#endif /* CONFIG_KEXEC */
+#endif /* CONFIG_KEXEC_CORE */
 
 #endif /* _ASM_M68K_KEXEC_H */
diff --git a/arch/m68k/include/asm/kmap.h b/arch/m68k/include/asm/kmap.h
index 4efb3efa593a..b778f015c917 100644
--- a/arch/m68k/include/asm/kmap.h
+++ b/arch/m68k/include/asm/kmap.h
@@ -25,7 +25,6 @@ static inline void __iomem *ioremap(unsigned long physaddr, unsigned long size)
 	return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
 }
 
-#define ioremap_uc ioremap
 #define ioremap_wt ioremap_wt
 static inline void __iomem *ioremap_wt(unsigned long physaddr,
 				       unsigned long size)
diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h
index 7a2da780830b..8f2676c3a988 100644
--- a/arch/m68k/include/asm/processor.h
+++ b/arch/m68k/include/asm/processor.h
@@ -8,6 +8,7 @@
 #ifndef __ASM_M68K_PROCESSOR_H
 #define __ASM_M68K_PROCESSOR_H
 
+#include <linux/preempt.h>
 #include <linux/thread_info.h>
 #include <asm/fpu.h>
 #include <asm/ptrace.h>
diff --git a/arch/m68k/kernel/Makefile b/arch/m68k/kernel/Makefile
index 01fb69a5095f..f335bf3268a1 100644
--- a/arch/m68k/kernel/Makefile
+++ b/arch/m68k/kernel/Makefile
@@ -25,7 +25,7 @@ obj-$(CONFIG_PCI) += pcibios.o
 
 obj-$(CONFIG_M68K_NONCOHERENT_DMA) += dma.o
 
-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
+obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec.o relocate_kernel.o
 obj-$(CONFIG_BOOTINFO_PROC)	+= bootinfo_proc.o
 obj-$(CONFIG_UBOOT)		+= uboot.o
 
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 7a4b780e82cb..7fd43fd4c9f2 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -456,3 +456,8 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount
+459	common	lsm_get_self_attr		sys_lsm_get_self_attr
+460	common	lsm_set_self_attr		sys_lsm_set_self_attr
+461	common	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/microblaze/include/asm/ftrace.h b/arch/microblaze/include/asm/ftrace.h
index 6a92bed37794..4ca38b92a3a2 100644
--- a/arch/microblaze/include/asm/ftrace.h
+++ b/arch/microblaze/include/asm/ftrace.h
@@ -10,6 +10,7 @@
 #ifndef __ASSEMBLY__
 extern void _mcount(void);
 extern void ftrace_call_graph(void);
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr);
 #endif
 
 #ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h
index 3042eb98bb56..e4ea2ec3642f 100644
--- a/arch/microblaze/include/asm/pgtable.h
+++ b/arch/microblaze/include/asm/pgtable.h
@@ -336,6 +336,7 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
 }
 
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+struct vm_area_struct;
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 		unsigned long address, pte_t *ptep)
 {
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 5b6a0b02b7de..b00ab2cabab9 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -462,3 +462,8 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount
+459	common	lsm_get_self_attr		sys_lsm_get_self_attr
+460	common	lsm_set_self_attr		sys_lsm_set_self_attr
+461	common	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/microblaze/kernel/traps.c b/arch/microblaze/kernel/traps.c
index 94b6fe93147d..080aa769218d 100644
--- a/arch/microblaze/kernel/traps.c
+++ b/arch/microblaze/kernel/traps.c
@@ -8,6 +8,7 @@
  * for more details.
  */
 
+#include <linux/cpu.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/kallsyms.h>
diff --git a/arch/mips/Kbuild b/arch/mips/Kbuild
index af2967bffb73..e2d623621a00 100644
--- a/arch/mips/Kbuild
+++ b/arch/mips/Kbuild
@@ -1,10 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-# Fail on warnings - also for files referenced in subdirs
-# -Werror can be disabled for specific files using:
-# CFLAGS_<file.o> := -Wno-error
-ifeq ($(W),)
-subdir-ccflags-y := -Werror
-endif
 
 # platform specific definitions
 include $(srctree)/arch/mips/Kbuild.platforms
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 76db82542519..797ae590ebdb 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -460,6 +460,7 @@ config MACH_LOONGSON2EF
 
 config MACH_LOONGSON64
 	bool "Loongson 64-bit family of machines"
+	select ARCH_DMA_DEFAULT_COHERENT
 	select ARCH_SPARSEMEM_ENABLE
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
@@ -1251,6 +1252,7 @@ config CPU_LOONGSON64
 	select CPU_SUPPORTS_MSA
 	select CPU_DIEI_BROKEN if !LOONGSON3_ENHANCEMENT
 	select CPU_MIPSR2_IRQ_VI
+	select DMA_NONCOHERENT
 	select WEAK_ORDERING
 	select WEAK_REORDERING_BEYOND_LLSC
 	select MIPS_ASID_BITS_VARIABLE
diff --git a/arch/mips/boot/compressed/dbg.c b/arch/mips/boot/compressed/dbg.c
index f6728a8fd1c3..2f1ac38fe1cc 100644
--- a/arch/mips/boot/compressed/dbg.c
+++ b/arch/mips/boot/compressed/dbg.c
@@ -9,6 +9,8 @@
 #include <linux/compiler.h>
 #include <linux/types.h>
 
+#include "decompress.h"
+
 void __weak putc(char c)
 {
 }
diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c
index c5dd415254d3..adb6d5b0e6eb 100644
--- a/arch/mips/boot/compressed/decompress.c
+++ b/arch/mips/boot/compressed/decompress.c
@@ -19,6 +19,8 @@
 #include <asm/unaligned.h>
 #include <asm-generic/vmlinux.lds.h>
 
+#include "decompress.h"
+
 /*
  * These two variables specify the free mem region
  * that can be used for temporary malloc area
@@ -26,20 +28,6 @@
 unsigned long free_mem_ptr;
 unsigned long free_mem_end_ptr;
 
-/* The linker tells us where the image is. */
-extern unsigned char __image_begin[], __image_end[];
-
-/* debug interfaces  */
-#ifdef CONFIG_DEBUG_ZBOOT
-extern void puts(const char *s);
-extern void puthex(unsigned long long val);
-#else
-#define puts(s) do {} while (0)
-#define puthex(val) do {} while (0)
-#endif
-
-extern char __appended_dtb[];
-
 void error(char *x)
 {
 	puts("\n\n");
diff --git a/arch/mips/boot/compressed/decompress.h b/arch/mips/boot/compressed/decompress.h
new file mode 100644
index 000000000000..073b64593b3d
--- /dev/null
+++ b/arch/mips/boot/compressed/decompress.h
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _DECOMPRESSOR_H
+#define _DECOMPRESSOR_H
+
+/* The linker tells us where the image is. */
+extern unsigned char __image_begin[], __image_end[];
+
+/* debug interfaces  */
+#ifdef CONFIG_DEBUG_ZBOOT
+extern void putc(char c);
+extern void puts(const char *s);
+extern void puthex(unsigned long long val);
+#else
+#define putc(s) do {} while (0)
+#define puts(s) do {} while (0)
+#define puthex(val) do {} while (0)
+#endif
+
+extern char __appended_dtb[];
+
+void error(char *x);
+void decompress_kernel(unsigned long boot_heap_start);
+
+#endif
diff --git a/arch/mips/boot/compressed/string.c b/arch/mips/boot/compressed/string.c
index 0b593b709228..f0eb251e44e5 100644
--- a/arch/mips/boot/compressed/string.c
+++ b/arch/mips/boot/compressed/string.c
@@ -7,6 +7,7 @@
 
 #include <linux/compiler_attributes.h>
 #include <linux/types.h>
+#include <asm/string.h>
 
 void *memcpy(void *dest, const void *src, size_t n)
 {
diff --git a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi
index f878f47e4501..ee3e2153dd13 100644
--- a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi
+++ b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi
@@ -130,8 +130,7 @@
 				compatible = "pci0014,7a03.0",
 						   "pci0014,7a03",
 						   "pciclass0c0320",
-						   "pciclass0c03",
-						   "loongson, pci-gmac";
+						   "pciclass0c03";
 
 				reg = <0x1800 0x0 0x0 0x0 0x0>;
 				interrupts = <12 IRQ_TYPE_LEVEL_LOW>,
diff --git a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi
index 7c69e8245c2f..cce9428afc41 100644
--- a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi
+++ b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi
@@ -193,8 +193,7 @@
 				compatible = "pci0014,7a03.0",
 						   "pci0014,7a03",
 						   "pciclass020000",
-						   "pciclass0200",
-						   "loongson, pci-gmac";
+						   "pciclass0200";
 
 				reg = <0x1800 0x0 0x0 0x0 0x0>;
 				interrupts = <12 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index 33c09688210f..08ea2cde1eb5 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -422,7 +422,7 @@ static const struct plat_smp_ops octeon_smp_ops = {
 	.cpu_disable		= octeon_cpu_disable,
 	.cpu_die		= octeon_cpu_die,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu	= kexec_nonboot_cpu_jump,
 #endif
 };
@@ -502,7 +502,7 @@ static const struct plat_smp_ops octeon_78xx_smp_ops = {
 	.cpu_disable		= octeon_cpu_disable,
 	.cpu_die		= octeon_cpu_die,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu	= kexec_nonboot_cpu_jump,
 #endif
 };
diff --git a/arch/mips/configs/ip22_defconfig b/arch/mips/configs/ip22_defconfig
index dc49b09d492b..e22e8b825903 100644
--- a/arch/mips/configs/ip22_defconfig
+++ b/arch/mips/configs/ip22_defconfig
@@ -173,7 +173,6 @@ CONFIG_NET_ACT_POLICE=y
 CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
-CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig
index 6f8046024557..4390d30206d9 100644
--- a/arch/mips/configs/malta_defconfig
+++ b/arch/mips/configs/malta_defconfig
@@ -202,7 +202,6 @@ CONFIG_NET_ACT_POLICE=y
 CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
-CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
diff --git a/arch/mips/configs/malta_kvm_defconfig b/arch/mips/configs/malta_kvm_defconfig
index 16a91eeff67f..d63d8be8cb50 100644
--- a/arch/mips/configs/malta_kvm_defconfig
+++ b/arch/mips/configs/malta_kvm_defconfig
@@ -206,7 +206,6 @@ CONFIG_NET_ACT_POLICE=y
 CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
-CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
diff --git a/arch/mips/configs/maltaup_xpa_defconfig b/arch/mips/configs/maltaup_xpa_defconfig
index 264aba29ea4f..338bb6544a93 100644
--- a/arch/mips/configs/maltaup_xpa_defconfig
+++ b/arch/mips/configs/maltaup_xpa_defconfig
@@ -203,7 +203,6 @@ CONFIG_NET_ACT_POLICE=y
 CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
-CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
diff --git a/arch/mips/configs/rb532_defconfig b/arch/mips/configs/rb532_defconfig
index 02ec6c1a5116..517f1b060bf4 100644
--- a/arch/mips/configs/rb532_defconfig
+++ b/arch/mips/configs/rb532_defconfig
@@ -96,7 +96,6 @@ CONFIG_NET_ACT_POLICE=y
 CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
-CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_HAMRADIO=y
 CONFIG_MTD=y
diff --git a/arch/mips/include/asm/cache.h b/arch/mips/include/asm/cache.h
index 3424a7908c0f..8b08db3fb17a 100644
--- a/arch/mips/include/asm/cache.h
+++ b/arch/mips/include/asm/cache.h
@@ -17,5 +17,11 @@
 #define __read_mostly __section(".data..read_mostly")
 
 extern void cache_noop(void);
+extern void r3k_cache_init(void);
+extern unsigned long r3k_cache_size(unsigned long);
+extern unsigned long r3k_cache_lsize(unsigned long);
+extern void r4k_cache_init(void);
+extern void octeon_cache_init(void);
+extern void au1x00_fixup_config_od(void);
 
 #endif /* _ASM_CACHE_H */
diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h
index db497a8167da..dc025888f6d2 100644
--- a/arch/mips/include/asm/ftrace.h
+++ b/arch/mips/include/asm/ftrace.h
@@ -85,6 +85,10 @@ struct dyn_arch_ftrace {
 };
 
 #endif /*  CONFIG_DYNAMIC_FTRACE */
+
+void prepare_ftrace_return(unsigned long *parent_ra_addr, unsigned long self_ra,
+			   unsigned long fp);
+
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_FUNCTION_TRACER */
 #endif /* _ASM_MIPS_FTRACE_H */
diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index 062dd4e6b954..85bbd967e05f 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -13,7 +13,6 @@
 #define _ASM_IO_H
 
 #include <linux/compiler.h>
-#include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/irqflags.h>
 
@@ -25,7 +24,6 @@
 #include <asm/cpu-features.h>
 #include <asm/page.h>
 #include <asm/pgtable-bits.h>
-#include <asm/processor.h>
 #include <asm/string.h>
 #include <mangle-port.h>
 
@@ -41,6 +39,11 @@
 # define __raw_ioswabq(a, x)	(x)
 # define ____raw_ioswabq(a, x)	(x)
 
+# define _ioswabb ioswabb
+# define _ioswabw ioswabw
+# define _ioswabl ioswabl
+# define _ioswabq ioswabq
+
 # define __relaxed_ioswabb ioswabb
 # define __relaxed_ioswabw ioswabw
 # define __relaxed_ioswabl ioswabl
@@ -115,23 +118,6 @@ static inline phys_addr_t virt_to_phys(const volatile void *x)
 }
 
 /*
- *     phys_to_virt    -       map physical address to virtual
- *     @address: address to remap
- *
- *     The returned virtual address is a current CPU mapping for
- *     the memory address given. It is only valid to use this function on
- *     addresses that have a kernel mapping
- *
- *     This function does not handle bus mappings for DMA transfers. In
- *     almost all conceivable cases a device driver should not be using
- *     this function
- */
-static inline void * phys_to_virt(unsigned long address)
-{
-	return __va(address);
-}
-
-/*
  * ISA I/O bus memory addresses are 1:1 with the physical address.
  */
 static inline unsigned long isa_virt_to_bus(volatile void *address)
@@ -139,11 +125,6 @@ static inline unsigned long isa_virt_to_bus(volatile void *address)
 	return virt_to_phys(address);
 }
 
-static inline void *isa_bus_to_virt(unsigned long address)
-{
-	return phys_to_virt(address);
-}
-
 /*
  * Change "struct page" to physical address.
  */
@@ -166,7 +147,6 @@ void iounmap(const volatile void __iomem *addr);
  */
 #define ioremap(offset, size)						\
 	ioremap_prot((offset), (size), _CACHE_UNCACHED)
-#define ioremap_uc		ioremap
 
 /*
  * ioremap_cache -	map bus memory into CPU space
@@ -207,8 +187,6 @@ void iounmap(const volatile void __iomem *addr);
 #define ioremap_wc(offset, size)					\
 	ioremap_prot((offset), (size), boot_cpu_data.writecombine)
 
-#include <asm-generic/iomap.h>
-
 #if defined(CONFIG_CPU_CAVIUM_OCTEON)
 #define war_io_reorder_wmb()		wmb()
 #else
@@ -296,9 +274,9 @@ static inline type pfx##read##bwlq(const volatile void __iomem *mem)	\
 	return pfx##ioswab##bwlq(__mem, __val);				\
 }
 
-#define __BUILD_IOPORT_SINGLE(pfx, bwlq, type, barrier, relax, p)	\
+#define __BUILD_IOPORT_SINGLE(pfx, bwlq, type, barrier, relax)		\
 									\
-static inline void pfx##out##bwlq##p(type val, unsigned long port)	\
+static inline void pfx##out##bwlq(type val, unsigned long port)		\
 {									\
 	volatile type *__addr;						\
 	type __val;							\
@@ -318,7 +296,7 @@ static inline void pfx##out##bwlq##p(type val, unsigned long port)	\
 	*__addr = __val;						\
 }									\
 									\
-static inline type pfx##in##bwlq##p(unsigned long port)			\
+static inline type pfx##in##bwlq(unsigned long port)			\
 {									\
 	volatile type *__addr;						\
 	type __val;							\
@@ -360,11 +338,10 @@ __BUILD_MEMORY_PFX(__mem_, q, u64, 0)
 #endif
 
 #define __BUILD_IOPORT_PFX(bus, bwlq, type)				\
-	__BUILD_IOPORT_SINGLE(bus, bwlq, type, 1, 0,)			\
-	__BUILD_IOPORT_SINGLE(bus, bwlq, type, 1, 0, _p)
+	__BUILD_IOPORT_SINGLE(bus, bwlq, type, 1, 0)
 
 #define BUILDIO_IOPORT(bwlq, type)					\
-	__BUILD_IOPORT_PFX(, bwlq, type)				\
+	__BUILD_IOPORT_PFX(_, bwlq, type)				\
 	__BUILD_IOPORT_PFX(__mem_, bwlq, type)
 
 BUILDIO_IOPORT(b, u8)
@@ -412,14 +389,6 @@ __BUILDIO(q, u64)
 #define writeq_be(val, addr)						\
 	__raw_writeq(cpu_to_be64((val)), (__force unsigned *)(addr))
 
-/*
- * Some code tests for these symbols
- */
-#ifdef CONFIG_64BIT
-#define readq				readq
-#define writeq				writeq
-#endif
-
 #define __BUILD_MEMORY_STRING(bwlq, type)				\
 									\
 static inline void writes##bwlq(volatile void __iomem *mem,		\
@@ -480,18 +449,6 @@ BUILDSTRING(l, u32)
 BUILDSTRING(q, u64)
 #endif
 
-static inline void memset_io(volatile void __iomem *addr, unsigned char val, int count)
-{
-	memset((void __force *) addr, val, count);
-}
-static inline void memcpy_fromio(void *dst, const volatile void __iomem *src, int count)
-{
-	memcpy(dst, (void __force *) src, count);
-}
-static inline void memcpy_toio(volatile void __iomem *dst, const void *src, int count)
-{
-	memcpy((void __force *) dst, src, count);
-}
 
 /*
  * The caches on some architectures aren't dma-coherent and have need to
@@ -548,13 +505,66 @@ extern void (*_dma_cache_inv)(unsigned long start, unsigned long size);
 #define csr_out32(v, a) (*(volatile u32 *)((unsigned long)(a) + __CSR_32_ADJUST) = (v))
 #define csr_in32(a)    (*(volatile u32 *)((unsigned long)(a) + __CSR_32_ADJUST))
 
-/*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p)	__va(p)
-#define unxlate_dev_mem_ptr(p, v) do { } while (0)
+#define __raw_readb __raw_readb
+#define __raw_readw __raw_readw
+#define __raw_readl __raw_readl
+#ifdef CONFIG_64BIT
+#define __raw_readq __raw_readq
+#endif
+#define __raw_writeb __raw_writeb
+#define __raw_writew __raw_writew
+#define __raw_writel __raw_writel
+#ifdef CONFIG_64BIT
+#define __raw_writeq __raw_writeq
+#endif
+
+#define readb readb
+#define readw readw
+#define readl readl
+#ifdef CONFIG_64BIT
+#define readq readq
+#endif
+#define writeb writeb
+#define writew writew
+#define writel writel
+#ifdef CONFIG_64BIT
+#define writeq writeq
+#endif
+
+#define readsb readsb
+#define readsw readsw
+#define readsl readsl
+#ifdef CONFIG_64BIT
+#define readsq readsq
+#endif
+#define writesb writesb
+#define writesw writesw
+#define writesl writesl
+#ifdef CONFIG_64BIT
+#define writesq writesq
+#endif
+
+#define _inb _inb
+#define _inw _inw
+#define _inl _inl
+#define insb insb
+#define insw insw
+#define insl insl
+
+#define _outb _outb
+#define _outw _outw
+#define _outl _outl
+#define outsb outsb
+#define outsw outsw
+#define outsl outsl
 
 void __ioread64_copy(void *to, const void __iomem *from, size_t count);
 
+#include <asm-generic/io.h>
+
+static inline void *isa_bus_to_virt(unsigned long address)
+{
+	return phys_to_virt(address);
+}
+
 #endif /* _ASM_IO_H */
diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h
index c5c6864e64bc..081be98c71ef 100644
--- a/arch/mips/include/asm/jump_label.h
+++ b/arch/mips/include/asm/jump_label.h
@@ -15,6 +15,9 @@
 #include <linux/types.h>
 #include <asm/isa-rev.h>
 
+struct module;
+extern void jump_label_apply_nops(struct module *mod);
+
 #define JUMP_LABEL_NOP_SIZE 4
 
 #ifdef CONFIG_64BIT
diff --git a/arch/mips/include/asm/kexec.h b/arch/mips/include/asm/kexec.h
index d6d5fa5cc31d..69e579e41e66 100644
--- a/arch/mips/include/asm/kexec.h
+++ b/arch/mips/include/asm/kexec.h
@@ -31,7 +31,7 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
 		prepare_frametrace(newregs);
 }
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 struct kimage;
 extern unsigned long kexec_args[4];
 extern int (*_machine_kexec_prepare)(struct kimage *);
diff --git a/arch/mips/include/asm/mach-loongson64/boot_param.h b/arch/mips/include/asm/mach-loongson64/boot_param.h
index 035b1a69e2d0..e007edd6b60a 100644
--- a/arch/mips/include/asm/mach-loongson64/boot_param.h
+++ b/arch/mips/include/asm/mach-loongson64/boot_param.h
@@ -14,7 +14,11 @@
 #define ADAPTER_ROM		8
 #define ACPI_TABLE		9
 #define SMBIOS_TABLE		10
-#define MAX_MEMORY_TYPE		11
+#define UMA_VIDEO_RAM		11
+#define VUMA_VIDEO_RAM		12
+#define MAX_MEMORY_TYPE		13
+
+#define MEM_SIZE_IS_IN_BYTES	(1 << 31)
 
 #define LOONGSON3_BOOT_MEM_MAP_MAX 128
 struct efi_memory_map_loongson {
@@ -117,7 +121,8 @@ struct irq_source_routing_table {
 	u64 pci_io_start_addr;
 	u64 pci_io_end_addr;
 	u64 pci_config_addr;
-	u32 dma_mask_bits;
+	u16 dma_mask_bits;
+	u16 dma_noncoherent;
 } __packed;
 
 struct interface_info {
diff --git a/arch/mips/include/asm/mach-loongson64/mmzone.h b/arch/mips/include/asm/mach-loongson64/mmzone.h
index ebb1deaa77b9..a3d65d37b8b5 100644
--- a/arch/mips/include/asm/mach-loongson64/mmzone.h
+++ b/arch/mips/include/asm/mach-loongson64/mmzone.h
@@ -18,7 +18,6 @@ extern struct pglist_data *__node_data[];
 
 #define NODE_DATA(n)		(__node_data[n])
 
-extern void setup_zero_pages(void);
 extern void __init prom_init_numa_memory(void);
 
 #endif /* _ASM_MACH_MMZONE_H */
diff --git a/arch/mips/include/asm/mmiowb.h b/arch/mips/include/asm/mmiowb.h
index a40824e3ef8e..cf27752fd220 100644
--- a/arch/mips/include/asm/mmiowb.h
+++ b/arch/mips/include/asm/mmiowb.h
@@ -2,9 +2,9 @@
 #ifndef _ASM_MMIOWB_H
 #define _ASM_MMIOWB_H
 
-#include <asm/io.h>
+#include <asm/barrier.h>
 
-#define mmiowb()	iobarrier_w()
+#define mmiowb()	wmb()
 
 #include <asm-generic/mmiowb.h>
 
diff --git a/arch/mips/include/asm/mmzone.h b/arch/mips/include/asm/mmzone.h
index 602a21aee9d4..14226ea42036 100644
--- a/arch/mips/include/asm/mmzone.h
+++ b/arch/mips/include/asm/mmzone.h
@@ -20,4 +20,6 @@
 #define nid_to_addrbase(nid) 0
 #endif
 
+extern void setup_zero_pages(void);
+
 #endif /* _ASM_MMZONE_H_ */
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 430b208c0130..e27a4c83c548 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -655,6 +655,7 @@ static inline pmd_t pmd_mkwrite_novma(pmd_t pmd)
 	return pmd;
 }
 
+#define pmd_dirty pmd_dirty
 static inline int pmd_dirty(pmd_t pmd)
 {
 	return !!(pmd_val(pmd) & _PAGE_MODIFIED);
diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index ae2cd37a38f0..ca7662cc65a7 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -402,4 +402,6 @@ extern int mips_set_process_fp_mode(struct task_struct *task,
 #define GET_FP_MODE(task)		mips_get_process_fp_mode(task)
 #define SET_FP_MODE(task,value)		mips_set_process_fp_mode(task, value)
 
+void show_registers(struct pt_regs *regs);
+
 #endif /* _ASM_PROCESSOR_H */
diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h
index 431a1c9d53fc..da1cd1bbdbc5 100644
--- a/arch/mips/include/asm/r4kcache.h
+++ b/arch/mips/include/asm/r4kcache.h
@@ -24,6 +24,10 @@
 #include <asm/mmzone.h>
 #include <asm/unroll.h>
 
+extern void r5k_sc_init(void);
+extern void rm7k_sc_init(void);
+extern int mips_sc_init(void);
+
 extern void (*r4k_blast_dcache)(void);
 extern void (*r4k_blast_icache)(void);
 
diff --git a/arch/mips/include/asm/setup.h b/arch/mips/include/asm/setup.h
index 8c56b862fd9c..4dce41138bad 100644
--- a/arch/mips/include/asm/setup.h
+++ b/arch/mips/include/asm/setup.h
@@ -27,5 +27,6 @@ extern unsigned long ebase;
 extern unsigned int hwrena;
 extern void per_cpu_trap_init(bool);
 extern void cpu_cache_init(void);
+extern void tlb_init(void);
 
 #endif /* __SETUP_H */
diff --git a/arch/mips/include/asm/signal.h b/arch/mips/include/asm/signal.h
index 23d6b8015c79..8de81ccef7ad 100644
--- a/arch/mips/include/asm/signal.h
+++ b/arch/mips/include/asm/signal.h
@@ -31,5 +31,6 @@ extern struct mips_abi mips_abi_32;
 
 extern int protected_save_fp_context(void __user *sc);
 extern int protected_restore_fp_context(void __user *sc);
+void do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags);
 
 #endif /* _ASM_SIGNAL_H */
diff --git a/arch/mips/include/asm/smp-ops.h b/arch/mips/include/asm/smp-ops.h
index 5719ff49eff1..1617b207723f 100644
--- a/arch/mips/include/asm/smp-ops.h
+++ b/arch/mips/include/asm/smp-ops.h
@@ -13,8 +13,6 @@
 
 #include <linux/errno.h>
 
-#include <asm/mips-cps.h>
-
 #ifdef CONFIG_SMP
 
 #include <linux/cpumask.h>
@@ -35,7 +33,7 @@ struct plat_smp_ops {
 	void (*cpu_die)(unsigned int cpu);
 	void (*cleanup_dead_cpu)(unsigned cpu);
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	void (*kexec_nonboot_cpu)(void);
 #endif
 };
diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h
index a40d8c0e4b87..bc2c240f414b 100644
--- a/arch/mips/include/asm/smp.h
+++ b/arch/mips/include/asm/smp.h
@@ -11,13 +11,11 @@
 #ifndef __ASM_SMP_H
 #define __ASM_SMP_H
 
-#include <linux/bitops.h>
+#include <linux/compiler.h>
 #include <linux/linkage.h>
-#include <linux/smp.h>
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 
-#include <linux/atomic.h>
 #include <asm/smp-ops.h>
 
 extern int smp_num_siblings;
@@ -63,6 +61,8 @@ extern asmlinkage void smp_bootstrap(void);
 
 extern void calculate_cpu_foreign_map(void);
 
+asmlinkage void start_secondary(void);
+
 /*
  * this function sends a 'reschedule' IPI to another CPU.
  * it goes straight through and wastes no time serializing
@@ -93,7 +93,7 @@ static inline void __cpu_die(unsigned int cpu)
 extern void __noreturn play_dead(void);
 #endif
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 static inline void kexec_nonboot_cpu(void)
 {
 	extern const struct plat_smp_ops *mp_ops;	/* private */
diff --git a/arch/mips/include/asm/spram.h b/arch/mips/include/asm/spram.h
index 373f2a5d495d..9f6a2cb1943a 100644
--- a/arch/mips/include/asm/spram.h
+++ b/arch/mips/include/asm/spram.h
@@ -3,7 +3,7 @@
 #define _MIPS_SPRAM_H
 
 #if defined(CONFIG_MIPS_SPRAM)
-extern __init void spram_config(void);
+extern void spram_config(void);
 #else
 static inline void spram_config(void) { }
 #endif /* CONFIG_MIPS_SPRAM */
diff --git a/arch/mips/include/asm/syscalls.h b/arch/mips/include/asm/syscalls.h
new file mode 100644
index 000000000000..59f9c0c9fa0a
--- /dev/null
+++ b/arch/mips/include/asm/syscalls.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ASM_MIPS_SYSCALLS_H
+#define _ASM_MIPS_SYSCALLS_H
+
+#include <linux/linkage.h>
+#include <linux/compat.h>
+
+asmlinkage void sys_sigreturn(void);
+asmlinkage void sys_rt_sigreturn(void);
+asmlinkage int sysm_pipe(void);
+asmlinkage long mipsmt_sys_sched_setaffinity(pid_t pid, unsigned int len,
+                                     unsigned long __user *user_mask_ptr);
+asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len,
+                                     unsigned long __user *user_mask_ptr);
+asmlinkage long sys32_fallocate(int fd, int mode, unsigned offset_a2,
+				unsigned offset_a3, unsigned len_a4,
+				unsigned len_a5);
+asmlinkage long sys32_fadvise64_64(int fd, int __pad,
+				   unsigned long a2, unsigned long a3,
+				   unsigned long a4, unsigned long a5,
+				   int flags);
+asmlinkage ssize_t sys32_readahead(int fd, u32 pad0, u64 a2, u64 a3,
+				   size_t count);
+asmlinkage long sys32_sync_file_range(int fd, int __pad,
+				      unsigned long a2, unsigned long a3,
+				      unsigned long a4, unsigned long a5,
+				      int flags);
+asmlinkage void sys32_rt_sigreturn(void);
+asmlinkage void sys32_sigreturn(void);
+asmlinkage int sys32_sigsuspend(compat_sigset_t __user *uset);
+asmlinkage void sysn32_rt_sigreturn(void);
+
+#endif
diff --git a/arch/mips/include/asm/tlbex.h b/arch/mips/include/asm/tlbex.h
index 6d97e23f30ab..24a2d06cc1c3 100644
--- a/arch/mips/include/asm/tlbex.h
+++ b/arch/mips/include/asm/tlbex.h
@@ -23,6 +23,7 @@ void build_update_entries(u32 **p, unsigned int tmp, unsigned int ptep);
 void build_tlb_write_entry(u32 **p, struct uasm_label **l,
 			   struct uasm_reloc **r,
 			   enum tlb_write_entry wmode);
+void build_tlb_refill_handler(void);
 
 extern void handle_tlbl(void);
 extern char handle_tlbl_end[];
diff --git a/arch/mips/include/asm/traps.h b/arch/mips/include/asm/traps.h
index 15cde638b407..2a8a258730c9 100644
--- a/arch/mips/include/asm/traps.h
+++ b/arch/mips/include/asm/traps.h
@@ -39,4 +39,30 @@ extern char except_vec_nmi[];
 	register_nmi_notifier(&fn##_nb);				\
 })
 
+asmlinkage void do_ade(struct pt_regs *regs);
+asmlinkage void do_be(struct pt_regs *regs);
+asmlinkage void do_ov(struct pt_regs *regs);
+asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31);
+asmlinkage void do_bp(struct pt_regs *regs);
+asmlinkage void do_tr(struct pt_regs *regs);
+asmlinkage void do_ri(struct pt_regs *regs);
+asmlinkage void do_cpu(struct pt_regs *regs);
+asmlinkage void do_msa_fpe(struct pt_regs *regs, unsigned int msacsr);
+asmlinkage void do_msa(struct pt_regs *regs);
+asmlinkage void do_mdmx(struct pt_regs *regs);
+asmlinkage void do_watch(struct pt_regs *regs);
+asmlinkage void do_mcheck(struct pt_regs *regs);
+asmlinkage void do_mt(struct pt_regs *regs);
+asmlinkage void do_dsp(struct pt_regs *regs);
+asmlinkage void do_reserved(struct pt_regs *regs);
+asmlinkage void do_ftlb(void);
+asmlinkage void do_gsexc(struct pt_regs *regs, u32 diag1);
+asmlinkage void do_daddi_ov(struct pt_regs *regs);
+asmlinkage void do_page_fault(struct pt_regs *regs,
+	unsigned long write, unsigned long address);
+
+asmlinkage void cache_parity_error(void);
+asmlinkage void ejtag_exception_handler(struct pt_regs *regs);
+asmlinkage void __noreturn nmi_exception_handler(struct pt_regs *regs);
+
 #endif /* _ASM_TRAPS_H */
diff --git a/arch/mips/include/asm/uasm.h b/arch/mips/include/asm/uasm.h
index 296bcf31abb5..b43bfd445252 100644
--- a/arch/mips/include/asm/uasm.h
+++ b/arch/mips/include/asm/uasm.h
@@ -193,9 +193,7 @@ struct uasm_label {
 
 void uasm_build_label(struct uasm_label **lab, u32 *addr,
 			int lid);
-#ifdef CONFIG_64BIT
 int uasm_in_compat_space_p(long addr);
-#endif
 int uasm_rel_hi(long val);
 int uasm_rel_lo(long val);
 void UASM_i_LA_mostly(u32 **buf, unsigned int rs, long addr);
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index 853a43ee4b44..ecf3278a32f7 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -90,7 +90,7 @@ obj-$(CONFIG_GPIO_TXX9)		+= gpio_txx9.o
 
 obj-$(CONFIG_RELOCATABLE)	+= relocate.o
 
-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o crash.o
+obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec.o relocate_kernel.o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 obj-$(CONFIG_EARLY_PRINTK_8250)	+= early_printk_8250.o
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index b406d8bfb15a..de7460c3a72e 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -179,7 +179,6 @@ void __init check_bugs32(void)
 static inline int cpu_has_confreg(void)
 {
 #ifdef CONFIG_CPU_R3000
-	extern unsigned long r3k_cache_size(unsigned long);
 	unsigned long size1, size2;
 	unsigned long cfg = read_c0_conf();
 
diff --git a/arch/mips/kernel/cpu-r3k-probe.c b/arch/mips/kernel/cpu-r3k-probe.c
index be93469c0e0e..0c826f729f75 100644
--- a/arch/mips/kernel/cpu-r3k-probe.c
+++ b/arch/mips/kernel/cpu-r3k-probe.c
@@ -42,7 +42,6 @@ void __init check_bugs32(void)
 static inline int cpu_has_confreg(void)
 {
 #ifdef CONFIG_CPU_R3000
-	extern unsigned long r3k_cache_size(unsigned long);
 	unsigned long size1, size2;
 	unsigned long cfg = read_c0_conf();
 
diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c
index 6b61be486303..a0c0a7a654e9 100644
--- a/arch/mips/kernel/linux32.c
+++ b/arch/mips/kernel/linux32.c
@@ -42,6 +42,7 @@
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/mman.h>
+#include <asm/syscalls.h>
 
 #ifdef __MIPSEB__
 #define merge_64(r1, r2) ((((r1) & 0xffffffffUL) << 32) + ((r2) & 0xffffffffUL))
diff --git a/arch/mips/kernel/machine_kexec.c b/arch/mips/kernel/machine_kexec.c
index 432bfd3e7f22..4e3579bbd620 100644
--- a/arch/mips/kernel/machine_kexec.c
+++ b/arch/mips/kernel/machine_kexec.c
@@ -8,6 +8,7 @@
 #include <linux/mm.h>
 #include <linux/delay.h>
 #include <linux/libfdt.h>
+#include <linux/reboot.h>
 
 #include <asm/cacheflush.h>
 #include <asm/page.h>
diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c
index 3f00788b0871..84b3affb9de8 100644
--- a/arch/mips/kernel/mips-cm.c
+++ b/arch/mips/kernel/mips-cm.c
@@ -201,7 +201,7 @@ phys_addr_t __mips_cm_phys_base(void)
 phys_addr_t mips_cm_phys_base(void)
 	__attribute__((weak, alias("__mips_cm_phys_base")));
 
-phys_addr_t __mips_cm_l2sync_phys_base(void)
+static phys_addr_t __mips_cm_l2sync_phys_base(void)
 {
 	u32 base_reg;
 
diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c
index 67e130d3f038..10172fc4f627 100644
--- a/arch/mips/kernel/mips-mt-fpaff.c
+++ b/arch/mips/kernel/mips-mt-fpaff.c
@@ -15,6 +15,7 @@
 #include <linux/security.h>
 #include <linux/types.h>
 #include <linux/uaccess.h>
+#include <asm/syscalls.h>
 
 /*
  * CPU mask used to set process affinity for MT VPEs/TCs with FPUs
diff --git a/arch/mips/kernel/mips-mt.c b/arch/mips/kernel/mips-mt.c
index f88b7919f11f..c07d64438b5b 100644
--- a/arch/mips/kernel/mips-mt.c
+++ b/arch/mips/kernel/mips-mt.c
@@ -19,6 +19,7 @@
 #include <asm/mipsmtregs.h>
 #include <asm/r4kcache.h>
 #include <asm/cacheflush.h>
+#include <asm/mips_mt.h>
 
 int vpelimit;
 
diff --git a/arch/mips/kernel/module.c b/arch/mips/kernel/module.c
index 0c936cbf20c5..7b2fbaa9cac5 100644
--- a/arch/mips/kernel/module.c
+++ b/arch/mips/kernel/module.c
@@ -20,8 +20,7 @@
 #include <linux/kernel.h>
 #include <linux/spinlock.h>
 #include <linux/jump_label.h>
-
-extern void jump_label_apply_nops(struct module *mod);
+#include <asm/jump_label.h>
 
 struct mips_hi16 {
 	struct mips_hi16 *next;
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 5387ed0a5186..b630604c577f 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -121,6 +121,19 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	/*  Put the stack after the struct pt_regs.  */
 	childksp = (unsigned long) childregs;
 	p->thread.cp0_status = (read_c0_status() & ~(ST0_CU2|ST0_CU1)) | ST0_KERNEL_CUMASK;
+
+	/*
+	 * New tasks lose permission to use the fpu. This accelerates context
+	 * switching for most programs since they don't use the fpu.
+	 */
+	clear_tsk_thread_flag(p, TIF_USEDFPU);
+	clear_tsk_thread_flag(p, TIF_USEDMSA);
+	clear_tsk_thread_flag(p, TIF_MSA_CTX_LIVE);
+
+#ifdef CONFIG_MIPS_MT_FPAFF
+	clear_tsk_thread_flag(p, TIF_FPUBOUND);
+#endif /* CONFIG_MIPS_MT_FPAFF */
+
 	if (unlikely(args->fn)) {
 		/* kernel thread */
 		unsigned long status = p->thread.cp0_status;
@@ -149,20 +162,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	p->thread.reg29 = (unsigned long) childregs;
 	p->thread.reg31 = (unsigned long) ret_from_fork;
 
-	/*
-	 * New tasks lose permission to use the fpu. This accelerates context
-	 * switching for most programs since they don't use the fpu.
-	 */
 	childregs->cp0_status &= ~(ST0_CU2|ST0_CU1);
 
-	clear_tsk_thread_flag(p, TIF_USEDFPU);
-	clear_tsk_thread_flag(p, TIF_USEDMSA);
-	clear_tsk_thread_flag(p, TIF_MSA_CTX_LIVE);
-
-#ifdef CONFIG_MIPS_MT_FPAFF
-	clear_tsk_thread_flag(p, TIF_FPUBOUND);
-#endif /* CONFIG_MIPS_MT_FPAFF */
-
 #ifdef CONFIG_MIPS_FP_SUPPORT
 	atomic_set(&p->thread.bd_emu_frame, BD_EMUFRAME_NONE);
 #endif
diff --git a/arch/mips/kernel/r4k-bugs64.c b/arch/mips/kernel/r4k-bugs64.c
index 6ffefb2c6971..1e300330078d 100644
--- a/arch/mips/kernel/r4k-bugs64.c
+++ b/arch/mips/kernel/r4k-bugs64.c
@@ -14,6 +14,7 @@
 #include <asm/fpu.h>
 #include <asm/mipsregs.h>
 #include <asm/setup.h>
+#include <asm/traps.h>
 
 static char bug64hit[] __initdata =
 	"reliable operation impossible!\n%s";
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 2d2ca024bd47..328426c3ed6f 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -42,6 +42,7 @@
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/smp-ops.h>
+#include <asm/mips-cps.h>
 #include <asm/prom.h>
 #include <asm/fw/fw.h>
 
diff --git a/arch/mips/kernel/signal-common.h b/arch/mips/kernel/signal-common.h
index f50d48435c68..136eb20ac024 100644
--- a/arch/mips/kernel/signal-common.h
+++ b/arch/mips/kernel/signal-common.h
@@ -40,4 +40,7 @@ _restore_fp_context(void __user *fpregs, void __user *csr);
 extern asmlinkage int _save_msa_all_upper(void __user *buf);
 extern asmlinkage int _restore_msa_all_upper(void __user *buf);
 
+extern int setup_sigcontext(struct pt_regs *, struct sigcontext __user *);
+extern int restore_sigcontext(struct pt_regs *, struct sigcontext __user *);
+
 #endif	/* __SIGNAL_COMMON_H */
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index 479999b7f2de..ccbf580827f6 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -38,6 +38,7 @@
 #include <asm/dsp.h>
 #include <asm/inst.h>
 #include <asm/msa.h>
+#include <asm/syscalls.h>
 
 #include "signal-common.h"
 
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index 59b8965433c2..73081d4ee8c1 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -18,6 +18,7 @@
 #include <asm/compat-signal.h>
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
+#include <asm/syscalls.h>
 
 #include "signal-common.h"
 
diff --git a/arch/mips/kernel/signal_n32.c b/arch/mips/kernel/signal_n32.c
index cfc77b69420a..139d2596b0d4 100644
--- a/arch/mips/kernel/signal_n32.c
+++ b/arch/mips/kernel/signal_n32.c
@@ -24,6 +24,7 @@
 #include <asm/ucontext.h>
 #include <asm/fpu.h>
 #include <asm/cpu-features.h>
+#include <asm/syscalls.h>
 
 #include "signal-common.h"
 
@@ -32,9 +33,6 @@
  */
 #define __NR_N32_restart_syscall	6214
 
-extern int setup_sigcontext(struct pt_regs *, struct sigcontext __user *);
-extern int restore_sigcontext(struct pt_regs *, struct sigcontext __user *);
-
 struct ucontextn32 {
 	u32		    uc_flags;
 	s32		    uc_link;
diff --git a/arch/mips/kernel/signal_o32.c b/arch/mips/kernel/signal_o32.c
index 299a7a28ca33..4f0458459650 100644
--- a/arch/mips/kernel/signal_o32.c
+++ b/arch/mips/kernel/signal_o32.c
@@ -19,6 +19,7 @@
 #include <asm/dsp.h>
 #include <asm/sim.h>
 #include <asm/unistd.h>
+#include <asm/syscalls.h>
 
 #include "signal-common.h"
 
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index c074ecce3fbf..b3dbf9ecb0d6 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -434,7 +434,7 @@ const struct plat_smp_ops bmips43xx_smp_ops = {
 	.cpu_disable		= bmips_cpu_disable,
 	.cpu_die		= bmips_cpu_die,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu	= kexec_nonboot_cpu_jump,
 #endif
 };
@@ -451,7 +451,7 @@ const struct plat_smp_ops bmips5000_smp_ops = {
 	.cpu_disable		= bmips_cpu_disable,
 	.cpu_die		= bmips_cpu_die,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu	= kexec_nonboot_cpu_jump,
 #endif
 };
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index dd55d59b88db..f6c37d407f36 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -392,7 +392,7 @@ static void cps_smp_finish(void)
 	local_irq_enable();
 }
 
-#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_KEXEC)
+#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_KEXEC_CORE)
 
 enum cpu_death {
 	CPU_DEATH_HALT,
@@ -429,7 +429,7 @@ static void cps_shutdown_this_cpu(enum cpu_death death)
 	}
 }
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 
 static void cps_kexec_nonboot_cpu(void)
 {
@@ -439,9 +439,9 @@ static void cps_kexec_nonboot_cpu(void)
 		cps_shutdown_this_cpu(CPU_DEATH_POWER);
 }
 
-#endif /* CONFIG_KEXEC */
+#endif /* CONFIG_KEXEC_CORE */
 
-#endif /* CONFIG_HOTPLUG_CPU || CONFIG_KEXEC */
+#endif /* CONFIG_HOTPLUG_CPU || CONFIG_KEXEC_CORE */
 
 #ifdef CONFIG_HOTPLUG_CPU
 
@@ -610,7 +610,7 @@ static const struct plat_smp_ops cps_smp_ops = {
 	.cpu_die		= cps_cpu_die,
 	.cleanup_dead_cpu	= cps_cleanup_dead_cpu,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu	= cps_kexec_nonboot_cpu,
 #endif
 };
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 8fbef537fb88..0b53d35a116e 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -10,6 +10,7 @@
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/profile.h>
 #include <linux/smp.h>
 #include <linux/spinlock.h>
 #include <linux/threads.h>
@@ -351,10 +352,11 @@ early_initcall(mips_smp_ipi_init);
  */
 asmlinkage void start_secondary(void)
 {
-	unsigned int cpu;
+	unsigned int cpu = raw_smp_processor_id();
 
 	cpu_probe();
 	per_cpu_trap_init(false);
+	rcutree_report_cpu_starting(cpu);
 	mips_clockevent_init();
 	mp_ops->init_secondary();
 	cpu_report();
@@ -366,7 +368,6 @@ asmlinkage void start_secondary(void)
 	 */
 
 	calibrate_delay();
-	cpu = smp_processor_id();
 	cpu_data[cpu].udelay_val = loops_per_jiffy;
 
 	set_cpu_sibling_map(cpu);
@@ -468,11 +469,13 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 	return 0;
 }
 
+#ifdef CONFIG_PROFILING
 /* Not really SMP stuff ... */
 int setup_profiling_timer(unsigned int multiplier)
 {
 	return 0;
 }
+#endif
 
 static void flush_tlb_all_ipi(void *info)
 {
diff --git a/arch/mips/kernel/spram.c b/arch/mips/kernel/spram.c
index d5d96214cce5..71c7e5e27567 100644
--- a/arch/mips/kernel/spram.c
+++ b/arch/mips/kernel/spram.c
@@ -12,6 +12,7 @@
 #include <asm/mipsregs.h>
 #include <asm/r4kcache.h>
 #include <asm/hazards.h>
+#include <asm/spram.h>
 
 /*
  * These definitions are correct for the 24K/34K/74K SPRAM sample
diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c
index ae93a607ddf7..1bfc34a2e5b3 100644
--- a/arch/mips/kernel/syscall.c
+++ b/arch/mips/kernel/syscall.c
@@ -39,6 +39,7 @@
 #include <asm/shmparam.h>
 #include <asm/sync.h>
 #include <asm/sysmips.h>
+#include <asm/syscalls.h>
 #include <asm/switch_to.h>
 
 /*
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index a842b41c8e06..83cfc9eb6b88 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -395,3 +395,8 @@
 454	n32	futex_wake			sys_futex_wake
 455	n32	futex_wait			sys_futex_wait
 456	n32	futex_requeue			sys_futex_requeue
+457	n32	statmount			sys_statmount
+458	n32	listmount			sys_listmount
+459	n32	lsm_get_self_attr		sys_lsm_get_self_attr
+460	n32	lsm_set_self_attr		sys_lsm_set_self_attr
+461	n32	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index 116ff501bf92..532b855df589 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -371,3 +371,8 @@
 454	n64	futex_wake			sys_futex_wake
 455	n64	futex_wait			sys_futex_wait
 456	n64	futex_requeue			sys_futex_requeue
+457	n64	statmount			sys_statmount
+458	n64	listmount			sys_listmount
+459	n64	lsm_get_self_attr		sys_lsm_get_self_attr
+460	n64	lsm_set_self_attr		sys_lsm_set_self_attr
+461	n64	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 525cc54bc63b..f45c9530ea93 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -444,3 +444,8 @@
 454	o32	futex_wake			sys_futex_wake
 455	o32	futex_wait			sys_futex_wait
 456	o32	futex_requeue			sys_futex_requeue
+457	o32	statmount			sys_statmount
+458	o32	listmount			sys_listmount
+459	o32	lsm_get_self_attr		sys_lsm_get_self_attr
+460	o32	lsm_set_self_attr		sys_lsm_set_self_attr
+461	o32	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 246c6a6b0261..c58c0c3c5b40 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -2157,8 +2157,6 @@ void *set_vi_handler(int n, vi_handler_t addr)
 	return set_vi_srs_handler(n, addr, 0);
 }
 
-extern void tlb_init(void);
-
 /*
  * Timer interrupt
  */
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index f4cf94e92ec3..db652c99b72e 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -91,6 +91,7 @@
 #include <asm/inst.h>
 #include <asm/unaligned-emul.h>
 #include <asm/mmu_context.h>
+#include <asm/traps.h>
 #include <linux/uaccess.h>
 
 #include "access-helper.h"
diff --git a/arch/mips/loongson64/env.c b/arch/mips/loongson64/env.c
index c961e2999f15..ef3750a6ffac 100644
--- a/arch/mips/loongson64/env.c
+++ b/arch/mips/loongson64/env.c
@@ -13,6 +13,8 @@
  * Copyright (C) 2009 Lemote Inc.
  * Author: Wu Zhangjin, wuzhangjin@gmail.com
  */
+
+#include <linux/dma-map-ops.h>
 #include <linux/export.h>
 #include <linux/pci_ids.h>
 #include <asm/bootinfo.h>
@@ -147,8 +149,14 @@ void __init prom_lefi_init_env(void)
 
 	loongson_sysconf.dma_mask_bits = eirq_source->dma_mask_bits;
 	if (loongson_sysconf.dma_mask_bits < 32 ||
-		loongson_sysconf.dma_mask_bits > 64)
+			loongson_sysconf.dma_mask_bits > 64) {
 		loongson_sysconf.dma_mask_bits = 32;
+		dma_default_coherent = true;
+	} else {
+		dma_default_coherent = !eirq_source->dma_noncoherent;
+	}
+
+	pr_info("Firmware: Coherent DMA: %s\n", dma_default_coherent ? "on" : "off");
 
 	loongson_sysconf.restart_addr = boot_p->reset_system.ResetWarm;
 	loongson_sysconf.poweroff_addr = boot_p->reset_system.Shutdown;
diff --git a/arch/mips/loongson64/init.c b/arch/mips/loongson64/init.c
index ee8de1735b7c..f25caa6aa9d3 100644
--- a/arch/mips/loongson64/init.c
+++ b/arch/mips/loongson64/init.c
@@ -49,8 +49,7 @@ void virtual_early_config(void)
 void __init szmem(unsigned int node)
 {
 	u32 i, mem_type;
-	static unsigned long num_physpages;
-	u64 node_id, node_psize, start_pfn, end_pfn, mem_start, mem_size;
+	phys_addr_t node_id, mem_start, mem_size;
 
 	/* Otherwise come from DTB */
 	if (loongson_sysconf.fw_interface != LOONGSON_LEFI)
@@ -64,30 +63,46 @@ void __init szmem(unsigned int node)
 
 		mem_type = loongson_memmap->map[i].mem_type;
 		mem_size = loongson_memmap->map[i].mem_size;
-		mem_start = loongson_memmap->map[i].mem_start;
+
+		/* Memory size comes in MB if MEM_SIZE_IS_IN_BYTES not set */
+		if (mem_size & MEM_SIZE_IS_IN_BYTES)
+			mem_size &= ~MEM_SIZE_IS_IN_BYTES;
+		else
+			mem_size = mem_size << 20;
+
+		mem_start = (node_id << 44) | loongson_memmap->map[i].mem_start;
 
 		switch (mem_type) {
 		case SYSTEM_RAM_LOW:
 		case SYSTEM_RAM_HIGH:
-			start_pfn = ((node_id << 44) + mem_start) >> PAGE_SHIFT;
-			node_psize = (mem_size << 20) >> PAGE_SHIFT;
-			end_pfn  = start_pfn + node_psize;
-			num_physpages += node_psize;
-			pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n",
-				(u32)node_id, mem_type, mem_start, mem_size);
-			pr_info("       start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n",
-				start_pfn, end_pfn, num_physpages);
-			memblock_add_node(PFN_PHYS(start_pfn),
-					  PFN_PHYS(node_psize), node,
+		case UMA_VIDEO_RAM:
+			pr_info("Node %d, mem_type:%d\t[%pa], %pa bytes usable\n",
+				(u32)node_id, mem_type, &mem_start, &mem_size);
+			memblock_add_node(mem_start, mem_size, node,
 					  MEMBLOCK_NONE);
 			break;
 		case SYSTEM_RAM_RESERVED:
-			pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n",
-				(u32)node_id, mem_type, mem_start, mem_size);
-			memblock_reserve(((node_id << 44) + mem_start), mem_size << 20);
+		case VIDEO_ROM:
+		case ADAPTER_ROM:
+		case ACPI_TABLE:
+		case SMBIOS_TABLE:
+			pr_info("Node %d, mem_type:%d\t[%pa], %pa bytes reserved\n",
+				(u32)node_id, mem_type, &mem_start, &mem_size);
+			memblock_reserve(mem_start, mem_size);
+			break;
+		/* We should not reserve VUMA_VIDEO_RAM as it overlaps with MMIO */
+		case VUMA_VIDEO_RAM:
+		default:
+			pr_info("Node %d, mem_type:%d\t[%pa], %pa bytes unhandled\n",
+				(u32)node_id, mem_type, &mem_start, &mem_size);
 			break;
 		}
 	}
+
+	/* Reserve vgabios if it comes from firmware */
+	if (loongson_sysconf.vgabios_addr)
+		memblock_reserve(virt_to_phys((void *)loongson_sysconf.vgabios_addr),
+				SZ_256K);
 }
 
 #ifndef CONFIG_NUMA
diff --git a/arch/mips/loongson64/reset.c b/arch/mips/loongson64/reset.c
index e420800043b0..e01c8d4a805a 100644
--- a/arch/mips/loongson64/reset.c
+++ b/arch/mips/loongson64/reset.c
@@ -53,7 +53,7 @@ static void loongson_halt(void)
 	}
 }
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 
 /* 0X80000000~0X80200000 is safe */
 #define MAX_ARGS	64
@@ -158,7 +158,7 @@ static int __init mips_reboot_setup(void)
 	_machine_halt = loongson_halt;
 	pm_power_off = loongson_poweroff;
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	kexec_argv = kmalloc(KEXEC_ARGV_SIZE, GFP_KERNEL);
 	if (WARN_ON(!kexec_argv))
 		return -ENOMEM;
diff --git a/arch/mips/loongson64/smp.c b/arch/mips/loongson64/smp.c
index e015a26a40f7..498bdc1bb0ed 100644
--- a/arch/mips/loongson64/smp.c
+++ b/arch/mips/loongson64/smp.c
@@ -864,7 +864,7 @@ const struct plat_smp_ops loongson3_smp_ops = {
 	.cpu_disable = loongson3_cpu_disable,
 	.cpu_die = loongson3_cpu_die,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu = kexec_nonboot_cpu_jump,
 #endif
 };
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 187d1c16361c..b45bf026ee55 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -1485,10 +1485,6 @@ static void loongson3_sc_init(void)
 	return;
 }
 
-extern int r5k_sc_init(void);
-extern int rm7k_sc_init(void);
-extern int mips_sc_init(void);
-
 static void setup_scache(void)
 {
 	struct cpuinfo_mips *c = &current_cpu_data;
@@ -1828,7 +1824,7 @@ static struct notifier_block r4k_cache_pm_notifier_block = {
 	.notifier_call = r4k_cache_pm_notifier,
 };
 
-int __init r4k_cache_init_pm(void)
+static int __init r4k_cache_init_pm(void)
 {
 	return cpu_pm_register_notifier(&r4k_cache_pm_notifier_block);
 }
diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c
index 7f830634dbe7..df1ced4fc3b5 100644
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@@ -205,22 +205,13 @@ static inline void setup_protection_map(void)
 
 void cpu_cache_init(void)
 {
-	if (cpu_has_3k_cache) {
-		extern void __weak r3k_cache_init(void);
-
+	if (IS_ENABLED(CONFIG_CPU_R3000) && cpu_has_3k_cache)
 		r3k_cache_init();
-	}
-	if (cpu_has_4k_cache) {
-		extern void __weak r4k_cache_init(void);
-
+	if (IS_ENABLED(CONFIG_CPU_R4K_CACHE_TLB) && cpu_has_4k_cache)
 		r4k_cache_init();
-	}
-
-	if (cpu_has_octeon_cache) {
-		extern void __weak octeon_cache_init(void);
 
+	if (IS_ENABLED(CONFIG_CPU_CAVIUM_OCTEON) && cpu_has_octeon_cache)
 		octeon_cache_init();
-	}
 
 	setup_protection_map();
 }
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index d7878208bd3f..aaa9a242ebba 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -26,6 +26,7 @@
 #include <asm/mmu_context.h>
 #include <asm/ptrace.h>
 #include <asm/highmem.h>		/* For VMALLOC_END */
+#include <asm/traps.h>
 #include <linux/kdebug.h>
 
 int show_unhandled_signals = 1;
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 5dcb525a8995..c2e0e5aebe90 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -38,6 +38,7 @@
 #include <asm/dma.h>
 #include <asm/maar.h>
 #include <asm/mmu_context.h>
+#include <asm/mmzone.h>
 #include <asm/sections.h>
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
diff --git a/arch/mips/mm/pgtable-64.c b/arch/mips/mm/pgtable-64.c
index c76d21f7dffb..1e544827dea9 100644
--- a/arch/mips/mm/pgtable-64.c
+++ b/arch/mips/mm/pgtable-64.c
@@ -89,6 +89,7 @@ void pud_init(void *addr)
 }
 #endif
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 pmd_t mk_pmd(struct page *page, pgprot_t prot)
 {
 	pmd_t pmd;
@@ -103,6 +104,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 {
 	*pmdp = pmd;
 }
+#endif
 
 void __init pagetable_init(void)
 {
diff --git a/arch/mips/mm/tlb-r3k.c b/arch/mips/mm/tlb-r3k.c
index 53dfa2b9316b..f6db65410c65 100644
--- a/arch/mips/mm/tlb-r3k.c
+++ b/arch/mips/mm/tlb-r3k.c
@@ -23,11 +23,11 @@
 #include <asm/io.h>
 #include <asm/bootinfo.h>
 #include <asm/cpu.h>
+#include <asm/setup.h>
+#include <asm/tlbex.h>
 
 #undef DEBUG_TLB
 
-extern void build_tlb_refill_handler(void);
-
 /* CP0 hazard avoidance. */
 #define BARRIER				\
 	__asm__ __volatile__(		\
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index 93c2d695588a..7e2a0011a6fb 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -22,9 +22,9 @@
 #include <asm/hazards.h>
 #include <asm/mmu_context.h>
 #include <asm/tlb.h>
+#include <asm/tlbex.h>
 #include <asm/tlbmisc.h>
-
-extern void build_tlb_refill_handler(void);
+#include <asm/setup.h>
 
 /*
  * LOONGSON-2 has a 4 entry itlb which is a subset of jtlb, LOONGSON-3 has
@@ -458,6 +458,7 @@ EXPORT_SYMBOL(has_transparent_hugepage);
 
 int temp_tlb_entry;
 
+#ifndef CONFIG_64BIT
 __init int add_temporary_entry(unsigned long entrylo0, unsigned long entrylo1,
 			       unsigned long entryhi, unsigned long pagemask)
 {
@@ -496,6 +497,7 @@ out:
 	local_irq_restore(flags);
 	return ret;
 }
+#endif
 
 static int ntlb;
 static int __init set_ntlb(char *str)
diff --git a/arch/mips/pci/pci-ip27.c b/arch/mips/pci/pci-ip27.c
index d85cbf84e41c..973faea61cad 100644
--- a/arch/mips/pci/pci-ip27.c
+++ b/arch/mips/pci/pci-ip27.c
@@ -7,6 +7,9 @@
  * Copyright (C) 1999, 2000, 04 Ralf Baechle (ralf@linux-mips.org)
  * Copyright (C) 1999, 2000 Silicon Graphics, Inc.
  */
+
+#include <linux/io.h>
+
 #include <asm/sn/addrs.h>
 #include <asm/sn/types.h>
 #include <asm/sn/klconfig.h>
diff --git a/arch/mips/power/cpu.c b/arch/mips/power/cpu.c
index a15e29dfc7b3..d8ef7778e535 100644
--- a/arch/mips/power/cpu.c
+++ b/arch/mips/power/cpu.c
@@ -6,6 +6,7 @@
  * Author: Hu Hongbing <huhb@lemote.com>
  *	   Wu Zhangjin <wuzhangjin@gmail.com>
  */
+#include <linux/suspend.h>
 #include <asm/sections.h>
 #include <asm/fpu.h>
 #include <asm/dsp.h>
diff --git a/arch/mips/power/hibernate.c b/arch/mips/power/hibernate.c
index 94ab17c3c49d..192879e76c85 100644
--- a/arch/mips/power/hibernate.c
+++ b/arch/mips/power/hibernate.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/suspend.h>
 #include <asm/tlbflush.h>
 
 extern int restore_image(void);
diff --git a/arch/mips/vdso/vgettimeofday.c b/arch/mips/vdso/vgettimeofday.c
index 6b83b6376a4b..604afea3f336 100644
--- a/arch/mips/vdso/vgettimeofday.c
+++ b/arch/mips/vdso/vgettimeofday.c
@@ -9,6 +9,7 @@
  */
 #include <linux/time.h>
 #include <linux/types.h>
+#include <vdso/gettime.h>
 
 #if _MIPS_SIM != _MIPS_SIM_ABI64
 int __vdso_clock_gettime(clockid_t clock,
diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
index d54464021a61..58d9565dc2c7 100644
--- a/arch/nios2/Kconfig
+++ b/arch/nios2/Kconfig
@@ -50,7 +50,7 @@ config ARCH_FORCE_MAX_ORDER
 	default "10"
 	help
 	  The kernel page allocator limits the size of maximal physically
-	  contiguous allocations. The limit is called MAX_ORDER and it
+	  contiguous allocations. The limit is called MAX_PAGE_ORDER and it
 	  defines the maximal power of two of number of pages that can be
 	  allocated as a single contiguous block. This option allows
 	  overriding the default setting when ability to allocate very
diff --git a/arch/nios2/include/asm/traps.h b/arch/nios2/include/asm/traps.h
index 82a48473280d..afd77bef01c6 100644
--- a/arch/nios2/include/asm/traps.h
+++ b/arch/nios2/include/asm/traps.h
@@ -14,6 +14,8 @@
 
 #ifndef __ASSEMBLY__
 void _exception(int signo, struct pt_regs *regs, int code, unsigned long addr);
+void do_page_fault(struct pt_regs *regs, unsigned long cause,
+		   unsigned long address);
 #endif
 
 #endif /* _ASM_NIOS2_TRAPS_H */
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index fd69dfa0cdab..d14ccc948a29 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -115,9 +115,12 @@ config ARCH_HAS_ILOG2_U64
 	default n
 
 config GENERIC_BUG
-	bool
-	default y
+	def_bool y
 	depends on BUG
+	select GENERIC_BUG_RELATIVE_POINTERS if 64BIT
+
+config GENERIC_BUG_RELATIVE_POINTERS
+	bool
 
 config GENERIC_HWEIGHT
 	bool
@@ -140,11 +143,11 @@ config ARCH_MMAP_RND_COMPAT_BITS_MIN
 	default 8
 
 config ARCH_MMAP_RND_BITS_MAX
-	default 24 if 64BIT
-	default 17
+	default 18 if 64BIT
+	default 13
 
 config ARCH_MMAP_RND_COMPAT_BITS_MAX
-	default 17
+	default 13
 
 # unless you want to implement ACPI on PA-RISC ... ;-)
 config PM
diff --git a/arch/parisc/include/asm/alternative.h b/arch/parisc/include/asm/alternative.h
index 1ed45fd085d3..1eb488f25b83 100644
--- a/arch/parisc/include/asm/alternative.h
+++ b/arch/parisc/include/asm/alternative.h
@@ -34,7 +34,8 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end,
 
 /* Alternative SMP implementation. */
 #define ALTERNATIVE(cond, replacement)		"!0:"	\
-	".section .altinstructions, \"aw\"	!"	\
+	".section .altinstructions, \"a\"	!"	\
+	".align 4				!"	\
 	".word (0b-4-.)				!"	\
 	".hword 1, " __stringify(cond) "	!"	\
 	".word " __stringify(replacement) "	!"	\
@@ -44,7 +45,8 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end,
 
 /* to replace one single instructions by a new instruction */
 #define ALTERNATIVE(from, to, cond, replacement)\
-	.section .altinstructions, "aw"	!	\
+	.section .altinstructions, "a"	!	\
+	.align 4			!	\
 	.word (from - .)		!	\
 	.hword (to - from)/4, cond	!	\
 	.word replacement		!	\
@@ -52,7 +54,8 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end,
 
 /* to replace multiple instructions by new code */
 #define ALTERNATIVE_CODE(from, num_instructions, cond, new_instr_ptr)\
-	.section .altinstructions, "aw"	!	\
+	.section .altinstructions, "a"	!	\
+	.align 4			!	\
 	.word (from - .)		!	\
 	.hword -num_instructions, cond	!	\
 	.word (new_instr_ptr - .)	!	\
diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h
index 75677b526b2b..74d17d7e759d 100644
--- a/arch/parisc/include/asm/assembly.h
+++ b/arch/parisc/include/asm/assembly.h
@@ -574,6 +574,7 @@
 	 */
 #define ASM_EXCEPTIONTABLE_ENTRY(fault_addr, except_addr)	\
 	.section __ex_table,"aw"			!	\
+	.align 4					!	\
 	.word (fault_addr - .), (except_addr - .)	!	\
 	.previous
 
diff --git a/arch/parisc/include/asm/bug.h b/arch/parisc/include/asm/bug.h
index 4b6d60b94124..833555f74ffa 100644
--- a/arch/parisc/include/asm/bug.h
+++ b/arch/parisc/include/asm/bug.h
@@ -17,24 +17,27 @@
 #define	PARISC_BUG_BREAK_ASM	"break 0x1f, 0x1fff"
 #define	PARISC_BUG_BREAK_INSN	0x03ffe01f  /* PARISC_BUG_BREAK_ASM */
 
-#if defined(CONFIG_64BIT)
-#define ASM_WORD_INSN		".dword\t"
+#ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
+# define __BUG_REL(val) ".word " __stringify(val) " - ."
 #else
-#define ASM_WORD_INSN		".word\t"
+# define __BUG_REL(val) ".word " __stringify(val)
 #endif
 
+
 #ifdef CONFIG_DEBUG_BUGVERBOSE
 #define BUG()								\
 	do {								\
 		asm volatile("\n"					\
 			     "1:\t" PARISC_BUG_BREAK_ASM "\n"		\
-			     "\t.pushsection __bug_table,\"aw\"\n"	\
-			     "2:\t" ASM_WORD_INSN "1b, %c0\n"		\
-			     "\t.short %c1, %c2\n"			\
-			     "\t.org 2b+%c3\n"				\
+			     "\t.pushsection __bug_table,\"a\"\n"	\
+			     "\t.align 4\n"				\
+			     "2:\t" __BUG_REL(1b) "\n"			\
+			     "\t" __BUG_REL(%c0)  "\n"			\
+			     "\t.short %1, %2\n"			\
+			     "\t.blockz %3-2*4-2*2\n"			\
 			     "\t.popsection"				\
 			     : : "i" (__FILE__), "i" (__LINE__),	\
-			     "i" (0), "i" (sizeof(struct bug_entry)) ); \
+			     "i" (0), "i" (sizeof(struct bug_entry)) );	\
 		unreachable();						\
 	} while(0)
 
@@ -51,10 +54,12 @@
 	do {								\
 		asm volatile("\n"					\
 			     "1:\t" PARISC_BUG_BREAK_ASM "\n"		\
-			     "\t.pushsection __bug_table,\"aw\"\n"	\
-			     "2:\t" ASM_WORD_INSN "1b, %c0\n"		\
-			     "\t.short %c1, %c2\n"			\
-			     "\t.org 2b+%c3\n"				\
+			     "\t.pushsection __bug_table,\"a\"\n"	\
+			     "\t.align 4\n"				\
+			     "2:\t" __BUG_REL(1b) "\n"			\
+			     "\t" __BUG_REL(%c0)  "\n"			\
+			     "\t.short %1, %2\n"			\
+			     "\t.blockz %3-2*4-2*2\n"			\
 			     "\t.popsection"				\
 			     : : "i" (__FILE__), "i" (__LINE__),	\
 			     "i" (BUGFLAG_WARNING|(flags)),		\
@@ -65,10 +70,11 @@
 	do {								\
 		asm volatile("\n"					\
 			     "1:\t" PARISC_BUG_BREAK_ASM "\n"		\
-			     "\t.pushsection __bug_table,\"aw\"\n"	\
-			     "2:\t" ASM_WORD_INSN "1b\n"		\
-			     "\t.short %c0\n"				\
-			     "\t.org 2b+%c1\n"				\
+			     "\t.pushsection __bug_table,\"a\"\n"	\
+			     "\t.align 4\n"				\
+			     "2:\t" __BUG_REL(1b) "\n"			\
+			     "\t.short %0\n"				\
+			     "\t.blockz %1-4-2\n"			\
 			     "\t.popsection"				\
 			     : : "i" (BUGFLAG_WARNING|(flags)),		\
 			     "i" (sizeof(struct bug_entry)) );		\
diff --git a/arch/parisc/include/asm/elf.h b/arch/parisc/include/asm/elf.h
index 140eaa97bf21..2d73d3c3cd37 100644
--- a/arch/parisc/include/asm/elf.h
+++ b/arch/parisc/include/asm/elf.h
@@ -349,15 +349,7 @@ struct pt_regs;	/* forward declaration... */
 
 #define ELF_HWCAP	0
 
-/* Masks for stack and mmap randomization */
-#define BRK_RND_MASK	(is_32bit_task() ? 0x07ffUL : 0x3ffffUL)
-#define MMAP_RND_MASK	(is_32bit_task() ? 0x1fffUL : 0x3ffffUL)
-#define STACK_RND_MASK	MMAP_RND_MASK
-
-struct mm_struct;
-extern unsigned long arch_randomize_brk(struct mm_struct *);
-#define arch_randomize_brk arch_randomize_brk
-
+#define STACK_RND_MASK	0x7ff	/* 8MB of VA */
 
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
 struct linux_binprm;
diff --git a/arch/parisc/include/asm/io.h b/arch/parisc/include/asm/io.h
index 366537042465..a63190af2f05 100644
--- a/arch/parisc/include/asm/io.h
+++ b/arch/parisc/include/asm/io.h
@@ -132,8 +132,6 @@ static inline void gsc_writeq(unsigned long long val, unsigned long addr)
 
 #define ioremap_wc(addr, size)  \
 	ioremap_prot((addr), (size), _PAGE_IOREMAP)
-#define ioremap_uc(addr, size)  \
-	ioremap_prot((addr), (size), _PAGE_IOREMAP)
 
 #define pci_iounmap			pci_iounmap
 
@@ -267,12 +265,6 @@ extern void iowrite64be(u64 val, void __iomem *addr);
 #define iowrite16_rep iowrite16_rep
 #define iowrite32_rep iowrite32_rep
 
-/*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p)	__va(p)
-
 extern int devmem_is_allowed(unsigned long pfn);
 
 #include <asm-generic/io.h>
diff --git a/arch/parisc/include/asm/jump_label.h b/arch/parisc/include/asm/jump_label.h
index af2a598bc0f8..94428798b6aa 100644
--- a/arch/parisc/include/asm/jump_label.h
+++ b/arch/parisc/include/asm/jump_label.h
@@ -15,10 +15,12 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran
 	asm_volatile_goto("1:\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
+		 ".align %1\n\t"
 		 ".word 1b - ., %l[l_yes] - .\n\t"
 		 __stringify(ASM_ULONG_INSN) " %c0 - .\n\t"
 		 ".popsection\n\t"
-		 : :  "i" (&((char *)key)[branch]) :  : l_yes);
+		 : : "i" (&((char *)key)[branch]), "i" (sizeof(long))
+		 : : l_yes);
 
 	return false;
 l_yes:
@@ -30,10 +32,12 @@ static __always_inline bool arch_static_branch_jump(struct static_key *key, bool
 	asm_volatile_goto("1:\n\t"
 		 "b,n %l[l_yes]\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
+		 ".align %1\n\t"
 		 ".word 1b - ., %l[l_yes] - .\n\t"
 		 __stringify(ASM_ULONG_INSN) " %c0 - .\n\t"
 		 ".popsection\n\t"
-		 : :  "i" (&((char *)key)[branch]) :  : l_yes);
+		 : : "i" (&((char *)key)[branch]), "i" (sizeof(long))
+		 : : l_yes);
 
 	return false;
 l_yes:
diff --git a/arch/parisc/include/asm/ldcw.h b/arch/parisc/include/asm/ldcw.h
index ee9e071859b2..47ebc4c91eaf 100644
--- a/arch/parisc/include/asm/ldcw.h
+++ b/arch/parisc/include/asm/ldcw.h
@@ -55,7 +55,7 @@
 })
 
 #ifdef CONFIG_SMP
-# define __lock_aligned __section(".data..lock_aligned")
+# define __lock_aligned __section(".data..lock_aligned") __aligned(16)
 #endif
 
 #endif /* __PARISC_LDCW_H */
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index c05d121cf5d0..982aca20f56f 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -47,6 +47,8 @@
 
 #ifndef __ASSEMBLY__
 
+struct rlimit;
+unsigned long mmap_upper_limit(struct rlimit *rlim_stack);
 unsigned long calc_max_stack_size(unsigned long stack_max);
 
 /*
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index 2bf660eabe42..4165079898d9 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -41,6 +41,7 @@ struct exception_table_entry {
 
 #define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr )\
 	".section __ex_table,\"aw\"\n"			   \
+	".align 4\n"					   \
 	".word (" #fault_addr " - .), (" #except_addr " - .)\n\t" \
 	".previous\n"
 
diff --git a/arch/parisc/include/uapi/asm/errno.h b/arch/parisc/include/uapi/asm/errno.h
index 87245c584784..8d94739d75c6 100644
--- a/arch/parisc/include/uapi/asm/errno.h
+++ b/arch/parisc/include/uapi/asm/errno.h
@@ -75,7 +75,6 @@
 
 /* We now return you to your regularly scheduled HPUX. */
 
-#define ENOSYM		215	/* symbol does not exist in executable */
 #define	ENOTSOCK	216	/* Socket operation on non-socket */
 #define	EDESTADDRREQ	217	/* Destination address required */
 #define	EMSGSIZE	218	/* Message too long */
@@ -101,7 +100,6 @@
 #define	ETIMEDOUT	238	/* Connection timed out */
 #define	ECONNREFUSED	239	/* Connection refused */
 #define	EREFUSED	ECONNREFUSED	/* for HP's NFS apparently */
-#define	EREMOTERELEASE	240	/* Remote peer released connection */
 #define	EHOSTDOWN	241	/* Host is down */
 #define	EHOSTUNREACH	242	/* No route to host */
 
diff --git a/arch/parisc/kernel/kexec_file.c b/arch/parisc/kernel/kexec_file.c
index 8c534204f0fd..3fc82130b6c3 100644
--- a/arch/parisc/kernel/kexec_file.c
+++ b/arch/parisc/kernel/kexec_file.c
@@ -38,8 +38,8 @@ static void *elf_load(struct kimage *image, char *kernel_buf,
 	for (i = 0; i < image->nr_segments; i++)
 		image->segment[i].mem = __pa(image->segment[i].mem);
 
-	pr_debug("Loaded the kernel at 0x%lx, entry at 0x%lx\n",
-		 kernel_load_addr, image->start);
+	kexec_dprintk("Loaded the kernel at 0x%lx, entry at 0x%lx\n",
+		      kernel_load_addr, image->start);
 
 	if (initrd != NULL) {
 		kbuf.buffer = initrd;
@@ -51,7 +51,7 @@ static void *elf_load(struct kimage *image, char *kernel_buf,
 		if (ret)
 			goto out;
 
-		pr_debug("Loaded initrd at 0x%lx\n", kbuf.mem);
+		kexec_dprintk("Loaded initrd at 0x%lx\n", kbuf.mem);
 		image->arch.initrd_start = kbuf.mem;
 		image->arch.initrd_end = kbuf.mem + initrd_len;
 	}
@@ -68,7 +68,7 @@ static void *elf_load(struct kimage *image, char *kernel_buf,
 		if (ret)
 			goto out;
 
-		pr_debug("Loaded cmdline at 0x%lx\n", kbuf.mem);
+		kexec_dprintk("Loaded cmdline at 0x%lx\n", kbuf.mem);
 		image->arch.cmdline = kbuf.mem;
 	}
 out:
diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c
index 29e2750f86a4..e95a977ba5f3 100644
--- a/arch/parisc/kernel/processor.c
+++ b/arch/parisc/kernel/processor.c
@@ -383,7 +383,7 @@ show_cpuinfo (struct seq_file *m, void *v)
 	char cpu_name[60], *p;
 
 	/* strip PA path from CPU name to not confuse lscpu */
-	strlcpy(cpu_name, per_cpu(cpu_data, 0).dev->name, sizeof(cpu_name));
+	strscpy(cpu_name, per_cpu(cpu_data, 0).dev->name, sizeof(cpu_name));
 	p = strrchr(cpu_name, '[');
 	if (p)
 		*(--p) = 0;
diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index ab896eff7a1d..98af719d5f85 100644
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -77,7 +77,7 @@ unsigned long calc_max_stack_size(unsigned long stack_max)
  * indicating that "current" should be used instead of a passed-in
  * value from the exec bprm as done with arch_pick_mmap_layout().
  */
-static unsigned long mmap_upper_limit(struct rlimit *rlim_stack)
+unsigned long mmap_upper_limit(struct rlimit *rlim_stack)
 {
 	unsigned long stack_base;
 
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index a47798fed54e..b236a84c4e12 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -455,3 +455,8 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount
+459	common	lsm_get_self_attr		sys_lsm_get_self_attr
+460	common	lsm_set_self_attr		sys_lsm_set_self_attr
+461	common	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index 58694d1989c2..548051b0b4af 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -130,6 +130,7 @@ SECTIONS
 	RO_DATA(8)
 
 	/* unwind info */
+	. = ALIGN(4);
 	.PARISC.unwind : {
 		__start___unwind = .;
 		*(.PARISC.unwind)
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index a2a3e89f2d9a..f876af56e13f 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -33,6 +33,7 @@
 #include <asm/msgbuf.h>
 #include <asm/sparsemem.h>
 #include <asm/asm-offsets.h>
+#include <asm/shmbuf.h>
 
 extern int  data_start;
 extern void parisc_kernel_start(void);	/* Kernel entry point in head.S */
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 6f105ee4f3cf..414b978b8010 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -189,6 +189,7 @@ config PPC
 	select EDAC_ATOMIC_SCRUB
 	select EDAC_SUPPORT
 	select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY if ARCH_USING_PATCHABLE_FUNCTION_ENTRY
+	select FUNCTION_ALIGNMENT_4B
 	select GENERIC_ATOMIC64			if PPC32
 	select GENERIC_CLOCKEVENTS_BROADCAST	if SMP
 	select GENERIC_CMOS_UPDATE
@@ -608,10 +609,10 @@ config ARCH_SUPPORTS_KEXEC
 	def_bool PPC_BOOK3S || PPC_E500 || (44x && !SMP)
 
 config ARCH_SUPPORTS_KEXEC_FILE
-	def_bool PPC64 && CRYPTO=y && CRYPTO_SHA256=y
+	def_bool PPC64
 
 config ARCH_SUPPORTS_KEXEC_PURGATORY
-	def_bool KEXEC_FILE
+	def_bool y
 
 config ARCH_SELECTS_KEXEC_FILE
 	def_bool y
@@ -915,7 +916,7 @@ config ARCH_FORCE_MAX_ORDER
 	default "10"
 	help
 	  The kernel page allocator limits the size of maximal physically
-	  contiguous allocations. The limit is called MAX_ORDER and it
+	  contiguous allocations. The limit is called MAX_PAGE_ORDER and it
 	  defines the maximal power of two of number of pages that can be
 	  allocated as a single contiguous block. This option allows
 	  overriding the default setting when ability to allocate very
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index ea4033abc07d..8c80b154e814 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -271,7 +271,6 @@ config PPC_EARLY_DEBUG_USBGECKO
 config PPC_EARLY_DEBUG_PS3GELIC
 	bool "Early debugging through the PS3 Ethernet port"
 	depends on PPC_PS3
-	select PS3GELIC_UDBG
 	help
 	  Select this to enable early debugging for the PlayStation3 via
 	  UDP broadcasts sent out through the Ethernet port.
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index f19dbaa1d541..051247027da0 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -10,15 +10,26 @@
 # Rewritten by Cort Dougan and Paul Mackerras
 #
 
+ifdef cross_compiling
+  ifeq ($(CROSS_COMPILE),)
+    # Auto detect cross compiler prefix.
+    # Look for: (powerpc(64(le)?)?)(-unknown)?-linux(-gnu)?-
+    CC_ARCHES := powerpc powerpc64 powerpc64le
+    CC_SUFFIXES := linux linux-gnu unknown-linux-gnu
+    CROSS_COMPILE := $(call cc-cross-prefix, $(foreach a,$(CC_ARCHES), \
+                       $(foreach s,$(CC_SUFFIXES),$(a)-$(s)-)))
+  endif
+endif
+
 HAS_BIARCH	:= $(call cc-option-yn, -m32)
 
 # Set default 32 bits cross compilers for vdso and boot wrapper
 CROSS32_COMPILE ?=
 
 # If we're on a ppc/ppc64/ppc64le machine use that defconfig, otherwise just use
-# ppc64_defconfig because we have nothing better to go on.
+# ppc64le_defconfig because we have nothing better to go on.
 uname := $(shell uname -m)
-KBUILD_DEFCONFIG := $(if $(filter ppc%,$(uname)),$(uname),ppc64)_defconfig
+KBUILD_DEFCONFIG := $(if $(filter ppc%,$(uname)),$(uname),ppc64le)_defconfig
 
 new_nm := $(shell if $(NM) --help 2>&1 | grep -- '--synthetic' > /dev/null; then echo y; else echo n; fi)
 
@@ -161,7 +172,7 @@ CFLAGS-y += $(CONFIG_TUNE_CPU)
 
 asinstr := $(call as-instr,lis 9$(comma)foo@high,-DHAVE_AS_ATHIGH=1)
 
-KBUILD_CPPFLAGS	+= -I $(srctree)/arch/$(ARCH) $(asinstr)
+KBUILD_CPPFLAGS	+= -I $(srctree)/arch/powerpc $(asinstr)
 KBUILD_AFLAGS	+= $(AFLAGS-y)
 KBUILD_CFLAGS	+= $(call cc-option,-msoft-float)
 KBUILD_CFLAGS	+= $(CFLAGS-y)
@@ -232,7 +243,7 @@ BOOT_TARGETS2 := zImage% dtbImage% treeImage.% cuImage.% simpleImage.% uImage.%
 
 PHONY += $(BOOT_TARGETS1) $(BOOT_TARGETS2)
 
-boot := arch/$(ARCH)/boot
+boot := arch/powerpc/boot
 
 $(BOOT_TARGETS1): vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(patsubst %,$(boot)/%,$@)
@@ -336,7 +347,7 @@ PHONY += $(generated_configs)
 
 define archhelp
   echo '* zImage          - Build default images selected by kernel config'
-  echo '  zImage.*        - Compressed kernel image (arch/$(ARCH)/boot/zImage.*)'
+  echo '  zImage.*        - Compressed kernel image (arch/powerpc/boot/zImage.*)'
   echo '  uImage          - U-Boot native image format'
   echo '  cuImage.<dt>    - Backwards compatible U-Boot image for older'
   echo '                    versions which do not support device trees'
@@ -347,12 +358,12 @@ define archhelp
   echo '                    (your) ~/bin/$(INSTALLKERNEL) or'
   echo '                    (distribution) /sbin/$(INSTALLKERNEL) or'
   echo '                    install to $$(INSTALL_PATH) and run lilo'
-  echo '  *_defconfig     - Select default config from arch/$(ARCH)/configs'
+  echo '  *_defconfig     - Select default config from arch/powerpc/configs'
   echo ''
   echo '  Targets with <dt> embed a device tree blob inside the image'
   echo '  These targets support board with firmware that does not'
   echo '  support passing a device tree directly.  Replace <dt> with the'
-  echo '  name of a dts file from the arch/$(ARCH)/boot/dts/ directory'
+  echo '  name of a dts file from the arch/powerpc/boot/dts/ directory'
   echo '  (minus the .dts extension).'
   echo
   $(foreach cfg,$(generated_configs),
diff --git a/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
index d552044c5afc..aa5152ca8120 100644
--- a/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
@@ -367,45 +367,46 @@
 		reg = <0xf0000 0x1000>;
 		interrupts = <18 2 0 0>;
 		fsl,tmu-range = <0xb0000 0xa0026 0x80048 0x30061>;
-		fsl,tmu-calibration = <0x00000000 0x0000000f
-				       0x00000001 0x00000017
-				       0x00000002 0x0000001e
-				       0x00000003 0x00000026
-				       0x00000004 0x0000002e
-				       0x00000005 0x00000035
-				       0x00000006 0x0000003d
-				       0x00000007 0x00000044
-				       0x00000008 0x0000004c
-				       0x00000009 0x00000053
-				       0x0000000a 0x0000005b
-				       0x0000000b 0x00000064
-
-				       0x00010000 0x00000011
-				       0x00010001 0x0000001c
-				       0x00010002 0x00000024
-				       0x00010003 0x0000002b
-				       0x00010004 0x00000034
-				       0x00010005 0x00000039
-				       0x00010006 0x00000042
-				       0x00010007 0x0000004c
-				       0x00010008 0x00000051
-				       0x00010009 0x0000005a
-				       0x0001000a 0x00000063
-
-				       0x00020000 0x00000013
-				       0x00020001 0x00000019
-				       0x00020002 0x00000024
-				       0x00020003 0x0000002c
-				       0x00020004 0x00000035
-				       0x00020005 0x0000003d
-				       0x00020006 0x00000046
-				       0x00020007 0x00000050
-				       0x00020008 0x00000059
-
-				       0x00030000 0x00000002
-				       0x00030001 0x0000000d
-				       0x00030002 0x00000019
-				       0x00030003 0x00000024>;
+		fsl,tmu-calibration =
+				<0x00000000 0x0000000f>,
+				<0x00000001 0x00000017>,
+				<0x00000002 0x0000001e>,
+				<0x00000003 0x00000026>,
+				<0x00000004 0x0000002e>,
+				<0x00000005 0x00000035>,
+				<0x00000006 0x0000003d>,
+				<0x00000007 0x00000044>,
+				<0x00000008 0x0000004c>,
+				<0x00000009 0x00000053>,
+				<0x0000000a 0x0000005b>,
+				<0x0000000b 0x00000064>,
+
+				<0x00010000 0x00000011>,
+				<0x00010001 0x0000001c>,
+				<0x00010002 0x00000024>,
+				<0x00010003 0x0000002b>,
+				<0x00010004 0x00000034>,
+				<0x00010005 0x00000039>,
+				<0x00010006 0x00000042>,
+				<0x00010007 0x0000004c>,
+				<0x00010008 0x00000051>,
+				<0x00010009 0x0000005a>,
+				<0x0001000a 0x00000063>,
+
+				<0x00020000 0x00000013>,
+				<0x00020001 0x00000019>,
+				<0x00020002 0x00000024>,
+				<0x00020003 0x0000002c>,
+				<0x00020004 0x00000035>,
+				<0x00020005 0x0000003d>,
+				<0x00020006 0x00000046>,
+				<0x00020007 0x00000050>,
+				<0x00020008 0x00000059>,
+
+				<0x00030000 0x00000002>,
+				<0x00030001 0x0000000d>,
+				<0x00030002 0x00000019>,
+				<0x00030003 0x00000024>;
 		#thermal-sensor-cells = <1>;
 	};
 
diff --git a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
index ad0ab33336b8..776788623204 100644
--- a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
@@ -447,41 +447,42 @@
 		reg = <0xf0000 0x1000>;
 		interrupts = <18 2 0 0>;
 		fsl,tmu-range = <0xa0000 0x90026 0x8004a 0x1006a>;
-		fsl,tmu-calibration = <0x00000000 0x00000025
-				       0x00000001 0x00000028
-				       0x00000002 0x0000002d
-				       0x00000003 0x00000031
-				       0x00000004 0x00000036
-				       0x00000005 0x0000003a
-				       0x00000006 0x00000040
-				       0x00000007 0x00000044
-				       0x00000008 0x0000004a
-				       0x00000009 0x0000004f
-				       0x0000000a 0x00000054
-
-				       0x00010000 0x0000000d
-				       0x00010001 0x00000013
-				       0x00010002 0x00000019
-				       0x00010003 0x0000001f
-				       0x00010004 0x00000025
-				       0x00010005 0x0000002d
-				       0x00010006 0x00000033
-				       0x00010007 0x00000043
-				       0x00010008 0x0000004b
-				       0x00010009 0x00000053
-
-				       0x00020000 0x00000010
-				       0x00020001 0x00000017
-				       0x00020002 0x0000001f
-				       0x00020003 0x00000029
-				       0x00020004 0x00000031
-				       0x00020005 0x0000003c
-				       0x00020006 0x00000042
-				       0x00020007 0x0000004d
-				       0x00020008 0x00000056
-
-				       0x00030000 0x00000012
-				       0x00030001 0x0000001d>;
+		fsl,tmu-calibration =
+				<0x00000000 0x00000025>,
+				<0x00000001 0x00000028>,
+				<0x00000002 0x0000002d>,
+				<0x00000003 0x00000031>,
+				<0x00000004 0x00000036>,
+				<0x00000005 0x0000003a>,
+				<0x00000006 0x00000040>,
+				<0x00000007 0x00000044>,
+				<0x00000008 0x0000004a>,
+				<0x00000009 0x0000004f>,
+				<0x0000000a 0x00000054>,
+
+				<0x00010000 0x0000000d>,
+				<0x00010001 0x00000013>,
+				<0x00010002 0x00000019>,
+				<0x00010003 0x0000001f>,
+				<0x00010004 0x00000025>,
+				<0x00010005 0x0000002d>,
+				<0x00010006 0x00000033>,
+				<0x00010007 0x00000043>,
+				<0x00010008 0x0000004b>,
+				<0x00010009 0x00000053>,
+
+				<0x00020000 0x00000010>,
+				<0x00020001 0x00000017>,
+				<0x00020002 0x0000001f>,
+				<0x00020003 0x00000029>,
+				<0x00020004 0x00000031>,
+				<0x00020005 0x0000003c>,
+				<0x00020006 0x00000042>,
+				<0x00020007 0x0000004d>,
+				<0x00020008 0x00000056>,
+
+				<0x00030000 0x00000012>,
+				<0x00030001 0x0000001d>;
 		#thermal-sensor-cells = <1>;
 	};
 
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index 6e7b9e8fd225..544a65fda77b 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -92,6 +92,7 @@ CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
+CONFIG_MEM_SOFT_DIRTY=y
 CONFIG_ZONE_DEVICE=y
 CONFIG_NET=y
 CONFIG_PACKET=y
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index f279703425d4..66c7b28d7450 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -274,7 +274,6 @@ CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
-CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig
index 2b175ddf82f0..aa8bb0208bcc 100644
--- a/arch/powerpc/configs/ps3_defconfig
+++ b/arch/powerpc/configs/ps3_defconfig
@@ -24,6 +24,7 @@ CONFIG_PS3_VRAM=m
 CONFIG_PS3_LPM=m
 # CONFIG_PPC_OF_BOOT_TRAMPOLINE is not set
 CONFIG_KEXEC=y
+# CONFIG_PPC64_BIG_ENDIAN_ELF_ABI_V2 is not set
 CONFIG_PPC_4K_PAGES=y
 CONFIG_SCHED_SMT=y
 CONFIG_PM=y
diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig
index 8d3eacb50d56..9d44e6630908 100644
--- a/arch/powerpc/configs/skiroot_defconfig
+++ b/arch/powerpc/configs/skiroot_defconfig
@@ -301,7 +301,6 @@ CONFIG_WQ_WATCHDOG=y
 CONFIG_DEBUG_SG=y
 CONFIG_DEBUG_NOTIFIERS=y
 CONFIG_BUG_ON_DATA_CORRUPTION=y
-CONFIG_DEBUG_CREDENTIALS=y
 # CONFIG_FTRACE is not set
 CONFIG_XMON=y
 # CONFIG_RUNTIME_TESTING_MENU is not set
diff --git a/arch/powerpc/crypto/aes-gcm-p10-glue.c b/arch/powerpc/crypto/aes-gcm-p10-glue.c
index 4b6e899895e7..f62ee54076c0 100644
--- a/arch/powerpc/crypto/aes-gcm-p10-glue.c
+++ b/arch/powerpc/crypto/aes-gcm-p10-glue.c
@@ -37,7 +37,7 @@ asmlinkage void aes_p10_gcm_encrypt(u8 *in, u8 *out, size_t len,
 				    void *rkey, u8 *iv, void *Xi);
 asmlinkage void aes_p10_gcm_decrypt(u8 *in, u8 *out, size_t len,
 				    void *rkey, u8 *iv, void *Xi);
-asmlinkage void gcm_init_htable(unsigned char htable[256], unsigned char Xi[16]);
+asmlinkage void gcm_init_htable(unsigned char htable[], unsigned char Xi[]);
 asmlinkage void gcm_ghash_p10(unsigned char *Xi, unsigned char *Htable,
 		unsigned char *aad, unsigned int alen);
 
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index cb77eddca54b..927d585652bc 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -17,12 +17,6 @@
 #define _PAGE_EXEC		0x00001 /* execute permission */
 #define _PAGE_WRITE		0x00002 /* write access allowed */
 #define _PAGE_READ		0x00004	/* read access allowed */
-#define _PAGE_NA		_PAGE_PRIVILEGED
-#define _PAGE_NAX		_PAGE_EXEC
-#define _PAGE_RO		_PAGE_READ
-#define _PAGE_ROX		(_PAGE_READ | _PAGE_EXEC)
-#define _PAGE_RW		(_PAGE_READ | _PAGE_WRITE)
-#define _PAGE_RWX		(_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)
 #define _PAGE_PRIVILEGED	0x00008 /* kernel access only */
 #define _PAGE_SAO		0x00010 /* Strong access order */
 #define _PAGE_NON_IDEMPOTENT	0x00020 /* non idempotent memory */
@@ -532,8 +526,8 @@ static inline bool pte_user(pte_t pte)
 static inline bool pte_access_permitted(pte_t pte, bool write)
 {
 	/*
-	 * _PAGE_READ is needed for any access and will be
-	 * cleared for PROT_NONE
+	 * _PAGE_READ is needed for any access and will be cleared for
+	 * PROT_NONE. Execute-only mapping via PROT_EXEC also returns false.
 	 */
 	if (!pte_present(pte) || !pte_user(pte) || !pte_read(pte))
 		return false;
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h
index 1950c1b825b4..fd642b729775 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h
@@ -158,11 +158,6 @@ static inline void flush_tlb_fix_spurious_fault(struct vm_area_struct *vma,
 	 */
 }
 
-static inline bool __pte_protnone(unsigned long pte)
-{
-	return (pte & (pgprot_val(PAGE_NONE) | _PAGE_RWX)) == pgprot_val(PAGE_NONE);
-}
-
 static inline bool __pte_flags_need_flush(unsigned long oldval,
 					  unsigned long newval)
 {
@@ -179,8 +174,8 @@ static inline bool __pte_flags_need_flush(unsigned long oldval,
 	/*
 	 * We do not expect kernel mappings or non-PTEs or not-present PTEs.
 	 */
-	VM_WARN_ON_ONCE(!__pte_protnone(oldval) && oldval & _PAGE_PRIVILEGED);
-	VM_WARN_ON_ONCE(!__pte_protnone(newval) && newval & _PAGE_PRIVILEGED);
+	VM_WARN_ON_ONCE(oldval & _PAGE_PRIVILEGED);
+	VM_WARN_ON_ONCE(newval & _PAGE_PRIVILEGED);
 	VM_WARN_ON_ONCE(!(oldval & _PAGE_PTE));
 	VM_WARN_ON_ONCE(!(newval & _PAGE_PTE));
 	VM_WARN_ON_ONCE(!(oldval & _PAGE_PRESENT));
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index 9e5a39b6a311..1ebd2ca97f12 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -25,7 +25,7 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 	if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY))
 		addr += MCOUNT_INSN_SIZE;
 
-       return addr;
+	return addr;
 }
 
 unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index ddb99e982917..a41e542ba94d 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -349,7 +349,16 @@
 #define H_GET_ENERGY_SCALE_INFO	0x450
 #define H_PKS_SIGNED_UPDATE	0x454
 #define H_WATCHDOG		0x45C
-#define MAX_HCALL_OPCODE	H_WATCHDOG
+#define H_GUEST_GET_CAPABILITIES 0x460
+#define H_GUEST_SET_CAPABILITIES 0x464
+#define H_GUEST_CREATE		0x470
+#define H_GUEST_CREATE_VCPU	0x474
+#define H_GUEST_GET_STATE	0x478
+#define H_GUEST_SET_STATE	0x47C
+#define H_GUEST_RUN_VCPU	0x480
+#define H_GUEST_COPY_MEMORY	0x484
+#define H_GUEST_DELETE		0x488
+#define MAX_HCALL_OPCODE	H_GUEST_DELETE
 
 /* Scope args for H_SCM_UNBIND_ALL */
 #define H_UNBIND_SCOPE_ALL (0x1)
@@ -393,15 +402,6 @@
 #define H_ENTER_NESTED		0xF804
 #define H_TLB_INVALIDATE	0xF808
 #define H_COPY_TOFROM_GUEST	0xF80C
-#define H_GUEST_GET_CAPABILITIES 0x460
-#define H_GUEST_SET_CAPABILITIES 0x464
-#define H_GUEST_CREATE		0x470
-#define H_GUEST_CREATE_VCPU	0x474
-#define H_GUEST_GET_STATE	0x478
-#define H_GUEST_SET_STATE	0x47C
-#define H_GUEST_RUN_VCPU	0x480
-#define H_GUEST_COPY_MEMORY	0x484
-#define H_GUEST_DELETE		0x488
 
 /* Flags for H_SVM_PAGE_IN */
 #define H_PAGE_IN_SHARED        0x1
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index 5220274a6277..08c550ed49be 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -710,12 +710,6 @@ static inline void name at					\
 #define memcpy_toio memcpy_toio
 
 /*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p)	__va(p)
-
-/*
  * We don't do relaxed operations yet, at least not with this semantic
  */
 #define readb_relaxed(addr)	readb(addr)
@@ -900,7 +894,6 @@ void __iomem *ioremap_wt(phys_addr_t address, unsigned long size);
 #endif
 
 void __iomem *ioremap_coherent(phys_addr_t address, unsigned long size);
-#define ioremap_uc(addr, size)		ioremap((addr), (size))
 #define ioremap_cache(addr, size) \
 	ioremap_prot((addr), (size), pgprot_val(PAGE_KERNEL))
 
diff --git a/arch/powerpc/include/asm/irq_work.h b/arch/powerpc/include/asm/irq_work.h
index b8b0be8f1a07..c6d3078bd8c3 100644
--- a/arch/powerpc/include/asm/irq_work.h
+++ b/arch/powerpc/include/asm/irq_work.h
@@ -6,6 +6,5 @@ static inline bool arch_irq_work_has_interrupt(void)
 {
 	return true;
 }
-extern void arch_irq_work_raise(void);
 
 #endif /* _ASM_POWERPC_IRQ_WORK_H */
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 4f527d09c92b..3e1e2a698c9e 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -302,6 +302,7 @@ void kvmhv_nested_exit(void);
 void kvmhv_vm_nested_init(struct kvm *kvm);
 long kvmhv_set_partition_table(struct kvm_vcpu *vcpu);
 long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu);
+void kvmhv_flush_lpid(u64 lpid);
 void kvmhv_set_ptbl_entry(u64 lpid, u64 dw0, u64 dw1);
 void kvmhv_release_all_nested(struct kvm *kvm);
 long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu);
@@ -593,13 +594,17 @@ static inline u##size kvmppc_get_##reg(struct kvm_vcpu *vcpu)		\
 
 
 KVMPPC_BOOK3S_VCORE_ACCESSOR(vtb, 64, KVMPPC_GSID_VTB)
-KVMPPC_BOOK3S_VCORE_ACCESSOR(tb_offset, 64, KVMPPC_GSID_TB_OFFSET)
 KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(arch_compat, 32, KVMPPC_GSID_LOGICAL_PVR)
 KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(lpcr, 64, KVMPPC_GSID_LPCR)
+KVMPPC_BOOK3S_VCORE_ACCESSOR_SET(tb_offset, 64, KVMPPC_GSID_TB_OFFSET)
+
+static inline u64 kvmppc_get_tb_offset(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.vcore->tb_offset;
+}
 
 static inline u64 kvmppc_get_dec_expires(struct kvm_vcpu *vcpu)
 {
-	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_TB_OFFSET) < 0);
 	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_DEC_EXPIRY_TB) < 0);
 	return vcpu->arch.dec_expires;
 }
@@ -607,7 +612,6 @@ static inline u64 kvmppc_get_dec_expires(struct kvm_vcpu *vcpu)
 static inline void kvmppc_set_dec_expires(struct kvm_vcpu *vcpu, u64 val)
 {
 	vcpu->arch.dec_expires = val;
-	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_TB_OFFSET) < 0);
 	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_DEC_EXPIRY_TB);
 }
 
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 2477021bff54..d8729ec81ca0 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -682,6 +682,7 @@ void kvmhv_nestedv2_vcpu_free(struct kvm_vcpu *vcpu, struct kvmhv_nestedv2_io *i
 int kvmhv_nestedv2_flush_vcpu(struct kvm_vcpu *vcpu, u64 time_limit);
 int kvmhv_nestedv2_set_ptbl_entry(unsigned long lpid, u64 dw0, u64 dw1);
 int kvmhv_nestedv2_parse_output(struct kvm_vcpu *vcpu);
+int kvmhv_nestedv2_set_vpa(struct kvm_vcpu *vcpu, unsigned long vpa);
 
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
diff --git a/arch/powerpc/include/asm/linkage.h b/arch/powerpc/include/asm/linkage.h
index b88d1d2cf304..b71b9582e754 100644
--- a/arch/powerpc/include/asm/linkage.h
+++ b/arch/powerpc/include/asm/linkage.h
@@ -4,9 +4,6 @@
 
 #include <asm/types.h>
 
-#define __ALIGN		.align 2
-#define __ALIGN_STR	".align 2"
-
 #ifdef CONFIG_PPC64_ELF_ABI_V1
 #define cond_syscall(x) \
 	asm ("\t.weak " #x "\n\t.set " #x ", sys_ni_syscall\n"		\
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 52cc25864a1b..d8b7e246a32f 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -412,5 +412,9 @@ extern void *abatron_pteptrs[2];
 #include <asm/nohash/mmu.h>
 #endif
 
+#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP)
+#define __HAVE_ARCH_RESERVED_KERNEL_PAGES
+#endif
+
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_MMU_H_ */
diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h
index 4c6c6dbd182f..da827d2d0866 100644
--- a/arch/powerpc/include/asm/mmzone.h
+++ b/arch/powerpc/include/asm/mmzone.h
@@ -42,14 +42,6 @@ u64 memory_hotplug_max(void);
 #else
 #define memory_hotplug_max() memblock_end_of_DRAM()
 #endif /* CONFIG_NUMA */
-#ifdef CONFIG_FA_DUMP
-#define __HAVE_ARCH_RESERVED_KERNEL_PAGES
-#endif
-
-#ifdef CONFIG_MEMORY_HOTPLUG
-extern int create_section_mapping(unsigned long start, unsigned long end,
-				  int nid, pgprot_t prot);
-#endif
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_MMZONE_H_ */
diff --git a/arch/powerpc/include/asm/papr-sysparm.h b/arch/powerpc/include/asm/papr-sysparm.h
index f5fdbd8ae9db..0dbbff59101d 100644
--- a/arch/powerpc/include/asm/papr-sysparm.h
+++ b/arch/powerpc/include/asm/papr-sysparm.h
@@ -2,8 +2,10 @@
 #ifndef _ASM_POWERPC_PAPR_SYSPARM_H
 #define _ASM_POWERPC_PAPR_SYSPARM_H
 
+#include <uapi/asm/papr-sysparm.h>
+
 typedef struct {
-	const u32 token;
+	u32 token;
 } papr_sysparm_t;
 
 #define mk_papr_sysparm(x_) ((papr_sysparm_t){ .token = x_, })
@@ -20,11 +22,14 @@ typedef struct {
 #define PAPR_SYSPARM_TLB_BLOCK_INVALIDATE_ATTRS    mk_papr_sysparm(50)
 #define PAPR_SYSPARM_LPAR_NAME                     mk_papr_sysparm(55)
 
-enum {
-	PAPR_SYSPARM_MAX_INPUT  = 1024,
-	PAPR_SYSPARM_MAX_OUTPUT = 4000,
-};
-
+/**
+ * struct papr_sysparm_buf - RTAS work area layout for system parameter functions.
+ *
+ * This is the memory layout of the buffers passed to/from
+ * ibm,get-system-parameter and ibm,set-system-parameter. It is
+ * distinct from the papr_sysparm_io_block structure that is passed
+ * between user space and the kernel.
+ */
 struct papr_sysparm_buf {
 	__be16 len;
 	char val[PAPR_SYSPARM_MAX_OUTPUT];
diff --git a/arch/powerpc/include/asm/paravirt.h b/arch/powerpc/include/asm/paravirt.h
index ac4279208d63..b78b82d66057 100644
--- a/arch/powerpc/include/asm/paravirt.h
+++ b/arch/powerpc/include/asm/paravirt.h
@@ -76,6 +76,17 @@ static inline bool is_vcpu_idle(int vcpu)
 {
 	return lppaca_of(vcpu).idle;
 }
+
+static inline bool vcpu_is_dispatched(int vcpu)
+{
+	/*
+	 * This is the yield_count.  An "odd" value (low bit on) means that
+	 * the processor is yielded (either because of an OS yield or a
+	 * hypervisor preempt).  An even value implies that the processor is
+	 * currently executing.
+	 */
+	return (!(yield_count_of(vcpu) & 1));
+}
 #else
 static inline bool is_shared_processor(void)
 {
@@ -109,6 +120,10 @@ static inline bool is_vcpu_idle(int vcpu)
 {
 	return false;
 }
+static inline bool vcpu_is_dispatched(int vcpu)
+{
+	return true;
+}
 #endif
 
 #define vcpu_is_preempted vcpu_is_preempted
@@ -134,12 +149,12 @@ static inline bool vcpu_is_preempted(int cpu)
 	 * If the hypervisor has dispatched the target CPU on a physical
 	 * processor, then the target CPU is definitely not preempted.
 	 */
-	if (!(yield_count_of(cpu) & 1))
+	if (vcpu_is_dispatched(cpu))
 		return false;
 
 	/*
-	 * If the target CPU has yielded to Hypervisor but OS has not
-	 * requested idle then the target CPU is definitely preempted.
+	 * if the target CPU is not dispatched and the guest OS
+	 * has not marked the CPU idle, then it is hypervisor preempted.
 	 */
 	if (!is_vcpu_idle(cpu))
 		return true;
@@ -166,7 +181,7 @@ static inline bool vcpu_is_preempted(int cpu)
 
 		/*
 		 * The PowerVM hypervisor dispatches VMs on a whole core
-		 * basis. So we know that a thread sibling of the local CPU
+		 * basis. So we know that a thread sibling of the executing CPU
 		 * cannot have been preempted by the hypervisor, even if it
 		 * has called H_CONFER, which will set the yield bit.
 		 */
@@ -174,15 +189,17 @@ static inline bool vcpu_is_preempted(int cpu)
 			return false;
 
 		/*
-		 * If any of the threads of the target CPU's core are not
-		 * preempted or ceded, then consider target CPU to be
-		 * non-preempted.
+		 * The specific target CPU was marked by guest OS as idle, but
+		 * then also check all other cpus in the core for PowerVM
+		 * because it does core scheduling and one of the vcpu
+		 * of the core getting preempted by hypervisor implies
+		 * other vcpus can also be considered preempted.
 		 */
 		first_cpu = cpu_first_thread_sibling(cpu);
 		for (i = first_cpu; i < first_cpu + threads_per_core; i++) {
 			if (i == cpu)
 				continue;
-			if (!(yield_count_of(i) & 1))
+			if (vcpu_is_dispatched(i))
 				return false;
 			if (!is_vcpu_idle(i))
 				return true;
diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h
index d9fcff575027..ce2b1b5eebdd 100644
--- a/arch/powerpc/include/asm/ppc-pci.h
+++ b/arch/powerpc/include/asm/ppc-pci.h
@@ -35,6 +35,9 @@ extern void init_pci_config_tokens (void);
 extern unsigned long get_phb_buid (struct device_node *);
 extern int rtas_setup_phb(struct pci_controller *phb);
 
+int rtas_pci_dn_read_config(struct pci_dn *pdn, int where, int size, u32 *val);
+int rtas_pci_dn_write_config(struct pci_dn *pdn, int where, int size, u32 val);
+
 #ifdef CONFIG_EEH
 
 void eeh_addr_cache_insert_dev(struct pci_dev *dev);
@@ -44,8 +47,6 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity);
 int eeh_pci_enable(struct eeh_pe *pe, int function);
 int eeh_pe_reset_full(struct eeh_pe *pe, bool include_passed);
 void eeh_save_bars(struct eeh_dev *edev);
-int rtas_write_config(struct pci_dn *, int where, int size, u32 val);
-int rtas_read_config(struct pci_dn *, int where, int size, u32 *val);
 void eeh_pe_state_mark(struct eeh_pe *pe, int state);
 void eeh_pe_mark_isolated(struct eeh_pe *pe);
 void eeh_pe_state_clear(struct eeh_pe *pe, int state, bool include_passed);
diff --git a/arch/powerpc/include/asm/ps3.h b/arch/powerpc/include/asm/ps3.h
index a5f36546a052..d13d8fdc3411 100644
--- a/arch/powerpc/include/asm/ps3.h
+++ b/arch/powerpc/include/asm/ps3.h
@@ -514,4 +514,10 @@ u64 ps3_get_spe_id(void *arg);
 
 void ps3_early_mm_init(void);
 
+#ifdef CONFIG_PPC_EARLY_DEBUG_PS3GELIC
+void udbg_shutdown_ps3gelic(void);
+#else
+static inline void udbg_shutdown_ps3gelic(void) {}
+#endif
+
 #endif
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 4ae4ab9090a2..7fd09f25452d 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -1361,6 +1361,7 @@
 #define PVR_POWER8E	0x004B
 #define PVR_POWER8NVL	0x004C
 #define PVR_POWER8	0x004D
+#define PVR_HX_C2000	0x0066
 #define PVR_POWER9	0x004E
 #define PVR_POWER10	0x0080
 #define PVR_BE		0x0070
diff --git a/arch/powerpc/include/asm/reg_a2.h b/arch/powerpc/include/asm/reg_a2.h
deleted file mode 100644
index 74fba29e9491..000000000000
--- a/arch/powerpc/include/asm/reg_a2.h
+++ /dev/null
@@ -1,154 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- *  Register definitions specific to the A2 core
- *
- *  Copyright (C) 2008 Ben. Herrenschmidt (benh@kernel.crashing.org), IBM Corp.
- */
-
-#ifndef __ASM_POWERPC_REG_A2_H__
-#define __ASM_POWERPC_REG_A2_H__
-
-#include <asm/asm-const.h>
-
-#define SPRN_TENSR	0x1b5
-#define SPRN_TENS	0x1b6	/* Thread ENable Set */
-#define SPRN_TENC	0x1b7	/* Thread ENable Clear */
-
-#define SPRN_A2_CCR0	0x3f0	/* Core Configuration Register 0 */
-#define SPRN_A2_CCR1	0x3f1	/* Core Configuration Register 1 */
-#define SPRN_A2_CCR2	0x3f2	/* Core Configuration Register 2 */
-#define SPRN_MMUCR0	0x3fc	/* MMU Control Register 0 */
-#define SPRN_MMUCR1	0x3fd	/* MMU Control Register 1 */
-#define SPRN_MMUCR2	0x3fe	/* MMU Control Register 2 */
-#define SPRN_MMUCR3	0x3ff	/* MMU Control Register 3 */
-
-#define SPRN_IAR	0x372
-
-#define SPRN_IUCR0	0x3f3
-#define IUCR0_ICBI_ACK	0x1000
-
-#define SPRN_XUCR0	0x3f6	/* Execution Unit Config Register 0 */
-
-#define A2_IERAT_SIZE	16
-#define A2_DERAT_SIZE	32
-
-/* A2 MMUCR0 bits */
-#define MMUCR0_ECL	0x80000000	/* Extended Class for TLB fills */
-#define MMUCR0_TID_NZ	0x40000000	/* TID is non-zero */
-#define MMUCR0_TS	0x10000000	/* Translation space for TLB fills */
-#define MMUCR0_TGS	0x20000000	/* Guest space for TLB fills */
-#define MMUCR0_TLBSEL	0x0c000000	/* TLB or ERAT target for TLB fills */
-#define MMUCR0_TLBSEL_U	0x00000000	/*  TLBSEL = UTLB */
-#define MMUCR0_TLBSEL_I	0x08000000	/*  TLBSEL = I-ERAT */
-#define MMUCR0_TLBSEL_D	0x0c000000	/*  TLBSEL = D-ERAT */
-#define MMUCR0_LOCKSRSH	0x02000000	/* Use TLB lock on tlbsx. */
-#define MMUCR0_TID_MASK	0x000000ff	/* TID field */
-
-/* A2 MMUCR1 bits */
-#define MMUCR1_IRRE		0x80000000	/* I-ERAT round robin enable */
-#define MMUCR1_DRRE		0x40000000	/* D-ERAT round robin enable */
-#define MMUCR1_REE		0x20000000	/* Reference Exception Enable*/
-#define MMUCR1_CEE		0x10000000	/* Change exception enable */
-#define MMUCR1_CSINV_ALL	0x00000000	/* Inval ERAT on all CS evts */
-#define MMUCR1_CSINV_NISYNC	0x04000000	/* Inval ERAT on all ex isync*/
-#define MMUCR1_CSINV_NEVER	0x0c000000	/* Don't inval ERAT on CS */
-#define MMUCR1_ICTID		0x00080000	/* IERAT class field as TID */
-#define MMUCR1_ITTID		0x00040000	/* IERAT thdid field as TID */
-#define MMUCR1_DCTID		0x00020000	/* DERAT class field as TID */
-#define MMUCR1_DTTID		0x00010000	/* DERAT thdid field as TID */
-#define MMUCR1_DCCD		0x00008000	/* DERAT class ignore */
-#define MMUCR1_TLBWE_BINV	0x00004000	/* back invalidate on tlbwe */
-
-/* A2 MMUCR2 bits */
-#define MMUCR2_PSSEL_SHIFT	4
-
-/* A2 MMUCR3 bits */
-#define MMUCR3_THID		0x0000000f	/* Thread ID */
-
-/* *** ERAT TLB bits definitions */
-#define TLB0_EPN_MASK		ASM_CONST(0xfffffffffffff000)
-#define TLB0_CLASS_MASK		ASM_CONST(0x0000000000000c00)
-#define TLB0_CLASS_00		ASM_CONST(0x0000000000000000)
-#define TLB0_CLASS_01		ASM_CONST(0x0000000000000400)
-#define TLB0_CLASS_10		ASM_CONST(0x0000000000000800)
-#define TLB0_CLASS_11		ASM_CONST(0x0000000000000c00)
-#define TLB0_V			ASM_CONST(0x0000000000000200)
-#define TLB0_X			ASM_CONST(0x0000000000000100)
-#define TLB0_SIZE_MASK		ASM_CONST(0x00000000000000f0)
-#define TLB0_SIZE_4K		ASM_CONST(0x0000000000000010)
-#define TLB0_SIZE_64K		ASM_CONST(0x0000000000000030)
-#define TLB0_SIZE_1M		ASM_CONST(0x0000000000000050)
-#define TLB0_SIZE_16M		ASM_CONST(0x0000000000000070)
-#define TLB0_SIZE_1G		ASM_CONST(0x00000000000000a0)
-#define TLB0_THDID_MASK		ASM_CONST(0x000000000000000f)
-#define TLB0_THDID_0		ASM_CONST(0x0000000000000001)
-#define TLB0_THDID_1		ASM_CONST(0x0000000000000002)
-#define TLB0_THDID_2		ASM_CONST(0x0000000000000004)
-#define TLB0_THDID_3		ASM_CONST(0x0000000000000008)
-#define TLB0_THDID_ALL		ASM_CONST(0x000000000000000f)
-
-#define TLB1_RESVATTR		ASM_CONST(0x00f0000000000000)
-#define TLB1_U0			ASM_CONST(0x0008000000000000)
-#define TLB1_U1			ASM_CONST(0x0004000000000000)
-#define TLB1_U2			ASM_CONST(0x0002000000000000)
-#define TLB1_U3			ASM_CONST(0x0001000000000000)
-#define TLB1_R			ASM_CONST(0x0000800000000000)
-#define TLB1_C			ASM_CONST(0x0000400000000000)
-#define TLB1_RPN_MASK		ASM_CONST(0x000003fffffff000)
-#define TLB1_W			ASM_CONST(0x0000000000000800)
-#define TLB1_I			ASM_CONST(0x0000000000000400)
-#define TLB1_M			ASM_CONST(0x0000000000000200)
-#define TLB1_G			ASM_CONST(0x0000000000000100)
-#define TLB1_E			ASM_CONST(0x0000000000000080)
-#define TLB1_VF			ASM_CONST(0x0000000000000040)
-#define TLB1_UX			ASM_CONST(0x0000000000000020)
-#define TLB1_SX			ASM_CONST(0x0000000000000010)
-#define TLB1_UW			ASM_CONST(0x0000000000000008)
-#define TLB1_SW			ASM_CONST(0x0000000000000004)
-#define TLB1_UR			ASM_CONST(0x0000000000000002)
-#define TLB1_SR			ASM_CONST(0x0000000000000001)
-
-/* A2 erativax attributes definitions */
-#define ERATIVAX_RS_IS_ALL		0x000
-#define ERATIVAX_RS_IS_TID		0x040
-#define ERATIVAX_RS_IS_CLASS		0x080
-#define ERATIVAX_RS_IS_FULLMATCH	0x0c0
-#define ERATIVAX_CLASS_00		0x000
-#define ERATIVAX_CLASS_01		0x010
-#define ERATIVAX_CLASS_10		0x020
-#define ERATIVAX_CLASS_11		0x030
-#define ERATIVAX_PSIZE_4K		(TLB_PSIZE_4K >> 1)
-#define ERATIVAX_PSIZE_64K		(TLB_PSIZE_64K >> 1)
-#define ERATIVAX_PSIZE_1M		(TLB_PSIZE_1M >> 1)
-#define ERATIVAX_PSIZE_16M		(TLB_PSIZE_16M >> 1)
-#define ERATIVAX_PSIZE_1G		(TLB_PSIZE_1G >> 1)
-
-/* A2 eratilx attributes definitions */
-#define ERATILX_T_ALL			0
-#define ERATILX_T_TID			1
-#define ERATILX_T_TGS			2
-#define ERATILX_T_FULLMATCH		3
-#define ERATILX_T_CLASS0		4
-#define ERATILX_T_CLASS1		5
-#define ERATILX_T_CLASS2		6
-#define ERATILX_T_CLASS3		7
-
-/* XUCR0 bits */
-#define XUCR0_TRACE_UM_T0		0x40000000	/* Thread 0 */
-#define XUCR0_TRACE_UM_T1		0x20000000	/* Thread 1 */
-#define XUCR0_TRACE_UM_T2		0x10000000	/* Thread 2 */
-#define XUCR0_TRACE_UM_T3		0x08000000	/* Thread 3 */
-
-/* A2 CCR0 register */
-#define A2_CCR0_PME_DISABLED		0x00000000
-#define A2_CCR0_PME_SLEEP		0x40000000
-#define A2_CCR0_PME_RVW			0x80000000
-#define A2_CCR0_PME_DISABLED2		0xc0000000
-
-/* A2 CCR2 register */
-#define A2_CCR2_ERAT_ONLY_MODE		0x00000001
-#define A2_CCR2_ENABLE_ICSWX		0x00000002
-#define A2_CCR2_ENABLE_PC		0x20000000
-#define A2_CCR2_ENABLE_TRACE		0x40000000
-
-#endif /* __ASM_POWERPC_REG_A2_H__ */
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index c697c3c74694..9bb2210c8d44 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -3,6 +3,7 @@
 #define _POWERPC_RTAS_H
 #ifdef __KERNEL__
 
+#include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <asm/page.h>
 #include <asm/rtas-types.h>
@@ -201,12 +202,25 @@ typedef struct {
 /* Memory set aside for sys_rtas to use with calls that need a work area. */
 #define RTAS_USER_REGION_SIZE (64 * 1024)
 
-/* RTAS return status codes */
-#define RTAS_HARDWARE_ERROR	-1    /* Hardware Error */
-#define RTAS_BUSY		-2    /* RTAS Busy */
-#define RTAS_INVALID_PARAMETER	-3    /* Invalid indicator/domain/sensor etc. */
-#define RTAS_EXTENDED_DELAY_MIN	9900
-#define RTAS_EXTENDED_DELAY_MAX	9905
+/*
+ * Common RTAS function return values, derived from the table "RTAS
+ * Status Word Values" in PAPR+ v2.13 7.2.8: "Return Codes". If a
+ * function can return a value in this table then generally it has the
+ * meaning listed here. More extended commentary in the documentation
+ * for rtas_call().
+ *
+ * RTAS functions may use negative and positive numbers not in this
+ * set for function-specific error and success conditions,
+ * respectively.
+ */
+#define RTAS_SUCCESS                     0 /* Success. */
+#define RTAS_HARDWARE_ERROR             -1 /* Hardware or other unspecified error. */
+#define RTAS_BUSY                       -2 /* Retry immediately. */
+#define RTAS_INVALID_PARAMETER          -3 /* Invalid indicator/domain/sensor etc. */
+#define RTAS_UNEXPECTED_STATE_CHANGE    -7 /* Seems limited to EEH and slot reset. */
+#define RTAS_EXTENDED_DELAY_MIN       9900 /* Retry after delaying for ~1ms. */
+#define RTAS_EXTENDED_DELAY_MAX       9905 /* Retry after delaying for ~100s. */
+#define RTAS_ML_ISOLATION_ERROR      -9000 /* Multi-level isolation error. */
 
 /* statuses specific to ibm,suspend-me */
 #define RTAS_SUSPEND_ABORTED     9000 /* Suspension aborted */
@@ -268,7 +282,7 @@ typedef struct {
 #define RTAS_TYPE_DEALLOC		0xE3
 #define RTAS_TYPE_DUMP			0xE4
 #define RTAS_TYPE_HOTPLUG		0xE5
-/* I don't add PowerMGM events right now, this is a different topic */ 
+/* I don't add PowerMGM events right now, this is a different topic */
 #define RTAS_TYPE_PMGM_POWER_SW_ON	0x60
 #define RTAS_TYPE_PMGM_POWER_SW_OFF	0x61
 #define RTAS_TYPE_PMGM_LID_OPEN		0x62
@@ -408,44 +422,41 @@ static inline bool rtas_function_implemented(const rtas_fn_handle_t handle)
 {
 	return rtas_function_token(handle) != RTAS_UNKNOWN_SERVICE;
 }
-extern int rtas_token(const char *service);
-extern int rtas_service_present(const char *service);
-extern int rtas_call(int token, int, int, int *, ...);
+int rtas_token(const char *service);
+int rtas_call(int token, int nargs, int nret, int *outputs, ...);
 void rtas_call_unlocked(struct rtas_args *args, int token, int nargs,
 			int nret, ...);
-extern void __noreturn rtas_restart(char *cmd);
-extern void rtas_power_off(void);
-extern void __noreturn rtas_halt(void);
-extern void rtas_os_term(char *str);
+void __noreturn rtas_restart(char *cmd);
+void rtas_power_off(void);
+void __noreturn rtas_halt(void);
+void rtas_os_term(char *str);
 void rtas_activate_firmware(void);
-extern int rtas_get_sensor(int sensor, int index, int *state);
-extern int rtas_get_sensor_fast(int sensor, int index, int *state);
-extern int rtas_get_power_level(int powerdomain, int *level);
-extern int rtas_set_power_level(int powerdomain, int level, int *setlevel);
-extern bool rtas_indicator_present(int token, int *maxindex);
-extern int rtas_set_indicator(int indicator, int index, int new_value);
-extern int rtas_set_indicator_fast(int indicator, int index, int new_value);
-extern void rtas_progress(char *s, unsigned short hex);
+int rtas_get_sensor(int sensor, int index, int *state);
+int rtas_get_sensor_fast(int sensor, int index, int *state);
+int rtas_get_power_level(int powerdomain, int *level);
+int rtas_set_power_level(int powerdomain, int level, int *setlevel);
+bool rtas_indicator_present(int token, int *maxindex);
+int rtas_set_indicator(int indicator, int index, int new_value);
+int rtas_set_indicator_fast(int indicator, int index, int new_value);
+void rtas_progress(char *s, unsigned short hex);
 int rtas_ibm_suspend_me(int *fw_status);
 int rtas_error_rc(int rtas_rc);
 
 struct rtc_time;
-extern time64_t rtas_get_boot_time(void);
-extern void rtas_get_rtc_time(struct rtc_time *rtc_time);
-extern int rtas_set_rtc_time(struct rtc_time *rtc_time);
+time64_t rtas_get_boot_time(void);
+void rtas_get_rtc_time(struct rtc_time *rtc_time);
+int rtas_set_rtc_time(struct rtc_time *rtc_time);
 
-extern unsigned int rtas_busy_delay_time(int status);
+unsigned int rtas_busy_delay_time(int status);
 bool rtas_busy_delay(int status);
 
-extern int early_init_dt_scan_rtas(unsigned long node,
-		const char *uname, int depth, void *data);
+int early_init_dt_scan_rtas(unsigned long node, const char *uname, int depth, void *data);
 
-extern void pSeries_log_error(char *buf, unsigned int err_type, int fatal);
+void pSeries_log_error(char *buf, unsigned int err_type, int fatal);
 
 #ifdef CONFIG_PPC_PSERIES
 extern time64_t last_rtas_event;
-extern int clobbering_unread_rtas_event(void);
-extern void post_mobility_fixup(void);
+int clobbering_unread_rtas_event(void);
 int rtas_syscall_dispatch_ibm_suspend_me(u64 handle);
 #else
 static inline int clobbering_unread_rtas_event(void) { return 0; }
@@ -456,14 +467,14 @@ static inline int rtas_syscall_dispatch_ibm_suspend_me(u64 handle)
 #endif
 
 #ifdef CONFIG_PPC_RTAS_DAEMON
-extern void rtas_cancel_event_scan(void);
+void rtas_cancel_event_scan(void);
 #else
 static inline void rtas_cancel_event_scan(void) { }
 #endif
 
 /* Error types logged.  */
 #define ERR_FLAG_ALREADY_LOGGED	0x0
-#define ERR_FLAG_BOOT		0x1 	/* log was pulled from NVRAM on boot */
+#define ERR_FLAG_BOOT		0x1	/* log was pulled from NVRAM on boot */
 #define ERR_TYPE_RTAS_LOG	0x2	/* from rtas event-scan */
 #define ERR_TYPE_KERNEL_PANIC	0x4	/* from die()/panic() */
 #define ERR_TYPE_KERNEL_PANIC_GZ 0x8	/* ditto, compressed */
@@ -473,7 +484,7 @@ static inline void rtas_cancel_event_scan(void) { }
 	(ERR_TYPE_RTAS_LOG | ERR_TYPE_KERNEL_PANIC | ERR_TYPE_KERNEL_PANIC_GZ)
 
 #define RTAS_DEBUG KERN_DEBUG "RTAS: "
- 
+
 #define RTAS_ERROR_LOG_MAX 2048
 
 /*
@@ -481,7 +492,7 @@ static inline void rtas_cancel_event_scan(void) { }
  *  for all rtas calls that require an error buffer argument.
  *  This includes 'check-exception' and 'rtas-last-error'.
  */
-extern int rtas_get_error_log_max(void);
+int rtas_get_error_log_max(void);
 
 /* Event Scan Parameters */
 #define EVENT_SCAN_ALL_EVENTS	0xf0000000
@@ -502,6 +513,8 @@ extern char rtas_data_buf[RTAS_DATA_BUF_SIZE];
 /* RMO buffer reserved for user-space RTAS use */
 extern unsigned long rtas_rmo_buf;
 
+extern struct mutex rtas_ibm_get_vpd_lock;
+
 #define GLOBAL_INTERRUPT_QUEUE 9005
 
 /**
@@ -520,8 +533,8 @@ static inline u32 rtas_config_addr(int busno, int devfn, int reg)
 			(devfn << 8) | (reg & 0xff);
 }
 
-extern void rtas_give_timebase(void);
-extern void rtas_take_timebase(void);
+void rtas_give_timebase(void);
+void rtas_take_timebase(void);
 
 #ifdef CONFIG_PPC_RTAS
 static inline int page_is_rtas_user_buf(unsigned long pfn)
@@ -534,7 +547,7 @@ static inline int page_is_rtas_user_buf(unsigned long pfn)
 
 /* Not the best place to put pSeries_coalesce_init, will be fixed when we
  * move some of the rtas suspend-me stuff to pseries */
-extern void pSeries_coalesce_init(void);
+void pSeries_coalesce_init(void);
 void rtas_initialize(void);
 #else
 static inline int page_is_rtas_user_buf(unsigned long pfn) { return 0;}
@@ -542,8 +555,6 @@ static inline void pSeries_coalesce_init(void) { }
 static inline void rtas_initialize(void) { }
 #endif
 
-extern int call_rtas(const char *, int, int, unsigned long *, ...);
-
 #ifdef CONFIG_HV_PERF_CTRS
 void read_24x7_sys_info(void);
 #else
diff --git a/arch/powerpc/include/uapi/asm/papr-miscdev.h b/arch/powerpc/include/uapi/asm/papr-miscdev.h
new file mode 100644
index 000000000000..49a2a270b7f3
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/papr-miscdev.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_PAPR_MISCDEV_H_
+#define _UAPI_PAPR_MISCDEV_H_
+
+enum {
+	PAPR_MISCDEV_IOC_ID = 0xb2,
+};
+
+#endif /* _UAPI_PAPR_MISCDEV_H_ */
diff --git a/arch/powerpc/include/uapi/asm/papr-sysparm.h b/arch/powerpc/include/uapi/asm/papr-sysparm.h
new file mode 100644
index 000000000000..9f9a0f267ea5
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/papr-sysparm.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_PAPR_SYSPARM_H_
+#define _UAPI_PAPR_SYSPARM_H_
+
+#include <linux/types.h>
+#include <asm/ioctl.h>
+#include <asm/papr-miscdev.h>
+
+enum {
+	PAPR_SYSPARM_MAX_INPUT  = 1024,
+	PAPR_SYSPARM_MAX_OUTPUT = 4000,
+};
+
+struct papr_sysparm_io_block {
+	__u32 parameter;
+	__u16 length;
+	char data[PAPR_SYSPARM_MAX_OUTPUT];
+};
+
+/**
+ * PAPR_SYSPARM_IOC_GET - Retrieve the value of a PAPR system parameter.
+ *
+ * Uses _IOWR because of one corner case: Retrieving the value of the
+ * "OS Service Entitlement Status" parameter (60) requires the caller
+ * to supply input data (a date string) in the buffer passed to
+ * firmware. So the @length and @data of the incoming
+ * papr_sysparm_io_block are always used to initialize the work area
+ * supplied to ibm,get-system-parameter. No other parameters are known
+ * to parameterize the result this way, and callers are encouraged
+ * (but not required) to zero-initialize @length and @data in the
+ * common case.
+ *
+ * On error the contents of the ioblock are indeterminate.
+ *
+ * Return:
+ * 0: Success; @length is the length of valid data in @data, not to exceed @PAPR_SYSPARM_MAX_OUTPUT.
+ * -EIO: Platform error. (-1)
+ * -EINVAL: Incorrect data length or format. (-9999)
+ * -EPERM: The calling partition is not allowed to access this parameter. (-9002)
+ * -EOPNOTSUPP: Parameter not supported on this platform (-3)
+ */
+#define PAPR_SYSPARM_IOC_GET _IOWR(PAPR_MISCDEV_IOC_ID, 1, struct papr_sysparm_io_block)
+
+/**
+ * PAPR_SYSPARM_IOC_SET - Update the value of a PAPR system parameter.
+ *
+ * The contents of the ioblock are unchanged regardless of success.
+ *
+ * Return:
+ * 0: Success; the parameter has been updated.
+ * -EIO: Platform error. (-1)
+ * -EINVAL: Incorrect data length or format. (-9999)
+ * -EPERM: The calling partition is not allowed to access this parameter. (-9002)
+ * -EOPNOTSUPP: Parameter not supported on this platform (-3)
+ */
+#define PAPR_SYSPARM_IOC_SET _IOW(PAPR_MISCDEV_IOC_ID, 2, struct papr_sysparm_io_block)
+
+#endif /* _UAPI_PAPR_SYSPARM_H_ */
diff --git a/arch/powerpc/include/uapi/asm/papr-vpd.h b/arch/powerpc/include/uapi/asm/papr-vpd.h
new file mode 100644
index 000000000000..1c88e87cb420
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/papr-vpd.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_PAPR_VPD_H_
+#define _UAPI_PAPR_VPD_H_
+
+#include <asm/ioctl.h>
+#include <asm/papr-miscdev.h>
+
+struct papr_location_code {
+	/*
+	 * PAPR+ v2.13 12.3.2.4 Converged Location Code Rules - Length
+	 * Restrictions. 79 characters plus nul.
+	 */
+	char str[80];
+};
+
+/*
+ * ioctl for /dev/papr-vpd. Returns a VPD handle fd corresponding to
+ * the location code.
+ */
+#define PAPR_VPD_IOC_CREATE_HANDLE _IOW(PAPR_MISCDEV_IOC_ID, 0, struct papr_location_code)
+
+#endif /* _UAPI_PAPR_VPD_H_ */
diff --git a/arch/powerpc/kernel/cpu_specs_book3s_64.h b/arch/powerpc/kernel/cpu_specs_book3s_64.h
index c370c1b804a9..3ff9757df4c0 100644
--- a/arch/powerpc/kernel/cpu_specs_book3s_64.h
+++ b/arch/powerpc/kernel/cpu_specs_book3s_64.h
@@ -238,6 +238,21 @@ static struct cpu_spec cpu_specs[] __initdata = {
 		.machine_check_early	= __machine_check_early_realmode_p8,
 		.platform		= "power8",
 	},
+	{	/* 2.07-compliant processor, HeXin C2000 processor */
+		.pvr_mask		= 0xffff0000,
+		.pvr_value		= 0x00660000,
+		.cpu_name		= "HX-C2000",
+		.cpu_features		= CPU_FTRS_POWER8,
+		.cpu_user_features	= COMMON_USER_POWER8,
+		.cpu_user_features2	= COMMON_USER2_POWER8,
+		.mmu_features		= MMU_FTRS_POWER8,
+		.icache_bsize		= 128,
+		.dcache_bsize		= 128,
+		.cpu_setup		= __setup_cpu_power8,
+		.cpu_restore		= __restore_cpu_power8,
+		.machine_check_early	= __machine_check_early_realmode_p8,
+		.platform		= "power8",
+	},
 	{	/* 3.00-compliant processor, i.e. Power9 "architected" mode */
 		.pvr_mask		= 0xffffffff,
 		.pvr_value		= 0x0f000005,
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index e97a0fd0ae90..6f6801da9dc1 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -20,9 +20,9 @@
 #include <asm/setup.h>
 #include <asm/cpu_setup.h>
 
-static struct cpu_spec the_cpu_spec __read_mostly;
+static struct cpu_spec the_cpu_spec __ro_after_init;
 
-struct cpu_spec* cur_cpu_spec __read_mostly = NULL;
+struct cpu_spec *cur_cpu_spec __ro_after_init = NULL;
 EXPORT_SYMBOL(cur_cpu_spec);
 
 /* The platform string corresponding to the real PVR */
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 7ab4c8c0f1ab..dcf0591ad3c2 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -14,7 +14,6 @@
 #include <asm/cputable.h>
 #include <asm/setup.h>
 #include <asm/thread_info.h>
-#include <asm/reg_a2.h>
 #include <asm/exception-64e.h>
 #include <asm/bug.h>
 #include <asm/irqflags.h>
diff --git a/arch/powerpc/kernel/firmware.c b/arch/powerpc/kernel/firmware.c
index 20328f72f9f2..8987eee33dc8 100644
--- a/arch/powerpc/kernel/firmware.c
+++ b/arch/powerpc/kernel/firmware.c
@@ -23,6 +23,8 @@ EXPORT_SYMBOL_GPL(powerpc_firmware_features);
 
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_KVM_GUEST)
 DEFINE_STATIC_KEY_FALSE(kvm_guest);
+EXPORT_SYMBOL_GPL(kvm_guest);
+
 int __init check_kvm_guest(void)
 {
 	struct device_node *hyper_node;
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index 6a9acfb690c9..2f8f3f93cbb6 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -23,6 +23,15 @@
 #include <asm/feature-fixups.h>
 
 #ifdef CONFIG_VSX
+#define __REST_1FPVSR(n,c,base)						\
+BEGIN_FTR_SECTION							\
+	b	2f;							\
+END_FTR_SECTION_IFSET(CPU_FTR_VSX);					\
+	REST_FPR(n,base);						\
+	b	3f;							\
+2:	REST_VSR(n,c,base);						\
+3:
+
 #define __REST_32FPVSRS(n,c,base)					\
 BEGIN_FTR_SECTION							\
 	b	2f;							\
@@ -41,9 +50,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX);					\
 2:	SAVE_32VSRS(n,c,base);						\
 3:
 #else
+#define __REST_1FPVSR(n,b,base)		REST_FPR(n, base)
 #define __REST_32FPVSRS(n,b,base)	REST_32FPRS(n, base)
 #define __SAVE_32FPVSRS(n,b,base)	SAVE_32FPRS(n, base)
 #endif
+#define REST_1FPVSR(n,c,base)   __REST_1FPVSR(n,__REG_##c,__REG_##base)
 #define REST_32FPVSRS(n,c,base) __REST_32FPVSRS(n,__REG_##c,__REG_##base)
 #define SAVE_32FPVSRS(n,c,base) __SAVE_32FPVSRS(n,__REG_##c,__REG_##base)
 
@@ -67,6 +78,7 @@ _GLOBAL(store_fp_state)
 	SAVE_32FPVSRS(0, R4, R3)
 	mffs	fr0
 	stfd	fr0,FPSTATE_FPSCR(r3)
+	REST_1FPVSR(0, R4, R3)
 	blr
 EXPORT_SYMBOL(store_fp_state)
 
@@ -138,4 +150,5 @@ _GLOBAL(save_fpu)
 2:	SAVE_32FPVSRS(0, R4, R6)
 	mffs	fr0
 	stfd	fr0,FPSTATE_FPSCR(r6)
+	REST_1FPVSR(0, R4, R6)
 	blr
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index c4f6d3c69ba9..eca293794a1e 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -3,6 +3,7 @@
 #include <linux/context_tracking.h>
 #include <linux/err.h>
 #include <linux/compat.h>
+#include <linux/rseq.h>
 #include <linux/sched/debug.h> /* for show_regs */
 
 #include <asm/kup.h>
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 392404688cec..9452a54d356c 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1198,11 +1198,11 @@ void kvmppc_save_user_regs(void)
 
 	usermsr = current->thread.regs->msr;
 
+	/* Caller has enabled FP/VEC/VSX/TM in MSR */
 	if (usermsr & MSR_FP)
-		save_fpu(current);
-
+		__giveup_fpu(current);
 	if (usermsr & MSR_VEC)
-		save_altivec(current);
+		__giveup_altivec(current);
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	if (usermsr & MSR_TM) {
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index eddc031c4b95..7e793b503e29 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -18,6 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/lockdep.h>
 #include <linux/memblock.h>
+#include <linux/mutex.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/reboot.h>
@@ -70,14 +71,33 @@ struct rtas_filter {
  *                            ppc64le, and we want to keep it that way. It does
  *                            not make sense for this to be set when @filter
  *                            is NULL.
+ * @lock: Pointer to an optional dedicated per-function mutex. This
+ *        should be set for functions that require multiple calls in
+ *        sequence to complete a single operation, and such sequences
+ *        will disrupt each other if allowed to interleave. Users of
+ *        this function are required to hold the associated lock for
+ *        the duration of the call sequence. Add an explanatory
+ *        comment to the function table entry if setting this member.
  */
 struct rtas_function {
 	s32 token;
 	const bool banned_for_syscall_on_le:1;
 	const char * const name;
 	const struct rtas_filter *filter;
+	struct mutex *lock;
 };
 
+/*
+ * Per-function locks for sequence-based RTAS functions.
+ */
+static DEFINE_MUTEX(rtas_ibm_activate_firmware_lock);
+static DEFINE_MUTEX(rtas_ibm_get_dynamic_sensor_state_lock);
+static DEFINE_MUTEX(rtas_ibm_get_indices_lock);
+static DEFINE_MUTEX(rtas_ibm_lpar_perftools_lock);
+static DEFINE_MUTEX(rtas_ibm_physical_attestation_lock);
+static DEFINE_MUTEX(rtas_ibm_set_dynamic_indicator_lock);
+DEFINE_MUTEX(rtas_ibm_get_vpd_lock);
+
 static struct rtas_function rtas_function_table[] __ro_after_init = {
 	[RTAS_FNIDX__CHECK_EXCEPTION] = {
 		.name = "check-exception",
@@ -125,6 +145,13 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = -1, .size_idx1 = -1,
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
+		/*
+		 * PAPR+ as of v2.13 doesn't explicitly impose any
+		 * restriction, but this typically requires multiple
+		 * calls before success, and there's no reason to
+		 * allow sequences to interleave.
+		 */
+		.lock = &rtas_ibm_activate_firmware_lock,
 	},
 	[RTAS_FNIDX__IBM_CBE_START_PTCAL] = {
 		.name = "ibm,cbe-start-ptcal",
@@ -196,6 +223,13 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = 1, .size_idx1 = -1,
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
+		/*
+		 * PAPR+ v2.13 R1–7.3.19–3 is explicit that the OS
+		 * must not call ibm,get-dynamic-sensor-state with
+		 * different inputs until a non-retry status has been
+		 * returned.
+		 */
+		.lock = &rtas_ibm_get_dynamic_sensor_state_lock,
 	},
 	[RTAS_FNIDX__IBM_GET_INDICES] = {
 		.name = "ibm,get-indices",
@@ -203,6 +237,12 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = 2, .size_idx1 = 3,
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
+		/*
+		 * PAPR+ v2.13 R1–7.3.17–2 says that the OS must not
+		 * interleave ibm,get-indices call sequences with
+		 * different inputs.
+		 */
+		.lock = &rtas_ibm_get_indices_lock,
 	},
 	[RTAS_FNIDX__IBM_GET_RIO_TOPOLOGY] = {
 		.name = "ibm,get-rio-topology",
@@ -220,6 +260,11 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = 0, .size_idx1 = -1,
 			.buf_idx2 = 1, .size_idx2 = 2,
 		},
+		/*
+		 * PAPR+ v2.13 R1–7.3.20–4 indicates that sequences
+		 * should not be allowed to interleave.
+		 */
+		.lock = &rtas_ibm_get_vpd_lock,
 	},
 	[RTAS_FNIDX__IBM_GET_XIVE] = {
 		.name = "ibm,get-xive",
@@ -239,6 +284,11 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = 2, .size_idx1 = 3,
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
+		/*
+		 * PAPR+ v2.13 R1–7.3.26–6 says the OS should allow
+		 * only one call sequence in progress at a time.
+		 */
+		.lock = &rtas_ibm_lpar_perftools_lock,
 	},
 	[RTAS_FNIDX__IBM_MANAGE_FLASH_IMAGE] = {
 		.name = "ibm,manage-flash-image",
@@ -277,6 +327,14 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = 0, .size_idx1 = 1,
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
+		/*
+		 * This follows a sequence-based pattern similar to
+		 * ibm,get-vpd et al. Since PAPR+ restricts
+		 * interleaving call sequences for other functions of
+		 * this style, assume the restriction applies here,
+		 * even though it's not explicit in the spec.
+		 */
+		.lock = &rtas_ibm_physical_attestation_lock,
 	},
 	[RTAS_FNIDX__IBM_PLATFORM_DUMP] = {
 		.name = "ibm,platform-dump",
@@ -284,6 +342,13 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = 4, .size_idx1 = 5,
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
+		/*
+		 * PAPR+ v2.13 7.3.3.4.1 indicates that concurrent
+		 * sequences of ibm,platform-dump are allowed if they
+		 * are operating on different dump tags. So leave the
+		 * lock pointer unset for now. This may need
+		 * reconsideration if kernel-internal users appear.
+		 */
 	},
 	[RTAS_FNIDX__IBM_POWER_OFF_UPS] = {
 		.name = "ibm,power-off-ups",
@@ -326,6 +391,12 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = 2, .size_idx1 = -1,
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
+		/*
+		 * PAPR+ v2.13 R1–7.3.18–3 says the OS must not call
+		 * this function with different inputs until a
+		 * non-retry status has been returned.
+		 */
+		.lock = &rtas_ibm_set_dynamic_indicator_lock,
 	},
 	[RTAS_FNIDX__IBM_SET_EEH_OPTION] = {
 		.name = "ibm,set-eeh-option",
@@ -454,6 +525,11 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 	},
 };
 
+#define for_each_rtas_function(funcp)                                       \
+	for (funcp = &rtas_function_table[0];                               \
+	     funcp < &rtas_function_table[ARRAY_SIZE(rtas_function_table)]; \
+	     ++funcp)
+
 /*
  * Nearly all RTAS calls need to be serialized. All uses of the
  * default rtas_args block must hold rtas_lock.
@@ -525,10 +601,10 @@ static DEFINE_XARRAY(rtas_token_to_function_xarray);
 
 static int __init rtas_token_to_function_xarray_init(void)
 {
+	const struct rtas_function *func;
 	int err = 0;
 
-	for (size_t i = 0; i < ARRAY_SIZE(rtas_function_table); ++i) {
-		const struct rtas_function *func = &rtas_function_table[i];
+	for_each_rtas_function(func) {
 		const s32 token = func->token;
 
 		if (token == RTAS_UNKNOWN_SERVICE)
@@ -544,6 +620,21 @@ static int __init rtas_token_to_function_xarray_init(void)
 }
 arch_initcall(rtas_token_to_function_xarray_init);
 
+/*
+ * For use by sys_rtas(), where the token value is provided by user
+ * space and we don't want to warn on failed lookups.
+ */
+static const struct rtas_function *rtas_token_to_function_untrusted(s32 token)
+{
+	return xa_load(&rtas_token_to_function_xarray, token);
+}
+
+/*
+ * Reverse lookup for deriving the function descriptor from a
+ * known-good token value in contexts where the former is not already
+ * available. @token must be valid, e.g. derived from the result of a
+ * prior lookup against the function table.
+ */
 static const struct rtas_function *rtas_token_to_function(s32 token)
 {
 	const struct rtas_function *func;
@@ -551,12 +642,22 @@ static const struct rtas_function *rtas_token_to_function(s32 token)
 	if (WARN_ONCE(token < 0, "invalid token %d", token))
 		return NULL;
 
-	func = xa_load(&rtas_token_to_function_xarray, token);
-
-	if (WARN_ONCE(!func, "unexpected failed lookup for token %d", token))
-		return NULL;
+	func = rtas_token_to_function_untrusted(token);
+	if (func)
+		return func;
+	/*
+	 * Fall back to linear scan in case the reverse mapping hasn't
+	 * been initialized yet.
+	 */
+	if (xa_empty(&rtas_token_to_function_xarray)) {
+		for_each_rtas_function(func) {
+			if (func->token == token)
+				return func;
+		}
+	}
 
-	return func;
+	WARN_ONCE(true, "unexpected failed lookup for token %d", token);
+	return NULL;
 }
 
 /* This is here deliberately so it's only used in this file */
@@ -570,28 +671,25 @@ static void __do_enter_rtas(struct rtas_args *args)
 
 static void __do_enter_rtas_trace(struct rtas_args *args)
 {
-	const char *name = NULL;
+	const struct rtas_function *func = rtas_token_to_function(be32_to_cpu(args->token));
 
-	if (args == &rtas_args)
-		lockdep_assert_held(&rtas_lock);
 	/*
-	 * If the tracepoints that consume the function name aren't
-	 * active, avoid the lookup.
+	 * If there is a per-function lock, it must be held by the
+	 * caller.
 	 */
-	if ((trace_rtas_input_enabled() || trace_rtas_output_enabled())) {
-		const s32 token = be32_to_cpu(args->token);
-		const struct rtas_function *func = rtas_token_to_function(token);
+	if (func->lock)
+		lockdep_assert_held(func->lock);
 
-		name = func->name;
-	}
+	if (args == &rtas_args)
+		lockdep_assert_held(&rtas_lock);
 
-	trace_rtas_input(args, name);
+	trace_rtas_input(args, func->name);
 	trace_rtas_ll_entry(args);
 
 	__do_enter_rtas(args);
 
 	trace_rtas_ll_exit(args);
-	trace_rtas_output(args, name);
+	trace_rtas_output(args, func->name);
 }
 
 static void do_enter_rtas(struct rtas_args *args)
@@ -670,7 +768,7 @@ static void call_rtas_display_status_delay(char c)
 	static int pending_newline = 0;  /* did last write end with unprinted newline? */
 	static int width = 16;
 
-	if (c == '\n') {	
+	if (c == '\n') {
 		while (width-- > 0)
 			call_rtas_display_status(' ');
 		width = 16;
@@ -680,7 +778,7 @@ static void call_rtas_display_status_delay(char c)
 		if (pending_newline) {
 			call_rtas_display_status('\r');
 			call_rtas_display_status('\n');
-		} 
+		}
 		pending_newline = 0;
 		if (width--) {
 			call_rtas_display_status(c);
@@ -820,7 +918,7 @@ void rtas_progress(char *s, unsigned short hex)
 		else
 			rtas_call(display_character, 1, 1, NULL, '\r');
 	}
- 
+
 	if (row_width)
 		width = row_width[current_line];
 	else
@@ -840,9 +938,9 @@ void rtas_progress(char *s, unsigned short hex)
 				spin_unlock(&progress_lock);
 				return;
 			}
- 
+
 			/* RTAS wants CR-LF, not just LF */
- 
+
 			if (*os == '\n') {
 				rtas_call(display_character, 1, 1, NULL, '\r');
 				rtas_call(display_character, 1, 1, NULL, '\n');
@@ -852,7 +950,7 @@ void rtas_progress(char *s, unsigned short hex)
 				 */
 				rtas_call(display_character, 1, 1, NULL, *os);
 			}
- 
+
 			if (row_width)
 				width = row_width[current_line];
 			else
@@ -861,15 +959,15 @@ void rtas_progress(char *s, unsigned short hex)
 			width--;
 			rtas_call(display_character, 1, 1, NULL, *os);
 		}
- 
+
 		os++;
- 
+
 		/* if we overwrite the screen length */
 		if (width <= 0)
 			while ((*os != 0) && (*os != '\n') && (*os != '\r'))
 				os++;
 	}
- 
+
 	spin_unlock(&progress_lock);
 }
 EXPORT_SYMBOL_GPL(rtas_progress);		/* needed by rtas_flash module */
@@ -900,11 +998,6 @@ int rtas_token(const char *service)
 }
 EXPORT_SYMBOL_GPL(rtas_token);
 
-int rtas_service_present(const char *service)
-{
-	return rtas_token(service) != RTAS_UNKNOWN_SERVICE;
-}
-
 #ifdef CONFIG_RTAS_ERROR_LOGGING
 
 static u32 rtas_error_log_max __ro_after_init = RTAS_ERROR_LOG_MAX;
@@ -1638,10 +1731,14 @@ void rtas_activate_firmware(void)
 		return;
 	}
 
+	mutex_lock(&rtas_ibm_activate_firmware_lock);
+
 	do {
 		fwrc = rtas_call(token, 0, 1, NULL);
 	} while (rtas_busy_delay(fwrc));
 
+	mutex_unlock(&rtas_ibm_activate_firmware_lock);
+
 	if (fwrc)
 		pr_err("ibm,activate-firmware failed (%i)\n", fwrc);
 }
@@ -1713,24 +1810,18 @@ static bool in_rmo_buf(u32 base, u32 end)
 		end < (rtas_rmo_buf + RTAS_USER_REGION_SIZE);
 }
 
-static bool block_rtas_call(int token, int nargs,
+static bool block_rtas_call(const struct rtas_function *func, int nargs,
 			    struct rtas_args *args)
 {
-	const struct rtas_function *func;
 	const struct rtas_filter *f;
-	const bool is_platform_dump = token == rtas_function_token(RTAS_FN_IBM_PLATFORM_DUMP);
-	const bool is_config_conn = token == rtas_function_token(RTAS_FN_IBM_CONFIGURE_CONNECTOR);
+	const bool is_platform_dump =
+		func == &rtas_function_table[RTAS_FNIDX__IBM_PLATFORM_DUMP];
+	const bool is_config_conn =
+		func == &rtas_function_table[RTAS_FNIDX__IBM_CONFIGURE_CONNECTOR];
 	u32 base, size, end;
 
 	/*
-	 * If this token doesn't correspond to a function the kernel
-	 * understands, you're not allowed to call it.
-	 */
-	func = rtas_token_to_function(token);
-	if (!func)
-		goto err;
-	/*
-	 * And only functions with filters attached are allowed.
+	 * Only functions with filters attached are allowed.
 	 */
 	f = func->filter;
 	if (!f)
@@ -1787,14 +1878,15 @@ static bool block_rtas_call(int token, int nargs,
 	return false;
 err:
 	pr_err_ratelimited("sys_rtas: RTAS call blocked - exploit attempt?\n");
-	pr_err_ratelimited("sys_rtas: token=0x%x, nargs=%d (called by %s)\n",
-			   token, nargs, current->comm);
+	pr_err_ratelimited("sys_rtas: %s nargs=%d (called by %s)\n",
+			   func->name, nargs, current->comm);
 	return true;
 }
 
 /* We assume to be passed big endian arguments */
 SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
 {
+	const struct rtas_function *func;
 	struct pin_cookie cookie;
 	struct rtas_args args;
 	unsigned long flags;
@@ -1824,13 +1916,18 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
 			   nargs * sizeof(rtas_arg_t)) != 0)
 		return -EFAULT;
 
-	if (token == RTAS_UNKNOWN_SERVICE)
+	/*
+	 * If this token doesn't correspond to a function the kernel
+	 * understands, you're not allowed to call it.
+	 */
+	func = rtas_token_to_function_untrusted(token);
+	if (!func)
 		return -EINVAL;
 
 	args.rets = &args.args[nargs];
 	memset(args.rets, 0, nret * sizeof(rtas_arg_t));
 
-	if (block_rtas_call(token, nargs, &args))
+	if (block_rtas_call(func, nargs, &args))
 		return -EINVAL;
 
 	if (token_is_restricted_errinjct(token)) {
@@ -1863,6 +1960,15 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
 
 	buff_copy = get_errorlog_buffer();
 
+	/*
+	 * If this function has a mutex assigned to it, we must
+	 * acquire it to avoid interleaving with any kernel-based uses
+	 * of the same function. Kernel-based sequences acquire the
+	 * appropriate mutex explicitly.
+	 */
+	if (func->lock)
+		mutex_lock(func->lock);
+
 	raw_spin_lock_irqsave(&rtas_lock, flags);
 	cookie = lockdep_pin_lock(&rtas_lock);
 
@@ -1878,6 +1984,9 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
 	lockdep_unpin_lock(&rtas_lock, cookie);
 	raw_spin_unlock_irqrestore(&rtas_lock, flags);
 
+	if (func->lock)
+		mutex_unlock(func->lock);
+
 	if (buff_copy) {
 		if (errbuf)
 			log_error(errbuf, ERR_TYPE_RTAS_LOG, 0);
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index e1fdc7473b72..fccf96e897f6 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -43,7 +43,7 @@ static inline int config_access_valid(struct pci_dn *dn, int where)
 	return 0;
 }
 
-int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val)
+int rtas_pci_dn_read_config(struct pci_dn *pdn, int where, int size, u32 *val)
 {
 	int returnval = -1;
 	unsigned long buid, addr;
@@ -87,7 +87,7 @@ static int rtas_pci_read_config(struct pci_bus *bus,
 	pdn = pci_get_pdn_by_devfn(bus, devfn);
 
 	/* Validity of pdn is checked in here */
-	ret = rtas_read_config(pdn, where, size, val);
+	ret = rtas_pci_dn_read_config(pdn, where, size, val);
 	if (*val == EEH_IO_ERROR_VALUE(size) &&
 	    eeh_dev_check_failure(pdn_to_eeh_dev(pdn)))
 		return PCIBIOS_DEVICE_NOT_FOUND;
@@ -95,7 +95,7 @@ static int rtas_pci_read_config(struct pci_bus *bus,
 	return ret;
 }
 
-int rtas_write_config(struct pci_dn *pdn, int where, int size, u32 val)
+int rtas_pci_dn_write_config(struct pci_dn *pdn, int where, int size, u32 val)
 {
 	unsigned long buid, addr;
 	int ret;
@@ -134,7 +134,7 @@ static int rtas_pci_write_config(struct pci_bus *bus,
 	pdn = pci_get_pdn_by_devfn(bus, devfn);
 
 	/* Validity of pdn is checked in here. */
-	return rtas_write_config(pdn, where, size, val);
+	return rtas_pci_dn_write_config(pdn, where, size, val);
 }
 
 static struct pci_ops rtas_pci_ops = {
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index ab691c89d787..693334c20d07 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -77,10 +77,10 @@ static DEFINE_PER_CPU(int, cpu_state) = { 0 };
 #endif
 
 struct task_struct *secondary_current;
-bool has_big_cores;
-bool coregroup_enabled;
-bool thread_group_shares_l2;
-bool thread_group_shares_l3;
+bool has_big_cores __ro_after_init;
+bool coregroup_enabled __ro_after_init;
+bool thread_group_shares_l2 __ro_after_init;
+bool thread_group_shares_l3 __ro_after_init;
 
 DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
 DEFINE_PER_CPU(cpumask_var_t, cpu_smallcore_map);
@@ -93,15 +93,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_l2_cache_map);
 EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 EXPORT_SYMBOL_GPL(has_big_cores);
 
-enum {
-#ifdef CONFIG_SCHED_SMT
-	smt_idx,
-#endif
-	cache_idx,
-	mc_idx,
-	die_idx,
-};
-
 #define MAX_THREAD_LIST_SIZE	8
 #define THREAD_GROUP_SHARE_L1   1
 #define THREAD_GROUP_SHARE_L2_L3 2
@@ -987,7 +978,7 @@ static int __init init_thread_group_cache_map(int cpu, int cache_property)
 	return 0;
 }
 
-static bool shared_caches;
+static bool shared_caches __ro_after_init;
 
 #ifdef CONFIG_SCHED_SMT
 /* cpumask of CPUs with asymmetric SMT dependency */
@@ -1004,6 +995,13 @@ static int powerpc_smt_flags(void)
 #endif
 
 /*
+ * On shared processor LPARs scheduled on a big core (which has two or more
+ * independent thread groups per core), prefer lower numbered CPUs, so
+ * that workload consolidates to lesser number of cores.
+ */
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(splpar_asym_pack);
+
+/*
  * P9 has a slightly odd architecture where pairs of cores share an L2 cache.
  * This topology makes it *much* cheaper to migrate tasks between adjacent cores
  * since the migrated task remains cache hot. We want to take advantage of this
@@ -1011,9 +1009,20 @@ static int powerpc_smt_flags(void)
  */
 static int powerpc_shared_cache_flags(void)
 {
+	if (static_branch_unlikely(&splpar_asym_pack))
+		return SD_SHARE_PKG_RESOURCES | SD_ASYM_PACKING;
+
 	return SD_SHARE_PKG_RESOURCES;
 }
 
+static int powerpc_shared_proc_flags(void)
+{
+	if (static_branch_unlikely(&splpar_asym_pack))
+		return SD_ASYM_PACKING;
+
+	return 0;
+}
+
 /*
  * We can't just pass cpu_l2_cache_mask() directly because
  * returns a non-const pointer and the compiler barfs on that.
@@ -1037,6 +1046,10 @@ static struct cpumask *cpu_coregroup_mask(int cpu)
 
 static bool has_coregroup_support(void)
 {
+	/* Coregroup identification not available on shared systems */
+	if (is_shared_processor())
+		return 0;
+
 	return coregroup_enabled;
 }
 
@@ -1045,16 +1058,6 @@ static const struct cpumask *cpu_mc_mask(int cpu)
 	return cpu_coregroup_mask(cpu);
 }
 
-static struct sched_domain_topology_level powerpc_topology[] = {
-#ifdef CONFIG_SCHED_SMT
-	{ cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
-#endif
-	{ shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
-	{ cpu_mc_mask, SD_INIT_NAME(MC) },
-	{ cpu_cpu_mask, SD_INIT_NAME(PKG) },
-	{ NULL, },
-};
-
 static int __init init_big_cores(void)
 {
 	int cpu;
@@ -1682,43 +1685,45 @@ void start_secondary(void *unused)
 	BUG();
 }
 
-static void __init fixup_topology(void)
+static struct sched_domain_topology_level powerpc_topology[6];
+
+static void __init build_sched_topology(void)
 {
-	int i;
+	int i = 0;
+
+	if (is_shared_processor() && has_big_cores)
+		static_branch_enable(&splpar_asym_pack);
 
 #ifdef CONFIG_SCHED_SMT
 	if (has_big_cores) {
 		pr_info("Big cores detected but using small core scheduling\n");
-		powerpc_topology[smt_idx].mask = smallcore_smt_mask;
+		powerpc_topology[i++] = (struct sched_domain_topology_level){
+			smallcore_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT)
+		};
+	} else {
+		powerpc_topology[i++] = (struct sched_domain_topology_level){
+			cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT)
+		};
 	}
 #endif
+	if (shared_caches) {
+		powerpc_topology[i++] = (struct sched_domain_topology_level){
+			shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE)
+		};
+	}
+	if (has_coregroup_support()) {
+		powerpc_topology[i++] = (struct sched_domain_topology_level){
+			cpu_mc_mask, powerpc_shared_proc_flags, SD_INIT_NAME(MC)
+		};
+	}
+	powerpc_topology[i++] = (struct sched_domain_topology_level){
+		cpu_cpu_mask, powerpc_shared_proc_flags, SD_INIT_NAME(PKG)
+	};
 
-	if (!has_coregroup_support())
-		powerpc_topology[mc_idx].mask = powerpc_topology[cache_idx].mask;
-
-	/*
-	 * Try to consolidate topology levels here instead of
-	 * allowing scheduler to degenerate.
-	 * - Dont consolidate if masks are different.
-	 * - Dont consolidate if sd_flags exists and are different.
-	 */
-	for (i = 1; i <= die_idx; i++) {
-		if (powerpc_topology[i].mask != powerpc_topology[i - 1].mask)
-			continue;
-
-		if (powerpc_topology[i].sd_flags && powerpc_topology[i - 1].sd_flags &&
-				powerpc_topology[i].sd_flags != powerpc_topology[i - 1].sd_flags)
-			continue;
-
-		if (!powerpc_topology[i - 1].sd_flags)
-			powerpc_topology[i - 1].sd_flags = powerpc_topology[i].sd_flags;
+	/* There must be one trailing NULL entry left.  */
+	BUG_ON(i >= ARRAY_SIZE(powerpc_topology) - 1);
 
-		powerpc_topology[i].mask = powerpc_topology[i + 1].mask;
-		powerpc_topology[i].sd_flags = powerpc_topology[i + 1].sd_flags;
-#ifdef CONFIG_SCHED_DEBUG
-		powerpc_topology[i].name = powerpc_topology[i + 1].name;
-#endif
-	}
+	set_sched_topology(powerpc_topology);
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)
@@ -1733,9 +1738,20 @@ void __init smp_cpus_done(unsigned int max_cpus)
 		smp_ops->bringup_done();
 
 	dump_numa_cpu_topology();
+	build_sched_topology();
+}
 
-	fixup_topology();
-	set_sched_topology(powerpc_topology);
+/*
+ * For asym packing, by default lower numbered CPU has higher priority.
+ * On shared processors, pack to lower numbered core. However avoid moving
+ * between thread_groups within the same core.
+ */
+int arch_asym_cpu_priority(int cpu)
+{
+	if (static_branch_unlikely(&splpar_asym_pack))
+		return -cpu / threads_per_core;
+
+	return -cpu;
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/powerpc/kernel/swsusp_64.c b/arch/powerpc/kernel/swsusp_64.c
index 16ee3baaf09a..50fa8fc9ef95 100644
--- a/arch/powerpc/kernel/swsusp_64.c
+++ b/arch/powerpc/kernel/swsusp_64.c
@@ -11,6 +11,8 @@
 #include <linux/interrupt.h>
 #include <linux/nmi.h>
 
+void do_after_copyback(void);
+
 void do_after_copyback(void)
 {
 	iommu_restore();
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 7fab411378f2..17173b82ca21 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -543,3 +543,8 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount
+459	common	lsm_get_self_attr		sys_lsm_get_self_attr
+460	common	lsm_set_self_attr		sys_lsm_set_self_attr
+461	common	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/powerpc/kernel/trace/ftrace_entry.S b/arch/powerpc/kernel/trace/ftrace_entry.S
index 90701885762c..76dbe9fd2c0f 100644
--- a/arch/powerpc/kernel/trace/ftrace_entry.S
+++ b/arch/powerpc/kernel/trace/ftrace_entry.S
@@ -62,7 +62,7 @@
 	.endif
 
 	/* Save previous stack pointer (r1) */
-	addi	r8, r1, SWITCH_FRAME_SIZE
+	addi	r8, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
 	PPC_STL	r8, GPR1(r1)
 
 	.if \allregs == 1
@@ -162,7 +162,6 @@ _GLOBAL(ftrace_regs_caller)
 .globl ftrace_regs_call
 ftrace_regs_call:
 	bl	ftrace_stub
-	nop
 	ftrace_regs_exit 1
 
 _GLOBAL(ftrace_caller)
@@ -171,7 +170,6 @@ _GLOBAL(ftrace_caller)
 .globl ftrace_call
 ftrace_call:
 	bl	ftrace_stub
-	nop
 	ftrace_regs_exit 0
 
 _GLOBAL(ftrace_stub)
@@ -182,7 +180,7 @@ ftrace_no_trace:
 	mflr	r3
 	mtctr	r3
 	REST_GPR(3, r1)
-	addi	r1, r1, SWITCH_FRAME_SIZE
+	addi	r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
 	mtlr	r0
 	bctr
 #endif
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 5ea2014aff90..11e062b47d3f 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1439,10 +1439,12 @@ static int emulate_instruction(struct pt_regs *regs)
 	return -EINVAL;
 }
 
+#ifdef CONFIG_GENERIC_BUG
 int is_valid_bugaddr(unsigned long addr)
 {
 	return is_kernel_addr(addr);
 }
+#endif
 
 #ifdef CONFIG_MATH_EMULATION
 static int emulate_math(struct pt_regs *regs)
diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c
index 74ddf836f7a2..a0467e528b70 100644
--- a/arch/powerpc/kernel/udbg_16550.c
+++ b/arch/powerpc/kernel/udbg_16550.c
@@ -7,7 +7,6 @@
 #include <linux/types.h>
 #include <asm/udbg.h>
 #include <asm/io.h>
-#include <asm/reg_a2.h>
 #include <asm/early_ioremap.h>
 
 extern u8 real_readb(volatile u8 __iomem  *addr);
diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile
index 0c7d82c270c3..1b93655c2857 100644
--- a/arch/powerpc/kernel/vdso/Makefile
+++ b/arch/powerpc/kernel/vdso/Makefile
@@ -71,7 +71,7 @@ AS64FLAGS := -D__VDSO64__
 targets += vdso32.lds
 CPPFLAGS_vdso32.lds += -P -C -Upowerpc
 targets += vdso64.lds
-CPPFLAGS_vdso64.lds += -P -C -U$(ARCH)
+CPPFLAGS_vdso64.lds += -P -C
 
 # link rule for the .so file, .lds has to be first
 $(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday-32.o FORCE
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index 4094e4c4c77a..80b3f6e476b6 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -33,6 +33,7 @@ _GLOBAL(store_vr_state)
 	mfvscr	v0
 	li	r4, VRSTATE_VSCR
 	stvx	v0, r4, r3
+	lvx	v0, 0, r3
 	blr
 EXPORT_SYMBOL(store_vr_state)
 
@@ -109,6 +110,7 @@ _GLOBAL(save_altivec)
 	mfvscr	v0
 	li	r4,VRSTATE_VSCR
 	stvx	v0,r4,r7
+	lvx	v0,0,r7
 	blr
 
 #ifdef CONFIG_VSX
diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c
index 85846cadb9b5..27fa9098a5b7 100644
--- a/arch/powerpc/kexec/core.c
+++ b/arch/powerpc/kexec/core.c
@@ -75,6 +75,7 @@ void arch_crash_save_vmcoreinfo(void)
 	VMCOREINFO_OFFSET(mmu_psize_def, shift);
 #endif
 	VMCOREINFO_SYMBOL(cur_cpu_spec);
+	VMCOREINFO_OFFSET(cpu_spec, cpu_features);
 	VMCOREINFO_OFFSET(cpu_spec, mmu_features);
 	vmcoreinfo_append_str("NUMBER(RADIX_MMU)=%d\n", early_radix_enabled());
 	vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c
index 0bee7ca9a77c..762e4d09aacf 100644
--- a/arch/powerpc/kexec/core_64.c
+++ b/arch/powerpc/kexec/core_64.c
@@ -283,8 +283,7 @@ static void kexec_prepare_cpus(void)
  * We could use a smaller stack if we don't care about anything using
  * current, but that audit has not been performed.
  */
-static union thread_union kexec_stack __init_task_data =
-	{ };
+static union thread_union kexec_stack = { };
 
 /*
  * For similar reasons to the stack above, the kexecing CPU needs to be on a
diff --git a/arch/powerpc/kexec/elf_64.c b/arch/powerpc/kexec/elf_64.c
index eeb258002d1e..904016cf89ea 100644
--- a/arch/powerpc/kexec/elf_64.c
+++ b/arch/powerpc/kexec/elf_64.c
@@ -59,7 +59,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 	if (ret)
 		goto out;
 
-	pr_debug("Loaded the kernel at 0x%lx\n", kernel_load_addr);
+	kexec_dprintk("Loaded the kernel at 0x%lx\n", kernel_load_addr);
 
 	ret = kexec_load_purgatory(image, &pbuf);
 	if (ret) {
@@ -67,7 +67,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 		goto out;
 	}
 
-	pr_debug("Loaded purgatory at 0x%lx\n", pbuf.mem);
+	kexec_dprintk("Loaded purgatory at 0x%lx\n", pbuf.mem);
 
 	/* Load additional segments needed for panic kernel */
 	if (image->type == KEXEC_TYPE_CRASH) {
@@ -99,7 +99,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 			goto out;
 		initrd_load_addr = kbuf.mem;
 
-		pr_debug("Loaded initrd at 0x%lx\n", initrd_load_addr);
+		kexec_dprintk("Loaded initrd at 0x%lx\n", initrd_load_addr);
 	}
 
 	fdt = of_kexec_alloc_and_setup_fdt(image, initrd_load_addr,
@@ -132,7 +132,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 
 	fdt_load_addr = kbuf.mem;
 
-	pr_debug("Loaded device tree at 0x%lx\n", fdt_load_addr);
+	kexec_dprintk("Loaded device tree at 0x%lx\n", fdt_load_addr);
 
 	slave_code = elf_info.buffer + elf_info.proghdrs[0].p_offset;
 	ret = setup_purgatory_ppc64(image, slave_code, fdt, kernel_load_addr,
diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c
index 961a6dd67365..5b4c5cb23354 100644
--- a/arch/powerpc/kexec/file_load_64.c
+++ b/arch/powerpc/kexec/file_load_64.c
@@ -577,7 +577,7 @@ static int add_usable_mem_property(void *fdt, struct device_node *dn,
 		       NODE_PATH_LEN, dn);
 		return -EOVERFLOW;
 	}
-	pr_debug("Memory node path: %s\n", path);
+	kexec_dprintk("Memory node path: %s\n", path);
 
 	/* Now that we know the path, find its offset in kdump kernel's fdt */
 	node = fdt_path_offset(fdt, path);
@@ -590,8 +590,8 @@ static int add_usable_mem_property(void *fdt, struct device_node *dn,
 	/* Get the address & size cells */
 	n_mem_addr_cells = of_n_addr_cells(dn);
 	n_mem_size_cells = of_n_size_cells(dn);
-	pr_debug("address cells: %d, size cells: %d\n", n_mem_addr_cells,
-		 n_mem_size_cells);
+	kexec_dprintk("address cells: %d, size cells: %d\n", n_mem_addr_cells,
+		      n_mem_size_cells);
 
 	um_info->idx  = 0;
 	if (!check_realloc_usable_mem(um_info, 2)) {
@@ -664,7 +664,7 @@ static int update_usable_mem_fdt(void *fdt, struct crash_mem *usable_mem)
 
 	node = fdt_path_offset(fdt, "/ibm,dynamic-reconfiguration-memory");
 	if (node == -FDT_ERR_NOTFOUND)
-		pr_debug("No dynamic reconfiguration memory found\n");
+		kexec_dprintk("No dynamic reconfiguration memory found\n");
 	else if (node < 0) {
 		pr_err("Malformed device tree: error reading /ibm,dynamic-reconfiguration-memory.\n");
 		return -EINVAL;
@@ -776,8 +776,8 @@ static void update_backup_region_phdr(struct kimage *image, Elf64_Ehdr *ehdr)
 	for (i = 0; i < ehdr->e_phnum; i++) {
 		if (phdr->p_paddr == BACKUP_SRC_START) {
 			phdr->p_offset = image->arch.backup_start;
-			pr_debug("Backup region offset updated to 0x%lx\n",
-				 image->arch.backup_start);
+			kexec_dprintk("Backup region offset updated to 0x%lx\n",
+				      image->arch.backup_start);
 			return;
 		}
 	}
@@ -850,7 +850,7 @@ int load_crashdump_segments_ppc64(struct kimage *image,
 		pr_err("Failed to load backup segment\n");
 		return ret;
 	}
-	pr_debug("Loaded the backup region at 0x%lx\n", kbuf->mem);
+	kexec_dprintk("Loaded the backup region at 0x%lx\n", kbuf->mem);
 
 	/* Load elfcorehdr segment - to export crashing kernel's vmcore */
 	ret = load_elfcorehdr_segment(image, kbuf);
@@ -858,8 +858,8 @@ int load_crashdump_segments_ppc64(struct kimage *image,
 		pr_err("Failed to load elfcorehdr segment\n");
 		return ret;
 	}
-	pr_debug("Loaded elf core header at 0x%lx, bufsz=0x%lx memsz=0x%lx\n",
-		 image->elf_load_addr, kbuf->bufsz, kbuf->memsz);
+	kexec_dprintk("Loaded elf core header at 0x%lx, bufsz=0x%lx memsz=0x%lx\n",
+		      image->elf_load_addr, kbuf->bufsz, kbuf->memsz);
 
 	return 0;
 }
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 6cd20ab9e94e..8acec144120e 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -302,11 +302,11 @@ static int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu,
 
 	switch (priority) {
 	case BOOK3S_IRQPRIO_DECREMENTER:
-		deliver = (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
+		deliver = !kvmhv_is_nestedv2() && (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
 		vec = BOOK3S_INTERRUPT_DECREMENTER;
 		break;
 	case BOOK3S_IRQPRIO_EXTERNAL:
-		deliver = (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
+		deliver = !kvmhv_is_nestedv2() && (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
 		vec = BOOK3S_INTERRUPT_EXTERNAL;
 		break;
 	case BOOK3S_IRQPRIO_SYSTEM_RESET:
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 175a8eb2681f..4a1abb9f7c05 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -40,6 +40,9 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
 	unsigned long quadrant, ret = n;
 	bool is_load = !!to;
 
+	if (kvmhv_is_nestedv2())
+		return H_UNSUPPORTED;
+
 	/* Can't access quadrants 1 or 2 in non-HV mode, call the HV to do it */
 	if (kvmhv_on_pseries())
 		return plpar_hcall_norets(H_COPY_TOFROM_GUEST, lpid, pid, eaddr,
@@ -97,7 +100,7 @@ static long kvmhv_copy_tofrom_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr,
 					  void *to, void *from, unsigned long n)
 {
 	int lpid = vcpu->kvm->arch.lpid;
-	int pid = kvmppc_get_pid(vcpu);
+	int pid;
 
 	/* This would cause a data segment intr so don't allow the access */
 	if (eaddr & (0x3FFUL << 52))
@@ -110,6 +113,8 @@ static long kvmhv_copy_tofrom_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr,
 	/* If accessing quadrant 3 then pid is expected to be 0 */
 	if (((eaddr >> 62) & 0x3) == 0x3)
 		pid = 0;
+	else
+		pid = kvmppc_get_pid(vcpu);
 
 	eaddr &= ~(0xFFFUL << 52);
 
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 14c6d7e318da..b569ebaa590e 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -20,6 +20,7 @@
 #include <linux/iommu.h>
 #include <linux/file.h>
 #include <linux/mm.h>
+#include <linux/rcupdate_wait.h>
 
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 1ed6ec140701..e48126a59ba7 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -650,7 +650,8 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
 	return err;
 }
 
-static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap)
+static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap,
+			       struct kvmppc_vpa *old_vpap)
 {
 	struct kvm *kvm = vcpu->kvm;
 	void *va;
@@ -690,9 +691,8 @@ static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap)
 		kvmppc_unpin_guest_page(kvm, va, gpa, false);
 		va = NULL;
 	}
-	if (vpap->pinned_addr)
-		kvmppc_unpin_guest_page(kvm, vpap->pinned_addr, vpap->gpa,
-					vpap->dirty);
+	*old_vpap = *vpap;
+
 	vpap->gpa = gpa;
 	vpap->pinned_addr = va;
 	vpap->dirty = false;
@@ -702,6 +702,9 @@ static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap)
 
 static void kvmppc_update_vpas(struct kvm_vcpu *vcpu)
 {
+	struct kvm *kvm = vcpu->kvm;
+	struct kvmppc_vpa old_vpa = { 0 };
+
 	if (!(vcpu->arch.vpa.update_pending ||
 	      vcpu->arch.slb_shadow.update_pending ||
 	      vcpu->arch.dtl.update_pending))
@@ -709,17 +712,34 @@ static void kvmppc_update_vpas(struct kvm_vcpu *vcpu)
 
 	spin_lock(&vcpu->arch.vpa_update_lock);
 	if (vcpu->arch.vpa.update_pending) {
-		kvmppc_update_vpa(vcpu, &vcpu->arch.vpa);
-		if (vcpu->arch.vpa.pinned_addr)
+		kvmppc_update_vpa(vcpu, &vcpu->arch.vpa, &old_vpa);
+		if (old_vpa.pinned_addr) {
+			if (kvmhv_is_nestedv2())
+				kvmhv_nestedv2_set_vpa(vcpu, ~0ull);
+			kvmppc_unpin_guest_page(kvm, old_vpa.pinned_addr, old_vpa.gpa,
+						old_vpa.dirty);
+		}
+		if (vcpu->arch.vpa.pinned_addr) {
 			init_vpa(vcpu, vcpu->arch.vpa.pinned_addr);
+			if (kvmhv_is_nestedv2())
+				kvmhv_nestedv2_set_vpa(vcpu, __pa(vcpu->arch.vpa.pinned_addr));
+		}
 	}
 	if (vcpu->arch.dtl.update_pending) {
-		kvmppc_update_vpa(vcpu, &vcpu->arch.dtl);
+		kvmppc_update_vpa(vcpu, &vcpu->arch.dtl, &old_vpa);
+		if (old_vpa.pinned_addr)
+			kvmppc_unpin_guest_page(kvm, old_vpa.pinned_addr, old_vpa.gpa,
+						old_vpa.dirty);
 		vcpu->arch.dtl_ptr = vcpu->arch.dtl.pinned_addr;
 		vcpu->arch.dtl_index = 0;
 	}
-	if (vcpu->arch.slb_shadow.update_pending)
-		kvmppc_update_vpa(vcpu, &vcpu->arch.slb_shadow);
+	if (vcpu->arch.slb_shadow.update_pending) {
+		kvmppc_update_vpa(vcpu, &vcpu->arch.slb_shadow, &old_vpa);
+		if (old_vpa.pinned_addr)
+			kvmppc_unpin_guest_page(kvm, old_vpa.pinned_addr, old_vpa.gpa,
+						old_vpa.dirty);
+	}
+
 	spin_unlock(&vcpu->arch.vpa_update_lock);
 }
 
@@ -1597,7 +1617,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 	 * That can happen due to a bug, or due to a machine check
 	 * occurring at just the wrong time.
 	 */
-	if (__kvmppc_get_msr_hv(vcpu) & MSR_HV) {
+	if (!kvmhv_is_nestedv2() && (__kvmppc_get_msr_hv(vcpu) & MSR_HV)) {
 		printk(KERN_EMERG "KVM trap in HV mode!\n");
 		printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n",
 			vcpu->arch.trap, kvmppc_get_pc(vcpu),
@@ -1688,7 +1708,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 	{
 		int i;
 
-		if (unlikely(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) {
+		if (!kvmhv_is_nestedv2() && unlikely(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) {
 			/*
 			 * Guest userspace executed sc 1. This can only be
 			 * reached by the P9 path because the old path
@@ -4084,6 +4104,8 @@ static int kvmhv_vcpu_entry_nestedv2(struct kvm_vcpu *vcpu, u64 time_limit,
 	if (rc < 0)
 		return -EINVAL;
 
+	kvmppc_gse_put_u64(io->vcpu_run_input, KVMPPC_GSID_LPCR, lpcr);
+
 	accumulate_time(vcpu, &vcpu->arch.in_guest);
 	rc = plpar_guest_run_vcpu(0, vcpu->kvm->arch.lpid, vcpu->vcpu_id,
 				  &trap, &i);
@@ -4736,13 +4758,19 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 
 	if (!nested) {
 		kvmppc_core_prepare_to_enter(vcpu);
-		if (__kvmppc_get_msr_hv(vcpu) & MSR_EE) {
-			if (xive_interrupt_pending(vcpu))
+		if (test_bit(BOOK3S_IRQPRIO_EXTERNAL,
+			     &vcpu->arch.pending_exceptions) ||
+		    xive_interrupt_pending(vcpu)) {
+			/*
+			 * For nested HV, don't synthesize but always pass MER,
+			 * the L0 will be able to optimise that more
+			 * effectively than manipulating registers directly.
+			 */
+			if (!kvmhv_on_pseries() && (__kvmppc_get_msr_hv(vcpu) & MSR_EE))
 				kvmppc_inject_interrupt_hv(vcpu,
-						BOOK3S_INTERRUPT_EXTERNAL, 0);
-		} else if (test_bit(BOOK3S_IRQPRIO_EXTERNAL,
-			     &vcpu->arch.pending_exceptions)) {
-			lpcr |= LPCR_MER;
+							   BOOK3S_INTERRUPT_EXTERNAL, 0);
+			else
+				lpcr |= LPCR_MER;
 		}
 	} else if (vcpu->arch.pending_exceptions ||
 		   vcpu->arch.doorbell_request ||
@@ -4806,7 +4834,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 	 * entering a nested guest in which case the decrementer is now owned
 	 * by L2 and the L1 decrementer is provided in hdec_expires
 	 */
-	if (kvmppc_core_pending_dec(vcpu) &&
+	if (!kvmhv_is_nestedv2() && kvmppc_core_pending_dec(vcpu) &&
 			((tb < kvmppc_dec_expires_host_tb(vcpu)) ||
 			 (trap == BOOK3S_INTERRUPT_SYSCALL &&
 			  kvmppc_get_gpr(vcpu, 3) == H_ENTER_NESTED)))
@@ -4949,7 +4977,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
 		if (run->exit_reason == KVM_EXIT_PAPR_HCALL) {
 			accumulate_time(vcpu, &vcpu->arch.hcall);
 
-			if (WARN_ON_ONCE(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) {
+			if (!kvmhv_is_nestedv2() && WARN_ON_ONCE(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) {
 				/*
 				 * These should have been caught reflected
 				 * into the guest by now. Final sanity check:
@@ -5691,10 +5719,12 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
 			kvmhv_set_ptbl_entry(kvm->arch.lpid, 0, 0);
 	}
 
-	if (kvmhv_is_nestedv2())
+	if (kvmhv_is_nestedv2()) {
+		kvmhv_flush_lpid(kvm->arch.lpid);
 		plpar_guest_delete(0, kvm->arch.lpid);
-	else
+	} else {
 		kvmppc_free_lpid(kvm->arch.lpid);
+	}
 
 	kvmppc_free_pimap(kvm);
 }
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 3b658b8696bc..5c375ec1a3c6 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -503,7 +503,7 @@ void kvmhv_nested_exit(void)
 	}
 }
 
-static void kvmhv_flush_lpid(u64 lpid)
+void kvmhv_flush_lpid(u64 lpid)
 {
 	long rc;
 
diff --git a/arch/powerpc/kvm/book3s_hv_nestedv2.c b/arch/powerpc/kvm/book3s_hv_nestedv2.c
index fd3c4f2d9480..5378eb40b162 100644
--- a/arch/powerpc/kvm/book3s_hv_nestedv2.c
+++ b/arch/powerpc/kvm/book3s_hv_nestedv2.c
@@ -856,6 +856,35 @@ free_gsb:
 EXPORT_SYMBOL_GPL(kvmhv_nestedv2_set_ptbl_entry);
 
 /**
+ * kvmhv_nestedv2_set_vpa() - register L2 VPA with L0
+ * @vcpu: vcpu
+ * @vpa: L1 logical real address
+ */
+int kvmhv_nestedv2_set_vpa(struct kvm_vcpu *vcpu, unsigned long vpa)
+{
+	struct kvmhv_nestedv2_io *io;
+	struct kvmppc_gs_buff *gsb;
+	int rc = 0;
+
+	io = &vcpu->arch.nestedv2_io;
+	gsb = io->vcpu_run_input;
+
+	kvmppc_gsb_reset(gsb);
+	rc = kvmppc_gse_put_u64(gsb, KVMPPC_GSID_VPA, vpa);
+	if (rc < 0)
+		goto out;
+
+	rc = kvmppc_gsb_send(gsb, 0);
+	if (rc < 0)
+		pr_err("KVM-NESTEDv2: couldn't register the L2 VPA (rc=%d)\n", rc);
+
+out:
+	kvmppc_gsb_reset(gsb);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(kvmhv_nestedv2_set_vpa);
+
+/**
  * kvmhv_nestedv2_parse_output() - receive values from H_GUEST_RUN_VCPU output
  * @vcpu: vcpu
  *
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 9118242063fb..5b92619a05fd 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -604,6 +604,7 @@ static void kvmppc_set_pvr_pr(struct kvm_vcpu *vcpu, u32 pvr)
 	case PVR_POWER8:
 	case PVR_POWER8E:
 	case PVR_POWER8NVL:
+	case PVR_HX_C2000:
 	case PVR_POWER9:
 		vcpu->arch.hflags |= BOOK3S_HFLAG_MULTI_PGSIZE |
 			BOOK3S_HFLAG_NEW_TLBIE;
diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c
index 077fd88a0b68..ec60c7979718 100644
--- a/arch/powerpc/kvm/emulate_loadstore.c
+++ b/arch/powerpc/kvm/emulate_loadstore.c
@@ -93,7 +93,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 
 	emulated = EMULATE_FAIL;
 	vcpu->arch.regs.msr = kvmppc_get_msr(vcpu);
-	kvmhv_nestedv2_reload_ptregs(vcpu, &vcpu->arch.regs);
 	if (analyse_instr(&op, &vcpu->arch.regs, inst) == 0) {
 		int type = op.type & INSTR_TYPE_MASK;
 		int size = GETSIZE(op.type);
@@ -112,7 +111,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 						op.reg, size, !instr_byte_swap);
 
 			if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
-				kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
+				kvmppc_set_gpr(vcpu, op.update_reg, vcpu->arch.vaddr_accessed);
 
 			break;
 		}
@@ -132,7 +131,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 					     KVM_MMIO_REG_FPR|op.reg, size, 1);
 
 			if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
-				kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
+				kvmppc_set_gpr(vcpu, op.update_reg, vcpu->arch.vaddr_accessed);
 
 			break;
 #endif
@@ -224,16 +223,17 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 			break;
 		}
 #endif
-		case STORE:
-			/* if need byte reverse, op.val has been reversed by
-			 * analyse_instr().
-			 */
-			emulated = kvmppc_handle_store(vcpu, op.val, size, 1);
+		case STORE: {
+			int instr_byte_swap = op.type & BYTEREV;
+
+			emulated = kvmppc_handle_store(vcpu, kvmppc_get_gpr(vcpu, op.reg),
+						       size, !instr_byte_swap);
 
 			if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
-				kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
+				kvmppc_set_gpr(vcpu, op.update_reg, vcpu->arch.vaddr_accessed);
 
 			break;
+		}
 #ifdef CONFIG_PPC_FPU
 		case STORE_FP:
 			if (kvmppc_check_fp_disabled(vcpu))
@@ -254,7 +254,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 					kvmppc_get_fpr(vcpu, op.reg), size, 1);
 
 			if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
-				kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
+				kvmppc_set_gpr(vcpu, op.update_reg, vcpu->arch.vaddr_accessed);
 
 			break;
 #endif
@@ -358,7 +358,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 	}
 
 	trace_kvm_ppc_instr(ppc_inst_val(inst), kvmppc_get_pc(vcpu), emulated);
-	kvmhv_nestedv2_mark_dirty_ptregs(vcpu, &vcpu->arch.regs);
 
 	/* Advance past emulated instruction. */
 	if (emulated != EMULATE_FAIL)
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 51ad0397c17a..6eac63e79a89 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -45,7 +45,7 @@ obj-$(CONFIG_FUNCTION_ERROR_INJECTION)	+= error-inject.o
 # so it is only needed for modules, and only for older linkers which
 # do not support --save-restore-funcs
 ifndef CONFIG_LD_IS_BFD
-extra-$(CONFIG_PPC64)	+= crtsavres.o
+always-$(CONFIG_PPC64)	+= crtsavres.o
 endif
 
 obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index a4ab8625061a..5766180f5380 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -586,6 +586,8 @@ static int do_fp_load(struct instruction_op *op, unsigned long ea,
 	} u;
 
 	nb = GETSIZE(op->type);
+	if (nb > sizeof(u))
+		return -EINVAL;
 	if (!address_ok(regs, ea, nb))
 		return -EFAULT;
 	rn = op->reg;
@@ -636,6 +638,8 @@ static int do_fp_store(struct instruction_op *op, unsigned long ea,
 	} u;
 
 	nb = GETSIZE(op->type);
+	if (nb > sizeof(u))
+		return -EINVAL;
 	if (!address_ok(regs, ea, nb))
 		return -EFAULT;
 	rn = op->reg;
@@ -680,6 +684,9 @@ static nokprobe_inline int do_vec_load(int rn, unsigned long ea,
 		u8 b[sizeof(__vector128)];
 	} u = {};
 
+	if (size > sizeof(u))
+		return -EINVAL;
+
 	if (!address_ok(regs, ea & ~0xfUL, 16))
 		return -EFAULT;
 	/* align to multiple of size */
@@ -688,7 +695,7 @@ static nokprobe_inline int do_vec_load(int rn, unsigned long ea,
 	if (err)
 		return err;
 	if (unlikely(cross_endian))
-		do_byte_reverse(&u.b[ea & 0xf], size);
+		do_byte_reverse(&u.b[ea & 0xf], min_t(size_t, size, sizeof(u)));
 	preempt_disable();
 	if (regs->msr & MSR_VEC)
 		put_vr(rn, &u.v);
@@ -707,6 +714,9 @@ static nokprobe_inline int do_vec_store(int rn, unsigned long ea,
 		u8 b[sizeof(__vector128)];
 	} u;
 
+	if (size > sizeof(u))
+		return -EINVAL;
+
 	if (!address_ok(regs, ea & ~0xfUL, 16))
 		return -EFAULT;
 	/* align to multiple of size */
@@ -719,7 +729,7 @@ static nokprobe_inline int do_vec_store(int rn, unsigned long ea,
 		u.v = current->thread.vr_state.vr[rn];
 	preempt_enable();
 	if (unlikely(cross_endian))
-		do_byte_reverse(&u.b[ea & 0xf], size);
+		do_byte_reverse(&u.b[ea & 0xf], min_t(size_t, size, sizeof(u)));
 	return copy_mem_out(&u.b[ea & 0xf], ea, size, regs);
 }
 #endif /* CONFIG_ALTIVEC */
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index ad2afa08e62e..0626a25b0d72 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -310,9 +310,16 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags, unsigned long flags
 			else
 				rflags |= 0x3;
 		}
+		VM_WARN_ONCE(!(pteflags & _PAGE_RWX), "no-access mapping request");
 	} else {
 		if (pteflags & _PAGE_RWX)
 			rflags |= 0x2;
+		/*
+		 * We should never hit this in normal fault handling because
+		 * a permission check (check_pte_access()) will bubble this
+		 * to higher level linux handler even for PAGE_NONE.
+		 */
+		VM_WARN_ONCE(!(pteflags & _PAGE_RWX), "no-access mapping request");
 		if (!((pteflags & _PAGE_WRITE) && (pteflags & _PAGE_DIRTY)))
 			rflags |= 0x1;
 	}
diff --git a/arch/powerpc/mm/book3s64/iommu_api.c b/arch/powerpc/mm/book3s64/iommu_api.c
index d19fb1f3007d..c0e8d597e4cb 100644
--- a/arch/powerpc/mm/book3s64/iommu_api.c
+++ b/arch/powerpc/mm/book3s64/iommu_api.c
@@ -97,7 +97,7 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 	}
 
 	mmap_read_lock(mm);
-	chunk = (1UL << (PAGE_SHIFT + MAX_ORDER)) /
+	chunk = (1UL << (PAGE_SHIFT + MAX_PAGE_ORDER)) /
 			sizeof(struct vm_area_struct *);
 	chunk = min(chunk, entries);
 	for (entry = 0; entry < entries; entry += chunk) {
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index be229290a6a7..3438ab72c346 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -542,6 +542,7 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
 	set_pte_at(vma->vm_mm, addr, ptep, pte);
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 /*
  * For hash translation mode, we use the deposited table to store hash slot
  * information and they are stored at PTRS_PER_PMD offset from related pmd
@@ -563,6 +564,7 @@ int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
 
 	return true;
 }
+#endif
 
 /*
  * Does the CPU support tlbie?
diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c
index 125733962033..a974baf8f327 100644
--- a/arch/powerpc/mm/book3s64/pkeys.c
+++ b/arch/powerpc/mm/book3s64/pkeys.c
@@ -89,7 +89,8 @@ static int __init scan_pkey_feature(void)
 			unsigned long pvr = mfspr(SPRN_PVR);
 
 			if (PVR_VER(pvr) == PVR_POWER8 || PVR_VER(pvr) == PVR_POWER8E ||
-			    PVR_VER(pvr) == PVR_POWER8NVL || PVR_VER(pvr) == PVR_POWER9)
+			    PVR_VER(pvr) == PVR_POWER8NVL || PVR_VER(pvr) == PVR_POWER9 ||
+			    PVR_VER(pvr) == PVR_HX_C2000)
 				pkeys_total = 32;
 		}
 	}
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 9e49ede2bc1c..53335ae21a40 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -497,6 +497,8 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
 		goto done;
 	}
 	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+	if (fault & VM_FAULT_MAJOR)
+		flags |= FAULT_FLAG_TRIED;
 
 	if (fault_signal_pending(fault, regs))
 		return user_mode(regs) ? 0 : SIGBUS;
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index f7c683b672c1..0a540b37aab6 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -615,7 +615,7 @@ void __init gigantic_hugetlb_cma_reserve(void)
 		order = mmu_psize_to_shift(MMU_PAGE_16G) - PAGE_SHIFT;
 
 	if (order) {
-		VM_WARN_ON(order <= MAX_ORDER);
+		VM_WARN_ON(order <= MAX_PAGE_ORDER);
 		hugetlb_cma_reserve(order);
 	}
 }
diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c
index 119ef491f797..d3a7726ecf51 100644
--- a/arch/powerpc/mm/init-common.c
+++ b/arch/powerpc/mm/init-common.c
@@ -126,7 +126,7 @@ void pgtable_cache_add(unsigned int shift)
 	 * as to leave enough 0 bits in the address to contain it. */
 	unsigned long minalign = max(MAX_PGTABLE_INDEX_SIZE + 1,
 				     HUGEPD_SHIFT_MASK + 1);
-	struct kmem_cache *new;
+	struct kmem_cache *new = NULL;
 
 	/* It would be nice if this was a BUILD_BUG_ON(), but at the
 	 * moment, gcc doesn't seem to recognize is_power_of_2 as a
@@ -139,7 +139,8 @@ void pgtable_cache_add(unsigned int shift)
 
 	align = max_t(unsigned long, align, minalign);
 	name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift);
-	new = kmem_cache_create(name, table_size, align, 0, ctor(shift));
+	if (name)
+		new = kmem_cache_create(name, table_size, align, 0, ctor(shift));
 	if (!new)
 		panic("Could not allocate pgtable cache for order %d", shift);
 
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index 7f9ff0640124..72341b9fb552 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -181,3 +181,8 @@ static inline bool debug_pagealloc_enabled_or_kfence(void)
 {
 	return IS_ENABLED(CONFIG_KFENCE) || debug_pagealloc_enabled();
 }
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+int create_section_mapping(unsigned long start, unsigned long end,
+			   int nid, pgprot_t prot);
+#endif
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 10b946e9c6e7..b7ff680cde96 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2312,7 +2312,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			struct cpu_hw_events *cpuhw;
 			cpuhw = this_cpu_ptr(&cpu_hw_events);
 			power_pmu_bhrb_read(event, cpuhw);
-			perf_sample_save_brstack(&data, event, &cpuhw->bhrb_stack);
+			perf_sample_save_brstack(&data, event, &cpuhw->bhrb_stack, NULL);
 		}
 
 		if (event->attr.sample_type & PERF_SAMPLE_DATA_SRC &&
diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c
index 39dbe6b348df..27f18119fda1 100644
--- a/arch/powerpc/perf/hv-gpci.c
+++ b/arch/powerpc/perf/hv-gpci.c
@@ -534,6 +534,9 @@ static ssize_t affinity_domain_via_partition_show(struct device *dev, struct dev
 	if (!ret)
 		goto parse_result;
 
+	if (ret && (ret != H_PARAMETER))
+		goto out;
+
 	/*
 	 * ret value as 'H_PARAMETER' implies that the current buffer size
 	 * can't accommodate all the information, and a partial buffer
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index 5d12ca386c1f..8664a7d297ad 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -299,6 +299,8 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu)
 	attr_group->attrs = attrs;
 	do {
 		ev_val_str = kasprintf(GFP_KERNEL, "event=0x%x", pmu->events[i].value);
+		if (!ev_val_str)
+			continue;
 		dev_str = device_str_attr_create(pmu->events[i].name, ev_val_str);
 		if (!dev_str)
 			continue;
@@ -306,6 +308,8 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu)
 		attrs[j++] = dev_str;
 		if (pmu->events[i].scale) {
 			ev_scale_str = kasprintf(GFP_KERNEL, "%s.scale", pmu->events[i].name);
+			if (!ev_scale_str)
+				continue;
 			dev_str = device_str_attr_create(ev_scale_str, pmu->events[i].scale);
 			if (!dev_str)
 				continue;
@@ -315,6 +319,8 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu)
 
 		if (pmu->events[i].unit) {
 			ev_unit_str = kasprintf(GFP_KERNEL, "%s.unit", pmu->events[i].name);
+			if (!ev_unit_str)
+				continue;
 			dev_str = device_str_attr_create(ev_unit_str, pmu->events[i].unit);
 			if (!dev_str)
 				continue;
diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig
index 1624ebf95497..35a1f4b9f827 100644
--- a/arch/powerpc/platforms/44x/Kconfig
+++ b/arch/powerpc/platforms/44x/Kconfig
@@ -173,6 +173,7 @@ config ISS4xx
 config CURRITUCK
 	bool "IBM Currituck (476fpe) Support"
 	depends on PPC_47x
+	select I2C
 	select SWIOTLB
 	select 476FPE
 	select FORCE_PCI
diff --git a/arch/powerpc/platforms/44x/idle.c b/arch/powerpc/platforms/44x/idle.c
index f533b495e7db..e2eeef8dff78 100644
--- a/arch/powerpc/platforms/44x/idle.c
+++ b/arch/powerpc/platforms/44x/idle.c
@@ -27,7 +27,7 @@ static void ppc44x_idle(void)
 	isync();
 }
 
-int __init ppc44x_idle_init(void)
+static int __init ppc44x_idle_init(void)
 {
 	if (!mode_spin) {
 		/* If we are not setting spin mode 
diff --git a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
index 6f08d07aee3b..e995eb30bf09 100644
--- a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
+++ b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
@@ -17,6 +17,8 @@
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 
+#include "mpc5121_ads.h"
+
 static struct device_node *cpld_pic_node;
 static struct irq_domain *cpld_pic_host;
 
diff --git a/arch/powerpc/platforms/512x/pdm360ng.c b/arch/powerpc/platforms/512x/pdm360ng.c
index ce51cfeeb066..8bbbf78bb42b 100644
--- a/arch/powerpc/platforms/512x/pdm360ng.c
+++ b/arch/powerpc/platforms/512x/pdm360ng.c
@@ -101,7 +101,7 @@ static inline void __init pdm360ng_touchscreen_init(void)
 }
 #endif /* CONFIG_TOUCHSCREEN_ADS7846 */
 
-void __init pdm360ng_init(void)
+static void __init pdm360ng_init(void)
 {
 	mpc512x_init();
 	pdm360ng_touchscreen_init();
diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c
index 9833c36bda83..c9664e46b03d 100644
--- a/arch/powerpc/platforms/83xx/suspend.c
+++ b/arch/powerpc/platforms/83xx/suspend.c
@@ -261,9 +261,10 @@ static int mpc83xx_suspend_begin(suspend_state_t state)
 
 static int agent_thread_fn(void *data)
 {
+	set_freezable();
+
 	while (1) {
-		wait_event_interruptible(agent_wq, pci_pm_state >= 2);
-		try_to_freeze();
+		wait_event_freezable(agent_wq, pci_pm_state >= 2);
 
 		if (signal_pending(current) || pci_pm_state < 2)
 			continue;
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
index ec9f60fbebc7..e0cec670d8db 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
@@ -76,7 +76,7 @@ static void __init mpc85xx_rdb_setup_arch(void)
 			/* P1025 has pins muxed for QE and other functions. To
 			* enable QE UEC mode, we need to set bit QE0 for UCC1
 			* in Eth mode, QE0 and QE3 for UCC5 in Eth mode, QE9
-			* and QE12 for QE MII management singals in PMUXCR
+			* and QE12 for QE MII management signals in PMUXCR
 			* register.
 			*/
 				setbits32(&guts->pmuxcr, MPC85xx_PMUXCR_QE(0) |
diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig
index 67467cd6f34c..06b1e5c49d6f 100644
--- a/arch/powerpc/platforms/86xx/Kconfig
+++ b/arch/powerpc/platforms/86xx/Kconfig
@@ -52,10 +52,3 @@ config MPC8641
 	select MPIC
 	default y if GEF_SBC610 || GEF_SBC310 || GEF_PPC9A \
 			|| MVME7100
-
-config MPC8610
-	bool
-	select HAVE_PCI
-	select FSL_PCI if PCI
-	select PPC_UDBG_16550
-	select MPIC
diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c
index ef985ba2bf21..0761d98e5be3 100644
--- a/arch/powerpc/platforms/pasemi/setup.c
+++ b/arch/powerpc/platforms/pasemi/setup.c
@@ -64,7 +64,7 @@ static void __noreturn pas_restart(char *cmd)
 }
 
 #ifdef CONFIG_PPC_PASEMI_NEMO
-void pas_shutdown(void)
+static void pas_shutdown(void)
 {
 	/* Set the PLD bit that makes the SB600 think the power button is being pressed */
 	void __iomem *pld_map = ioremap(0xf5000000,4096);
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index c83d1e14077e..15644be31990 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -413,7 +413,7 @@ static void __init smp_psurge_setup_cpu(int cpu_nr)
 		printk(KERN_ERR "Couldn't get primary IPI interrupt");
 }
 
-void __init smp_psurge_take_timebase(void)
+static void __init smp_psurge_take_timebase(void)
 {
 	if (psurge_type != PSURGE_DUAL)
 		return;
@@ -429,7 +429,7 @@ void __init smp_psurge_take_timebase(void)
 	set_dec(tb_ticks_per_jiffy/2);
 }
 
-void __init smp_psurge_give_timebase(void)
+static void __init smp_psurge_give_timebase(void)
 {
 	/* Nothing to do here */
 }
diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c
index f9a7001dacb7..56a1f7ce78d2 100644
--- a/arch/powerpc/platforms/powernv/opal-irqchip.c
+++ b/arch/powerpc/platforms/powernv/opal-irqchip.c
@@ -275,6 +275,8 @@ int __init opal_event_init(void)
 		else
 			name = kasprintf(GFP_KERNEL, "opal");
 
+		if (!name)
+			continue;
 		/* Install interrupt handler */
 		rc = request_irq(r->start, opal_interrupt, r->flags & IRQD_TRIGGER_MASK,
 				 name, NULL);
diff --git a/arch/powerpc/platforms/powernv/opal-powercap.c b/arch/powerpc/platforms/powernv/opal-powercap.c
index 7bfe4cbeb35a..ea917266aa17 100644
--- a/arch/powerpc/platforms/powernv/opal-powercap.c
+++ b/arch/powerpc/platforms/powernv/opal-powercap.c
@@ -196,6 +196,12 @@ void __init opal_powercap_init(void)
 
 		j = 0;
 		pcaps[i].pg.name = kasprintf(GFP_KERNEL, "%pOFn", node);
+		if (!pcaps[i].pg.name) {
+			kfree(pcaps[i].pattrs);
+			kfree(pcaps[i].pg.attrs);
+			goto out_pcaps_pattrs;
+		}
+
 		if (has_min) {
 			powercap_add_attr(min, "powercap-min",
 					  &pcaps[i].pattrs[j]);
diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c
index 327e2f76905d..b66b06efcef1 100644
--- a/arch/powerpc/platforms/powernv/opal-prd.c
+++ b/arch/powerpc/platforms/powernv/opal-prd.c
@@ -66,6 +66,8 @@ static bool opal_prd_range_is_valid(uint64_t addr, uint64_t size)
 		const char *label;
 
 		addrp = of_get_address(node, 0, &range_size, NULL);
+		if (!addrp)
+			continue;
 
 		range_addr = of_read_number(addrp, 2);
 		range_end = range_addr + range_size;
diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c
index 262cd6fac907..748c2b97fa53 100644
--- a/arch/powerpc/platforms/powernv/opal-xscom.c
+++ b/arch/powerpc/platforms/powernv/opal-xscom.c
@@ -165,6 +165,11 @@ static int scom_debug_init_one(struct dentry *root, struct device_node *dn,
 	ent->chip = chip;
 	snprintf(ent->name, 16, "%08x", chip);
 	ent->path.data = (void *)kasprintf(GFP_KERNEL, "%pOF", dn);
+	if (!ent->path.data) {
+		kfree(ent);
+		return -ENOMEM;
+	}
+
 	ent->path.size = strlen((char *)ent->path.data);
 
 	dir = debugfs_create_dir(ent->name, root);
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 28fac4770073..23f5b5093ec1 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1389,7 +1389,7 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
 	 * DMA window can be larger than available memory, which will
 	 * cause errors later.
 	 */
-	const u64 maxblock = 1UL << (PAGE_SHIFT + MAX_ORDER);
+	const u64 maxblock = 1UL << (PAGE_SHIFT + MAX_PAGE_ORDER);
 
 	/*
 	 * We create the default window as big as we can. The constraint is
diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c
index 191424468f10..393e747541fb 100644
--- a/arch/powerpc/platforms/powernv/subcore.c
+++ b/arch/powerpc/platforms/powernv/subcore.c
@@ -425,7 +425,8 @@ static int subcore_init(void)
 
 	if (pvr_ver != PVR_POWER8 &&
 	    pvr_ver != PVR_POWER8E &&
-	    pvr_ver != PVR_POWER8NVL)
+	    pvr_ver != PVR_POWER8NVL &&
+	    pvr_ver != PVR_HX_C2000)
 		return 0;
 
 	/*
diff --git a/arch/powerpc/platforms/ps3/Kconfig b/arch/powerpc/platforms/ps3/Kconfig
index a44869e5ea70..e9c1087dd42e 100644
--- a/arch/powerpc/platforms/ps3/Kconfig
+++ b/arch/powerpc/platforms/ps3/Kconfig
@@ -167,16 +167,4 @@ config PS3_LPM
 	  profiling support of the Cell processor with programs like
 	  perfmon2, then say Y or M, otherwise say N.
 
-config PS3GELIC_UDBG
-	bool "PS3 udbg output via UDP broadcasts on Ethernet"
-	depends on PPC_PS3
-	help
-	  Enables udbg early debugging output by sending broadcast UDP
-	  via the Ethernet port (UDP port number 18194).
-
-	  This driver uses a trivial implementation and is independent
-	  from the main PS3 gelic network driver.
-
-	  If in doubt, say N here.
-
 endmenu
diff --git a/arch/powerpc/platforms/ps3/Makefile b/arch/powerpc/platforms/ps3/Makefile
index 86bf2967a8d4..bc79bb124d1e 100644
--- a/arch/powerpc/platforms/ps3/Makefile
+++ b/arch/powerpc/platforms/ps3/Makefile
@@ -3,7 +3,7 @@ obj-y += setup.o mm.o time.o hvcall.o htab.o repository.o
 obj-y += interrupt.o exports.o os-area.o
 obj-y += system-bus.o
 
-obj-$(CONFIG_PS3GELIC_UDBG) += gelic_udbg.o
+obj-$(CONFIG_PPC_EARLY_DEBUG_PS3GELIC) += gelic_udbg.o
 obj-$(CONFIG_SMP) += smp.o
 obj-$(CONFIG_SPU_BASE) += spu.o
 obj-y += device-init.o
diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c
index e87360a0fb40..878bc160246e 100644
--- a/arch/powerpc/platforms/ps3/device-init.c
+++ b/arch/powerpc/platforms/ps3/device-init.c
@@ -827,6 +827,7 @@ static int ps3_probe_thread(void *data)
 	if (res)
 		goto fail_free_irq;
 
+	set_freezable();
 	/* Loop here processing the requested notification events. */
 	do {
 		try_to_freeze();
diff --git a/arch/powerpc/platforms/ps3/gelic_udbg.c b/arch/powerpc/platforms/ps3/gelic_udbg.c
index 6b298010fd84..a5202c18c236 100644
--- a/arch/powerpc/platforms/ps3/gelic_udbg.c
+++ b/arch/powerpc/platforms/ps3/gelic_udbg.c
@@ -14,6 +14,7 @@
 #include <linux/ip.h>
 #include <linux/udp.h>
 
+#include <asm/ps3.h>
 #include <asm/io.h>
 #include <asm/udbg.h>
 #include <asm/lv1call.h>
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index 1476c5e4433c..f936962a2946 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -4,6 +4,7 @@ ccflags-$(CONFIG_PPC_PSERIES_DEBUG)	+= -DDEBUG
 
 obj-y			:= lpar.o hvCall.o nvram.o reconfig.o \
 			   of_helpers.o rtas-work-area.o papr-sysparm.o \
+			   papr-vpd.o \
 			   setup.o iommu.o event_sources.o ras.o \
 			   firmware.o power.o dlpar.o mobility.o rng.o \
 			   pci.o pci_dlpar.o eeh_pseries.o msi.o \
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index def184da51cf..b1ae0c0d1187 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -252,7 +252,7 @@ static int pseries_eeh_cap_start(struct pci_dn *pdn)
 	if (!pdn)
 		return 0;
 
-	rtas_read_config(pdn, PCI_STATUS, 2, &status);
+	rtas_pci_dn_read_config(pdn, PCI_STATUS, 2, &status);
 	if (!(status & PCI_STATUS_CAP_LIST))
 		return 0;
 
@@ -270,11 +270,11 @@ static int pseries_eeh_find_cap(struct pci_dn *pdn, int cap)
 		return 0;
 
         while (cnt--) {
-		rtas_read_config(pdn, pos, 1, &pos);
+		rtas_pci_dn_read_config(pdn, pos, 1, &pos);
 		if (pos < 0x40)
 			break;
 		pos &= ~3;
-		rtas_read_config(pdn, pos + PCI_CAP_LIST_ID, 1, &id);
+		rtas_pci_dn_read_config(pdn, pos + PCI_CAP_LIST_ID, 1, &id);
 		if (id == 0xff)
 			break;
 		if (id == cap)
@@ -294,7 +294,7 @@ static int pseries_eeh_find_ecap(struct pci_dn *pdn, int cap)
 
 	if (!edev || !edev->pcie_cap)
 		return 0;
-	if (rtas_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
+	if (rtas_pci_dn_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
 		return 0;
 	else if (!header)
 		return 0;
@@ -307,7 +307,7 @@ static int pseries_eeh_find_ecap(struct pci_dn *pdn, int cap)
 		if (pos < 256)
 			break;
 
-		if (rtas_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
+		if (rtas_pci_dn_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
 			break;
 	}
 
@@ -412,8 +412,8 @@ static void pseries_eeh_init_edev(struct pci_dn *pdn)
 	if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) {
 		edev->mode |= EEH_DEV_BRIDGE;
 		if (edev->pcie_cap) {
-			rtas_read_config(pdn, edev->pcie_cap + PCI_EXP_FLAGS,
-					 2, &pcie_flags);
+			rtas_pci_dn_read_config(pdn, edev->pcie_cap + PCI_EXP_FLAGS,
+						2, &pcie_flags);
 			pcie_flags = (pcie_flags & PCI_EXP_FLAGS_TYPE) >> 4;
 			if (pcie_flags == PCI_EXP_TYPE_ROOT_PORT)
 				edev->mode |= EEH_DEV_ROOT_PORT;
@@ -676,7 +676,7 @@ static int pseries_eeh_read_config(struct eeh_dev *edev, int where, int size, u3
 {
 	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 
-	return rtas_read_config(pdn, where, size, val);
+	return rtas_pci_dn_read_config(pdn, where, size, val);
 }
 
 /**
@@ -692,7 +692,7 @@ static int pseries_eeh_write_config(struct eeh_dev *edev, int where, int size, u
 {
 	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 
-	return rtas_write_config(pdn, where, size, val);
+	return rtas_pci_dn_write_config(pdn, where, size, val);
 }
 
 #ifdef CONFIG_PCI_IOV
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index a43bfb01720a..3fe3ddb30c04 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -208,8 +208,10 @@ static int dlpar_change_lmb_state(struct drmem_lmb *lmb, bool online)
 	int rc;
 
 	mem_block = lmb_to_memblock(lmb);
-	if (!mem_block)
+	if (!mem_block) {
+		pr_err("Failed memory block lookup for LMB 0x%x\n", lmb->drc_index);
 		return -EINVAL;
+	}
 
 	if (online && mem_block->dev.offline)
 		rc = device_online(&mem_block->dev);
@@ -436,14 +438,15 @@ static int dlpar_memory_remove_by_index(u32 drc_index)
 		}
 	}
 
-	if (!lmb_found)
+	if (!lmb_found) {
+		pr_debug("Failed to look up LMB for drc index %x\n", drc_index);
 		rc = -EINVAL;
-
-	if (rc)
+	} else if (rc) {
 		pr_debug("Failed to hot-remove memory at %llx\n",
 			 lmb->base_addr);
-	else
+	} else {
 		pr_debug("Memory at %llx was hot-removed\n", lmb->base_addr);
+	}
 
 	return rc;
 }
@@ -575,6 +578,7 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb)
 	rc = update_lmb_associativity_index(lmb);
 	if (rc) {
 		dlpar_release_drc(lmb->drc_index);
+		pr_err("Failed to configure LMB 0x%x\n", lmb->drc_index);
 		return rc;
 	}
 
@@ -588,12 +592,14 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb)
 	/* Add the memory */
 	rc = __add_memory(nid, lmb->base_addr, block_sz, MHP_MEMMAP_ON_MEMORY);
 	if (rc) {
+		pr_err("Failed to add LMB 0x%x to node %u", lmb->drc_index, nid);
 		invalidate_lmb_associativity_index(lmb);
 		return rc;
 	}
 
 	rc = dlpar_online_lmb(lmb);
 	if (rc) {
+		pr_err("Failed to online LMB 0x%x on node %u\n", lmb->drc_index, nid);
 		__remove_memory(lmb->base_addr, block_sz);
 		invalidate_lmb_associativity_index(lmb);
 	} else {
diff --git a/arch/powerpc/platforms/pseries/papr-sysparm.c b/arch/powerpc/platforms/pseries/papr-sysparm.c
index fedc61599e6c..7063ce8884e4 100644
--- a/arch/powerpc/platforms/pseries/papr-sysparm.c
+++ b/arch/powerpc/platforms/pseries/papr-sysparm.c
@@ -2,14 +2,20 @@
 
 #define pr_fmt(fmt)	"papr-sysparm: " fmt
 
+#include <linux/anon_inodes.h>
 #include <linux/bug.h>
+#include <linux/file.h>
+#include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/miscdevice.h>
 #include <linux/printk.h>
 #include <linux/slab.h>
-#include <asm/rtas.h>
+#include <linux/uaccess.h>
+#include <asm/machdep.h>
 #include <asm/papr-sysparm.h>
 #include <asm/rtas-work-area.h>
+#include <asm/rtas.h>
 
 struct papr_sysparm_buf *papr_sysparm_buf_alloc(void)
 {
@@ -23,6 +29,46 @@ void papr_sysparm_buf_free(struct papr_sysparm_buf *buf)
 	kfree(buf);
 }
 
+static size_t papr_sysparm_buf_get_length(const struct papr_sysparm_buf *buf)
+{
+	return be16_to_cpu(buf->len);
+}
+
+static void papr_sysparm_buf_set_length(struct papr_sysparm_buf *buf, size_t length)
+{
+	WARN_ONCE(length > sizeof(buf->val),
+		  "bogus length %zu, clamping to safe value", length);
+	length = min(sizeof(buf->val), length);
+	buf->len = cpu_to_be16(length);
+}
+
+/*
+ * For use on buffers returned from ibm,get-system-parameter before
+ * returning them to callers. Ensures the encoded length of valid data
+ * cannot overrun buf->val[].
+ */
+static void papr_sysparm_buf_clamp_length(struct papr_sysparm_buf *buf)
+{
+	papr_sysparm_buf_set_length(buf, papr_sysparm_buf_get_length(buf));
+}
+
+/*
+ * Perform some basic diligence on the system parameter buffer before
+ * submitting it to RTAS.
+ */
+static bool papr_sysparm_buf_can_submit(const struct papr_sysparm_buf *buf)
+{
+	/*
+	 * Firmware ought to reject buffer lengths that exceed the
+	 * maximum specified in PAPR, but there's no reason for the
+	 * kernel to allow them either.
+	 */
+	if (papr_sysparm_buf_get_length(buf) > sizeof(buf->val))
+		return false;
+
+	return true;
+}
+
 /**
  * papr_sysparm_get() - Retrieve the value of a PAPR system parameter.
  * @param: PAPR system parameter token as described in
@@ -47,7 +93,6 @@ void papr_sysparm_buf_free(struct papr_sysparm_buf *buf)
  *
  * Return: 0 on success, -errno otherwise. @buf is unmodified on error.
  */
-
 int papr_sysparm_get(papr_sysparm_t param, struct papr_sysparm_buf *buf)
 {
 	const s32 token = rtas_function_token(RTAS_FN_IBM_GET_SYSTEM_PARAMETER);
@@ -63,6 +108,9 @@ int papr_sysparm_get(papr_sysparm_t param, struct papr_sysparm_buf *buf)
 	if (token == RTAS_UNKNOWN_SERVICE)
 		return -ENOENT;
 
+	if (!papr_sysparm_buf_can_submit(buf))
+		return -EINVAL;
+
 	work_area = rtas_work_area_alloc(sizeof(*buf));
 
 	memcpy(rtas_work_area_raw_buf(work_area), buf, sizeof(*buf));
@@ -77,6 +125,7 @@ int papr_sysparm_get(papr_sysparm_t param, struct papr_sysparm_buf *buf)
 	case 0:
 		ret = 0;
 		memcpy(buf, rtas_work_area_raw_buf(work_area), sizeof(*buf));
+		papr_sysparm_buf_clamp_length(buf);
 		break;
 	case -3: /* parameter not implemented */
 		ret = -EOPNOTSUPP;
@@ -115,6 +164,9 @@ int papr_sysparm_set(papr_sysparm_t param, const struct papr_sysparm_buf *buf)
 	if (token == RTAS_UNKNOWN_SERVICE)
 		return -ENOENT;
 
+	if (!papr_sysparm_buf_can_submit(buf))
+		return -EINVAL;
+
 	work_area = rtas_work_area_alloc(sizeof(*buf));
 
 	memcpy(rtas_work_area_raw_buf(work_area), buf, sizeof(*buf));
@@ -149,3 +201,152 @@ int papr_sysparm_set(papr_sysparm_t param, const struct papr_sysparm_buf *buf)
 
 	return ret;
 }
+
+static struct papr_sysparm_buf *
+papr_sysparm_buf_from_user(const struct papr_sysparm_io_block __user *user_iob)
+{
+	struct papr_sysparm_buf *kern_spbuf;
+	long err;
+	u16 len;
+
+	/*
+	 * The length of valid data that userspace claims to be in
+	 * user_iob->data[].
+	 */
+	if (get_user(len, &user_iob->length))
+		return ERR_PTR(-EFAULT);
+
+	static_assert(sizeof(user_iob->data) >= PAPR_SYSPARM_MAX_INPUT);
+	static_assert(sizeof(kern_spbuf->val) >= PAPR_SYSPARM_MAX_INPUT);
+
+	if (len > PAPR_SYSPARM_MAX_INPUT)
+		return ERR_PTR(-EINVAL);
+
+	kern_spbuf = papr_sysparm_buf_alloc();
+	if (!kern_spbuf)
+		return ERR_PTR(-ENOMEM);
+
+	papr_sysparm_buf_set_length(kern_spbuf, len);
+
+	if (len > 0 && copy_from_user(kern_spbuf->val, user_iob->data, len)) {
+		err = -EFAULT;
+		goto free_sysparm_buf;
+	}
+
+	return kern_spbuf;
+
+free_sysparm_buf:
+	papr_sysparm_buf_free(kern_spbuf);
+	return ERR_PTR(err);
+}
+
+static int papr_sysparm_buf_to_user(const struct papr_sysparm_buf *kern_spbuf,
+				    struct papr_sysparm_io_block __user *user_iob)
+{
+	u16 len_out = papr_sysparm_buf_get_length(kern_spbuf);
+
+	if (put_user(len_out, &user_iob->length))
+		return -EFAULT;
+
+	static_assert(sizeof(user_iob->data) >= PAPR_SYSPARM_MAX_OUTPUT);
+	static_assert(sizeof(kern_spbuf->val) >= PAPR_SYSPARM_MAX_OUTPUT);
+
+	if (copy_to_user(user_iob->data, kern_spbuf->val, PAPR_SYSPARM_MAX_OUTPUT))
+		return -EFAULT;
+
+	return 0;
+}
+
+static long papr_sysparm_ioctl_get(struct papr_sysparm_io_block __user *user_iob)
+{
+	struct papr_sysparm_buf *kern_spbuf;
+	papr_sysparm_t param;
+	long ret;
+
+	if (get_user(param.token, &user_iob->parameter))
+		return -EFAULT;
+
+	kern_spbuf = papr_sysparm_buf_from_user(user_iob);
+	if (IS_ERR(kern_spbuf))
+		return PTR_ERR(kern_spbuf);
+
+	ret = papr_sysparm_get(param, kern_spbuf);
+	if (ret)
+		goto free_sysparm_buf;
+
+	ret = papr_sysparm_buf_to_user(kern_spbuf, user_iob);
+	if (ret)
+		goto free_sysparm_buf;
+
+	ret = 0;
+
+free_sysparm_buf:
+	papr_sysparm_buf_free(kern_spbuf);
+	return ret;
+}
+
+
+static long papr_sysparm_ioctl_set(struct papr_sysparm_io_block __user *user_iob)
+{
+	struct papr_sysparm_buf *kern_spbuf;
+	papr_sysparm_t param;
+	long ret;
+
+	if (get_user(param.token, &user_iob->parameter))
+		return -EFAULT;
+
+	kern_spbuf = papr_sysparm_buf_from_user(user_iob);
+	if (IS_ERR(kern_spbuf))
+		return PTR_ERR(kern_spbuf);
+
+	ret = papr_sysparm_set(param, kern_spbuf);
+	if (ret)
+		goto free_sysparm_buf;
+
+	ret = 0;
+
+free_sysparm_buf:
+	papr_sysparm_buf_free(kern_spbuf);
+	return ret;
+}
+
+static long papr_sysparm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
+{
+	void __user *argp = (__force void __user *)arg;
+	long ret;
+
+	switch (ioctl) {
+	case PAPR_SYSPARM_IOC_GET:
+		ret = papr_sysparm_ioctl_get(argp);
+		break;
+	case PAPR_SYSPARM_IOC_SET:
+		if (filp->f_mode & FMODE_WRITE)
+			ret = papr_sysparm_ioctl_set(argp);
+		else
+			ret = -EBADF;
+		break;
+	default:
+		ret = -ENOIOCTLCMD;
+		break;
+	}
+	return ret;
+}
+
+static const struct file_operations papr_sysparm_ops = {
+	.unlocked_ioctl = papr_sysparm_ioctl,
+};
+
+static struct miscdevice papr_sysparm_dev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "papr-sysparm",
+	.fops = &papr_sysparm_ops,
+};
+
+static __init int papr_sysparm_init(void)
+{
+	if (!rtas_function_implemented(RTAS_FN_IBM_GET_SYSTEM_PARAMETER))
+		return -ENODEV;
+
+	return misc_register(&papr_sysparm_dev);
+}
+machine_device_initcall(pseries, papr_sysparm_init);
diff --git a/arch/powerpc/platforms/pseries/papr-vpd.c b/arch/powerpc/platforms/pseries/papr-vpd.c
new file mode 100644
index 000000000000..c29e85db5f35
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/papr-vpd.c
@@ -0,0 +1,541 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define pr_fmt(fmt) "papr-vpd: " fmt
+
+#include <linux/anon_inodes.h>
+#include <linux/build_bug.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/lockdep.h>
+#include <linux/kernel.h>
+#include <linux/miscdevice.h>
+#include <linux/signal.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/string_helpers.h>
+#include <linux/uaccess.h>
+#include <asm/machdep.h>
+#include <asm/papr-vpd.h>
+#include <asm/rtas-work-area.h>
+#include <asm/rtas.h>
+#include <uapi/asm/papr-vpd.h>
+
+/*
+ * Function-specific return values for ibm,get-vpd, derived from PAPR+
+ * v2.13 7.3.20 "ibm,get-vpd RTAS Call".
+ */
+#define RTAS_IBM_GET_VPD_COMPLETE    0 /* All VPD has been retrieved. */
+#define RTAS_IBM_GET_VPD_MORE_DATA   1 /* More VPD is available. */
+#define RTAS_IBM_GET_VPD_START_OVER -4 /* VPD changed, restart call sequence. */
+
+/**
+ * struct rtas_ibm_get_vpd_params - Parameters (in and out) for ibm,get-vpd.
+ * @loc_code:  In: Caller-provided location code buffer. Must be RTAS-addressable.
+ * @work_area: In: Caller-provided work area buffer for results.
+ * @sequence:  In: Sequence number. Out: Next sequence number.
+ * @written:   Out: Bytes written by ibm,get-vpd to @work_area.
+ * @status:    Out: RTAS call status.
+ */
+struct rtas_ibm_get_vpd_params {
+	const struct papr_location_code *loc_code;
+	struct rtas_work_area *work_area;
+	u32 sequence;
+	u32 written;
+	s32 status;
+};
+
+/**
+ * rtas_ibm_get_vpd() - Call ibm,get-vpd to fill a work area buffer.
+ * @params: See &struct rtas_ibm_get_vpd_params.
+ *
+ * Calls ibm,get-vpd until it errors or successfully deposits data
+ * into the supplied work area. Handles RTAS retry statuses. Maps RTAS
+ * error statuses to reasonable errno values.
+ *
+ * The caller is expected to invoke rtas_ibm_get_vpd() multiple times
+ * to retrieve all the VPD for the provided location code. Only one
+ * sequence should be in progress at any time; starting a new sequence
+ * will disrupt any sequence already in progress. Serialization of VPD
+ * retrieval sequences is the responsibility of the caller.
+ *
+ * The caller should inspect @params.status to determine whether more
+ * calls are needed to complete the sequence.
+ *
+ * Context: May sleep.
+ * Return: -ve on error, 0 otherwise.
+ */
+static int rtas_ibm_get_vpd(struct rtas_ibm_get_vpd_params *params)
+{
+	const struct papr_location_code *loc_code = params->loc_code;
+	struct rtas_work_area *work_area = params->work_area;
+	u32 rets[2];
+	s32 fwrc;
+	int ret;
+
+	lockdep_assert_held(&rtas_ibm_get_vpd_lock);
+
+	do {
+		fwrc = rtas_call(rtas_function_token(RTAS_FN_IBM_GET_VPD), 4, 3,
+				 rets,
+				 __pa(loc_code),
+				 rtas_work_area_phys(work_area),
+				 rtas_work_area_size(work_area),
+				 params->sequence);
+	} while (rtas_busy_delay(fwrc));
+
+	switch (fwrc) {
+	case RTAS_HARDWARE_ERROR:
+		ret = -EIO;
+		break;
+	case RTAS_INVALID_PARAMETER:
+		ret = -EINVAL;
+		break;
+	case RTAS_IBM_GET_VPD_START_OVER:
+		ret = -EAGAIN;
+		break;
+	case RTAS_IBM_GET_VPD_MORE_DATA:
+		params->sequence = rets[0];
+		fallthrough;
+	case RTAS_IBM_GET_VPD_COMPLETE:
+		params->written = rets[1];
+		/*
+		 * Kernel or firmware bug, do not continue.
+		 */
+		if (WARN(params->written > rtas_work_area_size(work_area),
+			 "possible write beyond end of work area"))
+			ret = -EFAULT;
+		else
+			ret = 0;
+		break;
+	default:
+		ret = -EIO;
+		pr_err_ratelimited("unexpected ibm,get-vpd status %d\n", fwrc);
+		break;
+	}
+
+	params->status = fwrc;
+	return ret;
+}
+
+/*
+ * Internal VPD "blob" APIs for accumulating ibm,get-vpd results into
+ * an immutable buffer to be attached to a file descriptor.
+ */
+struct vpd_blob {
+	const char *data;
+	size_t len;
+};
+
+static bool vpd_blob_has_data(const struct vpd_blob *blob)
+{
+	return blob->data && blob->len;
+}
+
+static void vpd_blob_free(const struct vpd_blob *blob)
+{
+	if (blob) {
+		kvfree(blob->data);
+		kfree(blob);
+	}
+}
+
+/**
+ * vpd_blob_extend() - Append data to a &struct vpd_blob.
+ * @blob: The blob to extend.
+ * @data: The new data to append to @blob.
+ * @len:  The length of @data.
+ *
+ * Context: May sleep.
+ * Return: -ENOMEM on allocation failure, 0 otherwise.
+ */
+static int vpd_blob_extend(struct vpd_blob *blob, const char *data, size_t len)
+{
+	const size_t new_len = blob->len + len;
+	const size_t old_len = blob->len;
+	const char *old_ptr = blob->data;
+	char *new_ptr;
+
+	new_ptr = old_ptr ?
+		kvrealloc(old_ptr, old_len, new_len, GFP_KERNEL_ACCOUNT) :
+		kvmalloc(len, GFP_KERNEL_ACCOUNT);
+
+	if (!new_ptr)
+		return -ENOMEM;
+
+	memcpy(&new_ptr[old_len], data, len);
+	blob->data = new_ptr;
+	blob->len = new_len;
+	return 0;
+}
+
+/**
+ * vpd_blob_generate() - Construct a new &struct vpd_blob.
+ * @generator: Function that supplies the blob data.
+ * @arg:       Context pointer supplied by caller, passed to @generator.
+ *
+ * The @generator callback is invoked until it returns NULL. @arg is
+ * passed to @generator in its first argument on each call. When
+ * @generator returns data, it should store the data length in its
+ * second argument.
+ *
+ * Context: May sleep.
+ * Return: A completely populated &struct vpd_blob, or NULL on error.
+ */
+static const struct vpd_blob *
+vpd_blob_generate(const char * (*generator)(void *, size_t *), void *arg)
+{
+	struct vpd_blob *blob;
+	const char *buf;
+	size_t len;
+	int err = 0;
+
+	blob  = kzalloc(sizeof(*blob), GFP_KERNEL_ACCOUNT);
+	if (!blob)
+		return NULL;
+
+	while (err == 0 && (buf = generator(arg, &len)))
+		err = vpd_blob_extend(blob, buf, len);
+
+	if (err != 0 || !vpd_blob_has_data(blob))
+		goto free_blob;
+
+	return blob;
+free_blob:
+	vpd_blob_free(blob);
+	return NULL;
+}
+
+/*
+ * Internal VPD sequence APIs. A VPD sequence is a series of calls to
+ * ibm,get-vpd for a given location code. The sequence ends when an
+ * error is encountered or all VPD for the location code has been
+ * returned.
+ */
+
+/**
+ * struct vpd_sequence - State for managing a VPD sequence.
+ * @error:  Shall be zero as long as the sequence has not encountered an error,
+ *          -ve errno otherwise. Use vpd_sequence_set_err() to update this.
+ * @params: Parameter block to pass to rtas_ibm_get_vpd().
+ */
+struct vpd_sequence {
+	int error;
+	struct rtas_ibm_get_vpd_params params;
+};
+
+/**
+ * vpd_sequence_begin() - Begin a VPD retrieval sequence.
+ * @seq:      Uninitialized sequence state.
+ * @loc_code: Location code that defines the scope of the VPD to return.
+ *
+ * Initializes @seq with the resources necessary to carry out a VPD
+ * sequence. Callers must pass @seq to vpd_sequence_end() regardless
+ * of whether the sequence succeeds.
+ *
+ * Context: May sleep.
+ */
+static void vpd_sequence_begin(struct vpd_sequence *seq,
+			       const struct papr_location_code *loc_code)
+{
+	/*
+	 * Use a static data structure for the location code passed to
+	 * RTAS to ensure it's in the RMA and avoid a separate work
+	 * area allocation. Guarded by the function lock.
+	 */
+	static struct papr_location_code static_loc_code;
+
+	/*
+	 * We could allocate the work area before acquiring the
+	 * function lock, but that would allow concurrent requests to
+	 * exhaust the limited work area pool for no benefit. So
+	 * allocate the work area under the lock.
+	 */
+	mutex_lock(&rtas_ibm_get_vpd_lock);
+	static_loc_code = *loc_code;
+	*seq = (struct vpd_sequence) {
+		.params = {
+			.work_area = rtas_work_area_alloc(SZ_4K),
+			.loc_code = &static_loc_code,
+			.sequence = 1,
+		},
+	};
+}
+
+/**
+ * vpd_sequence_end() - Finalize a VPD retrieval sequence.
+ * @seq: Sequence state.
+ *
+ * Releases resources obtained by vpd_sequence_begin().
+ */
+static void vpd_sequence_end(struct vpd_sequence *seq)
+{
+	rtas_work_area_free(seq->params.work_area);
+	mutex_unlock(&rtas_ibm_get_vpd_lock);
+}
+
+/**
+ * vpd_sequence_should_stop() - Determine whether a VPD retrieval sequence
+ *                              should continue.
+ * @seq: VPD sequence state.
+ *
+ * Examines the sequence error state and outputs of the last call to
+ * ibm,get-vpd to determine whether the sequence in progress should
+ * continue or stop.
+ *
+ * Return: True if the sequence has encountered an error or if all VPD for
+ *         this sequence has been retrieved. False otherwise.
+ */
+static bool vpd_sequence_should_stop(const struct vpd_sequence *seq)
+{
+	bool done;
+
+	if (seq->error)
+		return true;
+
+	switch (seq->params.status) {
+	case 0:
+		if (seq->params.written == 0)
+			done = false; /* Initial state. */
+		else
+			done = true; /* All data consumed. */
+		break;
+	case 1:
+		done = false; /* More data available. */
+		break;
+	default:
+		done = true; /* Error encountered. */
+		break;
+	}
+
+	return done;
+}
+
+static int vpd_sequence_set_err(struct vpd_sequence *seq, int err)
+{
+	/* Preserve the first error recorded. */
+	if (seq->error == 0)
+		seq->error = err;
+
+	return seq->error;
+}
+
+/*
+ * Generator function to be passed to vpd_blob_generate().
+ */
+static const char *vpd_sequence_fill_work_area(void *arg, size_t *len)
+{
+	struct vpd_sequence *seq = arg;
+	struct rtas_ibm_get_vpd_params *p = &seq->params;
+
+	if (vpd_sequence_should_stop(seq))
+		return NULL;
+	if (vpd_sequence_set_err(seq, rtas_ibm_get_vpd(p)))
+		return NULL;
+	*len = p->written;
+	return rtas_work_area_raw_buf(p->work_area);
+}
+
+/*
+ * Higher-level VPD retrieval code below. These functions use the
+ * vpd_blob_* and vpd_sequence_* APIs defined above to create fd-based
+ * VPD handles for consumption by user space.
+ */
+
+/**
+ * papr_vpd_run_sequence() - Run a single VPD retrieval sequence.
+ * @loc_code: Location code that defines the scope of VPD to return.
+ *
+ * Context: May sleep. Holds a mutex and an RTAS work area for its
+ *          duration. Typically performs multiple sleepable slab
+ *          allocations.
+ *
+ * Return: A populated &struct vpd_blob on success. Encoded error
+ * pointer otherwise.
+ */
+static const struct vpd_blob *papr_vpd_run_sequence(const struct papr_location_code *loc_code)
+{
+	const struct vpd_blob *blob;
+	struct vpd_sequence seq;
+
+	vpd_sequence_begin(&seq, loc_code);
+	blob = vpd_blob_generate(vpd_sequence_fill_work_area, &seq);
+	if (!blob)
+		vpd_sequence_set_err(&seq, -ENOMEM);
+	vpd_sequence_end(&seq);
+
+	if (seq.error) {
+		vpd_blob_free(blob);
+		return ERR_PTR(seq.error);
+	}
+
+	return blob;
+}
+
+/**
+ * papr_vpd_retrieve() - Return the VPD for a location code.
+ * @loc_code: Location code that defines the scope of VPD to return.
+ *
+ * Run VPD sequences against @loc_code until a blob is successfully
+ * instantiated, or a hard error is encountered, or a fatal signal is
+ * pending.
+ *
+ * Context: May sleep.
+ * Return: A fully populated VPD blob when successful. Encoded error
+ * pointer otherwise.
+ */
+static const struct vpd_blob *papr_vpd_retrieve(const struct papr_location_code *loc_code)
+{
+	const struct vpd_blob *blob;
+
+	/*
+	 * EAGAIN means the sequence errored with a -4 (VPD changed)
+	 * status from ibm,get-vpd, and we should attempt a new
+	 * sequence. PAPR+ v2.13 R1–7.3.20–5 indicates that this
+	 * should be a transient condition, not something that happens
+	 * continuously. But we'll stop trying on a fatal signal.
+	 */
+	do {
+		blob = papr_vpd_run_sequence(loc_code);
+		if (!IS_ERR(blob)) /* Success. */
+			break;
+		if (PTR_ERR(blob) != -EAGAIN) /* Hard error. */
+			break;
+		pr_info_ratelimited("VPD changed during retrieval, retrying\n");
+		cond_resched();
+	} while (!fatal_signal_pending(current));
+
+	return blob;
+}
+
+static ssize_t papr_vpd_handle_read(struct file *file, char __user *buf, size_t size, loff_t *off)
+{
+	const struct vpd_blob *blob = file->private_data;
+
+	/* bug: we should not instantiate a handle without any data attached. */
+	if (!vpd_blob_has_data(blob)) {
+		pr_err_once("handle without data\n");
+		return -EIO;
+	}
+
+	return simple_read_from_buffer(buf, size, off, blob->data, blob->len);
+}
+
+static int papr_vpd_handle_release(struct inode *inode, struct file *file)
+{
+	const struct vpd_blob *blob = file->private_data;
+
+	vpd_blob_free(blob);
+
+	return 0;
+}
+
+static loff_t papr_vpd_handle_seek(struct file *file, loff_t off, int whence)
+{
+	const struct vpd_blob *blob = file->private_data;
+
+	return fixed_size_llseek(file, off, whence, blob->len);
+}
+
+
+static const struct file_operations papr_vpd_handle_ops = {
+	.read = papr_vpd_handle_read,
+	.llseek = papr_vpd_handle_seek,
+	.release = papr_vpd_handle_release,
+};
+
+/**
+ * papr_vpd_create_handle() - Create a fd-based handle for reading VPD.
+ * @ulc: Location code in user memory; defines the scope of the VPD to
+ *       retrieve.
+ *
+ * Handler for PAPR_VPD_IOC_CREATE_HANDLE ioctl command. Validates
+ * @ulc and instantiates an immutable VPD "blob" for it. The blob is
+ * attached to a file descriptor for reading by user space. The memory
+ * backing the blob is freed when the file is released.
+ *
+ * The entire requested VPD is retrieved by this call and all
+ * necessary RTAS interactions are performed before returning the fd
+ * to user space. This keeps the read handler simple and ensures that
+ * the kernel can prevent interleaving of ibm,get-vpd call sequences.
+ *
+ * Return: The installed fd number if successful, -ve errno otherwise.
+ */
+static long papr_vpd_create_handle(struct papr_location_code __user *ulc)
+{
+	struct papr_location_code klc;
+	const struct vpd_blob *blob;
+	struct file *file;
+	long err;
+	int fd;
+
+	if (copy_from_user(&klc, ulc, sizeof(klc)))
+		return -EFAULT;
+
+	if (!string_is_terminated(klc.str, ARRAY_SIZE(klc.str)))
+		return -EINVAL;
+
+	blob = papr_vpd_retrieve(&klc);
+	if (IS_ERR(blob))
+		return PTR_ERR(blob);
+
+	fd = get_unused_fd_flags(O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		err = fd;
+		goto free_blob;
+	}
+
+	file = anon_inode_getfile("[papr-vpd]", &papr_vpd_handle_ops,
+				  (void *)blob, O_RDONLY);
+	if (IS_ERR(file)) {
+		err = PTR_ERR(file);
+		goto put_fd;
+	}
+
+	file->f_mode |= FMODE_LSEEK | FMODE_PREAD;
+	fd_install(fd, file);
+	return fd;
+put_fd:
+	put_unused_fd(fd);
+free_blob:
+	vpd_blob_free(blob);
+	return err;
+}
+
+/*
+ * Top-level ioctl handler for /dev/papr-vpd.
+ */
+static long papr_vpd_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
+{
+	void __user *argp = (__force void __user *)arg;
+	long ret;
+
+	switch (ioctl) {
+	case PAPR_VPD_IOC_CREATE_HANDLE:
+		ret = papr_vpd_create_handle(argp);
+		break;
+	default:
+		ret = -ENOIOCTLCMD;
+		break;
+	}
+	return ret;
+}
+
+static const struct file_operations papr_vpd_ops = {
+	.unlocked_ioctl = papr_vpd_dev_ioctl,
+};
+
+static struct miscdevice papr_vpd_dev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "papr-vpd",
+	.fops = &papr_vpd_ops,
+};
+
+static __init int papr_vpd_init(void)
+{
+	if (!rtas_function_implemented(RTAS_FN_IBM_GET_VPD))
+		return -ENODEV;
+
+	return misc_register(&papr_vpd_dev);
+}
+machine_device_initcall(pseries, papr_vpd_init);
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index 8376f03f932a..bba4ad192b0f 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -55,6 +55,7 @@ extern int dlpar_detach_node(struct device_node *);
 extern int dlpar_acquire_drc(u32 drc_index);
 extern int dlpar_release_drc(u32 drc_index);
 extern int dlpar_unisolate_drc(u32 drc_index);
+extern void post_mobility_fixup(void);
 
 void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog);
 int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_errlog);
diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c
index 5c43435472cc..382003dfdb9a 100644
--- a/arch/powerpc/platforms/pseries/suspend.c
+++ b/arch/powerpc/platforms/pseries/suspend.c
@@ -13,6 +13,7 @@
 #include <asm/mmu.h>
 #include <asm/rtas.h>
 #include <asm/topology.h>
+#include "pseries.h"
 
 static struct device suspend_dev;
 
diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c
index b1f25bac280b..71d52a670d95 100644
--- a/arch/powerpc/platforms/pseries/vas.c
+++ b/arch/powerpc/platforms/pseries/vas.c
@@ -385,11 +385,15 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags,
 	 * same fault IRQ is not freed by the OS before.
 	 */
 	mutex_lock(&vas_pseries_mutex);
-	if (migration_in_progress)
+	if (migration_in_progress) {
 		rc = -EBUSY;
-	else
+	} else {
 		rc = allocate_setup_window(txwin, (u64 *)&domain[0],
 				   cop_feat_caps->win_type);
+		if (!rc)
+			caps->nr_open_wins_progress++;
+	}
+
 	mutex_unlock(&vas_pseries_mutex);
 	if (rc)
 		goto out;
@@ -404,8 +408,17 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags,
 		goto out_free;
 
 	txwin->win_type = cop_feat_caps->win_type;
-	mutex_lock(&vas_pseries_mutex);
+
 	/*
+	 * The migration SUSPEND thread sets migration_in_progress and
+	 * closes all open windows from the list. But the window is
+	 * added to the list after open and modify HCALLs. So possible
+	 * that migration_in_progress is set before modify HCALL which
+	 * may cause some windows are still open when the hypervisor
+	 * initiates the migration.
+	 * So checks the migration_in_progress flag again and close all
+	 * open windows.
+	 *
 	 * Possible to lose the acquired credit with DLPAR core
 	 * removal after the window is opened. So if there are any
 	 * closed windows (means with lost credits), do not give new
@@ -413,9 +426,11 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags,
 	 * after the existing windows are reopened when credits are
 	 * available.
 	 */
-	if (!caps->nr_close_wins) {
+	mutex_lock(&vas_pseries_mutex);
+	if (!caps->nr_close_wins && !migration_in_progress) {
 		list_add(&txwin->win_list, &caps->list);
 		caps->nr_open_windows++;
+		caps->nr_open_wins_progress--;
 		mutex_unlock(&vas_pseries_mutex);
 		vas_user_win_add_mm_context(&txwin->vas_win.task_ref);
 		return &txwin->vas_win;
@@ -433,6 +448,12 @@ out_free:
 	 */
 	free_irq_setup(txwin);
 	h_deallocate_vas_window(txwin->vas_win.winid);
+	/*
+	 * Hold mutex and reduce nr_open_wins_progress counter.
+	 */
+	mutex_lock(&vas_pseries_mutex);
+	caps->nr_open_wins_progress--;
+	mutex_unlock(&vas_pseries_mutex);
 out:
 	atomic_dec(&cop_feat_caps->nr_used_credits);
 	kfree(txwin);
@@ -937,14 +958,14 @@ int vas_migration_handler(int action)
 	struct vas_caps *vcaps;
 	int i, rc = 0;
 
+	pr_info("VAS migration event %d\n", action);
+
 	/*
 	 * NX-GZIP is not enabled. Nothing to do for migration.
 	 */
 	if (!copypaste_feat)
 		return rc;
 
-	mutex_lock(&vas_pseries_mutex);
-
 	if (action == VAS_SUSPEND)
 		migration_in_progress = true;
 	else
@@ -990,12 +1011,27 @@ int vas_migration_handler(int action)
 
 		switch (action) {
 		case VAS_SUSPEND:
+			mutex_lock(&vas_pseries_mutex);
 			rc = reconfig_close_windows(vcaps, vcaps->nr_open_windows,
 							true);
+			/*
+			 * Windows are included in the list after successful
+			 * open. So wait for closing these in-progress open
+			 * windows in vas_allocate_window() which will be
+			 * done if the migration_in_progress is set.
+			 */
+			while (vcaps->nr_open_wins_progress) {
+				mutex_unlock(&vas_pseries_mutex);
+				msleep(10);
+				mutex_lock(&vas_pseries_mutex);
+			}
+			mutex_unlock(&vas_pseries_mutex);
 			break;
 		case VAS_RESUME:
+			mutex_lock(&vas_pseries_mutex);
 			atomic_set(&caps->nr_total_credits, new_nr_creds);
 			rc = reconfig_open_windows(vcaps, new_nr_creds, true);
+			mutex_unlock(&vas_pseries_mutex);
 			break;
 		default:
 			/* should not happen */
@@ -1011,8 +1047,9 @@ int vas_migration_handler(int action)
 			goto out;
 	}
 
+	pr_info("VAS migration event (%d) successful\n", action);
+
 out:
-	mutex_unlock(&vas_pseries_mutex);
 	return rc;
 }
 
diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h
index 7115043ec488..45567cd13178 100644
--- a/arch/powerpc/platforms/pseries/vas.h
+++ b/arch/powerpc/platforms/pseries/vas.h
@@ -91,6 +91,8 @@ struct vas_cop_feat_caps {
 struct vas_caps {
 	struct vas_cop_feat_caps caps;
 	struct list_head list;	/* List of open windows */
+	int nr_open_wins_progress;	/* Number of open windows in */
+					/* progress. Used in migration */
 	int nr_close_wins;	/* closed windows in the hypervisor for DLPAR */
 	int nr_open_windows;	/* Number of successful open windows */
 	u8 feat;		/* Feature type */
diff --git a/arch/powerpc/sysdev/grackle.c b/arch/powerpc/sysdev/grackle.c
index fd2f94a884f0..7dce8278b71e 100644
--- a/arch/powerpc/sysdev/grackle.c
+++ b/arch/powerpc/sysdev/grackle.c
@@ -18,24 +18,8 @@
 #define GRACKLE_CFA(b, d, o)	(0x80 | ((b) << 8) | ((d) << 16) \
 				 | (((o) & ~3) << 24))
 
-#define GRACKLE_PICR1_STG		0x00000040
 #define GRACKLE_PICR1_LOOPSNOOP		0x00000010
 
-/* N.B. this is called before bridges is initialized, so we can't
-   use grackle_pcibios_{read,write}_config_dword. */
-static inline void grackle_set_stg(struct pci_controller* bp, int enable)
-{
-	unsigned int val;
-
-	out_be32(bp->cfg_addr, GRACKLE_CFA(0, 0, 0xa8));
-	val = in_le32(bp->cfg_data);
-	val = enable? (val | GRACKLE_PICR1_STG) :
-		(val & ~GRACKLE_PICR1_STG);
-	out_be32(bp->cfg_addr, GRACKLE_CFA(0, 0, 0xa8));
-	out_le32(bp->cfg_data, val);
-	(void)in_le32(bp->cfg_data);
-}
-
 static inline void grackle_set_loop_snoop(struct pci_controller *bp, int enable)
 {
 	unsigned int val;
@@ -56,7 +40,4 @@ void __init setup_grackle(struct pci_controller *hose)
 		pci_add_flags(PCI_REASSIGN_ALL_BUS);
 	if (of_machine_is_compatible("AAPL,PowerBook1998"))
 		grackle_set_loop_snoop(hose, 1);
-#if 0	/* Disabled for now, HW problems ??? */
-	grackle_set_stg(hose, 1);
-#endif
 }
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index f6ec6dba92dc..700b67476a7d 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -236,6 +236,8 @@ static int __init icp_native_map_one_cpu(int hw_id, unsigned long addr,
 	rname = kasprintf(GFP_KERNEL, "CPU %d [0x%x] Interrupt Presentation",
 			  cpu, hw_id);
 
+	if (!rname)
+		return -ENOMEM;
 	if (!request_mem_region(addr, size, rname)) {
 		pr_warn("icp_native: Could not reserve ICP MMIO for CPU %d, interrupt server #0x%x\n",
 			cpu, hw_id);
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 95a2a06acc6a..cd4c9a204d08 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -685,7 +685,7 @@ config RISCV_BOOT_SPINWAIT
 	  If unsure what to do here, say N.
 
 config ARCH_SUPPORTS_KEXEC
-	def_bool MMU
+	def_bool y
 
 config ARCH_SELECTS_KEXEC
 	def_bool y
@@ -693,7 +693,7 @@ config ARCH_SELECTS_KEXEC
 	select HOTPLUG_CPU if SMP
 
 config ARCH_SUPPORTS_KEXEC_FILE
-	def_bool 64BIT && MMU
+	def_bool 64BIT
 
 config ARCH_SELECTS_KEXEC_FILE
 	def_bool y
@@ -702,9 +702,7 @@ config ARCH_SELECTS_KEXEC_FILE
 	select KEXEC_ELF
 
 config ARCH_SUPPORTS_KEXEC_PURGATORY
-	def_bool KEXEC_FILE
-	depends on CRYPTO=y
-	depends on CRYPTO_SHA256=y
+	def_bool ARCH_SUPPORTS_KEXEC_FILE
 
 config ARCH_SUPPORTS_CRASH_DUMP
 	def_bool y
diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata
index e2c731cfed8c..f5c432b005e7 100644
--- a/arch/riscv/Kconfig.errata
+++ b/arch/riscv/Kconfig.errata
@@ -53,6 +53,25 @@ config ERRATA_SIFIVE_CIP_1200
 
 	  If you don't know what to do here, say "Y".
 
+config ERRATA_STARFIVE_JH7100
+	bool "StarFive JH7100 support"
+	depends on ARCH_STARFIVE
+	depends on !DMA_DIRECT_REMAP
+	depends on NONPORTABLE
+	select DMA_GLOBAL_POOL
+	select RISCV_DMA_NONCOHERENT
+	select RISCV_NONSTANDARD_CACHE_OPS
+	select SIFIVE_CCACHE
+	default n
+	help
+	  The StarFive JH7100 was a test chip for the JH7110 and has
+	  caches that are non-coherent with respect to peripheral DMAs.
+	  It was designed before the Zicbom extension so needs non-standard
+	  cache operations through the SiFive cache controller.
+
+	  Say "Y" if you want to support the BeagleV Starlight and/or
+	  StarFive VisionFive V1 boards.
+
 config ERRATA_THEAD
 	bool "T-HEAD errata"
 	depends on RISCV_ALTERNATIVE
diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts
index 90b261114763..222a39d90f85 100644
--- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts
+++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts
@@ -8,9 +8,6 @@
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/leds/common.h>
 
-/* Clock frequency (in Hz) of the rtcclk */
-#define RTCCLK_FREQ		1000000
-
 / {
 	model = "Microchip PolarFire-SoC Icicle Kit";
 	compatible = "microchip,mpfs-icicle-reference-rtlv2210", "microchip,mpfs-icicle-kit",
@@ -29,10 +26,6 @@
 		stdout-path = "serial1:115200n8";
 	};
 
-	cpus {
-		timebase-frequency = <RTCCLK_FREQ>;
-	};
-
 	leds {
 		compatible = "gpio-leds";
 
@@ -199,6 +192,27 @@
 	status = "okay";
 };
 
+&syscontroller_qspi {
+	/*
+	 * The flash *is* there, but Icicle kits that have engineering sample
+	 * silicon (write?) access to this flash to non-functional. The system
+	 * controller itself can actually access it, but the MSS cannot write
+	 * an image there. Instantiating a coreQSPI in the fabric & connecting
+	 * it to the flash instead should work though. Pre-production or later
+	 * silicon does not have this issue.
+	 */
+	status = "disabled";
+
+	sys_ctrl_flash: flash@0 { // MT25QL01GBBB8ESF-0SIT
+		compatible = "jedec,spi-nor";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		spi-max-frequency = <20000000>;
+		spi-rx-bus-width = <1>;
+		reg = <0>;
+	};
+};
+
 &usb {
 	status = "okay";
 	dr_mode = "host";
diff --git a/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts b/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts
index 184cb36a175e..a8d623ee9fa4 100644
--- a/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts
+++ b/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts
@@ -10,9 +10,6 @@
 #include "mpfs.dtsi"
 #include "mpfs-m100pfs-fabric.dtsi"
 
-/* Clock frequency (in Hz) of the rtcclk */
-#define MTIMER_FREQ	1000000
-
 / {
 	model = "Aries Embedded M100PFEVPS";
 	compatible = "aries,m100pfsevp", "microchip,mpfs";
@@ -33,10 +30,6 @@
 		stdout-path = "serial1:115200n8";
 	};
 
-	cpus {
-		timebase-frequency = <MTIMER_FREQ>;
-	};
-
 	ddrc_cache_lo: memory@80000000 {
 		device_type = "memory";
 		reg = <0x0 0x80000000 0x0 0x40000000>;
diff --git a/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts b/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts
index c87cc2d8fe29..ea0808ab1042 100644
--- a/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts
+++ b/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts
@@ -6,9 +6,6 @@
 #include "mpfs.dtsi"
 #include "mpfs-polarberry-fabric.dtsi"
 
-/* Clock frequency (in Hz) of the rtcclk */
-#define MTIMER_FREQ	1000000
-
 / {
 	model = "Sundance PolarBerry";
 	compatible = "sundance,polarberry", "microchip,mpfs";
@@ -22,10 +19,6 @@
 		stdout-path = "serial0:115200n8";
 	};
 
-	cpus {
-		timebase-frequency = <MTIMER_FREQ>;
-	};
-
 	ddrc_cache_lo: memory@80000000 {
 		device_type = "memory";
 		reg = <0x0 0x80000000 0x0 0x2e000000>;
diff --git a/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts b/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts
index 013cb666c72d..f9a890579438 100644
--- a/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts
+++ b/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts
@@ -6,9 +6,6 @@
 #include "mpfs.dtsi"
 #include "mpfs-sev-kit-fabric.dtsi"
 
-/* Clock frequency (in Hz) of the rtcclk */
-#define MTIMER_FREQ		1000000
-
 / {
 	#address-cells = <2>;
 	#size-cells = <2>;
@@ -28,10 +25,6 @@
 		stdout-path = "serial1:115200n8";
 	};
 
-	cpus {
-		timebase-frequency = <MTIMER_FREQ>;
-	};
-
 	reserved-memory {
 		#address-cells = <2>;
 		#size-cells = <2>;
diff --git a/arch/riscv/boot/dts/microchip/mpfs-tysom-m.dts b/arch/riscv/boot/dts/microchip/mpfs-tysom-m.dts
index e0797c7e1b35..d1120f5f2c01 100644
--- a/arch/riscv/boot/dts/microchip/mpfs-tysom-m.dts
+++ b/arch/riscv/boot/dts/microchip/mpfs-tysom-m.dts
@@ -11,9 +11,6 @@
 #include "mpfs.dtsi"
 #include "mpfs-tysom-m-fabric.dtsi"
 
-/* Clock frequency (in Hz) of the rtcclk */
-#define MTIMER_FREQ		1000000
-
 / {
 	model = "Aldec TySOM-M-MPFS250T-REV2";
 	compatible = "aldec,tysom-m-mpfs250t-rev2", "microchip,mpfs";
@@ -34,10 +31,6 @@
 		stdout-path = "serial1:115200n8";
 	};
 
-	cpus {
-		timebase-frequency = <MTIMER_FREQ>;
-	};
-
 	ddrc_cache_lo: memory@80000000 {
 		device_type = "memory";
 		reg = <0x0 0x80000000 0x0 0x30000000>;
diff --git a/arch/riscv/boot/dts/microchip/mpfs.dtsi b/arch/riscv/boot/dts/microchip/mpfs.dtsi
index a6faf24f1dba..59fd2d4ea523 100644
--- a/arch/riscv/boot/dts/microchip/mpfs.dtsi
+++ b/arch/riscv/boot/dts/microchip/mpfs.dtsi
@@ -13,6 +13,7 @@
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
+		timebase-frequency = <1000000>;
 
 		cpu0: cpu@0 {
 			compatible = "sifive,e51", "sifive,rocket0", "riscv";
@@ -193,6 +194,12 @@
 		mboxes = <&mbox 0>;
 	};
 
+	scbclk: mssclkclk {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <80000000>;
+	};
+
 	soc {
 		#address-cells = <2>;
 		#size-cells = <2>;
@@ -523,5 +530,16 @@
 			#mbox-cells = <1>;
 			status = "disabled";
 		};
+
+		syscontroller_qspi: spi@37020100 {
+			compatible = "microchip,mpfs-qspi", "microchip,coreqspi-rtl-v2";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x0 0x37020100 0x0 0x100>;
+			interrupt-parent = <&plic>;
+			interrupts = <110>;
+			clocks = <&scbclk>;
+			status = "disabled";
+		};
 	};
 };
diff --git a/arch/riscv/boot/dts/renesas/r9a07g043f.dtsi b/arch/riscv/boot/dts/renesas/r9a07g043f.dtsi
index b0796015e36b..a92cfcfc021b 100644
--- a/arch/riscv/boot/dts/renesas/r9a07g043f.dtsi
+++ b/arch/riscv/boot/dts/renesas/r9a07g043f.dtsi
@@ -24,6 +24,10 @@
 			reg = <0x0>;
 			status = "okay";
 			riscv,isa = "rv64imafdc";
+			riscv,isa-base = "rv64i";
+			riscv,isa-extensions = "i", "m", "a", "f", "d", "c",
+					       "zicntr", "zicsr", "zifencei",
+					       "zihpm";
 			mmu-type = "riscv,sv39";
 			i-cache-size = <0x8000>;
 			i-cache-line-size = <0x40>;
diff --git a/arch/riscv/boot/dts/sophgo/Makefile b/arch/riscv/boot/dts/sophgo/Makefile
index 3fb65512c631..57ad82a61ea6 100644
--- a/arch/riscv/boot/dts/sophgo/Makefile
+++ b/arch/riscv/boot/dts/sophgo/Makefile
@@ -1,3 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
 dtb-$(CONFIG_ARCH_SOPHGO) += cv1800b-milkv-duo.dtb
+dtb-$(CONFIG_ARCH_SOPHGO) += cv1812h-huashan-pi.dtb
 dtb-$(CONFIG_ARCH_SOPHGO) += sg2042-milkv-pioneer.dtb
diff --git a/arch/riscv/boot/dts/sophgo/cv1800b.dtsi b/arch/riscv/boot/dts/sophgo/cv1800b.dtsi
index df40e87ee063..165e9e320a8c 100644
--- a/arch/riscv/boot/dts/sophgo/cv1800b.dtsi
+++ b/arch/riscv/boot/dts/sophgo/cv1800b.dtsi
@@ -3,121 +3,16 @@
  * Copyright (C) 2023 Jisheng Zhang <jszhang@kernel.org>
  */
 
-#include <dt-bindings/interrupt-controller/irq.h>
+#include "cv18xx.dtsi"
 
 / {
 	compatible = "sophgo,cv1800b";
-	#address-cells = <1>;
-	#size-cells = <1>;
-
-	cpus: cpus {
-		#address-cells = <1>;
-		#size-cells = <0>;
-		timebase-frequency = <25000000>;
-
-		cpu0: cpu@0 {
-			compatible = "thead,c906", "riscv";
-			device_type = "cpu";
-			reg = <0>;
-			d-cache-block-size = <64>;
-			d-cache-sets = <512>;
-			d-cache-size = <65536>;
-			i-cache-block-size = <64>;
-			i-cache-sets = <128>;
-			i-cache-size = <32768>;
-			mmu-type = "riscv,sv39";
-			riscv,isa = "rv64imafdc";
-			riscv,isa-base = "rv64i";
-			riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr",
-					       "zifencei", "zihpm";
-
-			cpu0_intc: interrupt-controller {
-				compatible = "riscv,cpu-intc";
-				interrupt-controller;
-				#address-cells = <0>;
-				#interrupt-cells = <1>;
-			};
-		};
-	};
-
-	osc: oscillator {
-		compatible = "fixed-clock";
-		clock-output-names = "osc_25m";
-		#clock-cells = <0>;
-	};
-
-	soc {
-		compatible = "simple-bus";
-		interrupt-parent = <&plic>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-		dma-noncoherent;
-		ranges;
-
-		uart0: serial@4140000 {
-			compatible = "snps,dw-apb-uart";
-			reg = <0x04140000 0x100>;
-			interrupts = <44 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&osc>;
-			reg-shift = <2>;
-			reg-io-width = <4>;
-			status = "disabled";
-		};
-
-		uart1: serial@4150000 {
-			compatible = "snps,dw-apb-uart";
-			reg = <0x04150000 0x100>;
-			interrupts = <45 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&osc>;
-			reg-shift = <2>;
-			reg-io-width = <4>;
-			status = "disabled";
-		};
-
-		uart2: serial@4160000 {
-			compatible = "snps,dw-apb-uart";
-			reg = <0x04160000 0x100>;
-			interrupts = <46 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&osc>;
-			reg-shift = <2>;
-			reg-io-width = <4>;
-			status = "disabled";
-		};
-
-		uart3: serial@4170000 {
-			compatible = "snps,dw-apb-uart";
-			reg = <0x04170000 0x100>;
-			interrupts = <47 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&osc>;
-			reg-shift = <2>;
-			reg-io-width = <4>;
-			status = "disabled";
-		};
-
-		uart4: serial@41c0000 {
-			compatible = "snps,dw-apb-uart";
-			reg = <0x041c0000 0x100>;
-			interrupts = <48 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&osc>;
-			reg-shift = <2>;
-			reg-io-width = <4>;
-			status = "disabled";
-		};
+};
 
-		plic: interrupt-controller@70000000 {
-			compatible = "sophgo,cv1800b-plic", "thead,c900-plic";
-			reg = <0x70000000 0x4000000>;
-			interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>;
-			interrupt-controller;
-			#address-cells = <0>;
-			#interrupt-cells = <2>;
-			riscv,ndev = <101>;
-		};
+&plic {
+	compatible = "sophgo,cv1800b-plic", "thead,c900-plic";
+};
 
-		clint: timer@74000000 {
-			compatible = "sophgo,cv1800b-clint", "thead,c900-clint";
-			reg = <0x74000000 0x10000>;
-			interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>;
-		};
-	};
+&clint {
+	compatible = "sophgo,cv1800b-clint", "thead,c900-clint";
 };
diff --git a/arch/riscv/boot/dts/sophgo/cv1812h-huashan-pi.dts b/arch/riscv/boot/dts/sophgo/cv1812h-huashan-pi.dts
new file mode 100644
index 000000000000..aa361f3a86bb
--- /dev/null
+++ b/arch/riscv/boot/dts/sophgo/cv1812h-huashan-pi.dts
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (C) 2023 Inochi Amaoto <inochiama@outlook.com>
+ */
+
+/dts-v1/;
+
+#include "cv1812h.dtsi"
+
+/ {
+	model = "Huashan Pi";
+	compatible = "sophgo,huashan-pi", "sophgo,cv1812h";
+
+	aliases {
+		gpio0 = &gpio0;
+		gpio1 = &gpio1;
+		gpio2 = &gpio2;
+		gpio3 = &gpio3;
+		serial0 = &uart0;
+		serial1 = &uart1;
+		serial2 = &uart2;
+		serial3 = &uart3;
+		serial4 = &uart4;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	reserved-memory {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		coprocessor_rtos: region@8fe00000 {
+			reg = <0x8fe00000 0x200000>;
+			no-map;
+		};
+	};
+};
+
+&osc {
+	clock-frequency = <25000000>;
+};
+
+&uart0 {
+	status = "okay";
+};
diff --git a/arch/riscv/boot/dts/sophgo/cv1812h.dtsi b/arch/riscv/boot/dts/sophgo/cv1812h.dtsi
new file mode 100644
index 000000000000..3e7a942f5c1a
--- /dev/null
+++ b/arch/riscv/boot/dts/sophgo/cv1812h.dtsi
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (C) 2023 Inochi Amaoto <inochiama@outlook.com>
+ */
+
+#include <dt-bindings/interrupt-controller/irq.h>
+#include "cv18xx.dtsi"
+
+/ {
+	compatible = "sophgo,cv1812h";
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x80000000 0x10000000>;
+	};
+};
+
+&plic {
+	compatible = "sophgo,cv1812h-plic", "thead,c900-plic";
+};
+
+&clint {
+	compatible = "sophgo,cv1812h-clint", "thead,c900-clint";
+};
diff --git a/arch/riscv/boot/dts/sophgo/cv18xx.dtsi b/arch/riscv/boot/dts/sophgo/cv18xx.dtsi
new file mode 100644
index 000000000000..2d6f4a4b1e58
--- /dev/null
+++ b/arch/riscv/boot/dts/sophgo/cv18xx.dtsi
@@ -0,0 +1,192 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (C) 2023 Jisheng Zhang <jszhang@kernel.org>
+ * Copyright (C) 2023 Inochi Amaoto <inochiama@outlook.com>
+ */
+
+#include <dt-bindings/interrupt-controller/irq.h>
+
+/ {
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	cpus: cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		timebase-frequency = <25000000>;
+
+		cpu0: cpu@0 {
+			compatible = "thead,c906", "riscv";
+			device_type = "cpu";
+			reg = <0>;
+			d-cache-block-size = <64>;
+			d-cache-sets = <512>;
+			d-cache-size = <65536>;
+			i-cache-block-size = <64>;
+			i-cache-sets = <128>;
+			i-cache-size = <32768>;
+			mmu-type = "riscv,sv39";
+			riscv,isa = "rv64imafdc";
+			riscv,isa-base = "rv64i";
+			riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr",
+					       "zifencei", "zihpm";
+
+			cpu0_intc: interrupt-controller {
+				compatible = "riscv,cpu-intc";
+				interrupt-controller;
+				#interrupt-cells = <1>;
+			};
+		};
+	};
+
+	osc: oscillator {
+		compatible = "fixed-clock";
+		clock-output-names = "osc_25m";
+		#clock-cells = <0>;
+	};
+
+	soc {
+		compatible = "simple-bus";
+		interrupt-parent = <&plic>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		dma-noncoherent;
+		ranges;
+
+		gpio0: gpio@3020000 {
+			compatible = "snps,dw-apb-gpio";
+			reg = <0x3020000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			porta: gpio-controller@0 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				ngpios = <32>;
+				reg = <0>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				interrupts = <60 IRQ_TYPE_LEVEL_HIGH>;
+			};
+		};
+
+		gpio1: gpio@3021000 {
+			compatible = "snps,dw-apb-gpio";
+			reg = <0x3021000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			portb: gpio-controller@0 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				ngpios = <32>;
+				reg = <0>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				interrupts = <61 IRQ_TYPE_LEVEL_HIGH>;
+			};
+		};
+
+		gpio2: gpio@3022000 {
+			compatible = "snps,dw-apb-gpio";
+			reg = <0x3022000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			portc: gpio-controller@0 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				ngpios = <32>;
+				reg = <0>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				interrupts = <62 IRQ_TYPE_LEVEL_HIGH>;
+			};
+		};
+
+		gpio3: gpio@3023000 {
+			compatible = "snps,dw-apb-gpio";
+			reg = <0x3023000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			portd: gpio-controller@0 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				ngpios = <32>;
+				reg = <0>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				interrupts = <63 IRQ_TYPE_LEVEL_HIGH>;
+			};
+		};
+
+		uart0: serial@4140000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x04140000 0x100>;
+			interrupts = <44 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&osc>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			status = "disabled";
+		};
+
+		uart1: serial@4150000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x04150000 0x100>;
+			interrupts = <45 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&osc>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			status = "disabled";
+		};
+
+		uart2: serial@4160000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x04160000 0x100>;
+			interrupts = <46 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&osc>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			status = "disabled";
+		};
+
+		uart3: serial@4170000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x04170000 0x100>;
+			interrupts = <47 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&osc>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			status = "disabled";
+		};
+
+		uart4: serial@41c0000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x041c0000 0x100>;
+			interrupts = <48 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&osc>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			status = "disabled";
+		};
+
+		plic: interrupt-controller@70000000 {
+			reg = <0x70000000 0x4000000>;
+			interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>;
+			interrupt-controller;
+			#address-cells = <0>;
+			#interrupt-cells = <2>;
+			riscv,ndev = <101>;
+		};
+
+		clint: timer@74000000 {
+			reg = <0x74000000 0x10000>;
+			interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>;
+		};
+	};
+};
diff --git a/arch/riscv/boot/dts/starfive/jh7100-common.dtsi b/arch/riscv/boot/dts/starfive/jh7100-common.dtsi
index b93ce351a90f..42fb61c36068 100644
--- a/arch/riscv/boot/dts/starfive/jh7100-common.dtsi
+++ b/arch/riscv/boot/dts/starfive/jh7100-common.dtsi
@@ -12,6 +12,8 @@
 
 / {
 	aliases {
+		mmc0 = &sdio0;
+		mmc1 = &sdio1;
 		serial0 = &uart3;
 	};
 
@@ -39,6 +41,35 @@
 			label = "ack";
 		};
 	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		dma-reserved@fa000000 {
+			reg = <0x0 0xfa000000 0x0 0x1000000>;
+			no-map;
+		};
+
+		linux,dma@107a000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x10 0x7a000000 0x0 0x1000000>;
+			no-map;
+			linux,dma-default;
+		};
+	};
+
+	soc {
+		dma-ranges = <0x00 0x80000000 0x00 0x80000000 0x00 0x7a000000>,
+			     <0x00 0xfa000000 0x10 0x7a000000 0x00 0x01000000>,
+			     <0x00 0xfb000000 0x00 0xfb000000 0x07 0x85000000>;
+	};
+
+	wifi_pwrseq: wifi-pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		reset-gpios = <&gpio 37 GPIO_ACTIVE_LOW>;
+	};
 };
 
 &gpio {
@@ -84,6 +115,78 @@
 		};
 	};
 
+	sdio0_pins: sdio0-0 {
+		clk-pins {
+			pinmux = <GPIOMUX(54, GPO_SDIO0_PAD_CCLK_OUT,
+				  GPO_ENABLE, GPI_NONE)>;
+			bias-disable;
+			input-disable;
+			input-schmitt-disable;
+		};
+		sdio-pins {
+			pinmux = <GPIOMUX(55, GPO_LOW, GPO_DISABLE,
+				  GPI_SDIO0_PAD_CARD_DETECT_N)>,
+				 <GPIOMUX(53,
+				  GPO_SDIO0_PAD_CCMD_OUT,
+				  GPO_SDIO0_PAD_CCMD_OEN,
+				  GPI_SDIO0_PAD_CCMD_IN)>,
+				 <GPIOMUX(49,
+				  GPO_SDIO0_PAD_CDATA_OUT_BIT0,
+				  GPO_SDIO0_PAD_CDATA_OEN_BIT0,
+				  GPI_SDIO0_PAD_CDATA_IN_BIT0)>,
+				 <GPIOMUX(50,
+				  GPO_SDIO0_PAD_CDATA_OUT_BIT1,
+				  GPO_SDIO0_PAD_CDATA_OEN_BIT1,
+				  GPI_SDIO0_PAD_CDATA_IN_BIT1)>,
+				 <GPIOMUX(51,
+				  GPO_SDIO0_PAD_CDATA_OUT_BIT2,
+				  GPO_SDIO0_PAD_CDATA_OEN_BIT2,
+				  GPI_SDIO0_PAD_CDATA_IN_BIT2)>,
+				 <GPIOMUX(52,
+				  GPO_SDIO0_PAD_CDATA_OUT_BIT3,
+				  GPO_SDIO0_PAD_CDATA_OEN_BIT3,
+				  GPI_SDIO0_PAD_CDATA_IN_BIT3)>;
+			bias-pull-up;
+			input-enable;
+			input-schmitt-enable;
+		};
+	};
+
+	sdio1_pins: sdio1-0 {
+		clk-pins {
+			pinmux = <GPIOMUX(33, GPO_SDIO1_PAD_CCLK_OUT,
+				  GPO_ENABLE, GPI_NONE)>;
+			bias-disable;
+			input-disable;
+			input-schmitt-disable;
+		};
+		sdio-pins {
+			pinmux = <GPIOMUX(29,
+				  GPO_SDIO1_PAD_CCMD_OUT,
+				  GPO_SDIO1_PAD_CCMD_OEN,
+				  GPI_SDIO1_PAD_CCMD_IN)>,
+				 <GPIOMUX(36,
+				  GPO_SDIO1_PAD_CDATA_OUT_BIT0,
+				  GPO_SDIO1_PAD_CDATA_OEN_BIT0,
+				  GPI_SDIO1_PAD_CDATA_IN_BIT0)>,
+				 <GPIOMUX(30,
+				  GPO_SDIO1_PAD_CDATA_OUT_BIT1,
+				  GPO_SDIO1_PAD_CDATA_OEN_BIT1,
+				  GPI_SDIO1_PAD_CDATA_IN_BIT1)>,
+				 <GPIOMUX(34,
+				  GPO_SDIO1_PAD_CDATA_OUT_BIT2,
+				  GPO_SDIO1_PAD_CDATA_OEN_BIT2,
+				  GPI_SDIO1_PAD_CDATA_IN_BIT2)>,
+				 <GPIOMUX(31,
+				  GPO_SDIO1_PAD_CDATA_OUT_BIT3,
+				  GPO_SDIO1_PAD_CDATA_OEN_BIT3,
+				  GPI_SDIO1_PAD_CDATA_IN_BIT3)>;
+			bias-pull-up;
+			input-enable;
+			input-schmitt-enable;
+		};
+	};
+
 	uart3_pins: uart3-0 {
 		rx-pins {
 			pinmux = <GPIOMUX(13, GPO_LOW, GPO_DISABLE,
@@ -154,6 +257,34 @@
 	clock-frequency = <27000000>;
 };
 
+&sdio0 {
+	broken-cd;
+	bus-width = <4>;
+	cap-sd-highspeed;
+	pinctrl-names = "default";
+	pinctrl-0 = <&sdio0_pins>;
+	status = "okay";
+};
+
+&sdio1 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	bus-width = <4>;
+	cap-sd-highspeed;
+	cap-sdio-irq;
+	cap-power-off-card;
+	mmc-pwrseq = <&wifi_pwrseq>;
+	non-removable;
+	pinctrl-names = "default";
+	pinctrl-0 = <&sdio1_pins>;
+	status = "okay";
+
+	wifi@1 {
+		compatible = "brcm,bcm4329-fmac";
+		reg = <1>;
+	};
+};
+
 &uart3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&uart3_pins>;
diff --git a/arch/riscv/boot/dts/starfive/jh7100.dtsi b/arch/riscv/boot/dts/starfive/jh7100.dtsi
index e68cafe7545f..c216aaecac53 100644
--- a/arch/riscv/boot/dts/starfive/jh7100.dtsi
+++ b/arch/riscv/boot/dts/starfive/jh7100.dtsi
@@ -32,6 +32,7 @@
 			i-tlb-sets = <1>;
 			i-tlb-size = <32>;
 			mmu-type = "riscv,sv39";
+			next-level-cache = <&ccache>;
 			riscv,isa = "rv64imafdc";
 			riscv,isa-base = "rv64i";
 			riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr",
@@ -60,6 +61,7 @@
 			i-tlb-sets = <1>;
 			i-tlb-size = <32>;
 			mmu-type = "riscv,sv39";
+			next-level-cache = <&ccache>;
 			riscv,isa = "rv64imafdc";
 			riscv,isa-base = "rv64i";
 			riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr",
@@ -144,26 +146,64 @@
 		interrupt-parent = <&plic>;
 		#address-cells = <2>;
 		#size-cells = <2>;
+		dma-noncoherent;
 		ranges;
 
 		clint: clint@2000000 {
 			compatible = "starfive,jh7100-clint", "sifive,clint0";
 			reg = <0x0 0x2000000 0x0 0x10000>;
-			interrupts-extended = <&cpu0_intc 3 &cpu0_intc 7
-					       &cpu1_intc 3 &cpu1_intc 7>;
+			interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>,
+					      <&cpu1_intc 3>, <&cpu1_intc 7>;
+		};
+
+		ccache: cache-controller@2010000 {
+			compatible = "starfive,jh7100-ccache", "sifive,ccache0", "cache";
+			reg = <0x0 0x2010000 0x0 0x1000>;
+			interrupts = <128>, <130>, <131>, <129>;
+			cache-block-size = <64>;
+			cache-level = <2>;
+			cache-sets = <2048>;
+			cache-size = <2097152>;
+			cache-unified;
 		};
 
 		plic: interrupt-controller@c000000 {
 			compatible = "starfive,jh7100-plic", "sifive,plic-1.0.0";
 			reg = <0x0 0xc000000 0x0 0x4000000>;
-			interrupts-extended = <&cpu0_intc 11 &cpu0_intc 9
-					       &cpu1_intc 11 &cpu1_intc 9>;
+			interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>,
+					      <&cpu1_intc 11>, <&cpu1_intc 9>;
 			interrupt-controller;
 			#address-cells = <0>;
 			#interrupt-cells = <1>;
 			riscv,ndev = <133>;
 		};
 
+		sdio0: mmc@10000000 {
+			compatible = "snps,dw-mshc";
+			reg = <0x0 0x10000000 0x0 0x10000>;
+			clocks = <&clkgen JH7100_CLK_SDIO0_AHB>,
+				 <&clkgen JH7100_CLK_SDIO0_CCLKINT_INV>;
+			clock-names = "biu", "ciu";
+			interrupts = <4>;
+			data-addr = <0>;
+			fifo-depth = <32>;
+			fifo-watermark-aligned;
+			status = "disabled";
+		};
+
+		sdio1: mmc@10010000 {
+			compatible = "snps,dw-mshc";
+			reg = <0x0 0x10010000 0x0 0x10000>;
+			clocks = <&clkgen JH7100_CLK_SDIO1_AHB>,
+				 <&clkgen JH7100_CLK_SDIO1_CCLKINT_INV>;
+			clock-names = "biu", "ciu";
+			interrupts = <5>;
+			data-addr = <0>;
+			fifo-depth = <32>;
+			fifo-watermark-aligned;
+			status = "disabled";
+		};
+
 		clkgen: clock-controller@11800000 {
 			compatible = "starfive,jh7100-clkgen";
 			reg = <0x0 0x11800000 0x0 0x10000>;
diff --git a/arch/riscv/boot/dts/thead/th1520-beaglev-ahead.dts b/arch/riscv/boot/dts/thead/th1520-beaglev-ahead.dts
index 70e8042c8304..d9b4de9e4757 100644
--- a/arch/riscv/boot/dts/thead/th1520-beaglev-ahead.dts
+++ b/arch/riscv/boot/dts/thead/th1520-beaglev-ahead.dts
@@ -48,6 +48,10 @@
 	clock-frequency = <62500000>;
 };
 
+&sdhci_clk {
+	clock-frequency = <198000000>;
+};
+
 &uart_sclk {
 	clock-frequency = <100000000>;
 };
@@ -56,6 +60,22 @@
 	status = "okay";
 };
 
+&emmc {
+	bus-width = <8>;
+	max-frequency = <198000000>;
+	mmc-hs400-1_8v;
+	non-removable;
+	no-sdio;
+	no-sd;
+	status = "okay";
+};
+
+&sdio0 {
+	bus-width = <4>;
+	max-frequency = <198000000>;
+	status = "okay";
+};
+
 &uart0 {
 	status = "okay";
 };
diff --git a/arch/riscv/boot/dts/thead/th1520-lichee-module-4a.dtsi b/arch/riscv/boot/dts/thead/th1520-lichee-module-4a.dtsi
index a802ab110429..1365d3a512a3 100644
--- a/arch/riscv/boot/dts/thead/th1520-lichee-module-4a.dtsi
+++ b/arch/riscv/boot/dts/thead/th1520-lichee-module-4a.dtsi
@@ -29,6 +29,10 @@
 	clock-frequency = <62500000>;
 };
 
+&sdhci_clk {
+	clock-frequency = <198000000>;
+};
+
 &uart_sclk {
 	clock-frequency = <100000000>;
 };
@@ -36,3 +40,19 @@
 &dmac0 {
 	status = "okay";
 };
+
+&emmc {
+	bus-width = <8>;
+	max-frequency = <198000000>;
+	mmc-hs400-1_8v;
+	non-removable;
+	no-sdio;
+	no-sd;
+	status = "okay";
+};
+
+&sdio0 {
+	bus-width = <4>;
+	max-frequency = <198000000>;
+	status = "okay";
+};
diff --git a/arch/riscv/boot/dts/thead/th1520.dtsi b/arch/riscv/boot/dts/thead/th1520.dtsi
index ba4d2c673ac8..8b915e206f3a 100644
--- a/arch/riscv/boot/dts/thead/th1520.dtsi
+++ b/arch/riscv/boot/dts/thead/th1520.dtsi
@@ -146,6 +146,13 @@
 		#clock-cells = <0>;
 	};
 
+	sdhci_clk: sdhci-clock {
+		compatible = "fixed-clock";
+		clock-frequency = <198000000>;
+		clock-output-names = "sdhci_clk";
+		#clock-cells = <0>;
+	};
+
 	soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&plic>;
@@ -304,6 +311,33 @@
 			status = "disabled";
 		};
 
+		emmc: mmc@ffe7080000 {
+			compatible = "thead,th1520-dwcmshc";
+			reg = <0xff 0xe7080000 0x0 0x10000>;
+			interrupts = <62 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&sdhci_clk>;
+			clock-names = "core";
+			status = "disabled";
+		};
+
+		sdio0: mmc@ffe7090000 {
+			compatible = "thead,th1520-dwcmshc";
+			reg = <0xff 0xe7090000 0x0 0x10000>;
+			interrupts = <64 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&sdhci_clk>;
+			clock-names = "core";
+			status = "disabled";
+		};
+
+		sdio1: mmc@ffe70a0000 {
+			compatible = "thead,th1520-dwcmshc";
+			reg = <0xff 0xe70a0000 0x0 0x10000>;
+			interrupts = <71 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&sdhci_clk>;
+			clock-names = "core";
+			status = "disabled";
+		};
+
 		timer0: timer@ffefc32000 {
 			compatible = "snps,dw-apb-timer";
 			reg = <0xff 0xefc32000 0x0 0x14>;
diff --git a/arch/riscv/errata/andes/errata.c b/arch/riscv/errata/andes/errata.c
index 197db68cc8da..17a904869724 100644
--- a/arch/riscv/errata/andes/errata.c
+++ b/arch/riscv/errata/andes/errata.c
@@ -38,29 +38,35 @@ static long ax45mp_iocp_sw_workaround(void)
 	return ret.error ? 0 : ret.value;
 }
 
-static bool errata_probe_iocp(unsigned int stage, unsigned long arch_id, unsigned long impid)
+static void errata_probe_iocp(unsigned int stage, unsigned long arch_id, unsigned long impid)
 {
+	static bool done;
+
 	if (!IS_ENABLED(CONFIG_ERRATA_ANDES_CMO))
-		return false;
+		return;
+
+	if (done)
+		return;
+
+	done = true;
 
 	if (arch_id != ANDESTECH_AX45MP_MARCHID || impid != ANDESTECH_AX45MP_MIMPID)
-		return false;
+		return;
 
 	if (!ax45mp_iocp_sw_workaround())
-		return false;
+		return;
 
 	/* Set this just to make core cbo code happy */
 	riscv_cbom_block_size = 1;
 	riscv_noncoherent_supported();
-
-	return true;
 }
 
 void __init_or_module andes_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
 					      unsigned long archid, unsigned long impid,
 					      unsigned int stage)
 {
-	errata_probe_iocp(stage, archid, impid);
+	if (stage == RISCV_ALTERNATIVES_BOOT)
+		errata_probe_iocp(stage, archid, impid);
 
 	/* we have nothing to patch here ATM so just return back */
 }
diff --git a/arch/riscv/include/asm/cfi.h b/arch/riscv/include/asm/cfi.h
index 56bf9d69d5e3..8f7a62257044 100644
--- a/arch/riscv/include/asm/cfi.h
+++ b/arch/riscv/include/asm/cfi.h
@@ -7,8 +7,9 @@
  *
  * Copyright (C) 2023 Google LLC
  */
+#include <linux/bug.h>
 
-#include <linux/cfi.h>
+struct pt_regs;
 
 #ifdef CONFIG_CFI_CLANG
 enum bug_trap_type handle_cfi_failure(struct pt_regs *regs);
diff --git a/arch/riscv/include/asm/irq_work.h b/arch/riscv/include/asm/irq_work.h
index b53891964ae0..b27a4d64fc6a 100644
--- a/arch/riscv/include/asm/irq_work.h
+++ b/arch/riscv/include/asm/irq_work.h
@@ -6,5 +6,5 @@ static inline bool arch_irq_work_has_interrupt(void)
 {
 	return IS_ENABLED(CONFIG_SMP);
 }
-extern void arch_irq_work_raise(void);
+
 #endif /* _ASM_RISCV_IRQ_WORK_H */
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 294044429e8e..7b4287f36054 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -673,6 +673,7 @@ static inline int pmd_write(pmd_t pmd)
 	return pte_write(pmd_pte(pmd));
 }
 
+#define pmd_dirty pmd_dirty
 static inline int pmd_dirty(pmd_t pmd)
 {
 	return pte_dirty(pmd_pte(pmd));
@@ -899,7 +900,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
 #define PAGE_KERNEL		__pgprot(0)
 #define swapper_pg_dir		NULL
 #define TASK_SIZE		0xffffffffUL
-#define VMALLOC_START		0
+#define VMALLOC_START		_AC(0, UL)
 #define VMALLOC_END		TASK_SIZE
 
 #endif /* !CONFIG_MMU */
diff --git a/arch/riscv/include/asm/syscall_wrapper.h b/arch/riscv/include/asm/syscall_wrapper.h
index 1d7942c8a6cb..eeec04b7dae6 100644
--- a/arch/riscv/include/asm/syscall_wrapper.h
+++ b/arch/riscv/include/asm/syscall_wrapper.h
@@ -46,9 +46,6 @@ asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *);
 		return sys_ni_syscall();						\
 	}
 
-#define COMPAT_SYS_NI(name) \
-	SYSCALL_ALIAS(__riscv_compat_sys_##name, sys_ni_posix_timers);
-
 #endif /* CONFIG_COMPAT */
 
 #define __SYSCALL_DEFINEx(x, name, ...)						\
@@ -82,6 +79,4 @@ asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *);
 		return sys_ni_syscall();					\
 	}
 
-#define SYS_NI(name) SYSCALL_ALIAS(__riscv_sys_##name, sys_ni_posix_timers);
-
 #endif /* __ASM_SYSCALL_WRAPPER_H */
diff --git a/arch/riscv/include/asm/topology.h b/arch/riscv/include/asm/topology.h
index e316ab3b77f3..61183688bdd5 100644
--- a/arch/riscv/include/asm/topology.h
+++ b/arch/riscv/include/asm/topology.h
@@ -9,6 +9,7 @@
 #define arch_set_freq_scale		topology_set_freq_scale
 #define arch_scale_freq_capacity	topology_get_freq_scale
 #define arch_scale_freq_invariant	topology_scale_freq_invariant
+#define arch_scale_freq_ref		topology_get_freq_ref
 
 /* Replace task scheduler's default cpu-invariant accounting */
 #define arch_scale_cpu_capacity	topology_get_cpu_scale
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index fee22a3d1b53..82940b6a79a2 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -11,7 +11,7 @@ endif
 CFLAGS_syscall_table.o	+= $(call cc-option,-Wno-override-init,)
 CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,)
 
-ifdef CONFIG_KEXEC
+ifdef CONFIG_KEXEC_CORE
 AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax)
 endif
 
diff --git a/arch/riscv/kernel/cfi.c b/arch/riscv/kernel/cfi.c
index 820158d7a291..6ec9dbd7292e 100644
--- a/arch/riscv/kernel/cfi.c
+++ b/arch/riscv/kernel/cfi.c
@@ -4,7 +4,7 @@
  *
  * Copyright (C) 2023 Google LLC
  */
-#include <asm/cfi.h>
+#include <linux/cfi.h>
 #include <asm/insn.h>
 
 /*
diff --git a/arch/riscv/kernel/crash_core.c b/arch/riscv/kernel/crash_core.c
index 55f1d7856b54..8706736fd4e2 100644
--- a/arch/riscv/kernel/crash_core.c
+++ b/arch/riscv/kernel/crash_core.c
@@ -5,18 +5,20 @@
 
 void arch_crash_save_vmcoreinfo(void)
 {
-	VMCOREINFO_NUMBER(VA_BITS);
 	VMCOREINFO_NUMBER(phys_ram_base);
 
 	vmcoreinfo_append_str("NUMBER(PAGE_OFFSET)=0x%lx\n", PAGE_OFFSET);
 	vmcoreinfo_append_str("NUMBER(VMALLOC_START)=0x%lx\n", VMALLOC_START);
 	vmcoreinfo_append_str("NUMBER(VMALLOC_END)=0x%lx\n", VMALLOC_END);
+#ifdef CONFIG_MMU
+	VMCOREINFO_NUMBER(VA_BITS);
 	vmcoreinfo_append_str("NUMBER(VMEMMAP_START)=0x%lx\n", VMEMMAP_START);
 	vmcoreinfo_append_str("NUMBER(VMEMMAP_END)=0x%lx\n", VMEMMAP_END);
 #ifdef CONFIG_64BIT
 	vmcoreinfo_append_str("NUMBER(MODULES_VADDR)=0x%lx\n", MODULES_VADDR);
 	vmcoreinfo_append_str("NUMBER(MODULES_END)=0x%lx\n", MODULES_END);
 #endif
+#endif
 	vmcoreinfo_append_str("NUMBER(KERNEL_LINK_ADDR)=0x%lx\n", KERNEL_LINK_ADDR);
 	vmcoreinfo_append_str("NUMBER(va_kernel_pa_offset)=0x%lx\n",
 						kernel_map.va_kernel_pa_offset);
diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c
index e60fbd8660c4..5bd1ec3341fe 100644
--- a/arch/riscv/kernel/elf_kexec.c
+++ b/arch/riscv/kernel/elf_kexec.c
@@ -216,7 +216,6 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf,
 	if (ret)
 		goto out;
 	kernel_start = image->start;
-	pr_notice("The entry point of kernel at 0x%lx\n", image->start);
 
 	/* Add the kernel binary to the image */
 	ret = riscv_kexec_elf_load(image, &ehdr, &elf_info,
@@ -252,8 +251,8 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf,
 		image->elf_load_addr = kbuf.mem;
 		image->elf_headers_sz = headers_sz;
 
-		pr_debug("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
-			 image->elf_load_addr, kbuf.bufsz, kbuf.memsz);
+		kexec_dprintk("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+			      image->elf_load_addr, kbuf.bufsz, kbuf.memsz);
 
 		/* Setup cmdline for kdump kernel case */
 		modified_cmdline = setup_kdump_cmdline(image, cmdline,
@@ -275,6 +274,8 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf,
 		pr_err("Error loading purgatory ret=%d\n", ret);
 		goto out;
 	}
+	kexec_dprintk("Loaded purgatory at 0x%lx\n", kbuf.mem);
+
 	ret = kexec_purgatory_get_set_symbol(image, "riscv_kernel_entry",
 					     &kernel_start,
 					     sizeof(kernel_start), 0);
@@ -293,7 +294,7 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf,
 		if (ret)
 			goto out;
 		initrd_pbase = kbuf.mem;
-		pr_notice("Loaded initrd at 0x%lx\n", initrd_pbase);
+		kexec_dprintk("Loaded initrd at 0x%lx\n", initrd_pbase);
 	}
 
 	/* Add the DTB to the image */
@@ -318,7 +319,7 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf,
 	}
 	/* Cache the fdt buffer address for memory cleanup */
 	image->arch.fdt = fdt;
-	pr_notice("Loaded device tree at 0x%lx\n", kbuf.mem);
+	kexec_dprintk("Loaded device tree at 0x%lx\n", kbuf.mem);
 	goto out;
 
 out_free_fdt:
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index b77397432403..76ace1e0b46f 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -154,7 +154,6 @@ secondary_start_sbi:
 	XIP_FIXUP_OFFSET a3
 	add a3, a3, a1
 	REG_L sp, (a3)
-	scs_load_current
 
 .Lsecondary_start_common:
 
@@ -165,6 +164,7 @@ secondary_start_sbi:
 	call relocate_enable_mmu
 #endif
 	call .Lsetup_trap_vector
+	scs_load_current
 	tail smp_callin
 #endif /* CONFIG_SMP */
 
diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c
index 2d139b724bc8..ed9cad20c039 100644
--- a/arch/riscv/kernel/machine_kexec.c
+++ b/arch/riscv/kernel/machine_kexec.c
@@ -19,30 +19,6 @@
 #include <linux/irq.h>
 
 /*
- * kexec_image_info - Print received image details
- */
-static void
-kexec_image_info(const struct kimage *image)
-{
-	unsigned long i;
-
-	pr_debug("Kexec image info:\n");
-	pr_debug("\ttype:        %d\n", image->type);
-	pr_debug("\tstart:       %lx\n", image->start);
-	pr_debug("\thead:        %lx\n", image->head);
-	pr_debug("\tnr_segments: %lu\n", image->nr_segments);
-
-	for (i = 0; i < image->nr_segments; i++) {
-		pr_debug("\t    segment[%lu]: %016lx - %016lx", i,
-			image->segment[i].mem,
-			image->segment[i].mem + image->segment[i].memsz);
-		pr_debug("\t\t0x%lx bytes, %lu pages\n",
-			(unsigned long) image->segment[i].memsz,
-			(unsigned long) image->segment[i].memsz /  PAGE_SIZE);
-	}
-}
-
-/*
  * machine_kexec_prepare - Initialize kexec
  *
  * This function is called from do_kexec_load, when the user has
@@ -60,8 +36,6 @@ machine_kexec_prepare(struct kimage *image)
 	unsigned int control_code_buffer_sz = 0;
 	int i = 0;
 
-	kexec_image_info(image);
-
 	/* Find the Flattened Device Tree and save its physical address */
 	for (i = 0; i < image->nr_segments; i++) {
 		if (image->segment[i].memsz <= sizeof(fdt))
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 56a8c78e9e21..aac019ed63b1 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -40,15 +40,6 @@ struct relocation_handlers {
 				  long buffer);
 };
 
-unsigned int initialize_relocation_hashtable(unsigned int num_relocations);
-void process_accumulated_relocations(struct module *me);
-int add_relocation_to_accumulate(struct module *me, int type, void *location,
-				 unsigned int hashtable_bits, Elf_Addr v);
-
-struct hlist_head *relocation_hashtable;
-
-struct list_head used_buckets_list;
-
 /*
  * The auipc+jalr instruction pair can reach any PC-relative offset
  * in the range [-2^31 - 2^11, 2^31 - 2^11)
@@ -64,7 +55,7 @@ static bool riscv_insn_valid_32bit_offset(ptrdiff_t val)
 
 static int riscv_insn_rmw(void *location, u32 keep, u32 set)
 {
-	u16 *parcel = location;
+	__le16 *parcel = location;
 	u32 insn = (u32)le16_to_cpu(parcel[0]) | (u32)le16_to_cpu(parcel[1]) << 16;
 
 	insn &= keep;
@@ -77,7 +68,7 @@ static int riscv_insn_rmw(void *location, u32 keep, u32 set)
 
 static int riscv_insn_rvc_rmw(void *location, u16 keep, u16 set)
 {
-	u16 *parcel = location;
+	__le16 *parcel = location;
 	u16 insn = le16_to_cpu(*parcel);
 
 	insn &= keep;
@@ -604,7 +595,10 @@ static const struct relocation_handlers reloc_handlers[] = {
 	/* 192-255 nonstandard ABI extensions  */
 };
 
-void process_accumulated_relocations(struct module *me)
+static void
+process_accumulated_relocations(struct module *me,
+				struct hlist_head **relocation_hashtable,
+				struct list_head *used_buckets_list)
 {
 	/*
 	 * Only ADD/SUB/SET/ULEB128 should end up here.
@@ -624,18 +618,25 @@ void process_accumulated_relocations(struct module *me)
 	 *	- Each relocation entry for a location address
 	 */
 	struct used_bucket *bucket_iter;
+	struct used_bucket *bucket_iter_tmp;
 	struct relocation_head *rel_head_iter;
+	struct hlist_node *rel_head_iter_tmp;
 	struct relocation_entry *rel_entry_iter;
+	struct relocation_entry *rel_entry_iter_tmp;
 	int curr_type;
 	void *location;
 	long buffer;
 
-	list_for_each_entry(bucket_iter, &used_buckets_list, head) {
-		hlist_for_each_entry(rel_head_iter, bucket_iter->bucket, node) {
+	list_for_each_entry_safe(bucket_iter, bucket_iter_tmp,
+				 used_buckets_list, head) {
+		hlist_for_each_entry_safe(rel_head_iter, rel_head_iter_tmp,
+					  bucket_iter->bucket, node) {
 			buffer = 0;
 			location = rel_head_iter->location;
-			list_for_each_entry(rel_entry_iter,
-					    rel_head_iter->rel_entry, head) {
+			list_for_each_entry_safe(rel_entry_iter,
+						 rel_entry_iter_tmp,
+						 rel_head_iter->rel_entry,
+						 head) {
 				curr_type = rel_entry_iter->type;
 				reloc_handlers[curr_type].reloc_handler(
 					me, &buffer, rel_entry_iter->value);
@@ -648,11 +649,14 @@ void process_accumulated_relocations(struct module *me)
 		kfree(bucket_iter);
 	}
 
-	kfree(relocation_hashtable);
+	kfree(*relocation_hashtable);
 }
 
-int add_relocation_to_accumulate(struct module *me, int type, void *location,
-				 unsigned int hashtable_bits, Elf_Addr v)
+static int add_relocation_to_accumulate(struct module *me, int type,
+					void *location,
+					unsigned int hashtable_bits, Elf_Addr v,
+					struct hlist_head *relocation_hashtable,
+					struct list_head *used_buckets_list)
 {
 	struct relocation_entry *entry;
 	struct relocation_head *rel_head;
@@ -661,6 +665,10 @@ int add_relocation_to_accumulate(struct module *me, int type, void *location,
 	unsigned long hash;
 
 	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+
+	if (!entry)
+		return -ENOMEM;
+
 	INIT_LIST_HEAD(&entry->head);
 	entry->type = type;
 	entry->value = v;
@@ -669,7 +677,10 @@ int add_relocation_to_accumulate(struct module *me, int type, void *location,
 
 	current_head = &relocation_hashtable[hash];
 
-	/* Find matching location (if any) */
+	/*
+	 * Search for the relocation_head for the relocations that happen at the
+	 * provided location
+	 */
 	bool found = false;
 	struct relocation_head *rel_head_iter;
 
@@ -681,19 +692,45 @@ int add_relocation_to_accumulate(struct module *me, int type, void *location,
 		}
 	}
 
+	/*
+	 * If there has not yet been any relocations at the provided location,
+	 * create a relocation_head for that location and populate it with this
+	 * relocation_entry.
+	 */
 	if (!found) {
 		rel_head = kmalloc(sizeof(*rel_head), GFP_KERNEL);
+
+		if (!rel_head) {
+			kfree(entry);
+			return -ENOMEM;
+		}
+
 		rel_head->rel_entry =
 			kmalloc(sizeof(struct list_head), GFP_KERNEL);
+
+		if (!rel_head->rel_entry) {
+			kfree(entry);
+			kfree(rel_head);
+			return -ENOMEM;
+		}
+
 		INIT_LIST_HEAD(rel_head->rel_entry);
 		rel_head->location = location;
 		INIT_HLIST_NODE(&rel_head->node);
 		if (!current_head->first) {
 			bucket =
 				kmalloc(sizeof(struct used_bucket), GFP_KERNEL);
+
+			if (!bucket) {
+				kfree(entry);
+				kfree(rel_head);
+				kfree(rel_head->rel_entry);
+				return -ENOMEM;
+			}
+
 			INIT_LIST_HEAD(&bucket->head);
 			bucket->bucket = current_head;
-			list_add(&bucket->head, &used_buckets_list);
+			list_add(&bucket->head, used_buckets_list);
 		}
 		hlist_add_head(&rel_head->node, current_head);
 	}
@@ -704,7 +741,9 @@ int add_relocation_to_accumulate(struct module *me, int type, void *location,
 	return 0;
 }
 
-unsigned int initialize_relocation_hashtable(unsigned int num_relocations)
+static unsigned int
+initialize_relocation_hashtable(unsigned int num_relocations,
+				struct hlist_head **relocation_hashtable)
 {
 	/* Can safely assume that bits is not greater than sizeof(long) */
 	unsigned long hashtable_size = roundup_pow_of_two(num_relocations);
@@ -720,12 +759,13 @@ unsigned int initialize_relocation_hashtable(unsigned int num_relocations)
 
 	hashtable_size <<= should_double_size;
 
-	relocation_hashtable = kmalloc_array(hashtable_size,
-					     sizeof(*relocation_hashtable),
-					     GFP_KERNEL);
-	__hash_init(relocation_hashtable, hashtable_size);
+	*relocation_hashtable = kmalloc_array(hashtable_size,
+					      sizeof(*relocation_hashtable),
+					      GFP_KERNEL);
+	if (!*relocation_hashtable)
+		return -ENOMEM;
 
-	INIT_LIST_HEAD(&used_buckets_list);
+	__hash_init(*relocation_hashtable, hashtable_size);
 
 	return hashtable_bits;
 }
@@ -742,7 +782,17 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 	Elf_Addr v;
 	int res;
 	unsigned int num_relocations = sechdrs[relsec].sh_size / sizeof(*rel);
-	unsigned int hashtable_bits = initialize_relocation_hashtable(num_relocations);
+	struct hlist_head *relocation_hashtable;
+	struct list_head used_buckets_list;
+	unsigned int hashtable_bits;
+
+	hashtable_bits = initialize_relocation_hashtable(num_relocations,
+							 &relocation_hashtable);
+
+	if (hashtable_bits < 0)
+		return hashtable_bits;
+
+	INIT_LIST_HEAD(&used_buckets_list);
 
 	pr_debug("Applying relocate section %u to %u\n", relsec,
 	       sechdrs[relsec].sh_info);
@@ -823,14 +873,18 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 		}
 
 		if (reloc_handlers[type].accumulate_handler)
-			res = add_relocation_to_accumulate(me, type, location, hashtable_bits, v);
+			res = add_relocation_to_accumulate(me, type, location,
+							   hashtable_bits, v,
+							   relocation_hashtable,
+							   &used_buckets_list);
 		else
 			res = handler(me, location, v);
 		if (res)
 			return res;
 	}
 
-	process_accumulated_relocations(me);
+	process_accumulated_relocations(me, &relocation_hashtable,
+					&used_buckets_list);
 
 	return 0;
 }
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index c712037dbe10..a2ca5b7756a5 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -169,7 +169,7 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 	pair->value &= ~missing;
 }
 
-static bool hwprobe_ext0_has(const struct cpumask *cpus, unsigned long ext)
+static bool hwprobe_ext0_has(const struct cpumask *cpus, u64 ext)
 {
 	struct riscv_hwprobe pair;
 
diff --git a/arch/riscv/kernel/tests/module_test/test_uleb128.S b/arch/riscv/kernel/tests/module_test/test_uleb128.S
index 90f22049d553..8515ed7cd8c1 100644
--- a/arch/riscv/kernel/tests/module_test/test_uleb128.S
+++ b/arch/riscv/kernel/tests/module_test/test_uleb128.S
@@ -6,13 +6,13 @@
 .text
 .global test_uleb_basic
 test_uleb_basic:
-	ld	a0, second
+	lw	a0, second
 	addi	a0, a0, -127
 	ret
 
 .global test_uleb_large
 test_uleb_large:
-	ld	a0, fourth
+	lw	a0, fourth
 	addi	a0, a0, -0x07e8
 	ret
 
@@ -22,10 +22,10 @@ first:
 second:
 	.reloc second, R_RISCV_SET_ULEB128, second
 	.reloc second, R_RISCV_SUB_ULEB128, first
-	.dword 0
+	.word 0
 third:
 	.space 1000
 fourth:
 	.reloc fourth, R_RISCV_SET_ULEB128, fourth
 	.reloc fourth, R_RISCV_SUB_ULEB128, third
-	.dword 0
+	.word 0
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index 5eba37147caa..5255f8134aef 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -550,16 +550,14 @@ int handle_misaligned_store(struct pt_regs *regs)
 	} else if ((insn & INSN_MASK_C_SD) == INSN_MATCH_C_SD) {
 		len = 8;
 		val.data_ulong = GET_RS2S(insn, regs);
-	} else if ((insn & INSN_MASK_C_SDSP) == INSN_MATCH_C_SDSP &&
-		   ((insn >> SH_RD) & 0x1f)) {
+	} else if ((insn & INSN_MASK_C_SDSP) == INSN_MATCH_C_SDSP) {
 		len = 8;
 		val.data_ulong = GET_RS2C(insn, regs);
 #endif
 	} else if ((insn & INSN_MASK_C_SW) == INSN_MATCH_C_SW) {
 		len = 4;
 		val.data_ulong = GET_RS2S(insn, regs);
-	} else if ((insn & INSN_MASK_C_SWSP) == INSN_MATCH_C_SWSP &&
-		   ((insn >> SH_RD) & 0x1f)) {
+	} else if ((insn & INSN_MASK_C_SWSP) == INSN_MATCH_C_SWSP) {
 		len = 4;
 		val.data_ulong = GET_RS2C(insn, regs);
 	} else if ((insn & INSN_MASK_C_FSD) == INSN_MATCH_C_FSD) {
diff --git a/arch/riscv/kernel/vdso/vgettimeofday.c b/arch/riscv/kernel/vdso/vgettimeofday.c
index cc0d80699c31..b35057802584 100644
--- a/arch/riscv/kernel/vdso/vgettimeofday.c
+++ b/arch/riscv/kernel/vdso/vgettimeofday.c
@@ -8,23 +8,18 @@
 
 #include <linux/time.h>
 #include <linux/types.h>
+#include <vdso/gettime.h>
 
-extern
-int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
 int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
 {
 	return __cvdso_clock_gettime(clock, ts);
 }
 
-extern
-int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
 int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 {
 	return __cvdso_gettimeofday(tv, tz);
 }
 
-extern
-int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res);
 int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res)
 {
 	return __cvdso_clock_getres(clock_id, res);
diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c
index 6cf23b8adb71..e808723a85f1 100644
--- a/arch/riscv/kvm/aia_imsic.c
+++ b/arch/riscv/kvm/aia_imsic.c
@@ -55,6 +55,7 @@ struct imsic {
 	/* IMSIC SW-file */
 	struct imsic_mrif *swfile;
 	phys_addr_t swfile_pa;
+	spinlock_t swfile_extirq_lock;
 };
 
 #define imsic_vs_csr_read(__c)			\
@@ -613,12 +614,23 @@ static void imsic_swfile_extirq_update(struct kvm_vcpu *vcpu)
 {
 	struct imsic *imsic = vcpu->arch.aia_context.imsic_state;
 	struct imsic_mrif *mrif = imsic->swfile;
+	unsigned long flags;
+
+	/*
+	 * The critical section is necessary during external interrupt
+	 * updates to avoid the risk of losing interrupts due to potential
+	 * interruptions between reading topei and updating pending status.
+	 */
+
+	spin_lock_irqsave(&imsic->swfile_extirq_lock, flags);
 
 	if (imsic_mrif_atomic_read(mrif, &mrif->eidelivery) &&
 	    imsic_mrif_topei(mrif, imsic->nr_eix, imsic->nr_msis))
 		kvm_riscv_vcpu_set_interrupt(vcpu, IRQ_VS_EXT);
 	else
 		kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_EXT);
+
+	spin_unlock_irqrestore(&imsic->swfile_extirq_lock, flags);
 }
 
 static void imsic_swfile_read(struct kvm_vcpu *vcpu, bool clear,
@@ -1039,6 +1051,7 @@ int kvm_riscv_vcpu_aia_imsic_init(struct kvm_vcpu *vcpu)
 	}
 	imsic->swfile = page_to_virt(swfile_page);
 	imsic->swfile_pa = page_to_phys(swfile_page);
+	spin_lock_init(&imsic->swfile_extirq_lock);
 
 	/* Setup IO device */
 	kvm_iodevice_init(&imsic->iodev, &imsic_iodoev_ops);
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 90d4ba36d1d0..081339ddf47e 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -304,6 +304,8 @@ void handle_page_fault(struct pt_regs *regs)
 		goto done;
 	}
 	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+	if (fault & VM_FAULT_MAJOR)
+		flags |= FAULT_FLAG_TRIED;
 
 	if (fault_signal_pending(fault, regs)) {
 		if (!user_mode(regs))
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 8581693e62d3..58dc64dd94a8 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -1029,23 +1029,28 @@ out:
 	return ret;
 }
 
-int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
-				void *image_end, const struct btf_func_model *m,
-				u32 flags, struct bpf_tramp_links *tlinks,
-				void *func_addr)
+int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
+			     struct bpf_tramp_links *tlinks, void *func_addr)
 {
-	int ret;
+	struct bpf_tramp_image im;
 	struct rv_jit_context ctx;
+	int ret;
 
 	ctx.ninsns = 0;
 	ctx.insns = NULL;
 	ctx.ro_insns = NULL;
-	ret = __arch_prepare_bpf_trampoline(im, m, tlinks, func_addr, flags, &ctx);
-	if (ret < 0)
-		return ret;
+	ret = __arch_prepare_bpf_trampoline(&im, m, tlinks, func_addr, flags, &ctx);
 
-	if (ninsns_rvoff(ret) > (long)image_end - (long)image)
-		return -EFBIG;
+	return ret < 0 ? ret : ninsns_rvoff(ctx.ninsns);
+}
+
+int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
+				void *image_end, const struct btf_func_model *m,
+				u32 flags, struct bpf_tramp_links *tlinks,
+				void *func_addr)
+{
+	int ret;
+	struct rv_jit_context ctx;
 
 	ctx.ninsns = 0;
 	/*
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 3bec98d20283..8f39f0424796 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -123,7 +123,6 @@ config S390
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_SYM_ANNOTATIONS
-	select ARCH_WANTS_DYNAMIC_TASK_STRUCT
 	select ARCH_WANTS_NO_INSTR
 	select ARCH_WANT_DEFAULT_BPF_JIT
 	select ARCH_WANT_IPC_PARSE_VERSION
@@ -146,7 +145,7 @@ config S390
 	select GENERIC_TIME_VSYSCALL
 	select GENERIC_VDSO_TIME_NS
 	select GENERIC_IOREMAP if PCI
-	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
+	select HAVE_ALIGNED_STRUCT_PAGE
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE
@@ -254,13 +253,13 @@ config ARCH_SUPPORTS_KEXEC
 	def_bool y
 
 config ARCH_SUPPORTS_KEXEC_FILE
-	def_bool CRYPTO && CRYPTO_SHA256 && CRYPTO_SHA256_S390
+	def_bool y
 
 config ARCH_SUPPORTS_KEXEC_SIG
 	def_bool MODULE_SIG_FORMAT
 
 config ARCH_SUPPORTS_KEXEC_PURGATORY
-	def_bool KEXEC_FILE
+	def_bool y
 
 config ARCH_SUPPORTS_CRASH_DUMP
 	def_bool y
diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c
index 2ab4872fbee1..b24de9aabf7d 100644
--- a/arch/s390/boot/ipl_parm.c
+++ b/arch/s390/boot/ipl_parm.c
@@ -274,7 +274,7 @@ void parse_boot_command_line(void)
 			memory_limit = round_down(memparse(val, NULL), PAGE_SIZE);
 
 		if (!strcmp(param, "vmalloc") && val) {
-			vmalloc_size = round_up(memparse(val, NULL), PAGE_SIZE);
+			vmalloc_size = round_up(memparse(val, NULL), _SEGMENT_SIZE);
 			vmalloc_size_set = 1;
 		}
 
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index 8104e0e3d188..9cc76e631759 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -255,7 +255,8 @@ static unsigned long setup_kernel_memory_layout(void)
 	VMALLOC_END = MODULES_VADDR;
 
 	/* allow vmalloc area to occupy up to about 1/2 of the rest virtual space left */
-	vmalloc_size = min(vmalloc_size, round_down(VMALLOC_END / 2, _REGION3_SIZE));
+	vsize = round_down(VMALLOC_END / 2, _SEGMENT_SIZE);
+	vmalloc_size = min(vmalloc_size, vsize);
 	VMALLOC_START = VMALLOC_END - vmalloc_size;
 
 	/* split remaining virtual space between 1:1 mapping & vmemmap array */
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 438cd92e6080..85490d9373fc 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -44,8 +44,7 @@ CONFIG_KEXEC_FILE=y
 CONFIG_KEXEC_SIG=y
 CONFIG_CRASH_DUMP=y
 CONFIG_LIVEPATCH=y
-CONFIG_MARCH_ZEC12=y
-CONFIG_TUNE_ZEC12=y
+CONFIG_MARCH_Z13=y
 CONFIG_NR_CPUS=512
 CONFIG_NUMA=y
 CONFIG_HZ_100=y
@@ -76,7 +75,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
-CONFIG_MODULE_SIG_SHA256=y
 CONFIG_BLK_DEV_THROTTLING=y
 CONFIG_BLK_WBT=y
 CONFIG_BLK_CGROUP_IOLATENCY=y
@@ -93,6 +91,7 @@ CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_IOSCHED_BFQ=y
 CONFIG_BINFMT_MISC=m
 CONFIG_ZSWAP=y
+CONFIG_ZSWAP_ZPOOL_DEFAULT_ZBUD=y
 CONFIG_ZSMALLOC_STAT=y
 CONFIG_SLUB_STATS=y
 # CONFIG_COMPAT_BRK is not set
@@ -374,7 +373,6 @@ CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
-CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
@@ -619,6 +617,9 @@ CONFIG_BTRFS_FS_POSIX_ACL=y
 CONFIG_BTRFS_DEBUG=y
 CONFIG_BTRFS_ASSERT=y
 CONFIG_NILFS2_FS=m
+CONFIG_BCACHEFS_FS=y
+CONFIG_BCACHEFS_QUOTA=y
+CONFIG_BCACHEFS_POSIX_ACL=y
 CONFIG_FS_DAX=y
 CONFIG_EXPORTFS_BLOCK_OPS=y
 CONFIG_FS_ENCRYPTION=y
@@ -691,7 +692,6 @@ CONFIG_PERSISTENT_KEYRINGS=y
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_KEY_NOTIFICATIONS=y
 CONFIG_SECURITY=y
-CONFIG_SECURITY_NETWORK=y
 CONFIG_HARDENED_USERCOPY=y
 CONFIG_FORTIFY_SOURCE=y
 CONFIG_SECURITY_SELINUX=y
@@ -834,7 +834,6 @@ CONFIG_DEBUG_IRQFLAGS=y
 CONFIG_DEBUG_LIST=y
 CONFIG_DEBUG_SG=y
 CONFIG_DEBUG_NOTIFIERS=y
-CONFIG_DEBUG_CREDENTIALS=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_RCU_REF_SCALE_TEST=m
 CONFIG_RCU_CPU_STALL_TIMEOUT=300
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 1b8150e50f6a..fb690fbbf54b 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -42,8 +42,7 @@ CONFIG_KEXEC_FILE=y
 CONFIG_KEXEC_SIG=y
 CONFIG_CRASH_DUMP=y
 CONFIG_LIVEPATCH=y
-CONFIG_MARCH_ZEC12=y
-CONFIG_TUNE_ZEC12=y
+CONFIG_MARCH_Z13=y
 CONFIG_NR_CPUS=512
 CONFIG_NUMA=y
 CONFIG_HZ_100=y
@@ -71,7 +70,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
-CONFIG_MODULE_SIG_SHA256=y
 CONFIG_BLK_DEV_THROTTLING=y
 CONFIG_BLK_WBT=y
 CONFIG_BLK_CGROUP_IOLATENCY=y
@@ -88,6 +86,7 @@ CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_IOSCHED_BFQ=y
 CONFIG_BINFMT_MISC=m
 CONFIG_ZSWAP=y
+CONFIG_ZSWAP_ZPOOL_DEFAULT_ZBUD=y
 CONFIG_ZSMALLOC_STAT=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_MEMORY_HOTPLUG=y
@@ -364,7 +363,6 @@ CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
-CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
@@ -605,6 +603,9 @@ CONFIG_OCFS2_FS=m
 CONFIG_BTRFS_FS=y
 CONFIG_BTRFS_FS_POSIX_ACL=y
 CONFIG_NILFS2_FS=m
+CONFIG_BCACHEFS_FS=m
+CONFIG_BCACHEFS_QUOTA=y
+CONFIG_BCACHEFS_POSIX_ACL=y
 CONFIG_FS_DAX=y
 CONFIG_EXPORTFS_BLOCK_OPS=y
 CONFIG_FS_ENCRYPTION=y
@@ -677,7 +678,6 @@ CONFIG_PERSISTENT_KEYRINGS=y
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_KEY_NOTIFICATIONS=y
 CONFIG_SECURITY=y
-CONFIG_SECURITY_NETWORK=y
 CONFIG_SECURITY_SELINUX=y
 CONFIG_SECURITY_SELINUX_BOOTPARAM=y
 CONFIG_SECURITY_LOCKDOWN_LSM=y
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index b831083b4edd..47028450eee1 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -9,8 +9,7 @@ CONFIG_BPF_SYSCALL=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_CRASH_DUMP=y
-CONFIG_MARCH_ZEC12=y
-CONFIG_TUNE_ZEC12=y
+CONFIG_MARCH_Z13=y
 # CONFIG_COMPAT is not set
 CONFIG_NR_CPUS=2
 CONFIG_HZ_100=y
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index c773820e4af9..c6fe5405de4a 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -597,7 +597,9 @@ static int ctr_aes_crypt(struct skcipher_request *req)
 	 * final block may be < AES_BLOCK_SIZE, copy only nbytes
 	 */
 	if (nbytes) {
-		cpacf_kmctr(sctx->fc, sctx->key, buf, walk.src.virt.addr,
+		memset(buf, 0, AES_BLOCK_SIZE);
+		memcpy(buf, walk.src.virt.addr, nbytes);
+		cpacf_kmctr(sctx->fc, sctx->key, buf, buf,
 			    AES_BLOCK_SIZE, walk.iv);
 		memcpy(walk.dst.virt.addr, buf, nbytes);
 		crypto_inc(walk.iv, AES_BLOCK_SIZE);
diff --git a/arch/s390/crypto/chacha-glue.c b/arch/s390/crypto/chacha-glue.c
index 5fae187f947a..ed9959e6f714 100644
--- a/arch/s390/crypto/chacha-glue.c
+++ b/arch/s390/crypto/chacha-glue.c
@@ -82,7 +82,7 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src,
 	 * it cannot handle a block of data or less, but otherwise
 	 * it can handle data of arbitrary size
 	 */
-	if (bytes <= CHACHA_BLOCK_SIZE || nrounds != 20 || !MACHINE_HAS_VX)
+	if (bytes <= CHACHA_BLOCK_SIZE || nrounds != 20 || !cpu_has_vx())
 		chacha_crypt_generic(state, dst, src, bytes, nrounds);
 	else
 		chacha20_crypt_s390(state, dst, src, bytes,
diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c
index 8b541e44151d..55ee5567a5ea 100644
--- a/arch/s390/crypto/paes_s390.c
+++ b/arch/s390/crypto/paes_s390.c
@@ -693,9 +693,11 @@ static int ctr_paes_crypt(struct skcipher_request *req)
 	 * final block may be < AES_BLOCK_SIZE, copy only nbytes
 	 */
 	if (nbytes) {
+		memset(buf, 0, AES_BLOCK_SIZE);
+		memcpy(buf, walk.src.virt.addr, nbytes);
 		while (1) {
 			if (cpacf_kmctr(ctx->fc, &param, buf,
-					walk.src.virt.addr, AES_BLOCK_SIZE,
+					buf, AES_BLOCK_SIZE,
 					walk.iv) == AES_BLOCK_SIZE)
 				break;
 			if (__paes_convert_key(ctx))
diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h
index 40c2b82f083a..43ac4a64f49b 100644
--- a/arch/s390/include/asm/ap.h
+++ b/arch/s390/include/asm/ap.h
@@ -88,7 +88,7 @@ static inline bool ap_instructions_available(void)
 }
 
 /* TAPQ register GR2 response struct */
-struct ap_tapq_gr2 {
+struct ap_tapq_hwinfo {
 	union {
 		unsigned long value;
 		struct {
@@ -96,11 +96,13 @@ struct ap_tapq_gr2 {
 			unsigned int apinfo : 32; /* ap type, ... */
 		};
 		struct {
-			unsigned int s	   :  1; /* APSC */
-			unsigned int m	   :  1; /* AP4KM */
-			unsigned int c	   :  1; /* AP4KC */
-			unsigned int mode  :  3;
-			unsigned int n	   :  1; /* APXA */
+			unsigned int apsc  :  1; /* APSC */
+			unsigned int mex4k :  1; /* AP4KM */
+			unsigned int crt4k :  1; /* AP4KC */
+			unsigned int cca   :  1; /* D */
+			unsigned int accel :  1; /* A */
+			unsigned int ep11  :  1; /* X */
+			unsigned int apxa  :  1; /* APXA */
 			unsigned int	   :  1;
 			unsigned int class :  8;
 			unsigned int bs	   :  2; /* SE bind/assoc */
@@ -126,11 +128,12 @@ struct ap_tapq_gr2 {
 /**
  * ap_tapq(): Test adjunct processor queue.
  * @qid: The AP queue number
- * @info: Pointer to queue descriptor
+ * @info: Pointer to tapq hwinfo struct
  *
  * Returns AP queue status structure.
  */
-static inline struct ap_queue_status ap_tapq(ap_qid_t qid, struct ap_tapq_gr2 *info)
+static inline struct ap_queue_status ap_tapq(ap_qid_t qid,
+					     struct ap_tapq_hwinfo *info)
 {
 	union ap_queue_status_reg reg1;
 	unsigned long reg2;
@@ -158,7 +161,7 @@ static inline struct ap_queue_status ap_tapq(ap_qid_t qid, struct ap_tapq_gr2 *i
  * Returns AP queue status structure.
  */
 static inline struct ap_queue_status ap_test_queue(ap_qid_t qid, int tbit,
-						   struct ap_tapq_gr2 *info)
+						   struct ap_tapq_hwinfo *info)
 {
 	if (tbit)
 		qid |= 1UL << 23; /* set T bit*/
diff --git a/arch/s390/include/asm/ctlreg.h b/arch/s390/include/asm/ctlreg.h
index 6d4b85f2b541..72a9556d04f3 100644
--- a/arch/s390/include/asm/ctlreg.h
+++ b/arch/s390/include/asm/ctlreg.h
@@ -141,22 +141,26 @@ static __always_inline void local_ctl_store(unsigned int cr, struct ctlreg *reg)
 		: [cr] "i" (cr));
 }
 
-static __always_inline void local_ctl_set_bit(unsigned int cr, unsigned int bit)
+static __always_inline struct ctlreg local_ctl_set_bit(unsigned int cr, unsigned int bit)
 {
-	struct ctlreg reg;
+	struct ctlreg new, old;
 
-	local_ctl_store(cr, &reg);
-	reg.val |= 1UL << bit;
-	local_ctl_load(cr, &reg);
+	local_ctl_store(cr, &old);
+	new = old;
+	new.val |= 1UL << bit;
+	local_ctl_load(cr, &new);
+	return old;
 }
 
-static __always_inline void local_ctl_clear_bit(unsigned int cr, unsigned int bit)
+static __always_inline struct ctlreg local_ctl_clear_bit(unsigned int cr, unsigned int bit)
 {
-	struct ctlreg reg;
+	struct ctlreg new, old;
 
-	local_ctl_store(cr, &reg);
-	reg.val &= ~(1UL << bit);
-	local_ctl_load(cr, &reg);
+	local_ctl_store(cr, &old);
+	new = old;
+	new.val &= ~(1UL << bit);
+	local_ctl_load(cr, &new);
+	return old;
 }
 
 struct lowcore;
diff --git a/arch/s390/include/asm/fpu/api.h b/arch/s390/include/asm/fpu/api.h
index b714ed0ef688..d6ca8bc6ca68 100644
--- a/arch/s390/include/asm/fpu/api.h
+++ b/arch/s390/include/asm/fpu/api.h
@@ -46,26 +46,33 @@
 
 #include <linux/preempt.h>
 #include <asm/asm-extable.h>
+#include <asm/fpu/internal.h>
 
 void save_fpu_regs(void);
 void load_fpu_regs(void);
 void __load_fpu_regs(void);
 
-static inline int test_fp_ctl(u32 fpc)
+/**
+ * sfpc_safe - Set floating point control register safely.
+ * @fpc: new value for floating point control register
+ *
+ * Set floating point control register. This may lead to an exception,
+ * since a saved value may have been modified by user space (ptrace,
+ * signal return, kvm registers) to an invalid value. In such a case
+ * set the floating point control register to zero.
+ */
+static inline void sfpc_safe(u32 fpc)
 {
-	u32 orig_fpc;
-	int rc;
-
-	asm volatile(
-		"	efpc    %1\n"
-		"	sfpc	%2\n"
-		"0:	sfpc	%1\n"
-		"	la	%0,0\n"
-		"1:\n"
-		EX_TABLE(0b,1b)
-		: "=d" (rc), "=&d" (orig_fpc)
-		: "d" (fpc), "0" (-EINVAL));
-	return rc;
+	asm volatile("\n"
+		"0:	sfpc	%[fpc]\n"
+		"1:	nopr	%%r7\n"
+		".pushsection .fixup, \"ax\"\n"
+		"2:	lghi	%[fpc],0\n"
+		"	jg	0b\n"
+		".popsection\n"
+		EX_TABLE(1b, 2b)
+		: [fpc] "+d" (fpc)
+		: : "memory");
 }
 
 #define KERNEL_FPC		1
@@ -79,7 +86,7 @@ static inline int test_fp_ctl(u32 fpc)
 #define KERNEL_VXR_HIGH		(KERNEL_VXR_V16V23|KERNEL_VXR_V24V31)
 
 #define KERNEL_VXR		(KERNEL_VXR_LOW|KERNEL_VXR_HIGH)
-#define KERNEL_FPR		(KERNEL_FPC|KERNEL_VXR_V0V7)
+#define KERNEL_FPR		(KERNEL_FPC|KERNEL_VXR_LOW)
 
 struct kernel_fpu;
 
diff --git a/arch/s390/include/asm/fpu/internal.h b/arch/s390/include/asm/fpu/internal.h
index 8634581b9011..d511c4cf5afb 100644
--- a/arch/s390/include/asm/fpu/internal.h
+++ b/arch/s390/include/asm/fpu/internal.h
@@ -10,8 +10,14 @@
 #define _ASM_S390_FPU_INTERNAL_H
 
 #include <linux/string.h>
+#include <asm/facility.h>
 #include <asm/fpu/types.h>
 
+static inline bool cpu_has_vx(void)
+{
+	return likely(test_facility(129));
+}
+
 static inline void save_vx_regs(__vector128 *vxrs)
 {
 	asm volatile(
@@ -41,7 +47,7 @@ static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu)
 {
 	fpregs->pad = 0;
 	fpregs->fpc = fpu->fpc;
-	if (MACHINE_HAS_VX)
+	if (cpu_has_vx())
 		convert_vx_to_fp((freg_t *)&fpregs->fprs, fpu->vxrs);
 	else
 		memcpy((freg_t *)&fpregs->fprs, fpu->fprs,
@@ -51,7 +57,7 @@ static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu)
 static inline void fpregs_load(_s390_fp_regs *fpregs, struct fpu *fpu)
 {
 	fpu->fpc = fpregs->fpc;
-	if (MACHINE_HAS_VX)
+	if (cpu_has_vx())
 		convert_fp_to_vx(fpu->vxrs, (freg_t *)&fpregs->fprs);
 	else
 		memcpy(fpu->fprs, (freg_t *)&fpregs->fprs,
diff --git a/arch/s390/include/asm/irq_work.h b/arch/s390/include/asm/irq_work.h
index 603783766d0a..f00c9f610d5a 100644
--- a/arch/s390/include/asm/irq_work.h
+++ b/arch/s390/include/asm/irq_work.h
@@ -7,6 +7,4 @@ static inline bool arch_irq_work_has_interrupt(void)
 	return true;
 }
 
-void arch_irq_work_raise(void);
-
 #endif /* _ASM_S390_IRQ_WORK_H */
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 601e87fa8a9a..1299b56e43f6 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -770,6 +770,7 @@ static inline int pud_write(pud_t pud)
 	return (pud_val(pud) & _REGION3_ENTRY_WRITE) != 0;
 }
 
+#define pmd_dirty pmd_dirty
 static inline int pmd_dirty(pmd_t pmd)
 {
 	return (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0;
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index dc17896a001a..c0b6e74d899a 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -184,11 +184,7 @@ struct thread_struct {
 	struct gs_cb *gs_cb;			/* Current guarded storage cb */
 	struct gs_cb *gs_bc_cb;			/* Broadcast guarded storage cb */
 	struct pgm_tdb trap_tdb;		/* Transaction abort diagnose block */
-	/*
-	 * Warning: 'fpu' is dynamically-sized. It *MUST* be at
-	 * the end.
-	 */
-	struct fpu fpu;			/* FP and VX register save area */
+	struct fpu fpu;				/* FP and VX register save area */
 };
 
 /* Flag to disable transactions. */
@@ -228,7 +224,6 @@ typedef struct thread_struct thread_struct;
 	execve_tail();							\
 } while (0)
 
-/* Forward declaration, a strange C thing */
 struct task_struct;
 struct mm_struct;
 struct seq_file;
@@ -332,14 +327,36 @@ static inline unsigned long __extract_psw(void)
 	return (((unsigned long) reg1) << 32) | ((unsigned long) reg2);
 }
 
-static inline void local_mcck_enable(void)
+static inline unsigned long __local_mcck_save(void)
 {
-	__load_psw_mask(__extract_psw() | PSW_MASK_MCHECK);
+	unsigned long mask = __extract_psw();
+
+	__load_psw_mask(mask & ~PSW_MASK_MCHECK);
+	return mask & PSW_MASK_MCHECK;
+}
+
+#define local_mcck_save(mflags)			\
+do {						\
+	typecheck(unsigned long, mflags);	\
+	mflags = __local_mcck_save();		\
+} while (0)
+
+static inline void local_mcck_restore(unsigned long mflags)
+{
+	unsigned long mask = __extract_psw();
+
+	mask &= ~PSW_MASK_MCHECK;
+	__load_psw_mask(mask | mflags);
 }
 
 static inline void local_mcck_disable(void)
 {
-	__load_psw_mask(__extract_psw() & ~PSW_MASK_MCHECK);
+	__local_mcck_save();
+}
+
+static inline void local_mcck_enable(void)
+{
+	__load_psw_mask(__extract_psw() | PSW_MASK_MCHECK);
 }
 
 /*
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index df316436d2e1..03bcaa8effb2 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -28,7 +28,6 @@
 #define MACHINE_FLAG_TOPOLOGY	BIT(10)
 #define MACHINE_FLAG_TE		BIT(11)
 #define MACHINE_FLAG_TLB_LC	BIT(12)
-#define MACHINE_FLAG_VX		BIT(13)
 #define MACHINE_FLAG_TLB_GUEST	BIT(14)
 #define MACHINE_FLAG_NX		BIT(15)
 #define MACHINE_FLAG_GS		BIT(16)
@@ -90,7 +89,6 @@ extern unsigned long mio_wb_bit_mask;
 #define MACHINE_HAS_TOPOLOGY	(S390_lowcore.machine_flags & MACHINE_FLAG_TOPOLOGY)
 #define MACHINE_HAS_TE		(S390_lowcore.machine_flags & MACHINE_FLAG_TE)
 #define MACHINE_HAS_TLB_LC	(S390_lowcore.machine_flags & MACHINE_FLAG_TLB_LC)
-#define MACHINE_HAS_VX		(S390_lowcore.machine_flags & MACHINE_FLAG_VX)
 #define MACHINE_HAS_TLB_GUEST	(S390_lowcore.machine_flags & MACHINE_FLAG_TLB_GUEST)
 #define MACHINE_HAS_NX		(S390_lowcore.machine_flags & MACHINE_FLAG_NX)
 #define MACHINE_HAS_GS		(S390_lowcore.machine_flags & MACHINE_FLAG_GS)
diff --git a/arch/s390/include/asm/syscall_wrapper.h b/arch/s390/include/asm/syscall_wrapper.h
index 9286430fe729..35c1d1b860d8 100644
--- a/arch/s390/include/asm/syscall_wrapper.h
+++ b/arch/s390/include/asm/syscall_wrapper.h
@@ -63,10 +63,6 @@
 	cond_syscall(__s390x_sys_##name);				\
 	cond_syscall(__s390_sys_##name)
 
-#define SYS_NI(name)							\
-	SYSCALL_ALIAS(__s390x_sys_##name, sys_ni_posix_timers);		\
-	SYSCALL_ALIAS(__s390_sys_##name, sys_ni_posix_timers)
-
 #define COMPAT_SYSCALL_DEFINEx(x, name, ...)						\
 	long __s390_compat_sys##name(struct pt_regs *regs);				\
 	ALLOW_ERROR_INJECTION(__s390_compat_sys##name, ERRNO);				\
@@ -85,15 +81,11 @@
 
 /*
  * As some compat syscalls may not be implemented, we need to expand
- * COND_SYSCALL_COMPAT in kernel/sys_ni.c and COMPAT_SYS_NI in
- * kernel/time/posix-stubs.c to cover this case as well.
+ * COND_SYSCALL_COMPAT in kernel/sys_ni.c to cover this case as well.
  */
 #define COND_SYSCALL_COMPAT(name)					\
 	cond_syscall(__s390_compat_sys_##name)
 
-#define COMPAT_SYS_NI(name)						\
-	SYSCALL_ALIAS(__s390_compat_sys_##name, sys_ni_posix_timers)
-
 #define __S390_SYS_STUBx(x, name, ...)						\
 	long __s390_sys##name(struct pt_regs *regs);				\
 	ALLOW_ERROR_INJECTION(__s390_sys##name, ERRNO);				\
@@ -124,9 +116,6 @@
 #define COND_SYSCALL(name)						\
 	cond_syscall(__s390x_sys_##name)
 
-#define SYS_NI(name)							\
-	SYSCALL_ALIAS(__s390x_sys_##name, sys_ni_posix_timers)
-
 #define __S390_SYS_STUBx(x, fullname, name, ...)
 
 #endif /* CONFIG_COMPAT */
diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h
index ab1c6316055c..edca5a751df4 100644
--- a/arch/s390/include/asm/sysinfo.h
+++ b/arch/s390/include/asm/sysinfo.h
@@ -40,6 +40,10 @@ struct sysinfo_1_1_1 {
 	unsigned int ncr;
 	unsigned int npr;
 	unsigned int ntr;
+	char reserved_3[4];
+	char model_var_cap[16];
+	unsigned int model_var_cap_rating;
+	unsigned int nvr;
 };
 
 struct sysinfo_1_2_1 {
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index cecedd01d4ec..f8fc6c25d051 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -29,6 +29,7 @@
 #include <asm/lowcore.h>
 #include <asm/switch_to.h>
 #include <asm/vdso.h>
+#include <asm/fpu/api.h>
 #include "compat_linux.h"
 #include "compat_ptrace.h"
 #include "entry.h"
@@ -98,10 +99,6 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs)
 	if (!is_ri_task(current) && (user_sregs.regs.psw.mask & PSW32_MASK_RI))
 		return -EINVAL;
 
-	/* Test the floating-point-control word. */
-	if (test_fp_ctl(user_sregs.fpregs.fpc))
-		return -EINVAL;
-
 	/* Use regs->psw.mask instead of PSW_USER_BITS to preserve PER bit. */
 	regs->psw.mask = (regs->psw.mask & ~(PSW_MASK_USER | PSW_MASK_RI)) |
 		(__u64)(user_sregs.regs.psw.mask & PSW32_MASK_USER) << 32 |
@@ -137,7 +134,7 @@ static int save_sigregs_ext32(struct pt_regs *regs,
 		return -EFAULT;
 
 	/* Save vector registers to signal stack */
-	if (MACHINE_HAS_VX) {
+	if (cpu_has_vx()) {
 		for (i = 0; i < __NUM_VXRS_LOW; i++)
 			vxrs[i] = current->thread.fpu.vxrs[i].low;
 		if (__copy_to_user(&sregs_ext->vxrs_low, vxrs,
@@ -165,7 +162,7 @@ static int restore_sigregs_ext32(struct pt_regs *regs,
 		*(__u32 *)&regs->gprs[i] = gprs_high[i];
 
 	/* Restore vector registers from signal stack */
-	if (MACHINE_HAS_VX) {
+	if (cpu_has_vx()) {
 		if (__copy_from_user(vxrs, &sregs_ext->vxrs_low,
 				     sizeof(sregs_ext->vxrs_low)) ||
 		    __copy_from_user(current->thread.fpu.vxrs + __NUM_VXRS_LOW,
@@ -265,7 +262,7 @@ static int setup_frame32(struct ksignal *ksig, sigset_t *set,
 	 * the machine supports it
 	 */
 	frame_size = sizeof(*frame) - sizeof(frame->sregs_ext.__reserved);
-	if (!MACHINE_HAS_VX)
+	if (!cpu_has_vx())
 		frame_size -= sizeof(frame->sregs_ext.vxrs_low) +
 			      sizeof(frame->sregs_ext.vxrs_high);
 	frame = get_sigframe(&ksig->ka, regs, frame_size);
@@ -348,11 +345,12 @@ static int setup_rt_frame32(struct ksignal *ksig, sigset_t *set,
 	 * the machine supports it
 	 */
 	uc_flags = UC_GPRS_HIGH;
-	if (MACHINE_HAS_VX) {
+	if (cpu_has_vx()) {
 		uc_flags |= UC_VXRS;
-	} else
+	} else {
 		frame_size -= sizeof(frame->uc.uc_mcontext_ext.vxrs_low) +
 			      sizeof(frame->uc.uc_mcontext_ext.vxrs_high);
+	}
 	frame = get_sigframe(&ksig->ka, regs, frame_size);
 	if (frame == (void __user *) -1UL)
 		return -EFAULT;
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 514feadd4c58..5c46c2659305 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -22,6 +22,7 @@
 #include <asm/ipl.h>
 #include <asm/sclp.h>
 #include <asm/maccess.h>
+#include <asm/fpu/api.h>
 
 #define PTR_ADD(x, y) (((char *) (x)) + ((unsigned long) (y)))
 #define PTR_SUB(x, y) (((char *) (x)) - ((unsigned long) (y)))
@@ -319,7 +320,7 @@ static void *fill_cpu_elf_notes(void *ptr, int cpu, struct save_area *sa)
 	ptr = nt_init(ptr, NT_S390_TODPREG, &sa->todpreg, sizeof(sa->todpreg));
 	ptr = nt_init(ptr, NT_S390_CTRS, &sa->ctrs, sizeof(sa->ctrs));
 	ptr = nt_init(ptr, NT_S390_PREFIX, &sa->prefix, sizeof(sa->prefix));
-	if (MACHINE_HAS_VX) {
+	if (cpu_has_vx()) {
 		ptr = nt_init(ptr, NT_S390_VXRS_HIGH,
 			      &sa->vxrs_high, sizeof(sa->vxrs_high));
 		ptr = nt_init(ptr, NT_S390_VXRS_LOW,
@@ -343,7 +344,7 @@ static size_t get_cpu_elf_notes_size(void)
 	size +=  nt_size(NT_S390_TODPREG, sizeof(sa->todpreg));
 	size +=  nt_size(NT_S390_CTRS, sizeof(sa->ctrs));
 	size +=  nt_size(NT_S390_PREFIX, sizeof(sa->prefix));
-	if (MACHINE_HAS_VX) {
+	if (cpu_has_vx()) {
 		size += nt_size(NT_S390_VXRS_HIGH, sizeof(sa->vxrs_high));
 		size += nt_size(NT_S390_VXRS_LOW, sizeof(sa->vxrs_low));
 	}
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index eb43e5922a25..2345ea332b97 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -229,10 +229,8 @@ static __init void detect_machine_facilities(void)
 	}
 	if (test_facility(51))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_TLB_LC;
-	if (test_facility(129)) {
-		S390_lowcore.machine_flags |= MACHINE_FLAG_VX;
+	if (test_facility(129))
 		system_ctl_set_bit(0, CR0_VECTOR_BIT);
-	}
 	if (test_facility(130))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_NX;
 	if (test_facility(133))
@@ -271,14 +269,6 @@ static inline void setup_access_registers(void)
 	restore_access_regs(acrs);
 }
 
-static int __init disable_vector_extension(char *str)
-{
-	S390_lowcore.machine_flags &= ~MACHINE_FLAG_VX;
-	system_ctl_clear_bit(0, CR0_VECTOR_BIT);
-	return 0;
-}
-early_param("novx", disable_vector_extension);
-
 char __bootdata(early_command_line)[COMMAND_LINE_SIZE];
 static void __init setup_boot_command_line(void)
 {
diff --git a/arch/s390/kernel/fpu.c b/arch/s390/kernel/fpu.c
index 4666b29ac8a1..9e7c15fccfea 100644
--- a/arch/s390/kernel/fpu.c
+++ b/arch/s390/kernel/fpu.c
@@ -24,7 +24,7 @@ void __kernel_fpu_begin(struct kernel_fpu *state, u32 flags)
 		/* Save floating point control */
 		asm volatile("stfpc %0" : "=Q" (state->fpc));
 
-	if (!MACHINE_HAS_VX) {
+	if (!cpu_has_vx()) {
 		if (flags & KERNEL_VXR_V0V7) {
 			/* Save floating-point registers */
 			asm volatile("std 0,%0" : "=Q" (state->fprs[0]));
@@ -106,7 +106,7 @@ void __kernel_fpu_end(struct kernel_fpu *state, u32 flags)
 		/* Restore floating-point controls */
 		asm volatile("lfpc %0" : : "Q" (state->fpc));
 
-	if (!MACHINE_HAS_VX) {
+	if (!cpu_has_vx()) {
 		if (flags & KERNEL_VXR_V0V7) {
 			/* Restore floating-point registers */
 			asm volatile("ld 0,%0" : : "Q" (state->fprs[0]));
@@ -177,11 +177,11 @@ EXPORT_SYMBOL(__kernel_fpu_end);
 
 void __load_fpu_regs(void)
 {
-	struct fpu *state = &current->thread.fpu;
 	unsigned long *regs = current->thread.fpu.regs;
+	struct fpu *state = &current->thread.fpu;
 
-	asm volatile("lfpc %0" : : "Q" (state->fpc));
-	if (likely(MACHINE_HAS_VX)) {
+	sfpc_safe(state->fpc);
+	if (likely(cpu_has_vx())) {
 		asm volatile("lgr	1,%0\n"
 			     "VLM	0,15,0,1\n"
 			     "VLM	16,31,256,1\n"
@@ -232,7 +232,7 @@ void save_fpu_regs(void)
 	regs = current->thread.fpu.regs;
 
 	asm volatile("stfpc %0" : "=Q" (state->fpc));
-	if (likely(MACHINE_HAS_VX)) {
+	if (likely(cpu_has_vx())) {
 		asm volatile("lgr	1,%0\n"
 			     "VSTM	0,15,0,1\n"
 			     "VSTM	16,31,256,1\n"
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index cc364fce6aa9..ba75f6bee774 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -666,6 +666,7 @@ static int __init ipl_init(void)
 						&ipl_ccw_attr_group_lpar);
 		break;
 	case IPL_TYPE_ECKD:
+	case IPL_TYPE_ECKD_DUMP:
 		rc = sysfs_create_group(&ipl_kset->kobj, &ipl_eckd_attr_group);
 		break;
 	case IPL_TYPE_FCP:
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index bb0d4d68fcbe..aa22ffc16bcd 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -91,7 +91,7 @@ static noinline void __machine_kdump(void *image)
 	}
 	/* Store status of the boot CPU */
 	mcesa = __va(S390_lowcore.mcesad & MCESA_ORIGIN_MASK);
-	if (MACHINE_HAS_VX)
+	if (cpu_has_vx())
 		save_vx_regs((__vector128 *) mcesa->vector_save_area);
 	if (MACHINE_HAS_GS) {
 		local_ctl_store(2, &cr2_old.reg);
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 0daf0f1cdfc9..9ad44c26d1a2 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -32,6 +32,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/pai.h>
 #include <asm/vx-insn.h>
+#include <asm/fpu/api.h>
 
 struct mcck_struct {
 	unsigned int kill_task : 1;
@@ -45,7 +46,7 @@ static DEFINE_PER_CPU(struct mcck_struct, cpu_mcck);
 
 static inline int nmi_needs_mcesa(void)
 {
-	return MACHINE_HAS_VX || MACHINE_HAS_GS;
+	return cpu_has_vx() || MACHINE_HAS_GS;
 }
 
 /*
@@ -159,16 +160,17 @@ NOKPROBE_SYMBOL(s390_handle_damage);
 void s390_handle_mcck(void)
 {
 	struct mcck_struct mcck;
+	unsigned long mflags;
 
 	/*
 	 * Disable machine checks and get the current state of accumulated
 	 * machine checks. Afterwards delete the old state and enable machine
 	 * checks again.
 	 */
-	local_mcck_disable();
+	local_mcck_save(mflags);
 	mcck = *this_cpu_ptr(&cpu_mcck);
 	memset(this_cpu_ptr(&cpu_mcck), 0, sizeof(mcck));
-	local_mcck_enable();
+	local_mcck_restore(mflags);
 
 	if (mcck.channel_report)
 		crw_handle_channel_report();
@@ -234,7 +236,7 @@ static int notrace s390_validate_registers(union mci mci)
 	}
 
 	mcesa = __va(S390_lowcore.mcesad & MCESA_ORIGIN_MASK);
-	if (!MACHINE_HAS_VX) {
+	if (!cpu_has_vx()) {
 		/* Validate floating point registers */
 		asm volatile(
 			"	ld	0,0(%0)\n"
diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c
index 77fd24e6cbb6..39a91b00438a 100644
--- a/arch/s390/kernel/perf_pai_crypto.c
+++ b/arch/s390/kernel/perf_pai_crypto.c
@@ -279,12 +279,6 @@ static int paicrypt_event_init(struct perf_event *event)
 	if (IS_ERR(cpump))
 		return PTR_ERR(cpump);
 
-	/* Event initialization sets last_tag to 0. When later on the events
-	 * are deleted and re-added, do not reset the event count value to zero.
-	 * Events are added, deleted and re-added when 2 or more events
-	 * are active at the same time.
-	 */
-	event->hw.last_tag = 0;
 	event->destroy = paicrypt_event_destroy;
 
 	if (a->sample_period) {
@@ -318,6 +312,11 @@ static void paicrypt_start(struct perf_event *event, int flags)
 {
 	u64 sum;
 
+	/* Event initialization sets last_tag to 0. When later on the events
+	 * are deleted and re-added, do not reset the event count value to zero.
+	 * Events are added, deleted and re-added when 2 or more events
+	 * are active at the same time.
+	 */
 	if (!event->hw.last_tag) {
 		event->hw.last_tag = 1;
 		sum = paicrypt_getall(event);		/* Get current value */
diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c
index 8ba0f1a3a39d..e7013a2e8960 100644
--- a/arch/s390/kernel/perf_pai_ext.c
+++ b/arch/s390/kernel/perf_pai_ext.c
@@ -260,7 +260,6 @@ static int paiext_event_init(struct perf_event *event)
 	rc = paiext_alloc(a, event);
 	if (rc)
 		return rc;
-	event->hw.last_tag = 0;
 	event->destroy = paiext_event_destroy;
 
 	if (a->sample_period) {
diff --git a/arch/s390/kernel/perf_regs.c b/arch/s390/kernel/perf_regs.c
index 6e9e5d5e927e..3d93656bd948 100644
--- a/arch/s390/kernel/perf_regs.c
+++ b/arch/s390/kernel/perf_regs.c
@@ -20,8 +20,10 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 			return 0;
 
 		idx -= PERF_REG_S390_FP0;
-		fp = MACHINE_HAS_VX ? *(freg_t *)(current->thread.fpu.vxrs + idx)
-				    : current->thread.fpu.fprs[idx];
+		if (cpu_has_vx())
+			fp = *(freg_t *)(current->thread.fpu.vxrs + idx);
+		else
+			fp = current->thread.fpu.fprs[idx];
 		return fp.ui;
 	}
 
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 258000417724..4e3b366589fb 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -89,7 +89,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	 */
 	save_fpu_regs();
 
-	memcpy(dst, src, arch_task_struct_size);
+	*dst = *src;
 	dst->thread.fpu.regs = dst->thread.fpu.fprs;
 
 	/*
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 0a999c8226d7..65c1464eea4f 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -201,11 +201,8 @@ static int __init setup_hwcaps(void)
 	if (MACHINE_HAS_TE)
 		elf_hwcap |= HWCAP_TE;
 
-	/*
-	 * Vector extension can be disabled with the "novx" parameter.
-	 * Use MACHINE_HAS_VX instead of facility bit 129.
-	 */
-	if (MACHINE_HAS_VX) {
+	/* vector */
+	if (test_facility(129)) {
 		elf_hwcap |= HWCAP_VXRS;
 		if (test_facility(134))
 			elf_hwcap |= HWCAP_VXRS_BCD;
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 046403471c5d..2e6754b62b20 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -30,6 +30,7 @@
 #include <asm/switch_to.h>
 #include <asm/runtime_instr.h>
 #include <asm/facility.h>
+#include <asm/fpu/api.h>
 
 #include "entry.h"
 
@@ -254,7 +255,7 @@ static unsigned long __peek_user(struct task_struct *child, addr_t addr)
 		 * or the child->thread.fpu.vxrs array
 		 */
 		offset = addr - offsetof(struct user, regs.fp_regs.fprs);
-		if (MACHINE_HAS_VX)
+		if (cpu_has_vx())
 			tmp = *(addr_t *)
 			       ((addr_t) child->thread.fpu.vxrs + 2*offset);
 		else
@@ -392,8 +393,7 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
 		/*
 		 * floating point control reg. is in the thread structure
 		 */
-		if ((unsigned int) data != 0 ||
-		    test_fp_ctl(data >> (BITS_PER_LONG - 32)))
+		if ((unsigned int)data != 0)
 			return -EINVAL;
 		child->thread.fpu.fpc = data >> (BITS_PER_LONG - 32);
 
@@ -403,7 +403,7 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
 		 * or the child->thread.fpu.vxrs array
 		 */
 		offset = addr - offsetof(struct user, regs.fp_regs.fprs);
-		if (MACHINE_HAS_VX)
+		if (cpu_has_vx())
 			*(addr_t *)((addr_t)
 				child->thread.fpu.vxrs + 2*offset) = data;
 		else
@@ -630,7 +630,7 @@ static u32 __peek_user_compat(struct task_struct *child, addr_t addr)
 		 * or the child->thread.fpu.vxrs array
 		 */
 		offset = addr - offsetof(struct compat_user, regs.fp_regs.fprs);
-		if (MACHINE_HAS_VX)
+		if (cpu_has_vx())
 			tmp = *(__u32 *)
 			       ((addr_t) child->thread.fpu.vxrs + 2*offset);
 		else
@@ -748,8 +748,6 @@ static int __poke_user_compat(struct task_struct *child,
 		/*
 		 * floating point control reg. is in the thread structure
 		 */
-		if (test_fp_ctl(tmp))
-			return -EINVAL;
 		child->thread.fpu.fpc = data;
 
 	} else if (addr < offsetof(struct compat_user, regs.fp_regs) + sizeof(s390_fp_regs)) {
@@ -758,7 +756,7 @@ static int __poke_user_compat(struct task_struct *child,
 		 * or the child->thread.fpu.vxrs array
 		 */
 		offset = addr - offsetof(struct compat_user, regs.fp_regs.fprs);
-		if (MACHINE_HAS_VX)
+		if (cpu_has_vx())
 			*(__u32 *)((addr_t)
 				child->thread.fpu.vxrs + 2*offset) = tmp;
 		else
@@ -914,7 +912,7 @@ static int s390_fpregs_set(struct task_struct *target,
 	if (target == current)
 		save_fpu_regs();
 
-	if (MACHINE_HAS_VX)
+	if (cpu_has_vx())
 		convert_vx_to_fp(fprs, target->thread.fpu.vxrs);
 	else
 		memcpy(&fprs, target->thread.fpu.fprs, sizeof(fprs));
@@ -926,7 +924,7 @@ static int s390_fpregs_set(struct task_struct *target,
 					0, offsetof(s390_fp_regs, fprs));
 		if (rc)
 			return rc;
-		if (ufpc[1] != 0 || test_fp_ctl(ufpc[0]))
+		if (ufpc[1] != 0)
 			return -EINVAL;
 		target->thread.fpu.fpc = ufpc[0];
 	}
@@ -937,7 +935,7 @@ static int s390_fpregs_set(struct task_struct *target,
 	if (rc)
 		return rc;
 
-	if (MACHINE_HAS_VX)
+	if (cpu_has_vx())
 		convert_fp_to_vx(target->thread.fpu.vxrs, fprs);
 	else
 		memcpy(target->thread.fpu.fprs, &fprs, sizeof(fprs));
@@ -988,7 +986,7 @@ static int s390_vxrs_low_get(struct task_struct *target,
 	__u64 vxrs[__NUM_VXRS_LOW];
 	int i;
 
-	if (!MACHINE_HAS_VX)
+	if (!cpu_has_vx())
 		return -ENODEV;
 	if (target == current)
 		save_fpu_regs();
@@ -1005,7 +1003,7 @@ static int s390_vxrs_low_set(struct task_struct *target,
 	__u64 vxrs[__NUM_VXRS_LOW];
 	int i, rc;
 
-	if (!MACHINE_HAS_VX)
+	if (!cpu_has_vx())
 		return -ENODEV;
 	if (target == current)
 		save_fpu_regs();
@@ -1025,7 +1023,7 @@ static int s390_vxrs_high_get(struct task_struct *target,
 			      const struct user_regset *regset,
 			      struct membuf to)
 {
-	if (!MACHINE_HAS_VX)
+	if (!cpu_has_vx())
 		return -ENODEV;
 	if (target == current)
 		save_fpu_regs();
@@ -1040,7 +1038,7 @@ static int s390_vxrs_high_set(struct task_struct *target,
 {
 	int rc;
 
-	if (!MACHINE_HAS_VX)
+	if (!cpu_has_vx())
 		return -ENODEV;
 	if (target == current)
 		save_fpu_regs();
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 5701356f4f33..d1f3b56e7afc 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -408,15 +408,15 @@ static void __init setup_lowcore(void)
 
 	lc->restart_psw.mask = PSW_KERNEL_BITS & ~PSW_MASK_DAT;
 	lc->restart_psw.addr = __pa(restart_int_handler);
-	lc->external_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK;
+	lc->external_new_psw.mask = PSW_KERNEL_BITS;
 	lc->external_new_psw.addr = (unsigned long) ext_int_handler;
-	lc->svc_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK;
+	lc->svc_new_psw.mask = PSW_KERNEL_BITS;
 	lc->svc_new_psw.addr = (unsigned long) system_call;
-	lc->program_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK;
+	lc->program_new_psw.mask = PSW_KERNEL_BITS;
 	lc->program_new_psw.addr = (unsigned long) pgm_check_handler;
 	lc->mcck_new_psw.mask = PSW_KERNEL_BITS;
 	lc->mcck_new_psw.addr = (unsigned long) mcck_int_handler;
-	lc->io_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK;
+	lc->io_new_psw.mask = PSW_KERNEL_BITS;
 	lc->io_new_psw.addr = (unsigned long) io_int_handler;
 	lc->clock_comparator = clock_comparator_max;
 	lc->current_task = (unsigned long)&init_task;
@@ -820,22 +820,6 @@ static void __init setup_randomness(void)
 }
 
 /*
- * Find the correct size for the task_struct. This depends on
- * the size of the struct fpu at the end of the thread_struct
- * which is embedded in the task_struct.
- */
-static void __init setup_task_size(void)
-{
-	int task_size = sizeof(struct task_struct);
-
-	if (!MACHINE_HAS_VX) {
-		task_size -= sizeof(__vector128) * __NUM_VXRS;
-		task_size += sizeof(freg_t) * __NUM_FPRS;
-	}
-	arch_task_struct_size = task_size;
-}
-
-/*
  * Issue diagnose 318 to set the control program name and
  * version codes.
  */
@@ -927,7 +911,6 @@ void __init setup_arch(char **cmdline_p)
 
 	os_info_init();
 	setup_ipl();
-	setup_task_size();
 	setup_control_program_code();
 
 	/* Do some memory reservations *before* memory is added to memblock */
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index d63557d3868c..43e9661cd715 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -12,6 +12,7 @@
 
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
+#include <linux/rseq.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/kernel.h>
@@ -149,10 +150,6 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 	if (!is_ri_task(current) && (user_sregs.regs.psw.mask & PSW_MASK_RI))
 		return -EINVAL;
 
-	/* Test the floating-point-control word. */
-	if (test_fp_ctl(user_sregs.fpregs.fpc))
-		return -EINVAL;
-
 	/* Use regs->psw.mask instead of PSW_USER_BITS to preserve PER bit. */
 	regs->psw.mask = (regs->psw.mask & ~(PSW_MASK_USER | PSW_MASK_RI)) |
 		(user_sregs.regs.psw.mask & (PSW_MASK_USER | PSW_MASK_RI));
@@ -182,7 +179,7 @@ static int save_sigregs_ext(struct pt_regs *regs,
 	int i;
 
 	/* Save vector registers to signal stack */
-	if (MACHINE_HAS_VX) {
+	if (cpu_has_vx()) {
 		for (i = 0; i < __NUM_VXRS_LOW; i++)
 			vxrs[i] = current->thread.fpu.vxrs[i].low;
 		if (__copy_to_user(&sregs_ext->vxrs_low, vxrs,
@@ -202,7 +199,7 @@ static int restore_sigregs_ext(struct pt_regs *regs,
 	int i;
 
 	/* Restore vector registers from signal stack */
-	if (MACHINE_HAS_VX) {
+	if (cpu_has_vx()) {
 		if (__copy_from_user(vxrs, &sregs_ext->vxrs_low,
 				     sizeof(sregs_ext->vxrs_low)) ||
 		    __copy_from_user(current->thread.fpu.vxrs + __NUM_VXRS_LOW,
@@ -300,7 +297,7 @@ static int setup_frame(int sig, struct k_sigaction *ka,
 	 * included in the signal frame on a 31-bit system.
 	 */
 	frame_size = sizeof(*frame) - sizeof(frame->sregs_ext);
-	if (MACHINE_HAS_VX)
+	if (cpu_has_vx())
 		frame_size += sizeof(frame->sregs_ext);
 	frame = get_sigframe(ka, regs, frame_size);
 	if (frame == (void __user *) -1UL)
@@ -377,7 +374,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 	 * included in the signal frame on a 31-bit system.
 	 */
 	uc_flags = 0;
-	if (MACHINE_HAS_VX) {
+	if (cpu_has_vx()) {
 		frame_size += sizeof(_sigregs_ext);
 		uc_flags |= UC_VXRS;
 	}
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index f7fcfff09acf..c39d9f0d4b1c 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -582,7 +582,7 @@ int smp_store_status(int cpu)
 	if (__pcpu_sigp_relax(pcpu->address, SIGP_STORE_STATUS_AT_ADDRESS,
 			      pa) != SIGP_CC_ORDER_CODE_ACCEPTED)
 		return -EIO;
-	if (!MACHINE_HAS_VX && !MACHINE_HAS_GS)
+	if (!cpu_has_vx() && !MACHINE_HAS_GS)
 		return 0;
 	pa = lc->mcesad & MCESA_ORIGIN_MASK;
 	if (MACHINE_HAS_GS)
@@ -638,7 +638,7 @@ void __init smp_save_dump_ipl_cpu(void)
 	copy_oldmem_kernel(regs, __LC_FPREGS_SAVE_AREA, 512);
 	save_area_add_regs(sa, regs);
 	memblock_free(regs, 512);
-	if (MACHINE_HAS_VX)
+	if (cpu_has_vx())
 		save_area_add_vxrs(sa, boot_cpu_vector_save_area);
 }
 
@@ -671,7 +671,7 @@ void __init smp_save_dump_secondary_cpus(void)
 			panic("could not allocate memory for save area\n");
 		__pcpu_sigp_relax(addr, SIGP_STORE_STATUS_AT_ADDRESS, __pa(page));
 		save_area_add_regs(sa, page);
-		if (MACHINE_HAS_VX) {
+		if (cpu_has_vx()) {
 			__pcpu_sigp_relax(addr, SIGP_STORE_ADDITIONAL_STATUS, __pa(page));
 			save_area_add_vxrs(sa, page);
 		}
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 86fec9b080f6..095bb86339a7 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -459,3 +459,8 @@
 454  common	futex_wake		sys_futex_wake			sys_futex_wake
 455  common	futex_wait		sys_futex_wait			sys_futex_wait
 456  common	futex_requeue		sys_futex_requeue		sys_futex_requeue
+457  common	statmount		sys_statmount			sys_statmount
+458  common	listmount		sys_listmount			sys_listmount
+459  common	lsm_get_self_attr	sys_lsm_get_self_attr		sys_lsm_get_self_attr
+460  common	lsm_set_self_attr	sys_lsm_set_self_attr		sys_lsm_set_self_attr
+461  common	lsm_list_modules	sys_lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
index b5e364358ce4..f6f8f498c9be 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -81,10 +81,12 @@ static bool convert_ext_name(unsigned char encoding, char *name, size_t len)
 
 static void stsi_1_1_1(struct seq_file *m, struct sysinfo_1_1_1 *info)
 {
+	bool has_var_cap;
 	int i;
 
 	if (stsi(info, 1, 1, 1))
 		return;
+	has_var_cap = !!info->model_var_cap[0];
 	EBCASC(info->manufacturer, sizeof(info->manufacturer));
 	EBCASC(info->type, sizeof(info->type));
 	EBCASC(info->model, sizeof(info->model));
@@ -93,6 +95,8 @@ static void stsi_1_1_1(struct seq_file *m, struct sysinfo_1_1_1 *info)
 	EBCASC(info->model_capacity, sizeof(info->model_capacity));
 	EBCASC(info->model_perm_cap, sizeof(info->model_perm_cap));
 	EBCASC(info->model_temp_cap, sizeof(info->model_temp_cap));
+	if (has_var_cap)
+		EBCASC(info->model_var_cap, sizeof(info->model_var_cap));
 	seq_printf(m, "Manufacturer:         %-16.16s\n", info->manufacturer);
 	seq_printf(m, "Type:                 %-4.4s\n", info->type);
 	if (info->lic)
@@ -120,12 +124,18 @@ static void stsi_1_1_1(struct seq_file *m, struct sysinfo_1_1_1 *info)
 		seq_printf(m, "Model Temp. Capacity: %-16.16s %08u\n",
 			   info->model_temp_cap,
 			   info->model_temp_cap_rating);
+	if (has_var_cap && info->model_var_cap_rating)
+		seq_printf(m, "Model Var. Capacity:  %-16.16s %08u\n",
+			   info->model_var_cap,
+			   info->model_var_cap_rating);
 	if (info->ncr)
 		seq_printf(m, "Nominal Cap. Rating:  %08u\n", info->ncr);
 	if (info->npr)
 		seq_printf(m, "Nominal Perm. Rating: %08u\n", info->npr);
 	if (info->ntr)
 		seq_printf(m, "Nominal Temp. Rating: %08u\n", info->ntr);
+	if (has_var_cap && info->nvr)
+		seq_printf(m, "Nominal Var. Rating:  %08u\n", info->nvr);
 	if (info->cai) {
 		seq_printf(m, "Capacity Adj. Ind.:   %d\n", info->cai);
 		seq_printf(m, "Capacity Ch. Reason:  %d\n", info->ccr);
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 1d2aa448d103..46dac4540ca8 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -43,10 +43,12 @@ static inline void __user *get_trap_ip(struct pt_regs *regs)
 	return (void __user *) (address - (regs->int_code >> 16));
 }
 
+#ifdef CONFIG_GENERIC_BUG
 int is_valid_bugaddr(unsigned long addr)
 {
 	return 1;
 }
+#endif
 
 void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str)
 {
@@ -193,7 +195,7 @@ static void vector_exception(struct pt_regs *regs)
 {
 	int si_code, vic;
 
-	if (!MACHINE_HAS_VX) {
+	if (!cpu_has_vx()) {
 		do_trap(regs, SIGILL, ILL_ILLOPN, "illegal operation");
 		return;
 	}
@@ -286,6 +288,17 @@ static void __init test_monitor_call(void)
 
 void __init trap_init(void)
 {
+	unsigned long flags;
+	struct ctlreg cr0;
+
+	local_irq_save(flags);
+	cr0 = local_ctl_clear_bit(0, CR0_LOW_ADDRESS_PROTECTION_BIT);
+	psw_bits(S390_lowcore.external_new_psw).mcheck = 1;
+	psw_bits(S390_lowcore.program_new_psw).mcheck = 1;
+	psw_bits(S390_lowcore.svc_new_psw).mcheck = 1;
+	psw_bits(S390_lowcore.io_new_psw).mcheck = 1;
+	local_ctl_load(0, &cr0);
+	local_irq_restore(flags);
 	local_mcck_enable();
 	test_monitor_call();
 }
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 2ae201ebf90b..e32ef446f451 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -52,6 +52,7 @@ SECTIONS
 		SOFTIRQENTRY_TEXT
 		FTRACE_HOTPATCH_TRAMPOLINES_TEXT
 		*(.text.*_indirect_*)
+		*(.fixup)
 		*(.gnu.warning)
 		. = ALIGN(PAGE_SIZE);
 		_etext = .;		/* End of text section */
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index efaebba5ee19..fc4007cc067a 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -639,7 +639,7 @@ static int __write_machine_check(struct kvm_vcpu *vcpu,
 	rc |= put_guest_lc(vcpu, mci.val, (u64 __user *) __LC_MCCK_CODE);
 
 	/* Register-save areas */
-	if (MACHINE_HAS_VX) {
+	if (cpu_has_vx()) {
 		convert_vx_to_fp(fprs, (__vector128 *) vcpu->run->s.regs.vrs);
 		rc |= write_guest_lc(vcpu, __LC_FPREGS_SAVE_AREA, fprs, 128);
 	} else {
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 7aa0e668488f..acc81ca6492e 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -618,7 +618,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = MACHINE_HAS_ESOP;
 		break;
 	case KVM_CAP_S390_VECTOR_REGISTERS:
-		r = MACHINE_HAS_VX;
+		r = test_facility(129);
 		break;
 	case KVM_CAP_S390_RI:
 		r = test_facility(64);
@@ -767,7 +767,7 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		mutex_lock(&kvm->lock);
 		if (kvm->created_vcpus) {
 			r = -EBUSY;
-		} else if (MACHINE_HAS_VX) {
+		} else if (cpu_has_vx()) {
 			set_kvm_facility(kvm->arch.model.fac_mask, 129);
 			set_kvm_facility(kvm->arch.model.fac_list, 129);
 			if (test_facility(134)) {
@@ -3962,9 +3962,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	if (test_kvm_facility(vcpu->kvm, 156))
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_ETOKEN;
 	/* fprs can be synchronized via vrs, even if the guest has no vx. With
-	 * MACHINE_HAS_VX, (load|store)_fpu_regs() will work with vrs format.
+	 * cpu_has_vx(), (load|store)_fpu_regs() will work with vrs format.
 	 */
-	if (MACHINE_HAS_VX)
+	if (cpu_has_vx())
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
 	else
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS;
@@ -4316,18 +4316,13 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 
 	vcpu_load(vcpu);
 
-	if (test_fp_ctl(fpu->fpc)) {
-		ret = -EINVAL;
-		goto out;
-	}
 	vcpu->run->s.regs.fpc = fpu->fpc;
-	if (MACHINE_HAS_VX)
+	if (cpu_has_vx())
 		convert_fp_to_vx((__vector128 *) vcpu->run->s.regs.vrs,
 				 (freg_t *) fpu->fprs);
 	else
 		memcpy(vcpu->run->s.regs.fprs, &fpu->fprs, sizeof(fpu->fprs));
 
-out:
 	vcpu_put(vcpu);
 	return ret;
 }
@@ -4336,9 +4331,7 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
 	vcpu_load(vcpu);
 
-	/* make sure we have the latest values */
-	save_fpu_regs();
-	if (MACHINE_HAS_VX)
+	if (cpu_has_vx())
 		convert_vx_to_fp((freg_t *) fpu->fprs,
 				 (__vector128 *) vcpu->run->s.regs.vrs);
 	else
@@ -4963,14 +4956,11 @@ static void sync_regs(struct kvm_vcpu *vcpu)
 	save_fpu_regs();
 	vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc;
 	vcpu->arch.host_fpregs.regs = current->thread.fpu.regs;
-	if (MACHINE_HAS_VX)
+	if (cpu_has_vx())
 		current->thread.fpu.regs = vcpu->run->s.regs.vrs;
 	else
 		current->thread.fpu.regs = vcpu->run->s.regs.fprs;
 	current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
-	if (test_fp_ctl(current->thread.fpu.fpc))
-		/* User space provided an invalid FPC, let's clear it */
-		current->thread.fpu.fpc = 0;
 
 	/* Sync fmt2 only data */
 	if (likely(!kvm_s390_pv_cpu_is_protected(vcpu))) {
@@ -5145,7 +5135,7 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
 		gpa -= __LC_FPREGS_SAVE_AREA;
 
 	/* manually convert vector registers if necessary */
-	if (MACHINE_HAS_VX) {
+	if (cpu_has_vx()) {
 		convert_vx_to_fp(fprs, (__vector128 *) vcpu->run->s.regs.vrs);
 		rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
 				     fprs, 128);
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 02dcbe82a8e5..8207a892bbe2 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -587,10 +587,6 @@ void kvm_s390_vsie_gmap_notifier(struct gmap *gmap, unsigned long start,
 
 	if (!gmap_is_shadow(gmap))
 		return;
-	if (start >= 1UL << 31)
-		/* We are only interested in prefix pages */
-		return;
-
 	/*
 	 * Only new shadow blocks are added to the list during runtime,
 	 * therefore we can safely reference them all the time.
diff --git a/arch/s390/lib/test_unwind.c b/arch/s390/lib/test_unwind.c
index 7231bf97b93a..2848e3fb2ff5 100644
--- a/arch/s390/lib/test_unwind.c
+++ b/arch/s390/lib/test_unwind.c
@@ -350,15 +350,15 @@ static noinline int unwindme_func3(struct unwindme *u)
 /* This function must appear in the backtrace. */
 static noinline int unwindme_func2(struct unwindme *u)
 {
-	unsigned long flags;
+	unsigned long flags, mflags;
 	int rc;
 
 	if (u->flags & UWM_SWITCH_STACK) {
 		local_irq_save(flags);
-		local_mcck_disable();
+		local_mcck_save(mflags);
 		rc = call_on_stack(1, S390_lowcore.nodat_stack,
 				   int, unwindme_func3, struct unwindme *, u);
-		local_mcck_enable();
+		local_mcck_restore(mflags);
 		local_irq_restore(flags);
 		return rc;
 	} else {
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 249aefcf7c4e..ab4098886e56 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -337,6 +337,9 @@ static void do_exception(struct pt_regs *regs, int access)
 		return;
 	}
 	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+	if (fault & VM_FAULT_MAJOR)
+		flags |= FAULT_FLAG_TRIED;
+
 	/* Quick path to respond to signals */
 	if (fault_signal_pending(fault, regs)) {
 		if (!user_mode(regs))
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 3bd2ab2a9a34..99422926efe1 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -125,32 +125,23 @@ static inline pte_t ptep_flush_lazy(struct mm_struct *mm,
 
 static inline pgste_t pgste_get_lock(pte_t *ptep)
 {
-	unsigned long new = 0;
+	unsigned long value = 0;
 #ifdef CONFIG_PGSTE
-	unsigned long old;
-
-	asm(
-		"	lg	%0,%2\n"
-		"0:	lgr	%1,%0\n"
-		"	nihh	%0,0xff7f\n"	/* clear PCL bit in old */
-		"	oihh	%1,0x0080\n"	/* set PCL bit in new */
-		"	csg	%0,%1,%2\n"
-		"	jl	0b\n"
-		: "=&d" (old), "=&d" (new), "=Q" (ptep[PTRS_PER_PTE])
-		: "Q" (ptep[PTRS_PER_PTE]) : "cc", "memory");
+	unsigned long *ptr = (unsigned long *)(ptep + PTRS_PER_PTE);
+
+	do {
+		value = __atomic64_or_barrier(PGSTE_PCL_BIT, ptr);
+	} while (value & PGSTE_PCL_BIT);
+	value |= PGSTE_PCL_BIT;
 #endif
-	return __pgste(new);
+	return __pgste(value);
 }
 
 static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste)
 {
 #ifdef CONFIG_PGSTE
-	asm(
-		"	nihh	%1,0xff7f\n"	/* clear PCL bit */
-		"	stg	%1,%0\n"
-		: "=Q" (ptep[PTRS_PER_PTE])
-		: "d" (pgste_val(pgste)), "Q" (ptep[PTRS_PER_PTE])
-		: "cc", "memory");
+	barrier();
+	WRITE_ONCE(*(unsigned long *)(ptep + PTRS_PER_PTE), pgste_val(pgste) & ~PGSTE_PCL_BIT);
 #endif
 }
 
@@ -756,7 +747,7 @@ void ptep_zap_unused(struct mm_struct *mm, unsigned long addr,
 		pte_clear(mm, addr, ptep);
 	}
 	if (reset)
-		pgste_val(pgste) &= ~_PGSTE_GPS_USAGE_MASK;
+		pgste_val(pgste) &= ~(_PGSTE_GPS_USAGE_MASK | _PGSTE_GPS_NODAT);
 	pgste_set_unlock(ptep, pgste);
 	preempt_enable();
 }
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index bf06b7283f0c..b418333bb086 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -779,7 +779,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 				 int i, bool extra_pass, u32 stack_depth)
 {
 	struct bpf_insn *insn = &fp->insnsi[i];
-	s16 branch_oc_off = insn->off;
+	s32 branch_oc_off = insn->off;
 	u32 dst_reg = insn->dst_reg;
 	u32 src_reg = insn->src_reg;
 	int last, insn_count = 1;
@@ -2362,7 +2362,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 		return -ENOTSUPP;
 
 	/* Return to %r14, since func_addr and %r0 are not available. */
-	if (!func_addr && !(flags & BPF_TRAMP_F_ORIG_STACK))
+	if ((!func_addr && !(flags & BPF_TRAMP_F_ORIG_STACK)) ||
+	    (flags & BPF_TRAMP_F_INDIRECT))
 		flags |= BPF_TRAMP_F_SKIP_FRAME;
 
 	/*
@@ -2637,6 +2638,21 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 	return 0;
 }
 
+int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
+			     struct bpf_tramp_links *tlinks, void *orig_call)
+{
+	struct bpf_tramp_image im;
+	struct bpf_tramp_jit tjit;
+	int ret;
+
+	memset(&tjit, 0, sizeof(tjit));
+
+	ret = __arch_prepare_bpf_trampoline(&im, &tjit, m, flags,
+					    tlinks, orig_call);
+
+	return ret < 0 ? ret : tjit.common.prg;
+}
+
 int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
 				void *image_end, const struct btf_func_model *m,
 				u32 flags, struct bpf_tramp_links *tlinks,
@@ -2644,30 +2660,27 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
 {
 	struct bpf_tramp_jit tjit;
 	int ret;
-	int i;
 
-	for (i = 0; i < 2; i++) {
-		if (i == 0) {
-			/* Compute offsets, check whether the code fits. */
-			memset(&tjit, 0, sizeof(tjit));
-		} else {
-			/* Generate the code. */
-			tjit.common.prg = 0;
-			tjit.common.prg_buf = image;
-		}
-		ret = __arch_prepare_bpf_trampoline(im, &tjit, m, flags,
-						    tlinks, func_addr);
-		if (ret < 0)
-			return ret;
-		if (tjit.common.prg > (char *)image_end - (char *)image)
-			/*
-			 * Use the same error code as for exceeding
-			 * BPF_MAX_TRAMP_LINKS.
-			 */
-			return -E2BIG;
-	}
+	/* Compute offsets, check whether the code fits. */
+	memset(&tjit, 0, sizeof(tjit));
+	ret = __arch_prepare_bpf_trampoline(im, &tjit, m, flags,
+					    tlinks, func_addr);
+
+	if (ret < 0)
+		return ret;
+	if (tjit.common.prg > (char *)image_end - (char *)image)
+		/*
+		 * Use the same error code as for exceeding
+		 * BPF_MAX_TRAMP_LINKS.
+		 */
+		return -E2BIG;
+
+	tjit.common.prg = 0;
+	tjit.common.prg_buf = image;
+	ret = __arch_prepare_bpf_trampoline(im, &tjit, m, flags,
+					    tlinks, func_addr);
 
-	return tjit.common.prg;
+	return ret < 0 ? ret : tjit.common.prg;
 }
 
 bool bpf_jit_supports_subprog_tailcalls(void)
diff --git a/arch/s390/tools/gen_facilities.c b/arch/s390/tools/gen_facilities.c
index cb0aff5c0187..68580cbea4e6 100644
--- a/arch/s390/tools/gen_facilities.c
+++ b/arch/s390/tools/gen_facilities.c
@@ -46,6 +46,7 @@ static struct facility_def facility_defs[] = {
 #endif
 #ifdef CONFIG_HAVE_MARCH_Z13_FEATURES
 			53, /* load-and-zero-rightmost-byte, etc. */
+			129, /* vector */
 #endif
 #ifdef CONFIG_HAVE_MARCH_Z14_FEATURES
 			58, /* miscellaneous-instruction-extension 2 */
diff --git a/arch/sh/configs/titan_defconfig b/arch/sh/configs/titan_defconfig
index 871092753591..c1032559ecd4 100644
--- a/arch/sh/configs/titan_defconfig
+++ b/arch/sh/configs/titan_defconfig
@@ -138,7 +138,6 @@ CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
-CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_FW_LOADER=m
 CONFIG_CONNECTOR=m
diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h
index ac521f287fa5..cf5eab840d57 100644
--- a/arch/sh/include/asm/io.h
+++ b/arch/sh/include/asm/io.h
@@ -302,15 +302,6 @@ unsigned long long poke_real_address_q(unsigned long long addr,
 	ioremap_prot((addr), (size), pgprot_val(PAGE_KERNEL))
 #endif /* CONFIG_MMU */
 
-#define ioremap_uc	ioremap
-
-/*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p)	__va(p)
-#define unxlate_dev_mem_ptr(p, v) do { } while (0)
-
 #include <asm-generic/io.h>
 
 #define ARCH_HAS_VALID_PHYS_ADDR_RANGE
diff --git a/arch/sh/include/asm/kexec.h b/arch/sh/include/asm/kexec.h
index 927d80ba2332..76631714673c 100644
--- a/arch/sh/include/asm/kexec.h
+++ b/arch/sh/include/asm/kexec.h
@@ -28,7 +28,7 @@
 /* The native architecture */
 #define KEXEC_ARCH KEXEC_ARCH_SH
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 /* arch/sh/kernel/machine_kexec.c */
 void reserve_crashkernel(void);
 
@@ -67,6 +67,6 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
 }
 #else
 static inline void reserve_crashkernel(void) { }
-#endif /* CONFIG_KEXEC */
+#endif /* CONFIG_KEXEC_CORE */
 
 #endif /* __ASM_SH_KEXEC_H */
diff --git a/arch/sh/include/asm/traps_32.h b/arch/sh/include/asm/traps_32.h
index 8c5bbb7b6053..8f14071bea72 100644
--- a/arch/sh/include/asm/traps_32.h
+++ b/arch/sh/include/asm/traps_32.h
@@ -43,6 +43,9 @@ static inline void trigger_address_error(void)
 asmlinkage void do_address_error(struct pt_regs *regs,
 				 unsigned long writeaccess,
 				 unsigned long address);
+asmlinkage void do_page_fault(struct pt_regs *regs,
+			      unsigned long error_code,
+			      unsigned long address);
 asmlinkage void do_divide_error(unsigned long r4);
 asmlinkage void do_reserved_inst(void);
 asmlinkage void do_illegal_slot_inst(void);
diff --git a/arch/sh/kernel/Makefile b/arch/sh/kernel/Makefile
index 69cd9ac4b2ab..2d7e70537de0 100644
--- a/arch/sh/kernel/Makefile
+++ b/arch/sh/kernel/Makefile
@@ -33,7 +33,7 @@ obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_SH_STANDARD_BIOS)	+= sh_bios.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_MODULES)		+= sh_ksyms_32.o module.o
-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
+obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec.o relocate_kernel.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_IO_TRAPPED)	+= io_trapped.o
diff --git a/arch/sh/kernel/reboot.c b/arch/sh/kernel/reboot.c
index e8eeedc9b182..1de006b1c339 100644
--- a/arch/sh/kernel/reboot.c
+++ b/arch/sh/kernel/reboot.c
@@ -63,7 +63,7 @@ struct machine_ops machine_ops = {
 	.shutdown	= native_machine_shutdown,
 	.restart	= native_machine_restart,
 	.halt		= native_machine_halt,
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.crash_shutdown = native_machine_crash_shutdown,
 #endif
 };
@@ -88,7 +88,7 @@ void machine_halt(void)
 	machine_ops.halt();
 }
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 void machine_crash_shutdown(struct pt_regs *regs)
 {
 	machine_ops.crash_shutdown(regs);
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index 3d80515298d2..d3175f09b3aa 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -220,7 +220,7 @@ void __init __add_active_range(unsigned int nid, unsigned long start_pfn,
 	request_resource(res, &code_resource);
 	request_resource(res, &data_resource);
 	request_resource(res, &bss_resource);
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	request_resource(res, &crashk_res);
 #endif
 
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index 363fae0fe9bf..86fe269f0220 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -459,3 +459,8 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount
+459	common	lsm_get_self_attr		sys_lsm_get_self_attr
+460	common	lsm_set_self_attr		sys_lsm_set_self_attr
+461	common	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig
index 511c17aede4a..455311d9a5e9 100644
--- a/arch/sh/mm/Kconfig
+++ b/arch/sh/mm/Kconfig
@@ -26,7 +26,7 @@ config ARCH_FORCE_MAX_ORDER
 	default "10"
 	help
 	  The kernel page allocator limits the size of maximal physically
-	  contiguous allocations. The limit is called MAX_ORDER and it
+	  contiguous allocations. The limit is called MAX_PAGE:_ORDER and it
 	  defines the maximal power of two of number of pages that can be
 	  allocated as a single contiguous block. This option allows
 	  overriding the default setting when ability to allocate very
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 49849790e66d..204c43cb3d43 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -277,7 +277,7 @@ config ARCH_FORCE_MAX_ORDER
 	default "12"
 	help
 	  The kernel page allocator limits the size of maximal physically
-	  contiguous allocations. The limit is called MAX_ORDER and it
+	  contiguous allocations. The limit is called MAX_PAGE_ORDER and it
 	  defines the maximal power of two of number of pages that can be
 	  allocated as a single contiguous block. This option allows
 	  overriding the default setting when ability to allocate very
diff --git a/arch/sparc/boot/Makefile b/arch/sparc/boot/Makefile
index 45e5c76d449e..339c42d35089 100644
--- a/arch/sparc/boot/Makefile
+++ b/arch/sparc/boot/Makefile
@@ -24,16 +24,16 @@ ifeq ($(CONFIG_SPARC64),y)
 
 $(obj)/zImage: $(obj)/image FORCE
 	$(call if_changed,gzip)
-	@echo '  kernel: $@ is ready'
+	@$(kecho) 'Kernel: $@ is ready' '(#'$(or $(KBUILD_BUILD_VERSION),`cat .version`)')'
 
 $(obj)/vmlinux.aout: vmlinux FORCE
 	$(call if_changed,elftoaout)
-	@echo '  kernel: $@ is ready'
+	@$(kecho) 'Kernel: $@ is ready' '(#'$(or $(KBUILD_BUILD_VERSION),`cat .version`)')'
 else
 
 $(obj)/zImage: $(obj)/image FORCE
 	$(call if_changed,strip)
-	@echo '  kernel: $@ is ready'
+	@$(kecho) 'Kernel: $@ is ready' '(#'$(or $(KBUILD_BUILD_VERSION),`cat .version`)')'
 
 # The following lines make a readable image for U-Boot.
 #  uImage   - Binary file read by U-boot
@@ -59,13 +59,13 @@ targets += uImage
 $(obj)/uImage: $(obj)/image.gz FORCE
 	$(call if_changed,uimage)
 	$(call if_changed,uimage.o)
-	@echo '  Image $@ is ready'
+	@$(kecho) 'Kernel: $@ is ready' '(#'$(or $(KBUILD_BUILD_VERSION),`cat .version`)')'
 
 endif
 
 $(obj)/image: vmlinux FORCE
 	$(call if_changed,strip)
-	@echo '  kernel: $@ is ready'
+	@$(kecho) 'Kernel: $@ is ready' '(#'$(or $(KBUILD_BUILD_VERSION),`cat .version`)')'
 
 $(obj)/tftpboot.img: $(obj)/image $(obj)/piggyback System.map $(ROOT_IMG) FORCE
 	$(call if_changed,elftoaout)
diff --git a/arch/sparc/include/asm/io_64.h b/arch/sparc/include/asm/io_64.h
index 9303270b22f3..c9528e4719cd 100644
--- a/arch/sparc/include/asm/io_64.h
+++ b/arch/sparc/include/asm/io_64.h
@@ -423,7 +423,6 @@ static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
 	return (void __iomem *)offset;
 }
 
-#define ioremap_uc(X,Y)			ioremap((X),(Y))
 #define ioremap_wc(X,Y)			ioremap((X),(Y))
 #define ioremap_wt(X,Y)			ioremap((X),(Y))
 static inline void __iomem *ioremap_np(unsigned long offset, unsigned long size)
@@ -470,12 +469,6 @@ static inline int sbus_can_burst64(void)
 struct device;
 void sbus_set_sbus64(struct device *, int);
 
-/*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p)	__va(p)
-
 #endif
 
 #endif /* !(__SPARC64_IO_H) */
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 5e41033bf4ca..a8c871b7d786 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -706,6 +706,7 @@ static inline unsigned long pmd_write(pmd_t pmd)
 #define pud_write(pud)	pte_write(__pte(pud_val(pud)))
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define pmd_dirty pmd_dirty
 static inline unsigned long pmd_dirty(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index 0984bb6f0f17..58ea4ef9b622 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -5,7 +5,6 @@
 #
 
 asflags-y := -ansi
-ccflags-y := -Werror
 
 # Undefine sparc when processing vmlinux.lds - it is used
 # And teach CPP we are doing $(BITS) builds (for this case)
diff --git a/arch/sparc/kernel/asm-offsets.c b/arch/sparc/kernel/asm-offsets.c
index 5784f2df489a..3d9b9855dce9 100644
--- a/arch/sparc/kernel/asm-offsets.c
+++ b/arch/sparc/kernel/asm-offsets.c
@@ -19,14 +19,14 @@
 #include <asm/hibernate.h>
 
 #ifdef CONFIG_SPARC32
-int sparc32_foo(void)
+static int __used sparc32_foo(void)
 {
 	DEFINE(AOFF_thread_fork_kpsr,
 			offsetof(struct thread_struct, fork_kpsr));
 	return 0;
 }
 #else
-int sparc64_foo(void)
+static int __used sparc64_foo(void)
 {
 #ifdef CONFIG_HIBERNATION
 	BLANK();
@@ -45,7 +45,7 @@ int sparc64_foo(void)
 }
 #endif
 
-int foo(void)
+static int __used foo(void)
 {
 	BLANK();
 	DEFINE(AOFF_task_thread, offsetof(struct task_struct, thread));
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index c80b0a21d709..083e5f05a7f0 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -194,7 +194,7 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
 
 	size = IO_PAGE_ALIGN(size);
 	order = get_order(size);
-	if (unlikely(order > MAX_ORDER))
+	if (unlikely(order > MAX_PAGE_ORDER))
 		return NULL;
 
 	npages = size >> IO_PAGE_SHIFT;
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 7bcaa3d5ea44..b23d59313589 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -502,3 +502,8 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount
+459	common	lsm_get_self_attr		sys_lsm_get_self_attr
+460	common	lsm_set_self_attr		sys_lsm_set_self_attr
+461	common	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/sparc/kernel/traps_32.c b/arch/sparc/kernel/traps_32.c
index 179aabfa712e..bb149f6cc34b 100644
--- a/arch/sparc/kernel/traps_32.c
+++ b/arch/sparc/kernel/traps_32.c
@@ -10,6 +10,7 @@
  * I hate traps on the sparc, grrr...
  */
 
+#include <linux/cpu.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/debug.h>
 #include <linux/mm_types.h>
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 08ffd17d5ec3..dd048023bff5 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -9,6 +9,7 @@
  * I like traps on v9, :))))
  */
 
+#include <linux/cpu.h>
 #include <linux/extable.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/debug.h>
@@ -897,7 +898,7 @@ void __init cheetah_ecache_flush_init(void)
 
 	/* Now allocate error trap reporting scoreboard. */
 	sz = NR_CPUS * (2 * sizeof(struct cheetah_err_info));
-	for (order = 0; order <= MAX_ORDER; order++) {
+	for (order = 0; order < NR_PAGE_ORDERS; order++) {
 		if ((PAGE_SIZE << order) >= sz)
 			break;
 	}
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index 063556fe2cb1..59669ebddd4e 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -3,7 +3,6 @@
 #
 
 asflags-y := -ansi -DST_DIV0=0x02
-ccflags-y := -Werror
 
 lib-$(CONFIG_SPARC32) += ashrdi3.o
 lib-$(CONFIG_SPARC32) += memcpy.o memset.o
diff --git a/arch/sparc/mm/Makefile b/arch/sparc/mm/Makefile
index 871354aa3c00..809d993f6d88 100644
--- a/arch/sparc/mm/Makefile
+++ b/arch/sparc/mm/Makefile
@@ -3,7 +3,6 @@
 #
 
 asflags-y := -ansi
-ccflags-y := -Werror
 
 obj-$(CONFIG_SPARC64)   += ultra.o tlb.o tsb.o
 obj-y                   += fault_$(BITS).o
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 5e2931a18409..6acd8a4c1e2a 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -402,8 +402,8 @@ void tsb_grow(struct mm_struct *mm, unsigned long tsb_index, unsigned long rss)
 	unsigned long new_rss_limit;
 	gfp_t gfp_flags;
 
-	if (max_tsb_size > PAGE_SIZE << MAX_ORDER)
-		max_tsb_size = PAGE_SIZE << MAX_ORDER;
+	if (max_tsb_size > PAGE_SIZE << MAX_PAGE_ORDER)
+		max_tsb_size = PAGE_SIZE << MAX_PAGE_ORDER;
 
 	new_cache_index = 0;
 	for (new_size = 8192; new_size < max_tsb_size; new_size <<= 1UL) {
diff --git a/arch/sparc/prom/Makefile b/arch/sparc/prom/Makefile
index 397b79af77f7..a1adc75d8055 100644
--- a/arch/sparc/prom/Makefile
+++ b/arch/sparc/prom/Makefile
@@ -3,7 +3,6 @@
 # Linux.
 #
 asflags := -ansi
-ccflags := -Werror
 
 lib-y                 := bootstr_$(BITS).o
 lib-y                 += init_$(BITS).o
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 50206feac577..92ee2697ff39 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -798,7 +798,6 @@ static int ubd_open_dev(struct ubd *ubd_dev)
 		ubd_dev->cow.fd = err;
 	}
 	if (ubd_dev->no_trim == 0) {
-		ubd_dev->queue->limits.discard_granularity = SECTOR_SIZE;
 		blk_queue_max_discard_sectors(ubd_dev->queue, UBD_MAX_REQUEST);
 		blk_queue_max_write_zeroes_sectors(ubd_dev->queue, UBD_MAX_REQUEST);
 	}
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index b1bfed0c8528..7a9820797eae 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -373,10 +373,10 @@ int __init linux_main(int argc, char **argv)
 	max_physmem = TASK_SIZE - uml_physmem - iomem_size - MIN_VMALLOC;
 
 	/*
-	 * Zones have to begin on a 1 << MAX_ORDER page boundary,
+	 * Zones have to begin on a 1 << MAX_PAGE_ORDER page boundary,
 	 * so this makes sure that's true for highmem
 	 */
-	max_physmem &= ~((1 << (PAGE_SHIFT + MAX_ORDER)) - 1);
+	max_physmem &= ~((1 << (PAGE_SHIFT + MAX_PAGE_ORDER)) - 1);
 	if (physmem_size + iomem_size > max_physmem) {
 		highmem = physmem_size + iomem_size - max_physmem;
 		physmem_size -= highmem;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 3762f41bb092..53f2e7797b1d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -88,6 +88,7 @@ config X86
 	select ARCH_HAS_PMEM_API		if X86_64
 	select ARCH_HAS_PTE_DEVMAP		if X86_64
 	select ARCH_HAS_PTE_SPECIAL
+	select ARCH_HAS_HW_PTE_YOUNG
 	select ARCH_HAS_NONLEAF_PMD_YOUNG	if PGTABLE_LEVELS > 2
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
 	select ARCH_HAS_COPY_MC			if X86_64
@@ -169,7 +170,7 @@ config X86
 	select HAS_IOPORT
 	select HAVE_ACPI_APEI			if ACPI
 	select HAVE_ACPI_APEI_NMI		if ACPI
-	select HAVE_ALIGNED_STRUCT_PAGE		if SLUB
+	select HAVE_ALIGNED_STRUCT_PAGE
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_HUGE_VMAP		if X86_64 || X86_PAE
 	select HAVE_ARCH_HUGE_VMALLOC		if X86_64
@@ -384,10 +385,6 @@ config HAVE_INTEL_TXT
 	def_bool y
 	depends on INTEL_IOMMU && ACPI
 
-config X86_32_SMP
-	def_bool y
-	depends on X86_32 && SMP
-
 config X86_64_SMP
 	def_bool y
 	depends on X86_64 && SMP
@@ -1415,7 +1412,7 @@ config HIGHMEM4G
 
 config HIGHMEM64G
 	bool "64GB"
-	depends on !M486SX && !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !MWINCHIP3D && !MK6
+	depends on X86_HAVE_PAE
 	select X86_PAE
 	help
 	  Select this if you have a 32-bit processor and more than 4
@@ -1472,7 +1469,7 @@ config HIGHMEM
 
 config X86_PAE
 	bool "PAE (Physical Address Extension) Support"
-	depends on X86_32 && !HIGHMEM4G
+	depends on X86_32 && X86_HAVE_PAE
 	select PHYS_ADDR_T_64BIT
 	select SWIOTLB
 	help
@@ -2072,7 +2069,7 @@ config ARCH_SUPPORTS_KEXEC
 	def_bool y
 
 config ARCH_SUPPORTS_KEXEC_FILE
-	def_bool X86_64 && CRYPTO && CRYPTO_SHA256
+	def_bool X86_64
 
 config ARCH_SELECTS_KEXEC_FILE
 	def_bool y
@@ -2080,7 +2077,7 @@ config ARCH_SELECTS_KEXEC_FILE
 	select HAVE_IMA_KEXEC if IMA
 
 config ARCH_SUPPORTS_KEXEC_PURGATORY
-	def_bool KEXEC_FILE
+	def_bool y
 
 config ARCH_SUPPORTS_KEXEC_SIG
 	def_bool y
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 00468adf180f..b9224cf2ee4d 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -362,9 +362,13 @@ config X86_TSC
 	def_bool y
 	depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MATOM) || X86_64
 
+config X86_HAVE_PAE
+	def_bool y
+	depends on MCRUSOE || MEFFICEON || MCYRIXIII || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC7 || MCORE2 || MATOM || X86_64
+
 config X86_CMPXCHG64
 	def_bool y
-	depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586TSC || M586MMX || MATOM || MGEODE_LX || MGEODEGX1 || MK6 || MK7 || MK8
+	depends on X86_HAVE_PAE || M586TSC || M586MMX || MK6 || MK7
 
 # this should be set for all -march=.. options where the compiler
 # generates cmov.
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 71fc531b95b4..f19c038409aa 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -53,7 +53,7 @@ KBUILD_CFLAGS += -D__DISABLE_EXPORTS
 KBUILD_CFLAGS += $(call cc-option,-Wa$(comma)-mrelax-relocations=no)
 KBUILD_CFLAGS += -include $(srctree)/include/linux/hidden.h
 
-# sev.c indirectly inludes inat-table.h which is generated during
+# sev.c indirectly includes inat-table.h which is generated during
 # compilation and stored in $(objtree). Add the directory to the includes so
 # that the compiler finds it even with out-of-tree builds (make O=/some/path).
 CFLAGS_sev.o += -I$(objtree)/arch/x86/lib/
diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c
index 55c98fdd67d2..18d15d1ce87d 100644
--- a/arch/x86/boot/compressed/acpi.c
+++ b/arch/x86/boot/compressed/acpi.c
@@ -178,7 +178,7 @@ static unsigned long get_cmdline_acpi_rsdp(void)
 {
 	unsigned long addr = 0;
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	char val[MAX_ADDR_LEN] = { };
 	int ret;
 
diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c
index 473ba59b82a8..d040080d7edb 100644
--- a/arch/x86/boot/compressed/ident_map_64.c
+++ b/arch/x86/boot/compressed/ident_map_64.c
@@ -386,3 +386,8 @@ void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code)
 	 */
 	kernel_add_identity_map(address, end);
 }
+
+void do_boot_nmi_trap(struct pt_regs *regs, unsigned long error_code)
+{
+	/* Empty handler to ignore NMI during early boot */
+}
diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c
index 3cdf94b41456..d100284bbef4 100644
--- a/arch/x86/boot/compressed/idt_64.c
+++ b/arch/x86/boot/compressed/idt_64.c
@@ -61,6 +61,7 @@ void load_stage2_idt(void)
 	boot_idt_desc.address = (unsigned long)boot_idt;
 
 	set_idt_entry(X86_TRAP_PF, boot_page_fault);
+	set_idt_entry(X86_TRAP_NMI, boot_nmi_trap);
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 	/*
diff --git a/arch/x86/boot/compressed/idt_handlers_64.S b/arch/x86/boot/compressed/idt_handlers_64.S
index 22890e199f5b..4d03c8562f63 100644
--- a/arch/x86/boot/compressed/idt_handlers_64.S
+++ b/arch/x86/boot/compressed/idt_handlers_64.S
@@ -70,6 +70,7 @@ SYM_FUNC_END(\name)
 	.code64
 
 EXCEPTION_HANDLER	boot_page_fault do_boot_page_fault error_code=1
+EXCEPTION_HANDLER	boot_nmi_trap do_boot_nmi_trap error_code=0
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 EXCEPTION_HANDLER	boot_stage1_vc do_vc_no_ghcb		error_code=1
diff --git a/arch/x86/boot/compressed/mem.c b/arch/x86/boot/compressed/mem.c
index b3c3a4be7471..dbba332e4a12 100644
--- a/arch/x86/boot/compressed/mem.c
+++ b/arch/x86/boot/compressed/mem.c
@@ -8,7 +8,7 @@
 
 /*
  * accept_memory() and process_unaccepted_memory() called from EFI stub which
- * runs before decompresser and its early_tdx_detect().
+ * runs before decompressor and its early_tdx_detect().
  *
  * Enumerate TDX directly from the early users.
  */
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index c0d502bd8716..bc2f0f17fb90 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -196,6 +196,7 @@ static inline void cleanup_exception_handling(void) { }
 
 /* IDT Entry Points */
 void boot_page_fault(void);
+void boot_nmi_trap(void);
 void boot_stage1_vc(void);
 void boot_stage2_vc(void);
 
diff --git a/arch/x86/boot/pm.c b/arch/x86/boot/pm.c
index 40031a614712..5941f930f6c5 100644
--- a/arch/x86/boot/pm.c
+++ b/arch/x86/boot/pm.c
@@ -11,6 +11,7 @@
  */
 
 #include "boot.h"
+#include <asm/desc_defs.h>
 #include <asm/segment.h>
 
 /*
@@ -67,13 +68,13 @@ static void setup_gdt(void)
 	   being 8-byte unaligned.  Intel recommends 16 byte alignment. */
 	static const u64 boot_gdt[] __attribute__((aligned(16))) = {
 		/* CS: code, read/execute, 4 GB, base 0 */
-		[GDT_ENTRY_BOOT_CS] = GDT_ENTRY(0xc09b, 0, 0xfffff),
+		[GDT_ENTRY_BOOT_CS] = GDT_ENTRY(DESC_CODE32, 0, 0xfffff),
 		/* DS: data, read/write, 4 GB, base 0 */
-		[GDT_ENTRY_BOOT_DS] = GDT_ENTRY(0xc093, 0, 0xfffff),
+		[GDT_ENTRY_BOOT_DS] = GDT_ENTRY(DESC_DATA32, 0, 0xfffff),
 		/* TSS: 32-bit tss, 104 bytes, base 4096 */
 		/* We only have a TSS here to keep Intel VT happy;
 		   we don't actually use it for anything. */
-		[GDT_ENTRY_BOOT_TSS] = GDT_ENTRY(0x0089, 4096, 103),
+		[GDT_ENTRY_BOOT_TSS] = GDT_ENTRY(DESC_TSS32, 4096, 103),
 	};
 	/* Xen HVM incorrectly stores a pointer to the gdt_ptr, instead
 	   of the gdt_ptr contents.  Thus, make it static so it will
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 1c8541ae3b3a..c23f3b9c84fe 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -49,7 +49,7 @@ int strcmp(const char *str1, const char *str2)
 {
 	const unsigned char *s1 = (const unsigned char *)str1;
 	const unsigned char *s2 = (const unsigned char *)str2;
-	int delta = 0;
+	int delta;
 
 	while (*s1 || *s2) {
 		delta = *s1 - *s2;
diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index 1b5d17a9f70d..c1cb90369915 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -10,6 +10,7 @@
 #include <asm/coco.h>
 #include <asm/tdx.h>
 #include <asm/vmx.h>
+#include <asm/ia32.h>
 #include <asm/insn.h>
 #include <asm/insn-eval.h>
 #include <asm/pgtable.h>
@@ -886,7 +887,7 @@ void __init tdx_early_init(void)
 	 * there.
 	 *
 	 * Intel-TDX has a secure RDMSR hypercall, but that needs to be
-	 * implemented seperately in the low level startup ASM code.
+	 * implemented separately in the low level startup ASM code.
 	 * Until that is in place, disable parallel bringup for TDX.
 	 */
 	x86_cpuinit.parallel_bringup = false;
diff --git a/arch/x86/crypto/Kconfig b/arch/x86/crypto/Kconfig
index 9bbfd01cfa2f..c9e59589a1ce 100644
--- a/arch/x86/crypto/Kconfig
+++ b/arch/x86/crypto/Kconfig
@@ -189,7 +189,7 @@ config CRYPTO_SERPENT_AVX2_X86_64
 	  Processes 16 blocks in parallel.
 
 config CRYPTO_SM4_AESNI_AVX_X86_64
-	tristate "Ciphers: SM4 with modes: ECB, CBC, CFB, CTR (AES-NI/AVX)"
+	tristate "Ciphers: SM4 with modes: ECB, CBC, CTR (AES-NI/AVX)"
 	depends on X86 && 64BIT
 	select CRYPTO_SKCIPHER
 	select CRYPTO_SIMD
@@ -197,7 +197,7 @@ config CRYPTO_SM4_AESNI_AVX_X86_64
 	select CRYPTO_SM4
 	help
 	  Length-preserving ciphers: SM4 cipher algorithms
-	  (OSCCA GB/T 32907-2016) with ECB, CBC, CFB, and CTR modes
+	  (OSCCA GB/T 32907-2016) with ECB, CBC, and CTR modes
 
 	  Architecture: x86_64 using:
 	  - AES-NI (AES New Instructions)
@@ -210,7 +210,7 @@ config CRYPTO_SM4_AESNI_AVX_X86_64
 	  If unsure, say N.
 
 config CRYPTO_SM4_AESNI_AVX2_X86_64
-	tristate "Ciphers: SM4 with modes: ECB, CBC, CFB, CTR (AES-NI/AVX2)"
+	tristate "Ciphers: SM4 with modes: ECB, CBC, CTR (AES-NI/AVX2)"
 	depends on X86 && 64BIT
 	select CRYPTO_SKCIPHER
 	select CRYPTO_SIMD
@@ -219,7 +219,7 @@ config CRYPTO_SM4_AESNI_AVX2_X86_64
 	select CRYPTO_SM4_AESNI_AVX_X86_64
 	help
 	  Length-preserving ciphers: SM4 cipher algorithms
-	  (OSCCA GB/T 32907-2016) with ECB, CBC, CFB, and CTR modes
+	  (OSCCA GB/T 32907-2016) with ECB, CBC, and CTR modes
 
 	  Architecture: x86_64 using:
 	  - AES-NI (AES New Instructions)
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 187f913cc239..411d8c83e88a 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -666,7 +666,7 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 
 .ifc \operation, dec
 	movdqa	%xmm1, %xmm3
-	pxor	%xmm1, %xmm9		# Cyphertext XOR E(K, Yn)
+	pxor	%xmm1, %xmm9		# Ciphertext XOR E(K, Yn)
 
 	mov	\PLAIN_CYPH_LEN, %r10
 	add	%r13, %r10
diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S
index 74dd230973cf..8c9749ed0651 100644
--- a/arch/x86/crypto/aesni-intel_avx-x86_64.S
+++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S
@@ -747,7 +747,7 @@ VARIABLE_OFFSET = 16*8
 
 .if  \ENC_DEC ==  DEC
         vmovdqa	%xmm1, %xmm3
-        pxor	%xmm1, %xmm9		# Cyphertext XOR E(K, Yn)
+        pxor	%xmm1, %xmm9		# Ciphertext XOR E(K, Yn)
 
         mov	\PLAIN_CYPH_LEN, %r10
         add	%r13, %r10
diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
index 81ce0f4db555..bbcff1fb78cb 100644
--- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
+++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
@@ -184,7 +184,7 @@ SYM_FUNC_START(crc_pcl)
 	xor     crc1,crc1
 	xor     crc2,crc2
 
-	# Fall thruogh into top of crc array (crc_128)
+	# Fall through into top of crc array (crc_128)
 
 	################################################################
 	## 3) CRC Array:
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index 959afa705e95..ab8bc54f254d 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -2,8 +2,8 @@
 /*
  * Cryptographic API.
  *
- * Glue code for the SHA1 Secure Hash Algorithm assembler implementation using
- * Supplemental SSE3 instructions.
+ * Glue code for the SHA1 Secure Hash Algorithm assembler implementations
+ * using SSSE3, AVX, AVX2, and SHA-NI instructions.
  *
  * This file is based on sha1_generic.c
  *
@@ -28,6 +28,9 @@
 #include <asm/simd.h>
 
 static const struct x86_cpu_id module_cpu_ids[] = {
+#ifdef CONFIG_AS_SHA1_NI
+	X86_MATCH_FEATURE(X86_FEATURE_SHA_NI, NULL),
+#endif
 	X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL),
 	X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL),
 	X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL),
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
index 4c0383a90e11..e04a43d9f7d5 100644
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ b/arch/x86/crypto/sha256_ssse3_glue.c
@@ -1,8 +1,8 @@
 /*
  * Cryptographic API.
  *
- * Glue code for the SHA256 Secure Hash Algorithm assembler
- * implementation using supplemental SSE3 / AVX / AVX2 instructions.
+ * Glue code for the SHA256 Secure Hash Algorithm assembler implementations
+ * using SSSE3, AVX, AVX2, and SHA-NI instructions.
  *
  * This file is based on sha256_generic.c
  *
@@ -45,6 +45,9 @@ asmlinkage void sha256_transform_ssse3(struct sha256_state *state,
 				       const u8 *data, int blocks);
 
 static const struct x86_cpu_id module_cpu_ids[] = {
+#ifdef CONFIG_AS_SHA256_NI
+	X86_MATCH_FEATURE(X86_FEATURE_SHA_NI, NULL),
+#endif
 	X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL),
 	X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL),
 	X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL),
diff --git a/arch/x86/crypto/sha512-avx-asm.S b/arch/x86/crypto/sha512-avx-asm.S
index d902b8ea0721..5bfce4b045fd 100644
--- a/arch/x86/crypto/sha512-avx-asm.S
+++ b/arch/x86/crypto/sha512-avx-asm.S
@@ -84,7 +84,7 @@ frame_size = frame_WK + WK_SIZE
 
 # Useful QWORD "arrays" for simpler memory references
 # MSG, DIGEST, K_t, W_t are arrays
-# WK_2(t) points to 1 of 2 qwords at frame.WK depdending on t being odd/even
+# WK_2(t) points to 1 of 2 qwords at frame.WK depending on t being odd/even
 
 # Input message (arg1)
 #define MSG(i)    8*i(msg)
diff --git a/arch/x86/crypto/sha512-ssse3-asm.S b/arch/x86/crypto/sha512-ssse3-asm.S
index 65be30156816..30a2c4777f9d 100644
--- a/arch/x86/crypto/sha512-ssse3-asm.S
+++ b/arch/x86/crypto/sha512-ssse3-asm.S
@@ -82,7 +82,7 @@ frame_size = frame_WK + WK_SIZE
 
 # Useful QWORD "arrays" for simpler memory references
 # MSG, DIGEST, K_t, W_t are arrays
-# WK_2(t) points to 1 of 2 qwords at frame.WK depdending on t being odd/even
+# WK_2(t) points to 1 of 2 qwords at frame.WK depending on t being odd/even
 
 # Input message (arg1)
 #define MSG(i)    8*i(msg)
diff --git a/arch/x86/crypto/sm4-aesni-avx-asm_64.S b/arch/x86/crypto/sm4-aesni-avx-asm_64.S
index e2668d2fe6ce..2bf611eaa191 100644
--- a/arch/x86/crypto/sm4-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/sm4-aesni-avx-asm_64.S
@@ -534,55 +534,3 @@ SYM_TYPED_FUNC_START(sm4_aesni_avx_cbc_dec_blk8)
 	FRAME_END
 	RET;
 SYM_FUNC_END(sm4_aesni_avx_cbc_dec_blk8)
-
-/*
- * void sm4_aesni_avx_cfb_dec_blk8(const u32 *rk, u8 *dst,
- *                                 const u8 *src, u8 *iv)
- */
-SYM_TYPED_FUNC_START(sm4_aesni_avx_cfb_dec_blk8)
-	/* input:
-	 *	%rdi: round key array, CTX
-	 *	%rsi: dst (8 blocks)
-	 *	%rdx: src (8 blocks)
-	 *	%rcx: iv
-	 */
-	FRAME_BEGIN
-
-	/* Load input */
-	vmovdqu (%rcx), RA0;
-	vmovdqu 0 * 16(%rdx), RA1;
-	vmovdqu 1 * 16(%rdx), RA2;
-	vmovdqu 2 * 16(%rdx), RA3;
-	vmovdqu 3 * 16(%rdx), RB0;
-	vmovdqu 4 * 16(%rdx), RB1;
-	vmovdqu 5 * 16(%rdx), RB2;
-	vmovdqu 6 * 16(%rdx), RB3;
-
-	/* Update IV */
-	vmovdqu 7 * 16(%rdx), RNOT;
-	vmovdqu RNOT, (%rcx);
-
-	call __sm4_crypt_blk8;
-
-	vpxor (0 * 16)(%rdx), RA0, RA0;
-	vpxor (1 * 16)(%rdx), RA1, RA1;
-	vpxor (2 * 16)(%rdx), RA2, RA2;
-	vpxor (3 * 16)(%rdx), RA3, RA3;
-	vpxor (4 * 16)(%rdx), RB0, RB0;
-	vpxor (5 * 16)(%rdx), RB1, RB1;
-	vpxor (6 * 16)(%rdx), RB2, RB2;
-	vpxor (7 * 16)(%rdx), RB3, RB3;
-
-	vmovdqu RA0, (0 * 16)(%rsi);
-	vmovdqu RA1, (1 * 16)(%rsi);
-	vmovdqu RA2, (2 * 16)(%rsi);
-	vmovdqu RA3, (3 * 16)(%rsi);
-	vmovdqu RB0, (4 * 16)(%rsi);
-	vmovdqu RB1, (5 * 16)(%rsi);
-	vmovdqu RB2, (6 * 16)(%rsi);
-	vmovdqu RB3, (7 * 16)(%rsi);
-
-	vzeroall;
-	FRAME_END
-	RET;
-SYM_FUNC_END(sm4_aesni_avx_cfb_dec_blk8)
diff --git a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
index 98ede9459287..9ff5ba075591 100644
--- a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
@@ -439,58 +439,3 @@ SYM_TYPED_FUNC_START(sm4_aesni_avx2_cbc_dec_blk16)
 	FRAME_END
 	RET;
 SYM_FUNC_END(sm4_aesni_avx2_cbc_dec_blk16)
-
-/*
- * void sm4_aesni_avx2_cfb_dec_blk16(const u32 *rk, u8 *dst,
- *                                   const u8 *src, u8 *iv)
- */
-SYM_TYPED_FUNC_START(sm4_aesni_avx2_cfb_dec_blk16)
-	/* input:
-	 *	%rdi: round key array, CTX
-	 *	%rsi: dst (16 blocks)
-	 *	%rdx: src (16 blocks)
-	 *	%rcx: iv
-	 */
-	FRAME_BEGIN
-
-	vzeroupper;
-
-	/* Load input */
-	vmovdqu (%rcx), RNOTx;
-	vinserti128 $1, (%rdx), RNOT, RA0;
-	vmovdqu (0 * 32 + 16)(%rdx), RA1;
-	vmovdqu (1 * 32 + 16)(%rdx), RA2;
-	vmovdqu (2 * 32 + 16)(%rdx), RA3;
-	vmovdqu (3 * 32 + 16)(%rdx), RB0;
-	vmovdqu (4 * 32 + 16)(%rdx), RB1;
-	vmovdqu (5 * 32 + 16)(%rdx), RB2;
-	vmovdqu (6 * 32 + 16)(%rdx), RB3;
-
-	/* Update IV */
-	vmovdqu (7 * 32 + 16)(%rdx), RNOTx;
-	vmovdqu RNOTx, (%rcx);
-
-	call __sm4_crypt_blk16;
-
-	vpxor (0 * 32)(%rdx), RA0, RA0;
-	vpxor (1 * 32)(%rdx), RA1, RA1;
-	vpxor (2 * 32)(%rdx), RA2, RA2;
-	vpxor (3 * 32)(%rdx), RA3, RA3;
-	vpxor (4 * 32)(%rdx), RB0, RB0;
-	vpxor (5 * 32)(%rdx), RB1, RB1;
-	vpxor (6 * 32)(%rdx), RB2, RB2;
-	vpxor (7 * 32)(%rdx), RB3, RB3;
-
-	vmovdqu RA0, (0 * 32)(%rsi);
-	vmovdqu RA1, (1 * 32)(%rsi);
-	vmovdqu RA2, (2 * 32)(%rsi);
-	vmovdqu RA3, (3 * 32)(%rsi);
-	vmovdqu RB0, (4 * 32)(%rsi);
-	vmovdqu RB1, (5 * 32)(%rsi);
-	vmovdqu RB2, (6 * 32)(%rsi);
-	vmovdqu RB3, (7 * 32)(%rsi);
-
-	vzeroall;
-	FRAME_END
-	RET;
-SYM_FUNC_END(sm4_aesni_avx2_cfb_dec_blk16)
diff --git a/arch/x86/crypto/sm4-avx.h b/arch/x86/crypto/sm4-avx.h
index 1bceab7516aa..b5b5e67e40ed 100644
--- a/arch/x86/crypto/sm4-avx.h
+++ b/arch/x86/crypto/sm4-avx.h
@@ -14,10 +14,6 @@ int sm4_cbc_encrypt(struct skcipher_request *req);
 int sm4_avx_cbc_decrypt(struct skcipher_request *req,
 			unsigned int bsize, sm4_crypt_func func);
 
-int sm4_cfb_encrypt(struct skcipher_request *req);
-int sm4_avx_cfb_decrypt(struct skcipher_request *req,
-			unsigned int bsize, sm4_crypt_func func);
-
 int sm4_avx_ctr_crypt(struct skcipher_request *req,
 			unsigned int bsize, sm4_crypt_func func);
 
diff --git a/arch/x86/crypto/sm4_aesni_avx2_glue.c b/arch/x86/crypto/sm4_aesni_avx2_glue.c
index 84bc718f49a3..1148fd4cd57f 100644
--- a/arch/x86/crypto/sm4_aesni_avx2_glue.c
+++ b/arch/x86/crypto/sm4_aesni_avx2_glue.c
@@ -23,8 +23,6 @@ asmlinkage void sm4_aesni_avx2_ctr_enc_blk16(const u32 *rk, u8 *dst,
 					const u8 *src, u8 *iv);
 asmlinkage void sm4_aesni_avx2_cbc_dec_blk16(const u32 *rk, u8 *dst,
 					const u8 *src, u8 *iv);
-asmlinkage void sm4_aesni_avx2_cfb_dec_blk16(const u32 *rk, u8 *dst,
-					const u8 *src, u8 *iv);
 
 static int sm4_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			unsigned int key_len)
@@ -41,12 +39,6 @@ static int cbc_decrypt(struct skcipher_request *req)
 }
 
 
-static int cfb_decrypt(struct skcipher_request *req)
-{
-	return sm4_avx_cfb_decrypt(req, SM4_CRYPT16_BLOCK_SIZE,
-				sm4_aesni_avx2_cfb_dec_blk16);
-}
-
 static int ctr_crypt(struct skcipher_request *req)
 {
 	return sm4_avx_ctr_crypt(req, SM4_CRYPT16_BLOCK_SIZE,
@@ -89,24 +81,6 @@ static struct skcipher_alg sm4_aesni_avx2_skciphers[] = {
 		.decrypt	= cbc_decrypt,
 	}, {
 		.base = {
-			.cra_name		= "__cfb(sm4)",
-			.cra_driver_name	= "__cfb-sm4-aesni-avx2",
-			.cra_priority		= 500,
-			.cra_flags		= CRYPTO_ALG_INTERNAL,
-			.cra_blocksize		= 1,
-			.cra_ctxsize		= sizeof(struct sm4_ctx),
-			.cra_module		= THIS_MODULE,
-		},
-		.min_keysize	= SM4_KEY_SIZE,
-		.max_keysize	= SM4_KEY_SIZE,
-		.ivsize		= SM4_BLOCK_SIZE,
-		.chunksize	= SM4_BLOCK_SIZE,
-		.walksize	= 16 * SM4_BLOCK_SIZE,
-		.setkey		= sm4_skcipher_setkey,
-		.encrypt	= sm4_cfb_encrypt,
-		.decrypt	= cfb_decrypt,
-	}, {
-		.base = {
 			.cra_name		= "__ctr(sm4)",
 			.cra_driver_name	= "__ctr-sm4-aesni-avx2",
 			.cra_priority		= 500,
diff --git a/arch/x86/crypto/sm4_aesni_avx_glue.c b/arch/x86/crypto/sm4_aesni_avx_glue.c
index 7800f77d68ad..85b4ca78b47b 100644
--- a/arch/x86/crypto/sm4_aesni_avx_glue.c
+++ b/arch/x86/crypto/sm4_aesni_avx_glue.c
@@ -27,8 +27,6 @@ asmlinkage void sm4_aesni_avx_ctr_enc_blk8(const u32 *rk, u8 *dst,
 				const u8 *src, u8 *iv);
 asmlinkage void sm4_aesni_avx_cbc_dec_blk8(const u32 *rk, u8 *dst,
 				const u8 *src, u8 *iv);
-asmlinkage void sm4_aesni_avx_cfb_dec_blk8(const u32 *rk, u8 *dst,
-				const u8 *src, u8 *iv);
 
 static int sm4_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			unsigned int key_len)
@@ -188,116 +186,6 @@ static int cbc_decrypt(struct skcipher_request *req)
 				sm4_aesni_avx_cbc_dec_blk8);
 }
 
-int sm4_cfb_encrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct skcipher_walk walk;
-	unsigned int nbytes;
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	while ((nbytes = walk.nbytes) > 0) {
-		u8 keystream[SM4_BLOCK_SIZE];
-		const u8 *iv = walk.iv;
-		const u8 *src = walk.src.virt.addr;
-		u8 *dst = walk.dst.virt.addr;
-
-		while (nbytes >= SM4_BLOCK_SIZE) {
-			sm4_crypt_block(ctx->rkey_enc, keystream, iv);
-			crypto_xor_cpy(dst, src, keystream, SM4_BLOCK_SIZE);
-			iv = dst;
-			src += SM4_BLOCK_SIZE;
-			dst += SM4_BLOCK_SIZE;
-			nbytes -= SM4_BLOCK_SIZE;
-		}
-		if (iv != walk.iv)
-			memcpy(walk.iv, iv, SM4_BLOCK_SIZE);
-
-		/* tail */
-		if (walk.nbytes == walk.total && nbytes > 0) {
-			sm4_crypt_block(ctx->rkey_enc, keystream, walk.iv);
-			crypto_xor_cpy(dst, src, keystream, nbytes);
-			nbytes = 0;
-		}
-
-		err = skcipher_walk_done(&walk, nbytes);
-	}
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(sm4_cfb_encrypt);
-
-int sm4_avx_cfb_decrypt(struct skcipher_request *req,
-			unsigned int bsize, sm4_crypt_func func)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct skcipher_walk walk;
-	unsigned int nbytes;
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	while ((nbytes = walk.nbytes) > 0) {
-		const u8 *src = walk.src.virt.addr;
-		u8 *dst = walk.dst.virt.addr;
-
-		kernel_fpu_begin();
-
-		while (nbytes >= bsize) {
-			func(ctx->rkey_enc, dst, src, walk.iv);
-			dst += bsize;
-			src += bsize;
-			nbytes -= bsize;
-		}
-
-		while (nbytes >= SM4_BLOCK_SIZE) {
-			u8 keystream[SM4_BLOCK_SIZE * 8];
-			unsigned int nblocks = min(nbytes >> 4, 8u);
-
-			memcpy(keystream, walk.iv, SM4_BLOCK_SIZE);
-			if (nblocks > 1)
-				memcpy(&keystream[SM4_BLOCK_SIZE], src,
-					(nblocks - 1) * SM4_BLOCK_SIZE);
-			memcpy(walk.iv, src + (nblocks - 1) * SM4_BLOCK_SIZE,
-				SM4_BLOCK_SIZE);
-
-			sm4_aesni_avx_crypt8(ctx->rkey_enc, keystream,
-						keystream, nblocks);
-
-			crypto_xor_cpy(dst, src, keystream,
-					nblocks * SM4_BLOCK_SIZE);
-			dst += nblocks * SM4_BLOCK_SIZE;
-			src += nblocks * SM4_BLOCK_SIZE;
-			nbytes -= nblocks * SM4_BLOCK_SIZE;
-		}
-
-		kernel_fpu_end();
-
-		/* tail */
-		if (walk.nbytes == walk.total && nbytes > 0) {
-			u8 keystream[SM4_BLOCK_SIZE];
-
-			sm4_crypt_block(ctx->rkey_enc, keystream, walk.iv);
-			crypto_xor_cpy(dst, src, keystream, nbytes);
-			nbytes = 0;
-		}
-
-		err = skcipher_walk_done(&walk, nbytes);
-	}
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(sm4_avx_cfb_decrypt);
-
-static int cfb_decrypt(struct skcipher_request *req)
-{
-	return sm4_avx_cfb_decrypt(req, SM4_CRYPT8_BLOCK_SIZE,
-				sm4_aesni_avx_cfb_dec_blk8);
-}
-
 int sm4_avx_ctr_crypt(struct skcipher_request *req,
 			unsigned int bsize, sm4_crypt_func func)
 {
@@ -408,24 +296,6 @@ static struct skcipher_alg sm4_aesni_avx_skciphers[] = {
 		.decrypt	= cbc_decrypt,
 	}, {
 		.base = {
-			.cra_name		= "__cfb(sm4)",
-			.cra_driver_name	= "__cfb-sm4-aesni-avx",
-			.cra_priority		= 400,
-			.cra_flags		= CRYPTO_ALG_INTERNAL,
-			.cra_blocksize		= 1,
-			.cra_ctxsize		= sizeof(struct sm4_ctx),
-			.cra_module		= THIS_MODULE,
-		},
-		.min_keysize	= SM4_KEY_SIZE,
-		.max_keysize	= SM4_KEY_SIZE,
-		.ivsize		= SM4_BLOCK_SIZE,
-		.chunksize	= SM4_BLOCK_SIZE,
-		.walksize	= 8 * SM4_BLOCK_SIZE,
-		.setkey		= sm4_skcipher_setkey,
-		.encrypt	= sm4_cfb_encrypt,
-		.decrypt	= cfb_decrypt,
-	}, {
-		.base = {
 			.cra_name		= "__ctr(sm4)",
 			.cra_driver_name	= "__ctr-sm4-aesni-avx",
 			.cra_priority		= 400,
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index f6907627172b..9f1d94790a54 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -175,8 +175,7 @@ For 32-bit we have the following conventions - kernel is built with
 #define THIS_CPU_user_pcid_flush_mask   \
 	PER_CPU_VAR(cpu_tlbstate) + TLB_STATE_user_pcid_flush_mask
 
-.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
-	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+.macro SWITCH_TO_USER_CR3 scratch_reg:req scratch_reg2:req
 	mov	%cr3, \scratch_reg
 
 	ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
@@ -206,13 +205,20 @@ For 32-bit we have the following conventions - kernel is built with
 	/* Flip the PGD to the user version */
 	orq     $(PTI_USER_PGTABLE_MASK), \scratch_reg
 	mov	\scratch_reg, %cr3
+.endm
+
+.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+	SWITCH_TO_USER_CR3 \scratch_reg \scratch_reg2
 .Lend_\@:
 .endm
 
 .macro SWITCH_TO_USER_CR3_STACK	scratch_reg:req
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
 	pushq	%rax
-	SWITCH_TO_USER_CR3_NOSTACK scratch_reg=\scratch_reg scratch_reg2=%rax
+	SWITCH_TO_USER_CR3 scratch_reg=\scratch_reg scratch_reg2=%rax
 	popq	%rax
+.Lend_\@:
 .endm
 
 .macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index d813160b14d8..6356060caaf3 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -26,6 +26,7 @@
 #include <xen/events.h>
 #endif
 
+#include <asm/apic.h>
 #include <asm/desc.h>
 #include <asm/traps.h>
 #include <asm/vdso.h>
@@ -167,7 +168,96 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr)
 	}
 }
 
-/* Handles int $0x80 */
+#ifdef CONFIG_IA32_EMULATION
+static __always_inline bool int80_is_external(void)
+{
+	const unsigned int offs = (0x80 / 32) * 0x10;
+	const u32 bit = BIT(0x80 % 32);
+
+	/* The local APIC on XENPV guests is fake */
+	if (cpu_feature_enabled(X86_FEATURE_XENPV))
+		return false;
+
+	/*
+	 * If vector 0x80 is set in the APIC ISR then this is an external
+	 * interrupt. Either from broken hardware or injected by a VMM.
+	 *
+	 * Note: In guest mode this is only valid for secure guests where
+	 * the secure module fully controls the vAPIC exposed to the guest.
+	 */
+	return apic_read(APIC_ISR + offs) & bit;
+}
+
+/**
+ * int80_emulation - 32-bit legacy syscall entry
+ *
+ * This entry point can be used by 32-bit and 64-bit programs to perform
+ * 32-bit system calls.  Instances of INT $0x80 can be found inline in
+ * various programs and libraries.  It is also used by the vDSO's
+ * __kernel_vsyscall fallback for hardware that doesn't support a faster
+ * entry method.  Restarted 32-bit system calls also fall back to INT
+ * $0x80 regardless of what instruction was originally used to do the
+ * system call.
+ *
+ * This is considered a slow path.  It is not used by most libc
+ * implementations on modern hardware except during process startup.
+ *
+ * The arguments for the INT $0x80 based syscall are on stack in the
+ * pt_regs structure:
+ *   eax:				system call number
+ *   ebx, ecx, edx, esi, edi, ebp:	arg1 - arg 6
+ */
+DEFINE_IDTENTRY_RAW(int80_emulation)
+{
+	int nr;
+
+	/* Kernel does not use INT $0x80! */
+	if (unlikely(!user_mode(regs))) {
+		irqentry_enter(regs);
+		instrumentation_begin();
+		panic("Unexpected external interrupt 0x80\n");
+	}
+
+	/*
+	 * Establish kernel context for instrumentation, including for
+	 * int80_is_external() below which calls into the APIC driver.
+	 * Identical for soft and external interrupts.
+	 */
+	enter_from_user_mode(regs);
+
+	instrumentation_begin();
+	add_random_kstack_offset();
+
+	/* Validate that this is a soft interrupt to the extent possible */
+	if (unlikely(int80_is_external()))
+		panic("Unexpected external interrupt 0x80\n");
+
+	/*
+	 * The low level idtentry code pushed -1 into regs::orig_ax
+	 * and regs::ax contains the syscall number.
+	 *
+	 * User tracing code (ptrace or signal handlers) might assume
+	 * that the regs::orig_ax contains a 32-bit number on invoking
+	 * a 32-bit syscall.
+	 *
+	 * Establish the syscall convention by saving the 32bit truncated
+	 * syscall number in regs::orig_ax and by invalidating regs::ax.
+	 */
+	regs->orig_ax = regs->ax & GENMASK(31, 0);
+	regs->ax = -ENOSYS;
+
+	nr = syscall_32_enter(regs);
+
+	local_irq_enable();
+	nr = syscall_enter_from_user_mode_work(regs, nr);
+	do_syscall_32_irqs_on(regs, nr);
+
+	instrumentation_end();
+	syscall_exit_to_user_mode(regs);
+}
+#else /* CONFIG_IA32_EMULATION */
+
+/* Handles int $0x80 on a 32bit kernel */
 __visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
 {
 	int nr = syscall_32_enter(regs);
@@ -186,6 +276,7 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
 	instrumentation_end();
 	syscall_exit_to_user_mode(regs);
 }
+#endif /* !CONFIG_IA32_EMULATION */
 
 static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
 {
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index de6469dffe3a..c40f89ab1b4c 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -559,17 +559,27 @@ __irqentry_text_end:
 SYM_CODE_START_LOCAL(common_interrupt_return)
 SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 	IBRS_EXIT
-#ifdef CONFIG_DEBUG_ENTRY
-	/* Assert that pt_regs indicates user mode. */
-	testb	$3, CS(%rsp)
-	jnz	1f
-	ud2
-1:
-#endif
 #ifdef CONFIG_XEN_PV
 	ALTERNATIVE "", "jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
 #endif
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	ALTERNATIVE "", "jmp .Lpti_restore_regs_and_return_to_usermode", X86_FEATURE_PTI
+#endif
+
+	STACKLEAK_ERASE
+	POP_REGS
+	add	$8, %rsp	/* orig_ax */
+	UNWIND_HINT_IRET_REGS
+
+.Lswapgs_and_iret:
+	swapgs
+	/* Assert that the IRET frame indicates user mode. */
+	testb	$3, 8(%rsp)
+	jnz	.Lnative_iret
+	ud2
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+.Lpti_restore_regs_and_return_to_usermode:
 	POP_REGS pop_rdi=0
 
 	/*
@@ -596,13 +606,14 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 	 */
 	STACKLEAK_ERASE_NOCLOBBER
 
-	SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+	push	%rax
+	SWITCH_TO_USER_CR3 scratch_reg=%rdi scratch_reg2=%rax
+	pop	%rax
 
 	/* Restore RDI. */
 	popq	%rdi
-	swapgs
-	jmp	.Lnative_iret
-
+	jmp	.Lswapgs_and_iret
+#endif
 
 SYM_INNER_LABEL(restore_regs_and_return_to_kernel, SYM_L_GLOBAL)
 #ifdef CONFIG_DEBUG_ENTRY
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 27c05d08558a..de94e2e84ecc 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -275,80 +275,3 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
 	int3
 SYM_CODE_END(entry_SYSCALL_compat)
-
-/*
- * 32-bit legacy system call entry.
- *
- * 32-bit x86 Linux system calls traditionally used the INT $0x80
- * instruction.  INT $0x80 lands here.
- *
- * This entry point can be used by 32-bit and 64-bit programs to perform
- * 32-bit system calls.  Instances of INT $0x80 can be found inline in
- * various programs and libraries.  It is also used by the vDSO's
- * __kernel_vsyscall fallback for hardware that doesn't support a faster
- * entry method.  Restarted 32-bit system calls also fall back to INT
- * $0x80 regardless of what instruction was originally used to do the
- * system call.
- *
- * This is considered a slow path.  It is not used by most libc
- * implementations on modern hardware except during process startup.
- *
- * Arguments:
- * eax  system call number
- * ebx  arg1
- * ecx  arg2
- * edx  arg3
- * esi  arg4
- * edi  arg5
- * ebp  arg6
- */
-SYM_CODE_START(entry_INT80_compat)
-	UNWIND_HINT_ENTRY
-	ENDBR
-	/*
-	 * Interrupts are off on entry.
-	 */
-	ASM_CLAC			/* Do this early to minimize exposure */
-	ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV
-
-	/*
-	 * User tracing code (ptrace or signal handlers) might assume that
-	 * the saved RAX contains a 32-bit number when we're invoking a 32-bit
-	 * syscall.  Just in case the high bits are nonzero, zero-extend
-	 * the syscall number.  (This could almost certainly be deleted
-	 * with no ill effects.)
-	 */
-	movl	%eax, %eax
-
-	/* switch to thread stack expects orig_ax and rdi to be pushed */
-	pushq	%rax			/* pt_regs->orig_ax */
-
-	/* Need to switch before accessing the thread stack. */
-	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
-
-	/* In the Xen PV case we already run on the thread stack. */
-	ALTERNATIVE "", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV
-
-	movq	%rsp, %rax
-	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp
-
-	pushq	5*8(%rax)		/* regs->ss */
-	pushq	4*8(%rax)		/* regs->rsp */
-	pushq	3*8(%rax)		/* regs->eflags */
-	pushq	2*8(%rax)		/* regs->cs */
-	pushq	1*8(%rax)		/* regs->ip */
-	pushq	0*8(%rax)		/* regs->orig_ax */
-.Lint80_keep_stack:
-
-	PUSH_AND_CLEAR_REGS rax=$-ENOSYS
-	UNWIND_HINT_REGS
-
-	cld
-
-	IBRS_ENTER
-	UNTRAIN_RET
-
-	movq	%rsp, %rdi
-	call	do_int80_syscall_32
-	jmp	swapgs_restore_regs_and_return_to_usermode
-SYM_CODE_END(entry_INT80_compat)
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index c8fac5205803..5f8591ce7f25 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -461,3 +461,8 @@
 454	i386	futex_wake		sys_futex_wake
 455	i386	futex_wait		sys_futex_wait
 456	i386	futex_requeue		sys_futex_requeue
+457	i386	statmount		sys_statmount
+458	i386	listmount		sys_listmount
+459	i386	lsm_get_self_attr	sys_lsm_get_self_attr
+460	i386	lsm_set_self_attr	sys_lsm_set_self_attr
+461	i386	lsm_list_modules	sys_lsm_list_modules
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 8cb8bf68721c..7e8d46f4147f 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -378,6 +378,11 @@
 454	common	futex_wake		sys_futex_wake
 455	common	futex_wait		sys_futex_wait
 456	common	futex_requeue		sys_futex_requeue
+457	common	statmount		sys_statmount
+458	common	listmount		sys_listmount
+459	common	lsm_get_self_attr	sys_lsm_get_self_attr
+460	common	lsm_set_self_attr	sys_lsm_set_self_attr
+461	common	lsm_list_modules	sys_lsm_list_modules
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 7d70935b6758..0debc194bd78 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -11,12 +11,10 @@
 #include <linux/time.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
+#include <vdso/gettime.h>
 
 #include "../../../../lib/vdso/gettimeofday.c"
 
-extern int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
-extern __kernel_old_time_t __vdso_time(__kernel_old_time_t *t);
-
 int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 {
 	return __cvdso_gettimeofday(tv, tz);
@@ -35,9 +33,6 @@ __kernel_old_time_t time(__kernel_old_time_t *t)	__attribute__((weak, alias("__v
 
 #if defined(CONFIG_X86_64) && !defined(BUILD_VDSO32_64)
 /* both 64-bit and x32 use these */
-extern int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
-extern int __vdso_clock_getres(clockid_t clock, struct __kernel_timespec *res);
-
 int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
 {
 	return __cvdso_clock_gettime(clock, ts);
@@ -56,9 +51,6 @@ int clock_getres(clockid_t, struct __kernel_timespec *)
 
 #else
 /* i386 only */
-extern int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts);
-extern int __vdso_clock_getres(clockid_t clock, struct old_timespec32 *res);
-
 int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts)
 {
 	return __cvdso_clock_gettime32(clock, ts);
diff --git a/arch/x86/events/amd/brs.c b/arch/x86/events/amd/brs.c
index ed308719236c..780acd3dff22 100644
--- a/arch/x86/events/amd/brs.c
+++ b/arch/x86/events/amd/brs.c
@@ -125,7 +125,7 @@ int amd_brs_hw_config(struct perf_event *event)
 	 * Where X is the number of taken branches due to interrupt
 	 * skid. Skid is large.
 	 *
-	 * Where Y is the occurences of the event while BRS is
+	 * Where Y is the occurrences of the event while BRS is
 	 * capturing the lbr_nr entries.
 	 *
 	 * By using retired taken branches, we limit the impact on the
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index e24976593a29..81f6d8275b6b 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -940,7 +940,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 			continue;
 
 		if (has_branch_stack(event))
-			perf_sample_save_brstack(&data, event, &cpuc->lbr_stack);
+			perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
 
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);
@@ -1184,7 +1184,7 @@ static void amd_put_event_constraints_f17h(struct cpu_hw_events *cpuc,
  * period of each one and given that the BRS saturates, it would not be possible
  * to guarantee correlated content for all events. Therefore, in situations
  * where multiple events want to use BRS, the kernel enforces mutual exclusion.
- * Exclusion is enforced by chosing only one counter for events using BRS.
+ * Exclusion is enforced by choosing only one counter for events using BRS.
  * The event scheduling logic will then automatically multiplex the
  * events and ensure that at most one event is actively using BRS.
  *
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 6911c5399d02..e91970b01d62 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -287,6 +287,9 @@ static int perf_ibs_init(struct perf_event *event)
 	if (config & ~perf_ibs->config_mask)
 		return -EINVAL;
 
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	ret = validate_group(event);
 	if (ret)
 		return ret;
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 40ad1425ffa2..09050641ce5d 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -601,7 +601,7 @@ int x86_pmu_hw_config(struct perf_event *event)
 		}
 	}
 
-	if (event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK)
+	if (branch_sample_call_stack(event))
 		event->attach_state |= PERF_ATTACH_TASK_DATA;
 
 	/*
@@ -1702,7 +1702,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 		perf_sample_data_init(&data, 0, event->hw.last_period);
 
 		if (has_branch_stack(event))
-			perf_sample_save_brstack(&data, event, &cpuc->lbr_stack);
+			perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
 
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a08f794a0e79..3804f21ab049 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2527,9 +2527,14 @@ static void intel_pmu_assign_event(struct perf_event *event, int idx)
 		perf_report_aux_output_id(event, idx);
 }
 
+static __always_inline bool intel_pmu_needs_branch_stack(struct perf_event *event)
+{
+	return event->hw.flags & PERF_X86_EVENT_NEEDS_BRANCH_STACK;
+}
+
 static void intel_pmu_del_event(struct perf_event *event)
 {
-	if (needs_branch_stack(event))
+	if (intel_pmu_needs_branch_stack(event))
 		intel_pmu_lbr_del(event);
 	if (event->attr.precise_ip)
 		intel_pmu_pebs_del(event);
@@ -2787,6 +2792,7 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
 
 static void intel_pmu_enable_event(struct perf_event *event)
 {
+	u64 enable_mask = ARCH_PERFMON_EVENTSEL_ENABLE;
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
@@ -2795,8 +2801,10 @@ static void intel_pmu_enable_event(struct perf_event *event)
 
 	switch (idx) {
 	case 0 ... INTEL_PMC_IDX_FIXED - 1:
+		if (branch_sample_counters(event))
+			enable_mask |= ARCH_PERFMON_EVENTSEL_BR_CNTR;
 		intel_set_masks(event, idx);
-		__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+		__x86_pmu_enable_event(hwc, enable_mask);
 		break;
 	case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1:
 	case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END:
@@ -2820,7 +2828,7 @@ static void intel_pmu_add_event(struct perf_event *event)
 {
 	if (event->attr.precise_ip)
 		intel_pmu_pebs_add(event);
-	if (needs_branch_stack(event))
+	if (intel_pmu_needs_branch_stack(event))
 		intel_pmu_lbr_add(event);
 }
 
@@ -3047,7 +3055,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 		perf_sample_data_init(&data, 0, event->hw.last_period);
 
 		if (has_branch_stack(event))
-			perf_sample_save_brstack(&data, event, &cpuc->lbr_stack);
+			intel_pmu_lbr_save_brstack(&data, cpuc, event);
 
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);
@@ -3612,6 +3620,13 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 	if (cpuc->excl_cntrs)
 		return intel_get_excl_constraints(cpuc, event, idx, c2);
 
+	/* Not all counters support the branch counter feature. */
+	if (branch_sample_counters(event)) {
+		c2 = dyn_constraint(cpuc, c2, idx);
+		c2->idxmsk64 &= x86_pmu.lbr_counters;
+		c2->weight = hweight64(c2->idxmsk64);
+	}
+
 	return c2;
 }
 
@@ -3897,7 +3912,62 @@ static int intel_pmu_hw_config(struct perf_event *event)
 			x86_pmu.pebs_aliases(event);
 	}
 
-	if (needs_branch_stack(event)) {
+	if (needs_branch_stack(event) && is_sampling_event(event))
+		event->hw.flags  |= PERF_X86_EVENT_NEEDS_BRANCH_STACK;
+
+	if (branch_sample_counters(event)) {
+		struct perf_event *leader, *sibling;
+		int num = 0;
+
+		if (!(x86_pmu.flags & PMU_FL_BR_CNTR) ||
+		    (event->attr.config & ~INTEL_ARCH_EVENT_MASK))
+			return -EINVAL;
+
+		/*
+		 * The branch counter logging is not supported in the call stack
+		 * mode yet, since we cannot simply flush the LBR during e.g.,
+		 * multiplexing. Also, there is no obvious usage with the call
+		 * stack mode. Simply forbids it for now.
+		 *
+		 * If any events in the group enable the branch counter logging
+		 * feature, the group is treated as a branch counter logging
+		 * group, which requires the extra space to store the counters.
+		 */
+		leader = event->group_leader;
+		if (branch_sample_call_stack(leader))
+			return -EINVAL;
+		if (branch_sample_counters(leader))
+			num++;
+		leader->hw.flags |= PERF_X86_EVENT_BRANCH_COUNTERS;
+
+		for_each_sibling_event(sibling, leader) {
+			if (branch_sample_call_stack(sibling))
+				return -EINVAL;
+			if (branch_sample_counters(sibling))
+				num++;
+		}
+
+		if (num > fls(x86_pmu.lbr_counters))
+			return -EINVAL;
+		/*
+		 * Only applying the PERF_SAMPLE_BRANCH_COUNTERS doesn't
+		 * require any branch stack setup.
+		 * Clear the bit to avoid unnecessary branch stack setup.
+		 */
+		if (0 == (event->attr.branch_sample_type &
+			  ~(PERF_SAMPLE_BRANCH_PLM_ALL |
+			    PERF_SAMPLE_BRANCH_COUNTERS)))
+			event->hw.flags  &= ~PERF_X86_EVENT_NEEDS_BRANCH_STACK;
+
+		/*
+		 * Force the leader to be a LBR event. So LBRs can be reset
+		 * with the leader event. See intel_pmu_lbr_del() for details.
+		 */
+		if (!intel_pmu_needs_branch_stack(leader))
+			return -EINVAL;
+	}
+
+	if (intel_pmu_needs_branch_stack(event)) {
 		ret = intel_pmu_setup_lbr_filter(event);
 		if (ret)
 			return ret;
@@ -4027,7 +4097,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
 
 /*
  * Currently, the only caller of this function is the atomic_switch_perf_msrs().
- * The host perf conext helps to prepare the values of the real hardware for
+ * The host perf context helps to prepare the values of the real hardware for
  * a set of msrs that need to be switched atomically in a vmx transaction.
  *
  * For example, the pseudocode needed to add a new msr should look like:
@@ -4051,12 +4121,17 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
 	u64 pebs_mask = cpuc->pebs_enabled & x86_pmu.pebs_capable;
 	int global_ctrl, pebs_enable;
 
+	/*
+	 * In addition to obeying exclude_guest/exclude_host, remove bits being
+	 * used for PEBS when running a guest, because PEBS writes to virtual
+	 * addresses (not physical addresses).
+	 */
 	*nr = 0;
 	global_ctrl = (*nr)++;
 	arr[global_ctrl] = (struct perf_guest_switch_msr){
 		.msr = MSR_CORE_PERF_GLOBAL_CTRL,
 		.host = intel_ctrl & ~cpuc->intel_ctrl_guest_mask,
-		.guest = intel_ctrl & (~cpuc->intel_ctrl_host_mask | ~pebs_mask),
+		.guest = intel_ctrl & ~cpuc->intel_ctrl_host_mask & ~pebs_mask,
 	};
 
 	if (!x86_pmu.pebs)
@@ -4375,8 +4450,13 @@ cmt_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 	 */
 	if (event->attr.precise_ip == 3) {
 		/* Force instruction:ppp on PMC0, 1 and Fixed counter 0 */
-		if (constraint_match(&fixed0_constraint, event->hw.config))
-			return &fixed0_counter0_1_constraint;
+		if (constraint_match(&fixed0_constraint, event->hw.config)) {
+			/* The fixed counter 0 doesn't support LBR event logging. */
+			if (branch_sample_counters(event))
+				return &counter0_1_constraint;
+			else
+				return &fixed0_counter0_1_constraint;
+		}
 
 		switch (c->idxmsk64 & 0x3ull) {
 		case 0x1:
@@ -4555,7 +4635,7 @@ int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
 			goto err;
 	}
 
-	if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA)) {
+	if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA | PMU_FL_BR_CNTR)) {
 		size_t sz = X86_PMC_IDX_MAX * sizeof(struct event_constraint);
 
 		cpuc->constraint_list = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu));
@@ -4660,7 +4740,7 @@ static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
 	if (pmu->intel_cap.pebs_output_pt_available)
 		pmu->pmu.capabilities |= PERF_PMU_CAP_AUX_OUTPUT;
 	else
-		pmu->pmu.capabilities |= ~PERF_PMU_CAP_AUX_OUTPUT;
+		pmu->pmu.capabilities &= ~PERF_PMU_CAP_AUX_OUTPUT;
 
 	intel_pmu_check_event_constraints(pmu->event_constraints,
 					  pmu->num_counters,
@@ -5527,11 +5607,41 @@ static ssize_t branches_show(struct device *cdev,
 
 static DEVICE_ATTR_RO(branches);
 
+static ssize_t branch_counter_nr_show(struct device *cdev,
+				      struct device_attribute *attr,
+				      char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n", fls(x86_pmu.lbr_counters));
+}
+
+static DEVICE_ATTR_RO(branch_counter_nr);
+
+static ssize_t branch_counter_width_show(struct device *cdev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n", LBR_INFO_BR_CNTR_BITS);
+}
+
+static DEVICE_ATTR_RO(branch_counter_width);
+
 static struct attribute *lbr_attrs[] = {
 	&dev_attr_branches.attr,
+	&dev_attr_branch_counter_nr.attr,
+	&dev_attr_branch_counter_width.attr,
 	NULL
 };
 
+static umode_t
+lbr_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+	/* branches */
+	if (i == 0)
+		return x86_pmu.lbr_nr ? attr->mode : 0;
+
+	return (x86_pmu.flags & PMU_FL_BR_CNTR) ? attr->mode : 0;
+}
+
 static char pmu_name_str[30];
 
 static ssize_t pmu_name_show(struct device *cdev,
@@ -5559,6 +5669,15 @@ static struct attribute *intel_pmu_attrs[] = {
 };
 
 static umode_t
+default_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+	if (attr == &dev_attr_allow_tsx_force_abort.attr)
+		return x86_pmu.flags & PMU_FL_TFA ? attr->mode : 0;
+
+	return attr->mode;
+}
+
+static umode_t
 tsx_is_visible(struct kobject *kobj, struct attribute *attr, int i)
 {
 	return boot_cpu_has(X86_FEATURE_RTM) ? attr->mode : 0;
@@ -5580,26 +5699,11 @@ mem_is_visible(struct kobject *kobj, struct attribute *attr, int i)
 }
 
 static umode_t
-lbr_is_visible(struct kobject *kobj, struct attribute *attr, int i)
-{
-	return x86_pmu.lbr_nr ? attr->mode : 0;
-}
-
-static umode_t
 exra_is_visible(struct kobject *kobj, struct attribute *attr, int i)
 {
 	return x86_pmu.version >= 2 ? attr->mode : 0;
 }
 
-static umode_t
-default_is_visible(struct kobject *kobj, struct attribute *attr, int i)
-{
-	if (attr == &dev_attr_allow_tsx_force_abort.attr)
-		return x86_pmu.flags & PMU_FL_TFA ? attr->mode : 0;
-
-	return attr->mode;
-}
-
 static struct attribute_group group_events_td  = {
 	.name = "events",
 };
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index cbeb6d2bf5b4..4b50a3a9818a 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -41,7 +41,7 @@
  *	MSR_CORE_C1_RES: CORE C1 Residency Counter
  *			 perf code: 0x00
  *			 Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL
- *					  MTL
+ *					  MTL,SRF,GRR
  *			 Scope: Core (each processor core has a MSR)
  *	MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
  *			       perf code: 0x01
@@ -52,7 +52,8 @@
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
  *						SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
- *						TGL,TNT,RKL,ADL,RPL,SPR,MTL
+ *						TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF,
+ *						GRR
  *			       Scope: Core
  *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
  *			       perf code: 0x03
@@ -75,7 +76,7 @@
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
  *						SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
- *						TGL,TNT,RKL,ADL,RPL,SPR,MTL
+ *						TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF
  *			       Scope: Package (physical package)
  *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
  *			       perf code: 0x03
@@ -97,6 +98,10 @@
  *			       Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL,
  *						TNT,RKL,ADL,RPL,MTL
  *			       Scope: Package (physical package)
+ *	MSR_MODULE_C6_RES_MS:  Module C6 Residency Counter.
+ *			       perf code: 0x00
+ *			       Available model: SRF,GRR
+ *			       Scope: A cluster of cores shared L2 cache
  *
  */
 
@@ -130,6 +135,7 @@ static ssize_t cstate_get_attr_cpumask(struct device *dev,
 struct cstate_model {
 	unsigned long		core_events;
 	unsigned long		pkg_events;
+	unsigned long		module_events;
 	unsigned long		quirks;
 };
 
@@ -189,20 +195,20 @@ static struct attribute *attrs_empty[] = {
  * "events" group (with empty attrs) before updating
  * it with detected events.
  */
-static struct attribute_group core_events_attr_group = {
+static struct attribute_group cstate_events_attr_group = {
 	.name = "events",
 	.attrs = attrs_empty,
 };
 
-DEFINE_CSTATE_FORMAT_ATTR(core_event, event, "config:0-63");
-static struct attribute *core_format_attrs[] = {
-	&format_attr_core_event.attr,
+DEFINE_CSTATE_FORMAT_ATTR(cstate_event, event, "config:0-63");
+static struct attribute *cstate_format_attrs[] = {
+	&format_attr_cstate_event.attr,
 	NULL,
 };
 
-static struct attribute_group core_format_attr_group = {
+static struct attribute_group cstate_format_attr_group = {
 	.name = "format",
-	.attrs = core_format_attrs,
+	.attrs = cstate_format_attrs,
 };
 
 static cpumask_t cstate_core_cpu_mask;
@@ -217,9 +223,9 @@ static struct attribute_group cpumask_attr_group = {
 	.attrs = cstate_cpumask_attrs,
 };
 
-static const struct attribute_group *core_attr_groups[] = {
-	&core_events_attr_group,
-	&core_format_attr_group,
+static const struct attribute_group *cstate_attr_groups[] = {
+	&cstate_events_attr_group,
+	&cstate_format_attr_group,
 	&cpumask_attr_group,
 	NULL,
 };
@@ -268,30 +274,30 @@ static struct perf_msr pkg_msr[] = {
 	[PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY,	&group_cstate_pkg_c10,	test_msr },
 };
 
-static struct attribute_group pkg_events_attr_group = {
-	.name = "events",
-	.attrs = attrs_empty,
-};
+static cpumask_t cstate_pkg_cpu_mask;
 
-DEFINE_CSTATE_FORMAT_ATTR(pkg_event, event, "config:0-63");
-static struct attribute *pkg_format_attrs[] = {
-	&format_attr_pkg_event.attr,
-	NULL,
-};
-static struct attribute_group pkg_format_attr_group = {
-	.name = "format",
-	.attrs = pkg_format_attrs,
+/* cstate_module PMU */
+static struct pmu cstate_module_pmu;
+static bool has_cstate_module;
+
+enum perf_cstate_module_events {
+	PERF_CSTATE_MODULE_C6_RES = 0,
+
+	PERF_CSTATE_MODULE_EVENT_MAX,
 };
 
-static cpumask_t cstate_pkg_cpu_mask;
+PMU_EVENT_ATTR_STRING(c6-residency, attr_cstate_module_c6, "event=0x00");
 
-static const struct attribute_group *pkg_attr_groups[] = {
-	&pkg_events_attr_group,
-	&pkg_format_attr_group,
-	&cpumask_attr_group,
-	NULL,
+static unsigned long module_msr_mask;
+
+PMU_EVENT_GROUP(events, cstate_module_c6);
+
+static struct perf_msr module_msr[] = {
+	[PERF_CSTATE_MODULE_C6_RES]  = { MSR_MODULE_C6_RES_MS,	&group_cstate_module_c6,	test_msr },
 };
 
+static cpumask_t cstate_module_cpu_mask;
+
 static ssize_t cstate_get_attr_cpumask(struct device *dev,
 				       struct device_attribute *attr,
 				       char *buf)
@@ -302,6 +308,8 @@ static ssize_t cstate_get_attr_cpumask(struct device *dev,
 		return cpumap_print_to_pagebuf(true, buf, &cstate_core_cpu_mask);
 	else if (pmu == &cstate_pkg_pmu)
 		return cpumap_print_to_pagebuf(true, buf, &cstate_pkg_cpu_mask);
+	else if (pmu == &cstate_module_pmu)
+		return cpumap_print_to_pagebuf(true, buf, &cstate_module_cpu_mask);
 	else
 		return 0;
 }
@@ -342,6 +350,15 @@ static int cstate_pmu_event_init(struct perf_event *event)
 		event->hw.event_base = pkg_msr[cfg].msr;
 		cpu = cpumask_any_and(&cstate_pkg_cpu_mask,
 				      topology_die_cpumask(event->cpu));
+	} else if (event->pmu == &cstate_module_pmu) {
+		if (cfg >= PERF_CSTATE_MODULE_EVENT_MAX)
+			return -EINVAL;
+		cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_MODULE_EVENT_MAX);
+		if (!(module_msr_mask & (1 << cfg)))
+			return -EINVAL;
+		event->hw.event_base = module_msr[cfg].msr;
+		cpu = cpumask_any_and(&cstate_module_cpu_mask,
+				      topology_cluster_cpumask(event->cpu));
 	} else {
 		return -ENOENT;
 	}
@@ -429,6 +446,17 @@ static int cstate_cpu_exit(unsigned int cpu)
 			perf_pmu_migrate_context(&cstate_pkg_pmu, cpu, target);
 		}
 	}
+
+	if (has_cstate_module &&
+	    cpumask_test_and_clear_cpu(cpu, &cstate_module_cpu_mask)) {
+
+		target = cpumask_any_but(topology_cluster_cpumask(cpu), cpu);
+		/* Migrate events if there is a valid target */
+		if (target < nr_cpu_ids) {
+			cpumask_set_cpu(target, &cstate_module_cpu_mask);
+			perf_pmu_migrate_context(&cstate_module_pmu, cpu, target);
+		}
+	}
 	return 0;
 }
 
@@ -455,6 +483,15 @@ static int cstate_cpu_init(unsigned int cpu)
 	if (has_cstate_pkg && target >= nr_cpu_ids)
 		cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask);
 
+	/*
+	 * If this is the first online thread of that cluster, set it
+	 * in the cluster cpu mask as the designated reader.
+	 */
+	target = cpumask_any_and(&cstate_module_cpu_mask,
+				 topology_cluster_cpumask(cpu));
+	if (has_cstate_module && target >= nr_cpu_ids)
+		cpumask_set_cpu(cpu, &cstate_module_cpu_mask);
+
 	return 0;
 }
 
@@ -477,8 +514,13 @@ static const struct attribute_group *pkg_attr_update[] = {
 	NULL,
 };
 
+static const struct attribute_group *module_attr_update[] = {
+	&group_cstate_module_c6,
+	NULL
+};
+
 static struct pmu cstate_core_pmu = {
-	.attr_groups	= core_attr_groups,
+	.attr_groups	= cstate_attr_groups,
 	.attr_update	= core_attr_update,
 	.name		= "cstate_core",
 	.task_ctx_nr	= perf_invalid_context,
@@ -493,7 +535,7 @@ static struct pmu cstate_core_pmu = {
 };
 
 static struct pmu cstate_pkg_pmu = {
-	.attr_groups	= pkg_attr_groups,
+	.attr_groups	= cstate_attr_groups,
 	.attr_update	= pkg_attr_update,
 	.name		= "cstate_pkg",
 	.task_ctx_nr	= perf_invalid_context,
@@ -507,6 +549,21 @@ static struct pmu cstate_pkg_pmu = {
 	.module		= THIS_MODULE,
 };
 
+static struct pmu cstate_module_pmu = {
+	.attr_groups	= cstate_attr_groups,
+	.attr_update	= module_attr_update,
+	.name		= "cstate_module",
+	.task_ctx_nr	= perf_invalid_context,
+	.event_init	= cstate_pmu_event_init,
+	.add		= cstate_pmu_event_add,
+	.del		= cstate_pmu_event_del,
+	.start		= cstate_pmu_event_start,
+	.stop		= cstate_pmu_event_stop,
+	.read		= cstate_pmu_event_update,
+	.capabilities	= PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE,
+	.module		= THIS_MODULE,
+};
+
 static const struct cstate_model nhm_cstates __initconst = {
 	.core_events		= BIT(PERF_CSTATE_CORE_C3_RES) |
 				  BIT(PERF_CSTATE_CORE_C6_RES),
@@ -621,6 +678,22 @@ static const struct cstate_model glm_cstates __initconst = {
 				  BIT(PERF_CSTATE_PKG_C10_RES),
 };
 
+static const struct cstate_model grr_cstates __initconst = {
+	.core_events		= BIT(PERF_CSTATE_CORE_C1_RES) |
+				  BIT(PERF_CSTATE_CORE_C6_RES),
+
+	.module_events		= BIT(PERF_CSTATE_MODULE_C6_RES),
+};
+
+static const struct cstate_model srf_cstates __initconst = {
+	.core_events		= BIT(PERF_CSTATE_CORE_C1_RES) |
+				  BIT(PERF_CSTATE_CORE_C6_RES),
+
+	.pkg_events		= BIT(PERF_CSTATE_PKG_C6_RES),
+
+	.module_events		= BIT(PERF_CSTATE_MODULE_C6_RES),
+};
+
 
 static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM,		&nhm_cstates),
@@ -673,6 +746,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT,	&glm_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L,	&glm_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,	&adl_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT_X,	&srf_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT,	&grr_cstates),
 
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		&icl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE,		&icl_cstates),
@@ -714,10 +789,14 @@ static int __init cstate_probe(const struct cstate_model *cm)
 	pkg_msr_mask = perf_msr_probe(pkg_msr, PERF_CSTATE_PKG_EVENT_MAX,
 				      true, (void *) &cm->pkg_events);
 
+	module_msr_mask = perf_msr_probe(module_msr, PERF_CSTATE_MODULE_EVENT_MAX,
+				      true, (void *) &cm->module_events);
+
 	has_cstate_core = !!core_msr_mask;
 	has_cstate_pkg  = !!pkg_msr_mask;
+	has_cstate_module  = !!module_msr_mask;
 
-	return (has_cstate_core || has_cstate_pkg) ? 0 : -ENODEV;
+	return (has_cstate_core || has_cstate_pkg || has_cstate_module) ? 0 : -ENODEV;
 }
 
 static inline void cstate_cleanup(void)
@@ -730,6 +809,9 @@ static inline void cstate_cleanup(void)
 
 	if (has_cstate_pkg)
 		perf_pmu_unregister(&cstate_pkg_pmu);
+
+	if (has_cstate_module)
+		perf_pmu_unregister(&cstate_module_pmu);
 }
 
 static int __init cstate_init(void)
@@ -766,6 +848,16 @@ static int __init cstate_init(void)
 			return err;
 		}
 	}
+
+	if (has_cstate_module) {
+		err = perf_pmu_register(&cstate_module_pmu, cstate_module_pmu.name, -1);
+		if (err) {
+			has_cstate_module = false;
+			pr_info("Failed to register cstate cluster pmu\n");
+			cstate_cleanup();
+			return err;
+		}
+	}
 	return 0;
 }
 
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index bf97ab904d40..d49d661ec0a7 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1755,7 +1755,7 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 		setup_pebs_time(event, data, pebs->tsc);
 
 	if (has_branch_stack(event))
-		perf_sample_save_brstack(data, event, &cpuc->lbr_stack);
+		perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL);
 }
 
 static void adaptive_pebs_save_regs(struct pt_regs *regs,
@@ -1912,7 +1912,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 
 		if (has_branch_stack(event)) {
 			intel_pmu_store_pebs_lbrs(lbr);
-			perf_sample_save_brstack(data, event, &cpuc->lbr_stack);
+			intel_pmu_lbr_save_brstack(data, cpuc, event);
 		}
 	}
 
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index c3b0d15a9841..78cd5084104e 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -676,6 +676,25 @@ void intel_pmu_lbr_del(struct perf_event *event)
 	WARN_ON_ONCE(cpuc->lbr_users < 0);
 	WARN_ON_ONCE(cpuc->lbr_pebs_users < 0);
 	perf_sched_cb_dec(event->pmu);
+
+	/*
+	 * The logged occurrences information is only valid for the
+	 * current LBR group. If another LBR group is scheduled in
+	 * later, the information from the stale LBRs will be wrongly
+	 * interpreted. Reset the LBRs here.
+	 *
+	 * Only clear once for a branch counter group with the leader
+	 * event. Because
+	 * - Cannot simply reset the LBRs with the !cpuc->lbr_users.
+	 *   Because it's possible that the last LBR user is not in a
+	 *   branch counter group, e.g., a branch_counters group +
+	 *   several normal LBR events.
+	 * - The LBR reset can be done with any one of the events in a
+	 *   branch counter group, since they are always scheduled together.
+	 *   It's easy to force the leader event an LBR event.
+	 */
+	if (is_branch_counters_group(event) && event == event->group_leader)
+		intel_pmu_lbr_reset();
 }
 
 static inline bool vlbr_exclude_host(void)
@@ -866,6 +885,8 @@ static __always_inline u16 get_lbr_cycles(u64 info)
 	return cycles;
 }
 
+static_assert((64 - PERF_BRANCH_ENTRY_INFO_BITS_MAX) > LBR_INFO_BR_CNTR_NUM * LBR_INFO_BR_CNTR_BITS);
+
 static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc,
 				struct lbr_entry *entries)
 {
@@ -898,11 +919,67 @@ static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc,
 		e->abort	= !!(info & LBR_INFO_ABORT);
 		e->cycles	= get_lbr_cycles(info);
 		e->type		= get_lbr_br_type(info);
+
+		/*
+		 * Leverage the reserved field of cpuc->lbr_entries[i] to
+		 * temporarily store the branch counters information.
+		 * The later code will decide what content can be disclosed
+		 * to the perf tool. Pleae see intel_pmu_lbr_counters_reorder().
+		 */
+		e->reserved	= (info >> LBR_INFO_BR_CNTR_OFFSET) & LBR_INFO_BR_CNTR_FULL_MASK;
 	}
 
 	cpuc->lbr_stack.nr = i;
 }
 
+/*
+ * The enabled order may be different from the counter order.
+ * Update the lbr_counters with the enabled order.
+ */
+static void intel_pmu_lbr_counters_reorder(struct cpu_hw_events *cpuc,
+					   struct perf_event *event)
+{
+	int i, j, pos = 0, order[X86_PMC_IDX_MAX];
+	struct perf_event *leader, *sibling;
+	u64 src, dst, cnt;
+
+	leader = event->group_leader;
+	if (branch_sample_counters(leader))
+		order[pos++] = leader->hw.idx;
+
+	for_each_sibling_event(sibling, leader) {
+		if (!branch_sample_counters(sibling))
+			continue;
+		order[pos++] = sibling->hw.idx;
+	}
+
+	WARN_ON_ONCE(!pos);
+
+	for (i = 0; i < cpuc->lbr_stack.nr; i++) {
+		src = cpuc->lbr_entries[i].reserved;
+		dst = 0;
+		for (j = 0; j < pos; j++) {
+			cnt = (src >> (order[j] * LBR_INFO_BR_CNTR_BITS)) & LBR_INFO_BR_CNTR_MASK;
+			dst |= cnt << j * LBR_INFO_BR_CNTR_BITS;
+		}
+		cpuc->lbr_counters[i] = dst;
+		cpuc->lbr_entries[i].reserved = 0;
+	}
+}
+
+void intel_pmu_lbr_save_brstack(struct perf_sample_data *data,
+				struct cpu_hw_events *cpuc,
+				struct perf_event *event)
+{
+	if (is_branch_counters_group(event)) {
+		intel_pmu_lbr_counters_reorder(cpuc, event);
+		perf_sample_save_brstack(data, event, &cpuc->lbr_stack, cpuc->lbr_counters);
+		return;
+	}
+
+	perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL);
+}
+
 static void intel_pmu_arch_lbr_read(struct cpu_hw_events *cpuc)
 {
 	intel_pmu_store_lbr(cpuc, NULL);
@@ -1173,8 +1250,10 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
 	for (i = 0; i < cpuc->lbr_stack.nr; ) {
 		if (!cpuc->lbr_entries[i].from) {
 			j = i;
-			while (++j < cpuc->lbr_stack.nr)
+			while (++j < cpuc->lbr_stack.nr) {
 				cpuc->lbr_entries[j-1] = cpuc->lbr_entries[j];
+				cpuc->lbr_counters[j-1] = cpuc->lbr_counters[j];
+			}
 			cpuc->lbr_stack.nr--;
 			if (!cpuc->lbr_entries[i].from)
 				continue;
@@ -1525,8 +1604,12 @@ void __init intel_pmu_arch_lbr_init(void)
 	x86_pmu.lbr_mispred = ecx.split.lbr_mispred;
 	x86_pmu.lbr_timed_lbr = ecx.split.lbr_timed_lbr;
 	x86_pmu.lbr_br_type = ecx.split.lbr_br_type;
+	x86_pmu.lbr_counters = ecx.split.lbr_counters;
 	x86_pmu.lbr_nr = lbr_nr;
 
+	if (!!x86_pmu.lbr_counters)
+		x86_pmu.flags |= PMU_FL_BR_CNTR;
+
 	if (x86_pmu.lbr_mispred)
 		static_branch_enable(&x86_lbr_mispred);
 	if (x86_pmu.lbr_timed_lbr)
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 01023aa5125b..7927c0b832fa 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1814,6 +1814,14 @@ static const struct intel_uncore_init_fun spr_uncore_init __initconst = {
 	.uncore_units_ignore = spr_uncore_units_ignore,
 };
 
+static const struct intel_uncore_init_fun gnr_uncore_init __initconst = {
+	.cpu_init = gnr_uncore_cpu_init,
+	.pci_init = gnr_uncore_pci_init,
+	.mmio_init = gnr_uncore_mmio_init,
+	.use_discovery = true,
+	.uncore_units_ignore = gnr_uncore_units_ignore,
+};
+
 static const struct intel_uncore_init_fun generic_uncore_init __initconst = {
 	.cpu_init = intel_uncore_generic_uncore_cpu_init,
 	.pci_init = intel_uncore_generic_uncore_pci_init,
@@ -1865,8 +1873,12 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L,	&mtl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&spr_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X,	&spr_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_X,	&gnr_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_D,	&gnr_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&snr_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,	&adl_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT_X,	&gnr_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT,	&gnr_uncore_init),
 	{},
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match);
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index c30fb5bb1222..4838502d89ae 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -72,9 +72,9 @@ struct intel_uncore_type {
 	unsigned single_fixed:1;
 	unsigned pair_ctr_ctl:1;
 	union {
-		unsigned *msr_offsets;
-		unsigned *pci_offsets;
-		unsigned *mmio_offsets;
+		u64 *msr_offsets;
+		u64 *pci_offsets;
+		u64 *mmio_offsets;
 	};
 	unsigned *box_ids;
 	struct event_constraint unconstrainted;
@@ -593,6 +593,7 @@ extern struct list_head pci2phy_map_head;
 extern struct pci_extra_dev *uncore_extra_pci_dev;
 extern struct event_constraint uncore_constraint_empty;
 extern int spr_uncore_units_ignore[];
+extern int gnr_uncore_units_ignore[];
 
 /* uncore_snb.c */
 int snb_uncore_pci_init(void);
@@ -634,6 +635,9 @@ void icx_uncore_mmio_init(void);
 int spr_uncore_pci_init(void);
 void spr_uncore_cpu_init(void);
 void spr_uncore_mmio_init(void);
+int gnr_uncore_pci_init(void);
+void gnr_uncore_cpu_init(void);
+void gnr_uncore_mmio_init(void);
 
 /* uncore_nhmex.c */
 void nhmex_uncore_cpu_init(void);
diff --git a/arch/x86/events/intel/uncore_discovery.c b/arch/x86/events/intel/uncore_discovery.c
index cb488e41807c..9a698a92962a 100644
--- a/arch/x86/events/intel/uncore_discovery.c
+++ b/arch/x86/events/intel/uncore_discovery.c
@@ -125,7 +125,8 @@ uncore_insert_box_info(struct uncore_unit_discovery *unit,
 		       int die, bool parsed)
 {
 	struct intel_uncore_discovery_type *type;
-	unsigned int *box_offset, *ids;
+	unsigned int *ids;
+	u64 *box_offset;
 	int i;
 
 	if (!unit->ctl || !unit->ctl_offset || !unit->ctr_offset) {
@@ -153,7 +154,7 @@ uncore_insert_box_info(struct uncore_unit_discovery *unit,
 	if (!type)
 		return;
 
-	box_offset = kcalloc(type->num_boxes + 1, sizeof(unsigned int), GFP_KERNEL);
+	box_offset = kcalloc(type->num_boxes + 1, sizeof(u64), GFP_KERNEL);
 	if (!box_offset)
 		return;
 
diff --git a/arch/x86/events/intel/uncore_discovery.h b/arch/x86/events/intel/uncore_discovery.h
index 6ee80ad3423e..22e769a81103 100644
--- a/arch/x86/events/intel/uncore_discovery.h
+++ b/arch/x86/events/intel/uncore_discovery.h
@@ -125,7 +125,7 @@ struct intel_uncore_discovery_type {
 	u8		ctr_offset;	/* Counter 0 offset */
 	u16		num_boxes;	/* number of boxes for the uncore block */
 	unsigned int	*ids;		/* Box IDs */
-	unsigned int	*box_offset;	/* Box offset */
+	u64		*box_offset;	/* Box offset */
 };
 
 bool intel_uncore_has_discovery_tables(int *ignore);
diff --git a/arch/x86/events/intel/uncore_nhmex.c b/arch/x86/events/intel/uncore_nhmex.c
index 173e2674be6e..56eea2c66cfb 100644
--- a/arch/x86/events/intel/uncore_nhmex.c
+++ b/arch/x86/events/intel/uncore_nhmex.c
@@ -306,7 +306,7 @@ static const struct attribute_group nhmex_uncore_cbox_format_group = {
 };
 
 /* msr offset for each instance of cbox */
-static unsigned nhmex_cbox_msr_offsets[] = {
+static u64 nhmex_cbox_msr_offsets[] = {
 	0x0, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x240, 0x2c0,
 };
 
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 8250f0f59c2b..a96496bef678 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1396,6 +1396,29 @@ err:
 	return ret;
 }
 
+static int topology_gidnid_map(int nodeid, u32 gidnid)
+{
+	int i, die_id = -1;
+
+	/*
+	 * every three bits in the Node ID mapping register maps
+	 * to a particular node.
+	 */
+	for (i = 0; i < 8; i++) {
+		if (nodeid == GIDNIDMAP(gidnid, i)) {
+			if (topology_max_die_per_package() > 1)
+				die_id = i;
+			else
+				die_id = topology_phys_to_logical_pkg(i);
+			if (die_id < 0)
+				die_id = -ENODEV;
+			break;
+		}
+	}
+
+	return die_id;
+}
+
 /*
  * build pci bus to socket mapping
  */
@@ -1435,22 +1458,7 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool
 				break;
 			}
 
-			/*
-			 * every three bits in the Node ID mapping register maps
-			 * to a particular node.
-			 */
-			for (i = 0; i < 8; i++) {
-				if (nodeid == GIDNIDMAP(config, i)) {
-					if (topology_max_die_per_package() > 1)
-						die_id = i;
-					else
-						die_id = topology_phys_to_logical_pkg(i);
-					if (die_id < 0)
-						die_id = -ENODEV;
-					map->pbus_to_dieid[bus] = die_id;
-					break;
-				}
-			}
+			map->pbus_to_dieid[bus] = topology_gidnid_map(nodeid, config);
 			raw_spin_unlock(&pci2phy_map_lock);
 		} else {
 			segment = pci_domain_nr(ubox_dev->bus);
@@ -5278,7 +5286,7 @@ void snr_uncore_mmio_init(void)
 
 /* ICX uncore support */
 
-static unsigned icx_cha_msr_offsets[] = {
+static u64 icx_cha_msr_offsets[] = {
 	0x2a0, 0x2ae, 0x2bc, 0x2ca, 0x2d8, 0x2e6, 0x2f4, 0x302, 0x310,
 	0x31e, 0x32c, 0x33a, 0x348, 0x356, 0x364, 0x372, 0x380, 0x38e,
 	0x3aa, 0x3b8, 0x3c6, 0x3d4, 0x3e2, 0x3f0, 0x3fe, 0x40c, 0x41a,
@@ -5326,7 +5334,7 @@ static struct intel_uncore_type icx_uncore_chabox = {
 	.format_group		= &snr_uncore_chabox_format_group,
 };
 
-static unsigned icx_msr_offsets[] = {
+static u64 icx_msr_offsets[] = {
 	0x0, 0x20, 0x40, 0x90, 0xb0, 0xd0,
 };
 
@@ -5596,7 +5604,7 @@ static int discover_upi_topology(struct intel_uncore_type *type, int ubox_did, i
 	struct pci_dev *ubox = NULL;
 	struct pci_dev *dev = NULL;
 	u32 nid, gid;
-	int i, idx, ret = -EPERM;
+	int idx, lgc_pkg, ret = -EPERM;
 	struct intel_uncore_topology *upi;
 	unsigned int devfn;
 
@@ -5611,20 +5619,21 @@ static int discover_upi_topology(struct intel_uncore_type *type, int ubox_did, i
 			break;
 		}
 
-		for (i = 0; i < 8; i++) {
-			if (nid != GIDNIDMAP(gid, i))
-				continue;
-			for (idx = 0; idx < type->num_boxes; idx++) {
-				upi = &type->topology[nid][idx];
-				devfn = PCI_DEVFN(dev_link0 + idx, ICX_UPI_REGS_ADDR_FUNCTION);
-				dev = pci_get_domain_bus_and_slot(pci_domain_nr(ubox->bus),
-								  ubox->bus->number,
-								  devfn);
-				if (dev) {
-					ret = upi_fill_topology(dev, upi, idx);
-					if (ret)
-						goto err;
-				}
+		lgc_pkg = topology_gidnid_map(nid, gid);
+		if (lgc_pkg < 0) {
+			ret = -EPERM;
+			goto err;
+		}
+		for (idx = 0; idx < type->num_boxes; idx++) {
+			upi = &type->topology[lgc_pkg][idx];
+			devfn = PCI_DEVFN(dev_link0 + idx, ICX_UPI_REGS_ADDR_FUNCTION);
+			dev = pci_get_domain_bus_and_slot(pci_domain_nr(ubox->bus),
+							  ubox->bus->number,
+							  devfn);
+			if (dev) {
+				ret = upi_fill_topology(dev, upi, idx);
+				if (ret)
+					goto err;
 			}
 		}
 	}
@@ -6079,13 +6088,16 @@ static struct uncore_event_desc spr_uncore_imc_events[] = {
 	{ /* end: all zeroes */ },
 };
 
+#define SPR_UNCORE_MMIO_COMMON_FORMAT()				\
+	SPR_UNCORE_COMMON_FORMAT(),				\
+	.ops			= &spr_uncore_mmio_ops
+
 static struct intel_uncore_type spr_uncore_imc = {
-	SPR_UNCORE_COMMON_FORMAT(),
+	SPR_UNCORE_MMIO_COMMON_FORMAT(),
 	.name			= "imc",
 	.fixed_ctr_bits		= 48,
 	.fixed_ctr		= SNR_IMC_MMIO_PMON_FIXED_CTR,
 	.fixed_ctl		= SNR_IMC_MMIO_PMON_FIXED_CTL,
-	.ops			= &spr_uncore_mmio_ops,
 	.event_descs		= spr_uncore_imc_events,
 };
 
@@ -6181,7 +6193,7 @@ static struct intel_uncore_type *spr_uncores[UNCORE_SPR_NUM_UNCORE_TYPES] = {
  */
 #define SPR_UNCORE_UPI_NUM_BOXES	4
 
-static unsigned int spr_upi_pci_offsets[SPR_UNCORE_UPI_NUM_BOXES] = {
+static u64 spr_upi_pci_offsets[SPR_UNCORE_UPI_NUM_BOXES] = {
 	0, 0x8000, 0x10000, 0x18000
 };
 
@@ -6412,7 +6424,8 @@ static void uncore_type_customized_copy(struct intel_uncore_type *to_type,
 
 static struct intel_uncore_type **
 uncore_get_uncores(enum uncore_access_type type_id, int num_extra,
-		    struct intel_uncore_type **extra)
+		   struct intel_uncore_type **extra, int max_num_types,
+		   struct intel_uncore_type **uncores)
 {
 	struct intel_uncore_type **types, **start_types;
 	int i;
@@ -6421,9 +6434,9 @@ uncore_get_uncores(enum uncore_access_type type_id, int num_extra,
 
 	/* Only copy the customized features */
 	for (; *types; types++) {
-		if ((*types)->type_id >= UNCORE_SPR_NUM_UNCORE_TYPES)
+		if ((*types)->type_id >= max_num_types)
 			continue;
-		uncore_type_customized_copy(*types, spr_uncores[(*types)->type_id]);
+		uncore_type_customized_copy(*types, uncores[(*types)->type_id]);
 	}
 
 	for (i = 0; i < num_extra; i++, types++)
@@ -6470,7 +6483,9 @@ void spr_uncore_cpu_init(void)
 
 	uncore_msr_uncores = uncore_get_uncores(UNCORE_ACCESS_MSR,
 						UNCORE_SPR_MSR_EXTRA_UNCORES,
-						spr_msr_uncores);
+						spr_msr_uncores,
+						UNCORE_SPR_NUM_UNCORE_TYPES,
+						spr_uncores);
 
 	type = uncore_find_type_by_id(uncore_msr_uncores, UNCORE_SPR_CHA);
 	if (type) {
@@ -6552,7 +6567,9 @@ int spr_uncore_pci_init(void)
 	spr_update_device_location(UNCORE_SPR_M3UPI);
 	uncore_pci_uncores = uncore_get_uncores(UNCORE_ACCESS_PCI,
 						UNCORE_SPR_PCI_EXTRA_UNCORES,
-						spr_pci_uncores);
+						spr_pci_uncores,
+						UNCORE_SPR_NUM_UNCORE_TYPES,
+						spr_uncores);
 	return 0;
 }
 
@@ -6560,15 +6577,116 @@ void spr_uncore_mmio_init(void)
 {
 	int ret = snbep_pci2phy_map_init(0x3250, SKX_CPUNODEID, SKX_GIDNIDMAP, true);
 
-	if (ret)
-		uncore_mmio_uncores = uncore_get_uncores(UNCORE_ACCESS_MMIO, 0, NULL);
-	else {
+	if (ret) {
+		uncore_mmio_uncores = uncore_get_uncores(UNCORE_ACCESS_MMIO, 0, NULL,
+							 UNCORE_SPR_NUM_UNCORE_TYPES,
+							 spr_uncores);
+	} else {
 		uncore_mmio_uncores = uncore_get_uncores(UNCORE_ACCESS_MMIO,
 							 UNCORE_SPR_MMIO_EXTRA_UNCORES,
-							 spr_mmio_uncores);
+							 spr_mmio_uncores,
+							 UNCORE_SPR_NUM_UNCORE_TYPES,
+							 spr_uncores);
 
 		spr_uncore_imc_free_running.num_boxes = uncore_type_max_boxes(uncore_mmio_uncores, UNCORE_SPR_IMC) / 2;
 	}
 }
 
 /* end of SPR uncore support */
+
+/* GNR uncore support */
+
+#define UNCORE_GNR_NUM_UNCORE_TYPES	23
+#define UNCORE_GNR_TYPE_15		15
+#define UNCORE_GNR_B2UPI		18
+#define UNCORE_GNR_TYPE_21		21
+#define UNCORE_GNR_TYPE_22		22
+
+int gnr_uncore_units_ignore[] = {
+	UNCORE_SPR_UPI,
+	UNCORE_GNR_TYPE_15,
+	UNCORE_GNR_B2UPI,
+	UNCORE_GNR_TYPE_21,
+	UNCORE_GNR_TYPE_22,
+	UNCORE_IGNORE_END
+};
+
+static struct intel_uncore_type gnr_uncore_ubox = {
+	.name			= "ubox",
+	.attr_update		= uncore_alias_groups,
+};
+
+static struct intel_uncore_type gnr_uncore_b2cmi = {
+	SPR_UNCORE_PCI_COMMON_FORMAT(),
+	.name			= "b2cmi",
+};
+
+static struct intel_uncore_type gnr_uncore_b2cxl = {
+	SPR_UNCORE_MMIO_COMMON_FORMAT(),
+	.name			= "b2cxl",
+};
+
+static struct intel_uncore_type gnr_uncore_mdf_sbo = {
+	.name			= "mdf_sbo",
+	.attr_update		= uncore_alias_groups,
+};
+
+static struct intel_uncore_type *gnr_uncores[UNCORE_GNR_NUM_UNCORE_TYPES] = {
+	&spr_uncore_chabox,
+	&spr_uncore_iio,
+	&spr_uncore_irp,
+	NULL,
+	&spr_uncore_pcu,
+	&gnr_uncore_ubox,
+	&spr_uncore_imc,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	&gnr_uncore_b2cmi,
+	&gnr_uncore_b2cxl,
+	NULL,
+	NULL,
+	&gnr_uncore_mdf_sbo,
+	NULL,
+	NULL,
+};
+
+static struct freerunning_counters gnr_iio_freerunning[] = {
+	[SPR_IIO_MSR_IOCLK]	= { 0x290e, 0x01, 0x10, 1, 48 },
+	[SPR_IIO_MSR_BW_IN]	= { 0x360e, 0x10, 0x80, 8, 48 },
+	[SPR_IIO_MSR_BW_OUT]	= { 0x2e0e, 0x10, 0x80, 8, 48 },
+};
+
+void gnr_uncore_cpu_init(void)
+{
+	uncore_msr_uncores = uncore_get_uncores(UNCORE_ACCESS_MSR,
+						UNCORE_SPR_MSR_EXTRA_UNCORES,
+						spr_msr_uncores,
+						UNCORE_GNR_NUM_UNCORE_TYPES,
+						gnr_uncores);
+	spr_uncore_iio_free_running.num_boxes = uncore_type_max_boxes(uncore_msr_uncores, UNCORE_SPR_IIO);
+	spr_uncore_iio_free_running.freerunning = gnr_iio_freerunning;
+}
+
+int gnr_uncore_pci_init(void)
+{
+	uncore_pci_uncores = uncore_get_uncores(UNCORE_ACCESS_PCI, 0, NULL,
+						UNCORE_GNR_NUM_UNCORE_TYPES,
+						gnr_uncores);
+	return 0;
+}
+
+void gnr_uncore_mmio_init(void)
+{
+	uncore_mmio_uncores = uncore_get_uncores(UNCORE_ACCESS_MMIO, 0, NULL,
+						 UNCORE_GNR_NUM_UNCORE_TYPES,
+						 gnr_uncores);
+}
+
+/* end of GNR uncore support */
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 53dd5d495ba6..fb56518356ec 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -110,6 +110,11 @@ static inline bool is_topdown_event(struct perf_event *event)
 	return is_metric_event(event) || is_slots_event(event);
 }
 
+static inline bool is_branch_counters_group(struct perf_event *event)
+{
+	return event->group_leader->hw.flags & PERF_X86_EVENT_BRANCH_COUNTERS;
+}
+
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
 	int refcnt; /* reference count */
@@ -283,6 +288,7 @@ struct cpu_hw_events {
 	int				lbr_pebs_users;
 	struct perf_branch_stack	lbr_stack;
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
+	u64				lbr_counters[MAX_LBR_ENTRIES]; /* branch stack extra */
 	union {
 		struct er_account		*lbr_sel;
 		struct er_account		*lbr_ctl;
@@ -888,6 +894,7 @@ struct x86_pmu {
 	unsigned int	lbr_mispred:1;
 	unsigned int	lbr_timed_lbr:1;
 	unsigned int	lbr_br_type:1;
+	unsigned int	lbr_counters:4;
 
 	void		(*lbr_reset)(void);
 	void		(*lbr_read)(struct cpu_hw_events *cpuc);
@@ -1012,6 +1019,7 @@ do {									\
 #define PMU_FL_INSTR_LATENCY	0x80 /* Support Instruction Latency in PEBS Memory Info Record */
 #define PMU_FL_MEM_LOADS_AUX	0x100 /* Require an auxiliary event for the complete memory info */
 #define PMU_FL_RETIRE_LATENCY	0x200 /* Support Retire Latency in PEBS */
+#define PMU_FL_BR_CNTR		0x400 /* Support branch counter logging */
 
 #define EVENT_VAR(_id)  event_attr_##_id
 #define EVENT_PTR(_id) &event_attr_##_id.attr.attr
@@ -1552,6 +1560,10 @@ void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr);
 
 void intel_ds_init(void);
 
+void intel_pmu_lbr_save_brstack(struct perf_sample_data *data,
+				struct cpu_hw_events *cpuc,
+				struct perf_event *event);
+
 void intel_pmu_lbr_swap_task_ctx(struct perf_event_pmu_context *prev_epc,
 				 struct perf_event_pmu_context *next_epc);
 
diff --git a/arch/x86/events/perf_event_flags.h b/arch/x86/events/perf_event_flags.h
index 1dc19b9b4426..6c977c19f2cd 100644
--- a/arch/x86/events/perf_event_flags.h
+++ b/arch/x86/events/perf_event_flags.h
@@ -20,3 +20,5 @@ PERF_ARCH(TOPDOWN,		0x04000) /* Count Topdown slots/metrics events */
 PERF_ARCH(PEBS_STLAT,		0x08000) /* st+stlat data address sampling */
 PERF_ARCH(AMD_BRS,		0x10000) /* AMD Branch Sampling */
 PERF_ARCH(PEBS_LAT_HYBRID,	0x20000) /* ld and st lat for hybrid */
+PERF_ARCH(NEEDS_BRANCH_STACK,	0x40000) /* require branch stack setup */
+PERF_ARCH(BRANCH_COUNTERS,	0x80000) /* logs the counters in the extra space of each branch */
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index 97bfe5f0531f..5fc45543e955 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -209,7 +209,7 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector,
 
 		/*
 		 * This particular version of the IPI hypercall can
-		 * only target upto 64 CPUs.
+		 * only target up to 64 CPUs.
 		 */
 		if (vcpu >= 64)
 			goto do_ex_hypercall;
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 21556ad87f4b..8f3a4d16bb79 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -15,6 +15,7 @@
 #include <linux/io.h>
 #include <asm/apic.h>
 #include <asm/desc.h>
+#include <asm/e820/api.h>
 #include <asm/sev.h>
 #include <asm/ibt.h>
 #include <asm/hypervisor.h>
@@ -286,15 +287,31 @@ static int hv_cpu_die(unsigned int cpu)
 
 static int __init hv_pci_init(void)
 {
-	int gen2vm = efi_enabled(EFI_BOOT);
+	bool gen2vm = efi_enabled(EFI_BOOT);
 
 	/*
-	 * For Generation-2 VM, we exit from pci_arch_init() by returning 0.
-	 * The purpose is to suppress the harmless warning:
+	 * A Generation-2 VM doesn't support legacy PCI/PCIe, so both
+	 * raw_pci_ops and raw_pci_ext_ops are NULL, and pci_subsys_init() ->
+	 * pcibios_init() doesn't call pcibios_resource_survey() ->
+	 * e820__reserve_resources_late(); as a result, any emulated persistent
+	 * memory of E820_TYPE_PRAM (12) via the kernel parameter
+	 * memmap=nn[KMG]!ss is not added into iomem_resource and hence can't be
+	 * detected by register_e820_pmem(). Fix this by directly calling
+	 * e820__reserve_resources_late() here: e820__reserve_resources_late()
+	 * depends on e820__reserve_resources(), which has been called earlier
+	 * from setup_arch(). Note: e820__reserve_resources_late() also adds
+	 * any memory of E820_TYPE_PMEM (7) into iomem_resource, and
+	 * acpi_nfit_register_region() -> acpi_nfit_insert_resource() ->
+	 * region_intersects() returns REGION_INTERSECTS, so the memory of
+	 * E820_TYPE_PMEM won't get added twice.
+	 *
+	 * We return 0 here so that pci_arch_init() won't print the warning:
 	 * "PCI: Fatal: No config space access function found"
 	 */
-	if (gen2vm)
+	if (gen2vm) {
+		e820__reserve_resources_late();
 		return 0;
+	}
 
 	/* For Generation-1 VM, we'll proceed in pci_arch_init().  */
 	return 1;
diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c
index 42c70d28ef27..3215a4a07408 100644
--- a/arch/x86/hyperv/irqdomain.c
+++ b/arch/x86/hyperv/irqdomain.c
@@ -212,7 +212,7 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 		 * This interrupt is already mapped. Let's unmap first.
 		 *
 		 * We don't use retarget interrupt hypercalls here because
-		 * Microsoft Hypervisor doens't allow root to change the vector
+		 * Microsoft Hypervisor doesn't allow root to change the vector
 		 * or specify VPs outside of the set that is initially used
 		 * during mapping.
 		 */
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index 02e55237d919..7dcbf153ad72 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -144,7 +144,7 @@ void __noreturn hv_ghcb_terminate(unsigned int set, unsigned int reason)
 	/* Tell the hypervisor what went wrong. */
 	val |= GHCB_SEV_TERM_REASON(set, reason);
 
-	/* Request Guest Termination from Hypvervisor */
+	/* Request Guest Termination from Hypervisor */
 	wr_ghcb_msr(val);
 	VMGEXIT();
 
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index c8a7fc23f63c..f896eed4516c 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -16,6 +16,9 @@
 #include <asm/x86_init.h>
 #include <asm/cpufeature.h>
 #include <asm/irq_vectors.h>
+#include <asm/xen/hypervisor.h>
+
+#include <xen/xen.h>
 
 #ifdef CONFIG_ACPI_APEI
 # include <asm/pgtable_types.h>
@@ -127,6 +130,17 @@ static inline void arch_acpi_set_proc_cap_bits(u32 *cap)
 	if (!cpu_has(c, X86_FEATURE_MWAIT) ||
 	    boot_option_idle_override == IDLE_NOMWAIT)
 		*cap &= ~(ACPI_PROC_CAP_C_C1_FFH | ACPI_PROC_CAP_C_C2C3_FFH);
+
+	if (xen_initial_domain()) {
+		/*
+		 * When Linux is running as Xen dom0, the hypervisor is the
+		 * entity in charge of the processor power management, and so
+		 * Xen needs to check the OS capabilities reported in the
+		 * processor capabilities buffer matches what the hypervisor
+		 * driver supports.
+		 */
+		xen_sanitize_proc_cap_bits(cap);
+	}
 }
 
 static inline bool acpi_has_cpu_in_madt(void)
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 65f79092c9d9..fcd20c6dc7f9 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -10,6 +10,9 @@
 
 #define ALT_FLAG_NOT		(1 << 0)
 #define ALT_NOT(feature)	((ALT_FLAG_NOT << ALT_FLAGS_SHIFT) | (feature))
+#define ALT_FLAG_DIRECT_CALL	(1 << 1)
+#define ALT_DIRECT_CALL(feature) ((ALT_FLAG_DIRECT_CALL << ALT_FLAGS_SHIFT) | (feature))
+#define ALT_CALL_ALWAYS		ALT_DIRECT_CALL(X86_FEATURE_ALWAYS)
 
 #ifndef __ASSEMBLY__
 
@@ -86,6 +89,8 @@ struct alt_instr {
 	u8  replacementlen;	/* length of new instruction */
 } __packed;
 
+extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
+
 /*
  * Debug flag that can be tested to see whether alternative
  * instructions were patched in already:
@@ -101,11 +106,10 @@ extern void apply_fineibt(s32 *start_retpoline, s32 *end_retpoine,
 			  s32 *start_cfi, s32 *end_cfi);
 
 struct module;
-struct paravirt_patch_site;
 
 struct callthunk_sites {
 	s32				*call_start, *call_end;
-	struct paravirt_patch_site	*pv_start, *pv_end;
+	struct alt_instr		*alt_start, *alt_end;
 };
 
 #ifdef CONFIG_CALL_THUNKS
@@ -150,6 +154,8 @@ static inline int alternatives_text_reserved(void *start, void *end)
 }
 #endif	/* CONFIG_SMP */
 
+#define ALT_CALL_INSTR		"call BUG_func"
+
 #define b_replacement(num)	"664"#num
 #define e_replacement(num)	"665"#num
 
@@ -330,6 +336,22 @@ static inline int alternatives_text_reserved(void *start, void *end)
  */
 #define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr
 
+/* Macro for creating assembler functions avoiding any C magic. */
+#define DEFINE_ASM_FUNC(func, instr, sec)		\
+	asm (".pushsection " #sec ", \"ax\"\n"		\
+	     ".global " #func "\n\t"			\
+	     ".type " #func ", @function\n\t"		\
+	     ASM_FUNC_ALIGN "\n"			\
+	     #func ":\n\t"				\
+	     ASM_ENDBR					\
+	     instr "\n\t"				\
+	     ASM_RET					\
+	     ".size " #func ", . - " #func "\n\t"	\
+	     ".popsection")
+
+void BUG_func(void);
+void nop_func(void);
+
 #else /* __ASSEMBLY__ */
 
 #ifdef CONFIG_SMP
@@ -370,6 +392,10 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	.byte \alt_len
 .endm
 
+.macro ALT_CALL_INSTR
+	call BUG_func
+.endm
+
 /*
  * Define an alternative between two instructions. If @feature is
  * present, early code in apply_alternatives() replaces @oldinstr with
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index ed0eaf65c437..5c37944c8a5e 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -104,7 +104,7 @@ static inline bool amd_gart_present(void)
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
 		return false;
 
-	/* GART present only on Fam15h, upto model 0fh */
+	/* GART present only on Fam15h, up to model 0fh */
 	if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
 	    (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10))
 		return true;
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index d21f48f1c242..9d159b771dc8 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -272,8 +272,6 @@ struct apic {
 	void	(*send_IPI_all)(int vector);
 	void	(*send_IPI_self)(int vector);
 
-	enum apic_delivery_modes delivery_mode;
-
 	u32	disable_esr		: 1,
 		dest_mode_logical	: 1,
 		x2apic_set_max_apicid	: 1,
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index 4b125e5b3187..094106b6a538 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -20,6 +20,13 @@
  */
 #define IO_APIC_SLOT_SIZE		1024
 
+#define APIC_DELIVERY_MODE_FIXED	0
+#define APIC_DELIVERY_MODE_LOWESTPRIO	1
+#define APIC_DELIVERY_MODE_SMI		2
+#define APIC_DELIVERY_MODE_NMI		4
+#define APIC_DELIVERY_MODE_INIT		5
+#define APIC_DELIVERY_MODE_EXTINT	7
+
 #define	APIC_ID		0x20
 
 #define	APIC_LVR	0x30
@@ -165,279 +172,10 @@
 #define APIC_CPUID(apicid)	((apicid) & XAPIC_DEST_CPUS_MASK)
 #define NUM_APIC_CLUSTERS	((BAD_APICID + 1) >> XAPIC_DEST_CPUS_SHIFT)
 
-#ifndef __ASSEMBLY__
-/*
- * the local APIC register structure, memory mapped. Not terribly well
- * tested, but we might eventually use this one in the future - the
- * problem why we cannot use it right now is the P5 APIC, it has an
- * errata which cannot take 8-bit reads and writes, only 32-bit ones ...
- */
-#define u32 unsigned int
-
-struct local_apic {
-
-/*000*/	struct { u32 __reserved[4]; } __reserved_01;
-
-/*010*/	struct { u32 __reserved[4]; } __reserved_02;
-
-/*020*/	struct { /* APIC ID Register */
-		u32   __reserved_1	: 24,
-			phys_apic_id	:  4,
-			__reserved_2	:  4;
-		u32 __reserved[3];
-	} id;
-
-/*030*/	const
-	struct { /* APIC Version Register */
-		u32   version		:  8,
-			__reserved_1	:  8,
-			max_lvt		:  8,
-			__reserved_2	:  8;
-		u32 __reserved[3];
-	} version;
-
-/*040*/	struct { u32 __reserved[4]; } __reserved_03;
-
-/*050*/	struct { u32 __reserved[4]; } __reserved_04;
-
-/*060*/	struct { u32 __reserved[4]; } __reserved_05;
-
-/*070*/	struct { u32 __reserved[4]; } __reserved_06;
-
-/*080*/	struct { /* Task Priority Register */
-		u32   priority	:  8,
-			__reserved_1	: 24;
-		u32 __reserved_2[3];
-	} tpr;
-
-/*090*/	const
-	struct { /* Arbitration Priority Register */
-		u32   priority	:  8,
-			__reserved_1	: 24;
-		u32 __reserved_2[3];
-	} apr;
-
-/*0A0*/	const
-	struct { /* Processor Priority Register */
-		u32   priority	:  8,
-			__reserved_1	: 24;
-		u32 __reserved_2[3];
-	} ppr;
-
-/*0B0*/	struct { /* End Of Interrupt Register */
-		u32   eoi;
-		u32 __reserved[3];
-	} eoi;
-
-/*0C0*/	struct { u32 __reserved[4]; } __reserved_07;
-
-/*0D0*/	struct { /* Logical Destination Register */
-		u32   __reserved_1	: 24,
-			logical_dest	:  8;
-		u32 __reserved_2[3];
-	} ldr;
-
-/*0E0*/	struct { /* Destination Format Register */
-		u32   __reserved_1	: 28,
-			model		:  4;
-		u32 __reserved_2[3];
-	} dfr;
-
-/*0F0*/	struct { /* Spurious Interrupt Vector Register */
-		u32	spurious_vector	:  8,
-			apic_enabled	:  1,
-			focus_cpu	:  1,
-			__reserved_2	: 22;
-		u32 __reserved_3[3];
-	} svr;
-
-/*100*/	struct { /* In Service Register */
-/*170*/		u32 bitfield;
-		u32 __reserved[3];
-	} isr [8];
-
-/*180*/	struct { /* Trigger Mode Register */
-/*1F0*/		u32 bitfield;
-		u32 __reserved[3];
-	} tmr [8];
-
-/*200*/	struct { /* Interrupt Request Register */
-/*270*/		u32 bitfield;
-		u32 __reserved[3];
-	} irr [8];
-
-/*280*/	union { /* Error Status Register */
-		struct {
-			u32   send_cs_error			:  1,
-				receive_cs_error		:  1,
-				send_accept_error		:  1,
-				receive_accept_error		:  1,
-				__reserved_1			:  1,
-				send_illegal_vector		:  1,
-				receive_illegal_vector		:  1,
-				illegal_register_address	:  1,
-				__reserved_2			: 24;
-			u32 __reserved_3[3];
-		} error_bits;
-		struct {
-			u32 errors;
-			u32 __reserved_3[3];
-		} all_errors;
-	} esr;
-
-/*290*/	struct { u32 __reserved[4]; } __reserved_08;
-
-/*2A0*/	struct { u32 __reserved[4]; } __reserved_09;
-
-/*2B0*/	struct { u32 __reserved[4]; } __reserved_10;
-
-/*2C0*/	struct { u32 __reserved[4]; } __reserved_11;
-
-/*2D0*/	struct { u32 __reserved[4]; } __reserved_12;
-
-/*2E0*/	struct { u32 __reserved[4]; } __reserved_13;
-
-/*2F0*/	struct { u32 __reserved[4]; } __reserved_14;
-
-/*300*/	struct { /* Interrupt Command Register 1 */
-		u32   vector			:  8,
-			delivery_mode		:  3,
-			destination_mode	:  1,
-			delivery_status		:  1,
-			__reserved_1		:  1,
-			level			:  1,
-			trigger			:  1,
-			__reserved_2		:  2,
-			shorthand		:  2,
-			__reserved_3		:  12;
-		u32 __reserved_4[3];
-	} icr1;
-
-/*310*/	struct { /* Interrupt Command Register 2 */
-		union {
-			u32   __reserved_1	: 24,
-				phys_dest	:  4,
-				__reserved_2	:  4;
-			u32   __reserved_3	: 24,
-				logical_dest	:  8;
-		} dest;
-		u32 __reserved_4[3];
-	} icr2;
-
-/*320*/	struct { /* LVT - Timer */
-		u32   vector		:  8,
-			__reserved_1	:  4,
-			delivery_status	:  1,
-			__reserved_2	:  3,
-			mask		:  1,
-			timer_mode	:  1,
-			__reserved_3	: 14;
-		u32 __reserved_4[3];
-	} lvt_timer;
-
-/*330*/	struct { /* LVT - Thermal Sensor */
-		u32  vector		:  8,
-			delivery_mode	:  3,
-			__reserved_1	:  1,
-			delivery_status	:  1,
-			__reserved_2	:  3,
-			mask		:  1,
-			__reserved_3	: 15;
-		u32 __reserved_4[3];
-	} lvt_thermal;
-
-/*340*/	struct { /* LVT - Performance Counter */
-		u32   vector		:  8,
-			delivery_mode	:  3,
-			__reserved_1	:  1,
-			delivery_status	:  1,
-			__reserved_2	:  3,
-			mask		:  1,
-			__reserved_3	: 15;
-		u32 __reserved_4[3];
-	} lvt_pc;
-
-/*350*/	struct { /* LVT - LINT0 */
-		u32   vector		:  8,
-			delivery_mode	:  3,
-			__reserved_1	:  1,
-			delivery_status	:  1,
-			polarity	:  1,
-			remote_irr	:  1,
-			trigger		:  1,
-			mask		:  1,
-			__reserved_2	: 15;
-		u32 __reserved_3[3];
-	} lvt_lint0;
-
-/*360*/	struct { /* LVT - LINT1 */
-		u32   vector		:  8,
-			delivery_mode	:  3,
-			__reserved_1	:  1,
-			delivery_status	:  1,
-			polarity	:  1,
-			remote_irr	:  1,
-			trigger		:  1,
-			mask		:  1,
-			__reserved_2	: 15;
-		u32 __reserved_3[3];
-	} lvt_lint1;
-
-/*370*/	struct { /* LVT - Error */
-		u32   vector		:  8,
-			__reserved_1	:  4,
-			delivery_status	:  1,
-			__reserved_2	:  3,
-			mask		:  1,
-			__reserved_3	: 15;
-		u32 __reserved_4[3];
-	} lvt_error;
-
-/*380*/	struct { /* Timer Initial Count Register */
-		u32   initial_count;
-		u32 __reserved_2[3];
-	} timer_icr;
-
-/*390*/	const
-	struct { /* Timer Current Count Register */
-		u32   curr_count;
-		u32 __reserved_2[3];
-	} timer_ccr;
-
-/*3A0*/	struct { u32 __reserved[4]; } __reserved_16;
-
-/*3B0*/	struct { u32 __reserved[4]; } __reserved_17;
-
-/*3C0*/	struct { u32 __reserved[4]; } __reserved_18;
-
-/*3D0*/	struct { u32 __reserved[4]; } __reserved_19;
-
-/*3E0*/	struct { /* Timer Divide Configuration Register */
-		u32   divisor		:  4,
-			__reserved_1	: 28;
-		u32 __reserved_2[3];
-	} timer_dcr;
-
-/*3F0*/	struct { u32 __reserved[4]; } __reserved_20;
-
-} __attribute__ ((packed));
-
-#undef u32
-
 #ifdef CONFIG_X86_32
  #define BAD_APICID 0xFFu
 #else
  #define BAD_APICID 0xFFFFu
 #endif
 
-enum apic_delivery_modes {
-	APIC_DELIVERY_MODE_FIXED	= 0,
-	APIC_DELIVERY_MODE_LOWESTPRIO   = 1,
-	APIC_DELIVERY_MODE_SMI		= 2,
-	APIC_DELIVERY_MODE_NMI		= 4,
-	APIC_DELIVERY_MODE_INIT		= 5,
-	APIC_DELIVERY_MODE_EXTINT	= 7,
-};
-
-#endif /* !__ASSEMBLY__ */
 #endif /* _ASM_X86_APICDEF_H */
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 35389b2af88e..0216f63a366b 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -81,22 +81,4 @@ do {									\
 
 #include <asm-generic/barrier.h>
 
-/*
- * Make previous memory operations globally visible before
- * a WRMSR.
- *
- * MFENCE makes writes visible, but only affects load/store
- * instructions.  WRMSR is unfortunately not a load/store
- * instruction and is unaffected by MFENCE.  The LFENCE ensures
- * that the WRMSR is not reordered.
- *
- * Most WRMSRs are full serializing instructions themselves and
- * do not require this barrier.  This is only required for the
- * IA32_TSC_DEADLINE and X2APIC MSRs.
- */
-static inline void weak_wrmsr_fence(void)
-{
-	asm volatile("mfence; lfence" : : : "memory");
-}
-
 #endif /* _ASM_X86_BARRIER_H */
diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
index 58dacd90daef..7cd752557905 100644
--- a/arch/x86/include/asm/cfi.h
+++ b/arch/x86/include/asm/cfi.h
@@ -7,16 +7,140 @@
  *
  * Copyright (C) 2022 Google LLC
  */
+#include <linux/bug.h>
+#include <asm/ibt.h>
 
-#include <linux/cfi.h>
+/*
+ * An overview of the various calling conventions...
+ *
+ * Traditional:
+ *
+ * foo:
+ *   ... code here ...
+ *   ret
+ *
+ * direct caller:
+ *   call foo
+ *
+ * indirect caller:
+ *   lea foo(%rip), %r11
+ *   ...
+ *   call *%r11
+ *
+ *
+ * IBT:
+ *
+ * foo:
+ *   endbr64
+ *   ... code here ...
+ *   ret
+ *
+ * direct caller:
+ *   call foo / call foo+4
+ *
+ * indirect caller:
+ *   lea foo(%rip), %r11
+ *   ...
+ *   call *%r11
+ *
+ *
+ * kCFI:
+ *
+ * __cfi_foo:
+ *   movl $0x12345678, %eax
+ *				# 11 nops when CONFIG_CALL_PADDING
+ * foo:
+ *   endbr64			# when IBT
+ *   ... code here ...
+ *   ret
+ *
+ * direct call:
+ *   call foo			# / call foo+4 when IBT
+ *
+ * indirect call:
+ *   lea foo(%rip), %r11
+ *   ...
+ *   movl $(-0x12345678), %r10d
+ *   addl -4(%r11), %r10d	# -15 when CONFIG_CALL_PADDING
+ *   jz   1f
+ *   ud2
+ * 1:call *%r11
+ *
+ *
+ * FineIBT (builds as kCFI + CALL_PADDING + IBT + RETPOLINE and runtime patches into):
+ *
+ * __cfi_foo:
+ *   endbr64
+ *   subl 0x12345678, %r10d
+ *   jz   foo
+ *   ud2
+ *   nop
+ * foo:
+ *   osp nop3			# was endbr64
+ *   ... code here ...
+ *   ret
+ *
+ * direct caller:
+ *   call foo / call foo+4
+ *
+ * indirect caller:
+ *   lea foo(%rip), %r11
+ *   ...
+ *   movl $0x12345678, %r10d
+ *   subl $16, %r11
+ *   nop4
+ *   call *%r11
+ *
+ */
+enum cfi_mode {
+	CFI_DEFAULT,	/* FineIBT if hardware has IBT, otherwise kCFI */
+	CFI_OFF,	/* Taditional / IBT depending on .config */
+	CFI_KCFI,	/* Optionally CALL_PADDING, IBT, RETPOLINE */
+	CFI_FINEIBT,	/* see arch/x86/kernel/alternative.c */
+};
+
+extern enum cfi_mode cfi_mode;
+
+struct pt_regs;
 
 #ifdef CONFIG_CFI_CLANG
 enum bug_trap_type handle_cfi_failure(struct pt_regs *regs);
+#define __bpfcall
+extern u32 cfi_bpf_hash;
+extern u32 cfi_bpf_subprog_hash;
+
+static inline int cfi_get_offset(void)
+{
+	switch (cfi_mode) {
+	case CFI_FINEIBT:
+		return 16;
+	case CFI_KCFI:
+		if (IS_ENABLED(CONFIG_CALL_PADDING))
+			return 16;
+		return 5;
+	default:
+		return 0;
+	}
+}
+#define cfi_get_offset cfi_get_offset
+
+extern u32 cfi_get_func_hash(void *func);
+
 #else
 static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
 {
 	return BUG_TRAP_TYPE_NONE;
 }
+#define cfi_bpf_hash 0U
+#define cfi_bpf_subprog_hash 0U
+static inline u32 cfi_get_func_hash(void *func)
+{
+	return 0;
+}
 #endif /* CONFIG_CFI_CLANG */
 
+#if HAS_KERNEL_IBT == 1
+#define CFI_NOSEAL(x)	asm(IBT_NOSEAL(__stringify(x)))
+#endif
+
 #endif /* _ASM_X86_CFI_H */
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 4af140cf5719..632c26cdeeda 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -218,7 +218,7 @@
 #define X86_FEATURE_IBRS		( 7*32+25) /* Indirect Branch Restricted Speculation */
 #define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
 #define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
-#define X86_FEATURE_ZEN			(7*32+28) /* "" CPU based on Zen microarchitecture */
+#define X86_FEATURE_ZEN			( 7*32+28) /* "" Generic flag for all Zen and newer */
 #define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* "" L1TF workaround PTE inversion */
 #define X86_FEATURE_IBRS_ENHANCED	( 7*32+30) /* Enhanced IBRS */
 #define X86_FEATURE_MSR_IA32_FEAT_CTL	( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */
@@ -308,10 +308,14 @@
 #define X86_FEATURE_SMBA		(11*32+21) /* "" Slow Memory Bandwidth Allocation */
 #define X86_FEATURE_BMEC		(11*32+22) /* "" Bandwidth Monitoring Event Configuration */
 #define X86_FEATURE_USER_SHSTK		(11*32+23) /* Shadow stack support for user mode applications */
-
 #define X86_FEATURE_SRSO		(11*32+24) /* "" AMD BTB untrain RETs */
 #define X86_FEATURE_SRSO_ALIAS		(11*32+25) /* "" AMD BTB untrain RETs through aliasing */
 #define X86_FEATURE_IBPB_ON_VMEXIT	(11*32+26) /* "" Issue an IBPB only on VMEXIT */
+#define X86_FEATURE_APIC_MSRS_FENCE	(11*32+27) /* "" IA32_TSC_DEADLINE and X2APIC MSRs need fencing */
+#define X86_FEATURE_ZEN2		(11*32+28) /* "" CPU based on Zen2 microarchitecture */
+#define X86_FEATURE_ZEN3		(11*32+29) /* "" CPU based on Zen3 microarchitecture */
+#define X86_FEATURE_ZEN4		(11*32+30) /* "" CPU based on Zen4 microarchitecture */
+#define X86_FEATURE_ZEN1		(11*32+31) /* "" CPU based on Zen1 microarchitecture */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index a1168e7b69e5..dd4b67101bb7 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -2,6 +2,7 @@
 #ifndef _ASM_X86_CURRENT_H
 #define _ASM_X86_CURRENT_H
 
+#include <linux/build_bug.h>
 #include <linux/compiler.h>
 
 #ifndef __ASSEMBLY__
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 66eb5e1ac4fb..0cec92c430cc 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -5,6 +5,7 @@
 #include <linux/bug.h>
 #include <linux/percpu.h>
 #include <uapi/asm/debugreg.h>
+#include <asm/cpufeature.h>
 
 DECLARE_PER_CPU(unsigned long, cpu_dr7);
 
diff --git a/arch/x86/include/asm/desc_defs.h b/arch/x86/include/asm/desc_defs.h
index f7e7099af595..d440a65af8f3 100644
--- a/arch/x86/include/asm/desc_defs.h
+++ b/arch/x86/include/asm/desc_defs.h
@@ -8,6 +8,56 @@
  * archs.
  */
 
+/*
+ * Low-level interface mapping flags/field names to bits
+ */
+
+/* Flags for _DESC_S (non-system) descriptors */
+#define _DESC_ACCESSED		0x0001
+#define _DESC_DATA_WRITABLE	0x0002
+#define _DESC_CODE_READABLE	0x0002
+#define _DESC_DATA_EXPAND_DOWN	0x0004
+#define _DESC_CODE_CONFORMING	0x0004
+#define _DESC_CODE_EXECUTABLE	0x0008
+
+/* Common flags */
+#define _DESC_S			0x0010
+#define _DESC_DPL(dpl)		((dpl) << 5)
+#define _DESC_PRESENT		0x0080
+
+#define _DESC_LONG_CODE		0x2000
+#define _DESC_DB		0x4000
+#define _DESC_GRANULARITY_4K	0x8000
+
+/* System descriptors have a numeric "type" field instead of flags */
+#define _DESC_SYSTEM(code)	(code)
+
+/*
+ * High-level interface mapping intended usage to low-level combinations
+ * of flags
+ */
+
+#define _DESC_DATA		(_DESC_S | _DESC_PRESENT | _DESC_ACCESSED | \
+				 _DESC_DATA_WRITABLE)
+#define _DESC_CODE		(_DESC_S | _DESC_PRESENT | _DESC_ACCESSED | \
+				 _DESC_CODE_READABLE | _DESC_CODE_EXECUTABLE)
+
+#define DESC_DATA16		(_DESC_DATA)
+#define DESC_CODE16		(_DESC_CODE)
+
+#define DESC_DATA32		(_DESC_DATA | _DESC_GRANULARITY_4K | _DESC_DB)
+#define DESC_DATA32_BIOS	(_DESC_DATA | _DESC_DB)
+
+#define DESC_CODE32		(_DESC_CODE | _DESC_GRANULARITY_4K | _DESC_DB)
+#define DESC_CODE32_BIOS	(_DESC_CODE | _DESC_DB)
+
+#define DESC_TSS32		(_DESC_SYSTEM(9) | _DESC_PRESENT)
+
+#define DESC_DATA64		(_DESC_DATA | _DESC_GRANULARITY_4K | _DESC_DB)
+#define DESC_CODE64		(_DESC_CODE | _DESC_GRANULARITY_4K | _DESC_LONG_CODE)
+
+#define DESC_USER		(_DESC_DPL(3))
+
 #ifndef __ASSEMBLY__
 
 #include <linux/types.h>
@@ -22,19 +72,19 @@ struct desc_struct {
 
 #define GDT_ENTRY_INIT(flags, base, limit)			\
 	{							\
-		.limit0		= (u16) (limit),		\
-		.limit1		= ((limit) >> 16) & 0x0F,	\
-		.base0		= (u16) (base),			\
-		.base1		= ((base) >> 16) & 0xFF,	\
-		.base2		= ((base) >> 24) & 0xFF,	\
-		.type		= (flags & 0x0f),		\
-		.s		= (flags >> 4) & 0x01,		\
-		.dpl		= (flags >> 5) & 0x03,		\
-		.p		= (flags >> 7) & 0x01,		\
-		.avl		= (flags >> 12) & 0x01,		\
-		.l		= (flags >> 13) & 0x01,		\
-		.d		= (flags >> 14) & 0x01,		\
-		.g		= (flags >> 15) & 0x01,		\
+		.limit0		= ((limit) >>  0) & 0xFFFF,	\
+		.limit1		= ((limit) >> 16) & 0x000F,	\
+		.base0		= ((base)  >>  0) & 0xFFFF,	\
+		.base1		= ((base)  >> 16) & 0x00FF,	\
+		.base2		= ((base)  >> 24) & 0x00FF,	\
+		.type		= ((flags) >>  0) & 0x000F,	\
+		.s		= ((flags) >>  4) & 0x0001,	\
+		.dpl		= ((flags) >>  5) & 0x0003,	\
+		.p		= ((flags) >>  7) & 0x0001,	\
+		.avl		= ((flags) >> 12) & 0x0001,	\
+		.l		= ((flags) >> 13) & 0x0001,	\
+		.d		= ((flags) >> 14) & 0x0001,	\
+		.g		= ((flags) >> 15) & 0x0001,	\
 	}
 
 enum {
@@ -94,6 +144,7 @@ struct gate_struct {
 
 typedef struct gate_struct gate_desc;
 
+#ifndef _SETUP
 static inline unsigned long gate_offset(const gate_desc *g)
 {
 #ifdef CONFIG_X86_64
@@ -108,6 +159,7 @@ static inline unsigned long gate_segment(const gate_desc *g)
 {
 	return g->segment;
 }
+#endif
 
 struct desc_ptr {
 	unsigned short size;
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index a0234dfd1031..1e16bd5ac781 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -150,7 +150,7 @@ do {						\
 	((x)->e_machine == EM_X86_64)
 
 #define compat_elf_check_arch(x)					\
-	((elf_check_arch_ia32(x) && ia32_enabled()) ||			\
+	((elf_check_arch_ia32(x) && ia32_enabled_verbose()) ||		\
 	 (IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64))
 
 static inline void elf_common_init(struct thread_struct *t,
diff --git a/arch/x86/include/asm/extable_fixup_types.h b/arch/x86/include/asm/extable_fixup_types.h
index 991e31cfde94..fe6312045042 100644
--- a/arch/x86/include/asm/extable_fixup_types.h
+++ b/arch/x86/include/asm/extable_fixup_types.h
@@ -4,7 +4,7 @@
 
 /*
  * Our IMM is signed, as such it must live at the top end of the word. Also,
- * since C99 hex constants are of ambigious type, force cast the mask to 'int'
+ * since C99 hex constants are of ambiguous type, force cast the mask to 'int'
  * so that FIELD_GET() will DTRT and sign extend the value when it extracts it.
  */
 #define EX_DATA_TYPE_MASK		((int)0x000000FF)
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index eb810074f1e7..ace9aa3b78a3 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -5,6 +5,8 @@
 #ifndef _ASM_X86_FPU_H
 #define _ASM_X86_FPU_H
 
+#include <asm/page_types.h>
+
 /*
  * The legacy x87 FPU state format, as saved by FSAVE and
  * restored by the FRSTOR instructions:
@@ -415,7 +417,7 @@ struct fpu_state_perm {
 	 *
 	 * This master permission field is only to be used when
 	 * task.fpu.fpstate based checks fail to validate whether the task
-	 * is allowed to expand it's xfeatures set which requires to
+	 * is allowed to expand its xfeatures set which requires to
 	 * allocate a larger sized fpstate buffer.
 	 *
 	 * Do not access this field directly.  Use the provided helper
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index 5a2ae24b1204..c7ef6ea2fa99 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -2,7 +2,6 @@
 #ifndef _ASM_X86_IA32_H
 #define _ASM_X86_IA32_H
 
-
 #ifdef CONFIG_IA32_EMULATION
 
 #include <linux/compat.h>
@@ -75,6 +74,11 @@ static inline bool ia32_enabled(void)
 	return __ia32_enabled;
 }
 
+static inline void ia32_disable(void)
+{
+	__ia32_enabled = false;
+}
+
 #else /* !CONFIG_IA32_EMULATION */
 
 static inline bool ia32_enabled(void)
@@ -82,6 +86,18 @@ static inline bool ia32_enabled(void)
 	return IS_ENABLED(CONFIG_X86_32);
 }
 
+static inline void ia32_disable(void) {}
+
 #endif
 
+static inline bool ia32_enabled_verbose(void)
+{
+	bool enabled = ia32_enabled();
+
+	if (IS_ENABLED(CONFIG_IA32_EMULATION) && !enabled)
+		pr_notice_once("32-bit emulation disabled. You can reenable with ia32_emulation=on\n");
+
+	return enabled;
+}
+
 #endif /* _ASM_X86_IA32_H */
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 05fd175cec7d..13639e57e1f8 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -569,6 +569,10 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_UD,		exc_invalid_op);
 DECLARE_IDTENTRY_RAW(X86_TRAP_BP,		exc_int3);
 DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_PF,	exc_page_fault);
 
+#if defined(CONFIG_IA32_EMULATION)
+DECLARE_IDTENTRY_RAW(IA32_SYSCALL_VECTOR,	int80_emulation);
+#endif
+
 #ifdef CONFIG_X86_MCE
 #ifdef CONFIG_X86_64
 DECLARE_IDTENTRY_MCE(X86_TRAP_MC,	exc_machine_check);
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 76238842406a..3814a9263d64 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -242,7 +242,7 @@ static inline void slow_down_io(void)
 
 #endif
 
-#define BUILDIO(bwl, bw, type)						\
+#define BUILDIO(bwl, type)						\
 static inline void out##bwl##_p(type value, u16 port)			\
 {									\
 	out##bwl(value, port);						\
@@ -288,9 +288,9 @@ static inline void ins##bwl(u16 port, void *addr, unsigned long count)	\
 	}								\
 }
 
-BUILDIO(b, b, u8)
-BUILDIO(w, w, u16)
-BUILDIO(l,  , u32)
+BUILDIO(b, u8)
+BUILDIO(w, u16)
+BUILDIO(l, u32)
 #undef BUILDIO
 
 #define inb_p inb_p
diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h
index a1911fea8739..af7541c11821 100644
--- a/arch/x86/include/asm/iosf_mbi.h
+++ b/arch/x86/include/asm/iosf_mbi.h
@@ -111,7 +111,7 @@ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask);
  * This function will block all kernel access to the PMIC I2C bus, so that the
  * P-Unit can safely access the PMIC over the shared I2C bus.
  *
- * Note on these systems the i2c-bus driver will request a sempahore from the
+ * Note on these systems the i2c-bus driver will request a semaphore from the
  * P-Unit for exclusive access to the PMIC bus when i2c drivers are accessing
  * it, but this does not appear to be sufficient, we still need to avoid making
  * certain P-Unit requests during the access window to avoid problems.
diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h
index 800ffce0db29..6b4d36c95165 100644
--- a/arch/x86/include/asm/irq_work.h
+++ b/arch/x86/include/asm/irq_work.h
@@ -9,7 +9,6 @@ static inline bool arch_irq_work_has_interrupt(void)
 {
 	return boot_cpu_has(X86_FEATURE_APIC);
 }
-extern void arch_irq_work_raise(void);
 #else
 static inline bool arch_irq_work_has_interrupt(void)
 {
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d7036982332e..6711da000bb7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1652,7 +1652,7 @@ struct kvm_x86_ops {
 	/* Whether or not a virtual NMI is pending in hardware. */
 	bool (*is_vnmi_pending)(struct kvm_vcpu *vcpu);
 	/*
-	 * Attempt to pend a virtual NMI in harware.  Returns %true on success
+	 * Attempt to pend a virtual NMI in hardware.  Returns %true on success
 	 * to allow using static_call_ret0 as the fallback.
 	 */
 	bool (*set_vnmi_pending)(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 6de6e1d95952..de3118305838 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -311,6 +311,7 @@ enum smca_bank_types {
 	SMCA_PIE,	/* Power, Interrupts, etc. */
 	SMCA_UMC,	/* Unified Memory Controller */
 	SMCA_UMC_V2,
+	SMCA_MA_LLC,	/* Memory Attached Last Level Cache */
 	SMCA_PB,	/* Parameter Block */
 	SMCA_PSP,	/* Platform Security Processor */
 	SMCA_PSP_V2,
@@ -326,6 +327,8 @@ enum smca_bank_types {
 	SMCA_SHUB,	/* System HUB Unit */
 	SMCA_SATA,	/* SATA Unit */
 	SMCA_USB,	/* USB Unit */
+	SMCA_USR_DP,	/* Ultra Short Reach Data Plane Controller */
+	SMCA_USR_CP,	/* Ultra Short Reach Control Plane Controller */
 	SMCA_GMI_PCS,	/* GMI PCS Unit */
 	SMCA_XGMI_PHY,	/* xGMI PHY Unit */
 	SMCA_WAFL_PHY,	/* WAFL PHY Unit */
@@ -333,7 +336,6 @@ enum smca_bank_types {
 	N_SMCA_BANK_TYPES
 };
 
-extern const char *smca_get_long_name(enum smca_bank_types t);
 extern bool amd_mce_is_memory_error(struct mce *m);
 
 extern int mce_threshold_create_device(unsigned int cpu);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 1d51e1850ed0..737a52b89e64 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -237,6 +237,11 @@
 #define LBR_INFO_CYCLES			0xffff
 #define LBR_INFO_BR_TYPE_OFFSET		56
 #define LBR_INFO_BR_TYPE		(0xfull << LBR_INFO_BR_TYPE_OFFSET)
+#define LBR_INFO_BR_CNTR_OFFSET		32
+#define LBR_INFO_BR_CNTR_NUM		4
+#define LBR_INFO_BR_CNTR_BITS		2
+#define LBR_INFO_BR_CNTR_MASK		GENMASK_ULL(LBR_INFO_BR_CNTR_BITS - 1, 0)
+#define LBR_INFO_BR_CNTR_FULL_MASK	GENMASK_ULL(LBR_INFO_BR_CNTR_NUM * LBR_INFO_BR_CNTR_BITS - 1, 0)
 
 #define MSR_ARCH_LBR_CTL		0x000014ce
 #define ARCH_LBR_CTL_LBREN		BIT(0)
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 778df05f8539..920426d691ce 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -87,6 +87,15 @@ static __always_inline void __mwaitx(unsigned long eax, unsigned long ebx,
 		     :: "a" (eax), "b" (ebx), "c" (ecx));
 }
 
+/*
+ * Re-enable interrupts right upon calling mwait in such a way that
+ * no interrupt can fire _before_ the execution of mwait, ie: no
+ * instruction must be placed between "sti" and "mwait".
+ *
+ * This is necessary because if an interrupt queues a timer before
+ * executing mwait, it would otherwise go unnoticed and the next tick
+ * would not be reprogrammed accordingly before mwait ever wakes up.
+ */
 static __always_inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 {
 	mds_idle_clear_cpu_buffers();
@@ -115,8 +124,15 @@ static __always_inline void mwait_idle_with_hints(unsigned long eax, unsigned lo
 		}
 
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
-		if (!need_resched())
-			__mwait(eax, ecx);
+
+		if (!need_resched()) {
+			if (ecx & 1) {
+				__mwait(eax, ecx);
+			} else {
+				__sti_mwait(eax, ecx);
+				raw_local_irq_disable();
+			}
+		}
 	}
 	current_clr_polling();
 }
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index f93e9b96927a..262e65539f83 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -49,7 +49,7 @@
  * but there is still a cushion vs. the RSB depth. The algorithm does not
  * claim to be perfect and it can be speculated around by the CPU, but it
  * is considered that it obfuscates the problem enough to make exploitation
- * extremly difficult.
+ * extremely difficult.
  */
 #define RET_DEPTH_SHIFT			5
 #define RSB_RET_STUFF_LOOPS		16
@@ -208,7 +208,7 @@
 
 /*
  * Abuse ANNOTATE_RETPOLINE_SAFE on a NOP to indicate UNRET_END, should
- * eventually turn into it's own annotation.
+ * eventually turn into its own annotation.
  */
 .macro VALIDATE_UNRET_END
 #if defined(CONFIG_NOINSTR_VALIDATION) && \
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 6c8ff12140ae..d4eb9e1d61b8 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -6,6 +6,10 @@
 
 #include <asm/paravirt_types.h>
 
+#ifndef __ASSEMBLY__
+struct mm_struct;
+#endif
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/pgtable_types.h>
 #include <asm/asm.h>
@@ -142,8 +146,7 @@ static inline void write_cr0(unsigned long x)
 static __always_inline unsigned long read_cr2(void)
 {
 	return PVOP_ALT_CALLEE0(unsigned long, mmu.read_cr2,
-				"mov %%cr2, %%rax;",
-				ALT_NOT(X86_FEATURE_XENPV));
+				"mov %%cr2, %%rax;", ALT_NOT_XEN);
 }
 
 static __always_inline void write_cr2(unsigned long x)
@@ -154,13 +157,12 @@ static __always_inline void write_cr2(unsigned long x)
 static inline unsigned long __read_cr3(void)
 {
 	return PVOP_ALT_CALL0(unsigned long, mmu.read_cr3,
-			      "mov %%cr3, %%rax;", ALT_NOT(X86_FEATURE_XENPV));
+			      "mov %%cr3, %%rax;", ALT_NOT_XEN);
 }
 
 static inline void write_cr3(unsigned long x)
 {
-	PVOP_ALT_VCALL1(mmu.write_cr3, x,
-			"mov %%rdi, %%cr3", ALT_NOT(X86_FEATURE_XENPV));
+	PVOP_ALT_VCALL1(mmu.write_cr3, x, "mov %%rdi, %%cr3", ALT_NOT_XEN);
 }
 
 static inline void __write_cr4(unsigned long x)
@@ -182,7 +184,7 @@ extern noinstr void pv_native_wbinvd(void);
 
 static __always_inline void wbinvd(void)
 {
-	PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT(X86_FEATURE_XENPV));
+	PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT_XEN);
 }
 
 static inline u64 paravirt_read_msr(unsigned msr)
@@ -390,27 +392,25 @@ static inline void paravirt_release_p4d(unsigned long pfn)
 static inline pte_t __pte(pteval_t val)
 {
 	return (pte_t) { PVOP_ALT_CALLEE1(pteval_t, mmu.make_pte, val,
-					  "mov %%rdi, %%rax",
-					  ALT_NOT(X86_FEATURE_XENPV)) };
+					  "mov %%rdi, %%rax", ALT_NOT_XEN) };
 }
 
 static inline pteval_t pte_val(pte_t pte)
 {
 	return PVOP_ALT_CALLEE1(pteval_t, mmu.pte_val, pte.pte,
-				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
+				"mov %%rdi, %%rax", ALT_NOT_XEN);
 }
 
 static inline pgd_t __pgd(pgdval_t val)
 {
 	return (pgd_t) { PVOP_ALT_CALLEE1(pgdval_t, mmu.make_pgd, val,
-					  "mov %%rdi, %%rax",
-					  ALT_NOT(X86_FEATURE_XENPV)) };
+					  "mov %%rdi, %%rax", ALT_NOT_XEN) };
 }
 
 static inline pgdval_t pgd_val(pgd_t pgd)
 {
 	return PVOP_ALT_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd,
-				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
+				"mov %%rdi, %%rax", ALT_NOT_XEN);
 }
 
 #define  __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
@@ -444,14 +444,13 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 static inline pmd_t __pmd(pmdval_t val)
 {
 	return (pmd_t) { PVOP_ALT_CALLEE1(pmdval_t, mmu.make_pmd, val,
-					  "mov %%rdi, %%rax",
-					  ALT_NOT(X86_FEATURE_XENPV)) };
+					  "mov %%rdi, %%rax", ALT_NOT_XEN) };
 }
 
 static inline pmdval_t pmd_val(pmd_t pmd)
 {
 	return PVOP_ALT_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd,
-				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
+				"mov %%rdi, %%rax", ALT_NOT_XEN);
 }
 
 static inline void set_pud(pud_t *pudp, pud_t pud)
@@ -464,7 +463,7 @@ static inline pud_t __pud(pudval_t val)
 	pudval_t ret;
 
 	ret = PVOP_ALT_CALLEE1(pudval_t, mmu.make_pud, val,
-			       "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
+			       "mov %%rdi, %%rax", ALT_NOT_XEN);
 
 	return (pud_t) { ret };
 }
@@ -472,7 +471,7 @@ static inline pud_t __pud(pudval_t val)
 static inline pudval_t pud_val(pud_t pud)
 {
 	return PVOP_ALT_CALLEE1(pudval_t, mmu.pud_val, pud.pud,
-				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
+				"mov %%rdi, %%rax", ALT_NOT_XEN);
 }
 
 static inline void pud_clear(pud_t *pudp)
@@ -492,8 +491,7 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
 static inline p4d_t __p4d(p4dval_t val)
 {
 	p4dval_t ret = PVOP_ALT_CALLEE1(p4dval_t, mmu.make_p4d, val,
-					"mov %%rdi, %%rax",
-					ALT_NOT(X86_FEATURE_XENPV));
+					"mov %%rdi, %%rax", ALT_NOT_XEN);
 
 	return (p4d_t) { ret };
 }
@@ -501,7 +499,7 @@ static inline p4d_t __p4d(p4dval_t val)
 static inline p4dval_t p4d_val(p4d_t p4d)
 {
 	return PVOP_ALT_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d,
-				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
+				"mov %%rdi, %%rax", ALT_NOT_XEN);
 }
 
 static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd)
@@ -687,17 +685,17 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
 static __always_inline unsigned long arch_local_save_flags(void)
 {
 	return PVOP_ALT_CALLEE0(unsigned long, irq.save_fl, "pushf; pop %%rax;",
-				ALT_NOT(X86_FEATURE_XENPV));
+				ALT_NOT_XEN);
 }
 
 static __always_inline void arch_local_irq_disable(void)
 {
-	PVOP_ALT_VCALLEE0(irq.irq_disable, "cli;", ALT_NOT(X86_FEATURE_XENPV));
+	PVOP_ALT_VCALLEE0(irq.irq_disable, "cli;", ALT_NOT_XEN);
 }
 
 static __always_inline void arch_local_irq_enable(void)
 {
-	PVOP_ALT_VCALLEE0(irq.irq_enable, "sti;", ALT_NOT(X86_FEATURE_XENPV));
+	PVOP_ALT_VCALLEE0(irq.irq_enable, "sti;", ALT_NOT_XEN);
 }
 
 static __always_inline unsigned long arch_local_irq_save(void)
@@ -726,52 +724,25 @@ static __always_inline unsigned long arch_local_irq_save(void)
 #undef PVOP_VCALL4
 #undef PVOP_CALL4
 
-#define DEFINE_PARAVIRT_ASM(func, instr, sec)		\
-	asm (".pushsection " #sec ", \"ax\"\n"		\
-	     ".global " #func "\n\t"			\
-	     ".type " #func ", @function\n\t"		\
-	     ASM_FUNC_ALIGN "\n"			\
-	     #func ":\n\t"				\
-	     ASM_ENDBR					\
-	     instr "\n\t"				\
-	     ASM_RET					\
-	     ".size " #func ", . - " #func "\n\t"	\
-	     ".popsection")
-
 extern void default_banner(void);
 void native_pv_lock_init(void) __init;
 
 #else  /* __ASSEMBLY__ */
 
-#define _PVSITE(ptype, ops, word, algn)		\
-771:;						\
-	ops;					\
-772:;						\
-	.pushsection .parainstructions,"a";	\
-	 .align	algn;				\
-	 word 771b;				\
-	 .byte ptype;				\
-	 .byte 772b-771b;			\
-	 _ASM_ALIGN;				\
-	.popsection
-
-
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_PARAVIRT_XXL
+#ifdef CONFIG_DEBUG_ENTRY
 
-#define PARA_PATCH(off)		((off) / 8)
-#define PARA_SITE(ptype, ops)	_PVSITE(ptype, ops, .quad, 8)
 #define PARA_INDIRECT(addr)	*addr(%rip)
 
-#ifdef CONFIG_DEBUG_ENTRY
 .macro PARA_IRQ_save_fl
-	PARA_SITE(PARA_PATCH(PV_IRQ_save_fl),
-		  ANNOTATE_RETPOLINE_SAFE;
-		  call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl);)
+	ANNOTATE_RETPOLINE_SAFE;
+	call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl);
 .endm
 
-#define SAVE_FLAGS	ALTERNATIVE "PARA_IRQ_save_fl;", "pushf; pop %rax;", \
-				    ALT_NOT(X86_FEATURE_XENPV)
+#define SAVE_FLAGS ALTERNATIVE_2 "PARA_IRQ_save_fl;",			\
+				 "ALT_CALL_INSTR;", ALT_CALL_ALWAYS,	\
+				 "pushf; pop %rax;", ALT_NOT_XEN
 #endif
 #endif /* CONFIG_PARAVIRT_XXL */
 #endif	/* CONFIG_X86_64 */
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 772d03487520..8d4fbe1be489 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -2,18 +2,10 @@
 #ifndef _ASM_X86_PARAVIRT_TYPES_H
 #define _ASM_X86_PARAVIRT_TYPES_H
 
-#ifndef __ASSEMBLY__
-/* These all sit in the .parainstructions section to tell us what to patch. */
-struct paravirt_patch_site {
-	u8 *instr;		/* original instructions */
-	u8 type;		/* type of this instruction */
-	u8 len;			/* length of original instruction */
-};
-#endif
-
 #ifdef CONFIG_PARAVIRT
 
 #ifndef __ASSEMBLY__
+#include <linux/types.h>
 
 #include <asm/desc_defs.h>
 #include <asm/pgtable_types.h>
@@ -250,43 +242,11 @@ struct paravirt_patch_template {
 extern struct pv_info pv_info;
 extern struct paravirt_patch_template pv_ops;
 
-#define PARAVIRT_PATCH(x)					\
-	(offsetof(struct paravirt_patch_template, x) / sizeof(void *))
-
-#define paravirt_type(op)				\
-	[paravirt_typenum] "i" (PARAVIRT_PATCH(op)),	\
-	[paravirt_opptr] "m" (pv_ops.op)
-/*
- * Generate some code, and mark it as patchable by the
- * apply_paravirt() alternate instruction patcher.
- */
-#define _paravirt_alt(insn_string, type)		\
-	"771:\n\t" insn_string "\n" "772:\n"		\
-	".pushsection .parainstructions,\"a\"\n"	\
-	_ASM_ALIGN "\n"					\
-	_ASM_PTR " 771b\n"				\
-	"  .byte " type "\n"				\
-	"  .byte 772b-771b\n"				\
-	_ASM_ALIGN "\n"					\
-	".popsection\n"
-
-/* Generate patchable code, with the default asm parameters. */
-#define paravirt_alt(insn_string)					\
-	_paravirt_alt(insn_string, "%c[paravirt_typenum]")
-
-/* Simple instruction patching code. */
-#define NATIVE_LABEL(a,x,b) "\n\t.globl " a #x "_" #b "\n" a #x "_" #b ":\n\t"
-
-unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr, unsigned int len);
+#define paravirt_ptr(op)	[paravirt_opptr] "m" (pv_ops.op)
 
 int paravirt_disable_iospace(void);
 
-/*
- * This generates an indirect call based on the operation type number.
- * The type number, computed in PARAVIRT_PATCH, is derived from the
- * offset into the paravirt_patch_template structure, and can therefore be
- * freely converted back into a structure offset.
- */
+/* This generates an indirect call based on the operation type number. */
 #define PARAVIRT_CALL					\
 	ANNOTATE_RETPOLINE_SAFE				\
 	"call *%[paravirt_opptr];"
@@ -319,12 +279,6 @@ int paravirt_disable_iospace(void);
  * However, x86_64 also has to clobber all caller saved registers, which
  * unfortunately, are quite a bit (r8 - r11)
  *
- * The call instruction itself is marked by placing its start address
- * and size into the .parainstructions section, so that
- * apply_paravirt() in arch/i386/kernel/alternative.c can do the
- * appropriate patching under the control of the backend pv_init_ops
- * implementation.
- *
  * Unfortunately there's no way to get gcc to generate the args setup
  * for the call, and then allow the call itself to be generated by an
  * inline asm.  Because of this, we must do the complete arg setup and
@@ -423,14 +377,27 @@ int paravirt_disable_iospace(void);
 		__mask & __eax;						\
 	})
 
-
+/*
+ * Use alternative patching for paravirt calls:
+ * - For replacing an indirect call with a direct one, use the "normal"
+ *   ALTERNATIVE() macro with the indirect call as the initial code sequence,
+ *   which will be replaced with the related direct call by using the
+ *   ALT_FLAG_DIRECT_CALL special case and the "always on" feature.
+ * - In case the replacement is either a direct call or a short code sequence
+ *   depending on a feature bit, the ALTERNATIVE_2() macro is being used.
+ *   The indirect call is the initial code sequence again, while the special
+ *   code sequence is selected with the specified feature bit. In case the
+ *   feature is not active, the direct call is used as above via the
+ *   ALT_FLAG_DIRECT_CALL special case and the "always on" feature.
+ */
 #define ____PVOP_CALL(ret, op, call_clbr, extra_clbr, ...)	\
 	({								\
 		PVOP_CALL_ARGS;						\
 		PVOP_TEST_NULL(op);					\
-		asm volatile(paravirt_alt(PARAVIRT_CALL)		\
+		asm volatile(ALTERNATIVE(PARAVIRT_CALL, ALT_CALL_INSTR,	\
+				ALT_CALL_ALWAYS)			\
 			     : call_clbr, ASM_CALL_CONSTRAINT		\
-			     : paravirt_type(op),			\
+			     : paravirt_ptr(op),			\
 			       ##__VA_ARGS__				\
 			     : "memory", "cc" extra_clbr);		\
 		ret;							\
@@ -441,10 +408,11 @@ int paravirt_disable_iospace(void);
 	({								\
 		PVOP_CALL_ARGS;						\
 		PVOP_TEST_NULL(op);					\
-		asm volatile(ALTERNATIVE(paravirt_alt(PARAVIRT_CALL),	\
-					 alt, cond)			\
+		asm volatile(ALTERNATIVE_2(PARAVIRT_CALL,		\
+				 ALT_CALL_INSTR, ALT_CALL_ALWAYS,	\
+				 alt, cond)				\
 			     : call_clbr, ASM_CALL_CONSTRAINT		\
-			     : paravirt_type(op),			\
+			     : paravirt_ptr(op),			\
 			       ##__VA_ARGS__				\
 			     : "memory", "cc" extra_clbr);		\
 		ret;							\
@@ -542,8 +510,6 @@ int paravirt_disable_iospace(void);
 	__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),	\
 		     PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
 
-void _paravirt_nop(void);
-void paravirt_BUG(void);
 unsigned long paravirt_ret0(void);
 #ifdef CONFIG_PARAVIRT_XXL
 u64 _paravirt_ident_64(u64);
@@ -553,11 +519,11 @@ void pv_native_irq_enable(void);
 unsigned long pv_native_read_cr2(void);
 #endif
 
-#define paravirt_nop	((void *)_paravirt_nop)
-
-extern struct paravirt_patch_site __parainstructions[],
-	__parainstructions_end[];
+#define paravirt_nop	((void *)nop_func)
 
 #endif	/* __ASSEMBLY__ */
+
+#define ALT_NOT_XEN	ALT_NOT(X86_FEATURE_XENPV)
+
 #endif  /* CONFIG_PARAVIRT */
 #endif	/* _ASM_X86_PARAVIRT_TYPES_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 20624b80f890..5e01883eb51e 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -24,8 +24,8 @@
 
 #else /* ...!ASSEMBLY */
 
-#include <linux/kernel.h>
 #include <linux/stringify.h>
+#include <asm/asm.h>
 
 #ifdef CONFIG_SMP
 #define __percpu_prefix		"%%"__stringify(__percpu_seg)":"
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 2618ec7c3d1d..3736b8a46c04 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -31,6 +31,7 @@
 #define ARCH_PERFMON_EVENTSEL_ENABLE			(1ULL << 22)
 #define ARCH_PERFMON_EVENTSEL_INV			(1ULL << 23)
 #define ARCH_PERFMON_EVENTSEL_CMASK			0xFF000000ULL
+#define ARCH_PERFMON_EVENTSEL_BR_CNTR			(1ULL << 35)
 
 #define INTEL_FIXED_BITS_MASK				0xFULL
 #define INTEL_FIXED_BITS_STRIDE			4
@@ -223,6 +224,9 @@ union cpuid28_ecx {
 		unsigned int    lbr_timed_lbr:1;
 		/* Branch Type Field Supported */
 		unsigned int    lbr_br_type:1;
+		unsigned int	reserved:13;
+		/* Branch counters (Event Logging) Supported */
+		unsigned int	lbr_counters:4;
 	} split;
 	unsigned int            full;
 };
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 57bab91bbf50..9d077bca6a10 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -141,6 +141,7 @@ static inline int pte_young(pte_t pte)
 	return pte_flags(pte) & _PAGE_ACCESSED;
 }
 
+#define pmd_dirty pmd_dirty
 static inline bool pmd_dirty(pmd_t pmd)
 {
 	return pmd_flags(pmd) & _PAGE_DIRTY_BITS;
@@ -1679,12 +1680,6 @@ static inline bool arch_has_pfn_modify_check(void)
 	return boot_cpu_has_bug(X86_BUG_L1TF);
 }
 
-#define arch_has_hw_pte_young arch_has_hw_pte_young
-static inline bool arch_has_hw_pte_young(void)
-{
-	return true;
-}
-
 #define arch_check_zapped_pte arch_check_zapped_pte
 void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte);
 
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index a629b1b9f65a..24af25b1551a 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -203,7 +203,7 @@ static inline void native_pgd_clear(pgd_t *pgd)
  * F (2) in swp entry is used to record when a pagetable is
  * writeprotected by userfaultfd WP support.
  *
- * E (3) in swp entry is used to rememeber PG_anon_exclusive.
+ * E (3) in swp entry is used to remember PG_anon_exclusive.
  *
  * Bit 7 in swp entry should be 0 because pmd_present checks not only P,
  * but also L and G.
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 4527e1430c6d..af77235fded6 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -6,7 +6,6 @@
 #include <asm/percpu.h>
 #include <asm/current.h>
 
-#include <linux/thread_info.h>
 #include <linux/static_call_types.h>
 
 /* We use the MSB mostly because its available */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index ae81a7191c1c..26620d7642a9 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -749,4 +749,22 @@ enum mds_mitigations {
 
 extern bool gds_ucode_mitigated(void);
 
+/*
+ * Make previous memory operations globally visible before
+ * a WRMSR.
+ *
+ * MFENCE makes writes visible, but only affects load/store
+ * instructions.  WRMSR is unfortunately not a load/store
+ * instruction and is unaffected by MFENCE.  The LFENCE ensures
+ * that the WRMSR is not reordered.
+ *
+ * Most WRMSRs are full serializing instructions themselves and
+ * do not require this barrier.  This is only required for the
+ * IA32_TSC_DEADLINE and X2APIC MSRs.
+ */
+static inline void weak_wrmsr_fence(void)
+{
+	alternative("mfence; lfence", "", ALT_NOT(X86_FEATURE_APIC_MSRS_FENCE));
+}
+
 #endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 4d84122bd643..484f4f0131a5 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -32,10 +32,6 @@ void entry_SYSCALL_compat(void);
 void entry_SYSCALL_compat_safe_stack(void);
 void entry_SYSRETL_compat_unsafe_stack(void);
 void entry_SYSRETL_compat_end(void);
-void entry_INT80_compat(void);
-#ifdef CONFIG_XEN_PV
-void xen_entry_INT80_compat(void);
-#endif
 #else /* !CONFIG_IA32_EMULATION */
 #define entry_SYSCALL_compat NULL
 #define entry_SYSENTER_compat NULL
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
index 85b6e3609cb9..ef9697f20129 100644
--- a/arch/x86/include/asm/qspinlock_paravirt.h
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -56,8 +56,8 @@ __PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath, ".spinlock.text");
 	"pop    %rdx\n\t"						\
 	FRAME_END
 
-DEFINE_PARAVIRT_ASM(__raw_callee_save___pv_queued_spin_unlock,
-		    PV_UNLOCK_ASM, .spinlock.text);
+DEFINE_ASM_FUNC(__raw_callee_save___pv_queued_spin_unlock,
+		PV_UNLOCK_ASM, .spinlock.text);
 
 #else /* CONFIG_64BIT */
 
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index bf483fcb4e57..5c83729c8e71 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -31,8 +31,6 @@
 #include <asm/bootparam.h>
 #include <asm/x86_init.h>
 
-extern u64 relocated_ramdisk;
-
 /* Interrupt control for vSMPowered x86_64 systems */
 #ifdef CONFIG_X86_64
 void vsmp_init(void);
diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h
index fd2669b1cb2d..21f9407be5d3 100644
--- a/arch/x86/include/asm/syscall_wrapper.h
+++ b/arch/x86/include/asm/syscall_wrapper.h
@@ -86,9 +86,6 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
 		return sys_ni_syscall();				\
 	}
 
-#define __SYS_NI(abi, name)						\
-	SYSCALL_ALIAS(__##abi##_##name, sys_ni_posix_timers);
-
 #ifdef CONFIG_X86_64
 #define __X64_SYS_STUB0(name)						\
 	__SYS_STUB0(x64, sys_##name)
@@ -100,13 +97,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
 #define __X64_COND_SYSCALL(name)					\
 	__COND_SYSCALL(x64, sys_##name)
 
-#define __X64_SYS_NI(name)						\
-	__SYS_NI(x64, sys_##name)
 #else /* CONFIG_X86_64 */
 #define __X64_SYS_STUB0(name)
 #define __X64_SYS_STUBx(x, name, ...)
 #define __X64_COND_SYSCALL(name)
-#define __X64_SYS_NI(name)
 #endif /* CONFIG_X86_64 */
 
 #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
@@ -120,13 +114,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
 #define __IA32_COND_SYSCALL(name)					\
 	__COND_SYSCALL(ia32, sys_##name)
 
-#define __IA32_SYS_NI(name)						\
-	__SYS_NI(ia32, sys_##name)
 #else /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */
 #define __IA32_SYS_STUB0(name)
 #define __IA32_SYS_STUBx(x, name, ...)
 #define __IA32_COND_SYSCALL(name)
-#define __IA32_SYS_NI(name)
 #endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */
 
 #ifdef CONFIG_IA32_EMULATION
@@ -135,8 +126,7 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
  * additional wrappers (aptly named __ia32_sys_xyzzy) which decode the
  * ia32 regs in the proper order for shared or "common" syscalls. As some
  * syscalls may not be implemented, we need to expand COND_SYSCALL in
- * kernel/sys_ni.c and SYS_NI in kernel/time/posix-stubs.c to cover this
- * case as well.
+ * kernel/sys_ni.c to cover this case as well.
  */
 #define __IA32_COMPAT_SYS_STUB0(name)					\
 	__SYS_STUB0(ia32, compat_sys_##name)
@@ -148,14 +138,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
 #define __IA32_COMPAT_COND_SYSCALL(name)				\
 	__COND_SYSCALL(ia32, compat_sys_##name)
 
-#define __IA32_COMPAT_SYS_NI(name)					\
-	__SYS_NI(ia32, compat_sys_##name)
-
 #else /* CONFIG_IA32_EMULATION */
 #define __IA32_COMPAT_SYS_STUB0(name)
 #define __IA32_COMPAT_SYS_STUBx(x, name, ...)
 #define __IA32_COMPAT_COND_SYSCALL(name)
-#define __IA32_COMPAT_SYS_NI(name)
 #endif /* CONFIG_IA32_EMULATION */
 
 
@@ -175,13 +161,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
 #define __X32_COMPAT_COND_SYSCALL(name)					\
 	__COND_SYSCALL(x64, compat_sys_##name)
 
-#define __X32_COMPAT_SYS_NI(name)					\
-	__SYS_NI(x64, compat_sys_##name)
 #else /* CONFIG_X86_X32_ABI */
 #define __X32_COMPAT_SYS_STUB0(name)
 #define __X32_COMPAT_SYS_STUBx(x, name, ...)
 #define __X32_COMPAT_COND_SYSCALL(name)
-#define __X32_COMPAT_SYS_NI(name)
 #endif /* CONFIG_X86_X32_ABI */
 
 
@@ -212,17 +195,12 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
 
 /*
  * As some compat syscalls may not be implemented, we need to expand
- * COND_SYSCALL_COMPAT in kernel/sys_ni.c and COMPAT_SYS_NI in
- * kernel/time/posix-stubs.c to cover this case as well.
+ * COND_SYSCALL_COMPAT in kernel/sys_ni.c to cover this case as well.
  */
 #define COND_SYSCALL_COMPAT(name) 					\
 	__IA32_COMPAT_COND_SYSCALL(name)				\
 	__X32_COMPAT_COND_SYSCALL(name)
 
-#define COMPAT_SYS_NI(name)						\
-	__IA32_COMPAT_SYS_NI(name)					\
-	__X32_COMPAT_SYS_NI(name)
-
 #endif /* CONFIG_COMPAT */
 
 #define __SYSCALL_DEFINEx(x, name, ...)					\
@@ -243,8 +221,8 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
  * As the generic SYSCALL_DEFINE0() macro does not decode any parameters for
  * obvious reasons, and passing struct pt_regs *regs to it in %rdi does not
  * hurt, we only need to re-define it here to keep the naming congruent to
- * SYSCALL_DEFINEx() -- which is essential for the COND_SYSCALL() and SYS_NI()
- * macros to work correctly.
+ * SYSCALL_DEFINEx() -- which is essential for the COND_SYSCALL() macro
+ * to work correctly.
  */
 #define SYSCALL_DEFINE0(sname)						\
 	SYSCALL_METADATA(_##sname, 0);					\
@@ -257,10 +235,6 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
 	__X64_COND_SYSCALL(name)					\
 	__IA32_COND_SYSCALL(name)
 
-#define SYS_NI(name)							\
-	__X64_SYS_NI(name)						\
-	__IA32_SYS_NI(name)
-
 
 /*
  * For VSYSCALLS, we need to declare these three syscalls with the new
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index 29832c338cdc..0b70653a98c1 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -6,18 +6,6 @@
 #include <linux/stddef.h>
 #include <asm/ptrace.h>
 
-struct paravirt_patch_site;
-#ifdef CONFIG_PARAVIRT
-void apply_paravirt(struct paravirt_patch_site *start,
-		    struct paravirt_patch_site *end);
-#else
-static inline void apply_paravirt(struct paravirt_patch_site *start,
-				  struct paravirt_patch_site *end)
-{}
-#define __parainstructions	NULL
-#define __parainstructions_end	NULL
-#endif
-
 /*
  * Currently, the max observed size in the kernel code is
  * JUMP_LABEL_NOP_SIZE/RELATIVEJUMP_SIZE, which are 5.
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index b1c9cea6ba88..1f1deaecd364 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -14,7 +14,6 @@
 asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs);
 asmlinkage __visible notrace
 struct pt_regs *fixup_bad_iret(struct pt_regs *bad_regs);
-void __init trap_init(void);
 asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *eregs);
 #endif
 
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 5fa76c2ced51..ea877fd83114 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -653,7 +653,7 @@ static inline int uv_blade_to_node(int blade)
 	return uv_socket_to_node(blade);
 }
 
-/* Blade number of current cpu. Numnbered 0 .. <#blades -1> */
+/* Blade number of current cpu. Numbered 0 .. <#blades -1> */
 static inline int uv_numa_blade_id(void)
 {
 	return uv_hub_info->numa_blade_id;
diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h
index c81858d903dc..8e048ca980df 100644
--- a/arch/x86/include/asm/vdso/gettimeofday.h
+++ b/arch/x86/include/asm/vdso/gettimeofday.h
@@ -321,7 +321,7 @@ static __always_inline
 u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
 {
 	/*
-	 * Due to the MSB/Sign-bit being used as invald marker (see
+	 * Due to the MSB/Sign-bit being used as invalid marker (see
 	 * arch_vdso_cycles_valid() above), the effective mask is S64_MAX.
 	 */
 	u64 delta = (cycles - last) & S64_MAX;
@@ -337,8 +337,6 @@ u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
 }
 #define vdso_calc_delta vdso_calc_delta
 
-int __vdso_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts);
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 7048dfacc04b..a9088250770f 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -100,4 +100,13 @@ static inline void leave_lazy(enum xen_lazy_mode mode)
 
 enum xen_lazy_mode xen_get_lazy_mode(void);
 
+#if defined(CONFIG_XEN_DOM0) && defined(CONFIG_ACPI)
+void xen_sanitize_proc_cap_bits(uint32_t *buf);
+#else
+static inline void xen_sanitize_proc_cap_bits(uint32_t *buf)
+{
+	BUG();
+}
+#endif
+
 #endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/arch/x86/include/asm/xen/interface_64.h b/arch/x86/include/asm/xen/interface_64.h
index c599ec269a25..c10f279aae93 100644
--- a/arch/x86/include/asm/xen/interface_64.h
+++ b/arch/x86/include/asm/xen/interface_64.h
@@ -61,7 +61,7 @@
  *   RING1 -> RING3 kernel mode.
  *   RING2 -> RING3 kernel mode.
  *   RING3 -> RING3 user mode.
- * However RING0 indicates that the guest kernel should return to iteself
+ * However RING0 indicates that the guest kernel should return to itself
  * directly with
  *      orb   $3,1*8(%rsp)
  *      iretq
diff --git a/arch/x86/include/uapi/asm/amd_hsmp.h b/arch/x86/include/uapi/asm/amd_hsmp.h
index fce22686c834..e5d182c7373c 100644
--- a/arch/x86/include/uapi/asm/amd_hsmp.h
+++ b/arch/x86/include/uapi/asm/amd_hsmp.h
@@ -238,7 +238,7 @@ static const struct hsmp_msg_desc hsmp_msg_desc_table[] = {
 	/*
 	 * HSMP_GET_DIMM_THERMAL, num_args = 1, response_sz = 1
 	 * input: args[0] = DIMM address[7:0]
-	 * output: args[0] = temperature in degree celcius[31:21] + update rate in ms[16:8] +
+	 * output: args[0] = temperature in degree celsius[31:21] + update rate in ms[16:8] +
 	 * DIMM address[7:0]
 	 */
 	{1, 1, HSMP_GET},
diff --git a/arch/x86/include/uapi/asm/signal.h b/arch/x86/include/uapi/asm/signal.h
index 777c3a0f4e23..f777346450ec 100644
--- a/arch/x86/include/uapi/asm/signal.h
+++ b/arch/x86/include/uapi/asm/signal.h
@@ -4,7 +4,6 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
-#include <linux/time.h>
 #include <linux/compiler.h>
 
 /* Avoid too many header ordering problems.  */
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index d0918a75cb00..85a3ce2a3666 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -63,6 +63,7 @@ int acpi_fix_pin2_polarity __initdata;
 
 #ifdef CONFIG_X86_LOCAL_APIC
 static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
+static bool has_lapic_cpus __initdata;
 static bool acpi_support_online_capable;
 #endif
 
@@ -233,6 +234,14 @@ acpi_parse_x2apic(union acpi_subtable_headers *header, const unsigned long end)
 		return 0;
 
 	/*
+	 * According to https://uefi.org/specs/ACPI/6.5/05_ACPI_Software_Programming_Model.html#processor-local-x2apic-structure
+	 * when MADT provides both valid LAPIC and x2APIC entries, the APIC ID
+	 * in x2APIC must be equal or greater than 0xff.
+	 */
+	if (has_lapic_cpus && apic_id < 0xff)
+		return 0;
+
+	/*
 	 * We need to register disabled CPU as well to permit
 	 * counting disabled CPUs. This allows us to size
 	 * cpus_possible_map more accurately, to permit
@@ -284,6 +293,7 @@ acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end)
 			    processor->processor_id, /* ACPI ID */
 			    processor->lapic_flags & ACPI_MADT_ENABLED);
 
+	has_lapic_cpus = true;
 	return 0;
 }
 
@@ -1114,10 +1124,7 @@ static int __init early_acpi_parse_madt_lapic_addr_ovr(void)
 
 static int __init acpi_parse_madt_lapic_entries(void)
 {
-	int count;
-	int x2count = 0;
-	int ret;
-	struct acpi_subtable_proc madt_proc[2];
+	int count, x2count = 0;
 
 	if (!boot_cpu_has(X86_FEATURE_APIC))
 		return -ENODEV;
@@ -1126,21 +1133,10 @@ static int __init acpi_parse_madt_lapic_entries(void)
 				      acpi_parse_sapic, MAX_LOCAL_APIC);
 
 	if (!count) {
-		memset(madt_proc, 0, sizeof(madt_proc));
-		madt_proc[0].id = ACPI_MADT_TYPE_LOCAL_APIC;
-		madt_proc[0].handler = acpi_parse_lapic;
-		madt_proc[1].id = ACPI_MADT_TYPE_LOCAL_X2APIC;
-		madt_proc[1].handler = acpi_parse_x2apic;
-		ret = acpi_table_parse_entries_array(ACPI_SIG_MADT,
-				sizeof(struct acpi_table_madt),
-				madt_proc, ARRAY_SIZE(madt_proc), MAX_LOCAL_APIC);
-		if (ret < 0) {
-			pr_err("Error parsing LAPIC/X2APIC entries\n");
-			return ret;
-		}
-
-		count = madt_proc[0].count;
-		x2count = madt_proc[1].count;
+		count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC,
+					acpi_parse_lapic, MAX_LOCAL_APIC);
+		x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC,
+					acpi_parse_x2apic, MAX_LOCAL_APIC);
 	}
 	if (!count && !x2count) {
 		pr_err("No LAPIC entries present\n");
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 73be3931e4f0..cc130b57542a 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -30,6 +30,7 @@
 #include <asm/fixmap.h>
 #include <asm/paravirt.h>
 #include <asm/asm-prototypes.h>
+#include <asm/cfi.h>
 
 int __read_mostly alternatives_patched;
 
@@ -160,7 +161,6 @@ extern s32 __retpoline_sites[], __retpoline_sites_end[];
 extern s32 __return_sites[], __return_sites_end[];
 extern s32 __cfi_sites[], __cfi_sites_end[];
 extern s32 __ibt_endbr_seal[], __ibt_endbr_seal_end[];
-extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 extern s32 __smp_locks[], __smp_locks_end[];
 void text_poke_early(void *addr, const void *opcode, size_t len);
 
@@ -255,6 +255,16 @@ static void __init_or_module noinline optimize_nops(u8 *instr, size_t len)
 	}
 }
 
+static void __init_or_module noinline optimize_nops_inplace(u8 *instr, size_t len)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	optimize_nops(instr, len);
+	sync_core();
+	local_irq_restore(flags);
+}
+
 /*
  * In this context, "source" is where the instructions are placed in the
  * section .altinstr_replacement, for example during kernel build by the
@@ -385,6 +395,63 @@ apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len)
 	}
 }
 
+/* Low-level backend functions usable from alternative code replacements. */
+DEFINE_ASM_FUNC(nop_func, "", .entry.text);
+EXPORT_SYMBOL_GPL(nop_func);
+
+noinstr void BUG_func(void)
+{
+	BUG();
+}
+EXPORT_SYMBOL_GPL(BUG_func);
+
+#define CALL_RIP_REL_OPCODE	0xff
+#define CALL_RIP_REL_MODRM	0x15
+
+/*
+ * Rewrite the "call BUG_func" replacement to point to the target of the
+ * indirect pv_ops call "call *disp(%ip)".
+ */
+static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a)
+{
+	void *target, *bug = &BUG_func;
+	s32 disp;
+
+	if (a->replacementlen != 5 || insn_buff[0] != CALL_INSN_OPCODE) {
+		pr_err("ALT_FLAG_DIRECT_CALL set for a non-call replacement instruction\n");
+		BUG();
+	}
+
+	if (a->instrlen != 6 ||
+	    instr[0] != CALL_RIP_REL_OPCODE ||
+	    instr[1] != CALL_RIP_REL_MODRM) {
+		pr_err("ALT_FLAG_DIRECT_CALL set for unrecognized indirect call\n");
+		BUG();
+	}
+
+	/* Skip CALL_RIP_REL_OPCODE and CALL_RIP_REL_MODRM */
+	disp = *(s32 *)(instr + 2);
+#ifdef CONFIG_X86_64
+	/* ff 15 00 00 00 00   call   *0x0(%rip) */
+	/* target address is stored at "next instruction + disp". */
+	target = *(void **)(instr + a->instrlen + disp);
+#else
+	/* ff 15 00 00 00 00   call   *0x0 */
+	/* target address is stored at disp. */
+	target = *(void **)disp;
+#endif
+	if (!target)
+		target = bug;
+
+	/* (BUG_func - .) + (target - BUG_func) := target - . */
+	*(s32 *)(insn_buff + 1) += target - bug;
+
+	if (target == &nop_func)
+		return 0;
+
+	return 5;
+}
+
 /*
  * Replace instructions with better alternatives for this CPU type. This runs
  * before SMP is initialized to avoid SMP problems with self modifying code.
@@ -438,20 +505,25 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 		 *   patch if feature is *NOT* present.
 		 */
 		if (!boot_cpu_has(a->cpuid) == !(a->flags & ALT_FLAG_NOT)) {
-			optimize_nops(instr, a->instrlen);
+			optimize_nops_inplace(instr, a->instrlen);
 			continue;
 		}
 
-		DPRINTK(ALT, "feat: %s%d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d)",
-			(a->flags & ALT_FLAG_NOT) ? "!" : "",
+		DPRINTK(ALT, "feat: %d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d) flags: 0x%x",
 			a->cpuid >> 5,
 			a->cpuid & 0x1f,
 			instr, instr, a->instrlen,
-			replacement, a->replacementlen);
+			replacement, a->replacementlen, a->flags);
 
 		memcpy(insn_buff, replacement, a->replacementlen);
 		insn_buff_sz = a->replacementlen;
 
+		if (a->flags & ALT_FLAG_DIRECT_CALL) {
+			insn_buff_sz = alt_replace_call(instr, insn_buff, a);
+			if (insn_buff_sz < 0)
+				continue;
+		}
+
 		for (; insn_buff_sz < a->instrlen; insn_buff_sz++)
 			insn_buff[insn_buff_sz] = 0x90;
 
@@ -832,15 +904,82 @@ void __init_or_module apply_seal_endbr(s32 *start, s32 *end) { }
 #endif /* CONFIG_X86_KERNEL_IBT */
 
 #ifdef CONFIG_FINEIBT
+#define __CFI_DEFAULT	CFI_DEFAULT
+#elif defined(CONFIG_CFI_CLANG)
+#define __CFI_DEFAULT	CFI_KCFI
+#else
+#define __CFI_DEFAULT	CFI_OFF
+#endif
 
-enum cfi_mode {
-	CFI_DEFAULT,
-	CFI_OFF,
-	CFI_KCFI,
-	CFI_FINEIBT,
-};
+enum cfi_mode cfi_mode __ro_after_init = __CFI_DEFAULT;
+
+#ifdef CONFIG_CFI_CLANG
+struct bpf_insn;
+
+/* Must match bpf_func_t / DEFINE_BPF_PROG_RUN() */
+extern unsigned int __bpf_prog_runX(const void *ctx,
+				    const struct bpf_insn *insn);
+
+/*
+ * Force a reference to the external symbol so the compiler generates
+ * __kcfi_typid.
+ */
+__ADDRESSABLE(__bpf_prog_runX);
+
+/* u32 __ro_after_init cfi_bpf_hash = __kcfi_typeid___bpf_prog_runX; */
+asm (
+"	.pushsection	.data..ro_after_init,\"aw\",@progbits	\n"
+"	.type	cfi_bpf_hash,@object				\n"
+"	.globl	cfi_bpf_hash					\n"
+"	.p2align	2, 0x0					\n"
+"cfi_bpf_hash:							\n"
+"	.long	__kcfi_typeid___bpf_prog_runX			\n"
+"	.size	cfi_bpf_hash, 4					\n"
+"	.popsection						\n"
+);
+
+/* Must match bpf_callback_t */
+extern u64 __bpf_callback_fn(u64, u64, u64, u64, u64);
+
+__ADDRESSABLE(__bpf_callback_fn);
+
+/* u32 __ro_after_init cfi_bpf_subprog_hash = __kcfi_typeid___bpf_callback_fn; */
+asm (
+"	.pushsection	.data..ro_after_init,\"aw\",@progbits	\n"
+"	.type	cfi_bpf_subprog_hash,@object			\n"
+"	.globl	cfi_bpf_subprog_hash				\n"
+"	.p2align	2, 0x0					\n"
+"cfi_bpf_subprog_hash:						\n"
+"	.long	__kcfi_typeid___bpf_callback_fn			\n"
+"	.size	cfi_bpf_subprog_hash, 4				\n"
+"	.popsection						\n"
+);
+
+u32 cfi_get_func_hash(void *func)
+{
+	u32 hash;
+
+	func -= cfi_get_offset();
+	switch (cfi_mode) {
+	case CFI_FINEIBT:
+		func += 7;
+		break;
+	case CFI_KCFI:
+		func += 1;
+		break;
+	default:
+		return 0;
+	}
+
+	if (get_kernel_nofault(hash, func))
+		return 0;
+
+	return hash;
+}
+#endif
+
+#ifdef CONFIG_FINEIBT
 
-static enum cfi_mode cfi_mode __ro_after_init = CFI_DEFAULT;
 static bool cfi_rand __ro_after_init = true;
 static u32  cfi_seed __ro_after_init;
 
@@ -1149,8 +1288,11 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 		goto err;
 
 	if (cfi_rand) {
-		if (builtin)
+		if (builtin) {
 			cfi_seed = get_random_u32();
+			cfi_bpf_hash = cfi_rehash(cfi_bpf_hash);
+			cfi_bpf_subprog_hash = cfi_rehash(cfi_bpf_subprog_hash);
+		}
 
 		ret = cfi_rand_preamble(start_cfi, end_cfi);
 		if (ret)
@@ -1411,46 +1553,6 @@ int alternatives_text_reserved(void *start, void *end)
 }
 #endif /* CONFIG_SMP */
 
-#ifdef CONFIG_PARAVIRT
-
-/* Use this to add nops to a buffer, then text_poke the whole buffer. */
-static void __init_or_module add_nops(void *insns, unsigned int len)
-{
-	while (len > 0) {
-		unsigned int noplen = len;
-		if (noplen > ASM_NOP_MAX)
-			noplen = ASM_NOP_MAX;
-		memcpy(insns, x86_nops[noplen], noplen);
-		insns += noplen;
-		len -= noplen;
-	}
-}
-
-void __init_or_module apply_paravirt(struct paravirt_patch_site *start,
-				     struct paravirt_patch_site *end)
-{
-	struct paravirt_patch_site *p;
-	char insn_buff[MAX_PATCH_LEN];
-
-	for (p = start; p < end; p++) {
-		unsigned int used;
-
-		BUG_ON(p->len > MAX_PATCH_LEN);
-		/* prep the buffer with the original instructions */
-		memcpy(insn_buff, p->instr, p->len);
-		used = paravirt_patch(p->type, insn_buff, (unsigned long)p->instr, p->len);
-
-		BUG_ON(used > p->len);
-
-		/* Pad the rest with nops */
-		add_nops(insn_buff + used, p->len - used);
-		text_poke_early(p->instr, insn_buff, p->len);
-	}
-}
-extern struct paravirt_patch_site __start_parainstructions[],
-	__stop_parainstructions[];
-#endif	/* CONFIG_PARAVIRT */
-
 /*
  * Self-test for the INT3 based CALL emulation code.
  *
@@ -1586,28 +1688,11 @@ void __init alternative_instructions(void)
 	 */
 
 	/*
-	 * Paravirt patching and alternative patching can be combined to
-	 * replace a function call with a short direct code sequence (e.g.
-	 * by setting a constant return value instead of doing that in an
-	 * external function).
-	 * In order to make this work the following sequence is required:
-	 * 1. set (artificial) features depending on used paravirt
-	 *    functions which can later influence alternative patching
-	 * 2. apply paravirt patching (generally replacing an indirect
-	 *    function call with a direct one)
-	 * 3. apply alternative patching (e.g. replacing a direct function
-	 *    call with a custom code sequence)
-	 * Doing paravirt patching after alternative patching would clobber
-	 * the optimization of the custom code with a function call again.
+	 * Make sure to set (artificial) features depending on used paravirt
+	 * functions which can later influence alternative patching.
 	 */
 	paravirt_set_cap();
 
-	/*
-	 * First patch paravirt functions, such that we overwrite the indirect
-	 * call with the direct call.
-	 */
-	apply_paravirt(__parainstructions, __parainstructions_end);
-
 	__apply_fineibt(__retpoline_sites, __retpoline_sites_end,
 			__cfi_sites, __cfi_sites_end, true);
 
@@ -1618,10 +1703,6 @@ void __init alternative_instructions(void)
 	apply_retpolines(__retpoline_sites, __retpoline_sites_end);
 	apply_returns(__return_sites, __return_sites_end);
 
-	/*
-	 * Then patch alternatives, such that those paravirt calls that are in
-	 * alternatives can be overwritten by their immediate fragments.
-	 */
 	apply_alternatives(__alt_instructions, __alt_instructions_end);
 
 	/*
@@ -1685,8 +1766,8 @@ void __init_or_module text_poke_early(void *addr, const void *opcode,
 	} else {
 		local_irq_save(flags);
 		memcpy(addr, opcode, len);
-		local_irq_restore(flags);
 		sync_core();
+		local_irq_restore(flags);
 
 		/*
 		 * Could also do a CLFLUSH here to speed up CPU recovery; but
@@ -1896,7 +1977,7 @@ static void *__text_poke(text_poke_f func, void *addr, const void *src, size_t l
  * Note that the caller must ensure that if the modified code is part of a
  * module, the module would not be removed during poking. This can be achieved
  * by registering a module notifier, and ordering module removal and patching
- * trough a mutex.
+ * through a mutex.
  */
 void *text_poke(void *addr, const void *opcode, size_t len)
 {
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index 56a917df410d..2ae98f754e59 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -776,7 +776,7 @@ int __init gart_iommu_init(void)
 				iommu_size >> PAGE_SHIFT);
 	/*
 	 * Tricky. The GART table remaps the physical memory range,
-	 * so the CPU wont notice potential aliases and if the memory
+	 * so the CPU won't notice potential aliases and if the memory
 	 * is remapped to UC later on, we might surprise the PCI devices
 	 * with a stray writeout of a cacheline. So play it sure and
 	 * do an explicit, full-scale wbinvd() _after_ having marked all
diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile
index 2ee867d796d9..3bf0487cf3b7 100644
--- a/arch/x86/kernel/apic/Makefile
+++ b/arch/x86/kernel/apic/Makefile
@@ -4,7 +4,7 @@
 #
 
 # Leads to non-deterministic coverage that is not a function of syscall inputs.
-# In particualr, smp_apic_timer_interrupt() is called in random places.
+# In particular, smp_apic_timer_interrupt() is called in random places.
 KCOV_INSTRUMENT		:= n
 
 obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o apic_common.o apic_noop.o ipi.o vector.o init.o
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 41093cf20acd..4667bc4b00ab 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -782,7 +782,7 @@ bool __init apic_needs_pit(void)
 
 	/*
 	 * If interrupt delivery mode is legacy PIC or virtual wire without
-	 * configuration, the local APIC timer wont be set up. Make sure
+	 * configuration, the local APIC timer won't be set up. Make sure
 	 * that the PIT is initialized.
 	 */
 	if (apic_intr_mode == APIC_PIC ||
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 7139867d69cd..b295a056a4fc 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -82,7 +82,6 @@ static struct apic apic_flat __ro_after_init = {
 	.acpi_madt_oem_check		= flat_acpi_madt_oem_check,
 	.apic_id_registered		= default_apic_id_registered,
 
-	.delivery_mode			= APIC_DELIVERY_MODE_FIXED,
 	.dest_mode_logical		= true,
 
 	.disable_esr			= 0,
@@ -154,7 +153,6 @@ static struct apic apic_physflat __ro_after_init = {
 	.acpi_madt_oem_check		= physflat_acpi_madt_oem_check,
 	.apic_id_registered		= default_apic_id_registered,
 
-	.delivery_mode			= APIC_DELIVERY_MODE_FIXED,
 	.dest_mode_logical		= false,
 
 	.disable_esr			= 0,
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index b00d52ae84fa..9f1d553eb48f 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -47,7 +47,6 @@ static void noop_apic_write(u32 reg, u32 val)
 struct apic apic_noop __ro_after_init = {
 	.name				= "noop",
 
-	.delivery_mode			= APIC_DELIVERY_MODE_FIXED,
 	.dest_mode_logical		= true,
 
 	.disable_esr			= 0,
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 456a14c44f67..7d0c51b9d3bc 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -222,7 +222,6 @@ static const struct apic apic_numachip1 __refconst = {
 	.probe				= numachip1_probe,
 	.acpi_madt_oem_check		= numachip1_acpi_madt_oem_check,
 
-	.delivery_mode			= APIC_DELIVERY_MODE_FIXED,
 	.dest_mode_logical		= false,
 
 	.disable_esr			= 0,
@@ -259,7 +258,6 @@ static const struct apic apic_numachip2 __refconst = {
 	.probe				= numachip2_probe,
 	.acpi_madt_oem_check		= numachip2_acpi_madt_oem_check,
 
-	.delivery_mode			= APIC_DELIVERY_MODE_FIXED,
 	.dest_mode_logical		= false,
 
 	.disable_esr			= 0,
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index 7ee3c486cb33..5a0d60b38e6b 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -80,7 +80,6 @@ static struct apic apic_bigsmp __ro_after_init = {
 	.name				= "bigsmp",
 	.probe				= probe_bigsmp,
 
-	.delivery_mode			= APIC_DELIVERY_MODE_FIXED,
 	.dest_mode_logical		= false,
 
 	.disable_esr			= 1,
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 00da6cf6b07d..40c7cf180c20 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -997,7 +997,7 @@ static int alloc_isa_irq_from_domain(struct irq_domain *domain,
 	/*
 	 * Legacy ISA IRQ has already been allocated, just add pin to
 	 * the pin list associated with this IRQ and program the IOAPIC
-	 * entry. The IOAPIC entry
+	 * entry.
 	 */
 	if (irq_data && irq_data->parent_data) {
 		if (!mp_check_pin_attr(irq, info))
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 5eb3fbe472da..c0f78059f06a 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -45,7 +45,6 @@ static struct apic apic_default __ro_after_init = {
 	.probe				= probe_default,
 	.apic_id_registered		= default_apic_id_registered,
 
-	.delivery_mode			= APIC_DELIVERY_MODE_FIXED,
 	.dest_mode_logical		= true,
 
 	.disable_esr			= 0,
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 319448d87b99..185738c72766 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -738,8 +738,8 @@ int __init arch_probe_nr_irqs(void)
 void lapic_assign_legacy_vector(unsigned int irq, bool replace)
 {
 	/*
-	 * Use assign system here so it wont get accounted as allocated
-	 * and moveable in the cpu hotplug check and it prevents managed
+	 * Use assign system here so it won't get accounted as allocated
+	 * and movable in the cpu hotplug check and it prevents managed
 	 * irq reservation from touching it.
 	 */
 	irq_matrix_assign_system(vector_matrix, ISA_IRQ_VECTOR(irq), replace);
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index a8306089c91b..28a7d3f2312d 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -227,7 +227,6 @@ static struct apic apic_x2apic_cluster __ro_after_init = {
 	.probe				= x2apic_cluster_probe,
 	.acpi_madt_oem_check		= x2apic_acpi_madt_oem_check,
 
-	.delivery_mode			= APIC_DELIVERY_MODE_FIXED,
 	.dest_mode_logical		= true,
 
 	.disable_esr			= 0,
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 558a4a8824f4..409815a40668 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -145,7 +145,6 @@ static struct apic apic_x2apic_phys __ro_after_init = {
 	.probe				= x2apic_phys_probe,
 	.acpi_madt_oem_check		= x2apic_acpi_madt_oem_check,
 
-	.delivery_mode			= APIC_DELIVERY_MODE_FIXED,
 	.dest_mode_logical		= false,
 
 	.disable_esr			= 0,
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 1b0d7336a28f..f1766b18dcd0 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -805,7 +805,6 @@ static struct apic apic_x2apic_uv_x __ro_after_init = {
 	.probe				= uv_probe,
 	.acpi_madt_oem_check		= uv_acpi_madt_oem_check,
 
-	.delivery_mode			= APIC_DELIVERY_MODE_FIXED,
 	.dest_mode_logical		= false,
 
 	.disable_esr			= 0,
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 5934ee5bc087..76a5ced278c2 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -420,7 +420,7 @@ static DEFINE_MUTEX(apm_mutex);
  * This is for buggy BIOS's that refer to (real mode) segment 0x40
  * even though they are called in protected mode.
  */
-static struct desc_struct bad_bios_desc = GDT_ENTRY_INIT(0x4092,
+static struct desc_struct bad_bios_desc = GDT_ENTRY_INIT(DESC_DATA32_BIOS,
 			(unsigned long)__va(0x400UL), PAGE_SIZE - 0x400 - 1);
 
 static const char driver_version[] = "1.16ac";	/* no spaces */
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index e9ad518a5003..64ad2ddea121 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -233,14 +233,13 @@ patch_call_sites(s32 *start, s32 *end, const struct core_text *ct)
 }
 
 static __init_or_module void
-patch_paravirt_call_sites(struct paravirt_patch_site *start,
-			  struct paravirt_patch_site *end,
-			  const struct core_text *ct)
+patch_alt_call_sites(struct alt_instr *start, struct alt_instr *end,
+		     const struct core_text *ct)
 {
-	struct paravirt_patch_site *p;
+	struct alt_instr *a;
 
-	for (p = start; p < end; p++)
-		patch_call(p->instr, ct);
+	for (a = start; a < end; a++)
+		patch_call((void *)&a->instr_offset + a->instr_offset, ct);
 }
 
 static __init_or_module void
@@ -248,7 +247,7 @@ callthunks_setup(struct callthunk_sites *cs, const struct core_text *ct)
 {
 	prdbg("Patching call sites %s\n", ct->name);
 	patch_call_sites(cs->call_start, cs->call_end, ct);
-	patch_paravirt_call_sites(cs->pv_start, cs->pv_end, ct);
+	patch_alt_call_sites(cs->alt_start, cs->alt_end, ct);
 	prdbg("Patching call sites done%s\n", ct->name);
 }
 
@@ -257,8 +256,8 @@ void __init callthunks_patch_builtin_calls(void)
 	struct callthunk_sites cs = {
 		.call_start	= __call_sites,
 		.call_end	= __call_sites_end,
-		.pv_start	= __parainstructions,
-		.pv_end		= __parainstructions_end
+		.alt_start	= __alt_instructions,
+		.alt_end	= __alt_instructions_end
 	};
 
 	if (!cpu_feature_enabled(X86_FEATURE_CALL_DEPTH))
diff --git a/arch/x86/kernel/cfi.c b/arch/x86/kernel/cfi.c
index 8674a5c0c031..e6bf78fac146 100644
--- a/arch/x86/kernel/cfi.c
+++ b/arch/x86/kernel/cfi.c
@@ -4,10 +4,10 @@
  *
  * Copyright (C) 2022 Google LLC
  */
-#include <asm/cfi.h>
+#include <linux/string.h>
+#include <linux/cfi.h>
 #include <asm/insn.h>
 #include <asm/insn-eval.h>
-#include <linux/string.h>
 
 /*
  * Returns the target address and the expected type when regs->ip points
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index a7eab05e5f29..9f42d1c59e09 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -34,87 +34,6 @@
  */
 static u32 nodes_per_socket = 1;
 
-/*
- * AMD errata checking
- *
- * Errata are defined as arrays of ints using the AMD_LEGACY_ERRATUM() or
- * AMD_OSVW_ERRATUM() macros. The latter is intended for newer errata that
- * have an OSVW id assigned, which it takes as first argument. Both take a
- * variable number of family-specific model-stepping ranges created by
- * AMD_MODEL_RANGE().
- *
- * Example:
- *
- * const int amd_erratum_319[] =
- *	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0x4, 0x2),
- *			   AMD_MODEL_RANGE(0x10, 0x8, 0x0, 0x8, 0x0),
- *			   AMD_MODEL_RANGE(0x10, 0x9, 0x0, 0x9, 0x0));
- */
-
-#define AMD_LEGACY_ERRATUM(...)		{ -1, __VA_ARGS__, 0 }
-#define AMD_OSVW_ERRATUM(osvw_id, ...)	{ osvw_id, __VA_ARGS__, 0 }
-#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \
-	((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end))
-#define AMD_MODEL_RANGE_FAMILY(range)	(((range) >> 24) & 0xff)
-#define AMD_MODEL_RANGE_START(range)	(((range) >> 12) & 0xfff)
-#define AMD_MODEL_RANGE_END(range)	((range) & 0xfff)
-
-static const int amd_erratum_400[] =
-	AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf),
-			    AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf));
-
-static const int amd_erratum_383[] =
-	AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf));
-
-/* #1054: Instructions Retired Performance Counter May Be Inaccurate */
-static const int amd_erratum_1054[] =
-	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf));
-
-static const int amd_zenbleed[] =
-	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x30, 0x0, 0x4f, 0xf),
-			   AMD_MODEL_RANGE(0x17, 0x60, 0x0, 0x7f, 0xf),
-			   AMD_MODEL_RANGE(0x17, 0x90, 0x0, 0x91, 0xf),
-			   AMD_MODEL_RANGE(0x17, 0xa0, 0x0, 0xaf, 0xf));
-
-static const int amd_div0[] =
-	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x00, 0x0, 0x2f, 0xf),
-			   AMD_MODEL_RANGE(0x17, 0x50, 0x0, 0x5f, 0xf));
-
-static const int amd_erratum_1485[] =
-	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x19, 0x10, 0x0, 0x1f, 0xf),
-			   AMD_MODEL_RANGE(0x19, 0x60, 0x0, 0xaf, 0xf));
-
-static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
-{
-	int osvw_id = *erratum++;
-	u32 range;
-	u32 ms;
-
-	if (osvw_id >= 0 && osvw_id < 65536 &&
-	    cpu_has(cpu, X86_FEATURE_OSVW)) {
-		u64 osvw_len;
-
-		rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, osvw_len);
-		if (osvw_id < osvw_len) {
-			u64 osvw_bits;
-
-			rdmsrl(MSR_AMD64_OSVW_STATUS + (osvw_id >> 6),
-			    osvw_bits);
-			return osvw_bits & (1ULL << (osvw_id & 0x3f));
-		}
-	}
-
-	/* OSVW unavailable or ID unknown, match family-model-stepping range */
-	ms = (cpu->x86_model << 4) | cpu->x86_stepping;
-	while ((range = *erratum++))
-		if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) &&
-		    (ms >= AMD_MODEL_RANGE_START(range)) &&
-		    (ms <= AMD_MODEL_RANGE_END(range)))
-			return true;
-
-	return false;
-}
-
 static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
 {
 	u32 gprs[8] = { 0 };
@@ -616,6 +535,49 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 	}
 
 	resctrl_cpu_detect(c);
+
+	/* Figure out Zen generations: */
+	switch (c->x86) {
+	case 0x17: {
+		switch (c->x86_model) {
+		case 0x00 ... 0x2f:
+		case 0x50 ... 0x5f:
+			setup_force_cpu_cap(X86_FEATURE_ZEN1);
+			break;
+		case 0x30 ... 0x4f:
+		case 0x60 ... 0x7f:
+		case 0x90 ... 0x91:
+		case 0xa0 ... 0xaf:
+			setup_force_cpu_cap(X86_FEATURE_ZEN2);
+			break;
+		default:
+			goto warn;
+		}
+		break;
+	}
+	case 0x19: {
+		switch (c->x86_model) {
+		case 0x00 ... 0x0f:
+		case 0x20 ... 0x5f:
+			setup_force_cpu_cap(X86_FEATURE_ZEN3);
+			break;
+		case 0x10 ... 0x1f:
+		case 0x60 ... 0xaf:
+			setup_force_cpu_cap(X86_FEATURE_ZEN4);
+			break;
+		default:
+			goto warn;
+		}
+		break;
+	}
+	default:
+		break;
+	}
+
+	return;
+
+warn:
+	WARN_ONCE(1, "Family 0x%x, model: 0x%x??\n", c->x86, c->x86_model);
 }
 
 static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
@@ -739,15 +701,6 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 	if (c->x86 == 0x16 && c->x86_model <= 0xf)
 		msr_set_bit(MSR_AMD64_LS_CFG, 15);
 
-	/*
-	 * Check whether the machine is affected by erratum 400. This is
-	 * used to select the proper idle routine and to enable the check
-	 * whether the machine is affected in arch_post_acpi_init(), which
-	 * sets the X86_BUG_AMD_APIC_C1E bug depending on the MSR check.
-	 */
-	if (cpu_has_amd_erratum(c, amd_erratum_400))
-		set_cpu_bug(c, X86_BUG_AMD_E400);
-
 	early_detect_mem_encrypt(c);
 
 	/* Re-enable TopologyExtensions if switched off by BIOS */
@@ -814,6 +767,16 @@ static void init_amd_k8(struct cpuinfo_x86 *c)
 	msr_set_bit(MSR_K7_HWCR, 6);
 #endif
 	set_cpu_bug(c, X86_BUG_SWAPGS_FENCE);
+
+	/*
+	 * Check models and steppings affected by erratum 400. This is
+	 * used to select the proper idle routine and to enable the
+	 * check whether the machine is affected in arch_post_acpi_subsys_init()
+	 * which sets the X86_BUG_AMD_APIC_C1E bug depending on the MSR check.
+	 */
+	if (c->x86_model > 0x41 ||
+	    (c->x86_model == 0x41 && c->x86_stepping >= 0x2))
+		setup_force_cpu_bug(X86_BUG_AMD_E400);
 }
 
 static void init_amd_gh(struct cpuinfo_x86 *c)
@@ -847,8 +810,17 @@ static void init_amd_gh(struct cpuinfo_x86 *c)
 	 */
 	msr_clear_bit(MSR_AMD64_BU_CFG2, 24);
 
-	if (cpu_has_amd_erratum(c, amd_erratum_383))
-		set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
+	set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
+
+	/*
+	 * Check models and steppings affected by erratum 400. This is
+	 * used to select the proper idle routine and to enable the
+	 * check whether the machine is affected in arch_post_acpi_subsys_init()
+	 * which sets the X86_BUG_AMD_APIC_C1E bug depending on the MSR check.
+	 */
+	if (c->x86_model > 0x2 ||
+	    (c->x86_model == 0x2 && c->x86_stepping >= 0x1))
+		setup_force_cpu_bug(X86_BUG_AMD_E400);
 }
 
 static void init_amd_ln(struct cpuinfo_x86 *c)
@@ -941,6 +913,19 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
 	clear_rdrand_cpuid_bit(c);
 }
 
+static void fix_erratum_1386(struct cpuinfo_x86 *c)
+{
+	/*
+	 * Work around Erratum 1386.  The XSAVES instruction malfunctions in
+	 * certain circumstances on Zen1/2 uarch, and not all parts have had
+	 * updated microcode at the time of writing (March 2023).
+	 *
+	 * Affected parts all have no supervisor XSAVE states, meaning that
+	 * the XSAVEC instruction (which works fine) is equivalent.
+	 */
+	clear_cpu_cap(c, X86_FEATURE_XSAVES);
+}
+
 void init_spectral_chicken(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_CPU_UNRET_ENTRY
@@ -951,34 +936,28 @@ void init_spectral_chicken(struct cpuinfo_x86 *c)
 	 *
 	 * This suppresses speculation from the middle of a basic block, i.e. it
 	 * suppresses non-branch predictions.
-	 *
-	 * We use STIBP as a heuristic to filter out Zen2 from the rest of F17H
 	 */
-	if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has(c, X86_FEATURE_AMD_STIBP)) {
+	if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) {
 		if (!rdmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, &value)) {
 			value |= MSR_ZEN2_SPECTRAL_CHICKEN_BIT;
 			wrmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, value);
 		}
 	}
 #endif
-	/*
-	 * Work around Erratum 1386.  The XSAVES instruction malfunctions in
-	 * certain circumstances on Zen1/2 uarch, and not all parts have had
-	 * updated microcode at the time of writing (March 2023).
-	 *
-	 * Affected parts all have no supervisor XSAVE states, meaning that
-	 * the XSAVEC instruction (which works fine) is equivalent.
-	 */
-	clear_cpu_cap(c, X86_FEATURE_XSAVES);
 }
 
-static void init_amd_zn(struct cpuinfo_x86 *c)
+static void init_amd_zen_common(void)
 {
-	set_cpu_cap(c, X86_FEATURE_ZEN);
-
+	setup_force_cpu_cap(X86_FEATURE_ZEN);
 #ifdef CONFIG_NUMA
 	node_reclaim_distance = 32;
 #endif
+}
+
+static void init_amd_zen1(struct cpuinfo_x86 *c)
+{
+	init_amd_zen_common();
+	fix_erratum_1386(c);
 
 	/* Fix up CPUID bits, but only if not virtualised. */
 	if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) {
@@ -986,15 +965,10 @@ static void init_amd_zn(struct cpuinfo_x86 *c)
 		/* Erratum 1076: CPB feature bit not being set in CPUID. */
 		if (!cpu_has(c, X86_FEATURE_CPB))
 			set_cpu_cap(c, X86_FEATURE_CPB);
-
-		/*
-		 * Zen3 (Fam19 model < 0x10) parts are not susceptible to
-		 * Branch Type Confusion, but predate the allocation of the
-		 * BTC_NO bit.
-		 */
-		if (c->x86 == 0x19 && !cpu_has(c, X86_FEATURE_BTC_NO))
-			set_cpu_cap(c, X86_FEATURE_BTC_NO);
 	}
+
+	pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n");
+	setup_force_cpu_bug(X86_BUG_DIV0);
 }
 
 static bool cpu_has_zenbleed_microcode(void)
@@ -1018,11 +992,8 @@ static bool cpu_has_zenbleed_microcode(void)
 	return true;
 }
 
-static void zenbleed_check(struct cpuinfo_x86 *c)
+static void zen2_zenbleed_check(struct cpuinfo_x86 *c)
 {
-	if (!cpu_has_amd_erratum(c, amd_zenbleed))
-		return;
-
 	if (cpu_has(c, X86_FEATURE_HYPERVISOR))
 		return;
 
@@ -1037,6 +1008,37 @@ static void zenbleed_check(struct cpuinfo_x86 *c)
 	}
 }
 
+static void init_amd_zen2(struct cpuinfo_x86 *c)
+{
+	init_amd_zen_common();
+	init_spectral_chicken(c);
+	fix_erratum_1386(c);
+	zen2_zenbleed_check(c);
+}
+
+static void init_amd_zen3(struct cpuinfo_x86 *c)
+{
+	init_amd_zen_common();
+
+	if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) {
+		/*
+		 * Zen3 (Fam19 model < 0x10) parts are not susceptible to
+		 * Branch Type Confusion, but predate the allocation of the
+		 * BTC_NO bit.
+		 */
+		if (!cpu_has(c, X86_FEATURE_BTC_NO))
+			set_cpu_cap(c, X86_FEATURE_BTC_NO);
+	}
+}
+
+static void init_amd_zen4(struct cpuinfo_x86 *c)
+{
+	init_amd_zen_common();
+
+	if (!cpu_has(c, X86_FEATURE_HYPERVISOR))
+		msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT);
+}
+
 static void init_amd(struct cpuinfo_x86 *c)
 {
 	u64 vm_cr;
@@ -1072,11 +1074,17 @@ static void init_amd(struct cpuinfo_x86 *c)
 	case 0x12: init_amd_ln(c); break;
 	case 0x15: init_amd_bd(c); break;
 	case 0x16: init_amd_jg(c); break;
-	case 0x17: init_spectral_chicken(c);
-		   fallthrough;
-	case 0x19: init_amd_zn(c); break;
 	}
 
+	if (boot_cpu_has(X86_FEATURE_ZEN1))
+		init_amd_zen1(c);
+	else if (boot_cpu_has(X86_FEATURE_ZEN2))
+		init_amd_zen2(c);
+	else if (boot_cpu_has(X86_FEATURE_ZEN3))
+		init_amd_zen3(c);
+	else if (boot_cpu_has(X86_FEATURE_ZEN4))
+		init_amd_zen4(c);
+
 	/*
 	 * Enable workaround for FXSAVE leak on CPUs
 	 * without a XSaveErPtr feature
@@ -1136,7 +1144,7 @@ static void init_amd(struct cpuinfo_x86 *c)
 	 * Counter May Be Inaccurate".
 	 */
 	if (cpu_has(c, X86_FEATURE_IRPERF) &&
-	    !cpu_has_amd_erratum(c, amd_erratum_1054))
+	    (boot_cpu_has(X86_FEATURE_ZEN1) && c->x86_model > 0x2f))
 		msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT);
 
 	check_null_seg_clears_base(c);
@@ -1152,16 +1160,8 @@ static void init_amd(struct cpuinfo_x86 *c)
 	    cpu_has(c, X86_FEATURE_AUTOIBRS))
 		WARN_ON_ONCE(msr_set_bit(MSR_EFER, _EFER_AUTOIBRS));
 
-	zenbleed_check(c);
-
-	if (cpu_has_amd_erratum(c, amd_div0)) {
-		pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n");
-		setup_force_cpu_bug(X86_BUG_DIV0);
-	}
-
-	if (!cpu_has(c, X86_FEATURE_HYPERVISOR) &&
-	     cpu_has_amd_erratum(c, amd_erratum_1485))
-		msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT);
+	/* AMD CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */
+	clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
 }
 
 #ifdef CONFIG_X86_32
@@ -1315,11 +1315,14 @@ static void zenbleed_check_cpu(void *unused)
 {
 	struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
 
-	zenbleed_check(c);
+	zen2_zenbleed_check(c);
 }
 
 void amd_check_microcode(void)
 {
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+		return;
+
 	on_each_cpu(zenbleed_check_cpu, NULL, 1);
 }
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b14fc8c1c953..94bff381ef20 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -188,45 +188,37 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
 	 * TLS descriptors are currently at a different place compared to i386.
 	 * Hopefully nobody expects them at a fixed place (Wine?)
 	 */
-	[GDT_ENTRY_KERNEL32_CS]		= GDT_ENTRY_INIT(0xc09b, 0, 0xfffff),
-	[GDT_ENTRY_KERNEL_CS]		= GDT_ENTRY_INIT(0xa09b, 0, 0xfffff),
-	[GDT_ENTRY_KERNEL_DS]		= GDT_ENTRY_INIT(0xc093, 0, 0xfffff),
-	[GDT_ENTRY_DEFAULT_USER32_CS]	= GDT_ENTRY_INIT(0xc0fb, 0, 0xfffff),
-	[GDT_ENTRY_DEFAULT_USER_DS]	= GDT_ENTRY_INIT(0xc0f3, 0, 0xfffff),
-	[GDT_ENTRY_DEFAULT_USER_CS]	= GDT_ENTRY_INIT(0xa0fb, 0, 0xfffff),
+	[GDT_ENTRY_KERNEL32_CS]		= GDT_ENTRY_INIT(DESC_CODE32, 0, 0xfffff),
+	[GDT_ENTRY_KERNEL_CS]		= GDT_ENTRY_INIT(DESC_CODE64, 0, 0xfffff),
+	[GDT_ENTRY_KERNEL_DS]		= GDT_ENTRY_INIT(DESC_DATA64, 0, 0xfffff),
+	[GDT_ENTRY_DEFAULT_USER32_CS]	= GDT_ENTRY_INIT(DESC_CODE32 | DESC_USER, 0, 0xfffff),
+	[GDT_ENTRY_DEFAULT_USER_DS]	= GDT_ENTRY_INIT(DESC_DATA64 | DESC_USER, 0, 0xfffff),
+	[GDT_ENTRY_DEFAULT_USER_CS]	= GDT_ENTRY_INIT(DESC_CODE64 | DESC_USER, 0, 0xfffff),
 #else
-	[GDT_ENTRY_KERNEL_CS]		= GDT_ENTRY_INIT(0xc09a, 0, 0xfffff),
-	[GDT_ENTRY_KERNEL_DS]		= GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
-	[GDT_ENTRY_DEFAULT_USER_CS]	= GDT_ENTRY_INIT(0xc0fa, 0, 0xfffff),
-	[GDT_ENTRY_DEFAULT_USER_DS]	= GDT_ENTRY_INIT(0xc0f2, 0, 0xfffff),
+	[GDT_ENTRY_KERNEL_CS]		= GDT_ENTRY_INIT(DESC_CODE32, 0, 0xfffff),
+	[GDT_ENTRY_KERNEL_DS]		= GDT_ENTRY_INIT(DESC_DATA32, 0, 0xfffff),
+	[GDT_ENTRY_DEFAULT_USER_CS]	= GDT_ENTRY_INIT(DESC_CODE32 | DESC_USER, 0, 0xfffff),
+	[GDT_ENTRY_DEFAULT_USER_DS]	= GDT_ENTRY_INIT(DESC_DATA32 | DESC_USER, 0, 0xfffff),
 	/*
 	 * Segments used for calling PnP BIOS have byte granularity.
 	 * They code segments and data segments have fixed 64k limits,
 	 * the transfer segment sizes are set at run time.
 	 */
-	/* 32-bit code */
-	[GDT_ENTRY_PNPBIOS_CS32]	= GDT_ENTRY_INIT(0x409a, 0, 0xffff),
-	/* 16-bit code */
-	[GDT_ENTRY_PNPBIOS_CS16]	= GDT_ENTRY_INIT(0x009a, 0, 0xffff),
-	/* 16-bit data */
-	[GDT_ENTRY_PNPBIOS_DS]		= GDT_ENTRY_INIT(0x0092, 0, 0xffff),
-	/* 16-bit data */
-	[GDT_ENTRY_PNPBIOS_TS1]		= GDT_ENTRY_INIT(0x0092, 0, 0),
-	/* 16-bit data */
-	[GDT_ENTRY_PNPBIOS_TS2]		= GDT_ENTRY_INIT(0x0092, 0, 0),
+	[GDT_ENTRY_PNPBIOS_CS32]	= GDT_ENTRY_INIT(DESC_CODE32_BIOS, 0, 0xffff),
+	[GDT_ENTRY_PNPBIOS_CS16]	= GDT_ENTRY_INIT(DESC_CODE16, 0, 0xffff),
+	[GDT_ENTRY_PNPBIOS_DS]		= GDT_ENTRY_INIT(DESC_DATA16, 0, 0xffff),
+	[GDT_ENTRY_PNPBIOS_TS1]		= GDT_ENTRY_INIT(DESC_DATA16, 0, 0),
+	[GDT_ENTRY_PNPBIOS_TS2]		= GDT_ENTRY_INIT(DESC_DATA16, 0, 0),
 	/*
 	 * The APM segments have byte granularity and their bases
 	 * are set at run time.  All have 64k limits.
 	 */
-	/* 32-bit code */
-	[GDT_ENTRY_APMBIOS_BASE]	= GDT_ENTRY_INIT(0x409a, 0, 0xffff),
-	/* 16-bit code */
-	[GDT_ENTRY_APMBIOS_BASE+1]	= GDT_ENTRY_INIT(0x009a, 0, 0xffff),
-	/* data */
-	[GDT_ENTRY_APMBIOS_BASE+2]	= GDT_ENTRY_INIT(0x4092, 0, 0xffff),
-
-	[GDT_ENTRY_ESPFIX_SS]		= GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
-	[GDT_ENTRY_PERCPU]		= GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
+	[GDT_ENTRY_APMBIOS_BASE]	= GDT_ENTRY_INIT(DESC_CODE32_BIOS, 0, 0xffff),
+	[GDT_ENTRY_APMBIOS_BASE+1]	= GDT_ENTRY_INIT(DESC_CODE16, 0, 0xffff),
+	[GDT_ENTRY_APMBIOS_BASE+2]	= GDT_ENTRY_INIT(DESC_DATA32_BIOS, 0, 0xffff),
+
+	[GDT_ENTRY_ESPFIX_SS]		= GDT_ENTRY_INIT(DESC_DATA32, 0, 0xfffff),
+	[GDT_ENTRY_PERCPU]		= GDT_ENTRY_INIT(DESC_DATA32, 0, 0xfffff),
 #endif
 } };
 EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
@@ -1856,6 +1848,13 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0);
 #endif
 
+
+	/*
+	 * Set default APIC and TSC_DEADLINE MSR fencing flag. AMD and
+	 * Hygon will clear it in ->c_init() below.
+	 */
+	set_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
+
 	/*
 	 * Vendor-specific initialization.  In this section we
 	 * canonicalize the feature flags, meaning if there are
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index 6f247d66758d..f0cd95502faa 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -354,6 +354,9 @@ static void init_hygon(struct cpuinfo_x86 *c)
 		set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
 
 	check_null_seg_clears_base(c);
+
+	/* Hygon CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */
+	clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
 }
 
 static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c
index e4c3ba91321c..f18d35fe27a9 100644
--- a/arch/x86/kernel/cpu/intel_epb.c
+++ b/arch/x86/kernel/cpu/intel_epb.c
@@ -237,4 +237,4 @@ err_out_online:
 	cpuhp_remove_state(CPUHP_AP_X86_INTEL_EPB_ONLINE);
 	return ret;
 }
-subsys_initcall(intel_epb_init);
+late_initcall(intel_epb_init);
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index f3517b8a8e91..2b46eb0fdf3a 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -87,42 +87,40 @@ struct smca_bank {
 static DEFINE_PER_CPU_READ_MOSTLY(struct smca_bank[MAX_NR_BANKS], smca_banks);
 static DEFINE_PER_CPU_READ_MOSTLY(u8[N_SMCA_BANK_TYPES], smca_bank_counts);
 
-struct smca_bank_name {
-	const char *name;	/* Short name for sysfs */
-	const char *long_name;	/* Long name for pretty-printing */
-};
-
-static struct smca_bank_name smca_names[] = {
-	[SMCA_LS ... SMCA_LS_V2]	= { "load_store",	"Load Store Unit" },
-	[SMCA_IF]			= { "insn_fetch",	"Instruction Fetch Unit" },
-	[SMCA_L2_CACHE]			= { "l2_cache",		"L2 Cache" },
-	[SMCA_DE]			= { "decode_unit",	"Decode Unit" },
-	[SMCA_RESERVED]			= { "reserved",		"Reserved" },
-	[SMCA_EX]			= { "execution_unit",	"Execution Unit" },
-	[SMCA_FP]			= { "floating_point",	"Floating Point Unit" },
-	[SMCA_L3_CACHE]			= { "l3_cache",		"L3 Cache" },
-	[SMCA_CS ... SMCA_CS_V2]	= { "coherent_slave",	"Coherent Slave" },
-	[SMCA_PIE]			= { "pie",		"Power, Interrupts, etc." },
+static const char * const smca_names[] = {
+	[SMCA_LS ... SMCA_LS_V2]	= "load_store",
+	[SMCA_IF]			= "insn_fetch",
+	[SMCA_L2_CACHE]			= "l2_cache",
+	[SMCA_DE]			= "decode_unit",
+	[SMCA_RESERVED]			= "reserved",
+	[SMCA_EX]			= "execution_unit",
+	[SMCA_FP]			= "floating_point",
+	[SMCA_L3_CACHE]			= "l3_cache",
+	[SMCA_CS ... SMCA_CS_V2]	= "coherent_slave",
+	[SMCA_PIE]			= "pie",
 
 	/* UMC v2 is separate because both of them can exist in a single system. */
-	[SMCA_UMC]			= { "umc",		"Unified Memory Controller" },
-	[SMCA_UMC_V2]			= { "umc_v2",		"Unified Memory Controller v2" },
-	[SMCA_PB]			= { "param_block",	"Parameter Block" },
-	[SMCA_PSP ... SMCA_PSP_V2]	= { "psp",		"Platform Security Processor" },
-	[SMCA_SMU ... SMCA_SMU_V2]	= { "smu",		"System Management Unit" },
-	[SMCA_MP5]			= { "mp5",		"Microprocessor 5 Unit" },
-	[SMCA_MPDMA]			= { "mpdma",		"MPDMA Unit" },
-	[SMCA_NBIO]			= { "nbio",		"Northbridge IO Unit" },
-	[SMCA_PCIE ... SMCA_PCIE_V2]	= { "pcie",		"PCI Express Unit" },
-	[SMCA_XGMI_PCS]			= { "xgmi_pcs",		"Ext Global Memory Interconnect PCS Unit" },
-	[SMCA_NBIF]			= { "nbif",		"NBIF Unit" },
-	[SMCA_SHUB]			= { "shub",		"System Hub Unit" },
-	[SMCA_SATA]			= { "sata",		"SATA Unit" },
-	[SMCA_USB]			= { "usb",		"USB Unit" },
-	[SMCA_GMI_PCS]			= { "gmi_pcs",		"Global Memory Interconnect PCS Unit" },
-	[SMCA_XGMI_PHY]			= { "xgmi_phy",		"Ext Global Memory Interconnect PHY Unit" },
-	[SMCA_WAFL_PHY]			= { "wafl_phy",		"WAFL PHY Unit" },
-	[SMCA_GMI_PHY]			= { "gmi_phy",		"Global Memory Interconnect PHY Unit" },
+	[SMCA_UMC]			= "umc",
+	[SMCA_UMC_V2]			= "umc_v2",
+	[SMCA_MA_LLC]			= "ma_llc",
+	[SMCA_PB]			= "param_block",
+	[SMCA_PSP ... SMCA_PSP_V2]	= "psp",
+	[SMCA_SMU ... SMCA_SMU_V2]	= "smu",
+	[SMCA_MP5]			= "mp5",
+	[SMCA_MPDMA]			= "mpdma",
+	[SMCA_NBIO]			= "nbio",
+	[SMCA_PCIE ... SMCA_PCIE_V2]	= "pcie",
+	[SMCA_XGMI_PCS]			= "xgmi_pcs",
+	[SMCA_NBIF]			= "nbif",
+	[SMCA_SHUB]			= "shub",
+	[SMCA_SATA]			= "sata",
+	[SMCA_USB]			= "usb",
+	[SMCA_USR_DP]			= "usr_dp",
+	[SMCA_USR_CP]			= "usr_cp",
+	[SMCA_GMI_PCS]			= "gmi_pcs",
+	[SMCA_XGMI_PHY]			= "xgmi_phy",
+	[SMCA_WAFL_PHY]			= "wafl_phy",
+	[SMCA_GMI_PHY]			= "gmi_phy",
 };
 
 static const char *smca_get_name(enum smca_bank_types t)
@@ -130,17 +128,8 @@ static const char *smca_get_name(enum smca_bank_types t)
 	if (t >= N_SMCA_BANK_TYPES)
 		return NULL;
 
-	return smca_names[t].name;
-}
-
-const char *smca_get_long_name(enum smca_bank_types t)
-{
-	if (t >= N_SMCA_BANK_TYPES)
-		return NULL;
-
-	return smca_names[t].long_name;
+	return smca_names[t];
 }
-EXPORT_SYMBOL_GPL(smca_get_long_name);
 
 enum smca_bank_types smca_get_bank_type(unsigned int cpu, unsigned int bank)
 {
@@ -178,6 +167,7 @@ static const struct smca_hwid smca_hwid_mcatypes[] = {
 	{ SMCA_CS,	 HWID_MCATYPE(0x2E, 0x0)	},
 	{ SMCA_PIE,	 HWID_MCATYPE(0x2E, 0x1)	},
 	{ SMCA_CS_V2,	 HWID_MCATYPE(0x2E, 0x2)	},
+	{ SMCA_MA_LLC,	 HWID_MCATYPE(0x2E, 0x4)	},
 
 	/* Unified Memory Controller MCA type */
 	{ SMCA_UMC,	 HWID_MCATYPE(0x96, 0x0)	},
@@ -212,6 +202,8 @@ static const struct smca_hwid smca_hwid_mcatypes[] = {
 	{ SMCA_SHUB,	 HWID_MCATYPE(0x80, 0x0)	},
 	{ SMCA_SATA,	 HWID_MCATYPE(0xA8, 0x0)	},
 	{ SMCA_USB,	 HWID_MCATYPE(0xAA, 0x0)	},
+	{ SMCA_USR_DP,	 HWID_MCATYPE(0x170, 0x0)	},
+	{ SMCA_USR_CP,	 HWID_MCATYPE(0x180, 0x0)	},
 	{ SMCA_GMI_PCS,  HWID_MCATYPE(0x241, 0x0)	},
 	{ SMCA_XGMI_PHY, HWID_MCATYPE(0x259, 0x0)	},
 	{ SMCA_WAFL_PHY, HWID_MCATYPE(0x267, 0x0)	},
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 7b397370b4d6..fd5ce12c4f9a 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -44,6 +44,7 @@
 #include <linux/sync_core.h>
 #include <linux/task_work.h>
 #include <linux/hardirq.h>
+#include <linux/kexec.h>
 
 #include <asm/intel-family.h>
 #include <asm/processor.h>
@@ -233,6 +234,7 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp)
 	struct llist_node *pending;
 	struct mce_evt_llist *l;
 	int apei_err = 0;
+	struct page *p;
 
 	/*
 	 * Allow instrumentation around external facilities usage. Not that it
@@ -286,6 +288,20 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp)
 	if (!fake_panic) {
 		if (panic_timeout == 0)
 			panic_timeout = mca_cfg.panic_timeout;
+
+		/*
+		 * Kdump skips the poisoned page in order to avoid
+		 * touching the error bits again. Poison the page even
+		 * if the error is fatal and the machine is about to
+		 * panic.
+		 */
+		if (kexec_crash_loaded()) {
+			if (final && (final->status & MCI_STATUS_ADDRV)) {
+				p = pfn_to_online_page(final->addr >> PAGE_SHIFT);
+				if (p)
+					SetPageHWPoison(p);
+			}
+		}
 		panic(msg);
 	} else
 		pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg);
@@ -670,6 +686,16 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 		barrier();
 		m.status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS));
 
+		/*
+		 * Update storm tracking here, before checking for the
+		 * MCI_STATUS_VAL bit. Valid corrected errors count
+		 * towards declaring, or maintaining, storm status. No
+		 * error in a bank counts towards avoiding, or ending,
+		 * storm status.
+		 */
+		if (!mca_cfg.cmci_disabled)
+			mce_track_storm(&m);
+
 		/* If this entry is not valid, ignore it */
 		if (!(m.status & MCI_STATUS_VAL))
 			continue;
@@ -1601,13 +1627,6 @@ static unsigned long check_interval = INITIAL_CHECK_INTERVAL;
 static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */
 static DEFINE_PER_CPU(struct timer_list, mce_timer);
 
-static unsigned long mce_adjust_timer_default(unsigned long interval)
-{
-	return interval;
-}
-
-static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default;
-
 static void __start_timer(struct timer_list *t, unsigned long interval)
 {
 	unsigned long when = jiffies + interval;
@@ -1637,15 +1656,9 @@ static void mce_timer_fn(struct timer_list *t)
 
 	iv = __this_cpu_read(mce_next_interval);
 
-	if (mce_available(this_cpu_ptr(&cpu_info))) {
+	if (mce_available(this_cpu_ptr(&cpu_info)))
 		mc_poll_banks();
 
-		if (mce_intel_cmci_poll()) {
-			iv = mce_adjust_timer(iv);
-			goto done;
-		}
-	}
-
 	/*
 	 * Alert userspace if needed. If we logged an MCE, reduce the polling
 	 * interval, otherwise increase the polling interval.
@@ -1655,23 +1668,29 @@ static void mce_timer_fn(struct timer_list *t)
 	else
 		iv = min(iv * 2, round_jiffies_relative(check_interval * HZ));
 
-done:
-	__this_cpu_write(mce_next_interval, iv);
-	__start_timer(t, iv);
+	if (mce_get_storm_mode()) {
+		__start_timer(t, HZ);
+	} else {
+		__this_cpu_write(mce_next_interval, iv);
+		__start_timer(t, iv);
+	}
 }
 
 /*
- * Ensure that the timer is firing in @interval from now.
+ * When a storm starts on any bank on this CPU, switch to polling
+ * once per second. When the storm ends, revert to the default
+ * polling interval.
  */
-void mce_timer_kick(unsigned long interval)
+void mce_timer_kick(bool storm)
 {
 	struct timer_list *t = this_cpu_ptr(&mce_timer);
-	unsigned long iv = __this_cpu_read(mce_next_interval);
 
-	__start_timer(t, interval);
+	mce_set_storm_mode(storm);
 
-	if (interval < iv)
-		__this_cpu_write(mce_next_interval, interval);
+	if (storm)
+		__start_timer(t, HZ);
+	else
+		__this_cpu_write(mce_next_interval, check_interval * HZ);
 }
 
 /* Must not be called in IRQ context where del_timer_sync() can deadlock */
@@ -1995,7 +2014,6 @@ static void mce_zhaoxin_feature_init(struct cpuinfo_x86 *c)
 
 	intel_init_cmci();
 	intel_init_lmce();
-	mce_adjust_timer = cmci_intel_adjust_timer;
 }
 
 static void mce_zhaoxin_feature_clear(struct cpuinfo_x86 *c)
@@ -2008,7 +2026,6 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 	switch (c->x86_vendor) {
 	case X86_VENDOR_INTEL:
 		mce_intel_feature_init(c);
-		mce_adjust_timer = cmci_intel_adjust_timer;
 		break;
 
 	case X86_VENDOR_AMD: {
@@ -2568,9 +2585,6 @@ static int mce_device_create(unsigned int cpu)
 	int err;
 	int i, j;
 
-	if (!mce_available(&boot_cpu_data))
-		return -EIO;
-
 	dev = per_cpu(mce_device, cpu);
 	if (dev)
 		return 0;
@@ -2665,8 +2679,6 @@ static void mce_reenable_cpu(void)
 
 static int mce_cpu_dead(unsigned int cpu)
 {
-	mce_intel_hcpu_update(cpu);
-
 	/* intentionally ignoring frozen here */
 	if (!cpuhp_tasks_frozen)
 		cmci_rediscover();
diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 4d8d4bcf915d..72f0695c3dc1 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -746,6 +746,7 @@ static void check_hw_inj_possible(void)
 
 		wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), status);
 		rdmsrl_safe(mca_msr_reg(bank, MCA_STATUS), &status);
+		wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), 0);
 
 		if (!status) {
 			hw_injection_possible = false;
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index 52bce533ddcc..399b62e223d2 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -42,15 +42,6 @@
 static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned);
 
 /*
- * CMCI storm detection backoff counter
- *
- * During storm, we reset this counter to INITIAL_CHECK_INTERVAL in case we've
- * encountered an error. If not, we decrement it by one. We signal the end of
- * the CMCI storm when it reaches 0.
- */
-static DEFINE_PER_CPU(int, cmci_backoff_cnt);
-
-/*
  * cmci_discover_lock protects against parallel discovery attempts
  * which could race against each other.
  */
@@ -63,22 +54,26 @@ static DEFINE_RAW_SPINLOCK(cmci_discover_lock);
  */
 static DEFINE_SPINLOCK(cmci_poll_lock);
 
+/* Linux non-storm CMCI threshold (may be overridden by BIOS) */
 #define CMCI_THRESHOLD		1
-#define CMCI_POLL_INTERVAL	(30 * HZ)
-#define CMCI_STORM_INTERVAL	(HZ)
-#define CMCI_STORM_THRESHOLD	15
 
-static DEFINE_PER_CPU(unsigned long, cmci_time_stamp);
-static DEFINE_PER_CPU(unsigned int, cmci_storm_cnt);
-static DEFINE_PER_CPU(unsigned int, cmci_storm_state);
-
-enum {
-	CMCI_STORM_NONE,
-	CMCI_STORM_ACTIVE,
-	CMCI_STORM_SUBSIDED,
-};
+/*
+ * MCi_CTL2 threshold for each bank when there is no storm.
+ * Default value for each bank may have been set by BIOS.
+ */
+static u16 cmci_threshold[MAX_NR_BANKS];
 
-static atomic_t cmci_storm_on_cpus;
+/*
+ * High threshold to limit CMCI rate during storms. Max supported is
+ * 0x7FFF. Use this slightly smaller value so it has a distinctive
+ * signature when some asks "Why am I not seeing all corrected errors?"
+ * A high threshold is used instead of just disabling CMCI for a
+ * bank because both corrected and uncorrected errors may be logged
+ * in the same bank and signalled with CMCI. The threshold only applies
+ * to corrected errors, so keeping CMCI enabled means that uncorrected
+ * errors will still be processed in a timely fashion.
+ */
+#define CMCI_STORM_THRESHOLD	32749
 
 static int cmci_supported(int *banks)
 {
@@ -134,204 +129,166 @@ static bool lmce_supported(void)
 	return tmp & FEAT_CTL_LMCE_ENABLED;
 }
 
-bool mce_intel_cmci_poll(void)
+/*
+ * Set a new CMCI threshold value. Preserve the state of the
+ * MCI_CTL2_CMCI_EN bit in case this happens during a
+ * cmci_rediscover() operation.
+ */
+static void cmci_set_threshold(int bank, int thresh)
 {
-	if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE)
-		return false;
-
-	/*
-	 * Reset the counter if we've logged an error in the last poll
-	 * during the storm.
-	 */
-	if (machine_check_poll(0, this_cpu_ptr(&mce_banks_owned)))
-		this_cpu_write(cmci_backoff_cnt, INITIAL_CHECK_INTERVAL);
-	else
-		this_cpu_dec(cmci_backoff_cnt);
+	unsigned long flags;
+	u64 val;
 
-	return true;
+	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
+	rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+	val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK;
+	wrmsrl(MSR_IA32_MCx_CTL2(bank), val | thresh);
+	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
-void mce_intel_hcpu_update(unsigned long cpu)
+void mce_intel_handle_storm(int bank, bool on)
 {
-	if (per_cpu(cmci_storm_state, cpu) == CMCI_STORM_ACTIVE)
-		atomic_dec(&cmci_storm_on_cpus);
+	if (on)
+		cmci_set_threshold(bank, CMCI_STORM_THRESHOLD);
+	else
+		cmci_set_threshold(bank, cmci_threshold[bank]);
+}
 
-	per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE;
+/*
+ * The interrupt handler. This is called on every event.
+ * Just call the poller directly to log any events.
+ * This could in theory increase the threshold under high load,
+ * but doesn't for now.
+ */
+static void intel_threshold_interrupt(void)
+{
+	machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
 }
 
-static void cmci_toggle_interrupt_mode(bool on)
+/*
+ * Check all the reasons why current CPU cannot claim
+ * ownership of a bank.
+ * 1: CPU already owns this bank
+ * 2: BIOS owns this bank
+ * 3: Some other CPU owns this bank
+ */
+static bool cmci_skip_bank(int bank, u64 *val)
 {
-	unsigned long flags, *owned;
-	int bank;
-	u64 val;
+	unsigned long *owned = (void *)this_cpu_ptr(&mce_banks_owned);
 
-	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
-	owned = this_cpu_ptr(mce_banks_owned);
-	for_each_set_bit(bank, owned, MAX_NR_BANKS) {
-		rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+	if (test_bit(bank, owned))
+		return true;
 
-		if (on)
-			val |= MCI_CTL2_CMCI_EN;
-		else
-			val &= ~MCI_CTL2_CMCI_EN;
+	/* Skip banks in firmware first mode */
+	if (test_bit(bank, mce_banks_ce_disabled))
+		return true;
 
-		wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
-	}
-	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
-}
+	rdmsrl(MSR_IA32_MCx_CTL2(bank), *val);
 
-unsigned long cmci_intel_adjust_timer(unsigned long interval)
-{
-	if ((this_cpu_read(cmci_backoff_cnt) > 0) &&
-	    (__this_cpu_read(cmci_storm_state) == CMCI_STORM_ACTIVE)) {
-		mce_notify_irq();
-		return CMCI_STORM_INTERVAL;
+	/* Already owned by someone else? */
+	if (*val & MCI_CTL2_CMCI_EN) {
+		clear_bit(bank, owned);
+		__clear_bit(bank, this_cpu_ptr(mce_poll_banks));
+		return true;
 	}
 
-	switch (__this_cpu_read(cmci_storm_state)) {
-	case CMCI_STORM_ACTIVE:
-
-		/*
-		 * We switch back to interrupt mode once the poll timer has
-		 * silenced itself. That means no events recorded and the timer
-		 * interval is back to our poll interval.
-		 */
-		__this_cpu_write(cmci_storm_state, CMCI_STORM_SUBSIDED);
-		if (!atomic_sub_return(1, &cmci_storm_on_cpus))
-			pr_notice("CMCI storm subsided: switching to interrupt mode\n");
+	return false;
+}
 
-		fallthrough;
+/*
+ * Decide which CMCI interrupt threshold to use:
+ * 1: If this bank is in storm mode from whichever CPU was
+ *    the previous owner, stay in storm mode.
+ * 2: If ignoring any threshold set by BIOS, set Linux default
+ * 3: Try to honor BIOS threshold (unless buggy BIOS set it at zero).
+ */
+static u64 cmci_pick_threshold(u64 val, int *bios_zero_thresh)
+{
+	if ((val & MCI_CTL2_CMCI_THRESHOLD_MASK) == CMCI_STORM_THRESHOLD)
+		return val;
 
-	case CMCI_STORM_SUBSIDED:
+	if (!mca_cfg.bios_cmci_threshold) {
+		val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK;
+		val |= CMCI_THRESHOLD;
+	} else if (!(val & MCI_CTL2_CMCI_THRESHOLD_MASK)) {
 		/*
-		 * We wait for all CPUs to go back to SUBSIDED state. When that
-		 * happens we switch back to interrupt mode.
+		 * If bios_cmci_threshold boot option was specified
+		 * but the threshold is zero, we'll try to initialize
+		 * it to 1.
 		 */
-		if (!atomic_read(&cmci_storm_on_cpus)) {
-			__this_cpu_write(cmci_storm_state, CMCI_STORM_NONE);
-			cmci_toggle_interrupt_mode(true);
-			cmci_recheck();
-		}
-		return CMCI_POLL_INTERVAL;
-	default:
-
-		/* We have shiny weather. Let the poll do whatever it thinks. */
-		return interval;
+		*bios_zero_thresh = 1;
+		val |= CMCI_THRESHOLD;
 	}
+
+	return val;
 }
 
-static bool cmci_storm_detect(void)
+/*
+ * Try to claim ownership of a bank.
+ */
+static void cmci_claim_bank(int bank, u64 val, int bios_zero_thresh, int *bios_wrong_thresh)
 {
-	unsigned int cnt = __this_cpu_read(cmci_storm_cnt);
-	unsigned long ts = __this_cpu_read(cmci_time_stamp);
-	unsigned long now = jiffies;
-	int r;
+	struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc);
 
-	if (__this_cpu_read(cmci_storm_state) != CMCI_STORM_NONE)
-		return true;
+	val |= MCI_CTL2_CMCI_EN;
+	wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
+	rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
 
-	if (time_before_eq(now, ts + CMCI_STORM_INTERVAL)) {
-		cnt++;
-	} else {
-		cnt = 1;
-		__this_cpu_write(cmci_time_stamp, now);
+	/* If the enable bit did not stick, this bank should be polled. */
+	if (!(val & MCI_CTL2_CMCI_EN)) {
+		WARN_ON(!test_bit(bank, this_cpu_ptr(mce_poll_banks)));
+		storm->banks[bank].poll_only = true;
+		return;
 	}
-	__this_cpu_write(cmci_storm_cnt, cnt);
 
-	if (cnt <= CMCI_STORM_THRESHOLD)
-		return false;
-
-	cmci_toggle_interrupt_mode(false);
-	__this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE);
-	r = atomic_add_return(1, &cmci_storm_on_cpus);
-	mce_timer_kick(CMCI_STORM_INTERVAL);
-	this_cpu_write(cmci_backoff_cnt, INITIAL_CHECK_INTERVAL);
+	/* This CPU successfully set the enable bit. */
+	set_bit(bank, (void *)this_cpu_ptr(&mce_banks_owned));
 
-	if (r == 1)
-		pr_notice("CMCI storm detected: switching to poll mode\n");
-	return true;
-}
+	if ((val & MCI_CTL2_CMCI_THRESHOLD_MASK) == CMCI_STORM_THRESHOLD) {
+		pr_notice("CPU%d BANK%d CMCI inherited storm\n", smp_processor_id(), bank);
+		mce_inherit_storm(bank);
+		cmci_storm_begin(bank);
+	} else {
+		__clear_bit(bank, this_cpu_ptr(mce_poll_banks));
+	}
 
-/*
- * The interrupt handler. This is called on every event.
- * Just call the poller directly to log any events.
- * This could in theory increase the threshold under high load,
- * but doesn't for now.
- */
-static void intel_threshold_interrupt(void)
-{
-	if (cmci_storm_detect())
-		return;
+	/*
+	 * We are able to set thresholds for some banks that
+	 * had a threshold of 0. This means the BIOS has not
+	 * set the thresholds properly or does not work with
+	 * this boot option. Note down now and report later.
+	 */
+	if (mca_cfg.bios_cmci_threshold && bios_zero_thresh &&
+	    (val & MCI_CTL2_CMCI_THRESHOLD_MASK))
+		*bios_wrong_thresh = 1;
 
-	machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
+	/* Save default threshold for each bank */
+	if (cmci_threshold[bank] == 0)
+		cmci_threshold[bank] = val & MCI_CTL2_CMCI_THRESHOLD_MASK;
 }
 
 /*
  * Enable CMCI (Corrected Machine Check Interrupt) for available MCE banks
  * on this CPU. Use the algorithm recommended in the SDM to discover shared
- * banks.
+ * banks. Called during initial bootstrap, and also for hotplug CPU operations
+ * to rediscover/reassign machine check banks.
  */
 static void cmci_discover(int banks)
 {
-	unsigned long *owned = (void *)this_cpu_ptr(&mce_banks_owned);
+	int bios_wrong_thresh = 0;
 	unsigned long flags;
 	int i;
-	int bios_wrong_thresh = 0;
 
 	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
 	for (i = 0; i < banks; i++) {
 		u64 val;
 		int bios_zero_thresh = 0;
 
-		if (test_bit(i, owned))
+		if (cmci_skip_bank(i, &val))
 			continue;
 
-		/* Skip banks in firmware first mode */
-		if (test_bit(i, mce_banks_ce_disabled))
-			continue;
-
-		rdmsrl(MSR_IA32_MCx_CTL2(i), val);
-
-		/* Already owned by someone else? */
-		if (val & MCI_CTL2_CMCI_EN) {
-			clear_bit(i, owned);
-			__clear_bit(i, this_cpu_ptr(mce_poll_banks));
-			continue;
-		}
-
-		if (!mca_cfg.bios_cmci_threshold) {
-			val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK;
-			val |= CMCI_THRESHOLD;
-		} else if (!(val & MCI_CTL2_CMCI_THRESHOLD_MASK)) {
-			/*
-			 * If bios_cmci_threshold boot option was specified
-			 * but the threshold is zero, we'll try to initialize
-			 * it to 1.
-			 */
-			bios_zero_thresh = 1;
-			val |= CMCI_THRESHOLD;
-		}
-
-		val |= MCI_CTL2_CMCI_EN;
-		wrmsrl(MSR_IA32_MCx_CTL2(i), val);
-		rdmsrl(MSR_IA32_MCx_CTL2(i), val);
-
-		/* Did the enable bit stick? -- the bank supports CMCI */
-		if (val & MCI_CTL2_CMCI_EN) {
-			set_bit(i, owned);
-			__clear_bit(i, this_cpu_ptr(mce_poll_banks));
-			/*
-			 * We are able to set thresholds for some banks that
-			 * had a threshold of 0. This means the BIOS has not
-			 * set the thresholds properly or does not work with
-			 * this boot option. Note down now and report later.
-			 */
-			if (mca_cfg.bios_cmci_threshold && bios_zero_thresh &&
-					(val & MCI_CTL2_CMCI_THRESHOLD_MASK))
-				bios_wrong_thresh = 1;
-		} else {
-			WARN_ON(!test_bit(i, this_cpu_ptr(mce_poll_banks)));
-		}
+		val = cmci_pick_threshold(val, &bios_zero_thresh);
+		cmci_claim_bank(i, val, bios_zero_thresh, &bios_wrong_thresh);
 	}
 	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
 	if (mca_cfg.bios_cmci_threshold && bios_wrong_thresh) {
@@ -370,6 +327,9 @@ static void __cmci_disable_bank(int bank)
 	val &= ~MCI_CTL2_CMCI_EN;
 	wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
 	__clear_bit(bank, this_cpu_ptr(mce_banks_owned));
+
+	if ((val & MCI_CTL2_CMCI_THRESHOLD_MASK) == CMCI_STORM_THRESHOLD)
+		cmci_storm_end(bank);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index e13a26c9c0ac..01f8f03969e6 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -41,9 +41,7 @@ struct dentry *mce_get_debugfs_dir(void);
 extern mce_banks_t mce_banks_ce_disabled;
 
 #ifdef CONFIG_X86_MCE_INTEL
-unsigned long cmci_intel_adjust_timer(unsigned long interval);
-bool mce_intel_cmci_poll(void);
-void mce_intel_hcpu_update(unsigned long cpu);
+void mce_intel_handle_storm(int bank, bool on);
 void cmci_disable_bank(int bank);
 void intel_init_cmci(void);
 void intel_init_lmce(void);
@@ -51,9 +49,7 @@ void intel_clear_lmce(void);
 bool intel_filter_mce(struct mce *m);
 bool intel_mce_usable_address(struct mce *m);
 #else
-# define cmci_intel_adjust_timer mce_adjust_timer_default
-static inline bool mce_intel_cmci_poll(void) { return false; }
-static inline void mce_intel_hcpu_update(unsigned long cpu) { }
+static inline void mce_intel_handle_storm(int bank, bool on) { }
 static inline void cmci_disable_bank(int bank) { }
 static inline void intel_init_cmci(void) { }
 static inline void intel_init_lmce(void) { }
@@ -62,7 +58,63 @@ static inline bool intel_filter_mce(struct mce *m) { return false; }
 static inline bool intel_mce_usable_address(struct mce *m) { return false; }
 #endif
 
-void mce_timer_kick(unsigned long interval);
+void mce_timer_kick(bool storm);
+
+#ifdef CONFIG_X86_MCE_THRESHOLD
+void cmci_storm_begin(unsigned int bank);
+void cmci_storm_end(unsigned int bank);
+void mce_track_storm(struct mce *mce);
+void mce_inherit_storm(unsigned int bank);
+bool mce_get_storm_mode(void);
+void mce_set_storm_mode(bool storm);
+#else
+static inline void cmci_storm_begin(unsigned int bank) {}
+static inline void cmci_storm_end(unsigned int bank) {}
+static inline void mce_track_storm(struct mce *mce) {}
+static inline void mce_inherit_storm(unsigned int bank) {}
+static inline bool mce_get_storm_mode(void) { return false; }
+static inline void mce_set_storm_mode(bool storm) {}
+#endif
+
+/*
+ * history:		Bitmask tracking errors occurrence. Each set bit
+ *			represents an error seen.
+ *
+ * timestamp:		Last time (in jiffies) that the bank was polled.
+ * in_storm_mode:	Is this bank in storm mode?
+ * poll_only:		Bank does not support CMCI, skip storm tracking.
+ */
+struct storm_bank {
+	u64 history;
+	u64 timestamp;
+	bool in_storm_mode;
+	bool poll_only;
+};
+
+#define NUM_HISTORY_BITS (sizeof(u64) * BITS_PER_BYTE)
+
+/* How many errors within the history buffer mark the start of a storm. */
+#define STORM_BEGIN_THRESHOLD	5
+
+/*
+ * How many polls of machine check bank without an error before declaring
+ * the storm is over. Since it is tracked by the bitmasks in the history
+ * field of struct storm_bank the mask is 30 bits [0 ... 29].
+ */
+#define STORM_END_POLL_THRESHOLD	29
+
+/*
+ * banks:		per-cpu, per-bank details
+ * stormy_bank_count:	count of MC banks in storm state
+ * poll_mode:		CPU is in poll mode
+ */
+struct mca_storm_desc {
+	struct storm_bank	banks[MAX_NR_BANKS];
+	u8			stormy_bank_count;
+	bool			poll_mode;
+};
+
+DECLARE_PER_CPU(struct mca_storm_desc, storm_desc);
 
 #ifdef CONFIG_ACPI_APEI
 int apei_write_mce(struct mce *m);
diff --git a/arch/x86/kernel/cpu/mce/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c
index ef4e7bb5fd88..89e31e1e5c9c 100644
--- a/arch/x86/kernel/cpu/mce/threshold.c
+++ b/arch/x86/kernel/cpu/mce/threshold.c
@@ -29,3 +29,118 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_threshold)
 	trace_threshold_apic_exit(THRESHOLD_APIC_VECTOR);
 	apic_eoi();
 }
+
+DEFINE_PER_CPU(struct mca_storm_desc, storm_desc);
+
+void mce_inherit_storm(unsigned int bank)
+{
+	struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc);
+
+	/*
+	 * Previous CPU owning this bank had put it into storm mode,
+	 * but the precise history of that storm is unknown. Assume
+	 * the worst (all recent polls of the bank found a valid error
+	 * logged). This will avoid the new owner prematurely declaring
+	 * the storm has ended.
+	 */
+	storm->banks[bank].history = ~0ull;
+	storm->banks[bank].timestamp = jiffies;
+}
+
+bool mce_get_storm_mode(void)
+{
+	return __this_cpu_read(storm_desc.poll_mode);
+}
+
+void mce_set_storm_mode(bool storm)
+{
+	__this_cpu_write(storm_desc.poll_mode, storm);
+}
+
+static void mce_handle_storm(unsigned int bank, bool on)
+{
+	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_INTEL:
+		mce_intel_handle_storm(bank, on);
+		break;
+	}
+}
+
+void cmci_storm_begin(unsigned int bank)
+{
+	struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc);
+
+	__set_bit(bank, this_cpu_ptr(mce_poll_banks));
+	storm->banks[bank].in_storm_mode = true;
+
+	/*
+	 * If this is the first bank on this CPU to enter storm mode
+	 * start polling.
+	 */
+	if (++storm->stormy_bank_count == 1)
+		mce_timer_kick(true);
+}
+
+void cmci_storm_end(unsigned int bank)
+{
+	struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc);
+
+	__clear_bit(bank, this_cpu_ptr(mce_poll_banks));
+	storm->banks[bank].history = 0;
+	storm->banks[bank].in_storm_mode = false;
+
+	/* If no banks left in storm mode, stop polling. */
+	if (!this_cpu_dec_return(storm_desc.stormy_bank_count))
+		mce_timer_kick(false);
+}
+
+void mce_track_storm(struct mce *mce)
+{
+	struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc);
+	unsigned long now = jiffies, delta;
+	unsigned int shift = 1;
+	u64 history = 0;
+
+	/* No tracking needed for banks that do not support CMCI */
+	if (storm->banks[mce->bank].poll_only)
+		return;
+
+	/*
+	 * When a bank is in storm mode it is polled once per second and
+	 * the history mask will record about the last minute of poll results.
+	 * If it is not in storm mode, then the bank is only checked when
+	 * there is a CMCI interrupt. Check how long it has been since
+	 * this bank was last checked, and adjust the amount of "shift"
+	 * to apply to history.
+	 */
+	if (!storm->banks[mce->bank].in_storm_mode) {
+		delta = now - storm->banks[mce->bank].timestamp;
+		shift = (delta + HZ) / HZ;
+	}
+
+	/* If it has been a long time since the last poll, clear history. */
+	if (shift < NUM_HISTORY_BITS)
+		history = storm->banks[mce->bank].history << shift;
+
+	storm->banks[mce->bank].timestamp = now;
+
+	/* History keeps track of corrected errors. VAL=1 && UC=0 */
+	if ((mce->status & MCI_STATUS_VAL) && mce_is_correctable(mce))
+		history |= 1;
+
+	storm->banks[mce->bank].history = history;
+
+	if (storm->banks[mce->bank].in_storm_mode) {
+		if (history & GENMASK_ULL(STORM_END_POLL_THRESHOLD, 0))
+			return;
+		printk_deferred(KERN_NOTICE "CPU%d BANK%d CMCI storm subsided\n", smp_processor_id(), mce->bank);
+		mce_handle_storm(mce->bank, false);
+		cmci_storm_end(mce->bank);
+	} else {
+		if (hweight64(history) < STORM_BEGIN_THRESHOLD)
+			return;
+		printk_deferred(KERN_NOTICE "CPU%d BANK%d CMCI storm detected\n", smp_processor_id(), mce->bank);
+		mce_handle_storm(mce->bank, true);
+		cmci_storm_begin(mce->bank);
+	}
+}
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 9373ec01c5ae..13b45b9c806d 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -104,8 +104,6 @@ struct cont_desc {
 	size_t		     size;
 };
 
-static u32 ucode_new_rev;
-
 /*
  * Microcode patch container file is prepended to the initrd in cpio
  * format. See Documentation/arch/x86/microcode.rst
@@ -442,12 +440,11 @@ static int __apply_microcode_amd(struct microcode_amd *mc)
  *
  * Returns true if container found (sets @desc), false otherwise.
  */
-static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size)
+static bool early_apply_microcode(u32 cpuid_1_eax, u32 old_rev, void *ucode, size_t size)
 {
 	struct cont_desc desc = { 0 };
 	struct microcode_amd *mc;
 	bool ret = false;
-	u32 rev, dummy;
 
 	desc.cpuid_1_eax = cpuid_1_eax;
 
@@ -457,22 +454,15 @@ static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size)
 	if (!mc)
 		return ret;
 
-	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-
 	/*
 	 * Allow application of the same revision to pick up SMT-specific
 	 * changes even if the revision of the other SMT thread is already
 	 * up-to-date.
 	 */
-	if (rev > mc->hdr.patch_id)
+	if (old_rev > mc->hdr.patch_id)
 		return ret;
 
-	if (!__apply_microcode_amd(mc)) {
-		ucode_new_rev = mc->hdr.patch_id;
-		ret = true;
-	}
-
-	return ret;
+	return !__apply_microcode_amd(mc);
 }
 
 static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family)
@@ -506,9 +496,12 @@ static void __init find_blobs_in_containers(unsigned int cpuid_1_eax, struct cpi
 	*ret = cp;
 }
 
-void __init load_ucode_amd_bsp(unsigned int cpuid_1_eax)
+void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_eax)
 {
 	struct cpio_data cp = { };
+	u32 dummy;
+
+	native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->old_rev, dummy);
 
 	/* Needed in load_microcode_amd() */
 	ucode_cpu_info[0].cpu_sig.sig = cpuid_1_eax;
@@ -517,7 +510,8 @@ void __init load_ucode_amd_bsp(unsigned int cpuid_1_eax)
 	if (!(cp.data && cp.size))
 		return;
 
-	early_apply_microcode(cpuid_1_eax, cp.data, cp.size);
+	if (early_apply_microcode(cpuid_1_eax, ed->old_rev, cp.data, cp.size))
+		native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->new_rev, dummy);
 }
 
 static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size);
@@ -625,10 +619,8 @@ void reload_ucode_amd(unsigned int cpu)
 	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
 
 	if (rev < mc->hdr.patch_id) {
-		if (!__apply_microcode_amd(mc)) {
-			ucode_new_rev = mc->hdr.patch_id;
-			pr_info("reload patch_level=0x%08x\n", ucode_new_rev);
-		}
+		if (!__apply_microcode_amd(mc))
+			pr_info_once("reload revision: 0x%08x\n", mc->hdr.patch_id);
 	}
 }
 
@@ -649,8 +641,6 @@ static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
 	if (p && (p->patch_id == csig->rev))
 		uci->mc = p->data;
 
-	pr_info("CPU%d: patch_level=0x%08x\n", cpu, csig->rev);
-
 	return 0;
 }
 
@@ -691,8 +681,6 @@ static enum ucode_state apply_microcode_amd(int cpu)
 	rev = mc_amd->hdr.patch_id;
 	ret = UCODE_UPDATED;
 
-	pr_info("CPU%d: new patch_level=0x%08x\n", cpu, rev);
-
 out:
 	uci->cpu_sig.rev = rev;
 	c->microcode	 = rev;
@@ -935,11 +923,6 @@ struct microcode_ops * __init init_amd_microcode(void)
 		pr_warn("AMD CPU family 0x%x not supported\n", c->x86);
 		return NULL;
 	}
-
-	if (ucode_new_rev)
-		pr_info_once("microcode updated early to new patch_level=0x%08x\n",
-			     ucode_new_rev);
-
 	return &microcode_amd_ops;
 }
 
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 666d25bbc5ad..232026a239a6 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -41,8 +41,6 @@
 
 #include "internal.h"
 
-#define DRIVER_VERSION	"2.2"
-
 static struct microcode_ops	*microcode_ops;
 bool dis_ucode_ldr = true;
 
@@ -77,6 +75,8 @@ static u32 final_levels[] = {
 	0, /* T-101 terminator */
 };
 
+struct early_load_data early_data;
+
 /*
  * Check the current patch level on this CPU.
  *
@@ -155,9 +155,9 @@ void __init load_ucode_bsp(void)
 		return;
 
 	if (intel)
-		load_ucode_intel_bsp();
+		load_ucode_intel_bsp(&early_data);
 	else
-		load_ucode_amd_bsp(cpuid_1_eax);
+		load_ucode_amd_bsp(&early_data, cpuid_1_eax);
 }
 
 void load_ucode_ap(void)
@@ -828,6 +828,11 @@ static int __init microcode_init(void)
 	if (!microcode_ops)
 		return -ENODEV;
 
+	pr_info_once("Current revision: 0x%08x\n", (early_data.new_rev ?: early_data.old_rev));
+
+	if (early_data.new_rev)
+		pr_info_once("Updated early from: 0x%08x\n", early_data.old_rev);
+
 	microcode_pdev = platform_device_register_simple("microcode", -1, NULL, 0);
 	if (IS_ERR(microcode_pdev))
 		return PTR_ERR(microcode_pdev);
@@ -846,8 +851,6 @@ static int __init microcode_init(void)
 	cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/microcode:online",
 			  mc_cpu_online, mc_cpu_down_prep);
 
-	pr_info("Microcode Update Driver: v%s.", DRIVER_VERSION);
-
 	return 0;
 
  out_pdev:
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 6024feb98d29..857e608af641 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -339,16 +339,9 @@ static enum ucode_state __apply_microcode(struct ucode_cpu_info *uci,
 static enum ucode_state apply_microcode_early(struct ucode_cpu_info *uci)
 {
 	struct microcode_intel *mc = uci->mc;
-	enum ucode_state ret;
-	u32 cur_rev, date;
+	u32 cur_rev;
 
-	ret = __apply_microcode(uci, mc, &cur_rev);
-	if (ret == UCODE_UPDATED) {
-		date = mc->hdr.date;
-		pr_info_once("updated early: 0x%x -> 0x%x, date = %04x-%02x-%02x\n",
-			     cur_rev, mc->hdr.rev, date & 0xffff, date >> 24, (date >> 16) & 0xff);
-	}
-	return ret;
+	return __apply_microcode(uci, mc, &cur_rev);
 }
 
 static __init bool load_builtin_intel_microcode(struct cpio_data *cp)
@@ -377,14 +370,14 @@ static __init struct microcode_intel *get_microcode_blob(struct ucode_cpu_info *
 {
 	struct cpio_data cp;
 
+	intel_collect_cpu_info(&uci->cpu_sig);
+
 	if (!load_builtin_intel_microcode(&cp))
 		cp = find_microcode_in_initrd(ucode_path);
 
 	if (!(cp.data && cp.size))
 		return NULL;
 
-	intel_collect_cpu_info(&uci->cpu_sig);
-
 	return scan_microcode(cp.data, cp.size, uci, save);
 }
 
@@ -413,13 +406,17 @@ static int __init save_builtin_microcode(void)
 early_initcall(save_builtin_microcode);
 
 /* Load microcode on BSP from initrd or builtin blobs */
-void __init load_ucode_intel_bsp(void)
+void __init load_ucode_intel_bsp(struct early_load_data *ed)
 {
 	struct ucode_cpu_info uci;
 
 	uci.mc = get_microcode_blob(&uci, false);
-	if (uci.mc && apply_microcode_early(&uci) == UCODE_UPDATED)
+	ed->old_rev = uci.cpu_sig.rev;
+
+	if (uci.mc && apply_microcode_early(&uci) == UCODE_UPDATED) {
 		ucode_patch_va = UCODE_BSP_LOADED;
+		ed->new_rev = uci.cpu_sig.rev;
+	}
 }
 
 void load_ucode_intel_ap(void)
@@ -460,12 +457,6 @@ static enum ucode_state apply_microcode_late(int cpu)
 	if (ret != UCODE_UPDATED && ret != UCODE_OK)
 		return ret;
 
-	if (!cpu && uci->cpu_sig.rev != cur_rev) {
-		pr_info("Updated to revision 0x%x, date = %04x-%02x-%02x\n",
-			uci->cpu_sig.rev, mc->hdr.date & 0xffff, mc->hdr.date >> 24,
-			(mc->hdr.date >> 16) & 0xff);
-	}
-
 	cpu_data(cpu).microcode	 = uci->cpu_sig.rev;
 	if (!cpu)
 		boot_cpu_data.microcode = uci->cpu_sig.rev;
diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h
index f8047b12329a..21776c529fa9 100644
--- a/arch/x86/kernel/cpu/microcode/internal.h
+++ b/arch/x86/kernel/cpu/microcode/internal.h
@@ -37,6 +37,12 @@ struct microcode_ops {
 				use_nmi		: 1;
 };
 
+struct early_load_data {
+	u32 old_rev;
+	u32 new_rev;
+};
+
+extern struct early_load_data early_data;
 extern struct ucode_cpu_info ucode_cpu_info[];
 struct cpio_data find_microcode_in_initrd(const char *path);
 
@@ -92,14 +98,14 @@ extern bool dis_ucode_ldr;
 extern bool force_minrev;
 
 #ifdef CONFIG_CPU_SUP_AMD
-void load_ucode_amd_bsp(unsigned int family);
+void load_ucode_amd_bsp(struct early_load_data *ed, unsigned int family);
 void load_ucode_amd_ap(unsigned int family);
 int save_microcode_in_initrd_amd(unsigned int family);
 void reload_ucode_amd(unsigned int cpu);
 struct microcode_ops *init_amd_microcode(void);
 void exit_amd_microcode(void);
 #else /* CONFIG_CPU_SUP_AMD */
-static inline void load_ucode_amd_bsp(unsigned int family) { }
+static inline void load_ucode_amd_bsp(struct early_load_data *ed, unsigned int family) { }
 static inline void load_ucode_amd_ap(unsigned int family) { }
 static inline int save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; }
 static inline void reload_ucode_amd(unsigned int cpu) { }
@@ -108,12 +114,12 @@ static inline void exit_amd_microcode(void) { }
 #endif /* !CONFIG_CPU_SUP_AMD */
 
 #ifdef CONFIG_CPU_SUP_INTEL
-void load_ucode_intel_bsp(void);
+void load_ucode_intel_bsp(struct early_load_data *ed);
 void load_ucode_intel_ap(void);
 void reload_ucode_intel(void);
 struct microcode_ops *init_intel_microcode(void);
 #else /* CONFIG_CPU_SUP_INTEL */
-static inline void load_ucode_intel_bsp(void) { }
+static inline void load_ucode_intel_bsp(struct early_load_data *ed) { }
 static inline void load_ucode_intel_ap(void) { }
 static inline void reload_ucode_intel(void) { }
 static inline struct microcode_ops *init_intel_microcode(void) { return NULL; }
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index e6bba12c759c..01fa06dd06b6 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -262,11 +262,14 @@ static uint32_t  __init ms_hyperv_platform(void)
 static int hv_nmi_unknown(unsigned int val, struct pt_regs *regs)
 {
 	static atomic_t nmi_cpu = ATOMIC_INIT(-1);
+	unsigned int old_cpu, this_cpu;
 
 	if (!unknown_nmi_panic)
 		return NMI_DONE;
 
-	if (atomic_cmpxchg(&nmi_cpu, -1, raw_smp_processor_id()) != -1)
+	old_cpu = -1;
+	this_cpu = raw_smp_processor_id();
+	if (!atomic_try_cmpxchg(&nmi_cpu, &old_cpu, this_cpu))
 		return NMI_HANDLED;
 
 	return NMI_DONE;
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 2d6aa5d2e3d7..d3524778a545 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -428,6 +428,10 @@ void __init mtrr_copy_map(void)
  * from the x86_init.hyper.init_platform() hook.  It can be called only once.
  * The MTRR state can't be changed afterwards.  To ensure that, X86_FEATURE_MTRR
  * is cleared.
+ *
+ * @var: MTRR variable range array to use
+ * @num_var: length of the @var array
+ * @def_type: default caching type
  */
 void mtrr_overwrite_state(struct mtrr_var_range *var, unsigned int num_var,
 			  mtrr_type def_type)
@@ -492,13 +496,15 @@ static u8 type_merge(u8 type, u8 new_type, u8 *uniform)
 /**
  * mtrr_type_lookup - look up memory type in MTRR
  *
+ * @start: Begin of the physical address range
+ * @end: End of the physical address range
+ * @uniform: output argument:
+ *  - 1: the returned MTRR type is valid for the whole region
+ *  - 0: otherwise
+ *
  * Return Values:
  * MTRR_TYPE_(type)  - The effective MTRR type for the region
  * MTRR_TYPE_INVALID - MTRR is disabled
- *
- * Output Argument:
- * uniform - Set to 1 when the returned MTRR type is valid for the whole
- *	     region, set to 0 else.
  */
 u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform)
 {
diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c
index 5d390df21440..b65ab214bdf5 100644
--- a/arch/x86/kernel/cpu/sgx/ioctl.c
+++ b/arch/x86/kernel/cpu/sgx/ioctl.c
@@ -581,7 +581,7 @@ err_out:
  *
  * Flush any outstanding enqueued EADD operations and perform EINIT.  The
  * Launch Enclave Public Key Hash MSRs are rewritten as necessary to match
- * the enclave's MRSIGNER, which is caculated from the provided sigstruct.
+ * the enclave's MRSIGNER, which is calculated from the provided sigstruct.
  *
  * Return:
  * - 0:		Success.
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index c92d88680dbf..b6b044356f1b 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -170,7 +170,7 @@ static int elf_header_exclude_ranges(struct crash_mem *cmem)
 	int ret = 0;
 
 	/* Exclude the low 1M because it is always reserved */
-	ret = crash_exclude_mem_range(cmem, 0, (1<<20)-1);
+	ret = crash_exclude_mem_range(cmem, 0, SZ_1M - 1);
 	if (ret)
 		return ret;
 
@@ -198,8 +198,8 @@ static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg)
 }
 
 /* Prepare elf headers. Return addr and size */
-static int prepare_elf_headers(struct kimage *image, void **addr,
-					unsigned long *sz, unsigned long *nr_mem_ranges)
+static int prepare_elf_headers(void **addr, unsigned long *sz,
+			       unsigned long *nr_mem_ranges)
 {
 	struct crash_mem *cmem;
 	int ret;
@@ -221,7 +221,7 @@ static int prepare_elf_headers(struct kimage *image, void **addr,
 	*nr_mem_ranges = cmem->nr_ranges;
 
 	/* By default prepare 64bit headers */
-	ret =  crash_prepare_elf64_headers(cmem, IS_ENABLED(CONFIG_X86_64), addr, sz);
+	ret = crash_prepare_elf64_headers(cmem, IS_ENABLED(CONFIG_X86_64), addr, sz);
 
 out:
 	vfree(cmem);
@@ -349,7 +349,7 @@ int crash_load_segments(struct kimage *image)
 				  .buf_max = ULONG_MAX, .top_down = false };
 
 	/* Prepare elf headers and add a segment */
-	ret = prepare_elf_headers(image, &kbuf.buffer, &kbuf.bufsz, &pnum);
+	ret = prepare_elf_headers(&kbuf.buffer, &kbuf.bufsz, &pnum);
 	if (ret)
 		return ret;
 
@@ -386,8 +386,8 @@ int crash_load_segments(struct kimage *image)
 	if (ret)
 		return ret;
 	image->elf_load_addr = kbuf.mem;
-	pr_debug("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
-		 image->elf_load_addr, kbuf.bufsz, kbuf.memsz);
+	kexec_dprintk("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+		      image->elf_load_addr, kbuf.bufsz, kbuf.memsz);
 
 	return ret;
 }
@@ -452,7 +452,7 @@ void arch_crash_handle_hotplug_event(struct kimage *image)
 	 * Create the new elfcorehdr reflecting the changes to CPU and/or
 	 * memory resources.
 	 */
-	if (prepare_elf_headers(image, &elfbuf, &elfsz, &nr_mem_ranges)) {
+	if (prepare_elf_headers(&elfbuf, &elfsz, &nr_mem_ranges)) {
 		pr_err("unable to create new elfcorehdr");
 		goto out;
 	}
diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c
index 794e70151203..a06b876bbf2d 100644
--- a/arch/x86/kernel/fpu/bugs.c
+++ b/arch/x86/kernel/fpu/bugs.c
@@ -2,6 +2,7 @@
 /*
  * x86 FPU bug checks:
  */
+#include <asm/cpufeature.h>
 #include <asm/fpu/api.h>
 
 /*
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index a21a4d0ecc34..520deb411a70 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -308,7 +308,7 @@ EXPORT_SYMBOL_GPL(fpu_update_guest_xfd);
  * Must be invoked from KVM after a VMEXIT before enabling interrupts when
  * XFD write emulation is disabled. This is required because the guest can
  * freely modify XFD and the state at VMEXIT is not guaranteed to be the
- * same as the state on VMENTER. So software state has to be udpated before
+ * same as the state on VMENTER. So software state has to be updated before
  * any operation which depends on it can take place.
  *
  * Note: It can be invoked unconditionally even when write emulation is
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 05a110c97111..dc0956067944 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -71,9 +71,9 @@ EXPORT_SYMBOL(vmemmap_base);
  * GDT used on the boot CPU before switching to virtual addresses.
  */
 static struct desc_struct startup_gdt[GDT_ENTRIES] __initdata = {
-	[GDT_ENTRY_KERNEL32_CS]         = GDT_ENTRY_INIT(0xc09b, 0, 0xfffff),
-	[GDT_ENTRY_KERNEL_CS]           = GDT_ENTRY_INIT(0xa09b, 0, 0xfffff),
-	[GDT_ENTRY_KERNEL_DS]           = GDT_ENTRY_INIT(0xc093, 0, 0xfffff),
+	[GDT_ENTRY_KERNEL32_CS]         = GDT_ENTRY_INIT(DESC_CODE32, 0, 0xfffff),
+	[GDT_ENTRY_KERNEL_CS]           = GDT_ENTRY_INIT(DESC_CODE64, 0, 0xfffff),
+	[GDT_ENTRY_KERNEL_DS]           = GDT_ENTRY_INIT(DESC_DATA64, 0, 0xfffff),
 };
 
 /*
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 086a2c3aaaa0..d4918d03efb4 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -114,6 +114,28 @@ SYM_CODE_START_NOALIGN(startup_64)
 
 	/* Form the CR3 value being sure to include the CR3 modifier */
 	addq	$(early_top_pgt - __START_KERNEL_map), %rax
+
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+	mov	%rax, %rdi
+	mov	%rax, %r14
+
+	addq	phys_base(%rip), %rdi
+
+	/*
+	 * For SEV guests: Verify that the C-bit is correct. A malicious
+	 * hypervisor could lie about the C-bit position to perform a ROP
+	 * attack on the guest by writing to the unencrypted stack and wait for
+	 * the next RET instruction.
+	 */
+	call	sev_verify_cbit
+
+	/*
+	 * Restore CR3 value without the phys_base which will be added
+	 * below, before writing %cr3.
+	 */
+	 mov	%r14, %rax
+#endif
+
 	jmp 1f
 SYM_CODE_END(startup_64)
 
@@ -182,7 +204,7 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	/* Enable PAE mode, PSE, PGE and LA57 */
 	orl	$(X86_CR4_PAE | X86_CR4_PSE | X86_CR4_PGE), %ecx
 #ifdef CONFIG_X86_5LEVEL
-	testl	$1, __pgtable_l5_enabled(%rip)
+	testb	$1, __pgtable_l5_enabled(%rip)
 	jz	1f
 	orl	$X86_CR4_LA57, %ecx
 1:
@@ -193,21 +215,12 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	addq	phys_base(%rip), %rax
 
 	/*
-	 * For SEV guests: Verify that the C-bit is correct. A malicious
-	 * hypervisor could lie about the C-bit position to perform a ROP
-	 * attack on the guest by writing to the unencrypted stack and wait for
-	 * the next RET instruction.
-	 */
-	movq	%rax, %rdi
-	call	sev_verify_cbit
-
-	/*
 	 * Switch to new page-table
 	 *
 	 * For the boot CPU this switches to early_top_pgt which still has the
-	 * indentity mappings present. The secondary CPUs will switch to the
+	 * identity mappings present. The secondary CPUs will switch to the
 	 * init_top_pgt here, away from the trampoline_pgd and unmap the
-	 * indentity mapped ranges.
+	 * identity mapped ranges.
 	 */
 	movq	%rax, %cr3
 
@@ -255,6 +268,22 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	testl	$X2APIC_ENABLE, %eax
 	jnz	.Lread_apicid_msr
 
+#ifdef CONFIG_X86_X2APIC
+	/*
+	 * If system is in X2APIC mode then MMIO base might not be
+	 * mapped causing the MMIO read below to fault. Faults can't
+	 * be handled at that point.
+	 */
+	cmpl	$0, x2apic_mode(%rip)
+	jz	.Lread_apicid_mmio
+
+	/* Force the AP into X2APIC mode. */
+	orl	$X2APIC_ENABLE, %eax
+	wrmsr
+	jmp	.Lread_apicid_msr
+#endif
+
+.Lread_apicid_mmio:
 	/* Read the APIC ID from the fix-mapped MMIO space. */
 	movq	apic_mmio_base(%rip), %rcx
 	addq	$APIC_ID, %rcx
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 41eecf180b7f..8ff2bf921519 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -707,7 +707,7 @@ static void __init hpet_select_clockevents(void)
 
 	hpet_base.nr_clockevents = 0;
 
-	/* No point if MSI is disabled or CPU has an Always Runing APIC Timer */
+	/* No point if MSI is disabled or CPU has an Always Running APIC Timer */
 	if (hpet_msi_disable || boot_cpu_has(X86_FEATURE_ARAT))
 		return;
 
@@ -965,7 +965,7 @@ static bool __init mwait_pc10_supported(void)
  * and per CPU timer interrupts.
  *
  * The probability that this problem is going to be solved in the
- * forseeable future is close to zero, so the kernel has to be cluttered
+ * foreseeable future is close to zero, so the kernel has to be cluttered
  * with heuristics to keep up with the ever growing amount of hardware and
  * firmware trainwrecks. Hopefully some day hardware people will understand
  * that the approach of "This can be fixed in software" is not sustainable.
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index 8857abc706e4..660b601f1d6c 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -121,7 +121,7 @@ static const __initconst struct idt_data def_idts[] = {
 
 static const struct idt_data ia32_idt[] __initconst = {
 #if defined(CONFIG_IA32_EMULATION)
-	SYSG(IA32_SYSCALL_VECTOR,	entry_INT80_compat),
+	SYSG(IA32_SYSCALL_VECTOR,	asm_int80_emulation),
 #elif defined(CONFIG_X86_32)
 	SYSG(IA32_SYSCALL_VECTOR,	entry_INT80_32),
 #endif
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index a61c12c01270..2a422e00ed4b 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -82,7 +82,7 @@ static int setup_cmdline(struct kimage *image, struct boot_params *params,
 
 	cmdline_ptr[cmdline_len - 1] = '\0';
 
-	pr_debug("Final command line is: %s\n", cmdline_ptr);
+	kexec_dprintk("Final command line is: %s\n", cmdline_ptr);
 	cmdline_ptr_phys = bootparams_load_addr + cmdline_offset;
 	cmdline_low_32 = cmdline_ptr_phys & 0xffffffffUL;
 	cmdline_ext_32 = cmdline_ptr_phys >> 32;
@@ -272,7 +272,12 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params,
 
 	nr_e820_entries = params->e820_entries;
 
+	kexec_dprintk("E820 memmap:\n");
 	for (i = 0; i < nr_e820_entries; i++) {
+		kexec_dprintk("%016llx-%016llx (%d)\n",
+			      params->e820_table[i].addr,
+			      params->e820_table[i].addr + params->e820_table[i].size - 1,
+			      params->e820_table[i].type);
 		if (params->e820_table[i].type != E820_TYPE_RAM)
 			continue;
 		start = params->e820_table[i].addr;
@@ -424,7 +429,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 	 * command line. Make sure it does not overflow
 	 */
 	if (cmdline_len + MAX_ELFCOREHDR_STR_LEN > header->cmdline_size) {
-		pr_debug("Appending elfcorehdr=<addr> to command line exceeds maximum allowed length\n");
+		pr_err("Appending elfcorehdr=<addr> to command line exceeds maximum allowed length\n");
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -445,7 +450,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 		return ERR_PTR(ret);
 	}
 
-	pr_debug("Loaded purgatory at 0x%lx\n", pbuf.mem);
+	kexec_dprintk("Loaded purgatory at 0x%lx\n", pbuf.mem);
 
 
 	/*
@@ -490,8 +495,8 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 	if (ret)
 		goto out_free_params;
 	bootparam_load_addr = kbuf.mem;
-	pr_debug("Loaded boot_param, command line and misc at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
-		 bootparam_load_addr, kbuf.bufsz, kbuf.bufsz);
+	kexec_dprintk("Loaded boot_param, command line and misc at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+		      bootparam_load_addr, kbuf.bufsz, kbuf.memsz);
 
 	/* Load kernel */
 	kbuf.buffer = kernel + kern16_size;
@@ -505,8 +510,8 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 		goto out_free_params;
 	kernel_load_addr = kbuf.mem;
 
-	pr_debug("Loaded 64bit kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
-		 kernel_load_addr, kbuf.bufsz, kbuf.memsz);
+	kexec_dprintk("Loaded 64bit kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+		      kernel_load_addr, kbuf.bufsz, kbuf.memsz);
 
 	/* Load initrd high */
 	if (initrd) {
@@ -520,8 +525,8 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 			goto out_free_params;
 		initrd_load_addr = kbuf.mem;
 
-		pr_debug("Loaded initrd at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
-				initrd_load_addr, initrd_len, initrd_len);
+		kexec_dprintk("Loaded initrd at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+			      initrd_load_addr, initrd_len, initrd_len);
 
 		setup_initrd(params, initrd_load_addr, initrd_len);
 	}
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index e8babebad7b8..a0ce46c0a2d8 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -576,7 +576,8 @@ static void kprobe_emulate_call_indirect(struct kprobe *p, struct pt_regs *regs)
 {
 	unsigned long offs = addrmode_regoffs[p->ainsn.indirect.reg];
 
-	int3_emulate_call(regs, regs_get_register(regs, offs));
+	int3_emulate_push(regs, regs->ip - INT3_INSN_SIZE + p->ainsn.size);
+	int3_emulate_jmp(regs, regs_get_register(regs, offs));
 }
 NOKPROBE_SYMBOL(kprobe_emulate_call_indirect);
 
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 0ddb3bd0f1aa..dfe9945b9bec 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -803,8 +803,8 @@ extern bool __raw_callee_save___kvm_vcpu_is_preempted(long);
  "cmpb   $0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax)\n\t" \
  "setne  %al\n\t"
 
-DEFINE_PARAVIRT_ASM(__raw_callee_save___kvm_vcpu_is_preempted,
-		    PV_VCPU_PREEMPTED_ASM, .text);
+DEFINE_ASM_FUNC(__raw_callee_save___kvm_vcpu_is_preempted,
+		PV_VCPU_PREEMPTED_ASM, .text);
 #endif
 
 static void __init kvm_guest_init(void)
@@ -942,7 +942,7 @@ static void __init kvm_init_platform(void)
 		 * Reset the host's shared pages list related to kernel
 		 * specific page encryption status settings before we load a
 		 * new kernel by kexec. Reset the page encryption status
-		 * during early boot intead of just before kexec to avoid SMP
+		 * during early boot instead of just before kexec to avoid SMP
 		 * races during kvm_pv_guest_cpu_reboot().
 		 * NOTE: We cannot reset the complete shared pages list
 		 * here as we need to retain the UEFI/OVMF firmware
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index fb8f52149be9..a95d0900e8c6 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -42,7 +42,7 @@ static int __init parse_no_kvmclock_vsyscall(char *arg)
 }
 early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);
 
-/* Aligned to page sizes to match whats mapped via vsyscalls to userspace */
+/* Aligned to page sizes to match what's mapped via vsyscalls to userspace */
 #define HVC_BOOT_ARRAY_SIZE \
 	(PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info))
 
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index adc67f98819a..7a814b41402d 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -7,7 +7,7 @@
  * This handles calls from both 32bit and 64bit mode.
  *
  * Lock order:
- *	contex.ldt_usr_sem
+ *	context.ldt_usr_sem
  *	  mmap_lock
  *	    context.lock
  */
@@ -49,7 +49,7 @@ void load_mm_ldt(struct mm_struct *mm)
 	/*
 	 * Any change to mm->context.ldt is followed by an IPI to all
 	 * CPUs with the mm active.  The LDT will not be freed until
-	 * after the IPI is handled by all such CPUs.  This means that,
+	 * after the IPI is handled by all such CPUs.  This means that
 	 * if the ldt_struct changes before we return, the values we see
 	 * will be safe, and the new values will be loaded before we run
 	 * any user code.
@@ -685,7 +685,7 @@ SYSCALL_DEFINE3(modify_ldt, int , func , void __user * , ptr ,
 	}
 	/*
 	 * The SYSCALL_DEFINE() macros give us an 'unsigned long'
-	 * return type, but tht ABI for sys_modify_ldt() expects
+	 * return type, but the ABI for sys_modify_ldt() expects
 	 * 'int'.  This cast gives us an int-sized value in %rax
 	 * for the return code.  The 'unsigned' is necessary so
 	 * the compiler does not try to sign-extend the negative
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 1a3e2c05a8a5..bc0a5348b4a6 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -42,12 +42,9 @@ struct init_pgtable_data {
 static int mem_region_callback(struct resource *res, void *arg)
 {
 	struct init_pgtable_data *data = arg;
-	unsigned long mstart, mend;
-
-	mstart = res->start;
-	mend = mstart + resource_size(res) - 1;
 
-	return kernel_ident_mapping_init(data->info, data->level4p, mstart, mend);
+	return kernel_ident_mapping_init(data->info, data->level4p,
+					 res->start, res->end + 1);
 }
 
 static int
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 5f71a0cf4399..e18914c0e38a 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -276,7 +276,7 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    struct module *me)
 {
 	const Elf_Shdr *s, *alt = NULL, *locks = NULL,
-		*para = NULL, *orc = NULL, *orc_ip = NULL,
+		*orc = NULL, *orc_ip = NULL,
 		*retpolines = NULL, *returns = NULL, *ibt_endbr = NULL,
 		*calls = NULL, *cfi = NULL;
 	char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
@@ -286,8 +286,6 @@ int module_finalize(const Elf_Ehdr *hdr,
 			alt = s;
 		if (!strcmp(".smp_locks", secstrings + s->sh_name))
 			locks = s;
-		if (!strcmp(".parainstructions", secstrings + s->sh_name))
-			para = s;
 		if (!strcmp(".orc_unwind", secstrings + s->sh_name))
 			orc = s;
 		if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name))
@@ -304,14 +302,6 @@ int module_finalize(const Elf_Ehdr *hdr,
 			ibt_endbr = s;
 	}
 
-	/*
-	 * See alternative_instructions() for the ordering rules between the
-	 * various patching types.
-	 */
-	if (para) {
-		void *pseg = (void *)para->sh_addr;
-		apply_paravirt(pseg, pseg + para->sh_size);
-	}
 	if (retpolines || cfi) {
 		void *rseg = NULL, *cseg = NULL;
 		unsigned int rsize = 0, csize = 0;
@@ -341,7 +331,7 @@ int module_finalize(const Elf_Ehdr *hdr,
 		void *aseg = (void *)alt->sh_addr;
 		apply_alternatives(aseg, aseg + alt->sh_size);
 	}
-	if (calls || para) {
+	if (calls || alt) {
 		struct callthunk_sites cs = {};
 
 		if (calls) {
@@ -349,9 +339,9 @@ int module_finalize(const Elf_Ehdr *hdr,
 			cs.call_end = (void *)calls->sh_addr + calls->sh_size;
 		}
 
-		if (para) {
-			cs.pv_start = (void *)para->sh_addr;
-			cs.pv_end = (void *)para->sh_addr + para->sh_size;
+		if (alt) {
+			cs.alt_start = (void *)alt->sh_addr;
+			cs.alt_end = (void *)alt->sh_addr + alt->sh_size;
 		}
 
 		callthunks_patch_module_calls(&cs, me);
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 97f1436c1a20..5358d43886ad 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -34,14 +34,8 @@
 #include <asm/io_bitmap.h>
 #include <asm/gsseg.h>
 
-/*
- * nop stub, which must not clobber anything *including the stack* to
- * avoid confusing the entry prologues.
- */
-DEFINE_PARAVIRT_ASM(_paravirt_nop, "", .entry.text);
-
 /* stub always returning 0. */
-DEFINE_PARAVIRT_ASM(paravirt_ret0, "xor %eax,%eax", .entry.text);
+DEFINE_ASM_FUNC(paravirt_ret0, "xor %eax,%eax", .entry.text);
 
 void __init default_banner(void)
 {
@@ -49,26 +43,12 @@ void __init default_banner(void)
 	       pv_info.name);
 }
 
-/* Undefined instruction for dealing with missing ops pointers. */
-noinstr void paravirt_BUG(void)
-{
-	BUG();
-}
-
-static unsigned paravirt_patch_call(void *insn_buff, const void *target,
-				    unsigned long addr, unsigned len)
-{
-	__text_gen_insn(insn_buff, CALL_INSN_OPCODE,
-			(void *)addr, target, CALL_INSN_SIZE);
-	return CALL_INSN_SIZE;
-}
-
 #ifdef CONFIG_PARAVIRT_XXL
-DEFINE_PARAVIRT_ASM(_paravirt_ident_64, "mov %rdi, %rax", .text);
-DEFINE_PARAVIRT_ASM(pv_native_save_fl, "pushf; pop %rax", .noinstr.text);
-DEFINE_PARAVIRT_ASM(pv_native_irq_disable, "cli", .noinstr.text);
-DEFINE_PARAVIRT_ASM(pv_native_irq_enable, "sti", .noinstr.text);
-DEFINE_PARAVIRT_ASM(pv_native_read_cr2, "mov %cr2, %rax", .noinstr.text);
+DEFINE_ASM_FUNC(_paravirt_ident_64, "mov %rdi, %rax", .text);
+DEFINE_ASM_FUNC(pv_native_save_fl, "pushf; pop %rax", .noinstr.text);
+DEFINE_ASM_FUNC(pv_native_irq_disable, "cli", .noinstr.text);
+DEFINE_ASM_FUNC(pv_native_irq_enable, "sti", .noinstr.text);
+DEFINE_ASM_FUNC(pv_native_read_cr2, "mov %cr2, %rax", .noinstr.text);
 #endif
 
 DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key);
@@ -85,28 +65,6 @@ static void native_tlb_remove_table(struct mmu_gather *tlb, void *table)
 	tlb_remove_page(tlb, table);
 }
 
-unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr,
-			    unsigned int len)
-{
-	/*
-	 * Neat trick to map patch type back to the call within the
-	 * corresponding structure.
-	 */
-	void *opfunc = *((void **)&pv_ops + type);
-	unsigned ret;
-
-	if (opfunc == NULL)
-		/* If there's no function, patch it with paravirt_BUG() */
-		ret = paravirt_patch_call(insn_buff, paravirt_BUG, addr, len);
-	else if (opfunc == _paravirt_nop)
-		ret = 0;
-	else
-		/* Otherwise call the function. */
-		ret = paravirt_patch_call(insn_buff, opfunc, addr, len);
-
-	return ret;
-}
-
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index b6f4e8399fca..ab49ade31b0d 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -477,7 +477,7 @@ void native_tss_update_io_bitmap(void)
 	/*
 	 * Make sure that the TSS limit is covering the IO bitmap. It might have
 	 * been cut down by a VMEXIT to 0x67 which would cause a subsequent I/O
-	 * access from user space to trigger a #GP because tbe bitmap is outside
+	 * access from user space to trigger a #GP because the bitmap is outside
 	 * the TSS limit.
 	 */
 	refresh_tss_limit();
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 1526747bedf2..ec2c21a1844e 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -226,8 +226,6 @@ static void __init reserve_brk(void)
 	_brk_start = 0;
 }
 
-u64 relocated_ramdisk;
-
 #ifdef CONFIG_BLK_DEV_INITRD
 
 static u64 __init get_ramdisk_image(void)
@@ -261,7 +259,7 @@ static void __init relocate_initrd(void)
 	u64 area_size     = PAGE_ALIGN(ramdisk_size);
 
 	/* We need to move the initrd down into directly mapped mem */
-	relocated_ramdisk = memblock_phys_alloc_range(area_size, PAGE_SIZE, 0,
+	u64 relocated_ramdisk = memblock_phys_alloc_range(area_size, PAGE_SIZE, 0,
 						      PFN_PHYS(max_pfn_mapped));
 	if (!relocated_ramdisk)
 		panic("Cannot find place for new RAMDISK of size %lld\n",
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 2c97bf7b56ae..b30d6e180df7 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -106,8 +106,8 @@ void __init pcpu_populate_pte(unsigned long addr)
 static inline void setup_percpu_segment(int cpu)
 {
 #ifdef CONFIG_X86_32
-	struct desc_struct d = GDT_ENTRY_INIT(0x8092, per_cpu_offset(cpu),
-					      0xFFFFF);
+	struct desc_struct d = GDT_ENTRY_INIT(DESC_DATA32,
+					      per_cpu_offset(cpu), 0xFFFFF);
 
 	write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_PERCPU, &d, DESCTYPE_S);
 #endif
diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c
index ccb0915e84e1..1d24ec679915 100644
--- a/arch/x86/kernel/sev-shared.c
+++ b/arch/x86/kernel/sev-shared.c
@@ -96,7 +96,7 @@ static void __noreturn sev_es_terminate(unsigned int set, unsigned int reason)
 	/* Tell the hypervisor what went wrong. */
 	val |= GHCB_SEV_TERM_REASON(set, reason);
 
-	/* Request Guest Termination from Hypvervisor */
+	/* Request Guest Termination from Hypervisor */
 	sev_es_wr_ghcb_msr(val);
 	VMGEXIT();
 
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index 70472eebe719..c67285824e82 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -1234,10 +1234,6 @@ void setup_ghcb(void)
 	if (!cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT))
 		return;
 
-	/* First make sure the hypervisor talks a supported protocol. */
-	if (!sev_es_negotiate_protocol())
-		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
-
 	/*
 	 * Check whether the runtime #VC exception handler is active. It uses
 	 * the per-CPU GHCB page which is set up by sev_es_init_vc_handling().
@@ -1255,6 +1251,13 @@ void setup_ghcb(void)
 	}
 
 	/*
+	 * Make sure the hypervisor talks a supported protocol.
+	 * This gets called only in the BSP boot phase.
+	 */
+	if (!sev_es_negotiate_protocol())
+		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
+
+	/*
 	 * Clear the boot_ghcb. The first exception comes in before the bss
 	 * section is cleared.
 	 */
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 65fe2094da59..31b6f5dddfc2 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -27,6 +27,7 @@
 #include <linux/context_tracking.h>
 #include <linux/entry-common.h>
 #include <linux/syscalls.h>
+#include <linux/rseq.h>
 
 #include <asm/processor.h>
 #include <asm/ucontext.h>
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
index cacf2ede6217..23d8aaf8d9fd 100644
--- a/arch/x86/kernel/signal_64.c
+++ b/arch/x86/kernel/signal_64.c
@@ -175,9 +175,6 @@ int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
 	frame = get_sigframe(ksig, regs, sizeof(struct rt_sigframe), &fp);
 	uc_flags = frame_uc_flags(regs);
 
-	if (setup_signal_shadow_stack(ksig))
-		return -EFAULT;
-
 	if (!user_access_begin(frame, sizeof(*frame)))
 		return -EFAULT;
 
@@ -198,6 +195,9 @@ int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
 			return -EFAULT;
 	}
 
+	if (setup_signal_shadow_stack(ksig))
+		return -EFAULT;
+
 	/* Set up registers for signal handler */
 	regs->di = ksig->sig;
 	/* In case the signal handler was declared without prototypes */
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 2cc2aa120b4b..3f57ce68a3f1 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -757,6 +757,7 @@ const struct cpumask *cpu_clustergroup_mask(int cpu)
 {
 	return cpu_l2c_shared_mask(cpu);
 }
+EXPORT_SYMBOL_GPL(cpu_clustergroup_mask);
 
 static void impress_friends(void)
 {
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index c876f1d36a81..b0737a15c470 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -37,6 +37,7 @@
 #include <linux/nmi.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
+#include <linux/cpu.h>
 #include <linux/io.h>
 #include <linux/hardirq.h>
 #include <linux/atomic.h>
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 54a5596adaa6..a349dbfc6d5a 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -267,19 +267,6 @@ SECTIONS
 	}
 #endif
 
-	/*
-	 * start address and size of operations which during runtime
-	 * can be patched with virtualization friendly instructions or
-	 * baremetal native ones. Think page table operations.
-	 * Details in paravirt_types.h
-	 */
-	. = ALIGN(8);
-	.parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
-		__parainstructions = .;
-		*(.parainstructions)
-		__parainstructions_end = .;
-	}
-
 #ifdef CONFIG_RETPOLINE
 	/*
 	 * List of instructions that call/jmp/jcc to retpoline thunks
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index dda6fc4cfae8..42d3f47f4c07 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -105,7 +105,7 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find(
 
 		/*
 		 * If the index isn't significant, use the first entry with a
-		 * matching function.  It's userspace's responsibilty to not
+		 * matching function.  It's userspace's responsibility to not
 		 * provide "duplicate" entries in all cases.
 		 */
 		if (!(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) || e->index == index)
diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c
index ee8c4c3496ed..eea6ea7f14af 100644
--- a/arch/x86/kvm/debugfs.c
+++ b/arch/x86/kvm/debugfs.c
@@ -182,6 +182,7 @@ static int kvm_mmu_rmaps_stat_release(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations mmu_rmaps_stat_fops = {
+	.owner		= THIS_MODULE,
 	.open		= kvm_mmu_rmaps_stat_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 238afd7335e4..4943f6b2bbee 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -2388,7 +2388,7 @@ static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *h
 	if (!eventfd)
 		return HV_STATUS_INVALID_PORT_ID;
 
-	eventfd_signal(eventfd, 1);
+	eventfd_signal(eventfd);
 	return HV_STATUS_SUCCESS;
 }
 
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index c57e181bba21..0b1f991b9a31 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -987,7 +987,7 @@ static void pte_list_desc_remove_entry(struct kvm *kvm,
 
 	/*
 	 * The head descriptor is empty.  If there are no tail descriptors,
-	 * nullify the rmap head to mark the list as emtpy, else point the rmap
+	 * nullify the rmap head to mark the list as empty, else point the rmap
 	 * head at the next descriptor, i.e. the new head.
 	 */
 	if (!head_desc->more)
@@ -6544,7 +6544,7 @@ void kvm_mmu_try_split_huge_pages(struct kvm *kvm,
 	kvm_tdp_mmu_try_split_huge_pages(kvm, memslot, start, end, target_level, false);
 
 	/*
-	 * A TLB flush is unnecessary at this point for the same resons as in
+	 * A TLB flush is unnecessary at this point for the same reasons as in
 	 * kvm_mmu_slot_try_split_huge_pages().
 	 */
 }
diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c
index bd30ebfb2f2c..04c247bfe318 100644
--- a/arch/x86/kvm/mmu/tdp_iter.c
+++ b/arch/x86/kvm/mmu/tdp_iter.c
@@ -146,7 +146,7 @@ static bool try_step_up(struct tdp_iter *iter)
  * Step to the next SPTE in a pre-order traversal of the paging structure.
  * To get to the next SPTE, the iterator either steps down towards the goal
  * GFN, if at a present, non-last-level SPTE, or over to a SPTE mapping a
- * highter GFN.
+ * higher GFN.
  *
  * The basic algorithm is as follows:
  * 1. If the current SPTE is a non-last-level SPTE, step down into the page
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 4900c078045a..6ee925d66648 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2972,6 +2972,25 @@ static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm)
 
 		set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux);
 	}
+
+	/*
+	 * For SEV-ES, accesses to MSR_IA32_XSS should not be intercepted if
+	 * the host/guest supports its use.
+	 *
+	 * guest_can_use() checks a number of requirements on the host/guest to
+	 * ensure that MSR_IA32_XSS is available, but it might report true even
+	 * if X86_FEATURE_XSAVES isn't configured in the guest to ensure host
+	 * MSR_IA32_XSS is always properly restored. For SEV-ES, it is better
+	 * to further check that the guest CPUID actually supports
+	 * X86_FEATURE_XSAVES so that accesses to MSR_IA32_XSS by misbehaved
+	 * guests will still get intercepted and caught in the normal
+	 * kvm_emulate_rdmsr()/kvm_emulated_wrmsr() paths.
+	 */
+	if (guest_can_use(vcpu, X86_FEATURE_XSAVES) &&
+	    guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))
+		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 1, 1);
+	else
+		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 0, 0);
 }
 
 void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 712146312358..7fb51424fc74 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -103,6 +103,7 @@ static const struct svm_direct_access_msrs {
 	{ .index = MSR_IA32_LASTBRANCHTOIP,		.always = false },
 	{ .index = MSR_IA32_LASTINTFROMIP,		.always = false },
 	{ .index = MSR_IA32_LASTINTTOIP,		.always = false },
+	{ .index = MSR_IA32_XSS,			.always = false },
 	{ .index = MSR_EFER,				.always = false },
 	{ .index = MSR_IA32_CR_PAT,			.always = false },
 	{ .index = MSR_AMD64_SEV_ES_GHCB,		.always = true  },
@@ -1855,15 +1856,17 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	bool old_paging = is_paging(vcpu);
 
 #ifdef CONFIG_X86_64
-	if (vcpu->arch.efer & EFER_LME && !vcpu->arch.guest_state_protected) {
+	if (vcpu->arch.efer & EFER_LME) {
 		if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
 			vcpu->arch.efer |= EFER_LMA;
-			svm->vmcb->save.efer |= EFER_LMA | EFER_LME;
+			if (!vcpu->arch.guest_state_protected)
+				svm->vmcb->save.efer |= EFER_LMA | EFER_LME;
 		}
 
 		if (is_paging(vcpu) && !(cr0 & X86_CR0_PG)) {
 			vcpu->arch.efer &= ~EFER_LMA;
-			svm->vmcb->save.efer &= ~(EFER_LMA | EFER_LME);
+			if (!vcpu->arch.guest_state_protected)
+				svm->vmcb->save.efer &= ~(EFER_LMA | EFER_LME);
 		}
 	}
 #endif
@@ -4741,7 +4744,7 @@ static int svm_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
 	 * Emulation is possible for SEV guests if and only if a prefilled
 	 * buffer containing the bytes of the intercepted instruction is
 	 * available. SEV guest memory is encrypted with a guest specific key
-	 * and cannot be decrypted by KVM, i.e. KVM would read cyphertext and
+	 * and cannot be decrypted by KVM, i.e. KVM would read ciphertext and
 	 * decode garbage.
 	 *
 	 * If KVM is NOT trying to simply skip an instruction, inject #UD if
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index be67ab7fdd10..c409f934c377 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -30,7 +30,7 @@
 #define	IOPM_SIZE PAGE_SIZE * 3
 #define	MSRPM_SIZE PAGE_SIZE * 2
 
-#define MAX_DIRECT_ACCESS_MSRS	46
+#define MAX_DIRECT_ACCESS_MSRS	47
 #define MSRPM_OFFSETS	32
 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
 extern bool npt_enabled;
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index c5ec0ef51ff7..65826fe23f33 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -6561,7 +6561,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 		 * code was changed such that flag signals vmcs12 should
 		 * be copied into eVMCS in guest memory.
 		 *
-		 * To preserve backwards compatability, allow user
+		 * To preserve backwards compatibility, allow user
 		 * to set this flag even when there is no VMXON region.
 		 */
 		if (kvm_state->flags & ~KVM_STATE_NESTED_EVMCS)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index be20a60047b1..e0f86f11c345 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1809,7 +1809,7 @@ static void vmx_inject_exception(struct kvm_vcpu *vcpu)
 		 * do generate error codes with bits 31:16 set, and so KVM's
 		 * ABI lets userspace shove in arbitrary 32-bit values.  Drop
 		 * the upper bits to avoid VM-Fail, losing information that
-		 * does't really exist is preferable to killing the VM.
+		 * doesn't really exist is preferable to killing the VM.
 		 */
 		vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, (u16)ex->error_code);
 		intr_info |= INTR_INFO_DELIVER_CODE_MASK;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2c924075f6f1..cec0fc2a4b1c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5518,8 +5518,8 @@ static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu,
 static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 					 struct kvm_xsave *guest_xsave)
 {
-	return kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region,
-					     sizeof(guest_xsave->region));
+	kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region,
+				      sizeof(guest_xsave->region));
 }
 
 static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
@@ -10165,7 +10165,7 @@ static void kvm_inject_exception(struct kvm_vcpu *vcpu)
  *
  * But, if a VM-Exit occurs during instruction execution, and KVM does NOT skip
  * the instruction or inject an exception, then KVM can incorrecty inject a new
- * asynchrounous event if the event became pending after the CPU fetched the
+ * asynchronous event if the event became pending after the CPU fetched the
  * instruction (in the guest).  E.g. if a page fault (#PF, #NPF, EPT violation)
  * occurs and is resolved by KVM, a coincident NMI, SMI, IRQ, etc... can be
  * injected on the restarted instruction instead of being deferred until the
@@ -10186,7 +10186,7 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
 	int r;
 
 	/*
-	 * Process nested events first, as nested VM-Exit supercedes event
+	 * Process nested events first, as nested VM-Exit supersedes event
 	 * re-injection.  If there's an event queued for re-injection, it will
 	 * be saved into the appropriate vmc{b,s}12 fields on nested VM-Exit.
 	 */
@@ -10884,7 +10884,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		/*
 		 * Assert that vCPU vs. VM APICv state is consistent.  An APICv
 		 * update must kick and wait for all vCPUs before toggling the
-		 * per-VM state, and responsing vCPUs must wait for the update
+		 * per-VM state, and responding vCPUs must wait for the update
 		 * to complete before servicing KVM_REQ_APICV_UPDATE.
 		 */
 		WARN_ON_ONCE((kvm_vcpu_apicv_activated(vcpu) != kvm_vcpu_apicv_active(vcpu)) &&
@@ -13031,7 +13031,10 @@ bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.guest_state_protected)
 		return true;
 
-	return vcpu->arch.preempted_in_kernel;
+	if (vcpu != kvm_get_running_vcpu())
+		return vcpu->arch.preempted_in_kernel;
+
+	return static_call(kvm_x86_get_cpl)(vcpu) == 0;
 }
 
 unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index e53fad915a62..523bb6df5ac9 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -2088,7 +2088,7 @@ static bool kvm_xen_hcall_evtchn_send(struct kvm_vcpu *vcpu, u64 param, u64 *r)
 		if (ret < 0 && ret != -ENOTCONN)
 			return false;
 	} else {
-		eventfd_signal(evtchnfd->deliver.eventfd.ctx, 1);
+		eventfd_signal(evtchnfd->deliver.eventfd.ctx);
 	}
 
 	*r = 0;
diff --git a/arch/x86/lib/cache-smp.c b/arch/x86/lib/cache-smp.c
index 7c48ff4ae8d1..7af743bd3b13 100644
--- a/arch/x86/lib/cache-smp.c
+++ b/arch/x86/lib/cache-smp.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <asm/paravirt.h>
 #include <linux/smp.h>
 #include <linux/export.h>
 
diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c
index cea25ca8b8cf..c9dae65ac01b 100644
--- a/arch/x86/lib/csum-partial_64.c
+++ b/arch/x86/lib/csum-partial_64.c
@@ -11,26 +11,23 @@
 #include <asm/checksum.h>
 #include <asm/word-at-a-time.h>
 
-static inline unsigned short from32to16(unsigned a)
+static inline __wsum csum_finalize_sum(u64 temp64)
 {
-	unsigned short b = a >> 16;
-	asm("addw %w2,%w0\n\t"
-	    "adcw $0,%w0\n"
-	    : "=r" (b)
-	    : "0" (b), "r" (a));
-	return b;
+	return (__force __wsum)((temp64 + ror64(temp64, 32)) >> 32);
 }
 
-static inline __wsum csum_tail(u64 temp64, int odd)
+static inline unsigned long update_csum_40b(unsigned long sum, const unsigned long m[5])
 {
-	unsigned int result;
-
-	result = add32_with_carry(temp64 >> 32, temp64 & 0xffffffff);
-	if (unlikely(odd)) {
-		result = from32to16(result);
-		result = ((result >> 8) & 0xff) | ((result & 0xff) << 8);
-	}
-	return (__force __wsum)result;
+	asm("addq %1,%0\n\t"
+	     "adcq %2,%0\n\t"
+	     "adcq %3,%0\n\t"
+	     "adcq %4,%0\n\t"
+	     "adcq %5,%0\n\t"
+	     "adcq $0,%0"
+		:"+r" (sum)
+		:"m" (m[0]), "m" (m[1]), "m" (m[2]),
+		 "m" (m[3]), "m" (m[4]));
+	return sum;
 }
 
 /*
@@ -47,64 +44,32 @@ static inline __wsum csum_tail(u64 temp64, int odd)
 __wsum csum_partial(const void *buff, int len, __wsum sum)
 {
 	u64 temp64 = (__force u64)sum;
-	unsigned odd;
 
-	odd = 1 & (unsigned long) buff;
-	if (unlikely(odd)) {
-		if (unlikely(len == 0))
-			return sum;
-		temp64 = ror32((__force u32)sum, 8);
-		temp64 += (*(unsigned char *)buff << 8);
-		len--;
-		buff++;
+	/* Do two 40-byte chunks in parallel to get better ILP */
+	if (likely(len >= 80)) {
+		u64 temp64_2 = 0;
+		do {
+			temp64 = update_csum_40b(temp64, buff);
+			temp64_2 = update_csum_40b(temp64_2, buff + 40);
+			buff += 80;
+			len -= 80;
+		} while (len >= 80);
+
+		asm("addq %1,%0\n\t"
+		    "adcq $0,%0"
+		    :"+r" (temp64): "r" (temp64_2));
 	}
 
 	/*
-	 * len == 40 is the hot case due to IPv6 headers, but annotating it likely()
-	 * has noticeable negative affect on codegen for all other cases with
-	 * minimal performance benefit here.
+	 * len == 40 is the hot case due to IPv6 headers, so return
+	 * early for that exact case without checking the tail bytes.
 	 */
-	if (len == 40) {
-		asm("addq 0*8(%[src]),%[res]\n\t"
-		    "adcq 1*8(%[src]),%[res]\n\t"
-		    "adcq 2*8(%[src]),%[res]\n\t"
-		    "adcq 3*8(%[src]),%[res]\n\t"
-		    "adcq 4*8(%[src]),%[res]\n\t"
-		    "adcq $0,%[res]"
-		    : [res] "+r"(temp64)
-		    : [src] "r"(buff), "m"(*(const char(*)[40])buff));
-		return csum_tail(temp64, odd);
-	}
-	if (unlikely(len >= 64)) {
-		/*
-		 * Extra accumulators for better ILP in the loop.
-		 */
-		u64 tmp_accum, tmp_carries;
-
-		asm("xorl %k[tmp_accum],%k[tmp_accum]\n\t"
-		    "xorl %k[tmp_carries],%k[tmp_carries]\n\t"
-		    "subl $64, %[len]\n\t"
-		    "1:\n\t"
-		    "addq 0*8(%[src]),%[res]\n\t"
-		    "adcq 1*8(%[src]),%[res]\n\t"
-		    "adcq 2*8(%[src]),%[res]\n\t"
-		    "adcq 3*8(%[src]),%[res]\n\t"
-		    "adcl $0,%k[tmp_carries]\n\t"
-		    "addq 4*8(%[src]),%[tmp_accum]\n\t"
-		    "adcq 5*8(%[src]),%[tmp_accum]\n\t"
-		    "adcq 6*8(%[src]),%[tmp_accum]\n\t"
-		    "adcq 7*8(%[src]),%[tmp_accum]\n\t"
-		    "adcl $0,%k[tmp_carries]\n\t"
-		    "addq $64, %[src]\n\t"
-		    "subl $64, %[len]\n\t"
-		    "jge 1b\n\t"
-		    "addq %[tmp_accum],%[res]\n\t"
-		    "adcq %[tmp_carries],%[res]\n\t"
-		    "adcq $0,%[res]"
-		    : [tmp_accum] "=&r"(tmp_accum),
-		      [tmp_carries] "=&r"(tmp_carries), [res] "+r"(temp64),
-		      [len] "+r"(len), [src] "+r"(buff)
-		    : "m"(*(const char *)buff));
+	if (len >= 40) {
+		temp64 = update_csum_40b(temp64, buff);
+		len -= 40;
+		if (!len)
+			return csum_finalize_sum(temp64);
+		buff += 40;
 	}
 
 	if (len & 32) {
@@ -143,7 +108,7 @@ __wsum csum_partial(const void *buff, int len, __wsum sum)
 		    : [res] "+r"(temp64)
 		    : [trail] "r"(trail));
 	}
-	return csum_tail(temp64, odd);
+	return csum_finalize_sum(temp64);
 }
 EXPORT_SYMBOL(csum_partial);
 
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index 0e65d00e2339..23f81ca3f06b 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -128,7 +128,7 @@ static void delay_halt_mwaitx(u64 unused, u64 cycles)
 
 	delay = min_t(u64, MWAITX_MAX_WAIT_CYCLES, cycles);
 	/*
-	 * Use cpu_tss_rw as a cacheline-aligned, seldomly accessed per-cpu
+	 * Use cpu_tss_rw as a cacheline-aligned, seldom accessed per-cpu
 	 * variable as the monitor target.
 	 */
 	 __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0);
diff --git a/arch/x86/lib/misc.c b/arch/x86/lib/misc.c
index 92cd8ecc3a2c..40b81c338ae5 100644
--- a/arch/x86/lib/misc.c
+++ b/arch/x86/lib/misc.c
@@ -8,7 +8,7 @@
  */
 int num_digits(int val)
 {
-	int m = 10;
+	long long m = 10;
 	int d = 1;
 
 	if (val < 0) {
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index ab778eac1952..679b09cfe241 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1370,6 +1370,8 @@ void do_user_addr_fault(struct pt_regs *regs,
 		goto done;
 	}
 	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+	if (fault & VM_FAULT_MAJOR)
+		flags |= FAULT_FLAG_TRIED;
 
 	/* Quick path to respond to signals */
 	if (fault_signal_pending(fault, regs)) {
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index a190aae8ceaf..a0dffaca6d2b 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1013,7 +1013,7 @@ static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd)
 			return;
 	}
 
-	/* free a pte talbe */
+	/* free a pte table */
 	free_pagetable(pmd_page(*pmd), 0);
 	spin_lock(&init_mm.page_table_lock);
 	pmd_clear(pmd);
@@ -1031,7 +1031,7 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
 			return;
 	}
 
-	/* free a pmd talbe */
+	/* free a pmd table */
 	free_pagetable(pud_page(*pud), 0);
 	spin_lock(&init_mm.page_table_lock);
 	pud_clear(pud);
@@ -1049,7 +1049,7 @@ static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d)
 			return;
 	}
 
-	/* free a pud talbe */
+	/* free a pud table */
 	free_pagetable(p4d_page(*p4d), 0);
 	spin_lock(&init_mm.page_table_lock);
 	p4d_clear(p4d);
diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
index a68f2dda0948..70b91de2e053 100644
--- a/arch/x86/mm/mem_encrypt_amd.c
+++ b/arch/x86/mm/mem_encrypt_amd.c
@@ -32,6 +32,7 @@
 #include <asm/msr.h>
 #include <asm/cmdline.h>
 #include <asm/sev.h>
+#include <asm/ia32.h>
 
 #include "mm_internal.h"
 
@@ -481,6 +482,16 @@ void __init sme_early_init(void)
 	 */
 	if (sev_status & MSR_AMD64_SEV_ES_ENABLED)
 		x86_cpuinit.parallel_bringup = false;
+
+	/*
+	 * The VMM is capable of injecting interrupt 0x80 and triggering the
+	 * compatibility syscall path.
+	 *
+	 * By default, the 32-bit emulation is disabled in order to ensure
+	 * the safety of the VM.
+	 */
+	if (sev_status & MSR_AMD64_SEV_ENABLED)
+		ia32_disable();
 }
 
 void __init mem_encrypt_free_decrypted_mem(void)
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index b29ceb19e46e..adc497b93f03 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -450,37 +450,6 @@ int __node_distance(int from, int to)
 EXPORT_SYMBOL(__node_distance);
 
 /*
- * Sanity check to catch more bad NUMA configurations (they are amazingly
- * common).  Make sure the nodes cover all memory.
- */
-static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
-{
-	u64 numaram, e820ram;
-	int i;
-
-	numaram = 0;
-	for (i = 0; i < mi->nr_blks; i++) {
-		u64 s = mi->blk[i].start >> PAGE_SHIFT;
-		u64 e = mi->blk[i].end >> PAGE_SHIFT;
-		numaram += e - s;
-		numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e);
-		if ((s64)numaram < 0)
-			numaram = 0;
-	}
-
-	e820ram = max_pfn - absent_pages_in_range(0, max_pfn);
-
-	/* We seem to lose 3 pages somewhere. Allow 1M of slack. */
-	if ((s64)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) {
-		printk(KERN_ERR "NUMA: nodes only cover %LuMB of your %LuMB e820 RAM. Not used.\n",
-		       (numaram << PAGE_SHIFT) >> 20,
-		       (e820ram << PAGE_SHIFT) >> 20);
-		return false;
-	}
-	return true;
-}
-
-/*
  * Mark all currently memblock-reserved physical memory (which covers the
  * kernel's own memory ranges) as hot-unswappable.
  */
@@ -585,7 +554,8 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
 			return -EINVAL;
 		}
 	}
-	if (!numa_meminfo_cover_memory(mi))
+
+	if (!memblock_validate_numa_coverage(SZ_1M))
 		return -EINVAL;
 
 	/* Finally register nodes. */
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index de10800cd4dd..0904d7e8e126 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -14,7 +14,7 @@
  * memory ranges: uncached, write-combining, write-through, write-protected,
  * and the most commonly used and default attribute: write-back caching.
  *
- * PAT support supercedes and augments MTRR support in a compatible fashion: MTRR is
+ * PAT support supersedes and augments MTRR support in a compatible fashion: MTRR is
  * a hardware interface to enumerate a limited number of physical memory ranges
  * and set their caching attributes explicitly, programmed into the CPU via MSRs.
  * Even modern CPUs have MTRRs enabled - but these are typically not touched
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index bda9f129835e..e9b448d1b1b7 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -1621,7 +1621,7 @@ repeat:
 
 		/*
 		 * We need to keep the pfn from the existing PTE,
-		 * after all we're only going to change it's attributes
+		 * after all we're only going to change its attributes
 		 * not the memory it points to
 		 */
 		new_pte = pfn_pte(pfn, new_prot);
@@ -2447,7 +2447,7 @@ int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address,
 	/*
 	 * The typical sequence for unmapping is to find a pte through
 	 * lookup_address_in_pgd() (ideally, it should never return NULL because
-	 * the address is already mapped) and change it's protections. As pfn is
+	 * the address is already mapped) and change its protections. As pfn is
 	 * the *target* of a mapping, it's not useful while unmapping.
 	 */
 	struct cpa_data cpa = {
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 5dd733944629..669ba1c345b3 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -6,7 +6,7 @@
  *
  *	https://github.com/IAIK/KAISER
  *
- * The original work was written by and and signed off by for the Linux
+ * The original work was written by and signed off by for the Linux
  * kernel by:
  *
  *   Signed-off-by: Richard Fellner <richard.fellner@student.tugraz.at>
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 453ea95b667d..5768d386efab 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -355,7 +355,7 @@ static void l1d_flush_evaluate(unsigned long prev_mm, unsigned long next_mm,
 
 	/*
 	 * Validate that it is not running on an SMT sibling as this would
-	 * make the excercise pointless because the siblings share L1D. If
+	 * make the exercise pointless because the siblings share L1D. If
 	 * it runs on a SMT sibling, notify it with SIGBUS on return to
 	 * user/guest
 	 */
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 8c10d9abc239..919f647c740f 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -17,6 +17,7 @@
 #include <asm/nospec-branch.h>
 #include <asm/text-patching.h>
 #include <asm/unwind.h>
+#include <asm/cfi.h>
 
 static bool all_callee_regs_used[4] = {true, true, true, true};
 
@@ -51,9 +52,11 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 	do { EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0)
 
 #ifdef CONFIG_X86_KERNEL_IBT
-#define EMIT_ENDBR()	EMIT(gen_endbr(), 4)
+#define EMIT_ENDBR()		EMIT(gen_endbr(), 4)
+#define EMIT_ENDBR_POISON()	EMIT(gen_endbr_poison(), 4)
 #else
 #define EMIT_ENDBR()
+#define EMIT_ENDBR_POISON()
 #endif
 
 static bool is_imm8(int value)
@@ -304,6 +307,88 @@ static void pop_callee_regs(u8 **pprog, bool *callee_regs_used)
 	*pprog = prog;
 }
 
+static void emit_nops(u8 **pprog, int len)
+{
+	u8 *prog = *pprog;
+	int i, noplen;
+
+	while (len > 0) {
+		noplen = len;
+
+		if (noplen > ASM_NOP_MAX)
+			noplen = ASM_NOP_MAX;
+
+		for (i = 0; i < noplen; i++)
+			EMIT1(x86_nops[noplen][i]);
+		len -= noplen;
+	}
+
+	*pprog = prog;
+}
+
+/*
+ * Emit the various CFI preambles, see asm/cfi.h and the comments about FineIBT
+ * in arch/x86/kernel/alternative.c
+ */
+
+static void emit_fineibt(u8 **pprog, u32 hash)
+{
+	u8 *prog = *pprog;
+
+	EMIT_ENDBR();
+	EMIT3_off32(0x41, 0x81, 0xea, hash);		/* subl $hash, %r10d	*/
+	EMIT2(0x74, 0x07);				/* jz.d8 +7		*/
+	EMIT2(0x0f, 0x0b);				/* ud2			*/
+	EMIT1(0x90);					/* nop			*/
+	EMIT_ENDBR_POISON();
+
+	*pprog = prog;
+}
+
+static void emit_kcfi(u8 **pprog, u32 hash)
+{
+	u8 *prog = *pprog;
+
+	EMIT1_off32(0xb8, hash);			/* movl $hash, %eax	*/
+#ifdef CONFIG_CALL_PADDING
+	EMIT1(0x90);
+	EMIT1(0x90);
+	EMIT1(0x90);
+	EMIT1(0x90);
+	EMIT1(0x90);
+	EMIT1(0x90);
+	EMIT1(0x90);
+	EMIT1(0x90);
+	EMIT1(0x90);
+	EMIT1(0x90);
+	EMIT1(0x90);
+#endif
+	EMIT_ENDBR();
+
+	*pprog = prog;
+}
+
+static void emit_cfi(u8 **pprog, u32 hash)
+{
+	u8 *prog = *pprog;
+
+	switch (cfi_mode) {
+	case CFI_FINEIBT:
+		emit_fineibt(&prog, hash);
+		break;
+
+	case CFI_KCFI:
+		emit_kcfi(&prog, hash);
+		break;
+
+	default:
+		EMIT_ENDBR();
+		break;
+	}
+
+	*pprog = prog;
+}
+
 /*
  * Emit x86-64 prologue code for BPF program.
  * bpf_tail_call helper will skip the first X86_TAIL_CALL_OFFSET bytes
@@ -315,12 +400,11 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
 {
 	u8 *prog = *pprog;
 
+	emit_cfi(&prog, is_subprog ? cfi_bpf_subprog_hash : cfi_bpf_hash);
 	/* BPF trampoline can be made to work without these nops,
 	 * but let's waste 5 bytes for now and optimize later
 	 */
-	EMIT_ENDBR();
-	memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
-	prog += X86_PATCH_SIZE;
+	emit_nops(&prog, X86_PATCH_SIZE);
 	if (!ebpf_from_cbpf) {
 		if (tail_call_reachable && !is_subprog)
 			/* When it's the entry of the whole tailcall context,
@@ -626,8 +710,7 @@ static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog,
 	if (stack_depth)
 		EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8));
 
-	memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
-	prog += X86_PATCH_SIZE;
+	emit_nops(&prog, X86_PATCH_SIZE);
 
 	/* out: */
 	ctx->tail_call_direct_label = prog - start;
@@ -989,25 +1072,6 @@ static void detect_reg_usage(struct bpf_insn *insn, int insn_cnt,
 	}
 }
 
-static void emit_nops(u8 **pprog, int len)
-{
-	u8 *prog = *pprog;
-	int i, noplen;
-
-	while (len > 0) {
-		noplen = len;
-
-		if (noplen > ASM_NOP_MAX)
-			noplen = ASM_NOP_MAX;
-
-		for (i = 0; i < noplen; i++)
-			EMIT1(x86_nops[noplen][i]);
-		len -= noplen;
-	}
-
-	*pprog = prog;
-}
-
 /* emit the 3-byte VEX prefix
  *
  * r: same as rex.r, extra bit for ModRM reg field
@@ -2143,7 +2207,7 @@ static void save_args(const struct btf_func_model *m, u8 **prog,
 		} else {
 			/* Only copy the arguments on-stack to current
 			 * 'stack_size' and ignore the regs, used to
-			 * prepare the arguments on-stack for orign call.
+			 * prepare the arguments on-stack for origin call.
 			 */
 			if (for_call_origin) {
 				nr_regs += arg_regs;
@@ -2198,7 +2262,8 @@ static void restore_regs(const struct btf_func_model *m, u8 **prog,
 
 static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 			   struct bpf_tramp_link *l, int stack_size,
-			   int run_ctx_off, bool save_ret)
+			   int run_ctx_off, bool save_ret,
+			   void *image, void *rw_image)
 {
 	u8 *prog = *pprog;
 	u8 *jmp_insn;
@@ -2226,7 +2291,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	else
 		EMIT4(0x48, 0x8D, 0x75, -run_ctx_off);
 
-	if (emit_rsb_call(&prog, bpf_trampoline_enter(p), prog))
+	if (emit_rsb_call(&prog, bpf_trampoline_enter(p), image + (prog - (u8 *)rw_image)))
 		return -EINVAL;
 	/* remember prog start time returned by __bpf_prog_enter */
 	emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0);
@@ -2250,7 +2315,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 			       (long) p->insnsi >> 32,
 			       (u32) (long) p->insnsi);
 	/* call JITed bpf program or interpreter */
-	if (emit_rsb_call(&prog, p->bpf_func, prog))
+	if (emit_rsb_call(&prog, p->bpf_func, image + (prog - (u8 *)rw_image)))
 		return -EINVAL;
 
 	/*
@@ -2277,7 +2342,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 		EMIT3_off32(0x48, 0x8D, 0x95, -run_ctx_off);
 	else
 		EMIT4(0x48, 0x8D, 0x55, -run_ctx_off);
-	if (emit_rsb_call(&prog, bpf_trampoline_exit(p), prog))
+	if (emit_rsb_call(&prog, bpf_trampoline_exit(p), image + (prog - (u8 *)rw_image)))
 		return -EINVAL;
 
 	*pprog = prog;
@@ -2312,14 +2377,15 @@ static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond)
 
 static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
 		      struct bpf_tramp_links *tl, int stack_size,
-		      int run_ctx_off, bool save_ret)
+		      int run_ctx_off, bool save_ret,
+		      void *image, void *rw_image)
 {
 	int i;
 	u8 *prog = *pprog;
 
 	for (i = 0; i < tl->nr_links; i++) {
 		if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size,
-				    run_ctx_off, save_ret))
+				    run_ctx_off, save_ret, image, rw_image))
 			return -EINVAL;
 	}
 	*pprog = prog;
@@ -2328,7 +2394,8 @@ static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
 
 static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
 			      struct bpf_tramp_links *tl, int stack_size,
-			      int run_ctx_off, u8 **branches)
+			      int run_ctx_off, u8 **branches,
+			      void *image, void *rw_image)
 {
 	u8 *prog = *pprog;
 	int i;
@@ -2339,7 +2406,8 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
 	emit_mov_imm32(&prog, false, BPF_REG_0, 0);
 	emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
 	for (i = 0; i < tl->nr_links; i++) {
-		if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size, run_ctx_off, true))
+		if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size, run_ctx_off, true,
+				    image, rw_image))
 			return -EINVAL;
 
 		/* mod_ret prog stored return value into [rbp - 8]. Emit:
@@ -2422,10 +2490,11 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
  * add rsp, 8                      // skip eth_type_trans's frame
  * ret                             // return to its caller
  */
-int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
-				const struct btf_func_model *m, u32 flags,
-				struct bpf_tramp_links *tlinks,
-				void *func_addr)
+static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_image,
+					 void *rw_image_end, void *image,
+					 const struct btf_func_model *m, u32 flags,
+					 struct bpf_tramp_links *tlinks,
+					 void *func_addr)
 {
 	int i, ret, nr_regs = m->nr_args, stack_size = 0;
 	int regs_off, nregs_off, ip_off, run_ctx_off, arg_stack_off, rbx_off;
@@ -2437,10 +2506,19 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	u8 *prog;
 	bool save_ret;
 
+	/*
+	 * F_INDIRECT is only compatible with F_RET_FENTRY_RET, it is
+	 * explicitly incompatible with F_CALL_ORIG | F_SKIP_FRAME | F_IP_ARG
+	 * because @func_addr.
+	 */
+	WARN_ON_ONCE((flags & BPF_TRAMP_F_INDIRECT) &&
+		     (flags & ~(BPF_TRAMP_F_INDIRECT | BPF_TRAMP_F_RET_FENTRY_RET)));
+
 	/* extra registers for struct arguments */
-	for (i = 0; i < m->nr_args; i++)
+	for (i = 0; i < m->nr_args; i++) {
 		if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG)
 			nr_regs += (m->arg_size[i] + 7) / 8 - 1;
+	}
 
 	/* x86-64 supports up to MAX_BPF_FUNC_ARGS arguments. 1-6
 	 * are passed through regs, the remains are through stack.
@@ -2521,22 +2599,29 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 		orig_call += X86_PATCH_SIZE;
 	}
 
-	prog = image;
+	prog = rw_image;
 
-	EMIT_ENDBR();
-	/*
-	 * This is the direct-call trampoline, as such it needs accounting
-	 * for the __fentry__ call.
-	 */
-	x86_call_depth_emit_accounting(&prog, NULL);
+	if (flags & BPF_TRAMP_F_INDIRECT) {
+		/*
+		 * Indirect call for bpf_struct_ops
+		 */
+		emit_cfi(&prog, cfi_get_func_hash(func_addr));
+	} else {
+		/*
+		 * Direct-call fentry stub, as such it needs accounting for the
+		 * __fentry__ call.
+		 */
+		x86_call_depth_emit_accounting(&prog, NULL);
+	}
 	EMIT1(0x55);		 /* push rbp */
 	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
-	if (!is_imm8(stack_size))
+	if (!is_imm8(stack_size)) {
 		/* sub rsp, stack_size */
 		EMIT3_off32(0x48, 0x81, 0xEC, stack_size);
-	else
+	} else {
 		/* sub rsp, stack_size */
 		EMIT4(0x48, 0x83, 0xEC, stack_size);
+	}
 	if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
 		EMIT1(0x50);		/* push rax */
 	/* mov QWORD PTR [rbp - rbx_off], rbx */
@@ -2563,16 +2648,18 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
 		/* arg1: mov rdi, im */
 		emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im);
-		if (emit_rsb_call(&prog, __bpf_tramp_enter, prog)) {
+		if (emit_rsb_call(&prog, __bpf_tramp_enter,
+				  image + (prog - (u8 *)rw_image))) {
 			ret = -EINVAL;
 			goto cleanup;
 		}
 	}
 
-	if (fentry->nr_links)
+	if (fentry->nr_links) {
 		if (invoke_bpf(m, &prog, fentry, regs_off, run_ctx_off,
-			       flags & BPF_TRAMP_F_RET_FENTRY_RET))
+			       flags & BPF_TRAMP_F_RET_FENTRY_RET, image, rw_image))
 			return -EINVAL;
+	}
 
 	if (fmod_ret->nr_links) {
 		branches = kcalloc(fmod_ret->nr_links, sizeof(u8 *),
@@ -2581,7 +2668,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 			return -ENOMEM;
 
 		if (invoke_bpf_mod_ret(m, &prog, fmod_ret, regs_off,
-				       run_ctx_off, branches)) {
+				       run_ctx_off, branches, image, rw_image)) {
 			ret = -EINVAL;
 			goto cleanup;
 		}
@@ -2591,27 +2678,27 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 		restore_regs(m, &prog, regs_off);
 		save_args(m, &prog, arg_stack_off, true);
 
-		if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
+		if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) {
 			/* Before calling the original function, restore the
 			 * tail_call_cnt from stack to rax.
 			 */
 			RESTORE_TAIL_CALL_CNT(stack_size);
+		}
 
 		if (flags & BPF_TRAMP_F_ORIG_STACK) {
 			emit_ldx(&prog, BPF_DW, BPF_REG_6, BPF_REG_FP, 8);
 			EMIT2(0xff, 0xd3); /* call *rbx */
 		} else {
 			/* call original function */
-			if (emit_rsb_call(&prog, orig_call, prog)) {
+			if (emit_rsb_call(&prog, orig_call, image + (prog - (u8 *)rw_image))) {
 				ret = -EINVAL;
 				goto cleanup;
 			}
 		}
 		/* remember return value in a stack for bpf prog to access */
 		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
-		im->ip_after_call = prog;
-		memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
-		prog += X86_PATCH_SIZE;
+		im->ip_after_call = image + (prog - (u8 *)rw_image);
+		emit_nops(&prog, X86_PATCH_SIZE);
 	}
 
 	if (fmod_ret->nr_links) {
@@ -2624,16 +2711,19 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 		/* Update the branches saved in invoke_bpf_mod_ret with the
 		 * aligned address of do_fexit.
 		 */
-		for (i = 0; i < fmod_ret->nr_links; i++)
-			emit_cond_near_jump(&branches[i], prog, branches[i],
-					    X86_JNE);
+		for (i = 0; i < fmod_ret->nr_links; i++) {
+			emit_cond_near_jump(&branches[i], image + (prog - (u8 *)rw_image),
+					    image + (branches[i] - (u8 *)rw_image), X86_JNE);
+		}
 	}
 
-	if (fexit->nr_links)
-		if (invoke_bpf(m, &prog, fexit, regs_off, run_ctx_off, false)) {
+	if (fexit->nr_links) {
+		if (invoke_bpf(m, &prog, fexit, regs_off, run_ctx_off,
+			       false, image, rw_image)) {
 			ret = -EINVAL;
 			goto cleanup;
 		}
+	}
 
 	if (flags & BPF_TRAMP_F_RESTORE_REGS)
 		restore_regs(m, &prog, regs_off);
@@ -2643,18 +2733,19 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	 * restored to R0.
 	 */
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
-		im->ip_epilogue = prog;
+		im->ip_epilogue = image + (prog - (u8 *)rw_image);
 		/* arg1: mov rdi, im */
 		emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im);
-		if (emit_rsb_call(&prog, __bpf_tramp_exit, prog)) {
+		if (emit_rsb_call(&prog, __bpf_tramp_exit, image + (prog - (u8 *)rw_image))) {
 			ret = -EINVAL;
 			goto cleanup;
 		}
-	} else if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
+	} else if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) {
 		/* Before running the original function, restore the
 		 * tail_call_cnt from stack to rax.
 		 */
 		RESTORE_TAIL_CALL_CNT(stack_size);
+	}
 
 	/* restore return value of orig_call or fentry prog back into RAX */
 	if (save_ret)
@@ -2662,22 +2753,94 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 
 	emit_ldx(&prog, BPF_DW, BPF_REG_6, BPF_REG_FP, -rbx_off);
 	EMIT1(0xC9); /* leave */
-	if (flags & BPF_TRAMP_F_SKIP_FRAME)
+	if (flags & BPF_TRAMP_F_SKIP_FRAME) {
 		/* skip our return address and return to parent */
 		EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */
-	emit_return(&prog, prog);
+	}
+	emit_return(&prog, image + (prog - (u8 *)rw_image));
 	/* Make sure the trampoline generation logic doesn't overflow */
-	if (WARN_ON_ONCE(prog > (u8 *)image_end - BPF_INSN_SAFETY)) {
+	if (WARN_ON_ONCE(prog > (u8 *)rw_image_end - BPF_INSN_SAFETY)) {
 		ret = -EFAULT;
 		goto cleanup;
 	}
-	ret = prog - (u8 *)image;
+	ret = prog - (u8 *)rw_image + BPF_INSN_SAFETY;
 
 cleanup:
 	kfree(branches);
 	return ret;
 }
 
+void *arch_alloc_bpf_trampoline(unsigned int size)
+{
+	return bpf_prog_pack_alloc(size, jit_fill_hole);
+}
+
+void arch_free_bpf_trampoline(void *image, unsigned int size)
+{
+	bpf_prog_pack_free(image, size);
+}
+
+void arch_protect_bpf_trampoline(void *image, unsigned int size)
+{
+}
+
+void arch_unprotect_bpf_trampoline(void *image, unsigned int size)
+{
+}
+
+int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
+				const struct btf_func_model *m, u32 flags,
+				struct bpf_tramp_links *tlinks,
+				void *func_addr)
+{
+	void *rw_image, *tmp;
+	int ret;
+	u32 size = image_end - image;
+
+	/* rw_image doesn't need to be in module memory range, so we can
+	 * use kvmalloc.
+	 */
+	rw_image = kvmalloc(size, GFP_KERNEL);
+	if (!rw_image)
+		return -ENOMEM;
+
+	ret = __arch_prepare_bpf_trampoline(im, rw_image, rw_image + size, image, m,
+					    flags, tlinks, func_addr);
+	if (ret < 0)
+		goto out;
+
+	tmp = bpf_arch_text_copy(image, rw_image, size);
+	if (IS_ERR(tmp))
+		ret = PTR_ERR(tmp);
+out:
+	kvfree(rw_image);
+	return ret;
+}
+
+int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
+			     struct bpf_tramp_links *tlinks, void *func_addr)
+{
+	struct bpf_tramp_image im;
+	void *image;
+	int ret;
+
+	/* Allocate a temporary buffer for __arch_prepare_bpf_trampoline().
+	 * This will NOT cause fragmentation in direct map, as we do not
+	 * call set_memory_*() on this buffer.
+	 *
+	 * We cannot use kvmalloc here, because we need image to be in
+	 * module memory range.
+	 */
+	image = bpf_jit_alloc_exec(PAGE_SIZE);
+	if (!image)
+		return -ENOMEM;
+
+	ret = __arch_prepare_bpf_trampoline(&im, image, image + PAGE_SIZE, image,
+					    m, flags, tlinks, func_addr);
+	bpf_jit_free_exec(image);
+	return ret;
+}
+
 static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs, u8 *image, u8 *buf)
 {
 	u8 *jg_reloc, *prog = *pprog;
@@ -2935,9 +3098,16 @@ out_image:
 			jit_data->header = header;
 			jit_data->rw_header = rw_header;
 		}
-		prog->bpf_func = (void *)image;
+		/*
+		 * ctx.prog_offset is used when CFI preambles put code *before*
+		 * the function. See emit_cfi(). For FineIBT specifically this code
+		 * can also be executed and bpf_prog_kallsyms_add() will
+		 * generate an additional symbol to cover this, hence also
+		 * decrement proglen.
+		 */
+		prog->bpf_func = (void *)image + cfi_get_offset();
 		prog->jited = 1;
-		prog->jited_len = proglen;
+		prog->jited_len = proglen - cfi_get_offset();
 	} else {
 		prog = orig_prog;
 	}
@@ -2992,6 +3162,7 @@ void bpf_jit_free(struct bpf_prog *prog)
 			kvfree(jit_data->addrs);
 			kfree(jit_data);
 		}
+		prog->bpf_func = (void *)prog->bpf_func - cfi_get_offset();
 		hdr = bpf_jit_binary_pack_hdr(prog);
 		bpf_jit_binary_pack_free(hdr, NULL);
 		WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(prog));
@@ -3025,3 +3196,49 @@ void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp
 #endif
 	WARN(1, "verification of programs using bpf_throw should have failed\n");
 }
+
+void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
+			       struct bpf_prog *new, struct bpf_prog *old)
+{
+	u8 *old_addr, *new_addr, *old_bypass_addr;
+	int ret;
+
+	old_bypass_addr = old ? NULL : poke->bypass_addr;
+	old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL;
+	new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL;
+
+	/*
+	 * On program loading or teardown, the program's kallsym entry
+	 * might not be in place, so we use __bpf_arch_text_poke to skip
+	 * the kallsyms check.
+	 */
+	if (new) {
+		ret = __bpf_arch_text_poke(poke->tailcall_target,
+					   BPF_MOD_JUMP,
+					   old_addr, new_addr);
+		BUG_ON(ret < 0);
+		if (!old) {
+			ret = __bpf_arch_text_poke(poke->tailcall_bypass,
+						   BPF_MOD_JUMP,
+						   poke->bypass_addr,
+						   NULL);
+			BUG_ON(ret < 0);
+		}
+	} else {
+		ret = __bpf_arch_text_poke(poke->tailcall_bypass,
+					   BPF_MOD_JUMP,
+					   old_bypass_addr,
+					   poke->bypass_addr);
+		BUG_ON(ret < 0);
+		/* let other CPUs finish the execution of program
+		 * so that it will not possible to expose them
+		 * to invalid nop, stack unwind, nop state
+		 */
+		if (!ret)
+			synchronize_rcu();
+		ret = __bpf_arch_text_poke(poke->tailcall_target,
+					   BPF_MOD_JUMP,
+					   old_addr, NULL);
+		BUG_ON(ret < 0);
+	}
+}
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index 429a89c5468b..b18ce19981ec 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -1194,7 +1194,7 @@ struct jit_context {
 #define PROLOGUE_SIZE 35
 
 /*
- * Emit prologue code for BPF program and check it's size.
+ * Emit prologue code for BPF program and check its size.
  * bpf_tail_call helper will skip it while jumping into another program.
  */
 static void emit_prologue(u8 **pprog, u32 stack_depth)
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index 7368afc03998..8c8ddc4dcc08 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -14,6 +14,7 @@
 #include <linux/dma-map-ops.h>
 #include <linux/swiotlb.h>
 #include <asm/iommu.h>
+#include <asm/sta2x11.h>
 
 #define STA2X11_SWIOTLB_SIZE (4*1024*1024)
 
diff --git a/arch/x86/platform/intel-quark/imr_selftest.c b/arch/x86/platform/intel-quark/imr_selftest.c
index 761f3689f60a..84ba715f44d1 100644
--- a/arch/x86/platform/intel-quark/imr_selftest.c
+++ b/arch/x86/platform/intel-quark/imr_selftest.c
@@ -6,7 +6,7 @@
  * Copyright(c) 2015 Bryan O'Donoghue <pure.logic@nexus-software.ie>
  *
  * IMR self test. The purpose of this module is to run a set of tests on the
- * IMR API to validate it's sanity. We check for overlapping, reserved
+ * IMR API to validate its sanity. We check for overlapping, reserved
  * addresses and setup/teardown sanity.
  *
  */
diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S
index c4365a05ab83..f7235ef87bc3 100644
--- a/arch/x86/platform/pvh/head.S
+++ b/arch/x86/platform/pvh/head.S
@@ -11,6 +11,7 @@
 #include <linux/elfnote.h>
 #include <linux/init.h>
 #include <linux/linkage.h>
+#include <asm/desc_defs.h>
 #include <asm/segment.h>
 #include <asm/asm.h>
 #include <asm/boot.h>
@@ -41,7 +42,7 @@
  *             Bit 8 (TF) must be cleared. Other bits are all unspecified.
  *
  * All other processor registers and flag bits are unspecified. The OS is in
- * charge of setting up it's own stack, GDT and IDT.
+ * charge of setting up its own stack, GDT and IDT.
  */
 
 #define PVH_GDT_ENTRY_CS	1
@@ -148,11 +149,11 @@ SYM_DATA_END(gdt)
 SYM_DATA_START_LOCAL(gdt_start)
 	.quad 0x0000000000000000            /* NULL descriptor */
 #ifdef CONFIG_X86_64
-	.quad GDT_ENTRY(0xa09a, 0, 0xfffff) /* PVH_CS_SEL */
+	.quad GDT_ENTRY(DESC_CODE64, 0, 0xfffff) /* PVH_CS_SEL */
 #else
-	.quad GDT_ENTRY(0xc09a, 0, 0xfffff) /* PVH_CS_SEL */
+	.quad GDT_ENTRY(DESC_CODE32, 0, 0xfffff) /* PVH_CS_SEL */
 #endif
-	.quad GDT_ENTRY(0xc092, 0, 0xfffff) /* PVH_DS_SEL */
+	.quad GDT_ENTRY(DESC_DATA32, 0, 0xfffff) /* PVH_DS_SEL */
 SYM_DATA_END_LABEL(gdt_start, SYM_L_LOCAL, gdt_end)
 
 	.balign 16
diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c
index 4221259a5870..a379501b7a69 100644
--- a/arch/x86/platform/uv/uv_irq.c
+++ b/arch/x86/platform/uv/uv_irq.c
@@ -35,7 +35,7 @@ static void uv_program_mmr(struct irq_cfg *cfg, struct uv_irq_2_mmr_pnode *info)
 	mmr_value = 0;
 	entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
 	entry->vector		= cfg->vector;
-	entry->delivery_mode	= apic->delivery_mode;
+	entry->delivery_mode	= APIC_DELIVERY_MODE_FIXED;
 	entry->dest_mode	= apic->dest_mode_logical;
 	entry->polarity		= 0;
 	entry->trigger		= 0;
diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c
index e03207de2880..5c50e550ab63 100644
--- a/arch/x86/platform/uv/uv_nmi.c
+++ b/arch/x86/platform/uv/uv_nmi.c
@@ -741,7 +741,7 @@ static void uv_nmi_dump_state_cpu(int cpu, struct pt_regs *regs)
 	this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_DUMP_DONE);
 }
 
-/* Trigger a slave CPU to dump it's state */
+/* Trigger a slave CPU to dump its state */
 static void uv_nmi_trigger_dump(int cpu)
 {
 	int retry = uv_nmi_trigger_delay;
diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c
index ff5afc8a5a41..3712afc3534d 100644
--- a/arch/x86/platform/uv/uv_time.c
+++ b/arch/x86/platform/uv/uv_time.c
@@ -270,7 +270,7 @@ static int uv_rtc_unset_timer(int cpu, int force)
  * Read the RTC.
  *
  * Starting with HUB rev 2.0, the UV RTC register is replicated across all
- * cachelines of it's own page.  This allows faster simultaneous reads
+ * cachelines of its own page.  This allows faster simultaneous reads
  * from a given socket.
  */
 static u64 uv_read_rtc(struct clocksource *cs)
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index 788e5559549f..f9bc444a3064 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -61,7 +61,7 @@ void __init reserve_real_mode(void)
 		set_real_mode_mem(mem);
 
 	/*
-	 * Unconditionally reserve the entire fisrt 1M, see comment in
+	 * Unconditionally reserve the entire first 1M, see comment in
 	 * setup_arch().
 	 */
 	memblock_reserve(0, SZ_1M);
diff --git a/arch/x86/realmode/rm/reboot.S b/arch/x86/realmode/rm/reboot.S
index f10515b10e0a..e714b4624e36 100644
--- a/arch/x86/realmode/rm/reboot.S
+++ b/arch/x86/realmode/rm/reboot.S
@@ -1,5 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/linkage.h>
+#include <asm/desc_defs.h>
 #include <asm/segment.h>
 #include <asm/page_types.h>
 #include <asm/processor-flags.h>
@@ -153,5 +154,5 @@ SYM_DATA_START(machine_real_restart_gdt)
 	 * base value 0x100; since this is consistent with real mode
 	 * semantics we don't have to reload the segments once CR0.PE = 0.
 	 */
-	.quad	GDT_ENTRY(0x0093, 0x100, 0xffff)
+	.quad	GDT_ENTRY(DESC_DATA16, 0x100, 0xffff)
 SYM_DATA_END(machine_real_restart_gdt)
diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile
index 90e820ac9771..7278e2545c35 100644
--- a/arch/x86/tools/Makefile
+++ b/arch/x86/tools/Makefile
@@ -17,7 +17,7 @@ reformatter = $(srctree)/arch/x86/tools/objdump_reformat.awk
 chkobjdump = $(srctree)/arch/x86/tools/chkobjdump.awk
 
 quiet_cmd_posttest = TEST    $@
-      cmd_posttest = ($(OBJDUMP) -v | $(AWK) -f $(chkobjdump)) || $(OBJDUMP) -d -j .text $(objtree)/vmlinux | $(AWK) -f $(reformatter) | $(obj)/insn_decoder_test $(posttest_64bit) $(posttest_verbose)
+      cmd_posttest = $(OBJDUMP) -d -j .text $(objtree)/vmlinux | $(AWK) -f $(reformatter) | $(obj)/insn_decoder_test $(posttest_64bit) $(posttest_verbose)
 
 quiet_cmd_sanitytest = TEST    $@
       cmd_sanitytest = $(obj)/insn_sanity $(posttest_64bit) -m 1000000
diff --git a/arch/x86/tools/chkobjdump.awk b/arch/x86/tools/chkobjdump.awk
deleted file mode 100644
index a4cf678cf5c8..000000000000
--- a/arch/x86/tools/chkobjdump.awk
+++ /dev/null
@@ -1,34 +0,0 @@
-# GNU objdump version checker
-#
-# Usage:
-# objdump -v | awk -f chkobjdump.awk
-BEGIN {
-	# objdump version 2.19 or later is OK for the test.
-	od_ver = 2;
-	od_sver = 19;
-}
-
-/^GNU objdump/ {
-	verstr = ""
-	gsub(/\(.*\)/, "");
-	for (i = 3; i <= NF; i++)
-		if (match($(i), "^[0-9]")) {
-			verstr = $(i);
-			break;
-		}
-	if (verstr == "") {
-		printf("Warning: Failed to find objdump version number.\n");
-		exit 0;
-	}
-	split(verstr, ver, ".");
-	if (ver[1] > od_ver ||
-	    (ver[1] == od_ver && ver[2] >= od_sver)) {
-		exit 1;
-	} else {
-		printf("Warning: objdump version %s is older than %d.%d\n",
-		       verstr, od_ver, od_sver);
-		print("Warning: Skipping posttest.");
-		# Logic is inverted, because we just skip test without error.
-		exit 0;
-	}
-}
diff --git a/arch/x86/tools/objdump_reformat.awk b/arch/x86/tools/objdump_reformat.awk
index f418c91b71f0..20b08a6c4d33 100644
--- a/arch/x86/tools/objdump_reformat.awk
+++ b/arch/x86/tools/objdump_reformat.awk
@@ -11,8 +11,8 @@ BEGIN {
 	prev_addr = ""
 	prev_hex = ""
 	prev_mnemonic = ""
-	bad_expr = "(\\(bad\\)|^rex|^.byte|^rep(z|nz)$|^lock$|^es$|^cs$|^ss$|^ds$|^fs$|^gs$|^data(16|32)$|^addr(16|32|64))"
-	fwait_expr = "^9b "
+	bad_expr = "(\\(bad\\)|<unknown>|^rex|^.byte|^rep(z|nz)$|^lock$|^es$|^cs$|^ss$|^ds$|^fs$|^gs$|^data(16|32)$|^addr(16|32|64))"
+	fwait_expr = "^9b[ \t]*fwait"
 	fwait_str="9b\tfwait"
 }
 
@@ -22,7 +22,7 @@ BEGIN {
 }
 
 /^ *[0-9a-f]+:/ {
-	if (split($0, field, "\t") < 3) {
+	if (split($0, field, /: |\t/) < 3) {
 		# This is a continuation of the same insn.
 		prev_hex = prev_hex field[2]
 	} else {
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index d30949e25ebd..a3bae2b24626 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -66,7 +66,7 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = {
 	[S_REL] =
 	"^(__init_(begin|end)|"
 	"__x86_cpu_dev_(start|end)|"
-	"(__parainstructions|__alt_instructions)(_end)?|"
+	"__alt_instructions(_end)?|"
 	"(__iommu_table|__apicdrivers|__smp_locks)(_end)?|"
 	"__(start|end)_pci_.*|"
 #if CONFIG_FW_LOADER
diff --git a/arch/x86/um/sysrq_64.c b/arch/x86/um/sysrq_64.c
index ef1eb4f4f612..0bf6de40abff 100644
--- a/arch/x86/um/sysrq_64.c
+++ b/arch/x86/um/sysrq_64.c
@@ -6,6 +6,7 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/pid.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/utsname.h>
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 9b1ec5d8c99c..a65fc2ae15b4 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -9,6 +9,7 @@ config XEN
 	select PARAVIRT_CLOCK
 	select X86_HV_CALLBACK_VECTOR
 	depends on X86_64 || (X86_32 && X86_PAE)
+	depends on X86_64 || (X86_GENERIC || MPENTIUM4 || MCORE2 || MATOM || MK8)
 	depends on X86_LOCAL_APIC && X86_TSC
 	help
 	  This is the Linux Xen port.  Enabling this will allow the
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 0337392a3121..3c61bb98c10e 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -33,9 +33,12 @@ EXPORT_SYMBOL_GPL(hypercall_page);
  * and xen_vcpu_setup for details. By default it points to share_info->vcpu_info
  * but during boot it is switched to point to xen_vcpu_info.
  * The pointer is used in xen_evtchn_do_upcall to acknowledge pending events.
+ * Make sure that xen_vcpu_info doesn't cross a page boundary by making it
+ * cache-line aligned (the struct is guaranteed to have a size of 64 bytes,
+ * which matches the cache line size of 64-bit x86 processors).
  */
 DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
-DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
+DEFINE_PER_CPU_ALIGNED(struct vcpu_info, xen_vcpu_info);
 
 /* Linux <-> Xen vCPU id mapping */
 DEFINE_PER_CPU(uint32_t, xen_vcpu_id);
@@ -160,6 +163,7 @@ void xen_vcpu_setup(int cpu)
 	int err;
 	struct vcpu_info *vcpup;
 
+	BUILD_BUG_ON(sizeof(*vcpup) > SMP_CACHE_BYTES);
 	BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
 
 	/*
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index bbbfdd495ebd..aeb33e0a3f76 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -704,7 +704,7 @@ static struct trap_array_entry trap_array[] = {
 	TRAP_ENTRY(exc_int3,				false ),
 	TRAP_ENTRY(exc_overflow,			false ),
 #ifdef CONFIG_IA32_EMULATION
-	{ entry_INT80_compat,          xen_entry_INT80_compat,          false },
+	TRAP_ENTRY(int80_emulation,			false ),
 #endif
 	TRAP_ENTRY(exc_page_fault,			false ),
 	TRAP_ENTRY(exc_divide_error,			false ),
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index 6092fea7d651..39982f955cfe 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -45,7 +45,7 @@ static const typeof(pv_ops) xen_irq_ops __initconst = {
 		/* Initial interrupt flag handling only called while interrupts off. */
 		.save_fl = __PV_IS_CALLEE_SAVE(paravirt_ret0),
 		.irq_disable = __PV_IS_CALLEE_SAVE(paravirt_nop),
-		.irq_enable = __PV_IS_CALLEE_SAVE(paravirt_BUG),
+		.irq_enable = __PV_IS_CALLEE_SAVE(BUG_func),
 
 		.safe_halt = xen_safe_halt,
 		.halt = xen_halt,
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index b6830554ff69..72af496a160c 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -34,7 +34,7 @@
  * would need to validate the whole pagetable before going on.
  * Naturally, this is quite slow.  The solution is to "pin" a
  * pagetable, which enforces all the constraints on the pagetable even
- * when it is not actively in use.  This menas that Xen can be assured
+ * when it is not actively in use.  This means that Xen can be assured
  * that it is still valid when you do load it into %cr3, and doesn't
  * need to revalidate it.
  *
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 9e5e68008785..1a9cd18dfbd3 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -156,7 +156,7 @@ xen_pv_trap asm_xenpv_exc_machine_check
 #endif /* CONFIG_X86_MCE */
 xen_pv_trap asm_exc_simd_coprocessor_error
 #ifdef CONFIG_IA32_EMULATION
-xen_pv_trap entry_INT80_compat
+xen_pv_trap asm_int80_emulation
 #endif
 xen_pv_trap asm_exc_xen_unknown_trap
 xen_pv_trap asm_exc_xen_hypervisor_callback
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 408a2aa66c69..a87ab36889e7 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -21,7 +21,7 @@ extern void *xen_initial_gdt;
 struct trap_info;
 void xen_copy_trap_info(struct trap_info *traps);
 
-DECLARE_PER_CPU(struct vcpu_info, xen_vcpu_info);
+DECLARE_PER_CPU_ALIGNED(struct vcpu_info, xen_vcpu_info);
 DECLARE_PER_CPU(unsigned long, xen_cr3);
 DECLARE_PER_CPU(unsigned long, xen_current_cr3);
 
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 7d792077e5fd..e031eaf36c99 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -793,7 +793,7 @@ config ARCH_FORCE_MAX_ORDER
 	default "10"
 	help
 	  The kernel page allocator limits the size of maximal physically
-	  contiguous allocations. The limit is called MAX_ORDER and it
+	  contiguous allocations. The limit is called MAX_PAGE_ORDER and it
 	  defines the maximal power of two of number of pages that can be
 	  allocated as a single contiguous block. This option allows
 	  overriding the default setting when ability to allocate very
diff --git a/arch/xtensa/include/asm/kasan.h b/arch/xtensa/include/asm/kasan.h
index 216b6f32c375..8d2b4248466f 100644
--- a/arch/xtensa/include/asm/kasan.h
+++ b/arch/xtensa/include/asm/kasan.h
@@ -18,6 +18,8 @@
 #define KASAN_SHADOW_START (XCHAL_PAGE_TABLE_VADDR + XCHAL_PAGE_TABLE_SIZE)
 /* Size of the shadow map */
 #define KASAN_SHADOW_SIZE (-KASAN_START_VADDR >> KASAN_SHADOW_SCALE_SHIFT)
+/* End of the shadow map */
+#define KASAN_SHADOW_END (KASAN_SHADOW_START + KASAN_SHADOW_SIZE)
 /* Offset for mem to shadow address transformation */
 #define KASAN_SHADOW_OFFSET __XTENSA_UL_CONST(CONFIG_KASAN_SHADOW_OFFSET)
 
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 06eefa9c1458..dd116598fb25 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -427,3 +427,8 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount
+459	common	lsm_get_self_attr		sys_lsm_get_self_attr
+460	common	lsm_set_self_attr		sys_lsm_set_self_attr
+461	common	lsm_list_modules		sys_lsm_list_modules
diff --git a/block/Kconfig b/block/Kconfig
index 55ae2286a4de..1de4682d48cc 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -78,6 +78,26 @@ config BLK_DEV_INTEGRITY_T10
 	select CRC_T10DIF
 	select CRC64_ROCKSOFT
 
+config BLK_DEV_WRITE_MOUNTED
+	bool "Allow writing to mounted block devices"
+	default y
+	help
+	When a block device is mounted, writing to its buffer cache is very
+	likely going to cause filesystem corruption. It is also rather easy to
+	crash the kernel in this way since the filesystem has no practical way
+	of detecting these writes to buffer cache and verifying its metadata
+	integrity. However there are some setups that need this capability
+	like running fsck on read-only mounted root device, modifying some
+	features on mounted ext4 filesystem, and similar. If you say N, the
+	kernel will prevent processes from writing to block devices that are
+	mounted by filesystems which provides some more protection from runaway
+	privileged processes and generally makes it much harder to crash
+	filesystem drivers. Note however that this does not prevent
+	underlying device(s) from being modified by other means, e.g. by
+	directly submitting SCSI commands or through access to lower layers of
+	storage stack. If in doubt, say Y. The configuration can be overridden
+	with the bdev_allow_write_mounted boot option.
+
 config BLK_DEV_ZONED
 	bool "Zoned block device support"
 	select MQ_IOSCHED_DEADLINE
diff --git a/block/badblocks.c b/block/badblocks.c
index fc92d4e18aa3..db4ec8b9b2a8 100644
--- a/block/badblocks.c
+++ b/block/badblocks.c
@@ -1312,12 +1312,14 @@ re_check:
 	prev = prev_badblocks(bb, &bad, hint);
 
 	/* start after all badblocks */
-	if ((prev + 1) >= bb->count && !overlap_front(bb, prev, &bad)) {
+	if ((prev >= 0) &&
+	    ((prev + 1) >= bb->count) && !overlap_front(bb, prev, &bad)) {
 		len = sectors;
 		goto update_sectors;
 	}
 
-	if (overlap_front(bb, prev, &bad)) {
+	/* Overlapped with front badblocks record */
+	if ((prev >= 0) && overlap_front(bb, prev, &bad)) {
 		if (BB_ACK(p[prev]))
 			acked_badblocks++;
 		else
diff --git a/block/bdev.c b/block/bdev.c
index e4cfb7adb645..e9f1b12bd75c 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -30,6 +30,9 @@
 #include "../fs/internal.h"
 #include "blk.h"
 
+/* Should we allow writing to mounted block devices? */
+static bool bdev_allow_write_mounted = IS_ENABLED(CONFIG_BLK_DEV_WRITE_MOUNTED);
+
 struct bdev_inode {
 	struct block_device bdev;
 	struct inode vfs_inode;
@@ -207,85 +210,88 @@ int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend)
 EXPORT_SYMBOL(sync_blockdev_range);
 
 /**
- * freeze_bdev - lock a filesystem and force it into a consistent state
+ * bdev_freeze - lock a filesystem and force it into a consistent state
  * @bdev:	blockdevice to lock
  *
  * If a superblock is found on this device, we take the s_umount semaphore
  * on it to make sure nobody unmounts until the snapshot creation is done.
  * The reference counter (bd_fsfreeze_count) guarantees that only the last
  * unfreeze process can unfreeze the frozen filesystem actually when multiple
- * freeze requests arrive simultaneously. It counts up in freeze_bdev() and
- * count down in thaw_bdev(). When it becomes 0, thaw_bdev() will unfreeze
+ * freeze requests arrive simultaneously. It counts up in bdev_freeze() and
+ * count down in bdev_thaw(). When it becomes 0, thaw_bdev() will unfreeze
  * actually.
+ *
+ * Return: On success zero is returned, negative error code on failure.
  */
-int freeze_bdev(struct block_device *bdev)
+int bdev_freeze(struct block_device *bdev)
 {
-	struct super_block *sb;
 	int error = 0;
 
 	mutex_lock(&bdev->bd_fsfreeze_mutex);
-	if (++bdev->bd_fsfreeze_count > 1)
-		goto done;
-
-	sb = get_active_super(bdev);
-	if (!sb)
-		goto sync;
-	if (sb->s_op->freeze_super)
-		error = sb->s_op->freeze_super(sb, FREEZE_HOLDER_USERSPACE);
-	else
-		error = freeze_super(sb, FREEZE_HOLDER_USERSPACE);
-	deactivate_super(sb);
 
-	if (error) {
-		bdev->bd_fsfreeze_count--;
-		goto done;
+	if (atomic_inc_return(&bdev->bd_fsfreeze_count) > 1) {
+		mutex_unlock(&bdev->bd_fsfreeze_mutex);
+		return 0;
 	}
-	bdev->bd_fsfreeze_sb = sb;
 
-sync:
-	sync_blockdev(bdev);
-done:
+	mutex_lock(&bdev->bd_holder_lock);
+	if (bdev->bd_holder_ops && bdev->bd_holder_ops->freeze) {
+		error = bdev->bd_holder_ops->freeze(bdev);
+		lockdep_assert_not_held(&bdev->bd_holder_lock);
+	} else {
+		mutex_unlock(&bdev->bd_holder_lock);
+		error = sync_blockdev(bdev);
+	}
+
+	if (error)
+		atomic_dec(&bdev->bd_fsfreeze_count);
+
 	mutex_unlock(&bdev->bd_fsfreeze_mutex);
 	return error;
 }
-EXPORT_SYMBOL(freeze_bdev);
+EXPORT_SYMBOL(bdev_freeze);
 
 /**
- * thaw_bdev - unlock filesystem
+ * bdev_thaw - unlock filesystem
  * @bdev:	blockdevice to unlock
  *
- * Unlocks the filesystem and marks it writeable again after freeze_bdev().
+ * Unlocks the filesystem and marks it writeable again after bdev_freeze().
+ *
+ * Return: On success zero is returned, negative error code on failure.
  */
-int thaw_bdev(struct block_device *bdev)
+int bdev_thaw(struct block_device *bdev)
 {
-	struct super_block *sb;
-	int error = -EINVAL;
+	int error = -EINVAL, nr_freeze;
 
 	mutex_lock(&bdev->bd_fsfreeze_mutex);
-	if (!bdev->bd_fsfreeze_count)
+
+	/*
+	 * If this returns < 0 it means that @bd_fsfreeze_count was
+	 * already 0 and no decrement was performed.
+	 */
+	nr_freeze = atomic_dec_if_positive(&bdev->bd_fsfreeze_count);
+	if (nr_freeze < 0)
 		goto out;
 
 	error = 0;
-	if (--bdev->bd_fsfreeze_count > 0)
+	if (nr_freeze > 0)
 		goto out;
 
-	sb = bdev->bd_fsfreeze_sb;
-	if (!sb)
-		goto out;
+	mutex_lock(&bdev->bd_holder_lock);
+	if (bdev->bd_holder_ops && bdev->bd_holder_ops->thaw) {
+		error = bdev->bd_holder_ops->thaw(bdev);
+		lockdep_assert_not_held(&bdev->bd_holder_lock);
+	} else {
+		mutex_unlock(&bdev->bd_holder_lock);
+	}
 
-	if (sb->s_op->thaw_super)
-		error = sb->s_op->thaw_super(sb, FREEZE_HOLDER_USERSPACE);
-	else
-		error = thaw_super(sb, FREEZE_HOLDER_USERSPACE);
 	if (error)
-		bdev->bd_fsfreeze_count++;
-	else
-		bdev->bd_fsfreeze_sb = NULL;
+		atomic_inc(&bdev->bd_fsfreeze_count);
 out:
 	mutex_unlock(&bdev->bd_fsfreeze_mutex);
 	return error;
 }
-EXPORT_SYMBOL(thaw_bdev);
+EXPORT_SYMBOL(bdev_thaw);
 
 /*
  * pseudo-fs
@@ -425,6 +431,8 @@ void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors)
 
 void bdev_add(struct block_device *bdev, dev_t dev)
 {
+	if (bdev_stable_writes(bdev))
+		mapping_set_stable_writes(bdev->bd_inode->i_mapping);
 	bdev->bd_dev = dev;
 	bdev->bd_inode->i_rdev = dev;
 	bdev->bd_inode->i_ino = dev;
@@ -727,9 +735,60 @@ void blkdev_put_no_open(struct block_device *bdev)
 {
 	put_device(&bdev->bd_device);
 }
-	
+
+static bool bdev_writes_blocked(struct block_device *bdev)
+{
+	return bdev->bd_writers == -1;
+}
+
+static void bdev_block_writes(struct block_device *bdev)
+{
+	bdev->bd_writers = -1;
+}
+
+static void bdev_unblock_writes(struct block_device *bdev)
+{
+	bdev->bd_writers = 0;
+}
+
+static bool bdev_may_open(struct block_device *bdev, blk_mode_t mode)
+{
+	if (bdev_allow_write_mounted)
+		return true;
+	/* Writes blocked? */
+	if (mode & BLK_OPEN_WRITE && bdev_writes_blocked(bdev))
+		return false;
+	if (mode & BLK_OPEN_RESTRICT_WRITES && bdev->bd_writers > 0)
+		return false;
+	return true;
+}
+
+static void bdev_claim_write_access(struct block_device *bdev, blk_mode_t mode)
+{
+	if (bdev_allow_write_mounted)
+		return;
+
+	/* Claim exclusive or shared write access. */
+	if (mode & BLK_OPEN_RESTRICT_WRITES)
+		bdev_block_writes(bdev);
+	else if (mode & BLK_OPEN_WRITE)
+		bdev->bd_writers++;
+}
+
+static void bdev_yield_write_access(struct block_device *bdev, blk_mode_t mode)
+{
+	if (bdev_allow_write_mounted)
+		return;
+
+	/* Yield exclusive or shared write access. */
+	if (mode & BLK_OPEN_RESTRICT_WRITES)
+		bdev_unblock_writes(bdev);
+	else if (mode & BLK_OPEN_WRITE)
+		bdev->bd_writers--;
+}
+
 /**
- * blkdev_get_by_dev - open a block device by device number
+ * bdev_open_by_dev - open a block device by device number
  * @dev: device number of block device to open
  * @mode: open mode (BLK_OPEN_*)
  * @holder: exclusive holder identifier
@@ -741,32 +800,46 @@ void blkdev_put_no_open(struct block_device *bdev)
  *
  * Use this interface ONLY if you really do not have anything better - i.e. when
  * you are behind a truly sucky interface and all you are given is a device
- * number.  Everything else should use blkdev_get_by_path().
+ * number.  Everything else should use bdev_open_by_path().
  *
  * CONTEXT:
  * Might sleep.
  *
  * RETURNS:
- * Reference to the block_device on success, ERR_PTR(-errno) on failure.
+ * Handle with a reference to the block_device on success, ERR_PTR(-errno) on
+ * failure.
  */
-struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder,
-		const struct blk_holder_ops *hops)
+struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
+				     const struct blk_holder_ops *hops)
 {
-	bool unblock_events = true;
+	struct bdev_handle *handle = kmalloc(sizeof(struct bdev_handle),
+					     GFP_KERNEL);
 	struct block_device *bdev;
+	bool unblock_events = true;
 	struct gendisk *disk;
 	int ret;
 
+	if (!handle)
+		return ERR_PTR(-ENOMEM);
+
 	ret = devcgroup_check_permission(DEVCG_DEV_BLOCK,
 			MAJOR(dev), MINOR(dev),
 			((mode & BLK_OPEN_READ) ? DEVCG_ACC_READ : 0) |
 			((mode & BLK_OPEN_WRITE) ? DEVCG_ACC_WRITE : 0));
 	if (ret)
-		return ERR_PTR(ret);
+		goto free_handle;
+
+	/* Blocking writes requires exclusive opener */
+	if (mode & BLK_OPEN_RESTRICT_WRITES && !holder) {
+		ret = -EINVAL;
+		goto free_handle;
+	}
 
 	bdev = blkdev_get_no_open(dev);
-	if (!bdev)
-		return ERR_PTR(-ENXIO);
+	if (!bdev) {
+		ret = -ENXIO;
+		goto free_handle;
+	}
 	disk = bdev->bd_disk;
 
 	if (holder) {
@@ -789,12 +862,16 @@ struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder,
 		goto abort_claiming;
 	if (!try_module_get(disk->fops->owner))
 		goto abort_claiming;
+	ret = -EBUSY;
+	if (!bdev_may_open(bdev, mode))
+		goto abort_claiming;
 	if (bdev_is_partition(bdev))
 		ret = blkdev_get_part(bdev, mode);
 	else
 		ret = blkdev_get_whole(bdev, mode);
 	if (ret)
 		goto put_module;
+	bdev_claim_write_access(bdev, mode);
 	if (holder) {
 		bd_finish_claiming(bdev, holder, hops);
 
@@ -815,7 +892,10 @@ struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder,
 
 	if (unblock_events)
 		disk_unblock_events(disk);
-	return bdev;
+	handle->bdev = bdev;
+	handle->holder = holder;
+	handle->mode = mode;
+	return handle;
 put_module:
 	module_put(disk->fops->owner);
 abort_claiming:
@@ -825,34 +905,14 @@ abort_claiming:
 	disk_unblock_events(disk);
 put_blkdev:
 	blkdev_put_no_open(bdev);
+free_handle:
+	kfree(handle);
 	return ERR_PTR(ret);
 }
-EXPORT_SYMBOL(blkdev_get_by_dev);
-
-struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
-				     const struct blk_holder_ops *hops)
-{
-	struct bdev_handle *handle = kmalloc(sizeof(*handle), GFP_KERNEL);
-	struct block_device *bdev;
-
-	if (!handle)
-		return ERR_PTR(-ENOMEM);
-	bdev = blkdev_get_by_dev(dev, mode, holder, hops);
-	if (IS_ERR(bdev)) {
-		kfree(handle);
-		return ERR_CAST(bdev);
-	}
-	handle->bdev = bdev;
-	handle->holder = holder;
-	if (holder)
-		mode |= BLK_OPEN_EXCL;
-	handle->mode = mode;
-	return handle;
-}
 EXPORT_SYMBOL(bdev_open_by_dev);
 
 /**
- * blkdev_get_by_path - open a block device by name
+ * bdev_open_by_path - open a block device by name
  * @path: path to the block device to open
  * @mode: open mode (BLK_OPEN_*)
  * @holder: exclusive holder identifier
@@ -866,29 +926,9 @@ EXPORT_SYMBOL(bdev_open_by_dev);
  * Might sleep.
  *
  * RETURNS:
- * Reference to the block_device on success, ERR_PTR(-errno) on failure.
+ * Handle with a reference to the block_device on success, ERR_PTR(-errno) on
+ * failure.
  */
-struct block_device *blkdev_get_by_path(const char *path, blk_mode_t mode,
-		void *holder, const struct blk_holder_ops *hops)
-{
-	struct block_device *bdev;
-	dev_t dev;
-	int error;
-
-	error = lookup_bdev(path, &dev);
-	if (error)
-		return ERR_PTR(error);
-
-	bdev = blkdev_get_by_dev(dev, mode, holder, hops);
-	if (!IS_ERR(bdev) && (mode & BLK_OPEN_WRITE) && bdev_read_only(bdev)) {
-		blkdev_put(bdev, holder);
-		return ERR_PTR(-EACCES);
-	}
-
-	return bdev;
-}
-EXPORT_SYMBOL(blkdev_get_by_path);
-
 struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode,
 		void *holder, const struct blk_holder_ops *hops)
 {
@@ -911,8 +951,9 @@ struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode,
 }
 EXPORT_SYMBOL(bdev_open_by_path);
 
-void blkdev_put(struct block_device *bdev, void *holder)
+void bdev_release(struct bdev_handle *handle)
 {
+	struct block_device *bdev = handle->bdev;
 	struct gendisk *disk = bdev->bd_disk;
 
 	/*
@@ -926,8 +967,10 @@ void blkdev_put(struct block_device *bdev, void *holder)
 		sync_blockdev(bdev);
 
 	mutex_lock(&disk->open_mutex);
-	if (holder)
-		bd_end_claim(bdev, holder);
+	bdev_yield_write_access(bdev, handle->mode);
+
+	if (handle->holder)
+		bd_end_claim(bdev, handle->holder);
 
 	/*
 	 * Trigger event checking and tell drivers to flush MEDIA_CHANGE
@@ -944,12 +987,6 @@ void blkdev_put(struct block_device *bdev, void *holder)
 
 	module_put(disk->fops->owner);
 	blkdev_put_no_open(bdev);
-}
-EXPORT_SYMBOL(blkdev_put);
-
-void bdev_release(struct bdev_handle *handle)
-{
-	blkdev_put(handle->bdev, handle->holder);
 	kfree(handle);
 }
 EXPORT_SYMBOL(bdev_release);
@@ -1100,3 +1137,12 @@ void bdev_statx_dioalign(struct inode *inode, struct kstat *stat)
 
 	blkdev_put_no_open(bdev);
 }
+
+static int __init setup_bdev_allow_write_mounted(char *str)
+{
+	if (kstrtobool(str, &bdev_allow_write_mounted))
+		pr_warn("Invalid option string for bdev_allow_write_mounted:"
+			" '%s'\n", str);
+	return 1;
+}
+__setup("bdev_allow_write_mounted=", setup_bdev_allow_write_mounted);
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index ec8ac8cf6e1b..feef615e2c9c 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -69,15 +69,15 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 
 	memset(bip, 0, sizeof(*bip));
 
+	/* always report as many vecs as asked explicitly, not inline vecs */
+	bip->bip_max_vcnt = nr_vecs;
 	if (nr_vecs > inline_vecs) {
-		bip->bip_max_vcnt = nr_vecs;
 		bip->bip_vec = bvec_alloc(&bs->bvec_integrity_pool,
 					  &bip->bip_max_vcnt, gfp_mask);
 		if (!bip->bip_vec)
 			goto err;
 	} else {
 		bip->bip_vec = bip->bip_inline_vecs;
-		bip->bip_max_vcnt = inline_vecs;
 	}
 
 	bip->bip_bio = bio;
@@ -91,6 +91,47 @@ err:
 }
 EXPORT_SYMBOL(bio_integrity_alloc);
 
+static void bio_integrity_unpin_bvec(struct bio_vec *bv, int nr_vecs,
+				     bool dirty)
+{
+	int i;
+
+	for (i = 0; i < nr_vecs; i++) {
+		if (dirty && !PageCompound(bv[i].bv_page))
+			set_page_dirty_lock(bv[i].bv_page);
+		unpin_user_page(bv[i].bv_page);
+	}
+}
+
+static void bio_integrity_uncopy_user(struct bio_integrity_payload *bip)
+{
+	unsigned short nr_vecs = bip->bip_max_vcnt - 1;
+	struct bio_vec *copy = &bip->bip_vec[1];
+	size_t bytes = bip->bip_iter.bi_size;
+	struct iov_iter iter;
+	int ret;
+
+	iov_iter_bvec(&iter, ITER_DEST, copy, nr_vecs, bytes);
+	ret = copy_to_iter(bvec_virt(bip->bip_vec), bytes, &iter);
+	WARN_ON_ONCE(ret != bytes);
+
+	bio_integrity_unpin_bvec(copy, nr_vecs, true);
+}
+
+static void bio_integrity_unmap_user(struct bio_integrity_payload *bip)
+{
+	bool dirty = bio_data_dir(bip->bip_bio) == READ;
+
+	if (bip->bip_flags & BIP_COPY_USER) {
+		if (dirty)
+			bio_integrity_uncopy_user(bip);
+		kfree(bvec_virt(bip->bip_vec));
+		return;
+	}
+
+	bio_integrity_unpin_bvec(bip->bip_vec, bip->bip_max_vcnt, dirty);
+}
+
 /**
  * bio_integrity_free - Free bio integrity payload
  * @bio:	bio containing bip to be freed
@@ -105,6 +146,8 @@ void bio_integrity_free(struct bio *bio)
 
 	if (bip->bip_flags & BIP_BLOCK_INTEGRITY)
 		kfree(bvec_virt(bip->bip_vec));
+	else if (bip->bip_flags & BIP_INTEGRITY_USER)
+		bio_integrity_unmap_user(bip);
 
 	__bio_integrity_free(bs, bip);
 	bio->bi_integrity = NULL;
@@ -160,6 +203,177 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 }
 EXPORT_SYMBOL(bio_integrity_add_page);
 
+static int bio_integrity_copy_user(struct bio *bio, struct bio_vec *bvec,
+				   int nr_vecs, unsigned int len,
+				   unsigned int direction, u32 seed)
+{
+	bool write = direction == ITER_SOURCE;
+	struct bio_integrity_payload *bip;
+	struct iov_iter iter;
+	void *buf;
+	int ret;
+
+	buf = kmalloc(len, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	if (write) {
+		iov_iter_bvec(&iter, direction, bvec, nr_vecs, len);
+		if (!copy_from_iter_full(buf, len, &iter)) {
+			ret = -EFAULT;
+			goto free_buf;
+		}
+
+		bip = bio_integrity_alloc(bio, GFP_KERNEL, 1);
+	} else {
+		memset(buf, 0, len);
+
+		/*
+		 * We need to preserve the original bvec and the number of vecs
+		 * in it for completion handling
+		 */
+		bip = bio_integrity_alloc(bio, GFP_KERNEL, nr_vecs + 1);
+	}
+
+	if (IS_ERR(bip)) {
+		ret = PTR_ERR(bip);
+		goto free_buf;
+	}
+
+	if (write)
+		bio_integrity_unpin_bvec(bvec, nr_vecs, false);
+	else
+		memcpy(&bip->bip_vec[1], bvec, nr_vecs * sizeof(*bvec));
+
+	ret = bio_integrity_add_page(bio, virt_to_page(buf), len,
+				     offset_in_page(buf));
+	if (ret != len) {
+		ret = -ENOMEM;
+		goto free_bip;
+	}
+
+	bip->bip_flags |= BIP_INTEGRITY_USER | BIP_COPY_USER;
+	bip->bip_iter.bi_sector = seed;
+	return 0;
+free_bip:
+	bio_integrity_free(bio);
+free_buf:
+	kfree(buf);
+	return ret;
+}
+
+static int bio_integrity_init_user(struct bio *bio, struct bio_vec *bvec,
+				   int nr_vecs, unsigned int len, u32 seed)
+{
+	struct bio_integrity_payload *bip;
+
+	bip = bio_integrity_alloc(bio, GFP_KERNEL, nr_vecs);
+	if (IS_ERR(bip))
+		return PTR_ERR(bip);
+
+	memcpy(bip->bip_vec, bvec, nr_vecs * sizeof(*bvec));
+	bip->bip_flags |= BIP_INTEGRITY_USER;
+	bip->bip_iter.bi_sector = seed;
+	bip->bip_iter.bi_size = len;
+	return 0;
+}
+
+static unsigned int bvec_from_pages(struct bio_vec *bvec, struct page **pages,
+				    int nr_vecs, ssize_t bytes, ssize_t offset)
+{
+	unsigned int nr_bvecs = 0;
+	int i, j;
+
+	for (i = 0; i < nr_vecs; i = j) {
+		size_t size = min_t(size_t, bytes, PAGE_SIZE - offset);
+		struct folio *folio = page_folio(pages[i]);
+
+		bytes -= size;
+		for (j = i + 1; j < nr_vecs; j++) {
+			size_t next = min_t(size_t, PAGE_SIZE, bytes);
+
+			if (page_folio(pages[j]) != folio ||
+			    pages[j] != pages[j - 1] + 1)
+				break;
+			unpin_user_page(pages[j]);
+			size += next;
+			bytes -= next;
+		}
+
+		bvec_set_page(&bvec[nr_bvecs], pages[i], size, offset);
+		offset = 0;
+		nr_bvecs++;
+	}
+
+	return nr_bvecs;
+}
+
+int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes,
+			   u32 seed)
+{
+	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
+	unsigned int align = q->dma_pad_mask | queue_dma_alignment(q);
+	struct page *stack_pages[UIO_FASTIOV], **pages = stack_pages;
+	struct bio_vec stack_vec[UIO_FASTIOV], *bvec = stack_vec;
+	unsigned int direction, nr_bvecs;
+	struct iov_iter iter;
+	int ret, nr_vecs;
+	size_t offset;
+	bool copy;
+
+	if (bio_integrity(bio))
+		return -EINVAL;
+	if (bytes >> SECTOR_SHIFT > queue_max_hw_sectors(q))
+		return -E2BIG;
+
+	if (bio_data_dir(bio) == READ)
+		direction = ITER_DEST;
+	else
+		direction = ITER_SOURCE;
+
+	iov_iter_ubuf(&iter, direction, ubuf, bytes);
+	nr_vecs = iov_iter_npages(&iter, BIO_MAX_VECS + 1);
+	if (nr_vecs > BIO_MAX_VECS)
+		return -E2BIG;
+	if (nr_vecs > UIO_FASTIOV) {
+		bvec = kcalloc(sizeof(*bvec), nr_vecs, GFP_KERNEL);
+		if (!bvec)
+			return -ENOMEM;
+		pages = NULL;
+	}
+
+	copy = !iov_iter_is_aligned(&iter, align, align);
+	ret = iov_iter_extract_pages(&iter, &pages, bytes, nr_vecs, 0, &offset);
+	if (unlikely(ret < 0))
+		goto free_bvec;
+
+	nr_bvecs = bvec_from_pages(bvec, pages, nr_vecs, bytes, offset);
+	if (pages != stack_pages)
+		kvfree(pages);
+	if (nr_bvecs > queue_max_integrity_segments(q))
+		copy = true;
+
+	if (copy)
+		ret = bio_integrity_copy_user(bio, bvec, nr_bvecs, bytes,
+					      direction, seed);
+	else
+		ret = bio_integrity_init_user(bio, bvec, nr_bvecs, bytes, seed);
+	if (ret)
+		goto release_pages;
+	if (bvec != stack_vec)
+		kfree(bvec);
+
+	return 0;
+
+release_pages:
+	bio_integrity_unpin_bvec(bvec, nr_bvecs, false);
+free_bvec:
+	if (bvec != stack_vec)
+		kfree(bvec);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(bio_integrity_map_user);
+
 /**
  * bio_integrity_process - Process integrity metadata for a bio
  * @bio:	bio to generate/verify integrity metadata for
diff --git a/block/bio.c b/block/bio.c
index 816d412c06e9..b9642a41f286 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -944,7 +944,7 @@ bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv,
 
 	if ((addr1 | mask) != (addr2 | mask))
 		return false;
-	if (bv->bv_len + len > queue_max_segment_size(q))
+	if (len > queue_max_segment_size(q) - bv->bv_len)
 		return false;
 	return bvec_try_merge_page(bv, page, len, offset, same_page);
 }
@@ -966,10 +966,13 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio,
 		struct page *page, unsigned int len, unsigned int offset,
 		unsigned int max_sectors, bool *same_page)
 {
+	unsigned int max_size = max_sectors << SECTOR_SHIFT;
+
 	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
 		return 0;
 
-	if (((bio->bi_iter.bi_size + len) >> SECTOR_SHIFT) > max_sectors)
+	len = min3(len, max_size, queue_max_segment_size(q));
+	if (len > max_size - bio->bi_iter.bi_size)
 		return 0;
 
 	if (bio->bi_vcnt > 0) {
@@ -1145,13 +1148,22 @@ EXPORT_SYMBOL(bio_add_folio);
 
 void __bio_release_pages(struct bio *bio, bool mark_dirty)
 {
-	struct bvec_iter_all iter_all;
-	struct bio_vec *bvec;
+	struct folio_iter fi;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		if (mark_dirty && !PageCompound(bvec->bv_page))
-			set_page_dirty_lock(bvec->bv_page);
-		bio_release_page(bio, bvec->bv_page);
+	bio_for_each_folio_all(fi, bio) {
+		struct page *page;
+		size_t done = 0;
+
+		if (mark_dirty) {
+			folio_lock(fi.folio);
+			folio_mark_dirty(fi.folio);
+			folio_unlock(fi.folio);
+		}
+		page = folio_page(fi.folio, fi.offset / PAGE_SIZE);
+		do {
+			bio_release_page(bio, page++);
+			done += PAGE_SIZE;
+		} while (done < fi.length);
 	}
 }
 EXPORT_SYMBOL_GPL(__bio_release_pages);
@@ -1439,18 +1451,12 @@ EXPORT_SYMBOL(bio_free_pages);
  * bio_set_pages_dirty() and bio_check_pages_dirty() are support functions
  * for performing direct-IO in BIOs.
  *
- * The problem is that we cannot run set_page_dirty() from interrupt context
+ * The problem is that we cannot run folio_mark_dirty() from interrupt context
  * because the required locks are not interrupt-safe.  So what we can do is to
  * mark the pages dirty _before_ performing IO.  And in interrupt context,
  * check that the pages are still dirty.   If so, fine.  If not, redirty them
  * in process context.
  *
- * We special-case compound pages here: normally this means reads into hugetlb
- * pages.  The logic in here doesn't really work right for compound pages
- * because the VM does not uniformly chase down the head page in all cases.
- * But dirtiness of compound pages is pretty meaningless anyway: the VM doesn't
- * handle them at all.  So we skip compound pages here at an early stage.
- *
  * Note that this code is very hard to test under normal circumstances because
  * direct-io pins the pages with get_user_pages().  This makes
  * is_page_cache_freeable return false, and the VM will not clean the pages.
@@ -1466,12 +1472,12 @@ EXPORT_SYMBOL(bio_free_pages);
  */
 void bio_set_pages_dirty(struct bio *bio)
 {
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
+	struct folio_iter fi;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		if (!PageCompound(bvec->bv_page))
-			set_page_dirty_lock(bvec->bv_page);
+	bio_for_each_folio_all(fi, bio) {
+		folio_lock(fi.folio);
+		folio_mark_dirty(fi.folio);
+		folio_unlock(fi.folio);
 	}
 }
 EXPORT_SYMBOL_GPL(bio_set_pages_dirty);
@@ -1515,12 +1521,11 @@ static void bio_dirty_fn(struct work_struct *work)
 
 void bio_check_pages_dirty(struct bio *bio)
 {
-	struct bio_vec *bvec;
+	struct folio_iter fi;
 	unsigned long flags;
-	struct bvec_iter_all iter_all;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		if (!PageDirty(bvec->bv_page) && !PageCompound(bvec->bv_page))
+	bio_for_each_folio_all(fi, bio) {
+		if (!folio_test_dirty(fi.folio))
 			goto defer;
 	}
 
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 4a42ea2972ad..e303fd317313 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -575,12 +575,13 @@ static void blkg_destroy(struct blkcg_gq *blkg)
 static void blkg_destroy_all(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
-	struct blkcg_gq *blkg, *n;
+	struct blkcg_gq *blkg;
 	int count = BLKG_DESTROY_BATCH_SIZE;
+	int i;
 
 restart:
 	spin_lock_irq(&q->queue_lock);
-	list_for_each_entry_safe(blkg, n, &q->blkg_list, q_node) {
+	list_for_each_entry(blkg, &q->blkg_list, q_node) {
 		struct blkcg *blkcg = blkg->blkcg;
 
 		if (hlist_unhashed(&blkg->blkcg_node))
@@ -602,6 +603,18 @@ restart:
 		}
 	}
 
+	/*
+	 * Mark policy deactivated since policy offline has been done, and
+	 * the free is scheduled, so future blkcg_deactivate_policy() can
+	 * be bypassed
+	 */
+	for (i = 0; i < BLKCG_MAX_POLS; i++) {
+		struct blkcg_policy *pol = blkcg_policy[i];
+
+		if (pol)
+			__clear_bit(pol->plid, q->blkcg_pols);
+	}
+
 	q->root_blkg = NULL;
 	spin_unlock_irq(&q->queue_lock);
 }
@@ -2051,6 +2064,9 @@ void bio_associate_blkg(struct bio *bio)
 {
 	struct cgroup_subsys_state *css;
 
+	if (blk_op_is_passthrough(bio->bi_opf))
+		return;
+
 	rcu_read_lock();
 
 	if (bio->bi_blkg)
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 624c03c8fe64..b927a4a0ad03 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -249,12 +249,11 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg,
 {
 	struct blkcg_gq *blkg;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
-
 	if (blkcg == &blkcg_root)
 		return q->root_blkg;
 
-	blkg = rcu_dereference(blkcg->blkg_hint);
+	blkg = rcu_dereference_check(blkcg->blkg_hint,
+			lockdep_is_held(&q->queue_lock));
 	if (blkg && blkg->q == q)
 		return blkg;
 
diff --git a/block/blk-core.c b/block/blk-core.c
index fdf25b8d6e78..11342af420d0 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -501,9 +501,17 @@ static inline void bio_check_ro(struct bio *bio)
 	if (op_is_write(bio_op(bio)) && bdev_read_only(bio->bi_bdev)) {
 		if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
 			return;
-		pr_warn_ratelimited("Trying to write to read-only block-device %pg\n",
-				    bio->bi_bdev);
-		/* Older lvm-tools actually trigger this */
+
+		if (bio->bi_bdev->bd_ro_warned)
+			return;
+
+		bio->bi_bdev->bd_ro_warned = true;
+		/*
+		 * Use ioctl to set underlying disk of raid/dm to read-only
+		 * will trigger this.
+		 */
+		pr_warn("Trying to write to read-only block-device %pg\n",
+			bio->bi_bdev);
 	}
 }
 
@@ -764,6 +772,15 @@ void submit_bio_noacct(struct bio *bio)
 		bio_clear_polled(bio);
 
 	switch (bio_op(bio)) {
+	case REQ_OP_READ:
+	case REQ_OP_WRITE:
+		break;
+	case REQ_OP_FLUSH:
+		/*
+		 * REQ_OP_FLUSH can't be submitted through bios, it is only
+		 * synthetized in struct request by the flush state machine.
+		 */
+		goto not_supported;
 	case REQ_OP_DISCARD:
 		if (!bdev_max_discard_sectors(bdev))
 			goto not_supported;
@@ -777,6 +794,10 @@ void submit_bio_noacct(struct bio *bio)
 		if (status != BLK_STS_OK)
 			goto end_io;
 		break;
+	case REQ_OP_WRITE_ZEROES:
+		if (!q->limits.max_write_zeroes_sectors)
+			goto not_supported;
+		break;
 	case REQ_OP_ZONE_RESET:
 	case REQ_OP_ZONE_OPEN:
 	case REQ_OP_ZONE_CLOSE:
@@ -788,12 +809,15 @@ void submit_bio_noacct(struct bio *bio)
 		if (!bdev_is_zoned(bio->bi_bdev) || !blk_queue_zone_resetall(q))
 			goto not_supported;
 		break;
-	case REQ_OP_WRITE_ZEROES:
-		if (!q->limits.max_write_zeroes_sectors)
-			goto not_supported;
-		break;
+	case REQ_OP_DRV_IN:
+	case REQ_OP_DRV_OUT:
+		/*
+		 * Driver private operations are only used with passthrough
+		 * requests.
+		 */
+		fallthrough;
 	default:
-		break;
+		goto not_supported;
 	}
 
 	if (blk_throtl_bio(bio))
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 65e75efa9bd3..2d470cf2173e 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -115,17 +115,13 @@ static struct bio *bio_split_discard(struct bio *bio,
 
 	*nsegs = 1;
 
-	/* Zero-sector (unknown) and one-sector granularities are the same.  */
 	granularity = max(lim->discard_granularity >> 9, 1U);
 
 	max_discard_sectors =
 		min(lim->max_discard_sectors, bio_allowed_max_sectors(lim));
 	max_discard_sectors -= max_discard_sectors % granularity;
-
-	if (unlikely(!max_discard_sectors)) {
-		/* XXX: warn */
+	if (unlikely(!max_discard_sectors))
 		return NULL;
-	}
 
 	if (bio_sectors(bio) <= max_discard_sectors)
 		return NULL;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index e2d11183f62e..c11c97afa0bc 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1248,7 +1248,8 @@ void blk_mq_start_request(struct request *rq)
 
 	trace_block_rq_issue(rq);
 
-	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
+	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags) &&
+	    !blk_rq_is_passthrough(rq)) {
 		rq->io_start_time_ns = ktime_get_ns();
 		rq->stats_sectors = blk_rq_sectors(rq);
 		rq->rq_flags |= RQF_STATS;
@@ -1512,14 +1513,26 @@ void blk_mq_delay_kick_requeue_list(struct request_queue *q,
 }
 EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list);
 
+static bool blk_is_flush_data_rq(struct request *rq)
+{
+	return (rq->rq_flags & RQF_FLUSH_SEQ) && !is_flush_rq(rq);
+}
+
 static bool blk_mq_rq_inflight(struct request *rq, void *priv)
 {
 	/*
 	 * If we find a request that isn't idle we know the queue is busy
 	 * as it's checked in the iter.
 	 * Return false to stop the iteration.
+	 *
+	 * In case of queue quiesce, if one flush data request is completed,
+	 * don't count it as inflight given the flush sequence is suspended,
+	 * and the original flush data request is invisible to driver, just
+	 * like other pending requests because of quiesce
 	 */
-	if (blk_mq_request_started(rq)) {
+	if (blk_mq_request_started(rq) && !(blk_queue_quiesced(rq->q) &&
+				blk_is_flush_data_rq(rq) &&
+				blk_mq_request_completed(rq))) {
 		bool *busy = priv;
 
 		*busy = true;
@@ -2858,11 +2871,8 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q,
 	};
 	struct request *rq;
 
-	if (unlikely(bio_queue_enter(bio)))
-		return NULL;
-
 	if (blk_mq_attempt_bio_merge(q, bio, nsegs))
-		goto queue_exit;
+		return NULL;
 
 	rq_qos_throttle(q, bio);
 
@@ -2878,35 +2888,23 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q,
 	rq_qos_cleanup(q, bio);
 	if (bio->bi_opf & REQ_NOWAIT)
 		bio_wouldblock_error(bio);
-queue_exit:
-	blk_queue_exit(q);
 	return NULL;
 }
 
-static inline struct request *blk_mq_get_cached_request(struct request_queue *q,
-		struct blk_plug *plug, struct bio **bio, unsigned int nsegs)
+/* return true if this @rq can be used for @bio */
+static bool blk_mq_can_use_cached_rq(struct request *rq, struct blk_plug *plug,
+		struct bio *bio)
 {
-	struct request *rq;
-	enum hctx_type type, hctx_type;
+	enum hctx_type type = blk_mq_get_hctx_type(bio->bi_opf);
+	enum hctx_type hctx_type = rq->mq_hctx->type;
 
-	if (!plug)
-		return NULL;
-	rq = rq_list_peek(&plug->cached_rq);
-	if (!rq || rq->q != q)
-		return NULL;
-
-	if (blk_mq_attempt_bio_merge(q, *bio, nsegs)) {
-		*bio = NULL;
-		return NULL;
-	}
+	WARN_ON_ONCE(rq_list_peek(&plug->cached_rq) != rq);
 
-	type = blk_mq_get_hctx_type((*bio)->bi_opf);
-	hctx_type = rq->mq_hctx->type;
 	if (type != hctx_type &&
 	    !(type == HCTX_TYPE_READ && hctx_type == HCTX_TYPE_DEFAULT))
-		return NULL;
-	if (op_is_flush(rq->cmd_flags) != op_is_flush((*bio)->bi_opf))
-		return NULL;
+		return false;
+	if (op_is_flush(rq->cmd_flags) != op_is_flush(bio->bi_opf))
+		return false;
 
 	/*
 	 * If any qos ->throttle() end up blocking, we will have flushed the
@@ -2914,12 +2912,12 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q,
 	 * before we throttle.
 	 */
 	plug->cached_rq = rq_list_next(rq);
-	rq_qos_throttle(q, *bio);
+	rq_qos_throttle(rq->q, bio);
 
 	blk_mq_rq_time_init(rq, 0);
-	rq->cmd_flags = (*bio)->bi_opf;
+	rq->cmd_flags = bio->bi_opf;
 	INIT_LIST_HEAD(&rq->queuelist);
-	return rq;
+	return true;
 }
 
 static void bio_set_ioprio(struct bio *bio)
@@ -2949,7 +2947,7 @@ void blk_mq_submit_bio(struct bio *bio)
 	struct blk_plug *plug = blk_mq_plug(bio);
 	const int is_sync = op_is_sync(bio->bi_opf);
 	struct blk_mq_hw_ctx *hctx;
-	struct request *rq;
+	struct request *rq = NULL;
 	unsigned int nr_segs = 1;
 	blk_status_t ret;
 
@@ -2960,20 +2958,36 @@ void blk_mq_submit_bio(struct bio *bio)
 			return;
 	}
 
-	if (!bio_integrity_prep(bio))
-		return;
-
 	bio_set_ioprio(bio);
 
-	rq = blk_mq_get_cached_request(q, plug, &bio, nr_segs);
-	if (!rq) {
-		if (!bio)
+	if (plug) {
+		rq = rq_list_peek(&plug->cached_rq);
+		if (rq && rq->q != q)
+			rq = NULL;
+	}
+	if (rq) {
+		if (!bio_integrity_prep(bio))
 			return;
-		rq = blk_mq_get_new_requests(q, plug, bio, nr_segs);
-		if (unlikely(!rq))
+		if (blk_mq_attempt_bio_merge(q, bio, nr_segs))
 			return;
+		if (blk_mq_can_use_cached_rq(rq, plug, bio))
+			goto done;
+		percpu_ref_get(&q->q_usage_counter);
+	} else {
+		if (unlikely(bio_queue_enter(bio)))
+			return;
+		if (!bio_integrity_prep(bio))
+			goto fail;
 	}
 
+	rq = blk_mq_get_new_requests(q, plug, bio, nr_segs);
+	if (unlikely(!rq)) {
+fail:
+		blk_queue_exit(q);
+		return;
+	}
+
+done:
 	trace_block_getrq(bio);
 
 	rq_qos_track(q, rq, bio);
diff --git a/block/blk-pm.c b/block/blk-pm.c
index 6b72b2e03fc8..42e842074715 100644
--- a/block/blk-pm.c
+++ b/block/blk-pm.c
@@ -163,39 +163,16 @@ EXPORT_SYMBOL(blk_pre_runtime_resume);
  * @q: the queue of the device
  *
  * Description:
- *    For historical reasons, this routine merely calls blk_set_runtime_active()
- *    to do the real work of restarting the queue.  It does this regardless of
- *    whether the device's runtime-resume succeeded; even if it failed the
+ *    Restart the queue of a runtime suspended device. It does this regardless
+ *    of whether the device's runtime-resume succeeded; even if it failed the
  *    driver or error handler will need to communicate with the device.
  *
  *    This function should be called near the end of the device's
- *    runtime_resume callback.
+ *    runtime_resume callback to correct queue runtime PM status and re-enable
+ *    peeking requests from the queue.
  */
 void blk_post_runtime_resume(struct request_queue *q)
 {
-	blk_set_runtime_active(q);
-}
-EXPORT_SYMBOL(blk_post_runtime_resume);
-
-/**
- * blk_set_runtime_active - Force runtime status of the queue to be active
- * @q: the queue of the device
- *
- * If the device is left runtime suspended during system suspend the resume
- * hook typically resumes the device and corrects runtime status
- * accordingly. However, that does not affect the queue runtime PM status
- * which is still "suspended". This prevents processing requests from the
- * queue.
- *
- * This function can be used in driver's resume hook to correct queue
- * runtime PM status and re-enable peeking requests from the queue. It
- * should be called before first request is added to the queue.
- *
- * This function is also called by blk_post_runtime_resume() for
- * runtime resumes.  It does everything necessary to restart the queue.
- */
-void blk_set_runtime_active(struct request_queue *q)
-{
 	int old_status;
 
 	if (!q->dev)
@@ -211,4 +188,4 @@ void blk_set_runtime_active(struct request_queue *q)
 	if (old_status != RPM_ACTIVE)
 		blk_clear_pm_only(q);
 }
-EXPORT_SYMBOL(blk_set_runtime_active);
+EXPORT_SYMBOL(blk_post_runtime_resume);
diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
index f48ee150d667..37245c97ee61 100644
--- a/block/blk-rq-qos.h
+++ b/block/blk-rq-qos.h
@@ -118,7 +118,7 @@ static inline void rq_qos_cleanup(struct request_queue *q, struct bio *bio)
 
 static inline void rq_qos_done(struct request_queue *q, struct request *rq)
 {
-	if (q->rq_qos)
+	if (q->rq_qos && !blk_rq_is_passthrough(rq))
 		__rq_qos_done(q->rq_qos, rq);
 }
 
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 0046b447268f..06ea91e51b8b 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -48,7 +48,7 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->max_discard_sectors = 0;
 	lim->max_hw_discard_sectors = 0;
 	lim->max_secure_erase_sectors = 0;
-	lim->discard_granularity = 0;
+	lim->discard_granularity = 512;
 	lim->discard_alignment = 0;
 	lim->discard_misaligned = 0;
 	lim->logical_block_size = lim->physical_block_size = lim->io_min = 512;
@@ -56,7 +56,7 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->alignment_offset = 0;
 	lim->io_opt = 0;
 	lim->misaligned = 0;
-	lim->zoned = BLK_ZONED_NONE;
+	lim->zoned = false;
 	lim->zone_write_granularity = 0;
 	lim->dma_alignment = 511;
 }
@@ -127,8 +127,7 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto
 
 	if ((max_hw_sectors << 9) < PAGE_SIZE) {
 		max_hw_sectors = 1 << (PAGE_SHIFT - 9);
-		printk(KERN_INFO "%s: set to minimum %d\n",
-		       __func__, max_hw_sectors);
+		pr_info("%s: set to minimum %u\n", __func__, max_hw_sectors);
 	}
 
 	max_hw_sectors = round_down(max_hw_sectors,
@@ -140,7 +139,7 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto
 	if (limits->max_user_sectors)
 		max_sectors = min(max_sectors, limits->max_user_sectors);
 	else
-		max_sectors = min(max_sectors, BLK_DEF_MAX_SECTORS);
+		max_sectors = min(max_sectors, BLK_DEF_MAX_SECTORS_CAP);
 
 	max_sectors = round_down(max_sectors,
 				 limits->logical_block_size >> SECTOR_SHIFT);
@@ -248,8 +247,7 @@ void blk_queue_max_segments(struct request_queue *q, unsigned short max_segments
 {
 	if (!max_segments) {
 		max_segments = 1;
-		printk(KERN_INFO "%s: set to minimum %d\n",
-		       __func__, max_segments);
+		pr_info("%s: set to minimum %u\n", __func__, max_segments);
 	}
 
 	q->limits.max_segments = max_segments;
@@ -285,8 +283,7 @@ void blk_queue_max_segment_size(struct request_queue *q, unsigned int max_size)
 {
 	if (max_size < PAGE_SIZE) {
 		max_size = PAGE_SIZE;
-		printk(KERN_INFO "%s: set to minimum %d\n",
-		       __func__, max_size);
+		pr_info("%s: set to minimum %u\n", __func__, max_size);
 	}
 
 	/* see blk_queue_virt_boundary() for the explanation */
@@ -312,6 +309,9 @@ void blk_queue_logical_block_size(struct request_queue *q, unsigned int size)
 
 	limits->logical_block_size = size;
 
+	if (limits->discard_granularity < limits->logical_block_size)
+		limits->discard_granularity = limits->logical_block_size;
+
 	if (limits->physical_block_size < size)
 		limits->physical_block_size = size;
 
@@ -342,6 +342,9 @@ void blk_queue_physical_block_size(struct request_queue *q, unsigned int size)
 	if (q->limits.physical_block_size < q->limits.logical_block_size)
 		q->limits.physical_block_size = q->limits.logical_block_size;
 
+	if (q->limits.discard_granularity < q->limits.physical_block_size)
+		q->limits.discard_granularity = q->limits.physical_block_size;
+
 	if (q->limits.io_min < q->limits.physical_block_size)
 		q->limits.io_min = q->limits.physical_block_size;
 }
@@ -740,8 +743,7 @@ void blk_queue_segment_boundary(struct request_queue *q, unsigned long mask)
 {
 	if (mask < PAGE_SIZE - 1) {
 		mask = PAGE_SIZE - 1;
-		printk(KERN_INFO "%s: set to minimum %lx\n",
-		       __func__, mask);
+		pr_info("%s: set to minimum %lx\n", __func__, mask);
 	}
 
 	q->limits.seg_boundary_mask = mask;
@@ -841,8 +843,6 @@ void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua)
 		blk_queue_flag_set(QUEUE_FLAG_FUA, q);
 	else
 		blk_queue_flag_clear(QUEUE_FLAG_FUA, q);
-
-	wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
 }
 EXPORT_SYMBOL_GPL(blk_queue_write_cache);
 
@@ -884,81 +884,22 @@ bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
 }
 EXPORT_SYMBOL_GPL(blk_queue_can_use_dma_map_merging);
 
-static bool disk_has_partitions(struct gendisk *disk)
-{
-	unsigned long idx;
-	struct block_device *part;
-	bool ret = false;
-
-	rcu_read_lock();
-	xa_for_each(&disk->part_tbl, idx, part) {
-		if (bdev_is_partition(part)) {
-			ret = true;
-			break;
-		}
-	}
-	rcu_read_unlock();
-
-	return ret;
-}
-
 /**
- * disk_set_zoned - configure the zoned model for a disk
- * @disk:	the gendisk of the queue to configure
- * @model:	the zoned model to set
- *
- * Set the zoned model of @disk to @model.
- *
- * When @model is BLK_ZONED_HM (host managed), this should be called only
- * if zoned block device support is enabled (CONFIG_BLK_DEV_ZONED option).
- * If @model specifies BLK_ZONED_HA (host aware), the effective model used
- * depends on CONFIG_BLK_DEV_ZONED settings and on the existence of partitions
- * on the disk.
+ * disk_set_zoned - inidicate a zoned device
+ * @disk:	gendisk to configure
  */
-void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model)
+void disk_set_zoned(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
-	unsigned int old_model = q->limits.zoned;
-
-	switch (model) {
-	case BLK_ZONED_HM:
-		/*
-		 * Host managed devices are supported only if
-		 * CONFIG_BLK_DEV_ZONED is enabled.
-		 */
-		WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED));
-		break;
-	case BLK_ZONED_HA:
-		/*
-		 * Host aware devices can be treated either as regular block
-		 * devices (similar to drive managed devices) or as zoned block
-		 * devices to take advantage of the zone command set, similarly
-		 * to host managed devices. We try the latter if there are no
-		 * partitions and zoned block device support is enabled, else
-		 * we do nothing special as far as the block layer is concerned.
-		 */
-		if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) ||
-		    disk_has_partitions(disk))
-			model = BLK_ZONED_NONE;
-		break;
-	case BLK_ZONED_NONE:
-	default:
-		if (WARN_ON_ONCE(model != BLK_ZONED_NONE))
-			model = BLK_ZONED_NONE;
-		break;
-	}
 
-	q->limits.zoned = model;
-	if (model != BLK_ZONED_NONE) {
-		/*
-		 * Set the zone write granularity to the device logical block
-		 * size by default. The driver can change this value if needed.
-		 */
-		blk_queue_zone_write_granularity(q,
-						queue_logical_block_size(q));
-	} else if (old_model != BLK_ZONED_NONE) {
-		disk_clear_zone_settings(disk);
-	}
+	WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED));
+
+	/*
+	 * Set the zone write granularity to the device logical block
+	 * size by default. The driver can change this value if needed.
+	 */
+	q->limits.zoned = true;
+	blk_queue_zone_write_granularity(q, queue_logical_block_size(q));
 }
 EXPORT_SYMBOL_GPL(disk_set_zoned);
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 63e481262336..6b2429cad81a 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -241,7 +241,7 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 	if (max_sectors_kb == 0) {
 		q->limits.max_user_sectors = 0;
 		max_sectors_kb = min(max_hw_sectors_kb,
-				     BLK_DEF_MAX_SECTORS >> 1);
+				     BLK_DEF_MAX_SECTORS_CAP >> 1);
 	} else {
 		if (max_sectors_kb > max_hw_sectors_kb ||
 		    max_sectors_kb < page_kb)
@@ -309,14 +309,9 @@ QUEUE_SYSFS_BIT_FNS(stable_writes, STABLE_WRITES, 0);
 
 static ssize_t queue_zoned_show(struct request_queue *q, char *page)
 {
-	switch (blk_queue_zoned_model(q)) {
-	case BLK_ZONED_HA:
-		return sprintf(page, "host-aware\n");
-	case BLK_ZONED_HM:
+	if (blk_queue_is_zoned(q))
 		return sprintf(page, "host-managed\n");
-	default:
-		return sprintf(page, "none\n");
-	}
+	return sprintf(page, "none\n");
 }
 
 static ssize_t queue_nr_zones_show(struct request_queue *q, char *page)
@@ -615,6 +610,7 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
 QUEUE_RW_ENTRY(queue_wb_lat, "wbt_lat_usec");
 #endif
 
+/* Common attributes for bio-based and request-based queues. */
 static struct attribute *queue_attrs[] = {
 	&queue_ra_entry.attr,
 	&queue_max_hw_sectors_entry.attr,
@@ -659,6 +655,7 @@ static struct attribute *queue_attrs[] = {
 	NULL,
 };
 
+/* Request-based queue attributes that are not relevant for bio-based queues. */
 static struct attribute *blk_mq_queue_attrs[] = {
 	&queue_requests_entry.attr,
 	&elv_iosched_entry.attr,
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 13e4377a8b28..16f5766620a4 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -1320,6 +1320,7 @@ static void tg_conf_updated(struct throtl_grp *tg, bool global)
 		   tg_bps_limit(tg, READ), tg_bps_limit(tg, WRITE),
 		   tg_iops_limit(tg, READ), tg_iops_limit(tg, WRITE));
 
+	rcu_read_lock();
 	/*
 	 * Update has_rules[] flags for the updated tg's subtree.  A tg is
 	 * considered to have rules if either the tg itself or any of its
@@ -1347,6 +1348,7 @@ static void tg_conf_updated(struct throtl_grp *tg, bool global)
 		this_tg->latency_target = max(this_tg->latency_target,
 				parent_tg->latency_target);
 	}
+	rcu_read_unlock();
 
 	/*
 	 * We're already holding queue_lock and know @tg is valid.  Let's
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 0bb613139bec..5ba3cd574eac 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -84,8 +84,6 @@ struct rq_wb {
 	u64 sync_issue;
 	void *sync_cookie;
 
-	unsigned int wc;
-
 	unsigned long last_issue;		/* last non-throttled issue */
 	unsigned long last_comp;		/* last non-throttled comp */
 	unsigned long min_lat_nsec;
@@ -207,7 +205,8 @@ static void wbt_rqw_done(struct rq_wb *rwb, struct rq_wait *rqw,
 	 */
 	if (wb_acct & WBT_DISCARD)
 		limit = rwb->wb_background;
-	else if (rwb->wc && !wb_recent_wait(rwb))
+	else if (test_bit(QUEUE_FLAG_WC, &rwb->rqos.disk->queue->queue_flags) &&
+	         !wb_recent_wait(rwb))
 		limit = 0;
 	else
 		limit = rwb->wb_normal;
@@ -699,13 +698,6 @@ static void wbt_requeue(struct rq_qos *rqos, struct request *rq)
 	}
 }
 
-void wbt_set_write_cache(struct request_queue *q, bool write_cache_on)
-{
-	struct rq_qos *rqos = wbt_rq_qos(q);
-	if (rqos)
-		RQWB(rqos)->wc = write_cache_on;
-}
-
 /*
  * Enable wbt if defaults are configured that way
  */
@@ -918,7 +910,6 @@ int wbt_init(struct gendisk *disk)
 	rwb->last_comp = rwb->last_issue = jiffies;
 	rwb->win_nsec = RWB_WINDOW_NSEC;
 	rwb->enable_state = WBT_STATE_ON_DEFAULT;
-	rwb->wc = test_bit(QUEUE_FLAG_WC, &q->queue_flags);
 	rwb->rq_depth.default_depth = RWB_DEF_DEPTH;
 	rwb->min_lat_nsec = wbt_default_latency_nsec(q);
 	rwb->rq_depth.queue_depth = blk_queue_depth(q);
diff --git a/block/blk-wbt.h b/block/blk-wbt.h
index 8a029e138f7a..e5fc653b9b76 100644
--- a/block/blk-wbt.h
+++ b/block/blk-wbt.h
@@ -12,8 +12,6 @@ u64 wbt_get_min_lat(struct request_queue *q);
 void wbt_set_min_lat(struct request_queue *q, u64 val);
 bool wbt_disabled(struct request_queue *);
 
-void wbt_set_write_cache(struct request_queue *, bool);
-
 u64 wbt_default_latency_nsec(struct request_queue *);
 
 #else
@@ -24,9 +22,6 @@ static inline void wbt_disable_default(struct gendisk *disk)
 static inline void wbt_enable_default(struct gendisk *disk)
 {
 }
-static inline void wbt_set_write_cache(struct request_queue *q, bool wc)
-{
-}
 
 #endif /* CONFIG_BLK_WBT */
 
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 619ee41a51cc..d343e5756a9c 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -498,7 +498,6 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
 		set_bit(idx, args->conv_zones_bitmap);
 		break;
 	case BLK_ZONE_TYPE_SEQWRITE_REQ:
-	case BLK_ZONE_TYPE_SEQWRITE_PREF:
 		if (!args->seq_zones_wlock) {
 			args->seq_zones_wlock =
 				blk_alloc_zone_bitmap(q->node, args->nr_zones);
@@ -506,6 +505,7 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
 				return -ENOMEM;
 		}
 		break;
+	case BLK_ZONE_TYPE_SEQWRITE_PREF:
 	default:
 		pr_warn("%s: Invalid zone type 0x%x at sectors %llu\n",
 			disk->disk_name, (int)zone->type, zone->start);
@@ -615,22 +615,3 @@ int blk_revalidate_disk_zones(struct gendisk *disk,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);
-
-void disk_clear_zone_settings(struct gendisk *disk)
-{
-	struct request_queue *q = disk->queue;
-
-	blk_mq_freeze_queue(q);
-
-	disk_free_zone_bitmaps(disk);
-	blk_queue_flag_clear(QUEUE_FLAG_ZONE_RESETALL, q);
-	q->required_elevator_features &= ~ELEVATOR_F_ZBD_SEQ_WRITE;
-	disk->nr_zones = 0;
-	disk->max_open_zones = 0;
-	disk->max_active_zones = 0;
-	q->limits.chunk_sectors = 0;
-	q->limits.zone_write_granularity = 0;
-	q->limits.max_zone_append_sectors = 0;
-
-	blk_mq_unfreeze_queue(q);
-}
diff --git a/block/blk.h b/block/blk.h
index 08a358bc0919..1ef920f72e0f 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -395,14 +395,12 @@ static inline struct bio *blk_queue_bounce(struct bio *bio,
 
 #ifdef CONFIG_BLK_DEV_ZONED
 void disk_free_zone_bitmaps(struct gendisk *disk);
-void disk_clear_zone_settings(struct gendisk *disk);
 int blkdev_report_zones_ioctl(struct block_device *bdev, unsigned int cmd,
 		unsigned long arg);
 int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
 		unsigned int cmd, unsigned long arg);
 #else /* CONFIG_BLK_DEV_ZONED */
 static inline void disk_free_zone_bitmaps(struct gendisk *disk) {}
-static inline void disk_clear_zone_settings(struct gendisk *disk) {}
 static inline int blkdev_report_zones_ioctl(struct block_device *bdev,
 		unsigned int cmd, unsigned long arg)
 {
diff --git a/block/fops.c b/block/fops.c
index 0abaac705daf..0cf8cf72cdfa 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -410,9 +410,24 @@ static int blkdev_get_block(struct inode *inode, sector_t iblock,
 	return 0;
 }
 
-static int blkdev_writepage(struct page *page, struct writeback_control *wbc)
+/*
+ * We cannot call mpage_writepages() as it does not take the buffer lock.
+ * We must use block_write_full_folio() directly which holds the buffer
+ * lock.  The buffer lock provides the synchronisation with writeback
+ * that filesystems rely on when they use the blockdev's mapping.
+ */
+static int blkdev_writepages(struct address_space *mapping,
+		struct writeback_control *wbc)
 {
-	return block_write_full_page(page, blkdev_get_block, wbc);
+	struct blk_plug plug;
+	int err;
+
+	blk_start_plug(&plug);
+	err = write_cache_pages(mapping, wbc, block_write_full_folio,
+			blkdev_get_block);
+	blk_finish_plug(&plug);
+
+	return err;
 }
 
 static int blkdev_read_folio(struct file *file, struct folio *folio)
@@ -449,7 +464,7 @@ const struct address_space_operations def_blk_aops = {
 	.invalidate_folio = block_invalidate_folio,
 	.read_folio	= blkdev_read_folio,
 	.readahead	= blkdev_readahead,
-	.writepage	= blkdev_writepage,
+	.writepages	= blkdev_writepages,
 	.write_begin	= blkdev_write_begin,
 	.write_end	= blkdev_write_end,
 	.migrate_folio	= buffer_migrate_folio_norefs,
@@ -500,7 +515,7 @@ const struct address_space_operations def_blk_aops = {
 	.readahead		= blkdev_readahead,
 	.writepages		= blkdev_writepages,
 	.is_partially_uptodate  = iomap_is_partially_uptodate,
-	.error_remove_page	= generic_error_remove_page,
+	.error_remove_folio	= generic_error_remove_folio,
 	.migrate_folio		= filemap_migrate_folio,
 };
 #endif /* CONFIG_BUFFER_HEAD */
diff --git a/block/genhd.c b/block/genhd.c
index c9d06f72c587..d74fb5b4ae68 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -432,7 +432,9 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 				DISK_MAX_PARTS);
 			disk->minors = DISK_MAX_PARTS;
 		}
-		if (disk->first_minor + disk->minors > MINORMASK + 1)
+		if (disk->first_minor > MINORMASK ||
+		    disk->minors > MINORMASK + 1 ||
+		    disk->first_minor + disk->minors > MINORMASK + 1)
 			goto out_exit_elevator;
 	} else {
 		if (WARN_ON(disk->minors))
@@ -542,6 +544,7 @@ out_put_holder_dir:
 	kobject_put(disk->part0->bd_holder_dir);
 out_del_block_link:
 	sysfs_remove_link(block_depr, dev_name(ddev));
+	pm_runtime_set_memalloc_noio(ddev, false);
 out_device_del:
 	device_del(ddev);
 out_free_ext_minor:
diff --git a/block/ioctl.c b/block/ioctl.c
index 4160f4e6bd5b..9c73a763ef88 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -18,7 +18,7 @@ static int blkpg_do_ioctl(struct block_device *bdev,
 {
 	struct gendisk *disk = bdev->bd_disk;
 	struct blkpg_partition p;
-	long long start, length;
+	sector_t start, length;
 
 	if (disk->flags & GENHD_FL_NO_PART)
 		return -EINVAL;
@@ -35,14 +35,17 @@ static int blkpg_do_ioctl(struct block_device *bdev,
 	if (op == BLKPG_DEL_PARTITION)
 		return bdev_del_partition(disk, p.pno);
 
+	if (p.start < 0 || p.length <= 0 || p.start + p.length < 0)
+		return -EINVAL;
+	/* Check that the partition is aligned to the block size */
+	if (!IS_ALIGNED(p.start | p.length, bdev_logical_block_size(bdev)))
+		return -EINVAL;
+
 	start = p.start >> SECTOR_SHIFT;
 	length = p.length >> SECTOR_SHIFT;
 
 	switch (op) {
 	case BLKPG_ADD_PARTITION:
-		/* check if partition is aligned to blocksize */
-		if (p.start & (bdev_logical_block_size(bdev) - 1))
-			return -EINVAL;
 		return bdev_add_partition(disk, p.pno, start, length);
 	case BLKPG_RESIZE_PARTITION:
 		return bdev_resize_partition(disk, p.pno, start, length);
diff --git a/block/partitions/core.c b/block/partitions/core.c
index f47ffcfdfcec..e6ac73617f3e 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -305,18 +305,10 @@ static struct block_device *add_partition(struct gendisk *disk, int partno,
 	 * Partitions are not supported on zoned block devices that are used as
 	 * such.
 	 */
-	switch (disk->queue->limits.zoned) {
-	case BLK_ZONED_HM:
+	if (bdev_is_zoned(disk->part0)) {
 		pr_warn("%s: partitions not supported on host managed zoned block device\n",
 			disk->disk_name);
 		return ERR_PTR(-ENXIO);
-	case BLK_ZONED_HA:
-		pr_info("%s: disabling host aware zoned block device support due to partitions\n",
-			disk->disk_name);
-		disk_set_zoned(disk, BLK_ZONED_NONE);
-		break;
-	case BLK_ZONED_NONE:
-		break;
 	}
 
 	if (xa_load(&disk->part_tbl, partno))
@@ -613,7 +605,7 @@ static int blk_add_partitions(struct gendisk *disk)
 	/*
 	 * Partitions are not supported on host managed zoned block devices.
 	 */
-	if (disk->queue->limits.zoned == BLK_ZONED_HM) {
+	if (bdev_is_zoned(disk->part0)) {
 		pr_warn("%s: ignoring partition table on host managed zoned block device\n",
 			disk->disk_name);
 		ret = 0;
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 70661f58ee41..7d156c75f15f 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -661,15 +661,6 @@ config CRYPTO_CBC
 
 	  This block cipher mode is required for IPSec ESP (XFRM_ESP).
 
-config CRYPTO_CFB
-	tristate "CFB (Cipher Feedback)"
-	select CRYPTO_SKCIPHER
-	select CRYPTO_MANAGER
-	help
-	  CFB (Cipher Feedback) mode (NIST SP800-38A)
-
-	  This block cipher mode is required for TPM2 Cryptography.
-
 config CRYPTO_CTR
 	tristate "CTR (Counter)"
 	select CRYPTO_SKCIPHER
@@ -735,20 +726,6 @@ config CRYPTO_LRW
 
 	  See https://people.csail.mit.edu/rivest/pubs/LRW02.pdf
 
-config CRYPTO_OFB
-	tristate "OFB (Output Feedback)"
-	select CRYPTO_SKCIPHER
-	select CRYPTO_MANAGER
-	help
-	  OFB (Output Feedback) mode (NIST SP800-38A)
-
-	  This mode makes a block cipher into a synchronous
-	  stream cipher. It generates keystream blocks, which are then XORed
-	  with the plaintext blocks to get the ciphertext. Flipping a bit in the
-	  ciphertext produces a flipped bit in the plaintext at the same
-	  location. This property allows many error correcting codes to function
-	  normally even when applied before encryption.
-
 config CRYPTO_PCBC
 	tristate "PCBC (Propagating Cipher Block Chaining)"
 	select CRYPTO_SKCIPHER
diff --git a/crypto/Makefile b/crypto/Makefile
index 5ac6876f935a..408f0a1f9ab9 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -92,7 +92,6 @@ obj-$(CONFIG_CRYPTO_BLAKE2B) += blake2b_generic.o
 CFLAGS_blake2b_generic.o := -Wframe-larger-than=4096 #  https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105930
 obj-$(CONFIG_CRYPTO_ECB) += ecb.o
 obj-$(CONFIG_CRYPTO_CBC) += cbc.o
-obj-$(CONFIG_CRYPTO_CFB) += cfb.o
 obj-$(CONFIG_CRYPTO_PCBC) += pcbc.o
 obj-$(CONFIG_CRYPTO_CTS) += cts.o
 obj-$(CONFIG_CRYPTO_LRW) += lrw.o
@@ -186,7 +185,6 @@ obj-$(CONFIG_CRYPTO_USER_API_SKCIPHER) += algif_skcipher.o
 obj-$(CONFIG_CRYPTO_USER_API_RNG) += algif_rng.o
 obj-$(CONFIG_CRYPTO_USER_API_AEAD) += algif_aead.o
 obj-$(CONFIG_CRYPTO_ZSTD) += zstd.o
-obj-$(CONFIG_CRYPTO_OFB) += ofb.o
 obj-$(CONFIG_CRYPTO_ECC) += ecc.o
 obj-$(CONFIG_CRYPTO_ESSIV) += essiv.o
 obj-$(CONFIG_CRYPTO_CURVE25519) += curve25519-generic.o
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index ea6fb8e89d06..68cc9290cabe 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -1116,9 +1116,13 @@ EXPORT_SYMBOL_GPL(af_alg_sendmsg);
 void af_alg_free_resources(struct af_alg_async_req *areq)
 {
 	struct sock *sk = areq->sk;
+	struct af_alg_ctx *ctx;
 
 	af_alg_free_areq_sgls(areq);
 	sock_kfree_s(sk, areq, areq->areqlen);
+
+	ctx = alg_sk(sk)->private;
+	ctx->inflight = false;
 }
 EXPORT_SYMBOL_GPL(af_alg_free_resources);
 
@@ -1188,11 +1192,19 @@ EXPORT_SYMBOL_GPL(af_alg_poll);
 struct af_alg_async_req *af_alg_alloc_areq(struct sock *sk,
 					   unsigned int areqlen)
 {
-	struct af_alg_async_req *areq = sock_kmalloc(sk, areqlen, GFP_KERNEL);
+	struct af_alg_ctx *ctx = alg_sk(sk)->private;
+	struct af_alg_async_req *areq;
+
+	/* Only one AIO request can be in flight. */
+	if (ctx->inflight)
+		return ERR_PTR(-EBUSY);
 
+	areq = sock_kmalloc(sk, areqlen, GFP_KERNEL);
 	if (unlikely(!areq))
 		return ERR_PTR(-ENOMEM);
 
+	ctx->inflight = true;
+
 	areq->areqlen = areqlen;
 	areq->sk = sk;
 	areq->first_rsgl.sgl.sgt.sgl = areq->first_rsgl.sgl.sgl;
diff --git a/crypto/algapi.c b/crypto/algapi.c
index 4fe95c448047..85bc279b4233 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -341,6 +341,7 @@ __crypto_register_alg(struct crypto_alg *alg, struct list_head *algs_to_put)
 		}
 
 		if (!strcmp(q->cra_driver_name, alg->cra_name) ||
+		    !strcmp(q->cra_driver_name, alg->cra_driver_name) ||
 		    !strcmp(q->cra_name, alg->cra_driver_name))
 			goto err;
 	}
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 9ada9b741af8..02cea2149504 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -47,6 +47,52 @@ static int skcipher_sendmsg(struct socket *sock, struct msghdr *msg,
 	return af_alg_sendmsg(sock, msg, size, ivsize);
 }
 
+static int algif_skcipher_export(struct sock *sk, struct skcipher_request *req)
+{
+	struct alg_sock *ask = alg_sk(sk);
+	struct crypto_skcipher *tfm;
+	struct af_alg_ctx *ctx;
+	struct alg_sock *pask;
+	unsigned statesize;
+	struct sock *psk;
+	int err;
+
+	if (!(req->base.flags & CRYPTO_SKCIPHER_REQ_NOTFINAL))
+		return 0;
+
+	ctx = ask->private;
+	psk = ask->parent;
+	pask = alg_sk(psk);
+	tfm = pask->private;
+
+	statesize = crypto_skcipher_statesize(tfm);
+	ctx->state = sock_kmalloc(sk, statesize, GFP_ATOMIC);
+	if (!ctx->state)
+		return -ENOMEM;
+
+	err = crypto_skcipher_export(req, ctx->state);
+	if (err) {
+		sock_kzfree_s(sk, ctx->state, statesize);
+		ctx->state = NULL;
+	}
+
+	return err;
+}
+
+static void algif_skcipher_done(void *data, int err)
+{
+	struct af_alg_async_req *areq = data;
+	struct sock *sk = areq->sk;
+
+	if (err)
+		goto out;
+
+	err = algif_skcipher_export(sk, &areq->cra_u.skcipher_req);
+
+out:
+	af_alg_async_cb(data, err);
+}
+
 static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 			     size_t ignored, int flags)
 {
@@ -58,6 +104,7 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 	struct crypto_skcipher *tfm = pask->private;
 	unsigned int bs = crypto_skcipher_chunksize(tfm);
 	struct af_alg_async_req *areq;
+	unsigned cflags = 0;
 	int err = 0;
 	size_t len = 0;
 
@@ -82,8 +129,10 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 	 * If more buffers are to be expected to be processed, process only
 	 * full block size buffers.
 	 */
-	if (ctx->more || len < ctx->used)
+	if (ctx->more || len < ctx->used) {
 		len -= len % bs;
+		cflags |= CRYPTO_SKCIPHER_REQ_NOTFINAL;
+	}
 
 	/*
 	 * Create a per request TX SGL for this request which tracks the
@@ -107,6 +156,16 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 	skcipher_request_set_crypt(&areq->cra_u.skcipher_req, areq->tsgl,
 				   areq->first_rsgl.sgl.sgt.sgl, len, ctx->iv);
 
+	if (ctx->state) {
+		err = crypto_skcipher_import(&areq->cra_u.skcipher_req,
+					     ctx->state);
+		sock_kzfree_s(sk, ctx->state, crypto_skcipher_statesize(tfm));
+		ctx->state = NULL;
+		if (err)
+			goto free;
+		cflags |= CRYPTO_SKCIPHER_REQ_CONT;
+	}
+
 	if (msg->msg_iocb && !is_sync_kiocb(msg->msg_iocb)) {
 		/* AIO operation */
 		sock_hold(sk);
@@ -116,8 +175,9 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 		areq->outlen = len;
 
 		skcipher_request_set_callback(&areq->cra_u.skcipher_req,
+					      cflags |
 					      CRYPTO_TFM_REQ_MAY_SLEEP,
-					      af_alg_async_cb, areq);
+					      algif_skcipher_done, areq);
 		err = ctx->enc ?
 			crypto_skcipher_encrypt(&areq->cra_u.skcipher_req) :
 			crypto_skcipher_decrypt(&areq->cra_u.skcipher_req);
@@ -130,6 +190,7 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 	} else {
 		/* Synchronous operation */
 		skcipher_request_set_callback(&areq->cra_u.skcipher_req,
+					      cflags |
 					      CRYPTO_TFM_REQ_MAY_SLEEP |
 					      CRYPTO_TFM_REQ_MAY_BACKLOG,
 					      crypto_req_done, &ctx->wait);
@@ -137,8 +198,11 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 			crypto_skcipher_encrypt(&areq->cra_u.skcipher_req) :
 			crypto_skcipher_decrypt(&areq->cra_u.skcipher_req),
 						 &ctx->wait);
-	}
 
+		if (!err)
+			err = algif_skcipher_export(
+				sk, &areq->cra_u.skcipher_req);
+	}
 
 free:
 	af_alg_free_resources(areq);
@@ -301,6 +365,8 @@ static void skcipher_sock_destruct(struct sock *sk)
 
 	af_alg_pull_tsgl(sk, ctx->used, NULL, 0);
 	sock_kzfree_s(sk, ctx->iv, crypto_skcipher_ivsize(tfm));
+	if (ctx->state)
+		sock_kzfree_s(sk, ctx->state, crypto_skcipher_statesize(tfm));
 	sock_kfree_s(sk, ctx, ctx->len);
 	af_alg_release_parent(sk);
 }
diff --git a/crypto/arc4.c b/crypto/arc4.c
index eb3590dc9282..1a4825c97c5a 100644
--- a/crypto/arc4.c
+++ b/crypto/arc4.c
@@ -14,6 +14,8 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 
+#define ARC4_ALIGN __alignof__(struct arc4_ctx)
+
 static int crypto_arc4_setkey(struct crypto_lskcipher *tfm, const u8 *in_key,
 			      unsigned int key_len)
 {
@@ -23,10 +25,15 @@ static int crypto_arc4_setkey(struct crypto_lskcipher *tfm, const u8 *in_key,
 }
 
 static int crypto_arc4_crypt(struct crypto_lskcipher *tfm, const u8 *src,
-			     u8 *dst, unsigned nbytes, u8 *iv, bool final)
+			     u8 *dst, unsigned nbytes, u8 *siv, u32 flags)
 {
 	struct arc4_ctx *ctx = crypto_lskcipher_ctx(tfm);
 
+	if (!(flags & CRYPTO_LSKCIPHER_FLAG_CONT))
+		memcpy(siv, ctx, sizeof(*ctx));
+
+	ctx = (struct arc4_ctx *)siv;
+
 	arc4_crypt(ctx, dst, src, nbytes);
 	return 0;
 }
@@ -45,9 +52,11 @@ static struct lskcipher_alg arc4_alg = {
 	.co.base.cra_priority		=	100,
 	.co.base.cra_blocksize		=	ARC4_BLOCK_SIZE,
 	.co.base.cra_ctxsize		=	sizeof(struct arc4_ctx),
+	.co.base.cra_alignmask		=	ARC4_ALIGN - 1,
 	.co.base.cra_module		=	THIS_MODULE,
 	.co.min_keysize			=	ARC4_MIN_KEY_SIZE,
 	.co.max_keysize			=	ARC4_MAX_KEY_SIZE,
+	.co.statesize			=	sizeof(struct arc4_ctx),
 	.setkey				=	crypto_arc4_setkey,
 	.encrypt			=	crypto_arc4_crypt,
 	.decrypt			=	crypto_arc4_crypt,
diff --git a/crypto/cbc.c b/crypto/cbc.c
index 28345b8d921c..eedddef9ce40 100644
--- a/crypto/cbc.c
+++ b/crypto/cbc.c
@@ -51,9 +51,10 @@ out:
 }
 
 static int crypto_cbc_encrypt(struct crypto_lskcipher *tfm, const u8 *src,
-			      u8 *dst, unsigned len, u8 *iv, bool final)
+			      u8 *dst, unsigned len, u8 *iv, u32 flags)
 {
 	struct crypto_lskcipher **ctx = crypto_lskcipher_ctx(tfm);
+	bool final = flags & CRYPTO_LSKCIPHER_FLAG_FINAL;
 	struct crypto_lskcipher *cipher = *ctx;
 	int rem;
 
@@ -119,9 +120,10 @@ out:
 }
 
 static int crypto_cbc_decrypt(struct crypto_lskcipher *tfm, const u8 *src,
-			      u8 *dst, unsigned len, u8 *iv, bool final)
+			      u8 *dst, unsigned len, u8 *iv, u32 flags)
 {
 	struct crypto_lskcipher **ctx = crypto_lskcipher_ctx(tfm);
+	bool final = flags & CRYPTO_LSKCIPHER_FLAG_FINAL;
 	struct crypto_lskcipher *cipher = *ctx;
 	int rem;
 
diff --git a/crypto/cfb.c b/crypto/cfb.c
deleted file mode 100644
index 5c36b7b65e2a..000000000000
--- a/crypto/cfb.c
+++ /dev/null
@@ -1,254 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * CFB: Cipher FeedBack mode
- *
- * Copyright (c) 2018 James.Bottomley@HansenPartnership.com
- *
- * CFB is a stream cipher mode which is layered on to a block
- * encryption scheme.  It works very much like a one time pad where
- * the pad is generated initially from the encrypted IV and then
- * subsequently from the encrypted previous block of ciphertext.  The
- * pad is XOR'd into the plain text to get the final ciphertext.
- *
- * The scheme of CFB is best described by wikipedia:
- *
- * https://en.wikipedia.org/wiki/Block_cipher_mode_of_operation#CFB
- *
- * Note that since the pad for both encryption and decryption is
- * generated by an encryption operation, CFB never uses the block
- * decryption function.
- */
-
-#include <crypto/algapi.h>
-#include <crypto/internal/cipher.h>
-#include <crypto/internal/skcipher.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/string.h>
-
-static unsigned int crypto_cfb_bsize(struct crypto_skcipher *tfm)
-{
-	return crypto_cipher_blocksize(skcipher_cipher_simple(tfm));
-}
-
-static void crypto_cfb_encrypt_one(struct crypto_skcipher *tfm,
-					  const u8 *src, u8 *dst)
-{
-	crypto_cipher_encrypt_one(skcipher_cipher_simple(tfm), dst, src);
-}
-
-/* final encrypt and decrypt is the same */
-static void crypto_cfb_final(struct skcipher_walk *walk,
-			     struct crypto_skcipher *tfm)
-{
-	const unsigned long alignmask = crypto_skcipher_alignmask(tfm);
-	u8 tmp[MAX_CIPHER_BLOCKSIZE + MAX_CIPHER_ALIGNMASK];
-	u8 *stream = PTR_ALIGN(tmp + 0, alignmask + 1);
-	u8 *src = walk->src.virt.addr;
-	u8 *dst = walk->dst.virt.addr;
-	u8 *iv = walk->iv;
-	unsigned int nbytes = walk->nbytes;
-
-	crypto_cfb_encrypt_one(tfm, iv, stream);
-	crypto_xor_cpy(dst, stream, src, nbytes);
-}
-
-static int crypto_cfb_encrypt_segment(struct skcipher_walk *walk,
-				      struct crypto_skcipher *tfm)
-{
-	const unsigned int bsize = crypto_cfb_bsize(tfm);
-	unsigned int nbytes = walk->nbytes;
-	u8 *src = walk->src.virt.addr;
-	u8 *dst = walk->dst.virt.addr;
-	u8 *iv = walk->iv;
-
-	do {
-		crypto_cfb_encrypt_one(tfm, iv, dst);
-		crypto_xor(dst, src, bsize);
-		iv = dst;
-
-		src += bsize;
-		dst += bsize;
-	} while ((nbytes -= bsize) >= bsize);
-
-	memcpy(walk->iv, iv, bsize);
-
-	return nbytes;
-}
-
-static int crypto_cfb_encrypt_inplace(struct skcipher_walk *walk,
-				      struct crypto_skcipher *tfm)
-{
-	const unsigned int bsize = crypto_cfb_bsize(tfm);
-	unsigned int nbytes = walk->nbytes;
-	u8 *src = walk->src.virt.addr;
-	u8 *iv = walk->iv;
-	u8 tmp[MAX_CIPHER_BLOCKSIZE];
-
-	do {
-		crypto_cfb_encrypt_one(tfm, iv, tmp);
-		crypto_xor(src, tmp, bsize);
-		iv = src;
-
-		src += bsize;
-	} while ((nbytes -= bsize) >= bsize);
-
-	memcpy(walk->iv, iv, bsize);
-
-	return nbytes;
-}
-
-static int crypto_cfb_encrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct skcipher_walk walk;
-	unsigned int bsize = crypto_cfb_bsize(tfm);
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	while (walk.nbytes >= bsize) {
-		if (walk.src.virt.addr == walk.dst.virt.addr)
-			err = crypto_cfb_encrypt_inplace(&walk, tfm);
-		else
-			err = crypto_cfb_encrypt_segment(&walk, tfm);
-		err = skcipher_walk_done(&walk, err);
-	}
-
-	if (walk.nbytes) {
-		crypto_cfb_final(&walk, tfm);
-		err = skcipher_walk_done(&walk, 0);
-	}
-
-	return err;
-}
-
-static int crypto_cfb_decrypt_segment(struct skcipher_walk *walk,
-				      struct crypto_skcipher *tfm)
-{
-	const unsigned int bsize = crypto_cfb_bsize(tfm);
-	unsigned int nbytes = walk->nbytes;
-	u8 *src = walk->src.virt.addr;
-	u8 *dst = walk->dst.virt.addr;
-	u8 *iv = walk->iv;
-
-	do {
-		crypto_cfb_encrypt_one(tfm, iv, dst);
-		crypto_xor(dst, src, bsize);
-		iv = src;
-
-		src += bsize;
-		dst += bsize;
-	} while ((nbytes -= bsize) >= bsize);
-
-	memcpy(walk->iv, iv, bsize);
-
-	return nbytes;
-}
-
-static int crypto_cfb_decrypt_inplace(struct skcipher_walk *walk,
-				      struct crypto_skcipher *tfm)
-{
-	const unsigned int bsize = crypto_cfb_bsize(tfm);
-	unsigned int nbytes = walk->nbytes;
-	u8 *src = walk->src.virt.addr;
-	u8 * const iv = walk->iv;
-	u8 tmp[MAX_CIPHER_BLOCKSIZE];
-
-	do {
-		crypto_cfb_encrypt_one(tfm, iv, tmp);
-		memcpy(iv, src, bsize);
-		crypto_xor(src, tmp, bsize);
-		src += bsize;
-	} while ((nbytes -= bsize) >= bsize);
-
-	return nbytes;
-}
-
-static int crypto_cfb_decrypt_blocks(struct skcipher_walk *walk,
-				     struct crypto_skcipher *tfm)
-{
-	if (walk->src.virt.addr == walk->dst.virt.addr)
-		return crypto_cfb_decrypt_inplace(walk, tfm);
-	else
-		return crypto_cfb_decrypt_segment(walk, tfm);
-}
-
-static int crypto_cfb_decrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct skcipher_walk walk;
-	const unsigned int bsize = crypto_cfb_bsize(tfm);
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	while (walk.nbytes >= bsize) {
-		err = crypto_cfb_decrypt_blocks(&walk, tfm);
-		err = skcipher_walk_done(&walk, err);
-	}
-
-	if (walk.nbytes) {
-		crypto_cfb_final(&walk, tfm);
-		err = skcipher_walk_done(&walk, 0);
-	}
-
-	return err;
-}
-
-static int crypto_cfb_create(struct crypto_template *tmpl, struct rtattr **tb)
-{
-	struct skcipher_instance *inst;
-	struct crypto_alg *alg;
-	int err;
-
-	inst = skcipher_alloc_instance_simple(tmpl, tb);
-	if (IS_ERR(inst))
-		return PTR_ERR(inst);
-
-	alg = skcipher_ialg_simple(inst);
-
-	/* CFB mode is a stream cipher. */
-	inst->alg.base.cra_blocksize = 1;
-
-	/*
-	 * To simplify the implementation, configure the skcipher walk to only
-	 * give a partial block at the very end, never earlier.
-	 */
-	inst->alg.chunksize = alg->cra_blocksize;
-
-	inst->alg.encrypt = crypto_cfb_encrypt;
-	inst->alg.decrypt = crypto_cfb_decrypt;
-
-	err = skcipher_register_instance(tmpl, inst);
-	if (err)
-		inst->free(inst);
-
-	return err;
-}
-
-static struct crypto_template crypto_cfb_tmpl = {
-	.name = "cfb",
-	.create = crypto_cfb_create,
-	.module = THIS_MODULE,
-};
-
-static int __init crypto_cfb_module_init(void)
-{
-	return crypto_register_template(&crypto_cfb_tmpl);
-}
-
-static void __exit crypto_cfb_module_exit(void)
-{
-	crypto_unregister_template(&crypto_cfb_tmpl);
-}
-
-subsys_initcall(crypto_cfb_module_init);
-module_exit(crypto_cfb_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("CFB block cipher mode of operation");
-MODULE_ALIAS_CRYPTO("cfb");
-MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/crypto/drbg.c b/crypto/drbg.c
index e01f8c7769d0..3addce90930c 100644
--- a/crypto/drbg.c
+++ b/crypto/drbg.c
@@ -111,9 +111,9 @@
  * as stdrng. Each DRBG receives an increasing cra_priority values the later
  * they are defined in this array (see drbg_fill_array).
  *
- * HMAC DRBGs are favored over Hash DRBGs over CTR DRBGs, and
- * the SHA256 / AES 256 over other ciphers. Thus, the favored
- * DRBGs are the latest entries in this array.
+ * HMAC DRBGs are favored over Hash DRBGs over CTR DRBGs, and the
+ * HMAC-SHA512 / SHA256 / AES 256 over other ciphers. Thus, the
+ * favored DRBGs are the latest entries in this array.
  */
 static const struct drbg_core drbg_cores[] = {
 #ifdef CONFIG_CRYPTO_DRBG_CTR
@@ -139,12 +139,6 @@ static const struct drbg_core drbg_cores[] = {
 #endif /* CONFIG_CRYPTO_DRBG_CTR */
 #ifdef CONFIG_CRYPTO_DRBG_HASH
 	{
-		.flags = DRBG_HASH | DRBG_STRENGTH128,
-		.statelen = 55, /* 440 bits */
-		.blocklen_bytes = 20,
-		.cra_name = "sha1",
-		.backend_cra_name = "sha1",
-	}, {
 		.flags = DRBG_HASH | DRBG_STRENGTH256,
 		.statelen = 111, /* 888 bits */
 		.blocklen_bytes = 48,
@@ -166,12 +160,6 @@ static const struct drbg_core drbg_cores[] = {
 #endif /* CONFIG_CRYPTO_DRBG_HASH */
 #ifdef CONFIG_CRYPTO_DRBG_HMAC
 	{
-		.flags = DRBG_HMAC | DRBG_STRENGTH128,
-		.statelen = 20, /* block length of cipher */
-		.blocklen_bytes = 20,
-		.cra_name = "hmac_sha1",
-		.backend_cra_name = "hmac(sha1)",
-	}, {
 		.flags = DRBG_HMAC | DRBG_STRENGTH256,
 		.statelen = 48, /* block length of cipher */
 		.blocklen_bytes = 48,
@@ -648,8 +636,6 @@ MODULE_ALIAS_CRYPTO("drbg_pr_hmac_sha384");
 MODULE_ALIAS_CRYPTO("drbg_nopr_hmac_sha384");
 MODULE_ALIAS_CRYPTO("drbg_pr_hmac_sha256");
 MODULE_ALIAS_CRYPTO("drbg_nopr_hmac_sha256");
-MODULE_ALIAS_CRYPTO("drbg_pr_hmac_sha1");
-MODULE_ALIAS_CRYPTO("drbg_nopr_hmac_sha1");
 
 /* update function of HMAC DRBG as defined in 10.1.2.2 */
 static int drbg_hmac_update(struct drbg_state *drbg, struct list_head *seed,
@@ -768,8 +754,6 @@ MODULE_ALIAS_CRYPTO("drbg_pr_sha384");
 MODULE_ALIAS_CRYPTO("drbg_nopr_sha384");
 MODULE_ALIAS_CRYPTO("drbg_pr_sha256");
 MODULE_ALIAS_CRYPTO("drbg_nopr_sha256");
-MODULE_ALIAS_CRYPTO("drbg_pr_sha1");
-MODULE_ALIAS_CRYPTO("drbg_nopr_sha1");
 
 /*
  * Increment buffer
@@ -1475,11 +1459,11 @@ static int drbg_generate(struct drbg_state *drbg,
 		int err = 0;
 		pr_devel("DRBG: start to perform self test\n");
 		if (drbg->core->flags & DRBG_HMAC)
-			err = alg_test("drbg_pr_hmac_sha256",
-				       "drbg_pr_hmac_sha256", 0, 0);
+			err = alg_test("drbg_pr_hmac_sha512",
+				       "drbg_pr_hmac_sha512", 0, 0);
 		else if (drbg->core->flags & DRBG_CTR)
-			err = alg_test("drbg_pr_ctr_aes128",
-				       "drbg_pr_ctr_aes128", 0, 0);
+			err = alg_test("drbg_pr_ctr_aes256",
+				       "drbg_pr_ctr_aes256", 0, 0);
 		else
 			err = alg_test("drbg_pr_sha256",
 				       "drbg_pr_sha256", 0, 0);
@@ -2017,11 +2001,13 @@ static inline int __init drbg_healthcheck_sanity(void)
 		return 0;
 
 #ifdef CONFIG_CRYPTO_DRBG_CTR
-	drbg_convert_tfm_core("drbg_nopr_ctr_aes128", &coreref, &pr);
-#elif defined CONFIG_CRYPTO_DRBG_HASH
+	drbg_convert_tfm_core("drbg_nopr_ctr_aes256", &coreref, &pr);
+#endif
+#ifdef CONFIG_CRYPTO_DRBG_HASH
 	drbg_convert_tfm_core("drbg_nopr_sha256", &coreref, &pr);
-#else
-	drbg_convert_tfm_core("drbg_nopr_hmac_sha256", &coreref, &pr);
+#endif
+#ifdef CONFIG_CRYPTO_DRBG_HMAC
+	drbg_convert_tfm_core("drbg_nopr_hmac_sha512", &coreref, &pr);
 #endif
 
 	drbg = kzalloc(sizeof(struct drbg_state), GFP_KERNEL);
diff --git a/crypto/ecb.c b/crypto/ecb.c
index cc7625d1a475..e3a67789050e 100644
--- a/crypto/ecb.c
+++ b/crypto/ecb.c
@@ -32,22 +32,24 @@ static int crypto_ecb_crypt(struct crypto_cipher *cipher, const u8 *src,
 }
 
 static int crypto_ecb_encrypt2(struct crypto_lskcipher *tfm, const u8 *src,
-			       u8 *dst, unsigned len, u8 *iv, bool final)
+			       u8 *dst, unsigned len, u8 *iv, u32 flags)
 {
 	struct crypto_cipher **ctx = crypto_lskcipher_ctx(tfm);
 	struct crypto_cipher *cipher = *ctx;
 
-	return crypto_ecb_crypt(cipher, src, dst, len, final,
+	return crypto_ecb_crypt(cipher, src, dst, len,
+				flags & CRYPTO_LSKCIPHER_FLAG_FINAL,
 				crypto_cipher_alg(cipher)->cia_encrypt);
 }
 
 static int crypto_ecb_decrypt2(struct crypto_lskcipher *tfm, const u8 *src,
-			       u8 *dst, unsigned len, u8 *iv, bool final)
+			       u8 *dst, unsigned len, u8 *iv, u32 flags)
 {
 	struct crypto_cipher **ctx = crypto_lskcipher_ctx(tfm);
 	struct crypto_cipher *cipher = *ctx;
 
-	return crypto_ecb_crypt(cipher, src, dst, len, final,
+	return crypto_ecb_crypt(cipher, src, dst, len,
+				flags & CRYPTO_LSKCIPHER_FLAG_FINAL,
 				crypto_cipher_alg(cipher)->cia_decrypt);
 }
 
diff --git a/crypto/lskcipher.c b/crypto/lskcipher.c
index 9edc89730951..0b6dd8aa21f2 100644
--- a/crypto/lskcipher.c
+++ b/crypto/lskcipher.c
@@ -88,8 +88,9 @@ EXPORT_SYMBOL_GPL(crypto_lskcipher_setkey);
 static int crypto_lskcipher_crypt_unaligned(
 	struct crypto_lskcipher *tfm, const u8 *src, u8 *dst, unsigned len,
 	u8 *iv, int (*crypt)(struct crypto_lskcipher *tfm, const u8 *src,
-			     u8 *dst, unsigned len, u8 *iv, bool final))
+			     u8 *dst, unsigned len, u8 *iv, u32 flags))
 {
+	unsigned statesize = crypto_lskcipher_statesize(tfm);
 	unsigned ivsize = crypto_lskcipher_ivsize(tfm);
 	unsigned bs = crypto_lskcipher_blocksize(tfm);
 	unsigned cs = crypto_lskcipher_chunksize(tfm);
@@ -104,7 +105,7 @@ static int crypto_lskcipher_crypt_unaligned(
 	if (!tiv)
 		return -ENOMEM;
 
-	memcpy(tiv, iv, ivsize);
+	memcpy(tiv, iv, ivsize + statesize);
 
 	p = kmalloc(PAGE_SIZE, GFP_ATOMIC);
 	err = -ENOMEM;
@@ -119,7 +120,7 @@ static int crypto_lskcipher_crypt_unaligned(
 			chunk &= ~(cs - 1);
 
 		memcpy(p, src, chunk);
-		err = crypt(tfm, p, p, chunk, tiv, true);
+		err = crypt(tfm, p, p, chunk, tiv, CRYPTO_LSKCIPHER_FLAG_FINAL);
 		if (err)
 			goto out;
 
@@ -132,7 +133,7 @@ static int crypto_lskcipher_crypt_unaligned(
 	err = len ? -EINVAL : 0;
 
 out:
-	memcpy(iv, tiv, ivsize);
+	memcpy(iv, tiv, ivsize + statesize);
 	kfree_sensitive(p);
 	kfree_sensitive(tiv);
 	return err;
@@ -143,7 +144,7 @@ static int crypto_lskcipher_crypt(struct crypto_lskcipher *tfm, const u8 *src,
 				  int (*crypt)(struct crypto_lskcipher *tfm,
 					       const u8 *src, u8 *dst,
 					       unsigned len, u8 *iv,
-					       bool final))
+					       u32 flags))
 {
 	unsigned long alignmask = crypto_lskcipher_alignmask(tfm);
 	struct lskcipher_alg *alg = crypto_lskcipher_alg(tfm);
@@ -156,7 +157,7 @@ static int crypto_lskcipher_crypt(struct crypto_lskcipher *tfm, const u8 *src,
 		goto out;
 	}
 
-	ret = crypt(tfm, src, dst, len, iv, true);
+	ret = crypt(tfm, src, dst, len, iv, CRYPTO_LSKCIPHER_FLAG_FINAL);
 
 out:
 	return crypto_lskcipher_errstat(alg, ret);
@@ -197,23 +198,45 @@ EXPORT_SYMBOL_GPL(crypto_lskcipher_decrypt);
 static int crypto_lskcipher_crypt_sg(struct skcipher_request *req,
 				     int (*crypt)(struct crypto_lskcipher *tfm,
 						  const u8 *src, u8 *dst,
-						  unsigned len, u8 *iv,
-						  bool final))
+						  unsigned len, u8 *ivs,
+						  u32 flags))
 {
 	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
 	struct crypto_lskcipher **ctx = crypto_skcipher_ctx(skcipher);
+	u8 *ivs = skcipher_request_ctx(req);
 	struct crypto_lskcipher *tfm = *ctx;
 	struct skcipher_walk walk;
+	unsigned ivsize;
+	u32 flags;
 	int err;
 
+	ivsize = crypto_lskcipher_ivsize(tfm);
+	ivs = PTR_ALIGN(ivs, crypto_skcipher_alignmask(skcipher) + 1);
+
+	flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	if (req->base.flags & CRYPTO_SKCIPHER_REQ_CONT)
+		flags |= CRYPTO_LSKCIPHER_FLAG_CONT;
+	else
+		memcpy(ivs, req->iv, ivsize);
+
+	if (!(req->base.flags & CRYPTO_SKCIPHER_REQ_NOTFINAL))
+		flags |= CRYPTO_LSKCIPHER_FLAG_FINAL;
+
 	err = skcipher_walk_virt(&walk, req, false);
 
 	while (walk.nbytes) {
 		err = crypt(tfm, walk.src.virt.addr, walk.dst.virt.addr,
-			    walk.nbytes, walk.iv, walk.nbytes == walk.total);
+			    walk.nbytes, ivs,
+			    flags & ~(walk.nbytes == walk.total ?
+			    0 : CRYPTO_LSKCIPHER_FLAG_FINAL));
 		err = skcipher_walk_done(&walk, err);
+		flags |= CRYPTO_LSKCIPHER_FLAG_CONT;
 	}
 
+	if (flags & CRYPTO_LSKCIPHER_FLAG_FINAL)
+		memcpy(req->iv, ivs, ivsize);
+
 	return err;
 }
 
@@ -276,6 +299,7 @@ static void __maybe_unused crypto_lskcipher_show(
 	seq_printf(m, "max keysize  : %u\n", skcipher->co.max_keysize);
 	seq_printf(m, "ivsize       : %u\n", skcipher->co.ivsize);
 	seq_printf(m, "chunksize    : %u\n", skcipher->co.chunksize);
+	seq_printf(m, "statesize    : %u\n", skcipher->co.statesize);
 }
 
 static int __maybe_unused crypto_lskcipher_report(
@@ -618,6 +642,7 @@ struct lskcipher_instance *lskcipher_alloc_instance_simple(
 	inst->alg.co.min_keysize = cipher_alg->co.min_keysize;
 	inst->alg.co.max_keysize = cipher_alg->co.max_keysize;
 	inst->alg.co.ivsize = cipher_alg->co.base.cra_blocksize;
+	inst->alg.co.statesize = cipher_alg->co.statesize;
 
 	/* Use struct crypto_lskcipher * by default, can be overridden */
 	inst->alg.co.base.cra_ctxsize = sizeof(struct crypto_lskcipher *);
diff --git a/crypto/ofb.c b/crypto/ofb.c
deleted file mode 100644
index b630fdecceee..000000000000
--- a/crypto/ofb.c
+++ /dev/null
@@ -1,106 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-/*
- * OFB: Output FeedBack mode
- *
- * Copyright (C) 2018 ARM Limited or its affiliates.
- * All rights reserved.
- */
-
-#include <crypto/algapi.h>
-#include <crypto/internal/cipher.h>
-#include <crypto/internal/skcipher.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-static int crypto_ofb_crypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct crypto_cipher *cipher = skcipher_cipher_simple(tfm);
-	const unsigned int bsize = crypto_cipher_blocksize(cipher);
-	struct skcipher_walk walk;
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	while (walk.nbytes >= bsize) {
-		const u8 *src = walk.src.virt.addr;
-		u8 *dst = walk.dst.virt.addr;
-		u8 * const iv = walk.iv;
-		unsigned int nbytes = walk.nbytes;
-
-		do {
-			crypto_cipher_encrypt_one(cipher, iv, iv);
-			crypto_xor_cpy(dst, src, iv, bsize);
-			dst += bsize;
-			src += bsize;
-		} while ((nbytes -= bsize) >= bsize);
-
-		err = skcipher_walk_done(&walk, nbytes);
-	}
-
-	if (walk.nbytes) {
-		crypto_cipher_encrypt_one(cipher, walk.iv, walk.iv);
-		crypto_xor_cpy(walk.dst.virt.addr, walk.src.virt.addr, walk.iv,
-			       walk.nbytes);
-		err = skcipher_walk_done(&walk, 0);
-	}
-	return err;
-}
-
-static int crypto_ofb_create(struct crypto_template *tmpl, struct rtattr **tb)
-{
-	struct skcipher_instance *inst;
-	struct crypto_alg *alg;
-	int err;
-
-	inst = skcipher_alloc_instance_simple(tmpl, tb);
-	if (IS_ERR(inst))
-		return PTR_ERR(inst);
-
-	alg = skcipher_ialg_simple(inst);
-
-	/* OFB mode is a stream cipher. */
-	inst->alg.base.cra_blocksize = 1;
-
-	/*
-	 * To simplify the implementation, configure the skcipher walk to only
-	 * give a partial block at the very end, never earlier.
-	 */
-	inst->alg.chunksize = alg->cra_blocksize;
-
-	inst->alg.encrypt = crypto_ofb_crypt;
-	inst->alg.decrypt = crypto_ofb_crypt;
-
-	err = skcipher_register_instance(tmpl, inst);
-	if (err)
-		inst->free(inst);
-
-	return err;
-}
-
-static struct crypto_template crypto_ofb_tmpl = {
-	.name = "ofb",
-	.create = crypto_ofb_create,
-	.module = THIS_MODULE,
-};
-
-static int __init crypto_ofb_module_init(void)
-{
-	return crypto_register_template(&crypto_ofb_tmpl);
-}
-
-static void __exit crypto_ofb_module_exit(void)
-{
-	crypto_unregister_template(&crypto_ofb_tmpl);
-}
-
-subsys_initcall(crypto_ofb_module_init);
-module_exit(crypto_ofb_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("OFB block cipher mode of operation");
-MODULE_ALIAS_CRYPTO("ofb");
-MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/crypto/rsa.c b/crypto/rsa.c
index c79613cdce6e..b9cd11fb7d36 100644
--- a/crypto/rsa.c
+++ b/crypto/rsa.c
@@ -220,6 +220,8 @@ static int rsa_check_exponent_fips(MPI e)
 	}
 
 	e_max = mpi_alloc(0);
+	if (!e_max)
+		return -ENOMEM;
 	mpi_set_bit(e_max, 256);
 
 	if (mpi_cmp(e, e_max) >= 0) {
diff --git a/crypto/scompress.c b/crypto/scompress.c
index 442a82c9de7d..b108a30a7600 100644
--- a/crypto/scompress.c
+++ b/crypto/scompress.c
@@ -117,6 +117,7 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir)
 	struct crypto_scomp *scomp = *tfm_ctx;
 	void **ctx = acomp_request_ctx(req);
 	struct scomp_scratch *scratch;
+	unsigned int dlen;
 	int ret;
 
 	if (!req->src || !req->slen || req->slen > SCOMP_SCRATCH_SIZE)
@@ -128,6 +129,8 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir)
 	if (!req->dlen || req->dlen > SCOMP_SCRATCH_SIZE)
 		req->dlen = SCOMP_SCRATCH_SIZE;
 
+	dlen = req->dlen;
+
 	scratch = raw_cpu_ptr(&scomp_scratch);
 	spin_lock(&scratch->lock);
 
@@ -145,6 +148,9 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir)
 				ret = -ENOMEM;
 				goto out;
 			}
+		} else if (req->dlen > dlen) {
+			ret = -ENOSPC;
+			goto out;
 		}
 		scatterwalk_map_and_copy(scratch->dst, req->dst, 0, req->dlen,
 					 1);
diff --git a/crypto/shash.c b/crypto/shash.c
index d5194221c88c..c3f7f6a25280 100644
--- a/crypto/shash.c
+++ b/crypto/shash.c
@@ -23,12 +23,8 @@ static inline struct crypto_istat_hash *shash_get_stat(struct shash_alg *alg)
 
 static inline int crypto_shash_errstat(struct shash_alg *alg, int err)
 {
-	if (!IS_ENABLED(CONFIG_CRYPTO_STATS))
-		return err;
-
-	if (err && err != -EINPROGRESS && err != -EBUSY)
+	if (IS_ENABLED(CONFIG_CRYPTO_STATS) && err)
 		atomic64_inc(&shash_get_stat(alg)->err_cnt);
-
 	return err;
 }
 
diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index ac8b8c042654..bc70e159d27d 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -698,6 +698,64 @@ int crypto_skcipher_decrypt(struct skcipher_request *req)
 }
 EXPORT_SYMBOL_GPL(crypto_skcipher_decrypt);
 
+static int crypto_lskcipher_export(struct skcipher_request *req, void *out)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	u8 *ivs = skcipher_request_ctx(req);
+
+	ivs = PTR_ALIGN(ivs, crypto_skcipher_alignmask(tfm) + 1);
+
+	memcpy(out, ivs + crypto_skcipher_ivsize(tfm),
+	       crypto_skcipher_statesize(tfm));
+
+	return 0;
+}
+
+static int crypto_lskcipher_import(struct skcipher_request *req, const void *in)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	u8 *ivs = skcipher_request_ctx(req);
+
+	ivs = PTR_ALIGN(ivs, crypto_skcipher_alignmask(tfm) + 1);
+
+	memcpy(ivs + crypto_skcipher_ivsize(tfm), in,
+	       crypto_skcipher_statesize(tfm));
+
+	return 0;
+}
+
+static int skcipher_noexport(struct skcipher_request *req, void *out)
+{
+	return 0;
+}
+
+static int skcipher_noimport(struct skcipher_request *req, const void *in)
+{
+	return 0;
+}
+
+int crypto_skcipher_export(struct skcipher_request *req, void *out)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
+
+	if (alg->co.base.cra_type != &crypto_skcipher_type)
+		return crypto_lskcipher_export(req, out);
+	return alg->export(req, out);
+}
+EXPORT_SYMBOL_GPL(crypto_skcipher_export);
+
+int crypto_skcipher_import(struct skcipher_request *req, const void *in)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
+
+	if (alg->co.base.cra_type != &crypto_skcipher_type)
+		return crypto_lskcipher_import(req, in);
+	return alg->import(req, in);
+}
+EXPORT_SYMBOL_GPL(crypto_skcipher_import);
+
 static void crypto_skcipher_exit_tfm(struct crypto_tfm *tfm)
 {
 	struct crypto_skcipher *skcipher = __crypto_skcipher_cast(tfm);
@@ -713,8 +771,17 @@ static int crypto_skcipher_init_tfm(struct crypto_tfm *tfm)
 
 	skcipher_set_needkey(skcipher);
 
-	if (tfm->__crt_alg->cra_type != &crypto_skcipher_type)
+	if (tfm->__crt_alg->cra_type != &crypto_skcipher_type) {
+		unsigned am = crypto_skcipher_alignmask(skcipher);
+		unsigned reqsize;
+
+		reqsize = am & ~(crypto_tfm_ctx_alignment() - 1);
+		reqsize += crypto_skcipher_ivsize(skcipher);
+		reqsize += crypto_skcipher_statesize(skcipher);
+		crypto_skcipher_set_reqsize(skcipher, reqsize);
+
 		return crypto_init_lskcipher_ops_sg(tfm);
+	}
 
 	if (alg->exit)
 		skcipher->base.exit = crypto_skcipher_exit_tfm;
@@ -756,6 +823,7 @@ static void crypto_skcipher_show(struct seq_file *m, struct crypto_alg *alg)
 	seq_printf(m, "ivsize       : %u\n", skcipher->ivsize);
 	seq_printf(m, "chunksize    : %u\n", skcipher->chunksize);
 	seq_printf(m, "walksize     : %u\n", skcipher->walksize);
+	seq_printf(m, "statesize    : %u\n", skcipher->statesize);
 }
 
 static int __maybe_unused crypto_skcipher_report(
@@ -870,7 +938,9 @@ int skcipher_prepare_alg_common(struct skcipher_alg_common *alg)
 	struct crypto_istat_cipher *istat = skcipher_get_stat_common(alg);
 	struct crypto_alg *base = &alg->base;
 
-	if (alg->ivsize > PAGE_SIZE / 8 || alg->chunksize > PAGE_SIZE / 8)
+	if (alg->ivsize > PAGE_SIZE / 8 || alg->chunksize > PAGE_SIZE / 8 ||
+	    alg->statesize > PAGE_SIZE / 2 ||
+	    (alg->ivsize + alg->statesize) > PAGE_SIZE / 2)
 		return -EINVAL;
 
 	if (!alg->chunksize)
@@ -899,6 +969,12 @@ static int skcipher_prepare_alg(struct skcipher_alg *alg)
 	if (!alg->walksize)
 		alg->walksize = alg->chunksize;
 
+	if (!alg->statesize) {
+		alg->import = skcipher_noimport;
+		alg->export = skcipher_noexport;
+	} else if (!(alg->import && alg->export))
+		return -EINVAL;
+
 	base->cra_type = &crypto_skcipher_type;
 	base->cra_flags |= CRYPTO_ALG_TYPE_SKCIPHER;
 
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index 202ca1a3105d..ea4d1cea9c06 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -1524,8 +1524,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 		ret = min(ret, tcrypt_test("xts(aes)"));
 		ret = min(ret, tcrypt_test("ctr(aes)"));
 		ret = min(ret, tcrypt_test("rfc3686(ctr(aes))"));
-		ret = min(ret, tcrypt_test("ofb(aes)"));
-		ret = min(ret, tcrypt_test("cfb(aes)"));
 		ret = min(ret, tcrypt_test("xctr(aes)"));
 		break;
 
@@ -1845,14 +1843,12 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 	case 191:
 		ret = min(ret, tcrypt_test("ecb(sm4)"));
 		ret = min(ret, tcrypt_test("cbc(sm4)"));
-		ret = min(ret, tcrypt_test("cfb(sm4)"));
 		ret = min(ret, tcrypt_test("ctr(sm4)"));
 		ret = min(ret, tcrypt_test("xts(sm4)"));
 		break;
 	case 192:
 		ret = min(ret, tcrypt_test("ecb(aria)"));
 		ret = min(ret, tcrypt_test("cbc(aria)"));
-		ret = min(ret, tcrypt_test("cfb(aria)"));
 		ret = min(ret, tcrypt_test("ctr(aria)"));
 		break;
 	case 200:
@@ -1880,10 +1876,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 				speed_template_16_24_32);
 		test_cipher_speed("ctr(aes)", DECRYPT, sec, NULL, 0,
 				speed_template_16_24_32);
-		test_cipher_speed("cfb(aes)", ENCRYPT, sec, NULL, 0,
-				speed_template_16_24_32);
-		test_cipher_speed("cfb(aes)", DECRYPT, sec, NULL, 0,
-				speed_template_16_24_32);
 		break;
 
 	case 201:
@@ -2115,10 +2107,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 				speed_template_16);
 		test_cipher_speed("cts(cbc(sm4))", DECRYPT, sec, NULL, 0,
 				speed_template_16);
-		test_cipher_speed("cfb(sm4)", ENCRYPT, sec, NULL, 0,
-				speed_template_16);
-		test_cipher_speed("cfb(sm4)", DECRYPT, sec, NULL, 0,
-				speed_template_16);
 		test_cipher_speed("ctr(sm4)", ENCRYPT, sec, NULL, 0,
 				speed_template_16);
 		test_cipher_speed("ctr(sm4)", DECRYPT, sec, NULL, 0,
@@ -2198,10 +2186,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 				  speed_template_16_24_32);
 		test_cipher_speed("cbc(aria)", DECRYPT, sec, NULL, 0,
 				  speed_template_16_24_32);
-		test_cipher_speed("cfb(aria)", ENCRYPT, sec, NULL, 0,
-				  speed_template_16_24_32);
-		test_cipher_speed("cfb(aria)", DECRYPT, sec, NULL, 0,
-				  speed_template_16_24_32);
 		test_cipher_speed("ctr(aria)", ENCRYPT, sec, NULL, 0,
 				  speed_template_16_24_32);
 		test_cipher_speed("ctr(aria)", DECRYPT, sec, NULL, 0,
@@ -2436,14 +2420,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 				   speed_template_16_24_32);
 		test_acipher_speed("ctr(aes)", DECRYPT, sec, NULL, 0,
 				   speed_template_16_24_32);
-		test_acipher_speed("cfb(aes)", ENCRYPT, sec, NULL, 0,
-				   speed_template_16_24_32);
-		test_acipher_speed("cfb(aes)", DECRYPT, sec, NULL, 0,
-				   speed_template_16_24_32);
-		test_acipher_speed("ofb(aes)", ENCRYPT, sec, NULL, 0,
-				   speed_template_16_24_32);
-		test_acipher_speed("ofb(aes)", DECRYPT, sec, NULL, 0,
-				   speed_template_16_24_32);
 		test_acipher_speed("rfc3686(ctr(aes))", ENCRYPT, sec, NULL, 0,
 				   speed_template_20_28_36);
 		test_acipher_speed("rfc3686(ctr(aes))", DECRYPT, sec, NULL, 0,
@@ -2463,18 +2439,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 		test_acipher_speed("cbc(des3_ede)", DECRYPT, sec,
 				   des3_speed_template, DES3_SPEED_VECTORS,
 				   speed_template_24);
-		test_acipher_speed("cfb(des3_ede)", ENCRYPT, sec,
-				   des3_speed_template, DES3_SPEED_VECTORS,
-				   speed_template_24);
-		test_acipher_speed("cfb(des3_ede)", DECRYPT, sec,
-				   des3_speed_template, DES3_SPEED_VECTORS,
-				   speed_template_24);
-		test_acipher_speed("ofb(des3_ede)", ENCRYPT, sec,
-				   des3_speed_template, DES3_SPEED_VECTORS,
-				   speed_template_24);
-		test_acipher_speed("ofb(des3_ede)", DECRYPT, sec,
-				   des3_speed_template, DES3_SPEED_VECTORS,
-				   speed_template_24);
 		break;
 
 	case 502:
@@ -2486,14 +2450,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 				   speed_template_8);
 		test_acipher_speed("cbc(des)", DECRYPT, sec, NULL, 0,
 				   speed_template_8);
-		test_acipher_speed("cfb(des)", ENCRYPT, sec, NULL, 0,
-				   speed_template_8);
-		test_acipher_speed("cfb(des)", DECRYPT, sec, NULL, 0,
-				   speed_template_8);
-		test_acipher_speed("ofb(des)", ENCRYPT, sec, NULL, 0,
-				   speed_template_8);
-		test_acipher_speed("ofb(des)", DECRYPT, sec, NULL, 0,
-				   speed_template_8);
 		break;
 
 	case 503:
@@ -2632,10 +2588,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 				speed_template_16);
 		test_acipher_speed("cbc(sm4)", DECRYPT, sec, NULL, 0,
 				speed_template_16);
-		test_acipher_speed("cfb(sm4)", ENCRYPT, sec, NULL, 0,
-				speed_template_16);
-		test_acipher_speed("cfb(sm4)", DECRYPT, sec, NULL, 0,
-				speed_template_16);
 		test_acipher_speed("ctr(sm4)", ENCRYPT, sec, NULL, 0,
 				speed_template_16);
 		test_acipher_speed("ctr(sm4)", DECRYPT, sec, NULL, 0,
@@ -2682,14 +2634,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 				       speed_template_16_24_32, num_mb);
 		test_mb_skcipher_speed("ctr(aes)", DECRYPT, sec, NULL, 0,
 				       speed_template_16_24_32, num_mb);
-		test_mb_skcipher_speed("cfb(aes)", ENCRYPT, sec, NULL, 0,
-				       speed_template_16_24_32, num_mb);
-		test_mb_skcipher_speed("cfb(aes)", DECRYPT, sec, NULL, 0,
-				       speed_template_16_24_32, num_mb);
-		test_mb_skcipher_speed("ofb(aes)", ENCRYPT, sec, NULL, 0,
-				       speed_template_16_24_32, num_mb);
-		test_mb_skcipher_speed("ofb(aes)", DECRYPT, sec, NULL, 0,
-				       speed_template_16_24_32, num_mb);
 		test_mb_skcipher_speed("rfc3686(ctr(aes))", ENCRYPT, sec, NULL,
 				       0, speed_template_20_28_36, num_mb);
 		test_mb_skcipher_speed("rfc3686(ctr(aes))", DECRYPT, sec, NULL,
@@ -2709,18 +2653,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 		test_mb_skcipher_speed("cbc(des3_ede)", DECRYPT, sec,
 				       des3_speed_template, DES3_SPEED_VECTORS,
 				       speed_template_24, num_mb);
-		test_mb_skcipher_speed("cfb(des3_ede)", ENCRYPT, sec,
-				       des3_speed_template, DES3_SPEED_VECTORS,
-				       speed_template_24, num_mb);
-		test_mb_skcipher_speed("cfb(des3_ede)", DECRYPT, sec,
-				       des3_speed_template, DES3_SPEED_VECTORS,
-				       speed_template_24, num_mb);
-		test_mb_skcipher_speed("ofb(des3_ede)", ENCRYPT, sec,
-				       des3_speed_template, DES3_SPEED_VECTORS,
-				       speed_template_24, num_mb);
-		test_mb_skcipher_speed("ofb(des3_ede)", DECRYPT, sec,
-				       des3_speed_template, DES3_SPEED_VECTORS,
-				       speed_template_24, num_mb);
 		break;
 
 	case 602:
@@ -2732,14 +2664,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 				       speed_template_8, num_mb);
 		test_mb_skcipher_speed("cbc(des)", DECRYPT, sec, NULL, 0,
 				       speed_template_8, num_mb);
-		test_mb_skcipher_speed("cfb(des)", ENCRYPT, sec, NULL, 0,
-				       speed_template_8, num_mb);
-		test_mb_skcipher_speed("cfb(des)", DECRYPT, sec, NULL, 0,
-				       speed_template_8, num_mb);
-		test_mb_skcipher_speed("ofb(des)", ENCRYPT, sec, NULL, 0,
-				       speed_template_8, num_mb);
-		test_mb_skcipher_speed("ofb(des)", DECRYPT, sec, NULL, 0,
-				       speed_template_8, num_mb);
 		break;
 
 	case 603:
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index 15c7a3011269..c26aeda85787 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -4609,25 +4609,6 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
-		.alg = "cfb(aes)",
-		.test = alg_test_skcipher,
-		.fips_allowed = 1,
-		.suite = {
-			.cipher = __VECS(aes_cfb_tv_template)
-		},
-	}, {
-		.alg = "cfb(aria)",
-		.test = alg_test_skcipher,
-		.suite = {
-			.cipher = __VECS(aria_cfb_tv_template)
-		},
-	}, {
-		.alg = "cfb(sm4)",
-		.test = alg_test_skcipher,
-		.suite = {
-			.cipher = __VECS(sm4_cfb_tv_template)
-		}
-	}, {
 		.alg = "chacha20",
 		.test = alg_test_skcipher,
 		.suite = {
@@ -4816,6 +4797,16 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "deflate-iaa",
+		.test = alg_test_comp,
+		.fips_allowed = 1,
+		.suite = {
+			.comp = {
+				.comp = __VECS(deflate_comp_tv_template),
+				.decomp = __VECS(deflate_decomp_tv_template)
+			}
+		}
+	}, {
 		.alg = "dh",
 		.test = alg_test_kpp,
 		.suite = {
@@ -4846,14 +4837,6 @@ static const struct alg_test_desc alg_test_descs[] = {
 			.drbg = __VECS(drbg_nopr_ctr_aes256_tv_template)
 		}
 	}, {
-		/*
-		 * There is no need to specifically test the DRBG with every
-		 * backend cipher -- covered by drbg_nopr_hmac_sha256 test
-		 */
-		.alg = "drbg_nopr_hmac_sha1",
-		.fips_allowed = 1,
-		.test = alg_test_null,
-	}, {
 		.alg = "drbg_nopr_hmac_sha256",
 		.test = alg_test_drbg,
 		.fips_allowed = 1,
@@ -4861,7 +4844,10 @@ static const struct alg_test_desc alg_test_descs[] = {
 			.drbg = __VECS(drbg_nopr_hmac_sha256_tv_template)
 		}
 	}, {
-		/* covered by drbg_nopr_hmac_sha256 test */
+		/*
+		 * There is no need to specifically test the DRBG with every
+		 * backend cipher -- covered by drbg_nopr_hmac_sha512 test
+		 */
 		.alg = "drbg_nopr_hmac_sha384",
 		.test = alg_test_null,
 	}, {
@@ -4872,10 +4858,6 @@ static const struct alg_test_desc alg_test_descs[] = {
 			.drbg = __VECS(drbg_nopr_hmac_sha512_tv_template)
 		}
 	}, {
-		.alg = "drbg_nopr_sha1",
-		.fips_allowed = 1,
-		.test = alg_test_null,
-	}, {
 		.alg = "drbg_nopr_sha256",
 		.test = alg_test_drbg,
 		.fips_allowed = 1,
@@ -4907,10 +4889,6 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.fips_allowed = 1,
 		.test = alg_test_null,
 	}, {
-		.alg = "drbg_pr_hmac_sha1",
-		.fips_allowed = 1,
-		.test = alg_test_null,
-	}, {
 		.alg = "drbg_pr_hmac_sha256",
 		.test = alg_test_drbg,
 		.fips_allowed = 1,
@@ -4926,10 +4904,6 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.test = alg_test_null,
 		.fips_allowed = 1,
 	}, {
-		.alg = "drbg_pr_sha1",
-		.fips_allowed = 1,
-		.test = alg_test_null,
-	}, {
 		.alg = "drbg_pr_sha256",
 		.test = alg_test_drbg,
 		.fips_allowed = 1,
@@ -5420,26 +5394,6 @@ static const struct alg_test_desc alg_test_descs[] = {
 			.hash = __VECS(nhpoly1305_tv_template)
 		}
 	}, {
-		.alg = "ofb(aes)",
-		.test = alg_test_skcipher,
-		.fips_allowed = 1,
-		.suite = {
-			.cipher = __VECS(aes_ofb_tv_template)
-		}
-	}, {
-		/* Same as ofb(aes) except the key is stored in
-		 * hardware secure memory which we reference by index
-		 */
-		.alg = "ofb(paes)",
-		.test = alg_test_null,
-		.fips_allowed = 1,
-	}, {
-		.alg = "ofb(sm4)",
-		.test = alg_test_skcipher,
-		.suite = {
-			.cipher = __VECS(sm4_ofb_tv_template)
-		}
-	}, {
 		.alg = "pcbc(fcrypt)",
 		.test = alg_test_skcipher,
 		.suite = {
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index d7e98397549b..986f331a5fc2 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -14704,104 +14704,6 @@ static const struct cipher_testvec sm4_ctr_rfc3686_tv_template[] = {
 	}
 };
 
-static const struct cipher_testvec sm4_ofb_tv_template[] = {
-	{ /* From: draft-ribose-cfrg-sm4-02, paragraph 12.2.3 */
-		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
-			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.klen	= 16,
-		.iv	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
-			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
-			  "\xfe\xdc\xba\x98\x76\x54\x32\x10"
-			  "\x01\x23\x45\x67\x89\xab\xcd\xef"
-			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.ctext	= "\x69\x3d\x9a\x53\x5b\xad\x5b\xb1"
-			  "\x78\x6f\x53\xd7\x25\x3a\x70\x56"
-			  "\xf2\x07\x5d\x28\xb5\x23\x5f\x58"
-			  "\xd5\x00\x27\xe4\x17\x7d\x2b\xce",
-		.len	= 32,
-	}, { /* From: draft-ribose-cfrg-sm4-09, appendix A.2.3, Example 1 */
-		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
-			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.klen	= 16,
-		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.ptext	= "\xaa\xaa\xaa\xaa\xbb\xbb\xbb\xbb"
-			  "\xcc\xcc\xcc\xcc\xdd\xdd\xdd\xdd"
-			  "\xee\xee\xee\xee\xff\xff\xff\xff"
-			  "\xaa\xaa\xaa\xaa\xbb\xbb\xbb\xbb",
-		.ctext	= "\xac\x32\x36\xcb\x86\x1d\xd3\x16"
-			  "\xe6\x41\x3b\x4e\x3c\x75\x24\xb7"
-			  "\x1d\x01\xac\xa2\x48\x7c\xa5\x82"
-			  "\xcb\xf5\x46\x3e\x66\x98\x53\x9b",
-		.len	= 32,
-	}, { /* From: draft-ribose-cfrg-sm4-09, appendix A.2.3, Example 2 */
-		.key	= "\xfe\xdc\xba\x98\x76\x54\x32\x10"
-			  "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.klen	= 16,
-		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.ptext	= "\xaa\xaa\xaa\xaa\xbb\xbb\xbb\xbb"
-			  "\xcc\xcc\xcc\xcc\xdd\xdd\xdd\xdd"
-			  "\xee\xee\xee\xee\xff\xff\xff\xff"
-			  "\xaa\xaa\xaa\xaa\xbb\xbb\xbb\xbb",
-		.ctext	= "\x5d\xcc\xcd\x25\xa8\x4b\xa1\x65"
-			  "\x60\xd7\xf2\x65\x88\x70\x68\x49"
-			  "\x33\xfa\x16\xbd\x5c\xd9\xc8\x56"
-			  "\xca\xca\xa1\xe1\x01\x89\x7a\x97",
-		.len	= 32,
-	}
-};
-
-static const struct cipher_testvec sm4_cfb_tv_template[] = {
-	{ /* From: draft-ribose-cfrg-sm4-02, paragraph 12.2.4 */
-		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
-			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.klen	= 16,
-		.iv	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
-			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
-			  "\xfe\xdc\xba\x98\x76\x54\x32\x10"
-			  "\x01\x23\x45\x67\x89\xab\xcd\xef"
-			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.ctext	= "\x69\x3d\x9a\x53\x5b\xad\x5b\xb1"
-			  "\x78\x6f\x53\xd7\x25\x3a\x70\x56"
-			  "\x9e\xd2\x58\xa8\x5a\x04\x67\xcc"
-			  "\x92\xaa\xb3\x93\xdd\x97\x89\x95",
-		.len	= 32,
-	}, { /* From: draft-ribose-cfrg-sm4-09, appendix A.2.4, Example 1 */
-		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
-			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.klen	= 16,
-		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.ptext	= "\xaa\xaa\xaa\xaa\xbb\xbb\xbb\xbb"
-			  "\xcc\xcc\xcc\xcc\xdd\xdd\xdd\xdd"
-			  "\xee\xee\xee\xee\xff\xff\xff\xff"
-			  "\xaa\xaa\xaa\xaa\xbb\xbb\xbb\xbb",
-		.ctext	= "\xac\x32\x36\xcb\x86\x1d\xd3\x16"
-			  "\xe6\x41\x3b\x4e\x3c\x75\x24\xb7"
-			  "\x69\xd4\xc5\x4e\xd4\x33\xb9\xa0"
-			  "\x34\x60\x09\xbe\xb3\x7b\x2b\x3f",
-		.len	= 32,
-	}, { /* From: draft-ribose-cfrg-sm4-09, appendix A.2.4, Example 2 */
-		.key	= "\xfe\xdc\xba\x98\x76\x54\x32\x10"
-			  "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.klen	= 16,
-		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.ptext	= "\xaa\xaa\xaa\xaa\xbb\xbb\xbb\xbb"
-			  "\xcc\xcc\xcc\xcc\xdd\xdd\xdd\xdd"
-			  "\xee\xee\xee\xee\xff\xff\xff\xff"
-			  "\xaa\xaa\xaa\xaa\xbb\xbb\xbb\xbb",
-		.ctext	= "\x5d\xcc\xcd\x25\xa8\x4b\xa1\x65"
-			  "\x60\xd7\xf2\x65\x88\x70\x68\x49"
-			  "\x0d\x9b\x86\xff\x20\xc3\xbf\xe1"
-			  "\x15\xff\xa0\x2c\xa6\x19\x2c\xc5",
-		.len	= 32,
-	}
-};
-
 static const struct cipher_testvec sm4_cts_tv_template[] = {
 	/* Generated from AES-CTS test vectors */
 	{
@@ -17064,104 +16966,6 @@ static const struct cipher_testvec aes_cbc_tv_template[] = {
 	},
 };
 
-static const struct cipher_testvec aes_cfb_tv_template[] = {
-	{ /* From NIST SP800-38A */
-		.key	= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
-			  "\xab\xf7\x15\x88\x09\xcf\x4f\x3c",
-		.klen	= 16,
-		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.ptext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
-			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
-			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
-			  "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51"
-			  "\x30\xc8\x1c\x46\xa3\x5c\xe4\x11"
-			  "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef"
-			  "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17"
-			  "\xad\x2b\x41\x7b\xe6\x6c\x37\x10",
-		.ctext	= "\x3b\x3f\xd9\x2e\xb7\x2d\xad\x20"
-			  "\x33\x34\x49\xf8\xe8\x3c\xfb\x4a"
-			  "\xc8\xa6\x45\x37\xa0\xb3\xa9\x3f"
-			  "\xcd\xe3\xcd\xad\x9f\x1c\xe5\x8b"
-			  "\x26\x75\x1f\x67\xa3\xcb\xb1\x40"
-			  "\xb1\x80\x8c\xf1\x87\xa4\xf4\xdf"
-			  "\xc0\x4b\x05\x35\x7c\x5d\x1c\x0e"
-			  "\xea\xc4\xc6\x6f\x9f\xf7\xf2\xe6",
-		.len	= 64,
-	}, {
-		.key	= "\x8e\x73\xb0\xf7\xda\x0e\x64\x52"
-			  "\xc8\x10\xf3\x2b\x80\x90\x79\xe5"
-			  "\x62\xf8\xea\xd2\x52\x2c\x6b\x7b",
-		.klen	= 24,
-		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.ptext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
-			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
-			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
-			  "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51"
-			  "\x30\xc8\x1c\x46\xa3\x5c\xe4\x11"
-			  "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef"
-			  "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17"
-			  "\xad\x2b\x41\x7b\xe6\x6c\x37\x10",
-		.ctext	= "\xcd\xc8\x0d\x6f\xdd\xf1\x8c\xab"
-			  "\x34\xc2\x59\x09\xc9\x9a\x41\x74"
-			  "\x67\xce\x7f\x7f\x81\x17\x36\x21"
-			  "\x96\x1a\x2b\x70\x17\x1d\x3d\x7a"
-			  "\x2e\x1e\x8a\x1d\xd5\x9b\x88\xb1"
-			  "\xc8\xe6\x0f\xed\x1e\xfa\xc4\xc9"
-			  "\xc0\x5f\x9f\x9c\xa9\x83\x4f\xa0"
-			  "\x42\xae\x8f\xba\x58\x4b\x09\xff",
-		.len	= 64,
-	}, {
-		.key	= "\x60\x3d\xeb\x10\x15\xca\x71\xbe"
-			  "\x2b\x73\xae\xf0\x85\x7d\x77\x81"
-			  "\x1f\x35\x2c\x07\x3b\x61\x08\xd7"
-			  "\x2d\x98\x10\xa3\x09\x14\xdf\xf4",
-		.klen	= 32,
-		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.ptext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
-			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
-			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
-			  "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51"
-			  "\x30\xc8\x1c\x46\xa3\x5c\xe4\x11"
-			  "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef"
-			  "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17"
-			  "\xad\x2b\x41\x7b\xe6\x6c\x37\x10",
-		.ctext	= "\xdc\x7e\x84\xbf\xda\x79\x16\x4b"
-			  "\x7e\xcd\x84\x86\x98\x5d\x38\x60"
-			  "\x39\xff\xed\x14\x3b\x28\xb1\xc8"
-			  "\x32\x11\x3c\x63\x31\xe5\x40\x7b"
-			  "\xdf\x10\x13\x24\x15\xe5\x4b\x92"
-			  "\xa1\x3e\xd0\xa8\x26\x7a\xe2\xf9"
-			  "\x75\xa3\x85\x74\x1a\xb9\xce\xf8"
-			  "\x20\x31\x62\x3d\x55\xb1\xe4\x71",
-		.len	= 64,
-	}, { /* > 16 bytes, not a multiple of 16 bytes */
-		.key	= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
-			  "\xab\xf7\x15\x88\x09\xcf\x4f\x3c",
-		.klen	= 16,
-		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.ptext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
-			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
-			  "\xae",
-		.ctext	= "\x3b\x3f\xd9\x2e\xb7\x2d\xad\x20"
-			  "\x33\x34\x49\xf8\xe8\x3c\xfb\x4a"
-			  "\xc8",
-		.len	= 17,
-	}, { /* < 16 bytes */
-		.key	= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
-			  "\xab\xf7\x15\x88\x09\xcf\x4f\x3c",
-		.klen	= 16,
-		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.ptext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f",
-		.ctext	= "\x3b\x3f\xd9\x2e\xb7\x2d\xad",
-		.len	= 7,
-	},
-};
-
 static const struct aead_testvec hmac_md5_ecb_cipher_null_tv_template[] = {
 	{ /* Input data from RFC 2410 Case 1 */
 #ifdef __LITTLE_ENDIAN
@@ -20852,55 +20656,6 @@ static const struct cipher_testvec aes_ctr_rfc3686_tv_template[] = {
 	},
 };
 
-static const struct cipher_testvec aes_ofb_tv_template[] = {
-	{ /* From NIST Special Publication 800-38A, Appendix F.5 */
-		.key	= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
-			  "\xab\xf7\x15\x88\x09\xcf\x4f\x3c",
-		.klen	= 16,
-		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07\x08"
-			  "\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.ptext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
-			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
-			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
-			  "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51"
-			  "\x30\xc8\x1c\x46\xa3\x5c\xe4\x11"
-			  "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef"
-			  "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17"
-			  "\xad\x2b\x41\x7b\xe6\x6c\x37\x10",
-		.ctext	= "\x3b\x3f\xd9\x2e\xb7\x2d\xad\x20"
-			  "\x33\x34\x49\xf8\xe8\x3c\xfb\x4a"
-			  "\x77\x89\x50\x8d\x16\x91\x8f\x03\xf5"
-			  "\x3c\x52\xda\xc5\x4e\xd8\x25"
-			  "\x97\x40\x05\x1e\x9c\x5f\xec\xf6\x43"
-			  "\x44\xf7\xa8\x22\x60\xed\xcc"
-			  "\x30\x4c\x65\x28\xf6\x59\xc7\x78"
-			  "\x66\xa5\x10\xd9\xc1\xd6\xae\x5e",
-		.len	= 64,
-	}, { /* > 16 bytes, not a multiple of 16 bytes */
-		.key	= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
-			  "\xab\xf7\x15\x88\x09\xcf\x4f\x3c",
-		.klen	= 16,
-		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.ptext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
-			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
-			  "\xae",
-		.ctext	= "\x3b\x3f\xd9\x2e\xb7\x2d\xad\x20"
-			  "\x33\x34\x49\xf8\xe8\x3c\xfb\x4a"
-			  "\x77",
-		.len	= 17,
-	}, { /* < 16 bytes */
-		.key	= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
-			  "\xab\xf7\x15\x88\x09\xcf\x4f\x3c",
-		.klen	= 16,
-		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.ptext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f",
-		.ctext	= "\x3b\x3f\xd9\x2e\xb7\x2d\xad",
-		.len	= 7,
-	}
-};
-
 static const struct aead_testvec aes_gcm_tv_template[] = {
 	{ /* From McGrew & Viega - http://citeseer.ist.psu.edu/656989.html */
 		.key    = zeroed_string,
@@ -29349,909 +29104,6 @@ static const struct cipher_testvec aria_ctr_tv_template[] = {
 	}
 };
 
-static const struct cipher_testvec aria_cfb_tv_template[] = {
-	{
-		.key	= "\x7f\x92\xd5\x06\x30\x6b\xc0\x23"
-			  "\x87\xa8\x8e\x6d\xc7\xc5\xd7\xf1",
-		.klen	= 16,
-		.iv	= "\x5f\xce\x89\xb3\xd5\x7f\x7f\xf0"
-			  "\xfd\xab\x56\xa6\x6e\xda\x7c\x57",
-		.ptext	= "\x36\x36\x89\x09\xcd\xa8\xd3\x91"
-			  "\x48\x3e\x3c\x11\xcf\xd0\x4f\xc0",
-		.ctext	= "\x19\x28\xb5\xf2\x1c\xbc\xf8\xaf"
-			  "\xb9\xae\x1b\x23\x4f\xe1\x6e\x40",
-	}, {
-		.key	= "\x51\xe3\x8c\xe9\x76\xcd\xff\x37"
-			  "\xd6\x1a\x18\x2f\x68\x2f\xb6\xfe",
-		.klen	= 16,
-		.iv	= "\x3d\x2d\x85\x75\x6e\x18\x8a\x52"
-			  "\x53\x39\xfc\xc1\xf5\xc0\x56\x22",
-		.ptext	= "\xc6\xae\xaa\x0d\x90\xf2\x38\x93"
-			  "\xac\xd2\x3f\xc7\x74\x8d\x13\x7e"
-			  "\xfa\x3f\x70\x52\xfb\x04\x0e\xed"
-			  "\x0e\x60\x75\x84\x21\xdf\x13\xa1",
-		.ctext	= "\x3f\x8c\xa9\x19\xd6\xb4\xfb\xed"
-			  "\x9c\x6d\xaa\x1b\xe1\xc1\xe6\xa8"
-			  "\x47\x35\x7d\xa3\x96\x7d\x53\x60"
-			  "\xa9\x33\x9c\x34\xae\x7d\x7c\x74",
-		.len	= 32,
-	}, {
-		.key	= "\x26\xf8\x8c\x26\x0a\x37\x51\x8f"
-			  "\xe7\x9c\x74\x77\x7a\x3e\xbb\x5d",
-		.klen	= 16,
-		.iv	= "\xd7\x33\xf3\xa9\x5b\xb4\x86\xea"
-			  "\xe3\x7d\x50\x62\x3b\x73\xaf\xc4",
-		.ptext	= "\xda\x89\xd9\x3c\xcc\xe4\x73\xb0"
-			  "\xef\x3e\x5f\x46\x62\x88\xd5\x26"
-			  "\x3b\xd3\xb5\x81\x78\x70\x1b\xd2"
-			  "\x39\x56\x34\x63\x2c\xc5\x51\x13"
-			  "\x48\x29\x3a\x58\xbe\x41\xc5\x80"
-			  "\x2c\x80\xa7\x3c\x14\xb4\x89\x5e",
-		.ctext	= "\x28\xd8\xa7\xf8\x74\x98\x00\xfc"
-			  "\xd6\x48\xad\xbd\xbe\x3f\x0e\x7b"
-			  "\xa3\xec\x03\x6a\xfb\xc9\x01\x83"
-			  "\xb3\x2f\xda\x5e\x66\xa0\xc3\xec"
-			  "\xe9\xd4\x72\x2a\xa2\x90\x41\xcf"
-			  "\xde\x30\x79\xc3\x82\x10\x51\xe1",
-		.len	= 48,
-	}, {
-		.key	= "\x8e\xe5\x5f\xe2\x39\x80\xf5\x2b"
-			  "\x77\xb5\xca\x90\xda\x1d\x22\x17",
-		.klen	= 16,
-		.iv	= "\xd9\xa0\x57\x80\xc8\x96\x70\x86"
-			  "\x07\x2c\xf4\x61\x79\x09\x01\x8f",
-		.ptext	= "\x37\x32\x98\xd4\x86\x2b\x3b\x80"
-			  "\x07\x60\xba\xf0\x2e\xc3\x4a\x57"
-			  "\xf5\xb5\xd7\xbf\xd2\x2a\x9b\x4a"
-			  "\xe6\x08\xf0\xbe\x77\xd1\x62\x40"
-			  "\xa0\x82\x09\x60\x47\xbb\x16\x56"
-			  "\x50\x1f\xab\x8b\x10\xfe\xf0\x5c"
-			  "\x05\x32\x63\x1a\xc4\x46\x6f\x55"
-			  "\x32\xde\x41\x5a\xf7\x52\xd7\xfa",
-		.ctext	= "\x29\x31\x55\xd2\xe5\x0b\x81\x39"
-			  "\xf9\xbc\x63\xe2\xfa\x26\x99\xde"
-			  "\x5c\xd3\x0a\x56\xe5\xfc\x83\xdd"
-			  "\xab\x26\x90\x7d\xa8\x0f\x01\xa6"
-			  "\x0e\x01\xdc\x1f\xfa\xa7\xdd\x09"
-			  "\xf9\xbf\x12\xf4\xc6\x9f\xbd\x57"
-			  "\x23\x68\x54\x0f\xe0\xcf\x1c\x6d"
-			  "\xe1\x5e\x0b\x4a\x1e\x71\x1d\xaa",
-		.len	= 64,
-	}, {
-		.key	= "\x30\x9d\x59\x8d\x64\x76\xad\x37"
-			  "\xba\xbc\x46\x6a\x69\x17\x3c\xac",
-		.klen	= 16,
-		.iv	= "\x6f\xdd\xa2\x9b\x86\x32\x14\x2e"
-			  "\x54\x74\x8f\x3d\xe2\xd6\x85\x44",
-		.ptext	= "\x4f\x4a\x31\x64\xc6\xa5\x29\xaa"
-			  "\xad\xfd\x32\x94\x1f\x56\x57\xd1"
-			  "\x9d\x7e\x3d\x49\x00\x36\xb1\x5d"
-			  "\xb2\x92\x83\x70\x1e\xa3\x97\xa6"
-			  "\x65\x53\x39\xeb\x53\x8f\xb1\x38"
-			  "\x91\xac\x17\x11\x1c\x03\x69\x53"
-			  "\xf5\xdf\xdb\x2c\x1b\x9a\x6e\x6b"
-			  "\xb6\x02\xc4\xfa\x95\x01\x33\xa8"
-			  "\xda\x7e\x18\x2c\xf4\x7e\x6e\x67"
-			  "\xce\x8f\x9f\xea\x46\x66\x99\xb8",
-		.ctext	= "\x38\xbc\xf5\x9d\x0e\x26\xa6\x18"
-			  "\x95\x0b\x23\x54\x09\xa1\xf9\x46"
-			  "\x7a\x31\xa0\xd7\x4a\xec\xb3\x10"
-			  "\x8a\x8e\x99\x78\x6c\x6e\x76\xf2"
-			  "\x63\x8a\x3b\x90\xaa\xd5\x64\x65"
-			  "\x5a\x52\xb0\x36\x4c\xce\xed\xc7"
-			  "\x51\x3c\x06\xb0\xee\x54\xec\x10"
-			  "\xc0\x5f\xfd\xa9\x44\x9a\x29\x32"
-			  "\x19\x79\x7d\x2b\x14\x26\x96\x13"
-			  "\x9d\xa5\x61\xbd\xb6\x72\x37\x26",
-		.len	= 80,
-	}, {
-		.key	= "\xe1\xc7\x25\x4d\xbd\xa5\x74\xdf"
-			  "\xc7\x8b\xfb\xe3\x2d\x3a\x82\xd3",
-		.klen	= 16,
-		.iv	= "\x17\x94\x77\x2f\x92\xb8\x87\xc2"
-			  "\xcc\x6f\x70\x26\x87\xc7\x10\x8a",
-		.ptext	= "\xc8\xfd\xc2\xb3\xcf\xa0\xeb\x41"
-			  "\x4c\xf4\xd0\x34\xd0\x95\xab\xae"
-			  "\x82\x5c\xfd\xfa\x13\x86\x25\xce"
-			  "\xf4\x13\x32\xcd\xc6\x6d\xf6\x50"
-			  "\x12\x4a\x5b\x66\x3a\xd3\xfb\x1a"
-			  "\xaf\x06\xea\xf4\x65\x59\xd6\xc2"
-			  "\x84\xa0\x53\x97\x61\x30\x70\x15"
-			  "\xac\x45\x8e\xe8\xeb\xa1\x72\x93"
-			  "\x26\x76\x98\x6f\xe4\x86\xca\xf0"
-			  "\x57\x89\xf2\x2b\xd4\xcf\x2d\x95"
-			  "\x86\x26\x20\x0e\x62\xfe\x8f\x1e"
-			  "\x5d\xcb\x2b\x7e\xdd\xab\xac\xda",
-		.ctext	= "\xdf\x79\x58\x30\x6f\x47\x12\x78"
-			  "\x04\xb2\x0b\x1a\x62\x22\xe2\x9f"
-			  "\xfe\x90\x50\x41\x1b\x6a\x6a\x9c"
-			  "\x4e\x77\x8f\xca\xd1\x68\x31\xcd"
-			  "\x41\x82\xa5\x5b\xc0\x08\x2b\x37"
-			  "\x62\xec\x95\xf1\x56\x12\x38\x66"
-			  "\x84\x82\x72\xda\x00\x21\x96\x82"
-			  "\x33\xd4\x99\xaa\xb9\xeb\xd5\xc3"
-			  "\x2b\xa8\xf7\xdc\x13\x0e\x21\x9f"
-			  "\x4b\xf9\x42\x58\xa8\x39\x10\xd5"
-			  "\x86\xa5\xc6\x78\x3b\x34\x05\x03"
-			  "\x54\x43\x2b\x80\xa9\x53\x4d\x0e",
-		.len	= 96,
-	}, {
-		.key	= "\x6e\x49\x20\xd5\xb7\x01\x83\x4e"
-			  "\xac\x45\x8f\xe1\x05\x3f\xd5\xb1",
-		.klen	= 16,
-		.iv	= "\xee\xb7\x0d\x65\x00\x38\xab\x71"
-			  "\x70\x6e\xb3\x97\x86\xd3\xcd\xad",
-		.ptext	= "\x51\x8b\x9c\xa0\x9a\x8b\x4c\xb9"
-			  "\x16\x01\x6a\x1f\xdf\xf0\xf9\x9e"
-			  "\x25\x1b\xc2\xa6\x21\x25\xeb\x97"
-			  "\x4b\xf6\xcb\x3b\xcd\x61\xfd\x94"
-			  "\x37\x03\xb3\xd9\x74\x6e\x4d\xbb"
-			  "\xfd\x87\x2b\xec\x4c\x2c\xbf\xe2"
-			  "\x94\x1a\xe6\xd9\xaf\x0e\x78\x17"
-			  "\x58\x2b\x1d\x73\x9a\x9c\x63\x18"
-			  "\x88\x7a\x0e\x87\x2f\xf0\xb0\xdb"
-			  "\xc9\x9d\x79\x51\x34\x39\x4f\x07"
-			  "\xa2\x7c\x21\x04\x91\x3b\x79\x79"
-			  "\xfe\xd5\x51\x46\xd5\xcd\x28\xc0"
-			  "\xad\xb8\x55\xb2\xb2\x5a\x9a\xa2"
-			  "\xe2\x0c\xfc\x55\x7d\x60\xd2\x95",
-		.ctext	= "\xe4\x25\x0d\x22\xeb\xbe\x5e\x90"
-			  "\x01\xe5\xae\xc9\x94\xbd\x93\x89"
-			  "\x5e\x5a\x5a\x2f\xf6\xdf\xf8\x16"
-			  "\xd3\xb2\xed\x29\x51\xe2\x75\xb0"
-			  "\x1a\x48\xb5\xe6\xd3\x58\x40\xc7"
-			  "\x6f\x6f\xcf\x57\x82\x43\x5a\x36"
-			  "\xef\x27\xe1\x34\x85\x01\xec\x98"
-			  "\x00\xbd\x94\x6f\x12\x39\xa8\x13"
-			  "\xfe\x3c\x39\xc0\xc6\xe1\xcc\x05"
-			  "\x0e\xd5\xc9\xda\xbd\xdd\xdb\xaa"
-			  "\x5a\xaa\x8e\xe8\xa8\x0a\xc5\x18"
-			  "\xb4\x1d\x13\x81\xc9\xc4\xaa\x61"
-			  "\xa9\xbd\xaa\x03\x12\x93\xbb\xed"
-			  "\x0c\x6e\xbd\x1c\x05\x16\x8a\x59",
-		.len	= 112,
-	}, {
-		.key	= "\xb6\x08\x1d\x31\xaf\xf4\x17\x46"
-			  "\xa4\xbb\x0f\xbd\x67\x3c\x73\x15",
-		.klen	= 16,
-		.iv	= "\x0c\x85\x2f\x62\xe5\xf4\x35\x96"
-			  "\xb1\x9b\x5d\x00\x10\xe9\x70\x12",
-		.ptext	= "\x3a\x87\x7f\x67\xf1\x81\x7a\x05"
-			  "\xb4\xa6\xfe\xdf\x36\x31\x6d\x9e"
-			  "\x0e\xa9\x44\xa0\xb0\x05\xa9\x41"
-			  "\x9c\x14\x44\x5a\xd5\x1c\x50\x08"
-			  "\x95\xc2\xf2\xaf\x3f\x29\xc9\x3e"
-			  "\x95\x5e\xc6\xb4\x2b\xf4\x3e\xe3"
-			  "\x1b\xeb\x3d\x73\xfb\xd7\x1e\x2b"
-			  "\x0c\x3d\x58\x6c\xb4\x41\x9b\xfe"
-			  "\x2f\x7e\x1c\x10\x81\x36\x2d\x79"
-			  "\xaf\xab\x10\x44\x2e\xcc\x0d\x6c"
-			  "\x9c\x14\xc2\xe4\xae\xb0\xbb\xda"
-			  "\x6a\xe0\x42\x3d\x96\x9f\x78\x7d"
-			  "\x70\x86\xa5\x92\x9f\xee\xcd\x3f"
-			  "\x6a\x55\x84\x98\x28\x03\x02\xc2"
-			  "\xf7\xec\x7a\xfa\xb1\xd9\xa8\xd8"
-			  "\x1c\xc3\xaa\xd5\x61\x7f\x10\x0c",
-		.ctext	= "\xa7\x4c\x96\x55\x7c\x07\xce\xb2"
-			  "\x6f\x63\x9f\xc6\x8b\x6f\xc6\x4a"
-			  "\x85\xf2\x4b\xdf\x62\x0c\x6c\x8d"
-			  "\x13\x5d\xd3\x40\x58\xa6\xf9\x03"
-			  "\xd9\xf2\x48\x4e\x12\x64\x9a\x55"
-			  "\xa2\xa3\xd0\x19\xe5\x5b\xaa\x62"
-			  "\x7b\xe9\x2a\x23\xab\xb5\xa6\xcf"
-			  "\x53\x59\x70\xc6\xb8\x92\x12\x3b"
-			  "\x93\x68\x24\xba\x7d\xd6\xc0\x5b"
-			  "\x06\x2e\x7f\x2e\x32\x5d\x42\x9c"
-			  "\x13\x8e\x92\x3c\x99\x20\x32\x2b"
-			  "\x4a\x41\xb2\x4a\x81\xe8\x6e\x7f"
-			  "\x5b\x8e\xca\x4d\xd7\x29\x96\xde"
-			  "\x30\x9c\xa6\x84\x90\xe7\xc2\xae"
-			  "\xf4\x7e\x73\x32\x4c\x25\xec\xef"
-			  "\x58\x69\x63\x3f\x4e\x71\x4b\x1c",
-		.len	= 128,
-	}, {
-		.key	= "\xc0\xa1\x36\x3d\x81\x9a\xd2\x17"
-			  "\x2e\x23\xc9\xb7\xff\xdf\x47\x6c",
-		.klen	= 16,
-		.iv	= "\x96\x3b\x0e\xbd\xec\x9a\x0e\xad"
-			  "\x8c\xaf\x36\x3d\xff\x29\x8b\x33",
-		.ptext	= "\x87\x96\x77\x1a\x10\x81\x63\x8a"
-			  "\x63\xde\x88\xa9\x9d\xa9\x01\xf2"
-			  "\xdf\xc9\x25\x35\x48\x3a\x15\xdf"
-			  "\x20\x6b\x91\x7c\x56\xe5\x10\x7a"
-			  "\x2d\x2e\x0f\x30\x32\xed\xa9\x1f"
-			  "\x71\x4e\x68\x77\xe8\xa8\x5b\xdd"
-			  "\x3c\x5e\x68\x6b\xab\x03\xe4\xf8"
-			  "\x42\xc1\x61\x9a\x50\xfb\xc7\x6a"
-			  "\x1a\x31\xa7\x87\xd0\x24\xcb\x5e"
-			  "\xc0\x3b\x12\x28\xca\x26\x7b\xb3"
-			  "\x14\xc1\x7f\x66\xff\x3b\xa4\x80"
-			  "\x59\x77\x4f\xa0\xd4\xb2\xd9\x8a"
-			  "\xb6\x67\xe6\x28\xd3\x6f\xf2\xcf"
-			  "\xb8\x6d\x2d\xc4\x2a\x69\x89\xff"
-			  "\xcf\xbb\x11\x2e\x2a\x2b\x7c\xfd"
-			  "\xcd\x56\x02\x95\xc9\x54\x6e\x62"
-			  "\x6a\x97\x75\x1a\x21\x16\x46\xfb"
-			  "\xc2\xab\x62\x54\xef\xba\xae\x46",
-		.ctext	= "\x11\x7f\xea\x49\xaf\x24\x52\xa2"
-			  "\xde\x60\x99\x58\x23\xf9\x9e\x91"
-			  "\x94\x52\x31\xa3\x28\x07\x14\xad"
-			  "\x00\x24\x4a\x4a\xe7\x18\xd7\x24"
-			  "\xcc\x8b\x66\x53\x82\x65\x31\xa5"
-			  "\x54\x76\x59\x0b\x69\x6f\x90\x2c"
-			  "\x8d\xa5\x2b\x61\x05\x80\xfb\xe0"
-			  "\xf9\x6e\xaf\xb9\xc4\x15\x67\xcc"
-			  "\x15\xce\xa0\xc0\xf2\xae\xa6\x15"
-			  "\x24\x9a\xe5\xcb\x09\x42\xcf\x41"
-			  "\x95\xa4\x8d\xbf\xe8\xb8\x40\xcd"
-			  "\xb0\x33\x2c\xb3\xc4\xdd\xf9\x45"
-			  "\xda\xb2\xeb\xb3\xf8\xfa\x7f\xe3"
-			  "\xc0\x3a\x98\xe7\x17\x4a\x0c\x60"
-			  "\xb2\x22\xba\x3b\x21\x85\x27\x56"
-			  "\xe0\xb2\xf7\x2a\x59\xb1\x56\x20"
-			  "\x0b\xa9\x13\x73\xe0\x6f\x61\x32"
-			  "\xa5\x38\x14\xb3\xe3\xaa\x70\x44",
-		.len	= 144,
-	}, {
-		.key	= "\xd4\x14\xc6\xcc\x16\x1b\x95\xf9"
-			  "\x05\x26\x23\x81\x19\x27\xad\x7b",
-		.klen	= 16,
-		.iv	= "\x9c\x8b\xfb\x65\xa4\x61\xee\x69"
-			  "\x44\xbf\x59\xde\x03\x61\x11\x12",
-		.ptext	= "\x8d\x94\x48\x47\xa9\x52\x16\xfb"
-			  "\x6b\xaf\x59\x6d\xab\x74\xbf\x5c"
-			  "\xb6\x09\x21\x12\x42\x98\x13\xa1"
-			  "\xa8\x6f\xb9\x6d\x4d\xa6\xdc\xea"
-			  "\x61\x02\x3c\xa7\xcd\x1a\x28\x8c"
-			  "\x66\xb8\x4d\x60\x67\x82\xcc\x8d"
-			  "\x1e\xda\x8f\x28\xe5\x02\xdc\x2c"
-			  "\x54\x84\x2a\x06\xb5\xd1\x34\x57"
-			  "\xb8\x28\x4d\xf5\x69\xb9\xf3\x33"
-			  "\x5e\x0b\xa6\x62\x35\x9b\xfb\x97"
-			  "\x3e\xc6\xec\xaf\x74\xe8\x72\x91"
-			  "\xb2\xc6\x56\xb3\x23\x29\x43\xe0"
-			  "\xfb\xcc\x21\x38\x64\x78\x9e\x78"
-			  "\xbb\x6e\x0d\x7b\xfd\x05\x74\x01"
-			  "\x7c\x94\xe0\xb0\xd7\x92\xfc\x58"
-			  "\x28\xfc\xe2\x7b\x7f\xf7\x31\x0d"
-			  "\x90\xb7\x60\x78\xa8\x9f\x52\xe3"
-			  "\xe6\xaa\x2a\xb4\xa7\x09\x60\x53"
-			  "\x42\x0e\x15\x31\xf6\x48\xa3\x0a"
-			  "\x20\xf0\x79\x67\xb1\x83\x26\x66",
-		.ctext	= "\x5b\xc0\xe8\x17\xa4\xf9\xea\xce"
-			  "\x9e\xf9\xe0\xb1\xac\x37\xe9\x41"
-			  "\xc8\x06\xf9\x1c\x1a\xfc\xe8\x7a"
-			  "\x38\xf2\x80\x66\xc2\x70\x59\x4e"
-			  "\xe0\x32\x5b\x27\x39\xf5\xfb\x03"
-			  "\xc8\xaf\xd6\x7e\x57\xc7\xc6\x71"
-			  "\xd9\xd0\x48\x39\xb1\x0d\xa8\x1a"
-			  "\x23\x8a\x3d\x05\xe2\x90\x7e\x18"
-			  "\xd7\x20\x04\x3b\x82\x76\x3f\xaa"
-			  "\xc2\x89\xb6\x9e\x14\x2f\x46\xcd"
-			  "\x51\x9b\xa8\x7b\x62\x7b\x9c\x17"
-			  "\xc4\xe1\x8b\x3f\xb5\x4d\xac\x66"
-			  "\x49\xf6\xb6\x4c\x3e\x16\x46\xb0"
-			  "\xca\x04\xef\x72\x5c\x03\x0a\xe5"
-			  "\x2f\x4e\x36\x38\x36\x9f\xf4\xe2"
-			  "\x81\x7a\x4c\xdf\x36\x27\xd5\x9d"
-			  "\x03\xad\x1d\x3a\xe9\x2a\x99\xb0"
-			  "\x2c\xba\x13\x75\xc8\x37\x97\x11"
-			  "\xf4\x15\x0f\xb7\x75\x26\xa1\x14"
-			  "\x79\xec\x1f\xab\xd2\x10\x8c\x5f",
-		.len	= 160,
-	}, {
-		.key	= "\x7f\x92\xd5\x06\x30\x6b\xc0\x23"
-			  "\x87\xa8\x8e\x6d\xc7\xc5\xd7\xf1"
-			  "\x5f\xce\x89\xb3\xd5\x7f\x7f\xf0",
-		.klen	= 24,
-		.iv	= "\xfd\xab\x56\xa6\x6e\xda\x7c\x57"
-			  "\x36\x36\x89\x09\xcd\xa8\xd3\x91",
-		.ptext	= "\x48\x3e\x3c\x11\xcf\xd0\x4f\xc0"
-			  "\x51\xe3\x8c\xe9\x76\xcd\xff\x37",
-		.ctext	= "\xa4\x12\x2f\xc4\xf0\x6d\xd9\x46"
-			  "\xe4\xe6\xd1\x0b\x6d\x14\xf0\x8f",
-		.len	= 16,
-	}, {
-		.key	= "\xd6\x1a\x18\x2f\x68\x2f\xb6\xfe"
-			  "\x3d\x2d\x85\x75\x6e\x18\x8a\x52"
-			  "\x53\x39\xfc\xc1\xf5\xc0\x56\x22",
-		.klen	= 24,
-		.iv	= "\xc6\xae\xaa\x0d\x90\xf2\x38\x93"
-			  "\xac\xd2\x3f\xc7\x74\x8d\x13\x7e",
-		.ptext	= "\xfa\x3f\x70\x52\xfb\x04\x0e\xed"
-			  "\x0e\x60\x75\x84\x21\xdf\x13\xa1"
-			  "\x26\xf8\x8c\x26\x0a\x37\x51\x8f"
-			  "\xe7\x9c\x74\x77\x7a\x3e\xbb\x5d",
-		.ctext	= "\x80\x2b\xf0\x88\xb9\x4b\x8d\xf5"
-			  "\xc3\x0e\x15\x5b\xea\x5d\x5b\xa8"
-			  "\x52\xe7\x83\x3c\xa1\x51\x1c\x1f"
-			  "\x38\xd9\x7c\x88\x3c\x3a\xcd\x3e",
-		.len	= 32,
-	}, {
-		.key	= "\xd7\x33\xf3\xa9\x5b\xb4\x86\xea"
-			  "\xe3\x7d\x50\x62\x3b\x73\xaf\xc4"
-			  "\xda\x89\xd9\x3c\xcc\xe4\x73\xb0",
-		.klen	= 24,
-		.iv	= "\xef\x3e\x5f\x46\x62\x88\xd5\x26"
-			  "\x3b\xd3\xb5\x81\x78\x70\x1b\xd2",
-		.ptext	= "\x39\x56\x34\x63\x2c\xc5\x51\x13"
-			  "\x48\x29\x3a\x58\xbe\x41\xc5\x80"
-			  "\x2c\x80\xa7\x3c\x14\xb4\x89\x5e"
-			  "\x8e\xe5\x5f\xe2\x39\x80\xf5\x2b"
-			  "\x77\xb5\xca\x90\xda\x1d\x22\x17"
-			  "\xd9\xa0\x57\x80\xc8\x96\x70\x86",
-		.ctext	= "\x65\x01\x3c\xb0\xac\x4c\x63\xb6"
-			  "\xe7\xf1\xf4\x61\x35\xf4\x36\xde"
-			  "\xeb\x0f\x8c\x34\xd1\x78\xb4\x00"
-			  "\xb2\xc1\x7c\x28\xb2\xb7\xbb\xa3"
-			  "\xc6\xb7\x27\xf7\x6d\x56\x79\xfa"
-			  "\x61\x57\xba\x30\x6f\x56\xe9\x8c",
-		.len	= 48,
-	}, {
-		.key	= "\x07\x2c\xf4\x61\x79\x09\x01\x8f"
-			  "\x37\x32\x98\xd4\x86\x2b\x3b\x80"
-			  "\x07\x60\xba\xf0\x2e\xc3\x4a\x57",
-		.klen	= 24,
-		.iv	= "\xf5\xb5\xd7\xbf\xd2\x2a\x9b\x4a"
-			  "\xe6\x08\xf0\xbe\x77\xd1\x62\x40",
-		.ptext	= "\xa0\x82\x09\x60\x47\xbb\x16\x56"
-			  "\x50\x1f\xab\x8b\x10\xfe\xf0\x5c"
-			  "\x05\x32\x63\x1a\xc4\x46\x6f\x55"
-			  "\x32\xde\x41\x5a\xf7\x52\xd7\xfa"
-			  "\x30\x9d\x59\x8d\x64\x76\xad\x37"
-			  "\xba\xbc\x46\x6a\x69\x17\x3c\xac"
-			  "\x6f\xdd\xa2\x9b\x86\x32\x14\x2e"
-			  "\x54\x74\x8f\x3d\xe2\xd6\x85\x44",
-		.ctext	= "\x5a\xfb\xb1\x2c\x6e\xe5\xb8\xe0"
-			  "\x80\xb6\x77\xa8\xfe\x10\x3a\x99"
-			  "\xbf\xc0\x2a\xfe\x6f\x38\xf2\x1d"
-			  "\x53\x6c\x05\x83\xb1\x13\x00\x87"
-			  "\x92\x92\x42\x70\xcf\x9f\xf7\x8f"
-			  "\x53\x55\x18\x6f\x35\x68\x35\x50"
-			  "\x3a\xc8\x45\x3e\xa3\xf1\x33\x2e"
-			  "\xa1\x65\x42\xe2\x6d\x31\x8c\x4b",
-		.len	= 64,
-	}, {
-		.key	= "\x4f\x4a\x31\x64\xc6\xa5\x29\xaa"
-			  "\xad\xfd\x32\x94\x1f\x56\x57\xd1"
-			  "\x9d\x7e\x3d\x49\x00\x36\xb1\x5d",
-		.klen	= 24,
-		.iv	= "\xb2\x92\x83\x70\x1e\xa3\x97\xa6"
-			  "\x65\x53\x39\xeb\x53\x8f\xb1\x38",
-		.ptext	= "\x91\xac\x17\x11\x1c\x03\x69\x53"
-			  "\xf5\xdf\xdb\x2c\x1b\x9a\x6e\x6b"
-			  "\xb6\x02\xc4\xfa\x95\x01\x33\xa8"
-			  "\xda\x7e\x18\x2c\xf4\x7e\x6e\x67"
-			  "\xce\x8f\x9f\xea\x46\x66\x99\xb8"
-			  "\xe1\xc7\x25\x4d\xbd\xa5\x74\xdf"
-			  "\xc7\x8b\xfb\xe3\x2d\x3a\x82\xd3"
-			  "\x17\x94\x77\x2f\x92\xb8\x87\xc2"
-			  "\xcc\x6f\x70\x26\x87\xc7\x10\x8a"
-			  "\xc8\xfd\xc2\xb3\xcf\xa0\xeb\x41",
-		.ctext	= "\xc9\x5f\xe0\x60\x61\x38\x7e\x79"
-			  "\x52\x68\x64\x8f\x55\x9b\x6b\x72"
-			  "\xa5\x17\x61\xb7\xce\x02\xa9\xa4"
-			  "\x5c\x73\x45\x33\xd1\x07\x5e\xdc"
-			  "\xe5\xbe\xa7\xde\x69\xa0\x97\x98"
-			  "\x02\xef\xa4\x67\x51\x60\x69\x4f"
-			  "\x03\xf5\xa8\x5f\x03\x69\xbc\xc2"
-			  "\x34\x59\x7e\xd4\xd2\xb3\x32\x2f"
-			  "\x0c\xb4\x37\xca\xc4\xc7\x93\xf4"
-			  "\xa4\xab\x01\x3f\x91\x29\x55\x98",
-		.len	= 80,
-	}, {
-		.key	= "\x4c\xf4\xd0\x34\xd0\x95\xab\xae"
-			  "\x82\x5c\xfd\xfa\x13\x86\x25\xce"
-			  "\xf4\x13\x32\xcd\xc6\x6d\xf6\x50",
-		.klen	= 24,
-		.iv	= "\x12\x4a\x5b\x66\x3a\xd3\xfb\x1a"
-			  "\xaf\x06\xea\xf4\x65\x59\xd6\xc2",
-		.ptext	= "\x84\xa0\x53\x97\x61\x30\x70\x15"
-			  "\xac\x45\x8e\xe8\xeb\xa1\x72\x93"
-			  "\x26\x76\x98\x6f\xe4\x86\xca\xf0"
-			  "\x57\x89\xf2\x2b\xd4\xcf\x2d\x95"
-			  "\x86\x26\x20\x0e\x62\xfe\x8f\x1e"
-			  "\x5d\xcb\x2b\x7e\xdd\xab\xac\xda"
-			  "\x6e\x49\x20\xd5\xb7\x01\x83\x4e"
-			  "\xac\x45\x8f\xe1\x05\x3f\xd5\xb1"
-			  "\xee\xb7\x0d\x65\x00\x38\xab\x71"
-			  "\x70\x6e\xb3\x97\x86\xd3\xcd\xad"
-			  "\x51\x8b\x9c\xa0\x9a\x8b\x4c\xb9"
-			  "\x16\x01\x6a\x1f\xdf\xf0\xf9\x9e",
-		.ctext	= "\x03\x2c\x39\x24\x99\xb5\xf6\x79"
-			  "\x91\x89\xb7\xf8\x89\x68\x37\x9d"
-			  "\xa2\x80\x95\x74\x87\x64\xb9\xeb"
-			  "\x85\x28\x92\x9a\x6e\xd3\x3b\x50"
-			  "\x4c\x80\x5b\xe4\xf2\x7e\xda\x2a"
-			  "\xd4\xf8\xcb\xe3\x6f\xdf\xae\x0e"
-			  "\xc5\x6c\x0b\x49\x2e\x29\x1c\xf2"
-			  "\x3f\x44\x44\x12\x67\xa6\xff\x44"
-			  "\xe0\xec\xd8\xf7\x32\xde\x21\x15"
-			  "\xab\x8f\x98\x4d\xed\xb0\x42\xfd"
-			  "\x83\x94\xe2\xcc\x69\x6d\xe8\xdb"
-			  "\x62\x93\x1f\xd0\xf4\x8c\x62\xc0",
-		.len	= 96,
-	}, {
-		.key	= "\x25\x1b\xc2\xa6\x21\x25\xeb\x97"
-			  "\x4b\xf6\xcb\x3b\xcd\x61\xfd\x94"
-			  "\x37\x03\xb3\xd9\x74\x6e\x4d\xbb",
-		.klen	= 24,
-		.iv	= "\xfd\x87\x2b\xec\x4c\x2c\xbf\xe2"
-			  "\x94\x1a\xe6\xd9\xaf\x0e\x78\x17",
-		.ptext	= "\x58\x2b\x1d\x73\x9a\x9c\x63\x18"
-			  "\x88\x7a\x0e\x87\x2f\xf0\xb0\xdb"
-			  "\xc9\x9d\x79\x51\x34\x39\x4f\x07"
-			  "\xa2\x7c\x21\x04\x91\x3b\x79\x79"
-			  "\xfe\xd5\x51\x46\xd5\xcd\x28\xc0"
-			  "\xad\xb8\x55\xb2\xb2\x5a\x9a\xa2"
-			  "\xe2\x0c\xfc\x55\x7d\x60\xd2\x95"
-			  "\xb6\x08\x1d\x31\xaf\xf4\x17\x46"
-			  "\xa4\xbb\x0f\xbd\x67\x3c\x73\x15"
-			  "\x0c\x85\x2f\x62\xe5\xf4\x35\x96"
-			  "\xb1\x9b\x5d\x00\x10\xe9\x70\x12"
-			  "\x3a\x87\x7f\x67\xf1\x81\x7a\x05"
-			  "\xb4\xa6\xfe\xdf\x36\x31\x6d\x9e"
-			  "\x0e\xa9\x44\xa0\xb0\x05\xa9\x41",
-		.ctext	= "\xd4\x9a\x04\x54\x05\xd2\xe6\x3f"
-			  "\xb0\xa4\x36\x5e\x1e\x9c\x35\xb0"
-			  "\xc0\x89\xbd\x1c\xaa\x45\xa6\xc8"
-			  "\x16\x68\x4a\x06\x93\x67\x88\xd7"
-			  "\x72\x6e\x48\x0a\x17\xa3\x52\x8b"
-			  "\x96\x5f\x41\xf6\x17\x64\x55\x8b"
-			  "\xac\xce\xf6\x8c\xce\xd2\xd4\xd4"
-			  "\x8d\x92\x32\xe0\x0d\xb4\xf7\x4a"
-			  "\x90\xaf\x7b\x85\x21\x46\x2e\xa6"
-			  "\x9e\xac\x0d\x22\xf2\x26\xf6\xd3"
-			  "\x27\xcd\x59\xa0\xe2\xbb\x22\xcd"
-			  "\x35\xb6\x28\x45\x0a\x46\xb0\x3a"
-			  "\xac\x3e\xd3\x5b\xc6\x54\xa2\xa3"
-			  "\x6d\xbb\xb3\xcd\xc5\x64\x62\x92",
-		.len	= 112,
-	}, {
-		.key	= "\x9c\x14\x44\x5a\xd5\x1c\x50\x08"
-			  "\x95\xc2\xf2\xaf\x3f\x29\xc9\x3e"
-			  "\x95\x5e\xc6\xb4\x2b\xf4\x3e\xe3",
-		.klen	= 24,
-		.iv	= "\x1b\xeb\x3d\x73\xfb\xd7\x1e\x2b"
-			  "\x0c\x3d\x58\x6c\xb4\x41\x9b\xfe",
-		.ptext	= "\x2f\x7e\x1c\x10\x81\x36\x2d\x79"
-			  "\xaf\xab\x10\x44\x2e\xcc\x0d\x6c"
-			  "\x9c\x14\xc2\xe4\xae\xb0\xbb\xda"
-			  "\x6a\xe0\x42\x3d\x96\x9f\x78\x7d"
-			  "\x70\x86\xa5\x92\x9f\xee\xcd\x3f"
-			  "\x6a\x55\x84\x98\x28\x03\x02\xc2"
-			  "\xf7\xec\x7a\xfa\xb1\xd9\xa8\xd8"
-			  "\x1c\xc3\xaa\xd5\x61\x7f\x10\x0c"
-			  "\xc0\xa1\x36\x3d\x81\x9a\xd2\x17"
-			  "\x2e\x23\xc9\xb7\xff\xdf\x47\x6c"
-			  "\x96\x3b\x0e\xbd\xec\x9a\x0e\xad"
-			  "\x8c\xaf\x36\x3d\xff\x29\x8b\x33"
-			  "\x87\x96\x77\x1a\x10\x81\x63\x8a"
-			  "\x63\xde\x88\xa9\x9d\xa9\x01\xf2"
-			  "\xdf\xc9\x25\x35\x48\x3a\x15\xdf"
-			  "\x20\x6b\x91\x7c\x56\xe5\x10\x7a",
-		.ctext	= "\xbc\x57\x2a\x88\x0a\xd0\x06\x4f"
-			  "\xdb\x7b\x03\x9f\x97\x1a\x20\xfe"
-			  "\x15\x91\xb4\xed\x5d\x78\x89\x2a"
-			  "\x67\x6b\x9c\x47\x36\xc2\x80\x0e"
-			  "\x03\x8d\x6f\xfc\x94\xc7\xc5\xc2"
-			  "\xeb\x43\x74\x5d\xfe\xc4\x5a\xa1"
-			  "\x80\x51\x8a\x63\xd1\x27\x1b\x0a"
-			  "\x88\x2c\xc4\x7f\x1a\xa3\x28\xe5"
-			  "\xfd\xd0\x8a\xd4\x36\xa6\x19\xd5"
-			  "\xff\x41\x7a\x8b\x6e\x9a\x97\x14"
-			  "\x2a\xc8\xd0\xb8\xa3\x8e\x64\x32"
-			  "\xb7\x2d\x76\x9b\x3b\xe2\x3f\x91"
-			  "\xb4\x64\xbf\x59\x67\x14\xc3\xf5"
-			  "\xa8\x92\x4b\x85\xdf\x80\xcb\xb5"
-			  "\xc7\x80\xf9\x4a\xbc\xed\x67\x5a"
-			  "\x0b\x58\x65\x1f\xc9\x6e\x9b\x0a",
-		.len	= 128,
-	}, {
-		.key	= "\x2d\x2e\x0f\x30\x32\xed\xa9\x1f"
-			  "\x71\x4e\x68\x77\xe8\xa8\x5b\xdd"
-			  "\x3c\x5e\x68\x6b\xab\x03\xe4\xf8",
-		.klen	= 24,
-		.iv	= "\x42\xc1\x61\x9a\x50\xfb\xc7\x6a"
-			  "\x1a\x31\xa7\x87\xd0\x24\xcb\x5e",
-		.ptext	= "\xc0\x3b\x12\x28\xca\x26\x7b\xb3"
-			  "\x14\xc1\x7f\x66\xff\x3b\xa4\x80"
-			  "\x59\x77\x4f\xa0\xd4\xb2\xd9\x8a"
-			  "\xb6\x67\xe6\x28\xd3\x6f\xf2\xcf"
-			  "\xb8\x6d\x2d\xc4\x2a\x69\x89\xff"
-			  "\xcf\xbb\x11\x2e\x2a\x2b\x7c\xfd"
-			  "\xcd\x56\x02\x95\xc9\x54\x6e\x62"
-			  "\x6a\x97\x75\x1a\x21\x16\x46\xfb"
-			  "\xc2\xab\x62\x54\xef\xba\xae\x46"
-			  "\xd4\x14\xc6\xcc\x16\x1b\x95\xf9"
-			  "\x05\x26\x23\x81\x19\x27\xad\x7b"
-			  "\x9c\x8b\xfb\x65\xa4\x61\xee\x69"
-			  "\x44\xbf\x59\xde\x03\x61\x11\x12"
-			  "\x8d\x94\x48\x47\xa9\x52\x16\xfb"
-			  "\x6b\xaf\x59\x6d\xab\x74\xbf\x5c"
-			  "\xb6\x09\x21\x12\x42\x98\x13\xa1"
-			  "\xa8\x6f\xb9\x6d\x4d\xa6\xdc\xea"
-			  "\x61\x02\x3c\xa7\xcd\x1a\x28\x8c",
-		.ctext	= "\xd7\xb4\xfc\xcc\x1f\xf7\xfc\x7d"
-			  "\x69\xfa\xcb\x01\x60\xf3\x5a\x14"
-			  "\xfe\x8c\x4e\xfa\x09\xb5\x0d\xda"
-			  "\xff\xdd\xba\xdf\xa3\x6b\x3a\x87"
-			  "\x21\xbb\xf8\x62\x14\x22\xdd\x9b"
-			  "\x92\x23\xaa\xd7\xcc\xb2\x15\xd0"
-			  "\xbd\x81\x95\x24\xc2\xc6\x53\x5b"
-			  "\xf7\x3c\xa0\xf7\x36\xbc\xbf\xf3"
-			  "\xfc\x1c\x6e\xe0\x71\x8d\xa1\x3d"
-			  "\x8e\x1a\xc5\xba\xd5\x68\xd4\x7a"
-			  "\xe0\x4f\x0a\x14\x89\x0b\xa6\x2f"
-			  "\x18\xc5\x38\x76\xf1\xe7\x5c\xae"
-			  "\x7a\xbb\x27\x1c\xf0\x7c\x6c\x14"
-			  "\x07\xb7\x49\x6e\x29\x04\x38\x31"
-			  "\x91\xe8\x1d\x0f\xfc\x3b\xb8\x20"
-			  "\x58\x64\x11\xa1\xf5\xba\xa3\x62"
-			  "\x92\xcf\x44\x63\x2c\xe8\x10\xb5"
-			  "\xf0\x97\x86\xcb\x5f\xc1\x80\x7a",
-		.len	= 144,
-	}, {
-		.key	= "\x66\xb8\x4d\x60\x67\x82\xcc\x8d"
-			  "\x1e\xda\x8f\x28\xe5\x02\xdc\x2c"
-			  "\x54\x84\x2a\x06\xb5\xd1\x34\x57",
-		.klen	= 24,
-		.iv	= "\xb8\x28\x4d\xf5\x69\xb9\xf3\x33"
-			  "\x5e\x0b\xa6\x62\x35\x9b\xfb\x97",
-		.ptext	= "\x3e\xc6\xec\xaf\x74\xe8\x72\x91"
-			  "\xb2\xc6\x56\xb3\x23\x29\x43\xe0"
-			  "\xfb\xcc\x21\x38\x64\x78\x9e\x78"
-			  "\xbb\x6e\x0d\x7b\xfd\x05\x74\x01"
-			  "\x7c\x94\xe0\xb0\xd7\x92\xfc\x58"
-			  "\x28\xfc\xe2\x7b\x7f\xf7\x31\x0d"
-			  "\x90\xb7\x60\x78\xa8\x9f\x52\xe3"
-			  "\xe6\xaa\x2a\xb4\xa7\x09\x60\x53"
-			  "\x42\x0e\x15\x31\xf6\x48\xa3\x0a"
-			  "\x20\xf0\x79\x67\xb1\x83\x26\x66"
-			  "\xe0\xb1\xb3\xbd\x1c\x76\x36\xfd"
-			  "\x45\x87\xa4\x14\x1b\xef\xe7\x16"
-			  "\xf7\xfa\x30\x3d\xb9\x52\x8f\x2e"
-			  "\x01\x68\xc1\x7d\xa2\x15\x49\x74"
-			  "\x53\x82\xc2\x10\xa8\x45\x73\x4d"
-			  "\x41\xcc\x24\xa3\x42\xff\x30\xd1"
-			  "\x02\x21\xdc\xd9\x08\xf7\xe7\x4c"
-			  "\x33\x2d\x62\xc7\x38\xf5\xc2\xbe"
-			  "\x52\xf1\x34\x78\x34\x53\x30\x5b"
-			  "\x43\x43\x51\x6a\x02\x81\x64\x0c",
-		.ctext	= "\x71\xf6\x96\x02\x07\x71\x1a\x08"
-			  "\x7c\xfe\x33\xc4\xc9\xbe\xe2\xed"
-			  "\xd0\xcc\x5d\x27\x75\xb4\x5d\x8d"
-			  "\x24\x03\xe4\x96\x31\x94\x0e\x38"
-			  "\x14\x4f\xad\x16\x58\x0d\x73\xdc"
-			  "\xbe\x5b\xcb\x38\xeb\x4d\xbc\x9a"
-			  "\x44\x69\x7a\x12\x91\x14\x52\xfa"
-			  "\xd2\xa2\xc5\x66\xd7\xaf\x4d\xb9"
-			  "\xb1\x58\x24\x10\xde\x6a\xee\x7e"
-			  "\x45\xf3\x76\xea\x47\x8a\xe6\x96"
-			  "\x41\xf2\x96\x2d\x3c\xec\xcf\xc6"
-			  "\x1d\xf4\x26\xc0\xea\x90\x27\x6e"
-			  "\x87\xef\xb5\x39\x38\xdb\xad\xbf"
-			  "\x57\x9a\x1d\xbc\x1d\xe5\x16\x91"
-			  "\x41\x45\xbe\x67\x6c\x42\x0f\xad"
-			  "\xcf\xfb\xcd\xf1\x4c\xd8\x73\xe7"
-			  "\x24\x3b\xd7\x03\xeb\xd1\xb1\x1b"
-			  "\x7d\xc9\x3d\x34\xd7\xb8\x69\x03"
-			  "\x76\x95\x32\x26\xed\x88\x76\x89"
-			  "\x13\xc6\xc8\xa6\x60\xf9\x73\x4d",
-		.len	= 160,
-	}, {
-		.key	= "\x82\x8e\x9e\x06\x7b\xc2\xe9\xb3"
-			  "\x06\xa3\xfa\x99\x42\x67\x87\xac"
-			  "\x21\xc7\xb0\x98\x6c\xf8\x26\x57"
-			  "\x08\xdd\x92\x02\x77\x7b\x35\xe7",
-		.klen	= 32,
-		.iv	= "\xa1\xad\xcb\xdd\xd5\x19\xb6\xd4"
-			  "\x0b\x62\x58\xb0\x6c\xa0\xc1\x58",
-		.ptext	= "\x14\x0d\x8a\x09\x16\x00\x00\xf1"
-			  "\xc0\x20\x86\xf9\x21\xd1\x34\xe2",
-		.ctext	= "\x05\xe3\x34\xaf\x6c\x83\x14\x8b"
-			  "\x9d\x1c\xd6\x87\x74\x91\xdf\x17",
-		.len	= 16,
-	}, {
-		.key	= "\xc9\xf3\xc4\x93\xd0\xcc\xaf\xb1"
-			  "\x1a\x42\x93\x71\xd8\x4e\xd8\xaa"
-			  "\x52\xad\x93\x2f\xe5\xd9\xaa\x5b"
-			  "\x47\x37\x3a\xed\x13\x92\x35\x16",
-		.klen	= 32,
-		.iv	= "\x81\xc8\x50\xd1\x74\xc3\x1c\x73"
-			  "\xbb\xab\x72\x83\x90\x5a\x15\xcb",
-		.ptext	= "\x65\x11\x93\xaf\xe1\x69\x6c\xbe"
-			  "\x25\x8c\x76\x87\x53\xa4\x80\xae"
-			  "\x51\x94\x36\x3f\xca\xe7\x45\x41"
-			  "\x76\x05\xbf\x8f\x9c\xad\xc0\xe3",
-		.ctext	= "\x6B\x00\x6E\x49\x7A\x6D\xE3\x04"
-			  "\x4E\xF7\x9F\x8A\x1F\x14\xBD\xB1"
-			  "\xD3\x5D\xA4\x30\x26\x85\x85\xEF"
-			  "\x12\xBC\xC7\xA1\x65\x82\xA7\x74",
-		.len	= 32,
-	}, {
-		.key	= "\xd5\x9f\x52\x34\x12\x99\x8e\x42"
-			  "\xe0\x85\x04\x6f\xeb\xf1\x5d\xd0"
-			  "\xc1\xbf\x3f\x84\xd9\x1e\x71\x44"
-			  "\xd4\xb9\x40\x3c\x02\x2e\x21\x19",
-		.klen	= 32,
-		.iv	= "\x28\xc1\x97\x64\x81\x52\x57\x0e"
-			  "\x02\x8c\xab\x4c\xe2\x60\x14\xa5",
-		.ptext	= "\x5a\xb1\x33\x48\xaa\x51\xe9\xa4"
-			  "\x5c\x2d\xbe\x33\xcc\xc4\x7f\x96"
-			  "\xe8\xde\x2b\xe7\x35\x7a\x11\x4b"
-			  "\x13\x08\x32\xc6\x41\xd8\xec\x54"
-			  "\xa3\xd3\xda\x35\x43\x69\xf6\x88"
-			  "\x97\xca\x00\x1b\x02\x59\x24\x82",
-		.ctext	= "\x03\xaf\x76\xbd\x5e\x5b\xca\xc0"
-			  "\xae\x44\xa2\x2f\xc2\x76\x2f\x50"
-			  "\x6a\x73\x28\xf2\xba\xe8\xb2\xb8"
-			  "\x43\x61\x41\x92\xff\xac\xcb\xa6"
-			  "\x84\x31\xe3\x34\xd0\x37\x81\xab"
-			  "\x2b\x0e\x97\x3c\x4a\x2d\xa4\x83",
-		.len	= 48,
-	}, {
-		.key	= "\x9c\x5d\xd7\x66\x36\xfa\x02\x20"
-			  "\x99\x61\x62\x86\x0f\x43\x2e\x05"
-			  "\x25\x8b\xfb\xf1\xae\x4c\xde\x18"
-			  "\x0b\xf8\xd0\x9d\xaa\xd4\x56\x04",
-		.klen	= 32,
-		.iv	= "\xcd\xa8\x61\x89\x8d\xbb\x72\xb6"
-			  "\x1e\xfe\x03\x34\x54\x88\x23\xe2",
-		.ptext	= "\x66\x42\x60\x24\xf3\xe4\xe9\x7e"
-			  "\x42\x20\xf4\x61\xce\x1c\x5e\x44"
-			  "\x02\x26\x91\xf7\x41\xa4\xab\x34"
-			  "\x29\x49\xdd\x78\x19\x8f\x10\x10"
-			  "\xf0\x61\xcf\x77\x18\x17\x61\xdf"
-			  "\xc4\xa8\x35\x0e\x75\x1b\x84\x6b"
-			  "\xc3\x3f\x31\x59\x5a\x9c\xf4\xc3"
-			  "\x43\xa9\xb7\xf8\x65\x40\x40\xba",
-		.ctext	= "\xb6\x41\x55\x8f\xeb\x16\x1e\x4c"
-			  "\x81\xa0\x85\x6c\xf0\x07\xa5\x2a"
-			  "\x12\x0f\x1d\xb2\xaa\xba\x85\x0f"
-			  "\xa6\x27\x1a\x91\xa6\xc5\x8c\x2a"
-			  "\xde\x8d\x3a\xa9\x8b\xcf\x24\xf1"
-			  "\x82\x51\x6b\xc8\x01\xd7\x7b\x89"
-			  "\x6c\xfc\xb1\x96\x6c\xa2\xd7\x1f"
-			  "\x4b\x7a\xd9\x8d\x34\xaa\xa0\x8a",
-		.len	= 64,
-	}, {
-		.key	= "\x4b\x4e\x11\x91\x27\xcf\x8c\x66"
-			  "\x17\xfa\x5b\x4c\xa8\xb8\x0f\xa1"
-			  "\x99\x5b\x07\x56\xe1\x8d\x94\x8b"
-			  "\xf2\x86\x5a\x5f\x40\x83\xfa\x06",
-		.klen	= 32,
-		.iv	= "\xfd\x73\xee\x1c\x27\xf3\xb4\x38"
-			  "\xc5\x7c\x2e\xc5\x6e\xdb\x49\x0d",
-		.ptext	= "\x0a\xe2\xdd\x97\xdd\x5e\xd4\xb3"
-			  "\xc1\x49\x8f\x53\xb2\x40\x85\x1c"
-			  "\x90\x37\x2d\xbd\x21\x6b\x1f\x80"
-			  "\x56\x98\x76\x1e\xcf\x6c\x78\xd8"
-			  "\xa0\x3c\x79\xc3\x56\xf7\xfc\x64"
-			  "\x35\x58\x1c\x7c\xc4\x5f\x2a\x25"
-			  "\x8c\x01\x98\x1e\x1c\x1f\x15\x64"
-			  "\x50\xb5\xfa\x02\xd3\x54\xe5\x29"
-			  "\xe3\xd2\xa3\x83\x54\x40\x54\xc5"
-			  "\xd8\x1c\xc9\x84\x7d\xc8\x31\x49",
-		.ctext	= "\x53\x2a\xa8\xa0\x15\xaf\x2f\xc4"
-			  "\x7d\x31\xb4\x61\x80\x5f\xd1\xb6"
-			  "\xa4\x29\x40\x72\x1b\xb2\x96\xb7"
-			  "\x4d\x5e\x5b\x53\x44\xa4\xf1\xe9"
-			  "\xf0\x27\x2f\x26\x84\x66\x13\xa4"
-			  "\xb2\x19\x55\xb1\x18\xf3\x69\xfd"
-			  "\xb0\x2f\x08\x3f\xa5\x41\xe2\x34"
-			  "\x5e\x63\x57\x0e\xef\x17\x78\xbc"
-			  "\xc3\x65\x7c\xbe\x6b\xa3\xa3\xef"
-			  "\x58\x05\x30\x5a\x08\xbd\xf7\x0e",
-		.len	= 80,
-	}, {
-		.key	= "\x77\x3b\xf5\xe7\x20\xf7\xe0\x0c"
-			  "\x3d\x3a\x83\x17\x83\x79\xd8\x29"
-			  "\x5a\x0a\x25\x7f\xe0\x21\x23\xff"
-			  "\x31\xfd\x60\x10\xe6\x63\xe2\xaf",
-		.klen	= 32,
-		.iv	= "\xdb\x4c\x0d\xc0\x36\xdb\xc7\xa1"
-			  "\xa4\x91\xd9\x05\xe6\xc4\x98\x00",
-		.ptext	= "\x8d\x4d\xc6\x5e\x01\x82\xb3\x39"
-			  "\xc8\x64\xa7\xcb\x05\x19\x84\x80"
-			  "\x3f\x9c\xa8\x4f\x64\xb3\x11\x4b"
-			  "\x0e\x21\xc4\x75\x04\x1d\x6f\xd5"
-			  "\x04\x04\x4d\xc9\xc0\x4b\x4a\x9c"
-			  "\x26\xb7\x68\x5a\xe4\xd0\x61\xe3"
-			  "\x2c\x93\x8e\x3f\xb4\x67\x07\x31"
-			  "\x02\x52\x0c\x0f\xe6\x6d\xa3\xd0"
-			  "\x48\x95\x83\x67\x23\x64\x31\x50"
-			  "\xd2\x5f\x69\x68\x8b\x71\xbf\x01"
-			  "\x29\x99\x86\x36\x2e\xdf\xf1\x7c"
-			  "\x08\x8c\x78\x7a\x93\x9a\x7d\x1b",
-		.ctext	= "\x92\x90\x48\x2f\x3a\x6b\x68\x43"
-			  "\x28\x9b\x7d\x1e\x46\x28\xd8\x58"
-			  "\x0f\x47\x8b\xb5\x83\x35\x35\x3e"
-			  "\xdf\x59\x3d\xb3\x47\xfc\xfc\x52"
-			  "\x86\xeb\xb3\x58\x54\xd5\x0a\xb4"
-			  "\xad\xbd\x5c\x09\xfc\x08\xc2\x01"
-			  "\x5e\x9b\x30\x11\xc4\x40\x2e\x32"
-			  "\x9c\xa0\xf1\xfd\xae\xd4\x75\x5e"
-			  "\x52\xd9\x19\x4d\xc1\xd4\xb6\x19"
-			  "\x88\xfb\x29\x17\x15\xbb\x60\xd6"
-			  "\x5a\xe9\x82\x89\xaf\x30\x4e\xd4"
-			  "\x47\xde\x86\x88\x95\x4c\x13\x59",
-		.len	= 96,
-	}, {
-		.key	= "\xe0\x6a\x30\xe1\x35\xb5\xb0\x7c"
-			  "\x54\xc5\x73\x9b\x00\xe5\xe7\x02"
-			  "\xbe\x16\x59\xdc\xd9\x03\x17\x53"
-			  "\xa8\x37\xd1\x5f\x13\x8e\x45\xdb",
-		.klen	= 32,
-		.iv	= "\x54\xe9\x1c\xde\xfb\x26\x0e\x48"
-			  "\x35\x50\x4d\x9b\x4d\x12\x21\x0d",
-		.ptext	= "\x73\x72\xcf\xdb\xbd\xbc\xc0\xdf"
-			  "\x6b\xbb\xdf\x65\x6f\x2f\x43\x3b"
-			  "\x2d\x7c\x0e\x07\x7f\xa0\x95\xdd"
-			  "\xfc\x67\xc1\x11\x7a\xe2\xb5\x4a"
-			  "\xd1\x15\xb0\xd8\xe2\xf0\x35\x48"
-			  "\xd8\x81\x6a\x35\xae\x67\xbf\x61"
-			  "\xf2\x8a\xcf\x04\xc8\x09\x8b\x63"
-			  "\x31\x74\x95\xa5\x8d\x3c\xea\xe2"
-			  "\x5f\x67\xc4\x7e\x51\x88\xbf\xb5"
-			  "\x78\xef\x3a\x76\xd8\x1d\x00\x75"
-			  "\x2b\x7b\x28\x7c\xde\x4b\x39\x01"
-			  "\x5d\xde\x92\xfe\x90\x07\x09\xfd"
-			  "\xa5\xd1\xd3\x72\x11\x6d\xa4\x4e"
-			  "\xd1\x6e\x16\xd1\xf6\x39\x4f\xa0",
-		.ctext	= "\x3b\xc5\xee\xfc\x05\xaf\xa6\xb7"
-			  "\xfe\x12\x24\x79\x31\xad\x32\xb5"
-			  "\x64\x5a\x17\xc9\xbf\x1f\xdc\xce"
-			  "\x8d\x73\x00\x71\xd9\xfb\xd2\xe6"
-			  "\xc3\x54\xb4\xf3\x36\xe8\x89\x12"
-			  "\x5a\x32\x0b\xa6\xec\x5f\x89\xe7"
-			  "\xe8\x34\x92\xa6\xce\xde\x8f\xf9"
-			  "\x4f\xda\xed\x61\x8e\xb2\x81\xbe"
-			  "\xf2\x15\x85\xbe\xa1\x5f\x19\x85"
-			  "\x71\x7e\xda\x46\x59\xed\x5d\xb0"
-			  "\xd9\x68\x97\xe0\xcd\x1d\x1b\x65"
-			  "\xf5\xc9\x44\xe2\xb4\x42\x17\x7c"
-			  "\xe7\x58\xf3\x2f\xcf\xbe\x5c\x66"
-			  "\xaa\xd3\x61\xa5\x9a\x79\xbb\xa0",
-		.len	= 112,
-	}, {
-		.key	= "\x60\xb6\xde\x17\xca\x4c\xe7\xe0"
-			  "\x07\x0d\x80\xc5\x8a\x2d\x5a\xc2"
-			  "\x2c\xb9\xa4\x5f\x2a\x85\x2c\x3d"
-			  "\x6d\x67\xc8\xee\x0f\xa2\xf4\x09",
-		.klen	= 32,
-		.iv	= "\x1a\xa5\xbc\x7e\x93\xf6\xdd\x28"
-			  "\xb7\x69\x27\xa1\x84\x95\x25\x5a",
-		.ptext	= "\x7b\x88\x00\xeb\xa5\xba\xa1\xa7"
-			  "\xd4\x40\x16\x74\x2b\x42\x37\xda"
-			  "\xe0\xaf\x89\x59\x41\x2f\x62\x00"
-			  "\xf5\x5a\x4e\x3b\x85\x27\xb2\xed"
-			  "\x1b\xa7\xaf\xbe\x89\xf3\x49\xb7"
-			  "\x8c\x63\xc9\x0c\x52\x00\x5f\x38"
-			  "\x3b\x3c\x0c\x4f\xdd\xe1\xbf\x90"
-			  "\x4a\x48\xbf\x3a\x95\xcb\x48\xa2"
-			  "\x92\x7c\x79\x81\xde\x18\x6e\x92"
-			  "\x1f\x36\xa9\x5d\x8d\xc4\xb6\x4d"
-			  "\xb2\xb4\x0e\x09\x6d\xf3\x3d\x01"
-			  "\x3d\x9b\x40\x47\xbc\x69\x31\xa1"
-			  "\x6a\x71\x26\xdc\xac\x10\x56\x63"
-			  "\x15\x23\x7d\x10\xe3\x76\x82\x41"
-			  "\xcd\x80\x57\x2f\xfc\x4d\x22\x7b"
-			  "\x57\xbb\x9a\x0a\x03\xe9\xb3\x13",
-		.ctext	= "\x37\x0d\x47\x21\xbc\x28\x0b\xf7"
-			  "\x85\x5f\x60\x57\xf2\x7f\x92\x20"
-			  "\x53\x1a\xbf\xd1\x7f\x8c\x39\x29"
-			  "\x0e\x18\xab\x0c\x00\x92\xd3\x68"
-			  "\x60\x56\x3b\x00\xef\xf8\x02\xfa"
-			  "\xcb\x92\x1a\x91\xe1\xf0\x4f\x8a"
-			  "\xc6\x4f\x65\x16\x71\x8b\x5d\xd5"
-			  "\x79\xa9\x6d\x68\x1b\x59\xe7\x2a"
-			  "\x1c\xd0\x5d\xfb\x06\x3b\x15\x72"
-			  "\xa8\xd1\x59\x9a\xb2\x6c\xf2\xd5"
-			  "\x19\xef\xde\x03\x4c\x75\x65\x38"
-			  "\x5b\xda\xc9\xf0\x44\x99\xb2\x6e"
-			  "\x78\xfb\x85\x5a\x92\x91\x1a\x0a"
-			  "\x13\x0c\x1b\x1c\xbe\xbe\x46\x6e"
-			  "\x73\xff\xc2\x6e\xb9\x06\x16\x7e"
-			  "\xf6\xc0\x01\x30\x34\x56\x46\x55",
-		.len	= 128,
-	}, {
-		.key	= "\x2a\xed\x7d\x76\xfc\xc5\x49\x50"
-			  "\xf4\x90\x0f\xcc\x5d\xff\x0c\x3c"
-			  "\x14\x06\xaf\x68\x8f\xd7\xb6\x25"
-			  "\x1e\x10\x95\x2a\x71\x33\x17\x20",
-		.klen	= 32,
-		.iv	= "\x5b\x58\x47\xf8\xd5\x1e\x91\x81"
-			  "\x46\xe7\x25\x3a\x02\x45\x9c\x65",
-		.ptext	= "\x10\xaf\xde\x5c\x30\x79\x43\x28"
-			  "\x1c\x03\xf8\x50\x0f\x30\xa5\xef"
-			  "\x84\x19\x4c\x09\x40\x03\x75\x1f"
-			  "\x92\x8f\x88\x01\xda\x31\x7a\xe4"
-			  "\x48\xe3\xab\xb4\xe6\x1b\x0f\xac"
-			  "\xd9\xfa\x8d\x23\xe4\xc6\xa4\xa9"
-			  "\x2d\x9a\x54\x52\x44\x5c\x3c\x52"
-			  "\x61\xf0\x00\xca\xed\xab\xed\xe2"
-			  "\x44\x0b\xe0\x18\xba\xa5\x63\xd8"
-			  "\xdc\x5e\x1a\x4c\xf8\xde\x5e\x75"
-			  "\xdf\x42\x27\x7b\xe9\x11\x2f\x41"
-			  "\x3a\x72\x54\x3d\x44\x9c\x3e\x87"
-			  "\x8d\x8d\x43\x2f\xb2\xff\x87\xd4"
-			  "\xad\x98\x68\x72\x53\x61\x19\x7c"
-			  "\x20\x79\x8c\x2b\x37\x0b\x96\x15"
-			  "\xa5\x7d\x4e\x01\xe6\xea\xb6\xfa"
-			  "\xaa\xd3\x9d\xa2\xd9\x11\xc3\xc9"
-			  "\xd4\x0e\x3f\x3e\xfe\x35\x1e\xe5",
-		.ctext	= "\xb0\x2b\x75\x5f\x33\x1b\x05\x49"
-			  "\x06\xf1\x43\x91\xc2\x85\xfa\xac"
-			  "\x74\xd5\x8c\xc9\x47\x6e\x5a\xf6"
-			  "\x69\x33\x4c\xcb\x2f\x36\x4b\x41"
-			  "\xec\x05\x69\xab\x7f\x42\xc9\xd2"
-			  "\x26\x64\x51\x9e\x3d\x65\x35\xf0"
-			  "\x8d\x5e\x8a\xb1\xee\xdf\x1a\x98"
-			  "\x36\xd2\x37\x49\x5b\xe2\x57\x00"
-			  "\x1d\x72\x7e\xe8\x38\x11\x83\x15"
-			  "\xc7\x4e\x65\xa4\x2c\x9e\x6a\x3e"
-			  "\xb4\x78\x3f\xe9\x91\x5d\x06\xa9"
-			  "\xf1\xfc\x6b\x08\xe5\x2b\x2a\x99"
-			  "\x65\xa7\x2e\x47\xf9\xc2\xb1\x8b"
-			  "\x88\x2f\xb7\x62\x84\x63\x94\x00"
-			  "\x49\xa7\xd0\x2b\x54\x7a\x69\xb3"
-			  "\x04\x66\xfc\x97\x40\x92\xd1\xb8"
-			  "\xb4\x2a\x9e\xdb\x31\xcd\x48\x84"
-			  "\x29\x3b\x02\xac\xb8\x54\x95\xb4",
-		.len	= 144,
-	}, {
-		.key	= "\x7b\xa7\x4d\x0a\x37\x30\xb9\xf5"
-			  "\x2a\x79\xb4\xbf\xdb\x7f\x9b\x64"
-			  "\x23\x43\xb5\x18\x34\xc4\x5f\xdf"
-			  "\xd9\x2a\x66\x58\x00\x44\xb5\xd9",
-		.klen	= 32,
-		.iv	= "\x75\x34\x30\xc1\xf0\x69\xdf\x0a"
-			  "\x52\xce\x4f\x1e\x2c\x41\x35\xec",
-		.ptext	= "\x81\x47\x55\x3a\xcd\xfe\xa2\x3d"
-			  "\x45\x53\xa7\x67\x61\x74\x25\x80"
-			  "\x98\x89\xfe\xf8\x6a\x9f\x51\x7c"
-			  "\xa4\xe4\xe7\xc7\xe0\x1a\xce\xbb"
-			  "\x4b\x46\x43\xb0\xab\xa8\xd6\x0c"
-			  "\xa0\xf0\xc8\x13\x29\xaf\xb8\x01"
-			  "\x6b\x0c\x7e\x56\xae\xb8\x58\x72"
-			  "\xa9\x24\x44\x61\xff\xf1\xac\xf8"
-			  "\x09\xa8\x48\x21\xd6\xab\x41\x73"
-			  "\x70\x6b\x92\x06\x61\xdc\xb4\x85"
-			  "\x76\x26\x7a\x84\xc3\x9e\x3a\x14"
-			  "\xe7\xf4\x2d\x95\x92\xad\x18\xcc"
-			  "\x44\xd4\x2c\x36\x57\xed\x2b\x9b"
-			  "\x3f\x2b\xcd\xe5\x11\xe3\x62\x33"
-			  "\x42\x3f\xb8\x2a\xb1\x37\x3f\x8b"
-			  "\xe8\xbd\x6b\x0b\x9f\x38\x5a\x5f"
-			  "\x82\x34\xb7\x96\x35\x58\xde\xab"
-			  "\x94\x98\x41\x5b\x3f\xac\x0a\x34"
-			  "\x56\xc0\x02\xef\x81\x6d\xb1\xff"
-			  "\x34\xe8\xc7\x6a\x31\x79\xba\xd8",
-		.ctext	= "\x4e\x00\x7c\x52\x45\x76\xf9\x3d"
-			  "\x1a\xd1\x72\xbc\xb9\x0f\xa9\xfb"
-			  "\x0a\xf5\xe8\x11\x66\x8b\xad\x68"
-			  "\x5a\x2e\xbf\x09\x33\x9d\xb6\x67"
-			  "\xe5\xcb\x0a\xe0\xac\xed\x73\x4b"
-			  "\xbb\x15\xde\xd8\xab\x33\x28\x5f"
-			  "\x96\x07\x3c\x28\x79\x88\x84\xc7"
-			  "\x13\xf7\x0d\xa5\x97\x3b\xd9\xb1"
-			  "\xf2\x65\xb0\xac\xbb\x8a\x97\xd1"
-			  "\x70\x3a\x91\x65\xc8\x39\x04\xe7"
-			  "\x1a\x9c\x80\x65\x2b\x69\x4b\xdc"
-			  "\xdc\xc7\xf1\x31\xda\xab\xb4\xd7"
-			  "\x46\x2e\x1d\xc9\x2e\xe9\x46\xec"
-			  "\xa4\xa1\x91\x6b\x4a\x09\xf9\x39"
-			  "\x7b\x7d\x6d\xf5\x43\x7f\xcc\x74"
-			  "\x96\xfa\x48\xd0\xe1\x74\x24\xd0"
-			  "\x19\x22\x24\x84\x2b\x12\x10\x46"
-			  "\x90\xbd\xa9\x93\xb7\xf7\x36\xd4"
-			  "\x48\xc7\x32\x83\x8c\xa9\xcd\x5a"
-			  "\x2f\x05\x33\xc1\x5b\x50\x70\xc4",
-		.len	= 160,
-	}
-};
-
 static const struct aead_testvec aria_gcm_tv_template[] = {
 	{
 		.key	= "\xe9\x1e\x5e\x75\xda\x65\x55\x4a"
diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c
index 9711e8fc979d..3a89644f087c 100644
--- a/drivers/accel/habanalabs/common/device.c
+++ b/drivers/accel/habanalabs/common/device.c
@@ -2044,7 +2044,7 @@ static void hl_notifier_event_send(struct hl_notifier_event *notifier_event, u64
 	notifier_event->events_mask |= event_mask;
 
 	if (notifier_event->eventfd)
-		eventfd_signal(notifier_event->eventfd, 1);
+		eventfd_signal(notifier_event->eventfd);
 
 	mutex_unlock(&notifier_event->lock);
 }
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index 5c0246b9e522..d530384f8d60 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -53,10 +53,12 @@
 
 #define ICB_0_1_IRQ_MASK ((((u64)ICB_1_IRQ_MASK) << 32) | ICB_0_IRQ_MASK)
 
-#define BUTTRESS_IRQ_MASK ((REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE)) | \
-			   (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR)) | \
+#define BUTTRESS_IRQ_MASK ((REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR)) | \
 			   (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, UFI_ERR)))
 
+#define BUTTRESS_ALL_IRQ_MASK (BUTTRESS_IRQ_MASK | \
+			       (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE)))
+
 #define BUTTRESS_IRQ_ENABLE_MASK ((u32)~BUTTRESS_IRQ_MASK)
 #define BUTTRESS_IRQ_DISABLE_MASK ((u32)-1)
 
@@ -74,8 +76,12 @@ static void ivpu_hw_wa_init(struct ivpu_device *vdev)
 	vdev->wa.clear_runtime_mem = false;
 	vdev->wa.d3hot_after_power_off = true;
 
-	if (ivpu_device_id(vdev) == PCI_DEVICE_ID_MTL && ivpu_revision(vdev) < 4)
+	REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, BUTTRESS_ALL_IRQ_MASK);
+	if (REGB_RD32(VPU_37XX_BUTTRESS_INTERRUPT_STAT) == BUTTRESS_ALL_IRQ_MASK) {
+		/* Writing 1s does not clear the interrupt status register */
 		vdev->wa.interrupt_clear_with_0 = true;
+		REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, 0x0);
+	}
 
 	IVPU_PRINT_WA(punit_disabled);
 	IVPU_PRINT_WA(clear_runtime_mem);
@@ -502,6 +508,16 @@ static int ivpu_boot_pwr_domain_enable(struct ivpu_device *vdev)
 	return ret;
 }
 
+static int ivpu_boot_pwr_domain_disable(struct ivpu_device *vdev)
+{
+	ivpu_boot_dpu_active_drive(vdev, false);
+	ivpu_boot_pwr_island_isolation_drive(vdev, true);
+	ivpu_boot_pwr_island_trickle_drive(vdev, false);
+	ivpu_boot_pwr_island_drive(vdev, false);
+
+	return ivpu_boot_wait_for_pwr_island_status(vdev, 0x0);
+}
+
 static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
 {
 	u32 val = REGV_RD32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES);
@@ -600,25 +616,17 @@ static int ivpu_hw_37xx_info_init(struct ivpu_device *vdev)
 
 static int ivpu_hw_37xx_reset(struct ivpu_device *vdev)
 {
-	int ret;
-	u32 val;
-
-	if (IVPU_WA(punit_disabled))
-		return 0;
+	int ret = 0;
 
-	ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US);
-	if (ret) {
-		ivpu_err(vdev, "Timed out waiting for TRIGGER bit\n");
-		return ret;
+	if (ivpu_boot_pwr_domain_disable(vdev)) {
+		ivpu_err(vdev, "Failed to disable power domain\n");
+		ret = -EIO;
 	}
 
-	val = REGB_RD32(VPU_37XX_BUTTRESS_VPU_IP_RESET);
-	val = REG_SET_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, val);
-	REGB_WR32(VPU_37XX_BUTTRESS_VPU_IP_RESET, val);
-
-	ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US);
-	if (ret)
-		ivpu_err(vdev, "Timed out waiting for RESET completion\n");
+	if (ivpu_pll_disable(vdev)) {
+		ivpu_err(vdev, "Failed to disable PLL\n");
+		ret = -EIO;
+	}
 
 	return ret;
 }
@@ -651,10 +659,6 @@ static int ivpu_hw_37xx_power_up(struct ivpu_device *vdev)
 {
 	int ret;
 
-	ret = ivpu_hw_37xx_reset(vdev);
-	if (ret)
-		ivpu_warn(vdev, "Failed to reset HW: %d\n", ret);
-
 	ret = ivpu_hw_37xx_d0i3_disable(vdev);
 	if (ret)
 		ivpu_warn(vdev, "Failed to disable D0I3: %d\n", ret);
@@ -722,11 +726,11 @@ static int ivpu_hw_37xx_power_down(struct ivpu_device *vdev)
 {
 	int ret = 0;
 
-	if (!ivpu_hw_37xx_is_idle(vdev) && ivpu_hw_37xx_reset(vdev))
-		ivpu_err(vdev, "Failed to reset the VPU\n");
+	if (!ivpu_hw_37xx_is_idle(vdev))
+		ivpu_warn(vdev, "VPU not idle during power down\n");
 
-	if (ivpu_pll_disable(vdev)) {
-		ivpu_err(vdev, "Failed to disable PLL\n");
+	if (ivpu_hw_37xx_reset(vdev)) {
+		ivpu_err(vdev, "Failed to reset VPU\n");
 		ret = -EIO;
 	}
 
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index 0ace218783c8..e9b16cbc26f4 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -250,9 +250,6 @@ int ivpu_rpm_get_if_active(struct ivpu_device *vdev)
 {
 	int ret;
 
-	ivpu_dbg(vdev, RPM, "rpm_get_if_active count %d\n",
-		 atomic_read(&vdev->drm.dev->power.usage_count));
-
 	ret = pm_runtime_get_if_active(vdev->drm.dev, false);
 	drm_WARN_ON(&vdev->drm, ret < 0);
 
diff --git a/drivers/accel/qaic/mhi_controller.c b/drivers/accel/qaic/mhi_controller.c
index 5036e58e7235..1405623b03e4 100644
--- a/drivers/accel/qaic/mhi_controller.c
+++ b/drivers/accel/qaic/mhi_controller.c
@@ -404,8 +404,21 @@ static struct mhi_controller_config aic100_config = {
 
 static int mhi_read_reg(struct mhi_controller *mhi_cntrl, void __iomem *addr, u32 *out)
 {
-	u32 tmp = readl_relaxed(addr);
+	u32 tmp;
 
+	/*
+	 * SOC_HW_VERSION quirk
+	 * The SOC_HW_VERSION register (offset 0x224) is not reliable and
+	 * may contain uninitialized values, including 0xFFFFFFFF. This could
+	 * cause a false positive link down error.  Instead, intercept any
+	 * reads and provide the correct value of the register.
+	 */
+	if (addr - mhi_cntrl->regs == 0x224) {
+		*out = 0x60110200;
+		return 0;
+	}
+
+	tmp = readl_relaxed(addr);
 	if (tmp == U32_MAX)
 		return -EIO;
 
diff --git a/drivers/accel/qaic/qaic_data.c b/drivers/accel/qaic/qaic_data.c
index 4a8e43a7a6a4..24e886f857d5 100644
--- a/drivers/accel/qaic/qaic_data.c
+++ b/drivers/accel/qaic/qaic_data.c
@@ -451,7 +451,7 @@ static int create_sgt(struct qaic_device *qdev, struct sg_table **sgt_out, u64 s
 		 * later
 		 */
 		buf_extra = (PAGE_SIZE - size % PAGE_SIZE) % PAGE_SIZE;
-		max_order = min(MAX_ORDER - 1, get_order(size));
+		max_order = min(MAX_PAGE_ORDER - 1, get_order(size));
 	} else {
 		/* allocate a single page for book keeping */
 		nr_pages = 1;
@@ -777,7 +777,6 @@ struct drm_gem_object *qaic_gem_prime_import(struct drm_device *dev, struct dma_
 	struct dma_buf_attachment *attach;
 	struct drm_gem_object *obj;
 	struct qaic_bo *bo;
-	size_t size;
 	int ret;
 
 	bo = qaic_alloc_init_bo();
@@ -795,13 +794,12 @@ struct drm_gem_object *qaic_gem_prime_import(struct drm_device *dev, struct dma_
 		goto attach_fail;
 	}
 
-	size = PAGE_ALIGN(attach->dmabuf->size);
-	if (size == 0) {
+	if (!attach->dmabuf->size) {
 		ret = -EINVAL;
 		goto size_align_fail;
 	}
 
-	drm_gem_private_object_init(dev, obj, size);
+	drm_gem_private_object_init(dev, obj, attach->dmabuf->size);
 	/*
 	 * skipping dma_buf_map_attachment() as we do not know the direction
 	 * just yet. Once the direction is known in the subsequent IOCTL to
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index f819e760ff19..6f2bfcf7645c 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -61,6 +61,10 @@ config ACPI_CCA_REQUIRED
 config ACPI_TABLE_LIB
 	bool
 
+config ACPI_THERMAL_LIB
+       depends on THERMAL
+       bool
+
 config ACPI_DEBUGGER
 	bool "AML debugger interface"
 	select ACPI_DEBUG
@@ -327,6 +331,7 @@ config ACPI_THERMAL
 	tristate "Thermal Zone"
 	depends on ACPI_PROCESSOR
 	select THERMAL
+	select ACPI_THERMAL_LIB
 	default y
 	help
 	  This driver supports ACPI thermal zones.  Most mobile and
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index eaa09bf52f17..12ef8180d272 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -37,7 +37,7 @@ acpi-$(CONFIG_ACPI_SLEEP)	+= proc.o
 # ACPI Bus and Device Drivers
 #
 acpi-y				+= bus.o glue.o
-acpi-y				+= scan.o
+acpi-y				+= scan.o mipi-disco-img.o
 acpi-y				+= resource.o
 acpi-y				+= acpi_processor.o
 acpi-y				+= processor_core.o
@@ -89,6 +89,7 @@ obj-$(CONFIG_ACPI_TAD)		+= acpi_tad.o
 obj-$(CONFIG_ACPI_PCI_SLOT)	+= pci_slot.o
 obj-$(CONFIG_ACPI_PROCESSOR)	+= processor.o
 obj-$(CONFIG_ACPI)		+= container.o
+obj-$(CONFIG_ACPI_THERMAL_LIB)	+= thermal_lib.o
 obj-$(CONFIG_ACPI_THERMAL)	+= thermal.o
 obj-$(CONFIG_ACPI_PLATFORM_PROFILE) 	+= platform_profile.o
 obj-$(CONFIG_ACPI_NFIT)		+= nfit/
diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c
index e120a96e1eae..ca87a0939135 100644
--- a/drivers/acpi/acpi_extlog.c
+++ b/drivers/acpi/acpi_extlog.c
@@ -145,9 +145,14 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
 	static u32 err_seq;
 
 	estatus = extlog_elog_entry_check(cpu, bank);
-	if (estatus == NULL || (mce->kflags & MCE_HANDLED_CEC))
+	if (!estatus)
 		return NOTIFY_DONE;
 
+	if (mce->kflags & MCE_HANDLED_CEC) {
+		estatus->block_status = 0;
+		return NOTIFY_DONE;
+	}
+
 	memcpy(elog_buf, (void *)estatus, ELOG_ENTRY_LEN);
 	/* clear record status to enable BIOS to update it again */
 	estatus->block_status = 0;
@@ -303,9 +308,10 @@ err:
 static void __exit extlog_exit(void)
 {
 	mce_unregister_decode_chain(&extlog_mce_dec);
-	((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN;
-	if (extlog_l1_addr)
+	if (extlog_l1_addr) {
+		((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN;
 		acpi_os_unmap_iomem(extlog_l1_addr, l1_size);
+	}
 	if (elog_addr)
 		acpi_os_unmap_iomem(elog_addr, elog_size);
 	release_mem_region(elog_base, elog_size);
diff --git a/drivers/acpi/acpi_lpit.c b/drivers/acpi/acpi_lpit.c
index c5598b6d5db8..794962c5c88e 100644
--- a/drivers/acpi/acpi_lpit.c
+++ b/drivers/acpi/acpi_lpit.c
@@ -105,7 +105,7 @@ static void lpit_update_residency(struct lpit_residency_info *info,
 		return;
 
 	info->frequency = lpit_native->counter_frequency ?
-				lpit_native->counter_frequency : tsc_khz * 1000;
+				lpit_native->counter_frequency : mul_u32_u32(tsc_khz, 1000U);
 	if (!info->frequency)
 		info->frequency = 1;
 
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 875de44961bf..04e273167e92 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -167,13 +167,9 @@ static struct pwm_lookup byt_pwm_lookup[] = {
 
 static void byt_pwm_setup(struct lpss_private_data *pdata)
 {
-	u64 uid;
-
 	/* Only call pwm_add_table for the first PWM controller */
-	if (acpi_dev_uid_to_integer(pdata->adev, &uid) || uid != 1)
-		return;
-
-	pwm_add_table(byt_pwm_lookup, ARRAY_SIZE(byt_pwm_lookup));
+	if (acpi_dev_uid_match(pdata->adev, 1))
+		pwm_add_table(byt_pwm_lookup, ARRAY_SIZE(byt_pwm_lookup));
 }
 
 #define LPSS_I2C_ENABLE			0x6c
@@ -218,13 +214,9 @@ static struct pwm_lookup bsw_pwm_lookup[] = {
 
 static void bsw_pwm_setup(struct lpss_private_data *pdata)
 {
-	u64 uid;
-
 	/* Only call pwm_add_table for the first PWM controller */
-	if (acpi_dev_uid_to_integer(pdata->adev, &uid) || uid != 1)
-		return;
-
-	pwm_add_table(bsw_pwm_lookup, ARRAY_SIZE(bsw_pwm_lookup));
+	if (acpi_dev_uid_match(pdata->adev, 1))
+		pwm_add_table(bsw_pwm_lookup, ARRAY_SIZE(bsw_pwm_lookup));
 }
 
 static const struct property_entry lpt_spi_properties[] = {
@@ -461,8 +453,9 @@ static int register_device_clock(struct acpi_device *adev,
 		if (!clk_name)
 			return -ENOMEM;
 		clk = clk_register_fractional_divider(NULL, clk_name, parent,
+						      0, prv_base, 1, 15, 16, 15,
 						      CLK_FRAC_DIVIDER_POWER_OF_TWO_PS,
-						      prv_base, 1, 15, 16, 15, 0, NULL);
+						      NULL);
 		parent = clk_name;
 
 		clk_name = kasprintf(GFP_KERNEL, "%s-update", devname);
@@ -570,34 +563,6 @@ static struct device *acpi_lpss_find_device(const char *hid, const char *uid)
 	return bus_find_device(&pci_bus_type, NULL, &data, match_hid_uid);
 }
 
-static bool acpi_lpss_dep(struct acpi_device *adev, acpi_handle handle)
-{
-	struct acpi_handle_list dep_devices;
-	acpi_status status;
-	bool ret = false;
-	int i;
-
-	if (!acpi_has_method(adev->handle, "_DEP"))
-		return false;
-
-	status = acpi_evaluate_reference(adev->handle, "_DEP", NULL,
-					 &dep_devices);
-	if (ACPI_FAILURE(status)) {
-		dev_dbg(&adev->dev, "Failed to evaluate _DEP.\n");
-		return false;
-	}
-
-	for (i = 0; i < dep_devices.count; i++) {
-		if (dep_devices.handles[i] == handle) {
-			ret = true;
-			break;
-		}
-	}
-
-	acpi_handle_list_free(&dep_devices);
-	return ret;
-}
-
 static void acpi_lpss_link_consumer(struct device *dev1,
 				    const struct lpss_device_links *link)
 {
@@ -608,7 +573,7 @@ static void acpi_lpss_link_consumer(struct device *dev1,
 		return;
 
 	if ((link->dep_missing_ids && dmi_check_system(link->dep_missing_ids))
-	    || acpi_lpss_dep(ACPI_COMPANION(dev2), ACPI_HANDLE(dev1)))
+	    || acpi_device_dep(ACPI_HANDLE(dev2), ACPI_HANDLE(dev1)))
 		device_link_add(dev2, dev1, link->flags);
 
 	put_device(dev2);
@@ -624,7 +589,7 @@ static void acpi_lpss_link_supplier(struct device *dev1,
 		return;
 
 	if ((link->dep_missing_ids && dmi_check_system(link->dep_missing_ids))
-	    || acpi_lpss_dep(ACPI_COMPANION(dev1), ACPI_HANDLE(dev2)))
+	    || acpi_device_dep(ACPI_HANDLE(dev1), ACPI_HANDLE(dev2)))
 		device_link_add(dev1, dev2, link->flags);
 
 	put_device(dev2);
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 0b7a01f38b65..4afdda9db019 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -67,7 +67,7 @@ MODULE_PARM_DESC(hw_changes_brightness,
 static bool device_id_scheme = false;
 module_param(device_id_scheme, bool, 0444);
 
-static int only_lcd = -1;
+static int only_lcd;
 module_param(only_lcd, int, 0444);
 
 static bool may_report_brightness_keys;
@@ -253,8 +253,7 @@ static const struct backlight_ops acpi_backlight_ops = {
 static int video_get_max_state(struct thermal_cooling_device *cooling_dev,
 			       unsigned long *state)
 {
-	struct acpi_device *device = cooling_dev->devdata;
-	struct acpi_video_device *video = acpi_driver_data(device);
+	struct acpi_video_device *video = cooling_dev->devdata;
 
 	*state = video->brightness->count - ACPI_VIDEO_FIRST_LEVEL - 1;
 	return 0;
@@ -263,8 +262,7 @@ static int video_get_max_state(struct thermal_cooling_device *cooling_dev,
 static int video_get_cur_state(struct thermal_cooling_device *cooling_dev,
 			       unsigned long *state)
 {
-	struct acpi_device *device = cooling_dev->devdata;
-	struct acpi_video_device *video = acpi_driver_data(device);
+	struct acpi_video_device *video = cooling_dev->devdata;
 	unsigned long long level;
 	int offset;
 
@@ -283,8 +281,7 @@ static int video_get_cur_state(struct thermal_cooling_device *cooling_dev,
 static int
 video_set_cur_state(struct thermal_cooling_device *cooling_dev, unsigned long state)
 {
-	struct acpi_device *device = cooling_dev->devdata;
-	struct acpi_video_device *video = acpi_driver_data(device);
+	struct acpi_video_device *video = cooling_dev->devdata;
 	int level;
 
 	if (state >= video->brightness->count - ACPI_VIDEO_FIRST_LEVEL)
@@ -503,6 +500,15 @@ static const struct dmi_system_id video_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 3350"),
 		},
 	},
+	{
+	 .callback = video_set_report_key_events,
+	 .driver_data = (void *)((uintptr_t)REPORT_BRIGHTNESS_KEY_EVENTS),
+	 .ident = "COLORFUL X15 AT 23",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "COLORFUL"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "X15 AT 23"),
+		},
+	},
 	/*
 	 * Some machines change the brightness themselves when a brightness
 	 * hotkey gets pressed, despite us telling them not to. In this case
@@ -1125,7 +1131,6 @@ static int acpi_video_bus_get_one_device(struct acpi_device *device, void *arg)
 
 	strcpy(acpi_device_name(device), ACPI_VIDEO_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_VIDEO_CLASS);
-	device->driver_data = data;
 
 	data->device_id = device_id;
 	data->video = video;
@@ -1717,12 +1722,12 @@ static void acpi_video_dev_register_backlight(struct acpi_video_device *device)
 		return;
 	count++;
 
-	acpi_get_parent(device->dev->handle, &acpi_parent);
-
-	pdev = acpi_get_pci_dev(acpi_parent);
-	if (pdev) {
-		parent = &pdev->dev;
-		pci_dev_put(pdev);
+	if (ACPI_SUCCESS(acpi_get_parent(device->dev->handle, &acpi_parent))) {
+		pdev = acpi_get_pci_dev(acpi_parent);
+		if (pdev) {
+			parent = &pdev->dev;
+			pci_dev_put(pdev);
+		}
 	}
 
 	memset(&props, 0, sizeof(struct backlight_properties));
@@ -1747,8 +1752,8 @@ static void acpi_video_dev_register_backlight(struct acpi_video_device *device)
 	device->backlight->props.brightness =
 			acpi_video_get_brightness(device->backlight);
 
-	device->cooling_dev = thermal_cooling_device_register("LCD",
-				device->dev, &video_cooling_ops);
+	device->cooling_dev = thermal_cooling_device_register("LCD", device,
+							      &video_cooling_ops);
 	if (IS_ERR(device->cooling_dev)) {
 		/*
 		 * Set cooling_dev to NULL so we don't crash trying to free it.
@@ -2031,7 +2036,7 @@ static int acpi_video_bus_add(struct acpi_device *device)
 	 * HP ZBook Fury 16 G10 requires ACPI video's child devices have _PS0
 	 * evaluated to have functional panel brightness control.
 	 */
-	acpi_device_fix_up_power_extended(device);
+	acpi_device_fix_up_power_children(device);
 
 	pr_info("%s [%s] (multi-head: %s  rom: %s  post: %s)\n",
 	       ACPI_VIDEO_DEVICE_NAME, acpi_device_bid(device),
@@ -2141,57 +2146,6 @@ static int __init intel_opregion_present(void)
 	return opregion;
 }
 
-/* Check if the chassis-type indicates there is no builtin LCD panel */
-static bool dmi_is_desktop(void)
-{
-	const char *chassis_type;
-	unsigned long type;
-
-	chassis_type = dmi_get_system_info(DMI_CHASSIS_TYPE);
-	if (!chassis_type)
-		return false;
-
-	if (kstrtoul(chassis_type, 10, &type) != 0)
-		return false;
-
-	switch (type) {
-	case 0x03: /* Desktop */
-	case 0x04: /* Low Profile Desktop */
-	case 0x05: /* Pizza Box */
-	case 0x06: /* Mini Tower */
-	case 0x07: /* Tower */
-	case 0x10: /* Lunch Box */
-	case 0x11: /* Main Server Chassis */
-		return true;
-	}
-
-	return false;
-}
-
-/*
- * We're seeing a lot of bogus backlight interfaces on newer machines
- * without a LCD such as desktops, servers and HDMI sticks. Checking the
- * lcd flag fixes this, enable this by default on any machines which are:
- * 1.  Win8 ready (where we also prefer the native backlight driver, so
- *     normally the acpi_video code should not register there anyways); *and*
- * 2.1 Report a desktop/server DMI chassis-type, or
- * 2.2 Are an ACPI-reduced-hardware platform (and thus won't use the EC for
-       backlight control)
- */
-static bool should_check_lcd_flag(void)
-{
-	if (!acpi_osi_is_win8())
-		return false;
-
-	if (dmi_is_desktop())
-		return true;
-
-	if (acpi_reduced_hardware())
-		return true;
-
-	return false;
-}
-
 int acpi_video_register(void)
 {
 	int ret = 0;
@@ -2205,9 +2159,6 @@ int acpi_video_register(void)
 		goto leave;
 	}
 
-	if (only_lcd == -1)
-		only_lcd = should_check_lcd_flag();
-
 	dmi_check_system(video_dmi_table);
 
 	ret = acpi_bus_register_driver(&acpi_video_bus);
diff --git a/drivers/acpi/acpi_watchdog.c b/drivers/acpi/acpi_watchdog.c
index ca28183f4d13..8e9e001da38f 100644
--- a/drivers/acpi/acpi_watchdog.c
+++ b/drivers/acpi/acpi_watchdog.c
@@ -81,7 +81,7 @@ static const struct acpi_table_wdat *acpi_watchdog_get_wdat(void)
 	return wdat;
 }
 
-/**
+/*
  * Returns true if this system should prefer ACPI based watchdog instead of
  * the native one (which are typically the same hardware).
  */
diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c
index 013eb621dc92..89fb9331c611 100644
--- a/drivers/acpi/apei/einj.c
+++ b/drivers/acpi/apei/einj.c
@@ -73,6 +73,7 @@ static u32 notrigger;
 
 static u32 vendor_flags;
 static struct debugfs_blob_wrapper vendor_blob;
+static struct debugfs_blob_wrapper vendor_errors;
 static char vendor_dev[64];
 
 /*
@@ -182,6 +183,21 @@ static int einj_timedout(u64 *t)
 	return 0;
 }
 
+static void get_oem_vendor_struct(u64 paddr, int offset,
+				  struct vendor_error_type_extension *v)
+{
+	unsigned long vendor_size;
+	u64 target_pa = paddr + offset + sizeof(struct vendor_error_type_extension);
+
+	vendor_size = v->length - sizeof(struct vendor_error_type_extension);
+
+	if (vendor_size)
+		vendor_errors.data = acpi_os_map_memory(target_pa, vendor_size);
+
+	if (vendor_errors.data)
+		vendor_errors.size = vendor_size;
+}
+
 static void check_vendor_extension(u64 paddr,
 				   struct set_error_type_with_address *v5param)
 {
@@ -194,6 +210,7 @@ static void check_vendor_extension(u64 paddr,
 	v = acpi_os_map_iomem(paddr + offset, sizeof(*v));
 	if (!v)
 		return;
+	get_oem_vendor_struct(paddr, offset, v);
 	sbdf = v->pcie_sbdf;
 	sprintf(vendor_dev, "%x:%x:%x.%x vendor_id=%x device_id=%x rev_id=%x\n",
 		sbdf >> 24, (sbdf >> 16) & 0xff,
@@ -577,38 +594,40 @@ static u64 error_param2;
 static u64 error_param3;
 static u64 error_param4;
 static struct dentry *einj_debug_dir;
-static const char * const einj_error_type_string[] = {
-	"0x00000001\tProcessor Correctable\n",
-	"0x00000002\tProcessor Uncorrectable non-fatal\n",
-	"0x00000004\tProcessor Uncorrectable fatal\n",
-	"0x00000008\tMemory Correctable\n",
-	"0x00000010\tMemory Uncorrectable non-fatal\n",
-	"0x00000020\tMemory Uncorrectable fatal\n",
-	"0x00000040\tPCI Express Correctable\n",
-	"0x00000080\tPCI Express Uncorrectable non-fatal\n",
-	"0x00000100\tPCI Express Uncorrectable fatal\n",
-	"0x00000200\tPlatform Correctable\n",
-	"0x00000400\tPlatform Uncorrectable non-fatal\n",
-	"0x00000800\tPlatform Uncorrectable fatal\n",
-	"0x00001000\tCXL.cache Protocol Correctable\n",
-	"0x00002000\tCXL.cache Protocol Uncorrectable non-fatal\n",
-	"0x00004000\tCXL.cache Protocol Uncorrectable fatal\n",
-	"0x00008000\tCXL.mem Protocol Correctable\n",
-	"0x00010000\tCXL.mem Protocol Uncorrectable non-fatal\n",
-	"0x00020000\tCXL.mem Protocol Uncorrectable fatal\n",
+static struct { u32 mask; const char *str; } const einj_error_type_string[] = {
+	{ BIT(0), "Processor Correctable" },
+	{ BIT(1), "Processor Uncorrectable non-fatal" },
+	{ BIT(2), "Processor Uncorrectable fatal" },
+	{ BIT(3), "Memory Correctable" },
+	{ BIT(4), "Memory Uncorrectable non-fatal" },
+	{ BIT(5), "Memory Uncorrectable fatal" },
+	{ BIT(6), "PCI Express Correctable" },
+	{ BIT(7), "PCI Express Uncorrectable non-fatal" },
+	{ BIT(8), "PCI Express Uncorrectable fatal" },
+	{ BIT(9), "Platform Correctable" },
+	{ BIT(10), "Platform Uncorrectable non-fatal" },
+	{ BIT(11), "Platform Uncorrectable fatal"},
+	{ BIT(12), "CXL.cache Protocol Correctable" },
+	{ BIT(13), "CXL.cache Protocol Uncorrectable non-fatal" },
+	{ BIT(14), "CXL.cache Protocol Uncorrectable fatal" },
+	{ BIT(15), "CXL.mem Protocol Correctable" },
+	{ BIT(16), "CXL.mem Protocol Uncorrectable non-fatal" },
+	{ BIT(17), "CXL.mem Protocol Uncorrectable fatal" },
+	{ BIT(31), "Vendor Defined Error Types" },
 };
 
 static int available_error_type_show(struct seq_file *m, void *v)
 {
 	int rc;
-	u32 available_error_type = 0;
+	u32 error_type = 0;
 
-	rc = einj_get_available_error_type(&available_error_type);
+	rc = einj_get_available_error_type(&error_type);
 	if (rc)
 		return rc;
 	for (int pos = 0; pos < ARRAY_SIZE(einj_error_type_string); pos++)
-		if (available_error_type & BIT(pos))
-			seq_puts(m, einj_error_type_string[pos]);
+		if (error_type & einj_error_type_string[pos].mask)
+			seq_printf(m, "0x%08x\t%s\n", einj_error_type_string[pos].mask,
+				   einj_error_type_string[pos].str);
 
 	return 0;
 }
@@ -767,6 +786,10 @@ static int __init einj_init(void)
 				   einj_debug_dir, &vendor_flags);
 	}
 
+	if (vendor_errors.size)
+		debugfs_create_blob("oem_error", 0600, einj_debug_dir,
+				    &vendor_errors);
+
 	pr_info("Error INJection is initialized.\n");
 
 	return 0;
@@ -792,6 +815,8 @@ static void __exit einj_exit(void)
 			sizeof(struct einj_parameter);
 
 		acpi_os_unmap_iomem(einj_param, size);
+		if (vendor_errors.size)
+			acpi_os_unmap_memory(vendor_errors.data, vendor_errors.size);
 	}
 	einj_exec_ctx_init(&ctx);
 	apei_exec_post_unmap_gars(&ctx);
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 63ad0541db38..ab2a82cb1b0b 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -102,6 +102,20 @@ static inline bool is_hest_type_generic_v2(struct ghes *ghes)
 }
 
 /*
+ * A platform may describe one error source for the handling of synchronous
+ * errors (e.g. MCE or SEA), or for handling asynchronous errors (e.g. SCI
+ * or External Interrupt). On x86, the HEST notifications are always
+ * asynchronous, so only SEA on ARM is delivered as a synchronous
+ * notification.
+ */
+static inline bool is_hest_sync_notify(struct ghes *ghes)
+{
+	u8 notify_type = ghes->generic->notify.type;
+
+	return notify_type == ACPI_HEST_NOTIFY_SEA;
+}
+
+/*
  * This driver isn't really modular, however for the time being,
  * continuing to use module_param is the easiest way to remain
  * compatible with existing boot arg use cases.
@@ -489,7 +503,7 @@ static bool ghes_do_memory_failure(u64 physical_addr, int flags)
 }
 
 static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
-				       int sev)
+				       int sev, bool sync)
 {
 	int flags = -1;
 	int sec_sev = ghes_severity(gdata->error_severity);
@@ -503,7 +517,7 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
 	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED))
 		flags = MF_SOFT_OFFLINE;
 	if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE)
-		flags = 0;
+		flags = sync ? MF_ACTION_REQUIRED : 0;
 
 	if (flags != -1)
 		return ghes_do_memory_failure(mem_err->physical_addr, flags);
@@ -511,9 +525,11 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
 	return false;
 }
 
-static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int sev)
+static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
+				       int sev, bool sync)
 {
 	struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
+	int flags = sync ? MF_ACTION_REQUIRED : 0;
 	bool queued = false;
 	int sec_sev, i;
 	char *p;
@@ -538,7 +554,7 @@ static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int s
 		 * and don't filter out 'corrected' error here.
 		 */
 		if (is_cache && has_pa) {
-			queued = ghes_do_memory_failure(err_info->physical_fault_addr, 0);
+			queued = ghes_do_memory_failure(err_info->physical_fault_addr, flags);
 			p += err_info->length;
 			continue;
 		}
@@ -666,6 +682,7 @@ static bool ghes_do_proc(struct ghes *ghes,
 	const guid_t *fru_id = &guid_null;
 	char *fru_text = "";
 	bool queued = false;
+	bool sync = is_hest_sync_notify(ghes);
 
 	sev = ghes_severity(estatus->error_severity);
 	apei_estatus_for_each_section(estatus, gdata) {
@@ -683,13 +700,13 @@ static bool ghes_do_proc(struct ghes *ghes,
 			atomic_notifier_call_chain(&ghes_report_chain, sev, mem_err);
 
 			arch_apei_report_mem_error(sev, mem_err);
-			queued = ghes_handle_memory_failure(gdata, sev);
+			queued = ghes_handle_memory_failure(gdata, sev, sync);
 		}
 		else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
 			ghes_handle_aer(gdata);
 		}
 		else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
-			queued = ghes_handle_arm_hw_error(gdata, sev);
+			queued = ghes_handle_arm_hw_error(gdata, sev, sync);
 		} else {
 			void *err = acpi_hest_get_payload(gdata);
 
diff --git a/drivers/acpi/arm64/Makefile b/drivers/acpi/arm64/Makefile
index 143debc1ba4a..726944648c9b 100644
--- a/drivers/acpi/arm64/Makefile
+++ b/drivers/acpi/arm64/Makefile
@@ -5,3 +5,4 @@ obj-$(CONFIG_ACPI_GTDT) 	+= gtdt.o
 obj-$(CONFIG_ACPI_APMT) 	+= apmt.o
 obj-$(CONFIG_ARM_AMBA)		+= amba.o
 obj-y				+= dma.o init.o
+obj-y				+= thermal_cpufreq.o
diff --git a/drivers/acpi/arm64/thermal_cpufreq.c b/drivers/acpi/arm64/thermal_cpufreq.c
new file mode 100644
index 000000000000..582854914c5c
--- /dev/null
+++ b/drivers/acpi/arm64/thermal_cpufreq.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/acpi.h>
+#include <linux/export.h>
+
+#include "../internal.h"
+
+#define SMCCC_SOC_ID_T241      0x036b0241
+
+int acpi_arch_thermal_cpufreq_pctg(void)
+{
+	s32 soc_id = arm_smccc_get_soc_id_version();
+
+	/*
+	 * Check JEP106 code for NVIDIA Tegra241 chip (036b:0241) and
+	 * reduce the CPUFREQ Thermal reduction percentage to 5%.
+	 */
+	if (soc_id == SMCCC_SOC_ID_T241)
+		return 5;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(acpi_arch_thermal_cpufreq_pctg);
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 72e64c0718c9..569bd15f211b 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -408,7 +408,7 @@ static void acpi_bus_decode_usb_osc(const char *msg, u32 bits)
 static u8 sb_usb_uuid_str[] = "23A0D13A-26AB-486C-9C5F-0FFA525A575A";
 static void acpi_bus_osc_negotiate_usb_control(void)
 {
-	u32 capbuf[3];
+	u32 capbuf[3], *capbuf_ret;
 	struct acpi_osc_context context = {
 		.uuid_str = sb_usb_uuid_str,
 		.rev = 1,
@@ -428,7 +428,12 @@ static void acpi_bus_osc_negotiate_usb_control(void)
 	control = OSC_USB_USB3_TUNNELING | OSC_USB_DP_TUNNELING |
 		  OSC_USB_PCIE_TUNNELING | OSC_USB_XDOMAIN;
 
-	capbuf[OSC_QUERY_DWORD] = 0;
+	/*
+	 * Run _OSC first with query bit set, trying to get control over
+	 * all tunneling. The platform can then clear out bits in the
+	 * control dword that it does not want to grant to the OS.
+	 */
+	capbuf[OSC_QUERY_DWORD] = OSC_QUERY_ENABLE;
 	capbuf[OSC_SUPPORT_DWORD] = 0;
 	capbuf[OSC_CONTROL_DWORD] = control;
 
@@ -441,8 +446,29 @@ static void acpi_bus_osc_negotiate_usb_control(void)
 		goto out_free;
 	}
 
+	/*
+	 * Run _OSC again now with query bit clear and the control dword
+	 * matching what the platform granted (which may not have all
+	 * the control bits set).
+	 */
+	capbuf_ret = context.ret.pointer;
+
+	capbuf[OSC_QUERY_DWORD] = 0;
+	capbuf[OSC_CONTROL_DWORD] = capbuf_ret[OSC_CONTROL_DWORD];
+
+	kfree(context.ret.pointer);
+
+	status = acpi_run_osc(handle, &context);
+	if (ACPI_FAILURE(status))
+		return;
+
+	if (context.ret.length != sizeof(capbuf)) {
+		pr_info("USB4 _OSC: returned invalid length buffer\n");
+		goto out_free;
+	}
+
 	osc_sb_native_usb4_control =
-		control &  acpi_osc_ctx_get_pci_control(&context);
+		control & acpi_osc_ctx_get_pci_control(&context);
 
 	acpi_bus_decode_usb_osc("USB4 _OSC: OS supports", control);
 	acpi_bus_decode_usb_osc("USB4 _OSC: OS controls",
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 1e76a64cce0a..cc61020756be 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -480,6 +480,7 @@ static int acpi_button_suspend(struct device *dev)
 
 static int acpi_button_resume(struct device *dev)
 {
+	struct input_dev *input;
 	struct acpi_device *device = to_acpi_device(dev);
 	struct acpi_button *button = acpi_driver_data(device);
 
@@ -489,6 +490,14 @@ static int acpi_button_resume(struct device *dev)
 		button->last_time = ktime_get();
 		acpi_lid_initialize_state(device);
 	}
+
+	if (button->type == ACPI_BUTTON_TYPE_POWER) {
+		input = button->input;
+		input_report_key(input, KEY_WAKEUP, 1);
+		input_sync(input);
+		input_report_key(input, KEY_WAKEUP, 0);
+		input_sync(input);
+	}
 	return 0;
 }
 #endif
@@ -579,6 +588,7 @@ static int acpi_button_add(struct acpi_device *device)
 	switch (button->type) {
 	case ACPI_BUTTON_TYPE_POWER:
 		input_set_capability(input, EV_KEY, KEY_POWER);
+		input_set_capability(input, EV_KEY, KEY_WAKEUP);
 		break;
 
 	case ACPI_BUTTON_TYPE_SLEEP:
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 7ff269a78c20..d155a86a8614 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -39,6 +39,9 @@
 #include <linux/rwsem.h>
 #include <linux/wait.h>
 #include <linux/topology.h>
+#include <linux/dmi.h>
+#include <linux/units.h>
+#include <asm/unaligned.h>
 
 #include <acpi/cppc_acpi.h>
 
@@ -1760,3 +1763,104 @@ unsigned int cppc_get_transition_latency(int cpu_num)
 	return latency_ns;
 }
 EXPORT_SYMBOL_GPL(cppc_get_transition_latency);
+
+/* Minimum struct length needed for the DMI processor entry we want */
+#define DMI_ENTRY_PROCESSOR_MIN_LENGTH	48
+
+/* Offset in the DMI processor structure for the max frequency */
+#define DMI_PROCESSOR_MAX_SPEED		0x14
+
+/* Callback function used to retrieve the max frequency from DMI */
+static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private)
+{
+	const u8 *dmi_data = (const u8 *)dm;
+	u16 *mhz = (u16 *)private;
+
+	if (dm->type == DMI_ENTRY_PROCESSOR &&
+	    dm->length >= DMI_ENTRY_PROCESSOR_MIN_LENGTH) {
+		u16 val = (u16)get_unaligned((const u16 *)
+				(dmi_data + DMI_PROCESSOR_MAX_SPEED));
+		*mhz = val > *mhz ? val : *mhz;
+	}
+}
+
+/* Look up the max frequency in DMI */
+static u64 cppc_get_dmi_max_khz(void)
+{
+	u16 mhz = 0;
+
+	dmi_walk(cppc_find_dmi_mhz, &mhz);
+
+	/*
+	 * Real stupid fallback value, just in case there is no
+	 * actual value set.
+	 */
+	mhz = mhz ? mhz : 1;
+
+	return KHZ_PER_MHZ * mhz;
+}
+
+/*
+ * If CPPC lowest_freq and nominal_freq registers are exposed then we can
+ * use them to convert perf to freq and vice versa. The conversion is
+ * extrapolated as an affine function passing by the 2 points:
+ *  - (Low perf, Low freq)
+ *  - (Nominal perf, Nominal freq)
+ */
+unsigned int cppc_perf_to_khz(struct cppc_perf_caps *caps, unsigned int perf)
+{
+	s64 retval, offset = 0;
+	static u64 max_khz;
+	u64 mul, div;
+
+	if (caps->lowest_freq && caps->nominal_freq) {
+		mul = caps->nominal_freq - caps->lowest_freq;
+		mul *= KHZ_PER_MHZ;
+		div = caps->nominal_perf - caps->lowest_perf;
+		offset = caps->nominal_freq * KHZ_PER_MHZ -
+			 div64_u64(caps->nominal_perf * mul, div);
+	} else {
+		if (!max_khz)
+			max_khz = cppc_get_dmi_max_khz();
+		mul = max_khz;
+		div = caps->highest_perf;
+	}
+
+	retval = offset + div64_u64(perf * mul, div);
+	if (retval >= 0)
+		return retval;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cppc_perf_to_khz);
+
+unsigned int cppc_khz_to_perf(struct cppc_perf_caps *caps, unsigned int freq)
+{
+	s64 retval, offset = 0;
+	static u64 max_khz;
+	u64  mul, div;
+
+	if (caps->lowest_freq && caps->nominal_freq) {
+		mul = caps->nominal_perf - caps->lowest_perf;
+		div = caps->nominal_freq - caps->lowest_freq;
+		/*
+		 * We don't need to convert to kHz for computing offset and can
+		 * directly use nominal_freq and lowest_freq as the div64_u64
+		 * will remove the frequency unit.
+		 */
+		offset = caps->nominal_perf -
+			 div64_u64(caps->nominal_freq * mul, div);
+		/* But we need it for computing the perf level. */
+		div *= KHZ_PER_MHZ;
+	} else {
+		if (!max_khz)
+			max_khz = cppc_get_dmi_max_khz();
+		mul = caps->highest_perf;
+		div = max_khz;
+	}
+
+	retval = offset + div64_u64(freq * mul, div);
+	if (retval >= 0)
+		return retval;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cppc_khz_to_perf);
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index f007116a8427..3b4d048c4941 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -397,6 +397,19 @@ void acpi_device_fix_up_power_extended(struct acpi_device *adev)
 }
 EXPORT_SYMBOL_GPL(acpi_device_fix_up_power_extended);
 
+/**
+ * acpi_device_fix_up_power_children - Force a device's children into D0.
+ * @adev: Parent device object whose children's power state is to be fixed up.
+ *
+ * Call acpi_device_fix_up_power() for @adev's children so long as they
+ * are reported as present and enabled.
+ */
+void acpi_device_fix_up_power_children(struct acpi_device *adev)
+{
+	acpi_dev_for_each_child(adev, fix_up_power_if_applicable, NULL);
+}
+EXPORT_SYMBOL_GPL(acpi_device_fix_up_power_children);
+
 int acpi_device_update_power(struct acpi_device *device, int *state_p)
 {
 	int state;
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index a59c11df7375..dbdee2924594 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -525,12 +525,10 @@ static void acpi_ec_clear(struct acpi_ec *ec)
 
 static void acpi_ec_enable_event(struct acpi_ec *ec)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&ec->lock, flags);
+	spin_lock(&ec->lock);
 	if (acpi_ec_started(ec))
 		__acpi_ec_enable_event(ec);
-	spin_unlock_irqrestore(&ec->lock, flags);
+	spin_unlock(&ec->lock);
 
 	/* Drain additional events if hardware requires that */
 	if (EC_FLAGS_CLEAR_ON_RESUME)
@@ -546,11 +544,9 @@ static void __acpi_ec_flush_work(void)
 
 static void acpi_ec_disable_event(struct acpi_ec *ec)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&ec->lock, flags);
+	spin_lock(&ec->lock);
 	__acpi_ec_disable_event(ec);
-	spin_unlock_irqrestore(&ec->lock, flags);
+	spin_unlock(&ec->lock);
 
 	/*
 	 * When ec_freeze_events is true, we need to flush events in
@@ -571,10 +567,9 @@ void acpi_ec_flush_work(void)
 
 static bool acpi_ec_guard_event(struct acpi_ec *ec)
 {
-	unsigned long flags;
 	bool guarded;
 
-	spin_lock_irqsave(&ec->lock, flags);
+	spin_lock(&ec->lock);
 	/*
 	 * If firmware SCI_EVT clearing timing is "event", we actually
 	 * don't know when the SCI_EVT will be cleared by firmware after
@@ -590,31 +585,29 @@ static bool acpi_ec_guard_event(struct acpi_ec *ec)
 	guarded = ec_event_clearing == ACPI_EC_EVT_TIMING_EVENT &&
 		ec->event_state != EC_EVENT_READY &&
 		(!ec->curr || ec->curr->command != ACPI_EC_COMMAND_QUERY);
-	spin_unlock_irqrestore(&ec->lock, flags);
+	spin_unlock(&ec->lock);
 	return guarded;
 }
 
 static int ec_transaction_polled(struct acpi_ec *ec)
 {
-	unsigned long flags;
 	int ret = 0;
 
-	spin_lock_irqsave(&ec->lock, flags);
+	spin_lock(&ec->lock);
 	if (ec->curr && (ec->curr->flags & ACPI_EC_COMMAND_POLL))
 		ret = 1;
-	spin_unlock_irqrestore(&ec->lock, flags);
+	spin_unlock(&ec->lock);
 	return ret;
 }
 
 static int ec_transaction_completed(struct acpi_ec *ec)
 {
-	unsigned long flags;
 	int ret = 0;
 
-	spin_lock_irqsave(&ec->lock, flags);
+	spin_lock(&ec->lock);
 	if (ec->curr && (ec->curr->flags & ACPI_EC_COMMAND_COMPLETE))
 		ret = 1;
-	spin_unlock_irqrestore(&ec->lock, flags);
+	spin_unlock(&ec->lock);
 	return ret;
 }
 
@@ -756,7 +749,6 @@ static int ec_guard(struct acpi_ec *ec)
 
 static int ec_poll(struct acpi_ec *ec)
 {
-	unsigned long flags;
 	int repeat = 5; /* number of command restarts */
 
 	while (repeat--) {
@@ -765,14 +757,14 @@ static int ec_poll(struct acpi_ec *ec)
 		do {
 			if (!ec_guard(ec))
 				return 0;
-			spin_lock_irqsave(&ec->lock, flags);
+			spin_lock(&ec->lock);
 			advance_transaction(ec, false);
-			spin_unlock_irqrestore(&ec->lock, flags);
+			spin_unlock(&ec->lock);
 		} while (time_before(jiffies, delay));
 		pr_debug("controller reset, restart transaction\n");
-		spin_lock_irqsave(&ec->lock, flags);
+		spin_lock(&ec->lock);
 		start_transaction(ec);
-		spin_unlock_irqrestore(&ec->lock, flags);
+		spin_unlock(&ec->lock);
 	}
 	return -ETIME;
 }
@@ -780,11 +772,10 @@ static int ec_poll(struct acpi_ec *ec)
 static int acpi_ec_transaction_unlocked(struct acpi_ec *ec,
 					struct transaction *t)
 {
-	unsigned long tmp;
 	int ret = 0;
 
 	/* start transaction */
-	spin_lock_irqsave(&ec->lock, tmp);
+	spin_lock(&ec->lock);
 	/* Enable GPE for command processing (IBF=0/OBF=1) */
 	if (!acpi_ec_submit_flushable_request(ec)) {
 		ret = -EINVAL;
@@ -795,11 +786,11 @@ static int acpi_ec_transaction_unlocked(struct acpi_ec *ec,
 	ec->curr = t;
 	ec_dbg_req("Command(%s) started", acpi_ec_cmd_string(t->command));
 	start_transaction(ec);
-	spin_unlock_irqrestore(&ec->lock, tmp);
+	spin_unlock(&ec->lock);
 
 	ret = ec_poll(ec);
 
-	spin_lock_irqsave(&ec->lock, tmp);
+	spin_lock(&ec->lock);
 	if (t->irq_count == ec_storm_threshold)
 		acpi_ec_unmask_events(ec);
 	ec_dbg_req("Command(%s) stopped", acpi_ec_cmd_string(t->command));
@@ -808,7 +799,7 @@ static int acpi_ec_transaction_unlocked(struct acpi_ec *ec,
 	acpi_ec_complete_request(ec);
 	ec_dbg_ref(ec, "Decrease command");
 unlock:
-	spin_unlock_irqrestore(&ec->lock, tmp);
+	spin_unlock(&ec->lock);
 	return ret;
 }
 
@@ -936,9 +927,7 @@ EXPORT_SYMBOL(ec_get_handle);
 
 static void acpi_ec_start(struct acpi_ec *ec, bool resuming)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&ec->lock, flags);
+	spin_lock(&ec->lock);
 	if (!test_and_set_bit(EC_FLAGS_STARTED, &ec->flags)) {
 		ec_dbg_drv("Starting EC");
 		/* Enable GPE for event processing (SCI_EVT=1) */
@@ -948,31 +937,28 @@ static void acpi_ec_start(struct acpi_ec *ec, bool resuming)
 		}
 		ec_log_drv("EC started");
 	}
-	spin_unlock_irqrestore(&ec->lock, flags);
+	spin_unlock(&ec->lock);
 }
 
 static bool acpi_ec_stopped(struct acpi_ec *ec)
 {
-	unsigned long flags;
 	bool flushed;
 
-	spin_lock_irqsave(&ec->lock, flags);
+	spin_lock(&ec->lock);
 	flushed = acpi_ec_flushed(ec);
-	spin_unlock_irqrestore(&ec->lock, flags);
+	spin_unlock(&ec->lock);
 	return flushed;
 }
 
 static void acpi_ec_stop(struct acpi_ec *ec, bool suspending)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&ec->lock, flags);
+	spin_lock(&ec->lock);
 	if (acpi_ec_started(ec)) {
 		ec_dbg_drv("Stopping EC");
 		set_bit(EC_FLAGS_STOPPED, &ec->flags);
-		spin_unlock_irqrestore(&ec->lock, flags);
+		spin_unlock(&ec->lock);
 		wait_event(ec->wait, acpi_ec_stopped(ec));
-		spin_lock_irqsave(&ec->lock, flags);
+		spin_lock(&ec->lock);
 		/* Disable GPE for event processing (SCI_EVT=1) */
 		if (!suspending) {
 			acpi_ec_complete_request(ec);
@@ -983,29 +969,25 @@ static void acpi_ec_stop(struct acpi_ec *ec, bool suspending)
 		clear_bit(EC_FLAGS_STOPPED, &ec->flags);
 		ec_log_drv("EC stopped");
 	}
-	spin_unlock_irqrestore(&ec->lock, flags);
+	spin_unlock(&ec->lock);
 }
 
 static void acpi_ec_enter_noirq(struct acpi_ec *ec)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&ec->lock, flags);
+	spin_lock(&ec->lock);
 	ec->busy_polling = true;
 	ec->polling_guard = 0;
 	ec_log_drv("interrupt blocked");
-	spin_unlock_irqrestore(&ec->lock, flags);
+	spin_unlock(&ec->lock);
 }
 
 static void acpi_ec_leave_noirq(struct acpi_ec *ec)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&ec->lock, flags);
+	spin_lock(&ec->lock);
 	ec->busy_polling = ec_busy_polling;
 	ec->polling_guard = ec_polling_guard;
 	ec_log_drv("interrupt unblocked");
-	spin_unlock_irqrestore(&ec->lock, flags);
+	spin_unlock(&ec->lock);
 }
 
 void acpi_ec_block_transactions(void)
@@ -1137,9 +1119,9 @@ static void acpi_ec_event_processor(struct work_struct *work)
 
 	ec_dbg_evt("Query(0x%02x) stopped", handler->query_bit);
 
-	spin_lock_irq(&ec->lock);
+	spin_lock(&ec->lock);
 	ec->queries_in_progress--;
-	spin_unlock_irq(&ec->lock);
+	spin_unlock(&ec->lock);
 
 	acpi_ec_put_query_handler(handler);
 	kfree(q);
@@ -1202,12 +1184,12 @@ static int acpi_ec_submit_query(struct acpi_ec *ec)
 	 */
 	ec_dbg_evt("Query(0x%02x) scheduled", value);
 
-	spin_lock_irq(&ec->lock);
+	spin_lock(&ec->lock);
 
 	ec->queries_in_progress++;
 	queue_work(ec_query_wq, &q->work);
 
-	spin_unlock_irq(&ec->lock);
+	spin_unlock(&ec->lock);
 
 	return 0;
 
@@ -1223,14 +1205,14 @@ static void acpi_ec_event_handler(struct work_struct *work)
 
 	ec_dbg_evt("Event started");
 
-	spin_lock_irq(&ec->lock);
+	spin_lock(&ec->lock);
 
 	while (ec->events_to_process) {
-		spin_unlock_irq(&ec->lock);
+		spin_unlock(&ec->lock);
 
 		acpi_ec_submit_query(ec);
 
-		spin_lock_irq(&ec->lock);
+		spin_lock(&ec->lock);
 
 		ec->events_to_process--;
 	}
@@ -1247,11 +1229,11 @@ static void acpi_ec_event_handler(struct work_struct *work)
 
 		ec_dbg_evt("Event stopped");
 
-		spin_unlock_irq(&ec->lock);
+		spin_unlock(&ec->lock);
 
 		guard_timeout = !!ec_guard(ec);
 
-		spin_lock_irq(&ec->lock);
+		spin_lock(&ec->lock);
 
 		/* Take care of SCI_EVT unless someone else is doing that. */
 		if (guard_timeout && !ec->curr)
@@ -1264,7 +1246,7 @@ static void acpi_ec_event_handler(struct work_struct *work)
 
 	ec->events_in_progress--;
 
-	spin_unlock_irq(&ec->lock);
+	spin_unlock(&ec->lock);
 }
 
 static void clear_gpe_and_advance_transaction(struct acpi_ec *ec, bool interrupt)
@@ -1289,13 +1271,11 @@ static void clear_gpe_and_advance_transaction(struct acpi_ec *ec, bool interrupt
 
 static void acpi_ec_handle_interrupt(struct acpi_ec *ec)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&ec->lock, flags);
+	spin_lock(&ec->lock);
 
 	clear_gpe_and_advance_transaction(ec, true);
 
-	spin_unlock_irqrestore(&ec->lock, flags);
+	spin_unlock(&ec->lock);
 }
 
 static u32 acpi_ec_gpe_handler(acpi_handle gpe_device,
@@ -1458,8 +1438,8 @@ static bool install_gpe_event_handler(struct acpi_ec *ec)
 
 static bool install_gpio_irq_event_handler(struct acpi_ec *ec)
 {
-	return request_irq(ec->irq, acpi_ec_irq_handler, IRQF_SHARED,
-			   "ACPI EC", ec) >= 0;
+	return request_threaded_irq(ec->irq, NULL, acpi_ec_irq_handler,
+				    IRQF_SHARED | IRQF_ONESHOT, "ACPI EC", ec) >= 0;
 }
 
 /**
@@ -2105,7 +2085,7 @@ bool acpi_ec_dispatch_gpe(void)
 	 * Dispatch the EC GPE in-band, but do not report wakeup in any case
 	 * to allow the caller to process events properly after that.
 	 */
-	spin_lock_irq(&first_ec->lock);
+	spin_lock(&first_ec->lock);
 
 	if (acpi_ec_gpe_status_set(first_ec)) {
 		pm_pr_dbg("ACPI EC GPE status set\n");
@@ -2114,7 +2094,7 @@ bool acpi_ec_dispatch_gpe(void)
 		work_in_progress = acpi_ec_work_in_progress(first_ec);
 	}
 
-	spin_unlock_irq(&first_ec->lock);
+	spin_unlock(&first_ec->lock);
 
 	if (!work_in_progress)
 		return false;
@@ -2127,11 +2107,11 @@ bool acpi_ec_dispatch_gpe(void)
 
 		pm_pr_dbg("ACPI EC work flushed\n");
 
-		spin_lock_irq(&first_ec->lock);
+		spin_lock(&first_ec->lock);
 
 		work_in_progress = acpi_ec_work_in_progress(first_ec);
 
-		spin_unlock_irq(&first_ec->lock);
+		spin_unlock(&first_ec->lock);
 	} while (work_in_progress && !pm_wakeup_pending());
 
 	return false;
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 866c7c4ed233..6588525c45ef 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -85,6 +85,20 @@ bool acpi_scan_is_offline(struct acpi_device *adev, bool uevent);
 acpi_status acpi_sysfs_table_handler(u32 event, void *table, void *context);
 void acpi_scan_table_notify(void);
 
+int acpi_active_trip_temp(struct acpi_device *adev, int id, int *ret_temp);
+int acpi_passive_trip_temp(struct acpi_device *adev, int *ret_temp);
+int acpi_hot_trip_temp(struct acpi_device *adev, int *ret_temp);
+int acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp);
+
+#ifdef CONFIG_ARM64
+int acpi_arch_thermal_cpufreq_pctg(void);
+#else
+static inline int acpi_arch_thermal_cpufreq_pctg(void)
+{
+	return 0;
+}
+#endif
+
 /* --------------------------------------------------------------------------
                      Device Node Initialization / Removal
    -------------------------------------------------------------------------- */
@@ -148,8 +162,11 @@ int acpi_wakeup_device_init(void);
 #ifdef CONFIG_ARCH_MIGHT_HAVE_ACPI_PDC
 void acpi_early_processor_control_setup(void);
 void acpi_early_processor_set_pdc(void);
-
+#ifdef CONFIG_X86
 void acpi_proc_quirk_mwait_check(void);
+#else
+static inline void acpi_proc_quirk_mwait_check(void) {}
+#endif
 bool processor_physically_present(acpi_handle handle);
 #else
 static inline void acpi_early_processor_control_setup(void) {}
@@ -276,4 +293,13 @@ void acpi_init_lpit(void);
 static inline void acpi_init_lpit(void) { }
 #endif
 
+/*--------------------------------------------------------------------------
+		ACPI _CRS CSI-2 and MIPI DisCo for Imaging
+  -------------------------------------------------------------------------- */
+
+void acpi_mipi_check_crs_csi2(acpi_handle handle);
+void acpi_mipi_scan_crs_csi2(void);
+void acpi_mipi_init_crs_csi2_swnodes(void);
+void acpi_mipi_crs_csi2_cleanup(void);
+
 #endif /* _ACPI_INTERNAL_H_ */
diff --git a/drivers/acpi/mipi-disco-img.c b/drivers/acpi/mipi-disco-img.c
new file mode 100644
index 000000000000..7286cf4579bc
--- /dev/null
+++ b/drivers/acpi/mipi-disco-img.c
@@ -0,0 +1,725 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * MIPI DisCo for Imaging support.
+ *
+ * Copyright (C) 2023 Intel Corporation
+ *
+ * Support MIPI DisCo for Imaging by parsing ACPI _CRS CSI-2 records defined in
+ * Section 6.4.3.8.2.4 "Camera Serial Interface (CSI-2) Connection Resource
+ * Descriptor" of ACPI 6.5 and using device properties defined by the MIPI DisCo
+ * for Imaging specification.
+ *
+ * The implementation looks for the information in the ACPI namespace (CSI-2
+ * resource descriptors in _CRS) and constructs software nodes compatible with
+ * Documentation/firmware-guide/acpi/dsd/graph.rst to represent the CSI-2
+ * connection graph.  The software nodes are then populated with the data
+ * extracted from the _CRS CSI-2 resource descriptors and the MIPI DisCo
+ * for Imaging device properties present in _DSD for the ACPI device objects
+ * with CSI-2 connections.
+ */
+
+#include <linux/acpi.h>
+#include <linux/limits.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/overflow.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+
+#include <media/v4l2-fwnode.h>
+
+#include "internal.h"
+
+static LIST_HEAD(acpi_mipi_crs_csi2_list);
+
+static void acpi_mipi_data_tag(acpi_handle handle, void *context)
+{
+}
+
+/* Connection data extracted from one _CRS CSI-2 resource descriptor. */
+struct crs_csi2_connection {
+	struct list_head entry;
+	struct acpi_resource_csi2_serialbus csi2_data;
+	acpi_handle remote_handle;
+	char remote_name[];
+};
+
+/* Data extracted from _CRS CSI-2 resource descriptors for one device. */
+struct crs_csi2 {
+	struct list_head entry;
+	acpi_handle handle;
+	struct acpi_device_software_nodes *swnodes;
+	struct list_head connections;
+	u32 port_count;
+};
+
+struct csi2_resources_walk_data {
+	acpi_handle handle;
+	struct list_head connections;
+};
+
+static acpi_status parse_csi2_resource(struct acpi_resource *res, void *context)
+{
+	struct csi2_resources_walk_data *crwd = context;
+	struct acpi_resource_csi2_serialbus *csi2_res;
+	struct acpi_resource_source *csi2_res_src;
+	u16 csi2_res_src_length;
+	struct crs_csi2_connection *conn;
+	acpi_handle remote_handle;
+
+	if (res->type != ACPI_RESOURCE_TYPE_SERIAL_BUS)
+		return AE_OK;
+
+	csi2_res = &res->data.csi2_serial_bus;
+
+	if (csi2_res->type != ACPI_RESOURCE_SERIAL_TYPE_CSI2)
+		return AE_OK;
+
+	csi2_res_src = &csi2_res->resource_source;
+	if (ACPI_FAILURE(acpi_get_handle(NULL, csi2_res_src->string_ptr,
+					 &remote_handle))) {
+		acpi_handle_debug(crwd->handle,
+				  "unable to find resource source\n");
+		return AE_OK;
+	}
+	csi2_res_src_length = csi2_res_src->string_length;
+	if (!csi2_res_src_length) {
+		acpi_handle_debug(crwd->handle,
+				  "invalid resource source string length\n");
+		return AE_OK;
+	}
+
+	conn = kmalloc(struct_size(conn, remote_name, csi2_res_src_length + 1),
+		       GFP_KERNEL);
+	if (!conn)
+		return AE_OK;
+
+	conn->csi2_data = *csi2_res;
+	strscpy(conn->remote_name, csi2_res_src->string_ptr, csi2_res_src_length);
+	conn->csi2_data.resource_source.string_ptr = conn->remote_name;
+	conn->remote_handle = remote_handle;
+
+	list_add(&conn->entry, &crwd->connections);
+
+	return AE_OK;
+}
+
+static struct crs_csi2 *acpi_mipi_add_crs_csi2(acpi_handle handle,
+					       struct list_head *list)
+{
+	struct crs_csi2 *csi2;
+
+	csi2 = kzalloc(sizeof(*csi2), GFP_KERNEL);
+	if (!csi2)
+		return NULL;
+
+	csi2->handle = handle;
+	INIT_LIST_HEAD(&csi2->connections);
+	csi2->port_count = 1;
+
+	if (ACPI_FAILURE(acpi_attach_data(handle, acpi_mipi_data_tag, csi2))) {
+		kfree(csi2);
+		return NULL;
+	}
+
+	list_add(&csi2->entry, list);
+
+	return csi2;
+}
+
+static struct crs_csi2 *acpi_mipi_get_crs_csi2(acpi_handle handle)
+{
+	struct crs_csi2 *csi2;
+
+	if (ACPI_FAILURE(acpi_get_data_full(handle, acpi_mipi_data_tag,
+					    (void **)&csi2, NULL)))
+		return NULL;
+
+	return csi2;
+}
+
+static void csi_csr2_release_connections(struct list_head *list)
+{
+	struct crs_csi2_connection *conn, *conn_tmp;
+
+	list_for_each_entry_safe(conn, conn_tmp, list, entry) {
+		list_del(&conn->entry);
+		kfree(conn);
+	}
+}
+
+static void acpi_mipi_del_crs_csi2(struct crs_csi2 *csi2)
+{
+	list_del(&csi2->entry);
+	acpi_detach_data(csi2->handle, acpi_mipi_data_tag);
+	kfree(csi2->swnodes);
+	csi_csr2_release_connections(&csi2->connections);
+	kfree(csi2);
+}
+
+/**
+ * acpi_mipi_check_crs_csi2 - Look for CSI-2 resources in _CRS
+ * @handle: Device object handle to evaluate _CRS for.
+ *
+ * Find all CSI-2 resource descriptors in the given device's _CRS
+ * and collect them into a list.
+ */
+void acpi_mipi_check_crs_csi2(acpi_handle handle)
+{
+	struct csi2_resources_walk_data crwd = {
+		.handle = handle,
+		.connections = LIST_HEAD_INIT(crwd.connections),
+	};
+	struct crs_csi2 *csi2;
+
+	/*
+	 * Avoid allocating _CRS CSI-2 objects for devices without any CSI-2
+	 * resource descriptions in _CRS to reduce overhead.
+	 */
+	acpi_walk_resources(handle, METHOD_NAME__CRS, parse_csi2_resource, &crwd);
+	if (list_empty(&crwd.connections))
+		return;
+
+	/*
+	 * Create a _CRS CSI-2 entry to store the extracted connection
+	 * information and add it to the global list.
+	 */
+	csi2 = acpi_mipi_add_crs_csi2(handle, &acpi_mipi_crs_csi2_list);
+	if (!csi2) {
+		csi_csr2_release_connections(&crwd.connections);
+		return; /* Nothing really can be done about this. */
+	}
+
+	list_replace(&crwd.connections, &csi2->connections);
+}
+
+#define NO_CSI2_PORT (UINT_MAX - 1)
+
+static void alloc_crs_csi2_swnodes(struct crs_csi2 *csi2)
+{
+	size_t port_count = csi2->port_count;
+	struct acpi_device_software_nodes *swnodes;
+	size_t alloc_size;
+	unsigned int i;
+
+	/*
+	 * Allocate memory for ports, node pointers (number of nodes +
+	 * 1 (guardian), nodes (root + number of ports * 2 (because for
+	 * every port there is an endpoint)).
+	 */
+	if (check_mul_overflow(sizeof(*swnodes->ports) +
+			       sizeof(*swnodes->nodes) * 2 +
+			       sizeof(*swnodes->nodeptrs) * 2,
+			       port_count, &alloc_size) ||
+	    check_add_overflow(sizeof(*swnodes) +
+			       sizeof(*swnodes->nodes) +
+			       sizeof(*swnodes->nodeptrs) * 2,
+			       alloc_size, &alloc_size)) {
+		acpi_handle_info(csi2->handle,
+				 "too many _CRS CSI-2 resource handles (%zu)",
+				 port_count);
+		return;
+	}
+
+	swnodes = kmalloc(alloc_size, GFP_KERNEL);
+	if (!swnodes)
+		return;
+
+	swnodes->ports = (struct acpi_device_software_node_port *)(swnodes + 1);
+	swnodes->nodes = (struct software_node *)(swnodes->ports + port_count);
+	swnodes->nodeptrs = (const struct software_node **)(swnodes->nodes + 1 +
+				2 * port_count);
+	swnodes->num_ports = port_count;
+
+	for (i = 0; i < 2 * port_count + 1; i++)
+		swnodes->nodeptrs[i] = &swnodes->nodes[i];
+
+	swnodes->nodeptrs[i] = NULL;
+
+	for (i = 0; i < port_count; i++)
+		swnodes->ports[i].port_nr = NO_CSI2_PORT;
+
+	csi2->swnodes = swnodes;
+}
+
+#define ACPI_CRS_CSI2_PHY_TYPE_C	0
+#define ACPI_CRS_CSI2_PHY_TYPE_D	1
+
+static unsigned int next_csi2_port_index(struct acpi_device_software_nodes *swnodes,
+					 unsigned int port_nr)
+{
+	unsigned int i;
+
+	for (i = 0; i < swnodes->num_ports; i++) {
+		struct acpi_device_software_node_port *port = &swnodes->ports[i];
+
+		if (port->port_nr == port_nr)
+			return i;
+
+		if (port->port_nr == NO_CSI2_PORT) {
+			port->port_nr = port_nr;
+			return i;
+		}
+	}
+
+	return NO_CSI2_PORT;
+}
+
+/* Print graph port name into a buffer, return non-zero on failure. */
+#define GRAPH_PORT_NAME(var, num)					    \
+	(snprintf((var), sizeof(var), SWNODE_GRAPH_PORT_NAME_FMT, (num)) >= \
+	 sizeof(var))
+
+static void extract_crs_csi2_conn_info(acpi_handle local_handle,
+				       struct acpi_device_software_nodes *local_swnodes,
+				       struct crs_csi2_connection *conn)
+{
+	struct crs_csi2 *remote_csi2 = acpi_mipi_get_crs_csi2(conn->remote_handle);
+	struct acpi_device_software_nodes *remote_swnodes;
+	struct acpi_device_software_node_port *local_port, *remote_port;
+	struct software_node *local_node, *remote_node;
+	unsigned int local_index, remote_index;
+	unsigned int bus_type;
+
+	/*
+	 * If the previous steps have failed to make room for a _CRS CSI-2
+	 * representation for the remote end of the given connection, skip it.
+	 */
+	if (!remote_csi2)
+		return;
+
+	remote_swnodes = remote_csi2->swnodes;
+	if (!remote_swnodes)
+		return;
+
+	switch (conn->csi2_data.phy_type) {
+	case ACPI_CRS_CSI2_PHY_TYPE_C:
+		bus_type = V4L2_FWNODE_BUS_TYPE_CSI2_CPHY;
+		break;
+
+	case ACPI_CRS_CSI2_PHY_TYPE_D:
+		bus_type = V4L2_FWNODE_BUS_TYPE_CSI2_DPHY;
+		break;
+
+	default:
+		acpi_handle_info(local_handle, "unknown CSI-2 PHY type %u\n",
+				 conn->csi2_data.phy_type);
+		return;
+	}
+
+	local_index = next_csi2_port_index(local_swnodes,
+					   conn->csi2_data.local_port_instance);
+	if (WARN_ON_ONCE(local_index >= local_swnodes->num_ports))
+		return;
+
+	remote_index = next_csi2_port_index(remote_swnodes,
+					    conn->csi2_data.resource_source.index);
+	if (WARN_ON_ONCE(remote_index >= remote_swnodes->num_ports))
+		return;
+
+	local_port = &local_swnodes->ports[local_index];
+	local_node = &local_swnodes->nodes[ACPI_DEVICE_SWNODE_EP(local_index)];
+	local_port->crs_csi2_local = true;
+
+	remote_port = &remote_swnodes->ports[remote_index];
+	remote_node = &remote_swnodes->nodes[ACPI_DEVICE_SWNODE_EP(remote_index)];
+
+	local_port->remote_ep[0] = SOFTWARE_NODE_REFERENCE(remote_node);
+	remote_port->remote_ep[0] = SOFTWARE_NODE_REFERENCE(local_node);
+
+	local_port->ep_props[ACPI_DEVICE_SWNODE_EP_REMOTE_EP] =
+			PROPERTY_ENTRY_REF_ARRAY("remote-endpoint",
+						 local_port->remote_ep);
+
+	local_port->ep_props[ACPI_DEVICE_SWNODE_EP_BUS_TYPE] =
+			PROPERTY_ENTRY_U32("bus-type", bus_type);
+
+	local_port->ep_props[ACPI_DEVICE_SWNODE_EP_REG] =
+			PROPERTY_ENTRY_U32("reg", 0);
+
+	local_port->port_props[ACPI_DEVICE_SWNODE_PORT_REG] =
+			PROPERTY_ENTRY_U32("reg", conn->csi2_data.local_port_instance);
+
+	if (GRAPH_PORT_NAME(local_port->port_name,
+			    conn->csi2_data.local_port_instance))
+		acpi_handle_info(local_handle, "local port %u name too long",
+				 conn->csi2_data.local_port_instance);
+
+	remote_port->ep_props[ACPI_DEVICE_SWNODE_EP_REMOTE_EP] =
+			PROPERTY_ENTRY_REF_ARRAY("remote-endpoint",
+						 remote_port->remote_ep);
+
+	remote_port->ep_props[ACPI_DEVICE_SWNODE_EP_BUS_TYPE] =
+			PROPERTY_ENTRY_U32("bus-type", bus_type);
+
+	remote_port->ep_props[ACPI_DEVICE_SWNODE_EP_REG] =
+			PROPERTY_ENTRY_U32("reg", 0);
+
+	remote_port->port_props[ACPI_DEVICE_SWNODE_PORT_REG] =
+			PROPERTY_ENTRY_U32("reg", conn->csi2_data.resource_source.index);
+
+	if (GRAPH_PORT_NAME(remote_port->port_name,
+			    conn->csi2_data.resource_source.index))
+		acpi_handle_info(local_handle, "remote port %u name too long",
+				 conn->csi2_data.resource_source.index);
+}
+
+static void prepare_crs_csi2_swnodes(struct crs_csi2 *csi2)
+{
+	struct acpi_device_software_nodes *local_swnodes = csi2->swnodes;
+	acpi_handle local_handle = csi2->handle;
+	struct crs_csi2_connection *conn;
+
+	/* Bail out if the allocation of swnodes has failed. */
+	if (!local_swnodes)
+		return;
+
+	list_for_each_entry(conn, &csi2->connections, entry)
+		extract_crs_csi2_conn_info(local_handle, local_swnodes, conn);
+}
+
+/**
+ * acpi_mipi_scan_crs_csi2 - Create ACPI _CRS CSI-2 software nodes
+ *
+ * Note that this function must be called before any struct acpi_device objects
+ * are bound to any ACPI drivers or scan handlers, so it cannot assume the
+ * existence of struct acpi_device objects for every device present in the ACPI
+ * namespace.
+ *
+ * acpi_scan_lock in scan.c must be held when calling this function.
+ */
+void acpi_mipi_scan_crs_csi2(void)
+{
+	struct crs_csi2 *csi2;
+	LIST_HEAD(aux_list);
+
+	/* Count references to each ACPI handle in the CSI-2 connection graph. */
+	list_for_each_entry(csi2, &acpi_mipi_crs_csi2_list, entry) {
+		struct crs_csi2_connection *conn;
+
+		list_for_each_entry(conn, &csi2->connections, entry) {
+			struct crs_csi2 *remote_csi2;
+
+			csi2->port_count++;
+
+			remote_csi2 = acpi_mipi_get_crs_csi2(conn->remote_handle);
+			if (remote_csi2) {
+				remote_csi2->port_count++;
+				continue;
+			}
+			/*
+			 * The remote endpoint has no _CRS CSI-2 list entry yet,
+			 * so create one for it and add it to the list.
+			 */
+			acpi_mipi_add_crs_csi2(conn->remote_handle, &aux_list);
+		}
+	}
+	list_splice(&aux_list, &acpi_mipi_crs_csi2_list);
+
+	/*
+	 * Allocate software nodes for representing the CSI-2 information.
+	 *
+	 * This needs to be done for all of the list entries in one go, because
+	 * they may point to each other without restrictions and the next step
+	 * relies on the availability of swnodes memory for each list entry.
+	 */
+	list_for_each_entry(csi2, &acpi_mipi_crs_csi2_list, entry)
+		alloc_crs_csi2_swnodes(csi2);
+
+	/*
+	 * Set up software node properties using data from _CRS CSI-2 resource
+	 * descriptors.
+	 */
+	list_for_each_entry(csi2, &acpi_mipi_crs_csi2_list, entry)
+		prepare_crs_csi2_swnodes(csi2);
+}
+
+/*
+ * Get the index of the next property in the property array, with a given
+ * maximum value.
+ */
+#define NEXT_PROPERTY(index, max)			\
+	(WARN_ON((index) > ACPI_DEVICE_SWNODE_##max) ?	\
+	 ACPI_DEVICE_SWNODE_##max : (index)++)
+
+static void init_csi2_port_local(struct acpi_device *adev,
+				 struct acpi_device_software_node_port *port,
+				 struct fwnode_handle *port_fwnode,
+				 unsigned int index)
+{
+	acpi_handle handle = acpi_device_handle(adev);
+	unsigned int num_link_freqs;
+	int ret;
+
+	ret = fwnode_property_count_u64(port_fwnode, "mipi-img-link-frequencies");
+	if (ret <= 0)
+		return;
+
+	num_link_freqs = ret;
+	if (num_link_freqs > ACPI_DEVICE_CSI2_DATA_LANES) {
+		acpi_handle_info(handle, "Too many link frequencies: %u\n",
+				 num_link_freqs);
+		num_link_freqs = ACPI_DEVICE_CSI2_DATA_LANES;
+	}
+
+	ret = fwnode_property_read_u64_array(port_fwnode,
+					     "mipi-img-link-frequencies",
+					     port->link_frequencies,
+					     num_link_freqs);
+	if (ret) {
+		acpi_handle_info(handle, "Unable to get link frequencies (%d)\n",
+				 ret);
+		return;
+	}
+
+	port->ep_props[NEXT_PROPERTY(index, EP_LINK_FREQUENCIES)] =
+				PROPERTY_ENTRY_U64_ARRAY_LEN("link-frequencies",
+							     port->link_frequencies,
+							     num_link_freqs);
+}
+
+static void init_csi2_port(struct acpi_device *adev,
+			   struct acpi_device_software_nodes *swnodes,
+			   struct acpi_device_software_node_port *port,
+			   struct fwnode_handle *port_fwnode,
+			   unsigned int port_index)
+{
+	unsigned int ep_prop_index = ACPI_DEVICE_SWNODE_EP_CLOCK_LANES;
+	acpi_handle handle = acpi_device_handle(adev);
+	u8 val[ACPI_DEVICE_CSI2_DATA_LANES];
+	int num_lanes = 0;
+	int ret;
+
+	if (GRAPH_PORT_NAME(port->port_name, port->port_nr))
+		return;
+
+	swnodes->nodes[ACPI_DEVICE_SWNODE_PORT(port_index)] =
+			SOFTWARE_NODE(port->port_name, port->port_props,
+				      &swnodes->nodes[ACPI_DEVICE_SWNODE_ROOT]);
+
+	ret = fwnode_property_read_u8(port_fwnode, "mipi-img-clock-lane", val);
+	if (!ret)
+		port->ep_props[NEXT_PROPERTY(ep_prop_index, EP_CLOCK_LANES)] =
+			PROPERTY_ENTRY_U32("clock-lanes", val[0]);
+
+	ret = fwnode_property_count_u8(port_fwnode, "mipi-img-data-lanes");
+	if (ret > 0) {
+		num_lanes = ret;
+
+		if (num_lanes > ACPI_DEVICE_CSI2_DATA_LANES) {
+			acpi_handle_info(handle, "Too many data lanes: %u\n",
+					 num_lanes);
+			num_lanes = ACPI_DEVICE_CSI2_DATA_LANES;
+		}
+
+		ret = fwnode_property_read_u8_array(port_fwnode,
+						    "mipi-img-data-lanes",
+						    val, num_lanes);
+		if (!ret) {
+			unsigned int i;
+
+			for (i = 0; i < num_lanes; i++)
+				port->data_lanes[i] = val[i];
+
+			port->ep_props[NEXT_PROPERTY(ep_prop_index, EP_DATA_LANES)] =
+				PROPERTY_ENTRY_U32_ARRAY_LEN("data-lanes",
+							     port->data_lanes,
+							     num_lanes);
+		}
+	}
+
+	ret = fwnode_property_count_u8(port_fwnode, "mipi-img-lane-polarities");
+	if (ret < 0) {
+		acpi_handle_debug(handle, "Lane polarity bytes missing\n");
+	} else if (ret * BITS_PER_TYPE(u8) < num_lanes + 1) {
+		acpi_handle_info(handle, "Too few lane polarity bits (%zu vs. %d)\n",
+				 ret * BITS_PER_TYPE(u8), num_lanes + 1);
+	} else {
+		unsigned long mask = 0;
+		int byte_count = ret;
+		unsigned int i;
+
+		/*
+		 * The total number of lanes is ACPI_DEVICE_CSI2_DATA_LANES + 1
+		 * (data lanes + clock lane).  It is not expected to ever be
+		 * greater than the number of bits in an unsigned long
+		 * variable, but ensure that this is the case.
+		 */
+		BUILD_BUG_ON(BITS_PER_TYPE(unsigned long) <= ACPI_DEVICE_CSI2_DATA_LANES);
+
+		if (byte_count > sizeof(mask)) {
+			acpi_handle_info(handle, "Too many lane polarities: %d\n",
+					 byte_count);
+			byte_count = sizeof(mask);
+		}
+		fwnode_property_read_u8_array(port_fwnode, "mipi-img-lane-polarities",
+					      val, byte_count);
+
+		for (i = 0; i < byte_count; i++)
+			mask |= (unsigned long)val[i] << BITS_PER_TYPE(u8) * i;
+
+		for (i = 0; i <= num_lanes; i++)
+			port->lane_polarities[i] = test_bit(i, &mask);
+
+		port->ep_props[NEXT_PROPERTY(ep_prop_index, EP_LANE_POLARITIES)] =
+				PROPERTY_ENTRY_U32_ARRAY_LEN("lane-polarities",
+							     port->lane_polarities,
+							     num_lanes + 1);
+	}
+
+	swnodes->nodes[ACPI_DEVICE_SWNODE_EP(port_index)] =
+		SOFTWARE_NODE("endpoint@0", swnodes->ports[port_index].ep_props,
+			      &swnodes->nodes[ACPI_DEVICE_SWNODE_PORT(port_index)]);
+
+	if (port->crs_csi2_local)
+		init_csi2_port_local(adev, port, port_fwnode, ep_prop_index);
+}
+
+#define MIPI_IMG_PORT_PREFIX "mipi-img-port-"
+
+static struct fwnode_handle *get_mipi_port_handle(struct fwnode_handle *adev_fwnode,
+						  unsigned int port_nr)
+{
+	char port_name[sizeof(MIPI_IMG_PORT_PREFIX) + 2];
+
+	if (snprintf(port_name, sizeof(port_name), "%s%u",
+		     MIPI_IMG_PORT_PREFIX, port_nr) >= sizeof(port_name))
+		return NULL;
+
+	return fwnode_get_named_child_node(adev_fwnode, port_name);
+}
+
+static void init_crs_csi2_swnodes(struct crs_csi2 *csi2)
+{
+	struct acpi_buffer buffer = { .length = ACPI_ALLOCATE_BUFFER };
+	struct acpi_device_software_nodes *swnodes = csi2->swnodes;
+	acpi_handle handle = csi2->handle;
+	unsigned int prop_index = 0;
+	struct fwnode_handle *adev_fwnode;
+	struct acpi_device *adev;
+	acpi_status status;
+	unsigned int i;
+	u32 val;
+	int ret;
+
+	/*
+	 * Bail out if the swnodes are not available (either they have not been
+	 * allocated or they have been assigned to the device already).
+	 */
+	if (!swnodes)
+		return;
+
+	adev = acpi_fetch_acpi_dev(handle);
+	if (!adev)
+		return;
+
+	adev_fwnode = acpi_fwnode_handle(adev);
+
+	/*
+	 * If the "rotation" property is not present, but _PLD is there,
+	 * evaluate it to get the "rotation" value.
+	 */
+	if (!fwnode_property_present(adev_fwnode, "rotation")) {
+		struct acpi_pld_info *pld;
+
+		status = acpi_get_physical_device_location(handle, &pld);
+		if (ACPI_SUCCESS(status)) {
+			swnodes->dev_props[NEXT_PROPERTY(prop_index, DEV_ROTATION)] =
+					PROPERTY_ENTRY_U32("rotation",
+							   pld->rotation * 45U);
+			kfree(pld);
+		}
+	}
+
+	if (!fwnode_property_read_u32(adev_fwnode, "mipi-img-clock-frequency", &val))
+		swnodes->dev_props[NEXT_PROPERTY(prop_index, DEV_CLOCK_FREQUENCY)] =
+			PROPERTY_ENTRY_U32("clock-frequency", val);
+
+	if (!fwnode_property_read_u32(adev_fwnode, "mipi-img-led-max-current", &val))
+		swnodes->dev_props[NEXT_PROPERTY(prop_index, DEV_LED_MAX_MICROAMP)] =
+			PROPERTY_ENTRY_U32("led-max-microamp", val);
+
+	if (!fwnode_property_read_u32(adev_fwnode, "mipi-img-flash-max-current", &val))
+		swnodes->dev_props[NEXT_PROPERTY(prop_index, DEV_FLASH_MAX_MICROAMP)] =
+			PROPERTY_ENTRY_U32("flash-max-microamp", val);
+
+	if (!fwnode_property_read_u32(adev_fwnode, "mipi-img-flash-max-timeout-us", &val))
+		swnodes->dev_props[NEXT_PROPERTY(prop_index, DEV_FLASH_MAX_TIMEOUT_US)] =
+			PROPERTY_ENTRY_U32("flash-max-timeout-us", val);
+
+	status = acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer);
+	if (ACPI_FAILURE(status)) {
+		acpi_handle_info(handle, "Unable to get the path name\n");
+		return;
+	}
+
+	swnodes->nodes[ACPI_DEVICE_SWNODE_ROOT] =
+			SOFTWARE_NODE(buffer.pointer, swnodes->dev_props, NULL);
+
+	for (i = 0; i < swnodes->num_ports; i++) {
+		struct acpi_device_software_node_port *port = &swnodes->ports[i];
+		struct fwnode_handle *port_fwnode;
+
+		/*
+		 * The MIPI DisCo for Imaging specification defines _DSD device
+		 * properties for providing CSI-2 port parameters that can be
+		 * accessed through the generic device properties framework.  To
+		 * access them, it is first necessary to find the data node
+		 * representing the port under the given ACPI device object.
+		 */
+		port_fwnode = get_mipi_port_handle(adev_fwnode, port->port_nr);
+		if (!port_fwnode) {
+			acpi_handle_info(handle,
+					 "MIPI port name too long for port %u\n",
+					 port->port_nr);
+			continue;
+		}
+
+		init_csi2_port(adev, swnodes, port, port_fwnode, i);
+
+		fwnode_handle_put(port_fwnode);
+	}
+
+	ret = software_node_register_node_group(swnodes->nodeptrs);
+	if (ret < 0) {
+		acpi_handle_info(handle,
+				 "Unable to register software nodes (%d)\n", ret);
+		return;
+	}
+
+	adev->swnodes = swnodes;
+	adev_fwnode->secondary = software_node_fwnode(swnodes->nodes);
+
+	/*
+	 * Prevents the swnodes from this csi2 entry from being assigned again
+	 * or freed prematurely.
+	 */
+	csi2->swnodes = NULL;
+}
+
+/**
+ * acpi_mipi_init_crs_csi2_swnodes - Initialize _CRS CSI-2 software nodes
+ *
+ * Use MIPI DisCo for Imaging device properties to finalize the initialization
+ * of CSI-2 software nodes for all ACPI device objects that have been already
+ * enumerated.
+ */
+void acpi_mipi_init_crs_csi2_swnodes(void)
+{
+	struct crs_csi2 *csi2, *csi2_tmp;
+
+	list_for_each_entry_safe(csi2, csi2_tmp, &acpi_mipi_crs_csi2_list, entry)
+		init_crs_csi2_swnodes(csi2);
+}
+
+/**
+ * acpi_mipi_crs_csi2_cleanup - Free _CRS CSI-2 temporary data
+ */
+void acpi_mipi_crs_csi2_cleanup(void)
+{
+	struct crs_csi2 *csi2, *csi2_tmp;
+
+	list_for_each_entry_safe(csi2, csi2_tmp, &acpi_mipi_crs_csi2_list, entry)
+		acpi_mipi_del_crs_csi2(csi2);
+}
diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c
index 12f330b0eac0..0214518fc582 100644
--- a/drivers/acpi/numa/srat.c
+++ b/drivers/acpi/numa/srat.c
@@ -67,9 +67,9 @@ int acpi_map_pxm_to_node(int pxm)
 	node = pxm_to_node_map[pxm];
 
 	if (node == NUMA_NO_NODE) {
-		if (nodes_weight(nodes_found_map) >= MAX_NUMNODES)
-			return NUMA_NO_NODE;
 		node = first_unset_node(nodes_found_map);
+		if (node >= MAX_NUMNODES)
+			return NUMA_NO_NODE;
 		__acpi_map_pxm_to_node(pxm, node);
 		node_set(node, nodes_found_map);
 	}
@@ -183,7 +183,7 @@ static int __init slit_valid(struct acpi_table_slit *slit)
 	int i, j;
 	int d = slit->locality_count;
 	for (i = 0; i < d; i++) {
-		for (j = 0; j < d; j++)  {
+		for (j = 0; j < d; j++) {
 			u8 val = slit->entry[d*i + j];
 			if (i == j) {
 				if (val != LOCAL_DISTANCE)
@@ -430,7 +430,7 @@ acpi_parse_gi_affinity(union acpi_subtable_headers *header,
 		return -EINVAL;
 
 	node = acpi_map_pxm_to_node(gi_affinity->proximity_domain);
-	if (node == NUMA_NO_NODE || node >= MAX_NUMNODES) {
+	if (node == NUMA_NO_NODE) {
 		pr_err("SRAT: Too many proximity domains.\n");
 		return -EINVAL;
 	}
@@ -532,7 +532,7 @@ int __init acpi_numa_init(void)
 	 */
 
 	/* fake_pxm is the next unused PXM value after SRAT parsing */
-	for (i = 0, fake_pxm = -1; i < MAX_NUMNODES - 1; i++) {
+	for (i = 0, fake_pxm = -1; i < MAX_NUMNODES; i++) {
 		if (node_to_pxm_map[i] > fake_pxm)
 			fake_pxm = node_to_pxm_map[i];
 	}
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index c09cc3c68633..70af3fbbebe5 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -544,11 +544,7 @@ acpi_os_predefined_override(const struct acpi_predefined_names *init_val,
 
 static irqreturn_t acpi_irq(int irq, void *dev_id)
 {
-	u32 handled;
-
-	handled = (*acpi_irq_handler) (acpi_irq_context);
-
-	if (handled) {
+	if ((*acpi_irq_handler)(acpi_irq_context)) {
 		acpi_irq_handled++;
 		return IRQ_HANDLED;
 	} else {
@@ -582,7 +578,8 @@ acpi_os_install_interrupt_handler(u32 gsi, acpi_osd_handler handler,
 
 	acpi_irq_handler = handler;
 	acpi_irq_context = context;
-	if (request_irq(irq, acpi_irq, IRQF_SHARED, "acpi", acpi_irq)) {
+	if (request_threaded_irq(irq, NULL, acpi_irq, IRQF_SHARED | IRQF_ONESHOT,
+			         "acpi", acpi_irq)) {
 		pr_err("SCI (IRQ%d) allocation failed\n", irq);
 		acpi_irq_handler = NULL;
 		return AE_NOT_ACQUIRED;
@@ -1063,9 +1060,7 @@ int __init acpi_debugger_init(void)
 acpi_status acpi_os_execute(acpi_execute_type type,
 			    acpi_osd_exec_callback function, void *context)
 {
-	acpi_status status = AE_OK;
 	struct acpi_os_dpc *dpc;
-	struct workqueue_struct *queue;
 	int ret;
 
 	ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
@@ -1076,9 +1071,9 @@ acpi_status acpi_os_execute(acpi_execute_type type,
 		ret = acpi_debugger_create_thread(function, context);
 		if (ret) {
 			pr_err("Kernel thread creation failed\n");
-			status = AE_ERROR;
+			return AE_ERROR;
 		}
-		goto out_thread;
+		return AE_OK;
 	}
 
 	/*
@@ -1096,43 +1091,41 @@ acpi_status acpi_os_execute(acpi_execute_type type,
 
 	dpc->function = function;
 	dpc->context = context;
+	INIT_WORK(&dpc->work, acpi_os_execute_deferred);
 
 	/*
 	 * To prevent lockdep from complaining unnecessarily, make sure that
 	 * there is a different static lockdep key for each workqueue by using
 	 * INIT_WORK() for each of them separately.
 	 */
-	if (type == OSL_NOTIFY_HANDLER) {
-		queue = kacpi_notify_wq;
-		INIT_WORK(&dpc->work, acpi_os_execute_deferred);
-	} else if (type == OSL_GPE_HANDLER) {
-		queue = kacpid_wq;
-		INIT_WORK(&dpc->work, acpi_os_execute_deferred);
-	} else {
+	switch (type) {
+	case OSL_NOTIFY_HANDLER:
+		ret = queue_work(kacpi_notify_wq, &dpc->work);
+		break;
+	case OSL_GPE_HANDLER:
+		/*
+		 * On some machines, a software-initiated SMI causes corruption
+		 * unless the SMI runs on CPU 0.  An SMI can be initiated by
+		 * any AML, but typically it's done in GPE-related methods that
+		 * are run via workqueues, so we can avoid the known corruption
+		 * cases by always queueing on CPU 0.
+		 */
+		ret = queue_work_on(0, kacpid_wq, &dpc->work);
+		break;
+	default:
 		pr_err("Unsupported os_execute type %d.\n", type);
-		status = AE_ERROR;
+		goto err;
 	}
-
-	if (ACPI_FAILURE(status))
-		goto err_workqueue;
-
-	/*
-	 * On some machines, a software-initiated SMI causes corruption unless
-	 * the SMI runs on CPU 0.  An SMI can be initiated by any AML, but
-	 * typically it's done in GPE-related methods that are run via
-	 * workqueues, so we can avoid the known corruption cases by always
-	 * queueing on CPU 0.
-	 */
-	ret = queue_work_on(0, queue, &dpc->work);
 	if (!ret) {
 		pr_err("Unable to queue work\n");
-		status = AE_ERROR;
+		goto err;
 	}
-err_workqueue:
-	if (ACPI_FAILURE(status))
-		kfree(dpc);
-out_thread:
-	return status;
+
+	return AE_OK;
+
+err:
+	kfree(dpc);
+	return AE_ERROR;
 }
 EXPORT_SYMBOL(acpi_os_execute);
 
@@ -1522,20 +1515,18 @@ void acpi_os_delete_lock(acpi_spinlock handle)
 acpi_cpu_flags acpi_os_acquire_lock(acpi_spinlock lockp)
 	__acquires(lockp)
 {
-	acpi_cpu_flags flags;
-
-	spin_lock_irqsave(lockp, flags);
-	return flags;
+	spin_lock(lockp);
+	return 0;
 }
 
 /*
  * Release a spinlock. See above.
  */
 
-void acpi_os_release_lock(acpi_spinlock lockp, acpi_cpu_flags flags)
+void acpi_os_release_lock(acpi_spinlock lockp, acpi_cpu_flags not_used)
 	__releases(lockp)
 {
-	spin_unlock_irqrestore(lockp, flags);
+	spin_unlock(lockp);
 }
 
 #ifndef ACPI_USE_LOCAL_CACHE
@@ -1672,7 +1663,7 @@ acpi_status __init acpi_os_initialize(void)
 acpi_status __init acpi_os_initialize1(void)
 {
 	kacpid_wq = alloc_workqueue("kacpid", 0, 1);
-	kacpi_notify_wq = alloc_workqueue("kacpi_notify", 0, 1);
+	kacpi_notify_wq = alloc_workqueue("kacpi_notify", 0, 0);
 	kacpi_hotplug_wq = alloc_ordered_workqueue("kacpi_hotplug", 0);
 	BUG_ON(!kacpid_wq);
 	BUG_ON(!kacpi_notify_wq);
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 3a34a8c425fe..55437f5e0c3a 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -592,7 +592,7 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
 	while (1) {
 
 		if (cx->entry_method == ACPI_CSTATE_HALT)
-			safe_halt();
+			raw_safe_halt();
 		else if (cx->entry_method == ACPI_CSTATE_SYSTEMIO) {
 			io_idle(cx->address);
 		} else
diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c
index b7c6287eccca..1219adb11ab9 100644
--- a/drivers/acpi/processor_thermal.c
+++ b/drivers/acpi/processor_thermal.c
@@ -17,6 +17,8 @@
 #include <acpi/processor.h>
 #include <linux/uaccess.h>
 
+#include "internal.h"
+
 #ifdef CONFIG_CPU_FREQ
 
 /* If a passive cooling situation is detected, primarily CPUfreq is used, as it
@@ -26,12 +28,21 @@
  */
 
 #define CPUFREQ_THERMAL_MIN_STEP 0
-#define CPUFREQ_THERMAL_MAX_STEP 3
 
-static DEFINE_PER_CPU(unsigned int, cpufreq_thermal_reduction_pctg);
+static int cpufreq_thermal_max_step __read_mostly = 3;
+
+/*
+ * Minimum throttle percentage for processor_thermal cooling device.
+ * The processor_thermal driver uses it to calculate the percentage amount by
+ * which cpu frequency must be reduced for each cooling state. This is also used
+ * to calculate the maximum number of throttling steps or cooling states.
+ */
+static int cpufreq_thermal_reduction_pctg __read_mostly = 20;
 
-#define reduction_pctg(cpu) \
-	per_cpu(cpufreq_thermal_reduction_pctg, phys_package_first_cpu(cpu))
+static DEFINE_PER_CPU(unsigned int, cpufreq_thermal_reduction_step);
+
+#define reduction_step(cpu) \
+	per_cpu(cpufreq_thermal_reduction_step, phys_package_first_cpu(cpu))
 
 /*
  * Emulate "per package data" using per cpu data (which should really be
@@ -71,7 +82,7 @@ static int cpufreq_get_max_state(unsigned int cpu)
 	if (!cpu_has_cpufreq(cpu))
 		return 0;
 
-	return CPUFREQ_THERMAL_MAX_STEP;
+	return cpufreq_thermal_max_step;
 }
 
 static int cpufreq_get_cur_state(unsigned int cpu)
@@ -79,7 +90,7 @@ static int cpufreq_get_cur_state(unsigned int cpu)
 	if (!cpu_has_cpufreq(cpu))
 		return 0;
 
-	return reduction_pctg(cpu);
+	return reduction_step(cpu);
 }
 
 static int cpufreq_set_cur_state(unsigned int cpu, int state)
@@ -92,7 +103,7 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
 	if (!cpu_has_cpufreq(cpu))
 		return 0;
 
-	reduction_pctg(cpu) = state;
+	reduction_step(cpu) = state;
 
 	/*
 	 * Update all the CPUs in the same package because they all
@@ -113,7 +124,8 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
 		if (!policy)
 			return -EINVAL;
 
-		max_freq = (policy->cpuinfo.max_freq * (100 - reduction_pctg(i) * 20)) / 100;
+		max_freq = (policy->cpuinfo.max_freq *
+			    (100 - reduction_step(i) * cpufreq_thermal_reduction_pctg)) / 100;
 
 		cpufreq_cpu_put(policy);
 
@@ -126,10 +138,29 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
 	return 0;
 }
 
+static void acpi_thermal_cpufreq_config(void)
+{
+	int cpufreq_pctg = acpi_arch_thermal_cpufreq_pctg();
+
+	if (!cpufreq_pctg)
+		return;
+
+	cpufreq_thermal_reduction_pctg = cpufreq_pctg;
+
+	/*
+	 * Derive the MAX_STEP from minimum throttle percentage so that the reduction
+	 * percentage doesn't end up becoming negative. Also, cap the MAX_STEP so that
+	 * the CPU performance doesn't become 0.
+	 */
+	cpufreq_thermal_max_step = (100 / cpufreq_pctg) - 2;
+}
+
 void acpi_thermal_cpufreq_init(struct cpufreq_policy *policy)
 {
 	unsigned int cpu;
 
+	acpi_thermal_cpufreq_config();
+
 	for_each_cpu(cpu, policy->related_cpus) {
 		struct acpi_processor *pr = per_cpu(processors, cpu);
 		int ret;
@@ -190,7 +221,7 @@ static int acpi_processor_max_state(struct acpi_processor *pr)
 
 	/*
 	 * There exists four states according to
-	 * cpufreq_thermal_reduction_pctg. 0, 1, 2, 3
+	 * cpufreq_thermal_reduction_step. 0, 1, 2, 3
 	 */
 	max_state += cpufreq_get_max_state(pr->id);
 	if (pr->flags.throttling)
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 6979a3f9f90a..07d76fb740b6 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -2,14 +2,17 @@
 /*
  * ACPI device specific properties support.
  *
- * Copyright (C) 2014, Intel Corporation
+ * Copyright (C) 2014 - 2023, Intel Corporation
  * All rights reserved.
  *
  * Authors: Mika Westerberg <mika.westerberg@linux.intel.com>
  *          Darren Hart <dvhart@linux.intel.com>
  *          Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *          Sakari Ailus <sakari.ailus@linux.intel.com>
  */
 
+#define pr_fmt(fmt) "ACPI: " fmt
+
 #include <linux/acpi.h>
 #include <linux/device.h>
 #include <linux/export.h>
@@ -801,27 +804,15 @@ static int acpi_get_ref_args(struct fwnode_reference_args *args,
 	u32 nargs = 0, i;
 
 	/*
-	 * Find the referred data extension node under the
-	 * referred device node.
-	 */
-	for (; *element < end && (*element)->type == ACPI_TYPE_STRING;
-	     (*element)++) {
-		const char *child_name = (*element)->string.pointer;
-
-		ref_fwnode = acpi_fwnode_get_named_child_node(ref_fwnode, child_name);
-		if (!ref_fwnode)
-			return -EINVAL;
-	}
-
-	/*
 	 * Assume the following integer elements are all args. Stop counting on
-	 * the first reference or end of the package arguments. In case of
-	 * neither reference, nor integer, return an error, we can't parse it.
+	 * the first reference (possibly represented as a string) or end of the
+	 * package arguments. In case of neither reference, nor integer, return
+	 * an error, we can't parse it.
 	 */
 	for (i = 0; (*element) + i < end && i < num_args; i++) {
 		acpi_object_type type = (*element)[i].type;
 
-		if (type == ACPI_TYPE_LOCAL_REFERENCE)
+		if (type == ACPI_TYPE_LOCAL_REFERENCE || type == ACPI_TYPE_STRING)
 			break;
 
 		if (type == ACPI_TYPE_INTEGER)
@@ -845,6 +836,44 @@ static int acpi_get_ref_args(struct fwnode_reference_args *args,
 	return 0;
 }
 
+static struct fwnode_handle *acpi_parse_string_ref(const struct fwnode_handle *fwnode,
+						   const char *refstring)
+{
+	acpi_handle scope, handle;
+	struct acpi_data_node *dn;
+	struct acpi_device *device;
+	acpi_status status;
+
+	if (is_acpi_device_node(fwnode)) {
+		scope = to_acpi_device_node(fwnode)->handle;
+	} else if (is_acpi_data_node(fwnode)) {
+		scope = to_acpi_data_node(fwnode)->handle;
+	} else {
+		pr_debug("Bad node type for node %pfw\n", fwnode);
+		return NULL;
+	}
+
+	status = acpi_get_handle(scope, refstring, &handle);
+	if (ACPI_FAILURE(status)) {
+		acpi_handle_debug(scope, "Unable to get an ACPI handle for %s\n",
+				  refstring);
+		return NULL;
+	}
+
+	device = acpi_fetch_acpi_dev(handle);
+	if (device)
+		return acpi_fwnode_handle(device);
+
+	status = acpi_get_data_full(handle, acpi_nondev_subnode_tag,
+				    (void **)&dn, NULL);
+	if (ACPI_FAILURE(status) || !dn) {
+		acpi_handle_debug(handle, "Subnode not found\n");
+		return NULL;
+	}
+
+	return &dn->fwnode;
+}
+
 /**
  * __acpi_node_get_property_reference - returns handle to the referenced object
  * @fwnode: Firmware node to get the property from
@@ -887,6 +916,7 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 	const union acpi_object *element, *end;
 	const union acpi_object *obj;
 	const struct acpi_device_data *data;
+	struct fwnode_handle *ref_fwnode;
 	struct acpi_device *device;
 	int ret, idx = 0;
 
@@ -910,16 +940,30 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 
 		args->fwnode = acpi_fwnode_handle(device);
 		args->nargs = 0;
+
+		return 0;
+	case ACPI_TYPE_STRING:
+		if (index)
+			return -ENOENT;
+
+		ref_fwnode = acpi_parse_string_ref(fwnode, obj->string.pointer);
+		if (!ref_fwnode)
+			return -EINVAL;
+
+		args->fwnode = ref_fwnode;
+		args->nargs = 0;
+
 		return 0;
 	case ACPI_TYPE_PACKAGE:
 		/*
 		 * If it is not a single reference, then it is a package of
-		 * references followed by number of ints as follows:
+		 * references, followed by number of ints as follows:
 		 *
 		 *  Package () { REF, INT, REF, INT, INT }
 		 *
-		 * The index argument is then used to determine which reference
-		 * the caller wants (along with the arguments).
+		 * Here, REF may be either a local reference or a string. The
+		 * index argument is then used to determine which reference the
+		 * caller wants (along with the arguments).
 		 */
 		break;
 	default:
@@ -951,6 +995,24 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 				return 0;
 
 			break;
+		case ACPI_TYPE_STRING:
+			ref_fwnode = acpi_parse_string_ref(fwnode,
+							   element->string.pointer);
+			if (!ref_fwnode)
+				return -EINVAL;
+
+			element++;
+
+			ret = acpi_get_ref_args(idx == index ? args : NULL,
+						ref_fwnode, &element, end,
+						num_args);
+			if (ret < 0)
+				return ret;
+
+			if (idx == index)
+				return 0;
+
+			break;
 		case ACPI_TYPE_INTEGER:
 			if (idx == index)
 				return -ENOENT;
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 15a3bdbd0755..0e2c397b1399 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -448,6 +448,13 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = {
 		},
 	},
 	{
+		/* Asus ExpertBook B1402CVA */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "B1402CVA"),
+		},
+	},
+	{
 		/* Asus ExpertBook B1502CBA */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
@@ -504,6 +511,13 @@ static const struct dmi_system_id irq1_edge_low_force_override[] = {
 		},
 	},
 	{
+		/* TongFang GMxXGxx sold as Eluktronics Inc. RP-15 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Eluktronics Inc."),
+			DMI_MATCH(DMI_BOARD_NAME, "RP-15"),
+		},
+	},
+	{
 		/* TongFang GM6XGxX/TUXEDO Stellaris 16 Gen5 AMD */
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "GM6XGxX"),
@@ -541,6 +555,18 @@ static const struct dmi_system_id irq1_edge_low_force_override[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "GM6BG0Q"),
 		},
 	},
+	{
+		/* Infinity E15-5A165-BM */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "GM5RG1E0009COM"),
+		},
+	},
+	{
+		/* Infinity E15-5A305-1M */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "GM5RGEE0016COM"),
+		},
+	},
 	{ }
 };
 
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index fa5dd71a80fa..0ba008773b00 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1532,7 +1532,6 @@ int acpi_dma_get_range(struct device *dev, const struct bus_dma_region **map)
 			r->cpu_start = rentry->res->start;
 			r->dma_start = rentry->res->start - rentry->offset;
 			r->size = resource_size(rentry->res);
-			r->offset = rentry->offset;
 			r++;
 		}
 	}
@@ -1568,17 +1567,22 @@ static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev,
 	int err;
 	const struct iommu_ops *ops;
 
+	/* Serialise to make dev->iommu stable under our potential fwspec */
+	mutex_lock(&iommu_probe_device_lock);
 	/*
 	 * If we already translated the fwspec there is nothing left to do,
 	 * return the iommu_ops.
 	 */
 	ops = acpi_iommu_fwspec_ops(dev);
-	if (ops)
+	if (ops) {
+		mutex_unlock(&iommu_probe_device_lock);
 		return ops;
+	}
 
 	err = iort_iommu_configure_id(dev, id_in);
 	if (err && err != -EPROBE_DEFER)
 		err = viot_iommu_configure(dev);
+	mutex_unlock(&iommu_probe_device_lock);
 
 	/*
 	 * If we have reason to believe the IOMMU driver missed the initial
@@ -1727,6 +1731,7 @@ static bool acpi_device_enumeration_by_parent(struct acpi_device *device)
 	 * Some ACPI devs contain SerialBus resources even though they are not
 	 * attached to a serial bus at all.
 	 */
+		{ACPI_VIDEO_HID, },
 		{"MSHW0028", },
 	/*
 	 * HIDs of device with an UartSerialBusV2 resource for which userspace
@@ -1976,10 +1981,9 @@ static void acpi_scan_init_hotplug(struct acpi_device *adev)
 	}
 }
 
-static u32 acpi_scan_check_dep(acpi_handle handle, bool check_dep)
+static u32 acpi_scan_check_dep(acpi_handle handle)
 {
 	struct acpi_handle_list dep_devices;
-	acpi_status status;
 	u32 count;
 	int i;
 
@@ -1989,12 +1993,10 @@ static u32 acpi_scan_check_dep(acpi_handle handle, bool check_dep)
 	 * 2. ACPI nodes describing USB ports.
 	 * Still, checking for _HID catches more then just these cases ...
 	 */
-	if (!check_dep || !acpi_has_method(handle, "_DEP") ||
-	    !acpi_has_method(handle, "_HID"))
+	if (!acpi_has_method(handle, "_DEP") || !acpi_has_method(handle, "_HID"))
 		return 0;
 
-	status = acpi_evaluate_reference(handle, "_DEP", NULL, &dep_devices);
-	if (ACPI_FAILURE(status)) {
+	if (!acpi_evaluate_reference(handle, "_DEP", NULL, &dep_devices)) {
 		acpi_handle_debug(handle, "Failed to evaluate _DEP.\n");
 		return 0;
 	}
@@ -2003,6 +2005,7 @@ static u32 acpi_scan_check_dep(acpi_handle handle, bool check_dep)
 		struct acpi_device_info *info;
 		struct acpi_dep_data *dep;
 		bool skip, honor_dep;
+		acpi_status status;
 
 		status = acpi_get_object_info(dep_devices.handles[i], &info);
 		if (ACPI_FAILURE(status)) {
@@ -2036,7 +2039,13 @@ static u32 acpi_scan_check_dep(acpi_handle handle, bool check_dep)
 	return count;
 }
 
-static acpi_status acpi_bus_check_add(acpi_handle handle, bool check_dep,
+static acpi_status acpi_scan_check_crs_csi2_cb(acpi_handle handle, u32 a, void *b, void **c)
+{
+	acpi_mipi_check_crs_csi2(handle);
+	return AE_OK;
+}
+
+static acpi_status acpi_bus_check_add(acpi_handle handle, bool first_pass,
 				      struct acpi_device **adev_p)
 {
 	struct acpi_device *device = acpi_fetch_acpi_dev(handle);
@@ -2054,9 +2063,25 @@ static acpi_status acpi_bus_check_add(acpi_handle handle, bool check_dep,
 		if (acpi_device_should_be_hidden(handle))
 			return AE_OK;
 
-		/* Bail out if there are dependencies. */
-		if (acpi_scan_check_dep(handle, check_dep) > 0)
-			return AE_CTRL_DEPTH;
+		if (first_pass) {
+			acpi_mipi_check_crs_csi2(handle);
+
+			/* Bail out if there are dependencies. */
+			if (acpi_scan_check_dep(handle) > 0) {
+				/*
+				 * The entire CSI-2 connection graph needs to be
+				 * extracted before any drivers or scan handlers
+				 * are bound to struct device objects, so scan
+				 * _CRS CSI-2 resource descriptors for all
+				 * devices below the current handle.
+				 */
+				acpi_walk_namespace(ACPI_TYPE_DEVICE, handle,
+						    ACPI_UINT32_MAX,
+						    acpi_scan_check_crs_csi2_cb,
+						    NULL, NULL, NULL);
+				return AE_CTRL_DEPTH;
+			}
+		}
 
 		fallthrough;
 	case ACPI_TYPE_ANY:	/* for ACPI_ROOT_OBJECT */
@@ -2079,10 +2104,10 @@ static acpi_status acpi_bus_check_add(acpi_handle handle, bool check_dep,
 	}
 
 	/*
-	 * If check_dep is true at this point, the device has no dependencies,
+	 * If first_pass is true at this point, the device has no dependencies,
 	 * or the creation of the device object would have been postponed above.
 	 */
-	acpi_add_single_object(&device, handle, type, !check_dep);
+	acpi_add_single_object(&device, handle, type, !first_pass);
 	if (!device)
 		return AE_CTRL_DEPTH;
 
@@ -2426,6 +2451,13 @@ static void acpi_scan_postponed_branch(acpi_handle handle)
 
 	acpi_walk_namespace(ACPI_TYPE_ANY, handle, ACPI_UINT32_MAX,
 			    acpi_bus_check_add_2, NULL, NULL, (void **)&adev);
+
+	/*
+	 * Populate the ACPI _CRS CSI-2 software nodes for the ACPI devices that
+	 * have been added above.
+	 */
+	acpi_mipi_init_crs_csi2_swnodes();
+
 	acpi_bus_attach(adev, NULL);
 }
 
@@ -2494,12 +2526,22 @@ int acpi_bus_scan(acpi_handle handle)
 	if (!device)
 		return -ENODEV;
 
+	/*
+	 * Set up ACPI _CRS CSI-2 software nodes using information extracted
+	 * from the _CRS CSI-2 resource descriptors during the ACPI namespace
+	 * walk above and MIPI DisCo for Imaging device properties.
+	 */
+	acpi_mipi_scan_crs_csi2();
+	acpi_mipi_init_crs_csi2_swnodes();
+
 	acpi_bus_attach(device, (void *)true);
 
 	/* Pass 2: Enumerate all of the remaining devices. */
 
 	acpi_scan_postponed();
 
+	acpi_mipi_crs_csi2_cleanup();
+
 	return 0;
 }
 EXPORT_SYMBOL(acpi_bus_scan);
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index f74d81abdbfc..4748e8061253 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -31,6 +31,8 @@
 #include <linux/uaccess.h>
 #include <linux/units.h>
 
+#include "internal.h"
+
 #define ACPI_THERMAL_CLASS		"thermal_zone"
 #define ACPI_THERMAL_DEVICE_NAME	"Thermal Zone"
 #define ACPI_THERMAL_NOTIFY_TEMPERATURE	0x80
@@ -90,7 +92,7 @@ struct acpi_thermal_passive {
 	struct acpi_thermal_trip trip;
 	unsigned long tc1;
 	unsigned long tc2;
-	unsigned long tsp;
+	unsigned long delay;
 };
 
 struct acpi_thermal_active {
@@ -188,24 +190,19 @@ static int active_trip_index(struct acpi_thermal *tz,
 
 static long get_passive_temp(struct acpi_thermal *tz)
 {
-	unsigned long long tmp;
-	acpi_status status;
+	int temp;
 
-	status = acpi_evaluate_integer(tz->device->handle, "_PSV", NULL, &tmp);
-	if (ACPI_FAILURE(status))
+	if (acpi_passive_trip_temp(tz->device, &temp))
 		return THERMAL_TEMP_INVALID;
 
-	return tmp;
+	return temp;
 }
 
 static long get_active_temp(struct acpi_thermal *tz, int index)
 {
-	char method[] = { '_', 'A', 'C', '0' + index, '\0' };
-	unsigned long long tmp;
-	acpi_status status;
+	int temp;
 
-	status = acpi_evaluate_integer(tz->device->handle, method, NULL, &tmp);
-	if (ACPI_FAILURE(status))
+	if (acpi_active_trip_temp(tz->device, index, &temp))
 		return THERMAL_TEMP_INVALID;
 
 	/*
@@ -215,10 +212,10 @@ static long get_active_temp(struct acpi_thermal *tz, int index)
 	if (act > 0) {
 		unsigned long long override = celsius_to_deci_kelvin(act);
 
-		if (tmp > override)
-			tmp = override;
+		if (temp > override)
+			return override;
 	}
-	return tmp;
+	return temp;
 }
 
 static void acpi_thermal_update_trip(struct acpi_thermal *tz,
@@ -247,7 +244,6 @@ static bool update_trip_devices(struct acpi_thermal *tz,
 {
 	struct acpi_handle_list devices = { 0 };
 	char method[] = "_PSL";
-	acpi_status status;
 
 	if (index != ACPI_THERMAL_TRIP_PASSIVE) {
 		method[1] = 'A';
@@ -255,8 +251,7 @@ static bool update_trip_devices(struct acpi_thermal *tz,
 		method[3] = '0' + index;
 	}
 
-	status = acpi_evaluate_reference(tz->device->handle, method, NULL, &devices);
-	if (ACPI_FAILURE(status)) {
+	if (!acpi_evaluate_reference(tz->device->handle, method, NULL, &devices)) {
 		acpi_handle_info(tz->device->handle, "%s evaluation failure\n", method);
 		return false;
 	}
@@ -297,6 +292,7 @@ static int acpi_thermal_adjust_trip(struct thermal_trip *trip, void *data)
 	struct acpi_thermal_trip *acpi_trip = trip->priv;
 	struct adjust_trip_data *atd = data;
 	struct acpi_thermal *tz = atd->tz;
+	int temp;
 
 	if (!acpi_trip || !acpi_thermal_trip_valid(acpi_trip))
 		return 0;
@@ -307,9 +303,11 @@ static int acpi_thermal_adjust_trip(struct thermal_trip *trip, void *data)
 		acpi_thermal_update_trip_devices(tz, trip);
 
 	if (acpi_thermal_trip_valid(acpi_trip))
-		trip->temperature = acpi_thermal_temp(tz, acpi_trip->temp_dk);
+		temp = acpi_thermal_temp(tz, acpi_trip->temp_dk);
 	else
-		trip->temperature = THERMAL_TEMP_INVALID;
+		temp = THERMAL_TEMP_INVALID;
+
+	thermal_zone_set_trip_temp(tz->thermal_zone, trip, temp);
 
 	return 0;
 }
@@ -339,13 +337,12 @@ static void acpi_thermal_trips_update(struct acpi_thermal *tz, u32 event)
 					dev_name(&adev->dev), event, 0);
 }
 
-static long acpi_thermal_get_critical_trip(struct acpi_thermal *tz)
+static int acpi_thermal_get_critical_trip(struct acpi_thermal *tz)
 {
-	unsigned long long tmp;
-	acpi_status status;
+	int temp;
 
 	if (crt > 0) {
-		tmp = celsius_to_deci_kelvin(crt);
+		temp = celsius_to_deci_kelvin(crt);
 		goto set;
 	}
 	if (crt == -1) {
@@ -353,38 +350,34 @@ static long acpi_thermal_get_critical_trip(struct acpi_thermal *tz)
 		return THERMAL_TEMP_INVALID;
 	}
 
-	status = acpi_evaluate_integer(tz->device->handle, "_CRT", NULL, &tmp);
-	if (ACPI_FAILURE(status)) {
-		acpi_handle_debug(tz->device->handle, "No critical threshold\n");
+	if (acpi_critical_trip_temp(tz->device, &temp))
 		return THERMAL_TEMP_INVALID;
-	}
-	if (tmp <= 2732) {
+
+	if (temp <= 2732) {
 		/*
 		 * Below zero (Celsius) values clearly aren't right for sure,
 		 * so discard them as invalid.
 		 */
-		pr_info(FW_BUG "Invalid critical threshold (%llu)\n", tmp);
+		pr_info(FW_BUG "Invalid critical threshold (%d)\n", temp);
 		return THERMAL_TEMP_INVALID;
 	}
 
 set:
-	acpi_handle_debug(tz->device->handle, "Critical threshold [%llu]\n", tmp);
-	return tmp;
+	acpi_handle_debug(tz->device->handle, "Critical threshold [%d]\n", temp);
+	return temp;
 }
 
-static long acpi_thermal_get_hot_trip(struct acpi_thermal *tz)
+static int acpi_thermal_get_hot_trip(struct acpi_thermal *tz)
 {
-	unsigned long long tmp;
-	acpi_status status;
+	int temp;
 
-	status = acpi_evaluate_integer(tz->device->handle, "_HOT", NULL, &tmp);
-	if (ACPI_FAILURE(status)) {
+	if (acpi_hot_trip_temp(tz->device, &temp) || temp == THERMAL_TEMP_INVALID) {
 		acpi_handle_debug(tz->device->handle, "No hot threshold\n");
 		return THERMAL_TEMP_INVALID;
 	}
 
-	acpi_handle_debug(tz->device->handle, "Hot threshold [%llu]\n", tmp);
-	return tmp;
+	acpi_handle_debug(tz->device->handle, "Hot threshold [%d]\n", temp);
+	return temp;
 }
 
 static bool passive_trip_params_init(struct acpi_thermal *tz)
@@ -404,11 +397,17 @@ static bool passive_trip_params_init(struct acpi_thermal *tz)
 
 	tz->trips.passive.tc2 = tmp;
 
+	status = acpi_evaluate_integer(tz->device->handle, "_TFP", NULL, &tmp);
+	if (ACPI_SUCCESS(status)) {
+		tz->trips.passive.delay = tmp;
+		return true;
+	}
+
 	status = acpi_evaluate_integer(tz->device->handle, "_TSP", NULL, &tmp);
 	if (ACPI_FAILURE(status))
 		return false;
 
-	tz->trips.passive.tsp = tmp;
+	tz->trips.passive.delay = tmp * 100;
 
 	return true;
 }
@@ -904,7 +903,7 @@ static int acpi_thermal_add(struct acpi_device *device)
 
 	acpi_trip = &tz->trips.passive.trip;
 	if (acpi_thermal_trip_valid(acpi_trip)) {
-		passive_delay = tz->trips.passive.tsp * 100;
+		passive_delay = tz->trips.passive.delay;
 
 		trip->type = THERMAL_TRIP_PASSIVE;
 		trip->temperature = acpi_thermal_temp(tz, acpi_trip->temp_dk);
@@ -1142,6 +1141,7 @@ static void __exit acpi_thermal_exit(void)
 module_init(acpi_thermal_init);
 module_exit(acpi_thermal_exit);
 
+MODULE_IMPORT_NS(ACPI_THERMAL);
 MODULE_AUTHOR("Paul Diefenbaugh");
 MODULE_DESCRIPTION("ACPI Thermal Zone Driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/thermal/thermal_acpi.c b/drivers/acpi/thermal_lib.c
index 43eaf0f2ff49..4e0519ca9739 100644
--- a/drivers/thermal/thermal_acpi.c
+++ b/drivers/acpi/thermal_lib.c
@@ -3,12 +3,13 @@
  * Copyright 2023 Linaro Limited
  * Copyright 2023 Intel Corporation
  *
- * Library routines for populating a generic thermal trip point structure
- * with data obtained by evaluating a specific object in the ACPI Namespace.
+ * Library routines for retrieving trip point temperature values from the
+ * platform firmware via ACPI.
  */
 #include <linux/acpi.h>
 #include <linux/units.h>
 #include <linux/thermal.h>
+#include "internal.h"
 
 /*
  * Minimum temperature for full military grade is 218°K (-55°C) and
@@ -17,11 +18,11 @@
  * firmware. Any values out of these boundaries may be considered
  * bogus and we can assume the firmware has no data to provide.
  */
-#define TEMP_MIN_DECIK	2180
-#define TEMP_MAX_DECIK	4480
+#define TEMP_MIN_DECIK	2180ULL
+#define TEMP_MAX_DECIK	4480ULL
 
-static int thermal_acpi_trip_temp(struct acpi_device *adev, char *obj_name,
-				  int *ret_temp)
+static int acpi_trip_temp(struct acpi_device *adev, char *obj_name,
+			  int *ret_temp)
 {
 	unsigned long long temp;
 	acpi_status status;
@@ -33,7 +34,7 @@ static int thermal_acpi_trip_temp(struct acpi_device *adev, char *obj_name,
 	}
 
 	if (temp >= TEMP_MIN_DECIK && temp <= TEMP_MAX_DECIK) {
-		*ret_temp = deci_kelvin_to_millicelsius(temp);
+		*ret_temp = temp;
 	} else {
 		acpi_handle_debug(adev->handle, "%s result %llu out of range\n",
 				  obj_name, temp);
@@ -43,6 +44,48 @@ static int thermal_acpi_trip_temp(struct acpi_device *adev, char *obj_name,
 	return 0;
 }
 
+int acpi_active_trip_temp(struct acpi_device *adev, int id, int *ret_temp)
+{
+	char obj_name[] = {'_', 'A', 'C', '0' + id, '\0'};
+
+	if (id < 0 || id > 9)
+		return -EINVAL;
+
+	return acpi_trip_temp(adev, obj_name, ret_temp);
+}
+EXPORT_SYMBOL_NS_GPL(acpi_active_trip_temp, ACPI_THERMAL);
+
+int acpi_passive_trip_temp(struct acpi_device *adev, int *ret_temp)
+{
+	return acpi_trip_temp(adev, "_PSV", ret_temp);
+}
+EXPORT_SYMBOL_NS_GPL(acpi_passive_trip_temp, ACPI_THERMAL);
+
+int acpi_hot_trip_temp(struct acpi_device *adev, int *ret_temp)
+{
+	return acpi_trip_temp(adev, "_HOT", ret_temp);
+}
+EXPORT_SYMBOL_NS_GPL(acpi_hot_trip_temp, ACPI_THERMAL);
+
+int acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp)
+{
+	return acpi_trip_temp(adev, "_CRT", ret_temp);
+}
+EXPORT_SYMBOL_NS_GPL(acpi_critical_trip_temp, ACPI_THERMAL);
+
+static int thermal_temp(int error, int temp_decik, int *ret_temp)
+{
+	if (error)
+		return error;
+
+	if (temp_decik == THERMAL_TEMP_INVALID)
+		*ret_temp = THERMAL_TEMP_INVALID;
+	else
+		*ret_temp = deci_kelvin_to_millicelsius(temp_decik);
+
+	return 0;
+}
+
 /**
  * thermal_acpi_active_trip_temp - Retrieve active trip point temperature
  * @adev: Target thermal zone ACPI device object.
@@ -57,12 +100,10 @@ static int thermal_acpi_trip_temp(struct acpi_device *adev, char *obj_name,
  */
 int thermal_acpi_active_trip_temp(struct acpi_device *adev, int id, int *ret_temp)
 {
-	char obj_name[] = {'_', 'A', 'C', '0' + id, '\0'};
-
-	if (id < 0 || id > 9)
-		return -EINVAL;
+	int temp_decik;
+	int ret = acpi_active_trip_temp(adev, id, &temp_decik);
 
-	return thermal_acpi_trip_temp(adev, obj_name, ret_temp);
+	return thermal_temp(ret, temp_decik, ret_temp);
 }
 EXPORT_SYMBOL_GPL(thermal_acpi_active_trip_temp);
 
@@ -78,7 +119,10 @@ EXPORT_SYMBOL_GPL(thermal_acpi_active_trip_temp);
  */
 int thermal_acpi_passive_trip_temp(struct acpi_device *adev, int *ret_temp)
 {
-	return thermal_acpi_trip_temp(adev, "_PSV", ret_temp);
+	int temp_decik;
+	int ret = acpi_passive_trip_temp(adev, &temp_decik);
+
+	return thermal_temp(ret, temp_decik, ret_temp);
 }
 EXPORT_SYMBOL_GPL(thermal_acpi_passive_trip_temp);
 
@@ -95,7 +139,10 @@ EXPORT_SYMBOL_GPL(thermal_acpi_passive_trip_temp);
  */
 int thermal_acpi_hot_trip_temp(struct acpi_device *adev, int *ret_temp)
 {
-	return thermal_acpi_trip_temp(adev, "_HOT", ret_temp);
+	int temp_decik;
+	int ret = acpi_hot_trip_temp(adev, &temp_decik);
+
+	return thermal_temp(ret, temp_decik, ret_temp);
 }
 EXPORT_SYMBOL_GPL(thermal_acpi_hot_trip_temp);
 
@@ -111,6 +158,9 @@ EXPORT_SYMBOL_GPL(thermal_acpi_hot_trip_temp);
  */
 int thermal_acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp)
 {
-	return thermal_acpi_trip_temp(adev, "_CRT", ret_temp);
+	int temp_decik;
+	int ret = acpi_critical_trip_temp(adev, &temp_decik);
+
+	return thermal_temp(ret, temp_decik, ret_temp);
 }
 EXPORT_SYMBOL_GPL(thermal_acpi_critical_trip_temp);
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 28c75242fca9..abac5cc25477 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -329,21 +329,18 @@ const char *acpi_get_subsystem_id(acpi_handle handle)
 }
 EXPORT_SYMBOL_GPL(acpi_get_subsystem_id);
 
-acpi_status
-acpi_evaluate_reference(acpi_handle handle,
-			acpi_string pathname,
-			struct acpi_object_list *arguments,
-			struct acpi_handle_list *list)
+bool acpi_evaluate_reference(acpi_handle handle, acpi_string pathname,
+			     struct acpi_object_list *arguments,
+			     struct acpi_handle_list *list)
 {
-	acpi_status status = AE_OK;
-	union acpi_object *package = NULL;
-	union acpi_object *element = NULL;
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
-	u32 i = 0;
-
+	union acpi_object *package;
+	acpi_status status;
+	bool ret = false;
+	u32 i;
 
 	if (!list)
-		return AE_BAD_PARAMETER;
+		return false;
 
 	/* Evaluate object. */
 
@@ -353,62 +350,47 @@ acpi_evaluate_reference(acpi_handle handle,
 
 	package = buffer.pointer;
 
-	if ((buffer.length == 0) || !package) {
-		status = AE_BAD_DATA;
-		acpi_util_eval_error(handle, pathname, status);
-		goto end;
-	}
-	if (package->type != ACPI_TYPE_PACKAGE) {
-		status = AE_BAD_DATA;
-		acpi_util_eval_error(handle, pathname, status);
-		goto end;
-	}
-	if (!package->package.count) {
-		status = AE_BAD_DATA;
-		acpi_util_eval_error(handle, pathname, status);
-		goto end;
-	}
+	if (buffer.length == 0 || !package ||
+	    package->type != ACPI_TYPE_PACKAGE || !package->package.count)
+		goto err;
 
-	list->handles = kcalloc(package->package.count, sizeof(*list->handles), GFP_KERNEL);
-	if (!list->handles) {
-		kfree(package);
-		return AE_NO_MEMORY;
-	}
 	list->count = package->package.count;
+	list->handles = kcalloc(list->count, sizeof(*list->handles), GFP_KERNEL);
+	if (!list->handles)
+		goto err_clear;
 
 	/* Extract package data. */
 
 	for (i = 0; i < list->count; i++) {
+		union acpi_object *element = &(package->package.elements[i]);
 
-		element = &(package->package.elements[i]);
-
-		if (element->type != ACPI_TYPE_LOCAL_REFERENCE) {
-			status = AE_BAD_DATA;
-			acpi_util_eval_error(handle, pathname, status);
-			break;
-		}
+		if (element->type != ACPI_TYPE_LOCAL_REFERENCE ||
+		    !element->reference.handle)
+			goto err_free;
 
-		if (!element->reference.handle) {
-			status = AE_NULL_ENTRY;
-			acpi_util_eval_error(handle, pathname, status);
-			break;
-		}
 		/* Get the  acpi_handle. */
 
 		list->handles[i] = element->reference.handle;
 		acpi_handle_debug(list->handles[i], "Found in reference list\n");
 	}
 
-end:
-	if (ACPI_FAILURE(status)) {
-		list->count = 0;
-		kfree(list->handles);
-		list->handles = NULL;
-	}
+	ret = true;
 
+end:
 	kfree(buffer.pointer);
 
-	return status;
+	return ret;
+
+err_free:
+	kfree(list->handles);
+	list->handles = NULL;
+
+err_clear:
+	list->count = 0;
+
+err:
+	acpi_util_eval_error(handle, pathname, status);
+	goto end;
 }
 
 EXPORT_SYMBOL(acpi_evaluate_reference);
@@ -426,7 +408,7 @@ bool acpi_handle_list_equal(struct acpi_handle_list *list1,
 {
 	return list1->count == list2->count &&
 		!memcmp(list1->handles, list2->handles,
-		        list1->count * sizeof(acpi_handle));
+		        list1->count * sizeof(*list1->handles));
 }
 EXPORT_SYMBOL_GPL(acpi_handle_list_equal);
 
@@ -468,6 +450,40 @@ void acpi_handle_list_free(struct acpi_handle_list *list)
 }
 EXPORT_SYMBOL_GPL(acpi_handle_list_free);
 
+/**
+ * acpi_device_dep - Check ACPI device dependency
+ * @target: ACPI handle of the target ACPI device.
+ * @match: ACPI handle to look up in the target's _DEP list.
+ *
+ * Return true if @match is present in the list returned by _DEP for
+ * @target or false otherwise.
+ */
+bool acpi_device_dep(acpi_handle target, acpi_handle match)
+{
+	struct acpi_handle_list dep_devices;
+	bool ret = false;
+	int i;
+
+	if (!acpi_has_method(target, "_DEP"))
+		return false;
+
+	if (!acpi_evaluate_reference(target, "_DEP", NULL, &dep_devices)) {
+		acpi_handle_debug(target, "Failed to evaluate _DEP.\n");
+		return false;
+	}
+
+	for (i = 0; i < dep_devices.count; i++) {
+		if (dep_devices.handles[i] == match) {
+			ret = true;
+			break;
+		}
+	}
+
+	acpi_handle_list_free(&dep_devices);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(acpi_device_dep);
+
 acpi_status
 acpi_get_physical_device_location(acpi_handle handle, struct acpi_pld_info **pld)
 {
@@ -825,54 +841,6 @@ bool acpi_check_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 funcs)
 EXPORT_SYMBOL(acpi_check_dsm);
 
 /**
- * acpi_dev_uid_match - Match device by supplied UID
- * @adev: ACPI device to match.
- * @uid2: Unique ID of the device.
- *
- * Matches UID in @adev with given @uid2.
- *
- * Returns:
- *  - %true if matches.
- *  - %false otherwise.
- */
-bool acpi_dev_uid_match(struct acpi_device *adev, const char *uid2)
-{
-	const char *uid1 = acpi_device_uid(adev);
-
-	return uid1 && uid2 && !strcmp(uid1, uid2);
-}
-EXPORT_SYMBOL_GPL(acpi_dev_uid_match);
-
-/**
- * acpi_dev_hid_uid_match - Match device by supplied HID and UID
- * @adev: ACPI device to match.
- * @hid2: Hardware ID of the device.
- * @uid2: Unique ID of the device, pass NULL to not check _UID.
- *
- * Matches HID and UID in @adev with given @hid2 and @uid2. Absence of @uid2
- * will be treated as a match. If user wants to validate @uid2, it should be
- * done before calling this function.
- *
- * Returns:
- *  - %true if matches or @uid2 is NULL.
- *  - %false otherwise.
- */
-bool acpi_dev_hid_uid_match(struct acpi_device *adev,
-			    const char *hid2, const char *uid2)
-{
-	const char *hid1 = acpi_device_hid(adev);
-
-	if (strcmp(hid1, hid2))
-		return false;
-
-	if (!uid2)
-		return true;
-
-	return acpi_dev_uid_match(adev, uid2);
-}
-EXPORT_SYMBOL(acpi_dev_hid_uid_match);
-
-/**
  * acpi_dev_uid_to_integer - treat ACPI device _UID as integer
  * @adev: ACPI device to get _UID from
  * @integer: output buffer for integer
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 92128aae2d06..7658103ba760 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -1921,7 +1921,7 @@ static void binder_deferred_fd_close(int fd)
 	if (!twcb)
 		return;
 	init_task_work(&twcb->twork, binder_do_fd_close);
-	twcb->file = close_fd_get_file(fd);
+	twcb->file = file_close_fd(fd);
 	if (twcb->file) {
 		// pin it until binder_do_fd_close(); see comments there
 		get_file(twcb->file);
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 138f6d43d13b..f69d30c9f50f 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -234,7 +234,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 		if (page->page_ptr) {
 			trace_binder_alloc_lru_start(alloc, index);
 
-			on_lru = list_lru_del(&binder_alloc_lru, &page->lru);
+			on_lru = list_lru_del_obj(&binder_alloc_lru, &page->lru);
 			WARN_ON(!on_lru);
 
 			trace_binder_alloc_lru_end(alloc, index);
@@ -285,7 +285,7 @@ free_range:
 
 		trace_binder_free_lru_start(alloc, index);
 
-		ret = list_lru_add(&binder_alloc_lru, &page->lru);
+		ret = list_lru_add_obj(&binder_alloc_lru, &page->lru);
 		WARN_ON(!ret);
 
 		trace_binder_free_lru_end(alloc, index);
@@ -848,7 +848,7 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 			if (!alloc->pages[i].page_ptr)
 				continue;
 
-			on_lru = list_lru_del(&binder_alloc_lru,
+			on_lru = list_lru_del_obj(&binder_alloc_lru,
 					      &alloc->pages[i].lru);
 			page_addr = alloc->buffer + i * PAGE_SIZE;
 			binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
@@ -1287,4 +1287,3 @@ int binder_alloc_copy_from_buffer(struct binder_alloc *alloc,
 	return binder_alloc_do_buffer_copy(alloc, false, buffer, buffer_offset,
 					   dest, bytes);
 }
-
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index c10ff8985203..0a0f483124c3 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1055,9 +1055,14 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev)
 		 * Ask the sd driver to issue START STOP UNIT on runtime suspend
 		 * and resume and shutdown only. For system level suspend/resume,
 		 * devices power state is handled directly by libata EH.
+		 * Given that disks are always spun up on system resume, also
+		 * make sure that the sd driver forces runtime suspended disks
+		 * to be resumed to correctly reflect the power state of the
+		 * device.
 		 */
-		sdev->manage_runtime_start_stop = true;
-		sdev->manage_shutdown = true;
+		sdev->manage_runtime_start_stop = 1;
+		sdev->manage_shutdown = 1;
+		sdev->force_runtime_start_on_system_start = 1;
 	}
 
 	/*
diff --git a/drivers/ata/pata_isapnp.c b/drivers/ata/pata_isapnp.c
index 25a63d043c8e..0f77e0424066 100644
--- a/drivers/ata/pata_isapnp.c
+++ b/drivers/ata/pata_isapnp.c
@@ -82,6 +82,9 @@ static int isapnp_init_one(struct pnp_dev *idev, const struct pnp_device_id *dev
 	if (pnp_port_valid(idev, 1)) {
 		ctl_addr = devm_ioport_map(&idev->dev,
 					   pnp_port_start(idev, 1), 1);
+		if (!ctl_addr)
+			return -ENOMEM;
+
 		ap->ioaddr.altstatus_addr = ctl_addr;
 		ap->ioaddr.ctl_addr = ctl_addr;
 		ap->ops = &isapnp_port_ops;
diff --git a/drivers/ata/pata_pxa.c b/drivers/ata/pata_pxa.c
index 5275c6464f57..538bd3423d85 100644
--- a/drivers/ata/pata_pxa.c
+++ b/drivers/ata/pata_pxa.c
@@ -274,10 +274,9 @@ static int pxa_ata_probe(struct platform_device *pdev)
 	/*
 	 * Request the DMA channel
 	 */
-	data->dma_chan =
-		dma_request_slave_channel(&pdev->dev, "data");
-	if (!data->dma_chan)
-		return -EBUSY;
+	data->dma_chan = dma_request_chan(&pdev->dev, "data");
+	if (IS_ERR(data->dma_chan))
+		return PTR_ERR(data->dma_chan);
 	ret = dmaengine_slave_config(data->dma_chan, &config);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "dma configuration failed: %d\n", ret);
diff --git a/drivers/atm/atmtcp.c b/drivers/atm/atmtcp.c
index 96bea1ab1ecc..d4aa0f353b6c 100644
--- a/drivers/atm/atmtcp.c
+++ b/drivers/atm/atmtcp.c
@@ -494,6 +494,7 @@ static void __exit atmtcp_exit(void)
 	deregister_atm_ioctl(&atmtcp_ioctl_ops);
 }
 
+MODULE_DESCRIPTION("ATM over TCP");
 MODULE_LICENSE("GPL");
 module_init(atmtcp_init);
 module_exit(atmtcp_exit);
diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c
index a31ffe16e626..3011cf1a84a9 100644
--- a/drivers/atm/eni.c
+++ b/drivers/atm/eni.c
@@ -2318,4 +2318,5 @@ static int __init eni_init(void)
 module_init(eni_init);
 /* @@@ since exit routine not defined, this module can not be unloaded */
 
+MODULE_DESCRIPTION("Efficient Networks ENI155P ATM NIC driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/atm/idt77105.c b/drivers/atm/idt77105.c
index bfca7b8a6f31..fcd70e094a2e 100644
--- a/drivers/atm/idt77105.c
+++ b/drivers/atm/idt77105.c
@@ -372,4 +372,5 @@ static void __exit idt77105_exit(void)
 
 module_exit(idt77105_exit);
 
+MODULE_DESCRIPTION("IDT77105 PHY driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
index 9bba8f280a4d..d213adcefe33 100644
--- a/drivers/atm/iphase.c
+++ b/drivers/atm/iphase.c
@@ -90,6 +90,7 @@ module_param(IA_RX_BUF, int, 0);
 module_param(IA_RX_BUF_SZ, int, 0);
 module_param(IADebugFlag, uint, 0644);
 
+MODULE_DESCRIPTION("Driver for Interphase ATM PCI NICs");
 MODULE_LICENSE("GPL");
 
 /**************************** IA_LIB **********************************/
diff --git a/drivers/atm/nicstar.c b/drivers/atm/nicstar.c
index 1a50de39f5b5..27153d6bc781 100644
--- a/drivers/atm/nicstar.c
+++ b/drivers/atm/nicstar.c
@@ -171,6 +171,7 @@ static const struct atmdev_ops atm_ops = {
 static struct timer_list ns_timer;
 static char *mac[NS_MAX_CARDS];
 module_param_array(mac, charp, NULL, 0);
+MODULE_DESCRIPTION("ATM NIC driver for IDT 77201/77211 \"NICStAR\" and Fore ForeRunnerLE.");
 MODULE_LICENSE("GPL");
 
 /* Functions */
diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c
index 94fbc3abe60e..d3c30a28c410 100644
--- a/drivers/atm/solos-pci.c
+++ b/drivers/atm/solos-pci.c
@@ -449,9 +449,9 @@ static ssize_t console_show(struct device *dev, struct device_attribute *attr,
 	struct sk_buff *skb;
 	unsigned int len;
 
-	spin_lock(&card->cli_queue_lock);
+	spin_lock_bh(&card->cli_queue_lock);
 	skb = skb_dequeue(&card->cli_queue[SOLOS_CHAN(atmdev)]);
-	spin_unlock(&card->cli_queue_lock);
+	spin_unlock_bh(&card->cli_queue_lock);
 	if(skb == NULL)
 		return sprintf(buf, "No data.\n");
 
@@ -956,14 +956,14 @@ static void pclose(struct atm_vcc *vcc)
 	struct pkt_hdr *header;
 
 	/* Remove any yet-to-be-transmitted packets from the pending queue */
-	spin_lock(&card->tx_queue_lock);
+	spin_lock_bh(&card->tx_queue_lock);
 	skb_queue_walk_safe(&card->tx_queue[port], skb, tmpskb) {
 		if (SKB_CB(skb)->vcc == vcc) {
 			skb_unlink(skb, &card->tx_queue[port]);
 			solos_pop(vcc, skb);
 		}
 	}
-	spin_unlock(&card->tx_queue_lock);
+	spin_unlock_bh(&card->tx_queue_lock);
 
 	skb = alloc_skb(sizeof(*header), GFP_KERNEL);
 	if (!skb) {
diff --git a/drivers/atm/suni.c b/drivers/atm/suni.c
index 21e5acc766b8..32802ea9521c 100644
--- a/drivers/atm/suni.c
+++ b/drivers/atm/suni.c
@@ -387,4 +387,5 @@ int suni_init(struct atm_dev *dev)
 
 EXPORT_SYMBOL(suni_init);
 
+MODULE_DESCRIPTION("S/UNI PHY driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/auxdisplay/img-ascii-lcd.c b/drivers/auxdisplay/img-ascii-lcd.c
index fa23e415f260..56efda0740fb 100644
--- a/drivers/auxdisplay/img-ascii-lcd.c
+++ b/drivers/auxdisplay/img-ascii-lcd.c
@@ -8,9 +8,9 @@
 #include <linux/io.h>
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
-#include <linux/of_address.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
 
@@ -225,17 +225,11 @@ MODULE_DEVICE_TABLE(of, img_ascii_lcd_matches);
  */
 static int img_ascii_lcd_probe(struct platform_device *pdev)
 {
-	const struct of_device_id *match;
-	const struct img_ascii_lcd_config *cfg;
 	struct device *dev = &pdev->dev;
+	const struct img_ascii_lcd_config *cfg = device_get_match_data(dev);
 	struct img_ascii_lcd_ctx *ctx;
 	int err;
 
-	match = of_match_device(img_ascii_lcd_matches, dev);
-	if (!match)
-		return -ENODEV;
-
-	cfg = match->data;
 	ctx = devm_kzalloc(dev, sizeof(*ctx) + cfg->num_chars, GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c
index eaa31e567d1e..5b59d133b6af 100644
--- a/drivers/base/arch_numa.c
+++ b/drivers/base/arch_numa.c
@@ -144,7 +144,7 @@ void __init early_map_cpu_to_node(unsigned int cpu, int nid)
 unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(__per_cpu_offset);
 
-static int __init early_cpu_to_node(int cpu)
+int __init early_cpu_to_node(int cpu)
 {
 	return cpu_to_node_map[cpu];
 }
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index b741b5ba82bd..5aaa0865625d 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
+#include <linux/units.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/thermal_pressure.h>
@@ -26,7 +27,8 @@
 static DEFINE_PER_CPU(struct scale_freq_data __rcu *, sft_data);
 static struct cpumask scale_freq_counters_mask;
 static bool scale_freq_invariant;
-static DEFINE_PER_CPU(u32, freq_factor) = 1;
+DEFINE_PER_CPU(unsigned long, capacity_freq_ref) = 1;
+EXPORT_PER_CPU_SYMBOL_GPL(capacity_freq_ref);
 
 static bool supports_scale_freq_counters(const struct cpumask *cpus)
 {
@@ -170,9 +172,9 @@ DEFINE_PER_CPU(unsigned long, thermal_pressure);
  * operating on stale data when hot-plug is used for some CPUs. The
  * @capped_freq reflects the currently allowed max CPUs frequency due to
  * thermal capping. It might be also a boost frequency value, which is bigger
- * than the internal 'freq_factor' max frequency. In such case the pressure
- * value should simply be removed, since this is an indication that there is
- * no thermal throttling. The @capped_freq must be provided in kHz.
+ * than the internal 'capacity_freq_ref' max frequency. In such case the
+ * pressure value should simply be removed, since this is an indication that
+ * there is no thermal throttling. The @capped_freq must be provided in kHz.
  */
 void topology_update_thermal_pressure(const struct cpumask *cpus,
 				      unsigned long capped_freq)
@@ -183,10 +185,7 @@ void topology_update_thermal_pressure(const struct cpumask *cpus,
 
 	cpu = cpumask_first(cpus);
 	max_capacity = arch_scale_cpu_capacity(cpu);
-	max_freq = per_cpu(freq_factor, cpu);
-
-	/* Convert to MHz scale which is used in 'freq_factor' */
-	capped_freq /= 1000;
+	max_freq = arch_scale_freq_ref(cpu);
 
 	/*
 	 * Handle properly the boost frequencies, which should simply clean
@@ -279,13 +278,13 @@ void topology_normalize_cpu_scale(void)
 
 	capacity_scale = 1;
 	for_each_possible_cpu(cpu) {
-		capacity = raw_capacity[cpu] * per_cpu(freq_factor, cpu);
+		capacity = raw_capacity[cpu] * per_cpu(capacity_freq_ref, cpu);
 		capacity_scale = max(capacity, capacity_scale);
 	}
 
 	pr_debug("cpu_capacity: capacity_scale=%llu\n", capacity_scale);
 	for_each_possible_cpu(cpu) {
-		capacity = raw_capacity[cpu] * per_cpu(freq_factor, cpu);
+		capacity = raw_capacity[cpu] * per_cpu(capacity_freq_ref, cpu);
 		capacity = div64_u64(capacity << SCHED_CAPACITY_SHIFT,
 			capacity_scale);
 		topology_set_cpu_scale(cpu, capacity);
@@ -321,15 +320,15 @@ bool __init topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu)
 			cpu_node, raw_capacity[cpu]);
 
 		/*
-		 * Update freq_factor for calculating early boot cpu capacities.
+		 * Update capacity_freq_ref for calculating early boot CPU capacities.
 		 * For non-clk CPU DVFS mechanism, there's no way to get the
 		 * frequency value now, assuming they are running at the same
-		 * frequency (by keeping the initial freq_factor value).
+		 * frequency (by keeping the initial capacity_freq_ref value).
 		 */
 		cpu_clk = of_clk_get(cpu_node, 0);
 		if (!PTR_ERR_OR_ZERO(cpu_clk)) {
-			per_cpu(freq_factor, cpu) =
-				clk_get_rate(cpu_clk) / 1000;
+			per_cpu(capacity_freq_ref, cpu) =
+				clk_get_rate(cpu_clk) / HZ_PER_KHZ;
 			clk_put(cpu_clk);
 		}
 	} else {
@@ -345,11 +344,16 @@ bool __init topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu)
 	return !ret;
 }
 
+void __weak freq_inv_set_max_ratio(int cpu, u64 max_rate)
+{
+}
+
 #ifdef CONFIG_ACPI_CPPC_LIB
 #include <acpi/cppc_acpi.h>
 
 void topology_init_cpu_capacity_cppc(void)
 {
+	u64 capacity, capacity_scale = 0;
 	struct cppc_perf_caps perf_caps;
 	int cpu;
 
@@ -366,6 +370,10 @@ void topology_init_cpu_capacity_cppc(void)
 		    (perf_caps.highest_perf >= perf_caps.nominal_perf) &&
 		    (perf_caps.highest_perf >= perf_caps.lowest_perf)) {
 			raw_capacity[cpu] = perf_caps.highest_perf;
+			capacity_scale = max_t(u64, capacity_scale, raw_capacity[cpu]);
+
+			per_cpu(capacity_freq_ref, cpu) = cppc_perf_to_khz(&perf_caps, raw_capacity[cpu]);
+
 			pr_debug("cpu_capacity: CPU%d cpu_capacity=%u (raw).\n",
 				 cpu, raw_capacity[cpu]);
 			continue;
@@ -376,7 +384,18 @@ void topology_init_cpu_capacity_cppc(void)
 		goto exit;
 	}
 
-	topology_normalize_cpu_scale();
+	for_each_possible_cpu(cpu) {
+		freq_inv_set_max_ratio(cpu,
+				       per_cpu(capacity_freq_ref, cpu) * HZ_PER_KHZ);
+
+		capacity = raw_capacity[cpu];
+		capacity = div64_u64(capacity << SCHED_CAPACITY_SHIFT,
+				     capacity_scale);
+		topology_set_cpu_scale(cpu, capacity);
+		pr_debug("cpu_capacity: CPU%d cpu_capacity=%lu\n",
+			cpu, topology_get_cpu_scale(cpu));
+	}
+
 	schedule_work(&update_topology_flags_work);
 	pr_debug("cpu_capacity: cpu_capacity initialization done\n");
 
@@ -410,8 +429,11 @@ init_cpu_capacity_callback(struct notifier_block *nb,
 
 	cpumask_andnot(cpus_to_visit, cpus_to_visit, policy->related_cpus);
 
-	for_each_cpu(cpu, policy->related_cpus)
-		per_cpu(freq_factor, cpu) = policy->cpuinfo.max_freq / 1000;
+	for_each_cpu(cpu, policy->related_cpus) {
+		per_cpu(capacity_freq_ref, cpu) = policy->cpuinfo.max_freq;
+		freq_inv_set_max_ratio(cpu,
+				       per_cpu(capacity_freq_ref, cpu) * HZ_PER_KHZ);
+	}
 
 	if (cpumask_empty(cpus_to_visit)) {
 		topology_normalize_cpu_scale();
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 9ea22e165acd..548491de818e 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -144,7 +144,7 @@ static DEVICE_ATTR(release, S_IWUSR, NULL, cpu_release_store);
 #endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
 #endif /* CONFIG_HOTPLUG_CPU */
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 #include <linux/kexec.h>
 
 static ssize_t crash_notes_show(struct device *dev,
@@ -189,14 +189,14 @@ static const struct attribute_group crash_note_cpu_attr_group = {
 #endif
 
 static const struct attribute_group *common_cpu_attr_groups[] = {
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	&crash_note_cpu_attr_group,
 #endif
 	NULL
 };
 
 static const struct attribute_group *hotplugable_cpu_attr_groups[] = {
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	&crash_note_cpu_attr_group,
 #endif
 	NULL
diff --git a/drivers/base/devcoredump.c b/drivers/base/devcoredump.c
index 91536ee05f14..7e2d1f0d903a 100644
--- a/drivers/base/devcoredump.c
+++ b/drivers/base/devcoredump.c
@@ -362,6 +362,7 @@ void dev_coredumpm(struct device *dev, struct module *owner,
 	devcd->devcd_dev.class = &devcd_class;
 
 	mutex_lock(&devcd->mutex);
+	dev_set_uevent_suppress(&devcd->devcd_dev, true);
 	if (device_add(&devcd->devcd_dev))
 		goto put_device;
 
@@ -376,6 +377,8 @@ void dev_coredumpm(struct device *dev, struct module *owner,
 		              "devcoredump"))
 		dev_warn(dev, "devcoredump create_link failed\n");
 
+	dev_set_uevent_suppress(&devcd->devcd_dev, false);
+	kobject_uevent(&devcd->devcd_dev.kobj, KOBJ_ADD);
 	INIT_DELAYED_WORK(&devcd->del_wk, devcd_del);
 	schedule_delayed_work(&devcd->del_wk, DEVCD_TIMEOUT);
 	mutex_unlock(&devcd->mutex);
diff --git a/drivers/base/firmware_loader/sysfs_upload.c b/drivers/base/firmware_loader/sysfs_upload.c
index a0af8f5f13d8..829270067d16 100644
--- a/drivers/base/firmware_loader/sysfs_upload.c
+++ b/drivers/base/firmware_loader/sysfs_upload.c
@@ -27,6 +27,7 @@ static const char * const fw_upload_err_str[] = {
 	[FW_UPLOAD_ERR_INVALID_SIZE] = "invalid-file-size",
 	[FW_UPLOAD_ERR_RW_ERROR]     = "read-write-error",
 	[FW_UPLOAD_ERR_WEAROUT]	     = "flash-wearout",
+	[FW_UPLOAD_ERR_FW_INVALID]   = "firmware-invalid",
 };
 
 static const char *fw_upload_progress(struct device *dev,
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index f3b9a4d0fa3b..8a13babd826c 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -180,6 +180,9 @@ static inline unsigned long memblk_nr_poison(struct memory_block *mem)
 }
 #endif
 
+/*
+ * Must acquire mem_hotplug_lock in write mode.
+ */
 static int memory_block_online(struct memory_block *mem)
 {
 	unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
@@ -204,10 +207,11 @@ static int memory_block_online(struct memory_block *mem)
 	if (mem->altmap)
 		nr_vmemmap_pages = mem->altmap->free;
 
+	mem_hotplug_begin();
 	if (nr_vmemmap_pages) {
 		ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	ret = online_pages(start_pfn + nr_vmemmap_pages,
@@ -215,7 +219,7 @@ static int memory_block_online(struct memory_block *mem)
 	if (ret) {
 		if (nr_vmemmap_pages)
 			mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages);
-		return ret;
+		goto out;
 	}
 
 	/*
@@ -227,9 +231,14 @@ static int memory_block_online(struct memory_block *mem)
 					  nr_vmemmap_pages);
 
 	mem->zone = zone;
+out:
+	mem_hotplug_done();
 	return ret;
 }
 
+/*
+ * Must acquire mem_hotplug_lock in write mode.
+ */
 static int memory_block_offline(struct memory_block *mem)
 {
 	unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
@@ -247,6 +256,7 @@ static int memory_block_offline(struct memory_block *mem)
 	if (mem->altmap)
 		nr_vmemmap_pages = mem->altmap->free;
 
+	mem_hotplug_begin();
 	if (nr_vmemmap_pages)
 		adjust_present_page_count(pfn_to_page(start_pfn), mem->group,
 					  -nr_vmemmap_pages);
@@ -258,13 +268,15 @@ static int memory_block_offline(struct memory_block *mem)
 		if (nr_vmemmap_pages)
 			adjust_present_page_count(pfn_to_page(start_pfn),
 						  mem->group, nr_vmemmap_pages);
-		return ret;
+		goto out;
 	}
 
 	if (nr_vmemmap_pages)
 		mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages);
 
 	mem->zone = NULL;
+out:
+	mem_hotplug_done();
 	return ret;
 }
 
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index f85f3515c258..9c5a5f4dba5a 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -579,7 +579,7 @@ bool dev_pm_skip_resume(struct device *dev)
 }
 
 /**
- * device_resume_noirq - Execute a "noirq resume" callback for given device.
+ * __device_resume_noirq - Execute a "noirq resume" callback for given device.
  * @dev: Device to handle.
  * @state: PM transition of the system being carried out.
  * @async: If true, the device is being resumed asynchronously.
@@ -587,7 +587,7 @@ bool dev_pm_skip_resume(struct device *dev)
  * The driver of @dev will not receive interrupts while this function is being
  * executed.
  */
-static int device_resume_noirq(struct device *dev, pm_message_t state, bool async)
+static void __device_resume_noirq(struct device *dev, pm_message_t state, bool async)
 {
 	pm_callback_t callback = NULL;
 	const char *info = NULL;
@@ -655,7 +655,13 @@ Skip:
 Out:
 	complete_all(&dev->power.completion);
 	TRACE_RESUME(error);
-	return error;
+
+	if (error) {
+		suspend_stats.failed_resume_noirq++;
+		dpm_save_failed_step(SUSPEND_RESUME_NOIRQ);
+		dpm_save_failed_dev(dev_name(dev));
+		pm_dev_err(dev, state, async ? " async noirq" : " noirq", error);
+	}
 }
 
 static bool is_async(struct device *dev)
@@ -668,11 +674,15 @@ static bool dpm_async_fn(struct device *dev, async_func_t func)
 {
 	reinit_completion(&dev->power.completion);
 
-	if (is_async(dev)) {
-		get_device(dev);
-		async_schedule_dev(func, dev);
+	if (!is_async(dev))
+		return false;
+
+	get_device(dev);
+
+	if (async_schedule_dev_nocall(func, dev))
 		return true;
-	}
+
+	put_device(dev);
 
 	return false;
 }
@@ -680,15 +690,19 @@ static bool dpm_async_fn(struct device *dev, async_func_t func)
 static void async_resume_noirq(void *data, async_cookie_t cookie)
 {
 	struct device *dev = data;
-	int error;
-
-	error = device_resume_noirq(dev, pm_transition, true);
-	if (error)
-		pm_dev_err(dev, pm_transition, " async", error);
 
+	__device_resume_noirq(dev, pm_transition, true);
 	put_device(dev);
 }
 
+static void device_resume_noirq(struct device *dev)
+{
+	if (dpm_async_fn(dev, async_resume_noirq))
+		return;
+
+	__device_resume_noirq(dev, pm_transition, false);
+}
+
 static void dpm_noirq_resume_devices(pm_message_t state)
 {
 	struct device *dev;
@@ -698,14 +712,6 @@ static void dpm_noirq_resume_devices(pm_message_t state)
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
 
-	/*
-	 * Advanced the async threads upfront,
-	 * in case the starting of async threads is
-	 * delayed by non-async resuming devices.
-	 */
-	list_for_each_entry(dev, &dpm_noirq_list, power.entry)
-		dpm_async_fn(dev, async_resume_noirq);
-
 	while (!list_empty(&dpm_noirq_list)) {
 		dev = to_device(dpm_noirq_list.next);
 		get_device(dev);
@@ -713,17 +719,7 @@ static void dpm_noirq_resume_devices(pm_message_t state)
 
 		mutex_unlock(&dpm_list_mtx);
 
-		if (!is_async(dev)) {
-			int error;
-
-			error = device_resume_noirq(dev, state, false);
-			if (error) {
-				suspend_stats.failed_resume_noirq++;
-				dpm_save_failed_step(SUSPEND_RESUME_NOIRQ);
-				dpm_save_failed_dev(dev_name(dev));
-				pm_dev_err(dev, state, " noirq", error);
-			}
-		}
+		device_resume_noirq(dev);
 
 		put_device(dev);
 
@@ -751,14 +747,14 @@ void dpm_resume_noirq(pm_message_t state)
 }
 
 /**
- * device_resume_early - Execute an "early resume" callback for given device.
+ * __device_resume_early - Execute an "early resume" callback for given device.
  * @dev: Device to handle.
  * @state: PM transition of the system being carried out.
  * @async: If true, the device is being resumed asynchronously.
  *
  * Runtime PM is disabled for @dev while this function is being executed.
  */
-static int device_resume_early(struct device *dev, pm_message_t state, bool async)
+static void __device_resume_early(struct device *dev, pm_message_t state, bool async)
 {
 	pm_callback_t callback = NULL;
 	const char *info = NULL;
@@ -811,21 +807,31 @@ Out:
 
 	pm_runtime_enable(dev);
 	complete_all(&dev->power.completion);
-	return error;
+
+	if (error) {
+		suspend_stats.failed_resume_early++;
+		dpm_save_failed_step(SUSPEND_RESUME_EARLY);
+		dpm_save_failed_dev(dev_name(dev));
+		pm_dev_err(dev, state, async ? " async early" : " early", error);
+	}
 }
 
 static void async_resume_early(void *data, async_cookie_t cookie)
 {
 	struct device *dev = data;
-	int error;
-
-	error = device_resume_early(dev, pm_transition, true);
-	if (error)
-		pm_dev_err(dev, pm_transition, " async", error);
 
+	__device_resume_early(dev, pm_transition, true);
 	put_device(dev);
 }
 
+static void device_resume_early(struct device *dev)
+{
+	if (dpm_async_fn(dev, async_resume_early))
+		return;
+
+	__device_resume_early(dev, pm_transition, false);
+}
+
 /**
  * dpm_resume_early - Execute "early resume" callbacks for all devices.
  * @state: PM transition of the system being carried out.
@@ -839,14 +845,6 @@ void dpm_resume_early(pm_message_t state)
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
 
-	/*
-	 * Advanced the async threads upfront,
-	 * in case the starting of async threads is
-	 * delayed by non-async resuming devices.
-	 */
-	list_for_each_entry(dev, &dpm_late_early_list, power.entry)
-		dpm_async_fn(dev, async_resume_early);
-
 	while (!list_empty(&dpm_late_early_list)) {
 		dev = to_device(dpm_late_early_list.next);
 		get_device(dev);
@@ -854,17 +852,7 @@ void dpm_resume_early(pm_message_t state)
 
 		mutex_unlock(&dpm_list_mtx);
 
-		if (!is_async(dev)) {
-			int error;
-
-			error = device_resume_early(dev, state, false);
-			if (error) {
-				suspend_stats.failed_resume_early++;
-				dpm_save_failed_step(SUSPEND_RESUME_EARLY);
-				dpm_save_failed_dev(dev_name(dev));
-				pm_dev_err(dev, state, " early", error);
-			}
-		}
+		device_resume_early(dev);
 
 		put_device(dev);
 
@@ -888,12 +876,12 @@ void dpm_resume_start(pm_message_t state)
 EXPORT_SYMBOL_GPL(dpm_resume_start);
 
 /**
- * device_resume - Execute "resume" callbacks for given device.
+ * __device_resume - Execute "resume" callbacks for given device.
  * @dev: Device to handle.
  * @state: PM transition of the system being carried out.
  * @async: If true, the device is being resumed asynchronously.
  */
-static int device_resume(struct device *dev, pm_message_t state, bool async)
+static void __device_resume(struct device *dev, pm_message_t state, bool async)
 {
 	pm_callback_t callback = NULL;
 	const char *info = NULL;
@@ -975,20 +963,30 @@ static int device_resume(struct device *dev, pm_message_t state, bool async)
 
 	TRACE_RESUME(error);
 
-	return error;
+	if (error) {
+		suspend_stats.failed_resume++;
+		dpm_save_failed_step(SUSPEND_RESUME);
+		dpm_save_failed_dev(dev_name(dev));
+		pm_dev_err(dev, state, async ? " async" : "", error);
+	}
 }
 
 static void async_resume(void *data, async_cookie_t cookie)
 {
 	struct device *dev = data;
-	int error;
 
-	error = device_resume(dev, pm_transition, true);
-	if (error)
-		pm_dev_err(dev, pm_transition, " async", error);
+	__device_resume(dev, pm_transition, true);
 	put_device(dev);
 }
 
+static void device_resume(struct device *dev)
+{
+	if (dpm_async_fn(dev, async_resume))
+		return;
+
+	__device_resume(dev, pm_transition, false);
+}
+
 /**
  * dpm_resume - Execute "resume" callbacks for non-sysdev devices.
  * @state: PM transition of the system being carried out.
@@ -1008,27 +1006,17 @@ void dpm_resume(pm_message_t state)
 	pm_transition = state;
 	async_error = 0;
 
-	list_for_each_entry(dev, &dpm_suspended_list, power.entry)
-		dpm_async_fn(dev, async_resume);
-
 	while (!list_empty(&dpm_suspended_list)) {
 		dev = to_device(dpm_suspended_list.next);
+
 		get_device(dev);
-		if (!is_async(dev)) {
-			int error;
 
-			mutex_unlock(&dpm_list_mtx);
+		mutex_unlock(&dpm_list_mtx);
+
+		device_resume(dev);
 
-			error = device_resume(dev, state, false);
-			if (error) {
-				suspend_stats.failed_resume++;
-				dpm_save_failed_step(SUSPEND_RESUME);
-				dpm_save_failed_dev(dev_name(dev));
-				pm_dev_err(dev, state, "", error);
-			}
+		mutex_lock(&dpm_list_mtx);
 
-			mutex_lock(&dpm_list_mtx);
-		}
 		if (!list_empty(&dev->power.entry))
 			list_move_tail(&dev->power.entry, &dpm_prepared_list);
 
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 4545669cb973..05793c9fbb84 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -11,6 +11,7 @@
 #include <linux/export.h>
 #include <linux/pm_runtime.h>
 #include <linux/pm_wakeirq.h>
+#include <linux/rculist.h>
 #include <trace/events/rpm.h>
 
 #include "../base.h"
diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index 9a9ea514c2d8..583dd5d7d46b 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -318,6 +318,7 @@ struct regmap_ram_data {
 	bool *read;
 	bool *written;
 	enum regmap_endian reg_endian;
+	bool (*noinc_reg)(struct regmap_ram_data *data, unsigned int reg);
 };
 
 /*
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index 92592f944a3d..ac63a73ccdaa 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -410,8 +410,7 @@ out:
 			rb_entry(node, struct regmap_range_node, node);
 
 		/* If there's nothing in the cache there's nothing to sync */
-		ret = regcache_read(map, this->selector_reg, &i);
-		if (ret != 0)
+		if (regcache_read(map, this->selector_reg, &i) != 0)
 			continue;
 
 		ret = _regmap_write(map, this->selector_reg, i);
diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index bdd80b73c3e6..fb84cda92a75 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -226,8 +226,8 @@ static ssize_t regmap_read_debugfs(struct regmap *map, unsigned int from,
 	if (*ppos < 0 || !count)
 		return -EINVAL;
 
-	if (count > (PAGE_SIZE << MAX_ORDER))
-		count = PAGE_SIZE << MAX_ORDER;
+	if (count > (PAGE_SIZE << MAX_PAGE_ORDER))
+		count = PAGE_SIZE << MAX_PAGE_ORDER;
 
 	buf = kmalloc(count, GFP_KERNEL);
 	if (!buf)
@@ -373,8 +373,8 @@ static ssize_t regmap_reg_ranges_read_file(struct file *file,
 	if (*ppos < 0 || !count)
 		return -EINVAL;
 
-	if (count > (PAGE_SIZE << MAX_ORDER))
-		count = PAGE_SIZE << MAX_ORDER;
+	if (count > (PAGE_SIZE << MAX_PAGE_ORDER))
+		count = PAGE_SIZE << MAX_PAGE_ORDER;
 
 	buf = kmalloc(count, GFP_KERNEL);
 	if (!buf)
diff --git a/drivers/base/regmap/regmap-kunit.c b/drivers/base/regmap/regmap-kunit.c
index e14cc03a17f6..026bdcb45127 100644
--- a/drivers/base/regmap/regmap-kunit.c
+++ b/drivers/base/regmap/regmap-kunit.c
@@ -1186,6 +1186,65 @@ static void raw_write(struct kunit *test)
 	regmap_exit(map);
 }
 
+static bool reg_zero(struct device *dev, unsigned int reg)
+{
+	return reg == 0;
+}
+
+static bool ram_reg_zero(struct regmap_ram_data *data, unsigned int reg)
+{
+	return reg == 0;
+}
+
+static void raw_noinc_write(struct kunit *test)
+{
+	struct raw_test_types *t = (struct raw_test_types *)test->param_value;
+	struct regmap *map;
+	struct regmap_config config;
+	struct regmap_ram_data *data;
+	unsigned int val, val_test, val_last;
+	u16 val_array[BLOCK_TEST_SIZE];
+
+	config = raw_regmap_config;
+	config.volatile_reg = reg_zero;
+	config.writeable_noinc_reg = reg_zero;
+	config.readable_noinc_reg = reg_zero;
+
+	map = gen_raw_regmap(&config, t, &data);
+	KUNIT_ASSERT_FALSE(test, IS_ERR(map));
+	if (IS_ERR(map))
+		return;
+
+	data->noinc_reg = ram_reg_zero;
+
+	get_random_bytes(&val_array, sizeof(val_array));
+
+	if (config.val_format_endian == REGMAP_ENDIAN_BIG) {
+		val_test = be16_to_cpu(val_array[1]) + 100;
+		val_last = be16_to_cpu(val_array[BLOCK_TEST_SIZE - 1]);
+	} else {
+		val_test = le16_to_cpu(val_array[1]) + 100;
+		val_last = le16_to_cpu(val_array[BLOCK_TEST_SIZE - 1]);
+	}
+
+	/* Put some data into the register following the noinc register */
+	KUNIT_EXPECT_EQ(test, 0, regmap_write(map, 1, val_test));
+
+	/* Write some data to the noinc register */
+	KUNIT_EXPECT_EQ(test, 0, regmap_noinc_write(map, 0, val_array,
+						    sizeof(val_array)));
+
+	/* We should read back the last value written */
+	KUNIT_EXPECT_EQ(test, 0, regmap_read(map, 0, &val));
+	KUNIT_ASSERT_EQ(test, val_last, val);
+
+	/* Make sure we didn't touch the register after the noinc register */
+	KUNIT_EXPECT_EQ(test, 0, regmap_read(map, 1, &val));
+	KUNIT_ASSERT_EQ(test, val_test, val);
+
+	regmap_exit(map);
+}
+
 static void raw_sync(struct kunit *test)
 {
 	struct raw_test_types *t = (struct raw_test_types *)test->param_value;
@@ -1284,6 +1343,7 @@ static struct kunit_case regmap_test_cases[] = {
 	KUNIT_CASE_PARAM(raw_read_defaults, raw_test_types_gen_params),
 	KUNIT_CASE_PARAM(raw_write_read_single, raw_test_types_gen_params),
 	KUNIT_CASE_PARAM(raw_write, raw_test_types_gen_params),
+	KUNIT_CASE_PARAM(raw_noinc_write, raw_test_types_gen_params),
 	KUNIT_CASE_PARAM(raw_sync, raw_test_cache_types_gen_params),
 	{}
 };
diff --git a/drivers/base/regmap/regmap-ram.c b/drivers/base/regmap/regmap-ram.c
index 85f34a5dee04..192d6b131dff 100644
--- a/drivers/base/regmap/regmap-ram.c
+++ b/drivers/base/regmap/regmap-ram.c
@@ -65,12 +65,12 @@ struct regmap *__regmap_init_ram(const struct regmap_config *config,
 		return ERR_PTR(-EINVAL);
 	}
 
-	data->read = kcalloc(sizeof(bool), config->max_register + 1,
+	data->read = kcalloc(config->max_register + 1, sizeof(bool),
 			     GFP_KERNEL);
 	if (!data->read)
 		return ERR_PTR(-ENOMEM);
 
-	data->written = kcalloc(sizeof(bool), config->max_register + 1,
+	data->written = kcalloc(config->max_register + 1, sizeof(bool),
 				GFP_KERNEL);
 	if (!data->written)
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/base/regmap/regmap-raw-ram.c b/drivers/base/regmap/regmap-raw-ram.c
index c9b800885f3b..93ae07b503fd 100644
--- a/drivers/base/regmap/regmap-raw-ram.c
+++ b/drivers/base/regmap/regmap-raw-ram.c
@@ -41,10 +41,15 @@ static int regmap_raw_ram_gather_write(void *context,
 		return -EINVAL;
 
 	r = decode_reg(data->reg_endian, reg);
-	memcpy(&our_buf[r], val, val_len);
-
-	for (i = 0; i < val_len / 2; i++)
-		data->written[r + i] = true;
+	if (data->noinc_reg && data->noinc_reg(data, r)) {
+		memcpy(&our_buf[r], val + val_len - 2, 2);
+		data->written[r] = true;
+	} else {
+		memcpy(&our_buf[r], val, val_len);
+
+		for (i = 0; i < val_len / 2; i++)
+			data->written[r + i] = true;
+	}
 	
 	return 0;
 }
@@ -70,10 +75,16 @@ static int regmap_raw_ram_read(void *context,
 		return -EINVAL;
 
 	r = decode_reg(data->reg_endian, reg);
-	memcpy(val, &our_buf[r], val_len);
-
-	for (i = 0; i < val_len / 2; i++)
-		data->read[r + i] = true;
+	if (data->noinc_reg && data->noinc_reg(data, r)) {
+		for (i = 0; i < val_len; i += 2)
+			memcpy(val + i, &our_buf[r], 2);
+		data->read[r] = true;
+	} else {
+		memcpy(val, &our_buf[r], val_len);
+
+		for (i = 0; i < val_len / 2; i++)
+			data->read[r + i] = true;
+	}
 
 	return 0;
 }
@@ -111,12 +122,12 @@ struct regmap *__regmap_init_raw_ram(const struct regmap_config *config,
 		return ERR_PTR(-EINVAL);
 	}
 
-	data->read = kcalloc(sizeof(bool), config->max_register + 1,
+	data->read = kcalloc(config->max_register + 1, sizeof(bool),
 			     GFP_KERNEL);
 	if (!data->read)
 		return ERR_PTR(-ENOMEM);
 
-	data->written = kcalloc(sizeof(bool), config->max_register + 1,
+	data->written = kcalloc(config->max_register + 1, sizeof(bool),
 				GFP_KERNEL);
 	if (!data->written)
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index ea6157747199..6db77d8e45f9 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -2136,7 +2136,7 @@ static int regmap_noinc_readwrite(struct regmap *map, unsigned int reg,
 }
 
 /**
- * regmap_noinc_write(): Write data from a register without incrementing the
+ * regmap_noinc_write(): Write data to a register without incrementing the
  *			register number
  *
  * @map: Register map to write to
diff --git a/drivers/bcma/driver_pci_host.c b/drivers/bcma/driver_pci_host.c
index aa0581cda718..ed3be52ab63d 100644
--- a/drivers/bcma/driver_pci_host.c
+++ b/drivers/bcma/driver_pci_host.c
@@ -280,7 +280,7 @@ static u8 bcma_find_pci_capability(struct bcma_drv_pci *pc, unsigned int dev,
 	/* check for Header type 0 */
 	bcma_extpci_read_config(pc, dev, func, PCI_HEADER_TYPE, &byte_val,
 				sizeof(u8));
-	if ((byte_val & 0x7F) != PCI_HEADER_TYPE_NORMAL)
+	if ((byte_val & PCI_HEADER_TYPE_MASK) != PCI_HEADER_TYPE_NORMAL)
 		return cap_ptr;
 
 	/* check if the capability pointer field exists */
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index cf6883756155..d2dbf8aaccb5 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -383,7 +383,8 @@ aoeblk_gdalloc(void *vp)
 	WARN_ON(d->flags & DEVFL_TKILL);
 	WARN_ON(d->gd);
 	WARN_ON(d->flags & DEVFL_UP);
-	blk_queue_max_hw_sectors(gd->queue, BLK_DEF_MAX_SECTORS);
+	/* random number picked from the history block max_sectors cap */
+	blk_queue_max_hw_sectors(gd->queue, 2560u);
 	blk_queue_io_opt(gd->queue, SZ_2M);
 	d->bufpool = mp;
 	d->blkq = gd->queue;
diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 64b3a1c76f03..742b2908ff68 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -838,8 +838,8 @@ static bool plausible_request_size(int size)
 }
 
 /* clear the bit corresponding to the piece of storage in question:
- * size byte of data starting from sector.  Only clear a bits of the affected
- * one ore more _aligned_ BM_BLOCK_SIZE blocks.
+ * size byte of data starting from sector.  Only clear bits of the affected
+ * one or more _aligned_ BM_BLOCK_SIZE blocks.
  *
  * called by worker on C_SYNC_TARGET and receiver on SyncSource.
  *
@@ -957,7 +957,9 @@ static int _is_in_al(struct drbd_device *device, unsigned int enr)
  * @device:	DRBD device.
  * @sector:	The sector number.
  *
- * This functions sleeps on al_wait. Returns 0 on success, -EINTR if interrupted.
+ * This functions sleeps on al_wait.
+ *
+ * Returns: %0 on success, -EINTR if interrupted.
  */
 int drbd_rs_begin_io(struct drbd_device *device, sector_t sector)
 {
@@ -1004,11 +1006,13 @@ retry:
 
 /**
  * drbd_try_rs_begin_io() - Gets an extent in the resync LRU cache, does not sleep
- * @device:	DRBD device.
+ * @peer_device: DRBD device.
  * @sector:	The sector number.
  *
  * Gets an extent in the resync LRU cache, sets it to BME_NO_WRITES, then
- * tries to set it to BME_LOCKED. Returns 0 upon success, and -EAGAIN
+ * tries to set it to BME_LOCKED.
+ *
+ * Returns: %0 upon success, and -EAGAIN
  * if there is still application IO going on in this area.
  */
 int drbd_try_rs_begin_io(struct drbd_peer_device *peer_device, sector_t sector)
@@ -1190,7 +1194,7 @@ void drbd_rs_cancel_all(struct drbd_device *device)
  * drbd_rs_del_all() - Gracefully remove all extents from the resync LRU
  * @device:	DRBD device.
  *
- * Returns 0 upon success, -EAGAIN if at least one reference count was
+ * Returns: %0 upon success, -EAGAIN if at least one reference count was
  * not zero.
  */
 int drbd_rs_del_all(struct drbd_device *device)
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 11114a5d9e5c..d0e41d52d6a9 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -3079,7 +3079,7 @@ static void raw_cmd_free(struct floppy_raw_cmd **ptr)
 	}
 }
 
-#define MAX_LEN (1UL << MAX_ORDER << PAGE_SHIFT)
+#define MAX_LEN (1UL << MAX_PAGE_ORDER << PAGE_SHIFT)
 
 static int raw_cmd_copyin(int cmd, void __user *param,
 				 struct floppy_raw_cmd **rcmd)
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 9f2d412fc560..146b32fa7b47 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -245,9 +245,7 @@ static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos)
 
 	iov_iter_bvec(&i, ITER_SOURCE, bvec, 1, bvec->bv_len);
 
-	file_start_write(file);
 	bw = vfs_iter_write(file, &i, ppos, 0);
-	file_end_write(file);
 
 	if (likely(bw ==  bvec->bv_len))
 		return 0;
@@ -1303,8 +1301,6 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 		loop_set_size(lo, new_size);
 	}
 
-	loop_config_discard(lo);
-
 	/* update dio if lo_offset or transfer is changed */
 	__loop_update_dio(lo, lo->use_dio);
 
@@ -2038,7 +2034,8 @@ static int loop_add(int i)
 	}
 	lo->lo_queue = lo->lo_disk->queue;
 
-	blk_queue_max_hw_sectors(lo->lo_queue, BLK_DEF_MAX_SECTORS);
+	/* random number picked from the history block max_sectors cap */
+	blk_queue_max_hw_sectors(lo->lo_queue, 2560u);
 
 	/*
 	 * By default, we do buffer IO, so it doesn't make sense to enable
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 855fdf5c3b4e..4e72ec4e25ac 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -67,6 +67,7 @@ struct nbd_sock {
 struct recv_thread_args {
 	struct work_struct work;
 	struct nbd_device *nbd;
+	struct nbd_sock *nsock;
 	int index;
 };
 
@@ -333,10 +334,8 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
 	if (!nbd->pid)
 		return 0;
 
-	if (nbd->config->flags & NBD_FLAG_SEND_TRIM) {
-		nbd->disk->queue->limits.discard_granularity = blksize;
+	if (nbd->config->flags & NBD_FLAG_SEND_TRIM)
 		blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX);
-	}
 	blk_queue_logical_block_size(nbd->disk->queue, blksize);
 	blk_queue_physical_block_size(nbd->disk->queue, blksize);
 
@@ -395,6 +394,22 @@ static u32 req_to_nbd_cmd_type(struct request *req)
 	}
 }
 
+static struct nbd_config *nbd_get_config_unlocked(struct nbd_device *nbd)
+{
+	if (refcount_inc_not_zero(&nbd->config_refs)) {
+		/*
+		 * Add smp_mb__after_atomic to ensure that reading nbd->config_refs
+		 * and reading nbd->config is ordered. The pair is the barrier in
+		 * nbd_alloc_and_init_config(), avoid nbd->config_refs is set
+		 * before nbd->config.
+		 */
+		smp_mb__after_atomic();
+		return nbd->config;
+	}
+
+	return NULL;
+}
+
 static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req)
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
@@ -409,13 +424,13 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req)
 		return BLK_EH_DONE;
 	}
 
-	if (!refcount_inc_not_zero(&nbd->config_refs)) {
+	config = nbd_get_config_unlocked(nbd);
+	if (!config) {
 		cmd->status = BLK_STS_TIMEOUT;
 		__clear_bit(NBD_CMD_INFLIGHT, &cmd->flags);
 		mutex_unlock(&cmd->lock);
 		goto done;
 	}
-	config = nbd->config;
 
 	if (config->num_connections > 1 ||
 	    (config->num_connections == 1 && nbd->tag_set.timeout)) {
@@ -489,15 +504,9 @@ done:
 	return BLK_EH_DONE;
 }
 
-/*
- *  Send or receive packet. Return a positive value on success and
- *  negtive value on failue, and never return 0.
- */
-static int sock_xmit(struct nbd_device *nbd, int index, int send,
-		     struct iov_iter *iter, int msg_flags, int *sent)
+static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send,
+		       struct iov_iter *iter, int msg_flags, int *sent)
 {
-	struct nbd_config *config = nbd->config;
-	struct socket *sock = config->socks[index]->sock;
 	int result;
 	struct msghdr msg;
 	unsigned int noreclaim_flag;
@@ -541,6 +550,19 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send,
 }
 
 /*
+ *  Send or receive packet. Return a positive value on success and
+ *  negtive value on failure, and never return 0.
+ */
+static int sock_xmit(struct nbd_device *nbd, int index, int send,
+		     struct iov_iter *iter, int msg_flags, int *sent)
+{
+	struct nbd_config *config = nbd->config;
+	struct socket *sock = config->socks[index]->sock;
+
+	return __sock_xmit(nbd, sock, send, iter, msg_flags, sent);
+}
+
+/*
  * Different settings for sk->sk_sndtimeo can result in different return values
  * if there is a signal pending when we enter sendmsg, because reasons?
  */
@@ -696,7 +718,7 @@ out:
 	return 0;
 }
 
-static int nbd_read_reply(struct nbd_device *nbd, int index,
+static int nbd_read_reply(struct nbd_device *nbd, struct socket *sock,
 			  struct nbd_reply *reply)
 {
 	struct kvec iov = {.iov_base = reply, .iov_len = sizeof(*reply)};
@@ -705,7 +727,7 @@ static int nbd_read_reply(struct nbd_device *nbd, int index,
 
 	reply->magic = 0;
 	iov_iter_kvec(&to, ITER_DEST, &iov, 1, sizeof(*reply));
-	result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL);
+	result = __sock_xmit(nbd, sock, 0, &to, MSG_WAITALL, NULL);
 	if (result < 0) {
 		if (!nbd_disconnected(nbd->config))
 			dev_err(disk_to_dev(nbd->disk),
@@ -829,14 +851,14 @@ static void recv_work(struct work_struct *work)
 	struct nbd_device *nbd = args->nbd;
 	struct nbd_config *config = nbd->config;
 	struct request_queue *q = nbd->disk->queue;
-	struct nbd_sock *nsock;
+	struct nbd_sock *nsock = args->nsock;
 	struct nbd_cmd *cmd;
 	struct request *rq;
 
 	while (1) {
 		struct nbd_reply reply;
 
-		if (nbd_read_reply(nbd, args->index, &reply))
+		if (nbd_read_reply(nbd, nsock->sock, &reply))
 			break;
 
 		/*
@@ -871,7 +893,6 @@ static void recv_work(struct work_struct *work)
 		percpu_ref_put(&q->q_usage_counter);
 	}
 
-	nsock = config->socks[args->index];
 	mutex_lock(&nsock->tx_lock);
 	nbd_mark_nsock_dead(nbd, nsock, 1);
 	mutex_unlock(&nsock->tx_lock);
@@ -977,12 +998,12 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
 	struct nbd_sock *nsock;
 	int ret;
 
-	if (!refcount_inc_not_zero(&nbd->config_refs)) {
+	config = nbd_get_config_unlocked(nbd);
+	if (!config) {
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
 				    "Socks array is empty\n");
 		return -EINVAL;
 	}
-	config = nbd->config;
 
 	if (index >= config->num_connections) {
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
@@ -1215,6 +1236,7 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
 		INIT_WORK(&args->work, recv_work);
 		args->index = i;
 		args->nbd = nbd;
+		args->nsock = nsock;
 		nsock->cookie++;
 		mutex_unlock(&nsock->tx_lock);
 		sockfd_put(old);
@@ -1333,7 +1355,6 @@ static void nbd_config_put(struct nbd_device *nbd)
 		nbd->config = NULL;
 
 		nbd->tag_set.timeout = 0;
-		nbd->disk->queue->limits.discard_granularity = 0;
 		blk_queue_max_discard_sectors(nbd->disk->queue, 0);
 
 		mutex_unlock(&nbd->config_lock);
@@ -1397,6 +1418,7 @@ static int nbd_start_device(struct nbd_device *nbd)
 		refcount_inc(&nbd->config_refs);
 		INIT_WORK(&args->work, recv_work);
 		args->nbd = nbd;
+		args->nsock = config->socks[i];
 		args->index = i;
 		queue_work(nbd->recv_workq, &args->work);
 	}
@@ -1530,17 +1552,20 @@ static int nbd_ioctl(struct block_device *bdev, blk_mode_t mode,
 	return error;
 }
 
-static struct nbd_config *nbd_alloc_config(void)
+static int nbd_alloc_and_init_config(struct nbd_device *nbd)
 {
 	struct nbd_config *config;
 
+	if (WARN_ON(nbd->config))
+		return -EINVAL;
+
 	if (!try_module_get(THIS_MODULE))
-		return ERR_PTR(-ENODEV);
+		return -ENODEV;
 
 	config = kzalloc(sizeof(struct nbd_config), GFP_NOFS);
 	if (!config) {
 		module_put(THIS_MODULE);
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 	}
 
 	atomic_set(&config->recv_threads, 0);
@@ -1548,12 +1573,24 @@ static struct nbd_config *nbd_alloc_config(void)
 	init_waitqueue_head(&config->conn_wait);
 	config->blksize_bits = NBD_DEF_BLKSIZE_BITS;
 	atomic_set(&config->live_connections, 0);
-	return config;
+
+	nbd->config = config;
+	/*
+	 * Order refcount_set(&nbd->config_refs, 1) and nbd->config assignment,
+	 * its pair is the barrier in nbd_get_config_unlocked().
+	 * So nbd_get_config_unlocked() won't see nbd->config as null after
+	 * refcount_inc_not_zero() succeed.
+	 */
+	smp_mb__before_atomic();
+	refcount_set(&nbd->config_refs, 1);
+
+	return 0;
 }
 
 static int nbd_open(struct gendisk *disk, blk_mode_t mode)
 {
 	struct nbd_device *nbd;
+	struct nbd_config *config;
 	int ret = 0;
 
 	mutex_lock(&nbd_index_mutex);
@@ -1566,27 +1603,25 @@ static int nbd_open(struct gendisk *disk, blk_mode_t mode)
 		ret = -ENXIO;
 		goto out;
 	}
-	if (!refcount_inc_not_zero(&nbd->config_refs)) {
-		struct nbd_config *config;
 
+	config = nbd_get_config_unlocked(nbd);
+	if (!config) {
 		mutex_lock(&nbd->config_lock);
 		if (refcount_inc_not_zero(&nbd->config_refs)) {
 			mutex_unlock(&nbd->config_lock);
 			goto out;
 		}
-		config = nbd_alloc_config();
-		if (IS_ERR(config)) {
-			ret = PTR_ERR(config);
+		ret = nbd_alloc_and_init_config(nbd);
+		if (ret) {
 			mutex_unlock(&nbd->config_lock);
 			goto out;
 		}
-		nbd->config = config;
-		refcount_set(&nbd->config_refs, 1);
+
 		refcount_inc(&nbd->refs);
 		mutex_unlock(&nbd->config_lock);
 		if (max_part)
 			set_bit(GD_NEED_PART_SCAN, &disk->state);
-	} else if (nbd_disconnected(nbd->config)) {
+	} else if (nbd_disconnected(config)) {
 		if (max_part)
 			set_bit(GD_NEED_PART_SCAN, &disk->state);
 	}
@@ -1812,7 +1847,6 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
 	 * Tell the block layer that we are not a rotational device
 	 */
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
-	disk->queue->limits.discard_granularity = 0;
 	blk_queue_max_discard_sectors(disk->queue, 0);
 	blk_queue_max_segment_size(disk->queue, UINT_MAX);
 	blk_queue_max_segments(disk->queue, USHRT_MAX);
@@ -1990,22 +2024,17 @@ again:
 		pr_err("nbd%d already in use\n", index);
 		return -EBUSY;
 	}
-	if (WARN_ON(nbd->config)) {
-		mutex_unlock(&nbd->config_lock);
-		nbd_put(nbd);
-		return -EINVAL;
-	}
-	config = nbd_alloc_config();
-	if (IS_ERR(config)) {
+
+	ret = nbd_alloc_and_init_config(nbd);
+	if (ret) {
 		mutex_unlock(&nbd->config_lock);
 		nbd_put(nbd);
 		pr_err("couldn't allocate config\n");
-		return PTR_ERR(config);
+		return ret;
 	}
-	nbd->config = config;
-	refcount_set(&nbd->config_refs, 1);
-	set_bit(NBD_RT_BOUND, &config->runtime_flags);
 
+	config = nbd->config;
+	set_bit(NBD_RT_BOUND, &config->runtime_flags);
 	ret = nbd_genl_size_set(info, nbd);
 	if (ret)
 		goto out;
@@ -2208,7 +2237,8 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
 	}
 	mutex_unlock(&nbd_index_mutex);
 
-	if (!refcount_inc_not_zero(&nbd->config_refs)) {
+	config = nbd_get_config_unlocked(nbd);
+	if (!config) {
 		dev_err(nbd_to_dev(nbd),
 			"not configured, cannot reconfigure\n");
 		nbd_put(nbd);
@@ -2216,7 +2246,6 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	mutex_lock(&nbd->config_lock);
-	config = nbd->config;
 	if (!test_bit(NBD_RT_BOUND, &config->runtime_flags) ||
 	    !nbd->pid) {
 		dev_err(nbd_to_dev(nbd),
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 22a3cf7f32e2..9f7695f00c2d 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -1464,19 +1464,13 @@ blk_status_t null_process_cmd(struct nullb_cmd *cmd, enum req_op op,
 	return BLK_STS_OK;
 }
 
-static blk_status_t null_handle_cmd(struct nullb_cmd *cmd, sector_t sector,
-				    sector_t nr_sectors, enum req_op op)
+static void null_handle_cmd(struct nullb_cmd *cmd, sector_t sector,
+			    sector_t nr_sectors, enum req_op op)
 {
 	struct nullb_device *dev = cmd->nq->dev;
 	struct nullb *nullb = dev->nullb;
 	blk_status_t sts;
 
-	if (test_bit(NULLB_DEV_FL_THROTTLED, &dev->flags)) {
-		sts = null_handle_throttled(cmd);
-		if (sts != BLK_STS_OK)
-			return sts;
-	}
-
 	if (op == REQ_OP_FLUSH) {
 		cmd->error = errno_to_blk_status(null_handle_flush(nullb));
 		goto out;
@@ -1493,7 +1487,6 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd, sector_t sector,
 
 out:
 	nullb_complete_cmd(cmd);
-	return BLK_STS_OK;
 }
 
 static enum hrtimer_restart nullb_bwtimer_fn(struct hrtimer *timer)
@@ -1724,8 +1717,6 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
 	cmd->fake_timeout = should_timeout_request(rq) ||
 		blk_should_fake_timeout(rq->q);
 
-	blk_mq_start_request(rq);
-
 	if (should_requeue_request(rq)) {
 		/*
 		 * Alternate between hitting the core BUSY path, and the
@@ -1738,6 +1729,15 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
 		return BLK_STS_OK;
 	}
 
+	if (test_bit(NULLB_DEV_FL_THROTTLED, &nq->dev->flags)) {
+		blk_status_t sts = null_handle_throttled(cmd);
+
+		if (sts != BLK_STS_OK)
+			return sts;
+	}
+
+	blk_mq_start_request(rq);
+
 	if (is_poll) {
 		spin_lock(&nq->poll_lock);
 		list_add_tail(&rq->queuelist, &nq->poll_list);
@@ -1747,7 +1747,8 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (cmd->fake_timeout)
 		return BLK_STS_OK;
 
-	return null_handle_cmd(cmd, sector, nr_sectors, req_op(rq));
+	null_handle_cmd(cmd, sector, nr_sectors, req_op(rq));
+	return BLK_STS_OK;
 }
 
 static void null_queue_rqs(struct request **rqlist)
@@ -1879,7 +1880,6 @@ static void null_config_discard(struct nullb *nullb)
 		return;
 	}
 
-	nullb->q->limits.discard_granularity = nullb->dev->blocksize;
 	blk_queue_max_discard_sectors(nullb->q, UINT_MAX >> 9);
 }
 
@@ -2185,10 +2185,8 @@ static int null_add_dev(struct nullb_device *dev)
 
 	blk_queue_logical_block_size(nullb->q, dev->blocksize);
 	blk_queue_physical_block_size(nullb->q, dev->blocksize);
-	if (!dev->max_sectors)
-		dev->max_sectors = queue_max_hw_sectors(nullb->q);
-	dev->max_sectors = min(dev->max_sectors, BLK_DEF_MAX_SECTORS);
-	blk_queue_max_hw_sectors(nullb->q, dev->max_sectors);
+	if (dev->max_sectors)
+		blk_queue_max_hw_sectors(nullb->q, dev->max_sectors);
 
 	if (dev->virt_boundary)
 		blk_queue_virt_boundary(nullb->q, PAGE_SIZE - 1);
@@ -2288,12 +2286,6 @@ static int __init null_init(void)
 		g_bs = PAGE_SIZE;
 	}
 
-	if (g_max_sectors > BLK_DEF_MAX_SECTORS) {
-		pr_warn("invalid max sectors\n");
-		pr_warn("defaults max sectors to %u\n", BLK_DEF_MAX_SECTORS);
-		g_max_sectors = BLK_DEF_MAX_SECTORS;
-	}
-
 	if (g_home_node != NUMA_NO_NODE && g_home_node >= nr_online_nodes) {
 		pr_err("invalid home_node value\n");
 		g_home_node = NUMA_NO_NODE;
diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c
index 55c5b48bc276..6f5e0994862e 100644
--- a/drivers/block/null_blk/zoned.c
+++ b/drivers/block/null_blk/zoned.c
@@ -159,7 +159,7 @@ int null_register_zoned_dev(struct nullb *nullb)
 	struct nullb_device *dev = nullb->dev;
 	struct request_queue *q = nullb->q;
 
-	disk_set_zoned(nullb->disk, BLK_ZONED_HM);
+	disk_set_zoned(nullb->disk);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 	blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE);
 	blk_queue_chunk_sectors(q, dev->zone_size_sects);
diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c
index b0550b68645d..4044c369d22a 100644
--- a/drivers/block/rnbd/rnbd-clt.c
+++ b/drivers/block/rnbd/rnbd-clt.c
@@ -1006,10 +1006,10 @@ static int rnbd_client_xfer_request(struct rnbd_clt_dev *dev,
 	msg.prio	= cpu_to_le16(req_get_ioprio(rq));
 
 	/*
-	 * We only support discards with single segment for now.
+	 * We only support discards/WRITE_ZEROES with single segment for now.
 	 * See queue limits.
 	 */
-	if (req_op(rq) != REQ_OP_DISCARD)
+	if ((req_op(rq) != REQ_OP_DISCARD) && (req_op(rq) != REQ_OP_WRITE_ZEROES))
 		sg_cnt = blk_rq_map_sg(dev->queue, rq, iu->sgt.sgl);
 
 	if (sg_cnt == 0)
@@ -1362,6 +1362,8 @@ static void setup_request_queue(struct rnbd_clt_dev *dev,
 	blk_queue_write_cache(dev->queue,
 			      !!(rsp->cache_policy & RNBD_WRITEBACK),
 			      !!(rsp->cache_policy & RNBD_FUA));
+	blk_queue_max_write_zeroes_sectors(dev->queue,
+					   le32_to_cpu(rsp->max_write_zeroes_sectors));
 }
 
 static int rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev,
@@ -1567,8 +1569,8 @@ struct rnbd_clt_dev *rnbd_clt_map_device(const char *sessname,
 
 	dev = init_dev(sess, access_mode, pathname, nr_poll_queues);
 	if (IS_ERR(dev)) {
-		pr_err("map_device: failed to map device '%s' from session %s, can't initialize device, err: %ld\n",
-		       pathname, sess->sessname, PTR_ERR(dev));
+		pr_err("map_device: failed to map device '%s' from session %s, can't initialize device, err: %pe\n",
+		       pathname, sess->sessname, dev);
 		ret = PTR_ERR(dev);
 		goto put_sess;
 	}
@@ -1626,10 +1628,11 @@ struct rnbd_clt_dev *rnbd_clt_map_device(const char *sessname,
 	}
 
 	rnbd_clt_info(dev,
-		       "map_device: Device mapped as %s (nsectors: %llu, logical_block_size: %d, physical_block_size: %d, max_discard_sectors: %d, discard_granularity: %d, discard_alignment: %d, secure_discard: %d, max_segments: %d, max_hw_sectors: %d, wc: %d, fua: %d)\n",
+		       "map_device: Device mapped as %s (nsectors: %llu, logical_block_size: %d, physical_block_size: %d, max_write_zeroes_sectors: %d, max_discard_sectors: %d, discard_granularity: %d, discard_alignment: %d, secure_discard: %d, max_segments: %d, max_hw_sectors: %d, wc: %d, fua: %d)\n",
 		       dev->gd->disk_name, le64_to_cpu(rsp->nsectors),
 		       le16_to_cpu(rsp->logical_block_size),
 		       le16_to_cpu(rsp->physical_block_size),
+		       le32_to_cpu(rsp->max_write_zeroes_sectors),
 		       le32_to_cpu(rsp->max_discard_sectors),
 		       le32_to_cpu(rsp->discard_granularity),
 		       le32_to_cpu(rsp->discard_alignment),
diff --git a/drivers/block/rnbd/rnbd-proto.h b/drivers/block/rnbd/rnbd-proto.h
index e32f8f2c868a..f35be51d213c 100644
--- a/drivers/block/rnbd/rnbd-proto.h
+++ b/drivers/block/rnbd/rnbd-proto.h
@@ -128,7 +128,7 @@ enum rnbd_cache_policy {
  * @device_id:		device_id on server side to identify the device
  * @nsectors:		number of sectors in the usual 512b unit
  * @max_hw_sectors:	max hardware sectors in the usual 512b unit
- * @max_write_same_sectors: max sectors for WRITE SAME in the 512b unit
+ * @max_write_zeroes_sectors: max sectors for WRITE ZEROES in the 512b unit
  * @max_discard_sectors: max. sectors that can be discarded at once in 512b
  * unit.
  * @discard_granularity: size of the internal discard allocation unit in bytes
@@ -145,7 +145,7 @@ struct rnbd_msg_open_rsp {
 	__le32			device_id;
 	__le64			nsectors;
 	__le32			max_hw_sectors;
-	__le32			max_write_same_sectors;
+	__le32			max_write_zeroes_sectors;
 	__le32			max_discard_sectors;
 	__le32			discard_granularity;
 	__le32			discard_alignment;
@@ -186,7 +186,7 @@ struct rnbd_msg_io {
  * @RNBD_OP_FLUSH:	     flush the volatile write cache
  * @RNBD_OP_DISCARD:        discard sectors
  * @RNBD_OP_SECURE_ERASE:   securely erase sectors
- * @RNBD_OP_WRITE_SAME:     write the same sectors many times
+ * @RNBD_OP_WRITE_ZEROES:   write zeroes sectors
 
  * @RNBD_F_SYNC:	     request is sync (sync write or read)
  * @RNBD_F_FUA:             forced unit access
@@ -199,7 +199,7 @@ enum rnbd_io_flags {
 	RNBD_OP_FLUSH		= 2,
 	RNBD_OP_DISCARD	= 3,
 	RNBD_OP_SECURE_ERASE	= 4,
-	RNBD_OP_WRITE_SAME	= 5,
+	RNBD_OP_WRITE_ZEROES	= 5,
 
 	/* Flags */
 	RNBD_F_SYNC  = 1<<(RNBD_OP_BITS + 0),
@@ -236,6 +236,9 @@ static inline blk_opf_t rnbd_to_bio_flags(u32 rnbd_opf)
 	case RNBD_OP_SECURE_ERASE:
 		bio_opf = REQ_OP_SECURE_ERASE;
 		break;
+	case RNBD_OP_WRITE_ZEROES:
+		bio_opf = REQ_OP_WRITE_ZEROES;
+		break;
 	default:
 		WARN(1, "Unknown RNBD type: %d (flags %d)\n",
 		     rnbd_op(rnbd_opf), rnbd_opf);
@@ -268,6 +271,9 @@ static inline u32 rq_to_rnbd_flags(struct request *rq)
 	case REQ_OP_SECURE_ERASE:
 		rnbd_opf = RNBD_OP_SECURE_ERASE;
 		break;
+	case REQ_OP_WRITE_ZEROES:
+		rnbd_opf = RNBD_OP_WRITE_ZEROES;
+		break;
 	case REQ_OP_FLUSH:
 		rnbd_opf = RNBD_OP_FLUSH;
 		break;
diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c
index 65de51f3dfd9..3a0d5dcec6f2 100644
--- a/drivers/block/rnbd/rnbd-srv.c
+++ b/drivers/block/rnbd/rnbd-srv.c
@@ -136,8 +136,8 @@ static int process_rdma(struct rnbd_srv_session *srv_sess,
 
 	sess_dev = rnbd_get_sess_dev(dev_id, srv_sess);
 	if (IS_ERR(sess_dev)) {
-		pr_err_ratelimited("Got I/O request on session %s for unknown device id %d\n",
-				   srv_sess->sessname, dev_id);
+		pr_err_ratelimited("Got I/O request on session %s for unknown device id %d: %pe\n",
+				   srv_sess->sessname, dev_id, sess_dev);
 		err = -ENOTCONN;
 		goto err;
 	}
@@ -544,7 +544,8 @@ static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp,
 	rsp->max_segments = cpu_to_le16(bdev_max_segments(bdev));
 	rsp->max_hw_sectors =
 		cpu_to_le32(queue_max_hw_sectors(bdev_get_queue(bdev)));
-	rsp->max_write_same_sectors = 0;
+	rsp->max_write_zeroes_sectors =
+		cpu_to_le32(bdev_write_zeroes_sectors(bdev));
 	rsp->max_discard_sectors = cpu_to_le32(bdev_max_discard_sectors(bdev));
 	rsp->discard_granularity = cpu_to_le32(bdev_discard_granularity(bdev));
 	rsp->discard_alignment = cpu_to_le32(bdev_discard_alignment(bdev));
@@ -585,6 +586,7 @@ static char *rnbd_srv_get_full_path(struct rnbd_srv_session *srv_sess,
 {
 	char *full_path;
 	char *a, *b;
+	int len;
 
 	full_path = kmalloc(PATH_MAX, GFP_KERNEL);
 	if (!full_path)
@@ -596,19 +598,19 @@ static char *rnbd_srv_get_full_path(struct rnbd_srv_session *srv_sess,
 	 */
 	a = strnstr(dev_search_path, "%SESSNAME%", sizeof(dev_search_path));
 	if (a) {
-		int len = a - dev_search_path;
+		len = a - dev_search_path;
 
 		len = snprintf(full_path, PATH_MAX, "%.*s/%s/%s", len,
 			       dev_search_path, srv_sess->sessname, dev_name);
-		if (len >= PATH_MAX) {
-			pr_err("Too long path: %s, %s, %s\n",
-			       dev_search_path, srv_sess->sessname, dev_name);
-			kfree(full_path);
-			return ERR_PTR(-EINVAL);
-		}
 	} else {
-		snprintf(full_path, PATH_MAX, "%s/%s",
-			 dev_search_path, dev_name);
+		len = snprintf(full_path, PATH_MAX, "%s/%s",
+			       dev_search_path, dev_name);
+	}
+	if (len >= PATH_MAX) {
+		pr_err("Too long path: %s, %s, %s\n",
+		       dev_search_path, srv_sess->sessname, dev_name);
+		kfree(full_path);
+		return ERR_PTR(-EINVAL);
 	}
 
 	/* eliminitate duplicated slashes */
@@ -709,24 +711,24 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess,
 	full_path = rnbd_srv_get_full_path(srv_sess, open_msg->dev_name);
 	if (IS_ERR(full_path)) {
 		ret = PTR_ERR(full_path);
-		pr_err("Opening device '%s' for client %s failed, failed to get device full path, err: %d\n",
-		       open_msg->dev_name, srv_sess->sessname, ret);
+		pr_err("Opening device '%s' for client %s failed, failed to get device full path, err: %pe\n",
+		       open_msg->dev_name, srv_sess->sessname, full_path);
 		goto reject;
 	}
 
 	bdev_handle = bdev_open_by_path(full_path, open_flags, NULL, NULL);
 	if (IS_ERR(bdev_handle)) {
 		ret = PTR_ERR(bdev_handle);
-		pr_err("Opening device '%s' on session %s failed, failed to open the block device, err: %d\n",
-		       full_path, srv_sess->sessname, ret);
+		pr_err("Opening device '%s' on session %s failed, failed to open the block device, err: %pe\n",
+		       full_path, srv_sess->sessname, bdev_handle);
 		goto free_path;
 	}
 
 	srv_dev = rnbd_srv_get_or_create_srv_dev(bdev_handle->bdev, srv_sess,
 						  open_msg->access_mode);
 	if (IS_ERR(srv_dev)) {
-		pr_err("Opening device '%s' on session %s failed, creating srv_dev failed, err: %ld\n",
-		       full_path, srv_sess->sessname, PTR_ERR(srv_dev));
+		pr_err("Opening device '%s' on session %s failed, creating srv_dev failed, err: %pe\n",
+		       full_path, srv_sess->sessname, srv_dev);
 		ret = PTR_ERR(srv_dev);
 		goto blkdev_put;
 	}
@@ -736,8 +738,8 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess,
 				open_msg->access_mode == RNBD_ACCESS_RO,
 				srv_dev);
 	if (IS_ERR(srv_sess_dev)) {
-		pr_err("Opening device '%s' on session %s failed, creating sess_dev failed, err: %ld\n",
-		       full_path, srv_sess->sessname, PTR_ERR(srv_sess_dev));
+		pr_err("Opening device '%s' on session %s failed, creating sess_dev failed, err: %pe\n",
+		       full_path, srv_sess->sessname, srv_sess_dev);
 		ret = PTR_ERR(srv_sess_dev);
 		goto srv_dev_put;
 	}
@@ -818,7 +820,7 @@ static int __init rnbd_srv_init_module(void)
 	};
 	rtrs_ctx = rtrs_srv_open(&rtrs_ops, port_nr);
 	if (IS_ERR(rtrs_ctx)) {
-		pr_err("rtrs_srv_open(), err: %d\n", err);
+		pr_err("rtrs_srv_open(), err: %pe\n", rtrs_ctx);
 		return PTR_ERR(rtrs_ctx);
 	}
 
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 83600b45e12a..1dfb2e77898b 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -36,7 +36,7 @@
 #include <linux/sched/mm.h>
 #include <linux/uaccess.h>
 #include <linux/cdev.h>
-#include <linux/io_uring.h>
+#include <linux/io_uring/cmd.h>
 #include <linux/blk-mq.h>
 #include <linux/delay.h>
 #include <linux/mm.h>
@@ -250,7 +250,7 @@ static int ublk_dev_param_zoned_apply(struct ublk_device *ub)
 {
 	const struct ublk_param_zoned *p = &ub->params.zoned;
 
-	disk_set_zoned(ub->ub_disk, BLK_ZONED_HM);
+	disk_set_zoned(ub->ub_disk);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ub->ub_disk->queue);
 	blk_queue_required_elevator_features(ub->ub_disk->queue,
 					     ELEVATOR_F_ZBD_SEQ_WRITE);
@@ -893,12 +893,9 @@ static int ublk_map_io(const struct ublk_queue *ubq, const struct request *req,
 	 */
 	if (ublk_need_map_req(req)) {
 		struct iov_iter iter;
-		struct iovec iov;
 		const int dir = ITER_DEST;
 
-		import_single_range(dir, u64_to_user_ptr(io->addr), rq_bytes,
-				&iov, &iter);
-
+		import_ubuf(dir, u64_to_user_ptr(io->addr), rq_bytes, &iter);
 		return ublk_copy_user_pages(req, 0, &iter, dir);
 	}
 	return rq_bytes;
@@ -915,13 +912,11 @@ static int ublk_unmap_io(const struct ublk_queue *ubq,
 
 	if (ublk_need_unmap_req(req)) {
 		struct iov_iter iter;
-		struct iovec iov;
 		const int dir = ITER_SOURCE;
 
 		WARN_ON_ONCE(io->res > rq_bytes);
 
-		import_single_range(dir, u64_to_user_ptr(io->addr), io->res,
-				&iov, &iter);
+		import_ubuf(dir, u64_to_user_ptr(io->addr), io->res, &iter);
 		return ublk_copy_user_pages(req, 0, &iter, dir);
 	}
 	return rq_bytes;
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index d53d6aa8ee69..3b6b9abb8ce1 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -722,52 +722,15 @@ fail_report:
 	return ret;
 }
 
-static void virtblk_revalidate_zones(struct virtio_blk *vblk)
-{
-	u8 model;
-
-	virtio_cread(vblk->vdev, struct virtio_blk_config,
-		     zoned.model, &model);
-	switch (model) {
-	default:
-		dev_err(&vblk->vdev->dev, "unknown zone model %d\n", model);
-		fallthrough;
-	case VIRTIO_BLK_Z_NONE:
-	case VIRTIO_BLK_Z_HA:
-		disk_set_zoned(vblk->disk, BLK_ZONED_NONE);
-		return;
-	case VIRTIO_BLK_Z_HM:
-		WARN_ON_ONCE(!vblk->zone_sectors);
-		if (!blk_revalidate_disk_zones(vblk->disk, NULL))
-			set_capacity_and_notify(vblk->disk, 0);
-	}
-}
-
 static int virtblk_probe_zoned_device(struct virtio_device *vdev,
 				       struct virtio_blk *vblk,
 				       struct request_queue *q)
 {
 	u32 v, wg;
-	u8 model;
-
-	virtio_cread(vdev, struct virtio_blk_config,
-		     zoned.model, &model);
-
-	switch (model) {
-	case VIRTIO_BLK_Z_NONE:
-	case VIRTIO_BLK_Z_HA:
-		/* Present the host-aware device as non-zoned */
-		return 0;
-	case VIRTIO_BLK_Z_HM:
-		break;
-	default:
-		dev_err(&vdev->dev, "unsupported zone model %d\n", model);
-		return -EINVAL;
-	}
 
 	dev_dbg(&vdev->dev, "probing host-managed zoned device\n");
 
-	disk_set_zoned(vblk->disk, BLK_ZONED_HM);
+	disk_set_zoned(vblk->disk);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 
 	virtio_cread(vdev, struct virtio_blk_config,
@@ -839,23 +802,12 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev,
  */
 #define virtblk_report_zones       NULL
 
-static inline void virtblk_revalidate_zones(struct virtio_blk *vblk)
-{
-}
-
 static inline int virtblk_probe_zoned_device(struct virtio_device *vdev,
 			struct virtio_blk *vblk, struct request_queue *q)
 {
-	u8 model;
-
-	virtio_cread(vdev, struct virtio_blk_config, zoned.model, &model);
-	if (model == VIRTIO_BLK_Z_HM) {
-		dev_err(&vdev->dev,
-			"virtio_blk: zoned devices are not supported");
-		return -EOPNOTSUPP;
-	}
-
-	return 0;
+	dev_err(&vdev->dev,
+		"virtio_blk: zoned devices are not supported");
+	return -EOPNOTSUPP;
 }
 #endif /* CONFIG_BLK_DEV_ZONED */
 
@@ -1005,7 +957,6 @@ static void virtblk_config_changed_work(struct work_struct *work)
 	struct virtio_blk *vblk =
 		container_of(work, struct virtio_blk, config_work);
 
-	virtblk_revalidate_zones(vblk);
 	virtblk_update_capacity(vblk, true);
 }
 
@@ -1019,12 +970,12 @@ static void virtblk_config_changed(struct virtio_device *vdev)
 static int init_vq(struct virtio_blk *vblk)
 {
 	int err;
-	int i;
+	unsigned short i;
 	vq_callback_t **callbacks;
 	const char **names;
 	struct virtqueue **vqs;
 	unsigned short num_vqs;
-	unsigned int num_poll_vqs;
+	unsigned short num_poll_vqs;
 	struct virtio_device *vdev = vblk->vdev;
 	struct irq_affinity desc = { 0, };
 
@@ -1068,13 +1019,13 @@ static int init_vq(struct virtio_blk *vblk)
 
 	for (i = 0; i < num_vqs - num_poll_vqs; i++) {
 		callbacks[i] = virtblk_done;
-		snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req.%d", i);
+		snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req.%u", i);
 		names[i] = vblk->vqs[i].name;
 	}
 
 	for (; i < num_vqs; i++) {
 		callbacks[i] = NULL;
-		snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req_poll.%d", i);
+		snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req_poll.%u", i);
 		names[i] = vblk->vqs[i].name;
 	}
 
@@ -1570,9 +1521,26 @@ static int virtblk_probe(struct virtio_device *vdev)
 	 * placed after the virtio_device_ready() call above.
 	 */
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_ZONED)) {
-		err = virtblk_probe_zoned_device(vdev, vblk, q);
-		if (err)
+		u8 model;
+
+		virtio_cread(vdev, struct virtio_blk_config, zoned.model,
+				&model);
+		switch (model) {
+		case VIRTIO_BLK_Z_NONE:
+		case VIRTIO_BLK_Z_HA:
+			/* Present the host-aware device as non-zoned */
+			break;
+		case VIRTIO_BLK_Z_HM:
+			err = virtblk_probe_zoned_device(vdev, vblk, q);
+			if (err)
+				goto out_cleanup_disk;
+			break;
+		default:
+			dev_err(&vdev->dev, "unsupported zone model %d\n",
+				model);
+			err = -EINVAL;
 			goto out_cleanup_disk;
+		}
 	}
 
 	err = device_add_disk(&vdev->dev, vblk->disk, virtblk_attr_groups);
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index 5ff50e76cee5..1432c83183d0 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -132,7 +132,7 @@ struct blkif_x86_32_request {
 struct blkif_x86_64_request_rw {
 	uint8_t        nr_segments;  /* number of segments                   */
 	blkif_vdev_t   handle;       /* only for read/write requests         */
-	uint32_t       _pad1;        /* offsetof(blkif_reqest..,u.rw.id)==8  */
+	uint32_t       _pad1;        /* offsetof(blkif_request..,u.rw.id)==8 */
 	uint64_t       id;
 	blkif_sector_t sector_number;/* start sector idx on disk (r/w only)  */
 	struct blkif_request_segment seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig
index 0386b7da02aa..7b29cce60ab2 100644
--- a/drivers/block/zram/Kconfig
+++ b/drivers/block/zram/Kconfig
@@ -59,8 +59,8 @@ config ZRAM_WRITEBACK
        bool "Write back incompressible or idle page to backing device"
        depends on ZRAM
        help
-	 With incompressible page, there is no memory saving to keep it
-	 in memory. Instead, write it out to backing device.
+	 This lets zram entries (incompressible or idle pages) be written
+	 back to a backing device, helping save memory.
 	 For this feature, admin should set up backing device via
 	 /sys/block/zramX/backing_dev.
 
@@ -69,9 +69,18 @@ config ZRAM_WRITEBACK
 
 	 See Documentation/admin-guide/blockdev/zram.rst for more information.
 
+config ZRAM_TRACK_ENTRY_ACTIME
+	bool "Track access time of zram entries"
+	depends on ZRAM
+	help
+	  With this feature zram tracks access time of every stored
+	  entry (page), which can be used for a more fine grained IDLE
+	  pages writeback.
+
 config ZRAM_MEMORY_TRACKING
 	bool "Track zRam block status"
 	depends on ZRAM && DEBUG_FS
+	select ZRAM_TRACK_ENTRY_ACTIME
 	help
 	  With this feature, admin can track the state of allocated blocks
 	  of zRAM. Admin could see the information via
@@ -86,4 +95,4 @@ config ZRAM_MULTI_COMP
 	  This will enable multi-compression streams, so that ZRAM can
 	  re-compress pages using a potentially slower but more effective
 	  compression algorithm. Note, that IDLE page recompression
-	  requires ZRAM_MEMORY_TRACKING.
+	  requires ZRAM_TRACK_ENTRY_ACTIME.
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index d77d3664ca08..6772e0c654fa 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -174,6 +174,14 @@ static inline u32 zram_get_priority(struct zram *zram, u32 index)
 	return prio & ZRAM_COMP_PRIORITY_MASK;
 }
 
+static void zram_accessed(struct zram *zram, u32 index)
+{
+	zram_clear_flag(zram, index, ZRAM_IDLE);
+#ifdef CONFIG_ZRAM_TRACK_ENTRY_ACTIME
+	zram->table[index].ac_time = ktime_get_boottime();
+#endif
+}
+
 static inline void update_used_max(struct zram *zram,
 					const unsigned long pages)
 {
@@ -293,8 +301,9 @@ static void mark_idle(struct zram *zram, ktime_t cutoff)
 		zram_slot_lock(zram, index);
 		if (zram_allocated(zram, index) &&
 				!zram_test_flag(zram, index, ZRAM_UNDER_WB)) {
-#ifdef CONFIG_ZRAM_MEMORY_TRACKING
-			is_idle = !cutoff || ktime_after(cutoff, zram->table[index].ac_time);
+#ifdef CONFIG_ZRAM_TRACK_ENTRY_ACTIME
+			is_idle = !cutoff || ktime_after(cutoff,
+							 zram->table[index].ac_time);
 #endif
 			if (is_idle)
 				zram_set_flag(zram, index, ZRAM_IDLE);
@@ -317,7 +326,7 @@ static ssize_t idle_store(struct device *dev,
 		 */
 		u64 age_sec;
 
-		if (IS_ENABLED(CONFIG_ZRAM_MEMORY_TRACKING) && !kstrtoull(buf, 0, &age_sec))
+		if (IS_ENABLED(CONFIG_ZRAM_TRACK_ENTRY_ACTIME) && !kstrtoull(buf, 0, &age_sec))
 			cutoff_time = ktime_sub(ktime_get_boottime(),
 					ns_to_ktime(age_sec * NSEC_PER_SEC));
 		else
@@ -841,12 +850,6 @@ static void zram_debugfs_destroy(void)
 	debugfs_remove_recursive(zram_debugfs_root);
 }
 
-static void zram_accessed(struct zram *zram, u32 index)
-{
-	zram_clear_flag(zram, index, ZRAM_IDLE);
-	zram->table[index].ac_time = ktime_get_boottime();
-}
-
 static ssize_t read_block_state(struct file *file, char __user *buf,
 				size_t count, loff_t *ppos)
 {
@@ -930,10 +933,6 @@ static void zram_debugfs_unregister(struct zram *zram)
 #else
 static void zram_debugfs_create(void) {};
 static void zram_debugfs_destroy(void) {};
-static void zram_accessed(struct zram *zram, u32 index)
-{
-	zram_clear_flag(zram, index, ZRAM_IDLE);
-};
 static void zram_debugfs_register(struct zram *zram) {};
 static void zram_debugfs_unregister(struct zram *zram) {};
 #endif
@@ -1254,7 +1253,7 @@ static void zram_free_page(struct zram *zram, size_t index)
 {
 	unsigned long handle;
 
-#ifdef CONFIG_ZRAM_MEMORY_TRACKING
+#ifdef CONFIG_ZRAM_TRACK_ENTRY_ACTIME
 	zram->table[index].ac_time = 0;
 #endif
 	if (zram_test_flag(zram, index, ZRAM_IDLE))
@@ -1322,9 +1321,9 @@ static int zram_read_from_zspool(struct zram *zram, struct page *page,
 		void *mem;
 
 		value = handle ? zram_get_element(zram, index) : 0;
-		mem = kmap_atomic(page);
+		mem = kmap_local_page(page);
 		zram_fill_page(mem, PAGE_SIZE, value);
-		kunmap_atomic(mem);
+		kunmap_local(mem);
 		return 0;
 	}
 
@@ -1337,14 +1336,14 @@ static int zram_read_from_zspool(struct zram *zram, struct page *page,
 
 	src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO);
 	if (size == PAGE_SIZE) {
-		dst = kmap_atomic(page);
+		dst = kmap_local_page(page);
 		memcpy(dst, src, PAGE_SIZE);
-		kunmap_atomic(dst);
+		kunmap_local(dst);
 		ret = 0;
 	} else {
-		dst = kmap_atomic(page);
+		dst = kmap_local_page(page);
 		ret = zcomp_decompress(zstrm, src, size, dst);
-		kunmap_atomic(dst);
+		kunmap_local(dst);
 		zcomp_stream_put(zram->comps[prio]);
 	}
 	zs_unmap_object(zram->mem_pool, handle);
@@ -1417,21 +1416,21 @@ static int zram_write_page(struct zram *zram, struct page *page, u32 index)
 	unsigned long element = 0;
 	enum zram_pageflags flags = 0;
 
-	mem = kmap_atomic(page);
+	mem = kmap_local_page(page);
 	if (page_same_filled(mem, &element)) {
-		kunmap_atomic(mem);
+		kunmap_local(mem);
 		/* Free memory associated with this sector now. */
 		flags = ZRAM_SAME;
 		atomic64_inc(&zram->stats.same_pages);
 		goto out;
 	}
-	kunmap_atomic(mem);
+	kunmap_local(mem);
 
 compress_again:
 	zstrm = zcomp_stream_get(zram->comps[ZRAM_PRIMARY_COMP]);
-	src = kmap_atomic(page);
+	src = kmap_local_page(page);
 	ret = zcomp_compress(zstrm, src, &comp_len);
-	kunmap_atomic(src);
+	kunmap_local(src);
 
 	if (unlikely(ret)) {
 		zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]);
@@ -1495,10 +1494,10 @@ compress_again:
 
 	src = zstrm->buffer;
 	if (comp_len == PAGE_SIZE)
-		src = kmap_atomic(page);
+		src = kmap_local_page(page);
 	memcpy(dst, src, comp_len);
 	if (comp_len == PAGE_SIZE)
-		kunmap_atomic(src);
+		kunmap_local(src);
 
 	zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]);
 	zs_unmap_object(zram->mem_pool, handle);
@@ -1615,9 +1614,9 @@ static int zram_recompress(struct zram *zram, u32 index, struct page *page,
 
 		num_recomps++;
 		zstrm = zcomp_stream_get(zram->comps[prio]);
-		src = kmap_atomic(page);
+		src = kmap_local_page(page);
 		ret = zcomp_compress(zstrm, src, &comp_len_new);
-		kunmap_atomic(src);
+		kunmap_local(src);
 
 		if (ret) {
 			zcomp_stream_put(zram->comps[prio]);
@@ -2227,7 +2226,6 @@ static int zram_add(void)
 					ZRAM_LOGICAL_BLOCK_SIZE);
 	blk_queue_io_min(zram->disk->queue, PAGE_SIZE);
 	blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
-	zram->disk->queue->limits.discard_granularity = PAGE_SIZE;
 	blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX);
 
 	/*
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index d090753f97be..3b94d12f41b4 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -69,7 +69,7 @@ struct zram_table_entry {
 		unsigned long element;
 	};
 	unsigned long flags;
-#ifdef CONFIG_ZRAM_MEMORY_TRACKING
+#ifdef CONFIG_ZRAM_TRACK_ENTRY_ACTIME
 	ktime_t ac_time;
 #endif
 };
diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index 2462796a512a..cdc5c08824a0 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -535,6 +535,8 @@ static int btintel_version_info_tlv(struct hci_dev *hdev,
 	bt_dev_info(hdev, "%s timestamp %u.%u buildtype %u build %u", variant,
 		    2000 + (version->timestamp >> 8), version->timestamp & 0xff,
 		    version->build_type, version->build_num);
+	if (version->img_type == 0x03)
+		bt_dev_info(hdev, "Firmware SHA1: 0x%8.8x", version->git_sha1);
 
 	return 0;
 }
@@ -630,6 +632,9 @@ static int btintel_parse_version_tlv(struct hci_dev *hdev,
 			memcpy(&version->otp_bd_addr, tlv->val,
 							sizeof(bdaddr_t));
 			break;
+		case INTEL_TLV_GIT_SHA1:
+			version->git_sha1 = get_unaligned_le32(tlv->val);
+			break;
 		default:
 			/* Ignore rest of information */
 			break;
diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h
index 3a2d5b4219dd..d19fcdb9ff0b 100644
--- a/drivers/bluetooth/btintel.h
+++ b/drivers/bluetooth/btintel.h
@@ -41,7 +41,8 @@ enum {
 	INTEL_TLV_LIMITED_CCE,
 	INTEL_TLV_SBE_TYPE,
 	INTEL_TLV_OTP_BDADDR,
-	INTEL_TLV_UNLOCKED_STATE
+	INTEL_TLV_UNLOCKED_STATE,
+	INTEL_TLV_GIT_SHA1
 };
 
 struct intel_tlv {
@@ -69,6 +70,7 @@ struct intel_version_tlv {
 	u8	min_fw_build_yy;
 	u8	limited_cce;
 	u8	sbe_type;
+	u32	git_sha1;
 	bdaddr_t otp_bd_addr;
 };
 
diff --git a/drivers/bluetooth/btmtkuart.c b/drivers/bluetooth/btmtkuart.c
index 935feab815d9..203a000a84e3 100644
--- a/drivers/bluetooth/btmtkuart.c
+++ b/drivers/bluetooth/btmtkuart.c
@@ -336,7 +336,7 @@ mtk_stp_split(struct btmtkuart_dev *bdev, const unsigned char *data, int count,
 	return data;
 }
 
-static int btmtkuart_recv(struct hci_dev *hdev, const u8 *data, size_t count)
+static void btmtkuart_recv(struct hci_dev *hdev, const u8 *data, size_t count)
 {
 	struct btmtkuart_dev *bdev = hci_get_drvdata(hdev);
 	const unsigned char *p_left = data, *p_h4;
@@ -375,25 +375,20 @@ static int btmtkuart_recv(struct hci_dev *hdev, const u8 *data, size_t count)
 			bt_dev_err(bdev->hdev,
 				   "Frame reassembly failed (%d)", err);
 			bdev->rx_skb = NULL;
-			return err;
+			return;
 		}
 
 		sz_left -= sz_h4;
 		p_left += sz_h4;
 	}
-
-	return 0;
 }
 
 static int btmtkuart_receive_buf(struct serdev_device *serdev, const u8 *data,
 				 size_t count)
 {
 	struct btmtkuart_dev *bdev = serdev_device_get_drvdata(serdev);
-	int err;
 
-	err = btmtkuart_recv(bdev->hdev, data, count);
-	if (err < 0)
-		return err;
+	btmtkuart_recv(bdev->hdev, data, count);
 
 	bdev->hdev->stat.byte_rx += count;
 
diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index b7e66b7ac570..b7c56be078f8 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -1276,11 +1276,9 @@ static int btnxpuart_receive_buf(struct serdev_device *serdev, const u8 *data,
 	if (IS_ERR(nxpdev->rx_skb)) {
 		int err = PTR_ERR(nxpdev->rx_skb);
 		/* Safe to ignore out-of-sync bootloader signatures */
-		if (is_fw_downloading(nxpdev))
-			return count;
-		bt_dev_err(nxpdev->hdev, "Frame reassembly failed (%d)", err);
-		nxpdev->rx_skb = NULL;
-		return err;
+		if (!is_fw_downloading(nxpdev))
+			bt_dev_err(nxpdev->hdev, "Frame reassembly failed (%d)", err);
+		return count;
 	}
 	if (!is_fw_downloading(nxpdev))
 		nxpdev->hdev->stat.byte_rx += count;
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index b8e9de887b5d..7835170b1d66 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -550,6 +550,8 @@ static const struct usb_device_id quirks_table[] = {
 						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3571), .driver_info = BTUSB_REALTEK |
 						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x13d3, 0x3572), .driver_info = BTUSB_REALTEK |
+						     BTUSB_WIDEBAND_SPEECH },
 
 	/* Realtek Bluetooth devices */
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x0bda, 0xe0, 0x01, 0x01),
@@ -4629,6 +4631,10 @@ static int btusb_suspend(struct usb_interface *intf, pm_message_t message)
 
 	BT_DBG("intf %p", intf);
 
+	/* Don't suspend if there are connections */
+	if (hci_conn_count(data->hdev))
+		return -EBUSY;
+
 	if (data->suspend_count++)
 		return 0;
 
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 067e248e3599..94b8c406f0c0 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -1815,6 +1815,24 @@ static void hci_coredump_qca(struct hci_dev *hdev)
 	kfree_skb(skb);
 }
 
+static int qca_get_data_path_id(struct hci_dev *hdev, __u8 *data_path_id)
+{
+	/* QCA uses 1 as non-HCI data path id for HFP */
+	*data_path_id = 1;
+	return 0;
+}
+
+static int qca_configure_hfp_offload(struct hci_dev *hdev)
+{
+	bt_dev_info(hdev, "HFP non-HCI data transport is supported");
+	hdev->get_data_path_id = qca_get_data_path_id;
+	/* Do not need to send HCI_Configure_Data_Path to configure non-HCI
+	 * data transport path for QCA controllers, so set below field as NULL.
+	 */
+	hdev->get_codec_config_data = NULL;
+	return 0;
+}
+
 static int qca_setup(struct hci_uart *hu)
 {
 	struct hci_dev *hdev = hu->hdev;
@@ -1969,6 +1987,10 @@ out:
 		hu->hdev->set_bdaddr = qca_set_bdaddr_rome;
 	else
 		hu->hdev->set_bdaddr = qca_set_bdaddr;
+
+	if (soc_type == QCA_QCA2066)
+		qca_configure_hfp_offload(hdev);
+
 	qca->fw_version = le16_to_cpu(ver.patch_ver);
 	qca->controller_id = le16_to_cpu(ver.rom_ver);
 	hci_devcd_register(hdev, hci_coredump_qca, qca_dmp_hdr, NULL);
@@ -2039,6 +2061,7 @@ static const struct qca_device_data qca_soc_data_wcn3998 __maybe_unused = {
 static const struct qca_device_data qca_soc_data_qca2066 __maybe_unused = {
 	.soc_type = QCA_QCA2066,
 	.num_vregs = 0,
+	.capabilities = QCA_CAP_WIDEBAND_SPEECH | QCA_CAP_VALID_LE_STATES,
 };
 
 static const struct qca_device_data qca_soc_data_qca6390 __maybe_unused = {
diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c
index f3892e9ce800..572d68d52965 100644
--- a/drivers/bluetooth/hci_vhci.c
+++ b/drivers/bluetooth/hci_vhci.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <asm/unaligned.h>
 
+#include <linux/atomic.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/slab.h>
@@ -44,6 +45,7 @@ struct vhci_data {
 	bool wakeup;
 	__u16 msft_opcode;
 	bool aosp_capable;
+	atomic_t initialized;
 };
 
 static int vhci_open_dev(struct hci_dev *hdev)
@@ -75,11 +77,10 @@ static int vhci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 
 	memcpy(skb_push(skb, 1), &hci_skb_pkt_type(skb), 1);
 
-	mutex_lock(&data->open_mutex);
 	skb_queue_tail(&data->readq, skb);
-	mutex_unlock(&data->open_mutex);
 
-	wake_up_interruptible(&data->read_wait);
+	if (atomic_read(&data->initialized))
+		wake_up_interruptible(&data->read_wait);
 	return 0;
 }
 
@@ -464,7 +465,8 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode)
 	skb_put_u8(skb, 0xff);
 	skb_put_u8(skb, opcode);
 	put_unaligned_le16(hdev->id, skb_put(skb, 2));
-	skb_queue_tail(&data->readq, skb);
+	skb_queue_head(&data->readq, skb);
+	atomic_inc(&data->initialized);
 
 	wake_up_interruptible(&data->read_wait);
 	return 0;
diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c
index 2f6d5002e43d..78b96cd63de9 100644
--- a/drivers/bus/fsl-mc/fsl-mc-bus.c
+++ b/drivers/bus/fsl-mc/fsl-mc-bus.c
@@ -1167,14 +1167,11 @@ error_cleanup_mc_io:
  * fsl_mc_bus_remove - callback invoked when the root MC bus is being
  * removed
  */
-static int fsl_mc_bus_remove(struct platform_device *pdev)
+static void fsl_mc_bus_remove(struct platform_device *pdev)
 {
 	struct fsl_mc *mc = platform_get_drvdata(pdev);
 	struct fsl_mc_io *mc_io;
 
-	if (!fsl_mc_is_root_dprc(&mc->root_mc_bus_dev->dev))
-		return -EINVAL;
-
 	mc_io = mc->root_mc_bus_dev->mc_io;
 	fsl_mc_device_remove(mc->root_mc_bus_dev);
 	fsl_destroy_mc_io(mc_io);
@@ -1190,13 +1187,6 @@ static int fsl_mc_bus_remove(struct platform_device *pdev)
 		       (GCR1_P1_STOP | GCR1_P2_STOP),
 		       mc->fsl_mc_regs + FSL_MC_GCR1);
 	}
-
-	return 0;
-}
-
-static void fsl_mc_bus_shutdown(struct platform_device *pdev)
-{
-	fsl_mc_bus_remove(pdev);
 }
 
 static const struct of_device_id fsl_mc_bus_match_table[] = {
@@ -1220,8 +1210,8 @@ static struct platform_driver fsl_mc_bus_driver = {
 		   .acpi_match_table = fsl_mc_bus_acpi_match_table,
 		   },
 	.probe = fsl_mc_bus_probe,
-	.remove = fsl_mc_bus_remove,
-	.shutdown = fsl_mc_bus_shutdown,
+	.remove_new = fsl_mc_bus_remove,
+	.shutdown = fsl_mc_bus_remove,
 };
 
 static int fsl_mc_bus_notifier(struct notifier_block *nb,
diff --git a/drivers/bus/hisi_lpc.c b/drivers/bus/hisi_lpc.c
index cdc4e38c113e..09340adbacc2 100644
--- a/drivers/bus/hisi_lpc.c
+++ b/drivers/bus/hisi_lpc.c
@@ -657,7 +657,7 @@ static int hisi_lpc_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int hisi_lpc_remove(struct platform_device *pdev)
+static void hisi_lpc_remove(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct hisi_lpc_dev *lpcdev = dev_get_drvdata(dev);
@@ -669,8 +669,6 @@ static int hisi_lpc_remove(struct platform_device *pdev)
 		of_platform_depopulate(dev);
 
 	logic_pio_unregister_range(range);
-
-	return 0;
 }
 
 static const struct of_device_id hisi_lpc_of_match[] = {
@@ -691,6 +689,6 @@ static struct platform_driver hisi_lpc_driver = {
 		.acpi_match_table = hisi_lpc_acpi_match,
 	},
 	.probe = hisi_lpc_probe,
-	.remove = hisi_lpc_remove,
+	.remove_new = hisi_lpc_remove,
 };
 builtin_platform_driver(hisi_lpc_driver);
diff --git a/drivers/bus/imx-weim.c b/drivers/bus/imx-weim.c
index 42c9386a7b42..6b5da73c8541 100644
--- a/drivers/bus/imx-weim.c
+++ b/drivers/bus/imx-weim.c
@@ -11,7 +11,10 @@
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/of_address.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/mfd/syscon.h>
 #include <linux/mfd/syscon/imx6q-iomuxc-gpr.h>
 #include <linux/regmap.h>
@@ -202,9 +205,7 @@ static int weim_timing_setup(struct device *dev, struct device_node *np,
 
 static int weim_parse_dt(struct platform_device *pdev)
 {
-	const struct of_device_id *of_id = of_match_device(weim_id_table,
-							   &pdev->dev);
-	const struct imx_weim_devtype *devtype = of_id->data;
+	const struct imx_weim_devtype *devtype = device_get_match_data(&pdev->dev);
 	int ret = 0, have_child = 0;
 	struct device_node *child;
 	struct weim_priv *priv;
diff --git a/drivers/bus/moxtet.c b/drivers/bus/moxtet.c
index 5eb0fe73ddc4..e384fbc6c1d9 100644
--- a/drivers/bus/moxtet.c
+++ b/drivers/bus/moxtet.c
@@ -755,7 +755,7 @@ static int moxtet_irq_setup(struct moxtet *moxtet)
 	moxtet->irq.masked = ~0;
 
 	ret = request_threaded_irq(moxtet->dev_irq, NULL, moxtet_irq_thread_fn,
-				   IRQF_ONESHOT, "moxtet", moxtet);
+				   IRQF_SHARED | IRQF_ONESHOT, "moxtet", moxtet);
 	if (ret < 0)
 		goto err_free;
 
@@ -830,6 +830,12 @@ static void moxtet_remove(struct spi_device *spi)
 	mutex_destroy(&moxtet->lock);
 }
 
+static const struct spi_device_id moxtet_spi_ids[] = {
+	{ "moxtet" },
+	{ },
+};
+MODULE_DEVICE_TABLE(spi, moxtet_spi_ids);
+
 static const struct of_device_id moxtet_dt_ids[] = {
 	{ .compatible = "cznic,moxtet" },
 	{},
@@ -841,6 +847,7 @@ static struct spi_driver moxtet_spi_driver = {
 		.name		= "moxtet",
 		.of_match_table = moxtet_dt_ids,
 	},
+	.id_table	= moxtet_spi_ids,
 	.probe		= moxtet_probe,
 	.remove		= moxtet_remove,
 };
diff --git a/drivers/bus/omap-ocp2scp.c b/drivers/bus/omap-ocp2scp.c
index e02d0656242b..7d7479ba0a75 100644
--- a/drivers/bus/omap-ocp2scp.c
+++ b/drivers/bus/omap-ocp2scp.c
@@ -84,12 +84,10 @@ err0:
 	return ret;
 }
 
-static int omap_ocp2scp_remove(struct platform_device *pdev)
+static void omap_ocp2scp_remove(struct platform_device *pdev)
 {
 	pm_runtime_disable(&pdev->dev);
 	device_for_each_child(&pdev->dev, NULL, ocp2scp_remove_devices);
-
-	return 0;
 }
 
 #ifdef CONFIG_OF
@@ -103,7 +101,7 @@ MODULE_DEVICE_TABLE(of, omap_ocp2scp_id_table);
 
 static struct platform_driver omap_ocp2scp_driver = {
 	.probe		= omap_ocp2scp_probe,
-	.remove		= omap_ocp2scp_remove,
+	.remove_new	= omap_ocp2scp_remove,
 	.driver		= {
 		.name	= "omap-ocp2scp",
 		.of_match_table = of_match_ptr(omap_ocp2scp_id_table),
diff --git a/drivers/bus/omap_l3_smx.c b/drivers/bus/omap_l3_smx.c
index 31774648be9d..ee6d29925e4d 100644
--- a/drivers/bus/omap_l3_smx.c
+++ b/drivers/bus/omap_l3_smx.c
@@ -261,7 +261,7 @@ err0:
 	return ret;
 }
 
-static int omap3_l3_remove(struct platform_device *pdev)
+static void omap3_l3_remove(struct platform_device *pdev)
 {
 	struct omap3_l3         *l3 = platform_get_drvdata(pdev);
 
@@ -269,13 +269,11 @@ static int omap3_l3_remove(struct platform_device *pdev)
 	free_irq(l3->debug_irq, l3);
 	iounmap(l3->rt);
 	kfree(l3);
-
-	return 0;
 }
 
 static struct platform_driver omap3_l3_driver = {
 	.probe		= omap3_l3_probe,
-	.remove         = omap3_l3_remove,
+	.remove_new     = omap3_l3_remove,
 	.driver         = {
 		.name   = "omap_l3_smx",
 		.of_match_table = of_match_ptr(omap3_l3_match),
diff --git a/drivers/bus/qcom-ssc-block-bus.c b/drivers/bus/qcom-ssc-block-bus.c
index 3fef18a43c01..5931974a21fa 100644
--- a/drivers/bus/qcom-ssc-block-bus.c
+++ b/drivers/bus/qcom-ssc-block-bus.c
@@ -350,7 +350,7 @@ static int qcom_ssc_block_bus_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int qcom_ssc_block_bus_remove(struct platform_device *pdev)
+static void qcom_ssc_block_bus_remove(struct platform_device *pdev)
 {
 	struct qcom_ssc_block_bus_data *data = platform_get_drvdata(pdev);
 
@@ -363,8 +363,6 @@ static int qcom_ssc_block_bus_remove(struct platform_device *pdev)
 	qcom_ssc_block_bus_pds_detach(&pdev->dev, data->pds, data->num_pds);
 	pm_runtime_disable(&pdev->dev);
 	pm_clk_destroy(&pdev->dev);
-
-	return 0;
 }
 
 static const struct of_device_id qcom_ssc_block_bus_of_match[] = {
@@ -375,7 +373,7 @@ MODULE_DEVICE_TABLE(of, qcom_ssc_block_bus_of_match);
 
 static struct platform_driver qcom_ssc_block_bus_driver = {
 	.probe = qcom_ssc_block_bus_probe,
-	.remove = qcom_ssc_block_bus_remove,
+	.remove_new = qcom_ssc_block_bus_remove,
 	.driver = {
 		.name = "qcom-ssc-block-bus",
 		.of_match_table = qcom_ssc_block_bus_of_match,
diff --git a/drivers/bus/simple-pm-bus.c b/drivers/bus/simple-pm-bus.c
index aafcc481de91..50870c827889 100644
--- a/drivers/bus/simple-pm-bus.c
+++ b/drivers/bus/simple-pm-bus.c
@@ -74,17 +74,16 @@ static int simple_pm_bus_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int simple_pm_bus_remove(struct platform_device *pdev)
+static void simple_pm_bus_remove(struct platform_device *pdev)
 {
 	const void *data = of_device_get_match_data(&pdev->dev);
 
 	if (pdev->driver_override || data)
-		return 0;
+		return;
 
 	dev_dbg(&pdev->dev, "%s\n", __func__);
 
 	pm_runtime_disable(&pdev->dev);
-	return 0;
 }
 
 static int simple_pm_bus_runtime_suspend(struct device *dev)
@@ -129,7 +128,7 @@ MODULE_DEVICE_TABLE(of, simple_pm_bus_of_match);
 
 static struct platform_driver simple_pm_bus_driver = {
 	.probe = simple_pm_bus_probe,
-	.remove = simple_pm_bus_remove,
+	.remove_new = simple_pm_bus_remove,
 	.driver = {
 		.name = "simple-pm-bus",
 		.of_match_table = simple_pm_bus_of_match,
diff --git a/drivers/bus/sun50i-de2.c b/drivers/bus/sun50i-de2.c
index 414f29cdedf0..3339311ce068 100644
--- a/drivers/bus/sun50i-de2.c
+++ b/drivers/bus/sun50i-de2.c
@@ -24,10 +24,9 @@ static int sun50i_de2_bus_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int sun50i_de2_bus_remove(struct platform_device *pdev)
+static void sun50i_de2_bus_remove(struct platform_device *pdev)
 {
 	sunxi_sram_release(&pdev->dev);
-	return 0;
 }
 
 static const struct of_device_id sun50i_de2_bus_of_match[] = {
@@ -37,7 +36,7 @@ static const struct of_device_id sun50i_de2_bus_of_match[] = {
 
 static struct platform_driver sun50i_de2_bus_driver = {
 	.probe = sun50i_de2_bus_probe,
-	.remove = sun50i_de2_bus_remove,
+	.remove_new = sun50i_de2_bus_remove,
 	.driver = {
 		.name = "sun50i-de2-bus",
 		.of_match_table = sun50i_de2_bus_of_match,
diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c
index db0ed4e5d315..fd3e9d82340a 100644
--- a/drivers/bus/sunxi-rsb.c
+++ b/drivers/bus/sunxi-rsb.c
@@ -817,15 +817,13 @@ static int sunxi_rsb_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int sunxi_rsb_remove(struct platform_device *pdev)
+static void sunxi_rsb_remove(struct platform_device *pdev)
 {
 	struct sunxi_rsb *rsb = platform_get_drvdata(pdev);
 
 	device_for_each_child(rsb->dev, NULL, sunxi_rsb_remove_devices);
 	pm_runtime_disable(&pdev->dev);
 	sunxi_rsb_hw_exit(rsb);
-
-	return 0;
 }
 
 static const struct dev_pm_ops sunxi_rsb_dev_pm_ops = {
@@ -842,7 +840,7 @@ MODULE_DEVICE_TABLE(of, sunxi_rsb_of_match_table);
 
 static struct platform_driver sunxi_rsb_driver = {
 	.probe = sunxi_rsb_probe,
-	.remove	= sunxi_rsb_remove,
+	.remove_new = sunxi_rsb_remove,
 	.driver	= {
 		.name = RSB_CTRL_NAME,
 		.of_match_table = sunxi_rsb_of_match_table,
diff --git a/drivers/bus/tegra-aconnect.c b/drivers/bus/tegra-aconnect.c
index ac58142301f4..de80008bff92 100644
--- a/drivers/bus/tegra-aconnect.c
+++ b/drivers/bus/tegra-aconnect.c
@@ -53,11 +53,9 @@ static int tegra_aconnect_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int tegra_aconnect_remove(struct platform_device *pdev)
+static void tegra_aconnect_remove(struct platform_device *pdev)
 {
 	pm_runtime_disable(&pdev->dev);
-
-	return 0;
 }
 
 static int tegra_aconnect_runtime_resume(struct device *dev)
@@ -106,7 +104,7 @@ MODULE_DEVICE_TABLE(of, tegra_aconnect_of_match);
 
 static struct platform_driver tegra_aconnect_driver = {
 	.probe = tegra_aconnect_probe,
-	.remove = tegra_aconnect_remove,
+	.remove_new = tegra_aconnect_remove,
 	.driver = {
 		.name = "tegra-aconnect",
 		.of_match_table = tegra_aconnect_of_match,
diff --git a/drivers/bus/tegra-gmi.c b/drivers/bus/tegra-gmi.c
index 59919e99f7cc..f5d6414df9f2 100644
--- a/drivers/bus/tegra-gmi.c
+++ b/drivers/bus/tegra-gmi.c
@@ -258,14 +258,12 @@ static int tegra_gmi_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int tegra_gmi_remove(struct platform_device *pdev)
+static void tegra_gmi_remove(struct platform_device *pdev)
 {
 	struct tegra_gmi *gmi = platform_get_drvdata(pdev);
 
 	of_platform_depopulate(gmi->dev);
 	tegra_gmi_disable(gmi);
-
-	return 0;
 }
 
 static int __maybe_unused tegra_gmi_runtime_resume(struct device *dev)
@@ -305,7 +303,7 @@ MODULE_DEVICE_TABLE(of, tegra_gmi_id_table);
 
 static struct platform_driver tegra_gmi_driver = {
 	.probe = tegra_gmi_probe,
-	.remove = tegra_gmi_remove,
+	.remove_new = tegra_gmi_remove,
 	.driver = {
 		.name		= "tegra-gmi",
 		.of_match_table	= tegra_gmi_id_table,
diff --git a/drivers/bus/ti-pwmss.c b/drivers/bus/ti-pwmss.c
index 480a4de76cd4..4969c556e752 100644
--- a/drivers/bus/ti-pwmss.c
+++ b/drivers/bus/ti-pwmss.c
@@ -33,10 +33,9 @@ static int pwmss_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int pwmss_remove(struct platform_device *pdev)
+static void pwmss_remove(struct platform_device *pdev)
 {
 	pm_runtime_disable(&pdev->dev);
-	return 0;
 }
 
 static struct platform_driver pwmss_driver = {
@@ -45,7 +44,7 @@ static struct platform_driver pwmss_driver = {
 		.of_match_table	= pwmss_of_match,
 	},
 	.probe	= pwmss_probe,
-	.remove	= pwmss_remove,
+	.remove_new = pwmss_remove,
 };
 
 module_platform_driver(pwmss_driver);
diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c
index d57bc066dce6..245e5e827d0d 100644
--- a/drivers/bus/ti-sysc.c
+++ b/drivers/bus/ti-sysc.c
@@ -2158,13 +2158,23 @@ static int sysc_reset(struct sysc *ddata)
 		sysc_val = sysc_read_sysconfig(ddata);
 		sysc_val |= sysc_mask;
 		sysc_write(ddata, sysc_offset, sysc_val);
-		/* Flush posted write */
+
+		/*
+		 * Some devices need a delay before reading registers
+		 * after reset. Presumably a srst_udelay is not needed
+		 * for devices that use a rstctrl register reset.
+		 */
+		if (ddata->cfg.srst_udelay)
+			fsleep(ddata->cfg.srst_udelay);
+
+		/*
+		 * Flush posted write. For devices needing srst_udelay
+		 * this should trigger an interconnect error if the
+		 * srst_udelay value is needed but not configured.
+		 */
 		sysc_val = sysc_read_sysconfig(ddata);
 	}
 
-	if (ddata->cfg.srst_udelay)
-		fsleep(ddata->cfg.srst_udelay);
-
 	if (ddata->post_reset_quirk)
 		ddata->post_reset_quirk(ddata);
 
@@ -3387,7 +3397,7 @@ unprepare:
 	return error;
 }
 
-static int sysc_remove(struct platform_device *pdev)
+static void sysc_remove(struct platform_device *pdev)
 {
 	struct sysc *ddata = platform_get_drvdata(pdev);
 	int error;
@@ -3412,8 +3422,6 @@ static int sysc_remove(struct platform_device *pdev)
 
 unprepare:
 	sysc_unprepare(ddata);
-
-	return 0;
 }
 
 static const struct of_device_id sysc_match[] = {
@@ -3439,7 +3447,7 @@ MODULE_DEVICE_TABLE(of, sysc_match);
 
 static struct platform_driver sysc_driver = {
 	.probe		= sysc_probe,
-	.remove		= sysc_remove,
+	.remove_new	= sysc_remove,
 	.driver         = {
 		.name   = "ti-sysc",
 		.of_match_table	= sysc_match,
diff --git a/drivers/bus/ts-nbus.c b/drivers/bus/ts-nbus.c
index 38c886dc2ed6..4fa932cb0915 100644
--- a/drivers/bus/ts-nbus.c
+++ b/drivers/bus/ts-nbus.c
@@ -331,7 +331,7 @@ static int ts_nbus_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int ts_nbus_remove(struct platform_device *pdev)
+static void ts_nbus_remove(struct platform_device *pdev)
 {
 	struct ts_nbus *ts_nbus = dev_get_drvdata(&pdev->dev);
 
@@ -339,8 +339,6 @@ static int ts_nbus_remove(struct platform_device *pdev)
 	mutex_lock(&ts_nbus->lock);
 	pwm_disable(ts_nbus->pwm);
 	mutex_unlock(&ts_nbus->lock);
-
-	return 0;
 }
 
 static const struct of_device_id ts_nbus_of_match[] = {
@@ -351,7 +349,7 @@ MODULE_DEVICE_TABLE(of, ts_nbus_of_match);
 
 static struct platform_driver ts_nbus_driver = {
 	.probe		= ts_nbus_probe,
-	.remove		= ts_nbus_remove,
+	.remove_new	= ts_nbus_remove,
 	.driver		= {
 		.name	= "ts_nbus",
 		.of_match_table = ts_nbus_of_match,
diff --git a/drivers/cache/Kconfig b/drivers/cache/Kconfig
index d6e5e3abaad8..9345ce4976d7 100644
--- a/drivers/cache/Kconfig
+++ b/drivers/cache/Kconfig
@@ -8,4 +8,10 @@ config AX45MP_L2_CACHE
 	help
 	  Support for the L2 cache controller on Andes Technology AX45MP platforms.
 
+config SIFIVE_CCACHE
+	bool "Sifive Composable Cache controller"
+	depends on ARCH_SIFIVE || ARCH_STARFIVE
+	help
+	  Support for the composable cache controller on SiFive platforms.
+
 endmenu
diff --git a/drivers/cache/Makefile b/drivers/cache/Makefile
index 2012e7fb978d..7657cff3bd6c 100644
--- a/drivers/cache/Makefile
+++ b/drivers/cache/Makefile
@@ -1,3 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
 
-obj-$(CONFIG_AX45MP_L2_CACHE) += ax45mp_cache.o
+obj-$(CONFIG_AX45MP_L2_CACHE)	+= ax45mp_cache.o
+obj-$(CONFIG_SIFIVE_CCACHE)	+= sifive_ccache.o
diff --git a/drivers/soc/sifive/sifive_ccache.c b/drivers/cache/sifive_ccache.c
index 3684f5b40a80..89ed6cd6b059 100644
--- a/drivers/soc/sifive/sifive_ccache.c
+++ b/drivers/cache/sifive_ccache.c
@@ -8,13 +8,16 @@
 
 #define pr_fmt(fmt) "CCACHE: " fmt
 
+#include <linux/align.h>
 #include <linux/debugfs.h>
 #include <linux/interrupt.h>
 #include <linux/of_irq.h>
 #include <linux/of_address.h>
 #include <linux/device.h>
 #include <linux/bitfield.h>
+#include <asm/cacheflush.h>
 #include <asm/cacheinfo.h>
+#include <asm/dma-noncoherent.h>
 #include <soc/sifive/sifive_ccache.h>
 
 #define SIFIVE_CCACHE_DIRECCFIX_LOW 0x100
@@ -39,10 +42,14 @@
 #define SIFIVE_CCACHE_CONFIG_SETS_MASK GENMASK_ULL(23, 16)
 #define SIFIVE_CCACHE_CONFIG_BLKS_MASK GENMASK_ULL(31, 24)
 
+#define SIFIVE_CCACHE_FLUSH64 0x200
+#define SIFIVE_CCACHE_FLUSH32 0x240
+
 #define SIFIVE_CCACHE_WAYENABLE 0x08
 #define SIFIVE_CCACHE_ECCINJECTERR 0x40
 
 #define SIFIVE_CCACHE_MAX_ECCINTR 4
+#define SIFIVE_CCACHE_LINE_SIZE 64
 
 static void __iomem *ccache_base;
 static int g_irq[SIFIVE_CCACHE_MAX_ECCINTR];
@@ -56,6 +63,11 @@ enum {
 	DIR_UNCORR,
 };
 
+enum {
+	QUIRK_NONSTANDARD_CACHE_OPS	= BIT(0),
+	QUIRK_BROKEN_DATA_UNCORR	= BIT(1),
+};
+
 #ifdef CONFIG_DEBUG_FS
 static struct dentry *sifive_test;
 
@@ -106,6 +118,8 @@ static void ccache_config_read(void)
 static const struct of_device_id sifive_ccache_ids[] = {
 	{ .compatible = "sifive,fu540-c000-ccache" },
 	{ .compatible = "sifive,fu740-c000-ccache" },
+	{ .compatible = "starfive,jh7100-ccache",
+	  .data = (void *)(QUIRK_NONSTANDARD_CACHE_OPS | QUIRK_BROKEN_DATA_UNCORR) },
 	{ .compatible = "sifive,ccache0" },
 	{ /* end of table */ }
 };
@@ -124,6 +138,34 @@ int unregister_sifive_ccache_error_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL_GPL(unregister_sifive_ccache_error_notifier);
 
+#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
+static void ccache_flush_range(phys_addr_t start, size_t len)
+{
+	phys_addr_t end = start + len;
+	phys_addr_t line;
+
+	if (!len)
+		return;
+
+	mb();
+	for (line = ALIGN_DOWN(start, SIFIVE_CCACHE_LINE_SIZE); line < end;
+			line += SIFIVE_CCACHE_LINE_SIZE) {
+#ifdef CONFIG_32BIT
+		writel(line >> 4, ccache_base + SIFIVE_CCACHE_FLUSH32);
+#else
+		writeq(line, ccache_base + SIFIVE_CCACHE_FLUSH64);
+#endif
+		mb();
+	}
+}
+
+static const struct riscv_nonstd_cache_ops ccache_mgmt_ops __initconst = {
+	.wback = &ccache_flush_range,
+	.inv = &ccache_flush_range,
+	.wback_inv = &ccache_flush_range,
+};
+#endif /* CONFIG_RISCV_NONSTANDARD_CACHE_OPS */
+
 static int ccache_largest_wayenabled(void)
 {
 	return readl(ccache_base + SIFIVE_CCACHE_WAYENABLE) & 0xFF;
@@ -210,11 +252,15 @@ static int __init sifive_ccache_init(void)
 	struct device_node *np;
 	struct resource res;
 	int i, rc, intr_num;
+	const struct of_device_id *match;
+	unsigned long quirks;
 
-	np = of_find_matching_node(NULL, sifive_ccache_ids);
+	np = of_find_matching_node_and_match(NULL, sifive_ccache_ids, &match);
 	if (!np)
 		return -ENODEV;
 
+	quirks = (uintptr_t)match->data;
+
 	if (of_address_to_resource(np, 0, &res)) {
 		rc = -ENODEV;
 		goto err_node_put;
@@ -240,6 +286,10 @@ static int __init sifive_ccache_init(void)
 
 	for (i = 0; i < intr_num; i++) {
 		g_irq[i] = irq_of_parse_and_map(np, i);
+
+		if (i == DATA_UNCORR && (quirks & QUIRK_BROKEN_DATA_UNCORR))
+			continue;
+
 		rc = request_irq(g_irq[i], ccache_int_handler, 0, "ccache_ecc",
 				 NULL);
 		if (rc) {
@@ -249,6 +299,14 @@ static int __init sifive_ccache_init(void)
 	}
 	of_node_put(np);
 
+#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
+	if (quirks & QUIRK_NONSTANDARD_CACHE_OPS) {
+		riscv_cbom_block_size = SIFIVE_CCACHE_LINE_SIZE;
+		riscv_noncoherent_supported();
+		riscv_noncoherent_register_cache_ops(&ccache_mgmt_ops);
+	}
+#endif
+
 	ccache_config_read();
 
 	ccache_cache_ops.get_priv_group = ccache_get_priv_group;
@@ -269,4 +327,4 @@ err_node_put:
 	return rc;
 }
 
-device_initcall(sifive_ccache_init);
+arch_initcall(sifive_ccache_init);
diff --git a/drivers/char/hw_random/atmel-rng.c b/drivers/char/hw_random/atmel-rng.c
index a37367ebcbac..e9157255f851 100644
--- a/drivers/char/hw_random/atmel-rng.c
+++ b/drivers/char/hw_random/atmel-rng.c
@@ -161,15 +161,13 @@ static int atmel_trng_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int atmel_trng_remove(struct platform_device *pdev)
+static void atmel_trng_remove(struct platform_device *pdev)
 {
 	struct atmel_trng *trng = platform_get_drvdata(pdev);
 
 	atmel_trng_cleanup(trng);
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_set_suspended(&pdev->dev);
-
-	return 0;
 }
 
 static int __maybe_unused atmel_trng_runtime_suspend(struct device *dev)
@@ -218,7 +216,7 @@ MODULE_DEVICE_TABLE(of, atmel_trng_dt_ids);
 
 static struct platform_driver atmel_trng_driver = {
 	.probe		= atmel_trng_probe,
-	.remove		= atmel_trng_remove,
+	.remove_new	= atmel_trng_remove,
 	.driver		= {
 		.name	= "atmel-trng",
 		.pm	= pm_ptr(&atmel_trng_pm_ops),
diff --git a/drivers/char/hw_random/cctrng.c b/drivers/char/hw_random/cctrng.c
index 1abbff04a015..c0d2f824769f 100644
--- a/drivers/char/hw_random/cctrng.c
+++ b/drivers/char/hw_random/cctrng.c
@@ -560,7 +560,7 @@ post_pm_err:
 	return rc;
 }
 
-static int cctrng_remove(struct platform_device *pdev)
+static void cctrng_remove(struct platform_device *pdev)
 {
 	struct cctrng_drvdata *drvdata = platform_get_drvdata(pdev);
 	struct device *dev = &pdev->dev;
@@ -570,8 +570,6 @@ static int cctrng_remove(struct platform_device *pdev)
 	cc_trng_pm_fini(drvdata);
 
 	dev_info(dev, "ARM cctrng device terminated\n");
-
-	return 0;
 }
 
 static int __maybe_unused cctrng_suspend(struct device *dev)
@@ -654,7 +652,7 @@ static struct platform_driver cctrng_driver = {
 		.pm = &cctrng_pm,
 	},
 	.probe = cctrng_probe,
-	.remove = cctrng_remove,
+	.remove_new = cctrng_remove,
 };
 
 module_platform_driver(cctrng_driver);
diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index 420f155d251f..a3bbdd6e60fc 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -23,10 +23,13 @@
 #include <linux/sched.h>
 #include <linux/sched/signal.h>
 #include <linux/slab.h>
+#include <linux/string.h>
 #include <linux/uaccess.h>
 
 #define RNG_MODULE_NAME		"hw_random"
 
+#define RNG_BUFFER_SIZE (SMP_CACHE_BYTES < 32 ? 32 : SMP_CACHE_BYTES)
+
 static struct hwrng *current_rng;
 /* the current rng has been explicitly chosen by user via sysfs */
 static int cur_rng_set_by_user;
@@ -58,7 +61,7 @@ static inline int rng_get_data(struct hwrng *rng, u8 *buffer, size_t size,
 
 static size_t rng_buffer_size(void)
 {
-	return SMP_CACHE_BYTES < 32 ? 32 : SMP_CACHE_BYTES;
+	return RNG_BUFFER_SIZE;
 }
 
 static void add_early_randomness(struct hwrng *rng)
@@ -209,6 +212,7 @@ static inline int rng_get_data(struct hwrng *rng, u8 *buffer, size_t size,
 static ssize_t rng_dev_read(struct file *filp, char __user *buf,
 			    size_t size, loff_t *offp)
 {
+	u8 buffer[RNG_BUFFER_SIZE];
 	ssize_t ret = 0;
 	int err = 0;
 	int bytes_read, len;
@@ -236,34 +240,37 @@ static ssize_t rng_dev_read(struct file *filp, char __user *buf,
 			if (bytes_read < 0) {
 				err = bytes_read;
 				goto out_unlock_reading;
+			} else if (bytes_read == 0 &&
+				   (filp->f_flags & O_NONBLOCK)) {
+				err = -EAGAIN;
+				goto out_unlock_reading;
 			}
+
 			data_avail = bytes_read;
 		}
 
-		if (!data_avail) {
-			if (filp->f_flags & O_NONBLOCK) {
-				err = -EAGAIN;
-				goto out_unlock_reading;
-			}
-		} else {
-			len = data_avail;
+		len = data_avail;
+		if (len) {
 			if (len > size)
 				len = size;
 
 			data_avail -= len;
 
-			if (copy_to_user(buf + ret, rng_buffer + data_avail,
-								len)) {
+			memcpy(buffer, rng_buffer + data_avail, len);
+		}
+		mutex_unlock(&reading_mutex);
+		put_rng(rng);
+
+		if (len) {
+			if (copy_to_user(buf + ret, buffer, len)) {
 				err = -EFAULT;
-				goto out_unlock_reading;
+				goto out;
 			}
 
 			size -= len;
 			ret += len;
 		}
 
-		mutex_unlock(&reading_mutex);
-		put_rng(rng);
 
 		if (need_resched())
 			schedule_timeout_interruptible(1);
@@ -274,6 +281,7 @@ static ssize_t rng_dev_read(struct file *filp, char __user *buf,
 		}
 	}
 out:
+	memzero_explicit(buffer, sizeof(buffer));
 	return ret ? : err;
 
 out_unlock_reading:
diff --git a/drivers/char/hw_random/exynos-trng.c b/drivers/char/hw_random/exynos-trng.c
index 30207b7ac5f4..0ed5d22fe667 100644
--- a/drivers/char/hw_random/exynos-trng.c
+++ b/drivers/char/hw_random/exynos-trng.c
@@ -173,7 +173,7 @@ err_pm_get:
 	return ret;
 }
 
-static int exynos_trng_remove(struct platform_device *pdev)
+static void exynos_trng_remove(struct platform_device *pdev)
 {
 	struct exynos_trng_dev *trng =  platform_get_drvdata(pdev);
 
@@ -181,8 +181,6 @@ static int exynos_trng_remove(struct platform_device *pdev)
 
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-
-	return 0;
 }
 
 static int exynos_trng_suspend(struct device *dev)
@@ -223,7 +221,7 @@ static struct platform_driver exynos_trng_driver = {
 		.of_match_table = exynos_trng_dt_match,
 	},
 	.probe = exynos_trng_probe,
-	.remove = exynos_trng_remove,
+	.remove_new = exynos_trng_remove,
 };
 
 module_platform_driver(exynos_trng_driver);
diff --git a/drivers/char/hw_random/ingenic-rng.c b/drivers/char/hw_random/ingenic-rng.c
index 4f18c3fa5427..2f9b6483c4a1 100644
--- a/drivers/char/hw_random/ingenic-rng.c
+++ b/drivers/char/hw_random/ingenic-rng.c
@@ -11,7 +11,7 @@
 #include <linux/io.h>
 #include <linux/iopoll.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 
@@ -114,15 +114,13 @@ static int ingenic_rng_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int ingenic_rng_remove(struct platform_device *pdev)
+static void ingenic_rng_remove(struct platform_device *pdev)
 {
 	struct ingenic_rng *priv = platform_get_drvdata(pdev);
 
 	hwrng_unregister(&priv->rng);
 
 	writel(0, priv->base + RNG_REG_ERNG_OFFSET);
-
-	return 0;
 }
 
 static const struct of_device_id ingenic_rng_of_match[] = {
@@ -134,7 +132,7 @@ MODULE_DEVICE_TABLE(of, ingenic_rng_of_match);
 
 static struct platform_driver ingenic_rng_driver = {
 	.probe		= ingenic_rng_probe,
-	.remove		= ingenic_rng_remove,
+	.remove_new	= ingenic_rng_remove,
 	.driver		= {
 		.name	= "ingenic-rng",
 		.of_match_table = ingenic_rng_of_match,
diff --git a/drivers/char/hw_random/jh7110-trng.c b/drivers/char/hw_random/jh7110-trng.c
index 38474d48a25e..9776f4daa044 100644
--- a/drivers/char/hw_random/jh7110-trng.c
+++ b/drivers/char/hw_random/jh7110-trng.c
@@ -300,7 +300,7 @@ static int starfive_trng_probe(struct platform_device *pdev)
 	ret = devm_request_irq(&pdev->dev, irq, starfive_trng_irq, 0, pdev->name,
 			       (void *)trng);
 	if (ret)
-		return dev_err_probe(&pdev->dev, irq,
+		return dev_err_probe(&pdev->dev, ret,
 				     "Failed to register interrupt handler\n");
 
 	trng->hclk = devm_clk_get(&pdev->dev, "hclk");
@@ -369,8 +369,12 @@ static int __maybe_unused starfive_trng_resume(struct device *dev)
 	return 0;
 }
 
-static DEFINE_SIMPLE_DEV_PM_OPS(starfive_trng_pm_ops, starfive_trng_suspend,
-				starfive_trng_resume);
+static const struct dev_pm_ops starfive_trng_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(starfive_trng_suspend,
+				starfive_trng_resume)
+	SET_RUNTIME_PM_OPS(starfive_trng_suspend,
+			   starfive_trng_resume, NULL)
+};
 
 static const struct of_device_id trng_dt_ids[] __maybe_unused = {
 	{ .compatible = "starfive,jh7110-trng" },
diff --git a/drivers/char/hw_random/ks-sa-rng.c b/drivers/char/hw_random/ks-sa-rng.c
index dff7b9db7044..36c34252b4f6 100644
--- a/drivers/char/hw_random/ks-sa-rng.c
+++ b/drivers/char/hw_random/ks-sa-rng.c
@@ -241,12 +241,10 @@ static int ks_sa_rng_probe(struct platform_device *pdev)
 	return devm_hwrng_register(&pdev->dev, &ks_sa_rng->rng);
 }
 
-static int ks_sa_rng_remove(struct platform_device *pdev)
+static void ks_sa_rng_remove(struct platform_device *pdev)
 {
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-
-	return 0;
 }
 
 static const struct of_device_id ks_sa_rng_dt_match[] = {
@@ -263,7 +261,7 @@ static struct platform_driver ks_sa_rng_driver = {
 		.of_match_table = ks_sa_rng_dt_match,
 	},
 	.probe		= ks_sa_rng_probe,
-	.remove		= ks_sa_rng_remove,
+	.remove_new	= ks_sa_rng_remove,
 };
 
 module_platform_driver(ks_sa_rng_driver);
diff --git a/drivers/char/hw_random/mxc-rnga.c b/drivers/char/hw_random/mxc-rnga.c
index 008763c988ed..07ec000e4cd7 100644
--- a/drivers/char/hw_random/mxc-rnga.c
+++ b/drivers/char/hw_random/mxc-rnga.c
@@ -176,15 +176,13 @@ err_ioremap:
 	return err;
 }
 
-static int __exit mxc_rnga_remove(struct platform_device *pdev)
+static void __exit mxc_rnga_remove(struct platform_device *pdev)
 {
 	struct mxc_rng *mxc_rng = platform_get_drvdata(pdev);
 
 	hwrng_unregister(&mxc_rng->rng);
 
 	clk_disable_unprepare(mxc_rng->clk);
-
-	return 0;
 }
 
 static const struct of_device_id mxc_rnga_of_match[] = {
@@ -199,7 +197,7 @@ static struct platform_driver mxc_rnga_driver = {
 		.name = "mxc_rnga",
 		.of_match_table = mxc_rnga_of_match,
 	},
-	.remove = __exit_p(mxc_rnga_remove),
+	.remove_new = __exit_p(mxc_rnga_remove),
 };
 
 module_platform_driver_probe(mxc_rnga_driver, mxc_rnga_probe);
diff --git a/drivers/char/hw_random/n2-drv.c b/drivers/char/hw_random/n2-drv.c
index aaae16b98475..2e669e7c14d3 100644
--- a/drivers/char/hw_random/n2-drv.c
+++ b/drivers/char/hw_random/n2-drv.c
@@ -781,7 +781,7 @@ out:
 	return err;
 }
 
-static int n2rng_remove(struct platform_device *op)
+static void n2rng_remove(struct platform_device *op)
 {
 	struct n2rng *np = platform_get_drvdata(op);
 
@@ -790,8 +790,6 @@ static int n2rng_remove(struct platform_device *op)
 	cancel_delayed_work_sync(&np->work);
 
 	sun4v_hvapi_unregister(HV_GRP_RNG);
-
-	return 0;
 }
 
 static struct n2rng_template n2_template = {
@@ -860,7 +858,7 @@ static struct platform_driver n2rng_driver = {
 		.of_match_table = n2rng_match,
 	},
 	.probe		= n2rng_probe,
-	.remove		= n2rng_remove,
+	.remove_new	= n2rng_remove,
 };
 
 module_platform_driver(n2rng_driver);
diff --git a/drivers/char/hw_random/npcm-rng.c b/drivers/char/hw_random/npcm-rng.c
index 8a304b754217..bce8c4829a1f 100644
--- a/drivers/char/hw_random/npcm-rng.c
+++ b/drivers/char/hw_random/npcm-rng.c
@@ -126,15 +126,13 @@ static int npcm_rng_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int npcm_rng_remove(struct platform_device *pdev)
+static void npcm_rng_remove(struct platform_device *pdev)
 {
 	struct npcm_rng *priv = platform_get_drvdata(pdev);
 
 	devm_hwrng_unregister(&pdev->dev, &priv->rng);
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_set_suspended(&pdev->dev);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM
@@ -178,7 +176,7 @@ static struct platform_driver npcm_rng_driver = {
 		.of_match_table = of_match_ptr(rng_dt_id),
 	},
 	.probe		= npcm_rng_probe,
-	.remove		= npcm_rng_remove,
+	.remove_new	= npcm_rng_remove,
 };
 
 module_platform_driver(npcm_rng_driver);
diff --git a/drivers/char/hw_random/omap-rng.c b/drivers/char/hw_random/omap-rng.c
index be03f76a2a80..d4c02e900466 100644
--- a/drivers/char/hw_random/omap-rng.c
+++ b/drivers/char/hw_random/omap-rng.c
@@ -509,7 +509,7 @@ err_ioremap:
 	return ret;
 }
 
-static int omap_rng_remove(struct platform_device *pdev)
+static void omap_rng_remove(struct platform_device *pdev)
 {
 	struct omap_rng_dev *priv = platform_get_drvdata(pdev);
 
@@ -521,8 +521,6 @@ static int omap_rng_remove(struct platform_device *pdev)
 
 	clk_disable_unprepare(priv->clk);
 	clk_disable_unprepare(priv->clk_reg);
-
-	return 0;
 }
 
 static int __maybe_unused omap_rng_suspend(struct device *dev)
@@ -560,7 +558,7 @@ static struct platform_driver omap_rng_driver = {
 		.of_match_table = of_match_ptr(omap_rng_of_match),
 	},
 	.probe		= omap_rng_probe,
-	.remove		= omap_rng_remove,
+	.remove_new	= omap_rng_remove,
 };
 
 module_platform_driver(omap_rng_driver);
diff --git a/drivers/char/hw_random/stm32-rng.c b/drivers/char/hw_random/stm32-rng.c
index 41e1dbea5d2e..379bc245c520 100644
--- a/drivers/char/hw_random/stm32-rng.c
+++ b/drivers/char/hw_random/stm32-rng.c
@@ -325,6 +325,7 @@ static int stm32_rng_init(struct hwrng *rng)
 							(!(reg & RNG_CR_CONDRST)),
 							10, 50000);
 		if (err) {
+			clk_disable_unprepare(priv->clk);
 			dev_err((struct device *)priv->rng.priv,
 				"%s: timeout %x!\n", __func__, reg);
 			return -EINVAL;
@@ -362,11 +363,9 @@ static int stm32_rng_init(struct hwrng *rng)
 	return 0;
 }
 
-static int stm32_rng_remove(struct platform_device *ofdev)
+static void stm32_rng_remove(struct platform_device *ofdev)
 {
 	pm_runtime_disable(&ofdev->dev);
-
-	return 0;
 }
 
 static int __maybe_unused stm32_rng_runtime_suspend(struct device *dev)
@@ -557,7 +556,7 @@ static struct platform_driver stm32_rng_driver = {
 		.of_match_table = stm32_rng_match,
 	},
 	.probe = stm32_rng_probe,
-	.remove = stm32_rng_remove,
+	.remove_new = stm32_rng_remove,
 };
 
 module_platform_driver(stm32_rng_driver);
diff --git a/drivers/char/hw_random/timeriomem-rng.c b/drivers/char/hw_random/timeriomem-rng.c
index 3db9d868efb1..65b8260339f5 100644
--- a/drivers/char/hw_random/timeriomem-rng.c
+++ b/drivers/char/hw_random/timeriomem-rng.c
@@ -174,13 +174,11 @@ static int timeriomem_rng_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int timeriomem_rng_remove(struct platform_device *pdev)
+static void timeriomem_rng_remove(struct platform_device *pdev)
 {
 	struct timeriomem_rng_private *priv = platform_get_drvdata(pdev);
 
 	hrtimer_cancel(&priv->timer);
-
-	return 0;
 }
 
 static const struct of_device_id timeriomem_rng_match[] = {
@@ -195,7 +193,7 @@ static struct platform_driver timeriomem_rng_driver = {
 		.of_match_table	= timeriomem_rng_match,
 	},
 	.probe		= timeriomem_rng_probe,
-	.remove		= timeriomem_rng_remove,
+	.remove_new	= timeriomem_rng_remove,
 };
 
 module_platform_driver(timeriomem_rng_driver);
diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c
index e41a84e6b4b5..7a4b45393acb 100644
--- a/drivers/char/hw_random/virtio-rng.c
+++ b/drivers/char/hw_random/virtio-rng.c
@@ -135,7 +135,7 @@ static int probe_common(struct virtio_device *vdev)
 	if (!vi)
 		return -ENOMEM;
 
-	vi->index = index = ida_simple_get(&rng_index_ida, 0, 0, GFP_KERNEL);
+	vi->index = index = ida_alloc(&rng_index_ida, GFP_KERNEL);
 	if (index < 0) {
 		err = index;
 		goto err_ida;
@@ -166,7 +166,7 @@ static int probe_common(struct virtio_device *vdev)
 	return 0;
 
 err_find:
-	ida_simple_remove(&rng_index_ida, index);
+	ida_free(&rng_index_ida, index);
 err_ida:
 	kfree(vi);
 	return err;
@@ -184,7 +184,7 @@ static void remove_common(struct virtio_device *vdev)
 		hwrng_unregister(&vi->hwrng);
 	virtio_reset_device(vdev);
 	vdev->config->del_vqs(vdev);
-	ida_simple_remove(&rng_index_ida, vi->index);
+	ida_free(&rng_index_ida, vi->index);
 	kfree(vi);
 }
 
@@ -208,7 +208,6 @@ static void virtrng_scan(struct virtio_device *vdev)
 		vi->hwrng_register_done = true;
 }
 
-#ifdef CONFIG_PM_SLEEP
 static int virtrng_freeze(struct virtio_device *vdev)
 {
 	remove_common(vdev);
@@ -238,7 +237,6 @@ static int virtrng_restore(struct virtio_device *vdev)
 
 	return err;
 }
-#endif
 
 static const struct virtio_device_id id_table[] = {
 	{ VIRTIO_ID_RNG, VIRTIO_DEV_ANY_ID },
@@ -252,10 +250,8 @@ static struct virtio_driver virtio_rng_driver = {
 	.probe =	virtrng_probe,
 	.remove =	virtrng_remove,
 	.scan =		virtrng_scan,
-#ifdef CONFIG_PM_SLEEP
-	.freeze =	virtrng_freeze,
-	.restore =	virtrng_restore,
-#endif
+	.freeze =	pm_sleep_ptr(virtrng_freeze),
+	.restore =	pm_sleep_ptr(virtrng_restore),
 };
 
 module_virtio_driver(virtio_rng_driver);
diff --git a/drivers/char/hw_random/xgene-rng.c b/drivers/char/hw_random/xgene-rng.c
index 7382724bf501..642d13519464 100644
--- a/drivers/char/hw_random/xgene-rng.c
+++ b/drivers/char/hw_random/xgene-rng.c
@@ -357,15 +357,13 @@ static int xgene_rng_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int xgene_rng_remove(struct platform_device *pdev)
+static void xgene_rng_remove(struct platform_device *pdev)
 {
 	int rc;
 
 	rc = device_init_wakeup(&pdev->dev, 0);
 	if (rc)
 		dev_err(&pdev->dev, "RNG init wakeup failed error %d\n", rc);
-
-	return 0;
 }
 
 static const struct of_device_id xgene_rng_of_match[] = {
@@ -377,7 +375,7 @@ MODULE_DEVICE_TABLE(of, xgene_rng_of_match);
 
 static struct platform_driver xgene_rng_driver = {
 	.probe = xgene_rng_probe,
-	.remove	= xgene_rng_remove,
+	.remove_new = xgene_rng_remove,
 	.driver = {
 		.name		= "xgene-rng",
 		.of_match_table = xgene_rng_of_match,
diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index d6f14279684d..b0eedc4595b3 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -3053,7 +3053,7 @@ static void cleanup_bmc_work(struct work_struct *work)
 	int id = bmc->pdev.id; /* Unregister overwrites id */
 
 	platform_device_unregister(&bmc->pdev);
-	ida_simple_remove(&ipmi_bmc_ida, id);
+	ida_free(&ipmi_bmc_ida, id);
 }
 
 static void
@@ -3169,7 +3169,7 @@ static int __ipmi_bmc_register(struct ipmi_smi *intf,
 
 		bmc->pdev.name = "ipmi_bmc";
 
-		rv = ida_simple_get(&ipmi_bmc_ida, 0, 0, GFP_KERNEL);
+		rv = ida_alloc(&ipmi_bmc_ida, GFP_KERNEL);
 		if (rv < 0) {
 			kfree(bmc);
 			goto out;
diff --git a/drivers/char/ipmi/ipmi_si_hardcode.c b/drivers/char/ipmi/ipmi_si_hardcode.c
index ed5e91b1e040..0c92fa3eee88 100644
--- a/drivers/char/ipmi/ipmi_si_hardcode.c
+++ b/drivers/char/ipmi/ipmi_si_hardcode.c
@@ -80,10 +80,10 @@ static void __init ipmi_hardcode_init_one(const char *si_type_str,
 	}
 
 	p.regsize = regsizes[i];
+	p.regspacing = regspacings[i];
 	p.slave_addr = slave_addrs[i];
 	p.addr_source = SI_HARDCODED;
 	p.regshift = regshifts[i];
-	p.regsize = regsizes[i];
 	p.addr = addr;
 	p.space = addr_space;
 
diff --git a/drivers/char/ipmi/ipmi_si_platform.c b/drivers/char/ipmi/ipmi_si_platform.c
index c3d8ac7873ba..cd2edd8f8a03 100644
--- a/drivers/char/ipmi/ipmi_si_platform.c
+++ b/drivers/char/ipmi/ipmi_si_platform.c
@@ -11,10 +11,11 @@
 
 #include <linux/types.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/acpi.h>
 #include "ipmi_si.h"
 #include "ipmi_dmi.h"
@@ -224,7 +225,6 @@ MODULE_DEVICE_TABLE(of, of_ipmi_match);
 
 static int of_ipmi_probe(struct platform_device *pdev)
 {
-	const struct of_device_id *match;
 	struct si_sm_io io;
 	struct resource resource;
 	const __be32 *regsize, *regspacing, *regshift;
@@ -237,10 +237,6 @@ static int of_ipmi_probe(struct platform_device *pdev)
 
 	dev_info(&pdev->dev, "probing via device tree\n");
 
-	match = of_match_device(of_ipmi_match, &pdev->dev);
-	if (!match)
-		return -ENODEV;
-
 	if (!of_device_is_available(np))
 		return -EINVAL;
 
@@ -269,7 +265,7 @@ static int of_ipmi_probe(struct platform_device *pdev)
 	}
 
 	memset(&io, 0, sizeof(io));
-	io.si_type	= (unsigned long) match->data;
+	io.si_type	= (enum si_type)device_get_match_data(&pdev->dev);
 	io.addr_source	= SI_DEVICETREE;
 	io.irq_setup	= ipmi_std_irq_setup;
 
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 4a9c79391dee..456be28ba67c 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1364,7 +1364,6 @@ static void __cold try_to_generate_entropy(void)
 SYSCALL_DEFINE3(getrandom, char __user *, ubuf, size_t, len, unsigned int, flags)
 {
 	struct iov_iter iter;
-	struct iovec iov;
 	int ret;
 
 	if (flags & ~(GRND_NONBLOCK | GRND_RANDOM | GRND_INSECURE))
@@ -1385,7 +1384,7 @@ SYSCALL_DEFINE3(getrandom, char __user *, ubuf, size_t, len, unsigned int, flags
 			return ret;
 	}
 
-	ret = import_single_range(ITER_DEST, ubuf, len, &iov, &iter);
+	ret = import_ubuf(ITER_DEST, ubuf, len, &iter);
 	if (unlikely(ret))
 		return ret;
 	return get_random_bytes_user(&iter);
@@ -1491,7 +1490,6 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 		return 0;
 	case RNDADDENTROPY: {
 		struct iov_iter iter;
-		struct iovec iov;
 		ssize_t ret;
 		int len;
 
@@ -1503,7 +1501,7 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 			return -EINVAL;
 		if (get_user(len, p++))
 			return -EFAULT;
-		ret = import_single_range(ITER_SOURCE, p, len, &iov, &iter);
+		ret = import_ubuf(ITER_SOURCE, p, len, &iter);
 		if (unlikely(ret))
 			return ret;
 		ret = write_pool_user(&iter);
diff --git a/drivers/char/tpm/tpm_i2c_nuvoton.c b/drivers/char/tpm/tpm_i2c_nuvoton.c
index d7be03c41098..5490f7e0fa43 100644
--- a/drivers/char/tpm/tpm_i2c_nuvoton.c
+++ b/drivers/char/tpm/tpm_i2c_nuvoton.c
@@ -19,7 +19,8 @@
 #include <linux/interrupt.h>
 #include <linux/wait.h>
 #include <linux/i2c.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/property.h>
 #include "tpm.h"
 
 /* I2C interface offsets */
@@ -524,7 +525,6 @@ static int get_vid(struct i2c_client *client, u32 *res)
 
 static int i2c_nuvoton_probe(struct i2c_client *client)
 {
-	const struct i2c_device_id *id = i2c_client_get_device_id(client);
 	int rc;
 	struct tpm_chip *chip;
 	struct device *dev = &client->dev;
@@ -546,15 +546,8 @@ static int i2c_nuvoton_probe(struct i2c_client *client)
 	if (!priv)
 		return -ENOMEM;
 
-	if (dev->of_node) {
-		const struct of_device_id *of_id;
-
-		of_id = of_match_device(dev->driver->of_match_table, dev);
-		if (of_id && of_id->data == OF_IS_TPM2)
-			chip->flags |= TPM_CHIP_FLAG_TPM2;
-	} else
-		if (id->driver_data == I2C_IS_TPM2)
-			chip->flags |= TPM_CHIP_FLAG_TPM2;
+	if (i2c_get_match_data(client))
+		chip->flags |= TPM_CHIP_FLAG_TPM2;
 
 	init_waitqueue_head(&priv->read_queue);
 
diff --git a/drivers/char/tpm/tpm_tis_i2c_cr50.c b/drivers/char/tpm/tpm_tis_i2c_cr50.c
index e70abd69e1ae..adf22992138e 100644
--- a/drivers/char/tpm/tpm_tis_i2c_cr50.c
+++ b/drivers/char/tpm/tpm_tis_i2c_cr50.c
@@ -235,7 +235,7 @@ out:
  * @len:	Number of bytes to write.
  *
  * The provided address is prepended to the data in 'buffer', the
- * cobined address+data is sent to the TPM, then wait for TPM to
+ * combined address+data is sent to the TPM, then wait for TPM to
  * indicate it is done writing.
  *
  * Return:
@@ -671,7 +671,6 @@ MODULE_DEVICE_TABLE(of, of_cr50_i2c_match);
 /**
  * tpm_cr50_i2c_probe() - Driver probe function.
  * @client:	I2C client information.
- * @id:		I2C device id.
  *
  * Return:
  * - 0:		Success.
diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig
index ad1acd9b7426..dbc3950c5960 100644
--- a/drivers/clk/qcom/Kconfig
+++ b/drivers/clk/qcom/Kconfig
@@ -767,6 +767,7 @@ config SM_CAMCC_8450
 
 config SM_CAMCC_8550
 	tristate "SM8550 Camera Clock Controller"
+	depends on ARM64 || COMPILE_TEST
 	select SM_GCC_8550
 	help
 	  Support for the camera clock controller on SM8550 devices.
diff --git a/drivers/clk/rockchip/clk-rk3128.c b/drivers/clk/rockchip/clk-rk3128.c
index aa53797dbfc1..75071e0cd321 100644
--- a/drivers/clk/rockchip/clk-rk3128.c
+++ b/drivers/clk/rockchip/clk-rk3128.c
@@ -138,7 +138,7 @@ PNAME(mux_pll_src_5plls_p)	= { "cpll", "gpll", "gpll_div2", "gpll_div3", "usb480
 PNAME(mux_pll_src_4plls_p)	= { "cpll", "gpll", "gpll_div2", "usb480m" };
 PNAME(mux_pll_src_3plls_p)	= { "cpll", "gpll", "gpll_div2" };
 
-PNAME(mux_aclk_peri_src_p)	= { "gpll_peri", "cpll_peri", "gpll_div2_peri", "gpll_div3_peri" };
+PNAME(mux_clk_peri_src_p)	= { "gpll", "cpll", "gpll_div2", "gpll_div3" };
 PNAME(mux_mmc_src_p)		= { "cpll", "gpll", "gpll_div2", "xin24m" };
 PNAME(mux_clk_cif_out_src_p)		= { "clk_cif_src", "xin24m" };
 PNAME(mux_sclk_vop_src_p)	= { "cpll", "gpll", "gpll_div2", "gpll_div3" };
@@ -275,23 +275,17 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = {
 			RK2928_CLKGATE_CON(0), 11, GFLAGS),
 
 	/* PD_PERI */
-	GATE(0, "gpll_peri", "gpll", CLK_IGNORE_UNUSED,
+	COMPOSITE(0, "clk_peri_src", mux_clk_peri_src_p, 0,
+			RK2928_CLKSEL_CON(10), 14, 2, MFLAGS, 0, 5, DFLAGS,
 			RK2928_CLKGATE_CON(2), 0, GFLAGS),
-	GATE(0, "cpll_peri", "cpll", CLK_IGNORE_UNUSED,
-			RK2928_CLKGATE_CON(2), 0, GFLAGS),
-	GATE(0, "gpll_div2_peri", "gpll_div2", CLK_IGNORE_UNUSED,
-			RK2928_CLKGATE_CON(2), 0, GFLAGS),
-	GATE(0, "gpll_div3_peri", "gpll_div3", CLK_IGNORE_UNUSED,
-			RK2928_CLKGATE_CON(2), 0, GFLAGS),
-	COMPOSITE_NOGATE(0, "aclk_peri_src", mux_aclk_peri_src_p, 0,
-			RK2928_CLKSEL_CON(10), 14, 2, MFLAGS, 0, 5, DFLAGS),
-	COMPOSITE_NOMUX(PCLK_PERI, "pclk_peri", "aclk_peri_src", 0,
+
+	COMPOSITE_NOMUX(PCLK_PERI, "pclk_peri", "clk_peri_src", 0,
 			RK2928_CLKSEL_CON(10), 12, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO,
 			RK2928_CLKGATE_CON(2), 3, GFLAGS),
-	COMPOSITE_NOMUX(HCLK_PERI, "hclk_peri", "aclk_peri_src", 0,
+	COMPOSITE_NOMUX(HCLK_PERI, "hclk_peri", "clk_peri_src", 0,
 			RK2928_CLKSEL_CON(10), 8, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO,
 			RK2928_CLKGATE_CON(2), 2, GFLAGS),
-	GATE(ACLK_PERI, "aclk_peri", "aclk_peri_src", 0,
+	GATE(ACLK_PERI, "aclk_peri", "clk_peri_src", 0,
 			RK2928_CLKGATE_CON(2), 1, GFLAGS),
 
 	GATE(SCLK_TIMER0, "sclk_timer0", "xin24m", 0,
@@ -316,7 +310,7 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = {
 	GATE(SCLK_MIPI_24M, "clk_mipi_24m", "xin24m", CLK_IGNORE_UNUSED,
 			RK2928_CLKGATE_CON(2), 15, GFLAGS),
 
-	COMPOSITE(SCLK_SDMMC, "sclk_sdmmc0", mux_mmc_src_p, 0,
+	COMPOSITE(SCLK_SDMMC, "sclk_sdmmc", mux_mmc_src_p, 0,
 			RK2928_CLKSEL_CON(11), 6, 2, MFLAGS, 0, 6, DFLAGS,
 			RK2928_CLKGATE_CON(2), 11, GFLAGS),
 
@@ -490,7 +484,7 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = {
 	GATE(HCLK_I2S_2CH, "hclk_i2s_2ch", "hclk_peri", 0, RK2928_CLKGATE_CON(7), 2, GFLAGS),
 	GATE(0, "hclk_usb_peri", "hclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 13, GFLAGS),
 	GATE(HCLK_HOST2, "hclk_host2", "hclk_peri", 0, RK2928_CLKGATE_CON(7), 3, GFLAGS),
-	GATE(HCLK_OTG, "hclk_otg", "hclk_peri", 0, RK2928_CLKGATE_CON(3), 13, GFLAGS),
+	GATE(HCLK_OTG, "hclk_otg", "hclk_peri", 0, RK2928_CLKGATE_CON(5), 13, GFLAGS),
 	GATE(0, "hclk_peri_ahb", "hclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 14, GFLAGS),
 	GATE(HCLK_SPDIF, "hclk_spdif", "hclk_peri", 0, RK2928_CLKGATE_CON(10), 9, GFLAGS),
 	GATE(HCLK_TSP, "hclk_tsp", "hclk_peri", 0, RK2928_CLKGATE_CON(10), 12, GFLAGS),
diff --git a/drivers/clk/rockchip/clk-rk3568.c b/drivers/clk/rockchip/clk-rk3568.c
index 16dabe2b9c47..db713e1526cd 100644
--- a/drivers/clk/rockchip/clk-rk3568.c
+++ b/drivers/clk/rockchip/clk-rk3568.c
@@ -72,6 +72,7 @@ static struct rockchip_pll_rate_table rk3568_pll_rates[] = {
 	RK3036_PLL_RATE(408000000, 1, 68, 2, 2, 1, 0),
 	RK3036_PLL_RATE(312000000, 1, 78, 6, 1, 1, 0),
 	RK3036_PLL_RATE(297000000, 2, 99, 4, 1, 1, 0),
+	RK3036_PLL_RATE(292500000, 1, 195, 4, 4, 1, 0),
 	RK3036_PLL_RATE(241500000, 2, 161, 4, 2, 1, 0),
 	RK3036_PLL_RATE(216000000, 1, 72, 4, 2, 1, 0),
 	RK3036_PLL_RATE(200000000, 1, 100, 3, 4, 1, 0),
diff --git a/drivers/clk/samsung/Makefile b/drivers/clk/samsung/Makefile
index ebbeacabe88f..3056944a5a54 100644
--- a/drivers/clk/samsung/Makefile
+++ b/drivers/clk/samsung/Makefile
@@ -21,6 +21,7 @@ obj-$(CONFIG_EXYNOS_ARM64_COMMON_CLK)	+= clk-exynos7.o
 obj-$(CONFIG_EXYNOS_ARM64_COMMON_CLK)	+= clk-exynos7885.o
 obj-$(CONFIG_EXYNOS_ARM64_COMMON_CLK)	+= clk-exynos850.o
 obj-$(CONFIG_EXYNOS_ARM64_COMMON_CLK)	+= clk-exynosautov9.o
+obj-$(CONFIG_EXYNOS_ARM64_COMMON_CLK)	+= clk-gs101.o
 obj-$(CONFIG_S3C64XX_COMMON_CLK)	+= clk-s3c64xx.o
 obj-$(CONFIG_S5PV210_COMMON_CLK)	+= clk-s5pv210.o clk-s5pv210-audss.o
 obj-$(CONFIG_TESLA_FSD_COMMON_CLK)	+= clk-fsd.o
diff --git a/drivers/clk/samsung/clk-gs101.c b/drivers/clk/samsung/clk-gs101.c
new file mode 100644
index 000000000000..0964bb11657f
--- /dev/null
+++ b/drivers/clk/samsung/clk-gs101.c
@@ -0,0 +1,2518 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023 Linaro Ltd.
+ * Author: Peter Griffin <peter.griffin@linaro.org>
+ *
+ * Common Clock Framework support for GS101.
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#include <dt-bindings/clock/google,gs101.h>
+
+#include "clk.h"
+#include "clk-exynos-arm64.h"
+
+/* NOTE: Must be equal to the last clock ID increased by one */
+#define CLKS_NR_TOP	(CLK_GOUT_CMU_TPU_UART + 1)
+#define CLKS_NR_APM	(CLK_APM_PLL_DIV16_APM + 1)
+#define CLKS_NR_MISC	(CLK_GOUT_MISC_XIU_D_MISC_ACLK + 1)
+
+/* ---- CMU_TOP ------------------------------------------------------------- */
+
+/* Register Offset definitions for CMU_TOP (0x1e080000) */
+
+#define PLL_LOCKTIME_PLL_SHARED0			0x0000
+#define PLL_LOCKTIME_PLL_SHARED1			0x0004
+#define PLL_LOCKTIME_PLL_SHARED2			0x0008
+#define PLL_LOCKTIME_PLL_SHARED3			0x000c
+#define PLL_LOCKTIME_PLL_SPARE				0x0010
+#define PLL_CON0_PLL_SHARED0				0x0100
+#define PLL_CON1_PLL_SHARED0				0x0104
+#define PLL_CON2_PLL_SHARED0				0x0108
+#define PLL_CON3_PLL_SHARED0				0x010c
+#define PLL_CON4_PLL_SHARED0				0x0110
+#define PLL_CON0_PLL_SHARED1				0x0140
+#define PLL_CON1_PLL_SHARED1				0x0144
+#define PLL_CON2_PLL_SHARED1				0x0148
+#define PLL_CON3_PLL_SHARED1				0x014c
+#define PLL_CON4_PLL_SHARED1				0x0150
+#define PLL_CON0_PLL_SHARED2				0x0180
+#define PLL_CON1_PLL_SHARED2				0x0184
+#define PLL_CON2_PLL_SHARED2				0x0188
+#define PLL_CON3_PLL_SHARED2				0x018c
+#define PLL_CON4_PLL_SHARED2				0x0190
+#define PLL_CON0_PLL_SHARED3				0x01c0
+#define PLL_CON1_PLL_SHARED3				0x01c4
+#define PLL_CON2_PLL_SHARED3				0x01c8
+#define PLL_CON3_PLL_SHARED3				0x01cc
+#define PLL_CON4_PLL_SHARED3				0x01d0
+#define PLL_CON0_PLL_SPARE				0x0200
+#define PLL_CON1_PLL_SPARE				0x0204
+#define PLL_CON2_PLL_SPARE				0x0208
+#define PLL_CON3_PLL_SPARE				0x020c
+#define PLL_CON4_PLL_SPARE				0x0210
+#define CMU_CMU_TOP_CONTROLLER_OPTION			0x0800
+#define CLKOUT_CON_BLK_CMU_CMU_TOP_CLKOUT0		0x0810
+#define CMU_HCHGEN_CLKMUX_CMU_BOOST			0x0840
+#define CMU_HCHGEN_CLKMUX_TOP_BOOST			0x0844
+#define CMU_HCHGEN_CLKMUX				0x0850
+#define POWER_FAIL_DETECT_PLL				0x0864
+#define EARLY_WAKEUP_FORCED_0_ENABLE			0x0870
+#define EARLY_WAKEUP_FORCED_1_ENABLE			0x0874
+#define EARLY_WAKEUP_APM_CTRL				0x0878
+#define EARLY_WAKEUP_CLUSTER0_CTRL			0x087c
+#define EARLY_WAKEUP_DPU_CTRL				0x0880
+#define EARLY_WAKEUP_CSIS_CTRL				0x0884
+#define EARLY_WAKEUP_APM_DEST				0x0890
+#define EARLY_WAKEUP_CLUSTER0_DEST			0x0894
+#define EARLY_WAKEUP_DPU_DEST				0x0898
+#define EARLY_WAKEUP_CSIS_DEST				0x089c
+#define EARLY_WAKEUP_SW_TRIG_APM			0x08c0
+#define EARLY_WAKEUP_SW_TRIG_APM_SET			0x08c4
+#define EARLY_WAKEUP_SW_TRIG_APM_CLEAR			0x08c8
+#define EARLY_WAKEUP_SW_TRIG_CLUSTER0			0x08d0
+#define EARLY_WAKEUP_SW_TRIG_CLUSTER0_SET		0x08d4
+#define EARLY_WAKEUP_SW_TRIG_CLUSTER0_CLEAR		0x08d8
+#define EARLY_WAKEUP_SW_TRIG_DPU			0x08e0
+#define EARLY_WAKEUP_SW_TRIG_DPU_SET			0x08e4
+#define EARLY_WAKEUP_SW_TRIG_DPU_CLEAR			0x08e8
+#define EARLY_WAKEUP_SW_TRIG_CSIS			0x08f0
+#define EARLY_WAKEUP_SW_TRIG_CSIS_SET			0x08f4
+#define EARLY_WAKEUP_SW_TRIG_CSIS_CLEAR			0x08f8
+#define CLK_CON_MUX_MUX_CLKCMU_BO_BUS			0x1000
+#define CLK_CON_MUX_MUX_CLKCMU_BUS0_BUS			0x1004
+#define CLK_CON_MUX_MUX_CLKCMU_BUS1_BUS			0x1008
+#define CLK_CON_MUX_MUX_CLKCMU_BUS2_BUS			0x100c
+#define CLK_CON_MUX_MUX_CLKCMU_CIS_CLK0			0x1010
+#define CLK_CON_MUX_MUX_CLKCMU_CIS_CLK1			0x1014
+#define CLK_CON_MUX_MUX_CLKCMU_CIS_CLK2			0x1018
+#define CLK_CON_MUX_MUX_CLKCMU_CIS_CLK3			0x101c
+#define CLK_CON_MUX_MUX_CLKCMU_CIS_CLK4			0x1020
+#define CLK_CON_MUX_MUX_CLKCMU_CIS_CLK5			0x1024
+#define CLK_CON_MUX_MUX_CLKCMU_CIS_CLK6			0x1028
+#define CLK_CON_MUX_MUX_CLKCMU_CIS_CLK7			0x102c
+#define CLK_CON_MUX_MUX_CLKCMU_CMU_BOOST		0x1030
+#define CLK_CON_MUX_MUX_CLKCMU_CMU_BOOST_OPTION1	0x1034
+#define CLK_CON_MUX_MUX_CLKCMU_CORE_BUS			0x1038
+#define CLK_CON_MUX_MUX_CLKCMU_CPUCL0_DBG		0x103c
+#define CLK_CON_MUX_MUX_CLKCMU_CPUCL0_SWITCH		0x1040
+#define CLK_CON_MUX_MUX_CLKCMU_CPUCL1_SWITCH		0x1044
+#define CLK_CON_MUX_MUX_CLKCMU_CPUCL2_SWITCH		0x1048
+#define CLK_CON_MUX_MUX_CLKCMU_CSIS_BUS			0x104c
+#define CLK_CON_MUX_MUX_CLKCMU_DISP_BUS			0x1050
+#define CLK_CON_MUX_MUX_CLKCMU_DNS_BUS			0x1054
+#define CLK_CON_MUX_MUX_CLKCMU_DPU_BUS			0x1058
+#define CLK_CON_MUX_MUX_CLKCMU_EH_BUS			0x105c
+#define CLK_CON_MUX_MUX_CLKCMU_G2D_G2D			0x1060
+#define CLK_CON_MUX_MUX_CLKCMU_G2D_MSCL			0x1064
+#define CLK_CON_MUX_MUX_CLKCMU_G3AA_G3AA		0x1068
+#define CLK_CON_MUX_MUX_CLKCMU_G3D_BUSD			0x106c
+#define CLK_CON_MUX_MUX_CLKCMU_G3D_GLB			0x1070
+#define CLK_CON_MUX_MUX_CLKCMU_G3D_SWITCH		0x1074
+#define CLK_CON_MUX_MUX_CLKCMU_GDC_GDC0			0x1078
+#define CLK_CON_MUX_MUX_CLKCMU_GDC_GDC1			0x107c
+#define CLK_CON_MUX_MUX_CLKCMU_GDC_SCSC			0x1080
+#define CLK_CON_MUX_MUX_CLKCMU_HPM			0x1084
+#define CLK_CON_MUX_MUX_CLKCMU_HSI0_BUS			0x1088
+#define CLK_CON_MUX_MUX_CLKCMU_HSI0_DPGTC		0x108c
+#define CLK_CON_MUX_MUX_CLKCMU_HSI0_USB31DRD		0x1090
+#define CLK_CON_MUX_MUX_CLKCMU_HSI0_USBDPDBG		0x1094
+#define CLK_CON_MUX_MUX_CLKCMU_HSI1_BUS			0x1098
+#define CLK_CON_MUX_MUX_CLKCMU_HSI1_PCIE		0x109c
+#define CLK_CON_MUX_MUX_CLKCMU_HSI2_BUS			0x10a0
+#define CLK_CON_MUX_MUX_CLKCMU_HSI2_MMC_CARD		0x10a4
+#define CLK_CON_MUX_MUX_CLKCMU_HSI2_PCIE		0x10a8
+#define CLK_CON_MUX_MUX_CLKCMU_HSI2_UFS_EMBD		0x10ac
+#define CLK_CON_MUX_MUX_CLKCMU_IPP_BUS			0x10b0
+#define CLK_CON_MUX_MUX_CLKCMU_ITP_BUS			0x10b4
+#define CLK_CON_MUX_MUX_CLKCMU_MCSC_ITSC		0x10b8
+#define CLK_CON_MUX_MUX_CLKCMU_MCSC_MCSC		0x10bc
+#define CLK_CON_MUX_MUX_CLKCMU_MFC_MFC			0x10c0
+#define CLK_CON_MUX_MUX_CLKCMU_MIF_BUSP			0x10c4
+#define CLK_CON_MUX_MUX_CLKCMU_MIF_SWITCH		0x10c8
+#define CLK_CON_MUX_MUX_CLKCMU_MISC_BUS			0x10cc
+#define CLK_CON_MUX_MUX_CLKCMU_MISC_SSS			0x10d0
+#define CLK_CON_MUX_MUX_CLKCMU_PDP_BUS			0x10d4
+#define CLK_CON_MUX_MUX_CLKCMU_PDP_VRA			0x10d8
+#define CLK_CON_MUX_MUX_CLKCMU_PERIC0_BUS		0x10dc
+#define CLK_CON_MUX_MUX_CLKCMU_PERIC0_IP		0x10e0
+#define CLK_CON_MUX_MUX_CLKCMU_PERIC1_BUS		0x10e4
+#define CLK_CON_MUX_MUX_CLKCMU_PERIC1_IP		0x10e8
+#define CLK_CON_MUX_MUX_CLKCMU_TNR_BUS			0x10ec
+#define CLK_CON_MUX_MUX_CLKCMU_TOP_BOOST_OPTION1	0x10f0
+#define CLK_CON_MUX_MUX_CLKCMU_TOP_CMUREF		0x10f4
+#define CLK_CON_MUX_MUX_CLKCMU_TPU_BUS			0x10f8
+#define CLK_CON_MUX_MUX_CLKCMU_TPU_TPU			0x10fc
+#define CLK_CON_MUX_MUX_CLKCMU_TPU_TPUCTL		0x1100
+#define CLK_CON_MUX_MUX_CLKCMU_TPU_UART			0x1104
+#define CLK_CON_MUX_MUX_CMU_CMUREF			0x1108
+#define CLK_CON_DIV_CLKCMU_BO_BUS			0x1800
+#define CLK_CON_DIV_CLKCMU_BUS0_BUS			0x1804
+#define CLK_CON_DIV_CLKCMU_BUS1_BUS			0x1808
+#define CLK_CON_DIV_CLKCMU_BUS2_BUS			0x180c
+#define CLK_CON_DIV_CLKCMU_CIS_CLK0			0x1810
+#define CLK_CON_DIV_CLKCMU_CIS_CLK1			0x1814
+#define CLK_CON_DIV_CLKCMU_CIS_CLK2			0x1818
+#define CLK_CON_DIV_CLKCMU_CIS_CLK3			0x181c
+#define CLK_CON_DIV_CLKCMU_CIS_CLK4			0x1820
+#define CLK_CON_DIV_CLKCMU_CIS_CLK5			0x1824
+#define CLK_CON_DIV_CLKCMU_CIS_CLK6			0x1828
+#define CLK_CON_DIV_CLKCMU_CIS_CLK7			0x182c
+#define CLK_CON_DIV_CLKCMU_CORE_BUS			0x1830
+#define CLK_CON_DIV_CLKCMU_CPUCL0_DBG			0x1834
+#define CLK_CON_DIV_CLKCMU_CPUCL0_SWITCH		0x1838
+#define CLK_CON_DIV_CLKCMU_CPUCL1_SWITCH		0x183c
+#define CLK_CON_DIV_CLKCMU_CPUCL2_SWITCH		0x1840
+#define CLK_CON_DIV_CLKCMU_CSIS_BUS			0x1844
+#define CLK_CON_DIV_CLKCMU_DISP_BUS			0x1848
+#define CLK_CON_DIV_CLKCMU_DNS_BUS			0x184c
+#define CLK_CON_DIV_CLKCMU_DPU_BUS			0x1850
+#define CLK_CON_DIV_CLKCMU_EH_BUS			0x1854
+#define CLK_CON_DIV_CLKCMU_G2D_G2D			0x1858
+#define CLK_CON_DIV_CLKCMU_G2D_MSCL			0x185c
+#define CLK_CON_DIV_CLKCMU_G3AA_G3AA			0x1860
+#define CLK_CON_DIV_CLKCMU_G3D_BUSD			0x1864
+#define CLK_CON_DIV_CLKCMU_G3D_GLB			0x1868
+#define CLK_CON_DIV_CLKCMU_G3D_SWITCH			0x186c
+#define CLK_CON_DIV_CLKCMU_GDC_GDC0			0x1870
+#define CLK_CON_DIV_CLKCMU_GDC_GDC1			0x1874
+#define CLK_CON_DIV_CLKCMU_GDC_SCSC			0x1878
+#define CLK_CON_DIV_CLKCMU_HPM				0x187c
+#define CLK_CON_DIV_CLKCMU_HSI0_BUS			0x1880
+#define CLK_CON_DIV_CLKCMU_HSI0_DPGTC			0x1884
+#define CLK_CON_DIV_CLKCMU_HSI0_USB31DRD		0x1888
+#define CLK_CON_DIV_CLKCMU_HSI0_USBDPDBG		0x188c
+#define CLK_CON_DIV_CLKCMU_HSI1_BUS			0x1890
+#define CLK_CON_DIV_CLKCMU_HSI1_PCIE			0x1894
+#define CLK_CON_DIV_CLKCMU_HSI2_BUS			0x1898
+#define CLK_CON_DIV_CLKCMU_HSI2_MMC_CARD		0x189c
+#define CLK_CON_DIV_CLKCMU_HSI2_PCIE			0x18a0
+#define CLK_CON_DIV_CLKCMU_HSI2_UFS_EMBD		0x18a4
+#define CLK_CON_DIV_CLKCMU_IPP_BUS			0x18a8
+#define CLK_CON_DIV_CLKCMU_ITP_BUS			0x18ac
+#define CLK_CON_DIV_CLKCMU_MCSC_ITSC			0x18b0
+#define CLK_CON_DIV_CLKCMU_MCSC_MCSC			0x18b4
+#define CLK_CON_DIV_CLKCMU_MFC_MFC			0x18b8
+#define CLK_CON_DIV_CLKCMU_MIF_BUSP			0x18bc
+#define CLK_CON_DIV_CLKCMU_MISC_BUS			0x18c0
+#define CLK_CON_DIV_CLKCMU_MISC_SSS			0x18c4
+#define CLK_CON_DIV_CLKCMU_OTP				0x18c8
+#define CLK_CON_DIV_CLKCMU_PDP_BUS			0x18cc
+#define CLK_CON_DIV_CLKCMU_PDP_VRA			0x18d0
+#define CLK_CON_DIV_CLKCMU_PERIC0_BUS			0x18d4
+#define CLK_CON_DIV_CLKCMU_PERIC0_IP			0x18d8
+#define CLK_CON_DIV_CLKCMU_PERIC1_BUS			0x18dc
+#define CLK_CON_DIV_CLKCMU_PERIC1_IP			0x18e0
+#define CLK_CON_DIV_CLKCMU_TNR_BUS			0x18e4
+#define CLK_CON_DIV_CLKCMU_TPU_BUS			0x18e8
+#define CLK_CON_DIV_CLKCMU_TPU_TPU			0x18ec
+#define CLK_CON_DIV_CLKCMU_TPU_TPUCTL			0x18f0
+#define CLK_CON_DIV_CLKCMU_TPU_UART			0x18f4
+#define CLK_CON_DIV_DIV_CLKCMU_CMU_BOOST		0x18f8
+#define CLK_CON_DIV_DIV_CLK_CMU_CMUREF			0x18fc
+#define CLK_CON_DIV_PLL_SHARED0_DIV2			0x1900
+#define CLK_CON_DIV_PLL_SHARED0_DIV3			0x1904
+#define CLK_CON_DIV_PLL_SHARED0_DIV4			0x1908
+#define CLK_CON_DIV_PLL_SHARED0_DIV5			0x190c
+#define CLK_CON_DIV_PLL_SHARED1_DIV2			0x1910
+#define CLK_CON_DIV_PLL_SHARED1_DIV3			0x1914
+#define CLK_CON_DIV_PLL_SHARED1_DIV4			0x1918
+#define CLK_CON_DIV_PLL_SHARED2_DIV2			0x191c
+#define CLK_CON_DIV_PLL_SHARED3_DIV2			0x1920
+#define CLK_CON_GAT_CLKCMU_BUS0_BOOST			0x2000
+#define CLK_CON_GAT_CLKCMU_BUS1_BOOST			0x2004
+#define CLK_CON_GAT_CLKCMU_BUS2_BOOST			0x2008
+#define CLK_CON_GAT_CLKCMU_CORE_BOOST			0x200c
+#define CLK_CON_GAT_CLKCMU_CPUCL0_BOOST			0x2010
+#define CLK_CON_GAT_CLKCMU_CPUCL1_BOOST			0x2014
+#define CLK_CON_GAT_CLKCMU_CPUCL2_BOOST			0x2018
+#define CLK_CON_GAT_CLKCMU_MIF_BOOST			0x201c
+#define CLK_CON_GAT_CLKCMU_MIF_SWITCH			0x2020
+#define CLK_CON_GAT_GATE_CLKCMU_BO_BUS			0x2024
+#define CLK_CON_GAT_GATE_CLKCMU_BUS0_BUS		0x2028
+#define CLK_CON_GAT_GATE_CLKCMU_BUS1_BUS		0x202c
+#define CLK_CON_GAT_GATE_CLKCMU_BUS2_BUS		0x2030
+#define CLK_CON_GAT_GATE_CLKCMU_CIS_CLK0		0x2034
+#define CLK_CON_GAT_GATE_CLKCMU_CIS_CLK1		0x2038
+#define CLK_CON_GAT_GATE_CLKCMU_CIS_CLK2		0x203c
+#define CLK_CON_GAT_GATE_CLKCMU_CIS_CLK3		0x2040
+#define CLK_CON_GAT_GATE_CLKCMU_CIS_CLK4		0x2044
+#define CLK_CON_GAT_GATE_CLKCMU_CIS_CLK5		0x2048
+#define CLK_CON_GAT_GATE_CLKCMU_CIS_CLK6		0x204c
+#define CLK_CON_GAT_GATE_CLKCMU_CIS_CLK7		0x2050
+#define CLK_CON_GAT_GATE_CLKCMU_CMU_BOOST		0x2054
+#define CLK_CON_GAT_GATE_CLKCMU_CORE_BUS		0x2058
+#define CLK_CON_GAT_GATE_CLKCMU_CPUCL0_DBG_BUS		0x205c
+#define CLK_CON_GAT_GATE_CLKCMU_CPUCL0_SWITCH		0x2060
+#define CLK_CON_GAT_GATE_CLKCMU_CPUCL1_SWITCH		0x2064
+#define CLK_CON_GAT_GATE_CLKCMU_CPUCL2_SWITCH		0x2068
+#define CLK_CON_GAT_GATE_CLKCMU_CSIS_BUS		0x206c
+#define CLK_CON_GAT_GATE_CLKCMU_DISP_BUS		0x2070
+#define CLK_CON_GAT_GATE_CLKCMU_DNS_BUS			0x2074
+#define CLK_CON_GAT_GATE_CLKCMU_DPU_BUS			0x2078
+#define CLK_CON_GAT_GATE_CLKCMU_EH_BUS			0x207c
+#define CLK_CON_GAT_GATE_CLKCMU_G2D_G2D			0x2080
+#define CLK_CON_GAT_GATE_CLKCMU_G2D_MSCL		0x2084
+#define CLK_CON_GAT_GATE_CLKCMU_G3AA_G3AA		0x2088
+#define CLK_CON_GAT_GATE_CLKCMU_G3D_BUSD		0x208c
+#define CLK_CON_GAT_GATE_CLKCMU_G3D_GLB			0x2090
+#define CLK_CON_GAT_GATE_CLKCMU_G3D_SWITCH		0x2094
+#define CLK_CON_GAT_GATE_CLKCMU_GDC_GDC0		0x2098
+#define CLK_CON_GAT_GATE_CLKCMU_GDC_GDC1		0x209c
+#define CLK_CON_GAT_GATE_CLKCMU_GDC_SCSC		0x20a0
+#define CLK_CON_GAT_GATE_CLKCMU_HPM			0x20a4
+#define CLK_CON_GAT_GATE_CLKCMU_HSI0_BUS		0x20a8
+#define CLK_CON_GAT_GATE_CLKCMU_HSI0_DPGTC		0x20ac
+#define CLK_CON_GAT_GATE_CLKCMU_HSI0_USB31DRD		0x20b0
+#define CLK_CON_GAT_GATE_CLKCMU_HSI0_USBDPDBG		0x20b4
+#define CLK_CON_GAT_GATE_CLKCMU_HSI1_BUS		0x20b8
+#define CLK_CON_GAT_GATE_CLKCMU_HSI1_PCIE		0x20bc
+#define CLK_CON_GAT_GATE_CLKCMU_HSI2_BUS		0x20c0
+#define CLK_CON_GAT_GATE_CLKCMU_HSI2_MMCCARD		0x20c4
+#define CLK_CON_GAT_GATE_CLKCMU_HSI2_PCIE		0x20c8
+#define CLK_CON_GAT_GATE_CLKCMU_HSI2_UFS_EMBD		0x20cc
+#define CLK_CON_GAT_GATE_CLKCMU_IPP_BUS			0x20d0
+#define CLK_CON_GAT_GATE_CLKCMU_ITP_BUS			0x20d4
+#define CLK_CON_GAT_GATE_CLKCMU_MCSC_ITSC		0x20d8
+#define CLK_CON_GAT_GATE_CLKCMU_MCSC_MCSC		0x20dc
+#define CLK_CON_GAT_GATE_CLKCMU_MFC_MFC			0x20e0
+#define CLK_CON_GAT_GATE_CLKCMU_MIF_BUSP		0x20e4
+#define CLK_CON_GAT_GATE_CLKCMU_MISC_BUS		0x20e8
+#define CLK_CON_GAT_GATE_CLKCMU_MISC_SSS		0x20ec
+#define CLK_CON_GAT_GATE_CLKCMU_PDP_BUS			0x20f0
+#define CLK_CON_GAT_GATE_CLKCMU_PDP_VRA			0x20f4
+#define CLK_CON_GAT_GATE_CLKCMU_PERIC0_BUS		0x20f8
+#define CLK_CON_GAT_GATE_CLKCMU_PERIC0_IP		0x20fc
+#define CLK_CON_GAT_GATE_CLKCMU_PERIC1_BUS		0x2100
+#define CLK_CON_GAT_GATE_CLKCMU_PERIC1_IP		0x2104
+#define CLK_CON_GAT_GATE_CLKCMU_TNR_BUS			0x2108
+#define CLK_CON_GAT_GATE_CLKCMU_TOP_CMUREF		0x210c
+#define CLK_CON_GAT_GATE_CLKCMU_TPU_BUS			0x2110
+#define CLK_CON_GAT_GATE_CLKCMU_TPU_TPU			0x2114
+#define CLK_CON_GAT_GATE_CLKCMU_TPU_TPUCTL		0x2118
+#define CLK_CON_GAT_GATE_CLKCMU_TPU_UART		0x211c
+#define DMYQCH_CON_CMU_TOP_CMUREF_QCH			0x3000
+#define DMYQCH_CON_DFTMUX_CMU_QCH_CIS_CLK0		0x3004
+#define DMYQCH_CON_DFTMUX_CMU_QCH_CIS_CLK1		0x3008
+#define DMYQCH_CON_DFTMUX_CMU_QCH_CIS_CLK2		0x300c
+#define DMYQCH_CON_DFTMUX_CMU_QCH_CIS_CLK3		0x3010
+#define DMYQCH_CON_DFTMUX_CMU_QCH_CIS_CLK4		0x3014
+#define DMYQCH_CON_DFTMUX_CMU_QCH_CIS_CLK5		0x3018
+#define DMYQCH_CON_DFTMUX_CMU_QCH_CIS_CLK6		0x301c
+#define DMYQCH_CON_DFTMUX_CMU_QCH_CIS_CLK7		0x3020
+#define DMYQCH_CON_OTP_QCH				0x3024
+#define QUEUE_CTRL_REG_BLK_CMU_CMU_TOP			0x3c00
+#define QUEUE_ENTRY0_BLK_CMU_CMU_TOP			0x3c10
+#define QUEUE_ENTRY1_BLK_CMU_CMU_TOP			0x3c14
+#define QUEUE_ENTRY2_BLK_CMU_CMU_TOP			0x3c18
+#define QUEUE_ENTRY3_BLK_CMU_CMU_TOP			0x3c1c
+#define QUEUE_ENTRY4_BLK_CMU_CMU_TOP			0x3c20
+#define QUEUE_ENTRY5_BLK_CMU_CMU_TOP			0x3c24
+#define QUEUE_ENTRY6_BLK_CMU_CMU_TOP			0x3c28
+#define QUEUE_ENTRY7_BLK_CMU_CMU_TOP			0x3c2c
+#define MIFMIRROR_QUEUE_CTRL_REG			0x3e00
+#define MIFMIRROR_QUEUE_ENTRY0				0x3e10
+#define MIFMIRROR_QUEUE_ENTRY1				0x3e14
+#define MIFMIRROR_QUEUE_ENTRY2				0x3e18
+#define MIFMIRROR_QUEUE_ENTRY3				0x3e1c
+#define MIFMIRROR_QUEUE_ENTRY4				0x3e20
+#define MIFMIRROR_QUEUE_ENTRY5				0x3e24
+#define MIFMIRROR_QUEUE_ENTRY6				0x3e28
+#define MIFMIRROR_QUEUE_ENTRY7				0x3e2c
+#define MIFMIRROR_QUEUE_BUSY				0x3e30
+#define GENERALIO_ACD_CHANNEL_0				0x3f00
+#define GENERALIO_ACD_CHANNEL_1				0x3f04
+#define GENERALIO_ACD_CHANNEL_2				0x3f08
+#define GENERALIO_ACD_CHANNEL_3				0x3f0c
+#define GENERALIO_ACD_MASK				0x3f14
+
+static const unsigned long cmu_top_clk_regs[] __initconst = {
+	PLL_LOCKTIME_PLL_SHARED0,
+	PLL_LOCKTIME_PLL_SHARED1,
+	PLL_LOCKTIME_PLL_SHARED2,
+	PLL_LOCKTIME_PLL_SHARED3,
+	PLL_LOCKTIME_PLL_SPARE,
+	PLL_CON0_PLL_SHARED0,
+	PLL_CON1_PLL_SHARED0,
+	PLL_CON2_PLL_SHARED0,
+	PLL_CON3_PLL_SHARED0,
+	PLL_CON4_PLL_SHARED0,
+	PLL_CON0_PLL_SHARED1,
+	PLL_CON1_PLL_SHARED1,
+	PLL_CON2_PLL_SHARED1,
+	PLL_CON3_PLL_SHARED1,
+	PLL_CON4_PLL_SHARED1,
+	PLL_CON0_PLL_SHARED2,
+	PLL_CON1_PLL_SHARED2,
+	PLL_CON2_PLL_SHARED2,
+	PLL_CON3_PLL_SHARED2,
+	PLL_CON4_PLL_SHARED2,
+	PLL_CON0_PLL_SHARED3,
+	PLL_CON1_PLL_SHARED3,
+	PLL_CON2_PLL_SHARED3,
+	PLL_CON3_PLL_SHARED3,
+	PLL_CON4_PLL_SHARED3,
+	PLL_CON0_PLL_SPARE,
+	PLL_CON1_PLL_SPARE,
+	PLL_CON2_PLL_SPARE,
+	PLL_CON3_PLL_SPARE,
+	PLL_CON4_PLL_SPARE,
+	CMU_CMU_TOP_CONTROLLER_OPTION,
+	CLKOUT_CON_BLK_CMU_CMU_TOP_CLKOUT0,
+	CMU_HCHGEN_CLKMUX_CMU_BOOST,
+	CMU_HCHGEN_CLKMUX_TOP_BOOST,
+	CMU_HCHGEN_CLKMUX,
+	POWER_FAIL_DETECT_PLL,
+	EARLY_WAKEUP_FORCED_0_ENABLE,
+	EARLY_WAKEUP_FORCED_1_ENABLE,
+	EARLY_WAKEUP_APM_CTRL,
+	EARLY_WAKEUP_CLUSTER0_CTRL,
+	EARLY_WAKEUP_DPU_CTRL,
+	EARLY_WAKEUP_CSIS_CTRL,
+	EARLY_WAKEUP_APM_DEST,
+	EARLY_WAKEUP_CLUSTER0_DEST,
+	EARLY_WAKEUP_DPU_DEST,
+	EARLY_WAKEUP_CSIS_DEST,
+	EARLY_WAKEUP_SW_TRIG_APM,
+	EARLY_WAKEUP_SW_TRIG_APM_SET,
+	EARLY_WAKEUP_SW_TRIG_APM_CLEAR,
+	EARLY_WAKEUP_SW_TRIG_CLUSTER0,
+	EARLY_WAKEUP_SW_TRIG_CLUSTER0_SET,
+	EARLY_WAKEUP_SW_TRIG_CLUSTER0_CLEAR,
+	EARLY_WAKEUP_SW_TRIG_DPU,
+	EARLY_WAKEUP_SW_TRIG_DPU_SET,
+	EARLY_WAKEUP_SW_TRIG_DPU_CLEAR,
+	EARLY_WAKEUP_SW_TRIG_CSIS,
+	EARLY_WAKEUP_SW_TRIG_CSIS_SET,
+	EARLY_WAKEUP_SW_TRIG_CSIS_CLEAR,
+	CLK_CON_MUX_MUX_CLKCMU_BO_BUS,
+	CLK_CON_MUX_MUX_CLKCMU_BUS0_BUS,
+	CLK_CON_MUX_MUX_CLKCMU_BUS1_BUS,
+	CLK_CON_MUX_MUX_CLKCMU_BUS2_BUS,
+	CLK_CON_MUX_MUX_CLKCMU_CIS_CLK0,
+	CLK_CON_MUX_MUX_CLKCMU_CIS_CLK1,
+	CLK_CON_MUX_MUX_CLKCMU_CIS_CLK2,
+	CLK_CON_MUX_MUX_CLKCMU_CIS_CLK3,
+	CLK_CON_MUX_MUX_CLKCMU_CIS_CLK4,
+	CLK_CON_MUX_MUX_CLKCMU_CIS_CLK5,
+	CLK_CON_MUX_MUX_CLKCMU_CIS_CLK6,
+	CLK_CON_MUX_MUX_CLKCMU_CIS_CLK7,
+	CLK_CON_MUX_MUX_CLKCMU_CMU_BOOST,
+	CLK_CON_MUX_MUX_CLKCMU_CMU_BOOST_OPTION1,
+	CLK_CON_MUX_MUX_CLKCMU_CORE_BUS,
+	CLK_CON_MUX_MUX_CLKCMU_CPUCL0_DBG,
+	CLK_CON_MUX_MUX_CLKCMU_CPUCL0_SWITCH,
+	CLK_CON_MUX_MUX_CLKCMU_CPUCL1_SWITCH,
+	CLK_CON_MUX_MUX_CLKCMU_CPUCL2_SWITCH,
+	CLK_CON_MUX_MUX_CLKCMU_CSIS_BUS,
+	CLK_CON_MUX_MUX_CLKCMU_DISP_BUS,
+	CLK_CON_MUX_MUX_CLKCMU_DNS_BUS,
+	CLK_CON_MUX_MUX_CLKCMU_DPU_BUS,
+	CLK_CON_MUX_MUX_CLKCMU_EH_BUS,
+	CLK_CON_MUX_MUX_CLKCMU_G2D_G2D,
+	CLK_CON_MUX_MUX_CLKCMU_G2D_MSCL,
+	CLK_CON_MUX_MUX_CLKCMU_G3AA_G3AA,
+	CLK_CON_MUX_MUX_CLKCMU_G3D_BUSD,
+	CLK_CON_MUX_MUX_CLKCMU_G3D_GLB,
+	CLK_CON_MUX_MUX_CLKCMU_G3D_SWITCH,
+	CLK_CON_MUX_MUX_CLKCMU_GDC_GDC0,
+	CLK_CON_MUX_MUX_CLKCMU_GDC_GDC1,
+	CLK_CON_MUX_MUX_CLKCMU_GDC_SCSC,
+	CLK_CON_MUX_MUX_CLKCMU_HPM,
+	CLK_CON_MUX_MUX_CLKCMU_HSI0_BUS,
+	CLK_CON_MUX_MUX_CLKCMU_HSI0_DPGTC,
+	CLK_CON_MUX_MUX_CLKCMU_HSI0_USB31DRD,
+	CLK_CON_MUX_MUX_CLKCMU_HSI0_USBDPDBG,
+	CLK_CON_MUX_MUX_CLKCMU_HSI1_BUS,
+	CLK_CON_MUX_MUX_CLKCMU_HSI1_PCIE,
+	CLK_CON_MUX_MUX_CLKCMU_HSI2_BUS,
+	CLK_CON_MUX_MUX_CLKCMU_HSI2_MMC_CARD,
+	CLK_CON_MUX_MUX_CLKCMU_HSI2_PCIE,
+	CLK_CON_MUX_MUX_CLKCMU_HSI2_UFS_EMBD,
+	CLK_CON_MUX_MUX_CLKCMU_IPP_BUS,
+	CLK_CON_MUX_MUX_CLKCMU_ITP_BUS,
+	CLK_CON_MUX_MUX_CLKCMU_MCSC_ITSC,
+	CLK_CON_MUX_MUX_CLKCMU_MCSC_MCSC,
+	CLK_CON_MUX_MUX_CLKCMU_MFC_MFC,
+	CLK_CON_MUX_MUX_CLKCMU_MIF_BUSP,
+	CLK_CON_MUX_MUX_CLKCMU_MIF_SWITCH,
+	CLK_CON_MUX_MUX_CLKCMU_MISC_BUS,
+	CLK_CON_MUX_MUX_CLKCMU_MISC_SSS,
+	CLK_CON_MUX_MUX_CLKCMU_PDP_BUS,
+	CLK_CON_MUX_MUX_CLKCMU_PDP_VRA,
+	CLK_CON_MUX_MUX_CLKCMU_PERIC0_BUS,
+	CLK_CON_MUX_MUX_CLKCMU_PERIC0_IP,
+	CLK_CON_MUX_MUX_CLKCMU_PERIC1_BUS,
+	CLK_CON_MUX_MUX_CLKCMU_PERIC1_IP,
+	CLK_CON_MUX_MUX_CLKCMU_TNR_BUS,
+	CLK_CON_MUX_MUX_CLKCMU_TOP_BOOST_OPTION1,
+	CLK_CON_MUX_MUX_CLKCMU_TOP_CMUREF,
+	CLK_CON_MUX_MUX_CLKCMU_TPU_BUS,
+	CLK_CON_MUX_MUX_CLKCMU_TPU_TPU,
+	CLK_CON_MUX_MUX_CLKCMU_TPU_TPUCTL,
+	CLK_CON_MUX_MUX_CLKCMU_TPU_UART,
+	CLK_CON_MUX_MUX_CMU_CMUREF,
+	CLK_CON_DIV_CLKCMU_BO_BUS,
+	CLK_CON_DIV_CLKCMU_BUS0_BUS,
+	CLK_CON_DIV_CLKCMU_BUS1_BUS,
+	CLK_CON_DIV_CLKCMU_BUS2_BUS,
+	CLK_CON_DIV_CLKCMU_CIS_CLK0,
+	CLK_CON_DIV_CLKCMU_CIS_CLK1,
+	CLK_CON_DIV_CLKCMU_CIS_CLK2,
+	CLK_CON_DIV_CLKCMU_CIS_CLK3,
+	CLK_CON_DIV_CLKCMU_CIS_CLK4,
+	CLK_CON_DIV_CLKCMU_CIS_CLK5,
+	CLK_CON_DIV_CLKCMU_CIS_CLK6,
+	CLK_CON_DIV_CLKCMU_CIS_CLK7,
+	CLK_CON_DIV_CLKCMU_CORE_BUS,
+	CLK_CON_DIV_CLKCMU_CPUCL0_DBG,
+	CLK_CON_DIV_CLKCMU_CPUCL0_SWITCH,
+	CLK_CON_DIV_CLKCMU_CPUCL1_SWITCH,
+	CLK_CON_DIV_CLKCMU_CPUCL2_SWITCH,
+	CLK_CON_DIV_CLKCMU_CSIS_BUS,
+	CLK_CON_DIV_CLKCMU_DISP_BUS,
+	CLK_CON_DIV_CLKCMU_DNS_BUS,
+	CLK_CON_DIV_CLKCMU_DPU_BUS,
+	CLK_CON_DIV_CLKCMU_EH_BUS,
+	CLK_CON_DIV_CLKCMU_G2D_G2D,
+	CLK_CON_DIV_CLKCMU_G2D_MSCL,
+	CLK_CON_DIV_CLKCMU_G3AA_G3AA,
+	CLK_CON_DIV_CLKCMU_G3D_BUSD,
+	CLK_CON_DIV_CLKCMU_G3D_GLB,
+	CLK_CON_DIV_CLKCMU_G3D_SWITCH,
+	CLK_CON_DIV_CLKCMU_GDC_GDC0,
+	CLK_CON_DIV_CLKCMU_GDC_GDC1,
+	CLK_CON_DIV_CLKCMU_GDC_SCSC,
+	CLK_CON_DIV_CLKCMU_HPM,
+	CLK_CON_DIV_CLKCMU_HSI0_BUS,
+	CLK_CON_DIV_CLKCMU_HSI0_DPGTC,
+	CLK_CON_DIV_CLKCMU_HSI0_USB31DRD,
+	CLK_CON_DIV_CLKCMU_HSI0_USBDPDBG,
+	CLK_CON_DIV_CLKCMU_HSI1_BUS,
+	CLK_CON_DIV_CLKCMU_HSI1_PCIE,
+	CLK_CON_DIV_CLKCMU_HSI2_BUS,
+	CLK_CON_DIV_CLKCMU_HSI2_MMC_CARD,
+	CLK_CON_DIV_CLKCMU_HSI2_PCIE,
+	CLK_CON_DIV_CLKCMU_HSI2_UFS_EMBD,
+	CLK_CON_DIV_CLKCMU_IPP_BUS,
+	CLK_CON_DIV_CLKCMU_ITP_BUS,
+	CLK_CON_DIV_CLKCMU_MCSC_ITSC,
+	CLK_CON_DIV_CLKCMU_MCSC_MCSC,
+	CLK_CON_DIV_CLKCMU_MFC_MFC,
+	CLK_CON_DIV_CLKCMU_MIF_BUSP,
+	CLK_CON_DIV_CLKCMU_MISC_BUS,
+	CLK_CON_DIV_CLKCMU_MISC_SSS,
+	CLK_CON_DIV_CLKCMU_OTP,
+	CLK_CON_DIV_CLKCMU_PDP_BUS,
+	CLK_CON_DIV_CLKCMU_PDP_VRA,
+	CLK_CON_DIV_CLKCMU_PERIC0_BUS,
+	CLK_CON_DIV_CLKCMU_PERIC0_IP,
+	CLK_CON_DIV_CLKCMU_PERIC1_BUS,
+	CLK_CON_DIV_CLKCMU_PERIC1_IP,
+	CLK_CON_DIV_CLKCMU_TNR_BUS,
+	CLK_CON_DIV_CLKCMU_TPU_BUS,
+	CLK_CON_DIV_CLKCMU_TPU_TPU,
+	CLK_CON_DIV_CLKCMU_TPU_TPUCTL,
+	CLK_CON_DIV_CLKCMU_TPU_UART,
+	CLK_CON_DIV_DIV_CLKCMU_CMU_BOOST,
+	CLK_CON_DIV_DIV_CLK_CMU_CMUREF,
+	CLK_CON_DIV_PLL_SHARED0_DIV2,
+	CLK_CON_DIV_PLL_SHARED0_DIV3,
+	CLK_CON_DIV_PLL_SHARED0_DIV4,
+	CLK_CON_DIV_PLL_SHARED0_DIV5,
+	CLK_CON_DIV_PLL_SHARED1_DIV2,
+	CLK_CON_DIV_PLL_SHARED1_DIV3,
+	CLK_CON_DIV_PLL_SHARED1_DIV4,
+	CLK_CON_DIV_PLL_SHARED2_DIV2,
+	CLK_CON_DIV_PLL_SHARED3_DIV2,
+	CLK_CON_GAT_CLKCMU_BUS0_BOOST,
+	CLK_CON_GAT_CLKCMU_BUS1_BOOST,
+	CLK_CON_GAT_CLKCMU_BUS2_BOOST,
+	CLK_CON_GAT_CLKCMU_CORE_BOOST,
+	CLK_CON_GAT_CLKCMU_CPUCL0_BOOST,
+	CLK_CON_GAT_CLKCMU_CPUCL1_BOOST,
+	CLK_CON_GAT_CLKCMU_CPUCL2_BOOST,
+	CLK_CON_GAT_CLKCMU_MIF_BOOST,
+	CLK_CON_GAT_CLKCMU_MIF_SWITCH,
+	CLK_CON_GAT_GATE_CLKCMU_BO_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_BUS0_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_BUS1_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_BUS2_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_CIS_CLK0,
+	CLK_CON_GAT_GATE_CLKCMU_CIS_CLK1,
+	CLK_CON_GAT_GATE_CLKCMU_CIS_CLK2,
+	CLK_CON_GAT_GATE_CLKCMU_CIS_CLK3,
+	CLK_CON_GAT_GATE_CLKCMU_CIS_CLK4,
+	CLK_CON_GAT_GATE_CLKCMU_CIS_CLK5,
+	CLK_CON_GAT_GATE_CLKCMU_CIS_CLK6,
+	CLK_CON_GAT_GATE_CLKCMU_CIS_CLK7,
+	CLK_CON_GAT_GATE_CLKCMU_CMU_BOOST,
+	CLK_CON_GAT_GATE_CLKCMU_CORE_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_CPUCL0_DBG_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_CPUCL0_SWITCH,
+	CLK_CON_GAT_GATE_CLKCMU_CPUCL1_SWITCH,
+	CLK_CON_GAT_GATE_CLKCMU_CPUCL2_SWITCH,
+	CLK_CON_GAT_GATE_CLKCMU_CSIS_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_DISP_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_DNS_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_DPU_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_EH_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_G2D_G2D,
+	CLK_CON_GAT_GATE_CLKCMU_G2D_MSCL,
+	CLK_CON_GAT_GATE_CLKCMU_G3AA_G3AA,
+	CLK_CON_GAT_GATE_CLKCMU_G3D_BUSD,
+	CLK_CON_GAT_GATE_CLKCMU_G3D_GLB,
+	CLK_CON_GAT_GATE_CLKCMU_G3D_SWITCH,
+	CLK_CON_GAT_GATE_CLKCMU_GDC_GDC0,
+	CLK_CON_GAT_GATE_CLKCMU_GDC_GDC1,
+	CLK_CON_GAT_GATE_CLKCMU_GDC_SCSC,
+	CLK_CON_GAT_GATE_CLKCMU_HPM,
+	CLK_CON_GAT_GATE_CLKCMU_HSI0_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_HSI0_DPGTC,
+	CLK_CON_GAT_GATE_CLKCMU_HSI0_USB31DRD,
+	CLK_CON_GAT_GATE_CLKCMU_HSI0_USBDPDBG,
+	CLK_CON_GAT_GATE_CLKCMU_HSI1_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_HSI1_PCIE,
+	CLK_CON_GAT_GATE_CLKCMU_HSI2_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_HSI2_MMCCARD,
+	CLK_CON_GAT_GATE_CLKCMU_HSI2_PCIE,
+	CLK_CON_GAT_GATE_CLKCMU_HSI2_UFS_EMBD,
+	CLK_CON_GAT_GATE_CLKCMU_IPP_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_ITP_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_MCSC_ITSC,
+	CLK_CON_GAT_GATE_CLKCMU_MCSC_MCSC,
+	CLK_CON_GAT_GATE_CLKCMU_MFC_MFC,
+	CLK_CON_GAT_GATE_CLKCMU_MIF_BUSP,
+	CLK_CON_GAT_GATE_CLKCMU_MISC_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_MISC_SSS,
+	CLK_CON_GAT_GATE_CLKCMU_PDP_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_PDP_VRA,
+	CLK_CON_GAT_GATE_CLKCMU_PERIC0_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_PERIC0_IP,
+	CLK_CON_GAT_GATE_CLKCMU_PERIC1_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_PERIC1_IP,
+	CLK_CON_GAT_GATE_CLKCMU_TNR_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_TOP_CMUREF,
+	CLK_CON_GAT_GATE_CLKCMU_TPU_BUS,
+	CLK_CON_GAT_GATE_CLKCMU_TPU_TPU,
+	CLK_CON_GAT_GATE_CLKCMU_TPU_TPUCTL,
+	CLK_CON_GAT_GATE_CLKCMU_TPU_UART,
+	DMYQCH_CON_CMU_TOP_CMUREF_QCH,
+	DMYQCH_CON_DFTMUX_CMU_QCH_CIS_CLK0,
+	DMYQCH_CON_DFTMUX_CMU_QCH_CIS_CLK1,
+	DMYQCH_CON_DFTMUX_CMU_QCH_CIS_CLK2,
+	DMYQCH_CON_DFTMUX_CMU_QCH_CIS_CLK3,
+	DMYQCH_CON_DFTMUX_CMU_QCH_CIS_CLK4,
+	DMYQCH_CON_DFTMUX_CMU_QCH_CIS_CLK5,
+	DMYQCH_CON_DFTMUX_CMU_QCH_CIS_CLK6,
+	DMYQCH_CON_DFTMUX_CMU_QCH_CIS_CLK7,
+	DMYQCH_CON_OTP_QCH,
+	QUEUE_CTRL_REG_BLK_CMU_CMU_TOP,
+	QUEUE_ENTRY0_BLK_CMU_CMU_TOP,
+	QUEUE_ENTRY1_BLK_CMU_CMU_TOP,
+	QUEUE_ENTRY2_BLK_CMU_CMU_TOP,
+	QUEUE_ENTRY3_BLK_CMU_CMU_TOP,
+	QUEUE_ENTRY4_BLK_CMU_CMU_TOP,
+	QUEUE_ENTRY5_BLK_CMU_CMU_TOP,
+	QUEUE_ENTRY6_BLK_CMU_CMU_TOP,
+	QUEUE_ENTRY7_BLK_CMU_CMU_TOP,
+	MIFMIRROR_QUEUE_CTRL_REG,
+	MIFMIRROR_QUEUE_ENTRY0,
+	MIFMIRROR_QUEUE_ENTRY1,
+	MIFMIRROR_QUEUE_ENTRY2,
+	MIFMIRROR_QUEUE_ENTRY3,
+	MIFMIRROR_QUEUE_ENTRY4,
+	MIFMIRROR_QUEUE_ENTRY5,
+	MIFMIRROR_QUEUE_ENTRY6,
+	MIFMIRROR_QUEUE_ENTRY7,
+	MIFMIRROR_QUEUE_BUSY,
+	GENERALIO_ACD_CHANNEL_0,
+	GENERALIO_ACD_CHANNEL_1,
+	GENERALIO_ACD_CHANNEL_2,
+	GENERALIO_ACD_CHANNEL_3,
+	GENERALIO_ACD_MASK,
+};
+
+static const struct samsung_pll_clock cmu_top_pll_clks[] __initconst = {
+	/* CMU_TOP_PURECLKCOMP */
+	PLL(pll_0517x, CLK_FOUT_SHARED0_PLL, "fout_shared0_pll", "oscclk",
+	    PLL_LOCKTIME_PLL_SHARED0, PLL_CON3_PLL_SHARED0,
+	    NULL),
+	PLL(pll_0517x, CLK_FOUT_SHARED1_PLL, "fout_shared1_pll", "oscclk",
+	    PLL_LOCKTIME_PLL_SHARED1, PLL_CON3_PLL_SHARED1,
+	    NULL),
+	PLL(pll_0518x, CLK_FOUT_SHARED2_PLL, "fout_shared2_pll", "oscclk",
+	    PLL_LOCKTIME_PLL_SHARED2, PLL_CON3_PLL_SHARED2,
+	    NULL),
+	PLL(pll_0518x, CLK_FOUT_SHARED3_PLL, "fout_shared3_pll", "oscclk",
+	    PLL_LOCKTIME_PLL_SHARED3, PLL_CON3_PLL_SHARED3,
+	    NULL),
+	PLL(pll_0518x, CLK_FOUT_SPARE_PLL, "fout_spare_pll", "oscclk",
+	    PLL_LOCKTIME_PLL_SPARE, PLL_CON3_PLL_SPARE,
+	    NULL),
+};
+
+/* List of parent clocks for Muxes in CMU_TOP */
+PNAME(mout_pll_shared0_p)	= { "oscclk", "fout_shared0_pll" };
+PNAME(mout_pll_shared1_p)	= { "oscclk", "fout_shared1_pll" };
+PNAME(mout_pll_shared2_p)	= { "oscclk", "fout_shared2_pll" };
+PNAME(mout_pll_shared3_p)	= { "oscclk", "fout_shared3_pll" };
+PNAME(mout_pll_spare_p)		= { "oscclk", "fout_spare_pll" };
+PNAME(mout_cmu_bo_bus_p)	= { "fout_shared2_pll", "dout_cmu_shared0_div3",
+				    "fout_shared3_pll", "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "fout_spare_pll", "oscclk" };
+PNAME(mout_cmu_bus0_bus_p)	= { "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "dout_cmu_shared3_div2",
+				    "fout_spare_pll", "oscclk",
+				    "oscclk", "oscclk" };
+PNAME(mout_cmu_bus1_bus_p)	= { "dout_cmu_shared0_div3", "fout_shared3_pll",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "fout_spare_pll", "oscclk" };
+PNAME(mout_cmu_bus2_bus_p)	= { "dout_cmu_shared0_div2",
+				    "dout_cmu_shared1_div2",
+				    "fout_shared2_pll", "fout_shared3_pll",
+				    "dout_cmu_shared0_div3",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div5", "fout_spare_pll" };
+PNAME(mout_cmu_cis_clk0_7_p)	= { "oscclk", "dout_cmu_shared0_div3",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared2_div2",
+				    "dout_cmu_shared3_div2", "fout_spare_pll",
+				    "oscclk", "oscclk" };
+PNAME(mout_cmu_cmu_boost_p)	= { "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "dout_cmu_shared3_div2" };
+PNAME(mout_cmu_cmu_boost_option1_p) = { "dout_cmu_cmu_boost",
+					"gout_cmu_boost_option1" };
+PNAME(mout_cmu_core_bus_p)	= { "dout_cmu_shared0_div2",
+				    "dout_cmu_shared1_div2",
+				    "fout_shared2_pll", "fout_shared3_pll",
+				    "dout_cmu_shared0_div3",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div5", "fout_spare_pll" };
+PNAME(mout_cmu_cpucl0_dbg_p)	= { "fout_shared2_pll", "fout_shared3_pll",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2", "fout_spare_pll",
+				    "oscclk", "oscclk" };
+PNAME(mout_cmu_cpucl0_switch_p)	= { "fout_shared1_pll", "dout_cmu_shared0_div2",
+				    "dout_cmu_shared1_div2", "fout_shared2_pll",
+				    "fout_shared3_pll", "dout_cmu_shared0_div3",
+				    "dout_cmu_shared1_div3", "fout_spare_pll" };
+PNAME(mout_cmu_cpucl1_switch_p)	= { "fout_shared1_pll", "dout_cmu_shared0_div2",
+				    "dout_cmu_shared1_div2", "fout_shared2_pll",
+				    "fout_shared3_pll", "dout_cmu_shared0_div3",
+				    "dout_cmu_shared1_div3", "fout_spare_pll" };
+PNAME(mout_cmu_cpucl2_switch_p)	= { "fout_shared1_pll", "dout_cmu_shared0_div2",
+				    "dout_cmu_shared1_div2", "fout_shared2_pll",
+				    "fout_shared3_pll", "dout_cmu_shared0_div3",
+				    "dout_cmu_shared1_div3", "fout_spare_pll" };
+PNAME(mout_cmu_csis_bus_p)	= { "dout_cmu_shared0_div3", "fout_shared3_pll",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "fout_spare_pll", "oscclk" };
+PNAME(mout_cmu_disp_bus_p)	= { "dout_cmu_shared0_div3", "fout_shared3_pll",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "fout_spare_pll", "oscclk" };
+PNAME(mout_cmu_dns_bus_p)	= { "dout_cmu_shared0_div3", "fout_shared3_pll",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "fout_spare_pll", "oscclk" };
+PNAME(mout_cmu_dpu_p)		= { "dout_cmu_shared0_div3",
+				    "fout_shared3_pll",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "fout_spare_pll", "oscclk" };
+PNAME(mout_cmu_eh_bus_p)	= { "dout_cmu_shared0_div2",
+				    "dout_cmu_shared1_div2",
+				    "fout_shared2_pll", "fout_shared3_pll",
+				    "dout_cmu_shared0_div3",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div5", "fout_spare_pll" };
+PNAME(mout_cmu_g2d_g2d_p)	= { "dout_cmu_shared0_div3", "fout_shared3_pll",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "fout_spare_pll", "oscclk" };
+PNAME(mout_cmu_g2d_mscl_p)	= { "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "dout_cmu_shared3_div2",
+				    "fout_spare_pll", "oscclk",
+				    "oscclk", "oscclk" };
+PNAME(mout_cmu_g3aa_g3aa_p)	= { "dout_cmu_shared0_div3", "fout_shared3_pll",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "fout_spare_pll", "oscclk" };
+PNAME(mout_cmu_g3d_busd_p)	= { "dout_cmu_shared0_div2",
+				    "dout_cmu_shared1_div2",
+				    "fout_shared2_pll", "fout_shared3_pll",
+				    "dout_cmu_shared0_div3",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4", "fout_spare_pll" };
+PNAME(mout_cmu_g3d_glb_p)	= { "dout_cmu_shared0_div2",
+				    "dout_cmu_shared1_div2",
+				    "fout_shared2_pll", "fout_shared3_pll",
+				    "dout_cmu_shared0_div3",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4", "fout_spare_pll" };
+PNAME(mout_cmu_g3d_switch_p)	= { "fout_shared2_pll", "dout_cmu_shared0_div3",
+				    "fout_shared3_pll", "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "fout_spare_pll", "fout_spare_pll"};
+PNAME(mout_cmu_gdc_gdc0_p)	= { "dout_cmu_shared0_div3", "fout_shared3_pll",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "fout_spare_pll", "oscclk" };
+PNAME(mout_cmu_gdc_gdc1_p)	= { "dout_cmu_shared0_div3", "fout_shared3_pll",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "fout_spare_pll", "oscclk" };
+PNAME(mout_cmu_gdc_scsc_p)	= { "dout_cmu_shared0_div3", "fout_shared3_pll",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "fout_spare_pll", "oscclk" };
+PNAME(mout_cmu_hpm_p)		= { "oscclk", "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared2_div2" };
+PNAME(mout_cmu_hsi0_bus_p)	= { "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "dout_cmu_shared3_div2",
+				    "fout_spare_pll", "oscclk",
+				    "oscclk", "oscclk" };
+PNAME(mout_cmu_hsi0_dpgtc_p)	= { "oscclk", "dout_cmu_shared0_div4",
+				    "dout_cmu_shared2_div2", "fout_spare_pll" };
+PNAME(mout_cmu_hsi0_usb31drd_p)	= { "oscclk", "dout_cmu_shared2_div2" };
+PNAME(mout_cmu_hsi0_usbdpdbg_p)	= { "oscclk", "dout_cmu_shared2_div2" };
+PNAME(mout_cmu_hsi1_bus_p)	= { "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "dout_cmu_shared3_div2",
+				    "fout_spare_pll" };
+PNAME(mout_cmu_hsi1_pcie_p)	= { "oscclk", "dout_cmu_shared2_div2" };
+PNAME(mout_cmu_hsi2_bus_p)	= { "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "dout_cmu_shared3_div2",
+				    "fout_spare_pll", "oscclk",
+				    "oscclk", "oscclk" };
+PNAME(mout_cmu_hsi2_mmc_card_p)	= { "fout_shared2_pll", "fout_shared3_pll",
+				    "dout_cmu_shared0_div4", "fout_spare_pll" };
+PNAME(mout_cmu_hsi2_pcie0_p)	= { "oscclk", "dout_cmu_shared2_div2" };
+PNAME(mout_cmu_hsi2_ufs_embd_p)	= { "oscclk", "dout_cmu_shared0_div4",
+				    "dout_cmu_shared2_div2", "fout_spare_pll" };
+PNAME(mout_cmu_ipp_bus_p)	= { "dout_cmu_shared0_div3", "fout_shared3_pll",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "fout_spare_pll", "oscclk" };
+PNAME(mout_cmu_itp_bus_p)	= { "dout_cmu_shared0_div3", "fout_shared3_pll",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "fout_spare_pll", "oscclk" };
+PNAME(mout_cmu_mcsc_itsc_p)	= { "dout_cmu_shared0_div3", "fout_shared3_pll",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "fout_spare_pll", "oscclk" };
+PNAME(mout_cmu_mcsc_mcsc_p)	= { "dout_cmu_shared0_div3", "fout_shared3_pll",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "fout_spare_pll", "oscclk" };
+PNAME(mout_cmu_mfc_mfc_p)	= { "dout_cmu_shared0_div3", "fout_shared3_pll",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2", "fout_spare_pll",
+				    "oscclk", "oscclk" };
+PNAME(mout_cmu_mif_busp_p)	= { "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared0_div5", "fout_spare_pll" };
+PNAME(mout_cmu_mif_switch_p)	= { "fout_shared0_pll", "fout_shared1_pll",
+				    "dout_cmu_shared0_div2",
+				    "dout_cmu_shared1_div2",
+				    "fout_shared2_pll", "dout_cmu_shared0_div3",
+				    "fout_shared3_pll", "fout_spare_pll" };
+PNAME(mout_cmu_misc_bus_p)	= { "dout_cmu_shared0_div4",
+				    "dout_cmu_shared2_div2",
+				    "dout_cmu_shared3_div2", "fout_spare_pll" };
+PNAME(mout_cmu_misc_sss_p)	= { "dout_cmu_shared0_div4",
+				    "dout_cmu_shared2_div2",
+				    "dout_cmu_shared3_div2", "fout_spare_pll" };
+PNAME(mout_cmu_pdp_bus_p)	= { "dout_cmu_shared0_div3", "fout_shared3_pll",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "fout_spare_pll", "oscclk" };
+PNAME(mout_cmu_pdp_vra_p)	= { "fout_shared2_pll", "dout_cmu_shared0_div3",
+				    "fout_shared3_pll", "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "fout_spare_pll", "oscclk" };
+PNAME(mout_cmu_peric0_bus_p)	= { "dout_cmu_shared0_div4",
+				    "dout_cmu_shared2_div2",
+				    "dout_cmu_shared3_div2", "fout_spare_pll" };
+PNAME(mout_cmu_peric0_ip_p)	= { "dout_cmu_shared0_div4",
+				    "dout_cmu_shared2_div2",
+				    "dout_cmu_shared3_div2", "fout_spare_pll" };
+PNAME(mout_cmu_peric1_bus_p)	= { "dout_cmu_shared0_div4",
+				    "dout_cmu_shared2_div2",
+				    "dout_cmu_shared3_div2", "fout_spare_pll" };
+PNAME(mout_cmu_peric1_ip_p)	= { "dout_cmu_shared0_div4",
+				    "dout_cmu_shared2_div2",
+				    "dout_cmu_shared3_div2", "fout_spare_pll" };
+PNAME(mout_cmu_tnr_bus_p)	= { "dout_cmu_shared0_div3", "fout_shared3_pll",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "fout_spare_pll", "oscclk" };
+PNAME(mout_cmu_top_boost_option1_p) = { "oscclk",
+					"gout_cmu_boost_option1" };
+PNAME(mout_cmu_top_cmuref_p)	= { "dout_cmu_shared0_div4",
+				    "dout_cmu_shared1_div4",
+				    "dout_cmu_shared2_div2",
+				    "dout_cmu_shared3_div2" };
+PNAME(mout_cmu_tpu_bus_p)	= { "dout_cmu_shared0_div2",
+				    "dout_cmu_shared1_div2",
+				    "fout_shared2_pll",
+				    "fout_shared3_pll",
+				    "dout_cmu_shared0_div3",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4",
+				    "fout_spare_pll" };
+PNAME(mout_cmu_tpu_tpu_p)	= { "dout_cmu_shared0_div2",
+				    "dout_cmu_shared1_div2",
+				    "fout_shared2_pll",
+				    "fout_shared3_pll",
+				    "dout_cmu_shared0_div3",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4", "fout_spare_pll" };
+PNAME(mout_cmu_tpu_tpuctl_p)	= { "dout_cmu_shared0_div2",
+				    "dout_cmu_shared1_div2",
+				    "fout_shared2_pll", "fout_shared3_pll",
+				    "dout_cmu_shared0_div3",
+				    "dout_cmu_shared1_div3",
+				    "dout_cmu_shared0_div4", "fout_spare_pll" };
+PNAME(mout_cmu_tpu_uart_p)	= { "dout_cmu_shared0_div4",
+				    "dout_cmu_shared2_div2",
+				    "dout_cmu_shared3_div2", "fout_spare_pll" };
+PNAME(mout_cmu_cmuref_p)	= { "mout_cmu_top_boost_option1",
+				    "dout_cmu_cmuref" };
+
+/*
+ * Register name to clock name mangling strategy used in this file
+ *
+ * Replace PLL_CON0_PLL	           with CLK_MOUT_PLL and mout_pll
+ * Replace CLK_CON_MUX_MUX_CLKCMU  with CLK_MOUT_CMU and mout_cmu
+ * Replace CLK_CON_DIV_CLKCMU      with CLK_DOUT_CMU and dout_cmu
+ * Replace CLK_CON_DIV_DIV_CLKCMU  with CLK_DOUT_CMU and dout_cmu
+ * Replace CLK_CON_GAT_CLKCMU      with CLK_GOUT_CMU and gout_cmu
+ * Replace CLK_CON_GAT_GATE_CLKCMU with CLK_GOUT_CMU and gout_cmu
+ *
+ * For gates remove _UID _BLK _IPCLKPORT and _RSTNSYNC
+ */
+
+static const struct samsung_mux_clock cmu_top_mux_clks[] __initconst = {
+	MUX(CLK_MOUT_PLL_SHARED0, "mout_pll_shared0", mout_pll_shared0_p,
+	    PLL_CON0_PLL_SHARED0, 4, 1),
+	MUX(CLK_MOUT_PLL_SHARED1, "mout_pll_shared1", mout_pll_shared1_p,
+	    PLL_CON0_PLL_SHARED1, 4, 1),
+	MUX(CLK_MOUT_PLL_SHARED2, "mout_pll_shared2", mout_pll_shared2_p,
+	    PLL_CON0_PLL_SHARED2, 4, 1),
+	MUX(CLK_MOUT_PLL_SHARED3, "mout_pll_shared3", mout_pll_shared3_p,
+	    PLL_CON0_PLL_SHARED3, 4, 1),
+	MUX(CLK_MOUT_PLL_SPARE, "mout_pll_spare", mout_pll_spare_p,
+	    PLL_CON0_PLL_SPARE, 4, 1),
+	MUX(CLK_MOUT_CMU_BO_BUS, "mout_cmu_bo_bus", mout_cmu_bo_bus_p,
+	    CLK_CON_MUX_MUX_CLKCMU_BO_BUS, 0, 3),
+	MUX(CLK_MOUT_CMU_BUS0_BUS, "mout_cmu_bus0_bus", mout_cmu_bus0_bus_p,
+	    CLK_CON_MUX_MUX_CLKCMU_BUS0_BUS, 0, 3),
+	MUX(CLK_MOUT_CMU_BUS1_BUS, "mout_cmu_bus1_bus", mout_cmu_bus1_bus_p,
+	    CLK_CON_MUX_MUX_CLKCMU_BUS1_BUS, 0, 3),
+	MUX(CLK_MOUT_CMU_BUS2_BUS, "mout_cmu_bus2_bus", mout_cmu_bus2_bus_p,
+	    CLK_CON_MUX_MUX_CLKCMU_BUS2_BUS, 0, 3),
+	MUX(CLK_MOUT_CMU_CIS_CLK0, "mout_cmu_cis_clk0", mout_cmu_cis_clk0_7_p,
+	    CLK_CON_MUX_MUX_CLKCMU_CIS_CLK0, 0, 3),
+	MUX(CLK_MOUT_CMU_CIS_CLK1, "mout_cmu_cis_clk1", mout_cmu_cis_clk0_7_p,
+	    CLK_CON_MUX_MUX_CLKCMU_CIS_CLK1, 0, 3),
+	MUX(CLK_MOUT_CMU_CIS_CLK2, "mout_cmu_cis_clk2", mout_cmu_cis_clk0_7_p,
+	    CLK_CON_MUX_MUX_CLKCMU_CIS_CLK2, 0, 3),
+	MUX(CLK_MOUT_CMU_CIS_CLK3, "mout_cmu_cis_clk3", mout_cmu_cis_clk0_7_p,
+	    CLK_CON_MUX_MUX_CLKCMU_CIS_CLK3, 0, 3),
+	MUX(CLK_MOUT_CMU_CIS_CLK4, "mout_cmu_cis_clk4", mout_cmu_cis_clk0_7_p,
+	    CLK_CON_MUX_MUX_CLKCMU_CIS_CLK4, 0, 3),
+	MUX(CLK_MOUT_CMU_CIS_CLK5, "mout_cmu_cis_clk5", mout_cmu_cis_clk0_7_p,
+	    CLK_CON_MUX_MUX_CLKCMU_CIS_CLK5, 0, 3),
+	MUX(CLK_MOUT_CMU_CIS_CLK6, "mout_cmu_cis_clk6", mout_cmu_cis_clk0_7_p,
+	    CLK_CON_MUX_MUX_CLKCMU_CIS_CLK6, 0, 3),
+	MUX(CLK_MOUT_CMU_CIS_CLK7, "mout_cmu_cis_clk7", mout_cmu_cis_clk0_7_p,
+	    CLK_CON_MUX_MUX_CLKCMU_CIS_CLK7, 0, 3),
+	MUX(CLK_MOUT_CMU_CMU_BOOST, "mout_cmu_cmu_boost", mout_cmu_cmu_boost_p,
+	    CLK_CON_MUX_MUX_CLKCMU_CMU_BOOST, 0, 2),
+	MUX(CLK_MOUT_CMU_BOOST_OPTION1, "mout_cmu_boost_option1",
+	    mout_cmu_cmu_boost_option1_p,
+	    CLK_CON_MUX_MUX_CLKCMU_CMU_BOOST_OPTION1, 0, 1),
+	MUX(CLK_MOUT_CMU_CORE_BUS, "mout_cmu_core_bus", mout_cmu_core_bus_p,
+	    CLK_CON_MUX_MUX_CLKCMU_CORE_BUS, 0, 3),
+	MUX(CLK_MOUT_CMU_CPUCL0_DBG, "mout_cmu_cpucl0_dbg",
+	    mout_cmu_cpucl0_dbg_p, CLK_CON_DIV_CLKCMU_CPUCL0_DBG, 0, 3),
+	MUX(CLK_MOUT_CMU_CPUCL0_SWITCH, "mout_cmu_cpucl0_switch",
+	    mout_cmu_cpucl0_switch_p, CLK_CON_MUX_MUX_CLKCMU_CPUCL0_SWITCH,
+	    0, 3),
+	MUX(CLK_MOUT_CMU_CPUCL1_SWITCH, "mout_cmu_cpucl1_switch",
+	    mout_cmu_cpucl1_switch_p, CLK_CON_MUX_MUX_CLKCMU_CPUCL1_SWITCH,
+	    0, 3),
+	MUX(CLK_MOUT_CMU_CPUCL2_SWITCH, "mout_cmu_cpucl2_switch",
+	    mout_cmu_cpucl2_switch_p, CLK_CON_MUX_MUX_CLKCMU_CPUCL2_SWITCH,
+	    0, 3),
+	MUX(CLK_MOUT_CMU_CSIS_BUS, "mout_cmu_csis_bus", mout_cmu_csis_bus_p,
+	    CLK_CON_MUX_MUX_CLKCMU_CSIS_BUS, 0, 3),
+	MUX(CLK_MOUT_CMU_DISP_BUS, "mout_cmu_disp_bus", mout_cmu_disp_bus_p,
+	    CLK_CON_MUX_MUX_CLKCMU_DISP_BUS, 0, 3),
+	MUX(CLK_MOUT_CMU_DNS_BUS, "mout_cmu_dns_bus", mout_cmu_dns_bus_p,
+	    CLK_CON_MUX_MUX_CLKCMU_DNS_BUS, 0, 3),
+	MUX(CLK_MOUT_CMU_DPU_BUS, "mout_cmu_dpu_bus", mout_cmu_dpu_p,
+	    CLK_CON_MUX_MUX_CLKCMU_DPU_BUS, 0, 3),
+	MUX(CLK_MOUT_CMU_EH_BUS, "mout_cmu_eh_bus", mout_cmu_eh_bus_p,
+	    CLK_CON_MUX_MUX_CLKCMU_EH_BUS, 0, 3),
+	MUX(CLK_MOUT_CMU_G2D_G2D, "mout_cmu_g2d_g2d", mout_cmu_g2d_g2d_p,
+	    CLK_CON_MUX_MUX_CLKCMU_G2D_G2D, 0, 3),
+	MUX(CLK_MOUT_CMU_G2D_MSCL, "mout_cmu_g2d_mscl", mout_cmu_g2d_mscl_p,
+	    CLK_CON_MUX_MUX_CLKCMU_G2D_MSCL, 0, 3),
+	MUX(CLK_MOUT_CMU_G3AA_G3AA, "mout_cmu_g3aa_g3aa", mout_cmu_g3aa_g3aa_p,
+	    CLK_CON_MUX_MUX_CLKCMU_G3AA_G3AA, 0, 3),
+	MUX(CLK_MOUT_CMU_G3D_BUSD, "mout_cmu_g3d_busd", mout_cmu_g3d_busd_p,
+	    CLK_CON_MUX_MUX_CLKCMU_G3D_BUSD, 0, 3),
+	MUX(CLK_MOUT_CMU_G3D_GLB, "mout_cmu_g3d_glb", mout_cmu_g3d_glb_p,
+	    CLK_CON_MUX_MUX_CLKCMU_G3D_GLB, 0, 3),
+	MUX(CLK_MOUT_CMU_G3D_SWITCH, "mout_cmu_g3d_switch",
+	    mout_cmu_g3d_switch_p, CLK_CON_MUX_MUX_CLKCMU_G3D_SWITCH, 0, 3),
+	MUX(CLK_MOUT_CMU_GDC_GDC0, "mout_cmu_gdc_gdc0", mout_cmu_gdc_gdc0_p,
+	    CLK_CON_MUX_MUX_CLKCMU_GDC_GDC0, 0, 3),
+	MUX(CLK_MOUT_CMU_GDC_GDC1, "mout_cmu_gdc_gdc1", mout_cmu_gdc_gdc1_p,
+	    CLK_CON_MUX_MUX_CLKCMU_GDC_GDC1, 0, 3),
+	MUX(CLK_MOUT_CMU_GDC_SCSC, "mout_cmu_gdc_scsc", mout_cmu_gdc_scsc_p,
+	    CLK_CON_MUX_MUX_CLKCMU_GDC_SCSC, 0, 3),
+	MUX(CLK_MOUT_CMU_HPM, "mout_cmu_hpm", mout_cmu_hpm_p,
+	    CLK_CON_MUX_MUX_CLKCMU_HPM, 0, 2),
+	MUX(CLK_MOUT_CMU_HSI0_BUS, "mout_cmu_hsi0_bus", mout_cmu_hsi0_bus_p,
+	    CLK_CON_MUX_MUX_CLKCMU_HSI0_BUS, 0, 3),
+	MUX(CLK_MOUT_CMU_HSI0_DPGTC, "mout_cmu_hsi0_dpgtc",
+	    mout_cmu_hsi0_dpgtc_p, CLK_CON_MUX_MUX_CLKCMU_HSI0_DPGTC, 0, 2),
+	MUX(CLK_MOUT_CMU_HSI0_USB31DRD, "mout_cmu_hsi0_usb31drd",
+	    mout_cmu_hsi0_usb31drd_p, CLK_CON_MUX_MUX_CLKCMU_HSI0_USB31DRD,
+	    0, 1),
+	MUX(CLK_MOUT_CMU_HSI0_USBDPDBG, "mout_cmu_hsi0_usbdpdbg",
+	    mout_cmu_hsi0_usbdpdbg_p, CLK_CON_MUX_MUX_CLKCMU_HSI0_USBDPDBG,
+	    0, 1),
+	MUX(CLK_MOUT_CMU_HSI1_BUS, "mout_cmu_hsi1_bus", mout_cmu_hsi1_bus_p,
+	    CLK_CON_MUX_MUX_CLKCMU_HSI1_BUS, 0, 3),
+	MUX(CLK_MOUT_CMU_HSI1_PCIE, "mout_cmu_hsi1_pcie", mout_cmu_hsi1_pcie_p,
+	    CLK_CON_MUX_MUX_CLKCMU_HSI1_PCIE, 0, 1),
+	MUX(CLK_MOUT_CMU_HSI2_BUS, "mout_cmu_hsi2_bus", mout_cmu_hsi2_bus_p,
+	    CLK_CON_MUX_MUX_CLKCMU_HSI2_BUS, 0, 3),
+	MUX(CLK_MOUT_CMU_HSI2_MMC_CARD, "mout_cmu_hsi2_mmc_card",
+	    mout_cmu_hsi2_mmc_card_p, CLK_CON_MUX_MUX_CLKCMU_HSI2_MMC_CARD,
+	    0, 2),
+	MUX(CLK_MOUT_CMU_HSI2_PCIE, "mout_cmu_hsi2_pcie", mout_cmu_hsi2_pcie0_p,
+	    CLK_CON_MUX_MUX_CLKCMU_HSI2_PCIE, 0, 1),
+	MUX(CLK_MOUT_CMU_HSI2_UFS_EMBD, "mout_cmu_hsi2_ufs_embd",
+	    mout_cmu_hsi2_ufs_embd_p, CLK_CON_MUX_MUX_CLKCMU_HSI2_UFS_EMBD,
+	    0, 2),
+	MUX(CLK_MOUT_CMU_IPP_BUS, "mout_cmu_ipp_bus", mout_cmu_ipp_bus_p,
+	    CLK_CON_MUX_MUX_CLKCMU_IPP_BUS, 0, 3),
+	MUX(CLK_MOUT_CMU_ITP_BUS, "mout_cmu_itp_bus", mout_cmu_itp_bus_p,
+	    CLK_CON_MUX_MUX_CLKCMU_ITP_BUS, 0, 3),
+	MUX(CLK_MOUT_CMU_MCSC_ITSC, "mout_cmu_mcsc_itsc", mout_cmu_mcsc_itsc_p,
+	    CLK_CON_MUX_MUX_CLKCMU_MCSC_ITSC, 0, 3),
+	MUX(CLK_MOUT_CMU_MCSC_MCSC, "mout_cmu_mcsc_mcsc", mout_cmu_mcsc_mcsc_p,
+	    CLK_CON_MUX_MUX_CLKCMU_MCSC_MCSC, 0, 3),
+	MUX(CLK_MOUT_CMU_MFC_MFC, "mout_cmu_mfc_mfc", mout_cmu_mfc_mfc_p,
+	    CLK_CON_MUX_MUX_CLKCMU_MFC_MFC, 0, 3),
+	MUX(CLK_MOUT_CMU_MIF_BUSP, "mout_cmu_mif_busp", mout_cmu_mif_busp_p,
+	    CLK_CON_MUX_MUX_CLKCMU_MIF_BUSP, 0, 2),
+	MUX(CLK_MOUT_CMU_MIF_SWITCH, "mout_cmu_mif_switch",
+	    mout_cmu_mif_switch_p, CLK_CON_MUX_MUX_CLKCMU_MIF_SWITCH, 0, 3),
+	MUX(CLK_MOUT_CMU_MISC_BUS, "mout_cmu_misc_bus", mout_cmu_misc_bus_p,
+	    CLK_CON_MUX_MUX_CLKCMU_MISC_BUS, 0, 2),
+	MUX(CLK_MOUT_CMU_MISC_SSS, "mout_cmu_misc_sss", mout_cmu_misc_sss_p,
+	    CLK_CON_MUX_MUX_CLKCMU_MISC_SSS, 0, 2),
+	MUX(CLK_MOUT_CMU_PDP_BUS, "mout_cmu_pdp_bus", mout_cmu_pdp_bus_p,
+	    CLK_CON_MUX_MUX_CLKCMU_PDP_BUS, 0, 3),
+	MUX(CLK_MOUT_CMU_PDP_VRA, "mout_cmu_pdp_vra", mout_cmu_pdp_vra_p,
+	    CLK_CON_MUX_MUX_CLKCMU_PDP_VRA, 0, 3),
+	MUX(CLK_MOUT_CMU_PERIC0_BUS, "mout_cmu_peric0_bus",
+	    mout_cmu_peric0_bus_p, CLK_CON_MUX_MUX_CLKCMU_PERIC0_BUS, 0, 2),
+	MUX(CLK_MOUT_CMU_PERIC0_IP, "mout_cmu_peric0_ip", mout_cmu_peric0_ip_p,
+	    CLK_CON_MUX_MUX_CLKCMU_PERIC0_IP, 0, 2),
+	MUX(CLK_MOUT_CMU_PERIC1_BUS, "mout_cmu_peric1_bus",
+	    mout_cmu_peric1_bus_p, CLK_CON_MUX_MUX_CLKCMU_PERIC1_BUS, 0, 2),
+	MUX(CLK_MOUT_CMU_PERIC1_IP, "mout_cmu_peric1_ip", mout_cmu_peric1_ip_p,
+	    CLK_CON_MUX_MUX_CLKCMU_PERIC1_IP, 0, 2),
+	MUX(CLK_MOUT_CMU_TNR_BUS, "mout_cmu_tnr_bus", mout_cmu_tnr_bus_p,
+	    CLK_CON_MUX_MUX_CLKCMU_TNR_BUS, 0, 3),
+	MUX(CLK_MOUT_CMU_TOP_BOOST_OPTION1, "mout_cmu_top_boost_option1",
+	    mout_cmu_top_boost_option1_p,
+	    CLK_CON_MUX_MUX_CLKCMU_TOP_BOOST_OPTION1, 0, 1),
+	MUX(CLK_MOUT_CMU_TOP_CMUREF, "mout_cmu_top_cmuref",
+	    mout_cmu_top_cmuref_p, CLK_CON_MUX_MUX_CLKCMU_TOP_CMUREF, 0, 2),
+	MUX(CLK_MOUT_CMU_TPU_BUS, "mout_cmu_tpu_bus", mout_cmu_tpu_bus_p,
+	    CLK_CON_MUX_MUX_CLKCMU_TPU_BUS, 0, 3),
+	MUX(CLK_MOUT_CMU_TPU_TPU, "mout_cmu_tpu_tpu", mout_cmu_tpu_tpu_p,
+	    CLK_CON_MUX_MUX_CLKCMU_TPU_TPU, 0, 3),
+	MUX(CLK_MOUT_CMU_TPU_TPUCTL, "mout_cmu_tpu_tpuctl",
+	    mout_cmu_tpu_tpuctl_p, CLK_CON_MUX_MUX_CLKCMU_TPU_TPUCTL, 0, 3),
+	MUX(CLK_MOUT_CMU_TPU_UART, "mout_cmu_tpu_uart", mout_cmu_tpu_uart_p,
+	    CLK_CON_MUX_MUX_CLKCMU_TPU_UART, 0, 2),
+	MUX(CLK_MOUT_CMU_CMUREF, "mout_cmu_cmuref", mout_cmu_cmuref_p,
+	    CLK_CON_MUX_MUX_CMU_CMUREF, 0, 1),
+};
+
+static const struct samsung_div_clock cmu_top_div_clks[] __initconst = {
+	DIV(CLK_DOUT_CMU_BO_BUS, "dout_cmu_bo_bus", "gout_cmu_bo_bus",
+	    CLK_CON_DIV_CLKCMU_BO_BUS, 0, 4),
+	DIV(CLK_DOUT_CMU_BUS0_BUS, "dout_cmu_bus0_bus", "gout_cmu_bus0_bus",
+	    CLK_CON_DIV_CLKCMU_BUS0_BUS, 0, 4),
+	DIV(CLK_DOUT_CMU_BUS1_BUS, "dout_cmu_bus1_bus", "gout_cmu_bus1_bus",
+	    CLK_CON_DIV_CLKCMU_BUS1_BUS, 0, 4),
+	DIV(CLK_DOUT_CMU_BUS2_BUS, "dout_cmu_bus2_bus", "gout_cmu_bus2_bus",
+	    CLK_CON_DIV_CLKCMU_BUS2_BUS, 0, 4),
+	DIV(CLK_DOUT_CMU_CIS_CLK0, "dout_cmu_cis_clk0", "gout_cmu_cis_clk0",
+	    CLK_CON_DIV_CLKCMU_CIS_CLK0, 0, 5),
+	DIV(CLK_DOUT_CMU_CIS_CLK1, "dout_cmu_cis_clk1", "gout_cmu_cis_clk1",
+	    CLK_CON_DIV_CLKCMU_CIS_CLK1, 0, 5),
+	DIV(CLK_DOUT_CMU_CIS_CLK2, "dout_cmu_cis_clk2", "gout_cmu_cis_clk2",
+	    CLK_CON_DIV_CLKCMU_CIS_CLK2, 0, 5),
+	DIV(CLK_DOUT_CMU_CIS_CLK3, "dout_cmu_cis_clk3", "gout_cmu_cis_clk3",
+	    CLK_CON_DIV_CLKCMU_CIS_CLK3, 0, 5),
+	DIV(CLK_DOUT_CMU_CIS_CLK4, "dout_cmu_cis_clk4", "gout_cmu_cis_clk4",
+	    CLK_CON_DIV_CLKCMU_CIS_CLK4, 0, 5),
+	DIV(CLK_DOUT_CMU_CIS_CLK5, "dout_cmu_cis_clk5", "gout_cmu_cis_clk5",
+	    CLK_CON_DIV_CLKCMU_CIS_CLK5, 0, 5),
+	DIV(CLK_DOUT_CMU_CIS_CLK6, "dout_cmu_cis_clk6", "gout_cmu_cis_clk6",
+	    CLK_CON_DIV_CLKCMU_CIS_CLK6, 0, 5),
+	DIV(CLK_DOUT_CMU_CIS_CLK7, "dout_cmu_cis_clk7", "gout_cmu_cis_clk7",
+	    CLK_CON_DIV_CLKCMU_CIS_CLK7, 0, 5),
+	DIV(CLK_DOUT_CMU_CORE_BUS, "dout_cmu_core_bus", "gout_cmu_core_bus",
+	    CLK_CON_DIV_CLKCMU_CORE_BUS, 0, 4),
+	DIV(CLK_DOUT_CMU_CPUCL0_DBG, "dout_cmu_cpucl0_dbg",
+	    "gout_cmu_cpucl0_dbg", CLK_CON_DIV_CLKCMU_CPUCL0_DBG, 0, 4),
+	DIV(CLK_DOUT_CMU_CPUCL0_SWITCH, "dout_cmu_cpucl0_switch",
+	    "gout_cmu_cpucl0_switch", CLK_CON_DIV_CLKCMU_CPUCL0_SWITCH, 0, 3),
+	DIV(CLK_DOUT_CMU_CPUCL1_SWITCH, "dout_cmu_cpucl1_switch",
+	    "gout_cmu_cpucl1_switch", CLK_CON_DIV_CLKCMU_CPUCL1_SWITCH, 0, 3),
+	DIV(CLK_DOUT_CMU_CPUCL2_SWITCH, "dout_cmu_cpucl2_switch",
+	    "gout_cmu_cpucl2_switch", CLK_CON_DIV_CLKCMU_CPUCL2_SWITCH, 0, 3),
+	DIV(CLK_DOUT_CMU_CSIS_BUS, "dout_cmu_csis_bus", "gout_cmu_csis_bus",
+	    CLK_CON_DIV_CLKCMU_CSIS_BUS, 0, 4),
+	DIV(CLK_DOUT_CMU_DISP_BUS, "dout_cmu_disp_bus", "gout_cmu_disp_bus",
+	    CLK_CON_DIV_CLKCMU_DISP_BUS, 0, 4),
+	DIV(CLK_DOUT_CMU_DNS_BUS, "dout_cmu_dns_bus", "gout_cmu_dns_bus",
+	    CLK_CON_DIV_CLKCMU_DNS_BUS, 0, 4),
+	DIV(CLK_DOUT_CMU_DPU_BUS, "dout_cmu_dpu_bus", "gout_cmu_dpu_bus",
+	    CLK_CON_DIV_CLKCMU_DPU_BUS, 0, 4),
+	DIV(CLK_DOUT_CMU_EH_BUS, "dout_cmu_eh_bus", "gout_cmu_eh_bus",
+	    CLK_CON_DIV_CLKCMU_EH_BUS, 0, 4),
+	DIV(CLK_DOUT_CMU_G2D_G2D, "dout_cmu_g2d_g2d", "gout_cmu_g2d_g2d",
+	    CLK_CON_DIV_CLKCMU_G2D_G2D, 0, 4),
+	DIV(CLK_DOUT_CMU_G2D_MSCL, "dout_cmu_g2d_mscl", "gout_cmu_g2d_mscl",
+	    CLK_CON_DIV_CLKCMU_G2D_MSCL, 0, 4),
+	DIV(CLK_DOUT_CMU_G3AA_G3AA, "dout_cmu_g3aa_g3aa", "gout_cmu_g3aa_g3aa",
+	    CLK_CON_DIV_CLKCMU_G3AA_G3AA, 0, 4),
+	DIV(CLK_DOUT_CMU_G3D_SWITCH, "dout_cmu_g3d_busd", "gout_cmu_g3d_busd",
+	    CLK_CON_DIV_CLKCMU_G3D_BUSD, 0, 4),
+	DIV(CLK_DOUT_CMU_G3D_GLB, "dout_cmu_g3d_glb", "gout_cmu_g3d_glb",
+	    CLK_CON_DIV_CLKCMU_G3D_GLB, 0, 4),
+	DIV(CLK_DOUT_CMU_G3D_SWITCH, "dout_cmu_g3d_switch",
+	    "gout_cmu_g3d_switch", CLK_CON_DIV_CLKCMU_G3D_SWITCH, 0, 3),
+	DIV(CLK_DOUT_CMU_GDC_GDC0, "dout_cmu_gdc_gdc0", "gout_cmu_gdc_gdc0",
+	    CLK_CON_DIV_CLKCMU_GDC_GDC0, 0, 4),
+	DIV(CLK_DOUT_CMU_GDC_GDC1, "dout_cmu_gdc_gdc1", "gout_cmu_gdc_gdc1",
+	    CLK_CON_DIV_CLKCMU_GDC_GDC1, 0, 4),
+	DIV(CLK_DOUT_CMU_GDC_SCSC, "dout_cmu_gdc_scsc", "gout_cmu_gdc_scsc",
+	    CLK_CON_DIV_CLKCMU_GDC_SCSC, 0, 4),
+	DIV(CLK_DOUT_CMU_CMU_HPM, "dout_cmu_hpm", "gout_cmu_hpm",
+	    CLK_CON_DIV_CLKCMU_HPM, 0, 2),
+	DIV(CLK_DOUT_CMU_HSI0_BUS, "dout_cmu_hsi0_bus", "gout_cmu_hsi0_bus",
+	    CLK_CON_DIV_CLKCMU_HSI0_BUS, 0, 4),
+	DIV(CLK_DOUT_CMU_HSI0_DPGTC, "dout_cmu_hsi0_dpgtc",
+	    "gout_cmu_hsi0_dpgtc", CLK_CON_DIV_CLKCMU_HSI0_DPGTC, 0, 4),
+	DIV(CLK_DOUT_CMU_HSI0_USB31DRD, "dout_cmu_hsi0_usb31drd",
+	    "gout_cmu_hsi0_usb31drd", CLK_CON_DIV_CLKCMU_HSI0_USB31DRD, 0, 5),
+	DIV(CLK_DOUT_CMU_HSI1_BUS, "dout_cmu_hsi1_bus", "gout_cmu_hsi1_bus",
+	    CLK_CON_DIV_CLKCMU_HSI1_BUS, 0, 4),
+	DIV(CLK_DOUT_CMU_HSI1_PCIE, "dout_cmu_hsi1_pcie", "gout_cmu_hsi1_pcie",
+	    CLK_CON_DIV_CLKCMU_HSI1_PCIE, 0, 3),
+	DIV(CLK_DOUT_CMU_HSI2_BUS, "dout_cmu_hsi2_bus", "gout_cmu_hsi2_bus",
+	    CLK_CON_DIV_CLKCMU_HSI2_BUS, 0, 4),
+	DIV(CLK_DOUT_CMU_HSI2_MMC_CARD, "dout_cmu_hsi2_mmc_card",
+	    "gout_cmu_hsi2_mmc_card", CLK_CON_DIV_CLKCMU_HSI2_MMC_CARD, 0, 9),
+	DIV(CLK_DOUT_CMU_HSI2_PCIE, "dout_cmu_hsi2_pcie", "gout_cmu_hsi2_pcie",
+	    CLK_CON_DIV_CLKCMU_HSI2_PCIE, 0, 3),
+	DIV(CLK_DOUT_CMU_HSI2_UFS_EMBD, "dout_cmu_hsi2_ufs_embd",
+	    "gout_cmu_hsi2_ufs_embd", CLK_CON_DIV_CLKCMU_HSI2_UFS_EMBD, 0, 4),
+	DIV(CLK_DOUT_CMU_IPP_BUS, "dout_cmu_ipp_bus", "gout_cmu_ipp_bus",
+	    CLK_CON_DIV_CLKCMU_IPP_BUS, 0, 4),
+	DIV(CLK_DOUT_CMU_ITP_BUS, "dout_cmu_itp_bus", "gout_cmu_itp_bus",
+	    CLK_CON_DIV_CLKCMU_ITP_BUS, 0, 4),
+	DIV(CLK_DOUT_CMU_MCSC_ITSC, "dout_cmu_mcsc_itsc", "gout_cmu_mcsc_itsc",
+	    CLK_CON_DIV_CLKCMU_MCSC_ITSC, 0, 4),
+	DIV(CLK_DOUT_CMU_MCSC_MCSC, "dout_cmu_mcsc_mcsc", "gout_cmu_mcsc_mcsc",
+	    CLK_CON_DIV_CLKCMU_MCSC_MCSC, 0, 4),
+	DIV(CLK_DOUT_CMU_MFC_MFC, "dout_cmu_mfc_mfc", "gout_cmu_mfc_mfc",
+	    CLK_CON_DIV_CLKCMU_MFC_MFC, 0, 4),
+	DIV(CLK_DOUT_CMU_MIF_BUSP, "dout_cmu_mif_busp", "gout_cmu_mif_busp",
+	    CLK_CON_DIV_CLKCMU_MIF_BUSP, 0, 4),
+	DIV(CLK_DOUT_CMU_MISC_BUS, "dout_cmu_misc_bus", "gout_cmu_misc_bus",
+	    CLK_CON_DIV_CLKCMU_MISC_BUS, 0, 4),
+	DIV(CLK_DOUT_CMU_MISC_SSS, "dout_cmu_misc_sss", "gout_cmu_misc_sss",
+	    CLK_CON_DIV_CLKCMU_MISC_SSS, 0, 4),
+	DIV(CLK_DOUT_CMU_PDP_BUS, "dout_cmu_pdp_bus", "gout_cmu_pdp_bus",
+	    CLK_CON_DIV_CLKCMU_PDP_BUS, 0, 4),
+	DIV(CLK_DOUT_CMU_PDP_VRA, "dout_cmu_pdp_vra", "gout_cmu_pdp_vra",
+	    CLK_CON_DIV_CLKCMU_PDP_VRA, 0, 4),
+	DIV(CLK_DOUT_CMU_PERIC0_BUS, "dout_cmu_peric0_bus",
+	    "gout_cmu_peric0_bus", CLK_CON_DIV_CLKCMU_PERIC0_BUS, 0, 4),
+	DIV(CLK_DOUT_CMU_PERIC0_IP, "dout_cmu_peric0_ip", "gout_cmu_peric0_ip",
+	    CLK_CON_DIV_CLKCMU_PERIC0_IP, 0, 4),
+	DIV(CLK_DOUT_CMU_PERIC1_BUS, "dout_cmu_peric1_bus",
+	    "gout_cmu_peric1_bus", CLK_CON_DIV_CLKCMU_PERIC1_BUS, 0, 4),
+	DIV(CLK_DOUT_CMU_PERIC1_IP, "dout_cmu_peric1_ip", "gout_cmu_peric1_ip",
+	    CLK_CON_DIV_CLKCMU_PERIC1_IP, 0, 4),
+	DIV(CLK_DOUT_CMU_TNR_BUS, "dout_cmu_tnr_bus", "gout_cmu_tnr_bus",
+	    CLK_CON_DIV_CLKCMU_TNR_BUS, 0, 4),
+	DIV(CLK_DOUT_CMU_TPU_BUS, "dout_cmu_tpu_bus", "gout_cmu_tpu_bus",
+	    CLK_CON_DIV_CLKCMU_TPU_BUS, 0, 4),
+	DIV(CLK_DOUT_CMU_TPU_TPU, "dout_cmu_tpu_tpu", "gout_cmu_tpu_tpu",
+	    CLK_CON_DIV_CLKCMU_TPU_TPU, 0, 4),
+	DIV(CLK_DOUT_CMU_TPU_TPUCTL, "dout_cmu_tpu_tpuctl",
+	    "gout_cmu_tpu_tpuctl", CLK_CON_DIV_CLKCMU_TPU_TPUCTL, 0, 4),
+	DIV(CLK_DOUT_CMU_TPU_UART, "dout_cmu_tpu_uart", "gout_cmu_tpu_uart",
+	    CLK_CON_DIV_CLKCMU_TPU_UART, 0, 4),
+	DIV(CLK_DOUT_CMU_CMU_BOOST, "dout_cmu_cmu_boost", "gout_cmu_cmu_boost",
+	    CLK_CON_DIV_DIV_CLKCMU_CMU_BOOST, 0, 2),
+	DIV(CLK_DOUT_CMU_CMU_CMUREF, "dout_cmu_cmuref", "gout_cmu_cmuref",
+	    CLK_CON_DIV_DIV_CLK_CMU_CMUREF, 0, 2),
+	DIV(CLK_DOUT_CMU_SHARED0_DIV2, "dout_cmu_shared0_div2",
+	    "mout_pll_shared0", CLK_CON_DIV_PLL_SHARED0_DIV2, 0, 1),
+	DIV(CLK_DOUT_CMU_SHARED0_DIV3, "dout_cmu_shared0_div3",
+	    "mout_pll_shared0", CLK_CON_DIV_PLL_SHARED0_DIV3, 0, 2),
+	DIV(CLK_DOUT_CMU_SHARED0_DIV4, "dout_cmu_shared0_div4",
+	    "dout_cmu_shared0_div2", CLK_CON_DIV_PLL_SHARED0_DIV4, 0, 1),
+	DIV(CLK_DOUT_CMU_SHARED0_DIV5, "dout_cmu_shared0_div5",
+	    "mout_pll_shared0", CLK_CON_DIV_PLL_SHARED0_DIV5, 0, 3),
+	DIV(CLK_DOUT_CMU_SHARED1_DIV2, "dout_cmu_shared1_div2",
+	    "mout_pll_shared1", CLK_CON_DIV_PLL_SHARED1_DIV2, 0, 1),
+	DIV(CLK_DOUT_CMU_SHARED1_DIV3, "dout_cmu_shared1_div3",
+	    "mout_pll_shared1", CLK_CON_DIV_PLL_SHARED1_DIV3, 0, 2),
+	DIV(CLK_DOUT_CMU_SHARED1_DIV4, "dout_cmu_shared1_div4",
+	    "mout_pll_shared1", CLK_CON_DIV_PLL_SHARED1_DIV4, 0, 1),
+	DIV(CLK_DOUT_CMU_SHARED2_DIV2, "dout_cmu_shared2_div2",
+	    "mout_pll_shared2", CLK_CON_DIV_PLL_SHARED2_DIV2, 0, 1),
+	DIV(CLK_DOUT_CMU_SHARED3_DIV2, "dout_cmu_shared3_div2",
+	    "mout_pll_shared3", CLK_CON_DIV_PLL_SHARED3_DIV2, 0, 1),
+};
+
+static const struct samsung_fixed_factor_clock cmu_top_ffactor[] __initconst = {
+	FFACTOR(CLK_DOUT_CMU_HSI0_USBDPDBG, "dout_cmu_hsi0_usbdpdbg",
+		"gout_cmu_hsi0_usbdpdbg", 1, 4, 0),
+	FFACTOR(CLK_DOUT_CMU_OTP, "dout_cmu_otp", "oscclk", 1, 8, 0),
+};
+
+static const struct samsung_gate_clock cmu_top_gate_clks[] __initconst = {
+	GATE(CLK_GOUT_CMU_BUS0_BOOST, "gout_cmu_bus0_boost",
+	     "mout_cmu_boost_option1", CLK_CON_GAT_CLKCMU_BUS0_BOOST, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_BUS1_BOOST, "gout_cmu_bus1_boost",
+	     "mout_cmu_boost_option1", CLK_CON_GAT_CLKCMU_BUS1_BOOST, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_BUS2_BOOST, "gout_cmu_bus2_boost",
+	     "mout_cmu_boost_option1", CLK_CON_GAT_CLKCMU_BUS2_BOOST, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_CORE_BOOST, "gout_cmu_core_boost",
+	     "mout_cmu_boost_option1", CLK_CON_GAT_CLKCMU_CORE_BOOST, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_CPUCL0_BOOST, "gout_cmu_cpucl0_boost",
+	     "mout_cmu_boost_option1", CLK_CON_GAT_CLKCMU_CPUCL0_BOOST,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_CPUCL1_BOOST, "gout_cmu_cpucl1_boost",
+	     "mout_cmu_boost_option1", CLK_CON_GAT_CLKCMU_CPUCL1_BOOST,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_CPUCL2_BOOST, "gout_cmu_cpucl2_boost",
+	     "mout_cmu_boost_option1", CLK_CON_GAT_CLKCMU_CPUCL2_BOOST,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_MIF_BOOST, "gout_cmu_mif_boost",
+	     "mout_cmu_boost_option1", CLK_CON_GAT_CLKCMU_MIF_BOOST,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_MIF_SWITCH, "gout_cmu_mif_switch",
+	     "mout_cmu_mif_switch", CLK_CON_GAT_CLKCMU_MIF_SWITCH, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_BO_BUS, "gout_cmu_bo_bus", "mout_cmu_bo_bus",
+	     CLK_CON_GAT_GATE_CLKCMU_BO_BUS, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_BUS0_BUS, "gout_cmu_bus0_bus", "mout_cmu_bus0_bus",
+	     CLK_CON_GAT_GATE_CLKCMU_BUS0_BUS, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_BUS1_BUS, "gout_cmu_bus1_bus", "mout_cmu_bus1_bus",
+	     CLK_CON_GAT_GATE_CLKCMU_BUS1_BUS, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_BUS2_BUS, "gout_cmu_bus2_bus", "mout_cmu_bus2_bus",
+	     CLK_CON_GAT_GATE_CLKCMU_BUS2_BUS, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_CIS_CLK0, "gout_cmu_cis_clk0", "mout_cmu_cis_clk0",
+	     CLK_CON_GAT_GATE_CLKCMU_CIS_CLK0, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_CIS_CLK1, "gout_cmu_cis_clk1", "mout_cmu_cis_clk1",
+	     CLK_CON_GAT_GATE_CLKCMU_CIS_CLK1, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_CIS_CLK2, "gout_cmu_cis_clk2", "mout_cmu_cis_clk2",
+	     CLK_CON_GAT_GATE_CLKCMU_CIS_CLK2, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_CIS_CLK3, "gout_cmu_cis_clk3", "mout_cmu_cis_clk3",
+	     CLK_CON_GAT_GATE_CLKCMU_CIS_CLK3, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_CIS_CLK4, "gout_cmu_cis_clk4", "mout_cmu_cis_clk4",
+	     CLK_CON_GAT_GATE_CLKCMU_CIS_CLK4, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_CIS_CLK5, "gout_cmu_cis_clk5", "mout_cmu_cis_clk5",
+	     CLK_CON_GAT_GATE_CLKCMU_CIS_CLK5, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_CIS_CLK6, "gout_cmu_cis_clk6", "mout_cmu_cis_clk6",
+	     CLK_CON_GAT_GATE_CLKCMU_CIS_CLK6, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_CIS_CLK7, "gout_cmu_cis_clk7", "mout_cmu_cis_clk7",
+	     CLK_CON_GAT_GATE_CLKCMU_CIS_CLK7, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_CMU_BOOST, "gout_cmu_cmu_boost", "mout_cmu_cmu_boost",
+	     CLK_CON_GAT_GATE_CLKCMU_CMU_BOOST, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_CORE_BUS, "gout_cmu_core_bus", "mout_cmu_core_bus",
+	     CLK_CON_GAT_GATE_CLKCMU_CORE_BUS, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_CPUCL0_DBG, "gout_cmu_cpucl0_dbg",
+	     "mout_cmu_cpucl0_dbg", CLK_CON_GAT_GATE_CLKCMU_CPUCL0_DBG_BUS,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_CPUCL0_SWITCH, "gout_cmu_cpucl0_switch",
+	     "mout_cmu_cpucl0_switch", CLK_CON_GAT_GATE_CLKCMU_CPUCL0_SWITCH,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_CPUCL1_SWITCH, "gout_cmu_cpucl1_switch",
+	     "mout_cmu_cpucl1_switch", CLK_CON_GAT_GATE_CLKCMU_CPUCL1_SWITCH,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_CPUCL2_SWITCH, "gout_cmu_cpucl2_switch",
+	     "mout_cmu_cpucl2_switch", CLK_CON_GAT_GATE_CLKCMU_CPUCL2_SWITCH,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_CSIS_BUS, "gout_cmu_csis_bus", "mout_cmu_csis_bus",
+	     CLK_CON_GAT_GATE_CLKCMU_CSIS_BUS, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_DISP_BUS, "gout_cmu_disp_bus", "mout_cmu_disp_bus",
+	     CLK_CON_GAT_GATE_CLKCMU_DISP_BUS, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_DNS_BUS, "gout_cmu_dns_bus", "mout_cmu_dns_bus",
+	     CLK_CON_GAT_GATE_CLKCMU_DNS_BUS, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_DPU_BUS, "gout_cmu_dpu_bus", "mout_cmu_dpu_bus",
+	     CLK_CON_GAT_GATE_CLKCMU_DPU_BUS, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_EH_BUS, "gout_cmu_eh_bus", "mout_cmu_eh_bus",
+	     CLK_CON_GAT_GATE_CLKCMU_EH_BUS, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_G2D_G2D, "gout_cmu_g2d_g2d", "mout_cmu_g2d_g2d",
+	     CLK_CON_GAT_GATE_CLKCMU_G2D_G2D, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_G2D_MSCL, "gout_cmu_g2d_mscl", "mout_cmu_g2d_mscl",
+	     CLK_CON_GAT_GATE_CLKCMU_G2D_MSCL, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_G3AA_G3AA, "gout_cmu_g3aa_g3aa", "mout_cmu_g3aa_g3aa",
+	     CLK_CON_MUX_MUX_CLKCMU_G3AA_G3AA, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_G3D_BUSD, "gout_cmu_g3d_busd", "mout_cmu_g3d_busd",
+	     CLK_CON_GAT_GATE_CLKCMU_G3D_BUSD, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_G3D_GLB, "gout_cmu_g3d_glb", "mout_cmu_g3d_glb",
+	     CLK_CON_GAT_GATE_CLKCMU_G3D_GLB, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_G3D_SWITCH, "gout_cmu_g3d_switch",
+	     "mout_cmu_g3d_switch", CLK_CON_GAT_GATE_CLKCMU_G3D_SWITCH,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_GDC_GDC0, "gout_cmu_gdc_gdc0", "mout_cmu_gdc_gdc0",
+	     CLK_CON_GAT_GATE_CLKCMU_GDC_GDC0, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_GDC_GDC1, "gout_cmu_gdc_gdc1", "mout_cmu_gdc_gdc1",
+	     CLK_CON_GAT_GATE_CLKCMU_GDC_GDC1, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_GDC_SCSC, "gout_cmu_gdc_scsc", "mout_cmu_gdc_scsc",
+	     CLK_CON_GAT_GATE_CLKCMU_GDC_SCSC, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_HPM, "gout_cmu_hpm", "mout_cmu_hpm",
+	     CLK_CON_GAT_GATE_CLKCMU_HPM, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_HSI0_BUS, "gout_cmu_hsi0_bus", "mout_cmu_hsi0_bus",
+	     CLK_CON_GAT_GATE_CLKCMU_HSI0_BUS, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_HSI0_DPGTC, "gout_cmu_hsi0_dpgtc",
+	     "mout_cmu_hsi0_dpgtc", CLK_CON_GAT_GATE_CLKCMU_HSI0_DPGTC,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_HSI0_USB31DRD, "gout_cmu_hsi0_usb31drd",
+	     "mout_cmu_hsi0_usb31drd", CLK_CON_GAT_GATE_CLKCMU_HSI0_USB31DRD,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_HSI0_USBDPDBG, "gout_cmu_hsi0_usbdpdbg",
+	     "mout_cmu_hsi0_usbdpdbg", CLK_CON_GAT_GATE_CLKCMU_HSI0_USBDPDBG,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_HSI1_BUS, "gout_cmu_hsi1_bus", "mout_cmu_hsi1_bus",
+	     CLK_CON_GAT_GATE_CLKCMU_HSI1_BUS, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_HSI1_PCIE, "gout_cmu_hsi1_pcie", "mout_cmu_hsi1_pcie",
+	     CLK_CON_GAT_GATE_CLKCMU_HSI1_PCIE, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_HSI2_BUS, "gout_cmu_hsi2_bus", "mout_cmu_hsi2_bus",
+	     CLK_CON_GAT_GATE_CLKCMU_HSI2_BUS, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_HSI2_MMC_CARD, "gout_cmu_hsi2_mmc_card",
+	     "mout_cmu_hsi2_mmc_card", CLK_CON_GAT_GATE_CLKCMU_HSI2_MMCCARD,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_HSI2_PCIE, "gout_cmu_hsi2_pcie", "mout_cmu_hsi2_pcie",
+	     CLK_CON_GAT_GATE_CLKCMU_HSI2_PCIE, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_HSI2_UFS_EMBD, "gout_cmu_hsi2_ufs_embd",
+	     "mout_cmu_hsi2_ufs_embd", CLK_CON_GAT_GATE_CLKCMU_HSI2_UFS_EMBD,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_IPP_BUS, "gout_cmu_ipp_bus", "mout_cmu_ipp_bus",
+	     CLK_CON_GAT_GATE_CLKCMU_IPP_BUS, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_ITP_BUS, "gout_cmu_itp_bus", "mout_cmu_itp_bus",
+	     CLK_CON_GAT_GATE_CLKCMU_ITP_BUS, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_MCSC_ITSC, "gout_cmu_mcsc_itsc", "mout_cmu_mcsc_itsc",
+	     CLK_CON_GAT_GATE_CLKCMU_MCSC_ITSC, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_MCSC_MCSC, "gout_cmu_mcsc_mcsc", "mout_cmu_mcsc_mcsc",
+	     CLK_CON_GAT_GATE_CLKCMU_MCSC_MCSC, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_MFC_MFC, "gout_cmu_mfc_mfc", "mout_cmu_mfc_mfc",
+	     CLK_CON_GAT_GATE_CLKCMU_MFC_MFC, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_MIF_BUSP, "gout_cmu_mif_busp", "mout_cmu_mif_busp",
+	     CLK_CON_GAT_GATE_CLKCMU_MIF_BUSP, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_MISC_BUS, "gout_cmu_misc_bus", "mout_cmu_misc_bus",
+	     CLK_CON_GAT_GATE_CLKCMU_MISC_BUS, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_MISC_SSS, "gout_cmu_misc_sss", "mout_cmu_misc_sss",
+	     CLK_CON_GAT_GATE_CLKCMU_MISC_SSS, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_PDP_BUS, "gout_cmu_pdp_bus", "mout_cmu_pdp_bus",
+	     CLK_CON_GAT_GATE_CLKCMU_PDP_BUS, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_PDP_VRA, "gout_cmu_pdp_vra", "mout_cmu_pdp_vra",
+	     CLK_CON_GAT_GATE_CLKCMU_PDP_BUS, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_PERIC0_BUS, "gout_cmu_peric0_bus",
+	     "mout_cmu_peric0_bus", CLK_CON_GAT_GATE_CLKCMU_PERIC0_BUS,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_PERIC0_IP, "gout_cmu_peric0_ip", "mout_cmu_peric0_ip",
+	     CLK_CON_GAT_GATE_CLKCMU_PERIC0_IP, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_PERIC1_BUS, "gout_cmu_peric1_bus",
+	     "mout_cmu_peric1_bus", CLK_CON_GAT_GATE_CLKCMU_PERIC1_BUS,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_PERIC1_IP, "gout_cmu_peric1_ip", "mout_cmu_peric1_ip",
+	     CLK_CON_GAT_GATE_CLKCMU_PERIC1_IP, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_TNR_BUS, "gout_cmu_tnr_bus", "mout_cmu_tnr_bus",
+	     CLK_CON_GAT_GATE_CLKCMU_TNR_BUS, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_TOP_CMUREF, "gout_cmu_top_cmuref",
+	     "mout_cmu_top_cmuref", CLK_CON_GAT_GATE_CLKCMU_TOP_CMUREF,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_TPU_BUS, "gout_cmu_tpu_bus", "mout_cmu_tpu_bus",
+	     CLK_CON_GAT_GATE_CLKCMU_TPU_BUS, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_TPU_TPU, "gout_cmu_tpu_tpu", "mout_cmu_tpu_tpu",
+	     CLK_CON_GAT_GATE_CLKCMU_TPU_TPU, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_TPU_TPUCTL, "gout_cmu_tpu_tpuctl",
+	     "mout_cmu_tpu_tpuctl", CLK_CON_GAT_GATE_CLKCMU_TPU_TPUCTL,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_TPU_UART, "gout_cmu_tpu_uart", "mout_cmu_tpu_uart",
+	     CLK_CON_GAT_GATE_CLKCMU_TPU_UART, 21, 0, 0),
+};
+
+static const struct samsung_cmu_info top_cmu_info __initconst = {
+	.pll_clks		= cmu_top_pll_clks,
+	.nr_pll_clks		= ARRAY_SIZE(cmu_top_pll_clks),
+	.mux_clks		= cmu_top_mux_clks,
+	.nr_mux_clks		= ARRAY_SIZE(cmu_top_mux_clks),
+	.div_clks		= cmu_top_div_clks,
+	.nr_div_clks		= ARRAY_SIZE(cmu_top_div_clks),
+	.fixed_factor_clks	= cmu_top_ffactor,
+	.nr_fixed_factor_clks	= ARRAY_SIZE(cmu_top_ffactor),
+	.gate_clks		= cmu_top_gate_clks,
+	.nr_gate_clks		= ARRAY_SIZE(cmu_top_gate_clks),
+	.nr_clk_ids		= CLKS_NR_TOP,
+	.clk_regs		= cmu_top_clk_regs,
+	.nr_clk_regs		= ARRAY_SIZE(cmu_top_clk_regs),
+};
+
+static void __init gs101_cmu_top_init(struct device_node *np)
+{
+	exynos_arm64_register_cmu(NULL, np, &top_cmu_info);
+}
+
+/* Register CMU_TOP early, as it's a dependency for other early domains */
+CLK_OF_DECLARE(gs101_cmu_top, "google,gs101-cmu-top",
+	       gs101_cmu_top_init);
+
+/* ---- CMU_APM ------------------------------------------------------------- */
+
+/* Register Offset definitions for CMU_APM (0x17400000) */
+#define APM_CMU_APM_CONTROLLER_OPTION							0x0800
+#define CLKOUT_CON_BLK_APM_CMU_APM_CLKOUT0						0x0810
+#define CLK_CON_MUX_MUX_CLKCMU_APM_FUNC							0x1000
+#define CLK_CON_MUX_MUX_CLKCMU_APM_FUNCSRC						0x1004
+#define CLK_CON_DIV_DIV_CLK_APM_BOOST							0x1800
+#define CLK_CON_DIV_DIV_CLK_APM_USI0_UART						0x1804
+#define CLK_CON_DIV_DIV_CLK_APM_USI0_USI						0x1808
+#define CLK_CON_DIV_DIV_CLK_APM_USI1_UART						0x180c
+#define CLK_CON_GAT_CLK_BLK_APM_UID_APM_CMU_APM_IPCLKPORT_PCLK				0x2000
+#define CLK_CON_GAT_CLK_BUS0_BOOST_OPTION1						0x2004
+#define CLK_CON_GAT_CLK_CMU_BOOST_OPTION1						0x2008
+#define CLK_CON_GAT_CLK_CORE_BOOST_OPTION1						0x200c
+#define CLK_CON_GAT_GATE_CLKCMU_APM_FUNC						0x2010
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_APBIF_GPIO_ALIVE_IPCLKPORT_PCLK			0x2014
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_APBIF_GPIO_FAR_ALIVE_IPCLKPORT_PCLK		0x2018
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_APBIF_PMU_ALIVE_IPCLKPORT_PCLK			0x201c
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_APBIF_RTC_IPCLKPORT_PCLK				0x2020
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_APBIF_TRTC_IPCLKPORT_PCLK				0x2024
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_APM_USI0_UART_IPCLKPORT_IPCLK			0x2028
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_APM_USI0_UART_IPCLKPORT_PCLK			0x202c
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_APM_USI0_USI_IPCLKPORT_IPCLK			0x2030
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_APM_USI0_USI_IPCLKPORT_PCLK			0x2034
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_APM_USI1_UART_IPCLKPORT_IPCLK			0x2038
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_APM_USI1_UART_IPCLKPORT_PCLK			0x203c
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_D_TZPC_APM_IPCLKPORT_PCLK				0x2040
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_GPC_APM_IPCLKPORT_PCLK				0x2044
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_GREBEINTEGRATION_IPCLKPORT_HCLK			0x2048
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_INTMEM_IPCLKPORT_ACLK				0x204c
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_INTMEM_IPCLKPORT_PCLK				0x2050
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_LHM_AXI_G_SWD_IPCLKPORT_I_CLK			0x2054
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_LHM_AXI_P_AOCAPM_IPCLKPORT_I_CLK			0x2058
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_LHM_AXI_P_APM_IPCLKPORT_I_CLK			0x205c
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_LHS_AXI_D_APM_IPCLKPORT_I_CLK			0x2060
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_LHS_AXI_G_DBGCORE_IPCLKPORT_I_CLK			0x2064
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_LHS_AXI_G_SCAN2DRAM_IPCLKPORT_I_CLK		0x2068
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_MAILBOX_APM_AOC_IPCLKPORT_PCLK			0x206c
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_MAILBOX_APM_AP_IPCLKPORT_PCLK			0x2070
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_MAILBOX_APM_GSA_IPCLKPORT_PCLK			0x2074
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_MAILBOX_APM_SWD_IPCLKPORT_PCLK			0x207c
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_MAILBOX_APM_TPU_IPCLKPORT_PCLK			0x2080
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_MAILBOX_AP_AOC_IPCLKPORT_PCLK			0x2084
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_MAILBOX_AP_DBGCORE_IPCLKPORT_PCLK			0x2088
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_PMU_INTR_GEN_IPCLKPORT_PCLK			0x208c
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_ROM_CRC32_HOST_IPCLKPORT_ACLK			0x2090
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_ROM_CRC32_HOST_IPCLKPORT_PCLK			0x2094
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_RSTNSYNC_CLK_APM_BUS_IPCLKPORT_CLK			0x2098
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_RSTNSYNC_CLK_APM_USI0_UART_IPCLKPORT_CLK		0x209c
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_RSTNSYNC_CLK_APM_USI0_USI_IPCLKPORT_CLK		0x20a0
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_RSTNSYNC_CLK_APM_USI1_UART_IPCLKPORT_CLK		0x20a4
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_SPEEDY_APM_IPCLKPORT_PCLK				0x20a8
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_SPEEDY_SUB_APM_IPCLKPORT_PCLK			0x20ac
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_SSMT_D_APM_IPCLKPORT_ACLK				0x20b0
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_SSMT_D_APM_IPCLKPORT_PCLK				0x20b4
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_SSMT_G_DBGCORE_IPCLKPORT_ACLK			0x20b8
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_SSMT_G_DBGCORE_IPCLKPORT_PCLK			0x20bc
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_SS_DBGCORE_IPCLKPORT_SS_DBGCORE_IPCLKPORT_HCLK	0x20c0
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_SYSMMU_D_APM_IPCLKPORT_CLK_S2			0x20c4
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_SYSREG_APM_IPCLKPORT_PCLK				0x20cc
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_APM_IPCLKPORT_ACLK				0x20d0
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_APM_IPCLKPORT_PCLK				0x20d4
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_DBGCORE_IPCLKPORT_ACLK			0x20d8
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_DBGCORE_IPCLKPORT_PCLK			0x20dc
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_G_SWD_IPCLKPORT_ACLK				0x20e0
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_G_SWD_IPCLKPORT_PCLK				0x20e4
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_P_AOCAPM_IPCLKPORT_ACLK			0x20e8
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_P_AOCAPM_IPCLKPORT_PCLK			0x20ec
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_P_APM_IPCLKPORT_ACLK				0x20f0
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_P_APM_IPCLKPORT_PCLK				0x20f4
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_WDT_APM_IPCLKPORT_PCLK				0x20f8
+#define CLK_CON_GAT_GOUT_BLK_APM_UID_XIU_DP_APM_IPCLKPORT_ACLK				0x20fc
+#define PCH_CON_LHM_AXI_G_SWD_PCH							0x3000
+#define PCH_CON_LHM_AXI_P_AOCAPM_PCH							0x3004
+#define PCH_CON_LHM_AXI_P_APM_PCH							0x3008
+#define PCH_CON_LHS_AXI_D_APM_PCH							0x300c
+#define PCH_CON_LHS_AXI_G_DBGCORE_PCH							0x3010
+#define PCH_CON_LHS_AXI_G_SCAN2DRAM_PCH							0x3014
+#define QCH_CON_APBIF_GPIO_ALIVE_QCH							0x3018
+#define QCH_CON_APBIF_GPIO_FAR_ALIVE_QCH						0x301c
+#define QCH_CON_APBIF_PMU_ALIVE_QCH							0x3020
+#define QCH_CON_APBIF_RTC_QCH								0x3024
+#define QCH_CON_APBIF_TRTC_QCH								0x3028
+#define QCH_CON_APM_CMU_APM_QCH								0x302c
+#define QCH_CON_APM_USI0_UART_QCH							0x3030
+#define QCH_CON_APM_USI0_USI_QCH							0x3034
+#define QCH_CON_APM_USI1_UART_QCH							0x3038
+#define QCH_CON_D_TZPC_APM_QCH								0x303c
+#define QCH_CON_GPC_APM_QCH								0x3040
+#define QCH_CON_GREBEINTEGRATION_QCH_DBG						0x3044
+#define QCH_CON_GREBEINTEGRATION_QCH_GREBE						0x3048
+#define QCH_CON_INTMEM_QCH								0x304c
+#define QCH_CON_LHM_AXI_G_SWD_QCH							0x3050
+#define QCH_CON_LHM_AXI_P_AOCAPM_QCH							0x3054
+#define QCH_CON_LHM_AXI_P_APM_QCH							0x3058
+#define QCH_CON_LHS_AXI_D_APM_QCH							0x305c
+#define QCH_CON_LHS_AXI_G_DBGCORE_QCH							0x3060
+#define QCH_CON_LHS_AXI_G_SCAN2DRAM_QCH							0x3064
+#define QCH_CON_MAILBOX_APM_AOC_QCH							0x3068
+#define QCH_CON_MAILBOX_APM_AP_QCH							0x306c
+#define QCH_CON_MAILBOX_APM_GSA_QCH							0x3070
+#define QCH_CON_MAILBOX_APM_SWD_QCH							0x3078
+#define QCH_CON_MAILBOX_APM_TPU_QCH							0x307c
+#define QCH_CON_MAILBOX_AP_AOC_QCH							0x3080
+#define QCH_CON_MAILBOX_AP_DBGCORE_QCH							0x3084
+#define QCH_CON_PMU_INTR_GEN_QCH							0x3088
+#define QCH_CON_ROM_CRC32_HOST_QCH							0x308c
+#define QCH_CON_RSTNSYNC_CLK_APM_BUS_QCH_GREBE						0x3090
+#define QCH_CON_RSTNSYNC_CLK_APM_BUS_QCH_GREBE_DBG					0x3094
+#define QCH_CON_SPEEDY_APM_QCH								0x3098
+#define QCH_CON_SPEEDY_SUB_APM_QCH							0x309c
+#define QCH_CON_SSMT_D_APM_QCH								0x30a0
+#define QCH_CON_SSMT_G_DBGCORE_QCH							0x30a4
+#define QCH_CON_SS_DBGCORE_QCH_DBG							0x30a8
+#define QCH_CON_SS_DBGCORE_QCH_GREBE							0x30ac
+#define QCH_CON_SYSMMU_D_APM_QCH							0x30b0
+#define QCH_CON_SYSREG_APM_QCH								0x30b8
+#define QCH_CON_UASC_APM_QCH								0x30bc
+#define QCH_CON_UASC_DBGCORE_QCH							0x30c0
+#define QCH_CON_UASC_G_SWD_QCH								0x30c4
+#define QCH_CON_UASC_P_AOCAPM_QCH							0x30c8
+#define QCH_CON_UASC_P_APM_QCH								0x30cc
+#define QCH_CON_WDT_APM_QCH								0x30d0
+#define QUEUE_CTRL_REG_BLK_APM_CMU_APM							0x3c00
+
+static const unsigned long apm_clk_regs[] __initconst = {
+	APM_CMU_APM_CONTROLLER_OPTION,
+	CLKOUT_CON_BLK_APM_CMU_APM_CLKOUT0,
+	CLK_CON_MUX_MUX_CLKCMU_APM_FUNC,
+	CLK_CON_MUX_MUX_CLKCMU_APM_FUNCSRC,
+	CLK_CON_DIV_DIV_CLK_APM_BOOST,
+	CLK_CON_DIV_DIV_CLK_APM_USI0_UART,
+	CLK_CON_DIV_DIV_CLK_APM_USI0_USI,
+	CLK_CON_DIV_DIV_CLK_APM_USI1_UART,
+	CLK_CON_GAT_CLK_BLK_APM_UID_APM_CMU_APM_IPCLKPORT_PCLK,
+	CLK_CON_GAT_CLK_BUS0_BOOST_OPTION1,
+	CLK_CON_GAT_CLK_CMU_BOOST_OPTION1,
+	CLK_CON_GAT_CLK_CORE_BOOST_OPTION1,
+	CLK_CON_GAT_GATE_CLKCMU_APM_FUNC,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_APBIF_GPIO_ALIVE_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_APBIF_GPIO_FAR_ALIVE_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_APBIF_PMU_ALIVE_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_APBIF_RTC_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_APBIF_TRTC_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_APM_USI0_UART_IPCLKPORT_IPCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_APM_USI0_UART_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_APM_USI0_USI_IPCLKPORT_IPCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_APM_USI0_USI_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_APM_USI1_UART_IPCLKPORT_IPCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_APM_USI1_UART_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_D_TZPC_APM_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_GPC_APM_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_GREBEINTEGRATION_IPCLKPORT_HCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_INTMEM_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_INTMEM_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_LHM_AXI_G_SWD_IPCLKPORT_I_CLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_LHM_AXI_P_AOCAPM_IPCLKPORT_I_CLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_LHM_AXI_P_APM_IPCLKPORT_I_CLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_LHS_AXI_D_APM_IPCLKPORT_I_CLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_LHS_AXI_G_DBGCORE_IPCLKPORT_I_CLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_LHS_AXI_G_SCAN2DRAM_IPCLKPORT_I_CLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_MAILBOX_APM_AOC_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_MAILBOX_APM_AP_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_MAILBOX_APM_GSA_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_MAILBOX_APM_SWD_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_MAILBOX_APM_TPU_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_MAILBOX_AP_AOC_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_MAILBOX_AP_DBGCORE_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_PMU_INTR_GEN_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_ROM_CRC32_HOST_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_ROM_CRC32_HOST_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_RSTNSYNC_CLK_APM_BUS_IPCLKPORT_CLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_RSTNSYNC_CLK_APM_USI0_UART_IPCLKPORT_CLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_RSTNSYNC_CLK_APM_USI0_USI_IPCLKPORT_CLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_RSTNSYNC_CLK_APM_USI1_UART_IPCLKPORT_CLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_SPEEDY_APM_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_SPEEDY_SUB_APM_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_SSMT_D_APM_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_SSMT_D_APM_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_SSMT_G_DBGCORE_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_SSMT_G_DBGCORE_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_SS_DBGCORE_IPCLKPORT_SS_DBGCORE_IPCLKPORT_HCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_SYSMMU_D_APM_IPCLKPORT_CLK_S2,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_SYSREG_APM_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_APM_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_APM_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_DBGCORE_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_DBGCORE_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_G_SWD_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_G_SWD_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_P_AOCAPM_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_P_AOCAPM_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_P_APM_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_P_APM_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_WDT_APM_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_APM_UID_XIU_DP_APM_IPCLKPORT_ACLK,
+};
+
+PNAME(mout_apm_func_p)		= { "oscclk", "mout_apm_funcsrc",
+				    "pad_clk_apm", "oscclk" };
+PNAME(mout_apm_funcsrc_p)	= { "pll_alv_div2_apm", "pll_alv_div4_apm",
+				    "pll_alv_div16_apm" };
+
+static const struct samsung_fixed_rate_clock apm_fixed_clks[] __initconst = {
+	FRATE(CLK_APM_PLL_DIV2_APM, "pll_alv_div2_apm", NULL, 0, 393216000),
+	FRATE(CLK_APM_PLL_DIV4_APM, "pll_alv_div4_apm", NULL, 0, 196608000),
+	FRATE(CLK_APM_PLL_DIV16_APM, "pll_alv_div16_apm", NULL, 0, 49152000),
+};
+
+static const struct samsung_mux_clock apm_mux_clks[] __initconst = {
+	MUX(CLK_MOUT_APM_FUNC, "mout_apm_func", mout_apm_func_p,
+	    CLK_CON_MUX_MUX_CLKCMU_APM_FUNC, 4, 1),
+	MUX(CLK_MOUT_APM_FUNCSRC, "mout_apm_funcsrc", mout_apm_funcsrc_p,
+	    CLK_CON_MUX_MUX_CLKCMU_APM_FUNCSRC, 3, 1),
+};
+
+static const struct samsung_div_clock apm_div_clks[] __initconst = {
+	DIV(CLK_DOUT_APM_BOOST, "dout_apm_boost", "gout_apm_func",
+	    CLK_CON_DIV_DIV_CLK_APM_BOOST, 0, 1),
+	DIV(CLK_DOUT_APM_USI0_UART, "dout_apm_usi0_uart", "gout_apm_func",
+	    CLK_CON_DIV_DIV_CLK_APM_USI0_UART, 0, 7),
+	DIV(CLK_DOUT_APM_USI0_USI, "dout_apm_usi0_usi", "gout_apm_func",
+	    CLK_CON_DIV_DIV_CLK_APM_USI0_USI, 0, 7),
+	DIV(CLK_DOUT_APM_USI1_UART, "dout_apm_usi1_uart", "gout_apm_func",
+	    CLK_CON_DIV_DIV_CLK_APM_USI1_UART, 0, 7),
+};
+
+static const struct samsung_gate_clock apm_gate_clks[] __initconst = {
+	GATE(CLK_GOUT_APM_APM_CMU_APM_PCLK,
+	     "gout_apm_apm_cmu_apm_pclk", "mout_apm_func",
+	     CLK_CON_GAT_CLK_BLK_APM_UID_APM_CMU_APM_IPCLKPORT_PCLK, 21, 0, 0),
+	GATE(CLK_GOUT_BUS0_BOOST_OPTION1, "gout_bus0_boost_option1",
+	     "dout_apm_boost", CLK_CON_GAT_CLK_BUS0_BOOST_OPTION1, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_BOOST_OPTION1, "gout_cmu_boost_option1",
+	     "dout_apm_boost", CLK_CON_GAT_CLK_CMU_BOOST_OPTION1, 21, 0, 0),
+	GATE(CLK_GOUT_CORE_BOOST_OPTION1, "gout_core_boost_option1",
+	     "dout_apm_boost", CLK_CON_GAT_CLK_CORE_BOOST_OPTION1, 21, 0, 0),
+	GATE(CLK_GOUT_APM_FUNC, "gout_apm_func", "mout_apm_func",
+	     CLK_CON_GAT_GATE_CLKCMU_APM_FUNC, 21, 0, 0),
+	GATE(CLK_GOUT_APM_APBIF_GPIO_ALIVE_PCLK,
+	     "gout_apm_apbif_gpio_alive_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_APBIF_GPIO_ALIVE_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_APBIF_GPIO_FAR_ALIVE_PCLK,
+	     "gout_apm_apbif_gpio_far_alive_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_APBIF_GPIO_FAR_ALIVE_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_APBIF_PMU_ALIVE_PCLK,
+	     "gout_apm_apbif_pmu_alive_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_APBIF_PMU_ALIVE_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_APBIF_RTC_PCLK,
+	     "gout_apm_apbif_rtc_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_APBIF_RTC_IPCLKPORT_PCLK, 21, 0, 0),
+	GATE(CLK_GOUT_APM_APBIF_TRTC_PCLK,
+	     "gout_apm_apbif_trtc_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_APBIF_TRTC_IPCLKPORT_PCLK, 21, 0, 0),
+	GATE(CLK_GOUT_APM_APM_USI0_UART_IPCLK,
+	     "gout_apm_apm_usi0_uart_ipclk", "dout_apm_usi0_uart",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_APM_USI0_UART_IPCLKPORT_IPCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_APM_USI0_UART_PCLK,
+	     "gout_apm_apm_usi0_uart_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_APM_USI0_UART_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_APM_USI0_USI_IPCLK,
+	     "gout_apm_apm_usi0_usi_ipclk", "dout_apm_usi0_usi",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_APM_USI0_USI_IPCLKPORT_IPCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_APM_USI0_USI_PCLK,
+	     "gout_apm_apm_usi0_usi_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_APM_USI0_USI_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_APM_USI1_UART_IPCLK,
+	     "gout_apm_apm_usi1_uart_ipclk", "dout_apm_usi1_uart",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_APM_USI1_UART_IPCLKPORT_IPCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_APM_USI1_UART_PCLK,
+	     "gout_apm_apm_usi1_uart_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_APM_USI1_UART_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_D_TZPC_APM_PCLK,
+	     "gout_apm_d_tzpc_apm_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_D_TZPC_APM_IPCLKPORT_PCLK, 21, 0, 0),
+	GATE(CLK_GOUT_APM_GPC_APM_PCLK,
+	     "gout_apm_gpc_apm_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_GPC_APM_IPCLKPORT_PCLK, 21, 0, 0),
+	GATE(CLK_GOUT_APM_GREBEINTEGRATION_HCLK,
+	     "gout_apm_grebeintegration_hclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_GREBEINTEGRATION_IPCLKPORT_HCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_INTMEM_ACLK,
+	     "gout_apm_intmem_aclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_INTMEM_IPCLKPORT_ACLK, 21, 0, 0),
+	GATE(CLK_GOUT_APM_INTMEM_PCLK,
+	     "gout_apm_intmem_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_INTMEM_IPCLKPORT_PCLK, 21, 0, 0),
+	GATE(CLK_GOUT_APM_LHM_AXI_G_SWD_I_CLK,
+	     "gout_apm_lhm_axi_g_swd_i_clk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_LHM_AXI_G_SWD_IPCLKPORT_I_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_LHM_AXI_P_AOCAPM_I_CLK,
+	     "gout_apm_lhm_axi_p_aocapm_i_clk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_LHM_AXI_P_AOCAPM_IPCLKPORT_I_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_LHM_AXI_P_APM_I_CLK,
+	     "gout_apm_lhm_axi_p_apm_i_clk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_LHS_AXI_D_APM_IPCLKPORT_I_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_LHS_AXI_D_APM_I_CLK,
+	     "gout_apm_lhs_axi_d_apm_i_clk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_LHS_AXI_D_APM_IPCLKPORT_I_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_LHS_AXI_G_DBGCORE_I_CLK,
+	     "gout_apm_lhs_axi_g_dbgcore_i_clk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_LHS_AXI_G_DBGCORE_IPCLKPORT_I_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_LHS_AXI_G_SCAN2DRAM_I_CLK,
+	     "gout_apm_lhs_axi_g_scan2dram_i_clk",
+	     "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_LHS_AXI_G_SCAN2DRAM_IPCLKPORT_I_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_MAILBOX_APM_AOC_PCLK,
+	     "gout_apm_mailbox_apm_aoc_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_MAILBOX_APM_AOC_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_MAILBOX_APM_AP_PCLK,
+	     "gout_apm_mailbox_apm_ap_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_MAILBOX_APM_AP_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_MAILBOX_APM_GSA_PCLK,
+	     "gout_apm_mailbox_apm_gsa_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_MAILBOX_APM_GSA_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_MAILBOX_APM_SWD_PCLK,
+	     "gout_apm_mailbox_apm_swd_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_MAILBOX_APM_SWD_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_MAILBOX_APM_TPU_PCLK,
+	     "gout_apm_mailbox_apm_tpu_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_MAILBOX_APM_TPU_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_MAILBOX_AP_AOC_PCLK,
+	     "gout_apm_mailbox_ap_aoc_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_MAILBOX_AP_AOC_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_MAILBOX_AP_DBGCORE_PCLK,
+	     "gout_apm_mailbox_ap_dbgcore_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_MAILBOX_AP_DBGCORE_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_PMU_INTR_GEN_PCLK,
+	     "gout_apm_pmu_intr_gen_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_PMU_INTR_GEN_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_ROM_CRC32_HOST_ACLK,
+	     "gout_apm_rom_crc32_host_aclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_ROM_CRC32_HOST_IPCLKPORT_ACLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_ROM_CRC32_HOST_PCLK,
+	     "gout_apm_rom_crc32_host_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_ROM_CRC32_HOST_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_CLK_APM_BUS_CLK,
+	     "gout_apm_clk_apm_bus_clk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_RSTNSYNC_CLK_APM_BUS_IPCLKPORT_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_CLK_APM_USI0_UART_CLK,
+	     "gout_apm_clk_apm_usi0_uart_clk",
+	     "dout_apm_usi0_uart",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_RSTNSYNC_CLK_APM_USI0_UART_IPCLKPORT_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_CLK_APM_USI0_USI_CLK,
+	     "gout_apm_clk_apm_usi0_usi_clk",
+	     "dout_apm_usi0_usi",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_RSTNSYNC_CLK_APM_USI0_UART_IPCLKPORT_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_CLK_APM_USI1_UART_CLK,
+	     "gout_apm_clk_apm_usi1_uart_clk",
+	     "dout_apm_usi1_uart",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_RSTNSYNC_CLK_APM_USI1_UART_IPCLKPORT_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_SPEEDY_APM_PCLK,
+	     "gout_apm_speedy_apm_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_SPEEDY_APM_IPCLKPORT_PCLK, 21, 0, 0),
+	GATE(CLK_GOUT_APM_SPEEDY_SUB_APM_PCLK,
+	     "gout_apm_speedy_sub_apm_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_SPEEDY_SUB_APM_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_SSMT_D_APM_ACLK,
+	     "gout_apm_ssmt_d_apm_aclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_SSMT_D_APM_IPCLKPORT_ACLK, 21, 0, 0),
+	GATE(CLK_GOUT_APM_SSMT_D_APM_PCLK,
+	     "gout_apm_ssmt_d_apm_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_SSMT_D_APM_IPCLKPORT_PCLK, 21, 0, 0),
+	GATE(CLK_GOUT_APM_SSMT_G_DBGCORE_ACLK,
+	     "gout_apm_ssmt_g_dbgcore_aclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_SSMT_G_DBGCORE_IPCLKPORT_ACLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_SSMT_G_DBGCORE_PCLK,
+	     "gout_apm_ssmt_g_dbgcore_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_SSMT_G_DBGCORE_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_SS_DBGCORE_SS_DBGCORE_HCLK,
+	     "gout_apm_ss_dbgcore_ss_dbgcore_hclk",
+	     "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_SS_DBGCORE_IPCLKPORT_SS_DBGCORE_IPCLKPORT_HCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_SYSMMU_D_APM_CLK_S2,
+	     "gout_apm_sysmmu_d_dpm_clk_s2", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_SYSMMU_D_APM_IPCLKPORT_CLK_S2,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_SYSREG_APM_PCLK,
+	     "gout_apm_sysreg_apm_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_SYSREG_APM_IPCLKPORT_PCLK, 21, 0, 0),
+	GATE(CLK_GOUT_APM_UASC_APM_ACLK,
+	     "gout_apm_uasc_apm_aclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_APM_IPCLKPORT_ACLK, 21, 0, 0),
+	GATE(CLK_GOUT_APM_UASC_APM_PCLK,
+	     "gout_apm_uasc_apm_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_APM_IPCLKPORT_PCLK, 21, 0, 0),
+	GATE(CLK_GOUT_APM_UASC_DBGCORE_ACLK,
+	     "gout_apm_uasc_dbgcore_aclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_DBGCORE_IPCLKPORT_ACLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_UASC_DBGCORE_PCLK,
+	     "gout_apm_uasc_dbgcore_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_DBGCORE_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_UASC_G_SWD_ACLK,
+	     "gout_apm_uasc_g_swd_aclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_G_SWD_IPCLKPORT_ACLK, 21, 0, 0),
+	GATE(CLK_GOUT_APM_UASC_G_SWD_PCLK,
+	     "gout_apm_uasc_g_swd_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_G_SWD_IPCLKPORT_PCLK, 21, 0, 0),
+	GATE(CLK_GOUT_APM_UASC_P_AOCAPM_ACLK,
+	     "gout_apm_uasc_p_aocapm_aclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_P_AOCAPM_IPCLKPORT_ACLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_APM_UASC_P_AOCAPM_PCLK,
+	     "gout_apm_uasc_p_aocapm_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_G_SWD_IPCLKPORT_PCLK, 21, 0, 0),
+	GATE(CLK_GOUT_APM_UASC_P_APM_ACLK,
+	     "gout_apm_uasc_p_apm_aclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_P_APM_IPCLKPORT_ACLK, 21, 0, 0),
+	GATE(CLK_GOUT_APM_UASC_P_APM_PCLK,
+	     "gout_apm_uasc_p_apm_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_UASC_P_APM_IPCLKPORT_PCLK, 21, 0, 0),
+	GATE(CLK_GOUT_APM_WDT_APM_PCLK,
+	     "gout_apm_wdt_apm_pclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_WDT_APM_IPCLKPORT_PCLK, 21, 0, 0),
+	GATE(CLK_GOUT_APM_XIU_DP_APM_ACLK,
+	     "gout_apm_xiu_dp_apm_aclk", "gout_apm_func",
+	     CLK_CON_GAT_GOUT_BLK_APM_UID_XIU_DP_APM_IPCLKPORT_ACLK, 21, 0, 0),
+};
+
+static const struct samsung_cmu_info apm_cmu_info __initconst = {
+	.mux_clks		= apm_mux_clks,
+	.nr_mux_clks		= ARRAY_SIZE(apm_mux_clks),
+	.div_clks		= apm_div_clks,
+	.nr_div_clks		= ARRAY_SIZE(apm_div_clks),
+	.gate_clks		= apm_gate_clks,
+	.nr_gate_clks		= ARRAY_SIZE(apm_gate_clks),
+	.fixed_clks		= apm_fixed_clks,
+	.nr_fixed_clks		= ARRAY_SIZE(apm_fixed_clks),
+	.nr_clk_ids		= CLKS_NR_APM,
+	.clk_regs		= apm_clk_regs,
+	.nr_clk_regs		= ARRAY_SIZE(apm_clk_regs),
+};
+
+/* ---- CMU_MISC ------------------------------------------------------------ */
+
+/* Register Offset definitions for CMU_MISC (0x10010000) */
+#define PLL_CON0_MUX_CLKCMU_MISC_BUS_USER					0x0600
+#define PLL_CON1_MUX_CLKCMU_MISC_BUS_USER					0x0604
+#define PLL_CON0_MUX_CLKCMU_MISC_SSS_USER					0x0610
+#define PLL_CON1_MUX_CLKCMU_MISC_SSS_USER					0x0614
+#define MISC_CMU_MISC_CONTROLLER_OPTION						0x0800
+#define CLKOUT_CON_BLK_MISC_CMU_MISC_CLKOUT0					0x0810
+#define CLK_CON_MUX_MUX_CLK_MISC_GIC						0x1000
+#define CLK_CON_DIV_DIV_CLK_MISC_BUSP						0x1800
+#define CLK_CON_DIV_DIV_CLK_MISC_GIC						0x1804
+#define CLK_CON_GAT_CLK_BLK_MISC_UID_MISC_CMU_MISC_IPCLKPORT_PCLK		0x2000
+#define CLK_CON_GAT_CLK_BLK_MISC_UID_OTP_CON_BIRA_IPCLKPORT_I_OSCCLK		0x2004
+#define CLK_CON_GAT_CLK_BLK_MISC_UID_OTP_CON_BISR_IPCLKPORT_I_OSCCLK		0x2008
+#define CLK_CON_GAT_CLK_BLK_MISC_UID_OTP_CON_TOP_IPCLKPORT_I_OSCCLK		0x200c
+#define CLK_CON_GAT_CLK_BLK_MISC_UID_RSTNSYNC_CLK_MISC_OSCCLK_IPCLKPORT_CLK	0x2010
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_ADM_AHB_SSS_IPCLKPORT_HCLKM		0x2014
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_AD_APB_DIT_IPCLKPORT_PCLKM		0x2018
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_AD_APB_PUF_IPCLKPORT_PCLKM		0x201c
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_DIT_IPCLKPORT_ICLKL2A			0x2020
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_D_TZPC_MISC_IPCLKPORT_PCLK		0x2024
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_GIC_IPCLKPORT_GICCLK			0x2028
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_GPC_MISC_IPCLKPORT_PCLK			0x202c
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_LHM_AST_ICC_CPUGIC_IPCLKPORT_I_CLK	0x2030
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_LHM_AXI_D_SSS_IPCLKPORT_I_CLK		0x2034
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_LHM_AXI_P_GIC_IPCLKPORT_I_CLK		0x2038
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_LHM_AXI_P_MISC_IPCLKPORT_I_CLK		0x203c
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_LHS_ACEL_D_MISC_IPCLKPORT_I_CLK		0x2040
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_LHS_AST_IRI_GICCPU_IPCLKPORT_I_CLK	0x2044
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_LHS_AXI_D_SSS_IPCLKPORT_I_CLK		0x2048
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_MCT_IPCLKPORT_PCLK			0x204c
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_OTP_CON_BIRA_IPCLKPORT_PCLK		0x2050
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_OTP_CON_BISR_IPCLKPORT_PCLK		0x2054
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_OTP_CON_TOP_IPCLKPORT_PCLK		0x2058
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_PDMA_IPCLKPORT_ACLK			0x205c
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_PPMU_DMA_IPCLKPORT_ACLK			0x2060
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_PPMU_MISC_IPCLKPORT_ACLK			0x2064
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_PPMU_MISC_IPCLKPORT_PCLK			0x2068
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_PUF_IPCLKPORT_I_CLK			0x206c
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_DIT_IPCLKPORT_ACLK			0x2070
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_DIT_IPCLKPORT_PCLK			0x2074
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_PDMA_IPCLKPORT_ACLK			0x2078
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_PDMA_IPCLKPORT_PCLK			0x207c
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_PPMU_DMA_IPCLKPORT_ACLK		0x2080
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_PPMU_DMA_IPCLKPORT_PCLK		0x2084
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_RTIC_IPCLKPORT_ACLK			0x2088
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_RTIC_IPCLKPORT_PCLK			0x208c
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_SPDMA_IPCLKPORT_ACLK			0x2090
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_SPDMA_IPCLKPORT_PCLK			0x2094
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_SSS_IPCLKPORT_ACLK			0x2098
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_SSS_IPCLKPORT_PCLK			0x209c
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_RSTNSYNC_CLK_MISC_BUSD_IPCLKPORT_CLK	0x20a0
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_RSTNSYNC_CLK_MISC_BUSP_IPCLKPORT_CLK	0x20a4
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_RSTNSYNC_CLK_MISC_GIC_IPCLKPORT_CLK	0x20a8
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_RSTNSYNC_CLK_MISC_SSS_IPCLKPORT_CLK	0x20ac
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_RTIC_IPCLKPORT_I_ACLK			0x20b0
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_RTIC_IPCLKPORT_I_PCLK			0x20b4
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_SPDMA_IPCLKPORT_ACLK			0x20b8
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_DIT_IPCLKPORT_ACLK			0x20bc
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_DIT_IPCLKPORT_PCLK			0x20c0
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_PDMA_IPCLKPORT_ACLK			0x20c4
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_PDMA_IPCLKPORT_PCLK			0x20c8
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_PPMU_DMA_IPCLKPORT_ACLK		0x20cc
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_PPMU_DMA_IPCLKPORT_PCLK		0x20d0
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_RTIC_IPCLKPORT_ACLK			0x20d4
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_RTIC_IPCLKPORT_PCLK			0x20d8
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_SPDMA_IPCLKPORT_ACLK			0x20dc
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_SPDMA_IPCLKPORT_PCLK			0x20e0
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_SSS_IPCLKPORT_ACLK			0x20e4
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_SSS_IPCLKPORT_PCLK			0x20e8
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_SSS_IPCLKPORT_I_ACLK			0x20ec
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_SSS_IPCLKPORT_I_PCLK			0x20f0
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_SYSMMU_MISC_IPCLKPORT_CLK_S2		0x20f4
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_SYSMMU_SSS_IPCLKPORT_CLK_S1		0x20f8
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_SYSREG_MISC_IPCLKPORT_PCLK		0x20fc
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_TMU_SUB_IPCLKPORT_PCLK			0x2100
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_TMU_TOP_IPCLKPORT_PCLK			0x2104
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_WDT_CLUSTER0_IPCLKPORT_PCLK		0x2108
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_WDT_CLUSTER1_IPCLKPORT_PCLK		0x210c
+#define CLK_CON_GAT_GOUT_BLK_MISC_UID_XIU_D_MISC_IPCLKPORT_ACLK			0x2110
+#define DMYQCH_CON_PPMU_DMA_QCH							0x3000
+#define DMYQCH_CON_PUF_QCH							0x3004
+#define PCH_CON_LHM_AXI_D_SSS_PCH						0x300c
+#define PCH_CON_LHM_AXI_P_GIC_PCH						0x3010
+#define PCH_CON_LHM_AXI_P_MISC_PCH						0x3014
+#define PCH_CON_LHS_ACEL_D_MISC_PCH						0x3018
+#define PCH_CON_LHS_AST_IRI_GICCPU_PCH						0x301c
+#define PCH_CON_LHS_AXI_D_SSS_PCH						0x3020
+#define QCH_CON_ADM_AHB_SSS_QCH							0x3024
+#define QCH_CON_DIT_QCH								0x3028
+#define QCH_CON_GIC_QCH								0x3030
+#define QCH_CON_LHM_AST_ICC_CPUGIC_QCH						0x3038
+#define QCH_CON_LHM_AXI_D_SSS_QCH						0x303c
+#define QCH_CON_LHM_AXI_P_GIC_QCH						0x3040
+#define QCH_CON_LHM_AXI_P_MISC_QCH						0x3044
+#define QCH_CON_LHS_ACEL_D_MISC_QCH						0x3048
+#define QCH_CON_LHS_AST_IRI_GICCPU_QCH						0x304c
+#define QCH_CON_LHS_AXI_D_SSS_QCH						0x3050
+#define QCH_CON_MCT_QCH								0x3054
+#define QCH_CON_MISC_CMU_MISC_QCH						0x3058
+#define QCH_CON_OTP_CON_BIRA_QCH						0x305c
+#define QCH_CON_OTP_CON_BISR_QCH						0x3060
+#define QCH_CON_OTP_CON_TOP_QCH							0x3064
+#define QCH_CON_PDMA_QCH							0x3068
+#define QCH_CON_PPMU_MISC_QCH							0x306c
+#define QCH_CON_QE_DIT_QCH							0x3070
+#define QCH_CON_QE_PDMA_QCH							0x3074
+#define QCH_CON_QE_PPMU_DMA_QCH							0x3078
+#define QCH_CON_QE_RTIC_QCH							0x307c
+#define QCH_CON_QE_SPDMA_QCH							0x3080
+#define QCH_CON_QE_SSS_QCH							0x3084
+#define QCH_CON_RTIC_QCH							0x3088
+#define QCH_CON_SPDMA_QCH							0x308c
+#define QCH_CON_SSMT_DIT_QCH							0x3090
+#define QCH_CON_SSMT_PDMA_QCH							0x3094
+#define QCH_CON_SSMT_PPMU_DMA_QCH						0x3098
+#define QCH_CON_SSMT_RTIC_QCH							0x309c
+#define QCH_CON_SSMT_SPDMA_QCH							0x30a0
+#define QCH_CON_SSMT_SSS_QCH							0x30a4
+#define QCH_CON_SSS_QCH								0x30a8
+#define QCH_CON_SYSMMU_MISC_QCH							0x30ac
+#define QCH_CON_SYSMMU_SSS_QCH							0x30b0
+#define QCH_CON_SYSREG_MISC_QCH							0x30b4
+#define QCH_CON_TMU_SUB_QCH							0x30b8
+#define QCH_CON_TMU_TOP_QCH							0x30bc
+#define QCH_CON_WDT_CLUSTER0_QCH						0x30c0
+#define QCH_CON_WDT_CLUSTER1_QCH						0x30c4
+#define QUEUE_CTRL_REG_BLK_MISC_CMU_MISC					0x3c00
+
+static const unsigned long misc_clk_regs[] __initconst = {
+	PLL_CON0_MUX_CLKCMU_MISC_BUS_USER,
+	PLL_CON1_MUX_CLKCMU_MISC_BUS_USER,
+	PLL_CON0_MUX_CLKCMU_MISC_SSS_USER,
+	PLL_CON1_MUX_CLKCMU_MISC_SSS_USER,
+	MISC_CMU_MISC_CONTROLLER_OPTION,
+	CLKOUT_CON_BLK_MISC_CMU_MISC_CLKOUT0,
+	CLK_CON_MUX_MUX_CLK_MISC_GIC,
+	CLK_CON_DIV_DIV_CLK_MISC_BUSP,
+	CLK_CON_DIV_DIV_CLK_MISC_GIC,
+	CLK_CON_GAT_CLK_BLK_MISC_UID_MISC_CMU_MISC_IPCLKPORT_PCLK,
+	CLK_CON_GAT_CLK_BLK_MISC_UID_OTP_CON_BIRA_IPCLKPORT_I_OSCCLK,
+	CLK_CON_GAT_CLK_BLK_MISC_UID_OTP_CON_BISR_IPCLKPORT_I_OSCCLK,
+	CLK_CON_GAT_CLK_BLK_MISC_UID_OTP_CON_TOP_IPCLKPORT_I_OSCCLK,
+	CLK_CON_GAT_CLK_BLK_MISC_UID_RSTNSYNC_CLK_MISC_OSCCLK_IPCLKPORT_CLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_ADM_AHB_SSS_IPCLKPORT_HCLKM,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_AD_APB_DIT_IPCLKPORT_PCLKM,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_AD_APB_PUF_IPCLKPORT_PCLKM,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_DIT_IPCLKPORT_ICLKL2A,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_D_TZPC_MISC_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_GIC_IPCLKPORT_GICCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_GPC_MISC_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_LHM_AST_ICC_CPUGIC_IPCLKPORT_I_CLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_LHM_AXI_D_SSS_IPCLKPORT_I_CLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_LHM_AXI_P_GIC_IPCLKPORT_I_CLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_LHM_AXI_P_MISC_IPCLKPORT_I_CLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_LHS_ACEL_D_MISC_IPCLKPORT_I_CLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_LHS_AST_IRI_GICCPU_IPCLKPORT_I_CLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_LHS_AXI_D_SSS_IPCLKPORT_I_CLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_MCT_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_OTP_CON_BIRA_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_OTP_CON_BISR_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_OTP_CON_TOP_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_PDMA_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_PPMU_DMA_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_PPMU_MISC_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_PPMU_MISC_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_PUF_IPCLKPORT_I_CLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_DIT_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_DIT_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_PDMA_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_PDMA_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_PPMU_DMA_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_PPMU_DMA_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_RTIC_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_RTIC_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_SPDMA_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_SPDMA_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_SSS_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_SSS_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_RSTNSYNC_CLK_MISC_BUSD_IPCLKPORT_CLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_RSTNSYNC_CLK_MISC_BUSP_IPCLKPORT_CLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_RSTNSYNC_CLK_MISC_GIC_IPCLKPORT_CLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_RSTNSYNC_CLK_MISC_SSS_IPCLKPORT_CLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_RTIC_IPCLKPORT_I_ACLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_RTIC_IPCLKPORT_I_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_SPDMA_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_DIT_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_DIT_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_PDMA_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_PDMA_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_PPMU_DMA_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_PPMU_DMA_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_RTIC_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_RTIC_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_SPDMA_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_SPDMA_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_SSS_IPCLKPORT_ACLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_SSS_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_SSS_IPCLKPORT_I_ACLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_SSS_IPCLKPORT_I_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_SYSMMU_MISC_IPCLKPORT_CLK_S2,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_SYSMMU_SSS_IPCLKPORT_CLK_S1,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_SYSREG_MISC_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_TMU_SUB_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_TMU_TOP_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_WDT_CLUSTER0_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_WDT_CLUSTER1_IPCLKPORT_PCLK,
+	CLK_CON_GAT_GOUT_BLK_MISC_UID_XIU_D_MISC_IPCLKPORT_ACLK,
+	DMYQCH_CON_PPMU_DMA_QCH,
+	DMYQCH_CON_PUF_QCH,
+	PCH_CON_LHM_AXI_D_SSS_PCH,
+	PCH_CON_LHM_AXI_P_GIC_PCH,
+	PCH_CON_LHM_AXI_P_MISC_PCH,
+	PCH_CON_LHS_ACEL_D_MISC_PCH,
+	PCH_CON_LHS_AST_IRI_GICCPU_PCH,
+	PCH_CON_LHS_AXI_D_SSS_PCH,
+	QCH_CON_ADM_AHB_SSS_QCH,
+	QCH_CON_DIT_QCH,
+	QCH_CON_GIC_QCH,
+	QCH_CON_LHM_AST_ICC_CPUGIC_QCH,
+	QCH_CON_LHM_AXI_D_SSS_QCH,
+	QCH_CON_LHM_AXI_P_GIC_QCH,
+	QCH_CON_LHM_AXI_P_MISC_QCH,
+	QCH_CON_LHS_ACEL_D_MISC_QCH,
+	QCH_CON_LHS_AST_IRI_GICCPU_QCH,
+	QCH_CON_LHS_AXI_D_SSS_QCH,
+	QCH_CON_MCT_QCH,
+	QCH_CON_MISC_CMU_MISC_QCH,
+	QCH_CON_OTP_CON_BIRA_QCH,
+	QCH_CON_OTP_CON_BISR_QCH,
+	QCH_CON_OTP_CON_TOP_QCH,
+	QCH_CON_PDMA_QCH,
+	QCH_CON_PPMU_MISC_QCH,
+	QCH_CON_QE_DIT_QCH,
+	QCH_CON_QE_PDMA_QCH,
+	QCH_CON_QE_PPMU_DMA_QCH,
+	QCH_CON_QE_RTIC_QCH,
+	QCH_CON_QE_SPDMA_QCH,
+	QCH_CON_QE_SSS_QCH,
+	QCH_CON_RTIC_QCH,
+	QCH_CON_SPDMA_QCH,
+	QCH_CON_SSMT_DIT_QCH,
+	QCH_CON_SSMT_PDMA_QCH,
+	QCH_CON_SSMT_PPMU_DMA_QCH,
+	QCH_CON_SSMT_RTIC_QCH,
+	QCH_CON_SSMT_SPDMA_QCH,
+	QCH_CON_SSMT_SSS_QCH,
+	QCH_CON_SSS_QCH,
+	QCH_CON_SYSMMU_MISC_QCH,
+	QCH_CON_SYSMMU_SSS_QCH,
+	QCH_CON_SYSREG_MISC_QCH,
+	QCH_CON_TMU_SUB_QCH,
+	QCH_CON_TMU_TOP_QCH,
+	QCH_CON_WDT_CLUSTER0_QCH,
+	QCH_CON_WDT_CLUSTER1_QCH,
+	QUEUE_CTRL_REG_BLK_MISC_CMU_MISC,
+};
+
+ /* List of parent clocks for Muxes in CMU_MISC */
+PNAME(mout_misc_bus_user_p)		= { "oscclk", "dout_cmu_misc_bus" };
+PNAME(mout_misc_sss_user_p)		= { "oscclk", "dout_cmu_misc_sss" };
+PNAME(mout_misc_gic_p)			= { "dout_misc_gic", "oscclk" };
+
+static const struct samsung_mux_clock misc_mux_clks[] __initconst = {
+	MUX(CLK_MOUT_MISC_BUS_USER, "mout_misc_bus_user", mout_misc_bus_user_p,
+	    PLL_CON0_MUX_CLKCMU_MISC_BUS_USER, 4, 1),
+	MUX(CLK_MOUT_MISC_SSS_USER, "mout_misc_sss_user", mout_misc_sss_user_p,
+	    PLL_CON0_MUX_CLKCMU_MISC_SSS_USER, 4, 1),
+	MUX(CLK_MOUT_MISC_GIC, "mout_misc_gic", mout_misc_gic_p,
+	    CLK_CON_MUX_MUX_CLK_MISC_GIC, 0, 0),
+};
+
+static const struct samsung_div_clock misc_div_clks[] __initconst = {
+	DIV(CLK_DOUT_MISC_BUSP, "dout_misc_busp", "mout_misc_bus_user",
+	    CLK_CON_DIV_DIV_CLK_MISC_BUSP, 0, 3),
+	DIV(CLK_DOUT_MISC_GIC, "dout_misc_gic", "mout_misc_bus_user",
+	    CLK_CON_DIV_DIV_CLK_MISC_GIC, 0, 3),
+};
+
+static const struct samsung_gate_clock misc_gate_clks[] __initconst = {
+	GATE(CLK_GOUT_MISC_MISC_CMU_MISC_PCLK,
+	     "gout_misc_misc_cmu_misc_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_CLK_BLK_MISC_UID_MISC_CMU_MISC_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_OTP_CON_BIRA_I_OSCCLK,
+	     "gout_misc_otp_con_bira_i_oscclk", "oscclk",
+	     CLK_CON_GAT_CLK_BLK_MISC_UID_OTP_CON_BIRA_IPCLKPORT_I_OSCCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_OTP_CON_BISR_I_OSCCLK,
+	     "gout_misc_otp_con_bisr_i_oscclk", "oscclk",
+	     CLK_CON_GAT_CLK_BLK_MISC_UID_OTP_CON_BISR_IPCLKPORT_I_OSCCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_OTP_CON_TOP_I_OSCCLK,
+	     "gout_misc_otp_con_top_i_oscclk", "oscclk",
+	     CLK_CON_GAT_CLK_BLK_MISC_UID_OTP_CON_TOP_IPCLKPORT_I_OSCCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_CLK_MISC_OSCCLK_CLK,
+	     "gout_misc_clk_misc_oscclk_clk", "oscclk",
+	     CLK_CON_GAT_CLK_BLK_MISC_UID_RSTNSYNC_CLK_MISC_OSCCLK_IPCLKPORT_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_ADM_AHB_SSS_HCLKM,
+	     "gout_misc_adm_ahb_sss_hclkm", "mout_misc_sss_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_ADM_AHB_SSS_IPCLKPORT_HCLKM,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_AD_APB_DIT_PCLKM,
+	     "gout_misc_ad_apb_dit_pclkm", "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_AD_APB_DIT_IPCLKPORT_PCLKM,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_D_TZPC_MISC_PCLK,
+	     "gout_misc_d_tzpc_misc_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_D_TZPC_MISC_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_GIC_GICCLK,
+	     "gout_misc_gic_gicclk", "mout_misc_gic",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_GIC_IPCLKPORT_GICCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_GPC_MISC_PCLK,
+	     "gout_misc_gpc_misc_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_GPC_MISC_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_LHM_AST_ICC_CPUGIC_I_CLK,
+	     "gout_misc_lhm_ast_icc_gpugic_i_clk", "mout_misc_gic",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_LHM_AST_ICC_CPUGIC_IPCLKPORT_I_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_LHM_AXI_D_SSS_I_CLK,
+	     "gout_misc_lhm_axi_d_sss_i_clk", "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_LHM_AXI_D_SSS_IPCLKPORT_I_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_LHM_AXI_P_GIC_I_CLK,
+	     "gout_misc_lhm_axi_p_gic_i_clk", "mout_misc_gic",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_LHM_AXI_P_GIC_IPCLKPORT_I_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_LHM_AXI_P_MISC_I_CLK,
+	     "gout_misc_lhm_axi_p_misc_i_clk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_LHM_AXI_P_MISC_IPCLKPORT_I_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_LHS_ACEL_D_MISC_I_CLK,
+	     "gout_misc_lhs_acel_d_misc_i_clk", "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_LHS_ACEL_D_MISC_IPCLKPORT_I_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_LHS_AST_IRI_GICCPU_I_CLK,
+	     "gout_misc_lhs_ast_iri_giccpu_i_clk", "mout_misc_gic",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_LHS_AST_IRI_GICCPU_IPCLKPORT_I_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_LHS_AXI_D_SSS_I_CLK,
+	     "gout_misc_lhs_axi_d_sss_i_clk", "mout_misc_sss_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_LHS_AXI_D_SSS_IPCLKPORT_I_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_MCT_PCLK, "gout_misc_mct_pclk",
+	     "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_MCT_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_OTP_CON_BIRA_PCLK,
+	     "gout_misc_otp_con_bira_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_OTP_CON_BIRA_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_OTP_CON_BISR_PCLK,
+	     "gout_misc_otp_con_bisr_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_OTP_CON_BISR_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_OTP_CON_TOP_PCLK,
+	     "gout_misc_otp_con_top_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_OTP_CON_TOP_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_PDMA_ACLK, "gout_misc_pdma_aclk",
+	     "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_PDMA_IPCLKPORT_ACLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_PPMU_MISC_ACLK,
+	     "gout_misc_ppmu_misc_aclk", "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_PPMU_MISC_IPCLKPORT_ACLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_PPMU_MISC_PCLK,
+	     "gout_misc_ppmu_misc_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_PPMU_MISC_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_PUF_I_CLK,
+	     "gout_misc_puf_i_clk", "mout_misc_sss_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_PUF_IPCLKPORT_I_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_QE_DIT_ACLK,
+	     "gout_misc_qe_dit_aclk", "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_DIT_IPCLKPORT_ACLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_QE_DIT_PCLK,
+	     "gout_misc_qe_dit_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_DIT_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_QE_PDMA_ACLK,
+	     "gout_misc_qe_pdma_aclk", "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_PDMA_IPCLKPORT_ACLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_QE_PDMA_PCLK,
+	     "gout_misc_qe_pdma_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_PDMA_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_QE_PPMU_DMA_ACLK,
+	     "gout_misc_qe_ppmu_dma_aclk", "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_PPMU_DMA_IPCLKPORT_ACLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_QE_PPMU_DMA_PCLK,
+	     "gout_misc_qe_ppmu_dma_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_PPMU_DMA_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_QE_RTIC_ACLK,
+	     "gout_misc_qe_rtic_aclk", "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_RTIC_IPCLKPORT_ACLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_QE_RTIC_PCLK,
+	     "gout_misc_qe_rtic_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_RTIC_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_QE_SPDMA_ACLK,
+	     "gout_misc_qe_spdma_aclk", "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_SPDMA_IPCLKPORT_ACLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_QE_SPDMA_PCLK,
+	     "gout_misc_qe_spdma_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_SPDMA_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_QE_SSS_ACLK,
+	     "gout_misc_qe_sss_aclk", "mout_misc_sss_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_SSS_IPCLKPORT_ACLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_QE_SSS_PCLK,
+	     "gout_misc_qe_sss_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_QE_SSS_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_CLK_MISC_BUSD_CLK,
+	     "gout_misc_clk_misc_busd_clk", "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_RSTNSYNC_CLK_MISC_BUSD_IPCLKPORT_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_CLK_MISC_BUSP_CLK,
+	     "gout_misc_clk_misc_busp_clk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_RSTNSYNC_CLK_MISC_BUSP_IPCLKPORT_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_CLK_MISC_GIC_CLK,
+	     "gout_misc_clk_misc_gic_clk", "mout_misc_gic",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_RSTNSYNC_CLK_MISC_GIC_IPCLKPORT_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_CLK_MISC_SSS_CLK,
+	     "gout_misc_clk_misc_sss_clk", "mout_misc_sss_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_RSTNSYNC_CLK_MISC_SSS_IPCLKPORT_CLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_RTIC_I_ACLK,
+	     "gout_misc_rtic_i_aclk", "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_RTIC_IPCLKPORT_I_ACLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_RTIC_I_PCLK, "gout_misc_rtic_i_pclk",
+	     "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_RTIC_IPCLKPORT_I_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_SPDMA_ACLK,
+	     "gout_misc_spdma_ipclockport_aclk", "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_SPDMA_IPCLKPORT_ACLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_SSMT_DIT_ACLK,
+	     "gout_misc_ssmt_dit_aclk", "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_DIT_IPCLKPORT_ACLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_SSMT_DIT_PCLK,
+	     "gout_misc_ssmt_dit_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_DIT_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_SSMT_PDMA_ACLK,
+	     "gout_misc_ssmt_pdma_aclk", "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_PDMA_IPCLKPORT_ACLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_SSMT_PDMA_PCLK,
+	     "gout_misc_ssmt_pdma_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_PDMA_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_SSMT_PPMU_DMA_ACLK,
+	     "gout_misc_ssmt_ppmu_dma_aclk", "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_PPMU_DMA_IPCLKPORT_ACLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_SSMT_PPMU_DMA_PCLK,
+	     "gout_misc_ssmt_ppmu_dma_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_PPMU_DMA_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_SSMT_RTIC_ACLK,
+	     "gout_misc_ssmt_rtic_aclk", "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_RTIC_IPCLKPORT_ACLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_SSMT_RTIC_PCLK,
+	     "gout_misc_ssmt_rtic_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_RTIC_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_SSMT_SPDMA_ACLK,
+	     "gout_misc_ssmt_spdma_aclk", "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_SPDMA_IPCLKPORT_ACLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_SSMT_SPDMA_PCLK,
+	     "gout_misc_ssmt_spdma_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_SPDMA_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_SSMT_SSS_ACLK,
+	     "gout_misc_ssmt_sss_aclk", "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_SSS_IPCLKPORT_ACLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_SSMT_SSS_PCLK,
+	     "gout_misc_ssmt_sss_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_SSMT_SSS_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_SSS_I_ACLK,
+	     "gout_misc_sss_i_aclk", "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_SSS_IPCLKPORT_I_ACLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_SSS_I_PCLK,
+	     "gout_misc_sss_i_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_SSS_IPCLKPORT_I_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_SYSMMU_MISC_CLK_S2,
+	     "gout_misc_sysmmu_misc_clk_s2", "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_SYSMMU_MISC_IPCLKPORT_CLK_S2,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_SYSMMU_SSS_CLK_S1,
+	     "gout_misc_sysmmu_sss_clk_s1", "mout_misc_sss_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_SYSMMU_SSS_IPCLKPORT_CLK_S1,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_SYSREG_MISC_PCLK,
+	     "gout_misc_sysreg_misc_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_SYSREG_MISC_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_TMU_SUB_PCLK,
+	     "gout_misc_tmu_sub_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_TMU_SUB_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_TMU_TOP_PCLK,
+	     "gout_misc_tmu_top_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_TMU_TOP_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_WDT_CLUSTER0_PCLK,
+	     "gout_misc_wdt_cluster0_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_WDT_CLUSTER0_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_WDT_CLUSTER1_PCLK,
+	     "gout_misc_wdt_cluster1_pclk", "dout_misc_busp",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_WDT_CLUSTER1_IPCLKPORT_PCLK,
+	     21, 0, 0),
+	GATE(CLK_GOUT_MISC_XIU_D_MISC_ACLK,
+	     "gout_misc_xiu_d_misc_aclk", "mout_misc_bus_user",
+	     CLK_CON_GAT_GOUT_BLK_MISC_UID_XIU_D_MISC_IPCLKPORT_ACLK,
+	     21, 0, 0),
+};
+
+static const struct samsung_cmu_info misc_cmu_info __initconst = {
+	.mux_clks		= misc_mux_clks,
+	.nr_mux_clks		= ARRAY_SIZE(misc_mux_clks),
+	.div_clks		= misc_div_clks,
+	.nr_div_clks		= ARRAY_SIZE(misc_div_clks),
+	.gate_clks		= misc_gate_clks,
+	.nr_gate_clks		= ARRAY_SIZE(misc_gate_clks),
+	.nr_clk_ids		= CLKS_NR_MISC,
+	.clk_regs		= misc_clk_regs,
+	.nr_clk_regs		= ARRAY_SIZE(misc_clk_regs),
+	.clk_name		= "dout_cmu_misc_bus",
+};
+
+/* ---- platform_driver ----------------------------------------------------- */
+
+static int __init gs101_cmu_probe(struct platform_device *pdev)
+{
+	const struct samsung_cmu_info *info;
+	struct device *dev = &pdev->dev;
+
+	info = of_device_get_match_data(dev);
+	exynos_arm64_register_cmu(dev, dev->of_node, info);
+
+	return 0;
+}
+
+static const struct of_device_id gs101_cmu_of_match[] = {
+	{
+		.compatible = "google,gs101-cmu-apm",
+		.data = &apm_cmu_info,
+	}, {
+		.compatible = "google,gs101-cmu-misc",
+		.data = &misc_cmu_info,
+	}, {
+	},
+};
+
+static struct platform_driver gs101_cmu_driver __refdata = {
+	.driver	= {
+		.name = "gs101-cmu",
+		.of_match_table = gs101_cmu_of_match,
+		.suppress_bind_attrs = true,
+	},
+	.probe = gs101_cmu_probe,
+};
+
+static int __init gs101_cmu_init(void)
+{
+	return platform_driver_register(&gs101_cmu_driver);
+}
+core_initcall(gs101_cmu_init);
diff --git a/drivers/clk/samsung/clk-pll.c b/drivers/clk/samsung/clk-pll.c
index 74934c6182ce..4bbdf5e91650 100644
--- a/drivers/clk/samsung/clk-pll.c
+++ b/drivers/clk/samsung/clk-pll.c
@@ -443,6 +443,9 @@ static unsigned long samsung_pll0822x_recalc_rate(struct clk_hw *hw,
 	sdiv = (pll_con3 >> PLL0822X_SDIV_SHIFT) & PLL0822X_SDIV_MASK;
 
 	fvco *= mdiv;
+	if (pll->type == pll_0516x)
+		fvco *= 2;
+
 	do_div(fvco, (pdiv << sdiv));
 
 	return (unsigned long)fvco;
@@ -1316,6 +1319,9 @@ static void __init _samsung_clk_register_pll(struct samsung_clk_provider *ctx,
 	case pll_1417x:
 	case pll_0818x:
 	case pll_0822x:
+	case pll_0516x:
+	case pll_0517x:
+	case pll_0518x:
 		pll->enable_offs = PLL0822X_ENABLE_SHIFT;
 		pll->lock_offs = PLL0822X_LOCK_STAT_SHIFT;
 		if (!pll->rate_table)
diff --git a/drivers/clk/samsung/clk-pll.h b/drivers/clk/samsung/clk-pll.h
index 0725d485c6ee..ffd3d52c0dec 100644
--- a/drivers/clk/samsung/clk-pll.h
+++ b/drivers/clk/samsung/clk-pll.h
@@ -38,6 +38,9 @@ enum samsung_pll_type {
 	pll_0822x,
 	pll_0831x,
 	pll_142xx,
+	pll_0516x,
+	pll_0517x,
+	pll_0518x,
 };
 
 #define PLL_RATE(_fin, _m, _p, _s, _k, _ks) \
diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index 44b19e696176..3d5e6d705fc6 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -108,8 +108,9 @@ static inline void send_msg(struct cn_msg *msg)
 		filter_data[1] = 0;
 	}
 
-	cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT,
-			     cn_filter, (void *)filter_data);
+	if (cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT,
+			     cn_filter, (void *)filter_data) == -ESRCH)
+		atomic_set(&proc_event_num_listeners, 0);
 
 	local_unlock(&local_event.lock);
 }
diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index 7f7b94f616a6..4028e8eeba82 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -59,9 +59,8 @@ static int cn_already_initialized;
  * both, or if both are zero then the group is looked up and sent there.
  */
 int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 __group,
-	gfp_t gfp_mask,
-	int (*filter)(struct sock *dsk, struct sk_buff *skb, void *data),
-	void *filter_data)
+			 gfp_t gfp_mask, netlink_filter_fn filter,
+			 void *filter_data)
 {
 	struct cn_callback_entry *__cbq;
 	unsigned int size;
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 9a1e194d5cf8..1f6186475715 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -307,11 +307,11 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
 		highest_perf = AMD_CPPC_HIGHEST_PERF(cap1);
 
 	WRITE_ONCE(cpudata->highest_perf, highest_perf);
-
+	WRITE_ONCE(cpudata->max_limit_perf, highest_perf);
 	WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1));
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1));
 	WRITE_ONCE(cpudata->lowest_perf, AMD_CPPC_LOWEST_PERF(cap1));
-
+	WRITE_ONCE(cpudata->min_limit_perf, AMD_CPPC_LOWEST_PERF(cap1));
 	return 0;
 }
 
@@ -329,11 +329,12 @@ static int cppc_init_perf(struct amd_cpudata *cpudata)
 		highest_perf = cppc_perf.highest_perf;
 
 	WRITE_ONCE(cpudata->highest_perf, highest_perf);
-
+	WRITE_ONCE(cpudata->max_limit_perf, highest_perf);
 	WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf);
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf,
 		   cppc_perf.lowest_nonlinear_perf);
 	WRITE_ONCE(cpudata->lowest_perf, cppc_perf.lowest_perf);
+	WRITE_ONCE(cpudata->min_limit_perf, cppc_perf.lowest_perf);
 
 	if (cppc_state == AMD_PSTATE_ACTIVE)
 		return 0;
@@ -432,6 +433,10 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf,
 	u64 prev = READ_ONCE(cpudata->cppc_req_cached);
 	u64 value = prev;
 
+	min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf,
+			cpudata->max_limit_perf);
+	max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf,
+			cpudata->max_limit_perf);
 	des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf);
 
 	if ((cppc_state == AMD_PSTATE_GUIDED) && (gov_flags & CPUFREQ_GOV_DYNAMIC_SWITCHING)) {
@@ -470,6 +475,22 @@ static int amd_pstate_verify(struct cpufreq_policy_data *policy)
 	return 0;
 }
 
+static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy)
+{
+	u32 max_limit_perf, min_limit_perf;
+	struct amd_cpudata *cpudata = policy->driver_data;
+
+	max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq);
+	min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq);
+
+	WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf);
+	WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf);
+	WRITE_ONCE(cpudata->max_limit_freq, policy->max);
+	WRITE_ONCE(cpudata->min_limit_freq, policy->min);
+
+	return 0;
+}
+
 static int amd_pstate_update_freq(struct cpufreq_policy *policy,
 				  unsigned int target_freq, bool fast_switch)
 {
@@ -480,6 +501,9 @@ static int amd_pstate_update_freq(struct cpufreq_policy *policy,
 	if (!cpudata->max_freq)
 		return -ENODEV;
 
+	if (policy->min != cpudata->min_limit_freq || policy->max != cpudata->max_limit_freq)
+		amd_pstate_update_min_max_limit(policy);
+
 	cap_perf = READ_ONCE(cpudata->highest_perf);
 	min_perf = READ_ONCE(cpudata->lowest_perf);
 	max_perf = cap_perf;
@@ -518,7 +542,9 @@ static int amd_pstate_target(struct cpufreq_policy *policy,
 static unsigned int amd_pstate_fast_switch(struct cpufreq_policy *policy,
 				  unsigned int target_freq)
 {
-	return amd_pstate_update_freq(policy, target_freq, true);
+	if (!amd_pstate_update_freq(policy, target_freq, true))
+		return target_freq;
+	return policy->cur;
 }
 
 static void amd_pstate_adjust_perf(unsigned int cpu,
@@ -532,6 +558,10 @@ static void amd_pstate_adjust_perf(unsigned int cpu,
 	struct amd_cpudata *cpudata = policy->driver_data;
 	unsigned int target_freq;
 
+	if (policy->min != cpudata->min_limit_freq || policy->max != cpudata->max_limit_freq)
+		amd_pstate_update_min_max_limit(policy);
+
+
 	cap_perf = READ_ONCE(cpudata->highest_perf);
 	lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf);
 	max_freq = READ_ONCE(cpudata->max_freq);
@@ -745,6 +775,8 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 	/* Initial processor data capability frequencies */
 	cpudata->max_freq = max_freq;
 	cpudata->min_freq = min_freq;
+	cpudata->max_limit_freq = max_freq;
+	cpudata->min_limit_freq = min_freq;
 	cpudata->nominal_freq = nominal_freq;
 	cpudata->lowest_nonlinear_freq = lowest_nonlinear_freq;
 
@@ -850,11 +882,16 @@ static ssize_t show_energy_performance_available_preferences(
 {
 	int i = 0;
 	int offset = 0;
+	struct amd_cpudata *cpudata = policy->driver_data;
+
+	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
+		return sysfs_emit_at(buf, offset, "%s\n",
+				energy_perf_strings[EPP_INDEX_PERFORMANCE]);
 
 	while (energy_perf_strings[i] != NULL)
 		offset += sysfs_emit_at(buf, offset, "%s ", energy_perf_strings[i++]);
 
-	sysfs_emit_at(buf, offset, "\n");
+	offset += sysfs_emit_at(buf, offset, "\n");
 
 	return offset;
 }
@@ -1183,16 +1220,25 @@ static int amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static void amd_pstate_epp_init(unsigned int cpu)
+static void amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
 {
-	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
 	struct amd_cpudata *cpudata = policy->driver_data;
-	u32 max_perf, min_perf;
+	u32 max_perf, min_perf, min_limit_perf, max_limit_perf;
 	u64 value;
 	s16 epp;
 
 	max_perf = READ_ONCE(cpudata->highest_perf);
 	min_perf = READ_ONCE(cpudata->lowest_perf);
+	max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq);
+	min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq);
+
+	max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf,
+			cpudata->max_limit_perf);
+	min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf,
+			cpudata->max_limit_perf);
+
+	WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf);
+	WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf);
 
 	value = READ_ONCE(cpudata->cppc_req_cached);
 
@@ -1210,9 +1256,6 @@ static void amd_pstate_epp_init(unsigned int cpu)
 	value &= ~AMD_CPPC_DES_PERF(~0L);
 	value |= AMD_CPPC_DES_PERF(0);
 
-	if (cpudata->epp_policy == cpudata->policy)
-		goto skip_epp;
-
 	cpudata->epp_policy = cpudata->policy;
 
 	/* Get BIOS pre-defined epp value */
@@ -1222,7 +1265,7 @@ static void amd_pstate_epp_init(unsigned int cpu)
 		 * This return value can only be negative for shared_memory
 		 * systems where EPP register read/write not supported.
 		 */
-		goto skip_epp;
+		return;
 	}
 
 	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
@@ -1236,8 +1279,6 @@ static void amd_pstate_epp_init(unsigned int cpu)
 
 	WRITE_ONCE(cpudata->cppc_req_cached, value);
 	amd_pstate_set_epp(cpudata, epp);
-skip_epp:
-	cpufreq_cpu_put(policy);
 }
 
 static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
@@ -1252,7 +1293,7 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
 
 	cpudata->policy = policy->policy;
 
-	amd_pstate_epp_init(policy->cpu);
+	amd_pstate_epp_update_limit(policy);
 
 	return 0;
 }
diff --git a/drivers/cpufreq/armada-8k-cpufreq.c b/drivers/cpufreq/armada-8k-cpufreq.c
index 8afefdea4d80..ce5a5641b6dd 100644
--- a/drivers/cpufreq/armada-8k-cpufreq.c
+++ b/drivers/cpufreq/armada-8k-cpufreq.c
@@ -57,7 +57,7 @@ static void __init armada_8k_get_sharing_cpus(struct clk *cur_clk,
 			continue;
 		}
 
-		clk = clk_get(cpu_dev, 0);
+		clk = clk_get(cpu_dev, NULL);
 		if (IS_ERR(clk)) {
 			pr_warn("Cannot get clock for CPU %d\n", cpu);
 		} else {
@@ -165,7 +165,7 @@ static int __init armada_8k_cpufreq_init(void)
 			continue;
 		}
 
-		clk = clk_get(cpu_dev, 0);
+		clk = clk_get(cpu_dev, NULL);
 
 		if (IS_ERR(clk)) {
 			pr_err("Cannot get clock for CPU %d\n", cpu);
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index fe08ca419b3d..64420d9cfd1e 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -16,7 +16,6 @@
 #include <linux/delay.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
-#include <linux/dmi.h>
 #include <linux/irq_work.h>
 #include <linux/kthread.h>
 #include <linux/time.h>
@@ -27,12 +26,6 @@
 
 #include <acpi/cppc_acpi.h>
 
-/* Minimum struct length needed for the DMI processor entry we want */
-#define DMI_ENTRY_PROCESSOR_MIN_LENGTH	48
-
-/* Offset in the DMI processor structure for the max frequency */
-#define DMI_PROCESSOR_MAX_SPEED		0x14
-
 /*
  * This list contains information parsed from per CPU ACPI _CPC and _PSD
  * structures: e.g. the highest and lowest supported performance, capabilities,
@@ -291,97 +284,9 @@ static inline void cppc_freq_invariance_exit(void)
 }
 #endif /* CONFIG_ACPI_CPPC_CPUFREQ_FIE */
 
-/* Callback function used to retrieve the max frequency from DMI */
-static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private)
-{
-	const u8 *dmi_data = (const u8 *)dm;
-	u16 *mhz = (u16 *)private;
-
-	if (dm->type == DMI_ENTRY_PROCESSOR &&
-	    dm->length >= DMI_ENTRY_PROCESSOR_MIN_LENGTH) {
-		u16 val = (u16)get_unaligned((const u16 *)
-				(dmi_data + DMI_PROCESSOR_MAX_SPEED));
-		*mhz = val > *mhz ? val : *mhz;
-	}
-}
-
-/* Look up the max frequency in DMI */
-static u64 cppc_get_dmi_max_khz(void)
-{
-	u16 mhz = 0;
-
-	dmi_walk(cppc_find_dmi_mhz, &mhz);
-
-	/*
-	 * Real stupid fallback value, just in case there is no
-	 * actual value set.
-	 */
-	mhz = mhz ? mhz : 1;
-
-	return (1000 * mhz);
-}
-
-/*
- * If CPPC lowest_freq and nominal_freq registers are exposed then we can
- * use them to convert perf to freq and vice versa. The conversion is
- * extrapolated as an affine function passing by the 2 points:
- *  - (Low perf, Low freq)
- *  - (Nominal perf, Nominal perf)
- */
-static unsigned int cppc_cpufreq_perf_to_khz(struct cppc_cpudata *cpu_data,
-					     unsigned int perf)
-{
-	struct cppc_perf_caps *caps = &cpu_data->perf_caps;
-	s64 retval, offset = 0;
-	static u64 max_khz;
-	u64 mul, div;
-
-	if (caps->lowest_freq && caps->nominal_freq) {
-		mul = caps->nominal_freq - caps->lowest_freq;
-		div = caps->nominal_perf - caps->lowest_perf;
-		offset = caps->nominal_freq - div64_u64(caps->nominal_perf * mul, div);
-	} else {
-		if (!max_khz)
-			max_khz = cppc_get_dmi_max_khz();
-		mul = max_khz;
-		div = caps->highest_perf;
-	}
-
-	retval = offset + div64_u64(perf * mul, div);
-	if (retval >= 0)
-		return retval;
-	return 0;
-}
-
-static unsigned int cppc_cpufreq_khz_to_perf(struct cppc_cpudata *cpu_data,
-					     unsigned int freq)
-{
-	struct cppc_perf_caps *caps = &cpu_data->perf_caps;
-	s64 retval, offset = 0;
-	static u64 max_khz;
-	u64  mul, div;
-
-	if (caps->lowest_freq && caps->nominal_freq) {
-		mul = caps->nominal_perf - caps->lowest_perf;
-		div = caps->nominal_freq - caps->lowest_freq;
-		offset = caps->nominal_perf - div64_u64(caps->nominal_freq * mul, div);
-	} else {
-		if (!max_khz)
-			max_khz = cppc_get_dmi_max_khz();
-		mul = caps->highest_perf;
-		div = max_khz;
-	}
-
-	retval = offset + div64_u64(freq * mul, div);
-	if (retval >= 0)
-		return retval;
-	return 0;
-}
-
 static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
 				   unsigned int target_freq,
 				   unsigned int relation)
-
 {
 	struct cppc_cpudata *cpu_data = policy->driver_data;
 	unsigned int cpu = policy->cpu;
@@ -389,7 +294,7 @@ static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
 	u32 desired_perf;
 	int ret = 0;
 
-	desired_perf = cppc_cpufreq_khz_to_perf(cpu_data, target_freq);
+	desired_perf = cppc_khz_to_perf(&cpu_data->perf_caps, target_freq);
 	/* Return if it is exactly the same perf */
 	if (desired_perf == cpu_data->perf_ctrls.desired_perf)
 		return ret;
@@ -417,7 +322,7 @@ static unsigned int cppc_cpufreq_fast_switch(struct cpufreq_policy *policy,
 	u32 desired_perf;
 	int ret;
 
-	desired_perf = cppc_cpufreq_khz_to_perf(cpu_data, target_freq);
+	desired_perf = cppc_khz_to_perf(&cpu_data->perf_caps, target_freq);
 	cpu_data->perf_ctrls.desired_perf = desired_perf;
 	ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);
 
@@ -530,7 +435,7 @@ static int cppc_get_cpu_power(struct device *cpu_dev,
 	min_step = min_cap / CPPC_EM_CAP_STEP;
 	max_step = max_cap / CPPC_EM_CAP_STEP;
 
-	perf_prev = cppc_cpufreq_khz_to_perf(cpu_data, *KHz);
+	perf_prev = cppc_khz_to_perf(perf_caps, *KHz);
 	step = perf_prev / perf_step;
 
 	if (step > max_step)
@@ -550,8 +455,8 @@ static int cppc_get_cpu_power(struct device *cpu_dev,
 			perf = step * perf_step;
 	}
 
-	*KHz = cppc_cpufreq_perf_to_khz(cpu_data, perf);
-	perf_check = cppc_cpufreq_khz_to_perf(cpu_data, *KHz);
+	*KHz = cppc_perf_to_khz(perf_caps, perf);
+	perf_check = cppc_khz_to_perf(perf_caps, *KHz);
 	step_check = perf_check / perf_step;
 
 	/*
@@ -561,8 +466,8 @@ static int cppc_get_cpu_power(struct device *cpu_dev,
 	 */
 	while ((*KHz == prev_freq) || (step_check != step)) {
 		perf++;
-		*KHz = cppc_cpufreq_perf_to_khz(cpu_data, perf);
-		perf_check = cppc_cpufreq_khz_to_perf(cpu_data, *KHz);
+		*KHz = cppc_perf_to_khz(perf_caps, perf);
+		perf_check = cppc_khz_to_perf(perf_caps, *KHz);
 		step_check = perf_check / perf_step;
 	}
 
@@ -591,7 +496,7 @@ static int cppc_get_cpu_cost(struct device *cpu_dev, unsigned long KHz,
 	perf_caps = &cpu_data->perf_caps;
 	max_cap = arch_scale_cpu_capacity(cpu_dev->id);
 
-	perf_prev = cppc_cpufreq_khz_to_perf(cpu_data, KHz);
+	perf_prev = cppc_khz_to_perf(perf_caps, KHz);
 	perf_step = CPPC_EM_CAP_STEP * perf_caps->highest_perf / max_cap;
 	step = perf_prev / perf_step;
 
@@ -679,10 +584,6 @@ static struct cppc_cpudata *cppc_cpufreq_get_cpu_data(unsigned int cpu)
 		goto free_mask;
 	}
 
-	/* Convert the lowest and nominal freq from MHz to KHz */
-	cpu_data->perf_caps.lowest_freq *= 1000;
-	cpu_data->perf_caps.nominal_freq *= 1000;
-
 	list_add(&cpu_data->node, &cpu_data_list);
 
 	return cpu_data;
@@ -724,20 +625,16 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	 * Set min to lowest nonlinear perf to avoid any efficiency penalty (see
 	 * Section 8.4.7.1.1.5 of ACPI 6.1 spec)
 	 */
-	policy->min = cppc_cpufreq_perf_to_khz(cpu_data,
-					       caps->lowest_nonlinear_perf);
-	policy->max = cppc_cpufreq_perf_to_khz(cpu_data,
-					       caps->nominal_perf);
+	policy->min = cppc_perf_to_khz(caps, caps->lowest_nonlinear_perf);
+	policy->max = cppc_perf_to_khz(caps, caps->nominal_perf);
 
 	/*
 	 * Set cpuinfo.min_freq to Lowest to make the full range of performance
 	 * available if userspace wants to use any perf between lowest & lowest
 	 * nonlinear perf
 	 */
-	policy->cpuinfo.min_freq = cppc_cpufreq_perf_to_khz(cpu_data,
-							    caps->lowest_perf);
-	policy->cpuinfo.max_freq = cppc_cpufreq_perf_to_khz(cpu_data,
-							    caps->nominal_perf);
+	policy->cpuinfo.min_freq = cppc_perf_to_khz(caps, caps->lowest_perf);
+	policy->cpuinfo.max_freq = cppc_perf_to_khz(caps, caps->nominal_perf);
 
 	policy->transition_delay_us = cppc_cpufreq_get_transition_delay_us(cpu);
 	policy->shared_type = cpu_data->shared_type;
@@ -773,7 +670,7 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		boost_supported = true;
 
 	/* Set policy->cur to max now. The governors will adjust later. */
-	policy->cur = cppc_cpufreq_perf_to_khz(cpu_data, caps->highest_perf);
+	policy->cur = cppc_perf_to_khz(caps, caps->highest_perf);
 	cpu_data->perf_ctrls.desired_perf =  caps->highest_perf;
 
 	ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);
@@ -863,7 +760,7 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu)
 	delivered_perf = cppc_perf_from_fbctrs(cpu_data, &fb_ctrs_t0,
 					       &fb_ctrs_t1);
 
-	return cppc_cpufreq_perf_to_khz(cpu_data, delivered_perf);
+	return cppc_perf_to_khz(&cpu_data->perf_caps, delivered_perf);
 }
 
 static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state)
@@ -878,11 +775,9 @@ static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state)
 	}
 
 	if (state)
-		policy->max = cppc_cpufreq_perf_to_khz(cpu_data,
-						       caps->highest_perf);
+		policy->max = cppc_perf_to_khz(caps, caps->highest_perf);
 	else
-		policy->max = cppc_cpufreq_perf_to_khz(cpu_data,
-						       caps->nominal_perf);
+		policy->max = cppc_perf_to_khz(caps, caps->nominal_perf);
 	policy->cpuinfo.max_freq = policy->max;
 
 	ret = freq_qos_update_request(policy->max_freq_req, policy->max);
@@ -937,7 +832,7 @@ static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu)
 	if (ret < 0)
 		return -EIO;
 
-	return cppc_cpufreq_perf_to_khz(cpu_data, desired_perf);
+	return cppc_perf_to_khz(&cpu_data->perf_caps, desired_perf);
 }
 
 static void cppc_check_hisi_workaround(void)
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 934d35f570b7..44db4f59c4cc 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -454,7 +454,7 @@ void cpufreq_freq_transition_end(struct cpufreq_policy *policy,
 
 	arch_set_freq_scale(policy->related_cpus,
 			    policy->cur,
-			    policy->cpuinfo.max_freq);
+			    arch_scale_freq_ref(policy->cpu));
 
 	spin_lock(&policy->transition_lock);
 	policy->transition_ongoing = false;
@@ -2174,7 +2174,7 @@ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
 
 	policy->cur = freq;
 	arch_set_freq_scale(policy->related_cpus, freq,
-			    policy->cpuinfo.max_freq);
+			    arch_scale_freq_ref(policy->cpu));
 	cpufreq_stats_record_transition(policy, freq);
 
 	if (trace_cpu_frequency_enabled()) {
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index 494d044b9e72..33728c242f66 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -327,7 +327,7 @@ static int imx6ul_opp_check_speed_grading(struct device *dev)
 			imx6x_disable_freq_in_opp(dev, 696000000);
 
 	if (of_machine_is_compatible("fsl,imx6ull")) {
-		if (val != OCOTP_CFG3_6ULL_SPEED_792MHZ)
+		if (val < OCOTP_CFG3_6ULL_SPEED_792MHZ)
 			imx6x_disable_freq_in_opp(dev, 792000000);
 
 		if (val != OCOTP_CFG3_6ULL_SPEED_900MHZ)
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index a534a1f7f1ee..3c69040920b8 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1692,13 +1692,6 @@ static void intel_pstate_update_epp_defaults(struct cpudata *cpudata)
 	cpudata->epp_default = intel_pstate_get_epp(cpudata, 0);
 
 	/*
-	 * If this CPU gen doesn't call for change in balance_perf
-	 * EPP return.
-	 */
-	if (epp_values[EPP_INDEX_BALANCE_PERFORMANCE] == HWP_EPP_BALANCE_PERFORMANCE)
-		return;
-
-	/*
 	 * If the EPP is set by firmware, which means that firmware enabled HWP
 	 * - Is equal or less than 0x80 (default balance_perf EPP)
 	 * - But less performance oriented than performance EPP
@@ -1711,6 +1704,13 @@ static void intel_pstate_update_epp_defaults(struct cpudata *cpudata)
 	}
 
 	/*
+	 * If this CPU gen doesn't call for change in balance_perf
+	 * EPP return.
+	 */
+	if (epp_values[EPP_INDEX_BALANCE_PERFORMANCE] == HWP_EPP_BALANCE_PERFORMANCE)
+		return;
+
+	/*
 	 * Use hard coded value per gen to update the balance_perf
 	 * and default EPP.
 	 */
@@ -2406,6 +2406,7 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	X86_MATCH(ICELAKE_X,		core_funcs),
 	X86_MATCH(TIGERLAKE,		core_funcs),
 	X86_MATCH(SAPPHIRERAPIDS_X,	core_funcs),
+	X86_MATCH(EMERALDRAPIDS_X,      core_funcs),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
diff --git a/drivers/cpufreq/qcom-cpufreq-nvmem.c b/drivers/cpufreq/qcom-cpufreq-nvmem.c
index 6355a39418c5..ea05d9d67490 100644
--- a/drivers/cpufreq/qcom-cpufreq-nvmem.c
+++ b/drivers/cpufreq/qcom-cpufreq-nvmem.c
@@ -23,8 +23,10 @@
 #include <linux/nvmem-consumer.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 #include <linux/pm_domain.h>
 #include <linux/pm_opp.h>
+#include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/soc/qcom/smem.h>
 
@@ -55,6 +57,7 @@ struct qcom_cpufreq_match_data {
 
 struct qcom_cpufreq_drv_cpu {
 	int opp_token;
+	struct device **virt_devs;
 };
 
 struct qcom_cpufreq_drv {
@@ -424,6 +427,30 @@ static const struct qcom_cpufreq_match_data match_data_ipq8074 = {
 	.get_version = qcom_cpufreq_ipq8074_name_version,
 };
 
+static void qcom_cpufreq_suspend_virt_devs(struct qcom_cpufreq_drv *drv, unsigned int cpu)
+{
+	const char * const *name = drv->data->genpd_names;
+	int i;
+
+	if (!drv->cpus[cpu].virt_devs)
+		return;
+
+	for (i = 0; *name; i++, name++)
+		device_set_awake_path(drv->cpus[cpu].virt_devs[i]);
+}
+
+static void qcom_cpufreq_put_virt_devs(struct qcom_cpufreq_drv *drv, unsigned int cpu)
+{
+	const char * const *name = drv->data->genpd_names;
+	int i;
+
+	if (!drv->cpus[cpu].virt_devs)
+		return;
+
+	for (i = 0; *name; i++, name++)
+		pm_runtime_put(drv->cpus[cpu].virt_devs[i]);
+}
+
 static int qcom_cpufreq_probe(struct platform_device *pdev)
 {
 	struct qcom_cpufreq_drv *drv;
@@ -478,6 +505,7 @@ static int qcom_cpufreq_probe(struct platform_device *pdev)
 	of_node_put(np);
 
 	for_each_possible_cpu(cpu) {
+		struct device **virt_devs = NULL;
 		struct dev_pm_opp_config config = {
 			.supported_hw = NULL,
 		};
@@ -498,7 +526,7 @@ static int qcom_cpufreq_probe(struct platform_device *pdev)
 
 		if (drv->data->genpd_names) {
 			config.genpd_names = drv->data->genpd_names;
-			config.virt_devs = NULL;
+			config.virt_devs = &virt_devs;
 		}
 
 		if (config.supported_hw || config.genpd_names) {
@@ -509,6 +537,27 @@ static int qcom_cpufreq_probe(struct platform_device *pdev)
 				goto free_opp;
 			}
 		}
+
+		if (virt_devs) {
+			const char * const *name = config.genpd_names;
+			int i, j;
+
+			for (i = 0; *name; i++, name++) {
+				ret = pm_runtime_resume_and_get(virt_devs[i]);
+				if (ret) {
+					dev_err(cpu_dev, "failed to resume %s: %d\n",
+						*name, ret);
+
+					/* Rollback previous PM runtime calls */
+					name = config.genpd_names;
+					for (j = 0; *name && j < i; j++, name++)
+						pm_runtime_put(virt_devs[j]);
+
+					goto free_opp;
+				}
+			}
+			drv->cpus[cpu].virt_devs = virt_devs;
+		}
 	}
 
 	cpufreq_dt_pdev = platform_device_register_simple("cpufreq-dt", -1,
@@ -522,8 +571,10 @@ static int qcom_cpufreq_probe(struct platform_device *pdev)
 	dev_err(cpu_dev, "Failed to register platform device\n");
 
 free_opp:
-	for_each_possible_cpu(cpu)
+	for_each_possible_cpu(cpu) {
+		qcom_cpufreq_put_virt_devs(drv, cpu);
 		dev_pm_opp_clear_config(drv->cpus[cpu].opp_token);
+	}
 	return ret;
 }
 
@@ -534,15 +585,31 @@ static void qcom_cpufreq_remove(struct platform_device *pdev)
 
 	platform_device_unregister(cpufreq_dt_pdev);
 
-	for_each_possible_cpu(cpu)
+	for_each_possible_cpu(cpu) {
+		qcom_cpufreq_put_virt_devs(drv, cpu);
 		dev_pm_opp_clear_config(drv->cpus[cpu].opp_token);
+	}
 }
 
+static int qcom_cpufreq_suspend(struct device *dev)
+{
+	struct qcom_cpufreq_drv *drv = dev_get_drvdata(dev);
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu)
+		qcom_cpufreq_suspend_virt_devs(drv, cpu);
+
+	return 0;
+}
+
+static DEFINE_SIMPLE_DEV_PM_OPS(qcom_cpufreq_pm_ops, qcom_cpufreq_suspend, NULL);
+
 static struct platform_driver qcom_cpufreq_driver = {
 	.probe = qcom_cpufreq_probe,
 	.remove_new = qcom_cpufreq_remove,
 	.driver = {
 		.name = "qcom-cpufreq-nvmem",
+		.pm = pm_sleep_ptr(&qcom_cpufreq_pm_ops),
 	},
 };
 
diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c
index c8a7ccc42c16..4ee23f4ebf4a 100644
--- a/drivers/cpufreq/scmi-cpufreq.c
+++ b/drivers/cpufreq/scmi-cpufreq.c
@@ -334,8 +334,11 @@ static int scmi_cpufreq_probe(struct scmi_device *sdev)
 
 #ifdef CONFIG_COMMON_CLK
 	/* dummy clock provider as needed by OPP if clocks property is used */
-	if (of_property_present(dev->of_node, "#clock-cells"))
-		devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, NULL);
+	if (of_property_present(dev->of_node, "#clock-cells")) {
+		ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, NULL);
+		if (ret)
+			return dev_err_probe(dev, ret, "%s: registering clock provider failed\n", __func__);
+	}
 #endif
 
 	ret = cpufreq_register_driver(&scmi_cpufreq_driver);
diff --git a/drivers/cpuidle/cpuidle-haltpoll.c b/drivers/cpuidle/cpuidle-haltpoll.c
index e66df22f9695..d8515d5c0853 100644
--- a/drivers/cpuidle/cpuidle-haltpoll.c
+++ b/drivers/cpuidle/cpuidle-haltpoll.c
@@ -25,13 +25,12 @@ MODULE_PARM_DESC(force, "Load unconditionally");
 static struct cpuidle_device __percpu *haltpoll_cpuidle_devices;
 static enum cpuhp_state haltpoll_hp_state;
 
-static int default_enter_idle(struct cpuidle_device *dev,
-			      struct cpuidle_driver *drv, int index)
+static __cpuidle int default_enter_idle(struct cpuidle_device *dev,
+					struct cpuidle_driver *drv, int index)
 {
-	if (current_clr_polling_and_test()) {
-		local_irq_enable();
+	if (current_clr_polling_and_test())
 		return index;
-	}
+
 	arch_cpu_idle();
 	return index;
 }
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 79c3bb9c99c3..0991f026cb07 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -306,6 +306,7 @@ config CRYPTO_DEV_SAHARA
 	select CRYPTO_SKCIPHER
 	select CRYPTO_AES
 	select CRYPTO_ECB
+	select CRYPTO_ENGINE
 	help
 	  This option enables support for the SAHARA HW crypto accelerator
 	  found in some Freescale i.MX chips.
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c
index 8d4c42863a62..1262a7773ef3 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c
@@ -431,8 +431,8 @@ int sun8i_ce_cipher_init(struct crypto_tfm *tfm)
 		return PTR_ERR(op->fallback_tfm);
 	}
 
-	sktfm->reqsize = sizeof(struct sun8i_cipher_req_ctx) +
-			 crypto_skcipher_reqsize(op->fallback_tfm);
+	crypto_skcipher_set_reqsize(sktfm, sizeof(struct sun8i_cipher_req_ctx) +
+				    crypto_skcipher_reqsize(op->fallback_tfm));
 
 	memcpy(algt->fbname,
 	       crypto_tfm_alg_driver_name(crypto_skcipher_tfm(op->fallback_tfm)),
diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c
index 7fa359725ec7..9b9605ce8ee6 100644
--- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c
+++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c
@@ -405,9 +405,8 @@ int sun8i_ss_cipher_init(struct crypto_tfm *tfm)
 		return PTR_ERR(op->fallback_tfm);
 	}
 
-	sktfm->reqsize = sizeof(struct sun8i_cipher_req_ctx) +
-			 crypto_skcipher_reqsize(op->fallback_tfm);
-
+	crypto_skcipher_set_reqsize(sktfm, sizeof(struct sun8i_cipher_req_ctx) +
+				    crypto_skcipher_reqsize(op->fallback_tfm));
 
 	memcpy(algt->fbname,
 	       crypto_tfm_alg_driver_name(crypto_skcipher_tfm(op->fallback_tfm)),
diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c
index d70b105dcfa1..753f67a36dc5 100644
--- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c
+++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c
@@ -30,33 +30,16 @@ static int sun8i_ss_hashkey(struct sun8i_ss_hash_tfm_ctx *tfmctx, const u8 *key,
 			    unsigned int keylen)
 {
 	struct crypto_shash *xtfm;
-	struct shash_desc *sdesc;
-	size_t len;
-	int ret = 0;
+	int ret;
 
 	xtfm = crypto_alloc_shash("sha1", 0, CRYPTO_ALG_NEED_FALLBACK);
 	if (IS_ERR(xtfm))
 		return PTR_ERR(xtfm);
 
-	len = sizeof(*sdesc) + crypto_shash_descsize(xtfm);
-	sdesc = kmalloc(len, GFP_KERNEL);
-	if (!sdesc) {
-		ret = -ENOMEM;
-		goto err_hashkey_sdesc;
-	}
-	sdesc->tfm = xtfm;
-
-	ret = crypto_shash_init(sdesc);
-	if (ret) {
-		dev_err(tfmctx->ss->dev, "shash init error ret=%d\n", ret);
-		goto err_hashkey;
-	}
-	ret = crypto_shash_finup(sdesc, key, keylen, tfmctx->key);
+	ret = crypto_shash_tfm_digest(xtfm, key, keylen, tfmctx->key);
 	if (ret)
-		dev_err(tfmctx->ss->dev, "shash finup error\n");
-err_hashkey:
-	kfree(sdesc);
-err_hashkey_sdesc:
+		dev_err(tfmctx->ss->dev, "shash digest error ret=%d\n", ret);
+
 	crypto_free_shash(xtfm);
 	return ret;
 }
diff --git a/drivers/crypto/amcc/crypto4xx_alg.c b/drivers/crypto/amcc/crypto4xx_alg.c
index ded732242732..e0af611a95d8 100644
--- a/drivers/crypto/amcc/crypto4xx_alg.c
+++ b/drivers/crypto/amcc/crypto4xx_alg.c
@@ -181,13 +181,6 @@ int crypto4xx_setkey_aes_cbc(struct crypto_skcipher *cipher,
 				    CRYPTO_FEEDBACK_MODE_NO_FB);
 }
 
-int crypto4xx_setkey_aes_cfb(struct crypto_skcipher *cipher,
-			     const u8 *key, unsigned int keylen)
-{
-	return crypto4xx_setkey_aes(cipher, key, keylen, CRYPTO_MODE_CFB,
-				    CRYPTO_FEEDBACK_MODE_128BIT_CFB);
-}
-
 int crypto4xx_setkey_aes_ecb(struct crypto_skcipher *cipher,
 			     const u8 *key, unsigned int keylen)
 {
@@ -195,13 +188,6 @@ int crypto4xx_setkey_aes_ecb(struct crypto_skcipher *cipher,
 				    CRYPTO_FEEDBACK_MODE_NO_FB);
 }
 
-int crypto4xx_setkey_aes_ofb(struct crypto_skcipher *cipher,
-			     const u8 *key, unsigned int keylen)
-{
-	return crypto4xx_setkey_aes(cipher, key, keylen, CRYPTO_MODE_OFB,
-				    CRYPTO_FEEDBACK_MODE_64BIT_OFB);
-}
-
 int crypto4xx_setkey_rfc3686(struct crypto_skcipher *cipher,
 			     const u8 *key, unsigned int keylen)
 {
diff --git a/drivers/crypto/amcc/crypto4xx_core.c b/drivers/crypto/amcc/crypto4xx_core.c
index 8d53372245ad..6006703fb6d7 100644
--- a/drivers/crypto/amcc/crypto4xx_core.c
+++ b/drivers/crypto/amcc/crypto4xx_core.c
@@ -1211,26 +1211,6 @@ static struct crypto4xx_alg_common crypto4xx_alg[] = {
 	} },
 	{ .type = CRYPTO_ALG_TYPE_SKCIPHER, .u.cipher = {
 		.base = {
-			.cra_name = "cfb(aes)",
-			.cra_driver_name = "cfb-aes-ppc4xx",
-			.cra_priority = CRYPTO4XX_CRYPTO_PRIORITY,
-			.cra_flags = CRYPTO_ALG_ASYNC |
-				CRYPTO_ALG_KERN_DRIVER_ONLY,
-			.cra_blocksize = 1,
-			.cra_ctxsize = sizeof(struct crypto4xx_ctx),
-			.cra_module = THIS_MODULE,
-		},
-		.min_keysize = AES_MIN_KEY_SIZE,
-		.max_keysize = AES_MAX_KEY_SIZE,
-		.ivsize	= AES_IV_SIZE,
-		.setkey	= crypto4xx_setkey_aes_cfb,
-		.encrypt = crypto4xx_encrypt_iv_stream,
-		.decrypt = crypto4xx_decrypt_iv_stream,
-		.init = crypto4xx_sk_init,
-		.exit = crypto4xx_sk_exit,
-	} },
-	{ .type = CRYPTO_ALG_TYPE_SKCIPHER, .u.cipher = {
-		.base = {
 			.cra_name = "ctr(aes)",
 			.cra_driver_name = "ctr-aes-ppc4xx",
 			.cra_priority = CRYPTO4XX_CRYPTO_PRIORITY,
@@ -1289,26 +1269,6 @@ static struct crypto4xx_alg_common crypto4xx_alg[] = {
 		.init = crypto4xx_sk_init,
 		.exit = crypto4xx_sk_exit,
 	} },
-	{ .type = CRYPTO_ALG_TYPE_SKCIPHER, .u.cipher = {
-		.base = {
-			.cra_name = "ofb(aes)",
-			.cra_driver_name = "ofb-aes-ppc4xx",
-			.cra_priority = CRYPTO4XX_CRYPTO_PRIORITY,
-			.cra_flags = CRYPTO_ALG_ASYNC |
-				CRYPTO_ALG_KERN_DRIVER_ONLY,
-			.cra_blocksize = 1,
-			.cra_ctxsize = sizeof(struct crypto4xx_ctx),
-			.cra_module = THIS_MODULE,
-		},
-		.min_keysize = AES_MIN_KEY_SIZE,
-		.max_keysize = AES_MAX_KEY_SIZE,
-		.ivsize	= AES_IV_SIZE,
-		.setkey	= crypto4xx_setkey_aes_ofb,
-		.encrypt = crypto4xx_encrypt_iv_stream,
-		.decrypt = crypto4xx_decrypt_iv_stream,
-		.init = crypto4xx_sk_init,
-		.exit = crypto4xx_sk_exit,
-	} },
 
 	/* AEAD */
 	{ .type = CRYPTO_ALG_TYPE_AEAD, .u.aead = {
diff --git a/drivers/crypto/amcc/crypto4xx_core.h b/drivers/crypto/amcc/crypto4xx_core.h
index 56c10668c0ab..96355d463b04 100644
--- a/drivers/crypto/amcc/crypto4xx_core.h
+++ b/drivers/crypto/amcc/crypto4xx_core.h
@@ -162,14 +162,10 @@ int crypto4xx_build_pd(struct crypto_async_request *req,
 		       struct scatterlist *dst_tmp);
 int crypto4xx_setkey_aes_cbc(struct crypto_skcipher *cipher,
 			     const u8 *key, unsigned int keylen);
-int crypto4xx_setkey_aes_cfb(struct crypto_skcipher *cipher,
-			     const u8 *key, unsigned int keylen);
 int crypto4xx_setkey_aes_ctr(struct crypto_skcipher *cipher,
 			     const u8 *key, unsigned int keylen);
 int crypto4xx_setkey_aes_ecb(struct crypto_skcipher *cipher,
 			     const u8 *key, unsigned int keylen);
-int crypto4xx_setkey_aes_ofb(struct crypto_skcipher *cipher,
-			     const u8 *key, unsigned int keylen);
 int crypto4xx_setkey_rfc3686(struct crypto_skcipher *cipher,
 			     const u8 *key, unsigned int keylen);
 int crypto4xx_encrypt_ctr(struct skcipher_request *req);
diff --git a/drivers/crypto/amlogic/amlogic-gxl-cipher.c b/drivers/crypto/amlogic/amlogic-gxl-cipher.c
index 3308406612fc..29048da6f50a 100644
--- a/drivers/crypto/amlogic/amlogic-gxl-cipher.c
+++ b/drivers/crypto/amlogic/amlogic-gxl-cipher.c
@@ -327,8 +327,8 @@ int meson_cipher_init(struct crypto_tfm *tfm)
 		return PTR_ERR(op->fallback_tfm);
 	}
 
-	sktfm->reqsize = sizeof(struct meson_cipher_req_ctx) +
-			 crypto_skcipher_reqsize(op->fallback_tfm);
+	crypto_skcipher_set_reqsize(sktfm, sizeof(struct meson_cipher_req_ctx) +
+				    crypto_skcipher_reqsize(op->fallback_tfm));
 
 	return 0;
 }
diff --git a/drivers/crypto/aspeed/Kconfig b/drivers/crypto/aspeed/Kconfig
index db6c5b4cdc40..e93f2f82b418 100644
--- a/drivers/crypto/aspeed/Kconfig
+++ b/drivers/crypto/aspeed/Kconfig
@@ -38,14 +38,12 @@ config CRYPTO_DEV_ASPEED_HACE_CRYPTO
 	select CRYPTO_DES
 	select CRYPTO_ECB
 	select CRYPTO_CBC
-	select CRYPTO_CFB
-	select CRYPTO_OFB
 	select CRYPTO_CTR
 	help
 	  Select here to enable Aspeed Hash & Crypto Engine (HACE)
 	  crypto driver.
 	  Supports AES/DES symmetric-key encryption and decryption
-	  with ECB/CBC/CFB/OFB/CTR options.
+	  with ECB/CBC/CTR options.
 
 config CRYPTO_DEV_ASPEED_ACRY
 	bool "Enable Aspeed ACRY RSA Engine"
diff --git a/drivers/crypto/aspeed/aspeed-hace-crypto.c b/drivers/crypto/aspeed/aspeed-hace-crypto.c
index f0eddb7854e5..a72dfebc53ff 100644
--- a/drivers/crypto/aspeed/aspeed-hace-crypto.c
+++ b/drivers/crypto/aspeed/aspeed-hace-crypto.c
@@ -473,30 +473,6 @@ static int aspeed_tdes_ctr_encrypt(struct skcipher_request *req)
 				HACE_CMD_TRIPLE_DES);
 }
 
-static int aspeed_tdes_ofb_decrypt(struct skcipher_request *req)
-{
-	return aspeed_des_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_OFB |
-				HACE_CMD_TRIPLE_DES);
-}
-
-static int aspeed_tdes_ofb_encrypt(struct skcipher_request *req)
-{
-	return aspeed_des_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_OFB |
-				HACE_CMD_TRIPLE_DES);
-}
-
-static int aspeed_tdes_cfb_decrypt(struct skcipher_request *req)
-{
-	return aspeed_des_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_CFB |
-				HACE_CMD_TRIPLE_DES);
-}
-
-static int aspeed_tdes_cfb_encrypt(struct skcipher_request *req)
-{
-	return aspeed_des_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_CFB |
-				HACE_CMD_TRIPLE_DES);
-}
-
 static int aspeed_tdes_cbc_decrypt(struct skcipher_request *req)
 {
 	return aspeed_des_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_CBC |
@@ -533,30 +509,6 @@ static int aspeed_des_ctr_encrypt(struct skcipher_request *req)
 				HACE_CMD_SINGLE_DES);
 }
 
-static int aspeed_des_ofb_decrypt(struct skcipher_request *req)
-{
-	return aspeed_des_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_OFB |
-				HACE_CMD_SINGLE_DES);
-}
-
-static int aspeed_des_ofb_encrypt(struct skcipher_request *req)
-{
-	return aspeed_des_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_OFB |
-				HACE_CMD_SINGLE_DES);
-}
-
-static int aspeed_des_cfb_decrypt(struct skcipher_request *req)
-{
-	return aspeed_des_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_CFB |
-				HACE_CMD_SINGLE_DES);
-}
-
-static int aspeed_des_cfb_encrypt(struct skcipher_request *req)
-{
-	return aspeed_des_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_CFB |
-				HACE_CMD_SINGLE_DES);
-}
-
 static int aspeed_des_cbc_decrypt(struct skcipher_request *req)
 {
 	return aspeed_des_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_CBC |
@@ -659,26 +611,6 @@ static int aspeed_aes_ctr_encrypt(struct skcipher_request *req)
 	return aspeed_aes_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_CTR);
 }
 
-static int aspeed_aes_ofb_decrypt(struct skcipher_request *req)
-{
-	return aspeed_aes_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_OFB);
-}
-
-static int aspeed_aes_ofb_encrypt(struct skcipher_request *req)
-{
-	return aspeed_aes_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_OFB);
-}
-
-static int aspeed_aes_cfb_decrypt(struct skcipher_request *req)
-{
-	return aspeed_aes_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_CFB);
-}
-
-static int aspeed_aes_cfb_encrypt(struct skcipher_request *req)
-{
-	return aspeed_aes_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_CFB);
-}
-
 static int aspeed_aes_cbc_decrypt(struct skcipher_request *req)
 {
 	return aspeed_aes_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_CBC);
@@ -792,60 +724,6 @@ static struct aspeed_hace_alg aspeed_crypto_algs[] = {
 	},
 	{
 		.alg.skcipher.base = {
-			.ivsize		= AES_BLOCK_SIZE,
-			.min_keysize	= AES_MIN_KEY_SIZE,
-			.max_keysize	= AES_MAX_KEY_SIZE,
-			.setkey		= aspeed_aes_setkey,
-			.encrypt	= aspeed_aes_cfb_encrypt,
-			.decrypt	= aspeed_aes_cfb_decrypt,
-			.init		= aspeed_crypto_cra_init,
-			.exit		= aspeed_crypto_cra_exit,
-			.base = {
-				.cra_name		= "cfb(aes)",
-				.cra_driver_name	= "aspeed-cfb-aes",
-				.cra_priority		= 300,
-				.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
-							  CRYPTO_ALG_ASYNC |
-							  CRYPTO_ALG_NEED_FALLBACK,
-				.cra_blocksize		= 1,
-				.cra_ctxsize		= sizeof(struct aspeed_cipher_ctx),
-				.cra_alignmask		= 0x0f,
-				.cra_module		= THIS_MODULE,
-			}
-		},
-		.alg.skcipher.op = {
-			.do_one_request = aspeed_crypto_do_request,
-		},
-	},
-	{
-		.alg.skcipher.base = {
-			.ivsize		= AES_BLOCK_SIZE,
-			.min_keysize	= AES_MIN_KEY_SIZE,
-			.max_keysize	= AES_MAX_KEY_SIZE,
-			.setkey		= aspeed_aes_setkey,
-			.encrypt	= aspeed_aes_ofb_encrypt,
-			.decrypt	= aspeed_aes_ofb_decrypt,
-			.init		= aspeed_crypto_cra_init,
-			.exit		= aspeed_crypto_cra_exit,
-			.base = {
-				.cra_name		= "ofb(aes)",
-				.cra_driver_name	= "aspeed-ofb-aes",
-				.cra_priority		= 300,
-				.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
-							  CRYPTO_ALG_ASYNC |
-							  CRYPTO_ALG_NEED_FALLBACK,
-				.cra_blocksize		= 1,
-				.cra_ctxsize		= sizeof(struct aspeed_cipher_ctx),
-				.cra_alignmask		= 0x0f,
-				.cra_module		= THIS_MODULE,
-			}
-		},
-		.alg.skcipher.op = {
-			.do_one_request = aspeed_crypto_do_request,
-		},
-	},
-	{
-		.alg.skcipher.base = {
 			.min_keysize	= DES_KEY_SIZE,
 			.max_keysize	= DES_KEY_SIZE,
 			.setkey		= aspeed_des_setkey,
@@ -899,60 +777,6 @@ static struct aspeed_hace_alg aspeed_crypto_algs[] = {
 	},
 	{
 		.alg.skcipher.base = {
-			.ivsize		= DES_BLOCK_SIZE,
-			.min_keysize	= DES_KEY_SIZE,
-			.max_keysize	= DES_KEY_SIZE,
-			.setkey		= aspeed_des_setkey,
-			.encrypt	= aspeed_des_cfb_encrypt,
-			.decrypt	= aspeed_des_cfb_decrypt,
-			.init		= aspeed_crypto_cra_init,
-			.exit		= aspeed_crypto_cra_exit,
-			.base = {
-				.cra_name		= "cfb(des)",
-				.cra_driver_name	= "aspeed-cfb-des",
-				.cra_priority		= 300,
-				.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
-							  CRYPTO_ALG_ASYNC |
-							  CRYPTO_ALG_NEED_FALLBACK,
-				.cra_blocksize		= DES_BLOCK_SIZE,
-				.cra_ctxsize		= sizeof(struct aspeed_cipher_ctx),
-				.cra_alignmask		= 0x0f,
-				.cra_module		= THIS_MODULE,
-			}
-		},
-		.alg.skcipher.op = {
-			.do_one_request = aspeed_crypto_do_request,
-		},
-	},
-	{
-		.alg.skcipher.base = {
-			.ivsize		= DES_BLOCK_SIZE,
-			.min_keysize	= DES_KEY_SIZE,
-			.max_keysize	= DES_KEY_SIZE,
-			.setkey		= aspeed_des_setkey,
-			.encrypt	= aspeed_des_ofb_encrypt,
-			.decrypt	= aspeed_des_ofb_decrypt,
-			.init		= aspeed_crypto_cra_init,
-			.exit		= aspeed_crypto_cra_exit,
-			.base = {
-				.cra_name		= "ofb(des)",
-				.cra_driver_name	= "aspeed-ofb-des",
-				.cra_priority		= 300,
-				.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
-							  CRYPTO_ALG_ASYNC |
-							  CRYPTO_ALG_NEED_FALLBACK,
-				.cra_blocksize		= DES_BLOCK_SIZE,
-				.cra_ctxsize		= sizeof(struct aspeed_cipher_ctx),
-				.cra_alignmask		= 0x0f,
-				.cra_module		= THIS_MODULE,
-			}
-		},
-		.alg.skcipher.op = {
-			.do_one_request = aspeed_crypto_do_request,
-		},
-	},
-	{
-		.alg.skcipher.base = {
 			.min_keysize	= DES3_EDE_KEY_SIZE,
 			.max_keysize	= DES3_EDE_KEY_SIZE,
 			.setkey		= aspeed_des_setkey,
@@ -1004,60 +828,6 @@ static struct aspeed_hace_alg aspeed_crypto_algs[] = {
 			.do_one_request = aspeed_crypto_do_request,
 		},
 	},
-	{
-		.alg.skcipher.base = {
-			.ivsize		= DES_BLOCK_SIZE,
-			.min_keysize	= DES3_EDE_KEY_SIZE,
-			.max_keysize	= DES3_EDE_KEY_SIZE,
-			.setkey		= aspeed_des_setkey,
-			.encrypt	= aspeed_tdes_cfb_encrypt,
-			.decrypt	= aspeed_tdes_cfb_decrypt,
-			.init		= aspeed_crypto_cra_init,
-			.exit		= aspeed_crypto_cra_exit,
-			.base = {
-				.cra_name		= "cfb(des3_ede)",
-				.cra_driver_name	= "aspeed-cfb-tdes",
-				.cra_priority		= 300,
-				.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
-							  CRYPTO_ALG_ASYNC |
-							  CRYPTO_ALG_NEED_FALLBACK,
-				.cra_blocksize		= DES_BLOCK_SIZE,
-				.cra_ctxsize		= sizeof(struct aspeed_cipher_ctx),
-				.cra_alignmask		= 0x0f,
-				.cra_module		= THIS_MODULE,
-			}
-		},
-		.alg.skcipher.op = {
-			.do_one_request = aspeed_crypto_do_request,
-		},
-	},
-	{
-		.alg.skcipher.base = {
-			.ivsize		= DES_BLOCK_SIZE,
-			.min_keysize	= DES3_EDE_KEY_SIZE,
-			.max_keysize	= DES3_EDE_KEY_SIZE,
-			.setkey		= aspeed_des_setkey,
-			.encrypt	= aspeed_tdes_ofb_encrypt,
-			.decrypt	= aspeed_tdes_ofb_decrypt,
-			.init		= aspeed_crypto_cra_init,
-			.exit		= aspeed_crypto_cra_exit,
-			.base = {
-				.cra_name		= "ofb(des3_ede)",
-				.cra_driver_name	= "aspeed-ofb-tdes",
-				.cra_priority		= 300,
-				.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
-							  CRYPTO_ALG_ASYNC |
-							  CRYPTO_ALG_NEED_FALLBACK,
-				.cra_blocksize		= DES_BLOCK_SIZE,
-				.cra_ctxsize		= sizeof(struct aspeed_cipher_ctx),
-				.cra_alignmask		= 0x0f,
-				.cra_module		= THIS_MODULE,
-			}
-		},
-		.alg.skcipher.op = {
-			.do_one_request = aspeed_crypto_do_request,
-		},
-	},
 };
 
 static struct aspeed_hace_alg aspeed_crypto_algs_g6[] = {
diff --git a/drivers/crypto/atmel-aes.c b/drivers/crypto/atmel-aes.c
index d1d93e897892..8bd64fc37e75 100644
--- a/drivers/crypto/atmel-aes.c
+++ b/drivers/crypto/atmel-aes.c
@@ -46,11 +46,6 @@
 #define ATMEL_AES_BUFFER_ORDER	2
 #define ATMEL_AES_BUFFER_SIZE	(PAGE_SIZE << ATMEL_AES_BUFFER_ORDER)
 
-#define CFB8_BLOCK_SIZE		1
-#define CFB16_BLOCK_SIZE	2
-#define CFB32_BLOCK_SIZE	4
-#define CFB64_BLOCK_SIZE	8
-
 #define SIZE_IN_WORDS(x)	((x) >> 2)
 
 /* AES flags */
@@ -60,12 +55,6 @@
 #define AES_FLAGS_OPMODE_MASK	(AES_MR_OPMOD_MASK | AES_MR_CFBS_MASK)
 #define AES_FLAGS_ECB		AES_MR_OPMOD_ECB
 #define AES_FLAGS_CBC		AES_MR_OPMOD_CBC
-#define AES_FLAGS_OFB		AES_MR_OPMOD_OFB
-#define AES_FLAGS_CFB128	(AES_MR_OPMOD_CFB | AES_MR_CFBS_128b)
-#define AES_FLAGS_CFB64		(AES_MR_OPMOD_CFB | AES_MR_CFBS_64b)
-#define AES_FLAGS_CFB32		(AES_MR_OPMOD_CFB | AES_MR_CFBS_32b)
-#define AES_FLAGS_CFB16		(AES_MR_OPMOD_CFB | AES_MR_CFBS_16b)
-#define AES_FLAGS_CFB8		(AES_MR_OPMOD_CFB | AES_MR_CFBS_8b)
 #define AES_FLAGS_CTR		AES_MR_OPMOD_CTR
 #define AES_FLAGS_GCM		AES_MR_OPMOD_GCM
 #define AES_FLAGS_XTS		AES_MR_OPMOD_XTS
@@ -87,7 +76,6 @@
 
 struct atmel_aes_caps {
 	bool			has_dualbuff;
-	bool			has_cfb64;
 	bool			has_gcm;
 	bool			has_xts;
 	bool			has_authenc;
@@ -860,22 +848,6 @@ static int atmel_aes_dma_start(struct atmel_aes_dev *dd,
 	int err;
 
 	switch (dd->ctx->block_size) {
-	case CFB8_BLOCK_SIZE:
-		addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
-		maxburst = 1;
-		break;
-
-	case CFB16_BLOCK_SIZE:
-		addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
-		maxburst = 1;
-		break;
-
-	case CFB32_BLOCK_SIZE:
-	case CFB64_BLOCK_SIZE:
-		addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
-		maxburst = 1;
-		break;
-
 	case AES_BLOCK_SIZE:
 		addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 		maxburst = dd->caps.max_burst_size;
@@ -1103,7 +1075,7 @@ static int atmel_aes_crypt(struct skcipher_request *req, unsigned long mode)
 	}
 
 	/*
-	 * ECB, CBC, CFB, OFB or CTR mode require the plaintext and ciphertext
+	 * ECB, CBC or CTR mode require the plaintext and ciphertext
 	 * to have a positve integer length.
 	 */
 	if (!req->cryptlen && opmode != AES_FLAGS_XTS)
@@ -1113,27 +1085,7 @@ static int atmel_aes_crypt(struct skcipher_request *req, unsigned long mode)
 	    !IS_ALIGNED(req->cryptlen, crypto_skcipher_blocksize(skcipher)))
 		return -EINVAL;
 
-	switch (mode & AES_FLAGS_OPMODE_MASK) {
-	case AES_FLAGS_CFB8:
-		ctx->block_size = CFB8_BLOCK_SIZE;
-		break;
-
-	case AES_FLAGS_CFB16:
-		ctx->block_size = CFB16_BLOCK_SIZE;
-		break;
-
-	case AES_FLAGS_CFB32:
-		ctx->block_size = CFB32_BLOCK_SIZE;
-		break;
-
-	case AES_FLAGS_CFB64:
-		ctx->block_size = CFB64_BLOCK_SIZE;
-		break;
-
-	default:
-		ctx->block_size = AES_BLOCK_SIZE;
-		break;
-	}
+	ctx->block_size = AES_BLOCK_SIZE;
 	ctx->is_aead = false;
 
 	rctx = skcipher_request_ctx(req);
@@ -1188,66 +1140,6 @@ static int atmel_aes_cbc_decrypt(struct skcipher_request *req)
 	return atmel_aes_crypt(req, AES_FLAGS_CBC);
 }
 
-static int atmel_aes_ofb_encrypt(struct skcipher_request *req)
-{
-	return atmel_aes_crypt(req, AES_FLAGS_OFB | AES_FLAGS_ENCRYPT);
-}
-
-static int atmel_aes_ofb_decrypt(struct skcipher_request *req)
-{
-	return atmel_aes_crypt(req, AES_FLAGS_OFB);
-}
-
-static int atmel_aes_cfb_encrypt(struct skcipher_request *req)
-{
-	return atmel_aes_crypt(req, AES_FLAGS_CFB128 | AES_FLAGS_ENCRYPT);
-}
-
-static int atmel_aes_cfb_decrypt(struct skcipher_request *req)
-{
-	return atmel_aes_crypt(req, AES_FLAGS_CFB128);
-}
-
-static int atmel_aes_cfb64_encrypt(struct skcipher_request *req)
-{
-	return atmel_aes_crypt(req, AES_FLAGS_CFB64 | AES_FLAGS_ENCRYPT);
-}
-
-static int atmel_aes_cfb64_decrypt(struct skcipher_request *req)
-{
-	return atmel_aes_crypt(req, AES_FLAGS_CFB64);
-}
-
-static int atmel_aes_cfb32_encrypt(struct skcipher_request *req)
-{
-	return atmel_aes_crypt(req, AES_FLAGS_CFB32 | AES_FLAGS_ENCRYPT);
-}
-
-static int atmel_aes_cfb32_decrypt(struct skcipher_request *req)
-{
-	return atmel_aes_crypt(req, AES_FLAGS_CFB32);
-}
-
-static int atmel_aes_cfb16_encrypt(struct skcipher_request *req)
-{
-	return atmel_aes_crypt(req, AES_FLAGS_CFB16 | AES_FLAGS_ENCRYPT);
-}
-
-static int atmel_aes_cfb16_decrypt(struct skcipher_request *req)
-{
-	return atmel_aes_crypt(req, AES_FLAGS_CFB16);
-}
-
-static int atmel_aes_cfb8_encrypt(struct skcipher_request *req)
-{
-	return atmel_aes_crypt(req, AES_FLAGS_CFB8 | AES_FLAGS_ENCRYPT);
-}
-
-static int atmel_aes_cfb8_decrypt(struct skcipher_request *req)
-{
-	return atmel_aes_crypt(req, AES_FLAGS_CFB8);
-}
-
 static int atmel_aes_ctr_encrypt(struct skcipher_request *req)
 {
 	return atmel_aes_crypt(req, AES_FLAGS_CTR | AES_FLAGS_ENCRYPT);
@@ -1319,76 +1211,6 @@ static struct skcipher_alg aes_algs[] = {
 	.ivsize			= AES_BLOCK_SIZE,
 },
 {
-	.base.cra_name		= "ofb(aes)",
-	.base.cra_driver_name	= "atmel-ofb-aes",
-	.base.cra_blocksize	= 1,
-	.base.cra_ctxsize	= sizeof(struct atmel_aes_ctx),
-
-	.init			= atmel_aes_init_tfm,
-	.min_keysize		= AES_MIN_KEY_SIZE,
-	.max_keysize		= AES_MAX_KEY_SIZE,
-	.setkey			= atmel_aes_setkey,
-	.encrypt		= atmel_aes_ofb_encrypt,
-	.decrypt		= atmel_aes_ofb_decrypt,
-	.ivsize			= AES_BLOCK_SIZE,
-},
-{
-	.base.cra_name		= "cfb(aes)",
-	.base.cra_driver_name	= "atmel-cfb-aes",
-	.base.cra_blocksize	= 1,
-	.base.cra_ctxsize	= sizeof(struct atmel_aes_ctx),
-
-	.init			= atmel_aes_init_tfm,
-	.min_keysize		= AES_MIN_KEY_SIZE,
-	.max_keysize		= AES_MAX_KEY_SIZE,
-	.setkey			= atmel_aes_setkey,
-	.encrypt		= atmel_aes_cfb_encrypt,
-	.decrypt		= atmel_aes_cfb_decrypt,
-	.ivsize			= AES_BLOCK_SIZE,
-},
-{
-	.base.cra_name		= "cfb32(aes)",
-	.base.cra_driver_name	= "atmel-cfb32-aes",
-	.base.cra_blocksize	= CFB32_BLOCK_SIZE,
-	.base.cra_ctxsize	= sizeof(struct atmel_aes_ctx),
-
-	.init			= atmel_aes_init_tfm,
-	.min_keysize		= AES_MIN_KEY_SIZE,
-	.max_keysize		= AES_MAX_KEY_SIZE,
-	.setkey			= atmel_aes_setkey,
-	.encrypt		= atmel_aes_cfb32_encrypt,
-	.decrypt		= atmel_aes_cfb32_decrypt,
-	.ivsize			= AES_BLOCK_SIZE,
-},
-{
-	.base.cra_name		= "cfb16(aes)",
-	.base.cra_driver_name	= "atmel-cfb16-aes",
-	.base.cra_blocksize	= CFB16_BLOCK_SIZE,
-	.base.cra_ctxsize	= sizeof(struct atmel_aes_ctx),
-
-	.init			= atmel_aes_init_tfm,
-	.min_keysize		= AES_MIN_KEY_SIZE,
-	.max_keysize		= AES_MAX_KEY_SIZE,
-	.setkey			= atmel_aes_setkey,
-	.encrypt		= atmel_aes_cfb16_encrypt,
-	.decrypt		= atmel_aes_cfb16_decrypt,
-	.ivsize			= AES_BLOCK_SIZE,
-},
-{
-	.base.cra_name		= "cfb8(aes)",
-	.base.cra_driver_name	= "atmel-cfb8-aes",
-	.base.cra_blocksize	= CFB8_BLOCK_SIZE,
-	.base.cra_ctxsize	= sizeof(struct atmel_aes_ctx),
-
-	.init			= atmel_aes_init_tfm,
-	.min_keysize		= AES_MIN_KEY_SIZE,
-	.max_keysize		= AES_MAX_KEY_SIZE,
-	.setkey			= atmel_aes_setkey,
-	.encrypt		= atmel_aes_cfb8_encrypt,
-	.decrypt		= atmel_aes_cfb8_decrypt,
-	.ivsize			= AES_BLOCK_SIZE,
-},
-{
 	.base.cra_name		= "ctr(aes)",
 	.base.cra_driver_name	= "atmel-ctr-aes",
 	.base.cra_blocksize	= 1,
@@ -1404,21 +1226,6 @@ static struct skcipher_alg aes_algs[] = {
 },
 };
 
-static struct skcipher_alg aes_cfb64_alg = {
-	.base.cra_name		= "cfb64(aes)",
-	.base.cra_driver_name	= "atmel-cfb64-aes",
-	.base.cra_blocksize	= CFB64_BLOCK_SIZE,
-	.base.cra_ctxsize	= sizeof(struct atmel_aes_ctx),
-
-	.init			= atmel_aes_init_tfm,
-	.min_keysize		= AES_MIN_KEY_SIZE,
-	.max_keysize		= AES_MAX_KEY_SIZE,
-	.setkey			= atmel_aes_setkey,
-	.encrypt		= atmel_aes_cfb64_encrypt,
-	.decrypt		= atmel_aes_cfb64_decrypt,
-	.ivsize			= AES_BLOCK_SIZE,
-};
-
 
 /* gcm aead functions */
 
@@ -2407,9 +2214,6 @@ static void atmel_aes_unregister_algs(struct atmel_aes_dev *dd)
 	if (dd->caps.has_gcm)
 		crypto_unregister_aead(&aes_gcm_alg);
 
-	if (dd->caps.has_cfb64)
-		crypto_unregister_skcipher(&aes_cfb64_alg);
-
 	for (i = 0; i < ARRAY_SIZE(aes_algs); i++)
 		crypto_unregister_skcipher(&aes_algs[i]);
 }
@@ -2434,14 +2238,6 @@ static int atmel_aes_register_algs(struct atmel_aes_dev *dd)
 			goto err_aes_algs;
 	}
 
-	if (dd->caps.has_cfb64) {
-		atmel_aes_crypto_alg_init(&aes_cfb64_alg.base);
-
-		err = crypto_register_skcipher(&aes_cfb64_alg);
-		if (err)
-			goto err_aes_cfb64_alg;
-	}
-
 	if (dd->caps.has_gcm) {
 		atmel_aes_crypto_alg_init(&aes_gcm_alg.base);
 
@@ -2482,8 +2278,6 @@ err_aes_authenc_alg:
 err_aes_xts_alg:
 	crypto_unregister_aead(&aes_gcm_alg);
 err_aes_gcm_alg:
-	crypto_unregister_skcipher(&aes_cfb64_alg);
-err_aes_cfb64_alg:
 	i = ARRAY_SIZE(aes_algs);
 err_aes_algs:
 	for (j = 0; j < i; j++)
@@ -2495,7 +2289,6 @@ err_aes_algs:
 static void atmel_aes_get_cap(struct atmel_aes_dev *dd)
 {
 	dd->caps.has_dualbuff = 0;
-	dd->caps.has_cfb64 = 0;
 	dd->caps.has_gcm = 0;
 	dd->caps.has_xts = 0;
 	dd->caps.has_authenc = 0;
@@ -2507,7 +2300,6 @@ static void atmel_aes_get_cap(struct atmel_aes_dev *dd)
 	case 0x600:
 	case 0x500:
 		dd->caps.has_dualbuff = 1;
-		dd->caps.has_cfb64 = 1;
 		dd->caps.has_gcm = 1;
 		dd->caps.has_xts = 1;
 		dd->caps.has_authenc = 1;
@@ -2515,13 +2307,11 @@ static void atmel_aes_get_cap(struct atmel_aes_dev *dd)
 		break;
 	case 0x200:
 		dd->caps.has_dualbuff = 1;
-		dd->caps.has_cfb64 = 1;
 		dd->caps.has_gcm = 1;
 		dd->caps.max_burst_size = 4;
 		break;
 	case 0x130:
 		dd->caps.has_dualbuff = 1;
-		dd->caps.has_cfb64 = 1;
 		dd->caps.max_burst_size = 4;
 		break;
 	case 0x120:
diff --git a/drivers/crypto/atmel-tdes.c b/drivers/crypto/atmel-tdes.c
index 27b7000e25bc..dcc2380a5889 100644
--- a/drivers/crypto/atmel-tdes.c
+++ b/drivers/crypto/atmel-tdes.c
@@ -45,11 +45,6 @@
 #define TDES_FLAGS_OPMODE_MASK	(TDES_MR_OPMOD_MASK | TDES_MR_CFBS_MASK)
 #define TDES_FLAGS_ECB		TDES_MR_OPMOD_ECB
 #define TDES_FLAGS_CBC		TDES_MR_OPMOD_CBC
-#define TDES_FLAGS_OFB		TDES_MR_OPMOD_OFB
-#define TDES_FLAGS_CFB64	(TDES_MR_OPMOD_CFB | TDES_MR_CFBS_64b)
-#define TDES_FLAGS_CFB32	(TDES_MR_OPMOD_CFB | TDES_MR_CFBS_32b)
-#define TDES_FLAGS_CFB16	(TDES_MR_OPMOD_CFB | TDES_MR_CFBS_16b)
-#define TDES_FLAGS_CFB8		(TDES_MR_OPMOD_CFB | TDES_MR_CFBS_8b)
 
 #define TDES_FLAGS_MODE_MASK	(TDES_FLAGS_OPMODE_MASK | TDES_FLAGS_ENCRYPT)
 
@@ -60,13 +55,8 @@
 
 #define ATMEL_TDES_QUEUE_LENGTH	50
 
-#define CFB8_BLOCK_SIZE		1
-#define CFB16_BLOCK_SIZE	2
-#define CFB32_BLOCK_SIZE	4
-
 struct atmel_tdes_caps {
 	bool	has_dma;
-	u32		has_cfb_3keys;
 };
 
 struct atmel_tdes_dev;
@@ -376,7 +366,6 @@ static int atmel_tdes_crypt_pdc(struct atmel_tdes_dev *dd,
 				dma_addr_t dma_addr_in,
 				dma_addr_t dma_addr_out, int length)
 {
-	struct atmel_tdes_reqctx *rctx = skcipher_request_ctx(dd->req);
 	int len32;
 
 	dd->dma_size = length;
@@ -386,19 +375,7 @@ static int atmel_tdes_crypt_pdc(struct atmel_tdes_dev *dd,
 					   DMA_TO_DEVICE);
 	}
 
-	switch (rctx->mode & TDES_FLAGS_OPMODE_MASK) {
-	case TDES_FLAGS_CFB8:
-		len32 = DIV_ROUND_UP(length, sizeof(u8));
-		break;
-
-	case TDES_FLAGS_CFB16:
-		len32 = DIV_ROUND_UP(length, sizeof(u16));
-		break;
-
-	default:
-		len32 = DIV_ROUND_UP(length, sizeof(u32));
-		break;
-	}
+	len32 = DIV_ROUND_UP(length, sizeof(u32));
 
 	atmel_tdes_write(dd, TDES_PTCR, TDES_PTCR_TXTDIS|TDES_PTCR_RXTDIS);
 	atmel_tdes_write(dd, TDES_TPR, dma_addr_in);
@@ -419,7 +396,6 @@ static int atmel_tdes_crypt_dma(struct atmel_tdes_dev *dd,
 				dma_addr_t dma_addr_in,
 				dma_addr_t dma_addr_out, int length)
 {
-	struct atmel_tdes_reqctx *rctx = skcipher_request_ctx(dd->req);
 	struct scatterlist sg[2];
 	struct dma_async_tx_descriptor	*in_desc, *out_desc;
 	enum dma_slave_buswidth addr_width;
@@ -431,19 +407,7 @@ static int atmel_tdes_crypt_dma(struct atmel_tdes_dev *dd,
 					   DMA_TO_DEVICE);
 	}
 
-	switch (rctx->mode & TDES_FLAGS_OPMODE_MASK) {
-	case TDES_FLAGS_CFB8:
-		addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
-		break;
-
-	case TDES_FLAGS_CFB16:
-		addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
-		break;
-
-	default:
-		addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
-		break;
-	}
+	addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 
 	dd->dma_lch_in.dma_conf.dst_addr_width = addr_width;
 	dd->dma_lch_out.dma_conf.src_addr_width = addr_width;
@@ -680,39 +644,11 @@ static int atmel_tdes_crypt(struct skcipher_request *req, unsigned long mode)
 	if (!req->cryptlen)
 		return 0;
 
-	switch (mode & TDES_FLAGS_OPMODE_MASK) {
-	case TDES_FLAGS_CFB8:
-		if (!IS_ALIGNED(req->cryptlen, CFB8_BLOCK_SIZE)) {
-			dev_dbg(dev, "request size is not exact amount of CFB8 blocks\n");
-			return -EINVAL;
-		}
-		ctx->block_size = CFB8_BLOCK_SIZE;
-		break;
-
-	case TDES_FLAGS_CFB16:
-		if (!IS_ALIGNED(req->cryptlen, CFB16_BLOCK_SIZE)) {
-			dev_dbg(dev, "request size is not exact amount of CFB16 blocks\n");
-			return -EINVAL;
-		}
-		ctx->block_size = CFB16_BLOCK_SIZE;
-		break;
-
-	case TDES_FLAGS_CFB32:
-		if (!IS_ALIGNED(req->cryptlen, CFB32_BLOCK_SIZE)) {
-			dev_dbg(dev, "request size is not exact amount of CFB32 blocks\n");
-			return -EINVAL;
-		}
-		ctx->block_size = CFB32_BLOCK_SIZE;
-		break;
-
-	default:
-		if (!IS_ALIGNED(req->cryptlen, DES_BLOCK_SIZE)) {
-			dev_dbg(dev, "request size is not exact amount of DES blocks\n");
-			return -EINVAL;
-		}
-		ctx->block_size = DES_BLOCK_SIZE;
-		break;
+	if (!IS_ALIGNED(req->cryptlen, DES_BLOCK_SIZE)) {
+		dev_dbg(dev, "request size is not exact amount of DES blocks\n");
+		return -EINVAL;
 	}
+	ctx->block_size = DES_BLOCK_SIZE;
 
 	rctx->mode = mode;
 
@@ -832,55 +768,6 @@ static int atmel_tdes_cbc_decrypt(struct skcipher_request *req)
 {
 	return atmel_tdes_crypt(req, TDES_FLAGS_CBC);
 }
-static int atmel_tdes_cfb_encrypt(struct skcipher_request *req)
-{
-	return atmel_tdes_crypt(req, TDES_FLAGS_CFB64 | TDES_FLAGS_ENCRYPT);
-}
-
-static int atmel_tdes_cfb_decrypt(struct skcipher_request *req)
-{
-	return atmel_tdes_crypt(req, TDES_FLAGS_CFB64);
-}
-
-static int atmel_tdes_cfb8_encrypt(struct skcipher_request *req)
-{
-	return atmel_tdes_crypt(req, TDES_FLAGS_CFB8 | TDES_FLAGS_ENCRYPT);
-}
-
-static int atmel_tdes_cfb8_decrypt(struct skcipher_request *req)
-{
-	return atmel_tdes_crypt(req, TDES_FLAGS_CFB8);
-}
-
-static int atmel_tdes_cfb16_encrypt(struct skcipher_request *req)
-{
-	return atmel_tdes_crypt(req, TDES_FLAGS_CFB16 | TDES_FLAGS_ENCRYPT);
-}
-
-static int atmel_tdes_cfb16_decrypt(struct skcipher_request *req)
-{
-	return atmel_tdes_crypt(req, TDES_FLAGS_CFB16);
-}
-
-static int atmel_tdes_cfb32_encrypt(struct skcipher_request *req)
-{
-	return atmel_tdes_crypt(req, TDES_FLAGS_CFB32 | TDES_FLAGS_ENCRYPT);
-}
-
-static int atmel_tdes_cfb32_decrypt(struct skcipher_request *req)
-{
-	return atmel_tdes_crypt(req, TDES_FLAGS_CFB32);
-}
-
-static int atmel_tdes_ofb_encrypt(struct skcipher_request *req)
-{
-	return atmel_tdes_crypt(req, TDES_FLAGS_OFB | TDES_FLAGS_ENCRYPT);
-}
-
-static int atmel_tdes_ofb_decrypt(struct skcipher_request *req)
-{
-	return atmel_tdes_crypt(req, TDES_FLAGS_OFB);
-}
 
 static int atmel_tdes_init_tfm(struct crypto_skcipher *tfm)
 {
@@ -932,71 +819,6 @@ static struct skcipher_alg tdes_algs[] = {
 	.decrypt		= atmel_tdes_cbc_decrypt,
 },
 {
-	.base.cra_name		= "cfb(des)",
-	.base.cra_driver_name	= "atmel-cfb-des",
-	.base.cra_blocksize	= DES_BLOCK_SIZE,
-	.base.cra_alignmask	= 0x7,
-
-	.min_keysize		= DES_KEY_SIZE,
-	.max_keysize		= DES_KEY_SIZE,
-	.ivsize			= DES_BLOCK_SIZE,
-	.setkey			= atmel_des_setkey,
-	.encrypt		= atmel_tdes_cfb_encrypt,
-	.decrypt		= atmel_tdes_cfb_decrypt,
-},
-{
-	.base.cra_name		= "cfb8(des)",
-	.base.cra_driver_name	= "atmel-cfb8-des",
-	.base.cra_blocksize	= CFB8_BLOCK_SIZE,
-	.base.cra_alignmask	= 0,
-
-	.min_keysize		= DES_KEY_SIZE,
-	.max_keysize		= DES_KEY_SIZE,
-	.ivsize			= DES_BLOCK_SIZE,
-	.setkey			= atmel_des_setkey,
-	.encrypt		= atmel_tdes_cfb8_encrypt,
-	.decrypt		= atmel_tdes_cfb8_decrypt,
-},
-{
-	.base.cra_name		= "cfb16(des)",
-	.base.cra_driver_name	= "atmel-cfb16-des",
-	.base.cra_blocksize	= CFB16_BLOCK_SIZE,
-	.base.cra_alignmask	= 0x1,
-
-	.min_keysize		= DES_KEY_SIZE,
-	.max_keysize		= DES_KEY_SIZE,
-	.ivsize			= DES_BLOCK_SIZE,
-	.setkey			= atmel_des_setkey,
-	.encrypt		= atmel_tdes_cfb16_encrypt,
-	.decrypt		= atmel_tdes_cfb16_decrypt,
-},
-{
-	.base.cra_name		= "cfb32(des)",
-	.base.cra_driver_name	= "atmel-cfb32-des",
-	.base.cra_blocksize	= CFB32_BLOCK_SIZE,
-	.base.cra_alignmask	= 0x3,
-
-	.min_keysize		= DES_KEY_SIZE,
-	.max_keysize		= DES_KEY_SIZE,
-	.ivsize			= DES_BLOCK_SIZE,
-	.setkey			= atmel_des_setkey,
-	.encrypt		= atmel_tdes_cfb32_encrypt,
-	.decrypt		= atmel_tdes_cfb32_decrypt,
-},
-{
-	.base.cra_name		= "ofb(des)",
-	.base.cra_driver_name	= "atmel-ofb-des",
-	.base.cra_blocksize	= 1,
-	.base.cra_alignmask	= 0x7,
-
-	.min_keysize		= DES_KEY_SIZE,
-	.max_keysize		= DES_KEY_SIZE,
-	.ivsize			= DES_BLOCK_SIZE,
-	.setkey			= atmel_des_setkey,
-	.encrypt		= atmel_tdes_ofb_encrypt,
-	.decrypt		= atmel_tdes_ofb_decrypt,
-},
-{
 	.base.cra_name		= "ecb(des3_ede)",
 	.base.cra_driver_name	= "atmel-ecb-tdes",
 	.base.cra_blocksize	= DES_BLOCK_SIZE,
@@ -1021,19 +843,6 @@ static struct skcipher_alg tdes_algs[] = {
 	.decrypt		= atmel_tdes_cbc_decrypt,
 	.ivsize			= DES_BLOCK_SIZE,
 },
-{
-	.base.cra_name		= "ofb(des3_ede)",
-	.base.cra_driver_name	= "atmel-ofb-tdes",
-	.base.cra_blocksize	= DES_BLOCK_SIZE,
-	.base.cra_alignmask	= 0x7,
-
-	.min_keysize		= DES3_EDE_KEY_SIZE,
-	.max_keysize		= DES3_EDE_KEY_SIZE,
-	.setkey			= atmel_tdes_setkey,
-	.encrypt		= atmel_tdes_ofb_encrypt,
-	.decrypt		= atmel_tdes_ofb_decrypt,
-	.ivsize			= DES_BLOCK_SIZE,
-},
 };
 
 static void atmel_tdes_queue_task(unsigned long data)
@@ -1121,14 +930,12 @@ static void atmel_tdes_get_cap(struct atmel_tdes_dev *dd)
 {
 
 	dd->caps.has_dma = 0;
-	dd->caps.has_cfb_3keys = 0;
 
 	/* keep only major version number */
 	switch (dd->hw_version & 0xf00) {
 	case 0x800:
 	case 0x700:
 		dd->caps.has_dma = 1;
-		dd->caps.has_cfb_3keys = 1;
 		break;
 	case 0x600:
 		break;
diff --git a/drivers/crypto/axis/artpec6_crypto.c b/drivers/crypto/axis/artpec6_crypto.c
index ef9fe13ffa59..dbc1d483f2af 100644
--- a/drivers/crypto/axis/artpec6_crypto.c
+++ b/drivers/crypto/axis/artpec6_crypto.c
@@ -1535,7 +1535,8 @@ static int artpec6_crypto_aes_ecb_init(struct crypto_skcipher *tfm)
 {
 	struct artpec6_cryptotfm_context *ctx = crypto_skcipher_ctx(tfm);
 
-	tfm->reqsize = sizeof(struct artpec6_crypto_request_context);
+	crypto_skcipher_set_reqsize(tfm,
+				    sizeof(struct artpec6_crypto_request_context));
 	ctx->crypto_type = ARTPEC6_CRYPTO_CIPHER_AES_ECB;
 
 	return 0;
@@ -1551,7 +1552,8 @@ static int artpec6_crypto_aes_ctr_init(struct crypto_skcipher *tfm)
 	if (IS_ERR(ctx->fallback))
 		return PTR_ERR(ctx->fallback);
 
-	tfm->reqsize = sizeof(struct artpec6_crypto_request_context);
+	crypto_skcipher_set_reqsize(tfm,
+				    sizeof(struct artpec6_crypto_request_context));
 	ctx->crypto_type = ARTPEC6_CRYPTO_CIPHER_AES_CTR;
 
 	return 0;
@@ -1561,7 +1563,8 @@ static int artpec6_crypto_aes_cbc_init(struct crypto_skcipher *tfm)
 {
 	struct artpec6_cryptotfm_context *ctx = crypto_skcipher_ctx(tfm);
 
-	tfm->reqsize = sizeof(struct artpec6_crypto_request_context);
+	crypto_skcipher_set_reqsize(tfm,
+				    sizeof(struct artpec6_crypto_request_context));
 	ctx->crypto_type = ARTPEC6_CRYPTO_CIPHER_AES_CBC;
 
 	return 0;
@@ -1571,7 +1574,8 @@ static int artpec6_crypto_aes_xts_init(struct crypto_skcipher *tfm)
 {
 	struct artpec6_cryptotfm_context *ctx = crypto_skcipher_ctx(tfm);
 
-	tfm->reqsize = sizeof(struct artpec6_crypto_request_context);
+	crypto_skcipher_set_reqsize(tfm,
+				    sizeof(struct artpec6_crypto_request_context));
 	ctx->crypto_type = ARTPEC6_CRYPTO_CIPHER_AES_XTS;
 
 	return 0;
diff --git a/drivers/crypto/bcm/cipher.c b/drivers/crypto/bcm/cipher.c
index 10968ddb146b..1a3ecd44cbaf 100644
--- a/drivers/crypto/bcm/cipher.c
+++ b/drivers/crypto/bcm/cipher.c
@@ -3517,25 +3517,6 @@ static struct iproc_alg_s driver_algs[] = {
 	{
 	 .type = CRYPTO_ALG_TYPE_SKCIPHER,
 	 .alg.skcipher = {
-			.base.cra_name = "ofb(des)",
-			.base.cra_driver_name = "ofb-des-iproc",
-			.base.cra_blocksize = DES_BLOCK_SIZE,
-			.min_keysize = DES_KEY_SIZE,
-			.max_keysize = DES_KEY_SIZE,
-			.ivsize = DES_BLOCK_SIZE,
-			},
-	 .cipher_info = {
-			 .alg = CIPHER_ALG_DES,
-			 .mode = CIPHER_MODE_OFB,
-			 },
-	 .auth_info = {
-		       .alg = HASH_ALG_NONE,
-		       .mode = HASH_MODE_NONE,
-		       },
-	 },
-	{
-	 .type = CRYPTO_ALG_TYPE_SKCIPHER,
-	 .alg.skcipher = {
 			.base.cra_name = "cbc(des)",
 			.base.cra_driver_name = "cbc-des-iproc",
 			.base.cra_blocksize = DES_BLOCK_SIZE,
@@ -3574,25 +3555,6 @@ static struct iproc_alg_s driver_algs[] = {
 	{
 	 .type = CRYPTO_ALG_TYPE_SKCIPHER,
 	 .alg.skcipher = {
-			.base.cra_name = "ofb(des3_ede)",
-			.base.cra_driver_name = "ofb-des3-iproc",
-			.base.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.min_keysize = DES3_EDE_KEY_SIZE,
-			.max_keysize = DES3_EDE_KEY_SIZE,
-			.ivsize = DES3_EDE_BLOCK_SIZE,
-			},
-	 .cipher_info = {
-			 .alg = CIPHER_ALG_3DES,
-			 .mode = CIPHER_MODE_OFB,
-			 },
-	 .auth_info = {
-		       .alg = HASH_ALG_NONE,
-		       .mode = HASH_MODE_NONE,
-		       },
-	 },
-	{
-	 .type = CRYPTO_ALG_TYPE_SKCIPHER,
-	 .alg.skcipher = {
 			.base.cra_name = "cbc(des3_ede)",
 			.base.cra_driver_name = "cbc-des3-iproc",
 			.base.cra_blocksize = DES3_EDE_BLOCK_SIZE,
@@ -3631,25 +3593,6 @@ static struct iproc_alg_s driver_algs[] = {
 	{
 	 .type = CRYPTO_ALG_TYPE_SKCIPHER,
 	 .alg.skcipher = {
-			.base.cra_name = "ofb(aes)",
-			.base.cra_driver_name = "ofb-aes-iproc",
-			.base.cra_blocksize = AES_BLOCK_SIZE,
-			.min_keysize = AES_MIN_KEY_SIZE,
-			.max_keysize = AES_MAX_KEY_SIZE,
-			.ivsize = AES_BLOCK_SIZE,
-			},
-	 .cipher_info = {
-			 .alg = CIPHER_ALG_AES,
-			 .mode = CIPHER_MODE_OFB,
-			 },
-	 .auth_info = {
-		       .alg = HASH_ALG_NONE,
-		       .mode = HASH_MODE_NONE,
-		       },
-	 },
-	{
-	 .type = CRYPTO_ALG_TYPE_SKCIPHER,
-	 .alg.skcipher = {
 			.base.cra_name = "cbc(aes)",
 			.base.cra_driver_name = "cbc-aes-iproc",
 			.base.cra_blocksize = AES_BLOCK_SIZE,
diff --git a/drivers/crypto/cavium/cpt/cptvf_algs.c b/drivers/crypto/cavium/cpt/cptvf_algs.c
index ee476c6c7f82..219fe9be7606 100644
--- a/drivers/crypto/cavium/cpt/cptvf_algs.c
+++ b/drivers/crypto/cavium/cpt/cptvf_algs.c
@@ -311,12 +311,6 @@ static int cvm_ecb_aes_setkey(struct crypto_skcipher *cipher, const u8 *key,
 	return cvm_setkey(cipher, key, keylen, AES_ECB);
 }
 
-static int cvm_cfb_aes_setkey(struct crypto_skcipher *cipher, const u8 *key,
-			      u32 keylen)
-{
-	return cvm_setkey(cipher, key, keylen, AES_CFB);
-}
-
 static int cvm_cbc_des3_setkey(struct crypto_skcipher *cipher, const u8 *key,
 			       u32 keylen)
 {
@@ -394,24 +388,6 @@ static struct skcipher_alg algs[] = { {
 }, {
 	.base.cra_flags		= CRYPTO_ALG_ASYNC |
 				  CRYPTO_ALG_ALLOCATES_MEMORY,
-	.base.cra_blocksize	= AES_BLOCK_SIZE,
-	.base.cra_ctxsize	= sizeof(struct cvm_enc_ctx),
-	.base.cra_alignmask	= 7,
-	.base.cra_priority	= 4001,
-	.base.cra_name		= "cfb(aes)",
-	.base.cra_driver_name	= "cavium-cfb-aes",
-	.base.cra_module	= THIS_MODULE,
-
-	.ivsize			= AES_BLOCK_SIZE,
-	.min_keysize		= AES_MIN_KEY_SIZE,
-	.max_keysize		= AES_MAX_KEY_SIZE,
-	.setkey			= cvm_cfb_aes_setkey,
-	.encrypt		= cvm_encrypt,
-	.decrypt		= cvm_decrypt,
-	.init			= cvm_enc_dec_init,
-}, {
-	.base.cra_flags		= CRYPTO_ALG_ASYNC |
-				  CRYPTO_ALG_ALLOCATES_MEMORY,
 	.base.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct cvm_des3_ctx),
 	.base.cra_alignmask	= 7,
diff --git a/drivers/crypto/cavium/nitrox/nitrox_skcipher.c b/drivers/crypto/cavium/nitrox/nitrox_skcipher.c
index 138261dcd032..6e5e667bab75 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_skcipher.c
+++ b/drivers/crypto/cavium/nitrox/nitrox_skcipher.c
@@ -421,25 +421,6 @@ static struct skcipher_alg nitrox_skciphers[] = { {
 	.exit = nitrox_skcipher_exit,
 }, {
 	.base = {
-		.cra_name = "cfb(aes)",
-		.cra_driver_name = "n5_cfb(aes)",
-		.cra_priority = PRIO,
-		.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY,
-		.cra_blocksize = AES_BLOCK_SIZE,
-		.cra_ctxsize = sizeof(struct nitrox_crypto_ctx),
-		.cra_alignmask = 0,
-		.cra_module = THIS_MODULE,
-	},
-	.min_keysize = AES_MIN_KEY_SIZE,
-	.max_keysize = AES_MAX_KEY_SIZE,
-	.ivsize = AES_BLOCK_SIZE,
-	.setkey = nitrox_aes_setkey,
-	.encrypt = nitrox_aes_encrypt,
-	.decrypt = nitrox_aes_decrypt,
-	.init = nitrox_skcipher_init,
-	.exit = nitrox_skcipher_exit,
-}, {
-	.base = {
 		.cra_name = "xts(aes)",
 		.cra_driver_name = "n5_xts(aes)",
 		.cra_priority = PRIO,
diff --git a/drivers/crypto/ccp/ccp-crypto-aes.c b/drivers/crypto/ccp/ccp-crypto-aes.c
index 918e223f21b6..d11daaf47f06 100644
--- a/drivers/crypto/ccp/ccp-crypto-aes.c
+++ b/drivers/crypto/ccp/ccp-crypto-aes.c
@@ -267,24 +267,6 @@ static struct ccp_aes_def aes_algs[] = {
 		.alg_defaults	= &ccp_aes_defaults,
 	},
 	{
-		.mode		= CCP_AES_MODE_CFB,
-		.version	= CCP_VERSION(3, 0),
-		.name		= "cfb(aes)",
-		.driver_name	= "cfb-aes-ccp",
-		.blocksize	= 1,
-		.ivsize		= AES_BLOCK_SIZE,
-		.alg_defaults	= &ccp_aes_defaults,
-	},
-	{
-		.mode		= CCP_AES_MODE_OFB,
-		.version	= CCP_VERSION(3, 0),
-		.name		= "ofb(aes)",
-		.driver_name	= "ofb-aes-ccp",
-		.blocksize	= 1,
-		.ivsize		= AES_BLOCK_SIZE,
-		.alg_defaults	= &ccp_aes_defaults,
-	},
-	{
 		.mode		= CCP_AES_MODE_CTR,
 		.version	= CCP_VERSION(3, 0),
 		.name		= "ctr(aes)",
diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c
index aa4e1a500691..cb8e99936abb 100644
--- a/drivers/crypto/ccp/ccp-ops.c
+++ b/drivers/crypto/ccp/ccp-ops.c
@@ -179,8 +179,11 @@ static int ccp_init_dm_workarea(struct ccp_dm_workarea *wa,
 
 		wa->dma.address = dma_map_single(wa->dev, wa->address, len,
 						 dir);
-		if (dma_mapping_error(wa->dev, wa->dma.address))
+		if (dma_mapping_error(wa->dev, wa->dma.address)) {
+			kfree(wa->address);
+			wa->address = NULL;
 			return -ENOMEM;
+		}
 
 		wa->dma.length = len;
 	}
diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index fcaccd0b5a65..e4d3f45242f6 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -906,7 +906,7 @@ static int sev_ioctl_do_get_id2(struct sev_issue_cmd *argp)
 		/*
 		 * The length of the ID shouldn't be assumed by software since
 		 * it may change in the future.  The allocation size is limited
-		 * to 1 << (PAGE_SHIFT + MAX_ORDER) by the page allocator.
+		 * to 1 << (PAGE_SHIFT + MAX_PAGE_ORDER) by the page allocator.
 		 * If the allocation fails, simply return ENOMEM rather than
 		 * warning in the kernel log.
 		 */
diff --git a/drivers/crypto/ccree/cc_aead.c b/drivers/crypto/ccree/cc_aead.c
index 109ffb375fc6..5ef39d682389 100644
--- a/drivers/crypto/ccree/cc_aead.c
+++ b/drivers/crypto/ccree/cc_aead.c
@@ -2569,9 +2569,13 @@ static struct cc_crypto_alg *cc_create_aead_alg(struct cc_alg_template *tmpl,
 
 	alg = &tmpl->template_aead;
 
-	snprintf(alg->base.cra_name, CRYPTO_MAX_ALG_NAME, "%s", tmpl->name);
-	snprintf(alg->base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
-		 tmpl->driver_name);
+	if (snprintf(alg->base.cra_name, CRYPTO_MAX_ALG_NAME, "%s",
+		     tmpl->name) >= CRYPTO_MAX_ALG_NAME)
+		return ERR_PTR(-EINVAL);
+	if (snprintf(alg->base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
+		     tmpl->driver_name) >= CRYPTO_MAX_ALG_NAME)
+		return ERR_PTR(-EINVAL);
+
 	alg->base.cra_module = THIS_MODULE;
 	alg->base.cra_priority = CC_CRA_PRIO;
 
diff --git a/drivers/crypto/ccree/cc_cipher.c b/drivers/crypto/ccree/cc_cipher.c
index 2cd44d7457a4..cd66a580e8b6 100644
--- a/drivers/crypto/ccree/cc_cipher.c
+++ b/drivers/crypto/ccree/cc_cipher.c
@@ -1080,24 +1080,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.sec_func = true,
 	},
 	{
-		.name = "ofb(paes)",
-		.driver_name = "ofb-paes-ccree",
-		.blocksize = AES_BLOCK_SIZE,
-		.template_skcipher = {
-			.setkey = cc_cipher_sethkey,
-			.encrypt = cc_cipher_encrypt,
-			.decrypt = cc_cipher_decrypt,
-			.min_keysize = CC_HW_KEY_SIZE,
-			.max_keysize = CC_HW_KEY_SIZE,
-			.ivsize = AES_BLOCK_SIZE,
-			},
-		.cipher_mode = DRV_CIPHER_OFB,
-		.flow_mode = S_DIN_to_AES,
-		.min_hw_rev = CC_HW_REV_712,
-		.std_body = CC_STD_NIST,
-		.sec_func = true,
-	},
-	{
 		.name = "cts(cbc(paes))",
 		.driver_name = "cts-cbc-paes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
@@ -1206,23 +1188,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.std_body = CC_STD_NIST,
 	},
 	{
-		.name = "ofb(aes)",
-		.driver_name = "ofb-aes-ccree",
-		.blocksize = 1,
-		.template_skcipher = {
-			.setkey = cc_cipher_setkey,
-			.encrypt = cc_cipher_encrypt,
-			.decrypt = cc_cipher_decrypt,
-			.min_keysize = AES_MIN_KEY_SIZE,
-			.max_keysize = AES_MAX_KEY_SIZE,
-			.ivsize = AES_BLOCK_SIZE,
-			},
-		.cipher_mode = DRV_CIPHER_OFB,
-		.flow_mode = S_DIN_to_AES,
-		.min_hw_rev = CC_HW_REV_630,
-		.std_body = CC_STD_NIST,
-	},
-	{
 		.name = "cts(cbc(aes))",
 		.driver_name = "cts-cbc-aes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
@@ -1427,9 +1392,13 @@ static struct cc_crypto_alg *cc_create_alg(const struct cc_alg_template *tmpl,
 
 	memcpy(alg, &tmpl->template_skcipher, sizeof(*alg));
 
-	snprintf(alg->base.cra_name, CRYPTO_MAX_ALG_NAME, "%s", tmpl->name);
-	snprintf(alg->base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
-		 tmpl->driver_name);
+	if (snprintf(alg->base.cra_name, CRYPTO_MAX_ALG_NAME, "%s",
+		     tmpl->name) >= CRYPTO_MAX_ALG_NAME)
+		return ERR_PTR(-EINVAL);
+	if (snprintf(alg->base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
+		     tmpl->driver_name) >= CRYPTO_MAX_ALG_NAME)
+		return ERR_PTR(-EINVAL);
+
 	alg->base.cra_module = THIS_MODULE;
 	alg->base.cra_priority = CC_CRA_PRIO;
 	alg->base.cra_blocksize = tmpl->blocksize;
diff --git a/drivers/crypto/gemini/sl3516-ce-cipher.c b/drivers/crypto/gemini/sl3516-ce-cipher.c
index 49dce9e0a834..583010b2d007 100644
--- a/drivers/crypto/gemini/sl3516-ce-cipher.c
+++ b/drivers/crypto/gemini/sl3516-ce-cipher.c
@@ -332,8 +332,8 @@ int sl3516_ce_cipher_init(struct crypto_tfm *tfm)
 		return PTR_ERR(op->fallback_tfm);
 	}
 
-	sktfm->reqsize = sizeof(struct sl3516_ce_cipher_req_ctx) +
-			 crypto_skcipher_reqsize(op->fallback_tfm);
+	crypto_skcipher_set_reqsize(sktfm, sizeof(struct sl3516_ce_cipher_req_ctx) +
+				    crypto_skcipher_reqsize(op->fallback_tfm));
 
 	dev_info(op->ce->dev, "Fallback for %s is %s\n",
 		 crypto_tfm_alg_driver_name(&sktfm->base),
diff --git a/drivers/crypto/hifn_795x.c b/drivers/crypto/hifn_795x.c
index 7bddc3c786c1..b4a4ec35bce0 100644
--- a/drivers/crypto/hifn_795x.c
+++ b/drivers/crypto/hifn_795x.c
@@ -2096,16 +2096,6 @@ static inline int hifn_encrypt_aes_cbc(struct skcipher_request *req)
 	return hifn_setup_crypto(req, ACRYPTO_OP_ENCRYPT,
 			ACRYPTO_TYPE_AES_128, ACRYPTO_MODE_CBC);
 }
-static inline int hifn_encrypt_aes_cfb(struct skcipher_request *req)
-{
-	return hifn_setup_crypto(req, ACRYPTO_OP_ENCRYPT,
-			ACRYPTO_TYPE_AES_128, ACRYPTO_MODE_CFB);
-}
-static inline int hifn_encrypt_aes_ofb(struct skcipher_request *req)
-{
-	return hifn_setup_crypto(req, ACRYPTO_OP_ENCRYPT,
-			ACRYPTO_TYPE_AES_128, ACRYPTO_MODE_OFB);
-}
 
 /*
  * AES decryption functions.
@@ -2120,16 +2110,6 @@ static inline int hifn_decrypt_aes_cbc(struct skcipher_request *req)
 	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
 			ACRYPTO_TYPE_AES_128, ACRYPTO_MODE_CBC);
 }
-static inline int hifn_decrypt_aes_cfb(struct skcipher_request *req)
-{
-	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
-			ACRYPTO_TYPE_AES_128, ACRYPTO_MODE_CFB);
-}
-static inline int hifn_decrypt_aes_ofb(struct skcipher_request *req)
-{
-	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
-			ACRYPTO_TYPE_AES_128, ACRYPTO_MODE_OFB);
-}
 
 /*
  * DES ecryption functions.
@@ -2144,16 +2124,6 @@ static inline int hifn_encrypt_des_cbc(struct skcipher_request *req)
 	return hifn_setup_crypto(req, ACRYPTO_OP_ENCRYPT,
 			ACRYPTO_TYPE_DES, ACRYPTO_MODE_CBC);
 }
-static inline int hifn_encrypt_des_cfb(struct skcipher_request *req)
-{
-	return hifn_setup_crypto(req, ACRYPTO_OP_ENCRYPT,
-			ACRYPTO_TYPE_DES, ACRYPTO_MODE_CFB);
-}
-static inline int hifn_encrypt_des_ofb(struct skcipher_request *req)
-{
-	return hifn_setup_crypto(req, ACRYPTO_OP_ENCRYPT,
-			ACRYPTO_TYPE_DES, ACRYPTO_MODE_OFB);
-}
 
 /*
  * DES decryption functions.
@@ -2168,16 +2138,6 @@ static inline int hifn_decrypt_des_cbc(struct skcipher_request *req)
 	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
 			ACRYPTO_TYPE_DES, ACRYPTO_MODE_CBC);
 }
-static inline int hifn_decrypt_des_cfb(struct skcipher_request *req)
-{
-	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
-			ACRYPTO_TYPE_DES, ACRYPTO_MODE_CFB);
-}
-static inline int hifn_decrypt_des_ofb(struct skcipher_request *req)
-{
-	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
-			ACRYPTO_TYPE_DES, ACRYPTO_MODE_OFB);
-}
 
 /*
  * 3DES ecryption functions.
@@ -2192,16 +2152,6 @@ static inline int hifn_encrypt_3des_cbc(struct skcipher_request *req)
 	return hifn_setup_crypto(req, ACRYPTO_OP_ENCRYPT,
 			ACRYPTO_TYPE_3DES, ACRYPTO_MODE_CBC);
 }
-static inline int hifn_encrypt_3des_cfb(struct skcipher_request *req)
-{
-	return hifn_setup_crypto(req, ACRYPTO_OP_ENCRYPT,
-			ACRYPTO_TYPE_3DES, ACRYPTO_MODE_CFB);
-}
-static inline int hifn_encrypt_3des_ofb(struct skcipher_request *req)
-{
-	return hifn_setup_crypto(req, ACRYPTO_OP_ENCRYPT,
-			ACRYPTO_TYPE_3DES, ACRYPTO_MODE_OFB);
-}
 
 /* 3DES decryption functions. */
 static inline int hifn_decrypt_3des_ecb(struct skcipher_request *req)
@@ -2214,16 +2164,6 @@ static inline int hifn_decrypt_3des_cbc(struct skcipher_request *req)
 	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
 			ACRYPTO_TYPE_3DES, ACRYPTO_MODE_CBC);
 }
-static inline int hifn_decrypt_3des_cfb(struct skcipher_request *req)
-{
-	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
-			ACRYPTO_TYPE_3DES, ACRYPTO_MODE_CFB);
-}
-static inline int hifn_decrypt_3des_ofb(struct skcipher_request *req)
-{
-	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
-			ACRYPTO_TYPE_3DES, ACRYPTO_MODE_OFB);
-}
 
 struct hifn_alg_template {
 	char name[CRYPTO_MAX_ALG_NAME];
@@ -2234,29 +2174,9 @@ struct hifn_alg_template {
 
 static const struct hifn_alg_template hifn_alg_templates[] = {
 	/*
-	 * 3DES ECB, CBC, CFB and OFB modes.
+	 * 3DES ECB and CBC modes.
 	 */
 	{
-		.name = "cfb(des3_ede)", .drv_name = "cfb-3des", .bsize = 8,
-		.skcipher = {
-			.min_keysize	=	HIFN_3DES_KEY_LENGTH,
-			.max_keysize	=	HIFN_3DES_KEY_LENGTH,
-			.setkey		=	hifn_des3_setkey,
-			.encrypt	=	hifn_encrypt_3des_cfb,
-			.decrypt	=	hifn_decrypt_3des_cfb,
-		},
-	},
-	{
-		.name = "ofb(des3_ede)", .drv_name = "ofb-3des", .bsize = 8,
-		.skcipher = {
-			.min_keysize	=	HIFN_3DES_KEY_LENGTH,
-			.max_keysize	=	HIFN_3DES_KEY_LENGTH,
-			.setkey		=	hifn_des3_setkey,
-			.encrypt	=	hifn_encrypt_3des_ofb,
-			.decrypt	=	hifn_decrypt_3des_ofb,
-		},
-	},
-	{
 		.name = "cbc(des3_ede)", .drv_name = "cbc-3des", .bsize = 8,
 		.skcipher = {
 			.ivsize		=	HIFN_IV_LENGTH,
@@ -2279,29 +2199,9 @@ static const struct hifn_alg_template hifn_alg_templates[] = {
 	},
 
 	/*
-	 * DES ECB, CBC, CFB and OFB modes.
+	 * DES ECB and CBC modes.
 	 */
 	{
-		.name = "cfb(des)", .drv_name = "cfb-des", .bsize = 8,
-		.skcipher = {
-			.min_keysize	=	HIFN_DES_KEY_LENGTH,
-			.max_keysize	=	HIFN_DES_KEY_LENGTH,
-			.setkey		=	hifn_setkey,
-			.encrypt	=	hifn_encrypt_des_cfb,
-			.decrypt	=	hifn_decrypt_des_cfb,
-		},
-	},
-	{
-		.name = "ofb(des)", .drv_name = "ofb-des", .bsize = 8,
-		.skcipher = {
-			.min_keysize	=	HIFN_DES_KEY_LENGTH,
-			.max_keysize	=	HIFN_DES_KEY_LENGTH,
-			.setkey		=	hifn_setkey,
-			.encrypt	=	hifn_encrypt_des_ofb,
-			.decrypt	=	hifn_decrypt_des_ofb,
-		},
-	},
-	{
 		.name = "cbc(des)", .drv_name = "cbc-des", .bsize = 8,
 		.skcipher = {
 			.ivsize		=	HIFN_IV_LENGTH,
@@ -2324,7 +2224,7 @@ static const struct hifn_alg_template hifn_alg_templates[] = {
 	},
 
 	/*
-	 * AES ECB, CBC, CFB and OFB modes.
+	 * AES ECB and CBC modes.
 	 */
 	{
 		.name = "ecb(aes)", .drv_name = "ecb-aes", .bsize = 16,
@@ -2347,26 +2247,6 @@ static const struct hifn_alg_template hifn_alg_templates[] = {
 			.decrypt	=	hifn_decrypt_aes_cbc,
 		},
 	},
-	{
-		.name = "cfb(aes)", .drv_name = "cfb-aes", .bsize = 16,
-		.skcipher = {
-			.min_keysize	=	AES_MIN_KEY_SIZE,
-			.max_keysize	=	AES_MAX_KEY_SIZE,
-			.setkey		=	hifn_setkey,
-			.encrypt	=	hifn_encrypt_aes_cfb,
-			.decrypt	=	hifn_decrypt_aes_cfb,
-		},
-	},
-	{
-		.name = "ofb(aes)", .drv_name = "ofb-aes", .bsize = 16,
-		.skcipher = {
-			.min_keysize	=	AES_MIN_KEY_SIZE,
-			.max_keysize	=	AES_MAX_KEY_SIZE,
-			.setkey		=	hifn_setkey,
-			.encrypt	=	hifn_encrypt_aes_ofb,
-			.decrypt	=	hifn_decrypt_aes_ofb,
-		},
-	},
 };
 
 static int hifn_init_tfm(struct crypto_skcipher *tfm)
diff --git a/drivers/crypto/hisilicon/debugfs.c b/drivers/crypto/hisilicon/debugfs.c
index 7e8186fe0512..80ed4b2d209c 100644
--- a/drivers/crypto/hisilicon/debugfs.c
+++ b/drivers/crypto/hisilicon/debugfs.c
@@ -31,6 +31,10 @@ static const char * const qm_debug_file_name[] = {
 	[CLEAR_ENABLE] = "clear_enable",
 };
 
+static const char * const qm_s[] = {
+	"work", "stop",
+};
+
 struct qm_dfx_item {
 	const char *name;
 	u32 offset;
@@ -53,34 +57,34 @@ static struct qm_dfx_item qm_dfx_files[] = {
 #define CNT_CYC_REGS_NUM		10
 static const struct debugfs_reg32 qm_dfx_regs[] = {
 	/* XXX_CNT are reading clear register */
-	{"QM_ECC_1BIT_CNT               ",  0x104000ull},
-	{"QM_ECC_MBIT_CNT               ",  0x104008ull},
-	{"QM_DFX_MB_CNT                 ",  0x104018ull},
-	{"QM_DFX_DB_CNT                 ",  0x104028ull},
-	{"QM_DFX_SQE_CNT                ",  0x104038ull},
-	{"QM_DFX_CQE_CNT                ",  0x104048ull},
-	{"QM_DFX_SEND_SQE_TO_ACC_CNT    ",  0x104050ull},
-	{"QM_DFX_WB_SQE_FROM_ACC_CNT    ",  0x104058ull},
-	{"QM_DFX_ACC_FINISH_CNT         ",  0x104060ull},
-	{"QM_DFX_CQE_ERR_CNT            ",  0x1040b4ull},
-	{"QM_DFX_FUNS_ACTIVE_ST         ",  0x200ull},
-	{"QM_ECC_1BIT_INF               ",  0x104004ull},
-	{"QM_ECC_MBIT_INF               ",  0x10400cull},
-	{"QM_DFX_ACC_RDY_VLD0           ",  0x1040a0ull},
-	{"QM_DFX_ACC_RDY_VLD1           ",  0x1040a4ull},
-	{"QM_DFX_AXI_RDY_VLD            ",  0x1040a8ull},
-	{"QM_DFX_FF_ST0                 ",  0x1040c8ull},
-	{"QM_DFX_FF_ST1                 ",  0x1040ccull},
-	{"QM_DFX_FF_ST2                 ",  0x1040d0ull},
-	{"QM_DFX_FF_ST3                 ",  0x1040d4ull},
-	{"QM_DFX_FF_ST4                 ",  0x1040d8ull},
-	{"QM_DFX_FF_ST5                 ",  0x1040dcull},
-	{"QM_DFX_FF_ST6                 ",  0x1040e0ull},
-	{"QM_IN_IDLE_ST                 ",  0x1040e4ull},
+	{"QM_ECC_1BIT_CNT               ",  0x104000},
+	{"QM_ECC_MBIT_CNT               ",  0x104008},
+	{"QM_DFX_MB_CNT                 ",  0x104018},
+	{"QM_DFX_DB_CNT                 ",  0x104028},
+	{"QM_DFX_SQE_CNT                ",  0x104038},
+	{"QM_DFX_CQE_CNT                ",  0x104048},
+	{"QM_DFX_SEND_SQE_TO_ACC_CNT    ",  0x104050},
+	{"QM_DFX_WB_SQE_FROM_ACC_CNT    ",  0x104058},
+	{"QM_DFX_ACC_FINISH_CNT         ",  0x104060},
+	{"QM_DFX_CQE_ERR_CNT            ",  0x1040b4},
+	{"QM_DFX_FUNS_ACTIVE_ST         ",  0x200},
+	{"QM_ECC_1BIT_INF               ",  0x104004},
+	{"QM_ECC_MBIT_INF               ",  0x10400c},
+	{"QM_DFX_ACC_RDY_VLD0           ",  0x1040a0},
+	{"QM_DFX_ACC_RDY_VLD1           ",  0x1040a4},
+	{"QM_DFX_AXI_RDY_VLD            ",  0x1040a8},
+	{"QM_DFX_FF_ST0                 ",  0x1040c8},
+	{"QM_DFX_FF_ST1                 ",  0x1040cc},
+	{"QM_DFX_FF_ST2                 ",  0x1040d0},
+	{"QM_DFX_FF_ST3                 ",  0x1040d4},
+	{"QM_DFX_FF_ST4                 ",  0x1040d8},
+	{"QM_DFX_FF_ST5                 ",  0x1040dc},
+	{"QM_DFX_FF_ST6                 ",  0x1040e0},
+	{"QM_IN_IDLE_ST                 ",  0x1040e4},
 };
 
 static const struct debugfs_reg32 qm_vf_dfx_regs[] = {
-	{"QM_DFX_FUNS_ACTIVE_ST         ",  0x200ull},
+	{"QM_DFX_FUNS_ACTIVE_ST         ",  0x200},
 };
 
 /* define the QM's dfx regs region and region length */
diff --git a/drivers/crypto/hisilicon/hpre/hpre_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c
index 56777099ef69..3255b2a070c7 100644
--- a/drivers/crypto/hisilicon/hpre/hpre_main.c
+++ b/drivers/crypto/hisilicon/hpre/hpre_main.c
@@ -118,8 +118,6 @@
 #define HPRE_DFX_COMMON2_LEN		0xE
 #define HPRE_DFX_CORE_LEN		0x43
 
-#define HPRE_DEV_ALG_MAX_LEN	256
-
 static const char hpre_name[] = "hisi_hpre";
 static struct dentry *hpre_debugfs_root;
 static const struct pci_device_id hpre_dev_ids[] = {
@@ -135,12 +133,7 @@ struct hpre_hw_error {
 	const char *msg;
 };
 
-struct hpre_dev_alg {
-	u32 alg_msk;
-	const char *alg;
-};
-
-static const struct hpre_dev_alg hpre_dev_algs[] = {
+static const struct qm_dev_alg hpre_dev_algs[] = {
 	{
 		.alg_msk = BIT(0),
 		.alg = "rsa\n"
@@ -233,6 +226,20 @@ static const struct hisi_qm_cap_info hpre_basic_info[] = {
 	{HPRE_CORE10_ALG_BITMAP_CAP, 0x3170, 0, GENMASK(31, 0), 0x0, 0x10, 0x10}
 };
 
+enum hpre_pre_store_cap_idx {
+	HPRE_CLUSTER_NUM_CAP_IDX = 0x0,
+	HPRE_CORE_ENABLE_BITMAP_CAP_IDX,
+	HPRE_DRV_ALG_BITMAP_CAP_IDX,
+	HPRE_DEV_ALG_BITMAP_CAP_IDX,
+};
+
+static const u32 hpre_pre_store_caps[] = {
+	HPRE_CLUSTER_NUM_CAP,
+	HPRE_CORE_ENABLE_BITMAP_CAP,
+	HPRE_DRV_ALG_BITMAP_CAP,
+	HPRE_DEV_ALG_BITMAP_CAP,
+};
+
 static const struct hpre_hw_error hpre_hw_errors[] = {
 	{
 		.int_msk = BIT(0),
@@ -355,42 +362,13 @@ bool hpre_check_alg_support(struct hisi_qm *qm, u32 alg)
 {
 	u32 cap_val;
 
-	cap_val = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_DRV_ALG_BITMAP_CAP, qm->cap_ver);
+	cap_val = qm->cap_tables.dev_cap_table[HPRE_DRV_ALG_BITMAP_CAP_IDX].cap_val;
 	if (alg & cap_val)
 		return true;
 
 	return false;
 }
 
-static int hpre_set_qm_algs(struct hisi_qm *qm)
-{
-	struct device *dev = &qm->pdev->dev;
-	char *algs, *ptr;
-	u32 alg_msk;
-	int i;
-
-	if (!qm->use_sva)
-		return 0;
-
-	algs = devm_kzalloc(dev, HPRE_DEV_ALG_MAX_LEN * sizeof(char), GFP_KERNEL);
-	if (!algs)
-		return -ENOMEM;
-
-	alg_msk = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_DEV_ALG_BITMAP_CAP, qm->cap_ver);
-
-	for (i = 0; i < ARRAY_SIZE(hpre_dev_algs); i++)
-		if (alg_msk & hpre_dev_algs[i].alg_msk)
-			strcat(algs, hpre_dev_algs[i].alg);
-
-	ptr = strrchr(algs, '\n');
-	if (ptr)
-		*ptr = '\0';
-
-	qm->uacce->algs = algs;
-
-	return 0;
-}
-
 static int hpre_diff_regs_show(struct seq_file *s, void *unused)
 {
 	struct hisi_qm *qm = s->private;
@@ -460,16 +438,6 @@ static u32 vfs_num;
 module_param_cb(vfs_num, &vfs_num_ops, &vfs_num, 0444);
 MODULE_PARM_DESC(vfs_num, "Number of VFs to enable(1-63), 0(default)");
 
-static inline int hpre_cluster_num(struct hisi_qm *qm)
-{
-	return hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_CLUSTER_NUM_CAP, qm->cap_ver);
-}
-
-static inline int hpre_cluster_core_mask(struct hisi_qm *qm)
-{
-	return hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_CORE_ENABLE_BITMAP_CAP, qm->cap_ver);
-}
-
 struct hisi_qp *hpre_create_qp(u8 type)
 {
 	int node = cpu_to_node(smp_processor_id());
@@ -536,13 +504,15 @@ static int hpre_cfg_by_dsm(struct hisi_qm *qm)
 
 static int hpre_set_cluster(struct hisi_qm *qm)
 {
-	u32 cluster_core_mask = hpre_cluster_core_mask(qm);
-	u8 clusters_num = hpre_cluster_num(qm);
 	struct device *dev = &qm->pdev->dev;
 	unsigned long offset;
+	u32 cluster_core_mask;
+	u8 clusters_num;
 	u32 val = 0;
 	int ret, i;
 
+	cluster_core_mask = qm->cap_tables.dev_cap_table[HPRE_CORE_ENABLE_BITMAP_CAP_IDX].cap_val;
+	clusters_num = qm->cap_tables.dev_cap_table[HPRE_CLUSTER_NUM_CAP_IDX].cap_val;
 	for (i = 0; i < clusters_num; i++) {
 		offset = i * HPRE_CLSTR_ADDR_INTRVL;
 
@@ -737,11 +707,12 @@ static int hpre_set_user_domain_and_cache(struct hisi_qm *qm)
 
 static void hpre_cnt_regs_clear(struct hisi_qm *qm)
 {
-	u8 clusters_num = hpre_cluster_num(qm);
 	unsigned long offset;
+	u8 clusters_num;
 	int i;
 
 	/* clear clusterX/cluster_ctrl */
+	clusters_num = qm->cap_tables.dev_cap_table[HPRE_CLUSTER_NUM_CAP_IDX].cap_val;
 	for (i = 0; i < clusters_num; i++) {
 		offset = HPRE_CLSTR_BASE + i * HPRE_CLSTR_ADDR_INTRVL;
 		writel(0x0, qm->io_base + offset + HPRE_CLUSTER_INQURY);
@@ -1028,13 +999,14 @@ static int hpre_pf_comm_regs_debugfs_init(struct hisi_qm *qm)
 
 static int hpre_cluster_debugfs_init(struct hisi_qm *qm)
 {
-	u8 clusters_num = hpre_cluster_num(qm);
 	struct device *dev = &qm->pdev->dev;
 	char buf[HPRE_DBGFS_VAL_MAX_LEN];
 	struct debugfs_regset32 *regset;
 	struct dentry *tmp_d;
+	u8 clusters_num;
 	int i, ret;
 
+	clusters_num = qm->cap_tables.dev_cap_table[HPRE_CLUSTER_NUM_CAP_IDX].cap_val;
 	for (i = 0; i < clusters_num; i++) {
 		ret = snprintf(buf, HPRE_DBGFS_VAL_MAX_LEN, "cluster%d", i);
 		if (ret >= HPRE_DBGFS_VAL_MAX_LEN)
@@ -1139,8 +1111,37 @@ static void hpre_debugfs_exit(struct hisi_qm *qm)
 	debugfs_remove_recursive(qm->debug.debug_root);
 }
 
+static int hpre_pre_store_cap_reg(struct hisi_qm *qm)
+{
+	struct hisi_qm_cap_record *hpre_cap;
+	struct device *dev = &qm->pdev->dev;
+	size_t i, size;
+
+	size = ARRAY_SIZE(hpre_pre_store_caps);
+	hpre_cap = devm_kzalloc(dev, sizeof(*hpre_cap) * size, GFP_KERNEL);
+	if (!hpre_cap)
+		return -ENOMEM;
+
+	for (i = 0; i < size; i++) {
+		hpre_cap[i].type = hpre_pre_store_caps[i];
+		hpre_cap[i].cap_val = hisi_qm_get_hw_info(qm, hpre_basic_info,
+				      hpre_pre_store_caps[i], qm->cap_ver);
+	}
+
+	if (hpre_cap[HPRE_CLUSTER_NUM_CAP_IDX].cap_val > HPRE_CLUSTERS_NUM_MAX) {
+		dev_err(dev, "Device cluster num %u is out of range for driver supports %d!\n",
+			hpre_cap[HPRE_CLUSTER_NUM_CAP_IDX].cap_val, HPRE_CLUSTERS_NUM_MAX);
+		return -EINVAL;
+	}
+
+	qm->cap_tables.dev_cap_table = hpre_cap;
+
+	return 0;
+}
+
 static int hpre_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
 {
+	u64 alg_msk;
 	int ret;
 
 	if (pdev->revision == QM_HW_V1) {
@@ -1171,7 +1172,16 @@ static int hpre_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
 		return ret;
 	}
 
-	ret = hpre_set_qm_algs(qm);
+	/* Fetch and save the value of capability registers */
+	ret = hpre_pre_store_cap_reg(qm);
+	if (ret) {
+		pci_err(pdev, "Failed to pre-store capability registers!\n");
+		hisi_qm_uninit(qm);
+		return ret;
+	}
+
+	alg_msk = qm->cap_tables.dev_cap_table[HPRE_DEV_ALG_BITMAP_CAP_IDX].cap_val;
+	ret = hisi_qm_set_algs(qm, alg_msk, hpre_dev_algs, ARRAY_SIZE(hpre_dev_algs));
 	if (ret) {
 		pci_err(pdev, "Failed to set hpre algs!\n");
 		hisi_qm_uninit(qm);
@@ -1184,11 +1194,12 @@ static int hpre_show_last_regs_init(struct hisi_qm *qm)
 {
 	int cluster_dfx_regs_num =  ARRAY_SIZE(hpre_cluster_dfx_regs);
 	int com_dfx_regs_num = ARRAY_SIZE(hpre_com_dfx_regs);
-	u8 clusters_num = hpre_cluster_num(qm);
 	struct qm_debug *debug = &qm->debug;
 	void __iomem *io_base;
+	u8 clusters_num;
 	int i, j, idx;
 
+	clusters_num = qm->cap_tables.dev_cap_table[HPRE_CLUSTER_NUM_CAP_IDX].cap_val;
 	debug->last_words = kcalloc(cluster_dfx_regs_num * clusters_num +
 			com_dfx_regs_num, sizeof(unsigned int), GFP_KERNEL);
 	if (!debug->last_words)
@@ -1225,10 +1236,10 @@ static void hpre_show_last_dfx_regs(struct hisi_qm *qm)
 {
 	int cluster_dfx_regs_num =  ARRAY_SIZE(hpre_cluster_dfx_regs);
 	int com_dfx_regs_num = ARRAY_SIZE(hpre_com_dfx_regs);
-	u8 clusters_num = hpre_cluster_num(qm);
 	struct qm_debug *debug = &qm->debug;
 	struct pci_dev *pdev = qm->pdev;
 	void __iomem *io_base;
+	u8 clusters_num;
 	int i, j, idx;
 	u32 val;
 
@@ -1243,6 +1254,7 @@ static void hpre_show_last_dfx_regs(struct hisi_qm *qm)
 			  hpre_com_dfx_regs[i].name, debug->last_words[i], val);
 	}
 
+	clusters_num = qm->cap_tables.dev_cap_table[HPRE_CLUSTER_NUM_CAP_IDX].cap_val;
 	for (i = 0; i < clusters_num; i++) {
 		io_base = qm->io_base + hpre_cluster_offsets[i];
 		for (j = 0; j <  cluster_dfx_regs_num; j++) {
diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c
index 18599f3634c3..4b20b94e6371 100644
--- a/drivers/crypto/hisilicon/qm.c
+++ b/drivers/crypto/hisilicon/qm.c
@@ -129,16 +129,21 @@
 #define QM_FIFO_OVERFLOW_TYPE		0xc0
 #define QM_FIFO_OVERFLOW_TYPE_SHIFT	6
 #define QM_FIFO_OVERFLOW_VF		0x3f
+#define QM_FIFO_OVERFLOW_QP_SHIFT	16
 #define QM_ABNORMAL_INF01		0x100014
 #define QM_DB_TIMEOUT_TYPE		0xc0
 #define QM_DB_TIMEOUT_TYPE_SHIFT	6
 #define QM_DB_TIMEOUT_VF		0x3f
+#define QM_DB_TIMEOUT_QP_SHIFT		16
+#define QM_ABNORMAL_INF02		0x100018
+#define QM_AXI_POISON_ERR		BIT(22)
 #define QM_RAS_CE_ENABLE		0x1000ec
 #define QM_RAS_FE_ENABLE		0x1000f0
 #define QM_RAS_NFE_ENABLE		0x1000f4
 #define QM_RAS_CE_THRESHOLD		0x1000f8
 #define QM_RAS_CE_TIMES_PER_IRQ		1
 #define QM_OOO_SHUTDOWN_SEL		0x1040f8
+#define QM_AXI_RRESP_ERR		BIT(0)
 #define QM_ECC_MBIT			BIT(2)
 #define QM_DB_TIMEOUT			BIT(10)
 #define QM_OF_FIFO_OF			BIT(11)
@@ -229,6 +234,8 @@
 #define QM_QOS_MAX_CIR_U		6
 #define QM_AUTOSUSPEND_DELAY		3000
 
+#define QM_DEV_ALG_MAX_LEN		256
+
 #define QM_MK_CQC_DW3_V1(hop_num, pg_sz, buf_sz, cqe_sz) \
 	(((hop_num) << QM_CQ_HOP_NUM_SHIFT) | \
 	((pg_sz) << QM_CQ_PAGE_SIZE_SHIFT) | \
@@ -294,6 +301,13 @@ enum qm_basic_type {
 	QM_VF_IRQ_NUM_CAP,
 };
 
+enum qm_pre_store_cap_idx {
+	QM_EQ_IRQ_TYPE_CAP_IDX = 0x0,
+	QM_AEQ_IRQ_TYPE_CAP_IDX,
+	QM_ABN_IRQ_TYPE_CAP_IDX,
+	QM_PF2VF_IRQ_TYPE_CAP_IDX,
+};
+
 static const struct hisi_qm_cap_info qm_cap_info_comm[] = {
 	{QM_SUPPORT_DB_ISOLATION, 0x30,   0, BIT(0),  0x0, 0x0, 0x0},
 	{QM_SUPPORT_FUNC_QOS,     0x3100, 0, BIT(8),  0x0, 0x0, 0x1},
@@ -323,6 +337,13 @@ static const struct hisi_qm_cap_info qm_basic_info[] = {
 	{QM_VF_IRQ_NUM_CAP,     0x311c,   0,  GENMASK(15, 0), 0x1,       0x2,       0x3},
 };
 
+static const u32 qm_pre_store_caps[] = {
+	QM_EQ_IRQ_TYPE_CAP,
+	QM_AEQ_IRQ_TYPE_CAP,
+	QM_ABN_IRQ_TYPE_CAP,
+	QM_PF2VF_IRQ_TYPE_CAP,
+};
+
 struct qm_mailbox {
 	__le16 w0;
 	__le16 queue_num;
@@ -386,7 +407,6 @@ static const struct hisi_qm_hw_error qm_hw_error[] = {
 	{ .int_msk = BIT(12), .msg = "qm_db_random_invalid" },
 	{ .int_msk = BIT(13), .msg = "qm_mailbox_timeout" },
 	{ .int_msk = BIT(14), .msg = "qm_flr_timeout" },
-	{ /* sentinel */ }
 };
 
 static const char * const qm_db_timeout[] = {
@@ -397,10 +417,6 @@ static const char * const qm_fifo_overflow[] = {
 	"cq", "eq", "aeq",
 };
 
-static const char * const qp_s[] = {
-	"none", "init", "start", "stop", "close",
-};
-
 struct qm_typical_qos_table {
 	u32 start;
 	u32 end;
@@ -428,85 +444,6 @@ static struct qm_typical_qos_table shaper_cbs_s[] = {
 
 static void qm_irqs_unregister(struct hisi_qm *qm);
 
-static bool qm_avail_state(struct hisi_qm *qm, enum qm_state new)
-{
-	enum qm_state curr = atomic_read(&qm->status.flags);
-	bool avail = false;
-
-	switch (curr) {
-	case QM_INIT:
-		if (new == QM_START || new == QM_CLOSE)
-			avail = true;
-		break;
-	case QM_START:
-		if (new == QM_STOP)
-			avail = true;
-		break;
-	case QM_STOP:
-		if (new == QM_CLOSE || new == QM_START)
-			avail = true;
-		break;
-	default:
-		break;
-	}
-
-	dev_dbg(&qm->pdev->dev, "change qm state from %s to %s\n",
-		qm_s[curr], qm_s[new]);
-
-	if (!avail)
-		dev_warn(&qm->pdev->dev, "Can not change qm state from %s to %s\n",
-			 qm_s[curr], qm_s[new]);
-
-	return avail;
-}
-
-static bool qm_qp_avail_state(struct hisi_qm *qm, struct hisi_qp *qp,
-			      enum qp_state new)
-{
-	enum qm_state qm_curr = atomic_read(&qm->status.flags);
-	enum qp_state qp_curr = 0;
-	bool avail = false;
-
-	if (qp)
-		qp_curr = atomic_read(&qp->qp_status.flags);
-
-	switch (new) {
-	case QP_INIT:
-		if (qm_curr == QM_START || qm_curr == QM_INIT)
-			avail = true;
-		break;
-	case QP_START:
-		if ((qm_curr == QM_START && qp_curr == QP_INIT) ||
-		    (qm_curr == QM_START && qp_curr == QP_STOP))
-			avail = true;
-		break;
-	case QP_STOP:
-		if ((qm_curr == QM_START && qp_curr == QP_START) ||
-		    (qp_curr == QP_INIT))
-			avail = true;
-		break;
-	case QP_CLOSE:
-		if ((qm_curr == QM_START && qp_curr == QP_INIT) ||
-		    (qm_curr == QM_START && qp_curr == QP_STOP) ||
-		    (qm_curr == QM_STOP && qp_curr == QP_STOP)  ||
-		    (qm_curr == QM_STOP && qp_curr == QP_INIT))
-			avail = true;
-		break;
-	default:
-		break;
-	}
-
-	dev_dbg(&qm->pdev->dev, "change qp state from %s to %s in QM %s\n",
-		qp_s[qp_curr], qp_s[new], qm_s[qm_curr]);
-
-	if (!avail)
-		dev_warn(&qm->pdev->dev,
-			 "Can not change qp state from %s to %s in QM %s\n",
-			 qp_s[qp_curr], qp_s[new], qm_s[qm_curr]);
-
-	return avail;
-}
-
 static u32 qm_get_hw_error_status(struct hisi_qm *qm)
 {
 	return readl(qm->io_base + QM_ABNORMAL_INT_STATUS);
@@ -660,9 +597,6 @@ int hisi_qm_mb(struct hisi_qm *qm, u8 cmd, dma_addr_t dma_addr, u16 queue,
 	struct qm_mailbox mailbox;
 	int ret;
 
-	dev_dbg(&qm->pdev->dev, "QM mailbox request to q%u: %u-%llx\n",
-		queue, cmd, (unsigned long long)dma_addr);
-
 	qm_mb_pre_init(&mailbox, cmd, dma_addr, queue, op);
 
 	mutex_lock(&qm->mailbox_lock);
@@ -828,6 +762,40 @@ static void qm_get_xqc_depth(struct hisi_qm *qm, u16 *low_bits,
 	*high_bits = (depth >> QM_XQ_DEPTH_SHIFT) & QM_XQ_DEPTH_MASK;
 }
 
+int hisi_qm_set_algs(struct hisi_qm *qm, u64 alg_msk, const struct qm_dev_alg *dev_algs,
+		     u32 dev_algs_size)
+{
+	struct device *dev = &qm->pdev->dev;
+	char *algs, *ptr;
+	int i;
+
+	if (!qm->uacce)
+		return 0;
+
+	if (dev_algs_size >= QM_DEV_ALG_MAX_LEN) {
+		dev_err(dev, "algs size %u is equal or larger than %d.\n",
+			dev_algs_size, QM_DEV_ALG_MAX_LEN);
+		return -EINVAL;
+	}
+
+	algs = devm_kzalloc(dev, QM_DEV_ALG_MAX_LEN * sizeof(char), GFP_KERNEL);
+	if (!algs)
+		return -ENOMEM;
+
+	for (i = 0; i < dev_algs_size; i++)
+		if (alg_msk & dev_algs[i].alg_msk)
+			strcat(algs, dev_algs[i].alg);
+
+	ptr = strrchr(algs, '\n');
+	if (ptr) {
+		*ptr = '\0';
+		qm->uacce->algs = algs;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(hisi_qm_set_algs);
+
 static u32 qm_get_irq_num(struct hisi_qm *qm)
 {
 	if (qm->fun_type == QM_HW_PF)
@@ -1406,7 +1374,7 @@ static void qm_log_hw_error(struct hisi_qm *qm, u32 error_status)
 {
 	const struct hisi_qm_hw_error *err;
 	struct device *dev = &qm->pdev->dev;
-	u32 reg_val, type, vf_num;
+	u32 reg_val, type, vf_num, qp_id;
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(qm_hw_error); i++) {
@@ -1422,19 +1390,24 @@ static void qm_log_hw_error(struct hisi_qm *qm, u32 error_status)
 			type = (reg_val & QM_DB_TIMEOUT_TYPE) >>
 			       QM_DB_TIMEOUT_TYPE_SHIFT;
 			vf_num = reg_val & QM_DB_TIMEOUT_VF;
-			dev_err(dev, "qm %s doorbell timeout in function %u\n",
-				qm_db_timeout[type], vf_num);
+			qp_id = reg_val >> QM_DB_TIMEOUT_QP_SHIFT;
+			dev_err(dev, "qm %s doorbell timeout in function %u qp %u\n",
+				qm_db_timeout[type], vf_num, qp_id);
 		} else if (err->int_msk & QM_OF_FIFO_OF) {
 			reg_val = readl(qm->io_base + QM_ABNORMAL_INF00);
 			type = (reg_val & QM_FIFO_OVERFLOW_TYPE) >>
 			       QM_FIFO_OVERFLOW_TYPE_SHIFT;
 			vf_num = reg_val & QM_FIFO_OVERFLOW_VF;
-
+			qp_id = reg_val >> QM_FIFO_OVERFLOW_QP_SHIFT;
 			if (type < ARRAY_SIZE(qm_fifo_overflow))
-				dev_err(dev, "qm %s fifo overflow in function %u\n",
-					qm_fifo_overflow[type], vf_num);
+				dev_err(dev, "qm %s fifo overflow in function %u qp %u\n",
+					qm_fifo_overflow[type], vf_num, qp_id);
 			else
 				dev_err(dev, "unknown error type\n");
+		} else if (err->int_msk & QM_AXI_RRESP_ERR) {
+			reg_val = readl(qm->io_base + QM_ABNORMAL_INF02);
+			if (reg_val & QM_AXI_POISON_ERR)
+				dev_err(dev, "qm axi poison error happened\n");
 		}
 	}
 }
@@ -1843,8 +1816,10 @@ static struct hisi_qp *qm_create_qp_nolock(struct hisi_qm *qm, u8 alg_type)
 	struct hisi_qp *qp;
 	int qp_id;
 
-	if (!qm_qp_avail_state(qm, NULL, QP_INIT))
+	if (atomic_read(&qm->status.flags) == QM_STOP) {
+		dev_info_ratelimited(dev, "failed to create qp as qm is stop!\n");
 		return ERR_PTR(-EPERM);
+	}
 
 	if (qm->qp_in_used == qm->qp_num) {
 		dev_info_ratelimited(dev, "All %u queues of QM are busy!\n",
@@ -1871,7 +1846,6 @@ static struct hisi_qp *qm_create_qp_nolock(struct hisi_qm *qm, u8 alg_type)
 	qp->alg_type = alg_type;
 	qp->is_in_kernel = true;
 	qm->qp_in_used++;
-	atomic_set(&qp->qp_status.flags, QP_INIT);
 
 	return qp;
 }
@@ -1914,11 +1888,6 @@ static void hisi_qm_release_qp(struct hisi_qp *qp)
 
 	down_write(&qm->qps_lock);
 
-	if (!qm_qp_avail_state(qm, qp, QP_CLOSE)) {
-		up_write(&qm->qps_lock);
-		return;
-	}
-
 	qm->qp_in_used--;
 	idr_remove(&qm->qp_idr, qp->qp_id);
 
@@ -1966,6 +1935,11 @@ static int qm_cq_ctx_cfg(struct hisi_qp *qp, int qp_id, u32 pasid)
 		cqc.dw3 = cpu_to_le32(QM_MK_CQC_DW3_V2(QM_QC_CQE_SIZE, qp->cq_depth));
 		cqc.w8 = 0; /* rand_qc */
 	}
+	/*
+	 * Enable request finishing interrupts defaultly.
+	 * So, there will be some interrupts until disabling
+	 * this.
+	 */
 	cqc.dw6 = cpu_to_le32(1 << QM_CQ_PHASE_SHIFT | 1 << QM_CQ_FLAG_SHIFT);
 	cqc.base_l = cpu_to_le32(lower_32_bits(qp->cqe_dma));
 	cqc.base_h = cpu_to_le32(upper_32_bits(qp->cqe_dma));
@@ -1998,8 +1972,10 @@ static int qm_start_qp_nolock(struct hisi_qp *qp, unsigned long arg)
 	u32 pasid = arg;
 	int ret;
 
-	if (!qm_qp_avail_state(qm, qp, QP_START))
+	if (atomic_read(&qm->status.flags) == QM_STOP) {
+		dev_info_ratelimited(dev, "failed to start qp as qm is stop!\n");
 		return -EPERM;
+	}
 
 	ret = qm_qp_ctx_cfg(qp, qp_id, pasid);
 	if (ret)
@@ -2121,21 +2097,17 @@ static int qm_stop_qp_nolock(struct hisi_qp *qp)
 	 * is_resetting flag should be set negative so that this qp will not
 	 * be restarted after reset.
 	 */
-	if (atomic_read(&qp->qp_status.flags) == QP_STOP) {
+	if (atomic_read(&qp->qp_status.flags) != QP_START) {
 		qp->is_resetting = false;
 		return 0;
 	}
 
-	if (!qm_qp_avail_state(qp->qm, qp, QP_STOP))
-		return -EPERM;
-
 	atomic_set(&qp->qp_status.flags, QP_STOP);
 
 	ret = qm_drain_qp(qp);
 	if (ret)
 		dev_err(dev, "Failed to drain out data for stopping!\n");
 
-
 	flush_workqueue(qp->qm->wq);
 	if (unlikely(qp->is_resetting && atomic_read(&qp->qp_status.used)))
 		qp_stop_fail_cb(qp);
@@ -2855,13 +2827,8 @@ void hisi_qm_uninit(struct hisi_qm *qm)
 {
 	qm_cmd_uninit(qm);
 	hisi_qm_unint_work(qm);
-	down_write(&qm->qps_lock);
-
-	if (!qm_avail_state(qm, QM_CLOSE)) {
-		up_write(&qm->qps_lock);
-		return;
-	}
 
+	down_write(&qm->qps_lock);
 	hisi_qm_memory_uninit(qm);
 	hisi_qm_set_state(qm, QM_NOT_READY);
 	up_write(&qm->qps_lock);
@@ -3035,11 +3002,6 @@ int hisi_qm_start(struct hisi_qm *qm)
 
 	down_write(&qm->qps_lock);
 
-	if (!qm_avail_state(qm, QM_START)) {
-		up_write(&qm->qps_lock);
-		return -EPERM;
-	}
-
 	dev_dbg(dev, "qm start with %u queue pairs\n", qm->qp_num);
 
 	if (!qm->qp_num) {
@@ -3049,10 +3011,12 @@ int hisi_qm_start(struct hisi_qm *qm)
 	}
 
 	ret = __hisi_qm_start(qm);
-	if (!ret)
-		atomic_set(&qm->status.flags, QM_START);
+	if (ret)
+		goto err_unlock;
 
+	atomic_set(&qm->status.flags, QM_WORK);
 	hisi_qm_set_state(qm, QM_READY);
+
 err_unlock:
 	up_write(&qm->qps_lock);
 	return ret;
@@ -3149,10 +3113,11 @@ int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r)
 	down_write(&qm->qps_lock);
 
 	qm->status.stop_reason = r;
-	if (!qm_avail_state(qm, QM_STOP)) {
-		ret = -EPERM;
+	if (atomic_read(&qm->status.flags) == QM_STOP)
 		goto err_unlock;
-	}
+
+	/* Stop all the request sending at first. */
+	atomic_set(&qm->status.flags, QM_STOP);
 
 	if (qm->status.stop_reason == QM_SOFT_RESET ||
 	    qm->status.stop_reason == QM_DOWN) {
@@ -3176,7 +3141,6 @@ int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r)
 	}
 
 	qm_clear_queues(qm);
-	atomic_set(&qm->status.flags, QM_STOP);
 
 err_unlock:
 	up_write(&qm->qps_lock);
@@ -3966,6 +3930,11 @@ static int qm_set_vf_mse(struct hisi_qm *qm, bool set)
 	int pos;
 	int i;
 
+	/*
+	 * Since function qm_set_vf_mse is called only after SRIOV is enabled,
+	 * pci_find_ext_capability cannot return 0, pos does not need to be
+	 * checked.
+	 */
 	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV);
 	pci_read_config_word(pdev, pos + PCI_SRIOV_CTRL, &sriov_ctrl);
 	if (set)
@@ -4816,7 +4785,7 @@ static void qm_unregister_abnormal_irq(struct hisi_qm *qm)
 	if (qm->fun_type == QM_HW_VF)
 		return;
 
-	val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_ABN_IRQ_TYPE_CAP, qm->cap_ver);
+	val = qm->cap_tables.qm_cap_table[QM_ABN_IRQ_TYPE_CAP_IDX].cap_val;
 	if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_ABN_IRQ_TYPE_MASK))
 		return;
 
@@ -4833,7 +4802,7 @@ static int qm_register_abnormal_irq(struct hisi_qm *qm)
 	if (qm->fun_type == QM_HW_VF)
 		return 0;
 
-	val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_ABN_IRQ_TYPE_CAP, qm->cap_ver);
+	val = qm->cap_tables.qm_cap_table[QM_ABN_IRQ_TYPE_CAP_IDX].cap_val;
 	if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_ABN_IRQ_TYPE_MASK))
 		return 0;
 
@@ -4850,7 +4819,7 @@ static void qm_unregister_mb_cmd_irq(struct hisi_qm *qm)
 	struct pci_dev *pdev = qm->pdev;
 	u32 irq_vector, val;
 
-	val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_PF2VF_IRQ_TYPE_CAP, qm->cap_ver);
+	val = qm->cap_tables.qm_cap_table[QM_PF2VF_IRQ_TYPE_CAP_IDX].cap_val;
 	if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK))
 		return;
 
@@ -4864,7 +4833,7 @@ static int qm_register_mb_cmd_irq(struct hisi_qm *qm)
 	u32 irq_vector, val;
 	int ret;
 
-	val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_PF2VF_IRQ_TYPE_CAP, qm->cap_ver);
+	val = qm->cap_tables.qm_cap_table[QM_PF2VF_IRQ_TYPE_CAP_IDX].cap_val;
 	if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK))
 		return 0;
 
@@ -4881,7 +4850,7 @@ static void qm_unregister_aeq_irq(struct hisi_qm *qm)
 	struct pci_dev *pdev = qm->pdev;
 	u32 irq_vector, val;
 
-	val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_AEQ_IRQ_TYPE_CAP, qm->cap_ver);
+	val = qm->cap_tables.qm_cap_table[QM_AEQ_IRQ_TYPE_CAP_IDX].cap_val;
 	if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK))
 		return;
 
@@ -4895,7 +4864,7 @@ static int qm_register_aeq_irq(struct hisi_qm *qm)
 	u32 irq_vector, val;
 	int ret;
 
-	val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_AEQ_IRQ_TYPE_CAP, qm->cap_ver);
+	val = qm->cap_tables.qm_cap_table[QM_AEQ_IRQ_TYPE_CAP_IDX].cap_val;
 	if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK))
 		return 0;
 
@@ -4913,7 +4882,7 @@ static void qm_unregister_eq_irq(struct hisi_qm *qm)
 	struct pci_dev *pdev = qm->pdev;
 	u32 irq_vector, val;
 
-	val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_EQ_IRQ_TYPE_CAP, qm->cap_ver);
+	val = qm->cap_tables.qm_cap_table[QM_EQ_IRQ_TYPE_CAP_IDX].cap_val;
 	if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK))
 		return;
 
@@ -4927,7 +4896,7 @@ static int qm_register_eq_irq(struct hisi_qm *qm)
 	u32 irq_vector, val;
 	int ret;
 
-	val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_EQ_IRQ_TYPE_CAP, qm->cap_ver);
+	val = qm->cap_tables.qm_cap_table[QM_EQ_IRQ_TYPE_CAP_IDX].cap_val;
 	if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK))
 		return 0;
 
@@ -5015,7 +4984,29 @@ static int qm_get_qp_num(struct hisi_qm *qm)
 	return 0;
 }
 
-static void qm_get_hw_caps(struct hisi_qm *qm)
+static int qm_pre_store_irq_type_caps(struct hisi_qm *qm)
+{
+	struct hisi_qm_cap_record *qm_cap;
+	struct pci_dev *pdev = qm->pdev;
+	size_t i, size;
+
+	size = ARRAY_SIZE(qm_pre_store_caps);
+	qm_cap = devm_kzalloc(&pdev->dev, sizeof(*qm_cap) * size, GFP_KERNEL);
+	if (!qm_cap)
+		return -ENOMEM;
+
+	for (i = 0; i < size; i++) {
+		qm_cap[i].type = qm_pre_store_caps[i];
+		qm_cap[i].cap_val = hisi_qm_get_hw_info(qm, qm_basic_info,
+							qm_pre_store_caps[i], qm->cap_ver);
+	}
+
+	qm->cap_tables.qm_cap_table = qm_cap;
+
+	return 0;
+}
+
+static int qm_get_hw_caps(struct hisi_qm *qm)
 {
 	const struct hisi_qm_cap_info *cap_info = qm->fun_type == QM_HW_PF ?
 						  qm_cap_info_pf : qm_cap_info_vf;
@@ -5046,6 +5037,9 @@ static void qm_get_hw_caps(struct hisi_qm *qm)
 		if (val)
 			set_bit(cap_info[i].type, &qm->caps);
 	}
+
+	/* Fetch and save the value of irq type related capability registers */
+	return qm_pre_store_irq_type_caps(qm);
 }
 
 static int qm_get_pci_res(struct hisi_qm *qm)
@@ -5067,7 +5061,10 @@ static int qm_get_pci_res(struct hisi_qm *qm)
 		goto err_request_mem_regions;
 	}
 
-	qm_get_hw_caps(qm);
+	ret = qm_get_hw_caps(qm);
+	if (ret)
+		goto err_ioremap;
+
 	if (test_bit(QM_SUPPORT_DB_ISOLATION, &qm->caps)) {
 		qm->db_interval = QM_QP_DB_INTERVAL;
 		qm->db_phys_base = pci_resource_start(pdev, PCI_BAR_4);
@@ -5340,7 +5337,6 @@ int hisi_qm_init(struct hisi_qm *qm)
 		goto err_free_qm_memory;
 
 	qm_cmd_init(qm);
-	atomic_set(&qm->status.flags, QM_INIT);
 
 	return 0;
 
diff --git a/drivers/crypto/hisilicon/qm_common.h b/drivers/crypto/hisilicon/qm_common.h
index 7b0b15c83ec1..0760bf55f13e 100644
--- a/drivers/crypto/hisilicon/qm_common.h
+++ b/drivers/crypto/hisilicon/qm_common.h
@@ -72,10 +72,6 @@ struct qm_aeqc {
 	__le32 dw6;
 };
 
-static const char * const qm_s[] = {
-	"init", "start", "close", "stop",
-};
-
 int qm_set_and_get_xqc(struct hisi_qm *qm, u8 cmd, void *xqc, u32 qp_id, bool op);
 void hisi_qm_show_last_dfx_regs(struct hisi_qm *qm);
 void hisi_qm_set_algqos_init(struct hisi_qm *qm);
diff --git a/drivers/crypto/hisilicon/sec2/sec.h b/drivers/crypto/hisilicon/sec2/sec.h
index 3e57fc04b377..410c83712e28 100644
--- a/drivers/crypto/hisilicon/sec2/sec.h
+++ b/drivers/crypto/hisilicon/sec2/sec.h
@@ -220,6 +220,13 @@ enum sec_cap_type {
 	SEC_CORE4_ALG_BITMAP_HIGH,
 };
 
+enum sec_cap_reg_record_idx {
+	SEC_DRV_ALG_BITMAP_LOW_IDX = 0x0,
+	SEC_DRV_ALG_BITMAP_HIGH_IDX,
+	SEC_DEV_ALG_BITMAP_LOW_IDX,
+	SEC_DEV_ALG_BITMAP_HIGH_IDX,
+};
+
 void sec_destroy_qps(struct hisi_qp **qps, int qp_num);
 struct hisi_qp **sec_create_qps(void);
 int sec_register_to_crypto(struct hisi_qm *qm);
diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.c b/drivers/crypto/hisilicon/sec2/sec_crypto.c
index 6fcabbc87860..f028dcfd0ead 100644
--- a/drivers/crypto/hisilicon/sec2/sec_crypto.c
+++ b/drivers/crypto/hisilicon/sec2/sec_crypto.c
@@ -850,6 +850,7 @@ static int sec_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key,
 		ret = sec_skcipher_aes_sm4_setkey(c_ctx, keylen, c_mode);
 		break;
 	default:
+		dev_err(dev, "sec c_alg err!\n");
 		return -EINVAL;
 	}
 
@@ -879,15 +880,11 @@ static int sec_setkey_##name(struct crypto_skcipher *tfm, const u8 *key,\
 GEN_SEC_SETKEY_FUNC(aes_ecb, SEC_CALG_AES, SEC_CMODE_ECB)
 GEN_SEC_SETKEY_FUNC(aes_cbc, SEC_CALG_AES, SEC_CMODE_CBC)
 GEN_SEC_SETKEY_FUNC(aes_xts, SEC_CALG_AES, SEC_CMODE_XTS)
-GEN_SEC_SETKEY_FUNC(aes_ofb, SEC_CALG_AES, SEC_CMODE_OFB)
-GEN_SEC_SETKEY_FUNC(aes_cfb, SEC_CALG_AES, SEC_CMODE_CFB)
 GEN_SEC_SETKEY_FUNC(aes_ctr, SEC_CALG_AES, SEC_CMODE_CTR)
 GEN_SEC_SETKEY_FUNC(3des_ecb, SEC_CALG_3DES, SEC_CMODE_ECB)
 GEN_SEC_SETKEY_FUNC(3des_cbc, SEC_CALG_3DES, SEC_CMODE_CBC)
 GEN_SEC_SETKEY_FUNC(sm4_xts, SEC_CALG_SM4, SEC_CMODE_XTS)
 GEN_SEC_SETKEY_FUNC(sm4_cbc, SEC_CALG_SM4, SEC_CMODE_CBC)
-GEN_SEC_SETKEY_FUNC(sm4_ofb, SEC_CALG_SM4, SEC_CMODE_OFB)
-GEN_SEC_SETKEY_FUNC(sm4_cfb, SEC_CALG_SM4, SEC_CMODE_CFB)
 GEN_SEC_SETKEY_FUNC(sm4_ctr, SEC_CALG_SM4, SEC_CMODE_CTR)
 
 static int sec_cipher_pbuf_map(struct sec_ctx *ctx, struct sec_req *req,
@@ -1176,7 +1173,8 @@ static int sec_aead_setkey(struct crypto_aead *tfm, const u8 *key,
 		return 0;
 	}
 
-	if (crypto_authenc_extractkeys(&keys, key, keylen))
+	ret = crypto_authenc_extractkeys(&keys, key, keylen);
+	if (ret)
 		goto bad_key;
 
 	ret = sec_aead_aes_set_key(c_ctx, &keys);
@@ -1193,6 +1191,7 @@ static int sec_aead_setkey(struct crypto_aead *tfm, const u8 *key,
 
 	if ((ctx->a_ctx.mac_len & SEC_SQE_LEN_RATE_MASK)  ||
 	    (ctx->a_ctx.a_key_len & SEC_SQE_LEN_RATE_MASK)) {
+		ret = -EINVAL;
 		dev_err(dev, "MAC or AUTH key length error!\n");
 		goto bad_key;
 	}
@@ -1201,7 +1200,7 @@ static int sec_aead_setkey(struct crypto_aead *tfm, const u8 *key,
 
 bad_key:
 	memzero_explicit(&keys, sizeof(struct crypto_authenc_keys));
-	return -EINVAL;
+	return ret;
 }
 
 
@@ -2032,8 +2031,6 @@ static int sec_skcipher_cryptlen_check(struct sec_ctx *ctx,
 			ret = -EINVAL;
 		}
 		break;
-	case SEC_CMODE_CFB:
-	case SEC_CMODE_OFB:
 	case SEC_CMODE_CTR:
 		if (unlikely(ctx->sec->qm.ver < QM_HW_V3)) {
 			dev_err(dev, "skcipher HW version error!\n");
@@ -2198,16 +2195,6 @@ static struct sec_skcipher sec_skciphers[] = {
 					SEC_XTS_MAX_KEY_SIZE, AES_BLOCK_SIZE, AES_BLOCK_SIZE),
 	},
 	{
-		.alg_msk = BIT(4),
-		.alg = SEC_SKCIPHER_ALG("ofb(aes)", sec_setkey_aes_ofb,	AES_MIN_KEY_SIZE,
-					AES_MAX_KEY_SIZE, SEC_MIN_BLOCK_SZ, AES_BLOCK_SIZE),
-	},
-	{
-		.alg_msk = BIT(5),
-		.alg = SEC_SKCIPHER_ALG("cfb(aes)", sec_setkey_aes_cfb,	AES_MIN_KEY_SIZE,
-					AES_MAX_KEY_SIZE, SEC_MIN_BLOCK_SZ, AES_BLOCK_SIZE),
-	},
-	{
 		.alg_msk = BIT(12),
 		.alg = SEC_SKCIPHER_ALG("cbc(sm4)", sec_setkey_sm4_cbc,	AES_MIN_KEY_SIZE,
 					AES_MIN_KEY_SIZE, AES_BLOCK_SIZE, AES_BLOCK_SIZE),
@@ -2223,16 +2210,6 @@ static struct sec_skcipher sec_skciphers[] = {
 					SEC_XTS_MIN_KEY_SIZE, AES_BLOCK_SIZE, AES_BLOCK_SIZE),
 	},
 	{
-		.alg_msk = BIT(15),
-		.alg = SEC_SKCIPHER_ALG("ofb(sm4)", sec_setkey_sm4_ofb,	AES_MIN_KEY_SIZE,
-					AES_MIN_KEY_SIZE, SEC_MIN_BLOCK_SZ, AES_BLOCK_SIZE),
-	},
-	{
-		.alg_msk = BIT(16),
-		.alg = SEC_SKCIPHER_ALG("cfb(sm4)", sec_setkey_sm4_cfb,	AES_MIN_KEY_SIZE,
-					AES_MIN_KEY_SIZE, SEC_MIN_BLOCK_SZ, AES_BLOCK_SIZE),
-	},
-	{
 		.alg_msk = BIT(23),
 		.alg = SEC_SKCIPHER_ALG("ecb(des3_ede)", sec_setkey_3des_ecb, SEC_DES3_3KEY_SIZE,
 					SEC_DES3_3KEY_SIZE, DES3_EDE_BLOCK_SIZE, 0),
@@ -2547,9 +2524,12 @@ err:
 
 int sec_register_to_crypto(struct hisi_qm *qm)
 {
-	u64 alg_mask = sec_get_alg_bitmap(qm, SEC_DRV_ALG_BITMAP_HIGH, SEC_DRV_ALG_BITMAP_LOW);
+	u64 alg_mask;
 	int ret = 0;
 
+	alg_mask = sec_get_alg_bitmap(qm, SEC_DRV_ALG_BITMAP_HIGH_IDX,
+				      SEC_DRV_ALG_BITMAP_LOW_IDX);
+
 	mutex_lock(&sec_algs_lock);
 	if (sec_available_devs) {
 		sec_available_devs++;
@@ -2578,7 +2558,10 @@ unlock:
 
 void sec_unregister_from_crypto(struct hisi_qm *qm)
 {
-	u64 alg_mask = sec_get_alg_bitmap(qm, SEC_DRV_ALG_BITMAP_HIGH, SEC_DRV_ALG_BITMAP_LOW);
+	u64 alg_mask;
+
+	alg_mask = sec_get_alg_bitmap(qm, SEC_DRV_ALG_BITMAP_HIGH_IDX,
+				      SEC_DRV_ALG_BITMAP_LOW_IDX);
 
 	mutex_lock(&sec_algs_lock);
 	if (--sec_available_devs)
diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.h b/drivers/crypto/hisilicon/sec2/sec_crypto.h
index d033f63b583f..27a0ee5ad913 100644
--- a/drivers/crypto/hisilicon/sec2/sec_crypto.h
+++ b/drivers/crypto/hisilicon/sec2/sec_crypto.h
@@ -37,8 +37,6 @@ enum sec_mac_len {
 enum sec_cmode {
 	SEC_CMODE_ECB    = 0x0,
 	SEC_CMODE_CBC    = 0x1,
-	SEC_CMODE_CFB    = 0x2,
-	SEC_CMODE_OFB    = 0x3,
 	SEC_CMODE_CTR    = 0x4,
 	SEC_CMODE_CCM    = 0x5,
 	SEC_CMODE_GCM    = 0x6,
diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c
index 0e56a47eb862..7bb99381bbdf 100644
--- a/drivers/crypto/hisilicon/sec2/sec_main.c
+++ b/drivers/crypto/hisilicon/sec2/sec_main.c
@@ -120,7 +120,6 @@
 					GENMASK_ULL(42, 25))
 #define SEC_AEAD_BITMAP			(GENMASK_ULL(7, 6) | GENMASK_ULL(18, 17) | \
 					GENMASK_ULL(45, 43))
-#define SEC_DEV_ALG_MAX_LEN		256
 
 struct sec_hw_error {
 	u32 int_msk;
@@ -132,11 +131,6 @@ struct sec_dfx_item {
 	u32 offset;
 };
 
-struct sec_dev_alg {
-	u64 alg_msk;
-	const char *algs;
-};
-
 static const char sec_name[] = "hisi_sec2";
 static struct dentry *sec_debugfs_root;
 
@@ -159,7 +153,7 @@ static const struct hisi_qm_cap_info sec_basic_info[] = {
 	{SEC_CORE_NUM_CAP, 0x313c, 8, GENMASK(7, 0), 0x4, 0x4, 0x4},
 	{SEC_CORES_PER_CLUSTER_NUM_CAP, 0x313c, 0, GENMASK(7, 0), 0x4, 0x4, 0x4},
 	{SEC_CORE_ENABLE_BITMAP, 0x3140, 32, GENMASK(31, 0), 0x17F, 0x17F, 0xF},
-	{SEC_DRV_ALG_BITMAP_LOW, 0x3144, 0, GENMASK(31, 0), 0x18050CB, 0x18050CB, 0x187F0FF},
+	{SEC_DRV_ALG_BITMAP_LOW, 0x3144, 0, GENMASK(31, 0), 0x18050CB, 0x18050CB, 0x18670CF},
 	{SEC_DRV_ALG_BITMAP_HIGH, 0x3148, 0, GENMASK(31, 0), 0x395C, 0x395C, 0x395C},
 	{SEC_DEV_ALG_BITMAP_LOW, 0x314c, 0, GENMASK(31, 0), 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF},
 	{SEC_DEV_ALG_BITMAP_HIGH, 0x3150, 0, GENMASK(31, 0), 0x3FFF, 0x3FFF, 0x3FFF},
@@ -173,15 +167,22 @@ static const struct hisi_qm_cap_info sec_basic_info[] = {
 	{SEC_CORE4_ALG_BITMAP_HIGH, 0x3170, 0, GENMASK(31, 0), 0x3FFF, 0x3FFF, 0x3FFF},
 };
 
-static const struct sec_dev_alg sec_dev_algs[] = { {
+static const u32 sec_pre_store_caps[] = {
+	SEC_DRV_ALG_BITMAP_LOW,
+	SEC_DRV_ALG_BITMAP_HIGH,
+	SEC_DEV_ALG_BITMAP_LOW,
+	SEC_DEV_ALG_BITMAP_HIGH,
+};
+
+static const struct qm_dev_alg sec_dev_algs[] = { {
 		.alg_msk = SEC_CIPHER_BITMAP,
-		.algs = "cipher\n",
+		.alg = "cipher\n",
 	}, {
 		.alg_msk = SEC_DIGEST_BITMAP,
-		.algs = "digest\n",
+		.alg = "digest\n",
 	}, {
 		.alg_msk = SEC_AEAD_BITMAP,
-		.algs = "aead\n",
+		.alg = "aead\n",
 	},
 };
 
@@ -394,8 +395,8 @@ u64 sec_get_alg_bitmap(struct hisi_qm *qm, u32 high, u32 low)
 {
 	u32 cap_val_h, cap_val_l;
 
-	cap_val_h = hisi_qm_get_hw_info(qm, sec_basic_info, high, qm->cap_ver);
-	cap_val_l = hisi_qm_get_hw_info(qm, sec_basic_info, low, qm->cap_ver);
+	cap_val_h = qm->cap_tables.dev_cap_table[high].cap_val;
+	cap_val_l = qm->cap_tables.dev_cap_table[low].cap_val;
 
 	return ((u64)cap_val_h << SEC_ALG_BITMAP_SHIFT) | (u64)cap_val_l;
 }
@@ -1077,37 +1078,31 @@ static int sec_pf_probe_init(struct sec_dev *sec)
 	return ret;
 }
 
-static int sec_set_qm_algs(struct hisi_qm *qm)
+static int sec_pre_store_cap_reg(struct hisi_qm *qm)
 {
-	struct device *dev = &qm->pdev->dev;
-	char *algs, *ptr;
-	u64 alg_mask;
-	int i;
-
-	if (!qm->use_sva)
-		return 0;
+	struct hisi_qm_cap_record *sec_cap;
+	struct pci_dev *pdev = qm->pdev;
+	size_t i, size;
 
-	algs = devm_kzalloc(dev, SEC_DEV_ALG_MAX_LEN * sizeof(char), GFP_KERNEL);
-	if (!algs)
+	size = ARRAY_SIZE(sec_pre_store_caps);
+	sec_cap = devm_kzalloc(&pdev->dev, sizeof(*sec_cap) * size, GFP_KERNEL);
+	if (!sec_cap)
 		return -ENOMEM;
 
-	alg_mask = sec_get_alg_bitmap(qm, SEC_DEV_ALG_BITMAP_HIGH, SEC_DEV_ALG_BITMAP_LOW);
-
-	for (i = 0; i < ARRAY_SIZE(sec_dev_algs); i++)
-		if (alg_mask & sec_dev_algs[i].alg_msk)
-			strcat(algs, sec_dev_algs[i].algs);
-
-	ptr = strrchr(algs, '\n');
-	if (ptr)
-		*ptr = '\0';
+	for (i = 0; i < size; i++) {
+		sec_cap[i].type = sec_pre_store_caps[i];
+		sec_cap[i].cap_val = hisi_qm_get_hw_info(qm, sec_basic_info,
+				     sec_pre_store_caps[i], qm->cap_ver);
+	}
 
-	qm->uacce->algs = algs;
+	qm->cap_tables.dev_cap_table = sec_cap;
 
 	return 0;
 }
 
 static int sec_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
 {
+	u64 alg_msk;
 	int ret;
 
 	qm->pdev = pdev;
@@ -1142,7 +1137,16 @@ static int sec_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
 		return ret;
 	}
 
-	ret = sec_set_qm_algs(qm);
+	/* Fetch and save the value of capability registers */
+	ret = sec_pre_store_cap_reg(qm);
+	if (ret) {
+		pci_err(qm->pdev, "Failed to pre-store capability registers!\n");
+		hisi_qm_uninit(qm);
+		return ret;
+	}
+
+	alg_msk = sec_get_alg_bitmap(qm, SEC_DEV_ALG_BITMAP_HIGH_IDX, SEC_DEV_ALG_BITMAP_LOW_IDX);
+	ret = hisi_qm_set_algs(qm, alg_msk, sec_dev_algs, ARRAY_SIZE(sec_dev_algs));
 	if (ret) {
 		pci_err(qm->pdev, "Failed to set sec algs!\n");
 		hisi_qm_uninit(qm);
diff --git a/drivers/crypto/hisilicon/sgl.c b/drivers/crypto/hisilicon/sgl.c
index 3df7a256e919..0beca257c20b 100644
--- a/drivers/crypto/hisilicon/sgl.c
+++ b/drivers/crypto/hisilicon/sgl.c
@@ -70,11 +70,11 @@ struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev,
 			 HISI_ACC_SGL_ALIGN_SIZE);
 
 	/*
-	 * the pool may allocate a block of memory of size PAGE_SIZE * 2^MAX_ORDER,
+	 * the pool may allocate a block of memory of size PAGE_SIZE * 2^MAX_PAGE_ORDER,
 	 * block size may exceed 2^31 on ia64, so the max of block size is 2^31
 	 */
-	block_size = 1 << (PAGE_SHIFT + MAX_ORDER < 32 ?
-			   PAGE_SHIFT + MAX_ORDER : 31);
+	block_size = 1 << (PAGE_SHIFT + MAX_PAGE_ORDER < 32 ?
+			   PAGE_SHIFT + MAX_PAGE_ORDER : 31);
 	sgl_num_per_block = block_size / sgl_size;
 	block_num = count / sgl_num_per_block;
 	remain_sgl = count % sgl_num_per_block;
@@ -121,10 +121,10 @@ struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev,
 	return pool;
 
 err_free_mem:
-	for (j = 0; j < i; j++) {
+	for (j = 0; j < i; j++)
 		dma_free_coherent(dev, block_size, block[j].sgl,
 				  block[j].sgl_dma);
-	}
+
 	kfree_sensitive(pool);
 	return ERR_PTR(-ENOMEM);
 }
@@ -140,7 +140,7 @@ EXPORT_SYMBOL_GPL(hisi_acc_create_sgl_pool);
 void hisi_acc_free_sgl_pool(struct device *dev, struct hisi_acc_sgl_pool *pool)
 {
 	struct mem_block *block;
-	int i;
+	u32 i;
 
 	if (!dev || !pool)
 		return;
@@ -196,9 +196,10 @@ static void update_hw_sgl_sum_sge(struct hisi_acc_hw_sgl *hw_sgl, u16 sum)
 static void clear_hw_sgl_sge(struct hisi_acc_hw_sgl *hw_sgl)
 {
 	struct acc_hw_sge *hw_sge = hw_sgl->sge_entries;
+	u16 entry_sum = le16_to_cpu(hw_sgl->entry_sum_in_sgl);
 	int i;
 
-	for (i = 0; i < le16_to_cpu(hw_sgl->entry_sum_in_sgl); i++) {
+	for (i = 0; i < entry_sum; i++) {
 		hw_sge[i].page_ctrl = NULL;
 		hw_sge[i].buf = 0;
 		hw_sge[i].len = 0;
@@ -223,10 +224,11 @@ hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev,
 			      u32 index, dma_addr_t *hw_sgl_dma)
 {
 	struct hisi_acc_hw_sgl *curr_hw_sgl;
+	unsigned int i, sg_n_mapped;
 	dma_addr_t curr_sgl_dma = 0;
 	struct acc_hw_sge *curr_hw_sge;
 	struct scatterlist *sg;
-	int i, sg_n, sg_n_mapped;
+	int sg_n;
 
 	if (!dev || !sgl || !pool || !hw_sgl_dma)
 		return ERR_PTR(-EINVAL);
diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c
index db4c964cd649..479ba8a1d6b5 100644
--- a/drivers/crypto/hisilicon/zip/zip_main.c
+++ b/drivers/crypto/hisilicon/zip/zip_main.c
@@ -74,7 +74,6 @@
 #define HZIP_AXI_SHUTDOWN_ENABLE	BIT(14)
 #define HZIP_WR_PORT			BIT(11)
 
-#define HZIP_DEV_ALG_MAX_LEN		256
 #define HZIP_ALG_ZLIB_BIT		GENMASK(1, 0)
 #define HZIP_ALG_GZIP_BIT		GENMASK(3, 2)
 #define HZIP_ALG_DEFLATE_BIT		GENMASK(5, 4)
@@ -107,6 +106,14 @@
 #define HZIP_CLOCK_GATED_EN		(HZIP_CORE_GATED_EN | \
 					 HZIP_CORE_GATED_OOO_EN)
 
+/* zip comp high performance */
+#define HZIP_HIGH_PERF_OFFSET		0x301208
+
+enum {
+	HZIP_HIGH_COMP_RATE,
+	HZIP_HIGH_COMP_PERF,
+};
+
 static const char hisi_zip_name[] = "hisi_zip";
 static struct dentry *hzip_debugfs_root;
 
@@ -120,23 +127,18 @@ struct zip_dfx_item {
 	u32 offset;
 };
 
-struct zip_dev_alg {
-	u32 alg_msk;
-	const char *algs;
-};
-
-static const struct zip_dev_alg zip_dev_algs[] = { {
+static const struct qm_dev_alg zip_dev_algs[] = { {
 		.alg_msk = HZIP_ALG_ZLIB_BIT,
-		.algs = "zlib\n",
+		.alg = "zlib\n",
 	}, {
 		.alg_msk = HZIP_ALG_GZIP_BIT,
-		.algs = "gzip\n",
+		.alg = "gzip\n",
 	}, {
 		.alg_msk = HZIP_ALG_DEFLATE_BIT,
-		.algs = "deflate\n",
+		.alg = "deflate\n",
 	}, {
 		.alg_msk = HZIP_ALG_LZ77_BIT,
-		.algs = "lz77_zstd\n",
+		.alg = "lz77_zstd\n",
 	},
 };
 
@@ -247,6 +249,26 @@ static struct hisi_qm_cap_info zip_basic_cap_info[] = {
 	{ZIP_CAP_MAX, 0x317c, 0, GENMASK(0, 0), 0x0, 0x0, 0x0}
 };
 
+enum zip_pre_store_cap_idx {
+	ZIP_CORE_NUM_CAP_IDX = 0x0,
+	ZIP_CLUSTER_COMP_NUM_CAP_IDX,
+	ZIP_CLUSTER_DECOMP_NUM_CAP_IDX,
+	ZIP_DECOMP_ENABLE_BITMAP_IDX,
+	ZIP_COMP_ENABLE_BITMAP_IDX,
+	ZIP_DRV_ALG_BITMAP_IDX,
+	ZIP_DEV_ALG_BITMAP_IDX,
+};
+
+static const u32 zip_pre_store_caps[] = {
+	ZIP_CORE_NUM_CAP,
+	ZIP_CLUSTER_COMP_NUM_CAP,
+	ZIP_CLUSTER_DECOMP_NUM_CAP,
+	ZIP_DECOMP_ENABLE_BITMAP,
+	ZIP_COMP_ENABLE_BITMAP,
+	ZIP_DRV_ALG_BITMAP,
+	ZIP_DEV_ALG_BITMAP,
+};
+
 enum {
 	HZIP_COMP_CORE0,
 	HZIP_COMP_CORE1,
@@ -270,28 +292,28 @@ static const u64 core_offsets[] = {
 };
 
 static const struct debugfs_reg32 hzip_dfx_regs[] = {
-	{"HZIP_GET_BD_NUM                ",  0x00ull},
-	{"HZIP_GET_RIGHT_BD              ",  0x04ull},
-	{"HZIP_GET_ERROR_BD              ",  0x08ull},
-	{"HZIP_DONE_BD_NUM               ",  0x0cull},
-	{"HZIP_WORK_CYCLE                ",  0x10ull},
-	{"HZIP_IDLE_CYCLE                ",  0x18ull},
-	{"HZIP_MAX_DELAY                 ",  0x20ull},
-	{"HZIP_MIN_DELAY                 ",  0x24ull},
-	{"HZIP_AVG_DELAY                 ",  0x28ull},
-	{"HZIP_MEM_VISIBLE_DATA          ",  0x30ull},
-	{"HZIP_MEM_VISIBLE_ADDR          ",  0x34ull},
-	{"HZIP_CONSUMED_BYTE             ",  0x38ull},
-	{"HZIP_PRODUCED_BYTE             ",  0x40ull},
-	{"HZIP_COMP_INF                  ",  0x70ull},
-	{"HZIP_PRE_OUT                   ",  0x78ull},
-	{"HZIP_BD_RD                     ",  0x7cull},
-	{"HZIP_BD_WR                     ",  0x80ull},
-	{"HZIP_GET_BD_AXI_ERR_NUM        ",  0x84ull},
-	{"HZIP_GET_BD_PARSE_ERR_NUM      ",  0x88ull},
-	{"HZIP_ADD_BD_AXI_ERR_NUM        ",  0x8cull},
-	{"HZIP_DECOMP_STF_RELOAD_CURR_ST ",  0x94ull},
-	{"HZIP_DECOMP_LZ77_CURR_ST       ",  0x9cull},
+	{"HZIP_GET_BD_NUM                ",  0x00},
+	{"HZIP_GET_RIGHT_BD              ",  0x04},
+	{"HZIP_GET_ERROR_BD              ",  0x08},
+	{"HZIP_DONE_BD_NUM               ",  0x0c},
+	{"HZIP_WORK_CYCLE                ",  0x10},
+	{"HZIP_IDLE_CYCLE                ",  0x18},
+	{"HZIP_MAX_DELAY                 ",  0x20},
+	{"HZIP_MIN_DELAY                 ",  0x24},
+	{"HZIP_AVG_DELAY                 ",  0x28},
+	{"HZIP_MEM_VISIBLE_DATA          ",  0x30},
+	{"HZIP_MEM_VISIBLE_ADDR          ",  0x34},
+	{"HZIP_CONSUMED_BYTE             ",  0x38},
+	{"HZIP_PRODUCED_BYTE             ",  0x40},
+	{"HZIP_COMP_INF                  ",  0x70},
+	{"HZIP_PRE_OUT                   ",  0x78},
+	{"HZIP_BD_RD                     ",  0x7c},
+	{"HZIP_BD_WR                     ",  0x80},
+	{"HZIP_GET_BD_AXI_ERR_NUM        ",  0x84},
+	{"HZIP_GET_BD_PARSE_ERR_NUM      ",  0x88},
+	{"HZIP_ADD_BD_AXI_ERR_NUM        ",  0x8c},
+	{"HZIP_DECOMP_STF_RELOAD_CURR_ST ",  0x94},
+	{"HZIP_DECOMP_LZ77_CURR_ST       ",  0x9c},
 };
 
 static const struct debugfs_reg32 hzip_com_dfx_regs[] = {
@@ -303,11 +325,11 @@ static const struct debugfs_reg32 hzip_com_dfx_regs[] = {
 };
 
 static const struct debugfs_reg32 hzip_dump_dfx_regs[] = {
-	{"HZIP_GET_BD_NUM                ",  0x00ull},
-	{"HZIP_GET_RIGHT_BD              ",  0x04ull},
-	{"HZIP_GET_ERROR_BD              ",  0x08ull},
-	{"HZIP_DONE_BD_NUM               ",  0x0cull},
-	{"HZIP_MAX_DELAY                 ",  0x20ull},
+	{"HZIP_GET_BD_NUM                ",  0x00},
+	{"HZIP_GET_RIGHT_BD              ",  0x04},
+	{"HZIP_GET_ERROR_BD              ",  0x08},
+	{"HZIP_DONE_BD_NUM               ",  0x0c},
+	{"HZIP_MAX_DELAY                 ",  0x20},
 };
 
 /* define the ZIP's dfx regs region and region length */
@@ -352,6 +374,37 @@ static int hzip_diff_regs_show(struct seq_file *s, void *unused)
 	return 0;
 }
 DEFINE_SHOW_ATTRIBUTE(hzip_diff_regs);
+
+static int perf_mode_set(const char *val, const struct kernel_param *kp)
+{
+	int ret;
+	u32 n;
+
+	if (!val)
+		return -EINVAL;
+
+	ret = kstrtou32(val, 10, &n);
+	if (ret != 0 || (n != HZIP_HIGH_COMP_PERF &&
+			 n != HZIP_HIGH_COMP_RATE))
+		return -EINVAL;
+
+	return param_set_int(val, kp);
+}
+
+static const struct kernel_param_ops zip_com_perf_ops = {
+	.set = perf_mode_set,
+	.get = param_get_int,
+};
+
+/*
+ * perf_mode = 0 means enable high compression rate mode,
+ * perf_mode = 1 means enable high compression performance mode.
+ * These two modes only apply to the compression direction.
+ */
+static u32 perf_mode = HZIP_HIGH_COMP_RATE;
+module_param_cb(perf_mode, &zip_com_perf_ops, &perf_mode, 0444);
+MODULE_PARM_DESC(perf_mode, "ZIP high perf mode 0(default), 1(enable)");
+
 static const struct kernel_param_ops zip_uacce_mode_ops = {
 	.set = uacce_mode_set,
 	.get = param_get_int,
@@ -410,40 +463,33 @@ bool hisi_zip_alg_support(struct hisi_qm *qm, u32 alg)
 {
 	u32 cap_val;
 
-	cap_val = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_DRV_ALG_BITMAP, qm->cap_ver);
+	cap_val = qm->cap_tables.dev_cap_table[ZIP_DRV_ALG_BITMAP_IDX].cap_val;
 	if ((alg & cap_val) == alg)
 		return true;
 
 	return false;
 }
 
-static int hisi_zip_set_qm_algs(struct hisi_qm *qm)
+static int hisi_zip_set_high_perf(struct hisi_qm *qm)
 {
-	struct device *dev = &qm->pdev->dev;
-	char *algs, *ptr;
-	u32 alg_mask;
-	int i;
-
-	if (!qm->use_sva)
-		return 0;
-
-	algs = devm_kzalloc(dev, HZIP_DEV_ALG_MAX_LEN * sizeof(char), GFP_KERNEL);
-	if (!algs)
-		return -ENOMEM;
-
-	alg_mask = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_DEV_ALG_BITMAP, qm->cap_ver);
-
-	for (i = 0; i < ARRAY_SIZE(zip_dev_algs); i++)
-		if (alg_mask & zip_dev_algs[i].alg_msk)
-			strcat(algs, zip_dev_algs[i].algs);
-
-	ptr = strrchr(algs, '\n');
-	if (ptr)
-		*ptr = '\0';
+	u32 val;
+	int ret;
 
-	qm->uacce->algs = algs;
+	val = readl_relaxed(qm->io_base + HZIP_HIGH_PERF_OFFSET);
+	if (perf_mode == HZIP_HIGH_COMP_PERF)
+		val |= HZIP_HIGH_COMP_PERF;
+	else
+		val &= ~HZIP_HIGH_COMP_PERF;
+
+	/* Set perf mode */
+	writel(val, qm->io_base + HZIP_HIGH_PERF_OFFSET);
+	ret = readl_relaxed_poll_timeout(qm->io_base + HZIP_HIGH_PERF_OFFSET,
+					 val, val == perf_mode, HZIP_DELAY_1_US,
+					 HZIP_POLL_TIMEOUT_US);
+	if (ret)
+		pci_err(qm->pdev, "failed to set perf mode\n");
 
-	return 0;
+	return ret;
 }
 
 static void hisi_zip_open_sva_prefetch(struct hisi_qm *qm)
@@ -542,10 +588,8 @@ static int hisi_zip_set_user_domain_and_cache(struct hisi_qm *qm)
 	}
 
 	/* let's open all compression/decompression cores */
-	dcomp_bm = hisi_qm_get_hw_info(qm, zip_basic_cap_info,
-				       ZIP_DECOMP_ENABLE_BITMAP, qm->cap_ver);
-	comp_bm = hisi_qm_get_hw_info(qm, zip_basic_cap_info,
-				      ZIP_COMP_ENABLE_BITMAP, qm->cap_ver);
+	dcomp_bm = qm->cap_tables.dev_cap_table[ZIP_DECOMP_ENABLE_BITMAP_IDX].cap_val;
+	comp_bm = qm->cap_tables.dev_cap_table[ZIP_COMP_ENABLE_BITMAP_IDX].cap_val;
 	writel(HZIP_DECOMP_CHECK_ENABLE | dcomp_bm | comp_bm, base + HZIP_CLOCK_GATE_CTRL);
 
 	/* enable sqc,cqc writeback */
@@ -772,9 +816,8 @@ static int hisi_zip_core_debug_init(struct hisi_qm *qm)
 	char buf[HZIP_BUF_SIZE];
 	int i;
 
-	zip_core_num = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CORE_NUM_CAP, qm->cap_ver);
-	zip_comp_core_num = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CLUSTER_COMP_NUM_CAP,
-						qm->cap_ver);
+	zip_core_num = qm->cap_tables.dev_cap_table[ZIP_CORE_NUM_CAP_IDX].cap_val;
+	zip_comp_core_num = qm->cap_tables.dev_cap_table[ZIP_CLUSTER_COMP_NUM_CAP_IDX].cap_val;
 
 	for (i = 0; i < zip_core_num; i++) {
 		if (i < zip_comp_core_num)
@@ -916,7 +959,7 @@ static int hisi_zip_show_last_regs_init(struct hisi_qm *qm)
 	u32 zip_core_num;
 	int i, j, idx;
 
-	zip_core_num = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CORE_NUM_CAP, qm->cap_ver);
+	zip_core_num = qm->cap_tables.dev_cap_table[ZIP_CORE_NUM_CAP_IDX].cap_val;
 
 	debug->last_words = kcalloc(core_dfx_regs_num * zip_core_num + com_dfx_regs_num,
 				    sizeof(unsigned int), GFP_KERNEL);
@@ -972,9 +1015,9 @@ static void hisi_zip_show_last_dfx_regs(struct hisi_qm *qm)
 				 hzip_com_dfx_regs[i].name, debug->last_words[i], val);
 	}
 
-	zip_core_num = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CORE_NUM_CAP, qm->cap_ver);
-	zip_comp_core_num = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CLUSTER_COMP_NUM_CAP,
-						qm->cap_ver);
+	zip_core_num = qm->cap_tables.dev_cap_table[ZIP_CORE_NUM_CAP_IDX].cap_val;
+	zip_comp_core_num = qm->cap_tables.dev_cap_table[ZIP_CLUSTER_COMP_NUM_CAP_IDX].cap_val;
+
 	for (i = 0; i < zip_core_num; i++) {
 		if (i < zip_comp_core_num)
 			scnprintf(buf, sizeof(buf), "Comp_core-%d", i);
@@ -1115,6 +1158,10 @@ static int hisi_zip_pf_probe_init(struct hisi_zip *hisi_zip)
 	if (ret)
 		return ret;
 
+	ret = hisi_zip_set_high_perf(qm);
+	if (ret)
+		return ret;
+
 	hisi_zip_open_sva_prefetch(qm);
 	hisi_qm_dev_err_init(qm);
 	hisi_zip_debug_regs_clear(qm);
@@ -1126,8 +1173,31 @@ static int hisi_zip_pf_probe_init(struct hisi_zip *hisi_zip)
 	return ret;
 }
 
+static int zip_pre_store_cap_reg(struct hisi_qm *qm)
+{
+	struct hisi_qm_cap_record *zip_cap;
+	struct pci_dev *pdev = qm->pdev;
+	size_t i, size;
+
+	size = ARRAY_SIZE(zip_pre_store_caps);
+	zip_cap = devm_kzalloc(&pdev->dev, sizeof(*zip_cap) * size, GFP_KERNEL);
+	if (!zip_cap)
+		return -ENOMEM;
+
+	for (i = 0; i < size; i++) {
+		zip_cap[i].type = zip_pre_store_caps[i];
+		zip_cap[i].cap_val = hisi_qm_get_hw_info(qm, zip_basic_cap_info,
+				     zip_pre_store_caps[i], qm->cap_ver);
+	}
+
+	qm->cap_tables.dev_cap_table = zip_cap;
+
+	return 0;
+}
+
 static int hisi_zip_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
 {
+	u64 alg_msk;
 	int ret;
 
 	qm->pdev = pdev;
@@ -1163,7 +1233,16 @@ static int hisi_zip_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
 		return ret;
 	}
 
-	ret = hisi_zip_set_qm_algs(qm);
+	/* Fetch and save the value of capability registers */
+	ret = zip_pre_store_cap_reg(qm);
+	if (ret) {
+		pci_err(qm->pdev, "Failed to pre-store capability registers!\n");
+		hisi_qm_uninit(qm);
+		return ret;
+	}
+
+	alg_msk = qm->cap_tables.dev_cap_table[ZIP_DEV_ALG_BITMAP_IDX].cap_val;
+	ret = hisi_qm_set_algs(qm, alg_msk, zip_dev_algs, ARRAY_SIZE(zip_dev_algs));
 	if (ret) {
 		pci_err(qm->pdev, "Failed to set zip algs!\n");
 		hisi_qm_uninit(qm);
diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index 76da14af74b5..f5c1912aa564 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -1191,8 +1191,6 @@ static struct safexcel_alg_template *safexcel_algs[] = {
 	&safexcel_alg_cbc_des3_ede,
 	&safexcel_alg_ecb_aes,
 	&safexcel_alg_cbc_aes,
-	&safexcel_alg_cfb_aes,
-	&safexcel_alg_ofb_aes,
 	&safexcel_alg_ctr_aes,
 	&safexcel_alg_md5,
 	&safexcel_alg_sha1,
@@ -1231,8 +1229,6 @@ static struct safexcel_alg_template *safexcel_algs[] = {
 	&safexcel_alg_hmac_sm3,
 	&safexcel_alg_ecb_sm4,
 	&safexcel_alg_cbc_sm4,
-	&safexcel_alg_ofb_sm4,
-	&safexcel_alg_cfb_sm4,
 	&safexcel_alg_ctr_sm4,
 	&safexcel_alg_authenc_hmac_sha1_cbc_sm4,
 	&safexcel_alg_authenc_hmac_sm3_cbc_sm4,
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index 47ef6c7cd02c..d0059ce954dd 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -933,8 +933,6 @@ extern struct safexcel_alg_template safexcel_alg_ecb_des3_ede;
 extern struct safexcel_alg_template safexcel_alg_cbc_des3_ede;
 extern struct safexcel_alg_template safexcel_alg_ecb_aes;
 extern struct safexcel_alg_template safexcel_alg_cbc_aes;
-extern struct safexcel_alg_template safexcel_alg_cfb_aes;
-extern struct safexcel_alg_template safexcel_alg_ofb_aes;
 extern struct safexcel_alg_template safexcel_alg_ctr_aes;
 extern struct safexcel_alg_template safexcel_alg_md5;
 extern struct safexcel_alg_template safexcel_alg_sha1;
@@ -973,8 +971,6 @@ extern struct safexcel_alg_template safexcel_alg_sm3;
 extern struct safexcel_alg_template safexcel_alg_hmac_sm3;
 extern struct safexcel_alg_template safexcel_alg_ecb_sm4;
 extern struct safexcel_alg_template safexcel_alg_cbc_sm4;
-extern struct safexcel_alg_template safexcel_alg_ofb_sm4;
-extern struct safexcel_alg_template safexcel_alg_cfb_sm4;
 extern struct safexcel_alg_template safexcel_alg_ctr_sm4;
 extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha1_cbc_sm4;
 extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sm3_cbc_sm4;
diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index 272c28b5a088..42677f7458b7 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -742,9 +742,9 @@ static int safexcel_send_req(struct crypto_async_request *base, int ring,
 				max(totlen_src, totlen_dst));
 			return -EINVAL;
 		}
-		if (sreq->nr_src > 0)
-			dma_map_sg(priv->dev, src, sreq->nr_src,
-				   DMA_BIDIRECTIONAL);
+		if (sreq->nr_src > 0 &&
+		    !dma_map_sg(priv->dev, src, sreq->nr_src, DMA_BIDIRECTIONAL))
+			return -EIO;
 	} else {
 		if (unlikely(totlen_src && (sreq->nr_src <= 0))) {
 			dev_err(priv->dev, "Source buffer not large enough (need %d bytes)!",
@@ -752,8 +752,9 @@ static int safexcel_send_req(struct crypto_async_request *base, int ring,
 			return -EINVAL;
 		}
 
-		if (sreq->nr_src > 0)
-			dma_map_sg(priv->dev, src, sreq->nr_src, DMA_TO_DEVICE);
+		if (sreq->nr_src > 0 &&
+		    !dma_map_sg(priv->dev, src, sreq->nr_src, DMA_TO_DEVICE))
+			return -EIO;
 
 		if (unlikely(totlen_dst && (sreq->nr_dst <= 0))) {
 			dev_err(priv->dev, "Dest buffer not large enough (need %d bytes)!",
@@ -762,9 +763,11 @@ static int safexcel_send_req(struct crypto_async_request *base, int ring,
 			goto unmap;
 		}
 
-		if (sreq->nr_dst > 0)
-			dma_map_sg(priv->dev, dst, sreq->nr_dst,
-				   DMA_FROM_DEVICE);
+		if (sreq->nr_dst > 0 &&
+		    !dma_map_sg(priv->dev, dst, sreq->nr_dst, DMA_FROM_DEVICE)) {
+			ret = -EIO;
+			goto unmap;
+		}
 	}
 
 	memcpy(ctx->base.ctxr->data, ctx->key, ctx->key_len);
@@ -1349,82 +1352,6 @@ struct safexcel_alg_template safexcel_alg_cbc_aes = {
 	},
 };
 
-static int safexcel_skcipher_aes_cfb_cra_init(struct crypto_tfm *tfm)
-{
-	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	safexcel_skcipher_cra_init(tfm);
-	ctx->alg  = SAFEXCEL_AES;
-	ctx->blocksz = AES_BLOCK_SIZE;
-	ctx->mode = CONTEXT_CONTROL_CRYPTO_MODE_CFB;
-	return 0;
-}
-
-struct safexcel_alg_template safexcel_alg_cfb_aes = {
-	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
-	.algo_mask = SAFEXCEL_ALG_AES | SAFEXCEL_ALG_AES_XFB,
-	.alg.skcipher = {
-		.setkey = safexcel_skcipher_aes_setkey,
-		.encrypt = safexcel_encrypt,
-		.decrypt = safexcel_decrypt,
-		.min_keysize = AES_MIN_KEY_SIZE,
-		.max_keysize = AES_MAX_KEY_SIZE,
-		.ivsize = AES_BLOCK_SIZE,
-		.base = {
-			.cra_name = "cfb(aes)",
-			.cra_driver_name = "safexcel-cfb-aes",
-			.cra_priority = SAFEXCEL_CRA_PRIORITY,
-			.cra_flags = CRYPTO_ALG_ASYNC |
-				     CRYPTO_ALG_ALLOCATES_MEMORY |
-				     CRYPTO_ALG_KERN_DRIVER_ONLY,
-			.cra_blocksize = 1,
-			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
-			.cra_alignmask = 0,
-			.cra_init = safexcel_skcipher_aes_cfb_cra_init,
-			.cra_exit = safexcel_skcipher_cra_exit,
-			.cra_module = THIS_MODULE,
-		},
-	},
-};
-
-static int safexcel_skcipher_aes_ofb_cra_init(struct crypto_tfm *tfm)
-{
-	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	safexcel_skcipher_cra_init(tfm);
-	ctx->alg  = SAFEXCEL_AES;
-	ctx->blocksz = AES_BLOCK_SIZE;
-	ctx->mode = CONTEXT_CONTROL_CRYPTO_MODE_OFB;
-	return 0;
-}
-
-struct safexcel_alg_template safexcel_alg_ofb_aes = {
-	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
-	.algo_mask = SAFEXCEL_ALG_AES | SAFEXCEL_ALG_AES_XFB,
-	.alg.skcipher = {
-		.setkey = safexcel_skcipher_aes_setkey,
-		.encrypt = safexcel_encrypt,
-		.decrypt = safexcel_decrypt,
-		.min_keysize = AES_MIN_KEY_SIZE,
-		.max_keysize = AES_MAX_KEY_SIZE,
-		.ivsize = AES_BLOCK_SIZE,
-		.base = {
-			.cra_name = "ofb(aes)",
-			.cra_driver_name = "safexcel-ofb-aes",
-			.cra_priority = SAFEXCEL_CRA_PRIORITY,
-			.cra_flags = CRYPTO_ALG_ASYNC |
-				     CRYPTO_ALG_ALLOCATES_MEMORY |
-				     CRYPTO_ALG_KERN_DRIVER_ONLY,
-			.cra_blocksize = 1,
-			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
-			.cra_alignmask = 0,
-			.cra_init = safexcel_skcipher_aes_ofb_cra_init,
-			.cra_exit = safexcel_skcipher_cra_exit,
-			.cra_module = THIS_MODULE,
-		},
-	},
-};
-
 static int safexcel_skcipher_aesctr_setkey(struct crypto_skcipher *ctfm,
 					   const u8 *key, unsigned int len)
 {
@@ -3183,82 +3110,6 @@ struct safexcel_alg_template safexcel_alg_cbc_sm4 = {
 	},
 };
 
-static int safexcel_skcipher_sm4_ofb_cra_init(struct crypto_tfm *tfm)
-{
-	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	safexcel_skcipher_cra_init(tfm);
-	ctx->alg  = SAFEXCEL_SM4;
-	ctx->blocksz = SM4_BLOCK_SIZE;
-	ctx->mode = CONTEXT_CONTROL_CRYPTO_MODE_OFB;
-	return 0;
-}
-
-struct safexcel_alg_template safexcel_alg_ofb_sm4 = {
-	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
-	.algo_mask = SAFEXCEL_ALG_SM4 | SAFEXCEL_ALG_AES_XFB,
-	.alg.skcipher = {
-		.setkey = safexcel_skcipher_sm4_setkey,
-		.encrypt = safexcel_encrypt,
-		.decrypt = safexcel_decrypt,
-		.min_keysize = SM4_KEY_SIZE,
-		.max_keysize = SM4_KEY_SIZE,
-		.ivsize = SM4_BLOCK_SIZE,
-		.base = {
-			.cra_name = "ofb(sm4)",
-			.cra_driver_name = "safexcel-ofb-sm4",
-			.cra_priority = SAFEXCEL_CRA_PRIORITY,
-			.cra_flags = CRYPTO_ALG_ASYNC |
-				     CRYPTO_ALG_ALLOCATES_MEMORY |
-				     CRYPTO_ALG_KERN_DRIVER_ONLY,
-			.cra_blocksize = 1,
-			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
-			.cra_alignmask = 0,
-			.cra_init = safexcel_skcipher_sm4_ofb_cra_init,
-			.cra_exit = safexcel_skcipher_cra_exit,
-			.cra_module = THIS_MODULE,
-		},
-	},
-};
-
-static int safexcel_skcipher_sm4_cfb_cra_init(struct crypto_tfm *tfm)
-{
-	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	safexcel_skcipher_cra_init(tfm);
-	ctx->alg  = SAFEXCEL_SM4;
-	ctx->blocksz = SM4_BLOCK_SIZE;
-	ctx->mode = CONTEXT_CONTROL_CRYPTO_MODE_CFB;
-	return 0;
-}
-
-struct safexcel_alg_template safexcel_alg_cfb_sm4 = {
-	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
-	.algo_mask = SAFEXCEL_ALG_SM4 | SAFEXCEL_ALG_AES_XFB,
-	.alg.skcipher = {
-		.setkey = safexcel_skcipher_sm4_setkey,
-		.encrypt = safexcel_encrypt,
-		.decrypt = safexcel_decrypt,
-		.min_keysize = SM4_KEY_SIZE,
-		.max_keysize = SM4_KEY_SIZE,
-		.ivsize = SM4_BLOCK_SIZE,
-		.base = {
-			.cra_name = "cfb(sm4)",
-			.cra_driver_name = "safexcel-cfb-sm4",
-			.cra_priority = SAFEXCEL_CRA_PRIORITY,
-			.cra_flags = CRYPTO_ALG_ASYNC |
-				     CRYPTO_ALG_ALLOCATES_MEMORY |
-				     CRYPTO_ALG_KERN_DRIVER_ONLY,
-			.cra_blocksize = 1,
-			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
-			.cra_alignmask = 0,
-			.cra_init = safexcel_skcipher_sm4_cfb_cra_init,
-			.cra_exit = safexcel_skcipher_cra_exit,
-			.cra_module = THIS_MODULE,
-		},
-	},
-};
-
 static int safexcel_skcipher_sm4ctr_setkey(struct crypto_skcipher *ctfm,
 					   const u8 *key, unsigned int len)
 {
diff --git a/drivers/crypto/intel/Kconfig b/drivers/crypto/intel/Kconfig
index 3d90c87d4094..f38cd62a3f67 100644
--- a/drivers/crypto/intel/Kconfig
+++ b/drivers/crypto/intel/Kconfig
@@ -3,3 +3,4 @@
 source "drivers/crypto/intel/keembay/Kconfig"
 source "drivers/crypto/intel/ixp4xx/Kconfig"
 source "drivers/crypto/intel/qat/Kconfig"
+source "drivers/crypto/intel/iaa/Kconfig"
diff --git a/drivers/crypto/intel/Makefile b/drivers/crypto/intel/Makefile
index b3d0352ae188..2f56f6d34cf0 100644
--- a/drivers/crypto/intel/Makefile
+++ b/drivers/crypto/intel/Makefile
@@ -3,3 +3,4 @@
 obj-y += keembay/
 obj-y += ixp4xx/
 obj-$(CONFIG_CRYPTO_DEV_QAT) += qat/
+obj-$(CONFIG_CRYPTO_DEV_IAA_CRYPTO) += iaa/
diff --git a/drivers/crypto/intel/iaa/Kconfig b/drivers/crypto/intel/iaa/Kconfig
new file mode 100644
index 000000000000..d53f4b1d494f
--- /dev/null
+++ b/drivers/crypto/intel/iaa/Kconfig
@@ -0,0 +1,19 @@
+config CRYPTO_DEV_IAA_CRYPTO
+	tristate "Support for Intel(R) IAA Compression Accelerator"
+	depends on CRYPTO_DEFLATE
+	depends on INTEL_IDXD
+	default n
+	help
+	  This driver supports acceleration for compression and
+	  decompression with the Intel Analytics Accelerator (IAA)
+	  hardware using the cryptographic API.  If you choose 'M'
+	  here, the module will be called iaa_crypto.
+
+config CRYPTO_DEV_IAA_CRYPTO_STATS
+	bool "Enable Intel(R) IAA Compression Accelerator Statistics"
+	depends on CRYPTO_DEV_IAA_CRYPTO
+	default n
+	help
+	  Enable statistics for the IAA compression accelerator.
+	  These include per-device and per-workqueue statistics in
+	  addition to global driver statistics.
diff --git a/drivers/crypto/intel/iaa/Makefile b/drivers/crypto/intel/iaa/Makefile
new file mode 100644
index 000000000000..b64b208d2344
--- /dev/null
+++ b/drivers/crypto/intel/iaa/Makefile
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for IAA crypto device drivers
+#
+
+ccflags-y += -I $(srctree)/drivers/dma/idxd -DDEFAULT_SYMBOL_NAMESPACE=IDXD
+
+obj-$(CONFIG_CRYPTO_DEV_IAA_CRYPTO) := iaa_crypto.o
+
+iaa_crypto-y := iaa_crypto_main.o iaa_crypto_comp_fixed.o
+
+iaa_crypto-$(CONFIG_CRYPTO_DEV_IAA_CRYPTO_STATS) += iaa_crypto_stats.o
diff --git a/drivers/crypto/intel/iaa/iaa_crypto.h b/drivers/crypto/intel/iaa/iaa_crypto.h
new file mode 100644
index 000000000000..014420f7beb0
--- /dev/null
+++ b/drivers/crypto/intel/iaa/iaa_crypto.h
@@ -0,0 +1,173 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2021 Intel Corporation. All rights rsvd. */
+
+#ifndef __IAA_CRYPTO_H__
+#define __IAA_CRYPTO_H__
+
+#include <linux/crypto.h>
+#include <linux/idxd.h>
+#include <uapi/linux/idxd.h>
+
+#define IDXD_SUBDRIVER_NAME		"crypto"
+
+#define IAA_DECOMP_ENABLE		BIT(0)
+#define IAA_DECOMP_FLUSH_OUTPUT		BIT(1)
+#define IAA_DECOMP_CHECK_FOR_EOB	BIT(2)
+#define IAA_DECOMP_STOP_ON_EOB		BIT(3)
+#define IAA_DECOMP_SUPPRESS_OUTPUT	BIT(9)
+
+#define IAA_COMP_FLUSH_OUTPUT		BIT(1)
+#define IAA_COMP_APPEND_EOB		BIT(2)
+
+#define IAA_COMPLETION_TIMEOUT		1000000
+
+#define IAA_ANALYTICS_ERROR		0x0a
+#define IAA_ERROR_DECOMP_BUF_OVERFLOW	0x0b
+#define IAA_ERROR_COMP_BUF_OVERFLOW	0x19
+#define IAA_ERROR_WATCHDOG_EXPIRED	0x24
+
+#define IAA_COMP_MODES_MAX		2
+
+#define FIXED_HDR			0x2
+#define FIXED_HDR_SIZE			3
+
+#define IAA_COMP_FLAGS			(IAA_COMP_FLUSH_OUTPUT | \
+					 IAA_COMP_APPEND_EOB)
+
+#define IAA_DECOMP_FLAGS		(IAA_DECOMP_ENABLE |	   \
+					 IAA_DECOMP_FLUSH_OUTPUT | \
+					 IAA_DECOMP_CHECK_FOR_EOB | \
+					 IAA_DECOMP_STOP_ON_EOB)
+
+/* Representation of IAA workqueue */
+struct iaa_wq {
+	struct list_head	list;
+
+	struct idxd_wq		*wq;
+	int			ref;
+	bool			remove;
+
+	struct iaa_device	*iaa_device;
+
+	u64			comp_calls;
+	u64			comp_bytes;
+	u64			decomp_calls;
+	u64			decomp_bytes;
+};
+
+struct iaa_device_compression_mode {
+	const char			*name;
+
+	struct aecs_comp_table_record	*aecs_comp_table;
+	struct aecs_decomp_table_record	*aecs_decomp_table;
+
+	dma_addr_t			aecs_comp_table_dma_addr;
+	dma_addr_t			aecs_decomp_table_dma_addr;
+};
+
+/* Representation of IAA device with wqs, populated by probe */
+struct iaa_device {
+	struct list_head		list;
+	struct idxd_device		*idxd;
+
+	struct iaa_device_compression_mode	*compression_modes[IAA_COMP_MODES_MAX];
+
+	int				n_wq;
+	struct list_head		wqs;
+
+	u64				comp_calls;
+	u64				comp_bytes;
+	u64				decomp_calls;
+	u64				decomp_bytes;
+};
+
+struct wq_table_entry {
+	struct idxd_wq **wqs;
+	int	max_wqs;
+	int	n_wqs;
+	int	cur_wq;
+};
+
+#define IAA_AECS_ALIGN			32
+
+/*
+ * Analytics Engine Configuration and State (AECS) contains parameters and
+ * internal state of the analytics engine.
+ */
+struct aecs_comp_table_record {
+	u32 crc;
+	u32 xor_checksum;
+	u32 reserved0[5];
+	u32 num_output_accum_bits;
+	u8 output_accum[256];
+	u32 ll_sym[286];
+	u32 reserved1;
+	u32 reserved2;
+	u32 d_sym[30];
+	u32 reserved_padding[2];
+} __packed;
+
+/* AECS for decompress */
+struct aecs_decomp_table_record {
+	u32 crc;
+	u32 xor_checksum;
+	u32 low_filter_param;
+	u32 high_filter_param;
+	u32 output_mod_idx;
+	u32 drop_init_decomp_out_bytes;
+	u32 reserved[36];
+	u32 output_accum_data[2];
+	u32 out_bits_valid;
+	u32 bit_off_indexing;
+	u32 input_accum_data[64];
+	u8  size_qw[32];
+	u32 decomp_state[1220];
+} __packed;
+
+int iaa_aecs_init_fixed(void);
+void iaa_aecs_cleanup_fixed(void);
+
+typedef int (*iaa_dev_comp_init_fn_t) (struct iaa_device_compression_mode *mode);
+typedef int (*iaa_dev_comp_free_fn_t) (struct iaa_device_compression_mode *mode);
+
+struct iaa_compression_mode {
+	const char		*name;
+	u32			*ll_table;
+	int			ll_table_size;
+	u32			*d_table;
+	int			d_table_size;
+	u32			*header_table;
+	int			header_table_size;
+	u16			gen_decomp_table_flags;
+	iaa_dev_comp_init_fn_t	init;
+	iaa_dev_comp_free_fn_t	free;
+};
+
+int add_iaa_compression_mode(const char *name,
+			     const u32 *ll_table,
+			     int ll_table_size,
+			     const u32 *d_table,
+			     int d_table_size,
+			     const u8 *header_table,
+			     int header_table_size,
+			     u16 gen_decomp_table_flags,
+			     iaa_dev_comp_init_fn_t init,
+			     iaa_dev_comp_free_fn_t free);
+
+void remove_iaa_compression_mode(const char *name);
+
+enum iaa_mode {
+	IAA_MODE_FIXED,
+};
+
+struct iaa_compression_ctx {
+	enum iaa_mode	mode;
+	bool		verify_compress;
+	bool		async_mode;
+	bool		use_irq;
+};
+
+extern struct list_head iaa_devices;
+extern struct mutex iaa_devices_lock;
+
+#endif
diff --git a/drivers/crypto/intel/iaa/iaa_crypto_comp_fixed.c b/drivers/crypto/intel/iaa/iaa_crypto_comp_fixed.c
new file mode 100644
index 000000000000..45cf5d74f0fb
--- /dev/null
+++ b/drivers/crypto/intel/iaa/iaa_crypto_comp_fixed.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2021 Intel Corporation. All rights rsvd. */
+
+#include "idxd.h"
+#include "iaa_crypto.h"
+
+/*
+ * Fixed Huffman tables the IAA hardware requires to implement RFC-1951.
+ */
+static const u32 fixed_ll_sym[286] = {
+	0x40030, 0x40031, 0x40032, 0x40033, 0x40034, 0x40035, 0x40036, 0x40037,
+	0x40038, 0x40039, 0x4003A, 0x4003B, 0x4003C, 0x4003D, 0x4003E, 0x4003F,
+	0x40040, 0x40041, 0x40042, 0x40043, 0x40044, 0x40045, 0x40046, 0x40047,
+	0x40048, 0x40049, 0x4004A, 0x4004B, 0x4004C, 0x4004D, 0x4004E, 0x4004F,
+	0x40050, 0x40051, 0x40052, 0x40053, 0x40054, 0x40055, 0x40056, 0x40057,
+	0x40058, 0x40059, 0x4005A, 0x4005B, 0x4005C, 0x4005D, 0x4005E, 0x4005F,
+	0x40060, 0x40061, 0x40062, 0x40063, 0x40064, 0x40065, 0x40066, 0x40067,
+	0x40068, 0x40069, 0x4006A, 0x4006B, 0x4006C, 0x4006D, 0x4006E, 0x4006F,
+	0x40070, 0x40071, 0x40072, 0x40073, 0x40074, 0x40075, 0x40076, 0x40077,
+	0x40078, 0x40079, 0x4007A, 0x4007B, 0x4007C, 0x4007D, 0x4007E, 0x4007F,
+	0x40080, 0x40081, 0x40082, 0x40083, 0x40084, 0x40085, 0x40086, 0x40087,
+	0x40088, 0x40089, 0x4008A, 0x4008B, 0x4008C, 0x4008D, 0x4008E, 0x4008F,
+	0x40090, 0x40091, 0x40092, 0x40093, 0x40094, 0x40095, 0x40096, 0x40097,
+	0x40098, 0x40099, 0x4009A, 0x4009B, 0x4009C, 0x4009D, 0x4009E, 0x4009F,
+	0x400A0, 0x400A1, 0x400A2, 0x400A3, 0x400A4, 0x400A5, 0x400A6, 0x400A7,
+	0x400A8, 0x400A9, 0x400AA, 0x400AB, 0x400AC, 0x400AD, 0x400AE, 0x400AF,
+	0x400B0, 0x400B1, 0x400B2, 0x400B3, 0x400B4, 0x400B5, 0x400B6, 0x400B7,
+	0x400B8, 0x400B9, 0x400BA, 0x400BB, 0x400BC, 0x400BD, 0x400BE, 0x400BF,
+	0x48190, 0x48191, 0x48192, 0x48193, 0x48194, 0x48195, 0x48196, 0x48197,
+	0x48198, 0x48199, 0x4819A, 0x4819B, 0x4819C, 0x4819D, 0x4819E, 0x4819F,
+	0x481A0, 0x481A1, 0x481A2, 0x481A3, 0x481A4, 0x481A5, 0x481A6, 0x481A7,
+	0x481A8, 0x481A9, 0x481AA, 0x481AB, 0x481AC, 0x481AD, 0x481AE, 0x481AF,
+	0x481B0, 0x481B1, 0x481B2, 0x481B3, 0x481B4, 0x481B5, 0x481B6, 0x481B7,
+	0x481B8, 0x481B9, 0x481BA, 0x481BB, 0x481BC, 0x481BD, 0x481BE, 0x481BF,
+	0x481C0, 0x481C1, 0x481C2, 0x481C3, 0x481C4, 0x481C5, 0x481C6, 0x481C7,
+	0x481C8, 0x481C9, 0x481CA, 0x481CB, 0x481CC, 0x481CD, 0x481CE, 0x481CF,
+	0x481D0, 0x481D1, 0x481D2, 0x481D3, 0x481D4, 0x481D5, 0x481D6, 0x481D7,
+	0x481D8, 0x481D9, 0x481DA, 0x481DB, 0x481DC, 0x481DD, 0x481DE, 0x481DF,
+	0x481E0, 0x481E1, 0x481E2, 0x481E3, 0x481E4, 0x481E5, 0x481E6, 0x481E7,
+	0x481E8, 0x481E9, 0x481EA, 0x481EB, 0x481EC, 0x481ED, 0x481EE, 0x481EF,
+	0x481F0, 0x481F1, 0x481F2, 0x481F3, 0x481F4, 0x481F5, 0x481F6, 0x481F7,
+	0x481F8, 0x481F9, 0x481FA, 0x481FB, 0x481FC, 0x481FD, 0x481FE, 0x481FF,
+	0x38000, 0x38001, 0x38002, 0x38003, 0x38004, 0x38005, 0x38006, 0x38007,
+	0x38008, 0x38009, 0x3800A, 0x3800B, 0x3800C, 0x3800D, 0x3800E, 0x3800F,
+	0x38010, 0x38011, 0x38012, 0x38013, 0x38014, 0x38015, 0x38016, 0x38017,
+	0x400C0, 0x400C1, 0x400C2, 0x400C3, 0x400C4, 0x400C5
+};
+
+static const u32 fixed_d_sym[30] = {
+	0x28000, 0x28001, 0x28002, 0x28003, 0x28004, 0x28005, 0x28006, 0x28007,
+	0x28008, 0x28009, 0x2800A, 0x2800B, 0x2800C, 0x2800D, 0x2800E, 0x2800F,
+	0x28010, 0x28011, 0x28012, 0x28013, 0x28014, 0x28015, 0x28016, 0x28017,
+	0x28018, 0x28019, 0x2801A, 0x2801B, 0x2801C, 0x2801D
+};
+
+static int init_fixed_mode(struct iaa_device_compression_mode *mode)
+{
+	struct aecs_comp_table_record *comp_table = mode->aecs_comp_table;
+	u32 bfinal = 1;
+	u32 offset;
+
+	/* Configure aecs table using fixed Huffman table */
+	comp_table->crc = 0;
+	comp_table->xor_checksum = 0;
+	offset = comp_table->num_output_accum_bits / 8;
+	comp_table->output_accum[offset] = FIXED_HDR | bfinal;
+	comp_table->num_output_accum_bits = FIXED_HDR_SIZE;
+
+	return 0;
+}
+
+int iaa_aecs_init_fixed(void)
+{
+	int ret;
+
+	ret = add_iaa_compression_mode("fixed",
+				       fixed_ll_sym,
+				       sizeof(fixed_ll_sym),
+				       fixed_d_sym,
+				       sizeof(fixed_d_sym),
+				       NULL, 0, 0,
+				       init_fixed_mode, NULL);
+	if (!ret)
+		pr_debug("IAA fixed compression mode initialized\n");
+
+	return ret;
+}
+
+void iaa_aecs_cleanup_fixed(void)
+{
+	remove_iaa_compression_mode("fixed");
+}
diff --git a/drivers/crypto/intel/iaa/iaa_crypto_main.c b/drivers/crypto/intel/iaa/iaa_crypto_main.c
new file mode 100644
index 000000000000..dfd3baf0a8d8
--- /dev/null
+++ b/drivers/crypto/intel/iaa/iaa_crypto_main.c
@@ -0,0 +1,2193 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2021 Intel Corporation. All rights rsvd. */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/device.h>
+#include <linux/iommu.h>
+#include <uapi/linux/idxd.h>
+#include <linux/highmem.h>
+#include <linux/sched/smt.h>
+#include <crypto/internal/acompress.h>
+
+#include "idxd.h"
+#include "iaa_crypto.h"
+#include "iaa_crypto_stats.h"
+
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt)			"idxd: " IDXD_SUBDRIVER_NAME ": " fmt
+
+#define IAA_ALG_PRIORITY               300
+
+/* number of iaa instances probed */
+static unsigned int nr_iaa;
+static unsigned int nr_cpus;
+static unsigned int nr_nodes;
+static unsigned int nr_cpus_per_node;
+
+/* Number of physical cpus sharing each iaa instance */
+static unsigned int cpus_per_iaa;
+
+static struct crypto_comp *deflate_generic_tfm;
+
+/* Per-cpu lookup table for balanced wqs */
+static struct wq_table_entry __percpu *wq_table;
+
+static struct idxd_wq *wq_table_next_wq(int cpu)
+{
+	struct wq_table_entry *entry = per_cpu_ptr(wq_table, cpu);
+
+	if (++entry->cur_wq >= entry->n_wqs)
+		entry->cur_wq = 0;
+
+	if (!entry->wqs[entry->cur_wq])
+		return NULL;
+
+	pr_debug("%s: returning wq at idx %d (iaa wq %d.%d) from cpu %d\n", __func__,
+		 entry->cur_wq, entry->wqs[entry->cur_wq]->idxd->id,
+		 entry->wqs[entry->cur_wq]->id, cpu);
+
+	return entry->wqs[entry->cur_wq];
+}
+
+static void wq_table_add(int cpu, struct idxd_wq *wq)
+{
+	struct wq_table_entry *entry = per_cpu_ptr(wq_table, cpu);
+
+	if (WARN_ON(entry->n_wqs == entry->max_wqs))
+		return;
+
+	entry->wqs[entry->n_wqs++] = wq;
+
+	pr_debug("%s: added iaa wq %d.%d to idx %d of cpu %d\n", __func__,
+		 entry->wqs[entry->n_wqs - 1]->idxd->id,
+		 entry->wqs[entry->n_wqs - 1]->id, entry->n_wqs - 1, cpu);
+}
+
+static void wq_table_free_entry(int cpu)
+{
+	struct wq_table_entry *entry = per_cpu_ptr(wq_table, cpu);
+
+	kfree(entry->wqs);
+	memset(entry, 0, sizeof(*entry));
+}
+
+static void wq_table_clear_entry(int cpu)
+{
+	struct wq_table_entry *entry = per_cpu_ptr(wq_table, cpu);
+
+	entry->n_wqs = 0;
+	entry->cur_wq = 0;
+	memset(entry->wqs, 0, entry->max_wqs * sizeof(struct idxd_wq *));
+}
+
+LIST_HEAD(iaa_devices);
+DEFINE_MUTEX(iaa_devices_lock);
+
+/* If enabled, IAA hw crypto algos are registered, unavailable otherwise */
+static bool iaa_crypto_enabled;
+static bool iaa_crypto_registered;
+
+/* Verify results of IAA compress or not */
+static bool iaa_verify_compress = true;
+
+static ssize_t verify_compress_show(struct device_driver *driver, char *buf)
+{
+	return sprintf(buf, "%d\n", iaa_verify_compress);
+}
+
+static ssize_t verify_compress_store(struct device_driver *driver,
+				     const char *buf, size_t count)
+{
+	int ret = -EBUSY;
+
+	mutex_lock(&iaa_devices_lock);
+
+	if (iaa_crypto_enabled)
+		goto out;
+
+	ret = kstrtobool(buf, &iaa_verify_compress);
+	if (ret)
+		goto out;
+
+	ret = count;
+out:
+	mutex_unlock(&iaa_devices_lock);
+
+	return ret;
+}
+static DRIVER_ATTR_RW(verify_compress);
+
+/*
+ * The iaa crypto driver supports three 'sync' methods determining how
+ * compressions and decompressions are performed:
+ *
+ * - sync:      the compression or decompression completes before
+ *              returning.  This is the mode used by the async crypto
+ *              interface when the sync mode is set to 'sync' and by
+ *              the sync crypto interface regardless of setting.
+ *
+ * - async:     the compression or decompression is submitted and returns
+ *              immediately.  Completion interrupts are not used so
+ *              the caller is responsible for polling the descriptor
+ *              for completion.  This mode is applicable to only the
+ *              async crypto interface and is ignored for anything
+ *              else.
+ *
+ * - async_irq: the compression or decompression is submitted and
+ *              returns immediately.  Completion interrupts are
+ *              enabled so the caller can wait for the completion and
+ *              yield to other threads.  When the compression or
+ *              decompression completes, the completion is signaled
+ *              and the caller awakened.  This mode is applicable to
+ *              only the async crypto interface and is ignored for
+ *              anything else.
+ *
+ * These modes can be set using the iaa_crypto sync_mode driver
+ * attribute.
+ */
+
+/* Use async mode */
+static bool async_mode;
+/* Use interrupts */
+static bool use_irq;
+
+/**
+ * set_iaa_sync_mode - Set IAA sync mode
+ * @name: The name of the sync mode
+ *
+ * Make the IAA sync mode named @name the current sync mode used by
+ * compression/decompression.
+ */
+
+static int set_iaa_sync_mode(const char *name)
+{
+	int ret = 0;
+
+	if (sysfs_streq(name, "sync")) {
+		async_mode = false;
+		use_irq = false;
+	} else if (sysfs_streq(name, "async")) {
+		async_mode = true;
+		use_irq = false;
+	} else if (sysfs_streq(name, "async_irq")) {
+		async_mode = true;
+		use_irq = true;
+	} else {
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static ssize_t sync_mode_show(struct device_driver *driver, char *buf)
+{
+	int ret = 0;
+
+	if (!async_mode && !use_irq)
+		ret = sprintf(buf, "%s\n", "sync");
+	else if (async_mode && !use_irq)
+		ret = sprintf(buf, "%s\n", "async");
+	else if (async_mode && use_irq)
+		ret = sprintf(buf, "%s\n", "async_irq");
+
+	return ret;
+}
+
+static ssize_t sync_mode_store(struct device_driver *driver,
+			       const char *buf, size_t count)
+{
+	int ret = -EBUSY;
+
+	mutex_lock(&iaa_devices_lock);
+
+	if (iaa_crypto_enabled)
+		goto out;
+
+	ret = set_iaa_sync_mode(buf);
+	if (ret == 0)
+		ret = count;
+out:
+	mutex_unlock(&iaa_devices_lock);
+
+	return ret;
+}
+static DRIVER_ATTR_RW(sync_mode);
+
+static struct iaa_compression_mode *iaa_compression_modes[IAA_COMP_MODES_MAX];
+
+static int find_empty_iaa_compression_mode(void)
+{
+	int i = -EINVAL;
+
+	for (i = 0; i < IAA_COMP_MODES_MAX; i++) {
+		if (iaa_compression_modes[i])
+			continue;
+		break;
+	}
+
+	return i;
+}
+
+static struct iaa_compression_mode *find_iaa_compression_mode(const char *name, int *idx)
+{
+	struct iaa_compression_mode *mode;
+	int i;
+
+	for (i = 0; i < IAA_COMP_MODES_MAX; i++) {
+		mode = iaa_compression_modes[i];
+		if (!mode)
+			continue;
+
+		if (!strcmp(mode->name, name)) {
+			*idx = i;
+			return iaa_compression_modes[i];
+		}
+	}
+
+	return NULL;
+}
+
+static void free_iaa_compression_mode(struct iaa_compression_mode *mode)
+{
+	kfree(mode->name);
+	kfree(mode->ll_table);
+	kfree(mode->d_table);
+	kfree(mode->header_table);
+
+	kfree(mode);
+}
+
+/*
+ * IAA Compression modes are defined by an ll_table, a d_table, and an
+ * optional header_table.  These tables are typically generated and
+ * captured using statistics collected from running actual
+ * compress/decompress workloads.
+ *
+ * A module or other kernel code can add and remove compression modes
+ * with a given name using the exported @add_iaa_compression_mode()
+ * and @remove_iaa_compression_mode functions.
+ *
+ * When a new compression mode is added, the tables are saved in a
+ * global compression mode list.  When IAA devices are added, a
+ * per-IAA device dma mapping is created for each IAA device, for each
+ * compression mode.  These are the tables used to do the actual
+ * compression/deccompression and are unmapped if/when the devices are
+ * removed.  Currently, compression modes must be added before any
+ * device is added, and removed after all devices have been removed.
+ */
+
+/**
+ * remove_iaa_compression_mode - Remove an IAA compression mode
+ * @name: The name the compression mode will be known as
+ *
+ * Remove the IAA compression mode named @name.
+ */
+void remove_iaa_compression_mode(const char *name)
+{
+	struct iaa_compression_mode *mode;
+	int idx;
+
+	mutex_lock(&iaa_devices_lock);
+
+	if (!list_empty(&iaa_devices))
+		goto out;
+
+	mode = find_iaa_compression_mode(name, &idx);
+	if (mode) {
+		free_iaa_compression_mode(mode);
+		iaa_compression_modes[idx] = NULL;
+	}
+out:
+	mutex_unlock(&iaa_devices_lock);
+}
+EXPORT_SYMBOL_GPL(remove_iaa_compression_mode);
+
+/**
+ * add_iaa_compression_mode - Add an IAA compression mode
+ * @name: The name the compression mode will be known as
+ * @ll_table: The ll table
+ * @ll_table_size: The ll table size in bytes
+ * @d_table: The d table
+ * @d_table_size: The d table size in bytes
+ * @header_table: Optional header table
+ * @header_table_size: Optional header table size in bytes
+ * @gen_decomp_table_flags: Otional flags used to generate the decomp table
+ * @init: Optional callback function to init the compression mode data
+ * @free: Optional callback function to free the compression mode data
+ *
+ * Add a new IAA compression mode named @name.
+ *
+ * Returns 0 if successful, errcode otherwise.
+ */
+int add_iaa_compression_mode(const char *name,
+			     const u32 *ll_table,
+			     int ll_table_size,
+			     const u32 *d_table,
+			     int d_table_size,
+			     const u8 *header_table,
+			     int header_table_size,
+			     u16 gen_decomp_table_flags,
+			     iaa_dev_comp_init_fn_t init,
+			     iaa_dev_comp_free_fn_t free)
+{
+	struct iaa_compression_mode *mode;
+	int idx, ret = -ENOMEM;
+
+	mutex_lock(&iaa_devices_lock);
+
+	if (!list_empty(&iaa_devices)) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	mode = kzalloc(sizeof(*mode), GFP_KERNEL);
+	if (!mode)
+		goto out;
+
+	mode->name = kstrdup(name, GFP_KERNEL);
+	if (!mode->name)
+		goto free;
+
+	if (ll_table) {
+		mode->ll_table = kzalloc(ll_table_size, GFP_KERNEL);
+		if (!mode->ll_table)
+			goto free;
+		memcpy(mode->ll_table, ll_table, ll_table_size);
+		mode->ll_table_size = ll_table_size;
+	}
+
+	if (d_table) {
+		mode->d_table = kzalloc(d_table_size, GFP_KERNEL);
+		if (!mode->d_table)
+			goto free;
+		memcpy(mode->d_table, d_table, d_table_size);
+		mode->d_table_size = d_table_size;
+	}
+
+	if (header_table) {
+		mode->header_table = kzalloc(header_table_size, GFP_KERNEL);
+		if (!mode->header_table)
+			goto free;
+		memcpy(mode->header_table, header_table, header_table_size);
+		mode->header_table_size = header_table_size;
+	}
+
+	mode->gen_decomp_table_flags = gen_decomp_table_flags;
+
+	mode->init = init;
+	mode->free = free;
+
+	idx = find_empty_iaa_compression_mode();
+	if (idx < 0)
+		goto free;
+
+	pr_debug("IAA compression mode %s added at idx %d\n",
+		 mode->name, idx);
+
+	iaa_compression_modes[idx] = mode;
+
+	ret = 0;
+out:
+	mutex_unlock(&iaa_devices_lock);
+
+	return ret;
+free:
+	free_iaa_compression_mode(mode);
+	goto out;
+}
+EXPORT_SYMBOL_GPL(add_iaa_compression_mode);
+
+static struct iaa_device_compression_mode *
+get_iaa_device_compression_mode(struct iaa_device *iaa_device, int idx)
+{
+	return iaa_device->compression_modes[idx];
+}
+
+static void free_device_compression_mode(struct iaa_device *iaa_device,
+					 struct iaa_device_compression_mode *device_mode)
+{
+	size_t size = sizeof(struct aecs_comp_table_record) + IAA_AECS_ALIGN;
+	struct device *dev = &iaa_device->idxd->pdev->dev;
+
+	kfree(device_mode->name);
+
+	if (device_mode->aecs_comp_table)
+		dma_free_coherent(dev, size, device_mode->aecs_comp_table,
+				  device_mode->aecs_comp_table_dma_addr);
+	if (device_mode->aecs_decomp_table)
+		dma_free_coherent(dev, size, device_mode->aecs_decomp_table,
+				  device_mode->aecs_decomp_table_dma_addr);
+
+	kfree(device_mode);
+}
+
+#define IDXD_OP_FLAG_AECS_RW_TGLS       0x400000
+#define IAX_AECS_DEFAULT_FLAG (IDXD_OP_FLAG_CRAV | IDXD_OP_FLAG_RCR | IDXD_OP_FLAG_CC)
+#define IAX_AECS_COMPRESS_FLAG	(IAX_AECS_DEFAULT_FLAG | IDXD_OP_FLAG_RD_SRC2_AECS)
+#define IAX_AECS_DECOMPRESS_FLAG (IAX_AECS_DEFAULT_FLAG | IDXD_OP_FLAG_RD_SRC2_AECS)
+#define IAX_AECS_GEN_FLAG (IAX_AECS_DEFAULT_FLAG | \
+						IDXD_OP_FLAG_WR_SRC2_AECS_COMP | \
+						IDXD_OP_FLAG_AECS_RW_TGLS)
+
+static int check_completion(struct device *dev,
+			    struct iax_completion_record *comp,
+			    bool compress,
+			    bool only_once);
+
+static int decompress_header(struct iaa_device_compression_mode *device_mode,
+			     struct iaa_compression_mode *mode,
+			     struct idxd_wq *wq)
+{
+	dma_addr_t src_addr, src2_addr;
+	struct idxd_desc *idxd_desc;
+	struct iax_hw_desc *desc;
+	struct device *dev;
+	int ret = 0;
+
+	idxd_desc = idxd_alloc_desc(wq, IDXD_OP_BLOCK);
+	if (IS_ERR(idxd_desc))
+		return PTR_ERR(idxd_desc);
+
+	desc = idxd_desc->iax_hw;
+
+	dev = &wq->idxd->pdev->dev;
+
+	src_addr = dma_map_single(dev, (void *)mode->header_table,
+				  mode->header_table_size, DMA_TO_DEVICE);
+	dev_dbg(dev, "%s: mode->name %s, src_addr %llx, dev %p, src %p, slen %d\n",
+		__func__, mode->name, src_addr,	dev,
+		mode->header_table, mode->header_table_size);
+	if (unlikely(dma_mapping_error(dev, src_addr))) {
+		dev_dbg(dev, "dma_map_single err, exiting\n");
+		ret = -ENOMEM;
+		return ret;
+	}
+
+	desc->flags = IAX_AECS_GEN_FLAG;
+	desc->opcode = IAX_OPCODE_DECOMPRESS;
+
+	desc->src1_addr = (u64)src_addr;
+	desc->src1_size = mode->header_table_size;
+
+	src2_addr = device_mode->aecs_decomp_table_dma_addr;
+	desc->src2_addr = (u64)src2_addr;
+	desc->src2_size = 1088;
+	dev_dbg(dev, "%s: mode->name %s, src2_addr %llx, dev %p, src2_size %d\n",
+		__func__, mode->name, desc->src2_addr, dev, desc->src2_size);
+	desc->max_dst_size = 0; // suppressed output
+
+	desc->decompr_flags = mode->gen_decomp_table_flags;
+
+	desc->priv = 0;
+
+	desc->completion_addr = idxd_desc->compl_dma;
+
+	ret = idxd_submit_desc(wq, idxd_desc);
+	if (ret) {
+		pr_err("%s: submit_desc failed ret=0x%x\n", __func__, ret);
+		goto out;
+	}
+
+	ret = check_completion(dev, idxd_desc->iax_completion, false, false);
+	if (ret)
+		dev_dbg(dev, "%s: mode->name %s check_completion failed ret=%d\n",
+			__func__, mode->name, ret);
+	else
+		dev_dbg(dev, "%s: mode->name %s succeeded\n", __func__,
+			mode->name);
+out:
+	dma_unmap_single(dev, src_addr, 1088, DMA_TO_DEVICE);
+
+	return ret;
+}
+
+static int init_device_compression_mode(struct iaa_device *iaa_device,
+					struct iaa_compression_mode *mode,
+					int idx, struct idxd_wq *wq)
+{
+	size_t size = sizeof(struct aecs_comp_table_record) + IAA_AECS_ALIGN;
+	struct device *dev = &iaa_device->idxd->pdev->dev;
+	struct iaa_device_compression_mode *device_mode;
+	int ret = -ENOMEM;
+
+	device_mode = kzalloc(sizeof(*device_mode), GFP_KERNEL);
+	if (!device_mode)
+		return -ENOMEM;
+
+	device_mode->name = kstrdup(mode->name, GFP_KERNEL);
+	if (!device_mode->name)
+		goto free;
+
+	device_mode->aecs_comp_table = dma_alloc_coherent(dev, size,
+							  &device_mode->aecs_comp_table_dma_addr, GFP_KERNEL);
+	if (!device_mode->aecs_comp_table)
+		goto free;
+
+	device_mode->aecs_decomp_table = dma_alloc_coherent(dev, size,
+							    &device_mode->aecs_decomp_table_dma_addr, GFP_KERNEL);
+	if (!device_mode->aecs_decomp_table)
+		goto free;
+
+	/* Add Huffman table to aecs */
+	memset(device_mode->aecs_comp_table, 0, sizeof(*device_mode->aecs_comp_table));
+	memcpy(device_mode->aecs_comp_table->ll_sym, mode->ll_table, mode->ll_table_size);
+	memcpy(device_mode->aecs_comp_table->d_sym, mode->d_table, mode->d_table_size);
+
+	if (mode->header_table) {
+		ret = decompress_header(device_mode, mode, wq);
+		if (ret) {
+			pr_debug("iaa header decompression failed: ret=%d\n", ret);
+			goto free;
+		}
+	}
+
+	if (mode->init) {
+		ret = mode->init(device_mode);
+		if (ret)
+			goto free;
+	}
+
+	/* mode index should match iaa_compression_modes idx */
+	iaa_device->compression_modes[idx] = device_mode;
+
+	pr_debug("IAA %s compression mode initialized for iaa device %d\n",
+		 mode->name, iaa_device->idxd->id);
+
+	ret = 0;
+out:
+	return ret;
+free:
+	pr_debug("IAA %s compression mode initialization failed for iaa device %d\n",
+		 mode->name, iaa_device->idxd->id);
+
+	free_device_compression_mode(iaa_device, device_mode);
+	goto out;
+}
+
+static int init_device_compression_modes(struct iaa_device *iaa_device,
+					 struct idxd_wq *wq)
+{
+	struct iaa_compression_mode *mode;
+	int i, ret = 0;
+
+	for (i = 0; i < IAA_COMP_MODES_MAX; i++) {
+		mode = iaa_compression_modes[i];
+		if (!mode)
+			continue;
+
+		ret = init_device_compression_mode(iaa_device, mode, i, wq);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static void remove_device_compression_modes(struct iaa_device *iaa_device)
+{
+	struct iaa_device_compression_mode *device_mode;
+	int i;
+
+	for (i = 0; i < IAA_COMP_MODES_MAX; i++) {
+		device_mode = iaa_device->compression_modes[i];
+		if (!device_mode)
+			continue;
+
+		free_device_compression_mode(iaa_device, device_mode);
+		iaa_device->compression_modes[i] = NULL;
+		if (iaa_compression_modes[i]->free)
+			iaa_compression_modes[i]->free(device_mode);
+	}
+}
+
+static struct iaa_device *iaa_device_alloc(void)
+{
+	struct iaa_device *iaa_device;
+
+	iaa_device = kzalloc(sizeof(*iaa_device), GFP_KERNEL);
+	if (!iaa_device)
+		return NULL;
+
+	INIT_LIST_HEAD(&iaa_device->wqs);
+
+	return iaa_device;
+}
+
+static bool iaa_has_wq(struct iaa_device *iaa_device, struct idxd_wq *wq)
+{
+	struct iaa_wq *iaa_wq;
+
+	list_for_each_entry(iaa_wq, &iaa_device->wqs, list) {
+		if (iaa_wq->wq == wq)
+			return true;
+	}
+
+	return false;
+}
+
+static struct iaa_device *add_iaa_device(struct idxd_device *idxd)
+{
+	struct iaa_device *iaa_device;
+
+	iaa_device = iaa_device_alloc();
+	if (!iaa_device)
+		return NULL;
+
+	iaa_device->idxd = idxd;
+
+	list_add_tail(&iaa_device->list, &iaa_devices);
+
+	nr_iaa++;
+
+	return iaa_device;
+}
+
+static int init_iaa_device(struct iaa_device *iaa_device, struct iaa_wq *iaa_wq)
+{
+	int ret = 0;
+
+	ret = init_device_compression_modes(iaa_device, iaa_wq->wq);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+
+static void del_iaa_device(struct iaa_device *iaa_device)
+{
+	list_del(&iaa_device->list);
+
+	nr_iaa--;
+}
+
+static int add_iaa_wq(struct iaa_device *iaa_device, struct idxd_wq *wq,
+		      struct iaa_wq **new_wq)
+{
+	struct idxd_device *idxd = iaa_device->idxd;
+	struct pci_dev *pdev = idxd->pdev;
+	struct device *dev = &pdev->dev;
+	struct iaa_wq *iaa_wq;
+
+	iaa_wq = kzalloc(sizeof(*iaa_wq), GFP_KERNEL);
+	if (!iaa_wq)
+		return -ENOMEM;
+
+	iaa_wq->wq = wq;
+	iaa_wq->iaa_device = iaa_device;
+	idxd_wq_set_private(wq, iaa_wq);
+
+	list_add_tail(&iaa_wq->list, &iaa_device->wqs);
+
+	iaa_device->n_wq++;
+
+	if (new_wq)
+		*new_wq = iaa_wq;
+
+	dev_dbg(dev, "added wq %d to iaa device %d, n_wq %d\n",
+		wq->id, iaa_device->idxd->id, iaa_device->n_wq);
+
+	return 0;
+}
+
+static void del_iaa_wq(struct iaa_device *iaa_device, struct idxd_wq *wq)
+{
+	struct idxd_device *idxd = iaa_device->idxd;
+	struct pci_dev *pdev = idxd->pdev;
+	struct device *dev = &pdev->dev;
+	struct iaa_wq *iaa_wq;
+
+	list_for_each_entry(iaa_wq, &iaa_device->wqs, list) {
+		if (iaa_wq->wq == wq) {
+			list_del(&iaa_wq->list);
+			iaa_device->n_wq--;
+
+			dev_dbg(dev, "removed wq %d from iaa_device %d, n_wq %d, nr_iaa %d\n",
+				wq->id, iaa_device->idxd->id,
+				iaa_device->n_wq, nr_iaa);
+
+			if (iaa_device->n_wq == 0)
+				del_iaa_device(iaa_device);
+			break;
+		}
+	}
+}
+
+static void clear_wq_table(void)
+{
+	int cpu;
+
+	for (cpu = 0; cpu < nr_cpus; cpu++)
+		wq_table_clear_entry(cpu);
+
+	pr_debug("cleared wq table\n");
+}
+
+static void free_iaa_device(struct iaa_device *iaa_device)
+{
+	if (!iaa_device)
+		return;
+
+	remove_device_compression_modes(iaa_device);
+	kfree(iaa_device);
+}
+
+static void __free_iaa_wq(struct iaa_wq *iaa_wq)
+{
+	struct iaa_device *iaa_device;
+
+	if (!iaa_wq)
+		return;
+
+	iaa_device = iaa_wq->iaa_device;
+	if (iaa_device->n_wq == 0)
+		free_iaa_device(iaa_wq->iaa_device);
+}
+
+static void free_iaa_wq(struct iaa_wq *iaa_wq)
+{
+	struct idxd_wq *wq;
+
+	__free_iaa_wq(iaa_wq);
+
+	wq = iaa_wq->wq;
+
+	kfree(iaa_wq);
+	idxd_wq_set_private(wq, NULL);
+}
+
+static int iaa_wq_get(struct idxd_wq *wq)
+{
+	struct idxd_device *idxd = wq->idxd;
+	struct iaa_wq *iaa_wq;
+	int ret = 0;
+
+	spin_lock(&idxd->dev_lock);
+	iaa_wq = idxd_wq_get_private(wq);
+	if (iaa_wq && !iaa_wq->remove) {
+		iaa_wq->ref++;
+		idxd_wq_get(wq);
+	} else {
+		ret = -ENODEV;
+	}
+	spin_unlock(&idxd->dev_lock);
+
+	return ret;
+}
+
+static int iaa_wq_put(struct idxd_wq *wq)
+{
+	struct idxd_device *idxd = wq->idxd;
+	struct iaa_wq *iaa_wq;
+	bool free = false;
+	int ret = 0;
+
+	spin_lock(&idxd->dev_lock);
+	iaa_wq = idxd_wq_get_private(wq);
+	if (iaa_wq) {
+		iaa_wq->ref--;
+		if (iaa_wq->ref == 0 && iaa_wq->remove) {
+			idxd_wq_set_private(wq, NULL);
+			free = true;
+		}
+		idxd_wq_put(wq);
+	} else {
+		ret = -ENODEV;
+	}
+	spin_unlock(&idxd->dev_lock);
+	if (free) {
+		__free_iaa_wq(iaa_wq);
+		kfree(iaa_wq);
+	}
+
+	return ret;
+}
+
+static void free_wq_table(void)
+{
+	int cpu;
+
+	for (cpu = 0; cpu < nr_cpus; cpu++)
+		wq_table_free_entry(cpu);
+
+	free_percpu(wq_table);
+
+	pr_debug("freed wq table\n");
+}
+
+static int alloc_wq_table(int max_wqs)
+{
+	struct wq_table_entry *entry;
+	int cpu;
+
+	wq_table = alloc_percpu(struct wq_table_entry);
+	if (!wq_table)
+		return -ENOMEM;
+
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		entry = per_cpu_ptr(wq_table, cpu);
+		entry->wqs = kcalloc(max_wqs, sizeof(struct wq *), GFP_KERNEL);
+		if (!entry->wqs) {
+			free_wq_table();
+			return -ENOMEM;
+		}
+
+		entry->max_wqs = max_wqs;
+	}
+
+	pr_debug("initialized wq table\n");
+
+	return 0;
+}
+
+static int save_iaa_wq(struct idxd_wq *wq)
+{
+	struct iaa_device *iaa_device, *found = NULL;
+	struct idxd_device *idxd;
+	struct pci_dev *pdev;
+	struct device *dev;
+	int ret = 0;
+
+	list_for_each_entry(iaa_device, &iaa_devices, list) {
+		if (iaa_device->idxd == wq->idxd) {
+			idxd = iaa_device->idxd;
+			pdev = idxd->pdev;
+			dev = &pdev->dev;
+			/*
+			 * Check to see that we don't already have this wq.
+			 * Shouldn't happen but we don't control probing.
+			 */
+			if (iaa_has_wq(iaa_device, wq)) {
+				dev_dbg(dev, "same wq probed multiple times for iaa_device %p\n",
+					iaa_device);
+				goto out;
+			}
+
+			found = iaa_device;
+
+			ret = add_iaa_wq(iaa_device, wq, NULL);
+			if (ret)
+				goto out;
+
+			break;
+		}
+	}
+
+	if (!found) {
+		struct iaa_device *new_device;
+		struct iaa_wq *new_wq;
+
+		new_device = add_iaa_device(wq->idxd);
+		if (!new_device) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		ret = add_iaa_wq(new_device, wq, &new_wq);
+		if (ret) {
+			del_iaa_device(new_device);
+			free_iaa_device(new_device);
+			goto out;
+		}
+
+		ret = init_iaa_device(new_device, new_wq);
+		if (ret) {
+			del_iaa_wq(new_device, new_wq->wq);
+			del_iaa_device(new_device);
+			free_iaa_wq(new_wq);
+			goto out;
+		}
+	}
+
+	if (WARN_ON(nr_iaa == 0))
+		return -EINVAL;
+
+	cpus_per_iaa = (nr_nodes * nr_cpus_per_node) / nr_iaa;
+out:
+	return 0;
+}
+
+static void remove_iaa_wq(struct idxd_wq *wq)
+{
+	struct iaa_device *iaa_device;
+
+	list_for_each_entry(iaa_device, &iaa_devices, list) {
+		if (iaa_has_wq(iaa_device, wq)) {
+			del_iaa_wq(iaa_device, wq);
+			break;
+		}
+	}
+
+	if (nr_iaa)
+		cpus_per_iaa = (nr_nodes * nr_cpus_per_node) / nr_iaa;
+	else
+		cpus_per_iaa = 0;
+}
+
+static int wq_table_add_wqs(int iaa, int cpu)
+{
+	struct iaa_device *iaa_device, *found_device = NULL;
+	int ret = 0, cur_iaa = 0, n_wqs_added = 0;
+	struct idxd_device *idxd;
+	struct iaa_wq *iaa_wq;
+	struct pci_dev *pdev;
+	struct device *dev;
+
+	list_for_each_entry(iaa_device, &iaa_devices, list) {
+		idxd = iaa_device->idxd;
+		pdev = idxd->pdev;
+		dev = &pdev->dev;
+
+		if (cur_iaa != iaa) {
+			cur_iaa++;
+			continue;
+		}
+
+		found_device = iaa_device;
+		dev_dbg(dev, "getting wq from iaa_device %d, cur_iaa %d\n",
+			found_device->idxd->id, cur_iaa);
+		break;
+	}
+
+	if (!found_device) {
+		found_device = list_first_entry_or_null(&iaa_devices,
+							struct iaa_device, list);
+		if (!found_device) {
+			pr_debug("couldn't find any iaa devices with wqs!\n");
+			ret = -EINVAL;
+			goto out;
+		}
+		cur_iaa = 0;
+
+		idxd = found_device->idxd;
+		pdev = idxd->pdev;
+		dev = &pdev->dev;
+		dev_dbg(dev, "getting wq from only iaa_device %d, cur_iaa %d\n",
+			found_device->idxd->id, cur_iaa);
+	}
+
+	list_for_each_entry(iaa_wq, &found_device->wqs, list) {
+		wq_table_add(cpu, iaa_wq->wq);
+		pr_debug("rebalance: added wq for cpu=%d: iaa wq %d.%d\n",
+			 cpu, iaa_wq->wq->idxd->id, iaa_wq->wq->id);
+		n_wqs_added++;
+	}
+
+	if (!n_wqs_added) {
+		pr_debug("couldn't find any iaa wqs!\n");
+		ret = -EINVAL;
+		goto out;
+	}
+out:
+	return ret;
+}
+
+/*
+ * Rebalance the wq table so that given a cpu, it's easy to find the
+ * closest IAA instance.  The idea is to try to choose the most
+ * appropriate IAA instance for a caller and spread available
+ * workqueues around to clients.
+ */
+static void rebalance_wq_table(void)
+{
+	const struct cpumask *node_cpus;
+	int node, cpu, iaa = -1;
+
+	if (nr_iaa == 0)
+		return;
+
+	pr_debug("rebalance: nr_nodes=%d, nr_cpus %d, nr_iaa %d, cpus_per_iaa %d\n",
+		 nr_nodes, nr_cpus, nr_iaa, cpus_per_iaa);
+
+	clear_wq_table();
+
+	if (nr_iaa == 1) {
+		for (cpu = 0; cpu < nr_cpus; cpu++) {
+			if (WARN_ON(wq_table_add_wqs(0, cpu))) {
+				pr_debug("could not add any wqs for iaa 0 to cpu %d!\n", cpu);
+				return;
+			}
+		}
+
+		return;
+	}
+
+	for_each_node_with_cpus(node) {
+		node_cpus = cpumask_of_node(node);
+
+		for (cpu = 0; cpu < nr_cpus_per_node; cpu++) {
+			int node_cpu = cpumask_nth(cpu, node_cpus);
+
+			if (WARN_ON(node_cpu >= nr_cpu_ids)) {
+				pr_debug("node_cpu %d doesn't exist!\n", node_cpu);
+				return;
+			}
+
+			if ((cpu % cpus_per_iaa) == 0)
+				iaa++;
+
+			if (WARN_ON(wq_table_add_wqs(iaa, node_cpu))) {
+				pr_debug("could not add any wqs for iaa %d to cpu %d!\n", iaa, cpu);
+				return;
+			}
+		}
+	}
+}
+
+static inline int check_completion(struct device *dev,
+				   struct iax_completion_record *comp,
+				   bool compress,
+				   bool only_once)
+{
+	char *op_str = compress ? "compress" : "decompress";
+	int ret = 0;
+
+	while (!comp->status) {
+		if (only_once)
+			return -EAGAIN;
+		cpu_relax();
+	}
+
+	if (comp->status != IAX_COMP_SUCCESS) {
+		if (comp->status == IAA_ERROR_WATCHDOG_EXPIRED) {
+			ret = -ETIMEDOUT;
+			dev_dbg(dev, "%s timed out, size=0x%x\n",
+				op_str, comp->output_size);
+			update_completion_timeout_errs();
+			goto out;
+		}
+
+		if (comp->status == IAA_ANALYTICS_ERROR &&
+		    comp->error_code == IAA_ERROR_COMP_BUF_OVERFLOW && compress) {
+			ret = -E2BIG;
+			dev_dbg(dev, "compressed > uncompressed size,"
+				" not compressing, size=0x%x\n",
+				comp->output_size);
+			update_completion_comp_buf_overflow_errs();
+			goto out;
+		}
+
+		if (comp->status == IAA_ERROR_DECOMP_BUF_OVERFLOW) {
+			ret = -EOVERFLOW;
+			goto out;
+		}
+
+		ret = -EINVAL;
+		dev_dbg(dev, "iaa %s status=0x%x, error=0x%x, size=0x%x\n",
+			op_str, comp->status, comp->error_code, comp->output_size);
+		print_hex_dump(KERN_INFO, "cmp-rec: ", DUMP_PREFIX_OFFSET, 8, 1, comp, 64, 0);
+		update_completion_einval_errs();
+
+		goto out;
+	}
+out:
+	return ret;
+}
+
+static int deflate_generic_decompress(struct acomp_req *req)
+{
+	void *src, *dst;
+	int ret;
+
+	src = kmap_local_page(sg_page(req->src)) + req->src->offset;
+	dst = kmap_local_page(sg_page(req->dst)) + req->dst->offset;
+
+	ret = crypto_comp_decompress(deflate_generic_tfm,
+				     src, req->slen, dst, &req->dlen);
+
+	kunmap_local(src);
+	kunmap_local(dst);
+
+	update_total_sw_decomp_calls();
+
+	return ret;
+}
+
+static int iaa_remap_for_verify(struct device *dev, struct iaa_wq *iaa_wq,
+				struct acomp_req *req,
+				dma_addr_t *src_addr, dma_addr_t *dst_addr);
+
+static int iaa_compress_verify(struct crypto_tfm *tfm, struct acomp_req *req,
+			       struct idxd_wq *wq,
+			       dma_addr_t src_addr, unsigned int slen,
+			       dma_addr_t dst_addr, unsigned int *dlen,
+			       u32 compression_crc);
+
+static void iaa_desc_complete(struct idxd_desc *idxd_desc,
+			      enum idxd_complete_type comp_type,
+			      bool free_desc, void *__ctx,
+			      u32 *status)
+{
+	struct iaa_device_compression_mode *active_compression_mode;
+	struct iaa_compression_ctx *compression_ctx;
+	struct crypto_ctx *ctx = __ctx;
+	struct iaa_device *iaa_device;
+	struct idxd_device *idxd;
+	struct iaa_wq *iaa_wq;
+	struct pci_dev *pdev;
+	struct device *dev;
+	int ret, err = 0;
+
+	compression_ctx = crypto_tfm_ctx(ctx->tfm);
+
+	iaa_wq = idxd_wq_get_private(idxd_desc->wq);
+	iaa_device = iaa_wq->iaa_device;
+	idxd = iaa_device->idxd;
+	pdev = idxd->pdev;
+	dev = &pdev->dev;
+
+	active_compression_mode = get_iaa_device_compression_mode(iaa_device,
+								  compression_ctx->mode);
+	dev_dbg(dev, "%s: compression mode %s,"
+		" ctx->src_addr %llx, ctx->dst_addr %llx\n", __func__,
+		active_compression_mode->name,
+		ctx->src_addr, ctx->dst_addr);
+
+	ret = check_completion(dev, idxd_desc->iax_completion,
+			       ctx->compress, false);
+	if (ret) {
+		dev_dbg(dev, "%s: check_completion failed ret=%d\n", __func__, ret);
+		if (!ctx->compress &&
+		    idxd_desc->iax_completion->status == IAA_ANALYTICS_ERROR) {
+			pr_warn("%s: falling back to deflate-generic decompress, "
+				"analytics error code %x\n", __func__,
+				idxd_desc->iax_completion->error_code);
+			ret = deflate_generic_decompress(ctx->req);
+			if (ret) {
+				dev_dbg(dev, "%s: deflate-generic failed ret=%d\n",
+					__func__, ret);
+				err = -EIO;
+				goto err;
+			}
+		} else {
+			err = -EIO;
+			goto err;
+		}
+	} else {
+		ctx->req->dlen = idxd_desc->iax_completion->output_size;
+	}
+
+	/* Update stats */
+	if (ctx->compress) {
+		update_total_comp_bytes_out(ctx->req->dlen);
+		update_wq_comp_bytes(iaa_wq->wq, ctx->req->dlen);
+	} else {
+		update_total_decomp_bytes_in(ctx->req->dlen);
+		update_wq_decomp_bytes(iaa_wq->wq, ctx->req->dlen);
+	}
+
+	if (ctx->compress && compression_ctx->verify_compress) {
+		dma_addr_t src_addr, dst_addr;
+		u32 compression_crc;
+
+		compression_crc = idxd_desc->iax_completion->crc;
+
+		ret = iaa_remap_for_verify(dev, iaa_wq, ctx->req, &src_addr, &dst_addr);
+		if (ret) {
+			dev_dbg(dev, "%s: compress verify remap failed ret=%d\n", __func__, ret);
+			err = -EIO;
+			goto out;
+		}
+
+		ret = iaa_compress_verify(ctx->tfm, ctx->req, iaa_wq->wq, src_addr,
+					  ctx->req->slen, dst_addr, &ctx->req->dlen,
+					  compression_crc);
+		if (ret) {
+			dev_dbg(dev, "%s: compress verify failed ret=%d\n", __func__, ret);
+			err = -EIO;
+		}
+
+		dma_unmap_sg(dev, ctx->req->dst, sg_nents(ctx->req->dst), DMA_TO_DEVICE);
+		dma_unmap_sg(dev, ctx->req->src, sg_nents(ctx->req->src), DMA_FROM_DEVICE);
+
+		goto out;
+	}
+err:
+	dma_unmap_sg(dev, ctx->req->dst, sg_nents(ctx->req->dst), DMA_FROM_DEVICE);
+	dma_unmap_sg(dev, ctx->req->src, sg_nents(ctx->req->src), DMA_TO_DEVICE);
+out:
+	if (ret != 0)
+		dev_dbg(dev, "asynchronous compress failed ret=%d\n", ret);
+
+	if (ctx->req->base.complete)
+		acomp_request_complete(ctx->req, err);
+
+	if (free_desc)
+		idxd_free_desc(idxd_desc->wq, idxd_desc);
+	iaa_wq_put(idxd_desc->wq);
+}
+
+static int iaa_compress(struct crypto_tfm *tfm,	struct acomp_req *req,
+			struct idxd_wq *wq,
+			dma_addr_t src_addr, unsigned int slen,
+			dma_addr_t dst_addr, unsigned int *dlen,
+			u32 *compression_crc,
+			bool disable_async)
+{
+	struct iaa_device_compression_mode *active_compression_mode;
+	struct iaa_compression_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct iaa_device *iaa_device;
+	struct idxd_desc *idxd_desc;
+	struct iax_hw_desc *desc;
+	struct idxd_device *idxd;
+	struct iaa_wq *iaa_wq;
+	struct pci_dev *pdev;
+	struct device *dev;
+	int ret = 0;
+
+	iaa_wq = idxd_wq_get_private(wq);
+	iaa_device = iaa_wq->iaa_device;
+	idxd = iaa_device->idxd;
+	pdev = idxd->pdev;
+	dev = &pdev->dev;
+
+	active_compression_mode = get_iaa_device_compression_mode(iaa_device, ctx->mode);
+
+	idxd_desc = idxd_alloc_desc(wq, IDXD_OP_BLOCK);
+	if (IS_ERR(idxd_desc)) {
+		dev_dbg(dev, "idxd descriptor allocation failed\n");
+		dev_dbg(dev, "iaa compress failed: ret=%ld\n", PTR_ERR(idxd_desc));
+		return PTR_ERR(idxd_desc);
+	}
+	desc = idxd_desc->iax_hw;
+
+	desc->flags = IDXD_OP_FLAG_CRAV | IDXD_OP_FLAG_RCR |
+		IDXD_OP_FLAG_RD_SRC2_AECS | IDXD_OP_FLAG_CC;
+	desc->opcode = IAX_OPCODE_COMPRESS;
+	desc->compr_flags = IAA_COMP_FLAGS;
+	desc->priv = 0;
+
+	desc->src1_addr = (u64)src_addr;
+	desc->src1_size = slen;
+	desc->dst_addr = (u64)dst_addr;
+	desc->max_dst_size = *dlen;
+	desc->src2_addr = active_compression_mode->aecs_comp_table_dma_addr;
+	desc->src2_size = sizeof(struct aecs_comp_table_record);
+	desc->completion_addr = idxd_desc->compl_dma;
+
+	if (ctx->use_irq && !disable_async) {
+		desc->flags |= IDXD_OP_FLAG_RCI;
+
+		idxd_desc->crypto.req = req;
+		idxd_desc->crypto.tfm = tfm;
+		idxd_desc->crypto.src_addr = src_addr;
+		idxd_desc->crypto.dst_addr = dst_addr;
+		idxd_desc->crypto.compress = true;
+
+		dev_dbg(dev, "%s use_async_irq: compression mode %s,"
+			" src_addr %llx, dst_addr %llx\n", __func__,
+			active_compression_mode->name,
+			src_addr, dst_addr);
+	} else if (ctx->async_mode && !disable_async)
+		req->base.data = idxd_desc;
+
+	dev_dbg(dev, "%s: compression mode %s,"
+		" desc->src1_addr %llx, desc->src1_size %d,"
+		" desc->dst_addr %llx, desc->max_dst_size %d,"
+		" desc->src2_addr %llx, desc->src2_size %d\n", __func__,
+		active_compression_mode->name,
+		desc->src1_addr, desc->src1_size, desc->dst_addr,
+		desc->max_dst_size, desc->src2_addr, desc->src2_size);
+
+	ret = idxd_submit_desc(wq, idxd_desc);
+	if (ret) {
+		dev_dbg(dev, "submit_desc failed ret=%d\n", ret);
+		goto err;
+	}
+
+	/* Update stats */
+	update_total_comp_calls();
+	update_wq_comp_calls(wq);
+
+	if (ctx->async_mode && !disable_async) {
+		ret = -EINPROGRESS;
+		dev_dbg(dev, "%s: returning -EINPROGRESS\n", __func__);
+		goto out;
+	}
+
+	ret = check_completion(dev, idxd_desc->iax_completion, true, false);
+	if (ret) {
+		dev_dbg(dev, "check_completion failed ret=%d\n", ret);
+		goto err;
+	}
+
+	*dlen = idxd_desc->iax_completion->output_size;
+
+	/* Update stats */
+	update_total_comp_bytes_out(*dlen);
+	update_wq_comp_bytes(wq, *dlen);
+
+	*compression_crc = idxd_desc->iax_completion->crc;
+
+	if (!ctx->async_mode)
+		idxd_free_desc(wq, idxd_desc);
+out:
+	return ret;
+err:
+	idxd_free_desc(wq, idxd_desc);
+	dev_dbg(dev, "iaa compress failed: ret=%d\n", ret);
+
+	goto out;
+}
+
+static int iaa_remap_for_verify(struct device *dev, struct iaa_wq *iaa_wq,
+				struct acomp_req *req,
+				dma_addr_t *src_addr, dma_addr_t *dst_addr)
+{
+	int ret = 0;
+	int nr_sgs;
+
+	dma_unmap_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
+	dma_unmap_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
+
+	nr_sgs = dma_map_sg(dev, req->src, sg_nents(req->src), DMA_FROM_DEVICE);
+	if (nr_sgs <= 0 || nr_sgs > 1) {
+		dev_dbg(dev, "verify: couldn't map src sg for iaa device %d,"
+			" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
+			iaa_wq->wq->id, ret);
+		ret = -EIO;
+		goto out;
+	}
+	*src_addr = sg_dma_address(req->src);
+	dev_dbg(dev, "verify: dma_map_sg, src_addr %llx, nr_sgs %d, req->src %p,"
+		" req->slen %d, sg_dma_len(sg) %d\n", *src_addr, nr_sgs,
+		req->src, req->slen, sg_dma_len(req->src));
+
+	nr_sgs = dma_map_sg(dev, req->dst, sg_nents(req->dst), DMA_TO_DEVICE);
+	if (nr_sgs <= 0 || nr_sgs > 1) {
+		dev_dbg(dev, "verify: couldn't map dst sg for iaa device %d,"
+			" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
+			iaa_wq->wq->id, ret);
+		ret = -EIO;
+		dma_unmap_sg(dev, req->src, sg_nents(req->src), DMA_FROM_DEVICE);
+		goto out;
+	}
+	*dst_addr = sg_dma_address(req->dst);
+	dev_dbg(dev, "verify: dma_map_sg, dst_addr %llx, nr_sgs %d, req->dst %p,"
+		" req->dlen %d, sg_dma_len(sg) %d\n", *dst_addr, nr_sgs,
+		req->dst, req->dlen, sg_dma_len(req->dst));
+out:
+	return ret;
+}
+
+static int iaa_compress_verify(struct crypto_tfm *tfm, struct acomp_req *req,
+			       struct idxd_wq *wq,
+			       dma_addr_t src_addr, unsigned int slen,
+			       dma_addr_t dst_addr, unsigned int *dlen,
+			       u32 compression_crc)
+{
+	struct iaa_device_compression_mode *active_compression_mode;
+	struct iaa_compression_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct iaa_device *iaa_device;
+	struct idxd_desc *idxd_desc;
+	struct iax_hw_desc *desc;
+	struct idxd_device *idxd;
+	struct iaa_wq *iaa_wq;
+	struct pci_dev *pdev;
+	struct device *dev;
+	int ret = 0;
+
+	iaa_wq = idxd_wq_get_private(wq);
+	iaa_device = iaa_wq->iaa_device;
+	idxd = iaa_device->idxd;
+	pdev = idxd->pdev;
+	dev = &pdev->dev;
+
+	active_compression_mode = get_iaa_device_compression_mode(iaa_device, ctx->mode);
+
+	idxd_desc = idxd_alloc_desc(wq, IDXD_OP_BLOCK);
+	if (IS_ERR(idxd_desc)) {
+		dev_dbg(dev, "idxd descriptor allocation failed\n");
+		dev_dbg(dev, "iaa compress failed: ret=%ld\n",
+			PTR_ERR(idxd_desc));
+		return PTR_ERR(idxd_desc);
+	}
+	desc = idxd_desc->iax_hw;
+
+	/* Verify (optional) - decompress and check crc, suppress dest write */
+
+	desc->flags = IDXD_OP_FLAG_CRAV | IDXD_OP_FLAG_RCR | IDXD_OP_FLAG_CC;
+	desc->opcode = IAX_OPCODE_DECOMPRESS;
+	desc->decompr_flags = IAA_DECOMP_FLAGS | IAA_DECOMP_SUPPRESS_OUTPUT;
+	desc->priv = 0;
+
+	desc->src1_addr = (u64)dst_addr;
+	desc->src1_size = *dlen;
+	desc->dst_addr = (u64)src_addr;
+	desc->max_dst_size = slen;
+	desc->completion_addr = idxd_desc->compl_dma;
+
+	dev_dbg(dev, "(verify) compression mode %s,"
+		" desc->src1_addr %llx, desc->src1_size %d,"
+		" desc->dst_addr %llx, desc->max_dst_size %d,"
+		" desc->src2_addr %llx, desc->src2_size %d\n",
+		active_compression_mode->name,
+		desc->src1_addr, desc->src1_size, desc->dst_addr,
+		desc->max_dst_size, desc->src2_addr, desc->src2_size);
+
+	ret = idxd_submit_desc(wq, idxd_desc);
+	if (ret) {
+		dev_dbg(dev, "submit_desc (verify) failed ret=%d\n", ret);
+		goto err;
+	}
+
+	ret = check_completion(dev, idxd_desc->iax_completion, false, false);
+	if (ret) {
+		dev_dbg(dev, "(verify) check_completion failed ret=%d\n", ret);
+		goto err;
+	}
+
+	if (compression_crc != idxd_desc->iax_completion->crc) {
+		ret = -EINVAL;
+		dev_dbg(dev, "(verify) iaa comp/decomp crc mismatch:"
+			" comp=0x%x, decomp=0x%x\n", compression_crc,
+			idxd_desc->iax_completion->crc);
+		print_hex_dump(KERN_INFO, "cmp-rec: ", DUMP_PREFIX_OFFSET,
+			       8, 1, idxd_desc->iax_completion, 64, 0);
+		goto err;
+	}
+
+	idxd_free_desc(wq, idxd_desc);
+out:
+	return ret;
+err:
+	idxd_free_desc(wq, idxd_desc);
+	dev_dbg(dev, "iaa compress failed: ret=%d\n", ret);
+
+	goto out;
+}
+
+static int iaa_decompress(struct crypto_tfm *tfm, struct acomp_req *req,
+			  struct idxd_wq *wq,
+			  dma_addr_t src_addr, unsigned int slen,
+			  dma_addr_t dst_addr, unsigned int *dlen,
+			  bool disable_async)
+{
+	struct iaa_device_compression_mode *active_compression_mode;
+	struct iaa_compression_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct iaa_device *iaa_device;
+	struct idxd_desc *idxd_desc;
+	struct iax_hw_desc *desc;
+	struct idxd_device *idxd;
+	struct iaa_wq *iaa_wq;
+	struct pci_dev *pdev;
+	struct device *dev;
+	int ret = 0;
+
+	iaa_wq = idxd_wq_get_private(wq);
+	iaa_device = iaa_wq->iaa_device;
+	idxd = iaa_device->idxd;
+	pdev = idxd->pdev;
+	dev = &pdev->dev;
+
+	active_compression_mode = get_iaa_device_compression_mode(iaa_device, ctx->mode);
+
+	idxd_desc = idxd_alloc_desc(wq, IDXD_OP_BLOCK);
+	if (IS_ERR(idxd_desc)) {
+		dev_dbg(dev, "idxd descriptor allocation failed\n");
+		dev_dbg(dev, "iaa decompress failed: ret=%ld\n",
+			PTR_ERR(idxd_desc));
+		return PTR_ERR(idxd_desc);
+	}
+	desc = idxd_desc->iax_hw;
+
+	desc->flags = IDXD_OP_FLAG_CRAV | IDXD_OP_FLAG_RCR | IDXD_OP_FLAG_CC;
+	desc->opcode = IAX_OPCODE_DECOMPRESS;
+	desc->max_dst_size = PAGE_SIZE;
+	desc->decompr_flags = IAA_DECOMP_FLAGS;
+	desc->priv = 0;
+
+	desc->src1_addr = (u64)src_addr;
+	desc->dst_addr = (u64)dst_addr;
+	desc->max_dst_size = *dlen;
+	desc->src1_size = slen;
+	desc->completion_addr = idxd_desc->compl_dma;
+
+	if (ctx->use_irq && !disable_async) {
+		desc->flags |= IDXD_OP_FLAG_RCI;
+
+		idxd_desc->crypto.req = req;
+		idxd_desc->crypto.tfm = tfm;
+		idxd_desc->crypto.src_addr = src_addr;
+		idxd_desc->crypto.dst_addr = dst_addr;
+		idxd_desc->crypto.compress = false;
+
+		dev_dbg(dev, "%s: use_async_irq compression mode %s,"
+			" src_addr %llx, dst_addr %llx\n", __func__,
+			active_compression_mode->name,
+			src_addr, dst_addr);
+	} else if (ctx->async_mode && !disable_async)
+		req->base.data = idxd_desc;
+
+	dev_dbg(dev, "%s: decompression mode %s,"
+		" desc->src1_addr %llx, desc->src1_size %d,"
+		" desc->dst_addr %llx, desc->max_dst_size %d,"
+		" desc->src2_addr %llx, desc->src2_size %d\n", __func__,
+		active_compression_mode->name,
+		desc->src1_addr, desc->src1_size, desc->dst_addr,
+		desc->max_dst_size, desc->src2_addr, desc->src2_size);
+
+	ret = idxd_submit_desc(wq, idxd_desc);
+	if (ret) {
+		dev_dbg(dev, "submit_desc failed ret=%d\n", ret);
+		goto err;
+	}
+
+	/* Update stats */
+	update_total_decomp_calls();
+	update_wq_decomp_calls(wq);
+
+	if (ctx->async_mode && !disable_async) {
+		ret = -EINPROGRESS;
+		dev_dbg(dev, "%s: returning -EINPROGRESS\n", __func__);
+		goto out;
+	}
+
+	ret = check_completion(dev, idxd_desc->iax_completion, false, false);
+	if (ret) {
+		dev_dbg(dev, "%s: check_completion failed ret=%d\n", __func__, ret);
+		if (idxd_desc->iax_completion->status == IAA_ANALYTICS_ERROR) {
+			pr_warn("%s: falling back to deflate-generic decompress, "
+				"analytics error code %x\n", __func__,
+				idxd_desc->iax_completion->error_code);
+			ret = deflate_generic_decompress(req);
+			if (ret) {
+				dev_dbg(dev, "%s: deflate-generic failed ret=%d\n",
+					__func__, ret);
+				goto err;
+			}
+		} else {
+			goto err;
+		}
+	} else {
+		req->dlen = idxd_desc->iax_completion->output_size;
+	}
+
+	*dlen = req->dlen;
+
+	if (!ctx->async_mode)
+		idxd_free_desc(wq, idxd_desc);
+
+	/* Update stats */
+	update_total_decomp_bytes_in(slen);
+	update_wq_decomp_bytes(wq, slen);
+out:
+	return ret;
+err:
+	idxd_free_desc(wq, idxd_desc);
+	dev_dbg(dev, "iaa decompress failed: ret=%d\n", ret);
+
+	goto out;
+}
+
+static int iaa_comp_acompress(struct acomp_req *req)
+{
+	struct iaa_compression_ctx *compression_ctx;
+	struct crypto_tfm *tfm = req->base.tfm;
+	dma_addr_t src_addr, dst_addr;
+	bool disable_async = false;
+	int nr_sgs, cpu, ret = 0;
+	struct iaa_wq *iaa_wq;
+	u32 compression_crc;
+	struct idxd_wq *wq;
+	struct device *dev;
+	int order = -1;
+
+	compression_ctx = crypto_tfm_ctx(tfm);
+
+	if (!iaa_crypto_enabled) {
+		pr_debug("iaa_crypto disabled, not compressing\n");
+		return -ENODEV;
+	}
+
+	if (!req->src || !req->slen) {
+		pr_debug("invalid src, not compressing\n");
+		return -EINVAL;
+	}
+
+	cpu = get_cpu();
+	wq = wq_table_next_wq(cpu);
+	put_cpu();
+	if (!wq) {
+		pr_debug("no wq configured for cpu=%d\n", cpu);
+		return -ENODEV;
+	}
+
+	ret = iaa_wq_get(wq);
+	if (ret) {
+		pr_debug("no wq available for cpu=%d\n", cpu);
+		return -ENODEV;
+	}
+
+	iaa_wq = idxd_wq_get_private(wq);
+
+	if (!req->dst) {
+		gfp_t flags = req->flags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL : GFP_ATOMIC;
+
+		/* incompressible data will always be < 2 * slen */
+		req->dlen = 2 * req->slen;
+		order = order_base_2(round_up(req->dlen, PAGE_SIZE) / PAGE_SIZE);
+		req->dst = sgl_alloc_order(req->dlen, order, false, flags, NULL);
+		if (!req->dst) {
+			ret = -ENOMEM;
+			order = -1;
+			goto out;
+		}
+		disable_async = true;
+	}
+
+	dev = &wq->idxd->pdev->dev;
+
+	nr_sgs = dma_map_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
+	if (nr_sgs <= 0 || nr_sgs > 1) {
+		dev_dbg(dev, "couldn't map src sg for iaa device %d,"
+			" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
+			iaa_wq->wq->id, ret);
+		ret = -EIO;
+		goto out;
+	}
+	src_addr = sg_dma_address(req->src);
+	dev_dbg(dev, "dma_map_sg, src_addr %llx, nr_sgs %d, req->src %p,"
+		" req->slen %d, sg_dma_len(sg) %d\n", src_addr, nr_sgs,
+		req->src, req->slen, sg_dma_len(req->src));
+
+	nr_sgs = dma_map_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
+	if (nr_sgs <= 0 || nr_sgs > 1) {
+		dev_dbg(dev, "couldn't map dst sg for iaa device %d,"
+			" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
+			iaa_wq->wq->id, ret);
+		ret = -EIO;
+		goto err_map_dst;
+	}
+	dst_addr = sg_dma_address(req->dst);
+	dev_dbg(dev, "dma_map_sg, dst_addr %llx, nr_sgs %d, req->dst %p,"
+		" req->dlen %d, sg_dma_len(sg) %d\n", dst_addr, nr_sgs,
+		req->dst, req->dlen, sg_dma_len(req->dst));
+
+	ret = iaa_compress(tfm, req, wq, src_addr, req->slen, dst_addr,
+			   &req->dlen, &compression_crc, disable_async);
+	if (ret == -EINPROGRESS)
+		return ret;
+
+	if (!ret && compression_ctx->verify_compress) {
+		ret = iaa_remap_for_verify(dev, iaa_wq, req, &src_addr, &dst_addr);
+		if (ret) {
+			dev_dbg(dev, "%s: compress verify remap failed ret=%d\n", __func__, ret);
+			goto out;
+		}
+
+		ret = iaa_compress_verify(tfm, req, wq, src_addr, req->slen,
+					  dst_addr, &req->dlen, compression_crc);
+		if (ret)
+			dev_dbg(dev, "asynchronous compress verification failed ret=%d\n", ret);
+
+		dma_unmap_sg(dev, req->dst, sg_nents(req->dst), DMA_TO_DEVICE);
+		dma_unmap_sg(dev, req->src, sg_nents(req->src), DMA_FROM_DEVICE);
+
+		goto out;
+	}
+
+	if (ret)
+		dev_dbg(dev, "asynchronous compress failed ret=%d\n", ret);
+
+	dma_unmap_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
+err_map_dst:
+	dma_unmap_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
+out:
+	iaa_wq_put(wq);
+
+	if (order >= 0)
+		sgl_free_order(req->dst, order);
+
+	return ret;
+}
+
+static int iaa_comp_adecompress_alloc_dest(struct acomp_req *req)
+{
+	gfp_t flags = req->flags & CRYPTO_TFM_REQ_MAY_SLEEP ?
+		GFP_KERNEL : GFP_ATOMIC;
+	struct crypto_tfm *tfm = req->base.tfm;
+	dma_addr_t src_addr, dst_addr;
+	int nr_sgs, cpu, ret = 0;
+	struct iaa_wq *iaa_wq;
+	struct device *dev;
+	struct idxd_wq *wq;
+	int order = -1;
+
+	cpu = get_cpu();
+	wq = wq_table_next_wq(cpu);
+	put_cpu();
+	if (!wq) {
+		pr_debug("no wq configured for cpu=%d\n", cpu);
+		return -ENODEV;
+	}
+
+	ret = iaa_wq_get(wq);
+	if (ret) {
+		pr_debug("no wq available for cpu=%d\n", cpu);
+		return -ENODEV;
+	}
+
+	iaa_wq = idxd_wq_get_private(wq);
+
+	dev = &wq->idxd->pdev->dev;
+
+	nr_sgs = dma_map_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
+	if (nr_sgs <= 0 || nr_sgs > 1) {
+		dev_dbg(dev, "couldn't map src sg for iaa device %d,"
+			" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
+			iaa_wq->wq->id, ret);
+		ret = -EIO;
+		goto out;
+	}
+	src_addr = sg_dma_address(req->src);
+	dev_dbg(dev, "dma_map_sg, src_addr %llx, nr_sgs %d, req->src %p,"
+		" req->slen %d, sg_dma_len(sg) %d\n", src_addr, nr_sgs,
+		req->src, req->slen, sg_dma_len(req->src));
+
+	req->dlen = 4 * req->slen; /* start with ~avg comp rato */
+alloc_dest:
+	order = order_base_2(round_up(req->dlen, PAGE_SIZE) / PAGE_SIZE);
+	req->dst = sgl_alloc_order(req->dlen, order, false, flags, NULL);
+	if (!req->dst) {
+		ret = -ENOMEM;
+		order = -1;
+		goto out;
+	}
+
+	nr_sgs = dma_map_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
+	if (nr_sgs <= 0 || nr_sgs > 1) {
+		dev_dbg(dev, "couldn't map dst sg for iaa device %d,"
+			" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
+			iaa_wq->wq->id, ret);
+		ret = -EIO;
+		goto err_map_dst;
+	}
+
+	dst_addr = sg_dma_address(req->dst);
+	dev_dbg(dev, "dma_map_sg, dst_addr %llx, nr_sgs %d, req->dst %p,"
+		" req->dlen %d, sg_dma_len(sg) %d\n", dst_addr, nr_sgs,
+		req->dst, req->dlen, sg_dma_len(req->dst));
+	ret = iaa_decompress(tfm, req, wq, src_addr, req->slen,
+			     dst_addr, &req->dlen, true);
+	if (ret == -EOVERFLOW) {
+		dma_unmap_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
+		req->dlen *= 2;
+		if (req->dlen > CRYPTO_ACOMP_DST_MAX)
+			goto err_map_dst;
+		goto alloc_dest;
+	}
+
+	if (ret != 0)
+		dev_dbg(dev, "asynchronous decompress failed ret=%d\n", ret);
+
+	dma_unmap_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
+err_map_dst:
+	dma_unmap_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
+out:
+	iaa_wq_put(wq);
+
+	if (order >= 0)
+		sgl_free_order(req->dst, order);
+
+	return ret;
+}
+
+static int iaa_comp_adecompress(struct acomp_req *req)
+{
+	struct crypto_tfm *tfm = req->base.tfm;
+	dma_addr_t src_addr, dst_addr;
+	int nr_sgs, cpu, ret = 0;
+	struct iaa_wq *iaa_wq;
+	struct device *dev;
+	struct idxd_wq *wq;
+
+	if (!iaa_crypto_enabled) {
+		pr_debug("iaa_crypto disabled, not decompressing\n");
+		return -ENODEV;
+	}
+
+	if (!req->src || !req->slen) {
+		pr_debug("invalid src, not decompressing\n");
+		return -EINVAL;
+	}
+
+	if (!req->dst)
+		return iaa_comp_adecompress_alloc_dest(req);
+
+	cpu = get_cpu();
+	wq = wq_table_next_wq(cpu);
+	put_cpu();
+	if (!wq) {
+		pr_debug("no wq configured for cpu=%d\n", cpu);
+		return -ENODEV;
+	}
+
+	ret = iaa_wq_get(wq);
+	if (ret) {
+		pr_debug("no wq available for cpu=%d\n", cpu);
+		return -ENODEV;
+	}
+
+	iaa_wq = idxd_wq_get_private(wq);
+
+	dev = &wq->idxd->pdev->dev;
+
+	nr_sgs = dma_map_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
+	if (nr_sgs <= 0 || nr_sgs > 1) {
+		dev_dbg(dev, "couldn't map src sg for iaa device %d,"
+			" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
+			iaa_wq->wq->id, ret);
+		ret = -EIO;
+		goto out;
+	}
+	src_addr = sg_dma_address(req->src);
+	dev_dbg(dev, "dma_map_sg, src_addr %llx, nr_sgs %d, req->src %p,"
+		" req->slen %d, sg_dma_len(sg) %d\n", src_addr, nr_sgs,
+		req->src, req->slen, sg_dma_len(req->src));
+
+	nr_sgs = dma_map_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
+	if (nr_sgs <= 0 || nr_sgs > 1) {
+		dev_dbg(dev, "couldn't map dst sg for iaa device %d,"
+			" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
+			iaa_wq->wq->id, ret);
+		ret = -EIO;
+		goto err_map_dst;
+	}
+	dst_addr = sg_dma_address(req->dst);
+	dev_dbg(dev, "dma_map_sg, dst_addr %llx, nr_sgs %d, req->dst %p,"
+		" req->dlen %d, sg_dma_len(sg) %d\n", dst_addr, nr_sgs,
+		req->dst, req->dlen, sg_dma_len(req->dst));
+
+	ret = iaa_decompress(tfm, req, wq, src_addr, req->slen,
+			     dst_addr, &req->dlen, false);
+	if (ret == -EINPROGRESS)
+		return ret;
+
+	if (ret != 0)
+		dev_dbg(dev, "asynchronous decompress failed ret=%d\n", ret);
+
+	dma_unmap_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
+err_map_dst:
+	dma_unmap_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
+out:
+	iaa_wq_put(wq);
+
+	return ret;
+}
+
+static void compression_ctx_init(struct iaa_compression_ctx *ctx)
+{
+	ctx->verify_compress = iaa_verify_compress;
+	ctx->async_mode = async_mode;
+	ctx->use_irq = use_irq;
+}
+
+static int iaa_comp_init_fixed(struct crypto_acomp *acomp_tfm)
+{
+	struct crypto_tfm *tfm = crypto_acomp_tfm(acomp_tfm);
+	struct iaa_compression_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	compression_ctx_init(ctx);
+
+	ctx->mode = IAA_MODE_FIXED;
+
+	return 0;
+}
+
+static void dst_free(struct scatterlist *sgl)
+{
+	/*
+	 * Called for req->dst = NULL cases but we free elsewhere
+	 * using sgl_free_order().
+	 */
+}
+
+static struct acomp_alg iaa_acomp_fixed_deflate = {
+	.init			= iaa_comp_init_fixed,
+	.compress		= iaa_comp_acompress,
+	.decompress		= iaa_comp_adecompress,
+	.dst_free               = dst_free,
+	.base			= {
+		.cra_name		= "deflate",
+		.cra_driver_name	= "deflate-iaa",
+		.cra_ctxsize		= sizeof(struct iaa_compression_ctx),
+		.cra_module		= THIS_MODULE,
+		.cra_priority		= IAA_ALG_PRIORITY,
+	}
+};
+
+static int iaa_register_compression_device(void)
+{
+	int ret;
+
+	ret = crypto_register_acomp(&iaa_acomp_fixed_deflate);
+	if (ret) {
+		pr_err("deflate algorithm acomp fixed registration failed (%d)\n", ret);
+		goto out;
+	}
+
+	iaa_crypto_registered = true;
+out:
+	return ret;
+}
+
+static int iaa_unregister_compression_device(void)
+{
+	if (iaa_crypto_registered)
+		crypto_unregister_acomp(&iaa_acomp_fixed_deflate);
+
+	return 0;
+}
+
+static int iaa_crypto_probe(struct idxd_dev *idxd_dev)
+{
+	struct idxd_wq *wq = idxd_dev_to_wq(idxd_dev);
+	struct idxd_device *idxd = wq->idxd;
+	struct idxd_driver_data *data = idxd->data;
+	struct device *dev = &idxd_dev->conf_dev;
+	bool first_wq = false;
+	int ret = 0;
+
+	if (idxd->state != IDXD_DEV_ENABLED)
+		return -ENXIO;
+
+	if (data->type != IDXD_TYPE_IAX)
+		return -ENODEV;
+
+	mutex_lock(&wq->wq_lock);
+
+	if (idxd_wq_get_private(wq)) {
+		mutex_unlock(&wq->wq_lock);
+		return -EBUSY;
+	}
+
+	if (!idxd_wq_driver_name_match(wq, dev)) {
+		dev_dbg(dev, "wq %d.%d driver_name match failed: wq driver_name %s, dev driver name %s\n",
+			idxd->id, wq->id, wq->driver_name, dev->driver->name);
+		idxd->cmd_status = IDXD_SCMD_WQ_NO_DRV_NAME;
+		ret = -ENODEV;
+		goto err;
+	}
+
+	wq->type = IDXD_WQT_KERNEL;
+
+	ret = idxd_drv_enable_wq(wq);
+	if (ret < 0) {
+		dev_dbg(dev, "enable wq %d.%d failed: %d\n",
+			idxd->id, wq->id, ret);
+		ret = -ENXIO;
+		goto err;
+	}
+
+	mutex_lock(&iaa_devices_lock);
+
+	if (list_empty(&iaa_devices)) {
+		ret = alloc_wq_table(wq->idxd->max_wqs);
+		if (ret)
+			goto err_alloc;
+		first_wq = true;
+	}
+
+	ret = save_iaa_wq(wq);
+	if (ret)
+		goto err_save;
+
+	rebalance_wq_table();
+
+	if (first_wq) {
+		iaa_crypto_enabled = true;
+		ret = iaa_register_compression_device();
+		if (ret != 0) {
+			iaa_crypto_enabled = false;
+			dev_dbg(dev, "IAA compression device registration failed\n");
+			goto err_register;
+		}
+		try_module_get(THIS_MODULE);
+
+		pr_info("iaa_crypto now ENABLED\n");
+	}
+
+	mutex_unlock(&iaa_devices_lock);
+out:
+	mutex_unlock(&wq->wq_lock);
+
+	return ret;
+
+err_register:
+	remove_iaa_wq(wq);
+	free_iaa_wq(idxd_wq_get_private(wq));
+err_save:
+	if (first_wq)
+		free_wq_table();
+err_alloc:
+	mutex_unlock(&iaa_devices_lock);
+	idxd_drv_disable_wq(wq);
+err:
+	wq->type = IDXD_WQT_NONE;
+
+	goto out;
+}
+
+static void iaa_crypto_remove(struct idxd_dev *idxd_dev)
+{
+	struct idxd_wq *wq = idxd_dev_to_wq(idxd_dev);
+	struct idxd_device *idxd = wq->idxd;
+	struct iaa_wq *iaa_wq;
+	bool free = false;
+
+	idxd_wq_quiesce(wq);
+
+	mutex_lock(&wq->wq_lock);
+	mutex_lock(&iaa_devices_lock);
+
+	remove_iaa_wq(wq);
+
+	spin_lock(&idxd->dev_lock);
+	iaa_wq = idxd_wq_get_private(wq);
+	if (!iaa_wq) {
+		spin_unlock(&idxd->dev_lock);
+		pr_err("%s: no iaa_wq available to remove\n", __func__);
+		goto out;
+	}
+
+	if (iaa_wq->ref) {
+		iaa_wq->remove = true;
+	} else {
+		wq = iaa_wq->wq;
+		idxd_wq_set_private(wq, NULL);
+		free = true;
+	}
+	spin_unlock(&idxd->dev_lock);
+	if (free) {
+		__free_iaa_wq(iaa_wq);
+		kfree(iaa_wq);
+	}
+
+	idxd_drv_disable_wq(wq);
+	rebalance_wq_table();
+
+	if (nr_iaa == 0) {
+		iaa_crypto_enabled = false;
+		free_wq_table();
+		module_put(THIS_MODULE);
+
+		pr_info("iaa_crypto now DISABLED\n");
+	}
+out:
+	mutex_unlock(&iaa_devices_lock);
+	mutex_unlock(&wq->wq_lock);
+}
+
+static enum idxd_dev_type dev_types[] = {
+	IDXD_DEV_WQ,
+	IDXD_DEV_NONE,
+};
+
+static struct idxd_device_driver iaa_crypto_driver = {
+	.probe = iaa_crypto_probe,
+	.remove = iaa_crypto_remove,
+	.name = IDXD_SUBDRIVER_NAME,
+	.type = dev_types,
+	.desc_complete = iaa_desc_complete,
+};
+
+static int __init iaa_crypto_init_module(void)
+{
+	int ret = 0;
+	int node;
+
+	nr_cpus = num_online_cpus();
+	for_each_node_with_cpus(node)
+		nr_nodes++;
+	if (!nr_nodes) {
+		pr_err("IAA couldn't find any nodes with cpus\n");
+		return -ENODEV;
+	}
+	nr_cpus_per_node = nr_cpus / nr_nodes;
+
+	if (crypto_has_comp("deflate-generic", 0, 0))
+		deflate_generic_tfm = crypto_alloc_comp("deflate-generic", 0, 0);
+
+	if (IS_ERR_OR_NULL(deflate_generic_tfm)) {
+		pr_err("IAA could not alloc %s tfm: errcode = %ld\n",
+		       "deflate-generic", PTR_ERR(deflate_generic_tfm));
+		return -ENOMEM;
+	}
+
+	ret = iaa_aecs_init_fixed();
+	if (ret < 0) {
+		pr_debug("IAA fixed compression mode init failed\n");
+		goto err_aecs_init;
+	}
+
+	ret = idxd_driver_register(&iaa_crypto_driver);
+	if (ret) {
+		pr_debug("IAA wq sub-driver registration failed\n");
+		goto err_driver_reg;
+	}
+
+	ret = driver_create_file(&iaa_crypto_driver.drv,
+				 &driver_attr_verify_compress);
+	if (ret) {
+		pr_debug("IAA verify_compress attr creation failed\n");
+		goto err_verify_attr_create;
+	}
+
+	ret = driver_create_file(&iaa_crypto_driver.drv,
+				 &driver_attr_sync_mode);
+	if (ret) {
+		pr_debug("IAA sync mode attr creation failed\n");
+		goto err_sync_attr_create;
+	}
+
+	if (iaa_crypto_debugfs_init())
+		pr_warn("debugfs init failed, stats not available\n");
+
+	pr_debug("initialized\n");
+out:
+	return ret;
+
+err_sync_attr_create:
+	driver_remove_file(&iaa_crypto_driver.drv,
+			   &driver_attr_verify_compress);
+err_verify_attr_create:
+	idxd_driver_unregister(&iaa_crypto_driver);
+err_driver_reg:
+	iaa_aecs_cleanup_fixed();
+err_aecs_init:
+	crypto_free_comp(deflate_generic_tfm);
+
+	goto out;
+}
+
+static void __exit iaa_crypto_cleanup_module(void)
+{
+	if (iaa_unregister_compression_device())
+		pr_debug("IAA compression device unregister failed\n");
+
+	iaa_crypto_debugfs_cleanup();
+	driver_remove_file(&iaa_crypto_driver.drv,
+			   &driver_attr_sync_mode);
+	driver_remove_file(&iaa_crypto_driver.drv,
+			   &driver_attr_verify_compress);
+	idxd_driver_unregister(&iaa_crypto_driver);
+	iaa_aecs_cleanup_fixed();
+	crypto_free_comp(deflate_generic_tfm);
+
+	pr_debug("cleaned up\n");
+}
+
+MODULE_IMPORT_NS(IDXD);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_IDXD_DEVICE(0);
+MODULE_AUTHOR("Intel Corporation");
+MODULE_DESCRIPTION("IAA Compression Accelerator Crypto Driver");
+
+module_init(iaa_crypto_init_module);
+module_exit(iaa_crypto_cleanup_module);
diff --git a/drivers/crypto/intel/iaa/iaa_crypto_stats.c b/drivers/crypto/intel/iaa/iaa_crypto_stats.c
new file mode 100644
index 000000000000..2e3b7b73af20
--- /dev/null
+++ b/drivers/crypto/intel/iaa/iaa_crypto_stats.c
@@ -0,0 +1,312 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2021 Intel Corporation. All rights rsvd. */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/highmem.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/smp.h>
+#include <uapi/linux/idxd.h>
+#include <linux/idxd.h>
+#include <linux/dmaengine.h>
+#include "../../dma/idxd/idxd.h"
+#include <linux/debugfs.h>
+#include <crypto/internal/acompress.h>
+#include "iaa_crypto.h"
+#include "iaa_crypto_stats.h"
+
+static u64 total_comp_calls;
+static u64 total_decomp_calls;
+static u64 total_sw_decomp_calls;
+static u64 max_comp_delay_ns;
+static u64 max_decomp_delay_ns;
+static u64 max_acomp_delay_ns;
+static u64 max_adecomp_delay_ns;
+static u64 total_comp_bytes_out;
+static u64 total_decomp_bytes_in;
+static u64 total_completion_einval_errors;
+static u64 total_completion_timeout_errors;
+static u64 total_completion_comp_buf_overflow_errors;
+
+static struct dentry *iaa_crypto_debugfs_root;
+
+void update_total_comp_calls(void)
+{
+	total_comp_calls++;
+}
+
+void update_total_comp_bytes_out(int n)
+{
+	total_comp_bytes_out += n;
+}
+
+void update_total_decomp_calls(void)
+{
+	total_decomp_calls++;
+}
+
+void update_total_sw_decomp_calls(void)
+{
+	total_sw_decomp_calls++;
+}
+
+void update_total_decomp_bytes_in(int n)
+{
+	total_decomp_bytes_in += n;
+}
+
+void update_completion_einval_errs(void)
+{
+	total_completion_einval_errors++;
+}
+
+void update_completion_timeout_errs(void)
+{
+	total_completion_timeout_errors++;
+}
+
+void update_completion_comp_buf_overflow_errs(void)
+{
+	total_completion_comp_buf_overflow_errors++;
+}
+
+void update_max_comp_delay_ns(u64 start_time_ns)
+{
+	u64 time_diff;
+
+	time_diff = ktime_get_ns() - start_time_ns;
+
+	if (time_diff > max_comp_delay_ns)
+		max_comp_delay_ns = time_diff;
+}
+
+void update_max_decomp_delay_ns(u64 start_time_ns)
+{
+	u64 time_diff;
+
+	time_diff = ktime_get_ns() - start_time_ns;
+
+	if (time_diff > max_decomp_delay_ns)
+		max_decomp_delay_ns = time_diff;
+}
+
+void update_max_acomp_delay_ns(u64 start_time_ns)
+{
+	u64 time_diff;
+
+	time_diff = ktime_get_ns() - start_time_ns;
+
+	if (time_diff > max_acomp_delay_ns)
+		max_acomp_delay_ns = time_diff;
+}
+
+void update_max_adecomp_delay_ns(u64 start_time_ns)
+{
+	u64 time_diff;
+
+	time_diff = ktime_get_ns() - start_time_ns;
+
+	if (time_diff > max_adecomp_delay_ns)
+		max_adecomp_delay_ns = time_diff;
+}
+
+void update_wq_comp_calls(struct idxd_wq *idxd_wq)
+{
+	struct iaa_wq *wq = idxd_wq_get_private(idxd_wq);
+
+	wq->comp_calls++;
+	wq->iaa_device->comp_calls++;
+}
+
+void update_wq_comp_bytes(struct idxd_wq *idxd_wq, int n)
+{
+	struct iaa_wq *wq = idxd_wq_get_private(idxd_wq);
+
+	wq->comp_bytes += n;
+	wq->iaa_device->comp_bytes += n;
+}
+
+void update_wq_decomp_calls(struct idxd_wq *idxd_wq)
+{
+	struct iaa_wq *wq = idxd_wq_get_private(idxd_wq);
+
+	wq->decomp_calls++;
+	wq->iaa_device->decomp_calls++;
+}
+
+void update_wq_decomp_bytes(struct idxd_wq *idxd_wq, int n)
+{
+	struct iaa_wq *wq = idxd_wq_get_private(idxd_wq);
+
+	wq->decomp_bytes += n;
+	wq->iaa_device->decomp_bytes += n;
+}
+
+static void reset_iaa_crypto_stats(void)
+{
+	total_comp_calls = 0;
+	total_decomp_calls = 0;
+	total_sw_decomp_calls = 0;
+	max_comp_delay_ns = 0;
+	max_decomp_delay_ns = 0;
+	max_acomp_delay_ns = 0;
+	max_adecomp_delay_ns = 0;
+	total_comp_bytes_out = 0;
+	total_decomp_bytes_in = 0;
+	total_completion_einval_errors = 0;
+	total_completion_timeout_errors = 0;
+	total_completion_comp_buf_overflow_errors = 0;
+}
+
+static void reset_wq_stats(struct iaa_wq *wq)
+{
+	wq->comp_calls = 0;
+	wq->comp_bytes = 0;
+	wq->decomp_calls = 0;
+	wq->decomp_bytes = 0;
+}
+
+static void reset_device_stats(struct iaa_device *iaa_device)
+{
+	struct iaa_wq *iaa_wq;
+
+	iaa_device->comp_calls = 0;
+	iaa_device->comp_bytes = 0;
+	iaa_device->decomp_calls = 0;
+	iaa_device->decomp_bytes = 0;
+
+	list_for_each_entry(iaa_wq, &iaa_device->wqs, list)
+		reset_wq_stats(iaa_wq);
+}
+
+static void wq_show(struct seq_file *m, struct iaa_wq *iaa_wq)
+{
+	seq_printf(m, "    name: %s\n", iaa_wq->wq->name);
+	seq_printf(m, "    comp_calls: %llu\n", iaa_wq->comp_calls);
+	seq_printf(m, "    comp_bytes: %llu\n", iaa_wq->comp_bytes);
+	seq_printf(m, "    decomp_calls: %llu\n", iaa_wq->decomp_calls);
+	seq_printf(m, "    decomp_bytes: %llu\n\n", iaa_wq->decomp_bytes);
+}
+
+static void device_stats_show(struct seq_file *m, struct iaa_device *iaa_device)
+{
+	struct iaa_wq *iaa_wq;
+
+	seq_puts(m, "iaa device:\n");
+	seq_printf(m, "  id: %d\n", iaa_device->idxd->id);
+	seq_printf(m, "  n_wqs: %d\n", iaa_device->n_wq);
+	seq_printf(m, "  comp_calls: %llu\n", iaa_device->comp_calls);
+	seq_printf(m, "  comp_bytes: %llu\n", iaa_device->comp_bytes);
+	seq_printf(m, "  decomp_calls: %llu\n", iaa_device->decomp_calls);
+	seq_printf(m, "  decomp_bytes: %llu\n", iaa_device->decomp_bytes);
+	seq_puts(m, "  wqs:\n");
+
+	list_for_each_entry(iaa_wq, &iaa_device->wqs, list)
+		wq_show(m, iaa_wq);
+}
+
+static void global_stats_show(struct seq_file *m)
+{
+	seq_puts(m, "global stats:\n");
+	seq_printf(m, "  total_comp_calls: %llu\n", total_comp_calls);
+	seq_printf(m, "  total_decomp_calls: %llu\n", total_decomp_calls);
+	seq_printf(m, "  total_sw_decomp_calls: %llu\n", total_sw_decomp_calls);
+	seq_printf(m, "  total_comp_bytes_out: %llu\n", total_comp_bytes_out);
+	seq_printf(m, "  total_decomp_bytes_in: %llu\n", total_decomp_bytes_in);
+	seq_printf(m, "  total_completion_einval_errors: %llu\n",
+		   total_completion_einval_errors);
+	seq_printf(m, "  total_completion_timeout_errors: %llu\n",
+		   total_completion_timeout_errors);
+	seq_printf(m, "  total_completion_comp_buf_overflow_errors: %llu\n\n",
+		   total_completion_comp_buf_overflow_errors);
+}
+
+static int wq_stats_show(struct seq_file *m, void *v)
+{
+	struct iaa_device *iaa_device;
+
+	mutex_lock(&iaa_devices_lock);
+
+	global_stats_show(m);
+
+	list_for_each_entry(iaa_device, &iaa_devices, list)
+		device_stats_show(m, iaa_device);
+
+	mutex_unlock(&iaa_devices_lock);
+
+	return 0;
+}
+
+static int iaa_crypto_stats_reset(void *data, u64 value)
+{
+	struct iaa_device *iaa_device;
+
+	reset_iaa_crypto_stats();
+
+	mutex_lock(&iaa_devices_lock);
+
+	list_for_each_entry(iaa_device, &iaa_devices, list)
+		reset_device_stats(iaa_device);
+
+	mutex_unlock(&iaa_devices_lock);
+
+	return 0;
+}
+
+static int wq_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, wq_stats_show, file);
+}
+
+static const struct file_operations wq_stats_fops = {
+	.open = wq_stats_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+DEFINE_DEBUGFS_ATTRIBUTE(wq_stats_reset_fops, NULL, iaa_crypto_stats_reset, "%llu\n");
+
+int __init iaa_crypto_debugfs_init(void)
+{
+	if (!debugfs_initialized())
+		return -ENODEV;
+
+	iaa_crypto_debugfs_root = debugfs_create_dir("iaa_crypto", NULL);
+	if (!iaa_crypto_debugfs_root)
+		return -ENOMEM;
+
+	debugfs_create_u64("max_comp_delay_ns", 0644,
+			   iaa_crypto_debugfs_root, &max_comp_delay_ns);
+	debugfs_create_u64("max_decomp_delay_ns", 0644,
+			   iaa_crypto_debugfs_root, &max_decomp_delay_ns);
+	debugfs_create_u64("max_acomp_delay_ns", 0644,
+			   iaa_crypto_debugfs_root, &max_comp_delay_ns);
+	debugfs_create_u64("max_adecomp_delay_ns", 0644,
+			   iaa_crypto_debugfs_root, &max_decomp_delay_ns);
+	debugfs_create_u64("total_comp_calls", 0644,
+			   iaa_crypto_debugfs_root, &total_comp_calls);
+	debugfs_create_u64("total_decomp_calls", 0644,
+			   iaa_crypto_debugfs_root, &total_decomp_calls);
+	debugfs_create_u64("total_sw_decomp_calls", 0644,
+			   iaa_crypto_debugfs_root, &total_sw_decomp_calls);
+	debugfs_create_u64("total_comp_bytes_out", 0644,
+			   iaa_crypto_debugfs_root, &total_comp_bytes_out);
+	debugfs_create_u64("total_decomp_bytes_in", 0644,
+			   iaa_crypto_debugfs_root, &total_decomp_bytes_in);
+	debugfs_create_file("wq_stats", 0644, iaa_crypto_debugfs_root, NULL,
+			    &wq_stats_fops);
+	debugfs_create_file("stats_reset", 0644, iaa_crypto_debugfs_root, NULL,
+			    &wq_stats_reset_fops);
+
+	return 0;
+}
+
+void __exit iaa_crypto_debugfs_cleanup(void)
+{
+	debugfs_remove_recursive(iaa_crypto_debugfs_root);
+}
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/crypto/intel/iaa/iaa_crypto_stats.h b/drivers/crypto/intel/iaa/iaa_crypto_stats.h
new file mode 100644
index 000000000000..c10b87b86fa4
--- /dev/null
+++ b/drivers/crypto/intel/iaa/iaa_crypto_stats.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2021 Intel Corporation. All rights rsvd. */
+
+#ifndef __CRYPTO_DEV_IAA_CRYPTO_STATS_H__
+#define __CRYPTO_DEV_IAA_CRYPTO_STATS_H__
+
+#if defined(CONFIG_CRYPTO_DEV_IAA_CRYPTO_STATS)
+int	iaa_crypto_debugfs_init(void);
+void	iaa_crypto_debugfs_cleanup(void);
+
+void	update_total_comp_calls(void);
+void	update_total_comp_bytes_out(int n);
+void	update_total_decomp_calls(void);
+void	update_total_sw_decomp_calls(void);
+void	update_total_decomp_bytes_in(int n);
+void	update_max_comp_delay_ns(u64 start_time_ns);
+void	update_max_decomp_delay_ns(u64 start_time_ns);
+void	update_max_acomp_delay_ns(u64 start_time_ns);
+void	update_max_adecomp_delay_ns(u64 start_time_ns);
+void	update_completion_einval_errs(void);
+void	update_completion_timeout_errs(void);
+void	update_completion_comp_buf_overflow_errs(void);
+
+void	update_wq_comp_calls(struct idxd_wq *idxd_wq);
+void	update_wq_comp_bytes(struct idxd_wq *idxd_wq, int n);
+void	update_wq_decomp_calls(struct idxd_wq *idxd_wq);
+void	update_wq_decomp_bytes(struct idxd_wq *idxd_wq, int n);
+
+#else
+static inline int	iaa_crypto_debugfs_init(void) { return 0; }
+static inline void	iaa_crypto_debugfs_cleanup(void) {}
+
+static inline void	update_total_comp_calls(void) {}
+static inline void	update_total_comp_bytes_out(int n) {}
+static inline void	update_total_decomp_calls(void) {}
+static inline void	update_total_sw_decomp_calls(void) {}
+static inline void	update_total_decomp_bytes_in(int n) {}
+static inline void	update_max_comp_delay_ns(u64 start_time_ns) {}
+static inline void	update_max_decomp_delay_ns(u64 start_time_ns) {}
+static inline void	update_max_acomp_delay_ns(u64 start_time_ns) {}
+static inline void	update_max_adecomp_delay_ns(u64 start_time_ns) {}
+static inline void	update_completion_einval_errs(void) {}
+static inline void	update_completion_timeout_errs(void) {}
+static inline void	update_completion_comp_buf_overflow_errs(void) {}
+
+static inline void	update_wq_comp_calls(struct idxd_wq *idxd_wq) {}
+static inline void	update_wq_comp_bytes(struct idxd_wq *idxd_wq, int n) {}
+static inline void	update_wq_decomp_calls(struct idxd_wq *idxd_wq) {}
+static inline void	update_wq_decomp_bytes(struct idxd_wq *idxd_wq, int n) {}
+
+#endif // CONFIG_CRYPTO_DEV_IAA_CRYPTO_STATS
+
+#endif
diff --git a/drivers/crypto/intel/qat/Kconfig b/drivers/crypto/intel/qat/Kconfig
index 1220cc86f910..c120f6715a09 100644
--- a/drivers/crypto/intel/qat/Kconfig
+++ b/drivers/crypto/intel/qat/Kconfig
@@ -59,6 +59,17 @@ config CRYPTO_DEV_QAT_4XXX
 	  To compile this as a module, choose M here: the module
 	  will be called qat_4xxx.
 
+config CRYPTO_DEV_QAT_420XX
+	tristate "Support for Intel(R) QAT_420XX"
+	depends on PCI && (!CPU_BIG_ENDIAN || COMPILE_TEST)
+	select CRYPTO_DEV_QAT
+	help
+	  Support for Intel(R) QuickAssist Technology QAT_420xx
+	  for accelerating crypto and compression workloads.
+
+	  To compile this as a module, choose M here: the module
+	  will be called qat_420xx.
+
 config CRYPTO_DEV_QAT_DH895xCCVF
 	tristate "Support for Intel(R) DH895xCC Virtual Function"
 	depends on PCI && (!CPU_BIG_ENDIAN || COMPILE_TEST)
diff --git a/drivers/crypto/intel/qat/Makefile b/drivers/crypto/intel/qat/Makefile
index 258c8a626ce0..235b69f4f3f7 100644
--- a/drivers/crypto/intel/qat/Makefile
+++ b/drivers/crypto/intel/qat/Makefile
@@ -4,6 +4,7 @@ obj-$(CONFIG_CRYPTO_DEV_QAT_DH895xCC) += qat_dh895xcc/
 obj-$(CONFIG_CRYPTO_DEV_QAT_C3XXX) += qat_c3xxx/
 obj-$(CONFIG_CRYPTO_DEV_QAT_C62X) += qat_c62x/
 obj-$(CONFIG_CRYPTO_DEV_QAT_4XXX) += qat_4xxx/
+obj-$(CONFIG_CRYPTO_DEV_QAT_420XX) += qat_420xx/
 obj-$(CONFIG_CRYPTO_DEV_QAT_DH895xCCVF) += qat_dh895xccvf/
 obj-$(CONFIG_CRYPTO_DEV_QAT_C3XXXVF) += qat_c3xxxvf/
 obj-$(CONFIG_CRYPTO_DEV_QAT_C62XVF) += qat_c62xvf/
diff --git a/drivers/crypto/intel/qat/qat_420xx/Makefile b/drivers/crypto/intel/qat/qat_420xx/Makefile
new file mode 100644
index 000000000000..a90fbe00b3c8
--- /dev/null
+++ b/drivers/crypto/intel/qat/qat_420xx/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+ccflags-y := -I $(srctree)/$(src)/../qat_common
+obj-$(CONFIG_CRYPTO_DEV_QAT_420XX) += qat_420xx.o
+qat_420xx-objs := adf_drv.o adf_420xx_hw_data.o
diff --git a/drivers/crypto/intel/qat/qat_420xx/adf_420xx_hw_data.c b/drivers/crypto/intel/qat/qat_420xx/adf_420xx_hw_data.c
new file mode 100644
index 000000000000..a87d29ae724f
--- /dev/null
+++ b/drivers/crypto/intel/qat/qat_420xx/adf_420xx_hw_data.c
@@ -0,0 +1,528 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2023 Intel Corporation */
+#include <linux/iopoll.h>
+#include <adf_accel_devices.h>
+#include <adf_admin.h>
+#include <adf_cfg.h>
+#include <adf_cfg_services.h>
+#include <adf_clock.h>
+#include <adf_common_drv.h>
+#include <adf_fw_config.h>
+#include <adf_gen4_config.h>
+#include <adf_gen4_dc.h>
+#include <adf_gen4_hw_data.h>
+#include <adf_gen4_pfvf.h>
+#include <adf_gen4_pm.h>
+#include <adf_gen4_ras.h>
+#include <adf_gen4_timer.h>
+#include <adf_gen4_tl.h>
+#include "adf_420xx_hw_data.h"
+#include "icp_qat_hw.h"
+
+#define ADF_AE_GROUP_0		GENMASK(3, 0)
+#define ADF_AE_GROUP_1		GENMASK(7, 4)
+#define ADF_AE_GROUP_2		GENMASK(11, 8)
+#define ADF_AE_GROUP_3		GENMASK(15, 12)
+#define ADF_AE_GROUP_4		BIT(16)
+
+#define ENA_THD_MASK_ASYM	GENMASK(1, 0)
+#define ENA_THD_MASK_SYM	GENMASK(3, 0)
+#define ENA_THD_MASK_DC		GENMASK(1, 0)
+
+static const char * const adf_420xx_fw_objs[] = {
+	[ADF_FW_SYM_OBJ] =  ADF_420XX_SYM_OBJ,
+	[ADF_FW_ASYM_OBJ] =  ADF_420XX_ASYM_OBJ,
+	[ADF_FW_DC_OBJ] =  ADF_420XX_DC_OBJ,
+	[ADF_FW_ADMIN_OBJ] = ADF_420XX_ADMIN_OBJ,
+};
+
+static const struct adf_fw_config adf_fw_cy_config[] = {
+	{ADF_AE_GROUP_3, ADF_FW_SYM_OBJ},
+	{ADF_AE_GROUP_2, ADF_FW_ASYM_OBJ},
+	{ADF_AE_GROUP_1, ADF_FW_SYM_OBJ},
+	{ADF_AE_GROUP_0, ADF_FW_ASYM_OBJ},
+	{ADF_AE_GROUP_4, ADF_FW_ADMIN_OBJ},
+};
+
+static const struct adf_fw_config adf_fw_dc_config[] = {
+	{ADF_AE_GROUP_1, ADF_FW_DC_OBJ},
+	{ADF_AE_GROUP_0, ADF_FW_DC_OBJ},
+	{ADF_AE_GROUP_4, ADF_FW_ADMIN_OBJ},
+};
+
+static const struct adf_fw_config adf_fw_sym_config[] = {
+	{ADF_AE_GROUP_3, ADF_FW_SYM_OBJ},
+	{ADF_AE_GROUP_2, ADF_FW_SYM_OBJ},
+	{ADF_AE_GROUP_1, ADF_FW_SYM_OBJ},
+	{ADF_AE_GROUP_0, ADF_FW_SYM_OBJ},
+	{ADF_AE_GROUP_4, ADF_FW_ADMIN_OBJ},
+};
+
+static const struct adf_fw_config adf_fw_asym_config[] = {
+	{ADF_AE_GROUP_3, ADF_FW_ASYM_OBJ},
+	{ADF_AE_GROUP_2, ADF_FW_ASYM_OBJ},
+	{ADF_AE_GROUP_1, ADF_FW_ASYM_OBJ},
+	{ADF_AE_GROUP_0, ADF_FW_ASYM_OBJ},
+	{ADF_AE_GROUP_4, ADF_FW_ADMIN_OBJ},
+};
+
+static const struct adf_fw_config adf_fw_asym_dc_config[] = {
+	{ADF_AE_GROUP_3, ADF_FW_ASYM_OBJ},
+	{ADF_AE_GROUP_2, ADF_FW_ASYM_OBJ},
+	{ADF_AE_GROUP_1, ADF_FW_ASYM_OBJ},
+	{ADF_AE_GROUP_0, ADF_FW_DC_OBJ},
+	{ADF_AE_GROUP_4, ADF_FW_ADMIN_OBJ},
+};
+
+static const struct adf_fw_config adf_fw_sym_dc_config[] = {
+	{ADF_AE_GROUP_2, ADF_FW_SYM_OBJ},
+	{ADF_AE_GROUP_1, ADF_FW_SYM_OBJ},
+	{ADF_AE_GROUP_0, ADF_FW_DC_OBJ},
+	{ADF_AE_GROUP_4, ADF_FW_ADMIN_OBJ},
+};
+
+static const struct adf_fw_config adf_fw_dcc_config[] = {
+	{ADF_AE_GROUP_1, ADF_FW_DC_OBJ},
+	{ADF_AE_GROUP_0, ADF_FW_SYM_OBJ},
+	{ADF_AE_GROUP_4, ADF_FW_ADMIN_OBJ},
+};
+
+
+static struct adf_hw_device_class adf_420xx_class = {
+	.name = ADF_420XX_DEVICE_NAME,
+	.type = DEV_420XX,
+	.instances = 0,
+};
+
+static u32 get_ae_mask(struct adf_hw_device_data *self)
+{
+	u32 me_disable = self->fuses;
+
+	return ~me_disable & ADF_420XX_ACCELENGINES_MASK;
+}
+
+static u32 uof_get_num_objs(struct adf_accel_dev *accel_dev)
+{
+	switch (adf_get_service_enabled(accel_dev)) {
+	case SVC_CY:
+	case SVC_CY2:
+		return ARRAY_SIZE(adf_fw_cy_config);
+	case SVC_DC:
+		return ARRAY_SIZE(adf_fw_dc_config);
+	case SVC_DCC:
+		return ARRAY_SIZE(adf_fw_dcc_config);
+	case SVC_SYM:
+		return ARRAY_SIZE(adf_fw_sym_config);
+	case SVC_ASYM:
+		return ARRAY_SIZE(adf_fw_asym_config);
+	case SVC_ASYM_DC:
+	case SVC_DC_ASYM:
+		return ARRAY_SIZE(adf_fw_asym_dc_config);
+	case SVC_SYM_DC:
+	case SVC_DC_SYM:
+		return ARRAY_SIZE(adf_fw_sym_dc_config);
+	default:
+		return 0;
+	}
+}
+
+static const struct adf_fw_config *get_fw_config(struct adf_accel_dev *accel_dev)
+{
+	switch (adf_get_service_enabled(accel_dev)) {
+	case SVC_CY:
+	case SVC_CY2:
+		return adf_fw_cy_config;
+	case SVC_DC:
+		return adf_fw_dc_config;
+	case SVC_DCC:
+		return adf_fw_dcc_config;
+	case SVC_SYM:
+		return adf_fw_sym_config;
+	case SVC_ASYM:
+		return adf_fw_asym_config;
+	case SVC_ASYM_DC:
+	case SVC_DC_ASYM:
+		return adf_fw_asym_dc_config;
+	case SVC_SYM_DC:
+	case SVC_DC_SYM:
+		return adf_fw_sym_dc_config;
+	default:
+		return NULL;
+	}
+}
+
+static void update_ae_mask(struct adf_accel_dev *accel_dev)
+{
+	struct adf_hw_device_data *hw_data = GET_HW_DATA(accel_dev);
+	const struct adf_fw_config *fw_config;
+	u32 config_ae_mask = 0;
+	u32 ae_mask, num_objs;
+	int i;
+
+	ae_mask = get_ae_mask(hw_data);
+
+	/* Modify the AE mask based on the firmware configuration loaded */
+	fw_config = get_fw_config(accel_dev);
+	num_objs = uof_get_num_objs(accel_dev);
+
+	config_ae_mask |= ADF_420XX_ADMIN_AE_MASK;
+	for (i = 0; i < num_objs; i++)
+		config_ae_mask |= fw_config[i].ae_mask;
+
+	hw_data->ae_mask = ae_mask & config_ae_mask;
+}
+
+static u32 get_accel_cap(struct adf_accel_dev *accel_dev)
+{
+	u32 capabilities_sym, capabilities_asym, capabilities_dc;
+	struct pci_dev *pdev = accel_dev->accel_pci_dev.pci_dev;
+	u32 capabilities_dcc;
+	u32 fusectl1;
+
+	/* As a side effect, update ae_mask based on configuration */
+	update_ae_mask(accel_dev);
+
+	/* Read accelerator capabilities mask */
+	pci_read_config_dword(pdev, ADF_GEN4_FUSECTL1_OFFSET, &fusectl1);
+
+	capabilities_sym = ICP_ACCEL_CAPABILITIES_CRYPTO_SYMMETRIC |
+			  ICP_ACCEL_CAPABILITIES_CIPHER |
+			  ICP_ACCEL_CAPABILITIES_AUTHENTICATION |
+			  ICP_ACCEL_CAPABILITIES_SHA3 |
+			  ICP_ACCEL_CAPABILITIES_SHA3_EXT |
+			  ICP_ACCEL_CAPABILITIES_HKDF |
+			  ICP_ACCEL_CAPABILITIES_CHACHA_POLY |
+			  ICP_ACCEL_CAPABILITIES_AESGCM_SPC |
+			  ICP_ACCEL_CAPABILITIES_SM3 |
+			  ICP_ACCEL_CAPABILITIES_SM4 |
+			  ICP_ACCEL_CAPABILITIES_AES_V2 |
+			  ICP_ACCEL_CAPABILITIES_ZUC |
+			  ICP_ACCEL_CAPABILITIES_ZUC_256 |
+			  ICP_ACCEL_CAPABILITIES_WIRELESS_CRYPTO_EXT |
+			  ICP_ACCEL_CAPABILITIES_EXT_ALGCHAIN;
+
+	/* A set bit in fusectl1 means the feature is OFF in this SKU */
+	if (fusectl1 & ICP_ACCEL_GEN4_MASK_CIPHER_SLICE) {
+		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_CRYPTO_SYMMETRIC;
+		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_HKDF;
+		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_CIPHER;
+	}
+
+	if (fusectl1 & ICP_ACCEL_GEN4_MASK_UCS_SLICE) {
+		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_CHACHA_POLY;
+		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_AESGCM_SPC;
+		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_AES_V2;
+		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_CIPHER;
+	}
+
+	if (fusectl1 & ICP_ACCEL_GEN4_MASK_AUTH_SLICE) {
+		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_AUTHENTICATION;
+		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_SHA3;
+		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_SHA3_EXT;
+		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_CIPHER;
+	}
+
+	if (fusectl1 & ICP_ACCEL_GEN4_MASK_SMX_SLICE) {
+		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_SM3;
+		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_SM4;
+	}
+
+	if (fusectl1 & ICP_ACCEL_GEN4_MASK_WCP_WAT_SLICE) {
+		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_ZUC;
+		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_ZUC_256;
+		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_WIRELESS_CRYPTO_EXT;
+	}
+
+	if (fusectl1 & ICP_ACCEL_GEN4_MASK_EIA3_SLICE) {
+		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_ZUC;
+		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_ZUC_256;
+	}
+
+	if (fusectl1 & ICP_ACCEL_GEN4_MASK_ZUC_256_SLICE)
+		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_ZUC_256;
+
+	capabilities_asym = ICP_ACCEL_CAPABILITIES_CRYPTO_ASYMMETRIC |
+			  ICP_ACCEL_CAPABILITIES_SM2 |
+			  ICP_ACCEL_CAPABILITIES_ECEDMONT;
+
+	if (fusectl1 & ICP_ACCEL_GEN4_MASK_PKE_SLICE) {
+		capabilities_asym &= ~ICP_ACCEL_CAPABILITIES_CRYPTO_ASYMMETRIC;
+		capabilities_asym &= ~ICP_ACCEL_CAPABILITIES_SM2;
+		capabilities_asym &= ~ICP_ACCEL_CAPABILITIES_ECEDMONT;
+	}
+
+	capabilities_dc = ICP_ACCEL_CAPABILITIES_COMPRESSION |
+			  ICP_ACCEL_CAPABILITIES_LZ4_COMPRESSION |
+			  ICP_ACCEL_CAPABILITIES_LZ4S_COMPRESSION |
+			  ICP_ACCEL_CAPABILITIES_CNV_INTEGRITY64;
+
+	if (fusectl1 & ICP_ACCEL_GEN4_MASK_COMPRESS_SLICE) {
+		capabilities_dc &= ~ICP_ACCEL_CAPABILITIES_COMPRESSION;
+		capabilities_dc &= ~ICP_ACCEL_CAPABILITIES_LZ4_COMPRESSION;
+		capabilities_dc &= ~ICP_ACCEL_CAPABILITIES_LZ4S_COMPRESSION;
+		capabilities_dc &= ~ICP_ACCEL_CAPABILITIES_CNV_INTEGRITY64;
+	}
+
+	switch (adf_get_service_enabled(accel_dev)) {
+	case SVC_CY:
+	case SVC_CY2:
+		return capabilities_sym | capabilities_asym;
+	case SVC_DC:
+		return capabilities_dc;
+	case SVC_DCC:
+		/*
+		 * Sym capabilities are available for chaining operations,
+		 * but sym crypto instances cannot be supported
+		 */
+		capabilities_dcc = capabilities_dc | capabilities_sym;
+		capabilities_dcc &= ~ICP_ACCEL_CAPABILITIES_CRYPTO_SYMMETRIC;
+		return capabilities_dcc;
+	case SVC_SYM:
+		return capabilities_sym;
+	case SVC_ASYM:
+		return capabilities_asym;
+	case SVC_ASYM_DC:
+	case SVC_DC_ASYM:
+		return capabilities_asym | capabilities_dc;
+	case SVC_SYM_DC:
+	case SVC_DC_SYM:
+		return capabilities_sym | capabilities_dc;
+	default:
+		return 0;
+	}
+}
+
+static const u32 *adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev)
+{
+	if (adf_gen4_init_thd2arb_map(accel_dev))
+		dev_warn(&GET_DEV(accel_dev),
+			 "Generate of the thread to arbiter map failed");
+
+	return GET_HW_DATA(accel_dev)->thd_to_arb_map;
+}
+
+static void adf_init_rl_data(struct adf_rl_hw_data *rl_data)
+{
+	rl_data->pciout_tb_offset = ADF_GEN4_RL_TOKEN_PCIEOUT_BUCKET_OFFSET;
+	rl_data->pciin_tb_offset = ADF_GEN4_RL_TOKEN_PCIEIN_BUCKET_OFFSET;
+	rl_data->r2l_offset = ADF_GEN4_RL_R2L_OFFSET;
+	rl_data->l2c_offset = ADF_GEN4_RL_L2C_OFFSET;
+	rl_data->c2s_offset = ADF_GEN4_RL_C2S_OFFSET;
+
+	rl_data->pcie_scale_div = ADF_420XX_RL_PCIE_SCALE_FACTOR_DIV;
+	rl_data->pcie_scale_mul = ADF_420XX_RL_PCIE_SCALE_FACTOR_MUL;
+	rl_data->dcpr_correction = ADF_420XX_RL_DCPR_CORRECTION;
+	rl_data->max_tp[ADF_SVC_ASYM] = ADF_420XX_RL_MAX_TP_ASYM;
+	rl_data->max_tp[ADF_SVC_SYM] = ADF_420XX_RL_MAX_TP_SYM;
+	rl_data->max_tp[ADF_SVC_DC] = ADF_420XX_RL_MAX_TP_DC;
+	rl_data->scan_interval = ADF_420XX_RL_SCANS_PER_SEC;
+	rl_data->scale_ref = ADF_420XX_RL_SLICE_REF;
+}
+
+static int get_rp_group(struct adf_accel_dev *accel_dev, u32 ae_mask)
+{
+	switch (ae_mask) {
+	case ADF_AE_GROUP_0:
+		return RP_GROUP_0;
+	case ADF_AE_GROUP_1:
+	case ADF_AE_GROUP_3:
+		return RP_GROUP_1;
+	case ADF_AE_GROUP_2:
+		if (get_fw_config(accel_dev) == adf_fw_cy_config)
+			return RP_GROUP_0;
+		else
+			return RP_GROUP_1;
+	default:
+		dev_dbg(&GET_DEV(accel_dev), "ae_mask not recognized");
+		return -EINVAL;
+	}
+}
+
+static u32 get_ena_thd_mask(struct adf_accel_dev *accel_dev, u32 obj_num)
+{
+	const struct adf_fw_config *fw_config;
+
+	if (obj_num >= uof_get_num_objs(accel_dev))
+		return ADF_GEN4_ENA_THD_MASK_ERROR;
+
+	fw_config = get_fw_config(accel_dev);
+	if (!fw_config)
+		return ADF_GEN4_ENA_THD_MASK_ERROR;
+
+	switch (fw_config[obj_num].obj) {
+	case ADF_FW_ASYM_OBJ:
+		return ENA_THD_MASK_ASYM;
+	case ADF_FW_SYM_OBJ:
+		return ENA_THD_MASK_SYM;
+	case ADF_FW_DC_OBJ:
+		return ENA_THD_MASK_DC;
+	default:
+		return ADF_GEN4_ENA_THD_MASK_ERROR;
+	}
+}
+
+static u16 get_ring_to_svc_map(struct adf_accel_dev *accel_dev)
+{
+	enum adf_cfg_service_type rps[RP_GROUP_COUNT] = { };
+	const struct adf_fw_config *fw_config;
+	u16 ring_to_svc_map;
+	int i, j;
+
+	fw_config = get_fw_config(accel_dev);
+	if (!fw_config)
+		return 0;
+
+	for (i = 0; i < RP_GROUP_COUNT; i++) {
+		switch (fw_config[i].ae_mask) {
+		case ADF_AE_GROUP_0:
+			j = RP_GROUP_0;
+			break;
+		case ADF_AE_GROUP_1:
+			j = RP_GROUP_1;
+			break;
+		default:
+			return 0;
+		}
+
+		switch (fw_config[i].obj) {
+		case ADF_FW_SYM_OBJ:
+			rps[j] = SYM;
+			break;
+		case ADF_FW_ASYM_OBJ:
+			rps[j] = ASYM;
+			break;
+		case ADF_FW_DC_OBJ:
+			rps[j] = COMP;
+			break;
+		default:
+			rps[j] = 0;
+			break;
+		}
+	}
+
+	ring_to_svc_map = rps[RP_GROUP_0] << ADF_CFG_SERV_RING_PAIR_0_SHIFT |
+			  rps[RP_GROUP_1] << ADF_CFG_SERV_RING_PAIR_1_SHIFT |
+			  rps[RP_GROUP_0] << ADF_CFG_SERV_RING_PAIR_2_SHIFT |
+			  rps[RP_GROUP_1] << ADF_CFG_SERV_RING_PAIR_3_SHIFT;
+
+	return ring_to_svc_map;
+}
+
+static const char *uof_get_name(struct adf_accel_dev *accel_dev, u32 obj_num,
+				const char * const fw_objs[], int num_objs)
+{
+	const struct adf_fw_config *fw_config;
+	int id;
+
+	fw_config = get_fw_config(accel_dev);
+	if (fw_config)
+		id = fw_config[obj_num].obj;
+	else
+		id = -EINVAL;
+
+	if (id < 0 || id > num_objs)
+		return NULL;
+
+	return fw_objs[id];
+}
+
+static const char *uof_get_name_420xx(struct adf_accel_dev *accel_dev, u32 obj_num)
+{
+	int num_fw_objs = ARRAY_SIZE(adf_420xx_fw_objs);
+
+	return uof_get_name(accel_dev, obj_num, adf_420xx_fw_objs, num_fw_objs);
+}
+
+static u32 uof_get_ae_mask(struct adf_accel_dev *accel_dev, u32 obj_num)
+{
+	const struct adf_fw_config *fw_config;
+
+	fw_config = get_fw_config(accel_dev);
+	if (!fw_config)
+		return 0;
+
+	return fw_config[obj_num].ae_mask;
+}
+
+static void adf_gen4_set_err_mask(struct adf_dev_err_mask *dev_err_mask)
+{
+	dev_err_mask->cppagentcmdpar_mask = ADF_420XX_HICPPAGENTCMDPARERRLOG_MASK;
+	dev_err_mask->parerr_ath_cph_mask = ADF_420XX_PARITYERRORMASK_ATH_CPH_MASK;
+	dev_err_mask->parerr_cpr_xlt_mask = ADF_420XX_PARITYERRORMASK_CPR_XLT_MASK;
+	dev_err_mask->parerr_dcpr_ucs_mask = ADF_420XX_PARITYERRORMASK_DCPR_UCS_MASK;
+	dev_err_mask->parerr_pke_mask = ADF_420XX_PARITYERRORMASK_PKE_MASK;
+	dev_err_mask->ssmfeatren_mask = ADF_420XX_SSMFEATREN_MASK;
+}
+
+void adf_init_hw_data_420xx(struct adf_hw_device_data *hw_data, u32 dev_id)
+{
+	hw_data->dev_class = &adf_420xx_class;
+	hw_data->instance_id = adf_420xx_class.instances++;
+	hw_data->num_banks = ADF_GEN4_ETR_MAX_BANKS;
+	hw_data->num_banks_per_vf = ADF_GEN4_NUM_BANKS_PER_VF;
+	hw_data->num_rings_per_bank = ADF_GEN4_NUM_RINGS_PER_BANK;
+	hw_data->num_accel = ADF_GEN4_MAX_ACCELERATORS;
+	hw_data->num_engines = ADF_420XX_MAX_ACCELENGINES;
+	hw_data->num_logical_accel = 1;
+	hw_data->tx_rx_gap = ADF_GEN4_RX_RINGS_OFFSET;
+	hw_data->tx_rings_mask = ADF_GEN4_TX_RINGS_MASK;
+	hw_data->ring_to_svc_map = ADF_GEN4_DEFAULT_RING_TO_SRV_MAP;
+	hw_data->alloc_irq = adf_isr_resource_alloc;
+	hw_data->free_irq = adf_isr_resource_free;
+	hw_data->enable_error_correction = adf_gen4_enable_error_correction;
+	hw_data->get_accel_mask = adf_gen4_get_accel_mask;
+	hw_data->get_ae_mask = get_ae_mask;
+	hw_data->get_num_accels = adf_gen4_get_num_accels;
+	hw_data->get_num_aes = adf_gen4_get_num_aes;
+	hw_data->get_sram_bar_id = adf_gen4_get_sram_bar_id;
+	hw_data->get_etr_bar_id = adf_gen4_get_etr_bar_id;
+	hw_data->get_misc_bar_id = adf_gen4_get_misc_bar_id;
+	hw_data->get_arb_info = adf_gen4_get_arb_info;
+	hw_data->get_admin_info = adf_gen4_get_admin_info;
+	hw_data->get_accel_cap = get_accel_cap;
+	hw_data->get_sku = adf_gen4_get_sku;
+	hw_data->init_admin_comms = adf_init_admin_comms;
+	hw_data->exit_admin_comms = adf_exit_admin_comms;
+	hw_data->send_admin_init = adf_send_admin_init;
+	hw_data->init_arb = adf_init_arb;
+	hw_data->exit_arb = adf_exit_arb;
+	hw_data->get_arb_mapping = adf_get_arbiter_mapping;
+	hw_data->enable_ints = adf_gen4_enable_ints;
+	hw_data->init_device = adf_gen4_init_device;
+	hw_data->reset_device = adf_reset_flr;
+	hw_data->admin_ae_mask = ADF_420XX_ADMIN_AE_MASK;
+	hw_data->num_rps = ADF_GEN4_MAX_RPS;
+	hw_data->fw_name = ADF_420XX_FW;
+	hw_data->fw_mmp_name = ADF_420XX_MMP;
+	hw_data->uof_get_name = uof_get_name_420xx;
+	hw_data->uof_get_num_objs = uof_get_num_objs;
+	hw_data->uof_get_ae_mask = uof_get_ae_mask;
+	hw_data->get_rp_group = get_rp_group;
+	hw_data->get_ena_thd_mask = get_ena_thd_mask;
+	hw_data->set_msix_rttable = adf_gen4_set_msix_default_rttable;
+	hw_data->set_ssm_wdtimer = adf_gen4_set_ssm_wdtimer;
+	hw_data->get_ring_to_svc_map = get_ring_to_svc_map;
+	hw_data->disable_iov = adf_disable_sriov;
+	hw_data->ring_pair_reset = adf_gen4_ring_pair_reset;
+	hw_data->enable_pm = adf_gen4_enable_pm;
+	hw_data->handle_pm_interrupt = adf_gen4_handle_pm_interrupt;
+	hw_data->dev_config = adf_gen4_dev_config;
+	hw_data->start_timer = adf_gen4_timer_start;
+	hw_data->stop_timer = adf_gen4_timer_stop;
+	hw_data->get_hb_clock = adf_gen4_get_heartbeat_clock;
+	hw_data->num_hb_ctrs = ADF_NUM_HB_CNT_PER_AE;
+	hw_data->clock_frequency = ADF_420XX_AE_FREQ;
+
+	adf_gen4_set_err_mask(&hw_data->dev_err_mask);
+	adf_gen4_init_hw_csr_ops(&hw_data->csr_ops);
+	adf_gen4_init_pf_pfvf_ops(&hw_data->pfvf_ops);
+	adf_gen4_init_dc_ops(&hw_data->dc_ops);
+	adf_gen4_init_ras_ops(&hw_data->ras_ops);
+	adf_gen4_init_tl_data(&hw_data->tl_data);
+	adf_init_rl_data(&hw_data->rl_data);
+}
+
+void adf_clean_hw_data_420xx(struct adf_hw_device_data *hw_data)
+{
+	hw_data->dev_class->instances--;
+}
diff --git a/drivers/crypto/intel/qat/qat_420xx/adf_420xx_hw_data.h b/drivers/crypto/intel/qat/qat_420xx/adf_420xx_hw_data.h
new file mode 100644
index 000000000000..99abbfc14820
--- /dev/null
+++ b/drivers/crypto/intel/qat/qat_420xx/adf_420xx_hw_data.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright(c) 2023 Intel Corporation */
+#ifndef ADF_420XX_HW_DATA_H_
+#define ADF_420XX_HW_DATA_H_
+
+#include <adf_accel_devices.h>
+
+#define ADF_420XX_MAX_ACCELENGINES		17
+
+#define ADF_420XX_ACCELENGINES_MASK		0x1FFFF
+#define ADF_420XX_ADMIN_AE_MASK			0x10000
+
+#define ADF_420XX_HICPPAGENTCMDPARERRLOG_MASK	(0xFF)
+#define ADF_420XX_PARITYERRORMASK_ATH_CPH_MASK	(0xFF00FF)
+#define ADF_420XX_PARITYERRORMASK_CPR_XLT_MASK	(0x10001)
+#define ADF_420XX_PARITYERRORMASK_DCPR_UCS_MASK	(0xF0007)
+#define ADF_420XX_PARITYERRORMASK_PKE_MASK	(0xFFF)
+#define ADF_420XX_PARITYERRORMASK_WAT_WCP_MASK	(0x3FF03FF)
+
+/*
+ * SSMFEATREN bit mask
+ * BIT(4) - enables parity detection on CPP
+ * BIT(12) - enables the logging of push/pull data errors
+ *	     in pperr register
+ * BIT(16) - BIT(27) - enable parity detection on SPPs
+ */
+#define ADF_420XX_SSMFEATREN_MASK \
+	(BIT(4) | BIT(12) | BIT(16) | BIT(17) | BIT(18) | BIT(19) | BIT(20) | \
+	 BIT(21) | BIT(22) | BIT(23) | BIT(24) | BIT(25) | BIT(26) | BIT(27))
+
+/* Firmware Binaries */
+#define ADF_420XX_FW		"qat_420xx.bin"
+#define ADF_420XX_MMP		"qat_420xx_mmp.bin"
+#define ADF_420XX_SYM_OBJ	"qat_420xx_sym.bin"
+#define ADF_420XX_DC_OBJ	"qat_420xx_dc.bin"
+#define ADF_420XX_ASYM_OBJ	"qat_420xx_asym.bin"
+#define ADF_420XX_ADMIN_OBJ	"qat_420xx_admin.bin"
+
+/* RL constants */
+#define ADF_420XX_RL_PCIE_SCALE_FACTOR_DIV	100
+#define ADF_420XX_RL_PCIE_SCALE_FACTOR_MUL	102
+#define ADF_420XX_RL_DCPR_CORRECTION		1
+#define ADF_420XX_RL_SCANS_PER_SEC		954
+#define ADF_420XX_RL_MAX_TP_ASYM		173750UL
+#define ADF_420XX_RL_MAX_TP_SYM			95000UL
+#define ADF_420XX_RL_MAX_TP_DC			40000UL
+#define ADF_420XX_RL_SLICE_REF			1000UL
+
+/* Clocks frequency */
+#define ADF_420XX_AE_FREQ		(1000 * HZ_PER_MHZ)
+
+void adf_init_hw_data_420xx(struct adf_hw_device_data *hw_data, u32 dev_id);
+void adf_clean_hw_data_420xx(struct adf_hw_device_data *hw_data);
+
+#endif
diff --git a/drivers/crypto/intel/qat/qat_420xx/adf_drv.c b/drivers/crypto/intel/qat/qat_420xx/adf_drv.c
new file mode 100644
index 000000000000..2a3598409eeb
--- /dev/null
+++ b/drivers/crypto/intel/qat/qat_420xx/adf_drv.c
@@ -0,0 +1,202 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2023 Intel Corporation */
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+
+#include <adf_accel_devices.h>
+#include <adf_gen4_hw_data.h>
+#include <adf_gen4_config.h>
+#include <adf_cfg.h>
+#include <adf_common_drv.h>
+#include <adf_dbgfs.h>
+
+#include "adf_420xx_hw_data.h"
+
+static const struct pci_device_id adf_pci_tbl[] = {
+	{ PCI_VDEVICE(INTEL, ADF_420XX_PCI_DEVICE_ID), },
+	{ }
+};
+MODULE_DEVICE_TABLE(pci, adf_pci_tbl);
+
+static void adf_cleanup_accel(struct adf_accel_dev *accel_dev)
+{
+	if (accel_dev->hw_device) {
+		adf_clean_hw_data_420xx(accel_dev->hw_device);
+		accel_dev->hw_device = NULL;
+	}
+	adf_dbgfs_exit(accel_dev);
+	adf_cfg_dev_remove(accel_dev);
+	adf_devmgr_rm_dev(accel_dev, NULL);
+}
+
+static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	struct adf_accel_dev *accel_dev;
+	struct adf_accel_pci *accel_pci_dev;
+	struct adf_hw_device_data *hw_data;
+	unsigned int i, bar_nr;
+	unsigned long bar_mask;
+	struct adf_bar *bar;
+	int ret;
+
+	if (num_possible_nodes() > 1 && dev_to_node(&pdev->dev) < 0) {
+		/*
+		 * If the accelerator is connected to a node with no memory
+		 * there is no point in using the accelerator since the remote
+		 * memory transaction will be very slow.
+		 */
+		dev_err(&pdev->dev, "Invalid NUMA configuration.\n");
+		return -EINVAL;
+	}
+
+	accel_dev = devm_kzalloc(&pdev->dev, sizeof(*accel_dev), GFP_KERNEL);
+	if (!accel_dev)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&accel_dev->crypto_list);
+	accel_pci_dev = &accel_dev->accel_pci_dev;
+	accel_pci_dev->pci_dev = pdev;
+
+	/*
+	 * Add accel device to accel table
+	 * This should be called before adf_cleanup_accel is called
+	 */
+	if (adf_devmgr_add_dev(accel_dev, NULL)) {
+		dev_err(&pdev->dev, "Failed to add new accelerator device.\n");
+		return -EFAULT;
+	}
+
+	accel_dev->owner = THIS_MODULE;
+	/* Allocate and initialise device hardware meta-data structure */
+	hw_data = devm_kzalloc(&pdev->dev, sizeof(*hw_data), GFP_KERNEL);
+	if (!hw_data) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	accel_dev->hw_device = hw_data;
+	adf_init_hw_data_420xx(accel_dev->hw_device, ent->device);
+
+	pci_read_config_byte(pdev, PCI_REVISION_ID, &accel_pci_dev->revid);
+	pci_read_config_dword(pdev, ADF_GEN4_FUSECTL4_OFFSET, &hw_data->fuses);
+
+	/* Get Accelerators and Accelerators Engines masks */
+	hw_data->accel_mask = hw_data->get_accel_mask(hw_data);
+	hw_data->ae_mask = hw_data->get_ae_mask(hw_data);
+	accel_pci_dev->sku = hw_data->get_sku(hw_data);
+	/* If the device has no acceleration engines then ignore it */
+	if (!hw_data->accel_mask || !hw_data->ae_mask ||
+	    (~hw_data->ae_mask & 0x01)) {
+		dev_err(&pdev->dev, "No acceleration units found.\n");
+		ret = -EFAULT;
+		goto out_err;
+	}
+
+	/* Create device configuration table */
+	ret = adf_cfg_dev_add(accel_dev);
+	if (ret)
+		goto out_err;
+
+	/* Enable PCI device */
+	ret = pcim_enable_device(pdev);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't enable PCI device.\n");
+		goto out_err;
+	}
+
+	/* Set DMA identifier */
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	if (ret) {
+		dev_err(&pdev->dev, "No usable DMA configuration.\n");
+		goto out_err;
+	}
+
+	ret = adf_gen4_cfg_dev_init(accel_dev);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to initialize configuration.\n");
+		goto out_err;
+	}
+
+	/* Get accelerator capabilities mask */
+	hw_data->accel_capabilities_mask = hw_data->get_accel_cap(accel_dev);
+	if (!hw_data->accel_capabilities_mask) {
+		dev_err(&pdev->dev, "Failed to get capabilities mask.\n");
+		ret = -EINVAL;
+		goto out_err;
+	}
+
+	/* Find and map all the device's BARS */
+	bar_mask = pci_select_bars(pdev, IORESOURCE_MEM) & ADF_GEN4_BAR_MASK;
+
+	ret = pcim_iomap_regions_request_all(pdev, bar_mask, pci_name(pdev));
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to map pci regions.\n");
+		goto out_err;
+	}
+
+	i = 0;
+	for_each_set_bit(bar_nr, &bar_mask, PCI_STD_NUM_BARS) {
+		bar = &accel_pci_dev->pci_bars[i++];
+		bar->virt_addr = pcim_iomap_table(pdev)[bar_nr];
+	}
+
+	pci_set_master(pdev);
+
+	if (pci_save_state(pdev)) {
+		dev_err(&pdev->dev, "Failed to save pci state.\n");
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	accel_dev->ras_errors.enabled = true;
+	adf_dbgfs_init(accel_dev);
+
+	ret = adf_dev_up(accel_dev, true);
+	if (ret)
+		goto out_err_dev_stop;
+
+	ret = adf_sysfs_init(accel_dev);
+	if (ret)
+		goto out_err_dev_stop;
+
+	return ret;
+
+out_err_dev_stop:
+	adf_dev_down(accel_dev, false);
+out_err:
+	adf_cleanup_accel(accel_dev);
+	return ret;
+}
+
+static void adf_remove(struct pci_dev *pdev)
+{
+	struct adf_accel_dev *accel_dev = adf_devmgr_pci_to_accel_dev(pdev);
+
+	if (!accel_dev) {
+		pr_err("QAT: Driver removal failed\n");
+		return;
+	}
+	adf_dev_down(accel_dev, false);
+	adf_cleanup_accel(accel_dev);
+}
+
+static struct pci_driver adf_driver = {
+	.id_table = adf_pci_tbl,
+	.name = ADF_420XX_DEVICE_NAME,
+	.probe = adf_probe,
+	.remove = adf_remove,
+	.sriov_configure = adf_sriov_configure,
+	.err_handler = &adf_err_handler,
+};
+
+module_pci_driver(adf_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Intel");
+MODULE_FIRMWARE(ADF_420XX_FW);
+MODULE_FIRMWARE(ADF_420XX_MMP);
+MODULE_DESCRIPTION("Intel(R) QuickAssist Technology");
+MODULE_VERSION(ADF_DRV_VERSION);
+MODULE_SOFTDEP("pre: crypto-intel_qat");
+MODULE_IMPORT_NS(CRYPTO_QAT);
diff --git a/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c b/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c
index 0faedb5b2eb5..479062aa5e6b 100644
--- a/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c
+++ b/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c
@@ -7,12 +7,15 @@
 #include <adf_cfg_services.h>
 #include <adf_clock.h>
 #include <adf_common_drv.h>
+#include <adf_fw_config.h>
+#include <adf_gen4_config.h>
 #include <adf_gen4_dc.h>
 #include <adf_gen4_hw_data.h>
 #include <adf_gen4_pfvf.h>
 #include <adf_gen4_pm.h>
 #include "adf_gen4_ras.h"
 #include <adf_gen4_timer.h>
+#include <adf_gen4_tl.h>
 #include "adf_4xxx_hw_data.h"
 #include "icp_qat_hw.h"
 
@@ -20,12 +23,10 @@
 #define ADF_AE_GROUP_1		GENMASK(7, 4)
 #define ADF_AE_GROUP_2		BIT(8)
 
-enum adf_fw_objs {
-	ADF_FW_SYM_OBJ,
-	ADF_FW_ASYM_OBJ,
-	ADF_FW_DC_OBJ,
-	ADF_FW_ADMIN_OBJ,
-};
+#define ENA_THD_MASK_ASYM	GENMASK(1, 0)
+#define ENA_THD_MASK_ASYM_401XX	GENMASK(5, 0)
+#define ENA_THD_MASK_SYM	GENMASK(6, 0)
+#define ENA_THD_MASK_DC		GENMASK(1, 0)
 
 static const char * const adf_4xxx_fw_objs[] = {
 	[ADF_FW_SYM_OBJ] =  ADF_4XXX_SYM_OBJ,
@@ -41,11 +42,6 @@ static const char * const adf_402xx_fw_objs[] = {
 	[ADF_FW_ADMIN_OBJ] = ADF_402XX_ADMIN_OBJ,
 };
 
-struct adf_fw_config {
-	u32 ae_mask;
-	enum adf_fw_objs obj;
-};
-
 static const struct adf_fw_config adf_fw_cy_config[] = {
 	{ADF_AE_GROUP_1, ADF_FW_SYM_OBJ},
 	{ADF_AE_GROUP_0, ADF_FW_ASYM_OBJ},
@@ -95,59 +91,12 @@ static_assert(ARRAY_SIZE(adf_fw_cy_config) == ARRAY_SIZE(adf_fw_asym_dc_config))
 static_assert(ARRAY_SIZE(adf_fw_cy_config) == ARRAY_SIZE(adf_fw_sym_dc_config));
 static_assert(ARRAY_SIZE(adf_fw_cy_config) == ARRAY_SIZE(adf_fw_dcc_config));
 
-/* Worker thread to service arbiter mappings */
-static const u32 default_thrd_to_arb_map[ADF_4XXX_MAX_ACCELENGINES] = {
-	0x5555555, 0x5555555, 0x5555555, 0x5555555,
-	0xAAAAAAA, 0xAAAAAAA, 0xAAAAAAA, 0xAAAAAAA,
-	0x0
-};
-
-static const u32 thrd_to_arb_map_dc[ADF_4XXX_MAX_ACCELENGINES] = {
-	0x000000FF, 0x000000FF, 0x000000FF, 0x000000FF,
-	0x000000FF, 0x000000FF, 0x000000FF, 0x000000FF,
-	0x0
-};
-
-static const u32 thrd_to_arb_map_dcc[ADF_4XXX_MAX_ACCELENGINES] = {
-	0x00000000, 0x00000000, 0x00000000, 0x00000000,
-	0x0000FFFF, 0x0000FFFF, 0x0000FFFF, 0x0000FFFF,
-	0x0
-};
-
 static struct adf_hw_device_class adf_4xxx_class = {
 	.name = ADF_4XXX_DEVICE_NAME,
 	.type = DEV_4XXX,
 	.instances = 0,
 };
 
-static int get_service_enabled(struct adf_accel_dev *accel_dev)
-{
-	char services[ADF_CFG_MAX_VAL_LEN_IN_BYTES] = {0};
-	int ret;
-
-	ret = adf_cfg_get_param_value(accel_dev, ADF_GENERAL_SEC,
-				      ADF_SERVICES_ENABLED, services);
-	if (ret) {
-		dev_err(&GET_DEV(accel_dev),
-			ADF_SERVICES_ENABLED " param not found\n");
-		return ret;
-	}
-
-	ret = match_string(adf_cfg_services, ARRAY_SIZE(adf_cfg_services),
-			   services);
-	if (ret < 0)
-		dev_err(&GET_DEV(accel_dev),
-			"Invalid value of " ADF_SERVICES_ENABLED " param: %s\n",
-			services);
-
-	return ret;
-}
-
-static u32 get_accel_mask(struct adf_hw_device_data *self)
-{
-	return ADF_4XXX_ACCELERATORS_MASK;
-}
-
 static u32 get_ae_mask(struct adf_hw_device_data *self)
 {
 	u32 me_disable = self->fuses;
@@ -155,55 +104,6 @@ static u32 get_ae_mask(struct adf_hw_device_data *self)
 	return ~me_disable & ADF_4XXX_ACCELENGINES_MASK;
 }
 
-static u32 get_num_accels(struct adf_hw_device_data *self)
-{
-	return ADF_4XXX_MAX_ACCELERATORS;
-}
-
-static u32 get_num_aes(struct adf_hw_device_data *self)
-{
-	if (!self || !self->ae_mask)
-		return 0;
-
-	return hweight32(self->ae_mask);
-}
-
-static u32 get_misc_bar_id(struct adf_hw_device_data *self)
-{
-	return ADF_4XXX_PMISC_BAR;
-}
-
-static u32 get_etr_bar_id(struct adf_hw_device_data *self)
-{
-	return ADF_4XXX_ETR_BAR;
-}
-
-static u32 get_sram_bar_id(struct adf_hw_device_data *self)
-{
-	return ADF_4XXX_SRAM_BAR;
-}
-
-/*
- * The vector routing table is used to select the MSI-X entry to use for each
- * interrupt source.
- * The first ADF_4XXX_ETR_MAX_BANKS entries correspond to ring interrupts.
- * The final entry corresponds to VF2PF or error interrupts.
- * This vector table could be used to configure one MSI-X entry to be shared
- * between multiple interrupt sources.
- *
- * The default routing is set to have a one to one correspondence between the
- * interrupt source and the MSI-X entry used.
- */
-static void set_msix_default_rttable(struct adf_accel_dev *accel_dev)
-{
-	void __iomem *csr;
-	int i;
-
-	csr = (&GET_BARS(accel_dev)[ADF_4XXX_PMISC_BAR])->virt_addr;
-	for (i = 0; i <= ADF_4XXX_ETR_MAX_BANKS; i++)
-		ADF_CSR_WR(csr, ADF_4XXX_MSIX_RTTABLE_OFFSET(i), i);
-}
-
 static u32 get_accel_cap(struct adf_accel_dev *accel_dev)
 {
 	struct pci_dev *pdev = accel_dev->accel_pci_dev.pci_dev;
@@ -212,7 +112,7 @@ static u32 get_accel_cap(struct adf_accel_dev *accel_dev)
 	u32 fusectl1;
 
 	/* Read accelerator capabilities mask */
-	pci_read_config_dword(pdev, ADF_4XXX_FUSECTL1_OFFSET, &fusectl1);
+	pci_read_config_dword(pdev, ADF_GEN4_FUSECTL1_OFFSET, &fusectl1);
 
 	capabilities_sym = ICP_ACCEL_CAPABILITIES_CRYPTO_SYMMETRIC |
 			  ICP_ACCEL_CAPABILITIES_CIPHER |
@@ -227,27 +127,27 @@ static u32 get_accel_cap(struct adf_accel_dev *accel_dev)
 			  ICP_ACCEL_CAPABILITIES_AES_V2;
 
 	/* A set bit in fusectl1 means the feature is OFF in this SKU */
-	if (fusectl1 & ICP_ACCEL_4XXX_MASK_CIPHER_SLICE) {
+	if (fusectl1 & ICP_ACCEL_GEN4_MASK_CIPHER_SLICE) {
 		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_CRYPTO_SYMMETRIC;
 		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_HKDF;
 		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_CIPHER;
 	}
 
-	if (fusectl1 & ICP_ACCEL_4XXX_MASK_UCS_SLICE) {
+	if (fusectl1 & ICP_ACCEL_GEN4_MASK_UCS_SLICE) {
 		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_CHACHA_POLY;
 		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_AESGCM_SPC;
 		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_AES_V2;
 		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_CIPHER;
 	}
 
-	if (fusectl1 & ICP_ACCEL_4XXX_MASK_AUTH_SLICE) {
+	if (fusectl1 & ICP_ACCEL_GEN4_MASK_AUTH_SLICE) {
 		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_AUTHENTICATION;
 		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_SHA3;
 		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_SHA3_EXT;
 		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_CIPHER;
 	}
 
-	if (fusectl1 & ICP_ACCEL_4XXX_MASK_SMX_SLICE) {
+	if (fusectl1 & ICP_ACCEL_GEN4_MASK_SMX_SLICE) {
 		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_SM3;
 		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_SM4;
 	}
@@ -257,7 +157,7 @@ static u32 get_accel_cap(struct adf_accel_dev *accel_dev)
 			  ICP_ACCEL_CAPABILITIES_SM2 |
 			  ICP_ACCEL_CAPABILITIES_ECEDMONT;
 
-	if (fusectl1 & ICP_ACCEL_4XXX_MASK_PKE_SLICE) {
+	if (fusectl1 & ICP_ACCEL_GEN4_MASK_PKE_SLICE) {
 		capabilities_asym &= ~ICP_ACCEL_CAPABILITIES_CRYPTO_ASYMMETRIC;
 		capabilities_asym &= ~ICP_ACCEL_CAPABILITIES_SM2;
 		capabilities_asym &= ~ICP_ACCEL_CAPABILITIES_ECEDMONT;
@@ -268,14 +168,14 @@ static u32 get_accel_cap(struct adf_accel_dev *accel_dev)
 			  ICP_ACCEL_CAPABILITIES_LZ4S_COMPRESSION |
 			  ICP_ACCEL_CAPABILITIES_CNV_INTEGRITY64;
 
-	if (fusectl1 & ICP_ACCEL_4XXX_MASK_COMPRESS_SLICE) {
+	if (fusectl1 & ICP_ACCEL_GEN4_MASK_COMPRESS_SLICE) {
 		capabilities_dc &= ~ICP_ACCEL_CAPABILITIES_COMPRESSION;
 		capabilities_dc &= ~ICP_ACCEL_CAPABILITIES_LZ4_COMPRESSION;
 		capabilities_dc &= ~ICP_ACCEL_CAPABILITIES_LZ4S_COMPRESSION;
 		capabilities_dc &= ~ICP_ACCEL_CAPABILITIES_CNV_INTEGRITY64;
 	}
 
-	switch (get_service_enabled(accel_dev)) {
+	switch (adf_get_service_enabled(accel_dev)) {
 	case SVC_CY:
 	case SVC_CY2:
 		return capabilities_sym | capabilities_asym;
@@ -304,43 +204,13 @@ static u32 get_accel_cap(struct adf_accel_dev *accel_dev)
 	}
 }
 
-static enum dev_sku_info get_sku(struct adf_hw_device_data *self)
-{
-	return DEV_SKU_1;
-}
-
 static const u32 *adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev)
 {
-	switch (get_service_enabled(accel_dev)) {
-	case SVC_DC:
-		return thrd_to_arb_map_dc;
-	case SVC_DCC:
-		return thrd_to_arb_map_dcc;
-	default:
-		return default_thrd_to_arb_map;
-	}
-}
-
-static void get_arb_info(struct arb_info *arb_info)
-{
-	arb_info->arb_cfg = ADF_4XXX_ARB_CONFIG;
-	arb_info->arb_offset = ADF_4XXX_ARB_OFFSET;
-	arb_info->wt2sam_offset = ADF_4XXX_ARB_WRK_2_SER_MAP_OFFSET;
-}
+	if (adf_gen4_init_thd2arb_map(accel_dev))
+		dev_warn(&GET_DEV(accel_dev),
+			 "Generate of the thread to arbiter map failed");
 
-static void get_admin_info(struct admin_info *admin_csrs_info)
-{
-	admin_csrs_info->mailbox_offset = ADF_4XXX_MAILBOX_BASE_OFFSET;
-	admin_csrs_info->admin_msg_ur = ADF_4XXX_ADMINMSGUR_OFFSET;
-	admin_csrs_info->admin_msg_lr = ADF_4XXX_ADMINMSGLR_OFFSET;
-}
-
-static u32 get_heartbeat_clock(struct adf_hw_device_data *self)
-{
-	/*
-	 * 4XXX uses KPT counter for HB
-	 */
-	return ADF_4XXX_KPT_COUNTER_FREQ;
+	return GET_HW_DATA(accel_dev)->thd_to_arb_map;
 }
 
 static void adf_init_rl_data(struct adf_rl_hw_data *rl_data)
@@ -361,66 +231,14 @@ static void adf_init_rl_data(struct adf_rl_hw_data *rl_data)
 	rl_data->scale_ref = ADF_4XXX_RL_SLICE_REF;
 }
 
-static void adf_enable_error_correction(struct adf_accel_dev *accel_dev)
-{
-	struct adf_bar *misc_bar = &GET_BARS(accel_dev)[ADF_4XXX_PMISC_BAR];
-	void __iomem *csr = misc_bar->virt_addr;
-
-	/* Enable all in errsou3 except VFLR notification on host */
-	ADF_CSR_WR(csr, ADF_GEN4_ERRMSK3, ADF_GEN4_VFLNOTIFY);
-}
-
-static void adf_enable_ints(struct adf_accel_dev *accel_dev)
-{
-	void __iomem *addr;
-
-	addr = (&GET_BARS(accel_dev)[ADF_4XXX_PMISC_BAR])->virt_addr;
-
-	/* Enable bundle interrupts */
-	ADF_CSR_WR(addr, ADF_4XXX_SMIAPF_RP_X0_MASK_OFFSET, 0);
-	ADF_CSR_WR(addr, ADF_4XXX_SMIAPF_RP_X1_MASK_OFFSET, 0);
-
-	/* Enable misc interrupts */
-	ADF_CSR_WR(addr, ADF_4XXX_SMIAPF_MASK_OFFSET, 0);
-}
-
-static int adf_init_device(struct adf_accel_dev *accel_dev)
-{
-	void __iomem *addr;
-	u32 status;
-	u32 csr;
-	int ret;
-
-	addr = (&GET_BARS(accel_dev)[ADF_4XXX_PMISC_BAR])->virt_addr;
-
-	/* Temporarily mask PM interrupt */
-	csr = ADF_CSR_RD(addr, ADF_GEN4_ERRMSK2);
-	csr |= ADF_GEN4_PM_SOU;
-	ADF_CSR_WR(addr, ADF_GEN4_ERRMSK2, csr);
-
-	/* Set DRV_ACTIVE bit to power up the device */
-	ADF_CSR_WR(addr, ADF_GEN4_PM_INTERRUPT, ADF_GEN4_PM_DRV_ACTIVE);
-
-	/* Poll status register to make sure the device is powered up */
-	ret = read_poll_timeout(ADF_CSR_RD, status,
-				status & ADF_GEN4_PM_INIT_STATE,
-				ADF_GEN4_PM_POLL_DELAY_US,
-				ADF_GEN4_PM_POLL_TIMEOUT_US, true, addr,
-				ADF_GEN4_PM_STATUS);
-	if (ret)
-		dev_err(&GET_DEV(accel_dev), "Failed to power up the device\n");
-
-	return ret;
-}
-
-static u32 uof_get_num_objs(void)
+static u32 uof_get_num_objs(struct adf_accel_dev *accel_dev)
 {
 	return ARRAY_SIZE(adf_fw_cy_config);
 }
 
 static const struct adf_fw_config *get_fw_config(struct adf_accel_dev *accel_dev)
 {
-	switch (get_service_enabled(accel_dev)) {
+	switch (adf_get_service_enabled(accel_dev)) {
 	case SVC_CY:
 	case SVC_CY2:
 		return adf_fw_cy_config;
@@ -443,11 +261,64 @@ static const struct adf_fw_config *get_fw_config(struct adf_accel_dev *accel_dev
 	}
 }
 
-enum adf_rp_groups {
-	RP_GROUP_0 = 0,
-	RP_GROUP_1,
-	RP_GROUP_COUNT
-};
+static int get_rp_group(struct adf_accel_dev *accel_dev, u32 ae_mask)
+{
+	switch (ae_mask) {
+	case ADF_AE_GROUP_0:
+		return RP_GROUP_0;
+	case ADF_AE_GROUP_1:
+		return RP_GROUP_1;
+	default:
+		dev_dbg(&GET_DEV(accel_dev), "ae_mask not recognized");
+		return -EINVAL;
+	}
+}
+
+static u32 get_ena_thd_mask(struct adf_accel_dev *accel_dev, u32 obj_num)
+{
+	const struct adf_fw_config *fw_config;
+
+	if (obj_num >= uof_get_num_objs(accel_dev))
+		return ADF_GEN4_ENA_THD_MASK_ERROR;
+
+	fw_config = get_fw_config(accel_dev);
+	if (!fw_config)
+		return ADF_GEN4_ENA_THD_MASK_ERROR;
+
+	switch (fw_config[obj_num].obj) {
+	case ADF_FW_ASYM_OBJ:
+		return ENA_THD_MASK_ASYM;
+	case ADF_FW_SYM_OBJ:
+		return ENA_THD_MASK_SYM;
+	case ADF_FW_DC_OBJ:
+		return ENA_THD_MASK_DC;
+	default:
+		return ADF_GEN4_ENA_THD_MASK_ERROR;
+	}
+}
+
+static u32 get_ena_thd_mask_401xx(struct adf_accel_dev *accel_dev, u32 obj_num)
+{
+	const struct adf_fw_config *fw_config;
+
+	if (obj_num >= uof_get_num_objs(accel_dev))
+		return ADF_GEN4_ENA_THD_MASK_ERROR;
+
+	fw_config = get_fw_config(accel_dev);
+	if (!fw_config)
+		return ADF_GEN4_ENA_THD_MASK_ERROR;
+
+	switch (fw_config[obj_num].obj) {
+	case ADF_FW_ASYM_OBJ:
+		return ENA_THD_MASK_ASYM_401XX;
+	case ADF_FW_SYM_OBJ:
+		return ENA_THD_MASK_SYM;
+	case ADF_FW_DC_OBJ:
+		return ENA_THD_MASK_DC;
+	default:
+		return ADF_GEN4_ENA_THD_MASK_ERROR;
+	}
+}
 
 static u16 get_ring_to_svc_map(struct adf_accel_dev *accel_dev)
 {
@@ -553,54 +424,63 @@ void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data, u32 dev_id)
 {
 	hw_data->dev_class = &adf_4xxx_class;
 	hw_data->instance_id = adf_4xxx_class.instances++;
-	hw_data->num_banks = ADF_4XXX_ETR_MAX_BANKS;
-	hw_data->num_banks_per_vf = ADF_4XXX_NUM_BANKS_PER_VF;
-	hw_data->num_rings_per_bank = ADF_4XXX_NUM_RINGS_PER_BANK;
-	hw_data->num_accel = ADF_4XXX_MAX_ACCELERATORS;
+	hw_data->num_banks = ADF_GEN4_ETR_MAX_BANKS;
+	hw_data->num_banks_per_vf = ADF_GEN4_NUM_BANKS_PER_VF;
+	hw_data->num_rings_per_bank = ADF_GEN4_NUM_RINGS_PER_BANK;
+	hw_data->num_accel = ADF_GEN4_MAX_ACCELERATORS;
 	hw_data->num_engines = ADF_4XXX_MAX_ACCELENGINES;
 	hw_data->num_logical_accel = 1;
-	hw_data->tx_rx_gap = ADF_4XXX_RX_RINGS_OFFSET;
-	hw_data->tx_rings_mask = ADF_4XXX_TX_RINGS_MASK;
+	hw_data->tx_rx_gap = ADF_GEN4_RX_RINGS_OFFSET;
+	hw_data->tx_rings_mask = ADF_GEN4_TX_RINGS_MASK;
 	hw_data->ring_to_svc_map = ADF_GEN4_DEFAULT_RING_TO_SRV_MAP;
 	hw_data->alloc_irq = adf_isr_resource_alloc;
 	hw_data->free_irq = adf_isr_resource_free;
-	hw_data->enable_error_correction = adf_enable_error_correction;
-	hw_data->get_accel_mask = get_accel_mask;
+	hw_data->enable_error_correction = adf_gen4_enable_error_correction;
+	hw_data->get_accel_mask = adf_gen4_get_accel_mask;
 	hw_data->get_ae_mask = get_ae_mask;
-	hw_data->get_num_accels = get_num_accels;
-	hw_data->get_num_aes = get_num_aes;
-	hw_data->get_sram_bar_id = get_sram_bar_id;
-	hw_data->get_etr_bar_id = get_etr_bar_id;
-	hw_data->get_misc_bar_id = get_misc_bar_id;
-	hw_data->get_arb_info = get_arb_info;
-	hw_data->get_admin_info = get_admin_info;
+	hw_data->get_num_accels = adf_gen4_get_num_accels;
+	hw_data->get_num_aes = adf_gen4_get_num_aes;
+	hw_data->get_sram_bar_id = adf_gen4_get_sram_bar_id;
+	hw_data->get_etr_bar_id = adf_gen4_get_etr_bar_id;
+	hw_data->get_misc_bar_id = adf_gen4_get_misc_bar_id;
+	hw_data->get_arb_info = adf_gen4_get_arb_info;
+	hw_data->get_admin_info = adf_gen4_get_admin_info;
 	hw_data->get_accel_cap = get_accel_cap;
-	hw_data->get_sku = get_sku;
+	hw_data->get_sku = adf_gen4_get_sku;
 	hw_data->init_admin_comms = adf_init_admin_comms;
 	hw_data->exit_admin_comms = adf_exit_admin_comms;
 	hw_data->send_admin_init = adf_send_admin_init;
 	hw_data->init_arb = adf_init_arb;
 	hw_data->exit_arb = adf_exit_arb;
 	hw_data->get_arb_mapping = adf_get_arbiter_mapping;
-	hw_data->enable_ints = adf_enable_ints;
-	hw_data->init_device = adf_init_device;
+	hw_data->enable_ints = adf_gen4_enable_ints;
+	hw_data->init_device = adf_gen4_init_device;
 	hw_data->reset_device = adf_reset_flr;
 	hw_data->admin_ae_mask = ADF_4XXX_ADMIN_AE_MASK;
+	hw_data->num_rps = ADF_GEN4_MAX_RPS;
 	switch (dev_id) {
 	case ADF_402XX_PCI_DEVICE_ID:
 		hw_data->fw_name = ADF_402XX_FW;
 		hw_data->fw_mmp_name = ADF_402XX_MMP;
 		hw_data->uof_get_name = uof_get_name_402xx;
 		break;
-
+	case ADF_401XX_PCI_DEVICE_ID:
+		hw_data->fw_name = ADF_4XXX_FW;
+		hw_data->fw_mmp_name = ADF_4XXX_MMP;
+		hw_data->uof_get_name = uof_get_name_4xxx;
+		hw_data->get_ena_thd_mask = get_ena_thd_mask_401xx;
+		break;
 	default:
 		hw_data->fw_name = ADF_4XXX_FW;
 		hw_data->fw_mmp_name = ADF_4XXX_MMP;
 		hw_data->uof_get_name = uof_get_name_4xxx;
+		hw_data->get_ena_thd_mask = get_ena_thd_mask;
+		break;
 	}
 	hw_data->uof_get_num_objs = uof_get_num_objs;
 	hw_data->uof_get_ae_mask = uof_get_ae_mask;
-	hw_data->set_msix_rttable = set_msix_default_rttable;
+	hw_data->get_rp_group = get_rp_group;
+	hw_data->set_msix_rttable = adf_gen4_set_msix_default_rttable;
 	hw_data->set_ssm_wdtimer = adf_gen4_set_ssm_wdtimer;
 	hw_data->get_ring_to_svc_map = get_ring_to_svc_map;
 	hw_data->disable_iov = adf_disable_sriov;
@@ -610,7 +490,7 @@ void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data, u32 dev_id)
 	hw_data->dev_config = adf_gen4_dev_config;
 	hw_data->start_timer = adf_gen4_timer_start;
 	hw_data->stop_timer = adf_gen4_timer_stop;
-	hw_data->get_hb_clock = get_heartbeat_clock;
+	hw_data->get_hb_clock = adf_gen4_get_heartbeat_clock;
 	hw_data->num_hb_ctrs = ADF_NUM_HB_CNT_PER_AE;
 	hw_data->clock_frequency = ADF_4XXX_AE_FREQ;
 
@@ -619,6 +499,7 @@ void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data, u32 dev_id)
 	adf_gen4_init_pf_pfvf_ops(&hw_data->pfvf_ops);
 	adf_gen4_init_dc_ops(&hw_data->dc_ops);
 	adf_gen4_init_ras_ops(&hw_data->ras_ops);
+	adf_gen4_init_tl_data(&hw_data->tl_data);
 	adf_init_rl_data(&hw_data->rl_data);
 }
 
diff --git a/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.h b/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.h
index 33423295e90f..76388363ea87 100644
--- a/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.h
+++ b/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.h
@@ -6,25 +6,8 @@
 #include <linux/units.h>
 #include <adf_accel_devices.h>
 
-/* PCIe configuration space */
-#define ADF_4XXX_SRAM_BAR		0
-#define ADF_4XXX_PMISC_BAR		1
-#define ADF_4XXX_ETR_BAR		2
-#define ADF_4XXX_RX_RINGS_OFFSET	1
-#define ADF_4XXX_TX_RINGS_MASK		0x1
-#define ADF_4XXX_MAX_ACCELERATORS	1
 #define ADF_4XXX_MAX_ACCELENGINES	9
-#define ADF_4XXX_BAR_MASK		(BIT(0) | BIT(2) | BIT(4))
 
-/* Physical function fuses */
-#define ADF_4XXX_FUSECTL0_OFFSET	(0x2C8)
-#define ADF_4XXX_FUSECTL1_OFFSET	(0x2CC)
-#define ADF_4XXX_FUSECTL2_OFFSET	(0x2D0)
-#define ADF_4XXX_FUSECTL3_OFFSET	(0x2D4)
-#define ADF_4XXX_FUSECTL4_OFFSET	(0x2D8)
-#define ADF_4XXX_FUSECTL5_OFFSET	(0x2DC)
-
-#define ADF_4XXX_ACCELERATORS_MASK	(0x1)
 #define ADF_4XXX_ACCELENGINES_MASK	(0x1FF)
 #define ADF_4XXX_ADMIN_AE_MASK		(0x100)
 
@@ -45,28 +28,6 @@
 	(BIT(4) | BIT(12) | BIT(16) | BIT(17) | BIT(18) | \
 	 BIT(19) | BIT(20) | BIT(21) | BIT(22) | BIT(23))
 
-#define ADF_4XXX_ETR_MAX_BANKS		64
-
-/* MSIX interrupt */
-#define ADF_4XXX_SMIAPF_RP_X0_MASK_OFFSET	(0x41A040)
-#define ADF_4XXX_SMIAPF_RP_X1_MASK_OFFSET	(0x41A044)
-#define ADF_4XXX_SMIAPF_MASK_OFFSET		(0x41A084)
-#define ADF_4XXX_MSIX_RTTABLE_OFFSET(i)		(0x409000 + ((i) * 0x04))
-
-/* Bank and ring configuration */
-#define ADF_4XXX_NUM_RINGS_PER_BANK	2
-#define ADF_4XXX_NUM_BANKS_PER_VF	4
-
-/* Arbiter configuration */
-#define ADF_4XXX_ARB_CONFIG			(BIT(31) | BIT(6) | BIT(0))
-#define ADF_4XXX_ARB_OFFSET			(0x0)
-#define ADF_4XXX_ARB_WRK_2_SER_MAP_OFFSET	(0x400)
-
-/* Admin Interface Reg Offset */
-#define ADF_4XXX_ADMINMSGUR_OFFSET	(0x500574)
-#define ADF_4XXX_ADMINMSGLR_OFFSET	(0x500578)
-#define ADF_4XXX_MAILBOX_BASE_OFFSET	(0x600970)
-
 /* Firmware Binaries */
 #define ADF_4XXX_FW		"qat_4xxx.bin"
 #define ADF_4XXX_MMP		"qat_4xxx_mmp.bin"
@@ -93,22 +54,9 @@
 #define ADF_4XXX_RL_SLICE_REF			1000UL
 
 /* Clocks frequency */
-#define ADF_4XXX_KPT_COUNTER_FREQ	(100 * HZ_PER_MHZ)
 #define ADF_4XXX_AE_FREQ		(1000 * HZ_PER_MHZ)
 
-/* qat_4xxx fuse bits are different from old GENs, redefine them */
-enum icp_qat_4xxx_slice_mask {
-	ICP_ACCEL_4XXX_MASK_CIPHER_SLICE = BIT(0),
-	ICP_ACCEL_4XXX_MASK_AUTH_SLICE = BIT(1),
-	ICP_ACCEL_4XXX_MASK_PKE_SLICE = BIT(2),
-	ICP_ACCEL_4XXX_MASK_COMPRESS_SLICE = BIT(3),
-	ICP_ACCEL_4XXX_MASK_UCS_SLICE = BIT(4),
-	ICP_ACCEL_4XXX_MASK_EIA3_SLICE = BIT(5),
-	ICP_ACCEL_4XXX_MASK_SMX_SLICE = BIT(7),
-};
-
 void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data, u32 dev_id);
 void adf_clean_hw_data_4xxx(struct adf_hw_device_data *hw_data);
-int adf_gen4_dev_config(struct adf_accel_dev *accel_dev);
 
 #endif
diff --git a/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c b/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c
index 8f483d1197dd..9762f2bf7727 100644
--- a/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c
+++ b/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c
@@ -8,13 +8,10 @@
 #include <adf_cfg.h>
 #include <adf_common_drv.h>
 #include <adf_dbgfs.h>
-#include <adf_heartbeat.h>
+#include <adf_gen4_config.h>
+#include <adf_gen4_hw_data.h>
 
 #include "adf_4xxx_hw_data.h"
-#include "adf_cfg_services.h"
-#include "qat_compression.h"
-#include "qat_crypto.h"
-#include "adf_transport_access_macros.h"
 
 static const struct pci_device_id adf_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, ADF_4XXX_PCI_DEVICE_ID), },
@@ -35,270 +32,6 @@ static void adf_cleanup_accel(struct adf_accel_dev *accel_dev)
 	adf_devmgr_rm_dev(accel_dev, NULL);
 }
 
-static int adf_cfg_dev_init(struct adf_accel_dev *accel_dev)
-{
-	const char *config;
-	int ret;
-
-	config = accel_dev->accel_id % 2 ? ADF_CFG_DC : ADF_CFG_CY;
-
-	ret = adf_cfg_section_add(accel_dev, ADF_GENERAL_SEC);
-	if (ret)
-		return ret;
-
-	/* Default configuration is crypto only for even devices
-	 * and compression for odd devices
-	 */
-	ret = adf_cfg_add_key_value_param(accel_dev, ADF_GENERAL_SEC,
-					  ADF_SERVICES_ENABLED, config,
-					  ADF_STR);
-	if (ret)
-		return ret;
-
-	adf_heartbeat_save_cfg_param(accel_dev, ADF_CFG_HB_TIMER_MIN_MS);
-
-	return 0;
-}
-
-static int adf_crypto_dev_config(struct adf_accel_dev *accel_dev)
-{
-	char key[ADF_CFG_MAX_KEY_LEN_IN_BYTES];
-	int banks = GET_MAX_BANKS(accel_dev);
-	int cpus = num_online_cpus();
-	unsigned long bank, val;
-	int instances;
-	int ret;
-	int i;
-
-	if (adf_hw_dev_has_crypto(accel_dev))
-		instances = min(cpus, banks / 2);
-	else
-		instances = 0;
-
-	for (i = 0; i < instances; i++) {
-		val = i;
-		bank = i * 2;
-		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_BANK_NUM, i);
-		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						  key, &bank, ADF_DEC);
-		if (ret)
-			goto err;
-
-		bank += 1;
-		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_BANK_NUM, i);
-		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						  key, &bank, ADF_DEC);
-		if (ret)
-			goto err;
-
-		snprintf(key, sizeof(key), ADF_CY "%d" ADF_ETRMGR_CORE_AFFINITY,
-			 i);
-		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						  key, &val, ADF_DEC);
-		if (ret)
-			goto err;
-
-		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_SIZE, i);
-		val = 128;
-		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						  key, &val, ADF_DEC);
-		if (ret)
-			goto err;
-
-		val = 512;
-		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_SIZE, i);
-		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						  key, &val, ADF_DEC);
-		if (ret)
-			goto err;
-
-		val = 0;
-		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_TX, i);
-		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						  key, &val, ADF_DEC);
-		if (ret)
-			goto err;
-
-		val = 0;
-		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_TX, i);
-		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						  key, &val, ADF_DEC);
-		if (ret)
-			goto err;
-
-		val = 1;
-		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_RX, i);
-		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						  key, &val, ADF_DEC);
-		if (ret)
-			goto err;
-
-		val = 1;
-		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_RX, i);
-		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						  key, &val, ADF_DEC);
-		if (ret)
-			goto err;
-
-		val = ADF_COALESCING_DEF_TIME;
-		snprintf(key, sizeof(key), ADF_ETRMGR_COALESCE_TIMER_FORMAT, i);
-		ret = adf_cfg_add_key_value_param(accel_dev, "Accelerator0",
-						  key, &val, ADF_DEC);
-		if (ret)
-			goto err;
-	}
-
-	val = i;
-	ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, ADF_NUM_CY,
-					  &val, ADF_DEC);
-	if (ret)
-		goto err;
-
-	val = 0;
-	ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, ADF_NUM_DC,
-					  &val, ADF_DEC);
-	if (ret)
-		goto err;
-
-	return 0;
-err:
-	dev_err(&GET_DEV(accel_dev), "Failed to add configuration for crypto\n");
-	return ret;
-}
-
-static int adf_comp_dev_config(struct adf_accel_dev *accel_dev)
-{
-	char key[ADF_CFG_MAX_KEY_LEN_IN_BYTES];
-	int banks = GET_MAX_BANKS(accel_dev);
-	int cpus = num_online_cpus();
-	unsigned long val;
-	int instances;
-	int ret;
-	int i;
-
-	if (adf_hw_dev_has_compression(accel_dev))
-		instances = min(cpus, banks);
-	else
-		instances = 0;
-
-	for (i = 0; i < instances; i++) {
-		val = i;
-		snprintf(key, sizeof(key), ADF_DC "%d" ADF_RING_DC_BANK_NUM, i);
-		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						  key, &val, ADF_DEC);
-		if (ret)
-			goto err;
-
-		val = 512;
-		snprintf(key, sizeof(key), ADF_DC "%d" ADF_RING_DC_SIZE, i);
-		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						  key, &val, ADF_DEC);
-		if (ret)
-			goto err;
-
-		val = 0;
-		snprintf(key, sizeof(key), ADF_DC "%d" ADF_RING_DC_TX, i);
-		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						  key, &val, ADF_DEC);
-		if (ret)
-			goto err;
-
-		val = 1;
-		snprintf(key, sizeof(key), ADF_DC "%d" ADF_RING_DC_RX, i);
-		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						  key, &val, ADF_DEC);
-		if (ret)
-			goto err;
-
-		val = ADF_COALESCING_DEF_TIME;
-		snprintf(key, sizeof(key), ADF_ETRMGR_COALESCE_TIMER_FORMAT, i);
-		ret = adf_cfg_add_key_value_param(accel_dev, "Accelerator0",
-						  key, &val, ADF_DEC);
-		if (ret)
-			goto err;
-	}
-
-	val = i;
-	ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, ADF_NUM_DC,
-					  &val, ADF_DEC);
-	if (ret)
-		goto err;
-
-	val = 0;
-	ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, ADF_NUM_CY,
-					  &val, ADF_DEC);
-	if (ret)
-		goto err;
-
-	return 0;
-err:
-	dev_err(&GET_DEV(accel_dev), "Failed to add configuration for compression\n");
-	return ret;
-}
-
-static int adf_no_dev_config(struct adf_accel_dev *accel_dev)
-{
-	unsigned long val;
-	int ret;
-
-	val = 0;
-	ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, ADF_NUM_DC,
-					  &val, ADF_DEC);
-	if (ret)
-		return ret;
-
-	return adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, ADF_NUM_CY,
-					  &val, ADF_DEC);
-}
-
-int adf_gen4_dev_config(struct adf_accel_dev *accel_dev)
-{
-	char services[ADF_CFG_MAX_VAL_LEN_IN_BYTES] = {0};
-	int ret;
-
-	ret = adf_cfg_section_add(accel_dev, ADF_KERNEL_SEC);
-	if (ret)
-		goto err;
-
-	ret = adf_cfg_section_add(accel_dev, "Accelerator0");
-	if (ret)
-		goto err;
-
-	ret = adf_cfg_get_param_value(accel_dev, ADF_GENERAL_SEC,
-				      ADF_SERVICES_ENABLED, services);
-	if (ret)
-		goto err;
-
-	ret = sysfs_match_string(adf_cfg_services, services);
-	if (ret < 0)
-		goto err;
-
-	switch (ret) {
-	case SVC_CY:
-	case SVC_CY2:
-		ret = adf_crypto_dev_config(accel_dev);
-		break;
-	case SVC_DC:
-	case SVC_DCC:
-		ret = adf_comp_dev_config(accel_dev);
-		break;
-	default:
-		ret = adf_no_dev_config(accel_dev);
-		break;
-	}
-
-	if (ret)
-		goto err;
-
-	set_bit(ADF_STATUS_CONFIGURED, &accel_dev->status);
-
-	return ret;
-
-err:
-	dev_err(&GET_DEV(accel_dev), "Failed to configure QAT driver\n");
-	return ret;
-}
-
 static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct adf_accel_dev *accel_dev;
@@ -348,7 +81,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	adf_init_hw_data_4xxx(accel_dev->hw_device, ent->device);
 
 	pci_read_config_byte(pdev, PCI_REVISION_ID, &accel_pci_dev->revid);
-	pci_read_config_dword(pdev, ADF_4XXX_FUSECTL4_OFFSET, &hw_data->fuses);
+	pci_read_config_dword(pdev, ADF_GEN4_FUSECTL4_OFFSET, &hw_data->fuses);
 
 	/* Get Accelerators and Accelerators Engines masks */
 	hw_data->accel_mask = hw_data->get_accel_mask(hw_data);
@@ -381,7 +114,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto out_err;
 	}
 
-	ret = adf_cfg_dev_init(accel_dev);
+	ret = adf_gen4_cfg_dev_init(accel_dev);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to initialize configuration.\n");
 		goto out_err;
@@ -396,7 +129,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	/* Find and map all the device's BARS */
-	bar_mask = pci_select_bars(pdev, IORESOURCE_MEM) & ADF_4XXX_BAR_MASK;
+	bar_mask = pci_select_bars(pdev, IORESOURCE_MEM) & ADF_GEN4_BAR_MASK;
 
 	ret = pcim_iomap_regions_request_all(pdev, bar_mask, pci_name(pdev));
 	if (ret) {
diff --git a/drivers/crypto/intel/qat/qat_common/Makefile b/drivers/crypto/intel/qat/qat_common/Makefile
index 779a8aa0b8d2..6908727bff3b 100644
--- a/drivers/crypto/intel/qat/qat_common/Makefile
+++ b/drivers/crypto/intel/qat/qat_common/Makefile
@@ -16,6 +16,7 @@ intel_qat-objs := adf_cfg.o \
 	adf_sysfs_ras_counters.o \
 	adf_gen2_hw_data.o \
 	adf_gen2_config.o \
+	adf_gen4_config.o \
 	adf_gen4_hw_data.o \
 	adf_gen4_pm.o \
 	adf_gen2_dc.o \
@@ -40,9 +41,12 @@ intel_qat-$(CONFIG_DEBUG_FS) += adf_transport_debug.o \
 				adf_fw_counters.o \
 				adf_cnv_dbgfs.o \
 				adf_gen4_pm_debugfs.o \
+				adf_gen4_tl.o \
 				adf_heartbeat.o \
 				adf_heartbeat_dbgfs.o \
 				adf_pm_dbgfs.o \
+				adf_telemetry.o \
+				adf_tl_debugfs.o \
 				adf_dbgfs.o
 
 intel_qat-$(CONFIG_PCI_IOV) += adf_sriov.o adf_vf_isr.o adf_pfvf_utils.o \
diff --git a/drivers/crypto/intel/qat/qat_common/adf_accel_devices.h b/drivers/crypto/intel/qat/qat_common/adf_accel_devices.h
index 4ff5729a3496..a16c7e6edc65 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_accel_devices.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_accel_devices.h
@@ -6,11 +6,14 @@
 #include <linux/module.h>
 #include <linux/list.h>
 #include <linux/io.h>
+#include <linux/pci.h>
 #include <linux/ratelimit.h>
 #include <linux/types.h>
 #include "adf_cfg_common.h"
 #include "adf_rl.h"
+#include "adf_telemetry.h"
 #include "adf_pfvf_msg.h"
+#include "icp_qat_hw.h"
 
 #define ADF_DH895XCC_DEVICE_NAME "dh895xcc"
 #define ADF_DH895XCCVF_DEVICE_NAME "dh895xccvf"
@@ -19,12 +22,15 @@
 #define ADF_C3XXX_DEVICE_NAME "c3xxx"
 #define ADF_C3XXXVF_DEVICE_NAME "c3xxxvf"
 #define ADF_4XXX_DEVICE_NAME "4xxx"
+#define ADF_420XX_DEVICE_NAME "420xx"
 #define ADF_4XXX_PCI_DEVICE_ID 0x4940
 #define ADF_4XXXIOV_PCI_DEVICE_ID 0x4941
 #define ADF_401XX_PCI_DEVICE_ID 0x4942
 #define ADF_401XXIOV_PCI_DEVICE_ID 0x4943
 #define ADF_402XX_PCI_DEVICE_ID 0x4944
 #define ADF_402XXIOV_PCI_DEVICE_ID 0x4945
+#define ADF_420XX_PCI_DEVICE_ID 0x4946
+#define ADF_420XXIOV_PCI_DEVICE_ID 0x4947
 #define ADF_DEVICE_FUSECTL_OFFSET 0x40
 #define ADF_DEVICE_LEGFUSE_OFFSET 0x4C
 #define ADF_DEVICE_FUSECTL_MASK 0x80000000
@@ -92,6 +98,7 @@ enum ras_errors {
 
 struct adf_error_counters {
 	atomic_t counter[ADF_RAS_ERRORS];
+	bool sysfs_added;
 	bool enabled;
 };
 
@@ -240,8 +247,10 @@ struct adf_hw_device_data {
 	void (*reset_device)(struct adf_accel_dev *accel_dev);
 	void (*set_msix_rttable)(struct adf_accel_dev *accel_dev);
 	const char *(*uof_get_name)(struct adf_accel_dev *accel_dev, u32 obj_num);
-	u32 (*uof_get_num_objs)(void);
+	u32 (*uof_get_num_objs)(struct adf_accel_dev *accel_dev);
 	u32 (*uof_get_ae_mask)(struct adf_accel_dev *accel_dev, u32 obj_num);
+	int (*get_rp_group)(struct adf_accel_dev *accel_dev, u32 ae_mask);
+	u32 (*get_ena_thd_mask)(struct adf_accel_dev *accel_dev, u32 obj_num);
 	int (*dev_config)(struct adf_accel_dev *accel_dev);
 	struct adf_pfvf_ops pfvf_ops;
 	struct adf_hw_csr_ops csr_ops;
@@ -249,6 +258,7 @@ struct adf_hw_device_data {
 	struct adf_ras_ops ras_ops;
 	struct adf_dev_err_mask dev_err_mask;
 	struct adf_rl_hw_data rl_data;
+	struct adf_tl_hw_data tl_data;
 	const char *fw_name;
 	const char *fw_mmp_name;
 	u32 fuses;
@@ -263,6 +273,7 @@ struct adf_hw_device_data {
 	u32 admin_ae_mask;
 	u16 tx_rings_mask;
 	u16 ring_to_svc_map;
+	u32 thd_to_arb_map[ICP_QAT_HW_AE_DELIMITER];
 	u8 tx_rx_gap;
 	u8 num_banks;
 	u16 num_banks_per_vf;
@@ -271,6 +282,7 @@ struct adf_hw_device_data {
 	u8 num_logical_accel;
 	u8 num_engines;
 	u32 num_hb_ctrs;
+	u8 num_rps;
 };
 
 /* CSR write macro */
@@ -303,6 +315,7 @@ struct adf_hw_device_data {
 #define GET_CSR_OPS(accel_dev) (&(accel_dev)->hw_device->csr_ops)
 #define GET_PFVF_OPS(accel_dev) (&(accel_dev)->hw_device->pfvf_ops)
 #define GET_DC_OPS(accel_dev) (&(accel_dev)->hw_device->dc_ops)
+#define GET_TL_DATA(accel_dev) GET_HW_DATA(accel_dev)->tl_data
 #define accel_to_pci_dev(accel_ptr) accel_ptr->accel_pci_dev.pci_dev
 
 struct adf_admin_comms;
@@ -351,6 +364,7 @@ struct adf_accel_dev {
 	struct adf_cfg_device_data *cfg;
 	struct adf_fw_loader_data *fw_loader;
 	struct adf_admin_comms *admin;
+	struct adf_telemetry *telemetry;
 	struct adf_dc_data *dc_data;
 	struct adf_pm power_management;
 	struct list_head crypto_list;
diff --git a/drivers/crypto/intel/qat/qat_common/adf_accel_engine.c b/drivers/crypto/intel/qat/qat_common/adf_accel_engine.c
index 6be064dc64c8..4b5d0350fc2e 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_accel_engine.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_accel_engine.c
@@ -19,7 +19,7 @@ static int adf_ae_fw_load_images(struct adf_accel_dev *accel_dev, void *fw_addr,
 	int i;
 
 	loader = loader_data->fw_loader;
-	num_objs = hw_device->uof_get_num_objs();
+	num_objs = hw_device->uof_get_num_objs(accel_dev);
 
 	for (i = 0; i < num_objs; i++) {
 		obj_name = hw_device->uof_get_name(accel_dev, i);
diff --git a/drivers/crypto/intel/qat/qat_common/adf_admin.c b/drivers/crypto/intel/qat/qat_common/adf_admin.c
index 54b673ec2362..acad526eb741 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_admin.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_admin.c
@@ -498,6 +498,43 @@ int adf_get_cnv_stats(struct adf_accel_dev *accel_dev, u16 ae, u16 *err_cnt,
 	return ret;
 }
 
+int adf_send_admin_tl_start(struct adf_accel_dev *accel_dev,
+			    dma_addr_t tl_dma_addr, size_t layout_sz, u8 *rp_indexes,
+			    struct icp_qat_fw_init_admin_slice_cnt *slice_count)
+{
+	u32 ae_mask = GET_HW_DATA(accel_dev)->admin_ae_mask;
+	struct icp_qat_fw_init_admin_resp resp = { };
+	struct icp_qat_fw_init_admin_req req = { };
+	int ret;
+
+	req.cmd_id = ICP_QAT_FW_TL_START;
+	req.init_cfg_ptr = tl_dma_addr;
+	req.init_cfg_sz = layout_sz;
+
+	if (rp_indexes)
+		memcpy(&req.rp_indexes, rp_indexes, sizeof(req.rp_indexes));
+
+	ret = adf_send_admin(accel_dev, &req, &resp, ae_mask);
+	if (ret)
+		return ret;
+
+	memcpy(slice_count, &resp.slices, sizeof(*slice_count));
+
+	return 0;
+}
+
+int adf_send_admin_tl_stop(struct adf_accel_dev *accel_dev)
+{
+	struct adf_hw_device_data *hw_data = GET_HW_DATA(accel_dev);
+	struct icp_qat_fw_init_admin_resp resp = { };
+	struct icp_qat_fw_init_admin_req req = { };
+	u32 ae_mask = hw_data->admin_ae_mask;
+
+	req.cmd_id = ICP_QAT_FW_TL_STOP;
+
+	return adf_send_admin(accel_dev, &req, &resp, ae_mask);
+}
+
 int adf_init_admin_comms(struct adf_accel_dev *accel_dev)
 {
 	struct adf_admin_comms *admin;
diff --git a/drivers/crypto/intel/qat/qat_common/adf_admin.h b/drivers/crypto/intel/qat/qat_common/adf_admin.h
index 55cbcbc66c9f..647c8e196752 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_admin.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_admin.h
@@ -23,5 +23,9 @@ int adf_send_admin_rl_delete(struct adf_accel_dev *accel_dev, u16 node_id,
 int adf_get_fw_timestamp(struct adf_accel_dev *accel_dev, u64 *timestamp);
 int adf_get_pm_info(struct adf_accel_dev *accel_dev, dma_addr_t p_state_addr, size_t buff_size);
 int adf_get_cnv_stats(struct adf_accel_dev *accel_dev, u16 ae, u16 *err_cnt, u16 *latest_err);
+int adf_send_admin_tl_start(struct adf_accel_dev *accel_dev,
+			    dma_addr_t tl_dma_addr, size_t layout_sz, u8 *rp_indexes,
+			    struct icp_qat_fw_init_admin_slice_cnt *slice_count);
+int adf_send_admin_tl_stop(struct adf_accel_dev *accel_dev);
 
 #endif
diff --git a/drivers/crypto/intel/qat/qat_common/adf_cfg_common.h b/drivers/crypto/intel/qat/qat_common/adf_cfg_common.h
index 6e5de1dab97b..89df3888d7ea 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_cfg_common.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_cfg_common.h
@@ -47,6 +47,7 @@ enum adf_device_type {
 	DEV_C3XXX,
 	DEV_C3XXXVF,
 	DEV_4XXX,
+	DEV_420XX,
 };
 
 struct adf_dev_status_info {
diff --git a/drivers/crypto/intel/qat/qat_common/adf_cfg_services.c b/drivers/crypto/intel/qat/qat_common/adf_cfg_services.c
index 8e13fe938959..268052294468 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_cfg_services.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_cfg_services.c
@@ -2,6 +2,9 @@
 /* Copyright(c) 2023 Intel Corporation */
 
 #include <linux/export.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+#include "adf_cfg.h"
 #include "adf_cfg_services.h"
 #include "adf_cfg_strings.h"
 
@@ -18,3 +21,27 @@ const char *const adf_cfg_services[] = {
 	[SVC_SYM_DC] = ADF_CFG_SYM_DC,
 };
 EXPORT_SYMBOL_GPL(adf_cfg_services);
+
+int adf_get_service_enabled(struct adf_accel_dev *accel_dev)
+{
+	char services[ADF_CFG_MAX_VAL_LEN_IN_BYTES] = {0};
+	int ret;
+
+	ret = adf_cfg_get_param_value(accel_dev, ADF_GENERAL_SEC,
+				      ADF_SERVICES_ENABLED, services);
+	if (ret) {
+		dev_err(&GET_DEV(accel_dev),
+			ADF_SERVICES_ENABLED " param not found\n");
+		return ret;
+	}
+
+	ret = match_string(adf_cfg_services, ARRAY_SIZE(adf_cfg_services),
+			   services);
+	if (ret < 0)
+		dev_err(&GET_DEV(accel_dev),
+			"Invalid value of " ADF_SERVICES_ENABLED " param: %s\n",
+			services);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(adf_get_service_enabled);
diff --git a/drivers/crypto/intel/qat/qat_common/adf_cfg_services.h b/drivers/crypto/intel/qat/qat_common/adf_cfg_services.h
index f78fd697b4be..c6b0328b0f5b 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_cfg_services.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_cfg_services.h
@@ -5,6 +5,8 @@
 
 #include "adf_cfg_strings.h"
 
+struct adf_accel_dev;
+
 enum adf_services {
 	SVC_CY = 0,
 	SVC_CY2,
@@ -21,4 +23,6 @@ enum adf_services {
 
 extern const char *const adf_cfg_services[SVC_COUNT];
 
+int adf_get_service_enabled(struct adf_accel_dev *accel_dev);
+
 #endif
diff --git a/drivers/crypto/intel/qat/qat_common/adf_dbgfs.c b/drivers/crypto/intel/qat/qat_common/adf_dbgfs.c
index 477efcc81a16..c42f5c25aabd 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_dbgfs.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_dbgfs.c
@@ -10,6 +10,7 @@
 #include "adf_fw_counters.h"
 #include "adf_heartbeat_dbgfs.h"
 #include "adf_pm_dbgfs.h"
+#include "adf_tl_debugfs.h"
 
 /**
  * adf_dbgfs_init() - add persistent debugfs entries
@@ -66,6 +67,7 @@ void adf_dbgfs_add(struct adf_accel_dev *accel_dev)
 		adf_heartbeat_dbgfs_add(accel_dev);
 		adf_pm_dbgfs_add(accel_dev);
 		adf_cnv_dbgfs_add(accel_dev);
+		adf_tl_dbgfs_add(accel_dev);
 	}
 }
 
@@ -79,6 +81,7 @@ void adf_dbgfs_rm(struct adf_accel_dev *accel_dev)
 		return;
 
 	if (!accel_dev->is_vf) {
+		adf_tl_dbgfs_rm(accel_dev);
 		adf_cnv_dbgfs_rm(accel_dev);
 		adf_pm_dbgfs_rm(accel_dev);
 		adf_heartbeat_dbgfs_rm(accel_dev);
diff --git a/drivers/crypto/intel/qat/qat_common/adf_fw_config.h b/drivers/crypto/intel/qat/qat_common/adf_fw_config.h
new file mode 100644
index 000000000000..4f86696800c9
--- /dev/null
+++ b/drivers/crypto/intel/qat/qat_common/adf_fw_config.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright(c) 2023 Intel Corporation */
+#ifndef ADF_FW_CONFIG_H_
+#define ADF_FW_CONFIG_H_
+
+enum adf_fw_objs {
+	ADF_FW_SYM_OBJ,
+	ADF_FW_ASYM_OBJ,
+	ADF_FW_DC_OBJ,
+	ADF_FW_ADMIN_OBJ,
+};
+
+struct adf_fw_config {
+	u32 ae_mask;
+	enum adf_fw_objs obj;
+};
+
+#endif
diff --git a/drivers/crypto/intel/qat/qat_common/adf_gen4_config.c b/drivers/crypto/intel/qat/qat_common/adf_gen4_config.c
new file mode 100644
index 000000000000..fe1f3d727dc5
--- /dev/null
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen4_config.c
@@ -0,0 +1,287 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2023 Intel Corporation */
+#include "adf_accel_devices.h"
+#include "adf_cfg.h"
+#include "adf_cfg_services.h"
+#include "adf_cfg_strings.h"
+#include "adf_common_drv.h"
+#include "adf_gen4_config.h"
+#include "adf_heartbeat.h"
+#include "adf_transport_access_macros.h"
+#include "qat_compression.h"
+#include "qat_crypto.h"
+
+static int adf_crypto_dev_config(struct adf_accel_dev *accel_dev)
+{
+	char key[ADF_CFG_MAX_KEY_LEN_IN_BYTES];
+	int banks = GET_MAX_BANKS(accel_dev);
+	int cpus = num_online_cpus();
+	unsigned long bank, val;
+	int instances;
+	int ret;
+	int i;
+
+	if (adf_hw_dev_has_crypto(accel_dev))
+		instances = min(cpus, banks / 2);
+	else
+		instances = 0;
+
+	for (i = 0; i < instances; i++) {
+		val = i;
+		bank = i * 2;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_BANK_NUM, i);
+		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						  key, &bank, ADF_DEC);
+		if (ret)
+			goto err;
+
+		bank += 1;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_BANK_NUM, i);
+		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						  key, &bank, ADF_DEC);
+		if (ret)
+			goto err;
+
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_ETRMGR_CORE_AFFINITY,
+			 i);
+		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						  key, &val, ADF_DEC);
+		if (ret)
+			goto err;
+
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_SIZE, i);
+		val = 128;
+		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						  key, &val, ADF_DEC);
+		if (ret)
+			goto err;
+
+		val = 512;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_SIZE, i);
+		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						  key, &val, ADF_DEC);
+		if (ret)
+			goto err;
+
+		val = 0;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_TX, i);
+		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						  key, &val, ADF_DEC);
+		if (ret)
+			goto err;
+
+		val = 0;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_TX, i);
+		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						  key, &val, ADF_DEC);
+		if (ret)
+			goto err;
+
+		val = 1;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_RX, i);
+		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						  key, &val, ADF_DEC);
+		if (ret)
+			goto err;
+
+		val = 1;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_RX, i);
+		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						  key, &val, ADF_DEC);
+		if (ret)
+			goto err;
+
+		val = ADF_COALESCING_DEF_TIME;
+		snprintf(key, sizeof(key), ADF_ETRMGR_COALESCE_TIMER_FORMAT, i);
+		ret = adf_cfg_add_key_value_param(accel_dev, "Accelerator0",
+						  key, &val, ADF_DEC);
+		if (ret)
+			goto err;
+	}
+
+	val = i;
+	ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, ADF_NUM_CY,
+					  &val, ADF_DEC);
+	if (ret)
+		goto err;
+
+	val = 0;
+	ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, ADF_NUM_DC,
+					  &val, ADF_DEC);
+	if (ret)
+		goto err;
+
+	return 0;
+err:
+	dev_err(&GET_DEV(accel_dev), "Failed to add configuration for crypto\n");
+	return ret;
+}
+
+static int adf_comp_dev_config(struct adf_accel_dev *accel_dev)
+{
+	char key[ADF_CFG_MAX_KEY_LEN_IN_BYTES];
+	int banks = GET_MAX_BANKS(accel_dev);
+	int cpus = num_online_cpus();
+	unsigned long val;
+	int instances;
+	int ret;
+	int i;
+
+	if (adf_hw_dev_has_compression(accel_dev))
+		instances = min(cpus, banks);
+	else
+		instances = 0;
+
+	for (i = 0; i < instances; i++) {
+		val = i;
+		snprintf(key, sizeof(key), ADF_DC "%d" ADF_RING_DC_BANK_NUM, i);
+		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						  key, &val, ADF_DEC);
+		if (ret)
+			goto err;
+
+		val = 512;
+		snprintf(key, sizeof(key), ADF_DC "%d" ADF_RING_DC_SIZE, i);
+		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						  key, &val, ADF_DEC);
+		if (ret)
+			goto err;
+
+		val = 0;
+		snprintf(key, sizeof(key), ADF_DC "%d" ADF_RING_DC_TX, i);
+		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						  key, &val, ADF_DEC);
+		if (ret)
+			goto err;
+
+		val = 1;
+		snprintf(key, sizeof(key), ADF_DC "%d" ADF_RING_DC_RX, i);
+		ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						  key, &val, ADF_DEC);
+		if (ret)
+			goto err;
+
+		val = ADF_COALESCING_DEF_TIME;
+		snprintf(key, sizeof(key), ADF_ETRMGR_COALESCE_TIMER_FORMAT, i);
+		ret = adf_cfg_add_key_value_param(accel_dev, "Accelerator0",
+						  key, &val, ADF_DEC);
+		if (ret)
+			goto err;
+	}
+
+	val = i;
+	ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, ADF_NUM_DC,
+					  &val, ADF_DEC);
+	if (ret)
+		goto err;
+
+	val = 0;
+	ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, ADF_NUM_CY,
+					  &val, ADF_DEC);
+	if (ret)
+		goto err;
+
+	return 0;
+err:
+	dev_err(&GET_DEV(accel_dev), "Failed to add configuration for compression\n");
+	return ret;
+}
+
+static int adf_no_dev_config(struct adf_accel_dev *accel_dev)
+{
+	unsigned long val;
+	int ret;
+
+	val = 0;
+	ret = adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, ADF_NUM_DC,
+					  &val, ADF_DEC);
+	if (ret)
+		return ret;
+
+	return adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, ADF_NUM_CY,
+					  &val, ADF_DEC);
+}
+
+/**
+ * adf_gen4_dev_config() - create dev config required to create instances
+ *
+ * @accel_dev: Pointer to acceleration device.
+ *
+ * Function creates device configuration required to create instances
+ *
+ * Return: 0 on success, error code otherwise.
+ */
+int adf_gen4_dev_config(struct adf_accel_dev *accel_dev)
+{
+	char services[ADF_CFG_MAX_VAL_LEN_IN_BYTES] = {0};
+	int ret;
+
+	ret = adf_cfg_section_add(accel_dev, ADF_KERNEL_SEC);
+	if (ret)
+		goto err;
+
+	ret = adf_cfg_section_add(accel_dev, "Accelerator0");
+	if (ret)
+		goto err;
+
+	ret = adf_cfg_get_param_value(accel_dev, ADF_GENERAL_SEC,
+				      ADF_SERVICES_ENABLED, services);
+	if (ret)
+		goto err;
+
+	ret = sysfs_match_string(adf_cfg_services, services);
+	if (ret < 0)
+		goto err;
+
+	switch (ret) {
+	case SVC_CY:
+	case SVC_CY2:
+		ret = adf_crypto_dev_config(accel_dev);
+		break;
+	case SVC_DC:
+	case SVC_DCC:
+		ret = adf_comp_dev_config(accel_dev);
+		break;
+	default:
+		ret = adf_no_dev_config(accel_dev);
+		break;
+	}
+
+	if (ret)
+		goto err;
+
+	set_bit(ADF_STATUS_CONFIGURED, &accel_dev->status);
+
+	return ret;
+
+err:
+	dev_err(&GET_DEV(accel_dev), "Failed to configure QAT driver\n");
+	return ret;
+}
+EXPORT_SYMBOL_GPL(adf_gen4_dev_config);
+
+int adf_gen4_cfg_dev_init(struct adf_accel_dev *accel_dev)
+{
+	const char *config;
+	int ret;
+
+	config = accel_dev->accel_id % 2 ? ADF_CFG_DC : ADF_CFG_CY;
+
+	ret = adf_cfg_section_add(accel_dev, ADF_GENERAL_SEC);
+	if (ret)
+		return ret;
+
+	/* Default configuration is crypto only for even devices
+	 * and compression for odd devices
+	 */
+	ret = adf_cfg_add_key_value_param(accel_dev, ADF_GENERAL_SEC,
+					  ADF_SERVICES_ENABLED, config,
+					  ADF_STR);
+	if (ret)
+		return ret;
+
+	adf_heartbeat_save_cfg_param(accel_dev, ADF_CFG_HB_TIMER_MIN_MS);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(adf_gen4_cfg_dev_init);
diff --git a/drivers/crypto/intel/qat/qat_common/adf_gen4_config.h b/drivers/crypto/intel/qat/qat_common/adf_gen4_config.h
new file mode 100644
index 000000000000..bb87655f69a8
--- /dev/null
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen4_config.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright(c) 2023 Intel Corporation */
+#ifndef ADF_GEN4_CONFIG_H_
+#define ADF_GEN4_CONFIG_H_
+
+#include "adf_accel_devices.h"
+
+int adf_gen4_dev_config(struct adf_accel_dev *accel_dev);
+int adf_gen4_cfg_dev_init(struct adf_accel_dev *accel_dev);
+
+#endif
diff --git a/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.c b/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.c
index 3148a62938fd..9985683056d5 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.c
@@ -2,8 +2,10 @@
 /* Copyright(c) 2020 Intel Corporation */
 #include <linux/iopoll.h>
 #include "adf_accel_devices.h"
+#include "adf_cfg_services.h"
 #include "adf_common_drv.h"
 #include "adf_gen4_hw_data.h"
+#include "adf_gen4_pm.h"
 
 static u64 build_csr_ring_base_addr(dma_addr_t addr, u32 size)
 {
@@ -102,6 +104,131 @@ void adf_gen4_init_hw_csr_ops(struct adf_hw_csr_ops *csr_ops)
 }
 EXPORT_SYMBOL_GPL(adf_gen4_init_hw_csr_ops);
 
+u32 adf_gen4_get_accel_mask(struct adf_hw_device_data *self)
+{
+	return ADF_GEN4_ACCELERATORS_MASK;
+}
+EXPORT_SYMBOL_GPL(adf_gen4_get_accel_mask);
+
+u32 adf_gen4_get_num_accels(struct adf_hw_device_data *self)
+{
+	return ADF_GEN4_MAX_ACCELERATORS;
+}
+EXPORT_SYMBOL_GPL(adf_gen4_get_num_accels);
+
+u32 adf_gen4_get_num_aes(struct adf_hw_device_data *self)
+{
+	if (!self || !self->ae_mask)
+		return 0;
+
+	return hweight32(self->ae_mask);
+}
+EXPORT_SYMBOL_GPL(adf_gen4_get_num_aes);
+
+u32 adf_gen4_get_misc_bar_id(struct adf_hw_device_data *self)
+{
+	return ADF_GEN4_PMISC_BAR;
+}
+EXPORT_SYMBOL_GPL(adf_gen4_get_misc_bar_id);
+
+u32 adf_gen4_get_etr_bar_id(struct adf_hw_device_data *self)
+{
+	return ADF_GEN4_ETR_BAR;
+}
+EXPORT_SYMBOL_GPL(adf_gen4_get_etr_bar_id);
+
+u32 adf_gen4_get_sram_bar_id(struct adf_hw_device_data *self)
+{
+	return ADF_GEN4_SRAM_BAR;
+}
+EXPORT_SYMBOL_GPL(adf_gen4_get_sram_bar_id);
+
+enum dev_sku_info adf_gen4_get_sku(struct adf_hw_device_data *self)
+{
+	return DEV_SKU_1;
+}
+EXPORT_SYMBOL_GPL(adf_gen4_get_sku);
+
+void adf_gen4_get_arb_info(struct arb_info *arb_info)
+{
+	arb_info->arb_cfg = ADF_GEN4_ARB_CONFIG;
+	arb_info->arb_offset = ADF_GEN4_ARB_OFFSET;
+	arb_info->wt2sam_offset = ADF_GEN4_ARB_WRK_2_SER_MAP_OFFSET;
+}
+EXPORT_SYMBOL_GPL(adf_gen4_get_arb_info);
+
+void adf_gen4_get_admin_info(struct admin_info *admin_csrs_info)
+{
+	admin_csrs_info->mailbox_offset = ADF_GEN4_MAILBOX_BASE_OFFSET;
+	admin_csrs_info->admin_msg_ur = ADF_GEN4_ADMINMSGUR_OFFSET;
+	admin_csrs_info->admin_msg_lr = ADF_GEN4_ADMINMSGLR_OFFSET;
+}
+EXPORT_SYMBOL_GPL(adf_gen4_get_admin_info);
+
+u32 adf_gen4_get_heartbeat_clock(struct adf_hw_device_data *self)
+{
+	/*
+	 * GEN4 uses KPT counter for HB
+	 */
+	return ADF_GEN4_KPT_COUNTER_FREQ;
+}
+EXPORT_SYMBOL_GPL(adf_gen4_get_heartbeat_clock);
+
+void adf_gen4_enable_error_correction(struct adf_accel_dev *accel_dev)
+{
+	struct adf_bar *misc_bar = &GET_BARS(accel_dev)[ADF_GEN4_PMISC_BAR];
+	void __iomem *csr = misc_bar->virt_addr;
+
+	/* Enable all in errsou3 except VFLR notification on host */
+	ADF_CSR_WR(csr, ADF_GEN4_ERRMSK3, ADF_GEN4_VFLNOTIFY);
+}
+EXPORT_SYMBOL_GPL(adf_gen4_enable_error_correction);
+
+void adf_gen4_enable_ints(struct adf_accel_dev *accel_dev)
+{
+	void __iomem *addr;
+
+	addr = (&GET_BARS(accel_dev)[ADF_GEN4_PMISC_BAR])->virt_addr;
+
+	/* Enable bundle interrupts */
+	ADF_CSR_WR(addr, ADF_GEN4_SMIAPF_RP_X0_MASK_OFFSET, 0);
+	ADF_CSR_WR(addr, ADF_GEN4_SMIAPF_RP_X1_MASK_OFFSET, 0);
+
+	/* Enable misc interrupts */
+	ADF_CSR_WR(addr, ADF_GEN4_SMIAPF_MASK_OFFSET, 0);
+}
+EXPORT_SYMBOL_GPL(adf_gen4_enable_ints);
+
+int adf_gen4_init_device(struct adf_accel_dev *accel_dev)
+{
+	void __iomem *addr;
+	u32 status;
+	u32 csr;
+	int ret;
+
+	addr = (&GET_BARS(accel_dev)[ADF_GEN4_PMISC_BAR])->virt_addr;
+
+	/* Temporarily mask PM interrupt */
+	csr = ADF_CSR_RD(addr, ADF_GEN4_ERRMSK2);
+	csr |= ADF_GEN4_PM_SOU;
+	ADF_CSR_WR(addr, ADF_GEN4_ERRMSK2, csr);
+
+	/* Set DRV_ACTIVE bit to power up the device */
+	ADF_CSR_WR(addr, ADF_GEN4_PM_INTERRUPT, ADF_GEN4_PM_DRV_ACTIVE);
+
+	/* Poll status register to make sure the device is powered up */
+	ret = read_poll_timeout(ADF_CSR_RD, status,
+				status & ADF_GEN4_PM_INIT_STATE,
+				ADF_GEN4_PM_POLL_DELAY_US,
+				ADF_GEN4_PM_POLL_TIMEOUT_US, true, addr,
+				ADF_GEN4_PM_STATUS);
+	if (ret)
+		dev_err(&GET_DEV(accel_dev), "Failed to power up the device\n");
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(adf_gen4_init_device);
+
 static inline void adf_gen4_unpack_ssm_wdtimer(u64 value, u32 *upper,
 					       u32 *lower)
 {
@@ -135,6 +262,28 @@ void adf_gen4_set_ssm_wdtimer(struct adf_accel_dev *accel_dev)
 }
 EXPORT_SYMBOL_GPL(adf_gen4_set_ssm_wdtimer);
 
+/*
+ * The vector routing table is used to select the MSI-X entry to use for each
+ * interrupt source.
+ * The first ADF_GEN4_ETR_MAX_BANKS entries correspond to ring interrupts.
+ * The final entry corresponds to VF2PF or error interrupts.
+ * This vector table could be used to configure one MSI-X entry to be shared
+ * between multiple interrupt sources.
+ *
+ * The default routing is set to have a one to one correspondence between the
+ * interrupt source and the MSI-X entry used.
+ */
+void adf_gen4_set_msix_default_rttable(struct adf_accel_dev *accel_dev)
+{
+	void __iomem *csr;
+	int i;
+
+	csr = (&GET_BARS(accel_dev)[ADF_GEN4_PMISC_BAR])->virt_addr;
+	for (i = 0; i <= ADF_GEN4_ETR_MAX_BANKS; i++)
+		ADF_CSR_WR(csr, ADF_GEN4_MSIX_RTTABLE_OFFSET(i), i);
+}
+EXPORT_SYMBOL_GPL(adf_gen4_set_msix_default_rttable);
+
 int adf_pfvf_comms_disabled(struct adf_accel_dev *accel_dev)
 {
 	return 0;
@@ -192,3 +341,92 @@ int adf_gen4_ring_pair_reset(struct adf_accel_dev *accel_dev, u32 bank_number)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(adf_gen4_ring_pair_reset);
+
+static const u32 thrd_to_arb_map_dcc[] = {
+	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+	0x0000FFFF, 0x0000FFFF, 0x0000FFFF, 0x0000FFFF,
+	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+	0x0
+};
+
+static const u16 rp_group_to_arb_mask[] = {
+	[RP_GROUP_0] = 0x5,
+	[RP_GROUP_1] = 0xA,
+};
+
+static bool is_single_service(int service_id)
+{
+	switch (service_id) {
+	case SVC_DC:
+	case SVC_SYM:
+	case SVC_ASYM:
+		return true;
+	case SVC_CY:
+	case SVC_CY2:
+	case SVC_DCC:
+	case SVC_ASYM_DC:
+	case SVC_DC_ASYM:
+	case SVC_SYM_DC:
+	case SVC_DC_SYM:
+	default:
+		return false;
+	}
+}
+
+int adf_gen4_init_thd2arb_map(struct adf_accel_dev *accel_dev)
+{
+	struct adf_hw_device_data *hw_data = GET_HW_DATA(accel_dev);
+	u32 *thd2arb_map = hw_data->thd_to_arb_map;
+	unsigned int ae_cnt, worker_obj_cnt, i, j;
+	unsigned long ae_mask, thds_mask;
+	int srv_id, rp_group;
+	u32 thd2arb_map_base;
+	u16 arb_mask;
+
+	if (!hw_data->get_rp_group || !hw_data->get_ena_thd_mask ||
+	    !hw_data->get_num_aes || !hw_data->uof_get_num_objs ||
+	    !hw_data->uof_get_ae_mask)
+		return -EFAULT;
+
+	srv_id = adf_get_service_enabled(accel_dev);
+	if (srv_id < 0)
+		return srv_id;
+
+	ae_cnt = hw_data->get_num_aes(hw_data);
+	worker_obj_cnt = hw_data->uof_get_num_objs(accel_dev) -
+			 ADF_GEN4_ADMIN_ACCELENGINES;
+
+	if (srv_id == SVC_DCC) {
+		memcpy(thd2arb_map, thrd_to_arb_map_dcc,
+		       array_size(sizeof(*thd2arb_map), ae_cnt));
+		return 0;
+	}
+
+	for (i = 0; i < worker_obj_cnt; i++) {
+		ae_mask = hw_data->uof_get_ae_mask(accel_dev, i);
+		rp_group = hw_data->get_rp_group(accel_dev, ae_mask);
+		thds_mask = hw_data->get_ena_thd_mask(accel_dev, i);
+		thd2arb_map_base = 0;
+
+		if (rp_group >= RP_GROUP_COUNT || rp_group < RP_GROUP_0)
+			return -EINVAL;
+
+		if (thds_mask == ADF_GEN4_ENA_THD_MASK_ERROR)
+			return -EINVAL;
+
+		if (is_single_service(srv_id))
+			arb_mask = rp_group_to_arb_mask[RP_GROUP_0] |
+				   rp_group_to_arb_mask[RP_GROUP_1];
+		else
+			arb_mask = rp_group_to_arb_mask[rp_group];
+
+		for_each_set_bit(j, &thds_mask, ADF_NUM_THREADS_PER_AE)
+			thd2arb_map_base |= arb_mask << (j * 4);
+
+		for_each_set_bit(j, &ae_mask, ae_cnt)
+			thd2arb_map[j] = thd2arb_map_base;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(adf_gen4_init_thd2arb_map);
diff --git a/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.h b/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.h
index 1813fe1d5a06..7d8a774cadc8 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.h
@@ -3,9 +3,57 @@
 #ifndef ADF_GEN4_HW_CSR_DATA_H_
 #define ADF_GEN4_HW_CSR_DATA_H_
 
+#include <linux/units.h>
+
 #include "adf_accel_devices.h"
 #include "adf_cfg_common.h"
 
+/* PCIe configuration space */
+#define ADF_GEN4_BAR_MASK	(BIT(0) | BIT(2) | BIT(4))
+#define ADF_GEN4_SRAM_BAR	0
+#define ADF_GEN4_PMISC_BAR	1
+#define ADF_GEN4_ETR_BAR	2
+
+/* Clocks frequency */
+#define ADF_GEN4_KPT_COUNTER_FREQ	(100 * HZ_PER_MHZ)
+
+/* Physical function fuses */
+#define ADF_GEN4_FUSECTL0_OFFSET	0x2C8
+#define ADF_GEN4_FUSECTL1_OFFSET	0x2CC
+#define ADF_GEN4_FUSECTL2_OFFSET	0x2D0
+#define ADF_GEN4_FUSECTL3_OFFSET	0x2D4
+#define ADF_GEN4_FUSECTL4_OFFSET	0x2D8
+#define ADF_GEN4_FUSECTL5_OFFSET	0x2DC
+
+/* Accelerators */
+#define ADF_GEN4_ACCELERATORS_MASK	0x1
+#define ADF_GEN4_MAX_ACCELERATORS	1
+#define ADF_GEN4_ADMIN_ACCELENGINES	1
+
+/* MSIX interrupt */
+#define ADF_GEN4_SMIAPF_RP_X0_MASK_OFFSET	0x41A040
+#define ADF_GEN4_SMIAPF_RP_X1_MASK_OFFSET	0x41A044
+#define ADF_GEN4_SMIAPF_MASK_OFFSET		0x41A084
+#define ADF_GEN4_MSIX_RTTABLE_OFFSET(i)		(0x409000 + ((i) * 0x04))
+
+/* Bank and ring configuration */
+#define ADF_GEN4_MAX_RPS		64
+#define ADF_GEN4_NUM_RINGS_PER_BANK	2
+#define ADF_GEN4_NUM_BANKS_PER_VF	4
+#define ADF_GEN4_ETR_MAX_BANKS		64
+#define ADF_GEN4_RX_RINGS_OFFSET	1
+#define ADF_GEN4_TX_RINGS_MASK		0x1
+
+/* Arbiter configuration */
+#define ADF_GEN4_ARB_CONFIG			(BIT(31) | BIT(6) | BIT(0))
+#define ADF_GEN4_ARB_OFFSET			0x0
+#define ADF_GEN4_ARB_WRK_2_SER_MAP_OFFSET	0x400
+
+/* Admin Interface Reg Offset */
+#define ADF_GEN4_ADMINMSGUR_OFFSET	0x500574
+#define ADF_GEN4_ADMINMSGLR_OFFSET	0x500578
+#define ADF_GEN4_MAILBOX_BASE_OFFSET	0x600970
+
 /* Transport access */
 #define ADF_BANK_INT_SRC_SEL_MASK	0x44UL
 #define ADF_RING_CSR_RING_CONFIG	0x1000
@@ -146,7 +194,46 @@ do { \
 #define ADF_GEN4_RL_TOKEN_PCIEIN_BUCKET_OFFSET	0x508800
 #define ADF_GEN4_RL_TOKEN_PCIEOUT_BUCKET_OFFSET	0x508804
 
+/* Arbiter threads mask with error value */
+#define ADF_GEN4_ENA_THD_MASK_ERROR	GENMASK(ADF_NUM_THREADS_PER_AE, 0)
+
 void adf_gen4_set_ssm_wdtimer(struct adf_accel_dev *accel_dev);
+
+enum icp_qat_gen4_slice_mask {
+	ICP_ACCEL_GEN4_MASK_CIPHER_SLICE = BIT(0),
+	ICP_ACCEL_GEN4_MASK_AUTH_SLICE = BIT(1),
+	ICP_ACCEL_GEN4_MASK_PKE_SLICE = BIT(2),
+	ICP_ACCEL_GEN4_MASK_COMPRESS_SLICE = BIT(3),
+	ICP_ACCEL_GEN4_MASK_UCS_SLICE = BIT(4),
+	ICP_ACCEL_GEN4_MASK_EIA3_SLICE = BIT(5),
+	ICP_ACCEL_GEN4_MASK_SMX_SLICE = BIT(7),
+	ICP_ACCEL_GEN4_MASK_WCP_WAT_SLICE = BIT(8),
+	ICP_ACCEL_GEN4_MASK_ZUC_256_SLICE = BIT(9),
+};
+
+enum adf_gen4_rp_groups {
+	RP_GROUP_0,
+	RP_GROUP_1,
+	RP_GROUP_COUNT
+};
+
+void adf_gen4_enable_error_correction(struct adf_accel_dev *accel_dev);
+void adf_gen4_enable_ints(struct adf_accel_dev *accel_dev);
+u32 adf_gen4_get_accel_mask(struct adf_hw_device_data *self);
+void adf_gen4_get_admin_info(struct admin_info *admin_csrs_info);
+void adf_gen4_get_arb_info(struct arb_info *arb_info);
+u32 adf_gen4_get_etr_bar_id(struct adf_hw_device_data *self);
+u32 adf_gen4_get_heartbeat_clock(struct adf_hw_device_data *self);
+u32 adf_gen4_get_misc_bar_id(struct adf_hw_device_data *self);
+u32 adf_gen4_get_num_accels(struct adf_hw_device_data *self);
+u32 adf_gen4_get_num_aes(struct adf_hw_device_data *self);
+enum dev_sku_info adf_gen4_get_sku(struct adf_hw_device_data *self);
+u32 adf_gen4_get_sram_bar_id(struct adf_hw_device_data *self);
+int adf_gen4_init_device(struct adf_accel_dev *accel_dev);
 void adf_gen4_init_hw_csr_ops(struct adf_hw_csr_ops *csr_ops);
 int adf_gen4_ring_pair_reset(struct adf_accel_dev *accel_dev, u32 bank_number);
+void adf_gen4_set_msix_default_rttable(struct adf_accel_dev *accel_dev);
+void adf_gen4_set_ssm_wdtimer(struct adf_accel_dev *accel_dev);
+int adf_gen4_init_thd2arb_map(struct adf_accel_dev *accel_dev);
+
 #endif
diff --git a/drivers/crypto/intel/qat/qat_common/adf_gen4_tl.c b/drivers/crypto/intel/qat/qat_common/adf_gen4_tl.c
new file mode 100644
index 000000000000..7fc7a77f6aed
--- /dev/null
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen4_tl.c
@@ -0,0 +1,153 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2023 Intel Corporation. */
+#include <linux/export.h>
+#include <linux/kernel.h>
+
+#include "adf_gen4_tl.h"
+#include "adf_telemetry.h"
+#include "adf_tl_debugfs.h"
+
+#define ADF_GEN4_TL_DEV_REG_OFF(reg) ADF_TL_DEV_REG_OFF(reg, gen4)
+
+#define ADF_GEN4_TL_RP_REG_OFF(reg) ADF_TL_RP_REG_OFF(reg, gen4)
+
+#define ADF_GEN4_TL_SL_UTIL_COUNTER(_name)	\
+	ADF_TL_COUNTER("util_" #_name,		\
+			ADF_TL_SIMPLE_COUNT,	\
+			ADF_TL_SLICE_REG_OFF(_name, reg_tm_slice_util, gen4))
+
+#define ADF_GEN4_TL_SL_EXEC_COUNTER(_name)	\
+	ADF_TL_COUNTER("exec_" #_name,		\
+			ADF_TL_SIMPLE_COUNT,	\
+			ADF_TL_SLICE_REG_OFF(_name, reg_tm_slice_exec_cnt, gen4))
+
+/* Device level counters. */
+static const struct adf_tl_dbg_counter dev_counters[] = {
+	/* PCIe partial transactions. */
+	ADF_TL_COUNTER(PCI_TRANS_CNT_NAME, ADF_TL_SIMPLE_COUNT,
+		       ADF_GEN4_TL_DEV_REG_OFF(reg_tl_pci_trans_cnt)),
+	/* Max read latency[ns]. */
+	ADF_TL_COUNTER(MAX_RD_LAT_NAME, ADF_TL_COUNTER_NS,
+		       ADF_GEN4_TL_DEV_REG_OFF(reg_tl_rd_lat_max)),
+	/* Read latency average[ns]. */
+	ADF_TL_COUNTER_LATENCY(RD_LAT_ACC_NAME, ADF_TL_COUNTER_NS_AVG,
+			       ADF_GEN4_TL_DEV_REG_OFF(reg_tl_rd_lat_acc),
+			       ADF_GEN4_TL_DEV_REG_OFF(reg_tl_rd_cmpl_cnt)),
+	/* Max get to put latency[ns]. */
+	ADF_TL_COUNTER(MAX_LAT_NAME, ADF_TL_COUNTER_NS,
+		       ADF_GEN4_TL_DEV_REG_OFF(reg_tl_gp_lat_max)),
+	/* Get to put latency average[ns]. */
+	ADF_TL_COUNTER_LATENCY(LAT_ACC_NAME, ADF_TL_COUNTER_NS_AVG,
+			       ADF_GEN4_TL_DEV_REG_OFF(reg_tl_gp_lat_acc),
+			       ADF_GEN4_TL_DEV_REG_OFF(reg_tl_ae_put_cnt)),
+	/* PCIe write bandwidth[Mbps]. */
+	ADF_TL_COUNTER(BW_IN_NAME, ADF_TL_COUNTER_MBPS,
+		       ADF_GEN4_TL_DEV_REG_OFF(reg_tl_bw_in)),
+	/* PCIe read bandwidth[Mbps]. */
+	ADF_TL_COUNTER(BW_OUT_NAME, ADF_TL_COUNTER_MBPS,
+		       ADF_GEN4_TL_DEV_REG_OFF(reg_tl_bw_out)),
+	/* Page request latency average[ns]. */
+	ADF_TL_COUNTER_LATENCY(PAGE_REQ_LAT_NAME, ADF_TL_COUNTER_NS_AVG,
+			       ADF_GEN4_TL_DEV_REG_OFF(reg_tl_at_page_req_lat_acc),
+			       ADF_GEN4_TL_DEV_REG_OFF(reg_tl_at_page_req_cnt)),
+	/* Page translation latency average[ns]. */
+	ADF_TL_COUNTER_LATENCY(AT_TRANS_LAT_NAME, ADF_TL_COUNTER_NS_AVG,
+			       ADF_GEN4_TL_DEV_REG_OFF(reg_tl_at_trans_lat_acc),
+			       ADF_GEN4_TL_DEV_REG_OFF(reg_tl_at_trans_lat_cnt)),
+	/* Maximum uTLB used. */
+	ADF_TL_COUNTER(AT_MAX_UTLB_USED_NAME, ADF_TL_SIMPLE_COUNT,
+		       ADF_GEN4_TL_DEV_REG_OFF(reg_tl_at_max_tlb_used)),
+};
+
+/* Slice utilization counters. */
+static const struct adf_tl_dbg_counter sl_util_counters[ADF_TL_SL_CNT_COUNT] = {
+	/* Compression slice utilization. */
+	ADF_GEN4_TL_SL_UTIL_COUNTER(cpr),
+	/* Translator slice utilization. */
+	ADF_GEN4_TL_SL_UTIL_COUNTER(xlt),
+	/* Decompression slice utilization. */
+	ADF_GEN4_TL_SL_UTIL_COUNTER(dcpr),
+	/* PKE utilization. */
+	ADF_GEN4_TL_SL_UTIL_COUNTER(pke),
+	/* Wireless Authentication slice utilization. */
+	ADF_GEN4_TL_SL_UTIL_COUNTER(wat),
+	/* Wireless Cipher slice utilization. */
+	ADF_GEN4_TL_SL_UTIL_COUNTER(wcp),
+	/* UCS slice utilization. */
+	ADF_GEN4_TL_SL_UTIL_COUNTER(ucs),
+	/* Cipher slice utilization. */
+	ADF_GEN4_TL_SL_UTIL_COUNTER(cph),
+	/* Authentication slice utilization. */
+	ADF_GEN4_TL_SL_UTIL_COUNTER(ath),
+};
+
+/* Slice execution counters. */
+static const struct adf_tl_dbg_counter sl_exec_counters[ADF_TL_SL_CNT_COUNT] = {
+	/* Compression slice execution count. */
+	ADF_GEN4_TL_SL_EXEC_COUNTER(cpr),
+	/* Translator slice execution count. */
+	ADF_GEN4_TL_SL_EXEC_COUNTER(xlt),
+	/* Decompression slice execution count. */
+	ADF_GEN4_TL_SL_EXEC_COUNTER(dcpr),
+	/* PKE execution count. */
+	ADF_GEN4_TL_SL_EXEC_COUNTER(pke),
+	/* Wireless Authentication slice execution count. */
+	ADF_GEN4_TL_SL_EXEC_COUNTER(wat),
+	/* Wireless Cipher slice execution count. */
+	ADF_GEN4_TL_SL_EXEC_COUNTER(wcp),
+	/* UCS slice execution count. */
+	ADF_GEN4_TL_SL_EXEC_COUNTER(ucs),
+	/* Cipher slice execution count. */
+	ADF_GEN4_TL_SL_EXEC_COUNTER(cph),
+	/* Authentication slice execution count. */
+	ADF_GEN4_TL_SL_EXEC_COUNTER(ath),
+};
+
+/* Ring pair counters. */
+static const struct adf_tl_dbg_counter rp_counters[] = {
+	/* PCIe partial transactions. */
+	ADF_TL_COUNTER(PCI_TRANS_CNT_NAME, ADF_TL_SIMPLE_COUNT,
+		       ADF_GEN4_TL_RP_REG_OFF(reg_tl_pci_trans_cnt)),
+	/* Get to put latency average[ns]. */
+	ADF_TL_COUNTER_LATENCY(LAT_ACC_NAME, ADF_TL_COUNTER_NS_AVG,
+			       ADF_GEN4_TL_RP_REG_OFF(reg_tl_gp_lat_acc),
+			       ADF_GEN4_TL_RP_REG_OFF(reg_tl_ae_put_cnt)),
+	/* PCIe write bandwidth[Mbps]. */
+	ADF_TL_COUNTER(BW_IN_NAME, ADF_TL_COUNTER_MBPS,
+		       ADF_GEN4_TL_RP_REG_OFF(reg_tl_bw_in)),
+	/* PCIe read bandwidth[Mbps]. */
+	ADF_TL_COUNTER(BW_OUT_NAME, ADF_TL_COUNTER_MBPS,
+		       ADF_GEN4_TL_RP_REG_OFF(reg_tl_bw_out)),
+	/* Message descriptor DevTLB hit rate. */
+	ADF_TL_COUNTER(AT_GLOB_DTLB_HIT_NAME, ADF_TL_SIMPLE_COUNT,
+		       ADF_GEN4_TL_RP_REG_OFF(reg_tl_at_glob_devtlb_hit)),
+	/* Message descriptor DevTLB miss rate. */
+	ADF_TL_COUNTER(AT_GLOB_DTLB_MISS_NAME, ADF_TL_SIMPLE_COUNT,
+		       ADF_GEN4_TL_RP_REG_OFF(reg_tl_at_glob_devtlb_miss)),
+	/* Payload DevTLB hit rate. */
+	ADF_TL_COUNTER(AT_PAYLD_DTLB_HIT_NAME, ADF_TL_SIMPLE_COUNT,
+		       ADF_GEN4_TL_RP_REG_OFF(reg_tl_at_payld_devtlb_hit)),
+	/* Payload DevTLB miss rate. */
+	ADF_TL_COUNTER(AT_PAYLD_DTLB_MISS_NAME, ADF_TL_SIMPLE_COUNT,
+		       ADF_GEN4_TL_RP_REG_OFF(reg_tl_at_payld_devtlb_miss)),
+};
+
+void adf_gen4_init_tl_data(struct adf_tl_hw_data *tl_data)
+{
+	tl_data->layout_sz = ADF_GEN4_TL_LAYOUT_SZ;
+	tl_data->slice_reg_sz = ADF_GEN4_TL_SLICE_REG_SZ;
+	tl_data->rp_reg_sz = ADF_GEN4_TL_RP_REG_SZ;
+	tl_data->num_hbuff = ADF_GEN4_TL_NUM_HIST_BUFFS;
+	tl_data->max_rp = ADF_GEN4_TL_MAX_RP_NUM;
+	tl_data->msg_cnt_off = ADF_GEN4_TL_MSG_CNT_OFF;
+	tl_data->cpp_ns_per_cycle = ADF_GEN4_CPP_NS_PER_CYCLE;
+	tl_data->bw_units_to_bytes = ADF_GEN4_TL_BW_HW_UNITS_TO_BYTES;
+
+	tl_data->dev_counters = dev_counters;
+	tl_data->num_dev_counters = ARRAY_SIZE(dev_counters);
+	tl_data->sl_util_counters = sl_util_counters;
+	tl_data->sl_exec_counters = sl_exec_counters;
+	tl_data->rp_counters = rp_counters;
+	tl_data->num_rp_counters = ARRAY_SIZE(rp_counters);
+}
+EXPORT_SYMBOL_GPL(adf_gen4_init_tl_data);
diff --git a/drivers/crypto/intel/qat/qat_common/adf_gen4_tl.h b/drivers/crypto/intel/qat/qat_common/adf_gen4_tl.h
new file mode 100644
index 000000000000..32df4163beb9
--- /dev/null
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen4_tl.h
@@ -0,0 +1,158 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2023 Intel Corporation. */
+#ifndef ADF_GEN4_TL_H
+#define ADF_GEN4_TL_H
+
+#include <linux/stddef.h>
+#include <linux/types.h>
+
+struct adf_tl_hw_data;
+
+/* Computation constants. */
+#define ADF_GEN4_CPP_NS_PER_CYCLE		2
+#define ADF_GEN4_TL_BW_HW_UNITS_TO_BYTES	64
+
+/* Maximum aggregation time. Value in milliseconds. */
+#define ADF_GEN4_TL_MAX_AGGR_TIME_MS		4000
+/* Num of buffers to store historic values. */
+#define ADF_GEN4_TL_NUM_HIST_BUFFS \
+	(ADF_GEN4_TL_MAX_AGGR_TIME_MS / ADF_TL_DATA_WR_INTERVAL_MS)
+
+/* Max number of HW resources of one type. */
+#define ADF_GEN4_TL_MAX_SLICES_PER_TYPE		24
+
+/* Max number of simultaneously monitored ring pairs. */
+#define ADF_GEN4_TL_MAX_RP_NUM			4
+
+/**
+ * struct adf_gen4_tl_slice_data_regs - HW slice data as populated by FW.
+ * @reg_tm_slice_exec_cnt: Slice execution count.
+ * @reg_tm_slice_util: Slice utilization.
+ */
+struct adf_gen4_tl_slice_data_regs {
+	__u32 reg_tm_slice_exec_cnt;
+	__u32 reg_tm_slice_util;
+};
+
+#define ADF_GEN4_TL_SLICE_REG_SZ sizeof(struct adf_gen4_tl_slice_data_regs)
+
+/**
+ * struct adf_gen4_tl_device_data_regs - This structure stores device telemetry
+ * counter values as are being populated periodically by device.
+ * @reg_tl_rd_lat_acc: read latency accumulator
+ * @reg_tl_gp_lat_acc: get-put latency accumulator
+ * @reg_tl_at_page_req_lat_acc: AT/DevTLB page request latency accumulator
+ * @reg_tl_at_trans_lat_acc: DevTLB transaction latency accumulator
+ * @reg_tl_re_acc: accumulated ring empty time
+ * @reg_tl_pci_trans_cnt: PCIe partial transactions
+ * @reg_tl_rd_lat_max: maximum logged read latency
+ * @reg_tl_rd_cmpl_cnt: read requests completed count
+ * @reg_tl_gp_lat_max: maximum logged get to put latency
+ * @reg_tl_ae_put_cnt: Accelerator Engine put counts across all rings
+ * @reg_tl_bw_in: PCIe write bandwidth
+ * @reg_tl_bw_out: PCIe read bandwidth
+ * @reg_tl_at_page_req_cnt: DevTLB page requests count
+ * @reg_tl_at_trans_lat_cnt: DevTLB transaction latency samples count
+ * @reg_tl_at_max_tlb_used: maximum uTLB used
+ * @reg_tl_re_cnt: ring empty time samples count
+ * @reserved: reserved
+ * @ath_slices: array of Authentication slices utilization registers
+ * @cph_slices: array of Cipher slices utilization registers
+ * @cpr_slices: array of Compression slices utilization registers
+ * @xlt_slices: array of Translator slices utilization registers
+ * @dcpr_slices: array of Decompression slices utilization registers
+ * @pke_slices: array of PKE slices utilization registers
+ * @ucs_slices: array of UCS slices utilization registers
+ * @wat_slices: array of Wireless Authentication slices utilization registers
+ * @wcp_slices: array of Wireless Cipher slices utilization registers
+ */
+struct adf_gen4_tl_device_data_regs {
+	__u64 reg_tl_rd_lat_acc;
+	__u64 reg_tl_gp_lat_acc;
+	__u64 reg_tl_at_page_req_lat_acc;
+	__u64 reg_tl_at_trans_lat_acc;
+	__u64 reg_tl_re_acc;
+	__u32 reg_tl_pci_trans_cnt;
+	__u32 reg_tl_rd_lat_max;
+	__u32 reg_tl_rd_cmpl_cnt;
+	__u32 reg_tl_gp_lat_max;
+	__u32 reg_tl_ae_put_cnt;
+	__u32 reg_tl_bw_in;
+	__u32 reg_tl_bw_out;
+	__u32 reg_tl_at_page_req_cnt;
+	__u32 reg_tl_at_trans_lat_cnt;
+	__u32 reg_tl_at_max_tlb_used;
+	__u32 reg_tl_re_cnt;
+	__u32 reserved;
+	struct adf_gen4_tl_slice_data_regs ath_slices[ADF_GEN4_TL_MAX_SLICES_PER_TYPE];
+	struct adf_gen4_tl_slice_data_regs cph_slices[ADF_GEN4_TL_MAX_SLICES_PER_TYPE];
+	struct adf_gen4_tl_slice_data_regs cpr_slices[ADF_GEN4_TL_MAX_SLICES_PER_TYPE];
+	struct adf_gen4_tl_slice_data_regs xlt_slices[ADF_GEN4_TL_MAX_SLICES_PER_TYPE];
+	struct adf_gen4_tl_slice_data_regs dcpr_slices[ADF_GEN4_TL_MAX_SLICES_PER_TYPE];
+	struct adf_gen4_tl_slice_data_regs pke_slices[ADF_GEN4_TL_MAX_SLICES_PER_TYPE];
+	struct adf_gen4_tl_slice_data_regs ucs_slices[ADF_GEN4_TL_MAX_SLICES_PER_TYPE];
+	struct adf_gen4_tl_slice_data_regs wat_slices[ADF_GEN4_TL_MAX_SLICES_PER_TYPE];
+	struct adf_gen4_tl_slice_data_regs wcp_slices[ADF_GEN4_TL_MAX_SLICES_PER_TYPE];
+};
+
+/**
+ * struct adf_gen4_tl_ring_pair_data_regs - This structure stores Ring Pair
+ * telemetry counter values as are being populated periodically by device.
+ * @reg_tl_gp_lat_acc: get-put latency accumulator
+ * @reserved: reserved
+ * @reg_tl_pci_trans_cnt: PCIe partial transactions
+ * @reg_tl_ae_put_cnt: Accelerator Engine put counts across all rings
+ * @reg_tl_bw_in: PCIe write bandwidth
+ * @reg_tl_bw_out: PCIe read bandwidth
+ * @reg_tl_at_glob_devtlb_hit: Message descriptor DevTLB hit rate
+ * @reg_tl_at_glob_devtlb_miss: Message descriptor DevTLB miss rate
+ * @reg_tl_at_payld_devtlb_hit: Payload DevTLB hit rate
+ * @reg_tl_at_payld_devtlb_miss: Payload DevTLB miss rate
+ * @reg_tl_re_cnt: ring empty time samples count
+ * @reserved1: reserved
+ */
+struct adf_gen4_tl_ring_pair_data_regs {
+	__u64 reg_tl_gp_lat_acc;
+	__u64 reserved;
+	__u32 reg_tl_pci_trans_cnt;
+	__u32 reg_tl_ae_put_cnt;
+	__u32 reg_tl_bw_in;
+	__u32 reg_tl_bw_out;
+	__u32 reg_tl_at_glob_devtlb_hit;
+	__u32 reg_tl_at_glob_devtlb_miss;
+	__u32 reg_tl_at_payld_devtlb_hit;
+	__u32 reg_tl_at_payld_devtlb_miss;
+	__u32 reg_tl_re_cnt;
+	__u32 reserved1;
+};
+
+#define ADF_GEN4_TL_RP_REG_SZ sizeof(struct adf_gen4_tl_ring_pair_data_regs)
+
+/**
+ * struct adf_gen4_tl_layout - This structure represents entire telemetry
+ * counters data: Device + 4 Ring Pairs as are being populated periodically
+ * by device.
+ * @tl_device_data_regs: structure of device telemetry registers
+ * @tl_ring_pairs_data_regs: array of ring pairs telemetry registers
+ * @reg_tl_msg_cnt: telemetry messages counter
+ * @reserved: reserved
+ */
+struct adf_gen4_tl_layout {
+	struct adf_gen4_tl_device_data_regs tl_device_data_regs;
+	struct adf_gen4_tl_ring_pair_data_regs
+			tl_ring_pairs_data_regs[ADF_GEN4_TL_MAX_RP_NUM];
+	__u32 reg_tl_msg_cnt;
+	__u32 reserved;
+};
+
+#define ADF_GEN4_TL_LAYOUT_SZ	sizeof(struct adf_gen4_tl_layout)
+#define ADF_GEN4_TL_MSG_CNT_OFF	offsetof(struct adf_gen4_tl_layout, reg_tl_msg_cnt)
+
+#ifdef CONFIG_DEBUG_FS
+void adf_gen4_init_tl_data(struct adf_tl_hw_data *tl_data);
+#else
+static inline void adf_gen4_init_tl_data(struct adf_tl_hw_data *tl_data)
+{
+}
+#endif /* CONFIG_DEBUG_FS */
+#endif /* ADF_GEN4_TL_H */
diff --git a/drivers/crypto/intel/qat/qat_common/adf_init.c b/drivers/crypto/intel/qat/qat_common/adf_init.c
index 81c39f3d07e1..f43ae9111553 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_init.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_init.c
@@ -11,6 +11,7 @@
 #include "adf_heartbeat.h"
 #include "adf_rl.h"
 #include "adf_sysfs_ras_counters.h"
+#include "adf_telemetry.h"
 
 static LIST_HEAD(service_table);
 static DEFINE_MUTEX(service_lock);
@@ -142,6 +143,10 @@ static int adf_dev_init(struct adf_accel_dev *accel_dev)
 	if (ret && ret != -EOPNOTSUPP)
 		return ret;
 
+	ret = adf_tl_init(accel_dev);
+	if (ret && ret != -EOPNOTSUPP)
+		return ret;
+
 	/*
 	 * Subservice initialisation is divided into two stages: init and start.
 	 * This is to facilitate any ordering dependencies between services
@@ -220,6 +225,10 @@ static int adf_dev_start(struct adf_accel_dev *accel_dev)
 	if (ret && ret != -EOPNOTSUPP)
 		return ret;
 
+	ret = adf_tl_start(accel_dev);
+	if (ret && ret != -EOPNOTSUPP)
+		return ret;
+
 	list_for_each_entry(service, &service_table, list) {
 		if (service->event_hld(accel_dev, ADF_EVENT_START)) {
 			dev_err(&GET_DEV(accel_dev),
@@ -279,6 +288,7 @@ static void adf_dev_stop(struct adf_accel_dev *accel_dev)
 	    !test_bit(ADF_STATUS_STARTING, &accel_dev->status))
 		return;
 
+	adf_tl_stop(accel_dev);
 	adf_rl_stop(accel_dev);
 	adf_dbgfs_rm(accel_dev);
 	adf_sysfs_stop_ras(accel_dev);
@@ -374,6 +384,8 @@ static void adf_dev_shutdown(struct adf_accel_dev *accel_dev)
 
 	adf_heartbeat_shutdown(accel_dev);
 
+	adf_tl_shutdown(accel_dev);
+
 	hw_data->disable_iov(accel_dev);
 
 	if (test_bit(ADF_STATUS_IRQ_ALLOCATED, &accel_dev->status)) {
diff --git a/drivers/crypto/intel/qat/qat_common/adf_rl.c b/drivers/crypto/intel/qat/qat_common/adf_rl.c
index 86e3e2152b1b..de1b214dba1f 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_rl.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_rl.c
@@ -812,17 +812,16 @@ static int add_update_sla(struct adf_accel_dev *accel_dev,
 	if (!sla_in) {
 		dev_warn(&GET_DEV(accel_dev),
 			 "SLA input data pointer is missing\n");
-		ret = -EFAULT;
-		goto ret_err;
+		return -EFAULT;
 	}
 
+	mutex_lock(&rl_data->rl_lock);
+
 	/* Input validation */
 	ret = validate_user_input(accel_dev, sla_in, is_update);
 	if (ret)
 		goto ret_err;
 
-	mutex_lock(&rl_data->rl_lock);
-
 	if (is_update) {
 		ret = validate_sla_id(accel_dev, sla_in->sla_id);
 		if (ret)
diff --git a/drivers/crypto/intel/qat/qat_common/adf_rl.h b/drivers/crypto/intel/qat/qat_common/adf_rl.h
index eb5a330f8543..269c6656fb90 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_rl.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_rl.h
@@ -79,6 +79,7 @@ struct adf_rl_interface_data {
 	struct adf_rl_sla_input_data input;
 	enum adf_base_services cap_rem_srv;
 	struct rw_semaphore lock;
+	bool sysfs_added;
 };
 
 struct adf_rl_hw_data {
diff --git a/drivers/crypto/intel/qat/qat_common/adf_sysfs.c b/drivers/crypto/intel/qat/qat_common/adf_sysfs.c
index ddffc98119c6..d450dad32c9e 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_sysfs.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_sysfs.c
@@ -215,6 +215,9 @@ static ssize_t rp2srv_show(struct device *dev, struct device_attribute *attr,
 	enum adf_cfg_service_type svc;
 
 	accel_dev = adf_devmgr_pci_to_accel_dev(to_pci_dev(dev));
+	if (!accel_dev)
+		return -EINVAL;
+
 	hw_data = GET_HW_DATA(accel_dev);
 
 	if (accel_dev->sysfs.ring_num == UNSET_RING_NUM)
@@ -242,7 +245,8 @@ static ssize_t rp2srv_store(struct device *dev, struct device_attribute *attr,
 			    const char *buf, size_t count)
 {
 	struct adf_accel_dev *accel_dev;
-	int ring, num_rings, ret;
+	int num_rings, ret;
+	unsigned int ring;
 
 	accel_dev = adf_devmgr_pci_to_accel_dev(to_pci_dev(dev));
 	if (!accel_dev)
diff --git a/drivers/crypto/intel/qat/qat_common/adf_sysfs_ras_counters.c b/drivers/crypto/intel/qat/qat_common/adf_sysfs_ras_counters.c
index cffe2d722995..e97c67c87b3c 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_sysfs_ras_counters.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_sysfs_ras_counters.c
@@ -99,6 +99,8 @@ void adf_sysfs_start_ras(struct adf_accel_dev *accel_dev)
 	if (device_add_group(&GET_DEV(accel_dev), &qat_ras_group))
 		dev_err(&GET_DEV(accel_dev),
 			"Failed to create qat_ras attribute group.\n");
+
+	accel_dev->ras_errors.sysfs_added = true;
 }
 
 void adf_sysfs_stop_ras(struct adf_accel_dev *accel_dev)
@@ -106,7 +108,10 @@ void adf_sysfs_stop_ras(struct adf_accel_dev *accel_dev)
 	if (!accel_dev->ras_errors.enabled)
 		return;
 
-	device_remove_group(&GET_DEV(accel_dev), &qat_ras_group);
+	if (accel_dev->ras_errors.sysfs_added) {
+		device_remove_group(&GET_DEV(accel_dev), &qat_ras_group);
+		accel_dev->ras_errors.sysfs_added = false;
+	}
 
 	ADF_RAS_ERR_CTR_CLEAR(accel_dev->ras_errors);
 }
diff --git a/drivers/crypto/intel/qat/qat_common/adf_sysfs_rl.c b/drivers/crypto/intel/qat/qat_common/adf_sysfs_rl.c
index abf9c52474ec..bedb514d4e30 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_sysfs_rl.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_sysfs_rl.c
@@ -441,11 +441,19 @@ int adf_sysfs_rl_add(struct adf_accel_dev *accel_dev)
 
 	data->cap_rem_srv = ADF_SVC_NONE;
 	data->input.srv = ADF_SVC_NONE;
+	data->sysfs_added = true;
 
 	return ret;
 }
 
 void adf_sysfs_rl_rm(struct adf_accel_dev *accel_dev)
 {
+	struct adf_rl_interface_data *data;
+
+	data = &GET_RL_STRUCT(accel_dev);
+	if (!data->sysfs_added)
+		return;
+
 	device_remove_group(&GET_DEV(accel_dev), &qat_rl_group);
+	data->sysfs_added = false;
 }
diff --git a/drivers/crypto/intel/qat/qat_common/adf_telemetry.c b/drivers/crypto/intel/qat/qat_common/adf_telemetry.c
new file mode 100644
index 000000000000..2ff714d11bd2
--- /dev/null
+++ b/drivers/crypto/intel/qat/qat_common/adf_telemetry.c
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2023 Intel Corporation. */
+#define dev_fmt(fmt) "Telemetry: " fmt
+
+#include <asm/errno.h>
+#include <linux/atomic.h>
+#include <linux/device.h>
+#include <linux/dev_printk.h>
+#include <linux/dma-mapping.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/workqueue.h>
+
+#include "adf_admin.h"
+#include "adf_accel_devices.h"
+#include "adf_common_drv.h"
+#include "adf_telemetry.h"
+
+#define TL_IS_ZERO(input)	((input) == 0)
+
+static bool is_tl_supported(struct adf_accel_dev *accel_dev)
+{
+	u16 fw_caps =  GET_HW_DATA(accel_dev)->fw_capabilities;
+
+	return fw_caps & TL_CAPABILITY_BIT;
+}
+
+static int validate_tl_data(struct adf_tl_hw_data *tl_data)
+{
+	if (!tl_data->dev_counters ||
+	    TL_IS_ZERO(tl_data->num_dev_counters) ||
+	    !tl_data->sl_util_counters ||
+	    !tl_data->sl_exec_counters ||
+	    !tl_data->rp_counters ||
+	    TL_IS_ZERO(tl_data->num_rp_counters))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+static int adf_tl_alloc_mem(struct adf_accel_dev *accel_dev)
+{
+	struct adf_tl_hw_data *tl_data = &GET_TL_DATA(accel_dev);
+	struct device *dev = &GET_DEV(accel_dev);
+	size_t regs_sz = tl_data->layout_sz;
+	struct adf_telemetry *telemetry;
+	int node = dev_to_node(dev);
+	void *tl_data_regs;
+	unsigned int i;
+
+	telemetry = kzalloc_node(sizeof(*telemetry), GFP_KERNEL, node);
+	if (!telemetry)
+		return -ENOMEM;
+
+	telemetry->rp_num_indexes = kmalloc_array(tl_data->max_rp,
+						  sizeof(*telemetry->rp_num_indexes),
+						  GFP_KERNEL);
+	if (!telemetry->rp_num_indexes)
+		goto err_free_tl;
+
+	telemetry->regs_hist_buff = kmalloc_array(tl_data->num_hbuff,
+						  sizeof(*telemetry->regs_hist_buff),
+						  GFP_KERNEL);
+	if (!telemetry->regs_hist_buff)
+		goto err_free_rp_indexes;
+
+	telemetry->regs_data = dma_alloc_coherent(dev, regs_sz,
+						  &telemetry->regs_data_p,
+						  GFP_KERNEL);
+	if (!telemetry->regs_data)
+		goto err_free_regs_hist_buff;
+
+	for (i = 0; i < tl_data->num_hbuff; i++) {
+		tl_data_regs = kzalloc_node(regs_sz, GFP_KERNEL, node);
+		if (!tl_data_regs)
+			goto err_free_dma;
+
+		telemetry->regs_hist_buff[i] = tl_data_regs;
+	}
+
+	accel_dev->telemetry = telemetry;
+
+	return 0;
+
+err_free_dma:
+	dma_free_coherent(dev, regs_sz, telemetry->regs_data,
+			  telemetry->regs_data_p);
+
+	while (i--)
+		kfree(telemetry->regs_hist_buff[i]);
+
+err_free_regs_hist_buff:
+	kfree(telemetry->regs_hist_buff);
+err_free_rp_indexes:
+	kfree(telemetry->rp_num_indexes);
+err_free_tl:
+	kfree(telemetry);
+
+	return -ENOMEM;
+}
+
+static void adf_tl_free_mem(struct adf_accel_dev *accel_dev)
+{
+	struct adf_tl_hw_data *tl_data = &GET_TL_DATA(accel_dev);
+	struct adf_telemetry *telemetry = accel_dev->telemetry;
+	struct device *dev = &GET_DEV(accel_dev);
+	size_t regs_sz = tl_data->layout_sz;
+	unsigned int i;
+
+	for (i = 0; i < tl_data->num_hbuff; i++)
+		kfree(telemetry->regs_hist_buff[i]);
+
+	dma_free_coherent(dev, regs_sz, telemetry->regs_data,
+			  telemetry->regs_data_p);
+
+	kfree(telemetry->regs_hist_buff);
+	kfree(telemetry->rp_num_indexes);
+	kfree(telemetry);
+	accel_dev->telemetry = NULL;
+}
+
+static unsigned long get_next_timeout(void)
+{
+	return msecs_to_jiffies(ADF_TL_TIMER_INT_MS);
+}
+
+static void snapshot_regs(struct adf_telemetry *telemetry, size_t size)
+{
+	void *dst = telemetry->regs_hist_buff[telemetry->hb_num];
+	void *src = telemetry->regs_data;
+
+	memcpy(dst, src, size);
+}
+
+static void tl_work_handler(struct work_struct *work)
+{
+	struct delayed_work *delayed_work;
+	struct adf_telemetry *telemetry;
+	struct adf_tl_hw_data *tl_data;
+	u32 msg_cnt, old_msg_cnt;
+	size_t layout_sz;
+	u32 *regs_data;
+	size_t id;
+
+	delayed_work = to_delayed_work(work);
+	telemetry = container_of(delayed_work, struct adf_telemetry, work_ctx);
+	tl_data = &GET_TL_DATA(telemetry->accel_dev);
+	regs_data = telemetry->regs_data;
+
+	id = tl_data->msg_cnt_off / sizeof(*regs_data);
+	layout_sz = tl_data->layout_sz;
+
+	if (!atomic_read(&telemetry->state)) {
+		cancel_delayed_work_sync(&telemetry->work_ctx);
+		return;
+	}
+
+	msg_cnt = regs_data[id];
+	old_msg_cnt = msg_cnt;
+	if (msg_cnt == telemetry->msg_cnt)
+		goto out;
+
+	mutex_lock(&telemetry->regs_hist_lock);
+
+	snapshot_regs(telemetry, layout_sz);
+
+	/* Check if data changed while updating it */
+	msg_cnt = regs_data[id];
+	if (old_msg_cnt != msg_cnt)
+		snapshot_regs(telemetry, layout_sz);
+
+	telemetry->msg_cnt = msg_cnt;
+	telemetry->hb_num++;
+	telemetry->hb_num %= telemetry->hbuffs;
+
+	mutex_unlock(&telemetry->regs_hist_lock);
+
+out:
+	adf_misc_wq_queue_delayed_work(&telemetry->work_ctx, get_next_timeout());
+}
+
+int adf_tl_halt(struct adf_accel_dev *accel_dev)
+{
+	struct adf_telemetry *telemetry = accel_dev->telemetry;
+	struct device *dev = &GET_DEV(accel_dev);
+	int ret;
+
+	cancel_delayed_work_sync(&telemetry->work_ctx);
+	atomic_set(&telemetry->state, 0);
+
+	ret = adf_send_admin_tl_stop(accel_dev);
+	if (ret)
+		dev_err(dev, "failed to stop telemetry\n");
+
+	return ret;
+}
+
+int adf_tl_run(struct adf_accel_dev *accel_dev, int state)
+{
+	struct adf_tl_hw_data *tl_data = &GET_TL_DATA(accel_dev);
+	struct adf_telemetry *telemetry = accel_dev->telemetry;
+	struct device *dev = &GET_DEV(accel_dev);
+	size_t layout_sz = tl_data->layout_sz;
+	int ret;
+
+	ret = adf_send_admin_tl_start(accel_dev, telemetry->regs_data_p,
+				      layout_sz, telemetry->rp_num_indexes,
+				      &telemetry->slice_cnt);
+	if (ret) {
+		dev_err(dev, "failed to start telemetry\n");
+		return ret;
+	}
+
+	telemetry->hbuffs = state;
+	atomic_set(&telemetry->state, state);
+
+	adf_misc_wq_queue_delayed_work(&telemetry->work_ctx, get_next_timeout());
+
+	return 0;
+}
+
+int adf_tl_init(struct adf_accel_dev *accel_dev)
+{
+	struct adf_tl_hw_data *tl_data = &GET_TL_DATA(accel_dev);
+	u8 max_rp = GET_TL_DATA(accel_dev).max_rp;
+	struct device *dev = &GET_DEV(accel_dev);
+	struct adf_telemetry *telemetry;
+	unsigned int i;
+	int ret;
+
+	ret = validate_tl_data(tl_data);
+	if (ret)
+		return ret;
+
+	ret = adf_tl_alloc_mem(accel_dev);
+	if (ret) {
+		dev_err(dev, "failed to initialize: %d\n", ret);
+		return ret;
+	}
+
+	telemetry = accel_dev->telemetry;
+	telemetry->accel_dev = accel_dev;
+
+	mutex_init(&telemetry->wr_lock);
+	mutex_init(&telemetry->regs_hist_lock);
+	INIT_DELAYED_WORK(&telemetry->work_ctx, tl_work_handler);
+
+	for (i = 0; i < max_rp; i++)
+		telemetry->rp_num_indexes[i] = ADF_TL_RP_REGS_DISABLED;
+
+	return 0;
+}
+
+int adf_tl_start(struct adf_accel_dev *accel_dev)
+{
+	struct device *dev = &GET_DEV(accel_dev);
+
+	if (!accel_dev->telemetry)
+		return -EOPNOTSUPP;
+
+	if (!is_tl_supported(accel_dev)) {
+		dev_info(dev, "feature not supported by FW\n");
+		adf_tl_free_mem(accel_dev);
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+void adf_tl_stop(struct adf_accel_dev *accel_dev)
+{
+	if (!accel_dev->telemetry)
+		return;
+
+	if (atomic_read(&accel_dev->telemetry->state))
+		adf_tl_halt(accel_dev);
+}
+
+void adf_tl_shutdown(struct adf_accel_dev *accel_dev)
+{
+	if (!accel_dev->telemetry)
+		return;
+
+	adf_tl_free_mem(accel_dev);
+}
diff --git a/drivers/crypto/intel/qat/qat_common/adf_telemetry.h b/drivers/crypto/intel/qat/qat_common/adf_telemetry.h
new file mode 100644
index 000000000000..9be81cd3b886
--- /dev/null
+++ b/drivers/crypto/intel/qat/qat_common/adf_telemetry.h
@@ -0,0 +1,99 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2023 Intel Corporation. */
+#ifndef ADF_TELEMETRY_H
+#define ADF_TELEMETRY_H
+
+#include <linux/bits.h>
+#include <linux/mutex.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+
+#include "icp_qat_fw_init_admin.h"
+
+struct adf_accel_dev;
+struct adf_tl_dbg_counter;
+struct dentry;
+
+#define ADF_TL_SL_CNT_COUNT		\
+	(sizeof(struct icp_qat_fw_init_admin_slice_cnt) / sizeof(__u8))
+
+#define TL_CAPABILITY_BIT		BIT(1)
+/* Interval within device writes data to DMA region. Value in milliseconds. */
+#define ADF_TL_DATA_WR_INTERVAL_MS	1000
+/* Interval within timer interrupt should be handled. Value in milliseconds. */
+#define ADF_TL_TIMER_INT_MS		(ADF_TL_DATA_WR_INTERVAL_MS / 2)
+
+#define ADF_TL_RP_REGS_DISABLED		(0xff)
+
+struct adf_tl_hw_data {
+	size_t layout_sz;
+	size_t slice_reg_sz;
+	size_t rp_reg_sz;
+	size_t msg_cnt_off;
+	const struct adf_tl_dbg_counter *dev_counters;
+	const struct adf_tl_dbg_counter *sl_util_counters;
+	const struct adf_tl_dbg_counter *sl_exec_counters;
+	const struct adf_tl_dbg_counter *rp_counters;
+	u8 num_hbuff;
+	u8 cpp_ns_per_cycle;
+	u8 bw_units_to_bytes;
+	u8 num_dev_counters;
+	u8 num_rp_counters;
+	u8 max_rp;
+};
+
+struct adf_telemetry {
+	struct adf_accel_dev *accel_dev;
+	atomic_t state;
+	u32 hbuffs;
+	int hb_num;
+	u32 msg_cnt;
+	dma_addr_t regs_data_p; /* bus address for DMA mapping */
+	void *regs_data; /* virtual address for DMA mapping */
+	/**
+	 * @regs_hist_buff: array of pointers to copies of the last @hbuffs
+	 * values of @regs_data
+	 */
+	void **regs_hist_buff;
+	struct dentry *dbg_dir;
+	u8 *rp_num_indexes;
+	/**
+	 * @regs_hist_lock: protects from race conditions between write and read
+	 * to the copies referenced by @regs_hist_buff
+	 */
+	struct mutex regs_hist_lock;
+	/**
+	 * @wr_lock: protects from concurrent writes to debugfs telemetry files
+	 */
+	struct mutex wr_lock;
+	struct delayed_work work_ctx;
+	struct icp_qat_fw_init_admin_slice_cnt slice_cnt;
+};
+
+#ifdef CONFIG_DEBUG_FS
+int adf_tl_init(struct adf_accel_dev *accel_dev);
+int adf_tl_start(struct adf_accel_dev *accel_dev);
+void adf_tl_stop(struct adf_accel_dev *accel_dev);
+void adf_tl_shutdown(struct adf_accel_dev *accel_dev);
+int adf_tl_run(struct adf_accel_dev *accel_dev, int state);
+int adf_tl_halt(struct adf_accel_dev *accel_dev);
+#else
+static inline int adf_tl_init(struct adf_accel_dev *accel_dev)
+{
+	return 0;
+}
+
+static inline int adf_tl_start(struct adf_accel_dev *accel_dev)
+{
+	return 0;
+}
+
+static inline void adf_tl_stop(struct adf_accel_dev *accel_dev)
+{
+}
+
+static inline void adf_tl_shutdown(struct adf_accel_dev *accel_dev)
+{
+}
+#endif /* CONFIG_DEBUG_FS */
+#endif /* ADF_TELEMETRY_H */
diff --git a/drivers/crypto/intel/qat/qat_common/adf_tl_debugfs.c b/drivers/crypto/intel/qat/qat_common/adf_tl_debugfs.c
new file mode 100644
index 000000000000..c8241f5a0a26
--- /dev/null
+++ b/drivers/crypto/intel/qat/qat_common/adf_tl_debugfs.c
@@ -0,0 +1,710 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2023 Intel Corporation. */
+#define dev_fmt(fmt) "Telemetry debugfs: " fmt
+
+#include <linux/atomic.h>
+#include <linux/debugfs.h>
+#include <linux/dev_printk.h>
+#include <linux/dcache.h>
+#include <linux/file.h>
+#include <linux/kernel.h>
+#include <linux/math64.h>
+#include <linux/mutex.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/units.h>
+
+#include "adf_accel_devices.h"
+#include "adf_cfg_strings.h"
+#include "adf_telemetry.h"
+#include "adf_tl_debugfs.h"
+
+#define TL_VALUE_MIN_PADDING	20
+#define TL_KEY_MIN_PADDING	23
+#define TL_RP_SRV_UNKNOWN	"Unknown"
+
+static int tl_collect_values_u32(struct adf_telemetry *telemetry,
+				 size_t counter_offset, u64 *arr)
+{
+	unsigned int samples, hb_idx, i;
+	u32 *regs_hist_buff;
+	u32 counter_val;
+
+	samples = min(telemetry->msg_cnt, telemetry->hbuffs);
+	hb_idx = telemetry->hb_num + telemetry->hbuffs - samples;
+
+	mutex_lock(&telemetry->regs_hist_lock);
+
+	for (i = 0; i < samples; i++) {
+		regs_hist_buff = telemetry->regs_hist_buff[hb_idx % telemetry->hbuffs];
+		counter_val = regs_hist_buff[counter_offset / sizeof(counter_val)];
+		arr[i] = counter_val;
+		hb_idx++;
+	}
+
+	mutex_unlock(&telemetry->regs_hist_lock);
+
+	return samples;
+}
+
+static int tl_collect_values_u64(struct adf_telemetry *telemetry,
+				 size_t counter_offset, u64 *arr)
+{
+	unsigned int samples, hb_idx, i;
+	u64 *regs_hist_buff;
+	u64 counter_val;
+
+	samples = min(telemetry->msg_cnt, telemetry->hbuffs);
+	hb_idx = telemetry->hb_num + telemetry->hbuffs - samples;
+
+	mutex_lock(&telemetry->regs_hist_lock);
+
+	for (i = 0; i < samples; i++) {
+		regs_hist_buff = telemetry->regs_hist_buff[hb_idx % telemetry->hbuffs];
+		counter_val = regs_hist_buff[counter_offset / sizeof(counter_val)];
+		arr[i] = counter_val;
+		hb_idx++;
+	}
+
+	mutex_unlock(&telemetry->regs_hist_lock);
+
+	return samples;
+}
+
+/**
+ * avg_array() - Return average of values within an array.
+ * @array: Array of values.
+ * @len: Number of elements.
+ *
+ * This algorithm computes average of an array without running into overflow.
+ *
+ * Return: average of values.
+ */
+#define avg_array(array, len) (				\
+{							\
+	typeof(&(array)[0]) _array = (array);		\
+	__unqual_scalar_typeof(_array[0]) _x = 0;	\
+	__unqual_scalar_typeof(_array[0]) _y = 0;	\
+	__unqual_scalar_typeof(_array[0]) _a, _b;	\
+	typeof(len) _len = (len);			\
+	size_t _i;					\
+							\
+	for (_i = 0; _i < _len; _i++) {			\
+		_a = _array[_i];			\
+		_b = do_div(_a, _len);			\
+		_x += _a;				\
+		if (_y >= _len - _b) {			\
+			_x++;				\
+			_y -= _len - _b;		\
+		} else {				\
+			_y += _b;			\
+		}					\
+	}						\
+	do_div(_y, _len);				\
+	(_x + _y);					\
+})
+
+/* Calculation function for simple counter. */
+static int tl_calc_count(struct adf_telemetry *telemetry,
+			 const struct adf_tl_dbg_counter *ctr,
+			 struct adf_tl_dbg_aggr_values *vals)
+{
+	struct adf_tl_hw_data *tl_data = &GET_TL_DATA(telemetry->accel_dev);
+	u64 *hist_vals;
+	int sample_cnt;
+	int ret = 0;
+
+	hist_vals = kmalloc_array(tl_data->num_hbuff, sizeof(*hist_vals),
+				  GFP_KERNEL);
+	if (!hist_vals)
+		return -ENOMEM;
+
+	memset(vals, 0, sizeof(*vals));
+	sample_cnt = tl_collect_values_u32(telemetry, ctr->offset1, hist_vals);
+	if (!sample_cnt)
+		goto out_free_hist_vals;
+
+	vals->curr = hist_vals[sample_cnt - 1];
+	vals->min = min_array(hist_vals, sample_cnt);
+	vals->max = max_array(hist_vals, sample_cnt);
+	vals->avg = avg_array(hist_vals, sample_cnt);
+
+out_free_hist_vals:
+	kfree(hist_vals);
+	return ret;
+}
+
+/* Convert CPP bus cycles to ns. */
+static int tl_cycles_to_ns(struct adf_telemetry *telemetry,
+			   const struct adf_tl_dbg_counter *ctr,
+			   struct adf_tl_dbg_aggr_values *vals)
+{
+	struct adf_tl_hw_data *tl_data = &GET_TL_DATA(telemetry->accel_dev);
+	u8 cpp_ns_per_cycle = tl_data->cpp_ns_per_cycle;
+	int ret;
+
+	ret = tl_calc_count(telemetry, ctr, vals);
+	if (ret)
+		return ret;
+
+	vals->curr *= cpp_ns_per_cycle;
+	vals->min *= cpp_ns_per_cycle;
+	vals->max *= cpp_ns_per_cycle;
+	vals->avg *= cpp_ns_per_cycle;
+
+	return 0;
+}
+
+/*
+ * Compute latency cumulative average with division of accumulated value
+ * by sample count. Returned value is in ns.
+ */
+static int tl_lat_acc_avg(struct adf_telemetry *telemetry,
+			  const struct adf_tl_dbg_counter *ctr,
+			  struct adf_tl_dbg_aggr_values *vals)
+{
+	struct adf_tl_hw_data *tl_data = &GET_TL_DATA(telemetry->accel_dev);
+	u8 cpp_ns_per_cycle = tl_data->cpp_ns_per_cycle;
+	u8 num_hbuff = tl_data->num_hbuff;
+	int sample_cnt, i;
+	u64 *hist_vals;
+	u64 *hist_cnt;
+	int ret = 0;
+
+	hist_vals = kmalloc_array(num_hbuff, sizeof(*hist_vals), GFP_KERNEL);
+	if (!hist_vals)
+		return -ENOMEM;
+
+	hist_cnt = kmalloc_array(num_hbuff, sizeof(*hist_cnt), GFP_KERNEL);
+	if (!hist_cnt) {
+		ret = -ENOMEM;
+		goto out_free_hist_vals;
+	}
+
+	memset(vals, 0, sizeof(*vals));
+	sample_cnt = tl_collect_values_u64(telemetry, ctr->offset1, hist_vals);
+	if (!sample_cnt)
+		goto out_free_hist_cnt;
+
+	tl_collect_values_u32(telemetry, ctr->offset2, hist_cnt);
+
+	for (i = 0; i < sample_cnt; i++) {
+		/* Avoid division by 0 if count is 0. */
+		if (hist_cnt[i])
+			hist_vals[i] = div_u64(hist_vals[i] * cpp_ns_per_cycle,
+					       hist_cnt[i]);
+		else
+			hist_vals[i] = 0;
+	}
+
+	vals->curr = hist_vals[sample_cnt - 1];
+	vals->min = min_array(hist_vals, sample_cnt);
+	vals->max = max_array(hist_vals, sample_cnt);
+	vals->avg = avg_array(hist_vals, sample_cnt);
+
+out_free_hist_cnt:
+	kfree(hist_cnt);
+out_free_hist_vals:
+	kfree(hist_vals);
+	return ret;
+}
+
+/* Convert HW raw bandwidth units to Mbps. */
+static int tl_bw_hw_units_to_mbps(struct adf_telemetry *telemetry,
+				  const struct adf_tl_dbg_counter *ctr,
+				  struct adf_tl_dbg_aggr_values *vals)
+{
+	struct adf_tl_hw_data *tl_data = &GET_TL_DATA(telemetry->accel_dev);
+	u16 bw_hw_2_bits = tl_data->bw_units_to_bytes * BITS_PER_BYTE;
+	u64 *hist_vals;
+	int sample_cnt;
+	int ret = 0;
+
+	hist_vals = kmalloc_array(tl_data->num_hbuff, sizeof(*hist_vals),
+				  GFP_KERNEL);
+	if (!hist_vals)
+		return -ENOMEM;
+
+	memset(vals, 0, sizeof(*vals));
+	sample_cnt = tl_collect_values_u32(telemetry, ctr->offset1, hist_vals);
+	if (!sample_cnt)
+		goto out_free_hist_vals;
+
+	vals->curr = div_u64(hist_vals[sample_cnt - 1] * bw_hw_2_bits, MEGA);
+	vals->min = div_u64(min_array(hist_vals, sample_cnt) * bw_hw_2_bits, MEGA);
+	vals->max = div_u64(max_array(hist_vals, sample_cnt) * bw_hw_2_bits, MEGA);
+	vals->avg = div_u64(avg_array(hist_vals, sample_cnt) * bw_hw_2_bits, MEGA);
+
+out_free_hist_vals:
+	kfree(hist_vals);
+	return ret;
+}
+
+static void tl_seq_printf_counter(struct adf_telemetry *telemetry,
+				  struct seq_file *s, const char *name,
+				  struct adf_tl_dbg_aggr_values *vals)
+{
+	seq_printf(s, "%-*s", TL_KEY_MIN_PADDING, name);
+	seq_printf(s, "%*llu", TL_VALUE_MIN_PADDING, vals->curr);
+	if (atomic_read(&telemetry->state) > 1) {
+		seq_printf(s, "%*llu", TL_VALUE_MIN_PADDING, vals->min);
+		seq_printf(s, "%*llu", TL_VALUE_MIN_PADDING, vals->max);
+		seq_printf(s, "%*llu", TL_VALUE_MIN_PADDING, vals->avg);
+	}
+	seq_puts(s, "\n");
+}
+
+static int tl_calc_and_print_counter(struct adf_telemetry *telemetry,
+				     struct seq_file *s,
+				     const struct adf_tl_dbg_counter *ctr,
+				     const char *name)
+{
+	const char *counter_name = name ? name : ctr->name;
+	enum adf_tl_counter_type type = ctr->type;
+	struct adf_tl_dbg_aggr_values vals;
+	int ret;
+
+	switch (type) {
+	case ADF_TL_SIMPLE_COUNT:
+		ret = tl_calc_count(telemetry, ctr, &vals);
+		break;
+	case ADF_TL_COUNTER_NS:
+		ret = tl_cycles_to_ns(telemetry, ctr, &vals);
+		break;
+	case ADF_TL_COUNTER_NS_AVG:
+		ret = tl_lat_acc_avg(telemetry, ctr, &vals);
+		break;
+	case ADF_TL_COUNTER_MBPS:
+		ret = tl_bw_hw_units_to_mbps(telemetry, ctr, &vals);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (ret)
+		return ret;
+
+	tl_seq_printf_counter(telemetry, s, counter_name, &vals);
+
+	return 0;
+}
+
+static int tl_print_sl_counter(struct adf_telemetry *telemetry,
+			       const struct adf_tl_dbg_counter *ctr,
+			       struct seq_file *s, u8 cnt_id)
+{
+	size_t sl_regs_sz = GET_TL_DATA(telemetry->accel_dev).slice_reg_sz;
+	struct adf_tl_dbg_counter slice_ctr;
+	size_t offset_inc = cnt_id * sl_regs_sz;
+	char cnt_name[MAX_COUNT_NAME_SIZE];
+
+	snprintf(cnt_name, MAX_COUNT_NAME_SIZE, "%s%d", ctr->name, cnt_id);
+	slice_ctr = *ctr;
+	slice_ctr.offset1 += offset_inc;
+
+	return tl_calc_and_print_counter(telemetry, s, &slice_ctr, cnt_name);
+}
+
+static int tl_calc_and_print_sl_counters(struct adf_accel_dev *accel_dev,
+					 struct seq_file *s, u8 cnt_type, u8 cnt_id)
+{
+	struct adf_tl_hw_data *tl_data = &GET_TL_DATA(accel_dev);
+	struct adf_telemetry *telemetry = accel_dev->telemetry;
+	const struct adf_tl_dbg_counter *sl_tl_util_counters;
+	const struct adf_tl_dbg_counter *sl_tl_exec_counters;
+	const struct adf_tl_dbg_counter *ctr;
+	int ret;
+
+	sl_tl_util_counters = tl_data->sl_util_counters;
+	sl_tl_exec_counters = tl_data->sl_exec_counters;
+
+	ctr = &sl_tl_util_counters[cnt_type];
+
+	ret = tl_print_sl_counter(telemetry, ctr, s, cnt_id);
+	if (ret) {
+		dev_notice(&GET_DEV(accel_dev),
+			   "invalid slice utilization counter type\n");
+		return ret;
+	}
+
+	ctr = &sl_tl_exec_counters[cnt_type];
+
+	ret = tl_print_sl_counter(telemetry, ctr, s, cnt_id);
+	if (ret) {
+		dev_notice(&GET_DEV(accel_dev),
+			   "invalid slice execution counter type\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static void tl_print_msg_cnt(struct seq_file *s, u32 msg_cnt)
+{
+	seq_printf(s, "%-*s", TL_KEY_MIN_PADDING, SNAPSHOT_CNT_MSG);
+	seq_printf(s, "%*u\n", TL_VALUE_MIN_PADDING, msg_cnt);
+}
+
+static int tl_print_dev_data(struct adf_accel_dev *accel_dev,
+			     struct seq_file *s)
+{
+	struct adf_tl_hw_data *tl_data = &GET_TL_DATA(accel_dev);
+	struct adf_telemetry *telemetry = accel_dev->telemetry;
+	const struct adf_tl_dbg_counter *dev_tl_counters;
+	u8 num_dev_counters = tl_data->num_dev_counters;
+	u8 *sl_cnt = (u8 *)&telemetry->slice_cnt;
+	const struct adf_tl_dbg_counter *ctr;
+	unsigned int i;
+	int ret;
+	u8 j;
+
+	if (!atomic_read(&telemetry->state)) {
+		dev_info(&GET_DEV(accel_dev), "not enabled\n");
+		return -EPERM;
+	}
+
+	dev_tl_counters = tl_data->dev_counters;
+
+	tl_print_msg_cnt(s, telemetry->msg_cnt);
+
+	/* Print device level telemetry. */
+	for (i = 0; i < num_dev_counters; i++) {
+		ctr = &dev_tl_counters[i];
+		ret = tl_calc_and_print_counter(telemetry, s, ctr, NULL);
+		if (ret) {
+			dev_notice(&GET_DEV(accel_dev),
+				   "invalid counter type\n");
+			return ret;
+		}
+	}
+
+	/* Print per slice telemetry. */
+	for (i = 0; i < ADF_TL_SL_CNT_COUNT; i++) {
+		for (j = 0; j < sl_cnt[i]; j++) {
+			ret = tl_calc_and_print_sl_counters(accel_dev, s, i, j);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int tl_dev_data_show(struct seq_file *s, void *unused)
+{
+	struct adf_accel_dev *accel_dev = s->private;
+
+	if (!accel_dev)
+		return -EINVAL;
+
+	return tl_print_dev_data(accel_dev, s);
+}
+DEFINE_SHOW_ATTRIBUTE(tl_dev_data);
+
+static int tl_control_show(struct seq_file *s, void *unused)
+{
+	struct adf_accel_dev *accel_dev = s->private;
+
+	if (!accel_dev)
+		return -EINVAL;
+
+	seq_printf(s, "%d\n", atomic_read(&accel_dev->telemetry->state));
+
+	return 0;
+}
+
+static ssize_t tl_control_write(struct file *file, const char __user *userbuf,
+				size_t count, loff_t *ppos)
+{
+	struct seq_file *seq_f = file->private_data;
+	struct adf_accel_dev *accel_dev;
+	struct adf_telemetry *telemetry;
+	struct adf_tl_hw_data *tl_data;
+	struct device *dev;
+	u32 input;
+	int ret;
+
+	accel_dev = seq_f->private;
+	if (!accel_dev)
+		return -EINVAL;
+
+	tl_data = &GET_TL_DATA(accel_dev);
+	telemetry = accel_dev->telemetry;
+	dev = &GET_DEV(accel_dev);
+
+	mutex_lock(&telemetry->wr_lock);
+
+	ret = kstrtou32_from_user(userbuf, count, 10, &input);
+	if (ret)
+		goto unlock_and_exit;
+
+	if (input > tl_data->num_hbuff) {
+		dev_info(dev, "invalid control input\n");
+		ret = -EINVAL;
+		goto unlock_and_exit;
+	}
+
+	/* If input is 0, just stop telemetry. */
+	if (!input) {
+		ret = adf_tl_halt(accel_dev);
+		if (!ret)
+			ret = count;
+
+		goto unlock_and_exit;
+	}
+
+	/* If TL is already enabled, stop it. */
+	if (atomic_read(&telemetry->state)) {
+		dev_info(dev, "already enabled, restarting.\n");
+		ret = adf_tl_halt(accel_dev);
+		if (ret)
+			goto unlock_and_exit;
+	}
+
+	ret = adf_tl_run(accel_dev, input);
+	if (ret)
+		goto unlock_and_exit;
+
+	ret = count;
+
+unlock_and_exit:
+	mutex_unlock(&telemetry->wr_lock);
+	return ret;
+}
+DEFINE_SHOW_STORE_ATTRIBUTE(tl_control);
+
+static int get_rp_index_from_file(const struct file *f, u8 *rp_id, u8 rp_num)
+{
+	char alpha;
+	u8 index;
+	int ret;
+
+	ret = sscanf(f->f_path.dentry->d_name.name, ADF_TL_RP_REGS_FNAME, &alpha);
+	if (ret != 1)
+		return -EINVAL;
+
+	index = ADF_TL_DBG_RP_INDEX_ALPHA(alpha);
+	*rp_id = index;
+
+	return 0;
+}
+
+static int adf_tl_dbg_change_rp_index(struct adf_accel_dev *accel_dev,
+				      unsigned int new_rp_num,
+				      unsigned int rp_regs_index)
+{
+	struct adf_hw_device_data *hw_data = GET_HW_DATA(accel_dev);
+	struct adf_telemetry *telemetry = accel_dev->telemetry;
+	struct device *dev = &GET_DEV(accel_dev);
+	unsigned int i;
+	u8 curr_state;
+	int ret;
+
+	if (new_rp_num >= hw_data->num_rps) {
+		dev_info(dev, "invalid Ring Pair number selected\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < hw_data->tl_data.max_rp; i++) {
+		if (telemetry->rp_num_indexes[i] == new_rp_num) {
+			dev_info(dev, "RP nr: %d is already selected in slot rp_%c_data\n",
+				 new_rp_num, ADF_TL_DBG_RP_ALPHA_INDEX(i));
+			return 0;
+		}
+	}
+
+	dev_dbg(dev, "selecting RP nr %u into slot rp_%c_data\n",
+		new_rp_num, ADF_TL_DBG_RP_ALPHA_INDEX(rp_regs_index));
+
+	curr_state = atomic_read(&telemetry->state);
+
+	if (curr_state) {
+		ret = adf_tl_halt(accel_dev);
+		if (ret)
+			return ret;
+
+		telemetry->rp_num_indexes[rp_regs_index] = new_rp_num;
+
+		ret = adf_tl_run(accel_dev, curr_state);
+		if (ret)
+			return ret;
+	} else {
+		telemetry->rp_num_indexes[rp_regs_index] = new_rp_num;
+	}
+
+	return 0;
+}
+
+static void tl_print_rp_srv(struct adf_accel_dev *accel_dev, struct seq_file *s,
+			    u8 rp_idx)
+{
+	u32 banks_per_vf = GET_HW_DATA(accel_dev)->num_banks_per_vf;
+	enum adf_cfg_service_type svc;
+
+	seq_printf(s, "%-*s", TL_KEY_MIN_PADDING, RP_SERVICE_TYPE);
+
+	svc = GET_SRV_TYPE(accel_dev, rp_idx % banks_per_vf);
+	switch (svc) {
+	case COMP:
+		seq_printf(s, "%*s\n", TL_VALUE_MIN_PADDING, ADF_CFG_DC);
+		break;
+	case SYM:
+		seq_printf(s, "%*s\n", TL_VALUE_MIN_PADDING, ADF_CFG_SYM);
+		break;
+	case ASYM:
+		seq_printf(s, "%*s\n", TL_VALUE_MIN_PADDING, ADF_CFG_ASYM);
+		break;
+	default:
+		seq_printf(s, "%*s\n", TL_VALUE_MIN_PADDING, TL_RP_SRV_UNKNOWN);
+		break;
+	}
+}
+
+static int tl_print_rp_data(struct adf_accel_dev *accel_dev, struct seq_file *s,
+			    u8 rp_regs_index)
+{
+	struct adf_tl_hw_data *tl_data = &GET_TL_DATA(accel_dev);
+	struct adf_telemetry *telemetry = accel_dev->telemetry;
+	const struct adf_tl_dbg_counter *rp_tl_counters;
+	u8 num_rp_counters = tl_data->num_rp_counters;
+	size_t rp_regs_sz = tl_data->rp_reg_sz;
+	struct adf_tl_dbg_counter ctr;
+	unsigned int i;
+	u8 rp_idx;
+	int ret;
+
+	if (!atomic_read(&telemetry->state)) {
+		dev_info(&GET_DEV(accel_dev), "not enabled\n");
+		return -EPERM;
+	}
+
+	rp_tl_counters = tl_data->rp_counters;
+	rp_idx = telemetry->rp_num_indexes[rp_regs_index];
+
+	if (rp_idx == ADF_TL_RP_REGS_DISABLED) {
+		dev_info(&GET_DEV(accel_dev), "no RP number selected in rp_%c_data\n",
+			 ADF_TL_DBG_RP_ALPHA_INDEX(rp_regs_index));
+		return -EPERM;
+	}
+
+	tl_print_msg_cnt(s, telemetry->msg_cnt);
+	seq_printf(s, "%-*s", TL_KEY_MIN_PADDING, RP_NUM_INDEX);
+	seq_printf(s, "%*d\n", TL_VALUE_MIN_PADDING, rp_idx);
+	tl_print_rp_srv(accel_dev, s, rp_idx);
+
+	for (i = 0; i < num_rp_counters; i++) {
+		ctr = rp_tl_counters[i];
+		ctr.offset1 += rp_regs_sz * rp_regs_index;
+		ctr.offset2 += rp_regs_sz * rp_regs_index;
+		ret = tl_calc_and_print_counter(telemetry, s, &ctr, NULL);
+		if (ret) {
+			dev_dbg(&GET_DEV(accel_dev),
+				"invalid RP counter type\n");
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int tl_rp_data_show(struct seq_file *s, void *unused)
+{
+	struct adf_accel_dev *accel_dev = s->private;
+	u8 rp_regs_index;
+	u8 max_rp;
+	int ret;
+
+	if (!accel_dev)
+		return -EINVAL;
+
+	max_rp = GET_TL_DATA(accel_dev).max_rp;
+	ret = get_rp_index_from_file(s->file, &rp_regs_index, max_rp);
+	if (ret) {
+		dev_dbg(&GET_DEV(accel_dev), "invalid RP data file name\n");
+		return ret;
+	}
+
+	return tl_print_rp_data(accel_dev, s, rp_regs_index);
+}
+
+static ssize_t tl_rp_data_write(struct file *file, const char __user *userbuf,
+				size_t count, loff_t *ppos)
+{
+	struct seq_file *seq_f = file->private_data;
+	struct adf_accel_dev *accel_dev;
+	struct adf_telemetry *telemetry;
+	unsigned int new_rp_num;
+	u8 rp_regs_index;
+	u8 max_rp;
+	int ret;
+
+	accel_dev = seq_f->private;
+	if (!accel_dev)
+		return -EINVAL;
+
+	telemetry = accel_dev->telemetry;
+	max_rp = GET_TL_DATA(accel_dev).max_rp;
+
+	mutex_lock(&telemetry->wr_lock);
+
+	ret = get_rp_index_from_file(file, &rp_regs_index, max_rp);
+	if (ret) {
+		dev_dbg(&GET_DEV(accel_dev), "invalid RP data file name\n");
+		goto unlock_and_exit;
+	}
+
+	ret = kstrtou32_from_user(userbuf, count, 10, &new_rp_num);
+	if (ret)
+		goto unlock_and_exit;
+
+	ret = adf_tl_dbg_change_rp_index(accel_dev, new_rp_num, rp_regs_index);
+	if (ret)
+		goto unlock_and_exit;
+
+	ret = count;
+
+unlock_and_exit:
+	mutex_unlock(&telemetry->wr_lock);
+	return ret;
+}
+DEFINE_SHOW_STORE_ATTRIBUTE(tl_rp_data);
+
+void adf_tl_dbgfs_add(struct adf_accel_dev *accel_dev)
+{
+	struct adf_telemetry *telemetry = accel_dev->telemetry;
+	struct dentry *parent = accel_dev->debugfs_dir;
+	u8 max_rp = GET_TL_DATA(accel_dev).max_rp;
+	char name[ADF_TL_RP_REGS_FNAME_SIZE];
+	struct dentry *dir;
+	unsigned int i;
+
+	if (!telemetry)
+		return;
+
+	dir = debugfs_create_dir("telemetry", parent);
+	accel_dev->telemetry->dbg_dir = dir;
+	debugfs_create_file("device_data", 0444, dir, accel_dev, &tl_dev_data_fops);
+	debugfs_create_file("control", 0644, dir, accel_dev, &tl_control_fops);
+
+	for (i = 0; i < max_rp; i++) {
+		snprintf(name, sizeof(name), ADF_TL_RP_REGS_FNAME,
+			 ADF_TL_DBG_RP_ALPHA_INDEX(i));
+		debugfs_create_file(name, 0644, dir, accel_dev, &tl_rp_data_fops);
+	}
+}
+
+void adf_tl_dbgfs_rm(struct adf_accel_dev *accel_dev)
+{
+	struct adf_telemetry *telemetry = accel_dev->telemetry;
+	struct dentry *dbg_dir;
+
+	if (!telemetry)
+		return;
+
+	dbg_dir = telemetry->dbg_dir;
+
+	debugfs_remove_recursive(dbg_dir);
+
+	if (atomic_read(&telemetry->state))
+		adf_tl_halt(accel_dev);
+}
diff --git a/drivers/crypto/intel/qat/qat_common/adf_tl_debugfs.h b/drivers/crypto/intel/qat/qat_common/adf_tl_debugfs.h
new file mode 100644
index 000000000000..11cc9eae19b3
--- /dev/null
+++ b/drivers/crypto/intel/qat/qat_common/adf_tl_debugfs.h
@@ -0,0 +1,117 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2023 Intel Corporation. */
+#ifndef ADF_TL_DEBUGFS_H
+#define ADF_TL_DEBUGFS_H
+
+#include <linux/types.h>
+
+struct adf_accel_dev;
+
+#define MAX_COUNT_NAME_SIZE	32
+#define SNAPSHOT_CNT_MSG	"sample_cnt"
+#define RP_NUM_INDEX		"rp_num"
+#define PCI_TRANS_CNT_NAME	"pci_trans_cnt"
+#define MAX_RD_LAT_NAME		"max_rd_lat"
+#define RD_LAT_ACC_NAME		"rd_lat_acc_avg"
+#define MAX_LAT_NAME		"max_gp_lat"
+#define LAT_ACC_NAME		"gp_lat_acc_avg"
+#define BW_IN_NAME		"bw_in"
+#define BW_OUT_NAME		"bw_out"
+#define PAGE_REQ_LAT_NAME	"at_page_req_lat_avg"
+#define AT_TRANS_LAT_NAME	"at_trans_lat_avg"
+#define AT_MAX_UTLB_USED_NAME	"at_max_tlb_used"
+#define AT_GLOB_DTLB_HIT_NAME	"at_glob_devtlb_hit"
+#define AT_GLOB_DTLB_MISS_NAME	"at_glob_devtlb_miss"
+#define AT_PAYLD_DTLB_HIT_NAME	"tl_at_payld_devtlb_hit"
+#define AT_PAYLD_DTLB_MISS_NAME	"tl_at_payld_devtlb_miss"
+#define RP_SERVICE_TYPE		"service_type"
+
+#define ADF_TL_DBG_RP_ALPHA_INDEX(index) ((index) + 'A')
+#define ADF_TL_DBG_RP_INDEX_ALPHA(alpha) ((alpha) - 'A')
+
+#define ADF_TL_RP_REGS_FNAME		"rp_%c_data"
+#define ADF_TL_RP_REGS_FNAME_SIZE		16
+
+#define ADF_TL_DATA_REG_OFF(reg, qat_gen)	\
+	offsetof(struct adf_##qat_gen##_tl_layout, reg)
+
+#define ADF_TL_DEV_REG_OFF(reg, qat_gen)			\
+	(ADF_TL_DATA_REG_OFF(tl_device_data_regs, qat_gen) +	\
+	offsetof(struct adf_##qat_gen##_tl_device_data_regs, reg))
+
+#define ADF_TL_SLICE_REG_OFF(slice, reg, qat_gen)		\
+	(ADF_TL_DEV_REG_OFF(slice##_slices[0], qat_gen) +	\
+	offsetof(struct adf_##qat_gen##_tl_slice_data_regs, reg))
+
+#define ADF_TL_RP_REG_OFF(reg, qat_gen)					\
+	(ADF_TL_DATA_REG_OFF(tl_ring_pairs_data_regs[0], qat_gen) +	\
+	offsetof(struct adf_##qat_gen##_tl_ring_pair_data_regs, reg))
+
+/**
+ * enum adf_tl_counter_type - telemetry counter types
+ * @ADF_TL_COUNTER_UNSUPPORTED: unsupported counter
+ * @ADF_TL_SIMPLE_COUNT: simple counter
+ * @ADF_TL_COUNTER_NS: latency counter, value in ns
+ * @ADF_TL_COUNTER_NS_AVG: accumulated average latency counter, value in ns
+ * @ADF_TL_COUNTER_MBPS: bandwidth, value in MBps
+ */
+enum adf_tl_counter_type {
+	ADF_TL_COUNTER_UNSUPPORTED,
+	ADF_TL_SIMPLE_COUNT,
+	ADF_TL_COUNTER_NS,
+	ADF_TL_COUNTER_NS_AVG,
+	ADF_TL_COUNTER_MBPS,
+};
+
+/**
+ * struct adf_tl_dbg_counter - telemetry counter definition
+ * @name: name of the counter as printed in the report
+ * @adf_tl_counter_type: type of the counter
+ * @offset1: offset of 1st register
+ * @offset2: offset of 2nd optional register
+ */
+struct adf_tl_dbg_counter {
+	const char *name;
+	enum adf_tl_counter_type type;
+	size_t offset1;
+	size_t offset2;
+};
+
+#define ADF_TL_COUNTER(_name, _type, _offset)	\
+{	.name =		_name,			\
+	.type =		_type,			\
+	.offset1 =	_offset			\
+}
+
+#define ADF_TL_COUNTER_LATENCY(_name, _type, _offset1, _offset2)	\
+{	.name =		_name,						\
+	.type =		_type,						\
+	.offset1 =	_offset1,					\
+	.offset2 =	_offset2					\
+}
+
+/* Telemetry counter aggregated values. */
+struct adf_tl_dbg_aggr_values {
+	u64 curr;
+	u64 min;
+	u64 max;
+	u64 avg;
+};
+
+/**
+ * adf_tl_dbgfs_add() - Add telemetry's debug fs entries.
+ * @accel_dev: Pointer to acceleration device.
+ *
+ * Creates telemetry's debug fs folder and attributes in QAT debug fs root.
+ */
+void adf_tl_dbgfs_add(struct adf_accel_dev *accel_dev);
+
+/**
+ * adf_tl_dbgfs_rm() - Remove telemetry's debug fs entries.
+ * @accel_dev: Pointer to acceleration device.
+ *
+ * Removes telemetry's debug fs folder and attributes from QAT debug fs root.
+ */
+void adf_tl_dbgfs_rm(struct adf_accel_dev *accel_dev);
+
+#endif /* ADF_TL_DEBUGFS_H */
diff --git a/drivers/crypto/intel/qat/qat_common/icp_qat_fw_init_admin.h b/drivers/crypto/intel/qat/qat_common/icp_qat_fw_init_admin.h
index cd418b51d9f3..63cf18e2a4e5 100644
--- a/drivers/crypto/intel/qat/qat_common/icp_qat_fw_init_admin.h
+++ b/drivers/crypto/intel/qat/qat_common/icp_qat_fw_init_admin.h
@@ -29,6 +29,8 @@ enum icp_qat_fw_init_admin_cmd_id {
 	ICP_QAT_FW_RL_ADD = 134,
 	ICP_QAT_FW_RL_UPDATE = 135,
 	ICP_QAT_FW_RL_REMOVE = 136,
+	ICP_QAT_FW_TL_START = 137,
+	ICP_QAT_FW_TL_STOP = 138,
 };
 
 enum icp_qat_fw_init_admin_resp_status {
@@ -36,6 +38,13 @@ enum icp_qat_fw_init_admin_resp_status {
 	ICP_QAT_FW_INIT_RESP_STATUS_FAIL
 };
 
+struct icp_qat_fw_init_admin_tl_rp_indexes {
+	__u8 rp_num_index_0;
+	__u8 rp_num_index_1;
+	__u8 rp_num_index_2;
+	__u8 rp_num_index_3;
+};
+
 struct icp_qat_fw_init_admin_slice_cnt {
 	__u8 cpr_cnt;
 	__u8 xlt_cnt;
@@ -87,6 +96,7 @@ struct icp_qat_fw_init_admin_req {
 			__u8 rp_count;
 		};
 		__u32 idle_filter;
+		struct icp_qat_fw_init_admin_tl_rp_indexes rp_indexes;
 	};
 
 	__u32 resrvd4;
diff --git a/drivers/crypto/intel/qat/qat_common/icp_qat_hw.h b/drivers/crypto/intel/qat/qat_common/icp_qat_hw.h
index eb2ef225bcee..b8f1c4ffb8b5 100644
--- a/drivers/crypto/intel/qat/qat_common/icp_qat_hw.h
+++ b/drivers/crypto/intel/qat/qat_common/icp_qat_hw.h
@@ -18,7 +18,12 @@ enum icp_qat_hw_ae_id {
 	ICP_QAT_HW_AE_9 = 9,
 	ICP_QAT_HW_AE_10 = 10,
 	ICP_QAT_HW_AE_11 = 11,
-	ICP_QAT_HW_AE_DELIMITER = 12
+	ICP_QAT_HW_AE_12 = 12,
+	ICP_QAT_HW_AE_13 = 13,
+	ICP_QAT_HW_AE_14 = 14,
+	ICP_QAT_HW_AE_15 = 15,
+	ICP_QAT_HW_AE_16 = 16,
+	ICP_QAT_HW_AE_DELIMITER = 17
 };
 
 enum icp_qat_hw_qat_id {
@@ -95,7 +100,7 @@ enum icp_qat_capabilities_mask {
 	/* Bits 10-11 are currently reserved */
 	ICP_ACCEL_CAPABILITIES_HKDF = BIT(12),
 	ICP_ACCEL_CAPABILITIES_ECEDMONT = BIT(13),
-	/* Bit 14 is currently reserved */
+	ICP_ACCEL_CAPABILITIES_EXT_ALGCHAIN = BIT(14),
 	ICP_ACCEL_CAPABILITIES_SHA3_EXT = BIT(15),
 	ICP_ACCEL_CAPABILITIES_AESGCM_SPC = BIT(16),
 	ICP_ACCEL_CAPABILITIES_CHACHA_POLY = BIT(17),
@@ -107,7 +112,10 @@ enum icp_qat_capabilities_mask {
 	ICP_ACCEL_CAPABILITIES_CNV_INTEGRITY64 = BIT(23),
 	ICP_ACCEL_CAPABILITIES_LZ4_COMPRESSION = BIT(24),
 	ICP_ACCEL_CAPABILITIES_LZ4S_COMPRESSION = BIT(25),
-	ICP_ACCEL_CAPABILITIES_AES_V2 = BIT(26)
+	ICP_ACCEL_CAPABILITIES_AES_V2 = BIT(26),
+	/* Bits 27-28 are currently reserved */
+	ICP_ACCEL_CAPABILITIES_ZUC_256 = BIT(29),
+	ICP_ACCEL_CAPABILITIES_WIRELESS_CRYPTO_EXT = BIT(30),
 };
 
 #define QAT_AUTH_MODE_BITPOS 4
diff --git a/drivers/crypto/intel/qat/qat_common/icp_qat_uclo.h b/drivers/crypto/intel/qat/qat_common/icp_qat_uclo.h
index 69482abdb8b9..e28241bdd0f4 100644
--- a/drivers/crypto/intel/qat/qat_common/icp_qat_uclo.h
+++ b/drivers/crypto/intel/qat/qat_common/icp_qat_uclo.h
@@ -7,7 +7,7 @@
 #define ICP_QAT_AC_C62X_DEV_TYPE   0x01000000
 #define ICP_QAT_AC_C3XXX_DEV_TYPE  0x02000000
 #define ICP_QAT_AC_4XXX_A_DEV_TYPE 0x08000000
-#define ICP_QAT_UCLO_MAX_AE       12
+#define ICP_QAT_UCLO_MAX_AE       17
 #define ICP_QAT_UCLO_MAX_CTX      8
 #define ICP_QAT_UCLO_MAX_UIMAGE   (ICP_QAT_UCLO_MAX_AE * ICP_QAT_UCLO_MAX_CTX)
 #define ICP_QAT_UCLO_MAX_USTORE   0x4000
diff --git a/drivers/crypto/intel/qat/qat_common/qat_hal.c b/drivers/crypto/intel/qat/qat_common/qat_hal.c
index cbb946a80076..317cafa9d11f 100644
--- a/drivers/crypto/intel/qat/qat_common/qat_hal.c
+++ b/drivers/crypto/intel/qat/qat_common/qat_hal.c
@@ -697,12 +697,16 @@ static int qat_hal_chip_init(struct icp_qat_fw_loader_handle *handle,
 	case ADF_4XXX_PCI_DEVICE_ID:
 	case ADF_401XX_PCI_DEVICE_ID:
 	case ADF_402XX_PCI_DEVICE_ID:
+	case ADF_420XX_PCI_DEVICE_ID:
 		handle->chip_info->mmp_sram_size = 0;
 		handle->chip_info->nn = false;
 		handle->chip_info->lm2lm3 = true;
 		handle->chip_info->lm_size = ICP_QAT_UCLO_MAX_LMEM_REG_2X;
 		handle->chip_info->icp_rst_csr = ICP_RESET_CPP0;
-		handle->chip_info->icp_rst_mask = 0x100015;
+		if (handle->pci_dev->device == ADF_420XX_PCI_DEVICE_ID)
+			handle->chip_info->icp_rst_mask = 0x100155;
+		else
+			handle->chip_info->icp_rst_mask = 0x100015;
 		handle->chip_info->glb_clk_enable_csr = ICP_GLOBAL_CLK_ENABLE_CPP0;
 		handle->chip_info->misc_ctl_csr = MISC_CONTROL_C4XXX;
 		handle->chip_info->wakeup_event_val = 0x80000000;
diff --git a/drivers/crypto/intel/qat/qat_common/qat_uclo.c b/drivers/crypto/intel/qat/qat_common/qat_uclo.c
index e27ea7e28c51..ad2c64af7427 100644
--- a/drivers/crypto/intel/qat/qat_common/qat_uclo.c
+++ b/drivers/crypto/intel/qat/qat_common/qat_uclo.c
@@ -733,6 +733,7 @@ qat_uclo_get_dev_type(struct icp_qat_fw_loader_handle *handle)
 	case ADF_4XXX_PCI_DEVICE_ID:
 	case ADF_401XX_PCI_DEVICE_ID:
 	case ADF_402XX_PCI_DEVICE_ID:
+	case ADF_420XX_PCI_DEVICE_ID:
 		return ICP_QAT_AC_4XXX_A_DEV_TYPE;
 	default:
 		pr_err("QAT: unsupported device 0x%x\n",
diff --git a/drivers/crypto/marvell/cesa/cesa.c b/drivers/crypto/marvell/cesa/cesa.c
index 5744df30c838..5fd31ba715c2 100644
--- a/drivers/crypto/marvell/cesa/cesa.c
+++ b/drivers/crypto/marvell/cesa/cesa.c
@@ -488,7 +488,7 @@ static int mv_cesa_probe(struct platform_device *pdev)
 
 	for (i = 0; i < caps->nengines; i++) {
 		struct mv_cesa_engine *engine = &cesa->engines[i];
-		char res_name[7];
+		char res_name[16];
 
 		engine->id = i;
 		spin_lock_init(&engine->lock);
@@ -509,7 +509,7 @@ static int mv_cesa_probe(struct platform_device *pdev)
 		 * Not all platforms can gate the CESA clocks: do not complain
 		 * if the clock does not exist.
 		 */
-		snprintf(res_name, sizeof(res_name), "cesa%d", i);
+		snprintf(res_name, sizeof(res_name), "cesa%u", i);
 		engine->clk = devm_clk_get(dev, res_name);
 		if (IS_ERR(engine->clk)) {
 			engine->clk = devm_clk_get(dev, NULL);
@@ -517,7 +517,7 @@ static int mv_cesa_probe(struct platform_device *pdev)
 				engine->clk = NULL;
 		}
 
-		snprintf(res_name, sizeof(res_name), "cesaz%d", i);
+		snprintf(res_name, sizeof(res_name), "cesaz%u", i);
 		engine->zclk = devm_clk_get(dev, res_name);
 		if (IS_ERR(engine->zclk))
 			engine->zclk = NULL;
diff --git a/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c b/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c
index 1c2c870e887a..3c5d577d8f0d 100644
--- a/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c
+++ b/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c
@@ -473,12 +473,6 @@ static int otx_cpt_skcipher_ecb_aes_setkey(struct crypto_skcipher *tfm,
 	return cpt_aes_setkey(tfm, key, keylen, OTX_CPT_AES_ECB);
 }
 
-static int otx_cpt_skcipher_cfb_aes_setkey(struct crypto_skcipher *tfm,
-					   const u8 *key, u32 keylen)
-{
-	return cpt_aes_setkey(tfm, key, keylen, OTX_CPT_AES_CFB);
-}
-
 static int otx_cpt_skcipher_cbc_des3_setkey(struct crypto_skcipher *tfm,
 					    const u8 *key, u32 keylen)
 {
@@ -1352,23 +1346,6 @@ static struct skcipher_alg otx_cpt_skciphers[] = { {
 	.encrypt = otx_cpt_skcipher_encrypt,
 	.decrypt = otx_cpt_skcipher_decrypt,
 }, {
-	.base.cra_name = "cfb(aes)",
-	.base.cra_driver_name = "cpt_cfb_aes",
-	.base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY,
-	.base.cra_blocksize = AES_BLOCK_SIZE,
-	.base.cra_ctxsize = sizeof(struct otx_cpt_enc_ctx),
-	.base.cra_alignmask = 7,
-	.base.cra_priority = 4001,
-	.base.cra_module = THIS_MODULE,
-
-	.init = otx_cpt_enc_dec_init,
-	.ivsize = AES_BLOCK_SIZE,
-	.min_keysize = AES_MIN_KEY_SIZE,
-	.max_keysize = AES_MAX_KEY_SIZE,
-	.setkey = otx_cpt_skcipher_cfb_aes_setkey,
-	.encrypt = otx_cpt_skcipher_encrypt,
-	.decrypt = otx_cpt_skcipher_decrypt,
-}, {
 	.base.cra_name = "cbc(des3_ede)",
 	.base.cra_driver_name = "cpt_cbc_des3_ede",
 	.base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY,
diff --git a/drivers/crypto/marvell/octeontx2/cn10k_cpt.c b/drivers/crypto/marvell/octeontx2/cn10k_cpt.c
index 93d22b328991..79b4e74804f6 100644
--- a/drivers/crypto/marvell/octeontx2/cn10k_cpt.c
+++ b/drivers/crypto/marvell/octeontx2/cn10k_cpt.c
@@ -14,12 +14,14 @@ static struct cpt_hw_ops otx2_hw_ops = {
 	.send_cmd = otx2_cpt_send_cmd,
 	.cpt_get_compcode = otx2_cpt_get_compcode,
 	.cpt_get_uc_compcode = otx2_cpt_get_uc_compcode,
+	.cpt_sg_info_create = otx2_sg_info_create,
 };
 
 static struct cpt_hw_ops cn10k_hw_ops = {
 	.send_cmd = cn10k_cpt_send_cmd,
 	.cpt_get_compcode = cn10k_cpt_get_compcode,
 	.cpt_get_uc_compcode = cn10k_cpt_get_uc_compcode,
+	.cpt_sg_info_create = otx2_sg_info_create,
 };
 
 static void cn10k_cpt_send_cmd(union otx2_cpt_inst_s *cptinst, u32 insts_num,
@@ -78,12 +80,9 @@ int cn10k_cptvf_lmtst_init(struct otx2_cptvf_dev *cptvf)
 	struct pci_dev *pdev = cptvf->pdev;
 	resource_size_t offset, size;
 
-	if (!test_bit(CN10K_LMTST, &cptvf->cap_flag)) {
-		cptvf->lfs.ops = &otx2_hw_ops;
+	if (!test_bit(CN10K_LMTST, &cptvf->cap_flag))
 		return 0;
-	}
 
-	cptvf->lfs.ops = &cn10k_hw_ops;
 	offset = pci_resource_start(pdev, PCI_MBOX_BAR_NUM);
 	size = pci_resource_len(pdev, PCI_MBOX_BAR_NUM);
 	/* Map VF LMILINE region */
@@ -96,3 +95,82 @@ int cn10k_cptvf_lmtst_init(struct otx2_cptvf_dev *cptvf)
 	return 0;
 }
 EXPORT_SYMBOL_NS_GPL(cn10k_cptvf_lmtst_init, CRYPTO_DEV_OCTEONTX2_CPT);
+
+void cn10k_cpt_hw_ctx_clear(struct pci_dev *pdev,
+			    struct cn10k_cpt_errata_ctx *er_ctx)
+{
+	u64 cptr_dma;
+
+	if (!is_dev_cn10ka_ax(pdev))
+		return;
+
+	cptr_dma = er_ctx->cptr_dma & ~(BIT_ULL(60));
+	cn10k_cpt_ctx_flush(pdev, cptr_dma, true);
+	dma_unmap_single(&pdev->dev, cptr_dma, CN10K_CPT_HW_CTX_SIZE,
+			 DMA_BIDIRECTIONAL);
+	kfree(er_ctx->hw_ctx);
+}
+EXPORT_SYMBOL_NS_GPL(cn10k_cpt_hw_ctx_clear, CRYPTO_DEV_OCTEONTX2_CPT);
+
+void cn10k_cpt_hw_ctx_set(union cn10k_cpt_hw_ctx *hctx, u16 ctx_sz)
+{
+	hctx->w0.aop_valid = 1;
+	hctx->w0.ctx_hdr_sz = 0;
+	hctx->w0.ctx_sz = ctx_sz;
+	hctx->w0.ctx_push_sz = 1;
+}
+EXPORT_SYMBOL_NS_GPL(cn10k_cpt_hw_ctx_set, CRYPTO_DEV_OCTEONTX2_CPT);
+
+int cn10k_cpt_hw_ctx_init(struct pci_dev *pdev,
+			  struct cn10k_cpt_errata_ctx *er_ctx)
+{
+	union cn10k_cpt_hw_ctx *hctx;
+	u64 cptr_dma;
+
+	er_ctx->cptr_dma = 0;
+	er_ctx->hw_ctx = NULL;
+
+	if (!is_dev_cn10ka_ax(pdev))
+		return 0;
+
+	hctx = kmalloc(CN10K_CPT_HW_CTX_SIZE, GFP_KERNEL);
+	if (unlikely(!hctx))
+		return -ENOMEM;
+	cptr_dma = dma_map_single(&pdev->dev, hctx, CN10K_CPT_HW_CTX_SIZE,
+				  DMA_BIDIRECTIONAL);
+
+	cn10k_cpt_hw_ctx_set(hctx, 1);
+	er_ctx->hw_ctx = hctx;
+	er_ctx->cptr_dma = cptr_dma | BIT_ULL(60);
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cn10k_cpt_hw_ctx_init, CRYPTO_DEV_OCTEONTX2_CPT);
+
+void cn10k_cpt_ctx_flush(struct pci_dev *pdev, u64 cptr, bool inval)
+{
+	struct otx2_cptvf_dev *cptvf = pci_get_drvdata(pdev);
+	struct otx2_cptlfs_info *lfs = &cptvf->lfs;
+	u64 reg;
+
+	reg = (uintptr_t)cptr >> 7;
+	if (inval)
+		reg = reg | BIT_ULL(46);
+
+	otx2_cpt_write64(lfs->reg_base, lfs->blkaddr, lfs->lf[0].slot,
+			 OTX2_CPT_LF_CTX_FLUSH, reg);
+	/* Make sure that the FLUSH operation is complete */
+	wmb();
+	otx2_cpt_read64(lfs->reg_base, lfs->blkaddr, lfs->lf[0].slot,
+			OTX2_CPT_LF_CTX_ERR);
+}
+EXPORT_SYMBOL_NS_GPL(cn10k_cpt_ctx_flush, CRYPTO_DEV_OCTEONTX2_CPT);
+
+void cptvf_hw_ops_get(struct otx2_cptvf_dev *cptvf)
+{
+	if (test_bit(CN10K_LMTST, &cptvf->cap_flag))
+		cptvf->lfs.ops = &cn10k_hw_ops;
+	else
+		cptvf->lfs.ops = &otx2_hw_ops;
+}
+EXPORT_SYMBOL_NS_GPL(cptvf_hw_ops_get, CRYPTO_DEV_OCTEONTX2_CPT);
diff --git a/drivers/crypto/marvell/octeontx2/cn10k_cpt.h b/drivers/crypto/marvell/octeontx2/cn10k_cpt.h
index aaefc7e38e06..92be3ecf570f 100644
--- a/drivers/crypto/marvell/octeontx2/cn10k_cpt.h
+++ b/drivers/crypto/marvell/octeontx2/cn10k_cpt.h
@@ -8,6 +8,26 @@
 #include "otx2_cptpf.h"
 #include "otx2_cptvf.h"
 
+#define CN10K_CPT_HW_CTX_SIZE  256
+
+union cn10k_cpt_hw_ctx {
+	u64 u;
+	struct {
+		u64 reserved_0_47:48;
+		u64 ctx_push_sz:7;
+		u64 reserved_55:1;
+		u64 ctx_hdr_sz:2;
+		u64 aop_valid:1;
+		u64 reserved_59:1;
+		u64 ctx_sz:4;
+	} w0;
+};
+
+struct cn10k_cpt_errata_ctx {
+	union cn10k_cpt_hw_ctx *hw_ctx;
+	u64 cptr_dma;
+};
+
 static inline u8 cn10k_cpt_get_compcode(union otx2_cpt_res_s *result)
 {
 	return ((struct cn10k_cpt_res_s *)result)->compcode;
@@ -30,5 +50,12 @@ static inline u8 otx2_cpt_get_uc_compcode(union otx2_cpt_res_s *result)
 
 int cn10k_cptpf_lmtst_init(struct otx2_cptpf_dev *cptpf);
 int cn10k_cptvf_lmtst_init(struct otx2_cptvf_dev *cptvf);
+void cn10k_cpt_ctx_flush(struct pci_dev *pdev, u64 cptr, bool inval);
+int cn10k_cpt_hw_ctx_init(struct pci_dev *pdev,
+			  struct cn10k_cpt_errata_ctx *er_ctx);
+void cn10k_cpt_hw_ctx_clear(struct pci_dev *pdev,
+			    struct cn10k_cpt_errata_ctx *er_ctx);
+void cn10k_cpt_hw_ctx_set(union cn10k_cpt_hw_ctx *hctx, u16 ctx_sz);
+void cptvf_hw_ops_get(struct otx2_cptvf_dev *cptvf);
 
 #endif /* __CN10K_CPTLF_H */
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h b/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h
index 46b778bbbee4..c5b7c57574ef 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h
+++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h
@@ -56,7 +56,11 @@ struct otx2_cpt_rx_inline_lf_cfg {
 	u16 param2;
 	u16 opcode;
 	u32 credit;
+	u32 credit_th;
+	u16 bpid;
 	u32 reserved;
+	u8 ctx_ilen_valid : 1;
+	u8 ctx_ilen : 7;
 };
 
 /*
@@ -102,7 +106,10 @@ union otx2_cpt_eng_caps {
 		u64 kasumi:1;
 		u64 des:1;
 		u64 crc:1;
-		u64 reserved_14_63:50;
+		u64 mmul:1;
+		u64 reserved_15_33:19;
+		u64 pdcp_chain:1;
+		u64 reserved_35_63:29;
 	};
 };
 
@@ -145,6 +152,35 @@ static inline bool is_dev_otx2(struct pci_dev *pdev)
 	return false;
 }
 
+static inline bool is_dev_cn10ka(struct pci_dev *pdev)
+{
+	return pdev->subsystem_device == CPT_PCI_SUBSYS_DEVID_CN10K_A;
+}
+
+static inline bool is_dev_cn10ka_ax(struct pci_dev *pdev)
+{
+	if (pdev->subsystem_device == CPT_PCI_SUBSYS_DEVID_CN10K_A &&
+	    ((pdev->revision & 0xFF) == 4 || (pdev->revision & 0xFF) == 0x50 ||
+	     (pdev->revision & 0xff) == 0x51))
+		return true;
+
+	return false;
+}
+
+static inline bool is_dev_cn10kb(struct pci_dev *pdev)
+{
+	return pdev->subsystem_device == CPT_PCI_SUBSYS_DEVID_CN10K_B;
+}
+
+static inline bool is_dev_cn10ka_b0(struct pci_dev *pdev)
+{
+	if (pdev->subsystem_device == CPT_PCI_SUBSYS_DEVID_CN10K_A &&
+	    (pdev->revision & 0xFF) == 0x54)
+		return true;
+
+	return false;
+}
+
 static inline void otx2_cpt_set_hw_caps(struct pci_dev *pdev,
 					unsigned long *cap_flag)
 {
@@ -154,6 +190,21 @@ static inline void otx2_cpt_set_hw_caps(struct pci_dev *pdev,
 	}
 }
 
+static inline bool cpt_is_errata_38550_exists(struct pci_dev *pdev)
+{
+	if (is_dev_otx2(pdev) || is_dev_cn10ka_ax(pdev))
+		return true;
+
+	return false;
+}
+
+static inline bool cpt_feature_sgv2(struct pci_dev *pdev)
+{
+	if (!is_dev_otx2(pdev) && !is_dev_cn10ka_ax(pdev))
+		return true;
+
+	return false;
+}
 
 int otx2_cpt_send_ready_msg(struct otx2_mbox *mbox, struct pci_dev *pdev);
 int otx2_cpt_send_mbox_msg(struct otx2_mbox *mbox, struct pci_dev *pdev);
@@ -171,5 +222,6 @@ int otx2_cpt_attach_rscrs_msg(struct otx2_cptlfs_info *lfs);
 int otx2_cpt_detach_rsrcs_msg(struct otx2_cptlfs_info *lfs);
 int otx2_cpt_msix_offset_msg(struct otx2_cptlfs_info *lfs);
 int otx2_cpt_sync_mbox_msg(struct otx2_mbox *mbox);
+int otx2_cpt_lf_reset_msg(struct otx2_cptlfs_info *lfs, int slot);
 
 #endif /* __OTX2_CPT_COMMON_H */
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.c b/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.c
index a2aba0b0d68a..d2b8d26db968 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.c
+++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.c
@@ -24,10 +24,45 @@ static int otx2_cpt_dl_egrp_delete(struct devlink *dl, u32 id,
 static int otx2_cpt_dl_uc_info(struct devlink *dl, u32 id,
 			       struct devlink_param_gset_ctx *ctx)
 {
+	ctx->val.vstr[0] = '\0';
+
+	return 0;
+}
+
+static int otx2_cpt_dl_t106_mode_get(struct devlink *dl, u32 id,
+				     struct devlink_param_gset_ctx *ctx)
+{
 	struct otx2_cpt_devlink *cpt_dl = devlink_priv(dl);
 	struct otx2_cptpf_dev *cptpf = cpt_dl->cptpf;
+	struct pci_dev *pdev = cptpf->pdev;
+	u64 reg_val = 0;
+
+	otx2_cpt_read_af_reg(&cptpf->afpf_mbox, pdev, CPT_AF_CTL, &reg_val,
+			     BLKADDR_CPT0);
+	ctx->val.vu8 = (reg_val >> 18) & 0x1;
+
+	return 0;
+}
 
-	otx2_cpt_print_uc_dbg_info(cptpf);
+static int otx2_cpt_dl_t106_mode_set(struct devlink *dl, u32 id,
+				     struct devlink_param_gset_ctx *ctx)
+{
+	struct otx2_cpt_devlink *cpt_dl = devlink_priv(dl);
+	struct otx2_cptpf_dev *cptpf = cpt_dl->cptpf;
+	struct pci_dev *pdev = cptpf->pdev;
+	u64 reg_val = 0;
+
+	if (cptpf->enabled_vfs != 0 || cptpf->eng_grps.is_grps_created)
+		return -EPERM;
+
+	if (cpt_feature_sgv2(pdev)) {
+		otx2_cpt_read_af_reg(&cptpf->afpf_mbox, pdev, CPT_AF_CTL,
+				     &reg_val, BLKADDR_CPT0);
+		reg_val &= ~(0x1ULL << 18);
+		reg_val |= ((u64)ctx->val.vu8 & 0x1) << 18;
+		return otx2_cpt_write_af_reg(&cptpf->afpf_mbox, pdev,
+					     CPT_AF_CTL, reg_val, BLKADDR_CPT0);
+	}
 
 	return 0;
 }
@@ -36,6 +71,7 @@ enum otx2_cpt_dl_param_id {
 	OTX2_CPT_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
 	OTX2_CPT_DEVLINK_PARAM_ID_EGRP_CREATE,
 	OTX2_CPT_DEVLINK_PARAM_ID_EGRP_DELETE,
+	OTX2_CPT_DEVLINK_PARAM_ID_T106_MODE,
 };
 
 static const struct devlink_param otx2_cpt_dl_params[] = {
@@ -49,6 +85,11 @@ static const struct devlink_param otx2_cpt_dl_params[] = {
 			     BIT(DEVLINK_PARAM_CMODE_RUNTIME),
 			     otx2_cpt_dl_uc_info, otx2_cpt_dl_egrp_delete,
 			     NULL),
+	DEVLINK_PARAM_DRIVER(OTX2_CPT_DEVLINK_PARAM_ID_T106_MODE,
+			     "t106_mode", DEVLINK_PARAM_TYPE_U8,
+			     BIT(DEVLINK_PARAM_CMODE_RUNTIME),
+			     otx2_cpt_dl_t106_mode_get, otx2_cpt_dl_t106_mode_set,
+			     NULL),
 };
 
 static int otx2_cpt_dl_info_firmware_version_put(struct devlink_info_req *req,
@@ -120,7 +161,6 @@ int otx2_cpt_register_dl(struct otx2_cptpf_dev *cptpf)
 		devlink_free(dl);
 		return ret;
 	}
-
 	devlink_register(dl);
 
 	return 0;
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_hw_types.h b/drivers/crypto/marvell/octeontx2/otx2_cpt_hw_types.h
index 6f947978e4e8..7e746a4def86 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cpt_hw_types.h
+++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_hw_types.h
@@ -13,6 +13,9 @@
 #define CN10K_CPT_PCI_PF_DEVICE_ID 0xA0F2
 #define CN10K_CPT_PCI_VF_DEVICE_ID 0xA0F3
 
+#define CPT_PCI_SUBSYS_DEVID_CN10K_A 0xB900
+#define CPT_PCI_SUBSYS_DEVID_CN10K_B 0xBD00
+
 /* Mailbox interrupts offset */
 #define OTX2_CPT_PF_MBOX_INT	6
 #define OTX2_CPT_PF_INT_VEC_E_MBOXX(x, a) ((x) + (a))
@@ -99,6 +102,9 @@
 #define OTX2_CPT_LF_Q_INST_PTR          (0x110)
 #define OTX2_CPT_LF_Q_GRP_PTR           (0x120)
 #define OTX2_CPT_LF_NQX(a)              (0x400 | (a) << 3)
+#define OTX2_CPT_LF_CTX_CTL             (0x500)
+#define OTX2_CPT_LF_CTX_FLUSH           (0x510)
+#define OTX2_CPT_LF_CTX_ERR             (0x520)
 #define OTX2_CPT_RVU_FUNC_BLKADDR_SHIFT 20
 /* LMT LF registers */
 #define OTX2_CPT_LMT_LFBASE             BIT_ULL(OTX2_CPT_RVU_FUNC_BLKADDR_SHIFT)
@@ -467,7 +473,8 @@ union otx2_cptx_af_lf_ctrl {
 		u64 cont_err:1;
 		u64 reserved_11_15:5;
 		u64 nixtx_en:1;
-		u64 reserved_17_47:31;
+		u64 ctx_ilen:3;
+		u64 reserved_17_47:28;
 		u64 grp:8;
 		u64 reserved_56_63:8;
 	} s;
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c b/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c
index 273ee5352a50..5be0103c1fb8 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c
+++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c
@@ -229,3 +229,29 @@ int otx2_cpt_sync_mbox_msg(struct otx2_mbox *mbox)
 	return otx2_mbox_check_rsp_msgs(mbox, 0);
 }
 EXPORT_SYMBOL_NS_GPL(otx2_cpt_sync_mbox_msg, CRYPTO_DEV_OCTEONTX2_CPT);
+
+int otx2_cpt_lf_reset_msg(struct otx2_cptlfs_info *lfs, int slot)
+{
+	struct otx2_mbox *mbox = lfs->mbox;
+	struct pci_dev *pdev = lfs->pdev;
+	struct cpt_lf_rst_req *req;
+	int ret;
+
+	req = (struct cpt_lf_rst_req *)otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req),
+							       sizeof(struct msg_rsp));
+	if (!req) {
+		dev_err(&pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+
+	req->hdr.id = MBOX_MSG_CPT_LF_RESET;
+	req->hdr.sig = OTX2_MBOX_REQ_SIG;
+	req->hdr.pcifunc = 0;
+	req->slot = slot;
+	ret = otx2_cpt_send_mbox_msg(mbox, pdev);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cpt_lf_reset_msg, CRYPTO_DEV_OCTEONTX2_CPT);
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_reqmgr.h b/drivers/crypto/marvell/octeontx2/otx2_cpt_reqmgr.h
index dbb1ee746f4c..e27e849b01df 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cpt_reqmgr.h
+++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_reqmgr.h
@@ -27,6 +27,13 @@
 
 #define OTX2_CPT_MAX_REQ_SIZE 65535
 
+#define SG_COMPS_MAX    4
+#define SGV2_COMPS_MAX  3
+
+#define SG_COMP_3    3
+#define SG_COMP_2    2
+#define SG_COMP_1    1
+
 union otx2_cpt_opcode {
 	u16 flags;
 	struct {
@@ -40,6 +47,8 @@ struct otx2_cptvf_request {
 	u32 param2;
 	u16 dlen;
 	union otx2_cpt_opcode opcode;
+	dma_addr_t cptr_dma;
+	void *cptr;
 };
 
 /*
@@ -143,6 +152,8 @@ struct otx2_cpt_inst_info {
 	unsigned long time_in;
 	u32 dlen;
 	u32 dma_len;
+	u64 gthr_sz;
+	u64 sctr_sz;
 	u8 extra_time;
 };
 
@@ -157,6 +168,16 @@ struct otx2_cpt_sglist_component {
 	__be64 ptr3;
 };
 
+struct cn10kb_cpt_sglist_component {
+	u16 len0;
+	u16 len1;
+	u16 len2;
+	u16 valid_segs;
+	u64 ptr0;
+	u64 ptr1;
+	u64 ptr2;
+};
+
 static inline void otx2_cpt_info_destroy(struct pci_dev *pdev,
 					 struct otx2_cpt_inst_info *info)
 {
@@ -188,6 +209,283 @@ static inline void otx2_cpt_info_destroy(struct pci_dev *pdev,
 	kfree(info);
 }
 
+static inline int setup_sgio_components(struct pci_dev *pdev,
+					struct otx2_cpt_buf_ptr *list,
+					int buf_count, u8 *buffer)
+{
+	struct otx2_cpt_sglist_component *sg_ptr;
+	int components;
+	int i, j;
+
+	if (unlikely(!list)) {
+		dev_err(&pdev->dev, "Input list pointer is NULL\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < buf_count; i++) {
+		if (unlikely(!list[i].vptr))
+			continue;
+		list[i].dma_addr = dma_map_single(&pdev->dev, list[i].vptr,
+						  list[i].size,
+						  DMA_BIDIRECTIONAL);
+		if (unlikely(dma_mapping_error(&pdev->dev, list[i].dma_addr))) {
+			dev_err(&pdev->dev, "Dma mapping failed\n");
+			goto sg_cleanup;
+		}
+	}
+	components = buf_count / SG_COMPS_MAX;
+	sg_ptr = (struct otx2_cpt_sglist_component *)buffer;
+	for (i = 0; i < components; i++) {
+		sg_ptr->len0 = cpu_to_be16(list[i * SG_COMPS_MAX + 0].size);
+		sg_ptr->len1 = cpu_to_be16(list[i * SG_COMPS_MAX + 1].size);
+		sg_ptr->len2 = cpu_to_be16(list[i * SG_COMPS_MAX + 2].size);
+		sg_ptr->len3 = cpu_to_be16(list[i * SG_COMPS_MAX + 3].size);
+		sg_ptr->ptr0 = cpu_to_be64(list[i * SG_COMPS_MAX + 0].dma_addr);
+		sg_ptr->ptr1 = cpu_to_be64(list[i * SG_COMPS_MAX + 1].dma_addr);
+		sg_ptr->ptr2 = cpu_to_be64(list[i * SG_COMPS_MAX + 2].dma_addr);
+		sg_ptr->ptr3 = cpu_to_be64(list[i * SG_COMPS_MAX + 3].dma_addr);
+		sg_ptr++;
+	}
+	components = buf_count % SG_COMPS_MAX;
+
+	switch (components) {
+	case SG_COMP_3:
+		sg_ptr->len2 = cpu_to_be16(list[i * SG_COMPS_MAX + 2].size);
+		sg_ptr->ptr2 = cpu_to_be64(list[i * SG_COMPS_MAX + 2].dma_addr);
+		fallthrough;
+	case SG_COMP_2:
+		sg_ptr->len1 = cpu_to_be16(list[i * SG_COMPS_MAX + 1].size);
+		sg_ptr->ptr1 = cpu_to_be64(list[i * SG_COMPS_MAX + 1].dma_addr);
+		fallthrough;
+	case SG_COMP_1:
+		sg_ptr->len0 = cpu_to_be16(list[i * SG_COMPS_MAX + 0].size);
+		sg_ptr->ptr0 = cpu_to_be64(list[i * SG_COMPS_MAX + 0].dma_addr);
+		break;
+	default:
+		break;
+	}
+	return 0;
+
+sg_cleanup:
+	for (j = 0; j < i; j++) {
+		if (list[j].dma_addr) {
+			dma_unmap_single(&pdev->dev, list[j].dma_addr,
+					 list[j].size, DMA_BIDIRECTIONAL);
+		}
+
+		list[j].dma_addr = 0;
+	}
+	return -EIO;
+}
+
+static inline int sgv2io_components_setup(struct pci_dev *pdev,
+					  struct otx2_cpt_buf_ptr *list,
+					  int buf_count, u8 *buffer)
+{
+	struct cn10kb_cpt_sglist_component *sg_ptr;
+	int components;
+	int i, j;
+
+	if (unlikely(!list)) {
+		dev_err(&pdev->dev, "Input list pointer is NULL\n");
+		return -EFAULT;
+	}
+
+	for (i = 0; i < buf_count; i++) {
+		if (unlikely(!list[i].vptr))
+			continue;
+		list[i].dma_addr = dma_map_single(&pdev->dev, list[i].vptr,
+						  list[i].size,
+						  DMA_BIDIRECTIONAL);
+		if (unlikely(dma_mapping_error(&pdev->dev, list[i].dma_addr))) {
+			dev_err(&pdev->dev, "Dma mapping failed\n");
+			goto sg_cleanup;
+		}
+	}
+	components = buf_count / SGV2_COMPS_MAX;
+	sg_ptr = (struct cn10kb_cpt_sglist_component *)buffer;
+	for (i = 0; i < components; i++) {
+		sg_ptr->len0 = list[i * SGV2_COMPS_MAX + 0].size;
+		sg_ptr->len1 = list[i * SGV2_COMPS_MAX + 1].size;
+		sg_ptr->len2 = list[i * SGV2_COMPS_MAX + 2].size;
+		sg_ptr->ptr0 = list[i * SGV2_COMPS_MAX + 0].dma_addr;
+		sg_ptr->ptr1 = list[i * SGV2_COMPS_MAX + 1].dma_addr;
+		sg_ptr->ptr2 = list[i * SGV2_COMPS_MAX + 2].dma_addr;
+		sg_ptr->valid_segs = SGV2_COMPS_MAX;
+		sg_ptr++;
+	}
+	components = buf_count % SGV2_COMPS_MAX;
+
+	sg_ptr->valid_segs = components;
+	switch (components) {
+	case SG_COMP_2:
+		sg_ptr->len1 = list[i * SGV2_COMPS_MAX + 1].size;
+		sg_ptr->ptr1 = list[i * SGV2_COMPS_MAX + 1].dma_addr;
+		fallthrough;
+	case SG_COMP_1:
+		sg_ptr->len0 = list[i * SGV2_COMPS_MAX + 0].size;
+		sg_ptr->ptr0 = list[i * SGV2_COMPS_MAX + 0].dma_addr;
+		break;
+	default:
+		break;
+	}
+	return 0;
+
+sg_cleanup:
+	for (j = 0; j < i; j++) {
+		if (list[j].dma_addr) {
+			dma_unmap_single(&pdev->dev, list[j].dma_addr,
+					 list[j].size, DMA_BIDIRECTIONAL);
+		}
+
+		list[j].dma_addr = 0;
+	}
+	return -EIO;
+}
+
+static inline struct otx2_cpt_inst_info *
+cn10k_sgv2_info_create(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
+		       gfp_t gfp)
+{
+	u32 dlen = 0, g_len, sg_len, info_len;
+	int align = OTX2_CPT_DMA_MINALIGN;
+	struct otx2_cpt_inst_info *info;
+	u16 g_sz_bytes, s_sz_bytes;
+	u32 total_mem_len;
+	int i;
+
+	g_sz_bytes = ((req->in_cnt + 2) / 3) *
+		      sizeof(struct cn10kb_cpt_sglist_component);
+	s_sz_bytes = ((req->out_cnt + 2) / 3) *
+		      sizeof(struct cn10kb_cpt_sglist_component);
+
+	g_len = ALIGN(g_sz_bytes, align);
+	sg_len = ALIGN(g_len + s_sz_bytes, align);
+	info_len = ALIGN(sizeof(*info), align);
+	total_mem_len = sg_len + info_len + sizeof(union otx2_cpt_res_s);
+
+	info = kzalloc(total_mem_len, gfp);
+	if (unlikely(!info))
+		return NULL;
+
+	for (i = 0; i < req->in_cnt; i++)
+		dlen += req->in[i].size;
+
+	info->dlen = dlen;
+	info->in_buffer = (u8 *)info + info_len;
+	info->gthr_sz = req->in_cnt;
+	info->sctr_sz = req->out_cnt;
+
+	/* Setup gather (input) components */
+	if (sgv2io_components_setup(pdev, req->in, req->in_cnt,
+				    info->in_buffer)) {
+		dev_err(&pdev->dev, "Failed to setup gather list\n");
+		goto destroy_info;
+	}
+
+	if (sgv2io_components_setup(pdev, req->out, req->out_cnt,
+				    &info->in_buffer[g_len])) {
+		dev_err(&pdev->dev, "Failed to setup scatter list\n");
+		goto destroy_info;
+	}
+
+	info->dma_len = total_mem_len - info_len;
+	info->dptr_baddr = dma_map_single(&pdev->dev, info->in_buffer,
+					  info->dma_len, DMA_BIDIRECTIONAL);
+	if (unlikely(dma_mapping_error(&pdev->dev, info->dptr_baddr))) {
+		dev_err(&pdev->dev, "DMA Mapping failed for cpt req\n");
+		goto destroy_info;
+	}
+	info->rptr_baddr = info->dptr_baddr + g_len;
+	/*
+	 * Get buffer for union otx2_cpt_res_s response
+	 * structure and its physical address
+	 */
+	info->completion_addr = info->in_buffer + sg_len;
+	info->comp_baddr = info->dptr_baddr + sg_len;
+
+	return info;
+
+destroy_info:
+	otx2_cpt_info_destroy(pdev, info);
+	return NULL;
+}
+
+/* SG list header size in bytes */
+#define SG_LIST_HDR_SIZE	8
+static inline struct otx2_cpt_inst_info *
+otx2_sg_info_create(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
+		    gfp_t gfp)
+{
+	int align = OTX2_CPT_DMA_MINALIGN;
+	struct otx2_cpt_inst_info *info;
+	u32 dlen, align_dlen, info_len;
+	u16 g_sz_bytes, s_sz_bytes;
+	u32 total_mem_len;
+
+	if (unlikely(req->in_cnt > OTX2_CPT_MAX_SG_IN_CNT ||
+		     req->out_cnt > OTX2_CPT_MAX_SG_OUT_CNT)) {
+		dev_err(&pdev->dev, "Error too many sg components\n");
+		return NULL;
+	}
+
+	g_sz_bytes = ((req->in_cnt + 3) / 4) *
+		      sizeof(struct otx2_cpt_sglist_component);
+	s_sz_bytes = ((req->out_cnt + 3) / 4) *
+		      sizeof(struct otx2_cpt_sglist_component);
+
+	dlen = g_sz_bytes + s_sz_bytes + SG_LIST_HDR_SIZE;
+	align_dlen = ALIGN(dlen, align);
+	info_len = ALIGN(sizeof(*info), align);
+	total_mem_len = align_dlen + info_len + sizeof(union otx2_cpt_res_s);
+
+	info = kzalloc(total_mem_len, gfp);
+	if (unlikely(!info))
+		return NULL;
+
+	info->dlen = dlen;
+	info->in_buffer = (u8 *)info + info_len;
+
+	((u16 *)info->in_buffer)[0] = req->out_cnt;
+	((u16 *)info->in_buffer)[1] = req->in_cnt;
+	((u16 *)info->in_buffer)[2] = 0;
+	((u16 *)info->in_buffer)[3] = 0;
+	cpu_to_be64s((u64 *)info->in_buffer);
+
+	/* Setup gather (input) components */
+	if (setup_sgio_components(pdev, req->in, req->in_cnt,
+				  &info->in_buffer[8])) {
+		dev_err(&pdev->dev, "Failed to setup gather list\n");
+		goto destroy_info;
+	}
+
+	if (setup_sgio_components(pdev, req->out, req->out_cnt,
+				  &info->in_buffer[8 + g_sz_bytes])) {
+		dev_err(&pdev->dev, "Failed to setup scatter list\n");
+		goto destroy_info;
+	}
+
+	info->dma_len = total_mem_len - info_len;
+	info->dptr_baddr = dma_map_single(&pdev->dev, info->in_buffer,
+					  info->dma_len, DMA_BIDIRECTIONAL);
+	if (unlikely(dma_mapping_error(&pdev->dev, info->dptr_baddr))) {
+		dev_err(&pdev->dev, "DMA Mapping failed for cpt req\n");
+		goto destroy_info;
+	}
+	/*
+	 * Get buffer for union otx2_cpt_res_s response
+	 * structure and its physical address
+	 */
+	info->completion_addr = info->in_buffer + align_dlen;
+	info->comp_baddr = info->dptr_baddr + align_dlen;
+
+	return info;
+
+destroy_info:
+	otx2_cpt_info_destroy(pdev, info);
+	return NULL;
+}
+
 struct otx2_cptlf_wqe;
 int otx2_cpt_do_request(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
 			int cpu_num);
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptlf.c b/drivers/crypto/marvell/octeontx2/otx2_cptlf.c
index 6edd27ff8c4e..b52728e3c0d1 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptlf.c
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptlf.c
@@ -106,6 +106,32 @@ static int cptlf_set_grp_and_pri(struct otx2_cptlfs_info *lfs,
 	return ret;
 }
 
+static int cptlf_set_ctx_ilen(struct otx2_cptlfs_info *lfs, int ctx_ilen)
+{
+	union otx2_cptx_af_lf_ctrl lf_ctrl;
+	struct otx2_cptlf_info *lf;
+	int slot, ret = 0;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++) {
+		lf = &lfs->lf[slot];
+
+		ret = otx2_cpt_read_af_reg(lfs->mbox, lfs->pdev,
+					   CPT_AF_LFX_CTL(lf->slot),
+					   &lf_ctrl.u, lfs->blkaddr);
+		if (ret)
+			return ret;
+
+		lf_ctrl.s.ctx_ilen = ctx_ilen;
+
+		ret = otx2_cpt_write_af_reg(lfs->mbox, lfs->pdev,
+					    CPT_AF_LFX_CTL(lf->slot),
+					    lf_ctrl.u, lfs->blkaddr);
+		if (ret)
+			return ret;
+	}
+	return ret;
+}
+
 static void cptlf_hw_init(struct otx2_cptlfs_info *lfs)
 {
 	/* Disable instruction queues */
@@ -151,26 +177,14 @@ static void cptlf_set_misc_intrs(struct otx2_cptlfs_info *lfs, u8 enable)
 				 irq_misc.u);
 }
 
-static void cptlf_enable_intrs(struct otx2_cptlfs_info *lfs)
-{
-	int slot;
-
-	/* Enable done interrupts */
-	for (slot = 0; slot < lfs->lfs_num; slot++)
-		otx2_cpt_write64(lfs->reg_base, lfs->blkaddr, slot,
-				 OTX2_CPT_LF_DONE_INT_ENA_W1S, 0x1);
-	/* Enable Misc interrupts */
-	cptlf_set_misc_intrs(lfs, true);
-}
-
-static void cptlf_disable_intrs(struct otx2_cptlfs_info *lfs)
+static void cptlf_set_done_intrs(struct otx2_cptlfs_info *lfs, u8 enable)
 {
+	u64 reg = enable ? OTX2_CPT_LF_DONE_INT_ENA_W1S :
+			   OTX2_CPT_LF_DONE_INT_ENA_W1C;
 	int slot;
 
 	for (slot = 0; slot < lfs->lfs_num; slot++)
-		otx2_cpt_write64(lfs->reg_base, lfs->blkaddr, slot,
-				 OTX2_CPT_LF_DONE_INT_ENA_W1C, 0x1);
-	cptlf_set_misc_intrs(lfs, false);
+		otx2_cpt_write64(lfs->reg_base, lfs->blkaddr, slot, reg, 0x1);
 }
 
 static inline int cptlf_read_done_cnt(struct otx2_cptlf_info *lf)
@@ -257,24 +271,44 @@ static irqreturn_t cptlf_done_intr_handler(int irq, void *arg)
 	return IRQ_HANDLED;
 }
 
-void otx2_cptlf_unregister_interrupts(struct otx2_cptlfs_info *lfs)
+void otx2_cptlf_unregister_misc_interrupts(struct otx2_cptlfs_info *lfs)
 {
-	int i, offs, vector;
+	int i, irq_offs, vector;
 
+	irq_offs = OTX2_CPT_LF_INT_VEC_E_MISC;
 	for (i = 0; i < lfs->lfs_num; i++) {
-		for (offs = 0; offs < OTX2_CPT_LF_MSIX_VECTORS; offs++) {
-			if (!lfs->lf[i].is_irq_reg[offs])
-				continue;
+		if (!lfs->lf[i].is_irq_reg[irq_offs])
+			continue;
 
-			vector = pci_irq_vector(lfs->pdev,
-						lfs->lf[i].msix_offset + offs);
-			free_irq(vector, &lfs->lf[i]);
-			lfs->lf[i].is_irq_reg[offs] = false;
-		}
+		vector = pci_irq_vector(lfs->pdev,
+					lfs->lf[i].msix_offset + irq_offs);
+		free_irq(vector, &lfs->lf[i]);
+		lfs->lf[i].is_irq_reg[irq_offs] = false;
+	}
+
+	cptlf_set_misc_intrs(lfs, false);
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cptlf_unregister_misc_interrupts,
+		     CRYPTO_DEV_OCTEONTX2_CPT);
+
+void otx2_cptlf_unregister_done_interrupts(struct otx2_cptlfs_info *lfs)
+{
+	int i, irq_offs, vector;
+
+	irq_offs = OTX2_CPT_LF_INT_VEC_E_DONE;
+	for (i = 0; i < lfs->lfs_num; i++) {
+		if (!lfs->lf[i].is_irq_reg[irq_offs])
+			continue;
+
+		vector = pci_irq_vector(lfs->pdev,
+					lfs->lf[i].msix_offset + irq_offs);
+		free_irq(vector, &lfs->lf[i]);
+		lfs->lf[i].is_irq_reg[irq_offs] = false;
 	}
-	cptlf_disable_intrs(lfs);
+
+	cptlf_set_done_intrs(lfs, false);
 }
-EXPORT_SYMBOL_NS_GPL(otx2_cptlf_unregister_interrupts,
+EXPORT_SYMBOL_NS_GPL(otx2_cptlf_unregister_done_interrupts,
 		     CRYPTO_DEV_OCTEONTX2_CPT);
 
 static int cptlf_do_register_interrrupts(struct otx2_cptlfs_info *lfs,
@@ -296,34 +330,53 @@ static int cptlf_do_register_interrrupts(struct otx2_cptlfs_info *lfs,
 	return ret;
 }
 
-int otx2_cptlf_register_interrupts(struct otx2_cptlfs_info *lfs)
+int otx2_cptlf_register_misc_interrupts(struct otx2_cptlfs_info *lfs)
 {
+	bool is_cpt1 = (lfs->blkaddr == BLKADDR_CPT1);
 	int irq_offs, ret, i;
 
+	irq_offs = OTX2_CPT_LF_INT_VEC_E_MISC;
 	for (i = 0; i < lfs->lfs_num; i++) {
-		irq_offs = OTX2_CPT_LF_INT_VEC_E_MISC;
-		snprintf(lfs->lf[i].irq_name[irq_offs], 32, "CPTLF Misc%d", i);
+		snprintf(lfs->lf[i].irq_name[irq_offs], 32, "CPT%dLF Misc%d",
+			 is_cpt1, i);
 		ret = cptlf_do_register_interrrupts(lfs, i, irq_offs,
 						    cptlf_misc_intr_handler);
 		if (ret)
 			goto free_irq;
+	}
+	cptlf_set_misc_intrs(lfs, true);
+	return 0;
 
-		irq_offs = OTX2_CPT_LF_INT_VEC_E_DONE;
-		snprintf(lfs->lf[i].irq_name[irq_offs], 32, "OTX2_CPTLF Done%d",
-			 i);
+free_irq:
+	otx2_cptlf_unregister_misc_interrupts(lfs);
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cptlf_register_misc_interrupts,
+		     CRYPTO_DEV_OCTEONTX2_CPT);
+
+int otx2_cptlf_register_done_interrupts(struct otx2_cptlfs_info *lfs)
+{
+	bool is_cpt1 = (lfs->blkaddr == BLKADDR_CPT1);
+	int irq_offs, ret, i;
+
+	irq_offs = OTX2_CPT_LF_INT_VEC_E_DONE;
+	for (i = 0; i < lfs->lfs_num; i++) {
+		snprintf(lfs->lf[i].irq_name[irq_offs], 32,
+			 "OTX2_CPT%dLF Done%d", is_cpt1, i);
 		ret = cptlf_do_register_interrrupts(lfs, i, irq_offs,
 						    cptlf_done_intr_handler);
 		if (ret)
 			goto free_irq;
 	}
-	cptlf_enable_intrs(lfs);
+	cptlf_set_done_intrs(lfs, true);
 	return 0;
 
 free_irq:
-	otx2_cptlf_unregister_interrupts(lfs);
+	otx2_cptlf_unregister_done_interrupts(lfs);
 	return ret;
 }
-EXPORT_SYMBOL_NS_GPL(otx2_cptlf_register_interrupts, CRYPTO_DEV_OCTEONTX2_CPT);
+EXPORT_SYMBOL_NS_GPL(otx2_cptlf_register_done_interrupts,
+		     CRYPTO_DEV_OCTEONTX2_CPT);
 
 void otx2_cptlf_free_irqs_affinity(struct otx2_cptlfs_info *lfs)
 {
@@ -416,11 +469,17 @@ int otx2_cptlf_init(struct otx2_cptlfs_info *lfs, u8 eng_grp_mask, int pri,
 	if (ret)
 		goto free_iq;
 
+	if (lfs->ctx_ilen_ovrd) {
+		ret = cptlf_set_ctx_ilen(lfs, lfs->ctx_ilen);
+		if (ret)
+			goto free_iq;
+	}
+
 	return 0;
 
 free_iq:
-	otx2_cpt_free_instruction_queues(lfs);
 	cptlf_hw_cleanup(lfs);
+	otx2_cpt_free_instruction_queues(lfs);
 detach_rsrcs:
 	otx2_cpt_detach_rsrcs_msg(lfs);
 clear_lfs_num:
@@ -431,11 +490,13 @@ EXPORT_SYMBOL_NS_GPL(otx2_cptlf_init, CRYPTO_DEV_OCTEONTX2_CPT);
 
 void otx2_cptlf_shutdown(struct otx2_cptlfs_info *lfs)
 {
-	lfs->lfs_num = 0;
 	/* Cleanup LFs hardware side */
 	cptlf_hw_cleanup(lfs);
+	/* Free instruction queues */
+	otx2_cpt_free_instruction_queues(lfs);
 	/* Send request to detach LFs */
 	otx2_cpt_detach_rsrcs_msg(lfs);
+	lfs->lfs_num = 0;
 }
 EXPORT_SYMBOL_NS_GPL(otx2_cptlf_shutdown, CRYPTO_DEV_OCTEONTX2_CPT);
 
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptlf.h b/drivers/crypto/marvell/octeontx2/otx2_cptlf.h
index 5302fe3d0e6f..bd8604be2952 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptlf.h
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptlf.h
@@ -5,6 +5,7 @@
 #define __OTX2_CPTLF_H
 
 #include <linux/soc/marvell/octeontx2/asm.h>
+#include <linux/bitfield.h>
 #include <mbox.h>
 #include <rvu.h>
 #include "otx2_cpt_common.h"
@@ -99,6 +100,9 @@ struct cpt_hw_ops {
 			 struct otx2_cptlf_info *lf);
 	u8 (*cpt_get_compcode)(union otx2_cpt_res_s *result);
 	u8 (*cpt_get_uc_compcode)(union otx2_cpt_res_s *result);
+	struct otx2_cpt_inst_info *
+	(*cpt_sg_info_create)(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
+			      gfp_t gfp);
 };
 
 struct otx2_cptlfs_info {
@@ -116,6 +120,9 @@ struct otx2_cptlfs_info {
 	u8 kvf_limits;          /* Kernel crypto limits */
 	atomic_t state;         /* LF's state. started/reset */
 	int blkaddr;            /* CPT blkaddr: BLKADDR_CPT0/BLKADDR_CPT1 */
+	int global_slot;        /* Global slot across the blocks */
+	u8 ctx_ilen;
+	u8 ctx_ilen_ovrd;
 };
 
 static inline void otx2_cpt_free_instruction_queues(
@@ -203,48 +210,71 @@ static inline void otx2_cptlf_set_iqueues_size(struct otx2_cptlfs_info *lfs)
 		otx2_cptlf_do_set_iqueue_size(&lfs->lf[slot]);
 }
 
+#define INFLIGHT   GENMASK_ULL(8, 0)
+#define GRB_CNT    GENMASK_ULL(39, 32)
+#define GWB_CNT    GENMASK_ULL(47, 40)
+#define XQ_XOR     GENMASK_ULL(63, 63)
+#define DQPTR      GENMASK_ULL(19, 0)
+#define NQPTR      GENMASK_ULL(51, 32)
+
 static inline void otx2_cptlf_do_disable_iqueue(struct otx2_cptlf_info *lf)
 {
-	union otx2_cptx_lf_ctl lf_ctl = { .u = 0x0 };
-	union otx2_cptx_lf_inprog lf_inprog;
+	void __iomem *reg_base = lf->lfs->reg_base;
+	struct pci_dev *pdev = lf->lfs->pdev;
 	u8 blkaddr = lf->lfs->blkaddr;
-	int timeout = 20;
+	int timeout = 1000000;
+	u64 inprog, inst_ptr;
+	u64 slot = lf->slot;
+	u64 qsize, pending;
+	int i = 0;
 
 	/* Disable instructions enqueuing */
-	otx2_cpt_write64(lf->lfs->reg_base, blkaddr, lf->slot,
-			 OTX2_CPT_LF_CTL, lf_ctl.u);
+	otx2_cpt_write64(reg_base, blkaddr, slot, OTX2_CPT_LF_CTL, 0x0);
+
+	inprog = otx2_cpt_read64(reg_base, blkaddr, slot, OTX2_CPT_LF_INPROG);
+	inprog |= BIT_ULL(16);
+	otx2_cpt_write64(reg_base, blkaddr, slot, OTX2_CPT_LF_INPROG, inprog);
 
-	/* Wait for instruction queue to become empty */
+	qsize = otx2_cpt_read64(reg_base, blkaddr, slot, OTX2_CPT_LF_Q_SIZE) & 0x7FFF;
+	do {
+		inst_ptr = otx2_cpt_read64(reg_base, blkaddr, slot, OTX2_CPT_LF_Q_INST_PTR);
+		pending = (FIELD_GET(XQ_XOR, inst_ptr) * qsize * 40) +
+			  FIELD_GET(NQPTR, inst_ptr) - FIELD_GET(DQPTR, inst_ptr);
+		udelay(1);
+		timeout--;
+	} while ((pending != 0) && (timeout != 0));
+
+	if (timeout == 0)
+		dev_warn(&pdev->dev, "TIMEOUT: CPT poll on pending instructions\n");
+
+	timeout = 1000000;
+	/* Wait for CPT queue to become execution-quiescent */
 	do {
-		lf_inprog.u = otx2_cpt_read64(lf->lfs->reg_base, blkaddr,
-					      lf->slot, OTX2_CPT_LF_INPROG);
-		if (!lf_inprog.s.inflight)
-			break;
-
-		usleep_range(10000, 20000);
-		if (timeout-- < 0) {
-			dev_err(&lf->lfs->pdev->dev,
-				"Error LF %d is still busy.\n", lf->slot);
-			break;
+		inprog = otx2_cpt_read64(reg_base, blkaddr, slot, OTX2_CPT_LF_INPROG);
+
+		if ((FIELD_GET(INFLIGHT, inprog) == 0) &&
+		    (FIELD_GET(GRB_CNT, inprog) == 0)) {
+			i++;
+		} else {
+			i = 0;
+			timeout--;
 		}
+	} while ((timeout != 0) && (i < 10));
 
-	} while (1);
-
-	/*
-	 * Disable executions in the LF's queue,
-	 * the queue should be empty at this point
-	 */
-	lf_inprog.s.eena = 0x0;
-	otx2_cpt_write64(lf->lfs->reg_base, blkaddr, lf->slot,
-			 OTX2_CPT_LF_INPROG, lf_inprog.u);
+	if (timeout == 0)
+		dev_warn(&pdev->dev, "TIMEOUT: CPT poll on inflight count\n");
+	/* Wait for 2 us to flush all queue writes to memory */
+	udelay(2);
 }
 
 static inline void otx2_cptlf_disable_iqueues(struct otx2_cptlfs_info *lfs)
 {
 	int slot;
 
-	for (slot = 0; slot < lfs->lfs_num; slot++)
+	for (slot = 0; slot < lfs->lfs_num; slot++) {
 		otx2_cptlf_do_disable_iqueue(&lfs->lf[slot]);
+		otx2_cpt_lf_reset_msg(lfs, lfs->global_slot + slot);
+	}
 }
 
 static inline void otx2_cptlf_set_iqueue_enq(struct otx2_cptlf_info *lf,
@@ -282,6 +312,19 @@ static inline void otx2_cptlf_set_iqueue_exec(struct otx2_cptlf_info *lf,
 			 OTX2_CPT_LF_INPROG, lf_inprog.u);
 }
 
+static inline void otx2_cptlf_set_ctx_flr_flush(struct otx2_cptlf_info *lf)
+{
+	u8 blkaddr = lf->lfs->blkaddr;
+	u64 val;
+
+	val = otx2_cpt_read64(lf->lfs->reg_base, blkaddr, lf->slot,
+			      OTX2_CPT_LF_CTX_CTL);
+	val |= BIT_ULL(0);
+
+	otx2_cpt_write64(lf->lfs->reg_base, blkaddr, lf->slot,
+			 OTX2_CPT_LF_CTX_CTL, val);
+}
+
 static inline void otx2_cptlf_enable_iqueue_exec(struct otx2_cptlf_info *lf)
 {
 	otx2_cptlf_set_iqueue_exec(lf, true);
@@ -297,6 +340,10 @@ static inline void otx2_cptlf_enable_iqueues(struct otx2_cptlfs_info *lfs)
 	int slot;
 
 	for (slot = 0; slot < lfs->lfs_num; slot++) {
+		/* Enable flush on FLR for Errata */
+		if (is_dev_cn10kb(lfs->pdev))
+			otx2_cptlf_set_ctx_flr_flush(&lfs->lf[slot]);
+
 		otx2_cptlf_enable_iqueue_exec(&lfs->lf[slot]);
 		otx2_cptlf_enable_iqueue_enq(&lfs->lf[slot]);
 	}
@@ -382,8 +429,10 @@ static inline void otx2_cptlf_set_dev_info(struct otx2_cptlfs_info *lfs,
 int otx2_cptlf_init(struct otx2_cptlfs_info *lfs, u8 eng_grp_msk, int pri,
 		    int lfs_num);
 void otx2_cptlf_shutdown(struct otx2_cptlfs_info *lfs);
-int otx2_cptlf_register_interrupts(struct otx2_cptlfs_info *lfs);
-void otx2_cptlf_unregister_interrupts(struct otx2_cptlfs_info *lfs);
+int otx2_cptlf_register_misc_interrupts(struct otx2_cptlfs_info *lfs);
+int otx2_cptlf_register_done_interrupts(struct otx2_cptlfs_info *lfs);
+void otx2_cptlf_unregister_misc_interrupts(struct otx2_cptlfs_info *lfs);
+void otx2_cptlf_unregister_done_interrupts(struct otx2_cptlfs_info *lfs);
 void otx2_cptlf_free_irqs_affinity(struct otx2_cptlfs_info *lfs);
 int otx2_cptlf_set_irqs_affinity(struct otx2_cptlfs_info *lfs);
 
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf.h b/drivers/crypto/marvell/octeontx2/otx2_cptpf.h
index a209ec5af381..e5859a1e1c60 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptpf.h
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf.h
@@ -71,4 +71,8 @@ void otx2_cptpf_afpf_mbox_up_handler(struct work_struct *work);
 irqreturn_t otx2_cptpf_vfpf_mbox_intr(int irq, void *arg);
 void otx2_cptpf_vfpf_mbox_handler(struct work_struct *work);
 
+int otx2_inline_cptlf_setup(struct otx2_cptpf_dev *cptpf,
+			    struct otx2_cptlfs_info *lfs, u8 egrp, int num_lfs);
+void otx2_inline_cptlf_cleanup(struct otx2_cptlfs_info *lfs);
+
 #endif /* __OTX2_CPTPF_H */
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c
index e34223daa327..400e36d9908f 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c
@@ -14,6 +14,8 @@
 #define OTX2_CPT_DRV_STRING  "Marvell RVU CPT Physical Function Driver"
 
 #define CPT_UC_RID_CN9K_B0   1
+#define CPT_UC_RID_CN10K_A   4
+#define CPT_UC_RID_CN10K_B   5
 
 static void cptpf_enable_vfpf_mbox_intr(struct otx2_cptpf_dev *cptpf,
 					int num_vfs)
@@ -587,43 +589,22 @@ static int cpt_is_pf_usable(struct otx2_cptpf_dev *cptpf)
 	return 0;
 }
 
-static int cptx_device_reset(struct otx2_cptpf_dev *cptpf, int blkaddr)
+static void cptpf_get_rid(struct pci_dev *pdev, struct otx2_cptpf_dev *cptpf)
 {
-	int timeout = 10, ret;
-	u64 reg = 0;
+	struct otx2_cpt_eng_grps *eng_grps = &cptpf->eng_grps;
+	u64 reg_val = 0x0;
 
-	ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
-				    CPT_AF_BLK_RST, 0x1, blkaddr);
-	if (ret)
-		return ret;
-
-	do {
-		ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
-					   CPT_AF_BLK_RST, &reg, blkaddr);
-		if (ret)
-			return ret;
-
-		if (!((reg >> 63) & 0x1))
-			break;
-
-		usleep_range(10000, 20000);
-		if (timeout-- < 0)
-			return -EBUSY;
-	} while (1);
-
-	return ret;
-}
-
-static int cptpf_device_reset(struct otx2_cptpf_dev *cptpf)
-{
-	int ret = 0;
-
-	if (cptpf->has_cpt1) {
-		ret = cptx_device_reset(cptpf, BLKADDR_CPT1);
-		if (ret)
-			return ret;
+	if (is_dev_otx2(pdev)) {
+		eng_grps->rid = pdev->revision;
+		return;
 	}
-	return cptx_device_reset(cptpf, BLKADDR_CPT0);
+	otx2_cpt_read_af_reg(&cptpf->afpf_mbox, pdev, CPT_AF_CTL, &reg_val,
+			     BLKADDR_CPT0);
+	if ((cpt_feature_sgv2(pdev) && (reg_val & BIT_ULL(18))) ||
+	    is_dev_cn10ka_ax(pdev))
+		eng_grps->rid = CPT_UC_RID_CN10K_A;
+	else if (cpt_feature_sgv2(pdev))
+		eng_grps->rid = CPT_UC_RID_CN10K_B;
 }
 
 static void cptpf_check_block_implemented(struct otx2_cptpf_dev *cptpf)
@@ -643,10 +624,6 @@ static int cptpf_device_init(struct otx2_cptpf_dev *cptpf)
 
 	/* check if 'implemented' bit is set for block BLKADDR_CPT1 */
 	cptpf_check_block_implemented(cptpf);
-	/* Reset the CPT PF device */
-	ret = cptpf_device_reset(cptpf);
-	if (ret)
-		return ret;
 
 	/* Get number of SE, IE and AE engines */
 	ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
@@ -701,6 +678,7 @@ static int cptpf_sriov_enable(struct pci_dev *pdev, int num_vfs)
 	if (ret)
 		goto destroy_flr;
 
+	cptpf_get_rid(pdev, cptpf);
 	/* Get CPT HW capabilities using LOAD_FVC operation. */
 	ret = otx2_cpt_discover_eng_capabilities(cptpf);
 	if (ret)
@@ -744,7 +722,7 @@ static int otx2_cptpf_probe(struct pci_dev *pdev,
 {
 	struct device *dev = &pdev->dev;
 	struct otx2_cptpf_dev *cptpf;
-	int err;
+	int err, num_vec;
 
 	cptpf = devm_kzalloc(dev, sizeof(*cptpf), GFP_KERNEL);
 	if (!cptpf)
@@ -779,8 +757,13 @@ static int otx2_cptpf_probe(struct pci_dev *pdev,
 	if (err)
 		goto clear_drvdata;
 
-	err = pci_alloc_irq_vectors(pdev, RVU_PF_INT_VEC_CNT,
-				    RVU_PF_INT_VEC_CNT, PCI_IRQ_MSIX);
+	num_vec = pci_msix_vec_count(cptpf->pdev);
+	if (num_vec <= 0) {
+		err = -EINVAL;
+		goto clear_drvdata;
+	}
+
+	err = pci_alloc_irq_vectors(pdev, num_vec, num_vec, PCI_IRQ_MSIX);
 	if (err < 0) {
 		dev_err(dev, "Request for %d msix vectors failed\n",
 			RVU_PF_INT_VEC_CNT);
@@ -797,6 +780,7 @@ static int otx2_cptpf_probe(struct pci_dev *pdev,
 		goto destroy_afpf_mbox;
 
 	cptpf->max_vfs = pci_sriov_get_totalvfs(pdev);
+	cptpf->kvf_limits = 1;
 
 	err = cn10k_cptpf_lmtst_init(cptpf);
 	if (err)
@@ -844,6 +828,14 @@ static void otx2_cptpf_remove(struct pci_dev *pdev)
 
 	cptpf_sriov_disable(pdev);
 	otx2_cpt_unregister_dl(cptpf);
+
+	/* Cleanup Inline CPT LF's if attached */
+	if (cptpf->lfs.lfs_num)
+		otx2_inline_cptlf_cleanup(&cptpf->lfs);
+
+	if (cptpf->cpt1_lfs.lfs_num)
+		otx2_inline_cptlf_cleanup(&cptpf->cpt1_lfs);
+
 	/* Delete sysfs entry created for kernel VF limits */
 	sysfs_remove_group(&pdev->dev.kobj, &cptpf_sysfs_group);
 	/* Cleanup engine groups */
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c
index 480b3720f15a..ec1ac7e836a3 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c
@@ -78,7 +78,7 @@ static int handle_msg_get_caps(struct otx2_cptpf_dev *cptpf,
 	rsp->hdr.sig = OTX2_MBOX_RSP_SIG;
 	rsp->hdr.pcifunc = req->pcifunc;
 	rsp->cpt_pf_drv_version = OTX2_CPT_PF_DRV_VERSION;
-	rsp->cpt_revision = cptpf->pdev->revision;
+	rsp->cpt_revision = cptpf->eng_grps.rid;
 	memcpy(&rsp->eng_caps, &cptpf->eng_caps, sizeof(rsp->eng_caps));
 
 	return 0;
@@ -171,6 +171,8 @@ static int rx_inline_ipsec_lf_cfg(struct otx2_cptpf_dev *cptpf, u8 egrp,
 	nix_req->hdr.id = MBOX_MSG_NIX_INLINE_IPSEC_CFG;
 	nix_req->hdr.sig = OTX2_MBOX_REQ_SIG;
 	nix_req->enable = 1;
+	nix_req->credit_th = req->credit_th;
+	nix_req->bpid = req->bpid;
 	if (!req->credit || req->credit > OTX2_CPT_INST_QLEN_MSGS)
 		nix_req->cpt_credit = OTX2_CPT_INST_QLEN_MSGS - 1;
 	else
@@ -197,12 +199,53 @@ static int rx_inline_ipsec_lf_cfg(struct otx2_cptpf_dev *cptpf, u8 egrp,
 	return send_inline_ipsec_inbound_msg(cptpf, req->sso_pf_func, 0);
 }
 
+int
+otx2_inline_cptlf_setup(struct otx2_cptpf_dev *cptpf,
+			struct otx2_cptlfs_info *lfs, u8 egrp, int num_lfs)
+{
+	int ret;
+
+	ret = otx2_cptlf_init(lfs, 1 << egrp, OTX2_CPT_QUEUE_HI_PRIO, 1);
+	if (ret) {
+		dev_err(&cptpf->pdev->dev,
+			"LF configuration failed for RX inline ipsec.\n");
+		return ret;
+	}
+
+	/* Get msix offsets for attached LFs */
+	ret = otx2_cpt_msix_offset_msg(lfs);
+	if (ret)
+		goto cleanup_lf;
+
+	/* Register for CPT LF Misc interrupts */
+	ret = otx2_cptlf_register_misc_interrupts(lfs);
+	if (ret)
+		goto free_irq;
+
+	return 0;
+free_irq:
+	otx2_cptlf_unregister_misc_interrupts(lfs);
+cleanup_lf:
+	otx2_cptlf_shutdown(lfs);
+	return ret;
+}
+
+void
+otx2_inline_cptlf_cleanup(struct otx2_cptlfs_info *lfs)
+{
+	/* Unregister misc interrupt */
+	otx2_cptlf_unregister_misc_interrupts(lfs);
+
+	/* Cleanup LFs */
+	otx2_cptlf_shutdown(lfs);
+}
+
 static int handle_msg_rx_inline_ipsec_lf_cfg(struct otx2_cptpf_dev *cptpf,
 					     struct mbox_msghdr *req)
 {
 	struct otx2_cpt_rx_inline_lf_cfg *cfg_req;
+	int num_lfs = 1, ret;
 	u8 egrp;
-	int ret;
 
 	cfg_req = (struct otx2_cpt_rx_inline_lf_cfg *)req;
 	if (cptpf->lfs.lfs_num) {
@@ -223,11 +266,13 @@ static int handle_msg_rx_inline_ipsec_lf_cfg(struct otx2_cptpf_dev *cptpf,
 
 	otx2_cptlf_set_dev_info(&cptpf->lfs, cptpf->pdev, cptpf->reg_base,
 				&cptpf->afpf_mbox, BLKADDR_CPT0);
-	ret = otx2_cptlf_init(&cptpf->lfs, 1 << egrp, OTX2_CPT_QUEUE_HI_PRIO,
-			      1);
+	cptpf->lfs.global_slot = 0;
+	cptpf->lfs.ctx_ilen_ovrd = cfg_req->ctx_ilen_valid;
+	cptpf->lfs.ctx_ilen = cfg_req->ctx_ilen;
+
+	ret = otx2_inline_cptlf_setup(cptpf, &cptpf->lfs, egrp, num_lfs);
 	if (ret) {
-		dev_err(&cptpf->pdev->dev,
-			"LF configuration failed for RX inline ipsec.\n");
+		dev_err(&cptpf->pdev->dev, "Inline-Ipsec CPT0 LF setup failed.\n");
 		return ret;
 	}
 
@@ -236,11 +281,13 @@ static int handle_msg_rx_inline_ipsec_lf_cfg(struct otx2_cptpf_dev *cptpf,
 		otx2_cptlf_set_dev_info(&cptpf->cpt1_lfs, cptpf->pdev,
 					cptpf->reg_base, &cptpf->afpf_mbox,
 					BLKADDR_CPT1);
-		ret = otx2_cptlf_init(&cptpf->cpt1_lfs, 1 << egrp,
-				      OTX2_CPT_QUEUE_HI_PRIO, 1);
+		cptpf->cpt1_lfs.global_slot = num_lfs;
+		cptpf->cpt1_lfs.ctx_ilen_ovrd = cfg_req->ctx_ilen_valid;
+		cptpf->cpt1_lfs.ctx_ilen = cfg_req->ctx_ilen;
+		ret = otx2_inline_cptlf_setup(cptpf, &cptpf->cpt1_lfs, egrp,
+					      num_lfs);
 		if (ret) {
-			dev_err(&cptpf->pdev->dev,
-				"LF configuration failed for RX inline ipsec.\n");
+			dev_err(&cptpf->pdev->dev, "Inline CPT1 LF setup failed.\n");
 			goto lf_cleanup;
 		}
 		cptpf->rsrc_req_blkaddr = 0;
@@ -253,9 +300,9 @@ static int handle_msg_rx_inline_ipsec_lf_cfg(struct otx2_cptpf_dev *cptpf,
 	return 0;
 
 lf1_cleanup:
-	otx2_cptlf_shutdown(&cptpf->cpt1_lfs);
+	otx2_inline_cptlf_cleanup(&cptpf->cpt1_lfs);
 lf_cleanup:
-	otx2_cptlf_shutdown(&cptpf->lfs);
+	otx2_inline_cptlf_cleanup(&cptpf->lfs);
 	return ret;
 }
 
@@ -410,6 +457,8 @@ static void process_afpf_mbox_msg(struct otx2_cptpf_dev *cptpf,
 	struct otx2_cptlfs_info *lfs = &cptpf->lfs;
 	struct device *dev = &cptpf->pdev->dev;
 	struct cpt_rd_wr_reg_msg *rsp_rd_wr;
+	struct msix_offset_rsp *rsp_msix;
+	int i;
 
 	if (msg->id >= MBOX_MSG_MAX) {
 		dev_err(dev, "MBOX msg with unknown ID %d\n", msg->id);
@@ -428,6 +477,14 @@ static void process_afpf_mbox_msg(struct otx2_cptpf_dev *cptpf,
 		cptpf->pf_id = (msg->pcifunc >> RVU_PFVF_PF_SHIFT) &
 				RVU_PFVF_PF_MASK;
 		break;
+	case MBOX_MSG_MSIX_OFFSET:
+		rsp_msix = (struct msix_offset_rsp *) msg;
+		for (i = 0; i < rsp_msix->cptlfs; i++)
+			lfs->lf[i].msix_offset = rsp_msix->cptlf_msixoff[i];
+
+		for (i = 0; i < rsp_msix->cpt1_lfs; i++)
+			lfs->lf[i].msix_offset = rsp_msix->cpt1_lf_msixoff[i];
+		break;
 	case MBOX_MSG_CPT_RD_WR_REGISTER:
 		rsp_rd_wr = (struct cpt_rd_wr_reg_msg *)msg;
 		if (msg->rc) {
@@ -449,6 +506,7 @@ static void process_afpf_mbox_msg(struct otx2_cptpf_dev *cptpf,
 		break;
 	case MBOX_MSG_CPT_INLINE_IPSEC_CFG:
 	case MBOX_MSG_NIX_INLINE_IPSEC_CFG:
+	case MBOX_MSG_CPT_LF_RESET:
 		break;
 
 	default:
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c
index 1958b797a421..5c9484646172 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c
@@ -16,7 +16,11 @@
 #define LOADFVC_MAJOR_OP 0x01
 #define LOADFVC_MINOR_OP 0x08
 
-#define CTX_FLUSH_TIMER_CNT 0xFFFFFF
+/*
+ * Interval to flush dirty data for next CTX entry. The interval is measured
+ * in increments of 10ns(interval time = CTX_FLUSH_TIMER_COUNT * 10ns).
+ */
+#define CTX_FLUSH_TIMER_CNT 0x2FAF0
 
 struct fw_info_t {
 	struct list_head ucodes;
@@ -117,12 +121,10 @@ static char *get_ucode_type_str(int ucode_type)
 
 static int get_ucode_type(struct device *dev,
 			  struct otx2_cpt_ucode_hdr *ucode_hdr,
-			  int *ucode_type)
+			  int *ucode_type, u16 rid)
 {
-	struct otx2_cptpf_dev *cptpf = dev_get_drvdata(dev);
 	char ver_str_prefix[OTX2_CPT_UCODE_VER_STR_SZ];
 	char tmp_ver_str[OTX2_CPT_UCODE_VER_STR_SZ];
-	struct pci_dev *pdev = cptpf->pdev;
 	int i, val = 0;
 	u8 nn;
 
@@ -130,7 +132,7 @@ static int get_ucode_type(struct device *dev,
 	for (i = 0; i < strlen(tmp_ver_str); i++)
 		tmp_ver_str[i] = tolower(tmp_ver_str[i]);
 
-	sprintf(ver_str_prefix, "ocpt-%02d", pdev->revision);
+	sprintf(ver_str_prefix, "ocpt-%02d", rid);
 	if (!strnstr(tmp_ver_str, ver_str_prefix, OTX2_CPT_UCODE_VER_STR_SZ))
 		return -EINVAL;
 
@@ -359,7 +361,7 @@ static int cpt_attach_and_enable_cores(struct otx2_cpt_eng_grp_info *eng_grp,
 }
 
 static int load_fw(struct device *dev, struct fw_info_t *fw_info,
-		   char *filename)
+		   char *filename, u16 rid)
 {
 	struct otx2_cpt_ucode_hdr *ucode_hdr;
 	struct otx2_cpt_uc_info_t *uc_info;
@@ -375,7 +377,7 @@ static int load_fw(struct device *dev, struct fw_info_t *fw_info,
 		goto free_uc_info;
 
 	ucode_hdr = (struct otx2_cpt_ucode_hdr *)uc_info->fw->data;
-	ret = get_ucode_type(dev, ucode_hdr, &ucode_type);
+	ret = get_ucode_type(dev, ucode_hdr, &ucode_type, rid);
 	if (ret)
 		goto release_fw;
 
@@ -389,6 +391,7 @@ static int load_fw(struct device *dev, struct fw_info_t *fw_info,
 	set_ucode_filename(&uc_info->ucode, filename);
 	memcpy(uc_info->ucode.ver_str, ucode_hdr->ver_str,
 	       OTX2_CPT_UCODE_VER_STR_SZ);
+	uc_info->ucode.ver_str[OTX2_CPT_UCODE_VER_STR_SZ] = 0;
 	uc_info->ucode.ver_num = ucode_hdr->ver_num;
 	uc_info->ucode.type = ucode_type;
 	uc_info->ucode.size = ucode_size;
@@ -448,7 +451,8 @@ static void print_uc_info(struct fw_info_t *fw_info)
 	}
 }
 
-static int cpt_ucode_load_fw(struct pci_dev *pdev, struct fw_info_t *fw_info)
+static int cpt_ucode_load_fw(struct pci_dev *pdev, struct fw_info_t *fw_info,
+			     u16 rid)
 {
 	char filename[OTX2_CPT_NAME_LENGTH];
 	char eng_type[8] = {0};
@@ -462,9 +466,9 @@ static int cpt_ucode_load_fw(struct pci_dev *pdev, struct fw_info_t *fw_info)
 			eng_type[i] = tolower(eng_type[i]);
 
 		snprintf(filename, sizeof(filename), "mrvl/cpt%02d/%s.out",
-			 pdev->revision, eng_type);
+			 rid, eng_type);
 		/* Request firmware for each engine type */
-		ret = load_fw(&pdev->dev, fw_info, filename);
+		ret = load_fw(&pdev->dev, fw_info, filename, rid);
 		if (ret)
 			goto release_fw;
 	}
@@ -1155,7 +1159,7 @@ int otx2_cpt_create_eng_grps(struct otx2_cptpf_dev *cptpf,
 	if (eng_grps->is_grps_created)
 		goto unlock;
 
-	ret = cpt_ucode_load_fw(pdev, &fw_info);
+	ret = cpt_ucode_load_fw(pdev, &fw_info, eng_grps->rid);
 	if (ret)
 		goto unlock;
 
@@ -1230,14 +1234,16 @@ int otx2_cpt_create_eng_grps(struct otx2_cptpf_dev *cptpf,
 	 */
 	rnm_to_cpt_errata_fixup(&pdev->dev);
 
+	otx2_cpt_read_af_reg(&cptpf->afpf_mbox, pdev, CPT_AF_CTL, &reg_val,
+			     BLKADDR_CPT0);
 	/*
 	 * Configure engine group mask to allow context prefetching
 	 * for the groups and enable random number request, to enable
 	 * CPT to request random numbers from RNM.
 	 */
+	reg_val |= OTX2_CPT_ALL_ENG_GRPS_MASK << 3 | BIT_ULL(16);
 	otx2_cpt_write_af_reg(&cptpf->afpf_mbox, pdev, CPT_AF_CTL,
-			      OTX2_CPT_ALL_ENG_GRPS_MASK << 3 | BIT_ULL(16),
-			      BLKADDR_CPT0);
+			      reg_val, BLKADDR_CPT0);
 	/*
 	 * Set interval to periodically flush dirty data for the next
 	 * CTX cache entry. Set the interval count to maximum supported
@@ -1252,10 +1258,12 @@ int otx2_cpt_create_eng_grps(struct otx2_cptpf_dev *cptpf,
 	 * encounters a fault/poison, a rare case may result in
 	 * unpredictable data being delivered to a CPT engine.
 	 */
-	otx2_cpt_read_af_reg(&cptpf->afpf_mbox, pdev, CPT_AF_DIAG, &reg_val,
-			     BLKADDR_CPT0);
-	otx2_cpt_write_af_reg(&cptpf->afpf_mbox, pdev, CPT_AF_DIAG,
-			      reg_val | BIT_ULL(24), BLKADDR_CPT0);
+	if (cpt_is_errata_38550_exists(pdev)) {
+		otx2_cpt_read_af_reg(&cptpf->afpf_mbox, pdev, CPT_AF_DIAG,
+				     &reg_val, BLKADDR_CPT0);
+		otx2_cpt_write_af_reg(&cptpf->afpf_mbox, pdev, CPT_AF_DIAG,
+				      reg_val | BIT_ULL(24), BLKADDR_CPT0);
+	}
 
 	mutex_unlock(&eng_grps->lock);
 	return 0;
@@ -1412,7 +1420,7 @@ static int create_eng_caps_discovery_grps(struct pci_dev *pdev,
 	int ret;
 
 	mutex_lock(&eng_grps->lock);
-	ret = cpt_ucode_load_fw(pdev, &fw_info);
+	ret = cpt_ucode_load_fw(pdev, &fw_info, eng_grps->rid);
 	if (ret) {
 		mutex_unlock(&eng_grps->lock);
 		return ret;
@@ -1686,13 +1694,14 @@ int otx2_cpt_dl_custom_egrp_create(struct otx2_cptpf_dev *cptpf,
 		goto err_unlock;
 	}
 	INIT_LIST_HEAD(&fw_info.ucodes);
-	ret = load_fw(dev, &fw_info, ucode_filename[0]);
+
+	ret = load_fw(dev, &fw_info, ucode_filename[0], eng_grps->rid);
 	if (ret) {
 		dev_err(dev, "Unable to load firmware %s\n", ucode_filename[0]);
 		goto err_unlock;
 	}
 	if (ucode_idx > 1) {
-		ret = load_fw(dev, &fw_info, ucode_filename[1]);
+		ret = load_fw(dev, &fw_info, ucode_filename[1], eng_grps->rid);
 		if (ret) {
 			dev_err(dev, "Unable to load firmware %s\n",
 				ucode_filename[1]);
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.h b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.h
index e69320a54b5d..365fe8943bd9 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.h
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.h
@@ -73,7 +73,7 @@ struct otx2_cpt_ucode_hdr {
 };
 
 struct otx2_cpt_ucode {
-	u8 ver_str[OTX2_CPT_UCODE_VER_STR_SZ];/*
+	u8 ver_str[OTX2_CPT_UCODE_VER_STR_SZ + 1];/*
 					       * ucode version in readable
 					       * format
 					       */
@@ -150,6 +150,7 @@ struct otx2_cpt_eng_grps {
 	int engs_num;			/* total number of engines supported */
 	u8 eng_ref_cnt[OTX2_CPT_MAX_ENGINES];/* engines reference count */
 	bool is_grps_created; /* Is the engine groups are already created */
+	u16 rid;
 };
 struct otx2_cptpf_dev;
 int otx2_cpt_init_eng_grps(struct pci_dev *pdev,
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf.h b/drivers/crypto/marvell/octeontx2/otx2_cptvf.h
index 994291e90da1..11ab9af1df15 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptvf.h
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf.h
@@ -22,6 +22,7 @@ struct otx2_cptvf_dev {
 	int blkaddr;
 	void *bbuf_base;
 	unsigned long cap_flag;
+	u64 eng_caps[OTX2_CPT_MAX_ENG_TYPES];
 };
 
 irqreturn_t otx2_cptvf_pfvf_mbox_intr(int irq, void *arg);
@@ -29,5 +30,6 @@ void otx2_cptvf_pfvf_mbox_handler(struct work_struct *work);
 int otx2_cptvf_send_eng_grp_num_msg(struct otx2_cptvf_dev *cptvf, int eng_type);
 int otx2_cptvf_send_kvf_limits_msg(struct otx2_cptvf_dev *cptvf);
 int otx2_cpt_mbox_bbuf_init(struct otx2_cptvf_dev *cptvf, struct pci_dev *pdev);
+int otx2_cptvf_send_caps_msg(struct otx2_cptvf_dev *cptvf);
 
 #endif /* __OTX2_CPTVF_H */
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.c
index e27ddd3c4e55..1604fc58dc13 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.c
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.c
@@ -17,6 +17,7 @@
 #include "otx2_cptvf.h"
 #include "otx2_cptvf_algs.h"
 #include "otx2_cpt_reqmgr.h"
+#include "cn10k_cpt.h"
 
 /* Size of salt in AES GCM mode */
 #define AES_GCM_SALT_SIZE 4
@@ -384,6 +385,9 @@ static inline int cpt_enc_dec(struct skcipher_request *req, u32 enc)
 	req_info->is_trunc_hmac = false;
 	req_info->ctrl.s.grp = otx2_cpt_get_kcrypto_eng_grp_num(pdev);
 
+	req_info->req.cptr = ctx->er_ctx.hw_ctx;
+	req_info->req.cptr_dma = ctx->er_ctx.cptr_dma;
+
 	/*
 	 * We perform an asynchronous send and once
 	 * the request is completed the driver would
@@ -530,6 +534,8 @@ static int otx2_cpt_enc_dec_init(struct crypto_skcipher *stfm)
 	struct otx2_cpt_enc_ctx *ctx = crypto_skcipher_ctx(stfm);
 	struct crypto_tfm *tfm = crypto_skcipher_tfm(stfm);
 	struct crypto_alg *alg = tfm->__crt_alg;
+	struct pci_dev *pdev;
+	int ret, cpu_num;
 
 	memset(ctx, 0, sizeof(*ctx));
 	/*
@@ -541,6 +547,15 @@ static int otx2_cpt_enc_dec_init(struct crypto_skcipher *stfm)
 		stfm, sizeof(struct otx2_cpt_req_ctx) +
 		      sizeof(struct skcipher_request));
 
+	ret = get_se_device(&pdev, &cpu_num);
+	if (ret)
+		return ret;
+
+	ctx->pdev = pdev;
+	ret = cn10k_cpt_hw_ctx_init(pdev, &ctx->er_ctx);
+	if (ret)
+		return ret;
+
 	return cpt_skcipher_fallback_init(ctx, alg);
 }
 
@@ -552,6 +567,7 @@ static void otx2_cpt_skcipher_exit(struct crypto_skcipher *tfm)
 		crypto_free_skcipher(ctx->fbk_cipher);
 		ctx->fbk_cipher = NULL;
 	}
+	cn10k_cpt_hw_ctx_clear(ctx->pdev, &ctx->er_ctx);
 }
 
 static int cpt_aead_fallback_init(struct otx2_cpt_aead_ctx *ctx,
@@ -576,6 +592,8 @@ static int cpt_aead_init(struct crypto_aead *atfm, u8 cipher_type, u8 mac_type)
 	struct otx2_cpt_aead_ctx *ctx = crypto_aead_ctx_dma(atfm);
 	struct crypto_tfm *tfm = crypto_aead_tfm(atfm);
 	struct crypto_alg *alg = tfm->__crt_alg;
+	struct pci_dev *pdev;
+	int ret, cpu_num;
 
 	ctx->cipher_type = cipher_type;
 	ctx->mac_type = mac_type;
@@ -632,6 +650,15 @@ static int cpt_aead_init(struct crypto_aead *atfm, u8 cipher_type, u8 mac_type)
 	}
 	crypto_aead_set_reqsize_dma(atfm, sizeof(struct otx2_cpt_req_ctx));
 
+	ret = get_se_device(&pdev, &cpu_num);
+	if (ret)
+		return ret;
+
+	ctx->pdev = pdev;
+	ret = cn10k_cpt_hw_ctx_init(pdev, &ctx->er_ctx);
+	if (ret)
+		return ret;
+
 	return cpt_aead_fallback_init(ctx, alg);
 }
 
@@ -694,6 +721,7 @@ static void otx2_cpt_aead_exit(struct crypto_aead *tfm)
 		crypto_free_aead(ctx->fbk_cipher);
 		ctx->fbk_cipher = NULL;
 	}
+	cn10k_cpt_hw_ctx_clear(ctx->pdev, &ctx->er_ctx);
 }
 
 static int otx2_cpt_aead_gcm_set_authsize(struct crypto_aead *tfm,
@@ -1299,6 +1327,9 @@ static int cpt_aead_enc_dec(struct aead_request *req, u8 reg_type, u8 enc)
 	req_info->is_enc = enc;
 	req_info->is_trunc_hmac = false;
 
+	req_info->req.cptr = ctx->er_ctx.hw_ctx;
+	req_info->req.cptr_dma = ctx->er_ctx.cptr_dma;
+
 	switch (reg_type) {
 	case OTX2_CPT_AEAD_ENC_DEC_REQ:
 		status = create_aead_input_list(req, enc);
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.h b/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.h
index f04184bd1744..d29f84f01cee 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.h
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.h
@@ -9,6 +9,7 @@
 #include <crypto/skcipher.h>
 #include <crypto/aead.h>
 #include "otx2_cpt_common.h"
+#include "cn10k_cpt.h"
 
 #define OTX2_CPT_MAX_ENC_KEY_SIZE    32
 #define OTX2_CPT_MAX_HASH_KEY_SIZE   64
@@ -123,6 +124,8 @@ struct otx2_cpt_enc_ctx {
 	u8 key_type;
 	u8 enc_align_len;
 	struct crypto_skcipher *fbk_cipher;
+	struct pci_dev *pdev;
+	struct cn10k_cpt_errata_ctx er_ctx;
 };
 
 union otx2_cpt_offset_ctrl {
@@ -161,6 +164,8 @@ struct otx2_cpt_aead_ctx {
 	struct crypto_shash *hashalg;
 	struct otx2_cpt_sdesc *sdesc;
 	struct crypto_aead *fbk_cipher;
+	struct cn10k_cpt_errata_ctx er_ctx;
+	struct pci_dev *pdev;
 	u8 *ipad;
 	u8 *opad;
 	u32 enc_key_len;
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c
index bac729c885f9..527d34cc258b 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c
@@ -246,11 +246,15 @@ static void cptvf_lf_shutdown(struct otx2_cptlfs_info *lfs)
 	/* Unregister crypto algorithms */
 	otx2_cpt_crypto_exit(lfs->pdev, THIS_MODULE);
 	/* Unregister LFs interrupts */
-	otx2_cptlf_unregister_interrupts(lfs);
+	otx2_cptlf_unregister_misc_interrupts(lfs);
+	otx2_cptlf_unregister_done_interrupts(lfs);
 	/* Cleanup LFs software side */
 	lf_sw_cleanup(lfs);
+	/* Free instruction queues */
+	otx2_cpt_free_instruction_queues(lfs);
 	/* Send request to detach LFs */
 	otx2_cpt_detach_rsrcs_msg(lfs);
+	lfs->lfs_num = 0;
 }
 
 static int cptvf_lf_init(struct otx2_cptvf_dev *cptvf)
@@ -277,8 +281,7 @@ static int cptvf_lf_init(struct otx2_cptvf_dev *cptvf)
 	if (ret)
 		return ret;
 
-	lfs_num = cptvf->lfs.kvf_limits ? cptvf->lfs.kvf_limits :
-		  num_online_cpus();
+	lfs_num = cptvf->lfs.kvf_limits;
 
 	otx2_cptlf_set_dev_info(lfs, cptvf->pdev, cptvf->reg_base,
 				&cptvf->pfvf_mbox, cptvf->blkaddr);
@@ -298,7 +301,11 @@ static int cptvf_lf_init(struct otx2_cptvf_dev *cptvf)
 		goto cleanup_lf;
 
 	/* Register LFs interrupts */
-	ret = otx2_cptlf_register_interrupts(lfs);
+	ret = otx2_cptlf_register_misc_interrupts(lfs);
+	if (ret)
+		goto cleanup_lf_sw;
+
+	ret = otx2_cptlf_register_done_interrupts(lfs);
 	if (ret)
 		goto cleanup_lf_sw;
 
@@ -319,7 +326,8 @@ static int cptvf_lf_init(struct otx2_cptvf_dev *cptvf)
 disable_irqs:
 	otx2_cptlf_free_irqs_affinity(lfs);
 unregister_intr:
-	otx2_cptlf_unregister_interrupts(lfs);
+	otx2_cptlf_unregister_misc_interrupts(lfs);
+	otx2_cptlf_unregister_done_interrupts(lfs);
 cleanup_lf_sw:
 	lf_sw_cleanup(lfs);
 cleanup_lf:
@@ -380,6 +388,17 @@ static int otx2_cptvf_probe(struct pci_dev *pdev,
 		goto destroy_pfvf_mbox;
 
 	cptvf->blkaddr = BLKADDR_CPT0;
+
+	cptvf_hw_ops_get(cptvf);
+
+	ret = otx2_cptvf_send_caps_msg(cptvf);
+	if (ret) {
+		dev_err(&pdev->dev, "Couldn't get CPT engine capabilities.\n");
+		goto unregister_interrupts;
+	}
+	if (cptvf->eng_caps[OTX2_CPT_SE_TYPES] & BIT_ULL(35))
+		cptvf->lfs.ops->cpt_sg_info_create = cn10k_sgv2_info_create;
+
 	/* Initialize CPT LFs */
 	ret = cptvf_lf_init(cptvf);
 	if (ret)
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c
index 75c403f2b1d9..d9fa5f6e204d 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c
@@ -72,6 +72,7 @@ static void process_pfvf_mbox_mbox_msg(struct otx2_cptvf_dev *cptvf,
 	struct otx2_cptlfs_info *lfs = &cptvf->lfs;
 	struct otx2_cpt_kvf_limits_rsp *rsp_limits;
 	struct otx2_cpt_egrp_num_rsp *rsp_grp;
+	struct otx2_cpt_caps_rsp *eng_caps;
 	struct cpt_rd_wr_reg_msg *rsp_reg;
 	struct msix_offset_rsp *rsp_msix;
 	int i;
@@ -127,6 +128,13 @@ static void process_pfvf_mbox_mbox_msg(struct otx2_cptvf_dev *cptvf,
 		rsp_limits = (struct otx2_cpt_kvf_limits_rsp *) msg;
 		cptvf->lfs.kvf_limits = rsp_limits->kvf_limits;
 		break;
+	case MBOX_MSG_GET_CAPS:
+		eng_caps = (struct otx2_cpt_caps_rsp *)msg;
+		memcpy(cptvf->eng_caps, eng_caps->eng_caps,
+		       sizeof(cptvf->eng_caps));
+		break;
+	case MBOX_MSG_CPT_LF_RESET:
+		break;
 	default:
 		dev_err(&cptvf->pdev->dev, "Unsupported msg %d received.\n",
 			msg->id);
@@ -205,3 +213,23 @@ int otx2_cptvf_send_kvf_limits_msg(struct otx2_cptvf_dev *cptvf)
 
 	return otx2_cpt_send_mbox_msg(mbox, pdev);
 }
+
+int otx2_cptvf_send_caps_msg(struct otx2_cptvf_dev *cptvf)
+{
+	struct otx2_mbox *mbox = &cptvf->pfvf_mbox;
+	struct pci_dev *pdev = cptvf->pdev;
+	struct mbox_msghdr *req;
+
+	req = (struct mbox_msghdr *)
+	      otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req),
+				      sizeof(struct otx2_cpt_caps_rsp));
+	if (!req) {
+		dev_err(&pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+	req->id = MBOX_MSG_GET_CAPS;
+	req->sig = OTX2_MBOX_REQ_SIG;
+	req->pcifunc = OTX2_CPT_RVU_PFFUNC(cptvf->vf_id, 0);
+
+	return otx2_cpt_send_mbox_msg(mbox, pdev);
+}
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_reqmgr.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_reqmgr.c
index 811ded72ce5f..5387c68f3c9d 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptvf_reqmgr.c
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_reqmgr.c
@@ -4,9 +4,6 @@
 #include "otx2_cptvf.h"
 #include "otx2_cpt_common.h"
 
-/* SG list header size in bytes */
-#define SG_LIST_HDR_SIZE	8
-
 /* Default timeout when waiting for free pending entry in us */
 #define CPT_PENTRY_TIMEOUT	1000
 #define CPT_PENTRY_STEP		50
@@ -26,9 +23,9 @@ static void otx2_cpt_dump_sg_list(struct pci_dev *pdev,
 
 	pr_debug("Gather list size %d\n", req->in_cnt);
 	for (i = 0; i < req->in_cnt; i++) {
-		pr_debug("Buffer %d size %d, vptr 0x%p, dmaptr 0x%p\n", i,
+		pr_debug("Buffer %d size %d, vptr 0x%p, dmaptr 0x%llx\n", i,
 			 req->in[i].size, req->in[i].vptr,
-			 (void *) req->in[i].dma_addr);
+			 req->in[i].dma_addr);
 		pr_debug("Buffer hexdump (%d bytes)\n",
 			 req->in[i].size);
 		print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1,
@@ -36,9 +33,9 @@ static void otx2_cpt_dump_sg_list(struct pci_dev *pdev,
 	}
 	pr_debug("Scatter list size %d\n", req->out_cnt);
 	for (i = 0; i < req->out_cnt; i++) {
-		pr_debug("Buffer %d size %d, vptr 0x%p, dmaptr 0x%p\n", i,
+		pr_debug("Buffer %d size %d, vptr 0x%p, dmaptr 0x%llx\n", i,
 			 req->out[i].size, req->out[i].vptr,
-			 (void *) req->out[i].dma_addr);
+			 req->out[i].dma_addr);
 		pr_debug("Buffer hexdump (%d bytes)\n", req->out[i].size);
 		print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1,
 				     req->out[i].vptr, req->out[i].size, false);
@@ -84,149 +81,6 @@ static inline void free_pentry(struct otx2_cpt_pending_entry *pentry)
 	pentry->busy = false;
 }
 
-static inline int setup_sgio_components(struct pci_dev *pdev,
-					struct otx2_cpt_buf_ptr *list,
-					int buf_count, u8 *buffer)
-{
-	struct otx2_cpt_sglist_component *sg_ptr = NULL;
-	int ret = 0, i, j;
-	int components;
-
-	if (unlikely(!list)) {
-		dev_err(&pdev->dev, "Input list pointer is NULL\n");
-		return -EFAULT;
-	}
-
-	for (i = 0; i < buf_count; i++) {
-		if (unlikely(!list[i].vptr))
-			continue;
-		list[i].dma_addr = dma_map_single(&pdev->dev, list[i].vptr,
-						  list[i].size,
-						  DMA_BIDIRECTIONAL);
-		if (unlikely(dma_mapping_error(&pdev->dev, list[i].dma_addr))) {
-			dev_err(&pdev->dev, "Dma mapping failed\n");
-			ret = -EIO;
-			goto sg_cleanup;
-		}
-	}
-	components = buf_count / 4;
-	sg_ptr = (struct otx2_cpt_sglist_component *)buffer;
-	for (i = 0; i < components; i++) {
-		sg_ptr->len0 = cpu_to_be16(list[i * 4 + 0].size);
-		sg_ptr->len1 = cpu_to_be16(list[i * 4 + 1].size);
-		sg_ptr->len2 = cpu_to_be16(list[i * 4 + 2].size);
-		sg_ptr->len3 = cpu_to_be16(list[i * 4 + 3].size);
-		sg_ptr->ptr0 = cpu_to_be64(list[i * 4 + 0].dma_addr);
-		sg_ptr->ptr1 = cpu_to_be64(list[i * 4 + 1].dma_addr);
-		sg_ptr->ptr2 = cpu_to_be64(list[i * 4 + 2].dma_addr);
-		sg_ptr->ptr3 = cpu_to_be64(list[i * 4 + 3].dma_addr);
-		sg_ptr++;
-	}
-	components = buf_count % 4;
-
-	switch (components) {
-	case 3:
-		sg_ptr->len2 = cpu_to_be16(list[i * 4 + 2].size);
-		sg_ptr->ptr2 = cpu_to_be64(list[i * 4 + 2].dma_addr);
-		fallthrough;
-	case 2:
-		sg_ptr->len1 = cpu_to_be16(list[i * 4 + 1].size);
-		sg_ptr->ptr1 = cpu_to_be64(list[i * 4 + 1].dma_addr);
-		fallthrough;
-	case 1:
-		sg_ptr->len0 = cpu_to_be16(list[i * 4 + 0].size);
-		sg_ptr->ptr0 = cpu_to_be64(list[i * 4 + 0].dma_addr);
-		break;
-	default:
-		break;
-	}
-	return ret;
-
-sg_cleanup:
-	for (j = 0; j < i; j++) {
-		if (list[j].dma_addr) {
-			dma_unmap_single(&pdev->dev, list[j].dma_addr,
-					 list[j].size, DMA_BIDIRECTIONAL);
-		}
-
-		list[j].dma_addr = 0;
-	}
-	return ret;
-}
-
-static inline struct otx2_cpt_inst_info *info_create(struct pci_dev *pdev,
-					      struct otx2_cpt_req_info *req,
-					      gfp_t gfp)
-{
-	int align = OTX2_CPT_DMA_MINALIGN;
-	struct otx2_cpt_inst_info *info;
-	u32 dlen, align_dlen, info_len;
-	u16 g_sz_bytes, s_sz_bytes;
-	u32 total_mem_len;
-
-	if (unlikely(req->in_cnt > OTX2_CPT_MAX_SG_IN_CNT ||
-		     req->out_cnt > OTX2_CPT_MAX_SG_OUT_CNT)) {
-		dev_err(&pdev->dev, "Error too many sg components\n");
-		return NULL;
-	}
-
-	g_sz_bytes = ((req->in_cnt + 3) / 4) *
-		      sizeof(struct otx2_cpt_sglist_component);
-	s_sz_bytes = ((req->out_cnt + 3) / 4) *
-		      sizeof(struct otx2_cpt_sglist_component);
-
-	dlen = g_sz_bytes + s_sz_bytes + SG_LIST_HDR_SIZE;
-	align_dlen = ALIGN(dlen, align);
-	info_len = ALIGN(sizeof(*info), align);
-	total_mem_len = align_dlen + info_len + sizeof(union otx2_cpt_res_s);
-
-	info = kzalloc(total_mem_len, gfp);
-	if (unlikely(!info))
-		return NULL;
-
-	info->dlen = dlen;
-	info->in_buffer = (u8 *)info + info_len;
-
-	((u16 *)info->in_buffer)[0] = req->out_cnt;
-	((u16 *)info->in_buffer)[1] = req->in_cnt;
-	((u16 *)info->in_buffer)[2] = 0;
-	((u16 *)info->in_buffer)[3] = 0;
-	cpu_to_be64s((u64 *)info->in_buffer);
-
-	/* Setup gather (input) components */
-	if (setup_sgio_components(pdev, req->in, req->in_cnt,
-				  &info->in_buffer[8])) {
-		dev_err(&pdev->dev, "Failed to setup gather list\n");
-		goto destroy_info;
-	}
-
-	if (setup_sgio_components(pdev, req->out, req->out_cnt,
-				  &info->in_buffer[8 + g_sz_bytes])) {
-		dev_err(&pdev->dev, "Failed to setup scatter list\n");
-		goto destroy_info;
-	}
-
-	info->dma_len = total_mem_len - info_len;
-	info->dptr_baddr = dma_map_single(&pdev->dev, info->in_buffer,
-					  info->dma_len, DMA_BIDIRECTIONAL);
-	if (unlikely(dma_mapping_error(&pdev->dev, info->dptr_baddr))) {
-		dev_err(&pdev->dev, "DMA Mapping failed for cpt req\n");
-		goto destroy_info;
-	}
-	/*
-	 * Get buffer for union otx2_cpt_res_s response
-	 * structure and its physical address
-	 */
-	info->completion_addr = info->in_buffer + align_dlen;
-	info->comp_baddr = info->dptr_baddr + align_dlen;
-
-	return info;
-
-destroy_info:
-	otx2_cpt_info_destroy(pdev, info);
-	return NULL;
-}
-
 static int process_request(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
 			   struct otx2_cpt_pending_queue *pqueue,
 			   struct otx2_cptlf_info *lf)
@@ -247,7 +101,7 @@ static int process_request(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
 	if (unlikely(!otx2_cptlf_started(lf->lfs)))
 		return -ENODEV;
 
-	info = info_create(pdev, req, gfp);
+	info = lf->lfs->ops->cpt_sg_info_create(pdev, req, gfp);
 	if (unlikely(!info)) {
 		dev_err(&pdev->dev, "Setting up cpt inst info failed");
 		return -ENOMEM;
@@ -303,9 +157,9 @@ static int process_request(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
 
 	/* 64-bit swap for microcode data reads, not needed for addresses*/
 	cpu_to_be64s(&iq_cmd.cmd.u);
-	iq_cmd.dptr = info->dptr_baddr;
-	iq_cmd.rptr = 0;
-	iq_cmd.cptr.u = 0;
+	iq_cmd.dptr = info->dptr_baddr | info->gthr_sz << 60;
+	iq_cmd.rptr = info->rptr_baddr | info->sctr_sz << 60;
+	iq_cmd.cptr.s.cptr = cpt_req->cptr_dma;
 	iq_cmd.cptr.s.grp = ctrl->s.grp;
 
 	/* Fill in the CPT_INST_S type command for HW interpretation */
diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c
index caea98622c33..7a3083debc2b 100644
--- a/drivers/crypto/n2_core.c
+++ b/drivers/crypto/n2_core.c
@@ -1121,19 +1121,6 @@ static const struct n2_skcipher_tmpl skcipher_tmpls[] = {
 			.decrypt	= n2_decrypt_chaining,
 		},
 	},
-	{	.name		= "cfb(des)",
-		.drv_name	= "cfb-des",
-		.block_size	= DES_BLOCK_SIZE,
-		.enc_type	= (ENC_TYPE_ALG_DES |
-				   ENC_TYPE_CHAINING_CFB),
-		.skcipher	= {
-			.min_keysize	= DES_KEY_SIZE,
-			.max_keysize	= DES_KEY_SIZE,
-			.setkey		= n2_des_setkey,
-			.encrypt	= n2_encrypt_chaining,
-			.decrypt	= n2_decrypt_chaining,
-		},
-	},
 
 	/* 3DES: ECB CBC and CFB are supported */
 	{	.name		= "ecb(des3_ede)",
@@ -1163,19 +1150,7 @@ static const struct n2_skcipher_tmpl skcipher_tmpls[] = {
 			.decrypt	= n2_decrypt_chaining,
 		},
 	},
-	{	.name		= "cfb(des3_ede)",
-		.drv_name	= "cfb-3des",
-		.block_size	= DES_BLOCK_SIZE,
-		.enc_type	= (ENC_TYPE_ALG_3DES |
-				   ENC_TYPE_CHAINING_CFB),
-		.skcipher	= {
-			.min_keysize	= 3 * DES_KEY_SIZE,
-			.max_keysize	= 3 * DES_KEY_SIZE,
-			.setkey		= n2_3des_setkey,
-			.encrypt	= n2_encrypt_chaining,
-			.decrypt	= n2_decrypt_chaining,
-		},
-	},
+
 	/* AES: ECB CBC and CTR are supported */
 	{	.name		= "ecb(aes)",
 		.drv_name	= "ecb-aes",
@@ -1382,8 +1357,12 @@ static int __n2_register_one_hmac(struct n2_ahash_alg *n2ahash)
 	ahash->setkey = n2_hmac_async_setkey;
 
 	base = &ahash->halg.base;
-	snprintf(base->cra_name, CRYPTO_MAX_ALG_NAME, "hmac(%s)", p->child_alg);
-	snprintf(base->cra_driver_name, CRYPTO_MAX_ALG_NAME, "hmac-%s-n2", p->child_alg);
+	if (snprintf(base->cra_name, CRYPTO_MAX_ALG_NAME, "hmac(%s)",
+		     p->child_alg) >= CRYPTO_MAX_ALG_NAME)
+		goto out_free_p;
+	if (snprintf(base->cra_driver_name, CRYPTO_MAX_ALG_NAME, "hmac-%s-n2",
+		     p->child_alg) >= CRYPTO_MAX_ALG_NAME)
+		goto out_free_p;
 
 	base->cra_ctxsize = sizeof(struct n2_hmac_ctx);
 	base->cra_init = n2_hmac_cra_init;
@@ -1394,6 +1373,7 @@ static int __n2_register_one_hmac(struct n2_ahash_alg *n2ahash)
 	if (err) {
 		pr_err("%s alg registration failed\n", base->cra_name);
 		list_del(&p->derived.entry);
+out_free_p:
 		kfree(p);
 	} else {
 		pr_info("%s alg registered\n", base->cra_name);
diff --git a/drivers/crypto/rockchip/rk3288_crypto_skcipher.c b/drivers/crypto/rockchip/rk3288_crypto_skcipher.c
index da95747d973f..9393e10671c2 100644
--- a/drivers/crypto/rockchip/rk3288_crypto_skcipher.c
+++ b/drivers/crypto/rockchip/rk3288_crypto_skcipher.c
@@ -445,8 +445,8 @@ static int rk_cipher_tfm_init(struct crypto_skcipher *tfm)
 		return PTR_ERR(ctx->fallback_tfm);
 	}
 
-	tfm->reqsize = sizeof(struct rk_cipher_rctx) +
-		crypto_skcipher_reqsize(ctx->fallback_tfm);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct rk_cipher_rctx) +
+				    crypto_skcipher_reqsize(ctx->fallback_tfm));
 
 	return 0;
 }
diff --git a/drivers/crypto/sa2ul.c b/drivers/crypto/sa2ul.c
index 6846a8429574..78a4930c6480 100644
--- a/drivers/crypto/sa2ul.c
+++ b/drivers/crypto/sa2ul.c
@@ -1869,9 +1869,8 @@ static int sa_aead_setkey(struct crypto_aead *authenc,
 	crypto_aead_set_flags(ctx->fallback.aead,
 			      crypto_aead_get_flags(authenc) &
 			      CRYPTO_TFM_REQ_MASK);
-	crypto_aead_setkey(ctx->fallback.aead, key, keylen);
 
-	return 0;
+	return crypto_aead_setkey(ctx->fallback.aead, key, keylen);
 }
 
 static int sa_aead_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c
index 02065131c300..3423b5cde1c7 100644
--- a/drivers/crypto/sahara.c
+++ b/drivers/crypto/sahara.c
@@ -15,6 +15,7 @@
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
+#include <crypto/engine.h>
 #include <crypto/sha1.h>
 #include <crypto/sha2.h>
 
@@ -24,106 +25,101 @@
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/kernel.h>
-#include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/spinlock.h>
 
-#define SHA_BUFFER_LEN		PAGE_SIZE
-#define SAHARA_MAX_SHA_BLOCK_SIZE	SHA256_BLOCK_SIZE
-
-#define SAHARA_NAME "sahara"
-#define SAHARA_VERSION_3	3
-#define SAHARA_VERSION_4	4
-#define SAHARA_TIMEOUT_MS	1000
-#define SAHARA_MAX_HW_DESC	2
-#define SAHARA_MAX_HW_LINK	20
-
-#define FLAGS_MODE_MASK		0x000f
-#define FLAGS_ENCRYPT		BIT(0)
-#define FLAGS_CBC		BIT(1)
-#define FLAGS_NEW_KEY		BIT(3)
-
-#define SAHARA_HDR_BASE			0x00800000
-#define SAHARA_HDR_SKHA_ALG_AES	0
-#define SAHARA_HDR_SKHA_OP_ENC		(1 << 2)
-#define SAHARA_HDR_SKHA_MODE_ECB	(0 << 3)
-#define SAHARA_HDR_SKHA_MODE_CBC	(1 << 3)
-#define SAHARA_HDR_FORM_DATA		(5 << 16)
-#define SAHARA_HDR_FORM_KEY		(8 << 16)
-#define SAHARA_HDR_LLO			(1 << 24)
-#define SAHARA_HDR_CHA_SKHA		(1 << 28)
-#define SAHARA_HDR_CHA_MDHA		(2 << 28)
-#define SAHARA_HDR_PARITY_BIT		(1 << 31)
-
-#define SAHARA_HDR_MDHA_SET_MODE_MD_KEY	0x20880000
-#define SAHARA_HDR_MDHA_SET_MODE_HASH	0x208D0000
-#define SAHARA_HDR_MDHA_HASH		0xA0850000
-#define SAHARA_HDR_MDHA_STORE_DIGEST	0x20820000
-#define SAHARA_HDR_MDHA_ALG_SHA1	0
-#define SAHARA_HDR_MDHA_ALG_MD5		1
-#define SAHARA_HDR_MDHA_ALG_SHA256	2
-#define SAHARA_HDR_MDHA_ALG_SHA224	3
-#define SAHARA_HDR_MDHA_PDATA		(1 << 2)
-#define SAHARA_HDR_MDHA_HMAC		(1 << 3)
-#define SAHARA_HDR_MDHA_INIT		(1 << 5)
-#define SAHARA_HDR_MDHA_IPAD		(1 << 6)
-#define SAHARA_HDR_MDHA_OPAD		(1 << 7)
-#define SAHARA_HDR_MDHA_SWAP		(1 << 8)
-#define SAHARA_HDR_MDHA_MAC_FULL	(1 << 9)
-#define SAHARA_HDR_MDHA_SSL		(1 << 10)
-
-/* SAHARA can only process one request at a time */
-#define SAHARA_QUEUE_LENGTH	1
-
-#define SAHARA_REG_VERSION	0x00
-#define SAHARA_REG_DAR		0x04
-#define SAHARA_REG_CONTROL	0x08
-#define		SAHARA_CONTROL_SET_THROTTLE(x)	(((x) & 0xff) << 24)
-#define		SAHARA_CONTROL_SET_MAXBURST(x)	(((x) & 0xff) << 16)
-#define		SAHARA_CONTROL_RNG_AUTORSD	(1 << 7)
-#define		SAHARA_CONTROL_ENABLE_INT	(1 << 4)
-#define SAHARA_REG_CMD		0x0C
-#define		SAHARA_CMD_RESET		(1 << 0)
-#define		SAHARA_CMD_CLEAR_INT		(1 << 8)
-#define		SAHARA_CMD_CLEAR_ERR		(1 << 9)
-#define		SAHARA_CMD_SINGLE_STEP		(1 << 10)
-#define		SAHARA_CMD_MODE_BATCH		(1 << 16)
-#define		SAHARA_CMD_MODE_DEBUG		(1 << 18)
-#define	SAHARA_REG_STATUS	0x10
-#define		SAHARA_STATUS_GET_STATE(x)	((x) & 0x7)
-#define			SAHARA_STATE_IDLE	0
-#define			SAHARA_STATE_BUSY	1
-#define			SAHARA_STATE_ERR	2
-#define			SAHARA_STATE_FAULT	3
-#define			SAHARA_STATE_COMPLETE	4
-#define			SAHARA_STATE_COMP_FLAG	(1 << 2)
-#define		SAHARA_STATUS_DAR_FULL		(1 << 3)
-#define		SAHARA_STATUS_ERROR		(1 << 4)
-#define		SAHARA_STATUS_SECURE		(1 << 5)
-#define		SAHARA_STATUS_FAIL		(1 << 6)
-#define		SAHARA_STATUS_INIT		(1 << 7)
-#define		SAHARA_STATUS_RNG_RESEED	(1 << 8)
-#define		SAHARA_STATUS_ACTIVE_RNG	(1 << 9)
-#define		SAHARA_STATUS_ACTIVE_MDHA	(1 << 10)
-#define		SAHARA_STATUS_ACTIVE_SKHA	(1 << 11)
-#define		SAHARA_STATUS_MODE_BATCH	(1 << 16)
-#define		SAHARA_STATUS_MODE_DEDICATED	(1 << 17)
-#define		SAHARA_STATUS_MODE_DEBUG	(1 << 18)
-#define		SAHARA_STATUS_GET_ISTATE(x)	(((x) >> 24) & 0xff)
-#define SAHARA_REG_ERRSTATUS	0x14
-#define		SAHARA_ERRSTATUS_GET_SOURCE(x)	((x) & 0xf)
-#define			SAHARA_ERRSOURCE_CHA	14
-#define			SAHARA_ERRSOURCE_DMA	15
-#define		SAHARA_ERRSTATUS_DMA_DIR	(1 << 8)
-#define		SAHARA_ERRSTATUS_GET_DMASZ(x)(((x) >> 9) & 0x3)
-#define		SAHARA_ERRSTATUS_GET_DMASRC(x) (((x) >> 13) & 0x7)
-#define		SAHARA_ERRSTATUS_GET_CHASRC(x)	(((x) >> 16) & 0xfff)
-#define		SAHARA_ERRSTATUS_GET_CHAERR(x)	(((x) >> 28) & 0x3)
-#define SAHARA_REG_FADDR	0x18
-#define SAHARA_REG_CDAR		0x1C
-#define SAHARA_REG_IDAR		0x20
+#define SHA_BUFFER_LEN				PAGE_SIZE
+#define SAHARA_MAX_SHA_BLOCK_SIZE		SHA256_BLOCK_SIZE
+
+#define SAHARA_NAME				"sahara"
+#define SAHARA_VERSION_3			3
+#define SAHARA_VERSION_4			4
+#define SAHARA_TIMEOUT_MS			1000
+#define SAHARA_MAX_HW_DESC			2
+#define SAHARA_MAX_HW_LINK			20
+
+#define FLAGS_MODE_MASK				0x000f
+#define FLAGS_ENCRYPT				BIT(0)
+#define FLAGS_CBC				BIT(1)
+
+#define SAHARA_HDR_BASE				0x00800000
+#define SAHARA_HDR_SKHA_ALG_AES			0
+#define SAHARA_HDR_SKHA_MODE_ECB		0
+#define SAHARA_HDR_SKHA_OP_ENC			BIT(2)
+#define SAHARA_HDR_SKHA_MODE_CBC		BIT(3)
+#define SAHARA_HDR_FORM_DATA			(5 << 16)
+#define SAHARA_HDR_FORM_KEY			BIT(19)
+#define SAHARA_HDR_LLO				BIT(24)
+#define SAHARA_HDR_CHA_SKHA			BIT(28)
+#define SAHARA_HDR_CHA_MDHA			BIT(29)
+#define SAHARA_HDR_PARITY_BIT			BIT(31)
+
+#define SAHARA_HDR_MDHA_SET_MODE_MD_KEY		0x20880000
+#define SAHARA_HDR_MDHA_SET_MODE_HASH		0x208D0000
+#define SAHARA_HDR_MDHA_HASH			0xA0850000
+#define SAHARA_HDR_MDHA_STORE_DIGEST		0x20820000
+#define SAHARA_HDR_MDHA_ALG_SHA1		0
+#define SAHARA_HDR_MDHA_ALG_MD5			1
+#define SAHARA_HDR_MDHA_ALG_SHA256		2
+#define SAHARA_HDR_MDHA_ALG_SHA224		3
+#define SAHARA_HDR_MDHA_PDATA			BIT(2)
+#define SAHARA_HDR_MDHA_HMAC			BIT(3)
+#define SAHARA_HDR_MDHA_INIT			BIT(5)
+#define SAHARA_HDR_MDHA_IPAD			BIT(6)
+#define SAHARA_HDR_MDHA_OPAD			BIT(7)
+#define SAHARA_HDR_MDHA_SWAP			BIT(8)
+#define SAHARA_HDR_MDHA_MAC_FULL		BIT(9)
+#define SAHARA_HDR_MDHA_SSL			BIT(10)
+
+#define SAHARA_REG_VERSION			0x00
+#define SAHARA_REG_DAR				0x04
+#define SAHARA_REG_CONTROL			0x08
+#define SAHARA_CONTROL_SET_THROTTLE(x)		(((x) & 0xff) << 24)
+#define SAHARA_CONTROL_SET_MAXBURST(x)		(((x) & 0xff) << 16)
+#define SAHARA_CONTROL_RNG_AUTORSD		BIT(7)
+#define SAHARA_CONTROL_ENABLE_INT		BIT(4)
+#define SAHARA_REG_CMD				0x0C
+#define SAHARA_CMD_RESET			BIT(0)
+#define SAHARA_CMD_CLEAR_INT			BIT(8)
+#define SAHARA_CMD_CLEAR_ERR			BIT(9)
+#define SAHARA_CMD_SINGLE_STEP			BIT(10)
+#define SAHARA_CMD_MODE_BATCH			BIT(16)
+#define SAHARA_CMD_MODE_DEBUG			BIT(18)
+#define SAHARA_REG_STATUS			0x10
+#define SAHARA_STATUS_GET_STATE(x)		((x) & 0x7)
+#define SAHARA_STATE_IDLE			0
+#define SAHARA_STATE_BUSY			1
+#define SAHARA_STATE_ERR			2
+#define SAHARA_STATE_FAULT			3
+#define SAHARA_STATE_COMPLETE			4
+#define SAHARA_STATE_COMP_FLAG			BIT(2)
+#define SAHARA_STATUS_DAR_FULL			BIT(3)
+#define SAHARA_STATUS_ERROR			BIT(4)
+#define SAHARA_STATUS_SECURE			BIT(5)
+#define SAHARA_STATUS_FAIL			BIT(6)
+#define SAHARA_STATUS_INIT			BIT(7)
+#define SAHARA_STATUS_RNG_RESEED		BIT(8)
+#define SAHARA_STATUS_ACTIVE_RNG		BIT(9)
+#define SAHARA_STATUS_ACTIVE_MDHA		BIT(10)
+#define SAHARA_STATUS_ACTIVE_SKHA		BIT(11)
+#define SAHARA_STATUS_MODE_BATCH		BIT(16)
+#define SAHARA_STATUS_MODE_DEDICATED		BIT(17)
+#define SAHARA_STATUS_MODE_DEBUG		BIT(18)
+#define SAHARA_STATUS_GET_ISTATE(x)		(((x) >> 24) & 0xff)
+#define SAHARA_REG_ERRSTATUS			0x14
+#define SAHARA_ERRSTATUS_GET_SOURCE(x)		((x) & 0xf)
+#define SAHARA_ERRSOURCE_CHA			14
+#define SAHARA_ERRSOURCE_DMA			15
+#define SAHARA_ERRSTATUS_DMA_DIR		BIT(8)
+#define SAHARA_ERRSTATUS_GET_DMASZ(x)		(((x) >> 9) & 0x3)
+#define SAHARA_ERRSTATUS_GET_DMASRC(x)		(((x) >> 13) & 0x7)
+#define SAHARA_ERRSTATUS_GET_CHASRC(x)		(((x) >> 16) & 0xfff)
+#define SAHARA_ERRSTATUS_GET_CHAERR(x)		(((x) >> 28) & 0x3)
+#define SAHARA_REG_FADDR			0x18
+#define SAHARA_REG_CDAR				0x1C
+#define SAHARA_REG_IDAR				0x20
 
 struct sahara_hw_desc {
 	u32	hdr;
@@ -141,8 +137,6 @@ struct sahara_hw_link {
 };
 
 struct sahara_ctx {
-	unsigned long flags;
-
 	/* AES-specific context */
 	int keylen;
 	u8 key[AES_KEYSIZE_128];
@@ -151,6 +145,7 @@ struct sahara_ctx {
 
 struct sahara_aes_reqctx {
 	unsigned long mode;
+	u8 iv_out[AES_BLOCK_SIZE];
 	struct skcipher_request fallback_req;	// keep at the end
 };
 
@@ -170,7 +165,6 @@ struct sahara_aes_reqctx {
  * @total: total number of bytes for transfer
  * @last: is this the last block
  * @first: is this the first block
- * @active: inside a transfer
  */
 struct sahara_sha_reqctx {
 	u8			buf[SAHARA_MAX_SHA_BLOCK_SIZE];
@@ -186,7 +180,6 @@ struct sahara_sha_reqctx {
 	size_t			total;
 	unsigned int		last;
 	unsigned int		first;
-	unsigned int		active;
 };
 
 struct sahara_dev {
@@ -195,12 +188,9 @@ struct sahara_dev {
 	void __iomem		*regs_base;
 	struct clk		*clk_ipg;
 	struct clk		*clk_ahb;
-	spinlock_t		queue_spinlock;
-	struct task_struct	*kthread;
 	struct completion	dma_completion;
 
 	struct sahara_ctx	*ctx;
-	struct crypto_queue	queue;
 	unsigned long		flags;
 
 	struct sahara_hw_desc	*hw_desc[SAHARA_MAX_HW_DESC];
@@ -224,7 +214,7 @@ struct sahara_dev {
 	struct scatterlist	*out_sg;
 	int		nb_out_sg;
 
-	u32			error;
+	struct crypto_engine *engine;
 };
 
 static struct sahara_dev *dev_ptr;
@@ -446,27 +436,24 @@ static int sahara_hw_descriptor_create(struct sahara_dev *dev)
 	int ret;
 	int i, j;
 	int idx = 0;
+	u32 len;
 
-	/* Copy new key if necessary */
-	if (ctx->flags & FLAGS_NEW_KEY) {
-		memcpy(dev->key_base, ctx->key, ctx->keylen);
-		ctx->flags &= ~FLAGS_NEW_KEY;
+	memcpy(dev->key_base, ctx->key, ctx->keylen);
 
-		if (dev->flags & FLAGS_CBC) {
-			dev->hw_desc[idx]->len1 = AES_BLOCK_SIZE;
-			dev->hw_desc[idx]->p1 = dev->iv_phys_base;
-		} else {
-			dev->hw_desc[idx]->len1 = 0;
-			dev->hw_desc[idx]->p1 = 0;
-		}
-		dev->hw_desc[idx]->len2 = ctx->keylen;
-		dev->hw_desc[idx]->p2 = dev->key_phys_base;
-		dev->hw_desc[idx]->next = dev->hw_phys_desc[1];
+	if (dev->flags & FLAGS_CBC) {
+		dev->hw_desc[idx]->len1 = AES_BLOCK_SIZE;
+		dev->hw_desc[idx]->p1 = dev->iv_phys_base;
+	} else {
+		dev->hw_desc[idx]->len1 = 0;
+		dev->hw_desc[idx]->p1 = 0;
+	}
+	dev->hw_desc[idx]->len2 = ctx->keylen;
+	dev->hw_desc[idx]->p2 = dev->key_phys_base;
+	dev->hw_desc[idx]->next = dev->hw_phys_desc[1];
+	dev->hw_desc[idx]->hdr = sahara_aes_key_hdr(dev);
 
-		dev->hw_desc[idx]->hdr = sahara_aes_key_hdr(dev);
+	idx++;
 
-		idx++;
-	}
 
 	dev->nb_in_sg = sg_nents_for_len(dev->in_sg, dev->total);
 	if (dev->nb_in_sg < 0) {
@@ -488,24 +475,27 @@ static int sahara_hw_descriptor_create(struct sahara_dev *dev)
 			 DMA_TO_DEVICE);
 	if (!ret) {
 		dev_err(dev->device, "couldn't map in sg\n");
-		goto unmap_in;
+		return -EINVAL;
 	}
+
 	ret = dma_map_sg(dev->device, dev->out_sg, dev->nb_out_sg,
 			 DMA_FROM_DEVICE);
 	if (!ret) {
 		dev_err(dev->device, "couldn't map out sg\n");
-		goto unmap_out;
+		goto unmap_in;
 	}
 
 	/* Create input links */
 	dev->hw_desc[idx]->p1 = dev->hw_phys_link[0];
 	sg = dev->in_sg;
+	len = dev->total;
 	for (i = 0; i < dev->nb_in_sg; i++) {
-		dev->hw_link[i]->len = sg->length;
+		dev->hw_link[i]->len = min(len, sg->length);
 		dev->hw_link[i]->p = sg->dma_address;
 		if (i == (dev->nb_in_sg - 1)) {
 			dev->hw_link[i]->next = 0;
 		} else {
+			len -= min(len, sg->length);
 			dev->hw_link[i]->next = dev->hw_phys_link[i + 1];
 			sg = sg_next(sg);
 		}
@@ -514,12 +504,14 @@ static int sahara_hw_descriptor_create(struct sahara_dev *dev)
 	/* Create output links */
 	dev->hw_desc[idx]->p2 = dev->hw_phys_link[i];
 	sg = dev->out_sg;
+	len = dev->total;
 	for (j = i; j < dev->nb_out_sg + i; j++) {
-		dev->hw_link[j]->len = sg->length;
+		dev->hw_link[j]->len = min(len, sg->length);
 		dev->hw_link[j]->p = sg->dma_address;
 		if (j == (dev->nb_out_sg + i - 1)) {
 			dev->hw_link[j]->next = 0;
 		} else {
+			len -= min(len, sg->length);
 			dev->hw_link[j]->next = dev->hw_phys_link[j + 1];
 			sg = sg_next(sg);
 		}
@@ -538,9 +530,6 @@ static int sahara_hw_descriptor_create(struct sahara_dev *dev)
 
 	return 0;
 
-unmap_out:
-	dma_unmap_sg(dev->device, dev->out_sg, dev->nb_out_sg,
-		DMA_FROM_DEVICE);
 unmap_in:
 	dma_unmap_sg(dev->device, dev->in_sg, dev->nb_in_sg,
 		DMA_TO_DEVICE);
@@ -548,8 +537,24 @@ unmap_in:
 	return -EINVAL;
 }
 
+static void sahara_aes_cbc_update_iv(struct skcipher_request *req)
+{
+	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
+	struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req);
+	unsigned int ivsize = crypto_skcipher_ivsize(skcipher);
+
+	/* Update IV buffer to contain the last ciphertext block */
+	if (rctx->mode & FLAGS_ENCRYPT) {
+		sg_pcopy_to_buffer(req->dst, sg_nents(req->dst), req->iv,
+				   ivsize, req->cryptlen - ivsize);
+	} else {
+		memcpy(req->iv, rctx->iv_out, ivsize);
+	}
+}
+
 static int sahara_aes_process(struct skcipher_request *req)
 {
+	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
 	struct sahara_dev *dev = dev_ptr;
 	struct sahara_ctx *ctx;
 	struct sahara_aes_reqctx *rctx;
@@ -571,8 +576,17 @@ static int sahara_aes_process(struct skcipher_request *req)
 	rctx->mode &= FLAGS_MODE_MASK;
 	dev->flags = (dev->flags & ~FLAGS_MODE_MASK) | rctx->mode;
 
-	if ((dev->flags & FLAGS_CBC) && req->iv)
-		memcpy(dev->iv_base, req->iv, AES_KEYSIZE_128);
+	if ((dev->flags & FLAGS_CBC) && req->iv) {
+		unsigned int ivsize = crypto_skcipher_ivsize(skcipher);
+
+		memcpy(dev->iv_base, req->iv, ivsize);
+
+		if (!(dev->flags & FLAGS_ENCRYPT)) {
+			sg_pcopy_to_buffer(req->src, sg_nents(req->src),
+					   rctx->iv_out, ivsize,
+					   req->cryptlen - ivsize);
+		}
+	}
 
 	/* assign new context to device */
 	dev->ctx = ctx;
@@ -585,16 +599,20 @@ static int sahara_aes_process(struct skcipher_request *req)
 
 	timeout = wait_for_completion_timeout(&dev->dma_completion,
 				msecs_to_jiffies(SAHARA_TIMEOUT_MS));
-	if (!timeout) {
-		dev_err(dev->device, "AES timeout\n");
-		return -ETIMEDOUT;
-	}
 
 	dma_unmap_sg(dev->device, dev->out_sg, dev->nb_out_sg,
 		DMA_FROM_DEVICE);
 	dma_unmap_sg(dev->device, dev->in_sg, dev->nb_in_sg,
 		DMA_TO_DEVICE);
 
+	if (!timeout) {
+		dev_err(dev->device, "AES timeout\n");
+		return -ETIMEDOUT;
+	}
+
+	if ((dev->flags & FLAGS_CBC) && req->iv)
+		sahara_aes_cbc_update_iv(req);
+
 	return 0;
 }
 
@@ -608,7 +626,6 @@ static int sahara_aes_setkey(struct crypto_skcipher *tfm, const u8 *key,
 	/* SAHARA only supports 128bit keys */
 	if (keylen == AES_KEYSIZE_128) {
 		memcpy(ctx->key, key, keylen);
-		ctx->flags |= FLAGS_NEW_KEY;
 		return 0;
 	}
 
@@ -624,109 +641,67 @@ static int sahara_aes_setkey(struct crypto_skcipher *tfm, const u8 *key,
 	return crypto_skcipher_setkey(ctx->fallback, key, keylen);
 }
 
+static int sahara_aes_fallback(struct skcipher_request *req, unsigned long mode)
+{
+	struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req);
+	struct sahara_ctx *ctx = crypto_skcipher_ctx(
+		crypto_skcipher_reqtfm(req));
+
+	skcipher_request_set_tfm(&rctx->fallback_req, ctx->fallback);
+	skcipher_request_set_callback(&rctx->fallback_req,
+				      req->base.flags,
+				      req->base.complete,
+				      req->base.data);
+	skcipher_request_set_crypt(&rctx->fallback_req, req->src,
+				   req->dst, req->cryptlen, req->iv);
+
+	if (mode & FLAGS_ENCRYPT)
+		return crypto_skcipher_encrypt(&rctx->fallback_req);
+
+	return crypto_skcipher_decrypt(&rctx->fallback_req);
+}
+
 static int sahara_aes_crypt(struct skcipher_request *req, unsigned long mode)
 {
 	struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req);
+	struct sahara_ctx *ctx = crypto_skcipher_ctx(
+		crypto_skcipher_reqtfm(req));
 	struct sahara_dev *dev = dev_ptr;
-	int err = 0;
+
+	if (!req->cryptlen)
+		return 0;
+
+	if (unlikely(ctx->keylen != AES_KEYSIZE_128))
+		return sahara_aes_fallback(req, mode);
 
 	dev_dbg(dev->device, "nbytes: %d, enc: %d, cbc: %d\n",
 		req->cryptlen, !!(mode & FLAGS_ENCRYPT), !!(mode & FLAGS_CBC));
 
-	if (!IS_ALIGNED(req->cryptlen, AES_BLOCK_SIZE)) {
-		dev_err(dev->device,
-			"request size is not exact amount of AES blocks\n");
+	if (!IS_ALIGNED(req->cryptlen, AES_BLOCK_SIZE))
 		return -EINVAL;
-	}
 
 	rctx->mode = mode;
 
-	spin_lock_bh(&dev->queue_spinlock);
-	err = crypto_enqueue_request(&dev->queue, &req->base);
-	spin_unlock_bh(&dev->queue_spinlock);
-
-	wake_up_process(dev->kthread);
-
-	return err;
+	return crypto_transfer_skcipher_request_to_engine(dev->engine, req);
 }
 
 static int sahara_aes_ecb_encrypt(struct skcipher_request *req)
 {
-	struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req);
-	struct sahara_ctx *ctx = crypto_skcipher_ctx(
-		crypto_skcipher_reqtfm(req));
-
-	if (unlikely(ctx->keylen != AES_KEYSIZE_128)) {
-		skcipher_request_set_tfm(&rctx->fallback_req, ctx->fallback);
-		skcipher_request_set_callback(&rctx->fallback_req,
-					      req->base.flags,
-					      req->base.complete,
-					      req->base.data);
-		skcipher_request_set_crypt(&rctx->fallback_req, req->src,
-					   req->dst, req->cryptlen, req->iv);
-		return crypto_skcipher_encrypt(&rctx->fallback_req);
-	}
-
 	return sahara_aes_crypt(req, FLAGS_ENCRYPT);
 }
 
 static int sahara_aes_ecb_decrypt(struct skcipher_request *req)
 {
-	struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req);
-	struct sahara_ctx *ctx = crypto_skcipher_ctx(
-		crypto_skcipher_reqtfm(req));
-
-	if (unlikely(ctx->keylen != AES_KEYSIZE_128)) {
-		skcipher_request_set_tfm(&rctx->fallback_req, ctx->fallback);
-		skcipher_request_set_callback(&rctx->fallback_req,
-					      req->base.flags,
-					      req->base.complete,
-					      req->base.data);
-		skcipher_request_set_crypt(&rctx->fallback_req, req->src,
-					   req->dst, req->cryptlen, req->iv);
-		return crypto_skcipher_decrypt(&rctx->fallback_req);
-	}
-
 	return sahara_aes_crypt(req, 0);
 }
 
 static int sahara_aes_cbc_encrypt(struct skcipher_request *req)
 {
-	struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req);
-	struct sahara_ctx *ctx = crypto_skcipher_ctx(
-		crypto_skcipher_reqtfm(req));
-
-	if (unlikely(ctx->keylen != AES_KEYSIZE_128)) {
-		skcipher_request_set_tfm(&rctx->fallback_req, ctx->fallback);
-		skcipher_request_set_callback(&rctx->fallback_req,
-					      req->base.flags,
-					      req->base.complete,
-					      req->base.data);
-		skcipher_request_set_crypt(&rctx->fallback_req, req->src,
-					   req->dst, req->cryptlen, req->iv);
-		return crypto_skcipher_encrypt(&rctx->fallback_req);
-	}
-
 	return sahara_aes_crypt(req, FLAGS_ENCRYPT | FLAGS_CBC);
 }
 
 static int sahara_aes_cbc_decrypt(struct skcipher_request *req)
 {
-	struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req);
-	struct sahara_ctx *ctx = crypto_skcipher_ctx(
-		crypto_skcipher_reqtfm(req));
-
-	if (unlikely(ctx->keylen != AES_KEYSIZE_128)) {
-		skcipher_request_set_tfm(&rctx->fallback_req, ctx->fallback);
-		skcipher_request_set_callback(&rctx->fallback_req,
-					      req->base.flags,
-					      req->base.complete,
-					      req->base.data);
-		skcipher_request_set_crypt(&rctx->fallback_req, req->src,
-					   req->dst, req->cryptlen, req->iv);
-		return crypto_skcipher_decrypt(&rctx->fallback_req);
-	}
-
 	return sahara_aes_crypt(req, FLAGS_CBC);
 }
 
@@ -783,6 +758,7 @@ static int sahara_sha_hw_links_create(struct sahara_dev *dev,
 				       int start)
 {
 	struct scatterlist *sg;
+	unsigned int len;
 	unsigned int i;
 	int ret;
 
@@ -804,12 +780,14 @@ static int sahara_sha_hw_links_create(struct sahara_dev *dev,
 	if (!ret)
 		return -EFAULT;
 
+	len = rctx->total;
 	for (i = start; i < dev->nb_in_sg + start; i++) {
-		dev->hw_link[i]->len = sg->length;
+		dev->hw_link[i]->len = min(len, sg->length);
 		dev->hw_link[i]->p = sg->dma_address;
 		if (i == (dev->nb_in_sg + start - 1)) {
 			dev->hw_link[i]->next = 0;
 		} else {
+			len -= min(len, sg->length);
 			dev->hw_link[i]->next = dev->hw_phys_link[i + 1];
 			sg = sg_next(sg);
 		}
@@ -890,24 +868,6 @@ static int sahara_sha_hw_context_descriptor_create(struct sahara_dev *dev,
 	return 0;
 }
 
-static int sahara_walk_and_recalc(struct scatterlist *sg, unsigned int nbytes)
-{
-	if (!sg || !sg->length)
-		return nbytes;
-
-	while (nbytes && sg) {
-		if (nbytes <= sg->length) {
-			sg->length = nbytes;
-			sg_mark_end(sg);
-			break;
-		}
-		nbytes -= sg->length;
-		sg = sg_next(sg);
-	}
-
-	return nbytes;
-}
-
 static int sahara_sha_prepare_request(struct ahash_request *req)
 {
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
@@ -944,36 +904,20 @@ static int sahara_sha_prepare_request(struct ahash_request *req)
 					hash_later, 0);
 	}
 
-	/* nbytes should now be multiple of blocksize */
-	req->nbytes = req->nbytes - hash_later;
-
-	sahara_walk_and_recalc(req->src, req->nbytes);
-
+	rctx->total = len - hash_later;
 	/* have data from previous operation and current */
 	if (rctx->buf_cnt && req->nbytes) {
 		sg_init_table(rctx->in_sg_chain, 2);
 		sg_set_buf(rctx->in_sg_chain, rctx->rembuf, rctx->buf_cnt);
-
 		sg_chain(rctx->in_sg_chain, 2, req->src);
-
-		rctx->total = req->nbytes + rctx->buf_cnt;
 		rctx->in_sg = rctx->in_sg_chain;
-
-		req->src = rctx->in_sg_chain;
 	/* only data from previous operation */
 	} else if (rctx->buf_cnt) {
-		if (req->src)
-			rctx->in_sg = req->src;
-		else
-			rctx->in_sg = rctx->in_sg_chain;
-		/* buf was copied into rembuf above */
+		rctx->in_sg = rctx->in_sg_chain;
 		sg_init_one(rctx->in_sg, rctx->rembuf, rctx->buf_cnt);
-		rctx->total = rctx->buf_cnt;
 	/* no data from previous operation */
 	} else {
 		rctx->in_sg = req->src;
-		rctx->total = req->nbytes;
-		req->src = rctx->in_sg;
 	}
 
 	/* on next call, we only have the remaining data in the buffer */
@@ -994,7 +938,10 @@ static int sahara_sha_process(struct ahash_request *req)
 		return ret;
 
 	if (rctx->first) {
-		sahara_sha_hw_data_descriptor_create(dev, rctx, req, 0);
+		ret = sahara_sha_hw_data_descriptor_create(dev, rctx, req, 0);
+		if (ret)
+			return ret;
+
 		dev->hw_desc[0]->next = 0;
 		rctx->first = 0;
 	} else {
@@ -1002,7 +949,10 @@ static int sahara_sha_process(struct ahash_request *req)
 
 		sahara_sha_hw_context_descriptor_create(dev, rctx, req, 0);
 		dev->hw_desc[0]->next = dev->hw_phys_desc[1];
-		sahara_sha_hw_data_descriptor_create(dev, rctx, req, 1);
+		ret = sahara_sha_hw_data_descriptor_create(dev, rctx, req, 1);
+		if (ret)
+			return ret;
+
 		dev->hw_desc[1]->next = 0;
 	}
 
@@ -1015,62 +965,44 @@ static int sahara_sha_process(struct ahash_request *req)
 
 	timeout = wait_for_completion_timeout(&dev->dma_completion,
 				msecs_to_jiffies(SAHARA_TIMEOUT_MS));
-	if (!timeout) {
-		dev_err(dev->device, "SHA timeout\n");
-		return -ETIMEDOUT;
-	}
 
 	if (rctx->sg_in_idx)
 		dma_unmap_sg(dev->device, dev->in_sg, dev->nb_in_sg,
 			     DMA_TO_DEVICE);
 
+	if (!timeout) {
+		dev_err(dev->device, "SHA timeout\n");
+		return -ETIMEDOUT;
+	}
+
 	memcpy(rctx->context, dev->context_base, rctx->context_size);
 
-	if (req->result)
+	if (req->result && rctx->last)
 		memcpy(req->result, rctx->context, rctx->digest_size);
 
 	return 0;
 }
 
-static int sahara_queue_manage(void *data)
+static int sahara_do_one_request(struct crypto_engine *engine, void *areq)
 {
-	struct sahara_dev *dev = data;
-	struct crypto_async_request *async_req;
-	struct crypto_async_request *backlog;
-	int ret = 0;
-
-	do {
-		__set_current_state(TASK_INTERRUPTIBLE);
-
-		spin_lock_bh(&dev->queue_spinlock);
-		backlog = crypto_get_backlog(&dev->queue);
-		async_req = crypto_dequeue_request(&dev->queue);
-		spin_unlock_bh(&dev->queue_spinlock);
-
-		if (backlog)
-			crypto_request_complete(backlog, -EINPROGRESS);
-
-		if (async_req) {
-			if (crypto_tfm_alg_type(async_req->tfm) ==
-			    CRYPTO_ALG_TYPE_AHASH) {
-				struct ahash_request *req =
-					ahash_request_cast(async_req);
-
-				ret = sahara_sha_process(req);
-			} else {
-				struct skcipher_request *req =
-					skcipher_request_cast(async_req);
-
-				ret = sahara_aes_process(req);
-			}
+	struct crypto_async_request *async_req = areq;
+	int err;
 
-			crypto_request_complete(async_req, ret);
+	if (crypto_tfm_alg_type(async_req->tfm) == CRYPTO_ALG_TYPE_AHASH) {
+		struct ahash_request *req = ahash_request_cast(async_req);
 
-			continue;
-		}
+		err = sahara_sha_process(req);
+		local_bh_disable();
+		crypto_finalize_hash_request(engine, req, err);
+		local_bh_enable();
+	} else {
+		struct skcipher_request *req = skcipher_request_cast(async_req);
 
-		schedule();
-	} while (!kthread_should_stop());
+		err = sahara_aes_process(skcipher_request_cast(async_req));
+		local_bh_disable();
+		crypto_finalize_skcipher_request(engine, req, err);
+		local_bh_enable();
+	}
 
 	return 0;
 }
@@ -1079,25 +1011,13 @@ static int sahara_sha_enqueue(struct ahash_request *req, int last)
 {
 	struct sahara_sha_reqctx *rctx = ahash_request_ctx(req);
 	struct sahara_dev *dev = dev_ptr;
-	int ret;
 
 	if (!req->nbytes && !last)
 		return 0;
 
 	rctx->last = last;
 
-	if (!rctx->active) {
-		rctx->active = 1;
-		rctx->first = 1;
-	}
-
-	spin_lock_bh(&dev->queue_spinlock);
-	ret = crypto_enqueue_request(&dev->queue, &req->base);
-	spin_unlock_bh(&dev->queue_spinlock);
-
-	wake_up_process(dev->kthread);
-
-	return ret;
+	return crypto_transfer_hash_request_to_engine(dev->engine, req);
 }
 
 static int sahara_sha_init(struct ahash_request *req)
@@ -1121,7 +1041,7 @@ static int sahara_sha_init(struct ahash_request *req)
 	}
 
 	rctx->context_size = rctx->digest_size + 4;
-	rctx->active = 0;
+	rctx->first = 1;
 
 	return 0;
 }
@@ -1170,100 +1090,119 @@ static int sahara_sha_import(struct ahash_request *req, const void *in)
 static int sahara_sha_cra_init(struct crypto_tfm *tfm)
 {
 	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
-				 sizeof(struct sahara_sha_reqctx) +
-				 SHA_BUFFER_LEN + SHA256_BLOCK_SIZE);
+				 sizeof(struct sahara_sha_reqctx));
 
 	return 0;
 }
 
-static struct skcipher_alg aes_algs[] = {
+static struct skcipher_engine_alg aes_algs[] = {
 {
-	.base.cra_name		= "ecb(aes)",
-	.base.cra_driver_name	= "sahara-ecb-aes",
-	.base.cra_priority	= 300,
-	.base.cra_flags		= CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
-	.base.cra_blocksize	= AES_BLOCK_SIZE,
-	.base.cra_ctxsize	= sizeof(struct sahara_ctx),
-	.base.cra_alignmask	= 0x0,
-	.base.cra_module	= THIS_MODULE,
-
-	.init			= sahara_aes_init_tfm,
-	.exit			= sahara_aes_exit_tfm,
-	.min_keysize		= AES_MIN_KEY_SIZE ,
-	.max_keysize		= AES_MAX_KEY_SIZE,
-	.setkey			= sahara_aes_setkey,
-	.encrypt		= sahara_aes_ecb_encrypt,
-	.decrypt		= sahara_aes_ecb_decrypt,
+	.base = {
+		.base.cra_name		= "ecb(aes)",
+		.base.cra_driver_name	= "sahara-ecb-aes",
+		.base.cra_priority	= 300,
+		.base.cra_flags		= CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+		.base.cra_blocksize	= AES_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct sahara_ctx),
+		.base.cra_alignmask	= 0x0,
+		.base.cra_module	= THIS_MODULE,
+
+		.init			= sahara_aes_init_tfm,
+		.exit			= sahara_aes_exit_tfm,
+		.min_keysize		= AES_MIN_KEY_SIZE,
+		.max_keysize		= AES_MAX_KEY_SIZE,
+		.setkey			= sahara_aes_setkey,
+		.encrypt		= sahara_aes_ecb_encrypt,
+		.decrypt		= sahara_aes_ecb_decrypt,
+	},
+	.op = {
+		.do_one_request = sahara_do_one_request,
+	},
 }, {
-	.base.cra_name		= "cbc(aes)",
-	.base.cra_driver_name	= "sahara-cbc-aes",
-	.base.cra_priority	= 300,
-	.base.cra_flags		= CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
-	.base.cra_blocksize	= AES_BLOCK_SIZE,
-	.base.cra_ctxsize	= sizeof(struct sahara_ctx),
-	.base.cra_alignmask	= 0x0,
-	.base.cra_module	= THIS_MODULE,
-
-	.init			= sahara_aes_init_tfm,
-	.exit			= sahara_aes_exit_tfm,
-	.min_keysize		= AES_MIN_KEY_SIZE ,
-	.max_keysize		= AES_MAX_KEY_SIZE,
-	.ivsize			= AES_BLOCK_SIZE,
-	.setkey			= sahara_aes_setkey,
-	.encrypt		= sahara_aes_cbc_encrypt,
-	.decrypt		= sahara_aes_cbc_decrypt,
+	.base = {
+		.base.cra_name		= "cbc(aes)",
+		.base.cra_driver_name	= "sahara-cbc-aes",
+		.base.cra_priority	= 300,
+		.base.cra_flags		= CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+		.base.cra_blocksize	= AES_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct sahara_ctx),
+		.base.cra_alignmask	= 0x0,
+		.base.cra_module	= THIS_MODULE,
+
+		.init			= sahara_aes_init_tfm,
+		.exit			= sahara_aes_exit_tfm,
+		.min_keysize		= AES_MIN_KEY_SIZE,
+		.max_keysize		= AES_MAX_KEY_SIZE,
+		.ivsize			= AES_BLOCK_SIZE,
+		.setkey			= sahara_aes_setkey,
+		.encrypt		= sahara_aes_cbc_encrypt,
+		.decrypt		= sahara_aes_cbc_decrypt,
+	},
+	.op = {
+		.do_one_request = sahara_do_one_request,
+	},
 }
 };
 
-static struct ahash_alg sha_v3_algs[] = {
+static struct ahash_engine_alg sha_v3_algs[] = {
 {
-	.init		= sahara_sha_init,
-	.update		= sahara_sha_update,
-	.final		= sahara_sha_final,
-	.finup		= sahara_sha_finup,
-	.digest		= sahara_sha_digest,
-	.export		= sahara_sha_export,
-	.import		= sahara_sha_import,
-	.halg.digestsize	= SHA1_DIGEST_SIZE,
-	.halg.statesize         = sizeof(struct sahara_sha_reqctx),
-	.halg.base	= {
-		.cra_name		= "sha1",
-		.cra_driver_name	= "sahara-sha1",
-		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_ASYNC |
-						CRYPTO_ALG_NEED_FALLBACK,
-		.cra_blocksize		= SHA1_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct sahara_ctx),
-		.cra_alignmask		= 0,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= sahara_sha_cra_init,
-	}
+	.base = {
+		.init		= sahara_sha_init,
+		.update		= sahara_sha_update,
+		.final		= sahara_sha_final,
+		.finup		= sahara_sha_finup,
+		.digest		= sahara_sha_digest,
+		.export		= sahara_sha_export,
+		.import		= sahara_sha_import,
+		.halg.digestsize	= SHA1_DIGEST_SIZE,
+		.halg.statesize         = sizeof(struct sahara_sha_reqctx),
+		.halg.base	= {
+			.cra_name		= "sha1",
+			.cra_driver_name	= "sahara-sha1",
+			.cra_priority		= 300,
+			.cra_flags		= CRYPTO_ALG_ASYNC |
+							CRYPTO_ALG_NEED_FALLBACK,
+			.cra_blocksize		= SHA1_BLOCK_SIZE,
+			.cra_ctxsize		= sizeof(struct sahara_ctx),
+			.cra_alignmask		= 0,
+			.cra_module		= THIS_MODULE,
+			.cra_init		= sahara_sha_cra_init,
+		}
+	},
+	.op = {
+		.do_one_request = sahara_do_one_request,
+	},
 },
 };
 
-static struct ahash_alg sha_v4_algs[] = {
+static struct ahash_engine_alg sha_v4_algs[] = {
 {
-	.init		= sahara_sha_init,
-	.update		= sahara_sha_update,
-	.final		= sahara_sha_final,
-	.finup		= sahara_sha_finup,
-	.digest		= sahara_sha_digest,
-	.export		= sahara_sha_export,
-	.import		= sahara_sha_import,
-	.halg.digestsize	= SHA256_DIGEST_SIZE,
-	.halg.statesize         = sizeof(struct sahara_sha_reqctx),
-	.halg.base	= {
-		.cra_name		= "sha256",
-		.cra_driver_name	= "sahara-sha256",
-		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_ASYNC |
-						CRYPTO_ALG_NEED_FALLBACK,
-		.cra_blocksize		= SHA256_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct sahara_ctx),
-		.cra_alignmask		= 0,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= sahara_sha_cra_init,
-	}
+	.base = {
+		.init		= sahara_sha_init,
+		.update		= sahara_sha_update,
+		.final		= sahara_sha_final,
+		.finup		= sahara_sha_finup,
+		.digest		= sahara_sha_digest,
+		.export		= sahara_sha_export,
+		.import		= sahara_sha_import,
+		.halg.digestsize	= SHA256_DIGEST_SIZE,
+		.halg.statesize         = sizeof(struct sahara_sha_reqctx),
+		.halg.base	= {
+			.cra_name		= "sha256",
+			.cra_driver_name	= "sahara-sha256",
+			.cra_priority		= 300,
+			.cra_flags		= CRYPTO_ALG_ASYNC |
+							CRYPTO_ALG_NEED_FALLBACK,
+			.cra_blocksize		= SHA256_BLOCK_SIZE,
+			.cra_ctxsize		= sizeof(struct sahara_ctx),
+			.cra_alignmask		= 0,
+			.cra_module		= THIS_MODULE,
+			.cra_init		= sahara_sha_cra_init,
+		}
+	},
+	.op = {
+		.do_one_request = sahara_do_one_request,
+	},
 },
 };
 
@@ -1278,14 +1217,11 @@ static irqreturn_t sahara_irq_handler(int irq, void *data)
 
 	sahara_decode_status(dev, stat);
 
-	if (SAHARA_STATUS_GET_STATE(stat) == SAHARA_STATE_BUSY) {
+	if (SAHARA_STATUS_GET_STATE(stat) == SAHARA_STATE_BUSY)
 		return IRQ_NONE;
-	} else if (SAHARA_STATUS_GET_STATE(stat) == SAHARA_STATE_COMPLETE) {
-		dev->error = 0;
-	} else {
+
+	if (SAHARA_STATUS_GET_STATE(stat) != SAHARA_STATE_COMPLETE)
 		sahara_decode_error(dev, err);
-		dev->error = -EINVAL;
-	}
 
 	complete(&dev->dma_completion);
 
@@ -1296,57 +1232,42 @@ static irqreturn_t sahara_irq_handler(int irq, void *data)
 static int sahara_register_algs(struct sahara_dev *dev)
 {
 	int err;
-	unsigned int i, j, k, l;
 
-	for (i = 0; i < ARRAY_SIZE(aes_algs); i++) {
-		err = crypto_register_skcipher(&aes_algs[i]);
-		if (err)
-			goto err_aes_algs;
-	}
+	err = crypto_engine_register_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
+	if (err)
+		return err;
+
+	err = crypto_engine_register_ahashes(sha_v3_algs,
+					     ARRAY_SIZE(sha_v3_algs));
+	if (err)
+		goto err_aes_algs;
 
-	for (k = 0; k < ARRAY_SIZE(sha_v3_algs); k++) {
-		err = crypto_register_ahash(&sha_v3_algs[k]);
+	if (dev->version > SAHARA_VERSION_3) {
+		err = crypto_engine_register_ahashes(sha_v4_algs,
+						     ARRAY_SIZE(sha_v4_algs));
 		if (err)
 			goto err_sha_v3_algs;
 	}
 
-	if (dev->version > SAHARA_VERSION_3)
-		for (l = 0; l < ARRAY_SIZE(sha_v4_algs); l++) {
-			err = crypto_register_ahash(&sha_v4_algs[l]);
-			if (err)
-				goto err_sha_v4_algs;
-		}
-
 	return 0;
 
-err_sha_v4_algs:
-	for (j = 0; j < l; j++)
-		crypto_unregister_ahash(&sha_v4_algs[j]);
-
 err_sha_v3_algs:
-	for (j = 0; j < k; j++)
-		crypto_unregister_ahash(&sha_v3_algs[j]);
+	crypto_engine_unregister_ahashes(sha_v3_algs, ARRAY_SIZE(sha_v3_algs));
 
 err_aes_algs:
-	for (j = 0; j < i; j++)
-		crypto_unregister_skcipher(&aes_algs[j]);
+	crypto_engine_unregister_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
 
 	return err;
 }
 
 static void sahara_unregister_algs(struct sahara_dev *dev)
 {
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(aes_algs); i++)
-		crypto_unregister_skcipher(&aes_algs[i]);
-
-	for (i = 0; i < ARRAY_SIZE(sha_v3_algs); i++)
-		crypto_unregister_ahash(&sha_v3_algs[i]);
+	crypto_engine_unregister_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
+	crypto_engine_unregister_ahashes(sha_v3_algs, ARRAY_SIZE(sha_v3_algs));
 
 	if (dev->version > SAHARA_VERSION_3)
-		for (i = 0; i < ARRAY_SIZE(sha_v4_algs); i++)
-			crypto_unregister_ahash(&sha_v4_algs[i]);
+		crypto_engine_unregister_ahashes(sha_v4_algs,
+						 ARRAY_SIZE(sha_v4_algs));
 }
 
 static const struct of_device_id sahara_dt_ids[] = {
@@ -1383,32 +1304,27 @@ static int sahara_probe(struct platform_device *pdev)
 
 	err = devm_request_irq(&pdev->dev, irq, sahara_irq_handler,
 			       0, dev_name(&pdev->dev), dev);
-	if (err) {
-		dev_err(&pdev->dev, "failed to request irq\n");
-		return err;
-	}
+	if (err)
+		return dev_err_probe(&pdev->dev, err,
+				     "failed to request irq\n");
 
 	/* clocks */
-	dev->clk_ipg = devm_clk_get(&pdev->dev, "ipg");
-	if (IS_ERR(dev->clk_ipg)) {
-		dev_err(&pdev->dev, "Could not get ipg clock\n");
-		return PTR_ERR(dev->clk_ipg);
-	}
+	dev->clk_ipg = devm_clk_get_enabled(&pdev->dev, "ipg");
+	if (IS_ERR(dev->clk_ipg))
+		return dev_err_probe(&pdev->dev, PTR_ERR(dev->clk_ipg),
+				     "Could not get ipg clock\n");
 
-	dev->clk_ahb = devm_clk_get(&pdev->dev, "ahb");
-	if (IS_ERR(dev->clk_ahb)) {
-		dev_err(&pdev->dev, "Could not get ahb clock\n");
-		return PTR_ERR(dev->clk_ahb);
-	}
+	dev->clk_ahb = devm_clk_get_enabled(&pdev->dev, "ahb");
+	if (IS_ERR(dev->clk_ahb))
+		return dev_err_probe(&pdev->dev, PTR_ERR(dev->clk_ahb),
+				     "Could not get ahb clock\n");
 
 	/* Allocate HW descriptors */
 	dev->hw_desc[0] = dmam_alloc_coherent(&pdev->dev,
 			SAHARA_MAX_HW_DESC * sizeof(struct sahara_hw_desc),
 			&dev->hw_phys_desc[0], GFP_KERNEL);
-	if (!dev->hw_desc[0]) {
-		dev_err(&pdev->dev, "Could not allocate hw descriptors\n");
+	if (!dev->hw_desc[0])
 		return -ENOMEM;
-	}
 	dev->hw_desc[1] = dev->hw_desc[0] + 1;
 	dev->hw_phys_desc[1] = dev->hw_phys_desc[0] +
 				sizeof(struct sahara_hw_desc);
@@ -1416,10 +1332,8 @@ static int sahara_probe(struct platform_device *pdev)
 	/* Allocate space for iv and key */
 	dev->key_base = dmam_alloc_coherent(&pdev->dev, 2 * AES_KEYSIZE_128,
 				&dev->key_phys_base, GFP_KERNEL);
-	if (!dev->key_base) {
-		dev_err(&pdev->dev, "Could not allocate memory for key\n");
+	if (!dev->key_base)
 		return -ENOMEM;
-	}
 	dev->iv_base = dev->key_base + AES_KEYSIZE_128;
 	dev->iv_phys_base = dev->key_phys_base + AES_KEYSIZE_128;
 
@@ -1427,45 +1341,36 @@ static int sahara_probe(struct platform_device *pdev)
 	dev->context_base = dmam_alloc_coherent(&pdev->dev,
 					SHA256_DIGEST_SIZE + 4,
 					&dev->context_phys_base, GFP_KERNEL);
-	if (!dev->context_base) {
-		dev_err(&pdev->dev, "Could not allocate memory for MDHA context\n");
+	if (!dev->context_base)
 		return -ENOMEM;
-	}
 
 	/* Allocate space for HW links */
 	dev->hw_link[0] = dmam_alloc_coherent(&pdev->dev,
 			SAHARA_MAX_HW_LINK * sizeof(struct sahara_hw_link),
 			&dev->hw_phys_link[0], GFP_KERNEL);
-	if (!dev->hw_link[0]) {
-		dev_err(&pdev->dev, "Could not allocate hw links\n");
+	if (!dev->hw_link[0])
 		return -ENOMEM;
-	}
 	for (i = 1; i < SAHARA_MAX_HW_LINK; i++) {
 		dev->hw_phys_link[i] = dev->hw_phys_link[i - 1] +
 					sizeof(struct sahara_hw_link);
 		dev->hw_link[i] = dev->hw_link[i - 1] + 1;
 	}
 
-	crypto_init_queue(&dev->queue, SAHARA_QUEUE_LENGTH);
-
-	spin_lock_init(&dev->queue_spinlock);
-
 	dev_ptr = dev;
 
-	dev->kthread = kthread_run(sahara_queue_manage, dev, "sahara_crypto");
-	if (IS_ERR(dev->kthread)) {
-		return PTR_ERR(dev->kthread);
+	dev->engine = crypto_engine_alloc_init(&pdev->dev, true);
+	if (!dev->engine)
+		return -ENOMEM;
+
+	err = crypto_engine_start(dev->engine);
+	if (err) {
+		crypto_engine_exit(dev->engine);
+		return dev_err_probe(&pdev->dev, err,
+				     "Could not start crypto engine\n");
 	}
 
 	init_completion(&dev->dma_completion);
 
-	err = clk_prepare_enable(dev->clk_ipg);
-	if (err)
-		return err;
-	err = clk_prepare_enable(dev->clk_ahb);
-	if (err)
-		goto clk_ipg_disable;
-
 	version = sahara_read(dev, SAHARA_REG_VERSION);
 	if (of_device_is_compatible(pdev->dev.of_node, "fsl,imx27-sahara")) {
 		if (version != SAHARA_VERSION_3)
@@ -1477,8 +1382,8 @@ static int sahara_probe(struct platform_device *pdev)
 		version = (version >> 8) & 0xff;
 	}
 	if (err == -ENODEV) {
-		dev_err(&pdev->dev, "SAHARA version %d not supported\n",
-				version);
+		dev_err_probe(&pdev->dev, err,
+			      "SAHARA version %d not supported\n", version);
 		goto err_algs;
 	}
 
@@ -1501,11 +1406,7 @@ static int sahara_probe(struct platform_device *pdev)
 	return 0;
 
 err_algs:
-	kthread_stop(dev->kthread);
-	dev_ptr = NULL;
-	clk_disable_unprepare(dev->clk_ahb);
-clk_ipg_disable:
-	clk_disable_unprepare(dev->clk_ipg);
+	crypto_engine_exit(dev->engine);
 
 	return err;
 }
@@ -1514,14 +1415,8 @@ static void sahara_remove(struct platform_device *pdev)
 {
 	struct sahara_dev *dev = platform_get_drvdata(pdev);
 
-	kthread_stop(dev->kthread);
-
+	crypto_engine_exit(dev->engine);
 	sahara_unregister_algs(dev);
-
-	clk_disable_unprepare(dev->clk_ipg);
-	clk_disable_unprepare(dev->clk_ahb);
-
-	dev_ptr = NULL;
 }
 
 static struct platform_driver sahara_driver = {
diff --git a/drivers/crypto/starfive/Kconfig b/drivers/crypto/starfive/Kconfig
index 2cb192502c1b..cb59357b58b2 100644
--- a/drivers/crypto/starfive/Kconfig
+++ b/drivers/crypto/starfive/Kconfig
@@ -4,7 +4,7 @@
 
 config CRYPTO_DEV_JH7110
 	tristate "StarFive JH7110 cryptographic engine driver"
-	depends on SOC_STARFIVE || AMBA_PL08X || COMPILE_TEST
+	depends on (SOC_STARFIVE && AMBA_PL08X) || COMPILE_TEST
 	depends on HAS_DMA
 	select CRYPTO_ENGINE
 	select CRYPTO_HMAC
diff --git a/drivers/crypto/starfive/jh7110-aes.c b/drivers/crypto/starfive/jh7110-aes.c
index 9378e6682f0e..1ac15cc4ef3c 100644
--- a/drivers/crypto/starfive/jh7110-aes.c
+++ b/drivers/crypto/starfive/jh7110-aes.c
@@ -262,12 +262,7 @@ static int starfive_aes_hw_init(struct starfive_cryp_ctx *ctx)
 	rctx->csr.aes.mode  = hw_mode;
 	rctx->csr.aes.cmode = !is_encrypt(cryp);
 	rctx->csr.aes.ie = 1;
-
-	if (hw_mode == STARFIVE_AES_MODE_CFB ||
-	    hw_mode == STARFIVE_AES_MODE_OFB)
-		rctx->csr.aes.stmode = STARFIVE_AES_MODE_XFB_128;
-	else
-		rctx->csr.aes.stmode = STARFIVE_AES_MODE_XFB_1;
+	rctx->csr.aes.stmode = STARFIVE_AES_MODE_XFB_1;
 
 	if (cryp->side_chan) {
 		rctx->csr.aes.delay_aes = 1;
@@ -294,8 +289,6 @@ static int starfive_aes_hw_init(struct starfive_cryp_ctx *ctx)
 		starfive_aes_ccm_init(ctx);
 		starfive_aes_aead_hw_start(ctx, hw_mode);
 		break;
-	case STARFIVE_AES_MODE_OFB:
-	case STARFIVE_AES_MODE_CFB:
 	case STARFIVE_AES_MODE_CBC:
 	case STARFIVE_AES_MODE_CTR:
 		starfive_aes_write_iv(ctx, (void *)cryp->req.sreq->iv);
@@ -500,7 +493,7 @@ static int starfive_aes_prepare_req(struct skcipher_request *req,
 	scatterwalk_start(&cryp->out_walk, rctx->out_sg);
 
 	if (cryp->assoclen) {
-		rctx->adata = kzalloc(ALIGN(cryp->assoclen, AES_BLOCK_SIZE), GFP_KERNEL);
+		rctx->adata = kzalloc(cryp->assoclen + AES_BLOCK_SIZE, GFP_KERNEL);
 		if (!rctx->adata)
 			return dev_err_probe(cryp->dev, -ENOMEM,
 					     "Failed to alloc memory for adata");
@@ -569,7 +562,7 @@ static int starfive_aes_aead_do_one_req(struct crypto_engine *engine, void *areq
 	struct starfive_cryp_ctx *ctx =
 		crypto_aead_ctx(crypto_aead_reqtfm(req));
 	struct starfive_cryp_dev *cryp = ctx->cryp;
-	struct starfive_cryp_request_ctx *rctx = ctx->rctx;
+	struct starfive_cryp_request_ctx *rctx;
 	u32 block[AES_BLOCK_32];
 	u32 stat;
 	int err;
@@ -579,6 +572,8 @@ static int starfive_aes_aead_do_one_req(struct crypto_engine *engine, void *areq
 	if (err)
 		return err;
 
+	rctx = ctx->rctx;
+
 	if (!cryp->assoclen)
 		goto write_text;
 
@@ -783,26 +778,6 @@ static int starfive_aes_cbc_decrypt(struct skcipher_request *req)
 	return starfive_aes_crypt(req, STARFIVE_AES_MODE_CBC);
 }
 
-static int starfive_aes_cfb_encrypt(struct skcipher_request *req)
-{
-	return starfive_aes_crypt(req, STARFIVE_AES_MODE_CFB | FLG_ENCRYPT);
-}
-
-static int starfive_aes_cfb_decrypt(struct skcipher_request *req)
-{
-	return starfive_aes_crypt(req, STARFIVE_AES_MODE_CFB);
-}
-
-static int starfive_aes_ofb_encrypt(struct skcipher_request *req)
-{
-	return starfive_aes_crypt(req, STARFIVE_AES_MODE_OFB | FLG_ENCRYPT);
-}
-
-static int starfive_aes_ofb_decrypt(struct skcipher_request *req)
-{
-	return starfive_aes_crypt(req, STARFIVE_AES_MODE_OFB);
-}
-
 static int starfive_aes_ctr_encrypt(struct skcipher_request *req)
 {
 	return starfive_aes_crypt(req, STARFIVE_AES_MODE_CTR | FLG_ENCRYPT);
@@ -908,48 +883,6 @@ static struct skcipher_engine_alg skcipher_algs[] = {
 	.op = {
 		.do_one_request = starfive_aes_do_one_req,
 	},
-}, {
-	.base.init			= starfive_aes_init_tfm,
-	.base.setkey			= starfive_aes_setkey,
-	.base.encrypt			= starfive_aes_cfb_encrypt,
-	.base.decrypt			= starfive_aes_cfb_decrypt,
-	.base.min_keysize		= AES_MIN_KEY_SIZE,
-	.base.max_keysize		= AES_MAX_KEY_SIZE,
-	.base.ivsize			= AES_BLOCK_SIZE,
-	.base.base = {
-		.cra_name		= "cfb(aes)",
-		.cra_driver_name	= "starfive-cfb-aes",
-		.cra_priority		= 200,
-		.cra_flags		= CRYPTO_ALG_ASYNC,
-		.cra_blocksize		= 1,
-		.cra_ctxsize		= sizeof(struct starfive_cryp_ctx),
-		.cra_alignmask		= 0xf,
-		.cra_module		= THIS_MODULE,
-	},
-	.op = {
-		.do_one_request = starfive_aes_do_one_req,
-	},
-}, {
-	.base.init			= starfive_aes_init_tfm,
-	.base.setkey			= starfive_aes_setkey,
-	.base.encrypt			= starfive_aes_ofb_encrypt,
-	.base.decrypt			= starfive_aes_ofb_decrypt,
-	.base.min_keysize		= AES_MIN_KEY_SIZE,
-	.base.max_keysize		= AES_MAX_KEY_SIZE,
-	.base.ivsize			= AES_BLOCK_SIZE,
-	.base.base = {
-		.cra_name		= "ofb(aes)",
-		.cra_driver_name	= "starfive-ofb-aes",
-		.cra_priority		= 200,
-		.cra_flags		= CRYPTO_ALG_ASYNC,
-		.cra_blocksize		= 1,
-		.cra_ctxsize		= sizeof(struct starfive_cryp_ctx),
-		.cra_alignmask		= 0xf,
-		.cra_module		= THIS_MODULE,
-	},
-	.op = {
-		.do_one_request = starfive_aes_do_one_req,
-	},
 },
 };
 
diff --git a/drivers/crypto/starfive/jh7110-cryp.c b/drivers/crypto/starfive/jh7110-cryp.c
index 08e974e0dd12..425fddf3a8ab 100644
--- a/drivers/crypto/starfive/jh7110-cryp.c
+++ b/drivers/crypto/starfive/jh7110-cryp.c
@@ -109,12 +109,6 @@ static irqreturn_t starfive_cryp_irq(int irq, void *priv)
 		tasklet_schedule(&cryp->hash_done);
 	}
 
-	if (status & STARFIVE_IE_FLAG_PKA_DONE) {
-		mask |= STARFIVE_IE_MASK_PKA_DONE;
-		writel(mask, cryp->base + STARFIVE_IE_MASK_OFFSET);
-		complete(&cryp->pka_done);
-	}
-
 	return IRQ_HANDLED;
 }
 
@@ -159,8 +153,6 @@ static int starfive_cryp_probe(struct platform_device *pdev)
 		return dev_err_probe(&pdev->dev, PTR_ERR(cryp->rst),
 				     "Error getting hardware reset line\n");
 
-	init_completion(&cryp->pka_done);
-
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
 		return irq;
@@ -168,7 +160,7 @@ static int starfive_cryp_probe(struct platform_device *pdev)
 	ret = devm_request_irq(&pdev->dev, irq, starfive_cryp_irq, 0, pdev->name,
 			       (void *)cryp);
 	if (ret)
-		return dev_err_probe(&pdev->dev, irq,
+		return dev_err_probe(&pdev->dev, ret,
 				     "Failed to register interrupt handler\n");
 
 	clk_prepare_enable(cryp->hclk);
@@ -180,12 +172,8 @@ static int starfive_cryp_probe(struct platform_device *pdev)
 	spin_unlock(&dev_list.lock);
 
 	ret = starfive_dma_init(cryp);
-	if (ret) {
-		if (ret == -EPROBE_DEFER)
-			goto err_probe_defer;
-		else
-			goto err_dma_init;
-	}
+	if (ret)
+		goto err_dma_init;
 
 	/* Initialize crypto engine */
 	cryp->engine = crypto_engine_alloc_init(&pdev->dev, 1);
@@ -233,7 +221,7 @@ err_dma_init:
 
 	tasklet_kill(&cryp->aes_done);
 	tasklet_kill(&cryp->hash_done);
-err_probe_defer:
+
 	return ret;
 }
 
diff --git a/drivers/crypto/starfive/jh7110-cryp.h b/drivers/crypto/starfive/jh7110-cryp.h
index fe011d50473d..6cdf6db5d904 100644
--- a/drivers/crypto/starfive/jh7110-cryp.h
+++ b/drivers/crypto/starfive/jh7110-cryp.h
@@ -50,8 +50,6 @@ union starfive_aes_csr {
 		u32 ccm_start			:1;
 #define STARFIVE_AES_MODE_ECB			0x0
 #define STARFIVE_AES_MODE_CBC			0x1
-#define STARFIVE_AES_MODE_CFB			0x2
-#define STARFIVE_AES_MODE_OFB			0x3
 #define STARFIVE_AES_MODE_CTR			0x4
 #define STARFIVE_AES_MODE_CCM			0x5
 #define STARFIVE_AES_MODE_GCM			0x6
@@ -125,6 +123,15 @@ union starfive_pka_cacr {
 	};
 };
 
+union starfive_pka_casr {
+	u32 v;
+	struct {
+#define STARFIVE_PKA_DONE			BIT(0)
+		u32 done			:1;
+		u32 rsvd_0			:31;
+	};
+};
+
 struct starfive_rsa_key {
 	u8	*n;
 	u8	*e;
@@ -183,7 +190,6 @@ struct starfive_cryp_dev {
 	struct crypto_engine			*engine;
 	struct tasklet_struct			aes_done;
 	struct tasklet_struct			hash_done;
-	struct completion			pka_done;
 	size_t					assoclen;
 	size_t					total_in;
 	size_t					total_out;
diff --git a/drivers/crypto/starfive/jh7110-rsa.c b/drivers/crypto/starfive/jh7110-rsa.c
index f31bbd825f88..cf8bda7f0855 100644
--- a/drivers/crypto/starfive/jh7110-rsa.c
+++ b/drivers/crypto/starfive/jh7110-rsa.c
@@ -6,13 +6,7 @@
  */
 
 #include <linux/crypto.h>
-#include <linux/delay.h>
-#include <linux/device.h>
-#include <linux/dma-direct.h>
-#include <linux/interrupt.h>
 #include <linux/iopoll.h>
-#include <linux/io.h>
-#include <linux/mod_devicetable.h>
 #include <crypto/akcipher.h>
 #include <crypto/algapi.h>
 #include <crypto/internal/akcipher.h>
@@ -28,13 +22,13 @@
 #define STARFIVE_PKA_CAER_OFFSET	(STARFIVE_PKA_REGS_OFFSET + 0x108)
 #define STARFIVE_PKA_CANR_OFFSET	(STARFIVE_PKA_REGS_OFFSET + 0x208)
 
-// R^2 mod N and N0'
+/* R ^ 2 mod N and N0' */
 #define CRYPTO_CMD_PRE			0x0
-// A * R mod N   ==> A
+/* A * R mod N   ==> A */
 #define CRYPTO_CMD_ARN			0x5
-// A * E * R mod N ==> A
+/* A * E * R mod N ==> A */
 #define CRYPTO_CMD_AERN			0x6
-// A * A * R mod N ==> A
+/* A * A * R mod N ==> A */
 #define CRYPTO_CMD_AARN			0x7
 
 #define STARFIVE_RSA_MAX_KEYSZ		256
@@ -43,31 +37,17 @@
 static inline int starfive_pka_wait_done(struct starfive_cryp_ctx *ctx)
 {
 	struct starfive_cryp_dev *cryp = ctx->cryp;
+	u32 status;
 
-	return wait_for_completion_timeout(&cryp->pka_done,
-					   usecs_to_jiffies(100000));
-}
-
-static inline void starfive_pka_irq_mask_clear(struct starfive_cryp_ctx *ctx)
-{
-	struct starfive_cryp_dev *cryp = ctx->cryp;
-	u32 stat;
-
-	stat = readl(cryp->base + STARFIVE_IE_MASK_OFFSET);
-	stat &= ~STARFIVE_IE_MASK_PKA_DONE;
-	writel(stat, cryp->base + STARFIVE_IE_MASK_OFFSET);
-
-	reinit_completion(&cryp->pka_done);
+	return readl_relaxed_poll_timeout(cryp->base + STARFIVE_PKA_CASR_OFFSET, status,
+					  status & STARFIVE_PKA_DONE, 10, 100000);
 }
 
 static void starfive_rsa_free_key(struct starfive_rsa_key *key)
 {
-	if (key->d)
-		kfree_sensitive(key->d);
-	if (key->e)
-		kfree_sensitive(key->e);
-	if (key->n)
-		kfree_sensitive(key->n);
+	kfree_sensitive(key->d);
+	kfree_sensitive(key->e);
+	kfree_sensitive(key->n);
 	memset(key, 0, sizeof(*key));
 }
 
@@ -114,10 +94,9 @@ static int starfive_rsa_montgomery_form(struct starfive_cryp_ctx *ctx,
 		rctx->csr.pka.not_r2 = 1;
 		rctx->csr.pka.ie = 1;
 
-		starfive_pka_irq_mask_clear(ctx);
 		writel(rctx->csr.pka.v, cryp->base + STARFIVE_PKA_CACR_OFFSET);
 
-		if (!starfive_pka_wait_done(ctx))
+		if (starfive_pka_wait_done(ctx))
 			return -ETIMEDOUT;
 
 		for (loop = 0; loop <= opsize; loop++)
@@ -136,10 +115,9 @@ static int starfive_rsa_montgomery_form(struct starfive_cryp_ctx *ctx,
 		rctx->csr.pka.start = 1;
 		rctx->csr.pka.ie = 1;
 
-		starfive_pka_irq_mask_clear(ctx);
 		writel(rctx->csr.pka.v, cryp->base + STARFIVE_PKA_CACR_OFFSET);
 
-		if (!starfive_pka_wait_done(ctx))
+		if (starfive_pka_wait_done(ctx))
 			return -ETIMEDOUT;
 	} else {
 		rctx->csr.pka.v = 0;
@@ -151,10 +129,9 @@ static int starfive_rsa_montgomery_form(struct starfive_cryp_ctx *ctx,
 		rctx->csr.pka.pre_expf = 1;
 		rctx->csr.pka.ie = 1;
 
-		starfive_pka_irq_mask_clear(ctx);
 		writel(rctx->csr.pka.v, cryp->base + STARFIVE_PKA_CACR_OFFSET);
 
-		if (!starfive_pka_wait_done(ctx))
+		if (starfive_pka_wait_done(ctx))
 			return -ETIMEDOUT;
 
 		for (loop = 0; loop <= count; loop++)
@@ -172,10 +149,9 @@ static int starfive_rsa_montgomery_form(struct starfive_cryp_ctx *ctx,
 		rctx->csr.pka.start = 1;
 		rctx->csr.pka.ie = 1;
 
-		starfive_pka_irq_mask_clear(ctx);
 		writel(rctx->csr.pka.v, cryp->base + STARFIVE_PKA_CACR_OFFSET);
 
-		if (!starfive_pka_wait_done(ctx))
+		if (starfive_pka_wait_done(ctx))
 			return -ETIMEDOUT;
 	}
 
@@ -226,11 +202,10 @@ static int starfive_rsa_cpu_start(struct starfive_cryp_ctx *ctx, u32 *result,
 		rctx->csr.pka.start = 1;
 		rctx->csr.pka.ie = 1;
 
-		starfive_pka_irq_mask_clear(ctx);
 		writel(rctx->csr.pka.v, cryp->base + STARFIVE_PKA_CACR_OFFSET);
 
 		ret = -ETIMEDOUT;
-		if (!starfive_pka_wait_done(ctx))
+		if (starfive_pka_wait_done(ctx))
 			goto rsa_err;
 
 		if (mlen) {
@@ -242,10 +217,9 @@ static int starfive_rsa_cpu_start(struct starfive_cryp_ctx *ctx, u32 *result,
 			rctx->csr.pka.start = 1;
 			rctx->csr.pka.ie = 1;
 
-			starfive_pka_irq_mask_clear(ctx);
 			writel(rctx->csr.pka.v, cryp->base + STARFIVE_PKA_CACR_OFFSET);
 
-			if (!starfive_pka_wait_done(ctx))
+			if (starfive_pka_wait_done(ctx))
 				goto rsa_err;
 		}
 	}
diff --git a/drivers/crypto/stm32/stm32-crc32.c b/drivers/crypto/stm32/stm32-crc32.c
index b2d5c8921ab3..b0cf6d2fd352 100644
--- a/drivers/crypto/stm32/stm32-crc32.c
+++ b/drivers/crypto/stm32/stm32-crc32.c
@@ -104,7 +104,7 @@ static struct stm32_crc *stm32_crc_get_next_crc(void)
 	struct stm32_crc *crc;
 
 	spin_lock_bh(&crc_list.lock);
-	crc = list_first_entry(&crc_list.dev_list, struct stm32_crc, list);
+	crc = list_first_entry_or_null(&crc_list.dev_list, struct stm32_crc, list);
 	if (crc)
 		list_move_tail(&crc->list, &crc_list.dev_list);
 	spin_unlock_bh(&crc_list.lock);
diff --git a/drivers/crypto/stm32/stm32-cryp.c b/drivers/crypto/stm32/stm32-cryp.c
index c3cbc2673338..11ad4ffdce0d 100644
--- a/drivers/crypto/stm32/stm32-cryp.c
+++ b/drivers/crypto/stm32/stm32-cryp.c
@@ -838,7 +838,7 @@ static int stm32_cryp_aead_one_req(struct crypto_engine *engine, void *areq);
 
 static int stm32_cryp_aes_aead_init(struct crypto_aead *tfm)
 {
-	tfm->reqsize = sizeof(struct stm32_cryp_reqctx);
+	crypto_aead_set_reqsize(tfm, sizeof(struct stm32_cryp_reqctx));
 
 	return 0;
 }
diff --git a/drivers/crypto/virtio/virtio_crypto_common.h b/drivers/crypto/virtio/virtio_crypto_common.h
index 154590e1f764..7059bbe5a2eb 100644
--- a/drivers/crypto/virtio/virtio_crypto_common.h
+++ b/drivers/crypto/virtio/virtio_crypto_common.h
@@ -10,6 +10,7 @@
 #include <linux/virtio.h>
 #include <linux/crypto.h>
 #include <linux/spinlock.h>
+#include <linux/interrupt.h>
 #include <crypto/aead.h>
 #include <crypto/aes.h>
 #include <crypto/engine.h>
@@ -28,6 +29,7 @@ struct data_queue {
 	char name[32];
 
 	struct crypto_engine *engine;
+	struct tasklet_struct done_task;
 };
 
 struct virtio_crypto {
diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c
index 43a0838d31ff..b909c6a2bf1c 100644
--- a/drivers/crypto/virtio/virtio_crypto_core.c
+++ b/drivers/crypto/virtio/virtio_crypto_core.c
@@ -72,27 +72,28 @@ int virtio_crypto_ctrl_vq_request(struct virtio_crypto *vcrypto, struct scatterl
 	return 0;
 }
 
-static void virtcrypto_dataq_callback(struct virtqueue *vq)
+static void virtcrypto_done_task(unsigned long data)
 {
-	struct virtio_crypto *vcrypto = vq->vdev->priv;
+	struct data_queue *data_vq = (struct data_queue *)data;
+	struct virtqueue *vq = data_vq->vq;
 	struct virtio_crypto_request *vc_req;
-	unsigned long flags;
 	unsigned int len;
-	unsigned int qid = vq->index;
 
-	spin_lock_irqsave(&vcrypto->data_vq[qid].lock, flags);
 	do {
 		virtqueue_disable_cb(vq);
 		while ((vc_req = virtqueue_get_buf(vq, &len)) != NULL) {
-			spin_unlock_irqrestore(
-				&vcrypto->data_vq[qid].lock, flags);
 			if (vc_req->alg_cb)
 				vc_req->alg_cb(vc_req, len);
-			spin_lock_irqsave(
-				&vcrypto->data_vq[qid].lock, flags);
 		}
 	} while (!virtqueue_enable_cb(vq));
-	spin_unlock_irqrestore(&vcrypto->data_vq[qid].lock, flags);
+}
+
+static void virtcrypto_dataq_callback(struct virtqueue *vq)
+{
+	struct virtio_crypto *vcrypto = vq->vdev->priv;
+	struct data_queue *dq = &vcrypto->data_vq[vq->index];
+
+	tasklet_schedule(&dq->done_task);
 }
 
 static int virtcrypto_find_vqs(struct virtio_crypto *vi)
@@ -150,6 +151,8 @@ static int virtcrypto_find_vqs(struct virtio_crypto *vi)
 			ret = -ENOMEM;
 			goto err_engine;
 		}
+		tasklet_init(&vi->data_vq[i].done_task, virtcrypto_done_task,
+				(unsigned long)&vi->data_vq[i]);
 	}
 
 	kfree(names);
@@ -497,12 +500,15 @@ static void virtcrypto_free_unused_reqs(struct virtio_crypto *vcrypto)
 static void virtcrypto_remove(struct virtio_device *vdev)
 {
 	struct virtio_crypto *vcrypto = vdev->priv;
+	int i;
 
 	dev_info(&vdev->dev, "Start virtcrypto_remove.\n");
 
 	flush_work(&vcrypto->config_work);
 	if (virtcrypto_dev_started(vcrypto))
 		virtcrypto_dev_stop(vcrypto);
+	for (i = 0; i < vcrypto->max_data_queues; i++)
+		tasklet_kill(&vcrypto->data_vq[i].done_task);
 	virtio_reset_device(vdev);
 	virtcrypto_free_unused_reqs(vcrypto);
 	virtcrypto_clear_crypto_engines(vcrypto);
diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c
index 1cc9be85ba4c..7d97790b893d 100644
--- a/drivers/cxl/core/hdm.c
+++ b/drivers/cxl/core/hdm.c
@@ -363,10 +363,9 @@ resource_size_t cxl_dpa_resource_start(struct cxl_endpoint_decoder *cxled)
 {
 	resource_size_t base = -1;
 
-	down_read(&cxl_dpa_rwsem);
+	lockdep_assert_held(&cxl_dpa_rwsem);
 	if (cxled->dpa_res)
 		base = cxled->dpa_res->start;
-	up_read(&cxl_dpa_rwsem);
 
 	return base;
 }
@@ -839,6 +838,8 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
 			cxld->target_type = CXL_DECODER_HOSTONLYMEM;
 		else
 			cxld->target_type = CXL_DECODER_DEVMEM;
+
+		guard(rwsem_write)(&cxl_region_rwsem);
 		if (cxld->id != cxl_num_decoders_committed(port)) {
 			dev_warn(&port->dev,
 				 "decoder%d.%d: Committed out of order\n",
diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c
index fc5c2b414793..2f43d368ba07 100644
--- a/drivers/cxl/core/memdev.c
+++ b/drivers/cxl/core/memdev.c
@@ -227,10 +227,16 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd)
 	if (!port || !is_cxl_endpoint(port))
 		return -EINVAL;
 
-	rc = down_read_interruptible(&cxl_dpa_rwsem);
+	rc = down_read_interruptible(&cxl_region_rwsem);
 	if (rc)
 		return rc;
 
+	rc = down_read_interruptible(&cxl_dpa_rwsem);
+	if (rc) {
+		up_read(&cxl_region_rwsem);
+		return rc;
+	}
+
 	if (cxl_num_decoders_committed(port) == 0) {
 		/* No regions mapped to this memdev */
 		rc = cxl_get_poison_by_memdev(cxlmd);
@@ -239,6 +245,7 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd)
 		rc =  cxl_get_poison_by_endpoint(port);
 	}
 	up_read(&cxl_dpa_rwsem);
+	up_read(&cxl_region_rwsem);
 
 	return rc;
 }
@@ -324,10 +331,16 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa)
 	if (!IS_ENABLED(CONFIG_DEBUG_FS))
 		return 0;
 
-	rc = down_read_interruptible(&cxl_dpa_rwsem);
+	rc = down_read_interruptible(&cxl_region_rwsem);
 	if (rc)
 		return rc;
 
+	rc = down_read_interruptible(&cxl_dpa_rwsem);
+	if (rc) {
+		up_read(&cxl_region_rwsem);
+		return rc;
+	}
+
 	rc = cxl_validate_poison_dpa(cxlmd, dpa);
 	if (rc)
 		goto out;
@@ -355,6 +368,7 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa)
 	trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_INJECT);
 out:
 	up_read(&cxl_dpa_rwsem);
+	up_read(&cxl_region_rwsem);
 
 	return rc;
 }
@@ -372,10 +386,16 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa)
 	if (!IS_ENABLED(CONFIG_DEBUG_FS))
 		return 0;
 
-	rc = down_read_interruptible(&cxl_dpa_rwsem);
+	rc = down_read_interruptible(&cxl_region_rwsem);
 	if (rc)
 		return rc;
 
+	rc = down_read_interruptible(&cxl_dpa_rwsem);
+	if (rc) {
+		up_read(&cxl_region_rwsem);
+		return rc;
+	}
+
 	rc = cxl_validate_poison_dpa(cxlmd, dpa);
 	if (rc)
 		goto out;
@@ -412,6 +432,7 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa)
 	trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_CLEAR);
 out:
 	up_read(&cxl_dpa_rwsem);
+	up_read(&cxl_region_rwsem);
 
 	return rc;
 }
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index eff20e83d0a6..37e1652afbc7 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -620,7 +620,7 @@ void read_cdat_data(struct cxl_port *port)
 	struct pci_dev *pdev = NULL;
 	struct cxl_memdev *cxlmd;
 	size_t cdat_length;
-	void *cdat_table;
+	void *cdat_table, *cdat_buf;
 	int rc;
 
 	if (is_cxl_memdev(uport)) {
@@ -651,16 +651,15 @@ void read_cdat_data(struct cxl_port *port)
 		return;
 	}
 
-	cdat_table = devm_kzalloc(dev, cdat_length + sizeof(__le32),
-				  GFP_KERNEL);
-	if (!cdat_table)
+	cdat_buf = devm_kzalloc(dev, cdat_length + sizeof(__le32), GFP_KERNEL);
+	if (!cdat_buf)
 		return;
 
-	rc = cxl_cdat_read_table(dev, cdat_doe, cdat_table, &cdat_length);
+	rc = cxl_cdat_read_table(dev, cdat_doe, cdat_buf, &cdat_length);
 	if (rc)
 		goto err;
 
-	cdat_table = cdat_table + sizeof(__le32);
+	cdat_table = cdat_buf + sizeof(__le32);
 	if (cdat_checksum(cdat_table, cdat_length))
 		goto err;
 
@@ -670,7 +669,7 @@ void read_cdat_data(struct cxl_port *port)
 
 err:
 	/* Don't leave table data allocated on error */
-	devm_kfree(dev, cdat_table);
+	devm_kfree(dev, cdat_buf);
 	dev_err(dev, "Failed to read/validate CDAT.\n");
 }
 EXPORT_SYMBOL_NS_GPL(read_cdat_data, CXL);
diff --git a/drivers/cxl/core/pmu.c b/drivers/cxl/core/pmu.c
index 7684c843e5a5..5d8e06b0ba6e 100644
--- a/drivers/cxl/core/pmu.c
+++ b/drivers/cxl/core/pmu.c
@@ -23,7 +23,7 @@ const struct device_type cxl_pmu_type = {
 
 static void remove_dev(void *dev)
 {
-	device_del(dev);
+	device_unregister(dev);
 }
 
 int devm_cxl_pmu_add(struct device *parent, struct cxl_pmu_regs *regs,
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index 38441634e4c6..b7c93bb18f6e 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -226,9 +226,9 @@ static ssize_t dpa_resource_show(struct device *dev, struct device_attribute *at
 			    char *buf)
 {
 	struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev);
-	u64 base = cxl_dpa_resource_start(cxled);
 
-	return sysfs_emit(buf, "%#llx\n", base);
+	guard(rwsem_read)(&cxl_dpa_rwsem);
+	return sysfs_emit(buf, "%#llx\n", (u64)cxl_dpa_resource_start(cxled));
 }
 static DEVICE_ATTR_RO(dpa_resource);
 
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 56e575c79bb4..3e817a6f94c6 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -2467,10 +2467,6 @@ int cxl_get_poison_by_endpoint(struct cxl_port *port)
 	struct cxl_poison_context ctx;
 	int rc = 0;
 
-	rc = down_read_interruptible(&cxl_region_rwsem);
-	if (rc)
-		return rc;
-
 	ctx = (struct cxl_poison_context) {
 		.port = port
 	};
@@ -2480,7 +2476,6 @@ int cxl_get_poison_by_endpoint(struct cxl_port *port)
 		rc = cxl_get_poison_unmapped(to_cxl_memdev(port->uport_dev),
 					     &ctx);
 
-	up_read(&cxl_region_rwsem);
 	return rc;
 }
 
diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index 1659b787b65f..1ff1ab5fa105 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -367,6 +367,7 @@ static ssize_t create_store(struct device *dev, struct device_attribute *attr,
 			.dax_region = dax_region,
 			.size = 0,
 			.id = -1,
+			.memmap_on_memory = false,
 		};
 		struct dev_dax *dev_dax = devm_create_dev_dax(&data);
 
@@ -1400,6 +1401,8 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
 	dev_dax->align = dax_region->align;
 	ida_init(&dev_dax->ida);
 
+	dev_dax->memmap_on_memory = data->memmap_on_memory;
+
 	inode = dax_inode(dax_dev);
 	dev->devt = inode->i_rdev;
 	dev->bus = &dax_bus_type;
diff --git a/drivers/dax/bus.h b/drivers/dax/bus.h
index 1ccd23360124..cbbf64443098 100644
--- a/drivers/dax/bus.h
+++ b/drivers/dax/bus.h
@@ -23,6 +23,7 @@ struct dev_dax_data {
 	struct dev_pagemap *pgmap;
 	resource_size_t size;
 	int id;
+	bool memmap_on_memory;
 };
 
 struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data);
diff --git a/drivers/dax/cxl.c b/drivers/dax/cxl.c
index 8bc9d04034d6..c696837ab23c 100644
--- a/drivers/dax/cxl.c
+++ b/drivers/dax/cxl.c
@@ -26,6 +26,7 @@ static int cxl_dax_region_probe(struct device *dev)
 		.dax_region = dax_region,
 		.id = -1,
 		.size = range_len(&cxlr_dax->hpa_range),
+		.memmap_on_memory = true,
 	};
 
 	return PTR_ERR_OR_ZERO(devm_create_dev_dax(&data));
diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h
index 27cf2daaaa79..446617b73aea 100644
--- a/drivers/dax/dax-private.h
+++ b/drivers/dax/dax-private.h
@@ -70,6 +70,7 @@ struct dev_dax {
 	struct ida ida;
 	struct device dev;
 	struct dev_pagemap *pgmap;
+	bool memmap_on_memory;
 	int nr_range;
 	struct dev_dax_range {
 		unsigned long pgoff;
diff --git a/drivers/dax/hmem/hmem.c b/drivers/dax/hmem/hmem.c
index 5d2ddef0f8f5..b9da69f92697 100644
--- a/drivers/dax/hmem/hmem.c
+++ b/drivers/dax/hmem/hmem.c
@@ -36,6 +36,7 @@ static int dax_hmem_probe(struct platform_device *pdev)
 		.dax_region = dax_region,
 		.id = -1,
 		.size = region_idle ? 0 : range_len(&mri->range),
+		.memmap_on_memory = false,
 	};
 
 	return PTR_ERR_OR_ZERO(devm_create_dev_dax(&data));
diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index 369c698b7706..42ee360cf4e3 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -12,6 +12,7 @@
 #include <linux/mm.h>
 #include <linux/mman.h>
 #include <linux/memory-tiers.h>
+#include <linux/memory_hotplug.h>
 #include "dax-private.h"
 #include "bus.h"
 
@@ -93,6 +94,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 	struct dax_kmem_data *data;
 	struct memory_dev_type *mtype;
 	int i, rc, mapped = 0;
+	mhp_t mhp_flags;
 	int numa_node;
 	int adist = MEMTIER_DEFAULT_DAX_ADISTANCE;
 
@@ -179,12 +181,16 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 		 */
 		res->flags = IORESOURCE_SYSTEM_RAM;
 
+		mhp_flags = MHP_NID_IS_MGID;
+		if (dev_dax->memmap_on_memory)
+			mhp_flags |= MHP_MEMMAP_ON_MEMORY;
+
 		/*
 		 * Ensure that future kexec'd kernels will not treat
 		 * this as RAM automatically.
 		 */
 		rc = add_memory_driver_managed(data->mgid, range.start,
-				range_len(&range), kmem_name, MHP_NID_IS_MGID);
+				range_len(&range), kmem_name, mhp_flags);
 
 		if (rc) {
 			dev_warn(dev, "mapping%d: %#llx-%#llx memory add failed\n",
diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
index ae0cb113a5d3..f3c6c67b8412 100644
--- a/drivers/dax/pmem.c
+++ b/drivers/dax/pmem.c
@@ -63,6 +63,7 @@ static struct dev_dax *__dax_pmem_probe(struct device *dev)
 		.id = id,
 		.pgmap = &pgmap,
 		.size = range_len(&range),
+		.memmap_on_memory = false,
 	};
 
 	return devm_create_dev_dax(&data);
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 0da9232ea175..f4b635526345 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -326,7 +326,8 @@ void kill_dax(struct dax_device *dax_dev)
 		return;
 
 	if (dax_dev->holder_data != NULL)
-		dax_holder_notify_failure(dax_dev, 0, U64_MAX, 0);
+		dax_holder_notify_failure(dax_dev, 0, U64_MAX,
+				MF_MEM_PRE_REMOVE);
 
 	clear_bit(DAXDEV_ALIVE, &dax_dev->flags);
 	synchronize_srcu(&dax_srcu);
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index b3a68d5833bd..98657d3b9435 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -461,10 +461,14 @@ static void devfreq_monitor(struct work_struct *work)
 	if (err)
 		dev_err(&devfreq->dev, "dvfs failed with (%d) error\n", err);
 
+	if (devfreq->stop_polling)
+		goto out;
+
 	queue_delayed_work(devfreq_wq, &devfreq->work,
 				msecs_to_jiffies(devfreq->profile->polling_ms));
-	mutex_unlock(&devfreq->lock);
 
+out:
+	mutex_unlock(&devfreq->lock);
 	trace_devfreq_monitor(devfreq);
 }
 
@@ -483,6 +487,10 @@ void devfreq_monitor_start(struct devfreq *devfreq)
 	if (IS_SUPPORTED_FLAG(devfreq->governor->flags, IRQ_DRIVEN))
 		return;
 
+	mutex_lock(&devfreq->lock);
+	if (delayed_work_pending(&devfreq->work))
+		goto out;
+
 	switch (devfreq->profile->timer) {
 	case DEVFREQ_TIMER_DEFERRABLE:
 		INIT_DEFERRABLE_WORK(&devfreq->work, devfreq_monitor);
@@ -491,12 +499,16 @@ void devfreq_monitor_start(struct devfreq *devfreq)
 		INIT_DELAYED_WORK(&devfreq->work, devfreq_monitor);
 		break;
 	default:
-		return;
+		goto out;
 	}
 
 	if (devfreq->profile->polling_ms)
 		queue_delayed_work(devfreq_wq, &devfreq->work,
 			msecs_to_jiffies(devfreq->profile->polling_ms));
+
+out:
+	devfreq->stop_polling = false;
+	mutex_unlock(&devfreq->lock);
 }
 EXPORT_SYMBOL(devfreq_monitor_start);
 
@@ -513,6 +525,14 @@ void devfreq_monitor_stop(struct devfreq *devfreq)
 	if (IS_SUPPORTED_FLAG(devfreq->governor->flags, IRQ_DRIVEN))
 		return;
 
+	mutex_lock(&devfreq->lock);
+	if (devfreq->stop_polling) {
+		mutex_unlock(&devfreq->lock);
+		return;
+	}
+
+	devfreq->stop_polling = true;
+	mutex_unlock(&devfreq->lock);
 	cancel_delayed_work_sync(&devfreq->work);
 }
 EXPORT_SYMBOL(devfreq_monitor_stop);
@@ -1688,7 +1708,7 @@ static ssize_t trans_stat_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
 	struct devfreq *df = to_devfreq(dev);
-	ssize_t len;
+	ssize_t len = 0;
 	int i, j;
 	unsigned int max_state;
 
@@ -1697,7 +1717,7 @@ static ssize_t trans_stat_show(struct device *dev,
 	max_state = df->max_state;
 
 	if (max_state == 0)
-		return sprintf(buf, "Not Supported.\n");
+		return sysfs_emit(buf, "Not Supported.\n");
 
 	mutex_lock(&df->lock);
 	if (!df->stop_polling &&
@@ -1707,31 +1727,49 @@ static ssize_t trans_stat_show(struct device *dev,
 	}
 	mutex_unlock(&df->lock);
 
-	len = sprintf(buf, "     From  :   To\n");
-	len += sprintf(buf + len, "           :");
-	for (i = 0; i < max_state; i++)
-		len += sprintf(buf + len, "%10lu",
-				df->freq_table[i]);
+	len += sysfs_emit_at(buf, len, "     From  :   To\n");
+	len += sysfs_emit_at(buf, len, "           :");
+	for (i = 0; i < max_state; i++) {
+		if (len >= PAGE_SIZE - 1)
+			break;
+		len += sysfs_emit_at(buf, len, "%10lu",
+				     df->freq_table[i]);
+	}
 
-	len += sprintf(buf + len, "   time(ms)\n");
+	if (len >= PAGE_SIZE - 1)
+		return PAGE_SIZE - 1;
+	len += sysfs_emit_at(buf, len, "   time(ms)\n");
 
 	for (i = 0; i < max_state; i++) {
-		if (df->freq_table[i] == df->previous_freq)
-			len += sprintf(buf + len, "*");
+		if (len >= PAGE_SIZE - 1)
+			break;
+		if (df->freq_table[2] == df->previous_freq)
+			len += sysfs_emit_at(buf, len, "*");
 		else
-			len += sprintf(buf + len, " ");
-
-		len += sprintf(buf + len, "%10lu:", df->freq_table[i]);
-		for (j = 0; j < max_state; j++)
-			len += sprintf(buf + len, "%10u",
+			len += sysfs_emit_at(buf, len, " ");
+		if (len >= PAGE_SIZE - 1)
+			break;
+		len += sysfs_emit_at(buf, len, "%10lu:", df->freq_table[i]);
+		for (j = 0; j < max_state; j++) {
+			if (len >= PAGE_SIZE - 1)
+				break;
+			len += sysfs_emit_at(buf, len, "%10u",
 				df->stats.trans_table[(i * max_state) + j]);
+		}
+		if (len >= PAGE_SIZE - 1)
+			break;
+		len += sysfs_emit_at(buf, len, "%10llu\n", (u64)
+				     jiffies64_to_msecs(df->stats.time_in_state[i]));
+	}
 
-		len += sprintf(buf + len, "%10llu\n", (u64)
-			jiffies64_to_msecs(df->stats.time_in_state[i]));
+	if (len < PAGE_SIZE - 1)
+		len += sysfs_emit_at(buf, len, "Total transition : %u\n",
+				     df->stats.total_trans);
+	if (len >= PAGE_SIZE - 1) {
+		pr_warn_once("devfreq transition table exceeds PAGE_SIZE. Disabling\n");
+		return -EFBIG;
 	}
 
-	len += sprintf(buf + len, "Total transition : %u\n",
-					df->stats.total_trans);
 	return len;
 }
 
diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index 38b4110378de..eb8b733065b2 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -301,7 +301,7 @@ void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence,
 
 		dma_resv_list_entry(fobj, i, obj, &old, &old_usage);
 		if ((old->context == fence->context && old_usage >= usage &&
-		     dma_fence_is_later(fence, old)) ||
+		     dma_fence_is_later_or_same(fence, old)) ||
 		    dma_fence_is_signaled(old)) {
 			dma_resv_list_set(fobj, i, fence, usage);
 			dma_fence_put(old);
diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c
index 6a3abe5b1790..b53f46245c37 100644
--- a/drivers/dma/fsl-edma-common.c
+++ b/drivers/dma/fsl-edma-common.c
@@ -828,6 +828,7 @@ void fsl_edma_free_chan_resources(struct dma_chan *chan)
 	dma_pool_destroy(fsl_chan->tcd_pool);
 	fsl_chan->tcd_pool = NULL;
 	fsl_chan->is_sw = false;
+	fsl_chan->srcid = 0;
 }
 
 void fsl_edma_cleanup_vchan(struct dma_device *dmadev)
diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c
index 4635e16d7705..238a69bd0d6f 100644
--- a/drivers/dma/fsl-edma-main.c
+++ b/drivers/dma/fsl-edma-main.c
@@ -396,9 +396,8 @@ static int fsl_edma3_attach_pd(struct platform_device *pdev, struct fsl_edma_eng
 		link = device_link_add(dev, pd_chan, DL_FLAG_STATELESS |
 					     DL_FLAG_PM_RUNTIME |
 					     DL_FLAG_RPM_ACTIVE);
-		if (IS_ERR(link)) {
-			dev_err(dev, "Failed to add device_link to %d: %ld\n", i,
-				PTR_ERR(link));
+		if (!link) {
+			dev_err(dev, "Failed to add device_link to %d\n", i);
 			return -EINVAL;
 		}
 
@@ -631,6 +630,8 @@ static int fsl_edma_suspend_late(struct device *dev)
 
 	for (i = 0; i < fsl_edma->n_chans; i++) {
 		fsl_chan = &fsl_edma->chans[i];
+		if (fsl_edma->chan_masked & BIT(i))
+			continue;
 		spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
 		/* Make sure chan is idle or will force disable. */
 		if (unlikely(!fsl_chan->idle)) {
@@ -655,13 +656,16 @@ static int fsl_edma_resume_early(struct device *dev)
 
 	for (i = 0; i < fsl_edma->n_chans; i++) {
 		fsl_chan = &fsl_edma->chans[i];
+		if (fsl_edma->chan_masked & BIT(i))
+			continue;
 		fsl_chan->pm_state = RUNNING;
 		edma_write_tcdreg(fsl_chan, 0, csr);
 		if (fsl_chan->slave_id != 0)
 			fsl_edma_chan_mux(fsl_chan, fsl_chan->slave_id, true);
 	}
 
-	edma_writel(fsl_edma, EDMA_CR_ERGA | EDMA_CR_ERCA, regs->cr);
+	if (!(fsl_edma->drvdata->flags & FSL_EDMA_DRV_SPLIT_REG))
+		edma_writel(fsl_edma, EDMA_CR_ERGA | EDMA_CR_ERCA, regs->cr);
 
 	return 0;
 }
diff --git a/drivers/dma/idxd/Makefile b/drivers/dma/idxd/Makefile
index c5e679070e46..2b4a0d406e1e 100644
--- a/drivers/dma/idxd/Makefile
+++ b/drivers/dma/idxd/Makefile
@@ -4,7 +4,7 @@ obj-$(CONFIG_INTEL_IDXD_BUS) += idxd_bus.o
 idxd_bus-y := bus.o
 
 obj-$(CONFIG_INTEL_IDXD) += idxd.o
-idxd-y := init.o irq.o device.o sysfs.o submit.o dma.o cdev.o debugfs.o
+idxd-y := init.o irq.o device.o sysfs.o submit.o dma.o cdev.o debugfs.o defaults.o
 
 idxd-$(CONFIG_INTEL_IDXD_PERFMON) += perfmon.o
 
diff --git a/drivers/dma/idxd/bus.c b/drivers/dma/idxd/bus.c
index 6f84621053c6..0c9e689a2e77 100644
--- a/drivers/dma/idxd/bus.c
+++ b/drivers/dma/idxd/bus.c
@@ -67,11 +67,17 @@ static void idxd_config_bus_remove(struct device *dev)
 	idxd_drv->remove(idxd_dev);
 }
 
+static int idxd_bus_uevent(const struct device *dev, struct kobj_uevent_env *env)
+{
+	return add_uevent_var(env, "MODALIAS=" IDXD_DEVICES_MODALIAS_FMT, 0);
+}
+
 struct bus_type dsa_bus_type = {
 	.name = "dsa",
 	.match = idxd_config_bus_match,
 	.probe = idxd_config_bus_probe,
 	.remove = idxd_config_bus_remove,
+	.uevent = idxd_bus_uevent,
 };
 EXPORT_SYMBOL_GPL(dsa_bus_type);
 
diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index 0423655f5a88..1d918d45d9f6 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -550,7 +550,7 @@ static int idxd_user_drv_probe(struct idxd_dev *idxd_dev)
 	}
 
 	wq->type = IDXD_WQT_USER;
-	rc = drv_enable_wq(wq);
+	rc = idxd_drv_enable_wq(wq);
 	if (rc < 0)
 		goto err;
 
@@ -565,7 +565,7 @@ static int idxd_user_drv_probe(struct idxd_dev *idxd_dev)
 	return 0;
 
 err_cdev:
-	drv_disable_wq(wq);
+	idxd_drv_disable_wq(wq);
 err:
 	destroy_workqueue(wq->wq);
 	wq->type = IDXD_WQT_NONE;
@@ -580,7 +580,7 @@ static void idxd_user_drv_remove(struct idxd_dev *idxd_dev)
 
 	mutex_lock(&wq->wq_lock);
 	idxd_wq_del_cdev(wq);
-	drv_disable_wq(wq);
+	idxd_drv_disable_wq(wq);
 	wq->type = IDXD_WQT_NONE;
 	destroy_workqueue(wq->wq);
 	wq->wq = NULL;
diff --git a/drivers/dma/idxd/defaults.c b/drivers/dma/idxd/defaults.c
new file mode 100644
index 000000000000..c607ae8dd12c
--- /dev/null
+++ b/drivers/dma/idxd/defaults.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2023 Intel Corporation. All rights rsvd. */
+#include <linux/kernel.h>
+#include "idxd.h"
+
+int idxd_load_iaa_device_defaults(struct idxd_device *idxd)
+{
+	struct idxd_engine *engine;
+	struct idxd_group *group;
+	struct idxd_wq *wq;
+
+	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
+		return 0;
+
+	wq = idxd->wqs[0];
+
+	if (wq->state != IDXD_WQ_DISABLED)
+		return -EPERM;
+
+	/* set mode to "dedicated" */
+	set_bit(WQ_FLAG_DEDICATED, &wq->flags);
+	wq->threshold = 0;
+
+	/* only setting up 1 wq, so give it all the wq space */
+	wq->size = idxd->max_wq_size;
+
+	/* set priority to 10 */
+	wq->priority = 10;
+
+	/* set type to "kernel" */
+	wq->type = IDXD_WQT_KERNEL;
+
+	/* set wq group to 0 */
+	group = idxd->groups[0];
+	wq->group = group;
+	group->num_wqs++;
+
+	/* set name to "iaa_crypto" */
+	memset(wq->name, 0, WQ_NAME_SIZE + 1);
+	strscpy(wq->name, "iaa_crypto", WQ_NAME_SIZE + 1);
+
+	/* set driver_name to "crypto" */
+	memset(wq->driver_name, 0, DRIVER_NAME_SIZE + 1);
+	strscpy(wq->driver_name, "crypto", DRIVER_NAME_SIZE + 1);
+
+	engine = idxd->engines[0];
+
+	/* set engine group to 0 */
+	engine->group = idxd->groups[0];
+	engine->group->num_engines++;
+
+	return 0;
+}
diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index 8f754f922217..f43d81128b96 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -161,6 +161,7 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq)
 	free_hw_descs(wq);
 	return rc;
 }
+EXPORT_SYMBOL_NS_GPL(idxd_wq_alloc_resources, IDXD);
 
 void idxd_wq_free_resources(struct idxd_wq *wq)
 {
@@ -174,6 +175,7 @@ void idxd_wq_free_resources(struct idxd_wq *wq)
 	dma_free_coherent(dev, wq->compls_size, wq->compls, wq->compls_addr);
 	sbitmap_queue_free(&wq->sbq);
 }
+EXPORT_SYMBOL_NS_GPL(idxd_wq_free_resources, IDXD);
 
 int idxd_wq_enable(struct idxd_wq *wq)
 {
@@ -405,6 +407,7 @@ int idxd_wq_init_percpu_ref(struct idxd_wq *wq)
 	reinit_completion(&wq->wq_resurrect);
 	return 0;
 }
+EXPORT_SYMBOL_NS_GPL(idxd_wq_init_percpu_ref, IDXD);
 
 void __idxd_wq_quiesce(struct idxd_wq *wq)
 {
@@ -414,6 +417,7 @@ void __idxd_wq_quiesce(struct idxd_wq *wq)
 	complete_all(&wq->wq_resurrect);
 	wait_for_completion(&wq->wq_dead);
 }
+EXPORT_SYMBOL_NS_GPL(__idxd_wq_quiesce, IDXD);
 
 void idxd_wq_quiesce(struct idxd_wq *wq)
 {
@@ -421,6 +425,7 @@ void idxd_wq_quiesce(struct idxd_wq *wq)
 	__idxd_wq_quiesce(wq);
 	mutex_unlock(&wq->wq_lock);
 }
+EXPORT_SYMBOL_NS_GPL(idxd_wq_quiesce, IDXD);
 
 /* Device control bits */
 static inline bool idxd_is_enabled(struct idxd_device *idxd)
@@ -1266,7 +1271,7 @@ static void idxd_flush_pending_descs(struct idxd_irq_entry *ie)
 		tx = &desc->txd;
 		tx->callback = NULL;
 		tx->callback_result = NULL;
-		idxd_dma_complete_txd(desc, ctype, true);
+		idxd_dma_complete_txd(desc, ctype, true, NULL, NULL);
 	}
 }
 
@@ -1350,7 +1355,7 @@ err_irq:
 	return rc;
 }
 
-int drv_enable_wq(struct idxd_wq *wq)
+int idxd_drv_enable_wq(struct idxd_wq *wq)
 {
 	struct idxd_device *idxd = wq->idxd;
 	struct device *dev = &idxd->pdev->dev;
@@ -1482,8 +1487,9 @@ err_map_portal:
 err:
 	return rc;
 }
+EXPORT_SYMBOL_NS_GPL(idxd_drv_enable_wq, IDXD);
 
-void drv_disable_wq(struct idxd_wq *wq)
+void idxd_drv_disable_wq(struct idxd_wq *wq)
 {
 	struct idxd_device *idxd = wq->idxd;
 	struct device *dev = &idxd->pdev->dev;
@@ -1503,6 +1509,7 @@ void drv_disable_wq(struct idxd_wq *wq)
 	wq->type = IDXD_WQT_NONE;
 	wq->client_count = 0;
 }
+EXPORT_SYMBOL_NS_GPL(idxd_drv_disable_wq, IDXD);
 
 int idxd_device_drv_probe(struct idxd_dev *idxd_dev)
 {
diff --git a/drivers/dma/idxd/dma.c b/drivers/dma/idxd/dma.c
index 47a01893cfdb..cd835eabd31b 100644
--- a/drivers/dma/idxd/dma.c
+++ b/drivers/dma/idxd/dma.c
@@ -22,7 +22,7 @@ static inline struct idxd_wq *to_idxd_wq(struct dma_chan *c)
 
 void idxd_dma_complete_txd(struct idxd_desc *desc,
 			   enum idxd_complete_type comp_type,
-			   bool free_desc)
+			   bool free_desc, void *ctx, u32 *status)
 {
 	struct idxd_device *idxd = desc->wq->idxd;
 	struct dma_async_tx_descriptor *tx;
@@ -314,7 +314,7 @@ static int idxd_dmaengine_drv_probe(struct idxd_dev *idxd_dev)
 
 	wq->type = IDXD_WQT_KERNEL;
 
-	rc = drv_enable_wq(wq);
+	rc = idxd_drv_enable_wq(wq);
 	if (rc < 0) {
 		dev_dbg(dev, "Enable wq %d failed: %d\n", wq->id, rc);
 		rc = -ENXIO;
@@ -333,7 +333,7 @@ static int idxd_dmaengine_drv_probe(struct idxd_dev *idxd_dev)
 	return 0;
 
 err_dma:
-	drv_disable_wq(wq);
+	idxd_drv_disable_wq(wq);
 err:
 	wq->type = IDXD_WQT_NONE;
 	mutex_unlock(&wq->wq_lock);
@@ -347,7 +347,7 @@ static void idxd_dmaengine_drv_remove(struct idxd_dev *idxd_dev)
 	mutex_lock(&wq->wq_lock);
 	__idxd_wq_quiesce(wq);
 	idxd_unregister_dma_channel(wq);
-	drv_disable_wq(wq);
+	idxd_drv_disable_wq(wq);
 	mutex_unlock(&wq->wq_lock);
 }
 
@@ -359,6 +359,7 @@ static enum idxd_dev_type dev_types[] = {
 struct idxd_device_driver idxd_dmaengine_drv = {
 	.probe = idxd_dmaengine_drv_probe,
 	.remove = idxd_dmaengine_drv_remove,
+	.desc_complete = idxd_dma_complete_txd,
 	.name = "dmaengine",
 	.type = dev_types,
 };
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index 1e89c80a07fc..47de3f93ff1e 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -13,6 +13,7 @@
 #include <linux/bitmap.h>
 #include <linux/perf_event.h>
 #include <linux/iommu.h>
+#include <linux/crypto.h>
 #include <uapi/linux/idxd.h>
 #include "registers.h"
 
@@ -57,11 +58,23 @@ enum idxd_type {
 #define IDXD_ENQCMDS_RETRIES		32
 #define IDXD_ENQCMDS_MAX_RETRIES	64
 
+enum idxd_complete_type {
+	IDXD_COMPLETE_NORMAL = 0,
+	IDXD_COMPLETE_ABORT,
+	IDXD_COMPLETE_DEV_FAIL,
+};
+
+struct idxd_desc;
+
 struct idxd_device_driver {
 	const char *name;
 	enum idxd_dev_type *type;
 	int (*probe)(struct idxd_dev *idxd_dev);
 	void (*remove)(struct idxd_dev *idxd_dev);
+	void (*desc_complete)(struct idxd_desc *desc,
+			      enum idxd_complete_type comp_type,
+			      bool free_desc,
+			      void *ctx, u32 *status);
 	struct device_driver drv;
 };
 
@@ -174,12 +187,6 @@ enum idxd_op_type {
 	IDXD_OP_NONBLOCK = 1,
 };
 
-enum idxd_complete_type {
-	IDXD_COMPLETE_NORMAL = 0,
-	IDXD_COMPLETE_ABORT,
-	IDXD_COMPLETE_DEV_FAIL,
-};
-
 struct idxd_dma_chan {
 	struct dma_chan chan;
 	struct idxd_wq *wq;
@@ -270,6 +277,8 @@ struct idxd_dma_dev {
 	struct dma_device dma;
 };
 
+typedef int (*load_device_defaults_fn_t) (struct idxd_device *idxd);
+
 struct idxd_driver_data {
 	const char *name_prefix;
 	enum idxd_type type;
@@ -279,6 +288,7 @@ struct idxd_driver_data {
 	int evl_cr_off;
 	int cr_status_off;
 	int cr_result_off;
+	load_device_defaults_fn_t load_device_defaults;
 };
 
 struct idxd_evl {
@@ -378,6 +388,14 @@ static inline unsigned int evl_size(struct idxd_device *idxd)
 	return idxd->evl->size * evl_ent_size(idxd);
 }
 
+struct crypto_ctx {
+	struct acomp_req *req;
+	struct crypto_tfm *tfm;
+	dma_addr_t src_addr;
+	dma_addr_t dst_addr;
+	bool compress;
+};
+
 /* IDXD software descriptor */
 struct idxd_desc {
 	union {
@@ -390,7 +408,10 @@ struct idxd_desc {
 		struct iax_completion_record *iax_completion;
 	};
 	dma_addr_t compl_dma;
-	struct dma_async_tx_descriptor txd;
+	union {
+		struct dma_async_tx_descriptor txd;
+		struct crypto_ctx crypto;
+	};
 	struct llist_node llnode;
 	struct list_head list;
 	int id;
@@ -417,6 +438,15 @@ enum idxd_completion_status {
 #define idxd_dev_to_idxd(idxd_dev) container_of(idxd_dev, struct idxd_device, idxd_dev)
 #define idxd_dev_to_wq(idxd_dev) container_of(idxd_dev, struct idxd_wq, idxd_dev)
 
+static inline struct idxd_device_driver *wq_to_idxd_drv(struct idxd_wq *wq)
+{
+	struct device *dev = wq_confdev(wq);
+	struct idxd_device_driver *idxd_drv =
+		container_of(dev->driver, struct idxd_device_driver, drv);
+
+	return idxd_drv;
+}
+
 static inline struct idxd_device *confdev_to_idxd(struct device *dev)
 {
 	struct idxd_dev *idxd_dev = confdev_to_idxd_dev(dev);
@@ -618,6 +648,16 @@ static inline int idxd_wq_refcount(struct idxd_wq *wq)
 	return wq->client_count;
 };
 
+static inline void idxd_wq_set_private(struct idxd_wq *wq, void *private)
+{
+	dev_set_drvdata(wq_confdev(wq), private);
+}
+
+static inline void *idxd_wq_get_private(struct idxd_wq *wq)
+{
+	return dev_get_drvdata(wq_confdev(wq));
+}
+
 /*
  * Intel IAA does not support batch processing.
  * The max batch size of device, max batch size of wq and
@@ -655,6 +695,9 @@ static inline int idxd_wq_driver_name_match(struct idxd_wq *wq, struct device *d
 	return (strncmp(wq->driver_name, dev->driver->name, strlen(dev->driver->name)) == 0);
 }
 
+#define MODULE_ALIAS_IDXD_DEVICE(type) MODULE_ALIAS("idxd:t" __stringify(type) "*")
+#define IDXD_DEVICES_MODALIAS_FMT "idxd:t%d"
+
 int __must_check __idxd_driver_register(struct idxd_device_driver *idxd_drv,
 					struct module *module, const char *mod_name);
 #define idxd_driver_register(driver) \
@@ -665,6 +708,24 @@ void idxd_driver_unregister(struct idxd_device_driver *idxd_drv);
 #define module_idxd_driver(__idxd_driver) \
 	module_driver(__idxd_driver, idxd_driver_register, idxd_driver_unregister)
 
+void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc);
+void idxd_dma_complete_txd(struct idxd_desc *desc,
+			   enum idxd_complete_type comp_type,
+			   bool free_desc, void *ctx, u32 *status);
+
+static inline void idxd_desc_complete(struct idxd_desc *desc,
+				      enum idxd_complete_type comp_type,
+				      bool free_desc)
+{
+	struct idxd_device_driver *drv;
+	u32 status;
+
+	drv = wq_to_idxd_drv(desc->wq);
+	if (drv->desc_complete)
+		drv->desc_complete(desc, comp_type, free_desc,
+				   &desc->txd, &status);
+}
+
 int idxd_register_bus_type(void);
 void idxd_unregister_bus_type(void);
 int idxd_register_devices(struct idxd_device *idxd);
@@ -672,6 +733,7 @@ void idxd_unregister_devices(struct idxd_device *idxd);
 void idxd_wqs_quiesce(struct idxd_device *idxd);
 bool idxd_queue_int_handle_resubmit(struct idxd_desc *desc);
 void multi_u64_to_bmap(unsigned long *bmap, u64 *val, int count);
+int idxd_load_iaa_device_defaults(struct idxd_device *idxd);
 
 /* device interrupt control */
 irqreturn_t idxd_misc_thread(int vec, void *data);
@@ -682,8 +744,8 @@ void idxd_unmask_error_interrupts(struct idxd_device *idxd);
 /* device control */
 int idxd_device_drv_probe(struct idxd_dev *idxd_dev);
 void idxd_device_drv_remove(struct idxd_dev *idxd_dev);
-int drv_enable_wq(struct idxd_wq *wq);
-void drv_disable_wq(struct idxd_wq *wq);
+int idxd_drv_enable_wq(struct idxd_wq *wq);
+void idxd_drv_disable_wq(struct idxd_wq *wq);
 int idxd_device_init_reset(struct idxd_device *idxd);
 int idxd_device_enable(struct idxd_device *idxd);
 int idxd_device_disable(struct idxd_device *idxd);
@@ -718,14 +780,11 @@ int idxd_wq_request_irq(struct idxd_wq *wq);
 /* submission */
 int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc);
 struct idxd_desc *idxd_alloc_desc(struct idxd_wq *wq, enum idxd_op_type optype);
-void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc);
 int idxd_enqcmds(struct idxd_wq *wq, void __iomem *portal, const void *desc);
 
 /* dmaengine */
 int idxd_register_dma_device(struct idxd_device *idxd);
 void idxd_unregister_dma_device(struct idxd_device *idxd);
-void idxd_dma_complete_txd(struct idxd_desc *desc,
-			   enum idxd_complete_type comp_type, bool free_desc);
 
 /* cdev */
 int idxd_cdev_register(void);
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index 0eb1c827a215..14df1f1347a8 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -59,6 +59,7 @@ static struct idxd_driver_data idxd_driver_data[] = {
 		.evl_cr_off = offsetof(struct iax_evl_entry, cr),
 		.cr_status_off = offsetof(struct iax_completion_record, status),
 		.cr_result_off = offsetof(struct iax_completion_record, error_code),
+		.load_device_defaults = idxd_load_iaa_device_defaults,
 	},
 };
 
@@ -745,6 +746,12 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err;
 	}
 
+	if (data->load_device_defaults) {
+		rc = data->load_device_defaults(idxd);
+		if (rc)
+			dev_warn(dev, "IDXD loading device defaults failed\n");
+	}
+
 	rc = idxd_register_devices(idxd);
 	if (rc) {
 		dev_err(dev, "IDXD sysfs setup failed\n");
diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
index 2183d7f9cdbd..c8a0aa874b11 100644
--- a/drivers/dma/idxd/irq.c
+++ b/drivers/dma/idxd/irq.c
@@ -123,7 +123,7 @@ static void idxd_abort_invalid_int_handle_descs(struct idxd_irq_entry *ie)
 
 	list_for_each_entry_safe(d, t, &flist, list) {
 		list_del(&d->list);
-		idxd_dma_complete_txd(d, IDXD_COMPLETE_ABORT, true);
+		idxd_desc_complete(d, IDXD_COMPLETE_ABORT, true);
 	}
 }
 
@@ -534,7 +534,7 @@ static void idxd_int_handle_resubmit_work(struct work_struct *work)
 		 */
 		if (rc != -EAGAIN) {
 			desc->completion->status = IDXD_COMP_DESC_ABORT;
-			idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT, false);
+			idxd_desc_complete(desc, IDXD_COMPLETE_ABORT, false);
 		}
 		idxd_free_desc(wq, desc);
 	}
@@ -575,11 +575,11 @@ static void irq_process_pending_llist(struct idxd_irq_entry *irq_entry)
 			 * and 0xff, which DSA_COMP_STATUS_MASK can mask out.
 			 */
 			if (unlikely(desc->completion->status == IDXD_COMP_DESC_ABORT)) {
-				idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT, true);
+				idxd_desc_complete(desc, IDXD_COMPLETE_ABORT, true);
 				continue;
 			}
 
-			idxd_dma_complete_txd(desc, IDXD_COMPLETE_NORMAL, true);
+			idxd_desc_complete(desc, IDXD_COMPLETE_NORMAL, true);
 		} else {
 			spin_lock(&irq_entry->list_lock);
 			list_add_tail(&desc->list,
@@ -618,11 +618,11 @@ static void irq_process_work_list(struct idxd_irq_entry *irq_entry)
 		 * and 0xff, which DSA_COMP_STATUS_MASK can mask out.
 		 */
 		if (unlikely(desc->completion->status == IDXD_COMP_DESC_ABORT)) {
-			idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT, true);
+			idxd_desc_complete(desc, IDXD_COMPLETE_ABORT, true);
 			continue;
 		}
 
-		idxd_dma_complete_txd(desc, IDXD_COMPLETE_NORMAL, true);
+		idxd_desc_complete(desc, IDXD_COMPLETE_NORMAL, true);
 	}
 }
 
diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h
index 7b54a3939ea1..315c004f58e4 100644
--- a/drivers/dma/idxd/registers.h
+++ b/drivers/dma/idxd/registers.h
@@ -440,12 +440,14 @@ union wqcfg {
 /*
  * This macro calculates the offset into the GRPCFG register
  * idxd - struct idxd *
- * n - wq id
- * ofs - the index of the 32b dword for the config register
+ * n - group id
+ * ofs - the index of the 64b qword for the config register
  *
- * The WQCFG register block is divided into groups per each wq. The n index
- * allows us to move to the register group that's for that particular wq.
- * Each register is 32bits. The ofs gives us the number of register to access.
+ * The GRPCFG register block is divided into three sub-registers, which
+ * are GRPWQCFG, GRPENGCFG and GRPFLGCFG. The n index allows us to move
+ * to the register block that contains the three sub-registers.
+ * Each register block is 64bits. And the ofs gives us the offset
+ * within the GRPWQCFG register to access.
  */
 #define GRPWQCFG_OFFSET(idxd_dev, n, ofs) ((idxd_dev)->grpcfg_offset +\
 					   (n) * GRPCFG_SIZE + sizeof(u64) * (ofs))
diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c
index c01db23e3333..817a564413b0 100644
--- a/drivers/dma/idxd/submit.c
+++ b/drivers/dma/idxd/submit.c
@@ -61,6 +61,7 @@ struct idxd_desc *idxd_alloc_desc(struct idxd_wq *wq, enum idxd_op_type optype)
 
 	return __get_desc(wq, idx, cpu);
 }
+EXPORT_SYMBOL_NS_GPL(idxd_alloc_desc, IDXD);
 
 void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 {
@@ -69,6 +70,7 @@ void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 	desc->cpu = -1;
 	sbitmap_queue_clear(&wq->sbq, desc->id, cpu);
 }
+EXPORT_SYMBOL_NS_GPL(idxd_free_desc, IDXD);
 
 static struct idxd_desc *list_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
 					 struct idxd_desc *desc)
@@ -125,7 +127,8 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
 	spin_unlock(&ie->list_lock);
 
 	if (found)
-		idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, false);
+		idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, false,
+				      NULL, NULL);
 
 	/*
 	 * completing the descriptor will return desc to allocator and
@@ -135,7 +138,8 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
 	 */
 	list_for_each_entry_safe(d, t, &flist, list) {
 		list_del_init(&d->list);
-		idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, true);
+		idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, true,
+				      NULL, NULL);
 	}
 }
 
@@ -183,13 +187,6 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 	portal = idxd_wq_portal_addr(wq);
 
 	/*
-	 * The wmb() flushes writes to coherent DMA data before
-	 * possibly triggering a DMA read. The wmb() is necessary
-	 * even on UP because the recipient is a device.
-	 */
-	wmb();
-
-	/*
 	 * Pending the descriptor to the lockless list for the irq_entry
 	 * that we designated the descriptor to.
 	 */
@@ -199,6 +196,13 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 		llist_add(&desc->llnode, &ie->pending_llist);
 	}
 
+	/*
+	 * The wmb() flushes writes to coherent DMA data before
+	 * possibly triggering a DMA read. The wmb() is necessary
+	 * even on UP because the recipient is a device.
+	 */
+	wmb();
+
 	if (wq_dedicated(wq)) {
 		iosubmit_cmds512(portal, desc->hw, 1);
 	} else {
@@ -215,3 +219,4 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 	percpu_ref_put(&wq->wq_active);
 	return 0;
 }
+EXPORT_SYMBOL_NS_GPL(idxd_submit_desc, IDXD);
diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c
index 72d83cd9ed6b..90857d08a1a7 100644
--- a/drivers/dma/stm32-dma.c
+++ b/drivers/dma/stm32-dma.c
@@ -1246,8 +1246,8 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_dma_memcpy(
 	enum dma_slave_buswidth max_width;
 	struct stm32_dma_desc *desc;
 	size_t xfer_count, offset;
-	u32 num_sgs, best_burst, dma_burst, threshold;
-	int i;
+	u32 num_sgs, best_burst, threshold;
+	int dma_burst, i;
 
 	num_sgs = DIV_ROUND_UP(len, STM32_DMA_ALIGNED_MAX_DATA_ITEMS);
 	desc = kzalloc(struct_size(desc, sg_req, num_sgs), GFP_NOWAIT);
@@ -1266,6 +1266,10 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_dma_memcpy(
 		best_burst = stm32_dma_get_best_burst(len, STM32_DMA_MAX_BURST,
 						      threshold, max_width);
 		dma_burst = stm32_dma_get_burst(chan, best_burst);
+		if (dma_burst < 0) {
+			kfree(desc);
+			return NULL;
+		}
 
 		stm32_dma_clear_reg(&desc->sg_req[i].chan_reg);
 		desc->sg_req[i].chan_reg.dma_scr =
diff --git a/drivers/dma/ti/k3-psil-am62.c b/drivers/dma/ti/k3-psil-am62.c
index 2b6fd6e37c61..1272b1541f61 100644
--- a/drivers/dma/ti/k3-psil-am62.c
+++ b/drivers/dma/ti/k3-psil-am62.c
@@ -74,7 +74,9 @@ static struct psil_ep am62_src_ep_map[] = {
 	PSIL_SAUL(0x7505, 21, 35, 8, 36, 0),
 	PSIL_SAUL(0x7506, 22, 43, 8, 43, 0),
 	PSIL_SAUL(0x7507, 23, 43, 8, 44, 0),
-	/* PDMA_MAIN0 - SPI0-3 */
+	/* PDMA_MAIN0 - SPI0-2 */
+	PSIL_PDMA_XY_PKT(0x4300),
+	PSIL_PDMA_XY_PKT(0x4301),
 	PSIL_PDMA_XY_PKT(0x4302),
 	PSIL_PDMA_XY_PKT(0x4303),
 	PSIL_PDMA_XY_PKT(0x4304),
@@ -85,8 +87,6 @@ static struct psil_ep am62_src_ep_map[] = {
 	PSIL_PDMA_XY_PKT(0x4309),
 	PSIL_PDMA_XY_PKT(0x430a),
 	PSIL_PDMA_XY_PKT(0x430b),
-	PSIL_PDMA_XY_PKT(0x430c),
-	PSIL_PDMA_XY_PKT(0x430d),
 	/* PDMA_MAIN1 - UART0-6 */
 	PSIL_PDMA_XY_PKT(0x4400),
 	PSIL_PDMA_XY_PKT(0x4401),
@@ -141,7 +141,9 @@ static struct psil_ep am62_dst_ep_map[] = {
 	/* SAUL */
 	PSIL_SAUL(0xf500, 27, 83, 8, 83, 1),
 	PSIL_SAUL(0xf501, 28, 91, 8, 91, 1),
-	/* PDMA_MAIN0 - SPI0-3 */
+	/* PDMA_MAIN0 - SPI0-2 */
+	PSIL_PDMA_XY_PKT(0xc300),
+	PSIL_PDMA_XY_PKT(0xc301),
 	PSIL_PDMA_XY_PKT(0xc302),
 	PSIL_PDMA_XY_PKT(0xc303),
 	PSIL_PDMA_XY_PKT(0xc304),
@@ -152,8 +154,6 @@ static struct psil_ep am62_dst_ep_map[] = {
 	PSIL_PDMA_XY_PKT(0xc309),
 	PSIL_PDMA_XY_PKT(0xc30a),
 	PSIL_PDMA_XY_PKT(0xc30b),
-	PSIL_PDMA_XY_PKT(0xc30c),
-	PSIL_PDMA_XY_PKT(0xc30d),
 	/* PDMA_MAIN1 - UART0-6 */
 	PSIL_PDMA_XY_PKT(0xc400),
 	PSIL_PDMA_XY_PKT(0xc401),
diff --git a/drivers/dma/ti/k3-psil-am62a.c b/drivers/dma/ti/k3-psil-am62a.c
index ca9d71f91422..4cf9123b0e93 100644
--- a/drivers/dma/ti/k3-psil-am62a.c
+++ b/drivers/dma/ti/k3-psil-am62a.c
@@ -84,7 +84,9 @@ static struct psil_ep am62a_src_ep_map[] = {
 	PSIL_SAUL(0x7505, 21, 35, 8, 36, 0),
 	PSIL_SAUL(0x7506, 22, 43, 8, 43, 0),
 	PSIL_SAUL(0x7507, 23, 43, 8, 44, 0),
-	/* PDMA_MAIN0 - SPI0-3 */
+	/* PDMA_MAIN0 - SPI0-2 */
+	PSIL_PDMA_XY_PKT(0x4300),
+	PSIL_PDMA_XY_PKT(0x4301),
 	PSIL_PDMA_XY_PKT(0x4302),
 	PSIL_PDMA_XY_PKT(0x4303),
 	PSIL_PDMA_XY_PKT(0x4304),
@@ -95,8 +97,6 @@ static struct psil_ep am62a_src_ep_map[] = {
 	PSIL_PDMA_XY_PKT(0x4309),
 	PSIL_PDMA_XY_PKT(0x430a),
 	PSIL_PDMA_XY_PKT(0x430b),
-	PSIL_PDMA_XY_PKT(0x430c),
-	PSIL_PDMA_XY_PKT(0x430d),
 	/* PDMA_MAIN1 - UART0-6 */
 	PSIL_PDMA_XY_PKT(0x4400),
 	PSIL_PDMA_XY_PKT(0x4401),
@@ -151,7 +151,9 @@ static struct psil_ep am62a_dst_ep_map[] = {
 	/* SAUL */
 	PSIL_SAUL(0xf500, 27, 83, 8, 83, 1),
 	PSIL_SAUL(0xf501, 28, 91, 8, 91, 1),
-	/* PDMA_MAIN0 - SPI0-3 */
+	/* PDMA_MAIN0 - SPI0-2 */
+	PSIL_PDMA_XY_PKT(0xc300),
+	PSIL_PDMA_XY_PKT(0xc301),
 	PSIL_PDMA_XY_PKT(0xc302),
 	PSIL_PDMA_XY_PKT(0xc303),
 	PSIL_PDMA_XY_PKT(0xc304),
@@ -162,8 +164,6 @@ static struct psil_ep am62a_dst_ep_map[] = {
 	PSIL_PDMA_XY_PKT(0xc309),
 	PSIL_PDMA_XY_PKT(0xc30a),
 	PSIL_PDMA_XY_PKT(0xc30b),
-	PSIL_PDMA_XY_PKT(0xc30c),
-	PSIL_PDMA_XY_PKT(0xc30d),
 	/* PDMA_MAIN1 - UART0-6 */
 	PSIL_PDMA_XY_PKT(0xc400),
 	PSIL_PDMA_XY_PKT(0xc401),
diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c
index 3568149b9562..1eca8cc271f8 100644
--- a/drivers/dpll/dpll_core.c
+++ b/drivers/dpll/dpll_core.c
@@ -22,7 +22,8 @@ DEFINE_MUTEX(dpll_lock);
 DEFINE_XARRAY_FLAGS(dpll_device_xa, XA_FLAGS_ALLOC);
 DEFINE_XARRAY_FLAGS(dpll_pin_xa, XA_FLAGS_ALLOC);
 
-static u32 dpll_xa_id;
+static u32 dpll_device_xa_id;
+static u32 dpll_pin_xa_id;
 
 #define ASSERT_DPLL_REGISTERED(d)	\
 	WARN_ON_ONCE(!xa_get_mark(&dpll_device_xa, (d)->id, DPLL_REGISTERED))
@@ -246,7 +247,7 @@ dpll_device_alloc(const u64 clock_id, u32 device_idx, struct module *module)
 	dpll->clock_id = clock_id;
 	dpll->module = module;
 	ret = xa_alloc_cyclic(&dpll_device_xa, &dpll->id, dpll, xa_limit_32b,
-			      &dpll_xa_id, GFP_KERNEL);
+			      &dpll_device_xa_id, GFP_KERNEL);
 	if (ret < 0) {
 		kfree(dpll);
 		return ERR_PTR(ret);
@@ -446,7 +447,8 @@ dpll_pin_alloc(u64 clock_id, u32 pin_idx, struct module *module,
 	refcount_set(&pin->refcount, 1);
 	xa_init_flags(&pin->dpll_refs, XA_FLAGS_ALLOC);
 	xa_init_flags(&pin->parent_refs, XA_FLAGS_ALLOC);
-	ret = xa_alloc(&dpll_pin_xa, &pin->id, pin, xa_limit_16b, GFP_KERNEL);
+	ret = xa_alloc_cyclic(&dpll_pin_xa, &pin->id, pin, xa_limit_32b,
+			      &dpll_pin_xa_id, GFP_KERNEL);
 	if (ret)
 		goto err;
 	return pin;
diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c
index a6dc3997bf5c..3370dbddb86b 100644
--- a/drivers/dpll/dpll_netlink.c
+++ b/drivers/dpll/dpll_netlink.c
@@ -101,13 +101,17 @@ dpll_msg_add_mode_supported(struct sk_buff *msg, struct dpll_device *dpll,
 {
 	const struct dpll_device_ops *ops = dpll_device_ops(dpll);
 	enum dpll_mode mode;
+	int ret;
 
-	if (!ops->mode_supported)
-		return 0;
-	for (mode = DPLL_MODE_MANUAL; mode <= DPLL_MODE_MAX; mode++)
-		if (ops->mode_supported(dpll, dpll_priv(dpll), mode, extack))
-			if (nla_put_u32(msg, DPLL_A_MODE_SUPPORTED, mode))
-				return -EMSGSIZE;
+	/* No mode change is supported now, so the only supported mode is the
+	 * one obtained by mode_get().
+	 */
+
+	ret = ops->mode_get(dpll, dpll_priv(dpll), &mode, extack);
+	if (ret)
+		return ret;
+	if (nla_put_u32(msg, DPLL_A_MODE_SUPPORTED, mode))
+		return -EMSGSIZE;
 
 	return 0;
 }
@@ -259,6 +263,27 @@ dpll_msg_add_phase_offset(struct sk_buff *msg, struct dpll_pin *pin,
 	return 0;
 }
 
+static int dpll_msg_add_ffo(struct sk_buff *msg, struct dpll_pin *pin,
+			    struct dpll_pin_ref *ref,
+			    struct netlink_ext_ack *extack)
+{
+	const struct dpll_pin_ops *ops = dpll_pin_ops(ref);
+	struct dpll_device *dpll = ref->dpll;
+	s64 ffo;
+	int ret;
+
+	if (!ops->ffo_get)
+		return 0;
+	ret = ops->ffo_get(pin, dpll_pin_on_dpll_priv(dpll, pin),
+			   dpll, dpll_priv(dpll), &ffo, extack);
+	if (ret) {
+		if (ret == -ENODATA)
+			return 0;
+		return ret;
+	}
+	return nla_put_sint(msg, DPLL_A_PIN_FRACTIONAL_FREQUENCY_OFFSET, ffo);
+}
+
 static int
 dpll_msg_add_pin_freq(struct sk_buff *msg, struct dpll_pin *pin,
 		      struct dpll_pin_ref *ref, struct netlink_ext_ack *extack)
@@ -438,6 +463,9 @@ dpll_cmd_pin_get_one(struct sk_buff *msg, struct dpll_pin *pin,
 	ret = dpll_msg_add_pin_phase_adjust(msg, pin, ref, extack);
 	if (ret)
 		return ret;
+	ret = dpll_msg_add_ffo(msg, pin, ref, extack);
+	if (ret)
+		return ret;
 	if (xa_empty(&pin->parent_refs))
 		ret = dpll_msg_add_pin_dplls(msg, pin, extack);
 	else
@@ -925,7 +953,6 @@ dpll_pin_parent_pin_set(struct dpll_pin *pin, struct nlattr *parent_nest,
 			struct netlink_ext_ack *extack)
 {
 	struct nlattr *tb[DPLL_A_PIN_MAX + 1];
-	enum dpll_pin_state state;
 	u32 ppin_idx;
 	int ret;
 
@@ -936,10 +963,14 @@ dpll_pin_parent_pin_set(struct dpll_pin *pin, struct nlattr *parent_nest,
 		return -EINVAL;
 	}
 	ppin_idx = nla_get_u32(tb[DPLL_A_PIN_PARENT_ID]);
-	state = nla_get_u32(tb[DPLL_A_PIN_STATE]);
-	ret = dpll_pin_on_pin_state_set(pin, ppin_idx, state, extack);
-	if (ret)
-		return ret;
+
+	if (tb[DPLL_A_PIN_STATE]) {
+		enum dpll_pin_state state = nla_get_u32(tb[DPLL_A_PIN_STATE]);
+
+		ret = dpll_pin_on_pin_state_set(pin, ppin_idx, state, extack);
+		if (ret)
+			return ret;
+	}
 
 	return 0;
 }
@@ -1093,9 +1124,10 @@ int dpll_nl_pin_id_get_doit(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 	hdr = genlmsg_put_reply(msg, info, &dpll_nl_family, 0,
 				DPLL_CMD_PIN_ID_GET);
-	if (!hdr)
+	if (!hdr) {
+		nlmsg_free(msg);
 		return -EMSGSIZE;
-
+	}
 	pin = dpll_pin_find_from_nlattr(info);
 	if (!IS_ERR(pin)) {
 		ret = dpll_msg_add_pin_handle(msg, pin);
@@ -1123,8 +1155,10 @@ int dpll_nl_pin_get_doit(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 	hdr = genlmsg_put_reply(msg, info, &dpll_nl_family, 0,
 				DPLL_CMD_PIN_GET);
-	if (!hdr)
+	if (!hdr) {
+		nlmsg_free(msg);
 		return -EMSGSIZE;
+	}
 	ret = dpll_cmd_pin_get_one(msg, pin, info->extack);
 	if (ret) {
 		nlmsg_free(msg);
@@ -1256,8 +1290,10 @@ int dpll_nl_device_id_get_doit(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 	hdr = genlmsg_put_reply(msg, info, &dpll_nl_family, 0,
 				DPLL_CMD_DEVICE_ID_GET);
-	if (!hdr)
+	if (!hdr) {
+		nlmsg_free(msg);
 		return -EMSGSIZE;
+	}
 
 	dpll = dpll_device_find_from_nlattr(info);
 	if (!IS_ERR(dpll)) {
@@ -1284,8 +1320,10 @@ int dpll_nl_device_get_doit(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 	hdr = genlmsg_put_reply(msg, info, &dpll_nl_family, 0,
 				DPLL_CMD_DEVICE_GET);
-	if (!hdr)
+	if (!hdr) {
+		nlmsg_free(msg);
 		return -EMSGSIZE;
+	}
 
 	ret = dpll_device_get_one(dpll, msg, info->extack);
 	if (ret) {
diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c
index 8b31cd54bdb6..ae17ce4d9722 100644
--- a/drivers/edac/altera_edac.c
+++ b/drivers/edac/altera_edac.c
@@ -22,6 +22,7 @@
 #include <linux/of_platform.h>
 #include <linux/panic_notifier.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/regmap.h>
 #include <linux/types.h>
 #include <linux/uaccess.h>
@@ -279,7 +280,6 @@ release:
 
 static int altr_sdram_probe(struct platform_device *pdev)
 {
-	const struct of_device_id *id;
 	struct edac_mc_layer layers[2];
 	struct mem_ctl_info *mci;
 	struct altr_sdram_mc_data *drvdata;
@@ -290,10 +290,6 @@ static int altr_sdram_probe(struct platform_device *pdev)
 	int irq, irq2, res = 0;
 	unsigned long mem_size, irqflags = 0;
 
-	id = of_match_device(altr_sdram_ctrl_of_match, &pdev->dev);
-	if (!id)
-		return -ENODEV;
-
 	/* Grab the register range from the sdr controller in device tree */
 	mc_vbase = syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
 						   "altr,sdr-syscon");
@@ -304,8 +300,7 @@ static int altr_sdram_probe(struct platform_device *pdev)
 	}
 
 	/* Check specific dependencies for the module */
-	priv = of_match_node(altr_sdram_ctrl_of_match,
-			     pdev->dev.of_node)->data;
+	priv = device_get_match_data(&pdev->dev);
 
 	/* Validate the SDRAM controller has ECC enabled */
 	if (regmap_read(mc_vbase, priv->ecc_ctrl_offset, &read_reg) ||
@@ -459,15 +454,13 @@ free:
 	return res;
 }
 
-static int altr_sdram_remove(struct platform_device *pdev)
+static void altr_sdram_remove(struct platform_device *pdev)
 {
 	struct mem_ctl_info *mci = platform_get_drvdata(pdev);
 
 	edac_mc_del_mc(&pdev->dev);
 	edac_mc_free(mci);
 	platform_set_drvdata(pdev, NULL);
-
-	return 0;
 }
 
 /*
@@ -489,7 +482,7 @@ static const struct dev_pm_ops altr_sdram_pm_ops = {
 
 static struct platform_driver altr_sdram_edac_driver = {
 	.probe = altr_sdram_probe,
-	.remove = altr_sdram_remove,
+	.remove_new = altr_sdram_remove,
 	.driver = {
 		.name = "altr_sdram_edac",
 #ifdef CONFIG_PM
@@ -812,7 +805,7 @@ fail:
 	return res;
 }
 
-static int altr_edac_device_remove(struct platform_device *pdev)
+static void altr_edac_device_remove(struct platform_device *pdev)
 {
 	struct edac_device_ctl_info *dci = platform_get_drvdata(pdev);
 	struct altr_edac_device_dev *drvdata = dci->pvt_info;
@@ -820,13 +813,11 @@ static int altr_edac_device_remove(struct platform_device *pdev)
 	debugfs_remove_recursive(drvdata->debugfs_dir);
 	edac_device_del_device(&pdev->dev);
 	edac_device_free_ctl_info(dci);
-
-	return 0;
 }
 
 static struct platform_driver altr_edac_device_driver = {
 	.probe =  altr_edac_device_probe,
-	.remove = altr_edac_device_remove,
+	.remove_new = altr_edac_device_remove,
 	.driver = {
 		.name = "altr_edac_device",
 		.of_match_table = altr_edac_device_of_match,
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 9b6642d00871..537b9987a431 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -996,15 +996,23 @@ static struct local_node_map {
 #define LNTM_NODE_COUNT				GENMASK(27, 16)
 #define LNTM_BASE_NODE_ID			GENMASK(11, 0)
 
-static int gpu_get_node_map(void)
+static int gpu_get_node_map(struct amd64_pvt *pvt)
 {
 	struct pci_dev *pdev;
 	int ret;
 	u32 tmp;
 
 	/*
-	 * Node ID 0 is reserved for CPUs.
-	 * Therefore, a non-zero Node ID means we've already cached the values.
+	 * Mapping of nodes from hardware-provided AMD Node ID to a
+	 * Linux logical one is applicable for MI200 models. Therefore,
+	 * return early for other heterogeneous systems.
+	 */
+	if (pvt->F3->device != PCI_DEVICE_ID_AMD_MI200_DF_F3)
+		return 0;
+
+	/*
+	 * Node ID 0 is reserved for CPUs. Therefore, a non-zero Node ID
+	 * means the values have been already cached.
 	 */
 	if (gpu_node_map.base_node_id)
 		return 0;
@@ -3851,7 +3859,7 @@ static void gpu_init_csrows(struct mem_ctl_info *mci)
 
 			dimm->nr_pages = gpu_get_csrow_nr_pages(pvt, umc, cs);
 			dimm->edac_mode = EDAC_SECDED;
-			dimm->mtype = MEM_HBM2;
+			dimm->mtype = pvt->dram_type;
 			dimm->dtype = DEV_X16;
 			dimm->grain = 64;
 		}
@@ -3880,7 +3888,7 @@ static bool gpu_ecc_enabled(struct amd64_pvt *pvt)
 	return true;
 }
 
-static inline u32 gpu_get_umc_base(u8 umc, u8 channel)
+static inline u32 gpu_get_umc_base(struct amd64_pvt *pvt, u8 umc, u8 channel)
 {
 	/*
 	 * On CPUs, there is one channel per UMC, so UMC numbering equals
@@ -3893,13 +3901,16 @@ static inline u32 gpu_get_umc_base(u8 umc, u8 channel)
 	 * On GPU nodes channels are selected in 3rd nibble
 	 * HBM chX[3:0]= [Y  ]5X[3:0]000;
 	 * HBM chX[7:4]= [Y+1]5X[3:0]000
+	 *
+	 * On MI300 APU nodes, same as GPU nodes but channels are selected
+	 * in the base address of 0x90000
 	 */
 	umc *= 2;
 
 	if (channel >= 4)
 		umc++;
 
-	return 0x50000 + (umc << 20) + ((channel % 4) << 12);
+	return pvt->gpu_umc_base + (umc << 20) + ((channel % 4) << 12);
 }
 
 static void gpu_read_mc_regs(struct amd64_pvt *pvt)
@@ -3910,7 +3921,7 @@ static void gpu_read_mc_regs(struct amd64_pvt *pvt)
 
 	/* Read registers from each UMC */
 	for_each_umc(i) {
-		umc_base = gpu_get_umc_base(i, 0);
+		umc_base = gpu_get_umc_base(pvt, i, 0);
 		umc = &pvt->umc[i];
 
 		amd_smn_read(nid, umc_base + UMCCH_UMC_CFG, &umc->umc_cfg);
@@ -3927,7 +3938,7 @@ static void gpu_read_base_mask(struct amd64_pvt *pvt)
 
 	for_each_umc(umc) {
 		for_each_chip_select(cs, umc, pvt) {
-			base_reg = gpu_get_umc_base(umc, cs) + UMCCH_BASE_ADDR;
+			base_reg = gpu_get_umc_base(pvt, umc, cs) + UMCCH_BASE_ADDR;
 			base = &pvt->csels[umc].csbases[cs];
 
 			if (!amd_smn_read(pvt->mc_node_id, base_reg, base)) {
@@ -3935,7 +3946,7 @@ static void gpu_read_base_mask(struct amd64_pvt *pvt)
 					 umc, cs, *base, base_reg);
 			}
 
-			mask_reg = gpu_get_umc_base(umc, cs) + UMCCH_ADDR_MASK;
+			mask_reg = gpu_get_umc_base(pvt, umc, cs) + UMCCH_ADDR_MASK;
 			mask = &pvt->csels[umc].csmasks[cs];
 
 			if (!amd_smn_read(pvt->mc_node_id, mask_reg, mask)) {
@@ -3960,7 +3971,7 @@ static int gpu_hw_info_get(struct amd64_pvt *pvt)
 {
 	int ret;
 
-	ret = gpu_get_node_map();
+	ret = gpu_get_node_map(pvt);
 	if (ret)
 		return ret;
 
@@ -4125,6 +4136,8 @@ static int per_family_init(struct amd64_pvt *pvt)
 			if (pvt->F3->device == PCI_DEVICE_ID_AMD_MI200_DF_F3) {
 				pvt->ctl_name		= "MI200";
 				pvt->max_mcs		= 4;
+				pvt->dram_type		= MEM_HBM2;
+				pvt->gpu_umc_base	= 0x50000;
 				pvt->ops		= &gpu_ops;
 			} else {
 				pvt->ctl_name		= "F19h_M30h";
@@ -4142,6 +4155,13 @@ static int per_family_init(struct amd64_pvt *pvt)
 			pvt->ctl_name			= "F19h_M70h";
 			pvt->flags.zn_regs_v2		= 1;
 			break;
+		case 0x90 ... 0x9f:
+			pvt->ctl_name			= "F19h_M90h";
+			pvt->max_mcs			= 4;
+			pvt->dram_type			= MEM_HBM3;
+			pvt->gpu_umc_base		= 0x90000;
+			pvt->ops			= &gpu_ops;
+			break;
 		case 0xa0 ... 0xaf:
 			pvt->ctl_name			= "F19h_MA0h";
 			pvt->max_mcs			= 12;
@@ -4180,23 +4200,33 @@ static const struct attribute_group *amd64_edac_attr_groups[] = {
 	NULL
 };
 
+/*
+ * For heterogeneous and APU models EDAC CHIP_SELECT and CHANNEL layers
+ * should be swapped to fit into the layers.
+ */
+static unsigned int get_layer_size(struct amd64_pvt *pvt, u8 layer)
+{
+	bool is_gpu = (pvt->ops == &gpu_ops);
+
+	if (!layer)
+		return is_gpu ? pvt->max_mcs
+			      : pvt->csels[0].b_cnt;
+	else
+		return is_gpu ? pvt->csels[0].b_cnt
+			      : pvt->max_mcs;
+}
+
 static int init_one_instance(struct amd64_pvt *pvt)
 {
 	struct mem_ctl_info *mci = NULL;
 	struct edac_mc_layer layers[2];
 	int ret = -ENOMEM;
 
-	/*
-	 * For Heterogeneous family EDAC CHIP_SELECT and CHANNEL layers should
-	 * be swapped to fit into the layers.
-	 */
 	layers[0].type = EDAC_MC_LAYER_CHIP_SELECT;
-	layers[0].size = (pvt->F3->device == PCI_DEVICE_ID_AMD_MI200_DF_F3) ?
-			 pvt->max_mcs : pvt->csels[0].b_cnt;
+	layers[0].size = get_layer_size(pvt, 0);
 	layers[0].is_virt_csrow = true;
 	layers[1].type = EDAC_MC_LAYER_CHANNEL;
-	layers[1].size = (pvt->F3->device == PCI_DEVICE_ID_AMD_MI200_DF_F3) ?
-			 pvt->csels[0].b_cnt : pvt->max_mcs;
+	layers[1].size = get_layer_size(pvt, 1);
 	layers[1].is_virt_csrow = false;
 
 	mci = edac_mc_alloc(pvt->mc_node_id, ARRAY_SIZE(layers), layers, 0);
diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h
index 5a4e4a59682b..1665f7932bac 100644
--- a/drivers/edac/amd64_edac.h
+++ b/drivers/edac/amd64_edac.h
@@ -362,6 +362,7 @@ struct amd64_pvt {
 	u32 dct_sel_lo;		/* DRAM Controller Select Low */
 	u32 dct_sel_hi;		/* DRAM Controller Select High */
 	u32 online_spare;	/* On-Line spare Reg */
+	u32 gpu_umc_base;	/* Base address used for channel selection on GPUs */
 
 	/* x4, x8, or x16 syndromes in use */
 	u8 ecc_sym_sz;
diff --git a/drivers/edac/armada_xp_edac.c b/drivers/edac/armada_xp_edac.c
index c4bd2fb9c46b..25517c99b3ea 100644
--- a/drivers/edac/armada_xp_edac.c
+++ b/drivers/edac/armada_xp_edac.c
@@ -5,7 +5,9 @@
 
 #include <linux/kernel.h>
 #include <linux/edac.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
 
 #include <asm/hardware/cache-l2x0.h>
 #include <asm/hardware/cache-aurora-l2.h>
@@ -351,20 +353,18 @@ static int axp_mc_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int axp_mc_remove(struct platform_device *pdev)
+static void axp_mc_remove(struct platform_device *pdev)
 {
 	struct mem_ctl_info *mci = platform_get_drvdata(pdev);
 
 	edac_mc_del_mc(&pdev->dev);
 	edac_mc_free(mci);
 	platform_set_drvdata(pdev, NULL);
-
-	return 0;
 }
 
 static struct platform_driver axp_mc_driver = {
 	.probe = axp_mc_probe,
-	.remove = axp_mc_remove,
+	.remove_new = axp_mc_remove,
 	.driver = {
 		.name = "armada_xp_mc_edac",
 		.of_match_table = of_match_ptr(axp_mc_of_match),
@@ -564,7 +564,7 @@ static int aurora_l2_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int aurora_l2_remove(struct platform_device *pdev)
+static void aurora_l2_remove(struct platform_device *pdev)
 {
 	struct edac_device_ctl_info *dci = platform_get_drvdata(pdev);
 #ifdef CONFIG_EDAC_DEBUG
@@ -575,13 +575,11 @@ static int aurora_l2_remove(struct platform_device *pdev)
 	edac_device_del_device(&pdev->dev);
 	edac_device_free_ctl_info(dci);
 	platform_set_drvdata(pdev, NULL);
-
-	return 0;
 }
 
 static struct platform_driver aurora_l2_driver = {
 	.probe = aurora_l2_probe,
-	.remove = aurora_l2_remove,
+	.remove_new = aurora_l2_remove,
 	.driver = {
 		.name = "aurora_l2_edac",
 		.of_match_table = of_match_ptr(aurora_l2_of_match),
diff --git a/drivers/edac/aspeed_edac.c b/drivers/edac/aspeed_edac.c
index 6bd5f8815919..157a480eb761 100644
--- a/drivers/edac/aspeed_edac.c
+++ b/drivers/edac/aspeed_edac.c
@@ -357,7 +357,7 @@ probe_exit02:
 }
 
 
-static int aspeed_remove(struct platform_device *pdev)
+static void aspeed_remove(struct platform_device *pdev)
 {
 	struct mem_ctl_info *mci;
 
@@ -369,8 +369,6 @@ static int aspeed_remove(struct platform_device *pdev)
 	mci = edac_mc_del_mc(&pdev->dev);
 	if (mci)
 		edac_mc_free(mci);
-
-	return 0;
 }
 
 
@@ -389,7 +387,7 @@ static struct platform_driver aspeed_driver = {
 		.of_match_table = aspeed_of_match
 	},
 	.probe		= aspeed_probe,
-	.remove		= aspeed_remove
+	.remove_new	= aspeed_remove
 };
 module_platform_driver(aspeed_driver);
 
diff --git a/drivers/edac/bluefield_edac.c b/drivers/edac/bluefield_edac.c
index e4736eb37bfb..5b3164560648 100644
--- a/drivers/edac/bluefield_edac.c
+++ b/drivers/edac/bluefield_edac.c
@@ -323,14 +323,12 @@ err:
 
 }
 
-static int bluefield_edac_mc_remove(struct platform_device *pdev)
+static void bluefield_edac_mc_remove(struct platform_device *pdev)
 {
 	struct mem_ctl_info *mci = platform_get_drvdata(pdev);
 
 	edac_mc_del_mc(&pdev->dev);
 	edac_mc_free(mci);
-
-	return 0;
 }
 
 static const struct acpi_device_id bluefield_mc_acpi_ids[] = {
@@ -346,7 +344,7 @@ static struct platform_driver bluefield_edac_mc_driver = {
 		.acpi_match_table = bluefield_mc_acpi_ids,
 	},
 	.probe = bluefield_edac_mc_probe,
-	.remove = bluefield_edac_mc_remove,
+	.remove_new = bluefield_edac_mc_remove,
 };
 
 module_platform_driver(bluefield_edac_mc_driver);
diff --git a/drivers/edac/cell_edac.c b/drivers/edac/cell_edac.c
index bc1f3416400e..2000f66fbf5c 100644
--- a/drivers/edac/cell_edac.c
+++ b/drivers/edac/cell_edac.c
@@ -234,12 +234,11 @@ static int cell_edac_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int cell_edac_remove(struct platform_device *pdev)
+static void cell_edac_remove(struct platform_device *pdev)
 {
 	struct mem_ctl_info *mci = edac_mc_del_mc(&pdev->dev);
 	if (mci)
 		edac_mc_free(mci);
-	return 0;
 }
 
 static struct platform_driver cell_edac_driver = {
@@ -247,7 +246,7 @@ static struct platform_driver cell_edac_driver = {
 		.name	= "cbe-mic",
 	},
 	.probe		= cell_edac_probe,
-	.remove		= cell_edac_remove,
+	.remove_new	= cell_edac_remove,
 };
 
 static int __init cell_edac_init(void)
diff --git a/drivers/edac/cpc925_edac.c b/drivers/edac/cpc925_edac.c
index 9797e6d60dde..5075dc7526e3 100644
--- a/drivers/edac/cpc925_edac.c
+++ b/drivers/edac/cpc925_edac.c
@@ -1010,7 +1010,7 @@ out:
 	return res;
 }
 
-static int cpc925_remove(struct platform_device *pdev)
+static void cpc925_remove(struct platform_device *pdev)
 {
 	struct mem_ctl_info *mci = platform_get_drvdata(pdev);
 
@@ -1023,13 +1023,11 @@ static int cpc925_remove(struct platform_device *pdev)
 
 	edac_mc_del_mc(&pdev->dev);
 	edac_mc_free(mci);
-
-	return 0;
 }
 
 static struct platform_driver cpc925_edac_driver = {
 	.probe = cpc925_probe,
-	.remove = cpc925_remove,
+	.remove_new = cpc925_remove,
 	.driver = {
 		   .name = "cpc925_edac",
 	}
diff --git a/drivers/edac/dmc520_edac.c b/drivers/edac/dmc520_edac.c
index 1fa5ca57e9ec..4e30b989a1a4 100644
--- a/drivers/edac/dmc520_edac.c
+++ b/drivers/edac/dmc520_edac.c
@@ -602,7 +602,7 @@ err:
 	return ret;
 }
 
-static int dmc520_edac_remove(struct platform_device *pdev)
+static void dmc520_edac_remove(struct platform_device *pdev)
 {
 	u32 reg_val, idx, irq_mask_all = 0;
 	struct mem_ctl_info *mci;
@@ -626,8 +626,6 @@ static int dmc520_edac_remove(struct platform_device *pdev)
 
 	edac_mc_del_mc(&pdev->dev);
 	edac_mc_free(mci);
-
-	return 0;
 }
 
 static const struct of_device_id dmc520_edac_driver_id[] = {
@@ -644,7 +642,7 @@ static struct platform_driver dmc520_edac_driver = {
 	},
 
 	.probe = dmc520_edac_probe,
-	.remove = dmc520_edac_remove
+	.remove_new = dmc520_edac_remove
 };
 
 module_platform_driver(dmc520_edac_driver);
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 6faeb2ab3960..d6eed727b0cd 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -166,6 +166,7 @@ const char * const edac_mem_types[] = {
 	[MEM_NVDIMM]	= "Non-volatile-RAM",
 	[MEM_WIO2]	= "Wide-IO-2",
 	[MEM_HBM2]	= "High-bandwidth-memory-Gen2",
+	[MEM_HBM3]	= "High-bandwidth-memory-Gen3",
 };
 EXPORT_SYMBOL_GPL(edac_mem_types);
 
diff --git a/drivers/edac/edac_pci_sysfs.c b/drivers/edac/edac_pci_sysfs.c
index 287cc51dbc86..901d4cd3ca38 100644
--- a/drivers/edac/edac_pci_sysfs.c
+++ b/drivers/edac/edac_pci_sysfs.c
@@ -521,7 +521,7 @@ static void edac_pci_dev_parity_clear(struct pci_dev *dev)
 	/* read the device TYPE, looking for bridges */
 	pci_read_config_byte(dev, PCI_HEADER_TYPE, &header_type);
 
-	if ((header_type & 0x7F) == PCI_HEADER_TYPE_BRIDGE)
+	if ((header_type & PCI_HEADER_TYPE_MASK) == PCI_HEADER_TYPE_BRIDGE)
 		get_pci_parity_status(dev, 1);
 }
 
@@ -583,7 +583,7 @@ static void edac_pci_dev_parity_test(struct pci_dev *dev)
 	edac_dbg(4, "PCI HEADER TYPE= 0x%02x %s\n",
 		 header_type, dev_name(&dev->dev));
 
-	if ((header_type & 0x7F) == PCI_HEADER_TYPE_BRIDGE) {
+	if ((header_type & PCI_HEADER_TYPE_MASK) == PCI_HEADER_TYPE_BRIDGE) {
 		/* On bridges, need to examine secondary status register  */
 		status = get_pci_parity_status(dev, 1);
 
diff --git a/drivers/edac/fsl_ddr_edac.c b/drivers/edac/fsl_ddr_edac.c
index b81757555a8a..d148d262d0d4 100644
--- a/drivers/edac/fsl_ddr_edac.c
+++ b/drivers/edac/fsl_ddr_edac.c
@@ -612,7 +612,7 @@ err:
 	return res;
 }
 
-int fsl_mc_err_remove(struct platform_device *op)
+void fsl_mc_err_remove(struct platform_device *op)
 {
 	struct mem_ctl_info *mci = dev_get_drvdata(&op->dev);
 	struct fsl_mc_pdata *pdata = mci->pvt_info;
@@ -629,5 +629,4 @@ int fsl_mc_err_remove(struct platform_device *op)
 
 	edac_mc_del_mc(&op->dev);
 	edac_mc_free(mci);
-	return 0;
 }
diff --git a/drivers/edac/fsl_ddr_edac.h b/drivers/edac/fsl_ddr_edac.h
index 332439d7b2d9..c0994a2a003c 100644
--- a/drivers/edac/fsl_ddr_edac.h
+++ b/drivers/edac/fsl_ddr_edac.h
@@ -72,5 +72,5 @@ struct fsl_mc_pdata {
 	int irq;
 };
 int fsl_mc_err_probe(struct platform_device *op);
-int fsl_mc_err_remove(struct platform_device *op);
+void fsl_mc_err_remove(struct platform_device *op);
 #endif
diff --git a/drivers/edac/highbank_l2_edac.c b/drivers/edac/highbank_l2_edac.c
index 140d4431bd0d..5646c049a934 100644
--- a/drivers/edac/highbank_l2_edac.c
+++ b/drivers/edac/highbank_l2_edac.c
@@ -118,18 +118,17 @@ err:
 	return res;
 }
 
-static int highbank_l2_err_remove(struct platform_device *pdev)
+static void highbank_l2_err_remove(struct platform_device *pdev)
 {
 	struct edac_device_ctl_info *dci = platform_get_drvdata(pdev);
 
 	edac_device_del_device(&pdev->dev);
 	edac_device_free_ctl_info(dci);
-	return 0;
 }
 
 static struct platform_driver highbank_l2_edac_driver = {
 	.probe = highbank_l2_err_probe,
-	.remove = highbank_l2_err_remove,
+	.remove_new = highbank_l2_err_remove,
 	.driver = {
 		.name = "hb_l2_edac",
 		.of_match_table = hb_l2_err_of_match,
diff --git a/drivers/edac/highbank_mc_edac.c b/drivers/edac/highbank_mc_edac.c
index a0c04a7f95e9..1c5b888ab11d 100644
--- a/drivers/edac/highbank_mc_edac.c
+++ b/drivers/edac/highbank_mc_edac.c
@@ -251,18 +251,17 @@ free:
 	return res;
 }
 
-static int highbank_mc_remove(struct platform_device *pdev)
+static void highbank_mc_remove(struct platform_device *pdev)
 {
 	struct mem_ctl_info *mci = platform_get_drvdata(pdev);
 
 	edac_mc_del_mc(&pdev->dev);
 	edac_mc_free(mci);
-	return 0;
 }
 
 static struct platform_driver highbank_mc_edac_driver = {
 	.probe = highbank_mc_probe,
-	.remove = highbank_mc_remove,
+	.remove_new = highbank_mc_remove,
 	.driver = {
 		.name = "hb_mc_edac",
 		.of_match_table = hb_ddr_ctrl_of_match,
diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c
index 23d25724bae4..91e0a88ef904 100644
--- a/drivers/edac/i7core_edac.c
+++ b/drivers/edac/i7core_edac.c
@@ -376,7 +376,7 @@ static const struct pci_id_table pci_dev_table[] = {
 	PCI_ID_TABLE_ENTRY(pci_dev_descr_i7core_nehalem),
 	PCI_ID_TABLE_ENTRY(pci_dev_descr_lynnfield),
 	PCI_ID_TABLE_ENTRY(pci_dev_descr_i7core_westmere),
-	{0,}			/* 0 terminated list. */
+	{ NULL, }
 };
 
 /*
@@ -385,7 +385,7 @@ static const struct pci_id_table pci_dev_table[] = {
 static const struct pci_device_id i7core_pci_tbl[] = {
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_X58_HUB_MGMT)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_LYNNFIELD_QPI_LINK0)},
-	{0,}			/* 0 terminated list. */
+	{ 0, }
 };
 
 /****************************************************************************
diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c
index 1a18693294db..2b0ecdeba5cd 100644
--- a/drivers/edac/igen6_edac.c
+++ b/drivers/edac/igen6_edac.c
@@ -58,6 +58,7 @@
 /* Capability register E */
 #define CAPID_E_OFFSET			0xf0
 #define CAPID_E_IBECC			BIT(12)
+#define CAPID_E_IBECC_BIT18		BIT(18)
 
 /* Error Status */
 #define ERRSTS_OFFSET			0xc8
@@ -80,6 +81,7 @@
 #define ECC_ERROR_LOG_UE		BIT_ULL(63)
 #define ECC_ERROR_LOG_ADDR_SHIFT	5
 #define ECC_ERROR_LOG_ADDR(v)		GET_BITFIELD(v, 5, 38)
+#define ECC_ERROR_LOG_ADDR45(v)		GET_BITFIELD(v, 5, 45)
 #define ECC_ERROR_LOG_SYND(v)		GET_BITFIELD(v, 46, 61)
 
 /* Host MMIO base address */
@@ -133,6 +135,8 @@ static struct res_config {
 	u32 ibecc_base;
 	u32 ibecc_error_log_offset;
 	bool (*ibecc_available)(struct pci_dev *pdev);
+	/* Extract error address logged in IBECC */
+	u64 (*err_addr)(u64 ecclog);
 	/* Convert error address logged in IBECC to system physical address */
 	u64 (*err_addr_to_sys_addr)(u64 eaddr, int mc);
 	/* Convert error address logged in IBECC to integrated memory controller address */
@@ -222,6 +226,67 @@ static struct work_struct ecclog_work;
 #define DID_ADL_SKU3	0x4621
 #define DID_ADL_SKU4	0x4641
 
+/* Compute die IDs for Alder Lake-N with IBECC */
+#define DID_ADL_N_SKU1	0x4614
+#define DID_ADL_N_SKU2	0x4617
+#define DID_ADL_N_SKU3	0x461b
+#define DID_ADL_N_SKU4	0x461c
+#define DID_ADL_N_SKU5	0x4673
+#define DID_ADL_N_SKU6	0x4674
+#define DID_ADL_N_SKU7	0x4675
+#define DID_ADL_N_SKU8	0x4677
+#define DID_ADL_N_SKU9	0x4678
+#define DID_ADL_N_SKU10	0x4679
+#define DID_ADL_N_SKU11	0x467c
+
+/* Compute die IDs for Raptor Lake-P with IBECC */
+#define DID_RPL_P_SKU1	0xa706
+#define DID_RPL_P_SKU2	0xa707
+#define DID_RPL_P_SKU3	0xa708
+#define DID_RPL_P_SKU4	0xa716
+#define DID_RPL_P_SKU5	0xa718
+
+/* Compute die IDs for Meteor Lake-PS with IBECC */
+#define DID_MTL_PS_SKU1	0x7d21
+#define DID_MTL_PS_SKU2	0x7d22
+#define DID_MTL_PS_SKU3	0x7d23
+#define DID_MTL_PS_SKU4	0x7d24
+
+/* Compute die IDs for Meteor Lake-P with IBECC */
+#define DID_MTL_P_SKU1	0x7d01
+#define DID_MTL_P_SKU2	0x7d02
+#define DID_MTL_P_SKU3	0x7d14
+
+static int get_mchbar(struct pci_dev *pdev, u64 *mchbar)
+{
+	union  {
+		u64 v;
+		struct {
+			u32 v_lo;
+			u32 v_hi;
+		};
+	} u;
+
+	if (pci_read_config_dword(pdev, MCHBAR_OFFSET, &u.v_lo)) {
+		igen6_printk(KERN_ERR, "Failed to read lower MCHBAR\n");
+		return -ENODEV;
+	}
+
+	if (pci_read_config_dword(pdev, MCHBAR_OFFSET + 4, &u.v_hi)) {
+		igen6_printk(KERN_ERR, "Failed to read upper MCHBAR\n");
+		return -ENODEV;
+	}
+
+	if (!(u.v & MCHBAR_EN)) {
+		igen6_printk(KERN_ERR, "MCHBAR is disabled\n");
+		return -ENODEV;
+	}
+
+	*mchbar = MCHBAR_BASE(u.v);
+
+	return 0;
+}
+
 static bool ehl_ibecc_available(struct pci_dev *pdev)
 {
 	u32 v;
@@ -272,6 +337,39 @@ static bool tgl_ibecc_available(struct pci_dev *pdev)
 	return !(CAPID_E_IBECC & v);
 }
 
+static bool mtl_p_ibecc_available(struct pci_dev *pdev)
+{
+	u32 v;
+
+	if (pci_read_config_dword(pdev, CAPID_E_OFFSET, &v))
+		return false;
+
+	return !(CAPID_E_IBECC_BIT18 & v);
+}
+
+static bool mtl_ps_ibecc_available(struct pci_dev *pdev)
+{
+#define MCHBAR_MEMSS_IBECCDIS	0x13c00
+	void __iomem *window;
+	u64 mchbar;
+	u32 val;
+
+	if (get_mchbar(pdev, &mchbar))
+		return false;
+
+	window = ioremap(mchbar, MCHBAR_SIZE * 2);
+	if (!window) {
+		igen6_printk(KERN_ERR, "Failed to ioremap 0x%llx\n", mchbar);
+		return false;
+	}
+
+	val = readl(window + MCHBAR_MEMSS_IBECCDIS);
+	iounmap(window);
+
+	/* Bit6: 1 - IBECC is disabled, 0 - IBECC isn't disabled */
+	return !GET_BITFIELD(val, 6, 6);
+}
+
 static u64 mem_addr_to_sys_addr(u64 maddr)
 {
 	if (maddr < igen6_tolud)
@@ -358,6 +456,11 @@ static u64 adl_err_addr_to_imc_addr(u64 eaddr, int mc)
 	return imc_addr;
 }
 
+static u64 rpl_p_err_addr(u64 ecclog)
+{
+	return ECC_ERROR_LOG_ADDR45(ecclog);
+}
+
 static struct res_config ehl_cfg = {
 	.num_imc		= 1,
 	.imc_base		= 0x5000,
@@ -403,6 +506,51 @@ static struct res_config adl_cfg = {
 	.err_addr_to_imc_addr	= adl_err_addr_to_imc_addr,
 };
 
+static struct res_config adl_n_cfg = {
+	.machine_check		= true,
+	.num_imc		= 1,
+	.imc_base		= 0xd800,
+	.ibecc_base		= 0xd400,
+	.ibecc_error_log_offset	= 0x68,
+	.ibecc_available	= tgl_ibecc_available,
+	.err_addr_to_sys_addr	= adl_err_addr_to_sys_addr,
+	.err_addr_to_imc_addr	= adl_err_addr_to_imc_addr,
+};
+
+static struct res_config rpl_p_cfg = {
+	.machine_check		= true,
+	.num_imc		= 2,
+	.imc_base		= 0xd800,
+	.ibecc_base		= 0xd400,
+	.ibecc_error_log_offset	= 0x68,
+	.ibecc_available	= tgl_ibecc_available,
+	.err_addr		= rpl_p_err_addr,
+	.err_addr_to_sys_addr	= adl_err_addr_to_sys_addr,
+	.err_addr_to_imc_addr	= adl_err_addr_to_imc_addr,
+};
+
+static struct res_config mtl_ps_cfg = {
+	.machine_check		= true,
+	.num_imc		= 2,
+	.imc_base		= 0xd800,
+	.ibecc_base		= 0xd400,
+	.ibecc_error_log_offset	= 0x170,
+	.ibecc_available	= mtl_ps_ibecc_available,
+	.err_addr_to_sys_addr	= adl_err_addr_to_sys_addr,
+	.err_addr_to_imc_addr	= adl_err_addr_to_imc_addr,
+};
+
+static struct res_config mtl_p_cfg = {
+	.machine_check		= true,
+	.num_imc		= 2,
+	.imc_base		= 0xd800,
+	.ibecc_base		= 0xd400,
+	.ibecc_error_log_offset	= 0x170,
+	.ibecc_available	= mtl_p_ibecc_available,
+	.err_addr_to_sys_addr	= adl_err_addr_to_sys_addr,
+	.err_addr_to_imc_addr	= adl_err_addr_to_imc_addr,
+};
+
 static const struct pci_device_id igen6_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, DID_EHL_SKU5), (kernel_ulong_t)&ehl_cfg },
 	{ PCI_VDEVICE(INTEL, DID_EHL_SKU6), (kernel_ulong_t)&ehl_cfg },
@@ -424,6 +572,29 @@ static const struct pci_device_id igen6_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, DID_ADL_SKU2), (kernel_ulong_t)&adl_cfg },
 	{ PCI_VDEVICE(INTEL, DID_ADL_SKU3), (kernel_ulong_t)&adl_cfg },
 	{ PCI_VDEVICE(INTEL, DID_ADL_SKU4), (kernel_ulong_t)&adl_cfg },
+	{ PCI_VDEVICE(INTEL, DID_ADL_N_SKU1), (kernel_ulong_t)&adl_n_cfg },
+	{ PCI_VDEVICE(INTEL, DID_ADL_N_SKU2), (kernel_ulong_t)&adl_n_cfg },
+	{ PCI_VDEVICE(INTEL, DID_ADL_N_SKU3), (kernel_ulong_t)&adl_n_cfg },
+	{ PCI_VDEVICE(INTEL, DID_ADL_N_SKU4), (kernel_ulong_t)&adl_n_cfg },
+	{ PCI_VDEVICE(INTEL, DID_ADL_N_SKU5), (kernel_ulong_t)&adl_n_cfg },
+	{ PCI_VDEVICE(INTEL, DID_ADL_N_SKU6), (kernel_ulong_t)&adl_n_cfg },
+	{ PCI_VDEVICE(INTEL, DID_ADL_N_SKU7), (kernel_ulong_t)&adl_n_cfg },
+	{ PCI_VDEVICE(INTEL, DID_ADL_N_SKU8), (kernel_ulong_t)&adl_n_cfg },
+	{ PCI_VDEVICE(INTEL, DID_ADL_N_SKU9), (kernel_ulong_t)&adl_n_cfg },
+	{ PCI_VDEVICE(INTEL, DID_ADL_N_SKU10), (kernel_ulong_t)&adl_n_cfg },
+	{ PCI_VDEVICE(INTEL, DID_ADL_N_SKU11), (kernel_ulong_t)&adl_n_cfg },
+	{ PCI_VDEVICE(INTEL, DID_RPL_P_SKU1), (kernel_ulong_t)&rpl_p_cfg },
+	{ PCI_VDEVICE(INTEL, DID_RPL_P_SKU2), (kernel_ulong_t)&rpl_p_cfg },
+	{ PCI_VDEVICE(INTEL, DID_RPL_P_SKU3), (kernel_ulong_t)&rpl_p_cfg },
+	{ PCI_VDEVICE(INTEL, DID_RPL_P_SKU4), (kernel_ulong_t)&rpl_p_cfg },
+	{ PCI_VDEVICE(INTEL, DID_RPL_P_SKU5), (kernel_ulong_t)&rpl_p_cfg },
+	{ PCI_VDEVICE(INTEL, DID_MTL_PS_SKU1), (kernel_ulong_t)&mtl_ps_cfg },
+	{ PCI_VDEVICE(INTEL, DID_MTL_PS_SKU2), (kernel_ulong_t)&mtl_ps_cfg },
+	{ PCI_VDEVICE(INTEL, DID_MTL_PS_SKU3), (kernel_ulong_t)&mtl_ps_cfg },
+	{ PCI_VDEVICE(INTEL, DID_MTL_PS_SKU4), (kernel_ulong_t)&mtl_ps_cfg },
+	{ PCI_VDEVICE(INTEL, DID_MTL_P_SKU1), (kernel_ulong_t)&mtl_p_cfg },
+	{ PCI_VDEVICE(INTEL, DID_MTL_P_SKU2), (kernel_ulong_t)&mtl_p_cfg },
+	{ PCI_VDEVICE(INTEL, DID_MTL_P_SKU3), (kernel_ulong_t)&mtl_p_cfg },
 	{ },
 };
 MODULE_DEVICE_TABLE(pci, igen6_pci_tbl);
@@ -679,8 +850,11 @@ static void ecclog_work_cb(struct work_struct *work)
 
 	llist_for_each_entry_safe(node, tmp, head, llnode) {
 		memset(&res, 0, sizeof(res));
-		eaddr = ECC_ERROR_LOG_ADDR(node->ecclog) <<
-			ECC_ERROR_LOG_ADDR_SHIFT;
+		if (res_cfg->err_addr)
+			eaddr = res_cfg->err_addr(node->ecclog);
+		else
+			eaddr = ECC_ERROR_LOG_ADDR(node->ecclog) <<
+				ECC_ERROR_LOG_ADDR_SHIFT;
 		res.mc	     = node->mc;
 		res.sys_addr = res_cfg->err_addr_to_sys_addr(eaddr, res.mc);
 		res.imc_addr = res_cfg->err_addr_to_imc_addr(eaddr, res.mc);
@@ -969,22 +1143,8 @@ static int igen6_pci_setup(struct pci_dev *pdev, u64 *mchbar)
 
 	igen6_tom = u.v & GENMASK_ULL(38, 20);
 
-	if (pci_read_config_dword(pdev, MCHBAR_OFFSET, &u.v_lo)) {
-		igen6_printk(KERN_ERR, "Failed to read lower MCHBAR\n");
+	if (get_mchbar(pdev, mchbar))
 		goto fail;
-	}
-
-	if (pci_read_config_dword(pdev, MCHBAR_OFFSET + 4, &u.v_hi)) {
-		igen6_printk(KERN_ERR, "Failed to read upper MCHBAR\n");
-		goto fail;
-	}
-
-	if (!(u.v & MCHBAR_EN)) {
-		igen6_printk(KERN_ERR, "MCHBAR is disabled\n");
-		goto fail;
-	}
-
-	*mchbar = MCHBAR_BASE(u.v);
 
 #ifdef CONFIG_EDAC_DEBUG
 	if (pci_read_config_dword(pdev, TOUUD_OFFSET, &u.v_lo))
diff --git a/drivers/edac/layerscape_edac.c b/drivers/edac/layerscape_edac.c
index 7c5e2b3c0daa..d2f895033280 100644
--- a/drivers/edac/layerscape_edac.c
+++ b/drivers/edac/layerscape_edac.c
@@ -27,7 +27,7 @@ MODULE_DEVICE_TABLE(of, fsl_ddr_mc_err_of_match);
 
 static struct platform_driver fsl_ddr_mc_err_driver = {
 	.probe = fsl_mc_err_probe,
-	.remove = fsl_mc_err_remove,
+	.remove_new = fsl_mc_err_remove,
 	.driver = {
 		.name = "fsl_ddr_mc_err",
 		.of_match_table = fsl_ddr_mc_err_of_match,
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index 9215c06783df..ec8b6c9fedfd 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -143,482 +143,6 @@ static const char * const mc6_mce_desc[] = {
 	"Status Register File",
 };
 
-/* Scalable MCA error strings */
-static const char * const smca_ls_mce_desc[] = {
-	"Load queue parity error",
-	"Store queue parity error",
-	"Miss address buffer payload parity error",
-	"Level 1 TLB parity error",
-	"DC Tag error type 5",
-	"DC Tag error type 6",
-	"DC Tag error type 1",
-	"Internal error type 1",
-	"Internal error type 2",
-	"System Read Data Error Thread 0",
-	"System Read Data Error Thread 1",
-	"DC Tag error type 2",
-	"DC Data error type 1 and poison consumption",
-	"DC Data error type 2",
-	"DC Data error type 3",
-	"DC Tag error type 4",
-	"Level 2 TLB parity error",
-	"PDC parity error",
-	"DC Tag error type 3",
-	"DC Tag error type 5",
-	"L2 Fill Data error",
-};
-
-static const char * const smca_ls2_mce_desc[] = {
-	"An ECC error was detected on a data cache read by a probe or victimization",
-	"An ECC error or L2 poison was detected on a data cache read by a load",
-	"An ECC error was detected on a data cache read-modify-write by a store",
-	"An ECC error or poison bit mismatch was detected on a tag read by a probe or victimization",
-	"An ECC error or poison bit mismatch was detected on a tag read by a load",
-	"An ECC error or poison bit mismatch was detected on a tag read by a store",
-	"An ECC error was detected on an EMEM read by a load",
-	"An ECC error was detected on an EMEM read-modify-write by a store",
-	"A parity error was detected in an L1 TLB entry by any access",
-	"A parity error was detected in an L2 TLB entry by any access",
-	"A parity error was detected in a PWC entry by any access",
-	"A parity error was detected in an STQ entry by any access",
-	"A parity error was detected in an LDQ entry by any access",
-	"A parity error was detected in a MAB entry by any access",
-	"A parity error was detected in an SCB entry state field by any access",
-	"A parity error was detected in an SCB entry address field by any access",
-	"A parity error was detected in an SCB entry data field by any access",
-	"A parity error was detected in a WCB entry by any access",
-	"A poisoned line was detected in an SCB entry by any access",
-	"A SystemReadDataError error was reported on read data returned from L2 for a load",
-	"A SystemReadDataError error was reported on read data returned from L2 for an SCB store",
-	"A SystemReadDataError error was reported on read data returned from L2 for a WCB store",
-	"A hardware assertion error was reported",
-	"A parity error was detected in an STLF, SCB EMEM entry or SRB store data by any access",
-};
-
-static const char * const smca_if_mce_desc[] = {
-	"Op Cache Microtag Probe Port Parity Error",
-	"IC Microtag or Full Tag Multi-hit Error",
-	"IC Full Tag Parity Error",
-	"IC Data Array Parity Error",
-	"Decoupling Queue PhysAddr Parity Error",
-	"L0 ITLB Parity Error",
-	"L1 ITLB Parity Error",
-	"L2 ITLB Parity Error",
-	"BPQ Thread 0 Snoop Parity Error",
-	"BPQ Thread 1 Snoop Parity Error",
-	"L1 BTB Multi-Match Error",
-	"L2 BTB Multi-Match Error",
-	"L2 Cache Response Poison Error",
-	"System Read Data Error",
-	"Hardware Assertion Error",
-	"L1-TLB Multi-Hit",
-	"L2-TLB Multi-Hit",
-	"BSR Parity Error",
-	"CT MCE",
-};
-
-static const char * const smca_l2_mce_desc[] = {
-	"L2M Tag Multiple-Way-Hit error",
-	"L2M Tag or State Array ECC Error",
-	"L2M Data Array ECC Error",
-	"Hardware Assert Error",
-};
-
-static const char * const smca_de_mce_desc[] = {
-	"Micro-op cache tag parity error",
-	"Micro-op cache data parity error",
-	"Instruction buffer parity error",
-	"Micro-op queue parity error",
-	"Instruction dispatch queue parity error",
-	"Fetch address FIFO parity error",
-	"Patch RAM data parity error",
-	"Patch RAM sequencer parity error",
-	"Micro-op buffer parity error",
-	"Hardware Assertion MCA Error",
-};
-
-static const char * const smca_ex_mce_desc[] = {
-	"Watchdog Timeout error",
-	"Physical register file parity error",
-	"Flag register file parity error",
-	"Immediate displacement register file parity error",
-	"Address generator payload parity error",
-	"EX payload parity error",
-	"Checkpoint queue parity error",
-	"Retire dispatch queue parity error",
-	"Retire status queue parity error",
-	"Scheduling queue parity error",
-	"Branch buffer queue parity error",
-	"Hardware Assertion error",
-	"Spec Map parity error",
-	"Retire Map parity error",
-};
-
-static const char * const smca_fp_mce_desc[] = {
-	"Physical register file (PRF) parity error",
-	"Freelist (FL) parity error",
-	"Schedule queue parity error",
-	"NSQ parity error",
-	"Retire queue (RQ) parity error",
-	"Status register file (SRF) parity error",
-	"Hardware assertion",
-};
-
-static const char * const smca_l3_mce_desc[] = {
-	"Shadow Tag Macro ECC Error",
-	"Shadow Tag Macro Multi-way-hit Error",
-	"L3M Tag ECC Error",
-	"L3M Tag Multi-way-hit Error",
-	"L3M Data ECC Error",
-	"SDP Parity Error or SystemReadDataError from XI",
-	"L3 Victim Queue Parity Error",
-	"L3 Hardware Assertion",
-};
-
-static const char * const smca_cs_mce_desc[] = {
-	"Illegal Request",
-	"Address Violation",
-	"Security Violation",
-	"Illegal Response",
-	"Unexpected Response",
-	"Request or Probe Parity Error",
-	"Read Response Parity Error",
-	"Atomic Request Parity Error",
-	"Probe Filter ECC Error",
-};
-
-static const char * const smca_cs2_mce_desc[] = {
-	"Illegal Request",
-	"Address Violation",
-	"Security Violation",
-	"Illegal Response",
-	"Unexpected Response",
-	"Request or Probe Parity Error",
-	"Read Response Parity Error",
-	"Atomic Request Parity Error",
-	"SDP read response had no match in the CS queue",
-	"Probe Filter Protocol Error",
-	"Probe Filter ECC Error",
-	"SDP read response had an unexpected RETRY error",
-	"Counter overflow error",
-	"Counter underflow error",
-};
-
-static const char * const smca_pie_mce_desc[] = {
-	"Hardware Assert",
-	"Register security violation",
-	"Link Error",
-	"Poison data consumption",
-	"A deferred error was detected in the DF"
-};
-
-static const char * const smca_umc_mce_desc[] = {
-	"DRAM ECC error",
-	"Data poison error",
-	"SDP parity error",
-	"Advanced peripheral bus error",
-	"Address/Command parity error",
-	"Write data CRC error",
-	"DCQ SRAM ECC error",
-	"AES SRAM ECC error",
-};
-
-static const char * const smca_umc2_mce_desc[] = {
-	"DRAM ECC error",
-	"Data poison error",
-	"SDP parity error",
-	"Reserved",
-	"Address/Command parity error",
-	"Write data parity error",
-	"DCQ SRAM ECC error",
-	"Reserved",
-	"Read data parity error",
-	"Rdb SRAM ECC error",
-	"RdRsp SRAM ECC error",
-	"LM32 MP errors",
-};
-
-static const char * const smca_pb_mce_desc[] = {
-	"An ECC error in the Parameter Block RAM array",
-};
-
-static const char * const smca_psp_mce_desc[] = {
-	"An ECC or parity error in a PSP RAM instance",
-};
-
-static const char * const smca_psp2_mce_desc[] = {
-	"High SRAM ECC or parity error",
-	"Low SRAM ECC or parity error",
-	"Instruction Cache Bank 0 ECC or parity error",
-	"Instruction Cache Bank 1 ECC or parity error",
-	"Instruction Tag Ram 0 parity error",
-	"Instruction Tag Ram 1 parity error",
-	"Data Cache Bank 0 ECC or parity error",
-	"Data Cache Bank 1 ECC or parity error",
-	"Data Cache Bank 2 ECC or parity error",
-	"Data Cache Bank 3 ECC or parity error",
-	"Data Tag Bank 0 parity error",
-	"Data Tag Bank 1 parity error",
-	"Data Tag Bank 2 parity error",
-	"Data Tag Bank 3 parity error",
-	"Dirty Data Ram parity error",
-	"TLB Bank 0 parity error",
-	"TLB Bank 1 parity error",
-	"System Hub Read Buffer ECC or parity error",
-};
-
-static const char * const smca_smu_mce_desc[] = {
-	"An ECC or parity error in an SMU RAM instance",
-};
-
-static const char * const smca_smu2_mce_desc[] = {
-	"High SRAM ECC or parity error",
-	"Low SRAM ECC or parity error",
-	"Data Cache Bank A ECC or parity error",
-	"Data Cache Bank B ECC or parity error",
-	"Data Tag Cache Bank A ECC or parity error",
-	"Data Tag Cache Bank B ECC or parity error",
-	"Instruction Cache Bank A ECC or parity error",
-	"Instruction Cache Bank B ECC or parity error",
-	"Instruction Tag Cache Bank A ECC or parity error",
-	"Instruction Tag Cache Bank B ECC or parity error",
-	"System Hub Read Buffer ECC or parity error",
-	"PHY RAM ECC error",
-};
-
-static const char * const smca_mp5_mce_desc[] = {
-	"High SRAM ECC or parity error",
-	"Low SRAM ECC or parity error",
-	"Data Cache Bank A ECC or parity error",
-	"Data Cache Bank B ECC or parity error",
-	"Data Tag Cache Bank A ECC or parity error",
-	"Data Tag Cache Bank B ECC or parity error",
-	"Instruction Cache Bank A ECC or parity error",
-	"Instruction Cache Bank B ECC or parity error",
-	"Instruction Tag Cache Bank A ECC or parity error",
-	"Instruction Tag Cache Bank B ECC or parity error",
-};
-
-static const char * const smca_mpdma_mce_desc[] = {
-	"Main SRAM [31:0] bank ECC or parity error",
-	"Main SRAM [63:32] bank ECC or parity error",
-	"Main SRAM [95:64] bank ECC or parity error",
-	"Main SRAM [127:96] bank ECC or parity error",
-	"Data Cache Bank A ECC or parity error",
-	"Data Cache Bank B ECC or parity error",
-	"Data Tag Cache Bank A ECC or parity error",
-	"Data Tag Cache Bank B ECC or parity error",
-	"Instruction Cache Bank A ECC or parity error",
-	"Instruction Cache Bank B ECC or parity error",
-	"Instruction Tag Cache Bank A ECC or parity error",
-	"Instruction Tag Cache Bank B ECC or parity error",
-	"Data Cache Bank A ECC or parity error",
-	"Data Cache Bank B ECC or parity error",
-	"Data Tag Cache Bank A ECC or parity error",
-	"Data Tag Cache Bank B ECC or parity error",
-	"Instruction Cache Bank A ECC or parity error",
-	"Instruction Cache Bank B ECC or parity error",
-	"Instruction Tag Cache Bank A ECC or parity error",
-	"Instruction Tag Cache Bank B ECC or parity error",
-	"Data Cache Bank A ECC or parity error",
-	"Data Cache Bank B ECC or parity error",
-	"Data Tag Cache Bank A ECC or parity error",
-	"Data Tag Cache Bank B ECC or parity error",
-	"Instruction Cache Bank A ECC or parity error",
-	"Instruction Cache Bank B ECC or parity error",
-	"Instruction Tag Cache Bank A ECC or parity error",
-	"Instruction Tag Cache Bank B ECC or parity error",
-	"System Hub Read Buffer ECC or parity error",
-	"MPDMA TVF DVSEC Memory ECC or parity error",
-	"MPDMA TVF MMIO Mailbox0 ECC or parity error",
-	"MPDMA TVF MMIO Mailbox1 ECC or parity error",
-	"MPDMA TVF Doorbell Memory ECC or parity error",
-	"MPDMA TVF SDP Slave Memory 0 ECC or parity error",
-	"MPDMA TVF SDP Slave Memory 1 ECC or parity error",
-	"MPDMA TVF SDP Slave Memory 2 ECC or parity error",
-	"MPDMA TVF SDP Master Memory 0 ECC or parity error",
-	"MPDMA TVF SDP Master Memory 1 ECC or parity error",
-	"MPDMA TVF SDP Master Memory 2 ECC or parity error",
-	"MPDMA TVF SDP Master Memory 3 ECC or parity error",
-	"MPDMA TVF SDP Master Memory 4 ECC or parity error",
-	"MPDMA TVF SDP Master Memory 5 ECC or parity error",
-	"MPDMA TVF SDP Master Memory 6 ECC or parity error",
-	"MPDMA PTE Command FIFO ECC or parity error",
-	"MPDMA PTE Hub Data FIFO ECC or parity error",
-	"MPDMA PTE Internal Data FIFO ECC or parity error",
-	"MPDMA PTE Command Memory DMA ECC or parity error",
-	"MPDMA PTE Command Memory Internal ECC or parity error",
-	"MPDMA PTE DMA Completion FIFO ECC or parity error",
-	"MPDMA PTE Tablewalk Completion FIFO ECC or parity error",
-	"MPDMA PTE Descriptor Completion FIFO ECC or parity error",
-	"MPDMA PTE ReadOnly Completion FIFO ECC or parity error",
-	"MPDMA PTE DirectWrite Completion FIFO ECC or parity error",
-	"SDP Watchdog Timer expired",
-};
-
-static const char * const smca_nbio_mce_desc[] = {
-	"ECC or Parity error",
-	"PCIE error",
-	"SDP ErrEvent error",
-	"SDP Egress Poison Error",
-	"IOHC Internal Poison Error",
-};
-
-static const char * const smca_pcie_mce_desc[] = {
-	"CCIX PER Message logging",
-	"CCIX Read Response with Status: Non-Data Error",
-	"CCIX Write Response with Status: Non-Data Error",
-	"CCIX Read Response with Status: Data Error",
-	"CCIX Non-okay write response with data error",
-};
-
-static const char * const smca_pcie2_mce_desc[] = {
-	"SDP Parity Error logging",
-};
-
-static const char * const smca_xgmipcs_mce_desc[] = {
-	"Data Loss Error",
-	"Training Error",
-	"Flow Control Acknowledge Error",
-	"Rx Fifo Underflow Error",
-	"Rx Fifo Overflow Error",
-	"CRC Error",
-	"BER Exceeded Error",
-	"Tx Vcid Data Error",
-	"Replay Buffer Parity Error",
-	"Data Parity Error",
-	"Replay Fifo Overflow Error",
-	"Replay Fifo Underflow Error",
-	"Elastic Fifo Overflow Error",
-	"Deskew Error",
-	"Flow Control CRC Error",
-	"Data Startup Limit Error",
-	"FC Init Timeout Error",
-	"Recovery Timeout Error",
-	"Ready Serial Timeout Error",
-	"Ready Serial Attempt Error",
-	"Recovery Attempt Error",
-	"Recovery Relock Attempt Error",
-	"Replay Attempt Error",
-	"Sync Header Error",
-	"Tx Replay Timeout Error",
-	"Rx Replay Timeout Error",
-	"LinkSub Tx Timeout Error",
-	"LinkSub Rx Timeout Error",
-	"Rx CMD Packet Error",
-};
-
-static const char * const smca_xgmiphy_mce_desc[] = {
-	"RAM ECC Error",
-	"ARC instruction buffer parity error",
-	"ARC data buffer parity error",
-	"PHY APB error",
-};
-
-static const char * const smca_nbif_mce_desc[] = {
-	"Timeout error from GMI",
-	"SRAM ECC error",
-	"NTB Error Event",
-	"SDP Parity error",
-};
-
-static const char * const smca_sata_mce_desc[] = {
-	"Parity error for port 0",
-	"Parity error for port 1",
-	"Parity error for port 2",
-	"Parity error for port 3",
-	"Parity error for port 4",
-	"Parity error for port 5",
-	"Parity error for port 6",
-	"Parity error for port 7",
-};
-
-static const char * const smca_usb_mce_desc[] = {
-	"Parity error or ECC error for S0 RAM0",
-	"Parity error or ECC error for S0 RAM1",
-	"Parity error or ECC error for S0 RAM2",
-	"Parity error for PHY RAM0",
-	"Parity error for PHY RAM1",
-	"AXI Slave Response error",
-};
-
-static const char * const smca_gmipcs_mce_desc[] = {
-	"Data Loss Error",
-	"Training Error",
-	"Replay Parity Error",
-	"Rx Fifo Underflow Error",
-	"Rx Fifo Overflow Error",
-	"CRC Error",
-	"BER Exceeded Error",
-	"Tx Fifo Underflow Error",
-	"Replay Buffer Parity Error",
-	"Tx Overflow Error",
-	"Replay Fifo Overflow Error",
-	"Replay Fifo Underflow Error",
-	"Elastic Fifo Overflow Error",
-	"Deskew Error",
-	"Offline Error",
-	"Data Startup Limit Error",
-	"FC Init Timeout Error",
-	"Recovery Timeout Error",
-	"Ready Serial Timeout Error",
-	"Ready Serial Attempt Error",
-	"Recovery Attempt Error",
-	"Recovery Relock Attempt Error",
-	"Deskew Abort Error",
-	"Rx Buffer Error",
-	"Rx LFDS Fifo Overflow Error",
-	"Rx LFDS Fifo Underflow Error",
-	"LinkSub Tx Timeout Error",
-	"LinkSub Rx Timeout Error",
-	"Rx CMD Packet Error",
-	"LFDS Training Timeout Error",
-	"LFDS FC Init Timeout Error",
-	"Data Loss Error",
-};
-
-struct smca_mce_desc {
-	const char * const *descs;
-	unsigned int num_descs;
-};
-
-static struct smca_mce_desc smca_mce_descs[] = {
-	[SMCA_LS]	= { smca_ls_mce_desc,	ARRAY_SIZE(smca_ls_mce_desc)	},
-	[SMCA_LS_V2]	= { smca_ls2_mce_desc,	ARRAY_SIZE(smca_ls2_mce_desc)	},
-	[SMCA_IF]	= { smca_if_mce_desc,	ARRAY_SIZE(smca_if_mce_desc)	},
-	[SMCA_L2_CACHE]	= { smca_l2_mce_desc,	ARRAY_SIZE(smca_l2_mce_desc)	},
-	[SMCA_DE]	= { smca_de_mce_desc,	ARRAY_SIZE(smca_de_mce_desc)	},
-	[SMCA_EX]	= { smca_ex_mce_desc,	ARRAY_SIZE(smca_ex_mce_desc)	},
-	[SMCA_FP]	= { smca_fp_mce_desc,	ARRAY_SIZE(smca_fp_mce_desc)	},
-	[SMCA_L3_CACHE]	= { smca_l3_mce_desc,	ARRAY_SIZE(smca_l3_mce_desc)	},
-	[SMCA_CS]	= { smca_cs_mce_desc,	ARRAY_SIZE(smca_cs_mce_desc)	},
-	[SMCA_CS_V2]	= { smca_cs2_mce_desc,	ARRAY_SIZE(smca_cs2_mce_desc)	},
-	[SMCA_PIE]	= { smca_pie_mce_desc,	ARRAY_SIZE(smca_pie_mce_desc)	},
-	[SMCA_UMC]	= { smca_umc_mce_desc,	ARRAY_SIZE(smca_umc_mce_desc)	},
-	[SMCA_UMC_V2]	= { smca_umc2_mce_desc,	ARRAY_SIZE(smca_umc2_mce_desc)	},
-	[SMCA_PB]	= { smca_pb_mce_desc,	ARRAY_SIZE(smca_pb_mce_desc)	},
-	[SMCA_PSP]	= { smca_psp_mce_desc,	ARRAY_SIZE(smca_psp_mce_desc)	},
-	[SMCA_PSP_V2]	= { smca_psp2_mce_desc,	ARRAY_SIZE(smca_psp2_mce_desc)	},
-	[SMCA_SMU]	= { smca_smu_mce_desc,	ARRAY_SIZE(smca_smu_mce_desc)	},
-	[SMCA_SMU_V2]	= { smca_smu2_mce_desc,	ARRAY_SIZE(smca_smu2_mce_desc)	},
-	[SMCA_MP5]	= { smca_mp5_mce_desc,	ARRAY_SIZE(smca_mp5_mce_desc)	},
-	[SMCA_MPDMA]	= { smca_mpdma_mce_desc,	ARRAY_SIZE(smca_mpdma_mce_desc)	},
-	[SMCA_NBIO]	= { smca_nbio_mce_desc,	ARRAY_SIZE(smca_nbio_mce_desc)	},
-	[SMCA_PCIE]	= { smca_pcie_mce_desc,	ARRAY_SIZE(smca_pcie_mce_desc)	},
-	[SMCA_PCIE_V2]	= { smca_pcie2_mce_desc,   ARRAY_SIZE(smca_pcie2_mce_desc)	},
-	[SMCA_XGMI_PCS]	= { smca_xgmipcs_mce_desc, ARRAY_SIZE(smca_xgmipcs_mce_desc)	},
-	/* NBIF and SHUB have the same error descriptions, for now. */
-	[SMCA_NBIF]	= { smca_nbif_mce_desc, ARRAY_SIZE(smca_nbif_mce_desc)	},
-	[SMCA_SHUB]	= { smca_nbif_mce_desc, ARRAY_SIZE(smca_nbif_mce_desc)	},
-	[SMCA_SATA]	= { smca_sata_mce_desc, ARRAY_SIZE(smca_sata_mce_desc)	},
-	[SMCA_USB]	= { smca_usb_mce_desc,	ARRAY_SIZE(smca_usb_mce_desc)	},
-	[SMCA_GMI_PCS]	= { smca_gmipcs_mce_desc,  ARRAY_SIZE(smca_gmipcs_mce_desc)	},
-	/* All the PHY bank types have the same error descriptions, for now. */
-	[SMCA_XGMI_PHY]	= { smca_xgmiphy_mce_desc, ARRAY_SIZE(smca_xgmiphy_mce_desc)	},
-	[SMCA_WAFL_PHY]	= { smca_xgmiphy_mce_desc, ARRAY_SIZE(smca_xgmiphy_mce_desc)	},
-	[SMCA_GMI_PHY]	= { smca_xgmiphy_mce_desc, ARRAY_SIZE(smca_xgmiphy_mce_desc)	},
-};
-
 static bool f12h_mc0_mce(u16 ec, u8 xec)
 {
 	bool ret = false;
@@ -1163,11 +687,51 @@ static void decode_mc6_mce(struct mce *m)
 	pr_emerg(HW_ERR "Corrupted MC6 MCE info?\n");
 }
 
+static const char * const smca_long_names[] = {
+	[SMCA_LS ... SMCA_LS_V2]	= "Load Store Unit",
+	[SMCA_IF]			= "Instruction Fetch Unit",
+	[SMCA_L2_CACHE]			= "L2 Cache",
+	[SMCA_DE]			= "Decode Unit",
+	[SMCA_RESERVED]			= "Reserved",
+	[SMCA_EX]			= "Execution Unit",
+	[SMCA_FP]			= "Floating Point Unit",
+	[SMCA_L3_CACHE]			= "L3 Cache",
+	[SMCA_CS ... SMCA_CS_V2]	= "Coherent Slave",
+	[SMCA_PIE]			= "Power, Interrupts, etc.",
+
+	/* UMC v2 is separate because both of them can exist in a single system. */
+	[SMCA_UMC]			= "Unified Memory Controller",
+	[SMCA_UMC_V2]			= "Unified Memory Controller v2",
+	[SMCA_PB]			= "Parameter Block",
+	[SMCA_PSP ... SMCA_PSP_V2]	= "Platform Security Processor",
+	[SMCA_SMU ... SMCA_SMU_V2]	= "System Management Unit",
+	[SMCA_MP5]			= "Microprocessor 5 Unit",
+	[SMCA_MPDMA]			= "MPDMA Unit",
+	[SMCA_NBIO]			= "Northbridge IO Unit",
+	[SMCA_PCIE ... SMCA_PCIE_V2]	= "PCI Express Unit",
+	[SMCA_XGMI_PCS]			= "Ext Global Memory Interconnect PCS Unit",
+	[SMCA_NBIF]			= "NBIF Unit",
+	[SMCA_SHUB]			= "System Hub Unit",
+	[SMCA_SATA]			= "SATA Unit",
+	[SMCA_USB]			= "USB Unit",
+	[SMCA_GMI_PCS]			= "Global Memory Interconnect PCS Unit",
+	[SMCA_XGMI_PHY]			= "Ext Global Memory Interconnect PHY Unit",
+	[SMCA_WAFL_PHY]			= "WAFL PHY Unit",
+	[SMCA_GMI_PHY]			= "Global Memory Interconnect PHY Unit",
+};
+
+static const char *smca_get_long_name(enum smca_bank_types t)
+{
+	if (t >= N_SMCA_BANK_TYPES)
+		return NULL;
+
+	return smca_long_names[t];
+}
+
 /* Decode errors according to Scalable MCA specification */
 static void decode_smca_error(struct mce *m)
 {
 	enum smca_bank_types bank_type = smca_get_bank_type(m->extcpu, m->bank);
-	const char *ip_name;
 	u8 xec = XEC(m->status, xec_mask);
 
 	if (bank_type >= N_SMCA_BANK_TYPES)
@@ -1178,13 +742,7 @@ static void decode_smca_error(struct mce *m)
 		return;
 	}
 
-	ip_name = smca_get_long_name(bank_type);
-
-	pr_emerg(HW_ERR "%s Ext. Error Code: %d", ip_name, xec);
-
-	/* Only print the decode of valid error codes */
-	if (xec < smca_mce_descs[bank_type].num_descs)
-		pr_cont(", %s.\n", smca_mce_descs[bank_type].descs[xec]);
+	pr_emerg(HW_ERR "%s Ext. Error Code: %d", smca_get_long_name(bank_type), xec);
 
 	if ((bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2) &&
 	    xec == 0 && decode_dram_ecc)
diff --git a/drivers/edac/mpc85xx_edac.c b/drivers/edac/mpc85xx_edac.c
index 2b5703e5066e..c1bc53f4e184 100644
--- a/drivers/edac/mpc85xx_edac.c
+++ b/drivers/edac/mpc85xx_edac.c
@@ -300,7 +300,7 @@ err:
 	return res;
 }
 
-static int mpc85xx_pci_err_remove(struct platform_device *op)
+static void mpc85xx_pci_err_remove(struct platform_device *op)
 {
 	struct edac_pci_ctl_info *pci = dev_get_drvdata(&op->dev);
 	struct mpc85xx_pci_pdata *pdata = pci->pvt_info;
@@ -312,8 +312,6 @@ static int mpc85xx_pci_err_remove(struct platform_device *op)
 
 	edac_pci_del_device(&op->dev);
 	edac_pci_free_ctl_info(pci);
-
-	return 0;
 }
 
 static const struct platform_device_id mpc85xx_pci_err_match[] = {
@@ -325,7 +323,7 @@ static const struct platform_device_id mpc85xx_pci_err_match[] = {
 
 static struct platform_driver mpc85xx_pci_err_driver = {
 	.probe = mpc85xx_pci_err_probe,
-	.remove = mpc85xx_pci_err_remove,
+	.remove_new = mpc85xx_pci_err_remove,
 	.id_table = mpc85xx_pci_err_match,
 	.driver = {
 		.name = "mpc85xx_pci_err",
@@ -591,7 +589,7 @@ err:
 	return res;
 }
 
-static int mpc85xx_l2_err_remove(struct platform_device *op)
+static void mpc85xx_l2_err_remove(struct platform_device *op)
 {
 	struct edac_device_ctl_info *edac_dev = dev_get_drvdata(&op->dev);
 	struct mpc85xx_l2_pdata *pdata = edac_dev->pvt_info;
@@ -606,7 +604,6 @@ static int mpc85xx_l2_err_remove(struct platform_device *op)
 	out_be32(pdata->l2_vbase + MPC85XX_L2_ERRDIS, orig_l2_err_disable);
 	edac_device_del_device(&op->dev);
 	edac_device_free_ctl_info(edac_dev);
-	return 0;
 }
 
 static const struct of_device_id mpc85xx_l2_err_of_match[] = {
@@ -630,7 +627,7 @@ MODULE_DEVICE_TABLE(of, mpc85xx_l2_err_of_match);
 
 static struct platform_driver mpc85xx_l2_err_driver = {
 	.probe = mpc85xx_l2_err_probe,
-	.remove = mpc85xx_l2_err_remove,
+	.remove_new = mpc85xx_l2_err_remove,
 	.driver = {
 		.name = "mpc85xx_l2_err",
 		.of_match_table = mpc85xx_l2_err_of_match,
@@ -659,7 +656,7 @@ MODULE_DEVICE_TABLE(of, mpc85xx_mc_err_of_match);
 
 static struct platform_driver mpc85xx_mc_err_driver = {
 	.probe = fsl_mc_err_probe,
-	.remove = fsl_mc_err_remove,
+	.remove_new = fsl_mc_err_remove,
 	.driver = {
 		.name = "mpc85xx_mc_err",
 		.of_match_table = mpc85xx_mc_err_of_match,
diff --git a/drivers/edac/npcm_edac.c b/drivers/edac/npcm_edac.c
index 6d15c1550263..2e2133b784e9 100644
--- a/drivers/edac/npcm_edac.c
+++ b/drivers/edac/npcm_edac.c
@@ -410,7 +410,7 @@ free_edac_mc:
 	return rc;
 }
 
-static int edac_remove(struct platform_device *pdev)
+static void edac_remove(struct platform_device *pdev)
 {
 	struct mem_ctl_info *mci = platform_get_drvdata(pdev);
 	struct priv_data *priv = mci->pvt_info;
@@ -426,8 +426,6 @@ static int edac_remove(struct platform_device *pdev)
 	regmap_write(npcm_regmap, pdata->ctl_int_mask_master,
 		     pdata->int_mask_master_global_mask);
 	regmap_update_bits(npcm_regmap, pdata->ctl_ecc_en, pdata->ecc_en_mask, 0);
-
-	return 0;
 }
 
 static const struct npcm_platform_data npcm750_edac = {
@@ -533,7 +531,7 @@ static struct platform_driver npcm_edac_driver = {
 		.of_match_table = npcm_edac_of_match,
 	},
 	.probe = edac_probe,
-	.remove = edac_remove,
+	.remove_new = edac_remove,
 };
 
 module_platform_driver(npcm_edac_driver);
diff --git a/drivers/edac/octeon_edac-l2c.c b/drivers/edac/octeon_edac-l2c.c
index c33059e9b0be..4015eb9af6fe 100644
--- a/drivers/edac/octeon_edac-l2c.c
+++ b/drivers/edac/octeon_edac-l2c.c
@@ -184,19 +184,17 @@ err:
 	return -ENXIO;
 }
 
-static int octeon_l2c_remove(struct platform_device *pdev)
+static void octeon_l2c_remove(struct platform_device *pdev)
 {
 	struct edac_device_ctl_info *l2c = platform_get_drvdata(pdev);
 
 	edac_device_del_device(&pdev->dev);
 	edac_device_free_ctl_info(l2c);
-
-	return 0;
 }
 
 static struct platform_driver octeon_l2c_driver = {
 	.probe = octeon_l2c_probe,
-	.remove = octeon_l2c_remove,
+	.remove_new = octeon_l2c_remove,
 	.driver = {
 		   .name = "octeon_l2c_edac",
 	}
diff --git a/drivers/edac/octeon_edac-lmc.c b/drivers/edac/octeon_edac-lmc.c
index aeb222ca3ed1..18615cbcd9ea 100644
--- a/drivers/edac/octeon_edac-lmc.c
+++ b/drivers/edac/octeon_edac-lmc.c
@@ -302,18 +302,17 @@ static int octeon_lmc_edac_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int octeon_lmc_edac_remove(struct platform_device *pdev)
+static void octeon_lmc_edac_remove(struct platform_device *pdev)
 {
 	struct mem_ctl_info *mci = platform_get_drvdata(pdev);
 
 	edac_mc_del_mc(&pdev->dev);
 	edac_mc_free(mci);
-	return 0;
 }
 
 static struct platform_driver octeon_lmc_edac_driver = {
 	.probe = octeon_lmc_edac_probe,
-	.remove = octeon_lmc_edac_remove,
+	.remove_new = octeon_lmc_edac_remove,
 	.driver = {
 		   .name = "octeon_lmc_edac",
 	}
diff --git a/drivers/edac/octeon_edac-pc.c b/drivers/edac/octeon_edac-pc.c
index 754eced59c32..ea8a8e337b1e 100644
--- a/drivers/edac/octeon_edac-pc.c
+++ b/drivers/edac/octeon_edac-pc.c
@@ -119,19 +119,18 @@ err:
 	return -ENXIO;
 }
 
-static int co_cache_error_remove(struct platform_device *pdev)
+static void co_cache_error_remove(struct platform_device *pdev)
 {
 	struct co_cache_error *p = platform_get_drvdata(pdev);
 
 	unregister_co_cache_error_notifier(&p->notifier);
 	edac_device_del_device(&pdev->dev);
 	edac_device_free_ctl_info(p->ed);
-	return 0;
 }
 
 static struct platform_driver co_cache_error_driver = {
 	.probe = co_cache_error_probe,
-	.remove = co_cache_error_remove,
+	.remove_new = co_cache_error_remove,
 	.driver = {
 		   .name = "octeon_pc_edac",
 	}
diff --git a/drivers/edac/octeon_edac-pci.c b/drivers/edac/octeon_edac-pci.c
index 28b238eecefc..108ad9493cfb 100644
--- a/drivers/edac/octeon_edac-pci.c
+++ b/drivers/edac/octeon_edac-pci.c
@@ -87,19 +87,17 @@ err:
 	return res;
 }
 
-static int octeon_pci_remove(struct platform_device *pdev)
+static void octeon_pci_remove(struct platform_device *pdev)
 {
 	struct edac_pci_ctl_info *pci = platform_get_drvdata(pdev);
 
 	edac_pci_del_device(&pdev->dev);
 	edac_pci_free_ctl_info(pci);
-
-	return 0;
 }
 
 static struct platform_driver octeon_pci_driver = {
 	.probe = octeon_pci_probe,
-	.remove = octeon_pci_remove,
+	.remove_new = octeon_pci_remove,
 	.driver = {
 		   .name = "octeon_pci_edac",
 	}
diff --git a/drivers/edac/pnd2_edac.c b/drivers/edac/pnd2_edac.c
index 2b306f2cc605..2afcd148fcf8 100644
--- a/drivers/edac/pnd2_edac.c
+++ b/drivers/edac/pnd2_edac.c
@@ -16,18 +16,20 @@
  * rank, bank, row and column using the appropriate "dunit_ops" functions/parameters.
  */
 
-#include <linux/module.h>
+#include <linux/bitmap.h>
+#include <linux/delay.h>
+#include <linux/edac.h>
 #include <linux/init.h>
+#include <linux/math64.h>
+#include <linux/mmzone.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/pci_ids.h>
+#include <linux/sizes.h>
 #include <linux/slab.h>
-#include <linux/delay.h>
-#include <linux/edac.h>
-#include <linux/mmzone.h>
 #include <linux/smp.h>
-#include <linux/bitmap.h>
-#include <linux/math64.h>
-#include <linux/mod_devicetable.h>
+
 #include <linux/platform_data/x86/p2sb.h>
 
 #include <asm/cpu_device_id.h>
@@ -109,7 +111,6 @@ static struct mem_ctl_info *pnd2_mci;
 #define MOT_CHAN_INTLV_BIT_1SLC_2CH 12
 #define MOT_CHAN_INTLV_BIT_2SLC_2CH 13
 #define SELECTOR_DISABLED (-1)
-#define _4GB (1ul << 32)
 
 #define PMI_ADDRESS_WIDTH	31
 #define PND_MAX_PHYS_BIT	39
@@ -183,7 +184,7 @@ static int _apl_rd_reg(int port, int off, int op, u32 *data)
 	}
 
 	P2SB_READ(dword, P2SB_DATA_OFF, data);
-	ret = (status >> 1) & 0x3;
+	ret = (status >> 1) & GENMASK(1, 0);
 out:
 	/* Hide the P2SB device, if it was hidden before */
 	if (hidden)
@@ -307,7 +308,7 @@ static bool two_channels; /* Both PMI channels in one slice enabled */
 
 static u8 sym_chan_mask;
 static u8 asym_chan_mask;
-static u8 chan_mask;
+static unsigned long chan_mask;
 
 static int slice_selector = -1;
 static int chan_selector = -1;
@@ -329,7 +330,7 @@ static void mk_region_mask(char *name, struct region *rp, u64 base, u64 mask)
 		return;
 	}
 	if (mask != GENMASK_ULL(PND_MAX_PHYS_BIT, __ffs(mask))) {
-		pr_info(FW_BUG "MOT mask not power of two\n");
+		pr_info(FW_BUG "MOT mask is invalid\n");
 		return;
 	}
 	if (base & ~mask) {
@@ -587,7 +588,7 @@ static int get_registers(void)
 /* Get a contiguous memory address (remove the MMIO gap) */
 static u64 remove_mmio_gap(u64 sys)
 {
-	return (sys < _4GB) ? sys : sys - (_4GB - top_lm);
+	return (sys < SZ_4G) ? sys : sys - (SZ_4G - top_lm);
 }
 
 /* Squeeze out one address bit, shift upper part down to fill gap */
@@ -598,7 +599,7 @@ static void remove_addr_bit(u64 *addr, int bitidx)
 	if (bitidx == -1)
 		return;
 
-	mask = (1ull << bitidx) - 1;
+	mask = BIT_ULL(bitidx) - 1;
 	*addr = ((*addr >> 1) & ~mask) | (*addr & mask);
 }
 
@@ -642,8 +643,8 @@ static int sys2pmi(const u64 addr, u32 *pmiidx, u64 *pmiaddr, char *msg)
 	int sym_chan_shift = sym_channels >> 1;
 
 	/* Give up if address is out of range, or in MMIO gap */
-	if (addr >= (1ul << PND_MAX_PHYS_BIT) ||
-	   (addr >= top_lm && addr < _4GB) || addr >= top_hm) {
+	if (addr >= BIT(PND_MAX_PHYS_BIT) ||
+	   (addr >= top_lm && addr < SZ_4G) || addr >= top_hm) {
 		snprintf(msg, PND2_MSG_SIZE, "Error address 0x%llx is not DRAM", addr);
 		return -EINVAL;
 	}
@@ -727,10 +728,10 @@ static int sys2pmi(const u64 addr, u32 *pmiidx, u64 *pmiaddr, char *msg)
 }
 
 /* Translate PMI address to memory (rank, row, bank, column) */
-#define C(n) (0x10 | (n))	/* column */
-#define B(n) (0x20 | (n))	/* bank */
-#define R(n) (0x40 | (n))	/* row */
-#define RS   (0x80)			/* rank */
+#define C(n) (BIT(4) | (n))	/* column */
+#define B(n) (BIT(5) | (n))	/* bank */
+#define R(n) (BIT(6) | (n))	/* row */
+#define RS   (BIT(7))		/* rank */
 
 /* addrdec values */
 #define AMAP_1KB	0
@@ -1064,9 +1065,9 @@ static int apl_check_ecc_active(void)
 	int	i, ret = 0;
 
 	/* Check dramtype and ECC mode for each present DIMM */
-	for (i = 0; i < APL_NUM_CHANNELS; i++)
-		if (chan_mask & BIT(i))
-			ret += check_channel(i);
+	for_each_set_bit(i, &chan_mask, APL_NUM_CHANNELS)
+		ret += check_channel(i);
+
 	return ret ? -EINVAL : 0;
 }
 
@@ -1205,10 +1206,7 @@ static void apl_get_dimm_config(struct mem_ctl_info *mci)
 	u64	capacity;
 	int	i, g;
 
-	for (i = 0; i < APL_NUM_CHANNELS; i++) {
-		if (!(chan_mask & BIT(i)))
-			continue;
-
+	for_each_set_bit(i, &chan_mask, APL_NUM_CHANNELS) {
 		dimm = edac_get_dimm(mci, i, 0, 0);
 		if (!dimm) {
 			edac_dbg(0, "No allocated DIMM for channel %d\n", i);
@@ -1228,8 +1226,7 @@ static void apl_get_dimm_config(struct mem_ctl_info *mci)
 		}
 
 		pvt->dimm_geom[i] = g;
-		capacity = (d->rken0 + d->rken1) * 8 * (1ul << dimms[g].rowbits) *
-				   (1ul << dimms[g].colbits);
+		capacity = (d->rken0 + d->rken1) * 8 * BIT(dimms[g].rowbits + dimms[g].colbits);
 		edac_dbg(0, "Channel %d: %lld MByte DIMM\n", i, capacity >> (20 - 3));
 		dimm->nr_pages = MiB_TO_PAGES(capacity >> (20 - 3));
 		dimm->grain = 32;
@@ -1295,7 +1292,7 @@ static void dnv_get_dimm_config(struct mem_ctl_info *mci)
 				continue;
 			}
 
-			capacity = ranks_of_dimm[j] * banks * (1ul << rowbits) * (1ul << colbits);
+			capacity = ranks_of_dimm[j] * banks * BIT(rowbits + colbits);
 			edac_dbg(0, "Channel %d DIMM %d: %lld MByte DIMM\n", i, j, capacity >> (20 - 3));
 			dimm->nr_pages = MiB_TO_PAGES(capacity >> (20 - 3));
 			dimm->grain = 32;
diff --git a/drivers/edac/ppc4xx_edac.c b/drivers/edac/ppc4xx_edac.c
index 046969b4e82e..1eea3341a916 100644
--- a/drivers/edac/ppc4xx_edac.c
+++ b/drivers/edac/ppc4xx_edac.c
@@ -1329,8 +1329,7 @@ static int ppc4xx_edac_probe(struct platform_device *op)
  *
  * Unconditionally returns 0.
  */
-static int
-ppc4xx_edac_remove(struct platform_device *op)
+static void ppc4xx_edac_remove(struct platform_device *op)
 {
 	struct mem_ctl_info *mci = dev_get_drvdata(&op->dev);
 	struct ppc4xx_edac_pdata *pdata = mci->pvt_info;
@@ -1344,8 +1343,6 @@ ppc4xx_edac_remove(struct platform_device *op)
 
 	edac_mc_del_mc(mci->pdev);
 	edac_mc_free(mci);
-
-	return 0;
 }
 
 /**
@@ -1379,7 +1376,7 @@ ppc4xx_edac_opstate_init(void)
 
 static struct platform_driver ppc4xx_edac_driver = {
 	.probe			= ppc4xx_edac_probe,
-	.remove			= ppc4xx_edac_remove,
+	.remove_new		= ppc4xx_edac_remove,
 	.driver = {
 		.name = PPC4XX_EDAC_MODULE_NAME,
 		.of_match_table = ppc4xx_edac_match,
diff --git a/drivers/edac/qcom_edac.c b/drivers/edac/qcom_edac.c
index b2db545c6810..5539917c01dd 100644
--- a/drivers/edac/qcom_edac.c
+++ b/drivers/edac/qcom_edac.c
@@ -390,14 +390,12 @@ irq_done:
 	return rc;
 }
 
-static int qcom_llcc_edac_remove(struct platform_device *pdev)
+static void qcom_llcc_edac_remove(struct platform_device *pdev)
 {
 	struct edac_device_ctl_info *edev_ctl = dev_get_drvdata(&pdev->dev);
 
 	edac_device_del_device(edev_ctl->dev);
 	edac_device_free_ctl_info(edev_ctl);
-
-	return 0;
 }
 
 static const struct platform_device_id qcom_llcc_edac_id_table[] = {
@@ -408,7 +406,7 @@ MODULE_DEVICE_TABLE(platform, qcom_llcc_edac_id_table);
 
 static struct platform_driver qcom_llcc_edac_driver = {
 	.probe = qcom_llcc_edac_probe,
-	.remove = qcom_llcc_edac_remove,
+	.remove_new = qcom_llcc_edac_remove,
 	.driver = {
 		.name = "qcom_llcc_edac",
 	},
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index 0c779a0326b6..26cca5a9322d 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -439,7 +439,7 @@ static const struct pci_id_descr pci_dev_descr_sbridge[] = {
 
 static const struct pci_id_table pci_dev_descr_sbridge_table[] = {
 	PCI_ID_TABLE_ENTRY(pci_dev_descr_sbridge, ARRAY_SIZE(pci_dev_descr_sbridge), 1, SANDY_BRIDGE),
-	{0,}			/* 0 terminated list. */
+	{ NULL, }
 };
 
 /* This changes depending if 1HA or 2HA:
@@ -505,7 +505,7 @@ static const struct pci_id_descr pci_dev_descr_ibridge[] = {
 
 static const struct pci_id_table pci_dev_descr_ibridge_table[] = {
 	PCI_ID_TABLE_ENTRY(pci_dev_descr_ibridge, 12, 2, IVY_BRIDGE),
-	{0,}			/* 0 terminated list. */
+	{ NULL, }
 };
 
 /* Haswell support */
@@ -576,7 +576,7 @@ static const struct pci_id_descr pci_dev_descr_haswell[] = {
 
 static const struct pci_id_table pci_dev_descr_haswell_table[] = {
 	PCI_ID_TABLE_ENTRY(pci_dev_descr_haswell, 13, 2, HASWELL),
-	{0,}			/* 0 terminated list. */
+	{ NULL, }
 };
 
 /* Knight's Landing Support */
@@ -620,7 +620,7 @@ static const struct pci_id_descr pci_dev_descr_knl[] = {
 
 static const struct pci_id_table pci_dev_descr_knl_table[] = {
 	PCI_ID_TABLE_ENTRY(pci_dev_descr_knl, ARRAY_SIZE(pci_dev_descr_knl), 1, KNIGHTS_LANDING),
-	{0,}
+	{ NULL, }
 };
 
 /*
@@ -686,7 +686,7 @@ static const struct pci_id_descr pci_dev_descr_broadwell[] = {
 
 static const struct pci_id_table pci_dev_descr_broadwell_table[] = {
 	PCI_ID_TABLE_ENTRY(pci_dev_descr_broadwell, 10, 2, BROADWELL),
-	{0,}			/* 0 terminated list. */
+	{ NULL, }
 };
 
 
diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c
index ce3e0069e028..9c5b6f8bd8bd 100644
--- a/drivers/edac/skx_common.c
+++ b/drivers/edac/skx_common.c
@@ -648,6 +648,10 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val,
 	memset(&res, 0, sizeof(res));
 	res.mce  = mce;
 	res.addr = mce->addr & MCI_ADDR_PHYSADDR;
+	if (!pfn_to_online_page(res.addr >> PAGE_SHIFT)) {
+		pr_err("Invalid address 0x%llx in IA32_MC%d_ADDR\n", mce->addr, mce->bank);
+		return NOTIFY_DONE;
+	}
 
 	/* Try driver decoder first */
 	if (!(driver_decode && driver_decode(&res))) {
diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c
index c4fc64cbecd0..709babce43ba 100644
--- a/drivers/edac/synopsys_edac.c
+++ b/drivers/edac/synopsys_edac.c
@@ -1410,7 +1410,7 @@ free_edac_mc:
  *
  * Return: Unconditionally 0
  */
-static int mc_remove(struct platform_device *pdev)
+static void mc_remove(struct platform_device *pdev)
 {
 	struct mem_ctl_info *mci = platform_get_drvdata(pdev);
 	struct synps_edac_priv *priv = mci->pvt_info;
@@ -1425,8 +1425,6 @@ static int mc_remove(struct platform_device *pdev)
 
 	edac_mc_del_mc(&pdev->dev);
 	edac_mc_free(mci);
-
-	return 0;
 }
 
 static struct platform_driver synps_edac_mc_driver = {
@@ -1435,7 +1433,7 @@ static struct platform_driver synps_edac_mc_driver = {
 		   .of_match_table = synps_edac_match,
 		   },
 	.probe = mc_probe,
-	.remove = mc_remove,
+	.remove_new = mc_remove,
 };
 
 module_platform_driver(synps_edac_mc_driver);
diff --git a/drivers/edac/thunderx_edac.c b/drivers/edac/thunderx_edac.c
index b9c5772da959..90d46e5c4ff0 100644
--- a/drivers/edac/thunderx_edac.c
+++ b/drivers/edac/thunderx_edac.c
@@ -1133,7 +1133,7 @@ static irqreturn_t thunderx_ocx_com_threaded_isr(int irq, void *irq_id)
 		decode_register(other, OCX_OTHER_SIZE,
 				ocx_com_errors, ctx->reg_com_int);
 
-		strncat(msg, other, OCX_MESSAGE_SIZE);
+		strlcat(msg, other, OCX_MESSAGE_SIZE);
 
 		for (lane = 0; lane < OCX_RX_LANES; lane++)
 			if (ctx->reg_com_int & BIT(lane)) {
@@ -1142,12 +1142,12 @@ static irqreturn_t thunderx_ocx_com_threaded_isr(int irq, void *irq_id)
 					 lane, ctx->reg_lane_int[lane],
 					 lane, ctx->reg_lane_stat11[lane]);
 
-				strncat(msg, other, OCX_MESSAGE_SIZE);
+				strlcat(msg, other, OCX_MESSAGE_SIZE);
 
 				decode_register(other, OCX_OTHER_SIZE,
 						ocx_lane_errors,
 						ctx->reg_lane_int[lane]);
-				strncat(msg, other, OCX_MESSAGE_SIZE);
+				strlcat(msg, other, OCX_MESSAGE_SIZE);
 			}
 
 		if (ctx->reg_com_int & OCX_COM_INT_CE)
@@ -1217,7 +1217,7 @@ static irqreturn_t thunderx_ocx_lnk_threaded_isr(int irq, void *irq_id)
 		decode_register(other, OCX_OTHER_SIZE,
 				ocx_com_link_errors, ctx->reg_com_link_int);
 
-		strncat(msg, other, OCX_MESSAGE_SIZE);
+		strlcat(msg, other, OCX_MESSAGE_SIZE);
 
 		if (ctx->reg_com_link_int & OCX_COM_LINK_INT_UE)
 			edac_device_handle_ue(ocx->edac_dev, 0, 0, msg);
@@ -1896,7 +1896,7 @@ static irqreturn_t thunderx_l2c_threaded_isr(int irq, void *irq_id)
 
 		decode_register(other, L2C_OTHER_SIZE, l2_errors, ctx->reg_int);
 
-		strncat(msg, other, L2C_MESSAGE_SIZE);
+		strlcat(msg, other, L2C_MESSAGE_SIZE);
 
 		if (ctx->reg_int & mask_ue)
 			edac_device_handle_ue(l2c->edac_dev, 0, 0, msg);
diff --git a/drivers/edac/ti_edac.c b/drivers/edac/ti_edac.c
index 6971ded598de..29723c9592f7 100644
--- a/drivers/edac/ti_edac.c
+++ b/drivers/edac/ti_edac.c
@@ -312,19 +312,17 @@ err:
 	return ret;
 }
 
-static int ti_edac_remove(struct platform_device *pdev)
+static void ti_edac_remove(struct platform_device *pdev)
 {
 	struct mem_ctl_info *mci = platform_get_drvdata(pdev);
 
 	edac_mc_del_mc(&pdev->dev);
 	edac_mc_free(mci);
-
-	return 0;
 }
 
 static struct platform_driver ti_edac_driver = {
 	.probe = ti_edac_probe,
-	.remove = ti_edac_remove,
+	.remove_new = ti_edac_remove,
 	.driver = {
 		   .name = EDAC_MOD_NAME,
 		   .of_match_table = ti_edac_of_match,
diff --git a/drivers/edac/versal_edac.c b/drivers/edac/versal_edac.c
index 87e730dfefa0..8625de20fc71 100644
--- a/drivers/edac/versal_edac.c
+++ b/drivers/edac/versal_edac.c
@@ -966,10 +966,10 @@ static int mc_probe(struct platform_device *pdev)
 	edac_mc_id = emif_get_id(pdev->dev.of_node);
 
 	regval = readl(ddrmc_baseaddr + XDDR_REG_CONFIG0_OFFSET);
-	num_chans = FIELD_PREP(XDDR_REG_CONFIG0_NUM_CHANS_MASK, regval);
+	num_chans = FIELD_GET(XDDR_REG_CONFIG0_NUM_CHANS_MASK, regval);
 	num_chans++;
 
-	num_csrows = FIELD_PREP(XDDR_REG_CONFIG0_NUM_RANKS_MASK, regval);
+	num_csrows = FIELD_GET(XDDR_REG_CONFIG0_NUM_RANKS_MASK, regval);
 	num_csrows *= 2;
 	if (!num_csrows)
 		num_csrows = 1;
diff --git a/drivers/edac/xgene_edac.c b/drivers/edac/xgene_edac.c
index c52b9dd9154c..1b50f8160013 100644
--- a/drivers/edac/xgene_edac.c
+++ b/drivers/edac/xgene_edac.c
@@ -1960,7 +1960,7 @@ out_err:
 	return rc;
 }
 
-static int xgene_edac_remove(struct platform_device *pdev)
+static void xgene_edac_remove(struct platform_device *pdev)
 {
 	struct xgene_edac *edac = dev_get_drvdata(&pdev->dev);
 	struct xgene_edac_mc_ctx *mcu;
@@ -1981,8 +1981,6 @@ static int xgene_edac_remove(struct platform_device *pdev)
 
 	list_for_each_entry_safe(node, temp_node, &edac->socs, next)
 		xgene_edac_soc_remove(node);
-
-	return 0;
 }
 
 static const struct of_device_id xgene_edac_of_match[] = {
@@ -1993,7 +1991,7 @@ MODULE_DEVICE_TABLE(of, xgene_edac_of_match);
 
 static struct platform_driver xgene_edac_driver = {
 	.probe = xgene_edac_probe,
-	.remove = xgene_edac_remove,
+	.remove_new = xgene_edac_remove,
 	.driver = {
 		.name = "xgene-edac",
 		.of_match_table = xgene_edac_of_match,
diff --git a/drivers/edac/zynqmp_edac.c b/drivers/edac/zynqmp_edac.c
index ac7d1e0b324c..2d9a5cfd8931 100644
--- a/drivers/edac/zynqmp_edac.c
+++ b/drivers/edac/zynqmp_edac.c
@@ -426,7 +426,7 @@ free_dev_ctl:
 	return ret;
 }
 
-static int edac_remove(struct platform_device *pdev)
+static void edac_remove(struct platform_device *pdev)
 {
 	struct edac_device_ctl_info *dci = platform_get_drvdata(pdev);
 	struct edac_priv *priv = dci->pvt_info;
@@ -440,8 +440,6 @@ static int edac_remove(struct platform_device *pdev)
 
 	edac_device_del_device(&pdev->dev);
 	edac_device_free_ctl_info(dci);
-
-	return 0;
 }
 
 static const struct of_device_id zynqmp_ocm_edac_match[] = {
@@ -457,7 +455,7 @@ static struct platform_driver zynqmp_ocm_edac_driver = {
 		   .of_match_table = zynqmp_ocm_edac_match,
 		   },
 	.probe = edac_probe,
-	.remove = edac_remove,
+	.remove_new = edac_remove,
 };
 
 module_platform_driver(zynqmp_ocm_edac_driver);
diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c
index aa597cda0d88..2828e9573e90 100644
--- a/drivers/firewire/core-device.c
+++ b/drivers/firewire/core-device.c
@@ -717,14 +717,11 @@ static void create_units(struct fw_device *device)
 					fw_unit_attributes,
 					&unit->attribute_group);
 
-		if (device_register(&unit->device) < 0)
-			goto skip_unit;
-
 		fw_device_get(device);
-		continue;
-
-	skip_unit:
-		kfree(unit);
+		if (device_register(&unit->device) < 0) {
+			put_device(&unit->device);
+			continue;
+		}
 	}
 }
 
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 7e88fd489741..9db9290c3269 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -279,6 +279,51 @@ static char ohci_driver_name[] = KBUILD_MODNAME;
 #define QUIRK_TI_SLLZ059		0x20
 #define QUIRK_IR_WAKE			0x40
 
+// On PCI Express Root Complex in any type of AMD Ryzen machine, VIA VT6306/6307/6308 with Asmedia
+// ASM1083/1085 brings an inconvenience that the read accesses to 'Isochronous Cycle Timer' register
+// (at offset 0xf0 in PCI I/O space) often causes unexpected system reboot. The mechanism is not
+// clear, since the read access to the other registers is enough safe; e.g. 'Node ID' register,
+// while it is probable due to detection of any type of PCIe error.
+#define QUIRK_REBOOT_BY_CYCLE_TIMER_READ	0x80000000
+
+#if IS_ENABLED(CONFIG_X86)
+
+static bool has_reboot_by_cycle_timer_read_quirk(const struct fw_ohci *ohci)
+{
+	return !!(ohci->quirks & QUIRK_REBOOT_BY_CYCLE_TIMER_READ);
+}
+
+#define PCI_DEVICE_ID_ASMEDIA_ASM108X	0x1080
+
+static bool detect_vt630x_with_asm1083_on_amd_ryzen_machine(const struct pci_dev *pdev)
+{
+	const struct pci_dev *pcie_to_pci_bridge;
+
+	// Detect any type of AMD Ryzen machine.
+	if (!static_cpu_has(X86_FEATURE_ZEN))
+		return false;
+
+	// Detect VIA VT6306/6307/6308.
+	if (pdev->vendor != PCI_VENDOR_ID_VIA)
+		return false;
+	if (pdev->device != PCI_DEVICE_ID_VIA_VT630X)
+		return false;
+
+	// Detect Asmedia ASM1083/1085.
+	pcie_to_pci_bridge = pdev->bus->self;
+	if (pcie_to_pci_bridge->vendor != PCI_VENDOR_ID_ASMEDIA)
+		return false;
+	if (pcie_to_pci_bridge->device != PCI_DEVICE_ID_ASMEDIA_ASM108X)
+		return false;
+
+	return true;
+}
+
+#else
+#define has_reboot_by_cycle_timer_read_quirk(ohci) false
+#define detect_vt630x_with_asm1083_on_amd_ryzen_machine(pdev)	false
+#endif
+
 /* In case of multiple matches in ohci_quirks[], only the first one is used. */
 static const struct {
 	unsigned short vendor, device, revision, flags;
@@ -1724,6 +1769,9 @@ static u32 get_cycle_time(struct fw_ohci *ohci)
 	s32 diff01, diff12;
 	int i;
 
+	if (has_reboot_by_cycle_timer_read_quirk(ohci))
+		return 0;
+
 	c2 = reg_read(ohci, OHCI1394_IsochronousCycleTimer);
 
 	if (ohci->quirks & QUIRK_CYCLE_TIMER) {
@@ -3630,6 +3678,9 @@ static int pci_probe(struct pci_dev *dev,
 	if (param_quirks)
 		ohci->quirks = param_quirks;
 
+	if (detect_vt630x_with_asm1083_on_amd_ryzen_machine(dev))
+		ohci->quirks |= QUIRK_REBOOT_BY_CYCLE_TIMER_READ;
+
 	/*
 	 * Because dma_alloc_coherent() allocates at least one page,
 	 * we save space by using a common buffer for the AR request/
diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c
index 7edf2c95282f..e779d866022b 100644
--- a/drivers/firewire/sbp2.c
+++ b/drivers/firewire/sbp2.c
@@ -1519,9 +1519,9 @@ static int sbp2_scsi_slave_configure(struct scsi_device *sdev)
 	sdev->use_10_for_rw = 1;
 
 	if (sbp2_param_exclusive_login) {
-		sdev->manage_system_start_stop = true;
-		sdev->manage_runtime_start_stop = true;
-		sdev->manage_shutdown = true;
+		sdev->manage_system_start_stop = 1;
+		sdev->manage_runtime_start_stop = 1;
+		sdev->manage_shutdown = 1;
 	}
 
 	if (sdev->type == TYPE_ROM)
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index 74d00b0c83fe..61eba7646edc 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -131,7 +131,7 @@ config RASPBERRYPI_FIRMWARE
 
 config FW_CFG_SYSFS
 	tristate "QEMU fw_cfg device support in sysfs"
-	depends on SYSFS && (ARM || ARM64 || PARISC || PPC_PMAC || SPARC || X86)
+	depends on SYSFS && (ARM || ARM64 || PARISC || PPC_PMAC || RISCV || SPARC || X86)
 	depends on HAS_IOPORT_MAP
 	default n
 	help
@@ -272,6 +272,7 @@ source "drivers/firmware/google/Kconfig"
 source "drivers/firmware/efi/Kconfig"
 source "drivers/firmware/imx/Kconfig"
 source "drivers/firmware/meson/Kconfig"
+source "drivers/firmware/microchip/Kconfig"
 source "drivers/firmware/psci/Kconfig"
 source "drivers/firmware/qcom/Kconfig"
 source "drivers/firmware/smccc/Kconfig"
diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile
index 5f9dab82e1a0..d305d66bc820 100644
--- a/drivers/firmware/Makefile
+++ b/drivers/firmware/Makefile
@@ -28,6 +28,7 @@ obj-y				+= arm_scmi/
 obj-y				+= broadcom/
 obj-y				+= cirrus/
 obj-y				+= meson/
+obj-y				+= microchip/
 obj-$(CONFIG_GOOGLE_FIRMWARE)	+= google/
 obj-y				+= efi/
 obj-y				+= imx/
diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index 07b72c679247..6146b2927d5c 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -99,6 +99,7 @@ struct ffa_drv_info {
 	void *tx_buffer;
 	bool mem_ops_native;
 	bool bitmap_created;
+	bool notif_enabled;
 	unsigned int sched_recv_irq;
 	unsigned int cpuhp_state;
 	struct ffa_pcpu_irq __percpu *irq_pcpu;
@@ -782,7 +783,7 @@ static void ffa_notification_info_get(void)
 			if (ids_processed >= max_ids - 1)
 				break;
 
-			part_id = packed_id_list[++ids_processed];
+			part_id = packed_id_list[ids_processed++];
 
 			if (!ids_count[list]) { /* Global Notification */
 				__do_sched_recv_cb(part_id, 0, false);
@@ -794,7 +795,7 @@ static void ffa_notification_info_get(void)
 				if (ids_processed >= max_ids - 1)
 					break;
 
-				vcpu_id = packed_id_list[++ids_processed];
+				vcpu_id = packed_id_list[ids_processed++];
 
 				__do_sched_recv_cb(part_id, vcpu_id, true);
 			}
@@ -889,6 +890,8 @@ static int ffa_memory_lend(struct ffa_mem_ops_args *args)
 
 #define FFA_SECURE_PARTITION_ID_FLAG	BIT(15)
 
+#define ffa_notifications_disabled()	(!drv_info->notif_enabled)
+
 enum notify_type {
 	NON_SECURE_VM,
 	SECURE_PARTITION,
@@ -908,6 +911,9 @@ static int ffa_sched_recv_cb_update(u16 part_id, ffa_sched_recv_cb callback,
 	struct ffa_dev_part_info *partition;
 	bool cb_valid;
 
+	if (ffa_notifications_disabled())
+		return -EOPNOTSUPP;
+
 	partition = xa_load(&drv_info->partition_info, part_id);
 	write_lock(&partition->rw_lock);
 
@@ -1001,6 +1007,9 @@ static int ffa_notify_relinquish(struct ffa_device *dev, int notify_id)
 	int rc;
 	enum notify_type type = ffa_notify_type_get(dev->vm_id);
 
+	if (ffa_notifications_disabled())
+		return -EOPNOTSUPP;
+
 	if (notify_id >= FFA_MAX_NOTIFICATIONS)
 		return -EINVAL;
 
@@ -1027,6 +1036,9 @@ static int ffa_notify_request(struct ffa_device *dev, bool is_per_vcpu,
 	u32 flags = 0;
 	enum notify_type type = ffa_notify_type_get(dev->vm_id);
 
+	if (ffa_notifications_disabled())
+		return -EOPNOTSUPP;
+
 	if (notify_id >= FFA_MAX_NOTIFICATIONS)
 		return -EINVAL;
 
@@ -1057,6 +1069,9 @@ static int ffa_notify_send(struct ffa_device *dev, int notify_id,
 {
 	u32 flags = 0;
 
+	if (ffa_notifications_disabled())
+		return -EOPNOTSUPP;
+
 	if (is_per_vcpu)
 		flags |= (PER_VCPU_NOTIFICATION_FLAG | vcpu << 16);
 
@@ -1233,7 +1248,7 @@ static void ffa_partitions_cleanup(void)
 	if (!count)
 		return;
 
-	info = kcalloc(count, sizeof(**info), GFP_KERNEL);
+	info = kcalloc(count, sizeof(*info), GFP_KERNEL);
 	if (!info)
 		return;
 
@@ -1311,8 +1326,10 @@ static int ffa_sched_recv_irq_map(void)
 
 static void ffa_sched_recv_irq_unmap(void)
 {
-	if (drv_info->sched_recv_irq)
+	if (drv_info->sched_recv_irq) {
 		irq_dispose_mapping(drv_info->sched_recv_irq);
+		drv_info->sched_recv_irq = 0;
+	}
 }
 
 static int ffa_cpuhp_pcpu_irq_enable(unsigned int cpu)
@@ -1329,17 +1346,23 @@ static int ffa_cpuhp_pcpu_irq_disable(unsigned int cpu)
 
 static void ffa_uninit_pcpu_irq(void)
 {
-	if (drv_info->cpuhp_state)
+	if (drv_info->cpuhp_state) {
 		cpuhp_remove_state(drv_info->cpuhp_state);
+		drv_info->cpuhp_state = 0;
+	}
 
-	if (drv_info->notif_pcpu_wq)
+	if (drv_info->notif_pcpu_wq) {
 		destroy_workqueue(drv_info->notif_pcpu_wq);
+		drv_info->notif_pcpu_wq = NULL;
+	}
 
 	if (drv_info->sched_recv_irq)
 		free_percpu_irq(drv_info->sched_recv_irq, drv_info->irq_pcpu);
 
-	if (drv_info->irq_pcpu)
+	if (drv_info->irq_pcpu) {
 		free_percpu(drv_info->irq_pcpu);
+		drv_info->irq_pcpu = NULL;
+	}
 }
 
 static int ffa_init_pcpu_irq(unsigned int irq)
@@ -1388,22 +1411,23 @@ static void ffa_notifications_cleanup(void)
 		ffa_notification_bitmap_destroy();
 		drv_info->bitmap_created = false;
 	}
+	drv_info->notif_enabled = false;
 }
 
-static int ffa_notifications_setup(void)
+static void ffa_notifications_setup(void)
 {
 	int ret, irq;
 
 	ret = ffa_features(FFA_NOTIFICATION_BITMAP_CREATE, 0, NULL, NULL);
 	if (ret) {
-		pr_err("Notifications not supported, continuing with it ..\n");
-		return 0;
+		pr_info("Notifications not supported, continuing with it ..\n");
+		return;
 	}
 
 	ret = ffa_notification_bitmap_create();
 	if (ret) {
-		pr_err("notification_bitmap_create error %d\n", ret);
-		return ret;
+		pr_info("Notification bitmap create error %d\n", ret);
+		return;
 	}
 	drv_info->bitmap_created = true;
 
@@ -1422,14 +1446,11 @@ static int ffa_notifications_setup(void)
 	hash_init(drv_info->notifier_hash);
 	mutex_init(&drv_info->notify_lock);
 
-	/* Register internal scheduling callback */
-	ret = ffa_sched_recv_cb_update(drv_info->vm_id, ffa_self_notif_handle,
-				       drv_info, true);
-	if (!ret)
-		return ret;
+	drv_info->notif_enabled = true;
+	return;
 cleanup:
+	pr_info("Notification setup failed %d, not enabled\n", ret);
 	ffa_notifications_cleanup();
-	return ret;
 }
 
 static int __init ffa_init(void)
@@ -1483,17 +1504,18 @@ static int __init ffa_init(void)
 	mutex_init(&drv_info->rx_lock);
 	mutex_init(&drv_info->tx_lock);
 
-	ffa_setup_partitions();
-
 	ffa_set_up_mem_ops_native_flag();
 
-	ret = ffa_notifications_setup();
+	ffa_notifications_setup();
+
+	ffa_setup_partitions();
+
+	ret = ffa_sched_recv_cb_update(drv_info->vm_id, ffa_self_notif_handle,
+				       drv_info, true);
 	if (ret)
-		goto partitions_cleanup;
+		pr_info("Failed to register driver sched callback %d\n", ret);
 
 	return 0;
-partitions_cleanup:
-	ffa_partitions_cleanup();
 free_pages:
 	if (drv_info->tx_buffer)
 		free_pages_exact(drv_info->tx_buffer, RXTX_BUFFER_SIZE);
diff --git a/drivers/firmware/arm_scmi/base.c b/drivers/firmware/arm_scmi/base.c
index a52f084a6a87..97254de35ab0 100644
--- a/drivers/firmware/arm_scmi/base.c
+++ b/drivers/firmware/arm_scmi/base.c
@@ -13,6 +13,9 @@
 #include "common.h"
 #include "notify.h"
 
+/* Updated only after ALL the mandatory features for that version are merged */
+#define SCMI_PROTOCOL_SUPPORTED_VERSION		0x20000
+
 #define SCMI_BASE_NUM_SOURCES		1
 #define SCMI_BASE_MAX_CMD_ERR_COUNT	1024
 
@@ -385,7 +388,7 @@ static int scmi_base_protocol_init(const struct scmi_protocol_handle *ph)
 
 	rev->major_ver = PROTOCOL_REV_MAJOR(version),
 	rev->minor_ver = PROTOCOL_REV_MINOR(version);
-	ph->set_priv(ph, rev);
+	ph->set_priv(ph, rev, version);
 
 	ret = scmi_base_attributes_get(ph);
 	if (ret)
@@ -423,6 +426,7 @@ static const struct scmi_protocol scmi_base = {
 	.instance_init = &scmi_base_protocol_init,
 	.ops = NULL,
 	.events = &base_protocol_events,
+	.supported_version = SCMI_PROTOCOL_SUPPORTED_VERSION,
 };
 
 DEFINE_SCMI_PROTOCOL_REGISTER_UNREGISTER(base, scmi_base)
diff --git a/drivers/firmware/arm_scmi/clock.c b/drivers/firmware/arm_scmi/clock.c
index 42b81c181d68..c0644558042a 100644
--- a/drivers/firmware/arm_scmi/clock.c
+++ b/drivers/firmware/arm_scmi/clock.c
@@ -12,6 +12,9 @@
 #include "protocols.h"
 #include "notify.h"
 
+/* Updated only after ALL the mandatory features for that version are merged */
+#define SCMI_PROTOCOL_SUPPORTED_VERSION		0x20001
+
 enum scmi_clock_protocol_cmd {
 	CLOCK_ATTRIBUTES = 0x3,
 	CLOCK_DESCRIBE_RATES = 0x4,
@@ -318,7 +321,7 @@ static int scmi_clock_attributes_get(const struct scmi_protocol_handle *ph,
 	if (!ret && PROTOCOL_REV_MAJOR(version) >= 0x2) {
 		if (SUPPORTS_EXTENDED_NAMES(attributes))
 			ph->hops->extended_name_get(ph, CLOCK_NAME_GET, clk_id,
-						    clk->name,
+						    NULL, clk->name,
 						    SCMI_MAX_STR_SIZE);
 
 		if (SUPPORTS_RATE_CHANGED_NOTIF(attributes))
@@ -961,7 +964,7 @@ static int scmi_clock_protocol_init(const struct scmi_protocol_handle *ph)
 	}
 
 	cinfo->version = version;
-	return ph->set_priv(ph, cinfo);
+	return ph->set_priv(ph, cinfo, version);
 }
 
 static const struct scmi_protocol scmi_clock = {
@@ -970,6 +973,7 @@ static const struct scmi_protocol scmi_clock = {
 	.instance_init = &scmi_clock_protocol_init,
 	.ops = &clk_proto_ops,
 	.events = &clk_protocol_events,
+	.supported_version = SCMI_PROTOCOL_SUPPORTED_VERSION,
 };
 
 DEFINE_SCMI_PROTOCOL_REGISTER_UNREGISTER(clock, scmi_clock)
diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c
index 09371f40d61f..a9f70e6e58ac 100644
--- a/drivers/firmware/arm_scmi/driver.c
+++ b/drivers/firmware/arm_scmi/driver.c
@@ -85,6 +85,7 @@ struct scmi_xfers_info {
  * @gid: A reference for per-protocol devres management.
  * @users: A refcount to track effective users of this protocol.
  * @priv: Reference for optional protocol private data.
+ * @version: Protocol version supported by the platform as detected at runtime.
  * @ph: An embedded protocol handle that will be passed down to protocol
  *	initialization code to identify this instance.
  *
@@ -97,6 +98,7 @@ struct scmi_protocol_instance {
 	void				*gid;
 	refcount_t			users;
 	void				*priv;
+	unsigned int			version;
 	struct scmi_protocol_handle	ph;
 };
 
@@ -1392,15 +1394,17 @@ static int version_get(const struct scmi_protocol_handle *ph, u32 *version)
  *
  * @ph: A reference to the protocol handle.
  * @priv: The private data to set.
+ * @version: The detected protocol version for the core to register.
  *
  * Return: 0 on Success
  */
 static int scmi_set_protocol_priv(const struct scmi_protocol_handle *ph,
-				  void *priv)
+				  void *priv, u32 version)
 {
 	struct scmi_protocol_instance *pi = ph_to_pi(ph);
 
 	pi->priv = priv;
+	pi->version = version;
 
 	return 0;
 }
@@ -1438,6 +1442,7 @@ struct scmi_msg_resp_domain_name_get {
  * @ph: A protocol handle reference.
  * @cmd_id: The specific command ID to use.
  * @res_id: The specific resource ID to use.
+ * @flags: A pointer to specific flags to use, if any.
  * @name: A pointer to the preallocated area where the retrieved name will be
  *	  stored as a NULL terminated string.
  * @len: The len in bytes of the @name char array.
@@ -1445,19 +1450,22 @@ struct scmi_msg_resp_domain_name_get {
  * Return: 0 on Succcess
  */
 static int scmi_common_extended_name_get(const struct scmi_protocol_handle *ph,
-					 u8 cmd_id, u32 res_id, char *name,
-					 size_t len)
+					 u8 cmd_id, u32 res_id, u32 *flags,
+					 char *name, size_t len)
 {
 	int ret;
+	size_t txlen;
 	struct scmi_xfer *t;
 	struct scmi_msg_resp_domain_name_get *resp;
 
-	ret = ph->xops->xfer_get_init(ph, cmd_id, sizeof(res_id),
-				      sizeof(*resp), &t);
+	txlen = !flags ? sizeof(res_id) : sizeof(res_id) + sizeof(*flags);
+	ret = ph->xops->xfer_get_init(ph, cmd_id, txlen, sizeof(*resp), &t);
 	if (ret)
 		goto out;
 
 	put_unaligned_le32(res_id, t->tx.buf);
+	if (flags)
+		put_unaligned_le32(*flags, t->tx.buf + sizeof(res_id));
 	resp = t->rx.buf;
 
 	ret = ph->xops->do_xfer(ph, t);
@@ -1845,6 +1853,12 @@ scmi_alloc_init_protocol_instance(struct scmi_info *info,
 	devres_close_group(handle->dev, pi->gid);
 	dev_dbg(handle->dev, "Initialized protocol: 0x%X\n", pi->proto->id);
 
+	if (pi->version > proto->supported_version)
+		dev_warn(handle->dev,
+			 "Detected UNSUPPORTED higher version 0x%X for protocol 0x%X."
+			 "Backward compatibility is NOT assured.\n",
+			 pi->version, pi->proto->id);
+
 	return pi;
 
 clean:
diff --git a/drivers/firmware/arm_scmi/optee.c b/drivers/firmware/arm_scmi/optee.c
index e123de6e8c67..25bfb465484d 100644
--- a/drivers/firmware/arm_scmi/optee.c
+++ b/drivers/firmware/arm_scmi/optee.c
@@ -440,6 +440,10 @@ static int scmi_optee_chan_setup(struct scmi_chan_info *cinfo, struct device *de
 	if (ret)
 		goto err_free_shm;
 
+	ret = tee_client_system_session(scmi_optee_private->tee_ctx, channel->tee_session);
+	if (ret)
+		dev_warn(dev, "Could not switch to system session, do best effort\n");
+
 	ret = get_channel(channel);
 	if (ret)
 		goto err_close_sess;
diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c
index c2435be0ae1b..8ea2a7b3d35d 100644
--- a/drivers/firmware/arm_scmi/perf.c
+++ b/drivers/firmware/arm_scmi/perf.c
@@ -24,7 +24,10 @@
 #include "protocols.h"
 #include "notify.h"
 
-#define MAX_OPPS		16
+/* Updated only after ALL the mandatory features for that version are merged */
+#define SCMI_PROTOCOL_SUPPORTED_VERSION		0x40000
+
+#define MAX_OPPS		32
 
 enum scmi_performance_protocol_cmd {
 	PERF_DOMAIN_ATTRIBUTES = 0x3,
@@ -152,7 +155,7 @@ struct perf_dom_info {
 	u32 opp_count;
 	u32 sustained_freq_khz;
 	u32 sustained_perf_level;
-	u32 mult_factor;
+	unsigned long mult_factor;
 	struct scmi_perf_domain_info info;
 	struct scmi_opp opp[MAX_OPPS];
 	struct scmi_fc_info *fc_info;
@@ -268,13 +271,14 @@ scmi_perf_domain_attributes_get(const struct scmi_protocol_handle *ph,
 		dom_info->sustained_perf_level =
 					le32_to_cpu(attr->sustained_perf_level);
 		if (!dom_info->sustained_freq_khz ||
-		    !dom_info->sustained_perf_level)
+		    !dom_info->sustained_perf_level ||
+		    dom_info->level_indexing_mode)
 			/* CPUFreq converts to kHz, hence default 1000 */
 			dom_info->mult_factor =	1000;
 		else
 			dom_info->mult_factor =
-					(dom_info->sustained_freq_khz * 1000) /
-					dom_info->sustained_perf_level;
+					(dom_info->sustained_freq_khz * 1000UL)
+					/ dom_info->sustained_perf_level;
 		strscpy(dom_info->info.name, attr->name,
 			SCMI_SHORT_NAME_MAX_SIZE);
 	}
@@ -288,7 +292,7 @@ scmi_perf_domain_attributes_get(const struct scmi_protocol_handle *ph,
 	if (!ret && PROTOCOL_REV_MAJOR(version) >= 0x3 &&
 	    SUPPORTS_EXTENDED_NAMES(flags))
 		ph->hops->extended_name_get(ph, PERF_DOMAIN_NAME_GET,
-					    dom_info->id, dom_info->info.name,
+					    dom_info->id, NULL, dom_info->info.name,
 					    SCMI_MAX_STR_SIZE);
 
 	if (dom_info->level_indexing_mode) {
@@ -504,6 +508,9 @@ static int scmi_perf_limits_set(const struct scmi_protocol_handle *ph,
 	if (IS_ERR(dom))
 		return PTR_ERR(dom);
 
+	if (!dom->set_limits)
+		return -EOPNOTSUPP;
+
 	if (PROTOCOL_REV_MAJOR(pi->version) >= 0x3 && !max_perf && !min_perf)
 		return -EINVAL;
 
@@ -654,6 +661,9 @@ static int scmi_perf_level_set(const struct scmi_protocol_handle *ph,
 	if (IS_ERR(dom))
 		return PTR_ERR(dom);
 
+	if (!dom->info.set_perf)
+		return -EOPNOTSUPP;
+
 	if (dom->level_indexing_mode) {
 		struct scmi_opp *opp;
 
@@ -753,7 +763,7 @@ static int scmi_perf_level_limits_notify(const struct scmi_protocol_handle *ph,
 }
 
 static void scmi_perf_domain_init_fc(const struct scmi_protocol_handle *ph,
-				     u32 domain, struct scmi_fc_info **p_fc)
+				     struct perf_dom_info *dom)
 {
 	struct scmi_fc_info *fc;
 
@@ -762,24 +772,26 @@ static void scmi_perf_domain_init_fc(const struct scmi_protocol_handle *ph,
 		return;
 
 	ph->hops->fastchannel_init(ph, PERF_DESCRIBE_FASTCHANNEL,
-				   PERF_LEVEL_SET, 4, domain,
-				   &fc[PERF_FC_LEVEL].set_addr,
-				   &fc[PERF_FC_LEVEL].set_db);
-
-	ph->hops->fastchannel_init(ph, PERF_DESCRIBE_FASTCHANNEL,
-				   PERF_LEVEL_GET, 4, domain,
+				   PERF_LEVEL_GET, 4, dom->id,
 				   &fc[PERF_FC_LEVEL].get_addr, NULL);
 
 	ph->hops->fastchannel_init(ph, PERF_DESCRIBE_FASTCHANNEL,
-				   PERF_LIMITS_SET, 8, domain,
-				   &fc[PERF_FC_LIMIT].set_addr,
-				   &fc[PERF_FC_LIMIT].set_db);
-
-	ph->hops->fastchannel_init(ph, PERF_DESCRIBE_FASTCHANNEL,
-				   PERF_LIMITS_GET, 8, domain,
+				   PERF_LIMITS_GET, 8, dom->id,
 				   &fc[PERF_FC_LIMIT].get_addr, NULL);
 
-	*p_fc = fc;
+	if (dom->info.set_perf)
+		ph->hops->fastchannel_init(ph, PERF_DESCRIBE_FASTCHANNEL,
+					   PERF_LEVEL_SET, 4, dom->id,
+					   &fc[PERF_FC_LEVEL].set_addr,
+					   &fc[PERF_FC_LEVEL].set_db);
+
+	if (dom->set_limits)
+		ph->hops->fastchannel_init(ph, PERF_DESCRIBE_FASTCHANNEL,
+					   PERF_LIMITS_SET, 8, dom->id,
+					   &fc[PERF_FC_LIMIT].set_addr,
+					   &fc[PERF_FC_LIMIT].set_db);
+
+	dom->fc_info = fc;
 }
 
 static int scmi_dvfs_device_opps_add(const struct scmi_protocol_handle *ph,
@@ -798,7 +810,7 @@ static int scmi_dvfs_device_opps_add(const struct scmi_protocol_handle *ph,
 		if (!dom->level_indexing_mode)
 			freq = dom->opp[idx].perf * dom->mult_factor;
 		else
-			freq = dom->opp[idx].indicative_freq * 1000;
+			freq = dom->opp[idx].indicative_freq * dom->mult_factor;
 
 		data.level = dom->opp[idx].perf;
 		data.freq = freq;
@@ -845,7 +857,8 @@ static int scmi_dvfs_freq_set(const struct scmi_protocol_handle *ph, u32 domain,
 	} else {
 		struct scmi_opp *opp;
 
-		opp = LOOKUP_BY_FREQ(dom->opps_by_freq, freq / 1000);
+		opp = LOOKUP_BY_FREQ(dom->opps_by_freq,
+				     freq / dom->mult_factor);
 		if (!opp)
 			return -EIO;
 
@@ -879,7 +892,7 @@ static int scmi_dvfs_freq_get(const struct scmi_protocol_handle *ph, u32 domain,
 		if (!opp)
 			return -EIO;
 
-		*freq = opp->indicative_freq * 1000;
+		*freq = opp->indicative_freq * dom->mult_factor;
 	}
 
 	return ret;
@@ -902,7 +915,7 @@ static int scmi_dvfs_est_power_get(const struct scmi_protocol_handle *ph,
 		if (!dom->level_indexing_mode)
 			opp_freq = opp->perf * dom->mult_factor;
 		else
-			opp_freq = opp->indicative_freq * 1000;
+			opp_freq = opp->indicative_freq * dom->mult_factor;
 
 		if (opp_freq < *freq)
 			continue;
@@ -1089,14 +1102,14 @@ static int scmi_perf_protocol_init(const struct scmi_protocol_handle *ph)
 		scmi_perf_describe_levels_get(ph, dom, version);
 
 		if (dom->perf_fastchannels)
-			scmi_perf_domain_init_fc(ph, dom->id, &dom->fc_info);
+			scmi_perf_domain_init_fc(ph, dom);
 	}
 
 	ret = devm_add_action_or_reset(ph->dev, scmi_perf_xa_destroy, pinfo);
 	if (ret)
 		return ret;
 
-	return ph->set_priv(ph, pinfo);
+	return ph->set_priv(ph, pinfo, version);
 }
 
 static const struct scmi_protocol scmi_perf = {
@@ -1105,6 +1118,7 @@ static const struct scmi_protocol scmi_perf = {
 	.instance_init = &scmi_perf_protocol_init,
 	.ops = &perf_proto_ops,
 	.events = &perf_protocol_events,
+	.supported_version = SCMI_PROTOCOL_SUPPORTED_VERSION,
 };
 
 DEFINE_SCMI_PROTOCOL_REGISTER_UNREGISTER(perf, scmi_perf)
diff --git a/drivers/firmware/arm_scmi/power.c b/drivers/firmware/arm_scmi/power.c
index 356e83631664..c2e6b9b4d941 100644
--- a/drivers/firmware/arm_scmi/power.c
+++ b/drivers/firmware/arm_scmi/power.c
@@ -13,6 +13,9 @@
 #include "protocols.h"
 #include "notify.h"
 
+/* Updated only after ALL the mandatory features for that version are merged */
+#define SCMI_PROTOCOL_SUPPORTED_VERSION		0x30000
+
 enum scmi_power_protocol_cmd {
 	POWER_DOMAIN_ATTRIBUTES = 0x3,
 	POWER_STATE_SET = 0x4,
@@ -133,7 +136,7 @@ scmi_power_domain_attributes_get(const struct scmi_protocol_handle *ph,
 	if (!ret && PROTOCOL_REV_MAJOR(version) >= 0x3 &&
 	    SUPPORTS_EXTENDED_NAMES(flags)) {
 		ph->hops->extended_name_get(ph, POWER_DOMAIN_NAME_GET,
-					    domain, dom_info->name,
+					    domain, NULL, dom_info->name,
 					    SCMI_MAX_STR_SIZE);
 	}
 
@@ -328,7 +331,7 @@ static int scmi_power_protocol_init(const struct scmi_protocol_handle *ph)
 
 	pinfo->version = version;
 
-	return ph->set_priv(ph, pinfo);
+	return ph->set_priv(ph, pinfo, version);
 }
 
 static const struct scmi_protocol scmi_power = {
@@ -337,6 +340,7 @@ static const struct scmi_protocol scmi_power = {
 	.instance_init = &scmi_power_protocol_init,
 	.ops = &power_proto_ops,
 	.events = &power_protocol_events,
+	.supported_version = SCMI_PROTOCOL_SUPPORTED_VERSION,
 };
 
 DEFINE_SCMI_PROTOCOL_REGISTER_UNREGISTER(power, scmi_power)
diff --git a/drivers/firmware/arm_scmi/powercap.c b/drivers/firmware/arm_scmi/powercap.c
index cb5617443a14..a4c6cd4716fe 100644
--- a/drivers/firmware/arm_scmi/powercap.c
+++ b/drivers/firmware/arm_scmi/powercap.c
@@ -17,6 +17,9 @@
 #include "protocols.h"
 #include "notify.h"
 
+/* Updated only after ALL the mandatory features for that version are merged */
+#define SCMI_PROTOCOL_SUPPORTED_VERSION		0x20000
+
 enum scmi_powercap_protocol_cmd {
 	POWERCAP_DOMAIN_ATTRIBUTES = 0x3,
 	POWERCAP_CAP_GET = 0x4,
@@ -270,7 +273,7 @@ clean:
 	 */
 	if (!ret && SUPPORTS_EXTENDED_NAMES(flags))
 		ph->hops->extended_name_get(ph, POWERCAP_DOMAIN_NAME_GET,
-					    domain, dom_info->name,
+					    domain, NULL, dom_info->name,
 					    SCMI_MAX_STR_SIZE);
 
 	return ret;
@@ -975,7 +978,7 @@ scmi_powercap_protocol_init(const struct scmi_protocol_handle *ph)
 	}
 
 	pinfo->version = version;
-	return ph->set_priv(ph, pinfo);
+	return ph->set_priv(ph, pinfo, version);
 }
 
 static const struct scmi_protocol scmi_powercap = {
@@ -984,6 +987,7 @@ static const struct scmi_protocol scmi_powercap = {
 	.instance_init = &scmi_powercap_protocol_init,
 	.ops = &powercap_proto_ops,
 	.events = &powercap_protocol_events,
+	.supported_version = SCMI_PROTOCOL_SUPPORTED_VERSION,
 };
 
 DEFINE_SCMI_PROTOCOL_REGISTER_UNREGISTER(powercap, scmi_powercap)
diff --git a/drivers/firmware/arm_scmi/protocols.h b/drivers/firmware/arm_scmi/protocols.h
index 78e1a01eb656..e683c26f24eb 100644
--- a/drivers/firmware/arm_scmi/protocols.h
+++ b/drivers/firmware/arm_scmi/protocols.h
@@ -174,7 +174,8 @@ struct scmi_protocol_handle {
 	struct device *dev;
 	const struct scmi_xfer_ops *xops;
 	const struct scmi_proto_helpers_ops *hops;
-	int (*set_priv)(const struct scmi_protocol_handle *ph, void *priv);
+	int (*set_priv)(const struct scmi_protocol_handle *ph, void *priv,
+			u32 version);
 	void *(*get_priv)(const struct scmi_protocol_handle *ph);
 };
 
@@ -256,7 +257,8 @@ struct scmi_fc_info {
  */
 struct scmi_proto_helpers_ops {
 	int (*extended_name_get)(const struct scmi_protocol_handle *ph,
-				 u8 cmd_id, u32 res_id, char *name, size_t len);
+				 u8 cmd_id, u32 res_id, u32 *flags, char *name,
+				 size_t len);
 	void *(*iter_response_init)(const struct scmi_protocol_handle *ph,
 				    struct scmi_iterator_ops *ops,
 				    unsigned int max_resources, u8 msg_id,
@@ -310,6 +312,10 @@ typedef int (*scmi_prot_init_ph_fn_t)(const struct scmi_protocol_handle *);
  * @ops: Optional reference to the operations provided by the protocol and
  *	 exposed in scmi_protocol.h.
  * @events: An optional reference to the events supported by this protocol.
+ * @supported_version: The highest version currently supported for this
+ *		       protocol by the agent. Each protocol implementation
+ *		       in the agent is supposed to downgrade to match the
+ *		       protocol version supported by the platform.
  */
 struct scmi_protocol {
 	const u8				id;
@@ -318,6 +324,7 @@ struct scmi_protocol {
 	const scmi_prot_init_ph_fn_t		instance_deinit;
 	const void				*ops;
 	const struct scmi_protocol_events	*events;
+	unsigned int				supported_version;
 };
 
 #define DEFINE_SCMI_PROTOCOL_REGISTER_UNREGISTER(name, proto)	\
diff --git a/drivers/firmware/arm_scmi/reset.c b/drivers/firmware/arm_scmi/reset.c
index e9afa8cab730..19970d9f9e36 100644
--- a/drivers/firmware/arm_scmi/reset.c
+++ b/drivers/firmware/arm_scmi/reset.c
@@ -13,6 +13,9 @@
 #include "protocols.h"
 #include "notify.h"
 
+/* Updated only after ALL the mandatory features for that version are merged */
+#define SCMI_PROTOCOL_SUPPORTED_VERSION		0x30000
+
 enum scmi_reset_protocol_cmd {
 	RESET_DOMAIN_ATTRIBUTES = 0x3,
 	RESET = 0x4,
@@ -128,7 +131,8 @@ scmi_reset_domain_attributes_get(const struct scmi_protocol_handle *ph,
 	if (!ret && PROTOCOL_REV_MAJOR(version) >= 0x3 &&
 	    SUPPORTS_EXTENDED_NAMES(attributes))
 		ph->hops->extended_name_get(ph, RESET_DOMAIN_NAME_GET, domain,
-					    dom_info->name, SCMI_MAX_STR_SIZE);
+					    NULL, dom_info->name,
+					    SCMI_MAX_STR_SIZE);
 
 	return ret;
 }
@@ -342,7 +346,7 @@ static int scmi_reset_protocol_init(const struct scmi_protocol_handle *ph)
 	}
 
 	pinfo->version = version;
-	return ph->set_priv(ph, pinfo);
+	return ph->set_priv(ph, pinfo, version);
 }
 
 static const struct scmi_protocol scmi_reset = {
@@ -351,6 +355,7 @@ static const struct scmi_protocol scmi_reset = {
 	.instance_init = &scmi_reset_protocol_init,
 	.ops = &reset_proto_ops,
 	.events = &reset_protocol_events,
+	.supported_version = SCMI_PROTOCOL_SUPPORTED_VERSION,
 };
 
 DEFINE_SCMI_PROTOCOL_REGISTER_UNREGISTER(reset, scmi_reset)
diff --git a/drivers/firmware/arm_scmi/sensors.c b/drivers/firmware/arm_scmi/sensors.c
index 0b5853fa9d87..311149965370 100644
--- a/drivers/firmware/arm_scmi/sensors.c
+++ b/drivers/firmware/arm_scmi/sensors.c
@@ -14,6 +14,9 @@
 #include "protocols.h"
 #include "notify.h"
 
+/* Updated only after ALL the mandatory features for that version are merged */
+#define SCMI_PROTOCOL_SUPPORTED_VERSION		0x30000
+
 #define SCMI_MAX_NUM_SENSOR_AXIS	63
 #define	SCMIv2_SENSOR_PROTOCOL		0x10000
 
@@ -644,7 +647,7 @@ iter_sens_descr_process_response(const struct scmi_protocol_handle *ph,
 	if (PROTOCOL_REV_MAJOR(si->version) >= 0x3 &&
 	    SUPPORTS_EXTENDED_NAMES(attrl))
 		ph->hops->extended_name_get(ph, SENSOR_NAME_GET, s->id,
-					    s->name, SCMI_MAX_STR_SIZE);
+					    NULL, s->name, SCMI_MAX_STR_SIZE);
 
 	if (s->extended_scalar_attrs) {
 		s->sensor_power = le32_to_cpu(sdesc->power);
@@ -1138,7 +1141,7 @@ static int scmi_sensors_protocol_init(const struct scmi_protocol_handle *ph)
 	if (ret)
 		return ret;
 
-	return ph->set_priv(ph, sinfo);
+	return ph->set_priv(ph, sinfo, version);
 }
 
 static const struct scmi_protocol scmi_sensors = {
@@ -1147,6 +1150,7 @@ static const struct scmi_protocol scmi_sensors = {
 	.instance_init = &scmi_sensors_protocol_init,
 	.ops = &sensor_proto_ops,
 	.events = &sensor_protocol_events,
+	.supported_version = SCMI_PROTOCOL_SUPPORTED_VERSION,
 };
 
 DEFINE_SCMI_PROTOCOL_REGISTER_UNREGISTER(sensors, scmi_sensors)
diff --git a/drivers/firmware/arm_scmi/system.c b/drivers/firmware/arm_scmi/system.c
index 9383d7584539..1621da97bcbb 100644
--- a/drivers/firmware/arm_scmi/system.c
+++ b/drivers/firmware/arm_scmi/system.c
@@ -13,6 +13,9 @@
 #include "protocols.h"
 #include "notify.h"
 
+/* Updated only after ALL the mandatory features for that version are merged */
+#define SCMI_PROTOCOL_SUPPORTED_VERSION		0x20000
+
 #define SCMI_SYSTEM_NUM_SOURCES		1
 
 enum scmi_system_protocol_cmd {
@@ -144,7 +147,7 @@ static int scmi_system_protocol_init(const struct scmi_protocol_handle *ph)
 	if (PROTOCOL_REV_MAJOR(pinfo->version) >= 0x2)
 		pinfo->graceful_timeout_supported = true;
 
-	return ph->set_priv(ph, pinfo);
+	return ph->set_priv(ph, pinfo, version);
 }
 
 static const struct scmi_protocol scmi_system = {
@@ -153,6 +156,7 @@ static const struct scmi_protocol scmi_system = {
 	.instance_init = &scmi_system_protocol_init,
 	.ops = NULL,
 	.events = &system_protocol_events,
+	.supported_version = SCMI_PROTOCOL_SUPPORTED_VERSION,
 };
 
 DEFINE_SCMI_PROTOCOL_REGISTER_UNREGISTER(system, scmi_system)
diff --git a/drivers/firmware/arm_scmi/voltage.c b/drivers/firmware/arm_scmi/voltage.c
index eaa8d944926a..2175ffd6cef5 100644
--- a/drivers/firmware/arm_scmi/voltage.c
+++ b/drivers/firmware/arm_scmi/voltage.c
@@ -10,6 +10,9 @@
 
 #include "protocols.h"
 
+/* Updated only after ALL the mandatory features for that version are merged */
+#define SCMI_PROTOCOL_SUPPORTED_VERSION		0x20000
+
 #define VOLTAGE_DOMS_NUM_MASK		GENMASK(15, 0)
 #define REMAINING_LEVELS_MASK		GENMASK(31, 16)
 #define RETURNED_LEVELS_MASK		GENMASK(11, 0)
@@ -242,7 +245,7 @@ static int scmi_voltage_descriptors_get(const struct scmi_protocol_handle *ph,
 			if (SUPPORTS_EXTENDED_NAMES(attributes))
 				ph->hops->extended_name_get(ph,
 							VOLTAGE_DOMAIN_NAME_GET,
-							v->id, v->name,
+							v->id, NULL, v->name,
 							SCMI_MAX_STR_SIZE);
 			if (SUPPORTS_ASYNC_LEVEL_SET(attributes))
 				v->async_level_set = true;
@@ -432,7 +435,7 @@ static int scmi_voltage_protocol_init(const struct scmi_protocol_handle *ph)
 		dev_warn(ph->dev, "No Voltage domains found.\n");
 	}
 
-	return ph->set_priv(ph, vinfo);
+	return ph->set_priv(ph, vinfo, version);
 }
 
 static const struct scmi_protocol scmi_voltage = {
@@ -440,6 +443,7 @@ static const struct scmi_protocol scmi_voltage = {
 	.owner = THIS_MODULE,
 	.instance_init = &scmi_voltage_protocol_init,
 	.ops = &voltage_proto_ops,
+	.supported_version = SCMI_PROTOCOL_SUPPORTED_VERSION,
 };
 
 DEFINE_SCMI_PROTOCOL_REGISTER_UNREGISTER(voltage, scmi_voltage)
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index cb374b2da9b7..72f2537d90ca 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -301,3 +301,18 @@ config UEFI_CPER_X86
 	bool
 	depends on UEFI_CPER && X86
 	default y
+
+config TEE_STMM_EFI
+	tristate "TEE-based EFI runtime variable service driver"
+	depends on EFI && OPTEE
+	help
+	  Select this config option if TEE is compiled to include StandAloneMM
+	  as a separate secure partition. It has the ability to check and store
+	  EFI variables on an RPMB or any other non-volatile medium used by
+	  StandAloneMM.
+
+	  Enabling this will change the EFI runtime services from the firmware
+	  provided functions to TEE calls.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called tee_stmm_efi.
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index e489fefd23da..a2d0009560d0 100644
--- a/drivers/firmware/efi/Makefile
+++ b/drivers/firmware/efi/Makefile
@@ -42,3 +42,4 @@ obj-$(CONFIG_EFI_EARLYCON)		+= earlycon.o
 obj-$(CONFIG_UEFI_CPER_ARM)		+= cper-arm.o
 obj-$(CONFIG_UEFI_CPER_X86)		+= cper-x86.o
 obj-$(CONFIG_UNACCEPTED_MEMORY)		+= unaccepted_memory.o
+obj-$(CONFIG_TEE_STMM_EFI)		+= stmm/tee_stmm_efi.o
diff --git a/drivers/firmware/efi/dev-path-parser.c b/drivers/firmware/efi/dev-path-parser.c
index f80d87c199c3..937be269fee8 100644
--- a/drivers/firmware/efi/dev-path-parser.c
+++ b/drivers/firmware/efi/dev-path-parser.c
@@ -18,8 +18,6 @@ static long __init parse_acpi_path(const struct efi_dev_path *node,
 	struct acpi_device *adev;
 	struct device *phys_dev;
 	char hid[ACPI_ID_LEN];
-	u64 uid;
-	int ret;
 
 	if (node->header.length != 12)
 		return -EINVAL;
@@ -31,10 +29,9 @@ static long __init parse_acpi_path(const struct efi_dev_path *node,
 			node->acpi.hid >> 16);
 
 	for_each_acpi_dev_match(adev, hid, NULL, -1) {
-		ret = acpi_dev_uid_to_integer(adev, &uid);
-		if (ret == 0 && node->acpi.uid == uid)
+		if (acpi_dev_uid_match(adev, node->acpi.uid))
 			break;
-		if (ret == -ENODATA && node->acpi.uid == 0)
+		if (!acpi_device_uid(adev) && node->acpi.uid == 0)
 			break;
 	}
 	if (!adev)
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 9d3910d1abe1..4fcda50acfa4 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -32,6 +32,7 @@
 #include <linux/ucs2_string.h>
 #include <linux/memblock.h>
 #include <linux/security.h>
+#include <linux/notifier.h>
 
 #include <asm/early_ioremap.h>
 
@@ -187,6 +188,9 @@ static const struct attribute_group efi_subsys_attr_group = {
 	.is_visible = efi_attr_is_visible,
 };
 
+struct blocking_notifier_head efivar_ops_nh;
+EXPORT_SYMBOL_GPL(efivar_ops_nh);
+
 static struct efivars generic_efivars;
 static struct efivar_operations generic_ops;
 
@@ -231,6 +235,18 @@ static void generic_ops_unregister(void)
 	efivars_unregister(&generic_efivars);
 }
 
+void efivars_generic_ops_register(void)
+{
+	generic_ops_register();
+}
+EXPORT_SYMBOL_GPL(efivars_generic_ops_register);
+
+void efivars_generic_ops_unregister(void)
+{
+	generic_ops_unregister();
+}
+EXPORT_SYMBOL_GPL(efivars_generic_ops_unregister);
+
 #ifdef CONFIG_EFI_CUSTOM_SSDT_OVERLAYS
 #define EFIVAR_SSDT_NAME_MAX	16UL
 static char efivar_ssdt[EFIVAR_SSDT_NAME_MAX] __initdata;
@@ -419,6 +435,8 @@ static int __init efisubsys_init(void)
 		platform_device_register_simple("efivars", 0, NULL, 0);
 	}
 
+	BLOCKING_INIT_NOTIFIER_HEAD(&efivar_ops_nh);
+
 	error = sysfs_create_group(efi_kobj, &efi_subsys_attr_group);
 	if (error) {
 		pr_err("efi: Sysfs attribute export failed with error %d.\n",
diff --git a/drivers/firmware/efi/libstub/Makefile.zboot b/drivers/firmware/efi/libstub/Makefile.zboot
index 2c489627a807..65ffd0b760b2 100644
--- a/drivers/firmware/efi/libstub/Makefile.zboot
+++ b/drivers/firmware/efi/libstub/Makefile.zboot
@@ -5,8 +5,8 @@
 # EFI_ZBOOT_FORWARD_CFI
 
 quiet_cmd_copy_and_pad = PAD     $@
-      cmd_copy_and_pad = cp $< $@ && \
-			 truncate -s $(shell hexdump -s16 -n4 -e '"%u"' $<) $@
+      cmd_copy_and_pad = cp $< $@; \
+			 truncate -s $$(hexdump -s16 -n4 -e '"%u"' $<) $@
 
 # Pad the file to the size of the uncompressed image in memory, including BSS
 $(obj)/vmlinux.bin: $(obj)/$(EFI_ZBOOT_PAYLOAD) FORCE
diff --git a/drivers/firmware/efi/libstub/loongarch-stub.c b/drivers/firmware/efi/libstub/loongarch-stub.c
index 72c71ae201f0..736b6aae323d 100644
--- a/drivers/firmware/efi/libstub/loongarch-stub.c
+++ b/drivers/firmware/efi/libstub/loongarch-stub.c
@@ -8,10 +8,10 @@
 #include <asm/efi.h>
 #include <asm/addrspace.h>
 #include "efistub.h"
+#include "loongarch-stub.h"
 
 extern int kernel_asize;
 extern int kernel_fsize;
-extern int kernel_offset;
 extern int kernel_entry;
 
 efi_status_t handle_kernel_image(unsigned long *image_addr,
@@ -24,7 +24,7 @@ efi_status_t handle_kernel_image(unsigned long *image_addr,
 	efi_status_t status;
 	unsigned long kernel_addr = 0;
 
-	kernel_addr = (unsigned long)&kernel_offset - kernel_offset;
+	kernel_addr = (unsigned long)image->image_base;
 
 	status = efi_relocate_kernel(&kernel_addr, kernel_fsize, kernel_asize,
 		     EFI_KIMG_PREFERRED_ADDRESS, efi_get_kimg_min_align(), 0x0);
@@ -35,9 +35,10 @@ efi_status_t handle_kernel_image(unsigned long *image_addr,
 	return status;
 }
 
-unsigned long kernel_entry_address(void)
+unsigned long kernel_entry_address(unsigned long kernel_addr,
+		efi_loaded_image_t *image)
 {
-	unsigned long base = (unsigned long)&kernel_offset - kernel_offset;
+	unsigned long base = (unsigned long)image->image_base;
 
-	return (unsigned long)&kernel_entry - base + VMLINUX_LOAD_ADDRESS;
+	return (unsigned long)&kernel_entry - base + kernel_addr;
 }
diff --git a/drivers/firmware/efi/libstub/loongarch-stub.h b/drivers/firmware/efi/libstub/loongarch-stub.h
new file mode 100644
index 000000000000..cd015955a015
--- /dev/null
+++ b/drivers/firmware/efi/libstub/loongarch-stub.h
@@ -0,0 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+unsigned long kernel_entry_address(unsigned long kernel_addr,
+		efi_loaded_image_t *image);
diff --git a/drivers/firmware/efi/libstub/loongarch.c b/drivers/firmware/efi/libstub/loongarch.c
index 807cba2693fc..684c9354637c 100644
--- a/drivers/firmware/efi/libstub/loongarch.c
+++ b/drivers/firmware/efi/libstub/loongarch.c
@@ -8,6 +8,7 @@
 #include <asm/efi.h>
 #include <asm/addrspace.h>
 #include "efistub.h"
+#include "loongarch-stub.h"
 
 typedef void __noreturn (*kernel_entry_t)(bool efi, unsigned long cmdline,
 					  unsigned long systab);
@@ -37,9 +38,10 @@ static efi_status_t exit_boot_func(struct efi_boot_memmap *map, void *priv)
 	return EFI_SUCCESS;
 }
 
-unsigned long __weak kernel_entry_address(void)
+unsigned long __weak kernel_entry_address(unsigned long kernel_addr,
+		efi_loaded_image_t *image)
 {
-	return *(unsigned long *)(PHYSADDR(VMLINUX_LOAD_ADDRESS) + 8);
+	return *(unsigned long *)(kernel_addr + 8) - VMLINUX_LOAD_ADDRESS + kernel_addr;
 }
 
 efi_status_t efi_boot_kernel(void *handle, efi_loaded_image_t *image,
@@ -73,7 +75,7 @@ efi_status_t efi_boot_kernel(void *handle, efi_loaded_image_t *image,
 	csr_write64(CSR_DMW0_INIT, LOONGARCH_CSR_DMWIN0);
 	csr_write64(CSR_DMW1_INIT, LOONGARCH_CSR_DMWIN1);
 
-	real_kernel_entry = (void *)kernel_entry_address();
+	real_kernel_entry = (void *)kernel_entry_address(kernel_addr, image);
 
 	real_kernel_entry(true, (unsigned long)cmdline_ptr,
 			  (unsigned long)efi_system_table);
diff --git a/drivers/firmware/efi/libstub/x86-5lvl.c b/drivers/firmware/efi/libstub/x86-5lvl.c
index 479dd445acdc..77359e802181 100644
--- a/drivers/firmware/efi/libstub/x86-5lvl.c
+++ b/drivers/firmware/efi/libstub/x86-5lvl.c
@@ -13,8 +13,8 @@ bool efi_no5lvl;
 static void (*la57_toggle)(void *cr3);
 
 static const struct desc_struct gdt[] = {
-	[GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(0xc09b, 0, 0xfffff),
-	[GDT_ENTRY_KERNEL_CS]   = GDT_ENTRY_INIT(0xa09b, 0, 0xfffff),
+	[GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(DESC_CODE32, 0, 0xfffff),
+	[GDT_ENTRY_KERNEL_CS]   = GDT_ENTRY_INIT(DESC_CODE64, 0, 0xfffff),
 };
 
 /*
diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c
index 1bfdae34df39..0d510c9a06a4 100644
--- a/drivers/firmware/efi/libstub/x86-stub.c
+++ b/drivers/firmware/efi/libstub/x86-stub.c
@@ -307,17 +307,20 @@ static void setup_unaccepted_memory(void)
 		efi_err("Memory acceptance protocol failed\n");
 }
 
+static efi_char16_t *efistub_fw_vendor(void)
+{
+	unsigned long vendor = efi_table_attr(efi_system_table, fw_vendor);
+
+	return (efi_char16_t *)vendor;
+}
+
 static const efi_char16_t apple[] = L"Apple";
 
 static void setup_quirks(struct boot_params *boot_params)
 {
-	efi_char16_t *fw_vendor = (efi_char16_t *)(unsigned long)
-		efi_table_attr(efi_system_table, fw_vendor);
-
-	if (!memcmp(fw_vendor, apple, sizeof(apple))) {
-		if (IS_ENABLED(CONFIG_APPLE_PROPERTIES))
-			retrieve_apple_device_properties(boot_params);
-	}
+	if (IS_ENABLED(CONFIG_APPLE_PROPERTIES) &&
+	    !memcmp(efistub_fw_vendor(), apple, sizeof(apple)))
+		retrieve_apple_device_properties(boot_params);
 }
 
 /*
@@ -765,11 +768,27 @@ static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry)
 
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && !efi_nokaslr) {
 		u64 range = KERNEL_IMAGE_SIZE - LOAD_PHYSICAL_ADDR - kernel_total_size;
+		static const efi_char16_t ami[] = L"American Megatrends";
 
 		efi_get_seed(seed, sizeof(seed));
 
 		virt_addr += (range * seed[1]) >> 32;
 		virt_addr &= ~(CONFIG_PHYSICAL_ALIGN - 1);
+
+		/*
+		 * Older Dell systems with AMI UEFI firmware v2.0 may hang
+		 * while decompressing the kernel if physical address
+		 * randomization is enabled.
+		 *
+		 * https://bugzilla.kernel.org/show_bug.cgi?id=218173
+		 */
+		if (efi_system_table->hdr.revision <= EFI_2_00_SYSTEM_TABLE_REVISION &&
+		    !memcmp(efistub_fw_vendor(), ami, sizeof(ami))) {
+			efi_debug("AMI firmware v2.0 or older detected - disabling physical KASLR\n");
+			seed[0] = 0;
+		}
+
+		boot_params_ptr->hdr.loadflags |= KASLR_FLAG;
 	}
 
 	status = efi_random_alloc(alloc_size, CONFIG_PHYSICAL_ALIGN, &addr,
diff --git a/drivers/firmware/efi/memmap.c b/drivers/firmware/efi/memmap.c
index a1180461a445..3365944f7965 100644
--- a/drivers/firmware/efi/memmap.c
+++ b/drivers/firmware/efi/memmap.c
@@ -32,7 +32,7 @@
  * space isn't setup.  Once the kernel is fully booted we can fallback
  * to the more robust memremap*() API.
  *
- * Returns zero on success, a negative error code on failure.
+ * Returns: zero on success, a negative error code on failure.
  */
 int __init __efi_memmap_init(struct efi_memory_map_data *data)
 {
@@ -77,6 +77,8 @@ int __init __efi_memmap_init(struct efi_memory_map_data *data)
  *
  * Use early_memremap() to map the passed in EFI memory map and assign
  * it to efi.memmap.
+ *
+ * Returns: zero on success, a negative error code on failure.
  */
 int __init efi_memmap_init_early(struct efi_memory_map_data *data)
 {
@@ -107,7 +109,7 @@ void __init efi_memmap_unmap(void)
 
 /**
  * efi_memmap_init_late - Map efi.memmap with memremap()
- * @phys_addr: Physical address of the new EFI memory map
+ * @addr: Physical address of the new EFI memory map
  * @size: Size in bytes of the new EFI memory map
  *
  * Setup a mapping of the EFI memory map using ioremap_cache(). This
@@ -126,7 +128,7 @@ void __init efi_memmap_unmap(void)
  * runtime so that things like efi_mem_desc_lookup() and
  * efi_mem_attributes() always work.
  *
- * Returns zero on success, a negative error code on failure.
+ * Returns: zero on success, a negative error code on failure.
  */
 int __init efi_memmap_init_late(phys_addr_t addr, unsigned long size)
 {
diff --git a/drivers/firmware/efi/stmm/mm_communication.h b/drivers/firmware/efi/stmm/mm_communication.h
new file mode 100644
index 000000000000..52a1f32cd1eb
--- /dev/null
+++ b/drivers/firmware/efi/stmm/mm_communication.h
@@ -0,0 +1,236 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ *  Headers for EFI variable service via StandAloneMM, EDK2 application running
+ *  in OP-TEE. Most of the structs and defines resemble the EDK2 naming.
+ *
+ *  Copyright (c) 2017, Intel Corporation. All rights reserved.
+ *  Copyright (C) 2020 Linaro Ltd.
+ */
+
+#ifndef _MM_COMMUNICATION_H_
+#define _MM_COMMUNICATION_H_
+
+/*
+ * Interface to the pseudo Trusted Application (TA), which provides a
+ * communication channel with the Standalone MM (Management Mode)
+ * Secure Partition running at Secure-EL0
+ */
+
+#define PTA_STMM_CMD_COMMUNICATE 0
+
+/*
+ * Defined in OP-TEE, this UUID is used to identify the pseudo-TA.
+ * OP-TEE is using big endian GUIDs while UEFI uses little endian ones
+ */
+#define PTA_STMM_UUID \
+	UUID_INIT(0xed32d533, 0x99e6, 0x4209, \
+		  0x9c, 0xc0, 0x2d, 0x72, 0xcd, 0xd9, 0x98, 0xa7)
+
+#define EFI_MM_VARIABLE_GUID \
+	EFI_GUID(0xed32d533, 0x99e6, 0x4209, \
+		 0x9c, 0xc0, 0x2d, 0x72, 0xcd, 0xd9, 0x98, 0xa7)
+
+/**
+ * struct efi_mm_communicate_header - Header used for SMM variable communication
+
+ * @header_guid:  header use for disambiguation of content
+ * @message_len:  length of the message. Does not include the size of the
+ *                header
+ * @data:         payload of the message
+ *
+ * Defined in the PI spec as EFI_MM_COMMUNICATE_HEADER.
+ * To avoid confusion in interpreting frames, the communication buffer should
+ * always begin with efi_mm_communicate_header.
+ */
+struct efi_mm_communicate_header {
+	efi_guid_t header_guid;
+	size_t     message_len;
+	u8         data[];
+} __packed;
+
+#define MM_COMMUNICATE_HEADER_SIZE \
+	(sizeof(struct efi_mm_communicate_header))
+
+/* SPM return error codes */
+#define ARM_SVC_SPM_RET_SUCCESS               0
+#define ARM_SVC_SPM_RET_NOT_SUPPORTED        -1
+#define ARM_SVC_SPM_RET_INVALID_PARAMS       -2
+#define ARM_SVC_SPM_RET_DENIED               -3
+#define ARM_SVC_SPM_RET_NO_MEMORY            -5
+
+#define SMM_VARIABLE_FUNCTION_GET_VARIABLE  1
+/*
+ * The payload for this function is
+ * SMM_VARIABLE_COMMUNICATE_GET_NEXT_VARIABLE_NAME.
+ */
+#define SMM_VARIABLE_FUNCTION_GET_NEXT_VARIABLE_NAME  2
+/*
+ * The payload for this function is SMM_VARIABLE_COMMUNICATE_ACCESS_VARIABLE.
+ */
+#define SMM_VARIABLE_FUNCTION_SET_VARIABLE  3
+/*
+ * The payload for this function is
+ * SMM_VARIABLE_COMMUNICATE_QUERY_VARIABLE_INFO.
+ */
+#define SMM_VARIABLE_FUNCTION_QUERY_VARIABLE_INFO  4
+/*
+ * It is a notify event, no extra payload for this function.
+ */
+#define SMM_VARIABLE_FUNCTION_READY_TO_BOOT  5
+/*
+ * It is a notify event, no extra payload for this function.
+ */
+#define SMM_VARIABLE_FUNCTION_EXIT_BOOT_SERVICE  6
+/*
+ * The payload for this function is VARIABLE_INFO_ENTRY.
+ * The GUID in EFI_SMM_COMMUNICATE_HEADER is gEfiSmmVariableProtocolGuid.
+ */
+#define SMM_VARIABLE_FUNCTION_GET_STATISTICS  7
+/*
+ * The payload for this function is SMM_VARIABLE_COMMUNICATE_LOCK_VARIABLE
+ */
+#define SMM_VARIABLE_FUNCTION_LOCK_VARIABLE   8
+
+#define SMM_VARIABLE_FUNCTION_VAR_CHECK_VARIABLE_PROPERTY_SET  9
+
+#define SMM_VARIABLE_FUNCTION_VAR_CHECK_VARIABLE_PROPERTY_GET  10
+
+#define SMM_VARIABLE_FUNCTION_GET_PAYLOAD_SIZE  11
+/*
+ * The payload for this function is
+ * SMM_VARIABLE_COMMUNICATE_RUNTIME_VARIABLE_CACHE_CONTEXT
+ */
+#define SMM_VARIABLE_FUNCTION_INIT_RUNTIME_VARIABLE_CACHE_CONTEXT 12
+
+#define SMM_VARIABLE_FUNCTION_SYNC_RUNTIME_CACHE  13
+/*
+ * The payload for this function is
+ * SMM_VARIABLE_COMMUNICATE_GET_RUNTIME_CACHE_INFO
+ */
+#define SMM_VARIABLE_FUNCTION_GET_RUNTIME_CACHE_INFO  14
+
+/**
+ * struct smm_variable_communicate_header - Used for SMM variable communication
+
+ * @function:     function to call in Smm.
+ * @ret_status:   return status
+ * @data:         payload
+ */
+struct smm_variable_communicate_header {
+	size_t  function;
+	efi_status_t ret_status;
+	u8 data[];
+};
+
+#define MM_VARIABLE_COMMUNICATE_SIZE \
+	(sizeof(struct smm_variable_communicate_header))
+
+/**
+ * struct smm_variable_access - Used to communicate with StMM by
+ *                              SetVariable and GetVariable.
+
+ * @guid:         vendor GUID
+ * @data_size:    size of EFI variable data
+ * @name_size:    size of EFI name
+ * @attr:         attributes
+ * @name:         variable name
+ *
+ */
+struct smm_variable_access {
+	efi_guid_t  guid;
+	size_t data_size;
+	size_t name_size;
+	u32 attr;
+	u16 name[];
+};
+
+#define MM_VARIABLE_ACCESS_HEADER_SIZE \
+	(sizeof(struct smm_variable_access))
+/**
+ * struct smm_variable_payload_size - Used to get the max allowed
+ *                                    payload used in StMM.
+ *
+ * @size:  size to fill in
+ *
+ */
+struct smm_variable_payload_size {
+	size_t size;
+};
+
+/**
+ * struct smm_variable_getnext - Used to communicate with StMM for
+ *                               GetNextVariableName.
+ *
+ * @guid:       vendor GUID
+ * @name_size:  size of the name of the variable
+ * @name:       variable name
+ *
+ */
+struct smm_variable_getnext {
+	efi_guid_t  guid;
+	size_t name_size;
+	u16         name[];
+};
+
+#define MM_VARIABLE_GET_NEXT_HEADER_SIZE \
+	(sizeof(struct smm_variable_getnext))
+
+/**
+ * struct smm_variable_query_info - Used to communicate with StMM for
+ *                                  QueryVariableInfo.
+ *
+ * @max_variable_storage:        max available storage
+ * @remaining_variable_storage:  remaining available storage
+ * @max_variable_size:           max variable supported size
+ * @attr:                        attributes to query storage for
+ *
+ */
+struct smm_variable_query_info {
+	u64 max_variable_storage;
+	u64 remaining_variable_storage;
+	u64 max_variable_size;
+	u32 attr;
+};
+
+#define VAR_CHECK_VARIABLE_PROPERTY_REVISION 0x0001
+#define VAR_CHECK_VARIABLE_PROPERTY_READ_ONLY BIT(0)
+/**
+ * struct var_check_property - Used to store variable properties in StMM
+ *
+ * @revision:   magic revision number for variable property checking
+ * @property:   properties mask for the variable used in StMM.
+ *              Currently RO flag is supported
+ * @attributes: variable attributes used in StMM checking when properties
+ *              for a variable are enabled
+ * @minsize:    minimum allowed size for variable payload checked against
+ *              smm_variable_access->datasize in StMM
+ * @maxsize:    maximum allowed size for variable payload checked against
+ *              smm_variable_access->datasize in StMM
+ *
+ */
+struct var_check_property {
+	u16 revision;
+	u16 property;
+	u32 attributes;
+	size_t minsize;
+	size_t maxsize;
+};
+
+/**
+ * struct smm_variable_var_check_property - Used to communicate variable
+ *                                          properties with StMM
+ *
+ * @guid:       vendor GUID
+ * @name_size:  size of EFI name
+ * @property:   variable properties struct
+ * @name:       variable name
+ *
+ */
+struct smm_variable_var_check_property {
+	efi_guid_t guid;
+	size_t name_size;
+	struct var_check_property property;
+	u16 name[];
+};
+
+#endif /* _MM_COMMUNICATION_H_ */
diff --git a/drivers/firmware/efi/stmm/tee_stmm_efi.c b/drivers/firmware/efi/stmm/tee_stmm_efi.c
new file mode 100644
index 000000000000..f741ca279052
--- /dev/null
+++ b/drivers/firmware/efi/stmm/tee_stmm_efi.c
@@ -0,0 +1,616 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ *  EFI variable service via TEE
+ *
+ *  Copyright (C) 2022 Linaro
+ */
+
+#include <linux/efi.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/tee.h>
+#include <linux/tee_drv.h>
+#include <linux/ucs2_string.h>
+#include "mm_communication.h"
+
+static struct efivars tee_efivars;
+static struct efivar_operations tee_efivar_ops;
+
+static size_t max_buffer_size; /* comm + var + func + data */
+static size_t max_payload_size; /* func + data */
+
+struct tee_stmm_efi_private {
+	struct tee_context *ctx;
+	u32 session;
+	struct device *dev;
+};
+
+static struct tee_stmm_efi_private pvt_data;
+
+/* UUID of the stmm PTA */
+static const struct tee_client_device_id tee_stmm_efi_id_table[] = {
+	{PTA_STMM_UUID},
+	{}
+};
+
+static int tee_ctx_match(struct tee_ioctl_version_data *ver, const void *data)
+{
+	/* currently only OP-TEE is supported as a communication path */
+	if (ver->impl_id == TEE_IMPL_ID_OPTEE)
+		return 1;
+	else
+		return 0;
+}
+
+/**
+ * tee_mm_communicate() - Pass a buffer to StandaloneMM running in TEE
+ *
+ * @comm_buf:		locally allocated communication buffer
+ * @dsize:		buffer size
+ * Return:		status code
+ */
+static efi_status_t tee_mm_communicate(void *comm_buf, size_t dsize)
+{
+	size_t buf_size;
+	struct efi_mm_communicate_header *mm_hdr;
+	struct tee_ioctl_invoke_arg arg;
+	struct tee_param param[4];
+	struct tee_shm *shm = NULL;
+	int rc;
+
+	if (!comm_buf)
+		return EFI_INVALID_PARAMETER;
+
+	mm_hdr = (struct efi_mm_communicate_header *)comm_buf;
+	buf_size = mm_hdr->message_len + sizeof(efi_guid_t) + sizeof(size_t);
+
+	if (dsize != buf_size)
+		return EFI_INVALID_PARAMETER;
+
+	shm = tee_shm_register_kernel_buf(pvt_data.ctx, comm_buf, buf_size);
+	if (IS_ERR(shm)) {
+		dev_err(pvt_data.dev, "Unable to register shared memory\n");
+		return EFI_UNSUPPORTED;
+	}
+
+	memset(&arg, 0, sizeof(arg));
+	arg.func = PTA_STMM_CMD_COMMUNICATE;
+	arg.session = pvt_data.session;
+	arg.num_params = 4;
+
+	memset(param, 0, sizeof(param));
+	param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT;
+	param[0].u.memref.size = buf_size;
+	param[0].u.memref.shm = shm;
+	param[1].attr = TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_OUTPUT;
+	param[2].attr = TEE_IOCTL_PARAM_ATTR_TYPE_NONE;
+	param[3].attr = TEE_IOCTL_PARAM_ATTR_TYPE_NONE;
+
+	rc = tee_client_invoke_func(pvt_data.ctx, &arg, param);
+	tee_shm_free(shm);
+
+	if (rc < 0 || arg.ret != 0) {
+		dev_err(pvt_data.dev,
+			"PTA_STMM_CMD_COMMUNICATE invoke error: 0x%x\n", arg.ret);
+		return EFI_DEVICE_ERROR;
+	}
+
+	switch (param[1].u.value.a) {
+	case ARM_SVC_SPM_RET_SUCCESS:
+		return EFI_SUCCESS;
+
+	case ARM_SVC_SPM_RET_INVALID_PARAMS:
+		return EFI_INVALID_PARAMETER;
+
+	case ARM_SVC_SPM_RET_DENIED:
+		return EFI_ACCESS_DENIED;
+
+	case ARM_SVC_SPM_RET_NO_MEMORY:
+		return EFI_OUT_OF_RESOURCES;
+
+	default:
+		return EFI_ACCESS_DENIED;
+	}
+}
+
+/**
+ * mm_communicate() - Adjust the communication buffer to StandAlonneMM and send
+ * it to TEE
+ *
+ * @comm_buf:		locally allocated communication buffer, buffer should
+ *			be enough big to have some headers and payload
+ * @payload_size:	payload size
+ * Return:		status code
+ */
+static efi_status_t mm_communicate(u8 *comm_buf, size_t payload_size)
+{
+	size_t dsize;
+	efi_status_t ret;
+	struct efi_mm_communicate_header *mm_hdr;
+	struct smm_variable_communicate_header *var_hdr;
+
+	dsize = payload_size + MM_COMMUNICATE_HEADER_SIZE +
+		MM_VARIABLE_COMMUNICATE_SIZE;
+	mm_hdr = (struct efi_mm_communicate_header *)comm_buf;
+	var_hdr = (struct smm_variable_communicate_header *)mm_hdr->data;
+
+	ret = tee_mm_communicate(comm_buf, dsize);
+	if (ret != EFI_SUCCESS) {
+		dev_err(pvt_data.dev, "%s failed!\n", __func__);
+		return ret;
+	}
+
+	return var_hdr->ret_status;
+}
+
+/**
+ * setup_mm_hdr() -	Allocate a buffer for StandAloneMM and initialize the
+ *			header data.
+ *
+ * @dptr:		pointer address to store allocated buffer
+ * @payload_size:	payload size
+ * @func:		standAloneMM function number
+ * @ret:		EFI return code
+ * Return:		pointer to corresponding StandAloneMM function buffer or NULL
+ */
+static void *setup_mm_hdr(u8 **dptr, size_t payload_size, size_t func,
+			  efi_status_t *ret)
+{
+	const efi_guid_t mm_var_guid = EFI_MM_VARIABLE_GUID;
+	struct efi_mm_communicate_header *mm_hdr;
+	struct smm_variable_communicate_header *var_hdr;
+	u8 *comm_buf;
+
+	/* In the init function we initialize max_buffer_size with
+	 * get_max_payload(). So skip the test if max_buffer_size is initialized
+	 * StandAloneMM will perform similar checks and drop the buffer if it's
+	 * too long
+	 */
+	if (max_buffer_size &&
+	    max_buffer_size < (MM_COMMUNICATE_HEADER_SIZE +
+			       MM_VARIABLE_COMMUNICATE_SIZE + payload_size)) {
+		*ret = EFI_INVALID_PARAMETER;
+		return NULL;
+	}
+
+	comm_buf = kzalloc(MM_COMMUNICATE_HEADER_SIZE +
+				   MM_VARIABLE_COMMUNICATE_SIZE + payload_size,
+			   GFP_KERNEL);
+	if (!comm_buf) {
+		*ret = EFI_OUT_OF_RESOURCES;
+		return NULL;
+	}
+
+	mm_hdr = (struct efi_mm_communicate_header *)comm_buf;
+	memcpy(&mm_hdr->header_guid, &mm_var_guid, sizeof(mm_hdr->header_guid));
+	mm_hdr->message_len = MM_VARIABLE_COMMUNICATE_SIZE + payload_size;
+
+	var_hdr = (struct smm_variable_communicate_header *)mm_hdr->data;
+	var_hdr->function = func;
+	if (dptr)
+		*dptr = comm_buf;
+	*ret = EFI_SUCCESS;
+
+	return var_hdr->data;
+}
+
+/**
+ * get_max_payload() - Get variable payload size from StandAloneMM.
+ *
+ * @size:    size of the variable in storage
+ * Return:   status code
+ */
+static efi_status_t get_max_payload(size_t *size)
+{
+	struct smm_variable_payload_size *var_payload = NULL;
+	size_t payload_size;
+	u8 *comm_buf = NULL;
+	efi_status_t ret;
+
+	if (!size)
+		return EFI_INVALID_PARAMETER;
+
+	payload_size = sizeof(*var_payload);
+	var_payload = setup_mm_hdr(&comm_buf, payload_size,
+				   SMM_VARIABLE_FUNCTION_GET_PAYLOAD_SIZE,
+				   &ret);
+	if (!var_payload)
+		return EFI_OUT_OF_RESOURCES;
+
+	ret = mm_communicate(comm_buf, payload_size);
+	if (ret != EFI_SUCCESS)
+		goto out;
+
+	/* Make sure the buffer is big enough for storing variables */
+	if (var_payload->size < MM_VARIABLE_ACCESS_HEADER_SIZE + 0x20) {
+		ret = EFI_DEVICE_ERROR;
+		goto out;
+	}
+	*size = var_payload->size;
+	/*
+	 * There seems to be a bug in EDK2 miscalculating the boundaries and
+	 * size checks, so deduct 2 more bytes to fulfill this requirement. Fix
+	 * it up here to ensure backwards compatibility with older versions
+	 * (cf. StandaloneMmPkg/Drivers/StandaloneMmCpu/AArch64/EventHandle.c.
+	 * sizeof (EFI_MM_COMMUNICATE_HEADER) instead the size minus the
+	 * flexible array member).
+	 *
+	 * size is guaranteed to be > 2 due to checks on the beginning.
+	 */
+	*size -= 2;
+out:
+	kfree(comm_buf);
+	return ret;
+}
+
+static efi_status_t get_property_int(u16 *name, size_t name_size,
+				     const efi_guid_t *vendor,
+				     struct var_check_property *var_property)
+{
+	struct smm_variable_var_check_property *smm_property;
+	size_t payload_size;
+	u8 *comm_buf = NULL;
+	efi_status_t ret;
+
+	memset(var_property, 0, sizeof(*var_property));
+	payload_size = sizeof(*smm_property) + name_size;
+	if (payload_size > max_payload_size)
+		return EFI_INVALID_PARAMETER;
+
+	smm_property = setup_mm_hdr(
+		&comm_buf, payload_size,
+		SMM_VARIABLE_FUNCTION_VAR_CHECK_VARIABLE_PROPERTY_GET, &ret);
+	if (!smm_property)
+		return EFI_OUT_OF_RESOURCES;
+
+	memcpy(&smm_property->guid, vendor, sizeof(smm_property->guid));
+	smm_property->name_size = name_size;
+	memcpy(smm_property->name, name, name_size);
+
+	ret = mm_communicate(comm_buf, payload_size);
+	/*
+	 * Currently only R/O property is supported in StMM.
+	 * Variables that are not set to R/O will not set the property in StMM
+	 * and the call will return EFI_NOT_FOUND. We are setting the
+	 * properties to 0x0 so checking against that is enough for the
+	 * EFI_NOT_FOUND case.
+	 */
+	if (ret == EFI_NOT_FOUND)
+		ret = EFI_SUCCESS;
+	if (ret != EFI_SUCCESS)
+		goto out;
+	memcpy(var_property, &smm_property->property, sizeof(*var_property));
+
+out:
+	kfree(comm_buf);
+	return ret;
+}
+
+static efi_status_t tee_get_variable(u16 *name, efi_guid_t *vendor,
+				     u32 *attributes, unsigned long *data_size,
+				     void *data)
+{
+	struct var_check_property var_property;
+	struct smm_variable_access *var_acc;
+	size_t payload_size;
+	size_t name_size;
+	size_t tmp_dsize;
+	u8 *comm_buf = NULL;
+	efi_status_t ret;
+
+	if (!name || !vendor || !data_size)
+		return EFI_INVALID_PARAMETER;
+
+	name_size = (ucs2_strnlen(name, EFI_VAR_NAME_LEN) + 1) * sizeof(u16);
+	if (name_size > max_payload_size - MM_VARIABLE_ACCESS_HEADER_SIZE)
+		return EFI_INVALID_PARAMETER;
+
+	/* Trim output buffer size */
+	tmp_dsize = *data_size;
+	if (name_size + tmp_dsize >
+	    max_payload_size - MM_VARIABLE_ACCESS_HEADER_SIZE) {
+		tmp_dsize = max_payload_size - MM_VARIABLE_ACCESS_HEADER_SIZE -
+			    name_size;
+	}
+
+	payload_size = MM_VARIABLE_ACCESS_HEADER_SIZE + name_size + tmp_dsize;
+	var_acc = setup_mm_hdr(&comm_buf, payload_size,
+			       SMM_VARIABLE_FUNCTION_GET_VARIABLE, &ret);
+	if (!var_acc)
+		return EFI_OUT_OF_RESOURCES;
+
+	/* Fill in contents */
+	memcpy(&var_acc->guid, vendor, sizeof(var_acc->guid));
+	var_acc->data_size = tmp_dsize;
+	var_acc->name_size = name_size;
+	var_acc->attr = attributes ? *attributes : 0;
+	memcpy(var_acc->name, name, name_size);
+
+	ret = mm_communicate(comm_buf, payload_size);
+	if (ret == EFI_SUCCESS || ret == EFI_BUFFER_TOO_SMALL)
+		/* Update with reported data size for trimmed case */
+		*data_size = var_acc->data_size;
+	if (ret != EFI_SUCCESS)
+		goto out;
+
+	ret = get_property_int(name, name_size, vendor, &var_property);
+	if (ret != EFI_SUCCESS)
+		goto out;
+
+	if (attributes)
+		*attributes = var_acc->attr;
+
+	if (!data) {
+		ret = EFI_INVALID_PARAMETER;
+		goto out;
+	}
+	memcpy(data, (u8 *)var_acc->name + var_acc->name_size,
+	       var_acc->data_size);
+out:
+	kfree(comm_buf);
+	return ret;
+}
+
+static efi_status_t tee_get_next_variable(unsigned long *name_size,
+					  efi_char16_t *name, efi_guid_t *guid)
+{
+	struct smm_variable_getnext *var_getnext;
+	size_t payload_size;
+	size_t out_name_size;
+	size_t in_name_size;
+	u8 *comm_buf = NULL;
+	efi_status_t ret;
+
+	if (!name_size || !name || !guid)
+		return EFI_INVALID_PARAMETER;
+
+	out_name_size = *name_size;
+	in_name_size = (ucs2_strnlen(name, EFI_VAR_NAME_LEN) + 1) * sizeof(u16);
+
+	if (out_name_size < in_name_size)
+		return EFI_INVALID_PARAMETER;
+
+	if (in_name_size > max_payload_size - MM_VARIABLE_GET_NEXT_HEADER_SIZE)
+		return EFI_INVALID_PARAMETER;
+
+	/* Trim output buffer size */
+	if (out_name_size > max_payload_size - MM_VARIABLE_GET_NEXT_HEADER_SIZE)
+		out_name_size =
+			max_payload_size - MM_VARIABLE_GET_NEXT_HEADER_SIZE;
+
+	payload_size = MM_VARIABLE_GET_NEXT_HEADER_SIZE + out_name_size;
+	var_getnext = setup_mm_hdr(&comm_buf, payload_size,
+				   SMM_VARIABLE_FUNCTION_GET_NEXT_VARIABLE_NAME,
+				   &ret);
+	if (!var_getnext)
+		return EFI_OUT_OF_RESOURCES;
+
+	/* Fill in contents */
+	memcpy(&var_getnext->guid, guid, sizeof(var_getnext->guid));
+	var_getnext->name_size = out_name_size;
+	memcpy(var_getnext->name, name, in_name_size);
+	memset((u8 *)var_getnext->name + in_name_size, 0x0,
+	       out_name_size - in_name_size);
+
+	ret = mm_communicate(comm_buf, payload_size);
+	if (ret == EFI_SUCCESS || ret == EFI_BUFFER_TOO_SMALL) {
+		/* Update with reported data size for trimmed case */
+		*name_size = var_getnext->name_size;
+	}
+	if (ret != EFI_SUCCESS)
+		goto out;
+
+	memcpy(guid, &var_getnext->guid, sizeof(*guid));
+	memcpy(name, var_getnext->name, var_getnext->name_size);
+
+out:
+	kfree(comm_buf);
+	return ret;
+}
+
+static efi_status_t tee_set_variable(efi_char16_t *name, efi_guid_t *vendor,
+				     u32 attributes, unsigned long data_size,
+				     void *data)
+{
+	efi_status_t ret;
+	struct var_check_property var_property;
+	struct smm_variable_access *var_acc;
+	size_t payload_size;
+	size_t name_size;
+	u8 *comm_buf = NULL;
+
+	if (!name || name[0] == 0 || !vendor)
+		return EFI_INVALID_PARAMETER;
+
+	if (data_size > 0 && !data)
+		return EFI_INVALID_PARAMETER;
+
+	/* Check payload size */
+	name_size = (ucs2_strnlen(name, EFI_VAR_NAME_LEN) + 1) * sizeof(u16);
+	payload_size = MM_VARIABLE_ACCESS_HEADER_SIZE + name_size + data_size;
+	if (payload_size > max_payload_size)
+		return EFI_INVALID_PARAMETER;
+
+	/*
+	 * Allocate the buffer early, before switching to RW (if needed)
+	 * so we won't need to account for any failures in reading/setting
+	 * the properties, if the allocation fails
+	 */
+	var_acc = setup_mm_hdr(&comm_buf, payload_size,
+			       SMM_VARIABLE_FUNCTION_SET_VARIABLE, &ret);
+	if (!var_acc)
+		return EFI_OUT_OF_RESOURCES;
+
+	/*
+	 * The API has the ability to override RO flags. If no RO check was
+	 * requested switch the variable to RW for the duration of this call
+	 */
+	ret = get_property_int(name, name_size, vendor, &var_property);
+	if (ret != EFI_SUCCESS) {
+		dev_err(pvt_data.dev, "Getting variable property failed\n");
+		goto out;
+	}
+
+	if (var_property.property & VAR_CHECK_VARIABLE_PROPERTY_READ_ONLY) {
+		ret = EFI_WRITE_PROTECTED;
+		goto out;
+	}
+
+	/* Fill in contents */
+	memcpy(&var_acc->guid, vendor, sizeof(var_acc->guid));
+	var_acc->data_size = data_size;
+	var_acc->name_size = name_size;
+	var_acc->attr = attributes;
+	memcpy(var_acc->name, name, name_size);
+	memcpy((u8 *)var_acc->name + name_size, data, data_size);
+
+	ret = mm_communicate(comm_buf, payload_size);
+	dev_dbg(pvt_data.dev, "Set Variable %s %d %lx\n", __FILE__, __LINE__, ret);
+out:
+	kfree(comm_buf);
+	return ret;
+}
+
+static efi_status_t tee_set_variable_nonblocking(efi_char16_t *name,
+						 efi_guid_t *vendor,
+						 u32 attributes,
+						 unsigned long data_size,
+						 void *data)
+{
+	return EFI_UNSUPPORTED;
+}
+
+static efi_status_t tee_query_variable_info(u32 attributes,
+					    u64 *max_variable_storage_size,
+					    u64 *remain_variable_storage_size,
+					    u64 *max_variable_size)
+{
+	struct smm_variable_query_info *mm_query_info;
+	size_t payload_size;
+	efi_status_t ret;
+	u8 *comm_buf;
+
+	payload_size = sizeof(*mm_query_info);
+	mm_query_info = setup_mm_hdr(&comm_buf, payload_size,
+				SMM_VARIABLE_FUNCTION_QUERY_VARIABLE_INFO,
+				&ret);
+	if (!mm_query_info)
+		return EFI_OUT_OF_RESOURCES;
+
+	mm_query_info->attr = attributes;
+	ret = mm_communicate(comm_buf, payload_size);
+	if (ret != EFI_SUCCESS)
+		goto out;
+	*max_variable_storage_size = mm_query_info->max_variable_storage;
+	*remain_variable_storage_size =
+		mm_query_info->remaining_variable_storage;
+	*max_variable_size = mm_query_info->max_variable_size;
+
+out:
+	kfree(comm_buf);
+	return ret;
+}
+
+static void tee_stmm_efi_close_context(void *data)
+{
+	tee_client_close_context(pvt_data.ctx);
+}
+
+static void tee_stmm_efi_close_session(void *data)
+{
+	tee_client_close_session(pvt_data.ctx, pvt_data.session);
+}
+
+static void tee_stmm_restore_efivars_generic_ops(void)
+{
+	efivars_unregister(&tee_efivars);
+	efivars_generic_ops_register();
+}
+
+static int tee_stmm_efi_probe(struct device *dev)
+{
+	struct tee_ioctl_open_session_arg sess_arg;
+	efi_status_t ret;
+	int rc;
+
+	pvt_data.ctx = tee_client_open_context(NULL, tee_ctx_match, NULL, NULL);
+	if (IS_ERR(pvt_data.ctx))
+		return -ENODEV;
+
+	rc = devm_add_action_or_reset(dev, tee_stmm_efi_close_context, NULL);
+	if (rc)
+		return rc;
+
+	/* Open session with StMM PTA */
+	memset(&sess_arg, 0, sizeof(sess_arg));
+	export_uuid(sess_arg.uuid, &tee_stmm_efi_id_table[0].uuid);
+	rc = tee_client_open_session(pvt_data.ctx, &sess_arg, NULL);
+	if ((rc < 0) || (sess_arg.ret != 0)) {
+		dev_err(dev, "tee_client_open_session failed, err: %x\n",
+			sess_arg.ret);
+		return -EINVAL;
+	}
+	pvt_data.session = sess_arg.session;
+	pvt_data.dev = dev;
+	rc = devm_add_action_or_reset(dev, tee_stmm_efi_close_session, NULL);
+	if (rc)
+		return rc;
+
+	ret = get_max_payload(&max_payload_size);
+	if (ret != EFI_SUCCESS)
+		return -EIO;
+
+	max_buffer_size = MM_COMMUNICATE_HEADER_SIZE +
+			  MM_VARIABLE_COMMUNICATE_SIZE +
+			  max_payload_size;
+
+	tee_efivar_ops.get_variable		= tee_get_variable;
+	tee_efivar_ops.get_next_variable	= tee_get_next_variable;
+	tee_efivar_ops.set_variable		= tee_set_variable;
+	tee_efivar_ops.set_variable_nonblocking	= tee_set_variable_nonblocking;
+	tee_efivar_ops.query_variable_store	= efi_query_variable_store;
+	tee_efivar_ops.query_variable_info	= tee_query_variable_info;
+
+	efivars_generic_ops_unregister();
+	pr_info("Using TEE-based EFI runtime variable services\n");
+	efivars_register(&tee_efivars, &tee_efivar_ops);
+
+	return 0;
+}
+
+static int tee_stmm_efi_remove(struct device *dev)
+{
+	tee_stmm_restore_efivars_generic_ops();
+
+	return 0;
+}
+
+MODULE_DEVICE_TABLE(tee, tee_stmm_efi_id_table);
+
+static struct tee_client_driver tee_stmm_efi_driver = {
+	.id_table	= tee_stmm_efi_id_table,
+	.driver		= {
+		.name		= "tee-stmm-efi",
+		.bus		= &tee_bus_type,
+		.probe		= tee_stmm_efi_probe,
+		.remove		= tee_stmm_efi_remove,
+	},
+};
+
+static int __init tee_stmm_efi_mod_init(void)
+{
+	return driver_register(&tee_stmm_efi_driver.driver);
+}
+
+static void __exit tee_stmm_efi_mod_exit(void)
+{
+	driver_unregister(&tee_stmm_efi_driver.driver);
+}
+
+module_init(tee_stmm_efi_mod_init);
+module_exit(tee_stmm_efi_mod_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Ilias Apalodimas <ilias.apalodimas@linaro.org>");
+MODULE_AUTHOR("Masahisa Kojima <masahisa.kojima@linaro.org>");
+MODULE_DESCRIPTION("TEE based EFI runtime variable service driver");
diff --git a/drivers/firmware/efi/unaccepted_memory.c b/drivers/firmware/efi/unaccepted_memory.c
index 3f2f7bf6e335..5b439d04079c 100644
--- a/drivers/firmware/efi/unaccepted_memory.c
+++ b/drivers/firmware/efi/unaccepted_memory.c
@@ -101,7 +101,7 @@ retry:
 	 * overlap on physical address level.
 	 */
 	list_for_each_entry(entry, &accepting_list, list) {
-		if (entry->end < range.start)
+		if (entry->end <= range.start)
 			continue;
 		if (entry->start >= range.end)
 			continue;
diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index e9dc7116daf1..f654e6f6af87 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -63,6 +63,7 @@ int efivars_register(struct efivars *efivars,
 		     const struct efivar_operations *ops)
 {
 	int rv;
+	int event;
 
 	if (down_interruptible(&efivars_lock))
 		return -EINTR;
@@ -77,6 +78,13 @@ int efivars_register(struct efivars *efivars,
 
 	__efivars = efivars;
 
+	if (efivar_supports_writes())
+		event = EFIVAR_OPS_RDWR;
+	else
+		event = EFIVAR_OPS_RDONLY;
+
+	blocking_notifier_call_chain(&efivar_ops_nh, event, NULL);
+
 	pr_info("Registered efivars operations\n");
 	rv = 0;
 out:
diff --git a/drivers/firmware/google/coreboot_table.c b/drivers/firmware/google/coreboot_table.c
index 33ae94745aef..2a4469bf1b81 100644
--- a/drivers/firmware/google/coreboot_table.c
+++ b/drivers/firmware/google/coreboot_table.c
@@ -176,10 +176,9 @@ static int __cb_dev_unregister(struct device *dev, void *dummy)
 	return 0;
 }
 
-static int coreboot_table_remove(struct platform_device *pdev)
+static void coreboot_table_remove(struct platform_device *pdev)
 {
 	bus_for_each_dev(&coreboot_bus_type, NULL, NULL, __cb_dev_unregister);
-	return 0;
 }
 
 #ifdef CONFIG_ACPI
@@ -201,7 +200,7 @@ MODULE_DEVICE_TABLE(of, coreboot_of_match);
 
 static struct platform_driver coreboot_table_driver = {
 	.probe = coreboot_table_probe,
-	.remove = coreboot_table_remove,
+	.remove_new = coreboot_table_remove,
 	.driver = {
 		.name = "coreboot_table",
 		.acpi_match_table = ACPI_PTR(cros_coreboot_acpi_match),
diff --git a/drivers/firmware/google/framebuffer-coreboot.c b/drivers/firmware/google/framebuffer-coreboot.c
index c323a818805c..5c84bbebfef8 100644
--- a/drivers/firmware/google/framebuffer-coreboot.c
+++ b/drivers/firmware/google/framebuffer-coreboot.c
@@ -36,6 +36,9 @@ static int framebuffer_probe(struct coreboot_device *dev)
 		.format = NULL,
 	};
 
+	if (!fb->physical_address)
+		return -ENODEV;
+
 	for (i = 0; i < ARRAY_SIZE(formats); ++i) {
 		if (fb->bits_per_pixel     == formats[i].bits_per_pixel &&
 		    fb->red_mask_pos       == formats[i].red.offset &&
diff --git a/drivers/firmware/meson/meson_sm.c b/drivers/firmware/meson/meson_sm.c
index ed60f1103053..5d7f62fe1d5f 100644
--- a/drivers/firmware/meson/meson_sm.c
+++ b/drivers/firmware/meson/meson_sm.c
@@ -274,14 +274,11 @@ static ssize_t serial_show(struct device *dev, struct device_attribute *attr,
 
 static DEVICE_ATTR_RO(serial);
 
-static struct attribute *meson_sm_sysfs_attributes[] = {
+static struct attribute *meson_sm_sysfs_attrs[] = {
 	&dev_attr_serial.attr,
 	NULL,
 };
-
-static const struct attribute_group meson_sm_sysfs_attr_group = {
-	.attrs = meson_sm_sysfs_attributes,
-};
+ATTRIBUTE_GROUPS(meson_sm_sysfs);
 
 static const struct of_device_id meson_sm_ids[] = {
 	{ .compatible = "amlogic,meson-gxbb-sm", .data = &gxbb_chip },
@@ -313,7 +310,7 @@ static int __init meson_sm_probe(struct platform_device *pdev)
 		fw->sm_shmem_out_base = meson_sm_map_shmem(chip->cmd_shmem_out_base,
 							   chip->shmem_size);
 		if (WARN_ON(!fw->sm_shmem_out_base))
-			goto out_in_base;
+			goto unmap_in_base;
 	}
 
 	fw->chip = chip;
@@ -321,16 +318,15 @@ static int __init meson_sm_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, fw);
 
 	if (devm_of_platform_populate(dev))
-		goto out_in_base;
-
-	if (sysfs_create_group(&pdev->dev.kobj, &meson_sm_sysfs_attr_group))
-		goto out_in_base;
+		goto unmap_out_base;
 
 	pr_info("secure-monitor enabled\n");
 
 	return 0;
 
-out_in_base:
+unmap_out_base:
+	iounmap(fw->sm_shmem_out_base);
+unmap_in_base:
 	iounmap(fw->sm_shmem_in_base);
 out:
 	return -EINVAL;
@@ -340,6 +336,7 @@ static struct platform_driver meson_sm_driver = {
 	.driver = {
 		.name = "meson-sm",
 		.of_match_table = of_match_ptr(meson_sm_ids),
+		.dev_groups = meson_sm_sysfs_groups,
 	},
 };
 module_platform_driver_probe(meson_sm_driver, meson_sm_probe);
diff --git a/drivers/firmware/microchip/Kconfig b/drivers/firmware/microchip/Kconfig
new file mode 100644
index 000000000000..434b923e08c2
--- /dev/null
+++ b/drivers/firmware/microchip/Kconfig
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config POLARFIRE_SOC_AUTO_UPDATE
+	tristate "Microchip PolarFire SoC AUTO UPDATE"
+	depends on POLARFIRE_SOC_SYS_CTRL
+	select FW_LOADER
+	select FW_UPLOAD
+	help
+	  Support for reprogramming PolarFire SoC from within Linux, using the
+	  Auto Upgrade feature of the system controller.
+
+	  If built as a module, it will be called mpfs-auto-update.
diff --git a/drivers/firmware/microchip/Makefile b/drivers/firmware/microchip/Makefile
new file mode 100644
index 000000000000..38796fd82893
--- /dev/null
+++ b/drivers/firmware/microchip/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_POLARFIRE_SOC_AUTO_UPDATE) += mpfs-auto-update.o
diff --git a/drivers/firmware/microchip/mpfs-auto-update.c b/drivers/firmware/microchip/mpfs-auto-update.c
new file mode 100644
index 000000000000..81f5f62e34fc
--- /dev/null
+++ b/drivers/firmware/microchip/mpfs-auto-update.c
@@ -0,0 +1,494 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Microchip Polarfire SoC "Auto Update" FPGA reprogramming.
+ *
+ * Documentation of this functionality is available in the "PolarFire® FPGA and
+ * PolarFire SoC FPGA Programming" User Guide.
+ *
+ * Copyright (c) 2022-2023 Microchip Corporation. All rights reserved.
+ *
+ * Author: Conor Dooley <conor.dooley@microchip.com>
+ */
+#include <linux/debugfs.h>
+#include <linux/firmware.h>
+#include <linux/math.h>
+#include <linux/module.h>
+#include <linux/mtd/mtd.h>
+#include <linux/platform_device.h>
+#include <linux/sizes.h>
+
+#include <soc/microchip/mpfs.h>
+
+#define AUTO_UPDATE_DEFAULT_MBOX_OFFSET		0u
+#define AUTO_UPDATE_DEFAULT_RESP_OFFSET		0u
+
+#define AUTO_UPDATE_FEATURE_CMD_OPCODE		0x05u
+#define AUTO_UPDATE_FEATURE_CMD_DATA_SIZE	0u
+#define AUTO_UPDATE_FEATURE_RESP_SIZE		33u
+#define AUTO_UPDATE_FEATURE_CMD_DATA		NULL
+#define AUTO_UPDATE_FEATURE_ENABLED		BIT(5)
+
+#define AUTO_UPDATE_AUTHENTICATE_CMD_OPCODE	0x22u
+#define AUTO_UPDATE_AUTHENTICATE_CMD_DATA_SIZE	0u
+#define AUTO_UPDATE_AUTHENTICATE_RESP_SIZE	1u
+#define AUTO_UPDATE_AUTHENTICATE_CMD_DATA	NULL
+
+#define AUTO_UPDATE_PROGRAM_CMD_OPCODE		0x46u
+#define AUTO_UPDATE_PROGRAM_CMD_DATA_SIZE	0u
+#define AUTO_UPDATE_PROGRAM_RESP_SIZE		1u
+#define AUTO_UPDATE_PROGRAM_CMD_DATA		NULL
+
+/*
+ * SPI Flash layout example:
+ * |------------------------------| 0x0000000
+ * | 1 KiB                        |
+ * | SPI "directories"            |
+ * |------------------------------| 0x0000400
+ * | 1 MiB                        |
+ * | Reserved area                |
+ * | Used for bitstream info      |
+ * |------------------------------| 0x0100400
+ * | 20 MiB                       |
+ * | Golden Image                 |
+ * |------------------------------| 0x1500400
+ * | 20 MiB                       |
+ * | Auto Upgrade Image           |
+ * |------------------------------| 0x2900400
+ * | 20 MiB                       |
+ * | Reserved for multi-image IAP |
+ * | Unused for Auto Upgrade      |
+ * |------------------------------| 0x3D00400
+ * | ? B                          |
+ * | Unused                       |
+ * |------------------------------| 0x?
+ */
+#define AUTO_UPDATE_DIRECTORY_BASE	0u
+#define AUTO_UPDATE_DIRECTORY_WIDTH	4u
+#define AUTO_UPDATE_GOLDEN_INDEX	0u
+#define AUTO_UPDATE_UPGRADE_INDEX	1u
+#define AUTO_UPDATE_BLANK_INDEX		2u
+#define AUTO_UPDATE_GOLDEN_DIRECTORY	(AUTO_UPDATE_DIRECTORY_WIDTH * AUTO_UPDATE_GOLDEN_INDEX)
+#define AUTO_UPDATE_UPGRADE_DIRECTORY	(AUTO_UPDATE_DIRECTORY_WIDTH * AUTO_UPDATE_UPGRADE_INDEX)
+#define AUTO_UPDATE_BLANK_DIRECTORY	(AUTO_UPDATE_DIRECTORY_WIDTH * AUTO_UPDATE_BLANK_INDEX)
+#define AUTO_UPDATE_DIRECTORY_SIZE	SZ_1K
+#define AUTO_UPDATE_RESERVED_SIZE	SZ_1M
+#define AUTO_UPDATE_BITSTREAM_BASE	(AUTO_UPDATE_DIRECTORY_SIZE + AUTO_UPDATE_RESERVED_SIZE)
+
+#define AUTO_UPDATE_TIMEOUT_MS		60000
+
+struct mpfs_auto_update_priv {
+	struct mpfs_sys_controller *sys_controller;
+	struct device *dev;
+	struct mtd_info *flash;
+	struct fw_upload *fw_uploader;
+	struct completion programming_complete;
+	size_t size_per_bitstream;
+	bool cancel_request;
+};
+
+static enum fw_upload_err mpfs_auto_update_prepare(struct fw_upload *fw_uploader, const u8 *data,
+						   u32 size)
+{
+	struct mpfs_auto_update_priv *priv = fw_uploader->dd_handle;
+	size_t erase_size = AUTO_UPDATE_DIRECTORY_SIZE;
+
+	/*
+	 * Verifying the Golden Image is idealistic. It will be evaluated
+	 * against the currently programmed image and thus may fail - due to
+	 * either rollback protection (if its an older version than that in use)
+	 * or if the version is the same as that of the in-use image.
+	 * Extracting the information as to why a failure occurred is not
+	 * currently possible due to limitations of the system controller
+	 * driver. If those are fixed, verification of the Golden Image should
+	 * be added here.
+	 */
+
+	priv->flash = mpfs_sys_controller_get_flash(priv->sys_controller);
+	if (!priv->flash)
+		return FW_UPLOAD_ERR_HW_ERROR;
+
+	erase_size = round_up(erase_size, (u64)priv->flash->erasesize);
+
+	/*
+	 * We need to calculate if we have enough space in the flash for the
+	 * new image.
+	 * First, chop off the first 1 KiB as it's reserved for the directory.
+	 * The 1 MiB reserved for design info needs to be ignored also.
+	 * All that remains is carved into 3 & rounded down to the erasesize.
+	 * If this is smaller than the image size, we abort.
+	 * There's also no need to consume more than 20 MiB per image.
+	 */
+	priv->size_per_bitstream = priv->flash->size - SZ_1K - SZ_1M;
+	priv->size_per_bitstream = round_down(priv->size_per_bitstream / 3, erase_size);
+	if (priv->size_per_bitstream > 20 * SZ_1M)
+		priv->size_per_bitstream = 20 * SZ_1M;
+
+	if (priv->size_per_bitstream < size) {
+		dev_err(priv->dev,
+			"flash device has insufficient capacity to store this bitstream\n");
+		return FW_UPLOAD_ERR_INVALID_SIZE;
+	}
+
+	priv->cancel_request = false;
+
+	return FW_UPLOAD_ERR_NONE;
+}
+
+static void mpfs_auto_update_cancel(struct fw_upload *fw_uploader)
+{
+	struct mpfs_auto_update_priv *priv = fw_uploader->dd_handle;
+
+	priv->cancel_request = true;
+}
+
+static enum fw_upload_err mpfs_auto_update_poll_complete(struct fw_upload *fw_uploader)
+{
+	struct mpfs_auto_update_priv *priv = fw_uploader->dd_handle;
+	int ret;
+
+	/*
+	 * There is no meaningful way to get the status of the programming while
+	 * it is in progress, so attempting anything other than waiting for it
+	 * to complete would be misplaced.
+	 */
+	ret = wait_for_completion_timeout(&priv->programming_complete,
+					  msecs_to_jiffies(AUTO_UPDATE_TIMEOUT_MS));
+	if (ret)
+		return FW_UPLOAD_ERR_TIMEOUT;
+
+	return FW_UPLOAD_ERR_NONE;
+}
+
+static int mpfs_auto_update_verify_image(struct fw_upload *fw_uploader)
+{
+	struct mpfs_auto_update_priv *priv = fw_uploader->dd_handle;
+	struct mpfs_mss_response *response;
+	struct mpfs_mss_msg *message;
+	u32 *response_msg;
+	int ret;
+
+	response_msg = devm_kzalloc(priv->dev, AUTO_UPDATE_FEATURE_RESP_SIZE * sizeof(response_msg),
+				    GFP_KERNEL);
+	if (!response_msg)
+		return -ENOMEM;
+
+	response = devm_kzalloc(priv->dev, sizeof(struct mpfs_mss_response), GFP_KERNEL);
+	if (!response) {
+		ret = -ENOMEM;
+		goto free_response_msg;
+	}
+
+	message = devm_kzalloc(priv->dev, sizeof(struct mpfs_mss_msg), GFP_KERNEL);
+	if (!message) {
+		ret = -ENOMEM;
+		goto free_response;
+	}
+
+	/*
+	 * The system controller can verify that an image in the flash is valid.
+	 * Rather than duplicate the check in this driver, call the relevant
+	 * service from the system controller instead.
+	 * This service has no command data and no response data. It overloads
+	 * mbox_offset with the image index in the flash's SPI directory where
+	 * the bitstream is located.
+	 */
+	response->resp_msg = response_msg;
+	response->resp_size = AUTO_UPDATE_AUTHENTICATE_RESP_SIZE;
+	message->cmd_opcode = AUTO_UPDATE_AUTHENTICATE_CMD_OPCODE;
+	message->cmd_data_size = AUTO_UPDATE_AUTHENTICATE_CMD_DATA_SIZE;
+	message->response = response;
+	message->cmd_data = AUTO_UPDATE_AUTHENTICATE_CMD_DATA;
+	message->mbox_offset = AUTO_UPDATE_UPGRADE_INDEX;
+	message->resp_offset = AUTO_UPDATE_DEFAULT_RESP_OFFSET;
+
+	dev_info(priv->dev, "Running verification of Upgrade Image\n");
+	ret = mpfs_blocking_transaction(priv->sys_controller, message);
+	if (ret | response->resp_status) {
+		dev_warn(priv->dev, "Verification of Upgrade Image failed!\n");
+		ret = ret ? ret : -EBADMSG;
+	}
+
+	dev_info(priv->dev, "Verification of Upgrade Image passed!\n");
+
+	devm_kfree(priv->dev, message);
+free_response:
+	devm_kfree(priv->dev, response);
+free_response_msg:
+	devm_kfree(priv->dev, response_msg);
+
+	return ret;
+}
+
+static int mpfs_auto_update_set_image_address(struct mpfs_auto_update_priv *priv, char *buffer,
+					      u32 image_address, loff_t directory_address)
+{
+	struct erase_info erase;
+	size_t erase_size = AUTO_UPDATE_DIRECTORY_SIZE;
+	size_t bytes_written = 0, bytes_read = 0;
+	int ret;
+
+	erase_size = round_up(erase_size, (u64)priv->flash->erasesize);
+
+	erase.addr = AUTO_UPDATE_DIRECTORY_BASE;
+	erase.len = erase_size;
+
+	/*
+	 * We need to write the "SPI DIRECTORY" to the first 1 KiB, telling
+	 * the system controller where to find the actual bitstream. Since
+	 * this is spi-nor, we have to read the first eraseblock, erase that
+	 * portion of the flash, modify the data and then write it back.
+	 * There's no need to do this though if things are already the way they
+	 * should be, so check and save the write in that case.
+	 */
+	ret = mtd_read(priv->flash, AUTO_UPDATE_DIRECTORY_BASE, erase_size, &bytes_read,
+		       (u_char *)buffer);
+	if (ret)
+		return ret;
+
+	if (bytes_read != erase_size)
+		return -EIO;
+
+	if ((*(u32 *)(buffer + AUTO_UPDATE_UPGRADE_DIRECTORY) == image_address) &&
+	    !(*(u32 *)(buffer + AUTO_UPDATE_BLANK_DIRECTORY)))
+		return 0;
+
+	ret = mtd_erase(priv->flash, &erase);
+	if (ret)
+		return ret;
+
+	/*
+	 * Populate the image address and then zero out the next directory so
+	 * that the system controller doesn't complain if in "Single Image"
+	 * mode.
+	 */
+	memcpy(buffer + AUTO_UPDATE_UPGRADE_DIRECTORY, &image_address,
+	       AUTO_UPDATE_DIRECTORY_WIDTH);
+	memset(buffer + AUTO_UPDATE_BLANK_DIRECTORY, 0x0, AUTO_UPDATE_DIRECTORY_WIDTH);
+
+	dev_info(priv->dev, "Writing the image address (%x) to the flash directory (%llx)\n",
+		 image_address, directory_address);
+
+	ret = mtd_write(priv->flash, 0x0, erase_size, &bytes_written, (u_char *)buffer);
+	if (ret)
+		return ret;
+
+	if (bytes_written != erase_size)
+		return ret;
+
+	return 0;
+}
+
+static int mpfs_auto_update_write_bitstream(struct fw_upload *fw_uploader, const u8 *data,
+					    u32 offset, u32 size, u32 *written)
+{
+	struct mpfs_auto_update_priv *priv = fw_uploader->dd_handle;
+	struct erase_info erase;
+	char *buffer;
+	loff_t directory_address = AUTO_UPDATE_UPGRADE_DIRECTORY;
+	size_t erase_size = AUTO_UPDATE_DIRECTORY_SIZE;
+	size_t bytes_written = 0;
+	u32 image_address;
+	int ret;
+
+	erase_size = round_up(erase_size, (u64)priv->flash->erasesize);
+
+	image_address = AUTO_UPDATE_BITSTREAM_BASE +
+		AUTO_UPDATE_UPGRADE_INDEX * priv->size_per_bitstream;
+
+	buffer = devm_kzalloc(priv->dev, erase_size, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
+	ret = mpfs_auto_update_set_image_address(priv, buffer, image_address, directory_address);
+	if (ret) {
+		dev_err(priv->dev, "failed to set image address in the SPI directory: %d\n", ret);
+		goto out;
+	}
+
+	/*
+	 * Now the .spi image itself can be written to the flash. Preservation
+	 * of contents here is not important here, unlike the spi "directory"
+	 * which must be RMWed.
+	 */
+	erase.len = round_up(size, (size_t)priv->flash->erasesize);
+	erase.addr = image_address;
+
+	dev_info(priv->dev, "Erasing the flash at address (%x)\n", image_address);
+	ret = mtd_erase(priv->flash, &erase);
+	if (ret)
+		goto out;
+
+	/*
+	 * No parsing etc of the bitstream is required. The system controller
+	 * will do all of that itself - including verifying that the bitstream
+	 * is valid.
+	 */
+	dev_info(priv->dev, "Writing the image to the flash at address (%x)\n", image_address);
+	ret = mtd_write(priv->flash, (loff_t)image_address, size, &bytes_written, data);
+	if (ret)
+		goto out;
+
+	if (bytes_written != size) {
+		ret = -EIO;
+		goto out;
+	}
+
+	*written = bytes_written;
+
+out:
+	devm_kfree(priv->dev, buffer);
+	return ret;
+}
+
+static enum fw_upload_err mpfs_auto_update_write(struct fw_upload *fw_uploader, const u8 *data,
+						 u32 offset, u32 size, u32 *written)
+{
+	struct mpfs_auto_update_priv *priv = fw_uploader->dd_handle;
+	enum fw_upload_err err = FW_UPLOAD_ERR_NONE;
+	int ret;
+
+	reinit_completion(&priv->programming_complete);
+
+	ret = mpfs_auto_update_write_bitstream(fw_uploader, data, offset, size, written);
+	if (ret) {
+		err = FW_UPLOAD_ERR_RW_ERROR;
+		goto out;
+	}
+
+	if (priv->cancel_request) {
+		err = FW_UPLOAD_ERR_CANCELED;
+		goto out;
+	}
+
+	ret = mpfs_auto_update_verify_image(fw_uploader);
+	if (ret)
+		err = FW_UPLOAD_ERR_FW_INVALID;
+
+out:
+	complete(&priv->programming_complete);
+
+	return err;
+}
+
+static const struct fw_upload_ops mpfs_auto_update_ops = {
+	.prepare = mpfs_auto_update_prepare,
+	.write = mpfs_auto_update_write,
+	.poll_complete = mpfs_auto_update_poll_complete,
+	.cancel = mpfs_auto_update_cancel,
+};
+
+static int mpfs_auto_update_available(struct mpfs_auto_update_priv *priv)
+{
+	struct mpfs_mss_response *response;
+	struct mpfs_mss_msg *message;
+	u32 *response_msg;
+	int ret;
+
+	response_msg = devm_kzalloc(priv->dev, AUTO_UPDATE_FEATURE_RESP_SIZE * sizeof(response_msg),
+				    GFP_KERNEL);
+	if (!response_msg)
+		return -ENOMEM;
+
+	response = devm_kzalloc(priv->dev, sizeof(struct mpfs_mss_response), GFP_KERNEL);
+	if (!response)
+		return -ENOMEM;
+
+	message = devm_kzalloc(priv->dev, sizeof(struct mpfs_mss_msg), GFP_KERNEL);
+	if (!message)
+		return -ENOMEM;
+
+	/*
+	 * To verify that Auto Update is possible, the "Query Security Service
+	 * Request" is performed.
+	 * This service has no command data & does not overload mbox_offset.
+	 */
+	response->resp_msg = response_msg;
+	response->resp_size = AUTO_UPDATE_FEATURE_RESP_SIZE;
+	message->cmd_opcode = AUTO_UPDATE_FEATURE_CMD_OPCODE;
+	message->cmd_data_size = AUTO_UPDATE_FEATURE_CMD_DATA_SIZE;
+	message->response = response;
+	message->cmd_data = AUTO_UPDATE_FEATURE_CMD_DATA;
+	message->mbox_offset = AUTO_UPDATE_DEFAULT_MBOX_OFFSET;
+	message->resp_offset = AUTO_UPDATE_DEFAULT_RESP_OFFSET;
+
+	ret = mpfs_blocking_transaction(priv->sys_controller, message);
+	if (ret)
+		return ret;
+
+	/*
+	 * Currently, the system controller's firmware does not generate any
+	 * interrupts for failed services, so mpfs_blocking_transaction() should
+	 * time out & therefore return an error.
+	 * Hitting this check is highly unlikely at present, but if the system
+	 * controller's behaviour changes so that it does generate interrupts
+	 * for failed services, it will be required.
+	 */
+	if (response->resp_status)
+		return -EIO;
+
+	/*
+	 * Bit 5 of byte 1 is "UL_Auto Update" & if it is set, Auto Update is
+	 * not possible.
+	 */
+	if (response_msg[1] & AUTO_UPDATE_FEATURE_ENABLED)
+		return -EPERM;
+
+	return 0;
+}
+
+static int mpfs_auto_update_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct mpfs_auto_update_priv *priv;
+	struct fw_upload *fw_uploader;
+	int ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->sys_controller = mpfs_sys_controller_get(dev);
+	if (IS_ERR(priv->sys_controller))
+		return dev_err_probe(dev, PTR_ERR(priv->sys_controller),
+				     "Could not register as a sub device of the system controller\n");
+
+	priv->dev = dev;
+	platform_set_drvdata(pdev, priv);
+
+	ret = mpfs_auto_update_available(priv);
+	if (ret)
+		return dev_err_probe(dev, ret,
+				     "The current bitstream does not support auto-update\n");
+
+	init_completion(&priv->programming_complete);
+
+	fw_uploader = firmware_upload_register(THIS_MODULE, dev, "mpfs-auto-update",
+					       &mpfs_auto_update_ops, priv);
+	if (IS_ERR(fw_uploader))
+		return dev_err_probe(dev, PTR_ERR(fw_uploader),
+				     "Failed to register the bitstream uploader\n");
+
+	priv->fw_uploader = fw_uploader;
+
+	return 0;
+}
+
+static void mpfs_auto_update_remove(struct platform_device *pdev)
+{
+	struct mpfs_auto_update_priv *priv = platform_get_drvdata(pdev);
+
+	firmware_upload_unregister(priv->fw_uploader);
+}
+
+static struct platform_driver mpfs_auto_update_driver = {
+	.driver = {
+		.name = "mpfs-auto-update",
+	},
+	.probe = mpfs_auto_update_probe,
+	.remove_new = mpfs_auto_update_remove,
+};
+module_platform_driver(mpfs_auto_update_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Conor Dooley <conor.dooley@microchip.com>");
+MODULE_DESCRIPTION("PolarFire SoC Auto Update FPGA reprogramming");
diff --git a/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c b/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c
index a33acdaf7b78..32188f098ef3 100644
--- a/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c
+++ b/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c
@@ -325,8 +325,10 @@ static efi_status_t qsee_uefi_get_variable(struct qcuefi_client *qcuefi, const e
 	req_data->length = req_size;
 
 	status = ucs2_strscpy(((void *)req_data) + req_data->name_offset, name, name_length);
-	if (status < 0)
-		return EFI_INVALID_PARAMETER;
+	if (status < 0) {
+		efi_status = EFI_INVALID_PARAMETER;
+		goto out_free;
+	}
 
 	memcpy(((void *)req_data) + req_data->guid_offset, guid, req_data->guid_size);
 
@@ -471,8 +473,10 @@ static efi_status_t qsee_uefi_set_variable(struct qcuefi_client *qcuefi, const e
 	req_data->length = req_size;
 
 	status = ucs2_strscpy(((void *)req_data) + req_data->name_offset, name, name_length);
-	if (status < 0)
-		return EFI_INVALID_PARAMETER;
+	if (status < 0) {
+		efi_status = EFI_INVALID_PARAMETER;
+		goto out_free;
+	}
 
 	memcpy(((void *)req_data) + req_data->guid_offset, guid, req_data->guid_size);
 
@@ -563,8 +567,10 @@ static efi_status_t qsee_uefi_get_next_variable(struct qcuefi_client *qcuefi,
 	memcpy(((void *)req_data) + req_data->guid_offset, guid, req_data->guid_size);
 	status = ucs2_strscpy(((void *)req_data) + req_data->name_offset, name,
 			      *name_size / sizeof(*name));
-	if (status < 0)
-		return EFI_INVALID_PARAMETER;
+	if (status < 0) {
+		efi_status = EFI_INVALID_PARAMETER;
+		goto out_free;
+	}
 
 	status = qcom_qseecom_app_send(qcuefi->client, req_data, req_size, rsp_data, rsp_size);
 	if (status) {
@@ -635,7 +641,7 @@ static efi_status_t qsee_uefi_get_next_variable(struct qcuefi_client *qcuefi,
 		 * have already been validated above, causing this function to
 		 * bail with EFI_BUFFER_TOO_SMALL.
 		 */
-		return EFI_DEVICE_ERROR;
+		efi_status = EFI_DEVICE_ERROR;
 	}
 
 out_free:
diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c
index a69399a6b7c0..1448f61173b3 100644
--- a/drivers/firmware/qemu_fw_cfg.c
+++ b/drivers/firmware/qemu_fw_cfg.c
@@ -211,7 +211,7 @@ static void fw_cfg_io_cleanup(void)
 
 /* arch-specific ctrl & data register offsets are not available in ACPI, DT */
 #if !(defined(FW_CFG_CTRL_OFF) && defined(FW_CFG_DATA_OFF))
-# if (defined(CONFIG_ARM) || defined(CONFIG_ARM64))
+# if (defined(CONFIG_ARM) || defined(CONFIG_ARM64) || defined(CONFIG_RISCV))
 #  define FW_CFG_CTRL_OFF 0x08
 #  define FW_CFG_DATA_OFF 0x00
 #  define FW_CFG_DMA_OFF 0x10
diff --git a/drivers/firmware/ti_sci.c b/drivers/firmware/ti_sci.c
index 7041befc756a..8b9a2556de16 100644
--- a/drivers/firmware/ti_sci.c
+++ b/drivers/firmware/ti_sci.c
@@ -164,7 +164,7 @@ static int ti_sci_debugfs_create(struct platform_device *pdev,
 {
 	struct device *dev = &pdev->dev;
 	struct resource *res;
-	char debug_name[50] = "ti_sci_debug@";
+	char debug_name[50];
 
 	/* Debug region is optional */
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
@@ -181,10 +181,10 @@ static int ti_sci_debugfs_create(struct platform_device *pdev,
 	/* Setup NULL termination */
 	info->debug_buffer[info->debug_region_size] = 0;
 
-	info->d = debugfs_create_file(strncat(debug_name, dev_name(dev),
-					      sizeof(debug_name) -
-					      sizeof("ti_sci_debug@")),
-				      0444, NULL, info, &ti_sci_debug_fops);
+	snprintf(debug_name, sizeof(debug_name), "ti_sci_debug@%s",
+		 dev_name(dev));
+	info->d = debugfs_create_file(debug_name, 0444, NULL, info,
+				      &ti_sci_debug_fops);
 	if (IS_ERR(info->d))
 		return PTR_ERR(info->d);
 
diff --git a/drivers/fpga/dfl.c b/drivers/fpga/dfl.c
index dd7a783d53b5..e73f88050f08 100644
--- a/drivers/fpga/dfl.c
+++ b/drivers/fpga/dfl.c
@@ -1872,7 +1872,7 @@ static irqreturn_t dfl_irq_handler(int irq, void *arg)
 {
 	struct eventfd_ctx *trigger = arg;
 
-	eventfd_signal(trigger, 1);
+	eventfd_signal(trigger);
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c
index 4a4f61bf6c58..8c59332429c2 100644
--- a/drivers/gpio/gpio-dwapb.c
+++ b/drivers/gpio/gpio-dwapb.c
@@ -282,13 +282,15 @@ static void dwapb_irq_enable(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct dwapb_gpio *gpio = to_dwapb_gpio(gc);
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
 	unsigned long flags;
 	u32 val;
 
 	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
-	val = dwapb_read(gpio, GPIO_INTEN);
-	val |= BIT(irqd_to_hwirq(d));
+	val = dwapb_read(gpio, GPIO_INTEN) | BIT(hwirq);
 	dwapb_write(gpio, GPIO_INTEN, val);
+	val = dwapb_read(gpio, GPIO_INTMASK) & ~BIT(hwirq);
+	dwapb_write(gpio, GPIO_INTMASK, val);
 	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 }
 
@@ -296,12 +298,14 @@ static void dwapb_irq_disable(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct dwapb_gpio *gpio = to_dwapb_gpio(gc);
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
 	unsigned long flags;
 	u32 val;
 
 	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
-	val = dwapb_read(gpio, GPIO_INTEN);
-	val &= ~BIT(irqd_to_hwirq(d));
+	val = dwapb_read(gpio, GPIO_INTMASK) | BIT(hwirq);
+	dwapb_write(gpio, GPIO_INTMASK, val);
+	val = dwapb_read(gpio, GPIO_INTEN) & ~BIT(hwirq);
 	dwapb_write(gpio, GPIO_INTEN, val);
 	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 }
diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c
index 02ffda6c1e51..f713d1ef7746 100644
--- a/drivers/gpio/gpiolib-cdev.c
+++ b/drivers/gpio/gpiolib-cdev.c
@@ -2481,10 +2481,7 @@ static int lineinfo_unwatch(struct gpio_chardev_data *cdev, void __user *ip)
 	return 0;
 }
 
-/*
- * gpio_ioctl() - ioctl handler for the GPIO chardev
- */
-static long gpio_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+static long gpio_ioctl_unlocked(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct gpio_chardev_data *cdev = file->private_data;
 	struct gpio_device *gdev = cdev->gdev;
@@ -2521,6 +2518,17 @@ static long gpio_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	}
 }
 
+/*
+ * gpio_ioctl() - ioctl handler for the GPIO chardev
+ */
+static long gpio_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct gpio_chardev_data *cdev = file->private_data;
+
+	return call_ioctl_locked(file, cmd, arg, cdev->gdev,
+				 gpio_ioctl_unlocked);
+}
+
 #ifdef CONFIG_COMPAT
 static long gpio_ioctl_compat(struct file *file, unsigned int cmd,
 			      unsigned long arg)
diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c
index 6f309a3b2d9a..12d853845bb8 100644
--- a/drivers/gpio/gpiolib-sysfs.c
+++ b/drivers/gpio/gpiolib-sysfs.c
@@ -474,14 +474,17 @@ static ssize_t export_store(const struct class *class,
 		goto done;
 
 	status = gpiod_set_transitory(desc, false);
-	if (!status) {
-		status = gpiod_export(desc, true);
-		if (status < 0)
-			gpiod_free(desc);
-		else
-			set_bit(FLAG_SYSFS, &desc->flags);
+	if (status) {
+		gpiod_free(desc);
+		goto done;
 	}
 
+	status = gpiod_export(desc, true);
+	if (status < 0)
+		gpiod_free(desc);
+	else
+		set_bit(FLAG_SYSFS, &desc->flags);
+
 done:
 	if (status)
 		pr_debug("%s: status %d\n", __func__, status);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index afec09930efa..9d92ca157677 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -248,6 +248,7 @@ extern int amdgpu_umsch_mm;
 extern int amdgpu_seamless;
 
 extern int amdgpu_user_partt_mode;
+extern int amdgpu_agp;
 
 #define AMDGPU_VM_MAX_NUM_CTX			4096
 #define AMDGPU_SG_THRESHOLD			(256*1024*1024)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index b8412202a1b0..75dc58470393 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -547,7 +547,7 @@ int amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(struct amdgpu_device *dst,
 	struct amdgpu_device *adev = dst, *peer_adev;
 	int num_links;
 
-	if (adev->asic_type != CHIP_ALDEBARAN)
+	if (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(9, 4, 2))
 		return 0;
 
 	if (src)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index df3ecfa9e13f..e50be6500030 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -207,7 +207,7 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p,
 	}
 
 	for (i = 0; i < p->nchunks; i++) {
-		struct drm_amdgpu_cs_chunk __user **chunk_ptr = NULL;
+		struct drm_amdgpu_cs_chunk __user *chunk_ptr = NULL;
 		struct drm_amdgpu_cs_chunk user_chunk;
 		uint32_t __user *cdata;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index a53f436fa9f1..0e61ebdb3f3e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -638,6 +638,9 @@ static ssize_t amdgpu_debugfs_regs_didt_read(struct file *f, char __user *buf,
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	if (!adev->didt_rreg)
+		return -EOPNOTSUPP;
+
 	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
 		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
@@ -694,6 +697,9 @@ static ssize_t amdgpu_debugfs_regs_didt_write(struct file *f, const char __user
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	if (!adev->didt_wreg)
+		return -EOPNOTSUPP;
+
 	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
 		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 7eeaf0aa7f81..93cf73d6fa11 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2188,15 +2188,8 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 
 	adev->firmware.gpu_info_fw = NULL;
 
-	if (adev->mman.discovery_bin) {
-		/*
-		 * FIXME: The bounding box is still needed by Navi12, so
-		 * temporarily read it from gpu_info firmware. Should be dropped
-		 * when DAL no longer needs it.
-		 */
-		if (adev->asic_type != CHIP_NAVI12)
-			return 0;
-	}
+	if (adev->mman.discovery_bin)
+		return 0;
 
 	switch (adev->asic_type) {
 	default:
@@ -3791,10 +3784,6 @@ static void amdgpu_device_set_mcbp(struct amdgpu_device *adev)
 		adev->gfx.mcbp = true;
 	else if (amdgpu_mcbp == 0)
 		adev->gfx.mcbp = false;
-	else if ((amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(9, 0, 0)) &&
-		 (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(10, 0, 0)) &&
-		 adev->gfx.num_gfx_rings)
-		adev->gfx.mcbp = true;
 
 	if (amdgpu_sriov_vf(adev))
 		adev->gfx.mcbp = true;
@@ -4520,8 +4509,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 
 	amdgpu_ras_suspend(adev);
 
-	amdgpu_ttm_set_buffer_funcs_status(adev, false);
-
 	amdgpu_device_ip_suspend_phase1(adev);
 
 	if (!adev->in_s0ix)
@@ -4531,6 +4518,8 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 	if (r)
 		return r;
 
+	amdgpu_ttm_set_buffer_funcs_status(adev, false);
+
 	amdgpu_fence_driver_hw_fini(adev);
 
 	amdgpu_device_ip_suspend_phase2(adev);
@@ -4538,6 +4527,10 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_release_full_gpu(adev, false);
 
+	r = amdgpu_dpm_notify_rlc_state(adev, false);
+	if (r)
+		return r;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 0cacd0b9f8be..b8fbe97efe1d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -340,14 +340,11 @@ int amdgpu_display_crtc_set_config(struct drm_mode_set *set,
 		adev->have_disp_power_ref = true;
 		return ret;
 	}
-	/* if we have no active crtcs, then drop the power ref
-	 * we got before
+	/* if we have no active crtcs, then go to
+	 * drop the power ref we got before
 	 */
-	if (!active && adev->have_disp_power_ref) {
-		pm_runtime_put_autosuspend(dev->dev);
+	if (!active && adev->have_disp_power_ref)
 		adev->have_disp_power_ref = false;
-	}
-
 out:
 	/* drop the power reference we got coming in here */
 	pm_runtime_put_autosuspend(dev->dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 3095a3a864af..8b33b130ea36 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -207,6 +207,7 @@ int amdgpu_user_partt_mode = AMDGPU_AUTO_COMPUTE_PARTITION_MODE;
 int amdgpu_umsch_mm;
 int amdgpu_seamless = -1; /* auto */
 uint amdgpu_debug_mask;
+int amdgpu_agp = -1; /* auto */
 
 static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work);
 
@@ -961,6 +962,15 @@ module_param_named(seamless, amdgpu_seamless, int, 0444);
 MODULE_PARM_DESC(debug_mask, "debug options for amdgpu, disabled by default");
 module_param_named(debug_mask, amdgpu_debug_mask, uint, 0444);
 
+/**
+ * DOC: agp (int)
+ * Enable the AGP aperture.  This provides an aperture in the GPU's internal
+ * address space for direct access to system memory.  Note that these accesses
+ * are non-snooped, so they are only used for access to uncached memory.
+ */
+MODULE_PARM_DESC(agp, "AGP (-1 = auto (default), 0 = disable, 1 = enable)");
+module_param_named(agp, amdgpu_agp, int, 0444);
+
 /* These devices are not supported by amdgpu.
  * They are supported by the mach64, r128, radeon drivers
  */
@@ -2253,6 +2263,8 @@ retry_init:
 		pm_runtime_mark_last_busy(ddev->dev);
 		pm_runtime_put_autosuspend(ddev->dev);
 
+		pci_wake_from_d3(pdev, TRUE);
+
 		/*
 		 * For runpm implemented via BACO, PMFW will handle the
 		 * timing for BACO in and out:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 5f71414190e9..d2f273d77e59 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -181,6 +181,9 @@ uint64_t amdgpu_gmc_agp_addr(struct ttm_buffer_object *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
 
+	if (!bo->ttm)
+		return AMDGPU_BO_INVALID_OFFSET;
+
 	if (bo->ttm->num_pages != 1 || bo->ttm->caching == ttm_cached)
 		return AMDGPU_BO_INVALID_OFFSET;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
index 2b488fcf2f95..e51e8918e667 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
@@ -46,6 +46,8 @@
 #define MCA_REG__STATUS__ERRORCODEEXT(x)	MCA_REG_FIELD(x, 21, 16)
 #define MCA_REG__STATUS__ERRORCODE(x)		MCA_REG_FIELD(x, 15, 0)
 
+#define MCA_REG__SYND__ERRORINFORMATION(x)	MCA_REG_FIELD(x, 17, 0)
+
 enum amdgpu_mca_ip {
 	AMDGPU_MCA_IP_UNKNOW = -1,
 	AMDGPU_MCA_IP_PSP = 0,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index cef920a93924..5ad03f2afdb4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -1343,6 +1343,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo)
 
 	abo = ttm_to_amdgpu_bo(bo);
 
+	WARN_ON(abo->vm_bo);
+
 	if (abo->kfd_bo)
 		amdgpu_amdkfd_release_notify(abo);
 
@@ -1527,10 +1529,14 @@ u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo)
 u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
-	uint64_t offset;
+	uint64_t offset = AMDGPU_BO_INVALID_OFFSET;
+
+	if (bo->tbo.resource->mem_type == TTM_PL_TT)
+		offset = amdgpu_gmc_agp_addr(&bo->tbo);
 
-	offset = (bo->tbo.resource->start << PAGE_SHIFT) +
-		 amdgpu_ttm_domain_start(adev, bo->tbo.resource->mem_type);
+	if (offset == AMDGPU_BO_INVALID_OFFSET)
+		offset = (bo->tbo.resource->start << PAGE_SHIFT) +
+			amdgpu_ttm_domain_start(adev, bo->tbo.resource->mem_type);
 
 	return amdgpu_gmc_sign_extend(offset);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 32b701cc0376..a21045d018f2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -1473,6 +1473,11 @@ int psp_xgmi_get_topology_info(struct psp_context *psp,
 				topology->nodes[i].num_links = (requires_reflection && topology->nodes[i].num_links) ?
 								topology->nodes[i].num_links : node_num_links;
 			}
+			/* popluate the connected port num info if supported and available */
+			if (ta_port_num_support && topology->nodes[i].num_links) {
+				memcpy(topology->nodes[i].port_num, link_extend_info_output->nodes[i].port_num,
+				       sizeof(struct xgmi_connected_port_num) * TA_XGMI__MAX_PORT_NUM);
+			}
 
 			/* reflect the topology information for bi-directionality */
 			if (requires_reflection && topology->nodes[i].num_hops)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
index 5d36ad3f48c7..c4d9cbde55b9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
@@ -150,6 +150,7 @@ struct psp_xgmi_node_info {
 	uint8_t					is_sharing_enabled;
 	enum ta_xgmi_assigned_sdma_engine	sdma_engine;
 	uint8_t					num_links;
+	struct xgmi_connected_port_num		port_num[TA_XGMI__MAX_PORT_NUM];
 };
 
 struct psp_xgmi_topology_info {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 84e5987b14e0..63fb4cd85e53 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -28,6 +28,7 @@
 #include <linux/reboot.h>
 #include <linux/syscalls.h>
 #include <linux/pm_runtime.h>
+#include <linux/list_sort.h>
 
 #include "amdgpu.h"
 #include "amdgpu_ras.h"
@@ -1188,7 +1189,7 @@ static int amdgpu_ras_query_error_status_helper(struct amdgpu_device *adev,
 			}
 
 			if (block_obj->hw_ops->query_ras_error_count)
-				block_obj->hw_ops->query_ras_error_count(adev, &err_data);
+				block_obj->hw_ops->query_ras_error_count(adev, err_data);
 
 			if ((info->head.block == AMDGPU_RAS_BLOCK__SDMA) ||
 			    (info->head.block == AMDGPU_RAS_BLOCK__GFX) ||
@@ -3665,6 +3666,21 @@ static struct ras_err_node *amdgpu_ras_error_node_new(void)
 	return err_node;
 }
 
+static int ras_err_info_cmp(void *priv, const struct list_head *a, const struct list_head *b)
+{
+	struct ras_err_node *nodea = container_of(a, struct ras_err_node, node);
+	struct ras_err_node *nodeb = container_of(b, struct ras_err_node, node);
+	struct amdgpu_smuio_mcm_config_info *infoa = &nodea->err_info.mcm_info;
+	struct amdgpu_smuio_mcm_config_info *infob = &nodeb->err_info.mcm_info;
+
+	if (unlikely(infoa->socket_id != infob->socket_id))
+		return infoa->socket_id - infob->socket_id;
+	else
+		return infoa->die_id - infob->die_id;
+
+	return 0;
+}
+
 static struct ras_err_info *amdgpu_ras_error_get_info(struct ras_err_data *err_data,
 						      struct amdgpu_smuio_mcm_config_info *mcm_info)
 {
@@ -3682,6 +3698,7 @@ static struct ras_err_info *amdgpu_ras_error_get_info(struct ras_err_data *err_d
 
 	err_data->err_list_count++;
 	list_add_tail(&err_node->node, &err_data->err_node_list);
+	list_sort(NULL, &err_data->err_node_list, ras_err_info_cmp);
 
 	return &err_node->err_info;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 65aa218380be..2fde93b00cab 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -214,6 +214,12 @@ static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev,
 			control->i2c_address = EEPROM_I2C_MADDR_0;
 		return true;
 	case IP_VERSION(13, 0, 0):
+		if (strnstr(atom_ctx->vbios_pn, "D707",
+			    sizeof(atom_ctx->vbios_pn)))
+			control->i2c_address = EEPROM_I2C_MADDR_0;
+		else
+			control->i2c_address = EEPROM_I2C_MADDR_4;
+		return true;
 	case IP_VERSION(13, 0, 6):
 	case IP_VERSION(13, 0, 10):
 		control->i2c_address = EEPROM_I2C_MADDR_4;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 05991c5c8ddb..ab4a762aed5b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -959,10 +959,8 @@ int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo)
 		return 0;
 
 	addr = amdgpu_gmc_agp_addr(bo);
-	if (addr != AMDGPU_BO_INVALID_OFFSET) {
-		bo->resource->start = addr >> PAGE_SHIFT;
+	if (addr != AMDGPU_BO_INVALID_OFFSET)
 		return 0;
-	}
 
 	/* allocate GART space */
 	placement.num_placement = 1;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 65949cc7abb9..07d930339b07 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -398,6 +398,7 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev)
  * amdgpu_uvd_entity_init - init entity
  *
  * @adev: amdgpu_device pointer
+ * @ring: amdgpu_ring pointer to check
  *
  * Initialize the entity used for handle management in the kernel driver.
  */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 0954447f689d..59acf424a078 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -230,6 +230,7 @@ int amdgpu_vce_sw_fini(struct amdgpu_device *adev)
  * amdgpu_vce_entity_init - init entity
  *
  * @adev: amdgpu_device pointer
+ * @ring: amdgpu_ring pointer to check
  *
  * Initialize the entity used for handle management in the kernel driver.
  */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index d1b8afd105c9..5baefb548a29 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -285,6 +285,7 @@ static void amdgpu_vm_bo_reset_state_machine(struct amdgpu_vm *vm)
 	list_for_each_entry_safe(vm_bo, tmp, &vm->idle, vm_status) {
 		struct amdgpu_bo *bo = vm_bo->bo;
 
+		vm_bo->moved = true;
 		if (!bo || bo->tbo.type != ttm_bo_type_kernel)
 			list_move(&vm_bo->vm_status, &vm_bo->vm->moved);
 		else if (bo->parent)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
index a2287bb25223..a160265ddc07 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
@@ -642,13 +642,14 @@ static void amdgpu_vm_pt_free(struct amdgpu_vm_bo_base *entry)
 
 	if (!entry->bo)
 		return;
+
+	entry->bo->vm_bo = NULL;
 	shadow = amdgpu_bo_shadowed(entry->bo);
 	if (shadow) {
 		ttm_bo_set_bulk_move(&shadow->tbo, NULL);
 		amdgpu_bo_unref(&shadow);
 	}
 	ttm_bo_set_bulk_move(&entry->bo->tbo, NULL);
-	entry->bo->vm_bo = NULL;
 
 	spin_lock(&entry->vm->status_lock);
 	list_del(&entry->vm_status);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 0c6133cc5e57..8ed4a6fb147a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -89,6 +89,10 @@ MODULE_FIRMWARE("amdgpu/gc_11_5_0_me.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_0_mec.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_0_rlc.bin");
 
+static const struct soc15_reg_golden golden_settings_gc_11_0[] = {
+	SOC15_REG_GOLDEN_VALUE(GC, 0, regTCP_CNTL, 0x20000000, 0x20000000)
+};
+
 static const struct soc15_reg_golden golden_settings_gc_11_0_1[] =
 {
 	SOC15_REG_GOLDEN_VALUE(GC, 0, regCGTT_GS_NGG_CLK_CTRL, 0x9fff8fff, 0x00000010),
@@ -304,6 +308,10 @@ static void gfx_v11_0_init_golden_registers(struct amdgpu_device *adev)
 	default:
 		break;
 	}
+	soc15_program_register_sequence(adev,
+					golden_settings_gc_11_0,
+					(const u32)ARRAY_SIZE(golden_settings_gc_11_0));
+
 }
 
 static void gfx_v11_0_write_data_to_reg(struct amdgpu_ring *ring, int eng_sel,
@@ -419,7 +427,7 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 		adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD);
 		cpu_ptr = &adev->wb.wb[index];
 
-		r = amdgpu_ib_get(adev, NULL, 16, AMDGPU_IB_POOL_DIRECT, &ib);
+		r = amdgpu_ib_get(adev, NULL, 20, AMDGPU_IB_POOL_DIRECT, &ib);
 		if (r) {
 			DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r);
 			goto err1;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 885ebd703260..1943beb135c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -883,8 +883,8 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	gpu_addr = adev->wb.gpu_addr + (index * 4);
 	adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD);
 	memset(&ib, 0, sizeof(ib));
-	r = amdgpu_ib_get(adev, NULL, 16,
-					AMDGPU_IB_POOL_DIRECT, &ib);
+
+	r = amdgpu_ib_get(adev, NULL, 20, AMDGPU_IB_POOL_DIRECT, &ib);
 	if (r)
 		goto err1;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index e3ff6e46f3f7..69c500910746 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1039,8 +1039,8 @@ static int gfx_v9_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	gpu_addr = adev->wb.gpu_addr + (index * 4);
 	adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD);
 	memset(&ib, 0, sizeof(ib));
-	r = amdgpu_ib_get(adev, NULL, 16,
-					AMDGPU_IB_POOL_DIRECT, &ib);
+
+	r = amdgpu_ib_get(adev, NULL, 20, AMDGPU_IB_POOL_DIRECT, &ib);
 	if (r)
 		goto err1;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index 40d06d32bb74..4a09cc0d8ce0 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -297,8 +297,8 @@ static int gfx_v9_4_3_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	gpu_addr = adev->wb.gpu_addr + (index * 4);
 	adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD);
 	memset(&ib, 0, sizeof(ib));
-	r = amdgpu_ib_get(adev, NULL, 16,
-			  AMDGPU_IB_POOL_DIRECT, &ib);
+
+	r = amdgpu_ib_get(adev, NULL, 20, AMDGPU_IB_POOL_DIRECT, &ib);
 	if (r)
 		goto err1;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 0ec7b061d7c2..a5a05c16c10d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -675,7 +675,7 @@ static void gmc_v10_0_vram_gtt_location(struct amdgpu_device *adev,
 	amdgpu_gmc_set_agp_default(adev, mc);
 	amdgpu_gmc_vram_location(adev, &adev->gmc, base);
 	amdgpu_gmc_gart_location(adev, mc, AMDGPU_GART_PLACEMENT_BEST_FIT);
-	if (!amdgpu_sriov_vf(adev))
+	if (!amdgpu_sriov_vf(adev) && (amdgpu_agp == 1))
 		amdgpu_gmc_agp_location(adev, mc);
 
 	/* base offset of vram pages */
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
index 6dce9b29f675..23d7b548d13f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
@@ -640,8 +640,9 @@ static void gmc_v11_0_vram_gtt_location(struct amdgpu_device *adev,
 	amdgpu_gmc_set_agp_default(adev, mc);
 	amdgpu_gmc_vram_location(adev, &adev->gmc, base);
 	amdgpu_gmc_gart_location(adev, mc, AMDGPU_GART_PLACEMENT_HIGH);
-	if (!amdgpu_sriov_vf(adev) ||
-	    (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(11, 5, 0)))
+	if (!amdgpu_sriov_vf(adev) &&
+	    (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(11, 5, 0)) &&
+	    (amdgpu_agp == 1))
 		amdgpu_gmc_agp_location(adev, mc);
 
 	/* base offset of vram pages */
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index bde25eb4ed8e..2ac5820e9c92 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1630,7 +1630,7 @@ static void gmc_v9_0_vram_gtt_location(struct amdgpu_device *adev,
 	} else {
 		amdgpu_gmc_vram_location(adev, mc, base);
 		amdgpu_gmc_gart_location(adev, mc, AMDGPU_GART_PLACEMENT_BEST_FIT);
-		if (!amdgpu_sriov_vf(adev))
+		if (!amdgpu_sriov_vf(adev) && (amdgpu_agp == 1))
 			amdgpu_gmc_agp_location(adev, mc);
 	}
 	/* base offset of vram pages */
@@ -2170,8 +2170,6 @@ static int gmc_v9_0_sw_fini(void *handle)
 
 	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3))
 		amdgpu_gmc_sysfs_fini(adev);
-	adev->gmc.num_mem_partitions = 0;
-	kfree(adev->gmc.mem_partitions);
 
 	amdgpu_gmc_ras_fini(adev);
 	amdgpu_gem_force_release(adev);
@@ -2185,6 +2183,9 @@ static int gmc_v9_0_sw_fini(void *handle)
 	amdgpu_bo_free_kernel(&adev->gmc.pdb0_bo, NULL, &adev->gmc.ptr_pdb0);
 	amdgpu_bo_fini(adev);
 
+	adev->gmc.num_mem_partitions = 0;
+	kfree(adev->gmc.mem_partitions);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
index 49e934975719..4db6bb73ead4 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
@@ -129,6 +129,11 @@ static void hdp_v4_0_get_clockgating_state(struct amdgpu_device *adev,
 {
 	int data;
 
+	if (amdgpu_ip_version(adev, HDP_HWIP, 0) == IP_VERSION(4, 4, 2)) {
+		/* Default enabled */
+		*flags |= AMD_CG_SUPPORT_HDP_MGCG;
+		return;
+	}
 	/* AMD_CG_SUPPORT_HDP_LS */
 	data = RREG32(SOC15_REG_OFFSET(HDP, 0, mmHDP_MEM_POWER_LS));
 	if (data & HDP_MEM_POWER_LS__LS_ENABLE_MASK)
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
index 9df011323d4b..6ede85b28cc8 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
@@ -155,13 +155,6 @@ static int jpeg_v4_0_5_hw_init(void *handle)
 	struct amdgpu_ring *ring = adev->jpeg.inst->ring_dec;
 	int r;
 
-	adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
-				(adev->doorbell_index.vcn.vcn_ring0_1 << 1), 0);
-
-	WREG32_SOC15(VCN, 0, regVCN_JPEG_DB_CTRL,
-		ring->doorbell_index << VCN_JPEG_DB_CTRL__OFFSET__SHIFT |
-		VCN_JPEG_DB_CTRL__EN_MASK);
-
 	r = amdgpu_ring_test_helper(ring);
 	if (r)
 		return r;
@@ -336,6 +329,14 @@ static int jpeg_v4_0_5_start(struct amdgpu_device *adev)
 	if (adev->pm.dpm_enabled)
 		amdgpu_dpm_enable_jpeg(adev, true);
 
+	/* doorbell programming is done for every playback */
+	adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
+				(adev->doorbell_index.vcn.vcn_ring0_1 << 1), 0);
+
+	WREG32_SOC15(VCN, 0, regVCN_JPEG_DB_CTRL,
+		ring->doorbell_index << VCN_JPEG_DB_CTRL__OFFSET__SHIFT |
+		VCN_JPEG_DB_CTRL__EN_MASK);
+
 	/* disable power gating */
 	r = jpeg_v4_0_5_disable_static_power_gating(adev);
 	if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c
index ea142611be1c..9b0146732e13 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c
@@ -130,6 +130,9 @@ static void mmhub_v1_8_init_system_aperture_regs(struct amdgpu_device *adev)
 	uint64_t value;
 	int i;
 
+	if (amdgpu_sriov_vf(adev))
+		return;
+
 	inst_mask = adev->aid_mask;
 	for_each_inst(i, inst_mask) {
 		/* Program the AGP BAR */
@@ -139,9 +142,6 @@ static void mmhub_v1_8_init_system_aperture_regs(struct amdgpu_device *adev)
 		WREG32_SOC15(MMHUB, i, regMC_VM_AGP_TOP,
 			     adev->gmc.agp_end >> 24);
 
-		if (amdgpu_sriov_vf(adev))
-			return;
-
 		/* Program the system aperture low logical page number. */
 		WREG32_SOC15(MMHUB, i, regMC_VM_SYSTEM_APERTURE_LOW_ADDR,
 			min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
index 676ab1d20d2f..1f52b4b1db03 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
@@ -259,17 +259,17 @@ const struct nbio_hdp_flush_reg nbio_v7_11_hdp_flush_reg = {
 
 static void nbio_v7_11_init_registers(struct amdgpu_device *adev)
 {
-/*	uint32_t def, data;
+	uint32_t def, data;
+
+	def = data = RREG32_SOC15(NBIO, 0, regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3);
+	data = REG_SET_FIELD(data, BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3,
+				CI_SWUS_MAX_READ_REQUEST_SIZE_MODE, 1);
+	data = REG_SET_FIELD(data, BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3,
+				CI_SWUS_MAX_READ_REQUEST_SIZE_PRIV, 1);
 
-		def = data = RREG32_SOC15(NBIO, 0, regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3);
-		data = REG_SET_FIELD(data, BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3,
-			CI_SWUS_MAX_READ_REQUEST_SIZE_MODE, 1);
-		data = REG_SET_FIELD(data, BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3,
-			CI_SWUS_MAX_READ_REQUEST_SIZE_PRIV, 1);
+	if (def != data)
+		WREG32_SOC15(NBIO, 0, regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3, data);
 
-		if (def != data)
-			WREG32_SOC15(NBIO, 0, regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3, data);
-*/
 }
 
 static void nbio_v7_11_update_medium_grain_clock_gating(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
index 23f26f8caad4..25a3da83e0fb 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
@@ -611,11 +611,6 @@ static void nbio_v7_9_handle_ras_controller_intr_no_bifring(struct amdgpu_device
 
 		dev_info(adev->dev, "RAS controller interrupt triggered "
 					"by NBIF error\n");
-
-		/* ras_controller_int is dedicated for nbif ras error,
-		 * not the global interrupt for sync flood
-		 */
-		amdgpu_ras_reset_gpu(adev);
 	}
 
 	amdgpu_ras_error_data_fini(&err_data);
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
index 3cf4684d0d3f..df1844d0800f 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
@@ -60,7 +60,7 @@ MODULE_FIRMWARE("amdgpu/psp_14_0_0_ta.bin");
 #define GFX_CMD_USB_PD_USE_LFB 0x480
 
 /* Retry times for vmbx ready wait */
-#define PSP_VMBX_POLLING_LIMIT 20000
+#define PSP_VMBX_POLLING_LIMIT 3000
 
 /* VBIOS gfl defines */
 #define MBOX_READY_MASK 0x80000000
@@ -161,14 +161,18 @@ static int psp_v13_0_wait_for_vmbx_ready(struct psp_context *psp)
 static int psp_v13_0_wait_for_bootloader(struct psp_context *psp)
 {
 	struct amdgpu_device *adev = psp->adev;
-	int retry_loop, ret;
+	int retry_loop, retry_cnt, ret;
 
+	retry_cnt =
+		(amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 6)) ?
+			PSP_VMBX_POLLING_LIMIT :
+			10;
 	/* Wait for bootloader to signify that it is ready having bit 31 of
 	 * C2PMSG_35 set to 1. All other bits are expected to be cleared.
 	 * If there is an error in processing command, bits[7:0] will be set.
 	 * This is applicable for PSP v13.0.6 and newer.
 	 */
-	for (retry_loop = 0; retry_loop < PSP_VMBX_POLLING_LIMIT; retry_loop++) {
+	for (retry_loop = 0; retry_loop < retry_cnt; retry_loop++) {
 		ret = psp_wait_for(
 			psp, SOC15_REG_OFFSET(MP0, 0, regMP0_SMN_C2PMSG_35),
 			0x80000000, 0xffffffff, false);
@@ -821,7 +825,7 @@ static int psp_v13_0_query_boot_status(struct psp_context *psp)
 	if (amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 6))
 		return 0;
 
-	if (RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_59) < 0x00a10007)
+	if (RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_59) < 0x00a10109)
 		return 0;
 
 	for_each_inst(i, inst_mask) {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index 45377a175250..8d5d86675a7f 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -813,12 +813,12 @@ static int sdma_v2_4_early_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	int r;
 
+	adev->sdma.num_instances = SDMA_MAX_INSTANCE;
+
 	r = sdma_v2_4_init_microcode(adev);
 	if (r)
 		return r;
 
-	adev->sdma.num_instances = SDMA_MAX_INSTANCE;
-
 	sdma_v2_4_set_ring_funcs(adev);
 	sdma_v2_4_set_buffer_funcs(adev);
 	sdma_v2_4_set_vm_pte_funcs(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index 83c240f741b5..0058f3f7cf6e 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -1643,6 +1643,32 @@ static void sdma_v5_2_get_clockgating_state(void *handle, u64 *flags)
 		*flags |= AMD_CG_SUPPORT_SDMA_LS;
 }
 
+static void sdma_v5_2_ring_begin_use(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	/* SDMA 5.2.3 (RMB) FW doesn't seem to properly
+	 * disallow GFXOFF in some cases leading to
+	 * hangs in SDMA.  Disallow GFXOFF while SDMA is active.
+	 * We can probably just limit this to 5.2.3,
+	 * but it shouldn't hurt for other parts since
+	 * this GFXOFF will be disallowed anyway when SDMA is
+	 * active, this just makes it explicit.
+	 */
+	amdgpu_gfx_off_ctrl(adev, false);
+}
+
+static void sdma_v5_2_ring_end_use(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	/* SDMA 5.2.3 (RMB) FW doesn't seem to properly
+	 * disallow GFXOFF in some cases leading to
+	 * hangs in SDMA.  Allow GFXOFF when SDMA is complete.
+	 */
+	amdgpu_gfx_off_ctrl(adev, true);
+}
+
 const struct amd_ip_funcs sdma_v5_2_ip_funcs = {
 	.name = "sdma_v5_2",
 	.early_init = sdma_v5_2_early_init,
@@ -1690,6 +1716,8 @@ static const struct amdgpu_ring_funcs sdma_v5_2_ring_funcs = {
 	.test_ib = sdma_v5_2_ring_test_ib,
 	.insert_nop = sdma_v5_2_ring_insert_nop,
 	.pad_ib = sdma_v5_2_ring_pad_ib,
+	.begin_use = sdma_v5_2_ring_begin_use,
+	.end_use = sdma_v5_2_ring_end_use,
 	.emit_wreg = sdma_v5_2_ring_emit_wreg,
 	.emit_reg_wait = sdma_v5_2_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = sdma_v5_2_ring_emit_reg_write_reg_wait,
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index d4b8d62f4294..51342809af03 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1161,6 +1161,11 @@ static int soc15_common_early_init(void *handle)
 			AMD_PG_SUPPORT_VCN_DPG |
 			AMD_PG_SUPPORT_JPEG;
 		adev->external_rev_id = adev->rev_id + 0x46;
+		/* GC 9.4.3 uses MMIO register region hole at a different offset */
+		if (!amdgpu_sriov_vf(adev)) {
+			adev->rmmio_remap.reg_offset = 0x1A000;
+			adev->rmmio_remap.bus_addr = adev->rmmio_base + 0x1A000;
+		}
 		break;
 	default:
 		/* FIXME: not supported yet */
@@ -1418,11 +1423,14 @@ static void soc15_common_get_clockgating_state(void *handle, u64 *flags)
 	if (amdgpu_sriov_vf(adev))
 		*flags = 0;
 
-	adev->nbio.funcs->get_clockgating_state(adev, flags);
+	if (adev->nbio.funcs && adev->nbio.funcs->get_clockgating_state)
+		adev->nbio.funcs->get_clockgating_state(adev, flags);
 
-	adev->hdp.funcs->get_clock_gating_state(adev, flags);
+	if (adev->hdp.funcs && adev->hdp.funcs->get_clock_gating_state)
+		adev->hdp.funcs->get_clock_gating_state(adev, flags);
 
-	if (amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 2)) {
+	if ((amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 2)) &&
+	    (amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 6))) {
 		/* AMD_CG_SUPPORT_DRM_MGCG */
 		data = RREG32(SOC15_REG_OFFSET(MP0, 0, mmMP0_MISC_CGTT_CTRL0));
 		if (!(data & 0x01000000))
@@ -1435,9 +1443,11 @@ static void soc15_common_get_clockgating_state(void *handle, u64 *flags)
 	}
 
 	/* AMD_CG_SUPPORT_ROM_MGCG */
-	adev->smuio.funcs->get_clock_gating_state(adev, flags);
+	if (adev->smuio.funcs && adev->smuio.funcs->get_clock_gating_state)
+		adev->smuio.funcs->get_clock_gating_state(adev, flags);
 
-	adev->df.funcs->get_clockgating_state(adev, flags);
+	if (adev->df.funcs && adev->df.funcs->get_clockgating_state)
+		adev->df.funcs->get_clockgating_state(adev, flags);
 }
 
 static int soc15_common_set_powergating_state(void *handle,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 9cc32f577e38..4c8e278a0d0c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1128,7 +1128,7 @@ static inline struct kfd_node *kfd_node_by_irq_ids(struct amdgpu_device *adev,
 	struct kfd_dev *dev = adev->kfd.dev;
 	uint32_t i;
 
-	if (adev->ip_versions[GC_HWIP][0] != IP_VERSION(9, 4, 3))
+	if (KFD_GC_VERSION(dev) != IP_VERSION(9, 4, 3))
 		return dev->nodes[0];
 
 	for (i = 0; i < dev->num_nodes; i++)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 77649392e233..77f493262e05 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -169,16 +169,43 @@ int pqm_init(struct process_queue_manager *pqm, struct kfd_process *p)
 	return 0;
 }
 
+static void pqm_clean_queue_resource(struct process_queue_manager *pqm,
+				     struct process_queue_node *pqn)
+{
+	struct kfd_node *dev;
+	struct kfd_process_device *pdd;
+
+	dev = pqn->q->device;
+
+	pdd = kfd_get_process_device_data(dev, pqm->process);
+	if (!pdd) {
+		pr_err("Process device data doesn't exist\n");
+		return;
+	}
+
+	if (pqn->q->gws) {
+		if (KFD_GC_VERSION(pqn->q->device) != IP_VERSION(9, 4, 3) &&
+		    !dev->kfd->shared_resources.enable_mes)
+			amdgpu_amdkfd_remove_gws_from_process(
+				pqm->process->kgd_process_info, pqn->q->gws);
+		pdd->qpd.num_gws = 0;
+	}
+
+	if (dev->kfd->shared_resources.enable_mes) {
+		amdgpu_amdkfd_free_gtt_mem(dev->adev, pqn->q->gang_ctx_bo);
+		if (pqn->q->wptr_bo)
+			amdgpu_amdkfd_free_gtt_mem(dev->adev, pqn->q->wptr_bo);
+	}
+}
+
 void pqm_uninit(struct process_queue_manager *pqm)
 {
 	struct process_queue_node *pqn, *next;
 
 	list_for_each_entry_safe(pqn, next, &pqm->queues, process_queue_list) {
-		if (pqn->q && pqn->q->gws &&
-		    KFD_GC_VERSION(pqn->q->device) != IP_VERSION(9, 4, 3) &&
-		    !pqn->q->device->kfd->shared_resources.enable_mes)
-			amdgpu_amdkfd_remove_gws_from_process(pqm->process->kgd_process_info,
-				pqn->q->gws);
+		if (pqn->q)
+			pqm_clean_queue_resource(pqm, pqn);
+
 		kfd_procfs_del_queue(pqn->q);
 		uninit_queue(pqn->q);
 		list_del(&pqn->process_queue_list);
@@ -461,22 +488,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
 				goto err_destroy_queue;
 		}
 
-		if (pqn->q->gws) {
-			if (KFD_GC_VERSION(pqn->q->device) != IP_VERSION(9, 4, 3) &&
-			    !dev->kfd->shared_resources.enable_mes)
-				amdgpu_amdkfd_remove_gws_from_process(
-						pqm->process->kgd_process_info,
-						pqn->q->gws);
-			pdd->qpd.num_gws = 0;
-		}
-
-		if (dev->kfd->shared_resources.enable_mes) {
-			amdgpu_amdkfd_free_gtt_mem(dev->adev,
-						   pqn->q->gang_ctx_bo);
-			if (pqn->q->wptr_bo)
-				amdgpu_amdkfd_free_gtt_mem(dev->adev, pqn->q->wptr_bo);
-
-		}
+		pqm_clean_queue_resource(pqm, pqn);
 		uninit_queue(pqn->q);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index f2f3c338fd94..a15bfb5223e8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1653,18 +1653,24 @@ static int svm_range_validate_and_map(struct mm_struct *mm,
 			if (test_bit(gpuidx, prange->bitmap_access))
 				bitmap_set(ctx->bitmap, gpuidx, 1);
 		}
+
+		/*
+		 * If prange is already mapped or with always mapped flag,
+		 * update mapping on GPUs with ACCESS attribute
+		 */
+		if (bitmap_empty(ctx->bitmap, MAX_GPU_INSTANCE)) {
+			if (prange->mapped_to_gpu ||
+			    prange->flags & KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED)
+				bitmap_copy(ctx->bitmap, prange->bitmap_access, MAX_GPU_INSTANCE);
+		}
 	} else {
 		bitmap_or(ctx->bitmap, prange->bitmap_access,
 			  prange->bitmap_aip, MAX_GPU_INSTANCE);
 	}
 
 	if (bitmap_empty(ctx->bitmap, MAX_GPU_INSTANCE)) {
-		bitmap_copy(ctx->bitmap, prange->bitmap_access, MAX_GPU_INSTANCE);
-		if (!prange->mapped_to_gpu ||
-		    bitmap_empty(ctx->bitmap, MAX_GPU_INSTANCE)) {
-			r = 0;
-			goto free_ctx;
-		}
+		r = 0;
+		goto free_ctx;
 	}
 
 	if (prange->actual_loc && !prange->ttm_res) {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 6f99f6754c11..4e82ee4d74ac 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2079,7 +2079,7 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev)
 	struct dmub_srv_create_params create_params;
 	struct dmub_srv_region_params region_params;
 	struct dmub_srv_region_info region_info;
-	struct dmub_srv_fb_params fb_params;
+	struct dmub_srv_memory_params memory_params;
 	struct dmub_srv_fb_info *fb_info;
 	struct dmub_srv *dmub_srv;
 	const struct dmcub_firmware_header_v1_0 *hdr;
@@ -2182,6 +2182,7 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev)
 		adev->dm.dmub_fw->data +
 		le32_to_cpu(hdr->header.ucode_array_offset_bytes) +
 		PSP_HEADER_BYTES;
+	region_params.is_mailbox_in_inbox = false;
 
 	status = dmub_srv_calc_region_info(dmub_srv, &region_params,
 					   &region_info);
@@ -2205,10 +2206,10 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev)
 		return r;
 
 	/* Rebase the regions on the framebuffer address. */
-	memset(&fb_params, 0, sizeof(fb_params));
-	fb_params.cpu_addr = adev->dm.dmub_bo_cpu_addr;
-	fb_params.gpu_addr = adev->dm.dmub_bo_gpu_addr;
-	fb_params.region_info = &region_info;
+	memset(&memory_params, 0, sizeof(memory_params));
+	memory_params.cpu_fb_addr = adev->dm.dmub_bo_cpu_addr;
+	memory_params.gpu_fb_addr = adev->dm.dmub_bo_gpu_addr;
+	memory_params.region_info = &region_info;
 
 	adev->dm.dmub_fb_info =
 		kzalloc(sizeof(*adev->dm.dmub_fb_info), GFP_KERNEL);
@@ -2220,7 +2221,7 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev)
 		return -ENOMEM;
 	}
 
-	status = dmub_srv_calc_fb_info(dmub_srv, &fb_params, fb_info);
+	status = dmub_srv_calc_mem_info(dmub_srv, &memory_params, fb_info);
 	if (status != DMUB_STATUS_OK) {
 		DRM_ERROR("Error calculating DMUB FB info: %d\n", status);
 		return -EINVAL;
@@ -5181,6 +5182,9 @@ static void fill_dc_dirty_rects(struct drm_plane *plane,
 	if (plane->type == DRM_PLANE_TYPE_CURSOR)
 		return;
 
+	if (new_plane_state->rotation != DRM_MODE_ROTATE_0)
+		goto ffu;
+
 	num_clips = drm_plane_get_damage_clips_count(new_plane_state);
 	clips = drm_plane_get_damage_clips(new_plane_state);
 
@@ -6166,8 +6170,9 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 
 	if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A)
 		mod_build_hf_vsif_infopacket(stream, &stream->vsp_infopacket);
-
-	if (stream->link->psr_settings.psr_feature_enabled || stream->link->replay_settings.replay_feature_enabled) {
+	else if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT ||
+			 stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST ||
+			 stream->signal == SIGNAL_TYPE_EDP) {
 		//
 		// should decide stream support vsc sdp colorimetry capability
 		// before building vsc info packet
@@ -6183,8 +6188,9 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 		if (stream->out_transfer_func->tf == TRANSFER_FUNCTION_GAMMA22)
 			tf = TRANSFER_FUNC_GAMMA_22;
 		mod_build_vsc_infopacket(stream, &stream->vsc_infopacket, stream->output_color_space, tf);
-		aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY;
 
+		if (stream->link->psr_settings.psr_feature_enabled)
+			aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY;
 	}
 finish:
 	dc_sink_release(sink);
@@ -6266,7 +6272,7 @@ int amdgpu_dm_connector_atomic_set_property(struct drm_connector *connector,
 		dm_new_state->underscan_enable = val;
 		ret = 0;
 	} else if (property == adev->mode_info.abm_level_property) {
-		dm_new_state->abm_level = val;
+		dm_new_state->abm_level = val ?: ABM_LEVEL_IMMEDIATE_DISABLE;
 		ret = 0;
 	}
 
@@ -6311,7 +6317,8 @@ int amdgpu_dm_connector_atomic_get_property(struct drm_connector *connector,
 		*val = dm_state->underscan_enable;
 		ret = 0;
 	} else if (property == adev->mode_info.abm_level_property) {
-		*val = dm_state->abm_level;
+		*val = (dm_state->abm_level != ABM_LEVEL_IMMEDIATE_DISABLE) ?
+			dm_state->abm_level : 0;
 		ret = 0;
 	}
 
@@ -6384,7 +6391,8 @@ void amdgpu_dm_connector_funcs_reset(struct drm_connector *connector)
 		state->pbn = 0;
 
 		if (connector->connector_type == DRM_MODE_CONNECTOR_eDP)
-			state->abm_level = amdgpu_dm_abm_level;
+			state->abm_level = amdgpu_dm_abm_level ?:
+				ABM_LEVEL_IMMEDIATE_DISABLE;
 
 		__drm_atomic_helper_connector_reset(connector, &state->base);
 	}
@@ -6908,8 +6916,7 @@ static int dm_encoder_helper_atomic_check(struct drm_encoder *encoder,
 	if (IS_ERR(mst_state))
 		return PTR_ERR(mst_state);
 
-	if (!mst_state->pbn_div)
-		mst_state->pbn_div = dm_mst_get_pbn_divider(aconnector->mst_root->dc_link);
+	mst_state->pbn_div = dm_mst_get_pbn_divider(aconnector->mst_root->dc_link);
 
 	if (!state->duplicated) {
 		int max_bpc = conn_state->max_requested_bpc;
@@ -7481,6 +7488,9 @@ static int amdgpu_dm_i2c_xfer(struct i2c_adapter *i2c_adap,
 	int i;
 	int result = -EIO;
 
+	if (!ddc_service->ddc_pin || !ddc_service->ddc_pin->hw_info.hw_supported)
+		return result;
+
 	cmd.payloads = kcalloc(num, sizeof(struct i2c_payload), GFP_KERNEL);
 
 	if (!cmd.payloads)
@@ -9603,14 +9613,14 @@ static bool should_reset_plane(struct drm_atomic_state *state,
 	struct drm_plane *other;
 	struct drm_plane_state *old_other_state, *new_other_state;
 	struct drm_crtc_state *new_crtc_state;
+	struct amdgpu_device *adev = drm_to_adev(plane->dev);
 	int i;
 
 	/*
-	 * TODO: Remove this hack once the checks below are sufficient
-	 * enough to determine when we need to reset all the planes on
-	 * the stream.
+	 * TODO: Remove this hack for all asics once it proves that the
+	 * fast updates works fine on DCN3.2+.
 	 */
-	if (state->allow_modeset)
+	if (adev->ip_versions[DCE_HWIP][0] < IP_VERSION(3, 2, 0) && state->allow_modeset)
 		return true;
 
 	/* Exit early if we know that we're adding or removing the plane. */
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index ed784cf27d39..aac98f93545a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -63,6 +63,12 @@ static void apply_edid_quirks(struct edid *edid, struct dc_edid_caps *edid_caps)
 		DRM_DEBUG_DRIVER("Disabling FAMS on monitor with panel id %X\n", panel_id);
 		edid_caps->panel_patch.disable_fams = true;
 		break;
+	/* Workaround for some monitors that do not clear DPCD 0x317 if FreeSync is unsupported */
+	case drm_edid_encode_panel_id('A', 'U', 'O', 0xA7AB):
+	case drm_edid_encode_panel_id('A', 'U', 'O', 0xE69B):
+		DRM_DEBUG_DRIVER("Clearing DPCD 0x317 on monitor with panel id %X\n", panel_id);
+		edid_caps->panel_patch.remove_sink_ext_caps = true;
+		break;
 	default:
 		return;
 	}
@@ -536,11 +542,8 @@ bool dm_helpers_dp_read_dpcd(
 
 	struct amdgpu_dm_connector *aconnector = link->priv;
 
-	if (!aconnector) {
-		drm_dbg_dp(aconnector->base.dev,
-			   "Failed to find connector for link!\n");
+	if (!aconnector)
 		return false;
-	}
 
 	return drm_dp_dpcd_read(&aconnector->dm_dp_aux.aux, address, data,
 				size) == size;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index d3b13d362eda..11da0eebee6c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -1604,31 +1604,31 @@ enum dc_status dm_dp_mst_is_port_support_mode(
 	unsigned int upper_link_bw_in_kbps = 0, down_link_bw_in_kbps = 0;
 	unsigned int max_compressed_bw_in_kbps = 0;
 	struct dc_dsc_bw_range bw_range = {0};
-	struct drm_dp_mst_topology_mgr *mst_mgr;
+	uint16_t full_pbn = aconnector->mst_output_port->full_pbn;
 
 	/*
-	 * check if the mode could be supported if DSC pass-through is supported
-	 * AND check if there enough bandwidth available to support the mode
-	 * with DSC enabled.
+	 * Consider the case with the depth of the mst topology tree is equal or less than 2
+	 * A. When dsc bitstream can be transmitted along the entire path
+	 *    1. dsc is possible between source and branch/leaf device (common dsc params is possible), AND
+	 *    2. dsc passthrough supported at MST branch, or
+	 *    3. dsc decoding supported at leaf MST device
+	 *    Use maximum dsc compression as bw constraint
+	 * B. When dsc bitstream cannot be transmitted along the entire path
+	 *    Use native bw as bw constraint
 	 */
 	if (is_dsc_common_config_possible(stream, &bw_range) &&
-	    aconnector->mst_output_port->passthrough_aux) {
-		mst_mgr = aconnector->mst_output_port->mgr;
-		mutex_lock(&mst_mgr->lock);
-
+	   (aconnector->mst_output_port->passthrough_aux ||
+	    aconnector->dsc_aux == &aconnector->mst_output_port->aux)) {
 		cur_link_settings = stream->link->verified_link_cap;
 
 		upper_link_bw_in_kbps = dc_link_bandwidth_kbps(aconnector->dc_link,
-							       &cur_link_settings
-							       );
-		down_link_bw_in_kbps = kbps_from_pbn(aconnector->mst_output_port->full_pbn);
+							       &cur_link_settings);
+		down_link_bw_in_kbps = kbps_from_pbn(full_pbn);
 
 		/* pick the bottleneck */
 		end_to_end_bw_in_kbps = min(upper_link_bw_in_kbps,
 					    down_link_bw_in_kbps);
 
-		mutex_unlock(&mst_mgr->lock);
-
 		/*
 		 * use the maximum dsc compression bandwidth as the required
 		 * bandwidth for the mode
@@ -1643,8 +1643,7 @@ enum dc_status dm_dp_mst_is_port_support_mode(
 		/* check if mode could be supported within full_pbn */
 		bpp = convert_dc_color_depth_into_bpc(stream->timing.display_color_depth) * 3;
 		pbn = drm_dp_calc_pbn_mode(stream->timing.pix_clk_100hz / 10, bpp, false);
-
-		if (pbn > aconnector->mst_output_port->full_pbn)
+		if (pbn > full_pbn)
 			return DC_FAIL_BANDWIDTH_VALIDATE;
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index 7cdb1a8a0ba0..2d1f5efa9091 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -1014,13 +1014,20 @@ static enum bp_result get_ss_info_v4_5(
 		DC_LOG_BIOS("AS_SIGNAL_TYPE_HDMI ss_percentage: %d\n", ss_info->spread_spectrum_percentage);
 		break;
 	case AS_SIGNAL_TYPE_DISPLAY_PORT:
-		ss_info->spread_spectrum_percentage =
+		if (bp->base.integrated_info) {
+			DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", bp->base.integrated_info->gpuclk_ss_percentage);
+			ss_info->spread_spectrum_percentage =
+					bp->base.integrated_info->gpuclk_ss_percentage;
+			ss_info->type.CENTER_MODE =
+					bp->base.integrated_info->gpuclk_ss_type;
+		} else {
+			ss_info->spread_spectrum_percentage =
 				disp_cntl_tbl->dp_ss_percentage;
-		ss_info->spread_spectrum_range =
+			ss_info->spread_spectrum_range =
 				disp_cntl_tbl->dp_ss_rate_10hz * 10;
-		if (disp_cntl_tbl->dp_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE)
-			ss_info->type.CENTER_MODE = true;
-
+			if (disp_cntl_tbl->dp_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE)
+				ss_info->type.CENTER_MODE = true;
+		}
 		DC_LOG_BIOS("AS_SIGNAL_TYPE_DISPLAY_PORT ss_percentage: %d\n", ss_info->spread_spectrum_percentage);
 		break;
 	case AS_SIGNAL_TYPE_GPU_PLL:
@@ -2814,6 +2821,8 @@ static enum bp_result get_integrated_info_v2_2(
 	info->ma_channel_number = info_v2_2->umachannelnumber;
 	info->dp_ss_control =
 		le16_to_cpu(info_v2_2->reserved1);
+	info->gpuclk_ss_percentage = info_v2_2->gpuclk_ss_percentage;
+	info->gpuclk_ss_type = info_v2_2->gpuclk_ss_type;
 
 	for (i = 0; i < NUMBER_OF_UCHAR_FOR_GUID; ++i) {
 		info->ext_disp_conn_info.gu_id[i] =
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
index b2c4f97afc8b..8776055bbeaa 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
@@ -334,7 +334,7 @@ static struct wm_table lpddr5_wm_table = {
 		{
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 11.65333,
+			.pstate_latency_us = 129.0,
 			.sr_exit_time_us = 11.5,
 			.sr_enter_plus_exit_time_us = 14.5,
 			.valid = true,
@@ -342,7 +342,7 @@ static struct wm_table lpddr5_wm_table = {
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 11.65333,
+			.pstate_latency_us = 129.0,
 			.sr_exit_time_us = 11.5,
 			.sr_enter_plus_exit_time_us = 14.5,
 			.valid = true,
@@ -350,7 +350,7 @@ static struct wm_table lpddr5_wm_table = {
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 11.65333,
+			.pstate_latency_us = 129.0,
 			.sr_exit_time_us = 11.5,
 			.sr_enter_plus_exit_time_us = 14.5,
 			.valid = true,
@@ -358,7 +358,7 @@ static struct wm_table lpddr5_wm_table = {
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 11.65333,
+			.pstate_latency_us = 129.0,
 			.sr_exit_time_us = 11.5,
 			.sr_enter_plus_exit_time_us = 14.5,
 			.valid = true,
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
index 0fa4fcd00de2..d5fde7d23fbf 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
@@ -232,6 +232,10 @@ void dcn35_update_clocks(struct clk_mgr *clk_mgr_base,
 	if (dc->work_arounds.skip_clock_update)
 		return;
 
+	/* DTBCLK is fixed, so set a default if unspecified. */
+	if (new_clocks->dtbclk_en && !new_clocks->ref_dtbclk_khz)
+		new_clocks->ref_dtbclk_khz = 600000;
+
 	/*
 	 * if it is safe to lower, but we are already in the lower state, we don't have to do anything
 	 * also if safe to lower is false, we just go in the higher state
@@ -265,8 +269,10 @@ void dcn35_update_clocks(struct clk_mgr *clk_mgr_base,
 
 		if (!clk_mgr_base->clks.dtbclk_en && new_clocks->dtbclk_en) {
 			dcn35_smu_set_dtbclk(clk_mgr, true);
-			dcn35_update_clocks_update_dtb_dto(clk_mgr, context, clk_mgr_base->clks.ref_dtbclk_khz);
 			clk_mgr_base->clks.dtbclk_en = new_clocks->dtbclk_en;
+
+			dcn35_update_clocks_update_dtb_dto(clk_mgr, context, new_clocks->ref_dtbclk_khz);
+			clk_mgr_base->clks.ref_dtbclk_khz = new_clocks->ref_dtbclk_khz;
 		}
 
 		/* check that we're not already in D0 */
@@ -314,17 +320,12 @@ void dcn35_update_clocks(struct clk_mgr *clk_mgr_base,
 		update_dispclk = true;
 	}
 
-	if (!new_clocks->dtbclk_en) {
-		new_clocks->ref_dtbclk_khz = 600000;
-	}
-
 	/* clock limits are received with MHz precision, divide by 1000 to prevent setting clocks at every call */
 	if (!dc->debug.disable_dtb_ref_clk_switch &&
-			should_set_clock(safe_to_lower, new_clocks->ref_dtbclk_khz / 1000, clk_mgr_base->clks.ref_dtbclk_khz / 1000)) {
-		/* DCCG requires KHz precision for DTBCLK */
-		dcn35_smu_set_dtbclk(clk_mgr, true);
-
-		dcn35_update_clocks_update_dtb_dto(clk_mgr, context, clk_mgr_base->clks.ref_dtbclk_khz);
+	    should_set_clock(safe_to_lower, new_clocks->ref_dtbclk_khz / 1000,
+			     clk_mgr_base->clks.ref_dtbclk_khz / 1000)) {
+		dcn35_update_clocks_update_dtb_dto(clk_mgr, context, new_clocks->ref_dtbclk_khz);
+		clk_mgr_base->clks.ref_dtbclk_khz = new_clocks->ref_dtbclk_khz;
 	}
 
 	if (dpp_clock_lowered) {
@@ -443,32 +444,32 @@ static struct wm_table ddr5_wm_table = {
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 9,
-			.sr_enter_plus_exit_time_us = 11,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 9,
-			.sr_enter_plus_exit_time_us = 11,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 9,
-			.sr_enter_plus_exit_time_us = 11,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 9,
-			.sr_enter_plus_exit_time_us = 11,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 	}
@@ -480,32 +481,32 @@ static struct wm_table lpddr5_wm_table = {
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 11.5,
-			.sr_enter_plus_exit_time_us = 14.5,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 11.5,
-			.sr_enter_plus_exit_time_us = 14.5,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 11.5,
-			.sr_enter_plus_exit_time_us = 14.5,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 11.5,
-			.sr_enter_plus_exit_time_us = 14.5,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 	}
@@ -515,11 +516,6 @@ static DpmClocks_t_dcn35 dummy_clocks;
 
 static struct dcn35_watermarks dummy_wms = { 0 };
 
-static struct dcn35_ss_info_table ss_info_table = {
-	.ss_divider = 1000,
-	.ss_percentage = {0, 0, 375, 375, 375}
-};
-
 static void dcn35_build_watermark_ranges(struct clk_bw_params *bw_params, struct dcn35_watermarks *table)
 {
 	int i, num_valid_sets;
@@ -653,27 +649,47 @@ static unsigned int convert_wck_ratio(uint8_t wck_ratio)
 	return 1;
 }
 
+static inline uint32_t calc_dram_speed_mts(const MemPstateTable_t *entry)
+{
+	return entry->UClk * convert_wck_ratio(entry->WckRatio) * 2;
+}
+
 static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk_mgr,
 						    struct integrated_info *bios_info,
 						    DpmClocks_t_dcn35 *clock_table)
 {
 	struct clk_bw_params *bw_params = clk_mgr->base.bw_params;
 	struct clk_limit_table_entry def_max = bw_params->clk_table.entries[bw_params->clk_table.num_entries - 1];
-	uint32_t max_pstate = 0,  max_uclk = 0, max_fclk = 0;
-	uint32_t min_pstate = 0, max_dispclk = 0, max_dppclk = 0;
+	uint32_t max_fclk = 0, min_pstate = 0, max_dispclk = 0, max_dppclk = 0;
+	uint32_t max_pstate = 0, max_dram_speed_mts = 0, min_dram_speed_mts = 0;
 	int i;
 
+	/* Determine min/max p-state values. */
 	for (i = 0; i < clock_table->NumMemPstatesEnabled; i++) {
-		if (is_valid_clock_value(clock_table->MemPstateTable[i].UClk) &&
-		    clock_table->MemPstateTable[i].UClk > max_uclk) {
-			max_uclk = clock_table->MemPstateTable[i].UClk;
+		uint32_t dram_speed_mts = calc_dram_speed_mts(&clock_table->MemPstateTable[i]);
+
+		if (is_valid_clock_value(dram_speed_mts) && dram_speed_mts > max_dram_speed_mts) {
+			max_dram_speed_mts = dram_speed_mts;
 			max_pstate = i;
 		}
 	}
 
-	/* We expect the table to contain at least one valid Uclk entry. */
-	ASSERT(is_valid_clock_value(max_uclk));
+	min_dram_speed_mts = max_dram_speed_mts;
+	min_pstate = max_pstate;
+
+	for (i = 0; i < clock_table->NumMemPstatesEnabled; i++) {
+		uint32_t dram_speed_mts = calc_dram_speed_mts(&clock_table->MemPstateTable[i]);
+
+		if (is_valid_clock_value(dram_speed_mts) && dram_speed_mts < min_dram_speed_mts) {
+			min_dram_speed_mts = dram_speed_mts;
+			min_pstate = i;
+		}
+	}
 
+	/* We expect the table to contain at least one valid P-state entry. */
+	ASSERT(clock_table->NumMemPstatesEnabled &&
+	       is_valid_clock_value(max_dram_speed_mts) &&
+	       is_valid_clock_value(min_dram_speed_mts));
 
 	/* dispclk and dppclk can be max at any voltage, same number of levels for both */
 	if (clock_table->NumDispClkLevelsEnabled <= NUM_DISPCLK_DPM_LEVELS &&
@@ -683,47 +699,46 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
 		max_dppclk = find_max_clk_value(clock_table->DppClocks,
 			clock_table->NumDispClkLevelsEnabled);
 	} else {
+		/* Invalid number of entries in the table from PMFW. */
 		ASSERT(0);
 	}
-	if (clock_table->NumFclkLevelsEnabled <= NUM_FCLK_DPM_LEVELS)
-		max_fclk = find_max_clk_value(clock_table->FclkClocks_Freq,
-			clock_table->NumFclkLevelsEnabled);
 
-	for (i = 0; i < clock_table->NumMemPstatesEnabled; i++) {
-		uint32_t min_uclk = clock_table->MemPstateTable[0].UClk;
-		int j;
+	/* Base the clock table on dcfclk, need at least one entry regardless of pmfw table */
+	ASSERT(clock_table->NumDcfClkLevelsEnabled > 0);
 
-		for (j = 1; j < clock_table->NumMemPstatesEnabled; j++) {
-			if (is_valid_clock_value(clock_table->MemPstateTable[j].UClk) &&
-			    clock_table->MemPstateTable[j].UClk < min_uclk &&
-			    clock_table->MemPstateTable[j].Voltage <= clock_table->SocVoltage[i]) {
-				min_uclk = clock_table->MemPstateTable[j].UClk;
-				min_pstate = j;
-			}
-		}
+	max_fclk = find_max_clk_value(clock_table->FclkClocks_Freq, clock_table->NumFclkLevelsEnabled);
+
+	for (i = 0; i < clock_table->NumDcfClkLevelsEnabled; i++) {
+		int j;
 
+		/* First search defaults for the clocks we don't read using closest lower or equal default dcfclk */
 		for (j = bw_params->clk_table.num_entries - 1; j > 0; j--)
 			if (bw_params->clk_table.entries[j].dcfclk_mhz <= clock_table->DcfClocks[i])
-			break;
+				break;
 
 		bw_params->clk_table.entries[i].phyclk_mhz = bw_params->clk_table.entries[j].phyclk_mhz;
 		bw_params->clk_table.entries[i].phyclk_d18_mhz = bw_params->clk_table.entries[j].phyclk_d18_mhz;
 		bw_params->clk_table.entries[i].dtbclk_mhz = bw_params->clk_table.entries[j].dtbclk_mhz;
-		bw_params->clk_table.entries[i].fclk_mhz = max_fclk;
+
+		/* Now update clocks we do read */
 		bw_params->clk_table.entries[i].memclk_mhz = clock_table->MemPstateTable[min_pstate].MemClk;
 		bw_params->clk_table.entries[i].voltage = clock_table->MemPstateTable[min_pstate].Voltage;
 		bw_params->clk_table.entries[i].dcfclk_mhz = clock_table->DcfClocks[i];
 		bw_params->clk_table.entries[i].socclk_mhz = clock_table->SocClocks[i];
 		bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk;
 		bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk;
-		bw_params->clk_table.entries[i].wck_ratio = convert_wck_ratio(
-			clock_table->MemPstateTable[min_pstate].WckRatio);
-		}
+		bw_params->clk_table.entries[i].wck_ratio =
+			convert_wck_ratio(clock_table->MemPstateTable[min_pstate].WckRatio);
+
+		/* Dcfclk and Fclk are tied, but at a different ratio */
+		bw_params->clk_table.entries[i].fclk_mhz = min(max_fclk, 2 * clock_table->DcfClocks[i]);
+	}
 
 	/* Make sure to include at least one entry at highest pstate */
 	if (max_pstate != min_pstate || i == 0) {
 		if (i > MAX_NUM_DPM_LVL - 1)
 			i = MAX_NUM_DPM_LVL - 1;
+
 		bw_params->clk_table.entries[i].fclk_mhz = max_fclk;
 		bw_params->clk_table.entries[i].memclk_mhz = clock_table->MemPstateTable[max_pstate].MemClk;
 		bw_params->clk_table.entries[i].voltage = clock_table->MemPstateTable[max_pstate].Voltage;
@@ -739,6 +754,7 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
 	}
 	bw_params->clk_table.num_entries = i--;
 
+	/* Make sure all highest clocks are included*/
 	bw_params->clk_table.entries[i].socclk_mhz =
 		find_max_clk_value(clock_table->SocClocks, NUM_SOCCLK_DPM_LEVELS);
 	bw_params->clk_table.entries[i].dispclk_mhz =
@@ -757,6 +773,11 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
 	bw_params->clk_table.num_entries_per_clk.num_fclk_levels = clock_table->NumFclkLevelsEnabled;
 	bw_params->clk_table.num_entries_per_clk.num_memclk_levels = clock_table->NumMemPstatesEnabled;
 	bw_params->clk_table.num_entries_per_clk.num_socclk_levels = clock_table->NumSocClkLevelsEnabled;
+
+	/*
+	 * Set any 0 clocks to max default setting. Not an issue for
+	 * power since we aren't doing switching in such case anyway
+	 */
 	for (i = 0; i < bw_params->clk_table.num_entries; i++) {
 		if (!bw_params->clk_table.entries[i].fclk_mhz) {
 			bw_params->clk_table.entries[i].fclk_mhz = def_max.fclk_mhz;
@@ -820,22 +841,22 @@ static void dcn35_set_idle_state(struct clk_mgr *clk_mgr_base, bool allow_idle)
 
 	if (dc->config.disable_ips == DMUB_IPS_ENABLE ||
 		dc->config.disable_ips == DMUB_IPS_DISABLE_DYNAMIC) {
-		val |= DMUB_IPS1_ALLOW_MASK;
-		val |= DMUB_IPS2_ALLOW_MASK;
-	} else if (dc->config.disable_ips == DMUB_IPS_DISABLE_IPS1) {
 		val = val & ~DMUB_IPS1_ALLOW_MASK;
 		val = val & ~DMUB_IPS2_ALLOW_MASK;
-	} else if (dc->config.disable_ips == DMUB_IPS_DISABLE_IPS2) {
-		val |= DMUB_IPS1_ALLOW_MASK;
-		val = val & ~DMUB_IPS2_ALLOW_MASK;
-	} else if (dc->config.disable_ips == DMUB_IPS_DISABLE_IPS2_Z10) {
+	} else if (dc->config.disable_ips == DMUB_IPS_DISABLE_IPS1) {
 		val |= DMUB_IPS1_ALLOW_MASK;
 		val |= DMUB_IPS2_ALLOW_MASK;
+	} else if (dc->config.disable_ips == DMUB_IPS_DISABLE_IPS2) {
+		val = val & ~DMUB_IPS1_ALLOW_MASK;
+		val |= DMUB_IPS2_ALLOW_MASK;
+	} else if (dc->config.disable_ips == DMUB_IPS_DISABLE_IPS2_Z10) {
+		val = val & ~DMUB_IPS1_ALLOW_MASK;
+		val = val & ~DMUB_IPS2_ALLOW_MASK;
 	}
 
 	if (!allow_idle) {
-		val = val & ~DMUB_IPS1_ALLOW_MASK;
-		val = val & ~DMUB_IPS2_ALLOW_MASK;
+		val |= DMUB_IPS1_ALLOW_MASK;
+		val |= DMUB_IPS2_ALLOW_MASK;
 	}
 
 	dcn35_smu_write_ips_scratch(clk_mgr, val);
@@ -965,21 +986,6 @@ struct clk_mgr_funcs dcn35_fpga_funcs = {
 	.get_dtb_ref_clk_frequency = dcn31_get_dtb_ref_freq_khz,
 };
 
-static void dcn35_read_ss_info_from_lut(struct clk_mgr_internal *clk_mgr)
-{
-	uint32_t clock_source;
-	struct dc_context *ctx = clk_mgr->base.ctx;
-
-	REG_GET(CLK1_CLK2_BYPASS_CNTL, CLK2_BYPASS_SEL, &clock_source);
-
-	clk_mgr->dprefclk_ss_percentage = ss_info_table.ss_percentage[clock_source];
-
-	if (clk_mgr->dprefclk_ss_percentage != 0) {
-		clk_mgr->ss_on_dprefclk = true;
-		clk_mgr->dprefclk_ss_divider = ss_info_table.ss_divider;
-	}
-}
-
 void dcn35_clk_mgr_construct(
 		struct dc_context *ctx,
 		struct clk_mgr_dcn35 *clk_mgr,
@@ -1043,17 +1049,11 @@ void dcn35_clk_mgr_construct(
 	dcn35_dump_clk_registers(&clk_mgr->base.base.boot_snapshot, &clk_mgr->base.base, &log_info);
 
 	clk_mgr->base.base.dprefclk_khz = dcn35_smu_get_dprefclk(&clk_mgr->base);
-	clk_mgr->base.base.clks.ref_dtbclk_khz = dcn35_smu_get_dtbclk(&clk_mgr->base);
-
-	if (!clk_mgr->base.base.clks.ref_dtbclk_khz)
-		dcn35_smu_set_dtbclk(&clk_mgr->base, true);
+	clk_mgr->base.base.clks.ref_dtbclk_khz = 600000;
 
-	clk_mgr->base.base.clks.dtbclk_en = true;
 	dce_clock_read_ss_info(&clk_mgr->base);
 	/*when clk src is from FCH, it could have ss, same clock src as DPREF clk*/
 
-	dcn35_read_ss_info_from_lut(&clk_mgr->base);
-
 	clk_mgr->base.base.bw_params = &dcn35_bw_params;
 
 	if (clk_mgr->base.base.ctx->dc->debug.pstate_enabled) {
@@ -1129,7 +1129,6 @@ void dcn35_clk_mgr_construct(
 			ctx->dc->debug.disable_dpp_power_gate = false;
 			ctx->dc->debug.disable_hubp_power_gate = false;
 			ctx->dc->debug.disable_dsc_power_gate = false;
-			ctx->dc->debug.disable_hpo_power_gate = false;
 		} else {
 			/*let's reset the config control flag*/
 			ctx->dc->config.disable_ips = DMUB_IPS_DISABLE_ALL; /*pmfw not support it, disable it all*/
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 7b9bf5cb4529..5c1185206645 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -3178,7 +3178,7 @@ static bool update_planes_and_stream_state(struct dc *dc,
 			struct pipe_ctx *otg_master = resource_get_otg_master_for_stream(&context->res_ctx,
 					context->streams[i]);
 
-			if (otg_master->stream->test_pattern.type != DP_TEST_PATTERN_VIDEO_MODE)
+			if (otg_master && otg_master->stream->test_pattern.type != DP_TEST_PATTERN_VIDEO_MODE)
 				resource_build_test_pattern_params(&context->res_ctx, otg_master);
 		}
 	}
@@ -4934,8 +4934,8 @@ bool dc_dmub_is_ips_idle_state(struct dc *dc)
 	if (dc->hwss.get_idle_state)
 		idle_state = dc->hwss.get_idle_state(dc);
 
-	if ((idle_state & DMUB_IPS1_ALLOW_MASK) ||
-		(idle_state & DMUB_IPS2_ALLOW_MASK))
+	if (!(idle_state & DMUB_IPS1_ALLOW_MASK) ||
+		!(idle_state & DMUB_IPS2_ALLOW_MASK))
 		return true;
 
 	return false;
@@ -5095,18 +5095,28 @@ void dc_mclk_switch_using_fw_based_vblank_stretch_shut_down(struct dc *dc)
  */
 bool dc_is_dmub_outbox_supported(struct dc *dc)
 {
-	/* DCN31 B0 USB4 DPIA needs dmub notifications for interrupts */
-	if (dc->ctx->asic_id.chip_family == FAMILY_YELLOW_CARP &&
-	    dc->ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0 &&
-	    !dc->debug.dpia_debug.bits.disable_dpia)
-		return true;
+	switch (dc->ctx->asic_id.chip_family) {
 
-	if (dc->ctx->asic_id.chip_family == AMDGPU_FAMILY_GC_11_0_1 &&
-	    !dc->debug.dpia_debug.bits.disable_dpia)
-		return true;
+	case FAMILY_YELLOW_CARP:
+		/* DCN31 B0 USB4 DPIA needs dmub notifications for interrupts */
+		if (dc->ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0 &&
+		    !dc->debug.dpia_debug.bits.disable_dpia)
+			return true;
+	break;
+
+	case AMDGPU_FAMILY_GC_11_0_1:
+	case AMDGPU_FAMILY_GC_11_5_0:
+		if (!dc->debug.dpia_debug.bits.disable_dpia)
+			return true;
+	break;
+
+	default:
+		break;
+	}
 
 	/* dmub aux needs dmub notifications to be enabled */
 	return dc->debug.enable_dmub_aux_for_legacy_ddc;
+
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 1d48278cba96..a1f1d1003992 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -5190,6 +5190,9 @@ bool dc_resource_acquire_secondary_pipe_for_mpc_odm_legacy(
 	sec_next = sec_pipe->next_odm_pipe;
 	sec_prev = sec_pipe->prev_odm_pipe;
 
+	if (pri_pipe == NULL)
+		return false;
+
 	*sec_pipe = *pri_pipe;
 
 	sec_pipe->top_pipe = sec_top;
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 9316b737a8ba..2cafd644baff 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -874,6 +874,7 @@ struct dc_debug_options {
 	unsigned int seamless_boot_odm_combine;
 	unsigned int force_odm_combine_4to1; //bit vector based on otg inst
 	int minimum_z8_residency_time;
+	int minimum_z10_residency_time;
 	bool disable_z9_mpc;
 	unsigned int force_fclk_khz;
 	bool enable_tri_buf;
@@ -1608,7 +1609,6 @@ struct dc_link {
 	enum edp_revision edp_revision;
 	union dpcd_sink_ext_caps dpcd_sink_ext_caps;
 
-	struct backlight_settings backlight_settings;
 	struct psr_settings psr_settings;
 
 	struct replay_settings replay_settings;
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
index e4c007203318..0e07699c1e83 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
@@ -1202,11 +1202,11 @@ void dc_dmub_srv_exit_low_power_state(const struct dc *dc)
 		allow_state = dc->hwss.get_idle_state(dc);
 		dc->hwss.set_idle_state(dc, false);
 
-		if (allow_state & DMUB_IPS2_ALLOW_MASK) {
+		if (!(allow_state & DMUB_IPS2_ALLOW_MASK)) {
 			// Wait for evaluation time
 			udelay(dc->debug.ips2_eval_delay_us);
 			commit_state = dc->hwss.get_idle_state(dc);
-			if (commit_state & DMUB_IPS2_COMMIT_MASK) {
+			if (!(commit_state & DMUB_IPS2_COMMIT_MASK)) {
 				// Tell PMFW to exit low power state
 				dc->clk_mgr->funcs->exit_low_power_state(dc->clk_mgr);
 
@@ -1216,7 +1216,7 @@ void dc_dmub_srv_exit_low_power_state(const struct dc *dc)
 
 				for (i = 0; i < max_num_polls; ++i) {
 					commit_state = dc->hwss.get_idle_state(dc);
-					if (!(commit_state & DMUB_IPS2_COMMIT_MASK))
+					if (commit_state & DMUB_IPS2_COMMIT_MASK)
 						break;
 
 					udelay(1);
@@ -1235,10 +1235,10 @@ void dc_dmub_srv_exit_low_power_state(const struct dc *dc)
 		}
 
 		dc_dmub_srv_notify_idle(dc, false);
-		if (allow_state & DMUB_IPS1_ALLOW_MASK) {
+		if (!(allow_state & DMUB_IPS1_ALLOW_MASK)) {
 			for (i = 0; i < max_num_polls; ++i) {
 				commit_state = dc->hwss.get_idle_state(dc);
-				if (!(commit_state & DMUB_IPS1_COMMIT_MASK))
+				if (commit_state & DMUB_IPS1_COMMIT_MASK)
 					break;
 
 				udelay(1);
diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
index 9649934ea186..e2a3aa8812df 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
@@ -465,6 +465,7 @@ struct dc_cursor_mi_param {
 	struct fixed31_32 v_scale_ratio;
 	enum dc_rotation_angle rotation;
 	bool mirror;
+	struct dc_stream_state *stream;
 };
 
 /* IPP related types */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index cea666ea66c6..35d146217aef 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -177,6 +177,7 @@ struct dc_panel_patch {
 	unsigned int disable_fams;
 	unsigned int skip_avmute;
 	unsigned int mst_start_top_delay;
+	unsigned int remove_sink_ext_caps;
 };
 
 struct dc_edid_caps {
@@ -990,10 +991,6 @@ struct link_mst_stream_allocation_table {
 	struct link_mst_stream_allocation stream_allocations[MAX_CONTROLLER_NUM];
 };
 
-struct backlight_settings {
-	uint32_t backlight_millinits;
-};
-
 /* PSR feature flags */
 struct psr_settings {
 	bool psr_feature_enabled;		// PSR is supported by sink
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
index 139cf31d2e45..89c3bf0fe0c9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
@@ -1077,8 +1077,16 @@ void hubp2_cursor_set_position(
 	if (src_y_offset < 0)
 		src_y_offset = 0;
 	/* Save necessary cursor info x, y position. w, h is saved in attribute func. */
-	hubp->cur_rect.x = src_x_offset + param->viewport.x;
-	hubp->cur_rect.y = src_y_offset + param->viewport.y;
+	if (param->stream->link->psr_settings.psr_version >= DC_PSR_VERSION_SU_1 &&
+	    param->rotation != ROTATION_ANGLE_0) {
+		hubp->cur_rect.x = 0;
+		hubp->cur_rect.y = 0;
+		hubp->cur_rect.w = param->stream->timing.h_addressable;
+		hubp->cur_rect.h = param->stream->timing.v_addressable;
+	} else {
+		hubp->cur_rect.x = src_x_offset + param->viewport.x;
+		hubp->cur_rect.y = src_y_offset + param->viewport.y;
+	}
 }
 
 void hubp2_clk_cntl(struct hubp *hubp, bool enable)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
index 677361d74a4e..c97391edb5ff 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
@@ -871,7 +871,7 @@ static const struct dc_plane_cap plane_cap = {
 static const struct dc_debug_options debug_defaults_drv = {
 	.disable_z10 = false,
 	.enable_z9_disable_interface = true,
-	.minimum_z8_residency_time = 2000,
+	.minimum_z8_residency_time = 2100,
 	.psr_skip_crtc_disable = true,
 	.replay_skip_crtc_disabled = true,
 	.disable_dmcu = true,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_stream_encoder.c
index 001f9eb66920..62a8f0b56006 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_stream_encoder.c
@@ -261,12 +261,6 @@ static void enc35_stream_encoder_enable(
 			/* invalid mode ! */
 			ASSERT_CRITICAL(false);
 		}
-
-		REG_UPDATE(DIG_FE_CLK_CNTL, DIG_FE_CLK_EN, 1);
-		REG_UPDATE(DIG_FE_EN_CNTL, DIG_FE_ENABLE, 1);
-	} else {
-		REG_UPDATE(DIG_FE_EN_CNTL, DIG_FE_ENABLE, 0);
-		REG_UPDATE(DIG_FE_CLK_CNTL, DIG_FE_CLK_EN, 0);
 	}
 }
 
@@ -436,6 +430,8 @@ static void enc35_disable_fifo(struct stream_encoder *enc)
 	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
 
 	REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_ENABLE, 0);
+	REG_UPDATE(DIG_FE_EN_CNTL, DIG_FE_ENABLE, 0);
+	REG_UPDATE(DIG_FE_CLK_CNTL, DIG_FE_CLK_EN, 0);
 }
 
 static void enc35_enable_fifo(struct stream_encoder *enc)
@@ -443,6 +439,8 @@ static void enc35_enable_fifo(struct stream_encoder *enc)
 	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
 
 	REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_READ_START_LEVEL, 0x7);
+	REG_UPDATE(DIG_FE_CLK_CNTL, DIG_FE_CLK_EN, 1);
+	REG_UPDATE(DIG_FE_EN_CNTL, DIG_FE_ENABLE, 1);
 
 	enc35_reset_fifo(enc, true);
 	enc35_reset_fifo(enc, false);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_pg_cntl.c b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_pg_cntl.c
index 46f71ff08fd1..d19db8e9b8a5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_pg_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_pg_cntl.c
@@ -261,6 +261,7 @@ void pg_cntl35_hpo_pg_control(struct pg_cntl *pg_cntl, bool power_on)
 	uint32_t power_gate = power_on ? 0 : 1;
 	uint32_t pwr_status = power_on ? 0 : 2;
 	uint32_t org_ip_request_cntl;
+	uint32_t power_forceon;
 	bool block_enabled;
 
 	if (pg_cntl->ctx->dc->debug.ignore_pg ||
@@ -277,6 +278,10 @@ void pg_cntl35_hpo_pg_control(struct pg_cntl *pg_cntl, bool power_on)
 			return;
 	}
 
+	REG_GET(DOMAIN25_PG_CONFIG, DOMAIN_POWER_FORCEON, &power_forceon);
+	if (power_forceon)
+		return;
+
 	REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl);
 	if (org_ip_request_cntl == 0)
 		REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1);
@@ -304,6 +309,7 @@ void pg_cntl35_io_clk_pg_control(struct pg_cntl *pg_cntl, bool power_on)
 	uint32_t power_gate = power_on ? 0 : 1;
 	uint32_t pwr_status = power_on ? 0 : 2;
 	uint32_t org_ip_request_cntl;
+	uint32_t power_forceon;
 	bool block_enabled;
 
 	if (pg_cntl->ctx->dc->debug.ignore_pg ||
@@ -319,6 +325,10 @@ void pg_cntl35_io_clk_pg_control(struct pg_cntl *pg_cntl, bool power_on)
 			return;
 	}
 
+	REG_GET(DOMAIN22_PG_CONFIG, DOMAIN_POWER_FORCEON, &power_forceon);
+	if (power_forceon)
+		return;
+
 	REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl);
 	if (org_ip_request_cntl == 0)
 		REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_resource.c
index c7e011d26d41..70ef1e7ff841 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_resource.c
@@ -1712,6 +1712,13 @@ static bool dcn35_validate_bandwidth(struct dc *dc,
 
 	out = dml2_validate(dc, context, fast_validate);
 
+	if (fast_validate)
+		return out;
+
+	DC_FP_START();
+	dcn35_decide_zstate_support(dc, context);
+	DC_FP_END();
+
 	return out;
 }
 
@@ -1857,7 +1864,7 @@ static bool dcn35_resource_construct(
 
 	/* Use pipe context based otg sync logic */
 	dc->config.use_pipe_ctx_sync_logic = true;
-	dc->config.use_default_clock_table = false;
+
 	/* read VBIOS LTTPR caps */
 	{
 		if (ctx->dc_bios->funcs->get_lttpr_caps) {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index ea7d60f9a9b4..6042a5a6a44f 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -61,8 +61,12 @@ endif
 endif
 
 ifneq ($(CONFIG_FRAME_WARN),0)
+ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y)
+frame_warn_flag := -Wframe-larger-than=3072
+else
 frame_warn_flag := -Wframe-larger-than=2048
 endif
+endif
 
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags)
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dc_features.h b/drivers/gpu/drm/amd/display/dc/dml/dc_features.h
index 2cbdd75429ff..6e669a2c5b2d 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dc_features.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dc_features.h
@@ -36,7 +36,7 @@
  * Define the maximum amount of states supported by the ASIC. Every ASIC has a
  * specific number of states; this macro defines the maximum number of states.
  */
-#define DC__VOLTAGE_STATES 20
+#define DC__VOLTAGE_STATES 40
 #define DC__NUM_DPP__4 1
 #define DC__NUM_DPP__0_PRESENT 1
 #define DC__NUM_DPP__1_PRESENT 1
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
index 7fc8b18096ba..d2271e308fa0 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
@@ -440,7 +440,115 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc = {
 	.use_urgent_burst_bw = 0
 };
 
-struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv12_soc = { 0 };
+struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv12_soc = {
+	.clock_limits = {
+		{
+			.state = 0,
+			.dcfclk_mhz = 560.0,
+			.fabricclk_mhz = 560.0,
+			.dispclk_mhz = 513.0,
+			.dppclk_mhz = 513.0,
+			.phyclk_mhz = 540.0,
+			.socclk_mhz = 560.0,
+			.dscclk_mhz = 171.0,
+			.dram_speed_mts = 1069.0,
+		},
+		{
+			.state = 1,
+			.dcfclk_mhz = 694.0,
+			.fabricclk_mhz = 694.0,
+			.dispclk_mhz = 642.0,
+			.dppclk_mhz = 642.0,
+			.phyclk_mhz = 600.0,
+			.socclk_mhz = 694.0,
+			.dscclk_mhz = 214.0,
+			.dram_speed_mts = 1324.0,
+		},
+		{
+			.state = 2,
+			.dcfclk_mhz = 875.0,
+			.fabricclk_mhz = 875.0,
+			.dispclk_mhz = 734.0,
+			.dppclk_mhz = 734.0,
+			.phyclk_mhz = 810.0,
+			.socclk_mhz = 875.0,
+			.dscclk_mhz = 245.0,
+			.dram_speed_mts = 1670.0,
+		},
+		{
+			.state = 3,
+			.dcfclk_mhz = 1000.0,
+			.fabricclk_mhz = 1000.0,
+			.dispclk_mhz = 1100.0,
+			.dppclk_mhz = 1100.0,
+			.phyclk_mhz = 810.0,
+			.socclk_mhz = 1000.0,
+			.dscclk_mhz = 367.0,
+			.dram_speed_mts = 2000.0,
+		},
+		{
+			.state = 4,
+			.dcfclk_mhz = 1200.0,
+			.fabricclk_mhz = 1200.0,
+			.dispclk_mhz = 1284.0,
+			.dppclk_mhz = 1284.0,
+			.phyclk_mhz = 810.0,
+			.socclk_mhz = 1200.0,
+			.dscclk_mhz = 428.0,
+			.dram_speed_mts = 2000.0,
+		},
+		{
+			.state = 5,
+			.dcfclk_mhz = 1200.0,
+			.fabricclk_mhz = 1200.0,
+			.dispclk_mhz = 1284.0,
+			.dppclk_mhz = 1284.0,
+			.phyclk_mhz = 810.0,
+			.socclk_mhz = 1200.0,
+			.dscclk_mhz = 428.0,
+			.dram_speed_mts = 2000.0,
+		},
+	},
+
+	.num_states = 5,
+	.sr_exit_time_us = 1.9,
+	.sr_enter_plus_exit_time_us = 4.4,
+	.urgent_latency_us = 3.0,
+	.urgent_latency_pixel_data_only_us = 4.0,
+	.urgent_latency_pixel_mixed_with_vm_data_us = 4.0,
+	.urgent_latency_vm_data_only_us = 4.0,
+	.urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096,
+	.urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096,
+	.urgent_out_of_order_return_per_channel_vm_only_bytes = 4096,
+	.pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 40.0,
+	.pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 40.0,
+	.pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0,
+	.max_avg_sdp_bw_use_normal_percent = 40.0,
+	.max_avg_dram_bw_use_normal_percent = 40.0,
+	.writeback_latency_us = 12.0,
+	.ideal_dram_bw_after_urgent_percent = 40.0,
+	.max_request_size_bytes = 256,
+	.dram_channel_width_bytes = 16,
+	.fabric_datapath_to_dcn_data_return_bytes = 64,
+	.dcn_downspread_percent = 0.5,
+	.downspread_percent = 0.5,
+	.dram_page_open_time_ns = 50.0,
+	.dram_rw_turnaround_time_ns = 17.5,
+	.dram_return_buffer_per_channel_bytes = 8192,
+	.round_trip_ping_latency_dcfclk_cycles = 131,
+	.urgent_out_of_order_return_per_channel_bytes = 4096,
+	.channel_interleave_bytes = 256,
+	.num_banks = 8,
+	.num_chans = 16,
+	.vmm_page_size_bytes = 4096,
+	.dram_clock_change_latency_us = 45.0,
+	.writeback_dram_clock_change_latency_us = 23.0,
+	.return_bus_width_bytes = 64,
+	.dispclk_dppclk_vco_speed_mhz = 3850,
+	.xfc_bus_transport_time_us = 20,
+	.xfc_xbuf_latency_tolerance_us = 50,
+	.use_urgent_burst_bw = 0,
+};
 
 struct _vcs_dpi_ip_params_st dcn2_1_ip = {
 	.odm_capable = 1,
@@ -950,10 +1058,8 @@ static enum dcn_zstate_support_state  decide_zstate_support(struct dc *dc, struc
 {
 	int plane_count;
 	int i;
-	unsigned int min_dst_y_next_start_us;
 
 	plane_count = 0;
-	min_dst_y_next_start_us = 0;
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		if (context->res_ctx.pipe_ctx[i].plane_state)
 			plane_count++;
@@ -975,26 +1081,15 @@ static enum dcn_zstate_support_state  decide_zstate_support(struct dc *dc, struc
 	else if (context->stream_count == 1 &&  context->streams[0]->signal == SIGNAL_TYPE_EDP) {
 		struct dc_link *link = context->streams[0]->sink->link;
 		struct dc_stream_status *stream_status = &context->stream_status[0];
-		struct dc_stream_state *current_stream = context->streams[0];
 		int minmum_z8_residency = dc->debug.minimum_z8_residency_time > 0 ? dc->debug.minimum_z8_residency_time : 1000;
 		bool allow_z8 = context->bw_ctx.dml.vba.StutterPeriod > (double)minmum_z8_residency;
 		bool is_pwrseq0 = link->link_index == 0;
-		bool isFreesyncVideo;
-
-		isFreesyncVideo = current_stream->adjust.v_total_min == current_stream->adjust.v_total_max;
-		isFreesyncVideo = isFreesyncVideo && current_stream->timing.v_total < current_stream->adjust.v_total_min;
-		for (i = 0; i < dc->res_pool->pipe_count; i++) {
-			if (context->res_ctx.pipe_ctx[i].stream == current_stream && isFreesyncVideo) {
-				min_dst_y_next_start_us = context->res_ctx.pipe_ctx[i].dlg_regs.min_dst_y_next_start_us;
-				break;
-			}
-		}
 
 		/* Don't support multi-plane configurations */
 		if (stream_status->plane_count > 1)
 			return DCN_ZSTATE_SUPPORT_DISALLOW;
 
-		if (is_pwrseq0 && (context->bw_ctx.dml.vba.StutterPeriod > 5000.0 || min_dst_y_next_start_us > 5000))
+		if (is_pwrseq0 && context->bw_ctx.dml.vba.StutterPeriod > 5000.0)
 			return DCN_ZSTATE_SUPPORT_ALLOW;
 		else if (is_pwrseq0 && link->psr_settings.psr_version == DC_PSR_VERSION_1 && !link->panel_config.psr.disable_psr)
 			return allow_z8 ? DCN_ZSTATE_SUPPORT_ALLOW_Z8_Z10_ONLY : DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index 9ec4172d1c2d..b46cde525066 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -1192,13 +1192,16 @@ static bool update_pipe_slice_table_with_split_flags(
 	 */
 	struct pipe_ctx *pipe;
 	bool odm;
-	int i;
+	int dc_pipe_idx, dml_pipe_idx = 0;
 	bool updated = false;
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		pipe = &context->res_ctx.pipe_ctx[i];
+	for (dc_pipe_idx = 0;
+			dc_pipe_idx < dc->res_pool->pipe_count; dc_pipe_idx++) {
+		pipe = &context->res_ctx.pipe_ctx[dc_pipe_idx];
+		if (resource_is_pipe_type(pipe, FREE_PIPE))
+			continue;
 
-		if (merge[i]) {
+		if (merge[dc_pipe_idx]) {
 			if (resource_is_pipe_type(pipe, OPP_HEAD))
 				/* merging OPP head means reducing ODM slice
 				 * count by 1
@@ -1213,17 +1216,18 @@ static bool update_pipe_slice_table_with_split_flags(
 			updated = true;
 		}
 
-		if (split[i]) {
-			odm = vba->ODMCombineEnabled[vba->pipe_plane[i]] !=
+		if (split[dc_pipe_idx]) {
+			odm = vba->ODMCombineEnabled[vba->pipe_plane[dml_pipe_idx]] !=
 					dm_odm_combine_mode_disabled;
 			if (odm && resource_is_pipe_type(pipe, OPP_HEAD))
 				update_slice_table_for_stream(
-						table, pipe->stream, split[i] - 1);
+						table, pipe->stream, split[dc_pipe_idx] - 1);
 			else if (!odm && resource_is_pipe_type(pipe, DPP_PIPE))
 				update_slice_table_for_plane(table, pipe,
-						pipe->plane_state, split[i] - 1);
+						pipe->plane_state, split[dc_pipe_idx] - 1);
 			updated = true;
 		}
+		dml_pipe_idx++;
 	}
 	return updated;
 }
@@ -2231,6 +2235,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context,
 	int i, pipe_idx, vlevel_temp = 0;
 	double dcfclk = dcn3_2_soc.clock_limits[0].dcfclk_mhz;
 	double dcfclk_from_validation = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb];
+	double dram_speed_from_validation = context->bw_ctx.dml.vba.DRAMSpeed;
 	double dcfclk_from_fw_based_mclk_switching = dcfclk_from_validation;
 	bool pstate_en = context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] !=
 			dm_dram_clock_change_unsupported;
@@ -2418,7 +2423,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context,
 	}
 
 	if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].valid) {
-		min_dram_speed_mts = context->bw_ctx.dml.vba.DRAMSpeed;
+		min_dram_speed_mts = dram_speed_from_validation;
 		min_dram_speed_mts_margin = 160;
 
 		context->bw_ctx.dml.soc.dram_clock_change_latency_us =
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
index a5fe523668e9..f154a3eb1d1a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
@@ -124,7 +124,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
 			.phyclk_mhz = 600.0,
 			.phyclk_d18_mhz = 667.0,
 			.dscclk_mhz = 186.0,
-			.dtbclk_mhz = 625.0,
+			.dtbclk_mhz = 600.0,
 		},
 		{
 			.state = 1,
@@ -133,7 +133,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
 			.phyclk_mhz = 810.0,
 			.phyclk_d18_mhz = 667.0,
 			.dscclk_mhz = 209.0,
-			.dtbclk_mhz = 625.0,
+			.dtbclk_mhz = 600.0,
 		},
 		{
 			.state = 2,
@@ -142,7 +142,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
 			.phyclk_mhz = 810.0,
 			.phyclk_d18_mhz = 667.0,
 			.dscclk_mhz = 209.0,
-			.dtbclk_mhz = 625.0,
+			.dtbclk_mhz = 600.0,
 		},
 		{
 			.state = 3,
@@ -151,7 +151,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
 			.phyclk_mhz = 810.0,
 			.phyclk_d18_mhz = 667.0,
 			.dscclk_mhz = 371.0,
-			.dtbclk_mhz = 625.0,
+			.dtbclk_mhz = 600.0,
 		},
 		{
 			.state = 4,
@@ -160,14 +160,14 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
 			.phyclk_mhz = 810.0,
 			.phyclk_d18_mhz = 667.0,
 			.dscclk_mhz = 417.0,
-			.dtbclk_mhz = 625.0,
+			.dtbclk_mhz = 600.0,
 		},
 	},
 	.num_states = 5,
-	.sr_exit_time_us = 9.0,
-	.sr_enter_plus_exit_time_us = 11.0,
-	.sr_exit_z8_time_us = 50.0, /*changed from 442.0*/
-	.sr_enter_plus_exit_z8_time_us = 50.0,/*changed from 560.0*/
+	.sr_exit_time_us = 14.0,
+	.sr_enter_plus_exit_time_us = 16.0,
+	.sr_exit_z8_time_us = 525.0,
+	.sr_enter_plus_exit_z8_time_us = 715.0,
 	.fclk_change_latency_us = 20.0,
 	.usr_retraining_latency_us = 2,
 	.writeback_latency_us = 12.0,
@@ -329,6 +329,52 @@ void dcn35_update_bw_bounding_box_fpu(struct dc *dc,
 	/*temp till dml2 fully work without dml1*/
 	dml_init_instance(&dc->dml, &dcn3_5_soc, &dcn3_5_ip,
 				DML_PROJECT_DCN31);
+
+	/*copy to dml2, before dml2_create*/
+	if (clk_table->num_entries > 2) {
+
+		for (i = 0; i < clk_table->num_entries; i++) {
+			dc->dml2_options.bbox_overrides.clks_table.num_states =
+				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].dcfclk_mhz =
+				clock_limits[i].dcfclk_mhz;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].fclk_mhz =
+				clock_limits[i].fabricclk_mhz;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].dispclk_mhz =
+				clock_limits[i].dispclk_mhz;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].dppclk_mhz =
+				clock_limits[i].dppclk_mhz;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].socclk_mhz =
+				clock_limits[i].socclk_mhz;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].memclk_mhz =
+				clk_table->entries[i].memclk_mhz * clk_table->entries[i].wck_ratio;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz =
+				clock_limits[i].dtbclk_mhz;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dcfclk_levels =
+				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_fclk_levels =
+				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dispclk_levels =
+				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dppclk_levels =
+				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_socclk_levels =
+				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_memclk_levels =
+				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dtbclk_levels =
+				clk_table->num_entries;
+		}
+	}
+
+	/* Update latency values */
+	dc->dml2_options.bbox_overrides.dram_clock_change_latency_us = dcn3_5_soc.dram_clock_change_latency_us;
+
+	dc->dml2_options.bbox_overrides.sr_exit_latency_us = dcn3_5_soc.sr_exit_time_us;
+	dc->dml2_options.bbox_overrides.sr_enter_plus_exit_latency_us = dcn3_5_soc.sr_enter_plus_exit_time_us;
+
+	dc->dml2_options.bbox_overrides.sr_exit_z8_time_us = dcn3_5_soc.sr_exit_z8_time_us;
+	dc->dml2_options.bbox_overrides.sr_enter_plus_exit_z8_time_us = dcn3_5_soc.sr_enter_plus_exit_z8_time_us;
 }
 
 static bool is_dual_plane(enum surface_pixel_format format)
@@ -507,3 +553,37 @@ int dcn35_populate_dml_pipes_from_context_fpu(struct dc *dc,
 
 	return pipe_cnt;
 }
+
+void dcn35_decide_zstate_support(struct dc *dc, struct dc_state *context)
+{
+	enum dcn_zstate_support_state support = DCN_ZSTATE_SUPPORT_DISALLOW;
+	unsigned int i, plane_count = 0;
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		if (context->res_ctx.pipe_ctx[i].plane_state)
+			plane_count++;
+	}
+
+	if (plane_count == 0) {
+		support = DCN_ZSTATE_SUPPORT_ALLOW;
+	} else if (plane_count == 1 && context->stream_count == 1 && context->streams[0]->signal == SIGNAL_TYPE_EDP) {
+		struct dc_link *link = context->streams[0]->sink->link;
+		bool is_pwrseq0 = link && link->link_index == 0;
+		bool is_psr1 = link && link->psr_settings.psr_version == DC_PSR_VERSION_1 && !link->panel_config.psr.disable_psr;
+		int minmum_z8_residency =
+			dc->debug.minimum_z8_residency_time > 0 ? dc->debug.minimum_z8_residency_time : 1000;
+		bool allow_z8 = context->bw_ctx.dml.vba.StutterPeriod > (double)minmum_z8_residency;
+		int minmum_z10_residency =
+			dc->debug.minimum_z10_residency_time > 0 ? dc->debug.minimum_z10_residency_time : 5000;
+		bool allow_z10 = context->bw_ctx.dml.vba.StutterPeriod > (double)minmum_z10_residency;
+
+		if (is_pwrseq0 && allow_z10)
+			support = DCN_ZSTATE_SUPPORT_ALLOW;
+		else if (is_pwrseq0 && is_psr1)
+			support = allow_z8 ? DCN_ZSTATE_SUPPORT_ALLOW_Z8_Z10_ONLY : DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY;
+		else if (allow_z8)
+			support = DCN_ZSTATE_SUPPORT_ALLOW_Z8_ONLY;
+	}
+
+	context->bw_ctx.bw.dcn.clk.zstate_support = support;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.h
index e8d5a170893e..067480fc3691 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.h
@@ -39,4 +39,6 @@ int dcn35_populate_dml_pipes_from_context_fpu(struct dc *dc,
 					      display_e2e_pipe_params_st *pipes,
 					      bool fast_validate);
 
+void dcn35_decide_zstate_support(struct dc *dc, struct dc_state *context);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
index 510be909cd75..b95bf27f2fe2 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
@@ -5420,7 +5420,7 @@ static void CalculateOutputLink(
 					*OutBpp = TruncToValidBPP((1 - Downspreading / 100) * 13500, OutputLinkDPLanes, HTotal, HActive, PixelClockBackEnd, ForcedOutputLinkBPP, LinkDSCEnable, Output,
 												OutputFormat, DSCInputBitPerComponent, NumberOfDSCSlices, (dml_uint_t)AudioSampleRate, AudioSampleLayout, ODMModeNoDSC, ODMModeDSC, RequiredSlots);
 
-					if (OutBpp == 0 && PHYCLKD32PerState < 20000 / 32 && DSCEnable == dml_dsc_enable_if_necessary && ForcedOutputLinkBPP == 0) {
+					if (*OutBpp == 0 && PHYCLKD32PerState < 20000 / 32 && DSCEnable == dml_dsc_enable_if_necessary && ForcedOutputLinkBPP == 0) {
 						*RequiresDSC = true;
 						LinkDSCEnable = true;
 						*OutBpp = TruncToValidBPP((1 - Downspreading / 100) * 13500, OutputLinkDPLanes, HTotal, HActive, PixelClockBackEnd, ForcedOutputLinkBPP, LinkDSCEnable, Output,
@@ -9447,12 +9447,12 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
 
 		// Output
 		CalculateWatermarks_params->Watermark = &s->dummy_watermark; // Watermarks *Watermark
-		CalculateWatermarks_params->DRAMClockChangeSupport = &mode_lib->ms.support.DRAMClockChangeSupport[j];
+		CalculateWatermarks_params->DRAMClockChangeSupport = &mode_lib->ms.support.DRAMClockChangeSupport[0];
 		CalculateWatermarks_params->MaxActiveDRAMClockChangeLatencySupported = &s->dummy_single_array[0][0]; // dml_float_t *MaxActiveDRAMClockChangeLatencySupported[]
 		CalculateWatermarks_params->SubViewportLinesNeededInMALL = &mode_lib->ms.SubViewportLinesNeededInMALL[j]; // dml_uint_t SubViewportLinesNeededInMALL[]
-		CalculateWatermarks_params->FCLKChangeSupport = &mode_lib->ms.support.FCLKChangeSupport[j];
+		CalculateWatermarks_params->FCLKChangeSupport = &mode_lib->ms.support.FCLKChangeSupport[0];
 		CalculateWatermarks_params->MaxActiveFCLKChangeLatencySupported = &s->dummy_single[0]; // dml_float_t *MaxActiveFCLKChangeLatencySupported
-		CalculateWatermarks_params->USRRetrainingSupport = &mode_lib->ms.support.USRRetrainingSupport[j];
+		CalculateWatermarks_params->USRRetrainingSupport = &mode_lib->ms.support.USRRetrainingSupport[0];
 
 		CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
 			&mode_lib->scratch,
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
index 75171bee6f71..db06a5b749b4 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
@@ -341,25 +341,42 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc,
 		break;
 	}
 
-	/* Override from passed values, mainly for debugging purposes, if available */
-	if (dml2->config.bbox_overrides.sr_exit_latency_us) {
-		p->in_states->state_array[0].sr_exit_time_us = dml2->config.bbox_overrides.sr_exit_latency_us;
-	}
+	/* Override from passed values, if available */
+	for (i = 0; i < p->in_states->num_states; i++) {
+		if (dml2->config.bbox_overrides.sr_exit_latency_us) {
+			p->in_states->state_array[i].sr_exit_time_us =
+				dml2->config.bbox_overrides.sr_exit_latency_us;
+		}
 
-	if (dml2->config.bbox_overrides.sr_enter_plus_exit_latency_us) {
-		p->in_states->state_array[0].sr_enter_plus_exit_time_us = dml2->config.bbox_overrides.sr_enter_plus_exit_latency_us;
-	}
+		if (dml2->config.bbox_overrides.sr_enter_plus_exit_latency_us) {
+			p->in_states->state_array[i].sr_enter_plus_exit_time_us =
+				dml2->config.bbox_overrides.sr_enter_plus_exit_latency_us;
+		}
 
-	if (dml2->config.bbox_overrides.urgent_latency_us) {
-		p->in_states->state_array[0].urgent_latency_pixel_data_only_us = dml2->config.bbox_overrides.urgent_latency_us;
-	}
+		if (dml2->config.bbox_overrides.sr_exit_z8_time_us) {
+			p->in_states->state_array[i].sr_exit_z8_time_us =
+				dml2->config.bbox_overrides.sr_exit_z8_time_us;
+		}
 
-	if (dml2->config.bbox_overrides.dram_clock_change_latency_us) {
-		p->in_states->state_array[0].dram_clock_change_latency_us = dml2->config.bbox_overrides.dram_clock_change_latency_us;
-	}
+		if (dml2->config.bbox_overrides.sr_enter_plus_exit_z8_time_us) {
+			p->in_states->state_array[i].sr_enter_plus_exit_z8_time_us =
+				dml2->config.bbox_overrides.sr_enter_plus_exit_z8_time_us;
+		}
+
+		if (dml2->config.bbox_overrides.urgent_latency_us) {
+			p->in_states->state_array[i].urgent_latency_pixel_data_only_us =
+				dml2->config.bbox_overrides.urgent_latency_us;
+		}
 
-	if (dml2->config.bbox_overrides.fclk_change_latency_us) {
-		p->in_states->state_array[0].fclk_change_latency_us = dml2->config.bbox_overrides.fclk_change_latency_us;
+		if (dml2->config.bbox_overrides.dram_clock_change_latency_us) {
+			p->in_states->state_array[i].dram_clock_change_latency_us =
+				dml2->config.bbox_overrides.dram_clock_change_latency_us;
+		}
+
+		if (dml2->config.bbox_overrides.fclk_change_latency_us) {
+			p->in_states->state_array[i].fclk_change_latency_us =
+				dml2->config.bbox_overrides.fclk_change_latency_us;
+		}
 	}
 
 	/* DCFCLK stas values are project specific */
@@ -406,8 +423,9 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc,
 		}
 
 		for (i = 0; i < dml2->config.bbox_overrides.clks_table.num_entries_per_clk.num_dtbclk_levels; i++) {
-			p->in_states->state_array[i].dtbclk_mhz =
-				dml2->config.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz;
+			if (dml2->config.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz > 0)
+				p->in_states->state_array[i].dtbclk_mhz =
+					dml2->config.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz;
 		}
 
 		for (i = 0; i < dml2->config.bbox_overrides.clks_table.num_entries_per_clk.num_dispclk_levels; i++) {
@@ -498,8 +516,8 @@ void dml2_translate_socbb_params(const struct dc *in, struct soc_bounding_box_st
 	out->do_urgent_latency_adjustment = in_soc_params->do_urgent_latency_adjustment;
 	out->dram_channel_width_bytes = (dml_uint_t)in_soc_params->dram_channel_width_bytes;
 	out->fabric_datapath_to_dcn_data_return_bytes = (dml_uint_t)in_soc_params->fabric_datapath_to_dcn_data_return_bytes;
-	out->gpuvm_min_page_size_kbytes = in_soc_params->gpuvm_min_page_size_bytes * 1024;
-	out->hostvm_min_page_size_kbytes = in_soc_params->hostvm_min_page_size_bytes * 1024;
+	out->gpuvm_min_page_size_kbytes = in_soc_params->gpuvm_min_page_size_bytes / 1024;
+	out->hostvm_min_page_size_kbytes = in_soc_params->hostvm_min_page_size_bytes / 1024;
 	out->mall_allocated_for_dcn_mbytes = (dml_uint_t)in_soc_params->mall_allocated_for_dcn_mbytes;
 	out->max_avg_dram_bw_use_normal_percent = in_soc_params->max_avg_dram_bw_use_normal_percent;
 	out->max_avg_fabric_bw_use_normal_percent = in_soc_params->max_avg_fabric_bw_use_normal_percent;
@@ -1040,9 +1058,12 @@ void map_dc_state_into_dml_display_cfg(struct dml2_context *dml2, struct dc_stat
 	}
 
 	//Generally these are set by referencing our latest BB/IP params in dcn32_resource.c file
-	dml_dispcfg->plane.GPUVMEnable = true;
-	dml_dispcfg->plane.GPUVMMaxPageTableLevels = 4;
-	dml_dispcfg->plane.HostVMEnable = false;
+	dml_dispcfg->plane.GPUVMEnable = dml2->v20.dml_core_ctx.ip.gpuvm_enable;
+	dml_dispcfg->plane.GPUVMMaxPageTableLevels = dml2->v20.dml_core_ctx.ip.gpuvm_max_page_table_levels;
+	dml_dispcfg->plane.HostVMEnable = dml2->v20.dml_core_ctx.ip.hostvm_enable;
+	dml_dispcfg->plane.HostVMMaxPageTableLevels = dml2->v20.dml_core_ctx.ip.hostvm_max_page_table_levels;
+	if (dml2->v20.dml_core_ctx.ip.hostvm_enable)
+		dml2->v20.dml_core_ctx.policy.AllowForPStateChangeOrStutterInVBlankFinal = dml_prefetch_support_uclk_fclk_and_stutter;
 
 	dml2_populate_pipe_to_plane_index_mapping(dml2, context);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h
index 317f90776d97..fe15baa4bf09 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h
@@ -139,6 +139,8 @@ struct dml2_soc_bbox_overrides {
 	double urgent_latency_us;
 	double sr_exit_latency_us;
 	double sr_enter_plus_exit_latency_us;
+	double sr_exit_z8_time_us;
+	double sr_enter_plus_exit_z8_time_us;
 	double dram_clock_change_latency_us;
 	double fclk_change_latency_us;
 	unsigned int dram_num_chan;
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
index 2b8b8366538e..cdb903116eb7 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
@@ -3417,7 +3417,8 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 		.h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz,
 		.v_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.vert,
 		.rotation = pipe_ctx->plane_state->rotation,
-		.mirror = pipe_ctx->plane_state->horizontal_mirror
+		.mirror = pipe_ctx->plane_state->horizontal_mirror,
+		.stream = pipe_ctx->stream,
 	};
 	bool pipe_split_on = false;
 	bool odm_combine_on = (pipe_ctx->next_odm_pipe != NULL) ||
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
index 6a65af8c36b9..c1a9b746c43f 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
@@ -487,8 +487,7 @@ bool dcn32_set_mcm_luts(
 		if (plane_state->blend_tf->type == TF_TYPE_HWPWL)
 			lut_params = &plane_state->blend_tf->pwl;
 		else if (plane_state->blend_tf->type == TF_TYPE_DISTRIBUTED_POINTS) {
-			cm_helper_translate_curve_to_hw_format(plane_state->ctx,
-					plane_state->blend_tf,
+			cm3_helper_translate_curve_to_hw_format(plane_state->blend_tf,
 					&dpp_base->regamma_params, false);
 			lut_params = &dpp_base->regamma_params;
 		}
@@ -503,8 +502,7 @@ bool dcn32_set_mcm_luts(
 		else if (plane_state->in_shaper_func->type == TF_TYPE_DISTRIBUTED_POINTS) {
 			// TODO: dpp_base replace
 			ASSERT(false);
-			cm_helper_translate_curve_to_hw_format(plane_state->ctx,
-					plane_state->in_shaper_func,
+			cm3_helper_translate_curve_to_hw_format(plane_state->in_shaper_func,
 					&dpp_base->shaper_params, true);
 			lut_params = &dpp_base->shaper_params;
 		}
@@ -962,6 +960,12 @@ void dcn32_init_hw(struct dc *dc)
 		dc->caps.dmub_caps.subvp_psr = dc->ctx->dmub_srv->dmub->feature_caps.subvp_psr_support;
 		dc->caps.dmub_caps.gecc_enable = dc->ctx->dmub_srv->dmub->feature_caps.gecc_enable;
 		dc->caps.dmub_caps.mclk_sw = dc->ctx->dmub_srv->dmub->feature_caps.fw_assisted_mclk_switch;
+
+		if (dc->ctx->dmub_srv->dmub->fw_version <
+		    DMUB_FW_VERSION(7, 0, 35)) {
+			dc->debug.force_disable_subvp = true;
+			dc->debug.disable_fpo_optimizations = true;
+		}
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c
index d6f0f857c05a..24153b0df503 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c
@@ -879,7 +879,7 @@ static bool detect_link_and_local_sink(struct dc_link *link,
 			(link->dpcd_sink_ext_caps.bits.oled == 1)) {
 			dpcd_set_source_specific_data(link);
 			msleep(post_oui_delay);
-			set_cached_brightness_aux(link);
+			set_default_brightness_aux(link);
 		}
 
 		return true;
@@ -1088,6 +1088,9 @@ static bool detect_link_and_local_sink(struct dc_link *link,
 		if (sink->edid_caps.panel_patch.skip_scdc_overwrite)
 			link->ctx->dc->debug.hdmi20_disable = true;
 
+		if (sink->edid_caps.panel_patch.remove_sink_ext_caps)
+			link->dpcd_sink_ext_caps.raw = 0;
+
 		if (dc_is_hdmi_signal(link->connector_signal))
 			read_scdc_caps(link->ddc, link->local_sink);
 
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
index 34a4a8c0e18c..f8e01ca09d96 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
@@ -2142,8 +2142,7 @@ static enum dc_status enable_link_dp(struct dc_state *state,
 	if (link->dpcd_sink_ext_caps.bits.oled == 1 ||
 		link->dpcd_sink_ext_caps.bits.sdr_aux_backlight_control == 1 ||
 		link->dpcd_sink_ext_caps.bits.hdr_aux_backlight_control == 1) {
-		set_cached_brightness_aux(link);
-
+		set_default_brightness_aux(link);
 		if (link->dpcd_sink_ext_caps.bits.oled == 1)
 			msleep(bl_oled_enable_delay);
 		edp_backlight_enable_aux(link, true);
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c
index fd8f6f198146..68096d12f52f 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c
@@ -115,7 +115,7 @@ static enum link_training_result perform_fixed_vs_pe_nontransparent_training_seq
 		lt_settings->cr_pattern_time = 16000;
 
 	/* Fixed VS/PE specific: Toggle link rate */
-	apply_toggle_rate_wa = (link->vendor_specific_lttpr_link_rate_wa == target_rate);
+	apply_toggle_rate_wa = ((link->vendor_specific_lttpr_link_rate_wa == target_rate) || (link->vendor_specific_lttpr_link_rate_wa == 0));
 	target_rate = get_dpcd_link_rate(&lt_settings->link_settings);
 	toggle_rate = (target_rate == 0x6) ? 0xA : 0x6;
 
@@ -271,7 +271,7 @@ enum link_training_result dp_perform_fixed_vs_pe_training_sequence_legacy(
 	/* Vendor specific: Toggle link rate */
 	toggle_rate = (rate == 0x6) ? 0xA : 0x6;
 
-	if (link->vendor_specific_lttpr_link_rate_wa == rate) {
+	if (link->vendor_specific_lttpr_link_rate_wa == rate || link->vendor_specific_lttpr_link_rate_wa == 0) {
 		core_link_write_dpcd(
 				link,
 				DP_LINK_BW_SET,
@@ -617,7 +617,7 @@ enum link_training_result dp_perform_fixed_vs_pe_training_sequence(
 	/* Vendor specific: Toggle link rate */
 	toggle_rate = (rate == 0x6) ? 0xA : 0x6;
 
-	if (link->vendor_specific_lttpr_link_rate_wa == rate) {
+	if (link->vendor_specific_lttpr_link_rate_wa == rate || link->vendor_specific_lttpr_link_rate_wa == 0) {
 		core_link_write_dpcd(
 				link,
 				DP_LINK_BW_SET,
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
index e32a7974a4bc..e5cfaaef70b3 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
@@ -170,7 +170,6 @@ bool edp_set_backlight_level_nits(struct dc_link *link,
 	*(uint32_t *)&dpcd_backlight_set.backlight_level_millinits = backlight_millinits;
 	*(uint16_t *)&dpcd_backlight_set.backlight_transition_time_ms = (uint16_t)transition_time_in_ms;
 
-	link->backlight_settings.backlight_millinits = backlight_millinits;
 
 	if (!link->dpcd_caps.panel_luminance_control) {
 		if (core_link_write_dpcd(link, DP_SOURCE_BACKLIGHT_LEVEL,
@@ -290,7 +289,7 @@ bool set_default_brightness_aux(struct dc_link *link)
 			default_backlight = 150000;
 		// if < 1 nits or > 5000, it might be wrong readback
 		if (default_backlight < 1000 || default_backlight > 5000000)
-			default_backlight = 150000; //
+			default_backlight = 150000;
 
 		return edp_set_backlight_level_nits(link, true,
 				default_backlight, 0);
@@ -298,15 +297,6 @@ bool set_default_brightness_aux(struct dc_link *link)
 	return false;
 }
 
-bool set_cached_brightness_aux(struct dc_link *link)
-{
-	if (link->backlight_settings.backlight_millinits)
-		return edp_set_backlight_level_nits(link, true,
-						    link->backlight_settings.backlight_millinits, 0);
-	else
-		return set_default_brightness_aux(link);
-	return false;
-}
 bool edp_is_ilr_optimization_enabled(struct dc_link *link)
 {
 	if (link->dpcd_caps.edp_supported_link_rates_count == 0 || !link->panel_config.ilr.optimize_edp_link_rate)
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h
index ebf7deb63d13..a034288ad75d 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h
@@ -30,7 +30,6 @@
 enum dp_panel_mode dp_get_panel_mode(struct dc_link *link);
 void dp_set_panel_mode(struct dc_link *link, enum dp_panel_mode panel_mode);
 bool set_default_brightness_aux(struct dc_link *link);
-bool set_cached_brightness_aux(struct dc_link *link);
 void edp_panel_backlight_power_on(struct dc_link *link, bool wait_for_hpd);
 int edp_get_backlight_level(const struct dc_link *link);
 bool edp_get_backlight_level_nits(struct dc_link *link,
diff --git a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
index 9665ada0f894..df63aa8f01e9 100644
--- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
+++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
@@ -195,6 +195,7 @@ struct dmub_srv_region_params {
 	uint32_t vbios_size;
 	const uint8_t *fw_inst_const;
 	const uint8_t *fw_bss_data;
+	bool is_mailbox_in_inbox;
 };
 
 /**
@@ -214,20 +215,25 @@ struct dmub_srv_region_params {
  */
 struct dmub_srv_region_info {
 	uint32_t fb_size;
+	uint32_t inbox_size;
 	uint8_t num_regions;
 	struct dmub_region regions[DMUB_WINDOW_TOTAL];
 };
 
 /**
- * struct dmub_srv_fb_params - parameters used for driver fb setup
+ * struct dmub_srv_memory_params - parameters used for driver fb setup
  * @region_info: region info calculated by dmub service
- * @cpu_addr: base cpu address for the framebuffer
- * @gpu_addr: base gpu virtual address for the framebuffer
+ * @cpu_fb_addr: base cpu address for the framebuffer
+ * @cpu_inbox_addr: base cpu address for the gart
+ * @gpu_fb_addr: base gpu virtual address for the framebuffer
+ * @gpu_inbox_addr: base gpu virtual address for the gart
  */
-struct dmub_srv_fb_params {
+struct dmub_srv_memory_params {
 	const struct dmub_srv_region_info *region_info;
-	void *cpu_addr;
-	uint64_t gpu_addr;
+	void *cpu_fb_addr;
+	void *cpu_inbox_addr;
+	uint64_t gpu_fb_addr;
+	uint64_t gpu_inbox_addr;
 };
 
 /**
@@ -563,8 +569,8 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub,
  *   DMUB_STATUS_OK - success
  *   DMUB_STATUS_INVALID - unspecified error
  */
-enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub,
-				       const struct dmub_srv_fb_params *params,
+enum dmub_status dmub_srv_calc_mem_info(struct dmub_srv *dmub,
+				       const struct dmub_srv_memory_params *params,
 				       struct dmub_srv_fb_info *out);
 
 /**
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
index e43e8d4bfe37..38360adc53d9 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
@@ -434,7 +434,7 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub,
 	uint32_t fw_state_size = DMUB_FW_STATE_SIZE;
 	uint32_t trace_buffer_size = DMUB_TRACE_BUFFER_SIZE;
 	uint32_t scratch_mem_size = DMUB_SCRATCH_MEM_SIZE;
-
+	uint32_t previous_top = 0;
 	if (!dmub->sw_init)
 		return DMUB_STATUS_INVALID;
 
@@ -459,8 +459,15 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub,
 	bios->base = dmub_align(stack->top, 256);
 	bios->top = bios->base + params->vbios_size;
 
-	mail->base = dmub_align(bios->top, 256);
-	mail->top = mail->base + DMUB_MAILBOX_SIZE;
+	if (params->is_mailbox_in_inbox) {
+		mail->base = 0;
+		mail->top = mail->base + DMUB_MAILBOX_SIZE;
+		previous_top = bios->top;
+	} else {
+		mail->base = dmub_align(bios->top, 256);
+		mail->top = mail->base + DMUB_MAILBOX_SIZE;
+		previous_top = mail->top;
+	}
 
 	fw_info = dmub_get_fw_meta_info(params);
 
@@ -479,7 +486,7 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub,
 			dmub->fw_version = fw_info->fw_version;
 	}
 
-	trace_buff->base = dmub_align(mail->top, 256);
+	trace_buff->base = dmub_align(previous_top, 256);
 	trace_buff->top = trace_buff->base + dmub_align(trace_buffer_size, 64);
 
 	fw_state->base = dmub_align(trace_buff->top, 256);
@@ -490,11 +497,14 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub,
 
 	out->fb_size = dmub_align(scratch_mem->top, 4096);
 
+	if (params->is_mailbox_in_inbox)
+		out->inbox_size = dmub_align(mail->top, 4096);
+
 	return DMUB_STATUS_OK;
 }
 
-enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub,
-				       const struct dmub_srv_fb_params *params,
+enum dmub_status dmub_srv_calc_mem_info(struct dmub_srv *dmub,
+				       const struct dmub_srv_memory_params *params,
 				       struct dmub_srv_fb_info *out)
 {
 	uint8_t *cpu_base;
@@ -509,8 +519,8 @@ enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub,
 	if (params->region_info->num_regions != DMUB_NUM_WINDOWS)
 		return DMUB_STATUS_INVALID;
 
-	cpu_base = (uint8_t *)params->cpu_addr;
-	gpu_base = params->gpu_addr;
+	cpu_base = (uint8_t *)params->cpu_fb_addr;
+	gpu_base = params->gpu_fb_addr;
 
 	for (i = 0; i < DMUB_NUM_WINDOWS; ++i) {
 		const struct dmub_region *reg =
@@ -518,6 +528,12 @@ enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub,
 
 		out->fb[i].cpu_addr = cpu_base + reg->base;
 		out->fb[i].gpu_addr = gpu_base + reg->base;
+
+		if (i == DMUB_WINDOW_4_MAILBOX && params->cpu_inbox_addr != 0) {
+			out->fb[i].cpu_addr = (uint8_t *)params->cpu_inbox_addr + reg->base;
+			out->fb[i].gpu_addr = params->gpu_inbox_addr + reg->base;
+		}
+
 		out->fb[i].size = reg->top - reg->base;
 	}
 
@@ -707,9 +723,16 @@ enum dmub_status dmub_srv_sync_inbox1(struct dmub_srv *dmub)
 		return DMUB_STATUS_INVALID;
 
 	if (dmub->hw_funcs.get_inbox1_rptr && dmub->hw_funcs.get_inbox1_wptr) {
-		dmub->inbox1_rb.rptr = dmub->hw_funcs.get_inbox1_rptr(dmub);
-		dmub->inbox1_rb.wrpt = dmub->hw_funcs.get_inbox1_wptr(dmub);
-		dmub->inbox1_last_wptr = dmub->inbox1_rb.wrpt;
+		uint32_t rptr = dmub->hw_funcs.get_inbox1_rptr(dmub);
+		uint32_t wptr = dmub->hw_funcs.get_inbox1_wptr(dmub);
+
+		if (rptr > dmub->inbox1_rb.capacity || wptr > dmub->inbox1_rb.capacity) {
+			return DMUB_STATUS_HW_FAILURE;
+		} else {
+			dmub->inbox1_rb.rptr = rptr;
+			dmub->inbox1_rb.wrpt = wptr;
+			dmub->inbox1_last_wptr = dmub->inbox1_rb.wrpt;
+		}
 	}
 
 	return DMUB_STATUS_OK;
@@ -743,6 +766,11 @@ enum dmub_status dmub_srv_cmd_queue(struct dmub_srv *dmub,
 	if (!dmub->hw_init)
 		return DMUB_STATUS_INVALID;
 
+	if (dmub->inbox1_rb.rptr > dmub->inbox1_rb.capacity ||
+	    dmub->inbox1_rb.wrpt > dmub->inbox1_rb.capacity) {
+		return DMUB_STATUS_HW_FAILURE;
+	}
+
 	if (dmub_rb_push_front(&dmub->inbox1_rb, cmd))
 		return DMUB_STATUS_OK;
 
@@ -1049,6 +1077,7 @@ enum dmub_status dmub_srv_wait_for_inbox0_ack(struct dmub_srv *dmub, uint32_t ti
 		ack = dmub->hw_funcs.read_inbox0_ack_register(dmub);
 		if (ack)
 			return DMUB_STATUS_OK;
+		udelay(1);
 	}
 	return DMUB_STATUS_TIMEOUT;
 }
diff --git a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h
index bc96d0211360..813463ffe15c 100644
--- a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h
+++ b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h
@@ -417,6 +417,8 @@ struct integrated_info {
 	/* V2.1 */
 	struct edp_info edp1_info;
 	struct edp_info edp2_info;
+	uint32_t gpuclk_ss_percentage;
+	uint32_t gpuclk_ss_type;
 };
 
 /*
diff --git a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
index 84f9b412a4f1..738ee763f24a 100644
--- a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
+++ b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
@@ -147,12 +147,15 @@ void mod_build_vsc_infopacket(const struct dc_stream_state *stream,
 	}
 
 	/* VSC packet set to 4 for PSR-SU, or 2 for PSR1 */
-	if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1)
-		vsc_packet_revision = vsc_packet_rev4;
-	else if (stream->link->replay_settings.config.replay_supported)
+	if (stream->link->psr_settings.psr_feature_enabled) {
+		if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1)
+			vsc_packet_revision = vsc_packet_rev4;
+		else if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_1)
+			vsc_packet_revision = vsc_packet_rev2;
+	}
+
+	if (stream->link->replay_settings.config.replay_supported)
 		vsc_packet_revision = vsc_packet_rev4;
-	else if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_1)
-		vsc_packet_revision = vsc_packet_rev2;
 
 	/* Update to revision 5 for extended colorimetry support */
 	if (stream->use_vsc_sdp_for_colorimetry)
diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
index a522a7c02911..1675314a3ff2 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
@@ -839,6 +839,8 @@ bool is_psr_su_specific_panel(struct dc_link *link)
 				((dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x08) ||
 				(dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x07)))
 				isPSRSUSupported = false;
+			else if (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x03)
+				isPSRSUSupported = false;
 			else if (dpcd_caps->psr_info.force_psrsu_cap == 0x1)
 				isPSRSUSupported = true;
 		}
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_0_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_0_0_offset.h
index c92c4b83253f..4bff1ef8a9a6 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_0_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_0_0_offset.h
@@ -6369,6 +6369,8 @@
 #define regTCP_INVALIDATE_BASE_IDX                                                                      1
 #define regTCP_STATUS                                                                                   0x19a1
 #define regTCP_STATUS_BASE_IDX                                                                          1
+#define regTCP_CNTL                                                                                     0x19a2
+#define regTCP_CNTL_BASE_IDX                                                                            1
 #define regTCP_CNTL2                                                                                    0x19a3
 #define regTCP_CNTL2_BASE_IDX                                                                           1
 #define regTCP_DEBUG_INDEX                                                                              0x19a5
diff --git a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h
index ff30f04be591..7ee3d291120d 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h
@@ -781,6 +781,8 @@
 #define regBIF_BIF256_CI256_RC3X4_USB4_PCIE_CNTL2_BASE_IDX                                              5
 #define regBIF_BIF256_CI256_RC3X4_USB4_PCIE_TX_POWER_CTRL_1                                             0x420187
 #define regBIF_BIF256_CI256_RC3X4_USB4_PCIE_TX_POWER_CTRL_1_BASE_IDX                                    5
+#define regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3                                                  0x4201c6
+#define regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3_BASE_IDX                                         5
 
 
 // addressBlock: nbio_nbif0_bif_cfg_dev0_rc_bifcfgdecp
diff --git a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_sh_mask.h
index 7f131999a263..eb8c556d9c93 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_sh_mask.h
@@ -24646,6 +24646,35 @@
 //BIF_BIF256_CI256_RC3X4_USB4_PCIE_TX_POWER_CTRL_1
 #define BIF_BIF256_CI256_RC3X4_USB4_PCIE_TX_POWER_CTRL_1__MST_MEM_LS_EN_MASK                                  0x00000001L
 #define BIF_BIF256_CI256_RC3X4_USB4_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_LS_EN_MASK                               0x00000008L
+//BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_MAX_PAYLOAD_SIZE_MODE__SHIFT                     0x8
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_PRIV_MAX_PAYLOAD_SIZE__SHIFT                     0x9
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_10BIT_TAG_EN_OVERRIDE__SHIFT                          0xb
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_10BIT_TAG_EN_OVERRIDE__SHIFT                     0xd
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__MST_DROP_SYNC_FLOOD_EN__SHIFT                            0xf
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_MAX_PAYLOAD_SIZE_MODE__SHIFT                          0x10
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_PRIV_MAX_PAYLOAD_SIZE__SHIFT                          0x11
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_MAX_READ_REQUEST_SIZE_MODE__SHIFT                     0x14
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_PRIV_MAX_READ_REQUEST_SIZE__SHIFT                     0x15
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_MAX_READ_SAFE_MODE__SHIFT                             0x18
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_EXTENDED_TAG_EN_OVERRIDE__SHIFT                       0x19
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_MAX_READ_REQUEST_SIZE_MODE__SHIFT                0x1b
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_MAX_READ_REQUEST_SIZE_PRIV__SHIFT                0x1c
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_EXTENDED_TAG_EN_OVERRIDE__SHIFT                  0x1e
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_MAX_PAYLOAD_SIZE_MODE_MASK                       0x00000100L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_PRIV_MAX_PAYLOAD_SIZE_MASK                       0x00000600L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_10BIT_TAG_EN_OVERRIDE_MASK                            0x00001800L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_10BIT_TAG_EN_OVERRIDE_MASK                       0x00006000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__MST_DROP_SYNC_FLOOD_EN_MASK                              0x00008000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_MAX_PAYLOAD_SIZE_MODE_MASK                            0x00010000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_PRIV_MAX_PAYLOAD_SIZE_MASK                            0x000E0000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_MAX_READ_REQUEST_SIZE_MODE_MASK                       0x00100000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_PRIV_MAX_READ_REQUEST_SIZE_MASK                       0x00E00000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_MAX_READ_SAFE_MODE_MASK                               0x01000000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_EXTENDED_TAG_EN_OVERRIDE_MASK                         0x06000000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_MAX_READ_REQUEST_SIZE_MODE_MASK                  0x08000000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_MAX_READ_REQUEST_SIZE_PRIV_MASK                  0x30000000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_EXTENDED_TAG_EN_OVERRIDE_MASK                    0xC0000000L
 
 // addressBlock: nbio_nbif0_bif_cfg_dev0_rc_bifcfgdecp
 //BIF_CFG_DEV0_RC0_VENDOR_ID
diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index cd3c40a86029..c2ccf3724e37 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -318,6 +318,7 @@ enum pp_xgmi_plpd_mode {
 #define MAX_GFX_CLKS 8
 #define MAX_CLKS 4
 #define NUM_VCN 4
+#define NUM_JPEG_ENG 32
 
 struct seq_file;
 enum amd_pp_clock_type;
@@ -444,6 +445,7 @@ struct amd_pm_funcs {
 				   struct dpm_clocks *clock_table);
 	int (*get_smu_prv_buf_details)(void *handle, void **addr, size_t *size);
 	void (*pm_compute_clocks)(void *handle);
+	int (*notify_rlc_state)(void *handle, bool en);
 };
 
 struct metrics_table_header {
@@ -773,6 +775,85 @@ struct gpu_metrics_v1_4 {
 	uint16_t			padding;
 };
 
+struct gpu_metrics_v1_5 {
+	struct metrics_table_header	common_header;
+
+	/* Temperature (Celsius) */
+	uint16_t			temperature_hotspot;
+	uint16_t			temperature_mem;
+	uint16_t			temperature_vrsoc;
+
+	/* Power (Watts) */
+	uint16_t			curr_socket_power;
+
+	/* Utilization (%) */
+	uint16_t			average_gfx_activity;
+	uint16_t			average_umc_activity; // memory controller
+	uint16_t			vcn_activity[NUM_VCN];
+	uint16_t			jpeg_activity[NUM_JPEG_ENG];
+
+	/* Energy (15.259uJ (2^-16) units) */
+	uint64_t			energy_accumulator;
+
+	/* Driver attached timestamp (in ns) */
+	uint64_t			system_clock_counter;
+
+	/* Throttle status */
+	uint32_t			throttle_status;
+
+	/* Clock Lock Status. Each bit corresponds to clock instance */
+	uint32_t			gfxclk_lock_status;
+
+	/* Link width (number of lanes) and speed (in 0.1 GT/s) */
+	uint16_t			pcie_link_width;
+	uint16_t			pcie_link_speed;
+
+	/* XGMI bus width and bitrate (in Gbps) */
+	uint16_t			xgmi_link_width;
+	uint16_t			xgmi_link_speed;
+
+	/* Utilization Accumulated (%) */
+	uint32_t			gfx_activity_acc;
+	uint32_t			mem_activity_acc;
+
+	/*PCIE accumulated bandwidth (GB/sec) */
+	uint64_t			pcie_bandwidth_acc;
+
+	/*PCIE instantaneous bandwidth (GB/sec) */
+	uint64_t			pcie_bandwidth_inst;
+
+	/* PCIE L0 to recovery state transition accumulated count */
+	uint64_t			pcie_l0_to_recov_count_acc;
+
+	/* PCIE replay accumulated count */
+	uint64_t			pcie_replay_count_acc;
+
+	/* PCIE replay rollover accumulated count */
+	uint64_t			pcie_replay_rover_count_acc;
+
+	/* PCIE NAK sent  accumulated count */
+	uint32_t			pcie_nak_sent_count_acc;
+
+	/* PCIE NAK received accumulated count */
+	uint32_t			pcie_nak_rcvd_count_acc;
+
+	/* XGMI accumulated data transfer size(KiloBytes) */
+	uint64_t			xgmi_read_data_acc[NUM_XGMI_LINKS];
+	uint64_t			xgmi_write_data_acc[NUM_XGMI_LINKS];
+
+	/* PMFW attached timestamp (10ns resolution) */
+	uint64_t			firmware_timestamp;
+
+	/* Current clocks (Mhz) */
+	uint16_t			current_gfxclk[MAX_GFX_CLKS];
+	uint16_t			current_socclk[MAX_CLKS];
+	uint16_t			current_vclk0[MAX_CLKS];
+	uint16_t			current_dclk0[MAX_CLKS];
+	uint16_t			current_uclk;
+
+	uint16_t			padding;
+};
+
 /*
  * gpu_metrics_v2_0 is not recommended as it's not naturally aligned.
  * Use gpu_metrics_v2_1 or later instead.
@@ -1084,6 +1165,10 @@ struct gpu_metrics_v3_0 {
 	uint16_t			average_dram_reads;
 	/* time filtered DRAM write bandwidth [MB/sec] */
 	uint16_t			average_dram_writes;
+	/* time filtered IPU read bandwidth [MB/sec] */
+	uint16_t			average_ipu_reads;
+	/* time filtered IPU write bandwidth [MB/sec] */
+	uint16_t			average_ipu_writes;
 
 	/* Driver attached timestamp (in ns) */
 	uint64_t			system_clock_counter;
@@ -1103,6 +1188,8 @@ struct gpu_metrics_v3_0 {
 	uint32_t			average_all_core_power;
 	/* calculated core power [mW] */
 	uint16_t			average_core_power[16];
+	/* time filtered total system power [mW] */
+	uint16_t			average_sys_power;
 	/* maximum IRM defined STAPM power limit [mW] */
 	uint16_t			stapm_power_limit;
 	/* time filtered STAPM power limit [mW] */
@@ -1115,6 +1202,8 @@ struct gpu_metrics_v3_0 {
 	uint16_t			average_ipuclk_frequency;
 	uint16_t			average_fclk_frequency;
 	uint16_t			average_vclk_frequency;
+	uint16_t			average_uclk_frequency;
+	uint16_t			average_mpipu_frequency;
 
 	/* Current clocks */
 	/* target core frequency [MHz] */
@@ -1124,6 +1213,15 @@ struct gpu_metrics_v3_0 {
 	/* GFXCLK frequency limit enforced on GFX [MHz] */
 	uint16_t			current_gfx_maxfreq;
 
+	/* Throttle Residency (ASIC dependent) */
+	uint32_t			throttle_residency_prochot;
+	uint32_t			throttle_residency_spl;
+	uint32_t			throttle_residency_fppt;
+	uint32_t			throttle_residency_sppt;
+	uint32_t			throttle_residency_thm_core;
+	uint32_t			throttle_residency_thm_gfx;
+	uint32_t			throttle_residency_thm_soc;
+
 	/* Metrics table alpha filter time constant [us] */
 	uint32_t			time_filter_alphavalue;
 };
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
index 08cb79401410..8ec11da0319f 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -181,6 +181,24 @@ int amdgpu_dpm_set_mp1_state(struct amdgpu_device *adev,
 	return ret;
 }
 
+int amdgpu_dpm_notify_rlc_state(struct amdgpu_device *adev, bool en)
+{
+	int ret = 0;
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+
+	if (pp_funcs && pp_funcs->notify_rlc_state) {
+		mutex_lock(&adev->pm.mutex);
+
+		ret = pp_funcs->notify_rlc_state(
+				adev->powerplay.pp_handle,
+				en);
+
+		mutex_unlock(&adev->pm.mutex);
+	}
+
+	return ret;
+}
+
 bool amdgpu_dpm_is_baco_supported(struct amdgpu_device *adev)
 {
 	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index ca2ece24e1e0..20c53eefd680 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -2128,7 +2128,9 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_
 		if (amdgpu_dpm_is_overdrive_supported(adev))
 			*states = ATTR_STATE_SUPPORTED;
 	} else if (DEVICE_ATTR_IS(mem_busy_percent)) {
-		if (adev->flags & AMD_IS_APU || gc_ver == IP_VERSION(9, 0, 1))
+		if ((adev->flags & AMD_IS_APU &&
+		     gc_ver != IP_VERSION(9, 4, 3)) ||
+		    gc_ver == IP_VERSION(9, 0, 1))
 			*states = ATTR_STATE_UNSUPPORTED;
 	} else if (DEVICE_ATTR_IS(pcie_bw)) {
 		/* PCIe Perf counters won't work on APU nodes */
@@ -2198,10 +2200,10 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_
 	} else if (DEVICE_ATTR_IS(xgmi_plpd_policy)) {
 		if (amdgpu_dpm_get_xgmi_plpd_mode(adev, NULL) == XGMI_PLPD_NONE)
 			*states = ATTR_STATE_UNSUPPORTED;
-	} else if (DEVICE_ATTR_IS(pp_dpm_mclk_od)) {
+	} else if (DEVICE_ATTR_IS(pp_mclk_od)) {
 		if (amdgpu_dpm_get_mclk_od(adev) == -EOPNOTSUPP)
 			*states = ATTR_STATE_UNSUPPORTED;
-	} else if (DEVICE_ATTR_IS(pp_dpm_sclk_od)) {
+	} else if (DEVICE_ATTR_IS(pp_sclk_od)) {
 		if (amdgpu_dpm_get_sclk_od(adev) == -EOPNOTSUPP)
 			*states = ATTR_STATE_UNSUPPORTED;
 	} else if (DEVICE_ATTR_IS(apu_thermal_cap)) {
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
index feccd2a7120d..482ea30147ab 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -415,6 +415,8 @@ int amdgpu_dpm_mode1_reset(struct amdgpu_device *adev);
 int amdgpu_dpm_set_mp1_state(struct amdgpu_device *adev,
 			     enum pp_mp1_state mp1_state);
 
+int amdgpu_dpm_notify_rlc_state(struct amdgpu_device *adev, bool en);
+
 int amdgpu_dpm_set_gfx_power_up_by_imu(struct amdgpu_device *adev);
 
 int amdgpu_dpm_baco_exit(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 1ead323f1c78..e1a5ee911dbb 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1710,6 +1710,16 @@ static int smu_disable_dpms(struct smu_context *smu)
 		}
 	}
 
+	/* Notify SMU RLC is going to be off, stop RLC and SMU interaction.
+	 * otherwise SMU will hang while interacting with RLC if RLC is halted
+	 * this is a WA for Vangogh asic which fix the SMU hang issue.
+	 */
+	ret = smu_notify_rlc_state(smu, false);
+	if (ret) {
+		dev_err(adev->dev, "Fail to notify rlc status!\n");
+		return ret;
+	}
+
 	if (amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(9, 4, 2) &&
 	    !((adev->flags & AMD_IS_APU) && adev->gfx.imu.funcs) &&
 	    !amdgpu_sriov_vf(adev) && adev->gfx.rlc.funcs->stop)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index 8def291b18bc..f8b2e6cc2568 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -1360,6 +1360,11 @@ struct pptable_funcs {
 	 *                       management.
 	 */
 	int (*dpm_set_umsch_mm_enable)(struct smu_context *smu, bool enable);
+
+	/**
+	 * @notify_rlc_state: Notify RLC power state to SMU.
+	 */
+	int (*notify_rlc_state)(struct smu_context *smu, bool en);
 };
 
 typedef enum {
@@ -1403,6 +1408,16 @@ typedef enum {
 	METRICS_PCIE_WIDTH,
 	METRICS_CURR_FANPWM,
 	METRICS_CURR_SOCKETPOWER,
+	METRICS_AVERAGE_VPECLK,
+	METRICS_AVERAGE_IPUCLK,
+	METRICS_AVERAGE_MPIPUCLK,
+	METRICS_THROTTLER_RESIDENCY_PROCHOT,
+	METRICS_THROTTLER_RESIDENCY_SPL,
+	METRICS_THROTTLER_RESIDENCY_FPPT,
+	METRICS_THROTTLER_RESIDENCY_SPPT,
+	METRICS_THROTTLER_RESIDENCY_THM_CORE,
+	METRICS_THROTTLER_RESIDENCY_THM_GFX,
+	METRICS_THROTTLER_RESIDENCY_THM_SOC,
 } MetricsMember_t;
 
 enum smu_cmn2asic_mapping_type {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h
index 22f88842a7fd..8f42771e1f0a 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h
@@ -27,7 +27,7 @@
 // *** IMPORTANT ***
 // SMU TEAM: Always increment the interface version if
 // any structure is changed in this file
-#define PMFW_DRIVER_IF_VERSION 6
+#define PMFW_DRIVER_IF_VERSION 7
 
 typedef struct {
   int32_t value;
@@ -150,37 +150,50 @@ typedef struct {
 } DpmClocks_t;
 
 typedef struct {
-  uint16_t CoreFrequency[16];        //Target core frequency [MHz]
-  uint16_t CorePower[16];            //CAC calculated core power [mW]
-  uint16_t CoreTemperature[16];      //TSEN measured core temperature [centi-C]
-  uint16_t GfxTemperature;           //TSEN measured GFX temperature [centi-C]
-  uint16_t SocTemperature;           //TSEN measured SOC temperature [centi-C]
-  uint16_t StapmOpnLimit;            //Maximum IRM defined STAPM power limit [mW]
-  uint16_t StapmCurrentLimit;        //Time filtered STAPM power limit [mW]
-  uint16_t InfrastructureCpuMaxFreq; //CCLK frequency limit enforced on classic cores [MHz]
-  uint16_t InfrastructureGfxMaxFreq; //GFXCLK frequency limit enforced on GFX [MHz]
-  uint16_t SkinTemp;                 //Maximum skin temperature reported by APU and HS2 chassis sensors [centi-C]
-  uint16_t GfxclkFrequency;          //Time filtered target GFXCLK frequency [MHz]
-  uint16_t FclkFrequency;            //Time filtered target FCLK frequency [MHz]
-  uint16_t GfxActivity;              //Time filtered GFX busy % [0-100]
-  uint16_t SocclkFrequency;          //Time filtered target SOCCLK frequency [MHz]
-  uint16_t VclkFrequency;            //Time filtered target VCLK frequency [MHz]
-  uint16_t VcnActivity;              //Time filtered VCN busy % [0-100]
-  uint16_t VpeclkFrequency;          //Time filtered target VPECLK frequency [MHz]
-  uint16_t IpuclkFrequency;          //Time filtered target IPUCLK frequency [MHz]
-  uint16_t IpuBusy[8];               //Time filtered IPU per-column busy % [0-100]
-  uint16_t DRAMReads;                //Time filtered DRAM read bandwidth [MB/sec]
-  uint16_t DRAMWrites;               //Time filtered DRAM write bandwidth [MB/sec]
-  uint16_t CoreC0Residency[16];      //Time filtered per-core C0 residency % [0-100]
-  uint16_t IpuPower;                 //Time filtered IPU power [mW]
-  uint32_t ApuPower;                 //Time filtered APU power [mW]
-  uint32_t GfxPower;                 //Time filtered GFX power [mW]
-  uint32_t dGpuPower;                //Time filtered dGPU power [mW]
-  uint32_t SocketPower;              //Time filtered power used for PPT/STAPM [APU+dGPU] [mW]
-  uint32_t AllCorePower;             //Time filtered sum of core power across all cores in the socket [mW]
-  uint32_t FilterAlphaValue;         //Metrics table alpha filter time constant [us]
-  uint32_t MetricsCounter;           //Counter that is incremented on every metrics table update [PM_TIMER cycles]
-  uint32_t spare[16];
+  uint16_t CoreFrequency[16];          //Target core frequency [MHz]
+  uint16_t CorePower[16];              //CAC calculated core power [mW]
+  uint16_t CoreTemperature[16];        //TSEN measured core temperature [centi-C]
+  uint16_t GfxTemperature;             //TSEN measured GFX temperature [centi-C]
+  uint16_t SocTemperature;             //TSEN measured SOC temperature [centi-C]
+  uint16_t StapmOpnLimit;              //Maximum IRM defined STAPM power limit [mW]
+  uint16_t StapmCurrentLimit;          //Time filtered STAPM power limit [mW]
+  uint16_t InfrastructureCpuMaxFreq;   //CCLK frequency limit enforced on classic cores [MHz]
+  uint16_t InfrastructureGfxMaxFreq;   //GFXCLK frequency limit enforced on GFX [MHz]
+  uint16_t SkinTemp;                   //Maximum skin temperature reported by APU and HS2 chassis sensors [centi-C]
+  uint16_t GfxclkFrequency;            //Time filtered target GFXCLK frequency [MHz]
+  uint16_t FclkFrequency;              //Time filtered target FCLK frequency [MHz]
+  uint16_t GfxActivity;                //Time filtered GFX busy % [0-100]
+  uint16_t SocclkFrequency;            //Time filtered target SOCCLK frequency [MHz]
+  uint16_t VclkFrequency;              //Time filtered target VCLK frequency [MHz]
+  uint16_t VcnActivity;                //Time filtered VCN busy % [0-100]
+  uint16_t VpeclkFrequency;            //Time filtered target VPECLK frequency [MHz]
+  uint16_t IpuclkFrequency;            //Time filtered target IPUCLK frequency [MHz]
+  uint16_t IpuBusy[8];                 //Time filtered IPU per-column busy % [0-100]
+  uint16_t DRAMReads;                  //Time filtered DRAM read bandwidth [MB/sec]
+  uint16_t DRAMWrites;                 //Time filtered DRAM write bandwidth [MB/sec]
+  uint16_t CoreC0Residency[16];        //Time filtered per-core C0 residency % [0-100]
+  uint16_t IpuPower;                   //Time filtered IPU power [mW]
+  uint32_t ApuPower;                   //Time filtered APU power [mW]
+  uint32_t GfxPower;                   //Time filtered GFX power [mW]
+  uint32_t dGpuPower;                  //Time filtered dGPU power [mW]
+  uint32_t SocketPower;                //Time filtered power used for PPT/STAPM [APU+dGPU] [mW]
+  uint32_t AllCorePower;               //Time filtered sum of core power across all cores in the socket [mW]
+  uint32_t FilterAlphaValue;           //Metrics table alpha filter time constant [us]
+  uint32_t MetricsCounter;             //Counter that is incremented on every metrics table update [PM_TIMER cycles]
+  uint16_t MemclkFrequency;            //Time filtered target MEMCLK frequency [MHz]
+  uint16_t MpipuclkFrequency;          //Time filtered target MPIPUCLK frequency [MHz]
+  uint16_t IpuReads;                   //Time filtered IPU read bandwidth [MB/sec]
+  uint16_t IpuWrites;                  //Time filtered IPU write bandwidth [MB/sec]
+  uint32_t ThrottleResidency_PROCHOT;  //Counter that is incremented on every metrics table update when PROCHOT was engaged [PM_TIMER cycles]
+  uint32_t ThrottleResidency_SPL;      //Counter that is incremented on every metrics table update when SPL was engaged [PM_TIMER cycles]
+  uint32_t ThrottleResidency_FPPT;     //Counter that is incremented on every metrics table update when fast PPT was engaged [PM_TIMER cycles]
+  uint32_t ThrottleResidency_SPPT;     //Counter that is incremented on every metrics table update when slow PPT was engaged [PM_TIMER cycles]
+  uint32_t ThrottleResidency_THM_CORE; //Counter that is incremented on every metrics table update when CORE thermal throttling was engaged [PM_TIMER cycles]
+  uint32_t ThrottleResidency_THM_GFX;  //Counter that is incremented on every metrics table update when GFX thermal throttling was engaged [PM_TIMER cycles]
+  uint32_t ThrottleResidency_THM_SOC;  //Counter that is incremented on every metrics table update when SOC thermal throttling was engaged [PM_TIMER cycles]
+  uint16_t Psys;                       //Time filtered Psys power [mW]
+  uint16_t spare1;
+  uint32_t spare[6];
 } SmuMetrics_t;
 
 //ISP tile definitions
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h
index dab35d878a90..7b812b9994d7 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h
@@ -123,7 +123,7 @@ typedef enum {
   VOLTAGE_GUARDBAND_COUNT
 } GFX_GUARDBAND_e;
 
-#define SMU_METRICS_TABLE_VERSION 0x8
+#define SMU_METRICS_TABLE_VERSION 0xB
 
 typedef struct __attribute__((packed, aligned(4))) {
   uint32_t AccumulationCounter;
@@ -211,7 +211,111 @@ typedef struct __attribute__((packed, aligned(4))) {
   //XGMI Data tranfser size
   uint64_t XgmiReadDataSizeAcc[8];//in KByte
   uint64_t XgmiWriteDataSizeAcc[8];//in KByte
-} MetricsTable_t;
+
+  //PCIE BW Data and error count
+  uint32_t PcieBandwidth[4];
+  uint32_t PCIeL0ToRecoveryCountAcc;      // The Pcie counter itself is accumulated
+  uint32_t PCIenReplayAAcc;               // The Pcie counter itself is accumulated
+  uint32_t PCIenReplayARolloverCountAcc;  // The Pcie counter itself is accumulated
+  uint32_t PCIeNAKSentCountAcc;           // The Pcie counter itself is accumulated
+  uint32_t PCIeNAKReceivedCountAcc;       // The Pcie counter itself is accumulated
+
+  // VCN/JPEG ACTIVITY
+  uint32_t VcnBusy[4];
+  uint32_t JpegBusy[32];
+} MetricsTableX_t;
+
+typedef struct __attribute__((packed, aligned(4))) {
+  uint32_t AccumulationCounter;
+
+  //TEMPERATURE
+  uint32_t MaxSocketTemperature;
+  uint32_t MaxVrTemperature;
+  uint32_t MaxHbmTemperature;
+  uint64_t MaxSocketTemperatureAcc;
+  uint64_t MaxVrTemperatureAcc;
+  uint64_t MaxHbmTemperatureAcc;
+
+  //POWER
+  uint32_t SocketPowerLimit;
+  uint32_t MaxSocketPowerLimit;
+  uint32_t SocketPower;
+
+  //ENERGY
+  uint64_t Timestamp;
+  uint64_t SocketEnergyAcc;
+  uint64_t CcdEnergyAcc;
+  uint64_t XcdEnergyAcc;
+  uint64_t AidEnergyAcc;
+  uint64_t HbmEnergyAcc;
+
+  //FREQUENCY
+  uint32_t CclkFrequencyLimit;
+  uint32_t GfxclkFrequencyLimit;
+  uint32_t FclkFrequency;
+  uint32_t UclkFrequency;
+  uint32_t SocclkFrequency[4];
+  uint32_t VclkFrequency[4];
+  uint32_t DclkFrequency[4];
+  uint32_t LclkFrequency[4];
+  uint64_t GfxclkFrequencyAcc[8];
+  uint64_t CclkFrequencyAcc[96];
+
+  //FREQUENCY RANGE
+  uint32_t MaxCclkFrequency;
+  uint32_t MinCclkFrequency;
+  uint32_t MaxGfxclkFrequency;
+  uint32_t MinGfxclkFrequency;
+  uint32_t FclkFrequencyTable[4];
+  uint32_t UclkFrequencyTable[4];
+  uint32_t SocclkFrequencyTable[4];
+  uint32_t VclkFrequencyTable[4];
+  uint32_t DclkFrequencyTable[4];
+  uint32_t LclkFrequencyTable[4];
+  uint32_t MaxLclkDpmRange;
+  uint32_t MinLclkDpmRange;
+
+  //XGMI
+  uint32_t XgmiWidth;
+  uint32_t XgmiBitrate;
+  uint64_t XgmiReadBandwidthAcc[8];
+  uint64_t XgmiWriteBandwidthAcc[8];
+
+  //ACTIVITY
+  uint32_t SocketC0Residency;
+  uint32_t SocketGfxBusy;
+  uint32_t DramBandwidthUtilization;
+  uint64_t SocketC0ResidencyAcc;
+  uint64_t SocketGfxBusyAcc;
+  uint64_t DramBandwidthAcc;
+  uint32_t MaxDramBandwidth;
+  uint64_t DramBandwidthUtilizationAcc;
+  uint64_t PcieBandwidthAcc[4];
+
+  //THROTTLERS
+  uint32_t ProchotResidencyAcc;
+  uint32_t PptResidencyAcc;
+  uint32_t SocketThmResidencyAcc;
+  uint32_t VrThmResidencyAcc;
+  uint32_t HbmThmResidencyAcc;
+  uint32_t GfxLockXCDMak;
+
+  // New Items at end to maintain driver compatibility
+  uint32_t GfxclkFrequency[8];
+
+  //PSNs
+  uint64_t PublicSerialNumber_AID[4];
+  uint64_t PublicSerialNumber_XCD[8];
+  uint64_t PublicSerialNumber_CCD[12];
+
+  //XGMI Data tranfser size
+  uint64_t XgmiReadDataSizeAcc[8];//in KByte
+  uint64_t XgmiWriteDataSizeAcc[8];//in KByte
+
+  // VCN/JPEG ACTIVITY
+  uint32_t VcnBusy[4];
+  uint32_t JpegBusy[32];
+} MetricsTableA_t;
 
 #define SMU_VF_METRICS_TABLE_VERSION 0x3
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
index 762b31455a0b..2ff6deedef95 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -2193,8 +2193,7 @@ static int vangogh_get_dpm_clock_table(struct smu_context *smu, struct dpm_clock
 	return 0;
 }
 
-
-static int vangogh_system_features_control(struct smu_context *smu, bool en)
+static int vangogh_notify_rlc_state(struct smu_context *smu, bool en)
 {
 	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
@@ -2523,7 +2522,7 @@ static const struct pptable_funcs vangogh_ppt_funcs = {
 	.print_clk_levels = vangogh_common_print_clk_levels,
 	.set_default_dpm_table = vangogh_set_default_dpm_tables,
 	.set_fine_grain_gfx_freq_parameters = vangogh_set_fine_grain_gfx_freq_parameters,
-	.system_features_control = vangogh_system_features_control,
+	.notify_rlc_state = vangogh_notify_rlc_state,
 	.feature_is_enabled = smu_cmn_feature_is_enabled,
 	.set_power_profile_mode = vangogh_set_power_profile_mode,
 	.get_power_profile_mode = vangogh_get_power_profile_mode,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
index 1a6675d70a4b..f1440869d1ce 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
@@ -257,8 +257,11 @@ static int aldebaran_tables_init(struct smu_context *smu)
 	}
 
 	smu_table->ecc_table = kzalloc(tables[SMU_TABLE_ECCINFO].size, GFP_KERNEL);
-	if (!smu_table->ecc_table)
+	if (!smu_table->ecc_table) {
+		kfree(smu_table->metrics_table);
+		kfree(smu_table->gpu_metrics_table);
 		return -ENOMEM;
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 891605d4975f..b64e07b75937 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -245,6 +245,8 @@ struct PPTable_t {
 #define SMUQ10_TO_UINT(x) ((x) >> 10)
 #define SMUQ10_FRAC(x) ((x) & 0x3ff)
 #define SMUQ10_ROUND(x) ((SMUQ10_TO_UINT(x)) + ((SMUQ10_FRAC(x)) >= 0x200))
+#define GET_METRIC_FIELD(field) ((adev->flags & AMD_IS_APU) ?\
+		(metrics_a->field) : (metrics_x->field))
 
 struct smu_v13_0_6_dpm_map {
 	enum smu_clk_type clk_type;
@@ -327,7 +329,8 @@ static int smu_v13_0_6_tables_init(struct smu_context *smu)
 		SMU_TABLE_INIT(tables, SMU_TABLE_PMSTATUSLOG, SMU13_TOOL_SIZE,
 			       PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM);
 
-	SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, sizeof(MetricsTable_t),
+	SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS,
+		       max(sizeof(MetricsTableX_t), sizeof(MetricsTableA_t)),
 		       PAGE_SIZE,
 		       AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT);
 
@@ -335,12 +338,13 @@ static int smu_v13_0_6_tables_init(struct smu_context *smu)
 		       PAGE_SIZE,
 		       AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT);
 
-	smu_table->metrics_table = kzalloc(sizeof(MetricsTable_t), GFP_KERNEL);
+	smu_table->metrics_table = kzalloc(max(sizeof(MetricsTableX_t),
+		       sizeof(MetricsTableA_t)), GFP_KERNEL);
 	if (!smu_table->metrics_table)
 		return -ENOMEM;
 	smu_table->metrics_time = 0;
 
-	smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_4);
+	smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_5);
 	smu_table->gpu_metrics_table =
 		kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL);
 	if (!smu_table->gpu_metrics_table) {
@@ -431,9 +435,11 @@ static int smu_v13_0_6_get_metrics_table(struct smu_context *smu,
 static int smu_v13_0_6_setup_driver_pptable(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
-	MetricsTable_t *metrics = (MetricsTable_t *)smu_table->metrics_table;
+	MetricsTableX_t *metrics_x = (MetricsTableX_t *)smu_table->metrics_table;
+	MetricsTableA_t *metrics_a = (MetricsTableA_t *)smu_table->metrics_table;
 	struct PPTable_t *pptable =
 		(struct PPTable_t *)smu_table->driver_pptable;
+	struct amdgpu_device *adev = smu->adev;
 	int ret, i, retry = 100;
 
 	/* Store one-time values in driver PPTable */
@@ -444,7 +450,7 @@ static int smu_v13_0_6_setup_driver_pptable(struct smu_context *smu)
 				return ret;
 
 			/* Ensure that metrics have been updated */
-			if (metrics->AccumulationCounter)
+			if (GET_METRIC_FIELD(AccumulationCounter))
 				break;
 
 			usleep_range(1000, 1100);
@@ -454,29 +460,29 @@ static int smu_v13_0_6_setup_driver_pptable(struct smu_context *smu)
 			return -ETIME;
 
 		pptable->MaxSocketPowerLimit =
-			SMUQ10_ROUND(metrics->MaxSocketPowerLimit);
+			SMUQ10_ROUND(GET_METRIC_FIELD(MaxSocketPowerLimit));
 		pptable->MaxGfxclkFrequency =
-			SMUQ10_ROUND(metrics->MaxGfxclkFrequency);
+			SMUQ10_ROUND(GET_METRIC_FIELD(MaxGfxclkFrequency));
 		pptable->MinGfxclkFrequency =
-			SMUQ10_ROUND(metrics->MinGfxclkFrequency);
+			SMUQ10_ROUND(GET_METRIC_FIELD(MinGfxclkFrequency));
 
 		for (i = 0; i < 4; ++i) {
 			pptable->FclkFrequencyTable[i] =
-				SMUQ10_ROUND(metrics->FclkFrequencyTable[i]);
+				SMUQ10_ROUND(GET_METRIC_FIELD(FclkFrequencyTable)[i]);
 			pptable->UclkFrequencyTable[i] =
-				SMUQ10_ROUND(metrics->UclkFrequencyTable[i]);
+				SMUQ10_ROUND(GET_METRIC_FIELD(UclkFrequencyTable)[i]);
 			pptable->SocclkFrequencyTable[i] = SMUQ10_ROUND(
-				metrics->SocclkFrequencyTable[i]);
+				GET_METRIC_FIELD(SocclkFrequencyTable)[i]);
 			pptable->VclkFrequencyTable[i] =
-				SMUQ10_ROUND(metrics->VclkFrequencyTable[i]);
+				SMUQ10_ROUND(GET_METRIC_FIELD(VclkFrequencyTable)[i]);
 			pptable->DclkFrequencyTable[i] =
-				SMUQ10_ROUND(metrics->DclkFrequencyTable[i]);
+				SMUQ10_ROUND(GET_METRIC_FIELD(DclkFrequencyTable)[i]);
 			pptable->LclkFrequencyTable[i] =
-				SMUQ10_ROUND(metrics->LclkFrequencyTable[i]);
+				SMUQ10_ROUND(GET_METRIC_FIELD(LclkFrequencyTable)[i]);
 		}
 
 		/* use AID0 serial number by default */
-		pptable->PublicSerialNumber_AID = metrics->PublicSerialNumber_AID[0];
+		pptable->PublicSerialNumber_AID = GET_METRIC_FIELD(PublicSerialNumber_AID)[0];
 
 		pptable->Init = true;
 	}
@@ -778,7 +784,8 @@ static int smu_v13_0_6_get_smu_metrics_data(struct smu_context *smu,
 					    uint32_t *value)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
-	MetricsTable_t *metrics = (MetricsTable_t *)smu_table->metrics_table;
+	MetricsTableX_t *metrics_x = (MetricsTableX_t *)smu_table->metrics_table;
+	MetricsTableA_t *metrics_a = (MetricsTableA_t *)smu_table->metrics_table;
 	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
 	int xcc_id;
@@ -793,50 +800,50 @@ static int smu_v13_0_6_get_smu_metrics_data(struct smu_context *smu,
 	case METRICS_AVERAGE_GFXCLK:
 		if (smu->smc_fw_version >= 0x552F00) {
 			xcc_id = GET_INST(GC, 0);
-			*value = SMUQ10_ROUND(metrics->GfxclkFrequency[xcc_id]);
+			*value = SMUQ10_ROUND(GET_METRIC_FIELD(GfxclkFrequency)[xcc_id]);
 		} else {
 			*value = 0;
 		}
 		break;
 	case METRICS_CURR_SOCCLK:
 	case METRICS_AVERAGE_SOCCLK:
-		*value = SMUQ10_ROUND(metrics->SocclkFrequency[0]);
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(SocclkFrequency)[0]);
 		break;
 	case METRICS_CURR_UCLK:
 	case METRICS_AVERAGE_UCLK:
-		*value = SMUQ10_ROUND(metrics->UclkFrequency);
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(UclkFrequency));
 		break;
 	case METRICS_CURR_VCLK:
-		*value = SMUQ10_ROUND(metrics->VclkFrequency[0]);
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(VclkFrequency)[0]);
 		break;
 	case METRICS_CURR_DCLK:
-		*value = SMUQ10_ROUND(metrics->DclkFrequency[0]);
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(DclkFrequency)[0]);
 		break;
 	case METRICS_CURR_FCLK:
-		*value = SMUQ10_ROUND(metrics->FclkFrequency);
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(FclkFrequency));
 		break;
 	case METRICS_AVERAGE_GFXACTIVITY:
-		*value = SMUQ10_ROUND(metrics->SocketGfxBusy);
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(SocketGfxBusy));
 		break;
 	case METRICS_AVERAGE_MEMACTIVITY:
-		*value = SMUQ10_ROUND(metrics->DramBandwidthUtilization);
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(DramBandwidthUtilization));
 		break;
 	case METRICS_CURR_SOCKETPOWER:
-		*value = SMUQ10_ROUND(metrics->SocketPower) << 8;
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(SocketPower)) << 8;
 		break;
 	case METRICS_TEMPERATURE_HOTSPOT:
-		*value = SMUQ10_ROUND(metrics->MaxSocketTemperature) *
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(MaxSocketTemperature)) *
 			 SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 		break;
 	case METRICS_TEMPERATURE_MEM:
-		*value = SMUQ10_ROUND(metrics->MaxHbmTemperature) *
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(MaxHbmTemperature)) *
 			 SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 		break;
 	/* This is the max of all VRs and not just SOC VR.
 	 * No need to define another data type for the same.
 	 */
 	case METRICS_TEMPERATURE_VRSOC:
-		*value = SMUQ10_ROUND(metrics->MaxVrTemperature) *
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(MaxVrTemperature)) *
 			 SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 		break;
 	default:
@@ -1454,7 +1461,7 @@ static int smu_v13_0_6_register_irq_handler(struct smu_context *smu)
 
 static int smu_v13_0_6_notify_unload(struct smu_context *smu)
 {
-	if (smu->smc_fw_version <= 0x553500)
+	if (amdgpu_in_reset(smu->adev))
 		return 0;
 
 	dev_dbg(smu->adev->dev, "Notify PMFW about driver unload");
@@ -2022,67 +2029,70 @@ static int smu_v13_0_6_get_current_pcie_link_speed(struct smu_context *smu)
 static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
-	struct gpu_metrics_v1_4 *gpu_metrics =
-		(struct gpu_metrics_v1_4 *)smu_table->gpu_metrics_table;
+	struct gpu_metrics_v1_5 *gpu_metrics =
+		(struct gpu_metrics_v1_5 *)smu_table->gpu_metrics_table;
 	struct amdgpu_device *adev = smu->adev;
-	int ret = 0, xcc_id, inst, i;
-	MetricsTable_t *metrics;
+	int ret = 0, xcc_id, inst, i, j;
+	MetricsTableX_t *metrics_x;
+	MetricsTableA_t *metrics_a;
 	u16 link_width_level;
 
-	metrics = kzalloc(sizeof(MetricsTable_t), GFP_KERNEL);
-	ret = smu_v13_0_6_get_metrics_table(smu, metrics, true);
+	metrics_x = kzalloc(max(sizeof(MetricsTableX_t), sizeof(MetricsTableA_t)), GFP_KERNEL);
+	ret = smu_v13_0_6_get_metrics_table(smu, metrics_x, true);
 	if (ret) {
-		kfree(metrics);
+		kfree(metrics_x);
 		return ret;
 	}
 
-	smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 4);
+	metrics_a = (MetricsTableA_t *)metrics_x;
+
+	smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 5);
 
 	gpu_metrics->temperature_hotspot =
-		SMUQ10_ROUND(metrics->MaxSocketTemperature);
+		SMUQ10_ROUND(GET_METRIC_FIELD(MaxSocketTemperature));
 	/* Individual HBM stack temperature is not reported */
 	gpu_metrics->temperature_mem =
-		SMUQ10_ROUND(metrics->MaxHbmTemperature);
+		SMUQ10_ROUND(GET_METRIC_FIELD(MaxHbmTemperature));
 	/* Reports max temperature of all voltage rails */
 	gpu_metrics->temperature_vrsoc =
-		SMUQ10_ROUND(metrics->MaxVrTemperature);
+		SMUQ10_ROUND(GET_METRIC_FIELD(MaxVrTemperature));
 
 	gpu_metrics->average_gfx_activity =
-		SMUQ10_ROUND(metrics->SocketGfxBusy);
+		SMUQ10_ROUND(GET_METRIC_FIELD(SocketGfxBusy));
 	gpu_metrics->average_umc_activity =
-		SMUQ10_ROUND(metrics->DramBandwidthUtilization);
+		SMUQ10_ROUND(GET_METRIC_FIELD(DramBandwidthUtilization));
 
 	gpu_metrics->curr_socket_power =
-		SMUQ10_ROUND(metrics->SocketPower);
+		SMUQ10_ROUND(GET_METRIC_FIELD(SocketPower));
 	/* Energy counter reported in 15.259uJ (2^-16) units */
-	gpu_metrics->energy_accumulator = metrics->SocketEnergyAcc;
+	gpu_metrics->energy_accumulator = GET_METRIC_FIELD(SocketEnergyAcc);
 
 	for (i = 0; i < MAX_GFX_CLKS; i++) {
 		xcc_id = GET_INST(GC, i);
 		if (xcc_id >= 0)
 			gpu_metrics->current_gfxclk[i] =
-				SMUQ10_ROUND(metrics->GfxclkFrequency[xcc_id]);
+				SMUQ10_ROUND(GET_METRIC_FIELD(GfxclkFrequency)[xcc_id]);
 
 		if (i < MAX_CLKS) {
 			gpu_metrics->current_socclk[i] =
-				SMUQ10_ROUND(metrics->SocclkFrequency[i]);
+				SMUQ10_ROUND(GET_METRIC_FIELD(SocclkFrequency)[i]);
 			inst = GET_INST(VCN, i);
 			if (inst >= 0) {
 				gpu_metrics->current_vclk0[i] =
-					SMUQ10_ROUND(metrics->VclkFrequency[inst]);
+					SMUQ10_ROUND(GET_METRIC_FIELD(VclkFrequency)[inst]);
 				gpu_metrics->current_dclk0[i] =
-					SMUQ10_ROUND(metrics->DclkFrequency[inst]);
+					SMUQ10_ROUND(GET_METRIC_FIELD(DclkFrequency)[inst]);
 			}
 		}
 	}
 
-	gpu_metrics->current_uclk = SMUQ10_ROUND(metrics->UclkFrequency);
+	gpu_metrics->current_uclk = SMUQ10_ROUND(GET_METRIC_FIELD(UclkFrequency));
 
 	/* Throttle status is not reported through metrics now */
 	gpu_metrics->throttle_status = 0;
 
 	/* Clock Lock Status. Each bit corresponds to each GFXCLK instance */
-	gpu_metrics->gfxclk_lock_status = metrics->GfxLockXCDMak >> GET_INST(GC, 0);
+	gpu_metrics->gfxclk_lock_status = GET_METRIC_FIELD(GfxLockXCDMak) >> GET_INST(GC, 0);
 
 	if (!(adev->flags & AMD_IS_APU)) {
 		link_width_level = smu_v13_0_6_get_current_pcie_link_width_level(smu);
@@ -2094,30 +2104,57 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table
 		gpu_metrics->pcie_link_speed =
 			smu_v13_0_6_get_current_pcie_link_speed(smu);
 		gpu_metrics->pcie_bandwidth_acc =
-				SMUQ10_ROUND(metrics->PcieBandwidthAcc[0]);
+				SMUQ10_ROUND(metrics_x->PcieBandwidthAcc[0]);
+		gpu_metrics->pcie_bandwidth_inst =
+				SMUQ10_ROUND(metrics_x->PcieBandwidth[0]);
+		gpu_metrics->pcie_l0_to_recov_count_acc =
+				metrics_x->PCIeL0ToRecoveryCountAcc;
+		gpu_metrics->pcie_replay_count_acc =
+				metrics_x->PCIenReplayAAcc;
+		gpu_metrics->pcie_replay_rover_count_acc =
+				metrics_x->PCIenReplayARolloverCountAcc;
+		gpu_metrics->pcie_nak_sent_count_acc =
+				metrics_x->PCIeNAKSentCountAcc;
+		gpu_metrics->pcie_nak_rcvd_count_acc =
+				metrics_x->PCIeNAKReceivedCountAcc;
 	}
 
 	gpu_metrics->system_clock_counter = ktime_get_boottime_ns();
 
 	gpu_metrics->gfx_activity_acc =
-		SMUQ10_ROUND(metrics->SocketGfxBusyAcc);
+		SMUQ10_ROUND(GET_METRIC_FIELD(SocketGfxBusyAcc));
 	gpu_metrics->mem_activity_acc =
-		SMUQ10_ROUND(metrics->DramBandwidthUtilizationAcc);
+		SMUQ10_ROUND(GET_METRIC_FIELD(DramBandwidthUtilizationAcc));
 
 	for (i = 0; i < NUM_XGMI_LINKS; i++) {
 		gpu_metrics->xgmi_read_data_acc[i] =
-			SMUQ10_ROUND(metrics->XgmiReadDataSizeAcc[i]);
+			SMUQ10_ROUND(GET_METRIC_FIELD(XgmiReadDataSizeAcc)[i]);
 		gpu_metrics->xgmi_write_data_acc[i] =
-			SMUQ10_ROUND(metrics->XgmiWriteDataSizeAcc[i]);
+			SMUQ10_ROUND(GET_METRIC_FIELD(XgmiWriteDataSizeAcc)[i]);
+	}
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		inst = GET_INST(JPEG, i);
+		for (j = 0; j < adev->jpeg.num_jpeg_rings; ++j) {
+			gpu_metrics->jpeg_activity[(i * adev->jpeg.num_jpeg_rings) + j] =
+				SMUQ10_ROUND(GET_METRIC_FIELD(JpegBusy)
+				[(inst * adev->jpeg.num_jpeg_rings) + j]);
+		}
 	}
 
-	gpu_metrics->xgmi_link_width = SMUQ10_ROUND(metrics->XgmiWidth);
-	gpu_metrics->xgmi_link_speed = SMUQ10_ROUND(metrics->XgmiBitrate);
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		inst = GET_INST(VCN, i);
+		gpu_metrics->vcn_activity[i] =
+			SMUQ10_ROUND(GET_METRIC_FIELD(VcnBusy)[inst]);
+	}
 
-	gpu_metrics->firmware_timestamp = metrics->Timestamp;
+	gpu_metrics->xgmi_link_width = SMUQ10_ROUND(GET_METRIC_FIELD(XgmiWidth));
+	gpu_metrics->xgmi_link_speed = SMUQ10_ROUND(GET_METRIC_FIELD(XgmiBitrate));
+
+	gpu_metrics->firmware_timestamp = GET_METRIC_FIELD(Timestamp);
 
 	*table = (void *)gpu_metrics;
-	kfree(metrics);
+	kfree(metrics_x);
 
 	return sizeof(*gpu_metrics);
 }
@@ -2585,13 +2622,20 @@ static bool mca_gfx_smu_bank_is_valid(const struct mca_ras_info *mca_ras, struct
 static bool mca_smu_bank_is_valid(const struct mca_ras_info *mca_ras, struct amdgpu_device *adev,
 				  enum amdgpu_mca_error_type type, struct mca_bank_entry *entry)
 {
+	struct smu_context *smu = adev->powerplay.pp_handle;
 	uint32_t errcode, instlo;
 
 	instlo = REG_GET_FIELD(entry->regs[MCA_REG_IDX_IPID], MCMP1_IPIDT0, InstanceIdLo);
 	if (instlo != 0x03b30400)
 		return false;
 
-	errcode = REG_GET_FIELD(entry->regs[MCA_REG_IDX_STATUS], MCMP1_STATUST0, ErrorCode);
+	if (!(adev->flags & AMD_IS_APU) && smu->smc_fw_version >= 0x00555600) {
+		errcode = MCA_REG__SYND__ERRORINFORMATION(entry->regs[MCA_REG_IDX_SYND]);
+		errcode &= 0xff;
+	} else {
+		errcode = REG_GET_FIELD(entry->regs[MCA_REG_IDX_STATUS], MCMP1_STATUST0, ErrorCode);
+	}
+
 	return mca_smu_check_error_code(adev, mca_ras, errcode);
 }
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
index 03b38c3a9968..94ccdbfd7090 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
@@ -246,11 +246,20 @@ static int smu_v14_0_0_get_smu_metrics_data(struct smu_context *smu,
 		*value = 0;
 		break;
 	case METRICS_AVERAGE_UCLK:
-		*value = 0;
+		*value = metrics->MemclkFrequency;
 		break;
 	case METRICS_AVERAGE_FCLK:
 		*value = metrics->FclkFrequency;
 		break;
+	case METRICS_AVERAGE_VPECLK:
+		*value = metrics->VpeclkFrequency;
+		break;
+	case METRICS_AVERAGE_IPUCLK:
+		*value = metrics->IpuclkFrequency;
+		break;
+	case METRICS_AVERAGE_MPIPUCLK:
+		*value = metrics->MpipuclkFrequency;
+		break;
 	case METRICS_AVERAGE_GFXACTIVITY:
 		*value = metrics->GfxActivity / 100;
 		break;
@@ -270,8 +279,26 @@ static int smu_v14_0_0_get_smu_metrics_data(struct smu_context *smu,
 		*value = metrics->SocTemperature / 100 *
 		SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 		break;
-	case METRICS_THROTTLER_STATUS:
-		*value = 0;
+	case METRICS_THROTTLER_RESIDENCY_PROCHOT:
+		*value = metrics->ThrottleResidency_PROCHOT;
+		break;
+	case METRICS_THROTTLER_RESIDENCY_SPL:
+		*value = metrics->ThrottleResidency_SPL;
+		break;
+	case METRICS_THROTTLER_RESIDENCY_FPPT:
+		*value = metrics->ThrottleResidency_FPPT;
+		break;
+	case METRICS_THROTTLER_RESIDENCY_SPPT:
+		*value = metrics->ThrottleResidency_SPPT;
+		break;
+	case METRICS_THROTTLER_RESIDENCY_THM_CORE:
+		*value = metrics->ThrottleResidency_THM_CORE;
+		break;
+	case METRICS_THROTTLER_RESIDENCY_THM_GFX:
+		*value = metrics->ThrottleResidency_THM_GFX;
+		break;
+	case METRICS_THROTTLER_RESIDENCY_THM_SOC:
+		*value = metrics->ThrottleResidency_THM_SOC;
 		break;
 	case METRICS_VOLTAGE_VDDGFX:
 		*value = 0;
@@ -498,6 +525,8 @@ static ssize_t smu_v14_0_0_get_gpu_metrics(struct smu_context *smu,
 		sizeof(uint16_t) * 16);
 	gpu_metrics->average_dram_reads = metrics.DRAMReads;
 	gpu_metrics->average_dram_writes = metrics.DRAMWrites;
+	gpu_metrics->average_ipu_reads = metrics.IpuReads;
+	gpu_metrics->average_ipu_writes = metrics.IpuWrites;
 
 	gpu_metrics->average_socket_power = metrics.SocketPower;
 	gpu_metrics->average_ipu_power = metrics.IpuPower;
@@ -505,6 +534,7 @@ static ssize_t smu_v14_0_0_get_gpu_metrics(struct smu_context *smu,
 	gpu_metrics->average_gfx_power = metrics.GfxPower;
 	gpu_metrics->average_dgpu_power = metrics.dGpuPower;
 	gpu_metrics->average_all_core_power = metrics.AllCorePower;
+	gpu_metrics->average_sys_power = metrics.Psys;
 	memcpy(&gpu_metrics->average_core_power[0],
 		&metrics.CorePower[0],
 		sizeof(uint16_t) * 16);
@@ -515,6 +545,8 @@ static ssize_t smu_v14_0_0_get_gpu_metrics(struct smu_context *smu,
 	gpu_metrics->average_fclk_frequency = metrics.FclkFrequency;
 	gpu_metrics->average_vclk_frequency = metrics.VclkFrequency;
 	gpu_metrics->average_ipuclk_frequency = metrics.IpuclkFrequency;
+	gpu_metrics->average_uclk_frequency = metrics.MemclkFrequency;
+	gpu_metrics->average_mpipu_frequency = metrics.MpipuclkFrequency;
 
 	memcpy(&gpu_metrics->current_coreclk[0],
 		&metrics.CoreFrequency[0],
@@ -522,6 +554,14 @@ static ssize_t smu_v14_0_0_get_gpu_metrics(struct smu_context *smu,
 	gpu_metrics->current_core_maxfreq = metrics.InfrastructureCpuMaxFreq;
 	gpu_metrics->current_gfx_maxfreq = metrics.InfrastructureGfxMaxFreq;
 
+	gpu_metrics->throttle_residency_prochot = metrics.ThrottleResidency_PROCHOT;
+	gpu_metrics->throttle_residency_spl = metrics.ThrottleResidency_SPL;
+	gpu_metrics->throttle_residency_fppt = metrics.ThrottleResidency_FPPT;
+	gpu_metrics->throttle_residency_sppt = metrics.ThrottleResidency_SPPT;
+	gpu_metrics->throttle_residency_thm_core = metrics.ThrottleResidency_THM_CORE;
+	gpu_metrics->throttle_residency_thm_gfx = metrics.ThrottleResidency_THM_GFX;
+	gpu_metrics->throttle_residency_thm_soc = metrics.ThrottleResidency_THM_SOC;
+
 	gpu_metrics->time_filter_alphavalue = metrics.FilterAlphaValue;
 	gpu_metrics->system_clock_counter = ktime_get_boottime_ns();
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index 001a5cf09657..00cd615bbcdc 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -989,6 +989,9 @@ void smu_cmn_init_soft_gpu_metrics(void *table, uint8_t frev, uint8_t crev)
 	case METRICS_VERSION(1, 4):
 		structure_size = sizeof(struct gpu_metrics_v1_4);
 		break;
+	case METRICS_VERSION(1, 5):
+		structure_size = sizeof(struct gpu_metrics_v1_5);
+		break;
 	case METRICS_VERSION(2, 0):
 		structure_size = sizeof(struct gpu_metrics_v2_0);
 		break;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h b/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h
index 80b3c3efc006..64766ac69c53 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h
@@ -97,6 +97,7 @@
 #define smu_get_default_config_table_settings(smu, config_table)	smu_ppt_funcs(get_default_config_table_settings, -EOPNOTSUPP, smu, config_table)
 #define smu_set_config_table(smu, config_table)				smu_ppt_funcs(set_config_table, -EOPNOTSUPP, smu, config_table)
 #define smu_init_pptable_microcode(smu)					smu_ppt_funcs(init_pptable_microcode, 0, smu)
+#define smu_notify_rlc_state(smu, en)					smu_ppt_funcs(notify_rlc_state, 0, smu, en)
 
 #endif
 #endif
diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h
index 2aee32344f4a..772f3b049c16 100644
--- a/drivers/gpu/drm/ast/ast_drv.h
+++ b/drivers/gpu/drm/ast/ast_drv.h
@@ -174,6 +174,17 @@ to_ast_sil164_connector(struct drm_connector *connector)
 	return container_of(connector, struct ast_sil164_connector, base);
 }
 
+struct ast_bmc_connector {
+	struct drm_connector base;
+	struct drm_connector *physical_connector;
+};
+
+static inline struct ast_bmc_connector *
+to_ast_bmc_connector(struct drm_connector *connector)
+{
+	return container_of(connector, struct ast_bmc_connector, base);
+}
+
 /*
  * Device
  */
@@ -218,7 +229,7 @@ struct ast_device {
 		} astdp;
 		struct {
 			struct drm_encoder encoder;
-			struct drm_connector connector;
+			struct ast_bmc_connector bmc_connector;
 		} bmc;
 	} output;
 
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index cb9614984285..c20534d0ef7c 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -1767,6 +1767,30 @@ static const struct drm_encoder_funcs ast_bmc_encoder_funcs = {
 	.destroy = drm_encoder_cleanup,
 };
 
+static int ast_bmc_connector_helper_detect_ctx(struct drm_connector *connector,
+					       struct drm_modeset_acquire_ctx *ctx,
+					       bool force)
+{
+	struct ast_bmc_connector *bmc_connector = to_ast_bmc_connector(connector);
+	struct drm_connector *physical_connector = bmc_connector->physical_connector;
+
+	/*
+	 * Most user-space compositors cannot handle more than one connected
+	 * connector per CRTC. Hence, we only mark the BMC as connected if the
+	 * physical connector is disconnected. If the physical connector's status
+	 * is connected or unknown, the BMC remains disconnected. This has no
+	 * effect on the output of the BMC.
+	 *
+	 * FIXME: Remove this logic once user-space compositors can handle more
+	 *        than one connector per CRTC. The BMC should always be connected.
+	 */
+
+	if (physical_connector && physical_connector->status == connector_status_disconnected)
+		return connector_status_connected;
+
+	return connector_status_disconnected;
+}
+
 static int ast_bmc_connector_helper_get_modes(struct drm_connector *connector)
 {
 	return drm_add_modes_noedid(connector, 4096, 4096);
@@ -1774,6 +1798,7 @@ static int ast_bmc_connector_helper_get_modes(struct drm_connector *connector)
 
 static const struct drm_connector_helper_funcs ast_bmc_connector_helper_funcs = {
 	.get_modes = ast_bmc_connector_helper_get_modes,
+	.detect_ctx = ast_bmc_connector_helper_detect_ctx,
 };
 
 static const struct drm_connector_funcs ast_bmc_connector_funcs = {
@@ -1784,12 +1809,33 @@ static const struct drm_connector_funcs ast_bmc_connector_funcs = {
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 };
 
-static int ast_bmc_output_init(struct ast_device *ast)
+static int ast_bmc_connector_init(struct drm_device *dev,
+				  struct ast_bmc_connector *bmc_connector,
+				  struct drm_connector *physical_connector)
+{
+	struct drm_connector *connector = &bmc_connector->base;
+	int ret;
+
+	ret = drm_connector_init(dev, connector, &ast_bmc_connector_funcs,
+				 DRM_MODE_CONNECTOR_VIRTUAL);
+	if (ret)
+		return ret;
+
+	drm_connector_helper_add(connector, &ast_bmc_connector_helper_funcs);
+
+	bmc_connector->physical_connector = physical_connector;
+
+	return 0;
+}
+
+static int ast_bmc_output_init(struct ast_device *ast,
+			       struct drm_connector *physical_connector)
 {
 	struct drm_device *dev = &ast->base;
 	struct drm_crtc *crtc = &ast->crtc;
 	struct drm_encoder *encoder = &ast->output.bmc.encoder;
-	struct drm_connector *connector = &ast->output.bmc.connector;
+	struct ast_bmc_connector *bmc_connector = &ast->output.bmc.bmc_connector;
+	struct drm_connector *connector = &bmc_connector->base;
 	int ret;
 
 	ret = drm_encoder_init(dev, encoder,
@@ -1799,13 +1845,10 @@ static int ast_bmc_output_init(struct ast_device *ast)
 		return ret;
 	encoder->possible_crtcs = drm_crtc_mask(crtc);
 
-	ret = drm_connector_init(dev, connector, &ast_bmc_connector_funcs,
-				 DRM_MODE_CONNECTOR_VIRTUAL);
+	ret = ast_bmc_connector_init(dev, bmc_connector, physical_connector);
 	if (ret)
 		return ret;
 
-	drm_connector_helper_add(connector, &ast_bmc_connector_helper_funcs);
-
 	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret)
 		return ret;
@@ -1864,6 +1907,7 @@ static const struct drm_mode_config_funcs ast_mode_config_funcs = {
 int ast_mode_config_init(struct ast_device *ast)
 {
 	struct drm_device *dev = &ast->base;
+	struct drm_connector *physical_connector = NULL;
 	int ret;
 
 	ret = drmm_mode_config_init(dev);
@@ -1904,23 +1948,27 @@ int ast_mode_config_init(struct ast_device *ast)
 		ret = ast_vga_output_init(ast);
 		if (ret)
 			return ret;
+		physical_connector = &ast->output.vga.vga_connector.base;
 	}
 	if (ast->tx_chip_types & AST_TX_SIL164_BIT) {
 		ret = ast_sil164_output_init(ast);
 		if (ret)
 			return ret;
+		physical_connector = &ast->output.sil164.sil164_connector.base;
 	}
 	if (ast->tx_chip_types & AST_TX_DP501_BIT) {
 		ret = ast_dp501_output_init(ast);
 		if (ret)
 			return ret;
+		physical_connector = &ast->output.dp501.connector;
 	}
 	if (ast->tx_chip_types & AST_TX_ASTDP_BIT) {
 		ret = ast_astdp_output_init(ast);
 		if (ret)
 			return ret;
+		physical_connector = &ast->output.astdp.connector;
 	}
-	ret = ast_bmc_output_init(ast);
+	ret = ast_bmc_output_init(ast, physical_connector);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig
index ba82a1142adf..3e6a4e2044c0 100644
--- a/drivers/gpu/drm/bridge/Kconfig
+++ b/drivers/gpu/drm/bridge/Kconfig
@@ -313,6 +313,7 @@ config DRM_TOSHIBA_TC358768
 	select REGMAP_I2C
 	select DRM_PANEL
 	select DRM_MIPI_DSI
+	select VIDEOMODE_HELPERS
 	help
 	  Toshiba TC358768AXBG/TC358778XBG DSI bridge chip driver.
 
diff --git a/drivers/gpu/drm/bridge/panel.c b/drivers/gpu/drm/bridge/panel.c
index e48823a4f1ed..7f41525f7a6e 100644
--- a/drivers/gpu/drm/bridge/panel.c
+++ b/drivers/gpu/drm/bridge/panel.c
@@ -4,8 +4,6 @@
  * Copyright (C) 2017 Broadcom
  */
 
-#include <linux/device.h>
-
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_bridge.h>
 #include <drm/drm_connector.h>
@@ -21,7 +19,6 @@ struct panel_bridge {
 	struct drm_bridge bridge;
 	struct drm_connector connector;
 	struct drm_panel *panel;
-	struct device_link *link;
 	u32 connector_type;
 };
 
@@ -63,24 +60,13 @@ static int panel_bridge_attach(struct drm_bridge *bridge,
 {
 	struct panel_bridge *panel_bridge = drm_bridge_to_panel_bridge(bridge);
 	struct drm_connector *connector = &panel_bridge->connector;
-	struct drm_panel *panel = panel_bridge->panel;
-	struct drm_device *drm_dev = bridge->dev;
 	int ret;
 
-	panel_bridge->link = device_link_add(drm_dev->dev, panel->dev,
-					     DL_FLAG_STATELESS);
-	if (!panel_bridge->link) {
-		DRM_ERROR("Failed to add device link between %s and %s\n",
-			  dev_name(drm_dev->dev), dev_name(panel->dev));
-		return -EINVAL;
-	}
-
 	if (flags & DRM_BRIDGE_ATTACH_NO_CONNECTOR)
 		return 0;
 
 	if (!bridge->encoder) {
 		DRM_ERROR("Missing encoder\n");
-		device_link_del(panel_bridge->link);
 		return -ENODEV;
 	}
 
@@ -92,7 +78,6 @@ static int panel_bridge_attach(struct drm_bridge *bridge,
 				 panel_bridge->connector_type);
 	if (ret) {
 		DRM_ERROR("Failed to initialize connector\n");
-		device_link_del(panel_bridge->link);
 		return ret;
 	}
 
@@ -115,8 +100,6 @@ static void panel_bridge_detach(struct drm_bridge *bridge)
 	struct panel_bridge *panel_bridge = drm_bridge_to_panel_bridge(bridge);
 	struct drm_connector *connector = &panel_bridge->connector;
 
-	device_link_del(panel_bridge->link);
-
 	/*
 	 * Cleanup the connector if we know it was initialized.
 	 *
diff --git a/drivers/gpu/drm/bridge/parade-ps8640.c b/drivers/gpu/drm/bridge/parade-ps8640.c
index 8161b1a1a4b1..541e4f5afc4c 100644
--- a/drivers/gpu/drm/bridge/parade-ps8640.c
+++ b/drivers/gpu/drm/bridge/parade-ps8640.c
@@ -210,7 +210,7 @@ static ssize_t ps8640_aux_transfer_msg(struct drm_dp_aux *aux,
 	struct ps8640 *ps_bridge = aux_to_ps8640(aux);
 	struct regmap *map = ps_bridge->regmap[PAGE0_DP_CNTL];
 	struct device *dev = &ps_bridge->page[PAGE0_DP_CNTL]->dev;
-	unsigned int len = msg->size;
+	size_t len = msg->size;
 	unsigned int data;
 	unsigned int base;
 	int ret;
@@ -330,11 +330,12 @@ static ssize_t ps8640_aux_transfer_msg(struct drm_dp_aux *aux,
 				return ret;
 			}
 
-			buf[i] = data;
+			if (i < msg->size)
+				buf[i] = data;
 		}
 	}
 
-	return len;
+	return min(len, msg->size);
 }
 
 static ssize_t ps8640_aux_transfer(struct drm_dp_aux *aux,
diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
index c45c07840f64..b5464199b633 100644
--- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c
+++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
@@ -527,6 +527,7 @@ static ssize_t ti_sn_aux_transfer(struct drm_dp_aux *aux,
 	u32 request_val = AUX_CMD_REQ(msg->request);
 	u8 *buf = msg->buffer;
 	unsigned int len = msg->size;
+	unsigned int short_len;
 	unsigned int val;
 	int ret;
 	u8 addr_len[SN_AUX_LENGTH_REG + 1 - SN_AUX_ADDR_19_16_REG];
@@ -600,7 +601,8 @@ static ssize_t ti_sn_aux_transfer(struct drm_dp_aux *aux,
 	}
 
 	if (val & AUX_IRQ_STATUS_AUX_SHORT) {
-		ret = regmap_read(pdata->regmap, SN_AUX_LENGTH_REG, &len);
+		ret = regmap_read(pdata->regmap, SN_AUX_LENGTH_REG, &short_len);
+		len = min(len, short_len);
 		if (ret)
 			goto exit;
 	} else if (val & AUX_IRQ_STATUS_NAT_I2C_FAIL) {
diff --git a/drivers/gpu/drm/ci/xfails/requirements.txt b/drivers/gpu/drm/ci/xfails/requirements.txt
index d8856d1581fd..e9994c9db799 100644
--- a/drivers/gpu/drm/ci/xfails/requirements.txt
+++ b/drivers/gpu/drm/ci/xfails/requirements.txt
@@ -5,7 +5,7 @@ termcolor==2.3.0
 certifi==2023.7.22
 charset-normalizer==3.2.0
 idna==3.4
-pip==23.2.1
+pip==23.3
 python-gitlab==3.15.0
 requests==2.31.0
 requests-toolbelt==1.0.0
@@ -13,5 +13,5 @@ ruamel.yaml==0.17.32
 ruamel.yaml.clib==0.2.7
 setuptools==68.0.0
 tenacity==8.2.3
-urllib3==2.0.4
-wheel==0.41.1
\ No newline at end of file
+urllib3==2.0.7
+wheel==0.41.1
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 2444fc33dd7c..68ffcc0b00dc 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -2012,7 +2012,7 @@ int drm_atomic_helper_commit(struct drm_device *dev,
 			return ret;
 
 		drm_atomic_helper_async_commit(dev, state);
-		drm_atomic_helper_cleanup_planes(dev, state);
+		drm_atomic_helper_unprepare_planes(dev, state);
 
 		return 0;
 	}
@@ -2072,7 +2072,7 @@ int drm_atomic_helper_commit(struct drm_device *dev,
 	return 0;
 
 err:
-	drm_atomic_helper_cleanup_planes(dev, state);
+	drm_atomic_helper_unprepare_planes(dev, state);
 	return ret;
 }
 EXPORT_SYMBOL(drm_atomic_helper_commit);
@@ -2650,6 +2650,39 @@ fail_prepare_fb:
 }
 EXPORT_SYMBOL(drm_atomic_helper_prepare_planes);
 
+/**
+ * drm_atomic_helper_unprepare_planes - release plane resources on aborts
+ * @dev: DRM device
+ * @state: atomic state object with old state structures
+ *
+ * This function cleans up plane state, specifically framebuffers, from the
+ * atomic state. It undoes the effects of drm_atomic_helper_prepare_planes()
+ * when aborting an atomic commit. For cleaning up after a successful commit
+ * use drm_atomic_helper_cleanup_planes().
+ */
+void drm_atomic_helper_unprepare_planes(struct drm_device *dev,
+					struct drm_atomic_state *state)
+{
+	struct drm_plane *plane;
+	struct drm_plane_state *new_plane_state;
+	int i;
+
+	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
+		const struct drm_plane_helper_funcs *funcs = plane->helper_private;
+
+		if (funcs->end_fb_access)
+			funcs->end_fb_access(plane, new_plane_state);
+	}
+
+	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
+		const struct drm_plane_helper_funcs *funcs = plane->helper_private;
+
+		if (funcs->cleanup_fb)
+			funcs->cleanup_fb(plane, new_plane_state);
+	}
+}
+EXPORT_SYMBOL(drm_atomic_helper_unprepare_planes);
+
 static bool plane_crtc_active(const struct drm_plane_state *state)
 {
 	return state->crtc && state->crtc->state->active;
@@ -2784,6 +2817,17 @@ void drm_atomic_helper_commit_planes(struct drm_device *dev,
 
 		funcs->atomic_flush(crtc, old_state);
 	}
+
+	/*
+	 * Signal end of framebuffer access here before hw_done. After hw_done,
+	 * a later commit might have already released the plane state.
+	 */
+	for_each_old_plane_in_state(old_state, plane, old_plane_state, i) {
+		const struct drm_plane_helper_funcs *funcs = plane->helper_private;
+
+		if (funcs->end_fb_access)
+			funcs->end_fb_access(plane, old_plane_state);
+	}
 }
 EXPORT_SYMBOL(drm_atomic_helper_commit_planes);
 
@@ -2911,40 +2955,22 @@ EXPORT_SYMBOL(drm_atomic_helper_disable_planes_on_crtc);
  * configuration. Hence the old configuration must be perserved in @old_state to
  * be able to call this function.
  *
- * This function must also be called on the new state when the atomic update
- * fails at any point after calling drm_atomic_helper_prepare_planes().
+ * This function may not be called on the new state when the atomic update
+ * fails at any point after calling drm_atomic_helper_prepare_planes(). Use
+ * drm_atomic_helper_unprepare_planes() in this case.
  */
 void drm_atomic_helper_cleanup_planes(struct drm_device *dev,
 				      struct drm_atomic_state *old_state)
 {
 	struct drm_plane *plane;
-	struct drm_plane_state *old_plane_state, *new_plane_state;
+	struct drm_plane_state *old_plane_state;
 	int i;
 
-	for_each_oldnew_plane_in_state(old_state, plane, old_plane_state, new_plane_state, i) {
+	for_each_old_plane_in_state(old_state, plane, old_plane_state, i) {
 		const struct drm_plane_helper_funcs *funcs = plane->helper_private;
 
-		if (funcs->end_fb_access)
-			funcs->end_fb_access(plane, new_plane_state);
-	}
-
-	for_each_oldnew_plane_in_state(old_state, plane, old_plane_state, new_plane_state, i) {
-		const struct drm_plane_helper_funcs *funcs;
-		struct drm_plane_state *plane_state;
-
-		/*
-		 * This might be called before swapping when commit is aborted,
-		 * in which case we have to cleanup the new state.
-		 */
-		if (old_plane_state == plane->state)
-			plane_state = new_plane_state;
-		else
-			plane_state = old_plane_state;
-
-		funcs = plane->helper_private;
-
 		if (funcs->cleanup_fb)
-			funcs->cleanup_fb(plane, plane_state);
+			funcs->cleanup_fb(plane, old_plane_state);
 	}
 }
 EXPORT_SYMBOL(drm_atomic_helper_cleanup_planes);
diff --git a/drivers/gpu/drm/drm_auth.c b/drivers/gpu/drm/drm_auth.c
index 2ed2585ded37..6899b3dc1f12 100644
--- a/drivers/gpu/drm/drm_auth.c
+++ b/drivers/gpu/drm/drm_auth.c
@@ -236,7 +236,7 @@ static int
 drm_master_check_perm(struct drm_device *dev, struct drm_file *file_priv)
 {
 	if (file_priv->was_master &&
-	    rcu_access_pointer(file_priv->pid) == task_pid(current))
+	    rcu_access_pointer(file_priv->pid) == task_tgid(current))
 		return 0;
 
 	if (!capable(CAP_SYS_ADMIN))
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index df9bf3c9206e..cb90e70d85e8 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -715,8 +715,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data,
 	struct drm_mode_set set;
 	uint32_t __user *set_connectors_ptr;
 	struct drm_modeset_acquire_ctx ctx;
-	int ret;
-	int i;
+	int ret, i, num_connectors = 0;
 
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EOPNOTSUPP;
@@ -871,6 +870,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data,
 					connector->name);
 
 			connector_set[i] = connector;
+			num_connectors++;
 		}
 	}
 
@@ -879,7 +879,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data,
 	set.y = crtc_req->y;
 	set.mode = mode;
 	set.connectors = connector_set;
-	set.num_connectors = crtc_req->count_connectors;
+	set.num_connectors = num_connectors;
 	set.fb = fb;
 
 	if (drm_drv_uses_atomic_modeset(dev))
@@ -892,7 +892,7 @@ out:
 		drm_framebuffer_put(fb);
 
 	if (connector_set) {
-		for (i = 0; i < crtc_req->count_connectors; i++) {
+		for (i = 0; i < num_connectors; i++) {
 			if (connector_set[i])
 				drm_connector_put(connector_set[i]);
 		}
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 39db08f803ea..3b4065099872 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -2309,7 +2309,8 @@ int drm_edid_override_connector_update(struct drm_connector *connector)
 
 	override = drm_edid_override_get(connector);
 	if (override) {
-		num_modes = drm_edid_connector_update(connector, override);
+		if (drm_edid_connector_update(connector, override) == 0)
+			num_modes = drm_edid_connector_add_modes(connector);
 
 		drm_edid_free(override);
 
diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c
index 08c088319652..b80d4e1cc9b7 100644
--- a/drivers/gpu/drm/drm_gpuvm.c
+++ b/drivers/gpu/drm/drm_gpuvm.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0 OR MIT
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Copyright (c) 2022 Red Hat.
  *
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index ac9a406250c5..893f52ee4926 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -2617,8 +2617,7 @@ void drm_mode_convert_to_umode(struct drm_mode_modeinfo *out,
 		break;
 	}
 
-	strncpy(out->name, in->name, DRM_DISPLAY_MODE_LEN);
-	out->name[DRM_DISPLAY_MODE_LEN-1] = 0;
+	strscpy_pad(out->name, in->name, sizeof(out->name));
 }
 
 /**
@@ -2659,8 +2658,7 @@ int drm_mode_convert_umode(struct drm_device *dev,
 	 * useful for the kernel->userspace direction anyway.
 	 */
 	out->type = in->type & DRM_MODE_TYPE_ALL;
-	strncpy(out->name, in->name, DRM_DISPLAY_MODE_LEN);
-	out->name[DRM_DISPLAY_MODE_LEN-1] = 0;
+	strscpy_pad(out->name, in->name, sizeof(out->name));
 
 	/* Clearing picture aspect ratio bits from out flags,
 	 * as the aspect-ratio information is not stored in
diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
index d5c15292ae93..3d92f66e550c 100644
--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
+++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
@@ -336,6 +336,12 @@ static const struct dmi_system_id orientation_data[] = {
 		  DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "IdeaPad Duet 3 10IGL5"),
 		},
 		.driver_data = (void *)&lcd1200x1920_rightside_up,
+	}, {	/* Lenovo Legion Go 8APU1 */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Legion Go 8APU1"),
+		},
+		.driver_data = (void *)&lcd1600x2560_leftside_up,
 	}, {	/* Lenovo Yoga Book X90F / X90L */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Intel Corporation"),
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 63b709a67471..834a5e28abbe 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -278,7 +278,7 @@ void drm_gem_dmabuf_release(struct dma_buf *dma_buf)
 }
 EXPORT_SYMBOL(drm_gem_dmabuf_release);
 
-/*
+/**
  * drm_gem_prime_fd_to_handle - PRIME import function for GEM drivers
  * @dev: drm_device to import into
  * @file_priv: drm file-private structure
@@ -292,9 +292,9 @@ EXPORT_SYMBOL(drm_gem_dmabuf_release);
  *
  * Returns 0 on success or a negative error code on failure.
  */
-static int drm_gem_prime_fd_to_handle(struct drm_device *dev,
-				      struct drm_file *file_priv, int prime_fd,
-				      uint32_t *handle)
+int drm_gem_prime_fd_to_handle(struct drm_device *dev,
+			       struct drm_file *file_priv, int prime_fd,
+			       uint32_t *handle)
 {
 	struct dma_buf *dma_buf;
 	struct drm_gem_object *obj;
@@ -360,6 +360,7 @@ out_put:
 	dma_buf_put(dma_buf);
 	return ret;
 }
+EXPORT_SYMBOL(drm_gem_prime_fd_to_handle);
 
 int drm_prime_fd_to_handle_ioctl(struct drm_device *dev, void *data,
 				 struct drm_file *file_priv)
@@ -408,7 +409,7 @@ static struct dma_buf *export_and_register_object(struct drm_device *dev,
 	return dmabuf;
 }
 
-/*
+/**
  * drm_gem_prime_handle_to_fd - PRIME export function for GEM drivers
  * @dev: dev to export the buffer from
  * @file_priv: drm file-private structure
@@ -421,10 +422,10 @@ static struct dma_buf *export_and_register_object(struct drm_device *dev,
  * The actual exporting from GEM object to a dma-buf is done through the
  * &drm_gem_object_funcs.export callback.
  */
-static int drm_gem_prime_handle_to_fd(struct drm_device *dev,
-				      struct drm_file *file_priv, uint32_t handle,
-				      uint32_t flags,
-				      int *prime_fd)
+int drm_gem_prime_handle_to_fd(struct drm_device *dev,
+			       struct drm_file *file_priv, uint32_t handle,
+			       uint32_t flags,
+			       int *prime_fd)
 {
 	struct drm_gem_object *obj;
 	int ret = 0;
@@ -506,6 +507,7 @@ out_unlock:
 
 	return ret;
 }
+EXPORT_SYMBOL(drm_gem_prime_handle_to_fd);
 
 int drm_prime_handle_to_fd_ioctl(struct drm_device *dev, void *data,
 				 struct drm_file *file_priv)
@@ -864,9 +866,9 @@ EXPORT_SYMBOL(drm_prime_get_contiguous_size);
  * @obj: GEM object to export
  * @flags: flags like DRM_CLOEXEC and DRM_RDWR
  *
- * This is the implementation of the &drm_gem_object_funcs.export functions
- * for GEM drivers using the PRIME helpers. It is used as the default for
- * drivers that do not set their own.
+ * This is the implementation of the &drm_gem_object_funcs.export functions for GEM drivers
+ * using the PRIME helpers. It is used as the default in
+ * drm_gem_prime_handle_to_fd().
  */
 struct dma_buf *drm_gem_prime_export(struct drm_gem_object *obj,
 				     int flags)
@@ -962,9 +964,10 @@ EXPORT_SYMBOL(drm_gem_prime_import_dev);
  * @dev: drm_device to import into
  * @dma_buf: dma-buf object to import
  *
- * This is the implementation of the gem_prime_import functions for GEM
- * drivers using the PRIME helpers. It is the default for drivers that do
- * not set their own &drm_driver.gem_prime_import.
+ * This is the implementation of the gem_prime_import functions for GEM drivers
+ * using the PRIME helpers. Drivers can use this as their
+ * &drm_driver.gem_prime_import implementation. It is used as the default
+ * implementation in drm_gem_prime_fd_to_handle().
  *
  * Drivers must arrange to call drm_prime_gem_destroy() from their
  * &drm_gem_object_funcs.free hook when using this function.
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index 01da6789d044..b9cc62982196 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -1365,7 +1365,7 @@ static void syncobj_eventfd_entry_fence_func(struct dma_fence *fence,
 	struct syncobj_eventfd_entry *entry =
 		container_of(cb, struct syncobj_eventfd_entry, fence_cb);
 
-	eventfd_signal(entry->ev_fd_ctx, 1);
+	eventfd_signal(entry->ev_fd_ctx);
 	syncobj_eventfd_entry_free(entry);
 }
 
@@ -1388,13 +1388,13 @@ syncobj_eventfd_entry_func(struct drm_syncobj *syncobj,
 	entry->fence = fence;
 
 	if (entry->flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE) {
-		eventfd_signal(entry->ev_fd_ctx, 1);
+		eventfd_signal(entry->ev_fd_ctx);
 		syncobj_eventfd_entry_free(entry);
 	} else {
 		ret = dma_fence_add_callback(fence, &entry->fence_cb,
 					     syncobj_eventfd_entry_fence_func);
 		if (ret == -ENOENT) {
-			eventfd_signal(entry->ev_fd_ctx, 1);
+			eventfd_signal(entry->ev_fd_ctx);
 			syncobj_eventfd_entry_free(entry);
 		}
 	}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c
index a971590b8132..e2c7373f20c6 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dma.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c
@@ -107,18 +107,16 @@ int exynos_drm_register_dma(struct drm_device *drm, struct device *dev,
 		return 0;
 
 	if (!priv->mapping) {
-		void *mapping;
+		void *mapping = NULL;
 
 		if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU))
 			mapping = arm_iommu_create_mapping(&platform_bus_type,
 				EXYNOS_DEV_ADDR_START, EXYNOS_DEV_ADDR_SIZE);
 		else if (IS_ENABLED(CONFIG_IOMMU_DMA))
 			mapping = iommu_get_domain_for_dev(priv->dma_dev);
-		else
-			mapping = ERR_PTR(-ENODEV);
 
-		if (IS_ERR(mapping))
-			return PTR_ERR(mapping);
+		if (!mapping)
+			return -ENODEV;
 		priv->mapping = mapping;
 	}
 
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index f3aaa4ea3e68..dd9903eab563 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -1861,6 +1861,8 @@ static int hdmi_bind(struct device *dev, struct device *master, void *data)
 		return ret;
 
 	crtc = exynos_drm_crtc_get_by_type(drm_dev, EXYNOS_DISPLAY_TYPE_HDMI);
+	if (IS_ERR(crtc))
+		return PTR_ERR(crtc);
 	crtc->pipe_clk = &hdata->phy_clk;
 
 	ret = hdmi_create_connector(encoder);
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index c4585e445198..67143a0f5189 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -1440,6 +1440,13 @@ static void gen11_dsi_post_disable(struct intel_atomic_state *state,
 static enum drm_mode_status gen11_dsi_mode_valid(struct drm_connector *connector,
 						 struct drm_display_mode *mode)
 {
+	struct drm_i915_private *i915 = to_i915(connector->dev);
+	enum drm_mode_status status;
+
+	status = intel_cpu_transcoder_mode_valid(i915, mode);
+	if (status != MODE_OK)
+		return status;
+
 	/* FIXME: DSC? */
 	return intel_dsi_mode_valid(connector, mode);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c
index 913e5d230a4d..6f6b348b8a40 100644
--- a/drivers/gpu/drm/i915/display/intel_crt.c
+++ b/drivers/gpu/drm/i915/display/intel_crt.c
@@ -348,8 +348,13 @@ intel_crt_mode_valid(struct drm_connector *connector,
 	struct drm_device *dev = connector->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	int max_dotclk = dev_priv->max_dotclk_freq;
+	enum drm_mode_status status;
 	int max_clock;
 
+	status = intel_cpu_transcoder_mode_valid(dev_priv, mode);
+	if (status != MODE_OK)
+		return status;
+
 	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return MODE_NO_DBLESCAN;
 
diff --git a/drivers/gpu/drm/i915/display/intel_cx0_phy.c b/drivers/gpu/drm/i915/display/intel_cx0_phy.c
index d414f6b7f993..ccf225afeb2a 100644
--- a/drivers/gpu/drm/i915/display/intel_cx0_phy.c
+++ b/drivers/gpu/drm/i915/display/intel_cx0_phy.c
@@ -2465,7 +2465,8 @@ static void intel_program_port_clock_ctl(struct intel_encoder *encoder,
 
 	val |= XELPDP_FORWARD_CLOCK_UNGATE;
 
-	if (is_hdmi_frl(crtc_state->port_clock))
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI) &&
+	    is_hdmi_frl(crtc_state->port_clock))
 		val |= XELPDP_DDI_CLOCK_SELECT(XELPDP_DDI_CLOCK_SELECT_DIV18CLK);
 	else
 		val |= XELPDP_DDI_CLOCK_SELECT(XELPDP_DDI_CLOCK_SELECT_MAXPCLK);
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 28d85e1e858e..df582ff81b45 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -906,12 +906,18 @@ static bool needs_async_flip_vtd_wa(const struct intel_crtc_state *crtc_state)
 static bool planes_enabling(const struct intel_crtc_state *old_crtc_state,
 			    const struct intel_crtc_state *new_crtc_state)
 {
+	if (!new_crtc_state->hw.active)
+		return false;
+
 	return is_enabling(active_planes, old_crtc_state, new_crtc_state);
 }
 
 static bool planes_disabling(const struct intel_crtc_state *old_crtc_state,
 			     const struct intel_crtc_state *new_crtc_state)
 {
+	if (!old_crtc_state->hw.active)
+		return false;
+
 	return is_disabling(active_planes, old_crtc_state, new_crtc_state);
 }
 
@@ -928,6 +934,9 @@ static bool vrr_params_changed(const struct intel_crtc_state *old_crtc_state,
 static bool vrr_enabling(const struct intel_crtc_state *old_crtc_state,
 			 const struct intel_crtc_state *new_crtc_state)
 {
+	if (!new_crtc_state->hw.active)
+		return false;
+
 	return is_enabling(vrr.enable, old_crtc_state, new_crtc_state) ||
 		(new_crtc_state->vrr.enable &&
 		 (new_crtc_state->update_m_n || new_crtc_state->update_lrr ||
@@ -937,6 +946,9 @@ static bool vrr_enabling(const struct intel_crtc_state *old_crtc_state,
 static bool vrr_disabling(const struct intel_crtc_state *old_crtc_state,
 			  const struct intel_crtc_state *new_crtc_state)
 {
+	if (!old_crtc_state->hw.active)
+		return false;
+
 	return is_disabling(vrr.enable, old_crtc_state, new_crtc_state) ||
 		(old_crtc_state->vrr.enable &&
 		 (new_crtc_state->update_m_n || new_crtc_state->update_lrr ||
@@ -3735,8 +3747,8 @@ static bool hsw_get_pipe_config(struct intel_crtc *crtc,
 	if (!active)
 		goto out;
 
-	intel_dsc_get_config(pipe_config);
 	intel_bigjoiner_get_config(pipe_config);
+	intel_dsc_get_config(pipe_config);
 
 	if (!transcoder_is_dsi(pipe_config->cpu_transcoder) ||
 	    DISPLAY_VER(dev_priv) >= 11)
@@ -6021,6 +6033,17 @@ static int intel_async_flip_check_uapi(struct intel_atomic_state *state,
 		return -EINVAL;
 	}
 
+	/*
+	 * FIXME: Bigjoiner+async flip is busted currently.
+	 * Remove this check once the issues are fixed.
+	 */
+	if (new_crtc_state->bigjoiner_pipes) {
+		drm_dbg_kms(&i915->drm,
+			    "[CRTC:%d:%s] async flip disallowed with bigjoiner\n",
+			    crtc->base.base.id, crtc->base.name);
+		return -EINVAL;
+	}
+
 	for_each_oldnew_intel_plane_in_state(state, plane, old_plane_state,
 					     new_plane_state, i) {
 		if (plane->pipe != crtc->pipe)
@@ -6853,10 +6876,11 @@ static void intel_commit_modeset_disables(struct intel_atomic_state *state)
 		if (!intel_crtc_needs_modeset(new_crtc_state))
 			continue;
 
+		intel_pre_plane_update(state, crtc);
+
 		if (!old_crtc_state->hw.active)
 			continue;
 
-		intel_pre_plane_update(state, crtc);
 		intel_crtc_disable_planes(state, crtc);
 	}
 
@@ -7475,7 +7499,7 @@ int intel_atomic_commit(struct drm_device *dev, struct drm_atomic_state *_state,
 		for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i)
 			intel_color_cleanup_commit(new_crtc_state);
 
-		drm_atomic_helper_cleanup_planes(dev, &state->base);
+		drm_atomic_helper_unprepare_planes(dev, &state->base);
 		intel_runtime_pm_put(&dev_priv->runtime_pm, state->wakeref);
 		return ret;
 	}
@@ -7856,6 +7880,16 @@ enum drm_mode_status intel_mode_valid(struct drm_device *dev,
 	    mode->vtotal > vtotal_max)
 		return MODE_V_ILLEGAL;
 
+	return MODE_OK;
+}
+
+enum drm_mode_status intel_cpu_transcoder_mode_valid(struct drm_i915_private *dev_priv,
+						     const struct drm_display_mode *mode)
+{
+	/*
+	 * Additional transcoder timing limits,
+	 * excluding BXT/GLK DSI transcoders.
+	 */
 	if (DISPLAY_VER(dev_priv) >= 5) {
 		if (mode->hdisplay < 64 ||
 		    mode->htotal - mode->hdisplay < 32)
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index 0e5dffe8f018..a05c7e2b782e 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -403,6 +403,9 @@ enum drm_mode_status
 intel_mode_valid_max_plane_size(struct drm_i915_private *dev_priv,
 				const struct drm_display_mode *mode,
 				bool bigjoiner);
+enum drm_mode_status
+intel_cpu_transcoder_mode_valid(struct drm_i915_private *i915,
+				const struct drm_display_mode *mode);
 enum phy intel_port_to_phy(struct drm_i915_private *i915, enum port port);
 bool is_trans_port_sync_mode(const struct intel_crtc_state *state);
 bool is_trans_port_sync_master(const struct intel_crtc_state *state);
diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c
index 63e080e07023..073b85b57679 100644
--- a/drivers/gpu/drm/i915/display/intel_dmc.c
+++ b/drivers/gpu/drm/i915/display/intel_dmc.c
@@ -389,7 +389,7 @@ disable_all_flip_queue_events(struct drm_i915_private *i915)
 	enum intel_dmc_id dmc_id;
 
 	/* TODO: check if the following applies to all D13+ platforms. */
-	if (!IS_DG2(i915) && !IS_TIGERLAKE(i915))
+	if (!IS_TIGERLAKE(i915))
 		return;
 
 	for_each_dmc_id(dmc_id) {
@@ -493,6 +493,45 @@ void intel_dmc_disable_pipe(struct drm_i915_private *i915, enum pipe pipe)
 		intel_de_rmw(i915, PIPEDMC_CONTROL(pipe), PIPEDMC_ENABLE, 0);
 }
 
+static bool is_dmc_evt_ctl_reg(struct drm_i915_private *i915,
+			       enum intel_dmc_id dmc_id, i915_reg_t reg)
+{
+	u32 offset = i915_mmio_reg_offset(reg);
+	u32 start = i915_mmio_reg_offset(DMC_EVT_CTL(i915, dmc_id, 0));
+	u32 end = i915_mmio_reg_offset(DMC_EVT_CTL(i915, dmc_id, DMC_EVENT_HANDLER_COUNT_GEN12));
+
+	return offset >= start && offset < end;
+}
+
+static bool disable_dmc_evt(struct drm_i915_private *i915,
+			    enum intel_dmc_id dmc_id,
+			    i915_reg_t reg, u32 data)
+{
+	if (!is_dmc_evt_ctl_reg(i915, dmc_id, reg))
+		return false;
+
+	/* keep all pipe DMC events disabled by default */
+	if (dmc_id != DMC_FW_MAIN)
+		return true;
+
+	return false;
+}
+
+static u32 dmc_mmiodata(struct drm_i915_private *i915,
+			struct intel_dmc *dmc,
+			enum intel_dmc_id dmc_id, int i)
+{
+	if (disable_dmc_evt(i915, dmc_id,
+			    dmc->dmc_info[dmc_id].mmioaddr[i],
+			    dmc->dmc_info[dmc_id].mmiodata[i]))
+		return REG_FIELD_PREP(DMC_EVT_CTL_TYPE_MASK,
+				      DMC_EVT_CTL_TYPE_EDGE_0_1) |
+			REG_FIELD_PREP(DMC_EVT_CTL_EVENT_ID_MASK,
+				       DMC_EVT_CTL_EVENT_ID_FALSE);
+	else
+		return dmc->dmc_info[dmc_id].mmiodata[i];
+}
+
 /**
  * intel_dmc_load_program() - write the firmware from memory to register.
  * @i915: i915 drm device.
@@ -532,7 +571,7 @@ void intel_dmc_load_program(struct drm_i915_private *i915)
 	for_each_dmc_id(dmc_id) {
 		for (i = 0; i < dmc->dmc_info[dmc_id].mmio_count; i++) {
 			intel_de_write(i915, dmc->dmc_info[dmc_id].mmioaddr[i],
-				       dmc->dmc_info[dmc_id].mmiodata[i]);
+				       dmc_mmiodata(i915, dmc, dmc_id, i));
 		}
 	}
 
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 2c1034578984..62ce92772367 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -1172,6 +1172,10 @@ intel_dp_mode_valid(struct drm_connector *_connector,
 	enum drm_mode_status status;
 	bool dsc = false, bigjoiner = false;
 
+	status = intel_cpu_transcoder_mode_valid(dev_priv, mode);
+	if (status != MODE_OK)
+		return status;
+
 	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
 		return MODE_H_ILLEGAL;
 
@@ -4492,7 +4496,7 @@ static void intel_dp_process_phy_request(struct intel_dp *intel_dp,
 			  intel_dp->train_set, crtc_state->lane_count);
 
 	drm_dp_set_phy_test_pattern(&intel_dp->aux, data,
-				    link_status[DP_DPCD_REV]);
+				    intel_dp->dpcd[DP_DPCD_REV]);
 }
 
 static u8 intel_dp_autotest_phy_pattern(struct intel_dp *intel_dp)
@@ -6037,8 +6041,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	 * (eg. Acer Chromebook C710), so we'll check it only if multiple
 	 * ports are attempting to use the same AUX CH, according to VBT.
 	 */
-	if (intel_bios_dp_has_shared_aux_ch(encoder->devdata) &&
-	    !intel_digital_port_connected(encoder)) {
+	if (intel_bios_dp_has_shared_aux_ch(encoder->devdata)) {
 		/*
 		 * If this fails, presume the DPCD answer came
 		 * from some other port using the same AUX CH.
@@ -6046,10 +6049,27 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 		 * FIXME maybe cleaner to check this before the
 		 * DPCD read? Would need sort out the VDD handling...
 		 */
-		drm_info(&dev_priv->drm,
-			 "[ENCODER:%d:%s] HPD is down, disabling eDP\n",
-			 encoder->base.base.id, encoder->base.name);
-		goto out_vdd_off;
+		if (!intel_digital_port_connected(encoder)) {
+			drm_info(&dev_priv->drm,
+				 "[ENCODER:%d:%s] HPD is down, disabling eDP\n",
+				 encoder->base.base.id, encoder->base.name);
+			goto out_vdd_off;
+		}
+
+		/*
+		 * Unfortunately even the HPD based detection fails on
+		 * eg. Asus B360M-A (CFL+CNP), so as a last resort fall
+		 * back to checking for a VGA branch device. Only do this
+		 * on known affected platforms to minimize false positives.
+		 */
+		if (DISPLAY_VER(dev_priv) == 9 && drm_dp_is_branch(intel_dp->dpcd) &&
+		    (intel_dp->dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_TYPE_MASK) ==
+		    DP_DWN_STRM_PORT_TYPE_ANALOG) {
+			drm_info(&dev_priv->drm,
+				 "[ENCODER:%d:%s] VGA converter detected, disabling eDP\n",
+				 encoder->base.base.id, encoder->base.name);
+			goto out_vdd_off;
+		}
 	}
 
 	mutex_lock(&dev_priv->drm.mode_config.mutex);
diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index dbc1b66c8ee4..1abfafbbfa75 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -650,19 +650,30 @@ intel_dp_update_link_bw_set(struct intel_dp *intel_dp,
 			    const struct intel_crtc_state *crtc_state,
 			    u8 link_bw, u8 rate_select)
 {
-	u8 link_config[2];
+	u8 lane_count = crtc_state->lane_count;
 
-	/* Write the link configuration data */
-	link_config[0] = link_bw;
-	link_config[1] = crtc_state->lane_count;
 	if (crtc_state->enhanced_framing)
-		link_config[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN;
-	drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_BW_SET, link_config, 2);
+		lane_count |= DP_LANE_COUNT_ENHANCED_FRAME_EN;
+
+	if (link_bw) {
+		/* DP and eDP v1.3 and earlier link bw set method. */
+		u8 link_config[] = { link_bw, lane_count };
 
-	/* eDP 1.4 rate select method. */
-	if (!link_bw)
-		drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_RATE_SET,
-				  &rate_select, 1);
+		drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_BW_SET, link_config,
+				  ARRAY_SIZE(link_config));
+	} else {
+		/*
+		 * eDP v1.4 and later link rate set method.
+		 *
+		 * eDP v1.4x sinks shall ignore DP_LINK_RATE_SET if
+		 * DP_LINK_BW_SET is set. Avoid writing DP_LINK_BW_SET.
+		 *
+		 * eDP v1.5 sinks allow choosing either, and the last choice
+		 * shall be active.
+		 */
+		drm_dp_dpcd_writeb(&intel_dp->aux, DP_LANE_COUNT_SET, lane_count);
+		drm_dp_dpcd_writeb(&intel_dp->aux, DP_LINK_RATE_SET, rate_select);
+	}
 }
 
 /*
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 7b4628f4f124..aa1061262613 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -959,6 +959,10 @@ intel_dp_mst_mode_valid_ctx(struct drm_connector *connector,
 		return 0;
 	}
 
+	*status = intel_cpu_transcoder_mode_valid(dev_priv, mode);
+	if (*status != MODE_OK)
+		return 0;
+
 	if (mode->flags & DRM_MODE_FLAG_DBLSCAN) {
 		*status = MODE_NO_DBLESCAN;
 		return 0;
@@ -993,6 +997,10 @@ intel_dp_mst_mode_valid_ctx(struct drm_connector *connector,
 	if (intel_dp_need_bigjoiner(intel_dp, mode->hdisplay, target_clock)) {
 		bigjoiner = true;
 		max_dotclk *= 2;
+
+		/* TODO: add support for bigjoiner */
+		*status = MODE_CLOCK_HIGH;
+		return 0;
 	}
 
 	if (DISPLAY_VER(dev_priv) >= 10 &&
@@ -1027,11 +1035,15 @@ intel_dp_mst_mode_valid_ctx(struct drm_connector *connector,
 	 * Big joiner configuration needs DSC for TGL which is not true for
 	 * XE_LPD where uncompressed joiner is supported.
 	 */
-	if (DISPLAY_VER(dev_priv) < 13 && bigjoiner && !dsc)
-		return MODE_CLOCK_HIGH;
+	if (DISPLAY_VER(dev_priv) < 13 && bigjoiner && !dsc) {
+		*status = MODE_CLOCK_HIGH;
+		return 0;
+	}
 
-	if (mode_rate > max_rate && !dsc)
-		return MODE_CLOCK_HIGH;
+	if (mode_rate > max_rate && !dsc) {
+		*status = MODE_CLOCK_HIGH;
+		return 0;
+	}
 
 	*status = intel_mode_valid_max_plane_size(dev_priv, mode, false);
 	return 0;
@@ -1161,6 +1173,14 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo
 	intel_connector->port = port;
 	drm_dp_mst_get_port_malloc(port);
 
+	/*
+	 * TODO: set the AUX for the actual MST port decompressing the stream.
+	 * At the moment the driver only supports enabling this globally in the
+	 * first downstream MST branch, via intel_dp's (root port) AUX.
+	 */
+	intel_connector->dp.dsc_decompression_aux = &intel_dp->aux;
+	intel_dp_mst_read_decompression_port_dsc_caps(intel_dp, intel_connector);
+
 	connector = &intel_connector->base;
 	ret = drm_connector_init(dev, connector, &intel_dp_mst_connector_funcs,
 				 DRM_MODE_CONNECTOR_DisplayPort);
@@ -1172,14 +1192,6 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo
 
 	drm_connector_helper_add(connector, &intel_dp_mst_connector_helper_funcs);
 
-	/*
-	 * TODO: set the AUX for the actual MST port decompressing the stream.
-	 * At the moment the driver only supports enabling this globally in the
-	 * first downstream MST branch, via intel_dp's (root port) AUX.
-	 */
-	intel_connector->dp.dsc_decompression_aux = &intel_dp->aux;
-	intel_dp_mst_read_decompression_port_dsc_caps(intel_dp, intel_connector);
-
 	for_each_pipe(dev_priv, pipe) {
 		struct drm_encoder *enc =
 			&intel_dp->mst_encoders[pipe]->base.base;
diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c
index 78b6fe24dcd8..7fd6280c54a7 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.c
+++ b/drivers/gpu/drm/i915/display/intel_dsb.c
@@ -340,7 +340,7 @@ static int intel_dsb_dewake_scanline(const struct intel_crtc_state *crtc_state)
 }
 
 static void _intel_dsb_commit(struct intel_dsb *dsb, u32 ctrl,
-			      unsigned int dewake_scanline)
+			      int dewake_scanline)
 {
 	struct intel_crtc *crtc = dsb->crtc;
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
diff --git a/drivers/gpu/drm/i915/display/intel_dvo.c b/drivers/gpu/drm/i915/display/intel_dvo.c
index 55d6743374bd..9111e9d46486 100644
--- a/drivers/gpu/drm/i915/display/intel_dvo.c
+++ b/drivers/gpu/drm/i915/display/intel_dvo.c
@@ -217,11 +217,17 @@ intel_dvo_mode_valid(struct drm_connector *_connector,
 		     struct drm_display_mode *mode)
 {
 	struct intel_connector *connector = to_intel_connector(_connector);
+	struct drm_i915_private *i915 = to_i915(connector->base.dev);
 	struct intel_dvo *intel_dvo = intel_attached_dvo(connector);
 	const struct drm_display_mode *fixed_mode =
 		intel_panel_fixed_mode(connector, mode);
 	int max_dotclk = to_i915(connector->base.dev)->max_dotclk_freq;
 	int target_clock = mode->clock;
+	enum drm_mode_status status;
+
+	status = intel_cpu_transcoder_mode_valid(i915, mode);
+	if (status != MODE_OK)
+		return status;
 
 	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return MODE_NO_DBLESCAN;
diff --git a/drivers/gpu/drm/i915/display/intel_fb.c b/drivers/gpu/drm/i915/display/intel_fb.c
index 19b35ece31f1..646f367a13f5 100644
--- a/drivers/gpu/drm/i915/display/intel_fb.c
+++ b/drivers/gpu/drm/i915/display/intel_fb.c
@@ -1374,7 +1374,8 @@ plane_view_scanout_stride(const struct intel_framebuffer *fb, int color_plane,
 	struct drm_i915_private *i915 = to_i915(fb->base.dev);
 	unsigned int stride_tiles;
 
-	if (IS_ALDERLAKE_P(i915) || DISPLAY_VER(i915) >= 14)
+	if ((IS_ALDERLAKE_P(i915) || DISPLAY_VER(i915) >= 14) &&
+	    src_stride_tiles < dst_stride_tiles)
 		stride_tiles = src_stride_tiles;
 	else
 		stride_tiles = dst_stride_tiles;
@@ -1501,8 +1502,20 @@ static u32 calc_plane_remap_info(const struct intel_framebuffer *fb, int color_p
 
 			size += remap_info->size;
 		} else {
-			unsigned int dst_stride = plane_view_dst_stride_tiles(fb, color_plane,
-									      remap_info->width);
+			unsigned int dst_stride;
+
+			/*
+			 * The hardware automagically calculates the CCS AUX surface
+			 * stride from the main surface stride so can't really remap a
+			 * smaller subset (unless we'd remap in whole AUX page units).
+			 */
+			if (intel_fb_needs_pot_stride_remap(fb) &&
+			    intel_fb_is_ccs_modifier(fb->base.modifier))
+				dst_stride = remap_info->src_stride;
+			else
+				dst_stride = remap_info->width;
+
+			dst_stride = plane_view_dst_stride_tiles(fb, color_plane, dst_stride);
 
 			assign_chk_ovf(i915, remap_info->dst_stride, dst_stride);
 			color_plane_info->mapping_stride = dst_stride *
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index ac315f8e7820..bfa456fa7d25 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -1983,6 +1983,10 @@ intel_hdmi_mode_valid(struct drm_connector *connector,
 	bool ycbcr_420_only;
 	enum intel_output_format sink_format;
 
+	status = intel_cpu_transcoder_mode_valid(dev_priv, mode);
+	if (status != MODE_OK)
+		return status;
+
 	if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING)
 		clock *= 2;
 
diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c
index 2a4ca7e65775..bcbdd1984fd9 100644
--- a/drivers/gpu/drm/i915/display/intel_lvds.c
+++ b/drivers/gpu/drm/i915/display/intel_lvds.c
@@ -389,11 +389,16 @@ intel_lvds_mode_valid(struct drm_connector *_connector,
 		      struct drm_display_mode *mode)
 {
 	struct intel_connector *connector = to_intel_connector(_connector);
+	struct drm_i915_private *i915 = to_i915(connector->base.dev);
 	const struct drm_display_mode *fixed_mode =
 		intel_panel_fixed_mode(connector, mode);
 	int max_pixclk = to_i915(connector->base.dev)->max_dotclk_freq;
 	enum drm_mode_status status;
 
+	status = intel_cpu_transcoder_mode_valid(i915, mode);
+	if (status != MODE_OK)
+		return status;
+
 	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return MODE_NO_DBLESCAN;
 
diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index a636f42ceae5..a9ac7d45d1f3 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -1921,13 +1921,19 @@ static enum drm_mode_status
 intel_sdvo_mode_valid(struct drm_connector *connector,
 		      struct drm_display_mode *mode)
 {
+	struct drm_i915_private *i915 = to_i915(connector->dev);
 	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(to_intel_connector(connector));
 	struct intel_sdvo_connector *intel_sdvo_connector =
 		to_intel_sdvo_connector(connector);
-	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
 	bool has_hdmi_sink = intel_has_hdmi_sink(intel_sdvo_connector, connector->state);
+	int max_dotclk = i915->max_dotclk_freq;
+	enum drm_mode_status status;
 	int clock = mode->clock;
 
+	status = intel_cpu_transcoder_mode_valid(i915, mode);
+	if (status != MODE_OK)
+		return status;
+
 	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return MODE_NO_DBLESCAN;
 
diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c
index 31a79fdfc812..2ee4f0d95851 100644
--- a/drivers/gpu/drm/i915/display/intel_tv.c
+++ b/drivers/gpu/drm/i915/display/intel_tv.c
@@ -958,8 +958,14 @@ static enum drm_mode_status
 intel_tv_mode_valid(struct drm_connector *connector,
 		    struct drm_display_mode *mode)
 {
+	struct drm_i915_private *i915 = to_i915(connector->dev);
 	const struct tv_mode *tv_mode = intel_tv_mode_find(connector->state);
-	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
+	int max_dotclk = i915->max_dotclk_freq;
+	enum drm_mode_status status;
+
+	status = intel_cpu_transcoder_mode_valid(i915, mode);
+	if (status != MODE_OK)
+		return status;
 
 	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return MODE_NO_DBLESCAN;
diff --git a/drivers/gpu/drm/i915/display/skl_scaler.c b/drivers/gpu/drm/i915/display/skl_scaler.c
index 1e7c97243fcf..8a934bada624 100644
--- a/drivers/gpu/drm/i915/display/skl_scaler.c
+++ b/drivers/gpu/drm/i915/display/skl_scaler.c
@@ -504,7 +504,6 @@ int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv,
 {
 	struct drm_plane *plane = NULL;
 	struct intel_plane *intel_plane;
-	struct intel_plane_state *plane_state = NULL;
 	struct intel_crtc_scaler_state *scaler_state =
 		&crtc_state->scaler_state;
 	struct drm_atomic_state *drm_state = crtc_state->uapi.state;
@@ -536,6 +535,7 @@ int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv,
 
 	/* walkthrough scaler_users bits and start assigning scalers */
 	for (i = 0; i < sizeof(scaler_state->scaler_users) * 8; i++) {
+		struct intel_plane_state *plane_state = NULL;
 		int *scaler_id;
 		const char *name;
 		int idx, ret;
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index 55da627a8b8d..f488394d3108 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -1541,9 +1541,25 @@ static const struct drm_encoder_funcs intel_dsi_funcs = {
 	.destroy = intel_dsi_encoder_destroy,
 };
 
+static enum drm_mode_status vlv_dsi_mode_valid(struct drm_connector *connector,
+					       struct drm_display_mode *mode)
+{
+	struct drm_i915_private *i915 = to_i915(connector->dev);
+
+	if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) {
+		enum drm_mode_status status;
+
+		status = intel_cpu_transcoder_mode_valid(i915, mode);
+		if (status != MODE_OK)
+			return status;
+	}
+
+	return intel_dsi_mode_valid(connector, mode);
+}
+
 static const struct drm_connector_helper_funcs intel_dsi_connector_helper_funcs = {
 	.get_modes = intel_dsi_get_modes,
-	.mode_valid = intel_dsi_mode_valid,
+	.mode_valid = vlv_dsi_mode_valid,
 	.atomic_check = intel_digital_connector_atomic_check,
 };
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
index 6bc26b4b06b8..ea7561ae6e13 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
@@ -36,7 +36,7 @@ static int i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj)
 	struct sg_table *st;
 	struct scatterlist *sg;
 	unsigned int npages; /* restricted by sg_alloc_table */
-	int max_order = MAX_ORDER;
+	int max_order = MAX_PAGE_ORDER;
 	unsigned int max_segment;
 	gfp_t gfp;
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index 6b9f6cf50bf6..84c50c4c4af7 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -115,7 +115,7 @@ static int get_huge_pages(struct drm_i915_gem_object *obj)
 		do {
 			struct page *page;
 
-			GEM_BUG_ON(order > MAX_ORDER);
+			GEM_BUG_ON(order > MAX_PAGE_ORDER);
 			page = alloc_pages(GFP | __GFP_ZERO, order);
 			if (!page)
 				goto err;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_user.c b/drivers/gpu/drm/i915/gt/intel_engine_user.c
index 118164ddbb2e..833987015b8b 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_user.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_user.c
@@ -41,12 +41,15 @@ void intel_engine_add_user(struct intel_engine_cs *engine)
 	llist_add(&engine->uabi_llist, &engine->i915->uabi_engines_llist);
 }
 
-static const u8 uabi_classes[] = {
+#define I915_NO_UABI_CLASS ((u16)(-1))
+
+static const u16 uabi_classes[] = {
 	[RENDER_CLASS] = I915_ENGINE_CLASS_RENDER,
 	[COPY_ENGINE_CLASS] = I915_ENGINE_CLASS_COPY,
 	[VIDEO_DECODE_CLASS] = I915_ENGINE_CLASS_VIDEO,
 	[VIDEO_ENHANCEMENT_CLASS] = I915_ENGINE_CLASS_VIDEO_ENHANCE,
 	[COMPUTE_CLASS] = I915_ENGINE_CLASS_COMPUTE,
+	[OTHER_CLASS] = I915_NO_UABI_CLASS, /* Not exposed to users, no uabi class. */
 };
 
 static int engine_cmp(void *priv, const struct list_head *A,
@@ -200,6 +203,7 @@ static void engine_rename(struct intel_engine_cs *engine, const char *name, u16
 
 void intel_engines_driver_register(struct drm_i915_private *i915)
 {
+	u16 name_instance, other_instance = 0;
 	struct legacy_ring ring = {};
 	struct list_head *it, *next;
 	struct rb_node **p, *prev;
@@ -216,27 +220,28 @@ void intel_engines_driver_register(struct drm_i915_private *i915)
 		if (intel_gt_has_unrecoverable_error(engine->gt))
 			continue; /* ignore incomplete engines */
 
-		/*
-		 * We don't want to expose the GSC engine to the users, but we
-		 * still rename it so it is easier to identify in the debug logs
-		 */
-		if (engine->id == GSC0) {
-			engine_rename(engine, "gsc", 0);
-			continue;
-		}
-
 		GEM_BUG_ON(engine->class >= ARRAY_SIZE(uabi_classes));
 		engine->uabi_class = uabi_classes[engine->class];
+		if (engine->uabi_class == I915_NO_UABI_CLASS) {
+			name_instance = other_instance++;
+		} else {
+			GEM_BUG_ON(engine->uabi_class >=
+				   ARRAY_SIZE(i915->engine_uabi_class_count));
+			name_instance =
+				i915->engine_uabi_class_count[engine->uabi_class]++;
+		}
+		engine->uabi_instance = name_instance;
 
-		GEM_BUG_ON(engine->uabi_class >=
-			   ARRAY_SIZE(i915->engine_uabi_class_count));
-		engine->uabi_instance =
-			i915->engine_uabi_class_count[engine->uabi_class]++;
-
-		/* Replace the internal name with the final user facing name */
+		/*
+		 * Replace the internal name with the final user and log facing
+		 * name.
+		 */
 		engine_rename(engine,
 			      intel_engine_class_repr(engine->class),
-			      engine->uabi_instance);
+			      name_instance);
+
+		if (engine->uabi_class == I915_NO_UABI_CLASS)
+			continue;
 
 		rb_link_node(&engine->uabi_node, prev, p);
 		rb_insert_color(&engine->uabi_node, &i915->uabi_engines);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index ed32bf5b1546..ba1186fc524f 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -982,8 +982,6 @@ int intel_gt_probe_all(struct drm_i915_private *i915)
 
 err:
 	i915_probe_error(i915, "Failed to initialize %s! (%d)\n", gtdef->name, ret);
-	intel_gt_release_all(i915);
-
 	return ret;
 }
 
@@ -1002,15 +1000,6 @@ int intel_gt_tiles_init(struct drm_i915_private *i915)
 	return 0;
 }
 
-void intel_gt_release_all(struct drm_i915_private *i915)
-{
-	struct intel_gt *gt;
-	unsigned int id;
-
-	for_each_gt(gt, i915, id)
-		i915->gt[id] = NULL;
-}
-
 void intel_gt_info_print(const struct intel_gt_info *info,
 			 struct drm_printer *p)
 {
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index d5ed904f355d..6801f8b95c53 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -1293,7 +1293,7 @@ int __intel_engine_reset_bh(struct intel_engine_cs *engine, const char *msg)
 	if (msg)
 		drm_notice(&engine->i915->drm,
 			   "Resetting %s for %s\n", engine->name, msg);
-	atomic_inc(&engine->i915->gpu_error.reset_engine_count[engine->uabi_class]);
+	i915_increase_reset_engine_count(&engine->i915->gpu_error, engine);
 
 	ret = intel_gt_reset_engine(engine);
 	if (ret) {
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index d37698bd6b91..17df71117cc7 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -5001,7 +5001,8 @@ static void capture_error_state(struct intel_guc *guc,
 			if (match) {
 				intel_engine_set_hung_context(e, ce);
 				engine_mask |= e->mask;
-				atomic_inc(&i915->gpu_error.reset_engine_count[e->uabi_class]);
+				i915_increase_reset_engine_count(&i915->gpu_error,
+								 e);
 			}
 		}
 
@@ -5013,7 +5014,7 @@ static void capture_error_state(struct intel_guc *guc,
 	} else {
 		intel_engine_set_hung_context(ce->engine, ce);
 		engine_mask = ce->engine->mask;
-		atomic_inc(&i915->gpu_error.reset_engine_count[ce->engine->uabi_class]);
+		i915_increase_reset_engine_count(&i915->gpu_error, ce->engine);
 	}
 
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
diff --git a/drivers/gpu/drm/i915/gvt/interrupt.c b/drivers/gpu/drm/i915/gvt/interrupt.c
index de3f5903d1a7..c8e7dfc9f791 100644
--- a/drivers/gpu/drm/i915/gvt/interrupt.c
+++ b/drivers/gpu/drm/i915/gvt/interrupt.c
@@ -422,7 +422,7 @@ static void init_irq_map(struct intel_gvt_irq *irq)
 #define MSI_CAP_DATA(offset) (offset + 8)
 #define MSI_CAP_EN 0x1
 
-static int inject_virtual_interrupt(struct intel_vgpu *vgpu)
+static void inject_virtual_interrupt(struct intel_vgpu *vgpu)
 {
 	unsigned long offset = vgpu->gvt->device_info.msi_cap_offset;
 	u16 control, data;
@@ -434,10 +434,10 @@ static int inject_virtual_interrupt(struct intel_vgpu *vgpu)
 
 	/* Do not generate MSI if MSIEN is disabled */
 	if (!(control & MSI_CAP_EN))
-		return 0;
+		return;
 
 	if (WARN(control & GENMASK(15, 1), "only support one MSI format\n"))
-		return -EINVAL;
+		return;
 
 	trace_inject_msi(vgpu->id, addr, data);
 
@@ -451,10 +451,9 @@ static int inject_virtual_interrupt(struct intel_vgpu *vgpu)
 	 * returned and don't inject interrupt into guest.
 	 */
 	if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
-		return -ESRCH;
-	if (vgpu->msi_trigger && eventfd_signal(vgpu->msi_trigger, 1) != 1)
-		return -EFAULT;
-	return 0;
+		return;
+	if (vgpu->msi_trigger)
+		eventfd_signal(vgpu->msi_trigger);
 }
 
 static void propagate_event(struct intel_gvt_irq *irq,
diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c
index 8a0e2c745e1f..802de2c6decb 100644
--- a/drivers/gpu/drm/i915/i915_driver.c
+++ b/drivers/gpu/drm/i915/i915_driver.c
@@ -782,7 +782,7 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	ret = i915_driver_mmio_probe(i915);
 	if (ret < 0)
-		goto out_tiles_cleanup;
+		goto out_runtime_pm_put;
 
 	ret = i915_driver_hw_probe(i915);
 	if (ret < 0)
@@ -842,8 +842,6 @@ out_cleanup_hw:
 	i915_ggtt_driver_late_release(i915);
 out_cleanup_mmio:
 	i915_driver_mmio_release(i915);
-out_tiles_cleanup:
-	intel_gt_release_all(i915);
 out_runtime_pm_put:
 	enable_rpm_wakeref_asserts(&i915->runtime_pm);
 	i915_driver_late_release(i915);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index 9f5971f5e980..48f6c00402c4 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -16,6 +16,7 @@
 
 #include "display/intel_display_device.h"
 #include "gt/intel_engine.h"
+#include "gt/intel_engine_types.h"
 #include "gt/intel_gt_types.h"
 #include "gt/uc/intel_uc_fw.h"
 
@@ -232,7 +233,7 @@ struct i915_gpu_error {
 	atomic_t reset_count;
 
 	/** Number of times an engine has been reset */
-	atomic_t reset_engine_count[I915_NUM_ENGINES];
+	atomic_t reset_engine_count[MAX_ENGINE_CLASS];
 };
 
 struct drm_i915_error_state_buf {
@@ -255,7 +256,14 @@ static inline u32 i915_reset_count(struct i915_gpu_error *error)
 static inline u32 i915_reset_engine_count(struct i915_gpu_error *error,
 					  const struct intel_engine_cs *engine)
 {
-	return atomic_read(&error->reset_engine_count[engine->uabi_class]);
+	return atomic_read(&error->reset_engine_count[engine->class]);
+}
+
+static inline void
+i915_increase_reset_engine_count(struct i915_gpu_error *error,
+				 const struct intel_engine_cs *engine)
+{
+	atomic_inc(&error->reset_engine_count[engine->class]);
 }
 
 #define CORE_DUMP_FLAG_NONE           0x0
diff --git a/drivers/gpu/drm/i915/i915_hwmon.c b/drivers/gpu/drm/i915/i915_hwmon.c
index 975da8e7f2a9..8c3f443c8347 100644
--- a/drivers/gpu/drm/i915/i915_hwmon.c
+++ b/drivers/gpu/drm/i915/i915_hwmon.c
@@ -175,7 +175,7 @@ hwm_power1_max_interval_show(struct device *dev, struct device_attribute *attr,
 	 *     tau4 = (4 | x) << y
 	 * but add 2 when doing the final right shift to account for units
 	 */
-	tau4 = ((1 << x_w) | x) << y;
+	tau4 = (u64)((1 << x_w) | x) << y;
 	/* val in hwmon interface units (millisec) */
 	out = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w);
 
@@ -211,7 +211,7 @@ hwm_power1_max_interval_store(struct device *dev,
 	r = FIELD_PREP(PKG_MAX_WIN, PKG_MAX_WIN_DEFAULT);
 	x = REG_FIELD_GET(PKG_MAX_WIN_X, r);
 	y = REG_FIELD_GET(PKG_MAX_WIN_Y, r);
-	tau4 = ((1 << x_w) | x) << y;
+	tau4 = (u64)((1 << x_w) | x) << y;
 	max_win = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w);
 
 	if (val > max_win)
diff --git a/drivers/gpu/drm/i915/i915_memcpy.c b/drivers/gpu/drm/i915/i915_memcpy.c
index 1b021a4902de..ba82277254b7 100644
--- a/drivers/gpu/drm/i915/i915_memcpy.c
+++ b/drivers/gpu/drm/i915/i915_memcpy.c
@@ -23,6 +23,8 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/cpufeature.h>
 #include <asm/fpu/api.h>
 
 #include "i915_memcpy.h"
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 7b1c8de2f9cb..2d695818f006 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -772,10 +772,6 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 		 * The reason field includes flags identifying what
 		 * triggered this specific report (mostly timer
 		 * triggered or e.g. due to a context switch).
-		 *
-		 * In MMIO triggered reports, some platforms do not set the
-		 * reason bit in this field and it is valid to have a reason
-		 * field of zero.
 		 */
 		reason = oa_report_reason(stream, report);
 		ctx_id = oa_context_id(stream, report32);
@@ -787,8 +783,41 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 		 *
 		 * Note: that we don't clear the valid_ctx_bit so userspace can
 		 * understand that the ID has been squashed by the kernel.
+		 *
+		 * Update:
+		 *
+		 * On XEHP platforms the behavior of context id valid bit has
+		 * changed compared to prior platforms. To describe this, we
+		 * define a few terms:
+		 *
+		 * context-switch-report: This is a report with the reason type
+		 * being context-switch. It is generated when a context switches
+		 * out.
+		 *
+		 * context-valid-bit: A bit that is set in the report ID field
+		 * to indicate that a valid context has been loaded.
+		 *
+		 * gpu-idle: A condition characterized by a
+		 * context-switch-report with context-valid-bit set to 0.
+		 *
+		 * On prior platforms, context-id-valid bit is set to 0 only
+		 * when GPU goes idle. In all other reports, it is set to 1.
+		 *
+		 * On XEHP platforms, context-valid-bit is set to 1 in a context
+		 * switch report if a new context switched in. For all other
+		 * reports it is set to 0.
+		 *
+		 * This change in behavior causes an issue with MMIO triggered
+		 * reports. MMIO triggered reports have the markers in the
+		 * context ID field and the context-valid-bit is 0. The logic
+		 * below to squash the context ID would render the report
+		 * useless since the user will not be able to find it in the OA
+		 * buffer. Since MMIO triggered reports exist only on XEHP,
+		 * we should avoid squashing these for XEHP platforms.
 		 */
-		if (oa_report_ctx_invalid(stream, report)) {
+
+		if (oa_report_ctx_invalid(stream, report) &&
+		    GRAPHICS_VER_FULL(stream->engine->i915) < IP_VER(12, 50)) {
 			ctx_id = INVALID_CTX_ID;
 			oa_context_id_squash(stream, report32);
 		}
diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.c b/drivers/gpu/drm/i915/selftests/igt_live_test.c
index 4ddc6d902752..7d41874a49c5 100644
--- a/drivers/gpu/drm/i915/selftests/igt_live_test.c
+++ b/drivers/gpu/drm/i915/selftests/igt_live_test.c
@@ -37,8 +37,9 @@ int igt_live_test_begin(struct igt_live_test *t,
 		}
 
 		for_each_engine(engine, gt, id)
-			t->reset_engine[id] =
-			i915_reset_engine_count(&i915->gpu_error, engine);
+			t->reset_engine[i][id] =
+				i915_reset_engine_count(&i915->gpu_error,
+							engine);
 	}
 
 	t->reset_global = i915_reset_count(&i915->gpu_error);
@@ -66,14 +67,14 @@ int igt_live_test_end(struct igt_live_test *t)
 
 	for_each_gt(gt, i915, i) {
 		for_each_engine(engine, gt, id) {
-			if (t->reset_engine[id] ==
+			if (t->reset_engine[i][id] ==
 			    i915_reset_engine_count(&i915->gpu_error, engine))
 				continue;
 
 			gt_err(gt, "%s(%s): engine '%s' was reset %d times!\n",
 			       t->func, t->name, engine->name,
 			       i915_reset_engine_count(&i915->gpu_error, engine) -
-			       t->reset_engine[id]);
+			       t->reset_engine[i][id]);
 			return -EIO;
 		}
 	}
diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.h b/drivers/gpu/drm/i915/selftests/igt_live_test.h
index 36ed42736c52..83e3ad430922 100644
--- a/drivers/gpu/drm/i915/selftests/igt_live_test.h
+++ b/drivers/gpu/drm/i915/selftests/igt_live_test.h
@@ -7,6 +7,7 @@
 #ifndef IGT_LIVE_TEST_H
 #define IGT_LIVE_TEST_H
 
+#include "gt/intel_gt_defines.h" /* for I915_MAX_GT */
 #include "gt/intel_engine.h" /* for I915_NUM_ENGINES */
 
 struct drm_i915_private;
@@ -17,7 +18,7 @@ struct igt_live_test {
 	const char *name;
 
 	unsigned int reset_global;
-	unsigned int reset_engine[I915_NUM_ENGINES];
+	unsigned int reset_engine[I915_MAX_GT][I915_NUM_ENGINES];
 };
 
 /*
diff --git a/drivers/gpu/drm/lima/lima_ctx.c b/drivers/gpu/drm/lima/lima_ctx.c
index 891d5cd5019a..8389f2d7d021 100644
--- a/drivers/gpu/drm/lima/lima_ctx.c
+++ b/drivers/gpu/drm/lima/lima_ctx.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR MIT
 /* Copyright 2018-2019 Qiang Yu <yuq825@gmail.com> */
 
+#include <linux/pid.h>
 #include <linux/slab.h>
 
 #include "lima_device.h"
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_gamma.c b/drivers/gpu/drm/mediatek/mtk_disp_gamma.c
index f81dc34c9c3e..c1bc8b00d938 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_gamma.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_gamma.c
@@ -203,7 +203,7 @@ void mtk_gamma_set(struct device *dev, struct drm_crtc_state *state)
 	/* Disable RELAY mode to pass the processed image */
 	cfg_val &= ~GAMMA_RELAY_MODE;
 
-	cfg_val = readl(gamma->regs + DISP_GAMMA_CFG);
+	writel(cfg_val, gamma->regs + DISP_GAMMA_CFG);
 }
 
 void mtk_gamma_config(struct device *dev, unsigned int w,
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index c277b9fae950..db43f9dff912 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -788,6 +788,7 @@ static void mtk_drm_crtc_atomic_begin(struct drm_crtc *crtc,
 									  crtc);
 	struct mtk_crtc_state *mtk_crtc_state = to_mtk_crtc_state(crtc_state);
 	struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
+	unsigned long flags;
 
 	if (mtk_crtc->event && mtk_crtc_state->base.event)
 		DRM_ERROR("new event while there is still a pending event\n");
@@ -795,7 +796,11 @@ static void mtk_drm_crtc_atomic_begin(struct drm_crtc *crtc,
 	if (mtk_crtc_state->base.event) {
 		mtk_crtc_state->base.event->pipe = drm_crtc_index(crtc);
 		WARN_ON(drm_crtc_vblank_get(crtc) != 0);
+
+		spin_lock_irqsave(&crtc->dev->event_lock, flags);
 		mtk_crtc->event = mtk_crtc_state->base.event;
+		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+
 		mtk_crtc_state->base.event = NULL;
 	}
 }
@@ -921,7 +926,14 @@ static int mtk_drm_crtc_init_comp_planes(struct drm_device *drm_dev,
 
 struct device *mtk_drm_crtc_dma_dev_get(struct drm_crtc *crtc)
 {
-	struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
+	struct mtk_drm_crtc *mtk_crtc = NULL;
+
+	if (!crtc)
+		return NULL;
+
+	mtk_crtc = to_mtk_crtc(crtc);
+	if (!mtk_crtc)
+		return NULL;
 
 	return mtk_crtc->dma_dev;
 }
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index 2dfaa613276a..2b0c35cacbc6 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -443,6 +443,7 @@ static int mtk_drm_kms_init(struct drm_device *drm)
 	struct mtk_drm_private *private = drm->dev_private;
 	struct mtk_drm_private *priv_n;
 	struct device *dma_dev = NULL;
+	struct drm_crtc *crtc;
 	int ret, i, j;
 
 	if (drm_firmware_drivers_only())
@@ -519,7 +520,9 @@ static int mtk_drm_kms_init(struct drm_device *drm)
 	}
 
 	/* Use OVL device for all DMA memory allocations */
-	dma_dev = mtk_drm_crtc_dma_dev_get(drm_crtc_from_index(drm, 0));
+	crtc = drm_crtc_from_index(drm, 0);
+	if (crtc)
+		dma_dev = mtk_drm_crtc_dma_dev_get(crtc);
 	if (!dma_dev) {
 		ret = -ENODEV;
 		dev_err(drm->dev, "Need at least one OVL device\n");
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h
index 57c7edcab602..765e49fd8911 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.h
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.h
@@ -392,6 +392,11 @@ void mgag200_primary_plane_helper_atomic_disable(struct drm_plane *plane,
 	.destroy = drm_plane_cleanup, \
 	DRM_GEM_SHADOW_PLANE_FUNCS
 
+void mgag200_crtc_set_gamma_linear(struct mga_device *mdev, const struct drm_format_info *format);
+void mgag200_crtc_set_gamma(struct mga_device *mdev,
+			    const struct drm_format_info *format,
+			    struct drm_color_lut *lut);
+
 enum drm_mode_status mgag200_crtc_helper_mode_valid(struct drm_crtc *crtc,
 						    const struct drm_display_mode *mode);
 int mgag200_crtc_helper_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *new_state);
diff --git a/drivers/gpu/drm/mgag200/mgag200_g200er.c b/drivers/gpu/drm/mgag200/mgag200_g200er.c
index bce267e0f7de..8d4538b71047 100644
--- a/drivers/gpu/drm/mgag200/mgag200_g200er.c
+++ b/drivers/gpu/drm/mgag200/mgag200_g200er.c
@@ -202,6 +202,11 @@ static void mgag200_g200er_crtc_helper_atomic_enable(struct drm_crtc *crtc,
 
 	mgag200_g200er_reset_tagfifo(mdev);
 
+	if (crtc_state->gamma_lut)
+		mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data);
+	else
+		mgag200_crtc_set_gamma_linear(mdev, format);
+
 	mgag200_enable_display(mdev);
 
 	if (funcs->enable_vidrst)
diff --git a/drivers/gpu/drm/mgag200/mgag200_g200ev.c b/drivers/gpu/drm/mgag200/mgag200_g200ev.c
index ac957f42abe1..56e6f986bff3 100644
--- a/drivers/gpu/drm/mgag200/mgag200_g200ev.c
+++ b/drivers/gpu/drm/mgag200/mgag200_g200ev.c
@@ -203,6 +203,11 @@ static void mgag200_g200ev_crtc_helper_atomic_enable(struct drm_crtc *crtc,
 
 	mgag200_g200ev_set_hiprilvl(mdev);
 
+	if (crtc_state->gamma_lut)
+		mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data);
+	else
+		mgag200_crtc_set_gamma_linear(mdev, format);
+
 	mgag200_enable_display(mdev);
 
 	if (funcs->enable_vidrst)
diff --git a/drivers/gpu/drm/mgag200/mgag200_g200se.c b/drivers/gpu/drm/mgag200/mgag200_g200se.c
index bd6e573c9a1a..ff2b3c6622e7 100644
--- a/drivers/gpu/drm/mgag200/mgag200_g200se.c
+++ b/drivers/gpu/drm/mgag200/mgag200_g200se.c
@@ -334,6 +334,11 @@ static void mgag200_g200se_crtc_helper_atomic_enable(struct drm_crtc *crtc,
 
 	mgag200_g200se_set_hiprilvl(mdev, adjusted_mode, format);
 
+	if (crtc_state->gamma_lut)
+		mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data);
+	else
+		mgag200_crtc_set_gamma_linear(mdev, format);
+
 	mgag200_enable_display(mdev);
 
 	if (funcs->enable_vidrst)
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index af3ce5a6a636..0f0d59938c3a 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -28,8 +28,8 @@
  * This file contains setup code for the CRTC.
  */
 
-static void mgag200_crtc_set_gamma_linear(struct mga_device *mdev,
-					  const struct drm_format_info *format)
+void mgag200_crtc_set_gamma_linear(struct mga_device *mdev,
+				   const struct drm_format_info *format)
 {
 	int i;
 
@@ -65,9 +65,9 @@ static void mgag200_crtc_set_gamma_linear(struct mga_device *mdev,
 	}
 }
 
-static void mgag200_crtc_set_gamma(struct mga_device *mdev,
-				   const struct drm_format_info *format,
-				   struct drm_color_lut *lut)
+void mgag200_crtc_set_gamma(struct mga_device *mdev,
+			    const struct drm_format_info *format,
+			    struct drm_color_lut *lut)
 {
 	int i;
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h
index 1ccd1edd693c..4c0528794e7a 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h
@@ -406,6 +406,7 @@ static const struct dpu_perf_cfg sc8280xp_perf_data = {
 	.min_llcc_ib = 0,
 	.min_dram_ib = 800000,
 	.danger_lut_tbl = {0xf, 0xffff, 0x0},
+	.safe_lut_tbl = {0xfe00, 0xfe00, 0xffff},
 	.qos_lut_tbl = {
 		{.nentry = ARRAY_SIZE(sc8180x_qos_linear),
 		.entries = sc8180x_qos_linear
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
index 11d9fc2c6bf5..ec933d597e20 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
@@ -844,8 +844,7 @@ static int mdp5_init(struct platform_device *pdev, struct drm_device *dev)
 
 	return 0;
 fail:
-	if (mdp5_kms)
-		mdp5_destroy(mdp5_kms);
+	mdp5_destroy(mdp5_kms);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c
index e329e03e068d..1b88fb52726f 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -365,9 +365,11 @@ static int dp_display_send_hpd_notification(struct dp_display_private *dp,
 	/* reset video pattern flag on disconnect */
 	if (!hpd) {
 		dp->panel->video_test = false;
-		drm_dp_set_subconnector_property(dp->dp_display.connector,
-						 connector_status_disconnected,
-						 dp->panel->dpcd, dp->panel->downstream_ports);
+		if (!dp->dp_display.is_edp)
+			drm_dp_set_subconnector_property(dp->dp_display.connector,
+							 connector_status_disconnected,
+							 dp->panel->dpcd,
+							 dp->panel->downstream_ports);
 	}
 
 	dp->dp_display.is_connected = hpd;
@@ -396,8 +398,11 @@ static int dp_display_process_hpd_high(struct dp_display_private *dp)
 
 	dp_link_process_request(dp->link);
 
-	drm_dp_set_subconnector_property(dp->dp_display.connector, connector_status_connected,
-					 dp->panel->dpcd, dp->panel->downstream_ports);
+	if (!dp->dp_display.is_edp)
+		drm_dp_set_subconnector_property(dp->dp_display.connector,
+						 connector_status_connected,
+						 dp->panel->dpcd,
+						 dp->panel->downstream_ports);
 
 	edid = dp->panel->edid;
 
diff --git a/drivers/gpu/drm/msm/dp/dp_drm.c b/drivers/gpu/drm/msm/dp/dp_drm.c
index 40e7344180e3..e3bdd7dd4cdc 100644
--- a/drivers/gpu/drm/msm/dp/dp_drm.c
+++ b/drivers/gpu/drm/msm/dp/dp_drm.c
@@ -345,6 +345,9 @@ struct drm_connector *dp_drm_connector_init(struct msm_dp *dp_display, struct dr
 	if (IS_ERR(connector))
 		return connector;
 
+	if (!dp_display->is_edp)
+		drm_connector_attach_dp_subconnector_property(connector);
+
 	drm_connector_attach_encoder(connector, encoder);
 
 	return connector;
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
index 3b1ed02f644d..89a6344bc865 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
@@ -918,7 +918,7 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy,
 	if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V5_2)) {
 		if (phy->cphy_mode) {
 			vreg_ctrl_0 = 0x45;
-			vreg_ctrl_1 = 0x45;
+			vreg_ctrl_1 = 0x41;
 			glbl_rescode_top_ctrl = 0x00;
 			glbl_rescode_bot_ctrl = 0x00;
 		} else {
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 2aae7d107f33..3f217b578293 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -288,8 +288,6 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv)
 	if (ret)
 		goto err_msm_uninit;
 
-	drm_kms_helper_poll_init(ddev);
-
 	if (priv->kms_init) {
 		drm_kms_helper_poll_init(ddev);
 		msm_fbdev_setup(ddev);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index 7840b6428afb..118807e38422 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -2474,7 +2474,7 @@ nv50_disp_atomic_commit(struct drm_device *dev,
 
 err_cleanup:
 	if (ret)
-		drm_atomic_helper_cleanup_planes(dev, state);
+		drm_atomic_helper_unprepare_planes(dev, state);
 done:
 	pm_runtime_put_autosuspend(dev->dev);
 	return ret;
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/event.h b/drivers/gpu/drm/nouveau/include/nvkm/core/event.h
index 82b267c11147..460459af272d 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/event.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/event.h
@@ -14,7 +14,7 @@ struct nvkm_event {
 	int index_nr;
 
 	spinlock_t refs_lock;
-	spinlock_t list_lock;
+	rwlock_t list_lock;
 	int *refs;
 
 	struct list_head ntfy;
@@ -38,7 +38,7 @@ nvkm_event_init(const struct nvkm_event_func *func, struct nvkm_subdev *subdev,
 		int types_nr, int index_nr, struct nvkm_event *event)
 {
 	spin_lock_init(&event->refs_lock);
-	spin_lock_init(&event->list_lock);
+	rwlock_init(&event->list_lock);
 	return __nvkm_event_init(func, subdev, types_nr, index_nr, event);
 }
 
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
index 2fa0445d8928..d1437c08645f 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
@@ -187,7 +187,7 @@ struct nvkm_gsp {
 		void (*rpc_done)(struct nvkm_gsp *gsp, void *repv);
 
 		void *(*rm_ctrl_get)(struct nvkm_gsp_object *, u32 cmd, u32 argc);
-		void *(*rm_ctrl_push)(struct nvkm_gsp_object *, void *argv, u32 repc);
+		int (*rm_ctrl_push)(struct nvkm_gsp_object *, void **argv, u32 repc);
 		void (*rm_ctrl_done)(struct nvkm_gsp_object *, void *repv);
 
 		void *(*rm_alloc_get)(struct nvkm_gsp_object *, u32 oclass, u32 argc);
@@ -265,7 +265,7 @@ nvkm_gsp_rm_ctrl_get(struct nvkm_gsp_object *object, u32 cmd, u32 argc)
 	return object->client->gsp->rm->rm_ctrl_get(object, cmd, argc);
 }
 
-static inline void *
+static inline int
 nvkm_gsp_rm_ctrl_push(struct nvkm_gsp_object *object, void *argv, u32 repc)
 {
 	return object->client->gsp->rm->rm_ctrl_push(object, argv, repc);
@@ -275,21 +275,24 @@ static inline void *
 nvkm_gsp_rm_ctrl_rd(struct nvkm_gsp_object *object, u32 cmd, u32 repc)
 {
 	void *argv = nvkm_gsp_rm_ctrl_get(object, cmd, repc);
+	int ret;
 
 	if (IS_ERR(argv))
 		return argv;
 
-	return nvkm_gsp_rm_ctrl_push(object, argv, repc);
+	ret = nvkm_gsp_rm_ctrl_push(object, &argv, repc);
+	if (ret)
+		return ERR_PTR(ret);
+	return argv;
 }
 
 static inline int
 nvkm_gsp_rm_ctrl_wr(struct nvkm_gsp_object *object, void *argv)
 {
-	void *repv = nvkm_gsp_rm_ctrl_push(object, argv, 0);
-
-	if (IS_ERR(repv))
-		return PTR_ERR(repv);
+	int ret = nvkm_gsp_rm_ctrl_push(object, &argv, 0);
 
+	if (ret)
+		return ret;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/include/nvrm/535.113.01/common/shared/msgq/inc/msgq/msgq_priv.h b/drivers/gpu/drm/nouveau/include/nvrm/535.113.01/common/shared/msgq/inc/msgq/msgq_priv.h
index 5a2f273d95c8..0e32e71e123f 100644
--- a/drivers/gpu/drm/nouveau/include/nvrm/535.113.01/common/shared/msgq/inc/msgq/msgq_priv.h
+++ b/drivers/gpu/drm/nouveau/include/nvrm/535.113.01/common/shared/msgq/inc/msgq/msgq_priv.h
@@ -26,6 +26,49 @@
  * DEALINGS IN THE SOFTWARE.
  */
 
+/**
+ * msgqTxHeader -- TX queue data structure
+ * @version: the version of this structure, must be 0
+ * @size: the size of the entire queue, including this header
+ * @msgSize: the padded size of queue element, 16 is minimum
+ * @msgCount: the number of elements in this queue
+ * @writePtr: head index of this queue
+ * @flags: 1 = swap the RX pointers
+ * @rxHdrOff: offset of readPtr in this structure
+ * @entryOff: offset of beginning of queue (msgqRxHeader), relative to
+ *          beginning of this structure
+ *
+ * The command queue is a queue of RPCs that are sent from the driver to the
+ * GSP.  The status queue is a queue of messages/responses from GSP-RM to the
+ * driver.  Although the driver allocates memory for both queues, the command
+ * queue is owned by the driver and the status queue is owned by GSP-RM.  In
+ * addition, the headers of the two queues must not share the same 4K page.
+ *
+ * Each queue is prefixed with this data structure.  The idea is that a queue
+ * and its header are written to only by their owner.  That is, only the
+ * driver writes to the command queue and command queue header, and only the
+ * GSP writes to the status (receive) queue and its header.
+ *
+ * This is enforced by the concept of "swapping" the RX pointers.  This is
+ * why the 'flags' field must be set to 1.  'rxHdrOff' is how the GSP knows
+ * where the where the tail pointer of its status queue.
+ *
+ * When the driver writes a new RPC to the command queue, it updates writePtr.
+ * When it reads a new message from the status queue, it updates readPtr.  In
+ * this way, the GSP knows when a new command is in the queue (it polls
+ * writePtr) and it knows how much free space is in the status queue (it
+ * checks readPtr).  The driver never cares about how much free space is in
+ * the status queue.
+ *
+ * As usual, producers write to the head pointer, and consumers read from the
+ * tail pointer.  When head == tail, the queue is empty.
+ *
+ * So to summarize:
+ * command.writePtr = head of command queue
+ * command.readPtr = tail of status queue
+ * status.writePtr = head of status queue
+ * status.readPtr = tail of command queue
+ */
 typedef struct
 {
     NvU32 version;   // queue version
@@ -38,6 +81,14 @@ typedef struct
     NvU32 entryOff;  // Offset of entries from start of backing store.
 } msgqTxHeader;
 
+/**
+ * msgqRxHeader - RX queue data structure
+ * @readPtr: tail index of the other queue
+ *
+ * Although this is a separate struct, it could easily be merged into
+ * msgqTxHeader.  msgqTxHeader.rxHdrOff is simply the offset of readPtr
+ * from the beginning of msgqTxHeader.
+ */
 typedef struct
 {
     NvU32 readPtr; // message id of last message read
diff --git a/drivers/gpu/drm/nouveau/include/nvrm/535.113.01/nvidia/generated/g_os_nvoc.h b/drivers/gpu/drm/nouveau/include/nvrm/535.113.01/nvidia/generated/g_os_nvoc.h
index 754c6af42f30..10121218f4d3 100644
--- a/drivers/gpu/drm/nouveau/include/nvrm/535.113.01/nvidia/generated/g_os_nvoc.h
+++ b/drivers/gpu/drm/nouveau/include/nvrm/535.113.01/nvidia/generated/g_os_nvoc.h
@@ -38,7 +38,7 @@ typedef struct PACKED_REGISTRY_TABLE
 {
     NvU32                   size;
     NvU32                   numEntries;
-    PACKED_REGISTRY_ENTRY   entries[0];
+    PACKED_REGISTRY_ENTRY   entries[] __counted_by(numEntries);
 } PACKED_REGISTRY_TABLE;
 
 #endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 0f3bd187ede6..280d1d9a559b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -318,8 +318,9 @@ nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain,
 			    (!vmm->page[i].host || vmm->page[i].shift > PAGE_SHIFT))
 				continue;
 
-			if (pi < 0)
-				pi = i;
+			/* pick the last one as it will be smallest. */
+			pi = i;
+
 			/* Stop once the buffer is larger than the current page size. */
 			if (*size >= 1ULL << vmm->page[i].shift)
 				break;
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index d8c92521226d..f28f9a857458 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -726,6 +726,11 @@ nouveau_display_create(struct drm_device *dev)
 
 	if (nouveau_modeset != 2) {
 		ret = nvif_disp_ctor(&drm->client.device, "kmsDisp", 0, &disp->disp);
+		/* no display hw */
+		if (ret == -ENODEV) {
+			ret = 0;
+			goto disp_create_err;
+		}
 
 		if (!ret && (disp->disp.outp_mask || drm->vbios.dcb.entries)) {
 			nouveau_display_create_properties(dev);
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index ca762ea55413..5057d976fa57 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -62,7 +62,7 @@ nouveau_fence_signal(struct nouveau_fence *fence)
 	if (test_bit(DMA_FENCE_FLAG_USER_BITS, &fence->base.flags)) {
 		struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
 
-		if (!--fctx->notify_ref)
+		if (atomic_dec_and_test(&fctx->notify_ref))
 			drop = 1;
 	}
 
@@ -103,6 +103,7 @@ nouveau_fence_context_kill(struct nouveau_fence_chan *fctx, int error)
 void
 nouveau_fence_context_del(struct nouveau_fence_chan *fctx)
 {
+	cancel_work_sync(&fctx->allow_block_work);
 	nouveau_fence_context_kill(fctx, 0);
 	nvif_event_dtor(&fctx->event);
 	fctx->dead = 1;
@@ -167,6 +168,18 @@ nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc
 	return ret;
 }
 
+static void
+nouveau_fence_work_allow_block(struct work_struct *work)
+{
+	struct nouveau_fence_chan *fctx = container_of(work, struct nouveau_fence_chan,
+						       allow_block_work);
+
+	if (atomic_read(&fctx->notify_ref) == 0)
+		nvif_event_block(&fctx->event);
+	else
+		nvif_event_allow(&fctx->event);
+}
+
 void
 nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_chan *fctx)
 {
@@ -178,6 +191,7 @@ nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_cha
 	} args;
 	int ret;
 
+	INIT_WORK(&fctx->allow_block_work, nouveau_fence_work_allow_block);
 	INIT_LIST_HEAD(&fctx->flip);
 	INIT_LIST_HEAD(&fctx->pending);
 	spin_lock_init(&fctx->lock);
@@ -521,15 +535,19 @@ static bool nouveau_fence_enable_signaling(struct dma_fence *f)
 	struct nouveau_fence *fence = from_fence(f);
 	struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
 	bool ret;
+	bool do_work;
 
-	if (!fctx->notify_ref++)
-		nvif_event_allow(&fctx->event);
+	if (atomic_inc_return(&fctx->notify_ref) == 0)
+		do_work = true;
 
 	ret = nouveau_fence_no_signaling(f);
 	if (ret)
 		set_bit(DMA_FENCE_FLAG_USER_BITS, &fence->base.flags);
-	else if (!--fctx->notify_ref)
-		nvif_event_block(&fctx->event);
+	else if (atomic_dec_and_test(&fctx->notify_ref))
+		do_work = true;
+
+	if (do_work)
+		schedule_work(&fctx->allow_block_work);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h
index 64d33ae7f356..28f5cf013b89 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.h
@@ -3,6 +3,7 @@
 #define __NOUVEAU_FENCE_H__
 
 #include <linux/dma-fence.h>
+#include <linux/workqueue.h>
 #include <nvif/event.h>
 
 struct nouveau_drm;
@@ -45,7 +46,9 @@ struct nouveau_fence_chan {
 	char name[32];
 
 	struct nvif_event event;
-	int notify_ref, dead, killed;
+	struct work_struct allow_block_work;
+	atomic_t notify_ref;
+	int dead, killed;
 };
 
 struct nouveau_fence_priv {
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/event.c b/drivers/gpu/drm/nouveau/nvkm/core/event.c
index a6c877135598..61fed7792e41 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/event.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/event.c
@@ -81,17 +81,17 @@ nvkm_event_ntfy_state(struct nvkm_event_ntfy *ntfy)
 static void
 nvkm_event_ntfy_remove(struct nvkm_event_ntfy *ntfy)
 {
-	spin_lock_irq(&ntfy->event->list_lock);
+	write_lock_irq(&ntfy->event->list_lock);
 	list_del_init(&ntfy->head);
-	spin_unlock_irq(&ntfy->event->list_lock);
+	write_unlock_irq(&ntfy->event->list_lock);
 }
 
 static void
 nvkm_event_ntfy_insert(struct nvkm_event_ntfy *ntfy)
 {
-	spin_lock_irq(&ntfy->event->list_lock);
+	write_lock_irq(&ntfy->event->list_lock);
 	list_add_tail(&ntfy->head, &ntfy->event->ntfy);
-	spin_unlock_irq(&ntfy->event->list_lock);
+	write_unlock_irq(&ntfy->event->list_lock);
 }
 
 static void
@@ -176,7 +176,7 @@ nvkm_event_ntfy(struct nvkm_event *event, int id, u32 bits)
 		return;
 
 	nvkm_trace(event->subdev, "event: ntfy %08x on %d\n", bits, id);
-	spin_lock_irqsave(&event->list_lock, flags);
+	read_lock_irqsave(&event->list_lock, flags);
 
 	list_for_each_entry_safe(ntfy, ntmp, &event->ntfy, head) {
 		if (ntfy->id == id && ntfy->bits & bits) {
@@ -185,7 +185,7 @@ nvkm_event_ntfy(struct nvkm_event *event, int id, u32 bits)
 		}
 	}
 
-	spin_unlock_irqrestore(&event->list_lock, flags);
+	read_unlock_irqrestore(&event->list_lock, flags);
 }
 
 void
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c
index 457ec5db794d..b24eb1e560bc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c
@@ -209,7 +209,7 @@ nvkm_disp_dtor(struct nvkm_engine *engine)
 		nvkm_head_del(&head);
 	}
 
-	if (disp->func->dtor)
+	if (disp->func && disp->func->dtor)
 		disp->func->dtor(disp);
 
 	return data;
@@ -243,8 +243,10 @@ nvkm_disp_new_(const struct nvkm_disp_func *func, struct nvkm_device *device,
 	spin_lock_init(&disp->client.lock);
 
 	ret = nvkm_engine_ctor(&nvkm_disp, device, type, inst, true, &disp->engine);
-	if (ret)
+	if (ret) {
+		disp->func = NULL;
 		return ret;
+	}
 
 	if (func->super) {
 		disp->super.wq = create_singlethread_workqueue("nvkm-disp");
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c
index 298035070b3a..6a0a4d3b8902 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c
@@ -282,7 +282,7 @@ r535_sor_bl_get(struct nvkm_ior *sor)
 {
 	struct nvkm_disp *disp = sor->disp;
 	NV0073_CTRL_SPECIFIC_BACKLIGHT_BRIGHTNESS_PARAMS *ctrl;
-	int lvl;
+	int ret, lvl;
 
 	ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom,
 				    NV0073_CTRL_CMD_SPECIFIC_GET_BACKLIGHT_BRIGHTNESS,
@@ -292,9 +292,11 @@ r535_sor_bl_get(struct nvkm_ior *sor)
 
 	ctrl->displayId = BIT(sor->asy.outp->index);
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+	if (ret) {
+		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		return ret;
+	}
 
 	lvl = ctrl->brightness;
 	nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
@@ -649,9 +651,11 @@ r535_conn_new(struct nvkm_disp *disp, u32 id)
 	ctrl->subDeviceInstance = 0;
 	ctrl->displayId = BIT(id);
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return (void *)ctrl;
+	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+	if (ret) {
+		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		return ERR_PTR(ret);
+	}
 
 	list_for_each_entry(conn, &disp->conns, head) {
 		if (conn->index == ctrl->data[0].index) {
@@ -686,7 +690,7 @@ r535_outp_acquire(struct nvkm_outp *outp, bool hda)
 	struct nvkm_disp *disp = outp->disp;
 	struct nvkm_ior *ior;
 	NV0073_CTRL_DFP_ASSIGN_SOR_PARAMS *ctrl;
-	int or;
+	int ret, or;
 
 	ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom,
 				    NV0073_CTRL_CMD_DFP_ASSIGN_SOR, sizeof(*ctrl));
@@ -699,9 +703,11 @@ r535_outp_acquire(struct nvkm_outp *outp, bool hda)
 	if (hda)
 		ctrl->flags |= NVDEF(NV0073_CTRL, DFP_ASSIGN_SOR_FLAGS, AUDIO, OPTIMAL);
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+	if (ret) {
+		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		return ret;
+	}
 
 	for (or = 0; or < ARRAY_SIZE(ctrl->sorAssignListWithTag); or++) {
 		if (ctrl->sorAssignListWithTag[or].displayMask & BIT(outp->index)) {
@@ -727,6 +733,7 @@ static int
 r535_disp_head_displayid(struct nvkm_disp *disp, int head, u32 *displayid)
 {
 	NV0073_CTRL_SYSTEM_GET_ACTIVE_PARAMS *ctrl;
+	int ret;
 
 	ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom,
 				    NV0073_CTRL_CMD_SYSTEM_GET_ACTIVE, sizeof(*ctrl));
@@ -736,9 +743,11 @@ r535_disp_head_displayid(struct nvkm_disp *disp, int head, u32 *displayid)
 	ctrl->subDeviceInstance = 0;
 	ctrl->head = head;
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+	if (ret) {
+		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		return ret;
+	}
 
 	*displayid = ctrl->displayId;
 	nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
@@ -772,9 +781,11 @@ r535_outp_inherit(struct nvkm_outp *outp)
 			ctrl->subDeviceInstance = 0;
 			ctrl->displayId = displayid;
 
-			ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-			if (IS_ERR(ctrl))
+			ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+			if (ret) {
+				nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
 				return NULL;
+			}
 
 			id = ctrl->index;
 			proto = ctrl->protocol;
@@ -825,6 +836,7 @@ r535_outp_dfp_get_info(struct nvkm_outp *outp)
 {
 	NV0073_CTRL_DFP_GET_INFO_PARAMS *ctrl;
 	struct nvkm_disp *disp = outp->disp;
+	int ret;
 
 	ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DFP_GET_INFO, sizeof(*ctrl));
 	if (IS_ERR(ctrl))
@@ -832,9 +844,11 @@ r535_outp_dfp_get_info(struct nvkm_outp *outp)
 
 	ctrl->displayId = BIT(outp->index);
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+	if (ret) {
+		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		return ret;
+	}
 
 	nvkm_debug(&disp->engine.subdev, "DFP %08x: flags:%08x flags2:%08x\n",
 		   ctrl->displayId, ctrl->flags, ctrl->flags2);
@@ -858,9 +872,11 @@ r535_outp_detect(struct nvkm_outp *outp)
 	ctrl->subDeviceInstance = 0;
 	ctrl->displayMask = BIT(outp->index);
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+	if (ret) {
+		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		return ret;
+	}
 
 	if (ctrl->displayMask & BIT(outp->index)) {
 		ret = r535_outp_dfp_get_info(outp);
@@ -895,6 +911,7 @@ r535_dp_mst_id_get(struct nvkm_outp *outp, u32 *pid)
 {
 	NV0073_CTRL_CMD_DP_TOPOLOGY_ALLOCATE_DISPLAYID_PARAMS *ctrl;
 	struct nvkm_disp *disp = outp->disp;
+	int ret;
 
 	ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom,
 				    NV0073_CTRL_CMD_DP_TOPOLOGY_ALLOCATE_DISPLAYID,
@@ -904,9 +921,11 @@ r535_dp_mst_id_get(struct nvkm_outp *outp, u32 *pid)
 
 	ctrl->subDeviceInstance = 0;
 	ctrl->displayId = BIT(outp->index);
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+	if (ret) {
+		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		return ret;
+	}
 
 	*pid = ctrl->displayIdAssigned;
 	nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
@@ -938,38 +957,60 @@ r535_dp_train_target(struct nvkm_outp *outp, u8 target, bool mst, u8 link_nr, u8
 {
 	struct nvkm_disp *disp = outp->disp;
 	NV0073_CTRL_DP_CTRL_PARAMS *ctrl;
-	int ret;
-
-	ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DP_CTRL, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	int ret, retries;
+	u32 cmd, data;
 
-	ctrl->subDeviceInstance = 0;
-	ctrl->displayId = BIT(outp->index);
-	ctrl->cmd = NVDEF(NV0073_CTRL, DP_CMD, SET_LANE_COUNT, TRUE) |
-		    NVDEF(NV0073_CTRL, DP_CMD, SET_LINK_BW, TRUE) |
-		    NVDEF(NV0073_CTRL, DP_CMD, TRAIN_PHY_REPEATER, YES);
-	ctrl->data = NVVAL(NV0073_CTRL, DP_DATA, SET_LANE_COUNT, link_nr) |
-		     NVVAL(NV0073_CTRL, DP_DATA, SET_LINK_BW, link_bw) |
-		     NVVAL(NV0073_CTRL, DP_DATA, TARGET, target);
+	cmd = NVDEF(NV0073_CTRL, DP_CMD, SET_LANE_COUNT, TRUE) |
+	      NVDEF(NV0073_CTRL, DP_CMD, SET_LINK_BW, TRUE) |
+	      NVDEF(NV0073_CTRL, DP_CMD, TRAIN_PHY_REPEATER, YES);
+	data = NVVAL(NV0073_CTRL, DP_DATA, SET_LANE_COUNT, link_nr) |
+	       NVVAL(NV0073_CTRL, DP_DATA, SET_LINK_BW, link_bw) |
+	       NVVAL(NV0073_CTRL, DP_DATA, TARGET, target);
 
 	if (mst)
-		ctrl->cmd |= NVDEF(NV0073_CTRL, DP_CMD, SET_FORMAT_MODE, MULTI_STREAM);
+		cmd |= NVDEF(NV0073_CTRL, DP_CMD, SET_FORMAT_MODE, MULTI_STREAM);
 
 	if (outp->dp.dpcd[DPCD_RC02] & DPCD_RC02_ENHANCED_FRAME_CAP)
-		ctrl->cmd |= NVDEF(NV0073_CTRL, DP_CMD, SET_ENHANCED_FRAMING, TRUE);
+		cmd |= NVDEF(NV0073_CTRL, DP_CMD, SET_ENHANCED_FRAMING, TRUE);
 
 	if (target == 0 &&
 	     (outp->dp.dpcd[DPCD_RC02] & 0x20) &&
 	    !(outp->dp.dpcd[DPCD_RC03] & DPCD_RC03_TPS4_SUPPORTED))
-	    ctrl->cmd |= NVDEF(NV0073_CTRL, DP_CMD, POST_LT_ADJ_REQ_GRANTED, YES);
+		cmd |= NVDEF(NV0073_CTRL, DP_CMD, POST_LT_ADJ_REQ_GRANTED, YES);
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	/* We should retry up to 3 times, but only if GSP asks politely */
+	for (retries = 0; retries < 3; ++retries) {
+		ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DP_CTRL,
+					    sizeof(*ctrl));
+		if (IS_ERR(ctrl))
+			return PTR_ERR(ctrl);
+
+		ctrl->subDeviceInstance = 0;
+		ctrl->displayId = BIT(outp->index);
+		ctrl->retryTimeMs = 0;
+		ctrl->cmd = cmd;
+		ctrl->data = data;
+
+		ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+		if (ret == -EAGAIN && ctrl->retryTimeMs) {
+			/*
+			 * Device (likely an eDP panel) isn't ready yet, wait for the time specified
+			 * by GSP before retrying again
+			 */
+			nvkm_debug(&disp->engine.subdev,
+				   "Waiting %dms for GSP LT panel delay before retrying\n",
+				   ctrl->retryTimeMs);
+			msleep(ctrl->retryTimeMs);
+			nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		} else {
+			/* GSP didn't say to retry, or we were successful */
+			if (ctrl->err)
+				ret = -EIO;
+			nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+			break;
+		}
+	}
 
-	ret = ctrl->err ? -EIO : 0;
-	nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
 	return ret;
 }
 
@@ -1036,9 +1077,11 @@ r535_dp_aux_xfer(struct nvkm_outp *outp, u8 type, u32 addr, u8 *data, u8 *psize)
 	ctrl->size = !ctrl->bAddrOnly ? (size - 1) : 0;
 	memcpy(ctrl->data, data, size);
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
+	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+	if (ret) {
+		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
 		return PTR_ERR(ctrl);
+	}
 
 	memcpy(data, ctrl->data, size);
 	*psize = ctrl->size;
@@ -1111,10 +1154,13 @@ r535_tmds_edid_get(struct nvkm_outp *outp, u8 *data, u16 *psize)
 	ctrl->subDeviceInstance = 0;
 	ctrl->displayId = BIT(outp->index);
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+	if (ret) {
+		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		return ret;
+	}
 
+	ret = -E2BIG;
 	if (ctrl->bufferSize <= *psize) {
 		memcpy(data, ctrl->edidBuffer, ctrl->bufferSize);
 		*psize = ctrl->bufferSize;
@@ -1153,9 +1199,11 @@ r535_outp_new(struct nvkm_disp *disp, u32 id)
 	ctrl->subDeviceInstance = 0;
 	ctrl->displayId = BIT(id);
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+	if (ret) {
+		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		return ret;
+	}
 
 	switch (ctrl->type) {
 	case NV0073_CTRL_SPECIFIC_OR_TYPE_NONE:
@@ -1229,9 +1277,11 @@ r535_outp_new(struct nvkm_disp *disp, u32 id)
 
 		ctrl->sorIndex = ~0;
 
-		ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-		if (IS_ERR(ctrl))
-			return PTR_ERR(ctrl);
+		ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+		if (ret) {
+			nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+			return ret;
+		}
 
 		switch (NVVAL_GET(ctrl->maxLinkRate, NV0073_CTRL_CMD, DP_GET_CAPS, MAX_LINK_RATE)) {
 		case NV0073_CTRL_CMD_DP_GET_CAPS_MAX_LINK_RATE_1_62:
@@ -1465,8 +1515,6 @@ r535_disp_oneinit(struct nvkm_disp *disp)
 				bool nvhg = acpi_check_dsm(handle, &NVHG_DSM_GUID, NVHG_DSM_REV,
 						           1ULL << 0x00000014);
 
-				printk(KERN_ERR "bl: nbci:%d nvhg:%d\n", nbci, nvhg);
-
 				if (nbci || nvhg) {
 					union acpi_object argv4 = {
 						.buffer.type    = ACPI_TYPE_BUFFER,
@@ -1479,9 +1527,6 @@ r535_disp_oneinit(struct nvkm_disp *disp)
 					if (!obj) {
 						acpi_handle_info(handle, "failed to evaluate _DSM\n");
 					} else {
-						printk(KERN_ERR "bl: obj type %d\n", obj->type);
-						printk(KERN_ERR "bl: obj len %d\n", obj->package.count);
-
 						for (int i = 0; i < obj->package.count; i++) {
 							union acpi_object *elt = &obj->package.elements[i];
 							u32 size;
@@ -1491,12 +1536,10 @@ r535_disp_oneinit(struct nvkm_disp *disp)
 							else
 								size = 4;
 
-							printk(KERN_ERR "elt %03d: type %d size %d\n", i, elt->type, size);
 							memcpy(&ctrl->backLightData[ctrl->backLightDataSize], &elt->integer.value, size);
 							ctrl->backLightDataSize += size;
 						}
 
-						printk(KERN_ERR "bl: data size %d\n", ctrl->backLightDataSize);
 						ctrl->status = 0;
 						ACPI_FREE(obj);
 					}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c
index e4279f1772a1..377d0e0cef84 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c
@@ -385,7 +385,7 @@ nvkm_uoutp_mthd_inherit(struct nvkm_outp *outp, void *argv, u32 argc)
 
 	/* Ensure an ior is hooked up to this outp already */
 	ior = outp->func->inherit(outp);
-	if (!ior)
+	if (!ior || !ior->arm.head)
 		return -ENODEV;
 
 	/* With iors, there will be a separate output path for each type of connector - and all of
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c
index 3adbb05ff587..b903785056b5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c
@@ -242,6 +242,7 @@ r535_chan_id_put(struct nvkm_chan *chan)
 				nvkm_memory_unref(&userd->mem);
 				nvkm_chid_put(runl->chid, userd->chid, &chan->cgrp->lock);
 				list_del(&userd->head);
+				kfree(userd);
 			}
 
 			break;
@@ -539,7 +540,7 @@ r535_fifo_runl_ctor(struct nvkm_fifo *fifo)
 	struct nvkm_runl *runl;
 	struct nvkm_engn *engn;
 	u32 cgids = 2048;
-	u32 chids = 2048 / CHID_PER_USERD;
+	u32 chids = 2048;
 	int ret;
 	NV2080_CTRL_FIFO_GET_DEVICE_INFO_TABLE_PARAMS *ctrl;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index e31f9641114b..9ee58e2a0eb2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -70,6 +70,20 @@ struct r535_gsp_msg {
 
 #define GSP_MSG_HDR_SIZE offsetof(struct r535_gsp_msg, data)
 
+static int
+r535_rpc_status_to_errno(uint32_t rpc_status)
+{
+	switch (rpc_status) {
+	case 0x55: /* NV_ERR_NOT_READY */
+	case 0x66: /* NV_ERR_TIMEOUT_RETRY */
+		return -EAGAIN;
+	case 0x51: /* NV_ERR_NO_MEMORY */
+		return -ENOMEM;
+	default:
+		return -EINVAL;
+	}
+}
+
 static void *
 r535_gsp_msgq_wait(struct nvkm_gsp *gsp, u32 repc, u32 *prepc, int *ptime)
 {
@@ -298,7 +312,8 @@ retry:
 		struct nvkm_gsp_msgq_ntfy *ntfy = &gsp->msgq.ntfy[i];
 
 		if (ntfy->fn == msg->function) {
-			ntfy->func(ntfy->priv, ntfy->fn, msg->data, msg->length - sizeof(*msg));
+			if (ntfy->func)
+				ntfy->func(ntfy->priv, ntfy->fn, msg->data, msg->length - sizeof(*msg));
 			break;
 		}
 	}
@@ -365,10 +380,8 @@ r535_gsp_rpc_send(struct nvkm_gsp *gsp, void *argv, bool wait, u32 repc)
 	}
 
 	ret = r535_gsp_cmdq_push(gsp, rpc);
-	if (ret) {
-		mutex_unlock(&gsp->cmdq.mutex);
+	if (ret)
 		return ERR_PTR(ret);
-	}
 
 	if (wait) {
 		msg = r535_gsp_msg_recv(gsp, fn, repc);
@@ -585,14 +598,14 @@ r535_gsp_rpc_rm_alloc_push(struct nvkm_gsp_object *object, void *argv, u32 repc)
 		return rpc;
 
 	if (rpc->status) {
-		nvkm_error(&gsp->subdev, "RM_ALLOC: 0x%x\n", rpc->status);
-		ret = ERR_PTR(-EINVAL);
+		ret = ERR_PTR(r535_rpc_status_to_errno(rpc->status));
+		if (PTR_ERR(ret) != -EAGAIN)
+			nvkm_error(&gsp->subdev, "RM_ALLOC: 0x%x\n", rpc->status);
 	} else {
 		ret = repc ? rpc->params : NULL;
 	}
 
-	if (IS_ERR_OR_NULL(ret))
-		nvkm_gsp_rpc_done(gsp, rpc);
+	nvkm_gsp_rpc_done(gsp, rpc);
 
 	return ret;
 }
@@ -625,29 +638,34 @@ r535_gsp_rpc_rm_ctrl_done(struct nvkm_gsp_object *object, void *repv)
 {
 	rpc_gsp_rm_control_v03_00 *rpc = container_of(repv, typeof(*rpc), params);
 
+	if (!repv)
+		return;
 	nvkm_gsp_rpc_done(object->client->gsp, rpc);
 }
 
-static void *
-r535_gsp_rpc_rm_ctrl_push(struct nvkm_gsp_object *object, void *argv, u32 repc)
+static int
+r535_gsp_rpc_rm_ctrl_push(struct nvkm_gsp_object *object, void **argv, u32 repc)
 {
-	rpc_gsp_rm_control_v03_00 *rpc = container_of(argv, typeof(*rpc), params);
+	rpc_gsp_rm_control_v03_00 *rpc = container_of((*argv), typeof(*rpc), params);
 	struct nvkm_gsp *gsp = object->client->gsp;
-	void *ret;
+	int ret = 0;
 
 	rpc = nvkm_gsp_rpc_push(gsp, rpc, true, repc);
-	if (IS_ERR_OR_NULL(rpc))
-		return rpc;
+	if (IS_ERR_OR_NULL(rpc)) {
+		*argv = NULL;
+		return PTR_ERR(rpc);
+	}
 
 	if (rpc->status) {
-		nvkm_error(&gsp->subdev, "cli:0x%08x obj:0x%08x ctrl cmd:0x%08x failed: 0x%08x\n",
-			   object->client->object.handle, object->handle, rpc->cmd, rpc->status);
-		ret = ERR_PTR(-EINVAL);
-	} else {
-		ret = repc ? rpc->params : NULL;
+		ret = r535_rpc_status_to_errno(rpc->status);
+		if (ret != -EAGAIN)
+			nvkm_error(&gsp->subdev, "cli:0x%08x obj:0x%08x ctrl cmd:0x%08x failed: 0x%08x\n",
+				   object->client->object.handle, object->handle, rpc->cmd, rpc->status);
 	}
 
-	if (IS_ERR_OR_NULL(ret))
+	if (repc)
+		*argv = rpc->params;
+	else
 		nvkm_gsp_rpc_done(gsp, rpc);
 
 	return ret;
@@ -689,8 +707,8 @@ r535_gsp_rpc_get(struct nvkm_gsp *gsp, u32 fn, u32 argc)
 	struct nvfw_gsp_rpc *rpc;
 
 	rpc = r535_gsp_cmdq_get(gsp, ALIGN(sizeof(*rpc) + argc, sizeof(u64)));
-	if (!rpc)
-		return NULL;
+	if (IS_ERR(rpc))
+		return ERR_CAST(rpc);
 
 	rpc->header_version = 0x03000000;
 	rpc->signature = ('C' << 24) | ('P' << 16) | ('R' << 8) | 'V';
@@ -845,9 +863,11 @@ r535_gsp_intr_get_table(struct nvkm_gsp *gsp)
 	if (IS_ERR(ctrl))
 		return PTR_ERR(ctrl);
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&gsp->internal.device.subdevice, ctrl, sizeof(*ctrl));
-	if (WARN_ON(IS_ERR(ctrl)))
-		return PTR_ERR(ctrl);
+	ret = nvkm_gsp_rm_ctrl_push(&gsp->internal.device.subdevice, &ctrl, sizeof(*ctrl));
+	if (WARN_ON(ret)) {
+		nvkm_gsp_rm_ctrl_done(&gsp->internal.device.subdevice, ctrl);
+		return ret;
+	}
 
 	for (unsigned i = 0; i < ctrl->tableLen; i++) {
 		enum nvkm_subdev_type type;
@@ -1048,7 +1068,7 @@ r535_gsp_rpc_set_registry(struct nvkm_gsp *gsp)
 	char *strings;
 	int str_offset;
 	int i;
-	size_t rpc_size = sizeof(*rpc) + sizeof(rpc->entries[0]) * NV_GSP_REG_NUM_ENTRIES;
+	size_t rpc_size = struct_size(rpc, entries, NV_GSP_REG_NUM_ENTRIES);
 
 	/* add strings + null terminator */
 	for (i = 0; i < NV_GSP_REG_NUM_ENTRIES; i++)
@@ -1101,16 +1121,12 @@ r535_gsp_acpi_caps(acpi_handle handle, CAPS_METHOD_DATA *caps)
 	if (!obj)
 		return;
 
-	printk(KERN_ERR "nvop: obj type %d\n", obj->type);
-	printk(KERN_ERR "nvop: obj len %d\n", obj->buffer.length);
-
 	if (WARN_ON(obj->type != ACPI_TYPE_BUFFER) ||
 	    WARN_ON(obj->buffer.length != 4))
 		return;
 
 	caps->status = 0;
 	caps->optimusCaps = *(u32 *)obj->buffer.pointer;
-	printk(KERN_ERR "nvop: caps %08x\n", caps->optimusCaps);
 
 	ACPI_FREE(obj);
 
@@ -1137,9 +1153,6 @@ r535_gsp_acpi_jt(acpi_handle handle, JT_METHOD_DATA *jt)
 	if (!obj)
 		return;
 
-	printk(KERN_ERR "jt: obj type %d\n", obj->type);
-	printk(KERN_ERR "jt: obj len %d\n", obj->buffer.length);
-
 	if (WARN_ON(obj->type != ACPI_TYPE_BUFFER) ||
 	    WARN_ON(obj->buffer.length != 4))
 		return;
@@ -1148,7 +1161,6 @@ r535_gsp_acpi_jt(acpi_handle handle, JT_METHOD_DATA *jt)
 	jt->jtCaps = *(u32 *)obj->buffer.pointer;
 	jt->jtRevId = (jt->jtCaps & 0xfff00000) >> 20;
 	jt->bSBIOSCaps = 0;
-	printk(KERN_ERR "jt: caps %08x rev:%04x\n", jt->jtCaps, jt->jtRevId);
 
 	ACPI_FREE(obj);
 
@@ -1159,7 +1171,9 @@ static void
 r535_gsp_acpi_mux_id(acpi_handle handle, u32 id, MUX_METHOD_DATA_ELEMENT *mode,
 						 MUX_METHOD_DATA_ELEMENT *part)
 {
-	acpi_handle iter = NULL, handle_mux;
+	union acpi_object mux_arg = { ACPI_TYPE_INTEGER };
+	struct acpi_object_list input = { 1, &mux_arg };
+	acpi_handle iter = NULL, handle_mux = NULL;
 	acpi_status status;
 	unsigned long long value;
 
@@ -1181,14 +1195,18 @@ r535_gsp_acpi_mux_id(acpi_handle handle, u32 id, MUX_METHOD_DATA_ELEMENT *mode,
 	if (!handle_mux)
 		return;
 
-	status = acpi_evaluate_integer(handle_mux, "MXDM", NULL, &value);
+	/* I -think- 0 means "acquire" according to nvidia's driver source */
+	input.pointer->integer.type = ACPI_TYPE_INTEGER;
+	input.pointer->integer.value = 0;
+
+	status = acpi_evaluate_integer(handle_mux, "MXDM", &input, &value);
 	if (ACPI_SUCCESS(status)) {
 		mode->acpiId = id;
 		mode->mode   = value;
 		mode->status = 0;
 	}
 
-	status = acpi_evaluate_integer(handle_mux, "MXDS", NULL, &value);
+	status = acpi_evaluate_integer(handle_mux, "MXDS", &input, &value);
 	if (ACPI_SUCCESS(status)) {
 		part->acpiId = id;
 		part->mode   = value;
@@ -1234,8 +1252,8 @@ r535_gsp_acpi_dod(acpi_handle handle, DOD_METHOD_DATA *dod)
 		dod->acpiIdListLen += sizeof(dod->acpiIdList[0]);
 	}
 
-	printk(KERN_ERR "_DOD: ok! len:%d\n", dod->acpiIdListLen);
 	dod->status = 0;
+	kfree(output.pointer);
 }
 #endif
 
@@ -1379,6 +1397,13 @@ r535_gsp_msg_post_event(void *priv, u32 fn, void *repv, u32 repc)
 	return 0;
 }
 
+/**
+ * r535_gsp_msg_run_cpu_sequencer() -- process I/O commands from the GSP
+ *
+ * The GSP sequencer is a list of I/O commands that the GSP can send to
+ * the driver to perform for various purposes.  The most common usage is to
+ * perform a special mid-initialization reset.
+ */
 static int
 r535_gsp_msg_run_cpu_sequencer(void *priv, u32 fn, void *repv, u32 repc)
 {
@@ -1718,6 +1743,23 @@ r535_gsp_libos_id8(const char *name)
 	return id;
 }
 
+/**
+ * create_pte_array() - creates a PTE array of a physically contiguous buffer
+ * @ptes: pointer to the array
+ * @addr: base address of physically contiguous buffer (GSP_PAGE_SIZE aligned)
+ * @size: size of the buffer
+ *
+ * GSP-RM sometimes expects physically-contiguous buffers to have an array of
+ * "PTEs" for each page in that buffer.  Although in theory that allows for
+ * the buffer to be physically discontiguous, GSP-RM does not currently
+ * support that.
+ *
+ * In this case, the PTEs are DMA addresses of each page of the buffer.  Since
+ * the buffer is physically contiguous, calculating all the PTEs is simple
+ * math.
+ *
+ * See memdescGetPhysAddrsForGpu()
+ */
 static void create_pte_array(u64 *ptes, dma_addr_t addr, size_t size)
 {
 	unsigned int num_pages = DIV_ROUND_UP_ULL(size, GSP_PAGE_SIZE);
@@ -1727,6 +1769,35 @@ static void create_pte_array(u64 *ptes, dma_addr_t addr, size_t size)
 		ptes[i] = (u64)addr + (i << GSP_PAGE_SHIFT);
 }
 
+/**
+ * r535_gsp_libos_init() -- create the libos arguments structure
+ *
+ * The logging buffers are byte queues that contain encoded printf-like
+ * messages from GSP-RM.  They need to be decoded by a special application
+ * that can parse the buffers.
+ *
+ * The 'loginit' buffer contains logs from early GSP-RM init and
+ * exception dumps.  The 'logrm' buffer contains the subsequent logs. Both are
+ * written to directly by GSP-RM and can be any multiple of GSP_PAGE_SIZE.
+ *
+ * The physical address map for the log buffer is stored in the buffer
+ * itself, starting with offset 1. Offset 0 contains the "put" pointer.
+ *
+ * The GSP only understands 4K pages (GSP_PAGE_SIZE), so even if the kernel is
+ * configured for a larger page size (e.g. 64K pages), we need to give
+ * the GSP an array of 4K pages. Fortunately, since the buffer is
+ * physically contiguous, it's simple math to calculate the addresses.
+ *
+ * The buffers must be a multiple of GSP_PAGE_SIZE.  GSP-RM also currently
+ * ignores the @kind field for LOGINIT, LOGINTR, and LOGRM, but expects the
+ * buffers to be physically contiguous anyway.
+ *
+ * The memory allocated for the arguments must remain until the GSP sends the
+ * init_done RPC.
+ *
+ * See _kgspInitLibosLoggingStructures (allocates memory for buffers)
+ * See kgspSetupLibosInitArgs_IMPL (creates pLibosInitArgs[] array)
+ */
 static int
 r535_gsp_libos_init(struct nvkm_gsp *gsp)
 {
@@ -1837,6 +1908,35 @@ nvkm_gsp_radix3_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_radix3 *rx3)
 		nvkm_gsp_mem_dtor(gsp, &rx3->mem[i]);
 }
 
+/**
+ * nvkm_gsp_radix3_sg - build a radix3 table from a S/G list
+ *
+ * The GSP uses a three-level page table, called radix3, to map the firmware.
+ * Each 64-bit "pointer" in the table is either the bus address of an entry in
+ * the next table (for levels 0 and 1) or the bus address of the next page in
+ * the GSP firmware image itself.
+ *
+ * Level 0 contains a single entry in one page that points to the first page
+ * of level 1.
+ *
+ * Level 1, since it's also only one page in size, contains up to 512 entries,
+ * one for each page in Level 2.
+ *
+ * Level 2 can be up to 512 pages in size, and each of those entries points to
+ * the next page of the firmware image.  Since there can be up to 512*512
+ * pages, that limits the size of the firmware to 512*512*GSP_PAGE_SIZE = 1GB.
+ *
+ * Internally, the GSP has its window into system memory, but the base
+ * physical address of the aperture is not 0.  In fact, it varies depending on
+ * the GPU architecture.  Since the GPU is a PCI device, this window is
+ * accessed via DMA and is therefore bound by IOMMU translation.  The end
+ * result is that GSP-RM must translate the bus addresses in the table to GSP
+ * physical addresses.  All this should happen transparently.
+ *
+ * Returns 0 on success, or negative error code
+ *
+ * See kgspCreateRadix3_IMPL
+ */
 static int
 nvkm_gsp_radix3_sg(struct nvkm_device *device, struct sg_table *sgt, u64 size,
 		   struct nvkm_gsp_radix3 *rx3)
@@ -2106,7 +2206,9 @@ r535_gsp_oneinit(struct nvkm_gsp *gsp)
 	r535_gsp_msg_ntfy_add(gsp, NV_VGPU_MSG_EVENT_MMU_FAULT_QUEUED,
 			      r535_gsp_msg_mmu_fault_queued, gsp);
 	r535_gsp_msg_ntfy_add(gsp, NV_VGPU_MSG_EVENT_OS_ERROR_LOG, r535_gsp_msg_os_error_log, gsp);
-
+	r535_gsp_msg_ntfy_add(gsp, NV_VGPU_MSG_EVENT_PERF_BRIDGELESS_INFO_UPDATE, NULL, NULL);
+	r535_gsp_msg_ntfy_add(gsp, NV_VGPU_MSG_EVENT_UCODE_LIBOS_PRINT, NULL, NULL);
+	r535_gsp_msg_ntfy_add(gsp, NV_VGPU_MSG_EVENT_GSP_SEND_USER_SHARED_DATA, NULL, NULL);
 	ret = r535_gsp_rm_boot_ctor(gsp);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c
index 1b811d6972a1..201022ae9214 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c
@@ -49,14 +49,14 @@
 #include <subdev/mmu.h>
 
 struct gk20a_instobj {
-	struct nvkm_memory memory;
+	struct nvkm_instobj base;
 	struct nvkm_mm_node *mn;
 	struct gk20a_instmem *imem;
 
 	/* CPU mapping */
 	u32 *vaddr;
 };
-#define gk20a_instobj(p) container_of((p), struct gk20a_instobj, memory)
+#define gk20a_instobj(p) container_of((p), struct gk20a_instobj, base.memory)
 
 /*
  * Used for objects allocated using the DMA API
@@ -148,7 +148,7 @@ gk20a_instobj_iommu_recycle_vaddr(struct gk20a_instobj_iommu *obj)
 	list_del(&obj->vaddr_node);
 	vunmap(obj->base.vaddr);
 	obj->base.vaddr = NULL;
-	imem->vaddr_use -= nvkm_memory_size(&obj->base.memory);
+	imem->vaddr_use -= nvkm_memory_size(&obj->base.base.memory);
 	nvkm_debug(&imem->base.subdev, "vaddr used: %x/%x\n", imem->vaddr_use,
 		   imem->vaddr_max);
 }
@@ -283,7 +283,7 @@ gk20a_instobj_map(struct nvkm_memory *memory, u64 offset, struct nvkm_vmm *vmm,
 {
 	struct gk20a_instobj *node = gk20a_instobj(memory);
 	struct nvkm_vmm_map map = {
-		.memory = &node->memory,
+		.memory = &node->base.memory,
 		.offset = offset,
 		.mem = node->mn,
 	};
@@ -391,8 +391,8 @@ gk20a_instobj_ctor_dma(struct gk20a_instmem *imem, u32 npages, u32 align,
 		return -ENOMEM;
 	*_node = &node->base;
 
-	nvkm_memory_ctor(&gk20a_instobj_func_dma, &node->base.memory);
-	node->base.memory.ptrs = &gk20a_instobj_ptrs;
+	nvkm_memory_ctor(&gk20a_instobj_func_dma, &node->base.base.memory);
+	node->base.base.memory.ptrs = &gk20a_instobj_ptrs;
 
 	node->base.vaddr = dma_alloc_attrs(dev, npages << PAGE_SHIFT,
 					   &node->handle, GFP_KERNEL,
@@ -438,8 +438,8 @@ gk20a_instobj_ctor_iommu(struct gk20a_instmem *imem, u32 npages, u32 align,
 	*_node = &node->base;
 	node->dma_addrs = (void *)(node->pages + npages);
 
-	nvkm_memory_ctor(&gk20a_instobj_func_iommu, &node->base.memory);
-	node->base.memory.ptrs = &gk20a_instobj_ptrs;
+	nvkm_memory_ctor(&gk20a_instobj_func_iommu, &node->base.base.memory);
+	node->base.base.memory.ptrs = &gk20a_instobj_ptrs;
 
 	/* Allocate backing memory */
 	for (i = 0; i < npages; i++) {
@@ -533,7 +533,7 @@ gk20a_instobj_new(struct nvkm_instmem *base, u32 size, u32 align, bool zero,
 	else
 		ret = gk20a_instobj_ctor_dma(imem, size >> PAGE_SHIFT,
 					     align, &node);
-	*pmemory = node ? &node->memory : NULL;
+	*pmemory = node ? &node->base.memory : NULL;
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmtu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmtu102.c
index e34bc6076401..8379e72d77ab 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmtu102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmtu102.c
@@ -31,7 +31,7 @@ tu102_vmm_flush(struct nvkm_vmm *vmm, int depth)
 
 	type |= 0x00000001; /* PAGE_ALL */
 	if (atomic_read(&vmm->engref[NVKM_SUBDEV_BAR]))
-		type |= 0x00000004; /* HUB_ONLY */
+		type |= 0x00000006; /* HUB_ONLY | ALL PDB (hack) */
 
 	mutex_lock(&vmm->mmu->mutex);
 
diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
index 9323e7b9e384..c4c0f08e9202 100644
--- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
+++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
@@ -1709,6 +1709,7 @@ static const struct panel_desc auo_b101uan08_3_desc = {
 	.mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE |
 		      MIPI_DSI_MODE_LPM,
 	.init_cmds = auo_b101uan08_3_init_cmd,
+	.lp11_before_reset = true,
 };
 
 static const struct drm_display_mode boe_tv105wum_nw0_default_mode = {
@@ -1763,14 +1764,15 @@ static const struct panel_desc starry_qfh032011_53g_desc = {
 	.mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE |
 		      MIPI_DSI_MODE_LPM,
 	.init_cmds = starry_qfh032011_53g_init_cmd,
+	.lp11_before_reset = true,
 };
 
 static const struct drm_display_mode starry_himax83102_j02_default_mode = {
-	.clock = 161600,
+	.clock = 162850,
 	.hdisplay = 1200,
-	.hsync_start = 1200 + 40,
-	.hsync_end = 1200 + 40 + 20,
-	.htotal = 1200 + 40 + 20 + 40,
+	.hsync_start = 1200 + 50,
+	.hsync_end = 1200 + 50 + 20,
+	.htotal = 1200 + 50 + 20 + 50,
 	.vdisplay = 1920,
 	.vsync_start = 1920 + 116,
 	.vsync_end = 1920 + 116 + 8,
diff --git a/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c b/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c
index 6e3670508e3a..30919c872ac8 100644
--- a/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c
+++ b/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c
@@ -326,7 +326,7 @@ static const struct drm_display_mode ltk050h3148w_mode = {
 static const struct ltk050h3146w_desc ltk050h3148w_data = {
 	.mode = &ltk050h3148w_mode,
 	.init = ltk050h3148w_init_sequence,
-	.mode_flags = MIPI_DSI_MODE_VIDEO_SYNC_PULSE,
+	.mode_flags = MIPI_DSI_MODE_VIDEO_SYNC_PULSE | MIPI_DSI_MODE_VIDEO_BURST,
 };
 
 static int ltk050h3146w_init_sequence(struct ltk050h3146w *ctx)
diff --git a/drivers/gpu/drm/panel/panel-novatek-nt36523.c b/drivers/gpu/drm/panel/panel-novatek-nt36523.c
index 9b9a7eb1bc60..a189ce236328 100644
--- a/drivers/gpu/drm/panel/panel-novatek-nt36523.c
+++ b/drivers/gpu/drm/panel/panel-novatek-nt36523.c
@@ -1254,9 +1254,9 @@ static int nt36523_probe(struct mipi_dsi_device *dsi)
 			return dev_err_probe(dev, -EPROBE_DEFER, "cannot get secondary DSI host\n");
 
 		pinfo->dsi[1] = mipi_dsi_device_register_full(dsi1_host, info);
-		if (!pinfo->dsi[1]) {
+		if (IS_ERR(pinfo->dsi[1])) {
 			dev_err(dev, "cannot get secondary DSI device\n");
-			return -ENODEV;
+			return PTR_ERR(pinfo->dsi[1]);
 		}
 	}
 
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 6cd32b909087..9367a4572dcf 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -2379,13 +2379,13 @@ static const struct panel_desc innolux_g070y2_t02 = {
 static const struct display_timing innolux_g101ice_l01_timing = {
 	.pixelclock = { 60400000, 71100000, 74700000 },
 	.hactive = { 1280, 1280, 1280 },
-	.hfront_porch = { 41, 80, 100 },
-	.hback_porch = { 40, 79, 99 },
-	.hsync_len = { 1, 1, 1 },
+	.hfront_porch = { 30, 60, 70 },
+	.hback_porch = { 30, 60, 70 },
+	.hsync_len = { 22, 40, 60 },
 	.vactive = { 800, 800, 800 },
-	.vfront_porch = { 5, 11, 14 },
-	.vback_porch = { 4, 11, 14 },
-	.vsync_len = { 1, 1, 1 },
+	.vfront_porch = { 3, 8, 14 },
+	.vback_porch = { 3, 8, 14 },
+	.vsync_len = { 4, 7, 12 },
 	.flags = DISPLAY_FLAGS_DE_HIGH,
 };
 
@@ -2402,6 +2402,7 @@ static const struct panel_desc innolux_g101ice_l01 = {
 		.disable = 200,
 	},
 	.bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH,
 	.connector_type = DRM_MODE_CONNECTOR_LVDS,
 };
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
index f59c82ea8870..2d30da38c2c3 100644
--- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c
+++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
@@ -29,14 +29,20 @@ static void panfrost_devfreq_update_utilization(struct panfrost_devfreq *pfdevfr
 static int panfrost_devfreq_target(struct device *dev, unsigned long *freq,
 				   u32 flags)
 {
+	struct panfrost_device *ptdev = dev_get_drvdata(dev);
 	struct dev_pm_opp *opp;
+	int err;
 
 	opp = devfreq_recommended_opp(dev, freq, flags);
 	if (IS_ERR(opp))
 		return PTR_ERR(opp);
 	dev_pm_opp_put(opp);
 
-	return dev_pm_opp_set_rate(dev, *freq);
+	err =  dev_pm_opp_set_rate(dev, *freq);
+	if (!err)
+		ptdev->pfdevfreq.current_frequency = *freq;
+
+	return err;
 }
 
 static void panfrost_devfreq_reset(struct panfrost_devfreq *pfdevfreq)
@@ -58,7 +64,6 @@ static int panfrost_devfreq_get_dev_status(struct device *dev,
 	spin_lock_irqsave(&pfdevfreq->lock, irqflags);
 
 	panfrost_devfreq_update_utilization(pfdevfreq);
-	pfdevfreq->current_frequency = status->current_frequency;
 
 	status->total_time = ktime_to_ns(ktime_add(pfdevfreq->busy_time,
 						   pfdevfreq->idle_time));
@@ -165,6 +170,14 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev)
 	panfrost_devfreq_profile.initial_freq = cur_freq;
 
 	/*
+	 * We could wait until panfrost_devfreq_target() to set this value, but
+	 * since the simple_ondemand governor works asynchronously, there's a
+	 * chance by the time someone opens the device's fdinfo file, current
+	 * frequency hasn't been updated yet, so let's just do an early set.
+	 */
+	pfdevfreq->current_frequency = cur_freq;
+
+	/*
 	 * Set the recommend OPP this will enable and configure the regulator
 	 * if any and will avoid a switch off by regulator_late_cleanup()
 	 */
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c
index 0cf64456e29a..d47b40b82b0b 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.c
@@ -200,7 +200,7 @@ static enum drm_gem_object_status panfrost_gem_status(struct drm_gem_object *obj
 	struct panfrost_gem_object *bo = to_panfrost_bo(obj);
 	enum drm_gem_object_status res = 0;
 
-	if (bo->base.pages)
+	if (bo->base.base.import_attach || bo->base.pages)
 		res |= DRM_GEM_OBJECT_RESIDENT;
 
 	if (bo->base.madv == PANFROST_MADV_DONTNEED)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index 066299894d04..a13473b2d54c 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -247,14 +247,22 @@ static inline void vop_cfg_done(struct vop *vop)
 	VOP_REG_SET(vop, common, cfg_done, 1);
 }
 
-static bool has_rb_swapped(uint32_t format)
+static bool has_rb_swapped(uint32_t version, uint32_t format)
 {
 	switch (format) {
 	case DRM_FORMAT_XBGR8888:
 	case DRM_FORMAT_ABGR8888:
-	case DRM_FORMAT_BGR888:
 	case DRM_FORMAT_BGR565:
 		return true;
+	/*
+	 * full framework (IP version 3.x) only need rb swapped for RGB888 and
+	 * little framework (IP version 2.x) only need rb swapped for BGR888,
+	 * check for 3.x to also only rb swap BGR888 for unknown vop version
+	 */
+	case DRM_FORMAT_RGB888:
+		return VOP_MAJOR(version) == 3;
+	case DRM_FORMAT_BGR888:
+		return VOP_MAJOR(version) != 3;
 	default:
 		return false;
 	}
@@ -1030,7 +1038,7 @@ static void vop_plane_atomic_update(struct drm_plane *plane,
 	VOP_WIN_SET(vop, win, dsp_info, dsp_info);
 	VOP_WIN_SET(vop, win, dsp_st, dsp_st);
 
-	rb_swap = has_rb_swapped(fb->format->format);
+	rb_swap = has_rb_swapped(vop->data->version, fb->format->format);
 	VOP_WIN_SET(vop, win, rb_swap, rb_swap);
 
 	/*
diff --git a/drivers/gpu/drm/tests/drm_kunit_helpers.c b/drivers/gpu/drm/tests/drm_kunit_helpers.c
index bccb33b900f3..ca4f8e4c5d5d 100644
--- a/drivers/gpu/drm/tests/drm_kunit_helpers.c
+++ b/drivers/gpu/drm/tests/drm_kunit_helpers.c
@@ -5,6 +5,7 @@
 #include <drm/drm_kunit_helpers.h>
 #include <drm/drm_managed.h>
 
+#include <kunit/device.h>
 #include <kunit/resource.h>
 
 #include <linux/device.h>
@@ -15,40 +16,6 @@
 static const struct drm_mode_config_funcs drm_mode_config_funcs = {
 };
 
-static int fake_probe(struct platform_device *pdev)
-{
-	return 0;
-}
-
-static struct platform_driver fake_platform_driver = {
-	.probe	= fake_probe,
-	.driver = {
-		.name	= KUNIT_DEVICE_NAME,
-	},
-};
-
-static void kunit_action_platform_driver_unregister(void *ptr)
-{
-	struct platform_driver *drv = ptr;
-
-	platform_driver_unregister(drv);
-
-}
-
-static void kunit_action_platform_device_put(void *ptr)
-{
-	struct platform_device *pdev = ptr;
-
-	platform_device_put(pdev);
-}
-
-static void kunit_action_platform_device_del(void *ptr)
-{
-	struct platform_device *pdev = ptr;
-
-	platform_device_del(pdev);
-}
-
 /**
  * drm_kunit_helper_alloc_device - Allocate a mock device for a KUnit test
  * @test: The test context object
@@ -66,34 +33,7 @@ static void kunit_action_platform_device_del(void *ptr)
  */
 struct device *drm_kunit_helper_alloc_device(struct kunit *test)
 {
-	struct platform_device *pdev;
-	int ret;
-
-	ret = platform_driver_register(&fake_platform_driver);
-	KUNIT_ASSERT_EQ(test, ret, 0);
-
-	ret = kunit_add_action_or_reset(test,
-					kunit_action_platform_driver_unregister,
-					&fake_platform_driver);
-	KUNIT_ASSERT_EQ(test, ret, 0);
-
-	pdev = platform_device_alloc(KUNIT_DEVICE_NAME, PLATFORM_DEVID_NONE);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pdev);
-
-	ret = kunit_add_action_or_reset(test,
-					kunit_action_platform_device_put,
-					pdev);
-	KUNIT_ASSERT_EQ(test, ret, 0);
-
-	ret = platform_device_add(pdev);
-	KUNIT_ASSERT_EQ(test, ret, 0);
-
-	ret = kunit_add_action_or_reset(test,
-					kunit_action_platform_device_del,
-					pdev);
-	KUNIT_ASSERT_EQ(test, ret, 0);
-
-	return &pdev->dev;
+	return kunit_device_register(test, KUNIT_DEVICE_NAME);
 }
 EXPORT_SYMBOL_GPL(drm_kunit_helper_alloc_device);
 
@@ -106,19 +46,7 @@ EXPORT_SYMBOL_GPL(drm_kunit_helper_alloc_device);
  */
 void drm_kunit_helper_free_device(struct kunit *test, struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-
-	kunit_release_action(test,
-			     kunit_action_platform_device_del,
-			     pdev);
-
-	kunit_release_action(test,
-			     kunit_action_platform_device_put,
-			     pdev);
-
-	kunit_release_action(test,
-			     kunit_action_platform_driver_unregister,
-			     &fake_platform_driver);
+	kunit_device_unregister(test, dev);
 }
 EXPORT_SYMBOL_GPL(drm_kunit_helper_free_device);
 
diff --git a/drivers/gpu/drm/ttm/tests/ttm_device_test.c b/drivers/gpu/drm/ttm/tests/ttm_device_test.c
index b1b423b68cdf..19eaff22e6ae 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_device_test.c
+++ b/drivers/gpu/drm/ttm/tests/ttm_device_test.c
@@ -175,7 +175,7 @@ static void ttm_device_init_pools(struct kunit *test)
 
 	if (params->pools_init_expected) {
 		for (int i = 0; i < TTM_NUM_CACHING_TYPES; ++i) {
-			for (int j = 0; j <= MAX_ORDER; ++j) {
+			for (int j = 0; j < NR_PAGE_ORDERS; ++j) {
 				pt = pool->caching[i].orders[j];
 				KUNIT_EXPECT_PTR_EQ(test, pt.pool, pool);
 				KUNIT_EXPECT_EQ(test, pt.caching, i);
diff --git a/drivers/gpu/drm/ttm/tests/ttm_pool_test.c b/drivers/gpu/drm/ttm/tests/ttm_pool_test.c
index 2d9cae8cd984..cceaa18d4e46 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_pool_test.c
+++ b/drivers/gpu/drm/ttm/tests/ttm_pool_test.c
@@ -109,7 +109,7 @@ static const struct ttm_pool_test_case ttm_pool_basic_cases[] = {
 	},
 	{
 		.description = "Above the allocation limit",
-		.order = MAX_ORDER + 1,
+		.order = MAX_PAGE_ORDER + 1,
 	},
 	{
 		.description = "One page, with coherent DMA mappings enabled",
@@ -118,7 +118,7 @@ static const struct ttm_pool_test_case ttm_pool_basic_cases[] = {
 	},
 	{
 		.description = "Above the allocation limit, with coherent DMA mappings enabled",
-		.order = MAX_ORDER + 1,
+		.order = MAX_PAGE_ORDER + 1,
 		.use_dma_alloc = true,
 	},
 };
@@ -165,7 +165,7 @@ static void ttm_pool_alloc_basic(struct kunit *test)
 	fst_page = tt->pages[0];
 	last_page = tt->pages[tt->num_pages - 1];
 
-	if (params->order <= MAX_ORDER) {
+	if (params->order <= MAX_PAGE_ORDER) {
 		if (params->use_dma_alloc) {
 			KUNIT_ASSERT_NOT_NULL(test, (void *)fst_page->private);
 			KUNIT_ASSERT_NOT_NULL(test, (void *)last_page->private);
@@ -182,7 +182,7 @@ static void ttm_pool_alloc_basic(struct kunit *test)
 			 * order 0 blocks
 			 */
 			KUNIT_ASSERT_EQ(test, fst_page->private,
-					min_t(unsigned int, MAX_ORDER,
+					min_t(unsigned int, MAX_PAGE_ORDER,
 					      params->order));
 			KUNIT_ASSERT_EQ(test, last_page->private, 0);
 		}
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index fe610a3cace0..b62f420a9f96 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -65,11 +65,11 @@ module_param(page_pool_size, ulong, 0644);
 
 static atomic_long_t allocated_pages;
 
-static struct ttm_pool_type global_write_combined[MAX_ORDER + 1];
-static struct ttm_pool_type global_uncached[MAX_ORDER + 1];
+static struct ttm_pool_type global_write_combined[NR_PAGE_ORDERS];
+static struct ttm_pool_type global_uncached[NR_PAGE_ORDERS];
 
-static struct ttm_pool_type global_dma32_write_combined[MAX_ORDER + 1];
-static struct ttm_pool_type global_dma32_uncached[MAX_ORDER + 1];
+static struct ttm_pool_type global_dma32_write_combined[NR_PAGE_ORDERS];
+static struct ttm_pool_type global_dma32_uncached[NR_PAGE_ORDERS];
 
 static spinlock_t shrinker_lock;
 static struct list_head shrinker_list;
@@ -447,7 +447,7 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt,
 	else
 		gfp_flags |= GFP_HIGHUSER;
 
-	for (order = min_t(unsigned int, MAX_ORDER, __fls(num_pages));
+	for (order = min_t(unsigned int, MAX_PAGE_ORDER, __fls(num_pages));
 	     num_pages;
 	     order = min_t(unsigned int, order, __fls(num_pages))) {
 		struct ttm_pool_type *pt;
@@ -568,7 +568,7 @@ void ttm_pool_init(struct ttm_pool *pool, struct device *dev,
 
 	if (use_dma_alloc || nid != NUMA_NO_NODE) {
 		for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
-			for (j = 0; j <= MAX_ORDER; ++j)
+			for (j = 0; j < NR_PAGE_ORDERS; ++j)
 				ttm_pool_type_init(&pool->caching[i].orders[j],
 						   pool, i, j);
 	}
@@ -601,7 +601,7 @@ void ttm_pool_fini(struct ttm_pool *pool)
 
 	if (pool->use_dma_alloc || pool->nid != NUMA_NO_NODE) {
 		for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
-			for (j = 0; j <= MAX_ORDER; ++j)
+			for (j = 0; j < NR_PAGE_ORDERS; ++j)
 				ttm_pool_type_fini(&pool->caching[i].orders[j]);
 	}
 
@@ -656,7 +656,7 @@ static void ttm_pool_debugfs_header(struct seq_file *m)
 	unsigned int i;
 
 	seq_puts(m, "\t ");
-	for (i = 0; i <= MAX_ORDER; ++i)
+	for (i = 0; i < NR_PAGE_ORDERS; ++i)
 		seq_printf(m, " ---%2u---", i);
 	seq_puts(m, "\n");
 }
@@ -667,7 +667,7 @@ static void ttm_pool_debugfs_orders(struct ttm_pool_type *pt,
 {
 	unsigned int i;
 
-	for (i = 0; i <= MAX_ORDER; ++i)
+	for (i = 0; i < NR_PAGE_ORDERS; ++i)
 		seq_printf(m, " %8u", ttm_pool_type_count(&pt[i]));
 	seq_puts(m, "\n");
 }
@@ -776,7 +776,7 @@ int ttm_pool_mgr_init(unsigned long num_pages)
 	spin_lock_init(&shrinker_lock);
 	INIT_LIST_HEAD(&shrinker_list);
 
-	for (i = 0; i <= MAX_ORDER; ++i) {
+	for (i = 0; i < NR_PAGE_ORDERS; ++i) {
 		ttm_pool_type_init(&global_write_combined[i], NULL,
 				   ttm_write_combined, i);
 		ttm_pool_type_init(&global_uncached[i], NULL, ttm_uncached, i);
@@ -816,7 +816,7 @@ void ttm_pool_mgr_fini(void)
 {
 	unsigned int i;
 
-	for (i = 0; i <= MAX_ORDER; ++i) {
+	for (i = 0; i < NR_PAGE_ORDERS; ++i) {
 		ttm_pool_type_fini(&global_write_combined[i]);
 		ttm_pool_type_fini(&global_uncached[i]);
 
diff --git a/drivers/gpu/drm/vc4/tests/vc4_mock.c b/drivers/gpu/drm/vc4/tests/vc4_mock.c
index 63ca46f4cb35..becb3dbaa548 100644
--- a/drivers/gpu/drm/vc4/tests/vc4_mock.c
+++ b/drivers/gpu/drm/vc4/tests/vc4_mock.c
@@ -153,12 +153,9 @@ static int __build_mock(struct kunit *test, struct drm_device *drm,
 	return 0;
 }
 
-static void kunit_action_drm_dev_unregister(void *ptr)
-{
-	struct drm_device *drm = ptr;
-
-	drm_dev_unregister(drm);
-}
+KUNIT_DEFINE_ACTION_WRAPPER(kunit_action_drm_dev_unregister,
+			    drm_dev_unregister,
+			    struct drm_device *);
 
 static struct vc4_dev *__mock_device(struct kunit *test, bool is_vc5)
 {
diff --git a/drivers/greybus/Kconfig b/drivers/greybus/Kconfig
index 033d31dbf3b8..ab81ceceb337 100644
--- a/drivers/greybus/Kconfig
+++ b/drivers/greybus/Kconfig
@@ -20,6 +20,7 @@ if GREYBUS
 config GREYBUS_BEAGLEPLAY
 	tristate "Greybus BeaglePlay driver"
 	depends on SERIAL_DEV_BUS
+	select CRC_CCITT
 	help
 	  Select this option if you have a BeaglePlay where CC1352
 	  co-processor acts as Greybus SVC.
diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index 3ca45975c686..b9c7c0ed7bcc 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -345,6 +345,10 @@ static const struct apple_non_apple_keyboard non_apple_keyboards[] = {
 	{ "AONE" },
 	{ "GANSS" },
 	{ "Hailuck" },
+	{ "Jamesdonkey" },
+	{ "A3R" },
+	{ "hfd.cn" },
+	{ "WKB603" },
 };
 
 static bool apple_is_non_apple_keyboard(struct hid_device *hdev)
diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index fd61dba88233..78cdfb8b9a7a 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -381,7 +381,7 @@ static int asus_raw_event(struct hid_device *hdev,
 	return 0;
 }
 
-static int asus_kbd_set_report(struct hid_device *hdev, u8 *buf, size_t buf_size)
+static int asus_kbd_set_report(struct hid_device *hdev, const u8 *buf, size_t buf_size)
 {
 	unsigned char *dmabuf;
 	int ret;
@@ -404,7 +404,7 @@ static int asus_kbd_set_report(struct hid_device *hdev, u8 *buf, size_t buf_size
 
 static int asus_kbd_init(struct hid_device *hdev)
 {
-	u8 buf[] = { FEATURE_KBD_REPORT_ID, 0x41, 0x53, 0x55, 0x53, 0x20, 0x54,
+	const u8 buf[] = { FEATURE_KBD_REPORT_ID, 0x41, 0x53, 0x55, 0x53, 0x20, 0x54,
 		     0x65, 0x63, 0x68, 0x2e, 0x49, 0x6e, 0x63, 0x2e, 0x00 };
 	int ret;
 
@@ -418,7 +418,7 @@ static int asus_kbd_init(struct hid_device *hdev)
 static int asus_kbd_get_functions(struct hid_device *hdev,
 				  unsigned char *kbd_func)
 {
-	u8 buf[] = { FEATURE_KBD_REPORT_ID, 0x05, 0x20, 0x31, 0x00, 0x08 };
+	const u8 buf[] = { FEATURE_KBD_REPORT_ID, 0x05, 0x20, 0x31, 0x00, 0x08 };
 	u8 *readbuf;
 	int ret;
 
@@ -449,7 +449,7 @@ static int asus_kbd_get_functions(struct hid_device *hdev,
 
 static int rog_nkey_led_init(struct hid_device *hdev)
 {
-	u8 buf_init_start[] = { FEATURE_KBD_LED_REPORT_ID1, 0xB9 };
+	const u8 buf_init_start[] = { FEATURE_KBD_LED_REPORT_ID1, 0xB9 };
 	u8 buf_init2[] = { FEATURE_KBD_LED_REPORT_ID1, 0x41, 0x53, 0x55, 0x53, 0x20,
 				0x54, 0x65, 0x63, 0x68, 0x2e, 0x49, 0x6e, 0x63, 0x2e, 0x00 };
 	u8 buf_init3[] = { FEATURE_KBD_LED_REPORT_ID1,
@@ -1000,6 +1000,24 @@ static int asus_start_multitouch(struct hid_device *hdev)
 	return 0;
 }
 
+static int __maybe_unused asus_resume(struct hid_device *hdev) {
+	struct asus_drvdata *drvdata = hid_get_drvdata(hdev);
+	int ret = 0;
+
+	if (drvdata->kbd_backlight) {
+		const u8 buf[] = { FEATURE_KBD_REPORT_ID, 0xba, 0xc5, 0xc4,
+				drvdata->kbd_backlight->cdev.brightness };
+		ret = asus_kbd_set_report(hdev, buf, sizeof(buf));
+		if (ret < 0) {
+			hid_err(hdev, "Asus failed to set keyboard backlight: %d\n", ret);
+			goto asus_resume_err;
+		}
+	}
+
+asus_resume_err:
+	return ret;
+}
+
 static int __maybe_unused asus_reset_resume(struct hid_device *hdev)
 {
 	struct asus_drvdata *drvdata = hid_get_drvdata(hdev);
@@ -1294,6 +1312,7 @@ static struct hid_driver asus_driver = {
 	.input_configured       = asus_input_configured,
 #ifdef CONFIG_PM
 	.reset_resume           = asus_reset_resume,
+	.resume					= asus_resume,
 #endif
 	.event			= asus_event,
 	.raw_event		= asus_raw_event
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 8992e3c1e769..e0181218ad85 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -702,15 +702,22 @@ static void hid_close_report(struct hid_device *device)
  * Free a device structure, all reports, and all fields.
  */
 
-static void hid_device_release(struct device *dev)
+void hiddev_free(struct kref *ref)
 {
-	struct hid_device *hid = to_hid_device(dev);
+	struct hid_device *hid = container_of(ref, struct hid_device, ref);
 
 	hid_close_report(hid);
 	kfree(hid->dev_rdesc);
 	kfree(hid);
 }
 
+static void hid_device_release(struct device *dev)
+{
+	struct hid_device *hid = to_hid_device(dev);
+
+	kref_put(&hid->ref, hiddev_free);
+}
+
 /*
  * Fetch a report description item from the data stream. We support long
  * items, though they are not used yet.
@@ -2846,6 +2853,7 @@ struct hid_device *hid_allocate_device(void)
 	spin_lock_init(&hdev->debug_list_lock);
 	sema_init(&hdev->driver_input_lock, 1);
 	mutex_init(&hdev->ll_open_lock);
+	kref_init(&hdev->ref);
 
 	hid_bpf_device_init(hdev);
 
diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c
index e7ef1ea107c9..7dd83ec74f8a 100644
--- a/drivers/hid/hid-debug.c
+++ b/drivers/hid/hid-debug.c
@@ -1135,6 +1135,7 @@ static int hid_debug_events_open(struct inode *inode, struct file *file)
 		goto out;
 	}
 	list->hdev = (struct hid_device *) inode->i_private;
+	kref_get(&list->hdev->ref);
 	file->private_data = list;
 	mutex_init(&list->read_mutex);
 
@@ -1227,6 +1228,8 @@ static int hid_debug_events_release(struct inode *inode, struct file *file)
 	list_del(&list->node);
 	spin_unlock_irqrestore(&list->hdev->debug_list_lock, flags);
 	kfifo_free(&list->hid_debug_fifo);
+
+	kref_put(&list->hdev->ref, hiddev_free);
 	kfree(list);
 
 	return 0;
diff --git a/drivers/hid/hid-glorious.c b/drivers/hid/hid-glorious.c
index 558eb08c19ef..281b3a7187ce 100644
--- a/drivers/hid/hid-glorious.c
+++ b/drivers/hid/hid-glorious.c
@@ -21,6 +21,10 @@ MODULE_DESCRIPTION("HID driver for Glorious PC Gaming Race mice");
  * Glorious Model O and O- specify the const flag in the consumer input
  * report descriptor, which leads to inputs being ignored. Fix this
  * by patching the descriptor.
+ *
+ * Glorious Model I incorrectly specifes the Usage Minimum for its
+ * keyboard HID report, causing keycodes to be misinterpreted.
+ * Fix this by setting Usage Minimum to 0 in that report.
  */
 static __u8 *glorious_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		unsigned int *rsize)
@@ -32,6 +36,10 @@ static __u8 *glorious_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		rdesc[85] = rdesc[113] = rdesc[141] = \
 			HID_MAIN_ITEM_VARIABLE | HID_MAIN_ITEM_RELATIVE;
 	}
+	if (*rsize == 156 && rdesc[41] == 1) {
+		hid_info(hdev, "patching Glorious Model I keyboard report descriptor\n");
+		rdesc[41] = 0;
+	}
 	return rdesc;
 }
 
@@ -44,6 +52,8 @@ static void glorious_update_name(struct hid_device *hdev)
 		model = "Model O"; break;
 	case USB_DEVICE_ID_GLORIOUS_MODEL_D:
 		model = "Model D"; break;
+	case USB_DEVICE_ID_GLORIOUS_MODEL_I:
+		model = "Model I"; break;
 	}
 
 	snprintf(hdev->name, sizeof(hdev->name), "%s %s", "Glorious", model);
@@ -66,10 +76,12 @@ static int glorious_probe(struct hid_device *hdev,
 }
 
 static const struct hid_device_id glorious_devices[] = {
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GLORIOUS,
+	{ HID_USB_DEVICE(USB_VENDOR_ID_SINOWEALTH,
 		USB_DEVICE_ID_GLORIOUS_MODEL_O) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GLORIOUS,
+	{ HID_USB_DEVICE(USB_VENDOR_ID_SINOWEALTH,
 		USB_DEVICE_ID_GLORIOUS_MODEL_D) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LAVIEW,
+		USB_DEVICE_ID_GLORIOUS_MODEL_I) },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, glorious_devices);
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index f7973ccd84a2..72046039d1be 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -511,10 +511,6 @@
 #define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_010A 0x010a
 #define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_E100 0xe100
 
-#define USB_VENDOR_ID_GLORIOUS  0x258a
-#define USB_DEVICE_ID_GLORIOUS_MODEL_D 0x0033
-#define USB_DEVICE_ID_GLORIOUS_MODEL_O 0x0036
-
 #define I2C_VENDOR_ID_GOODIX		0x27c6
 #define I2C_DEVICE_ID_GOODIX_01F0	0x01f0
 
@@ -744,6 +740,10 @@
 
 #define USB_VENDOR_ID_LABTEC		0x1020
 #define USB_DEVICE_ID_LABTEC_WIRELESS_KEYBOARD	0x0006
+#define USB_DEVICE_ID_LABTEC_ODDOR_HANDBRAKE	0x8888
+
+#define USB_VENDOR_ID_LAVIEW		0x22D4
+#define USB_DEVICE_ID_GLORIOUS_MODEL_I	0x1503
 
 #define USB_VENDOR_ID_LCPOWER		0x1241
 #define USB_DEVICE_ID_LCPOWER_LC1000	0xf767
@@ -869,7 +869,6 @@
 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_2		0xc534
 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1	0xc539
 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_1	0xc53f
-#define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_2	0xc547
 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_POWERPLAY	0xc53a
 #define USB_DEVICE_ID_SPACETRAVELLER	0xc623
 #define USB_DEVICE_ID_SPACENAVIGATOR	0xc626
@@ -1160,6 +1159,10 @@
 #define USB_VENDOR_ID_SIGMATEL		0x066F
 #define USB_DEVICE_ID_SIGMATEL_STMP3780	0x3780
 
+#define USB_VENDOR_ID_SINOWEALTH  0x258a
+#define USB_DEVICE_ID_GLORIOUS_MODEL_D 0x0033
+#define USB_DEVICE_ID_GLORIOUS_MODEL_O 0x0036
+
 #define USB_VENDOR_ID_SIS_TOUCH		0x0457
 #define USB_DEVICE_ID_SIS9200_TOUCH	0x9200
 #define USB_DEVICE_ID_SIS817_TOUCH	0x0817
diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c
index 7c1b33be9d13..149a3c74346b 100644
--- a/drivers/hid/hid-lenovo.c
+++ b/drivers/hid/hid-lenovo.c
@@ -692,7 +692,8 @@ static int lenovo_event_cptkbd(struct hid_device *hdev,
 		 * so set middlebutton_state to 3
 		 * to never apply workaround anymore
 		 */
-		if (cptkbd_data->middlebutton_state == 1 &&
+		if (hdev->product == USB_DEVICE_ID_LENOVO_CUSBKBD &&
+				cptkbd_data->middlebutton_state == 1 &&
 				usage->type == EV_REL &&
 				(usage->code == REL_X || usage->code == REL_Y)) {
 			cptkbd_data->middlebutton_state = 3;
diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c
index 8afe3be683ba..e6a8b6d8eab7 100644
--- a/drivers/hid/hid-logitech-dj.c
+++ b/drivers/hid/hid-logitech-dj.c
@@ -1695,12 +1695,11 @@ static int logi_dj_raw_event(struct hid_device *hdev,
 		}
 		/*
 		 * Mouse-only receivers send unnumbered mouse data. The 27 MHz
-		 * receiver uses 6 byte packets, the nano receiver 8 bytes,
-		 * the lightspeed receiver (Pro X Superlight) 13 bytes.
+		 * receiver uses 6 byte packets, the nano receiver 8 bytes.
 		 */
 		if (djrcv_dev->unnumbered_application == HID_GD_MOUSE &&
-		    size <= 13){
-			u8 mouse_report[14];
+		    size <= 8) {
+			u8 mouse_report[9];
 
 			/* Prepend report id */
 			mouse_report[0] = REPORT_TYPE_MOUSE;
@@ -1984,10 +1983,6 @@ static const struct hid_device_id logi_dj_receivers[] = {
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
 		USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_1),
 	 .driver_data = recvr_type_gaming_hidpp},
-	{ /* Logitech lightspeed receiver (0xc547) */
-	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
-		USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_2),
-	 .driver_data = recvr_type_gaming_hidpp},
 
 	{ /* Logitech 27 MHz HID++ 1.0 receiver (0xc513) */
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_MX3000_RECEIVER),
diff --git a/drivers/hid/hid-mcp2221.c b/drivers/hid/hid-mcp2221.c
index 72883e0ce757..aef0785c91cc 100644
--- a/drivers/hid/hid-mcp2221.c
+++ b/drivers/hid/hid-mcp2221.c
@@ -1142,6 +1142,8 @@ static int mcp2221_probe(struct hid_device *hdev,
 	if (ret)
 		return ret;
 
+	hid_device_io_start(hdev);
+
 	/* Set I2C bus clock diviser */
 	if (i2c_clk_freq > 400)
 		i2c_clk_freq = 400;
@@ -1157,12 +1159,12 @@ static int mcp2221_probe(struct hid_device *hdev,
 	snprintf(mcp->adapter.name, sizeof(mcp->adapter.name),
 			"MCP2221 usb-i2c bridge");
 
+	i2c_set_adapdata(&mcp->adapter, mcp);
 	ret = devm_i2c_add_adapter(&hdev->dev, &mcp->adapter);
 	if (ret) {
 		hid_err(hdev, "can't add usb-i2c adapter: %d\n", ret);
 		return ret;
 	}
-	i2c_set_adapdata(&mcp->adapter, mcp);
 
 #if IS_REACHABLE(CONFIG_GPIOLIB)
 	/* Setup GPIO chip */
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index e098cc7b3944..fd5b0637dad6 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -2046,6 +2046,11 @@ static const struct hid_device_id mt_devices[] = {
 		MT_USB_DEVICE(USB_VENDOR_ID_HANVON_ALT,
 			USB_DEVICE_ID_HANVON_ALT_MULTITOUCH) },
 
+	/* HONOR GLO-GXXX panel */
+	{ .driver_data = MT_CLS_VTL,
+		HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
+			0x347d, 0x7853) },
+
 	/* Ilitek dual touch panel */
 	{  .driver_data = MT_CLS_NSMU,
 		MT_USB_DEVICE(USB_VENDOR_ID_ILITEK,
diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c
index 138f154fecef..997c3a1adaca 100644
--- a/drivers/hid/hid-nintendo.c
+++ b/drivers/hid/hid-nintendo.c
@@ -325,28 +325,28 @@ struct joycon_imu_cal {
  * All the controller's button values are stored in a u32.
  * They can be accessed with bitwise ANDs.
  */
-static const u32 JC_BTN_Y	= BIT(0);
-static const u32 JC_BTN_X	= BIT(1);
-static const u32 JC_BTN_B	= BIT(2);
-static const u32 JC_BTN_A	= BIT(3);
-static const u32 JC_BTN_SR_R	= BIT(4);
-static const u32 JC_BTN_SL_R	= BIT(5);
-static const u32 JC_BTN_R	= BIT(6);
-static const u32 JC_BTN_ZR	= BIT(7);
-static const u32 JC_BTN_MINUS	= BIT(8);
-static const u32 JC_BTN_PLUS	= BIT(9);
-static const u32 JC_BTN_RSTICK	= BIT(10);
-static const u32 JC_BTN_LSTICK	= BIT(11);
-static const u32 JC_BTN_HOME	= BIT(12);
-static const u32 JC_BTN_CAP	= BIT(13); /* capture button */
-static const u32 JC_BTN_DOWN	= BIT(16);
-static const u32 JC_BTN_UP	= BIT(17);
-static const u32 JC_BTN_RIGHT	= BIT(18);
-static const u32 JC_BTN_LEFT	= BIT(19);
-static const u32 JC_BTN_SR_L	= BIT(20);
-static const u32 JC_BTN_SL_L	= BIT(21);
-static const u32 JC_BTN_L	= BIT(22);
-static const u32 JC_BTN_ZL	= BIT(23);
+#define JC_BTN_Y	 BIT(0)
+#define JC_BTN_X	 BIT(1)
+#define JC_BTN_B	 BIT(2)
+#define JC_BTN_A	 BIT(3)
+#define JC_BTN_SR_R	 BIT(4)
+#define JC_BTN_SL_R	 BIT(5)
+#define JC_BTN_R	 BIT(6)
+#define JC_BTN_ZR	 BIT(7)
+#define JC_BTN_MINUS	 BIT(8)
+#define JC_BTN_PLUS	 BIT(9)
+#define JC_BTN_RSTICK	 BIT(10)
+#define JC_BTN_LSTICK	 BIT(11)
+#define JC_BTN_HOME	 BIT(12)
+#define JC_BTN_CAP	 BIT(13) /* capture button */
+#define JC_BTN_DOWN	 BIT(16)
+#define JC_BTN_UP	 BIT(17)
+#define JC_BTN_RIGHT	 BIT(18)
+#define JC_BTN_LEFT	 BIT(19)
+#define JC_BTN_SR_L	 BIT(20)
+#define JC_BTN_SL_L	 BIT(21)
+#define JC_BTN_L	 BIT(22)
+#define JC_BTN_ZL	 BIT(23)
 
 enum joycon_msg_type {
 	JOYCON_MSG_TYPE_NONE,
@@ -927,14 +927,27 @@ static int joycon_request_calibration(struct joycon_ctlr *ctlr)
  */
 static void joycon_calc_imu_cal_divisors(struct joycon_ctlr *ctlr)
 {
-	int i;
+	int i, divz = 0;
 
 	for (i = 0; i < 3; i++) {
 		ctlr->imu_cal_accel_divisor[i] = ctlr->accel_cal.scale[i] -
 						ctlr->accel_cal.offset[i];
 		ctlr->imu_cal_gyro_divisor[i] = ctlr->gyro_cal.scale[i] -
 						ctlr->gyro_cal.offset[i];
+
+		if (ctlr->imu_cal_accel_divisor[i] == 0) {
+			ctlr->imu_cal_accel_divisor[i] = 1;
+			divz++;
+		}
+
+		if (ctlr->imu_cal_gyro_divisor[i] == 0) {
+			ctlr->imu_cal_gyro_divisor[i] = 1;
+			divz++;
+		}
 	}
+
+	if (divz)
+		hid_warn(ctlr->hdev, "inaccurate IMU divisors (%d)\n", divz);
 }
 
 static const s16 DFLT_ACCEL_OFFSET /*= 0*/;
@@ -1163,16 +1176,16 @@ static void joycon_parse_imu_report(struct joycon_ctlr *ctlr,
 		    JC_IMU_SAMPLES_PER_DELTA_AVG) {
 			ctlr->imu_avg_delta_ms = ctlr->imu_delta_samples_sum /
 						 ctlr->imu_delta_samples_count;
-			/* don't ever want divide by zero shenanigans */
-			if (ctlr->imu_avg_delta_ms == 0) {
-				ctlr->imu_avg_delta_ms = 1;
-				hid_warn(ctlr->hdev,
-					 "calculated avg imu delta of 0\n");
-			}
 			ctlr->imu_delta_samples_count = 0;
 			ctlr->imu_delta_samples_sum = 0;
 		}
 
+		/* don't ever want divide by zero shenanigans */
+		if (ctlr->imu_avg_delta_ms == 0) {
+			ctlr->imu_avg_delta_ms = 1;
+			hid_warn(ctlr->hdev, "calculated avg imu delta of 0\n");
+		}
+
 		/* useful for debugging IMU sample rate */
 		hid_dbg(ctlr->hdev,
 			"imu_report: ms=%u last_ms=%u delta=%u avg_delta=%u\n",
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index 5a48fcaa32f0..e0bbf0c6345d 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -33,6 +33,7 @@ static const struct hid_device_id hid_quirks[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AKAI, USB_DEVICE_ID_AKAI_MPKMINI2), HID_QUIRK_NO_INIT_REPORTS },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ALPS, USB_DEVICE_ID_IBM_GAMEPAD), HID_QUIRK_BADPAD },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AMI, USB_DEVICE_ID_AMI_VIRT_KEYBOARD_AND_MOUSE), HID_QUIRK_ALWAYS_POLL },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ANSI), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_2PORTKVM), HID_QUIRK_NOGET },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_4PORTKVMC), HID_QUIRK_NOGET },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_4PORTKVM), HID_QUIRK_NOGET },
@@ -120,6 +121,7 @@ static const struct hid_device_id hid_quirks[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M406XE), HID_QUIRK_MULTI_INPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_V2), HID_QUIRK_MULTI_INPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_PENSKETCH_T609A), HID_QUIRK_MULTI_INPUT },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LABTEC, USB_DEVICE_ID_LABTEC_ODDOR_HANDBRAKE), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_OPTICAL_USB_MOUSE_600E), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6019), HID_QUIRK_ALWAYS_POLL },
diff --git a/drivers/hid/i2c-hid/i2c-hid-acpi.c b/drivers/hid/i2c-hid/i2c-hid-acpi.c
index ac918a9ea8d3..1b49243adb16 100644
--- a/drivers/hid/i2c-hid/i2c-hid-acpi.c
+++ b/drivers/hid/i2c-hid/i2c-hid-acpi.c
@@ -40,6 +40,11 @@ static const struct acpi_device_id i2c_hid_acpi_blacklist[] = {
 	 * ICN8505 controller, has a _CID of PNP0C50 but is not HID compatible.
 	 */
 	{ "CHPN0001" },
+	/*
+	 * The IDEA5002 ACPI device causes high interrupt usage and spurious
+	 * wakeups from suspend.
+	 */
+	{ "IDEA5002" },
 	{ }
 };
 
diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c
index 4588d2cd4ea4..a54c7995b9be 100644
--- a/drivers/hid/uhid.c
+++ b/drivers/hid/uhid.c
@@ -490,7 +490,7 @@ static int uhid_dev_create2(struct uhid_device *uhid,
 			    const struct uhid_event *ev)
 {
 	struct hid_device *hid;
-	size_t rd_size, len;
+	size_t rd_size;
 	void *rd_data;
 	int ret;
 
@@ -514,13 +514,12 @@ static int uhid_dev_create2(struct uhid_device *uhid,
 		goto err_free;
 	}
 
-	/* @hid is zero-initialized, strncpy() is correct, strlcpy() not */
-	len = min(sizeof(hid->name), sizeof(ev->u.create2.name)) - 1;
-	strncpy(hid->name, ev->u.create2.name, len);
-	len = min(sizeof(hid->phys), sizeof(ev->u.create2.phys)) - 1;
-	strncpy(hid->phys, ev->u.create2.phys, len);
-	len = min(sizeof(hid->uniq), sizeof(ev->u.create2.uniq)) - 1;
-	strncpy(hid->uniq, ev->u.create2.uniq, len);
+	BUILD_BUG_ON(sizeof(hid->name) != sizeof(ev->u.create2.name));
+	strscpy(hid->name, ev->u.create2.name, sizeof(hid->name));
+	BUILD_BUG_ON(sizeof(hid->phys) != sizeof(ev->u.create2.phys));
+	strscpy(hid->phys, ev->u.create2.phys, sizeof(hid->phys));
+	BUILD_BUG_ON(sizeof(hid->uniq) != sizeof(ev->u.create2.uniq));
+	strscpy(hid->uniq, ev->u.create2.uniq, sizeof(hid->uniq));
 
 	hid->ll_driver = &uhid_hid_driver;
 	hid->bus = ev->u.create2.bus;
diff --git a/drivers/hwmon/acpi_power_meter.c b/drivers/hwmon/acpi_power_meter.c
index 8db740214ffd..703666b95bf4 100644
--- a/drivers/hwmon/acpi_power_meter.c
+++ b/drivers/hwmon/acpi_power_meter.c
@@ -31,6 +31,7 @@
 #define POWER_METER_CAN_NOTIFY	(1 << 3)
 #define POWER_METER_IS_BATTERY	(1 << 8)
 #define UNKNOWN_HYSTERESIS	0xFFFFFFFF
+#define UNKNOWN_POWER		0xFFFFFFFF
 
 #define METER_NOTIFY_CONFIG	0x80
 #define METER_NOTIFY_TRIP	0x81
@@ -348,6 +349,9 @@ static ssize_t show_power(struct device *dev,
 	update_meter(resource);
 	mutex_unlock(&resource->lock);
 
+	if (resource->power == UNKNOWN_POWER)
+		return -ENODATA;
+
 	return sprintf(buf, "%llu\n", resource->power * 1000);
 }
 
diff --git a/drivers/hwmon/corsair-psu.c b/drivers/hwmon/corsair-psu.c
index 904890598c11..2c7c92272fe3 100644
--- a/drivers/hwmon/corsair-psu.c
+++ b/drivers/hwmon/corsair-psu.c
@@ -899,7 +899,23 @@ static struct hid_driver corsairpsu_driver = {
 	.reset_resume	= corsairpsu_resume,
 #endif
 };
-module_hid_driver(corsairpsu_driver);
+
+static int __init corsair_init(void)
+{
+	return hid_register_driver(&corsairpsu_driver);
+}
+
+static void __exit corsair_exit(void)
+{
+	hid_unregister_driver(&corsairpsu_driver);
+}
+
+/*
+ * With module_init() the driver would load before the HID bus when
+ * built-in, so use late_initcall() instead.
+ */
+late_initcall(corsair_init);
+module_exit(corsair_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Wilken Gottwalt <wilken.gottwalt@posteo.net>");
diff --git a/drivers/hwmon/ltc2991.c b/drivers/hwmon/ltc2991.c
index bd63c61129a9..fc53fdcb2b6c 100644
--- a/drivers/hwmon/ltc2991.c
+++ b/drivers/hwmon/ltc2991.c
@@ -373,7 +373,7 @@ static int ltc2991_init(struct ltc2991_state *st)
 			   LTC2991_REPEAT_ACQ_EN);
 	if (ret)
 		return dev_err_probe(st->dev, ret,
-				     "Error: Failed to set contiuous mode.\n");
+				     "Error: Failed to set continuous mode.\n");
 
 	/* Enable all channels and trigger conversions */
 	return regmap_write(st->regmap, LTC2991_CH_EN_TRIGGER,
diff --git a/drivers/hwmon/max31827.c b/drivers/hwmon/max31827.c
index fd1fed1a797c..a1ce65145669 100644
--- a/drivers/hwmon/max31827.c
+++ b/drivers/hwmon/max31827.c
@@ -12,6 +12,7 @@
 #include <linux/i2c.h>
 #include <linux/mutex.h>
 #include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
 
 #define MAX31827_T_REG			0x0
 #define MAX31827_CONFIGURATION_REG	0x2
diff --git a/drivers/hwmon/nzxt-kraken2.c b/drivers/hwmon/nzxt-kraken2.c
index 428c77b5fce5..7caf387eb144 100644
--- a/drivers/hwmon/nzxt-kraken2.c
+++ b/drivers/hwmon/nzxt-kraken2.c
@@ -161,13 +161,13 @@ static int kraken2_probe(struct hid_device *hdev,
 	ret = hid_hw_start(hdev, HID_CONNECT_HIDRAW);
 	if (ret) {
 		hid_err(hdev, "hid hw start failed with %d\n", ret);
-		goto fail_and_stop;
+		return ret;
 	}
 
 	ret = hid_hw_open(hdev);
 	if (ret) {
 		hid_err(hdev, "hid hw open failed with %d\n", ret);
-		goto fail_and_close;
+		goto fail_and_stop;
 	}
 
 	priv->hwmon_dev = hwmon_device_register_with_info(&hdev->dev, "kraken2",
diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c
index 5ca6278baff4..89e8ed214ea4 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.c
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.c
@@ -493,7 +493,7 @@ static void etm_event_start(struct perf_event *event, int flags)
 		goto fail_end_stop;
 
 	/* Finally enable the tracer */
-	if (coresight_enable_source(csdev, CS_MODE_PERF, event))
+	if (source_ops(csdev)->enable(csdev, event, CS_MODE_PERF))
 		goto fail_disable_path;
 
 	/*
@@ -587,7 +587,7 @@ static void etm_event_stop(struct perf_event *event, int mode)
 		return;
 
 	/* stop tracer */
-	coresight_disable_source(csdev, event);
+	source_ops(csdev)->disable(csdev, event);
 
 	/* tell the core */
 	event->hw.state = PERF_HES_STOPPED;
diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c
index 77b0271ce6eb..34aee59dd147 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x-core.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c
@@ -2224,7 +2224,7 @@ static void clear_etmdrvdata(void *info)
 	per_cpu(delayed_probe, cpu) = NULL;
 }
 
-static void __exit etm4_remove_dev(struct etmv4_drvdata *drvdata)
+static void etm4_remove_dev(struct etmv4_drvdata *drvdata)
 {
 	bool had_delayed_probe;
 	/*
@@ -2253,7 +2253,7 @@ static void __exit etm4_remove_dev(struct etmv4_drvdata *drvdata)
 	}
 }
 
-static void __exit etm4_remove_amba(struct amba_device *adev)
+static void etm4_remove_amba(struct amba_device *adev)
 {
 	struct etmv4_drvdata *drvdata = dev_get_drvdata(&adev->dev);
 
@@ -2261,7 +2261,7 @@ static void __exit etm4_remove_amba(struct amba_device *adev)
 		etm4_remove_dev(drvdata);
 }
 
-static int __exit etm4_remove_platform_dev(struct platform_device *pdev)
+static int etm4_remove_platform_dev(struct platform_device *pdev)
 {
 	struct etmv4_drvdata *drvdata = dev_get_drvdata(&pdev->dev);
 
diff --git a/drivers/hwtracing/coresight/ultrasoc-smb.c b/drivers/hwtracing/coresight/ultrasoc-smb.c
index e9a32a97fbee..6e32d31a95fe 100644
--- a/drivers/hwtracing/coresight/ultrasoc-smb.c
+++ b/drivers/hwtracing/coresight/ultrasoc-smb.c
@@ -99,7 +99,7 @@ static int smb_open(struct inode *inode, struct file *file)
 					struct smb_drv_data, miscdev);
 	int ret = 0;
 
-	mutex_lock(&drvdata->mutex);
+	spin_lock(&drvdata->spinlock);
 
 	if (drvdata->reading) {
 		ret = -EBUSY;
@@ -115,7 +115,7 @@ static int smb_open(struct inode *inode, struct file *file)
 
 	drvdata->reading = true;
 out:
-	mutex_unlock(&drvdata->mutex);
+	spin_unlock(&drvdata->spinlock);
 
 	return ret;
 }
@@ -132,10 +132,8 @@ static ssize_t smb_read(struct file *file, char __user *data, size_t len,
 	if (!len)
 		return 0;
 
-	mutex_lock(&drvdata->mutex);
-
 	if (!sdb->data_size)
-		goto out;
+		return 0;
 
 	to_copy = min(sdb->data_size, len);
 
@@ -145,20 +143,15 @@ static ssize_t smb_read(struct file *file, char __user *data, size_t len,
 
 	if (copy_to_user(data, sdb->buf_base + sdb->buf_rdptr, to_copy)) {
 		dev_dbg(dev, "Failed to copy data to user\n");
-		to_copy = -EFAULT;
-		goto out;
+		return -EFAULT;
 	}
 
 	*ppos += to_copy;
-
 	smb_update_read_ptr(drvdata, to_copy);
-
-	dev_dbg(dev, "%zu bytes copied\n", to_copy);
-out:
 	if (!sdb->data_size)
 		smb_reset_buffer(drvdata);
-	mutex_unlock(&drvdata->mutex);
 
+	dev_dbg(dev, "%zu bytes copied\n", to_copy);
 	return to_copy;
 }
 
@@ -167,9 +160,9 @@ static int smb_release(struct inode *inode, struct file *file)
 	struct smb_drv_data *drvdata = container_of(file->private_data,
 					struct smb_drv_data, miscdev);
 
-	mutex_lock(&drvdata->mutex);
+	spin_lock(&drvdata->spinlock);
 	drvdata->reading = false;
-	mutex_unlock(&drvdata->mutex);
+	spin_unlock(&drvdata->spinlock);
 
 	return 0;
 }
@@ -262,7 +255,7 @@ static int smb_enable(struct coresight_device *csdev, enum cs_mode mode,
 	struct smb_drv_data *drvdata = dev_get_drvdata(csdev->dev.parent);
 	int ret = 0;
 
-	mutex_lock(&drvdata->mutex);
+	spin_lock(&drvdata->spinlock);
 
 	/* Do nothing, the trace data is reading by other interface now */
 	if (drvdata->reading) {
@@ -294,7 +287,7 @@ static int smb_enable(struct coresight_device *csdev, enum cs_mode mode,
 
 	dev_dbg(&csdev->dev, "Ultrasoc SMB enabled\n");
 out:
-	mutex_unlock(&drvdata->mutex);
+	spin_unlock(&drvdata->spinlock);
 
 	return ret;
 }
@@ -304,7 +297,7 @@ static int smb_disable(struct coresight_device *csdev)
 	struct smb_drv_data *drvdata = dev_get_drvdata(csdev->dev.parent);
 	int ret = 0;
 
-	mutex_lock(&drvdata->mutex);
+	spin_lock(&drvdata->spinlock);
 
 	if (drvdata->reading) {
 		ret = -EBUSY;
@@ -327,7 +320,7 @@ static int smb_disable(struct coresight_device *csdev)
 
 	dev_dbg(&csdev->dev, "Ultrasoc SMB disabled\n");
 out:
-	mutex_unlock(&drvdata->mutex);
+	spin_unlock(&drvdata->spinlock);
 
 	return ret;
 }
@@ -408,7 +401,7 @@ static unsigned long smb_update_buffer(struct coresight_device *csdev,
 	if (!buf)
 		return 0;
 
-	mutex_lock(&drvdata->mutex);
+	spin_lock(&drvdata->spinlock);
 
 	/* Don't do anything if another tracer is using this sink. */
 	if (atomic_read(&csdev->refcnt) != 1)
@@ -432,7 +425,7 @@ static unsigned long smb_update_buffer(struct coresight_device *csdev,
 	if (!buf->snapshot && lost)
 		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
 out:
-	mutex_unlock(&drvdata->mutex);
+	spin_unlock(&drvdata->spinlock);
 
 	return data_size;
 }
@@ -484,7 +477,6 @@ static int smb_init_data_buffer(struct platform_device *pdev,
 static void smb_init_hw(struct smb_drv_data *drvdata)
 {
 	smb_disable_hw(drvdata);
-	smb_reset_buffer(drvdata);
 
 	writel(SMB_LB_CFG_LO_DEFAULT, drvdata->base + SMB_LB_CFG_LO_REG);
 	writel(SMB_LB_CFG_HI_DEFAULT, drvdata->base + SMB_LB_CFG_HI_REG);
@@ -590,37 +582,33 @@ static int smb_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	mutex_init(&drvdata->mutex);
+	ret = smb_config_inport(dev, true);
+	if (ret)
+		return ret;
+
+	smb_reset_buffer(drvdata);
+	platform_set_drvdata(pdev, drvdata);
+	spin_lock_init(&drvdata->spinlock);
 	drvdata->pid = -1;
 
 	ret = smb_register_sink(pdev, drvdata);
 	if (ret) {
+		smb_config_inport(&pdev->dev, false);
 		dev_err(dev, "Failed to register SMB sink\n");
 		return ret;
 	}
 
-	ret = smb_config_inport(dev, true);
-	if (ret) {
-		smb_unregister_sink(drvdata);
-		return ret;
-	}
-
-	platform_set_drvdata(pdev, drvdata);
-
 	return 0;
 }
 
 static int smb_remove(struct platform_device *pdev)
 {
 	struct smb_drv_data *drvdata = platform_get_drvdata(pdev);
-	int ret;
-
-	ret = smb_config_inport(&pdev->dev, false);
-	if (ret)
-		return ret;
 
 	smb_unregister_sink(drvdata);
 
+	smb_config_inport(&pdev->dev, false);
+
 	return 0;
 }
 
diff --git a/drivers/hwtracing/coresight/ultrasoc-smb.h b/drivers/hwtracing/coresight/ultrasoc-smb.h
index d2e14e8d2c8a..82a44c14a882 100644
--- a/drivers/hwtracing/coresight/ultrasoc-smb.h
+++ b/drivers/hwtracing/coresight/ultrasoc-smb.h
@@ -8,7 +8,7 @@
 #define _ULTRASOC_SMB_H
 
 #include <linux/miscdevice.h>
-#include <linux/mutex.h>
+#include <linux/spinlock.h>
 
 /* Offset of SMB global registers */
 #define SMB_GLB_CFG_REG		0x00
@@ -105,7 +105,7 @@ struct smb_data_buffer {
  * @csdev:	Component vitals needed by the framework.
  * @sdb:	Data buffer for SMB.
  * @miscdev:	Specifics to handle "/dev/xyz.smb" entry.
- * @mutex:	Control data access to one at a time.
+ * @spinlock:	Control data access to one at a time.
  * @reading:	Synchronise user space access to SMB buffer.
  * @pid:	Process ID of the process being monitored by the
  *		session that is using this component.
@@ -116,7 +116,7 @@ struct smb_drv_data {
 	struct coresight_device	*csdev;
 	struct smb_data_buffer sdb;
 	struct miscdevice miscdev;
-	struct mutex mutex;
+	spinlock_t spinlock;
 	bool reading;
 	pid_t pid;
 	enum cs_mode mode;
diff --git a/drivers/hwtracing/ptt/hisi_ptt.c b/drivers/hwtracing/ptt/hisi_ptt.c
index 49ea1b0f7489..a991ecb7515a 100644
--- a/drivers/hwtracing/ptt/hisi_ptt.c
+++ b/drivers/hwtracing/ptt/hisi_ptt.c
@@ -342,9 +342,9 @@ static int hisi_ptt_register_irq(struct hisi_ptt *hisi_ptt)
 		return ret;
 
 	hisi_ptt->trace_irq = pci_irq_vector(pdev, HISI_PTT_TRACE_DMA_IRQ);
-	ret = devm_request_threaded_irq(&pdev->dev, hisi_ptt->trace_irq,
-					NULL, hisi_ptt_isr, 0,
-					DRV_NAME, hisi_ptt);
+	ret = devm_request_irq(&pdev->dev, hisi_ptt->trace_irq, hisi_ptt_isr,
+				IRQF_NOBALANCING | IRQF_NO_THREAD, DRV_NAME,
+				hisi_ptt);
 	if (ret) {
 		pci_err(pdev, "failed to request irq %d, ret = %d\n",
 			hisi_ptt->trace_irq, ret);
@@ -1000,6 +1000,9 @@ static int hisi_ptt_pmu_event_init(struct perf_event *event)
 		return -EOPNOTSUPP;
 	}
 
+	if (event->attach_state & PERF_ATTACH_TASK)
+		return -EOPNOTSUPP;
+
 	if (event->attr.type != hisi_ptt->hisi_ptt_pmu.type)
 		return -ENOENT;
 
@@ -1178,6 +1181,10 @@ static void hisi_ptt_pmu_del(struct perf_event *event, int flags)
 	hisi_ptt_pmu_stop(event, PERF_EF_UPDATE);
 }
 
+static void hisi_ptt_pmu_read(struct perf_event *event)
+{
+}
+
 static void hisi_ptt_remove_cpuhp_instance(void *hotplug_node)
 {
 	cpuhp_state_remove_instance_nocalls(hisi_ptt_pmu_online, hotplug_node);
@@ -1221,6 +1228,7 @@ static int hisi_ptt_register_pmu(struct hisi_ptt *hisi_ptt)
 		.stop		= hisi_ptt_pmu_stop,
 		.add		= hisi_ptt_pmu_add,
 		.del		= hisi_ptt_pmu_del,
+		.read		= hisi_ptt_pmu_read,
 	};
 
 	reg = readl(hisi_ptt->iobase + HISI_PTT_LOCATION);
diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c
index 28e2a5fc4528..5511fd46a65e 100644
--- a/drivers/i2c/busses/i2c-aspeed.c
+++ b/drivers/i2c/busses/i2c-aspeed.c
@@ -249,18 +249,46 @@ static u32 aspeed_i2c_slave_irq(struct aspeed_i2c_bus *bus, u32 irq_status)
 	if (!slave)
 		return 0;
 
-	command = readl(bus->base + ASPEED_I2C_CMD_REG);
+	/*
+	 * Handle stop conditions early, prior to SLAVE_MATCH. Some masters may drive
+	 * transfers with low enough latency between the nak/stop phase of the current
+	 * command and the start/address phase of the following command that the
+	 * interrupts are coalesced by the time we process them.
+	 */
+	if (irq_status & ASPEED_I2CD_INTR_NORMAL_STOP) {
+		irq_handled |= ASPEED_I2CD_INTR_NORMAL_STOP;
+		bus->slave_state = ASPEED_I2C_SLAVE_STOP;
+	}
+
+	if (irq_status & ASPEED_I2CD_INTR_TX_NAK &&
+	    bus->slave_state == ASPEED_I2C_SLAVE_READ_PROCESSED) {
+		irq_handled |= ASPEED_I2CD_INTR_TX_NAK;
+		bus->slave_state = ASPEED_I2C_SLAVE_STOP;
+	}
+
+	/* Propagate any stop conditions to the slave implementation. */
+	if (bus->slave_state == ASPEED_I2C_SLAVE_STOP) {
+		i2c_slave_event(slave, I2C_SLAVE_STOP, &value);
+		bus->slave_state = ASPEED_I2C_SLAVE_INACTIVE;
+	}
 
-	/* Slave was requested, restart state machine. */
+	/*
+	 * Now that we've dealt with any potentially coalesced stop conditions,
+	 * address any start conditions.
+	 */
 	if (irq_status & ASPEED_I2CD_INTR_SLAVE_MATCH) {
 		irq_handled |= ASPEED_I2CD_INTR_SLAVE_MATCH;
 		bus->slave_state = ASPEED_I2C_SLAVE_START;
 	}
 
-	/* Slave is not currently active, irq was for someone else. */
+	/*
+	 * If the slave has been stopped and not started then slave interrupt
+	 * handling is complete.
+	 */
 	if (bus->slave_state == ASPEED_I2C_SLAVE_INACTIVE)
 		return irq_handled;
 
+	command = readl(bus->base + ASPEED_I2C_CMD_REG);
 	dev_dbg(bus->dev, "slave irq status 0x%08x, cmd 0x%08x\n",
 		irq_status, command);
 
@@ -279,17 +307,6 @@ static u32 aspeed_i2c_slave_irq(struct aspeed_i2c_bus *bus, u32 irq_status)
 		irq_handled |= ASPEED_I2CD_INTR_RX_DONE;
 	}
 
-	/* Slave was asked to stop. */
-	if (irq_status & ASPEED_I2CD_INTR_NORMAL_STOP) {
-		irq_handled |= ASPEED_I2CD_INTR_NORMAL_STOP;
-		bus->slave_state = ASPEED_I2C_SLAVE_STOP;
-	}
-	if (irq_status & ASPEED_I2CD_INTR_TX_NAK &&
-	    bus->slave_state == ASPEED_I2C_SLAVE_READ_PROCESSED) {
-		irq_handled |= ASPEED_I2CD_INTR_TX_NAK;
-		bus->slave_state = ASPEED_I2C_SLAVE_STOP;
-	}
-
 	switch (bus->slave_state) {
 	case ASPEED_I2C_SLAVE_READ_REQUESTED:
 		if (unlikely(irq_status & ASPEED_I2CD_INTR_TX_ACK))
@@ -324,8 +341,7 @@ static u32 aspeed_i2c_slave_irq(struct aspeed_i2c_bus *bus, u32 irq_status)
 		i2c_slave_event(slave, I2C_SLAVE_WRITE_RECEIVED, &value);
 		break;
 	case ASPEED_I2C_SLAVE_STOP:
-		i2c_slave_event(slave, I2C_SLAVE_STOP, &value);
-		bus->slave_state = ASPEED_I2C_SLAVE_INACTIVE;
+		/* Stop event handling is done early. Unreachable. */
 		break;
 	case ASPEED_I2C_SLAVE_START:
 		/* Slave was just started. Waiting for the next event. */;
diff --git a/drivers/i2c/busses/i2c-designware-common.c b/drivers/i2c/busses/i2c-designware-common.c
index affcfb243f0f..35f762872b8a 100644
--- a/drivers/i2c/busses/i2c-designware-common.c
+++ b/drivers/i2c/busses/i2c-designware-common.c
@@ -63,7 +63,7 @@ static int dw_reg_read(void *context, unsigned int reg, unsigned int *val)
 {
 	struct dw_i2c_dev *dev = context;
 
-	*val = readl_relaxed(dev->base + reg);
+	*val = readl(dev->base + reg);
 
 	return 0;
 }
@@ -72,7 +72,7 @@ static int dw_reg_write(void *context, unsigned int reg, unsigned int val)
 {
 	struct dw_i2c_dev *dev = context;
 
-	writel_relaxed(val, dev->base + reg);
+	writel(val, dev->base + reg);
 
 	return 0;
 }
@@ -81,7 +81,7 @@ static int dw_reg_read_swab(void *context, unsigned int reg, unsigned int *val)
 {
 	struct dw_i2c_dev *dev = context;
 
-	*val = swab32(readl_relaxed(dev->base + reg));
+	*val = swab32(readl(dev->base + reg));
 
 	return 0;
 }
@@ -90,7 +90,7 @@ static int dw_reg_write_swab(void *context, unsigned int reg, unsigned int val)
 {
 	struct dw_i2c_dev *dev = context;
 
-	writel_relaxed(swab32(val), dev->base + reg);
+	writel(swab32(val), dev->base + reg);
 
 	return 0;
 }
@@ -99,8 +99,8 @@ static int dw_reg_read_word(void *context, unsigned int reg, unsigned int *val)
 {
 	struct dw_i2c_dev *dev = context;
 
-	*val = readw_relaxed(dev->base + reg) |
-		(readw_relaxed(dev->base + reg + 2) << 16);
+	*val = readw(dev->base + reg) |
+		(readw(dev->base + reg + 2) << 16);
 
 	return 0;
 }
@@ -109,8 +109,8 @@ static int dw_reg_write_word(void *context, unsigned int reg, unsigned int val)
 {
 	struct dw_i2c_dev *dev = context;
 
-	writew_relaxed(val, dev->base + reg);
-	writew_relaxed(val >> 16, dev->base + reg + 2);
+	writew(val, dev->base + reg);
+	writew(val >> 16, dev->base + reg + 2);
 
 	return 0;
 }
diff --git a/drivers/i2c/busses/i2c-ocores.c b/drivers/i2c/busses/i2c-ocores.c
index 041a76f71a49..e106af83cef4 100644
--- a/drivers/i2c/busses/i2c-ocores.c
+++ b/drivers/i2c/busses/i2c-ocores.c
@@ -771,8 +771,8 @@ static int ocores_i2c_resume(struct device *dev)
 	return ocores_init(dev, i2c);
 }
 
-static DEFINE_SIMPLE_DEV_PM_OPS(ocores_i2c_pm,
-				ocores_i2c_suspend, ocores_i2c_resume);
+static DEFINE_NOIRQ_DEV_PM_OPS(ocores_i2c_pm,
+			       ocores_i2c_suspend, ocores_i2c_resume);
 
 static struct platform_driver ocores_i2c_driver = {
 	.probe   = ocores_i2c_probe,
diff --git a/drivers/i2c/busses/i2c-pxa.c b/drivers/i2c/busses/i2c-pxa.c
index 1d7648242749..76f79b68cef8 100644
--- a/drivers/i2c/busses/i2c-pxa.c
+++ b/drivers/i2c/busses/i2c-pxa.c
@@ -265,6 +265,9 @@ struct pxa_i2c {
 	u32			hs_mask;
 
 	struct i2c_bus_recovery_info recovery;
+	struct pinctrl		*pinctrl;
+	struct pinctrl_state	*pinctrl_default;
+	struct pinctrl_state	*pinctrl_recovery;
 };
 
 #define _IBMR(i2c)	((i2c)->reg_ibmr)
@@ -1299,12 +1302,13 @@ static void i2c_pxa_prepare_recovery(struct i2c_adapter *adap)
 	 */
 	gpiod_set_value(i2c->recovery.scl_gpiod, ibmr & IBMR_SCLS);
 	gpiod_set_value(i2c->recovery.sda_gpiod, ibmr & IBMR_SDAS);
+
+	WARN_ON(pinctrl_select_state(i2c->pinctrl, i2c->pinctrl_recovery));
 }
 
 static void i2c_pxa_unprepare_recovery(struct i2c_adapter *adap)
 {
 	struct pxa_i2c *i2c = adap->algo_data;
-	struct i2c_bus_recovery_info *bri = adap->bus_recovery_info;
 	u32 isr;
 
 	/*
@@ -1318,7 +1322,7 @@ static void i2c_pxa_unprepare_recovery(struct i2c_adapter *adap)
 		i2c_pxa_do_reset(i2c);
 	}
 
-	WARN_ON(pinctrl_select_state(bri->pinctrl, bri->pins_default));
+	WARN_ON(pinctrl_select_state(i2c->pinctrl, i2c->pinctrl_default));
 
 	dev_dbg(&i2c->adap.dev, "recovery: IBMR 0x%08x ISR 0x%08x\n",
 	        readl(_IBMR(i2c)), readl(_ISR(i2c)));
@@ -1340,20 +1344,76 @@ static int i2c_pxa_init_recovery(struct pxa_i2c *i2c)
 	if (IS_ENABLED(CONFIG_I2C_PXA_SLAVE))
 		return 0;
 
-	bri->pinctrl = devm_pinctrl_get(dev);
-	if (PTR_ERR(bri->pinctrl) == -ENODEV) {
-		bri->pinctrl = NULL;
+	i2c->pinctrl = devm_pinctrl_get(dev);
+	if (PTR_ERR(i2c->pinctrl) == -ENODEV)
+		i2c->pinctrl = NULL;
+	if (IS_ERR(i2c->pinctrl))
+		return PTR_ERR(i2c->pinctrl);
+
+	if (!i2c->pinctrl)
+		return 0;
+
+	i2c->pinctrl_default = pinctrl_lookup_state(i2c->pinctrl,
+						    PINCTRL_STATE_DEFAULT);
+	i2c->pinctrl_recovery = pinctrl_lookup_state(i2c->pinctrl, "recovery");
+
+	if (IS_ERR(i2c->pinctrl_default) || IS_ERR(i2c->pinctrl_recovery)) {
+		dev_info(dev, "missing pinmux recovery information: %ld %ld\n",
+			 PTR_ERR(i2c->pinctrl_default),
+			 PTR_ERR(i2c->pinctrl_recovery));
+		return 0;
+	}
+
+	/*
+	 * Claiming GPIOs can influence the pinmux state, and may glitch the
+	 * I2C bus. Do this carefully.
+	 */
+	bri->scl_gpiod = devm_gpiod_get(dev, "scl", GPIOD_OUT_HIGH_OPEN_DRAIN);
+	if (bri->scl_gpiod == ERR_PTR(-EPROBE_DEFER))
+		return -EPROBE_DEFER;
+	if (IS_ERR(bri->scl_gpiod)) {
+		dev_info(dev, "missing scl gpio recovery information: %pe\n",
+			 bri->scl_gpiod);
+		return 0;
+	}
+
+	/*
+	 * We have SCL. Pull SCL low and wait a bit so that SDA glitches
+	 * have no effect.
+	 */
+	gpiod_direction_output(bri->scl_gpiod, 0);
+	udelay(10);
+	bri->sda_gpiod = devm_gpiod_get(dev, "sda", GPIOD_OUT_HIGH_OPEN_DRAIN);
+
+	/* Wait a bit in case of a SDA glitch, and then release SCL. */
+	udelay(10);
+	gpiod_direction_output(bri->scl_gpiod, 1);
+
+	if (bri->sda_gpiod == ERR_PTR(-EPROBE_DEFER))
+		return -EPROBE_DEFER;
+
+	if (IS_ERR(bri->sda_gpiod)) {
+		dev_info(dev, "missing sda gpio recovery information: %pe\n",
+			 bri->sda_gpiod);
 		return 0;
 	}
-	if (IS_ERR(bri->pinctrl))
-		return PTR_ERR(bri->pinctrl);
 
 	bri->prepare_recovery = i2c_pxa_prepare_recovery;
 	bri->unprepare_recovery = i2c_pxa_unprepare_recovery;
+	bri->recover_bus = i2c_generic_scl_recovery;
 
 	i2c->adap.bus_recovery_info = bri;
 
-	return 0;
+	/*
+	 * Claiming GPIOs can change the pinmux state, which confuses the
+	 * pinctrl since pinctrl's idea of the current setting is unaffected
+	 * by the pinmux change caused by claiming the GPIO. Work around that
+	 * by switching pinctrl to the GPIO state here. We do it this way to
+	 * avoid glitching the I2C bus.
+	 */
+	pinctrl_select_state(i2c->pinctrl, i2c->pinctrl_recovery);
+
+	return pinctrl_select_state(i2c->pinctrl, i2c->pinctrl_default);
 }
 
 static int i2c_pxa_probe(struct platform_device *dev)
diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c
index 6d829ed2f868..0d2e7171e3a6 100644
--- a/drivers/i2c/busses/i2c-qcom-geni.c
+++ b/drivers/i2c/busses/i2c-qcom-geni.c
@@ -858,6 +858,7 @@ static int geni_i2c_probe(struct platform_device *pdev)
 	ret = geni_se_resources_on(&gi2c->se);
 	if (ret) {
 		dev_err(dev, "Error turning on resources %d\n", ret);
+		clk_disable_unprepare(gi2c->core_clk);
 		return ret;
 	}
 	proto = geni_se_read_proto(&gi2c->se);
@@ -877,8 +878,11 @@ static int geni_i2c_probe(struct platform_device *pdev)
 		/* FIFO is disabled, so we can only use GPI DMA */
 		gi2c->gpi_mode = true;
 		ret = setup_gpi_dma(gi2c);
-		if (ret)
+		if (ret) {
+			geni_se_resources_off(&gi2c->se);
+			clk_disable_unprepare(gi2c->core_clk);
 			return dev_err_probe(dev, ret, "Failed to setup GPI DMA mode\n");
+		}
 
 		dev_dbg(dev, "Using GPI DMA mode for I2C\n");
 	} else {
@@ -891,6 +895,8 @@ static int geni_i2c_probe(struct platform_device *pdev)
 
 		if (!tx_depth) {
 			dev_err(dev, "Invalid TX FIFO depth\n");
+			geni_se_resources_off(&gi2c->se);
+			clk_disable_unprepare(gi2c->core_clk);
 			return -EINVAL;
 		}
 
diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c
index a044ca0c35a1..4362db7c5789 100644
--- a/drivers/i2c/busses/i2c-rk3x.c
+++ b/drivers/i2c/busses/i2c-rk3x.c
@@ -178,6 +178,7 @@ struct rk3x_i2c_soc_data {
  * @clk: function clk for rk3399 or function & Bus clks for others
  * @pclk: Bus clk for rk3399
  * @clk_rate_nb: i2c clk rate change notify
+ * @irq: irq number
  * @t: I2C known timing information
  * @lock: spinlock for the i2c bus
  * @wait: the waitqueue to wait for i2c transfer
@@ -200,6 +201,7 @@ struct rk3x_i2c {
 	struct clk *clk;
 	struct clk *pclk;
 	struct notifier_block clk_rate_nb;
+	int irq;
 
 	/* Settings */
 	struct i2c_timings t;
@@ -1087,13 +1089,18 @@ static int rk3x_i2c_xfer_common(struct i2c_adapter *adap,
 
 		spin_unlock_irqrestore(&i2c->lock, flags);
 
-		rk3x_i2c_start(i2c);
-
 		if (!polling) {
+			rk3x_i2c_start(i2c);
+
 			timeout = wait_event_timeout(i2c->wait, !i2c->busy,
 						     msecs_to_jiffies(WAIT_TIMEOUT));
 		} else {
+			disable_irq(i2c->irq);
+			rk3x_i2c_start(i2c);
+
 			timeout = rk3x_i2c_wait_xfer_poll(i2c);
+
+			enable_irq(i2c->irq);
 		}
 
 		spin_lock_irqsave(&i2c->lock, flags);
@@ -1310,6 +1317,8 @@ static int rk3x_i2c_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	i2c->irq = irq;
+
 	platform_set_drvdata(pdev, i2c);
 
 	if (i2c->soc_data->calc_timings == rk3x_i2c_v0_calc_timings) {
diff --git a/drivers/i2c/i2c-core.h b/drivers/i2c/i2c-core.h
index 05b8b8dfa9bd..36587f38dff3 100644
--- a/drivers/i2c/i2c-core.h
+++ b/drivers/i2c/i2c-core.h
@@ -3,6 +3,7 @@
  * i2c-core.h - interfaces internal to the I2C framework
  */
 
+#include <linux/kconfig.h>
 #include <linux/rwsem.h>
 
 struct i2c_devinfo {
@@ -29,7 +30,8 @@ int i2c_dev_irq_from_resources(const struct resource *resources,
  */
 static inline bool i2c_in_atomic_xfer_mode(void)
 {
-	return system_state > SYSTEM_RUNNING && !preemptible();
+	return system_state > SYSTEM_RUNNING &&
+	       (IS_ENABLED(CONFIG_PREEMPT_COUNT) ? !preemptible() : irqs_disabled());
 }
 
 static inline int __i2c_lock_bus_helper(struct i2c_adapter *adap)
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index dcda0afecfc5..bcf1198e8991 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -131,11 +131,12 @@ static unsigned int mwait_substates __initdata;
 #define MWAIT2flg(eax) ((eax & 0xFF) << 24)
 
 static __always_inline int __intel_idle(struct cpuidle_device *dev,
-					struct cpuidle_driver *drv, int index)
+					struct cpuidle_driver *drv,
+					int index, bool irqoff)
 {
 	struct cpuidle_state *state = &drv->states[index];
 	unsigned long eax = flg2MWAIT(state->flags);
-	unsigned long ecx = 1; /* break on interrupt flag */
+	unsigned long ecx = 1*irqoff; /* break on interrupt flag */
 
 	mwait_idle_with_hints(eax, ecx);
 
@@ -159,19 +160,13 @@ static __always_inline int __intel_idle(struct cpuidle_device *dev,
 static __cpuidle int intel_idle(struct cpuidle_device *dev,
 				struct cpuidle_driver *drv, int index)
 {
-	return __intel_idle(dev, drv, index);
+	return __intel_idle(dev, drv, index, true);
 }
 
 static __cpuidle int intel_idle_irq(struct cpuidle_device *dev,
 				    struct cpuidle_driver *drv, int index)
 {
-	int ret;
-
-	raw_local_irq_enable();
-	ret = __intel_idle(dev, drv, index);
-	raw_local_irq_disable();
-
-	return ret;
+	return __intel_idle(dev, drv, index, false);
 }
 
 static __cpuidle int intel_idle_ibrs(struct cpuidle_device *dev,
@@ -184,7 +179,7 @@ static __cpuidle int intel_idle_ibrs(struct cpuidle_device *dev,
 	if (smt_active)
 		__update_spec_ctrl(0);
 
-	ret = __intel_idle(dev, drv, index);
+	ret = __intel_idle(dev, drv, index, true);
 
 	if (smt_active)
 		__update_spec_ctrl(spec_ctrl);
@@ -196,7 +191,7 @@ static __cpuidle int intel_idle_xstate(struct cpuidle_device *dev,
 				       struct cpuidle_driver *drv, int index)
 {
 	fpu_idle_fpregs();
-	return __intel_idle(dev, drv, index);
+	return __intel_idle(dev, drv, index, true);
 }
 
 /**
@@ -923,6 +918,35 @@ static struct cpuidle_state adl_l_cstates[] __initdata = {
 		.enter = NULL }
 };
 
+static struct cpuidle_state mtl_l_cstates[] __initdata = {
+	{
+		.name = "C1E",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE,
+		.exit_latency = 1,
+		.target_residency = 1,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C6",
+		.desc = "MWAIT 0x20",
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 140,
+		.target_residency = 420,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C10",
+		.desc = "MWAIT 0x60",
+		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 310,
+		.target_residency = 930,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.enter = NULL }
+};
+
 static struct cpuidle_state gmt_cstates[] __initdata = {
 	{
 		.name = "C1",
@@ -1242,6 +1266,72 @@ static struct cpuidle_state snr_cstates[] __initdata = {
 		.enter = NULL }
 };
 
+static struct cpuidle_state grr_cstates[] __initdata = {
+	{
+		.name = "C1",
+		.desc = "MWAIT 0x00",
+		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_ALWAYS_ENABLE,
+		.exit_latency = 1,
+		.target_residency = 1,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C1E",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE,
+		.exit_latency = 2,
+		.target_residency = 10,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C6S",
+		.desc = "MWAIT 0x22",
+		.flags = MWAIT2flg(0x22) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 140,
+		.target_residency = 500,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.enter = NULL }
+};
+
+static struct cpuidle_state srf_cstates[] __initdata = {
+	{
+		.name = "C1",
+		.desc = "MWAIT 0x00",
+		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_ALWAYS_ENABLE,
+		.exit_latency = 1,
+		.target_residency = 1,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C1E",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE,
+		.exit_latency = 2,
+		.target_residency = 10,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C6S",
+		.desc = "MWAIT 0x22",
+		.flags = MWAIT2flg(0x22) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 270,
+		.target_residency = 700,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C6SP",
+		.desc = "MWAIT 0x23",
+		.flags = MWAIT2flg(0x23) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 310,
+		.target_residency = 900,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.enter = NULL }
+};
+
 static const struct idle_cpu idle_cpu_nehalem __initconst = {
 	.state_table = nehalem_cstates,
 	.auto_demotion_disable_flags = NHM_C1_AUTO_DEMOTE | NHM_C3_AUTO_DEMOTE,
@@ -1349,6 +1439,10 @@ static const struct idle_cpu idle_cpu_adl_l __initconst = {
 	.state_table = adl_l_cstates,
 };
 
+static const struct idle_cpu idle_cpu_mtl_l __initconst = {
+	.state_table = mtl_l_cstates,
+};
+
 static const struct idle_cpu idle_cpu_gmt __initconst = {
 	.state_table = gmt_cstates,
 };
@@ -1387,6 +1481,18 @@ static const struct idle_cpu idle_cpu_snr __initconst = {
 	.use_acpi = true,
 };
 
+static const struct idle_cpu idle_cpu_grr __initconst = {
+	.state_table = grr_cstates,
+	.disable_promotion_to_c1e = true,
+	.use_acpi = true,
+};
+
+static const struct idle_cpu idle_cpu_srf __initconst = {
+	.state_table = srf_cstates,
+	.disable_promotion_to_c1e = true,
+	.use_acpi = true,
+};
+
 static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EP,		&idle_cpu_nhx),
 	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM,		&idle_cpu_nehalem),
@@ -1423,6 +1529,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D,		&idle_cpu_icx),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		&idle_cpu_adl),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		&idle_cpu_adl_l),
+	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L,	&idle_cpu_mtl_l),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,	&idle_cpu_gmt),
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&idle_cpu_spr),
 	X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X,	&idle_cpu_spr),
@@ -1432,6 +1539,8 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS,	&idle_cpu_bxt),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D,	&idle_cpu_dnv),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&idle_cpu_snr),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT,	&idle_cpu_grr),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT_X,	&idle_cpu_srf),
 	{}
 };
 
diff --git a/drivers/iio/accel/kionix-kx022a.c b/drivers/iio/accel/kionix-kx022a.c
index 60864be3a667..53d59a04ae15 100644
--- a/drivers/iio/accel/kionix-kx022a.c
+++ b/drivers/iio/accel/kionix-kx022a.c
@@ -393,17 +393,17 @@ static const unsigned int kx022a_odrs[] = {
  *	(range / 2^bits) * g = (range / 2^bits) * 9.80665 m/s^2
  *	=> KX022A uses 16 bit (HiRes mode - assume the low 8 bits are zeroed
  *	in low-power mode(?) )
- *	=> +/-2G  => 4 / 2^16 * 9,80665 * 10^6 (to scale to micro)
- *	=> +/-2G  - 598.550415
- *	   +/-4G  - 1197.10083
- *	   +/-8G  - 2394.20166
- *	   +/-16G - 4788.40332
+ *	=> +/-2G  => 4 / 2^16 * 9,80665
+ *	=> +/-2G  - 0.000598550415
+ *	   +/-4G  - 0.00119710083
+ *	   +/-8G  - 0.00239420166
+ *	   +/-16G - 0.00478840332
  */
 static const int kx022a_scale_table[][2] = {
-	{ 598, 550415 },
-	{ 1197, 100830 },
-	{ 2394, 201660 },
-	{ 4788, 403320 },
+	{ 0, 598550 },
+	{ 0, 1197101 },
+	{ 0, 2394202 },
+	{ 0, 4788403 },
 };
 
 static int kx022a_read_avail(struct iio_dev *indio_dev,
@@ -422,7 +422,7 @@ static int kx022a_read_avail(struct iio_dev *indio_dev,
 		*vals = (const int *)kx022a_scale_table;
 		*length = ARRAY_SIZE(kx022a_scale_table) *
 			  ARRAY_SIZE(kx022a_scale_table[0]);
-		*type = IIO_VAL_INT_PLUS_MICRO;
+		*type = IIO_VAL_INT_PLUS_NANO;
 		return IIO_AVAIL_LIST;
 	default:
 		return -EINVAL;
@@ -485,6 +485,20 @@ static int kx022a_turn_on_unlock(struct kx022a_data *data)
 	return ret;
 }
 
+static int kx022a_write_raw_get_fmt(struct iio_dev *idev,
+				    struct iio_chan_spec const *chan,
+				    long mask)
+{
+	switch (mask) {
+	case IIO_CHAN_INFO_SCALE:
+		return IIO_VAL_INT_PLUS_NANO;
+	case IIO_CHAN_INFO_SAMP_FREQ:
+		return IIO_VAL_INT_PLUS_MICRO;
+	default:
+		return -EINVAL;
+	}
+}
+
 static int kx022a_write_raw(struct iio_dev *idev,
 			    struct iio_chan_spec const *chan,
 			    int val, int val2, long mask)
@@ -629,7 +643,7 @@ static int kx022a_read_raw(struct iio_dev *idev,
 
 		kx022a_reg2scale(regval, val, val2);
 
-		return IIO_VAL_INT_PLUS_MICRO;
+		return IIO_VAL_INT_PLUS_NANO;
 	}
 
 	return -EINVAL;
@@ -856,6 +870,7 @@ static int kx022a_fifo_flush(struct iio_dev *idev, unsigned int samples)
 static const struct iio_info kx022a_info = {
 	.read_raw = &kx022a_read_raw,
 	.write_raw = &kx022a_write_raw,
+	.write_raw_get_fmt = &kx022a_write_raw_get_fmt,
 	.read_avail = &kx022a_read_avail,
 
 	.validate_trigger	= iio_validate_own_trigger,
diff --git a/drivers/iio/adc/imx93_adc.c b/drivers/iio/adc/imx93_adc.c
index 9bb1e4ba1aee..4ccf4819f1f1 100644
--- a/drivers/iio/adc/imx93_adc.c
+++ b/drivers/iio/adc/imx93_adc.c
@@ -93,6 +93,10 @@ static const struct iio_chan_spec imx93_adc_iio_channels[] = {
 	IMX93_ADC_CHAN(1),
 	IMX93_ADC_CHAN(2),
 	IMX93_ADC_CHAN(3),
+	IMX93_ADC_CHAN(4),
+	IMX93_ADC_CHAN(5),
+	IMX93_ADC_CHAN(6),
+	IMX93_ADC_CHAN(7),
 };
 
 static void imx93_adc_power_down(struct imx93_adc *adc)
diff --git a/drivers/iio/adc/mcp3564.c b/drivers/iio/adc/mcp3564.c
index e3f1de5fcc5a..311b613b6057 100644
--- a/drivers/iio/adc/mcp3564.c
+++ b/drivers/iio/adc/mcp3564.c
@@ -918,7 +918,7 @@ static int mcp3564_write_raw(struct iio_dev *indio_dev,
 		mutex_unlock(&adc->lock);
 		return ret;
 	case IIO_CHAN_INFO_CALIBBIAS:
-		if (val < mcp3564_calib_bias[0] && val > mcp3564_calib_bias[2])
+		if (val < mcp3564_calib_bias[0] || val > mcp3564_calib_bias[2])
 			return -EINVAL;
 
 		mutex_lock(&adc->lock);
@@ -928,7 +928,7 @@ static int mcp3564_write_raw(struct iio_dev *indio_dev,
 		mutex_unlock(&adc->lock);
 		return ret;
 	case IIO_CHAN_INFO_CALIBSCALE:
-		if (val < mcp3564_calib_scale[0] && val > mcp3564_calib_scale[2])
+		if (val < mcp3564_calib_scale[0] || val > mcp3564_calib_scale[2])
 			return -EINVAL;
 
 		if (adc->calib_scale == val)
@@ -1122,7 +1122,7 @@ static int mcp3564_config(struct iio_dev *indio_dev)
 	enum mcp3564_ids ids;
 	int ret = 0;
 	unsigned int tmp = 0x01;
-	bool err = true;
+	bool err = false;
 
 	/*
 	 * The address is set on a per-device basis by fuses in the factory,
@@ -1509,5 +1509,5 @@ static struct spi_driver mcp3564_driver = {
 module_spi_driver(mcp3564_driver);
 
 MODULE_AUTHOR("Marius Cristea <marius.cristea@microchip.com>");
-MODULE_DESCRIPTION("Microchip MCP346x/MCP346xR and MCP356x/MCP346xR ADCs");
+MODULE_DESCRIPTION("Microchip MCP346x/MCP346xR and MCP356x/MCP356xR ADCs");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/iio/adc/meson_saradc.c b/drivers/iio/adc/meson_saradc.c
index 950ff13e6dde..13b473d8c6c7 100644
--- a/drivers/iio/adc/meson_saradc.c
+++ b/drivers/iio/adc/meson_saradc.c
@@ -1241,6 +1241,20 @@ static const struct meson_sar_adc_param meson_sar_adc_gxl_param = {
 	.cmv_select = 1,
 };
 
+static const struct meson_sar_adc_param meson_sar_adc_axg_param = {
+	.has_bl30_integration = true,
+	.clock_rate = 1200000,
+	.bandgap_reg = MESON_SAR_ADC_REG11,
+	.regmap_config = &meson_sar_adc_regmap_config_gxbb,
+	.resolution = 12,
+	.disable_ring_counter = 1,
+	.has_reg11 = true,
+	.vref_volatge = 1,
+	.has_vref_select = true,
+	.vref_select = VREF_VDDA,
+	.cmv_select = 1,
+};
+
 static const struct meson_sar_adc_param meson_sar_adc_g12a_param = {
 	.has_bl30_integration = false,
 	.clock_rate = 1200000,
@@ -1285,7 +1299,7 @@ static const struct meson_sar_adc_data meson_sar_adc_gxm_data = {
 };
 
 static const struct meson_sar_adc_data meson_sar_adc_axg_data = {
-	.param = &meson_sar_adc_gxl_param,
+	.param = &meson_sar_adc_axg_param,
 	.name = "meson-axg-saradc",
 };
 
diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c
index c755e8cd5220..95fa857e8aad 100644
--- a/drivers/iio/adc/ti_am335x_adc.c
+++ b/drivers/iio/adc/ti_am335x_adc.c
@@ -670,8 +670,10 @@ static int tiadc_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, indio_dev);
 
 	err = tiadc_request_dma(pdev, adc_dev);
-	if (err && err == -EPROBE_DEFER)
+	if (err && err != -ENODEV) {
+		dev_err_probe(&pdev->dev, err, "DMA request failed\n");
 		goto err_dma;
+	}
 
 	return 0;
 
diff --git a/drivers/iio/buffer/industrialio-triggered-buffer.c b/drivers/iio/buffer/industrialio-triggered-buffer.c
index c7671b1f5ead..c06515987e7a 100644
--- a/drivers/iio/buffer/industrialio-triggered-buffer.c
+++ b/drivers/iio/buffer/industrialio-triggered-buffer.c
@@ -46,6 +46,16 @@ int iio_triggered_buffer_setup_ext(struct iio_dev *indio_dev,
 	struct iio_buffer *buffer;
 	int ret;
 
+	/*
+	 * iio_triggered_buffer_cleanup() assumes that the buffer allocated here
+	 * is assigned to indio_dev->buffer but this is only the case if this
+	 * function is the first caller to iio_device_attach_buffer(). If
+	 * indio_dev->buffer is already set then we can't proceed otherwise the
+	 * cleanup function will try to free a buffer that was not allocated here.
+	 */
+	if (indio_dev->buffer)
+		return -EADDRINUSE;
+
 	buffer = iio_kfifo_allocate();
 	if (!buffer) {
 		ret = -ENOMEM;
diff --git a/drivers/iio/common/ms_sensors/ms_sensors_i2c.c b/drivers/iio/common/ms_sensors/ms_sensors_i2c.c
index 6633b35a94e6..9c9bc77003c7 100644
--- a/drivers/iio/common/ms_sensors/ms_sensors_i2c.c
+++ b/drivers/iio/common/ms_sensors/ms_sensors_i2c.c
@@ -15,8 +15,8 @@
 /* Conversion times in us */
 static const u16 ms_sensors_ht_t_conversion_time[] = { 50000, 25000,
 						       13000, 7000 };
-static const u16 ms_sensors_ht_h_conversion_time[] = { 16000, 3000,
-						       5000, 8000 };
+static const u16 ms_sensors_ht_h_conversion_time[] = { 16000, 5000,
+						       3000, 8000 };
 static const u16 ms_sensors_tp_conversion_time[] = { 500, 1100, 2100,
 						     4100, 8220, 16440 };
 
diff --git a/drivers/iio/imu/adis16475.c b/drivers/iio/imu/adis16475.c
index b7cbe1565aee..64be656f0b80 100644
--- a/drivers/iio/imu/adis16475.c
+++ b/drivers/iio/imu/adis16475.c
@@ -70,8 +70,8 @@
 #define ADIS16475_MAX_SCAN_DATA		20
 /* spi max speed in brust mode */
 #define ADIS16475_BURST_MAX_SPEED	1000000
-#define ADIS16475_LSB_DEC_MASK		BIT(0)
-#define ADIS16475_LSB_FIR_MASK		BIT(1)
+#define ADIS16475_LSB_DEC_MASK		0
+#define ADIS16475_LSB_FIR_MASK		1
 #define ADIS16500_BURST_DATA_SEL_0_CHN_MASK	GENMASK(5, 0)
 #define ADIS16500_BURST_DATA_SEL_1_CHN_MASK	GENMASK(12, 7)
 
@@ -1406,50 +1406,6 @@ static int adis16475_config_irq_pin(struct adis16475 *st)
 	return 0;
 }
 
-static const struct of_device_id adis16475_of_match[] = {
-	{ .compatible = "adi,adis16470",
-		.data = &adis16475_chip_info[ADIS16470] },
-	{ .compatible = "adi,adis16475-1",
-		.data = &adis16475_chip_info[ADIS16475_1] },
-	{ .compatible = "adi,adis16475-2",
-		.data = &adis16475_chip_info[ADIS16475_2] },
-	{ .compatible = "adi,adis16475-3",
-		.data = &adis16475_chip_info[ADIS16475_3] },
-	{ .compatible = "adi,adis16477-1",
-		.data = &adis16475_chip_info[ADIS16477_1] },
-	{ .compatible = "adi,adis16477-2",
-		.data = &adis16475_chip_info[ADIS16477_2] },
-	{ .compatible = "adi,adis16477-3",
-		.data = &adis16475_chip_info[ADIS16477_3] },
-	{ .compatible = "adi,adis16465-1",
-		.data = &adis16475_chip_info[ADIS16465_1] },
-	{ .compatible = "adi,adis16465-2",
-		.data = &adis16475_chip_info[ADIS16465_2] },
-	{ .compatible = "adi,adis16465-3",
-		.data = &adis16475_chip_info[ADIS16465_3] },
-	{ .compatible = "adi,adis16467-1",
-		.data = &adis16475_chip_info[ADIS16467_1] },
-	{ .compatible = "adi,adis16467-2",
-		.data = &adis16475_chip_info[ADIS16467_2] },
-	{ .compatible = "adi,adis16467-3",
-		.data = &adis16475_chip_info[ADIS16467_3] },
-	{ .compatible = "adi,adis16500",
-		.data = &adis16475_chip_info[ADIS16500] },
-	{ .compatible = "adi,adis16505-1",
-		.data = &adis16475_chip_info[ADIS16505_1] },
-	{ .compatible = "adi,adis16505-2",
-		.data = &adis16475_chip_info[ADIS16505_2] },
-	{ .compatible = "adi,adis16505-3",
-		.data = &adis16475_chip_info[ADIS16505_3] },
-	{ .compatible = "adi,adis16507-1",
-		.data = &adis16475_chip_info[ADIS16507_1] },
-	{ .compatible = "adi,adis16507-2",
-		.data = &adis16475_chip_info[ADIS16507_2] },
-	{ .compatible = "adi,adis16507-3",
-		.data = &adis16475_chip_info[ADIS16507_3] },
-	{ },
-};
-MODULE_DEVICE_TABLE(of, adis16475_of_match);
 
 static int adis16475_probe(struct spi_device *spi)
 {
@@ -1463,7 +1419,7 @@ static int adis16475_probe(struct spi_device *spi)
 
 	st = iio_priv(indio_dev);
 
-	st->info = device_get_match_data(&spi->dev);
+	st->info = spi_get_device_match_data(spi);
 	if (!st->info)
 		return -EINVAL;
 
@@ -1503,12 +1459,83 @@ static int adis16475_probe(struct spi_device *spi)
 	return 0;
 }
 
+static const struct of_device_id adis16475_of_match[] = {
+	{ .compatible = "adi,adis16470",
+		.data = &adis16475_chip_info[ADIS16470] },
+	{ .compatible = "adi,adis16475-1",
+		.data = &adis16475_chip_info[ADIS16475_1] },
+	{ .compatible = "adi,adis16475-2",
+		.data = &adis16475_chip_info[ADIS16475_2] },
+	{ .compatible = "adi,adis16475-3",
+		.data = &adis16475_chip_info[ADIS16475_3] },
+	{ .compatible = "adi,adis16477-1",
+		.data = &adis16475_chip_info[ADIS16477_1] },
+	{ .compatible = "adi,adis16477-2",
+		.data = &adis16475_chip_info[ADIS16477_2] },
+	{ .compatible = "adi,adis16477-3",
+		.data = &adis16475_chip_info[ADIS16477_3] },
+	{ .compatible = "adi,adis16465-1",
+		.data = &adis16475_chip_info[ADIS16465_1] },
+	{ .compatible = "adi,adis16465-2",
+		.data = &adis16475_chip_info[ADIS16465_2] },
+	{ .compatible = "adi,adis16465-3",
+		.data = &adis16475_chip_info[ADIS16465_3] },
+	{ .compatible = "adi,adis16467-1",
+		.data = &adis16475_chip_info[ADIS16467_1] },
+	{ .compatible = "adi,adis16467-2",
+		.data = &adis16475_chip_info[ADIS16467_2] },
+	{ .compatible = "adi,adis16467-3",
+		.data = &adis16475_chip_info[ADIS16467_3] },
+	{ .compatible = "adi,adis16500",
+		.data = &adis16475_chip_info[ADIS16500] },
+	{ .compatible = "adi,adis16505-1",
+		.data = &adis16475_chip_info[ADIS16505_1] },
+	{ .compatible = "adi,adis16505-2",
+		.data = &adis16475_chip_info[ADIS16505_2] },
+	{ .compatible = "adi,adis16505-3",
+		.data = &adis16475_chip_info[ADIS16505_3] },
+	{ .compatible = "adi,adis16507-1",
+		.data = &adis16475_chip_info[ADIS16507_1] },
+	{ .compatible = "adi,adis16507-2",
+		.data = &adis16475_chip_info[ADIS16507_2] },
+	{ .compatible = "adi,adis16507-3",
+		.data = &adis16475_chip_info[ADIS16507_3] },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, adis16475_of_match);
+
+static const struct spi_device_id adis16475_ids[] = {
+	{ "adis16470", (kernel_ulong_t)&adis16475_chip_info[ADIS16470] },
+	{ "adis16475-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16475_1] },
+	{ "adis16475-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16475_2] },
+	{ "adis16475-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16475_3] },
+	{ "adis16477-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16477_1] },
+	{ "adis16477-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16477_2] },
+	{ "adis16477-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16477_3] },
+	{ "adis16465-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16465_1] },
+	{ "adis16465-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16465_2] },
+	{ "adis16465-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16465_3] },
+	{ "adis16467-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16467_1] },
+	{ "adis16467-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16467_2] },
+	{ "adis16467-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16467_3] },
+	{ "adis16500", (kernel_ulong_t)&adis16475_chip_info[ADIS16500] },
+	{ "adis16505-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16505_1] },
+	{ "adis16505-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16505_2] },
+	{ "adis16505-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16505_3] },
+	{ "adis16507-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16507_1] },
+	{ "adis16507-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16507_2] },
+	{ "adis16507-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16507_3] },
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, adis16475_ids);
+
 static struct spi_driver adis16475_driver = {
 	.driver = {
 		.name = "adis16475",
 		.of_match_table = adis16475_of_match,
 	},
 	.probe = adis16475_probe,
+	.id_table = adis16475_ids,
 };
 module_spi_driver(adis16475_driver);
 
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
index 3fbeef1a7018..6b034dccc3b1 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
@@ -750,13 +750,13 @@ inv_mpu6050_read_raw(struct iio_dev *indio_dev,
 			ret = inv_mpu6050_sensor_show(st, st->reg->gyro_offset,
 						chan->channel2, val);
 			mutex_unlock(&st->lock);
-			return IIO_VAL_INT;
+			return ret;
 		case IIO_ACCEL:
 			mutex_lock(&st->lock);
 			ret = inv_mpu6050_sensor_show(st, st->reg->accl_offset,
 						chan->channel2, val);
 			mutex_unlock(&st->lock);
-			return IIO_VAL_INT;
+			return ret;
 
 		default:
 			return -EINVAL;
diff --git a/drivers/iio/light/hid-sensor-als.c b/drivers/iio/light/hid-sensor-als.c
index f17304b54468..5cd27f04b45e 100644
--- a/drivers/iio/light/hid-sensor-als.c
+++ b/drivers/iio/light/hid-sensor-als.c
@@ -14,11 +14,8 @@
 #include "../common/hid-sensors/hid-sensor-trigger.h"
 
 enum {
-	CHANNEL_SCAN_INDEX_INTENSITY,
-	CHANNEL_SCAN_INDEX_ILLUM,
-	CHANNEL_SCAN_INDEX_COLOR_TEMP,
-	CHANNEL_SCAN_INDEX_CHROMATICITY_X,
-	CHANNEL_SCAN_INDEX_CHROMATICITY_Y,
+	CHANNEL_SCAN_INDEX_INTENSITY = 0,
+	CHANNEL_SCAN_INDEX_ILLUM = 1,
 	CHANNEL_SCAN_INDEX_MAX
 };
 
@@ -68,40 +65,6 @@ static const struct iio_chan_spec als_channels[] = {
 		BIT(IIO_CHAN_INFO_HYSTERESIS_RELATIVE),
 		.scan_index = CHANNEL_SCAN_INDEX_ILLUM,
 	},
-	{
-		.type = IIO_COLORTEMP,
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) |
-		BIT(IIO_CHAN_INFO_SCALE) |
-		BIT(IIO_CHAN_INFO_SAMP_FREQ) |
-		BIT(IIO_CHAN_INFO_HYSTERESIS) |
-		BIT(IIO_CHAN_INFO_HYSTERESIS_RELATIVE),
-		.scan_index = CHANNEL_SCAN_INDEX_COLOR_TEMP,
-	},
-	{
-		.type = IIO_CHROMATICITY,
-		.modified = 1,
-		.channel2 = IIO_MOD_X,
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) |
-		BIT(IIO_CHAN_INFO_SCALE) |
-		BIT(IIO_CHAN_INFO_SAMP_FREQ) |
-		BIT(IIO_CHAN_INFO_HYSTERESIS) |
-		BIT(IIO_CHAN_INFO_HYSTERESIS_RELATIVE),
-		.scan_index = CHANNEL_SCAN_INDEX_CHROMATICITY_X,
-	},
-	{
-		.type = IIO_CHROMATICITY,
-		.modified = 1,
-		.channel2 = IIO_MOD_Y,
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) |
-		BIT(IIO_CHAN_INFO_SCALE) |
-		BIT(IIO_CHAN_INFO_SAMP_FREQ) |
-		BIT(IIO_CHAN_INFO_HYSTERESIS) |
-		BIT(IIO_CHAN_INFO_HYSTERESIS_RELATIVE),
-		.scan_index = CHANNEL_SCAN_INDEX_CHROMATICITY_Y,
-	},
 	IIO_CHAN_SOFT_TIMESTAMP(CHANNEL_SCAN_INDEX_TIMESTAMP)
 };
 
@@ -140,21 +103,6 @@ static int als_read_raw(struct iio_dev *indio_dev,
 			min = als_state->als[chan->scan_index].logical_minimum;
 			address = HID_USAGE_SENSOR_LIGHT_ILLUM;
 			break;
-		case  CHANNEL_SCAN_INDEX_COLOR_TEMP:
-			report_id = als_state->als[chan->scan_index].report_id;
-			min = als_state->als[chan->scan_index].logical_minimum;
-			address = HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE;
-			break;
-		case  CHANNEL_SCAN_INDEX_CHROMATICITY_X:
-			report_id = als_state->als[chan->scan_index].report_id;
-			min = als_state->als[chan->scan_index].logical_minimum;
-			address = HID_USAGE_SENSOR_LIGHT_CHROMATICITY_X;
-			break;
-		case  CHANNEL_SCAN_INDEX_CHROMATICITY_Y:
-			report_id = als_state->als[chan->scan_index].report_id;
-			min = als_state->als[chan->scan_index].logical_minimum;
-			address = HID_USAGE_SENSOR_LIGHT_CHROMATICITY_Y;
-			break;
 		default:
 			report_id = -1;
 			break;
@@ -275,18 +223,6 @@ static int als_capture_sample(struct hid_sensor_hub_device *hsdev,
 		als_state->scan.illum[CHANNEL_SCAN_INDEX_ILLUM] = sample_data;
 		ret = 0;
 		break;
-	case HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE:
-		als_state->scan.illum[CHANNEL_SCAN_INDEX_COLOR_TEMP] = sample_data;
-		ret = 0;
-		break;
-	case HID_USAGE_SENSOR_LIGHT_CHROMATICITY_X:
-		als_state->scan.illum[CHANNEL_SCAN_INDEX_CHROMATICITY_X] = sample_data;
-		ret = 0;
-		break;
-	case HID_USAGE_SENSOR_LIGHT_CHROMATICITY_Y:
-		als_state->scan.illum[CHANNEL_SCAN_INDEX_CHROMATICITY_Y] = sample_data;
-		ret = 0;
-		break;
 	case HID_USAGE_SENSOR_TIME_TIMESTAMP:
 		als_state->timestamp = hid_sensor_convert_timestamp(&als_state->common_attributes,
 								    *(s64 *)raw_data);
@@ -322,38 +258,6 @@ static int als_parse_report(struct platform_device *pdev,
 			st->als[i].report_id);
 	}
 
-	ret = sensor_hub_input_get_attribute_info(hsdev, HID_INPUT_REPORT,
-				usage_id,
-				HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE,
-				&st->als[CHANNEL_SCAN_INDEX_COLOR_TEMP]);
-	if (ret < 0)
-		return ret;
-	als_adjust_channel_bit_mask(channels, CHANNEL_SCAN_INDEX_COLOR_TEMP,
-				st->als[CHANNEL_SCAN_INDEX_COLOR_TEMP].size);
-
-	dev_dbg(&pdev->dev, "als %x:%x\n",
-		st->als[CHANNEL_SCAN_INDEX_COLOR_TEMP].index,
-		st->als[CHANNEL_SCAN_INDEX_COLOR_TEMP].report_id);
-
-	for (i = 0; i < 2; i++) {
-		int next_scan_index = CHANNEL_SCAN_INDEX_CHROMATICITY_X + i;
-
-		ret = sensor_hub_input_get_attribute_info(hsdev,
-				HID_INPUT_REPORT, usage_id,
-				HID_USAGE_SENSOR_LIGHT_CHROMATICITY_X + i,
-				&st->als[next_scan_index]);
-		if (ret < 0)
-			return ret;
-
-		als_adjust_channel_bit_mask(channels,
-					CHANNEL_SCAN_INDEX_CHROMATICITY_X + i,
-					st->als[next_scan_index].size);
-
-		dev_dbg(&pdev->dev, "als %x:%x\n",
-			st->als[next_scan_index].index,
-			st->als[next_scan_index].report_id);
-	}
-
 	st->scale_precision = hid_sensor_format_scale(usage_id,
 				&st->als[CHANNEL_SCAN_INDEX_INTENSITY],
 				&st->scale_pre_decml, &st->scale_post_decml);
diff --git a/drivers/iio/magnetometer/tmag5273.c b/drivers/iio/magnetometer/tmag5273.c
index c5e5c4ad681e..e8c4ca142d21 100644
--- a/drivers/iio/magnetometer/tmag5273.c
+++ b/drivers/iio/magnetometer/tmag5273.c
@@ -356,7 +356,7 @@ static int tmag5273_read_raw(struct iio_dev *indio_dev,
 	case IIO_CHAN_INFO_OFFSET:
 		switch (chan->type) {
 		case IIO_TEMP:
-			*val = -266314;
+			*val = -16005;
 			return IIO_VAL_INT;
 		default:
 			return -EINVAL;
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index f9ab671c8eda..07c571c7b699 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -96,12 +96,6 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
 		return page_size;
 	}
 
-	/* rdma_for_each_block() has a bug if the page size is smaller than the
-	 * page size used to build the umem. For now prevent smaller page sizes
-	 * from being returned.
-	 */
-	pgsz_bitmap &= GENMASK(BITS_PER_LONG - 1, PAGE_SHIFT);
-
 	/* The best result is the smallest page size that results in the minimum
 	 * number of required pages. Compute the largest page size that could
 	 * work based on VA address bits that don't change.
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 8a6da87f464b..94a7f3b0c71c 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1971,7 +1971,7 @@ int ib_get_eth_speed(struct ib_device *dev, u32 port_num, u16 *speed, u8 *width)
 	int rc;
 	u32 netdev_speed;
 	struct net_device *netdev;
-	struct ethtool_link_ksettings lksettings;
+	struct ethtool_link_ksettings lksettings = {};
 
 	if (rdma_port_get_link_layer(dev, port_num) != IB_LINK_LAYER_ETHERNET)
 		return -EINVAL;
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index f79369c8360a..a99c68247af0 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -71,7 +71,7 @@ static char version[] =
 		BNXT_RE_DESC "\n";
 
 MODULE_AUTHOR("Eddie Wai <eddie.wai@broadcom.com>");
-MODULE_DESCRIPTION(BNXT_RE_DESC " Driver");
+MODULE_DESCRIPTION(BNXT_RE_DESC);
 MODULE_LICENSE("Dual BSD/GPL");
 
 /* globals */
diff --git a/drivers/infiniband/hw/erdma/erdma_hw.h b/drivers/infiniband/hw/erdma/erdma_hw.h
index 9d316fdc6f9a..a155519a862f 100644
--- a/drivers/infiniband/hw/erdma/erdma_hw.h
+++ b/drivers/infiniband/hw/erdma/erdma_hw.h
@@ -11,8 +11,6 @@
 #include <linux/types.h>
 
 /* PCIe device related definition. */
-#define PCI_VENDOR_ID_ALIBABA 0x1ded
-
 #define ERDMA_PCI_WIDTH 64
 #define ERDMA_FUNC_BAR 0
 #define ERDMA_MISX_BAR 2
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index 0cd2612a4987..2bca9560f32d 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -4760,10 +4760,15 @@ static int check_cong_type(struct ib_qp *ibqp,
 		cong_alg->wnd_mode_sel = WND_LIMIT;
 		break;
 	default:
-		ibdev_err(&hr_dev->ib_dev,
-			  "error type(%u) for congestion selection.\n",
-			  hr_dev->caps.cong_type);
-		return -EINVAL;
+		ibdev_warn(&hr_dev->ib_dev,
+			   "invalid type(%u) for congestion selection.\n",
+			   hr_dev->caps.cong_type);
+		hr_dev->caps.cong_type = CONG_TYPE_DCQCN;
+		cong_alg->alg_sel = CONG_DCQCN;
+		cong_alg->alg_sub_sel = UNSUPPORT_CONG_LEVEL;
+		cong_alg->dip_vld = DIP_INVALID;
+		cong_alg->wnd_mode_sel = WND_LIMIT;
+		break;
 	}
 
 	return 0;
diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c
index 8fa7e4a18e73..bd4b2b896444 100644
--- a/drivers/infiniband/hw/irdma/hw.c
+++ b/drivers/infiniband/hw/irdma/hw.c
@@ -321,7 +321,11 @@ static void irdma_process_aeq(struct irdma_pci_f *rf)
 			break;
 		case IRDMA_AE_QP_SUSPEND_COMPLETE:
 			if (iwqp->iwdev->vsi.tc_change_pending) {
-				atomic_dec(&iwqp->sc_qp.vsi->qp_suspend_reqs);
+				if (!atomic_dec_return(&qp->vsi->qp_suspend_reqs))
+					wake_up(&iwqp->iwdev->suspend_wq);
+			}
+			if (iwqp->suspend_pending) {
+				iwqp->suspend_pending = false;
 				wake_up(&iwqp->iwdev->suspend_wq);
 			}
 			break;
@@ -581,9 +585,6 @@ static void irdma_destroy_cqp(struct irdma_pci_f *rf)
 	struct irdma_cqp *cqp = &rf->cqp;
 	int status = 0;
 
-	if (rf->cqp_cmpl_wq)
-		destroy_workqueue(rf->cqp_cmpl_wq);
-
 	status = irdma_sc_cqp_destroy(dev->cqp);
 	if (status)
 		ibdev_dbg(to_ibdev(dev), "ERR: Destroy CQP failed %d\n", status);
@@ -748,6 +749,9 @@ static void irdma_destroy_ccq(struct irdma_pci_f *rf)
 	struct irdma_ccq *ccq = &rf->ccq;
 	int status = 0;
 
+	if (rf->cqp_cmpl_wq)
+		destroy_workqueue(rf->cqp_cmpl_wq);
+
 	if (!rf->reset)
 		status = irdma_sc_ccq_destroy(dev->ccq, 0, true);
 	if (status)
@@ -1180,7 +1184,6 @@ static int irdma_create_ceq(struct irdma_pci_f *rf, struct irdma_ceq *iwceq,
 	int status;
 	struct irdma_ceq_init_info info = {};
 	struct irdma_sc_dev *dev = &rf->sc_dev;
-	u64 scratch;
 	u32 ceq_size;
 
 	info.ceq_id = ceq_id;
@@ -1201,14 +1204,13 @@ static int irdma_create_ceq(struct irdma_pci_f *rf, struct irdma_ceq *iwceq,
 	iwceq->sc_ceq.ceq_id = ceq_id;
 	info.dev = dev;
 	info.vsi = vsi;
-	scratch = (uintptr_t)&rf->cqp.sc_cqp;
 	status = irdma_sc_ceq_init(&iwceq->sc_ceq, &info);
 	if (!status) {
 		if (dev->ceq_valid)
 			status = irdma_cqp_ceq_cmd(&rf->sc_dev, &iwceq->sc_ceq,
 						   IRDMA_OP_CEQ_CREATE);
 		else
-			status = irdma_sc_cceq_create(&iwceq->sc_ceq, scratch);
+			status = irdma_sc_cceq_create(&iwceq->sc_ceq, 0);
 	}
 
 	if (status) {
diff --git a/drivers/infiniband/hw/irdma/main.c b/drivers/infiniband/hw/irdma/main.c
index 9ac48b4dab41..3f13200ff71b 100644
--- a/drivers/infiniband/hw/irdma/main.c
+++ b/drivers/infiniband/hw/irdma/main.c
@@ -48,7 +48,7 @@ static void irdma_prep_tc_change(struct irdma_device *iwdev)
 	/* Wait for all qp's to suspend */
 	wait_event_timeout(iwdev->suspend_wq,
 			   !atomic_read(&iwdev->vsi.qp_suspend_reqs),
-			   IRDMA_EVENT_TIMEOUT);
+			   msecs_to_jiffies(IRDMA_EVENT_TIMEOUT_MS));
 	irdma_ws_reset(&iwdev->vsi);
 }
 
diff --git a/drivers/infiniband/hw/irdma/main.h b/drivers/infiniband/hw/irdma/main.h
index d66d87bb8bc4..b65bc2ea542f 100644
--- a/drivers/infiniband/hw/irdma/main.h
+++ b/drivers/infiniband/hw/irdma/main.h
@@ -78,7 +78,7 @@ extern struct auxiliary_driver i40iw_auxiliary_drv;
 
 #define MAX_DPC_ITERATIONS	128
 
-#define IRDMA_EVENT_TIMEOUT		50000
+#define IRDMA_EVENT_TIMEOUT_MS		5000
 #define IRDMA_VCHNL_EVENT_TIMEOUT	100000
 #define IRDMA_RST_TIMEOUT_HZ		4
 
diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index 2138f0a2ff85..b5eb8d421988 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -1157,6 +1157,21 @@ exit:
 	return prio;
 }
 
+static int irdma_wait_for_suspend(struct irdma_qp *iwqp)
+{
+	if (!wait_event_timeout(iwqp->iwdev->suspend_wq,
+				!iwqp->suspend_pending,
+				msecs_to_jiffies(IRDMA_EVENT_TIMEOUT_MS))) {
+		iwqp->suspend_pending = false;
+		ibdev_warn(&iwqp->iwdev->ibdev,
+			   "modify_qp timed out waiting for suspend. qp_id = %d, last_ae = 0x%x\n",
+			   iwqp->ibqp.qp_num, iwqp->last_aeq);
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
 /**
  * irdma_modify_qp_roce - modify qp request
  * @ibqp: qp's pointer for modify
@@ -1420,17 +1435,11 @@ int irdma_modify_qp_roce(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 
 			info.next_iwarp_state = IRDMA_QP_STATE_SQD;
 			issue_modify_qp = 1;
+			iwqp->suspend_pending = true;
 			break;
 		case IB_QPS_SQE:
 		case IB_QPS_ERR:
 		case IB_QPS_RESET:
-			if (iwqp->iwarp_state == IRDMA_QP_STATE_RTS) {
-				spin_unlock_irqrestore(&iwqp->lock, flags);
-				info.next_iwarp_state = IRDMA_QP_STATE_SQD;
-				irdma_hw_modify_qp(iwdev, iwqp, &info, true);
-				spin_lock_irqsave(&iwqp->lock, flags);
-			}
-
 			if (iwqp->iwarp_state == IRDMA_QP_STATE_ERROR) {
 				spin_unlock_irqrestore(&iwqp->lock, flags);
 				if (udata && udata->inlen) {
@@ -1467,6 +1476,11 @@ int irdma_modify_qp_roce(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 			ctx_info->rem_endpoint_idx = udp_info->arp_idx;
 			if (irdma_hw_modify_qp(iwdev, iwqp, &info, true))
 				return -EINVAL;
+			if (info.next_iwarp_state == IRDMA_QP_STATE_SQD) {
+				ret = irdma_wait_for_suspend(iwqp);
+				if (ret)
+					return ret;
+			}
 			spin_lock_irqsave(&iwqp->lock, flags);
 			if (iwqp->iwarp_state == info.curr_iwarp_state) {
 				iwqp->iwarp_state = info.next_iwarp_state;
@@ -2900,7 +2914,7 @@ static struct irdma_mr *irdma_alloc_iwmr(struct ib_umem *region,
 	iwmr->type = reg_type;
 
 	pgsz_bitmap = (reg_type == IRDMA_MEMREG_TYPE_MEM) ?
-		iwdev->rf->sc_dev.hw_attrs.page_size_cap : PAGE_SIZE;
+		iwdev->rf->sc_dev.hw_attrs.page_size_cap : SZ_4K;
 
 	iwmr->page_size = ib_umem_find_best_pgsz(region, pgsz_bitmap, virt);
 	if (unlikely(!iwmr->page_size)) {
@@ -2932,6 +2946,11 @@ static int irdma_reg_user_mr_type_qp(struct irdma_mem_reg_req req,
 	int err;
 	u8 lvl;
 
+	/* iWarp: Catch page not starting on OS page boundary */
+	if (!rdma_protocol_roce(&iwdev->ibdev, 1) &&
+	    ib_umem_offset(iwmr->region))
+		return -EINVAL;
+
 	total = req.sq_pages + req.rq_pages + 1;
 	if (total > iwmr->page_cnt)
 		return -EINVAL;
diff --git a/drivers/infiniband/hw/irdma/verbs.h b/drivers/infiniband/hw/irdma/verbs.h
index c42ac22de00e..cfa140b36395 100644
--- a/drivers/infiniband/hw/irdma/verbs.h
+++ b/drivers/infiniband/hw/irdma/verbs.h
@@ -198,6 +198,7 @@ struct irdma_qp {
 	u8 flush_issued : 1;
 	u8 sig_all : 1;
 	u8 pau_mode : 1;
+	u8 suspend_pending : 1;
 	u8 rsvd : 1;
 	u8 iwarp_state;
 	u16 term_sq_flush_code;
diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index 8ba53edf2311..869369cb5b5f 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -2498,7 +2498,7 @@ static void dispatch_event_fd(struct list_head *fd_list,
 
 	list_for_each_entry_rcu(item, fd_list, xa_list) {
 		if (item->eventfd)
-			eventfd_signal(item->eventfd, 1);
+			eventfd_signal(item->eventfd);
 		else
 			deliver_event(item, data);
 	}
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index 07261523c554..7f3167ce2972 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -384,7 +384,7 @@ static void complete_rdma_req(struct rtrs_clt_io_req *req, int errno,
 	struct rtrs_clt_path *clt_path;
 	int err;
 
-	if (WARN_ON(!req->in_use))
+	if (!req->in_use)
 		return;
 	if (WARN_ON(!req->con))
 		return;
@@ -1699,7 +1699,7 @@ static int create_con_cq_qp(struct rtrs_clt_con *con)
 		clt_path->s.dev_ref++;
 		max_send_wr = min_t(int, wr_limit,
 			      /* QD * (REQ + RSP + FR REGS or INVS) + drain */
-			      clt_path->queue_depth * 3 + 1);
+			      clt_path->queue_depth * 4 + 1);
 		max_recv_wr = min_t(int, wr_limit,
 			      clt_path->queue_depth * 3 + 1);
 		max_send_sge = 2;
@@ -2350,8 +2350,6 @@ static int init_conns(struct rtrs_clt_path *clt_path)
 	if (err)
 		goto destroy;
 
-	rtrs_start_hb(&clt_path->s);
-
 	return 0;
 
 destroy:
@@ -2625,6 +2623,7 @@ static int init_path(struct rtrs_clt_path *clt_path)
 		goto out;
 	}
 	rtrs_clt_path_up(clt_path);
+	rtrs_start_hb(&clt_path->s);
 out:
 	mutex_unlock(&clt_path->init_mutex);
 
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
index 75e56604e462..1d33efb8fb03 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
@@ -65,8 +65,9 @@ static bool rtrs_srv_change_state(struct rtrs_srv_path *srv_path,
 {
 	enum rtrs_srv_state old_state;
 	bool changed = false;
+	unsigned long flags;
 
-	spin_lock_irq(&srv_path->state_lock);
+	spin_lock_irqsave(&srv_path->state_lock, flags);
 	old_state = srv_path->state;
 	switch (new_state) {
 	case RTRS_SRV_CONNECTED:
@@ -87,7 +88,7 @@ static bool rtrs_srv_change_state(struct rtrs_srv_path *srv_path,
 	}
 	if (changed)
 		srv_path->state = new_state;
-	spin_unlock_irq(&srv_path->state_lock);
+	spin_unlock_irqrestore(&srv_path->state_lock, flags);
 
 	return changed;
 }
@@ -550,7 +551,10 @@ static void unmap_cont_bufs(struct rtrs_srv_path *srv_path)
 		struct rtrs_srv_mr *srv_mr;
 
 		srv_mr = &srv_path->mrs[i];
-		rtrs_iu_free(srv_mr->iu, srv_path->s.dev->ib_dev, 1);
+
+		if (always_invalidate)
+			rtrs_iu_free(srv_mr->iu, srv_path->s.dev->ib_dev, 1);
+
 		ib_dereg_mr(srv_mr->mr);
 		ib_dma_unmap_sg(srv_path->s.dev->ib_dev, srv_mr->sgt.sgl,
 				srv_mr->sgt.nents, DMA_BIDIRECTIONAL);
@@ -709,20 +713,23 @@ static void rtrs_srv_info_rsp_done(struct ib_cq *cq, struct ib_wc *wc)
 	WARN_ON(wc->opcode != IB_WC_SEND);
 }
 
-static void rtrs_srv_path_up(struct rtrs_srv_path *srv_path)
+static int rtrs_srv_path_up(struct rtrs_srv_path *srv_path)
 {
 	struct rtrs_srv_sess *srv = srv_path->srv;
 	struct rtrs_srv_ctx *ctx = srv->ctx;
-	int up;
+	int up, ret = 0;
 
 	mutex_lock(&srv->paths_ev_mutex);
 	up = ++srv->paths_up;
 	if (up == 1)
-		ctx->ops.link_ev(srv, RTRS_SRV_LINK_EV_CONNECTED, NULL);
+		ret = ctx->ops.link_ev(srv, RTRS_SRV_LINK_EV_CONNECTED, NULL);
 	mutex_unlock(&srv->paths_ev_mutex);
 
 	/* Mark session as established */
-	srv_path->established = true;
+	if (!ret)
+		srv_path->established = true;
+
+	return ret;
 }
 
 static void rtrs_srv_path_down(struct rtrs_srv_path *srv_path)
@@ -851,7 +858,12 @@ static int process_info_req(struct rtrs_srv_con *con,
 		goto iu_free;
 	kobject_get(&srv_path->kobj);
 	get_device(&srv_path->srv->dev);
-	rtrs_srv_change_state(srv_path, RTRS_SRV_CONNECTED);
+	err = rtrs_srv_change_state(srv_path, RTRS_SRV_CONNECTED);
+	if (!err) {
+		rtrs_err(s, "rtrs_srv_change_state(), err: %d\n", err);
+		goto iu_free;
+	}
+
 	rtrs_srv_start_hb(srv_path);
 
 	/*
@@ -860,7 +872,11 @@ static int process_info_req(struct rtrs_srv_con *con,
 	 * all connections are successfully established.  Thus, simply notify
 	 * listener with a proper event if we are the first path.
 	 */
-	rtrs_srv_path_up(srv_path);
+	err = rtrs_srv_path_up(srv_path);
+	if (err) {
+		rtrs_err(s, "rtrs_srv_path_up(), err: %d\n", err);
+		goto iu_free;
+	}
 
 	ib_dma_sync_single_for_device(srv_path->s.dev->ib_dev,
 				      tx_iu->dma_addr,
@@ -1516,7 +1532,6 @@ static void rtrs_srv_close_work(struct work_struct *work)
 
 	srv_path = container_of(work, typeof(*srv_path), close_work);
 
-	rtrs_srv_destroy_path_files(srv_path);
 	rtrs_srv_stop_hb(srv_path);
 
 	for (i = 0; i < srv_path->s.con_num; i++) {
@@ -1536,6 +1551,8 @@ static void rtrs_srv_close_work(struct work_struct *work)
 	/* Wait for all completion */
 	wait_for_completion(&srv_path->complete_done);
 
+	rtrs_srv_destroy_path_files(srv_path);
+
 	/* Notify upper layer if we are the last path */
 	rtrs_srv_path_down(srv_path);
 
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index f5c21565bb3c..e2c1848182de 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -286,6 +286,7 @@ static const struct xpad_device {
 	{ 0x146b, 0x0604, "Bigben Interactive DAIJA Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
 	{ 0x1532, 0x0a00, "Razer Atrox Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE },
 	{ 0x1532, 0x0a03, "Razer Wildcat", 0, XTYPE_XBOXONE },
+	{ 0x1532, 0x0a29, "Razer Wolverine V2", 0, XTYPE_XBOXONE },
 	{ 0x15e4, 0x3f00, "Power A Mini Pro Elite", 0, XTYPE_XBOX360 },
 	{ 0x15e4, 0x3f0a, "Xbox Airflo wired controller", 0, XTYPE_XBOX360 },
 	{ 0x15e4, 0x3f10, "Batarang Xbox 360 controller", 0, XTYPE_XBOX360 },
diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c
index c92e544c792d..786f00f6b7fd 100644
--- a/drivers/input/keyboard/atkbd.c
+++ b/drivers/input/keyboard/atkbd.c
@@ -765,6 +765,44 @@ static void atkbd_deactivate(struct atkbd *atkbd)
 			ps2dev->serio->phys);
 }
 
+#ifdef CONFIG_X86
+static bool atkbd_is_portable_device(void)
+{
+	static const char * const chassis_types[] = {
+		"8",	/* Portable */
+		"9",	/* Laptop */
+		"10",	/* Notebook */
+		"14",	/* Sub-Notebook */
+		"31",	/* Convertible */
+		"32",	/* Detachable */
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(chassis_types); i++)
+		if (dmi_match(DMI_CHASSIS_TYPE, chassis_types[i]))
+			return true;
+
+	return false;
+}
+
+/*
+ * On many modern laptops ATKBD_CMD_GETID may cause problems, on these laptops
+ * the controller is always in translated mode. In this mode mice/touchpads will
+ * not work. So in this case simply assume a keyboard is connected to avoid
+ * confusing some laptop keyboards.
+ *
+ * Skipping ATKBD_CMD_GETID ends up using a fake keyboard id. Using a fake id is
+ * ok in translated mode, only atkbd_select_set() checks atkbd->id and in
+ * translated mode that is a no-op.
+ */
+static bool atkbd_skip_getid(struct atkbd *atkbd)
+{
+	return atkbd->translated && atkbd_is_portable_device();
+}
+#else
+static inline bool atkbd_skip_getid(struct atkbd *atkbd) { return false; }
+#endif
+
 /*
  * atkbd_probe() probes for an AT keyboard on a serio port.
  */
@@ -794,12 +832,12 @@ static int atkbd_probe(struct atkbd *atkbd)
  */
 
 	param[0] = param[1] = 0xa5;	/* initialize with invalid values */
-	if (ps2_command(ps2dev, param, ATKBD_CMD_GETID)) {
+	if (atkbd_skip_getid(atkbd) || ps2_command(ps2dev, param, ATKBD_CMD_GETID)) {
 
 /*
- * If the get ID command failed, we check if we can at least set the LEDs on
- * the keyboard. This should work on every keyboard out there. It also turns
- * the LEDs off, which we want anyway.
+ * If the get ID command was skipped or failed, we check if we can at least set
+ * the LEDs on the keyboard. This should work on every keyboard out there.
+ * It also turns the LEDs off, which we want anyway.
  */
 		param[0] = 0;
 		if (ps2_command(ps2dev, param, ATKBD_CMD_SETLEDS))
diff --git a/drivers/input/keyboard/ipaq-micro-keys.c b/drivers/input/keyboard/ipaq-micro-keys.c
index 7b509bce2b33..1d71dd79ffd2 100644
--- a/drivers/input/keyboard/ipaq-micro-keys.c
+++ b/drivers/input/keyboard/ipaq-micro-keys.c
@@ -105,6 +105,9 @@ static int micro_key_probe(struct platform_device *pdev)
 	keys->codes = devm_kmemdup(&pdev->dev, micro_keycodes,
 			   keys->input->keycodesize * keys->input->keycodemax,
 			   GFP_KERNEL);
+	if (!keys->codes)
+		return -ENOMEM;
+
 	keys->input->keycode = keys->codes;
 
 	__set_bit(EV_KEY, keys->input->evbit);
diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c
index 08bcee3d6bcc..f6d060377d18 100644
--- a/drivers/input/misc/soc_button_array.c
+++ b/drivers/input/misc/soc_button_array.c
@@ -299,6 +299,11 @@ static int soc_button_parse_btn_desc(struct device *dev,
 		info->name = "power";
 		info->event_code = KEY_POWER;
 		info->wakeup = true;
+	} else if (upage == 0x01 && usage == 0xc6) {
+		info->name = "airplane mode switch";
+		info->event_type = EV_SW;
+		info->event_code = SW_RFKILL_ALL;
+		info->active_low = false;
 	} else if (upage == 0x01 && usage == 0xca) {
 		info->name = "rotation lock switch";
 		info->event_type = EV_SW;
diff --git a/drivers/input/mouse/amimouse.c b/drivers/input/mouse/amimouse.c
index a50e50354832..cda0c3ff5a28 100644
--- a/drivers/input/mouse/amimouse.c
+++ b/drivers/input/mouse/amimouse.c
@@ -125,16 +125,15 @@ static int __init amimouse_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int __exit amimouse_remove(struct platform_device *pdev)
+static void __exit amimouse_remove(struct platform_device *pdev)
 {
 	struct input_dev *dev = platform_get_drvdata(pdev);
 
 	input_unregister_device(dev);
-	return 0;
 }
 
 static struct platform_driver amimouse_driver = {
-	.remove = __exit_p(amimouse_remove),
+	.remove_new = __exit_p(amimouse_remove),
 	.driver   = {
 		.name	= "amiga-mouse",
 	},
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 22d16d80efb9..7a303a9d6bf7 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -183,6 +183,7 @@ static const char * const smbus_pnp_ids[] = {
 	"LEN009b", /* T580 */
 	"LEN0402", /* X1 Extreme Gen 2 / P1 Gen 2 */
 	"LEN040f", /* P1 Gen 3 */
+	"LEN0411", /* L14 Gen 1 */
 	"LEN200f", /* T450s */
 	"LEN2044", /* L470  */
 	"LEN2054", /* E480 */
diff --git a/drivers/input/rmi4/rmi_spi.c b/drivers/input/rmi4/rmi_spi.c
index 852aeb0b2c07..07c866f42296 100644
--- a/drivers/input/rmi4/rmi_spi.c
+++ b/drivers/input/rmi4/rmi_spi.c
@@ -375,7 +375,7 @@ static int rmi_spi_probe(struct spi_device *spi)
 	struct rmi_device_platform_data *spi_pdata = spi->dev.platform_data;
 	int error;
 
-	if (spi->master->flags & SPI_MASTER_HALF_DUPLEX)
+	if (spi->master->flags & SPI_CONTROLLER_HALF_DUPLEX)
 		return -EINVAL;
 
 	rmi_spi = devm_kzalloc(&spi->dev, sizeof(struct rmi_spi_xport),
diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h
index 9c39553d30fa..b585b1dab870 100644
--- a/drivers/input/serio/i8042-acpipnpio.h
+++ b/drivers/input/serio/i8042-acpipnpio.h
@@ -361,6 +361,14 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.driver_data = (void *)(SERIO_QUIRK_DRITEK)
 	},
 	{
+		/* Acer TravelMate P459-G2-M */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate P459-G2-M"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
+	},
+	{
 		/* Amoi M636/A737 */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Amoi Electronics CO.,LTD."),
diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c
index dfab160ca529..50bac2d79d9b 100644
--- a/drivers/interconnect/core.c
+++ b/drivers/interconnect/core.c
@@ -395,6 +395,9 @@ struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec)
 	}
 	mutex_unlock(&icc_lock);
 
+	if (!node)
+		return ERR_PTR(-EINVAL);
+
 	if (IS_ERR(node))
 		return ERR_CAST(node);
 
diff --git a/drivers/interconnect/qcom/icc-rpm.c b/drivers/interconnect/qcom/icc-rpm.c
index 628e651c555c..dbacb2a7af50 100644
--- a/drivers/interconnect/qcom/icc-rpm.c
+++ b/drivers/interconnect/qcom/icc-rpm.c
@@ -307,7 +307,7 @@ static u64 qcom_icc_calc_rate(struct qcom_icc_provider *qp, struct qcom_icc_node
 
 	if (qn->ib_coeff) {
 		agg_peak_rate = qn->max_peak[ctx] * 100;
-		agg_peak_rate = div_u64(qn->max_peak[ctx], qn->ib_coeff);
+		agg_peak_rate = div_u64(agg_peak_rate, qn->ib_coeff);
 	} else {
 		agg_peak_rate = qn->max_peak[ctx];
 	}
diff --git a/drivers/interconnect/qcom/sm8250.c b/drivers/interconnect/qcom/sm8250.c
index 83aeb3eedc19..02d40eea0d69 100644
--- a/drivers/interconnect/qcom/sm8250.c
+++ b/drivers/interconnect/qcom/sm8250.c
@@ -1995,6 +1995,7 @@ static struct platform_driver qnoc_driver = {
 	.driver = {
 		.name = "qnoc-sm8250",
 		.of_match_table = qnoc_of_match,
+		.sync_state = icc_sync_state,
 	},
 };
 module_platform_driver(qnoc_driver);
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index fcc987f5d4ed..b9a0523cbb0a 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -3357,7 +3357,7 @@ static void irq_remapping_prepare_irte(struct amd_ir_data *data,
 
 	data->irq_2_irte.devid = devid;
 	data->irq_2_irte.index = index + sub_handle;
-	iommu->irte_ops->prepare(data->entry, apic->delivery_mode,
+	iommu->irte_ops->prepare(data->entry, APIC_DELIVERY_MODE_FIXED,
 				 apic->dest_mode_logical, irq_cfg->vector,
 				 irq_cfg->dest_apicid, devid);
 
@@ -3634,7 +3634,7 @@ int amd_iommu_deactivate_guest_mode(void *data)
 
 	entry->lo.fields_remap.valid       = valid;
 	entry->lo.fields_remap.dm          = apic->dest_mode_logical;
-	entry->lo.fields_remap.int_type    = apic->delivery_mode;
+	entry->lo.fields_remap.int_type    = APIC_DELIVERY_MODE_FIXED;
 	entry->hi.fields.vector            = cfg->vector;
 	entry->lo.fields_remap.destination =
 				APICID_TO_IRTE_DEST_LO(cfg->dest_apicid);
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index 961205ba86d2..925ac6a47bce 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -188,7 +188,7 @@
 #ifdef CONFIG_CMA_ALIGNMENT
 #define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + CONFIG_CMA_ALIGNMENT)
 #else
-#define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + MAX_ORDER)
+#define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + MAX_PAGE_ORDER)
 #endif
 
 /*
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 85163a83df2f..e59f50e11ea8 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -884,7 +884,7 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev,
 	struct page **pages;
 	unsigned int i = 0, nid = dev_to_node(dev);
 
-	order_mask &= GENMASK(MAX_ORDER, 0);
+	order_mask &= GENMASK(MAX_PAGE_ORDER, 0);
 	if (!order_mask)
 		return NULL;
 
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index a3414afe11b0..23cb80d62a9a 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -1522,6 +1522,15 @@ void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
 {
 	struct qi_desc desc;
 
+	/*
+	 * VT-d spec, section 4.3:
+	 *
+	 * Software is recommended to not submit any Device-TLB invalidation
+	 * requests while address remapping hardware is disabled.
+	 */
+	if (!(iommu->gcmd & DMA_GCMD_TE))
+		return;
+
 	if (mask) {
 		addr |= (1ULL << (VTD_PAGE_SHIFT + mask - 1)) - 1;
 		desc.qw1 = QI_DEV_IOTLB_ADDR(addr) | QI_DEV_IOTLB_SIZE;
@@ -1587,6 +1596,15 @@ void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid,
 	unsigned long mask = 1UL << (VTD_PAGE_SHIFT + size_order - 1);
 	struct qi_desc desc = {.qw1 = 0, .qw2 = 0, .qw3 = 0};
 
+	/*
+	 * VT-d spec, section 4.3:
+	 *
+	 * Software is recommended to not submit any Device-TLB invalidation
+	 * requests while address remapping hardware is disabled.
+	 */
+	if (!(iommu->gcmd & DMA_GCMD_TE))
+		return;
+
 	desc.qw0 = QI_DEV_EIOTLB_PASID(pasid) | QI_DEV_EIOTLB_SID(sid) |
 		QI_DEV_EIOTLB_QDEP(qdep) | QI_DEIOTLB_TYPE |
 		QI_DEV_IOTLB_PFSID(pfsid);
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 3531b956556c..897159dba47d 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -299,7 +299,7 @@ static int iommu_skip_te_disable;
 #define IDENTMAP_AZALIA		4
 
 const struct iommu_ops intel_iommu_ops;
-const struct iommu_dirty_ops intel_dirty_ops;
+static const struct iommu_dirty_ops intel_dirty_ops;
 
 static bool translation_pre_enabled(struct intel_iommu *iommu)
 {
@@ -2207,6 +2207,8 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 			attr |= DMA_FL_PTE_DIRTY;
 	}
 
+	domain->has_mappings = true;
+
 	pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | attr;
 
 	while (nr_pages > 0) {
@@ -2490,7 +2492,8 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
 		return ret;
 	}
 
-	iommu_enable_pci_caps(info);
+	if (sm_supported(info->iommu) || !domain_type_is_si(info->domain))
+		iommu_enable_pci_caps(info);
 
 	return 0;
 }
@@ -3925,8 +3928,8 @@ static int domain_context_clear_one_cb(struct pci_dev *pdev, u16 alias, void *op
  */
 static void domain_context_clear(struct device_domain_info *info)
 {
-	if (!info->iommu || !info->dev || !dev_is_pci(info->dev))
-		return;
+	if (!dev_is_pci(info->dev))
+		domain_context_clear_one(info, info->bus, info->devfn);
 
 	pci_for_each_dma_alias(to_pci_dev(info->dev),
 			       &domain_context_clear_one_cb, info);
@@ -4360,7 +4363,8 @@ static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain)
 		return true;
 
 	spin_lock_irqsave(&dmar_domain->lock, flags);
-	if (!domain_support_force_snooping(dmar_domain)) {
+	if (!domain_support_force_snooping(dmar_domain) ||
+	    (!dmar_domain->use_first_level && dmar_domain->has_mappings)) {
 		spin_unlock_irqrestore(&dmar_domain->lock, flags);
 		return false;
 	}
@@ -4925,7 +4929,7 @@ static int intel_iommu_read_and_clear_dirty(struct iommu_domain *domain,
 	return 0;
 }
 
-const struct iommu_dirty_ops intel_dirty_ops = {
+static const struct iommu_dirty_ops intel_dirty_ops = {
 	.set_dirty_tracking = intel_iommu_set_dirty_tracking,
 	.read_and_clear_dirty = intel_iommu_read_and_clear_dirty,
 };
@@ -5073,7 +5077,7 @@ static void quirk_igfx_skip_te_disable(struct pci_dev *dev)
 	ver = (dev->device >> 8) & 0xff;
 	if (ver != 0x45 && ver != 0x46 && ver != 0x4c &&
 	    ver != 0x4e && ver != 0x8a && ver != 0x98 &&
-	    ver != 0x9a && ver != 0xa7)
+	    ver != 0x9a && ver != 0xa7 && ver != 0x7d)
 		return;
 
 	if (risky_device(dev))
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index 65d37a138c75..ce030c5b5772 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -602,6 +602,9 @@ struct dmar_domain {
 					 */
 	u8 dirty_tracking:1;		/* Dirty tracking is enabled */
 	u8 nested_parent:1;		/* Has other domains nested on it */
+	u8 has_mappings:1;		/* Has mappings configured through
+					 * iommu_map() interface.
+					 */
 
 	spinlock_t lock;		/* Protect device tracking lists */
 	struct list_head devices;	/* all devices' list */
diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
index 29b9e55dcf26..566297bc87dd 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -1112,7 +1112,7 @@ static void prepare_irte(struct irte *irte, int vector, unsigned int dest)
 	 * irq migration in the presence of interrupt-remapping.
 	*/
 	irte->trigger_mode = 0;
-	irte->dlvry_mode = apic->delivery_mode;
+	irte->dlvry_mode = APIC_DELIVERY_MODE_FIXED;
 	irte->vector = vector;
 	irte->dest_id = IRTE_DEST(dest);
 	irte->redir_hint = 1;
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 50a481c895b8..ac12f76c1212 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -216,6 +216,27 @@ static void intel_flush_svm_range(struct intel_svm *svm, unsigned long address,
 	rcu_read_unlock();
 }
 
+static void intel_flush_svm_all(struct intel_svm *svm)
+{
+	struct device_domain_info *info;
+	struct intel_svm_dev *sdev;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(sdev, &svm->devs, list) {
+		info = dev_iommu_priv_get(sdev->dev);
+
+		qi_flush_piotlb(sdev->iommu, sdev->did, svm->pasid, 0, -1UL, 0);
+		if (info->ats_enabled) {
+			qi_flush_dev_iotlb_pasid(sdev->iommu, sdev->sid, info->pfsid,
+						 svm->pasid, sdev->qdep,
+						 0, 64 - VTD_PAGE_SHIFT);
+			quirk_extra_dev_tlb_flush(info, 0, 64 - VTD_PAGE_SHIFT,
+						  svm->pasid, sdev->qdep);
+		}
+	}
+	rcu_read_unlock();
+}
+
 /* Pages have been freed at this point */
 static void intel_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn,
 					struct mm_struct *mm,
@@ -223,6 +244,11 @@ static void intel_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn,
 {
 	struct intel_svm *svm = container_of(mn, struct intel_svm, notifier);
 
+	if (start == 0 && end == -1UL) {
+		intel_flush_svm_all(svm);
+		return;
+	}
+
 	intel_flush_svm_range(svm, start,
 			      (end - start + PAGE_SIZE - 1) >> VTD_PAGE_SHIFT, 0);
 }
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index f17a1113f3d6..33e2a9b5d339 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -485,11 +485,12 @@ static void iommu_deinit_device(struct device *dev)
 	dev_iommu_free(dev);
 }
 
+DEFINE_MUTEX(iommu_probe_device_lock);
+
 static int __iommu_probe_device(struct device *dev, struct list_head *group_list)
 {
 	const struct iommu_ops *ops = dev->bus->iommu_ops;
 	struct iommu_group *group;
-	static DEFINE_MUTEX(iommu_probe_device_lock);
 	struct group_device *gdev;
 	int ret;
 
@@ -502,17 +503,15 @@ static int __iommu_probe_device(struct device *dev, struct list_head *group_list
 	 * probably be able to use device_lock() here to minimise the scope,
 	 * but for now enforcing a simple global ordering is fine.
 	 */
-	mutex_lock(&iommu_probe_device_lock);
+	lockdep_assert_held(&iommu_probe_device_lock);
 
 	/* Device is probed already if in a group */
-	if (dev->iommu_group) {
-		ret = 0;
-		goto out_unlock;
-	}
+	if (dev->iommu_group)
+		return 0;
 
 	ret = iommu_init_device(dev, ops);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
 	group = dev->iommu_group;
 	gdev = iommu_group_alloc_device(group, dev);
@@ -548,7 +547,6 @@ static int __iommu_probe_device(struct device *dev, struct list_head *group_list
 			list_add_tail(&group->entry, group_list);
 	}
 	mutex_unlock(&group->mutex);
-	mutex_unlock(&iommu_probe_device_lock);
 
 	if (dev_is_pci(dev))
 		iommu_dma_set_pci_32bit_workaround(dev);
@@ -562,8 +560,6 @@ err_put_group:
 	iommu_deinit_device(dev);
 	mutex_unlock(&group->mutex);
 	iommu_group_put(group);
-out_unlock:
-	mutex_unlock(&iommu_probe_device_lock);
 
 	return ret;
 }
@@ -573,7 +569,9 @@ int iommu_probe_device(struct device *dev)
 	const struct iommu_ops *ops;
 	int ret;
 
+	mutex_lock(&iommu_probe_device_lock);
 	ret = __iommu_probe_device(dev, NULL);
+	mutex_unlock(&iommu_probe_device_lock);
 	if (ret)
 		return ret;
 
@@ -1788,7 +1786,7 @@ iommu_group_alloc_default_domain(struct iommu_group *group, int req_type)
 	 */
 	if (ops->default_domain) {
 		if (req_type)
-			return NULL;
+			return ERR_PTR(-EINVAL);
 		return ops->default_domain;
 	}
 
@@ -1797,15 +1795,15 @@ iommu_group_alloc_default_domain(struct iommu_group *group, int req_type)
 
 	/* The driver gave no guidance on what type to use, try the default */
 	dom = __iommu_group_alloc_default_domain(group, iommu_def_domain_type);
-	if (dom)
+	if (!IS_ERR(dom))
 		return dom;
 
 	/* Otherwise IDENTITY and DMA_FQ defaults will try DMA */
 	if (iommu_def_domain_type == IOMMU_DOMAIN_DMA)
-		return NULL;
+		return ERR_PTR(-EINVAL);
 	dom = __iommu_group_alloc_default_domain(group, IOMMU_DOMAIN_DMA);
-	if (!dom)
-		return NULL;
+	if (IS_ERR(dom))
+		return dom;
 
 	pr_warn("Failed to allocate default IOMMU domain of type %u for group %s - Falling back to IOMMU_DOMAIN_DMA",
 		iommu_def_domain_type, group->name);
@@ -1822,7 +1820,9 @@ static int probe_iommu_group(struct device *dev, void *data)
 	struct list_head *group_list = data;
 	int ret;
 
+	mutex_lock(&iommu_probe_device_lock);
 	ret = __iommu_probe_device(dev, group_list);
+	mutex_unlock(&iommu_probe_device_lock);
 	if (ret == -ENODEV)
 		ret = 0;
 
@@ -2094,10 +2094,17 @@ static struct iommu_domain *__iommu_domain_alloc(const struct iommu_ops *ops,
 	else if (ops->domain_alloc)
 		domain = ops->domain_alloc(alloc_type);
 	else
-		return NULL;
+		return ERR_PTR(-EOPNOTSUPP);
 
+	/*
+	 * Many domain_alloc ops now return ERR_PTR, make things easier for the
+	 * driver by accepting ERR_PTR from all domain_alloc ops instead of
+	 * having two rules.
+	 */
+	if (IS_ERR(domain))
+		return domain;
 	if (!domain)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	domain->type = type;
 	/*
@@ -2110,9 +2117,14 @@ static struct iommu_domain *__iommu_domain_alloc(const struct iommu_ops *ops,
 	if (!domain->ops)
 		domain->ops = ops->default_domain_ops;
 
-	if (iommu_is_dma_domain(domain) && iommu_get_dma_cookie(domain)) {
-		iommu_domain_free(domain);
-		domain = NULL;
+	if (iommu_is_dma_domain(domain)) {
+		int rc;
+
+		rc = iommu_get_dma_cookie(domain);
+		if (rc) {
+			iommu_domain_free(domain);
+			return ERR_PTR(rc);
+		}
 	}
 	return domain;
 }
@@ -2129,10 +2141,15 @@ __iommu_group_domain_alloc(struct iommu_group *group, unsigned int type)
 
 struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus)
 {
+	struct iommu_domain *domain;
+
 	if (bus == NULL || bus->iommu_ops == NULL)
 		return NULL;
-	return __iommu_domain_alloc(bus->iommu_ops, NULL,
+	domain = __iommu_domain_alloc(bus->iommu_ops, NULL,
 				    IOMMU_DOMAIN_UNMANAGED);
+	if (IS_ERR(domain))
+		return NULL;
+	return domain;
 }
 EXPORT_SYMBOL_GPL(iommu_domain_alloc);
 
@@ -3041,8 +3058,8 @@ static int iommu_setup_default_domain(struct iommu_group *group,
 		return -EINVAL;
 
 	dom = iommu_group_alloc_default_domain(group, req_type);
-	if (!dom)
-		return -ENODEV;
+	if (IS_ERR(dom))
+		return PTR_ERR(dom);
 
 	if (group->default_domain == dom)
 		return 0;
@@ -3243,21 +3260,23 @@ void iommu_device_unuse_default_domain(struct device *dev)
 
 static int __iommu_group_alloc_blocking_domain(struct iommu_group *group)
 {
+	struct iommu_domain *domain;
+
 	if (group->blocking_domain)
 		return 0;
 
-	group->blocking_domain =
-		__iommu_group_domain_alloc(group, IOMMU_DOMAIN_BLOCKED);
-	if (!group->blocking_domain) {
+	domain = __iommu_group_domain_alloc(group, IOMMU_DOMAIN_BLOCKED);
+	if (IS_ERR(domain)) {
 		/*
 		 * For drivers that do not yet understand IOMMU_DOMAIN_BLOCKED
 		 * create an empty domain instead.
 		 */
-		group->blocking_domain = __iommu_group_domain_alloc(
-			group, IOMMU_DOMAIN_UNMANAGED);
-		if (!group->blocking_domain)
-			return -EINVAL;
+		domain = __iommu_group_domain_alloc(group,
+						    IOMMU_DOMAIN_UNMANAGED);
+		if (IS_ERR(domain))
+			return PTR_ERR(domain);
 	}
+	group->blocking_domain = domain;
 	return 0;
 }
 
diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
index 59d3a07300d9..873630c111c1 100644
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -571,7 +571,7 @@ iommufd_device_auto_get_domain(struct iommufd_device *idev,
 			continue;
 		destroy_hwpt = (*do_attach)(idev, hwpt);
 		if (IS_ERR(destroy_hwpt)) {
-			iommufd_put_object(&hwpt->obj);
+			iommufd_put_object(idev->ictx, &hwpt->obj);
 			/*
 			 * -EINVAL means the domain is incompatible with the
 			 * device. Other error codes should propagate to
@@ -583,7 +583,7 @@ iommufd_device_auto_get_domain(struct iommufd_device *idev,
 			goto out_unlock;
 		}
 		*pt_id = hwpt->obj.id;
-		iommufd_put_object(&hwpt->obj);
+		iommufd_put_object(idev->ictx, &hwpt->obj);
 		goto out_unlock;
 	}
 
@@ -652,7 +652,7 @@ static int iommufd_device_change_pt(struct iommufd_device *idev, u32 *pt_id,
 		destroy_hwpt = ERR_PTR(-EINVAL);
 		goto out_put_pt_obj;
 	}
-	iommufd_put_object(pt_obj);
+	iommufd_put_object(idev->ictx, pt_obj);
 
 	/* This destruction has to be after we unlock everything */
 	if (destroy_hwpt)
@@ -660,7 +660,7 @@ static int iommufd_device_change_pt(struct iommufd_device *idev, u32 *pt_id,
 	return 0;
 
 out_put_pt_obj:
-	iommufd_put_object(pt_obj);
+	iommufd_put_object(idev->ictx, pt_obj);
 	return PTR_ERR(destroy_hwpt);
 }
 
@@ -792,7 +792,7 @@ static int iommufd_access_change_ioas_id(struct iommufd_access *access, u32 id)
 	if (IS_ERR(ioas))
 		return PTR_ERR(ioas);
 	rc = iommufd_access_change_ioas(access, ioas);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(access->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -941,7 +941,7 @@ void iommufd_access_notify_unmap(struct io_pagetable *iopt, unsigned long iova,
 
 		access->ops->unmap(access->data, iova, length);
 
-		iommufd_put_object(&access->obj);
+		iommufd_put_object(access->ictx, &access->obj);
 		xa_lock(&ioas->iopt.access_list);
 	}
 	xa_unlock(&ioas->iopt.access_list);
@@ -1243,6 +1243,6 @@ int iommufd_get_hw_info(struct iommufd_ucmd *ucmd)
 out_free:
 	kfree(data);
 out_put:
-	iommufd_put_object(&idev->obj);
+	iommufd_put_object(ucmd->ictx, &idev->obj);
 	return rc;
 }
diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index 2abbeafdbd22..cbb5df0a6c32 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -318,9 +318,9 @@ out_unlock:
 	if (ioas)
 		mutex_unlock(&ioas->mutex);
 out_put_pt:
-	iommufd_put_object(pt_obj);
+	iommufd_put_object(ucmd->ictx, pt_obj);
 out_put_idev:
-	iommufd_put_object(&idev->obj);
+	iommufd_put_object(ucmd->ictx, &idev->obj);
 	return rc;
 }
 
@@ -345,7 +345,7 @@ int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd)
 	rc = iopt_set_dirty_tracking(&ioas->iopt, hwpt_paging->common.domain,
 				     enable);
 
-	iommufd_put_object(&hwpt_paging->common.obj);
+	iommufd_put_object(ucmd->ictx, &hwpt_paging->common.obj);
 	return rc;
 }
 
@@ -368,6 +368,6 @@ int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd)
 	rc = iopt_read_and_clear_dirty_data(
 		&ioas->iopt, hwpt_paging->common.domain, cmd->flags, cmd);
 
-	iommufd_put_object(&hwpt_paging->common.obj);
+	iommufd_put_object(ucmd->ictx, &hwpt_paging->common.obj);
 	return rc;
 }
diff --git a/drivers/iommu/iommufd/ioas.c b/drivers/iommu/iommufd/ioas.c
index d5624577f79f..742248276548 100644
--- a/drivers/iommu/iommufd/ioas.c
+++ b/drivers/iommu/iommufd/ioas.c
@@ -105,7 +105,7 @@ int iommufd_ioas_iova_ranges(struct iommufd_ucmd *ucmd)
 		rc = -EMSGSIZE;
 out_put:
 	up_read(&ioas->iopt.iova_rwsem);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -175,7 +175,7 @@ out_free:
 		interval_tree_remove(node, &allowed_iova);
 		kfree(container_of(node, struct iopt_allowed, node));
 	}
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -228,7 +228,7 @@ int iommufd_ioas_map(struct iommufd_ucmd *ucmd)
 	cmd->iova = iova;
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 out_put:
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -258,7 +258,7 @@ int iommufd_ioas_copy(struct iommufd_ucmd *ucmd)
 		return PTR_ERR(src_ioas);
 	rc = iopt_get_pages(&src_ioas->iopt, cmd->src_iova, cmd->length,
 			    &pages_list);
-	iommufd_put_object(&src_ioas->obj);
+	iommufd_put_object(ucmd->ictx, &src_ioas->obj);
 	if (rc)
 		return rc;
 
@@ -279,7 +279,7 @@ int iommufd_ioas_copy(struct iommufd_ucmd *ucmd)
 	cmd->dst_iova = iova;
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 out_put_dst:
-	iommufd_put_object(&dst_ioas->obj);
+	iommufd_put_object(ucmd->ictx, &dst_ioas->obj);
 out_pages:
 	iopt_free_pages_list(&pages_list);
 	return rc;
@@ -315,7 +315,7 @@ int iommufd_ioas_unmap(struct iommufd_ucmd *ucmd)
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 
 out_put:
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -393,6 +393,6 @@ int iommufd_ioas_option(struct iommufd_ucmd *ucmd)
 		rc = -EOPNOTSUPP;
 	}
 
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index a74cfefffbc6..abae041e256f 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -21,6 +21,7 @@ struct iommufd_ctx {
 	struct file *file;
 	struct xarray objects;
 	struct xarray groups;
+	wait_queue_head_t destroy_wait;
 
 	u8 account_mode;
 	/* Compatibility with VFIO no iommu */
@@ -135,7 +136,7 @@ enum iommufd_object_type {
 
 /* Base struct for all objects with a userspace ID handle. */
 struct iommufd_object {
-	struct rw_semaphore destroy_rwsem;
+	refcount_t shortterm_users;
 	refcount_t users;
 	enum iommufd_object_type type;
 	unsigned int id;
@@ -143,10 +144,15 @@ struct iommufd_object {
 
 static inline bool iommufd_lock_obj(struct iommufd_object *obj)
 {
-	if (!down_read_trylock(&obj->destroy_rwsem))
+	if (!refcount_inc_not_zero(&obj->users))
 		return false;
-	if (!refcount_inc_not_zero(&obj->users)) {
-		up_read(&obj->destroy_rwsem);
+	if (!refcount_inc_not_zero(&obj->shortterm_users)) {
+		/*
+		 * If the caller doesn't already have a ref on obj this must be
+		 * called under the xa_lock. Otherwise the caller is holding a
+		 * ref on users. Thus it cannot be one before this decrement.
+		 */
+		refcount_dec(&obj->users);
 		return false;
 	}
 	return true;
@@ -154,10 +160,16 @@ static inline bool iommufd_lock_obj(struct iommufd_object *obj)
 
 struct iommufd_object *iommufd_get_object(struct iommufd_ctx *ictx, u32 id,
 					  enum iommufd_object_type type);
-static inline void iommufd_put_object(struct iommufd_object *obj)
+static inline void iommufd_put_object(struct iommufd_ctx *ictx,
+				      struct iommufd_object *obj)
 {
+	/*
+	 * Users first, then shortterm so that REMOVE_WAIT_SHORTTERM never sees
+	 * a spurious !0 users with a 0 shortterm_users.
+	 */
 	refcount_dec(&obj->users);
-	up_read(&obj->destroy_rwsem);
+	if (refcount_dec_and_test(&obj->shortterm_users))
+		wake_up_interruptible_all(&ictx->destroy_wait);
 }
 
 void iommufd_object_abort(struct iommufd_ctx *ictx, struct iommufd_object *obj);
@@ -165,17 +177,49 @@ void iommufd_object_abort_and_destroy(struct iommufd_ctx *ictx,
 				      struct iommufd_object *obj);
 void iommufd_object_finalize(struct iommufd_ctx *ictx,
 			     struct iommufd_object *obj);
-void __iommufd_object_destroy_user(struct iommufd_ctx *ictx,
-				   struct iommufd_object *obj, bool allow_fail);
+
+enum {
+	REMOVE_WAIT_SHORTTERM = 1,
+};
+int iommufd_object_remove(struct iommufd_ctx *ictx,
+			  struct iommufd_object *to_destroy, u32 id,
+			  unsigned int flags);
+
+/*
+ * The caller holds a users refcount and wants to destroy the object. At this
+ * point the caller has no shortterm_users reference and at least the xarray
+ * will be holding one.
+ */
 static inline void iommufd_object_destroy_user(struct iommufd_ctx *ictx,
 					       struct iommufd_object *obj)
 {
-	__iommufd_object_destroy_user(ictx, obj, false);
+	int ret;
+
+	ret = iommufd_object_remove(ictx, obj, obj->id, REMOVE_WAIT_SHORTTERM);
+
+	/*
+	 * If there is a bug and we couldn't destroy the object then we did put
+	 * back the caller's users refcount and will eventually try to free it
+	 * again during close.
+	 */
+	WARN_ON(ret);
 }
-static inline void iommufd_object_deref_user(struct iommufd_ctx *ictx,
-					     struct iommufd_object *obj)
+
+/*
+ * The HWPT allocated by autodomains is used in possibly many devices and
+ * is automatically destroyed when its refcount reaches zero.
+ *
+ * If userspace uses the HWPT manually, even for a short term, then it will
+ * disrupt this refcounting and the auto-free in the kernel will not work.
+ * Userspace that tries to use the automatically allocated HWPT must be careful
+ * to ensure that it is consistently destroyed, eg by not racing accesses
+ * and by not attaching an automatic HWPT to a device manually.
+ */
+static inline void
+iommufd_object_put_and_try_destroy(struct iommufd_ctx *ictx,
+				   struct iommufd_object *obj)
 {
-	__iommufd_object_destroy_user(ictx, obj, true);
+	iommufd_object_remove(ictx, obj, obj->id, 0);
 }
 
 struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx,
@@ -311,7 +355,7 @@ static inline void iommufd_hw_pagetable_put(struct iommufd_ctx *ictx,
 		lockdep_assert_not_held(&hwpt_paging->ioas->mutex);
 
 		if (hwpt_paging->auto_domain) {
-			iommufd_object_deref_user(ictx, &hwpt->obj);
+			iommufd_object_put_and_try_destroy(ictx, &hwpt->obj);
 			return;
 		}
 	}
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index 45b9d40773b1..c9091e46d208 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -33,7 +33,6 @@ struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx,
 					     size_t size,
 					     enum iommufd_object_type type)
 {
-	static struct lock_class_key obj_keys[IOMMUFD_OBJ_MAX];
 	struct iommufd_object *obj;
 	int rc;
 
@@ -41,15 +40,8 @@ struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx,
 	if (!obj)
 		return ERR_PTR(-ENOMEM);
 	obj->type = type;
-	/*
-	 * In most cases the destroy_rwsem is obtained with try so it doesn't
-	 * interact with lockdep, however on destroy we have to sleep. This
-	 * means if we have to destroy an object while holding a get on another
-	 * object it triggers lockdep. Using one locking class per object type
-	 * is a simple and reasonable way to avoid this.
-	 */
-	__init_rwsem(&obj->destroy_rwsem, "iommufd_object::destroy_rwsem",
-		     &obj_keys[type]);
+	/* Starts out bias'd by 1 until it is removed from the xarray */
+	refcount_set(&obj->shortterm_users, 1);
 	refcount_set(&obj->users, 1);
 
 	/*
@@ -129,92 +121,113 @@ struct iommufd_object *iommufd_get_object(struct iommufd_ctx *ictx, u32 id,
 	return obj;
 }
 
+static int iommufd_object_dec_wait_shortterm(struct iommufd_ctx *ictx,
+					     struct iommufd_object *to_destroy)
+{
+	if (refcount_dec_and_test(&to_destroy->shortterm_users))
+		return 0;
+
+	if (wait_event_timeout(ictx->destroy_wait,
+				refcount_read(&to_destroy->shortterm_users) ==
+					0,
+				msecs_to_jiffies(10000)))
+		return 0;
+
+	pr_crit("Time out waiting for iommufd object to become free\n");
+	refcount_inc(&to_destroy->shortterm_users);
+	return -EBUSY;
+}
+
 /*
  * Remove the given object id from the xarray if the only reference to the
- * object is held by the xarray. The caller must call ops destroy().
+ * object is held by the xarray.
  */
-static struct iommufd_object *iommufd_object_remove(struct iommufd_ctx *ictx,
-						    u32 id, bool extra_put)
+int iommufd_object_remove(struct iommufd_ctx *ictx,
+			  struct iommufd_object *to_destroy, u32 id,
+			  unsigned int flags)
 {
 	struct iommufd_object *obj;
 	XA_STATE(xas, &ictx->objects, id);
-
-	xa_lock(&ictx->objects);
-	obj = xas_load(&xas);
-	if (xa_is_zero(obj) || !obj) {
-		obj = ERR_PTR(-ENOENT);
-		goto out_xa;
-	}
+	bool zerod_shortterm = false;
+	int ret;
 
 	/*
-	 * If the caller is holding a ref on obj we put it here under the
-	 * spinlock.
+	 * The purpose of the shortterm_users is to ensure deterministic
+	 * destruction of objects used by external drivers and destroyed by this
+	 * function. Any temporary increment of the refcount must increment
+	 * shortterm_users, such as during ioctl execution.
 	 */
-	if (extra_put)
+	if (flags & REMOVE_WAIT_SHORTTERM) {
+		ret = iommufd_object_dec_wait_shortterm(ictx, to_destroy);
+		if (ret) {
+			/*
+			 * We have a bug. Put back the callers reference and
+			 * defer cleaning this object until close.
+			 */
+			refcount_dec(&to_destroy->users);
+			return ret;
+		}
+		zerod_shortterm = true;
+	}
+
+	xa_lock(&ictx->objects);
+	obj = xas_load(&xas);
+	if (to_destroy) {
+		/*
+		 * If the caller is holding a ref on obj we put it here under
+		 * the spinlock.
+		 */
 		refcount_dec(&obj->users);
 
+		if (WARN_ON(obj != to_destroy)) {
+			ret = -ENOENT;
+			goto err_xa;
+		}
+	} else if (xa_is_zero(obj) || !obj) {
+		ret = -ENOENT;
+		goto err_xa;
+	}
+
 	if (!refcount_dec_if_one(&obj->users)) {
-		obj = ERR_PTR(-EBUSY);
-		goto out_xa;
+		ret = -EBUSY;
+		goto err_xa;
 	}
 
 	xas_store(&xas, NULL);
 	if (ictx->vfio_ioas == container_of(obj, struct iommufd_ioas, obj))
 		ictx->vfio_ioas = NULL;
-
-out_xa:
 	xa_unlock(&ictx->objects);
 
-	/* The returned object reference count is zero */
-	return obj;
-}
-
-/*
- * The caller holds a users refcount and wants to destroy the object. Returns
- * true if the object was destroyed. In all cases the caller no longer has a
- * reference on obj.
- */
-void __iommufd_object_destroy_user(struct iommufd_ctx *ictx,
-				   struct iommufd_object *obj, bool allow_fail)
-{
-	struct iommufd_object *ret;
-
 	/*
-	 * The purpose of the destroy_rwsem is to ensure deterministic
-	 * destruction of objects used by external drivers and destroyed by this
-	 * function. Any temporary increment of the refcount must hold the read
-	 * side of this, such as during ioctl execution.
-	 */
-	down_write(&obj->destroy_rwsem);
-	ret = iommufd_object_remove(ictx, obj->id, true);
-	up_write(&obj->destroy_rwsem);
-
-	if (allow_fail && IS_ERR(ret))
-		return;
-
-	/*
-	 * If there is a bug and we couldn't destroy the object then we did put
-	 * back the caller's refcount and will eventually try to free it again
-	 * during close.
+	 * Since users is zero any positive users_shortterm must be racing
+	 * iommufd_put_object(), or we have a bug.
 	 */
-	if (WARN_ON(IS_ERR(ret)))
-		return;
+	if (!zerod_shortterm) {
+		ret = iommufd_object_dec_wait_shortterm(ictx, obj);
+		if (WARN_ON(ret))
+			return ret;
+	}
 
 	iommufd_object_ops[obj->type].destroy(obj);
 	kfree(obj);
+	return 0;
+
+err_xa:
+	if (zerod_shortterm) {
+		/* Restore the xarray owned reference */
+		refcount_set(&obj->shortterm_users, 1);
+	}
+	xa_unlock(&ictx->objects);
+
+	/* The returned object reference count is zero */
+	return ret;
 }
 
 static int iommufd_destroy(struct iommufd_ucmd *ucmd)
 {
 	struct iommu_destroy *cmd = ucmd->cmd;
-	struct iommufd_object *obj;
 
-	obj = iommufd_object_remove(ucmd->ictx, cmd->id, false);
-	if (IS_ERR(obj))
-		return PTR_ERR(obj);
-	iommufd_object_ops[obj->type].destroy(obj);
-	kfree(obj);
-	return 0;
+	return iommufd_object_remove(ucmd->ictx, NULL, cmd->id, 0);
 }
 
 static int iommufd_fops_open(struct inode *inode, struct file *filp)
@@ -238,6 +251,7 @@ static int iommufd_fops_open(struct inode *inode, struct file *filp)
 	xa_init_flags(&ictx->objects, XA_FLAGS_ALLOC1 | XA_FLAGS_ACCOUNT);
 	xa_init(&ictx->groups);
 	ictx->file = filp;
+	init_waitqueue_head(&ictx->destroy_wait);
 	filp->private_data = ictx;
 	return 0;
 }
diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
index 5d93434003d8..022ef8f55088 100644
--- a/drivers/iommu/iommufd/selftest.c
+++ b/drivers/iommu/iommufd/selftest.c
@@ -86,7 +86,7 @@ void iommufd_test_syz_conv_iova_id(struct iommufd_ucmd *ucmd,
 	if (IS_ERR(ioas))
 		return;
 	*iova = iommufd_test_syz_conv_iova(&ioas->iopt, iova);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 }
 
 struct mock_iommu_domain {
@@ -500,7 +500,7 @@ get_md_pagetable(struct iommufd_ucmd *ucmd, u32 mockpt_id,
 		return hwpt;
 	if (hwpt->domain->type != IOMMU_DOMAIN_UNMANAGED ||
 	    hwpt->domain->ops != mock_ops.default_domain_ops) {
-		iommufd_put_object(&hwpt->obj);
+		iommufd_put_object(ucmd->ictx, &hwpt->obj);
 		return ERR_PTR(-EINVAL);
 	}
 	*mock = container_of(hwpt->domain, struct mock_iommu_domain, domain);
@@ -518,7 +518,7 @@ get_md_pagetable_nested(struct iommufd_ucmd *ucmd, u32 mockpt_id,
 		return hwpt;
 	if (hwpt->domain->type != IOMMU_DOMAIN_NESTED ||
 	    hwpt->domain->ops != &domain_nested_ops) {
-		iommufd_put_object(&hwpt->obj);
+		iommufd_put_object(ucmd->ictx, &hwpt->obj);
 		return ERR_PTR(-EINVAL);
 	}
 	*mock_nested = container_of(hwpt->domain,
@@ -681,7 +681,7 @@ static int iommufd_test_mock_domain_replace(struct iommufd_ucmd *ucmd,
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 
 out_dev_obj:
-	iommufd_put_object(dev_obj);
+	iommufd_put_object(ucmd->ictx, dev_obj);
 	return rc;
 }
 
@@ -699,7 +699,7 @@ static int iommufd_test_add_reserved(struct iommufd_ucmd *ucmd,
 	down_write(&ioas->iopt.iova_rwsem);
 	rc = iopt_reserve_iova(&ioas->iopt, start, start + length - 1, NULL);
 	up_write(&ioas->iopt.iova_rwsem);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -754,7 +754,7 @@ static int iommufd_test_md_check_pa(struct iommufd_ucmd *ucmd,
 	rc = 0;
 
 out_put:
-	iommufd_put_object(&hwpt->obj);
+	iommufd_put_object(ucmd->ictx, &hwpt->obj);
 	return rc;
 }
 
@@ -1233,7 +1233,7 @@ static int iommufd_test_dirty(struct iommufd_ucmd *ucmd, unsigned int mockpt_id,
 out_free:
 	kvfree(tmp);
 out_put:
-	iommufd_put_object(&hwpt->obj);
+	iommufd_put_object(ucmd->ictx, &hwpt->obj);
 	return rc;
 }
 
diff --git a/drivers/iommu/iommufd/vfio_compat.c b/drivers/iommu/iommufd/vfio_compat.c
index 538fbf76354d..a3ad5f0b6c59 100644
--- a/drivers/iommu/iommufd/vfio_compat.c
+++ b/drivers/iommu/iommufd/vfio_compat.c
@@ -41,7 +41,7 @@ int iommufd_vfio_compat_ioas_get_id(struct iommufd_ctx *ictx, u32 *out_ioas_id)
 	if (IS_ERR(ioas))
 		return PTR_ERR(ioas);
 	*out_ioas_id = ioas->obj.id;
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ictx, &ioas->obj);
 	return 0;
 }
 EXPORT_SYMBOL_NS_GPL(iommufd_vfio_compat_ioas_get_id, IOMMUFD_VFIO);
@@ -98,7 +98,7 @@ int iommufd_vfio_compat_ioas_create(struct iommufd_ctx *ictx)
 
 	if (ictx->vfio_ioas && iommufd_lock_obj(&ictx->vfio_ioas->obj)) {
 		ret = 0;
-		iommufd_put_object(&ictx->vfio_ioas->obj);
+		iommufd_put_object(ictx, &ictx->vfio_ioas->obj);
 		goto out_abort;
 	}
 	ictx->vfio_ioas = ioas;
@@ -133,7 +133,7 @@ int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd)
 		if (IS_ERR(ioas))
 			return PTR_ERR(ioas);
 		cmd->ioas_id = ioas->obj.id;
-		iommufd_put_object(&ioas->obj);
+		iommufd_put_object(ucmd->ictx, &ioas->obj);
 		return iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 
 	case IOMMU_VFIO_IOAS_SET:
@@ -143,7 +143,7 @@ int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd)
 		xa_lock(&ucmd->ictx->objects);
 		ucmd->ictx->vfio_ioas = ioas;
 		xa_unlock(&ucmd->ictx->objects);
-		iommufd_put_object(&ioas->obj);
+		iommufd_put_object(ucmd->ictx, &ioas->obj);
 		return 0;
 
 	case IOMMU_VFIO_IOAS_CLEAR:
@@ -190,7 +190,7 @@ static int iommufd_vfio_map_dma(struct iommufd_ctx *ictx, unsigned int cmd,
 	iova = map.iova;
 	rc = iopt_map_user_pages(ictx, &ioas->iopt, &iova, u64_to_user_ptr(map.vaddr),
 				 map.size, iommu_prot, 0);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ictx, &ioas->obj);
 	return rc;
 }
 
@@ -249,7 +249,7 @@ static int iommufd_vfio_unmap_dma(struct iommufd_ctx *ictx, unsigned int cmd,
 		rc = -EFAULT;
 
 err_put:
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ictx, &ioas->obj);
 	return rc;
 }
 
@@ -272,7 +272,7 @@ static int iommufd_vfio_cc_iommu(struct iommufd_ctx *ictx)
 	}
 	mutex_unlock(&ioas->mutex);
 
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ictx, &ioas->obj);
 	return rc;
 }
 
@@ -349,7 +349,7 @@ static int iommufd_vfio_set_iommu(struct iommufd_ctx *ictx, unsigned long type)
 	 */
 	if (type == VFIO_TYPE1_IOMMU)
 		rc = iopt_disable_large_pages(&ioas->iopt);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ictx, &ioas->obj);
 	return rc;
 }
 
@@ -511,7 +511,7 @@ static int iommufd_vfio_iommu_get_info(struct iommufd_ctx *ictx,
 
 out_put:
 	up_read(&ioas->iopt.iova_rwsem);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ictx, &ioas->obj);
 	return rc;
 }
 
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 157b286e36bf..35ba090f3b5e 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -112,16 +112,20 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 					   const u32 *id)
 {
 	const struct iommu_ops *ops = NULL;
-	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct iommu_fwspec *fwspec;
 	int err = NO_IOMMU;
 
 	if (!master_np)
 		return NULL;
 
+	/* Serialise to make dev->iommu stable under our potential fwspec */
+	mutex_lock(&iommu_probe_device_lock);
+	fwspec = dev_iommu_fwspec_get(dev);
 	if (fwspec) {
-		if (fwspec->ops)
+		if (fwspec->ops) {
+			mutex_unlock(&iommu_probe_device_lock);
 			return fwspec->ops;
-
+		}
 		/* In the deferred case, start again from scratch */
 		iommu_fwspec_free(dev);
 	}
@@ -155,6 +159,8 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 		fwspec = dev_iommu_fwspec_get(dev);
 		ops    = fwspec->ops;
 	}
+	mutex_unlock(&iommu_probe_device_lock);
+
 	/*
 	 * If we have reason to believe the IOMMU driver missed the initial
 	 * probe for dev, replay it to get things in order.
@@ -191,7 +197,7 @@ iommu_resv_region_get_type(struct device *dev,
 	if (start == phys->start && end == phys->end)
 		return IOMMU_RESV_DIRECT;
 
-	dev_warn(dev, "treating non-direct mapping [%pr] -> [%pap-%pap] as reservation\n", &phys,
+	dev_warn(dev, "treating non-direct mapping [%pr] -> [%pap-%pap] as reservation\n", phys,
 		 &start, &end);
 	return IOMMU_RESV_RESERVED;
 }
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index a8c89df1a997..d097001c1e3e 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -2379,12 +2379,12 @@ retry_baser:
 		break;
 	}
 
+	if (!shr)
+		gic_flush_dcache_to_poc(base, PAGE_ORDER_TO_SIZE(order));
+
 	its_write_baser(its, baser, val);
 	tmp = baser->val;
 
-	if (its->flags & ITS_FLAGS_FORCE_NON_SHAREABLE)
-		tmp &= ~GITS_BASER_SHAREABILITY_MASK;
-
 	if ((val ^ tmp) & GITS_BASER_SHAREABILITY_MASK) {
 		/*
 		 * Shareability didn't stick. Just use
@@ -2394,10 +2394,9 @@ retry_baser:
 		 * non-cacheable as well.
 		 */
 		shr = tmp & GITS_BASER_SHAREABILITY_MASK;
-		if (!shr) {
+		if (!shr)
 			cache = GITS_BASER_nC;
-			gic_flush_dcache_to_poc(base, PAGE_ORDER_TO_SIZE(order));
-		}
+
 		goto retry_baser;
 	}
 
@@ -2466,8 +2465,8 @@ static bool its_parse_indirect_baser(struct its_node *its,
 	 * feature is not supported by hardware.
 	 */
 	new_order = max_t(u32, get_order(esz << ids), new_order);
-	if (new_order > MAX_ORDER) {
-		new_order = MAX_ORDER;
+	if (new_order > MAX_PAGE_ORDER) {
+		new_order = MAX_PAGE_ORDER;
 		ids = ilog2(PAGE_ORDER_TO_SIZE(new_order) / (int)esz);
 		pr_warn("ITS@%pa: %s Table too large, reduce ids %llu->%u\n",
 			&its->phys_base, its_base_type_string[type],
@@ -2609,6 +2608,11 @@ static int its_alloc_tables(struct its_node *its)
 		/* erratum 24313: ignore memory access type */
 		cache = GITS_BASER_nCnB;
 
+	if (its->flags & ITS_FLAGS_FORCE_NON_SHAREABLE) {
+		cache = GITS_BASER_nC;
+		shr = 0;
+	}
+
 	for (i = 0; i < GITS_BASER_NR_REGS; i++) {
 		struct its_baser *baser = its->tables + i;
 		u64 val = its_read_baser(its, baser);
diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c
index 94d56a03b175..ca32ac19d284 100644
--- a/drivers/irqchip/irq-gic-v4.c
+++ b/drivers/irqchip/irq-gic-v4.c
@@ -8,6 +8,7 @@
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
 #include <linux/msi.h>
+#include <linux/pid.h>
 #include <linux/sched.h>
 
 #include <linux/irqchip/arm-gic-v4.h>
diff --git a/drivers/irqchip/irq-qcom-mpm.c b/drivers/irqchip/irq-qcom-mpm.c
index 7124565234a5..cda5838d2232 100644
--- a/drivers/irqchip/irq-qcom-mpm.c
+++ b/drivers/irqchip/irq-qcom-mpm.c
@@ -14,6 +14,7 @@
 #include <linux/mailbox_client.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/pm_domain.h>
@@ -322,8 +323,10 @@ static int qcom_mpm_init(struct device_node *np, struct device_node *parent)
 	struct device *dev = &pdev->dev;
 	struct irq_domain *parent_domain;
 	struct generic_pm_domain *genpd;
+	struct device_node *msgram_np;
 	struct qcom_mpm_priv *priv;
 	unsigned int pin_cnt;
+	struct resource res;
 	int i, irq;
 	int ret;
 
@@ -374,9 +377,26 @@ static int qcom_mpm_init(struct device_node *np, struct device_node *parent)
 
 	raw_spin_lock_init(&priv->lock);
 
-	priv->base = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(priv->base))
-		return PTR_ERR(priv->base);
+	/* If we have a handle to an RPM message ram partition, use it. */
+	msgram_np = of_parse_phandle(np, "qcom,rpm-msg-ram", 0);
+	if (msgram_np) {
+		ret = of_address_to_resource(msgram_np, 0, &res);
+		if (ret) {
+			of_node_put(msgram_np);
+			return ret;
+		}
+
+		/* Don't use devm_ioremap_resource, as we're accessing a shared region. */
+		priv->base = devm_ioremap(dev, res.start, resource_size(&res));
+		of_node_put(msgram_np);
+		if (IS_ERR(priv->base))
+			return PTR_ERR(priv->base);
+	} else {
+		/* Otherwise, fall back to simple MMIO. */
+		priv->base = devm_platform_ioremap_resource(pdev, 0);
+		if (IS_ERR(priv->base))
+			return PTR_ERR(priv->base);
+	}
 
 	for (i = 0; i < priv->reg_stride; i++) {
 		qcom_mpm_write(priv, MPM_REG_ENABLE, i, 0);
diff --git a/drivers/irqchip/irq-renesas-rzg2l.c b/drivers/irqchip/irq-renesas-rzg2l.c
index fe8d516f3614..9494fc26259c 100644
--- a/drivers/irqchip/irq-renesas-rzg2l.c
+++ b/drivers/irqchip/irq-renesas-rzg2l.c
@@ -18,6 +18,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/reset.h>
 #include <linux/spinlock.h>
+#include <linux/syscore_ops.h>
 
 #define IRQC_IRQ_START			1
 #define IRQC_IRQ_COUNT			8
@@ -28,8 +29,7 @@
 #define ISCR				0x10
 #define IITSR				0x14
 #define TSCR				0x20
-#define TITSR0				0x24
-#define TITSR1				0x28
+#define TITSR(n)			(0x24 + (n) * 4)
 #define TITSR0_MAX_INT			16
 #define TITSEL_WIDTH			0x2
 #define TSSR(n)				(0x30 + ((n) * 4))
@@ -53,15 +53,33 @@
 #define IITSR_IITSEL_EDGE_BOTH		3
 #define IITSR_IITSEL_MASK(n)		IITSR_IITSEL((n), 3)
 
-#define TINT_EXTRACT_HWIRQ(x)           FIELD_GET(GENMASK(15, 0), (x))
-#define TINT_EXTRACT_GPIOINT(x)         FIELD_GET(GENMASK(31, 16), (x))
+#define TINT_EXTRACT_HWIRQ(x)		FIELD_GET(GENMASK(15, 0), (x))
+#define TINT_EXTRACT_GPIOINT(x)		FIELD_GET(GENMASK(31, 16), (x))
 
-struct rzg2l_irqc_priv {
-	void __iomem *base;
-	struct irq_fwspec fwspec[IRQC_NUM_IRQ];
-	raw_spinlock_t lock;
+/**
+ * struct rzg2l_irqc_reg_cache - registers cache (necessary for suspend/resume)
+ * @iitsr: IITSR register
+ * @titsr: TITSR registers
+ */
+struct rzg2l_irqc_reg_cache {
+	u32	iitsr;
+	u32	titsr[2];
 };
 
+/**
+ * struct rzg2l_irqc_priv - IRQ controller private data structure
+ * @base:	Controller's base address
+ * @fwspec:	IRQ firmware specific data
+ * @lock:	Lock to serialize access to hardware registers
+ * @cache:	Registers cache for suspend/resume
+ */
+static struct rzg2l_irqc_priv {
+	void __iomem			*base;
+	struct irq_fwspec		fwspec[IRQC_NUM_IRQ];
+	raw_spinlock_t			lock;
+	struct rzg2l_irqc_reg_cache	cache;
+} *rzg2l_irqc_data;
+
 static struct rzg2l_irqc_priv *irq_data_to_priv(struct irq_data *data)
 {
 	return data->domain->host_data;
@@ -72,11 +90,17 @@ static void rzg2l_irq_eoi(struct irq_data *d)
 	unsigned int hw_irq = irqd_to_hwirq(d) - IRQC_IRQ_START;
 	struct rzg2l_irqc_priv *priv = irq_data_to_priv(d);
 	u32 bit = BIT(hw_irq);
-	u32 reg;
+	u32 iitsr, iscr;
 
-	reg = readl_relaxed(priv->base + ISCR);
-	if (reg & bit)
-		writel_relaxed(reg & ~bit, priv->base + ISCR);
+	iscr = readl_relaxed(priv->base + ISCR);
+	iitsr = readl_relaxed(priv->base + IITSR);
+
+	/*
+	 * ISCR can only be cleared if the type is falling-edge, rising-edge or
+	 * falling/rising-edge.
+	 */
+	if ((iscr & bit) && (iitsr & IITSR_IITSEL_MASK(hw_irq)))
+		writel_relaxed(iscr & ~bit, priv->base + ISCR);
 }
 
 static void rzg2l_tint_eoi(struct irq_data *d)
@@ -188,8 +212,7 @@ static int rzg2l_tint_set_edge(struct irq_data *d, unsigned int type)
 	struct rzg2l_irqc_priv *priv = irq_data_to_priv(d);
 	unsigned int hwirq = irqd_to_hwirq(d);
 	u32 titseln = hwirq - IRQC_TINT_START;
-	u32 offset;
-	u8 sense;
+	u8 index, sense;
 	u32 reg;
 
 	switch (type & IRQ_TYPE_SENSE_MASK) {
@@ -205,17 +228,17 @@ static int rzg2l_tint_set_edge(struct irq_data *d, unsigned int type)
 		return -EINVAL;
 	}
 
-	offset = TITSR0;
+	index = 0;
 	if (titseln >= TITSR0_MAX_INT) {
 		titseln -= TITSR0_MAX_INT;
-		offset = TITSR1;
+		index = 1;
 	}
 
 	raw_spin_lock(&priv->lock);
-	reg = readl_relaxed(priv->base + offset);
+	reg = readl_relaxed(priv->base + TITSR(index));
 	reg &= ~(IRQ_MASK << (titseln * TITSEL_WIDTH));
 	reg |= sense << (titseln * TITSEL_WIDTH);
-	writel_relaxed(reg, priv->base + offset);
+	writel_relaxed(reg, priv->base + TITSR(index));
 	raw_spin_unlock(&priv->lock);
 
 	return 0;
@@ -236,6 +259,38 @@ static int rzg2l_irqc_set_type(struct irq_data *d, unsigned int type)
 	return irq_chip_set_type_parent(d, IRQ_TYPE_LEVEL_HIGH);
 }
 
+static int rzg2l_irqc_irq_suspend(void)
+{
+	struct rzg2l_irqc_reg_cache *cache = &rzg2l_irqc_data->cache;
+	void __iomem *base = rzg2l_irqc_data->base;
+
+	cache->iitsr = readl_relaxed(base + IITSR);
+	for (u8 i = 0; i < 2; i++)
+		cache->titsr[i] = readl_relaxed(base + TITSR(i));
+
+	return 0;
+}
+
+static void rzg2l_irqc_irq_resume(void)
+{
+	struct rzg2l_irqc_reg_cache *cache = &rzg2l_irqc_data->cache;
+	void __iomem *base = rzg2l_irqc_data->base;
+
+	/*
+	 * Restore only interrupt type. TSSRx will be restored at the
+	 * request of pin controller to avoid spurious interrupts due
+	 * to invalid PIN states.
+	 */
+	for (u8 i = 0; i < 2; i++)
+		writel_relaxed(cache->titsr[i], base + TITSR(i));
+	writel_relaxed(cache->iitsr, base + IITSR);
+}
+
+static struct syscore_ops rzg2l_irqc_syscore_ops = {
+	.suspend	= rzg2l_irqc_irq_suspend,
+	.resume		= rzg2l_irqc_irq_resume,
+};
+
 static const struct irq_chip irqc_chip = {
 	.name			= "rzg2l-irqc",
 	.irq_eoi		= rzg2l_irqc_eoi,
@@ -321,7 +376,6 @@ static int rzg2l_irqc_init(struct device_node *node, struct device_node *parent)
 	struct irq_domain *irq_domain, *parent_domain;
 	struct platform_device *pdev;
 	struct reset_control *resetn;
-	struct rzg2l_irqc_priv *priv;
 	int ret;
 
 	pdev = of_find_device_by_node(node);
@@ -334,15 +388,15 @@ static int rzg2l_irqc_init(struct device_node *node, struct device_node *parent)
 		return -ENODEV;
 	}
 
-	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
-	if (!priv)
+	rzg2l_irqc_data = devm_kzalloc(&pdev->dev, sizeof(*rzg2l_irqc_data), GFP_KERNEL);
+	if (!rzg2l_irqc_data)
 		return -ENOMEM;
 
-	priv->base = devm_of_iomap(&pdev->dev, pdev->dev.of_node, 0, NULL);
-	if (IS_ERR(priv->base))
-		return PTR_ERR(priv->base);
+	rzg2l_irqc_data->base = devm_of_iomap(&pdev->dev, pdev->dev.of_node, 0, NULL);
+	if (IS_ERR(rzg2l_irqc_data->base))
+		return PTR_ERR(rzg2l_irqc_data->base);
 
-	ret = rzg2l_irqc_parse_interrupts(priv, node);
+	ret = rzg2l_irqc_parse_interrupts(rzg2l_irqc_data, node);
 	if (ret) {
 		dev_err(&pdev->dev, "cannot parse interrupts: %d\n", ret);
 		return ret;
@@ -365,17 +419,19 @@ static int rzg2l_irqc_init(struct device_node *node, struct device_node *parent)
 		goto pm_disable;
 	}
 
-	raw_spin_lock_init(&priv->lock);
+	raw_spin_lock_init(&rzg2l_irqc_data->lock);
 
 	irq_domain = irq_domain_add_hierarchy(parent_domain, 0, IRQC_NUM_IRQ,
 					      node, &rzg2l_irqc_domain_ops,
-					      priv);
+					      rzg2l_irqc_data);
 	if (!irq_domain) {
 		dev_err(&pdev->dev, "failed to add irq domain\n");
 		ret = -ENOMEM;
 		goto pm_put;
 	}
 
+	register_syscore_ops(&rzg2l_irqc_syscore_ops);
+
 	return 0;
 
 pm_put:
diff --git a/drivers/irqchip/irq-xtensa-pic.c b/drivers/irqchip/irq-xtensa-pic.c
index 0c18d1f1e264..f9d6fce4da33 100644
--- a/drivers/irqchip/irq-xtensa-pic.c
+++ b/drivers/irqchip/irq-xtensa-pic.c
@@ -12,6 +12,7 @@
  * Kevin Chea
  */
 
+#include <linux/bits.h>
 #include <linux/interrupt.h>
 #include <linux/irqdomain.h>
 #include <linux/irq.h>
@@ -19,8 +20,6 @@
 #include <linux/irqchip/xtensa-pic.h>
 #include <linux/of.h>
 
-unsigned int cached_irq_mask;
-
 /*
  * Device Tree IRQ specifier translation function which works with one or
  * two cell bindings. First cell value maps directly to the hwirq number.
@@ -44,34 +43,30 @@ static const struct irq_domain_ops xtensa_irq_domain_ops = {
 
 static void xtensa_irq_mask(struct irq_data *d)
 {
-	cached_irq_mask &= ~(1 << d->hwirq);
-	xtensa_set_sr(cached_irq_mask, intenable);
-}
+	u32 irq_mask;
 
-static void xtensa_irq_unmask(struct irq_data *d)
-{
-	cached_irq_mask |= 1 << d->hwirq;
-	xtensa_set_sr(cached_irq_mask, intenable);
+	irq_mask = xtensa_get_sr(intenable);
+	irq_mask &= ~BIT(d->hwirq);
+	xtensa_set_sr(irq_mask, intenable);
 }
 
-static void xtensa_irq_enable(struct irq_data *d)
+static void xtensa_irq_unmask(struct irq_data *d)
 {
-	xtensa_irq_unmask(d);
-}
+	u32 irq_mask;
 
-static void xtensa_irq_disable(struct irq_data *d)
-{
-	xtensa_irq_mask(d);
+	irq_mask = xtensa_get_sr(intenable);
+	irq_mask |= BIT(d->hwirq);
+	xtensa_set_sr(irq_mask, intenable);
 }
 
 static void xtensa_irq_ack(struct irq_data *d)
 {
-	xtensa_set_sr(1 << d->hwirq, intclear);
+	xtensa_set_sr(BIT(d->hwirq), intclear);
 }
 
 static int xtensa_irq_retrigger(struct irq_data *d)
 {
-	unsigned int mask = 1u << d->hwirq;
+	unsigned int mask = BIT(d->hwirq);
 
 	if (WARN_ON(mask & ~XCHAL_INTTYPE_MASK_SOFTWARE))
 		return 0;
@@ -81,8 +76,6 @@ static int xtensa_irq_retrigger(struct irq_data *d)
 
 static struct irq_chip xtensa_irq_chip = {
 	.name		= "xtensa",
-	.irq_enable	= xtensa_irq_enable,
-	.irq_disable	= xtensa_irq_disable,
 	.irq_mask	= xtensa_irq_mask,
 	.irq_unmask	= xtensa_irq_unmask,
 	.irq_ack	= xtensa_irq_ack,
diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index 974b84f6bd6a..ba1be15cfd8e 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -75,19 +75,6 @@ static ssize_t max_brightness_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(max_brightness);
 
-static ssize_t color_show(struct device *dev,
-		struct device_attribute *attr, char *buf)
-{
-	const char *color_text = "invalid";
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-
-	if (led_cdev->color < LED_COLOR_ID_MAX)
-		color_text = led_colors[led_cdev->color];
-
-	return sysfs_emit(buf, "%s\n", color_text);
-}
-static DEVICE_ATTR_RO(color);
-
 #ifdef CONFIG_LEDS_TRIGGERS
 static BIN_ATTR(trigger, 0644, led_trigger_read, led_trigger_write, 0);
 static struct bin_attribute *led_trigger_bin_attrs[] = {
@@ -102,7 +89,6 @@ static const struct attribute_group led_trigger_group = {
 static struct attribute *led_class_attrs[] = {
 	&dev_attr_brightness.attr,
 	&dev_attr_max_brightness.attr,
-	&dev_attr_color.attr,
 	NULL,
 };
 
diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c
index e358e77e4b38..d76214fa9ad8 100644
--- a/drivers/leds/trigger/ledtrig-netdev.c
+++ b/drivers/leds/trigger/ledtrig-netdev.c
@@ -226,6 +226,11 @@ static int set_device_name(struct led_netdev_data *trigger_data,
 
 	cancel_delayed_work_sync(&trigger_data->work);
 
+	/*
+	 * Take RTNL lock before trigger_data lock to prevent potential
+	 * deadlock with netdev notifier registration.
+	 */
+	rtnl_lock();
 	mutex_lock(&trigger_data->lock);
 
 	if (trigger_data->net_dev) {
@@ -245,16 +250,14 @@ static int set_device_name(struct led_netdev_data *trigger_data,
 	trigger_data->carrier_link_up = false;
 	trigger_data->link_speed = SPEED_UNKNOWN;
 	trigger_data->duplex = DUPLEX_UNKNOWN;
-	if (trigger_data->net_dev != NULL) {
-		rtnl_lock();
+	if (trigger_data->net_dev)
 		get_device_state(trigger_data);
-		rtnl_unlock();
-	}
 
 	trigger_data->last_activity = 0;
 
 	set_baseline_state(trigger_data);
 	mutex_unlock(&trigger_data->lock);
+	rtnl_unlock();
 
 	return 0;
 }
diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig
index bc2e265cb02d..42940108a187 100644
--- a/drivers/mailbox/Kconfig
+++ b/drivers/mailbox/Kconfig
@@ -8,18 +8,6 @@ menuconfig MAILBOX
 
 if MAILBOX
 
-config APPLE_MAILBOX
-	tristate "Apple Mailbox driver"
-	depends on ARCH_APPLE || (ARM64 && COMPILE_TEST)
-	default ARCH_APPLE
-	help
-	  Apple SoCs have various co-processors required for certain
-	  peripherals to work (NVMe, display controller, etc.). This
-	  driver adds support for the mailbox controller used to
-	  communicate with those.
-
-	  Say Y here if you have a Apple SoC.
-
 config ARM_MHU
 	tristate "ARM MHU Mailbox"
 	depends on ARM_AMBA
diff --git a/drivers/mailbox/Makefile b/drivers/mailbox/Makefile
index fc9376117111..18793e6caa2f 100644
--- a/drivers/mailbox/Makefile
+++ b/drivers/mailbox/Makefile
@@ -60,5 +60,3 @@ obj-$(CONFIG_SUN6I_MSGBOX)	+= sun6i-msgbox.o
 obj-$(CONFIG_SPRD_MBOX)		+= sprd-mailbox.o
 
 obj-$(CONFIG_QCOM_IPCC)		+= qcom-ipcc.o
-
-obj-$(CONFIG_APPLE_MAILBOX)	+= apple-mailbox.o
diff --git a/drivers/mailbox/apple-mailbox.c b/drivers/mailbox/apple-mailbox.c
deleted file mode 100644
index 2a3e8d8ff8b5..000000000000
--- a/drivers/mailbox/apple-mailbox.c
+++ /dev/null
@@ -1,441 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only OR MIT
-/*
- * Apple mailbox driver
- *
- * Copyright (C) 2021 The Asahi Linux Contributors
- *
- * This driver adds support for two mailbox variants (called ASC and M3 by
- * Apple) found in Apple SoCs such as the M1. It consists of two FIFOs used to
- * exchange 64+32 bit messages between the main CPU and a co-processor.
- * Various coprocessors implement different IPC protocols based on these simple
- * messages and shared memory buffers.
- *
- * Both the main CPU and the co-processor see the same set of registers but
- * the first FIFO (A2I) is always used to transfer messages from the application
- * processor (us) to the I/O processor and the second one (I2A) for the
- * other direction.
- */
-
-#include <linux/apple-mailbox.h>
-#include <linux/delay.h>
-#include <linux/device.h>
-#include <linux/gfp.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/mailbox_controller.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/platform_device.h>
-#include <linux/spinlock.h>
-#include <linux/types.h>
-
-#define APPLE_ASC_MBOX_CONTROL_FULL  BIT(16)
-#define APPLE_ASC_MBOX_CONTROL_EMPTY BIT(17)
-
-#define APPLE_ASC_MBOX_A2I_CONTROL 0x110
-#define APPLE_ASC_MBOX_A2I_SEND0   0x800
-#define APPLE_ASC_MBOX_A2I_SEND1   0x808
-#define APPLE_ASC_MBOX_A2I_RECV0   0x810
-#define APPLE_ASC_MBOX_A2I_RECV1   0x818
-
-#define APPLE_ASC_MBOX_I2A_CONTROL 0x114
-#define APPLE_ASC_MBOX_I2A_SEND0   0x820
-#define APPLE_ASC_MBOX_I2A_SEND1   0x828
-#define APPLE_ASC_MBOX_I2A_RECV0   0x830
-#define APPLE_ASC_MBOX_I2A_RECV1   0x838
-
-#define APPLE_M3_MBOX_CONTROL_FULL  BIT(16)
-#define APPLE_M3_MBOX_CONTROL_EMPTY BIT(17)
-
-#define APPLE_M3_MBOX_A2I_CONTROL 0x50
-#define APPLE_M3_MBOX_A2I_SEND0	  0x60
-#define APPLE_M3_MBOX_A2I_SEND1	  0x68
-#define APPLE_M3_MBOX_A2I_RECV0	  0x70
-#define APPLE_M3_MBOX_A2I_RECV1	  0x78
-
-#define APPLE_M3_MBOX_I2A_CONTROL 0x80
-#define APPLE_M3_MBOX_I2A_SEND0	  0x90
-#define APPLE_M3_MBOX_I2A_SEND1	  0x98
-#define APPLE_M3_MBOX_I2A_RECV0	  0xa0
-#define APPLE_M3_MBOX_I2A_RECV1	  0xa8
-
-#define APPLE_M3_MBOX_IRQ_ENABLE	0x48
-#define APPLE_M3_MBOX_IRQ_ACK		0x4c
-#define APPLE_M3_MBOX_IRQ_A2I_EMPTY	BIT(0)
-#define APPLE_M3_MBOX_IRQ_A2I_NOT_EMPTY BIT(1)
-#define APPLE_M3_MBOX_IRQ_I2A_EMPTY	BIT(2)
-#define APPLE_M3_MBOX_IRQ_I2A_NOT_EMPTY BIT(3)
-
-#define APPLE_MBOX_MSG1_OUTCNT GENMASK(56, 52)
-#define APPLE_MBOX_MSG1_INCNT  GENMASK(51, 48)
-#define APPLE_MBOX_MSG1_OUTPTR GENMASK(47, 44)
-#define APPLE_MBOX_MSG1_INPTR  GENMASK(43, 40)
-#define APPLE_MBOX_MSG1_MSG    GENMASK(31, 0)
-
-struct apple_mbox_hw {
-	unsigned int control_full;
-	unsigned int control_empty;
-
-	unsigned int a2i_control;
-	unsigned int a2i_send0;
-	unsigned int a2i_send1;
-
-	unsigned int i2a_control;
-	unsigned int i2a_recv0;
-	unsigned int i2a_recv1;
-
-	bool has_irq_controls;
-	unsigned int irq_enable;
-	unsigned int irq_ack;
-	unsigned int irq_bit_recv_not_empty;
-	unsigned int irq_bit_send_empty;
-};
-
-struct apple_mbox {
-	void __iomem *regs;
-	const struct apple_mbox_hw *hw;
-
-	int irq_recv_not_empty;
-	int irq_send_empty;
-
-	struct mbox_chan chan;
-
-	struct device *dev;
-	struct mbox_controller controller;
-	spinlock_t rx_lock;
-};
-
-static const struct of_device_id apple_mbox_of_match[];
-
-static bool apple_mbox_hw_can_send(struct apple_mbox *apple_mbox)
-{
-	u32 mbox_ctrl =
-		readl_relaxed(apple_mbox->regs + apple_mbox->hw->a2i_control);
-
-	return !(mbox_ctrl & apple_mbox->hw->control_full);
-}
-
-static bool apple_mbox_hw_send_empty(struct apple_mbox *apple_mbox)
-{
-	u32 mbox_ctrl =
-		readl_relaxed(apple_mbox->regs + apple_mbox->hw->a2i_control);
-
-	return mbox_ctrl & apple_mbox->hw->control_empty;
-}
-
-static int apple_mbox_hw_send(struct apple_mbox *apple_mbox,
-			      struct apple_mbox_msg *msg)
-{
-	if (!apple_mbox_hw_can_send(apple_mbox))
-		return -EBUSY;
-
-	dev_dbg(apple_mbox->dev, "> TX %016llx %08x\n", msg->msg0, msg->msg1);
-
-	writeq_relaxed(msg->msg0, apple_mbox->regs + apple_mbox->hw->a2i_send0);
-	writeq_relaxed(FIELD_PREP(APPLE_MBOX_MSG1_MSG, msg->msg1),
-		       apple_mbox->regs + apple_mbox->hw->a2i_send1);
-
-	return 0;
-}
-
-static bool apple_mbox_hw_can_recv(struct apple_mbox *apple_mbox)
-{
-	u32 mbox_ctrl =
-		readl_relaxed(apple_mbox->regs + apple_mbox->hw->i2a_control);
-
-	return !(mbox_ctrl & apple_mbox->hw->control_empty);
-}
-
-static int apple_mbox_hw_recv(struct apple_mbox *apple_mbox,
-			      struct apple_mbox_msg *msg)
-{
-	if (!apple_mbox_hw_can_recv(apple_mbox))
-		return -ENOMSG;
-
-	msg->msg0 = readq_relaxed(apple_mbox->regs + apple_mbox->hw->i2a_recv0);
-	msg->msg1 = FIELD_GET(
-		APPLE_MBOX_MSG1_MSG,
-		readq_relaxed(apple_mbox->regs + apple_mbox->hw->i2a_recv1));
-
-	dev_dbg(apple_mbox->dev, "< RX %016llx %08x\n", msg->msg0, msg->msg1);
-
-	return 0;
-}
-
-static int apple_mbox_chan_send_data(struct mbox_chan *chan, void *data)
-{
-	struct apple_mbox *apple_mbox = chan->con_priv;
-	struct apple_mbox_msg *msg = data;
-	int ret;
-
-	ret = apple_mbox_hw_send(apple_mbox, msg);
-	if (ret)
-		return ret;
-
-	/*
-	 * The interrupt is level triggered and will keep firing as long as the
-	 * FIFO is empty. It will also keep firing if the FIFO was empty
-	 * at any point in the past until it has been acknowledged at the
-	 * mailbox level. By acknowledging it here we can ensure that we will
-	 * only get the interrupt once the FIFO has been cleared again.
-	 * If the FIFO is already empty before the ack it will fire again
-	 * immediately after the ack.
-	 */
-	if (apple_mbox->hw->has_irq_controls) {
-		writel_relaxed(apple_mbox->hw->irq_bit_send_empty,
-			       apple_mbox->regs + apple_mbox->hw->irq_ack);
-	}
-	enable_irq(apple_mbox->irq_send_empty);
-
-	return 0;
-}
-
-static irqreturn_t apple_mbox_send_empty_irq(int irq, void *data)
-{
-	struct apple_mbox *apple_mbox = data;
-
-	/*
-	 * We don't need to acknowledge the interrupt at the mailbox level
-	 * here even if supported by the hardware. It will keep firing but that
-	 * doesn't matter since it's disabled at the main interrupt controller.
-	 * apple_mbox_chan_send_data will acknowledge it before enabling
-	 * it at the main controller again.
-	 */
-	disable_irq_nosync(apple_mbox->irq_send_empty);
-	mbox_chan_txdone(&apple_mbox->chan, 0);
-	return IRQ_HANDLED;
-}
-
-static int apple_mbox_poll(struct apple_mbox *apple_mbox)
-{
-	struct apple_mbox_msg msg;
-	int ret = 0;
-
-	while (apple_mbox_hw_recv(apple_mbox, &msg) == 0) {
-		mbox_chan_received_data(&apple_mbox->chan, (void *)&msg);
-		ret++;
-	}
-
-	/*
-	 * The interrupt will keep firing even if there are no more messages
-	 * unless we also acknowledge it at the mailbox level here.
-	 * There's no race if a message comes in between the check in the while
-	 * loop above and the ack below: If a new messages arrives inbetween
-	 * those two the interrupt will just fire again immediately after the
-	 * ack since it's level triggered.
-	 */
-	if (apple_mbox->hw->has_irq_controls) {
-		writel_relaxed(apple_mbox->hw->irq_bit_recv_not_empty,
-			       apple_mbox->regs + apple_mbox->hw->irq_ack);
-	}
-
-	return ret;
-}
-
-static irqreturn_t apple_mbox_recv_irq(int irq, void *data)
-{
-	struct apple_mbox *apple_mbox = data;
-
-	spin_lock(&apple_mbox->rx_lock);
-	apple_mbox_poll(apple_mbox);
-	spin_unlock(&apple_mbox->rx_lock);
-
-	return IRQ_HANDLED;
-}
-
-static bool apple_mbox_chan_peek_data(struct mbox_chan *chan)
-{
-	struct apple_mbox *apple_mbox = chan->con_priv;
-	unsigned long flags;
-	int ret;
-
-	spin_lock_irqsave(&apple_mbox->rx_lock, flags);
-	ret = apple_mbox_poll(apple_mbox);
-	spin_unlock_irqrestore(&apple_mbox->rx_lock, flags);
-
-	return ret > 0;
-}
-
-static int apple_mbox_chan_flush(struct mbox_chan *chan, unsigned long timeout)
-{
-	struct apple_mbox *apple_mbox = chan->con_priv;
-	unsigned long deadline = jiffies + msecs_to_jiffies(timeout);
-
-	while (time_before(jiffies, deadline)) {
-		if (apple_mbox_hw_send_empty(apple_mbox)) {
-			mbox_chan_txdone(&apple_mbox->chan, 0);
-			return 0;
-		}
-
-		udelay(1);
-	}
-
-	return -ETIME;
-}
-
-static int apple_mbox_chan_startup(struct mbox_chan *chan)
-{
-	struct apple_mbox *apple_mbox = chan->con_priv;
-
-	/*
-	 * Only some variants of this mailbox HW provide interrupt control
-	 * at the mailbox level. We therefore need to handle enabling/disabling
-	 * interrupts at the main interrupt controller anyway for hardware that
-	 * doesn't. Just always keep the interrupts we care about enabled at
-	 * the mailbox level so that both hardware revisions behave almost
-	 * the same.
-	 */
-	if (apple_mbox->hw->has_irq_controls) {
-		writel_relaxed(apple_mbox->hw->irq_bit_recv_not_empty |
-				       apple_mbox->hw->irq_bit_send_empty,
-			       apple_mbox->regs + apple_mbox->hw->irq_enable);
-	}
-
-	enable_irq(apple_mbox->irq_recv_not_empty);
-	return 0;
-}
-
-static void apple_mbox_chan_shutdown(struct mbox_chan *chan)
-{
-	struct apple_mbox *apple_mbox = chan->con_priv;
-
-	disable_irq(apple_mbox->irq_recv_not_empty);
-}
-
-static const struct mbox_chan_ops apple_mbox_ops = {
-	.send_data = apple_mbox_chan_send_data,
-	.peek_data = apple_mbox_chan_peek_data,
-	.flush = apple_mbox_chan_flush,
-	.startup = apple_mbox_chan_startup,
-	.shutdown = apple_mbox_chan_shutdown,
-};
-
-static struct mbox_chan *apple_mbox_of_xlate(struct mbox_controller *mbox,
-					     const struct of_phandle_args *args)
-{
-	if (args->args_count != 0)
-		return ERR_PTR(-EINVAL);
-
-	return &mbox->chans[0];
-}
-
-static int apple_mbox_probe(struct platform_device *pdev)
-{
-	int ret;
-	const struct of_device_id *match;
-	char *irqname;
-	struct apple_mbox *mbox;
-	struct device *dev = &pdev->dev;
-
-	match = of_match_node(apple_mbox_of_match, pdev->dev.of_node);
-	if (!match)
-		return -EINVAL;
-	if (!match->data)
-		return -EINVAL;
-
-	mbox = devm_kzalloc(dev, sizeof(*mbox), GFP_KERNEL);
-	if (!mbox)
-		return -ENOMEM;
-	platform_set_drvdata(pdev, mbox);
-
-	mbox->dev = dev;
-	mbox->regs = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(mbox->regs))
-		return PTR_ERR(mbox->regs);
-
-	mbox->hw = match->data;
-	mbox->irq_recv_not_empty =
-		platform_get_irq_byname(pdev, "recv-not-empty");
-	if (mbox->irq_recv_not_empty < 0)
-		return -ENODEV;
-
-	mbox->irq_send_empty = platform_get_irq_byname(pdev, "send-empty");
-	if (mbox->irq_send_empty < 0)
-		return -ENODEV;
-
-	mbox->controller.dev = mbox->dev;
-	mbox->controller.num_chans = 1;
-	mbox->controller.chans = &mbox->chan;
-	mbox->controller.ops = &apple_mbox_ops;
-	mbox->controller.txdone_irq = true;
-	mbox->controller.of_xlate = apple_mbox_of_xlate;
-	mbox->chan.con_priv = mbox;
-	spin_lock_init(&mbox->rx_lock);
-
-	irqname = devm_kasprintf(dev, GFP_KERNEL, "%s-recv", dev_name(dev));
-	if (!irqname)
-		return -ENOMEM;
-
-	ret = devm_request_threaded_irq(dev, mbox->irq_recv_not_empty, NULL,
-					apple_mbox_recv_irq,
-					IRQF_NO_AUTOEN | IRQF_ONESHOT, irqname,
-					mbox);
-	if (ret)
-		return ret;
-
-	irqname = devm_kasprintf(dev, GFP_KERNEL, "%s-send", dev_name(dev));
-	if (!irqname)
-		return -ENOMEM;
-
-	ret = devm_request_irq(dev, mbox->irq_send_empty,
-			       apple_mbox_send_empty_irq, IRQF_NO_AUTOEN,
-			       irqname, mbox);
-	if (ret)
-		return ret;
-
-	return devm_mbox_controller_register(dev, &mbox->controller);
-}
-
-static const struct apple_mbox_hw apple_mbox_asc_hw = {
-	.control_full = APPLE_ASC_MBOX_CONTROL_FULL,
-	.control_empty = APPLE_ASC_MBOX_CONTROL_EMPTY,
-
-	.a2i_control = APPLE_ASC_MBOX_A2I_CONTROL,
-	.a2i_send0 = APPLE_ASC_MBOX_A2I_SEND0,
-	.a2i_send1 = APPLE_ASC_MBOX_A2I_SEND1,
-
-	.i2a_control = APPLE_ASC_MBOX_I2A_CONTROL,
-	.i2a_recv0 = APPLE_ASC_MBOX_I2A_RECV0,
-	.i2a_recv1 = APPLE_ASC_MBOX_I2A_RECV1,
-
-	.has_irq_controls = false,
-};
-
-static const struct apple_mbox_hw apple_mbox_m3_hw = {
-	.control_full = APPLE_M3_MBOX_CONTROL_FULL,
-	.control_empty = APPLE_M3_MBOX_CONTROL_EMPTY,
-
-	.a2i_control = APPLE_M3_MBOX_A2I_CONTROL,
-	.a2i_send0 = APPLE_M3_MBOX_A2I_SEND0,
-	.a2i_send1 = APPLE_M3_MBOX_A2I_SEND1,
-
-	.i2a_control = APPLE_M3_MBOX_I2A_CONTROL,
-	.i2a_recv0 = APPLE_M3_MBOX_I2A_RECV0,
-	.i2a_recv1 = APPLE_M3_MBOX_I2A_RECV1,
-
-	.has_irq_controls = true,
-	.irq_enable = APPLE_M3_MBOX_IRQ_ENABLE,
-	.irq_ack = APPLE_M3_MBOX_IRQ_ACK,
-	.irq_bit_recv_not_empty = APPLE_M3_MBOX_IRQ_I2A_NOT_EMPTY,
-	.irq_bit_send_empty = APPLE_M3_MBOX_IRQ_A2I_EMPTY,
-};
-
-static const struct of_device_id apple_mbox_of_match[] = {
-	{ .compatible = "apple,asc-mailbox-v4", .data = &apple_mbox_asc_hw },
-	{ .compatible = "apple,m3-mailbox-v2", .data = &apple_mbox_m3_hw },
-	{}
-};
-MODULE_DEVICE_TABLE(of, apple_mbox_of_match);
-
-static struct platform_driver apple_mbox_driver = {
-	.driver = {
-		.name = "apple-mailbox",
-		.of_match_table = apple_mbox_of_match,
-	},
-	.probe = apple_mbox_probe,
-};
-module_platform_driver(apple_mbox_driver);
-
-MODULE_LICENSE("Dual MIT/GPL");
-MODULE_AUTHOR("Sven Peter <sven@svenpeter.dev>");
-MODULE_DESCRIPTION("Apple Mailbox driver");
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 2a8b081bce7d..a743e2c572fc 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -61,19 +61,6 @@ config MD_BITMAP_FILE
 	  various kernel APIs and can only work with files on a file system not
 	  actually sitting on the MD device.
 
-config MD_LINEAR
-	tristate "Linear (append) mode (deprecated)"
-	depends on BLK_DEV_MD
-	help
-	  If you say Y here, then your multiple devices driver will be able to
-	  use the so-called linear mode, i.e. it will combine the hard disk
-	  partitions by simply appending one to the other.
-
-	  To compile this as a module, choose M here: the module
-	  will be called linear.
-
-	  If unsure, say Y.
-
 config MD_RAID0
 	tristate "RAID-0 (striping) mode"
 	depends on BLK_DEV_MD
@@ -172,27 +159,6 @@ config MD_RAID456
 
 	  If unsure, say Y.
 
-config MD_MULTIPATH
-	tristate "Multipath I/O support (deprecated)"
-	depends on BLK_DEV_MD
-	help
-	  MD_MULTIPATH provides a simple multi-path personality for use
-	  the MD framework.  It is not under active development.  New
-	  projects should consider using DM_MULTIPATH which has more
-	  features and more testing.
-
-	  If unsure, say N.
-
-config MD_FAULTY
-	tristate "Faulty test module for MD (deprecated)"
-	depends on BLK_DEV_MD
-	help
-	  The "faulty" module allows for a block device that occasionally returns
-	  read or write errors.  It is useful for testing.
-
-	  In unsure, say N.
-
-
 config MD_CLUSTER
 	tristate "Cluster Support for MD"
 	depends on BLK_DEV_MD
@@ -660,6 +626,7 @@ config DM_ZONED
 
 config DM_AUDIT
 	bool "DM audit events"
+	depends on BLK_DEV_DM
 	depends on AUDIT
 	help
 	  Generate audit events for device-mapper.
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 84291e38dca8..027d7cfeca3f 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -29,22 +29,16 @@ dm-zoned-y	+= dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o
 
 md-mod-y	+= md.o md-bitmap.o
 raid456-y	+= raid5.o raid5-cache.o raid5-ppl.o
-linear-y	+= md-linear.o
-multipath-y	+= md-multipath.o
-faulty-y	+= md-faulty.o
 
 # Note: link order is important.  All raid personalities
-# and must come before md.o, as they each initialise 
-# themselves, and md.o may use the personalities when it 
+# and must come before md.o, as they each initialise
+# themselves, and md.o may use the personalities when it
 # auto-initialised.
 
-obj-$(CONFIG_MD_LINEAR)		+= linear.o
 obj-$(CONFIG_MD_RAID0)		+= raid0.o
 obj-$(CONFIG_MD_RAID1)		+= raid1.o
 obj-$(CONFIG_MD_RAID10)		+= raid10.o
 obj-$(CONFIG_MD_RAID456)	+= raid456.o
-obj-$(CONFIG_MD_MULTIPATH)	+= multipath.o
-obj-$(CONFIG_MD_FAULTY)		+= faulty.o
 obj-$(CONFIG_MD_CLUSTER)	+= md-cluster.o
 obj-$(CONFIG_BCACHE)		+= bcache/
 obj-$(CONFIG_BLK_DEV_MD)	+= md-mod.o
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 05be59ae21b2..6ae2329052c9 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -265,6 +265,7 @@ struct bcache_device {
 #define BCACHE_DEV_WB_RUNNING		3
 #define BCACHE_DEV_RATE_DW_RUNNING	4
 	int			nr_stripes;
+#define BCH_MIN_STRIPE_SZ		((4 << 20) >> SECTOR_SHIFT)
 	unsigned int		stripe_size;
 	atomic_t		*stripe_sectors_dirty;
 	unsigned long		*full_dirty_stripes;
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index ae5cbb55861f..196cdacce38f 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -293,16 +293,16 @@ static void btree_complete_write(struct btree *b, struct btree_write *w)
 	w->journal	= NULL;
 }
 
-static void btree_node_write_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(btree_node_write_unlock)
 {
-	struct btree *b = container_of(cl, struct btree, io);
+	closure_type(b, struct btree, io);
 
 	up(&b->io_mutex);
 }
 
-static void __btree_node_write_done(struct closure *cl)
+static CLOSURE_CALLBACK(__btree_node_write_done)
 {
-	struct btree *b = container_of(cl, struct btree, io);
+	closure_type(b, struct btree, io);
 	struct btree_write *w = btree_prev_write(b);
 
 	bch_bbio_free(b->bio, b->c);
@@ -315,12 +315,12 @@ static void __btree_node_write_done(struct closure *cl)
 	closure_return_with_destructor(cl, btree_node_write_unlock);
 }
 
-static void btree_node_write_done(struct closure *cl)
+static CLOSURE_CALLBACK(btree_node_write_done)
 {
-	struct btree *b = container_of(cl, struct btree, io);
+	closure_type(b, struct btree, io);
 
 	bio_free_pages(b->bio);
-	__btree_node_write_done(cl);
+	__btree_node_write_done(&cl->work);
 }
 
 static void btree_node_write_endio(struct bio *bio)
@@ -1000,6 +1000,9 @@ err:
  *
  * The btree node will have either a read or a write lock held, depending on
  * level and op->lock.
+ *
+ * Note: Only error code or btree pointer will be returned, it is unncessary
+ *       for callers to check NULL pointer.
  */
 struct btree *bch_btree_node_get(struct cache_set *c, struct btree_op *op,
 				 struct bkey *k, int level, bool write,
@@ -1111,6 +1114,10 @@ retry:
 	mutex_unlock(&b->c->bucket_lock);
 }
 
+/*
+ * Only error code or btree pointer will be returned, it is unncessary for
+ * callers to check NULL pointer.
+ */
 struct btree *__bch_btree_node_alloc(struct cache_set *c, struct btree_op *op,
 				     int level, bool wait,
 				     struct btree *parent)
@@ -1368,7 +1375,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op,
 	memset(new_nodes, 0, sizeof(new_nodes));
 	closure_init_stack(&cl);
 
-	while (nodes < GC_MERGE_NODES && !IS_ERR(r[nodes].b))
+	while (nodes < GC_MERGE_NODES && !IS_ERR_OR_NULL(r[nodes].b))
 		keys += r[nodes++].keys;
 
 	blocks = btree_default_blocks(b->c) * 2 / 3;
@@ -1515,7 +1522,7 @@ out_nocoalesce:
 	bch_keylist_free(&keylist);
 
 	for (i = 0; i < nodes; i++)
-		if (!IS_ERR(new_nodes[i])) {
+		if (!IS_ERR_OR_NULL(new_nodes[i])) {
 			btree_node_free(new_nodes[i]);
 			rw_unlock(true, new_nodes[i]);
 		}
@@ -1532,6 +1539,8 @@ static int btree_gc_rewrite_node(struct btree *b, struct btree_op *op,
 		return 0;
 
 	n = btree_node_alloc_replacement(replace, NULL);
+	if (IS_ERR(n))
+		return 0;
 
 	/* recheck reserve after allocating replacement node */
 	if (btree_check_reserve(b, NULL)) {
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index c182c21de2e8..7ff14bd2feb8 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -723,11 +723,11 @@ static void journal_write_endio(struct bio *bio)
 	closure_put(&w->c->journal.io);
 }
 
-static void journal_write(struct closure *cl);
+static CLOSURE_CALLBACK(journal_write);
 
-static void journal_write_done(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write_done)
 {
-	struct journal *j = container_of(cl, struct journal, io);
+	closure_type(j, struct journal, io);
 	struct journal_write *w = (j->cur == j->w)
 		? &j->w[1]
 		: &j->w[0];
@@ -736,19 +736,19 @@ static void journal_write_done(struct closure *cl)
 	continue_at_nobarrier(cl, journal_write, bch_journal_wq);
 }
 
-static void journal_write_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write_unlock)
 	__releases(&c->journal.lock)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, journal.io);
+	closure_type(c, struct cache_set, journal.io);
 
 	c->journal.io_in_flight = 0;
 	spin_unlock(&c->journal.lock);
 }
 
-static void journal_write_unlocked(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write_unlocked)
 	__releases(c->journal.lock)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, journal.io);
+	closure_type(c, struct cache_set, journal.io);
 	struct cache *ca = c->cache;
 	struct journal_write *w = c->journal.cur;
 	struct bkey *k = &c->journal.key;
@@ -823,12 +823,12 @@ static void journal_write_unlocked(struct closure *cl)
 	continue_at(cl, journal_write_done, NULL);
 }
 
-static void journal_write(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, journal.io);
+	closure_type(c, struct cache_set, journal.io);
 
 	spin_lock(&c->journal.lock);
-	journal_write_unlocked(cl);
+	journal_write_unlocked(&cl->work);
 }
 
 static void journal_try_write(struct cache_set *c)
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index 9f32901fdad1..ebd500bdf0b2 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -35,16 +35,16 @@ static bool moving_pred(struct keybuf *buf, struct bkey *k)
 
 /* Moving GC - IO loop */
 
-static void moving_io_destructor(struct closure *cl)
+static CLOSURE_CALLBACK(moving_io_destructor)
 {
-	struct moving_io *io = container_of(cl, struct moving_io, cl);
+	closure_type(io, struct moving_io, cl);
 
 	kfree(io);
 }
 
-static void write_moving_finish(struct closure *cl)
+static CLOSURE_CALLBACK(write_moving_finish)
 {
-	struct moving_io *io = container_of(cl, struct moving_io, cl);
+	closure_type(io, struct moving_io, cl);
 	struct bio *bio = &io->bio.bio;
 
 	bio_free_pages(bio);
@@ -89,9 +89,9 @@ static void moving_init(struct moving_io *io)
 	bch_bio_map(bio, NULL);
 }
 
-static void write_moving(struct closure *cl)
+static CLOSURE_CALLBACK(write_moving)
 {
-	struct moving_io *io = container_of(cl, struct moving_io, cl);
+	closure_type(io, struct moving_io, cl);
 	struct data_insert_op *op = &io->op;
 
 	if (!op->status) {
@@ -113,9 +113,9 @@ static void write_moving(struct closure *cl)
 	continue_at(cl, write_moving_finish, op->wq);
 }
 
-static void read_moving_submit(struct closure *cl)
+static CLOSURE_CALLBACK(read_moving_submit)
 {
-	struct moving_io *io = container_of(cl, struct moving_io, cl);
+	closure_type(io, struct moving_io, cl);
 	struct bio *bio = &io->bio.bio;
 
 	bch_submit_bbio(bio, io->op.c, &io->w->key, 0);
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index a9b1f3896249..83d112bd2b1c 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -25,7 +25,7 @@
 
 struct kmem_cache *bch_search_cache;
 
-static void bch_data_insert_start(struct closure *cl);
+static CLOSURE_CALLBACK(bch_data_insert_start);
 
 static unsigned int cache_mode(struct cached_dev *dc)
 {
@@ -55,9 +55,9 @@ static void bio_csum(struct bio *bio, struct bkey *k)
 
 /* Insert data into cache */
 
-static void bch_data_insert_keys(struct closure *cl)
+static CLOSURE_CALLBACK(bch_data_insert_keys)
 {
-	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
+	closure_type(op, struct data_insert_op, cl);
 	atomic_t *journal_ref = NULL;
 	struct bkey *replace_key = op->replace ? &op->replace_key : NULL;
 	int ret;
@@ -136,9 +136,9 @@ out:
 	continue_at(cl, bch_data_insert_keys, op->wq);
 }
 
-static void bch_data_insert_error(struct closure *cl)
+static CLOSURE_CALLBACK(bch_data_insert_error)
 {
-	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
+	closure_type(op, struct data_insert_op, cl);
 
 	/*
 	 * Our data write just errored, which means we've got a bunch of keys to
@@ -163,7 +163,7 @@ static void bch_data_insert_error(struct closure *cl)
 
 	op->insert_keys.top = dst;
 
-	bch_data_insert_keys(cl);
+	bch_data_insert_keys(&cl->work);
 }
 
 static void bch_data_insert_endio(struct bio *bio)
@@ -184,9 +184,9 @@ static void bch_data_insert_endio(struct bio *bio)
 	bch_bbio_endio(op->c, bio, bio->bi_status, "writing data to cache");
 }
 
-static void bch_data_insert_start(struct closure *cl)
+static CLOSURE_CALLBACK(bch_data_insert_start)
 {
-	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
+	closure_type(op, struct data_insert_op, cl);
 	struct bio *bio = op->bio, *n;
 
 	if (op->bypass)
@@ -305,16 +305,16 @@ err:
  * If op->bypass is true, instead of inserting the data it invalidates the
  * region of the cache represented by op->bio and op->inode.
  */
-void bch_data_insert(struct closure *cl)
+CLOSURE_CALLBACK(bch_data_insert)
 {
-	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
+	closure_type(op, struct data_insert_op, cl);
 
 	trace_bcache_write(op->c, op->inode, op->bio,
 			   op->writeback, op->bypass);
 
 	bch_keylist_init(&op->insert_keys);
 	bio_get(op->bio);
-	bch_data_insert_start(cl);
+	bch_data_insert_start(&cl->work);
 }
 
 /*
@@ -575,9 +575,9 @@ static int cache_lookup_fn(struct btree_op *op, struct btree *b, struct bkey *k)
 	return n == bio ? MAP_DONE : MAP_CONTINUE;
 }
 
-static void cache_lookup(struct closure *cl)
+static CLOSURE_CALLBACK(cache_lookup)
 {
-	struct search *s = container_of(cl, struct search, iop.cl);
+	closure_type(s, struct search, iop.cl);
 	struct bio *bio = &s->bio.bio;
 	struct cached_dev *dc;
 	int ret;
@@ -698,9 +698,9 @@ static void do_bio_hook(struct search *s,
 	bio_cnt_set(bio, 3);
 }
 
-static void search_free(struct closure *cl)
+static CLOSURE_CALLBACK(search_free)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 
 	atomic_dec(&s->iop.c->search_inflight);
 
@@ -749,20 +749,20 @@ static inline struct search *search_alloc(struct bio *bio,
 
 /* Cached devices */
 
-static void cached_dev_bio_complete(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_bio_complete)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
 	cached_dev_put(dc);
-	search_free(cl);
+	search_free(&cl->work);
 }
 
 /* Process reads */
 
-static void cached_dev_read_error_done(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_read_error_done)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 
 	if (s->iop.replace_collision)
 		bch_mark_cache_miss_collision(s->iop.c, s->d);
@@ -770,12 +770,12 @@ static void cached_dev_read_error_done(struct closure *cl)
 	if (s->iop.bio)
 		bio_free_pages(s->iop.bio);
 
-	cached_dev_bio_complete(cl);
+	cached_dev_bio_complete(&cl->work);
 }
 
-static void cached_dev_read_error(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_read_error)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct bio *bio = &s->bio.bio;
 
 	/*
@@ -801,9 +801,9 @@ static void cached_dev_read_error(struct closure *cl)
 	continue_at(cl, cached_dev_read_error_done, NULL);
 }
 
-static void cached_dev_cache_miss_done(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_cache_miss_done)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct bcache_device *d = s->d;
 
 	if (s->iop.replace_collision)
@@ -812,13 +812,13 @@ static void cached_dev_cache_miss_done(struct closure *cl)
 	if (s->iop.bio)
 		bio_free_pages(s->iop.bio);
 
-	cached_dev_bio_complete(cl);
+	cached_dev_bio_complete(&cl->work);
 	closure_put(&d->cl);
 }
 
-static void cached_dev_read_done(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_read_done)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
 	/*
@@ -858,9 +858,9 @@ static void cached_dev_read_done(struct closure *cl)
 	continue_at(cl, cached_dev_cache_miss_done, NULL);
 }
 
-static void cached_dev_read_done_bh(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_read_done_bh)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
 	bch_mark_cache_accounting(s->iop.c, s->d,
@@ -955,13 +955,13 @@ static void cached_dev_read(struct cached_dev *dc, struct search *s)
 
 /* Process writes */
 
-static void cached_dev_write_complete(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_write_complete)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
 	up_read_non_owner(&dc->writeback_lock);
-	cached_dev_bio_complete(cl);
+	cached_dev_bio_complete(&cl->work);
 }
 
 static void cached_dev_write(struct cached_dev *dc, struct search *s)
@@ -1048,9 +1048,9 @@ insert_data:
 	continue_at(cl, cached_dev_write_complete, NULL);
 }
 
-static void cached_dev_nodata(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_nodata)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct bio *bio = &s->bio.bio;
 
 	if (s->iop.flush_journal)
@@ -1265,9 +1265,9 @@ static int flash_dev_cache_miss(struct btree *b, struct search *s,
 	return MAP_CONTINUE;
 }
 
-static void flash_dev_nodata(struct closure *cl)
+static CLOSURE_CALLBACK(flash_dev_nodata)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 
 	if (s->iop.flush_journal)
 		bch_journal_meta(s->iop.c, cl);
diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h
index 38ab4856eaab..46bbef00aebb 100644
--- a/drivers/md/bcache/request.h
+++ b/drivers/md/bcache/request.h
@@ -34,7 +34,7 @@ struct data_insert_op {
 };
 
 unsigned int bch_get_congested(const struct cache_set *c);
-void bch_data_insert(struct closure *cl);
+CLOSURE_CALLBACK(bch_data_insert);
 
 void bch_cached_dev_request_init(struct cached_dev *dc);
 void cached_dev_submit_bio(struct bio *bio);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 8bd899766372..dc3f50f69714 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -327,9 +327,9 @@ static void __write_super(struct cache_sb *sb, struct cache_sb_disk *out,
 	submit_bio(bio);
 }
 
-static void bch_write_bdev_super_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(bch_write_bdev_super_unlock)
 {
-	struct cached_dev *dc = container_of(cl, struct cached_dev, sb_write);
+	closure_type(dc, struct cached_dev, sb_write);
 
 	up(&dc->sb_write_mutex);
 }
@@ -363,9 +363,9 @@ static void write_super_endio(struct bio *bio)
 	closure_put(&ca->set->sb_write);
 }
 
-static void bcache_write_super_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(bcache_write_super_unlock)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, sb_write);
+	closure_type(c, struct cache_set, sb_write);
 
 	up(&c->sb_write_mutex);
 }
@@ -407,9 +407,9 @@ static void uuid_endio(struct bio *bio)
 	closure_put(cl);
 }
 
-static void uuid_io_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(uuid_io_unlock)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, uuid_write);
+	closure_type(c, struct cache_set, uuid_write);
 
 	up(&c->uuid_write_mutex);
 }
@@ -905,6 +905,8 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 
 	if (!d->stripe_size)
 		d->stripe_size = 1 << 31;
+	else if (d->stripe_size < BCH_MIN_STRIPE_SZ)
+		d->stripe_size = roundup(BCH_MIN_STRIPE_SZ, d->stripe_size);
 
 	n = DIV_ROUND_UP_ULL(sectors, d->stripe_size);
 	if (!n || n > max_stripes) {
@@ -952,7 +954,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 	q->limits.max_segment_size	= UINT_MAX;
 	q->limits.max_segments		= BIO_MAX_VECS;
 	blk_queue_max_discard_sectors(q, UINT_MAX);
-	q->limits.discard_granularity	= 512;
 	q->limits.io_min		= block_size;
 	q->limits.logical_block_size	= block_size;
 	q->limits.physical_block_size	= block_size;
@@ -1342,9 +1343,9 @@ void bch_cached_dev_release(struct kobject *kobj)
 	module_put(THIS_MODULE);
 }
 
-static void cached_dev_free(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_free)
 {
-	struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl);
+	closure_type(dc, struct cached_dev, disk.cl);
 
 	if (test_and_clear_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags))
 		cancel_writeback_rate_update_dwork(dc);
@@ -1376,9 +1377,9 @@ static void cached_dev_free(struct closure *cl)
 	kobject_put(&dc->disk.kobj);
 }
 
-static void cached_dev_flush(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_flush)
 {
-	struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl);
+	closure_type(dc, struct cached_dev, disk.cl);
 	struct bcache_device *d = &dc->disk;
 
 	mutex_lock(&bch_register_lock);
@@ -1497,9 +1498,9 @@ void bch_flash_dev_release(struct kobject *kobj)
 	kfree(d);
 }
 
-static void flash_dev_free(struct closure *cl)
+static CLOSURE_CALLBACK(flash_dev_free)
 {
-	struct bcache_device *d = container_of(cl, struct bcache_device, cl);
+	closure_type(d, struct bcache_device, cl);
 
 	mutex_lock(&bch_register_lock);
 	atomic_long_sub(bcache_dev_sectors_dirty(d),
@@ -1510,9 +1511,9 @@ static void flash_dev_free(struct closure *cl)
 	kobject_put(&d->kobj);
 }
 
-static void flash_dev_flush(struct closure *cl)
+static CLOSURE_CALLBACK(flash_dev_flush)
 {
-	struct bcache_device *d = container_of(cl, struct bcache_device, cl);
+	closure_type(d, struct bcache_device, cl);
 
 	mutex_lock(&bch_register_lock);
 	bcache_device_unlink(d);
@@ -1668,9 +1669,9 @@ void bch_cache_set_release(struct kobject *kobj)
 	module_put(THIS_MODULE);
 }
 
-static void cache_set_free(struct closure *cl)
+static CLOSURE_CALLBACK(cache_set_free)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, cl);
+	closure_type(c, struct cache_set, cl);
 	struct cache *ca;
 
 	debugfs_remove(c->debug);
@@ -1709,9 +1710,9 @@ static void cache_set_free(struct closure *cl)
 	kobject_put(&c->kobj);
 }
 
-static void cache_set_flush(struct closure *cl)
+static CLOSURE_CALLBACK(cache_set_flush)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, caching);
+	closure_type(c, struct cache_set, caching);
 	struct cache *ca = c->cache;
 	struct btree *b;
 
@@ -1806,9 +1807,9 @@ static void conditional_stop_bcache_device(struct cache_set *c,
 	}
 }
 
-static void __cache_set_unregister(struct closure *cl)
+static CLOSURE_CALLBACK(__cache_set_unregister)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, caching);
+	closure_type(c, struct cache_set, caching);
 	struct cached_dev *dc;
 	struct bcache_device *d;
 	size_t i;
@@ -2016,7 +2017,7 @@ static int run_cache_set(struct cache_set *c)
 		c->root = bch_btree_node_get(c, NULL, k,
 					     j->btree_level,
 					     true, NULL);
-		if (IS_ERR_OR_NULL(c->root))
+		if (IS_ERR(c->root))
 			goto err;
 
 		list_del_init(&c->root->list);
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 45d8af755de6..a438efb66069 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -1104,7 +1104,7 @@ SHOW(__bch_cache)
 			sum += INITIAL_PRIO - cached[i];
 
 		if (n)
-			do_div(sum, n);
+			sum = div64_u64(sum, n);
 
 		for (i = 0; i < ARRAY_SIZE(q); i++)
 			q[i] = INITIAL_PRIO - cached[n * (i + 1) /
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 24c049067f61..8827a6f130ad 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -341,16 +341,16 @@ static void dirty_init(struct keybuf_key *w)
 	bch_bio_map(bio, NULL);
 }
 
-static void dirty_io_destructor(struct closure *cl)
+static CLOSURE_CALLBACK(dirty_io_destructor)
 {
-	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
+	closure_type(io, struct dirty_io, cl);
 
 	kfree(io);
 }
 
-static void write_dirty_finish(struct closure *cl)
+static CLOSURE_CALLBACK(write_dirty_finish)
 {
-	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
+	closure_type(io, struct dirty_io, cl);
 	struct keybuf_key *w = io->bio.bi_private;
 	struct cached_dev *dc = io->dc;
 
@@ -400,9 +400,9 @@ static void dirty_endio(struct bio *bio)
 	closure_put(&io->cl);
 }
 
-static void write_dirty(struct closure *cl)
+static CLOSURE_CALLBACK(write_dirty)
 {
-	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
+	closure_type(io, struct dirty_io, cl);
 	struct keybuf_key *w = io->bio.bi_private;
 	struct cached_dev *dc = io->dc;
 
@@ -462,9 +462,9 @@ static void read_dirty_endio(struct bio *bio)
 	dirty_endio(bio);
 }
 
-static void read_dirty_submit(struct closure *cl)
+static CLOSURE_CALLBACK(read_dirty_submit)
 {
-	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
+	closure_type(io, struct dirty_io, cl);
 
 	closure_bio_submit(io->dc->disk.c, &io->bio, cl);
 
@@ -913,7 +913,7 @@ static int bch_dirty_init_thread(void *arg)
 	int cur_idx, prev_idx, skip_nr;
 
 	k = p = NULL;
-	cur_idx = prev_idx = 0;
+	prev_idx = 0;
 
 	bch_btree_iter_init(&c->root->keys, &iter, NULL);
 	k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad);
@@ -977,24 +977,35 @@ static int bch_btre_dirty_init_thread_nr(void)
 void bch_sectors_dirty_init(struct bcache_device *d)
 {
 	int i;
+	struct btree *b = NULL;
 	struct bkey *k = NULL;
 	struct btree_iter iter;
 	struct sectors_dirty_init op;
 	struct cache_set *c = d->c;
 	struct bch_dirty_init_state state;
 
+retry_lock:
+	b = c->root;
+	rw_lock(0, b, b->level);
+	if (b != c->root) {
+		rw_unlock(0, b);
+		goto retry_lock;
+	}
+
 	/* Just count root keys if no leaf node */
-	rw_lock(0, c->root, c->root->level);
 	if (c->root->level == 0) {
 		bch_btree_op_init(&op.op, -1);
 		op.inode = d->id;
 		op.count = 0;
 
 		for_each_key_filter(&c->root->keys,
-				    k, &iter, bch_ptr_invalid)
+				    k, &iter, bch_ptr_invalid) {
+			if (KEY_INODE(k) != op.inode)
+				continue;
 			sectors_dirty_init_fn(&op.op, c->root, k);
+		}
 
-		rw_unlock(0, c->root);
+		rw_unlock(0, b);
 		return;
 	}
 
@@ -1014,23 +1025,24 @@ void bch_sectors_dirty_init(struct bcache_device *d)
 		if (atomic_read(&state.enough))
 			break;
 
+		atomic_inc(&state.started);
 		state.infos[i].state = &state;
 		state.infos[i].thread =
 			kthread_run(bch_dirty_init_thread, &state.infos[i],
 				    "bch_dirtcnt[%d]", i);
 		if (IS_ERR(state.infos[i].thread)) {
 			pr_err("fails to run thread bch_dirty_init[%d]\n", i);
+			atomic_dec(&state.started);
 			for (--i; i >= 0; i--)
 				kthread_stop(state.infos[i].thread);
 			goto out;
 		}
-		atomic_inc(&state.started);
 	}
 
 out:
 	/* Must wait for all threads to stop. */
 	wait_event(state.wait, atomic_read(&state.started) == 0);
-	rw_unlock(0, c->root);
+	rw_unlock(0, b);
 }
 
 void bch_cached_dev_writeback_init(struct cached_dev *dc)
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 62eb27639c9b..13c65b7e1ed6 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -254,7 +254,7 @@ enum evict_result {
 
 typedef enum evict_result (*le_predicate)(struct lru_entry *le, void *context);
 
-static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *context)
+static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *context, bool no_sleep)
 {
 	unsigned long tested = 0;
 	struct list_head *h = lru->cursor;
@@ -295,7 +295,8 @@ static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *con
 
 		h = h->next;
 
-		cond_resched();
+		if (!no_sleep)
+			cond_resched();
 	}
 
 	return NULL;
@@ -382,7 +383,10 @@ struct dm_buffer {
  */
 
 struct buffer_tree {
-	struct rw_semaphore lock;
+	union {
+		struct rw_semaphore lock;
+		rwlock_t spinlock;
+	} u;
 	struct rb_root root;
 } ____cacheline_aligned_in_smp;
 
@@ -393,9 +397,12 @@ struct dm_buffer_cache {
 	 * on the locks.
 	 */
 	unsigned int num_locks;
+	bool no_sleep;
 	struct buffer_tree trees[];
 };
 
+static DEFINE_STATIC_KEY_FALSE(no_sleep_enabled);
+
 static inline unsigned int cache_index(sector_t block, unsigned int num_locks)
 {
 	return dm_hash_locks_index(block, num_locks);
@@ -403,22 +410,34 @@ static inline unsigned int cache_index(sector_t block, unsigned int num_locks)
 
 static inline void cache_read_lock(struct dm_buffer_cache *bc, sector_t block)
 {
-	down_read(&bc->trees[cache_index(block, bc->num_locks)].lock);
+	if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep)
+		read_lock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock);
+	else
+		down_read(&bc->trees[cache_index(block, bc->num_locks)].u.lock);
 }
 
 static inline void cache_read_unlock(struct dm_buffer_cache *bc, sector_t block)
 {
-	up_read(&bc->trees[cache_index(block, bc->num_locks)].lock);
+	if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep)
+		read_unlock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock);
+	else
+		up_read(&bc->trees[cache_index(block, bc->num_locks)].u.lock);
 }
 
 static inline void cache_write_lock(struct dm_buffer_cache *bc, sector_t block)
 {
-	down_write(&bc->trees[cache_index(block, bc->num_locks)].lock);
+	if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep)
+		write_lock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock);
+	else
+		down_write(&bc->trees[cache_index(block, bc->num_locks)].u.lock);
 }
 
 static inline void cache_write_unlock(struct dm_buffer_cache *bc, sector_t block)
 {
-	up_write(&bc->trees[cache_index(block, bc->num_locks)].lock);
+	if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep)
+		write_unlock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock);
+	else
+		up_write(&bc->trees[cache_index(block, bc->num_locks)].u.lock);
 }
 
 /*
@@ -442,18 +461,32 @@ static void lh_init(struct lock_history *lh, struct dm_buffer_cache *cache, bool
 
 static void __lh_lock(struct lock_history *lh, unsigned int index)
 {
-	if (lh->write)
-		down_write(&lh->cache->trees[index].lock);
-	else
-		down_read(&lh->cache->trees[index].lock);
+	if (lh->write) {
+		if (static_branch_unlikely(&no_sleep_enabled) && lh->cache->no_sleep)
+			write_lock_bh(&lh->cache->trees[index].u.spinlock);
+		else
+			down_write(&lh->cache->trees[index].u.lock);
+	} else {
+		if (static_branch_unlikely(&no_sleep_enabled) && lh->cache->no_sleep)
+			read_lock_bh(&lh->cache->trees[index].u.spinlock);
+		else
+			down_read(&lh->cache->trees[index].u.lock);
+	}
 }
 
 static void __lh_unlock(struct lock_history *lh, unsigned int index)
 {
-	if (lh->write)
-		up_write(&lh->cache->trees[index].lock);
-	else
-		up_read(&lh->cache->trees[index].lock);
+	if (lh->write) {
+		if (static_branch_unlikely(&no_sleep_enabled) && lh->cache->no_sleep)
+			write_unlock_bh(&lh->cache->trees[index].u.spinlock);
+		else
+			up_write(&lh->cache->trees[index].u.lock);
+	} else {
+		if (static_branch_unlikely(&no_sleep_enabled) && lh->cache->no_sleep)
+			read_unlock_bh(&lh->cache->trees[index].u.spinlock);
+		else
+			up_read(&lh->cache->trees[index].u.lock);
+	}
 }
 
 /*
@@ -502,14 +535,18 @@ static struct dm_buffer *list_to_buffer(struct list_head *l)
 	return le_to_buffer(le);
 }
 
-static void cache_init(struct dm_buffer_cache *bc, unsigned int num_locks)
+static void cache_init(struct dm_buffer_cache *bc, unsigned int num_locks, bool no_sleep)
 {
 	unsigned int i;
 
 	bc->num_locks = num_locks;
+	bc->no_sleep = no_sleep;
 
 	for (i = 0; i < bc->num_locks; i++) {
-		init_rwsem(&bc->trees[i].lock);
+		if (no_sleep)
+			rwlock_init(&bc->trees[i].u.spinlock);
+		else
+			init_rwsem(&bc->trees[i].u.lock);
 		bc->trees[i].root = RB_ROOT;
 	}
 
@@ -648,7 +685,7 @@ static struct dm_buffer *__cache_evict(struct dm_buffer_cache *bc, int list_mode
 	struct lru_entry *le;
 	struct dm_buffer *b;
 
-	le = lru_evict(&bc->lru[list_mode], __evict_pred, &w);
+	le = lru_evict(&bc->lru[list_mode], __evict_pred, &w, bc->no_sleep);
 	if (!le)
 		return NULL;
 
@@ -702,7 +739,7 @@ static void __cache_mark_many(struct dm_buffer_cache *bc, int old_mode, int new_
 	struct evict_wrapper w = {.lh = lh, .pred = pred, .context = context};
 
 	while (true) {
-		le = lru_evict(&bc->lru[old_mode], __evict_pred, &w);
+		le = lru_evict(&bc->lru[old_mode], __evict_pred, &w, bc->no_sleep);
 		if (!le)
 			break;
 
@@ -915,10 +952,11 @@ static void cache_remove_range(struct dm_buffer_cache *bc,
 {
 	unsigned int i;
 
+	BUG_ON(bc->no_sleep);
 	for (i = 0; i < bc->num_locks; i++) {
-		down_write(&bc->trees[i].lock);
+		down_write(&bc->trees[i].u.lock);
 		__remove_range(bc, &bc->trees[i].root, begin, end, pred, release);
-		up_write(&bc->trees[i].lock);
+		up_write(&bc->trees[i].u.lock);
 	}
 }
 
@@ -979,8 +1017,6 @@ struct dm_bufio_client {
 	struct dm_buffer_cache cache; /* must be last member */
 };
 
-static DEFINE_STATIC_KEY_FALSE(no_sleep_enabled);
-
 /*----------------------------------------------------------------*/
 
 #define dm_bufio_in_request()	(!!current->bio_list)
@@ -1134,7 +1170,7 @@ static void __cache_size_refresh(void)
  * If the allocation may fail we use __get_free_pages. Memory fragmentation
  * won't have a fatal effect here, but it just causes flushes of some other
  * buffers and more I/O will be performed. Don't use __get_free_pages if it
- * always fails (i.e. order > MAX_ORDER).
+ * always fails (i.e. order > MAX_PAGE_ORDER).
  *
  * If the allocation shouldn't fail we use __vmalloc. This is only for the
  * initial reserve allocation, so there's no risk of wasting all vmalloc
@@ -1871,7 +1907,8 @@ static void *new_read(struct dm_bufio_client *c, sector_t block,
 	if (need_submit)
 		submit_io(b, REQ_OP_READ, read_endio);
 
-	wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE);
+	if (nf != NF_GET)	/* we already tested this condition above */
+		wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE);
 
 	if (b->read_error) {
 		int error = blk_status_to_errno(b->read_error);
@@ -2421,7 +2458,7 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign
 		r = -ENOMEM;
 		goto bad_client;
 	}
-	cache_init(&c->cache, num_locks);
+	cache_init(&c->cache, num_locks, (flags & DM_BUFIO_CLIENT_NO_SLEEP) != 0);
 
 	c->bdev = bdev;
 	c->block_size = block_size;
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 6de107aff331..855b482cbff1 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1673,7 +1673,7 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned int size)
 	unsigned int nr_iovecs = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	gfp_t gfp_mask = GFP_NOWAIT | __GFP_HIGHMEM;
 	unsigned int remaining_size;
-	unsigned int order = MAX_ORDER - 1;
+	unsigned int order = MAX_PAGE_ORDER;
 
 retry:
 	if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM))
diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
index efd510984e25..5eabdb06c649 100644
--- a/drivers/md/dm-delay.c
+++ b/drivers/md/dm-delay.c
@@ -33,7 +33,7 @@ struct delay_c {
 	struct work_struct flush_expired_bios;
 	struct list_head delayed_bios;
 	struct task_struct *worker;
-	atomic_t may_delay;
+	bool may_delay;
 
 	struct delay_class read;
 	struct delay_class write;
@@ -73,39 +73,6 @@ static inline bool delay_is_fast(struct delay_c *dc)
 	return !!dc->worker;
 }
 
-static void flush_delayed_bios_fast(struct delay_c *dc, bool flush_all)
-{
-	struct dm_delay_info *delayed, *next;
-
-	mutex_lock(&delayed_bios_lock);
-	list_for_each_entry_safe(delayed, next, &dc->delayed_bios, list) {
-		if (flush_all || time_after_eq(jiffies, delayed->expires)) {
-			struct bio *bio = dm_bio_from_per_bio_data(delayed,
-						sizeof(struct dm_delay_info));
-			list_del(&delayed->list);
-			dm_submit_bio_remap(bio, NULL);
-			delayed->class->ops--;
-		}
-	}
-	mutex_unlock(&delayed_bios_lock);
-}
-
-static int flush_worker_fn(void *data)
-{
-	struct delay_c *dc = data;
-
-	while (1) {
-		flush_delayed_bios_fast(dc, false);
-		if (unlikely(list_empty(&dc->delayed_bios))) {
-			set_current_state(TASK_INTERRUPTIBLE);
-			schedule();
-		} else
-			cond_resched();
-	}
-
-	return 0;
-}
-
 static void flush_bios(struct bio *bio)
 {
 	struct bio *n;
@@ -118,36 +85,61 @@ static void flush_bios(struct bio *bio)
 	}
 }
 
-static struct bio *flush_delayed_bios(struct delay_c *dc, bool flush_all)
+static void flush_delayed_bios(struct delay_c *dc, bool flush_all)
 {
 	struct dm_delay_info *delayed, *next;
+	struct bio_list flush_bio_list;
 	unsigned long next_expires = 0;
-	unsigned long start_timer = 0;
-	struct bio_list flush_bios = { };
+	bool start_timer = false;
+	bio_list_init(&flush_bio_list);
 
 	mutex_lock(&delayed_bios_lock);
 	list_for_each_entry_safe(delayed, next, &dc->delayed_bios, list) {
+		cond_resched();
 		if (flush_all || time_after_eq(jiffies, delayed->expires)) {
 			struct bio *bio = dm_bio_from_per_bio_data(delayed,
 						sizeof(struct dm_delay_info));
 			list_del(&delayed->list);
-			bio_list_add(&flush_bios, bio);
+			bio_list_add(&flush_bio_list, bio);
 			delayed->class->ops--;
 			continue;
 		}
 
-		if (!start_timer) {
-			start_timer = 1;
-			next_expires = delayed->expires;
-		} else
-			next_expires = min(next_expires, delayed->expires);
+		if (!delay_is_fast(dc)) {
+			if (!start_timer) {
+				start_timer = true;
+				next_expires = delayed->expires;
+			} else {
+				next_expires = min(next_expires, delayed->expires);
+			}
+		}
 	}
 	mutex_unlock(&delayed_bios_lock);
 
 	if (start_timer)
 		queue_timeout(dc, next_expires);
 
-	return bio_list_get(&flush_bios);
+	flush_bios(bio_list_get(&flush_bio_list));
+}
+
+static int flush_worker_fn(void *data)
+{
+	struct delay_c *dc = data;
+
+	while (!kthread_should_stop()) {
+		flush_delayed_bios(dc, false);
+		mutex_lock(&delayed_bios_lock);
+		if (unlikely(list_empty(&dc->delayed_bios))) {
+			set_current_state(TASK_INTERRUPTIBLE);
+			mutex_unlock(&delayed_bios_lock);
+			schedule();
+		} else {
+			mutex_unlock(&delayed_bios_lock);
+			cond_resched();
+		}
+	}
+
+	return 0;
 }
 
 static void flush_expired_bios(struct work_struct *work)
@@ -155,10 +147,7 @@ static void flush_expired_bios(struct work_struct *work)
 	struct delay_c *dc;
 
 	dc = container_of(work, struct delay_c, flush_expired_bios);
-	if (delay_is_fast(dc))
-		flush_delayed_bios_fast(dc, false);
-	else
-		flush_bios(flush_delayed_bios(dc, false));
+	flush_delayed_bios(dc, false);
 }
 
 static void delay_dtr(struct dm_target *ti)
@@ -177,8 +166,7 @@ static void delay_dtr(struct dm_target *ti)
 	if (dc->worker)
 		kthread_stop(dc->worker);
 
-	if (!delay_is_fast(dc))
-		mutex_destroy(&dc->timer_lock);
+	mutex_destroy(&dc->timer_lock);
 
 	kfree(dc);
 }
@@ -236,7 +224,8 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	ti->private = dc;
 	INIT_LIST_HEAD(&dc->delayed_bios);
-	atomic_set(&dc->may_delay, 1);
+	mutex_init(&dc->timer_lock);
+	dc->may_delay = true;
 	dc->argc = argc;
 
 	ret = delay_class_ctr(ti, &dc->read, argv);
@@ -282,12 +271,12 @@ out:
 					    "dm-delay-flush-worker");
 		if (IS_ERR(dc->worker)) {
 			ret = PTR_ERR(dc->worker);
+			dc->worker = NULL;
 			goto bad;
 		}
 	} else {
 		timer_setup(&dc->delay_timer, handle_delayed_timer, 0);
 		INIT_WORK(&dc->flush_expired_bios, flush_expired_bios);
-		mutex_init(&dc->timer_lock);
 		dc->kdelayd_wq = alloc_workqueue("kdelayd", WQ_MEM_RECLAIM, 0);
 		if (!dc->kdelayd_wq) {
 			ret = -EINVAL;
@@ -312,7 +301,7 @@ static int delay_bio(struct delay_c *dc, struct delay_class *c, struct bio *bio)
 	struct dm_delay_info *delayed;
 	unsigned long expires = 0;
 
-	if (!c->delay || !atomic_read(&dc->may_delay))
+	if (!c->delay)
 		return DM_MAPIO_REMAPPED;
 
 	delayed = dm_per_bio_data(bio, sizeof(struct dm_delay_info));
@@ -321,6 +310,10 @@ static int delay_bio(struct delay_c *dc, struct delay_class *c, struct bio *bio)
 	delayed->expires = expires = jiffies + msecs_to_jiffies(c->delay);
 
 	mutex_lock(&delayed_bios_lock);
+	if (unlikely(!dc->may_delay)) {
+		mutex_unlock(&delayed_bios_lock);
+		return DM_MAPIO_REMAPPED;
+	}
 	c->ops++;
 	list_add_tail(&delayed->list, &dc->delayed_bios);
 	mutex_unlock(&delayed_bios_lock);
@@ -337,21 +330,20 @@ static void delay_presuspend(struct dm_target *ti)
 {
 	struct delay_c *dc = ti->private;
 
-	atomic_set(&dc->may_delay, 0);
+	mutex_lock(&delayed_bios_lock);
+	dc->may_delay = false;
+	mutex_unlock(&delayed_bios_lock);
 
-	if (delay_is_fast(dc))
-		flush_delayed_bios_fast(dc, true);
-	else {
+	if (!delay_is_fast(dc))
 		del_timer_sync(&dc->delay_timer);
-		flush_bios(flush_delayed_bios(dc, true));
-	}
+	flush_delayed_bios(dc, true);
 }
 
 static void delay_resume(struct dm_target *ti)
 {
 	struct delay_c *dc = ti->private;
 
-	atomic_set(&dc->may_delay, 1);
+	dc->may_delay = true;
 }
 
 static int delay_map(struct dm_target *ti, struct bio *bio)
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index 120153e44ae0..7916ed9f10e8 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -434,7 +434,7 @@ static struct bio *clone_bio(struct dm_target *ti, struct flakey_c *fc, struct b
 
 	remaining_size = size;
 
-	order = MAX_ORDER - 1;
+	order = MAX_PAGE_ORDER;
 	while (remaining_size) {
 		struct page *pages;
 		unsigned size_to_add, to_copy;
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index e85c688fd91e..c5f03aab4552 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -1755,11 +1755,12 @@ static void integrity_metadata(struct work_struct *w)
 		sectors_to_process = dio->range.n_sectors;
 
 		__bio_for_each_segment(bv, bio, iter, dio->bio_details.bi_iter) {
+			struct bio_vec bv_copy = bv;
 			unsigned int pos;
 			char *mem, *checksums_ptr;
 
 again:
-			mem = bvec_kmap_local(&bv);
+			mem = bvec_kmap_local(&bv_copy);
 			pos = 0;
 			checksums_ptr = checksums;
 			do {
@@ -1768,7 +1769,7 @@ again:
 				sectors_to_process -= ic->sectors_per_block;
 				pos += ic->sectors_per_block << SECTOR_SHIFT;
 				sector += ic->sectors_per_block;
-			} while (pos < bv.bv_len && sectors_to_process && checksums != checksums_onstack);
+			} while (pos < bv_copy.bv_len && sectors_to_process && checksums != checksums_onstack);
 			kunmap_local(mem);
 
 			r = dm_integrity_rw_tag(ic, checksums, &dio->metadata_block, &dio->metadata_offset,
@@ -1793,9 +1794,9 @@ again:
 			if (!sectors_to_process)
 				break;
 
-			if (unlikely(pos < bv.bv_len)) {
-				bv.bv_offset += pos;
-				bv.bv_len -= pos;
+			if (unlikely(pos < bv_copy.bv_len)) {
+				bv_copy.bv_offset += pos;
+				bv_copy.bv_len -= pos;
 				goto again;
 			}
 		}
diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c
index d01807c50f20..36bcfdccae04 100644
--- a/drivers/md/dm-kcopyd.c
+++ b/drivers/md/dm-kcopyd.c
@@ -807,7 +807,7 @@ void dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from,
 	 */
 	if (!(job->flags & BIT(DM_KCOPYD_WRITE_SEQ))) {
 		for (i = 0; i < job->num_dests; i++) {
-			if (bdev_zoned_model(dests[i].bdev) == BLK_ZONED_HM) {
+			if (bdev_is_zoned(dests[i].bdev)) {
 				job->flags |= BIT(DM_KCOPYD_WRITE_SEQ);
 				break;
 			}
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 91ebdcc6e9a8..eb009d6bb03a 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3317,6 +3317,9 @@ static void raid_dtr(struct dm_target *ti)
 	mddev_lock_nointr(&rs->md);
 	md_stop(&rs->md);
 	mddev_unlock(&rs->md);
+
+	if (work_pending(&rs->md.event_work))
+		flush_work(&rs->md.event_work);
 	raid_set_free(rs);
 }
 
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 198d38b53322..260b5b8f2b0d 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1579,21 +1579,18 @@ bool dm_table_has_no_data_devices(struct dm_table *t)
 	return true;
 }
 
-static int device_not_zoned_model(struct dm_target *ti, struct dm_dev *dev,
-				  sector_t start, sector_t len, void *data)
+static int device_not_zoned(struct dm_target *ti, struct dm_dev *dev,
+			    sector_t start, sector_t len, void *data)
 {
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-	enum blk_zoned_model *zoned_model = data;
+	bool *zoned = data;
 
-	return blk_queue_zoned_model(q) != *zoned_model;
+	return bdev_is_zoned(dev->bdev) != *zoned;
 }
 
 static int device_is_zoned_model(struct dm_target *ti, struct dm_dev *dev,
 				 sector_t start, sector_t len, void *data)
 {
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-
-	return blk_queue_zoned_model(q) != BLK_ZONED_NONE;
+	return bdev_is_zoned(dev->bdev);
 }
 
 /*
@@ -1603,8 +1600,7 @@ static int device_is_zoned_model(struct dm_target *ti, struct dm_dev *dev,
  * has the DM_TARGET_MIXED_ZONED_MODEL feature set, the devices can have any
  * zoned model with all zoned devices having the same zone size.
  */
-static bool dm_table_supports_zoned_model(struct dm_table *t,
-					  enum blk_zoned_model zoned_model)
+static bool dm_table_supports_zoned(struct dm_table *t, bool zoned)
 {
 	for (unsigned int i = 0; i < t->num_targets; i++) {
 		struct dm_target *ti = dm_table_get_target(t, i);
@@ -1623,11 +1619,11 @@ static bool dm_table_supports_zoned_model(struct dm_table *t,
 
 		if (dm_target_supports_zoned_hm(ti->type)) {
 			if (!ti->type->iterate_devices ||
-			    ti->type->iterate_devices(ti, device_not_zoned_model,
-						      &zoned_model))
+			    ti->type->iterate_devices(ti, device_not_zoned,
+						      &zoned))
 				return false;
 		} else if (!dm_target_supports_mixed_zoned_model(ti->type)) {
-			if (zoned_model == BLK_ZONED_HM)
+			if (zoned)
 				return false;
 		}
 	}
@@ -1650,14 +1646,13 @@ static int device_not_matches_zone_sectors(struct dm_target *ti, struct dm_dev *
  * zone sectors, if the destination device is a zoned block device, it shall
  * have the specified zone_sectors.
  */
-static int validate_hardware_zoned_model(struct dm_table *t,
-					 enum blk_zoned_model zoned_model,
-					 unsigned int zone_sectors)
+static int validate_hardware_zoned(struct dm_table *t, bool zoned,
+				   unsigned int zone_sectors)
 {
-	if (zoned_model == BLK_ZONED_NONE)
+	if (!zoned)
 		return 0;
 
-	if (!dm_table_supports_zoned_model(t, zoned_model)) {
+	if (!dm_table_supports_zoned(t, zoned)) {
 		DMERR("%s: zoned model is not consistent across all devices",
 		      dm_device_name(t->md));
 		return -EINVAL;
@@ -1683,8 +1678,8 @@ int dm_calculate_queue_limits(struct dm_table *t,
 			      struct queue_limits *limits)
 {
 	struct queue_limits ti_limits;
-	enum blk_zoned_model zoned_model = BLK_ZONED_NONE;
 	unsigned int zone_sectors = 0;
+	bool zoned = false;
 
 	blk_set_stacking_limits(limits);
 
@@ -1706,12 +1701,12 @@ int dm_calculate_queue_limits(struct dm_table *t,
 		ti->type->iterate_devices(ti, dm_set_device_limits,
 					  &ti_limits);
 
-		if (zoned_model == BLK_ZONED_NONE && ti_limits.zoned != BLK_ZONED_NONE) {
+		if (!zoned && ti_limits.zoned) {
 			/*
 			 * After stacking all limits, validate all devices
 			 * in table support this zoned model and zone sectors.
 			 */
-			zoned_model = ti_limits.zoned;
+			zoned = ti_limits.zoned;
 			zone_sectors = ti_limits.chunk_sectors;
 		}
 
@@ -1744,18 +1739,18 @@ combine_limits:
 	 * Verify that the zoned model and zone sectors, as determined before
 	 * any .io_hints override, are the same across all devices in the table.
 	 * - this is especially relevant if .io_hints is emulating a disk-managed
-	 *   zoned model (aka BLK_ZONED_NONE) on host-managed zoned block devices.
+	 *   zoned model on host-managed zoned block devices.
 	 * BUT...
 	 */
-	if (limits->zoned != BLK_ZONED_NONE) {
+	if (limits->zoned) {
 		/*
 		 * ...IF the above limits stacking determined a zoned model
 		 * validate that all of the table's devices conform to it.
 		 */
-		zoned_model = limits->zoned;
+		zoned = limits->zoned;
 		zone_sectors = limits->chunk_sectors;
 	}
-	if (validate_hardware_zoned_model(t, zoned_model, zone_sectors))
+	if (validate_hardware_zoned(t, zoned, zone_sectors))
 		return -EINVAL;
 
 	return validate_hardware_logical_block_alignment(t, limits);
diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c
index 3ef9f018da60..b475200d8586 100644
--- a/drivers/md/dm-verity-fec.c
+++ b/drivers/md/dm-verity-fec.c
@@ -24,7 +24,8 @@ bool verity_fec_is_enabled(struct dm_verity *v)
  */
 static inline struct dm_verity_fec_io *fec_io(struct dm_verity_io *io)
 {
-	return (struct dm_verity_fec_io *) verity_io_digest_end(io->v, io);
+	return (struct dm_verity_fec_io *)
+		((char *)io + io->v->ti->per_io_data_size - sizeof(struct dm_verity_fec_io));
 }
 
 /*
@@ -185,7 +186,7 @@ static int fec_is_erasure(struct dm_verity *v, struct dm_verity_io *io,
 {
 	if (unlikely(verity_hash(v, verity_io_hash_req(v, io),
 				 data, 1 << v->data_dev_block_bits,
-				 verity_io_real_digest(v, io))))
+				 verity_io_real_digest(v, io), true)))
 		return 0;
 
 	return memcmp(verity_io_real_digest(v, io), want_digest,
@@ -386,7 +387,7 @@ static int fec_decode_rsb(struct dm_verity *v, struct dm_verity_io *io,
 	/* Always re-validate the corrected block against the expected hash */
 	r = verity_hash(v, verity_io_hash_req(v, io), fio->output,
 			1 << v->data_dev_block_bits,
-			verity_io_real_digest(v, io));
+			verity_io_real_digest(v, io), true);
 	if (unlikely(r < 0))
 		return r;
 
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index 26adcfea0302..14e58ae70521 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -135,20 +135,21 @@ static int verity_hash_update(struct dm_verity *v, struct ahash_request *req,
  * Wrapper for crypto_ahash_init, which handles verity salting.
  */
 static int verity_hash_init(struct dm_verity *v, struct ahash_request *req,
-				struct crypto_wait *wait)
+				struct crypto_wait *wait, bool may_sleep)
 {
 	int r;
 
 	ahash_request_set_tfm(req, v->tfm);
-	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP |
-					CRYPTO_TFM_REQ_MAY_BACKLOG,
-					crypto_req_done, (void *)wait);
+	ahash_request_set_callback(req,
+		may_sleep ? CRYPTO_TFM_REQ_MAY_SLEEP | CRYPTO_TFM_REQ_MAY_BACKLOG : 0,
+		crypto_req_done, (void *)wait);
 	crypto_init_wait(wait);
 
 	r = crypto_wait_req(crypto_ahash_init(req), wait);
 
 	if (unlikely(r < 0)) {
-		DMERR("crypto_ahash_init failed: %d", r);
+		if (r != -ENOMEM)
+			DMERR("crypto_ahash_init failed: %d", r);
 		return r;
 	}
 
@@ -179,12 +180,12 @@ out:
 }
 
 int verity_hash(struct dm_verity *v, struct ahash_request *req,
-		const u8 *data, size_t len, u8 *digest)
+		const u8 *data, size_t len, u8 *digest, bool may_sleep)
 {
 	int r;
 	struct crypto_wait wait;
 
-	r = verity_hash_init(v, req, &wait);
+	r = verity_hash_init(v, req, &wait, may_sleep);
 	if (unlikely(r < 0))
 		goto out;
 
@@ -322,7 +323,7 @@ static int verity_verify_level(struct dm_verity *v, struct dm_verity_io *io,
 
 		r = verity_hash(v, verity_io_hash_req(v, io),
 				data, 1 << v->hash_dev_block_bits,
-				verity_io_real_digest(v, io));
+				verity_io_real_digest(v, io), !io->in_tasklet);
 		if (unlikely(r < 0))
 			goto release_ret_r;
 
@@ -556,7 +557,7 @@ static int verity_verify_io(struct dm_verity_io *io)
 			continue;
 		}
 
-		r = verity_hash_init(v, req, &wait);
+		r = verity_hash_init(v, req, &wait, !io->in_tasklet);
 		if (unlikely(r < 0))
 			return r;
 
@@ -641,7 +642,6 @@ static void verity_work(struct work_struct *w)
 
 	io->in_tasklet = false;
 
-	verity_fec_init_io(io);
 	verity_finish_io(io, errno_to_blk_status(verity_verify_io(io)));
 }
 
@@ -652,7 +652,7 @@ static void verity_tasklet(unsigned long data)
 
 	io->in_tasklet = true;
 	err = verity_verify_io(io);
-	if (err == -EAGAIN) {
+	if (err == -EAGAIN || err == -ENOMEM) {
 		/* fallback to retrying with work-queue */
 		INIT_WORK(&io->work, verity_work);
 		queue_work(io->v->verify_wq, &io->work);
@@ -667,7 +667,9 @@ static void verity_end_io(struct bio *bio)
 	struct dm_verity_io *io = bio->bi_private;
 
 	if (bio->bi_status &&
-	    (!verity_fec_is_enabled(io->v) || verity_is_system_shutting_down())) {
+	    (!verity_fec_is_enabled(io->v) ||
+	     verity_is_system_shutting_down() ||
+	     (bio->bi_opf & REQ_RAHEAD))) {
 		verity_finish_io(io, bio->bi_status);
 		return;
 	}
@@ -791,6 +793,8 @@ static int verity_map(struct dm_target *ti, struct bio *bio)
 	bio->bi_private = io;
 	io->iter = bio->bi_iter;
 
+	verity_fec_init_io(io);
+
 	verity_submit_prefetch(v, io);
 
 	submit_bio_noacct(bio);
@@ -1033,7 +1037,7 @@ static int verity_alloc_zero_digest(struct dm_verity *v)
 		goto out;
 
 	r = verity_hash(v, req, zero_data, 1 << v->data_dev_block_bits,
-			v->zero_digest);
+			v->zero_digest, true);
 
 out:
 	kfree(req);
diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h
index 2f555b420367..f9d522c870e6 100644
--- a/drivers/md/dm-verity.h
+++ b/drivers/md/dm-verity.h
@@ -115,12 +115,6 @@ static inline u8 *verity_io_want_digest(struct dm_verity *v,
 	return (u8 *)(io + 1) + v->ahash_reqsize + v->digest_size;
 }
 
-static inline u8 *verity_io_digest_end(struct dm_verity *v,
-				       struct dm_verity_io *io)
-{
-	return verity_io_want_digest(v, io) + v->digest_size;
-}
-
 extern int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io,
 			       struct bvec_iter *iter,
 			       int (*process)(struct dm_verity *v,
@@ -128,7 +122,7 @@ extern int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io,
 					      u8 *data, size_t len));
 
 extern int verity_hash(struct dm_verity *v, struct ahash_request *req,
-		       const u8 *data, size_t len, u8 *digest);
+		       const u8 *data, size_t len, u8 *digest, bool may_sleep);
 
 extern int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io,
 				 sector_t block, u8 *digest, bool *is_zero);
diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
index 60a4dc01ea18..fdfe30f7b697 100644
--- a/drivers/md/dm-zoned-metadata.c
+++ b/drivers/md/dm-zoned-metadata.c
@@ -2836,12 +2836,11 @@ static void dmz_print_dev(struct dmz_metadata *zmd, int num)
 {
 	struct dmz_dev *dev = &zmd->dev[num];
 
-	if (bdev_zoned_model(dev->bdev) == BLK_ZONED_NONE)
+	if (!bdev_is_zoned(dev->bdev))
 		dmz_dev_info(dev, "Regular block device");
 	else
-		dmz_dev_info(dev, "Host-%s zoned block device",
-			     bdev_zoned_model(dev->bdev) == BLK_ZONED_HA ?
-			     "aware" : "managed");
+		dmz_dev_info(dev, "Host-managed zoned block device");
+
 	if (zmd->sb_version > 1) {
 		sector_t sector_offset =
 			dev->zone_offset << zmd->zone_nr_sectors_shift;
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index b487f7acc860..621794a9edd6 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -702,7 +702,7 @@ static int dmz_get_zoned_device(struct dm_target *ti, char *path,
 	}
 
 	bdev = ddev->bdev;
-	if (bdev_zoned_model(bdev) == BLK_ZONED_NONE) {
+	if (!bdev_is_zoned(bdev)) {
 		if (nr_devs == 1) {
 			ti->error = "Invalid regular device";
 			goto err;
@@ -1010,7 +1010,7 @@ static void dmz_io_hints(struct dm_target *ti, struct queue_limits *limits)
 	limits->max_sectors = chunk_sectors;
 
 	/* We are exposing a drive-managed zoned block device */
-	limits->zoned = BLK_ZONED_NONE;
+	limits->zoned = false;
 }
 
 /*
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 23c32cd1f1d8..8dcabf84d866 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2675,7 +2675,7 @@ static int lock_fs(struct mapped_device *md)
 
 	WARN_ON(test_bit(DMF_FROZEN, &md->flags));
 
-	r = freeze_bdev(md->disk->part0);
+	r = bdev_freeze(md->disk->part0);
 	if (!r)
 		set_bit(DMF_FROZEN, &md->flags);
 	return r;
@@ -2685,7 +2685,7 @@ static void unlock_fs(struct mapped_device *md)
 {
 	if (!test_bit(DMF_FROZEN, &md->flags))
 		return;
-	thaw_bdev(md->disk->part0);
+	bdev_thaw(md->disk->part0);
 	clear_bit(DMF_FROZEN, &md->flags);
 }
 
diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c
index 4b80165afd23..b2a00f213c2c 100644
--- a/drivers/md/md-autodetect.c
+++ b/drivers/md/md-autodetect.c
@@ -49,7 +49,6 @@ static int md_setup_ents __initdata;
  *             instead of just one.  -- KTK
  * 18May2000: Added support for persistent-superblock arrays:
  *             md=n,0,factor,fault,device-list   uses RAID0 for device n
- *             md=n,-1,factor,fault,device-list  uses LINEAR for device n
  *             md=n,device-list      reads a RAID superblock from the devices
  *             elements in device-list are read by name_to_kdev_t so can be
  *             a hex number or something like /dev/hda1 /dev/sdb
@@ -88,7 +87,7 @@ static int __init md_setup(char *str)
 		md_setup_ents++;
 	switch (get_option(&str, &level)) {	/* RAID level */
 	case 2: /* could be 0 or -1.. */
-		if (level == 0 || level == LEVEL_LINEAR) {
+		if (level == 0) {
 			if (get_option(&str, &factor) != 2 ||	/* Chunk Size */
 					get_option(&str, &fault) != 2) {
 				printk(KERN_WARNING "md: Too few arguments supplied to md=.\n");
@@ -96,10 +95,7 @@ static int __init md_setup(char *str)
 			}
 			md_setup_args[ent].level = level;
 			md_setup_args[ent].chunk = 1 << (factor+12);
-			if (level ==  LEVEL_LINEAR)
-				pername = "linear";
-			else
-				pername = "raid0";
+			pername = "raid0";
 			break;
 		}
 		fallthrough;
diff --git a/drivers/md/md-faulty.c b/drivers/md/md-faulty.c
deleted file mode 100644
index a039e8e20f55..000000000000
--- a/drivers/md/md-faulty.c
+++ /dev/null
@@ -1,365 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * faulty.c : Multiple Devices driver for Linux
- *
- * Copyright (C) 2004 Neil Brown
- *
- * fautly-device-simulator personality for md
- */
-
-
-/*
- * The "faulty" personality causes some requests to fail.
- *
- * Possible failure modes are:
- *   reads fail "randomly" but succeed on retry
- *   writes fail "randomly" but succeed on retry
- *   reads for some address fail and then persist until a write
- *   reads for some address fail and then persist irrespective of write
- *   writes for some address fail and persist
- *   all writes fail
- *
- * Different modes can be active at a time, but only
- * one can be set at array creation.  Others can be added later.
- * A mode can be one-shot or recurrent with the recurrence being
- * once in every N requests.
- * The bottom 5 bits of the "layout" indicate the mode.  The
- * remainder indicate a period, or 0 for one-shot.
- *
- * There is an implementation limit on the number of concurrently
- * persisting-faulty blocks. When a new fault is requested that would
- * exceed the limit, it is ignored.
- * All current faults can be clear using a layout of "0".
- *
- * Requests are always sent to the device.  If they are to fail,
- * we clone the bio and insert a new b_end_io into the chain.
- */
-
-#define	WriteTransient	0
-#define	ReadTransient	1
-#define	WritePersistent	2
-#define	ReadPersistent	3
-#define	WriteAll	4 /* doesn't go to device */
-#define	ReadFixable	5
-#define	Modes	6
-
-#define	ClearErrors	31
-#define	ClearFaults	30
-
-#define AllPersist	100 /* internal use only */
-#define	NoPersist	101
-
-#define	ModeMask	0x1f
-#define	ModeShift	5
-
-#define MaxFault	50
-#include <linux/blkdev.h>
-#include <linux/module.h>
-#include <linux/raid/md_u.h>
-#include <linux/slab.h>
-#include "md.h"
-#include <linux/seq_file.h>
-
-
-static void faulty_fail(struct bio *bio)
-{
-	struct bio *b = bio->bi_private;
-
-	b->bi_iter.bi_size = bio->bi_iter.bi_size;
-	b->bi_iter.bi_sector = bio->bi_iter.bi_sector;
-
-	bio_put(bio);
-
-	bio_io_error(b);
-}
-
-struct faulty_conf {
-	int period[Modes];
-	atomic_t counters[Modes];
-	sector_t faults[MaxFault];
-	int	modes[MaxFault];
-	int nfaults;
-	struct md_rdev *rdev;
-};
-
-static int check_mode(struct faulty_conf *conf, int mode)
-{
-	if (conf->period[mode] == 0 &&
-	    atomic_read(&conf->counters[mode]) <= 0)
-		return 0; /* no failure, no decrement */
-
-
-	if (atomic_dec_and_test(&conf->counters[mode])) {
-		if (conf->period[mode])
-			atomic_set(&conf->counters[mode], conf->period[mode]);
-		return 1;
-	}
-	return 0;
-}
-
-static int check_sector(struct faulty_conf *conf, sector_t start, sector_t end, int dir)
-{
-	/* If we find a ReadFixable sector, we fix it ... */
-	int i;
-	for (i=0; i<conf->nfaults; i++)
-		if (conf->faults[i] >= start &&
-		    conf->faults[i] < end) {
-			/* found it ... */
-			switch (conf->modes[i] * 2 + dir) {
-			case WritePersistent*2+WRITE: return 1;
-			case ReadPersistent*2+READ: return 1;
-			case ReadFixable*2+READ: return 1;
-			case ReadFixable*2+WRITE:
-				conf->modes[i] = NoPersist;
-				return 0;
-			case AllPersist*2+READ:
-			case AllPersist*2+WRITE: return 1;
-			default:
-				return 0;
-			}
-		}
-	return 0;
-}
-
-static void add_sector(struct faulty_conf *conf, sector_t start, int mode)
-{
-	int i;
-	int n = conf->nfaults;
-	for (i=0; i<conf->nfaults; i++)
-		if (conf->faults[i] == start) {
-			switch(mode) {
-			case NoPersist: conf->modes[i] = mode; return;
-			case WritePersistent:
-				if (conf->modes[i] == ReadPersistent ||
-				    conf->modes[i] == ReadFixable)
-					conf->modes[i] = AllPersist;
-				else
-					conf->modes[i] = WritePersistent;
-				return;
-			case ReadPersistent:
-				if (conf->modes[i] == WritePersistent)
-					conf->modes[i] = AllPersist;
-				else
-					conf->modes[i] = ReadPersistent;
-				return;
-			case ReadFixable:
-				if (conf->modes[i] == WritePersistent ||
-				    conf->modes[i] == ReadPersistent)
-					conf->modes[i] = AllPersist;
-				else
-					conf->modes[i] = ReadFixable;
-				return;
-			}
-		} else if (conf->modes[i] == NoPersist)
-			n = i;
-
-	if (n >= MaxFault)
-		return;
-	conf->faults[n] = start;
-	conf->modes[n] = mode;
-	if (conf->nfaults == n)
-		conf->nfaults = n+1;
-}
-
-static bool faulty_make_request(struct mddev *mddev, struct bio *bio)
-{
-	struct faulty_conf *conf = mddev->private;
-	int failit = 0;
-
-	if (bio_data_dir(bio) == WRITE) {
-		/* write request */
-		if (atomic_read(&conf->counters[WriteAll])) {
-			/* special case - don't decrement, don't submit_bio_noacct,
-			 * just fail immediately
-			 */
-			bio_io_error(bio);
-			return true;
-		}
-
-		if (check_sector(conf, bio->bi_iter.bi_sector,
-				 bio_end_sector(bio), WRITE))
-			failit = 1;
-		if (check_mode(conf, WritePersistent)) {
-			add_sector(conf, bio->bi_iter.bi_sector,
-				   WritePersistent);
-			failit = 1;
-		}
-		if (check_mode(conf, WriteTransient))
-			failit = 1;
-	} else {
-		/* read request */
-		if (check_sector(conf, bio->bi_iter.bi_sector,
-				 bio_end_sector(bio), READ))
-			failit = 1;
-		if (check_mode(conf, ReadTransient))
-			failit = 1;
-		if (check_mode(conf, ReadPersistent)) {
-			add_sector(conf, bio->bi_iter.bi_sector,
-				   ReadPersistent);
-			failit = 1;
-		}
-		if (check_mode(conf, ReadFixable)) {
-			add_sector(conf, bio->bi_iter.bi_sector,
-				   ReadFixable);
-			failit = 1;
-		}
-	}
-
-	md_account_bio(mddev, &bio);
-	if (failit) {
-		struct bio *b = bio_alloc_clone(conf->rdev->bdev, bio, GFP_NOIO,
-						&mddev->bio_set);
-
-		b->bi_private = bio;
-		b->bi_end_io = faulty_fail;
-		bio = b;
-	} else
-		bio_set_dev(bio, conf->rdev->bdev);
-
-	submit_bio_noacct(bio);
-	return true;
-}
-
-static void faulty_status(struct seq_file *seq, struct mddev *mddev)
-{
-	struct faulty_conf *conf = mddev->private;
-	int n;
-
-	if ((n=atomic_read(&conf->counters[WriteTransient])) != 0)
-		seq_printf(seq, " WriteTransient=%d(%d)",
-			   n, conf->period[WriteTransient]);
-
-	if ((n=atomic_read(&conf->counters[ReadTransient])) != 0)
-		seq_printf(seq, " ReadTransient=%d(%d)",
-			   n, conf->period[ReadTransient]);
-
-	if ((n=atomic_read(&conf->counters[WritePersistent])) != 0)
-		seq_printf(seq, " WritePersistent=%d(%d)",
-			   n, conf->period[WritePersistent]);
-
-	if ((n=atomic_read(&conf->counters[ReadPersistent])) != 0)
-		seq_printf(seq, " ReadPersistent=%d(%d)",
-			   n, conf->period[ReadPersistent]);
-
-
-	if ((n=atomic_read(&conf->counters[ReadFixable])) != 0)
-		seq_printf(seq, " ReadFixable=%d(%d)",
-			   n, conf->period[ReadFixable]);
-
-	if ((n=atomic_read(&conf->counters[WriteAll])) != 0)
-		seq_printf(seq, " WriteAll");
-
-	seq_printf(seq, " nfaults=%d", conf->nfaults);
-}
-
-
-static int faulty_reshape(struct mddev *mddev)
-{
-	int mode = mddev->new_layout & ModeMask;
-	int count = mddev->new_layout >> ModeShift;
-	struct faulty_conf *conf = mddev->private;
-
-	if (mddev->new_layout < 0)
-		return 0;
-
-	/* new layout */
-	if (mode == ClearFaults)
-		conf->nfaults = 0;
-	else if (mode == ClearErrors) {
-		int i;
-		for (i=0 ; i < Modes ; i++) {
-			conf->period[i] = 0;
-			atomic_set(&conf->counters[i], 0);
-		}
-	} else if (mode < Modes) {
-		conf->period[mode] = count;
-		if (!count) count++;
-		atomic_set(&conf->counters[mode], count);
-	} else
-		return -EINVAL;
-	mddev->new_layout = -1;
-	mddev->layout = -1; /* makes sure further changes come through */
-	return 0;
-}
-
-static sector_t faulty_size(struct mddev *mddev, sector_t sectors, int raid_disks)
-{
-	WARN_ONCE(raid_disks,
-		  "%s does not support generic reshape\n", __func__);
-
-	if (sectors == 0)
-		return mddev->dev_sectors;
-
-	return sectors;
-}
-
-static int faulty_run(struct mddev *mddev)
-{
-	struct md_rdev *rdev;
-	int i;
-	struct faulty_conf *conf;
-
-	if (md_check_no_bitmap(mddev))
-		return -EINVAL;
-
-	conf = kmalloc(sizeof(*conf), GFP_KERNEL);
-	if (!conf)
-		return -ENOMEM;
-
-	for (i=0; i<Modes; i++) {
-		atomic_set(&conf->counters[i], 0);
-		conf->period[i] = 0;
-	}
-	conf->nfaults = 0;
-
-	rdev_for_each(rdev, mddev) {
-		conf->rdev = rdev;
-		disk_stack_limits(mddev->gendisk, rdev->bdev,
-				  rdev->data_offset << 9);
-	}
-
-	md_set_array_sectors(mddev, faulty_size(mddev, 0, 0));
-	mddev->private = conf;
-
-	faulty_reshape(mddev);
-
-	return 0;
-}
-
-static void faulty_free(struct mddev *mddev, void *priv)
-{
-	struct faulty_conf *conf = priv;
-
-	kfree(conf);
-}
-
-static struct md_personality faulty_personality =
-{
-	.name		= "faulty",
-	.level		= LEVEL_FAULTY,
-	.owner		= THIS_MODULE,
-	.make_request	= faulty_make_request,
-	.run		= faulty_run,
-	.free		= faulty_free,
-	.status		= faulty_status,
-	.check_reshape	= faulty_reshape,
-	.size		= faulty_size,
-};
-
-static int __init raid_init(void)
-{
-	return register_md_personality(&faulty_personality);
-}
-
-static void raid_exit(void)
-{
-	unregister_md_personality(&faulty_personality);
-}
-
-module_init(raid_init);
-module_exit(raid_exit);
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Fault injection personality for MD (deprecated)");
-MODULE_ALIAS("md-personality-10"); /* faulty */
-MODULE_ALIAS("md-faulty");
-MODULE_ALIAS("md-level--5");
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
deleted file mode 100644
index 8eca7693b793..000000000000
--- a/drivers/md/md-linear.c
+++ /dev/null
@@ -1,318 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
-   linear.c : Multiple Devices driver for Linux
-	      Copyright (C) 1994-96 Marc ZYNGIER
-	      <zyngier@ufr-info-p7.ibp.fr> or
-	      <maz@gloups.fdn.fr>
-
-   Linear mode management functions.
-
-*/
-
-#include <linux/blkdev.h>
-#include <linux/raid/md_u.h>
-#include <linux/seq_file.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <trace/events/block.h>
-#include "md.h"
-#include "md-linear.h"
-
-/*
- * find which device holds a particular offset
- */
-static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
-{
-	int lo, mid, hi;
-	struct linear_conf *conf;
-
-	lo = 0;
-	hi = mddev->raid_disks - 1;
-	conf = mddev->private;
-
-	/*
-	 * Binary Search
-	 */
-
-	while (hi > lo) {
-
-		mid = (hi + lo) / 2;
-		if (sector < conf->disks[mid].end_sector)
-			hi = mid;
-		else
-			lo = mid + 1;
-	}
-
-	return conf->disks + lo;
-}
-
-static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disks)
-{
-	struct linear_conf *conf;
-	sector_t array_sectors;
-
-	conf = mddev->private;
-	WARN_ONCE(sectors || raid_disks,
-		  "%s does not support generic reshape\n", __func__);
-	array_sectors = conf->array_sectors;
-
-	return array_sectors;
-}
-
-static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
-{
-	struct linear_conf *conf;
-	struct md_rdev *rdev;
-	int i, cnt;
-
-	conf = kzalloc(struct_size(conf, disks, raid_disks), GFP_KERNEL);
-	if (!conf)
-		return NULL;
-
-	/*
-	 * conf->raid_disks is copy of mddev->raid_disks. The reason to
-	 * keep a copy of mddev->raid_disks in struct linear_conf is,
-	 * mddev->raid_disks may not be consistent with pointers number of
-	 * conf->disks[] when it is updated in linear_add() and used to
-	 * iterate old conf->disks[] earray in linear_congested().
-	 * Here conf->raid_disks is always consitent with number of
-	 * pointers in conf->disks[] array, and mddev->private is updated
-	 * with rcu_assign_pointer() in linear_addr(), such race can be
-	 * avoided.
-	 */
-	conf->raid_disks = raid_disks;
-
-	cnt = 0;
-	conf->array_sectors = 0;
-
-	rdev_for_each(rdev, mddev) {
-		int j = rdev->raid_disk;
-		struct dev_info *disk = conf->disks + j;
-		sector_t sectors;
-
-		if (j < 0 || j >= raid_disks || disk->rdev) {
-			pr_warn("md/linear:%s: disk numbering problem. Aborting!\n",
-				mdname(mddev));
-			goto out;
-		}
-
-		disk->rdev = rdev;
-		if (mddev->chunk_sectors) {
-			sectors = rdev->sectors;
-			sector_div(sectors, mddev->chunk_sectors);
-			rdev->sectors = sectors * mddev->chunk_sectors;
-		}
-
-		disk_stack_limits(mddev->gendisk, rdev->bdev,
-				  rdev->data_offset << 9);
-
-		conf->array_sectors += rdev->sectors;
-		cnt++;
-	}
-	if (cnt != raid_disks) {
-		pr_warn("md/linear:%s: not enough drives present. Aborting!\n",
-			mdname(mddev));
-		goto out;
-	}
-
-	/*
-	 * Here we calculate the device offsets.
-	 */
-	conf->disks[0].end_sector = conf->disks[0].rdev->sectors;
-
-	for (i = 1; i < raid_disks; i++)
-		conf->disks[i].end_sector =
-			conf->disks[i-1].end_sector +
-			conf->disks[i].rdev->sectors;
-
-	return conf;
-
-out:
-	kfree(conf);
-	return NULL;
-}
-
-static int linear_run (struct mddev *mddev)
-{
-	struct linear_conf *conf;
-	int ret;
-
-	if (md_check_no_bitmap(mddev))
-		return -EINVAL;
-	conf = linear_conf(mddev, mddev->raid_disks);
-
-	if (!conf)
-		return 1;
-	mddev->private = conf;
-	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
-
-	ret =  md_integrity_register(mddev);
-	if (ret) {
-		kfree(conf);
-		mddev->private = NULL;
-	}
-	return ret;
-}
-
-static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
-{
-	/* Adding a drive to a linear array allows the array to grow.
-	 * It is permitted if the new drive has a matching superblock
-	 * already on it, with raid_disk equal to raid_disks.
-	 * It is achieved by creating a new linear_private_data structure
-	 * and swapping it in in-place of the current one.
-	 * The current one is never freed until the array is stopped.
-	 * This avoids races.
-	 */
-	struct linear_conf *newconf, *oldconf;
-
-	if (rdev->saved_raid_disk != mddev->raid_disks)
-		return -EINVAL;
-
-	rdev->raid_disk = rdev->saved_raid_disk;
-	rdev->saved_raid_disk = -1;
-
-	newconf = linear_conf(mddev,mddev->raid_disks+1);
-
-	if (!newconf)
-		return -ENOMEM;
-
-	/* newconf->raid_disks already keeps a copy of * the increased
-	 * value of mddev->raid_disks, WARN_ONCE() is just used to make
-	 * sure of this. It is possible that oldconf is still referenced
-	 * in linear_congested(), therefore kfree_rcu() is used to free
-	 * oldconf until no one uses it anymore.
-	 */
-	oldconf = rcu_dereference_protected(mddev->private,
-			lockdep_is_held(&mddev->reconfig_mutex));
-	mddev->raid_disks++;
-	WARN_ONCE(mddev->raid_disks != newconf->raid_disks,
-		"copied raid_disks doesn't match mddev->raid_disks");
-	rcu_assign_pointer(mddev->private, newconf);
-	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
-	set_capacity_and_notify(mddev->gendisk, mddev->array_sectors);
-	kfree_rcu(oldconf, rcu);
-	return 0;
-}
-
-static void linear_free(struct mddev *mddev, void *priv)
-{
-	struct linear_conf *conf = priv;
-
-	kfree(conf);
-}
-
-static bool linear_make_request(struct mddev *mddev, struct bio *bio)
-{
-	struct dev_info *tmp_dev;
-	sector_t start_sector, end_sector, data_offset;
-	sector_t bio_sector = bio->bi_iter.bi_sector;
-
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
-	    && md_flush_request(mddev, bio))
-		return true;
-
-	tmp_dev = which_dev(mddev, bio_sector);
-	start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
-	end_sector = tmp_dev->end_sector;
-	data_offset = tmp_dev->rdev->data_offset;
-
-	if (unlikely(bio_sector >= end_sector ||
-		     bio_sector < start_sector))
-		goto out_of_bounds;
-
-	if (unlikely(is_rdev_broken(tmp_dev->rdev))) {
-		md_error(mddev, tmp_dev->rdev);
-		bio_io_error(bio);
-		return true;
-	}
-
-	if (unlikely(bio_end_sector(bio) > end_sector)) {
-		/* This bio crosses a device boundary, so we have to split it */
-		struct bio *split = bio_split(bio, end_sector - bio_sector,
-					      GFP_NOIO, &mddev->bio_set);
-		bio_chain(split, bio);
-		submit_bio_noacct(bio);
-		bio = split;
-	}
-
-	md_account_bio(mddev, &bio);
-	bio_set_dev(bio, tmp_dev->rdev->bdev);
-	bio->bi_iter.bi_sector = bio->bi_iter.bi_sector -
-		start_sector + data_offset;
-
-	if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
-		     !bdev_max_discard_sectors(bio->bi_bdev))) {
-		/* Just ignore it */
-		bio_endio(bio);
-	} else {
-		if (mddev->gendisk)
-			trace_block_bio_remap(bio, disk_devt(mddev->gendisk),
-					      bio_sector);
-		mddev_check_write_zeroes(mddev, bio);
-		submit_bio_noacct(bio);
-	}
-	return true;
-
-out_of_bounds:
-	pr_err("md/linear:%s: make_request: Sector %llu out of bounds on dev %pg: %llu sectors, offset %llu\n",
-	       mdname(mddev),
-	       (unsigned long long)bio->bi_iter.bi_sector,
-	       tmp_dev->rdev->bdev,
-	       (unsigned long long)tmp_dev->rdev->sectors,
-	       (unsigned long long)start_sector);
-	bio_io_error(bio);
-	return true;
-}
-
-static void linear_status (struct seq_file *seq, struct mddev *mddev)
-{
-	seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2);
-}
-
-static void linear_error(struct mddev *mddev, struct md_rdev *rdev)
-{
-	if (!test_and_set_bit(MD_BROKEN, &mddev->flags)) {
-		char *md_name = mdname(mddev);
-
-		pr_crit("md/linear%s: Disk failure on %pg detected, failing array.\n",
-			md_name, rdev->bdev);
-	}
-}
-
-static void linear_quiesce(struct mddev *mddev, int state)
-{
-}
-
-static struct md_personality linear_personality =
-{
-	.name		= "linear",
-	.level		= LEVEL_LINEAR,
-	.owner		= THIS_MODULE,
-	.make_request	= linear_make_request,
-	.run		= linear_run,
-	.free		= linear_free,
-	.status		= linear_status,
-	.hot_add_disk	= linear_add,
-	.size		= linear_size,
-	.quiesce	= linear_quiesce,
-	.error_handler	= linear_error,
-};
-
-static int __init linear_init (void)
-{
-	return register_md_personality (&linear_personality);
-}
-
-static void linear_exit (void)
-{
-	unregister_md_personality (&linear_personality);
-}
-
-module_init(linear_init);
-module_exit(linear_exit);
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Linear device concatenation personality for MD (deprecated)");
-MODULE_ALIAS("md-personality-1"); /* LINEAR - deprecated*/
-MODULE_ALIAS("md-linear");
-MODULE_ALIAS("md-level--1");
diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c
deleted file mode 100644
index d22276870283..000000000000
--- a/drivers/md/md-multipath.c
+++ /dev/null
@@ -1,471 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * multipath.c : Multiple Devices driver for Linux
- *
- * Copyright (C) 1999, 2000, 2001 Ingo Molnar, Red Hat
- *
- * Copyright (C) 1996, 1997, 1998 Ingo Molnar, Miguel de Icaza, Gadi Oxman
- *
- * MULTIPATH management functions.
- *
- * derived from raid1.c.
- */
-
-#include <linux/blkdev.h>
-#include <linux/module.h>
-#include <linux/raid/md_u.h>
-#include <linux/seq_file.h>
-#include <linux/slab.h>
-#include "md.h"
-#include "md-multipath.h"
-
-#define MAX_WORK_PER_DISK 128
-
-#define	NR_RESERVED_BUFS	32
-
-static int multipath_map (struct mpconf *conf)
-{
-	int i, disks = conf->raid_disks;
-
-	/*
-	 * Later we do read balancing on the read side
-	 * now we use the first available disk.
-	 */
-
-	rcu_read_lock();
-	for (i = 0; i < disks; i++) {
-		struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev);
-		if (rdev && test_bit(In_sync, &rdev->flags) &&
-		    !test_bit(Faulty, &rdev->flags)) {
-			atomic_inc(&rdev->nr_pending);
-			rcu_read_unlock();
-			return i;
-		}
-	}
-	rcu_read_unlock();
-
-	pr_crit_ratelimited("multipath_map(): no more operational IO paths?\n");
-	return (-1);
-}
-
-static void multipath_reschedule_retry (struct multipath_bh *mp_bh)
-{
-	unsigned long flags;
-	struct mddev *mddev = mp_bh->mddev;
-	struct mpconf *conf = mddev->private;
-
-	spin_lock_irqsave(&conf->device_lock, flags);
-	list_add(&mp_bh->retry_list, &conf->retry_list);
-	spin_unlock_irqrestore(&conf->device_lock, flags);
-	md_wakeup_thread(mddev->thread);
-}
-
-/*
- * multipath_end_bh_io() is called when we have finished servicing a multipathed
- * operation and are ready to return a success/failure code to the buffer
- * cache layer.
- */
-static void multipath_end_bh_io(struct multipath_bh *mp_bh, blk_status_t status)
-{
-	struct bio *bio = mp_bh->master_bio;
-	struct mpconf *conf = mp_bh->mddev->private;
-
-	bio->bi_status = status;
-	bio_endio(bio);
-	mempool_free(mp_bh, &conf->pool);
-}
-
-static void multipath_end_request(struct bio *bio)
-{
-	struct multipath_bh *mp_bh = bio->bi_private;
-	struct mpconf *conf = mp_bh->mddev->private;
-	struct md_rdev *rdev = conf->multipaths[mp_bh->path].rdev;
-
-	if (!bio->bi_status)
-		multipath_end_bh_io(mp_bh, 0);
-	else if (!(bio->bi_opf & REQ_RAHEAD)) {
-		/*
-		 * oops, IO error:
-		 */
-		md_error (mp_bh->mddev, rdev);
-		pr_info("multipath: %pg: rescheduling sector %llu\n",
-			rdev->bdev,
-			(unsigned long long)bio->bi_iter.bi_sector);
-		multipath_reschedule_retry(mp_bh);
-	} else
-		multipath_end_bh_io(mp_bh, bio->bi_status);
-	rdev_dec_pending(rdev, conf->mddev);
-}
-
-static bool multipath_make_request(struct mddev *mddev, struct bio * bio)
-{
-	struct mpconf *conf = mddev->private;
-	struct multipath_bh * mp_bh;
-	struct multipath_info *multipath;
-
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
-	    && md_flush_request(mddev, bio))
-		return true;
-
-	md_account_bio(mddev, &bio);
-	mp_bh = mempool_alloc(&conf->pool, GFP_NOIO);
-
-	mp_bh->master_bio = bio;
-	mp_bh->mddev = mddev;
-
-	mp_bh->path = multipath_map(conf);
-	if (mp_bh->path < 0) {
-		bio_io_error(bio);
-		mempool_free(mp_bh, &conf->pool);
-		return true;
-	}
-	multipath = conf->multipaths + mp_bh->path;
-
-	bio_init_clone(multipath->rdev->bdev, &mp_bh->bio, bio, GFP_NOIO);
-
-	mp_bh->bio.bi_iter.bi_sector += multipath->rdev->data_offset;
-	mp_bh->bio.bi_opf |= REQ_FAILFAST_TRANSPORT;
-	mp_bh->bio.bi_end_io = multipath_end_request;
-	mp_bh->bio.bi_private = mp_bh;
-	mddev_check_write_zeroes(mddev, &mp_bh->bio);
-	submit_bio_noacct(&mp_bh->bio);
-	return true;
-}
-
-static void multipath_status(struct seq_file *seq, struct mddev *mddev)
-{
-	struct mpconf *conf = mddev->private;
-	int i;
-
-	seq_printf (seq, " [%d/%d] [", conf->raid_disks,
-		    conf->raid_disks - mddev->degraded);
-	rcu_read_lock();
-	for (i = 0; i < conf->raid_disks; i++) {
-		struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev);
-		seq_printf (seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_");
-	}
-	rcu_read_unlock();
-	seq_putc(seq, ']');
-}
-
-/*
- * Careful, this can execute in IRQ contexts as well!
- */
-static void multipath_error (struct mddev *mddev, struct md_rdev *rdev)
-{
-	struct mpconf *conf = mddev->private;
-
-	if (conf->raid_disks - mddev->degraded <= 1) {
-		/*
-		 * Uh oh, we can do nothing if this is our last path, but
-		 * first check if this is a queued request for a device
-		 * which has just failed.
-		 */
-		pr_warn("multipath: only one IO path left and IO error.\n");
-		/* leave it active... it's all we have */
-		return;
-	}
-	/*
-	 * Mark disk as unusable
-	 */
-	if (test_and_clear_bit(In_sync, &rdev->flags)) {
-		unsigned long flags;
-		spin_lock_irqsave(&conf->device_lock, flags);
-		mddev->degraded++;
-		spin_unlock_irqrestore(&conf->device_lock, flags);
-	}
-	set_bit(Faulty, &rdev->flags);
-	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
-	pr_err("multipath: IO failure on %pg, disabling IO path.\n"
-	       "multipath: Operation continuing on %d IO paths.\n",
-	       rdev->bdev,
-	       conf->raid_disks - mddev->degraded);
-}
-
-static void print_multipath_conf (struct mpconf *conf)
-{
-	int i;
-	struct multipath_info *tmp;
-
-	pr_debug("MULTIPATH conf printout:\n");
-	if (!conf) {
-		pr_debug("(conf==NULL)\n");
-		return;
-	}
-	pr_debug(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
-		 conf->raid_disks);
-
-	for (i = 0; i < conf->raid_disks; i++) {
-		tmp = conf->multipaths + i;
-		if (tmp->rdev)
-			pr_debug(" disk%d, o:%d, dev:%pg\n",
-				 i,!test_bit(Faulty, &tmp->rdev->flags),
-				 tmp->rdev->bdev);
-	}
-}
-
-static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev)
-{
-	struct mpconf *conf = mddev->private;
-	int err = -EEXIST;
-	int path;
-	struct multipath_info *p;
-	int first = 0;
-	int last = mddev->raid_disks - 1;
-
-	if (rdev->raid_disk >= 0)
-		first = last = rdev->raid_disk;
-
-	print_multipath_conf(conf);
-
-	for (path = first; path <= last; path++)
-		if ((p=conf->multipaths+path)->rdev == NULL) {
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-
-			err = md_integrity_add_rdev(rdev, mddev);
-			if (err)
-				break;
-			spin_lock_irq(&conf->device_lock);
-			mddev->degraded--;
-			rdev->raid_disk = path;
-			set_bit(In_sync, &rdev->flags);
-			spin_unlock_irq(&conf->device_lock);
-			rcu_assign_pointer(p->rdev, rdev);
-			err = 0;
-			break;
-		}
-
-	print_multipath_conf(conf);
-
-	return err;
-}
-
-static int multipath_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
-{
-	struct mpconf *conf = mddev->private;
-	int err = 0;
-	int number = rdev->raid_disk;
-	struct multipath_info *p = conf->multipaths + number;
-
-	print_multipath_conf(conf);
-
-	if (rdev == p->rdev) {
-		if (test_bit(In_sync, &rdev->flags) ||
-		    atomic_read(&rdev->nr_pending)) {
-			pr_warn("hot-remove-disk, slot %d is identified but is still operational!\n", number);
-			err = -EBUSY;
-			goto abort;
-		}
-		p->rdev = NULL;
-		if (!test_bit(RemoveSynchronized, &rdev->flags)) {
-			synchronize_rcu();
-			if (atomic_read(&rdev->nr_pending)) {
-				/* lost the race, try later */
-				err = -EBUSY;
-				p->rdev = rdev;
-				goto abort;
-			}
-		}
-		err = md_integrity_register(mddev);
-	}
-abort:
-
-	print_multipath_conf(conf);
-	return err;
-}
-
-/*
- * This is a kernel thread which:
- *
- *	1.	Retries failed read operations on working multipaths.
- *	2.	Updates the raid superblock when problems encounter.
- *	3.	Performs writes following reads for array syncronising.
- */
-
-static void multipathd(struct md_thread *thread)
-{
-	struct mddev *mddev = thread->mddev;
-	struct multipath_bh *mp_bh;
-	struct bio *bio;
-	unsigned long flags;
-	struct mpconf *conf = mddev->private;
-	struct list_head *head = &conf->retry_list;
-
-	md_check_recovery(mddev);
-	for (;;) {
-		spin_lock_irqsave(&conf->device_lock, flags);
-		if (list_empty(head))
-			break;
-		mp_bh = list_entry(head->prev, struct multipath_bh, retry_list);
-		list_del(head->prev);
-		spin_unlock_irqrestore(&conf->device_lock, flags);
-
-		bio = &mp_bh->bio;
-		bio->bi_iter.bi_sector = mp_bh->master_bio->bi_iter.bi_sector;
-
-		if ((mp_bh->path = multipath_map (conf))<0) {
-			pr_err("multipath: %pg: unrecoverable IO read error for block %llu\n",
-			       bio->bi_bdev,
-			       (unsigned long long)bio->bi_iter.bi_sector);
-			multipath_end_bh_io(mp_bh, BLK_STS_IOERR);
-		} else {
-			pr_err("multipath: %pg: redirecting sector %llu to another IO path\n",
-			       bio->bi_bdev,
-			       (unsigned long long)bio->bi_iter.bi_sector);
-			*bio = *(mp_bh->master_bio);
-			bio->bi_iter.bi_sector +=
-				conf->multipaths[mp_bh->path].rdev->data_offset;
-			bio_set_dev(bio, conf->multipaths[mp_bh->path].rdev->bdev);
-			bio->bi_opf |= REQ_FAILFAST_TRANSPORT;
-			bio->bi_end_io = multipath_end_request;
-			bio->bi_private = mp_bh;
-			submit_bio_noacct(bio);
-		}
-	}
-	spin_unlock_irqrestore(&conf->device_lock, flags);
-}
-
-static sector_t multipath_size(struct mddev *mddev, sector_t sectors, int raid_disks)
-{
-	WARN_ONCE(sectors || raid_disks,
-		  "%s does not support generic reshape\n", __func__);
-
-	return mddev->dev_sectors;
-}
-
-static int multipath_run (struct mddev *mddev)
-{
-	struct mpconf *conf;
-	int disk_idx;
-	struct multipath_info *disk;
-	struct md_rdev *rdev;
-	int working_disks;
-	int ret;
-
-	if (md_check_no_bitmap(mddev))
-		return -EINVAL;
-
-	if (mddev->level != LEVEL_MULTIPATH) {
-		pr_warn("multipath: %s: raid level not set to multipath IO (%d)\n",
-			mdname(mddev), mddev->level);
-		goto out;
-	}
-	/*
-	 * copy the already verified devices into our private MULTIPATH
-	 * bookkeeping area. [whatever we allocate in multipath_run(),
-	 * should be freed in multipath_free()]
-	 */
-
-	conf = kzalloc(sizeof(struct mpconf), GFP_KERNEL);
-	mddev->private = conf;
-	if (!conf)
-		goto out;
-
-	conf->multipaths = kcalloc(mddev->raid_disks,
-				   sizeof(struct multipath_info),
-				   GFP_KERNEL);
-	if (!conf->multipaths)
-		goto out_free_conf;
-
-	working_disks = 0;
-	rdev_for_each(rdev, mddev) {
-		disk_idx = rdev->raid_disk;
-		if (disk_idx < 0 ||
-		    disk_idx >= mddev->raid_disks)
-			continue;
-
-		disk = conf->multipaths + disk_idx;
-		disk->rdev = rdev;
-		disk_stack_limits(mddev->gendisk, rdev->bdev,
-				  rdev->data_offset << 9);
-
-		if (!test_bit(Faulty, &rdev->flags))
-			working_disks++;
-	}
-
-	conf->raid_disks = mddev->raid_disks;
-	conf->mddev = mddev;
-	spin_lock_init(&conf->device_lock);
-	INIT_LIST_HEAD(&conf->retry_list);
-
-	if (!working_disks) {
-		pr_warn("multipath: no operational IO paths for %s\n",
-			mdname(mddev));
-		goto out_free_conf;
-	}
-	mddev->degraded = conf->raid_disks - working_disks;
-
-	ret = mempool_init_kmalloc_pool(&conf->pool, NR_RESERVED_BUFS,
-					sizeof(struct multipath_bh));
-	if (ret)
-		goto out_free_conf;
-
-	rcu_assign_pointer(mddev->thread,
-			   md_register_thread(multipathd, mddev, "multipath"));
-	if (!mddev->thread)
-		goto out_free_conf;
-
-	pr_info("multipath: array %s active with %d out of %d IO paths\n",
-		mdname(mddev), conf->raid_disks - mddev->degraded,
-		mddev->raid_disks);
-	/*
-	 * Ok, everything is just fine now
-	 */
-	md_set_array_sectors(mddev, multipath_size(mddev, 0, 0));
-
-	if (md_integrity_register(mddev))
-		goto out_free_conf;
-
-	return 0;
-
-out_free_conf:
-	mempool_exit(&conf->pool);
-	kfree(conf->multipaths);
-	kfree(conf);
-	mddev->private = NULL;
-out:
-	return -EIO;
-}
-
-static void multipath_free(struct mddev *mddev, void *priv)
-{
-	struct mpconf *conf = priv;
-
-	mempool_exit(&conf->pool);
-	kfree(conf->multipaths);
-	kfree(conf);
-}
-
-static struct md_personality multipath_personality =
-{
-	.name		= "multipath",
-	.level		= LEVEL_MULTIPATH,
-	.owner		= THIS_MODULE,
-	.make_request	= multipath_make_request,
-	.run		= multipath_run,
-	.free		= multipath_free,
-	.status		= multipath_status,
-	.error_handler	= multipath_error,
-	.hot_add_disk	= multipath_add_disk,
-	.hot_remove_disk= multipath_remove_disk,
-	.size		= multipath_size,
-};
-
-static int __init multipath_init (void)
-{
-	return register_md_personality (&multipath_personality);
-}
-
-static void __exit multipath_exit (void)
-{
-	unregister_md_personality (&multipath_personality);
-}
-
-module_init(multipath_init);
-module_exit(multipath_exit);
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("simple multi-path personality for MD (deprecated)");
-MODULE_ALIAS("md-personality-7"); /* MULTIPATH */
-MODULE_ALIAS("md-multipath");
-MODULE_ALIAS("md-level--4");
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 4ee4593c874a..0a2bd72a6d76 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -82,6 +82,14 @@ static struct module *md_cluster_mod;
 
 static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
 static struct workqueue_struct *md_wq;
+
+/*
+ * This workqueue is used for sync_work to register new sync_thread, and for
+ * del_work to remove rdev, and for event_work that is only set by dm-raid.
+ *
+ * Noted that sync_work will grab reconfig_mutex, hence never flush this
+ * workqueue whith reconfig_mutex grabbed.
+ */
 static struct workqueue_struct *md_misc_wq;
 struct workqueue_struct *md_bitmap_wq;
 
@@ -490,7 +498,7 @@ int mddev_suspend(struct mddev *mddev, bool interruptible)
 }
 EXPORT_SYMBOL_GPL(mddev_suspend);
 
-void mddev_resume(struct mddev *mddev)
+static void __mddev_resume(struct mddev *mddev, bool recovery_needed)
 {
 	lockdep_assert_not_held(&mddev->reconfig_mutex);
 
@@ -507,12 +515,18 @@ void mddev_resume(struct mddev *mddev)
 	percpu_ref_resurrect(&mddev->active_io);
 	wake_up(&mddev->sb_wait);
 
-	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	if (recovery_needed)
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
 	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 
 	mutex_unlock(&mddev->suspend_mutex);
 }
+
+void mddev_resume(struct mddev *mddev)
+{
+	return __mddev_resume(mddev, true);
+}
 EXPORT_SYMBOL_GPL(mddev_resume);
 
 /*
@@ -529,6 +543,9 @@ static void md_end_flush(struct bio *bio)
 	rdev_dec_pending(rdev, mddev);
 
 	if (atomic_dec_and_test(&mddev->flush_pending)) {
+		/* The pair is percpu_ref_get() from md_flush_request() */
+		percpu_ref_put(&mddev->active_io);
+
 		/* The pre-request flush has finished */
 		queue_work(md_wq, &mddev->flush_work);
 	}
@@ -548,12 +565,8 @@ static void submit_flushes(struct work_struct *ws)
 	rdev_for_each_rcu(rdev, mddev)
 		if (rdev->raid_disk >= 0 &&
 		    !test_bit(Faulty, &rdev->flags)) {
-			/* Take two references, one is dropped
-			 * when request finishes, one after
-			 * we reclaim rcu_read_lock
-			 */
 			struct bio *bi;
-			atomic_inc(&rdev->nr_pending);
+
 			atomic_inc(&rdev->nr_pending);
 			rcu_read_unlock();
 			bi = bio_alloc_bioset(rdev->bdev, 0,
@@ -564,7 +577,6 @@ static void submit_flushes(struct work_struct *ws)
 			atomic_inc(&mddev->flush_pending);
 			submit_bio(bi);
 			rcu_read_lock();
-			rdev_dec_pending(rdev, mddev);
 		}
 	rcu_read_unlock();
 	if (atomic_dec_and_test(&mddev->flush_pending))
@@ -617,6 +629,18 @@ bool md_flush_request(struct mddev *mddev, struct bio *bio)
 	/* new request after previous flush is completed */
 	if (ktime_after(req_start, mddev->prev_flush_start)) {
 		WARN_ON(mddev->flush_bio);
+		/*
+		 * Grab a reference to make sure mddev_suspend() will wait for
+		 * this flush to be done.
+		 *
+		 * md_flush_reqeust() is called under md_handle_request() and
+		 * 'active_io' is already grabbed, hence percpu_ref_is_zero()
+		 * won't pass, percpu_ref_tryget_live() can't be used because
+		 * percpu_ref_kill() can be called by mddev_suspend()
+		 * concurrently.
+		 */
+		WARN_ON(percpu_ref_is_zero(&mddev->active_io));
+		percpu_ref_get(&mddev->active_io);
 		mddev->flush_bio = bio;
 		bio = NULL;
 	}
@@ -1013,9 +1037,10 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
 		return;
 
 	bio = bio_alloc_bioset(rdev->meta_bdev ? rdev->meta_bdev : rdev->bdev,
-			       1,
-			       REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH | REQ_FUA,
-			       GFP_NOIO, &mddev->sync_set);
+			      1,
+			      REQ_OP_WRITE | REQ_SYNC | REQ_IDLE | REQ_META
+				  | REQ_PREFLUSH | REQ_FUA,
+			      GFP_NOIO, &mddev->sync_set);
 
 	atomic_inc(&rdev->nr_pending);
 
@@ -1195,6 +1220,7 @@ struct super_type  {
 					  struct md_rdev *refdev,
 					  int minor_version);
 	int		    (*validate_super)(struct mddev *mddev,
+					      struct md_rdev *freshest,
 					      struct md_rdev *rdev);
 	void		    (*sync_super)(struct mddev *mddev,
 					  struct md_rdev *rdev);
@@ -1275,17 +1301,11 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 	rdev->sb_size = MD_SB_BYTES;
 	rdev->badblocks.shift = -1;
 
-	if (sb->level == LEVEL_MULTIPATH)
-		rdev->desc_nr = -1;
-	else
-		rdev->desc_nr = sb->this_disk.number;
-
-	/* not spare disk, or LEVEL_MULTIPATH */
-	if (sb->level == LEVEL_MULTIPATH ||
-		(rdev->desc_nr >= 0 &&
-		 rdev->desc_nr < MD_SB_DISKS &&
-		 sb->disks[rdev->desc_nr].state &
-		 ((1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE))))
+	rdev->desc_nr = sb->this_disk.number;
+
+	/* not spare disk */
+	if (rdev->desc_nr >= 0 && rdev->desc_nr < MD_SB_DISKS &&
+	    sb->disks[rdev->desc_nr].state & ((1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE)))
 		spare_disk = false;
 
 	if (!refdev) {
@@ -1332,8 +1352,9 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 
 /*
  * validate_super for 0.90.0
+ * note: we are not using "freshest" for 0.9 superblock
  */
-static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev)
+static int super_90_validate(struct mddev *mddev, struct md_rdev *freshest, struct md_rdev *rdev)
 {
 	mdp_disk_t *desc;
 	mdp_super_t *sb = page_address(rdev->sb_page);
@@ -1431,31 +1452,28 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev)
 			return 0;
 	}
 
-	if (mddev->level != LEVEL_MULTIPATH) {
-		desc = sb->disks + rdev->desc_nr;
+	desc = sb->disks + rdev->desc_nr;
 
-		if (desc->state & (1<<MD_DISK_FAULTY))
-			set_bit(Faulty, &rdev->flags);
-		else if (desc->state & (1<<MD_DISK_SYNC) /* &&
-			    desc->raid_disk < mddev->raid_disks */) {
-			set_bit(In_sync, &rdev->flags);
+	if (desc->state & (1<<MD_DISK_FAULTY))
+		set_bit(Faulty, &rdev->flags);
+	else if (desc->state & (1<<MD_DISK_SYNC)) {
+		set_bit(In_sync, &rdev->flags);
+		rdev->raid_disk = desc->raid_disk;
+		rdev->saved_raid_disk = desc->raid_disk;
+	} else if (desc->state & (1<<MD_DISK_ACTIVE)) {
+		/* active but not in sync implies recovery up to
+		 * reshape position.  We don't know exactly where
+		 * that is, so set to zero for now
+		 */
+		if (mddev->minor_version >= 91) {
+			rdev->recovery_offset = 0;
 			rdev->raid_disk = desc->raid_disk;
-			rdev->saved_raid_disk = desc->raid_disk;
-		} else if (desc->state & (1<<MD_DISK_ACTIVE)) {
-			/* active but not in sync implies recovery up to
-			 * reshape position.  We don't know exactly where
-			 * that is, so set to zero for now */
-			if (mddev->minor_version >= 91) {
-				rdev->recovery_offset = 0;
-				rdev->raid_disk = desc->raid_disk;
-			}
 		}
-		if (desc->state & (1<<MD_DISK_WRITEMOSTLY))
-			set_bit(WriteMostly, &rdev->flags);
-		if (desc->state & (1<<MD_DISK_FAILFAST))
-			set_bit(FailFast, &rdev->flags);
-	} else /* MULTIPATH are always insync */
-		set_bit(In_sync, &rdev->flags);
+	}
+	if (desc->state & (1<<MD_DISK_WRITEMOSTLY))
+		set_bit(WriteMostly, &rdev->flags);
+	if (desc->state & (1<<MD_DISK_FAILFAST))
+		set_bit(FailFast, &rdev->flags);
 	return 0;
 }
 
@@ -1745,10 +1763,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 	    && rdev->new_data_offset < sb_start + (rdev->sb_size/512))
 		return -EINVAL;
 
-	if (sb->level == cpu_to_le32(LEVEL_MULTIPATH))
-		rdev->desc_nr = -1;
-	else
-		rdev->desc_nr = le32_to_cpu(sb->dev_number);
+	rdev->desc_nr = le32_to_cpu(sb->dev_number);
 
 	if (!rdev->bb_page) {
 		rdev->bb_page = alloc_page(GFP_KERNEL);
@@ -1801,12 +1816,10 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 	    sb->level != 0)
 		return -EINVAL;
 
-	/* not spare disk, or LEVEL_MULTIPATH */
-	if (sb->level == cpu_to_le32(LEVEL_MULTIPATH) ||
-		(rdev->desc_nr >= 0 &&
-		rdev->desc_nr < le32_to_cpu(sb->max_dev) &&
-		(le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX ||
-		 le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL)))
+	/* not spare disk */
+	if (rdev->desc_nr >= 0 && rdev->desc_nr < le32_to_cpu(sb->max_dev) &&
+	    (le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX ||
+	     le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL))
 		spare_disk = false;
 
 	if (!refdev) {
@@ -1845,10 +1858,11 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 	return ret;
 }
 
-static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
+static int super_1_validate(struct mddev *mddev, struct md_rdev *freshest, struct md_rdev *rdev)
 {
 	struct mdp_superblock_1 *sb = page_address(rdev->sb_page);
 	__u64 ev1 = le64_to_cpu(sb->events);
+	int role;
 
 	rdev->raid_disk = -1;
 	clear_bit(Faulty, &rdev->flags);
@@ -1941,13 +1955,15 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
 		}
 	} else if (mddev->pers == NULL) {
 		/* Insist of good event counter while assembling, except for
-		 * spares (which don't need an event count) */
-		++ev1;
+		 * spares (which don't need an event count).
+		 * Similar to mdadm, we allow event counter difference of 1
+		 * from the freshest device.
+		 */
 		if (rdev->desc_nr >= 0 &&
 		    rdev->desc_nr < le32_to_cpu(sb->max_dev) &&
 		    (le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX ||
 		     le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL))
-			if (ev1 < mddev->events)
+			if (ev1 + 1 < mddev->events)
 				return -EINVAL;
 	} else if (mddev->bitmap) {
 		/* If adding to array with a bitmap, then we can accept an
@@ -1962,58 +1978,85 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
 			/* just a hot-add of a new device, leave raid_disk at -1 */
 			return 0;
 	}
-	if (mddev->level != LEVEL_MULTIPATH) {
-		int role;
-		if (rdev->desc_nr < 0 ||
-		    rdev->desc_nr >= le32_to_cpu(sb->max_dev)) {
-			role = MD_DISK_ROLE_SPARE;
-			rdev->desc_nr = -1;
-		} else
-			role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
-		switch(role) {
-		case MD_DISK_ROLE_SPARE: /* spare */
-			break;
-		case MD_DISK_ROLE_FAULTY: /* faulty */
-			set_bit(Faulty, &rdev->flags);
-			break;
-		case MD_DISK_ROLE_JOURNAL: /* journal device */
-			if (!(le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)) {
-				/* journal device without journal feature */
-				pr_warn("md: journal device provided without journal feature, ignoring the device\n");
-				return -EINVAL;
-			}
-			set_bit(Journal, &rdev->flags);
-			rdev->journal_tail = le64_to_cpu(sb->journal_tail);
-			rdev->raid_disk = 0;
-			break;
-		default:
-			rdev->saved_raid_disk = role;
-			if ((le32_to_cpu(sb->feature_map) &
-			     MD_FEATURE_RECOVERY_OFFSET)) {
-				rdev->recovery_offset = le64_to_cpu(sb->recovery_offset);
-				if (!(le32_to_cpu(sb->feature_map) &
-				      MD_FEATURE_RECOVERY_BITMAP))
-					rdev->saved_raid_disk = -1;
-			} else {
-				/*
-				 * If the array is FROZEN, then the device can't
-				 * be in_sync with rest of array.
-				 */
-				if (!test_bit(MD_RECOVERY_FROZEN,
-					      &mddev->recovery))
-					set_bit(In_sync, &rdev->flags);
-			}
-			rdev->raid_disk = role;
-			break;
+
+	if (rdev->desc_nr < 0 ||
+	    rdev->desc_nr >= le32_to_cpu(sb->max_dev)) {
+		role = MD_DISK_ROLE_SPARE;
+		rdev->desc_nr = -1;
+	} else if (mddev->pers == NULL && freshest && ev1 < mddev->events) {
+		/*
+		 * If we are assembling, and our event counter is smaller than the
+		 * highest event counter, we cannot trust our superblock about the role.
+		 * It could happen that our rdev was marked as Faulty, and all other
+		 * superblocks were updated with +1 event counter.
+		 * Then, before the next superblock update, which typically happens when
+		 * remove_and_add_spares() removes the device from the array, there was
+		 * a crash or reboot.
+		 * If we allow current rdev without consulting the freshest superblock,
+		 * we could cause data corruption.
+		 * Note that in this case our event counter is smaller by 1 than the
+		 * highest, otherwise, this rdev would not be allowed into array;
+		 * both kernel and mdadm allow event counter difference of 1.
+		 */
+		struct mdp_superblock_1 *freshest_sb = page_address(freshest->sb_page);
+		u32 freshest_max_dev = le32_to_cpu(freshest_sb->max_dev);
+
+		if (rdev->desc_nr >= freshest_max_dev) {
+			/* this is unexpected, better not proceed */
+			pr_warn("md: %s: rdev[%pg]: desc_nr(%d) >= freshest(%pg)->sb->max_dev(%u)\n",
+				mdname(mddev), rdev->bdev, rdev->desc_nr,
+				freshest->bdev, freshest_max_dev);
+			return -EUCLEAN;
 		}
-		if (sb->devflags & WriteMostly1)
-			set_bit(WriteMostly, &rdev->flags);
-		if (sb->devflags & FailFast1)
-			set_bit(FailFast, &rdev->flags);
-		if (le32_to_cpu(sb->feature_map) & MD_FEATURE_REPLACEMENT)
-			set_bit(Replacement, &rdev->flags);
-	} else /* MULTIPATH are always insync */
-		set_bit(In_sync, &rdev->flags);
+
+		role = le16_to_cpu(freshest_sb->dev_roles[rdev->desc_nr]);
+		pr_debug("md: %s: rdev[%pg]: role=%d(0x%x) according to freshest %pg\n",
+			 mdname(mddev), rdev->bdev, role, role, freshest->bdev);
+	} else {
+		role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
+	}
+	switch (role) {
+	case MD_DISK_ROLE_SPARE: /* spare */
+		break;
+	case MD_DISK_ROLE_FAULTY: /* faulty */
+		set_bit(Faulty, &rdev->flags);
+		break;
+	case MD_DISK_ROLE_JOURNAL: /* journal device */
+		if (!(le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)) {
+			/* journal device without journal feature */
+			pr_warn("md: journal device provided without journal feature, ignoring the device\n");
+			return -EINVAL;
+		}
+		set_bit(Journal, &rdev->flags);
+		rdev->journal_tail = le64_to_cpu(sb->journal_tail);
+		rdev->raid_disk = 0;
+		break;
+	default:
+		rdev->saved_raid_disk = role;
+		if ((le32_to_cpu(sb->feature_map) &
+		     MD_FEATURE_RECOVERY_OFFSET)) {
+			rdev->recovery_offset = le64_to_cpu(sb->recovery_offset);
+			if (!(le32_to_cpu(sb->feature_map) &
+			      MD_FEATURE_RECOVERY_BITMAP))
+				rdev->saved_raid_disk = -1;
+		} else {
+			/*
+			 * If the array is FROZEN, then the device can't
+			 * be in_sync with rest of array.
+			 */
+			if (!test_bit(MD_RECOVERY_FROZEN,
+				      &mddev->recovery))
+				set_bit(In_sync, &rdev->flags);
+		}
+		rdev->raid_disk = role;
+		break;
+	}
+	if (sb->devflags & WriteMostly1)
+		set_bit(WriteMostly, &rdev->flags);
+	if (sb->devflags & FailFast1)
+		set_bit(FailFast, &rdev->flags);
+	if (le32_to_cpu(sb->feature_map) & MD_FEATURE_REPLACEMENT)
+		set_bit(Replacement, &rdev->flags);
 
 	return 0;
 }
@@ -2831,10 +2874,6 @@ rewrite:
 		} else
 			pr_debug("md: %pg (skipping faulty)\n",
 				 rdev->bdev);
-
-		if (mddev->level == LEVEL_MULTIPATH)
-			/* only need to write one superblock... */
-			break;
 	}
 	if (md_super_wait(mddev) < 0)
 		goto rewrite;
@@ -2876,7 +2915,7 @@ static int add_bound_rdev(struct md_rdev *rdev)
 		 * and should be added immediately.
 		 */
 		super_types[mddev->major_version].
-			validate_super(mddev, rdev);
+			validate_super(mddev, NULL/*freshest*/, rdev);
 		err = mddev->pers->hot_add_disk(mddev, rdev);
 		if (err) {
 			md_kick_rdev_from_array(rdev);
@@ -3813,7 +3852,7 @@ static int analyze_sbs(struct mddev *mddev)
 	}
 
 	super_types[mddev->major_version].
-		validate_super(mddev, freshest);
+		validate_super(mddev, NULL/*freshest*/, freshest);
 
 	i = 0;
 	rdev_for_each_safe(rdev, tmp, mddev) {
@@ -3828,20 +3867,15 @@ static int analyze_sbs(struct mddev *mddev)
 		}
 		if (rdev != freshest) {
 			if (super_types[mddev->major_version].
-			    validate_super(mddev, rdev)) {
+			    validate_super(mddev, freshest, rdev)) {
 				pr_warn("md: kicking non-fresh %pg from array!\n",
 					rdev->bdev);
 				md_kick_rdev_from_array(rdev);
 				continue;
 			}
 		}
-		if (mddev->level == LEVEL_MULTIPATH) {
-			rdev->desc_nr = i++;
-			rdev->raid_disk = rdev->desc_nr;
-			set_bit(In_sync, &rdev->flags);
-		} else if (rdev->raid_disk >=
-			    (mddev->raid_disks - min(0, mddev->delta_disks)) &&
-			   !test_bit(Journal, &rdev->flags)) {
+		if (rdev->raid_disk >= (mddev->raid_disks - min(0, mddev->delta_disks)) &&
+		    !test_bit(Journal, &rdev->flags)) {
 			rdev->raid_disk = -1;
 			clear_bit(In_sync, &rdev->flags);
 		}
@@ -4840,25 +4874,29 @@ action_show(struct mddev *mddev, char *page)
 	return sprintf(page, "%s\n", type);
 }
 
-static void stop_sync_thread(struct mddev *mddev)
+/**
+ * stop_sync_thread() - wait for sync_thread to stop if it's running.
+ * @mddev:	the array.
+ * @locked:	if set, reconfig_mutex will still be held after this function
+ *		return; if not set, reconfig_mutex will be released after this
+ *		function return.
+ * @check_seq:	if set, only wait for curent running sync_thread to stop, noted
+ *		that new sync_thread can still start.
+ */
+static void stop_sync_thread(struct mddev *mddev, bool locked, bool check_seq)
 {
-	if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
-		return;
+	int sync_seq;
 
-	if (mddev_lock(mddev))
-		return;
+	if (check_seq)
+		sync_seq = atomic_read(&mddev->sync_seq);
 
-	/*
-	 * Check again in case MD_RECOVERY_RUNNING is cleared before lock is
-	 * held.
-	 */
 	if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
-		mddev_unlock(mddev);
+		if (!locked)
+			mddev_unlock(mddev);
 		return;
 	}
 
-	if (work_pending(&mddev->del_work))
-		flush_workqueue(md_misc_wq);
+	mddev_unlock(mddev);
 
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	/*
@@ -4866,21 +4904,28 @@ static void stop_sync_thread(struct mddev *mddev)
 	 * never happen
 	 */
 	md_wakeup_thread_directly(mddev->sync_thread);
+	if (work_pending(&mddev->sync_work))
+		flush_work(&mddev->sync_work);
 
-	mddev_unlock(mddev);
+	wait_event(resync_wait,
+		   !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+		   (check_seq && sync_seq != atomic_read(&mddev->sync_seq)));
+
+	if (locked)
+		mddev_lock_nointr(mddev);
 }
 
 static void idle_sync_thread(struct mddev *mddev)
 {
-	int sync_seq = atomic_read(&mddev->sync_seq);
-
 	mutex_lock(&mddev->sync_mutex);
 	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	stop_sync_thread(mddev);
 
-	wait_event(resync_wait, sync_seq != atomic_read(&mddev->sync_seq) ||
-			!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));
+	if (mddev_lock(mddev)) {
+		mutex_unlock(&mddev->sync_mutex);
+		return;
+	}
 
+	stop_sync_thread(mddev, false, true);
 	mutex_unlock(&mddev->sync_mutex);
 }
 
@@ -4888,11 +4933,13 @@ static void frozen_sync_thread(struct mddev *mddev)
 {
 	mutex_lock(&mddev->sync_mutex);
 	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	stop_sync_thread(mddev);
 
-	wait_event(resync_wait, mddev->sync_thread == NULL &&
-			!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));
+	if (mddev_lock(mddev)) {
+		mutex_unlock(&mddev->sync_mutex);
+		return;
+	}
 
+	stop_sync_thread(mddev, false, false);
 	mutex_unlock(&mddev->sync_mutex);
 }
 
@@ -6264,14 +6311,7 @@ static void md_clean(struct mddev *mddev)
 
 static void __md_stop_writes(struct mddev *mddev)
 {
-	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	if (work_pending(&mddev->del_work))
-		flush_workqueue(md_misc_wq);
-	if (mddev->sync_thread) {
-		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-		md_reap_sync_thread(mddev);
-	}
-
+	stop_sync_thread(mddev, true, false);
 	del_timer_sync(&mddev->safemode_timer);
 
 	if (mddev->pers && mddev->pers->quiesce) {
@@ -6318,9 +6358,6 @@ static void __md_stop(struct mddev *mddev)
 	struct md_personality *pers = mddev->pers;
 	md_bitmap_destroy(mddev);
 	mddev_detach(mddev);
-	/* Ensure ->event_work is done */
-	if (mddev->event_work.func)
-		flush_workqueue(md_misc_wq);
 	spin_lock(&mddev->lock);
 	mddev->pers = NULL;
 	spin_unlock(&mddev->lock);
@@ -6355,25 +6392,16 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 	int err = 0;
 	int did_freeze = 0;
 
+	if (mddev->external && test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
+		return -EBUSY;
+
 	if (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) {
 		did_freeze = 1;
 		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		md_wakeup_thread(mddev->thread);
 	}
-	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
-		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 
-	/*
-	 * Thread might be blocked waiting for metadata update which will now
-	 * never happen
-	 */
-	md_wakeup_thread_directly(mddev->sync_thread);
-
-	if (mddev->external && test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
-		return -EBUSY;
-	mddev_unlock(mddev);
-	wait_event(resync_wait, !test_bit(MD_RECOVERY_RUNNING,
-					  &mddev->recovery));
+	stop_sync_thread(mddev, false, false);
 	wait_event(mddev->sb_wait,
 		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
 	mddev_lock_nointr(mddev);
@@ -6383,29 +6411,30 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 	    mddev->sync_thread ||
 	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
 		pr_warn("md: %s still in use.\n",mdname(mddev));
-		if (did_freeze) {
-			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-			md_wakeup_thread(mddev->thread);
-		}
 		err = -EBUSY;
 		goto out;
 	}
+
 	if (mddev->pers) {
 		__md_stop_writes(mddev);
 
-		err  = -ENXIO;
-		if (mddev->ro == MD_RDONLY)
+		if (mddev->ro == MD_RDONLY) {
+			err  = -ENXIO;
 			goto out;
+		}
+
 		mddev->ro = MD_RDONLY;
 		set_disk_ro(mddev->gendisk, 1);
+	}
+
+out:
+	if ((mddev->pers && !err) || did_freeze) {
 		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 		md_wakeup_thread(mddev->thread);
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
-		err = 0;
 	}
-out:
+
 	mutex_unlock(&mddev->open_mutex);
 	return err;
 }
@@ -6426,20 +6455,8 @@ static int do_md_stop(struct mddev *mddev, int mode,
 		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		md_wakeup_thread(mddev->thread);
 	}
-	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
-		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 
-	/*
-	 * Thread might be blocked waiting for metadata update which will now
-	 * never happen
-	 */
-	md_wakeup_thread_directly(mddev->sync_thread);
-
-	mddev_unlock(mddev);
-	wait_event(resync_wait, (mddev->sync_thread == NULL &&
-				 !test_bit(MD_RECOVERY_RUNNING,
-					   &mddev->recovery)));
-	mddev_lock_nointr(mddev);
+	stop_sync_thread(mddev, true, false);
 
 	mutex_lock(&mddev->open_mutex);
 	if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) ||
@@ -6836,7 +6853,7 @@ int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info)
 			rdev->saved_raid_disk = rdev->raid_disk;
 		} else
 			super_types[mddev->major_version].
-				validate_super(mddev, rdev);
+				validate_super(mddev, NULL/*freshest*/, rdev);
 		if ((info->state & (1<<MD_DISK_SYNC)) &&
 		     rdev->raid_disk != info->raid_disk) {
 			/* This was a hot-add request, but events doesn't
@@ -8079,7 +8096,7 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev)
 		return;
 	mddev->pers->error_handler(mddev, rdev);
 
-	if (mddev->pers->level == 0 || mddev->pers->level == LEVEL_LINEAR)
+	if (mddev->pers->level == 0)
 		return;
 
 	if (mddev->degraded && !test_bit(MD_BROKEN, &mddev->flags))
@@ -8666,7 +8683,8 @@ static void md_end_clone_io(struct bio *bio)
 	struct bio *orig_bio = md_io_clone->orig_bio;
 	struct mddev *mddev = md_io_clone->mddev;
 
-	orig_bio->bi_status = bio->bi_status;
+	if (bio->bi_status && !orig_bio->bi_status)
+		orig_bio->bi_status = bio->bi_status;
 
 	if (md_io_clone->start_time)
 		bio_end_io_acct(orig_bio, md_io_clone->start_time);
@@ -9242,44 +9260,19 @@ static int remove_and_add_spares(struct mddev *mddev,
 	struct md_rdev *rdev;
 	int spares = 0;
 	int removed = 0;
-	bool remove_some = false;
 
 	if (this && test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
 		/* Mustn't remove devices when resync thread is running */
 		return 0;
 
 	rdev_for_each(rdev, mddev) {
-		if ((this == NULL || rdev == this) &&
-		    rdev->raid_disk >= 0 &&
-		    !test_bit(Blocked, &rdev->flags) &&
-		    test_bit(Faulty, &rdev->flags) &&
-		    atomic_read(&rdev->nr_pending)==0) {
-			/* Faulty non-Blocked devices with nr_pending == 0
-			 * never get nr_pending incremented,
-			 * never get Faulty cleared, and never get Blocked set.
-			 * So we can synchronize_rcu now rather than once per device
-			 */
-			remove_some = true;
-			set_bit(RemoveSynchronized, &rdev->flags);
-		}
-	}
-
-	if (remove_some)
-		synchronize_rcu();
-	rdev_for_each(rdev, mddev) {
-		if ((this == NULL || rdev == this) &&
-		    (test_bit(RemoveSynchronized, &rdev->flags) ||
-		     rdev_removeable(rdev))) {
-			if (mddev->pers->hot_remove_disk(
-				    mddev, rdev) == 0) {
-				sysfs_unlink_rdev(mddev, rdev);
-				rdev->saved_raid_disk = rdev->raid_disk;
-				rdev->raid_disk = -1;
-				removed++;
-			}
+		if ((this == NULL || rdev == this) && rdev_removeable(rdev) &&
+		    !mddev->pers->hot_remove_disk(mddev, rdev)) {
+			sysfs_unlink_rdev(mddev, rdev);
+			rdev->saved_raid_disk = rdev->raid_disk;
+			rdev->raid_disk = -1;
+			removed++;
 		}
-		if (remove_some && test_bit(RemoveSynchronized, &rdev->flags))
-			clear_bit(RemoveSynchronized, &rdev->flags);
 	}
 
 	if (removed && mddev->kobj.sd)
@@ -9402,7 +9395,15 @@ static void md_start_sync(struct work_struct *ws)
 		goto not_running;
 	}
 
-	suspend ? mddev_unlock_and_resume(mddev) : mddev_unlock(mddev);
+	mddev_unlock(mddev);
+	/*
+	 * md_start_sync was triggered by MD_RECOVERY_NEEDED, so we should
+	 * not set it again. Otherwise, we may cause issue like this one:
+	 *     https://bugzilla.kernel.org/show_bug.cgi?id=218200
+	 * Therefore, use __mddev_resume(mddev, false).
+	 */
+	if (suspend)
+		__mddev_resume(mddev, false);
 	md_wakeup_thread(mddev->sync_thread);
 	sysfs_notify_dirent_safe(mddev->sysfs_action);
 	md_new_event();
@@ -9414,7 +9415,15 @@ not_running:
 	clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
 	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 	clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-	suspend ? mddev_unlock_and_resume(mddev) : mddev_unlock(mddev);
+	mddev_unlock(mddev);
+	/*
+	 * md_start_sync was triggered by MD_RECOVERY_NEEDED, so we should
+	 * not set it again. Otherwise, we may cause issue like this one:
+	 *     https://bugzilla.kernel.org/show_bug.cgi?id=218200
+	 * Therefore, use __mddev_resume(mddev, false).
+	 */
+	if (suspend)
+		__mddev_resume(mddev, false);
 
 	wake_up(&resync_wait);
 	if (test_and_clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery) &&
diff --git a/drivers/md/md.h b/drivers/md/md.h
index ade83af123a2..8d881cc59799 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -190,11 +190,6 @@ enum flag_bits {
 				 * than other devices in the array
 				 */
 	ClusterRemove,
-	RemoveSynchronized,	/* synchronize_rcu() was called after
-				 * this device was known to be faulty,
-				 * so it is safe to remove without
-				 * another synchronize_rcu() call.
-				 */
 	ExternalBbl,            /* External metadata provides bad
 				 * block management for a disk
 				 */
diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c
index 3f22edec70e7..512746551f36 100644
--- a/drivers/md/raid1-10.c
+++ b/drivers/md/raid1-10.c
@@ -173,3 +173,57 @@ static inline void raid1_prepare_flush_writes(struct bitmap *bitmap)
 	else
 		md_bitmap_unplug(bitmap);
 }
+
+/*
+ * Used by fix_read_error() to decay the per rdev read_errors.
+ * We halve the read error count for every hour that has elapsed
+ * since the last recorded read error.
+ */
+static inline void check_decay_read_errors(struct mddev *mddev, struct md_rdev *rdev)
+{
+	long cur_time_mon;
+	unsigned long hours_since_last;
+	unsigned int read_errors = atomic_read(&rdev->read_errors);
+
+	cur_time_mon = ktime_get_seconds();
+
+	if (rdev->last_read_error == 0) {
+		/* first time we've seen a read error */
+		rdev->last_read_error = cur_time_mon;
+		return;
+	}
+
+	hours_since_last = (long)(cur_time_mon -
+			    rdev->last_read_error) / 3600;
+
+	rdev->last_read_error = cur_time_mon;
+
+	/*
+	 * if hours_since_last is > the number of bits in read_errors
+	 * just set read errors to 0. We do this to avoid
+	 * overflowing the shift of read_errors by hours_since_last.
+	 */
+	if (hours_since_last >= 8 * sizeof(read_errors))
+		atomic_set(&rdev->read_errors, 0);
+	else
+		atomic_set(&rdev->read_errors, read_errors >> hours_since_last);
+}
+
+static inline bool exceed_read_errors(struct mddev *mddev, struct md_rdev *rdev)
+{
+	int max_read_errors = atomic_read(&mddev->max_corr_read_errors);
+	int read_errors;
+
+	check_decay_read_errors(mddev, rdev);
+	read_errors =  atomic_inc_return(&rdev->read_errors);
+	if (read_errors > max_read_errors) {
+		pr_notice("md/"RAID_1_10_NAME":%s: %pg: Raid device exceeded read_error threshold [cur %d:max %d]\n",
+			  mdname(mddev), rdev->bdev, read_errors, max_read_errors);
+		pr_notice("md/"RAID_1_10_NAME":%s: %pg: Failing raid device\n",
+			  mdname(mddev), rdev->bdev);
+		md_error(mddev, rdev);
+		return true;
+	}
+
+	return false;
+}
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 35d12948e0a9..aaa434f0c175 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -49,6 +49,7 @@ static void lower_barrier(struct r1conf *conf, sector_t sector_nr);
 #define raid1_log(md, fmt, args...)				\
 	do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid1 " fmt, ##args); } while (0)
 
+#define RAID_1_10_NAME "raid1"
 #include "raid1-10.c"
 
 #define START(node) ((node)->start)
@@ -609,7 +610,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 	int choose_first;
 	int choose_next_idle;
 
-	rcu_read_lock();
 	/*
 	 * Check if we can balance. We can balance on the whole
 	 * device if no resync is going on, or below the resync window.
@@ -642,7 +642,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 		unsigned int pending;
 		bool nonrot;
 
-		rdev = rcu_dereference(conf->mirrors[disk].rdev);
+		rdev = conf->mirrors[disk].rdev;
 		if (r1_bio->bios[disk] == IO_BLOCKED
 		    || rdev == NULL
 		    || test_bit(Faulty, &rdev->flags))
@@ -773,7 +773,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 	}
 
 	if (best_disk >= 0) {
-		rdev = rcu_dereference(conf->mirrors[best_disk].rdev);
+		rdev = conf->mirrors[best_disk].rdev;
 		if (!rdev)
 			goto retry;
 		atomic_inc(&rdev->nr_pending);
@@ -784,7 +784,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 
 		conf->mirrors[best_disk].next_seq_sect = this_sector + sectors;
 	}
-	rcu_read_unlock();
 	*max_sectors = sectors;
 
 	return best_disk;
@@ -1126,8 +1125,6 @@ static void alloc_behind_master_bio(struct r1bio *r1_bio,
 
 	behind_bio = bio_alloc_bioset(NULL, vcnt, 0, GFP_NOIO,
 				      &r1_bio->mddev->bio_set);
-	if (!behind_bio)
-		return;
 
 	/* discard op, we don't support writezero/writesame yet */
 	if (!bio_has_data(bio)) {
@@ -1235,14 +1232,12 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 
 	if (r1bio_existed) {
 		/* Need to get the block device name carefully */
-		struct md_rdev *rdev;
-		rcu_read_lock();
-		rdev = rcu_dereference(conf->mirrors[r1_bio->read_disk].rdev);
+		struct md_rdev *rdev = conf->mirrors[r1_bio->read_disk].rdev;
+
 		if (rdev)
 			snprintf(b, sizeof(b), "%pg", rdev->bdev);
 		else
 			strcpy(b, "???");
-		rcu_read_unlock();
 	}
 
 	/*
@@ -1396,10 +1391,9 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 
 	disks = conf->raid_disks * 2;
 	blocked_rdev = NULL;
-	rcu_read_lock();
 	max_sectors = r1_bio->sectors;
 	for (i = 0;  i < disks; i++) {
-		struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
+		struct md_rdev *rdev = conf->mirrors[i].rdev;
 
 		/*
 		 * The write-behind io is only attempted on drives marked as
@@ -1465,7 +1459,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		}
 		r1_bio->bios[i] = bio;
 	}
-	rcu_read_unlock();
 
 	if (unlikely(blocked_rdev)) {
 		/* Wait for this device to become unblocked */
@@ -1617,15 +1610,16 @@ static void raid1_status(struct seq_file *seq, struct mddev *mddev)
 	struct r1conf *conf = mddev->private;
 	int i;
 
+	lockdep_assert_held(&mddev->lock);
+
 	seq_printf(seq, " [%d/%d] [", conf->raid_disks,
 		   conf->raid_disks - mddev->degraded);
-	rcu_read_lock();
 	for (i = 0; i < conf->raid_disks; i++) {
-		struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
+		struct md_rdev *rdev = READ_ONCE(conf->mirrors[i].rdev);
+
 		seq_printf(seq, "%s",
 			   rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_");
 	}
-	rcu_read_unlock();
 	seq_printf(seq, "]");
 }
 
@@ -1691,16 +1685,15 @@ static void print_conf(struct r1conf *conf)
 	pr_debug(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
 		 conf->raid_disks);
 
-	rcu_read_lock();
+	lockdep_assert_held(&conf->mddev->reconfig_mutex);
 	for (i = 0; i < conf->raid_disks; i++) {
-		struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
+		struct md_rdev *rdev = conf->mirrors[i].rdev;
 		if (rdev)
 			pr_debug(" disk %d, wo:%d, o:%d, dev:%pg\n",
 				 i, !test_bit(In_sync, &rdev->flags),
 				 !test_bit(Faulty, &rdev->flags),
 				 rdev->bdev);
 	}
-	rcu_read_unlock();
 }
 
 static void close_sync(struct r1conf *conf)
@@ -1810,7 +1803,7 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			 */
 			if (rdev->saved_raid_disk < 0)
 				conf->fullsync = 1;
-			rcu_assign_pointer(p->rdev, rdev);
+			WRITE_ONCE(p->rdev, rdev);
 			break;
 		}
 		if (test_bit(WantReplacement, &p->rdev->flags) &&
@@ -1826,7 +1819,7 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		rdev->raid_disk = repl_slot;
 		err = 0;
 		conf->fullsync = 1;
-		rcu_assign_pointer(p[conf->raid_disks].rdev, rdev);
+		WRITE_ONCE(p[conf->raid_disks].rdev, rdev);
 	}
 
 	print_conf(conf);
@@ -1862,16 +1855,7 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 			err = -EBUSY;
 			goto abort;
 		}
-		p->rdev = NULL;
-		if (!test_bit(RemoveSynchronized, &rdev->flags)) {
-			synchronize_rcu();
-			if (atomic_read(&rdev->nr_pending)) {
-				/* lost the race, try later */
-				err = -EBUSY;
-				p->rdev = rdev;
-				goto abort;
-			}
-		}
+		WRITE_ONCE(p->rdev, NULL);
 		if (conf->mirrors[conf->raid_disks + number].rdev) {
 			/* We just removed a device that is being replaced.
 			 * Move down the replacement.  We drain all IO before
@@ -1892,7 +1876,7 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 				goto abort;
 			}
 			clear_bit(Replacement, &repl->flags);
-			p->rdev = repl;
+			WRITE_ONCE(p->rdev, repl);
 			conf->mirrors[conf->raid_disks + number].rdev = NULL;
 			unfreeze_array(conf);
 		}
@@ -2272,16 +2256,24 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
  *	3.	Performs writes following reads for array synchronising.
  */
 
-static void fix_read_error(struct r1conf *conf, int read_disk,
-			   sector_t sect, int sectors)
+static void fix_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 {
+	sector_t sect = r1_bio->sector;
+	int sectors = r1_bio->sectors;
+	int read_disk = r1_bio->read_disk;
 	struct mddev *mddev = conf->mddev;
+	struct md_rdev *rdev = rcu_dereference(conf->mirrors[read_disk].rdev);
+
+	if (exceed_read_errors(mddev, rdev)) {
+		r1_bio->bios[r1_bio->read_disk] = IO_BLOCKED;
+		return;
+	}
+
 	while(sectors) {
 		int s = sectors;
 		int d = read_disk;
 		int success = 0;
 		int start;
-		struct md_rdev *rdev;
 
 		if (s > (PAGE_SIZE>>9))
 			s = PAGE_SIZE >> 9;
@@ -2290,8 +2282,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
 			sector_t first_bad;
 			int bad_sectors;
 
-			rcu_read_lock();
-			rdev = rcu_dereference(conf->mirrors[d].rdev);
+			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
 			    (test_bit(In_sync, &rdev->flags) ||
 			     (!test_bit(Faulty, &rdev->flags) &&
@@ -2299,15 +2290,14 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
 			    is_badblock(rdev, sect, s,
 					&first_bad, &bad_sectors) == 0) {
 				atomic_inc(&rdev->nr_pending);
-				rcu_read_unlock();
 				if (sync_page_io(rdev, sect, s<<9,
 					 conf->tmppage, REQ_OP_READ, false))
 					success = 1;
 				rdev_dec_pending(rdev, mddev);
 				if (success)
 					break;
-			} else
-				rcu_read_unlock();
+			}
+
 			d++;
 			if (d == conf->raid_disks * 2)
 				d = 0;
@@ -2326,29 +2316,24 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
 			if (d==0)
 				d = conf->raid_disks * 2;
 			d--;
-			rcu_read_lock();
-			rdev = rcu_dereference(conf->mirrors[d].rdev);
+			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
 			    !test_bit(Faulty, &rdev->flags)) {
 				atomic_inc(&rdev->nr_pending);
-				rcu_read_unlock();
 				r1_sync_page_io(rdev, sect, s,
 						conf->tmppage, WRITE);
 				rdev_dec_pending(rdev, mddev);
-			} else
-				rcu_read_unlock();
+			}
 		}
 		d = start;
 		while (d != read_disk) {
 			if (d==0)
 				d = conf->raid_disks * 2;
 			d--;
-			rcu_read_lock();
-			rdev = rcu_dereference(conf->mirrors[d].rdev);
+			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
 			    !test_bit(Faulty, &rdev->flags)) {
 				atomic_inc(&rdev->nr_pending);
-				rcu_read_unlock();
 				if (r1_sync_page_io(rdev, sect, s,
 						    conf->tmppage, READ)) {
 					atomic_add(s, &rdev->corrected_errors);
@@ -2359,8 +2344,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
 						rdev->bdev);
 				}
 				rdev_dec_pending(rdev, mddev);
-			} else
-				rcu_read_unlock();
+			}
 		}
 		sectors -= s;
 		sect += s;
@@ -2530,8 +2514,7 @@ static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 	if (mddev->ro == 0
 	    && !test_bit(FailFast, &rdev->flags)) {
 		freeze_array(conf, 1);
-		fix_read_error(conf, r1_bio->read_disk,
-			       r1_bio->sector, r1_bio->sectors);
+		fix_read_error(conf, r1_bio);
 		unfreeze_array(conf);
 	} else if (mddev->ro == 0 && test_bit(FailFast, &rdev->flags)) {
 		md_error(mddev, rdev);
@@ -2741,7 +2724,6 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 
 	r1_bio = raid1_alloc_init_r1buf(conf);
 
-	rcu_read_lock();
 	/*
 	 * If we get a correctably read error during resync or recovery,
 	 * we might want to read from a different device.  So we
@@ -2762,7 +2744,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 		struct md_rdev *rdev;
 		bio = r1_bio->bios[i];
 
-		rdev = rcu_dereference(conf->mirrors[i].rdev);
+		rdev = conf->mirrors[i].rdev;
 		if (rdev == NULL ||
 		    test_bit(Faulty, &rdev->flags)) {
 			if (i < conf->raid_disks)
@@ -2820,7 +2802,6 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 				bio->bi_opf |= MD_FAILFAST;
 		}
 	}
-	rcu_read_unlock();
 	if (disk < 0)
 		disk = wonly;
 	r1_bio->read_disk = disk;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index a5927e98dc67..7412066ea22c 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -19,6 +19,8 @@
 #include <linux/raid/md_p.h>
 #include <trace/events/block.h>
 #include "md.h"
+
+#define RAID_1_10_NAME "raid10"
 #include "raid10.h"
 #include "raid0.h"
 #include "md-bitmap.h"
@@ -743,7 +745,6 @@ static struct md_rdev *read_balance(struct r10conf *conf,
 	struct geom *geo = &conf->geo;
 
 	raid10_find_phys(conf, r10_bio);
-	rcu_read_lock();
 	best_dist_slot = -1;
 	min_pending = UINT_MAX;
 	best_dist_rdev = NULL;
@@ -775,18 +776,11 @@ static struct md_rdev *read_balance(struct r10conf *conf,
 		if (r10_bio->devs[slot].bio == IO_BLOCKED)
 			continue;
 		disk = r10_bio->devs[slot].devnum;
-		rdev = rcu_dereference(conf->mirrors[disk].replacement);
+		rdev = conf->mirrors[disk].replacement;
 		if (rdev == NULL || test_bit(Faulty, &rdev->flags) ||
 		    r10_bio->devs[slot].addr + sectors >
-		    rdev->recovery_offset) {
-			/*
-			 * Read replacement first to prevent reading both rdev
-			 * and replacement as NULL during replacement replace
-			 * rdev.
-			 */
-			smp_mb();
-			rdev = rcu_dereference(conf->mirrors[disk].rdev);
-		}
+		    rdev->recovery_offset)
+			rdev = conf->mirrors[disk].rdev;
 		if (rdev == NULL ||
 		    test_bit(Faulty, &rdev->flags))
 			continue;
@@ -876,7 +870,6 @@ static struct md_rdev *read_balance(struct r10conf *conf,
 		r10_bio->read_slot = slot;
 	} else
 		rdev = NULL;
-	rcu_read_unlock();
 	*max_sectors = best_good_sectors;
 
 	return rdev;
@@ -1198,9 +1191,8 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 		 */
 		gfp = GFP_NOIO | __GFP_HIGH;
 
-		rcu_read_lock();
 		disk = r10_bio->devs[slot].devnum;
-		err_rdev = rcu_dereference(conf->mirrors[disk].rdev);
+		err_rdev = conf->mirrors[disk].rdev;
 		if (err_rdev)
 			snprintf(b, sizeof(b), "%pg", err_rdev->bdev);
 		else {
@@ -1208,7 +1200,6 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 			/* This never gets dereferenced */
 			err_rdev = r10_bio->devs[slot].rdev;
 		}
-		rcu_read_unlock();
 	}
 
 	if (!regular_request_wait(mddev, conf, bio, r10_bio->sectors))
@@ -1279,15 +1270,8 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 	int devnum = r10_bio->devs[n_copy].devnum;
 	struct bio *mbio;
 
-	if (replacement) {
-		rdev = conf->mirrors[devnum].replacement;
-		if (rdev == NULL) {
-			/* Replacement just got moved to main 'rdev' */
-			smp_mb();
-			rdev = conf->mirrors[devnum].rdev;
-		}
-	} else
-		rdev = conf->mirrors[devnum].rdev;
+	rdev = replacement ? conf->mirrors[devnum].replacement :
+			     conf->mirrors[devnum].rdev;
 
 	mbio = bio_alloc_clone(rdev->bdev, bio, GFP_NOIO, &mddev->bio_set);
 	if (replacement)
@@ -1321,25 +1305,6 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 	}
 }
 
-static struct md_rdev *dereference_rdev_and_rrdev(struct raid10_info *mirror,
-						  struct md_rdev **prrdev)
-{
-	struct md_rdev *rdev, *rrdev;
-
-	rrdev = rcu_dereference(mirror->replacement);
-	/*
-	 * Read replacement first to prevent reading both rdev and
-	 * replacement as NULL during replacement replace rdev.
-	 */
-	smp_mb();
-	rdev = rcu_dereference(mirror->rdev);
-	if (rdev == rrdev)
-		rrdev = NULL;
-
-	*prrdev = rrdev;
-	return rdev;
-}
-
 static void wait_blocked_dev(struct mddev *mddev, struct r10bio *r10_bio)
 {
 	int i;
@@ -1348,11 +1313,11 @@ static void wait_blocked_dev(struct mddev *mddev, struct r10bio *r10_bio)
 
 retry_wait:
 	blocked_rdev = NULL;
-	rcu_read_lock();
 	for (i = 0; i < conf->copies; i++) {
 		struct md_rdev *rdev, *rrdev;
 
-		rdev = dereference_rdev_and_rrdev(&conf->mirrors[i], &rrdev);
+		rdev = conf->mirrors[i].rdev;
+		rrdev = conf->mirrors[i].replacement;
 		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
 			atomic_inc(&rdev->nr_pending);
 			blocked_rdev = rdev;
@@ -1391,7 +1356,6 @@ retry_wait:
 			}
 		}
 	}
-	rcu_read_unlock();
 
 	if (unlikely(blocked_rdev)) {
 		/* Have to wait for this device to get unblocked, then retry */
@@ -1474,14 +1438,14 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 
 	wait_blocked_dev(mddev, r10_bio);
 
-	rcu_read_lock();
 	max_sectors = r10_bio->sectors;
 
 	for (i = 0;  i < conf->copies; i++) {
 		int d = r10_bio->devs[i].devnum;
 		struct md_rdev *rdev, *rrdev;
 
-		rdev = dereference_rdev_and_rrdev(&conf->mirrors[d], &rrdev);
+		rdev = conf->mirrors[d].rdev;
+		rrdev = conf->mirrors[d].replacement;
 		if (rdev && (test_bit(Faulty, &rdev->flags)))
 			rdev = NULL;
 		if (rrdev && (test_bit(Faulty, &rrdev->flags)))
@@ -1535,7 +1499,6 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 			atomic_inc(&rrdev->nr_pending);
 		}
 	}
-	rcu_read_unlock();
 
 	if (max_sectors < r10_bio->sectors)
 		r10_bio->sectors = max_sectors;
@@ -1625,17 +1588,8 @@ static void raid10_end_discard_request(struct bio *bio)
 		set_bit(R10BIO_Uptodate, &r10_bio->state);
 
 	dev = find_bio_disk(conf, r10_bio, bio, &slot, &repl);
-	if (repl)
-		rdev = conf->mirrors[dev].replacement;
-	if (!rdev) {
-		/*
-		 * raid10_remove_disk uses smp_mb to make sure rdev is set to
-		 * replacement before setting replacement to NULL. It can read
-		 * rdev first without barrier protect even replacement is NULL
-		 */
-		smp_rmb();
-		rdev = conf->mirrors[dev].rdev;
-	}
+	rdev = repl ? conf->mirrors[dev].replacement :
+		      conf->mirrors[dev].rdev;
 
 	raid_end_discard_bio(r10_bio);
 	rdev_dec_pending(rdev, conf->mddev);
@@ -1785,11 +1739,11 @@ retry_discard:
 	 * inc refcount on their rdev.  Record them by setting
 	 * bios[x] to bio
 	 */
-	rcu_read_lock();
 	for (disk = 0; disk < geo->raid_disks; disk++) {
 		struct md_rdev *rdev, *rrdev;
 
-		rdev = dereference_rdev_and_rrdev(&conf->mirrors[disk], &rrdev);
+		rdev = conf->mirrors[disk].rdev;
+		rrdev = conf->mirrors[disk].replacement;
 		r10_bio->devs[disk].bio = NULL;
 		r10_bio->devs[disk].repl_bio = NULL;
 
@@ -1809,7 +1763,6 @@ retry_discard:
 			atomic_inc(&rrdev->nr_pending);
 		}
 	}
-	rcu_read_unlock();
 
 	atomic_set(&r10_bio->remaining, 1);
 	for (disk = 0; disk < geo->raid_disks; disk++) {
@@ -1939,6 +1892,8 @@ static void raid10_status(struct seq_file *seq, struct mddev *mddev)
 	struct r10conf *conf = mddev->private;
 	int i;
 
+	lockdep_assert_held(&mddev->lock);
+
 	if (conf->geo.near_copies < conf->geo.raid_disks)
 		seq_printf(seq, " %dK chunks", mddev->chunk_sectors / 2);
 	if (conf->geo.near_copies > 1)
@@ -1953,12 +1908,11 @@ static void raid10_status(struct seq_file *seq, struct mddev *mddev)
 	}
 	seq_printf(seq, " [%d/%d] [", conf->geo.raid_disks,
 					conf->geo.raid_disks - mddev->degraded);
-	rcu_read_lock();
 	for (i = 0; i < conf->geo.raid_disks; i++) {
-		struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
+		struct md_rdev *rdev = READ_ONCE(conf->mirrors[i].rdev);
+
 		seq_printf(seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_");
 	}
-	rcu_read_unlock();
 	seq_printf(seq, "]");
 }
 
@@ -1980,7 +1934,6 @@ static int _enough(struct r10conf *conf, int previous, int ignore)
 		ncopies = conf->geo.near_copies;
 	}
 
-	rcu_read_lock();
 	do {
 		int n = conf->copies;
 		int cnt = 0;
@@ -1988,7 +1941,7 @@ static int _enough(struct r10conf *conf, int previous, int ignore)
 		while (n--) {
 			struct md_rdev *rdev;
 			if (this != ignore &&
-			    (rdev = rcu_dereference(conf->mirrors[this].rdev)) &&
+			    (rdev = conf->mirrors[this].rdev) &&
 			    test_bit(In_sync, &rdev->flags))
 				cnt++;
 			this = (this+1) % disks;
@@ -1999,7 +1952,6 @@ static int _enough(struct r10conf *conf, int previous, int ignore)
 	} while (first != 0);
 	has_enough = 1;
 out:
-	rcu_read_unlock();
 	return has_enough;
 }
 
@@ -2072,8 +2024,7 @@ static void print_conf(struct r10conf *conf)
 	pr_debug(" --- wd:%d rd:%d\n", conf->geo.raid_disks - conf->mddev->degraded,
 		 conf->geo.raid_disks);
 
-	/* This is only called with ->reconfix_mutex held, so
-	 * rcu protection of rdev is not needed */
+	lockdep_assert_held(&conf->mddev->reconfig_mutex);
 	for (i = 0; i < conf->geo.raid_disks; i++) {
 		rdev = conf->mirrors[i].rdev;
 		if (rdev)
@@ -2190,7 +2141,7 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		err = 0;
 		if (rdev->saved_raid_disk != mirror)
 			conf->fullsync = 1;
-		rcu_assign_pointer(p->rdev, rdev);
+		WRITE_ONCE(p->rdev, rdev);
 		break;
 	}
 
@@ -2204,7 +2155,7 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			disk_stack_limits(mddev->gendisk, rdev->bdev,
 					  rdev->data_offset << 9);
 		conf->fullsync = 1;
-		rcu_assign_pointer(p->replacement, rdev);
+		WRITE_ONCE(p->replacement, rdev);
 	}
 
 	print_conf(conf);
@@ -2246,24 +2197,12 @@ static int raid10_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 		err = -EBUSY;
 		goto abort;
 	}
-	*rdevp = NULL;
-	if (!test_bit(RemoveSynchronized, &rdev->flags)) {
-		synchronize_rcu();
-		if (atomic_read(&rdev->nr_pending)) {
-			/* lost the race, try later */
-			err = -EBUSY;
-			*rdevp = rdev;
-			goto abort;
-		}
-	}
+	WRITE_ONCE(*rdevp, NULL);
 	if (p->replacement) {
 		/* We must have just cleared 'rdev' */
-		p->rdev = p->replacement;
+		WRITE_ONCE(p->rdev, p->replacement);
 		clear_bit(Replacement, &p->replacement->flags);
-		smp_mb(); /* Make sure other CPUs may see both as identical
-			   * but will never see neither -- if they are careful.
-			   */
-		p->replacement = NULL;
+		WRITE_ONCE(p->replacement, NULL);
 	}
 
 	clear_bit(WantReplacement, &rdev->flags);
@@ -2655,42 +2594,6 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 	}
 }
 
-/*
- * Used by fix_read_error() to decay the per rdev read_errors.
- * We halve the read error count for every hour that has elapsed
- * since the last recorded read error.
- *
- */
-static void check_decay_read_errors(struct mddev *mddev, struct md_rdev *rdev)
-{
-	long cur_time_mon;
-	unsigned long hours_since_last;
-	unsigned int read_errors = atomic_read(&rdev->read_errors);
-
-	cur_time_mon = ktime_get_seconds();
-
-	if (rdev->last_read_error == 0) {
-		/* first time we've seen a read error */
-		rdev->last_read_error = cur_time_mon;
-		return;
-	}
-
-	hours_since_last = (long)(cur_time_mon -
-			    rdev->last_read_error) / 3600;
-
-	rdev->last_read_error = cur_time_mon;
-
-	/*
-	 * if hours_since_last is > the number of bits in read_errors
-	 * just set read errors to 0. We do this to avoid
-	 * overflowing the shift of read_errors by hours_since_last.
-	 */
-	if (hours_since_last >= 8 * sizeof(read_errors))
-		atomic_set(&rdev->read_errors, 0);
-	else
-		atomic_set(&rdev->read_errors, read_errors >> hours_since_last);
-}
-
 static int r10_sync_page_io(struct md_rdev *rdev, sector_t sector,
 			    int sectors, struct page *page, enum req_op op)
 {
@@ -2728,7 +2631,6 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 	int sect = 0; /* Offset from r10_bio->sector */
 	int sectors = r10_bio->sectors, slot = r10_bio->read_slot;
 	struct md_rdev *rdev;
-	int max_read_errors = atomic_read(&mddev->max_corr_read_errors);
 	int d = r10_bio->devs[slot].devnum;
 
 	/* still own a reference to this rdev, so it cannot
@@ -2741,15 +2643,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 		   more fix_read_error() attempts */
 		return;
 
-	check_decay_read_errors(mddev, rdev);
-	atomic_inc(&rdev->read_errors);
-	if (atomic_read(&rdev->read_errors) > max_read_errors) {
-		pr_notice("md/raid10:%s: %pg: Raid device exceeded read_error threshold [cur %d:max %d]\n",
-			  mdname(mddev), rdev->bdev,
-			  atomic_read(&rdev->read_errors), max_read_errors);
-		pr_notice("md/raid10:%s: %pg: Failing raid device\n",
-			  mdname(mddev), rdev->bdev);
-		md_error(mddev, rdev);
+	if (exceed_read_errors(mddev, rdev)) {
 		r10_bio->devs[slot].bio = IO_BLOCKED;
 		return;
 	}
@@ -2763,20 +2657,18 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 		if (s > (PAGE_SIZE>>9))
 			s = PAGE_SIZE >> 9;
 
-		rcu_read_lock();
 		do {
 			sector_t first_bad;
 			int bad_sectors;
 
 			d = r10_bio->devs[sl].devnum;
-			rdev = rcu_dereference(conf->mirrors[d].rdev);
+			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
 			    test_bit(In_sync, &rdev->flags) &&
 			    !test_bit(Faulty, &rdev->flags) &&
 			    is_badblock(rdev, r10_bio->devs[sl].addr + sect, s,
 					&first_bad, &bad_sectors) == 0) {
 				atomic_inc(&rdev->nr_pending);
-				rcu_read_unlock();
 				success = sync_page_io(rdev,
 						       r10_bio->devs[sl].addr +
 						       sect,
@@ -2784,7 +2676,6 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 						       conf->tmppage,
 						       REQ_OP_READ, false);
 				rdev_dec_pending(rdev, mddev);
-				rcu_read_lock();
 				if (success)
 					break;
 			}
@@ -2792,7 +2683,6 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			if (sl == conf->copies)
 				sl = 0;
 		} while (sl != slot);
-		rcu_read_unlock();
 
 		if (!success) {
 			/* Cannot read from anywhere, just mark the block
@@ -2816,20 +2706,18 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 
 		start = sl;
 		/* write it back and re-read */
-		rcu_read_lock();
 		while (sl != slot) {
 			if (sl==0)
 				sl = conf->copies;
 			sl--;
 			d = r10_bio->devs[sl].devnum;
-			rdev = rcu_dereference(conf->mirrors[d].rdev);
+			rdev = conf->mirrors[d].rdev;
 			if (!rdev ||
 			    test_bit(Faulty, &rdev->flags) ||
 			    !test_bit(In_sync, &rdev->flags))
 				continue;
 
 			atomic_inc(&rdev->nr_pending);
-			rcu_read_unlock();
 			if (r10_sync_page_io(rdev,
 					     r10_bio->devs[sl].addr +
 					     sect,
@@ -2848,7 +2736,6 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 					  rdev->bdev);
 			}
 			rdev_dec_pending(rdev, mddev);
-			rcu_read_lock();
 		}
 		sl = start;
 		while (sl != slot) {
@@ -2856,14 +2743,13 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 				sl = conf->copies;
 			sl--;
 			d = r10_bio->devs[sl].devnum;
-			rdev = rcu_dereference(conf->mirrors[d].rdev);
+			rdev = conf->mirrors[d].rdev;
 			if (!rdev ||
 			    test_bit(Faulty, &rdev->flags) ||
 			    !test_bit(In_sync, &rdev->flags))
 				continue;
 
 			atomic_inc(&rdev->nr_pending);
-			rcu_read_unlock();
 			switch (r10_sync_page_io(rdev,
 					     r10_bio->devs[sl].addr +
 					     sect,
@@ -2891,9 +2777,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			}
 
 			rdev_dec_pending(rdev, mddev);
-			rcu_read_lock();
 		}
-		rcu_read_unlock();
 
 		sectors -= s;
 		sect += s;
@@ -3367,14 +3251,13 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				/* Completed a full sync so the replacements
 				 * are now fully recovered.
 				 */
-				rcu_read_lock();
 				for (i = 0; i < conf->geo.raid_disks; i++) {
 					struct md_rdev *rdev =
-						rcu_dereference(conf->mirrors[i].replacement);
+						conf->mirrors[i].replacement;
+
 					if (rdev)
 						rdev->recovery_offset = MaxSector;
 				}
-				rcu_read_unlock();
 			}
 			conf->fullsync = 0;
 		}
@@ -3455,9 +3338,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			struct raid10_info *mirror = &conf->mirrors[i];
 			struct md_rdev *mrdev, *mreplace;
 
-			rcu_read_lock();
-			mrdev = rcu_dereference(mirror->rdev);
-			mreplace = rcu_dereference(mirror->replacement);
+			mrdev = mirror->rdev;
+			mreplace = mirror->replacement;
 
 			if (mrdev && (test_bit(Faulty, &mrdev->flags) ||
 			    test_bit(In_sync, &mrdev->flags)))
@@ -3465,22 +3347,18 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			if (mreplace && test_bit(Faulty, &mreplace->flags))
 				mreplace = NULL;
 
-			if (!mrdev && !mreplace) {
-				rcu_read_unlock();
+			if (!mrdev && !mreplace)
 				continue;
-			}
 
 			still_degraded = 0;
 			/* want to reconstruct this device */
 			rb2 = r10_bio;
 			sect = raid10_find_virt(conf, sector_nr, i);
-			if (sect >= mddev->resync_max_sectors) {
+			if (sect >= mddev->resync_max_sectors)
 				/* last stripe is not complete - don't
 				 * try to recover this sector.
 				 */
-				rcu_read_unlock();
 				continue;
-			}
 			/* Unless we are doing a full sync, or a replacement
 			 * we only need to recover the block if it is set in
 			 * the bitmap
@@ -3496,14 +3374,12 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				 * that there will never be anything to do here
 				 */
 				chunks_skipped = -1;
-				rcu_read_unlock();
 				continue;
 			}
 			if (mrdev)
 				atomic_inc(&mrdev->nr_pending);
 			if (mreplace)
 				atomic_inc(&mreplace->nr_pending);
-			rcu_read_unlock();
 
 			r10_bio = raid10_alloc_init_r10buf(conf);
 			r10_bio->state = 0;
@@ -3522,10 +3398,9 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			/* Need to check if the array will still be
 			 * degraded
 			 */
-			rcu_read_lock();
 			for (j = 0; j < conf->geo.raid_disks; j++) {
-				struct md_rdev *rdev = rcu_dereference(
-					conf->mirrors[j].rdev);
+				struct md_rdev *rdev = conf->mirrors[j].rdev;
+
 				if (rdev == NULL || test_bit(Faulty, &rdev->flags)) {
 					still_degraded = 1;
 					break;
@@ -3540,8 +3415,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				int k;
 				int d = r10_bio->devs[j].devnum;
 				sector_t from_addr, to_addr;
-				struct md_rdev *rdev =
-					rcu_dereference(conf->mirrors[d].rdev);
+				struct md_rdev *rdev = conf->mirrors[d].rdev;
 				sector_t sector, first_bad;
 				int bad_sectors;
 				if (!rdev ||
@@ -3620,7 +3494,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				atomic_inc(&r10_bio->remaining);
 				break;
 			}
-			rcu_read_unlock();
 			if (j == conf->copies) {
 				/* Cannot recover, so abort the recovery or
 				 * record a bad block */
@@ -3747,12 +3620,10 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 
 			bio = r10_bio->devs[i].bio;
 			bio->bi_status = BLK_STS_IOERR;
-			rcu_read_lock();
-			rdev = rcu_dereference(conf->mirrors[d].rdev);
-			if (rdev == NULL || test_bit(Faulty, &rdev->flags)) {
-				rcu_read_unlock();
+			rdev = conf->mirrors[d].rdev;
+			if (rdev == NULL || test_bit(Faulty, &rdev->flags))
 				continue;
-			}
+
 			sector = r10_bio->devs[i].addr;
 			if (is_badblock(rdev, sector, max_sync,
 					&first_bad, &bad_sectors)) {
@@ -3762,7 +3633,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 					bad_sectors -= (sector - first_bad);
 					if (max_sync > bad_sectors)
 						max_sync = bad_sectors;
-					rcu_read_unlock();
 					continue;
 				}
 			}
@@ -3778,11 +3648,10 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			bio_set_dev(bio, rdev->bdev);
 			count++;
 
-			rdev = rcu_dereference(conf->mirrors[d].replacement);
-			if (rdev == NULL || test_bit(Faulty, &rdev->flags)) {
-				rcu_read_unlock();
+			rdev = conf->mirrors[d].replacement;
+			if (rdev == NULL || test_bit(Faulty, &rdev->flags))
 				continue;
-			}
+
 			atomic_inc(&rdev->nr_pending);
 
 			/* Need to set up for writing to the replacement */
@@ -3799,7 +3668,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			bio->bi_iter.bi_sector = sector + rdev->data_offset;
 			bio_set_dev(bio, rdev->bdev);
 			count++;
-			rcu_read_unlock();
 		}
 
 		if (count < 2) {
@@ -4509,11 +4377,11 @@ static int calc_degraded(struct r10conf *conf)
 	int degraded, degraded2;
 	int i;
 
-	rcu_read_lock();
 	degraded = 0;
 	/* 'prev' section first */
 	for (i = 0; i < conf->prev.raid_disks; i++) {
-		struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
+		struct md_rdev *rdev = conf->mirrors[i].rdev;
+
 		if (!rdev || test_bit(Faulty, &rdev->flags))
 			degraded++;
 		else if (!test_bit(In_sync, &rdev->flags))
@@ -4523,13 +4391,12 @@ static int calc_degraded(struct r10conf *conf)
 			 */
 			degraded++;
 	}
-	rcu_read_unlock();
 	if (conf->geo.raid_disks == conf->prev.raid_disks)
 		return degraded;
-	rcu_read_lock();
 	degraded2 = 0;
 	for (i = 0; i < conf->geo.raid_disks; i++) {
-		struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
+		struct md_rdev *rdev = conf->mirrors[i].rdev;
+
 		if (!rdev || test_bit(Faulty, &rdev->flags))
 			degraded2++;
 		else if (!test_bit(In_sync, &rdev->flags)) {
@@ -4542,7 +4409,6 @@ static int calc_degraded(struct r10conf *conf)
 				degraded2++;
 		}
 	}
-	rcu_read_unlock();
 	if (degraded2 > degraded)
 		return degraded2;
 	return degraded;
@@ -4974,16 +4840,15 @@ read_more:
 	blist = read_bio;
 	read_bio->bi_next = NULL;
 
-	rcu_read_lock();
 	for (s = 0; s < conf->copies*2; s++) {
 		struct bio *b;
 		int d = r10_bio->devs[s/2].devnum;
 		struct md_rdev *rdev2;
 		if (s&1) {
-			rdev2 = rcu_dereference(conf->mirrors[d].replacement);
+			rdev2 = conf->mirrors[d].replacement;
 			b = r10_bio->devs[s/2].repl_bio;
 		} else {
-			rdev2 = rcu_dereference(conf->mirrors[d].rdev);
+			rdev2 = conf->mirrors[d].rdev;
 			b = r10_bio->devs[s/2].bio;
 		}
 		if (!rdev2 || test_bit(Faulty, &rdev2->flags))
@@ -5017,7 +4882,6 @@ read_more:
 		sector_nr += len >> 9;
 		nr_sectors += len >> 9;
 	}
-	rcu_read_unlock();
 	r10_bio->sectors = nr_sectors;
 
 	/* Now submit the read */
@@ -5070,20 +4934,17 @@ static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 		struct bio *b;
 		int d = r10_bio->devs[s/2].devnum;
 		struct md_rdev *rdev;
-		rcu_read_lock();
 		if (s&1) {
-			rdev = rcu_dereference(conf->mirrors[d].replacement);
+			rdev = conf->mirrors[d].replacement;
 			b = r10_bio->devs[s/2].repl_bio;
 		} else {
-			rdev = rcu_dereference(conf->mirrors[d].rdev);
+			rdev = conf->mirrors[d].rdev;
 			b = r10_bio->devs[s/2].bio;
 		}
-		if (!rdev || test_bit(Faulty, &rdev->flags)) {
-			rcu_read_unlock();
+		if (!rdev || test_bit(Faulty, &rdev->flags))
 			continue;
-		}
+
 		atomic_inc(&rdev->nr_pending);
-		rcu_read_unlock();
 		md_sync_acct_bio(b, r10_bio->sectors);
 		atomic_inc(&r10_bio->remaining);
 		b->bi_next = NULL;
@@ -5154,10 +5015,9 @@ static int handle_reshape_read_error(struct mddev *mddev,
 		if (s > (PAGE_SIZE >> 9))
 			s = PAGE_SIZE >> 9;
 
-		rcu_read_lock();
 		while (!success) {
 			int d = r10b->devs[slot].devnum;
-			struct md_rdev *rdev = rcu_dereference(conf->mirrors[d].rdev);
+			struct md_rdev *rdev = conf->mirrors[d].rdev;
 			sector_t addr;
 			if (rdev == NULL ||
 			    test_bit(Faulty, &rdev->flags) ||
@@ -5166,14 +5026,12 @@ static int handle_reshape_read_error(struct mddev *mddev,
 
 			addr = r10b->devs[slot].addr + idx * PAGE_SIZE;
 			atomic_inc(&rdev->nr_pending);
-			rcu_read_unlock();
 			success = sync_page_io(rdev,
 					       addr,
 					       s << 9,
 					       pages[idx],
 					       REQ_OP_READ, false);
 			rdev_dec_pending(rdev, mddev);
-			rcu_read_lock();
 			if (success)
 				break;
 		failed:
@@ -5183,7 +5041,6 @@ static int handle_reshape_read_error(struct mddev *mddev,
 			if (slot == first_slot)
 				break;
 		}
-		rcu_read_unlock();
 		if (!success) {
 			/* couldn't read this block, must give up */
 			set_bit(MD_RECOVERY_INTR,
@@ -5209,12 +5066,8 @@ static void end_reshape_write(struct bio *bio)
 	struct md_rdev *rdev = NULL;
 
 	d = find_bio_disk(conf, r10_bio, bio, &slot, &repl);
-	if (repl)
-		rdev = conf->mirrors[d].replacement;
-	if (!rdev) {
-		smp_mb();
-		rdev = conf->mirrors[d].rdev;
-	}
+	rdev = repl ? conf->mirrors[d].replacement :
+		      conf->mirrors[d].rdev;
 
 	if (bio->bi_status) {
 		/* FIXME should record badblock */
@@ -5249,18 +5102,16 @@ static void raid10_finish_reshape(struct mddev *mddev)
 		mddev->resync_max_sectors = mddev->array_sectors;
 	} else {
 		int d;
-		rcu_read_lock();
 		for (d = conf->geo.raid_disks ;
 		     d < conf->geo.raid_disks - mddev->delta_disks;
 		     d++) {
-			struct md_rdev *rdev = rcu_dereference(conf->mirrors[d].rdev);
+			struct md_rdev *rdev = conf->mirrors[d].rdev;
 			if (rdev)
 				clear_bit(In_sync, &rdev->flags);
-			rdev = rcu_dereference(conf->mirrors[d].replacement);
+			rdev = conf->mirrors[d].replacement;
 			if (rdev)
 				clear_bit(In_sync, &rdev->flags);
 		}
-		rcu_read_unlock();
 	}
 	mddev->layout = mddev->new_layout;
 	mddev->chunk_sectors = 1 << conf->geo.chunk_shift;
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 6157f5beb9fe..874874fe4fa1 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -1890,28 +1890,22 @@ r5l_recovery_replay_one_stripe(struct r5conf *conf,
 			continue;
 
 		/* in case device is broken */
-		rcu_read_lock();
-		rdev = rcu_dereference(conf->disks[disk_index].rdev);
+		rdev = conf->disks[disk_index].rdev;
 		if (rdev) {
 			atomic_inc(&rdev->nr_pending);
-			rcu_read_unlock();
 			sync_page_io(rdev, sh->sector, PAGE_SIZE,
 				     sh->dev[disk_index].page, REQ_OP_WRITE,
 				     false);
 			rdev_dec_pending(rdev, rdev->mddev);
-			rcu_read_lock();
 		}
-		rrdev = rcu_dereference(conf->disks[disk_index].replacement);
+		rrdev = conf->disks[disk_index].replacement;
 		if (rrdev) {
 			atomic_inc(&rrdev->nr_pending);
-			rcu_read_unlock();
 			sync_page_io(rrdev, sh->sector, PAGE_SIZE,
 				     sh->dev[disk_index].page, REQ_OP_WRITE,
 				     false);
 			rdev_dec_pending(rrdev, rrdev->mddev);
-			rcu_read_lock();
 		}
-		rcu_read_unlock();
 	}
 	ctx->data_parity_stripes++;
 out:
@@ -2948,7 +2942,6 @@ bool r5c_big_stripe_cached(struct r5conf *conf, sector_t sect)
 	if (!log)
 		return false;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
 	tree_index = r5c_tree_index(conf, sect);
 	slot = radix_tree_lookup(&log->big_stripe_tree, tree_index);
 	return slot != NULL;
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
index eaea57aee602..da4ba736c4f0 100644
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -620,11 +620,9 @@ static void ppl_do_flush(struct ppl_io_unit *io)
 		struct md_rdev *rdev;
 		struct block_device *bdev = NULL;
 
-		rcu_read_lock();
-		rdev = rcu_dereference(conf->disks[i].rdev);
+		rdev = conf->disks[i].rdev;
 		if (rdev && !test_bit(Faulty, &rdev->flags))
 			bdev = rdev->bdev;
-		rcu_read_unlock();
 
 		if (bdev) {
 			struct bio *bio;
@@ -882,9 +880,7 @@ static int ppl_recover_entry(struct ppl_log *log, struct ppl_header_entry *e,
 				 (unsigned long long)r_sector, dd_idx,
 				 (unsigned long long)sector);
 
-			/* Array has not started so rcu dereference is safe */
-			rdev = rcu_dereference_protected(
-					conf->disks[dd_idx].rdev, 1);
+			rdev = conf->disks[dd_idx].rdev;
 			if (!rdev || (!test_bit(In_sync, &rdev->flags) &&
 				      sector >= rdev->recovery_offset)) {
 				pr_debug("%s:%*s data member disk %d missing\n",
@@ -936,9 +932,7 @@ static int ppl_recover_entry(struct ppl_log *log, struct ppl_header_entry *e,
 				0, &disk, &sh);
 		BUG_ON(sh.pd_idx != le32_to_cpu(e->parity_disk));
 
-		/* Array has not started so rcu dereference is safe */
-		parity_rdev = rcu_dereference_protected(
-					conf->disks[sh.pd_idx].rdev, 1);
+		parity_rdev = conf->disks[sh.pd_idx].rdev;
 
 		BUG_ON(parity_rdev->bdev->bd_dev != log->rdev->bdev->bd_dev);
 		pr_debug("%s:%*s write parity at sector %llu, disk %pg\n",
@@ -1404,9 +1398,7 @@ int ppl_init_log(struct r5conf *conf)
 
 	for (i = 0; i < ppl_conf->count; i++) {
 		struct ppl_log *log = &ppl_conf->child_logs[i];
-		/* Array has not started so rcu dereference is safe */
-		struct md_rdev *rdev =
-			rcu_dereference_protected(conf->disks[i].rdev, 1);
+		struct md_rdev *rdev = conf->disks[i].rdev;
 
 		mutex_init(&log->io_mutex);
 		spin_lock_init(&log->io_list_lock);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index dc031d42f53b..8497880135ee 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -36,7 +36,6 @@
  */
 
 #include <linux/blkdev.h>
-#include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/raid/pq.h>
 #include <linux/async_tx.h>
@@ -694,12 +693,12 @@ int raid5_calc_degraded(struct r5conf *conf)
 	int degraded, degraded2;
 	int i;
 
-	rcu_read_lock();
 	degraded = 0;
 	for (i = 0; i < conf->previous_raid_disks; i++) {
-		struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
+		struct md_rdev *rdev = READ_ONCE(conf->disks[i].rdev);
+
 		if (rdev && test_bit(Faulty, &rdev->flags))
-			rdev = rcu_dereference(conf->disks[i].replacement);
+			rdev = READ_ONCE(conf->disks[i].replacement);
 		if (!rdev || test_bit(Faulty, &rdev->flags))
 			degraded++;
 		else if (test_bit(In_sync, &rdev->flags))
@@ -717,15 +716,14 @@ int raid5_calc_degraded(struct r5conf *conf)
 			if (conf->raid_disks >= conf->previous_raid_disks)
 				degraded++;
 	}
-	rcu_read_unlock();
 	if (conf->raid_disks == conf->previous_raid_disks)
 		return degraded;
-	rcu_read_lock();
 	degraded2 = 0;
 	for (i = 0; i < conf->raid_disks; i++) {
-		struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
+		struct md_rdev *rdev = READ_ONCE(conf->disks[i].rdev);
+
 		if (rdev && test_bit(Faulty, &rdev->flags))
-			rdev = rcu_dereference(conf->disks[i].replacement);
+			rdev = READ_ONCE(conf->disks[i].replacement);
 		if (!rdev || test_bit(Faulty, &rdev->flags))
 			degraded2++;
 		else if (test_bit(In_sync, &rdev->flags))
@@ -739,7 +737,6 @@ int raid5_calc_degraded(struct r5conf *conf)
 			if (conf->raid_disks <= conf->previous_raid_disks)
 				degraded2++;
 	}
-	rcu_read_unlock();
 	if (degraded2 > degraded)
 		return degraded2;
 	return degraded;
@@ -1184,14 +1181,8 @@ again:
 		bi = &dev->req;
 		rbi = &dev->rreq; /* For writing to replacement */
 
-		rcu_read_lock();
-		rrdev = rcu_dereference(conf->disks[i].replacement);
-		smp_mb(); /* Ensure that if rrdev is NULL, rdev won't be */
-		rdev = rcu_dereference(conf->disks[i].rdev);
-		if (!rdev) {
-			rdev = rrdev;
-			rrdev = NULL;
-		}
+		rdev = conf->disks[i].rdev;
+		rrdev = conf->disks[i].replacement;
 		if (op_is_write(op)) {
 			if (replace_only)
 				rdev = NULL;
@@ -1212,7 +1203,6 @@ again:
 			rrdev = NULL;
 		if (rrdev)
 			atomic_inc(&rrdev->nr_pending);
-		rcu_read_unlock();
 
 		/* We have already checked bad blocks for reads.  Now
 		 * need to check for writes.  We never accept write errors
@@ -2731,28 +2721,6 @@ static void shrink_stripes(struct r5conf *conf)
 	conf->slab_cache = NULL;
 }
 
-/*
- * This helper wraps rcu_dereference_protected() and can be used when
- * it is known that the nr_pending of the rdev is elevated.
- */
-static struct md_rdev *rdev_pend_deref(struct md_rdev __rcu *rdev)
-{
-	return rcu_dereference_protected(rdev,
-			atomic_read(&rcu_access_pointer(rdev)->nr_pending));
-}
-
-/*
- * This helper wraps rcu_dereference_protected() and should be used
- * when it is known that the mddev_lock() is held. This is safe
- * seeing raid5_remove_disk() has the same lock held.
- */
-static struct md_rdev *rdev_mdlock_deref(struct mddev *mddev,
-					 struct md_rdev __rcu *rdev)
-{
-	return rcu_dereference_protected(rdev,
-			lockdep_is_held(&mddev->reconfig_mutex));
-}
-
 static void raid5_end_read_request(struct bio * bi)
 {
 	struct stripe_head *sh = bi->bi_private;
@@ -2778,9 +2746,9 @@ static void raid5_end_read_request(struct bio * bi)
 		 * In that case it moved down to 'rdev'.
 		 * rdev is not removed until all requests are finished.
 		 */
-		rdev = rdev_pend_deref(conf->disks[i].replacement);
+		rdev = conf->disks[i].replacement;
 	if (!rdev)
-		rdev = rdev_pend_deref(conf->disks[i].rdev);
+		rdev = conf->disks[i].rdev;
 
 	if (use_new_offset(conf, sh))
 		s = sh->sector + rdev->new_data_offset;
@@ -2893,11 +2861,11 @@ static void raid5_end_write_request(struct bio *bi)
 
 	for (i = 0 ; i < disks; i++) {
 		if (bi == &sh->dev[i].req) {
-			rdev = rdev_pend_deref(conf->disks[i].rdev);
+			rdev = conf->disks[i].rdev;
 			break;
 		}
 		if (bi == &sh->dev[i].rreq) {
-			rdev = rdev_pend_deref(conf->disks[i].replacement);
+			rdev = conf->disks[i].replacement;
 			if (rdev)
 				replacement = 1;
 			else
@@ -2905,7 +2873,7 @@ static void raid5_end_write_request(struct bio *bi)
 				 * replaced it.  rdev is not removed
 				 * until all requests are finished.
 				 */
-				rdev = rdev_pend_deref(conf->disks[i].rdev);
+				rdev = conf->disks[i].rdev;
 			break;
 		}
 	}
@@ -3667,15 +3635,13 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 		int bitmap_end = 0;
 
 		if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
-			struct md_rdev *rdev;
-			rcu_read_lock();
-			rdev = rcu_dereference(conf->disks[i].rdev);
+			struct md_rdev *rdev = conf->disks[i].rdev;
+
 			if (rdev && test_bit(In_sync, &rdev->flags) &&
 			    !test_bit(Faulty, &rdev->flags))
 				atomic_inc(&rdev->nr_pending);
 			else
 				rdev = NULL;
-			rcu_read_unlock();
 			if (rdev) {
 				if (!rdev_set_badblocks(
 					    rdev,
@@ -3793,16 +3759,17 @@ handle_failed_sync(struct r5conf *conf, struct stripe_head *sh,
 		/* During recovery devices cannot be removed, so
 		 * locking and refcounting of rdevs is not needed
 		 */
-		rcu_read_lock();
 		for (i = 0; i < conf->raid_disks; i++) {
-			struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
+			struct md_rdev *rdev = conf->disks[i].rdev;
+
 			if (rdev
 			    && !test_bit(Faulty, &rdev->flags)
 			    && !test_bit(In_sync, &rdev->flags)
 			    && !rdev_set_badblocks(rdev, sh->sector,
 						   RAID5_STRIPE_SECTORS(conf), 0))
 				abort = 1;
-			rdev = rcu_dereference(conf->disks[i].replacement);
+			rdev = conf->disks[i].replacement;
+
 			if (rdev
 			    && !test_bit(Faulty, &rdev->flags)
 			    && !test_bit(In_sync, &rdev->flags)
@@ -3810,7 +3777,6 @@ handle_failed_sync(struct r5conf *conf, struct stripe_head *sh,
 						   RAID5_STRIPE_SECTORS(conf), 0))
 				abort = 1;
 		}
-		rcu_read_unlock();
 		if (abort)
 			conf->recovery_disabled =
 				conf->mddev->recovery_disabled;
@@ -3823,15 +3789,13 @@ static int want_replace(struct stripe_head *sh, int disk_idx)
 	struct md_rdev *rdev;
 	int rv = 0;
 
-	rcu_read_lock();
-	rdev = rcu_dereference(sh->raid_conf->disks[disk_idx].replacement);
+	rdev = sh->raid_conf->disks[disk_idx].replacement;
 	if (rdev
 	    && !test_bit(Faulty, &rdev->flags)
 	    && !test_bit(In_sync, &rdev->flags)
 	    && (rdev->recovery_offset <= sh->sector
 		|| rdev->mddev->recovery_cp <= sh->sector))
 		rv = 1;
-	rcu_read_unlock();
 	return rv;
 }
 
@@ -4708,7 +4672,6 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 	s->log_failed = r5l_log_disk_error(conf);
 
 	/* Now to look around and see what can be done */
-	rcu_read_lock();
 	for (i=disks; i--; ) {
 		struct md_rdev *rdev;
 		sector_t first_bad;
@@ -4753,7 +4716,7 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 		/* Prefer to use the replacement for reads, but only
 		 * if it is recovered enough and has no bad blocks.
 		 */
-		rdev = rcu_dereference(conf->disks[i].replacement);
+		rdev = conf->disks[i].replacement;
 		if (rdev && !test_bit(Faulty, &rdev->flags) &&
 		    rdev->recovery_offset >= sh->sector + RAID5_STRIPE_SECTORS(conf) &&
 		    !is_badblock(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf),
@@ -4764,7 +4727,7 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 				set_bit(R5_NeedReplace, &dev->flags);
 			else
 				clear_bit(R5_NeedReplace, &dev->flags);
-			rdev = rcu_dereference(conf->disks[i].rdev);
+			rdev = conf->disks[i].rdev;
 			clear_bit(R5_ReadRepl, &dev->flags);
 		}
 		if (rdev && test_bit(Faulty, &rdev->flags))
@@ -4811,8 +4774,8 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 		if (test_bit(R5_WriteError, &dev->flags)) {
 			/* This flag does not apply to '.replacement'
 			 * only to .rdev, so make sure to check that*/
-			struct md_rdev *rdev2 = rcu_dereference(
-				conf->disks[i].rdev);
+			struct md_rdev *rdev2 = conf->disks[i].rdev;
+
 			if (rdev2 == rdev)
 				clear_bit(R5_Insync, &dev->flags);
 			if (rdev2 && !test_bit(Faulty, &rdev2->flags)) {
@@ -4824,8 +4787,8 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 		if (test_bit(R5_MadeGood, &dev->flags)) {
 			/* This flag does not apply to '.replacement'
 			 * only to .rdev, so make sure to check that*/
-			struct md_rdev *rdev2 = rcu_dereference(
-				conf->disks[i].rdev);
+			struct md_rdev *rdev2 = conf->disks[i].rdev;
+
 			if (rdev2 && !test_bit(Faulty, &rdev2->flags)) {
 				s->handle_bad_blocks = 1;
 				atomic_inc(&rdev2->nr_pending);
@@ -4833,8 +4796,8 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 				clear_bit(R5_MadeGood, &dev->flags);
 		}
 		if (test_bit(R5_MadeGoodRepl, &dev->flags)) {
-			struct md_rdev *rdev2 = rcu_dereference(
-				conf->disks[i].replacement);
+			struct md_rdev *rdev2 = conf->disks[i].replacement;
+
 			if (rdev2 && !test_bit(Faulty, &rdev2->flags)) {
 				s->handle_bad_blocks = 1;
 				atomic_inc(&rdev2->nr_pending);
@@ -4855,8 +4818,7 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 			if (rdev && !test_bit(Faulty, &rdev->flags))
 				do_recovery = 1;
 			else if (!rdev) {
-				rdev = rcu_dereference(
-				    conf->disks[i].replacement);
+				rdev = conf->disks[i].replacement;
 				if (rdev && !test_bit(Faulty, &rdev->flags))
 					do_recovery = 1;
 			}
@@ -4883,7 +4845,6 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 		else
 			s->replacing = 1;
 	}
-	rcu_read_unlock();
 }
 
 /*
@@ -5340,23 +5301,23 @@ finish:
 			struct r5dev *dev = &sh->dev[i];
 			if (test_and_clear_bit(R5_WriteError, &dev->flags)) {
 				/* We own a safe reference to the rdev */
-				rdev = rdev_pend_deref(conf->disks[i].rdev);
+				rdev = conf->disks[i].rdev;
 				if (!rdev_set_badblocks(rdev, sh->sector,
 							RAID5_STRIPE_SECTORS(conf), 0))
 					md_error(conf->mddev, rdev);
 				rdev_dec_pending(rdev, conf->mddev);
 			}
 			if (test_and_clear_bit(R5_MadeGood, &dev->flags)) {
-				rdev = rdev_pend_deref(conf->disks[i].rdev);
+				rdev = conf->disks[i].rdev;
 				rdev_clear_badblocks(rdev, sh->sector,
 						     RAID5_STRIPE_SECTORS(conf), 0);
 				rdev_dec_pending(rdev, conf->mddev);
 			}
 			if (test_and_clear_bit(R5_MadeGoodRepl, &dev->flags)) {
-				rdev = rdev_pend_deref(conf->disks[i].replacement);
+				rdev = conf->disks[i].replacement;
 				if (!rdev)
 					/* rdev have been moved down */
-					rdev = rdev_pend_deref(conf->disks[i].rdev);
+					rdev = conf->disks[i].rdev;
 				rdev_clear_badblocks(rdev, sh->sector,
 						     RAID5_STRIPE_SECTORS(conf), 0);
 				rdev_dec_pending(rdev, conf->mddev);
@@ -5515,24 +5476,22 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 				      &dd_idx, NULL);
 	end_sector = sector + bio_sectors(raid_bio);
 
-	rcu_read_lock();
 	if (r5c_big_stripe_cached(conf, sector))
-		goto out_rcu_unlock;
+		return 0;
 
-	rdev = rcu_dereference(conf->disks[dd_idx].replacement);
+	rdev = conf->disks[dd_idx].replacement;
 	if (!rdev || test_bit(Faulty, &rdev->flags) ||
 	    rdev->recovery_offset < end_sector) {
-		rdev = rcu_dereference(conf->disks[dd_idx].rdev);
+		rdev = conf->disks[dd_idx].rdev;
 		if (!rdev)
-			goto out_rcu_unlock;
+			return 0;
 		if (test_bit(Faulty, &rdev->flags) ||
 		    !(test_bit(In_sync, &rdev->flags) ||
 		      rdev->recovery_offset >= end_sector))
-			goto out_rcu_unlock;
+			return 0;
 	}
 
 	atomic_inc(&rdev->nr_pending);
-	rcu_read_unlock();
 
 	if (is_badblock(rdev, sector, bio_sectors(raid_bio), &first_bad,
 			&bad_sectors)) {
@@ -5576,10 +5535,6 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 				      raid_bio->bi_iter.bi_sector);
 	submit_bio_noacct(align_bio);
 	return 1;
-
-out_rcu_unlock:
-	rcu_read_unlock();
-	return 0;
 }
 
 static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio)
@@ -5892,11 +5847,11 @@ static bool stripe_ahead_of_reshape(struct mddev *mddev, struct r5conf *conf,
 	int dd_idx;
 
 	for (dd_idx = 0; dd_idx < sh->disks; dd_idx++) {
-		if (dd_idx == sh->pd_idx)
+		if (dd_idx == sh->pd_idx || dd_idx == sh->qd_idx)
 			continue;
 
 		min_sector = min(min_sector, sh->dev[dd_idx].sector);
-		max_sector = min(max_sector, sh->dev[dd_idx].sector);
+		max_sector = max(max_sector, sh->dev[dd_idx].sector);
 	}
 
 	spin_lock_irq(&conf->device_lock);
@@ -6582,14 +6537,12 @@ static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_n
 	 * Note in case of > 1 drive failures it's possible we're rebuilding
 	 * one drive while leaving another faulty drive in array.
 	 */
-	rcu_read_lock();
 	for (i = 0; i < conf->raid_disks; i++) {
-		struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
+		struct md_rdev *rdev = conf->disks[i].rdev;
 
 		if (rdev == NULL || test_bit(Faulty, &rdev->flags))
 			still_degraded = 1;
 	}
-	rcu_read_unlock();
 
 	md_bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, still_degraded);
 
@@ -6820,18 +6773,7 @@ static void raid5d(struct md_thread *thread)
 			spin_unlock_irq(&conf->device_lock);
 			md_check_recovery(mddev);
 			spin_lock_irq(&conf->device_lock);
-
-			/*
-			 * Waiting on MD_SB_CHANGE_PENDING below may deadlock
-			 * seeing md_check_recovery() is needed to clear
-			 * the flag when using mdmon.
-			 */
-			continue;
 		}
-
-		wait_event_lock_irq(mddev->sb_wait,
-			!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags),
-			conf->device_lock);
 	}
 	pr_debug("%d stripes handled\n", handled);
 
@@ -7911,18 +7853,10 @@ static int raid5_run(struct mddev *mddev)
 
 	for (i = 0; i < conf->raid_disks && conf->previous_raid_disks;
 	     i++) {
-		rdev = rdev_mdlock_deref(mddev, conf->disks[i].rdev);
-		if (!rdev && conf->disks[i].replacement) {
-			/* The replacement is all we have yet */
-			rdev = rdev_mdlock_deref(mddev,
-						 conf->disks[i].replacement);
-			conf->disks[i].replacement = NULL;
-			clear_bit(Replacement, &rdev->flags);
-			rcu_assign_pointer(conf->disks[i].rdev, rdev);
-		}
+		rdev = conf->disks[i].rdev;
 		if (!rdev)
 			continue;
-		if (rcu_access_pointer(conf->disks[i].replacement) &&
+		if (conf->disks[i].replacement &&
 		    conf->reshape_progress != MaxSector) {
 			/* replacements and reshape simply do not mix. */
 			pr_warn("md: cannot handle concurrent replacement and reshape.\n");
@@ -8106,15 +8040,16 @@ static void raid5_status(struct seq_file *seq, struct mddev *mddev)
 	struct r5conf *conf = mddev->private;
 	int i;
 
+	lockdep_assert_held(&mddev->lock);
+
 	seq_printf(seq, " level %d, %dk chunk, algorithm %d", mddev->level,
 		conf->chunk_sectors / 2, mddev->layout);
 	seq_printf (seq, " [%d/%d] [", conf->raid_disks, conf->raid_disks - mddev->degraded);
-	rcu_read_lock();
 	for (i = 0; i < conf->raid_disks; i++) {
-		struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
+		struct md_rdev *rdev = READ_ONCE(conf->disks[i].rdev);
+
 		seq_printf (seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_");
 	}
-	rcu_read_unlock();
 	seq_printf (seq, "]");
 }
 
@@ -8152,9 +8087,8 @@ static int raid5_spare_active(struct mddev *mddev)
 	unsigned long flags;
 
 	for (i = 0; i < conf->raid_disks; i++) {
-		rdev = rdev_mdlock_deref(mddev, conf->disks[i].rdev);
-		replacement = rdev_mdlock_deref(mddev,
-						conf->disks[i].replacement);
+		rdev = conf->disks[i].rdev;
+		replacement = conf->disks[i].replacement;
 		if (replacement
 		    && replacement->recovery_offset == MaxSector
 		    && !test_bit(Faulty, &replacement->flags)
@@ -8193,7 +8127,7 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 	struct r5conf *conf = mddev->private;
 	int err = 0;
 	int number = rdev->raid_disk;
-	struct md_rdev __rcu **rdevp;
+	struct md_rdev **rdevp;
 	struct disk_info *p;
 	struct md_rdev *tmp;
 
@@ -8216,9 +8150,9 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 	if (unlikely(number >= conf->pool_size))
 		return 0;
 	p = conf->disks + number;
-	if (rdev == rcu_access_pointer(p->rdev))
+	if (rdev == p->rdev)
 		rdevp = &p->rdev;
-	else if (rdev == rcu_access_pointer(p->replacement))
+	else if (rdev == p->replacement)
 		rdevp = &p->replacement;
 	else
 		return 0;
@@ -8238,37 +8172,24 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 	if (!test_bit(Faulty, &rdev->flags) &&
 	    mddev->recovery_disabled != conf->recovery_disabled &&
 	    !has_failed(conf) &&
-	    (!rcu_access_pointer(p->replacement) ||
-	     rcu_access_pointer(p->replacement) == rdev) &&
+	    (!p->replacement || p->replacement == rdev) &&
 	    number < conf->raid_disks) {
 		err = -EBUSY;
 		goto abort;
 	}
-	*rdevp = NULL;
-	if (!test_bit(RemoveSynchronized, &rdev->flags)) {
-		lockdep_assert_held(&mddev->reconfig_mutex);
-		synchronize_rcu();
-		if (atomic_read(&rdev->nr_pending)) {
-			/* lost the race, try later */
-			err = -EBUSY;
-			rcu_assign_pointer(*rdevp, rdev);
-		}
-	}
+	WRITE_ONCE(*rdevp, NULL);
 	if (!err) {
 		err = log_modify(conf, rdev, false);
 		if (err)
 			goto abort;
 	}
 
-	tmp = rcu_access_pointer(p->replacement);
+	tmp = p->replacement;
 	if (tmp) {
 		/* We must have just cleared 'rdev' */
-		rcu_assign_pointer(p->rdev, tmp);
+		WRITE_ONCE(p->rdev, tmp);
 		clear_bit(Replacement, &tmp->flags);
-		smp_mb(); /* Make sure other CPUs may see both as identical
-			   * but will never see neither - if they are careful
-			   */
-		rcu_assign_pointer(p->replacement, NULL);
+		WRITE_ONCE(p->replacement, NULL);
 
 		if (!err)
 			err = log_modify(conf, tmp, true);
@@ -8336,7 +8257,7 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			rdev->raid_disk = disk;
 			if (rdev->saved_raid_disk != disk)
 				conf->fullsync = 1;
-			rcu_assign_pointer(p->rdev, rdev);
+			WRITE_ONCE(p->rdev, rdev);
 
 			err = log_modify(conf, rdev, true);
 
@@ -8345,7 +8266,7 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	}
 	for (disk = first; disk <= last; disk++) {
 		p = conf->disks + disk;
-		tmp = rdev_mdlock_deref(mddev, p->rdev);
+		tmp = p->rdev;
 		if (test_bit(WantReplacement, &tmp->flags) &&
 		    mddev->reshape_position == MaxSector &&
 		    p->replacement == NULL) {
@@ -8354,7 +8275,7 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			rdev->raid_disk = disk;
 			err = 0;
 			conf->fullsync = 1;
-			rcu_assign_pointer(p->replacement, rdev);
+			WRITE_ONCE(p->replacement, rdev);
 			break;
 		}
 	}
@@ -8487,7 +8408,7 @@ static int raid5_start_reshape(struct mddev *mddev)
 	if (mddev->recovery_cp < MaxSector)
 		return -EBUSY;
 	for (i = 0; i < conf->raid_disks; i++)
-		if (rdev_mdlock_deref(mddev, conf->disks[i].replacement))
+		if (conf->disks[i].replacement)
 			return -EBUSY;
 
 	rdev_for_each(rdev, mddev) {
@@ -8658,12 +8579,10 @@ static void raid5_finish_reshape(struct mddev *mddev)
 			for (d = conf->raid_disks ;
 			     d < conf->raid_disks - mddev->delta_disks;
 			     d++) {
-				rdev = rdev_mdlock_deref(mddev,
-							 conf->disks[d].rdev);
+				rdev = conf->disks[d].rdev;
 				if (rdev)
 					clear_bit(In_sync, &rdev->flags);
-				rdev = rdev_mdlock_deref(mddev,
-						conf->disks[d].replacement);
+				rdev = conf->disks[d].replacement;
 				if (rdev)
 					clear_bit(In_sync, &rdev->flags);
 			}
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 22bea20eccbd..9b5a7dc3f2a0 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -473,8 +473,8 @@ enum {
  */
 
 struct disk_info {
-	struct md_rdev	__rcu *rdev;
-	struct md_rdev  __rcu *replacement;
+	struct md_rdev	*rdev;
+	struct md_rdev	*replacement;
 	struct page	*extra_page; /* extra page to use in prexor */
 };
 
diff --git a/drivers/media/pci/mgb4/Kconfig b/drivers/media/pci/mgb4/Kconfig
index 13fad15a434c..f2a05a1c8ffa 100644
--- a/drivers/media/pci/mgb4/Kconfig
+++ b/drivers/media/pci/mgb4/Kconfig
@@ -2,6 +2,7 @@
 config VIDEO_MGB4
 	tristate "Digiteq Automotive MGB4 support"
 	depends on VIDEO_DEV && PCI && I2C && DMADEVICES && SPI && MTD && IIO
+	depends on COMMON_CLK
 	select VIDEOBUF2_DMA_SG
 	select IIO_BUFFER
 	select IIO_TRIGGERED_BUFFER
diff --git a/drivers/media/pci/mgb4/mgb4_core.c b/drivers/media/pci/mgb4/mgb4_core.c
index 3efb33fbf40c..5bfb8a06202e 100644
--- a/drivers/media/pci/mgb4/mgb4_core.c
+++ b/drivers/media/pci/mgb4/mgb4_core.c
@@ -42,6 +42,10 @@
 
 #define MGB4_USER_IRQS 16
 
+#define DIGITEQ_VID 0x1ed8
+#define T100_DID    0x0101
+#define T200_DID    0x0201
+
 ATTRIBUTE_GROUPS(mgb4_pci);
 
 static int flashid;
@@ -151,7 +155,7 @@ static struct spi_master *get_spi_adap(struct platform_device *pdev)
 	return dev ? container_of(dev, struct spi_master, dev) : NULL;
 }
 
-static int init_spi(struct mgb4_dev *mgbdev)
+static int init_spi(struct mgb4_dev *mgbdev, u32 devid)
 {
 	struct resource spi_resources[] = {
 		{
@@ -213,8 +217,13 @@ static int init_spi(struct mgb4_dev *mgbdev)
 	snprintf(mgbdev->fw_part_name, sizeof(mgbdev->fw_part_name),
 		 "mgb4-fw.%d", flashid);
 	mgbdev->partitions[0].name = mgbdev->fw_part_name;
-	mgbdev->partitions[0].size = 0x400000;
-	mgbdev->partitions[0].offset = 0x400000;
+	if (devid == T200_DID) {
+		mgbdev->partitions[0].size = 0x950000;
+		mgbdev->partitions[0].offset = 0x1000000;
+	} else {
+		mgbdev->partitions[0].size = 0x400000;
+		mgbdev->partitions[0].offset = 0x400000;
+	}
 	mgbdev->partitions[0].mask_flags = 0;
 
 	snprintf(mgbdev->data_part_name, sizeof(mgbdev->data_part_name),
@@ -551,7 +560,7 @@ static int mgb4_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_video_regs;
 
 	/* SPI FLASH */
-	rv = init_spi(mgbdev);
+	rv = init_spi(mgbdev, id->device);
 	if (rv < 0)
 		goto err_cmt_regs;
 
@@ -666,7 +675,8 @@ static void mgb4_remove(struct pci_dev *pdev)
 }
 
 static const struct pci_device_id mgb4_pci_ids[] = {
-	{ PCI_DEVICE(0x1ed8, 0x0101), },
+	{ PCI_DEVICE(DIGITEQ_VID, T100_DID), },
+	{ PCI_DEVICE(DIGITEQ_VID, T200_DID), },
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, mgb4_pci_ids);
diff --git a/drivers/media/platform/renesas/vsp1/vsp1_pipe.c b/drivers/media/platform/renesas/vsp1/vsp1_pipe.c
index f8093ba9539e..68d05243c3ee 100644
--- a/drivers/media/platform/renesas/vsp1/vsp1_pipe.c
+++ b/drivers/media/platform/renesas/vsp1/vsp1_pipe.c
@@ -373,7 +373,7 @@ int vsp1_pipeline_stop(struct vsp1_pipeline *pipe)
 			   (7 << VI6_DPR_SMPPT_TGW_SHIFT) |
 			   (VI6_DPR_NODE_UNUSED << VI6_DPR_SMPPT_PT_SHIFT));
 
-	v4l2_subdev_call(&pipe->output->entity.subdev, video, s_stream, 0);
+	vsp1_wpf_stop(pipe->output);
 
 	return ret;
 }
diff --git a/drivers/media/platform/renesas/vsp1/vsp1_rpf.c b/drivers/media/platform/renesas/vsp1/vsp1_rpf.c
index 3b17f5fa4067..ea12c3f12c92 100644
--- a/drivers/media/platform/renesas/vsp1/vsp1_rpf.c
+++ b/drivers/media/platform/renesas/vsp1/vsp1_rpf.c
@@ -44,14 +44,6 @@ static inline void vsp1_rpf_write(struct vsp1_rwpf *rpf,
 }
 
 /* -----------------------------------------------------------------------------
- * V4L2 Subdevice Operations
- */
-
-static const struct v4l2_subdev_ops rpf_ops = {
-	.pad    = &vsp1_rwpf_pad_ops,
-};
-
-/* -----------------------------------------------------------------------------
  * VSP1 Entity Operations
  */
 
@@ -411,7 +403,7 @@ struct vsp1_rwpf *vsp1_rpf_create(struct vsp1_device *vsp1, unsigned int index)
 	rpf->entity.index = index;
 
 	sprintf(name, "rpf.%u", index);
-	ret = vsp1_entity_init(vsp1, &rpf->entity, name, 2, &rpf_ops,
+	ret = vsp1_entity_init(vsp1, &rpf->entity, name, 2, &vsp1_rwpf_subdev_ops,
 			       MEDIA_ENT_F_PROC_VIDEO_PIXEL_FORMATTER);
 	if (ret < 0)
 		return ERR_PTR(ret);
diff --git a/drivers/media/platform/renesas/vsp1/vsp1_rwpf.c b/drivers/media/platform/renesas/vsp1/vsp1_rwpf.c
index 22a82d218152..e0f87c8103ca 100644
--- a/drivers/media/platform/renesas/vsp1/vsp1_rwpf.c
+++ b/drivers/media/platform/renesas/vsp1/vsp1_rwpf.c
@@ -24,7 +24,7 @@ struct v4l2_rect *vsp1_rwpf_get_crop(struct vsp1_rwpf *rwpf,
 }
 
 /* -----------------------------------------------------------------------------
- * V4L2 Subdevice Pad Operations
+ * V4L2 Subdevice Operations
  */
 
 static int vsp1_rwpf_enum_mbus_code(struct v4l2_subdev *subdev,
@@ -243,7 +243,7 @@ done:
 	return ret;
 }
 
-const struct v4l2_subdev_pad_ops vsp1_rwpf_pad_ops = {
+static const struct v4l2_subdev_pad_ops vsp1_rwpf_pad_ops = {
 	.init_cfg = vsp1_entity_init_cfg,
 	.enum_mbus_code = vsp1_rwpf_enum_mbus_code,
 	.enum_frame_size = vsp1_rwpf_enum_frame_size,
@@ -253,6 +253,10 @@ const struct v4l2_subdev_pad_ops vsp1_rwpf_pad_ops = {
 	.set_selection = vsp1_rwpf_set_selection,
 };
 
+const struct v4l2_subdev_ops vsp1_rwpf_subdev_ops = {
+	.pad    = &vsp1_rwpf_pad_ops,
+};
+
 /* -----------------------------------------------------------------------------
  * Controls
  */
diff --git a/drivers/media/platform/renesas/vsp1/vsp1_rwpf.h b/drivers/media/platform/renesas/vsp1/vsp1_rwpf.h
index eac5c04c2239..e0d212c70b2f 100644
--- a/drivers/media/platform/renesas/vsp1/vsp1_rwpf.h
+++ b/drivers/media/platform/renesas/vsp1/vsp1_rwpf.h
@@ -79,9 +79,11 @@ static inline struct vsp1_rwpf *entity_to_rwpf(struct vsp1_entity *entity)
 struct vsp1_rwpf *vsp1_rpf_create(struct vsp1_device *vsp1, unsigned int index);
 struct vsp1_rwpf *vsp1_wpf_create(struct vsp1_device *vsp1, unsigned int index);
 
+void vsp1_wpf_stop(struct vsp1_rwpf *wpf);
+
 int vsp1_rwpf_init_ctrls(struct vsp1_rwpf *rwpf, unsigned int ncontrols);
 
-extern const struct v4l2_subdev_pad_ops vsp1_rwpf_pad_ops;
+extern const struct v4l2_subdev_ops vsp1_rwpf_subdev_ops;
 
 struct v4l2_rect *vsp1_rwpf_get_crop(struct vsp1_rwpf *rwpf,
 				     struct v4l2_subdev_state *sd_state);
diff --git a/drivers/media/platform/renesas/vsp1/vsp1_wpf.c b/drivers/media/platform/renesas/vsp1/vsp1_wpf.c
index d0074ca00920..cab4445eca69 100644
--- a/drivers/media/platform/renesas/vsp1/vsp1_wpf.c
+++ b/drivers/media/platform/renesas/vsp1/vsp1_wpf.c
@@ -186,17 +186,13 @@ static int wpf_init_controls(struct vsp1_rwpf *wpf)
 }
 
 /* -----------------------------------------------------------------------------
- * V4L2 Subdevice Core Operations
+ * VSP1 Entity Operations
  */
 
-static int wpf_s_stream(struct v4l2_subdev *subdev, int enable)
+void vsp1_wpf_stop(struct vsp1_rwpf *wpf)
 {
-	struct vsp1_rwpf *wpf = to_rwpf(subdev);
 	struct vsp1_device *vsp1 = wpf->entity.vsp1;
 
-	if (enable)
-		return 0;
-
 	/*
 	 * Write to registers directly when stopping the stream as there will be
 	 * no pipeline run to apply the display list.
@@ -204,27 +200,8 @@ static int wpf_s_stream(struct v4l2_subdev *subdev, int enable)
 	vsp1_write(vsp1, VI6_WPF_IRQ_ENB(wpf->entity.index), 0);
 	vsp1_write(vsp1, wpf->entity.index * VI6_WPF_OFFSET +
 		   VI6_WPF_SRCRPF, 0);
-
-	return 0;
 }
 
-/* -----------------------------------------------------------------------------
- * V4L2 Subdevice Operations
- */
-
-static const struct v4l2_subdev_video_ops wpf_video_ops = {
-	.s_stream = wpf_s_stream,
-};
-
-static const struct v4l2_subdev_ops wpf_ops = {
-	.video	= &wpf_video_ops,
-	.pad    = &vsp1_rwpf_pad_ops,
-};
-
-/* -----------------------------------------------------------------------------
- * VSP1 Entity Operations
- */
-
 static void vsp1_wpf_destroy(struct vsp1_entity *entity)
 {
 	struct vsp1_rwpf *wpf = entity_to_rwpf(entity);
@@ -583,7 +560,7 @@ struct vsp1_rwpf *vsp1_wpf_create(struct vsp1_device *vsp1, unsigned int index)
 	wpf->entity.index = index;
 
 	sprintf(name, "wpf.%u", index);
-	ret = vsp1_entity_init(vsp1, &wpf->entity, name, 2, &wpf_ops,
+	ret = vsp1_entity_init(vsp1, &wpf->entity, name, 2, &vsp1_rwpf_subdev_ops,
 			       MEDIA_ENT_F_PROC_VIDEO_PIXEL_FORMATTER);
 	if (ret < 0)
 		return ERR_PTR(ret);
diff --git a/drivers/media/test-drivers/vidtv/vidtv_pes.c b/drivers/media/test-drivers/vidtv/vidtv_pes.c
index 782e5e7fbb02..6a360a0a3ccf 100644
--- a/drivers/media/test-drivers/vidtv/vidtv_pes.c
+++ b/drivers/media/test-drivers/vidtv/vidtv_pes.c
@@ -14,6 +14,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ":%s, %d: " fmt, __func__, __LINE__
 
 #include <linux/types.h>
+#include <linux/math64.h>
 #include <linux/printk.h>
 #include <linux/ratelimit.h>
 
diff --git a/drivers/memory/brcmstb_dpfe.c b/drivers/memory/brcmstb_dpfe.c
index a7ab3d377206..5028467b2dc9 100644
--- a/drivers/memory/brcmstb_dpfe.c
+++ b/drivers/memory/brcmstb_dpfe.c
@@ -909,13 +909,11 @@ static int brcmstb_dpfe_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int brcmstb_dpfe_remove(struct platform_device *pdev)
+static void brcmstb_dpfe_remove(struct platform_device *pdev)
 {
 	struct brcmstb_dpfe_priv *priv = dev_get_drvdata(&pdev->dev);
 
 	sysfs_remove_groups(&pdev->dev.kobj, priv->dpfe_api->sysfs_attrs);
-
-	return 0;
 }
 
 static const struct of_device_id brcmstb_dpfe_of_match[] = {
@@ -936,7 +934,7 @@ static struct platform_driver brcmstb_dpfe_driver = {
 		.of_match_table = brcmstb_dpfe_of_match,
 	},
 	.probe = brcmstb_dpfe_probe,
-	.remove	= brcmstb_dpfe_remove,
+	.remove_new = brcmstb_dpfe_remove,
 	.resume = brcmstb_dpfe_resume,
 };
 
diff --git a/drivers/memory/brcmstb_memc.c b/drivers/memory/brcmstb_memc.c
index a6ea51996522..ea9213f7152e 100644
--- a/drivers/memory/brcmstb_memc.c
+++ b/drivers/memory/brcmstb_memc.c
@@ -152,13 +152,11 @@ static int brcmstb_memc_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int brcmstb_memc_remove(struct platform_device *pdev)
+static void brcmstb_memc_remove(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 
 	sysfs_remove_group(&dev->kobj, &dev_attr_group);
-
-	return 0;
 }
 
 enum brcmstb_memc_hwtype {
@@ -284,7 +282,7 @@ static DEFINE_SIMPLE_DEV_PM_OPS(brcmstb_memc_pm_ops, brcmstb_memc_suspend,
 
 static struct platform_driver brcmstb_memc_driver = {
 	.probe = brcmstb_memc_probe,
-	.remove = brcmstb_memc_remove,
+	.remove_new = brcmstb_memc_remove,
 	.driver = {
 		.name		= "brcmstb_memc",
 		.of_match_table	= brcmstb_memc_of_match,
diff --git a/drivers/memory/emif.c b/drivers/memory/emif.c
index f305643209f0..434982545be6 100644
--- a/drivers/memory/emif.c
+++ b/drivers/memory/emif.c
@@ -1159,13 +1159,11 @@ error:
 	return -ENODEV;
 }
 
-static int __exit emif_remove(struct platform_device *pdev)
+static void __exit emif_remove(struct platform_device *pdev)
 {
 	struct emif_data *emif = platform_get_drvdata(pdev);
 
 	emif_debugfs_exit(emif);
-
-	return 0;
 }
 
 static void emif_shutdown(struct platform_device *pdev)
@@ -1185,7 +1183,7 @@ MODULE_DEVICE_TABLE(of, emif_of_match);
 #endif
 
 static struct platform_driver emif_driver = {
-	.remove		= __exit_p(emif_remove),
+	.remove_new	= __exit_p(emif_remove),
 	.shutdown	= emif_shutdown,
 	.driver = {
 		.name = "emif",
diff --git a/drivers/memory/fsl-corenet-cf.c b/drivers/memory/fsl-corenet-cf.c
index 8096c4f33303..f47d05f7c5c5 100644
--- a/drivers/memory/fsl-corenet-cf.c
+++ b/drivers/memory/fsl-corenet-cf.c
@@ -223,7 +223,7 @@ static int ccf_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int ccf_remove(struct platform_device *pdev)
+static void ccf_remove(struct platform_device *pdev)
 {
 	struct ccf_private *ccf = dev_get_drvdata(&pdev->dev);
 
@@ -241,8 +241,6 @@ static int ccf_remove(struct platform_device *pdev)
 		iowrite32be(0, &ccf->err_regs->errinten);
 		break;
 	}
-
-	return 0;
 }
 
 static struct platform_driver ccf_driver = {
@@ -251,7 +249,7 @@ static struct platform_driver ccf_driver = {
 		.of_match_table = ccf_matches,
 	},
 	.probe = ccf_probe,
-	.remove = ccf_remove,
+	.remove_new = ccf_remove,
 };
 
 module_platform_driver(ccf_driver);
diff --git a/drivers/memory/fsl_ifc.c b/drivers/memory/fsl_ifc.c
index 2509e5152036..15e919c24f81 100644
--- a/drivers/memory/fsl_ifc.c
+++ b/drivers/memory/fsl_ifc.c
@@ -84,7 +84,7 @@ static int fsl_ifc_ctrl_init(struct fsl_ifc_ctrl *ctrl)
 	return 0;
 }
 
-static int fsl_ifc_ctrl_remove(struct platform_device *dev)
+static void fsl_ifc_ctrl_remove(struct platform_device *dev)
 {
 	struct fsl_ifc_ctrl *ctrl = dev_get_drvdata(&dev->dev);
 
@@ -98,8 +98,6 @@ static int fsl_ifc_ctrl_remove(struct platform_device *dev)
 	iounmap(ctrl->gregs);
 
 	dev_set_drvdata(&dev->dev, NULL);
-
-	return 0;
 }
 
 /*
@@ -318,7 +316,7 @@ static struct platform_driver fsl_ifc_ctrl_driver = {
 		.of_match_table = fsl_ifc_match,
 	},
 	.probe       = fsl_ifc_ctrl_probe,
-	.remove      = fsl_ifc_ctrl_remove,
+	.remove_new  = fsl_ifc_ctrl_remove,
 };
 
 static int __init fsl_ifc_init(void)
diff --git a/drivers/memory/jz4780-nemc.c b/drivers/memory/jz4780-nemc.c
index e5a93e7da15f..fb6db2ffe71b 100644
--- a/drivers/memory/jz4780-nemc.c
+++ b/drivers/memory/jz4780-nemc.c
@@ -384,12 +384,11 @@ static int jz4780_nemc_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int jz4780_nemc_remove(struct platform_device *pdev)
+static void jz4780_nemc_remove(struct platform_device *pdev)
 {
 	struct jz4780_nemc *nemc = platform_get_drvdata(pdev);
 
 	clk_disable_unprepare(nemc->clk);
-	return 0;
 }
 
 static const struct jz_soc_info jz4740_soc_info = {
@@ -408,7 +407,7 @@ static const struct of_device_id jz4780_nemc_dt_match[] = {
 
 static struct platform_driver jz4780_nemc_driver = {
 	.probe		= jz4780_nemc_probe,
-	.remove		= jz4780_nemc_remove,
+	.remove_new	= jz4780_nemc_remove,
 	.driver	= {
 		.name	= "jz4780-nemc",
 		.of_match_table = of_match_ptr(jz4780_nemc_dt_match),
diff --git a/drivers/memory/mtk-smi.c b/drivers/memory/mtk-smi.c
index 6523cb510518..572c7fbdcfd3 100644
--- a/drivers/memory/mtk-smi.c
+++ b/drivers/memory/mtk-smi.c
@@ -566,14 +566,13 @@ err_pm_disable:
 	return ret;
 }
 
-static int mtk_smi_larb_remove(struct platform_device *pdev)
+static void mtk_smi_larb_remove(struct platform_device *pdev)
 {
 	struct mtk_smi_larb *larb = platform_get_drvdata(pdev);
 
 	device_link_remove(&pdev->dev, larb->smi_common_dev);
 	pm_runtime_disable(&pdev->dev);
 	component_del(&pdev->dev, &mtk_smi_larb_component_ops);
-	return 0;
 }
 
 static int __maybe_unused mtk_smi_larb_resume(struct device *dev)
@@ -616,7 +615,7 @@ static const struct dev_pm_ops smi_larb_pm_ops = {
 
 static struct platform_driver mtk_smi_larb_driver = {
 	.probe	= mtk_smi_larb_probe,
-	.remove	= mtk_smi_larb_remove,
+	.remove_new = mtk_smi_larb_remove,
 	.driver	= {
 		.name = "mtk-smi-larb",
 		.of_match_table = mtk_smi_larb_of_ids,
@@ -795,14 +794,13 @@ static int mtk_smi_common_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int mtk_smi_common_remove(struct platform_device *pdev)
+static void mtk_smi_common_remove(struct platform_device *pdev)
 {
 	struct mtk_smi *common = dev_get_drvdata(&pdev->dev);
 
 	if (common->plat->type == MTK_SMI_GEN2_SUB_COMM)
 		device_link_remove(&pdev->dev, common->smi_common_dev);
 	pm_runtime_disable(&pdev->dev);
-	return 0;
 }
 
 static int __maybe_unused mtk_smi_common_resume(struct device *dev)
@@ -842,7 +840,7 @@ static const struct dev_pm_ops smi_common_pm_ops = {
 
 static struct platform_driver mtk_smi_common_driver = {
 	.probe	= mtk_smi_common_probe,
-	.remove = mtk_smi_common_remove,
+	.remove_new = mtk_smi_common_remove,
 	.driver	= {
 		.name = "mtk-smi-common",
 		.of_match_table = mtk_smi_common_of_ids,
diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c
index d78f73db37c8..80d038884207 100644
--- a/drivers/memory/omap-gpmc.c
+++ b/drivers/memory/omap-gpmc.c
@@ -2690,7 +2690,7 @@ gpio_init_failed:
 	return rc;
 }
 
-static int gpmc_remove(struct platform_device *pdev)
+static void gpmc_remove(struct platform_device *pdev)
 {
 	int i;
 	struct gpmc_device *gpmc = platform_get_drvdata(pdev);
@@ -2702,8 +2702,6 @@ static int gpmc_remove(struct platform_device *pdev)
 	gpmc_mem_exit();
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -2747,7 +2745,7 @@ MODULE_DEVICE_TABLE(of, gpmc_dt_ids);
 
 static struct platform_driver gpmc_driver = {
 	.probe		= gpmc_probe,
-	.remove		= gpmc_remove,
+	.remove_new	= gpmc_remove,
 	.driver		= {
 		.name	= DEVICE_NAME,
 		.of_match_table = of_match_ptr(gpmc_dt_ids),
diff --git a/drivers/memory/renesas-rpc-if.c b/drivers/memory/renesas-rpc-if.c
index 9695b2d3ae59..3167826b236a 100644
--- a/drivers/memory/renesas-rpc-if.c
+++ b/drivers/memory/renesas-rpc-if.c
@@ -777,13 +777,11 @@ static int rpcif_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int rpcif_remove(struct platform_device *pdev)
+static void rpcif_remove(struct platform_device *pdev)
 {
 	struct rpcif_priv *rpc = platform_get_drvdata(pdev);
 
 	platform_device_unregister(rpc->vdev);
-
-	return 0;
 }
 
 static const struct of_device_id rpcif_of_match[] = {
@@ -797,7 +795,7 @@ MODULE_DEVICE_TABLE(of, rpcif_of_match);
 
 static struct platform_driver rpcif_driver = {
 	.probe	= rpcif_probe,
-	.remove	= rpcif_remove,
+	.remove_new = rpcif_remove,
 	.driver = {
 		.name =	"rpc-if",
 		.of_match_table = rpcif_of_match,
diff --git a/drivers/memory/samsung/exynos5422-dmc.c b/drivers/memory/samsung/exynos5422-dmc.c
index 6d019dbd721c..da7ecd921c72 100644
--- a/drivers/memory/samsung/exynos5422-dmc.c
+++ b/drivers/memory/samsung/exynos5422-dmc.c
@@ -1558,7 +1558,7 @@ remove_clocks:
  * clean the device's resources. It just calls explicitly disable function for
  * the performance counters.
  */
-static int exynos5_dmc_remove(struct platform_device *pdev)
+static void exynos5_dmc_remove(struct platform_device *pdev)
 {
 	struct exynos5_dmc *dmc = dev_get_drvdata(&pdev->dev);
 
@@ -1569,8 +1569,6 @@ static int exynos5_dmc_remove(struct platform_device *pdev)
 
 	clk_disable_unprepare(dmc->mout_bpll);
 	clk_disable_unprepare(dmc->fout_bpll);
-
-	return 0;
 }
 
 static const struct of_device_id exynos5_dmc_of_match[] = {
@@ -1581,7 +1579,7 @@ MODULE_DEVICE_TABLE(of, exynos5_dmc_of_match);
 
 static struct platform_driver exynos5_dmc_platdrv = {
 	.probe	= exynos5_dmc_probe,
-	.remove = exynos5_dmc_remove,
+	.remove_new = exynos5_dmc_remove,
 	.driver = {
 		.name	= "exynos5-dmc",
 		.of_match_table = exynos5_dmc_of_match,
diff --git a/drivers/memory/stm32-fmc2-ebi.c b/drivers/memory/stm32-fmc2-ebi.c
index 9015e8277dc8..47d0ea5f1616 100644
--- a/drivers/memory/stm32-fmc2-ebi.c
+++ b/drivers/memory/stm32-fmc2-ebi.c
@@ -1146,7 +1146,7 @@ err_release:
 	return ret;
 }
 
-static int stm32_fmc2_ebi_remove(struct platform_device *pdev)
+static void stm32_fmc2_ebi_remove(struct platform_device *pdev)
 {
 	struct stm32_fmc2_ebi *ebi = platform_get_drvdata(pdev);
 
@@ -1154,8 +1154,6 @@ static int stm32_fmc2_ebi_remove(struct platform_device *pdev)
 	stm32_fmc2_ebi_disable_banks(ebi);
 	stm32_fmc2_ebi_disable(ebi);
 	clk_disable_unprepare(ebi->clk);
-
-	return 0;
 }
 
 static int __maybe_unused stm32_fmc2_ebi_suspend(struct device *dev)
@@ -1197,7 +1195,7 @@ MODULE_DEVICE_TABLE(of, stm32_fmc2_ebi_match);
 
 static struct platform_driver stm32_fmc2_ebi_driver = {
 	.probe	= stm32_fmc2_ebi_probe,
-	.remove	= stm32_fmc2_ebi_remove,
+	.remove_new = stm32_fmc2_ebi_remove,
 	.driver	= {
 		.name = "stm32_fmc2_ebi",
 		.of_match_table = stm32_fmc2_ebi_match,
diff --git a/drivers/memory/tegra/tegra186-emc.c b/drivers/memory/tegra/tegra186-emc.c
index 4007f4e16d74..fcd4aea48bda 100644
--- a/drivers/memory/tegra/tegra186-emc.c
+++ b/drivers/memory/tegra/tegra186-emc.c
@@ -378,7 +378,7 @@ put_bpmp:
 	return err;
 }
 
-static int tegra186_emc_remove(struct platform_device *pdev)
+static void tegra186_emc_remove(struct platform_device *pdev)
 {
 	struct tegra_mc *mc = dev_get_drvdata(pdev->dev.parent);
 	struct tegra186_emc *emc = platform_get_drvdata(pdev);
@@ -387,8 +387,6 @@ static int tegra186_emc_remove(struct platform_device *pdev)
 
 	mc->bpmp = NULL;
 	tegra_bpmp_put(emc->bpmp);
-
-	return 0;
 }
 
 static const struct of_device_id tegra186_emc_of_match[] = {
@@ -413,7 +411,7 @@ static struct platform_driver tegra186_emc_driver = {
 		.sync_state = icc_sync_state,
 	},
 	.probe = tegra186_emc_probe,
-	.remove = tegra186_emc_remove,
+	.remove_new = tegra186_emc_remove,
 };
 module_platform_driver(tegra186_emc_driver);
 
diff --git a/drivers/memory/tegra/tegra186.c b/drivers/memory/tegra/tegra186.c
index 533f85a4b2bd..0ff014a9d3cd 100644
--- a/drivers/memory/tegra/tegra186.c
+++ b/drivers/memory/tegra/tegra186.c
@@ -75,6 +75,9 @@ static void tegra186_mc_client_sid_override(struct tegra_mc *mc,
 {
 	u32 value, old;
 
+	if (client->regs.sid.security == 0 && client->regs.sid.override == 0)
+		return;
+
 	value = readl(mc->regs + client->regs.sid.security);
 	if ((value & MC_SID_STREAMID_SECURITY_OVERRIDE) == 0) {
 		/*
@@ -136,9 +139,25 @@ static int tegra186_mc_probe_device(struct tegra_mc *mc, struct device *dev)
 	return 0;
 }
 
+static int tegra186_mc_resume(struct tegra_mc *mc)
+{
+#if IS_ENABLED(CONFIG_IOMMU_API)
+	unsigned int i;
+
+	for (i = 0; i < mc->soc->num_clients; i++) {
+		const struct tegra_mc_client *client = &mc->soc->clients[i];
+
+		tegra186_mc_client_sid_override(mc, client, client->sid);
+	}
+#endif
+
+	return 0;
+}
+
 const struct tegra_mc_ops tegra186_mc_ops = {
 	.probe = tegra186_mc_probe,
 	.remove = tegra186_mc_remove,
+	.resume = tegra186_mc_resume,
 	.probe_device = tegra186_mc_probe_device,
 	.handle_irq = tegra30_mc_handle_irq,
 };
diff --git a/drivers/memory/tegra/tegra210-emc-core.c b/drivers/memory/tegra/tegra210-emc-core.c
index 3300bde47c13..78ca1d6c0977 100644
--- a/drivers/memory/tegra/tegra210-emc-core.c
+++ b/drivers/memory/tegra/tegra210-emc-core.c
@@ -1985,15 +1985,13 @@ release:
 	return err;
 }
 
-static int tegra210_emc_remove(struct platform_device *pdev)
+static void tegra210_emc_remove(struct platform_device *pdev)
 {
 	struct tegra210_emc *emc = platform_get_drvdata(pdev);
 
 	debugfs_remove_recursive(emc->debugfs.root);
 	tegra210_clk_emc_detach(emc->clk);
 	of_reserved_mem_device_release(emc->dev);
-
-	return 0;
 }
 
 static int __maybe_unused tegra210_emc_suspend(struct device *dev)
@@ -2053,7 +2051,7 @@ static struct platform_driver tegra210_emc_driver = {
 		.pm = &tegra210_emc_pm_ops,
 	},
 	.probe = tegra210_emc_probe,
-	.remove = tegra210_emc_remove,
+	.remove_new = tegra210_emc_remove,
 };
 
 module_platform_driver(tegra210_emc_driver);
diff --git a/drivers/memory/ti-aemif.c b/drivers/memory/ti-aemif.c
index f81e7df8798a..e192db9e0e4b 100644
--- a/drivers/memory/ti-aemif.c
+++ b/drivers/memory/ti-aemif.c
@@ -427,17 +427,16 @@ error:
 	return ret;
 }
 
-static int aemif_remove(struct platform_device *pdev)
+static void aemif_remove(struct platform_device *pdev)
 {
 	struct aemif_device *aemif = platform_get_drvdata(pdev);
 
 	clk_disable_unprepare(aemif->clk);
-	return 0;
 }
 
 static struct platform_driver aemif_driver = {
 	.probe = aemif_probe,
-	.remove = aemif_remove,
+	.remove_new = aemif_remove,
 	.driver = {
 		.name = "ti-aemif",
 		.of_match_table = of_match_ptr(aemif_of_match),
diff --git a/drivers/memory/ti-emif-pm.c b/drivers/memory/ti-emif-pm.c
index cef0d3beb63b..592f70e9c8e5 100644
--- a/drivers/memory/ti-emif-pm.c
+++ b/drivers/memory/ti-emif-pm.c
@@ -315,15 +315,13 @@ fail_free_sram:
 	return ret;
 }
 
-static int ti_emif_remove(struct platform_device *pdev)
+static void ti_emif_remove(struct platform_device *pdev)
 {
 	struct ti_emif_data *emif_data = emif_instance;
 
 	emif_instance = NULL;
 
 	ti_emif_free_sram(emif_data);
-
-	return 0;
 }
 
 static const struct dev_pm_ops ti_emif_pm_ops = {
@@ -332,7 +330,7 @@ static const struct dev_pm_ops ti_emif_pm_ops = {
 
 static struct platform_driver ti_emif_driver = {
 	.probe = ti_emif_probe,
-	.remove = ti_emif_remove,
+	.remove_new = ti_emif_remove,
 	.driver = {
 		.name = KBUILD_MODNAME,
 		.of_match_table = ti_emif_of_match,
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 90ce58fd629e..925c19ee513b 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -2255,7 +2255,7 @@ config MFD_VEXPRESS_SYSREG
 config RAVE_SP_CORE
 	tristate "RAVE SP MCU core driver"
 	depends on SERIAL_DEV_BUS
-	select CRC_CCITT
+	select CRC_ITU_T
 	help
 	  Select this to get support for the Supervisory Processor
 	  device found on several devices in RAVE line of hardware.
diff --git a/drivers/mfd/rave-sp.c b/drivers/mfd/rave-sp.c
index da50eba10014..f62422740de2 100644
--- a/drivers/mfd/rave-sp.c
+++ b/drivers/mfd/rave-sp.c
@@ -9,7 +9,7 @@
  */
 
 #include <linux/atomic.h>
-#include <linux/crc-ccitt.h>
+#include <linux/crc-itu-t.h>
 #include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/init.h>
@@ -251,7 +251,7 @@ static void csum_8b2c(const u8 *buf, size_t size, u8 *crc)
 
 static void csum_ccitt(const u8 *buf, size_t size, u8 *crc)
 {
-	const u16 calculated = crc_ccitt_false(0xffff, buf, size);
+	const u16 calculated = crc_itu_t(0xffff, buf, size);
 
 	/*
 	 * While the rest of the wire protocol is little-endian,
diff --git a/drivers/mfd/tps6594-spi.c b/drivers/mfd/tps6594-spi.c
index f4b4f37f957f..24b72847e3f5 100644
--- a/drivers/mfd/tps6594-spi.c
+++ b/drivers/mfd/tps6594-spi.c
@@ -98,7 +98,7 @@ static int tps6594_spi_probe(struct spi_device *spi)
 	spi_set_drvdata(spi, tps);
 
 	tps->dev = dev;
-	tps->reg = spi->chip_select;
+	tps->reg = spi_get_chipselect(spi, 0);
 	tps->irq = spi->irq;
 
 	tps->regmap = devm_regmap_init(dev, NULL, spi, &tps6594_spi_regmap_config);
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index 0562071cdd4a..6ad0ab892675 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -836,7 +836,8 @@ static inline bool cxl_is_power8(void)
 {
 	if ((pvr_version_is(PVR_POWER8E)) ||
 	    (pvr_version_is(PVR_POWER8NVL)) ||
-	    (pvr_version_is(PVR_POWER8)))
+	    (pvr_version_is(PVR_POWER8)) ||
+	    (pvr_version_is(PVR_HX_C2000)))
 		return true;
 	return false;
 }
diff --git a/drivers/misc/genwqe/card_dev.c b/drivers/misc/genwqe/card_dev.c
index 55fc5b80e649..4441aca2280a 100644
--- a/drivers/misc/genwqe/card_dev.c
+++ b/drivers/misc/genwqe/card_dev.c
@@ -443,7 +443,7 @@ static int genwqe_mmap(struct file *filp, struct vm_area_struct *vma)
 	if (vsize == 0)
 		return -EINVAL;
 
-	if (get_order(vsize) > MAX_ORDER)
+	if (get_order(vsize) > MAX_PAGE_ORDER)
 		return -ENOMEM;
 
 	dma_map = kzalloc(sizeof(struct dma_mapping), GFP_KERNEL);
diff --git a/drivers/misc/genwqe/card_utils.c b/drivers/misc/genwqe/card_utils.c
index 1c798d6b2dfb..a2c4a9b4f871 100644
--- a/drivers/misc/genwqe/card_utils.c
+++ b/drivers/misc/genwqe/card_utils.c
@@ -210,7 +210,7 @@ u32 genwqe_crc32(u8 *buff, size_t len, u32 init)
 void *__genwqe_alloc_consistent(struct genwqe_dev *cd, size_t size,
 			       dma_addr_t *dma_handle)
 {
-	if (get_order(size) > MAX_ORDER)
+	if (get_order(size) > MAX_PAGE_ORDER)
 		return NULL;
 
 	return dma_alloc_coherent(&cd->pci_dev->dev, size, dma_handle,
@@ -308,7 +308,7 @@ int genwqe_alloc_sync_sgl(struct genwqe_dev *cd, struct genwqe_sgl *sgl,
 	sgl->write = write;
 	sgl->sgl_size = genwqe_sgl_size(sgl->nr_pages);
 
-	if (get_order(sgl->sgl_size) > MAX_ORDER) {
+	if (get_order(sgl->sgl_size) > MAX_PAGE_ORDER) {
 		dev_err(&pci_dev->dev,
 			"[%s] err: too much memory requested!\n", __func__);
 		return ret;
diff --git a/drivers/misc/lkdtm/heap.c b/drivers/misc/lkdtm/heap.c
index 0ce4cbf6abda..4f467d3972a6 100644
--- a/drivers/misc/lkdtm/heap.c
+++ b/drivers/misc/lkdtm/heap.c
@@ -4,6 +4,7 @@
  * page allocation and slab allocations.
  */
 #include "lkdtm.h"
+#include <linux/kfence.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/sched.h>
@@ -132,6 +133,64 @@ static void lkdtm_READ_AFTER_FREE(void)
 	kfree(val);
 }
 
+static void lkdtm_KFENCE_READ_AFTER_FREE(void)
+{
+	int *base, val, saw;
+	unsigned long timeout, resched_after;
+	size_t len = 1024;
+	/*
+	 * The slub allocator will use the either the first word or
+	 * the middle of the allocation to store the free pointer,
+	 * depending on configurations. Store in the second word to
+	 * avoid running into the freelist.
+	 */
+	size_t offset = sizeof(*base);
+
+	/*
+	 * 100x the sample interval should be more than enough to ensure we get
+	 * a KFENCE allocation eventually.
+	 */
+	timeout = jiffies + msecs_to_jiffies(100 * kfence_sample_interval);
+	/*
+	 * Especially for non-preemption kernels, ensure the allocation-gate
+	 * timer can catch up: after @resched_after, every failed allocation
+	 * attempt yields, to ensure the allocation-gate timer is scheduled.
+	 */
+	resched_after = jiffies + msecs_to_jiffies(kfence_sample_interval);
+	do {
+		base = kmalloc(len, GFP_KERNEL);
+		if (!base) {
+			pr_err("FAIL: Unable to allocate kfence memory!\n");
+			return;
+		}
+
+		if (is_kfence_address(base)) {
+			val = 0x12345678;
+			base[offset] = val;
+			pr_info("Value in memory before free: %x\n", base[offset]);
+
+			kfree(base);
+
+			pr_info("Attempting bad read from freed memory\n");
+			saw = base[offset];
+			if (saw != val) {
+				/* Good! Poisoning happened, so declare a win. */
+				pr_info("Memory correctly poisoned (%x)\n", saw);
+			} else {
+				pr_err("FAIL: Memory was not poisoned!\n");
+				pr_expected_config_param(CONFIG_INIT_ON_FREE_DEFAULT_ON, "init_on_free");
+			}
+			return;
+		}
+
+		kfree(base);
+		if (time_after(jiffies, resched_after))
+			cond_resched();
+	} while (time_before(jiffies, timeout));
+
+	pr_err("FAIL: kfence memory never allocated!\n");
+}
+
 static void lkdtm_WRITE_BUDDY_AFTER_FREE(void)
 {
 	unsigned long p = __get_free_page(GFP_KERNEL);
@@ -327,6 +386,7 @@ static struct crashtype crashtypes[] = {
 	CRASHTYPE(VMALLOC_LINEAR_OVERFLOW),
 	CRASHTYPE(WRITE_AFTER_FREE),
 	CRASHTYPE(READ_AFTER_FREE),
+	CRASHTYPE(KFENCE_READ_AFTER_FREE),
 	CRASHTYPE(WRITE_BUDDY_AFTER_FREE),
 	CRASHTYPE(READ_BUDDY_AFTER_FREE),
 	CRASHTYPE(SLAB_INIT_ON_ALLOC),
diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c
index 9c8fc87938a7..9d090fa07516 100644
--- a/drivers/misc/mei/client.c
+++ b/drivers/misc/mei/client.c
@@ -2011,7 +2011,7 @@ ssize_t mei_cl_write(struct mei_cl *cl, struct mei_cl_cb *cb, unsigned long time
 
 	mei_hdr = mei_msg_hdr_init(cb);
 	if (IS_ERR(mei_hdr)) {
-		rets = -PTR_ERR(mei_hdr);
+		rets = PTR_ERR(mei_hdr);
 		mei_hdr = NULL;
 		goto err;
 	}
@@ -2032,7 +2032,7 @@ ssize_t mei_cl_write(struct mei_cl *cl, struct mei_cl_cb *cb, unsigned long time
 
 	hbuf_slots = mei_hbuf_empty_slots(dev);
 	if (hbuf_slots < 0) {
-		rets = -EOVERFLOW;
+		buf_len = -EOVERFLOW;
 		goto out;
 	}
 
diff --git a/drivers/misc/mei/pxp/mei_pxp.c b/drivers/misc/mei/pxp/mei_pxp.c
index f77d78fa5054..787c6a27a4be 100644
--- a/drivers/misc/mei/pxp/mei_pxp.c
+++ b/drivers/misc/mei/pxp/mei_pxp.c
@@ -84,9 +84,10 @@ mei_pxp_send_message(struct device *dev, const void *message, size_t size, unsig
 				byte = ret;
 			break;
 		}
+		return byte;
 	}
 
-	return byte;
+	return 0;
 }
 
 /**
diff --git a/drivers/misc/ocxl/afu_irq.c b/drivers/misc/ocxl/afu_irq.c
index a06920b7e049..36f7379b8e2d 100644
--- a/drivers/misc/ocxl/afu_irq.c
+++ b/drivers/misc/ocxl/afu_irq.c
@@ -57,7 +57,7 @@ EXPORT_SYMBOL_GPL(ocxl_irq_set_handler);
 
 static irqreturn_t afu_irq_handler(int virq, void *data)
 {
-	struct afu_irq *irq = (struct afu_irq *) data;
+	struct afu_irq *irq = data;
 
 	trace_ocxl_afu_irq_receive(virq);
 
diff --git a/drivers/misc/ocxl/context.c b/drivers/misc/ocxl/context.c
index 7f83116ae11a..cded7d1caf32 100644
--- a/drivers/misc/ocxl/context.c
+++ b/drivers/misc/ocxl/context.c
@@ -55,7 +55,7 @@ EXPORT_SYMBOL_GPL(ocxl_context_alloc);
  */
 static void xsl_fault_error(void *data, u64 addr, u64 dsisr)
 {
-	struct ocxl_context *ctx = (struct ocxl_context *) data;
+	struct ocxl_context *ctx = data;
 
 	mutex_lock(&ctx->xsl_error_lock);
 	ctx->xsl_error.addr = addr;
diff --git a/drivers/misc/ocxl/file.c b/drivers/misc/ocxl/file.c
index ac69b7f361f5..7eb74711ac96 100644
--- a/drivers/misc/ocxl/file.c
+++ b/drivers/misc/ocxl/file.c
@@ -184,7 +184,7 @@ static irqreturn_t irq_handler(void *private)
 {
 	struct eventfd_ctx *ev_ctx = private;
 
-	eventfd_signal(ev_ctx, 1);
+	eventfd_signal(ev_ctx);
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/misc/ocxl/link.c b/drivers/misc/ocxl/link.c
index c06c699c0e7b..03402203cacd 100644
--- a/drivers/misc/ocxl/link.c
+++ b/drivers/misc/ocxl/link.c
@@ -188,7 +188,7 @@ ack:
 
 static irqreturn_t xsl_fault_handler(int irq, void *data)
 {
-	struct ocxl_link *link = (struct ocxl_link *) data;
+	struct ocxl_link *link = data;
 	struct spa *spa = link->spa;
 	u64 dsisr, dar, pe_handle;
 	struct pe_data *pe_data;
@@ -483,7 +483,7 @@ static void release_xsl(struct kref *ref)
 
 void ocxl_link_release(struct pci_dev *dev, void *link_handle)
 {
-	struct ocxl_link *link = (struct ocxl_link *) link_handle;
+	struct ocxl_link *link = link_handle;
 
 	mutex_lock(&links_list_lock);
 	kref_put(&link->ref, release_xsl);
@@ -540,7 +540,7 @@ int ocxl_link_add_pe(void *link_handle, int pasid, u32 pidr, u32 tidr,
 		void (*xsl_err_cb)(void *data, u64 addr, u64 dsisr),
 		void *xsl_err_data)
 {
-	struct ocxl_link *link = (struct ocxl_link *) link_handle;
+	struct ocxl_link *link = link_handle;
 	struct spa *spa = link->spa;
 	struct ocxl_process_element *pe;
 	int pe_handle, rc = 0;
@@ -630,7 +630,7 @@ EXPORT_SYMBOL_GPL(ocxl_link_add_pe);
 
 int ocxl_link_update_pe(void *link_handle, int pasid, __u16 tid)
 {
-	struct ocxl_link *link = (struct ocxl_link *) link_handle;
+	struct ocxl_link *link = link_handle;
 	struct spa *spa = link->spa;
 	struct ocxl_process_element *pe;
 	int pe_handle, rc;
@@ -666,7 +666,7 @@ int ocxl_link_update_pe(void *link_handle, int pasid, __u16 tid)
 
 int ocxl_link_remove_pe(void *link_handle, int pasid)
 {
-	struct ocxl_link *link = (struct ocxl_link *) link_handle;
+	struct ocxl_link *link = link_handle;
 	struct spa *spa = link->spa;
 	struct ocxl_process_element *pe;
 	struct pe_data *pe_data;
@@ -752,7 +752,7 @@ EXPORT_SYMBOL_GPL(ocxl_link_remove_pe);
 
 int ocxl_link_irq_alloc(void *link_handle, int *hw_irq)
 {
-	struct ocxl_link *link = (struct ocxl_link *) link_handle;
+	struct ocxl_link *link = link_handle;
 	int irq;
 
 	if (atomic_dec_if_positive(&link->irq_available) < 0)
@@ -771,7 +771,7 @@ EXPORT_SYMBOL_GPL(ocxl_link_irq_alloc);
 
 void ocxl_link_free_irq(void *link_handle, int hw_irq)
 {
-	struct ocxl_link *link = (struct ocxl_link *) link_handle;
+	struct ocxl_link *link = link_handle;
 
 	xive_native_free_irq(hw_irq);
 	atomic_inc(&link->irq_available);
diff --git a/drivers/misc/ocxl/main.c b/drivers/misc/ocxl/main.c
index ef73cf35dda2..658974143c3c 100644
--- a/drivers/misc/ocxl/main.c
+++ b/drivers/misc/ocxl/main.c
@@ -7,7 +7,7 @@
 
 static int __init init_ocxl(void)
 {
-	int rc = 0;
+	int rc;
 
 	if (!tlbie_capable)
 		return -EINVAL;
diff --git a/drivers/misc/vmw_vmci/vmci_handle_array.h b/drivers/misc/vmw_vmci/vmci_handle_array.h
index 96193f85be5b..b0e6b1956014 100644
--- a/drivers/misc/vmw_vmci/vmci_handle_array.h
+++ b/drivers/misc/vmw_vmci/vmci_handle_array.h
@@ -17,7 +17,7 @@ struct vmci_handle_arr {
 	u32 max_capacity;
 	u32 size;
 	u32 pad;
-	struct vmci_handle entries[];
+	struct vmci_handle entries[] __counted_by(capacity);
 };
 
 #define VMCI_HANDLE_ARRAY_HEADER_SIZE				\
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 152dfe593c43..134c36edb6cf 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -851,9 +851,10 @@ static const struct block_device_operations mmc_bdops = {
 static int mmc_blk_part_switch_pre(struct mmc_card *card,
 				   unsigned int part_type)
 {
+	const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_RPMB;
 	int ret = 0;
 
-	if (part_type == EXT_CSD_PART_CONFIG_ACC_RPMB) {
+	if ((part_type & mask) == mask) {
 		if (card->ext_csd.cmdq_en) {
 			ret = mmc_cmdq_disable(card);
 			if (ret)
@@ -868,9 +869,10 @@ static int mmc_blk_part_switch_pre(struct mmc_card *card,
 static int mmc_blk_part_switch_post(struct mmc_card *card,
 				    unsigned int part_type)
 {
+	const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_RPMB;
 	int ret = 0;
 
-	if (part_type == EXT_CSD_PART_CONFIG_ACC_RPMB) {
+	if ((part_type & mask) == mask) {
 		mmc_retune_unpause(card->host);
 		if (card->reenable_cmdq && !card->ext_csd.cmdq_en)
 			ret = mmc_cmdq_enable(card);
@@ -1482,6 +1484,8 @@ static void mmc_blk_cqe_complete_rq(struct mmc_queue *mq, struct request *req)
 			blk_mq_requeue_request(req, true);
 		else
 			__blk_mq_end_request(req, BLK_STS_OK);
+	} else if (mq->in_recovery) {
+		blk_mq_requeue_request(req, true);
 	} else {
 		blk_mq_end_request(req, BLK_STS_OK);
 	}
@@ -3143,4 +3147,3 @@ module_exit(mmc_blk_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Multimedia Card (MMC) block device driver");
-
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 3d3e0ca52614..a8c17b4cd737 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -551,7 +551,9 @@ int mmc_cqe_recovery(struct mmc_host *host)
 	cmd.flags        = MMC_RSP_R1B | MMC_CMD_AC;
 	cmd.flags       &= ~MMC_RSP_CRC; /* Ignore CRC */
 	cmd.busy_timeout = MMC_CQE_RECOVERY_TIMEOUT;
-	mmc_wait_for_cmd(host, &cmd, 0);
+	mmc_wait_for_cmd(host, &cmd, MMC_CMD_RETRIES);
+
+	mmc_poll_for_busy(host->card, MMC_CQE_RECOVERY_TIMEOUT, true, MMC_BUSY_IO);
 
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.opcode       = MMC_CMDQ_TASK_MGMT;
@@ -559,10 +561,13 @@ int mmc_cqe_recovery(struct mmc_host *host)
 	cmd.flags        = MMC_RSP_R1B | MMC_CMD_AC;
 	cmd.flags       &= ~MMC_RSP_CRC; /* Ignore CRC */
 	cmd.busy_timeout = MMC_CQE_RECOVERY_TIMEOUT;
-	err = mmc_wait_for_cmd(host, &cmd, 0);
+	err = mmc_wait_for_cmd(host, &cmd, MMC_CMD_RETRIES);
 
 	host->cqe_ops->cqe_recovery_finish(host);
 
+	if (err)
+		err = mmc_wait_for_cmd(host, &cmd, MMC_CMD_RETRIES);
+
 	mmc_retune_release(host);
 
 	return err;
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 096093f7be00..2f51db4df1a8 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -692,6 +692,7 @@ EXPORT_SYMBOL(mmc_remove_host);
  */
 void mmc_free_host(struct mmc_host *host)
 {
+	cancel_delayed_work_sync(&host->detect);
 	mmc_pwrseq_free(host);
 	put_device(&host->class_dev);
 }
diff --git a/drivers/mmc/host/cqhci-core.c b/drivers/mmc/host/cqhci-core.c
index b3d7d6d8d654..41e94cd14109 100644
--- a/drivers/mmc/host/cqhci-core.c
+++ b/drivers/mmc/host/cqhci-core.c
@@ -942,8 +942,8 @@ static bool cqhci_clear_all_tasks(struct mmc_host *mmc, unsigned int timeout)
 	ret = cqhci_tasks_cleared(cq_host);
 
 	if (!ret)
-		pr_debug("%s: cqhci: Failed to clear tasks\n",
-			 mmc_hostname(mmc));
+		pr_warn("%s: cqhci: Failed to clear tasks\n",
+			mmc_hostname(mmc));
 
 	return ret;
 }
@@ -976,7 +976,7 @@ static bool cqhci_halt(struct mmc_host *mmc, unsigned int timeout)
 	ret = cqhci_halted(cq_host);
 
 	if (!ret)
-		pr_debug("%s: cqhci: Failed to halt\n", mmc_hostname(mmc));
+		pr_warn("%s: cqhci: Failed to halt\n", mmc_hostname(mmc));
 
 	return ret;
 }
@@ -984,10 +984,10 @@ static bool cqhci_halt(struct mmc_host *mmc, unsigned int timeout)
 /*
  * After halting we expect to be able to use the command line. We interpret the
  * failure to halt to mean the data lines might still be in use (and the upper
- * layers will need to send a STOP command), so we set the timeout based on a
- * generous command timeout.
+ * layers will need to send a STOP command), however failing to halt complicates
+ * the recovery, so set a timeout that would reasonably allow I/O to complete.
  */
-#define CQHCI_START_HALT_TIMEOUT	5
+#define CQHCI_START_HALT_TIMEOUT	500
 
 static void cqhci_recovery_start(struct mmc_host *mmc)
 {
@@ -1075,28 +1075,28 @@ static void cqhci_recovery_finish(struct mmc_host *mmc)
 
 	ok = cqhci_halt(mmc, CQHCI_FINISH_HALT_TIMEOUT);
 
-	if (!cqhci_clear_all_tasks(mmc, CQHCI_CLEAR_TIMEOUT))
-		ok = false;
-
 	/*
 	 * The specification contradicts itself, by saying that tasks cannot be
 	 * cleared if CQHCI does not halt, but if CQHCI does not halt, it should
 	 * be disabled/re-enabled, but not to disable before clearing tasks.
 	 * Have a go anyway.
 	 */
-	if (!ok) {
-		pr_debug("%s: cqhci: disable / re-enable\n", mmc_hostname(mmc));
-		cqcfg = cqhci_readl(cq_host, CQHCI_CFG);
-		cqcfg &= ~CQHCI_ENABLE;
-		cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
-		cqcfg |= CQHCI_ENABLE;
-		cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
-		/* Be sure that there are no tasks */
-		ok = cqhci_halt(mmc, CQHCI_FINISH_HALT_TIMEOUT);
-		if (!cqhci_clear_all_tasks(mmc, CQHCI_CLEAR_TIMEOUT))
-			ok = false;
-		WARN_ON(!ok);
-	}
+	if (!cqhci_clear_all_tasks(mmc, CQHCI_CLEAR_TIMEOUT))
+		ok = false;
+
+	/* Disable to make sure tasks really are cleared */
+	cqcfg = cqhci_readl(cq_host, CQHCI_CFG);
+	cqcfg &= ~CQHCI_ENABLE;
+	cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
+
+	cqcfg = cqhci_readl(cq_host, CQHCI_CFG);
+	cqcfg |= CQHCI_ENABLE;
+	cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
+
+	cqhci_halt(mmc, CQHCI_FINISH_HALT_TIMEOUT);
+
+	if (!ok)
+		cqhci_clear_all_tasks(mmc, CQHCI_CLEAR_TIMEOUT);
 
 	cqhci_recover_mrqs(cq_host);
 
diff --git a/drivers/mmc/host/meson-mx-sdhc-mmc.c b/drivers/mmc/host/meson-mx-sdhc-mmc.c
index 528ec8166e7c..1ed9731e77ef 100644
--- a/drivers/mmc/host/meson-mx-sdhc-mmc.c
+++ b/drivers/mmc/host/meson-mx-sdhc-mmc.c
@@ -269,7 +269,7 @@ static int meson_mx_sdhc_enable_clks(struct mmc_host *mmc)
 static int meson_mx_sdhc_set_clk(struct mmc_host *mmc, struct mmc_ios *ios)
 {
 	struct meson_mx_sdhc_host *host = mmc_priv(mmc);
-	u32 rx_clk_phase;
+	u32 val, rx_clk_phase;
 	int ret;
 
 	meson_mx_sdhc_disable_clks(mmc);
@@ -290,27 +290,11 @@ static int meson_mx_sdhc_set_clk(struct mmc_host *mmc, struct mmc_ios *ios)
 		mmc->actual_clock = clk_get_rate(host->sd_clk);
 
 		/*
-		 * according to Amlogic the following latching points are
-		 * selected with empirical values, there is no (known) formula
-		 * to calculate these.
+		 * Phase 90 should work in most cases. For data transmission,
+		 * meson_mx_sdhc_execute_tuning() will find a accurate value
 		 */
-		if (mmc->actual_clock > 100000000) {
-			rx_clk_phase = 1;
-		} else if (mmc->actual_clock > 45000000) {
-			if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_330)
-				rx_clk_phase = 15;
-			else
-				rx_clk_phase = 11;
-		} else if (mmc->actual_clock >= 25000000) {
-			rx_clk_phase = 15;
-		} else if (mmc->actual_clock > 5000000) {
-			rx_clk_phase = 23;
-		} else if (mmc->actual_clock > 1000000) {
-			rx_clk_phase = 55;
-		} else {
-			rx_clk_phase = 1061;
-		}
-
+		regmap_read(host->regmap, MESON_SDHC_CLKC, &val);
+		rx_clk_phase = FIELD_GET(MESON_SDHC_CLKC_CLK_DIV, val) / 4;
 		regmap_update_bits(host->regmap, MESON_SDHC_CLK2,
 				   MESON_SDHC_CLK2_RX_CLK_PHASE,
 				   FIELD_PREP(MESON_SDHC_CLK2_RX_CLK_PHASE,
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index cc333ad67cac..b0cccef4cfbf 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -1322,7 +1322,7 @@ static int mmc_spi_probe(struct spi_device *spi)
 	/* We rely on full duplex transfers, mostly to reduce
 	 * per-transfer overheads (by making fewer transfers).
 	 */
-	if (spi->master->flags & SPI_MASTER_HALF_DUPLEX)
+	if (spi->master->flags & SPI_CONTROLLER_HALF_DUPLEX)
 		return -EINVAL;
 
 	/* MMC and SD specs only seem to care that sampling is on the
diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c
index d8a991b349a8..77911a57b12c 100644
--- a/drivers/mmc/host/sdhci-pci-gli.c
+++ b/drivers/mmc/host/sdhci-pci-gli.c
@@ -1189,6 +1189,32 @@ static void gl9763e_hs400_enhanced_strobe(struct mmc_host *mmc,
 	sdhci_writel(host, val, SDHCI_GLI_9763E_HS400_ES_REG);
 }
 
+static void gl9763e_set_low_power_negotiation(struct sdhci_pci_slot *slot,
+					      bool enable)
+{
+	struct pci_dev *pdev = slot->chip->pdev;
+	u32 value;
+
+	pci_read_config_dword(pdev, PCIE_GLI_9763E_VHS, &value);
+	value &= ~GLI_9763E_VHS_REV;
+	value |= FIELD_PREP(GLI_9763E_VHS_REV, GLI_9763E_VHS_REV_W);
+	pci_write_config_dword(pdev, PCIE_GLI_9763E_VHS, value);
+
+	pci_read_config_dword(pdev, PCIE_GLI_9763E_CFG, &value);
+
+	if (enable)
+		value &= ~GLI_9763E_CFG_LPSN_DIS;
+	else
+		value |= GLI_9763E_CFG_LPSN_DIS;
+
+	pci_write_config_dword(pdev, PCIE_GLI_9763E_CFG, value);
+
+	pci_read_config_dword(pdev, PCIE_GLI_9763E_VHS, &value);
+	value &= ~GLI_9763E_VHS_REV;
+	value |= FIELD_PREP(GLI_9763E_VHS_REV, GLI_9763E_VHS_REV_R);
+	pci_write_config_dword(pdev, PCIE_GLI_9763E_VHS, value);
+}
+
 static void sdhci_set_gl9763e_signaling(struct sdhci_host *host,
 					unsigned int timing)
 {
@@ -1297,6 +1323,9 @@ static int gl9763e_add_host(struct sdhci_pci_slot *slot)
 	if (ret)
 		goto cleanup;
 
+	/* Disable LPM negotiation to avoid entering L1 state. */
+	gl9763e_set_low_power_negotiation(slot, false);
+
 	return 0;
 
 cleanup:
@@ -1340,31 +1369,6 @@ static void gli_set_gl9763e(struct sdhci_pci_slot *slot)
 }
 
 #ifdef CONFIG_PM
-static void gl9763e_set_low_power_negotiation(struct sdhci_pci_slot *slot, bool enable)
-{
-	struct pci_dev *pdev = slot->chip->pdev;
-	u32 value;
-
-	pci_read_config_dword(pdev, PCIE_GLI_9763E_VHS, &value);
-	value &= ~GLI_9763E_VHS_REV;
-	value |= FIELD_PREP(GLI_9763E_VHS_REV, GLI_9763E_VHS_REV_W);
-	pci_write_config_dword(pdev, PCIE_GLI_9763E_VHS, value);
-
-	pci_read_config_dword(pdev, PCIE_GLI_9763E_CFG, &value);
-
-	if (enable)
-		value &= ~GLI_9763E_CFG_LPSN_DIS;
-	else
-		value |= GLI_9763E_CFG_LPSN_DIS;
-
-	pci_write_config_dword(pdev, PCIE_GLI_9763E_CFG, value);
-
-	pci_read_config_dword(pdev, PCIE_GLI_9763E_VHS, &value);
-	value &= ~GLI_9763E_VHS_REV;
-	value |= FIELD_PREP(GLI_9763E_VHS_REV, GLI_9763E_VHS_REV_R);
-	pci_write_config_dword(pdev, PCIE_GLI_9763E_VHS, value);
-}
-
 static int gl9763e_runtime_suspend(struct sdhci_pci_chip *chip)
 {
 	struct sdhci_pci_slot *slot = chip->slots[0];
diff --git a/drivers/mmc/host/sdhci-sprd.c b/drivers/mmc/host/sdhci-sprd.c
index 6b84ba27e6ab..bed57a1c64b5 100644
--- a/drivers/mmc/host/sdhci-sprd.c
+++ b/drivers/mmc/host/sdhci-sprd.c
@@ -239,15 +239,19 @@ static inline void _sdhci_sprd_set_clock(struct sdhci_host *host,
 	div = ((div & 0x300) >> 2) | ((div & 0xFF) << 8);
 	sdhci_enable_clk(host, div);
 
+	val = sdhci_readl(host, SDHCI_SPRD_REG_32_BUSY_POSI);
+	mask = SDHCI_SPRD_BIT_OUTR_CLK_AUTO_EN | SDHCI_SPRD_BIT_INNR_CLK_AUTO_EN;
 	/* Enable CLK_AUTO when the clock is greater than 400K. */
 	if (clk > 400000) {
-		val = sdhci_readl(host, SDHCI_SPRD_REG_32_BUSY_POSI);
-		mask = SDHCI_SPRD_BIT_OUTR_CLK_AUTO_EN |
-			SDHCI_SPRD_BIT_INNR_CLK_AUTO_EN;
 		if (mask != (val & mask)) {
 			val |= mask;
 			sdhci_writel(host, val, SDHCI_SPRD_REG_32_BUSY_POSI);
 		}
+	} else {
+		if (val & mask) {
+			val &= ~mask;
+			sdhci_writel(host, val, SDHCI_SPRD_REG_32_BUSY_POSI);
+		}
 	}
 }
 
@@ -416,12 +420,33 @@ static void sdhci_sprd_request_done(struct sdhci_host *host,
 	mmc_request_done(host->mmc, mrq);
 }
 
+static void sdhci_sprd_set_power(struct sdhci_host *host, unsigned char mode,
+				 unsigned short vdd)
+{
+	struct mmc_host *mmc = host->mmc;
+
+	switch (mode) {
+	case MMC_POWER_OFF:
+		mmc_regulator_set_ocr(host->mmc, mmc->supply.vmmc, 0);
+
+		mmc_regulator_disable_vqmmc(mmc);
+		break;
+	case MMC_POWER_ON:
+		mmc_regulator_enable_vqmmc(mmc);
+		break;
+	case MMC_POWER_UP:
+		mmc_regulator_set_ocr(host->mmc, mmc->supply.vmmc, vdd);
+		break;
+	}
+}
+
 static struct sdhci_ops sdhci_sprd_ops = {
 	.read_l = sdhci_sprd_readl,
 	.write_l = sdhci_sprd_writel,
 	.write_w = sdhci_sprd_writew,
 	.write_b = sdhci_sprd_writeb,
 	.set_clock = sdhci_sprd_set_clock,
+	.set_power = sdhci_sprd_set_power,
 	.get_max_clock = sdhci_sprd_get_max_clock,
 	.get_min_clock = sdhci_sprd_get_min_clock,
 	.set_bus_width = sdhci_set_bus_width,
@@ -823,6 +848,10 @@ static int sdhci_sprd_probe(struct platform_device *pdev)
 	host->caps1 &= ~(SDHCI_SUPPORT_SDR50 | SDHCI_SUPPORT_SDR104 |
 			 SDHCI_SUPPORT_DDR50);
 
+	ret = mmc_regulator_get_supply(host->mmc);
+	if (ret)
+		goto pm_runtime_disable;
+
 	ret = sdhci_setup_host(host);
 	if (ret)
 		goto pm_runtime_disable;
diff --git a/drivers/mtd/maps/vmu-flash.c b/drivers/mtd/maps/vmu-flash.c
index a7ec947a3ebb..53019d313db7 100644
--- a/drivers/mtd/maps/vmu-flash.c
+++ b/drivers/mtd/maps/vmu-flash.c
@@ -719,7 +719,7 @@ static int vmu_can_unload(struct maple_device *mdev)
 	card = maple_get_drvdata(mdev);
 	for (x = 0; x < card->partitions; x++) {
 		mtd = &((card->mtd)[x]);
-		if (mtd->usecount > 0)
+		if (kref_read(&mtd->refcnt))
 			return 0;
 	}
 	return 1;
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index ff18636e0889..f0526dcc2162 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -376,10 +376,8 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, new->rq);
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, new->rq);
 
-	if (tr->discard) {
+	if (tr->discard)
 		blk_queue_max_discard_sectors(new->rq, UINT_MAX);
-		new->rq->limits.discard_granularity = tr->blksize;
-	}
 
 	gd->queue = new->rq;
 
@@ -463,7 +461,7 @@ static void blktrans_notify_add(struct mtd_info *mtd)
 {
 	struct mtd_blktrans_ops *tr;
 
-	if (mtd->type == MTD_ABSENT)
+	if (mtd->type == MTD_ABSENT || mtd->type == MTD_UBIVOLUME)
 		return;
 
 	list_for_each_entry(tr, &blktrans_majors, list)
@@ -503,7 +501,7 @@ int register_mtd_blktrans(struct mtd_blktrans_ops *tr)
 	mutex_lock(&mtd_table_mutex);
 	list_add(&tr->list, &blktrans_majors);
 	mtd_for_each_device(mtd)
-		if (mtd->type != MTD_ABSENT)
+		if (mtd->type != MTD_ABSENT && mtd->type != MTD_UBIVOLUME)
 			tr->add_mtd(tr, mtd);
 	mutex_unlock(&mtd_table_mutex);
 	return 0;
diff --git a/drivers/mtd/nand/raw/brcmnand/bcm63138_nand.c b/drivers/mtd/nand/raw/brcmnand/bcm63138_nand.c
index 9596629000f4..968c5b674b08 100644
--- a/drivers/mtd/nand/raw/brcmnand/bcm63138_nand.c
+++ b/drivers/mtd/nand/raw/brcmnand/bcm63138_nand.c
@@ -85,7 +85,7 @@ MODULE_DEVICE_TABLE(of, bcm63138_nand_of_match);
 
 static struct platform_driver bcm63138_nand_driver = {
 	.probe			= bcm63138_nand_probe,
-	.remove			= brcmnand_remove,
+	.remove_new		= brcmnand_remove,
 	.driver = {
 		.name		= "bcm63138_nand",
 		.pm		= &brcmnand_pm_ops,
diff --git a/drivers/mtd/nand/raw/brcmnand/bcm6368_nand.c b/drivers/mtd/nand/raw/brcmnand/bcm6368_nand.c
index a06cd87f839a..05b7b653bdf3 100644
--- a/drivers/mtd/nand/raw/brcmnand/bcm6368_nand.c
+++ b/drivers/mtd/nand/raw/brcmnand/bcm6368_nand.c
@@ -117,7 +117,7 @@ MODULE_DEVICE_TABLE(of, bcm6368_nand_of_match);
 
 static struct platform_driver bcm6368_nand_driver = {
 	.probe			= bcm6368_nand_probe,
-	.remove			= brcmnand_remove,
+	.remove_new		= brcmnand_remove,
 	.driver = {
 		.name		= "bcm6368_nand",
 		.pm		= &brcmnand_pm_ops,
diff --git a/drivers/mtd/nand/raw/brcmnand/bcma_nand.c b/drivers/mtd/nand/raw/brcmnand/bcma_nand.c
index dd27977919fb..4e7e435ba339 100644
--- a/drivers/mtd/nand/raw/brcmnand/bcma_nand.c
+++ b/drivers/mtd/nand/raw/brcmnand/bcma_nand.c
@@ -119,7 +119,7 @@ static int brcmnand_bcma_nand_probe(struct platform_device *pdev)
 
 static struct platform_driver brcmnand_bcma_nand_driver = {
 	.probe			= brcmnand_bcma_nand_probe,
-	.remove			= brcmnand_remove,
+	.remove_new		= brcmnand_remove,
 	.driver = {
 		.name		= "bcma_brcmnand",
 		.pm		= &brcmnand_pm_ops,
diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
index 440bef477930..8faca43ae1ff 100644
--- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
@@ -625,6 +625,8 @@ enum {
 /* Only for v7.2 */
 #define	ACC_CONTROL_ECC_EXT_SHIFT		13
 
+static u8 brcmnand_status(struct brcmnand_host *host);
+
 static inline bool brcmnand_non_mmio_ops(struct brcmnand_controller *ctrl)
 {
 #if IS_ENABLED(CONFIG_MTD_NAND_BRCMNAND_BCMA)
@@ -1022,19 +1024,6 @@ static inline int brcmnand_sector_1k_shift(struct brcmnand_controller *ctrl)
 		return -1;
 }
 
-static int brcmnand_get_sector_size_1k(struct brcmnand_host *host)
-{
-	struct brcmnand_controller *ctrl = host->ctrl;
-	int shift = brcmnand_sector_1k_shift(ctrl);
-	u16 acc_control_offs = brcmnand_cs_offset(ctrl, host->cs,
-						  BRCMNAND_CS_ACC_CONTROL);
-
-	if (shift < 0)
-		return 0;
-
-	return (nand_readreg(ctrl, acc_control_offs) >> shift) & 0x1;
-}
-
 static void brcmnand_set_sector_size_1k(struct brcmnand_host *host, int val)
 {
 	struct brcmnand_controller *ctrl = host->ctrl;
@@ -1061,10 +1050,11 @@ enum {
 	CS_SELECT_AUTO_DEVICE_ID_CFG		= BIT(30),
 };
 
-static int bcmnand_ctrl_poll_status(struct brcmnand_controller *ctrl,
+static int bcmnand_ctrl_poll_status(struct brcmnand_host *host,
 				    u32 mask, u32 expected_val,
 				    unsigned long timeout_ms)
 {
+	struct brcmnand_controller *ctrl = host->ctrl;
 	unsigned long limit;
 	u32 val;
 
@@ -1073,6 +1063,9 @@ static int bcmnand_ctrl_poll_status(struct brcmnand_controller *ctrl,
 
 	limit = jiffies + msecs_to_jiffies(timeout_ms);
 	do {
+		if (mask & INTFC_FLASH_STATUS)
+			brcmnand_status(host);
+
 		val = brcmnand_read_reg(ctrl, BRCMNAND_INTFC_STATUS);
 		if ((val & mask) == expected_val)
 			return 0;
@@ -1084,6 +1077,9 @@ static int bcmnand_ctrl_poll_status(struct brcmnand_controller *ctrl,
 	 * do a final check after time out in case the CPU was busy and the driver
 	 * did not get enough time to perform the polling to avoid false alarms
 	 */
+	if (mask & INTFC_FLASH_STATUS)
+		brcmnand_status(host);
+
 	val = brcmnand_read_reg(ctrl, BRCMNAND_INTFC_STATUS);
 	if ((val & mask) == expected_val)
 		return 0;
@@ -1379,7 +1375,7 @@ static void brcmnand_wp(struct mtd_info *mtd, int wp)
 		 * make sure ctrl/flash ready before and after
 		 * changing state of #WP pin
 		 */
-		ret = bcmnand_ctrl_poll_status(ctrl, NAND_CTRL_RDY |
+		ret = bcmnand_ctrl_poll_status(host, NAND_CTRL_RDY |
 					       NAND_STATUS_READY,
 					       NAND_CTRL_RDY |
 					       NAND_STATUS_READY, 0);
@@ -1387,9 +1383,10 @@ static void brcmnand_wp(struct mtd_info *mtd, int wp)
 			return;
 
 		brcmnand_set_wp(ctrl, wp);
-		nand_status_op(chip, NULL);
+		/* force controller operation to update internal copy of NAND chip status */
+		brcmnand_status(host);
 		/* NAND_STATUS_WP 0x00 = protected, 0x80 = not protected */
-		ret = bcmnand_ctrl_poll_status(ctrl,
+		ret = bcmnand_ctrl_poll_status(host,
 					       NAND_CTRL_RDY |
 					       NAND_STATUS_READY |
 					       NAND_STATUS_WP,
@@ -1629,13 +1626,13 @@ static void brcmnand_send_cmd(struct brcmnand_host *host, int cmd)
 	 */
 	if (oops_in_progress) {
 		if (ctrl->cmd_pending &&
-			bcmnand_ctrl_poll_status(ctrl, NAND_CTRL_RDY, NAND_CTRL_RDY, 0))
+			bcmnand_ctrl_poll_status(host, NAND_CTRL_RDY, NAND_CTRL_RDY, 0))
 			return;
 	} else
 		BUG_ON(ctrl->cmd_pending != 0);
 	ctrl->cmd_pending = cmd;
 
-	ret = bcmnand_ctrl_poll_status(ctrl, NAND_CTRL_RDY, NAND_CTRL_RDY, 0);
+	ret = bcmnand_ctrl_poll_status(host, NAND_CTRL_RDY, NAND_CTRL_RDY, 0);
 	WARN_ON(ret);
 
 	mb(); /* flush previous writes */
@@ -1643,16 +1640,6 @@ static void brcmnand_send_cmd(struct brcmnand_host *host, int cmd)
 			   cmd << brcmnand_cmd_shift(ctrl));
 }
 
-/***********************************************************************
- * NAND MTD API: read/program/erase
- ***********************************************************************/
-
-static void brcmnand_cmd_ctrl(struct nand_chip *chip, int dat,
-			      unsigned int ctrl)
-{
-	/* intentionally left blank */
-}
-
 static bool brcmstb_nand_wait_for_completion(struct nand_chip *chip)
 {
 	struct brcmnand_host *host = nand_get_controller_data(chip);
@@ -1664,7 +1651,7 @@ static bool brcmstb_nand_wait_for_completion(struct nand_chip *chip)
 	if (mtd->oops_panic_write || ctrl->irq < 0) {
 		/* switch to interrupt polling and PIO mode */
 		disable_ctrl_irqs(ctrl);
-		sts = bcmnand_ctrl_poll_status(ctrl, NAND_CTRL_RDY,
+		sts = bcmnand_ctrl_poll_status(host, NAND_CTRL_RDY,
 					       NAND_CTRL_RDY, 0);
 		err = sts < 0;
 	} else {
@@ -1703,6 +1690,26 @@ static int brcmnand_waitfunc(struct nand_chip *chip)
 				 INTFC_FLASH_STATUS;
 }
 
+static u8 brcmnand_status(struct brcmnand_host *host)
+{
+	struct nand_chip *chip = &host->chip;
+	struct mtd_info *mtd = nand_to_mtd(chip);
+
+	brcmnand_set_cmd_addr(mtd, 0);
+	brcmnand_send_cmd(host, CMD_STATUS_READ);
+
+	return brcmnand_waitfunc(chip);
+}
+
+static u8 brcmnand_reset(struct brcmnand_host *host)
+{
+	struct nand_chip *chip = &host->chip;
+
+	brcmnand_send_cmd(host, CMD_FLASH_RESET);
+
+	return brcmnand_waitfunc(chip);
+}
+
 enum {
 	LLOP_RE				= BIT(16),
 	LLOP_WE				= BIT(17),
@@ -1752,190 +1759,6 @@ static int brcmnand_low_level_op(struct brcmnand_host *host,
 	return brcmnand_waitfunc(chip);
 }
 
-static void brcmnand_cmdfunc(struct nand_chip *chip, unsigned command,
-			     int column, int page_addr)
-{
-	struct mtd_info *mtd = nand_to_mtd(chip);
-	struct brcmnand_host *host = nand_get_controller_data(chip);
-	struct brcmnand_controller *ctrl = host->ctrl;
-	u64 addr = (u64)page_addr << chip->page_shift;
-	int native_cmd = 0;
-
-	if (command == NAND_CMD_READID || command == NAND_CMD_PARAM ||
-			command == NAND_CMD_RNDOUT)
-		addr = (u64)column;
-	/* Avoid propagating a negative, don't-care address */
-	else if (page_addr < 0)
-		addr = 0;
-
-	dev_dbg(ctrl->dev, "cmd 0x%x addr 0x%llx\n", command,
-		(unsigned long long)addr);
-
-	host->last_cmd = command;
-	host->last_byte = 0;
-	host->last_addr = addr;
-
-	switch (command) {
-	case NAND_CMD_RESET:
-		native_cmd = CMD_FLASH_RESET;
-		break;
-	case NAND_CMD_STATUS:
-		native_cmd = CMD_STATUS_READ;
-		break;
-	case NAND_CMD_READID:
-		native_cmd = CMD_DEVICE_ID_READ;
-		break;
-	case NAND_CMD_READOOB:
-		native_cmd = CMD_SPARE_AREA_READ;
-		break;
-	case NAND_CMD_ERASE1:
-		native_cmd = CMD_BLOCK_ERASE;
-		brcmnand_wp(mtd, 0);
-		break;
-	case NAND_CMD_PARAM:
-		native_cmd = CMD_PARAMETER_READ;
-		break;
-	case NAND_CMD_SET_FEATURES:
-	case NAND_CMD_GET_FEATURES:
-		brcmnand_low_level_op(host, LL_OP_CMD, command, false);
-		brcmnand_low_level_op(host, LL_OP_ADDR, column, false);
-		break;
-	case NAND_CMD_RNDOUT:
-		native_cmd = CMD_PARAMETER_CHANGE_COL;
-		addr &= ~((u64)(FC_BYTES - 1));
-		/*
-		 * HW quirk: PARAMETER_CHANGE_COL requires SECTOR_SIZE_1K=0
-		 * NB: hwcfg.sector_size_1k may not be initialized yet
-		 */
-		if (brcmnand_get_sector_size_1k(host)) {
-			host->hwcfg.sector_size_1k =
-				brcmnand_get_sector_size_1k(host);
-			brcmnand_set_sector_size_1k(host, 0);
-		}
-		break;
-	}
-
-	if (!native_cmd)
-		return;
-
-	brcmnand_set_cmd_addr(mtd, addr);
-	brcmnand_send_cmd(host, native_cmd);
-	brcmnand_waitfunc(chip);
-
-	if (native_cmd == CMD_PARAMETER_READ ||
-			native_cmd == CMD_PARAMETER_CHANGE_COL) {
-		/* Copy flash cache word-wise */
-		u32 *flash_cache = (u32 *)ctrl->flash_cache;
-		int i;
-
-		brcmnand_soc_data_bus_prepare(ctrl->soc, true);
-
-		/*
-		 * Must cache the FLASH_CACHE now, since changes in
-		 * SECTOR_SIZE_1K may invalidate it
-		 */
-		for (i = 0; i < FC_WORDS; i++)
-			/*
-			 * Flash cache is big endian for parameter pages, at
-			 * least on STB SoCs
-			 */
-			flash_cache[i] = be32_to_cpu(brcmnand_read_fc(ctrl, i));
-
-		brcmnand_soc_data_bus_unprepare(ctrl->soc, true);
-
-		/* Cleanup from HW quirk: restore SECTOR_SIZE_1K */
-		if (host->hwcfg.sector_size_1k)
-			brcmnand_set_sector_size_1k(host,
-						    host->hwcfg.sector_size_1k);
-	}
-
-	/* Re-enable protection is necessary only after erase */
-	if (command == NAND_CMD_ERASE1)
-		brcmnand_wp(mtd, 1);
-}
-
-static uint8_t brcmnand_read_byte(struct nand_chip *chip)
-{
-	struct brcmnand_host *host = nand_get_controller_data(chip);
-	struct brcmnand_controller *ctrl = host->ctrl;
-	uint8_t ret = 0;
-	int addr, offs;
-
-	switch (host->last_cmd) {
-	case NAND_CMD_READID:
-		if (host->last_byte < 4)
-			ret = brcmnand_read_reg(ctrl, BRCMNAND_ID) >>
-				(24 - (host->last_byte << 3));
-		else if (host->last_byte < 8)
-			ret = brcmnand_read_reg(ctrl, BRCMNAND_ID_EXT) >>
-				(56 - (host->last_byte << 3));
-		break;
-
-	case NAND_CMD_READOOB:
-		ret = oob_reg_read(ctrl, host->last_byte);
-		break;
-
-	case NAND_CMD_STATUS:
-		ret = brcmnand_read_reg(ctrl, BRCMNAND_INTFC_STATUS) &
-					INTFC_FLASH_STATUS;
-		if (wp_on) /* hide WP status */
-			ret |= NAND_STATUS_WP;
-		break;
-
-	case NAND_CMD_PARAM:
-	case NAND_CMD_RNDOUT:
-		addr = host->last_addr + host->last_byte;
-		offs = addr & (FC_BYTES - 1);
-
-		/* At FC_BYTES boundary, switch to next column */
-		if (host->last_byte > 0 && offs == 0)
-			nand_change_read_column_op(chip, addr, NULL, 0, false);
-
-		ret = ctrl->flash_cache[offs];
-		break;
-	case NAND_CMD_GET_FEATURES:
-		if (host->last_byte >= ONFI_SUBFEATURE_PARAM_LEN) {
-			ret = 0;
-		} else {
-			bool last = host->last_byte ==
-				ONFI_SUBFEATURE_PARAM_LEN - 1;
-			brcmnand_low_level_op(host, LL_OP_RD, 0, last);
-			ret = brcmnand_read_reg(ctrl, BRCMNAND_LL_RDATA) & 0xff;
-		}
-	}
-
-	dev_dbg(ctrl->dev, "read byte = 0x%02x\n", ret);
-	host->last_byte++;
-
-	return ret;
-}
-
-static void brcmnand_read_buf(struct nand_chip *chip, uint8_t *buf, int len)
-{
-	int i;
-
-	for (i = 0; i < len; i++, buf++)
-		*buf = brcmnand_read_byte(chip);
-}
-
-static void brcmnand_write_buf(struct nand_chip *chip, const uint8_t *buf,
-			       int len)
-{
-	int i;
-	struct brcmnand_host *host = nand_get_controller_data(chip);
-
-	switch (host->last_cmd) {
-	case NAND_CMD_SET_FEATURES:
-		for (i = 0; i < len; i++)
-			brcmnand_low_level_op(host, LL_OP_WR, buf[i],
-						  (i + 1) == len);
-		break;
-	default:
-		BUG();
-		break;
-	}
-}
-
 /*
  *  Kick EDU engine
  */
@@ -2345,8 +2168,9 @@ static int brcmnand_read_page(struct nand_chip *chip, uint8_t *buf,
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct brcmnand_host *host = nand_get_controller_data(chip);
 	u8 *oob = oob_required ? (u8 *)chip->oob_poi : NULL;
+	u64 addr = (u64)page << chip->page_shift;
 
-	nand_read_page_op(chip, page, 0, NULL, 0);
+	host->last_addr = addr;
 
 	return brcmnand_read(mtd, chip, host->last_addr,
 			mtd->writesize >> FC_SHIFT, (u32 *)buf, oob);
@@ -2359,8 +2183,9 @@ static int brcmnand_read_page_raw(struct nand_chip *chip, uint8_t *buf,
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	u8 *oob = oob_required ? (u8 *)chip->oob_poi : NULL;
 	int ret;
+	u64 addr = (u64)page << chip->page_shift;
 
-	nand_read_page_op(chip, page, 0, NULL, 0);
+	host->last_addr = addr;
 
 	brcmnand_set_ecc_enabled(host, 0);
 	ret = brcmnand_read(mtd, chip, host->last_addr,
@@ -2468,11 +2293,11 @@ static int brcmnand_write_page(struct nand_chip *chip, const uint8_t *buf,
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct brcmnand_host *host = nand_get_controller_data(chip);
 	void *oob = oob_required ? chip->oob_poi : NULL;
+	u64 addr = (u64)page << chip->page_shift;
 
-	nand_prog_page_begin_op(chip, page, 0, NULL, 0);
-	brcmnand_write(mtd, chip, host->last_addr, (const u32 *)buf, oob);
+	host->last_addr = addr;
 
-	return nand_prog_page_end_op(chip);
+	return brcmnand_write(mtd, chip, host->last_addr, (const u32 *)buf, oob);
 }
 
 static int brcmnand_write_page_raw(struct nand_chip *chip, const uint8_t *buf,
@@ -2481,13 +2306,15 @@ static int brcmnand_write_page_raw(struct nand_chip *chip, const uint8_t *buf,
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct brcmnand_host *host = nand_get_controller_data(chip);
 	void *oob = oob_required ? chip->oob_poi : NULL;
+	u64 addr = (u64)page << chip->page_shift;
+	int ret = 0;
 
-	nand_prog_page_begin_op(chip, page, 0, NULL, 0);
+	host->last_addr = addr;
 	brcmnand_set_ecc_enabled(host, 0);
-	brcmnand_write(mtd, chip, host->last_addr, (const u32 *)buf, oob);
+	ret = brcmnand_write(mtd, chip, host->last_addr, (const u32 *)buf, oob);
 	brcmnand_set_ecc_enabled(host, 1);
 
-	return nand_prog_page_end_op(chip);
+	return ret;
 }
 
 static int brcmnand_write_oob(struct nand_chip *chip, int page)
@@ -2511,6 +2338,130 @@ static int brcmnand_write_oob_raw(struct nand_chip *chip, int page)
 	return ret;
 }
 
+static int brcmnand_exec_instr(struct brcmnand_host *host, int i,
+				const struct nand_operation *op)
+{
+	const struct nand_op_instr *instr = &op->instrs[i];
+	struct brcmnand_controller *ctrl = host->ctrl;
+	const u8 *out;
+	bool last_op;
+	int ret = 0;
+	u8 *in;
+
+	/*
+	 * The controller needs to be aware of the last command in the operation
+	 * (WAITRDY excepted).
+	 */
+	last_op = ((i == (op->ninstrs - 1)) && (instr->type != NAND_OP_WAITRDY_INSTR)) ||
+		  ((i == (op->ninstrs - 2)) && (op->instrs[i+1].type == NAND_OP_WAITRDY_INSTR));
+
+	switch (instr->type) {
+	case NAND_OP_CMD_INSTR:
+		brcmnand_low_level_op(host, LL_OP_CMD, instr->ctx.cmd.opcode, last_op);
+		break;
+
+	case NAND_OP_ADDR_INSTR:
+		for (i = 0; i < instr->ctx.addr.naddrs; i++)
+			brcmnand_low_level_op(host, LL_OP_ADDR, instr->ctx.addr.addrs[i],
+					      last_op && (i == (instr->ctx.addr.naddrs - 1)));
+		break;
+
+	case NAND_OP_DATA_IN_INSTR:
+		in = instr->ctx.data.buf.in;
+		for (i = 0; i < instr->ctx.data.len; i++) {
+			brcmnand_low_level_op(host, LL_OP_RD, 0,
+					      last_op && (i == (instr->ctx.data.len - 1)));
+			in[i] = brcmnand_read_reg(host->ctrl, BRCMNAND_LL_RDATA);
+		}
+		break;
+
+	case NAND_OP_DATA_OUT_INSTR:
+		out = instr->ctx.data.buf.out;
+		for (i = 0; i < instr->ctx.data.len; i++)
+			brcmnand_low_level_op(host, LL_OP_WR, out[i],
+					      last_op && (i == (instr->ctx.data.len - 1)));
+		break;
+
+	case NAND_OP_WAITRDY_INSTR:
+		ret = bcmnand_ctrl_poll_status(host, NAND_CTRL_RDY, NAND_CTRL_RDY, 0);
+		break;
+
+	default:
+		dev_err(ctrl->dev, "unsupported instruction type: %d\n",
+			instr->type);
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static int brcmnand_op_is_status(const struct nand_operation *op)
+{
+	if ((op->ninstrs == 2) &&
+	    (op->instrs[0].type == NAND_OP_CMD_INSTR) &&
+	    (op->instrs[0].ctx.cmd.opcode == NAND_CMD_STATUS) &&
+	    (op->instrs[1].type == NAND_OP_DATA_IN_INSTR))
+		return 1;
+
+	return 0;
+}
+
+static int brcmnand_op_is_reset(const struct nand_operation *op)
+{
+	if ((op->ninstrs == 2) &&
+	    (op->instrs[0].type == NAND_OP_CMD_INSTR) &&
+	    (op->instrs[0].ctx.cmd.opcode == NAND_CMD_RESET) &&
+	    (op->instrs[1].type == NAND_OP_WAITRDY_INSTR))
+		return 1;
+
+	return 0;
+}
+
+static int brcmnand_exec_op(struct nand_chip *chip,
+			    const struct nand_operation *op,
+			    bool check_only)
+{
+	struct brcmnand_host *host = nand_get_controller_data(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	u8 *status;
+	unsigned int i;
+	int ret = 0;
+
+	if (check_only)
+		return 0;
+
+	if (brcmnand_op_is_status(op)) {
+		status = op->instrs[1].ctx.data.buf.in;
+		*status = brcmnand_status(host);
+
+		return 0;
+	}
+	else if (brcmnand_op_is_reset(op)) {
+		ret = brcmnand_reset(host);
+		if (ret < 0)
+			return ret;
+
+		brcmnand_wp(mtd, 1);
+
+		return 0;
+	}
+
+	if (op->deassert_wp)
+		brcmnand_wp(mtd, 0);
+
+	for (i = 0; i < op->ninstrs; i++) {
+		ret = brcmnand_exec_instr(host, i, op);
+		if (ret)
+			break;
+	}
+
+	if (op->deassert_wp)
+		brcmnand_wp(mtd, 1);
+
+	return ret;
+}
+
 /***********************************************************************
  * Per-CS setup (1 NAND device)
  ***********************************************************************/
@@ -2821,6 +2772,7 @@ static int brcmnand_attach_chip(struct nand_chip *chip)
 
 static const struct nand_controller_ops brcmnand_controller_ops = {
 	.attach_chip = brcmnand_attach_chip,
+	.exec_op = brcmnand_exec_op,
 };
 
 static int brcmnand_init_cs(struct brcmnand_host *host,
@@ -2845,13 +2797,6 @@ static int brcmnand_init_cs(struct brcmnand_host *host,
 	mtd->owner = THIS_MODULE;
 	mtd->dev.parent = dev;
 
-	chip->legacy.cmd_ctrl = brcmnand_cmd_ctrl;
-	chip->legacy.cmdfunc = brcmnand_cmdfunc;
-	chip->legacy.waitfunc = brcmnand_waitfunc;
-	chip->legacy.read_byte = brcmnand_read_byte;
-	chip->legacy.read_buf = brcmnand_read_buf;
-	chip->legacy.write_buf = brcmnand_write_buf;
-
 	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	chip->ecc.read_page = brcmnand_read_page;
 	chip->ecc.write_page = brcmnand_write_page;
@@ -2863,6 +2808,7 @@ static int brcmnand_init_cs(struct brcmnand_host *host,
 	chip->ecc.write_oob = brcmnand_write_oob;
 
 	chip->controller = &ctrl->controller;
+	ctrl->controller.controller_wp = 1;
 
 	/*
 	 * The bootloader might have configured 16bit mode but
@@ -3299,7 +3245,7 @@ err:
 }
 EXPORT_SYMBOL_GPL(brcmnand_probe);
 
-int brcmnand_remove(struct platform_device *pdev)
+void brcmnand_remove(struct platform_device *pdev)
 {
 	struct brcmnand_controller *ctrl = dev_get_drvdata(&pdev->dev);
 	struct brcmnand_host *host;
@@ -3316,8 +3262,6 @@ int brcmnand_remove(struct platform_device *pdev)
 	clk_disable_unprepare(ctrl->clk);
 
 	dev_set_drvdata(&pdev->dev, NULL);
-
-	return 0;
 }
 EXPORT_SYMBOL_GPL(brcmnand_remove);
 
diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.h b/drivers/mtd/nand/raw/brcmnand/brcmnand.h
index f1f93d85f50d..928114c0be5e 100644
--- a/drivers/mtd/nand/raw/brcmnand/brcmnand.h
+++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.h
@@ -88,7 +88,7 @@ static inline void brcmnand_soc_write(struct brcmnand_soc *soc, u32 val,
 }
 
 int brcmnand_probe(struct platform_device *pdev, struct brcmnand_soc *soc);
-int brcmnand_remove(struct platform_device *pdev);
+void brcmnand_remove(struct platform_device *pdev);
 
 extern const struct dev_pm_ops brcmnand_pm_ops;
 
diff --git a/drivers/mtd/nand/raw/brcmnand/brcmstb_nand.c b/drivers/mtd/nand/raw/brcmnand/brcmstb_nand.c
index 950923d977b7..558f083b92e9 100644
--- a/drivers/mtd/nand/raw/brcmnand/brcmstb_nand.c
+++ b/drivers/mtd/nand/raw/brcmnand/brcmstb_nand.c
@@ -23,7 +23,7 @@ static int brcmstb_nand_probe(struct platform_device *pdev)
 
 static struct platform_driver brcmstb_nand_driver = {
 	.probe			= brcmstb_nand_probe,
-	.remove			= brcmnand_remove,
+	.remove_new		= brcmnand_remove,
 	.driver = {
 		.name		= "brcmstb_nand",
 		.pm		= &brcmnand_pm_ops,
diff --git a/drivers/mtd/nand/raw/brcmnand/iproc_nand.c b/drivers/mtd/nand/raw/brcmnand/iproc_nand.c
index 089c70fc6edf..bf46c8b85898 100644
--- a/drivers/mtd/nand/raw/brcmnand/iproc_nand.c
+++ b/drivers/mtd/nand/raw/brcmnand/iproc_nand.c
@@ -134,7 +134,7 @@ MODULE_DEVICE_TABLE(of, iproc_nand_of_match);
 
 static struct platform_driver iproc_nand_driver = {
 	.probe			= iproc_nand_probe,
-	.remove			= brcmnand_remove,
+	.remove_new		= brcmnand_remove,
 	.driver = {
 		.name		= "iproc_nand",
 		.pm		= &brcmnand_pm_ops,
diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c
index 5d2ddb037a9a..5243fab9face 100644
--- a/drivers/mtd/nand/raw/diskonchip.c
+++ b/drivers/mtd/nand/raw/diskonchip.c
@@ -1491,10 +1491,12 @@ static int __init doc_probe(unsigned long physadr)
 	else
 		numchips = doc2001_init(mtd);
 
-	if ((ret = nand_scan(nand, numchips)) || (ret = doc->late_init(mtd))) {
-		/* DBB note: i believe nand_cleanup is necessary here, as
-		   buffers may have been allocated in nand_base.  Check with
-		   Thomas. FIX ME! */
+	ret = nand_scan(nand, numchips);
+	if (ret)
+		goto fail;
+
+	ret = doc->late_init(mtd);
+	if (ret) {
 		nand_cleanup(nand);
 		goto fail;
 	}
diff --git a/drivers/mtd/nand/raw/fsl_ifc_nand.c b/drivers/mtd/nand/raw/fsl_ifc_nand.c
index 20bb1e0cb5eb..f0e2318ce088 100644
--- a/drivers/mtd/nand/raw/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_ifc_nand.c
@@ -21,7 +21,7 @@
 
 #define ERR_BYTE		0xFF /* Value returned for read
 					bytes when read failed	*/
-#define IFC_TIMEOUT_MSECS	500  /* Maximum number of mSecs to wait
+#define IFC_TIMEOUT_MSECS	1000 /* Maximum timeout to wait
 					for IFC NAND Machine	*/
 
 struct fsl_ifc_ctrl;
diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c
index 71ec4052e52a..cdb58aca59c0 100644
--- a/drivers/mtd/nand/raw/meson_nand.c
+++ b/drivers/mtd/nand/raw/meson_nand.c
@@ -90,6 +90,8 @@
 
 /* eMMC clock register, misc control */
 #define CLK_SELECT_NAND		BIT(31)
+#define CLK_ALWAYS_ON_NAND	BIT(24)
+#define CLK_SELECT_FIX_PLL2	BIT(6)
 
 #define NFC_CLK_CYCLE		6
 
@@ -509,7 +511,7 @@ static void meson_nfc_set_user_byte(struct nand_chip *nand, u8 *oob_buf)
 	__le64 *info;
 	int i, count;
 
-	for (i = 0, count = 0; i < nand->ecc.steps; i++, count += 2) {
+	for (i = 0, count = 0; i < nand->ecc.steps; i++, count += (2 + nand->ecc.bytes)) {
 		info = &meson_chip->info_buf[i];
 		*info |= oob_buf[count];
 		*info |= oob_buf[count + 1] << 8;
@@ -522,7 +524,7 @@ static void meson_nfc_get_user_byte(struct nand_chip *nand, u8 *oob_buf)
 	__le64 *info;
 	int i, count;
 
-	for (i = 0, count = 0; i < nand->ecc.steps; i++, count += 2) {
+	for (i = 0, count = 0; i < nand->ecc.steps; i++, count += (2 + nand->ecc.bytes)) {
 		info = &meson_chip->info_buf[i];
 		oob_buf[count] = *info;
 		oob_buf[count + 1] = *info >> 8;
@@ -1154,7 +1156,7 @@ static int meson_nfc_clk_init(struct meson_nfc *nfc)
 		return PTR_ERR(nfc->nand_clk);
 
 	/* init SD_EMMC_CLOCK to sane defaults w/min clock rate */
-	writel(CLK_SELECT_NAND | readl(nfc->reg_clk),
+	writel(CLK_ALWAYS_ON_NAND | CLK_SELECT_NAND | CLK_SELECT_FIX_PLL2,
 	       nfc->reg_clk);
 
 	ret = clk_prepare_enable(nfc->core_clk);
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 9e24bedffd89..3b3ce2926f5d 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -366,6 +366,10 @@ static int nand_check_wp(struct nand_chip *chip)
 	if (chip->options & NAND_BROKEN_XD)
 		return 0;
 
+	/* controller responsible for NAND write protect */
+	if (chip->controller->controller_wp)
+		return 0;
+
 	/* Check the WP bit */
 	ret = nand_status_op(chip, &status);
 	if (ret)
@@ -1207,6 +1211,23 @@ static int nand_lp_exec_read_page_op(struct nand_chip *chip, unsigned int page,
 	return nand_exec_op(chip, &op);
 }
 
+static void rawnand_cap_cont_reads(struct nand_chip *chip)
+{
+	struct nand_memory_organization *memorg;
+	unsigned int pages_per_lun, first_lun, last_lun;
+
+	memorg = nanddev_get_memorg(&chip->base);
+	pages_per_lun = memorg->pages_per_eraseblock * memorg->eraseblocks_per_lun;
+	first_lun = chip->cont_read.first_page / pages_per_lun;
+	last_lun = chip->cont_read.last_page / pages_per_lun;
+
+	/* Prevent sequential cache reads across LUN boundaries */
+	if (first_lun != last_lun)
+		chip->cont_read.pause_page = first_lun * pages_per_lun + pages_per_lun - 1;
+	else
+		chip->cont_read.pause_page = chip->cont_read.last_page;
+}
+
 static int nand_lp_exec_cont_read_page_op(struct nand_chip *chip, unsigned int page,
 					  unsigned int offset_in_page, void *buf,
 					  unsigned int len, bool check_only)
@@ -1225,7 +1246,7 @@ static int nand_lp_exec_cont_read_page_op(struct nand_chip *chip, unsigned int p
 		NAND_OP_DATA_IN(len, buf, 0),
 	};
 	struct nand_op_instr cont_instrs[] = {
-		NAND_OP_CMD(page == chip->cont_read.last_page ?
+		NAND_OP_CMD(page == chip->cont_read.pause_page ?
 			    NAND_CMD_READCACHEEND : NAND_CMD_READCACHESEQ,
 			    NAND_COMMON_TIMING_NS(conf, tWB_max)),
 		NAND_OP_WAIT_RDY(NAND_COMMON_TIMING_MS(conf, tR_max),
@@ -1262,16 +1283,29 @@ static int nand_lp_exec_cont_read_page_op(struct nand_chip *chip, unsigned int p
 	}
 
 	if (page == chip->cont_read.first_page)
-		return nand_exec_op(chip, &start_op);
+		ret = nand_exec_op(chip, &start_op);
 	else
-		return nand_exec_op(chip, &cont_op);
+		ret = nand_exec_op(chip, &cont_op);
+	if (ret)
+		return ret;
+
+	if (!chip->cont_read.ongoing)
+		return 0;
+
+	if (page == chip->cont_read.pause_page &&
+	    page != chip->cont_read.last_page) {
+		chip->cont_read.first_page = chip->cont_read.pause_page + 1;
+		rawnand_cap_cont_reads(chip);
+	} else if (page == chip->cont_read.last_page) {
+		chip->cont_read.ongoing = false;
+	}
+
+	return 0;
 }
 
 static bool rawnand_cont_read_ongoing(struct nand_chip *chip, unsigned int page)
 {
-	return chip->cont_read.ongoing &&
-		page >= chip->cont_read.first_page &&
-		page <= chip->cont_read.last_page;
+	return chip->cont_read.ongoing && page >= chip->cont_read.first_page;
 }
 
 /**
@@ -1493,7 +1527,8 @@ static int nand_exec_prog_page_op(struct nand_chip *chip, unsigned int page,
 			    NAND_COMMON_TIMING_NS(conf, tWB_max)),
 		NAND_OP_WAIT_RDY(NAND_COMMON_TIMING_MS(conf, tPROG_max), 0),
 	};
-	struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs);
+	struct nand_operation op = NAND_DESTRUCTIVE_OPERATION(chip->cur_cs,
+							      instrs);
 	int naddrs = nand_fill_column_cycles(chip, addrs, offset_in_page);
 
 	if (naddrs < 0)
@@ -1916,7 +1951,8 @@ int nand_erase_op(struct nand_chip *chip, unsigned int eraseblock)
 			NAND_OP_WAIT_RDY(NAND_COMMON_TIMING_MS(conf, tBERS_max),
 					 0),
 		};
-		struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs);
+		struct nand_operation op = NAND_DESTRUCTIVE_OPERATION(chip->cur_cs,
+								      instrs);
 
 		if (chip->options & NAND_ROW_ADDR_3)
 			instrs[1].ctx.addr.naddrs++;
@@ -3430,21 +3466,42 @@ static void rawnand_enable_cont_reads(struct nand_chip *chip, unsigned int page,
 				      u32 readlen, int col)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
+	unsigned int end_page, end_col;
+
+	chip->cont_read.ongoing = false;
 
 	if (!chip->controller->supported_op.cont_read)
 		return;
 
-	if ((col && col + readlen < (3 * mtd->writesize)) ||
-	    (!col && readlen < (2 * mtd->writesize))) {
-		chip->cont_read.ongoing = false;
+	end_page = DIV_ROUND_UP(col + readlen, mtd->writesize);
+	end_col = (col + readlen) % mtd->writesize;
+
+	if (col)
+		page++;
+
+	if (end_col && end_page)
+		end_page--;
+
+	if (page + 1 > end_page)
 		return;
-	}
 
-	chip->cont_read.ongoing = true;
 	chip->cont_read.first_page = page;
-	if (col)
+	chip->cont_read.last_page = end_page;
+	chip->cont_read.ongoing = true;
+
+	rawnand_cap_cont_reads(chip);
+}
+
+static void rawnand_cont_read_skip_first_page(struct nand_chip *chip, unsigned int page)
+{
+	if (!chip->cont_read.ongoing || page != chip->cont_read.first_page)
+		return;
+
+	chip->cont_read.first_page++;
+	if (chip->cont_read.first_page == chip->cont_read.pause_page)
 		chip->cont_read.first_page++;
-	chip->cont_read.last_page = page + ((readlen >> chip->page_shift) & chip->pagemask);
+	if (chip->cont_read.first_page >= chip->cont_read.last_page)
+		chip->cont_read.ongoing = false;
 }
 
 /**
@@ -3621,6 +3678,8 @@ read_retry:
 			buf += bytes;
 			max_bitflips = max_t(unsigned int, max_bitflips,
 					     chip->pagecache.bitflips);
+
+			rawnand_cont_read_skip_first_page(chip, page);
 		}
 
 		readlen -= bytes;
@@ -5125,6 +5184,14 @@ static void rawnand_late_check_supported_ops(struct nand_chip *chip)
 	/* The supported_op fields should not be set by individual drivers */
 	WARN_ON_ONCE(chip->controller->supported_op.cont_read);
 
+	/*
+	 * Too many devices do not support sequential cached reads with on-die
+	 * ECC correction enabled, so in this case refuse to perform the
+	 * automation.
+	 */
+	if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_DIE)
+		return;
+
 	if (!nand_has_exec_op(chip))
 		return;
 
diff --git a/drivers/mtd/nand/raw/pl35x-nand-controller.c b/drivers/mtd/nand/raw/pl35x-nand-controller.c
index c506e92a3e45..1c76ee98efb7 100644
--- a/drivers/mtd/nand/raw/pl35x-nand-controller.c
+++ b/drivers/mtd/nand/raw/pl35x-nand-controller.c
@@ -128,7 +128,7 @@ struct pl35x_nand {
  * @conf_regs: SMC configuration registers for command phase
  * @io_regs: NAND data registers for data phase
  * @controller: Core NAND controller structure
- * @chip: NAND chip information structure
+ * @chips: List of connected NAND chips
  * @selected_chip: NAND chip currently selected by the controller
  * @assigned_cs: List of assigned CS
  * @ecc_buf: Temporary buffer to extract ECC bytes
diff --git a/drivers/mtd/nand/raw/rockchip-nand-controller.c b/drivers/mtd/nand/raw/rockchip-nand-controller.c
index 596cf9a78274..7baaef69d70a 100644
--- a/drivers/mtd/nand/raw/rockchip-nand-controller.c
+++ b/drivers/mtd/nand/raw/rockchip-nand-controller.c
@@ -98,7 +98,7 @@ enum nfc_type {
  * @high: ECC count high bit index at register.
  * @high_mask: mask bit
  */
-struct ecc_cnt_status {
+struct rk_ecc_cnt_status {
 	u8 err_flag_bit;
 	u8 low;
 	u8 low_mask;
@@ -108,6 +108,7 @@ struct ecc_cnt_status {
 };
 
 /**
+ * struct nfc_cfg: Rockchip NAND controller configuration
  * @type: NFC version
  * @ecc_strengths: ECC strengths
  * @ecc_cfgs: ECC config values
@@ -144,8 +145,8 @@ struct nfc_cfg {
 	u32 int_st_off;
 	u32 oob0_off;
 	u32 oob1_off;
-	struct ecc_cnt_status ecc0;
-	struct ecc_cnt_status ecc1;
+	struct rk_ecc_cnt_status ecc0;
+	struct rk_ecc_cnt_status ecc1;
 };
 
 struct rk_nfc_nand_chip {
diff --git a/drivers/mtd/nand/raw/s3c2410.c b/drivers/mtd/nand/raw/s3c2410.c
index 3d3d5c9814ff..48c1d0eb66ca 100644
--- a/drivers/mtd/nand/raw/s3c2410.c
+++ b/drivers/mtd/nand/raw/s3c2410.c
@@ -105,7 +105,6 @@ struct s3c2410_nand_info;
 
 /**
  * struct s3c2410_nand_mtd - driver MTD structure
- * @mtd: The MTD instance to pass to the MTD layer.
  * @chip: The NAND chip information.
  * @set: The platform information supplied for this set of NAND chips.
  * @info: Link back to the hardware information.
@@ -145,7 +144,6 @@ enum s3c_nand_clk_state {
  * @clk_rate: The clock rate from @clk.
  * @clk_state: The current clock state.
  * @cpu_type: The exact type of this controller.
- * @freq_transition: CPUFreq notifier block
  */
 struct s3c2410_nand_info {
 	/* mtd info */
diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c
index eddcc0728a67..37f79c019a72 100644
--- a/drivers/mtd/nand/raw/txx9ndfmc.c
+++ b/drivers/mtd/nand/raw/txx9ndfmc.c
@@ -276,7 +276,7 @@ static const struct nand_controller_ops txx9ndfmc_controller_ops = {
 	.attach_chip = txx9ndfmc_attach_chip,
 };
 
-static int __init txx9ndfmc_probe(struct platform_device *dev)
+static int txx9ndfmc_probe(struct platform_device *dev)
 {
 	struct txx9ndfmc_platform_data *plat = dev_get_platdata(&dev->dev);
 	int hold, spw;
@@ -369,13 +369,11 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 	return 0;
 }
 
-static int __exit txx9ndfmc_remove(struct platform_device *dev)
+static void txx9ndfmc_remove(struct platform_device *dev)
 {
 	struct txx9ndfmc_drvdata *drvdata = platform_get_drvdata(dev);
 	int ret, i;
 
-	if (!drvdata)
-		return 0;
 	for (i = 0; i < MAX_TXX9NDFMC_DEV; i++) {
 		struct mtd_info *mtd = drvdata->mtds[i];
 		struct nand_chip *chip;
@@ -392,7 +390,6 @@ static int __exit txx9ndfmc_remove(struct platform_device *dev)
 		kfree(txx9_priv->mtdname);
 		kfree(txx9_priv);
 	}
-	return 0;
 }
 
 #ifdef CONFIG_PM
@@ -407,14 +404,14 @@ static int txx9ndfmc_resume(struct platform_device *dev)
 #endif
 
 static struct platform_driver txx9ndfmc_driver = {
-	.remove		= __exit_p(txx9ndfmc_remove),
+	.probe		= txx9ndfmc_probe,
+	.remove_new	= txx9ndfmc_remove,
 	.resume		= txx9ndfmc_resume,
 	.driver		= {
 		.name	= "txx9ndfmc",
 	},
 };
-
-module_platform_driver_probe(txx9ndfmc_driver, txx9ndfmc_probe);
+module_platform_driver(txx9ndfmc_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("TXx9 SoC NAND flash controller driver");
diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
index 849ccfedbc72..e0b6715e5dfe 100644
--- a/drivers/mtd/nand/spi/core.c
+++ b/drivers/mtd/nand/spi/core.c
@@ -974,7 +974,7 @@ static int spinand_manufacturer_match(struct spinand_device *spinand,
 		spinand->manufacturer = manufacturer;
 		return 0;
 	}
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static int spinand_id_detect(struct spinand_device *spinand)
diff --git a/drivers/mtd/spi-nor/atmel.c b/drivers/mtd/spi-nor/atmel.c
index e13b8d2dd50a..45d1153a04a0 100644
--- a/drivers/mtd/spi-nor/atmel.c
+++ b/drivers/mtd/spi-nor/atmel.c
@@ -16,12 +16,12 @@
  * is to unlock the whole flash array on startup. Therefore, we have to support
  * exactly this operation.
  */
-static int at25fs_nor_lock(struct spi_nor *nor, loff_t ofs, uint64_t len)
+static int at25fs_nor_lock(struct spi_nor *nor, loff_t ofs, u64 len)
 {
 	return -EOPNOTSUPP;
 }
 
-static int at25fs_nor_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len)
+static int at25fs_nor_unlock(struct spi_nor *nor, loff_t ofs, u64 len)
 {
 	int ret;
 
@@ -37,7 +37,7 @@ static int at25fs_nor_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 	return ret;
 }
 
-static int at25fs_nor_is_locked(struct spi_nor *nor, loff_t ofs, uint64_t len)
+static int at25fs_nor_is_locked(struct spi_nor *nor, loff_t ofs, u64 len)
 {
 	return -EOPNOTSUPP;
 }
@@ -69,7 +69,7 @@ static const struct spi_nor_fixups at25fs_nor_fixups = {
  * Return: 0 on success, -error otherwise.
  */
 static int atmel_nor_set_global_protection(struct spi_nor *nor, loff_t ofs,
-					   uint64_t len, bool is_protect)
+					   u64 len, bool is_protect)
 {
 	int ret;
 	u8 sr;
@@ -118,20 +118,18 @@ static int atmel_nor_set_global_protection(struct spi_nor *nor, loff_t ofs,
 	return spi_nor_write_sr(nor, nor->bouncebuf, 1);
 }
 
-static int atmel_nor_global_protect(struct spi_nor *nor, loff_t ofs,
-				    uint64_t len)
+static int atmel_nor_global_protect(struct spi_nor *nor, loff_t ofs, u64 len)
 {
 	return atmel_nor_set_global_protection(nor, ofs, len, true);
 }
 
-static int atmel_nor_global_unprotect(struct spi_nor *nor, loff_t ofs,
-				      uint64_t len)
+static int atmel_nor_global_unprotect(struct spi_nor *nor, loff_t ofs, u64 len)
 {
 	return atmel_nor_set_global_protection(nor, ofs, len, false);
 }
 
 static int atmel_nor_is_global_protected(struct spi_nor *nor, loff_t ofs,
-					 uint64_t len)
+					 u64 len)
 {
 	int ret;
 
diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c
index 1c443fe568cf..4129764fad8c 100644
--- a/drivers/mtd/spi-nor/core.c
+++ b/drivers/mtd/spi-nor/core.c
@@ -1060,24 +1060,32 @@ static int spi_nor_read_sr2(struct spi_nor *nor, u8 *sr2)
 }
 
 /**
- * spi_nor_erase_chip() - Erase the entire flash memory.
+ * spi_nor_erase_die() - Erase the entire die.
  * @nor:	pointer to 'struct spi_nor'.
+ * @addr:	address of the die.
+ * @die_size:	size of the die.
  *
  * Return: 0 on success, -errno otherwise.
  */
-static int spi_nor_erase_chip(struct spi_nor *nor)
+static int spi_nor_erase_die(struct spi_nor *nor, loff_t addr, size_t die_size)
 {
+	bool multi_die = nor->mtd.size != die_size;
 	int ret;
 
-	dev_dbg(nor->dev, " %lldKiB\n", (long long)(nor->mtd.size >> 10));
+	dev_dbg(nor->dev, " %lldKiB\n", (long long)(die_size >> 10));
 
 	if (nor->spimem) {
-		struct spi_mem_op op = SPI_NOR_CHIP_ERASE_OP;
+		struct spi_mem_op op =
+			SPI_NOR_DIE_ERASE_OP(nor->params->die_erase_opcode,
+					     nor->addr_nbytes, addr, multi_die);
 
 		spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
 
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
+		if (multi_die)
+			return -EOPNOTSUPP;
+
 		ret = spi_nor_controller_ops_write_reg(nor,
 						       SPINOR_OP_CHIP_ERASE,
 						       NULL, 0);
@@ -1792,6 +1800,51 @@ destroy_erase_cmd_list:
 	return ret;
 }
 
+static int spi_nor_erase_dice(struct spi_nor *nor, loff_t addr,
+			      size_t len, size_t die_size)
+{
+	unsigned long timeout;
+	int ret;
+
+	/*
+	 * Scale the timeout linearly with the size of the flash, with
+	 * a minimum calibrated to an old 2MB flash. We could try to
+	 * pull these from CFI/SFDP, but these values should be good
+	 * enough for now.
+	 */
+	timeout = max(CHIP_ERASE_2MB_READY_WAIT_JIFFIES,
+		      CHIP_ERASE_2MB_READY_WAIT_JIFFIES *
+		      (unsigned long)(nor->mtd.size / SZ_2M));
+
+	do {
+		ret = spi_nor_lock_device(nor);
+		if (ret)
+			return ret;
+
+		ret = spi_nor_write_enable(nor);
+		if (ret) {
+			spi_nor_unlock_device(nor);
+			return ret;
+		}
+
+		ret = spi_nor_erase_die(nor, addr, die_size);
+
+		spi_nor_unlock_device(nor);
+		if (ret)
+			return ret;
+
+		ret = spi_nor_wait_till_ready_with_timeout(nor, timeout);
+		if (ret)
+			return ret;
+
+		addr += die_size;
+		len -= die_size;
+
+	} while (len);
+
+	return 0;
+}
+
 /*
  * Erase an address range on the nor chip.  The address range may extend
  * one or more erase sectors. Return an error if there is a problem erasing.
@@ -1799,8 +1852,10 @@ destroy_erase_cmd_list:
 static int spi_nor_erase(struct mtd_info *mtd, struct erase_info *instr)
 {
 	struct spi_nor *nor = mtd_to_spi_nor(mtd);
-	u32 addr, len;
-	uint32_t rem;
+	u8 n_dice = nor->params->n_dice;
+	bool multi_die_erase = false;
+	u32 addr, len, rem;
+	size_t die_size;
 	int ret;
 
 	dev_dbg(nor->dev, "at 0x%llx, len %lld\n", (long long)instr->addr,
@@ -1815,39 +1870,22 @@ static int spi_nor_erase(struct mtd_info *mtd, struct erase_info *instr)
 	addr = instr->addr;
 	len = instr->len;
 
+	if (n_dice) {
+		die_size = div_u64(mtd->size, n_dice);
+		if (!(len & (die_size - 1)) && !(addr & (die_size - 1)))
+			multi_die_erase = true;
+	} else {
+		die_size = mtd->size;
+	}
+
 	ret = spi_nor_prep_and_lock_pe(nor, instr->addr, instr->len);
 	if (ret)
 		return ret;
 
-	/* whole-chip erase? */
-	if (len == mtd->size && !(nor->flags & SNOR_F_NO_OP_CHIP_ERASE)) {
-		unsigned long timeout;
-
-		ret = spi_nor_lock_device(nor);
-		if (ret)
-			goto erase_err;
-
-		ret = spi_nor_write_enable(nor);
-		if (ret) {
-			spi_nor_unlock_device(nor);
-			goto erase_err;
-		}
-
-		ret = spi_nor_erase_chip(nor);
-		spi_nor_unlock_device(nor);
-		if (ret)
-			goto erase_err;
-
-		/*
-		 * Scale the timeout linearly with the size of the flash, with
-		 * a minimum calibrated to an old 2MB flash. We could try to
-		 * pull these from CFI/SFDP, but these values should be good
-		 * enough for now.
-		 */
-		timeout = max(CHIP_ERASE_2MB_READY_WAIT_JIFFIES,
-			      CHIP_ERASE_2MB_READY_WAIT_JIFFIES *
-			      (unsigned long)(mtd->size / SZ_2M));
-		ret = spi_nor_wait_till_ready_with_timeout(nor, timeout);
+	/* chip (die) erase? */
+	if ((len == mtd->size && !(nor->flags & SNOR_F_NO_OP_CHIP_ERASE)) ||
+	    multi_die_erase) {
+		ret = spi_nor_erase_dice(nor, addr, len, die_size);
 		if (ret)
 			goto erase_err;
 
@@ -2146,7 +2184,7 @@ static int spi_nor_write(struct mtd_info *mtd, loff_t to, size_t len,
 		if (is_power_of_2(page_size)) {
 			page_offset = addr & (page_size - 1);
 		} else {
-			uint64_t aux = addr;
+			u64 aux = addr;
 
 			page_offset = do_div(aux, page_size);
 		}
@@ -2850,9 +2888,6 @@ static void spi_nor_init_flags(struct spi_nor *nor)
 			nor->flags |= SNOR_F_HAS_SR_BP3_BIT6;
 	}
 
-	if (flags & NO_CHIP_ERASE)
-		nor->flags |= SNOR_F_NO_OP_CHIP_ERASE;
-
 	if (flags & SPI_NOR_RWW && nor->params->n_banks > 1 &&
 	    !nor->controller_ops)
 		nor->flags |= SNOR_F_RWW;
@@ -2897,17 +2932,22 @@ static int spi_nor_late_init_params(struct spi_nor *nor)
 			return ret;
 	}
 
+	/* Needed by some flashes late_init hooks. */
+	spi_nor_init_flags(nor);
+
 	if (nor->info->fixups && nor->info->fixups->late_init) {
 		ret = nor->info->fixups->late_init(nor);
 		if (ret)
 			return ret;
 	}
 
+	if (!nor->params->die_erase_opcode)
+		nor->params->die_erase_opcode = SPINOR_OP_CHIP_ERASE;
+
 	/* Default method kept for backward compatibility. */
 	if (!params->set_4byte_addr_mode)
 		params->set_4byte_addr_mode = spi_nor_set_4byte_addr_mode_brwr;
 
-	spi_nor_init_flags(nor);
 	spi_nor_init_fixup_flags(nor);
 
 	/*
@@ -3145,8 +3185,20 @@ int spi_nor_set_4byte_addr_mode(struct spi_nor *nor, bool enable)
 	struct spi_nor_flash_parameter *params = nor->params;
 	int ret;
 
+	if (enable) {
+		/*
+		 * If the RESET# pin isn't hooked up properly, or the system
+		 * otherwise doesn't perform a reset command in the boot
+		 * sequence, it's impossible to 100% protect against unexpected
+		 * reboots (e.g., crashes). Warn the user (or hopefully, system
+		 * designer) that this is bad.
+		 */
+		WARN_ONCE(nor->flags & SNOR_F_BROKEN_RESET,
+			  "enabling reset hack; may not recover from unexpected reboots\n");
+	}
+
 	ret = params->set_4byte_addr_mode(nor, enable);
-	if (ret && ret != -ENOTSUPP)
+	if (ret && ret != -EOPNOTSUPP)
 		return ret;
 
 	if (enable) {
@@ -3193,20 +3245,8 @@ static int spi_nor_init(struct spi_nor *nor)
 
 	if (nor->addr_nbytes == 4 &&
 	    nor->read_proto != SNOR_PROTO_8_8_8_DTR &&
-	    !(nor->flags & SNOR_F_4B_OPCODES)) {
-		/*
-		 * If the RESET# pin isn't hooked up properly, or the system
-		 * otherwise doesn't perform a reset command in the boot
-		 * sequence, it's impossible to 100% protect against unexpected
-		 * reboots (e.g., crashes). Warn the user (or hopefully, system
-		 * designer) that this is bad.
-		 */
-		WARN_ONCE(nor->flags & SNOR_F_BROKEN_RESET,
-			  "enabling reset hack; may not recover from unexpected reboots\n");
-		err = spi_nor_set_4byte_addr_mode(nor, true);
-		if (err)
-			return err;
-	}
+	    !(nor->flags & SNOR_F_4B_OPCODES))
+		return spi_nor_set_4byte_addr_mode(nor, true);
 
 	return 0;
 }
@@ -3237,7 +3277,8 @@ static void spi_nor_soft_reset(struct spi_nor *nor)
 
 	ret = spi_mem_exec_op(nor->spimem, &op);
 	if (ret) {
-		dev_warn(nor->dev, "Software reset failed: %d\n", ret);
+		if (ret != -EOPNOTSUPP)
+			dev_warn(nor->dev, "Software reset failed: %d\n", ret);
 		return;
 	}
 
@@ -3452,9 +3493,7 @@ int spi_nor_scan(struct spi_nor *nor, const char *name,
 {
 	const struct flash_info *info;
 	struct device *dev = nor->dev;
-	struct mtd_info *mtd = &nor->mtd;
 	int ret;
-	int i;
 
 	ret = spi_nor_check(nor);
 	if (ret)
@@ -3518,25 +3557,9 @@ int spi_nor_scan(struct spi_nor *nor, const char *name,
 	/* No mtd_info fields should be used up to this point. */
 	spi_nor_set_mtd_info(nor);
 
-	dev_info(dev, "%s (%lld Kbytes)\n", info->name,
-			(long long)mtd->size >> 10);
-
-	dev_dbg(dev,
-		"mtd .name = %s, .size = 0x%llx (%lldMiB), "
-		".erasesize = 0x%.8x (%uKiB) .numeraseregions = %d\n",
-		mtd->name, (long long)mtd->size, (long long)(mtd->size >> 20),
-		mtd->erasesize, mtd->erasesize / 1024, mtd->numeraseregions);
-
-	if (mtd->numeraseregions)
-		for (i = 0; i < mtd->numeraseregions; i++)
-			dev_dbg(dev,
-				"mtd.eraseregions[%d] = { .offset = 0x%llx, "
-				".erasesize = 0x%.8x (%uKiB), "
-				".numblocks = %d }\n",
-				i, (long long)mtd->eraseregions[i].offset,
-				mtd->eraseregions[i].erasesize,
-				mtd->eraseregions[i].erasesize / 1024,
-				mtd->eraseregions[i].numblocks);
+	dev_dbg(dev, "Manufacturer and device ID: %*phN\n",
+		SPI_NOR_MAX_ID_LEN, nor->id);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(spi_nor_scan);
diff --git a/drivers/mtd/spi-nor/core.h b/drivers/mtd/spi-nor/core.h
index 93cd2fc3606d..d36c0e072954 100644
--- a/drivers/mtd/spi-nor/core.h
+++ b/drivers/mtd/spi-nor/core.h
@@ -85,9 +85,9 @@
 		   SPI_MEM_OP_NO_DUMMY,					\
 		   SPI_MEM_OP_NO_DATA)
 
-#define SPI_NOR_CHIP_ERASE_OP						\
-	SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_CHIP_ERASE, 0),		\
-		   SPI_MEM_OP_NO_ADDR,					\
+#define SPI_NOR_DIE_ERASE_OP(opcode, addr_nbytes, addr, dice)		\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(opcode, 0),				\
+		   SPI_MEM_OP_ADDR(dice ? addr_nbytes : 0, addr, 0),	\
 		   SPI_MEM_OP_NO_DUMMY,					\
 		   SPI_MEM_OP_NO_DATA)
 
@@ -293,9 +293,9 @@ struct spi_nor_erase_map {
  * @is_locked:	check if a region of the SPI NOR is completely locked
  */
 struct spi_nor_locking_ops {
-	int (*lock)(struct spi_nor *nor, loff_t ofs, uint64_t len);
-	int (*unlock)(struct spi_nor *nor, loff_t ofs, uint64_t len);
-	int (*is_locked)(struct spi_nor *nor, loff_t ofs, uint64_t len);
+	int (*lock)(struct spi_nor *nor, loff_t ofs, u64 len);
+	int (*unlock)(struct spi_nor *nor, loff_t ofs, u64 len);
+	int (*is_locked)(struct spi_nor *nor, loff_t ofs, u64 len);
 };
 
 /**
@@ -362,6 +362,7 @@ struct spi_nor_otp {
  *			command in octal DTR mode.
  * @n_banks:		number of banks.
  * @n_dice:		number of dice in the flash memory.
+ * @die_erase_opcode:	die erase opcode. Defaults to SPINOR_OP_CHIP_ERASE.
  * @vreg_offset:	volatile register offset for each die.
  * @hwcaps:		describes the read and page program hardware
  *			capabilities.
@@ -399,6 +400,7 @@ struct spi_nor_flash_parameter {
 	u8				rdsr_addr_nbytes;
 	u8				n_banks;
 	u8				n_dice;
+	u8				die_erase_opcode;
 	u32				*vreg_offset;
 
 	struct spi_nor_hwcaps		hwcaps;
@@ -463,7 +465,7 @@ struct spi_nor_id {
  * struct flash_info - SPI NOR flash_info entry.
  * @id:   pointer to struct spi_nor_id or NULL, which means "no ID" (mostly
  *        older chips).
- * @name: the name of the flash.
+ * @name: (obsolete) the name of the flash. Do not set it for new additions.
  * @size:           the size of the flash in bytes.
  * @sector_size:    (optional) the size listed here is what works with
  *                  SPINOR_OP_SE, which isn't necessarily called a "sector" by
@@ -487,7 +489,6 @@ struct spi_nor_id {
  *                            Usually these will power-up in a write-protected
  *                            state.
  *   SPI_NOR_NO_ERASE:        no erase command needed.
- *   NO_CHIP_ERASE:           chip does not support chip erase.
  *   SPI_NOR_NO_FR:           can't do fastread.
  *   SPI_NOR_QUAD_PP:         flash supports Quad Input Page Program.
  *   SPI_NOR_RWW:             flash supports reads while write.
@@ -537,10 +538,9 @@ struct flash_info {
 #define SPI_NOR_BP3_SR_BIT6		BIT(4)
 #define SPI_NOR_SWP_IS_VOLATILE		BIT(5)
 #define SPI_NOR_NO_ERASE		BIT(6)
-#define NO_CHIP_ERASE			BIT(7)
-#define SPI_NOR_NO_FR			BIT(8)
-#define SPI_NOR_QUAD_PP			BIT(9)
-#define SPI_NOR_RWW			BIT(10)
+#define SPI_NOR_NO_FR			BIT(7)
+#define SPI_NOR_QUAD_PP			BIT(8)
+#define SPI_NOR_RWW			BIT(9)
 
 	u8 no_sfdp_flags;
 #define SPI_NOR_SKIP_SFDP		BIT(0)
diff --git a/drivers/mtd/spi-nor/debugfs.c b/drivers/mtd/spi-nor/debugfs.c
index 6e163cb5b478..2dbda6b6938a 100644
--- a/drivers/mtd/spi-nor/debugfs.c
+++ b/drivers/mtd/spi-nor/debugfs.c
@@ -138,7 +138,7 @@ static int spi_nor_params_show(struct seq_file *s, void *data)
 
 	if (!(nor->flags & SNOR_F_NO_OP_CHIP_ERASE)) {
 		string_get_size(params->size, 1, STRING_UNITS_2, buf, sizeof(buf));
-		seq_printf(s, " %02x (%s)\n", SPINOR_OP_CHIP_ERASE, buf);
+		seq_printf(s, " %02x (%s)\n", nor->params->die_erase_opcode, buf);
 	}
 
 	seq_puts(s, "\nsector map\n");
diff --git a/drivers/mtd/spi-nor/micron-st.c b/drivers/mtd/spi-nor/micron-st.c
index 8920547c12bf..3c6499fdb712 100644
--- a/drivers/mtd/spi-nor/micron-st.c
+++ b/drivers/mtd/spi-nor/micron-st.c
@@ -11,6 +11,7 @@
 /* flash_info mfr_flag. Used to read proprietary FSR register. */
 #define USE_FSR		BIT(0)
 
+#define SPINOR_OP_MT_DIE_ERASE	0xc4	/* Chip (die) erase opcode */
 #define SPINOR_OP_RDFSR		0x70	/* Read flag status register */
 #define SPINOR_OP_CLFSR		0x50	/* Clear flag status register */
 #define SPINOR_OP_MT_DTR_RD	0xfd	/* Fast Read opcode in DTR mode */
@@ -192,6 +193,50 @@ static struct spi_nor_fixups mt25qu512a_fixups = {
 	.post_bfpt = mt25qu512a_post_bfpt_fixup,
 };
 
+static int st_nor_four_die_late_init(struct spi_nor *nor)
+{
+	struct spi_nor_flash_parameter *params = nor->params;
+
+	params->die_erase_opcode = SPINOR_OP_MT_DIE_ERASE;
+	params->n_dice = 4;
+
+	/*
+	 * Unfortunately the die erase opcode does not have a 4-byte opcode
+	 * correspondent for these flashes. The SFDP 4BAIT table fails to
+	 * consider the die erase too. We're forced to enter in the 4 byte
+	 * address mode in order to benefit of the die erase.
+	 */
+	return spi_nor_set_4byte_addr_mode(nor, true);
+}
+
+static int st_nor_two_die_late_init(struct spi_nor *nor)
+{
+	struct spi_nor_flash_parameter *params = nor->params;
+
+	params->die_erase_opcode = SPINOR_OP_MT_DIE_ERASE;
+	params->n_dice = 2;
+
+	/*
+	 * Unfortunately the die erase opcode does not have a 4-byte opcode
+	 * correspondent for these flashes. The SFDP 4BAIT table fails to
+	 * consider the die erase too. We're forced to enter in the 4 byte
+	 * address mode in order to benefit of the die erase.
+	 */
+	return spi_nor_set_4byte_addr_mode(nor, true);
+}
+
+static struct spi_nor_fixups n25q00_fixups = {
+	.late_init = st_nor_four_die_late_init,
+};
+
+static struct spi_nor_fixups mt25q01_fixups = {
+	.late_init = st_nor_two_die_late_init,
+};
+
+static struct spi_nor_fixups mt25q02_fixups = {
+	.late_init = st_nor_four_die_late_init,
+};
+
 static const struct flash_info st_nor_parts[] = {
 	{
 		.name = "m25p05-nonjedec",
@@ -366,16 +411,17 @@ static const struct flash_info st_nor_parts[] = {
 		.name = "n25q00",
 		.size = SZ_128M,
 		.flags = SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB | SPI_NOR_4BIT_BP |
-			 SPI_NOR_BP3_SR_BIT6 | NO_CHIP_ERASE,
+			 SPI_NOR_BP3_SR_BIT6,
 		.no_sfdp_flags = SECT_4K | SPI_NOR_QUAD_READ,
 		.mfr_flags = USE_FSR,
+		.fixups = &n25q00_fixups,
 	}, {
 		.id = SNOR_ID(0x20, 0xba, 0x22),
 		.name = "mt25ql02g",
 		.size = SZ_256M,
-		.flags = NO_CHIP_ERASE,
 		.no_sfdp_flags = SECT_4K | SPI_NOR_QUAD_READ,
 		.mfr_flags = USE_FSR,
+		.fixups = &mt25q02_fixups,
 	}, {
 		.id = SNOR_ID(0x20, 0xbb, 0x15),
 		.name = "n25q016a",
@@ -430,19 +476,24 @@ static const struct flash_info st_nor_parts[] = {
 		.no_sfdp_flags = SECT_4K | SPI_NOR_QUAD_READ,
 		.mfr_flags = USE_FSR,
 	}, {
+		.id = SNOR_ID(0x20, 0xbb, 0x21, 0x10, 0x44, 0x00),
+		.name = "mt25qu01g",
+		.mfr_flags = USE_FSR,
+		.fixups = &mt25q01_fixups,
+	}, {
 		.id = SNOR_ID(0x20, 0xbb, 0x21),
 		.name = "n25q00a",
 		.size = SZ_128M,
-		.flags = NO_CHIP_ERASE,
 		.no_sfdp_flags = SECT_4K | SPI_NOR_QUAD_READ,
 		.mfr_flags = USE_FSR,
+		.fixups = &n25q00_fixups,
 	}, {
 		.id = SNOR_ID(0x20, 0xbb, 0x22),
 		.name = "mt25qu02g",
 		.size = SZ_256M,
-		.flags = NO_CHIP_ERASE,
 		.no_sfdp_flags = SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ,
 		.mfr_flags = USE_FSR,
+		.fixups = &mt25q02_fixups,
 	}
 };
 
diff --git a/drivers/mtd/spi-nor/sfdp.c b/drivers/mtd/spi-nor/sfdp.c
index b3b11dfed789..57713de32832 100644
--- a/drivers/mtd/spi-nor/sfdp.c
+++ b/drivers/mtd/spi-nor/sfdp.c
@@ -446,6 +446,7 @@ static int spi_nor_parse_bfpt(struct spi_nor *nor,
 	u32 dword;
 	u16 half;
 	u8 erase_mask;
+	u8 wait_states, mode_clocks, opcode;
 
 	/* JESD216 Basic Flash Parameter Table length is at least 9 DWORDs. */
 	if (bfpt_header->length < BFPT_DWORD_MAX_JESD216)
@@ -631,6 +632,32 @@ static int spi_nor_parse_bfpt(struct spi_nor *nor,
 	if (bfpt_header->length == BFPT_DWORD_MAX_JESD216B)
 		return spi_nor_post_bfpt_fixups(nor, bfpt_header, &bfpt);
 
+	/* Parse 1-1-8 read instruction */
+	opcode = FIELD_GET(BFPT_DWORD17_RD_1_1_8_CMD, bfpt.dwords[SFDP_DWORD(17)]);
+	if (opcode) {
+		mode_clocks = FIELD_GET(BFPT_DWORD17_RD_1_1_8_MODE_CLOCKS,
+					bfpt.dwords[SFDP_DWORD(17)]);
+		wait_states = FIELD_GET(BFPT_DWORD17_RD_1_1_8_WAIT_STATES,
+					bfpt.dwords[SFDP_DWORD(17)]);
+		params->hwcaps.mask |= SNOR_HWCAPS_READ_1_1_8;
+		spi_nor_set_read_settings(&params->reads[SNOR_CMD_READ_1_1_8],
+					  mode_clocks, wait_states, opcode,
+					  SNOR_PROTO_1_1_8);
+	}
+
+	/* Parse 1-8-8 read instruction */
+	opcode = FIELD_GET(BFPT_DWORD17_RD_1_8_8_CMD, bfpt.dwords[SFDP_DWORD(17)]);
+	if (opcode) {
+		mode_clocks = FIELD_GET(BFPT_DWORD17_RD_1_8_8_MODE_CLOCKS,
+					bfpt.dwords[SFDP_DWORD(17)]);
+		wait_states = FIELD_GET(BFPT_DWORD17_RD_1_8_8_WAIT_STATES,
+					bfpt.dwords[SFDP_DWORD(17)]);
+		params->hwcaps.mask |= SNOR_HWCAPS_READ_1_8_8;
+		spi_nor_set_read_settings(&params->reads[SNOR_CMD_READ_1_8_8],
+					  mode_clocks, wait_states, opcode,
+					  SNOR_PROTO_1_8_8);
+	}
+
 	/* 8D-8D-8D command extension. */
 	switch (bfpt.dwords[SFDP_DWORD(18)] & BFPT_DWORD18_CMD_EXT_MASK) {
 	case BFPT_DWORD18_CMD_EXT_REP:
@@ -968,6 +995,8 @@ static int spi_nor_parse_4bait(struct spi_nor *nor,
 		{ SNOR_HWCAPS_READ_1_1_1_DTR,	BIT(13) },
 		{ SNOR_HWCAPS_READ_1_2_2_DTR,	BIT(14) },
 		{ SNOR_HWCAPS_READ_1_4_4_DTR,	BIT(15) },
+		{ SNOR_HWCAPS_READ_1_1_8,	BIT(20) },
+		{ SNOR_HWCAPS_READ_1_8_8,	BIT(21) },
 	};
 	static const struct sfdp_4bait programs[] = {
 		{ SNOR_HWCAPS_PP,		BIT(6) },
diff --git a/drivers/mtd/spi-nor/sfdp.h b/drivers/mtd/spi-nor/sfdp.h
index 6eb99e1cdd61..da0fe5aa9bb0 100644
--- a/drivers/mtd/spi-nor/sfdp.h
+++ b/drivers/mtd/spi-nor/sfdp.h
@@ -118,6 +118,13 @@ struct sfdp_bfpt {
 	(BFPT_DWORD16_EN4B_EN4B | BFPT_DWORD16_EX4B_EX4B)
 #define BFPT_DWORD16_SWRST_EN_RST		BIT(12)
 
+#define BFPT_DWORD17_RD_1_1_8_CMD		GENMASK(31, 24)
+#define BFPT_DWORD17_RD_1_1_8_MODE_CLOCKS	GENMASK(23, 21)
+#define BFPT_DWORD17_RD_1_1_8_WAIT_STATES	GENMASK(20, 16)
+#define BFPT_DWORD17_RD_1_8_8_CMD		GENMASK(15, 8)
+#define BFPT_DWORD17_RD_1_8_8_MODE_CLOCKS	GENMASK(7, 5)
+#define BFPT_DWORD17_RD_1_8_8_WAIT_STATES	GENMASK(4, 0)
+
 #define BFPT_DWORD18_CMD_EXT_MASK		GENMASK(30, 29)
 #define BFPT_DWORD18_CMD_EXT_REP		(0x0UL << 29) /* Repeat */
 #define BFPT_DWORD18_CMD_EXT_INV		(0x1UL << 29) /* Invert */
diff --git a/drivers/mtd/spi-nor/spansion.c b/drivers/mtd/spi-nor/spansion.c
index 12921344373d..6cc237c24e07 100644
--- a/drivers/mtd/spi-nor/spansion.c
+++ b/drivers/mtd/spi-nor/spansion.c
@@ -17,6 +17,7 @@
 
 #define SPINOR_OP_CLSR		0x30	/* Clear status register 1 */
 #define SPINOR_OP_CLPEF		0x82	/* Clear program/erase failure flags */
+#define SPINOR_OP_CYPRESS_DIE_ERASE		0x61	/* Chip (die) erase */
 #define SPINOR_OP_RD_ANY_REG			0x65	/* Read any register */
 #define SPINOR_OP_WR_ANY_REG			0x71	/* Write any register */
 #define SPINOR_REG_CYPRESS_VREG			0x00800000
@@ -644,6 +645,7 @@ static int s25hx_t_late_init(struct spi_nor *nor)
 	params->ready = cypress_nor_sr_ready_and_clear;
 	cypress_nor_ecc_init(nor);
 
+	params->die_erase_opcode = SPINOR_OP_CYPRESS_DIE_ERASE;
 	return 0;
 }
 
@@ -933,7 +935,6 @@ static const struct flash_info spansion_nor_parts[] = {
 		.id = SNOR_ID(0x34, 0x2a, 0x1c, 0x0f, 0x00, 0x90),
 		.name = "s25hl02gt",
 		.mfr_flags = USE_CLPEF,
-		.flags = NO_CHIP_ERASE,
 		.fixups = &s25hx_t_fixups
 	}, {
 		.id = SNOR_ID(0x34, 0x2b, 0x19, 0x0f, 0x08, 0x90),
@@ -954,7 +955,6 @@ static const struct flash_info spansion_nor_parts[] = {
 		.id = SNOR_ID(0x34, 0x2b, 0x1c, 0x0f, 0x00, 0x90),
 		.name = "s25hs02gt",
 		.mfr_flags = USE_CLPEF,
-		.flags = NO_CHIP_ERASE,
 		.fixups = &s25hx_t_fixups
 	}, {
 		.id = SNOR_ID(0x34, 0x5a, 0x1a),
diff --git a/drivers/mtd/spi-nor/sst.c b/drivers/mtd/spi-nor/sst.c
index 44d2a546bf17..180b7390690c 100644
--- a/drivers/mtd/spi-nor/sst.c
+++ b/drivers/mtd/spi-nor/sst.c
@@ -13,12 +13,12 @@
 
 #define SST26VF_CR_BPNV		BIT(3)
 
-static int sst26vf_nor_lock(struct spi_nor *nor, loff_t ofs, uint64_t len)
+static int sst26vf_nor_lock(struct spi_nor *nor, loff_t ofs, u64 len)
 {
 	return -EOPNOTSUPP;
 }
 
-static int sst26vf_nor_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len)
+static int sst26vf_nor_unlock(struct spi_nor *nor, loff_t ofs, u64 len)
 {
 	int ret;
 
@@ -38,7 +38,7 @@ static int sst26vf_nor_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 	return spi_nor_global_block_unlock(nor);
 }
 
-static int sst26vf_nor_is_locked(struct spi_nor *nor, loff_t ofs, uint64_t len)
+static int sst26vf_nor_is_locked(struct spi_nor *nor, loff_t ofs, u64 len)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/drivers/mtd/spi-nor/swp.c b/drivers/mtd/spi-nor/swp.c
index 585813310ee1..e48c3cff247a 100644
--- a/drivers/mtd/spi-nor/swp.c
+++ b/drivers/mtd/spi-nor/swp.c
@@ -53,7 +53,7 @@ static u64 spi_nor_get_min_prot_length_sr(struct spi_nor *nor)
 }
 
 static void spi_nor_get_locked_range_sr(struct spi_nor *nor, u8 sr, loff_t *ofs,
-					uint64_t *len)
+					u64 *len)
 {
 	struct mtd_info *mtd = &nor->mtd;
 	u64 min_prot_len;
@@ -90,10 +90,10 @@ static void spi_nor_get_locked_range_sr(struct spi_nor *nor, u8 sr, loff_t *ofs,
  * (if @locked is false); false otherwise.
  */
 static bool spi_nor_check_lock_status_sr(struct spi_nor *nor, loff_t ofs,
-					 uint64_t len, u8 sr, bool locked)
+					 u64 len, u8 sr, bool locked)
 {
 	loff_t lock_offs, lock_offs_max, offs_max;
-	uint64_t lock_len;
+	u64 lock_len;
 
 	if (!len)
 		return true;
@@ -111,14 +111,13 @@ static bool spi_nor_check_lock_status_sr(struct spi_nor *nor, loff_t ofs,
 		return (ofs >= lock_offs_max) || (offs_max <= lock_offs);
 }
 
-static bool spi_nor_is_locked_sr(struct spi_nor *nor, loff_t ofs, uint64_t len,
-				 u8 sr)
+static bool spi_nor_is_locked_sr(struct spi_nor *nor, loff_t ofs, u64 len, u8 sr)
 {
 	return spi_nor_check_lock_status_sr(nor, ofs, len, sr, true);
 }
 
-static bool spi_nor_is_unlocked_sr(struct spi_nor *nor, loff_t ofs,
-				   uint64_t len, u8 sr)
+static bool spi_nor_is_unlocked_sr(struct spi_nor *nor, loff_t ofs, u64 len,
+				   u8 sr)
 {
 	return spi_nor_check_lock_status_sr(nor, ofs, len, sr, false);
 }
@@ -156,7 +155,7 @@ static bool spi_nor_is_unlocked_sr(struct spi_nor *nor, loff_t ofs,
  *
  * Returns negative on errors, 0 on success.
  */
-static int spi_nor_sr_lock(struct spi_nor *nor, loff_t ofs, uint64_t len)
+static int spi_nor_sr_lock(struct spi_nor *nor, loff_t ofs, u64 len)
 {
 	struct mtd_info *mtd = &nor->mtd;
 	u64 min_prot_len;
@@ -246,7 +245,7 @@ static int spi_nor_sr_lock(struct spi_nor *nor, loff_t ofs, uint64_t len)
  *
  * Returns negative on errors, 0 on success.
  */
-static int spi_nor_sr_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len)
+static int spi_nor_sr_unlock(struct spi_nor *nor, loff_t ofs, u64 len)
 {
 	struct mtd_info *mtd = &nor->mtd;
 	u64 min_prot_len;
@@ -331,7 +330,7 @@ static int spi_nor_sr_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len)
  * Returns 1 if entire region is locked, 0 if any portion is unlocked, and
  * negative on errors.
  */
-static int spi_nor_sr_is_locked(struct spi_nor *nor, loff_t ofs, uint64_t len)
+static int spi_nor_sr_is_locked(struct spi_nor *nor, loff_t ofs, u64 len)
 {
 	int ret;
 
@@ -353,7 +352,7 @@ void spi_nor_init_default_locking_ops(struct spi_nor *nor)
 	nor->params->locking_ops = &spi_nor_sr_locking_ops;
 }
 
-static int spi_nor_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
+static int spi_nor_lock(struct mtd_info *mtd, loff_t ofs, u64 len)
 {
 	struct spi_nor *nor = mtd_to_spi_nor(mtd);
 	int ret;
@@ -368,7 +367,7 @@ static int spi_nor_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 	return ret;
 }
 
-static int spi_nor_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
+static int spi_nor_unlock(struct mtd_info *mtd, loff_t ofs, u64 len)
 {
 	struct spi_nor *nor = mtd_to_spi_nor(mtd);
 	int ret;
@@ -383,7 +382,7 @@ static int spi_nor_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 	return ret;
 }
 
-static int spi_nor_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len)
+static int spi_nor_is_locked(struct mtd_info *mtd, loff_t ofs, u64 len)
 {
 	struct spi_nor *nor = mtd_to_spi_nor(mtd);
 	int ret;
diff --git a/drivers/mtd/spi-nor/sysfs.c b/drivers/mtd/spi-nor/sysfs.c
index 2dfdc555a69f..96064e4babf0 100644
--- a/drivers/mtd/spi-nor/sysfs.c
+++ b/drivers/mtd/spi-nor/sysfs.c
@@ -78,6 +78,8 @@ static umode_t spi_nor_sysfs_is_visible(struct kobject *kobj,
 
 	if (attr == &dev_attr_manufacturer.attr && !nor->manufacturer)
 		return 0;
+	if (attr == &dev_attr_partname.attr && !nor->info->name)
+		return 0;
 	if (attr == &dev_attr_jedec_id.attr && !nor->info->id && !nor->id)
 		return 0;
 
diff --git a/drivers/mtd/ssfdc.c b/drivers/mtd/ssfdc.c
index 04da685c36be..211f279a33a9 100644
--- a/drivers/mtd/ssfdc.c
+++ b/drivers/mtd/ssfdc.c
@@ -18,7 +18,6 @@
 
 struct ssfdcr_record {
 	struct mtd_blktrans_dev mbd;
-	int usecount;
 	unsigned char heads;
 	unsigned char sectors;
 	unsigned short cylinders;
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index af0da4bb429b..8ca0bc223b30 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -434,6 +434,7 @@ config VIRTIO_NET
 	tristate "Virtio network driver"
 	depends on VIRTIO
 	select NET_FAILOVER
+	select DIMLIB
 	help
 	  This is the virtual network driver for virtio.  It can be used with
 	  QEMU based VMMs (like KVM or Xen).  Say Y or M.
diff --git a/drivers/net/arcnet/arcdevice.h b/drivers/net/arcnet/arcdevice.h
index 19e996a829c9..b54275389f8a 100644
--- a/drivers/net/arcnet/arcdevice.h
+++ b/drivers/net/arcnet/arcdevice.h
@@ -186,6 +186,8 @@ do {									\
 #define ARC_IS_5MBIT    1   /* card default speed is 5MBit */
 #define ARC_CAN_10MBIT  2   /* card uses COM20022, supporting 10MBit,
 				 but default is 2.5MBit. */
+#define ARC_HAS_LED     4   /* card has software controlled LEDs */
+#define ARC_HAS_ROTARY  8   /* card has rotary encoder */
 
 /* information needed to define an encapsulation driver */
 struct ArcProto {
diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c
index c580acb8b1d3..7b5c8bb02f11 100644
--- a/drivers/net/arcnet/com20020-pci.c
+++ b/drivers/net/arcnet/com20020-pci.c
@@ -213,12 +213,13 @@ static int com20020pci_probe(struct pci_dev *pdev,
 		if (!strncmp(ci->name, "EAE PLX-PCI FB2", 15))
 			lp->backplane = 1;
 
-		/* Get the dev_id from the PLX rotary coder */
-		if (!strncmp(ci->name, "EAE PLX-PCI MA1", 15))
-			dev_id_mask = 0x3;
-		dev->dev_id = (inb(priv->misc + ci->rotary) >> 4) & dev_id_mask;
-
-		snprintf(dev->name, sizeof(dev->name), "arc%d-%d", dev->dev_id, i);
+		if (ci->flags & ARC_HAS_ROTARY) {
+			/* Get the dev_id from the PLX rotary coder */
+			if (!strncmp(ci->name, "EAE PLX-PCI MA1", 15))
+				dev_id_mask = 0x3;
+			dev->dev_id = (inb(priv->misc + ci->rotary) >> 4) & dev_id_mask;
+			snprintf(dev->name, sizeof(dev->name), "arc%d-%d", dev->dev_id, i);
+		}
 
 		if (arcnet_inb(ioaddr, COM20020_REG_R_STATUS) == 0xFF) {
 			pr_err("IO address %Xh is empty!\n", ioaddr);
@@ -230,6 +231,10 @@ static int com20020pci_probe(struct pci_dev *pdev,
 			goto err_free_arcdev;
 		}
 
+		ret = com20020_found(dev, IRQF_SHARED);
+		if (ret)
+			goto err_free_arcdev;
+
 		card = devm_kzalloc(&pdev->dev, sizeof(struct com20020_dev),
 				    GFP_KERNEL);
 		if (!card) {
@@ -239,41 +244,39 @@ static int com20020pci_probe(struct pci_dev *pdev,
 
 		card->index = i;
 		card->pci_priv = priv;
-		card->tx_led.brightness_set = led_tx_set;
-		card->tx_led.default_trigger = devm_kasprintf(&pdev->dev,
-						GFP_KERNEL, "arc%d-%d-tx",
-						dev->dev_id, i);
-		card->tx_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
-						"pci:green:tx:%d-%d",
-						dev->dev_id, i);
-
-		card->tx_led.dev = &dev->dev;
-		card->recon_led.brightness_set = led_recon_set;
-		card->recon_led.default_trigger = devm_kasprintf(&pdev->dev,
-						GFP_KERNEL, "arc%d-%d-recon",
-						dev->dev_id, i);
-		card->recon_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
-						"pci:red:recon:%d-%d",
-						dev->dev_id, i);
-		card->recon_led.dev = &dev->dev;
-		card->dev = dev;
-
-		ret = devm_led_classdev_register(&pdev->dev, &card->tx_led);
-		if (ret)
-			goto err_free_arcdev;
 
-		ret = devm_led_classdev_register(&pdev->dev, &card->recon_led);
-		if (ret)
-			goto err_free_arcdev;
-
-		dev_set_drvdata(&dev->dev, card);
-
-		ret = com20020_found(dev, IRQF_SHARED);
-		if (ret)
-			goto err_free_arcdev;
-
-		devm_arcnet_led_init(dev, dev->dev_id, i);
+		if (ci->flags & ARC_HAS_LED) {
+			card->tx_led.brightness_set = led_tx_set;
+			card->tx_led.default_trigger = devm_kasprintf(&pdev->dev,
+							GFP_KERNEL, "arc%d-%d-tx",
+							dev->dev_id, i);
+			card->tx_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+							"pci:green:tx:%d-%d",
+							dev->dev_id, i);
+
+			card->tx_led.dev = &dev->dev;
+			card->recon_led.brightness_set = led_recon_set;
+			card->recon_led.default_trigger = devm_kasprintf(&pdev->dev,
+							GFP_KERNEL, "arc%d-%d-recon",
+							dev->dev_id, i);
+			card->recon_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+							"pci:red:recon:%d-%d",
+							dev->dev_id, i);
+			card->recon_led.dev = &dev->dev;
+
+			ret = devm_led_classdev_register(&pdev->dev, &card->tx_led);
+			if (ret)
+				goto err_free_arcdev;
+
+			ret = devm_led_classdev_register(&pdev->dev, &card->recon_led);
+			if (ret)
+				goto err_free_arcdev;
+
+			dev_set_drvdata(&dev->dev, card);
+			devm_arcnet_led_init(dev, dev->dev_id, i);
+		}
 
+		card->dev = dev;
 		list_add(&card->list, &priv->list_dev);
 		continue;
 
@@ -329,7 +332,7 @@ static struct com20020_pci_card_info card_info_5mbit = {
 };
 
 static struct com20020_pci_card_info card_info_sohard = {
-	.name = "PLX-PCI",
+	.name = "SOHARD SH ARC-PCI",
 	.devcount = 1,
 	/* SOHARD needs PCI base addr 4 */
 	.chan_map_tbl = {
@@ -364,7 +367,7 @@ static struct com20020_pci_card_info card_info_eae_arc1 = {
 		},
 	},
 	.rotary = 0x0,
-	.flags = ARC_CAN_10MBIT,
+	.flags = ARC_HAS_ROTARY | ARC_HAS_LED | ARC_CAN_10MBIT,
 };
 
 static struct com20020_pci_card_info card_info_eae_ma1 = {
@@ -396,7 +399,7 @@ static struct com20020_pci_card_info card_info_eae_ma1 = {
 		},
 	},
 	.rotary = 0x0,
-	.flags = ARC_CAN_10MBIT,
+	.flags = ARC_HAS_ROTARY | ARC_HAS_LED | ARC_CAN_10MBIT,
 };
 
 static struct com20020_pci_card_info card_info_eae_fb2 = {
@@ -421,7 +424,7 @@ static struct com20020_pci_card_info card_info_eae_fb2 = {
 		},
 	},
 	.rotary = 0x0,
-	.flags = ARC_CAN_10MBIT,
+	.flags = ARC_HAS_ROTARY | ARC_HAS_LED | ARC_CAN_10MBIT,
 };
 
 static const struct pci_device_id com20020pci_id_table[] = {
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index dc2c7b979656..7edf0fd58c34 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -985,7 +985,8 @@ static int alb_upper_dev_walk(struct net_device *upper,
 	if (netif_is_macvlan(upper) && !strict_match) {
 		tags = bond_verify_device_path(bond->dev, upper, 0);
 		if (IS_ERR_OR_NULL(tags))
-			BUG();
+			return -ENOMEM;
+
 		alb_send_lp_vid(slave, upper->dev_addr,
 				tags[0].vlan_proto, tags[0].vlan_id);
 		kfree(tags);
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 51d47eda1c87..4e0600c7b050 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1500,6 +1500,10 @@ done:
 static void bond_setup_by_slave(struct net_device *bond_dev,
 				struct net_device *slave_dev)
 {
+	bool was_up = !!(bond_dev->flags & IFF_UP);
+
+	dev_close(bond_dev);
+
 	bond_dev->header_ops	    = slave_dev->header_ops;
 
 	bond_dev->type		    = slave_dev->type;
@@ -1514,6 +1518,8 @@ static void bond_setup_by_slave(struct net_device *bond_dev,
 		bond_dev->flags &= ~(IFF_BROADCAST | IFF_MULTICAST);
 		bond_dev->flags |= (IFF_POINTOPOINT | IFF_NOARP);
 	}
+	if (was_up)
+		dev_open(bond_dev, NULL);
 }
 
 /* On bonding slaves other than the currently active slave, suppress
@@ -5749,10 +5755,8 @@ static int bond_ethtool_get_ts_info(struct net_device *bond_dev,
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct ethtool_ts_info ts_info;
-	const struct ethtool_ops *ops;
 	struct net_device *real_dev;
 	bool sw_tx_support = false;
-	struct phy_device *phydev;
 	struct list_head *iter;
 	struct slave *slave;
 	int ret = 0;
@@ -5763,29 +5767,12 @@ static int bond_ethtool_get_ts_info(struct net_device *bond_dev,
 	rcu_read_unlock();
 
 	if (real_dev) {
-		ops = real_dev->ethtool_ops;
-		phydev = real_dev->phydev;
-
-		if (phy_has_tsinfo(phydev)) {
-			ret = phy_ts_info(phydev, info);
-			goto out;
-		} else if (ops->get_ts_info) {
-			ret = ops->get_ts_info(real_dev, info);
-			goto out;
-		}
+		ret = ethtool_get_ts_info_by_layer(real_dev, info);
 	} else {
 		/* Check if all slaves support software tx timestamping */
 		rcu_read_lock();
 		bond_for_each_slave_rcu(bond, slave, iter) {
-			ret = -1;
-			ops = slave->dev->ethtool_ops;
-			phydev = slave->dev->phydev;
-
-			if (phy_has_tsinfo(phydev))
-				ret = phy_ts_info(phydev, &ts_info);
-			else if (ops->get_ts_info)
-				ret = ops->get_ts_info(slave->dev, &ts_info);
-
+			ret = ethtool_get_ts_info_by_layer(slave->dev, &ts_info);
 			if (!ret && (ts_info.so_timestamping & SOF_TIMESTAMPING_TX_SOFTWARE)) {
 				sw_tx_support = true;
 				continue;
@@ -5797,15 +5784,9 @@ static int bond_ethtool_get_ts_info(struct net_device *bond_dev,
 		rcu_read_unlock();
 	}
 
-	ret = 0;
-	info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
-				SOF_TIMESTAMPING_SOFTWARE;
 	if (sw_tx_support)
 		info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE;
 
-	info->phc_index = -1;
-
-out:
 	dev_put(real_dev);
 	return ret;
 }
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index cadee5505c29..4a52ccbe393f 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -621,8 +621,6 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds)
 		goto err_of_node_put;
 	}
 
-	priv->master_mii_dn = dn;
-
 	priv->user_mii_bus = mdiobus_alloc();
 	if (!priv->user_mii_bus) {
 		err = -ENOMEM;
@@ -635,7 +633,6 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds)
 	priv->user_mii_bus->write = bcm_sf2_sw_mdio_write;
 	snprintf(priv->user_mii_bus->id, MII_BUS_ID_SIZE, "sf2-%d",
 		 index++);
-	priv->user_mii_bus->dev.of_node = dn;
 
 	/* Include the pseudo-PHY address to divert reads towards our
 	 * workaround. This is only required for 7445D0, since 7445E0
@@ -683,9 +680,11 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds)
 	}
 
 	err = mdiobus_register(priv->user_mii_bus);
-	if (err && dn)
+	if (err)
 		goto err_free_user_mii_bus;
 
+	of_node_put(dn);
+
 	return 0;
 
 err_free_user_mii_bus:
diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h
index 424f896b5a6f..f95f4880b69e 100644
--- a/drivers/net/dsa/bcm_sf2.h
+++ b/drivers/net/dsa/bcm_sf2.h
@@ -107,7 +107,6 @@ struct bcm_sf2_priv {
 
 	/* Master and slave MDIO bus controller */
 	unsigned int			indir_phy_mask;
-	struct device_node		*master_mii_dn;
 	struct mii_bus			*user_mii_bus;
 	struct mii_bus			*master_mii_bus;
 
diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c
index 9c185c9f0963..de48b194048f 100644
--- a/drivers/net/dsa/lantiq_gswip.c
+++ b/drivers/net/dsa/lantiq_gswip.c
@@ -505,27 +505,34 @@ static int gswip_mdio_rd(struct mii_bus *bus, int addr, int reg)
 	return gswip_mdio_r(priv, GSWIP_MDIO_READ);
 }
 
-static int gswip_mdio(struct gswip_priv *priv, struct device_node *mdio_np)
+static int gswip_mdio(struct gswip_priv *priv)
 {
-	struct dsa_switch *ds = priv->ds;
-	int err;
+	struct device_node *mdio_np, *switch_np = priv->dev->of_node;
+	struct device *dev = priv->dev;
+	struct mii_bus *bus;
+	int err = 0;
 
-	ds->user_mii_bus = mdiobus_alloc();
-	if (!ds->user_mii_bus)
-		return -ENOMEM;
+	mdio_np = of_get_compatible_child(switch_np, "lantiq,xrx200-mdio");
+	if (!of_device_is_available(mdio_np))
+		goto out_put_node;
 
-	ds->user_mii_bus->priv = priv;
-	ds->user_mii_bus->read = gswip_mdio_rd;
-	ds->user_mii_bus->write = gswip_mdio_wr;
-	ds->user_mii_bus->name = "lantiq,xrx200-mdio";
-	snprintf(ds->user_mii_bus->id, MII_BUS_ID_SIZE, "%s-mii",
-		 dev_name(priv->dev));
-	ds->user_mii_bus->parent = priv->dev;
-	ds->user_mii_bus->phy_mask = ~ds->phys_mii_mask;
+	bus = devm_mdiobus_alloc(dev);
+	if (!bus) {
+		err = -ENOMEM;
+		goto out_put_node;
+	}
 
-	err = of_mdiobus_register(ds->user_mii_bus, mdio_np);
-	if (err)
-		mdiobus_free(ds->user_mii_bus);
+	bus->priv = priv;
+	bus->read = gswip_mdio_rd;
+	bus->write = gswip_mdio_wr;
+	bus->name = "lantiq,xrx200-mdio";
+	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(priv->dev));
+	bus->parent = priv->dev;
+
+	err = devm_of_mdiobus_register(dev, bus, mdio_np);
+
+out_put_node:
+	of_node_put(mdio_np);
 
 	return err;
 }
@@ -1759,7 +1766,7 @@ static void gswip_get_strings(struct dsa_switch *ds, int port, u32 stringset,
 		return;
 
 	for (i = 0; i < ARRAY_SIZE(gswip_rmon_cnt); i++)
-		ethtool_sprintf(&data, "%s", gswip_rmon_cnt[i].name);
+		ethtool_puts(&data, gswip_rmon_cnt[i].name);
 }
 
 static u32 gswip_bcm_ram_entry_read(struct gswip_priv *priv, u32 table,
@@ -2094,9 +2101,9 @@ remove_gphy:
 
 static int gswip_probe(struct platform_device *pdev)
 {
-	struct gswip_priv *priv;
-	struct device_node *np, *mdio_np, *gphy_fw_np;
+	struct device_node *np, *gphy_fw_np;
 	struct device *dev = &pdev->dev;
+	struct gswip_priv *priv;
 	int err;
 	int i;
 	u32 version;
@@ -2163,19 +2170,16 @@ static int gswip_probe(struct platform_device *pdev)
 	}
 
 	/* bring up the mdio bus */
-	mdio_np = of_get_compatible_child(dev->of_node, "lantiq,xrx200-mdio");
-	if (mdio_np) {
-		err = gswip_mdio(priv, mdio_np);
-		if (err) {
-			dev_err(dev, "mdio probe failed\n");
-			goto put_mdio_node;
-		}
+	err = gswip_mdio(priv);
+	if (err) {
+		dev_err(dev, "mdio probe failed\n");
+		goto gphy_fw_remove;
 	}
 
 	err = dsa_register_switch(priv->ds);
 	if (err) {
 		dev_err(dev, "dsa switch register failed: %i\n", err);
-		goto mdio_bus;
+		goto gphy_fw_remove;
 	}
 	if (!dsa_is_cpu_port(priv->ds, priv->hw_info->cpu_port)) {
 		dev_err(dev, "wrong CPU port defined, HW only supports port: %i",
@@ -2194,13 +2198,7 @@ static int gswip_probe(struct platform_device *pdev)
 disable_switch:
 	gswip_mdio_mask(priv, GSWIP_MDIO_GLOB_ENABLE, 0, GSWIP_MDIO_GLOB);
 	dsa_unregister_switch(priv->ds);
-mdio_bus:
-	if (mdio_np) {
-		mdiobus_unregister(priv->ds->user_mii_bus);
-		mdiobus_free(priv->ds->user_mii_bus);
-	}
-put_mdio_node:
-	of_node_put(mdio_np);
+gphy_fw_remove:
 	for (i = 0; i < priv->num_gphy_fw; i++)
 		gswip_gphy_fw_remove(priv, &priv->gphy_fw[i]);
 	return err;
@@ -2219,12 +2217,6 @@ static void gswip_remove(struct platform_device *pdev)
 
 	dsa_unregister_switch(priv->ds);
 
-	if (priv->ds->user_mii_bus) {
-		mdiobus_unregister(priv->ds->user_mii_bus);
-		of_node_put(priv->ds->user_mii_bus->dev.of_node);
-		mdiobus_free(priv->ds->user_mii_bus);
-	}
-
 	for (i = 0; i < priv->num_gphy_fw; i++)
 		gswip_gphy_fw_remove(priv, &priv->gphy_fw[i]);
 }
diff --git a/drivers/net/dsa/microchip/ksz8.h b/drivers/net/dsa/microchip/ksz8.h
index 4cea811e73ac..1a5225264e6a 100644
--- a/drivers/net/dsa/microchip/ksz8.h
+++ b/drivers/net/dsa/microchip/ksz8.h
@@ -56,5 +56,9 @@ int ksz8_reset_switch(struct ksz_device *dev);
 int ksz8_switch_init(struct ksz_device *dev);
 void ksz8_switch_exit(struct ksz_device *dev);
 int ksz8_change_mtu(struct ksz_device *dev, int port, int mtu);
+void ksz8_phylink_mac_link_up(struct ksz_device *dev, int port,
+			      unsigned int mode, phy_interface_t interface,
+			      struct phy_device *phydev, int speed, int duplex,
+			      bool tx_pause, bool rx_pause);
 
 #endif
diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c
index 4bf4d67557dc..61b71bcfe396 100644
--- a/drivers/net/dsa/microchip/ksz8795.c
+++ b/drivers/net/dsa/microchip/ksz8795.c
@@ -1358,6 +1358,9 @@ static void ksz8795_cpu_interface_select(struct ksz_device *dev, int port)
 {
 	struct ksz_port *p = &dev->ports[port];
 
+	if (!ksz_is_ksz87xx(dev))
+		return;
+
 	if (!p->interface && dev->compat_interface) {
 		dev_warn(dev->dev,
 			 "Using legacy switch \"phy-mode\" property, because it is missing on port %d node. "
@@ -1391,18 +1394,29 @@ void ksz8_port_setup(struct ksz_device *dev, int port, bool cpu_port)
 	/* enable 802.1p priority */
 	ksz_port_cfg(dev, port, P_PRIO_CTRL, PORT_802_1P_ENABLE, true);
 
-	if (cpu_port) {
-		if (!ksz_is_ksz88x3(dev))
-			ksz8795_cpu_interface_select(dev, port);
-
+	if (cpu_port)
 		member = dsa_user_ports(ds);
-	} else {
+	else
 		member = BIT(dsa_upstream_port(ds, port));
-	}
 
 	ksz8_cfg_port_member(dev, port, member);
 }
 
+static void ksz88x3_config_rmii_clk(struct ksz_device *dev)
+{
+	struct dsa_port *cpu_dp = dsa_to_port(dev->ds, dev->cpu_port);
+	bool rmii_clk_internal;
+
+	if (!ksz_is_ksz88x3(dev))
+		return;
+
+	rmii_clk_internal = of_property_read_bool(cpu_dp->dn,
+						  "microchip,rmii-clk-internal");
+
+	ksz_cfg(dev, KSZ88X3_REG_FVID_AND_HOST_MODE,
+		KSZ88X3_PORT3_RMII_CLK_INTERNAL, rmii_clk_internal);
+}
+
 void ksz8_config_cpu_port(struct dsa_switch *ds)
 {
 	struct ksz_device *dev = ds->priv;
@@ -1419,6 +1433,9 @@ void ksz8_config_cpu_port(struct dsa_switch *ds)
 
 	ksz8_port_setup(dev, dev->cpu_port, true);
 
+	ksz8795_cpu_interface_select(dev, dev->cpu_port);
+	ksz88x3_config_rmii_clk(dev);
+
 	for (i = 0; i < dev->phy_port_cnt; i++) {
 		ksz_port_stp_state_set(ds, i, BR_STATE_DISABLED);
 	}
@@ -1439,6 +1456,127 @@ void ksz8_config_cpu_port(struct dsa_switch *ds)
 	}
 }
 
+/**
+ * ksz8_phy_port_link_up - Configures ports with integrated PHYs
+ * @dev: The KSZ device instance.
+ * @port: The port number to configure.
+ * @duplex: The desired duplex mode.
+ * @tx_pause: If true, enables transmit pause.
+ * @rx_pause: If true, enables receive pause.
+ *
+ * Description:
+ * The function configures flow control settings for a given port based on the
+ * desired settings and current duplex mode.
+ *
+ * According to the KSZ8873 datasheet, the PORT_FORCE_FLOW_CTRL bit in the
+ * Port Control 2 register (0x1A for Port 1, 0x22 for Port 2, 0x32 for Port 3)
+ * determines how flow control is handled on the port:
+ *    "1 = will always enable full-duplex flow control on the port, regardless
+ *         of AN result.
+ *     0 = full-duplex flow control is enabled based on AN result."
+ *
+ * This means that the flow control behavior depends on the state of this bit:
+ * - If PORT_FORCE_FLOW_CTRL is set to 1, the switch will ignore AN results and
+ *   force flow control on the port.
+ * - If PORT_FORCE_FLOW_CTRL is set to 0, the switch will enable or disable
+ *   flow control based on the AN results.
+ *
+ * However, there is a potential limitation in this configuration. It is
+ * currently not possible to force disable flow control on a port if we still
+ * advertise pause support. While such a configuration is not currently
+ * supported by Linux, and may not make practical sense, it's important to be
+ * aware of this limitation when working with the KSZ8873 and similar devices.
+ */
+static void ksz8_phy_port_link_up(struct ksz_device *dev, int port, int duplex,
+				  bool tx_pause, bool rx_pause)
+{
+	const u16 *regs = dev->info->regs;
+	u8 sctrl = 0;
+
+	/* The KSZ8795 switch differs from the KSZ8873 by supporting
+	 * asymmetric pause control. However, since a single bit is used to
+	 * control both RX and TX pause, we can't enforce asymmetric pause
+	 * control - both TX and RX pause will be either enabled or disabled
+	 * together.
+	 *
+	 * If auto-negotiation is enabled, we usually allow the flow control to
+	 * be determined by the auto-negotiation process based on the
+	 * capabilities of both link partners. However, for KSZ8873, the
+	 * PORT_FORCE_FLOW_CTRL bit may be set by the hardware bootstrap,
+	 * ignoring the auto-negotiation result. Thus, even in auto-negotiation
+	 * mode, we need to ensure that the PORT_FORCE_FLOW_CTRL bit is
+	 * properly cleared.
+	 *
+	 * In the absence of pause auto-negotiation, we will enforce symmetric
+	 * pause control for both variants of switches - KSZ8873 and KSZ8795.
+	 *
+	 * Autoneg Pause Autoneg      rx,tx	PORT_FORCE_FLOW_CTRL
+	 * 1		1		x	0
+	 * 0		1		x	0 (flow control probably disabled)
+	 * x		0		1	1 (flow control force enabled)
+	 * 1		0		0	0 (flow control still depends on
+	 *					   aneg result due to hardware)
+	 * 0		0		0	0 (flow control probably disabled)
+	 */
+	if (dev->ports[port].manual_flow && tx_pause)
+		sctrl |= PORT_FORCE_FLOW_CTRL;
+
+	ksz_prmw8(dev, port, regs[P_STP_CTRL], PORT_FORCE_FLOW_CTRL, sctrl);
+}
+
+/**
+ * ksz8_cpu_port_link_up - Configures the CPU port of the switch.
+ * @dev: The KSZ device instance.
+ * @speed: The desired link speed.
+ * @duplex: The desired duplex mode.
+ * @tx_pause: If true, enables transmit pause.
+ * @rx_pause: If true, enables receive pause.
+ *
+ * Description:
+ * The function configures flow control and speed settings for the CPU
+ * port of the switch based on the desired settings, current duplex mode, and
+ * speed.
+ */
+static void ksz8_cpu_port_link_up(struct ksz_device *dev, int speed, int duplex,
+				  bool tx_pause, bool rx_pause)
+{
+	const u16 *regs = dev->info->regs;
+	u8 ctrl = 0;
+
+	/* SW_FLOW_CTRL, SW_HALF_DUPLEX, and SW_10_MBIT bits are bootstrappable
+	 * at least on KSZ8873. They can have different values depending on your
+	 * board setup.
+	 */
+	if (tx_pause || rx_pause)
+		ctrl |= SW_FLOW_CTRL;
+
+	if (duplex == DUPLEX_HALF)
+		ctrl |= SW_HALF_DUPLEX;
+
+	/* This hardware only supports SPEED_10 and SPEED_100. For SPEED_10
+	 * we need to set the SW_10_MBIT bit. Otherwise, we can leave it 0.
+	 */
+	if (speed == SPEED_10)
+		ctrl |= SW_10_MBIT;
+
+	ksz_rmw8(dev, regs[S_BROADCAST_CTRL], SW_HALF_DUPLEX | SW_FLOW_CTRL |
+		 SW_10_MBIT, ctrl);
+}
+
+void ksz8_phylink_mac_link_up(struct ksz_device *dev, int port,
+			      unsigned int mode, phy_interface_t interface,
+			      struct phy_device *phydev, int speed, int duplex,
+			      bool tx_pause, bool rx_pause)
+{
+	/* If the port is the CPU port, apply special handling. Only the CPU
+	 * port is configured via global registers.
+	 */
+	if (dev->cpu_port == port)
+		ksz8_cpu_port_link_up(dev, speed, duplex, tx_pause, rx_pause);
+	else if (dev->info->internal_phy[port])
+		ksz8_phy_port_link_up(dev, port, duplex, tx_pause, rx_pause);
+}
+
 static int ksz8_handle_global_errata(struct dsa_switch *ds)
 {
 	struct ksz_device *dev = ds->priv;
@@ -1487,8 +1625,6 @@ int ksz8_setup(struct dsa_switch *ds)
 	 */
 	ds->vlan_filtering_is_global = true;
 
-	ksz_cfg(dev, S_REPLACE_VID_CTRL, SW_FLOW_CTRL, true);
-
 	/* Enable automatic fast aging when link changed detected. */
 	ksz_cfg(dev, S_LINK_AGING_CTRL, SW_LINK_AUTO_AGING, true);
 
diff --git a/drivers/net/dsa/microchip/ksz8795_reg.h b/drivers/net/dsa/microchip/ksz8795_reg.h
index 3c9dae53e4d8..beca974e0171 100644
--- a/drivers/net/dsa/microchip/ksz8795_reg.h
+++ b/drivers/net/dsa/microchip/ksz8795_reg.h
@@ -22,6 +22,9 @@
 #define KSZ8863_GLOBAL_SOFTWARE_RESET	BIT(4)
 #define KSZ8863_PCS_RESET		BIT(0)
 
+#define KSZ88X3_REG_FVID_AND_HOST_MODE  0xC6
+#define KSZ88X3_PORT3_RMII_CLK_INTERNAL BIT(3)
+
 #define REG_SW_CTRL_0			0x02
 
 #define SW_NEW_BACKOFF			BIT(7)
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 3fed406fb46a..245dfb7a7a31 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -277,6 +277,7 @@ static const struct ksz_dev_ops ksz8_dev_ops = {
 	.mirror_add = ksz8_port_mirror_add,
 	.mirror_del = ksz8_port_mirror_del,
 	.get_caps = ksz8_get_caps,
+	.phylink_mac_link_up = ksz8_phylink_mac_link_up,
 	.config_cpu_port = ksz8_config_cpu_port,
 	.enable_stp_addr = ksz8_enable_stp_addr,
 	.reset = ksz8_reset_switch,
@@ -1672,15 +1673,23 @@ static const struct ksz_chip_data *ksz_lookup_info(unsigned int prod_num)
 
 static int ksz_check_device_id(struct ksz_device *dev)
 {
-	const struct ksz_chip_data *dt_chip_data;
+	const struct ksz_chip_data *expected_chip_data;
+	u32 expected_chip_id;
 
-	dt_chip_data = of_device_get_match_data(dev->dev);
+	if (dev->pdata) {
+		expected_chip_id = dev->pdata->chip_id;
+		expected_chip_data = ksz_lookup_info(expected_chip_id);
+		if (WARN_ON(!expected_chip_data))
+			return -ENODEV;
+	} else {
+		expected_chip_data = of_device_get_match_data(dev->dev);
+		expected_chip_id = expected_chip_data->chip_id;
+	}
 
-	/* Check for Device Tree and Chip ID */
-	if (dt_chip_data->chip_id != dev->chip_id) {
+	if (expected_chip_id != dev->chip_id) {
 		dev_err(dev->dev,
 			"Device tree specifies chip %s but found %s, please fix it!\n",
-			dt_chip_data->dev_name, dev->info->dev_name);
+			expected_chip_data->dev_name, dev->info->dev_name);
 		return -ENODEV;
 	}
 
@@ -2703,7 +2712,7 @@ static enum dsa_tag_protocol ksz_get_tag_protocol(struct dsa_switch *ds,
 		proto = DSA_TAG_PROTO_KSZ9477;
 
 	if (is_lan937x(dev))
-		proto = DSA_TAG_PROTO_LAN937X_VALUE;
+		proto = DSA_TAG_PROTO_LAN937X;
 
 	return proto;
 }
@@ -2713,10 +2722,18 @@ static int ksz_connect_tag_protocol(struct dsa_switch *ds,
 {
 	struct ksz_tagger_data *tagger_data;
 
-	tagger_data = ksz_tagger_data(ds);
-	tagger_data->xmit_work_fn = ksz_port_deferred_xmit;
-
-	return 0;
+	switch (proto) {
+	case DSA_TAG_PROTO_KSZ8795:
+		return 0;
+	case DSA_TAG_PROTO_KSZ9893:
+	case DSA_TAG_PROTO_KSZ9477:
+	case DSA_TAG_PROTO_LAN937X:
+		tagger_data = ksz_tagger_data(ds);
+		tagger_data->xmit_work_fn = ksz_port_deferred_xmit;
+		return 0;
+	default:
+		return -EPROTONOSUPPORT;
+	}
 }
 
 static int ksz_port_vlan_filtering(struct dsa_switch *ds, int port,
@@ -2966,8 +2983,10 @@ static void ksz_phylink_mac_config(struct dsa_switch *ds, int port,
 {
 	struct ksz_device *dev = ds->priv;
 
-	if (ksz_is_ksz88x3(dev))
+	if (ksz_is_ksz88x3(dev)) {
+		dev->ports[port].manual_flow = !(state->pause & MLO_PAUSE_AN);
 		return;
+	}
 
 	/* Internal PHYs */
 	if (dev->info->internal_phy[port])
@@ -3110,10 +3129,8 @@ static void ksz_phylink_mac_link_up(struct dsa_switch *ds, int port,
 {
 	struct ksz_device *dev = ds->priv;
 
-	if (dev->dev_ops->phylink_mac_link_up)
-		dev->dev_ops->phylink_mac_link_up(dev, port, mode, interface,
-						  phydev, speed, duplex,
-						  tx_pause, rx_pause);
+	dev->dev_ops->phylink_mac_link_up(dev, port, mode, interface, phydev,
+					  speed, duplex, tx_pause, rx_pause);
 }
 
 static int ksz_switch_detect(struct ksz_device *dev)
@@ -4155,9 +4172,6 @@ int ksz_switch_register(struct ksz_device *dev)
 	int ret;
 	int i;
 
-	if (dev->pdata)
-		dev->chip_id = dev->pdata->chip_id;
-
 	dev->reset_gpio = devm_gpiod_get_optional(dev->dev, "reset",
 						  GPIOD_OUT_LOW);
 	if (IS_ERR(dev->reset_gpio))
diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h
index b7e8a403a132..15612101a155 100644
--- a/drivers/net/dsa/microchip/ksz_common.h
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -14,6 +14,7 @@
 #include <linux/regmap.h>
 #include <net/dsa.h>
 #include <linux/irq.h>
+#include <linux/platform_data/microchip-ksz.h>
 
 #include "ksz_ptp.h"
 
@@ -134,6 +135,7 @@ struct ksz_port {
 	ktime_t tstamp_msg;
 	struct completion tstamp_msg_comp;
 #endif
+	bool manual_flow;
 };
 
 struct ksz_device {
@@ -202,25 +204,6 @@ enum ksz_model {
 	LAN9374,
 };
 
-enum ksz_chip_id {
-	KSZ8563_CHIP_ID = 0x8563,
-	KSZ8795_CHIP_ID = 0x8795,
-	KSZ8794_CHIP_ID = 0x8794,
-	KSZ8765_CHIP_ID = 0x8765,
-	KSZ8830_CHIP_ID = 0x8830,
-	KSZ9477_CHIP_ID = 0x00947700,
-	KSZ9896_CHIP_ID = 0x00989600,
-	KSZ9897_CHIP_ID = 0x00989700,
-	KSZ9893_CHIP_ID = 0x00989300,
-	KSZ9563_CHIP_ID = 0x00956300,
-	KSZ9567_CHIP_ID = 0x00956700,
-	LAN9370_CHIP_ID = 0x00937000,
-	LAN9371_CHIP_ID = 0x00937100,
-	LAN9372_CHIP_ID = 0x00937200,
-	LAN9373_CHIP_ID = 0x00937300,
-	LAN9374_CHIP_ID = 0x00937400,
-};
-
 enum ksz_regs {
 	REG_SW_MAC_ADDR,
 	REG_IND_CTRL_0,
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index d27c6b70a2f6..391c4dbdff42 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -836,7 +836,7 @@ mt7530_get_strings(struct dsa_switch *ds, int port, u32 stringset,
 		return;
 
 	for (i = 0; i < ARRAY_SIZE(mt7530_mib); i++)
-		ethtool_sprintf(&data, "%s", mt7530_mib[i].name);
+		ethtool_puts(&data, mt7530_mib[i].name);
 }
 
 static void
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 42b1acaca33a..383b3c4d6f59 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -577,6 +577,18 @@ static void mv88e6250_phylink_get_caps(struct mv88e6xxx_chip *chip, int port,
 	config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100;
 }
 
+static void mv88e6351_phylink_get_caps(struct mv88e6xxx_chip *chip, int port,
+				       struct phylink_config *config)
+{
+	unsigned long *supported = config->supported_interfaces;
+
+	/* Translate the default cmode */
+	mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported);
+
+	config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 |
+				   MAC_1000FD;
+}
+
 static int mv88e6352_get_port4_serdes_cmode(struct mv88e6xxx_chip *chip)
 {
 	u16 reg, val;
@@ -931,76 +943,94 @@ error:
 
 static int mv88e6xxx_stats_snapshot(struct mv88e6xxx_chip *chip, int port)
 {
+	int err;
+
 	if (!chip->info->ops->stats_snapshot)
 		return -EOPNOTSUPP;
 
-	return chip->info->ops->stats_snapshot(chip, port);
-}
-
-static struct mv88e6xxx_hw_stat mv88e6xxx_hw_stats[] = {
-	{ "in_good_octets",		8, 0x00, STATS_TYPE_BANK0, },
-	{ "in_bad_octets",		4, 0x02, STATS_TYPE_BANK0, },
-	{ "in_unicast",			4, 0x04, STATS_TYPE_BANK0, },
-	{ "in_broadcasts",		4, 0x06, STATS_TYPE_BANK0, },
-	{ "in_multicasts",		4, 0x07, STATS_TYPE_BANK0, },
-	{ "in_pause",			4, 0x16, STATS_TYPE_BANK0, },
-	{ "in_undersize",		4, 0x18, STATS_TYPE_BANK0, },
-	{ "in_fragments",		4, 0x19, STATS_TYPE_BANK0, },
-	{ "in_oversize",		4, 0x1a, STATS_TYPE_BANK0, },
-	{ "in_jabber",			4, 0x1b, STATS_TYPE_BANK0, },
-	{ "in_rx_error",		4, 0x1c, STATS_TYPE_BANK0, },
-	{ "in_fcs_error",		4, 0x1d, STATS_TYPE_BANK0, },
-	{ "out_octets",			8, 0x0e, STATS_TYPE_BANK0, },
-	{ "out_unicast",		4, 0x10, STATS_TYPE_BANK0, },
-	{ "out_broadcasts",		4, 0x13, STATS_TYPE_BANK0, },
-	{ "out_multicasts",		4, 0x12, STATS_TYPE_BANK0, },
-	{ "out_pause",			4, 0x15, STATS_TYPE_BANK0, },
-	{ "excessive",			4, 0x11, STATS_TYPE_BANK0, },
-	{ "collisions",			4, 0x1e, STATS_TYPE_BANK0, },
-	{ "deferred",			4, 0x05, STATS_TYPE_BANK0, },
-	{ "single",			4, 0x14, STATS_TYPE_BANK0, },
-	{ "multiple",			4, 0x17, STATS_TYPE_BANK0, },
-	{ "out_fcs_error",		4, 0x03, STATS_TYPE_BANK0, },
-	{ "late",			4, 0x1f, STATS_TYPE_BANK0, },
-	{ "hist_64bytes",		4, 0x08, STATS_TYPE_BANK0, },
-	{ "hist_65_127bytes",		4, 0x09, STATS_TYPE_BANK0, },
-	{ "hist_128_255bytes",		4, 0x0a, STATS_TYPE_BANK0, },
-	{ "hist_256_511bytes",		4, 0x0b, STATS_TYPE_BANK0, },
-	{ "hist_512_1023bytes",		4, 0x0c, STATS_TYPE_BANK0, },
-	{ "hist_1024_max_bytes",	4, 0x0d, STATS_TYPE_BANK0, },
-	{ "sw_in_discards",		4, 0x10, STATS_TYPE_PORT, },
-	{ "sw_in_filtered",		2, 0x12, STATS_TYPE_PORT, },
-	{ "sw_out_filtered",		2, 0x13, STATS_TYPE_PORT, },
-	{ "in_discards",		4, 0x00, STATS_TYPE_BANK1, },
-	{ "in_filtered",		4, 0x01, STATS_TYPE_BANK1, },
-	{ "in_accepted",		4, 0x02, STATS_TYPE_BANK1, },
-	{ "in_bad_accepted",		4, 0x03, STATS_TYPE_BANK1, },
-	{ "in_good_avb_class_a",	4, 0x04, STATS_TYPE_BANK1, },
-	{ "in_good_avb_class_b",	4, 0x05, STATS_TYPE_BANK1, },
-	{ "in_bad_avb_class_a",		4, 0x06, STATS_TYPE_BANK1, },
-	{ "in_bad_avb_class_b",		4, 0x07, STATS_TYPE_BANK1, },
-	{ "tcam_counter_0",		4, 0x08, STATS_TYPE_BANK1, },
-	{ "tcam_counter_1",		4, 0x09, STATS_TYPE_BANK1, },
-	{ "tcam_counter_2",		4, 0x0a, STATS_TYPE_BANK1, },
-	{ "tcam_counter_3",		4, 0x0b, STATS_TYPE_BANK1, },
-	{ "in_da_unknown",		4, 0x0e, STATS_TYPE_BANK1, },
-	{ "in_management",		4, 0x0f, STATS_TYPE_BANK1, },
-	{ "out_queue_0",		4, 0x10, STATS_TYPE_BANK1, },
-	{ "out_queue_1",		4, 0x11, STATS_TYPE_BANK1, },
-	{ "out_queue_2",		4, 0x12, STATS_TYPE_BANK1, },
-	{ "out_queue_3",		4, 0x13, STATS_TYPE_BANK1, },
-	{ "out_queue_4",		4, 0x14, STATS_TYPE_BANK1, },
-	{ "out_queue_5",		4, 0x15, STATS_TYPE_BANK1, },
-	{ "out_queue_6",		4, 0x16, STATS_TYPE_BANK1, },
-	{ "out_queue_7",		4, 0x17, STATS_TYPE_BANK1, },
-	{ "out_cut_through",		4, 0x18, STATS_TYPE_BANK1, },
-	{ "out_octets_a",		4, 0x1a, STATS_TYPE_BANK1, },
-	{ "out_octets_b",		4, 0x1b, STATS_TYPE_BANK1, },
-	{ "out_management",		4, 0x1f, STATS_TYPE_BANK1, },
+	mv88e6xxx_reg_lock(chip);
+	err = chip->info->ops->stats_snapshot(chip, port);
+	mv88e6xxx_reg_unlock(chip);
+
+	return err;
+}
+
+#define MV88E6XXX_HW_STAT_MAPPER(_fn)				    \
+	_fn(in_good_octets,		8, 0x00, STATS_TYPE_BANK0), \
+	_fn(in_bad_octets,		4, 0x02, STATS_TYPE_BANK0), \
+	_fn(in_unicast,			4, 0x04, STATS_TYPE_BANK0), \
+	_fn(in_broadcasts,		4, 0x06, STATS_TYPE_BANK0), \
+	_fn(in_multicasts,		4, 0x07, STATS_TYPE_BANK0), \
+	_fn(in_pause,			4, 0x16, STATS_TYPE_BANK0), \
+	_fn(in_undersize,		4, 0x18, STATS_TYPE_BANK0), \
+	_fn(in_fragments,		4, 0x19, STATS_TYPE_BANK0), \
+	_fn(in_oversize,		4, 0x1a, STATS_TYPE_BANK0), \
+	_fn(in_jabber,			4, 0x1b, STATS_TYPE_BANK0), \
+	_fn(in_rx_error,		4, 0x1c, STATS_TYPE_BANK0), \
+	_fn(in_fcs_error,		4, 0x1d, STATS_TYPE_BANK0), \
+	_fn(out_octets,			8, 0x0e, STATS_TYPE_BANK0), \
+	_fn(out_unicast,		4, 0x10, STATS_TYPE_BANK0), \
+	_fn(out_broadcasts,		4, 0x13, STATS_TYPE_BANK0), \
+	_fn(out_multicasts,		4, 0x12, STATS_TYPE_BANK0), \
+	_fn(out_pause,			4, 0x15, STATS_TYPE_BANK0), \
+	_fn(excessive,			4, 0x11, STATS_TYPE_BANK0), \
+	_fn(collisions,			4, 0x1e, STATS_TYPE_BANK0), \
+	_fn(deferred,			4, 0x05, STATS_TYPE_BANK0), \
+	_fn(single,			4, 0x14, STATS_TYPE_BANK0), \
+	_fn(multiple,			4, 0x17, STATS_TYPE_BANK0), \
+	_fn(out_fcs_error,		4, 0x03, STATS_TYPE_BANK0), \
+	_fn(late,			4, 0x1f, STATS_TYPE_BANK0), \
+	_fn(hist_64bytes,		4, 0x08, STATS_TYPE_BANK0), \
+	_fn(hist_65_127bytes,		4, 0x09, STATS_TYPE_BANK0), \
+	_fn(hist_128_255bytes,		4, 0x0a, STATS_TYPE_BANK0), \
+	_fn(hist_256_511bytes,		4, 0x0b, STATS_TYPE_BANK0), \
+	_fn(hist_512_1023bytes,		4, 0x0c, STATS_TYPE_BANK0), \
+	_fn(hist_1024_max_bytes,	4, 0x0d, STATS_TYPE_BANK0), \
+	_fn(sw_in_discards,		4, 0x10, STATS_TYPE_PORT), \
+	_fn(sw_in_filtered,		2, 0x12, STATS_TYPE_PORT), \
+	_fn(sw_out_filtered,		2, 0x13, STATS_TYPE_PORT), \
+	_fn(in_discards,		4, 0x00, STATS_TYPE_BANK1), \
+	_fn(in_filtered,		4, 0x01, STATS_TYPE_BANK1), \
+	_fn(in_accepted,		4, 0x02, STATS_TYPE_BANK1), \
+	_fn(in_bad_accepted,		4, 0x03, STATS_TYPE_BANK1), \
+	_fn(in_good_avb_class_a,	4, 0x04, STATS_TYPE_BANK1), \
+	_fn(in_good_avb_class_b,	4, 0x05, STATS_TYPE_BANK1), \
+	_fn(in_bad_avb_class_a,		4, 0x06, STATS_TYPE_BANK1), \
+	_fn(in_bad_avb_class_b,		4, 0x07, STATS_TYPE_BANK1), \
+	_fn(tcam_counter_0,		4, 0x08, STATS_TYPE_BANK1), \
+	_fn(tcam_counter_1,		4, 0x09, STATS_TYPE_BANK1), \
+	_fn(tcam_counter_2,		4, 0x0a, STATS_TYPE_BANK1), \
+	_fn(tcam_counter_3,		4, 0x0b, STATS_TYPE_BANK1), \
+	_fn(in_da_unknown,		4, 0x0e, STATS_TYPE_BANK1), \
+	_fn(in_management,		4, 0x0f, STATS_TYPE_BANK1), \
+	_fn(out_queue_0,		4, 0x10, STATS_TYPE_BANK1), \
+	_fn(out_queue_1,		4, 0x11, STATS_TYPE_BANK1), \
+	_fn(out_queue_2,		4, 0x12, STATS_TYPE_BANK1), \
+	_fn(out_queue_3,		4, 0x13, STATS_TYPE_BANK1), \
+	_fn(out_queue_4,		4, 0x14, STATS_TYPE_BANK1), \
+	_fn(out_queue_5,		4, 0x15, STATS_TYPE_BANK1), \
+	_fn(out_queue_6,		4, 0x16, STATS_TYPE_BANK1), \
+	_fn(out_queue_7,		4, 0x17, STATS_TYPE_BANK1), \
+	_fn(out_cut_through,		4, 0x18, STATS_TYPE_BANK1), \
+	_fn(out_octets_a,		4, 0x1a, STATS_TYPE_BANK1), \
+	_fn(out_octets_b,		4, 0x1b, STATS_TYPE_BANK1), \
+	_fn(out_management,		4, 0x1f, STATS_TYPE_BANK1), \
+	/*  */
+
+#define MV88E6XXX_HW_STAT_ENTRY(_string, _size, _reg, _type) \
+	{ #_string, _size, _reg, _type }
+static const struct mv88e6xxx_hw_stat mv88e6xxx_hw_stats[] = {
+	MV88E6XXX_HW_STAT_MAPPER(MV88E6XXX_HW_STAT_ENTRY)
+};
+
+#define MV88E6XXX_HW_STAT_ENUM(_string, _size, _reg, _type) \
+	MV88E6XXX_HW_STAT_ID_ ## _string
+enum mv88e6xxx_hw_stat_id {
+	MV88E6XXX_HW_STAT_MAPPER(MV88E6XXX_HW_STAT_ENUM)
 };
 
 static uint64_t _mv88e6xxx_get_ethtool_stat(struct mv88e6xxx_chip *chip,
-					    struct mv88e6xxx_hw_stat *s,
+					    const struct mv88e6xxx_hw_stat *s,
 					    int port, u16 bank1_select,
 					    u16 histogram)
 {
@@ -1043,7 +1073,7 @@ static uint64_t _mv88e6xxx_get_ethtool_stat(struct mv88e6xxx_chip *chip,
 static int mv88e6xxx_stats_get_strings(struct mv88e6xxx_chip *chip,
 				       uint8_t *data, int types)
 {
-	struct mv88e6xxx_hw_stat *stat;
+	const struct mv88e6xxx_hw_stat *stat;
 	int i, j;
 
 	for (i = 0, j = 0; i < ARRAY_SIZE(mv88e6xxx_hw_stats); i++) {
@@ -1124,7 +1154,7 @@ static void mv88e6xxx_get_strings(struct dsa_switch *ds, int port,
 static int mv88e6xxx_stats_get_sset_count(struct mv88e6xxx_chip *chip,
 					  int types)
 {
-	struct mv88e6xxx_hw_stat *stat;
+	const struct mv88e6xxx_hw_stat *stat;
 	int i, j;
 
 	for (i = 0, j = 0; i < ARRAY_SIZE(mv88e6xxx_hw_stats); i++) {
@@ -1183,59 +1213,82 @@ out:
 	return count;
 }
 
-static int mv88e6xxx_stats_get_stats(struct mv88e6xxx_chip *chip, int port,
-				     uint64_t *data, int types,
-				     u16 bank1_select, u16 histogram)
+static size_t mv88e6095_stats_get_stat(struct mv88e6xxx_chip *chip, int port,
+				       const struct mv88e6xxx_hw_stat *stat,
+				       uint64_t *data)
 {
-	struct mv88e6xxx_hw_stat *stat;
-	int i, j;
+	if (!(stat->type & (STATS_TYPE_BANK0 | STATS_TYPE_PORT)))
+		return 0;
 
-	for (i = 0, j = 0; i < ARRAY_SIZE(mv88e6xxx_hw_stats); i++) {
-		stat = &mv88e6xxx_hw_stats[i];
-		if (stat->type & types) {
-			mv88e6xxx_reg_lock(chip);
-			data[j] = _mv88e6xxx_get_ethtool_stat(chip, stat, port,
-							      bank1_select,
-							      histogram);
-			mv88e6xxx_reg_unlock(chip);
+	*data = _mv88e6xxx_get_ethtool_stat(chip, stat, port, 0,
+					    MV88E6XXX_G1_STATS_OP_HIST_RX);
+	return 1;
+}
 
-			j++;
-		}
-	}
-	return j;
+static size_t mv88e6250_stats_get_stat(struct mv88e6xxx_chip *chip, int port,
+				       const struct mv88e6xxx_hw_stat *stat,
+				       uint64_t *data)
+{
+	if (!(stat->type & STATS_TYPE_BANK0))
+		return 0;
+
+	*data = _mv88e6xxx_get_ethtool_stat(chip, stat, port, 0,
+					    MV88E6XXX_G1_STATS_OP_HIST_RX);
+	return 1;
 }
 
-static int mv88e6095_stats_get_stats(struct mv88e6xxx_chip *chip, int port,
-				     uint64_t *data)
+static size_t mv88e6320_stats_get_stat(struct mv88e6xxx_chip *chip, int port,
+				       const struct mv88e6xxx_hw_stat *stat,
+				       uint64_t *data)
 {
-	return mv88e6xxx_stats_get_stats(chip, port, data,
-					 STATS_TYPE_BANK0 | STATS_TYPE_PORT,
-					 0, MV88E6XXX_G1_STATS_OP_HIST_RX_TX);
+	if (!(stat->type & (STATS_TYPE_BANK0 | STATS_TYPE_BANK1)))
+		return 0;
+
+	*data = _mv88e6xxx_get_ethtool_stat(chip, stat, port,
+					    MV88E6XXX_G1_STATS_OP_BANK_1_BIT_9,
+					    MV88E6XXX_G1_STATS_OP_HIST_RX);
+	return 1;
 }
 
-static int mv88e6250_stats_get_stats(struct mv88e6xxx_chip *chip, int port,
-				     uint64_t *data)
+static size_t mv88e6390_stats_get_stat(struct mv88e6xxx_chip *chip, int port,
+				       const struct mv88e6xxx_hw_stat *stat,
+				       uint64_t *data)
 {
-	return mv88e6xxx_stats_get_stats(chip, port, data, STATS_TYPE_BANK0,
-					 0, MV88E6XXX_G1_STATS_OP_HIST_RX_TX);
+	if (!(stat->type & (STATS_TYPE_BANK0 | STATS_TYPE_BANK1)))
+		return 0;
+
+	*data = _mv88e6xxx_get_ethtool_stat(chip, stat, port,
+					    MV88E6XXX_G1_STATS_OP_BANK_1_BIT_10,
+					    0);
+	return 1;
 }
 
-static int mv88e6320_stats_get_stats(struct mv88e6xxx_chip *chip, int port,
-				     uint64_t *data)
+static size_t mv88e6xxx_stats_get_stat(struct mv88e6xxx_chip *chip, int port,
+				       const struct mv88e6xxx_hw_stat *stat,
+				       uint64_t *data)
 {
-	return mv88e6xxx_stats_get_stats(chip, port, data,
-					 STATS_TYPE_BANK0 | STATS_TYPE_BANK1,
-					 MV88E6XXX_G1_STATS_OP_BANK_1_BIT_9,
-					 MV88E6XXX_G1_STATS_OP_HIST_RX_TX);
+	int ret = 0;
+
+	if (chip->info->ops->stats_get_stat) {
+		mv88e6xxx_reg_lock(chip);
+		ret = chip->info->ops->stats_get_stat(chip, port, stat, data);
+		mv88e6xxx_reg_unlock(chip);
+	}
+
+	return ret;
 }
 
-static int mv88e6390_stats_get_stats(struct mv88e6xxx_chip *chip, int port,
-				     uint64_t *data)
+static size_t mv88e6xxx_stats_get_stats(struct mv88e6xxx_chip *chip, int port,
+					uint64_t *data)
 {
-	return mv88e6xxx_stats_get_stats(chip, port, data,
-					 STATS_TYPE_BANK0 | STATS_TYPE_BANK1,
-					 MV88E6XXX_G1_STATS_OP_BANK_1_BIT_10,
-					 0);
+	const struct mv88e6xxx_hw_stat *stat;
+	size_t i, j;
+
+	for (i = 0, j = 0; i < ARRAY_SIZE(mv88e6xxx_hw_stats); i++) {
+		stat = &mv88e6xxx_hw_stats[i];
+		j += mv88e6xxx_stats_get_stat(chip, port, stat, &data[j]);
+	}
+	return j;
 }
 
 static void mv88e6xxx_atu_vtu_get_stats(struct mv88e6xxx_chip *chip, int port,
@@ -1251,10 +1304,9 @@ static void mv88e6xxx_atu_vtu_get_stats(struct mv88e6xxx_chip *chip, int port,
 static void mv88e6xxx_get_stats(struct mv88e6xxx_chip *chip, int port,
 				uint64_t *data)
 {
-	int count = 0;
+	size_t count;
 
-	if (chip->info->ops->stats_get_stats)
-		count = chip->info->ops->stats_get_stats(chip, port, data);
+	count = mv88e6xxx_stats_get_stats(chip, port, data);
 
 	mv88e6xxx_reg_lock(chip);
 	if (chip->info->ops->serdes_get_stats) {
@@ -1272,16 +1324,90 @@ static void mv88e6xxx_get_ethtool_stats(struct dsa_switch *ds, int port,
 	struct mv88e6xxx_chip *chip = ds->priv;
 	int ret;
 
-	mv88e6xxx_reg_lock(chip);
+	ret = mv88e6xxx_stats_snapshot(chip, port);
+	if (ret < 0)
+		return;
+
+	mv88e6xxx_get_stats(chip, port, data);
+}
+
+static void mv88e6xxx_get_eth_mac_stats(struct dsa_switch *ds, int port,
+					struct ethtool_eth_mac_stats *mac_stats)
+{
+	struct mv88e6xxx_chip *chip = ds->priv;
+	int ret;
 
 	ret = mv88e6xxx_stats_snapshot(chip, port);
-	mv88e6xxx_reg_unlock(chip);
+	if (ret < 0)
+		return;
+
+#define MV88E6XXX_ETH_MAC_STAT_MAP(_id, _member)			\
+	mv88e6xxx_stats_get_stat(chip, port,				\
+				 &mv88e6xxx_hw_stats[MV88E6XXX_HW_STAT_ID_ ## _id], \
+				 &mac_stats->stats._member)
+
+	MV88E6XXX_ETH_MAC_STAT_MAP(out_unicast, FramesTransmittedOK);
+	MV88E6XXX_ETH_MAC_STAT_MAP(single, SingleCollisionFrames);
+	MV88E6XXX_ETH_MAC_STAT_MAP(multiple, MultipleCollisionFrames);
+	MV88E6XXX_ETH_MAC_STAT_MAP(in_unicast, FramesReceivedOK);
+	MV88E6XXX_ETH_MAC_STAT_MAP(in_fcs_error, FrameCheckSequenceErrors);
+	MV88E6XXX_ETH_MAC_STAT_MAP(out_octets, OctetsTransmittedOK);
+	MV88E6XXX_ETH_MAC_STAT_MAP(deferred, FramesWithDeferredXmissions);
+	MV88E6XXX_ETH_MAC_STAT_MAP(late, LateCollisions);
+	MV88E6XXX_ETH_MAC_STAT_MAP(in_good_octets, OctetsReceivedOK);
+	MV88E6XXX_ETH_MAC_STAT_MAP(out_multicasts, MulticastFramesXmittedOK);
+	MV88E6XXX_ETH_MAC_STAT_MAP(out_broadcasts, BroadcastFramesXmittedOK);
+	MV88E6XXX_ETH_MAC_STAT_MAP(excessive, FramesWithExcessiveDeferral);
+	MV88E6XXX_ETH_MAC_STAT_MAP(in_multicasts, MulticastFramesReceivedOK);
+	MV88E6XXX_ETH_MAC_STAT_MAP(in_broadcasts, BroadcastFramesReceivedOK);
+
+#undef MV88E6XXX_ETH_MAC_STAT_MAP
+
+	mac_stats->stats.FramesTransmittedOK += mac_stats->stats.MulticastFramesXmittedOK;
+	mac_stats->stats.FramesTransmittedOK += mac_stats->stats.BroadcastFramesXmittedOK;
+	mac_stats->stats.FramesReceivedOK += mac_stats->stats.MulticastFramesReceivedOK;
+	mac_stats->stats.FramesReceivedOK += mac_stats->stats.BroadcastFramesReceivedOK;
+}
+
+static void mv88e6xxx_get_rmon_stats(struct dsa_switch *ds, int port,
+				     struct ethtool_rmon_stats *rmon_stats,
+				     const struct ethtool_rmon_hist_range **ranges)
+{
+	static const struct ethtool_rmon_hist_range rmon_ranges[] = {
+		{   64,    64 },
+		{   65,   127 },
+		{  128,   255 },
+		{  256,   511 },
+		{  512,  1023 },
+		{ 1024, 65535 },
+		{}
+	};
+	struct mv88e6xxx_chip *chip = ds->priv;
+	int ret;
 
+	ret = mv88e6xxx_stats_snapshot(chip, port);
 	if (ret < 0)
 		return;
 
-	mv88e6xxx_get_stats(chip, port, data);
+#define MV88E6XXX_RMON_STAT_MAP(_id, _member)				\
+	mv88e6xxx_stats_get_stat(chip, port,				\
+				 &mv88e6xxx_hw_stats[MV88E6XXX_HW_STAT_ID_ ## _id], \
+				 &rmon_stats->stats._member)
+
+	MV88E6XXX_RMON_STAT_MAP(in_undersize, undersize_pkts);
+	MV88E6XXX_RMON_STAT_MAP(in_oversize, oversize_pkts);
+	MV88E6XXX_RMON_STAT_MAP(in_fragments, fragments);
+	MV88E6XXX_RMON_STAT_MAP(in_jabber, jabbers);
+	MV88E6XXX_RMON_STAT_MAP(hist_64bytes, hist[0]);
+	MV88E6XXX_RMON_STAT_MAP(hist_65_127bytes, hist[1]);
+	MV88E6XXX_RMON_STAT_MAP(hist_128_255bytes, hist[2]);
+	MV88E6XXX_RMON_STAT_MAP(hist_256_511bytes, hist[3]);
+	MV88E6XXX_RMON_STAT_MAP(hist_512_1023bytes, hist[4]);
+	MV88E6XXX_RMON_STAT_MAP(hist_1024_max_bytes, hist[5]);
 
+#undef MV88E6XXX_RMON_STAT_MAP
+
+	*ranges = rmon_ranges;
 }
 
 static int mv88e6xxx_get_regs_len(struct dsa_switch *ds, int port)
@@ -3880,7 +4006,8 @@ static int mv88e6xxx_port_setup(struct dsa_switch *ds, int port)
 	struct mv88e6xxx_chip *chip = ds->priv;
 	int err;
 
-	if (chip->info->ops->pcs_ops->pcs_init) {
+	if (chip->info->ops->pcs_ops &&
+	    chip->info->ops->pcs_ops->pcs_init) {
 		err = chip->info->ops->pcs_ops->pcs_init(chip, port);
 		if (err)
 			return err;
@@ -3895,7 +4022,8 @@ static void mv88e6xxx_port_teardown(struct dsa_switch *ds, int port)
 
 	mv88e6xxx_teardown_devlink_regions_port(ds, port);
 
-	if (chip->info->ops->pcs_ops->pcs_teardown)
+	if (chip->info->ops->pcs_ops &&
+	    chip->info->ops->pcs_ops->pcs_teardown)
 		chip->info->ops->pcs_ops->pcs_teardown(chip, port);
 }
 
@@ -3973,7 +4101,7 @@ static const struct mv88e6xxx_ops mv88e6085_ops = {
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
-	.stats_get_stats = mv88e6095_stats_get_stats,
+	.stats_get_stat = mv88e6095_stats_get_stat,
 	.set_cpu_port = mv88e6095_g1_set_cpu_port,
 	.set_egress_port = mv88e6095_g1_set_egress_port,
 	.watchdog_ops = &mv88e6097_watchdog_ops,
@@ -4011,7 +4139,7 @@ static const struct mv88e6xxx_ops mv88e6095_ops = {
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
-	.stats_get_stats = mv88e6095_stats_get_stats,
+	.stats_get_stat = mv88e6095_stats_get_stat,
 	.mgmt_rsvd2cpu = mv88e6185_g2_mgmt_rsvd2cpu,
 	.ppu_enable = mv88e6185_g1_ppu_enable,
 	.ppu_disable = mv88e6185_g1_ppu_disable,
@@ -4052,7 +4180,7 @@ static const struct mv88e6xxx_ops mv88e6097_ops = {
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
-	.stats_get_stats = mv88e6095_stats_get_stats,
+	.stats_get_stat = mv88e6095_stats_get_stat,
 	.set_cpu_port = mv88e6095_g1_set_cpu_port,
 	.set_egress_port = mv88e6095_g1_set_egress_port,
 	.watchdog_ops = &mv88e6097_watchdog_ops,
@@ -4094,7 +4222,7 @@ static const struct mv88e6xxx_ops mv88e6123_ops = {
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
-	.stats_get_stats = mv88e6095_stats_get_stats,
+	.stats_get_stat = mv88e6095_stats_get_stat,
 	.set_cpu_port = mv88e6095_g1_set_cpu_port,
 	.set_egress_port = mv88e6095_g1_set_egress_port,
 	.watchdog_ops = &mv88e6097_watchdog_ops,
@@ -4137,7 +4265,7 @@ static const struct mv88e6xxx_ops mv88e6131_ops = {
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
-	.stats_get_stats = mv88e6095_stats_get_stats,
+	.stats_get_stat = mv88e6095_stats_get_stat,
 	.set_cpu_port = mv88e6095_g1_set_cpu_port,
 	.set_egress_port = mv88e6095_g1_set_egress_port,
 	.watchdog_ops = &mv88e6097_watchdog_ops,
@@ -4186,7 +4314,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = {
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
 	.stats_get_strings = mv88e6320_stats_get_strings,
-	.stats_get_stats = mv88e6390_stats_get_stats,
+	.stats_get_stat = mv88e6390_stats_get_stat,
 	.set_cpu_port = mv88e6390_g1_set_cpu_port,
 	.set_egress_port = mv88e6390_g1_set_egress_port,
 	.watchdog_ops = &mv88e6390_watchdog_ops,
@@ -4241,7 +4369,7 @@ static const struct mv88e6xxx_ops mv88e6161_ops = {
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
-	.stats_get_stats = mv88e6095_stats_get_stats,
+	.stats_get_stat = mv88e6095_stats_get_stat,
 	.set_cpu_port = mv88e6095_g1_set_cpu_port,
 	.set_egress_port = mv88e6095_g1_set_egress_port,
 	.watchdog_ops = &mv88e6097_watchdog_ops,
@@ -4279,7 +4407,7 @@ static const struct mv88e6xxx_ops mv88e6165_ops = {
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
-	.stats_get_stats = mv88e6095_stats_get_stats,
+	.stats_get_stat = mv88e6095_stats_get_stat,
 	.set_cpu_port = mv88e6095_g1_set_cpu_port,
 	.set_egress_port = mv88e6095_g1_set_egress_port,
 	.watchdog_ops = &mv88e6097_watchdog_ops,
@@ -4327,7 +4455,7 @@ static const struct mv88e6xxx_ops mv88e6171_ops = {
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
-	.stats_get_stats = mv88e6095_stats_get_stats,
+	.stats_get_stat = mv88e6095_stats_get_stat,
 	.set_cpu_port = mv88e6095_g1_set_cpu_port,
 	.set_egress_port = mv88e6095_g1_set_egress_port,
 	.watchdog_ops = &mv88e6097_watchdog_ops,
@@ -4340,7 +4468,7 @@ static const struct mv88e6xxx_ops mv88e6171_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.stu_getnext = mv88e6352_g1_stu_getnext,
 	.stu_loadpurge = mv88e6352_g1_stu_loadpurge,
-	.phylink_get_caps = mv88e6185_phylink_get_caps,
+	.phylink_get_caps = mv88e6351_phylink_get_caps,
 };
 
 static const struct mv88e6xxx_ops mv88e6172_ops = {
@@ -4376,7 +4504,7 @@ static const struct mv88e6xxx_ops mv88e6172_ops = {
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
-	.stats_get_stats = mv88e6095_stats_get_stats,
+	.stats_get_stat = mv88e6095_stats_get_stat,
 	.set_cpu_port = mv88e6095_g1_set_cpu_port,
 	.set_egress_port = mv88e6095_g1_set_egress_port,
 	.watchdog_ops = &mv88e6097_watchdog_ops,
@@ -4427,7 +4555,7 @@ static const struct mv88e6xxx_ops mv88e6175_ops = {
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
-	.stats_get_stats = mv88e6095_stats_get_stats,
+	.stats_get_stat = mv88e6095_stats_get_stat,
 	.set_cpu_port = mv88e6095_g1_set_cpu_port,
 	.set_egress_port = mv88e6095_g1_set_egress_port,
 	.watchdog_ops = &mv88e6097_watchdog_ops,
@@ -4440,7 +4568,7 @@ static const struct mv88e6xxx_ops mv88e6175_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.stu_getnext = mv88e6352_g1_stu_getnext,
 	.stu_loadpurge = mv88e6352_g1_stu_loadpurge,
-	.phylink_get_caps = mv88e6185_phylink_get_caps,
+	.phylink_get_caps = mv88e6351_phylink_get_caps,
 };
 
 static const struct mv88e6xxx_ops mv88e6176_ops = {
@@ -4476,7 +4604,7 @@ static const struct mv88e6xxx_ops mv88e6176_ops = {
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
-	.stats_get_stats = mv88e6095_stats_get_stats,
+	.stats_get_stat = mv88e6095_stats_get_stat,
 	.set_cpu_port = mv88e6095_g1_set_cpu_port,
 	.set_egress_port = mv88e6095_g1_set_egress_port,
 	.watchdog_ops = &mv88e6097_watchdog_ops,
@@ -4521,7 +4649,7 @@ static const struct mv88e6xxx_ops mv88e6185_ops = {
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
-	.stats_get_stats = mv88e6095_stats_get_stats,
+	.stats_get_stat = mv88e6095_stats_get_stat,
 	.set_cpu_port = mv88e6095_g1_set_cpu_port,
 	.set_egress_port = mv88e6095_g1_set_egress_port,
 	.watchdog_ops = &mv88e6097_watchdog_ops,
@@ -4570,7 +4698,7 @@ static const struct mv88e6xxx_ops mv88e6190_ops = {
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
 	.stats_get_strings = mv88e6320_stats_get_strings,
-	.stats_get_stats = mv88e6390_stats_get_stats,
+	.stats_get_stat = mv88e6390_stats_get_stat,
 	.set_cpu_port = mv88e6390_g1_set_cpu_port,
 	.set_egress_port = mv88e6390_g1_set_egress_port,
 	.watchdog_ops = &mv88e6390_watchdog_ops,
@@ -4628,7 +4756,7 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = {
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
 	.stats_get_strings = mv88e6320_stats_get_strings,
-	.stats_get_stats = mv88e6390_stats_get_stats,
+	.stats_get_stat = mv88e6390_stats_get_stat,
 	.set_cpu_port = mv88e6390_g1_set_cpu_port,
 	.set_egress_port = mv88e6390_g1_set_egress_port,
 	.watchdog_ops = &mv88e6390_watchdog_ops,
@@ -4684,7 +4812,7 @@ static const struct mv88e6xxx_ops mv88e6191_ops = {
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
 	.stats_get_strings = mv88e6320_stats_get_strings,
-	.stats_get_stats = mv88e6390_stats_get_stats,
+	.stats_get_stat = mv88e6390_stats_get_stat,
 	.set_cpu_port = mv88e6390_g1_set_cpu_port,
 	.set_egress_port = mv88e6390_g1_set_egress_port,
 	.watchdog_ops = &mv88e6390_watchdog_ops,
@@ -4743,7 +4871,7 @@ static const struct mv88e6xxx_ops mv88e6240_ops = {
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
-	.stats_get_stats = mv88e6095_stats_get_stats,
+	.stats_get_stat = mv88e6095_stats_get_stat,
 	.set_cpu_port = mv88e6095_g1_set_cpu_port,
 	.set_egress_port = mv88e6095_g1_set_egress_port,
 	.watchdog_ops = &mv88e6097_watchdog_ops,
@@ -4796,7 +4924,7 @@ static const struct mv88e6xxx_ops mv88e6250_ops = {
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6250_stats_get_sset_count,
 	.stats_get_strings = mv88e6250_stats_get_strings,
-	.stats_get_stats = mv88e6250_stats_get_stats,
+	.stats_get_stat = mv88e6250_stats_get_stat,
 	.set_cpu_port = mv88e6095_g1_set_cpu_port,
 	.set_egress_port = mv88e6095_g1_set_egress_port,
 	.watchdog_ops = &mv88e6250_watchdog_ops,
@@ -4843,7 +4971,7 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
 	.stats_get_strings = mv88e6320_stats_get_strings,
-	.stats_get_stats = mv88e6390_stats_get_stats,
+	.stats_get_stat = mv88e6390_stats_get_stat,
 	.set_cpu_port = mv88e6390_g1_set_cpu_port,
 	.set_egress_port = mv88e6390_g1_set_egress_port,
 	.watchdog_ops = &mv88e6390_watchdog_ops,
@@ -4902,7 +5030,7 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
 	.stats_get_strings = mv88e6320_stats_get_strings,
-	.stats_get_stats = mv88e6320_stats_get_stats,
+	.stats_get_stat = mv88e6320_stats_get_stat,
 	.set_cpu_port = mv88e6095_g1_set_cpu_port,
 	.set_egress_port = mv88e6095_g1_set_egress_port,
 	.watchdog_ops = &mv88e6390_watchdog_ops,
@@ -4949,7 +5077,7 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
 	.stats_get_strings = mv88e6320_stats_get_strings,
-	.stats_get_stats = mv88e6320_stats_get_stats,
+	.stats_get_stat = mv88e6320_stats_get_stat,
 	.set_cpu_port = mv88e6095_g1_set_cpu_port,
 	.set_egress_port = mv88e6095_g1_set_egress_port,
 	.watchdog_ops = &mv88e6390_watchdog_ops,
@@ -4998,7 +5126,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = {
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
 	.stats_get_strings = mv88e6320_stats_get_strings,
-	.stats_get_stats = mv88e6390_stats_get_stats,
+	.stats_get_stat = mv88e6390_stats_get_stat,
 	.set_cpu_port = mv88e6390_g1_set_cpu_port,
 	.set_egress_port = mv88e6390_g1_set_egress_port,
 	.watchdog_ops = &mv88e6390_watchdog_ops,
@@ -5056,7 +5184,7 @@ static const struct mv88e6xxx_ops mv88e6350_ops = {
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
-	.stats_get_stats = mv88e6095_stats_get_stats,
+	.stats_get_stat = mv88e6095_stats_get_stat,
 	.set_cpu_port = mv88e6095_g1_set_cpu_port,
 	.set_egress_port = mv88e6095_g1_set_egress_port,
 	.watchdog_ops = &mv88e6097_watchdog_ops,
@@ -5069,7 +5197,7 @@ static const struct mv88e6xxx_ops mv88e6350_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.stu_getnext = mv88e6352_g1_stu_getnext,
 	.stu_loadpurge = mv88e6352_g1_stu_loadpurge,
-	.phylink_get_caps = mv88e6185_phylink_get_caps,
+	.phylink_get_caps = mv88e6351_phylink_get_caps,
 };
 
 static const struct mv88e6xxx_ops mv88e6351_ops = {
@@ -5102,7 +5230,7 @@ static const struct mv88e6xxx_ops mv88e6351_ops = {
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
-	.stats_get_stats = mv88e6095_stats_get_stats,
+	.stats_get_stat = mv88e6095_stats_get_stat,
 	.set_cpu_port = mv88e6095_g1_set_cpu_port,
 	.set_egress_port = mv88e6095_g1_set_egress_port,
 	.watchdog_ops = &mv88e6097_watchdog_ops,
@@ -5117,7 +5245,7 @@ static const struct mv88e6xxx_ops mv88e6351_ops = {
 	.stu_loadpurge = mv88e6352_g1_stu_loadpurge,
 	.avb_ops = &mv88e6352_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
-	.phylink_get_caps = mv88e6185_phylink_get_caps,
+	.phylink_get_caps = mv88e6351_phylink_get_caps,
 };
 
 static const struct mv88e6xxx_ops mv88e6352_ops = {
@@ -5153,7 +5281,7 @@ static const struct mv88e6xxx_ops mv88e6352_ops = {
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
-	.stats_get_stats = mv88e6095_stats_get_stats,
+	.stats_get_stat = mv88e6095_stats_get_stat,
 	.set_cpu_port = mv88e6095_g1_set_cpu_port,
 	.set_egress_port = mv88e6095_g1_set_egress_port,
 	.watchdog_ops = &mv88e6097_watchdog_ops,
@@ -5215,7 +5343,7 @@ static const struct mv88e6xxx_ops mv88e6390_ops = {
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
 	.stats_get_strings = mv88e6320_stats_get_strings,
-	.stats_get_stats = mv88e6390_stats_get_stats,
+	.stats_get_stat = mv88e6390_stats_get_stat,
 	.set_cpu_port = mv88e6390_g1_set_cpu_port,
 	.set_egress_port = mv88e6390_g1_set_egress_port,
 	.watchdog_ops = &mv88e6390_watchdog_ops,
@@ -5277,7 +5405,7 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
 	.stats_get_strings = mv88e6320_stats_get_strings,
-	.stats_get_stats = mv88e6390_stats_get_stats,
+	.stats_get_stat = mv88e6390_stats_get_stat,
 	.set_cpu_port = mv88e6390_g1_set_cpu_port,
 	.set_egress_port = mv88e6390_g1_set_egress_port,
 	.watchdog_ops = &mv88e6390_watchdog_ops,
@@ -5339,7 +5467,7 @@ static const struct mv88e6xxx_ops mv88e6393x_ops = {
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
 	.stats_get_strings = mv88e6320_stats_get_strings,
-	.stats_get_stats = mv88e6390_stats_get_stats,
+	.stats_get_stat = mv88e6390_stats_get_stat,
 	/* .set_cpu_port is missing because this family does not support a global
 	 * CPU port, only per port CPU port which is set via
 	 * .port_set_upstream_port method.
@@ -6803,6 +6931,8 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = {
 	.phylink_mac_link_up	= mv88e6xxx_mac_link_up,
 	.get_strings		= mv88e6xxx_get_strings,
 	.get_ethtool_stats	= mv88e6xxx_get_ethtool_stats,
+	.get_eth_mac_stats	= mv88e6xxx_get_eth_mac_stats,
+	.get_rmon_stats		= mv88e6xxx_get_rmon_stats,
 	.get_sset_count		= mv88e6xxx_get_sset_count,
 	.port_max_mtu		= mv88e6xxx_get_max_mtu,
 	.port_change_mtu	= mv88e6xxx_change_mtu,
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index 44383a03ef2f..85eb293381a7 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -318,6 +318,17 @@ struct mv88e6xxx_mst {
 	struct mv88e6xxx_stu_entry stu;
 };
 
+#define STATS_TYPE_PORT		BIT(0)
+#define STATS_TYPE_BANK0	BIT(1)
+#define STATS_TYPE_BANK1	BIT(2)
+
+struct mv88e6xxx_hw_stat {
+	char string[ETH_GSTRING_LEN];
+	size_t size;
+	int reg;
+	int type;
+};
+
 struct mv88e6xxx_chip {
 	const struct mv88e6xxx_info *info;
 
@@ -574,8 +585,9 @@ struct mv88e6xxx_ops {
 	/* Return the number of strings describing statistics */
 	int (*stats_get_sset_count)(struct mv88e6xxx_chip *chip);
 	int (*stats_get_strings)(struct mv88e6xxx_chip *chip,  uint8_t *data);
-	int (*stats_get_stats)(struct mv88e6xxx_chip *chip,  int port,
-			       uint64_t *data);
+	size_t (*stats_get_stat)(struct mv88e6xxx_chip *chip, int port,
+				 const struct mv88e6xxx_hw_stat *stat,
+				 uint64_t *data);
 	int (*set_cpu_port)(struct mv88e6xxx_chip *chip, int port);
 	int (*set_egress_port)(struct mv88e6xxx_chip *chip,
 			       enum mv88e6xxx_egress_direction direction,
@@ -601,8 +613,8 @@ struct mv88e6xxx_ops {
 	int (*serdes_get_sset_count)(struct mv88e6xxx_chip *chip, int port);
 	int (*serdes_get_strings)(struct mv88e6xxx_chip *chip,  int port,
 				  uint8_t *data);
-	int (*serdes_get_stats)(struct mv88e6xxx_chip *chip,  int port,
-				uint64_t *data);
+	size_t (*serdes_get_stats)(struct mv88e6xxx_chip *chip, int port,
+				   uint64_t *data);
 
 	/* SERDES registers for ethtool */
 	int (*serdes_get_regs_len)(struct mv88e6xxx_chip *chip,  int port);
@@ -727,17 +739,6 @@ struct mv88e6xxx_pcs_ops {
 
 };
 
-#define STATS_TYPE_PORT		BIT(0)
-#define STATS_TYPE_BANK0	BIT(1)
-#define STATS_TYPE_BANK1	BIT(2)
-
-struct mv88e6xxx_hw_stat {
-	char string[ETH_GSTRING_LEN];
-	size_t size;
-	int reg;
-	int type;
-};
-
 static inline bool mv88e6xxx_has_stu(struct mv88e6xxx_chip *chip)
 {
 	return chip->info->max_sid > 0 &&
diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c
index 174c773b38c2..49444a72ff09 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.c
+++ b/drivers/net/dsa/mv88e6xxx/global1.c
@@ -462,8 +462,7 @@ int mv88e6390_g1_rmu_disable(struct mv88e6xxx_chip *chip)
 int mv88e6390_g1_stats_set_histogram(struct mv88e6xxx_chip *chip)
 {
 	return mv88e6xxx_g1_ctl2_mask(chip, MV88E6390_G1_CTL2_HIST_MODE_MASK,
-				      MV88E6390_G1_CTL2_HIST_MODE_RX |
-				      MV88E6390_G1_CTL2_HIST_MODE_TX);
+				      MV88E6390_G1_CTL2_HIST_MODE_RX);
 }
 
 int mv88e6xxx_g1_set_device_number(struct mv88e6xxx_chip *chip, int index)
@@ -491,7 +490,7 @@ int mv88e6095_g1_stats_set_histogram(struct mv88e6xxx_chip *chip)
 	if (err)
 		return err;
 
-	val |= MV88E6XXX_G1_STATS_OP_HIST_RX_TX;
+	val |= MV88E6XXX_G1_STATS_OP_HIST_RX;
 
 	err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_STATS_OP, val);
 
@@ -506,7 +505,7 @@ int mv88e6xxx_g1_stats_snapshot(struct mv88e6xxx_chip *chip, int port)
 	err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_STATS_OP,
 				 MV88E6XXX_G1_STATS_OP_BUSY |
 				 MV88E6XXX_G1_STATS_OP_CAPTURE_PORT |
-				 MV88E6XXX_G1_STATS_OP_HIST_RX_TX | port);
+				 MV88E6XXX_G1_STATS_OP_HIST_RX | port);
 	if (err)
 		return err;
 
diff --git a/drivers/net/dsa/mv88e6xxx/pcs-639x.c b/drivers/net/dsa/mv88e6xxx/pcs-639x.c
index 9a8429f5d09c..d758a6c1b226 100644
--- a/drivers/net/dsa/mv88e6xxx/pcs-639x.c
+++ b/drivers/net/dsa/mv88e6xxx/pcs-639x.c
@@ -465,6 +465,7 @@ mv88e639x_pcs_select(struct mv88e6xxx_chip *chip, int port,
 	case PHY_INTERFACE_MODE_10GBASER:
 	case PHY_INTERFACE_MODE_XAUI:
 	case PHY_INTERFACE_MODE_RXAUI:
+	case PHY_INTERFACE_MODE_USXGMII:
 		return &mpcs->xg_pcs;
 
 	default:
@@ -873,7 +874,8 @@ static int mv88e6393x_xg_pcs_post_config(struct phylink_pcs *pcs,
 	struct mv88e639x_pcs *mpcs = xg_pcs_to_mv88e639x_pcs(pcs);
 	int err;
 
-	if (interface == PHY_INTERFACE_MODE_10GBASER) {
+	if (interface == PHY_INTERFACE_MODE_10GBASER ||
+	    interface == PHY_INTERFACE_MODE_USXGMII) {
 		err = mv88e6393x_erratum_5_2(mpcs);
 		if (err)
 			return err;
@@ -886,12 +888,37 @@ static int mv88e6393x_xg_pcs_post_config(struct phylink_pcs *pcs,
 	return mv88e639x_xg_pcs_enable(mpcs);
 }
 
+static void mv88e6393x_xg_pcs_get_state(struct phylink_pcs *pcs,
+					struct phylink_link_state *state)
+{
+	struct mv88e639x_pcs *mpcs = xg_pcs_to_mv88e639x_pcs(pcs);
+	u16 status, lp_status;
+	int err;
+
+	if (state->interface != PHY_INTERFACE_MODE_USXGMII)
+		return mv88e639x_xg_pcs_get_state(pcs, state);
+
+	state->link = false;
+
+	err = mv88e639x_read(mpcs, MV88E6390_USXGMII_PHY_STATUS, &status);
+	err = err ? : mv88e639x_read(mpcs, MV88E6390_USXGMII_LP_STATUS, &lp_status);
+	if (err) {
+		dev_err(mpcs->mdio.dev.parent,
+			"can't read USXGMII status: %pe\n", ERR_PTR(err));
+		return;
+	}
+
+	state->link = !!(status & MDIO_USXGMII_LINK);
+	state->an_complete = state->link;
+	phylink_decode_usxgmii_word(state, lp_status);
+}
+
 static const struct phylink_pcs_ops mv88e6393x_xg_pcs_ops = {
 	.pcs_enable = mv88e6393x_xg_pcs_enable,
 	.pcs_disable = mv88e6393x_xg_pcs_disable,
 	.pcs_pre_config = mv88e6393x_xg_pcs_pre_config,
 	.pcs_post_config = mv88e6393x_xg_pcs_post_config,
-	.pcs_get_state = mv88e639x_xg_pcs_get_state,
+	.pcs_get_state = mv88e6393x_xg_pcs_get_state,
 	.pcs_config = mv88e639x_xg_pcs_config,
 };
 
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c
index 3b4b42651fa3..01ea53940786 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.c
+++ b/drivers/net/dsa/mv88e6xxx/serdes.c
@@ -177,8 +177,8 @@ static uint64_t mv88e6352_serdes_get_stat(struct mv88e6xxx_chip *chip,
 	return val;
 }
 
-int mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port,
-			       uint64_t *data)
+size_t mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port,
+				  uint64_t *data)
 {
 	struct mv88e6xxx_port *mv88e6xxx_port = &chip->ports[port];
 	struct mv88e6352_serdes_hw_stat *stat;
@@ -187,7 +187,7 @@ int mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port,
 
 	err = mv88e6352_g2_scratch_port_has_serdes(chip, port);
 	if (err <= 0)
-		return err;
+		return 0;
 
 	BUILD_BUG_ON(ARRAY_SIZE(mv88e6352_serdes_hw_stats) >
 		     ARRAY_SIZE(mv88e6xxx_port->serdes_stats));
@@ -429,8 +429,8 @@ static uint64_t mv88e6390_serdes_get_stat(struct mv88e6xxx_chip *chip, int lane,
 	return reg[0] | ((u64)reg[1] << 16) | ((u64)reg[2] << 32);
 }
 
-int mv88e6390_serdes_get_stats(struct mv88e6xxx_chip *chip, int port,
-			       uint64_t *data)
+size_t mv88e6390_serdes_get_stats(struct mv88e6xxx_chip *chip, int port,
+				  uint64_t *data)
 {
 	struct mv88e6390_serdes_hw_stat *stat;
 	int lane;
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h
index aac95cab46e3..ff5c3ab31e15 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.h
+++ b/drivers/net/dsa/mv88e6xxx/serdes.h
@@ -127,13 +127,13 @@ unsigned int mv88e6390_serdes_irq_mapping(struct mv88e6xxx_chip *chip,
 int mv88e6352_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port);
 int mv88e6352_serdes_get_strings(struct mv88e6xxx_chip *chip,
 				 int port, uint8_t *data);
-int mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port,
-			       uint64_t *data);
+size_t mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port,
+				  uint64_t *data);
 int mv88e6390_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port);
 int mv88e6390_serdes_get_strings(struct mv88e6xxx_chip *chip,
 				 int port, uint8_t *data);
-int mv88e6390_serdes_get_stats(struct mv88e6xxx_chip *chip, int port,
-			       uint64_t *data);
+size_t mv88e6390_serdes_get_stats(struct mv88e6xxx_chip *chip, int port,
+				  uint64_t *data);
 
 int mv88e6352_serdes_get_regs_len(struct mv88e6xxx_chip *chip, int port);
 void mv88e6352_serdes_get_regs(struct mv88e6xxx_chip *chip, int port, void *_p);
diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c
index ec57d9d52072..c51f40960961 100644
--- a/drivers/net/dsa/qca/qca8k-8xxx.c
+++ b/drivers/net/dsa/qca/qca8k-8xxx.c
@@ -947,36 +947,49 @@ static int
 qca8k_mdio_register(struct qca8k_priv *priv)
 {
 	struct dsa_switch *ds = priv->ds;
+	struct device *dev = ds->dev;
 	struct device_node *mdio;
 	struct mii_bus *bus;
+	int err = 0;
 
-	bus = devm_mdiobus_alloc(ds->dev);
-	if (!bus)
-		return -ENOMEM;
+	mdio = of_get_child_by_name(dev->of_node, "mdio");
+	if (mdio && !of_device_is_available(mdio))
+		goto out;
+
+	bus = devm_mdiobus_alloc(dev);
+	if (!bus) {
+		err = -ENOMEM;
+		goto out_put_node;
+	}
 
+	priv->internal_mdio_bus = bus;
 	bus->priv = (void *)priv;
 	snprintf(bus->id, MII_BUS_ID_SIZE, "qca8k-%d.%d",
 		 ds->dst->index, ds->index);
-	bus->parent = ds->dev;
-	bus->phy_mask = ~ds->phys_mii_mask;
-	ds->user_mii_bus = bus;
+	bus->parent = dev;
 
-	/* Check if the devicetree declare the port:phy mapping */
-	mdio = of_get_child_by_name(priv->dev->of_node, "mdio");
-	if (of_device_is_available(mdio)) {
+	if (mdio) {
+		/* Check if the device tree declares the port:phy mapping */
 		bus->name = "qca8k user mii";
 		bus->read = qca8k_internal_mdio_read;
 		bus->write = qca8k_internal_mdio_write;
-		return devm_of_mdiobus_register(priv->dev, bus, mdio);
+	} else {
+		/* If a mapping can't be found, the legacy mapping is used,
+		 * using qca8k_port_to_phy()
+		 */
+		ds->user_mii_bus = bus;
+		bus->phy_mask = ~ds->phys_mii_mask;
+		bus->name = "qca8k-legacy user mii";
+		bus->read = qca8k_legacy_mdio_read;
+		bus->write = qca8k_legacy_mdio_write;
 	}
 
-	/* If a mapping can't be found the legacy mapping is used,
-	 * using the qca8k_port_to_phy function
-	 */
-	bus->name = "qca8k-legacy user mii";
-	bus->read = qca8k_legacy_mdio_read;
-	bus->write = qca8k_legacy_mdio_write;
-	return devm_mdiobus_register(priv->dev, bus);
+	err = devm_of_mdiobus_register(dev, bus, mdio);
+
+out_put_node:
+	of_node_put(mdio);
+out:
+	return err;
 }
 
 static int
diff --git a/drivers/net/dsa/qca/qca8k-common.c b/drivers/net/dsa/qca/qca8k-common.c
index 9243eff8918d..2358cd399c7e 100644
--- a/drivers/net/dsa/qca/qca8k-common.c
+++ b/drivers/net/dsa/qca/qca8k-common.c
@@ -487,7 +487,7 @@ void qca8k_get_strings(struct dsa_switch *ds, int port, u32 stringset,
 		return;
 
 	for (i = 0; i < priv->info->mib_count; i++)
-		ethtool_sprintf(&data, "%s", ar8327_mib[i].name);
+		ethtool_puts(&data, ar8327_mib[i].name);
 }
 
 void qca8k_get_ethtool_stats(struct dsa_switch *ds, int port,
diff --git a/drivers/net/dsa/qca/qca8k-leds.c b/drivers/net/dsa/qca/qca8k-leds.c
index 90e30c2909e4..811ebeeff4ed 100644
--- a/drivers/net/dsa/qca/qca8k-leds.c
+++ b/drivers/net/dsa/qca/qca8k-leds.c
@@ -366,7 +366,6 @@ qca8k_parse_port_leds(struct qca8k_priv *priv, struct fwnode_handle *port, int p
 {
 	struct fwnode_handle *led = NULL, *leds = NULL;
 	struct led_init_data init_data = { };
-	struct dsa_switch *ds = priv->ds;
 	enum led_default_state state;
 	struct qca8k_led *port_led;
 	int led_num, led_index;
@@ -429,7 +428,8 @@ qca8k_parse_port_leds(struct qca8k_priv *priv, struct fwnode_handle *port, int p
 		init_data.default_label = ":port";
 		init_data.fwnode = led;
 		init_data.devname_mandatory = true;
-		init_data.devicename = kasprintf(GFP_KERNEL, "%s:0%d", ds->user_mii_bus->id,
+		init_data.devicename = kasprintf(GFP_KERNEL, "%s:0%d",
+						 priv->internal_mdio_bus->id,
 						 port_num);
 		if (!init_data.devicename)
 			return -ENOMEM;
diff --git a/drivers/net/dsa/qca/qca8k.h b/drivers/net/dsa/qca/qca8k.h
index 2ac7e88f8da5..c8785c36c54e 100644
--- a/drivers/net/dsa/qca/qca8k.h
+++ b/drivers/net/dsa/qca/qca8k.h
@@ -454,6 +454,7 @@ struct qca8k_priv {
 	struct qca8k_ports_config ports_config;
 	struct regmap *regmap;
 	struct mii_bus *bus;
+	struct mii_bus *internal_mdio_bus;
 	struct dsa_switch *ds;
 	struct mutex reg_mutex;
 	struct device *dev;
diff --git a/drivers/net/dsa/realtek/rtl8365mb.c b/drivers/net/dsa/realtek/rtl8365mb.c
index 0875e4fc9f57..b072045eb154 100644
--- a/drivers/net/dsa/realtek/rtl8365mb.c
+++ b/drivers/net/dsa/realtek/rtl8365mb.c
@@ -1303,7 +1303,7 @@ static void rtl8365mb_get_strings(struct dsa_switch *ds, int port, u32 stringset
 
 	for (i = 0; i < RTL8365MB_MIB_END; i++) {
 		struct rtl8365mb_mib_counter *mib = &rtl8365mb_mib_counters[i];
-		ethtool_sprintf(&data, "%s", mib->name);
+		ethtool_puts(&data, mib->name);
 	}
 }
 
diff --git a/drivers/net/dsa/realtek/rtl8366-core.c b/drivers/net/dsa/realtek/rtl8366-core.c
index 82e267b8fddb..59f98d2c8769 100644
--- a/drivers/net/dsa/realtek/rtl8366-core.c
+++ b/drivers/net/dsa/realtek/rtl8366-core.c
@@ -401,7 +401,7 @@ void rtl8366_get_strings(struct dsa_switch *ds, int port, u32 stringset,
 		return;
 
 	for (i = 0; i < priv->num_mib_counters; i++)
-		ethtool_sprintf(&data, "%s", priv->mib_counters[i].name);
+		ethtool_puts(&data, priv->mib_counters[i].name);
 }
 EXPORT_SYMBOL_GPL(rtl8366_get_strings);
 
diff --git a/drivers/net/dsa/realtek/rtl8366rb.c b/drivers/net/dsa/realtek/rtl8366rb.c
index b39b719a5b8f..e3b6a470ca67 100644
--- a/drivers/net/dsa/realtek/rtl8366rb.c
+++ b/drivers/net/dsa/realtek/rtl8366rb.c
@@ -15,6 +15,7 @@
 #include <linux/bitops.h>
 #include <linux/etherdevice.h>
 #include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
 #include <linux/interrupt.h>
 #include <linux/irqdomain.h>
 #include <linux/irqchip/chained_irq.h>
@@ -117,10 +118,11 @@
 	RTL8366RB_STP_STATE((port), RTL8366RB_STP_MASK)
 
 /* CPU port control reg */
-#define RTL8368RB_CPU_CTRL_REG		0x0061
-#define RTL8368RB_CPU_PORTS_MSK		0x00FF
+#define RTL8366RB_CPU_CTRL_REG		0x0061
+#define RTL8366RB_CPU_PORTS_MSK		0x00FF
 /* Disables inserting custom tag length/type 0x8899 */
-#define RTL8368RB_CPU_NO_TAG		BIT(15)
+#define RTL8366RB_CPU_NO_TAG		BIT(15)
+#define RTL8366RB_CPU_TAG_SIZE		4
 
 #define RTL8366RB_SMAR0			0x0070 /* bits 0..15 */
 #define RTL8366RB_SMAR1			0x0071 /* bits 16..31 */
@@ -912,10 +914,10 @@ static int rtl8366rb_setup(struct dsa_switch *ds)
 
 	/* Enable CPU port with custom DSA tag 8899.
 	 *
-	 * If you set RTL8368RB_CPU_NO_TAG (bit 15) in this registers
+	 * If you set RTL8366RB_CPU_NO_TAG (bit 15) in this register
 	 * the custom tag is turned off.
 	 */
-	ret = regmap_update_bits(priv->map, RTL8368RB_CPU_CTRL_REG,
+	ret = regmap_update_bits(priv->map, RTL8366RB_CPU_CTRL_REG,
 				 0xFFFF,
 				 BIT(priv->cpu_port));
 	if (ret)
@@ -928,15 +930,19 @@ static int rtl8366rb_setup(struct dsa_switch *ds)
 	if (ret)
 		return ret;
 
-	/* Set maximum packet length to 1536 bytes */
+	/* Set default maximum packet length to 1536 bytes */
 	ret = regmap_update_bits(priv->map, RTL8366RB_SGCR,
 				 RTL8366RB_SGCR_MAX_LENGTH_MASK,
 				 RTL8366RB_SGCR_MAX_LENGTH_1536);
 	if (ret)
 		return ret;
-	for (i = 0; i < RTL8366RB_NUM_PORTS; i++)
-		/* layer 2 size, see rtl8366rb_change_mtu() */
-		rb->max_mtu[i] = 1532;
+	for (i = 0; i < RTL8366RB_NUM_PORTS; i++) {
+		if (i == priv->cpu_port)
+			/* CPU port need to also accept the tag */
+			rb->max_mtu[i] = ETH_DATA_LEN + RTL8366RB_CPU_TAG_SIZE;
+		else
+			rb->max_mtu[i] = ETH_DATA_LEN;
+	}
 
 	/* Disable learning for all ports */
 	ret = regmap_write(priv->map, RTL8366RB_PORT_LEARNDIS_CTRL,
@@ -1441,24 +1447,29 @@ static int rtl8366rb_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
 	/* Roof out the MTU for the entire switch to the greatest
 	 * common denominator: the biggest set for any one port will
 	 * be the biggest MTU for the switch.
-	 *
-	 * The first setting, 1522 bytes, is max IP packet 1500 bytes,
-	 * plus ethernet header, 1518 bytes, plus CPU tag, 4 bytes.
-	 * This function should consider the parameter an SDU, so the
-	 * MTU passed for this setting is 1518 bytes. The same logic
-	 * of subtracting the DSA tag of 4 bytes apply to the other
-	 * settings.
 	 */
-	max_mtu = 1518;
+	max_mtu = ETH_DATA_LEN;
 	for (i = 0; i < RTL8366RB_NUM_PORTS; i++) {
 		if (rb->max_mtu[i] > max_mtu)
 			max_mtu = rb->max_mtu[i];
 	}
-	if (max_mtu <= 1518)
+
+	/* Translate to layer 2 size.
+	 * Add ethernet and (possible) VLAN headers, and checksum to the size.
+	 * For ETH_DATA_LEN (1500 bytes) this will add up to 1522 bytes.
+	 */
+	max_mtu += VLAN_ETH_HLEN;
+	max_mtu += ETH_FCS_LEN;
+
+	if (max_mtu <= 1522)
 		len = RTL8366RB_SGCR_MAX_LENGTH_1522;
-	else if (max_mtu > 1518 && max_mtu <= 1532)
+	else if (max_mtu > 1522 && max_mtu <= 1536)
+		/* This will be the most common default if using VLAN and
+		 * CPU tagging on a port as both VLAN and CPU tag will
+		 * result in 1518 + 4 + 4 = 1526 bytes.
+		 */
 		len = RTL8366RB_SGCR_MAX_LENGTH_1536;
-	else if (max_mtu > 1532 && max_mtu <= 1548)
+	else if (max_mtu > 1536 && max_mtu <= 1552)
 		len = RTL8366RB_SGCR_MAX_LENGTH_1552;
 	else
 		len = RTL8366RB_SGCR_MAX_LENGTH_16000;
@@ -1470,10 +1481,12 @@ static int rtl8366rb_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
 
 static int rtl8366rb_max_mtu(struct dsa_switch *ds, int port)
 {
-	/* The max MTU is 16000 bytes, so we subtract the CPU tag
-	 * and the max presented to the system is 15996 bytes.
+	/* The max MTU is 16000 bytes, so we subtract the ethernet
+	 * headers with VLAN and checksum and arrive at
+	 * 16000 - 18 - 4 = 15978. This does not include the CPU tag
+	 * since that is added to the requested MTU by the DSA framework.
 	 */
-	return 15996;
+	return 16000 - VLAN_ETH_HLEN - ETH_FCS_LEN;
 }
 
 static int rtl8366rb_get_vlan_4k(struct realtek_priv *priv, u32 vid,
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 74cee39d73df..6646f7fb0f90 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -21,6 +21,8 @@
 #include <linux/if_bridge.h>
 #include <linux/if_ether.h>
 #include <linux/dsa/8021q.h>
+#include <linux/units.h>
+
 #include "sja1105.h"
 #include "sja1105_tas.h"
 
@@ -2138,7 +2140,6 @@ static void sja1105_bridge_leave(struct dsa_switch *ds, int port,
 	sja1105_bridge_member(ds, port, bridge, false);
 }
 
-#define BYTES_PER_KBIT (1000LL / 8)
 /* Port 0 (the uC port) does not have CBS shapers */
 #define SJA1110_FIXED_CBS(port, prio) ((((port) - 1) * SJA1105_NUM_TC) + (prio))
 
diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c
index e6f29e4e508c..dd50502e2122 100644
--- a/drivers/net/dsa/vitesse-vsc73xx-core.c
+++ b/drivers/net/dsa/vitesse-vsc73xx-core.c
@@ -949,7 +949,7 @@ static void vsc73xx_get_strings(struct dsa_switch *ds, int port, u32 stringset,
 	indices[5] = ((val >> 26) & 0x1f); /* TX counter 2 */
 
 	/* The first counters is the RX octets */
-	ethtool_sprintf(&buf, "RxEtherStatsOctets");
+	ethtool_puts(&buf, "RxEtherStatsOctets");
 
 	/* Each port supports recording 3 RX counters and 3 TX counters,
 	 * figure out what counters we use in this set-up and return the
@@ -959,15 +959,15 @@ static void vsc73xx_get_strings(struct dsa_switch *ds, int port, u32 stringset,
 	 */
 	for (i = 0; i < 3; i++) {
 		cnt = vsc73xx_find_counter(vsc, indices[i], false);
-		ethtool_sprintf(&buf, "%s", cnt ? cnt->name : "");
+		ethtool_puts(&buf, cnt ? cnt->name : "");
 	}
 
 	/* TX stats begins with the number of TX octets */
-	ethtool_sprintf(&buf, "TxEtherStatsOctets");
+	ethtool_puts(&buf, "TxEtherStatsOctets");
 
 	for (i = 3; i < 6; i++) {
 		cnt = vsc73xx_find_counter(vsc, indices[i], true);
-		ethtool_sprintf(&buf, "%s", cnt ? cnt->name : "");
+		ethtool_puts(&buf, cnt ? cnt->name : "");
 
 	}
 }
diff --git a/drivers/net/ethernet/amazon/ena/Makefile b/drivers/net/ethernet/amazon/ena/Makefile
index f1f752a8f7bb..6ab615365172 100644
--- a/drivers/net/ethernet/amazon/ena/Makefile
+++ b/drivers/net/ethernet/amazon/ena/Makefile
@@ -5,4 +5,4 @@
 
 obj-$(CONFIG_ENA_ETHERNET) += ena.o
 
-ena-y := ena_netdev.o ena_com.o ena_eth_com.o ena_ethtool.o
+ena-y := ena_netdev.o ena_com.o ena_eth_com.o ena_ethtool.o ena_xdp.o
diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
index 3d6f0a466a9e..f9f886289b97 100644
--- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
@@ -328,9 +328,6 @@ static int ena_com_create_and_store_tx_meta_desc(struct ena_com_io_sq *io_sq,
 	 * compare it to the stored version, just create the meta
 	 */
 	if (io_sq->disable_meta_caching) {
-		if (unlikely(!ena_tx_ctx->meta_valid))
-			return -EINVAL;
-
 		*have_meta = true;
 		return ena_com_create_meta(io_sq, ena_meta);
 	}
diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index d671df4b76bc..0cb6cc1cef56 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -7,6 +7,7 @@
 #include <linux/pci.h>
 
 #include "ena_netdev.h"
+#include "ena_xdp.h"
 
 struct ena_stats {
 	char name[ETH_GSTRING_LEN];
@@ -262,17 +263,14 @@ static void ena_queue_strings(struct ena_adapter *adapter, u8 **data)
 					ena_stats->name);
 		}
 
-		if (!is_xdp) {
-			/* RX stats, in XDP there isn't a RX queue
-			 * counterpart
-			 */
-			for (j = 0; j < ENA_STATS_ARRAY_RX; j++) {
-				ena_stats = &ena_stats_rx_strings[j];
+		/* In XDP there isn't an RX queue counterpart */
+		if (is_xdp)
+			continue;
 
-				ethtool_sprintf(data,
-						"queue_%u_rx_%s", i,
-						ena_stats->name);
-			}
+		for (j = 0; j < ENA_STATS_ARRAY_RX; j++) {
+			ena_stats = &ena_stats_rx_strings[j];
+
+			ethtool_sprintf(data, "queue_%u_rx_%s", i, ena_stats->name);
 		}
 	}
 }
@@ -299,13 +297,13 @@ static void ena_get_strings(struct ena_adapter *adapter,
 
 	for (i = 0; i < ENA_STATS_ARRAY_GLOBAL; i++) {
 		ena_stats = &ena_stats_global_strings[i];
-		ethtool_sprintf(&data, ena_stats->name);
+		ethtool_puts(&data, ena_stats->name);
 	}
 
 	if (eni_stats_needed) {
 		for (i = 0; i < ENA_STATS_ARRAY_ENI(adapter); i++) {
 			ena_stats = &ena_stats_eni_strings[i];
-			ethtool_sprintf(&data, ena_stats->name);
+			ethtool_puts(&data, ena_stats->name);
 		}
 	}
 
@@ -802,15 +800,15 @@ static int ena_indirection_table_get(struct ena_adapter *adapter, u32 *indir)
 	return rc;
 }
 
-static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			u8 *hfunc)
+static int ena_get_rxfh(struct net_device *netdev,
+			struct ethtool_rxfh_param *rxfh)
 {
 	struct ena_adapter *adapter = netdev_priv(netdev);
 	enum ena_admin_hash_functions ena_func;
 	u8 func;
 	int rc;
 
-	rc = ena_indirection_table_get(adapter, indir);
+	rc = ena_indirection_table_get(adapter, rxfh->indir);
 	if (rc)
 		return rc;
 
@@ -825,7 +823,7 @@ static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 		return rc;
 	}
 
-	rc = ena_com_get_hash_key(adapter->ena_dev, key);
+	rc = ena_com_get_hash_key(adapter->ena_dev, rxfh->key);
 	if (rc)
 		return rc;
 
@@ -842,27 +840,27 @@ static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 		return -EOPNOTSUPP;
 	}
 
-	if (hfunc)
-		*hfunc = func;
+	rxfh->hfunc = func;
 
 	return 0;
 }
 
-static int ena_set_rxfh(struct net_device *netdev, const u32 *indir,
-			const u8 *key, const u8 hfunc)
+static int ena_set_rxfh(struct net_device *netdev,
+			struct ethtool_rxfh_param *rxfh,
+			struct netlink_ext_ack *extack)
 {
 	struct ena_adapter *adapter = netdev_priv(netdev);
 	struct ena_com_dev *ena_dev = adapter->ena_dev;
 	enum ena_admin_hash_functions func = 0;
 	int rc;
 
-	if (indir) {
-		rc = ena_indirection_table_set(adapter, indir);
+	if (rxfh->indir) {
+		rc = ena_indirection_table_set(adapter, rxfh->indir);
 		if (rc)
 			return rc;
 	}
 
-	switch (hfunc) {
+	switch (rxfh->hfunc) {
 	case ETH_RSS_HASH_NO_CHANGE:
 		func = ena_com_get_current_hash_function(ena_dev);
 		break;
@@ -874,12 +872,12 @@ static int ena_set_rxfh(struct net_device *netdev, const u32 *indir,
 		break;
 	default:
 		netif_err(adapter, drv, netdev, "Unsupported hfunc %d\n",
-			  hfunc);
+			  rxfh->hfunc);
 		return -EOPNOTSUPP;
 	}
 
-	if (key || func) {
-		rc = ena_com_fill_hash_function(ena_dev, func, key,
+	if (rxfh->key || func) {
+		rc = ena_com_fill_hash_function(ena_dev, func, rxfh->key,
 						ENA_HASH_KEY_SIZE,
 						0xFFFFFFFF);
 		if (unlikely(rc)) {
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index b5bca4814830..1c0a7828d397 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -19,8 +19,8 @@
 #include <net/ip.h>
 
 #include "ena_netdev.h"
-#include <linux/bpf_trace.h>
 #include "ena_pci_id_tbl.h"
+#include "ena_xdp.h"
 
 MODULE_AUTHOR("Amazon.com, Inc. or its affiliates");
 MODULE_DESCRIPTION(DEVICE_NAME);
@@ -45,51 +45,6 @@ static void check_for_admin_com_state(struct ena_adapter *adapter);
 static void ena_destroy_device(struct ena_adapter *adapter, bool graceful);
 static int ena_restore_device(struct ena_adapter *adapter);
 
-static void ena_init_io_rings(struct ena_adapter *adapter,
-			      int first_index, int count);
-static void ena_init_napi_in_range(struct ena_adapter *adapter, int first_index,
-				   int count);
-static void ena_del_napi_in_range(struct ena_adapter *adapter, int first_index,
-				  int count);
-static int ena_setup_tx_resources(struct ena_adapter *adapter, int qid);
-static int ena_setup_tx_resources_in_range(struct ena_adapter *adapter,
-					   int first_index,
-					   int count);
-static int ena_create_io_tx_queue(struct ena_adapter *adapter, int qid);
-static void ena_free_tx_resources(struct ena_adapter *adapter, int qid);
-static int ena_clean_xdp_irq(struct ena_ring *xdp_ring, u32 budget);
-static void ena_destroy_all_tx_queues(struct ena_adapter *adapter);
-static void ena_free_all_io_tx_resources(struct ena_adapter *adapter);
-static void ena_napi_disable_in_range(struct ena_adapter *adapter,
-				      int first_index, int count);
-static void ena_napi_enable_in_range(struct ena_adapter *adapter,
-				     int first_index, int count);
-static int ena_up(struct ena_adapter *adapter);
-static void ena_down(struct ena_adapter *adapter);
-static void ena_unmask_interrupt(struct ena_ring *tx_ring,
-				 struct ena_ring *rx_ring);
-static void ena_update_ring_numa_node(struct ena_ring *tx_ring,
-				      struct ena_ring *rx_ring);
-static void ena_unmap_tx_buff(struct ena_ring *tx_ring,
-			      struct ena_tx_buffer *tx_info);
-static int ena_create_io_tx_queues_in_range(struct ena_adapter *adapter,
-					    int first_index, int count);
-
-/* Increase a stat by cnt while holding syncp seqlock on 32bit machines */
-static void ena_increase_stat(u64 *statp, u64 cnt,
-			      struct u64_stats_sync *syncp)
-{
-	u64_stats_update_begin(syncp);
-	(*statp) += cnt;
-	u64_stats_update_end(syncp);
-}
-
-static void ena_ring_tx_doorbell(struct ena_ring *tx_ring)
-{
-	ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq);
-	ena_increase_stat(&tx_ring->tx_stats.doorbells, 1, &tx_ring->syncp);
-}
-
 static void ena_tx_timeout(struct net_device *dev, unsigned int txqueue)
 {
 	struct ena_adapter *adapter = netdev_priv(dev);
@@ -133,19 +88,18 @@ static int ena_change_mtu(struct net_device *dev, int new_mtu)
 	return ret;
 }
 
-static int ena_xmit_common(struct net_device *dev,
-			   struct ena_ring *ring,
-			   struct ena_tx_buffer *tx_info,
-			   struct ena_com_tx_ctx *ena_tx_ctx,
-			   u16 next_to_use,
-			   u32 bytes)
+int ena_xmit_common(struct ena_adapter *adapter,
+		    struct ena_ring *ring,
+		    struct ena_tx_buffer *tx_info,
+		    struct ena_com_tx_ctx *ena_tx_ctx,
+		    u16 next_to_use,
+		    u32 bytes)
 {
-	struct ena_adapter *adapter = netdev_priv(dev);
 	int rc, nb_hw_desc;
 
 	if (unlikely(ena_com_is_doorbell_needed(ring->ena_com_io_sq,
 						ena_tx_ctx))) {
-		netif_dbg(adapter, tx_queued, dev,
+		netif_dbg(adapter, tx_queued, adapter->netdev,
 			  "llq tx max burst size of queue %d achieved, writing doorbell to send burst\n",
 			  ring->qid);
 		ena_ring_tx_doorbell(ring);
@@ -160,7 +114,7 @@ static int ena_xmit_common(struct net_device *dev,
 	 * ena_com_prepare_tx() are fatal and therefore require a device reset.
 	 */
 	if (unlikely(rc)) {
-		netif_err(adapter, tx_queued, dev,
+		netif_err(adapter, tx_queued, adapter->netdev,
 			  "Failed to prepare tx bufs\n");
 		ena_increase_stat(&ring->tx_stats.prepare_ctx_err, 1,
 				  &ring->syncp);
@@ -176,6 +130,7 @@ static int ena_xmit_common(struct net_device *dev,
 	u64_stats_update_end(&ring->syncp);
 
 	tx_info->tx_descs = nb_hw_desc;
+	tx_info->total_tx_size = bytes;
 	tx_info->last_jiffies = jiffies;
 	tx_info->print_once = 0;
 
@@ -184,468 +139,6 @@ static int ena_xmit_common(struct net_device *dev,
 	return 0;
 }
 
-/* This is the XDP napi callback. XDP queues use a separate napi callback
- * than Rx/Tx queues.
- */
-static int ena_xdp_io_poll(struct napi_struct *napi, int budget)
-{
-	struct ena_napi *ena_napi = container_of(napi, struct ena_napi, napi);
-	u32 xdp_work_done, xdp_budget;
-	struct ena_ring *xdp_ring;
-	int napi_comp_call = 0;
-	int ret;
-
-	xdp_ring = ena_napi->xdp_ring;
-
-	xdp_budget = budget;
-
-	if (!test_bit(ENA_FLAG_DEV_UP, &xdp_ring->adapter->flags) ||
-	    test_bit(ENA_FLAG_TRIGGER_RESET, &xdp_ring->adapter->flags)) {
-		napi_complete_done(napi, 0);
-		return 0;
-	}
-
-	xdp_work_done = ena_clean_xdp_irq(xdp_ring, xdp_budget);
-
-	/* If the device is about to reset or down, avoid unmask
-	 * the interrupt and return 0 so NAPI won't reschedule
-	 */
-	if (unlikely(!test_bit(ENA_FLAG_DEV_UP, &xdp_ring->adapter->flags))) {
-		napi_complete_done(napi, 0);
-		ret = 0;
-	} else if (xdp_budget > xdp_work_done) {
-		napi_comp_call = 1;
-		if (napi_complete_done(napi, xdp_work_done))
-			ena_unmask_interrupt(xdp_ring, NULL);
-		ena_update_ring_numa_node(xdp_ring, NULL);
-		ret = xdp_work_done;
-	} else {
-		ret = xdp_budget;
-	}
-
-	u64_stats_update_begin(&xdp_ring->syncp);
-	xdp_ring->tx_stats.napi_comp += napi_comp_call;
-	xdp_ring->tx_stats.tx_poll++;
-	u64_stats_update_end(&xdp_ring->syncp);
-	xdp_ring->tx_stats.last_napi_jiffies = jiffies;
-
-	return ret;
-}
-
-static int ena_xdp_tx_map_frame(struct ena_ring *xdp_ring,
-				struct ena_tx_buffer *tx_info,
-				struct xdp_frame *xdpf,
-				struct ena_com_tx_ctx *ena_tx_ctx)
-{
-	struct ena_adapter *adapter = xdp_ring->adapter;
-	struct ena_com_buf *ena_buf;
-	int push_len = 0;
-	dma_addr_t dma;
-	void *data;
-	u32 size;
-
-	tx_info->xdpf = xdpf;
-	data = tx_info->xdpf->data;
-	size = tx_info->xdpf->len;
-
-	if (xdp_ring->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV) {
-		/* Designate part of the packet for LLQ */
-		push_len = min_t(u32, size, xdp_ring->tx_max_header_size);
-
-		ena_tx_ctx->push_header = data;
-
-		size -= push_len;
-		data += push_len;
-	}
-
-	ena_tx_ctx->header_len = push_len;
-
-	if (size > 0) {
-		dma = dma_map_single(xdp_ring->dev,
-				     data,
-				     size,
-				     DMA_TO_DEVICE);
-		if (unlikely(dma_mapping_error(xdp_ring->dev, dma)))
-			goto error_report_dma_error;
-
-		tx_info->map_linear_data = 0;
-
-		ena_buf = tx_info->bufs;
-		ena_buf->paddr = dma;
-		ena_buf->len = size;
-
-		ena_tx_ctx->ena_bufs = ena_buf;
-		ena_tx_ctx->num_bufs = tx_info->num_of_bufs = 1;
-	}
-
-	return 0;
-
-error_report_dma_error:
-	ena_increase_stat(&xdp_ring->tx_stats.dma_mapping_err, 1,
-			  &xdp_ring->syncp);
-	netif_warn(adapter, tx_queued, adapter->netdev, "Failed to map xdp buff\n");
-
-	return -EINVAL;
-}
-
-static int ena_xdp_xmit_frame(struct ena_ring *xdp_ring,
-			      struct net_device *dev,
-			      struct xdp_frame *xdpf,
-			      int flags)
-{
-	struct ena_com_tx_ctx ena_tx_ctx = {};
-	struct ena_tx_buffer *tx_info;
-	u16 next_to_use, req_id;
-	int rc;
-
-	next_to_use = xdp_ring->next_to_use;
-	req_id = xdp_ring->free_ids[next_to_use];
-	tx_info = &xdp_ring->tx_buffer_info[req_id];
-	tx_info->num_of_bufs = 0;
-
-	rc = ena_xdp_tx_map_frame(xdp_ring, tx_info, xdpf, &ena_tx_ctx);
-	if (unlikely(rc))
-		return rc;
-
-	ena_tx_ctx.req_id = req_id;
-
-	rc = ena_xmit_common(dev,
-			     xdp_ring,
-			     tx_info,
-			     &ena_tx_ctx,
-			     next_to_use,
-			     xdpf->len);
-	if (rc)
-		goto error_unmap_dma;
-
-	/* trigger the dma engine. ena_ring_tx_doorbell()
-	 * calls a memory barrier inside it.
-	 */
-	if (flags & XDP_XMIT_FLUSH)
-		ena_ring_tx_doorbell(xdp_ring);
-
-	return rc;
-
-error_unmap_dma:
-	ena_unmap_tx_buff(xdp_ring, tx_info);
-	tx_info->xdpf = NULL;
-	return rc;
-}
-
-static int ena_xdp_xmit(struct net_device *dev, int n,
-			struct xdp_frame **frames, u32 flags)
-{
-	struct ena_adapter *adapter = netdev_priv(dev);
-	struct ena_ring *xdp_ring;
-	int qid, i, nxmit = 0;
-
-	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
-		return -EINVAL;
-
-	if (!test_bit(ENA_FLAG_DEV_UP, &adapter->flags))
-		return -ENETDOWN;
-
-	/* We assume that all rings have the same XDP program */
-	if (!READ_ONCE(adapter->rx_ring->xdp_bpf_prog))
-		return -ENXIO;
-
-	qid = smp_processor_id() % adapter->xdp_num_queues;
-	qid += adapter->xdp_first_ring;
-	xdp_ring = &adapter->tx_ring[qid];
-
-	/* Other CPU ids might try to send thorugh this queue */
-	spin_lock(&xdp_ring->xdp_tx_lock);
-
-	for (i = 0; i < n; i++) {
-		if (ena_xdp_xmit_frame(xdp_ring, dev, frames[i], 0))
-			break;
-		nxmit++;
-	}
-
-	/* Ring doorbell to make device aware of the packets */
-	if (flags & XDP_XMIT_FLUSH)
-		ena_ring_tx_doorbell(xdp_ring);
-
-	spin_unlock(&xdp_ring->xdp_tx_lock);
-
-	/* Return number of packets sent */
-	return nxmit;
-}
-
-static int ena_xdp_execute(struct ena_ring *rx_ring, struct xdp_buff *xdp)
-{
-	u32 verdict = ENA_XDP_PASS;
-	struct bpf_prog *xdp_prog;
-	struct ena_ring *xdp_ring;
-	struct xdp_frame *xdpf;
-	u64 *xdp_stat;
-
-	xdp_prog = READ_ONCE(rx_ring->xdp_bpf_prog);
-
-	if (!xdp_prog)
-		goto out;
-
-	verdict = bpf_prog_run_xdp(xdp_prog, xdp);
-
-	switch (verdict) {
-	case XDP_TX:
-		xdpf = xdp_convert_buff_to_frame(xdp);
-		if (unlikely(!xdpf)) {
-			trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict);
-			xdp_stat = &rx_ring->rx_stats.xdp_aborted;
-			verdict = ENA_XDP_DROP;
-			break;
-		}
-
-		/* Find xmit queue */
-		xdp_ring = rx_ring->xdp_ring;
-
-		/* The XDP queues are shared between XDP_TX and XDP_REDIRECT */
-		spin_lock(&xdp_ring->xdp_tx_lock);
-
-		if (ena_xdp_xmit_frame(xdp_ring, rx_ring->netdev, xdpf,
-				       XDP_XMIT_FLUSH))
-			xdp_return_frame(xdpf);
-
-		spin_unlock(&xdp_ring->xdp_tx_lock);
-		xdp_stat = &rx_ring->rx_stats.xdp_tx;
-		verdict = ENA_XDP_TX;
-		break;
-	case XDP_REDIRECT:
-		if (likely(!xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog))) {
-			xdp_stat = &rx_ring->rx_stats.xdp_redirect;
-			verdict = ENA_XDP_REDIRECT;
-			break;
-		}
-		trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict);
-		xdp_stat = &rx_ring->rx_stats.xdp_aborted;
-		verdict = ENA_XDP_DROP;
-		break;
-	case XDP_ABORTED:
-		trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict);
-		xdp_stat = &rx_ring->rx_stats.xdp_aborted;
-		verdict = ENA_XDP_DROP;
-		break;
-	case XDP_DROP:
-		xdp_stat = &rx_ring->rx_stats.xdp_drop;
-		verdict = ENA_XDP_DROP;
-		break;
-	case XDP_PASS:
-		xdp_stat = &rx_ring->rx_stats.xdp_pass;
-		verdict = ENA_XDP_PASS;
-		break;
-	default:
-		bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, verdict);
-		xdp_stat = &rx_ring->rx_stats.xdp_invalid;
-		verdict = ENA_XDP_DROP;
-	}
-
-	ena_increase_stat(xdp_stat, 1, &rx_ring->syncp);
-out:
-	return verdict;
-}
-
-static void ena_init_all_xdp_queues(struct ena_adapter *adapter)
-{
-	adapter->xdp_first_ring = adapter->num_io_queues;
-	adapter->xdp_num_queues = adapter->num_io_queues;
-
-	ena_init_io_rings(adapter,
-			  adapter->xdp_first_ring,
-			  adapter->xdp_num_queues);
-}
-
-static int ena_setup_and_create_all_xdp_queues(struct ena_adapter *adapter)
-{
-	int rc = 0;
-
-	rc = ena_setup_tx_resources_in_range(adapter, adapter->xdp_first_ring,
-					     adapter->xdp_num_queues);
-	if (rc)
-		goto setup_err;
-
-	rc = ena_create_io_tx_queues_in_range(adapter,
-					      adapter->xdp_first_ring,
-					      adapter->xdp_num_queues);
-	if (rc)
-		goto create_err;
-
-	return 0;
-
-create_err:
-	ena_free_all_io_tx_resources(adapter);
-setup_err:
-	return rc;
-}
-
-/* Provides a way for both kernel and bpf-prog to know
- * more about the RX-queue a given XDP frame arrived on.
- */
-static int ena_xdp_register_rxq_info(struct ena_ring *rx_ring)
-{
-	int rc;
-
-	rc = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, rx_ring->qid, 0);
-
-	if (rc) {
-		netif_err(rx_ring->adapter, ifup, rx_ring->netdev,
-			  "Failed to register xdp rx queue info. RX queue num %d rc: %d\n",
-			  rx_ring->qid, rc);
-		goto err;
-	}
-
-	rc = xdp_rxq_info_reg_mem_model(&rx_ring->xdp_rxq, MEM_TYPE_PAGE_SHARED,
-					NULL);
-
-	if (rc) {
-		netif_err(rx_ring->adapter, ifup, rx_ring->netdev,
-			  "Failed to register xdp rx queue info memory model. RX queue num %d rc: %d\n",
-			  rx_ring->qid, rc);
-		xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
-	}
-
-err:
-	return rc;
-}
-
-static void ena_xdp_unregister_rxq_info(struct ena_ring *rx_ring)
-{
-	xdp_rxq_info_unreg_mem_model(&rx_ring->xdp_rxq);
-	xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
-}
-
-static void ena_xdp_exchange_program_rx_in_range(struct ena_adapter *adapter,
-						 struct bpf_prog *prog,
-						 int first, int count)
-{
-	struct bpf_prog *old_bpf_prog;
-	struct ena_ring *rx_ring;
-	int i = 0;
-
-	for (i = first; i < count; i++) {
-		rx_ring = &adapter->rx_ring[i];
-		old_bpf_prog = xchg(&rx_ring->xdp_bpf_prog, prog);
-
-		if (!old_bpf_prog && prog) {
-			ena_xdp_register_rxq_info(rx_ring);
-			rx_ring->rx_headroom = XDP_PACKET_HEADROOM;
-		} else if (old_bpf_prog && !prog) {
-			ena_xdp_unregister_rxq_info(rx_ring);
-			rx_ring->rx_headroom = NET_SKB_PAD;
-		}
-	}
-}
-
-static void ena_xdp_exchange_program(struct ena_adapter *adapter,
-				     struct bpf_prog *prog)
-{
-	struct bpf_prog *old_bpf_prog = xchg(&adapter->xdp_bpf_prog, prog);
-
-	ena_xdp_exchange_program_rx_in_range(adapter,
-					     prog,
-					     0,
-					     adapter->num_io_queues);
-
-	if (old_bpf_prog)
-		bpf_prog_put(old_bpf_prog);
-}
-
-static int ena_destroy_and_free_all_xdp_queues(struct ena_adapter *adapter)
-{
-	bool was_up;
-	int rc;
-
-	was_up = test_bit(ENA_FLAG_DEV_UP, &adapter->flags);
-
-	if (was_up)
-		ena_down(adapter);
-
-	adapter->xdp_first_ring = 0;
-	adapter->xdp_num_queues = 0;
-	ena_xdp_exchange_program(adapter, NULL);
-	if (was_up) {
-		rc = ena_up(adapter);
-		if (rc)
-			return rc;
-	}
-	return 0;
-}
-
-static int ena_xdp_set(struct net_device *netdev, struct netdev_bpf *bpf)
-{
-	struct ena_adapter *adapter = netdev_priv(netdev);
-	struct bpf_prog *prog = bpf->prog;
-	struct bpf_prog *old_bpf_prog;
-	int rc, prev_mtu;
-	bool is_up;
-
-	is_up = test_bit(ENA_FLAG_DEV_UP, &adapter->flags);
-	rc = ena_xdp_allowed(adapter);
-	if (rc == ENA_XDP_ALLOWED) {
-		old_bpf_prog = adapter->xdp_bpf_prog;
-		if (prog) {
-			if (!is_up) {
-				ena_init_all_xdp_queues(adapter);
-			} else if (!old_bpf_prog) {
-				ena_down(adapter);
-				ena_init_all_xdp_queues(adapter);
-			}
-			ena_xdp_exchange_program(adapter, prog);
-
-			if (is_up && !old_bpf_prog) {
-				rc = ena_up(adapter);
-				if (rc)
-					return rc;
-			}
-			xdp_features_set_redirect_target(netdev, false);
-		} else if (old_bpf_prog) {
-			xdp_features_clear_redirect_target(netdev);
-			rc = ena_destroy_and_free_all_xdp_queues(adapter);
-			if (rc)
-				return rc;
-		}
-
-		prev_mtu = netdev->max_mtu;
-		netdev->max_mtu = prog ? ENA_XDP_MAX_MTU : adapter->max_mtu;
-
-		if (!old_bpf_prog)
-			netif_info(adapter, drv, adapter->netdev,
-				   "XDP program is set, changing the max_mtu from %d to %d",
-				   prev_mtu, netdev->max_mtu);
-
-	} else if (rc == ENA_XDP_CURRENT_MTU_TOO_LARGE) {
-		netif_err(adapter, drv, adapter->netdev,
-			  "Failed to set xdp program, the current MTU (%d) is larger than the maximum allowed MTU (%lu) while xdp is on",
-			  netdev->mtu, ENA_XDP_MAX_MTU);
-		NL_SET_ERR_MSG_MOD(bpf->extack,
-				   "Failed to set xdp program, the current MTU is larger than the maximum allowed MTU. Check the dmesg for more info");
-		return -EINVAL;
-	} else if (rc == ENA_XDP_NO_ENOUGH_QUEUES) {
-		netif_err(adapter, drv, adapter->netdev,
-			  "Failed to set xdp program, the Rx/Tx channel count should be at most half of the maximum allowed channel count. The current queue count (%d), the maximal queue count (%d)\n",
-			  adapter->num_io_queues, adapter->max_num_io_queues);
-		NL_SET_ERR_MSG_MOD(bpf->extack,
-				   "Failed to set xdp program, there is no enough space for allocating XDP queues, Check the dmesg for more info");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-/* This is the main xdp callback, it's used by the kernel to set/unset the xdp
- * program as well as to query the current xdp program id.
- */
-static int ena_xdp(struct net_device *netdev, struct netdev_bpf *bpf)
-{
-	switch (bpf->command) {
-	case XDP_SETUP_PROG:
-		return ena_xdp_set(netdev, bpf);
-	default:
-		return -EINVAL;
-	}
-	return 0;
-}
-
 static int ena_init_rx_cpu_rmap(struct ena_adapter *adapter)
 {
 #ifdef CONFIG_RFS_ACCEL
@@ -687,8 +180,8 @@ static void ena_init_io_rings_common(struct ena_adapter *adapter,
 	u64_stats_init(&ring->syncp);
 }
 
-static void ena_init_io_rings(struct ena_adapter *adapter,
-			      int first_index, int count)
+void ena_init_io_rings(struct ena_adapter *adapter,
+		       int first_index, int count)
 {
 	struct ena_com_dev *ena_dev;
 	struct ena_ring *txr, *rxr;
@@ -819,9 +312,8 @@ static void ena_free_tx_resources(struct ena_adapter *adapter, int qid)
 	tx_ring->push_buf_intermediate_buf = NULL;
 }
 
-static int ena_setup_tx_resources_in_range(struct ena_adapter *adapter,
-					   int first_index,
-					   int count)
+int ena_setup_tx_resources_in_range(struct ena_adapter *adapter,
+				    int first_index, int count)
 {
 	int i, rc = 0;
 
@@ -844,8 +336,8 @@ err_setup_tx:
 	return rc;
 }
 
-static void ena_free_all_io_tx_resources_in_range(struct ena_adapter *adapter,
-						  int first_index, int count)
+void ena_free_all_io_tx_resources_in_range(struct ena_adapter *adapter,
+					   int first_index, int count)
 {
 	int i;
 
@@ -858,7 +350,7 @@ static void ena_free_all_io_tx_resources_in_range(struct ena_adapter *adapter,
  *
  * Free all transmit software resources
  */
-static void ena_free_all_io_tx_resources(struct ena_adapter *adapter)
+void ena_free_all_io_tx_resources(struct ena_adapter *adapter)
 {
 	ena_free_all_io_tx_resources_in_range(adapter,
 					      0,
@@ -1168,8 +660,8 @@ static void ena_free_all_rx_bufs(struct ena_adapter *adapter)
 		ena_free_rx_bufs(adapter, i);
 }
 
-static void ena_unmap_tx_buff(struct ena_ring *tx_ring,
-			      struct ena_tx_buffer *tx_info)
+void ena_unmap_tx_buff(struct ena_ring *tx_ring,
+		       struct ena_tx_buffer *tx_info)
 {
 	struct ena_com_buf *ena_buf;
 	u32 cnt;
@@ -1261,6 +753,7 @@ static void ena_destroy_all_rx_queues(struct ena_adapter *adapter)
 	for (i = 0; i < adapter->num_io_queues; i++) {
 		ena_qid = ENA_IO_RXQ_IDX(i);
 		cancel_work_sync(&adapter->ena_napi[i].dim.work);
+		ena_xdp_unregister_rxq_info(&adapter->rx_ring[i]);
 		ena_com_destroy_io_queue(adapter->ena_dev, ena_qid);
 	}
 }
@@ -1271,8 +764,8 @@ static void ena_destroy_all_io_queues(struct ena_adapter *adapter)
 	ena_destroy_all_rx_queues(adapter);
 }
 
-static int handle_invalid_req_id(struct ena_ring *ring, u16 req_id,
-				 struct ena_tx_buffer *tx_info, bool is_xdp)
+int handle_invalid_req_id(struct ena_ring *ring, u16 req_id,
+			  struct ena_tx_buffer *tx_info, bool is_xdp)
 {
 	if (tx_info)
 		netif_err(ring->adapter,
@@ -1304,17 +797,6 @@ static int validate_tx_req_id(struct ena_ring *tx_ring, u16 req_id)
 	return handle_invalid_req_id(tx_ring, req_id, tx_info, false);
 }
 
-static int validate_xdp_req_id(struct ena_ring *xdp_ring, u16 req_id)
-{
-	struct ena_tx_buffer *tx_info;
-
-	tx_info = &xdp_ring->tx_buffer_info[req_id];
-	if (likely(tx_info->xdpf))
-		return 0;
-
-	return handle_invalid_req_id(xdp_ring, req_id, tx_info, true);
-}
-
 static int ena_clean_tx_irq(struct ena_ring *tx_ring, u32 budget)
 {
 	struct netdev_queue *txq;
@@ -1362,7 +844,7 @@ static int ena_clean_tx_irq(struct ena_ring *tx_ring, u32 budget)
 			  "tx_poll: q %d skb %p completed\n", tx_ring->qid,
 			  skb);
 
-		tx_bytes += skb->len;
+		tx_bytes += tx_info->total_tx_size;
 		dev_kfree_skb(skb);
 		tx_pkts++;
 		total_done += tx_info->tx_descs;
@@ -1492,11 +974,6 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring,
 		if (unlikely(!skb))
 			return NULL;
 
-		/* sync this buffer for CPU use */
-		dma_sync_single_for_cpu(rx_ring->dev,
-					dma_unmap_addr(&rx_info->ena_buf, paddr) + pkt_offset,
-					len,
-					DMA_FROM_DEVICE);
 		skb_copy_to_linear_data(skb, buf_addr + buf_offset, len);
 		dma_sync_single_for_device(rx_ring->dev,
 					   dma_unmap_addr(&rx_info->ena_buf, paddr) + pkt_offset,
@@ -1515,17 +992,10 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring,
 
 	buf_len = SKB_DATA_ALIGN(len + buf_offset + tailroom);
 
-	pre_reuse_paddr = dma_unmap_addr(&rx_info->ena_buf, paddr);
-
 	/* If XDP isn't loaded try to reuse part of the RX buffer */
 	reuse_rx_buf_page = !is_xdp_loaded &&
 			    ena_try_rx_buf_page_reuse(rx_info, buf_len, len, pkt_offset);
 
-	dma_sync_single_for_cpu(rx_ring->dev,
-				pre_reuse_paddr + pkt_offset,
-				len,
-				DMA_FROM_DEVICE);
-
 	if (!reuse_rx_buf_page)
 		ena_unmap_rx_buff_attrs(rx_ring, rx_info, DMA_ATTR_SKIP_CPU_SYNC);
 
@@ -1671,20 +1141,23 @@ static void ena_set_rx_hash(struct ena_ring *rx_ring,
 	}
 }
 
-static int ena_xdp_handle_buff(struct ena_ring *rx_ring, struct xdp_buff *xdp)
+static int ena_xdp_handle_buff(struct ena_ring *rx_ring, struct xdp_buff *xdp, u16 num_descs)
 {
 	struct ena_rx_buffer *rx_info;
 	int ret;
 
+	/* XDP multi-buffer packets not supported */
+	if (unlikely(num_descs > 1)) {
+		netdev_err_once(rx_ring->adapter->netdev,
+				"xdp: dropped unsupported multi-buffer packets\n");
+		ena_increase_stat(&rx_ring->rx_stats.xdp_drop, 1, &rx_ring->syncp);
+		return ENA_XDP_DROP;
+	}
+
 	rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id];
 	xdp_prepare_buff(xdp, page_address(rx_info->page),
 			 rx_info->buf_offset,
 			 rx_ring->ena_bufs[0].len, false);
-	/* If for some reason we received a bigger packet than
-	 * we expect, then we simply drop it
-	 */
-	if (unlikely(rx_ring->ena_bufs[0].len > ENA_XDP_MAX_MTU))
-		return ENA_XDP_DROP;
 
 	ret = ena_xdp_execute(rx_ring, xdp);
 
@@ -1696,6 +1169,7 @@ static int ena_xdp_handle_buff(struct ena_ring *rx_ring, struct xdp_buff *xdp)
 
 	return ret;
 }
+
 /* ena_clean_rx_irq - Cleanup RX irq
  * @rx_ring: RX ring to clean
  * @napi: napi handler
@@ -1719,6 +1193,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 	int xdp_flags = 0;
 	int total_len = 0;
 	int xdp_verdict;
+	u8 pkt_offset;
 	int rc = 0;
 	int i;
 
@@ -1745,15 +1220,21 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 
 		/* First descriptor might have an offset set by the device */
 		rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id];
-		rx_info->buf_offset += ena_rx_ctx.pkt_offset;
+		pkt_offset = ena_rx_ctx.pkt_offset;
+		rx_info->buf_offset += pkt_offset;
 
 		netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev,
 			  "rx_poll: q %d got packet from ena. descs #: %d l3 proto %d l4 proto %d hash: %x\n",
 			  rx_ring->qid, ena_rx_ctx.descs, ena_rx_ctx.l3_proto,
 			  ena_rx_ctx.l4_proto, ena_rx_ctx.hash);
 
+		dma_sync_single_for_cpu(rx_ring->dev,
+					dma_unmap_addr(&rx_info->ena_buf, paddr) + pkt_offset,
+					rx_ring->ena_bufs[0].len,
+					DMA_FROM_DEVICE);
+
 		if (ena_xdp_present_ring(rx_ring))
-			xdp_verdict = ena_xdp_handle_buff(rx_ring, &xdp);
+			xdp_verdict = ena_xdp_handle_buff(rx_ring, &xdp, ena_rx_ctx.descs);
 
 		/* allocate skb and fill it */
 		if (xdp_verdict == ENA_XDP_PASS)
@@ -1777,7 +1258,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 				if (xdp_verdict & ENA_XDP_FORWARDED) {
 					ena_unmap_rx_buff_attrs(rx_ring,
 								&rx_ring->rx_buffer_info[req_id],
-								0);
+								DMA_ATTR_SKIP_CPU_SYNC);
 					rx_ring->rx_buffer_info[req_id].page = NULL;
 				}
 			}
@@ -1881,8 +1362,8 @@ static void ena_adjust_adaptive_rx_intr_moderation(struct ena_napi *ena_napi)
 	rx_ring->per_napi_packets = 0;
 }
 
-static void ena_unmask_interrupt(struct ena_ring *tx_ring,
-					struct ena_ring *rx_ring)
+void ena_unmask_interrupt(struct ena_ring *tx_ring,
+			  struct ena_ring *rx_ring)
 {
 	u32 rx_interval = tx_ring->smoothed_interval;
 	struct ena_eth_io_intr_reg intr_reg;
@@ -1914,8 +1395,8 @@ static void ena_unmask_interrupt(struct ena_ring *tx_ring,
 	ena_com_unmask_intr(tx_ring->ena_com_io_cq, &intr_reg);
 }
 
-static void ena_update_ring_numa_node(struct ena_ring *tx_ring,
-					     struct ena_ring *rx_ring)
+void ena_update_ring_numa_node(struct ena_ring *tx_ring,
+			       struct ena_ring *rx_ring)
 {
 	int cpu = get_cpu();
 	int numa_node;
@@ -1950,67 +1431,6 @@ out:
 	put_cpu();
 }
 
-static int ena_clean_xdp_irq(struct ena_ring *xdp_ring, u32 budget)
-{
-	u32 total_done = 0;
-	u16 next_to_clean;
-	int tx_pkts = 0;
-	u16 req_id;
-	int rc;
-
-	if (unlikely(!xdp_ring))
-		return 0;
-	next_to_clean = xdp_ring->next_to_clean;
-
-	while (tx_pkts < budget) {
-		struct ena_tx_buffer *tx_info;
-		struct xdp_frame *xdpf;
-
-		rc = ena_com_tx_comp_req_id_get(xdp_ring->ena_com_io_cq,
-						&req_id);
-		if (rc) {
-			if (unlikely(rc == -EINVAL))
-				handle_invalid_req_id(xdp_ring, req_id, NULL,
-						      true);
-			break;
-		}
-
-		/* validate that the request id points to a valid xdp_frame */
-		rc = validate_xdp_req_id(xdp_ring, req_id);
-		if (rc)
-			break;
-
-		tx_info = &xdp_ring->tx_buffer_info[req_id];
-		xdpf = tx_info->xdpf;
-
-		tx_info->xdpf = NULL;
-		tx_info->last_jiffies = 0;
-		ena_unmap_tx_buff(xdp_ring, tx_info);
-
-		netif_dbg(xdp_ring->adapter, tx_done, xdp_ring->netdev,
-			  "tx_poll: q %d skb %p completed\n", xdp_ring->qid,
-			  xdpf);
-
-		tx_pkts++;
-		total_done += tx_info->tx_descs;
-
-		xdp_return_frame(xdpf);
-		xdp_ring->free_ids[next_to_clean] = req_id;
-		next_to_clean = ENA_TX_RING_IDX_NEXT(next_to_clean,
-						     xdp_ring->ring_size);
-	}
-
-	xdp_ring->next_to_clean = next_to_clean;
-	ena_com_comp_ack(xdp_ring->ena_com_io_sq, total_done);
-	ena_com_update_dev_comp_head(xdp_ring->ena_com_io_cq);
-
-	netif_dbg(xdp_ring->adapter, tx_done, xdp_ring->netdev,
-		  "tx_poll: q %d done. total pkts: %d\n",
-		  xdp_ring->qid, tx_pkts);
-
-	return tx_pkts;
-}
-
 static int ena_io_poll(struct napi_struct *napi, int budget)
 {
 	struct ena_napi *ena_napi = container_of(napi, struct ena_napi, napi);
@@ -2327,28 +1747,36 @@ static void ena_del_napi_in_range(struct ena_adapter *adapter,
 	for (i = first_index; i < first_index + count; i++) {
 		netif_napi_del(&adapter->ena_napi[i].napi);
 
-		WARN_ON(!ENA_IS_XDP_INDEX(adapter, i) &&
-			adapter->ena_napi[i].xdp_ring);
+		WARN_ON(ENA_IS_XDP_INDEX(adapter, i) &&
+			adapter->ena_napi[i].rx_ring);
 	}
 }
 
 static void ena_init_napi_in_range(struct ena_adapter *adapter,
 				   int first_index, int count)
 {
+	int (*napi_handler)(struct napi_struct *napi, int budget);
 	int i;
 
 	for (i = first_index; i < first_index + count; i++) {
 		struct ena_napi *napi = &adapter->ena_napi[i];
+		struct ena_ring *rx_ring, *tx_ring;
 
-		netif_napi_add(adapter->netdev, &napi->napi,
-			       ENA_IS_XDP_INDEX(adapter, i) ? ena_xdp_io_poll : ena_io_poll);
+		memset(napi, 0, sizeof(*napi));
 
-		if (!ENA_IS_XDP_INDEX(adapter, i)) {
-			napi->rx_ring = &adapter->rx_ring[i];
-			napi->tx_ring = &adapter->tx_ring[i];
-		} else {
-			napi->xdp_ring = &adapter->tx_ring[i];
-		}
+		rx_ring = &adapter->rx_ring[i];
+		tx_ring = &adapter->tx_ring[i];
+
+		napi_handler = ena_io_poll;
+		if (ENA_IS_XDP_INDEX(adapter, i))
+			napi_handler = ena_xdp_io_poll;
+
+		netif_napi_add(adapter->netdev, &napi->napi, napi_handler);
+
+		if (!ENA_IS_XDP_INDEX(adapter, i))
+			napi->rx_ring = rx_ring;
+
+		napi->tx_ring = tx_ring;
 		napi->qid = i;
 	}
 }
@@ -2476,8 +1904,8 @@ static int ena_create_io_tx_queue(struct ena_adapter *adapter, int qid)
 	return rc;
 }
 
-static int ena_create_io_tx_queues_in_range(struct ena_adapter *adapter,
-					    int first_index, int count)
+int ena_create_io_tx_queues_in_range(struct ena_adapter *adapter,
+				     int first_index, int count)
 {
 	struct ena_com_dev *ena_dev = adapter->ena_dev;
 	int rc, i;
@@ -2557,12 +1985,15 @@ static int ena_create_all_io_rx_queues(struct ena_adapter *adapter)
 		if (rc)
 			goto create_err;
 		INIT_WORK(&adapter->ena_napi[i].dim.work, ena_dim_work);
+
+		ena_xdp_register_rxq_info(&adapter->rx_ring[i]);
 	}
 
 	return 0;
 
 create_err:
 	while (i--) {
+		ena_xdp_unregister_rxq_info(&adapter->rx_ring[i]);
 		cancel_work_sync(&adapter->ena_napi[i].dim.work);
 		ena_com_destroy_io_queue(ena_dev, ENA_IO_RXQ_IDX(i));
 	}
@@ -2687,7 +2118,7 @@ err_setup_tx:
 	}
 }
 
-static int ena_up(struct ena_adapter *adapter)
+int ena_up(struct ena_adapter *adapter)
 {
 	int io_queue_count, rc, i;
 
@@ -2749,7 +2180,7 @@ err_req_irq:
 	return rc;
 }
 
-static void ena_down(struct ena_adapter *adapter)
+void ena_down(struct ena_adapter *adapter)
 {
 	int io_queue_count = adapter->num_io_queues + adapter->xdp_num_queues;
 
@@ -3180,7 +2611,7 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* set flags and meta data */
 	ena_tx_csum(&ena_tx_ctx, skb, tx_ring->disable_meta_caching);
 
-	rc = ena_xmit_common(dev,
+	rc = ena_xmit_common(adapter,
 			     tx_ring,
 			     tx_info,
 			     &ena_tx_ctx,
@@ -3276,8 +2707,8 @@ static void ena_config_host_info(struct ena_com_dev *ena_dev, struct pci_dev *pd
 	strscpy(host_info->kernel_ver_str, utsname()->version,
 		sizeof(host_info->kernel_ver_str) - 1);
 	host_info->os_dist = 0;
-	strncpy(host_info->os_dist_str, utsname()->release,
-		sizeof(host_info->os_dist_str) - 1);
+	strscpy(host_info->os_dist_str, utsname()->release,
+		sizeof(host_info->os_dist_str));
 	host_info->driver_version =
 		(DRV_MODULE_GEN_MAJOR) |
 		(DRV_MODULE_GEN_MINOR << ENA_ADMIN_HOST_INFO_MINOR_SHIFT) |
@@ -3364,6 +2795,7 @@ static void ena_get_stats64(struct net_device *netdev,
 {
 	struct ena_adapter *adapter = netdev_priv(netdev);
 	struct ena_ring *rx_ring, *tx_ring;
+	u64 total_xdp_rx_drops = 0;
 	unsigned int start;
 	u64 rx_drops;
 	u64 tx_drops;
@@ -3372,8 +2804,8 @@ static void ena_get_stats64(struct net_device *netdev,
 	if (!test_bit(ENA_FLAG_DEV_UP, &adapter->flags))
 		return;
 
-	for (i = 0; i < adapter->num_io_queues; i++) {
-		u64 bytes, packets;
+	for (i = 0; i < adapter->num_io_queues + adapter->xdp_num_queues; i++) {
+		u64 bytes, packets, xdp_rx_drops;
 
 		tx_ring = &adapter->tx_ring[i];
 
@@ -3386,16 +2818,22 @@ static void ena_get_stats64(struct net_device *netdev,
 		stats->tx_packets += packets;
 		stats->tx_bytes += bytes;
 
+		/* In XDP there isn't an RX queue counterpart */
+		if (ENA_IS_XDP_INDEX(adapter, i))
+			continue;
+
 		rx_ring = &adapter->rx_ring[i];
 
 		do {
 			start = u64_stats_fetch_begin(&rx_ring->syncp);
 			packets = rx_ring->rx_stats.cnt;
 			bytes = rx_ring->rx_stats.bytes;
+			xdp_rx_drops = rx_ring->rx_stats.xdp_drop;
 		} while (u64_stats_fetch_retry(&rx_ring->syncp, start));
 
 		stats->rx_packets += packets;
 		stats->rx_bytes += bytes;
+		total_xdp_rx_drops += xdp_rx_drops;
 	}
 
 	do {
@@ -3404,7 +2842,7 @@ static void ena_get_stats64(struct net_device *netdev,
 		tx_drops = adapter->dev_stats.tx_drops;
 	} while (u64_stats_fetch_retry(&adapter->syncp, start));
 
-	stats->rx_dropped = rx_drops;
+	stats->rx_dropped = rx_drops + total_xdp_rx_drops;
 	stats->tx_dropped = tx_drops;
 
 	stats->multicast = 0;
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 33c923e1261a..6d2cc20210cc 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -110,19 +110,6 @@
 
 #define ENA_MMIO_DISABLE_REG_READ	BIT(0)
 
-/* The max MTU size is configured to be the ethernet frame size without
- * the overhead of the ethernet header, which can have a VLAN header, and
- * a frame check sequence (FCS).
- * The buffer size we share with the device is defined to be ENA_PAGE_SIZE
- */
-
-#define ENA_XDP_MAX_MTU (ENA_PAGE_SIZE - ETH_HLEN - ETH_FCS_LEN -	\
-			 VLAN_HLEN - XDP_PACKET_HEADROOM -		\
-			 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
-
-#define ENA_IS_XDP_INDEX(adapter, index) (((index) >= (adapter)->xdp_first_ring) && \
-	((index) < (adapter)->xdp_first_ring + (adapter)->xdp_num_queues))
-
 struct ena_irq {
 	irq_handler_t handler;
 	void *data;
@@ -138,13 +125,18 @@ struct ena_napi {
 	struct napi_struct napi;
 	struct ena_ring *tx_ring;
 	struct ena_ring *rx_ring;
-	struct ena_ring *xdp_ring;
 	u32 qid;
 	struct dim dim;
 };
 
 struct ena_tx_buffer {
-	struct sk_buff *skb;
+	union {
+		struct sk_buff *skb;
+		/* XDP buffer structure which is used for sending packets in
+		 * the xdp queues
+		 */
+		struct xdp_frame *xdpf;
+	};
 	/* num of ena desc for this specific skb
 	 * (includes data desc and metadata desc)
 	 */
@@ -152,16 +144,14 @@ struct ena_tx_buffer {
 	/* num of buffers used by this skb */
 	u32 num_of_bufs;
 
-	/* XDP buffer structure which is used for sending packets in
-	 * the xdp queues
-	 */
-	struct xdp_frame *xdpf;
+	/* Total size of all buffers in bytes */
+	u32 total_tx_size;
 
 	/* Indicate if bufs[0] map the linear data of the skb. */
 	u8 map_linear_data;
 
 	/* Used for detect missing tx packets to limit the number of prints */
-	u32 print_once;
+	u8 print_once;
 	/* Save the last jiffies to detect missing tx packets
 	 *
 	 * sets to non zero value on ena_start_xmit and set to zero on
@@ -421,47 +411,44 @@ static inline void ena_reset_device(struct ena_adapter *adapter,
 	set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
 }
 
-enum ena_xdp_errors_t {
-	ENA_XDP_ALLOWED = 0,
-	ENA_XDP_CURRENT_MTU_TOO_LARGE,
-	ENA_XDP_NO_ENOUGH_QUEUES,
-};
+int handle_invalid_req_id(struct ena_ring *ring, u16 req_id,
+			  struct ena_tx_buffer *tx_info, bool is_xdp);
 
-enum ENA_XDP_ACTIONS {
-	ENA_XDP_PASS		= 0,
-	ENA_XDP_TX		= BIT(0),
-	ENA_XDP_REDIRECT	= BIT(1),
-	ENA_XDP_DROP		= BIT(2)
-};
-
-#define ENA_XDP_FORWARDED (ENA_XDP_TX | ENA_XDP_REDIRECT)
-
-static inline bool ena_xdp_present(struct ena_adapter *adapter)
-{
-	return !!adapter->xdp_bpf_prog;
-}
-
-static inline bool ena_xdp_present_ring(struct ena_ring *ring)
+/* Increase a stat by cnt while holding syncp seqlock on 32bit machines */
+static inline void ena_increase_stat(u64 *statp, u64 cnt,
+				     struct u64_stats_sync *syncp)
 {
-	return !!ring->xdp_bpf_prog;
+	u64_stats_update_begin(syncp);
+	(*statp) += cnt;
+	u64_stats_update_end(syncp);
 }
 
-static inline bool ena_xdp_legal_queue_count(struct ena_adapter *adapter,
-					     u32 queues)
+static inline void ena_ring_tx_doorbell(struct ena_ring *tx_ring)
 {
-	return 2 * queues <= adapter->max_num_io_queues;
-}
-
-static inline enum ena_xdp_errors_t ena_xdp_allowed(struct ena_adapter *adapter)
-{
-	enum ena_xdp_errors_t rc = ENA_XDP_ALLOWED;
-
-	if (adapter->netdev->mtu > ENA_XDP_MAX_MTU)
-		rc = ENA_XDP_CURRENT_MTU_TOO_LARGE;
-	else if (!ena_xdp_legal_queue_count(adapter, adapter->num_io_queues))
-		rc = ENA_XDP_NO_ENOUGH_QUEUES;
-
-	return rc;
+	ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq);
+	ena_increase_stat(&tx_ring->tx_stats.doorbells, 1, &tx_ring->syncp);
 }
 
+int ena_xmit_common(struct ena_adapter *adapter,
+		    struct ena_ring *ring,
+		    struct ena_tx_buffer *tx_info,
+		    struct ena_com_tx_ctx *ena_tx_ctx,
+		    u16 next_to_use,
+		    u32 bytes);
+void ena_unmap_tx_buff(struct ena_ring *tx_ring,
+		       struct ena_tx_buffer *tx_info);
+void ena_init_io_rings(struct ena_adapter *adapter,
+		       int first_index, int count);
+int ena_create_io_tx_queues_in_range(struct ena_adapter *adapter,
+				     int first_index, int count);
+int ena_setup_tx_resources_in_range(struct ena_adapter *adapter,
+				    int first_index, int count);
+void ena_free_all_io_tx_resources_in_range(struct ena_adapter *adapter,
+					   int first_index, int count);
+void ena_free_all_io_tx_resources(struct ena_adapter *adapter);
+void ena_down(struct ena_adapter *adapter);
+int ena_up(struct ena_adapter *adapter);
+void ena_unmask_interrupt(struct ena_ring *tx_ring, struct ena_ring *rx_ring);
+void ena_update_ring_numa_node(struct ena_ring *tx_ring,
+			       struct ena_ring *rx_ring);
 #endif /* !(ENA_H) */
diff --git a/drivers/net/ethernet/amazon/ena/ena_xdp.c b/drivers/net/ethernet/amazon/ena/ena_xdp.c
new file mode 100644
index 000000000000..fc1c4ef73ba3
--- /dev/null
+++ b/drivers/net/ethernet/amazon/ena/ena_xdp.c
@@ -0,0 +1,468 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright 2015-2021 Amazon.com, Inc. or its affiliates. All rights reserved.
+ */
+
+#include "ena_xdp.h"
+
+static int validate_xdp_req_id(struct ena_ring *tx_ring, u16 req_id)
+{
+	struct ena_tx_buffer *tx_info;
+
+	tx_info = &tx_ring->tx_buffer_info[req_id];
+	if (likely(tx_info->xdpf))
+		return 0;
+
+	return handle_invalid_req_id(tx_ring, req_id, tx_info, true);
+}
+
+static int ena_xdp_tx_map_frame(struct ena_ring *tx_ring,
+				struct ena_tx_buffer *tx_info,
+				struct xdp_frame *xdpf,
+				struct ena_com_tx_ctx *ena_tx_ctx)
+{
+	struct ena_adapter *adapter = tx_ring->adapter;
+	struct ena_com_buf *ena_buf;
+	int push_len = 0;
+	dma_addr_t dma;
+	void *data;
+	u32 size;
+
+	tx_info->xdpf = xdpf;
+	data = tx_info->xdpf->data;
+	size = tx_info->xdpf->len;
+
+	if (tx_ring->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV) {
+		/* Designate part of the packet for LLQ */
+		push_len = min_t(u32, size, tx_ring->tx_max_header_size);
+
+		ena_tx_ctx->push_header = data;
+
+		size -= push_len;
+		data += push_len;
+	}
+
+	ena_tx_ctx->header_len = push_len;
+
+	if (size > 0) {
+		dma = dma_map_single(tx_ring->dev,
+				     data,
+				     size,
+				     DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(tx_ring->dev, dma)))
+			goto error_report_dma_error;
+
+		tx_info->map_linear_data = 0;
+
+		ena_buf = tx_info->bufs;
+		ena_buf->paddr = dma;
+		ena_buf->len = size;
+
+		ena_tx_ctx->ena_bufs = ena_buf;
+		ena_tx_ctx->num_bufs = tx_info->num_of_bufs = 1;
+	}
+
+	return 0;
+
+error_report_dma_error:
+	ena_increase_stat(&tx_ring->tx_stats.dma_mapping_err, 1,
+			  &tx_ring->syncp);
+	netif_warn(adapter, tx_queued, adapter->netdev, "Failed to map xdp buff\n");
+
+	return -EINVAL;
+}
+
+int ena_xdp_xmit_frame(struct ena_ring *tx_ring,
+		       struct ena_adapter *adapter,
+		       struct xdp_frame *xdpf,
+		       int flags)
+{
+	struct ena_com_tx_ctx ena_tx_ctx = {};
+	struct ena_tx_buffer *tx_info;
+	u16 next_to_use, req_id;
+	int rc;
+
+	next_to_use = tx_ring->next_to_use;
+	req_id = tx_ring->free_ids[next_to_use];
+	tx_info = &tx_ring->tx_buffer_info[req_id];
+	tx_info->num_of_bufs = 0;
+
+	rc = ena_xdp_tx_map_frame(tx_ring, tx_info, xdpf, &ena_tx_ctx);
+	if (unlikely(rc))
+		return rc;
+
+	ena_tx_ctx.req_id = req_id;
+
+	rc = ena_xmit_common(adapter,
+			     tx_ring,
+			     tx_info,
+			     &ena_tx_ctx,
+			     next_to_use,
+			     xdpf->len);
+	if (rc)
+		goto error_unmap_dma;
+
+	/* trigger the dma engine. ena_ring_tx_doorbell()
+	 * calls a memory barrier inside it.
+	 */
+	if (flags & XDP_XMIT_FLUSH)
+		ena_ring_tx_doorbell(tx_ring);
+
+	return rc;
+
+error_unmap_dma:
+	ena_unmap_tx_buff(tx_ring, tx_info);
+	tx_info->xdpf = NULL;
+	return rc;
+}
+
+int ena_xdp_xmit(struct net_device *dev, int n,
+		 struct xdp_frame **frames, u32 flags)
+{
+	struct ena_adapter *adapter = netdev_priv(dev);
+	struct ena_ring *tx_ring;
+	int qid, i, nxmit = 0;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	if (!test_bit(ENA_FLAG_DEV_UP, &adapter->flags))
+		return -ENETDOWN;
+
+	/* We assume that all rings have the same XDP program */
+	if (!READ_ONCE(adapter->rx_ring->xdp_bpf_prog))
+		return -ENXIO;
+
+	qid = smp_processor_id() % adapter->xdp_num_queues;
+	qid += adapter->xdp_first_ring;
+	tx_ring = &adapter->tx_ring[qid];
+
+	/* Other CPU ids might try to send thorugh this queue */
+	spin_lock(&tx_ring->xdp_tx_lock);
+
+	for (i = 0; i < n; i++) {
+		if (ena_xdp_xmit_frame(tx_ring, adapter, frames[i], 0))
+			break;
+		nxmit++;
+	}
+
+	/* Ring doorbell to make device aware of the packets */
+	if (flags & XDP_XMIT_FLUSH)
+		ena_ring_tx_doorbell(tx_ring);
+
+	spin_unlock(&tx_ring->xdp_tx_lock);
+
+	/* Return number of packets sent */
+	return nxmit;
+}
+
+static void ena_init_all_xdp_queues(struct ena_adapter *adapter)
+{
+	adapter->xdp_first_ring = adapter->num_io_queues;
+	adapter->xdp_num_queues = adapter->num_io_queues;
+
+	ena_init_io_rings(adapter,
+			  adapter->xdp_first_ring,
+			  adapter->xdp_num_queues);
+}
+
+int ena_setup_and_create_all_xdp_queues(struct ena_adapter *adapter)
+{
+	u32 xdp_first_ring = adapter->xdp_first_ring;
+	u32 xdp_num_queues = adapter->xdp_num_queues;
+	int rc = 0;
+
+	rc = ena_setup_tx_resources_in_range(adapter, xdp_first_ring, xdp_num_queues);
+	if (rc)
+		goto setup_err;
+
+	rc = ena_create_io_tx_queues_in_range(adapter, xdp_first_ring, xdp_num_queues);
+	if (rc)
+		goto create_err;
+
+	return 0;
+
+create_err:
+	ena_free_all_io_tx_resources_in_range(adapter, xdp_first_ring, xdp_num_queues);
+setup_err:
+	return rc;
+}
+
+/* Provides a way for both kernel and bpf-prog to know
+ * more about the RX-queue a given XDP frame arrived on.
+ */
+int ena_xdp_register_rxq_info(struct ena_ring *rx_ring)
+{
+	int rc;
+
+	rc = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, rx_ring->qid, 0);
+
+	netif_dbg(rx_ring->adapter, ifup, rx_ring->netdev, "Registering RX info for queue %d",
+		  rx_ring->qid);
+	if (rc) {
+		netif_err(rx_ring->adapter, ifup, rx_ring->netdev,
+			  "Failed to register xdp rx queue info. RX queue num %d rc: %d\n",
+			  rx_ring->qid, rc);
+		goto err;
+	}
+
+	rc = xdp_rxq_info_reg_mem_model(&rx_ring->xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL);
+
+	if (rc) {
+		netif_err(rx_ring->adapter, ifup, rx_ring->netdev,
+			  "Failed to register xdp rx queue info memory model. RX queue num %d rc: %d\n",
+			  rx_ring->qid, rc);
+		xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
+	}
+
+err:
+	return rc;
+}
+
+void ena_xdp_unregister_rxq_info(struct ena_ring *rx_ring)
+{
+	netif_dbg(rx_ring->adapter, ifdown, rx_ring->netdev,
+		  "Unregistering RX info for queue %d",
+		  rx_ring->qid);
+	xdp_rxq_info_unreg_mem_model(&rx_ring->xdp_rxq);
+	xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
+}
+
+void ena_xdp_exchange_program_rx_in_range(struct ena_adapter *adapter,
+					  struct bpf_prog *prog,
+					  int first, int count)
+{
+	struct bpf_prog *old_bpf_prog;
+	struct ena_ring *rx_ring;
+	int i = 0;
+
+	for (i = first; i < count; i++) {
+		rx_ring = &adapter->rx_ring[i];
+		old_bpf_prog = xchg(&rx_ring->xdp_bpf_prog, prog);
+
+		if (!old_bpf_prog && prog) {
+			rx_ring->rx_headroom = XDP_PACKET_HEADROOM;
+		} else if (old_bpf_prog && !prog) {
+			rx_ring->rx_headroom = NET_SKB_PAD;
+		}
+	}
+}
+
+static void ena_xdp_exchange_program(struct ena_adapter *adapter,
+				     struct bpf_prog *prog)
+{
+	struct bpf_prog *old_bpf_prog = xchg(&adapter->xdp_bpf_prog, prog);
+
+	ena_xdp_exchange_program_rx_in_range(adapter,
+					     prog,
+					     0,
+					     adapter->num_io_queues);
+
+	if (old_bpf_prog)
+		bpf_prog_put(old_bpf_prog);
+}
+
+static int ena_destroy_and_free_all_xdp_queues(struct ena_adapter *adapter)
+{
+	bool was_up;
+	int rc;
+
+	was_up = test_bit(ENA_FLAG_DEV_UP, &adapter->flags);
+
+	if (was_up)
+		ena_down(adapter);
+
+	adapter->xdp_first_ring = 0;
+	adapter->xdp_num_queues = 0;
+	ena_xdp_exchange_program(adapter, NULL);
+	if (was_up) {
+		rc = ena_up(adapter);
+		if (rc)
+			return rc;
+	}
+	return 0;
+}
+
+static int ena_xdp_set(struct net_device *netdev, struct netdev_bpf *bpf)
+{
+	struct ena_adapter *adapter = netdev_priv(netdev);
+	struct bpf_prog *prog = bpf->prog;
+	struct bpf_prog *old_bpf_prog;
+	int rc, prev_mtu;
+	bool is_up;
+
+	is_up = test_bit(ENA_FLAG_DEV_UP, &adapter->flags);
+	rc = ena_xdp_allowed(adapter);
+	if (rc == ENA_XDP_ALLOWED) {
+		old_bpf_prog = adapter->xdp_bpf_prog;
+		if (prog) {
+			if (!is_up) {
+				ena_init_all_xdp_queues(adapter);
+			} else if (!old_bpf_prog) {
+				ena_down(adapter);
+				ena_init_all_xdp_queues(adapter);
+			}
+			ena_xdp_exchange_program(adapter, prog);
+
+			netif_dbg(adapter, drv, adapter->netdev, "Set a new XDP program\n");
+
+			if (is_up && !old_bpf_prog) {
+				rc = ena_up(adapter);
+				if (rc)
+					return rc;
+			}
+			xdp_features_set_redirect_target(netdev, false);
+		} else if (old_bpf_prog) {
+			xdp_features_clear_redirect_target(netdev);
+			netif_dbg(adapter, drv, adapter->netdev, "Removing XDP program\n");
+
+			rc = ena_destroy_and_free_all_xdp_queues(adapter);
+			if (rc)
+				return rc;
+		}
+
+		prev_mtu = netdev->max_mtu;
+		netdev->max_mtu = prog ? ENA_XDP_MAX_MTU : adapter->max_mtu;
+
+		if (!old_bpf_prog)
+			netif_info(adapter, drv, adapter->netdev,
+				   "XDP program is set, changing the max_mtu from %d to %d",
+				   prev_mtu, netdev->max_mtu);
+
+	} else if (rc == ENA_XDP_CURRENT_MTU_TOO_LARGE) {
+		netif_err(adapter, drv, adapter->netdev,
+			  "Failed to set xdp program, the current MTU (%d) is larger than the maximum allowed MTU (%lu) while xdp is on",
+			  netdev->mtu, ENA_XDP_MAX_MTU);
+		NL_SET_ERR_MSG_MOD(bpf->extack,
+				   "Failed to set xdp program, the current MTU is larger than the maximum allowed MTU. Check the dmesg for more info");
+		return -EINVAL;
+	} else if (rc == ENA_XDP_NO_ENOUGH_QUEUES) {
+		netif_err(adapter, drv, adapter->netdev,
+			  "Failed to set xdp program, the Rx/Tx channel count should be at most half of the maximum allowed channel count. The current queue count (%d), the maximal queue count (%d)\n",
+			  adapter->num_io_queues, adapter->max_num_io_queues);
+		NL_SET_ERR_MSG_MOD(bpf->extack,
+				   "Failed to set xdp program, there is no enough space for allocating XDP queues, Check the dmesg for more info");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/* This is the main xdp callback, it's used by the kernel to set/unset the xdp
+ * program as well as to query the current xdp program id.
+ */
+int ena_xdp(struct net_device *netdev, struct netdev_bpf *bpf)
+{
+	switch (bpf->command) {
+	case XDP_SETUP_PROG:
+		return ena_xdp_set(netdev, bpf);
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int ena_clean_xdp_irq(struct ena_ring *tx_ring, u32 budget)
+{
+	u32 total_done = 0;
+	u16 next_to_clean;
+	int tx_pkts = 0;
+	u16 req_id;
+	int rc;
+
+	if (unlikely(!tx_ring))
+		return 0;
+	next_to_clean = tx_ring->next_to_clean;
+
+	while (tx_pkts < budget) {
+		struct ena_tx_buffer *tx_info;
+		struct xdp_frame *xdpf;
+
+		rc = ena_com_tx_comp_req_id_get(tx_ring->ena_com_io_cq,
+						&req_id);
+		if (rc) {
+			if (unlikely(rc == -EINVAL))
+				handle_invalid_req_id(tx_ring, req_id, NULL, true);
+			break;
+		}
+
+		/* validate that the request id points to a valid xdp_frame */
+		rc = validate_xdp_req_id(tx_ring, req_id);
+		if (rc)
+			break;
+
+		tx_info = &tx_ring->tx_buffer_info[req_id];
+
+		tx_info->last_jiffies = 0;
+
+		xdpf = tx_info->xdpf;
+		tx_info->xdpf = NULL;
+		ena_unmap_tx_buff(tx_ring, tx_info);
+		xdp_return_frame(xdpf);
+
+		tx_pkts++;
+		total_done += tx_info->tx_descs;
+		tx_ring->free_ids[next_to_clean] = req_id;
+		next_to_clean = ENA_TX_RING_IDX_NEXT(next_to_clean,
+						     tx_ring->ring_size);
+
+		netif_dbg(tx_ring->adapter, tx_done, tx_ring->netdev,
+			  "tx_poll: q %d pkt #%d req_id %d\n", tx_ring->qid, tx_pkts, req_id);
+	}
+
+	tx_ring->next_to_clean = next_to_clean;
+	ena_com_comp_ack(tx_ring->ena_com_io_sq, total_done);
+	ena_com_update_dev_comp_head(tx_ring->ena_com_io_cq);
+
+	netif_dbg(tx_ring->adapter, tx_done, tx_ring->netdev,
+		  "tx_poll: q %d done. total pkts: %d\n",
+		  tx_ring->qid, tx_pkts);
+
+	return tx_pkts;
+}
+
+/* This is the XDP napi callback. XDP queues use a separate napi callback
+ * than Rx/Tx queues.
+ */
+int ena_xdp_io_poll(struct napi_struct *napi, int budget)
+{
+	struct ena_napi *ena_napi = container_of(napi, struct ena_napi, napi);
+	struct ena_ring *tx_ring;
+	u32 work_done;
+	int ret;
+
+	tx_ring = ena_napi->tx_ring;
+
+	if (!test_bit(ENA_FLAG_DEV_UP, &tx_ring->adapter->flags) ||
+	    test_bit(ENA_FLAG_TRIGGER_RESET, &tx_ring->adapter->flags)) {
+		napi_complete_done(napi, 0);
+		return 0;
+	}
+
+	work_done = ena_clean_xdp_irq(tx_ring, budget);
+
+	/* If the device is about to reset or down, avoid unmask
+	 * the interrupt and return 0 so NAPI won't reschedule
+	 */
+	if (unlikely(!test_bit(ENA_FLAG_DEV_UP, &tx_ring->adapter->flags))) {
+		napi_complete_done(napi, 0);
+		ret = 0;
+	} else if (budget > work_done) {
+		ena_increase_stat(&tx_ring->tx_stats.napi_comp, 1,
+				  &tx_ring->syncp);
+		if (napi_complete_done(napi, work_done))
+			ena_unmask_interrupt(tx_ring, NULL);
+
+		ena_update_ring_numa_node(tx_ring, NULL);
+		ret = work_done;
+	} else {
+		ret = budget;
+	}
+
+	u64_stats_update_begin(&tx_ring->syncp);
+	tx_ring->tx_stats.tx_poll++;
+	u64_stats_update_end(&tx_ring->syncp);
+	tx_ring->tx_stats.last_napi_jiffies = jiffies;
+
+	return ret;
+}
diff --git a/drivers/net/ethernet/amazon/ena/ena_xdp.h b/drivers/net/ethernet/amazon/ena/ena_xdp.h
new file mode 100644
index 000000000000..cfd82728486a
--- /dev/null
+++ b/drivers/net/ethernet/amazon/ena/ena_xdp.h
@@ -0,0 +1,151 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/*
+ * Copyright 2015-2021 Amazon.com, Inc. or its affiliates. All rights reserved.
+ */
+
+#ifndef ENA_XDP_H
+#define ENA_XDP_H
+
+#include "ena_netdev.h"
+#include <linux/bpf_trace.h>
+
+/* The max MTU size is configured to be the ethernet frame size without
+ * the overhead of the ethernet header, which can have a VLAN header, and
+ * a frame check sequence (FCS).
+ * The buffer size we share with the device is defined to be ENA_PAGE_SIZE
+ */
+#define ENA_XDP_MAX_MTU (ENA_PAGE_SIZE - ETH_HLEN - ETH_FCS_LEN -	\
+			 VLAN_HLEN - XDP_PACKET_HEADROOM -		\
+			 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+
+#define ENA_IS_XDP_INDEX(adapter, index) (((index) >= (adapter)->xdp_first_ring) && \
+	((index) < (adapter)->xdp_first_ring + (adapter)->xdp_num_queues))
+
+enum ENA_XDP_ACTIONS {
+	ENA_XDP_PASS		= 0,
+	ENA_XDP_TX		= BIT(0),
+	ENA_XDP_REDIRECT	= BIT(1),
+	ENA_XDP_DROP		= BIT(2)
+};
+
+#define ENA_XDP_FORWARDED (ENA_XDP_TX | ENA_XDP_REDIRECT)
+
+int ena_setup_and_create_all_xdp_queues(struct ena_adapter *adapter);
+void ena_xdp_exchange_program_rx_in_range(struct ena_adapter *adapter,
+					  struct bpf_prog *prog,
+					  int first, int count);
+int ena_xdp_io_poll(struct napi_struct *napi, int budget);
+int ena_xdp_xmit_frame(struct ena_ring *tx_ring,
+		       struct ena_adapter *adapter,
+		       struct xdp_frame *xdpf,
+		       int flags);
+int ena_xdp_xmit(struct net_device *dev, int n,
+		 struct xdp_frame **frames, u32 flags);
+int ena_xdp(struct net_device *netdev, struct netdev_bpf *bpf);
+int ena_xdp_register_rxq_info(struct ena_ring *rx_ring);
+void ena_xdp_unregister_rxq_info(struct ena_ring *rx_ring);
+
+enum ena_xdp_errors_t {
+	ENA_XDP_ALLOWED = 0,
+	ENA_XDP_CURRENT_MTU_TOO_LARGE,
+	ENA_XDP_NO_ENOUGH_QUEUES,
+};
+
+static inline bool ena_xdp_present(struct ena_adapter *adapter)
+{
+	return !!adapter->xdp_bpf_prog;
+}
+
+static inline bool ena_xdp_present_ring(struct ena_ring *ring)
+{
+	return !!ring->xdp_bpf_prog;
+}
+
+static inline bool ena_xdp_legal_queue_count(struct ena_adapter *adapter,
+					     u32 queues)
+{
+	return 2 * queues <= adapter->max_num_io_queues;
+}
+
+static inline enum ena_xdp_errors_t ena_xdp_allowed(struct ena_adapter *adapter)
+{
+	enum ena_xdp_errors_t rc = ENA_XDP_ALLOWED;
+
+	if (adapter->netdev->mtu > ENA_XDP_MAX_MTU)
+		rc = ENA_XDP_CURRENT_MTU_TOO_LARGE;
+	else if (!ena_xdp_legal_queue_count(adapter, adapter->num_io_queues))
+		rc = ENA_XDP_NO_ENOUGH_QUEUES;
+
+	return rc;
+}
+
+static inline int ena_xdp_execute(struct ena_ring *rx_ring, struct xdp_buff *xdp)
+{
+	u32 verdict = ENA_XDP_PASS;
+	struct bpf_prog *xdp_prog;
+	struct ena_ring *xdp_ring;
+	struct xdp_frame *xdpf;
+	u64 *xdp_stat;
+
+	xdp_prog = READ_ONCE(rx_ring->xdp_bpf_prog);
+
+	verdict = bpf_prog_run_xdp(xdp_prog, xdp);
+
+	switch (verdict) {
+	case XDP_TX:
+		xdpf = xdp_convert_buff_to_frame(xdp);
+		if (unlikely(!xdpf)) {
+			trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict);
+			xdp_stat = &rx_ring->rx_stats.xdp_aborted;
+			verdict = ENA_XDP_DROP;
+			break;
+		}
+
+		/* Find xmit queue */
+		xdp_ring = rx_ring->xdp_ring;
+
+		/* The XDP queues are shared between XDP_TX and XDP_REDIRECT */
+		spin_lock(&xdp_ring->xdp_tx_lock);
+
+		if (ena_xdp_xmit_frame(xdp_ring, rx_ring->adapter, xdpf,
+				       XDP_XMIT_FLUSH))
+			xdp_return_frame(xdpf);
+
+		spin_unlock(&xdp_ring->xdp_tx_lock);
+		xdp_stat = &rx_ring->rx_stats.xdp_tx;
+		verdict = ENA_XDP_TX;
+		break;
+	case XDP_REDIRECT:
+		if (likely(!xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog))) {
+			xdp_stat = &rx_ring->rx_stats.xdp_redirect;
+			verdict = ENA_XDP_REDIRECT;
+			break;
+		}
+		trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict);
+		xdp_stat = &rx_ring->rx_stats.xdp_aborted;
+		verdict = ENA_XDP_DROP;
+		break;
+	case XDP_ABORTED:
+		trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict);
+		xdp_stat = &rx_ring->rx_stats.xdp_aborted;
+		verdict = ENA_XDP_DROP;
+		break;
+	case XDP_DROP:
+		xdp_stat = &rx_ring->rx_stats.xdp_drop;
+		verdict = ENA_XDP_DROP;
+		break;
+	case XDP_PASS:
+		xdp_stat = &rx_ring->rx_stats.xdp_pass;
+		verdict = ENA_XDP_PASS;
+		break;
+	default:
+		bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, verdict);
+		xdp_stat = &rx_ring->rx_stats.xdp_invalid;
+		verdict = ENA_XDP_DROP;
+	}
+
+	ena_increase_stat(xdp_stat, 1, &rx_ring->syncp);
+
+	return verdict;
+}
+#endif /* ENA_XDP_H */
diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c
index 045fe133f6ee..5beadabc2136 100644
--- a/drivers/net/ethernet/amd/pds_core/adminq.c
+++ b/drivers/net/ethernet/amd/pds_core/adminq.c
@@ -146,7 +146,7 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data)
 	}
 
 	queue_work(pdsc->wq, &qcq->work);
-	pds_core_intr_mask(&pdsc->intr_ctrl[irq], PDS_CORE_INTR_MASK_CLEAR);
+	pds_core_intr_mask(&pdsc->intr_ctrl[qcq->intx], PDS_CORE_INTR_MASK_CLEAR);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h
index f3a7deda9972..e35d3e7006bf 100644
--- a/drivers/net/ethernet/amd/pds_core/core.h
+++ b/drivers/net/ethernet/amd/pds_core/core.h
@@ -15,7 +15,7 @@
 #define PDSC_DRV_DESCRIPTION	"AMD/Pensando Core Driver"
 
 #define PDSC_WATCHDOG_SECS	5
-#define PDSC_QUEUE_NAME_MAX_SZ  32
+#define PDSC_QUEUE_NAME_MAX_SZ  16
 #define PDSC_ADMINQ_MIN_LENGTH	16	/* must be a power of two */
 #define PDSC_NOTIFYQ_LENGTH	64	/* must be a power of two */
 #define PDSC_TEARDOWN_RECOVERY	false
diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c
index 7c1b965d61a9..31940b857e0e 100644
--- a/drivers/net/ethernet/amd/pds_core/dev.c
+++ b/drivers/net/ethernet/amd/pds_core/dev.c
@@ -261,10 +261,14 @@ static int pdsc_identify(struct pdsc *pdsc)
 	struct pds_core_drv_identity drv = {};
 	size_t sz;
 	int err;
+	int n;
 
 	drv.drv_type = cpu_to_le32(PDS_DRIVER_LINUX);
-	snprintf(drv.driver_ver_str, sizeof(drv.driver_ver_str),
-		 "%s %s", PDS_CORE_DRV_NAME, utsname()->release);
+	/* Catching the return quiets a Wformat-truncation complaint */
+	n = snprintf(drv.driver_ver_str, sizeof(drv.driver_ver_str),
+		     "%s %s", PDS_CORE_DRV_NAME, utsname()->release);
+	if (n > sizeof(drv.driver_ver_str))
+		dev_dbg(pdsc->dev, "release name truncated, don't care\n");
 
 	/* Next let's get some info about the device
 	 * We use the devcmd_lock at this level in order to
diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c
index 57f88c8b37de..e9948ea5bbcd 100644
--- a/drivers/net/ethernet/amd/pds_core/devlink.c
+++ b/drivers/net/ethernet/amd/pds_core/devlink.c
@@ -104,7 +104,7 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 	struct pds_core_fw_list_info fw_list;
 	struct pdsc *pdsc = devlink_priv(dl);
 	union pds_core_dev_comp comp;
-	char buf[16];
+	char buf[32];
 	int listlen;
 	int err;
 	int i;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 614c0278419b..6b73648b3779 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -682,10 +682,24 @@ static void xgbe_service(struct work_struct *work)
 static void xgbe_service_timer(struct timer_list *t)
 {
 	struct xgbe_prv_data *pdata = from_timer(pdata, t, service_timer);
+	struct xgbe_channel *channel;
+	unsigned int i;
 
 	queue_work(pdata->dev_workqueue, &pdata->service_work);
 
 	mod_timer(&pdata->service_timer, jiffies + HZ);
+
+	if (!pdata->tx_usecs)
+		return;
+
+	for (i = 0; i < pdata->channel_count; i++) {
+		channel = pdata->channel[i];
+		if (!channel->tx_ring || channel->tx_timer_active)
+			break;
+		channel->tx_timer_active = 1;
+		mod_timer(&channel->tx_timer,
+			  jiffies + usecs_to_jiffies(pdata->tx_usecs));
+	}
 }
 
 static void xgbe_init_timers(struct xgbe_prv_data *pdata)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
index 6e83ff59172a..58e7e88aae5b 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
@@ -314,10 +314,15 @@ static int xgbe_get_link_ksettings(struct net_device *netdev,
 
 	cmd->base.phy_address = pdata->phy.address;
 
-	cmd->base.autoneg = pdata->phy.autoneg;
-	cmd->base.speed = pdata->phy.speed;
-	cmd->base.duplex = pdata->phy.duplex;
+	if (netif_carrier_ok(netdev)) {
+		cmd->base.speed = pdata->phy.speed;
+		cmd->base.duplex = pdata->phy.duplex;
+	} else {
+		cmd->base.speed = SPEED_UNKNOWN;
+		cmd->base.duplex = DUPLEX_UNKNOWN;
+	}
 
+	cmd->base.autoneg = pdata->phy.autoneg;
 	cmd->base.port = PORT_NONE;
 
 	XGBE_LM_COPY(cmd, supported, lks, supported);
@@ -522,47 +527,48 @@ static u32 xgbe_get_rxfh_indir_size(struct net_device *netdev)
 	return ARRAY_SIZE(pdata->rss_table);
 }
 
-static int xgbe_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			 u8 *hfunc)
+static int xgbe_get_rxfh(struct net_device *netdev,
+			 struct ethtool_rxfh_param *rxfh)
 {
 	struct xgbe_prv_data *pdata = netdev_priv(netdev);
 	unsigned int i;
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < ARRAY_SIZE(pdata->rss_table); i++)
-			indir[i] = XGMAC_GET_BITS(pdata->rss_table[i],
-						  MAC_RSSDR, DMCH);
+			rxfh->indir[i] = XGMAC_GET_BITS(pdata->rss_table[i],
+							MAC_RSSDR, DMCH);
 	}
 
-	if (key)
-		memcpy(key, pdata->rss_key, sizeof(pdata->rss_key));
+	if (rxfh->key)
+		memcpy(rxfh->key, pdata->rss_key, sizeof(pdata->rss_key));
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	return 0;
 }
 
-static int xgbe_set_rxfh(struct net_device *netdev, const u32 *indir,
-			 const u8 *key, const u8 hfunc)
+static int xgbe_set_rxfh(struct net_device *netdev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
 	struct xgbe_prv_data *pdata = netdev_priv(netdev);
 	struct xgbe_hw_if *hw_if = &pdata->hw_if;
 	unsigned int ret;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) {
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP) {
 		netdev_err(netdev, "unsupported hash function\n");
 		return -EOPNOTSUPP;
 	}
 
-	if (indir) {
-		ret = hw_if->set_rss_lookup_table(pdata, indir);
+	if (rxfh->indir) {
+		ret = hw_if->set_rss_lookup_table(pdata, rxfh->indir);
 		if (ret)
 			return ret;
 	}
 
-	if (key) {
-		ret = hw_if->set_rss_hash_key(pdata, key);
+	if (rxfh->key) {
+		ret = hw_if->set_rss_hash_key(pdata, rxfh->key);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 32d2c6fac652..4a2dc705b528 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -1193,7 +1193,19 @@ static int xgbe_phy_config_fixed(struct xgbe_prv_data *pdata)
 	if (pdata->phy.duplex != DUPLEX_FULL)
 		return -EINVAL;
 
-	xgbe_set_mode(pdata, mode);
+	/* Force the mode change for SFI in Fixed PHY config.
+	 * Fixed PHY configs needs PLL to be enabled while doing mode set.
+	 * When the SFP module isn't connected during boot, driver assumes
+	 * AN is ON and attempts autonegotiation. However, if the connected
+	 * SFP comes up in Fixed PHY config, the link will not come up as
+	 * PLL isn't enabled while the initial mode set command is issued.
+	 * So, force the mode change for SFI in Fixed PHY configuration to
+	 * fix link issues.
+	 */
+	if (mode == XGBE_MODE_SFI)
+		xgbe_change_mode(pdata, mode);
+	else
+		xgbe_set_mode(pdata, mode);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index ad136ed493ed..f01a1e566da6 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -495,7 +495,7 @@ struct xgbe_ring {
  * a DMA channel.
  */
 struct xgbe_channel {
-	char name[16];
+	char name[20];
 
 	/* Address of private data area for device */
 	struct xgbe_prv_data *pdata;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index ac4ea93bd8dd..18a6c8d99fa0 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -447,8 +447,8 @@ static u32 aq_ethtool_get_rss_key_size(struct net_device *ndev)
 	return sizeof(cfg->aq_rss.hash_secret_key);
 }
 
-static int aq_ethtool_get_rss(struct net_device *ndev, u32 *indir, u8 *key,
-			      u8 *hfunc)
+static int aq_ethtool_get_rss(struct net_device *ndev,
+			      struct ethtool_rxfh_param *rxfh)
 {
 	struct aq_nic_s *aq_nic = netdev_priv(ndev);
 	struct aq_nic_cfg_s *cfg;
@@ -456,21 +456,21 @@ static int aq_ethtool_get_rss(struct net_device *ndev, u32 *indir, u8 *key,
 
 	cfg = aq_nic_get_cfg(aq_nic);
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP; /* Toeplitz */
-	if (indir) {
+	rxfh->hfunc = ETH_RSS_HASH_TOP; /* Toeplitz */
+	if (rxfh->indir) {
 		for (i = 0; i < AQ_CFG_RSS_INDIRECTION_TABLE_MAX; i++)
-			indir[i] = cfg->aq_rss.indirection_table[i];
+			rxfh->indir[i] = cfg->aq_rss.indirection_table[i];
 	}
-	if (key)
-		memcpy(key, cfg->aq_rss.hash_secret_key,
+	if (rxfh->key)
+		memcpy(rxfh->key, cfg->aq_rss.hash_secret_key,
 		       sizeof(cfg->aq_rss.hash_secret_key));
 
 	return 0;
 }
 
-static int aq_ethtool_set_rss(struct net_device *netdev, const u32 *indir,
-			      const u8 *key, const u8 hfunc)
+static int aq_ethtool_set_rss(struct net_device *netdev,
+			      struct ethtool_rxfh_param *rxfh,
+			      struct netlink_ext_ack *extack)
 {
 	struct aq_nic_s *aq_nic = netdev_priv(netdev);
 	struct aq_nic_cfg_s *cfg;
@@ -482,16 +482,17 @@ static int aq_ethtool_set_rss(struct net_device *netdev, const u32 *indir,
 	rss_entries = cfg->aq_rss.indirection_table_size;
 
 	/* We do not allow change in unsupported parameters */
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 	/* Fill out the redirection table */
-	if (indir)
+	if (rxfh->indir)
 		for (i = 0; i < rss_entries; i++)
-			cfg->aq_rss.indirection_table[i] = indir[i];
+			cfg->aq_rss.indirection_table[i] = rxfh->indir[i];
 
 	/* Fill out the rss hash key */
-	if (key) {
-		memcpy(cfg->aq_rss.hash_secret_key, key,
+	if (rxfh->key) {
+		memcpy(cfg->aq_rss.hash_secret_key, rxfh->key,
 		       sizeof(cfg->aq_rss.hash_secret_key));
 		err = aq_nic->aq_hw_ops->hw_rss_hash_set(aq_nic->aq_hw,
 			&cfg->aq_rss);
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
index 80b44043e6c5..abd4832e4ed2 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
@@ -553,17 +553,17 @@ void aq_ptp_tx_hwtstamp(struct aq_nic_s *aq_nic, u64 timestamp)
 
 /* aq_ptp_rx_hwtstamp - utility function which checks for RX time stamp
  * @adapter: pointer to adapter struct
- * @skb: particular skb to send timestamp with
+ * @shhwtstamps: particular skb_shared_hwtstamps to save timestamp
  *
  * if the timestamp is valid, we convert it into the timecounter ns
  * value, then store that result into the hwtstamps structure which
  * is passed up the network stack
  */
-static void aq_ptp_rx_hwtstamp(struct aq_ptp_s *aq_ptp, struct sk_buff *skb,
+static void aq_ptp_rx_hwtstamp(struct aq_ptp_s *aq_ptp, struct skb_shared_hwtstamps *shhwtstamps,
 			       u64 timestamp)
 {
 	timestamp -= atomic_read(&aq_ptp->offset_ingress);
-	aq_ptp_convert_to_hwtstamp(aq_ptp, skb_hwtstamps(skb), timestamp);
+	aq_ptp_convert_to_hwtstamp(aq_ptp, shhwtstamps, timestamp);
 }
 
 void aq_ptp_hwtstamp_config_get(struct aq_ptp_s *aq_ptp,
@@ -639,7 +639,7 @@ bool aq_ptp_ring(struct aq_nic_s *aq_nic, struct aq_ring_s *ring)
 	       &aq_ptp->ptp_rx == ring || &aq_ptp->hwts_rx == ring;
 }
 
-u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, struct sk_buff *skb, u8 *p,
+u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, struct skb_shared_hwtstamps *shhwtstamps, u8 *p,
 		      unsigned int len)
 {
 	struct aq_ptp_s *aq_ptp = aq_nic->aq_ptp;
@@ -648,7 +648,7 @@ u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, struct sk_buff *skb, u8 *p,
 						   p, len, &timestamp);
 
 	if (ret > 0)
-		aq_ptp_rx_hwtstamp(aq_ptp, skb, timestamp);
+		aq_ptp_rx_hwtstamp(aq_ptp, shhwtstamps, timestamp);
 
 	return ret;
 }
@@ -953,8 +953,6 @@ int aq_ptp_ring_alloc(struct aq_nic_s *aq_nic)
 {
 	struct aq_ptp_s *aq_ptp = aq_nic->aq_ptp;
 	unsigned int tx_ring_idx, rx_ring_idx;
-	struct aq_ring_s *hwts;
-	struct aq_ring_s *ring;
 	int err;
 
 	if (!aq_ptp)
@@ -962,29 +960,23 @@ int aq_ptp_ring_alloc(struct aq_nic_s *aq_nic)
 
 	tx_ring_idx = aq_ptp_ring_idx(aq_nic->aq_nic_cfg.tc_mode);
 
-	ring = aq_ring_tx_alloc(&aq_ptp->ptp_tx, aq_nic,
-				tx_ring_idx, &aq_nic->aq_nic_cfg);
-	if (!ring) {
-		err = -ENOMEM;
+	err = aq_ring_tx_alloc(&aq_ptp->ptp_tx, aq_nic,
+			       tx_ring_idx, &aq_nic->aq_nic_cfg);
+	if (err)
 		goto err_exit;
-	}
 
 	rx_ring_idx = aq_ptp_ring_idx(aq_nic->aq_nic_cfg.tc_mode);
 
-	ring = aq_ring_rx_alloc(&aq_ptp->ptp_rx, aq_nic,
-				rx_ring_idx, &aq_nic->aq_nic_cfg);
-	if (!ring) {
-		err = -ENOMEM;
+	err = aq_ring_rx_alloc(&aq_ptp->ptp_rx, aq_nic,
+			       rx_ring_idx, &aq_nic->aq_nic_cfg);
+	if (err)
 		goto err_exit_ptp_tx;
-	}
 
-	hwts = aq_ring_hwts_rx_alloc(&aq_ptp->hwts_rx, aq_nic, PTP_HWST_RING_IDX,
-				     aq_nic->aq_nic_cfg.rxds,
-				     aq_nic->aq_nic_cfg.aq_hw_caps->rxd_size);
-	if (!hwts) {
-		err = -ENOMEM;
+	err = aq_ring_hwts_rx_alloc(&aq_ptp->hwts_rx, aq_nic, PTP_HWST_RING_IDX,
+				    aq_nic->aq_nic_cfg.rxds,
+				    aq_nic->aq_nic_cfg.aq_hw_caps->rxd_size);
+	if (err)
 		goto err_exit_ptp_rx;
-	}
 
 	err = aq_ptp_skb_ring_init(&aq_ptp->skb_ring, aq_nic->aq_nic_cfg.rxds);
 	if (err != 0) {
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h
index 28ccb7ca2df9..210b723f2207 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h
@@ -67,7 +67,7 @@ int aq_ptp_hwtstamp_config_set(struct aq_ptp_s *aq_ptp,
 /* Return either ring is belong to PTP or not*/
 bool aq_ptp_ring(struct aq_nic_s *aq_nic, struct aq_ring_s *ring);
 
-u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, struct sk_buff *skb, u8 *p,
+u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, struct skb_shared_hwtstamps *shhwtstamps, u8 *p,
 		      unsigned int len);
 
 struct ptp_clock *aq_ptp_get_ptp_clock(struct aq_ptp_s *aq_ptp);
@@ -143,7 +143,7 @@ static inline bool aq_ptp_ring(struct aq_nic_s *aq_nic, struct aq_ring_s *ring)
 }
 
 static inline u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic,
-				    struct sk_buff *skb, u8 *p,
+				    struct skb_shared_hwtstamps *shhwtstamps, u8 *p,
 				    unsigned int len)
 {
 	return 0;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 4de22eed099a..cda8597b4e14 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -132,8 +132,8 @@ static int aq_get_rxpages(struct aq_ring_s *self, struct aq_ring_buff_s *rxbuf)
 	return 0;
 }
 
-static struct aq_ring_s *aq_ring_alloc(struct aq_ring_s *self,
-				       struct aq_nic_s *aq_nic)
+static int aq_ring_alloc(struct aq_ring_s *self,
+			 struct aq_nic_s *aq_nic)
 {
 	int err = 0;
 
@@ -156,46 +156,29 @@ static struct aq_ring_s *aq_ring_alloc(struct aq_ring_s *self,
 err_exit:
 	if (err < 0) {
 		aq_ring_free(self);
-		self = NULL;
 	}
 
-	return self;
+	return err;
 }
 
-struct aq_ring_s *aq_ring_tx_alloc(struct aq_ring_s *self,
-				   struct aq_nic_s *aq_nic,
-				   unsigned int idx,
-				   struct aq_nic_cfg_s *aq_nic_cfg)
+int aq_ring_tx_alloc(struct aq_ring_s *self,
+		     struct aq_nic_s *aq_nic,
+		     unsigned int idx,
+		     struct aq_nic_cfg_s *aq_nic_cfg)
 {
-	int err = 0;
-
 	self->aq_nic = aq_nic;
 	self->idx = idx;
 	self->size = aq_nic_cfg->txds;
 	self->dx_size = aq_nic_cfg->aq_hw_caps->txd_size;
 
-	self = aq_ring_alloc(self, aq_nic);
-	if (!self) {
-		err = -ENOMEM;
-		goto err_exit;
-	}
-
-err_exit:
-	if (err < 0) {
-		aq_ring_free(self);
-		self = NULL;
-	}
-
-	return self;
+	return aq_ring_alloc(self, aq_nic);
 }
 
-struct aq_ring_s *aq_ring_rx_alloc(struct aq_ring_s *self,
-				   struct aq_nic_s *aq_nic,
-				   unsigned int idx,
-				   struct aq_nic_cfg_s *aq_nic_cfg)
+int aq_ring_rx_alloc(struct aq_ring_s *self,
+		     struct aq_nic_s *aq_nic,
+		     unsigned int idx,
+		     struct aq_nic_cfg_s *aq_nic_cfg)
 {
-	int err = 0;
-
 	self->aq_nic = aq_nic;
 	self->idx = idx;
 	self->size = aq_nic_cfg->rxds;
@@ -217,22 +200,10 @@ struct aq_ring_s *aq_ring_rx_alloc(struct aq_ring_s *self,
 		self->tail_size = 0;
 	}
 
-	self = aq_ring_alloc(self, aq_nic);
-	if (!self) {
-		err = -ENOMEM;
-		goto err_exit;
-	}
-
-err_exit:
-	if (err < 0) {
-		aq_ring_free(self);
-		self = NULL;
-	}
-
-	return self;
+	return aq_ring_alloc(self, aq_nic);
 }
 
-struct aq_ring_s *
+int
 aq_ring_hwts_rx_alloc(struct aq_ring_s *self, struct aq_nic_s *aq_nic,
 		      unsigned int idx, unsigned int size, unsigned int dx_size)
 {
@@ -250,10 +221,10 @@ aq_ring_hwts_rx_alloc(struct aq_ring_s *self, struct aq_nic_s *aq_nic,
 					   GFP_KERNEL);
 	if (!self->dx_ring) {
 		aq_ring_free(self);
-		return NULL;
+		return -ENOMEM;
 	}
 
-	return self;
+	return 0;
 }
 
 int aq_ring_init(struct aq_ring_s *self, const enum atl_ring_type ring_type)
@@ -647,7 +618,7 @@ static int __aq_ring_rx_clean(struct aq_ring_s *self, struct napi_struct *napi,
 		}
 		if (is_ptp_ring)
 			buff->len -=
-				aq_ptp_extract_ts(self->aq_nic, skb,
+				aq_ptp_extract_ts(self->aq_nic, skb_hwtstamps(skb),
 						  aq_buf_vaddr(&buff->rxdata),
 						  buff->len);
 
@@ -742,6 +713,8 @@ static int __aq_ring_xdp_clean(struct aq_ring_s *rx_ring,
 		struct aq_ring_buff_s *buff = &rx_ring->buff_ring[rx_ring->sw_head];
 		bool is_ptp_ring = aq_ptp_ring(rx_ring->aq_nic, rx_ring);
 		struct aq_ring_buff_s *buff_ = NULL;
+		u16 ptp_hwtstamp_len = 0;
+		struct skb_shared_hwtstamps shhwtstamps;
 		struct sk_buff *skb = NULL;
 		unsigned int next_ = 0U;
 		struct xdp_buff xdp;
@@ -810,11 +783,12 @@ static int __aq_ring_xdp_clean(struct aq_ring_s *rx_ring,
 		hard_start = page_address(buff->rxdata.page) +
 			     buff->rxdata.pg_off - rx_ring->page_offset;
 
-		if (is_ptp_ring)
-			buff->len -=
-				aq_ptp_extract_ts(rx_ring->aq_nic, skb,
-						  aq_buf_vaddr(&buff->rxdata),
-						  buff->len);
+		if (is_ptp_ring) {
+			ptp_hwtstamp_len = aq_ptp_extract_ts(rx_ring->aq_nic, &shhwtstamps,
+							     aq_buf_vaddr(&buff->rxdata),
+							     buff->len);
+			buff->len -= ptp_hwtstamp_len;
+		}
 
 		xdp_init_buff(&xdp, frame_sz, &rx_ring->xdp_rxq);
 		xdp_prepare_buff(&xdp, hard_start, rx_ring->page_offset,
@@ -834,6 +808,9 @@ static int __aq_ring_xdp_clean(struct aq_ring_s *rx_ring,
 		if (IS_ERR(skb) || !skb)
 			continue;
 
+		if (ptp_hwtstamp_len > 0)
+			*skb_hwtstamps(skb) = shhwtstamps;
+
 		if (buff->is_vlan)
 			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
 					       buff->vlan_rx_tag);
@@ -932,11 +909,14 @@ void aq_ring_free(struct aq_ring_s *self)
 		return;
 
 	kfree(self->buff_ring);
+	self->buff_ring = NULL;
 
-	if (self->dx_ring)
+	if (self->dx_ring) {
 		dma_free_coherent(aq_nic_get_dev(self->aq_nic),
 				  self->size * self->dx_size, self->dx_ring,
 				  self->dx_ring_pa);
+		self->dx_ring = NULL;
+	}
 }
 
 unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
index 0a6c34438c1d..52847310740a 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
@@ -183,14 +183,14 @@ static inline unsigned int aq_ring_avail_dx(struct aq_ring_s *self)
 		self->sw_head - self->sw_tail - 1);
 }
 
-struct aq_ring_s *aq_ring_tx_alloc(struct aq_ring_s *self,
-				   struct aq_nic_s *aq_nic,
-				   unsigned int idx,
-				   struct aq_nic_cfg_s *aq_nic_cfg);
-struct aq_ring_s *aq_ring_rx_alloc(struct aq_ring_s *self,
-				   struct aq_nic_s *aq_nic,
-				   unsigned int idx,
-				   struct aq_nic_cfg_s *aq_nic_cfg);
+int aq_ring_tx_alloc(struct aq_ring_s *self,
+		     struct aq_nic_s *aq_nic,
+		     unsigned int idx,
+		     struct aq_nic_cfg_s *aq_nic_cfg);
+int aq_ring_rx_alloc(struct aq_ring_s *self,
+		     struct aq_nic_s *aq_nic,
+		     unsigned int idx,
+		     struct aq_nic_cfg_s *aq_nic_cfg);
 
 int aq_ring_init(struct aq_ring_s *self, const enum atl_ring_type ring_type);
 void aq_ring_rx_deinit(struct aq_ring_s *self);
@@ -207,9 +207,9 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 		     int budget);
 int aq_ring_rx_fill(struct aq_ring_s *self);
 
-struct aq_ring_s *aq_ring_hwts_rx_alloc(struct aq_ring_s *self,
-		struct aq_nic_s *aq_nic, unsigned int idx,
-		unsigned int size, unsigned int dx_size);
+int aq_ring_hwts_rx_alloc(struct aq_ring_s *self,
+			  struct aq_nic_s *aq_nic, unsigned int idx,
+			  unsigned int size, unsigned int dx_size);
 void aq_ring_hwts_rx_clean(struct aq_ring_s *self, struct aq_nic_s *aq_nic);
 
 unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data);
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
index f5db1c44e9b9..9769ab4f9bef 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
@@ -136,35 +136,32 @@ int aq_vec_ring_alloc(struct aq_vec_s *self, struct aq_nic_s *aq_nic,
 		const unsigned int idx_ring = AQ_NIC_CFG_TCVEC2RING(aq_nic_cfg,
 								    i, idx);
 
-		ring = aq_ring_tx_alloc(&self->ring[i][AQ_VEC_TX_ID], aq_nic,
-					idx_ring, aq_nic_cfg);
-		if (!ring) {
-			err = -ENOMEM;
+		ring = &self->ring[i][AQ_VEC_TX_ID];
+		err = aq_ring_tx_alloc(ring, aq_nic, idx_ring, aq_nic_cfg);
+		if (err)
 			goto err_exit;
-		}
 
 		++self->tx_rings;
 
 		aq_nic_set_tx_ring(aq_nic, idx_ring, ring);
 
-		if (xdp_rxq_info_reg(&self->ring[i][AQ_VEC_RX_ID].xdp_rxq,
+		ring = &self->ring[i][AQ_VEC_RX_ID];
+		if (xdp_rxq_info_reg(&ring->xdp_rxq,
 				     aq_nic->ndev, idx,
 				     self->napi.napi_id) < 0) {
 			err = -ENOMEM;
 			goto err_exit;
 		}
-		if (xdp_rxq_info_reg_mem_model(&self->ring[i][AQ_VEC_RX_ID].xdp_rxq,
+		if (xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 					       MEM_TYPE_PAGE_SHARED, NULL) < 0) {
-			xdp_rxq_info_unreg(&self->ring[i][AQ_VEC_RX_ID].xdp_rxq);
+			xdp_rxq_info_unreg(&ring->xdp_rxq);
 			err = -ENOMEM;
 			goto err_exit;
 		}
 
-		ring = aq_ring_rx_alloc(&self->ring[i][AQ_VEC_RX_ID], aq_nic,
-					idx_ring, aq_nic_cfg);
-		if (!ring) {
-			xdp_rxq_info_unreg(&self->ring[i][AQ_VEC_RX_ID].xdp_rxq);
-			err = -ENOMEM;
+		err = aq_ring_rx_alloc(ring, aq_nic, idx_ring, aq_nic_cfg);
+		if (err) {
+			xdp_rxq_info_unreg(&ring->xdp_rxq);
 			goto err_exit;
 		}
 
diff --git a/drivers/net/ethernet/asix/ax88796c_main.c b/drivers/net/ethernet/asix/ax88796c_main.c
index e551ffaed20d..11e8996b33d7 100644
--- a/drivers/net/ethernet/asix/ax88796c_main.c
+++ b/drivers/net/ethernet/asix/ax88796c_main.c
@@ -284,7 +284,7 @@ ax88796c_tx_fixup(struct net_device *ndev, struct sk_buff_head *q)
 	ax88796c_proc_tx_hdr(&info, skb->ip_summed);
 
 	/* SOP and SEG header */
-	memcpy(skb_push(skb, TX_OVERHEAD), &info.sop, TX_OVERHEAD);
+	memcpy(skb_push(skb, TX_OVERHEAD), &info.tx_overhead, TX_OVERHEAD);
 
 	/* Write SPI TXQ header */
 	memcpy(skb_push(skb, spi_len), ax88796c_tx_cmd_buf, spi_len);
diff --git a/drivers/net/ethernet/asix/ax88796c_main.h b/drivers/net/ethernet/asix/ax88796c_main.h
index 4a83c991dcbe..68a09edecab8 100644
--- a/drivers/net/ethernet/asix/ax88796c_main.h
+++ b/drivers/net/ethernet/asix/ax88796c_main.h
@@ -25,7 +25,7 @@
 #define AX88796C_PHY_REGDUMP_LEN	14
 #define AX88796C_PHY_ID			0x10
 
-#define TX_OVERHEAD			8
+#define TX_OVERHEAD     sizeof_field(struct tx_pkt_info, tx_overhead)
 #define TX_EOP_SIZE			4
 
 #define AX_MCAST_FILTER_SIZE		8
@@ -549,8 +549,10 @@ struct tx_eop_header {
 };
 
 struct tx_pkt_info {
-	struct tx_sop_header sop;
-	struct tx_segment_header seg;
+	struct_group(tx_overhead,
+		struct tx_sop_header sop;
+		struct tx_segment_header seg;
+	);
 	struct tx_eop_header eop;
 	u16 pkt_len;
 	u16 seq_num;
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
index 5935be190b9e..5f2a6fcba967 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -866,10 +866,13 @@ static int atl1e_setup_ring_resources(struct atl1e_adapter *adapter)
 		netdev_err(adapter->netdev, "offset(%d) > ring size(%d) !!\n",
 			   offset, adapter->ring_size);
 		err = -1;
-		goto failed;
+		goto free_buffer;
 	}
 
 	return 0;
+free_buffer:
+	kfree(tx_ring->tx_buffer);
+	tx_ring->tx_buffer = NULL;
 failed:
 	if (adapter->ring_vir_addr != NULL) {
 		dma_free_coherent(&pdev->dev, adapter->ring_size,
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index bda3ccc28eca..81d232e6d05f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -3486,16 +3486,15 @@ static u32 bnx2x_get_rxfh_indir_size(struct net_device *dev)
 	return T_ETH_INDIRECTION_TABLE_SIZE;
 }
 
-static int bnx2x_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
-			  u8 *hfunc)
+static int bnx2x_get_rxfh(struct net_device *dev,
+			  struct ethtool_rxfh_param *rxfh)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 	u8 ind_table[T_ETH_INDIRECTION_TABLE_SIZE] = {0};
 	size_t i;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (!indir)
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (!rxfh->indir)
 		return 0;
 
 	/* Get the current configuration of the RSS indirection table */
@@ -3511,13 +3510,14 @@ static int bnx2x_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
 	 * queue.
 	 */
 	for (i = 0; i < T_ETH_INDIRECTION_TABLE_SIZE; i++)
-		indir[i] = ind_table[i] - bp->fp->cl_id;
+		rxfh->indir[i] = ind_table[i] - bp->fp->cl_id;
 
 	return 0;
 }
 
-static int bnx2x_set_rxfh(struct net_device *dev, const u32 *indir,
-			  const u8 *key, const u8 hfunc)
+static int bnx2x_set_rxfh(struct net_device *dev,
+			  struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 	size_t i;
@@ -3525,11 +3525,12 @@ static int bnx2x_set_rxfh(struct net_device *dev, const u32 *indir,
 	/* We require at least one supported parameter to be changed and no
 	 * change in any of the unsupported parameters
 	 */
-	if (key ||
-	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->key ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP))
 		return -EOPNOTSUPP;
 
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
 	for (i = 0; i < T_ETH_INDIRECTION_TABLE_SIZE; i++) {
@@ -3542,7 +3543,7 @@ static int bnx2x_set_rxfh(struct net_device *dev, const u32 *indir,
 		 * align the received table to the Client ID of the leading RSS
 		 * queue
 		 */
-		bp->rss_conf_obj.ind_table[i] = indir[i] + bp->fp->cl_id;
+		bp->rss_conf_obj.ind_table[i] = rxfh->indir[i] + bp->fp->cl_id;
 	}
 
 	if (bp->state == BNX2X_STATE_OPEN)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index d0359b569afe..0aacd3c6ed5c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -120,6 +120,10 @@ static const struct {
 	[BCM57508] = { "Broadcom BCM57508 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb Ethernet" },
 	[BCM57504] = { "Broadcom BCM57504 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb Ethernet" },
 	[BCM57502] = { "Broadcom BCM57502 NetXtreme-E 10Gb/25Gb/50Gb Ethernet" },
+	[BCM57608] = { "Broadcom BCM57608 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb/400Gb Ethernet" },
+	[BCM57604] = { "Broadcom BCM57604 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb Ethernet" },
+	[BCM57602] = { "Broadcom BCM57602 NetXtreme-E 10Gb/25Gb/50Gb/100Gb Ethernet" },
+	[BCM57601] = { "Broadcom BCM57601 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb/400Gb Ethernet" },
 	[BCM57508_NPAR] = { "Broadcom BCM57508 NetXtreme-E Ethernet Partition" },
 	[BCM57504_NPAR] = { "Broadcom BCM57504 NetXtreme-E Ethernet Partition" },
 	[BCM57502_NPAR] = { "Broadcom BCM57502 NetXtreme-E Ethernet Partition" },
@@ -174,6 +178,10 @@ static const struct pci_device_id bnxt_pci_tbl[] = {
 	{ PCI_VDEVICE(BROADCOM, 0x1750), .driver_data = BCM57508 },
 	{ PCI_VDEVICE(BROADCOM, 0x1751), .driver_data = BCM57504 },
 	{ PCI_VDEVICE(BROADCOM, 0x1752), .driver_data = BCM57502 },
+	{ PCI_VDEVICE(BROADCOM, 0x1760), .driver_data = BCM57608 },
+	{ PCI_VDEVICE(BROADCOM, 0x1761), .driver_data = BCM57604 },
+	{ PCI_VDEVICE(BROADCOM, 0x1762), .driver_data = BCM57602 },
+	{ PCI_VDEVICE(BROADCOM, 0x1763), .driver_data = BCM57601 },
 	{ PCI_VDEVICE(BROADCOM, 0x1800), .driver_data = BCM57502_NPAR },
 	{ PCI_VDEVICE(BROADCOM, 0x1801), .driver_data = BCM57504_NPAR },
 	{ PCI_VDEVICE(BROADCOM, 0x1802), .driver_data = BCM57508_NPAR },
@@ -254,22 +262,28 @@ static bool bnxt_vf_pciid(enum board_idx idx)
 		writel(DB_CP_IRQ_DIS_FLAGS, db)
 
 #define BNXT_DB_CQ(db, idx)						\
-	writel(DB_CP_FLAGS | RING_CMP(idx), (db)->doorbell)
+	writel(DB_CP_FLAGS | DB_RING_IDX(db, idx), (db)->doorbell)
 
 #define BNXT_DB_NQ_P5(db, idx)						\
-	bnxt_writeq(bp, (db)->db_key64 | DBR_TYPE_NQ | RING_CMP(idx),	\
+	bnxt_writeq(bp, (db)->db_key64 | DBR_TYPE_NQ | DB_RING_IDX(db, idx),\
 		    (db)->doorbell)
 
+#define BNXT_DB_NQ_P7(db, idx)						\
+	bnxt_writeq(bp, (db)->db_key64 | DBR_TYPE_NQ_MASK |		\
+		    DB_RING_IDX(db, idx), (db)->doorbell)
+
 #define BNXT_DB_CQ_ARM(db, idx)						\
-	writel(DB_CP_REARM_FLAGS | RING_CMP(idx), (db)->doorbell)
+	writel(DB_CP_REARM_FLAGS | DB_RING_IDX(db, idx), (db)->doorbell)
 
 #define BNXT_DB_NQ_ARM_P5(db, idx)					\
-	bnxt_writeq(bp, (db)->db_key64 | DBR_TYPE_NQ_ARM | RING_CMP(idx),\
-		    (db)->doorbell)
+	bnxt_writeq(bp, (db)->db_key64 | DBR_TYPE_NQ_ARM |		\
+		    DB_RING_IDX(db, idx), (db)->doorbell)
 
 static void bnxt_db_nq(struct bnxt *bp, struct bnxt_db_info *db, u32 idx)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P7)
+		BNXT_DB_NQ_P7(db, idx);
+	else if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		BNXT_DB_NQ_P5(db, idx);
 	else
 		BNXT_DB_CQ(db, idx);
@@ -277,7 +291,7 @@ static void bnxt_db_nq(struct bnxt *bp, struct bnxt_db_info *db, u32 idx)
 
 static void bnxt_db_nq_arm(struct bnxt *bp, struct bnxt_db_info *db, u32 idx)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		BNXT_DB_NQ_ARM_P5(db, idx);
 	else
 		BNXT_DB_CQ_ARM(db, idx);
@@ -285,9 +299,9 @@ static void bnxt_db_nq_arm(struct bnxt *bp, struct bnxt_db_info *db, u32 idx)
 
 static void bnxt_db_cq(struct bnxt *bp, struct bnxt_db_info *db, u32 idx)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		bnxt_writeq(bp, db->db_key64 | DBR_TYPE_CQ_ARMALL |
-			    RING_CMP(idx), db->doorbell);
+			    DB_RING_IDX(db, idx), db->doorbell);
 	else
 		BNXT_DB_CQ(db, idx);
 }
@@ -321,7 +335,7 @@ static void bnxt_sched_reset_rxr(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
 {
 	if (!rxr->bnapi->in_reset) {
 		rxr->bnapi->in_reset = true;
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 			set_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event);
 		else
 			set_bit(BNXT_RST_RING_SP_EVENT, &bp->sp_event);
@@ -331,16 +345,16 @@ static void bnxt_sched_reset_rxr(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
 }
 
 void bnxt_sched_reset_txr(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
-			  int idx)
+			  u16 curr)
 {
 	struct bnxt_napi *bnapi = txr->bnapi;
 
 	if (bnapi->tx_fault)
 		return;
 
-	netdev_err(bp->dev, "Invalid Tx completion (ring:%d tx_pkts:%d cons:%u prod:%u i:%d)",
-		   txr->txq_index, bnapi->tx_pkts,
-		   txr->tx_cons, txr->tx_prod, idx);
+	netdev_err(bp->dev, "Invalid Tx completion (ring:%d tx_hw_cons:%u cons:%u prod:%u curr:%u)",
+		   txr->txq_index, txr->tx_hw_cons,
+		   txr->tx_cons, txr->tx_prod, curr);
 	WARN_ON_ONCE(1);
 	bnapi->tx_fault = 1;
 	bnxt_queue_sp_work(bp, BNXT_RESET_TASK_SP_EVENT);
@@ -381,6 +395,8 @@ static u16 bnxt_xmit_get_cfa_action(struct sk_buff *skb)
 static void bnxt_txr_db_kick(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 			     u16 prod)
 {
+	/* Sync BD data before updating doorbell */
+	wmb();
 	bnxt_db_write(bp, &txr->tx_db, prod);
 	txr->kick_pending = 0;
 }
@@ -388,7 +404,7 @@ static void bnxt_txr_db_kick(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
-	struct tx_bd *txbd;
+	struct tx_bd *txbd, *txbd0;
 	struct tx_bd_ext *txbd1;
 	struct netdev_queue *txq;
 	int i;
@@ -430,11 +446,9 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	len = skb_headlen(skb);
 	last_frag = skb_shinfo(skb)->nr_frags;
 
-	txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
+	txbd = &txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
 
-	txbd->tx_bd_opaque = prod;
-
-	tx_buf = &txr->tx_buf_ring[prod];
+	tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
 	tx_buf->skb = skb;
 	tx_buf->nr_frags = last_frag;
 
@@ -519,12 +533,15 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		txbd->tx_bd_len_flags_type = tx_push->tx_bd_len_flags_type;
 		txbd->tx_bd_haddr = txr->data_mapping;
+		txbd->tx_bd_opaque = SET_TX_OPAQUE(bp, txr, prod, 2);
 		prod = NEXT_TX(prod);
-		txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
+		tx_push->tx_bd_opaque = txbd->tx_bd_opaque;
+		txbd = &txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
 		memcpy(txbd, tx_push1, sizeof(*txbd));
 		prod = NEXT_TX(prod);
 		tx_push->doorbell =
-			cpu_to_le32(DB_KEY_TX_PUSH | DB_LONG_TX_PUSH | prod);
+			cpu_to_le32(DB_KEY_TX_PUSH | DB_LONG_TX_PUSH |
+				    DB_RING_IDX(&txr->tx_db, prod));
 		WRITE_ONCE(txr->tx_prod, prod);
 
 		tx_buf->is_push = 1;
@@ -562,19 +579,29 @@ normal_tx:
 		((last_frag + 2) << TX_BD_FLAGS_BD_CNT_SHIFT);
 
 	txbd->tx_bd_haddr = cpu_to_le64(mapping);
+	txbd->tx_bd_opaque = SET_TX_OPAQUE(bp, txr, prod, 2 + last_frag);
 
 	prod = NEXT_TX(prod);
 	txbd1 = (struct tx_bd_ext *)
-		&txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
+		&txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
 
 	txbd1->tx_bd_hsize_lflags = lflags;
 	if (skb_is_gso(skb)) {
+		bool udp_gso = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4);
 		u32 hdr_len;
 
-		if (skb->encapsulation)
-			hdr_len = skb_inner_tcp_all_headers(skb);
-		else
+		if (skb->encapsulation) {
+			if (udp_gso)
+				hdr_len = skb_inner_transport_offset(skb) +
+					  sizeof(struct udphdr);
+			else
+				hdr_len = skb_inner_tcp_all_headers(skb);
+		} else if (udp_gso) {
+			hdr_len = skb_transport_offset(skb) +
+				  sizeof(struct udphdr);
+		} else {
 			hdr_len = skb_tcp_all_headers(skb);
+		}
 
 		txbd1->tx_bd_hsize_lflags |= cpu_to_le32(TX_BD_FLAGS_LSO |
 					TX_BD_FLAGS_T_IPID |
@@ -601,11 +628,12 @@ normal_tx:
 	txbd1->tx_bd_cfa_meta = cpu_to_le32(vlan_tag_flags);
 	txbd1->tx_bd_cfa_action =
 			cpu_to_le32(cfa_action << TX_BD_CFA_ACTION_SHIFT);
+	txbd0 = txbd;
 	for (i = 0; i < last_frag; i++) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
 		prod = NEXT_TX(prod);
-		txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
+		txbd = &txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
 
 		len = skb_frag_size(frag);
 		mapping = skb_frag_dma_map(&pdev->dev, frag, 0, len,
@@ -614,7 +642,7 @@ normal_tx:
 		if (unlikely(dma_mapping_error(&pdev->dev, mapping)))
 			goto tx_dma_error;
 
-		tx_buf = &txr->tx_buf_ring[prod];
+		tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
 		dma_unmap_addr_set(tx_buf, mapping, mapping);
 
 		txbd->tx_bd_haddr = cpu_to_le64(mapping);
@@ -632,22 +660,26 @@ normal_tx:
 
 	skb_tx_timestamp(skb);
 
-	/* Sync BD data before updating doorbell */
-	wmb();
-
 	prod = NEXT_TX(prod);
 	WRITE_ONCE(txr->tx_prod, prod);
 
-	if (!netdev_xmit_more() || netif_xmit_stopped(txq))
+	if (!netdev_xmit_more() || netif_xmit_stopped(txq)) {
 		bnxt_txr_db_kick(bp, txr, prod);
-	else
+	} else {
+		if (free_size >= bp->tx_wake_thresh)
+			txbd0->tx_bd_len_flags_type |=
+				cpu_to_le32(TX_BD_FLAGS_NO_CMPL);
 		txr->kick_pending = 1;
+	}
 
 tx_done:
 
 	if (unlikely(bnxt_tx_avail(bp, txr) <= MAX_SKB_FRAGS + 1)) {
-		if (netdev_xmit_more() && !tx_buf->is_push)
+		if (netdev_xmit_more() && !tx_buf->is_push) {
+			txbd0->tx_bd_len_flags_type &=
+				cpu_to_le32(~TX_BD_FLAGS_NO_CMPL);
 			bnxt_txr_db_kick(bp, txr, prod);
+		}
 
 		netif_txq_try_stop(txq, bnxt_tx_avail(bp, txr),
 				   bp->tx_wake_thresh);
@@ -662,7 +694,7 @@ tx_dma_error:
 
 	/* start back at beginning and unmap skb */
 	prod = txr->tx_prod;
-	tx_buf = &txr->tx_buf_ring[prod];
+	tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
 	dma_unmap_single(&pdev->dev, dma_unmap_addr(tx_buf, mapping),
 			 skb_headlen(skb), DMA_TO_DEVICE);
 	prod = NEXT_TX(prod);
@@ -670,7 +702,7 @@ tx_dma_error:
 	/* unmap remaining mapped pages */
 	for (i = 0; i < last_frag; i++) {
 		prod = NEXT_TX(prod);
-		tx_buf = &txr->tx_buf_ring[prod];
+		tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
 		dma_unmap_page(&pdev->dev, dma_unmap_addr(tx_buf, mapping),
 			       skb_frag_size(&skb_shinfo(skb)->frags[i]),
 			       DMA_TO_DEVICE);
@@ -686,31 +718,32 @@ tx_kick_pending:
 	return NETDEV_TX_OK;
 }
 
-static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
+static void __bnxt_tx_int(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
+			  int budget)
 {
-	struct bnxt_tx_ring_info *txr = bnapi->tx_ring;
 	struct netdev_queue *txq = netdev_get_tx_queue(bp->dev, txr->txq_index);
-	u16 cons = txr->tx_cons;
 	struct pci_dev *pdev = bp->pdev;
-	int nr_pkts = bnapi->tx_pkts;
-	int i;
+	u16 hw_cons = txr->tx_hw_cons;
 	unsigned int tx_bytes = 0;
+	u16 cons = txr->tx_cons;
+	int tx_pkts = 0;
 
-	for (i = 0; i < nr_pkts; i++) {
+	while (RING_TX(bp, cons) != hw_cons) {
 		struct bnxt_sw_tx_bd *tx_buf;
 		struct sk_buff *skb;
 		int j, last;
 
-		tx_buf = &txr->tx_buf_ring[cons];
+		tx_buf = &txr->tx_buf_ring[RING_TX(bp, cons)];
 		cons = NEXT_TX(cons);
 		skb = tx_buf->skb;
 		tx_buf->skb = NULL;
 
 		if (unlikely(!skb)) {
-			bnxt_sched_reset_txr(bp, txr, i);
+			bnxt_sched_reset_txr(bp, txr, cons);
 			return;
 		}
 
+		tx_pkts++;
 		tx_bytes += skb->len;
 
 		if (tx_buf->is_push) {
@@ -724,7 +757,7 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 
 		for (j = 0; j < last; j++) {
 			cons = NEXT_TX(cons);
-			tx_buf = &txr->tx_buf_ring[cons];
+			tx_buf = &txr->tx_buf_ring[RING_TX(bp, cons)];
 			dma_unmap_page(
 				&pdev->dev,
 				dma_unmap_addr(tx_buf, mapping),
@@ -732,7 +765,7 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 				DMA_TO_DEVICE);
 		}
 		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) {
-			if (bp->flags & BNXT_FLAG_CHIP_P5) {
+			if (BNXT_CHIP_P5(bp)) {
 				/* PTP worker takes ownership of the skb */
 				if (!bnxt_get_tx_ts_p5(bp, skb))
 					skb = NULL;
@@ -747,14 +780,25 @@ next_tx_int:
 		dev_consume_skb_any(skb);
 	}
 
-	bnapi->tx_pkts = 0;
 	WRITE_ONCE(txr->tx_cons, cons);
 
-	__netif_txq_completed_wake(txq, nr_pkts, tx_bytes,
+	__netif_txq_completed_wake(txq, tx_pkts, tx_bytes,
 				   bnxt_tx_avail(bp, txr), bp->tx_wake_thresh,
 				   READ_ONCE(txr->dev_state) == BNXT_DEV_STATE_CLOSING);
 }
 
+static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
+{
+	struct bnxt_tx_ring_info *txr;
+	int i;
+
+	bnxt_for_each_napi_tx(i, bnapi, txr) {
+		if (txr->tx_hw_cons != RING_TX(bp, txr->tx_cons))
+			__bnxt_tx_int(bp, txr, budget);
+	}
+	bnapi->events &= ~BNXT_TX_CMP_EVENT;
+}
+
 static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
 					 struct bnxt_rx_ring_info *rxr,
 					 unsigned int *offset,
@@ -803,8 +847,8 @@ static inline u8 *__bnxt_alloc_rx_frag(struct bnxt *bp, dma_addr_t *mapping,
 int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 		       u16 prod, gfp_t gfp)
 {
-	struct rx_bd *rxbd = &rxr->rx_desc_ring[RX_RING(prod)][RX_IDX(prod)];
-	struct bnxt_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[prod];
+	struct rx_bd *rxbd = &rxr->rx_desc_ring[RX_RING(bp, prod)][RX_IDX(prod)];
+	struct bnxt_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[RING_RX(bp, prod)];
 	dma_addr_t mapping;
 
 	if (BNXT_RX_PAGE_MODE(bp)) {
@@ -837,9 +881,10 @@ void bnxt_reuse_rx_data(struct bnxt_rx_ring_info *rxr, u16 cons, void *data)
 {
 	u16 prod = rxr->rx_prod;
 	struct bnxt_sw_rx_bd *cons_rx_buf, *prod_rx_buf;
+	struct bnxt *bp = rxr->bnapi->bp;
 	struct rx_bd *cons_bd, *prod_bd;
 
-	prod_rx_buf = &rxr->rx_buf_ring[prod];
+	prod_rx_buf = &rxr->rx_buf_ring[RING_RX(bp, prod)];
 	cons_rx_buf = &rxr->rx_buf_ring[cons];
 
 	prod_rx_buf->data = data;
@@ -847,8 +892,8 @@ void bnxt_reuse_rx_data(struct bnxt_rx_ring_info *rxr, u16 cons, void *data)
 
 	prod_rx_buf->mapping = cons_rx_buf->mapping;
 
-	prod_bd = &rxr->rx_desc_ring[RX_RING(prod)][RX_IDX(prod)];
-	cons_bd = &rxr->rx_desc_ring[RX_RING(cons)][RX_IDX(cons)];
+	prod_bd = &rxr->rx_desc_ring[RX_RING(bp, prod)][RX_IDX(prod)];
+	cons_bd = &rxr->rx_desc_ring[RX_RING(bp, cons)][RX_IDX(cons)];
 
 	prod_bd->rx_bd_haddr = cons_bd->rx_bd_haddr;
 }
@@ -868,7 +913,7 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp,
 				     u16 prod, gfp_t gfp)
 {
 	struct rx_bd *rxbd =
-		&rxr->rx_agg_desc_ring[RX_RING(prod)][RX_IDX(prod)];
+		&rxr->rx_agg_desc_ring[RX_AGG_RING(bp, prod)][RX_IDX(prod)];
 	struct bnxt_sw_rx_agg_bd *rx_agg_buf;
 	struct page *page;
 	dma_addr_t mapping;
@@ -885,7 +930,7 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp,
 
 	__set_bit(sw_prod, rxr->rx_agg_bmap);
 	rx_agg_buf = &rxr->rx_agg_ring[sw_prod];
-	rxr->rx_sw_agg_prod = NEXT_RX_AGG(sw_prod);
+	rxr->rx_sw_agg_prod = RING_RX_AGG(bp, NEXT_RX_AGG(sw_prod));
 
 	rx_agg_buf->page = page;
 	rx_agg_buf->offset = offset;
@@ -927,7 +972,7 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 idx,
 	bool p5_tpa = false;
 	u32 i;
 
-	if ((bp->flags & BNXT_FLAG_CHIP_P5) && tpa)
+	if ((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) && tpa)
 		p5_tpa = true;
 
 	for (i = 0; i < agg_bufs; i++) {
@@ -961,13 +1006,13 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 idx,
 
 		prod_rx_buf->mapping = cons_rx_buf->mapping;
 
-		prod_bd = &rxr->rx_agg_desc_ring[RX_RING(prod)][RX_IDX(prod)];
+		prod_bd = &rxr->rx_agg_desc_ring[RX_AGG_RING(bp, prod)][RX_IDX(prod)];
 
 		prod_bd->rx_bd_haddr = cpu_to_le64(cons_rx_buf->mapping);
 		prod_bd->rx_bd_opaque = sw_prod;
 
 		prod = NEXT_RX_AGG(prod);
-		sw_prod = NEXT_RX_AGG(sw_prod);
+		sw_prod = RING_RX_AGG(bp, NEXT_RX_AGG(sw_prod));
 	}
 	rxr->rx_agg_prod = prod;
 	rxr->rx_sw_agg_prod = sw_prod;
@@ -1094,7 +1139,7 @@ static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
 	u32 i, total_frag_len = 0;
 	bool p5_tpa = false;
 
-	if ((bp->flags & BNXT_FLAG_CHIP_P5) && tpa)
+	if ((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) && tpa)
 		p5_tpa = true;
 
 	for (i = 0; i < agg_bufs; i++) {
@@ -1249,7 +1294,7 @@ static int bnxt_discard_rx(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	} else if (cmp_type == CMP_TYPE_RX_L2_TPA_END_CMP) {
 		struct rx_tpa_end_cmp *tpa_end = cmp;
 
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 			return 0;
 
 		agg_bufs = TPA_END_AGG_BUFS(tpa_end);
@@ -1290,8 +1335,39 @@ static u16 bnxt_lookup_agg_idx(struct bnxt_rx_ring_info *rxr, u16 agg_id)
 	return map->agg_id_tbl[agg_id];
 }
 
+static void bnxt_tpa_metadata(struct bnxt_tpa_info *tpa_info,
+			      struct rx_tpa_start_cmp *tpa_start,
+			      struct rx_tpa_start_cmp_ext *tpa_start1)
+{
+	tpa_info->cfa_code_valid = 1;
+	tpa_info->cfa_code = TPA_START_CFA_CODE(tpa_start1);
+	tpa_info->vlan_valid = 0;
+	if (tpa_info->flags2 & RX_CMP_FLAGS2_META_FORMAT_VLAN) {
+		tpa_info->vlan_valid = 1;
+		tpa_info->metadata =
+			le32_to_cpu(tpa_start1->rx_tpa_start_cmp_metadata);
+	}
+}
+
+static void bnxt_tpa_metadata_v2(struct bnxt_tpa_info *tpa_info,
+				 struct rx_tpa_start_cmp *tpa_start,
+				 struct rx_tpa_start_cmp_ext *tpa_start1)
+{
+	tpa_info->vlan_valid = 0;
+	if (TPA_START_VLAN_VALID(tpa_start)) {
+		u32 tpid_sel = TPA_START_VLAN_TPID_SEL(tpa_start);
+		u32 vlan_proto = ETH_P_8021Q;
+
+		tpa_info->vlan_valid = 1;
+		if (tpid_sel == RX_TPA_START_METADATA1_TPID_8021AD)
+			vlan_proto = ETH_P_8021AD;
+		tpa_info->metadata = vlan_proto << 16 |
+				     TPA_START_METADATA0_TCI(tpa_start1);
+	}
+}
+
 static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
-			   struct rx_tpa_start_cmp *tpa_start,
+			   u8 cmp_type, struct rx_tpa_start_cmp *tpa_start,
 			   struct rx_tpa_start_cmp_ext *tpa_start1)
 {
 	struct bnxt_sw_rx_bd *cons_rx_buf, *prod_rx_buf;
@@ -1300,7 +1376,7 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 	struct rx_bd *prod_bd;
 	dma_addr_t mapping;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		agg_id = TPA_START_AGG_ID_P5(tpa_start);
 		agg_id = bnxt_alloc_agg_idx(rxr, agg_id);
 	} else {
@@ -1309,7 +1385,7 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 	cons = tpa_start->rx_tpa_start_cmp_opaque;
 	prod = rxr->rx_prod;
 	cons_rx_buf = &rxr->rx_buf_ring[cons];
-	prod_rx_buf = &rxr->rx_buf_ring[prod];
+	prod_rx_buf = &rxr->rx_buf_ring[RING_RX(bp, prod)];
 	tpa_info = &rxr->rx_tpa[agg_id];
 
 	if (unlikely(cons != rxr->rx_next_cons ||
@@ -1320,17 +1396,13 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 		bnxt_sched_reset_rxr(bp, rxr);
 		return;
 	}
-	/* Store cfa_code in tpa_info to use in tpa_end
-	 * completion processing.
-	 */
-	tpa_info->cfa_code = TPA_START_CFA_CODE(tpa_start1);
 	prod_rx_buf->data = tpa_info->data;
 	prod_rx_buf->data_ptr = tpa_info->data_ptr;
 
 	mapping = tpa_info->mapping;
 	prod_rx_buf->mapping = mapping;
 
-	prod_bd = &rxr->rx_desc_ring[RX_RING(prod)][RX_IDX(prod)];
+	prod_bd = &rxr->rx_desc_ring[RX_RING(bp, prod)][RX_IDX(prod)];
 
 	prod_bd->rx_bd_haddr = cpu_to_le64(mapping);
 
@@ -1343,12 +1415,13 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 		le32_to_cpu(tpa_start->rx_tpa_start_cmp_len_flags_type) >>
 				RX_TPA_START_CMP_LEN_SHIFT;
 	if (likely(TPA_START_HASH_VALID(tpa_start))) {
-		u32 hash_type = TPA_START_HASH_TYPE(tpa_start);
-
 		tpa_info->hash_type = PKT_HASH_TYPE_L4;
 		tpa_info->gso_type = SKB_GSO_TCPV4;
+		if (TPA_START_IS_IPV6(tpa_start1))
+			tpa_info->gso_type = SKB_GSO_TCPV6;
 		/* RSS profiles 1 and 3 with extract code 0 for inner 4-tuple */
-		if (hash_type == 3 || TPA_START_IS_IPV6(tpa_start1))
+		else if (cmp_type == CMP_TYPE_RX_L2_TPA_START_CMP &&
+			 TPA_START_HASH_TYPE(tpa_start) == 3)
 			tpa_info->gso_type = SKB_GSO_TCPV6;
 		tpa_info->rss_hash =
 			le32_to_cpu(tpa_start->rx_tpa_start_cmp_rss_hash);
@@ -1358,13 +1431,16 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 		netif_warn(bp, rx_err, bp->dev, "TPA packet without valid hash\n");
 	}
 	tpa_info->flags2 = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_flags2);
-	tpa_info->metadata = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_metadata);
 	tpa_info->hdr_info = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_hdr_info);
+	if (cmp_type == CMP_TYPE_RX_L2_TPA_START_CMP)
+		bnxt_tpa_metadata(tpa_info, tpa_start, tpa_start1);
+	else
+		bnxt_tpa_metadata_v2(tpa_info, tpa_start, tpa_start1);
 	tpa_info->agg_count = 0;
 
 	rxr->rx_prod = NEXT_RX(prod);
-	cons = NEXT_RX(cons);
-	rxr->rx_next_cons = NEXT_RX(cons);
+	cons = RING_RX(bp, NEXT_RX(cons));
+	rxr->rx_next_cons = RING_RX(bp, NEXT_RX(cons));
 	cons_rx_buf = &rxr->rx_buf_ring[cons];
 
 	bnxt_reuse_rx_data(rxr, cons, cons_rx_buf->data);
@@ -1563,7 +1639,7 @@ static inline struct sk_buff *bnxt_gro_skb(struct bnxt *bp,
 	skb_shinfo(skb)->gso_size =
 		le32_to_cpu(tpa_end1->rx_tpa_end_cmp_seg_len);
 	skb_shinfo(skb)->gso_type = tpa_info->gso_type;
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		payload_off = TPA_END_PAYLOAD_OFF_P5(tpa_end1);
 	else
 		payload_off = TPA_END_PAYLOAD_OFF(tpa_end);
@@ -1594,6 +1670,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 {
 	struct bnxt_napi *bnapi = cpr->bnapi;
 	struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
+	struct net_device *dev = bp->dev;
 	u8 *data_ptr, agg_bufs;
 	unsigned int len;
 	struct bnxt_tpa_info *tpa_info;
@@ -1611,7 +1688,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 		return NULL;
 	}
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		agg_id = TPA_END_AGG_ID_P5(tpa_end);
 		agg_id = bnxt_lookup_agg_idx(rxr, agg_id);
 		agg_bufs = TPA_END_AGG_BUFS_P5(tpa_end1);
@@ -1700,14 +1777,15 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 		}
 	}
 
-	skb->protocol =
-		eth_type_trans(skb, bnxt_get_pkt_dev(bp, tpa_info->cfa_code));
+	if (tpa_info->cfa_code_valid)
+		dev = bnxt_get_pkt_dev(bp, tpa_info->cfa_code);
+	skb->protocol = eth_type_trans(skb, dev);
 
 	if (tpa_info->hash_type != PKT_HASH_TYPE_NONE)
 		skb_set_hash(skb, tpa_info->rss_hash, tpa_info->hash_type);
 
-	if ((tpa_info->flags2 & RX_CMP_FLAGS2_META_FORMAT_VLAN) &&
-	    (skb->dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX)) {
+	if (tpa_info->vlan_valid &&
+	    (dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX)) {
 		__be16 vlan_proto = htons(tpa_info->metadata >>
 					  RX_CMP_FLAGS2_METADATA_TPID_SFT);
 		u16 vtag = tpa_info->metadata & RX_CMP_FLAGS2_METADATA_TCI_MASK;
@@ -1748,16 +1826,90 @@ static void bnxt_tpa_agg(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 static void bnxt_deliver_skb(struct bnxt *bp, struct bnxt_napi *bnapi,
 			     struct sk_buff *skb)
 {
+	skb_mark_for_recycle(skb);
+
 	if (skb->dev != bp->dev) {
 		/* this packet belongs to a vf-rep */
 		bnxt_vf_rep_rx(bp, skb);
 		return;
 	}
 	skb_record_rx_queue(skb, bnapi->index);
-	skb_mark_for_recycle(skb);
 	napi_gro_receive(&bnapi->napi, skb);
 }
 
+static bool bnxt_rx_ts_valid(struct bnxt *bp, u32 flags,
+			     struct rx_cmp_ext *rxcmp1, u32 *cmpl_ts)
+{
+	u32 ts = le32_to_cpu(rxcmp1->rx_cmp_timestamp);
+
+	if (BNXT_PTP_RX_TS_VALID(flags))
+		goto ts_valid;
+	if (!bp->ptp_all_rx_tstamp || !ts || !BNXT_ALL_RX_TS_VALID(flags))
+		return false;
+
+ts_valid:
+	*cmpl_ts = ts;
+	return true;
+}
+
+static struct sk_buff *bnxt_rx_vlan(struct sk_buff *skb, u8 cmp_type,
+				    struct rx_cmp *rxcmp,
+				    struct rx_cmp_ext *rxcmp1)
+{
+	__be16 vlan_proto;
+	u16 vtag;
+
+	if (cmp_type == CMP_TYPE_RX_L2_CMP) {
+		__le32 flags2 = rxcmp1->rx_cmp_flags2;
+		u32 meta_data;
+
+		if (!(flags2 & cpu_to_le32(RX_CMP_FLAGS2_META_FORMAT_VLAN)))
+			return skb;
+
+		meta_data = le32_to_cpu(rxcmp1->rx_cmp_meta_data);
+		vtag = meta_data & RX_CMP_FLAGS2_METADATA_TCI_MASK;
+		vlan_proto = htons(meta_data >> RX_CMP_FLAGS2_METADATA_TPID_SFT);
+		if (eth_type_vlan(vlan_proto))
+			__vlan_hwaccel_put_tag(skb, vlan_proto, vtag);
+		else
+			goto vlan_err;
+	} else if (cmp_type == CMP_TYPE_RX_L2_V3_CMP) {
+		if (RX_CMP_VLAN_VALID(rxcmp)) {
+			u32 tpid_sel = RX_CMP_VLAN_TPID_SEL(rxcmp);
+
+			if (tpid_sel == RX_CMP_METADATA1_TPID_8021Q)
+				vlan_proto = htons(ETH_P_8021Q);
+			else if (tpid_sel == RX_CMP_METADATA1_TPID_8021AD)
+				vlan_proto = htons(ETH_P_8021AD);
+			else
+				goto vlan_err;
+			vtag = RX_CMP_METADATA0_TCI(rxcmp1);
+			__vlan_hwaccel_put_tag(skb, vlan_proto, vtag);
+		}
+	}
+	return skb;
+vlan_err:
+	dev_kfree_skb(skb);
+	return NULL;
+}
+
+static enum pkt_hash_types bnxt_rss_ext_op(struct bnxt *bp,
+					   struct rx_cmp *rxcmp)
+{
+	u8 ext_op;
+
+	ext_op = RX_CMP_V3_HASH_TYPE(bp, rxcmp);
+	switch (ext_op) {
+	case EXT_OP_INNER_4:
+	case EXT_OP_OUTER_4:
+	case EXT_OP_INNFL_3:
+	case EXT_OP_OUTFL_3:
+		return PKT_HASH_TYPE_L4;
+	default:
+		return PKT_HASH_TYPE_L3;
+	}
+}
+
 /* returns the following:
  * 1       - 1 packet successfully received
  * 0       - successful TPA_START, packet not completed yet
@@ -1774,7 +1926,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	struct rx_cmp *rxcmp;
 	struct rx_cmp_ext *rxcmp1;
 	u32 tmp_raw_cons = *raw_cons;
-	u16 cfa_code, cons, prod, cp_cons = RING_CMP(tmp_raw_cons);
+	u16 cons, prod, cp_cons = RING_CMP(tmp_raw_cons);
 	struct bnxt_sw_rx_bd *rx_buf;
 	unsigned int len;
 	u8 *data_ptr, agg_bufs, cmp_type;
@@ -1783,6 +1935,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	struct sk_buff *skb;
 	struct xdp_buff xdp;
 	u32 flags, misc;
+	u32 cmpl_ts;
 	void *data;
 	int rc = 0;
 
@@ -1810,8 +1963,10 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	dma_rmb();
 	prod = rxr->rx_prod;
 
-	if (cmp_type == CMP_TYPE_RX_L2_TPA_START_CMP) {
-		bnxt_tpa_start(bp, rxr, (struct rx_tpa_start_cmp *)rxcmp,
+	if (cmp_type == CMP_TYPE_RX_L2_TPA_START_CMP ||
+	    cmp_type == CMP_TYPE_RX_L2_TPA_START_V3_CMP) {
+		bnxt_tpa_start(bp, rxr, cmp_type,
+			       (struct rx_tpa_start_cmp *)rxcmp,
 			       (struct rx_tpa_start_cmp_ext *)rxcmp1);
 
 		*event |= BNXT_RX_EVENT;
@@ -1876,7 +2031,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		rc = -EIO;
 		if (rx_err & RX_CMPL_ERRORS_BUFFER_ERROR_MASK) {
 			bnapi->cp_ring.sw_stats.rx.rx_buf_errors++;
-			if (!(bp->flags & BNXT_FLAG_CHIP_P5) &&
+			if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS) &&
 			    !(bp->fw_cap & BNXT_FW_CAP_RING_MONITOR)) {
 				netdev_warn_once(bp->dev, "RX buffer error %x\n",
 						 rx_err);
@@ -1964,32 +2119,32 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	}
 
 	if (RX_CMP_HASH_VALID(rxcmp)) {
-		u32 hash_type = RX_CMP_HASH_TYPE(rxcmp);
-		enum pkt_hash_types type = PKT_HASH_TYPE_L4;
+		enum pkt_hash_types type;
 
-		/* RSS profiles 1 and 3 with extract code 0 for inner 4-tuple */
-		if (hash_type != 1 && hash_type != 3)
-			type = PKT_HASH_TYPE_L3;
+		if (cmp_type == CMP_TYPE_RX_L2_V3_CMP) {
+			type = bnxt_rss_ext_op(bp, rxcmp);
+		} else {
+			u32 hash_type = RX_CMP_HASH_TYPE(rxcmp);
+
+			/* RSS profiles 1 and 3 with extract code 0 for inner
+			 * 4-tuple
+			 */
+			if (hash_type != 1 && hash_type != 3)
+				type = PKT_HASH_TYPE_L3;
+			else
+				type = PKT_HASH_TYPE_L4;
+		}
 		skb_set_hash(skb, le32_to_cpu(rxcmp->rx_cmp_rss_hash), type);
 	}
 
-	cfa_code = RX_CMP_CFA_CODE(rxcmp1);
-	skb->protocol = eth_type_trans(skb, bnxt_get_pkt_dev(bp, cfa_code));
-
-	if ((rxcmp1->rx_cmp_flags2 &
-	     cpu_to_le32(RX_CMP_FLAGS2_META_FORMAT_VLAN)) &&
-	    (skb->dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX)) {
-		u32 meta_data = le32_to_cpu(rxcmp1->rx_cmp_meta_data);
-		u16 vtag = meta_data & RX_CMP_FLAGS2_METADATA_TCI_MASK;
-		__be16 vlan_proto = htons(meta_data >>
-					  RX_CMP_FLAGS2_METADATA_TPID_SFT);
+	if (cmp_type == CMP_TYPE_RX_L2_CMP)
+		dev = bnxt_get_pkt_dev(bp, RX_CMP_CFA_CODE(rxcmp1));
+	skb->protocol = eth_type_trans(skb, dev);
 
-		if (eth_type_vlan(vlan_proto)) {
-			__vlan_hwaccel_put_tag(skb, vlan_proto, vtag);
-		} else {
-			dev_kfree_skb(skb);
+	if (skb->dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX) {
+		skb = bnxt_rx_vlan(skb, cmp_type, rxcmp, rxcmp1);
+		if (!skb)
 			goto next_rx;
-		}
 	}
 
 	skb_checksum_none_assert(skb);
@@ -2005,10 +2160,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		}
 	}
 
-	if (unlikely((flags & RX_CMP_FLAGS_ITYPES_MASK) ==
-		     RX_CMP_FLAGS_ITYPE_PTP_W_TS) || bp->ptp_all_rx_tstamp) {
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
-			u32 cmpl_ts = le32_to_cpu(rxcmp1->rx_cmp_timestamp);
+	if (bnxt_rx_ts_valid(bp, flags, rxcmp1, &cmpl_ts)) {
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 			u64 ns, ts;
 
 			if (!bnxt_get_rx_ts_p5(bp, &ts, cmpl_ts)) {
@@ -2032,7 +2185,7 @@ next_rx:
 
 next_rx_no_len:
 	rxr->rx_prod = NEXT_RX(prod);
-	rxr->rx_next_cons = NEXT_RX(cons);
+	rxr->rx_next_cons = RING_RX(bp, NEXT_RX(cons));
 
 next_rx_no_prod_no_len:
 	*raw_cons = tmp_raw_cons;
@@ -2071,7 +2224,8 @@ static int bnxt_force_rx_discard(struct bnxt *bp,
 	 */
 	dma_rmb();
 	cmp_type = RX_CMP_TYPE(rxcmp);
-	if (cmp_type == CMP_TYPE_RX_L2_CMP) {
+	if (cmp_type == CMP_TYPE_RX_L2_CMP ||
+	    cmp_type == CMP_TYPE_RX_L2_V3_CMP) {
 		rxcmp1->rx_cmp_cfa_code_errors_v2 |=
 			cpu_to_le32(RX_CMPL_ERRORS_CRC_ERROR);
 	} else if (cmp_type == CMP_TYPE_RX_L2_TPA_END_CMP) {
@@ -2131,6 +2285,10 @@ static u16 bnxt_agg_ring_id_to_grp_idx(struct bnxt *bp, u16 ring_id)
 
 static u16 bnxt_get_force_speed(struct bnxt_link_info *link_info)
 {
+	struct bnxt *bp = container_of(link_info, struct bnxt, link_info);
+
+	if (bp->phy_flags & BNXT_PHY_FL_SPEEDS2)
+		return link_info->force_link_speed2;
 	if (link_info->req_signal_mode == BNXT_SIG_MODE_PAM4)
 		return link_info->force_pam4_link_speed;
 	return link_info->force_link_speed;
@@ -2138,6 +2296,28 @@ static u16 bnxt_get_force_speed(struct bnxt_link_info *link_info)
 
 static void bnxt_set_force_speed(struct bnxt_link_info *link_info)
 {
+	struct bnxt *bp = container_of(link_info, struct bnxt, link_info);
+
+	if (bp->phy_flags & BNXT_PHY_FL_SPEEDS2) {
+		link_info->req_link_speed = link_info->force_link_speed2;
+		link_info->req_signal_mode = BNXT_SIG_MODE_NRZ;
+		switch (link_info->req_link_speed) {
+		case BNXT_LINK_SPEED_50GB_PAM4:
+		case BNXT_LINK_SPEED_100GB_PAM4:
+		case BNXT_LINK_SPEED_200GB_PAM4:
+		case BNXT_LINK_SPEED_400GB_PAM4:
+			link_info->req_signal_mode = BNXT_SIG_MODE_PAM4;
+			break;
+		case BNXT_LINK_SPEED_100GB_PAM4_112:
+		case BNXT_LINK_SPEED_200GB_PAM4_112:
+		case BNXT_LINK_SPEED_400GB_PAM4_112:
+			link_info->req_signal_mode = BNXT_SIG_MODE_PAM4_112;
+			break;
+		default:
+			link_info->req_signal_mode = BNXT_SIG_MODE_NRZ;
+		}
+		return;
+	}
 	link_info->req_link_speed = link_info->force_link_speed;
 	link_info->req_signal_mode = BNXT_SIG_MODE_NRZ;
 	if (link_info->force_pam4_link_speed) {
@@ -2148,12 +2328,25 @@ static void bnxt_set_force_speed(struct bnxt_link_info *link_info)
 
 static void bnxt_set_auto_speed(struct bnxt_link_info *link_info)
 {
+	struct bnxt *bp = container_of(link_info, struct bnxt, link_info);
+
+	if (bp->phy_flags & BNXT_PHY_FL_SPEEDS2) {
+		link_info->advertising = link_info->auto_link_speeds2;
+		return;
+	}
 	link_info->advertising = link_info->auto_link_speeds;
 	link_info->advertising_pam4 = link_info->auto_pam4_link_speeds;
 }
 
 static bool bnxt_force_speed_updated(struct bnxt_link_info *link_info)
 {
+	struct bnxt *bp = container_of(link_info, struct bnxt, link_info);
+
+	if (bp->phy_flags & BNXT_PHY_FL_SPEEDS2) {
+		if (link_info->req_link_speed != link_info->force_link_speed2)
+			return true;
+		return false;
+	}
 	if (link_info->req_signal_mode == BNXT_SIG_MODE_NRZ &&
 	    link_info->req_link_speed != link_info->force_link_speed)
 		return true;
@@ -2165,6 +2358,13 @@ static bool bnxt_force_speed_updated(struct bnxt_link_info *link_info)
 
 static bool bnxt_auto_speed_updated(struct bnxt_link_info *link_info)
 {
+	struct bnxt *bp = container_of(link_info, struct bnxt, link_info);
+
+	if (bp->phy_flags & BNXT_PHY_FL_SPEEDS2) {
+		if (link_info->advertising != link_info->auto_link_speeds2)
+			return true;
+		return false;
+	}
 	if (link_info->advertising != link_info->auto_link_speeds ||
 	    link_info->advertising_pam4 != link_info->auto_pam4_link_speeds)
 		return true;
@@ -2415,7 +2615,7 @@ static int bnxt_async_event_process(struct bnxt *bp,
 		struct bnxt_rx_ring_info *rxr;
 		u16 grp_idx;
 
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 			goto async_event_process_exit;
 
 		netdev_warn(bp->dev, "Ring monitor event, ring type %lu id 0x%x\n",
@@ -2588,7 +2788,6 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	struct bnxt_napi *bnapi = cpr->bnapi;
 	u32 raw_cons = cpr->cp_raw_cons;
 	u32 cons;
-	int tx_pkts = 0;
 	int rx_pkts = 0;
 	u8 event = 0;
 	struct tx_cmp *txcmp;
@@ -2596,6 +2795,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	cpr->has_more_work = 0;
 	cpr->had_work_done = 1;
 	while (1) {
+		u8 cmp_type;
 		int rc;
 
 		cons = RING_CMP(raw_cons);
@@ -2608,17 +2808,31 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		 * reading any further.
 		 */
 		dma_rmb();
-		if (TX_CMP_TYPE(txcmp) == CMP_TYPE_TX_L2_CMP) {
-			tx_pkts++;
+		cmp_type = TX_CMP_TYPE(txcmp);
+		if (cmp_type == CMP_TYPE_TX_L2_CMP ||
+		    cmp_type == CMP_TYPE_TX_L2_COAL_CMP) {
+			u32 opaque = txcmp->tx_cmp_opaque;
+			struct bnxt_tx_ring_info *txr;
+			u16 tx_freed;
+
+			txr = bnapi->tx_ring[TX_OPAQUE_RING(opaque)];
+			event |= BNXT_TX_CMP_EVENT;
+			if (cmp_type == CMP_TYPE_TX_L2_COAL_CMP)
+				txr->tx_hw_cons = TX_CMP_SQ_CONS_IDX(txcmp);
+			else
+				txr->tx_hw_cons = TX_OPAQUE_PROD(bp, opaque);
+			tx_freed = (txr->tx_hw_cons - txr->tx_cons) &
+				   bp->tx_ring_mask;
 			/* return full budget so NAPI will complete. */
-			if (unlikely(tx_pkts >= bp->tx_wake_thresh)) {
+			if (unlikely(tx_freed >= bp->tx_wake_thresh)) {
 				rx_pkts = budget;
 				raw_cons = NEXT_RAW_CMP(raw_cons);
 				if (budget)
 					cpr->has_more_work = 1;
 				break;
 			}
-		} else if ((TX_CMP_TYPE(txcmp) & 0x30) == 0x10) {
+		} else if (cmp_type >= CMP_TYPE_RX_L2_CMP &&
+			   cmp_type <= CMP_TYPE_RX_L2_TPA_START_V3_CMP) {
 			if (likely(budget))
 				rc = bnxt_rx_pkt(bp, cpr, &raw_cons, &event);
 			else
@@ -2635,12 +2849,9 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 				rx_pkts++;
 			else if (rc == -EBUSY)	/* partial completion */
 				break;
-		} else if (unlikely((TX_CMP_TYPE(txcmp) ==
-				     CMPL_BASE_TYPE_HWRM_DONE) ||
-				    (TX_CMP_TYPE(txcmp) ==
-				     CMPL_BASE_TYPE_HWRM_FWD_REQ) ||
-				    (TX_CMP_TYPE(txcmp) ==
-				     CMPL_BASE_TYPE_HWRM_ASYNC_EVENT))) {
+		} else if (unlikely(cmp_type == CMPL_BASE_TYPE_HWRM_DONE ||
+				    cmp_type == CMPL_BASE_TYPE_HWRM_FWD_REQ ||
+				    cmp_type == CMPL_BASE_TYPE_HWRM_ASYNC_EVENT)) {
 			bnxt_hwrm_handler(bp, txcmp);
 		}
 		raw_cons = NEXT_RAW_CMP(raw_cons);
@@ -2655,7 +2866,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		xdp_do_flush();
 
 	if (event & BNXT_TX_EVENT) {
-		struct bnxt_tx_ring_info *txr = bnapi->tx_ring;
+		struct bnxt_tx_ring_info *txr = bnapi->tx_ring[0];
 		u16 prod = txr->tx_prod;
 
 		/* Sync BD data before updating doorbell */
@@ -2665,7 +2876,6 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	}
 
 	cpr->cp_raw_cons = raw_cons;
-	bnapi->tx_pkts += tx_pkts;
 	bnapi->events |= event;
 	return rx_pkts;
 }
@@ -2673,7 +2883,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 static void __bnxt_poll_work_done(struct bnxt *bp, struct bnxt_napi *bnapi,
 				  int budget)
 {
-	if (bnapi->tx_pkts && !bnapi->tx_fault)
+	if ((bnapi->events & BNXT_TX_CMP_EVENT) && !bnapi->tx_fault)
 		bnapi->tx_int(bp, bnapi, budget);
 
 	if ((bnapi->events & BNXT_RX_EVENT) && !(bnapi->in_reset)) {
@@ -2686,7 +2896,7 @@ static void __bnxt_poll_work_done(struct bnxt *bp, struct bnxt_napi *bnapi,
 
 		bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod);
 	}
-	bnapi->events = 0;
+	bnapi->events &= BNXT_TX_CMP_EVENT;
 }
 
 static int bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
@@ -2826,10 +3036,10 @@ static int __bnxt_poll_cqs(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 	struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
 	int i, work_done = 0;
 
-	for (i = 0; i < 2; i++) {
-		struct bnxt_cp_ring_info *cpr2 = cpr->cp_ring_arr[i];
+	for (i = 0; i < cpr->cp_ring_count; i++) {
+		struct bnxt_cp_ring_info *cpr2 = &cpr->cp_ring_arr[i];
 
-		if (cpr2) {
+		if (cpr2->had_nqe_notify) {
 			work_done += __bnxt_poll_work(bp, cpr2,
 						      budget - work_done);
 			cpr->has_more_work |= cpr2->has_more_work;
@@ -2844,14 +3054,22 @@ static void __bnxt_poll_cqs_done(struct bnxt *bp, struct bnxt_napi *bnapi,
 	struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
 	int i;
 
-	for (i = 0; i < 2; i++) {
-		struct bnxt_cp_ring_info *cpr2 = cpr->cp_ring_arr[i];
+	for (i = 0; i < cpr->cp_ring_count; i++) {
+		struct bnxt_cp_ring_info *cpr2 = &cpr->cp_ring_arr[i];
 		struct bnxt_db_info *db;
 
-		if (cpr2 && cpr2->had_work_done) {
+		if (cpr2->had_work_done) {
+			u32 tgl = 0;
+
+			if (dbr_type == DBR_TYPE_CQ_ARMALL) {
+				cpr2->had_nqe_notify = 0;
+				tgl = cpr2->toggle;
+			}
 			db = &cpr2->cp_db;
-			bnxt_writeq(bp, db->db_key64 | dbr_type |
-				    RING_CMP(cpr2->cp_raw_cons), db->doorbell);
+			bnxt_writeq(bp,
+				    db->db_key64 | dbr_type | DB_TOGGLE(tgl) |
+				    DB_RING_IDX(db, cpr2->cp_raw_cons),
+				    db->doorbell);
 			cpr2->had_work_done = 0;
 		}
 	}
@@ -2878,6 +3096,8 @@ static int bnxt_poll_p5(struct napi_struct *napi, int budget)
 		work_done = __bnxt_poll_cqs(bp, bnapi, budget);
 	}
 	while (1) {
+		u16 type;
+
 		cons = RING_CMP(raw_cons);
 		nqcmp = &cpr->nq_desc_ring[CP_RING(cons)][CP_IDX(cons)];
 
@@ -2899,15 +3119,21 @@ static int bnxt_poll_p5(struct napi_struct *napi, int budget)
 		 */
 		dma_rmb();
 
-		if (nqcmp->type == cpu_to_le16(NQ_CN_TYPE_CQ_NOTIFICATION)) {
+		type = le16_to_cpu(nqcmp->type);
+		if (NQE_CN_TYPE(type) == NQ_CN_TYPE_CQ_NOTIFICATION) {
 			u32 idx = le32_to_cpu(nqcmp->cq_handle_low);
+			u32 cq_type = BNXT_NQ_HDL_TYPE(idx);
 			struct bnxt_cp_ring_info *cpr2;
 
 			/* No more budget for RX work */
-			if (budget && work_done >= budget && idx == BNXT_RX_HDL)
+			if (budget && work_done >= budget &&
+			    cq_type == BNXT_NQ_HDL_TYPE_RX)
 				break;
 
-			cpr2 = cpr->cp_ring_arr[idx];
+			idx = BNXT_NQ_HDL_IDX(idx);
+			cpr2 = &cpr->cp_ring_arr[idx];
+			cpr2->had_nqe_notify = 1;
+			cpr2->toggle = NQE_CN_TOGGLE(type);
 			work_done += __bnxt_poll_work(bp, cpr2,
 						      budget - work_done);
 			cpr->has_more_work |= cpr2->has_more_work;
@@ -2922,8 +3148,9 @@ static int bnxt_poll_p5(struct napi_struct *napi, int budget)
 		BNXT_DB_NQ_P5(&cpr->cp_db, raw_cons);
 	}
 poll_done:
-	cpr_rx = cpr->cp_ring_arr[BNXT_RX_HDL];
-	if (cpr_rx && (bp->flags & BNXT_FLAG_DIM)) {
+	cpr_rx = &cpr->cp_ring_arr[0];
+	if (cpr_rx->cp_ring_type == BNXT_NQ_HDL_TYPE_RX &&
+	    (bp->flags & BNXT_FLAG_DIM)) {
 		struct dim_sample dim_sample = {};
 
 		dim_update_sample(cpr->event_ctr,
@@ -3097,20 +3324,20 @@ static void bnxt_free_skbs(struct bnxt *bp)
 	bnxt_free_rx_skbs(bp);
 }
 
-static void bnxt_init_ctx_mem(struct bnxt_mem_init *mem_init, void *p, int len)
+static void bnxt_init_ctx_mem(struct bnxt_ctx_mem_type *ctxm, void *p, int len)
 {
-	u8 init_val = mem_init->init_val;
-	u16 offset = mem_init->offset;
+	u8 init_val = ctxm->init_value;
+	u16 offset = ctxm->init_offset;
 	u8 *p2 = p;
 	int i;
 
 	if (!init_val)
 		return;
-	if (offset == BNXT_MEM_INVALID_OFFSET) {
+	if (offset == BNXT_CTX_INIT_INVALID_OFFSET) {
 		memset(p, init_val, len);
 		return;
 	}
-	for (i = 0; i < len; i += mem_init->size)
+	for (i = 0; i < len; i += ctxm->entry_size)
 		*(p2 + i + offset) = init_val;
 }
 
@@ -3177,8 +3404,8 @@ static int bnxt_alloc_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem)
 		if (!rmem->pg_arr[i])
 			return -ENOMEM;
 
-		if (rmem->mem_init)
-			bnxt_init_ctx_mem(rmem->mem_init, rmem->pg_arr[i],
+		if (rmem->ctx_mem)
+			bnxt_init_ctx_mem(rmem->ctx_mem, rmem->pg_arr[i],
 					  rmem->page_size);
 		if (rmem->nr_pages > 1 || rmem->depth > 0) {
 			if (i == rmem->nr_pages - 2 &&
@@ -3225,7 +3452,7 @@ static int bnxt_alloc_tpa_info(struct bnxt *bp)
 	int i, j;
 
 	bp->max_tpa = MAX_TPA;
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		if (!bp->max_tpa_v2)
 			return 0;
 		bp->max_tpa = max_t(u16, bp->max_tpa_v2, MAX_TPA_P5);
@@ -3240,7 +3467,7 @@ static int bnxt_alloc_tpa_info(struct bnxt *bp)
 		if (!rxr->rx_tpa)
 			return -ENOMEM;
 
-		if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+		if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 			continue;
 		for (j = 0; j < bp->max_tpa; j++) {
 			agg = kcalloc(MAX_SKB_FRAGS, sizeof(*agg), GFP_KERNEL);
@@ -3298,6 +3525,7 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
 		pp.pool_size += bp->rx_ring_size;
 	pp.nid = dev_to_node(&bp->pdev->dev);
 	pp.napi = &rxr->bnapi->napi;
+	pp.netdev = bp->dev;
 	pp.dev = &bp->pdev->dev;
 	pp.dma_dir = bp->rx_dir;
 	pp.max_len = PAGE_SIZE;
@@ -3395,6 +3623,15 @@ static void bnxt_free_tx_rings(struct bnxt *bp)
 	}
 }
 
+#define BNXT_TC_TO_RING_BASE(bp, tc)	\
+	((tc) * (bp)->tx_nr_rings_per_tc)
+
+#define BNXT_RING_TO_TC_OFF(bp, tx)	\
+	((tx) % (bp)->tx_nr_rings_per_tc)
+
+#define BNXT_RING_TO_TC(bp, tx)		\
+	((tx) / (bp)->tx_nr_rings_per_tc)
+
 static int bnxt_alloc_tx_rings(struct bnxt *bp)
 {
 	int i, j, rc;
@@ -3450,7 +3687,7 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp)
 		spin_lock_init(&txr->xdp_tx_lock);
 		if (i < bp->tx_nr_rings_xdp)
 			continue;
-		if (i % bp->tx_nr_rings_per_tc == (bp->tx_nr_rings_per_tc - 1))
+		if (BNXT_RING_TO_TC_OFF(bp, i) == (bp->tx_nr_rings_per_tc - 1))
 			j++;
 	}
 	return 0;
@@ -3533,36 +3770,33 @@ static void bnxt_free_cp_rings(struct bnxt *bp)
 
 		bnxt_free_ring(bp, &ring->ring_mem);
 
-		for (j = 0; j < 2; j++) {
-			struct bnxt_cp_ring_info *cpr2 = cpr->cp_ring_arr[j];
+		if (!cpr->cp_ring_arr)
+			continue;
+
+		for (j = 0; j < cpr->cp_ring_count; j++) {
+			struct bnxt_cp_ring_info *cpr2 = &cpr->cp_ring_arr[j];
 
-			if (cpr2) {
-				ring = &cpr2->cp_ring_struct;
-				bnxt_free_ring(bp, &ring->ring_mem);
-				bnxt_free_cp_arrays(cpr2);
-				kfree(cpr2);
-				cpr->cp_ring_arr[j] = NULL;
-			}
+			ring = &cpr2->cp_ring_struct;
+			bnxt_free_ring(bp, &ring->ring_mem);
+			bnxt_free_cp_arrays(cpr2);
 		}
+		kfree(cpr->cp_ring_arr);
+		cpr->cp_ring_arr = NULL;
+		cpr->cp_ring_count = 0;
 	}
 }
 
-static struct bnxt_cp_ring_info *bnxt_alloc_cp_sub_ring(struct bnxt *bp)
+static int bnxt_alloc_cp_sub_ring(struct bnxt *bp,
+				  struct bnxt_cp_ring_info *cpr)
 {
 	struct bnxt_ring_mem_info *rmem;
 	struct bnxt_ring_struct *ring;
-	struct bnxt_cp_ring_info *cpr;
 	int rc;
 
-	cpr = kzalloc(sizeof(*cpr), GFP_KERNEL);
-	if (!cpr)
-		return NULL;
-
 	rc = bnxt_alloc_cp_arrays(cpr, bp->cp_nr_pages);
 	if (rc) {
 		bnxt_free_cp_arrays(cpr);
-		kfree(cpr);
-		return NULL;
+		return -ENOMEM;
 	}
 	ring = &cpr->cp_ring_struct;
 	rmem = &ring->ring_mem;
@@ -3575,23 +3809,26 @@ static struct bnxt_cp_ring_info *bnxt_alloc_cp_sub_ring(struct bnxt *bp)
 	if (rc) {
 		bnxt_free_ring(bp, rmem);
 		bnxt_free_cp_arrays(cpr);
-		kfree(cpr);
-		cpr = NULL;
 	}
-	return cpr;
+	return rc;
 }
 
 static int bnxt_alloc_cp_rings(struct bnxt *bp)
 {
 	bool sh = !!(bp->flags & BNXT_FLAG_SHARED_RINGS);
-	int i, rc, ulp_base_vec, ulp_msix;
+	int i, j, rc, ulp_base_vec, ulp_msix;
+	int tcs = netdev_get_num_tc(bp->dev);
 
+	if (!tcs)
+		tcs = 1;
 	ulp_msix = bnxt_get_ulp_msix_num(bp);
 	ulp_base_vec = bnxt_get_ulp_msix_base(bp);
-	for (i = 0; i < bp->cp_nr_rings; i++) {
+	for (i = 0, j = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
-		struct bnxt_cp_ring_info *cpr;
+		struct bnxt_cp_ring_info *cpr, *cpr2;
 		struct bnxt_ring_struct *ring;
+		int cp_count = 0, k;
+		int rx = 0, tx = 0;
 
 		if (!bnapi)
 			continue;
@@ -3609,35 +3846,55 @@ static int bnxt_alloc_cp_rings(struct bnxt *bp)
 		else
 			ring->map_idx = i;
 
-		if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+		if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 			continue;
 
 		if (i < bp->rx_nr_rings) {
-			struct bnxt_cp_ring_info *cpr2 =
-				bnxt_alloc_cp_sub_ring(bp);
-
-			cpr->cp_ring_arr[BNXT_RX_HDL] = cpr2;
-			if (!cpr2)
-				return -ENOMEM;
-			cpr2->bnapi = bnapi;
+			cp_count++;
+			rx = 1;
+		}
+		if (i < bp->tx_nr_rings_xdp) {
+			cp_count++;
+			tx = 1;
+		} else if ((sh && i < bp->tx_nr_rings) ||
+			 (!sh && i >= bp->rx_nr_rings)) {
+			cp_count += tcs;
+			tx = 1;
 		}
-		if ((sh && i < bp->tx_nr_rings) ||
-		    (!sh && i >= bp->rx_nr_rings)) {
-			struct bnxt_cp_ring_info *cpr2 =
-				bnxt_alloc_cp_sub_ring(bp);
 
-			cpr->cp_ring_arr[BNXT_TX_HDL] = cpr2;
-			if (!cpr2)
-				return -ENOMEM;
+		cpr->cp_ring_arr = kcalloc(cp_count, sizeof(*cpr),
+					   GFP_KERNEL);
+		if (!cpr->cp_ring_arr)
+			return -ENOMEM;
+		cpr->cp_ring_count = cp_count;
+
+		for (k = 0; k < cp_count; k++) {
+			cpr2 = &cpr->cp_ring_arr[k];
+			rc = bnxt_alloc_cp_sub_ring(bp, cpr2);
+			if (rc)
+				return rc;
 			cpr2->bnapi = bnapi;
+			cpr2->cp_idx = k;
+			if (!k && rx) {
+				bp->rx_ring[i].rx_cpr = cpr2;
+				cpr2->cp_ring_type = BNXT_NQ_HDL_TYPE_RX;
+			} else {
+				int n, tc = k - rx;
+
+				n = BNXT_TC_TO_RING_BASE(bp, tc) + j;
+				bp->tx_ring[n].tx_cpr = cpr2;
+				cpr2->cp_ring_type = BNXT_NQ_HDL_TYPE_TX;
+			}
 		}
+		if (tx)
+			j++;
 	}
 	return 0;
 }
 
 static void bnxt_init_ring_struct(struct bnxt *bp)
 {
-	int i;
+	int i, j;
 
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
@@ -3682,18 +3939,16 @@ static void bnxt_init_ring_struct(struct bnxt *bp)
 		rmem->vmem = (void **)&rxr->rx_agg_ring;
 
 skip_rx:
-		txr = bnapi->tx_ring;
-		if (!txr)
-			continue;
-
-		ring = &txr->tx_ring_struct;
-		rmem = &ring->ring_mem;
-		rmem->nr_pages = bp->tx_nr_pages;
-		rmem->page_size = HW_RXBD_RING_SIZE;
-		rmem->pg_arr = (void **)txr->tx_desc_ring;
-		rmem->dma_arr = txr->tx_desc_mapping;
-		rmem->vmem_size = SW_TXBD_RING_SIZE * bp->tx_nr_pages;
-		rmem->vmem = (void **)&txr->tx_buf_ring;
+		bnxt_for_each_napi_tx(j, bnapi, txr) {
+			ring = &txr->tx_ring_struct;
+			rmem = &ring->ring_mem;
+			rmem->nr_pages = bp->tx_nr_pages;
+			rmem->page_size = HW_TXBD_RING_SIZE;
+			rmem->pg_arr = (void **)txr->tx_desc_ring;
+			rmem->dma_arr = txr->tx_desc_mapping;
+			rmem->vmem_size = SW_TXBD_RING_SIZE * bp->tx_nr_pages;
+			rmem->vmem = (void **)&txr->tx_buf_ring;
+		}
 	}
 }
 
@@ -3784,6 +4039,9 @@ static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr)
 	ring = &rxr->rx_ring_struct;
 	bnxt_init_rxbd_pages(ring, type);
 
+	netif_queue_set_napi(bp->dev, ring_nr, NETDEV_QUEUE_TYPE_RX,
+			     &rxr->bnapi->napi);
+
 	if (BNXT_RX_PAGE_MODE(bp) && bp->xdp_prog) {
 		bpf_prog_add(bp->xdp_prog, 1);
 		rxr->xdp_prog = bp->xdp_prog;
@@ -3814,11 +4072,10 @@ static void bnxt_init_cp_rings(struct bnxt *bp)
 		ring->fw_ring_id = INVALID_HW_RING_ID;
 		cpr->rx_ring_coal.coal_ticks = bp->rx_coal.coal_ticks;
 		cpr->rx_ring_coal.coal_bufs = bp->rx_coal.coal_bufs;
-		for (j = 0; j < 2; j++) {
-			struct bnxt_cp_ring_info *cpr2 = cpr->cp_ring_arr[j];
-
-			if (!cpr2)
-				continue;
+		if (!cpr->cp_ring_arr)
+			continue;
+		for (j = 0; j < cpr->cp_ring_count; j++) {
+			struct bnxt_cp_ring_info *cpr2 = &cpr->cp_ring_arr[j];
 
 			ring = &cpr2->cp_ring_struct;
 			ring->fw_ring_id = INVALID_HW_RING_ID;
@@ -3861,6 +4118,11 @@ static int bnxt_init_tx_rings(struct bnxt *bp)
 		struct bnxt_ring_struct *ring = &txr->tx_ring_struct;
 
 		ring->fw_ring_id = INVALID_HW_RING_ID;
+
+		if (i >= bp->tx_nr_rings_xdp)
+			netif_queue_set_napi(bp->dev, i - bp->tx_nr_rings_xdp,
+					     NETDEV_QUEUE_TYPE_TX,
+					     &txr->bnapi->napi);
 	}
 
 	return 0;
@@ -3906,7 +4168,7 @@ static int bnxt_alloc_vnics(struct bnxt *bp)
 	int num_vnics = 1;
 
 #ifdef CONFIG_RFS_ACCEL
-	if ((bp->flags & (BNXT_FLAG_RFS | BNXT_FLAG_CHIP_P5)) == BNXT_FLAG_RFS)
+	if ((bp->flags & (BNXT_FLAG_RFS | BNXT_FLAG_CHIP_P5_PLUS)) == BNXT_FLAG_RFS)
 		num_vnics += bp->rx_nr_rings;
 #endif
 
@@ -3937,13 +4199,22 @@ static void bnxt_init_vnics(struct bnxt *bp)
 		vnic->fw_l2_ctx_id = INVALID_HW_RING_ID;
 
 		if (bp->vnic_info[i].rss_hash_key) {
-			if (i == 0)
+			if (!i) {
+				u8 *key = (void *)vnic->rss_hash_key;
+				int k;
+
+				bp->toeplitz_prefix = 0;
 				get_random_bytes(vnic->rss_hash_key,
 					      HW_HASH_KEY_SIZE);
-			else
+				for (k = 0; k < 8; k++) {
+					bp->toeplitz_prefix <<= 8;
+					bp->toeplitz_prefix |= key[k];
+				}
+			} else {
 				memcpy(vnic->rss_hash_key,
 				       bp->vnic_info[0].rss_hash_key,
 				       HW_HASH_KEY_SIZE);
+			}
 		}
 	}
 }
@@ -4179,7 +4450,7 @@ static int bnxt_alloc_vnic_attributes(struct bnxt *bp)
 			}
 		}
 
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 			goto vnic_skip_grps;
 
 		if (vnic->flags & BNXT_VNIC_RSS_FLAG)
@@ -4193,13 +4464,13 @@ static int bnxt_alloc_vnic_attributes(struct bnxt *bp)
 			goto out;
 		}
 vnic_skip_grps:
-		if ((bp->flags & BNXT_FLAG_NEW_RSS_CAP) &&
+		if ((bp->rss_cap & BNXT_RSS_CAP_NEW_RSS_CAP) &&
 		    !(vnic->flags & BNXT_VNIC_RSS_FLAG))
 			continue;
 
 		/* Allocate rss table and hash key */
 		size = L1_CACHE_ALIGN(HW_HASH_INDEX_SIZE * sizeof(u16));
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 			size = L1_CACHE_ALIGN(BNXT_MAX_RSS_TABLE_SIZE_P5);
 
 		vnic->rss_table_size = size + HW_HASH_KEY_SIZE;
@@ -4309,7 +4580,7 @@ static int bnxt_hwrm_func_qstat_ext(struct bnxt *bp,
 	int rc;
 
 	if (!(bp->fw_cap & BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED) ||
-	    !(bp->flags & BNXT_FLAG_CHIP_P5))
+	    !(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		return -EOPNOTSUPP;
 
 	rc = hwrm_req_init(bp, req, HWRM_FUNC_QSTATS_EXT);
@@ -4347,7 +4618,7 @@ static void bnxt_init_stats(struct bnxt *bp)
 	stats = &cpr->stats;
 	rc = bnxt_hwrm_func_qstat_ext(bp, stats);
 	if (rc) {
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 			mask = (1ULL << 48) - 1;
 		else
 			mask = -1ULL;
@@ -4493,7 +4764,7 @@ alloc_tx_ext_stats:
 
 static void bnxt_clear_ring_indices(struct bnxt *bp)
 {
-	int i;
+	int i, j;
 
 	if (!bp->bnapi)
 		return;
@@ -4510,10 +4781,10 @@ static void bnxt_clear_ring_indices(struct bnxt *bp)
 		cpr = &bnapi->cp_ring;
 		cpr->cp_raw_cons = 0;
 
-		txr = bnapi->tx_ring;
-		if (txr) {
+		bnxt_for_each_napi_tx(j, bnapi, txr) {
 			txr->tx_prod = 0;
 			txr->tx_cons = 0;
+			txr->tx_hw_cons = 0;
 		}
 
 		rxr = bnapi->rx_ring;
@@ -4523,12 +4794,12 @@ static void bnxt_clear_ring_indices(struct bnxt *bp)
 			rxr->rx_sw_agg_prod = 0;
 			rxr->rx_next_cons = 0;
 		}
+		bnapi->events = 0;
 	}
 }
 
-static void bnxt_free_ntp_fltrs(struct bnxt *bp, bool irq_reinit)
+static void bnxt_free_ntp_fltrs(struct bnxt *bp, bool all)
 {
-#ifdef CONFIG_RFS_ACCEL
 	int i;
 
 	/* Under rtnl_lock and all our NAPIs have been disabled.  It's
@@ -4540,40 +4811,73 @@ static void bnxt_free_ntp_fltrs(struct bnxt *bp, bool irq_reinit)
 		struct bnxt_ntuple_filter *fltr;
 
 		head = &bp->ntp_fltr_hash_tbl[i];
-		hlist_for_each_entry_safe(fltr, tmp, head, hash) {
-			hlist_del(&fltr->hash);
+		hlist_for_each_entry_safe(fltr, tmp, head, base.hash) {
+			bnxt_del_l2_filter(bp, fltr->l2_fltr);
+			if (!all && (fltr->base.flags & BNXT_ACT_FUNC_DST))
+				continue;
+			hlist_del(&fltr->base.hash);
+			clear_bit(fltr->base.sw_id, bp->ntp_fltr_bmap);
+			bp->ntp_fltr_count--;
 			kfree(fltr);
 		}
 	}
-	if (irq_reinit) {
-		bitmap_free(bp->ntp_fltr_bmap);
-		bp->ntp_fltr_bmap = NULL;
-	}
+	if (!all)
+		return;
+
+	bitmap_free(bp->ntp_fltr_bmap);
+	bp->ntp_fltr_bmap = NULL;
 	bp->ntp_fltr_count = 0;
-#endif
 }
 
 static int bnxt_alloc_ntp_fltrs(struct bnxt *bp)
 {
-#ifdef CONFIG_RFS_ACCEL
 	int i, rc = 0;
 
-	if (!(bp->flags & BNXT_FLAG_RFS))
+	if (!(bp->flags & BNXT_FLAG_RFS) || bp->ntp_fltr_bmap)
 		return 0;
 
 	for (i = 0; i < BNXT_NTP_FLTR_HASH_SIZE; i++)
 		INIT_HLIST_HEAD(&bp->ntp_fltr_hash_tbl[i]);
 
 	bp->ntp_fltr_count = 0;
-	bp->ntp_fltr_bmap = bitmap_zalloc(BNXT_NTP_FLTR_MAX_FLTR, GFP_KERNEL);
+	bp->ntp_fltr_bmap = bitmap_zalloc(BNXT_MAX_FLTR, GFP_KERNEL);
 
 	if (!bp->ntp_fltr_bmap)
 		rc = -ENOMEM;
 
 	return rc;
-#else
-	return 0;
-#endif
+}
+
+static void bnxt_free_l2_filters(struct bnxt *bp, bool all)
+{
+	int i;
+
+	for (i = 0; i < BNXT_L2_FLTR_HASH_SIZE; i++) {
+		struct hlist_head *head;
+		struct hlist_node *tmp;
+		struct bnxt_l2_filter *fltr;
+
+		head = &bp->l2_fltr_hash_tbl[i];
+		hlist_for_each_entry_safe(fltr, tmp, head, base.hash) {
+			if (!all && (fltr->base.flags & BNXT_ACT_FUNC_DST))
+				continue;
+			hlist_del(&fltr->base.hash);
+			if (fltr->base.flags) {
+				clear_bit(fltr->base.sw_id, bp->ntp_fltr_bmap);
+				bp->ntp_fltr_count--;
+			}
+			kfree(fltr);
+		}
+	}
+}
+
+static void bnxt_init_l2_fltr_tbl(struct bnxt *bp)
+{
+	int i;
+
+	for (i = 0; i < BNXT_L2_FLTR_HASH_SIZE; i++)
+		INIT_HLIST_HEAD(&bp->l2_fltr_hash_tbl[i]);
+	get_random_bytes(&bp->hash_seed, sizeof(bp->hash_seed));
 }
 
 static void bnxt_free_mem(struct bnxt *bp, bool irq_re_init)
@@ -4583,7 +4887,8 @@ static void bnxt_free_mem(struct bnxt *bp, bool irq_re_init)
 	bnxt_free_rx_rings(bp);
 	bnxt_free_cp_rings(bp);
 	bnxt_free_all_cp_arrays(bp);
-	bnxt_free_ntp_fltrs(bp, irq_re_init);
+	bnxt_free_ntp_fltrs(bp, false);
+	bnxt_free_l2_filters(bp, false);
 	if (irq_re_init) {
 		bnxt_free_ring_stats(bp);
 		if (!(bp->phy_flags & BNXT_PHY_FL_PORT_STATS_NO_RESET) ||
@@ -4626,7 +4931,7 @@ static int bnxt_alloc_mem(struct bnxt *bp, bool irq_re_init)
 			bp->bnapi[i] = bnapi;
 			bp->bnapi[i]->index = i;
 			bp->bnapi[i]->bp = bp;
-			if (bp->flags & BNXT_FLAG_CHIP_P5) {
+			if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 				struct bnxt_cp_ring_info *cpr =
 					&bp->bnapi[i]->cp_ring;
 
@@ -4644,11 +4949,13 @@ static int bnxt_alloc_mem(struct bnxt *bp, bool irq_re_init)
 		for (i = 0; i < bp->rx_nr_rings; i++) {
 			struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
 
-			if (bp->flags & BNXT_FLAG_CHIP_P5) {
+			if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 				rxr->rx_ring_struct.ring_mem.flags =
 					BNXT_RMEM_RING_PTE_FLAG;
 				rxr->rx_agg_ring_struct.ring_mem.flags =
 					BNXT_RMEM_RING_PTE_FLAG;
+			} else {
+				rxr->rx_cpr =  &bp->bnapi[i]->cp_ring;
 			}
 			rxr->bnapi = bp->bnapi[i];
 			bp->bnapi[i]->rx_ring = &bp->rx_ring[i];
@@ -4671,22 +4978,33 @@ static int bnxt_alloc_mem(struct bnxt *bp, bool irq_re_init)
 		else
 			j = bp->rx_nr_rings;
 
-		for (i = 0; i < bp->tx_nr_rings; i++, j++) {
+		for (i = 0; i < bp->tx_nr_rings; i++) {
 			struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
+			struct bnxt_napi *bnapi2;
 
-			if (bp->flags & BNXT_FLAG_CHIP_P5)
+			if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 				txr->tx_ring_struct.ring_mem.flags =
 					BNXT_RMEM_RING_PTE_FLAG;
-			txr->bnapi = bp->bnapi[j];
-			bp->bnapi[j]->tx_ring = txr;
 			bp->tx_ring_map[i] = bp->tx_nr_rings_xdp + i;
 			if (i >= bp->tx_nr_rings_xdp) {
+				int k = j + BNXT_RING_TO_TC_OFF(bp, i);
+
+				bnapi2 = bp->bnapi[k];
 				txr->txq_index = i - bp->tx_nr_rings_xdp;
-				bp->bnapi[j]->tx_int = bnxt_tx_int;
+				txr->tx_napi_idx =
+					BNXT_RING_TO_TC(bp, txr->txq_index);
+				bnapi2->tx_ring[txr->tx_napi_idx] = txr;
+				bnapi2->tx_int = bnxt_tx_int;
 			} else {
-				bp->bnapi[j]->flags |= BNXT_NAPI_FLAG_XDP;
-				bp->bnapi[j]->tx_int = bnxt_tx_int_xdp;
+				bnapi2 = bp->bnapi[j];
+				bnapi2->flags |= BNXT_NAPI_FLAG_XDP;
+				bnapi2->tx_ring[0] = txr;
+				bnapi2->tx_int = bnxt_tx_int_xdp;
+				j++;
 			}
+			txr->bnapi = bnapi2;
+			if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
+				txr->tx_cpr = &bnapi2->cp_ring;
 		}
 
 		rc = bnxt_alloc_stats(bp);
@@ -4898,6 +5216,8 @@ int bnxt_hwrm_func_drv_unrgtr(struct bnxt *bp)
 	return hwrm_req_send(bp, req);
 }
 
+static int bnxt_set_tpa(struct bnxt *bp, bool set_tpa);
+
 static int bnxt_hwrm_tunnel_dst_port_free(struct bnxt *bp, u8 tunnel_type)
 {
 	struct hwrm_tunnel_dst_port_free_input *req;
@@ -4927,6 +5247,11 @@ static int bnxt_hwrm_tunnel_dst_port_free(struct bnxt *bp, u8 tunnel_type)
 		bp->nge_port = 0;
 		bp->nge_fw_dst_port_id = INVALID_HW_RING_ID;
 		break;
+	case TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE:
+		req->tunnel_dst_port_id = cpu_to_le16(bp->vxlan_gpe_fw_dst_port_id);
+		bp->vxlan_gpe_port = 0;
+		bp->vxlan_gpe_fw_dst_port_id = INVALID_HW_RING_ID;
+		break;
 	default:
 		break;
 	}
@@ -4935,6 +5260,8 @@ static int bnxt_hwrm_tunnel_dst_port_free(struct bnxt *bp, u8 tunnel_type)
 	if (rc)
 		netdev_err(bp->dev, "hwrm_tunnel_dst_port_free failed. rc:%d\n",
 			   rc);
+	if (bp->flags & BNXT_FLAG_TPA)
+		bnxt_set_tpa(bp, true);
 	return rc;
 }
 
@@ -4970,9 +5297,16 @@ static int bnxt_hwrm_tunnel_dst_port_alloc(struct bnxt *bp, __be16 port,
 		bp->nge_port = port;
 		bp->nge_fw_dst_port_id = le16_to_cpu(resp->tunnel_dst_port_id);
 		break;
+	case TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE:
+		bp->vxlan_gpe_port = port;
+		bp->vxlan_gpe_fw_dst_port_id =
+			le16_to_cpu(resp->tunnel_dst_port_id);
+		break;
 	default:
 		break;
 	}
+	if (bp->flags & BNXT_FLAG_TPA)
+		bnxt_set_tpa(bp, true);
 
 err_out:
 	hwrm_req_drop(bp, req);
@@ -4998,25 +5332,301 @@ static int bnxt_hwrm_cfa_l2_set_rx_mask(struct bnxt *bp, u16 vnic_id)
 	return hwrm_req_send_silent(bp, req);
 }
 
+void bnxt_del_l2_filter(struct bnxt *bp, struct bnxt_l2_filter *fltr)
+{
+	if (!atomic_dec_and_test(&fltr->refcnt))
+		return;
+	spin_lock_bh(&bp->ntp_fltr_lock);
+	if (!test_and_clear_bit(BNXT_FLTR_INSERTED, &fltr->base.state)) {
+		spin_unlock_bh(&bp->ntp_fltr_lock);
+		return;
+	}
+	hlist_del_rcu(&fltr->base.hash);
+	if (fltr->base.flags) {
+		clear_bit(fltr->base.sw_id, bp->ntp_fltr_bmap);
+		bp->ntp_fltr_count--;
+	}
+	spin_unlock_bh(&bp->ntp_fltr_lock);
+	kfree_rcu(fltr, base.rcu);
+}
+
+static struct bnxt_l2_filter *__bnxt_lookup_l2_filter(struct bnxt *bp,
+						      struct bnxt_l2_key *key,
+						      u32 idx)
+{
+	struct hlist_head *head = &bp->l2_fltr_hash_tbl[idx];
+	struct bnxt_l2_filter *fltr;
+
+	hlist_for_each_entry_rcu(fltr, head, base.hash) {
+		struct bnxt_l2_key *l2_key = &fltr->l2_key;
+
+		if (ether_addr_equal(l2_key->dst_mac_addr, key->dst_mac_addr) &&
+		    l2_key->vlan == key->vlan)
+			return fltr;
+	}
+	return NULL;
+}
+
+static struct bnxt_l2_filter *bnxt_lookup_l2_filter(struct bnxt *bp,
+						    struct bnxt_l2_key *key,
+						    u32 idx)
+{
+	struct bnxt_l2_filter *fltr = NULL;
+
+	rcu_read_lock();
+	fltr = __bnxt_lookup_l2_filter(bp, key, idx);
+	if (fltr)
+		atomic_inc(&fltr->refcnt);
+	rcu_read_unlock();
+	return fltr;
+}
+
+#define BNXT_IPV4_4TUPLE(bp, fkeys)					\
+	(((fkeys)->basic.ip_proto == IPPROTO_TCP &&			\
+	  (bp)->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4) ||	\
+	 ((fkeys)->basic.ip_proto == IPPROTO_UDP &&			\
+	  (bp)->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4))
+
+#define BNXT_IPV6_4TUPLE(bp, fkeys)					\
+	(((fkeys)->basic.ip_proto == IPPROTO_TCP &&			\
+	  (bp)->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6) ||	\
+	 ((fkeys)->basic.ip_proto == IPPROTO_UDP &&			\
+	  (bp)->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6))
+
+static u32 bnxt_get_rss_flow_tuple_len(struct bnxt *bp, struct flow_keys *fkeys)
+{
+	if (fkeys->basic.n_proto == htons(ETH_P_IP)) {
+		if (BNXT_IPV4_4TUPLE(bp, fkeys))
+			return sizeof(fkeys->addrs.v4addrs) +
+			       sizeof(fkeys->ports);
+
+		if (bp->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4)
+			return sizeof(fkeys->addrs.v4addrs);
+	}
+
+	if (fkeys->basic.n_proto == htons(ETH_P_IPV6)) {
+		if (BNXT_IPV6_4TUPLE(bp, fkeys))
+			return sizeof(fkeys->addrs.v6addrs) +
+			       sizeof(fkeys->ports);
+
+		if (bp->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6)
+			return sizeof(fkeys->addrs.v6addrs);
+	}
+
+	return 0;
+}
+
+static u32 bnxt_toeplitz(struct bnxt *bp, struct flow_keys *fkeys,
+			 const unsigned char *key)
+{
+	u64 prefix = bp->toeplitz_prefix, hash = 0;
+	struct bnxt_ipv4_tuple tuple4;
+	struct bnxt_ipv6_tuple tuple6;
+	int i, j, len = 0;
+	u8 *four_tuple;
+
+	len = bnxt_get_rss_flow_tuple_len(bp, fkeys);
+	if (!len)
+		return 0;
+
+	if (fkeys->basic.n_proto == htons(ETH_P_IP)) {
+		tuple4.v4addrs = fkeys->addrs.v4addrs;
+		tuple4.ports = fkeys->ports;
+		four_tuple = (unsigned char *)&tuple4;
+	} else {
+		tuple6.v6addrs = fkeys->addrs.v6addrs;
+		tuple6.ports = fkeys->ports;
+		four_tuple = (unsigned char *)&tuple6;
+	}
+
+	for (i = 0, j = 8; i < len; i++, j++) {
+		u8 byte = four_tuple[i];
+		int bit;
+
+		for (bit = 0; bit < 8; bit++, prefix <<= 1, byte <<= 1) {
+			if (byte & 0x80)
+				hash ^= prefix;
+		}
+		prefix |= (j < HW_HASH_KEY_SIZE) ? key[j] : 0;
+	}
+
+	/* The valid part of the hash is in the upper 32 bits. */
+	return (hash >> 32) & BNXT_NTP_FLTR_HASH_MASK;
+}
+
 #ifdef CONFIG_RFS_ACCEL
-static int bnxt_hwrm_cfa_ntuple_filter_free(struct bnxt *bp,
-					    struct bnxt_ntuple_filter *fltr)
+static struct bnxt_l2_filter *
+bnxt_lookup_l2_filter_from_key(struct bnxt *bp, struct bnxt_l2_key *key)
+{
+	struct bnxt_l2_filter *fltr;
+	u32 idx;
+
+	idx = jhash2(&key->filter_key, BNXT_L2_KEY_SIZE, bp->hash_seed) &
+	      BNXT_L2_FLTR_HASH_MASK;
+	fltr = bnxt_lookup_l2_filter(bp, key, idx);
+	return fltr;
+}
+#endif
+
+static int bnxt_init_l2_filter(struct bnxt *bp, struct bnxt_l2_filter *fltr,
+			       struct bnxt_l2_key *key, u32 idx)
+{
+	struct hlist_head *head;
+
+	ether_addr_copy(fltr->l2_key.dst_mac_addr, key->dst_mac_addr);
+	fltr->l2_key.vlan = key->vlan;
+	fltr->base.type = BNXT_FLTR_TYPE_L2;
+	if (fltr->base.flags) {
+		int bit_id;
+
+		bit_id = bitmap_find_free_region(bp->ntp_fltr_bmap,
+						 BNXT_MAX_FLTR, 0);
+		if (bit_id < 0)
+			return -ENOMEM;
+		fltr->base.sw_id = (u16)bit_id;
+	}
+	head = &bp->l2_fltr_hash_tbl[idx];
+	hlist_add_head_rcu(&fltr->base.hash, head);
+	set_bit(BNXT_FLTR_INSERTED, &fltr->base.state);
+	atomic_set(&fltr->refcnt, 1);
+	return 0;
+}
+
+static struct bnxt_l2_filter *bnxt_alloc_l2_filter(struct bnxt *bp,
+						   struct bnxt_l2_key *key,
+						   gfp_t gfp)
+{
+	struct bnxt_l2_filter *fltr;
+	u32 idx;
+	int rc;
+
+	idx = jhash2(&key->filter_key, BNXT_L2_KEY_SIZE, bp->hash_seed) &
+	      BNXT_L2_FLTR_HASH_MASK;
+	fltr = bnxt_lookup_l2_filter(bp, key, idx);
+	if (fltr)
+		return fltr;
+
+	fltr = kzalloc(sizeof(*fltr), gfp);
+	if (!fltr)
+		return ERR_PTR(-ENOMEM);
+	spin_lock_bh(&bp->ntp_fltr_lock);
+	rc = bnxt_init_l2_filter(bp, fltr, key, idx);
+	spin_unlock_bh(&bp->ntp_fltr_lock);
+	if (rc) {
+		bnxt_del_l2_filter(bp, fltr);
+		fltr = ERR_PTR(rc);
+	}
+	return fltr;
+}
+
+static u16 bnxt_vf_target_id(struct bnxt_pf_info *pf, u16 vf_idx)
+{
+#ifdef CONFIG_BNXT_SRIOV
+	struct bnxt_vf_info *vf = &pf->vf[vf_idx];
+
+	return vf->fw_fid;
+#else
+	return INVALID_HW_RING_ID;
+#endif
+}
+
+int bnxt_hwrm_l2_filter_free(struct bnxt *bp, struct bnxt_l2_filter *fltr)
+{
+	struct hwrm_cfa_l2_filter_free_input *req;
+	u16 target_id = 0xffff;
+	int rc;
+
+	if (fltr->base.flags & BNXT_ACT_FUNC_DST) {
+		struct bnxt_pf_info *pf = &bp->pf;
+
+		if (fltr->base.vf_idx >= pf->active_vfs)
+			return -EINVAL;
+
+		target_id = bnxt_vf_target_id(pf, fltr->base.vf_idx);
+		if (target_id == INVALID_HW_RING_ID)
+			return -EINVAL;
+	}
+
+	rc = hwrm_req_init(bp, req, HWRM_CFA_L2_FILTER_FREE);
+	if (rc)
+		return rc;
+
+	req->target_id = cpu_to_le16(target_id);
+	req->l2_filter_id = fltr->base.filter_id;
+	return hwrm_req_send(bp, req);
+}
+
+int bnxt_hwrm_l2_filter_alloc(struct bnxt *bp, struct bnxt_l2_filter *fltr)
+{
+	struct hwrm_cfa_l2_filter_alloc_output *resp;
+	struct hwrm_cfa_l2_filter_alloc_input *req;
+	u16 target_id = 0xffff;
+	int rc;
+
+	if (fltr->base.flags & BNXT_ACT_FUNC_DST) {
+		struct bnxt_pf_info *pf = &bp->pf;
+
+		if (fltr->base.vf_idx >= pf->active_vfs)
+			return -EINVAL;
+
+		target_id = bnxt_vf_target_id(pf, fltr->base.vf_idx);
+	}
+	rc = hwrm_req_init(bp, req, HWRM_CFA_L2_FILTER_ALLOC);
+	if (rc)
+		return rc;
+
+	req->target_id = cpu_to_le16(target_id);
+	req->flags = cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_RX);
+
+	if (!BNXT_CHIP_TYPE_NITRO_A0(bp))
+		req->flags |=
+			cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_FLAGS_OUTERMOST);
+	req->dst_id = cpu_to_le16(fltr->base.fw_vnic_id);
+	req->enables =
+		cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR |
+			    CFA_L2_FILTER_ALLOC_REQ_ENABLES_DST_ID |
+			    CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR_MASK);
+	ether_addr_copy(req->l2_addr, fltr->l2_key.dst_mac_addr);
+	eth_broadcast_addr(req->l2_addr_mask);
+
+	if (fltr->l2_key.vlan) {
+		req->enables |=
+			cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_IVLAN |
+				CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_IVLAN_MASK |
+				CFA_L2_FILTER_ALLOC_REQ_ENABLES_NUM_VLANS);
+		req->num_vlans = 1;
+		req->l2_ivlan = cpu_to_le16(fltr->l2_key.vlan);
+		req->l2_ivlan_mask = cpu_to_le16(0xfff);
+	}
+
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
+	if (!rc) {
+		fltr->base.filter_id = resp->l2_filter_id;
+		set_bit(BNXT_FLTR_VALID, &fltr->base.state);
+	}
+	hwrm_req_drop(bp, req);
+	return rc;
+}
+
+int bnxt_hwrm_cfa_ntuple_filter_free(struct bnxt *bp,
+				     struct bnxt_ntuple_filter *fltr)
 {
 	struct hwrm_cfa_ntuple_filter_free_input *req;
 	int rc;
 
+	set_bit(BNXT_FLTR_FW_DELETED, &fltr->base.state);
 	rc = hwrm_req_init(bp, req, HWRM_CFA_NTUPLE_FILTER_FREE);
 	if (rc)
 		return rc;
 
-	req->ntuple_filter_id = fltr->filter_id;
+	req->ntuple_filter_id = fltr->base.filter_id;
 	return hwrm_req_send(bp, req);
 }
 
 #define BNXT_NTP_FLTR_FLAGS					\
 	(CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_L2_FILTER_ID |	\
 	 CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_ETHERTYPE |	\
-	 CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_MACADDR |	\
 	 CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_IPADDR_TYPE |	\
 	 CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR |	\
 	 CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR_MASK |	\
@@ -5032,12 +5642,21 @@ static int bnxt_hwrm_cfa_ntuple_filter_free(struct bnxt *bp,
 #define BNXT_NTP_TUNNEL_FLTR_FLAG				\
 		CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE
 
-static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
-					     struct bnxt_ntuple_filter *fltr)
+void bnxt_fill_ipv6_mask(__be32 mask[4])
+{
+	int i;
+
+	for (i = 0; i < 4; i++)
+		mask[i] = cpu_to_be32(~0);
+}
+
+int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
+				      struct bnxt_ntuple_filter *fltr)
 {
 	struct hwrm_cfa_ntuple_filter_alloc_output *resp;
 	struct hwrm_cfa_ntuple_filter_alloc_input *req;
 	struct flow_keys *keys = &fltr->fkeys;
+	struct bnxt_l2_filter *l2_fltr;
 	struct bnxt_vnic_info *vnic;
 	u32 flags = 0;
 	int rc;
@@ -5046,42 +5665,47 @@ static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
 	if (rc)
 		return rc;
 
-	req->l2_filter_id = bp->vnic_info[0].fw_l2_filter_id[fltr->l2_fltr_idx];
+	l2_fltr = fltr->l2_fltr;
+	req->l2_filter_id = l2_fltr->base.filter_id;
+
 
 	if (bp->fw_cap & BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V2) {
 		flags = CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DEST_RFS_RING_IDX;
-		req->dst_id = cpu_to_le16(fltr->rxq);
+		req->dst_id = cpu_to_le16(fltr->base.rxq);
 	} else {
-		vnic = &bp->vnic_info[fltr->rxq + 1];
+		vnic = &bp->vnic_info[fltr->base.rxq + 1];
 		req->dst_id = cpu_to_le16(vnic->fw_vnic_id);
 	}
 	req->flags = cpu_to_le32(flags);
 	req->enables = cpu_to_le32(BNXT_NTP_FLTR_FLAGS);
 
 	req->ethertype = htons(ETH_P_IP);
-	memcpy(req->src_macaddr, fltr->src_mac_addr, ETH_ALEN);
 	req->ip_addr_type = CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4;
 	req->ip_protocol = keys->basic.ip_proto;
 
 	if (keys->basic.n_proto == htons(ETH_P_IPV6)) {
-		int i;
-
 		req->ethertype = htons(ETH_P_IPV6);
 		req->ip_addr_type =
 			CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6;
-		*(struct in6_addr *)&req->src_ipaddr[0] =
-			keys->addrs.v6addrs.src;
-		*(struct in6_addr *)&req->dst_ipaddr[0] =
-			keys->addrs.v6addrs.dst;
-		for (i = 0; i < 4; i++) {
-			req->src_ipaddr_mask[i] = cpu_to_be32(0xffffffff);
-			req->dst_ipaddr_mask[i] = cpu_to_be32(0xffffffff);
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_IP) {
+			*(struct in6_addr *)&req->src_ipaddr[0] =
+				keys->addrs.v6addrs.src;
+			bnxt_fill_ipv6_mask(req->src_ipaddr_mask);
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_DST_IP) {
+			*(struct in6_addr *)&req->dst_ipaddr[0] =
+				keys->addrs.v6addrs.dst;
+			bnxt_fill_ipv6_mask(req->dst_ipaddr_mask);
 		}
 	} else {
-		req->src_ipaddr[0] = keys->addrs.v4addrs.src;
-		req->src_ipaddr_mask[0] = cpu_to_be32(0xffffffff);
-		req->dst_ipaddr[0] = keys->addrs.v4addrs.dst;
-		req->dst_ipaddr_mask[0] = cpu_to_be32(0xffffffff);
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_IP) {
+			req->src_ipaddr[0] = keys->addrs.v4addrs.src;
+			req->src_ipaddr_mask[0] = cpu_to_be32(0xffffffff);
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_DST_IP) {
+			req->dst_ipaddr[0] = keys->addrs.v4addrs.dst;
+			req->dst_ipaddr_mask[0] = cpu_to_be32(0xffffffff);
+		}
 	}
 	if (keys->control.flags & FLOW_DIS_ENCAPSULATION) {
 		req->enables |= cpu_to_le32(BNXT_NTP_TUNNEL_FLTR_FLAG);
@@ -5089,80 +5713,85 @@ static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
 			CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL;
 	}
 
-	req->src_port = keys->ports.src;
-	req->src_port_mask = cpu_to_be16(0xffff);
-	req->dst_port = keys->ports.dst;
-	req->dst_port_mask = cpu_to_be16(0xffff);
+	if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_PORT) {
+		req->src_port = keys->ports.src;
+		req->src_port_mask = cpu_to_be16(0xffff);
+	}
+	if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_DST_PORT) {
+		req->dst_port = keys->ports.dst;
+		req->dst_port_mask = cpu_to_be16(0xffff);
+	}
 
 	resp = hwrm_req_hold(bp, req);
 	rc = hwrm_req_send(bp, req);
 	if (!rc)
-		fltr->filter_id = resp->ntuple_filter_id;
+		fltr->base.filter_id = resp->ntuple_filter_id;
 	hwrm_req_drop(bp, req);
 	return rc;
 }
-#endif
 
 static int bnxt_hwrm_set_vnic_filter(struct bnxt *bp, u16 vnic_id, u16 idx,
 				     const u8 *mac_addr)
 {
-	struct hwrm_cfa_l2_filter_alloc_output *resp;
-	struct hwrm_cfa_l2_filter_alloc_input *req;
+	struct bnxt_l2_filter *fltr;
+	struct bnxt_l2_key key;
 	int rc;
 
-	rc = hwrm_req_init(bp, req, HWRM_CFA_L2_FILTER_ALLOC);
-	if (rc)
-		return rc;
+	ether_addr_copy(key.dst_mac_addr, mac_addr);
+	key.vlan = 0;
+	fltr = bnxt_alloc_l2_filter(bp, &key, GFP_KERNEL);
+	if (IS_ERR(fltr))
+		return PTR_ERR(fltr);
 
-	req->flags = cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_RX);
-	if (!BNXT_CHIP_TYPE_NITRO_A0(bp))
-		req->flags |=
-			cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_FLAGS_OUTERMOST);
-	req->dst_id = cpu_to_le16(bp->vnic_info[vnic_id].fw_vnic_id);
-	req->enables =
-		cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR |
-			    CFA_L2_FILTER_ALLOC_REQ_ENABLES_DST_ID |
-			    CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR_MASK);
-	memcpy(req->l2_addr, mac_addr, ETH_ALEN);
-	req->l2_addr_mask[0] = 0xff;
-	req->l2_addr_mask[1] = 0xff;
-	req->l2_addr_mask[2] = 0xff;
-	req->l2_addr_mask[3] = 0xff;
-	req->l2_addr_mask[4] = 0xff;
-	req->l2_addr_mask[5] = 0xff;
-
-	resp = hwrm_req_hold(bp, req);
-	rc = hwrm_req_send(bp, req);
-	if (!rc)
-		bp->vnic_info[vnic_id].fw_l2_filter_id[idx] =
-							resp->l2_filter_id;
-	hwrm_req_drop(bp, req);
+	fltr->base.fw_vnic_id = bp->vnic_info[vnic_id].fw_vnic_id;
+	rc = bnxt_hwrm_l2_filter_alloc(bp, fltr);
+	if (rc)
+		bnxt_del_l2_filter(bp, fltr);
+	else
+		bp->vnic_info[vnic_id].l2_filters[idx] = fltr;
 	return rc;
 }
 
-static int bnxt_hwrm_clear_vnic_filter(struct bnxt *bp)
+static void bnxt_hwrm_clear_vnic_filter(struct bnxt *bp)
 {
-	struct hwrm_cfa_l2_filter_free_input *req;
 	u16 i, j, num_of_vnics = 1; /* only vnic 0 supported */
-	int rc;
 
 	/* Any associated ntuple filters will also be cleared by firmware. */
-	rc = hwrm_req_init(bp, req, HWRM_CFA_L2_FILTER_FREE);
-	if (rc)
-		return rc;
-	hwrm_req_hold(bp, req);
 	for (i = 0; i < num_of_vnics; i++) {
 		struct bnxt_vnic_info *vnic = &bp->vnic_info[i];
 
 		for (j = 0; j < vnic->uc_filter_count; j++) {
-			req->l2_filter_id = vnic->fw_l2_filter_id[j];
+			struct bnxt_l2_filter *fltr = vnic->l2_filters[j];
 
-			rc = hwrm_req_send(bp, req);
+			bnxt_hwrm_l2_filter_free(bp, fltr);
+			bnxt_del_l2_filter(bp, fltr);
 		}
 		vnic->uc_filter_count = 0;
 	}
-	hwrm_req_drop(bp, req);
-	return rc;
+}
+
+#define BNXT_DFLT_TUNL_TPA_BMAP				\
+	(VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_GRE |	\
+	 VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_IPV4 |	\
+	 VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_IPV6)
+
+static void bnxt_hwrm_vnic_update_tunl_tpa(struct bnxt *bp,
+					   struct hwrm_vnic_tpa_cfg_input *req)
+{
+	u32 tunl_tpa_bmap = BNXT_DFLT_TUNL_TPA_BMAP;
+
+	if (!(bp->fw_cap & BNXT_FW_CAP_VNIC_TUNNEL_TPA))
+		return;
+
+	if (bp->vxlan_port)
+		tunl_tpa_bmap |= VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_VXLAN;
+	if (bp->vxlan_gpe_port)
+		tunl_tpa_bmap |= VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_VXLAN_GPE;
+	if (bp->nge_port)
+		tunl_tpa_bmap |= VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_GENEVE;
+
+	req->enables |= cpu_to_le32(VNIC_TPA_CFG_REQ_ENABLES_TNL_TPA_EN);
+	req->tnl_tpa_en_bitmap = cpu_to_le32(tunl_tpa_bmap);
 }
 
 static int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, u16 vnic_id, u32 tpa_flags)
@@ -5211,7 +5840,7 @@ static int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, u16 vnic_id, u32 tpa_flags)
 			nsegs = (MAX_SKB_FRAGS - n) / n;
 		}
 
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 			segs = MAX_TPA_SEGS_P5;
 			max_aggs = bp->max_tpa;
 		} else {
@@ -5221,6 +5850,7 @@ static int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, u16 vnic_id, u32 tpa_flags)
 		req->max_aggs = cpu_to_le16(max_aggs);
 
 		req->min_agg_len = cpu_to_le32(512);
+		bnxt_hwrm_vnic_update_tunl_tpa(bp, req);
 	}
 	req->vnic_id = cpu_to_le16(vnic->fw_vnic_id);
 
@@ -5237,35 +5867,25 @@ static u16 bnxt_cp_ring_from_grp(struct bnxt *bp, struct bnxt_ring_struct *ring)
 
 static u16 bnxt_cp_ring_for_rx(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
-		struct bnxt_napi *bnapi = rxr->bnapi;
-		struct bnxt_cp_ring_info *cpr;
-
-		cpr = bnapi->cp_ring.cp_ring_arr[BNXT_RX_HDL];
-		return cpr->cp_ring_struct.fw_ring_id;
-	} else {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
+		return rxr->rx_cpr->cp_ring_struct.fw_ring_id;
+	else
 		return bnxt_cp_ring_from_grp(bp, &rxr->rx_ring_struct);
-	}
 }
 
 static u16 bnxt_cp_ring_for_tx(struct bnxt *bp, struct bnxt_tx_ring_info *txr)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
-		struct bnxt_napi *bnapi = txr->bnapi;
-		struct bnxt_cp_ring_info *cpr;
-
-		cpr = bnapi->cp_ring.cp_ring_arr[BNXT_TX_HDL];
-		return cpr->cp_ring_struct.fw_ring_id;
-	} else {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
+		return txr->tx_cpr->cp_ring_struct.fw_ring_id;
+	else
 		return bnxt_cp_ring_from_grp(bp, &txr->tx_ring_struct);
-	}
 }
 
 static int bnxt_alloc_rss_indir_tbl(struct bnxt *bp)
 {
 	int entries;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		entries = BNXT_MAX_RSS_TABLE_ENTRIES_P5;
 	else
 		entries = HW_HASH_INDEX_SIZE;
@@ -5315,7 +5935,7 @@ static u16 bnxt_get_max_rss_ring(struct bnxt *bp)
 
 int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		return DIV_ROUND_UP(rx_rings, BNXT_RSS_TABLE_ENTRIES_P5);
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp))
 		return 2;
@@ -5361,7 +5981,7 @@ static void
 __bnxt_hwrm_vnic_set_rss(struct bnxt *bp, struct hwrm_vnic_rss_cfg_input *req,
 			 struct bnxt_vnic_info *vnic)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		bnxt_fill_hw_rss_tbl_p5(bp, vnic);
 	else
 		bnxt_fill_hw_rss_tbl(bp, vnic);
@@ -5386,7 +6006,7 @@ static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, u16 vnic_id, bool set_rss)
 	struct hwrm_vnic_rss_cfg_input *req;
 	int rc;
 
-	if ((bp->flags & BNXT_FLAG_CHIP_P5) ||
+	if ((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) ||
 	    vnic->fw_rss_cos_lb_ctx[0] == INVALID_HW_RING_ID)
 		return 0;
 
@@ -5551,7 +6171,7 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id)
 	if (rc)
 		return rc;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[0];
 
 		req->default_rx_ring_id =
@@ -5651,7 +6271,7 @@ static int bnxt_hwrm_vnic_alloc(struct bnxt *bp, u16 vnic_id,
 	if (rc)
 		return rc;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		goto vnic_no_ring_grps;
 
 	/* map ring groups to this vnic */
@@ -5686,7 +6306,8 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp)
 	int rc;
 
 	bp->hw_ring_stats_size = sizeof(struct ctx_hw_stats);
-	bp->flags &= ~(BNXT_FLAG_NEW_RSS_CAP | BNXT_FLAG_ROCE_MIRROR_CAP);
+	bp->flags &= ~BNXT_FLAG_ROCE_MIRROR_CAP;
+	bp->rss_cap &= ~BNXT_RSS_CAP_NEW_RSS_CAP;
 	if (bp->hwrm_spec_code < 0x10600)
 		return 0;
 
@@ -5699,9 +6320,9 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp)
 	if (!rc) {
 		u32 flags = le32_to_cpu(resp->flags);
 
-		if (!(bp->flags & BNXT_FLAG_CHIP_P5) &&
+		if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS) &&
 		    (flags & VNIC_QCAPS_RESP_FLAGS_RSS_DFLT_CR_CAP))
-			bp->flags |= BNXT_FLAG_NEW_RSS_CAP;
+			bp->rss_cap |= BNXT_RSS_CAP_NEW_RSS_CAP;
 		if (flags &
 		    VNIC_QCAPS_RESP_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_CAP)
 			bp->flags |= BNXT_FLAG_ROCE_MIRROR_CAP;
@@ -5710,18 +6331,22 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp)
 		 * VLAN_STRIP_CAP properly.
 		 */
 		if ((flags & VNIC_QCAPS_RESP_FLAGS_VLAN_STRIP_CAP) ||
-		    (BNXT_CHIP_P5_THOR(bp) &&
+		    (BNXT_CHIP_P5(bp) &&
 		     !(bp->fw_cap & BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED)))
 			bp->fw_cap |= BNXT_FW_CAP_VLAN_RX_STRIP;
 		if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_HASH_TYPE_DELTA_CAP)
-			bp->fw_cap |= BNXT_FW_CAP_RSS_HASH_TYPE_DELTA;
+			bp->rss_cap |= BNXT_RSS_CAP_RSS_HASH_TYPE_DELTA;
+		if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_PROF_TCAM_MODE_ENABLED)
+			bp->rss_cap |= BNXT_RSS_CAP_RSS_TCAM;
 		bp->max_tpa_v2 = le16_to_cpu(resp->max_aggs_supported);
 		if (bp->max_tpa_v2) {
-			if (BNXT_CHIP_P5_THOR(bp))
+			if (BNXT_CHIP_P5(bp))
 				bp->hw_ring_stats_size = BNXT_RING_STATS_SIZE_P5;
 			else
-				bp->hw_ring_stats_size = BNXT_RING_STATS_SIZE_P5_SR2;
+				bp->hw_ring_stats_size = BNXT_RING_STATS_SIZE_P7;
 		}
+		if (flags & VNIC_QCAPS_RESP_FLAGS_HW_TUNNEL_TPA_CAP)
+			bp->fw_cap |= BNXT_FW_CAP_VNIC_TUNNEL_TPA;
 	}
 	hwrm_req_drop(bp, req);
 	return rc;
@@ -5734,7 +6359,7 @@ static int bnxt_hwrm_ring_grp_alloc(struct bnxt *bp)
 	int rc;
 	u16 i;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		return 0;
 
 	rc = hwrm_req_init(bp, req, HWRM_RING_GRP_ALLOC);
@@ -5767,7 +6392,7 @@ static void bnxt_hwrm_ring_grp_free(struct bnxt *bp)
 	struct hwrm_ring_grp_free_input *req;
 	u16 i;
 
-	if (!bp->grp_info || (bp->flags & BNXT_FLAG_CHIP_P5))
+	if (!bp->grp_info || (bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		return;
 
 	if (hwrm_req_init(bp, req, HWRM_RING_GRP_FREE))
@@ -5827,12 +6452,15 @@ static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 		req->length = cpu_to_le32(bp->tx_ring_mask + 1);
 		req->stat_ctx_id = cpu_to_le32(grp_info->fw_stats_ctx);
 		req->queue_id = cpu_to_le16(ring->queue_id);
+		if (bp->flags & BNXT_FLAG_TX_COAL_CMPL)
+			req->cmpl_coal_cnt =
+				RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_64;
 		break;
 	}
 	case HWRM_RING_ALLOC_RX:
 		req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX;
 		req->length = cpu_to_le32(bp->rx_ring_mask + 1);
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 			u16 flags = 0;
 
 			/* Association of rx ring with stats context */
@@ -5847,7 +6475,7 @@ static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 		}
 		break;
 	case HWRM_RING_ALLOC_AGG:
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 			req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX_AGG;
 			/* Association of agg ring with rx ring */
 			grp_info = &bp->grp_info[ring->grp_idx];
@@ -5865,7 +6493,7 @@ static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 	case HWRM_RING_ALLOC_CMPL:
 		req->ring_type = RING_ALLOC_REQ_RING_TYPE_L2_CMPL;
 		req->length = cpu_to_le32(bp->cp_ring_mask + 1);
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 			/* Association of cp ring with nq */
 			grp_info = &bp->grp_info[map_index];
 			req->nq_ring_id = cpu_to_le16(grp_info->cp_fw_ring_id);
@@ -5933,14 +6561,34 @@ static int bnxt_hwrm_set_async_event_cr(struct bnxt *bp, int idx)
 	}
 }
 
+static void bnxt_set_db_mask(struct bnxt *bp, struct bnxt_db_info *db,
+			     u32 ring_type)
+{
+	switch (ring_type) {
+	case HWRM_RING_ALLOC_TX:
+		db->db_ring_mask = bp->tx_ring_mask;
+		break;
+	case HWRM_RING_ALLOC_RX:
+		db->db_ring_mask = bp->rx_ring_mask;
+		break;
+	case HWRM_RING_ALLOC_AGG:
+		db->db_ring_mask = bp->rx_agg_ring_mask;
+		break;
+	case HWRM_RING_ALLOC_CMPL:
+	case HWRM_RING_ALLOC_NQ:
+		db->db_ring_mask = bp->cp_ring_mask;
+		break;
+	}
+	if (bp->flags & BNXT_FLAG_CHIP_P7) {
+		db->db_epoch_mask = db->db_ring_mask + 1;
+		db->db_epoch_shift = DBR_EPOCH_SFT - ilog2(db->db_epoch_mask);
+	}
+}
+
 static void bnxt_set_db(struct bnxt *bp, struct bnxt_db_info *db, u32 ring_type,
 			u32 map_idx, u32 xid)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
-		if (BNXT_PF(bp))
-			db->doorbell = bp->bar1 + DB_PF_OFFSET_P5;
-		else
-			db->doorbell = bp->bar1 + DB_VF_OFFSET_P5;
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		switch (ring_type) {
 		case HWRM_RING_ALLOC_TX:
 			db->db_key64 = DBR_PATH_L2 | DBR_TYPE_SQ;
@@ -5957,6 +6605,11 @@ static void bnxt_set_db(struct bnxt *bp, struct bnxt_db_info *db, u32 ring_type,
 			break;
 		}
 		db->db_key64 |= (u64)xid << DBR_XID_SFT;
+
+		if (bp->flags & BNXT_FLAG_CHIP_P7)
+			db->db_key64 |= DBR_VALID;
+
+		db->doorbell = bp->bar1 + bp->db_offset;
 	} else {
 		db->doorbell = bp->bar1 + map_idx * 0x80;
 		switch (ring_type) {
@@ -5972,6 +6625,7 @@ static void bnxt_set_db(struct bnxt *bp, struct bnxt_db_info *db, u32 ring_type,
 			break;
 		}
 	}
+	bnxt_set_db_mask(bp, db, ring_type);
 }
 
 static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
@@ -5980,7 +6634,7 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 	int i, rc = 0;
 	u32 type;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		type = HWRM_RING_ALLOC_NQ;
 	else
 		type = HWRM_RING_ALLOC_CMPL;
@@ -6016,15 +6670,13 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 		struct bnxt_ring_struct *ring;
 		u32 map_idx;
 
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+			struct bnxt_cp_ring_info *cpr2 = txr->tx_cpr;
 			struct bnxt_napi *bnapi = txr->bnapi;
-			struct bnxt_cp_ring_info *cpr, *cpr2;
 			u32 type2 = HWRM_RING_ALLOC_CMPL;
 
-			cpr = &bnapi->cp_ring;
-			cpr2 = cpr->cp_ring_arr[BNXT_TX_HDL];
 			ring = &cpr2->cp_ring_struct;
-			ring->handle = BNXT_TX_HDL;
+			ring->handle = BNXT_SET_NQ_HDL(cpr2);
 			map_idx = bnapi->index;
 			rc = hwrm_ring_alloc_send_msg(bp, ring, type2, map_idx);
 			if (rc)
@@ -6056,14 +6708,12 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 		if (!agg_rings)
 			bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod);
 		bp->grp_info[map_idx].rx_fw_ring_id = ring->fw_ring_id;
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
-			struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+			struct bnxt_cp_ring_info *cpr2 = rxr->rx_cpr;
 			u32 type2 = HWRM_RING_ALLOC_CMPL;
-			struct bnxt_cp_ring_info *cpr2;
 
-			cpr2 = cpr->cp_ring_arr[BNXT_RX_HDL];
 			ring = &cpr2->cp_ring_struct;
-			ring->handle = BNXT_RX_HDL;
+			ring->handle = BNXT_SET_NQ_HDL(cpr2);
 			rc = hwrm_ring_alloc_send_msg(bp, ring, type2, map_idx);
 			if (rc)
 				goto err_out;
@@ -6171,7 +6821,7 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 		}
 	}
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		type = RING_FREE_REQ_RING_TYPE_RX_AGG;
 	else
 		type = RING_FREE_REQ_RING_TYPE_RX;
@@ -6198,7 +6848,7 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 	 */
 	bnxt_disable_int_sync(bp);
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		type = RING_FREE_REQ_RING_TYPE_NQ;
 	else
 		type = RING_FREE_REQ_RING_TYPE_L2_CMPL;
@@ -6208,18 +6858,16 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 		struct bnxt_ring_struct *ring;
 		int j;
 
-		for (j = 0; j < 2; j++) {
-			struct bnxt_cp_ring_info *cpr2 = cpr->cp_ring_arr[j];
+		for (j = 0; j < cpr->cp_ring_count && cpr->cp_ring_arr; j++) {
+			struct bnxt_cp_ring_info *cpr2 = &cpr->cp_ring_arr[j];
 
-			if (cpr2) {
-				ring = &cpr2->cp_ring_struct;
-				if (ring->fw_ring_id == INVALID_HW_RING_ID)
-					continue;
-				hwrm_ring_free_send_msg(bp, ring,
-					RING_FREE_REQ_RING_TYPE_L2_CMPL,
-					INVALID_HW_RING_ID);
-				ring->fw_ring_id = INVALID_HW_RING_ID;
-			}
+			ring = &cpr2->cp_ring_struct;
+			if (ring->fw_ring_id == INVALID_HW_RING_ID)
+				continue;
+			hwrm_ring_free_send_msg(bp, ring,
+						RING_FREE_REQ_RING_TYPE_L2_CMPL,
+						INVALID_HW_RING_ID);
+			ring->fw_ring_id = INVALID_HW_RING_ID;
 		}
 		ring = &cpr->cp_ring_struct;
 		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
@@ -6231,6 +6879,8 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 	}
 }
 
+static int __bnxt_trim_rings(struct bnxt *bp, int *rx, int *tx, int max,
+			     bool shared);
 static int bnxt_trim_rings(struct bnxt *bp, int *rx, int *tx, int max,
 			   bool shared);
 
@@ -6267,14 +6917,16 @@ static int bnxt_hwrm_get_rings(struct bnxt *bp)
 		cp = le16_to_cpu(resp->alloc_cmpl_rings);
 		stats = le16_to_cpu(resp->alloc_stat_ctx);
 		hw_resc->resv_irqs = cp;
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 			int rx = hw_resc->resv_rx_rings;
 			int tx = hw_resc->resv_tx_rings;
 
 			if (bp->flags & BNXT_FLAG_AGG_RINGS)
 				rx >>= 1;
 			if (cp < (rx + tx)) {
-				bnxt_trim_rings(bp, &rx, &tx, cp, false);
+				rc = __bnxt_trim_rings(bp, &rx, &tx, cp, false);
+				if (rc)
+					return rc;
 				if (bp->flags & BNXT_FLAG_AGG_RINGS)
 					rx <<= 1;
 				hw_resc->resv_rx_rings = rx;
@@ -6331,7 +6983,7 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 	if (BNXT_NEW_RM(bp)) {
 		enables |= rx_rings ? FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS : 0;
 		enables |= stats ? FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 			enables |= cp_rings ? FUNC_CFG_REQ_ENABLES_NUM_MSIX : 0;
 			enables |= tx_rings + ring_grps ?
 				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
@@ -6347,7 +6999,7 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 		enables |= vnics ? FUNC_CFG_REQ_ENABLES_NUM_VNICS : 0;
 
 		req->num_rx_rings = cpu_to_le16(rx_rings);
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 			req->num_cmpl_rings = cpu_to_le16(tx_rings + ring_grps);
 			req->num_msix = cpu_to_le16(cp_rings);
 			req->num_rsscos_ctxs =
@@ -6356,7 +7008,7 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 			req->num_cmpl_rings = cpu_to_le16(cp_rings);
 			req->num_hw_ring_grps = cpu_to_le16(ring_grps);
 			req->num_rsscos_ctxs = cpu_to_le16(1);
-			if (!(bp->flags & BNXT_FLAG_NEW_RSS_CAP) &&
+			if (!(bp->rss_cap & BNXT_RSS_CAP_NEW_RSS_CAP) &&
 			    bnxt_rfs_supported(bp))
 				req->num_rsscos_ctxs =
 					cpu_to_le16(ring_grps + 1);
@@ -6382,7 +7034,7 @@ __bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 	enables |= rx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_RX_RINGS |
 			      FUNC_VF_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
 	enables |= stats ? FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		enables |= tx_rings + ring_grps ?
 			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 	} else {
@@ -6397,7 +7049,7 @@ __bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 	req->num_l2_ctxs = cpu_to_le16(BNXT_VF_MAX_L2_CTX);
 	req->num_tx_rings = cpu_to_le16(tx_rings);
 	req->num_rx_rings = cpu_to_le16(rx_rings);
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		req->num_cmpl_rings = cpu_to_le16(tx_rings + ring_grps);
 		req->num_rsscos_ctxs = cpu_to_le16(DIV_ROUND_UP(ring_grps, 64));
 	} else {
@@ -6493,7 +7145,7 @@ static int bnxt_cp_rings_in_use(struct bnxt *bp)
 {
 	int cp;
 
-	if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		return bnxt_nq_rings_in_use(bp);
 
 	cp = bp->tx_nr_rings + bp->rx_nr_rings;
@@ -6550,7 +7202,8 @@ static bool bnxt_need_reserve_rings(struct bnxt *bp)
 		bnxt_check_rss_tbl_no_rmgr(bp);
 		return false;
 	}
-	if ((bp->flags & BNXT_FLAG_RFS) && !(bp->flags & BNXT_FLAG_CHIP_P5))
+	if ((bp->flags & BNXT_FLAG_RFS) &&
+	    !(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		vnic = rx + 1;
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		rx <<= 1;
@@ -6558,9 +7211,9 @@ static bool bnxt_need_reserve_rings(struct bnxt *bp)
 	if (hw_resc->resv_rx_rings != rx || hw_resc->resv_cp_rings != cp ||
 	    hw_resc->resv_vnics != vnic || hw_resc->resv_stat_ctxs != stat ||
 	    (hw_resc->resv_hw_ring_grps != grp &&
-	     !(bp->flags & BNXT_FLAG_CHIP_P5)))
+	     !(bp->flags & BNXT_FLAG_CHIP_P5_PLUS)))
 		return true;
-	if ((bp->flags & BNXT_FLAG_CHIP_P5) && BNXT_PF(bp) &&
+	if ((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) && BNXT_PF(bp) &&
 	    hw_resc->resv_irqs != nq)
 		return true;
 	return false;
@@ -6575,13 +7228,15 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 	int grp, rx_rings, rc;
 	int vnic = 1, stat;
 	bool sh = false;
+	int tx_cp;
 
 	if (!bnxt_need_reserve_rings(bp))
 		return 0;
 
 	if (bp->flags & BNXT_FLAG_SHARED_RINGS)
 		sh = true;
-	if ((bp->flags & BNXT_FLAG_RFS) && !(bp->flags & BNXT_FLAG_CHIP_P5))
+	if ((bp->flags & BNXT_FLAG_RFS) &&
+	    !(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		vnic = rx + 1;
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		rx <<= 1;
@@ -6624,7 +7279,8 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 	rc = bnxt_trim_rings(bp, &rx_rings, &tx, cp, sh);
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		rx = rx_rings << 1;
-	cp = sh ? max_t(int, tx, rx_rings) : tx + rx_rings;
+	tx_cp = bnxt_num_tx_to_cp(bp, tx);
+	cp = sh ? max_t(int, tx_cp, rx_rings) : tx_cp + rx_rings;
 	bp->tx_nr_rings = tx;
 
 	/* If we cannot reserve all the RX rings, reset the RSS map only
@@ -6671,7 +7327,7 @@ static int bnxt_hwrm_check_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 		FUNC_VF_CFG_REQ_FLAGS_STAT_CTX_ASSETS_TEST |
 		FUNC_VF_CFG_REQ_FLAGS_VNIC_ASSETS_TEST |
 		FUNC_VF_CFG_REQ_FLAGS_RSSCOS_CTX_ASSETS_TEST;
-	if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		flags |= FUNC_VF_CFG_REQ_FLAGS_RING_GRP_ASSETS_TEST;
 
 	req->flags = cpu_to_le32(flags);
@@ -6693,7 +7349,7 @@ static int bnxt_hwrm_check_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 			 FUNC_CFG_REQ_FLAGS_CMPL_ASSETS_TEST |
 			 FUNC_CFG_REQ_FLAGS_STAT_CTX_ASSETS_TEST |
 			 FUNC_CFG_REQ_FLAGS_VNIC_ASSETS_TEST;
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 			flags |= FUNC_CFG_REQ_FLAGS_RSSCOS_CTX_ASSETS_TEST |
 				 FUNC_CFG_REQ_FLAGS_NQ_ASSETS_TEST;
 		else
@@ -6887,10 +7543,40 @@ int bnxt_hwrm_set_ring_coal(struct bnxt *bp, struct bnxt_napi *bnapi)
 	return hwrm_req_send(bp, req_rx);
 }
 
+static int
+bnxt_hwrm_set_rx_coal(struct bnxt *bp, struct bnxt_napi *bnapi,
+		      struct hwrm_ring_cmpl_ring_cfg_aggint_params_input *req)
+{
+	u16 ring_id = bnxt_cp_ring_for_rx(bp, bnapi->rx_ring);
+
+	req->ring_id = cpu_to_le16(ring_id);
+	return hwrm_req_send(bp, req);
+}
+
+static int
+bnxt_hwrm_set_tx_coal(struct bnxt *bp, struct bnxt_napi *bnapi,
+		      struct hwrm_ring_cmpl_ring_cfg_aggint_params_input *req)
+{
+	struct bnxt_tx_ring_info *txr;
+	int i, rc;
+
+	bnxt_for_each_napi_tx(i, bnapi, txr) {
+		u16 ring_id;
+
+		ring_id = bnxt_cp_ring_for_tx(bp, txr);
+		req->ring_id = cpu_to_le16(ring_id);
+		rc = hwrm_req_send(bp, req);
+		if (rc)
+			return rc;
+		if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
+			return 0;
+	}
+	return 0;
+}
+
 int bnxt_hwrm_set_coal(struct bnxt *bp)
 {
-	struct hwrm_ring_cmpl_ring_cfg_aggint_params_input *req_rx, *req_tx,
-							   *req;
+	struct hwrm_ring_cmpl_ring_cfg_aggint_params_input *req_rx, *req_tx;
 	int i, rc;
 
 	rc = hwrm_req_init(bp, req_rx, HWRM_RING_CMPL_RING_CFG_AGGINT_PARAMS);
@@ -6911,29 +7597,19 @@ int bnxt_hwrm_set_coal(struct bnxt *bp)
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 		struct bnxt_coal *hw_coal;
-		u16 ring_id;
 
-		req = req_rx;
-		if (!bnapi->rx_ring) {
-			ring_id = bnxt_cp_ring_for_tx(bp, bnapi->tx_ring);
-			req = req_tx;
-		} else {
-			ring_id = bnxt_cp_ring_for_rx(bp, bnapi->rx_ring);
-		}
-		req->ring_id = cpu_to_le16(ring_id);
-
-		rc = hwrm_req_send(bp, req);
+		if (!bnapi->rx_ring)
+			rc = bnxt_hwrm_set_tx_coal(bp, bnapi, req_tx);
+		else
+			rc = bnxt_hwrm_set_rx_coal(bp, bnapi, req_rx);
 		if (rc)
 			break;
 
-		if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+		if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 			continue;
 
-		if (bnapi->rx_ring && bnapi->tx_ring) {
-			req = req_tx;
-			ring_id = bnxt_cp_ring_for_tx(bp, bnapi->tx_ring);
-			req->ring_id = cpu_to_le16(ring_id);
-			rc = hwrm_req_send(bp, req);
+		if (bnapi->rx_ring && bnapi->tx_ring[0]) {
+			rc = bnxt_hwrm_set_tx_coal(bp, bnapi, req_tx);
 			if (rc)
 				break;
 		}
@@ -7029,7 +7705,6 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 {
 	struct hwrm_func_qcfg_output *resp;
 	struct hwrm_func_qcfg_input *req;
-	u32 min_db_offset = 0;
 	u16 flags;
 	int rc;
 
@@ -7087,16 +7762,17 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 	if (bp->db_size)
 		goto func_qcfg_exit;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	bp->db_offset = le16_to_cpu(resp->legacy_l2_db_size_kb) * 1024;
+	if (BNXT_CHIP_P5(bp)) {
 		if (BNXT_PF(bp))
-			min_db_offset = DB_PF_OFFSET_P5;
+			bp->db_offset = DB_PF_OFFSET_P5;
 		else
-			min_db_offset = DB_VF_OFFSET_P5;
+			bp->db_offset = DB_VF_OFFSET_P5;
 	}
 	bp->db_size = PAGE_ALIGN(le16_to_cpu(resp->l2_doorbell_bar_size_kb) *
 				 1024);
 	if (!bp->db_size || bp->db_size > pci_resource_len(bp->pdev, 2) ||
-	    bp->db_size <= min_db_offset)
+	    bp->db_size <= bp->db_offset)
 		bp->db_size = pci_resource_len(bp->pdev, 2);
 
 func_qcfg_exit:
@@ -7104,37 +7780,99 @@ func_qcfg_exit:
 	return rc;
 }
 
-static void bnxt_init_ctx_initializer(struct bnxt_ctx_mem_info *ctx,
-			struct hwrm_func_backing_store_qcaps_output *resp)
+static void bnxt_init_ctx_initializer(struct bnxt_ctx_mem_type *ctxm,
+				      u8 init_val, u8 init_offset,
+				      bool init_mask_set)
 {
-	struct bnxt_mem_init *mem_init;
-	u16 init_mask;
-	u8 init_val;
-	u8 *offset;
-	int i;
+	ctxm->init_value = init_val;
+	ctxm->init_offset = BNXT_CTX_INIT_INVALID_OFFSET;
+	if (init_mask_set)
+		ctxm->init_offset = init_offset * 4;
+	else
+		ctxm->init_value = 0;
+}
+
+static int bnxt_alloc_all_ctx_pg_info(struct bnxt *bp, int ctx_max)
+{
+	struct bnxt_ctx_mem_info *ctx = bp->ctx;
+	u16 type;
+
+	for (type = 0; type < ctx_max; type++) {
+		struct bnxt_ctx_mem_type *ctxm = &ctx->ctx_arr[type];
+		int n = 1;
 
-	init_val = resp->ctx_kind_initializer;
-	init_mask = le16_to_cpu(resp->ctx_init_mask);
-	offset = &resp->qp_init_offset;
-	mem_init = &ctx->mem_init[BNXT_CTX_MEM_INIT_QP];
-	for (i = 0; i < BNXT_CTX_MEM_INIT_MAX; i++, mem_init++, offset++) {
-		mem_init->init_val = init_val;
-		mem_init->offset = BNXT_MEM_INVALID_OFFSET;
-		if (!init_mask)
+		if (!ctxm->max_entries)
 			continue;
-		if (i == BNXT_CTX_MEM_INIT_STAT)
-			offset = &resp->stat_init_offset;
-		if (init_mask & (1 << i))
-			mem_init->offset = *offset * 4;
-		else
-			mem_init->init_val = 0;
+
+		if (ctxm->instance_bmap)
+			n = hweight32(ctxm->instance_bmap);
+		ctxm->pg_info = kcalloc(n, sizeof(*ctxm->pg_info), GFP_KERNEL);
+		if (!ctxm->pg_info)
+			return -ENOMEM;
 	}
-	ctx->mem_init[BNXT_CTX_MEM_INIT_QP].size = ctx->qp_entry_size;
-	ctx->mem_init[BNXT_CTX_MEM_INIT_SRQ].size = ctx->srq_entry_size;
-	ctx->mem_init[BNXT_CTX_MEM_INIT_CQ].size = ctx->cq_entry_size;
-	ctx->mem_init[BNXT_CTX_MEM_INIT_VNIC].size = ctx->vnic_entry_size;
-	ctx->mem_init[BNXT_CTX_MEM_INIT_STAT].size = ctx->stat_entry_size;
-	ctx->mem_init[BNXT_CTX_MEM_INIT_MRAV].size = ctx->mrav_entry_size;
+	return 0;
+}
+
+#define BNXT_CTX_INIT_VALID(flags)	\
+	(!!((flags) &			\
+	    FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_ENABLE_CTX_KIND_INIT))
+
+static int bnxt_hwrm_func_backing_store_qcaps_v2(struct bnxt *bp)
+{
+	struct hwrm_func_backing_store_qcaps_v2_output *resp;
+	struct hwrm_func_backing_store_qcaps_v2_input *req;
+	struct bnxt_ctx_mem_info *ctx;
+	u16 type;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_BACKING_STORE_QCAPS_V2);
+	if (rc)
+		return rc;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+	bp->ctx = ctx;
+
+	resp = hwrm_req_hold(bp, req);
+
+	for (type = 0; type < BNXT_CTX_V2_MAX; ) {
+		struct bnxt_ctx_mem_type *ctxm = &ctx->ctx_arr[type];
+		u8 init_val, init_off, i;
+		__le32 *p;
+		u32 flags;
+
+		req->type = cpu_to_le16(type);
+		rc = hwrm_req_send(bp, req);
+		if (rc)
+			goto ctx_done;
+		flags = le32_to_cpu(resp->flags);
+		type = le16_to_cpu(resp->next_valid_type);
+		if (!(flags & FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_TYPE_VALID))
+			continue;
+
+		ctxm->type = le16_to_cpu(resp->type);
+		ctxm->entry_size = le16_to_cpu(resp->entry_size);
+		ctxm->flags = flags;
+		ctxm->instance_bmap = le32_to_cpu(resp->instance_bit_map);
+		ctxm->entry_multiple = resp->entry_multiple;
+		ctxm->max_entries = le32_to_cpu(resp->max_num_entries);
+		ctxm->min_entries = le32_to_cpu(resp->min_num_entries);
+		init_val = resp->ctx_init_value;
+		init_off = resp->ctx_init_offset;
+		bnxt_init_ctx_initializer(ctxm, init_val, init_off,
+					  BNXT_CTX_INIT_VALID(flags));
+		ctxm->split_entry_cnt = min_t(u8, resp->subtype_valid_cnt,
+					      BNXT_MAX_SPLIT_ENTRY);
+		for (i = 0, p = &resp->split_entry_0; i < ctxm->split_entry_cnt;
+		     i++, p++)
+			ctxm->split[i] = le32_to_cpu(*p);
+	}
+	rc = bnxt_alloc_all_ctx_pg_info(bp, BNXT_CTX_V2_MAX);
+
+ctx_done:
+	hwrm_req_drop(bp, req);
+	return rc;
 }
 
 static int bnxt_hwrm_func_backing_store_qcaps(struct bnxt *bp)
@@ -7146,6 +7884,9 @@ static int bnxt_hwrm_func_backing_store_qcaps(struct bnxt *bp)
 	if (bp->hwrm_spec_code < 0x10902 || BNXT_VF(bp) || bp->ctx)
 		return 0;
 
+	if (bp->fw_cap & BNXT_FW_CAP_BACKING_STORE_V2)
+		return bnxt_hwrm_func_backing_store_qcaps_v2(bp);
+
 	rc = hwrm_req_init(bp, req, HWRM_FUNC_BACKING_STORE_QCAPS);
 	if (rc)
 		return rc;
@@ -7153,48 +7894,84 @@ static int bnxt_hwrm_func_backing_store_qcaps(struct bnxt *bp)
 	resp = hwrm_req_hold(bp, req);
 	rc = hwrm_req_send_silent(bp, req);
 	if (!rc) {
-		struct bnxt_ctx_pg_info *ctx_pg;
+		struct bnxt_ctx_mem_type *ctxm;
 		struct bnxt_ctx_mem_info *ctx;
-		int i, tqm_rings;
+		u8 init_val, init_idx = 0;
+		u16 init_mask;
 
-		ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+		ctx = bp->ctx;
 		if (!ctx) {
-			rc = -ENOMEM;
-			goto ctx_err;
-		}
-		ctx->qp_max_entries = le32_to_cpu(resp->qp_max_entries);
-		ctx->qp_min_qp1_entries = le16_to_cpu(resp->qp_min_qp1_entries);
-		ctx->qp_max_l2_entries = le16_to_cpu(resp->qp_max_l2_entries);
-		ctx->qp_entry_size = le16_to_cpu(resp->qp_entry_size);
-		ctx->srq_max_l2_entries = le16_to_cpu(resp->srq_max_l2_entries);
-		ctx->srq_max_entries = le32_to_cpu(resp->srq_max_entries);
-		ctx->srq_entry_size = le16_to_cpu(resp->srq_entry_size);
-		ctx->cq_max_l2_entries = le16_to_cpu(resp->cq_max_l2_entries);
-		ctx->cq_max_entries = le32_to_cpu(resp->cq_max_entries);
-		ctx->cq_entry_size = le16_to_cpu(resp->cq_entry_size);
-		ctx->vnic_max_vnic_entries =
-			le16_to_cpu(resp->vnic_max_vnic_entries);
-		ctx->vnic_max_ring_table_entries =
+			ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+			if (!ctx) {
+				rc = -ENOMEM;
+				goto ctx_err;
+			}
+			bp->ctx = ctx;
+		}
+		init_val = resp->ctx_kind_initializer;
+		init_mask = le16_to_cpu(resp->ctx_init_mask);
+
+		ctxm = &ctx->ctx_arr[BNXT_CTX_QP];
+		ctxm->max_entries = le32_to_cpu(resp->qp_max_entries);
+		ctxm->qp_qp1_entries = le16_to_cpu(resp->qp_min_qp1_entries);
+		ctxm->qp_l2_entries = le16_to_cpu(resp->qp_max_l2_entries);
+		ctxm->qp_fast_qpmd_entries = le16_to_cpu(resp->fast_qpmd_qp_num_entries);
+		ctxm->entry_size = le16_to_cpu(resp->qp_entry_size);
+		bnxt_init_ctx_initializer(ctxm, init_val, resp->qp_init_offset,
+					  (init_mask & (1 << init_idx++)) != 0);
+
+		ctxm = &ctx->ctx_arr[BNXT_CTX_SRQ];
+		ctxm->srq_l2_entries = le16_to_cpu(resp->srq_max_l2_entries);
+		ctxm->max_entries = le32_to_cpu(resp->srq_max_entries);
+		ctxm->entry_size = le16_to_cpu(resp->srq_entry_size);
+		bnxt_init_ctx_initializer(ctxm, init_val, resp->srq_init_offset,
+					  (init_mask & (1 << init_idx++)) != 0);
+
+		ctxm = &ctx->ctx_arr[BNXT_CTX_CQ];
+		ctxm->cq_l2_entries = le16_to_cpu(resp->cq_max_l2_entries);
+		ctxm->max_entries = le32_to_cpu(resp->cq_max_entries);
+		ctxm->entry_size = le16_to_cpu(resp->cq_entry_size);
+		bnxt_init_ctx_initializer(ctxm, init_val, resp->cq_init_offset,
+					  (init_mask & (1 << init_idx++)) != 0);
+
+		ctxm = &ctx->ctx_arr[BNXT_CTX_VNIC];
+		ctxm->vnic_entries = le16_to_cpu(resp->vnic_max_vnic_entries);
+		ctxm->max_entries = ctxm->vnic_entries +
 			le16_to_cpu(resp->vnic_max_ring_table_entries);
-		ctx->vnic_entry_size = le16_to_cpu(resp->vnic_entry_size);
-		ctx->stat_max_entries = le32_to_cpu(resp->stat_max_entries);
-		ctx->stat_entry_size = le16_to_cpu(resp->stat_entry_size);
-		ctx->tqm_entry_size = le16_to_cpu(resp->tqm_entry_size);
-		ctx->tqm_min_entries_per_ring =
-			le32_to_cpu(resp->tqm_min_entries_per_ring);
-		ctx->tqm_max_entries_per_ring =
-			le32_to_cpu(resp->tqm_max_entries_per_ring);
-		ctx->tqm_entries_multiple = resp->tqm_entries_multiple;
-		if (!ctx->tqm_entries_multiple)
-			ctx->tqm_entries_multiple = 1;
-		ctx->mrav_max_entries = le32_to_cpu(resp->mrav_max_entries);
-		ctx->mrav_entry_size = le16_to_cpu(resp->mrav_entry_size);
-		ctx->mrav_num_entries_units =
+		ctxm->entry_size = le16_to_cpu(resp->vnic_entry_size);
+		bnxt_init_ctx_initializer(ctxm, init_val,
+					  resp->vnic_init_offset,
+					  (init_mask & (1 << init_idx++)) != 0);
+
+		ctxm = &ctx->ctx_arr[BNXT_CTX_STAT];
+		ctxm->max_entries = le32_to_cpu(resp->stat_max_entries);
+		ctxm->entry_size = le16_to_cpu(resp->stat_entry_size);
+		bnxt_init_ctx_initializer(ctxm, init_val,
+					  resp->stat_init_offset,
+					  (init_mask & (1 << init_idx++)) != 0);
+
+		ctxm = &ctx->ctx_arr[BNXT_CTX_STQM];
+		ctxm->entry_size = le16_to_cpu(resp->tqm_entry_size);
+		ctxm->min_entries = le32_to_cpu(resp->tqm_min_entries_per_ring);
+		ctxm->max_entries = le32_to_cpu(resp->tqm_max_entries_per_ring);
+		ctxm->entry_multiple = resp->tqm_entries_multiple;
+		if (!ctxm->entry_multiple)
+			ctxm->entry_multiple = 1;
+
+		memcpy(&ctx->ctx_arr[BNXT_CTX_FTQM], ctxm, sizeof(*ctxm));
+
+		ctxm = &ctx->ctx_arr[BNXT_CTX_MRAV];
+		ctxm->max_entries = le32_to_cpu(resp->mrav_max_entries);
+		ctxm->entry_size = le16_to_cpu(resp->mrav_entry_size);
+		ctxm->mrav_num_entries_units =
 			le16_to_cpu(resp->mrav_num_entries_units);
-		ctx->tim_entry_size = le16_to_cpu(resp->tim_entry_size);
-		ctx->tim_max_entries = le32_to_cpu(resp->tim_max_entries);
+		bnxt_init_ctx_initializer(ctxm, init_val,
+					  resp->mrav_init_offset,
+					  (init_mask & (1 << init_idx++)) != 0);
 
-		bnxt_init_ctx_initializer(ctx, resp);
+		ctxm = &ctx->ctx_arr[BNXT_CTX_TIM];
+		ctxm->entry_size = le16_to_cpu(resp->tim_entry_size);
+		ctxm->max_entries = le32_to_cpu(resp->tim_max_entries);
 
 		ctx->tqm_fp_rings_count = resp->tqm_fp_rings_count;
 		if (!ctx->tqm_fp_rings_count)
@@ -7202,16 +7979,11 @@ static int bnxt_hwrm_func_backing_store_qcaps(struct bnxt *bp)
 		else if (ctx->tqm_fp_rings_count > BNXT_MAX_TQM_FP_RINGS)
 			ctx->tqm_fp_rings_count = BNXT_MAX_TQM_FP_RINGS;
 
-		tqm_rings = ctx->tqm_fp_rings_count + BNXT_MAX_TQM_SP_RINGS;
-		ctx_pg = kcalloc(tqm_rings, sizeof(*ctx_pg), GFP_KERNEL);
-		if (!ctx_pg) {
-			kfree(ctx);
-			rc = -ENOMEM;
-			goto ctx_err;
-		}
-		for (i = 0; i < tqm_rings; i++, ctx_pg++)
-			ctx->tqm_mem[i] = ctx_pg;
-		bp->ctx = ctx;
+		ctxm = &ctx->ctx_arr[BNXT_CTX_FTQM];
+		memcpy(ctxm, &ctx->ctx_arr[BNXT_CTX_STQM], sizeof(*ctxm));
+		ctxm->instance_bmap = (1 << ctx->tqm_fp_rings_count) - 1;
+
+		rc = bnxt_alloc_all_ctx_pg_info(bp, BNXT_CTX_MAX);
 	} else {
 		rc = 0;
 	}
@@ -7250,6 +8022,7 @@ static int bnxt_hwrm_func_backing_store_cfg(struct bnxt *bp, u32 enables)
 	struct hwrm_func_backing_store_cfg_input *req;
 	struct bnxt_ctx_mem_info *ctx = bp->ctx;
 	struct bnxt_ctx_pg_info *ctx_pg;
+	struct bnxt_ctx_mem_type *ctxm;
 	void **__req = (void **)&req;
 	u32 req_len = sizeof(*req);
 	__le32 *num_entries;
@@ -7271,82 +8044,102 @@ static int bnxt_hwrm_func_backing_store_cfg(struct bnxt *bp, u32 enables)
 
 	req->enables = cpu_to_le32(enables);
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP) {
-		ctx_pg = &ctx->qp_mem;
+		ctxm = &ctx->ctx_arr[BNXT_CTX_QP];
+		ctx_pg = ctxm->pg_info;
 		req->qp_num_entries = cpu_to_le32(ctx_pg->entries);
-		req->qp_num_qp1_entries = cpu_to_le16(ctx->qp_min_qp1_entries);
-		req->qp_num_l2_entries = cpu_to_le16(ctx->qp_max_l2_entries);
-		req->qp_entry_size = cpu_to_le16(ctx->qp_entry_size);
+		req->qp_num_qp1_entries = cpu_to_le16(ctxm->qp_qp1_entries);
+		req->qp_num_l2_entries = cpu_to_le16(ctxm->qp_l2_entries);
+		req->qp_entry_size = cpu_to_le16(ctxm->entry_size);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
 				      &req->qpc_pg_size_qpc_lvl,
 				      &req->qpc_page_dir);
+
+		if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP_FAST_QPMD)
+			req->qp_num_fast_qpmd_entries = cpu_to_le16(ctxm->qp_fast_qpmd_entries);
 	}
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_SRQ) {
-		ctx_pg = &ctx->srq_mem;
+		ctxm = &ctx->ctx_arr[BNXT_CTX_SRQ];
+		ctx_pg = ctxm->pg_info;
 		req->srq_num_entries = cpu_to_le32(ctx_pg->entries);
-		req->srq_num_l2_entries = cpu_to_le16(ctx->srq_max_l2_entries);
-		req->srq_entry_size = cpu_to_le16(ctx->srq_entry_size);
+		req->srq_num_l2_entries = cpu_to_le16(ctxm->srq_l2_entries);
+		req->srq_entry_size = cpu_to_le16(ctxm->entry_size);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
 				      &req->srq_pg_size_srq_lvl,
 				      &req->srq_page_dir);
 	}
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_CQ) {
-		ctx_pg = &ctx->cq_mem;
+		ctxm = &ctx->ctx_arr[BNXT_CTX_CQ];
+		ctx_pg = ctxm->pg_info;
 		req->cq_num_entries = cpu_to_le32(ctx_pg->entries);
-		req->cq_num_l2_entries = cpu_to_le16(ctx->cq_max_l2_entries);
-		req->cq_entry_size = cpu_to_le16(ctx->cq_entry_size);
+		req->cq_num_l2_entries = cpu_to_le16(ctxm->cq_l2_entries);
+		req->cq_entry_size = cpu_to_le16(ctxm->entry_size);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
 				      &req->cq_pg_size_cq_lvl,
 				      &req->cq_page_dir);
 	}
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_VNIC) {
-		ctx_pg = &ctx->vnic_mem;
-		req->vnic_num_vnic_entries =
-			cpu_to_le16(ctx->vnic_max_vnic_entries);
+		ctxm = &ctx->ctx_arr[BNXT_CTX_VNIC];
+		ctx_pg = ctxm->pg_info;
+		req->vnic_num_vnic_entries = cpu_to_le16(ctxm->vnic_entries);
 		req->vnic_num_ring_table_entries =
-			cpu_to_le16(ctx->vnic_max_ring_table_entries);
-		req->vnic_entry_size = cpu_to_le16(ctx->vnic_entry_size);
+			cpu_to_le16(ctxm->max_entries - ctxm->vnic_entries);
+		req->vnic_entry_size = cpu_to_le16(ctxm->entry_size);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
 				      &req->vnic_pg_size_vnic_lvl,
 				      &req->vnic_page_dir);
 	}
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_STAT) {
-		ctx_pg = &ctx->stat_mem;
-		req->stat_num_entries = cpu_to_le32(ctx->stat_max_entries);
-		req->stat_entry_size = cpu_to_le16(ctx->stat_entry_size);
+		ctxm = &ctx->ctx_arr[BNXT_CTX_STAT];
+		ctx_pg = ctxm->pg_info;
+		req->stat_num_entries = cpu_to_le32(ctxm->max_entries);
+		req->stat_entry_size = cpu_to_le16(ctxm->entry_size);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
 				      &req->stat_pg_size_stat_lvl,
 				      &req->stat_page_dir);
 	}
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV) {
-		ctx_pg = &ctx->mrav_mem;
+		u32 units;
+
+		ctxm = &ctx->ctx_arr[BNXT_CTX_MRAV];
+		ctx_pg = ctxm->pg_info;
 		req->mrav_num_entries = cpu_to_le32(ctx_pg->entries);
-		if (ctx->mrav_num_entries_units)
-			flags |=
-			FUNC_BACKING_STORE_CFG_REQ_FLAGS_MRAV_RESERVATION_SPLIT;
-		req->mrav_entry_size = cpu_to_le16(ctx->mrav_entry_size);
+		units = ctxm->mrav_num_entries_units;
+		if (units) {
+			u32 num_mr, num_ah = ctxm->mrav_av_entries;
+			u32 entries;
+
+			num_mr = ctx_pg->entries - num_ah;
+			entries = ((num_mr / units) << 16) | (num_ah / units);
+			req->mrav_num_entries = cpu_to_le32(entries);
+			flags |= FUNC_BACKING_STORE_CFG_REQ_FLAGS_MRAV_RESERVATION_SPLIT;
+		}
+		req->mrav_entry_size = cpu_to_le16(ctxm->entry_size);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
 				      &req->mrav_pg_size_mrav_lvl,
 				      &req->mrav_page_dir);
 	}
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM) {
-		ctx_pg = &ctx->tim_mem;
+		ctxm = &ctx->ctx_arr[BNXT_CTX_TIM];
+		ctx_pg = ctxm->pg_info;
 		req->tim_num_entries = cpu_to_le32(ctx_pg->entries);
-		req->tim_entry_size = cpu_to_le16(ctx->tim_entry_size);
+		req->tim_entry_size = cpu_to_le16(ctxm->entry_size);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
 				      &req->tim_pg_size_tim_lvl,
 				      &req->tim_page_dir);
 	}
+	ctxm = &ctx->ctx_arr[BNXT_CTX_STQM];
 	for (i = 0, num_entries = &req->tqm_sp_num_entries,
 	     pg_attr = &req->tqm_sp_pg_size_tqm_sp_lvl,
 	     pg_dir = &req->tqm_sp_page_dir,
-	     ena = FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_SP;
+	     ena = FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_SP,
+	     ctx_pg = ctxm->pg_info;
 	     i < BNXT_MAX_TQM_RINGS;
+	     ctx_pg = &ctx->ctx_arr[BNXT_CTX_FTQM].pg_info[i],
 	     i++, num_entries++, pg_attr++, pg_dir++, ena <<= 1) {
 		if (!(enables & ena))
 			continue;
 
-		req->tqm_entry_size = cpu_to_le16(ctx->tqm_entry_size);
-		ctx_pg = ctx->tqm_mem[i];
+		req->tqm_entry_size = cpu_to_le16(ctxm->entry_size);
 		*num_entries = cpu_to_le32(ctx_pg->entries);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem, pg_attr, pg_dir);
 	}
@@ -7370,7 +8163,7 @@ static int bnxt_alloc_ctx_mem_blk(struct bnxt *bp,
 
 static int bnxt_alloc_ctx_pg_tbls(struct bnxt *bp,
 				  struct bnxt_ctx_pg_info *ctx_pg, u32 mem_size,
-				  u8 depth, struct bnxt_mem_init *mem_init)
+				  u8 depth, struct bnxt_ctx_mem_type *ctxm)
 {
 	struct bnxt_ring_mem_info *rmem = &ctx_pg->ring_mem;
 	int rc;
@@ -7408,7 +8201,7 @@ static int bnxt_alloc_ctx_pg_tbls(struct bnxt *bp,
 			rmem->pg_tbl_map = ctx_pg->ctx_dma_arr[i];
 			rmem->depth = 1;
 			rmem->nr_pages = MAX_CTX_PAGES;
-			rmem->mem_init = mem_init;
+			rmem->ctx_mem = ctxm;
 			if (i == (nr_tbls - 1)) {
 				int rem = ctx_pg->nr_pages % MAX_CTX_PAGES;
 
@@ -7423,7 +8216,7 @@ static int bnxt_alloc_ctx_pg_tbls(struct bnxt *bp,
 		rmem->nr_pages = DIV_ROUND_UP(mem_size, BNXT_PAGE_SIZE);
 		if (rmem->nr_pages > 1 || depth)
 			rmem->depth = 1;
-		rmem->mem_init = mem_init;
+		rmem->ctx_mem = ctxm;
 		rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg);
 	}
 	return rc;
@@ -7458,41 +8251,144 @@ static void bnxt_free_ctx_pg_tbls(struct bnxt *bp,
 	ctx_pg->nr_pages = 0;
 }
 
+static int bnxt_setup_ctxm_pg_tbls(struct bnxt *bp,
+				   struct bnxt_ctx_mem_type *ctxm, u32 entries,
+				   u8 pg_lvl)
+{
+	struct bnxt_ctx_pg_info *ctx_pg = ctxm->pg_info;
+	int i, rc = 0, n = 1;
+	u32 mem_size;
+
+	if (!ctxm->entry_size || !ctx_pg)
+		return -EINVAL;
+	if (ctxm->instance_bmap)
+		n = hweight32(ctxm->instance_bmap);
+	if (ctxm->entry_multiple)
+		entries = roundup(entries, ctxm->entry_multiple);
+	entries = clamp_t(u32, entries, ctxm->min_entries, ctxm->max_entries);
+	mem_size = entries * ctxm->entry_size;
+	for (i = 0; i < n && !rc; i++) {
+		ctx_pg[i].entries = entries;
+		rc = bnxt_alloc_ctx_pg_tbls(bp, &ctx_pg[i], mem_size, pg_lvl,
+					    ctxm->init_value ? ctxm : NULL);
+	}
+	return rc;
+}
+
+static int bnxt_hwrm_func_backing_store_cfg_v2(struct bnxt *bp,
+					       struct bnxt_ctx_mem_type *ctxm,
+					       bool last)
+{
+	struct hwrm_func_backing_store_cfg_v2_input *req;
+	u32 instance_bmap = ctxm->instance_bmap;
+	int i, j, rc = 0, n = 1;
+	__le32 *p;
+
+	if (!(ctxm->flags & BNXT_CTX_MEM_TYPE_VALID) || !ctxm->pg_info)
+		return 0;
+
+	if (instance_bmap)
+		n = hweight32(ctxm->instance_bmap);
+	else
+		instance_bmap = 1;
+
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_BACKING_STORE_CFG_V2);
+	if (rc)
+		return rc;
+	hwrm_req_hold(bp, req);
+	req->type = cpu_to_le16(ctxm->type);
+	req->entry_size = cpu_to_le16(ctxm->entry_size);
+	req->subtype_valid_cnt = ctxm->split_entry_cnt;
+	for (i = 0, p = &req->split_entry_0; i < ctxm->split_entry_cnt; i++)
+		p[i] = cpu_to_le32(ctxm->split[i]);
+	for (i = 0, j = 0; j < n && !rc; i++) {
+		struct bnxt_ctx_pg_info *ctx_pg;
+
+		if (!(instance_bmap & (1 << i)))
+			continue;
+		req->instance = cpu_to_le16(i);
+		ctx_pg = &ctxm->pg_info[j++];
+		if (!ctx_pg->entries)
+			continue;
+		req->num_entries = cpu_to_le32(ctx_pg->entries);
+		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
+				      &req->page_size_pbl_level,
+				      &req->page_dir);
+		if (last && j == n)
+			req->flags =
+				cpu_to_le32(FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_BS_CFG_ALL_DONE);
+		rc = hwrm_req_send(bp, req);
+	}
+	hwrm_req_drop(bp, req);
+	return rc;
+}
+
+static int bnxt_backing_store_cfg_v2(struct bnxt *bp, u32 ena)
+{
+	struct bnxt_ctx_mem_info *ctx = bp->ctx;
+	struct bnxt_ctx_mem_type *ctxm;
+	u16 last_type;
+	int rc = 0;
+	u16 type;
+
+	if (!ena)
+		return 0;
+	else if (ena & FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM)
+		last_type = BNXT_CTX_MAX - 1;
+	else
+		last_type = BNXT_CTX_L2_MAX - 1;
+	ctx->ctx_arr[last_type].last = 1;
+
+	for (type = 0 ; type < BNXT_CTX_V2_MAX; type++) {
+		ctxm = &ctx->ctx_arr[type];
+
+		rc = bnxt_hwrm_func_backing_store_cfg_v2(bp, ctxm, ctxm->last);
+		if (rc)
+			return rc;
+	}
+	return 0;
+}
+
 void bnxt_free_ctx_mem(struct bnxt *bp)
 {
 	struct bnxt_ctx_mem_info *ctx = bp->ctx;
-	int i;
+	u16 type;
 
 	if (!ctx)
 		return;
 
-	if (ctx->tqm_mem[0]) {
-		for (i = 0; i < ctx->tqm_fp_rings_count + 1; i++)
-			bnxt_free_ctx_pg_tbls(bp, ctx->tqm_mem[i]);
-		kfree(ctx->tqm_mem[0]);
-		ctx->tqm_mem[0] = NULL;
+	for (type = 0; type < BNXT_CTX_V2_MAX; type++) {
+		struct bnxt_ctx_mem_type *ctxm = &ctx->ctx_arr[type];
+		struct bnxt_ctx_pg_info *ctx_pg = ctxm->pg_info;
+		int i, n = 1;
+
+		if (!ctx_pg)
+			continue;
+		if (ctxm->instance_bmap)
+			n = hweight32(ctxm->instance_bmap);
+		for (i = 0; i < n; i++)
+			bnxt_free_ctx_pg_tbls(bp, &ctx_pg[i]);
+
+		kfree(ctx_pg);
+		ctxm->pg_info = NULL;
 	}
 
-	bnxt_free_ctx_pg_tbls(bp, &ctx->tim_mem);
-	bnxt_free_ctx_pg_tbls(bp, &ctx->mrav_mem);
-	bnxt_free_ctx_pg_tbls(bp, &ctx->stat_mem);
-	bnxt_free_ctx_pg_tbls(bp, &ctx->vnic_mem);
-	bnxt_free_ctx_pg_tbls(bp, &ctx->cq_mem);
-	bnxt_free_ctx_pg_tbls(bp, &ctx->srq_mem);
-	bnxt_free_ctx_pg_tbls(bp, &ctx->qp_mem);
 	ctx->flags &= ~BNXT_CTX_FLAG_INITED;
+	kfree(ctx);
+	bp->ctx = NULL;
 }
 
 static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 {
-	struct bnxt_ctx_pg_info *ctx_pg;
+	struct bnxt_ctx_mem_type *ctxm;
 	struct bnxt_ctx_mem_info *ctx;
-	struct bnxt_mem_init *init;
-	u32 mem_size, ena, entries;
-	u32 entries_sp, min;
+	u32 l2_qps, qp1_qps, max_qps;
+	u32 ena, entries_sp, entries;
+	u32 srqs, max_srqs, min;
 	u32 num_mr, num_ah;
 	u32 extra_srqs = 0;
 	u32 extra_qps = 0;
+	u32 fast_qpmd_qps;
 	u8 pg_lvl = 1;
 	int i, rc;
 
@@ -7506,120 +8402,98 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 	if (!ctx || (ctx->flags & BNXT_CTX_FLAG_INITED))
 		return 0;
 
+	ctxm = &ctx->ctx_arr[BNXT_CTX_QP];
+	l2_qps = ctxm->qp_l2_entries;
+	qp1_qps = ctxm->qp_qp1_entries;
+	fast_qpmd_qps = ctxm->qp_fast_qpmd_entries;
+	max_qps = ctxm->max_entries;
+	ctxm = &ctx->ctx_arr[BNXT_CTX_SRQ];
+	srqs = ctxm->srq_l2_entries;
+	max_srqs = ctxm->max_entries;
+	ena = 0;
 	if ((bp->flags & BNXT_FLAG_ROCE_CAP) && !is_kdump_kernel()) {
 		pg_lvl = 2;
-		extra_qps = 65536;
-		extra_srqs = 8192;
+		extra_qps = min_t(u32, 65536, max_qps - l2_qps - qp1_qps);
+		/* allocate extra qps if fw supports RoCE fast qp destroy feature */
+		extra_qps += fast_qpmd_qps;
+		extra_srqs = min_t(u32, 8192, max_srqs - srqs);
+		if (fast_qpmd_qps)
+			ena |= FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP_FAST_QPMD;
 	}
 
-	ctx_pg = &ctx->qp_mem;
-	ctx_pg->entries = ctx->qp_min_qp1_entries + ctx->qp_max_l2_entries +
-			  extra_qps;
-	if (ctx->qp_entry_size) {
-		mem_size = ctx->qp_entry_size * ctx_pg->entries;
-		init = &ctx->mem_init[BNXT_CTX_MEM_INIT_QP];
-		rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, pg_lvl, init);
-		if (rc)
-			return rc;
-	}
+	ctxm = &ctx->ctx_arr[BNXT_CTX_QP];
+	rc = bnxt_setup_ctxm_pg_tbls(bp, ctxm, l2_qps + qp1_qps + extra_qps,
+				     pg_lvl);
+	if (rc)
+		return rc;
 
-	ctx_pg = &ctx->srq_mem;
-	ctx_pg->entries = ctx->srq_max_l2_entries + extra_srqs;
-	if (ctx->srq_entry_size) {
-		mem_size = ctx->srq_entry_size * ctx_pg->entries;
-		init = &ctx->mem_init[BNXT_CTX_MEM_INIT_SRQ];
-		rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, pg_lvl, init);
-		if (rc)
-			return rc;
-	}
+	ctxm = &ctx->ctx_arr[BNXT_CTX_SRQ];
+	rc = bnxt_setup_ctxm_pg_tbls(bp, ctxm, srqs + extra_srqs, pg_lvl);
+	if (rc)
+		return rc;
 
-	ctx_pg = &ctx->cq_mem;
-	ctx_pg->entries = ctx->cq_max_l2_entries + extra_qps * 2;
-	if (ctx->cq_entry_size) {
-		mem_size = ctx->cq_entry_size * ctx_pg->entries;
-		init = &ctx->mem_init[BNXT_CTX_MEM_INIT_CQ];
-		rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, pg_lvl, init);
-		if (rc)
-			return rc;
-	}
+	ctxm = &ctx->ctx_arr[BNXT_CTX_CQ];
+	rc = bnxt_setup_ctxm_pg_tbls(bp, ctxm, ctxm->cq_l2_entries +
+				     extra_qps * 2, pg_lvl);
+	if (rc)
+		return rc;
 
-	ctx_pg = &ctx->vnic_mem;
-	ctx_pg->entries = ctx->vnic_max_vnic_entries +
-			  ctx->vnic_max_ring_table_entries;
-	if (ctx->vnic_entry_size) {
-		mem_size = ctx->vnic_entry_size * ctx_pg->entries;
-		init = &ctx->mem_init[BNXT_CTX_MEM_INIT_VNIC];
-		rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1, init);
-		if (rc)
-			return rc;
-	}
+	ctxm = &ctx->ctx_arr[BNXT_CTX_VNIC];
+	rc = bnxt_setup_ctxm_pg_tbls(bp, ctxm, ctxm->max_entries, 1);
+	if (rc)
+		return rc;
 
-	ctx_pg = &ctx->stat_mem;
-	ctx_pg->entries = ctx->stat_max_entries;
-	if (ctx->stat_entry_size) {
-		mem_size = ctx->stat_entry_size * ctx_pg->entries;
-		init = &ctx->mem_init[BNXT_CTX_MEM_INIT_STAT];
-		rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1, init);
-		if (rc)
-			return rc;
-	}
+	ctxm = &ctx->ctx_arr[BNXT_CTX_STAT];
+	rc = bnxt_setup_ctxm_pg_tbls(bp, ctxm, ctxm->max_entries, 1);
+	if (rc)
+		return rc;
 
-	ena = 0;
 	if (!(bp->flags & BNXT_FLAG_ROCE_CAP))
 		goto skip_rdma;
 
-	ctx_pg = &ctx->mrav_mem;
+	ctxm = &ctx->ctx_arr[BNXT_CTX_MRAV];
 	/* 128K extra is needed to accommodate static AH context
 	 * allocation by f/w.
 	 */
-	num_mr = 1024 * 256;
-	num_ah = 1024 * 128;
-	ctx_pg->entries = num_mr + num_ah;
-	if (ctx->mrav_entry_size) {
-		mem_size = ctx->mrav_entry_size * ctx_pg->entries;
-		init = &ctx->mem_init[BNXT_CTX_MEM_INIT_MRAV];
-		rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 2, init);
-		if (rc)
-			return rc;
-	}
-	ena = FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV;
-	if (ctx->mrav_num_entries_units)
-		ctx_pg->entries =
-			((num_mr / ctx->mrav_num_entries_units) << 16) |
-			 (num_ah / ctx->mrav_num_entries_units);
-
-	ctx_pg = &ctx->tim_mem;
-	ctx_pg->entries = ctx->qp_mem.entries;
-	if (ctx->tim_entry_size) {
-		mem_size = ctx->tim_entry_size * ctx_pg->entries;
-		rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1, NULL);
-		if (rc)
-			return rc;
-	}
+	num_mr = min_t(u32, ctxm->max_entries / 2, 1024 * 256);
+	num_ah = min_t(u32, num_mr, 1024 * 128);
+	ctxm->split_entry_cnt = BNXT_CTX_MRAV_AV_SPLIT_ENTRY + 1;
+	if (!ctxm->mrav_av_entries || ctxm->mrav_av_entries > num_ah)
+		ctxm->mrav_av_entries = num_ah;
+
+	rc = bnxt_setup_ctxm_pg_tbls(bp, ctxm, num_mr + num_ah, 2);
+	if (rc)
+		return rc;
+	ena |= FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV;
+
+	ctxm = &ctx->ctx_arr[BNXT_CTX_TIM];
+	rc = bnxt_setup_ctxm_pg_tbls(bp, ctxm, l2_qps + qp1_qps + extra_qps, 1);
+	if (rc)
+		return rc;
 	ena |= FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM;
 
 skip_rdma:
-	min = ctx->tqm_min_entries_per_ring;
-	entries_sp = ctx->vnic_max_vnic_entries + ctx->qp_max_l2_entries +
-		     2 * (extra_qps + ctx->qp_min_qp1_entries) + min;
-	entries_sp = roundup(entries_sp, ctx->tqm_entries_multiple);
-	entries = ctx->qp_max_l2_entries + 2 * (extra_qps + ctx->qp_min_qp1_entries);
-	entries = roundup(entries, ctx->tqm_entries_multiple);
-	entries = clamp_t(u32, entries, min, ctx->tqm_max_entries_per_ring);
-	for (i = 0; i < ctx->tqm_fp_rings_count + 1; i++) {
-		ctx_pg = ctx->tqm_mem[i];
-		ctx_pg->entries = i ? entries : entries_sp;
-		if (ctx->tqm_entry_size) {
-			mem_size = ctx->tqm_entry_size * ctx_pg->entries;
-			rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1,
-						    NULL);
-			if (rc)
-				return rc;
-		}
+	ctxm = &ctx->ctx_arr[BNXT_CTX_STQM];
+	min = ctxm->min_entries;
+	entries_sp = ctx->ctx_arr[BNXT_CTX_VNIC].vnic_entries + l2_qps +
+		     2 * (extra_qps + qp1_qps) + min;
+	rc = bnxt_setup_ctxm_pg_tbls(bp, ctxm, entries_sp, 2);
+	if (rc)
+		return rc;
+
+	ctxm = &ctx->ctx_arr[BNXT_CTX_FTQM];
+	entries = l2_qps + 2 * (extra_qps + qp1_qps);
+	rc = bnxt_setup_ctxm_pg_tbls(bp, ctxm, entries, 2);
+	if (rc)
+		return rc;
+	for (i = 0; i < ctx->tqm_fp_rings_count + 1; i++)
 		ena |= FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_SP << i;
-	}
 	ena |= FUNC_BACKING_STORE_CFG_REQ_DFLT_ENABLES;
-	rc = bnxt_hwrm_func_backing_store_cfg(bp, ena);
+
+	if (bp->fw_cap & BNXT_FW_CAP_BACKING_STORE_V2)
+		rc = bnxt_backing_store_cfg_v2(bp, ena);
+	else
+		rc = bnxt_hwrm_func_backing_store_cfg(bp, ena);
 	if (rc) {
 		netdev_err(bp->dev, "Failed configuring context mem, rc = %d.\n",
 			   rc);
@@ -7667,7 +8541,7 @@ int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all)
 	hw_resc->min_stat_ctxs = le16_to_cpu(resp->min_stat_ctx);
 	hw_resc->max_stat_ctxs = le16_to_cpu(resp->max_stat_ctx);
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		u16 max_msix = le16_to_cpu(resp->max_msix);
 
 		hw_resc->max_nqs = max_msix;
@@ -7696,7 +8570,7 @@ static int __bnxt_hwrm_ptp_qcfg(struct bnxt *bp)
 	u8 flags;
 	int rc;
 
-	if (bp->hwrm_spec_code < 0x10801 || !BNXT_CHIP_P5_THOR(bp)) {
+	if (bp->hwrm_spec_code < 0x10801 || !BNXT_CHIP_P5(bp)) {
 		rc = -ENODEV;
 		goto no_ptp;
 	}
@@ -7728,7 +8602,7 @@ static int __bnxt_hwrm_ptp_qcfg(struct bnxt *bp)
 	if (flags & PORT_MAC_PTP_QCFG_RESP_FLAGS_PARTIAL_DIRECT_ACCESS_REF_CLOCK) {
 		ptp->refclk_regs[0] = le32_to_cpu(resp->ts_ref_clock_reg_lower);
 		ptp->refclk_regs[1] = le32_to_cpu(resp->ts_ref_clock_reg_upper);
-	} else if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	} else if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		ptp->refclk_regs[0] = BNXT_TS_REG_TIMESYNC_TS0_LOWER;
 		ptp->refclk_regs[1] = BNXT_TS_REG_TIMESYNC_TS0_UPPER;
 	} else {
@@ -7800,10 +8674,16 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
 		bp->fw_cap |= BNXT_FW_CAP_HOT_RESET_IF;
 	if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_FW_LIVEPATCH_SUPPORTED))
 		bp->fw_cap |= BNXT_FW_CAP_LIVEPATCH;
+	if (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_BS_V2_SUPPORTED)
+		bp->fw_cap |= BNXT_FW_CAP_BACKING_STORE_V2;
+	if (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_TX_COAL_CMPL_CAP)
+		bp->flags |= BNXT_FLAG_TX_COAL_CMPL;
 
 	flags_ext2 = le32_to_cpu(resp->flags_ext2);
 	if (flags_ext2 & FUNC_QCAPS_RESP_FLAGS_EXT2_RX_ALL_PKTS_TIMESTAMPS_SUPPORTED)
 		bp->fw_cap |= BNXT_FW_CAP_RX_ALL_PKT_TS;
+	if (flags_ext2 & FUNC_QCAPS_RESP_FLAGS_EXT2_UDP_GSO_SUPPORTED)
+		bp->flags |= BNXT_FLAG_UDP_GSO_CAP;
 
 	bp->tx_push_thresh = 0;
 	if ((flags & FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED) &&
@@ -8435,7 +9315,7 @@ static void bnxt_accumulate_all_stats(struct bnxt *bp)
 	int i;
 
 	/* Chip bug.  Counter intermittently becomes 0. */
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		ignore_zero = true;
 
 	for (i = 0; i < bp->cp_nr_rings; i++) {
@@ -8629,7 +9509,7 @@ static void bnxt_clear_vnic(struct bnxt *bp)
 		return;
 
 	bnxt_hwrm_clear_vnic_filter(bp);
-	if (!(bp->flags & BNXT_FLAG_CHIP_P5)) {
+	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS)) {
 		/* clear all RSS setting before free vnic ctx */
 		bnxt_hwrm_clear_vnic_rss(bp);
 		bnxt_hwrm_vnic_ctx_free(bp);
@@ -8638,7 +9518,7 @@ static void bnxt_clear_vnic(struct bnxt *bp)
 	if (bp->flags & BNXT_FLAG_TPA)
 		bnxt_set_tpa(bp, false);
 	bnxt_hwrm_vnic_free(bp);
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		bnxt_hwrm_vnic_ctx_free(bp);
 }
 
@@ -8795,7 +9675,7 @@ static int __bnxt_setup_vnic_p5(struct bnxt *bp, u16 vnic_id)
 
 static int bnxt_setup_vnic(struct bnxt *bp, u16 vnic_id)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		return __bnxt_setup_vnic_p5(bp, vnic_id);
 	else
 		return __bnxt_setup_vnic(bp, vnic_id);
@@ -8803,10 +9683,9 @@ static int bnxt_setup_vnic(struct bnxt *bp, u16 vnic_id)
 
 static int bnxt_alloc_rfs_vnics(struct bnxt *bp)
 {
-#ifdef CONFIG_RFS_ACCEL
 	int i, rc = 0;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		return 0;
 
 	for (i = 0; i < bp->rx_nr_rings; i++) {
@@ -8819,7 +9698,7 @@ static int bnxt_alloc_rfs_vnics(struct bnxt *bp)
 
 		vnic = &bp->vnic_info[vnic_id];
 		vnic->flags |= BNXT_VNIC_RFS_FLAG;
-		if (bp->flags & BNXT_FLAG_NEW_RSS_CAP)
+		if (bp->rss_cap & BNXT_RSS_CAP_NEW_RSS_CAP)
 			vnic->flags |= BNXT_VNIC_RFS_NEW_RSS_FLAG;
 		rc = bnxt_hwrm_vnic_alloc(bp, vnic_id, ring_id, 1);
 		if (rc) {
@@ -8832,9 +9711,6 @@ static int bnxt_alloc_rfs_vnics(struct bnxt *bp)
 			break;
 	}
 	return rc;
-#else
-	return 0;
-#endif
 }
 
 /* Allow PF, trusted VFs and VFs with default VLAN to be in promiscuous mode */
@@ -8913,7 +9789,7 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init)
 	rc = bnxt_setup_vnic(bp, 0);
 	if (rc)
 		goto err_out;
-	if (bp->fw_cap & BNXT_FW_CAP_RSS_HASH_TYPE_DELTA)
+	if (bp->rss_cap & BNXT_RSS_CAP_RSS_HASH_TYPE_DELTA)
 		bnxt_hwrm_update_rss_hash_cfg(bp);
 
 	if (bp->flags & BNXT_FLAG_RFS) {
@@ -9031,8 +9907,8 @@ static int bnxt_set_real_num_queues(struct bnxt *bp)
 	return rc;
 }
 
-static int bnxt_trim_rings(struct bnxt *bp, int *rx, int *tx, int max,
-			   bool shared)
+static int __bnxt_trim_rings(struct bnxt *bp, int *rx, int *tx, int max,
+			     bool shared)
 {
 	int _rx = *rx, _tx = *tx;
 
@@ -9055,6 +9931,46 @@ static int bnxt_trim_rings(struct bnxt *bp, int *rx, int *tx, int max,
 	return 0;
 }
 
+static int __bnxt_num_tx_to_cp(struct bnxt *bp, int tx, int tx_sets, int tx_xdp)
+{
+	return (tx - tx_xdp) / tx_sets + tx_xdp;
+}
+
+int bnxt_num_tx_to_cp(struct bnxt *bp, int tx)
+{
+	int tcs = netdev_get_num_tc(bp->dev);
+
+	if (!tcs)
+		tcs = 1;
+	return __bnxt_num_tx_to_cp(bp, tx, tcs, bp->tx_nr_rings_xdp);
+}
+
+static int bnxt_num_cp_to_tx(struct bnxt *bp, int tx_cp)
+{
+	int tcs = netdev_get_num_tc(bp->dev);
+
+	return (tx_cp - bp->tx_nr_rings_xdp) * tcs +
+	       bp->tx_nr_rings_xdp;
+}
+
+static int bnxt_trim_rings(struct bnxt *bp, int *rx, int *tx, int max,
+			   bool sh)
+{
+	int tx_cp = bnxt_num_tx_to_cp(bp, *tx);
+
+	if (tx_cp != *tx) {
+		int tx_saved = tx_cp, rc;
+
+		rc = __bnxt_trim_rings(bp, rx, &tx_cp, max, sh);
+		if (rc)
+			return rc;
+		if (tx_cp != tx_saved)
+			*tx = bnxt_num_cp_to_tx(bp, tx_cp);
+		return 0;
+	}
+	return __bnxt_trim_rings(bp, rx, tx, max, sh);
+}
+
 static void bnxt_setup_msix(struct bnxt *bp)
 {
 	const int len = sizeof(bp->irq_tbl[0].name);
@@ -9067,7 +9983,7 @@ static void bnxt_setup_msix(struct bnxt *bp)
 
 		for (i = 0; i < tcs; i++) {
 			count = bp->tx_nr_rings_per_tc;
-			off = i * count;
+			off = BNXT_TC_TO_RING_BASE(bp, i);
 			netdev_set_tc_queue(dev, i, count, off);
 		}
 	}
@@ -9122,7 +10038,6 @@ static int bnxt_setup_int_mode(struct bnxt *bp)
 	return rc;
 }
 
-#ifdef CONFIG_RFS_ACCEL
 static unsigned int bnxt_get_max_func_rss_ctxs(struct bnxt *bp)
 {
 	return bp->hw_resc.max_rsscos_ctxs;
@@ -9132,7 +10047,6 @@ static unsigned int bnxt_get_max_func_vnics(struct bnxt *bp)
 {
 	return bp->hw_resc.max_vnics;
 }
-#endif
 
 unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp)
 {
@@ -9148,7 +10062,7 @@ static unsigned int bnxt_get_max_func_cp_rings_for_en(struct bnxt *bp)
 {
 	unsigned int cp = bp->hw_resc.max_cp_rings;
 
-	if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		cp -= bnxt_get_ulp_msix_num(bp);
 
 	return cp;
@@ -9158,7 +10072,7 @@ static unsigned int bnxt_get_max_func_irqs(struct bnxt *bp)
 {
 	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		return min_t(unsigned int, hw_resc->max_irqs, hw_resc->max_nqs);
 
 	return min_t(unsigned int, hw_resc->max_irqs, hw_resc->max_cp_rings);
@@ -9174,7 +10088,7 @@ unsigned int bnxt_get_avail_cp_rings_for_en(struct bnxt *bp)
 	unsigned int cp;
 
 	cp = bnxt_get_max_func_cp_rings_for_en(bp);
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		return cp - bp->rx_nr_rings - bp->tx_nr_rings;
 	else
 		return cp - bp->cp_nr_rings;
@@ -9193,7 +10107,7 @@ int bnxt_get_avail_msix(struct bnxt *bp, int num)
 	int max_idx, avail_msix;
 
 	max_idx = bp->total_irqs;
-	if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		max_idx = min_t(int, bp->total_irqs, max_cp);
 	avail_msix = max_idx - bp->cp_nr_rings;
 	if (!BNXT_NEW_RM(bp) || avail_msix >= num)
@@ -9217,7 +10131,7 @@ static int bnxt_get_num_msix(struct bnxt *bp)
 
 static int bnxt_init_msix(struct bnxt *bp)
 {
-	int i, total_vecs, max, rc = 0, min = 1, ulp_msix;
+	int i, total_vecs, max, rc = 0, min = 1, ulp_msix, tx_cp;
 	struct msix_entry *msix_ent;
 
 	total_vecs = bnxt_get_num_msix(bp);
@@ -9259,9 +10173,10 @@ static int bnxt_init_msix(struct bnxt *bp)
 		if (rc)
 			goto msix_setup_exit;
 
+		tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings);
 		bp->cp_nr_rings = (min == 1) ?
-				  max_t(int, bp->tx_nr_rings, bp->rx_nr_rings) :
-				  bp->tx_nr_rings + bp->rx_nr_rings;
+				  max_t(int, tx_cp, bp->rx_nr_rings) :
+				  tx_cp + bp->rx_nr_rings;
 
 	} else {
 		rc = -ENOMEM;
@@ -9424,6 +10339,7 @@ static int bnxt_request_irq(struct bnxt *bp)
 		if (rc)
 			break;
 
+		netif_napi_set_irq(&bp->bnapi[i]->napi, irq->vector);
 		irq->requested = 1;
 
 		if (zalloc_cpumask_var(&irq->cpu_mask, GFP_KERNEL)) {
@@ -9451,6 +10367,11 @@ static void bnxt_del_napi(struct bnxt *bp)
 	if (!bp->bnapi)
 		return;
 
+	for (i = 0; i < bp->rx_nr_rings; i++)
+		netif_queue_set_napi(bp->dev, i, NETDEV_QUEUE_TYPE_RX, NULL);
+	for (i = 0; i < bp->tx_nr_rings - bp->tx_nr_rings_xdp; i++)
+		netif_queue_set_napi(bp->dev, i, NETDEV_QUEUE_TYPE_TX, NULL);
+
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 
@@ -9471,7 +10392,7 @@ static void bnxt_init_napi(struct bnxt *bp)
 	if (bp->flags & BNXT_FLAG_USING_MSIX) {
 		int (*poll_fn)(struct napi_struct *, int) = bnxt_poll;
 
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 			poll_fn = bnxt_poll_p5;
 		else if (BNXT_CHIP_TYPE_NITRO_A0(bp))
 			cp_nr_rings--;
@@ -9527,8 +10448,6 @@ static void bnxt_enable_napi(struct bnxt *bp)
 		cpr = &bnapi->cp_ring;
 		bnapi->in_reset = false;
 
-		bnapi->tx_pkts = 0;
-
 		if (bnapi->rx_ring) {
 			INIT_WORK(&cpr->dim.work, bnxt_dim_work);
 			cpr->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
@@ -9632,7 +10551,10 @@ void bnxt_report_link(struct bnxt *bp)
 				signal = "(NRZ) ";
 				break;
 			case PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4:
-				signal = "(PAM4) ";
+				signal = "(PAM4 56Gbps) ";
+				break;
+			case PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4_112:
+				signal = "(PAM4 112Gbps) ";
 				break;
 			default:
 				break;
@@ -9660,7 +10582,9 @@ static bool bnxt_phy_qcaps_no_speed(struct hwrm_port_phy_qcaps_output *resp)
 	if (!resp->supported_speeds_auto_mode &&
 	    !resp->supported_speeds_force_mode &&
 	    !resp->supported_pam4_speeds_auto_mode &&
-	    !resp->supported_pam4_speeds_force_mode)
+	    !resp->supported_pam4_speeds_force_mode &&
+	    !resp->supported_speeds2_auto_mode &&
+	    !resp->supported_speeds2_force_mode)
 		return true;
 	return false;
 }
@@ -9706,6 +10630,7 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp)
 			/* Phy re-enabled, reprobe the speeds */
 			link_info->support_auto_speeds = 0;
 			link_info->support_pam4_auto_speeds = 0;
+			link_info->support_auto_speeds2 = 0;
 		}
 	}
 	if (resp->supported_speeds_auto_mode)
@@ -9714,6 +10639,9 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp)
 	if (resp->supported_pam4_speeds_auto_mode)
 		link_info->support_pam4_auto_speeds =
 			le16_to_cpu(resp->supported_pam4_speeds_auto_mode);
+	if (resp->supported_speeds2_auto_mode)
+		link_info->support_auto_speeds2 =
+			le16_to_cpu(resp->supported_speeds2_auto_mode);
 
 	bp->port_count = resp->port_cnt;
 
@@ -9731,9 +10659,19 @@ static bool bnxt_support_dropped(u16 advertising, u16 supported)
 
 static bool bnxt_support_speed_dropped(struct bnxt_link_info *link_info)
 {
+	struct bnxt *bp = container_of(link_info, struct bnxt, link_info);
+
 	/* Check if any advertised speeds are no longer supported. The caller
 	 * holds the link_lock mutex, so we can modify link_info settings.
 	 */
+	if (bp->phy_flags & BNXT_PHY_FL_SPEEDS2) {
+		if (bnxt_support_dropped(link_info->advertising,
+					 link_info->support_auto_speeds2)) {
+			link_info->advertising = link_info->support_auto_speeds2;
+			return true;
+		}
+		return false;
+	}
 	if (bnxt_support_dropped(link_info->advertising,
 				 link_info->support_auto_speeds)) {
 		link_info->advertising = link_info->support_auto_speeds;
@@ -9782,18 +10720,25 @@ int bnxt_update_link(struct bnxt *bp, bool chng_link_state)
 	link_info->lp_pause = resp->link_partner_adv_pause;
 	link_info->force_pause_setting = resp->force_pause;
 	link_info->duplex_setting = resp->duplex_cfg;
-	if (link_info->phy_link_status == BNXT_LINK_LINK)
+	if (link_info->phy_link_status == BNXT_LINK_LINK) {
 		link_info->link_speed = le16_to_cpu(resp->link_speed);
-	else
+		if (bp->phy_flags & BNXT_PHY_FL_SPEEDS2)
+			link_info->active_lanes = resp->active_lanes;
+	} else {
 		link_info->link_speed = 0;
+		link_info->active_lanes = 0;
+	}
 	link_info->force_link_speed = le16_to_cpu(resp->force_link_speed);
 	link_info->force_pam4_link_speed =
 		le16_to_cpu(resp->force_pam4_link_speed);
+	link_info->force_link_speed2 = le16_to_cpu(resp->force_link_speeds2);
 	link_info->support_speeds = le16_to_cpu(resp->support_speeds);
 	link_info->support_pam4_speeds = le16_to_cpu(resp->support_pam4_speeds);
+	link_info->support_speeds2 = le16_to_cpu(resp->support_speeds2);
 	link_info->auto_link_speeds = le16_to_cpu(resp->auto_link_speed_mask);
 	link_info->auto_pam4_link_speeds =
 		le16_to_cpu(resp->auto_pam4_link_speed_mask);
+	link_info->auto_link_speeds2 = le16_to_cpu(resp->auto_link_speeds2);
 	link_info->lp_auto_link_speeds =
 		le16_to_cpu(resp->link_partner_adv_speeds);
 	link_info->lp_auto_pam4_link_speeds =
@@ -9932,7 +10877,11 @@ static void bnxt_hwrm_set_link_common(struct bnxt *bp, struct hwrm_port_phy_cfg_
 {
 	if (bp->link_info.autoneg & BNXT_AUTONEG_SPEED) {
 		req->auto_mode |= PORT_PHY_CFG_REQ_AUTO_MODE_SPEED_MASK;
-		if (bp->link_info.advertising) {
+		if (bp->phy_flags & BNXT_PHY_FL_SPEEDS2) {
+			req->enables |=
+				cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEEDS2_MASK);
+			req->auto_link_speeds2_mask = cpu_to_le16(bp->link_info.advertising);
+		} else if (bp->link_info.advertising) {
 			req->enables |= cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEED_MASK);
 			req->auto_link_speed_mask = cpu_to_le16(bp->link_info.advertising);
 		}
@@ -9946,7 +10895,12 @@ static void bnxt_hwrm_set_link_common(struct bnxt *bp, struct hwrm_port_phy_cfg_
 		req->flags |= cpu_to_le32(PORT_PHY_CFG_REQ_FLAGS_RESTART_AUTONEG);
 	} else {
 		req->flags |= cpu_to_le32(PORT_PHY_CFG_REQ_FLAGS_FORCE);
-		if (bp->link_info.req_signal_mode == BNXT_SIG_MODE_PAM4) {
+		if (bp->phy_flags & BNXT_PHY_FL_SPEEDS2) {
+			req->force_link_speeds2 = cpu_to_le16(bp->link_info.req_link_speed);
+			req->enables |= cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_FORCE_LINK_SPEEDS2);
+			netif_info(bp, link, bp->dev, "Forcing FW speed2: %d\n",
+				   (u32)bp->link_info.req_link_speed);
+		} else if (bp->link_info.req_signal_mode == BNXT_SIG_MODE_PAM4) {
 			req->force_pam4_link_speed = cpu_to_le16(bp->link_info.req_link_speed);
 			req->enables |= cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_FORCE_PAM4_LINK_SPEED);
 		} else {
@@ -10211,8 +11165,6 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 			if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
 				bnxt_ulp_stop(bp);
 			bnxt_free_ctx_mem(bp);
-			kfree(bp->ctx);
-			bp->ctx = NULL;
 			bnxt_dcb_free(bp);
 			rc = bnxt_fw_init_one(bp);
 			if (rc) {
@@ -10731,10 +11683,8 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,
 	bnxt_free_mem(bp, irq_re_init);
 }
 
-int bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
+void bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 {
-	int rc = 0;
-
 	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
 		/* If we get here, it means firmware reset is in progress
 		 * while we are trying to close.  We can safely proceed with
@@ -10749,15 +11699,18 @@ int bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 
 #ifdef CONFIG_BNXT_SRIOV
 	if (bp->sriov_cfg) {
+		int rc;
+
 		rc = wait_event_interruptible_timeout(bp->sriov_cfg_wait,
 						      !bp->sriov_cfg,
 						      BNXT_SRIOV_CFG_WAIT_TMO);
-		if (rc)
-			netdev_warn(bp->dev, "timeout waiting for SRIOV config operation to complete!\n");
+		if (!rc)
+			netdev_warn(bp->dev, "timeout waiting for SRIOV config operation to complete, proceeding to close!\n");
+		else if (rc < 0)
+			netdev_warn(bp->dev, "SRIOV config operation interrupted, proceeding to close!\n");
 	}
 #endif
 	__bnxt_close_nic(bp, irq_re_init, link_re_init);
-	return rc;
 }
 
 static int bnxt_close(struct net_device *dev)
@@ -11096,7 +12049,6 @@ static int bnxt_cfg_rx_mode(struct bnxt *bp)
 {
 	struct net_device *dev = bp->dev;
 	struct bnxt_vnic_info *vnic = &bp->vnic_info[0];
-	struct hwrm_cfa_l2_filter_free_input *req;
 	struct netdev_hw_addr *ha;
 	int i, off = 0, rc;
 	bool uc_update;
@@ -11108,16 +12060,12 @@ static int bnxt_cfg_rx_mode(struct bnxt *bp)
 	if (!uc_update)
 		goto skip_uc;
 
-	rc = hwrm_req_init(bp, req, HWRM_CFA_L2_FILTER_FREE);
-	if (rc)
-		return rc;
-	hwrm_req_hold(bp, req);
 	for (i = 1; i < vnic->uc_filter_count; i++) {
-		req->l2_filter_id = vnic->fw_l2_filter_id[i];
+		struct bnxt_l2_filter *fltr = vnic->l2_filters[i];
 
-		rc = hwrm_req_send(bp, req);
+		bnxt_hwrm_l2_filter_free(bp, fltr);
+		bnxt_del_l2_filter(bp, fltr);
 	}
-	hwrm_req_drop(bp, req);
 
 	vnic->uc_filter_count = 1;
 
@@ -11194,7 +12142,7 @@ static bool bnxt_can_reserve_rings(struct bnxt *bp)
 /* If the chip and firmware supports RFS */
 static bool bnxt_rfs_supported(struct bnxt *bp)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		if (bp->fw_cap & BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V2)
 			return true;
 		return false;
@@ -11204,7 +12152,7 @@ static bool bnxt_rfs_supported(struct bnxt *bp)
 		return false;
 	if (BNXT_PF(bp) && !BNXT_CHIP_TYPE_NITRO_A0(bp))
 		return true;
-	if (bp->flags & BNXT_FLAG_NEW_RSS_CAP)
+	if (bp->rss_cap & BNXT_RSS_CAP_NEW_RSS_CAP)
 		return true;
 	return false;
 }
@@ -11212,10 +12160,9 @@ static bool bnxt_rfs_supported(struct bnxt *bp)
 /* If runtime conditions support RFS */
 static bool bnxt_rfs_capable(struct bnxt *bp)
 {
-#ifdef CONFIG_RFS_ACCEL
 	int vnics, max_vnics, max_rss_ctxs;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		return bnxt_rfs_supported(bp);
 	if (!(bp->flags & BNXT_FLAG_MSIX_CAP) || !bnxt_can_reserve_rings(bp) || !bp->rx_nr_rings)
 		return false;
@@ -11225,7 +12172,7 @@ static bool bnxt_rfs_capable(struct bnxt *bp)
 	max_rss_ctxs = bnxt_get_max_func_rss_ctxs(bp);
 
 	/* RSS contexts not a limiting factor */
-	if (bp->flags & BNXT_FLAG_NEW_RSS_CAP)
+	if (bp->rss_cap & BNXT_RSS_CAP_NEW_RSS_CAP)
 		max_rss_ctxs = max_vnics;
 	if (vnics > max_vnics || vnics > max_rss_ctxs) {
 		if (bp->rx_nr_rings > 1)
@@ -11248,9 +12195,6 @@ static bool bnxt_rfs_capable(struct bnxt *bp)
 	netdev_warn(bp->dev, "Unable to reserve resources to support NTUPLE filters.\n");
 	bnxt_hwrm_reserve_rings(bp, 0, 0, 0, 0, 0, 1);
 	return false;
-#else
-	return false;
-#endif
 }
 
 static netdev_features_t bnxt_fix_features(struct net_device *dev,
@@ -11317,7 +12261,7 @@ static int bnxt_set_features(struct net_device *dev, netdev_features_t features)
 		update_tpa = true;
 		if ((bp->flags & BNXT_FLAG_TPA) == 0 ||
 		    (flags & BNXT_FLAG_TPA) == 0 ||
-		    (bp->flags & BNXT_FLAG_CHIP_P5))
+		    (bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 			re_init = true;
 	}
 
@@ -11426,9 +12370,10 @@ static bool bnxt_udp_tunl_check(struct bnxt *bp, struct sk_buff *skb)
 	struct udphdr *uh = udp_hdr(skb);
 	__be16 udp_port = uh->dest;
 
-	if (udp_port != bp->vxlan_port && udp_port != bp->nge_port)
+	if (udp_port != bp->vxlan_port && udp_port != bp->nge_port &&
+	    udp_port != bp->vxlan_gpe_port)
 		return false;
-	if (skb->inner_protocol_type == ENCAP_TYPE_ETHER) {
+	if (skb->inner_protocol == htons(ETH_P_TEB)) {
 		struct ethhdr *eh = inner_eth_hdr(skb);
 
 		switch (eh->h_proto) {
@@ -11439,6 +12384,11 @@ static bool bnxt_udp_tunl_check(struct bnxt *bp, struct sk_buff *skb)
 						 skb_inner_network_offset(skb),
 						 NULL);
 		}
+	} else if (skb->inner_protocol == htons(ETH_P_IP)) {
+		return true;
+	} else if (skb->inner_protocol == htons(ETH_P_IPV6)) {
+		return bnxt_exthdr_check(bp, skb, skb_inner_network_offset(skb),
+					 NULL);
 	}
 	return false;
 }
@@ -11559,15 +12509,13 @@ static int bnxt_dbg_hwrm_ring_info_get(struct bnxt *bp, u8 ring_type,
 
 static void bnxt_dump_tx_sw_state(struct bnxt_napi *bnapi)
 {
-	struct bnxt_tx_ring_info *txr = bnapi->tx_ring;
-	int i = bnapi->index;
-
-	if (!txr)
-		return;
+	struct bnxt_tx_ring_info *txr;
+	int i = bnapi->index, j;
 
-	netdev_info(bnapi->bp->dev, "[%d]: tx{fw_ring: %d prod: %x cons: %x}\n",
-		    i, txr->tx_ring_struct.fw_ring_id, txr->tx_prod,
-		    txr->tx_cons);
+	bnxt_for_each_napi_tx(j, bnapi, txr)
+		netdev_info(bnapi->bp->dev, "[%d.%d]: tx{fw_ring: %d prod: %x cons: %x}\n",
+			    i, j, txr->tx_ring_struct.fw_ring_id, txr->tx_prod,
+			    txr->tx_cons);
 }
 
 static void bnxt_dump_rx_sw_state(struct bnxt_napi *bnapi)
@@ -11730,8 +12678,7 @@ static void bnxt_timer(struct timer_list *t)
 	if (test_bit(BNXT_STATE_L2_FILTER_RETRY, &bp->state))
 		bnxt_queue_sp_work(bp, BNXT_RX_MASK_SP_EVENT);
 
-	if ((bp->flags & BNXT_FLAG_CHIP_P5) && !bp->chip_rev &&
-	    netif_carrier_ok(dev))
+	if ((BNXT_CHIP_P5(bp)) && !bp->chip_rev && netif_carrier_ok(dev))
 		bnxt_queue_sp_work(bp, BNXT_RING_COAL_NOW_SP_EVENT);
 
 bnxt_restart_timer:
@@ -11840,8 +12787,6 @@ static void bnxt_fw_reset_close(struct bnxt *bp)
 	if (pci_is_enabled(bp->pdev))
 		pci_disable_device(bp->pdev);
 	bnxt_free_ctx_mem(bp);
-	kfree(bp->ctx);
-	bp->ctx = NULL;
 }
 
 static bool is_bnxt_fw_ok(struct bnxt *bp)
@@ -11984,7 +12929,7 @@ static void bnxt_chk_missed_irq(struct bnxt *bp)
 {
 	int i;
 
-	if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		return;
 
 	for (i = 0; i < bp->cp_nr_rings; i++) {
@@ -11997,12 +12942,11 @@ static void bnxt_chk_missed_irq(struct bnxt *bp)
 			continue;
 
 		cpr = &bnapi->cp_ring;
-		for (j = 0; j < 2; j++) {
-			struct bnxt_cp_ring_info *cpr2 = cpr->cp_ring_arr[j];
+		for (j = 0; j < cpr->cp_ring_count; j++) {
+			struct bnxt_cp_ring_info *cpr2 = &cpr->cp_ring_arr[j];
 			u32 val[2];
 
-			if (!cpr2 || cpr2->has_more_work ||
-			    !bnxt_has_work(bp, cpr2))
+			if (cpr2->has_more_work || !bnxt_has_work(bp, cpr2))
 				continue;
 
 			if (cpr2->cp_raw_cons != cpr2->last_cp_raw_cons) {
@@ -12077,6 +13021,8 @@ static void bnxt_sp_task(struct work_struct *work)
 		bnxt_cfg_ntp_filters(bp);
 	if (test_and_clear_bit(BNXT_HWRM_EXEC_FWD_REQ_SP_EVENT, &bp->sp_event))
 		bnxt_hwrm_exec_fwd_req(bp);
+	if (test_and_clear_bit(BNXT_HWRM_PF_UNLOAD_SP_EVENT, &bp->sp_event))
+		netdev_info(bp->dev, "Receive PF driver unload event!\n");
 	if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event)) {
 		bnxt_hwrm_port_qstats(bp, 0);
 		bnxt_hwrm_port_qstats_ext(bp, 0);
@@ -12161,36 +13107,42 @@ static void bnxt_sp_task(struct work_struct *work)
 	clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
 }
 
+static void _bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx,
+				int *max_cp);
+
 /* Under rtnl_lock */
 int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 		     int tx_xdp)
 {
-	int max_rx, max_tx, tx_sets = 1;
+	int max_rx, max_tx, max_cp, tx_sets = 1, tx_cp;
 	int tx_rings_needed, stats;
 	int rx_rings = rx;
-	int cp, vnics, rc;
+	int cp, vnics;
 
 	if (tcs)
 		tx_sets = tcs;
 
-	rc = bnxt_get_max_rings(bp, &max_rx, &max_tx, sh);
-	if (rc)
-		return rc;
+	_bnxt_get_max_rings(bp, &max_rx, &max_tx, &max_cp);
 
-	if (max_rx < rx)
+	if (max_rx < rx_rings)
 		return -ENOMEM;
 
+	if (bp->flags & BNXT_FLAG_AGG_RINGS)
+		rx_rings <<= 1;
+
 	tx_rings_needed = tx * tx_sets + tx_xdp;
 	if (max_tx < tx_rings_needed)
 		return -ENOMEM;
 
 	vnics = 1;
-	if ((bp->flags & (BNXT_FLAG_RFS | BNXT_FLAG_CHIP_P5)) == BNXT_FLAG_RFS)
-		vnics += rx_rings;
+	if ((bp->flags & (BNXT_FLAG_RFS | BNXT_FLAG_CHIP_P5_PLUS)) ==
+	    BNXT_FLAG_RFS)
+		vnics += rx;
 
-	if (bp->flags & BNXT_FLAG_AGG_RINGS)
-		rx_rings <<= 1;
-	cp = sh ? max_t(int, tx_rings_needed, rx) : tx_rings_needed + rx;
+	tx_cp = __bnxt_num_tx_to_cp(bp, tx_rings_needed, tx_sets, tx_xdp);
+	cp = sh ? max_t(int, tx_cp, rx) : tx_cp + rx;
+	if (max_cp < cp)
+		return -ENOMEM;
 	stats = cp;
 	if (BNXT_NEW_RM(bp)) {
 		cp += bnxt_get_ulp_msix_num(bp);
@@ -12265,10 +13217,10 @@ static bool bnxt_fw_pre_resv_vnics(struct bnxt *bp)
 {
 	u16 fw_maj = BNXT_FW_MAJ(bp), fw_bld = BNXT_FW_BLD(bp);
 
-	if (!(bp->flags & BNXT_FLAG_CHIP_P5) &&
+	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS) &&
 	    (fw_maj > 218 || (fw_maj == 218 && fw_bld >= 18)))
 		return true;
-	if ((bp->flags & BNXT_FLAG_CHIP_P5) &&
+	if ((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) &&
 	    (fw_maj > 216 || (fw_maj == 216 && fw_bld >= 172)))
 		return true;
 	return false;
@@ -12346,15 +13298,15 @@ static int bnxt_fw_init_one_p2(struct bnxt *bp)
 
 static void bnxt_set_dflt_rss_hash_type(struct bnxt *bp)
 {
-	bp->flags &= ~BNXT_FLAG_UDP_RSS_CAP;
+	bp->rss_cap &= ~BNXT_RSS_CAP_UDP_RSS_CAP;
 	bp->rss_hash_cfg = VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4 |
 			   VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4 |
 			   VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 |
 			   VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6;
-	if (bp->fw_cap & BNXT_FW_CAP_RSS_HASH_TYPE_DELTA)
+	if (bp->rss_cap & BNXT_RSS_CAP_RSS_HASH_TYPE_DELTA)
 		bp->rss_hash_delta = bp->rss_hash_cfg;
 	if (BNXT_CHIP_P4_PLUS(bp) && bp->hwrm_spec_code >= 0x10501) {
-		bp->flags |= BNXT_FLAG_UDP_RSS_CAP;
+		bp->rss_cap |= BNXT_RSS_CAP_UDP_RSS_CAP;
 		bp->rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4 |
 				    VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6;
 	}
@@ -12824,7 +13776,7 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	bool sh = false;
-	int rc;
+	int rc, tx_cp;
 
 	if (tc > bp->max_tc) {
 		netdev_err(dev, "Too many traffic classes requested: %d. Max supported is %d.\n",
@@ -12855,8 +13807,9 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 		netdev_reset_tc(dev);
 	}
 	bp->tx_nr_rings += bp->tx_nr_rings_xdp;
-	bp->cp_nr_rings = sh ? max_t(int, bp->tx_nr_rings, bp->rx_nr_rings) :
-			       bp->tx_nr_rings + bp->rx_nr_rings;
+	tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings);
+	bp->cp_nr_rings = sh ? max_t(int, tx_cp, bp->rx_nr_rings) :
+			       tx_cp + bp->rx_nr_rings;
 
 	if (netif_running(bp->dev))
 		return bnxt_open_nic(bp, true, false);
@@ -12906,38 +13859,102 @@ static int bnxt_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	}
 }
 
-#ifdef CONFIG_RFS_ACCEL
+u32 bnxt_get_ntp_filter_idx(struct bnxt *bp, struct flow_keys *fkeys,
+			    const struct sk_buff *skb)
+{
+	struct bnxt_vnic_info *vnic;
+
+	if (skb)
+		return skb_get_hash_raw(skb) & BNXT_NTP_FLTR_HASH_MASK;
+
+	vnic = &bp->vnic_info[0];
+	return bnxt_toeplitz(bp, fkeys, (void *)vnic->rss_hash_key);
+}
+
+int bnxt_insert_ntp_filter(struct bnxt *bp, struct bnxt_ntuple_filter *fltr,
+			   u32 idx)
+{
+	struct hlist_head *head;
+	int bit_id;
+
+	spin_lock_bh(&bp->ntp_fltr_lock);
+	bit_id = bitmap_find_free_region(bp->ntp_fltr_bmap, BNXT_MAX_FLTR, 0);
+	if (bit_id < 0) {
+		spin_unlock_bh(&bp->ntp_fltr_lock);
+		return -ENOMEM;
+	}
+
+	fltr->base.sw_id = (u16)bit_id;
+	fltr->base.type = BNXT_FLTR_TYPE_NTUPLE;
+	fltr->base.flags |= BNXT_ACT_RING_DST;
+	head = &bp->ntp_fltr_hash_tbl[idx];
+	hlist_add_head_rcu(&fltr->base.hash, head);
+	set_bit(BNXT_FLTR_INSERTED, &fltr->base.state);
+	bp->ntp_fltr_count++;
+	spin_unlock_bh(&bp->ntp_fltr_lock);
+	return 0;
+}
+
 static bool bnxt_fltr_match(struct bnxt_ntuple_filter *f1,
 			    struct bnxt_ntuple_filter *f2)
 {
 	struct flow_keys *keys1 = &f1->fkeys;
 	struct flow_keys *keys2 = &f2->fkeys;
 
+	if (f1->ntuple_flags != f2->ntuple_flags)
+		return false;
+
 	if (keys1->basic.n_proto != keys2->basic.n_proto ||
 	    keys1->basic.ip_proto != keys2->basic.ip_proto)
 		return false;
 
 	if (keys1->basic.n_proto == htons(ETH_P_IP)) {
-		if (keys1->addrs.v4addrs.src != keys2->addrs.v4addrs.src ||
-		    keys1->addrs.v4addrs.dst != keys2->addrs.v4addrs.dst)
+		if (((f1->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_IP) &&
+		     keys1->addrs.v4addrs.src != keys2->addrs.v4addrs.src) ||
+		    ((f1->ntuple_flags & BNXT_NTUPLE_MATCH_DST_IP) &&
+		     keys1->addrs.v4addrs.dst != keys2->addrs.v4addrs.dst))
 			return false;
 	} else {
-		if (memcmp(&keys1->addrs.v6addrs.src, &keys2->addrs.v6addrs.src,
-			   sizeof(keys1->addrs.v6addrs.src)) ||
-		    memcmp(&keys1->addrs.v6addrs.dst, &keys2->addrs.v6addrs.dst,
-			   sizeof(keys1->addrs.v6addrs.dst)))
+		if (((f1->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_IP) &&
+		     memcmp(&keys1->addrs.v6addrs.src,
+			    &keys2->addrs.v6addrs.src,
+			    sizeof(keys1->addrs.v6addrs.src))) ||
+		    ((f1->ntuple_flags & BNXT_NTUPLE_MATCH_DST_IP) &&
+		     memcmp(&keys1->addrs.v6addrs.dst,
+			    &keys2->addrs.v6addrs.dst,
+			    sizeof(keys1->addrs.v6addrs.dst))))
 			return false;
 	}
 
-	if (keys1->ports.ports == keys2->ports.ports &&
-	    keys1->control.flags == keys2->control.flags &&
-	    ether_addr_equal(f1->src_mac_addr, f2->src_mac_addr) &&
-	    ether_addr_equal(f1->dst_mac_addr, f2->dst_mac_addr))
+	if (((f1->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_PORT) &&
+	     keys1->ports.src != keys2->ports.src) ||
+	    ((f1->ntuple_flags & BNXT_NTUPLE_MATCH_DST_PORT) &&
+	     keys1->ports.dst != keys2->ports.dst))
+		return false;
+
+	if (keys1->control.flags == keys2->control.flags &&
+	    f1->l2_fltr == f2->l2_fltr)
 		return true;
 
 	return false;
 }
 
+struct bnxt_ntuple_filter *
+bnxt_lookup_ntp_filter_from_idx(struct bnxt *bp,
+				struct bnxt_ntuple_filter *fltr, u32 idx)
+{
+	struct bnxt_ntuple_filter *f;
+	struct hlist_head *head;
+
+	head = &bp->ntp_fltr_hash_tbl[idx];
+	hlist_for_each_entry_rcu(f, head, base.hash) {
+		if (bnxt_fltr_match(f, fltr))
+			return f;
+	}
+	return NULL;
+}
+
+#ifdef CONFIG_RFS_ACCEL
 static int bnxt_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 			      u16 rxq_index, u32 flow_id)
 {
@@ -12945,29 +13962,31 @@ static int bnxt_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 	struct bnxt_ntuple_filter *fltr, *new_fltr;
 	struct flow_keys *fkeys;
 	struct ethhdr *eth = (struct ethhdr *)skb_mac_header(skb);
-	int rc = 0, idx, bit_id, l2_idx = 0;
-	struct hlist_head *head;
+	struct bnxt_l2_filter *l2_fltr;
+	int rc = 0, idx;
 	u32 flags;
 
-	if (!ether_addr_equal(dev->dev_addr, eth->h_dest)) {
-		struct bnxt_vnic_info *vnic = &bp->vnic_info[0];
-		int off = 0, j;
+	if (ether_addr_equal(dev->dev_addr, eth->h_dest)) {
+		l2_fltr = bp->vnic_info[0].l2_filters[0];
+		atomic_inc(&l2_fltr->refcnt);
+	} else {
+		struct bnxt_l2_key key;
 
-		netif_addr_lock_bh(dev);
-		for (j = 0; j < vnic->uc_filter_count; j++, off += ETH_ALEN) {
-			if (ether_addr_equal(eth->h_dest,
-					     vnic->uc_list + off)) {
-				l2_idx = j + 1;
-				break;
-			}
-		}
-		netif_addr_unlock_bh(dev);
-		if (!l2_idx)
+		ether_addr_copy(key.dst_mac_addr, eth->h_dest);
+		key.vlan = 0;
+		l2_fltr = bnxt_lookup_l2_filter_from_key(bp, &key);
+		if (!l2_fltr)
 			return -EINVAL;
+		if (l2_fltr->base.flags & BNXT_ACT_FUNC_DST) {
+			bnxt_del_l2_filter(bp, l2_fltr);
+			return -EINVAL;
+		}
 	}
 	new_fltr = kzalloc(sizeof(*new_fltr), GFP_ATOMIC);
-	if (!new_fltr)
+	if (!new_fltr) {
+		bnxt_del_l2_filter(bp, l2_fltr);
 		return -ENOMEM;
+	}
 
 	fkeys = &new_fltr->fkeys;
 	if (!skb_flow_dissect_flow_keys(skb, fkeys, 0)) {
@@ -12994,49 +14013,52 @@ static int bnxt_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 		goto err_free;
 	}
 
-	memcpy(new_fltr->dst_mac_addr, eth->h_dest, ETH_ALEN);
-	memcpy(new_fltr->src_mac_addr, eth->h_source, ETH_ALEN);
+	new_fltr->l2_fltr = l2_fltr;
+	new_fltr->ntuple_flags = BNXT_NTUPLE_MATCH_ALL;
 
-	idx = skb_get_hash_raw(skb) & BNXT_NTP_FLTR_HASH_MASK;
-	head = &bp->ntp_fltr_hash_tbl[idx];
+	idx = bnxt_get_ntp_filter_idx(bp, fkeys, skb);
 	rcu_read_lock();
-	hlist_for_each_entry_rcu(fltr, head, hash) {
-		if (bnxt_fltr_match(fltr, new_fltr)) {
-			rc = fltr->sw_id;
-			rcu_read_unlock();
-			goto err_free;
-		}
-	}
-	rcu_read_unlock();
-
-	spin_lock_bh(&bp->ntp_fltr_lock);
-	bit_id = bitmap_find_free_region(bp->ntp_fltr_bmap,
-					 BNXT_NTP_FLTR_MAX_FLTR, 0);
-	if (bit_id < 0) {
-		spin_unlock_bh(&bp->ntp_fltr_lock);
-		rc = -ENOMEM;
+	fltr = bnxt_lookup_ntp_filter_from_idx(bp, new_fltr, idx);
+	if (fltr) {
+		rc = fltr->base.sw_id;
+		rcu_read_unlock();
 		goto err_free;
 	}
+	rcu_read_unlock();
 
-	new_fltr->sw_id = (u16)bit_id;
 	new_fltr->flow_id = flow_id;
-	new_fltr->l2_fltr_idx = l2_idx;
-	new_fltr->rxq = rxq_index;
-	hlist_add_head_rcu(&new_fltr->hash, head);
-	bp->ntp_fltr_count++;
-	spin_unlock_bh(&bp->ntp_fltr_lock);
-
-	bnxt_queue_sp_work(bp, BNXT_RX_NTP_FLTR_SP_EVENT);
-
-	return new_fltr->sw_id;
+	new_fltr->base.rxq = rxq_index;
+	rc = bnxt_insert_ntp_filter(bp, new_fltr, idx);
+	if (!rc) {
+		bnxt_queue_sp_work(bp, BNXT_RX_NTP_FLTR_SP_EVENT);
+		return new_fltr->base.sw_id;
+	}
 
 err_free:
+	bnxt_del_l2_filter(bp, l2_fltr);
 	kfree(new_fltr);
 	return rc;
 }
+#endif
+
+void bnxt_del_ntp_filter(struct bnxt *bp, struct bnxt_ntuple_filter *fltr)
+{
+	spin_lock_bh(&bp->ntp_fltr_lock);
+	if (!test_and_clear_bit(BNXT_FLTR_INSERTED, &fltr->base.state)) {
+		spin_unlock_bh(&bp->ntp_fltr_lock);
+		return;
+	}
+	hlist_del_rcu(&fltr->base.hash);
+	bp->ntp_fltr_count--;
+	spin_unlock_bh(&bp->ntp_fltr_lock);
+	bnxt_del_l2_filter(bp, fltr->l2_fltr);
+	clear_bit(fltr->base.sw_id, bp->ntp_fltr_bmap);
+	kfree_rcu(fltr, base.rcu);
+}
 
 static void bnxt_cfg_ntp_filters(struct bnxt *bp)
 {
+#ifdef CONFIG_RFS_ACCEL
 	int i;
 
 	for (i = 0; i < BNXT_NTP_FLTR_HASH_SIZE; i++) {
@@ -13046,13 +14068,15 @@ static void bnxt_cfg_ntp_filters(struct bnxt *bp)
 		int rc;
 
 		head = &bp->ntp_fltr_hash_tbl[i];
-		hlist_for_each_entry_safe(fltr, tmp, head, hash) {
+		hlist_for_each_entry_safe(fltr, tmp, head, base.hash) {
 			bool del = false;
 
-			if (test_bit(BNXT_FLTR_VALID, &fltr->state)) {
-				if (rps_may_expire_flow(bp->dev, fltr->rxq,
+			if (test_bit(BNXT_FLTR_VALID, &fltr->base.state)) {
+				if (fltr->base.flags & BNXT_ACT_NO_AGING)
+					continue;
+				if (rps_may_expire_flow(bp->dev, fltr->base.rxq,
 							fltr->flow_id,
-							fltr->sw_id)) {
+							fltr->base.sw_id)) {
 					bnxt_hwrm_cfa_ntuple_filter_free(bp,
 									 fltr);
 					del = true;
@@ -13063,32 +14087,16 @@ static void bnxt_cfg_ntp_filters(struct bnxt *bp)
 				if (rc)
 					del = true;
 				else
-					set_bit(BNXT_FLTR_VALID, &fltr->state);
+					set_bit(BNXT_FLTR_VALID, &fltr->base.state);
 			}
 
-			if (del) {
-				spin_lock_bh(&bp->ntp_fltr_lock);
-				hlist_del_rcu(&fltr->hash);
-				bp->ntp_fltr_count--;
-				spin_unlock_bh(&bp->ntp_fltr_lock);
-				synchronize_rcu();
-				clear_bit(fltr->sw_id, bp->ntp_fltr_bmap);
-				kfree(fltr);
-			}
+			if (del)
+				bnxt_del_ntp_filter(bp, fltr);
 		}
 	}
-	if (test_and_clear_bit(BNXT_HWRM_PF_UNLOAD_SP_EVENT, &bp->sp_event))
-		netdev_info(bp->dev, "Receive PF driver unload event!\n");
-}
-
-#else
-
-static void bnxt_cfg_ntp_filters(struct bnxt *bp)
-{
+#endif
 }
 
-#endif /* CONFIG_RFS_ACCEL */
-
 static int bnxt_udp_tunnel_set_port(struct net_device *netdev, unsigned int table,
 				    unsigned int entry, struct udp_tunnel_info *ti)
 {
@@ -13096,9 +14104,11 @@ static int bnxt_udp_tunnel_set_port(struct net_device *netdev, unsigned int tabl
 	unsigned int cmd;
 
 	if (ti->type == UDP_TUNNEL_TYPE_VXLAN)
-		cmd = TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN;
+		cmd = TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN;
+	else if (ti->type == UDP_TUNNEL_TYPE_GENEVE)
+		cmd = TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE;
 	else
-		cmd = TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE;
+		cmd = TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE;
 
 	return bnxt_hwrm_tunnel_dst_port_alloc(bp, ti->port, cmd);
 }
@@ -13111,8 +14121,10 @@ static int bnxt_udp_tunnel_unset_port(struct net_device *netdev, unsigned int ta
 
 	if (ti->type == UDP_TUNNEL_TYPE_VXLAN)
 		cmd = TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN;
-	else
+	else if (ti->type == UDP_TUNNEL_TYPE_GENEVE)
 		cmd = TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE;
+	else
+		cmd = TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE;
 
 	return bnxt_hwrm_tunnel_dst_port_free(bp, cmd);
 }
@@ -13126,6 +14138,16 @@ static const struct udp_tunnel_nic_info bnxt_udp_tunnels = {
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN,  },
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
 	},
+}, bnxt_udp_tunnels_p7 = {
+	.set_port	= bnxt_udp_tunnel_set_port,
+	.unset_port	= bnxt_udp_tunnel_unset_port,
+	.flags		= UDP_TUNNEL_NIC_INFO_MAY_SLEEP |
+			  UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
+	.tables		= {
+		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN,  },
+		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
+		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN_GPE, },
+	},
 };
 
 static int bnxt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
@@ -13233,6 +14255,8 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 
 	bnxt_ptp_clear(bp);
 	unregister_netdev(dev);
+	bnxt_free_l2_filters(bp, true);
+	bnxt_free_ntp_fltrs(bp, true);
 	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
 	/* Flush any pending tasks */
 	cancel_work_sync(&bp->sp_task);
@@ -13255,8 +14279,6 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	bp->fw_health = NULL;
 	bnxt_cleanup_pci(bp);
 	bnxt_free_ctx_mem(bp);
-	kfree(bp->ctx);
-	bp->ctx = NULL;
 	kfree(bp->rss_indir_tbl);
 	bp->rss_indir_tbl = NULL;
 	bnxt_free_port_stats(bp);
@@ -13325,7 +14347,7 @@ static void _bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx,
 	max_irq = min_t(int, bnxt_get_max_func_irqs(bp) -
 			bnxt_get_ulp_msix_num(bp),
 			hw_resc->max_stat_ctxs - bnxt_get_ulp_stat_ctxs(bp));
-	if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		*max_cp = min_t(int, *max_cp, max_irq);
 	max_ring_grps = hw_resc->max_hw_ring_grps;
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp) && BNXT_PF(bp)) {
@@ -13334,8 +14356,14 @@ static void _bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx,
 	}
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		*max_rx >>= 1;
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
-		bnxt_trim_rings(bp, max_rx, max_tx, *max_cp, false);
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+		int rc;
+
+		rc = __bnxt_trim_rings(bp, max_rx, max_tx, *max_cp, false);
+		if (rc) {
+			*max_rx = 0;
+			*max_tx = 0;
+		}
 		/* On P5 chips, max_cp output param should be available NQs */
 		*max_cp = max_irq;
 	}
@@ -13636,7 +14664,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	max_irqs = bnxt_get_max_irq(pdev);
-	dev = alloc_etherdev_mq(sizeof(*bp), max_irqs);
+	dev = alloc_etherdev_mqs(sizeof(*bp), max_irqs * BNXT_MAX_QUEUE,
+				 max_irqs);
 	if (!dev)
 		return -ENOMEM;
 
@@ -13678,10 +14707,10 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (BNXT_PF(bp))
 		bnxt_vpd_read_info(bp);
 
-	if (BNXT_CHIP_P5(bp)) {
-		bp->flags |= BNXT_FLAG_CHIP_P5;
-		if (BNXT_CHIP_SR2(bp))
-			bp->flags |= BNXT_FLAG_CHIP_SR2;
+	if (BNXT_CHIP_P5_PLUS(bp)) {
+		bp->flags |= BNXT_FLAG_CHIP_P5_PLUS;
+		if (BNXT_CHIP_P7(bp))
+			bp->flags |= BNXT_FLAG_CHIP_P7;
 	}
 
 	rc = bnxt_alloc_rss_indir_tbl(bp);
@@ -13706,6 +14735,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			   NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_GRE_CSUM |
 			   NETIF_F_GSO_PARTIAL | NETIF_F_RXHASH |
 			   NETIF_F_RXCSUM | NETIF_F_GRO;
+	if (bp->flags & BNXT_FLAG_UDP_GSO_CAP)
+		dev->hw_features |= NETIF_F_GSO_UDP_L4;
 
 	if (BNXT_SUPPORTS_TPA(bp))
 		dev->hw_features |= NETIF_F_LRO;
@@ -13716,7 +14747,12 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE |
 			NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_GRE_CSUM |
 			NETIF_F_GSO_IPXIP4 | NETIF_F_GSO_PARTIAL;
-	dev->udp_tunnel_nic_info = &bnxt_udp_tunnels;
+	if (bp->flags & BNXT_FLAG_UDP_GSO_CAP)
+		dev->hw_enc_features |= NETIF_F_GSO_UDP_L4;
+	if (bp->flags & BNXT_FLAG_CHIP_P7)
+		dev->udp_tunnel_nic_info = &bnxt_udp_tunnels_p7;
+	else
+		dev->udp_tunnel_nic_info = &bnxt_udp_tunnels;
 
 	dev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM |
 				    NETIF_F_GSO_GRE_CSUM;
@@ -13744,7 +14780,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		bp->gro_func = bnxt_gro_func_5730x;
 		if (BNXT_CHIP_P4(bp))
 			bp->gro_func = bnxt_gro_func_5731x;
-		else if (BNXT_CHIP_P5(bp))
+		else if (BNXT_CHIP_P5_PLUS(bp))
 			bp->gro_func = bnxt_gro_func_5750x;
 	}
 	if (!BNXT_CHIP_P4_PLUS(bp))
@@ -13770,6 +14806,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto init_err_pci_clean;
 
+	bnxt_init_l2_fltr_tbl(bp);
 	bnxt_set_rx_skb_mode(bp, false);
 	bnxt_set_tpa_flags(bp);
 	bnxt_set_ring_params(bp);
@@ -13852,8 +14889,6 @@ init_err_pci_clean:
 	bp->fw_health = NULL;
 	bnxt_cleanup_pci(bp);
 	bnxt_free_ctx_mem(bp);
-	kfree(bp->ctx);
-	bp->ctx = NULL;
 	kfree(bp->rss_indir_tbl);
 	bp->rss_indir_tbl = NULL;
 
@@ -13906,8 +14941,6 @@ static int bnxt_suspend(struct device *device)
 	bnxt_hwrm_func_drv_unrgtr(bp);
 	pci_disable_device(bp->pdev);
 	bnxt_free_ctx_mem(bp);
-	kfree(bp->ctx);
-	bp->ctx = NULL;
 	rtnl_unlock();
 	return rc;
 }
@@ -13940,6 +14973,8 @@ static int bnxt_resume(struct device *device)
 	if (rc)
 		goto resume_exit;
 
+	bnxt_clear_reservations(bp, true);
+
 	if (bnxt_hwrm_func_drv_rgtr(bp, NULL, 0, false)) {
 		rc = -ENODEV;
 		goto resume_exit;
@@ -14004,8 +15039,6 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
 	if (pci_is_enabled(pdev))
 		pci_disable_device(pdev);
 	bnxt_free_ctx_mem(bp);
-	kfree(bp->ctx);
-	bp->ctx = NULL;
 	rtnl_unlock();
 
 	/* Request a slot slot reset. */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index e702dbc3e6b1..b8ef1717cb65 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -18,7 +18,7 @@
  */
 #define DRV_VER_MAJ	1
 #define DRV_VER_MIN	10
-#define DRV_VER_UPD	2
+#define DRV_VER_UPD	3
 
 #include <linux/ethtool.h>
 #include <linux/interrupt.h>
@@ -61,6 +61,24 @@ struct tx_bd {
 	__le64 tx_bd_haddr;
 } __packed;
 
+#define TX_OPAQUE_IDX_MASK	0x0000ffff
+#define TX_OPAQUE_BDS_MASK	0x00ff0000
+#define TX_OPAQUE_BDS_SHIFT	16
+#define TX_OPAQUE_RING_MASK	0xff000000
+#define TX_OPAQUE_RING_SHIFT	24
+
+#define SET_TX_OPAQUE(bp, txr, idx, bds)				\
+	(((txr)->tx_napi_idx << TX_OPAQUE_RING_SHIFT) |			\
+	 ((bds) << TX_OPAQUE_BDS_SHIFT) | ((idx) & (bp)->tx_ring_mask))
+
+#define TX_OPAQUE_IDX(opq)	((opq) & TX_OPAQUE_IDX_MASK)
+#define TX_OPAQUE_RING(opq)	(((opq) & TX_OPAQUE_RING_MASK) >>	\
+				 TX_OPAQUE_RING_SHIFT)
+#define TX_OPAQUE_BDS(opq)	(((opq) & TX_OPAQUE_BDS_MASK) >>	\
+				 TX_OPAQUE_BDS_SHIFT)
+#define TX_OPAQUE_PROD(bp, opq)	((TX_OPAQUE_IDX(opq) + TX_OPAQUE_BDS(opq)) &\
+				 (bp)->tx_ring_mask)
+
 struct tx_bd_ext {
 	__le32 tx_bd_hsize_lflags;
 	#define TX_BD_FLAGS_TCP_UDP_CHKSUM			(1 << 0)
@@ -121,11 +139,15 @@ struct tx_cmp {
 	__le32 tx_cmp_flags_type;
 	#define CMP_TYPE					(0x3f << 0)
 	 #define CMP_TYPE_TX_L2_CMP				 0
+	 #define CMP_TYPE_TX_L2_COAL_CMP			 2
+	 #define CMP_TYPE_TX_L2_PKT_TS_CMP			 4
 	 #define CMP_TYPE_RX_L2_CMP				 17
 	 #define CMP_TYPE_RX_AGG_CMP				 18
 	 #define CMP_TYPE_RX_L2_TPA_START_CMP			 19
 	 #define CMP_TYPE_RX_L2_TPA_END_CMP			 21
 	 #define CMP_TYPE_RX_TPA_AGG_CMP			 22
+	 #define CMP_TYPE_RX_L2_V3_CMP				 23
+	 #define CMP_TYPE_RX_L2_TPA_START_V3_CMP		 25
 	 #define CMP_TYPE_STATUS_CMP				 32
 	 #define CMP_TYPE_REMOTE_DRIVER_REQ			 34
 	 #define CMP_TYPE_REMOTE_DRIVER_RESP			 36
@@ -152,16 +174,20 @@ struct tx_cmp {
 	 #define TX_CMP_ERRORS_DMA_ERROR			 (1 << 6)
 	 #define TX_CMP_ERRORS_HINT_TOO_SHORT			 (1 << 7)
 
-	__le32 tx_cmp_unsed_3;
+	__le32 sq_cons_idx;
+	#define TX_CMP_SQ_CONS_IDX_MASK				0x00ffffff
 };
 
+#define TX_CMP_SQ_CONS_IDX(txcmp)					\
+	(le32_to_cpu((txcmp)->sq_cons_idx) & TX_CMP_SQ_CONS_IDX_MASK)
+
 struct rx_cmp {
 	__le32 rx_cmp_len_flags_type;
 	#define RX_CMP_CMP_TYPE					(0x3f << 0)
 	#define RX_CMP_FLAGS_ERROR				(1 << 6)
 	#define RX_CMP_FLAGS_PLACEMENT				(7 << 7)
 	#define RX_CMP_FLAGS_RSS_VALID				(1 << 10)
-	#define RX_CMP_FLAGS_UNUSED				(1 << 11)
+	#define RX_CMP_FLAGS_PKT_METADATA_PRESENT		(1 << 11)
 	 #define RX_CMP_FLAGS_ITYPES_SHIFT			 12
 	 #define RX_CMP_FLAGS_ITYPES_MASK			 0xf000
 	 #define RX_CMP_FLAGS_ITYPE_UNKNOWN			 (0 << 12)
@@ -182,12 +208,30 @@ struct rx_cmp {
 	 #define RX_CMP_AGG_BUFS_SHIFT				 1
 	#define RX_CMP_RSS_HASH_TYPE				(0x7f << 9)
 	 #define RX_CMP_RSS_HASH_TYPE_SHIFT			 9
+	#define RX_CMP_V3_RSS_EXT_OP_LEGACY			(0xf << 12)
+	 #define RX_CMP_V3_RSS_EXT_OP_LEGACY_SHIFT		 12
+	#define RX_CMP_V3_RSS_EXT_OP_NEW			(0xf << 8)
+	 #define RX_CMP_V3_RSS_EXT_OP_NEW_SHIFT			 8
 	#define RX_CMP_PAYLOAD_OFFSET				(0xff << 16)
 	 #define RX_CMP_PAYLOAD_OFFSET_SHIFT			 16
+	#define RX_CMP_SUB_NS_TS				(0xf << 16)
+	 #define RX_CMP_SUB_NS_TS_SHIFT				 16
+	#define RX_CMP_METADATA1				(0xf << 28)
+	 #define RX_CMP_METADATA1_SHIFT				 28
+	#define RX_CMP_METADATA1_TPID_SEL			(0x7 << 28)
+	#define RX_CMP_METADATA1_TPID_8021Q			(0x1 << 28)
+	#define RX_CMP_METADATA1_TPID_8021AD			(0x0 << 28)
+	#define RX_CMP_METADATA1_VALID				(0x8 << 28)
 
 	__le32 rx_cmp_rss_hash;
 };
 
+#define BNXT_PTP_RX_TS_VALID(flags)				\
+	(((flags) & RX_CMP_FLAGS_ITYPES_MASK) == RX_CMP_FLAGS_ITYPE_PTP_W_TS)
+
+#define BNXT_ALL_RX_TS_VALID(flags)				\
+	!((flags) & RX_CMP_FLAGS_PKT_METADATA_PRESENT)
+
 #define RX_CMP_HASH_VALID(rxcmp)				\
 	((rxcmp)->rx_cmp_len_flags_type & cpu_to_le32(RX_CMP_FLAGS_RSS_VALID))
 
@@ -197,6 +241,30 @@ struct rx_cmp {
 	(((le32_to_cpu((rxcmp)->rx_cmp_misc_v1) & RX_CMP_RSS_HASH_TYPE) >>\
 	  RX_CMP_RSS_HASH_TYPE_SHIFT) & RSS_PROFILE_ID_MASK)
 
+#define RX_CMP_V3_HASH_TYPE_LEGACY(rxcmp)				\
+	((le32_to_cpu((rxcmp)->rx_cmp_misc_v1) & RX_CMP_V3_RSS_EXT_OP_LEGACY) >>\
+	 RX_CMP_V3_RSS_EXT_OP_LEGACY_SHIFT)
+
+#define RX_CMP_V3_HASH_TYPE_NEW(rxcmp)				\
+	((le32_to_cpu((rxcmp)->rx_cmp_misc_v1) & RX_CMP_V3_RSS_EXT_OP_NEW) >>\
+	 RX_CMP_V3_RSS_EXT_OP_NEW_SHIFT)
+
+#define RX_CMP_V3_HASH_TYPE(bp, rxcmp)				\
+	(((bp)->rss_cap & BNXT_RSS_CAP_RSS_TCAM) ?		\
+	  RX_CMP_V3_HASH_TYPE_NEW(rxcmp) :			\
+	  RX_CMP_V3_HASH_TYPE_LEGACY(rxcmp))
+
+#define EXT_OP_INNER_4		0x0
+#define EXT_OP_OUTER_4		0x2
+#define EXT_OP_INNFL_3		0x8
+#define EXT_OP_OUTFL_3		0xa
+
+#define RX_CMP_VLAN_VALID(rxcmp)				\
+	((rxcmp)->rx_cmp_misc_v1 & cpu_to_le32(RX_CMP_METADATA1_VALID))
+
+#define RX_CMP_VLAN_TPID_SEL(rxcmp)				\
+	(le32_to_cpu((rxcmp)->rx_cmp_misc_v1) & RX_CMP_METADATA1_TPID_SEL)
+
 struct rx_cmp_ext {
 	__le32 rx_cmp_flags2;
 	#define RX_CMP_FLAGS2_IP_CS_CALC			0x1
@@ -244,6 +312,9 @@ struct rx_cmp_ext {
 
 	#define RX_CMPL_CFA_CODE_MASK				(0xffff << 16)
 	 #define RX_CMPL_CFA_CODE_SFT				 16
+	#define RX_CMPL_METADATA0_TCI_MASK			(0xffff << 16)
+	#define RX_CMPL_METADATA0_VID_MASK			(0x0fff << 16)
+	 #define RX_CMPL_METADATA0_SFT				 16
 
 	__le32 rx_cmp_timestamp;
 };
@@ -269,6 +340,10 @@ struct rx_cmp_ext {
 	((le32_to_cpu((rxcmpl1)->rx_cmp_cfa_code_errors_v2) &		\
 	  RX_CMPL_CFA_CODE_MASK) >> RX_CMPL_CFA_CODE_SFT)
 
+#define RX_CMP_METADATA0_TCI(rxcmp1)					\
+	((le32_to_cpu((rxcmp1)->rx_cmp_cfa_code_errors_v2) &		\
+	  RX_CMPL_METADATA0_TCI_MASK) >> RX_CMPL_METADATA0_SFT)
+
 struct rx_agg_cmp {
 	__le32 rx_agg_cmp_len_flags_type;
 	#define RX_AGG_CMP_TYPE					(0x3f << 0)
@@ -311,10 +386,18 @@ struct rx_tpa_start_cmp {
 	#define RX_TPA_START_CMP_V1				(0x1 << 0)
 	#define RX_TPA_START_CMP_RSS_HASH_TYPE			(0x7f << 9)
 	 #define RX_TPA_START_CMP_RSS_HASH_TYPE_SHIFT		 9
+	#define RX_TPA_START_CMP_V3_RSS_HASH_TYPE		(0x1ff << 7)
+	 #define RX_TPA_START_CMP_V3_RSS_HASH_TYPE_SHIFT	 7
 	#define RX_TPA_START_CMP_AGG_ID				(0x7f << 25)
 	 #define RX_TPA_START_CMP_AGG_ID_SHIFT			 25
 	#define RX_TPA_START_CMP_AGG_ID_P5			(0xffff << 16)
 	 #define RX_TPA_START_CMP_AGG_ID_SHIFT_P5		 16
+	#define RX_TPA_START_CMP_METADATA1			(0xf << 28)
+	 #define RX_TPA_START_CMP_METADATA1_SHIFT		 28
+	#define RX_TPA_START_METADATA1_TPID_SEL			(0x7 << 28)
+	#define RX_TPA_START_METADATA1_TPID_8021Q		(0x1 << 28)
+	#define RX_TPA_START_METADATA1_TPID_8021AD		(0x0 << 28)
+	#define RX_TPA_START_METADATA1_VALID			(0x8 << 28)
 
 	__le32 rx_tpa_start_cmp_rss_hash;
 };
@@ -328,6 +411,11 @@ struct rx_tpa_start_cmp {
 	   RX_TPA_START_CMP_RSS_HASH_TYPE) >>				\
 	  RX_TPA_START_CMP_RSS_HASH_TYPE_SHIFT) & RSS_PROFILE_ID_MASK)
 
+#define TPA_START_V3_HASH_TYPE(rx_tpa_start)				\
+	(((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_misc_v1) &	\
+	   RX_TPA_START_CMP_V3_RSS_HASH_TYPE) >>			\
+	  RX_TPA_START_CMP_V3_RSS_HASH_TYPE_SHIFT) & RSS_PROFILE_ID_MASK)
+
 #define TPA_START_AGG_ID(rx_tpa_start)					\
 	((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_misc_v1) &	\
 	 RX_TPA_START_CMP_AGG_ID) >> RX_TPA_START_CMP_AGG_ID_SHIFT)
@@ -340,6 +428,14 @@ struct rx_tpa_start_cmp {
 	((rx_tpa_start)->rx_tpa_start_cmp_len_flags_type &		\
 	 cpu_to_le32(RX_TPA_START_CMP_FLAGS_ERROR))
 
+#define TPA_START_VLAN_VALID(rx_tpa_start)				\
+	((rx_tpa_start)->rx_tpa_start_cmp_misc_v1 &			\
+	 cpu_to_le32(RX_TPA_START_METADATA1_VALID))
+
+#define TPA_START_VLAN_TPID_SEL(rx_tpa_start)				\
+	(le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_misc_v1) &	\
+	 RX_TPA_START_METADATA1_TPID_SEL)
+
 struct rx_tpa_start_cmp_ext {
 	__le32 rx_tpa_start_cmp_flags2;
 	#define RX_TPA_START_CMP_FLAGS2_IP_CS_CALC		(0x1 << 0)
@@ -350,6 +446,8 @@ struct rx_tpa_start_cmp_ext {
 	#define RX_TPA_START_CMP_FLAGS2_CSUM_CMPL_VALID		(0x1 << 9)
 	#define RX_TPA_START_CMP_FLAGS2_EXT_META_FORMAT		(0x3 << 10)
 	 #define RX_TPA_START_CMP_FLAGS2_EXT_META_FORMAT_SHIFT	 10
+	#define RX_TPA_START_CMP_V3_FLAGS2_T_IP_TYPE		(0x1 << 10)
+	#define RX_TPA_START_CMP_V3_FLAGS2_AGG_GRO		(0x1 << 11)
 	#define RX_TPA_START_CMP_FLAGS2_CSUM_CMPL		(0xffff << 16)
 	 #define RX_TPA_START_CMP_FLAGS2_CSUM_CMPL_SHIFT	 16
 
@@ -363,6 +461,9 @@ struct rx_tpa_start_cmp_ext {
 	 #define RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_FLUSH	 (0x5 << 1)
 	#define RX_TPA_START_CMP_CFA_CODE			(0xffff << 16)
 	 #define RX_TPA_START_CMPL_CFA_CODE_SHIFT		 16
+	#define RX_TPA_START_CMP_METADATA0_TCI_MASK		(0xffff << 16)
+	#define RX_TPA_START_CMP_METADATA0_VID_MASK		(0x0fff << 16)
+	 #define RX_TPA_START_CMP_METADATA0_SFT			 16
 	__le32 rx_tpa_start_cmp_hdr_info;
 };
 
@@ -379,6 +480,11 @@ struct rx_tpa_start_cmp_ext {
 	  RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_MASK) >>			\
 	 RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_SHIFT)
 
+#define TPA_START_METADATA0_TCI(rx_tpa_start)				\
+	((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_cfa_code_v2) &	\
+	  RX_TPA_START_CMP_METADATA0_TCI_MASK) >>			\
+	 RX_TPA_START_CMP_METADATA0_SFT)
+
 struct rx_tpa_end_cmp {
 	__le32 rx_tpa_end_cmp_len_flags_type;
 	#define RX_TPA_END_CMP_TYPE				(0x3f << 0)
@@ -523,6 +629,8 @@ struct nqe_cn {
 	#define NQ_CN_TYPE_SFT            0
 	#define NQ_CN_TYPE_CQ_NOTIFICATION  0x30UL
 	#define NQ_CN_TYPE_LAST            NQ_CN_TYPE_CQ_NOTIFICATION
+	#define NQ_CN_TOGGLE_MASK         0xc0UL
+	#define NQ_CN_TOGGLE_SFT          6
 	__le16	reserved16;
 	__le32	cq_handle_low;
 	__le32	v;
@@ -530,6 +638,23 @@ struct nqe_cn {
 	__le32	cq_handle_high;
 };
 
+#define BNXT_NQ_HDL_IDX_MASK	0x00ffffff
+#define BNXT_NQ_HDL_TYPE_MASK	0xff000000
+#define BNXT_NQ_HDL_TYPE_SHIFT	24
+#define BNXT_NQ_HDL_TYPE_RX	0x00
+#define BNXT_NQ_HDL_TYPE_TX	0x01
+
+#define BNXT_NQ_HDL_IDX(hdl)	((hdl) & BNXT_NQ_HDL_IDX_MASK)
+#define BNXT_NQ_HDL_TYPE(hdl)	(((hdl) & BNXT_NQ_HDL_TYPE_MASK) >>	\
+				 BNXT_NQ_HDL_TYPE_SHIFT)
+
+#define BNXT_SET_NQ_HDL(cpr)						\
+	(((cpr)->cp_ring_type << BNXT_NQ_HDL_TYPE_SHIFT) | (cpr)->cp_idx)
+
+#define NQE_CN_TYPE(type)	((type) & NQ_CN_TYPE_MASK)
+#define NQE_CN_TOGGLE(type)	(((type) & NQ_CN_TOGGLE_MASK) >>	\
+				 NQ_CN_TOGGLE_SFT)
+
 #define DB_IDX_MASK						0xffffff
 #define DB_IDX_VALID						(0x1 << 26)
 #define DB_IRQ_DIS						(0x1 << 27)
@@ -545,9 +670,14 @@ struct nqe_cn {
 
 /* 64-bit doorbell */
 #define DBR_INDEX_MASK					0x0000000000ffffffULL
+#define DBR_EPOCH_MASK					0x01000000UL
+#define DBR_EPOCH_SFT					24
+#define DBR_TOGGLE_MASK					0x06000000UL
+#define DBR_TOGGLE_SFT					25
 #define DBR_XID_MASK					0x000fffff00000000ULL
 #define DBR_XID_SFT					32
 #define DBR_PATH_L2					(0x1ULL << 56)
+#define DBR_VALID					(0x1ULL << 58)
 #define DBR_TYPE_SQ					(0x0ULL << 60)
 #define DBR_TYPE_RQ					(0x1ULL << 60)
 #define DBR_TYPE_SRQ					(0x2ULL << 60)
@@ -560,6 +690,7 @@ struct nqe_cn {
 #define DBR_TYPE_CQ_CUTOFF_ACK				(0x9ULL << 60)
 #define DBR_TYPE_NQ					(0xaULL << 60)
 #define DBR_TYPE_NQ_ARM					(0xbULL << 60)
+#define DBR_TYPE_NQ_MASK				(0xeULL << 60)
 #define DBR_TYPE_NULL					(0xfULL << 60)
 
 #define DB_PF_OFFSET_P5					0x10000
@@ -655,10 +786,12 @@ struct nqe_cn {
  */
 #define BNXT_MIN_TX_DESC_CNT		(MAX_SKB_FRAGS + 2)
 
-#define RX_RING(x)	(((x) & ~(RX_DESC_CNT - 1)) >> (BNXT_PAGE_SHIFT - 4))
+#define RX_RING(bp, x)	(((x) & (bp)->rx_ring_mask) >> (BNXT_PAGE_SHIFT - 4))
+#define RX_AGG_RING(bp, x)	(((x) & (bp)->rx_agg_ring_mask) >>	\
+				 (BNXT_PAGE_SHIFT - 4))
 #define RX_IDX(x)	((x) & (RX_DESC_CNT - 1))
 
-#define TX_RING(x)	(((x) & ~(TX_DESC_CNT - 1)) >> (BNXT_PAGE_SHIFT - 4))
+#define TX_RING(bp, x)	(((x) & (bp)->tx_ring_mask) >> (BNXT_PAGE_SHIFT - 4))
 #define TX_IDX(x)	((x) & (TX_DESC_CNT - 1))
 
 #define CP_RING(x)	(((x) & ~(CP_DESC_CNT - 1)) >> (BNXT_PAGE_SHIFT - 4))
@@ -685,11 +818,14 @@ struct nqe_cn {
 #define RX_CMP_TYPE(rxcmp)					\
 	(le32_to_cpu((rxcmp)->rx_cmp_len_flags_type) & RX_CMP_CMP_TYPE)
 
-#define NEXT_RX(idx)		(((idx) + 1) & bp->rx_ring_mask)
+#define RING_RX(bp, idx)	((idx) & (bp)->rx_ring_mask)
+#define NEXT_RX(idx)		((idx) + 1)
 
-#define NEXT_RX_AGG(idx)	(((idx) + 1) & bp->rx_agg_ring_mask)
+#define RING_RX_AGG(bp, idx)	((idx) & (bp)->rx_agg_ring_mask)
+#define NEXT_RX_AGG(idx)	((idx) + 1)
 
-#define NEXT_TX(idx)		(((idx) + 1) & bp->tx_ring_mask)
+#define RING_TX(bp, idx)	((idx) & (bp)->tx_ring_mask)
+#define NEXT_TX(idx)		((idx) + 1)
 
 #define ADV_RAW_CMP(idx, n)	((idx) + (n))
 #define NEXT_RAW_CMP(idx)	ADV_RAW_CMP(idx, 1)
@@ -702,6 +838,7 @@ struct nqe_cn {
 #define BNXT_AGG_EVENT		2
 #define BNXT_TX_EVENT		4
 #define BNXT_REDIRECT_EVENT	8
+#define BNXT_TX_CMP_EVENT	0x10
 
 struct bnxt_sw_tx_bd {
 	union {
@@ -730,13 +867,6 @@ struct bnxt_sw_rx_agg_bd {
 	dma_addr_t		mapping;
 };
 
-struct bnxt_mem_init {
-	u8	init_val;
-	u16	offset;
-#define	BNXT_MEM_INVALID_OFFSET	0xffff
-	u16	size;
-};
-
 struct bnxt_ring_mem_info {
 	int			nr_pages;
 	int			page_size;
@@ -746,7 +876,7 @@ struct bnxt_ring_mem_info {
 #define BNXT_RMEM_USE_FULL_PAGE_FLAG	4
 
 	u16			depth;
-	struct bnxt_mem_init	*mem_init;
+	struct bnxt_ctx_mem_type	*ctx_mem;
 
 	void			**pg_arr;
 	dma_addr_t		*dma_arr;
@@ -788,13 +918,27 @@ struct bnxt_db_info {
 		u64		db_key64;
 		u32		db_key32;
 	};
+	u32			db_ring_mask;
+	u32			db_epoch_mask;
+	u8			db_epoch_shift;
 };
 
+#define DB_EPOCH(db, idx)	(((idx) & (db)->db_epoch_mask) <<	\
+				 ((db)->db_epoch_shift))
+
+#define DB_TOGGLE(tgl)		((tgl) << DBR_TOGGLE_SFT)
+
+#define DB_RING_IDX(db, idx)	(((idx) & (db)->db_ring_mask) |		\
+				 DB_EPOCH(db, idx))
+
 struct bnxt_tx_ring_info {
 	struct bnxt_napi	*bnapi;
+	struct bnxt_cp_ring_info	*tx_cpr;
 	u16			tx_prod;
 	u16			tx_cons;
+	u16			tx_hw_cons;
 	u16			txq_index;
+	u8			tx_napi_idx;
 	u8			kick_pending;
 	struct bnxt_db_info	tx_db;
 
@@ -889,6 +1033,8 @@ struct bnxt_tpa_info {
 
 	u16			cfa_code; /* cfa_code in TPA start compl */
 	u8			agg_count;
+	u8			vlan_valid:1;
+	u8			cfa_code_valid:1;
 	struct rx_agg_cmp	*agg_arr;
 };
 
@@ -901,6 +1047,7 @@ struct bnxt_tpa_idx_map {
 
 struct bnxt_rx_ring_info {
 	struct bnxt_napi	*bnapi;
+	struct bnxt_cp_ring_info	*rx_cpr;
 	u16			rx_prod;
 	u16			rx_agg_prod;
 	u16			rx_sw_agg_prod;
@@ -980,6 +1127,11 @@ struct bnxt_cp_ring_info {
 
 	u8			had_work_done:1;
 	u8			has_more_work:1;
+	u8			had_nqe_notify:1;
+	u8			toggle;
+
+	u8			cp_ring_type;
+	u8			cp_idx;
 
 	u32			last_cp_raw_cons;
 
@@ -1004,11 +1156,18 @@ struct bnxt_cp_ring_info {
 
 	struct bnxt_ring_struct	cp_ring_struct;
 
-	struct bnxt_cp_ring_info *cp_ring_arr[2];
-#define BNXT_RX_HDL	0
-#define BNXT_TX_HDL	1
+	int			cp_ring_count;
+	struct bnxt_cp_ring_info *cp_ring_arr;
 };
 
+#define BNXT_MAX_QUEUE		8
+#define BNXT_MAX_TXR_PER_NAPI	BNXT_MAX_QUEUE
+
+#define bnxt_for_each_napi_tx(iter, bnapi, txr)		\
+	for (iter = 0, txr = (bnapi)->tx_ring[0]; txr;	\
+	     txr = (iter < BNXT_MAX_TXR_PER_NAPI - 1) ?	\
+	     (bnapi)->tx_ring[++iter] : NULL)
+
 struct bnxt_napi {
 	struct napi_struct	napi;
 	struct bnxt		*bp;
@@ -1016,11 +1175,10 @@ struct bnxt_napi {
 	int			index;
 	struct bnxt_cp_ring_info	cp_ring;
 	struct bnxt_rx_ring_info	*rx_ring;
-	struct bnxt_tx_ring_info	*tx_ring;
+	struct bnxt_tx_ring_info	*tx_ring[BNXT_MAX_TXR_PER_NAPI];
 
 	void			(*tx_int)(struct bnxt *, struct bnxt_napi *,
 					  int budget);
-	int			tx_pkts;
 	u8			events;
 	u8			tx_fault:1;
 
@@ -1061,7 +1219,7 @@ struct bnxt_vnic_info {
 	u16		fw_rss_cos_lb_ctx[BNXT_MAX_CTX_PER_VNIC];
 	u16		fw_l2_ctx_id;
 #define BNXT_MAX_UC_ADDRS	4
-	__le64		fw_l2_filter_id[BNXT_MAX_UC_ADDRS];
+	struct bnxt_l2_filter *l2_filters[BNXT_MAX_UC_ADDRS];
 				/* index 0 always dev_addr */
 	u16		uc_filter_count;
 	u8		*uc_list;
@@ -1174,19 +1332,71 @@ struct bnxt_pf_info {
 	struct bnxt_vf_info	*vf;
 };
 
-struct bnxt_ntuple_filter {
+struct bnxt_filter_base {
 	struct hlist_node	hash;
-	u8			dst_mac_addr[ETH_ALEN];
-	u8			src_mac_addr[ETH_ALEN];
-	struct flow_keys	fkeys;
 	__le64			filter_id;
+	u8			type;
+#define BNXT_FLTR_TYPE_NTUPLE	1
+#define BNXT_FLTR_TYPE_L2	2
+	u8			flags;
+#define BNXT_ACT_DROP		1
+#define BNXT_ACT_RING_DST	2
+#define BNXT_ACT_FUNC_DST	4
+#define BNXT_ACT_NO_AGING	8
 	u16			sw_id;
-	u8			l2_fltr_idx;
 	u16			rxq;
-	u32			flow_id;
+	u16			fw_vnic_id;
+	u16			vf_idx;
 	unsigned long		state;
 #define BNXT_FLTR_VALID		0
-#define BNXT_FLTR_UPDATE	1
+#define BNXT_FLTR_INSERTED	1
+#define BNXT_FLTR_FW_DELETED	2
+
+	struct rcu_head         rcu;
+};
+
+struct bnxt_ntuple_filter {
+	struct bnxt_filter_base	base;
+	struct flow_keys	fkeys;
+	struct bnxt_l2_filter	*l2_fltr;
+	u32			ntuple_flags;
+#define BNXT_NTUPLE_MATCH_SRC_IP	1
+#define BNXT_NTUPLE_MATCH_DST_IP	2
+#define BNXT_NTUPLE_MATCH_SRC_PORT	4
+#define BNXT_NTUPLE_MATCH_DST_PORT	8
+#define BNXT_NTUPLE_MATCH_ALL		(BNXT_NTUPLE_MATCH_SRC_IP |	\
+					 BNXT_NTUPLE_MATCH_DST_IP |	\
+					 BNXT_NTUPLE_MATCH_SRC_PORT |	\
+					 BNXT_NTUPLE_MATCH_DST_PORT)
+	u32			flow_id;
+};
+
+struct bnxt_l2_key {
+	union {
+		struct {
+			u8	dst_mac_addr[ETH_ALEN];
+			u16	vlan;
+		};
+		u32	filter_key;
+	};
+};
+
+struct bnxt_ipv4_tuple {
+	struct flow_dissector_key_ipv4_addrs v4addrs;
+	struct flow_dissector_key_ports ports;
+};
+
+struct bnxt_ipv6_tuple {
+	struct flow_dissector_key_ipv6_addrs v6addrs;
+	struct flow_dissector_key_ports ports;
+};
+
+#define BNXT_L2_KEY_SIZE	(sizeof(struct bnxt_l2_key) / 4)
+
+struct bnxt_l2_filter {
+	struct bnxt_filter_base	base;
+	struct bnxt_l2_key	l2_key;
+	atomic_t		refcnt;
 };
 
 struct bnxt_link_info {
@@ -1208,6 +1418,7 @@ struct bnxt_link_info {
 #define BNXT_LINK_STATE_DOWN	1
 #define BNXT_LINK_STATE_UP	2
 #define BNXT_LINK_IS_UP(bp)	((bp)->link_info.link_state == BNXT_LINK_STATE_UP)
+	u8			active_lanes;
 	u8			duplex;
 #define BNXT_LINK_DUPLEX_HALF	PORT_PHY_QCFG_RESP_DUPLEX_STATE_HALF
 #define BNXT_LINK_DUPLEX_FULL	PORT_PHY_QCFG_RESP_DUPLEX_STATE_FULL
@@ -1242,8 +1453,11 @@ struct bnxt_link_info {
 #define BNXT_LINK_SPEED_50GB	PORT_PHY_QCFG_RESP_LINK_SPEED_50GB
 #define BNXT_LINK_SPEED_100GB	PORT_PHY_QCFG_RESP_LINK_SPEED_100GB
 #define BNXT_LINK_SPEED_200GB	PORT_PHY_QCFG_RESP_LINK_SPEED_200GB
+#define BNXT_LINK_SPEED_400GB	PORT_PHY_QCFG_RESP_LINK_SPEED_400GB
 	u16			support_speeds;
 	u16			support_pam4_speeds;
+	u16			support_speeds2;
+
 	u16			auto_link_speeds;	/* fw adv setting */
 #define BNXT_LINK_SPEED_MSK_100MB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_100MB
 #define BNXT_LINK_SPEED_MSK_1GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_1GB
@@ -1259,12 +1473,52 @@ struct bnxt_link_info {
 #define BNXT_LINK_PAM4_SPEED_MSK_50GB PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_50G
 #define BNXT_LINK_PAM4_SPEED_MSK_100GB PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_100G
 #define BNXT_LINK_PAM4_SPEED_MSK_200GB PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_200G
+	u16			auto_link_speeds2;
+#define BNXT_LINK_SPEEDS2_MSK_1GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_1GB
+#define BNXT_LINK_SPEEDS2_MSK_10GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_10GB
+#define BNXT_LINK_SPEEDS2_MSK_25GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_25GB
+#define BNXT_LINK_SPEEDS2_MSK_40GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_40GB
+#define BNXT_LINK_SPEEDS2_MSK_50GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_50GB
+#define BNXT_LINK_SPEEDS2_MSK_100GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB
+#define BNXT_LINK_SPEEDS2_MSK_50GB_PAM4	\
+	PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_50GB_PAM4_56
+#define BNXT_LINK_SPEEDS2_MSK_100GB_PAM4	\
+	PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB_PAM4_56
+#define BNXT_LINK_SPEEDS2_MSK_200GB_PAM4	\
+	PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_200GB_PAM4_56
+#define BNXT_LINK_SPEEDS2_MSK_400GB_PAM4	\
+	PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_400GB_PAM4_56
+#define BNXT_LINK_SPEEDS2_MSK_100GB_PAM4_112	\
+	PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB_PAM4_112
+#define BNXT_LINK_SPEEDS2_MSK_200GB_PAM4_112	\
+	PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_200GB_PAM4_112
+#define BNXT_LINK_SPEEDS2_MSK_400GB_PAM4_112	\
+	PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_400GB_PAM4_112
+
 	u16			support_auto_speeds;
 	u16			support_pam4_auto_speeds;
+	u16			support_auto_speeds2;
+
 	u16			lp_auto_link_speeds;
 	u16			lp_auto_pam4_link_speeds;
 	u16			force_link_speed;
 	u16			force_pam4_link_speed;
+	u16			force_link_speed2;
+#define BNXT_LINK_SPEED_50GB_PAM4	\
+	PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_50GB_PAM4_56
+#define BNXT_LINK_SPEED_100GB_PAM4	\
+	PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB_PAM4_56
+#define BNXT_LINK_SPEED_200GB_PAM4	\
+	PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_200GB_PAM4_56
+#define BNXT_LINK_SPEED_400GB_PAM4	\
+	PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_56
+#define BNXT_LINK_SPEED_100GB_PAM4_112	\
+	PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB_PAM4_112
+#define BNXT_LINK_SPEED_200GB_PAM4_112	\
+	PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_200GB_PAM4_112
+#define BNXT_LINK_SPEED_400GB_PAM4_112	\
+	PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_112
+
 	u32			preemphasis;
 	u8			module_status;
 	u8			active_fec_sig_mode;
@@ -1295,6 +1549,7 @@ struct bnxt_link_info {
 	u8			req_signal_mode;
 #define BNXT_SIG_MODE_NRZ	PORT_PHY_QCFG_RESP_SIGNAL_MODE_NRZ
 #define BNXT_SIG_MODE_PAM4	PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4
+#define BNXT_SIG_MODE_PAM4_112	PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4_112
 #define BNXT_SIG_MODE_MAX	(PORT_PHY_QCFG_RESP_SIGNAL_MODE_LAST + 1)
 	u8			req_duplex;
 	u8			req_flow_ctrl;
@@ -1355,8 +1610,6 @@ struct bnxt_link_info {
 	(PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_DISABLE |		\
 	 BNXT_FEC_RS_OFF(link_info))
 
-#define BNXT_MAX_QUEUE	8
-
 struct bnxt_queue_info {
 	u8	queue_id;
 	u8	queue_profile;
@@ -1385,7 +1638,7 @@ struct bnxt_test_info {
 };
 
 #define CHIMP_REG_VIEW_ADDR				\
-	((bp->flags & BNXT_FLAG_CHIP_P5) ? 0x80000000 : 0xb1000000)
+	((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) ? 0x80000000 : 0xb1000000)
 
 #define BNXT_GRCPF_REG_CHIMP_COMM		0x0
 #define BNXT_GRCPF_REG_CHIMP_COMM_TRIGGER	0x100
@@ -1509,53 +1762,73 @@ do {									\
 		attr = FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_4K;	\
 } while (0)
 
+struct bnxt_ctx_mem_type {
+	u16	type;
+	u16	entry_size;
+	u32	flags;
+#define BNXT_CTX_MEM_TYPE_VALID FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_TYPE_VALID
+	u32	instance_bmap;
+	u8	init_value;
+	u8	entry_multiple;
+	u16	init_offset;
+#define	BNXT_CTX_INIT_INVALID_OFFSET	0xffff
+	u32	max_entries;
+	u32	min_entries;
+	u8	last:1;
+	u8	split_entry_cnt;
+#define BNXT_MAX_SPLIT_ENTRY	4
+	union {
+		struct {
+			u32	qp_l2_entries;
+			u32	qp_qp1_entries;
+			u32	qp_fast_qpmd_entries;
+		};
+		u32	srq_l2_entries;
+		u32	cq_l2_entries;
+		u32	vnic_entries;
+		struct {
+			u32	mrav_av_entries;
+			u32	mrav_num_entries_units;
+		};
+		u32	split[BNXT_MAX_SPLIT_ENTRY];
+	};
+	struct bnxt_ctx_pg_info	*pg_info;
+};
+
+#define BNXT_CTX_MRAV_AV_SPLIT_ENTRY	0
+
+#define BNXT_CTX_QP	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QP
+#define BNXT_CTX_SRQ	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ
+#define BNXT_CTX_CQ	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ
+#define BNXT_CTX_VNIC	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_VNIC
+#define BNXT_CTX_STAT	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_STAT
+#define BNXT_CTX_STQM	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SP_TQM_RING
+#define BNXT_CTX_FTQM	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING
+#define BNXT_CTX_MRAV	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV
+#define BNXT_CTX_TIM	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM
+#define BNXT_CTX_TKC	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TKC
+#define BNXT_CTX_RKC	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RKC
+#define BNXT_CTX_MTQM	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING
+#define BNXT_CTX_SQDBS	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SQ_DB_SHADOW
+#define BNXT_CTX_RQDBS	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RQ_DB_SHADOW
+#define BNXT_CTX_SRQDBS	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ_DB_SHADOW
+#define BNXT_CTX_CQDBS	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ_DB_SHADOW
+#define BNXT_CTX_QTKC	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QUIC_TKC
+#define BNXT_CTX_QRKC	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QUIC_RKC
+#define BNXT_CTX_TBLSC	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TBL_SCOPE
+#define BNXT_CTX_XPAR	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_XID_PARTITION
+
+#define BNXT_CTX_MAX	(BNXT_CTX_TIM + 1)
+#define BNXT_CTX_L2_MAX	(BNXT_CTX_FTQM + 1)
+#define BNXT_CTX_V2_MAX	(BNXT_CTX_XPAR + 1)
+#define BNXT_CTX_INV	((u16)-1)
+
 struct bnxt_ctx_mem_info {
-	u32	qp_max_entries;
-	u16	qp_min_qp1_entries;
-	u16	qp_max_l2_entries;
-	u16	qp_entry_size;
-	u16	srq_max_l2_entries;
-	u32	srq_max_entries;
-	u16	srq_entry_size;
-	u16	cq_max_l2_entries;
-	u32	cq_max_entries;
-	u16	cq_entry_size;
-	u16	vnic_max_vnic_entries;
-	u16	vnic_max_ring_table_entries;
-	u16	vnic_entry_size;
-	u32	stat_max_entries;
-	u16	stat_entry_size;
-	u16	tqm_entry_size;
-	u32	tqm_min_entries_per_ring;
-	u32	tqm_max_entries_per_ring;
-	u32	mrav_max_entries;
-	u16	mrav_entry_size;
-	u16	tim_entry_size;
-	u32	tim_max_entries;
-	u16	mrav_num_entries_units;
-	u8	tqm_entries_multiple;
 	u8	tqm_fp_rings_count;
 
 	u32	flags;
 	#define BNXT_CTX_FLAG_INITED	0x01
-
-	struct bnxt_ctx_pg_info qp_mem;
-	struct bnxt_ctx_pg_info srq_mem;
-	struct bnxt_ctx_pg_info cq_mem;
-	struct bnxt_ctx_pg_info vnic_mem;
-	struct bnxt_ctx_pg_info stat_mem;
-	struct bnxt_ctx_pg_info mrav_mem;
-	struct bnxt_ctx_pg_info tim_mem;
-	struct bnxt_ctx_pg_info *tqm_mem[BNXT_MAX_TQM_RINGS];
-
-#define BNXT_CTX_MEM_INIT_QP	0
-#define BNXT_CTX_MEM_INIT_SRQ	1
-#define BNXT_CTX_MEM_INIT_CQ	2
-#define BNXT_CTX_MEM_INIT_VNIC	3
-#define BNXT_CTX_MEM_INIT_STAT	4
-#define BNXT_CTX_MEM_INIT_MRAV	5
-#define BNXT_CTX_MEM_INIT_MAX	6
-	struct bnxt_mem_init	mem_init[BNXT_CTX_MEM_INIT_MAX];
+	struct bnxt_ctx_mem_type	ctx_arr[BNXT_CTX_V2_MAX];
 };
 
 enum bnxt_health_severity {
@@ -1691,6 +1964,10 @@ enum board_idx {
 	BCM57508_NPAR,
 	BCM57504_NPAR,
 	BCM57502_NPAR,
+	BCM57608,
+	BCM57604,
+	BCM57602,
+	BCM57601,
 	BCM58802,
 	BCM58804,
 	BCM58808,
@@ -1738,14 +2015,14 @@ struct bnxt {
 #define CHIP_NUM_57504		0x1751
 #define CHIP_NUM_57502		0x1752
 
+#define CHIP_NUM_57608		0x1760
+
 #define CHIP_NUM_58802		0xd802
 #define CHIP_NUM_58804		0xd804
 #define CHIP_NUM_58808		0xd808
 
 	u8			chip_rev;
 
-#define CHIP_NUM_58818		0xd818
-
 #define BNXT_CHIP_NUM_5730X(chip_num)		\
 	((chip_num) >= CHIP_NUM_57301 &&	\
 	 (chip_num) <= CHIP_NUM_57304)
@@ -1795,7 +2072,7 @@ struct bnxt {
 	atomic_t		intr_sem;
 
 	u32			flags;
-	#define BNXT_FLAG_CHIP_P5	0x1
+	#define BNXT_FLAG_CHIP_P5_PLUS	0x1
 	#define BNXT_FLAG_VF		0x2
 	#define BNXT_FLAG_LRO		0x4
 #ifdef CONFIG_INET
@@ -1814,8 +2091,6 @@ struct bnxt {
 	#define BNXT_FLAG_RFS		0x100
 	#define BNXT_FLAG_SHARED_RINGS	0x200
 	#define BNXT_FLAG_PORT_STATS	0x400
-	#define BNXT_FLAG_UDP_RSS_CAP	0x800
-	#define BNXT_FLAG_NEW_RSS_CAP	0x2000
 	#define BNXT_FLAG_WOL_CAP	0x4000
 	#define BNXT_FLAG_ROCEV1_CAP	0x8000
 	#define BNXT_FLAG_ROCEV2_CAP	0x10000
@@ -1823,13 +2098,15 @@ struct bnxt {
 					 BNXT_FLAG_ROCEV2_CAP)
 	#define BNXT_FLAG_NO_AGG_RINGS	0x20000
 	#define BNXT_FLAG_RX_PAGE_MODE	0x40000
-	#define BNXT_FLAG_CHIP_SR2	0x80000
+	#define BNXT_FLAG_CHIP_P7	0x80000
 	#define BNXT_FLAG_MULTI_HOST	0x100000
 	#define BNXT_FLAG_DSN_VALID	0x200000
 	#define BNXT_FLAG_DOUBLE_DB	0x400000
+	#define BNXT_FLAG_UDP_GSO_CAP	0x800000
 	#define BNXT_FLAG_CHIP_NITRO_A0	0x1000000
 	#define BNXT_FLAG_DIM		0x2000000
 	#define BNXT_FLAG_ROCE_MIRROR_CAP	0x4000000
+	#define BNXT_FLAG_TX_COAL_CMPL	0x8000000
 	#define BNXT_FLAG_PORT_STATS_EXT	0x10000000
 
 	#define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA |		\
@@ -1849,21 +2126,21 @@ struct bnxt {
 #define BNXT_CHIP_TYPE_NITRO_A0(bp) ((bp)->flags & BNXT_FLAG_CHIP_NITRO_A0)
 #define BNXT_RX_PAGE_MODE(bp)	((bp)->flags & BNXT_FLAG_RX_PAGE_MODE)
 #define BNXT_SUPPORTS_TPA(bp)	(!BNXT_CHIP_TYPE_NITRO_A0(bp) &&	\
-				 (!((bp)->flags & BNXT_FLAG_CHIP_P5) ||	\
+				 (!((bp)->flags & BNXT_FLAG_CHIP_P5_PLUS) ||\
 				  (bp)->max_tpa_v2) && !is_kdump_kernel())
 #define BNXT_RX_JUMBO_MODE(bp)	((bp)->flags & BNXT_FLAG_JUMBO)
 
-#define BNXT_CHIP_SR2(bp)			\
-	((bp)->chip_num == CHIP_NUM_58818)
+#define BNXT_CHIP_P7(bp)			\
+	((bp)->chip_num == CHIP_NUM_57608)
 
-#define BNXT_CHIP_P5_THOR(bp)			\
+#define BNXT_CHIP_P5(bp)			\
 	((bp)->chip_num == CHIP_NUM_57508 ||	\
 	 (bp)->chip_num == CHIP_NUM_57504 ||	\
 	 (bp)->chip_num == CHIP_NUM_57502)
 
 /* Chip class phase 5 */
-#define BNXT_CHIP_P5(bp)			\
-	(BNXT_CHIP_P5_THOR(bp) || BNXT_CHIP_SR2(bp))
+#define BNXT_CHIP_P5_PLUS(bp)			\
+	(BNXT_CHIP_P5(bp) || BNXT_CHIP_P7(bp))
 
 /* Chip class phase 4.x */
 #define BNXT_CHIP_P4(bp)			\
@@ -1874,7 +2151,7 @@ struct bnxt {
 	  !BNXT_CHIP_TYPE_NITRO_A0(bp)))
 
 #define BNXT_CHIP_P4_PLUS(bp)			\
-	(BNXT_CHIP_P4(bp) || BNXT_CHIP_P5(bp))
+	(BNXT_CHIP_P4(bp) || BNXT_CHIP_P5_PLUS(bp))
 
 	struct bnxt_aux_priv	*aux_priv;
 	struct bnxt_en_dev	*edev;
@@ -1935,6 +2212,11 @@ struct bnxt {
 	u16			rss_indir_tbl_entries;
 	u32			rss_hash_cfg;
 	u32			rss_hash_delta;
+	u32			rss_cap;
+#define BNXT_RSS_CAP_RSS_HASH_TYPE_DELTA	BIT(0)
+#define BNXT_RSS_CAP_UDP_RSS_CAP		BIT(1)
+#define BNXT_RSS_CAP_NEW_RSS_CAP		BIT(2)
+#define BNXT_RSS_CAP_RSS_TCAM			BIT(3)
 
 	u16			max_mtu;
 	u8			max_tc;
@@ -2000,7 +2282,6 @@ struct bnxt {
 	#define BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V2	BIT_ULL(16)
 	#define BNXT_FW_CAP_PCIE_STATS_SUPPORTED	BIT_ULL(17)
 	#define BNXT_FW_CAP_EXT_STATS_SUPPORTED		BIT_ULL(18)
-	#define BNXT_FW_CAP_RSS_HASH_TYPE_DELTA		BIT_ULL(19)
 	#define BNXT_FW_CAP_ERR_RECOVER_RELOAD		BIT_ULL(20)
 	#define BNXT_FW_CAP_HOT_RESET			BIT_ULL(21)
 	#define BNXT_FW_CAP_PTP_RTC			BIT_ULL(22)
@@ -2017,6 +2298,8 @@ struct bnxt {
 	#define BNXT_FW_CAP_THRESHOLD_TEMP_SUPPORTED	BIT_ULL(33)
 	#define BNXT_FW_CAP_DFLT_VLAN_TPID_PCP		BIT_ULL(34)
 	#define BNXT_FW_CAP_PRE_RESV_VNICS		BIT_ULL(35)
+	#define BNXT_FW_CAP_BACKING_STORE_V2		BIT_ULL(36)
+	#define BNXT_FW_CAP_VNIC_TUNNEL_TPA		BIT_ULL(37)
 
 	u32			fw_dbg_cap;
 
@@ -2061,8 +2344,10 @@ struct bnxt {
 
 	u16			vxlan_fw_dst_port_id;
 	u16			nge_fw_dst_port_id;
+	u16			vxlan_gpe_fw_dst_port_id;
 	__be16			vxlan_port;
 	__be16			nge_port;
+	__be16			vxlan_gpe_port;
 	u8			port_partition_type;
 	u8			port_count;
 	u16			br_mode;
@@ -2130,9 +2415,11 @@ struct bnxt {
 	/* ensure atomic 64-bit doorbell writes on 32-bit systems. */
 	spinlock_t		db_lock;
 #endif
+	int			db_offset;	/* db_offset within db_size */
 	int			db_size;
 
 #define BNXT_NTP_FLTR_MAX_FLTR	4096
+#define BNXT_MAX_FLTR		(BNXT_NTP_FLTR_MAX_FLTR + BNXT_L2_FLTR_MAX_FLTR)
 #define BNXT_NTP_FLTR_HASH_SIZE	512
 #define BNXT_NTP_FLTR_HASH_MASK	(BNXT_NTP_FLTR_HASH_SIZE - 1)
 	struct hlist_head	ntp_fltr_hash_tbl[BNXT_NTP_FLTR_HASH_SIZE];
@@ -2141,6 +2428,14 @@ struct bnxt {
 	unsigned long		*ntp_fltr_bmap;
 	int			ntp_fltr_count;
 
+#define BNXT_L2_FLTR_MAX_FLTR	1024
+#define BNXT_L2_FLTR_HASH_SIZE	32
+#define BNXT_L2_FLTR_HASH_MASK	(BNXT_L2_FLTR_HASH_SIZE - 1)
+	struct hlist_head	l2_fltr_hash_tbl[BNXT_L2_FLTR_HASH_SIZE];
+
+	u32			hash_seed;
+	u64			toeplitz_prefix;
+
 	/* To protect link related settings during link changes and
 	 * ethtool settings changes.
 	 */
@@ -2163,6 +2458,7 @@ struct bnxt {
 #define BNXT_PHY_FL_NO_PAUSE		(PORT_PHY_QCAPS_RESP_FLAGS2_PAUSE_UNSUPPORTED << 8)
 #define BNXT_PHY_FL_NO_PFC		(PORT_PHY_QCAPS_RESP_FLAGS2_PFC_UNSUPPORTED << 8)
 #define BNXT_PHY_FL_BANK_SEL		(PORT_PHY_QCAPS_RESP_FLAGS2_BANK_ADDR_SUPPORTED << 8)
+#define BNXT_PHY_FL_SPEEDS2		(PORT_PHY_QCAPS_RESP_FLAGS2_SPEEDS2_SUPPORTED << 8)
 
 	u8			num_tests;
 	struct bnxt_test_info	*test_info;
@@ -2206,15 +2502,15 @@ struct bnxt {
 #define BNXT_NUM_TX_RING_STATS			8
 #define BNXT_NUM_TPA_RING_STATS			4
 #define BNXT_NUM_TPA_RING_STATS_P5		5
-#define BNXT_NUM_TPA_RING_STATS_P5_SR2		6
+#define BNXT_NUM_TPA_RING_STATS_P7		6
 
 #define BNXT_RING_STATS_SIZE_P5					\
 	((BNXT_NUM_RX_RING_STATS + BNXT_NUM_TX_RING_STATS +	\
 	  BNXT_NUM_TPA_RING_STATS_P5) * 8)
 
-#define BNXT_RING_STATS_SIZE_P5_SR2				\
+#define BNXT_RING_STATS_SIZE_P7					\
 	((BNXT_NUM_RX_RING_STATS + BNXT_NUM_TX_RING_STATS +	\
-	  BNXT_NUM_TPA_RING_STATS_P5_SR2) * 8)
+	  BNXT_NUM_TPA_RING_STATS_P7) * 8)
 
 #define BNXT_GET_RING_STATS64(sw, counter)		\
 	(*((sw) + offsetof(struct ctx_hw_stats, counter) / 8))
@@ -2297,10 +2593,11 @@ static inline void bnxt_writeq_relaxed(struct bnxt *bp, u64 val,
 static inline void bnxt_db_write_relaxed(struct bnxt *bp,
 					 struct bnxt_db_info *db, u32 idx)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
-		bnxt_writeq_relaxed(bp, db->db_key64 | idx, db->doorbell);
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+		bnxt_writeq_relaxed(bp, db->db_key64 | DB_RING_IDX(db, idx),
+				    db->doorbell);
 	} else {
-		u32 db_val = db->db_key32 | idx;
+		u32 db_val = db->db_key32 | DB_RING_IDX(db, idx);
 
 		writel_relaxed(db_val, db->doorbell);
 		if (bp->flags & BNXT_FLAG_DOUBLE_DB)
@@ -2312,10 +2609,11 @@ static inline void bnxt_db_write_relaxed(struct bnxt *bp,
 static inline void bnxt_db_write(struct bnxt *bp, struct bnxt_db_info *db,
 				 u32 idx)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
-		bnxt_writeq(bp, db->db_key64 | idx, db->doorbell);
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+		bnxt_writeq(bp, db->db_key64 | DB_RING_IDX(db, idx),
+			    db->doorbell);
 	} else {
-		u32 db_val = db->db_key32 | idx;
+		u32 db_val = db->db_key32 | DB_RING_IDX(db, idx);
 
 		writel(db_val, db->doorbell);
 		if (bp->flags & BNXT_FLAG_DOUBLE_DB)
@@ -2345,12 +2643,21 @@ int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode);
 int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap,
 			    int bmap_size, bool async_only);
 int bnxt_hwrm_func_drv_unrgtr(struct bnxt *bp);
+void bnxt_del_l2_filter(struct bnxt *bp, struct bnxt_l2_filter *fltr);
+int bnxt_hwrm_l2_filter_free(struct bnxt *bp, struct bnxt_l2_filter *fltr);
+int bnxt_hwrm_l2_filter_alloc(struct bnxt *bp, struct bnxt_l2_filter *fltr);
+int bnxt_hwrm_cfa_ntuple_filter_free(struct bnxt *bp,
+				     struct bnxt_ntuple_filter *fltr);
+int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
+				      struct bnxt_ntuple_filter *fltr);
+void bnxt_fill_ipv6_mask(__be32 mask[4]);
 int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings);
 int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id);
 int __bnxt_hwrm_get_tx_rings(struct bnxt *bp, u16 fid, int *tx_rings);
 int bnxt_nq_rings_in_use(struct bnxt *bp);
 int bnxt_hwrm_set_coal(struct bnxt *);
 void bnxt_free_ctx_mem(struct bnxt *bp);
+int bnxt_num_tx_to_cp(struct bnxt *bp, int tx);
 unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp);
 unsigned int bnxt_get_avail_stat_ctxs_for_en(struct bnxt *bp);
 unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp);
@@ -2360,7 +2667,7 @@ int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init);
 void bnxt_tx_disable(struct bnxt *bp);
 void bnxt_tx_enable(struct bnxt *bp);
 void bnxt_sched_reset_txr(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
-			  int idx);
+			  u16 curr);
 void bnxt_report_link(struct bnxt *bp);
 int bnxt_update_link(struct bnxt *bp, bool chng_link_state);
 int bnxt_hwrm_set_pause(struct bnxt *);
@@ -2375,7 +2682,7 @@ int bnxt_open_nic(struct bnxt *, bool, bool);
 int bnxt_half_open_nic(struct bnxt *bp);
 void bnxt_half_close_nic(struct bnxt *bp);
 void bnxt_reenable_sriov(struct bnxt *bp);
-int bnxt_close_nic(struct bnxt *, bool, bool);
+void bnxt_close_nic(struct bnxt *, bool, bool);
 void bnxt_get_ring_err_stats(struct bnxt *bp,
 			     struct bnxt_total_ring_err_stats *stats);
 int bnxt_dbg_hwrm_rd_reg(struct bnxt *bp, u32 reg_off, u16 num_words,
@@ -2387,6 +2694,13 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 int bnxt_fw_init_one(struct bnxt *bp);
 bool bnxt_hwrm_reset_permitted(struct bnxt *bp);
 int bnxt_setup_mq_tc(struct net_device *dev, u8 tc);
+struct bnxt_ntuple_filter *bnxt_lookup_ntp_filter_from_idx(struct bnxt *bp,
+				struct bnxt_ntuple_filter *fltr, u32 idx);
+u32 bnxt_get_ntp_filter_idx(struct bnxt *bp, struct flow_keys *fkeys,
+			    const struct sk_buff *skb);
+int bnxt_insert_ntp_filter(struct bnxt *bp, struct bnxt_ntuple_filter *fltr,
+			   u32 idx);
+void bnxt_del_ntp_filter(struct bnxt *bp, struct bnxt_ntuple_filter *fltr);
 int bnxt_get_max_rings(struct bnxt *, int *, int *, bool);
 int bnxt_restore_pf_fw_resources(struct bnxt *bp);
 int bnxt_get_port_parent_id(struct net_device *dev,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index f302dac56599..ae4529c043f0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -449,15 +449,8 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change,
 			return -ENODEV;
 		}
 		bnxt_ulp_stop(bp);
-		if (netif_running(bp->dev)) {
-			rc = bnxt_close_nic(bp, true, true);
-			if (rc) {
-				NL_SET_ERR_MSG_MOD(extack, "Failed to close");
-				dev_close(bp->dev);
-				rtnl_unlock();
-				break;
-			}
-		}
+		if (netif_running(bp->dev))
+			bnxt_close_nic(bp, true, true);
 		bnxt_vf_reps_free(bp);
 		rc = bnxt_hwrm_func_drv_unrgtr(bp);
 		if (rc) {
@@ -469,8 +462,6 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change,
 		}
 		bnxt_cancel_reservations(bp, false);
 		bnxt_free_ctx_mem(bp);
-		kfree(bp->ctx);
-		bp->ctx = NULL;
 		break;
 	}
 	case DEVLINK_RELOAD_ACTION_FW_ACTIVATE: {
@@ -741,7 +732,7 @@ static int bnxt_hwrm_get_nvm_cfg_ver(struct bnxt *bp, u32 *nvm_cfg_ver)
 	}
 
 	/* earlier devices present as an array of raw bytes */
-	if (!BNXT_CHIP_P5(bp)) {
+	if (!BNXT_CHIP_P5_PLUS(bp)) {
 		dim = 0;
 		i = 0;
 		bits *= 3;  /* array of 3 version components */
@@ -761,7 +752,7 @@ static int bnxt_hwrm_get_nvm_cfg_ver(struct bnxt *bp, u32 *nvm_cfg_ver)
 			goto exit;
 		bnxt_copy_from_nvm_data(&ver, data, bits, bytes);
 
-		if (BNXT_CHIP_P5(bp)) {
+		if (BNXT_CHIP_P5_PLUS(bp)) {
 			*nvm_cfg_ver <<= 8;
 			*nvm_cfg_ver |= ver.vu8;
 		} else {
@@ -781,7 +772,7 @@ static int bnxt_dl_info_put(struct bnxt *bp, struct devlink_info_req *req,
 	if (!strlen(buf))
 		return 0;
 
-	if ((bp->flags & BNXT_FLAG_CHIP_P5) &&
+	if ((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) &&
 	    (!strcmp(key, DEVLINK_INFO_VERSION_GENERIC_FW_NCSI) ||
 	     !strcmp(key, DEVLINK_INFO_VERSION_GENERIC_FW_ROCE)))
 		return 0;
@@ -1007,7 +998,7 @@ static int bnxt_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 	if (rc)
 		return rc;
 
-	if (BNXT_CHIP_P5(bp)) {
+	if (BNXT_CHIP_P5_PLUS(bp)) {
 		rc = bnxt_dl_livepatch_info_put(bp, req, BNXT_FW_SRT_PATCH);
 		if (rc)
 			return rc;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index f3f384773ac0..27b983c0a8a9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -165,9 +165,8 @@ static int bnxt_set_coalesce(struct net_device *dev,
 reset_coalesce:
 	if (test_bit(BNXT_STATE_OPEN, &bp->state)) {
 		if (update_stats) {
-			rc = bnxt_close_nic(bp, true, false);
-			if (!rc)
-				rc = bnxt_open_nic(bp, true, false);
+			bnxt_close_nic(bp, true, false);
+			rc = bnxt_open_nic(bp, true, false);
 		} else {
 			rc = bnxt_hwrm_set_coal(bp);
 		}
@@ -461,6 +460,7 @@ static const struct {
 	BNXT_RX_STATS_EXT_DISCARD_COS_ENTRIES,
 	BNXT_RX_STATS_EXT_ENTRY(rx_fec_corrected_blocks),
 	BNXT_RX_STATS_EXT_ENTRY(rx_fec_uncorrectable_blocks),
+	BNXT_RX_STATS_EXT_ENTRY(rx_filter_miss),
 };
 
 static const struct {
@@ -511,9 +511,9 @@ static int bnxt_get_num_tpa_ring_stats(struct bnxt *bp)
 {
 	if (BNXT_SUPPORTS_TPA(bp)) {
 		if (bp->max_tpa_v2) {
-			if (BNXT_CHIP_P5_THOR(bp))
+			if (BNXT_CHIP_P5(bp))
 				return BNXT_NUM_TPA_RING_STATS_P5;
-			return BNXT_NUM_TPA_RING_STATS_P5_SR2;
+			return BNXT_NUM_TPA_RING_STATS_P7;
 		}
 		return BNXT_NUM_TPA_RING_STATS;
 	}
@@ -528,7 +528,8 @@ static int bnxt_get_num_ring_stats(struct bnxt *bp)
 	     bnxt_get_num_tpa_ring_stats(bp);
 	tx = NUM_RING_TX_HW_STATS;
 	cmn = NUM_RING_CMN_SW_STATS;
-	return rx * bp->rx_nr_rings + tx * bp->tx_nr_rings +
+	return rx * bp->rx_nr_rings +
+	       tx * (bp->tx_nr_rings_xdp + bp->tx_nr_rings_per_tc) +
 	       cmn * bp->cp_nr_rings;
 }
 
@@ -923,6 +924,7 @@ static int bnxt_set_channels(struct net_device *dev,
 	bool sh = false;
 	int tx_xdp = 0;
 	int rc = 0;
+	int tx_cp;
 
 	if (channel->other_count)
 		return -EINVAL;
@@ -972,12 +974,7 @@ static int bnxt_set_channels(struct net_device *dev,
 			 * before PF unload
 			 */
 		}
-		rc = bnxt_close_nic(bp, true, false);
-		if (rc) {
-			netdev_err(bp->dev, "Set channel failure rc :%x\n",
-				   rc);
-			return rc;
-		}
+		bnxt_close_nic(bp, true, false);
 	}
 
 	if (sh) {
@@ -994,8 +991,9 @@ static int bnxt_set_channels(struct net_device *dev,
 	if (tcs > 1)
 		bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tcs + tx_xdp;
 
-	bp->cp_nr_rings = sh ? max_t(int, bp->tx_nr_rings, bp->rx_nr_rings) :
-			       bp->tx_nr_rings + bp->rx_nr_rings;
+	tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings);
+	bp->cp_nr_rings = sh ? max_t(int, tx_cp, bp->rx_nr_rings) :
+			       tx_cp + bp->rx_nr_rings;
 
 	/* After changing number of rx channels, update NTUPLE feature. */
 	netdev_update_features(dev);
@@ -1013,29 +1011,60 @@ static int bnxt_set_channels(struct net_device *dev,
 	return rc;
 }
 
-#ifdef CONFIG_RFS_ACCEL
-static int bnxt_grxclsrlall(struct bnxt *bp, struct ethtool_rxnfc *cmd,
-			    u32 *rule_locs)
+static u32 bnxt_get_all_fltr_ids_rcu(struct bnxt *bp, struct hlist_head tbl[],
+				     int tbl_size, u32 *ids, u32 start,
+				     u32 id_cnt)
 {
-	int i, j = 0;
+	int i, j = start;
 
-	cmd->data = bp->ntp_fltr_count;
-	for (i = 0; i < BNXT_NTP_FLTR_HASH_SIZE; i++) {
+	if (j >= id_cnt)
+		return j;
+	for (i = 0; i < tbl_size; i++) {
 		struct hlist_head *head;
-		struct bnxt_ntuple_filter *fltr;
+		struct bnxt_filter_base *fltr;
 
-		head = &bp->ntp_fltr_hash_tbl[i];
-		rcu_read_lock();
+		head = &tbl[i];
 		hlist_for_each_entry_rcu(fltr, head, hash) {
-			if (j == cmd->rule_cnt)
-				break;
-			rule_locs[j++] = fltr->sw_id;
+			if (!fltr->flags ||
+			    test_bit(BNXT_FLTR_FW_DELETED, &fltr->state))
+				continue;
+			ids[j++] = fltr->sw_id;
+			if (j == id_cnt)
+				return j;
+		}
+	}
+	return j;
+}
+
+static struct bnxt_filter_base *bnxt_get_one_fltr_rcu(struct bnxt *bp,
+						      struct hlist_head tbl[],
+						      int tbl_size, u32 id)
+{
+	int i;
+
+	for (i = 0; i < tbl_size; i++) {
+		struct hlist_head *head;
+		struct bnxt_filter_base *fltr;
+
+		head = &tbl[i];
+		hlist_for_each_entry_rcu(fltr, head, hash) {
+			if (fltr->flags && fltr->sw_id == id)
+				return fltr;
 		}
-		rcu_read_unlock();
-		if (j == cmd->rule_cnt)
-			break;
 	}
-	cmd->rule_cnt = j;
+	return NULL;
+}
+
+static int bnxt_grxclsrlall(struct bnxt *bp, struct ethtool_rxnfc *cmd,
+			    u32 *rule_locs)
+{
+	cmd->data = bp->ntp_fltr_count;
+	rcu_read_lock();
+	cmd->rule_cnt = bnxt_get_all_fltr_ids_rcu(bp, bp->ntp_fltr_hash_tbl,
+						  BNXT_NTP_FLTR_HASH_SIZE,
+						  rule_locs, 0, cmd->rule_cnt);
+	rcu_read_unlock();
+
 	return 0;
 }
 
@@ -1043,27 +1072,24 @@ static int bnxt_grxclsrule(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 {
 	struct ethtool_rx_flow_spec *fs =
 		(struct ethtool_rx_flow_spec *)&cmd->fs;
+	struct bnxt_filter_base *fltr_base;
 	struct bnxt_ntuple_filter *fltr;
 	struct flow_keys *fkeys;
-	int i, rc = -EINVAL;
+	int rc = -EINVAL;
 
 	if (fs->location >= BNXT_NTP_FLTR_MAX_FLTR)
 		return rc;
 
-	for (i = 0; i < BNXT_NTP_FLTR_HASH_SIZE; i++) {
-		struct hlist_head *head;
-
-		head = &bp->ntp_fltr_hash_tbl[i];
-		rcu_read_lock();
-		hlist_for_each_entry_rcu(fltr, head, hash) {
-			if (fltr->sw_id == fs->location)
-				goto fltr_found;
-		}
+	rcu_read_lock();
+	fltr_base = bnxt_get_one_fltr_rcu(bp, bp->ntp_fltr_hash_tbl,
+					  BNXT_NTP_FLTR_HASH_SIZE,
+					  fs->location);
+	if (!fltr_base) {
 		rcu_read_unlock();
+		return rc;
 	}
-	return rc;
+	fltr = container_of(fltr_base, struct bnxt_ntuple_filter, base);
 
-fltr_found:
 	fkeys = &fltr->fkeys;
 	if (fkeys->basic.n_proto == htons(ETH_P_IP)) {
 		if (fkeys->basic.ip_proto == IPPROTO_TCP)
@@ -1073,20 +1099,23 @@ fltr_found:
 		else
 			goto fltr_err;
 
-		fs->h_u.tcp_ip4_spec.ip4src = fkeys->addrs.v4addrs.src;
-		fs->m_u.tcp_ip4_spec.ip4src = cpu_to_be32(~0);
-
-		fs->h_u.tcp_ip4_spec.ip4dst = fkeys->addrs.v4addrs.dst;
-		fs->m_u.tcp_ip4_spec.ip4dst = cpu_to_be32(~0);
-
-		fs->h_u.tcp_ip4_spec.psrc = fkeys->ports.src;
-		fs->m_u.tcp_ip4_spec.psrc = cpu_to_be16(~0);
-
-		fs->h_u.tcp_ip4_spec.pdst = fkeys->ports.dst;
-		fs->m_u.tcp_ip4_spec.pdst = cpu_to_be16(~0);
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_IP) {
+			fs->h_u.tcp_ip4_spec.ip4src = fkeys->addrs.v4addrs.src;
+			fs->m_u.tcp_ip4_spec.ip4src = cpu_to_be32(~0);
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_DST_IP) {
+			fs->h_u.tcp_ip4_spec.ip4dst = fkeys->addrs.v4addrs.dst;
+			fs->m_u.tcp_ip4_spec.ip4dst = cpu_to_be32(~0);
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_PORT) {
+			fs->h_u.tcp_ip4_spec.psrc = fkeys->ports.src;
+			fs->m_u.tcp_ip4_spec.psrc = cpu_to_be16(~0);
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_DST_PORT) {
+			fs->h_u.tcp_ip4_spec.pdst = fkeys->ports.dst;
+			fs->m_u.tcp_ip4_spec.pdst = cpu_to_be16(~0);
+		}
 	} else {
-		int i;
-
 		if (fkeys->basic.ip_proto == IPPROTO_TCP)
 			fs->flow_type = TCP_V6_FLOW;
 		else if (fkeys->basic.ip_proto == IPPROTO_UDP)
@@ -1094,22 +1123,27 @@ fltr_found:
 		else
 			goto fltr_err;
 
-		*(struct in6_addr *)&fs->h_u.tcp_ip6_spec.ip6src[0] =
-			fkeys->addrs.v6addrs.src;
-		*(struct in6_addr *)&fs->h_u.tcp_ip6_spec.ip6dst[0] =
-			fkeys->addrs.v6addrs.dst;
-		for (i = 0; i < 4; i++) {
-			fs->m_u.tcp_ip6_spec.ip6src[i] = cpu_to_be32(~0);
-			fs->m_u.tcp_ip6_spec.ip6dst[i] = cpu_to_be32(~0);
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_IP) {
+			*(struct in6_addr *)&fs->h_u.tcp_ip6_spec.ip6src[0] =
+				fkeys->addrs.v6addrs.src;
+			bnxt_fill_ipv6_mask(fs->m_u.tcp_ip6_spec.ip6src);
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_DST_IP) {
+			*(struct in6_addr *)&fs->h_u.tcp_ip6_spec.ip6dst[0] =
+				fkeys->addrs.v6addrs.dst;
+			bnxt_fill_ipv6_mask(fs->m_u.tcp_ip6_spec.ip6dst);
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_PORT) {
+			fs->h_u.tcp_ip6_spec.psrc = fkeys->ports.src;
+			fs->m_u.tcp_ip6_spec.psrc = cpu_to_be16(~0);
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_DST_PORT) {
+			fs->h_u.tcp_ip6_spec.pdst = fkeys->ports.dst;
+			fs->m_u.tcp_ip6_spec.pdst = cpu_to_be16(~0);
 		}
-		fs->h_u.tcp_ip6_spec.psrc = fkeys->ports.src;
-		fs->m_u.tcp_ip6_spec.psrc = cpu_to_be16(~0);
-
-		fs->h_u.tcp_ip6_spec.pdst = fkeys->ports.dst;
-		fs->m_u.tcp_ip6_spec.pdst = cpu_to_be16(~0);
 	}
 
-	fs->ring_cookie = fltr->rxq;
+	fs->ring_cookie = fltr->base.rxq;
 	rc = 0;
 
 fltr_err:
@@ -1117,7 +1151,221 @@ fltr_err:
 
 	return rc;
 }
-#endif
+
+#define IPV4_ALL_MASK		((__force __be32)~0)
+#define L4_PORT_ALL_MASK	((__force __be16)~0)
+
+static bool ipv6_mask_is_full(__be32 mask[4])
+{
+	return (mask[0] & mask[1] & mask[2] & mask[3]) == IPV4_ALL_MASK;
+}
+
+static bool ipv6_mask_is_zero(__be32 mask[4])
+{
+	return !(mask[0] | mask[1] | mask[2] | mask[3]);
+}
+
+static int bnxt_add_ntuple_cls_rule(struct bnxt *bp,
+				    struct ethtool_rx_flow_spec *fs)
+{
+	u8 vf = ethtool_get_flow_spec_ring_vf(fs->ring_cookie);
+	u32 ring = ethtool_get_flow_spec_ring(fs->ring_cookie);
+	struct bnxt_ntuple_filter *new_fltr, *fltr;
+	struct bnxt_l2_filter *l2_fltr;
+	u32 flow_type = fs->flow_type;
+	struct flow_keys *fkeys;
+	u32 idx;
+	int rc;
+
+	if (!bp->vnic_info)
+		return -EAGAIN;
+
+	if ((flow_type & (FLOW_MAC_EXT | FLOW_EXT)) || vf)
+		return -EOPNOTSUPP;
+
+	new_fltr = kzalloc(sizeof(*new_fltr), GFP_KERNEL);
+	if (!new_fltr)
+		return -ENOMEM;
+
+	l2_fltr = bp->vnic_info[0].l2_filters[0];
+	atomic_inc(&l2_fltr->refcnt);
+	new_fltr->l2_fltr = l2_fltr;
+	fkeys = &new_fltr->fkeys;
+
+	rc = -EOPNOTSUPP;
+	switch (flow_type) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW: {
+		struct ethtool_tcpip4_spec *ip_spec = &fs->h_u.tcp_ip4_spec;
+		struct ethtool_tcpip4_spec *ip_mask = &fs->m_u.tcp_ip4_spec;
+
+		fkeys->basic.ip_proto = IPPROTO_TCP;
+		if (flow_type == UDP_V4_FLOW)
+			fkeys->basic.ip_proto = IPPROTO_UDP;
+		fkeys->basic.n_proto = htons(ETH_P_IP);
+
+		if (ip_mask->ip4src == IPV4_ALL_MASK) {
+			fkeys->addrs.v4addrs.src = ip_spec->ip4src;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_SRC_IP;
+		} else if (ip_mask->ip4src) {
+			goto ntuple_err;
+		}
+		if (ip_mask->ip4dst == IPV4_ALL_MASK) {
+			fkeys->addrs.v4addrs.dst = ip_spec->ip4dst;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_DST_IP;
+		} else if (ip_mask->ip4dst) {
+			goto ntuple_err;
+		}
+
+		if (ip_mask->psrc == L4_PORT_ALL_MASK) {
+			fkeys->ports.src = ip_spec->psrc;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_SRC_PORT;
+		} else if (ip_mask->psrc) {
+			goto ntuple_err;
+		}
+		if (ip_mask->pdst == L4_PORT_ALL_MASK) {
+			fkeys->ports.dst = ip_spec->pdst;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_DST_PORT;
+		} else if (ip_mask->pdst) {
+			goto ntuple_err;
+		}
+		break;
+	}
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW: {
+		struct ethtool_tcpip6_spec *ip_spec = &fs->h_u.tcp_ip6_spec;
+		struct ethtool_tcpip6_spec *ip_mask = &fs->m_u.tcp_ip6_spec;
+
+		fkeys->basic.ip_proto = IPPROTO_TCP;
+		if (flow_type == UDP_V6_FLOW)
+			fkeys->basic.ip_proto = IPPROTO_UDP;
+		fkeys->basic.n_proto = htons(ETH_P_IPV6);
+
+		if (ipv6_mask_is_full(ip_mask->ip6src)) {
+			fkeys->addrs.v6addrs.src =
+				*(struct in6_addr *)&ip_spec->ip6src;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_SRC_IP;
+		} else if (!ipv6_mask_is_zero(ip_mask->ip6src)) {
+			goto ntuple_err;
+		}
+		if (ipv6_mask_is_full(ip_mask->ip6dst)) {
+			fkeys->addrs.v6addrs.dst =
+				*(struct in6_addr *)&ip_spec->ip6dst;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_DST_IP;
+		} else if (!ipv6_mask_is_zero(ip_mask->ip6dst)) {
+			goto ntuple_err;
+		}
+
+		if (ip_mask->psrc == L4_PORT_ALL_MASK) {
+			fkeys->ports.src = ip_spec->psrc;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_SRC_PORT;
+		} else if (ip_mask->psrc) {
+			goto ntuple_err;
+		}
+		if (ip_mask->pdst == L4_PORT_ALL_MASK) {
+			fkeys->ports.dst = ip_spec->pdst;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_DST_PORT;
+		} else if (ip_mask->pdst) {
+			goto ntuple_err;
+		}
+		break;
+	}
+	default:
+		rc = -EOPNOTSUPP;
+		goto ntuple_err;
+	}
+	if (!new_fltr->ntuple_flags)
+		goto ntuple_err;
+
+	idx = bnxt_get_ntp_filter_idx(bp, fkeys, NULL);
+	rcu_read_lock();
+	fltr = bnxt_lookup_ntp_filter_from_idx(bp, new_fltr, idx);
+	if (fltr) {
+		rcu_read_unlock();
+		rc = -EEXIST;
+		goto ntuple_err;
+	}
+	rcu_read_unlock();
+
+	new_fltr->base.rxq = ring;
+	new_fltr->base.flags = BNXT_ACT_NO_AGING;
+	__set_bit(BNXT_FLTR_VALID, &new_fltr->base.state);
+	rc = bnxt_insert_ntp_filter(bp, new_fltr, idx);
+	if (!rc) {
+		rc = bnxt_hwrm_cfa_ntuple_filter_alloc(bp, new_fltr);
+		if (rc) {
+			bnxt_del_ntp_filter(bp, new_fltr);
+			return rc;
+		}
+		fs->location = new_fltr->base.sw_id;
+		return 0;
+	}
+
+ntuple_err:
+	atomic_dec(&l2_fltr->refcnt);
+	kfree(new_fltr);
+	return rc;
+}
+
+static int bnxt_srxclsrlins(struct bnxt *bp, struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_rx_flow_spec *fs = &cmd->fs;
+	u32 ring, flow_type;
+	int rc;
+	u8 vf;
+
+	if (!netif_running(bp->dev))
+		return -EAGAIN;
+	if (!(bp->flags & BNXT_FLAG_RFS))
+		return -EPERM;
+	if (fs->location != RX_CLS_LOC_ANY)
+		return -EINVAL;
+
+	ring = ethtool_get_flow_spec_ring(fs->ring_cookie);
+	vf = ethtool_get_flow_spec_ring_vf(fs->ring_cookie);
+	if (BNXT_VF(bp) && vf)
+		return -EINVAL;
+	if (BNXT_PF(bp) && vf > bp->pf.active_vfs)
+		return -EINVAL;
+	if (!vf && ring >= bp->rx_nr_rings)
+		return -EINVAL;
+
+	flow_type = fs->flow_type;
+	if (flow_type & (FLOW_MAC_EXT | FLOW_RSS))
+		return -EINVAL;
+	flow_type &= ~FLOW_EXT;
+	if (flow_type == ETHER_FLOW)
+		rc = -EOPNOTSUPP;
+	else
+		rc = bnxt_add_ntuple_cls_rule(bp, fs);
+	return rc;
+}
+
+static int bnxt_srxclsrldel(struct bnxt *bp, struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_rx_flow_spec *fs = &cmd->fs;
+	struct bnxt_filter_base *fltr_base;
+	struct bnxt_ntuple_filter *fltr;
+
+	rcu_read_lock();
+	fltr_base = bnxt_get_one_fltr_rcu(bp, bp->ntp_fltr_hash_tbl,
+					  BNXT_NTP_FLTR_HASH_SIZE,
+					  fs->location);
+	if (!fltr_base) {
+		rcu_read_unlock();
+		return -ENOENT;
+	}
+
+	fltr = container_of(fltr_base, struct bnxt_ntuple_filter, base);
+	if (!(fltr->base.flags & BNXT_ACT_NO_AGING)) {
+		rcu_read_unlock();
+		return -EINVAL;
+	}
+	rcu_read_unlock();
+	bnxt_hwrm_cfa_ntuple_filter_free(bp, fltr);
+	bnxt_del_ntp_filter(bp, fltr);
+	return 0;
+}
 
 static u64 get_ethtool_ipv4_rss(struct bnxt *bp)
 {
@@ -1200,7 +1448,7 @@ static int bnxt_srxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 		if (tuple == 4)
 			rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4;
 	} else if (cmd->flow_type == UDP_V4_FLOW) {
-		if (tuple == 4 && !(bp->flags & BNXT_FLAG_UDP_RSS_CAP))
+		if (tuple == 4 && !(bp->rss_cap & BNXT_RSS_CAP_UDP_RSS_CAP))
 			return -EINVAL;
 		rss_hash_cfg &= ~VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4;
 		if (tuple == 4)
@@ -1210,7 +1458,7 @@ static int bnxt_srxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 		if (tuple == 4)
 			rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6;
 	} else if (cmd->flow_type == UDP_V6_FLOW) {
-		if (tuple == 4 && !(bp->flags & BNXT_FLAG_UDP_RSS_CAP))
+		if (tuple == 4 && !(bp->rss_cap & BNXT_RSS_CAP_UDP_RSS_CAP))
 			return -EINVAL;
 		rss_hash_cfg &= ~VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6;
 		if (tuple == 4)
@@ -1250,7 +1498,7 @@ static int bnxt_srxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 	if (bp->rss_hash_cfg == rss_hash_cfg)
 		return 0;
 
-	if (bp->fw_cap & BNXT_FW_CAP_RSS_HASH_TYPE_DELTA)
+	if (bp->rss_cap & BNXT_RSS_CAP_RSS_HASH_TYPE_DELTA)
 		bp->rss_hash_delta = bp->rss_hash_cfg ^ rss_hash_cfg;
 	bp->rss_hash_cfg = rss_hash_cfg;
 	if (netif_running(bp->dev)) {
@@ -1267,14 +1515,13 @@ static int bnxt_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 	int rc = 0;
 
 	switch (cmd->cmd) {
-#ifdef CONFIG_RFS_ACCEL
 	case ETHTOOL_GRXRINGS:
 		cmd->data = bp->rx_nr_rings;
 		break;
 
 	case ETHTOOL_GRXCLSRLCNT:
 		cmd->rule_cnt = bp->ntp_fltr_count;
-		cmd->data = BNXT_NTP_FLTR_MAX_FLTR;
+		cmd->data = BNXT_NTP_FLTR_MAX_FLTR | RX_CLS_LOC_SPECIAL;
 		break;
 
 	case ETHTOOL_GRXCLSRLALL:
@@ -1284,7 +1531,6 @@ static int bnxt_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 	case ETHTOOL_GRXCLSRULE:
 		rc = bnxt_grxclsrule(bp, cmd);
 		break;
-#endif
 
 	case ETHTOOL_GRXFH:
 		rc = bnxt_grxfh(bp, cmd);
@@ -1308,6 +1554,14 @@ static int bnxt_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 		rc = bnxt_srxfh(bp, cmd);
 		break;
 
+	case ETHTOOL_SRXCLSRLINS:
+		rc = bnxt_srxclsrlins(bp, cmd);
+		break;
+
+	case ETHTOOL_SRXCLSRLDEL:
+		rc = bnxt_srxclsrldel(bp, cmd);
+		break;
+
 	default:
 		rc = -EOPNOTSUPP;
 		break;
@@ -1319,7 +1573,7 @@ u32 bnxt_get_rxfh_indir_size(struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		return ALIGN(bp->rx_nr_rings, BNXT_RSS_TABLE_ENTRIES_P5);
 	return HW_HASH_INDEX_SIZE;
 }
@@ -1329,49 +1583,49 @@ static u32 bnxt_get_rxfh_key_size(struct net_device *dev)
 	return HW_HASH_KEY_SIZE;
 }
 
-static int bnxt_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
-			 u8 *hfunc)
+static int bnxt_get_rxfh(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_vnic_info *vnic;
 	u32 i, tbl_size;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	if (!bp->vnic_info)
 		return 0;
 
 	vnic = &bp->vnic_info[0];
-	if (indir && bp->rss_indir_tbl) {
+	if (rxfh->indir && bp->rss_indir_tbl) {
 		tbl_size = bnxt_get_rxfh_indir_size(dev);
 		for (i = 0; i < tbl_size; i++)
-			indir[i] = bp->rss_indir_tbl[i];
+			rxfh->indir[i] = bp->rss_indir_tbl[i];
 	}
 
-	if (key && vnic->rss_hash_key)
-		memcpy(key, vnic->rss_hash_key, HW_HASH_KEY_SIZE);
+	if (rxfh->key && vnic->rss_hash_key)
+		memcpy(rxfh->key, vnic->rss_hash_key, HW_HASH_KEY_SIZE);
 
 	return 0;
 }
 
-static int bnxt_set_rxfh(struct net_device *dev, const u32 *indir,
-			 const u8 *key, const u8 hfunc)
+static int bnxt_set_rxfh(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	int rc = 0;
 
-	if (hfunc && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc && rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (key)
+	if (rxfh->key)
 		return -EOPNOTSUPP;
 
-	if (indir) {
+	if (rxfh->indir) {
 		u32 i, pad, tbl_size = bnxt_get_rxfh_indir_size(dev);
 
 		for (i = 0; i < tbl_size; i++)
-			bp->rss_indir_tbl[i] = indir[i];
+			bp->rss_indir_tbl[i] = rxfh->indir[i];
 		pad = bp->rss_indir_tbl_entries - tbl_size;
 		if (pad)
 			memset(&bp->rss_indir_tbl[i], 0, pad * sizeof(u16));
@@ -1574,6 +1828,22 @@ static const enum bnxt_media_type bnxt_phy_types[] = {
 	[PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR2] = BNXT_MEDIA_SR,
 	[PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR2] = BNXT_MEDIA_LR_ER_FR,
 	[PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER2] = BNXT_MEDIA_LR_ER_FR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR] = BNXT_MEDIA_CR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR] = BNXT_MEDIA_SR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR] = BNXT_MEDIA_LR_ER_FR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER] = BNXT_MEDIA_LR_ER_FR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASECR2] = BNXT_MEDIA_CR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASESR2] = BNXT_MEDIA_SR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASELR2] = BNXT_MEDIA_LR_ER_FR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASEER2] = BNXT_MEDIA_LR_ER_FR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASECR8] = BNXT_MEDIA_CR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASESR8] = BNXT_MEDIA_SR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASELR8] = BNXT_MEDIA_LR_ER_FR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER8] = BNXT_MEDIA_LR_ER_FR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASECR4] = BNXT_MEDIA_CR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASESR4] = BNXT_MEDIA_SR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASELR4] = BNXT_MEDIA_LR_ER_FR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER4] = BNXT_MEDIA_LR_ER_FR,
 };
 
 static enum bnxt_media_type
@@ -1601,6 +1871,7 @@ enum bnxt_link_speed_indices {
 	BNXT_LINK_SPEED_50GB_IDX,
 	BNXT_LINK_SPEED_100GB_IDX,
 	BNXT_LINK_SPEED_200GB_IDX,
+	BNXT_LINK_SPEED_400GB_IDX,
 	__BNXT_LINK_SPEED_END
 };
 
@@ -1612,9 +1883,21 @@ static enum bnxt_link_speed_indices bnxt_fw_speed_idx(u16 speed)
 	case BNXT_LINK_SPEED_10GB: return BNXT_LINK_SPEED_10GB_IDX;
 	case BNXT_LINK_SPEED_25GB: return BNXT_LINK_SPEED_25GB_IDX;
 	case BNXT_LINK_SPEED_40GB: return BNXT_LINK_SPEED_40GB_IDX;
-	case BNXT_LINK_SPEED_50GB: return BNXT_LINK_SPEED_50GB_IDX;
-	case BNXT_LINK_SPEED_100GB: return BNXT_LINK_SPEED_100GB_IDX;
-	case BNXT_LINK_SPEED_200GB: return BNXT_LINK_SPEED_200GB_IDX;
+	case BNXT_LINK_SPEED_50GB:
+	case BNXT_LINK_SPEED_50GB_PAM4:
+		return BNXT_LINK_SPEED_50GB_IDX;
+	case BNXT_LINK_SPEED_100GB:
+	case BNXT_LINK_SPEED_100GB_PAM4:
+	case BNXT_LINK_SPEED_100GB_PAM4_112:
+		return BNXT_LINK_SPEED_100GB_IDX;
+	case BNXT_LINK_SPEED_200GB:
+	case BNXT_LINK_SPEED_200GB_PAM4:
+	case BNXT_LINK_SPEED_200GB_PAM4_112:
+		return BNXT_LINK_SPEED_200GB_IDX;
+	case BNXT_LINK_SPEED_400GB:
+	case BNXT_LINK_SPEED_400GB_PAM4:
+	case BNXT_LINK_SPEED_400GB_PAM4_112:
+		return BNXT_LINK_SPEED_400GB_IDX;
 	default: return BNXT_LINK_SPEED_UNKNOWN;
 	}
 }
@@ -1687,6 +1970,12 @@ bnxt_link_modes[__BNXT_LINK_SPEED_END][BNXT_SIG_MODE_MAX][__BNXT_MEDIA_END] = {
 			[BNXT_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT,
 			[BNXT_MEDIA_KR] = ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT,
 		},
+		[BNXT_SIG_MODE_PAM4_112] = {
+			[BNXT_MEDIA_CR] = ETHTOOL_LINK_MODE_100000baseCR_Full_BIT,
+			[BNXT_MEDIA_SR] = ETHTOOL_LINK_MODE_100000baseSR_Full_BIT,
+			[BNXT_MEDIA_KR] = ETHTOOL_LINK_MODE_100000baseKR_Full_BIT,
+			[BNXT_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_100000baseLR_ER_FR_Full_BIT,
+		},
 	},
 	[BNXT_LINK_SPEED_200GB_IDX] = {
 		[BNXT_SIG_MODE_PAM4] = {
@@ -1695,6 +1984,26 @@ bnxt_link_modes[__BNXT_LINK_SPEED_END][BNXT_SIG_MODE_MAX][__BNXT_MEDIA_END] = {
 			[BNXT_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT,
 			[BNXT_MEDIA_KR] = ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT,
 		},
+		[BNXT_SIG_MODE_PAM4_112] = {
+			[BNXT_MEDIA_CR] = ETHTOOL_LINK_MODE_200000baseCR2_Full_BIT,
+			[BNXT_MEDIA_KR] = ETHTOOL_LINK_MODE_200000baseKR2_Full_BIT,
+			[BNXT_MEDIA_SR] = ETHTOOL_LINK_MODE_200000baseSR2_Full_BIT,
+			[BNXT_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_200000baseLR2_ER2_FR2_Full_BIT,
+		},
+	},
+	[BNXT_LINK_SPEED_400GB_IDX] = {
+		[BNXT_SIG_MODE_PAM4] = {
+			[BNXT_MEDIA_CR] = ETHTOOL_LINK_MODE_400000baseCR8_Full_BIT,
+			[BNXT_MEDIA_KR] = ETHTOOL_LINK_MODE_400000baseKR8_Full_BIT,
+			[BNXT_MEDIA_SR] = ETHTOOL_LINK_MODE_400000baseSR8_Full_BIT,
+			[BNXT_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_400000baseLR8_ER8_FR8_Full_BIT,
+		},
+		[BNXT_SIG_MODE_PAM4_112] = {
+			[BNXT_MEDIA_CR] = ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT,
+			[BNXT_MEDIA_KR] = ETHTOOL_LINK_MODE_400000baseKR4_Full_BIT,
+			[BNXT_MEDIA_SR] = ETHTOOL_LINK_MODE_400000baseSR4_Full_BIT,
+			[BNXT_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_400000baseLR4_ER4_FR4_Full_BIT,
+		},
 	},
 };
 
@@ -1759,7 +2068,8 @@ static void bnxt_get_ethtool_modes(struct bnxt_link_info *link_info,
 				 lk_ksettings->link_modes.supported);
 	}
 
-	if (link_info->support_auto_speeds || link_info->support_pam4_auto_speeds)
+	if (link_info->support_auto_speeds || link_info->support_auto_speeds2 ||
+	    link_info->support_pam4_auto_speeds)
 		linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
 				 lk_ksettings->link_modes.supported);
 
@@ -1795,22 +2105,60 @@ static const u16 bnxt_pam4_speed_masks[] = {
 	[BNXT_LINK_SPEED_50GB_IDX] = BNXT_LINK_PAM4_SPEED_MSK_50GB,
 	[BNXT_LINK_SPEED_100GB_IDX] = BNXT_LINK_PAM4_SPEED_MSK_100GB,
 	[BNXT_LINK_SPEED_200GB_IDX] = BNXT_LINK_PAM4_SPEED_MSK_200GB,
+	[__BNXT_LINK_SPEED_END - 1] = 0 /* make any legal speed a valid index */
+};
+
+static const u16 bnxt_nrz_speeds2_masks[] = {
+	[BNXT_LINK_SPEED_1GB_IDX] = BNXT_LINK_SPEEDS2_MSK_1GB,
+	[BNXT_LINK_SPEED_10GB_IDX] = BNXT_LINK_SPEEDS2_MSK_10GB,
+	[BNXT_LINK_SPEED_25GB_IDX] = BNXT_LINK_SPEEDS2_MSK_25GB,
+	[BNXT_LINK_SPEED_40GB_IDX] = BNXT_LINK_SPEEDS2_MSK_40GB,
+	[BNXT_LINK_SPEED_50GB_IDX] = BNXT_LINK_SPEEDS2_MSK_50GB,
+	[BNXT_LINK_SPEED_100GB_IDX] = BNXT_LINK_SPEEDS2_MSK_100GB,
+	[__BNXT_LINK_SPEED_END - 1] = 0 /* make any legal speed a valid index */
+};
+
+static const u16 bnxt_pam4_speeds2_masks[] = {
+	[BNXT_LINK_SPEED_50GB_IDX] = BNXT_LINK_SPEEDS2_MSK_50GB_PAM4,
+	[BNXT_LINK_SPEED_100GB_IDX] = BNXT_LINK_SPEEDS2_MSK_100GB_PAM4,
+	[BNXT_LINK_SPEED_200GB_IDX] = BNXT_LINK_SPEEDS2_MSK_200GB_PAM4,
+	[BNXT_LINK_SPEED_400GB_IDX] = BNXT_LINK_SPEEDS2_MSK_400GB_PAM4,
+};
+
+static const u16 bnxt_pam4_112_speeds2_masks[] = {
+	[BNXT_LINK_SPEED_100GB_IDX] = BNXT_LINK_SPEEDS2_MSK_100GB_PAM4_112,
+	[BNXT_LINK_SPEED_200GB_IDX] = BNXT_LINK_SPEEDS2_MSK_200GB_PAM4_112,
+	[BNXT_LINK_SPEED_400GB_IDX] = BNXT_LINK_SPEEDS2_MSK_400GB_PAM4_112,
 };
 
 static enum bnxt_link_speed_indices
-bnxt_encoding_speed_idx(u8 sig_mode, u16 speed_msk)
+bnxt_encoding_speed_idx(u8 sig_mode, u16 phy_flags, u16 speed_msk)
 {
 	const u16 *speeds;
 	int idx, len;
 
 	switch (sig_mode) {
 	case BNXT_SIG_MODE_NRZ:
-		speeds = bnxt_nrz_speed_masks;
-		len = ARRAY_SIZE(bnxt_nrz_speed_masks);
+		if (phy_flags & BNXT_PHY_FL_SPEEDS2) {
+			speeds = bnxt_nrz_speeds2_masks;
+			len = ARRAY_SIZE(bnxt_nrz_speeds2_masks);
+		} else {
+			speeds = bnxt_nrz_speed_masks;
+			len = ARRAY_SIZE(bnxt_nrz_speed_masks);
+		}
 		break;
 	case BNXT_SIG_MODE_PAM4:
-		speeds = bnxt_pam4_speed_masks;
-		len = ARRAY_SIZE(bnxt_pam4_speed_masks);
+		if (phy_flags & BNXT_PHY_FL_SPEEDS2) {
+			speeds = bnxt_pam4_speeds2_masks;
+			len = ARRAY_SIZE(bnxt_pam4_speeds2_masks);
+		} else {
+			speeds = bnxt_pam4_speed_masks;
+			len = ARRAY_SIZE(bnxt_pam4_speed_masks);
+		}
+		break;
+	case BNXT_SIG_MODE_PAM4_112:
+		speeds = bnxt_pam4_112_speeds2_masks;
+		len = ARRAY_SIZE(bnxt_pam4_112_speeds2_masks);
 		break;
 	default:
 		return BNXT_LINK_SPEED_UNKNOWN;
@@ -1828,14 +2176,14 @@ bnxt_encoding_speed_idx(u8 sig_mode, u16 speed_msk)
 
 static void
 __bnxt_get_ethtool_speeds(unsigned long fw_mask, enum bnxt_media_type media,
-			  u8 sig_mode, unsigned long *et_mask)
+			  u8 sig_mode, u16 phy_flags, unsigned long *et_mask)
 {
 	enum ethtool_link_mode_bit_indices link_mode;
 	enum bnxt_link_speed_indices speed;
 	u8 bit;
 
 	for_each_set_bit(bit, &fw_mask, BNXT_FW_SPEED_MSK_BITS) {
-		speed = bnxt_encoding_speed_idx(sig_mode, 1 << bit);
+		speed = bnxt_encoding_speed_idx(sig_mode, phy_flags, 1 << bit);
 		if (!speed)
 			continue;
 
@@ -1849,16 +2197,83 @@ __bnxt_get_ethtool_speeds(unsigned long fw_mask, enum bnxt_media_type media,
 
 static void
 bnxt_get_ethtool_speeds(unsigned long fw_mask, enum bnxt_media_type media,
-			u8 sig_mode, unsigned long *et_mask)
+			u8 sig_mode, u16 phy_flags, unsigned long *et_mask)
 {
 	if (media) {
-		__bnxt_get_ethtool_speeds(fw_mask, media, sig_mode, et_mask);
+		__bnxt_get_ethtool_speeds(fw_mask, media, sig_mode, phy_flags,
+					  et_mask);
 		return;
 	}
 
 	/* list speeds for all media if unknown */
 	for (media = 1; media < __BNXT_MEDIA_END; media++)
-		__bnxt_get_ethtool_speeds(fw_mask, media, sig_mode, et_mask);
+		__bnxt_get_ethtool_speeds(fw_mask, media, sig_mode, phy_flags,
+					  et_mask);
+}
+
+static void
+bnxt_get_all_ethtool_support_speeds(struct bnxt_link_info *link_info,
+				    enum bnxt_media_type media,
+				    struct ethtool_link_ksettings *lk_ksettings)
+{
+	struct bnxt *bp = container_of(link_info, struct bnxt, link_info);
+	u16 sp_nrz, sp_pam4, sp_pam4_112 = 0;
+	u16 phy_flags = bp->phy_flags;
+
+	if (phy_flags & BNXT_PHY_FL_SPEEDS2) {
+		sp_nrz = link_info->support_speeds2;
+		sp_pam4 = link_info->support_speeds2;
+		sp_pam4_112 = link_info->support_speeds2;
+	} else {
+		sp_nrz = link_info->support_speeds;
+		sp_pam4 = link_info->support_pam4_speeds;
+	}
+	bnxt_get_ethtool_speeds(sp_nrz, media, BNXT_SIG_MODE_NRZ, phy_flags,
+				lk_ksettings->link_modes.supported);
+	bnxt_get_ethtool_speeds(sp_pam4, media, BNXT_SIG_MODE_PAM4, phy_flags,
+				lk_ksettings->link_modes.supported);
+	bnxt_get_ethtool_speeds(sp_pam4_112, media, BNXT_SIG_MODE_PAM4_112,
+				phy_flags, lk_ksettings->link_modes.supported);
+}
+
+static void
+bnxt_get_all_ethtool_adv_speeds(struct bnxt_link_info *link_info,
+				enum bnxt_media_type media,
+				struct ethtool_link_ksettings *lk_ksettings)
+{
+	struct bnxt *bp = container_of(link_info, struct bnxt, link_info);
+	u16 sp_nrz, sp_pam4, sp_pam4_112 = 0;
+	u16 phy_flags = bp->phy_flags;
+
+	sp_nrz = link_info->advertising;
+	if (phy_flags & BNXT_PHY_FL_SPEEDS2) {
+		sp_pam4 = link_info->advertising;
+		sp_pam4_112 = link_info->advertising;
+	} else {
+		sp_pam4 = link_info->advertising_pam4;
+	}
+	bnxt_get_ethtool_speeds(sp_nrz, media, BNXT_SIG_MODE_NRZ, phy_flags,
+				lk_ksettings->link_modes.advertising);
+	bnxt_get_ethtool_speeds(sp_pam4, media, BNXT_SIG_MODE_PAM4, phy_flags,
+				lk_ksettings->link_modes.advertising);
+	bnxt_get_ethtool_speeds(sp_pam4_112, media, BNXT_SIG_MODE_PAM4_112,
+				phy_flags, lk_ksettings->link_modes.advertising);
+}
+
+static void
+bnxt_get_all_ethtool_lp_speeds(struct bnxt_link_info *link_info,
+			       enum bnxt_media_type media,
+			       struct ethtool_link_ksettings *lk_ksettings)
+{
+	struct bnxt *bp = container_of(link_info, struct bnxt, link_info);
+	u16 phy_flags = bp->phy_flags;
+
+	bnxt_get_ethtool_speeds(link_info->lp_auto_link_speeds, media,
+				BNXT_SIG_MODE_NRZ, phy_flags,
+				lk_ksettings->link_modes.lp_advertising);
+	bnxt_get_ethtool_speeds(link_info->lp_auto_pam4_link_speeds, media,
+				BNXT_SIG_MODE_PAM4, phy_flags,
+				lk_ksettings->link_modes.lp_advertising);
 }
 
 static void bnxt_update_speed(u32 *delta, bool installed_media, u16 *speeds,
@@ -1887,22 +2302,42 @@ static void bnxt_update_speed(u32 *delta, bool installed_media, u16 *speeds,
 static void bnxt_set_ethtool_speeds(struct bnxt_link_info *link_info,
 				    const unsigned long *et_mask)
 {
+	struct bnxt *bp = container_of(link_info, struct bnxt, link_info);
+	u16 const *sp_msks, *sp_pam4_msks, *sp_pam4_112_msks;
 	enum bnxt_media_type media = bnxt_get_media(link_info);
+	u16 *adv, *adv_pam4, *adv_pam4_112 = NULL;
+	u32 delta_pam4_112 = 0;
 	u32 delta_pam4 = 0;
 	u32 delta_nrz = 0;
 	int i, m;
 
+	adv = &link_info->advertising;
+	if (bp->phy_flags & BNXT_PHY_FL_SPEEDS2) {
+		adv_pam4 = &link_info->advertising;
+		adv_pam4_112 = &link_info->advertising;
+		sp_msks = bnxt_nrz_speeds2_masks;
+		sp_pam4_msks = bnxt_pam4_speeds2_masks;
+		sp_pam4_112_msks = bnxt_pam4_112_speeds2_masks;
+	} else {
+		adv_pam4 = &link_info->advertising_pam4;
+		sp_msks = bnxt_nrz_speed_masks;
+		sp_pam4_msks = bnxt_pam4_speed_masks;
+	}
 	for (i = 1; i < __BNXT_LINK_SPEED_END; i++) {
 		/* accept any legal media from user */
 		for (m = 1; m < __BNXT_MEDIA_END; m++) {
 			bnxt_update_speed(&delta_nrz, m == media,
-					  &link_info->advertising,
-					  bnxt_nrz_speed_masks[i], et_mask,
+					  adv, sp_msks[i], et_mask,
 					  bnxt_link_modes[i][BNXT_SIG_MODE_NRZ][m]);
 			bnxt_update_speed(&delta_pam4, m == media,
-					  &link_info->advertising_pam4,
-					  bnxt_pam4_speed_masks[i], et_mask,
+					  adv_pam4, sp_pam4_msks[i], et_mask,
 					  bnxt_link_modes[i][BNXT_SIG_MODE_PAM4][m]);
+			if (!adv_pam4_112)
+				continue;
+
+			bnxt_update_speed(&delta_pam4_112, m == media,
+					  adv_pam4_112, sp_pam4_112_msks[i], et_mask,
+					  bnxt_link_modes[i][BNXT_SIG_MODE_PAM4_112][m]);
 		}
 	}
 }
@@ -1967,11 +2402,20 @@ u32 bnxt_fw_to_ethtool_speed(u16 fw_link_speed)
 	case BNXT_LINK_SPEED_40GB:
 		return SPEED_40000;
 	case BNXT_LINK_SPEED_50GB:
+	case BNXT_LINK_SPEED_50GB_PAM4:
 		return SPEED_50000;
 	case BNXT_LINK_SPEED_100GB:
+	case BNXT_LINK_SPEED_100GB_PAM4:
+	case BNXT_LINK_SPEED_100GB_PAM4_112:
 		return SPEED_100000;
 	case BNXT_LINK_SPEED_200GB:
+	case BNXT_LINK_SPEED_200GB_PAM4:
+	case BNXT_LINK_SPEED_200GB_PAM4_112:
 		return SPEED_200000;
+	case BNXT_LINK_SPEED_400GB:
+	case BNXT_LINK_SPEED_400GB_PAM4:
+	case BNXT_LINK_SPEED_400GB_PAM4_112:
+		return SPEED_400000;
 	default:
 		return SPEED_UNKNOWN;
 	}
@@ -1987,6 +2431,7 @@ static void bnxt_get_default_speeds(struct ethtool_link_ksettings *lk_ksettings,
 		base->duplex = DUPLEX_HALF;
 		if (link_info->duplex & BNXT_LINK_DUPLEX_FULL)
 			base->duplex = DUPLEX_FULL;
+		lk_ksettings->lanes = link_info->active_lanes;
 	} else if (!link_info->autoneg) {
 		base->speed = bnxt_fw_to_ethtool_speed(link_info->req_link_speed);
 		base->duplex = DUPLEX_HALF;
@@ -2014,12 +2459,7 @@ static int bnxt_get_link_ksettings(struct net_device *dev,
 	mutex_lock(&bp->link_lock);
 	bnxt_get_ethtool_modes(link_info, lk_ksettings);
 	media = bnxt_get_media(link_info);
-	bnxt_get_ethtool_speeds(link_info->support_speeds,
-				media, BNXT_SIG_MODE_NRZ,
-				lk_ksettings->link_modes.supported);
-	bnxt_get_ethtool_speeds(link_info->support_pam4_speeds,
-				media, BNXT_SIG_MODE_PAM4,
-				lk_ksettings->link_modes.supported);
+	bnxt_get_all_ethtool_support_speeds(link_info, media, lk_ksettings);
 	bnxt_fw_to_ethtool_support_fec(link_info, lk_ksettings);
 	link_mode = bnxt_get_link_mode(link_info);
 	if (link_mode != BNXT_LINK_MODE_UNKNOWN)
@@ -2032,20 +2472,10 @@ static int bnxt_get_link_ksettings(struct net_device *dev,
 		linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
 				 lk_ksettings->link_modes.advertising);
 		base->autoneg = AUTONEG_ENABLE;
-		bnxt_get_ethtool_speeds(link_info->advertising,
-					media, BNXT_SIG_MODE_NRZ,
-					lk_ksettings->link_modes.advertising);
-		bnxt_get_ethtool_speeds(link_info->advertising_pam4,
-					media, BNXT_SIG_MODE_PAM4,
-					lk_ksettings->link_modes.advertising);
-		if (link_info->phy_link_status == BNXT_LINK_LINK) {
-			bnxt_get_ethtool_speeds(link_info->lp_auto_link_speeds,
-						media, BNXT_SIG_MODE_NRZ,
-						lk_ksettings->link_modes.lp_advertising);
-			bnxt_get_ethtool_speeds(link_info->lp_auto_pam4_link_speeds,
-						media, BNXT_SIG_MODE_PAM4,
-						lk_ksettings->link_modes.lp_advertising);
-		}
+		bnxt_get_all_ethtool_adv_speeds(link_info, media, lk_ksettings);
+		if (link_info->phy_link_status == BNXT_LINK_LINK)
+			bnxt_get_all_ethtool_lp_speeds(link_info, media,
+						       lk_ksettings);
 	} else {
 		base->autoneg = AUTONEG_DISABLE;
 	}
@@ -2080,6 +2510,7 @@ bnxt_force_link_speed(struct net_device *dev, u32 ethtool_speed, u32 lanes)
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_link_info *link_info = &bp->link_info;
 	u16 support_pam4_spds = link_info->support_pam4_speeds;
+	u16 support_spds2 = link_info->support_speeds2;
 	u16 support_spds = link_info->support_speeds;
 	u8 sig_mode = BNXT_SIG_MODE_NRZ;
 	u32 lanes_needed = 1;
@@ -2091,7 +2522,8 @@ bnxt_force_link_speed(struct net_device *dev, u32 ethtool_speed, u32 lanes)
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_100MB;
 		break;
 	case SPEED_1000:
-		if (support_spds & BNXT_LINK_SPEED_MSK_1GB)
+		if ((support_spds & BNXT_LINK_SPEED_MSK_1GB) ||
+		    (support_spds2 & BNXT_LINK_SPEEDS2_MSK_1GB))
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_1GB;
 		break;
 	case SPEED_2500:
@@ -2099,7 +2531,8 @@ bnxt_force_link_speed(struct net_device *dev, u32 ethtool_speed, u32 lanes)
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_2_5GB;
 		break;
 	case SPEED_10000:
-		if (support_spds & BNXT_LINK_SPEED_MSK_10GB)
+		if ((support_spds & BNXT_LINK_SPEED_MSK_10GB) ||
+		    (support_spds2 & BNXT_LINK_SPEEDS2_MSK_10GB))
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10GB;
 		break;
 	case SPEED_20000:
@@ -2109,26 +2542,34 @@ bnxt_force_link_speed(struct net_device *dev, u32 ethtool_speed, u32 lanes)
 		}
 		break;
 	case SPEED_25000:
-		if (support_spds & BNXT_LINK_SPEED_MSK_25GB)
+		if ((support_spds & BNXT_LINK_SPEED_MSK_25GB) ||
+		    (support_spds2 & BNXT_LINK_SPEEDS2_MSK_25GB))
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_25GB;
 		break;
 	case SPEED_40000:
-		if (support_spds & BNXT_LINK_SPEED_MSK_40GB) {
+		if ((support_spds & BNXT_LINK_SPEED_MSK_40GB) ||
+		    (support_spds2 & BNXT_LINK_SPEEDS2_MSK_40GB)) {
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_40GB;
 			lanes_needed = 4;
 		}
 		break;
 	case SPEED_50000:
-		if ((support_spds & BNXT_LINK_SPEED_MSK_50GB) && lanes != 1) {
+		if (((support_spds & BNXT_LINK_SPEED_MSK_50GB) ||
+		     (support_spds2 & BNXT_LINK_SPEEDS2_MSK_50GB)) &&
+		    lanes != 1) {
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_50GB;
 			lanes_needed = 2;
 		} else if (support_pam4_spds & BNXT_LINK_PAM4_SPEED_MSK_50GB) {
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_50GB;
 			sig_mode = BNXT_SIG_MODE_PAM4;
+		} else if (support_spds2 & BNXT_LINK_SPEEDS2_MSK_50GB_PAM4) {
+			fw_speed = BNXT_LINK_SPEED_50GB_PAM4;
+			sig_mode = BNXT_SIG_MODE_PAM4;
 		}
 		break;
 	case SPEED_100000:
-		if ((support_spds & BNXT_LINK_SPEED_MSK_100GB) &&
+		if (((support_spds & BNXT_LINK_SPEED_MSK_100GB) ||
+		     (support_spds2 & BNXT_LINK_SPEEDS2_MSK_100GB)) &&
 		    lanes != 2 && lanes != 1) {
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_100GB;
 			lanes_needed = 4;
@@ -2136,6 +2577,14 @@ bnxt_force_link_speed(struct net_device *dev, u32 ethtool_speed, u32 lanes)
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_100GB;
 			sig_mode = BNXT_SIG_MODE_PAM4;
 			lanes_needed = 2;
+		} else if ((support_spds2 & BNXT_LINK_SPEEDS2_MSK_100GB_PAM4) &&
+			   lanes != 1) {
+			fw_speed = BNXT_LINK_SPEED_100GB_PAM4;
+			sig_mode = BNXT_SIG_MODE_PAM4;
+			lanes_needed = 2;
+		} else if (support_spds2 & BNXT_LINK_SPEEDS2_MSK_100GB_PAM4_112) {
+			fw_speed = BNXT_LINK_SPEED_100GB_PAM4_112;
+			sig_mode = BNXT_SIG_MODE_PAM4_112;
 		}
 		break;
 	case SPEED_200000:
@@ -2143,6 +2592,27 @@ bnxt_force_link_speed(struct net_device *dev, u32 ethtool_speed, u32 lanes)
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_200GB;
 			sig_mode = BNXT_SIG_MODE_PAM4;
 			lanes_needed = 4;
+		} else if ((support_spds2 & BNXT_LINK_SPEEDS2_MSK_200GB_PAM4) &&
+			   lanes != 2) {
+			fw_speed = BNXT_LINK_SPEED_200GB_PAM4;
+			sig_mode = BNXT_SIG_MODE_PAM4;
+			lanes_needed = 4;
+		} else if (support_spds2 & BNXT_LINK_SPEEDS2_MSK_200GB_PAM4_112) {
+			fw_speed = BNXT_LINK_SPEED_200GB_PAM4_112;
+			sig_mode = BNXT_SIG_MODE_PAM4_112;
+			lanes_needed = 2;
+		}
+		break;
+	case SPEED_400000:
+		if ((support_spds2 & BNXT_LINK_SPEEDS2_MSK_400GB_PAM4) &&
+		    lanes != 4) {
+			fw_speed = BNXT_LINK_SPEED_400GB_PAM4;
+			sig_mode = BNXT_SIG_MODE_PAM4;
+			lanes_needed = 8;
+		} else if (support_spds2 & BNXT_LINK_SPEEDS2_MSK_400GB_PAM4_112) {
+			fw_speed = BNXT_LINK_SPEED_400GB_PAM4_112;
+			sig_mode = BNXT_SIG_MODE_PAM4_112;
+			lanes_needed = 4;
 		}
 		break;
 	}
@@ -3916,7 +4386,8 @@ static int bnxt_poll_loopback(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		 * reading any further.
 		 */
 		dma_rmb();
-		if (TX_CMP_TYPE(txcmp) == CMP_TYPE_RX_L2_CMP) {
+		if (TX_CMP_TYPE(txcmp) == CMP_TYPE_RX_L2_CMP ||
+		    TX_CMP_TYPE(txcmp) == CMP_TYPE_RX_L2_V3_CMP) {
 			rc = bnxt_rx_loopback(bp, cpr, raw_cons, pkt_size);
 			raw_cons = NEXT_RAW_CMP(raw_cons);
 			raw_cons = NEXT_RAW_CMP(raw_cons);
@@ -3940,8 +4411,8 @@ static int bnxt_run_loopback(struct bnxt *bp)
 	int rc;
 
 	cpr = &rxr->bnapi->cp_ring;
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
-		cpr = cpr->cp_ring_arr[BNXT_RX_HDL];
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
+		cpr = rxr->rx_cpr;
 	pkt_size = min(bp->dev->mtu + ETH_HLEN, bp->rx_copy_thresh);
 	skb = netdev_alloc_skb(bp->dev, pkt_size);
 	if (!skb)
@@ -4042,12 +4513,7 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 		bnxt_run_fw_tests(bp, test_mask, &test_results);
 	} else {
 		bnxt_ulp_stop(bp);
-		rc = bnxt_close_nic(bp, true, false);
-		if (rc) {
-			etest->flags |= ETH_TEST_FL_FAILED;
-			bnxt_ulp_start(bp, rc);
-			return;
-		}
+		bnxt_close_nic(bp, true, false);
 		bnxt_run_fw_tests(bp, test_mask, &test_results);
 
 		buf[BNXT_MACLPBK_TEST_IDX] = 1;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index d5fad5a3cdd1..e957abd704db 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -40,6 +40,8 @@ struct hwrm_resp_hdr {
 #define TLV_TYPE_ROCE_SP_COMMAND                 0x3UL
 #define TLV_TYPE_QUERY_ROCE_CC_GEN1              0x4UL
 #define TLV_TYPE_MODIFY_ROCE_CC_GEN1             0x5UL
+#define TLV_TYPE_QUERY_ROCE_CC_GEN2              0x6UL
+#define TLV_TYPE_MODIFY_ROCE_CC_GEN2             0x7UL
 #define TLV_TYPE_ENGINE_CKV_ALIAS_ECC_PUBLIC_KEY 0x8001UL
 #define TLV_TYPE_ENGINE_CKV_IV                   0x8003UL
 #define TLV_TYPE_ENGINE_CKV_AUTH_TAG             0x8004UL
@@ -196,6 +198,9 @@ struct cmd_nums {
 	#define HWRM_QUEUE_ADPTV_QOS_TX_FEATURE_QCFG      0x8aUL
 	#define HWRM_QUEUE_ADPTV_QOS_TX_FEATURE_CFG       0x8bUL
 	#define HWRM_QUEUE_QCAPS                          0x8cUL
+	#define HWRM_QUEUE_ADPTV_QOS_RX_TUNING_QCFG       0x8dUL
+	#define HWRM_QUEUE_ADPTV_QOS_RX_TUNING_CFG        0x8eUL
+	#define HWRM_QUEUE_ADPTV_QOS_TX_TUNING_QCFG       0x8fUL
 	#define HWRM_CFA_L2_FILTER_ALLOC                  0x90UL
 	#define HWRM_CFA_L2_FILTER_FREE                   0x91UL
 	#define HWRM_CFA_L2_FILTER_CFG                    0x92UL
@@ -214,6 +219,7 @@ struct cmd_nums {
 	#define HWRM_TUNNEL_DST_PORT_QUERY                0xa0UL
 	#define HWRM_TUNNEL_DST_PORT_ALLOC                0xa1UL
 	#define HWRM_TUNNEL_DST_PORT_FREE                 0xa2UL
+	#define HWRM_QUEUE_ADPTV_QOS_TX_TUNING_CFG        0xa3UL
 	#define HWRM_STAT_CTX_ENG_QUERY                   0xafUL
 	#define HWRM_STAT_CTX_ALLOC                       0xb0UL
 	#define HWRM_STAT_CTX_FREE                        0xb1UL
@@ -261,6 +267,7 @@ struct cmd_nums {
 	#define HWRM_PORT_EP_TX_CFG                       0xdbUL
 	#define HWRM_PORT_CFG                             0xdcUL
 	#define HWRM_PORT_QCFG                            0xddUL
+	#define HWRM_PORT_MAC_QCAPS                       0xdfUL
 	#define HWRM_TEMP_MONITOR_QUERY                   0xe0UL
 	#define HWRM_REG_POWER_QUERY                      0xe1UL
 	#define HWRM_CORE_FREQUENCY_QUERY                 0xe2UL
@@ -392,6 +399,10 @@ struct cmd_nums {
 	#define HWRM_FUNC_KEY_CTX_FREE                    0x1adUL
 	#define HWRM_FUNC_LAG_MODE_CFG                    0x1aeUL
 	#define HWRM_FUNC_LAG_MODE_QCFG                   0x1afUL
+	#define HWRM_FUNC_LAG_CREATE                      0x1b0UL
+	#define HWRM_FUNC_LAG_UPDATE                      0x1b1UL
+	#define HWRM_FUNC_LAG_FREE                        0x1b2UL
+	#define HWRM_FUNC_LAG_QCFG                        0x1b3UL
 	#define HWRM_SELFTEST_QLIST                       0x200UL
 	#define HWRM_SELFTEST_EXEC                        0x201UL
 	#define HWRM_SELFTEST_IRQ                         0x202UL
@@ -406,9 +417,9 @@ struct cmd_nums {
 	#define HWRM_MFG_FRU_EEPROM_READ                  0x20bUL
 	#define HWRM_MFG_SOC_IMAGE                        0x20cUL
 	#define HWRM_MFG_SOC_QSTATUS                      0x20dUL
-	#define HWRM_MFG_PARAM_SEEPROM_SYNC               0x20eUL
-	#define HWRM_MFG_PARAM_SEEPROM_READ               0x20fUL
-	#define HWRM_MFG_PARAM_SEEPROM_HEALTH             0x210UL
+	#define HWRM_MFG_PARAM_CRITICAL_DATA_FINALIZE     0x20eUL
+	#define HWRM_MFG_PARAM_CRITICAL_DATA_READ         0x20fUL
+	#define HWRM_MFG_PARAM_CRITICAL_DATA_HEALTH       0x210UL
 	#define HWRM_MFG_PRVSN_EXPORT_CSR                 0x211UL
 	#define HWRM_MFG_PRVSN_IMPORT_CERT                0x212UL
 	#define HWRM_MFG_PRVSN_GET_STATE                  0x213UL
@@ -418,6 +429,16 @@ struct cmd_nums {
 	#define HWRM_MFG_SELFTEST_EXEC                    0x217UL
 	#define HWRM_STAT_GENERIC_QSTATS                  0x218UL
 	#define HWRM_MFG_PRVSN_EXPORT_CERT                0x219UL
+	#define HWRM_STAT_DB_ERROR_QSTATS                 0x21aUL
+	#define HWRM_UDCC_QCAPS                           0x258UL
+	#define HWRM_UDCC_CFG                             0x259UL
+	#define HWRM_UDCC_QCFG                            0x25aUL
+	#define HWRM_UDCC_SESSION_CFG                     0x25bUL
+	#define HWRM_UDCC_SESSION_QCFG                    0x25cUL
+	#define HWRM_UDCC_SESSION_QUERY                   0x25dUL
+	#define HWRM_UDCC_COMP_CFG                        0x25eUL
+	#define HWRM_UDCC_COMP_QCFG                       0x25fUL
+	#define HWRM_UDCC_COMP_QUERY                      0x260UL
 	#define HWRM_TF                                   0x2bcUL
 	#define HWRM_TF_VERSION_GET                       0x2bdUL
 	#define HWRM_TF_SESSION_OPEN                      0x2c6UL
@@ -582,9 +603,9 @@ struct hwrm_err_output {
 #define HWRM_TARGET_ID_TOOLS 0xFFFD
 #define HWRM_VERSION_MAJOR 1
 #define HWRM_VERSION_MINOR 10
-#define HWRM_VERSION_UPDATE 2
-#define HWRM_VERSION_RSVD 171
-#define HWRM_VERSION_STR "1.10.2.171"
+#define HWRM_VERSION_UPDATE 3
+#define HWRM_VERSION_RSVD 15
+#define HWRM_VERSION_STR "1.10.3.15"
 
 /* hwrm_ver_get_input (size:192b/24B) */
 struct hwrm_ver_get_input {
@@ -816,7 +837,8 @@ struct hwrm_async_event_cmpl {
 	#define ASYNC_EVENT_CMPL_EVENT_ID_DOORBELL_PACING_NQ_UPDATE       0x48UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_HW_DOORBELL_RECOVERY_READ_ERROR 0x49UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_CTX_ERROR                       0x4aUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID               0x4bUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_UDCC_SESSION_CHANGE             0x4bUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID               0x4cUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG                    0xfeUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR                      0xffUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_LAST                           ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR
@@ -1632,7 +1654,7 @@ struct hwrm_func_qcaps_input {
 	u8	unused_0[6];
 };
 
-/* hwrm_func_qcaps_output (size:896b/112B) */
+/* hwrm_func_qcaps_output (size:1088b/136B) */
 struct hwrm_func_qcaps_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -1736,21 +1758,29 @@ struct hwrm_func_qcaps_output {
 	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_PRIMATE     0x10UL
 	__le16	max_key_ctxs_alloc;
 	__le32	flags_ext2;
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_RX_ALL_PKTS_TIMESTAMPS_SUPPORTED     0x1UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_QUIC_SUPPORTED                       0x2UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_KDNET_SUPPORTED                      0x4UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DBR_PACING_EXT_SUPPORTED             0x8UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SW_DBR_DROP_RECOVERY_SUPPORTED       0x10UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_GENERIC_STATS_SUPPORTED              0x20UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_UDP_GSO_SUPPORTED                    0x40UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SYNCE_SUPPORTED                      0x80UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DBR_PACING_V0_SUPPORTED              0x100UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TX_PKT_TS_CMPL_SUPPORTED             0x200UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_HW_LAG_SUPPORTED                     0x400UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ON_CHIP_CTX_SUPPORTED                0x800UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_STEERING_TAG_SUPPORTED               0x1000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ENHANCED_VF_SCALE_SUPPORTED          0x2000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_KEY_XID_PARTITION_SUPPORTED          0x4000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_RX_ALL_PKTS_TIMESTAMPS_SUPPORTED      0x1UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_QUIC_SUPPORTED                        0x2UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_KDNET_SUPPORTED                       0x4UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DBR_PACING_EXT_SUPPORTED              0x8UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SW_DBR_DROP_RECOVERY_SUPPORTED        0x10UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_GENERIC_STATS_SUPPORTED               0x20UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_UDP_GSO_SUPPORTED                     0x40UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SYNCE_SUPPORTED                       0x80UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DBR_PACING_V0_SUPPORTED               0x100UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TX_PKT_TS_CMPL_SUPPORTED              0x200UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_HW_LAG_SUPPORTED                      0x400UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ON_CHIP_CTX_SUPPORTED                 0x800UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_STEERING_TAG_SUPPORTED                0x1000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ENHANCED_VF_SCALE_SUPPORTED           0x2000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_KEY_XID_PARTITION_SUPPORTED           0x4000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_CONCURRENT_KTLS_QUIC_SUPPORTED        0x8000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SCHQ_CROSS_TC_CAP_SUPPORTED           0x10000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SCHQ_PER_TC_CAP_SUPPORTED             0x20000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SCHQ_PER_TC_RESERVATION_SUPPORTED     0x40000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DB_ERROR_STATS_SUPPORTED              0x80000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ROCE_VF_RESOURCE_MGMT_SUPPORTED       0x100000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_UDCC_SUPPORTED                        0x200000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TIMED_TX_SO_TXTIME_SUPPORTED          0x400000UL
 	__le16	tunnel_disable_flag;
 	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_VXLAN      0x1UL
 	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_NGE        0x2UL
@@ -1760,15 +1790,21 @@ struct hwrm_func_qcaps_output {
 	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_IPINIP     0x20UL
 	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_MPLS       0x40UL
 	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_PPPOE      0x80UL
-	u8	key_xid_partition_cap;
-	#define FUNC_QCAPS_RESP_KEY_XID_PARTITION_CAP_TKC          0x1UL
-	#define FUNC_QCAPS_RESP_KEY_XID_PARTITION_CAP_RKC          0x2UL
-	#define FUNC_QCAPS_RESP_KEY_XID_PARTITION_CAP_QUIC_TKC     0x4UL
-	#define FUNC_QCAPS_RESP_KEY_XID_PARTITION_CAP_QUIC_RKC     0x8UL
-	u8	unused_1;
+	__le16	xid_partition_cap;
+	#define FUNC_QCAPS_RESP_XID_PARTITION_CAP_KTLS_TKC     0x1UL
+	#define FUNC_QCAPS_RESP_XID_PARTITION_CAP_KTLS_RKC     0x2UL
+	#define FUNC_QCAPS_RESP_XID_PARTITION_CAP_QUIC_TKC     0x4UL
+	#define FUNC_QCAPS_RESP_XID_PARTITION_CAP_QUIC_RKC     0x8UL
 	u8	device_serial_number[8];
 	__le16	ctxs_per_partition;
-	u8	unused_2[5];
+	u8	unused_2[2];
+	__le32	roce_vf_max_av;
+	__le32	roce_vf_max_cq;
+	__le32	roce_vf_max_mrw;
+	__le32	roce_vf_max_qp;
+	__le32	roce_vf_max_srq;
+	__le32	roce_vf_max_gid;
+	u8	unused_3[3];
 	u8	valid;
 };
 
@@ -1783,7 +1819,7 @@ struct hwrm_func_qcfg_input {
 	u8	unused_0[6];
 };
 
-/* hwrm_func_qcfg_output (size:1024b/128B) */
+/* hwrm_func_qcfg_output (size:1280b/160B) */
 struct hwrm_func_qcfg_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -1892,7 +1928,7 @@ struct hwrm_func_qcfg_output {
 	__le16	alloc_msix;
 	__le16	registered_vfs;
 	__le16	l2_doorbell_bar_size_kb;
-	u8	unused_1;
+	u8	active_endpoints;
 	u8	always_1;
 	__le32	reset_addr_poll;
 	__le16	legacy_l2_db_size_kb;
@@ -1952,15 +1988,26 @@ struct hwrm_func_qcfg_output {
 	u8	kdnet_pcie_function;
 	__le16	port_kdnet_fid;
 	u8	unused_5[2];
-	__le32	alloc_tx_key_ctxs;
-	__le32	alloc_rx_key_ctxs;
+	__le32	num_ktls_tx_key_ctxs;
+	__le32	num_ktls_rx_key_ctxs;
 	u8	lag_id;
 	u8	parif;
-	u8	unused_6[5];
+	u8	fw_lag_id;
+	u8	unused_6;
+	__le32	num_quic_tx_key_ctxs;
+	__le32	num_quic_rx_key_ctxs;
+	__le32	roce_max_av_per_vf;
+	__le32	roce_max_cq_per_vf;
+	__le32	roce_max_mrw_per_vf;
+	__le32	roce_max_qp_per_vf;
+	__le32	roce_max_srq_per_vf;
+	__le32	roce_max_gid_per_vf;
+	__le16	xid_partition_cfg;
+	u8	unused_7;
 	u8	valid;
 };
 
-/* hwrm_func_cfg_input (size:1088b/136B) */
+/* hwrm_func_cfg_input (size:1280b/160B) */
 struct hwrm_func_cfg_input {
 	__le16	req_type;
 	__le16	cmpl_ring;
@@ -1996,7 +2043,6 @@ struct hwrm_func_cfg_input {
 	#define FUNC_CFG_REQ_FLAGS_PPP_PUSH_MODE_DISABLE          0x10000000UL
 	#define FUNC_CFG_REQ_FLAGS_BD_METADATA_ENABLE             0x20000000UL
 	#define FUNC_CFG_REQ_FLAGS_BD_METADATA_DISABLE            0x40000000UL
-	#define FUNC_CFG_REQ_FLAGS_KEY_CTX_ASSETS_TEST            0x80000000UL
 	__le32	enables;
 	#define FUNC_CFG_REQ_ENABLES_ADMIN_MTU                0x1UL
 	#define FUNC_CFG_REQ_ENABLES_MRU                      0x2UL
@@ -2028,8 +2074,8 @@ struct hwrm_func_cfg_input {
 	#define FUNC_CFG_REQ_ENABLES_PARTITION_MAX_BW         0x8000000UL
 	#define FUNC_CFG_REQ_ENABLES_TPID                     0x10000000UL
 	#define FUNC_CFG_REQ_ENABLES_HOST_MTU                 0x20000000UL
-	#define FUNC_CFG_REQ_ENABLES_TX_KEY_CTXS              0x40000000UL
-	#define FUNC_CFG_REQ_ENABLES_RX_KEY_CTXS              0x80000000UL
+	#define FUNC_CFG_REQ_ENABLES_KTLS_TX_KEY_CTXS         0x40000000UL
+	#define FUNC_CFG_REQ_ENABLES_KTLS_RX_KEY_CTXS         0x80000000UL
 	__le16	admin_mtu;
 	__le16	mru;
 	__le16	num_rsscos_ctxs;
@@ -2139,10 +2185,21 @@ struct hwrm_func_cfg_input {
 	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_LAST         FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100
 	__be16	tpid;
 	__le16	host_mtu;
-	u8	unused_0[4];
+	__le32	flags2;
+	#define FUNC_CFG_REQ_FLAGS2_KTLS_KEY_CTX_ASSETS_TEST     0x1UL
+	#define FUNC_CFG_REQ_FLAGS2_QUIC_KEY_CTX_ASSETS_TEST     0x2UL
 	__le32	enables2;
-	#define FUNC_CFG_REQ_ENABLES2_KDNET            0x1UL
-	#define FUNC_CFG_REQ_ENABLES2_DB_PAGE_SIZE     0x2UL
+	#define FUNC_CFG_REQ_ENABLES2_KDNET                   0x1UL
+	#define FUNC_CFG_REQ_ENABLES2_DB_PAGE_SIZE            0x2UL
+	#define FUNC_CFG_REQ_ENABLES2_QUIC_TX_KEY_CTXS        0x4UL
+	#define FUNC_CFG_REQ_ENABLES2_QUIC_RX_KEY_CTXS        0x8UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_AV_PER_VF      0x10UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_CQ_PER_VF      0x20UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_MRW_PER_VF     0x40UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_QP_PER_VF      0x80UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_SRQ_PER_VF     0x100UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_GID_PER_VF     0x200UL
+	#define FUNC_CFG_REQ_ENABLES2_XID_PARTITION_CFG       0x400UL
 	u8	port_kdnet_mode;
 	#define FUNC_CFG_REQ_PORT_KDNET_MODE_DISABLED 0x0UL
 	#define FUNC_CFG_REQ_PORT_KDNET_MODE_ENABLED  0x1UL
@@ -2165,7 +2222,18 @@ struct hwrm_func_cfg_input {
 	__le32	num_ktls_rx_key_ctxs;
 	__le32	num_quic_tx_key_ctxs;
 	__le32	num_quic_rx_key_ctxs;
-	__le32	unused_2;
+	__le32	roce_max_av_per_vf;
+	__le32	roce_max_cq_per_vf;
+	__le32	roce_max_mrw_per_vf;
+	__le32	roce_max_qp_per_vf;
+	__le32	roce_max_srq_per_vf;
+	__le32	roce_max_gid_per_vf;
+	__le16	xid_partition_cfg;
+	#define FUNC_CFG_REQ_XID_PARTITION_CFG_KTLS_TKC     0x1UL
+	#define FUNC_CFG_REQ_XID_PARTITION_CFG_KTLS_RKC     0x2UL
+	#define FUNC_CFG_REQ_XID_PARTITION_CFG_QUIC_TKC     0x4UL
+	#define FUNC_CFG_REQ_XID_PARTITION_CFG_QUIC_RKC     0x8UL
+	__le16	unused_2;
 };
 
 /* hwrm_func_cfg_output (size:128b/16B) */
@@ -2604,7 +2672,7 @@ struct hwrm_func_vf_resource_cfg_input {
 	__le32	max_quic_rx_key_ctxs;
 };
 
-/* hwrm_func_vf_resource_cfg_output (size:320b/40B) */
+/* hwrm_func_vf_resource_cfg_output (size:384b/48B) */
 struct hwrm_func_vf_resource_cfg_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -2618,8 +2686,10 @@ struct hwrm_func_vf_resource_cfg_output {
 	__le16	reserved_vnics;
 	__le16	reserved_stat_ctx;
 	__le16	reserved_hw_ring_grps;
-	__le32	reserved_tx_key_ctxs;
-	__le32	reserved_rx_key_ctxs;
+	__le32	reserved_ktls_tx_key_ctxs;
+	__le32	reserved_ktls_rx_key_ctxs;
+	__le32	reserved_quic_tx_key_ctxs;
+	__le32	reserved_quic_rx_key_ctxs;
 	u8	unused_0[7];
 	u8	valid;
 };
@@ -3441,7 +3511,8 @@ struct hwrm_func_ptp_cfg_input {
 	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_4K   0x1UL
 	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_8K   0x2UL
 	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_10M  0x3UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_LAST FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_10M
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_25M  0x4UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_LAST FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_25M
 	u8	unused_0[3];
 	__le32	ptp_freq_adj_ext_period;
 	__le32	ptp_freq_adj_ext_up;
@@ -3627,28 +3698,28 @@ struct hwrm_func_backing_store_qcfg_v2_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	__le16	type;
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_QP            0x0UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRQ           0x1UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CQ            0x2UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_VNIC          0x3UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_STAT          0x4UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SP_TQM_RING   0x5UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_FP_TQM_RING   0x6UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MRAV          0xeUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TIM           0xfUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TKC           0x13UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RKC           0x14UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MP_TQM_RING   0x15UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SQ_DB_SHADOW  0x16UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RQ_DB_SHADOW  0x17UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRQ_DB_SHADOW 0x18UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CQ_DB_SHADOW  0x19UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_QUIC_TKC      0x1aUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_QUIC_RKC      0x1bUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TBL_SCOPE     0x1cUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_XID_PARTITION 0x1dUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID       0xffffUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_LAST         FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_QP                  0x0UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRQ                 0x1UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CQ                  0x2UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_VNIC                0x3UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_STAT                0x4UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SP_TQM_RING         0x5UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_FP_TQM_RING         0x6UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MRAV                0xeUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TIM                 0xfUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TKC                 0x13UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RKC                 0x14UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MP_TQM_RING         0x15UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SQ_DB_SHADOW        0x16UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RQ_DB_SHADOW        0x17UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRQ_DB_SHADOW       0x18UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CQ_DB_SHADOW        0x19UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_QUIC_TKC            0x1aUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_QUIC_RKC            0x1bUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TBL_SCOPE           0x1cUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_XID_PARTITION_TABLE 0x1dUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID             0xffffUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_LAST               FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID
 	__le16	instance;
 	u8	rsvd[4];
 };
@@ -3744,6 +3815,15 @@ struct mrav_split_entries {
 	__le32	rsvd2[2];
 };
 
+/* ts_split_entries (size:128b/16B) */
+struct ts_split_entries {
+	__le32	region_num_entries;
+	u8	tsid;
+	u8	lkup_static_bkt_cnt_exp[2];
+	u8	rsvd;
+	__le32	rsvd2[2];
+};
+
 /* hwrm_func_backing_store_qcaps_v2_input (size:192b/24B) */
 struct hwrm_func_backing_store_qcaps_v2_input {
 	__le16	req_type;
@@ -3761,8 +3841,8 @@ struct hwrm_func_backing_store_qcaps_v2_input {
 	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING   0x6UL
 	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV          0xeUL
 	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM           0xfUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TKC           0x13UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RKC           0x14UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_KTLS_TKC      0x13UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_KTLS_RKC      0x14UL
 	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING   0x15UL
 	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SQ_DB_SHADOW  0x16UL
 	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RQ_DB_SHADOW  0x17UL
@@ -3793,8 +3873,8 @@ struct hwrm_func_backing_store_qcaps_v2_output {
 	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_FP_TQM_RING   0x6UL
 	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MRAV          0xeUL
 	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TIM           0xfUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TKC           0x13UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RKC           0x14UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_KTLS_TKC      0x13UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_KTLS_RKC      0x14UL
 	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MP_TQM_RING   0x15UL
 	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SQ_DB_SHADOW  0x16UL
 	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RQ_DB_SHADOW  0x17UL
@@ -3838,56 +3918,55 @@ struct hwrm_func_backing_store_qcaps_v2_output {
 
 /* hwrm_func_dbr_pacing_qcfg_input (size:128b/16B) */
 struct hwrm_func_dbr_pacing_qcfg_input {
-	__le16  req_type;
-	__le16  cmpl_ring;
-	__le16  seq_id;
-	__le16  target_id;
-	__le64  resp_addr;
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
 };
 
 /* hwrm_func_dbr_pacing_qcfg_output (size:512b/64B) */
 struct hwrm_func_dbr_pacing_qcfg_output {
-	__le16  error_code;
-	__le16  req_type;
-	__le16  seq_id;
-	__le16  resp_len;
-	u8      flags;
-#define FUNC_DBR_PACING_QCFG_RESP_FLAGS_DBR_NQ_EVENT_ENABLED     0x1UL
-	u8      unused_0[7];
-	__le32  dbr_stat_db_fifo_reg;
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_MASK    0x3UL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_SFT     0
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_PCIE_CFG  0x0UL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_GRC       0x1UL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR0      0x2UL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR1      0x3UL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_LAST     \
-		FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR1
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_MASK          0xfffffffcUL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SFT           2
-	__le32  dbr_stat_db_fifo_reg_watermark_mask;
-	u8      dbr_stat_db_fifo_reg_watermark_shift;
-	u8      unused_1[3];
-	__le32  dbr_stat_db_fifo_reg_fifo_room_mask;
-	u8      dbr_stat_db_fifo_reg_fifo_room_shift;
-	u8      unused_2[3];
-	__le32  dbr_throttling_aeq_arm_reg;
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_MASK    0x3UL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_SFT     0
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_PCIE_CFG  0x0UL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_GRC       0x1UL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR0      0x2UL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR1      0x3UL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_LAST	\
-		FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR1
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_MASK          0xfffffffcUL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SFT           2
-	u8      dbr_throttling_aeq_arm_reg_val;
-	u8      unused_3[7];
-	__le32  primary_nq_id;
-	__le32  pacing_threshold;
-	u8      unused_4[7];
-	u8      valid;
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define FUNC_DBR_PACING_QCFG_RESP_FLAGS_DBR_NQ_EVENT_ENABLED     0x1UL
+	u8	unused_0[7];
+	__le32	dbr_stat_db_fifo_reg;
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_MASK    0x3UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_SFT     0
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_GRC       0x1UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR0      0x2UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR1      0x3UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_LAST     FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR1
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_MASK          0xfffffffcUL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SFT           2
+	__le32	dbr_stat_db_fifo_reg_watermark_mask;
+	u8	dbr_stat_db_fifo_reg_watermark_shift;
+	u8	unused_1[3];
+	__le32	dbr_stat_db_fifo_reg_fifo_room_mask;
+	u8	dbr_stat_db_fifo_reg_fifo_room_shift;
+	u8	unused_2[3];
+	__le32	dbr_throttling_aeq_arm_reg;
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_MASK    0x3UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_SFT     0
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_GRC       0x1UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR0      0x2UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR1      0x3UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_LAST     FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR1
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_MASK          0xfffffffcUL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SFT           2
+	u8	dbr_throttling_aeq_arm_reg_val;
+	u8	unused_3[3];
+	__le32	dbr_stat_db_max_fifo_depth;
+	__le32	primary_nq_id;
+	__le32	pacing_threshold;
+	u8	unused_4[7];
+	u8	valid;
 };
 
 /* hwrm_func_drv_if_change_input (size:192b/24B) */
@@ -3915,7 +3994,7 @@ struct hwrm_func_drv_if_change_output {
 	u8	valid;
 };
 
-/* hwrm_port_phy_cfg_input (size:448b/56B) */
+/* hwrm_port_phy_cfg_input (size:512b/64B) */
 struct hwrm_port_phy_cfg_input {
 	__le16	req_type;
 	__le16	cmpl_ring;
@@ -3960,6 +4039,8 @@ struct hwrm_port_phy_cfg_input {
 	#define PORT_PHY_CFG_REQ_ENABLES_TX_LPI_TIMER                  0x400UL
 	#define PORT_PHY_CFG_REQ_ENABLES_FORCE_PAM4_LINK_SPEED         0x800UL
 	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_PAM4_LINK_SPEED_MASK     0x1000UL
+	#define PORT_PHY_CFG_REQ_ENABLES_FORCE_LINK_SPEEDS2            0x2000UL
+	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEEDS2_MASK        0x4000UL
 	__le16	port_id;
 	__le16	force_link_speed;
 	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_100MB 0x1UL
@@ -3990,7 +4071,9 @@ struct hwrm_port_phy_cfg_input {
 	#define PORT_PHY_CFG_REQ_AUTO_PAUSE_TX                0x1UL
 	#define PORT_PHY_CFG_REQ_AUTO_PAUSE_RX                0x2UL
 	#define PORT_PHY_CFG_REQ_AUTO_PAUSE_AUTONEG_PAUSE     0x4UL
-	u8	unused_0;
+	u8	mgmt_flag;
+	#define PORT_PHY_CFG_REQ_MGMT_FLAG_LINK_RELEASE     0x1UL
+	#define PORT_PHY_CFG_REQ_MGMT_FLAG_MGMT_VALID       0x80UL
 	__le16	auto_link_speed;
 	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_100MB 0x1UL
 	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_1GB   0xaUL
@@ -4054,7 +4137,36 @@ struct hwrm_port_phy_cfg_input {
 	#define PORT_PHY_CFG_REQ_AUTO_LINK_PAM4_SPEED_MASK_50G      0x1UL
 	#define PORT_PHY_CFG_REQ_AUTO_LINK_PAM4_SPEED_MASK_100G     0x2UL
 	#define PORT_PHY_CFG_REQ_AUTO_LINK_PAM4_SPEED_MASK_200G     0x4UL
-	u8	unused_2[2];
+	__le16	force_link_speeds2;
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_1GB            0xaUL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_10GB           0x64UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_25GB           0xfaUL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_40GB           0x190UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_50GB           0x1f4UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB          0x3e8UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_50GB_PAM4_56   0x1f5UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB_PAM4_56  0x3e9UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_200GB_PAM4_56  0x7d1UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_56  0xfa1UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB_PAM4_112 0x3eaUL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_200GB_PAM4_112 0x7d2UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_112 0xfa2UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_LAST          PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_112
+	__le16	auto_link_speeds2_mask;
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_1GB                0x1UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_10GB               0x2UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_25GB               0x4UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_40GB               0x8UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_50GB               0x10UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_100GB              0x20UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_50GB_PAM4_56       0x40UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_100GB_PAM4_56      0x80UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_200GB_PAM4_56      0x100UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_400GB_PAM4_56      0x200UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_100GB_PAM4_112     0x400UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_200GB_PAM4_112     0x800UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_400GB_PAM4_112     0x1000UL
+	u8	unused_2[6];
 };
 
 /* hwrm_port_phy_cfg_output (size:128b/16B) */
@@ -4104,7 +4216,8 @@ struct hwrm_port_phy_qcfg_output {
 	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_SFT                 0
 	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_NRZ                   0x0UL
 	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4                  0x1UL
-	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_LAST                 PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4
+	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4_112              0x2UL
+	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_LAST                 PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4_112
 	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_MASK                 0xf0UL
 	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_SFT                  4
 	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_NONE_ACTIVE        (0x0UL << 4)
@@ -4127,6 +4240,7 @@ struct hwrm_port_phy_qcfg_output {
 	#define PORT_PHY_QCFG_RESP_LINK_SPEED_50GB  0x1f4UL
 	#define PORT_PHY_QCFG_RESP_LINK_SPEED_100GB 0x3e8UL
 	#define PORT_PHY_QCFG_RESP_LINK_SPEED_200GB 0x7d0UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_400GB 0xfa0UL
 	#define PORT_PHY_QCFG_RESP_LINK_SPEED_10MB  0xffffUL
 	#define PORT_PHY_QCFG_RESP_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_LINK_SPEED_10MB
 	u8	duplex_cfg;
@@ -4270,7 +4384,23 @@ struct hwrm_port_phy_qcfg_output {
 	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR2     0x25UL
 	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR2     0x26UL
 	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER2     0x27UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_LAST            PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER2
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR      0x28UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR      0x29UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR      0x2aUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER      0x2bUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASECR2     0x2cUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASESR2     0x2dUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASELR2     0x2eUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASEER2     0x2fUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASECR8     0x30UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASESR8     0x31UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASELR8     0x32UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER8     0x33UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASECR4     0x34UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASESR4     0x35UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASELR4     0x36UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER4     0x37UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_LAST            PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER4
 	u8	media_type;
 	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_UNKNOWN 0x0UL
 	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP      0x1UL
@@ -4366,6 +4496,7 @@ struct hwrm_port_phy_qcfg_output {
 	u8	option_flags;
 	#define PORT_PHY_QCFG_RESP_OPTION_FLAGS_MEDIA_AUTO_DETECT     0x1UL
 	#define PORT_PHY_QCFG_RESP_OPTION_FLAGS_SIGNAL_MODE_KNOWN     0x2UL
+	#define PORT_PHY_QCFG_RESP_OPTION_FLAGS_SPEEDS2_SUPPORTED     0x4UL
 	char	phy_vendor_name[16];
 	char	phy_vendor_partnumber[16];
 	__le16	support_pam4_speeds;
@@ -4387,7 +4518,53 @@ struct hwrm_port_phy_qcfg_output {
 	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_200GB     0x4UL
 	u8	link_down_reason;
 	#define PORT_PHY_QCFG_RESP_LINK_DOWN_REASON_RF     0x1UL
-	u8	unused_0[7];
+	__le16	support_speeds2;
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_1GB                0x1UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_10GB               0x2UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_25GB               0x4UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_40GB               0x8UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_50GB               0x10UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB              0x20UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_50GB_PAM4_56       0x40UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB_PAM4_56      0x80UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_200GB_PAM4_56      0x100UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_400GB_PAM4_56      0x200UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB_PAM4_112     0x400UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_200GB_PAM4_112     0x800UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_400GB_PAM4_112     0x1000UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_800GB_PAM4_112     0x2000UL
+	__le16	force_link_speeds2;
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_1GB            0xaUL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_10GB           0x64UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_25GB           0xfaUL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_40GB           0x190UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_50GB           0x1f4UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_100GB          0x3e8UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_50GB_PAM4_56   0x1f5UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_100GB_PAM4_56  0x3e9UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_200GB_PAM4_56  0x7d1UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_400GB_PAM4_56  0xfa1UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_100GB_PAM4_112 0x3eaUL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_200GB_PAM4_112 0x7d2UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_400GB_PAM4_112 0xfa2UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_800GB_PAM4_112 0x1f42UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_LAST          PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_800GB_PAM4_112
+	__le16	auto_link_speeds2;
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_1GB                0x1UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_10GB               0x2UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_25GB               0x4UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_40GB               0x8UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_50GB               0x10UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_100GB              0x20UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_50GB_PAM4_56       0x40UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_100GB_PAM4_56      0x80UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_200GB_PAM4_56      0x100UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_400GB_PAM4_56      0x200UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_100GB_PAM4_112     0x400UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_200GB_PAM4_112     0x800UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_400GB_PAM4_112     0x1000UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_800GB_PAM4_112     0x2000UL
+	u8	active_lanes;
 	u8	valid;
 };
 
@@ -4426,6 +4603,7 @@ struct hwrm_port_mac_cfg_input {
 	#define PORT_MAC_CFG_REQ_ENABLES_COS_FIELD_CFG                  0x100UL
 	#define PORT_MAC_CFG_REQ_ENABLES_PTP_FREQ_ADJ_PPB               0x200UL
 	#define PORT_MAC_CFG_REQ_ENABLES_PTP_ADJ_PHASE                  0x400UL
+	#define PORT_MAC_CFG_REQ_ENABLES_PTP_LOAD_CONTROL               0x800UL
 	__le16	port_id;
 	u8	ipg;
 	u8	lpbk;
@@ -4459,7 +4637,12 @@ struct hwrm_port_mac_cfg_input {
 	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_DEFAULT_COS_SFT           5
 	u8	unused_0[3];
 	__le32	ptp_freq_adj_ppb;
-	u8	unused_1[4];
+	u8	unused_1[3];
+	u8	ptp_load_control;
+	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_NONE      0x0UL
+	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_IMMEDIATE 0x1UL
+	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_PPS_EVENT 0x2UL
+	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_LAST     PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_PPS_EVENT
 	__le64	ptp_adj_phase;
 };
 
@@ -4504,6 +4687,7 @@ struct hwrm_port_mac_ptp_qcfg_output {
 	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_HWRM_ACCESS                         0x8UL
 	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_PARTIAL_DIRECT_ACCESS_REF_CLOCK     0x10UL
 	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_RTC_CONFIGURED                      0x20UL
+	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_64B_PHC_TIME                        0x40UL
 	u8	unused_0[3];
 	__le32	rx_ts_reg_off_lower;
 	__le32	rx_ts_reg_off_upper;
@@ -4968,7 +5152,7 @@ struct hwrm_port_phy_qcaps_input {
 	u8	unused_0[6];
 };
 
-/* hwrm_port_phy_qcaps_output (size:256b/32B) */
+/* hwrm_port_phy_qcaps_output (size:320b/40B) */
 struct hwrm_port_phy_qcaps_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -5051,7 +5235,40 @@ struct hwrm_port_phy_qcaps_output {
 	#define PORT_PHY_QCAPS_RESP_FLAGS2_PAUSE_UNSUPPORTED       0x1UL
 	#define PORT_PHY_QCAPS_RESP_FLAGS2_PFC_UNSUPPORTED         0x2UL
 	#define PORT_PHY_QCAPS_RESP_FLAGS2_BANK_ADDR_SUPPORTED     0x4UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS2_SPEEDS2_SUPPORTED       0x8UL
 	u8	internal_port_cnt;
+	u8	unused_0;
+	__le16	supported_speeds2_force_mode;
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_1GB                0x1UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_10GB               0x2UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_25GB               0x4UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_40GB               0x8UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_50GB               0x10UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_100GB              0x20UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_50GB_PAM4_56       0x40UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_100GB_PAM4_56      0x80UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_200GB_PAM4_56      0x100UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_400GB_PAM4_56      0x200UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_100GB_PAM4_112     0x400UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_200GB_PAM4_112     0x800UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_400GB_PAM4_112     0x1000UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_800GB_PAM4_112     0x2000UL
+	__le16	supported_speeds2_auto_mode;
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_1GB                0x1UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_10GB               0x2UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_25GB               0x4UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_40GB               0x8UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_50GB               0x10UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_100GB              0x20UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_50GB_PAM4_56       0x40UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_100GB_PAM4_56      0x80UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_200GB_PAM4_56      0x100UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_400GB_PAM4_56      0x200UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_100GB_PAM4_112     0x400UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_200GB_PAM4_112     0x800UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_400GB_PAM4_112     0x1000UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_800GB_PAM4_112     0x2000UL
+	u8	unused_1[3];
 	u8	valid;
 };
 
@@ -5472,6 +5689,30 @@ struct hwrm_port_led_qcaps_output {
 	u8	valid;
 };
 
+/* hwrm_port_mac_qcaps_input (size:192b/24B) */
+struct hwrm_port_mac_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_port_mac_qcaps_output (size:128b/16B) */
+struct hwrm_port_mac_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define PORT_MAC_QCAPS_RESP_FLAGS_LOCAL_LPBK_NOT_SUPPORTED     0x1UL
+	#define PORT_MAC_QCAPS_RESP_FLAGS_REMOTE_LPBK_SUPPORTED        0x2UL
+	u8	unused_0[6];
+	u8	valid;
+};
+
 /* hwrm_queue_qportcfg_input (size:192b/24B) */
 struct hwrm_queue_qportcfg_input {
 	__le16	req_type;
@@ -7488,7 +7729,7 @@ struct hwrm_cfa_ntuple_filter_alloc_input {
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_RSVD    0xffUL
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_LAST   CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_RSVD
 	__le16	dst_id;
-	__le16	mirror_vnic_id;
+	__le16	rfs_ring_tbl_idx;
 	u8	tunnel_type;
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
@@ -8201,6 +8442,7 @@ struct hwrm_cfa_adv_flow_mgnt_qcaps_output {
 	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_NO_L2CTX_SUPPORTED               0x40000UL
 	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NIC_FLOW_STATS_SUPPORTED                     0x80000UL
 	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_RX_EXT_IP_PROTO_SUPPORTED        0x100000UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_RFS_RING_TBL_IDX_V3_SUPPORTED                0x200000UL
 	u8	unused_0[3];
 	u8	valid;
 };
@@ -8223,7 +8465,8 @@ struct hwrm_tunnel_dst_port_query_input {
 	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ECPRI        0xeUL
 	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_SRV6         0xfUL
 	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST        TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GRE          0x11UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST        TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GRE
 	u8	tunnel_next_proto;
 	u8	unused_0[6];
 };
@@ -8245,7 +8488,10 @@ struct hwrm_tunnel_dst_port_query_output {
 	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR5     0x20UL
 	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR6     0x40UL
 	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR7     0x80UL
-	u8	unused_0[2];
+	u8	status;
+	#define TUNNEL_DST_PORT_QUERY_RESP_STATUS_CHIP_LEVEL     0x1UL
+	#define TUNNEL_DST_PORT_QUERY_RESP_STATUS_FUNC_LEVEL     0x2UL
+	u8	unused_0;
 	u8	valid;
 };
 
@@ -8267,7 +8513,8 @@ struct hwrm_tunnel_dst_port_alloc_input {
 	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ECPRI        0xeUL
 	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_SRV6         0xfUL
 	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST        TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GRE          0x11UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST        TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GRE
 	u8	tunnel_next_proto;
 	__be16	tunnel_dst_port_val;
 	u8	unused_0[4];
@@ -8284,7 +8531,8 @@ struct hwrm_tunnel_dst_port_alloc_output {
 	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_SUCCESS         0x0UL
 	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_ALLOCATED   0x1UL
 	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_NO_RESOURCE 0x2UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_LAST           TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_NO_RESOURCE
+	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_ENABLED     0x3UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_LAST           TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_ENABLED
 	u8	upar_in_use;
 	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR0     0x1UL
 	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR1     0x2UL
@@ -8316,7 +8564,8 @@ struct hwrm_tunnel_dst_port_free_input {
 	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ECPRI        0xeUL
 	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_SRV6         0xfUL
 	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST        TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GRE          0x11UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST        TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GRE
 	u8	tunnel_next_proto;
 	__le16	tunnel_dst_port_id;
 	u8	unused_0[4];
@@ -9717,7 +9966,7 @@ struct hwrm_nvm_get_dev_info_input {
 	__le64	resp_addr;
 };
 
-/* hwrm_nvm_get_dev_info_output (size:640b/80B) */
+/* hwrm_nvm_get_dev_info_output (size:704b/88B) */
 struct hwrm_nvm_get_dev_info_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -9747,6 +9996,10 @@ struct hwrm_nvm_get_dev_info_output {
 	__le16	roce_fw_minor;
 	__le16	roce_fw_build;
 	__le16	roce_fw_patch;
+	__le16	netctrl_fw_major;
+	__le16	netctrl_fw_minor;
+	__le16	netctrl_fw_build;
+	__le16	netctrl_fw_patch;
 	u8	unused_0[7];
 	u8	valid;
 };
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index f3886710e778..adad188e38b8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -129,7 +129,7 @@ static int bnxt_hwrm_port_ts_query(struct bnxt *bp, u32 flags, u64 *ts)
 	}
 	resp = hwrm_req_hold(bp, req);
 
-	rc = hwrm_req_send(bp, req);
+	rc = hwrm_req_send_silent(bp, req);
 	if (!rc)
 		*ts = le64_to_cpu(resp->ptp_msg_ts);
 	hwrm_req_drop(bp, req);
@@ -319,15 +319,17 @@ static int bnxt_ptp_cfg_event(struct bnxt *bp, u8 event)
 	return hwrm_req_send(bp, req);
 }
 
-void bnxt_ptp_cfg_tstamp_filters(struct bnxt *bp)
+int bnxt_ptp_cfg_tstamp_filters(struct bnxt *bp)
 {
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
 	struct hwrm_port_mac_cfg_input *req;
+	int rc;
 
 	if (!ptp || !ptp->tstamp_filters)
-		return;
+		return -EIO;
 
-	if (hwrm_req_init(bp, req, HWRM_PORT_MAC_CFG))
+	rc = hwrm_req_init(bp, req, HWRM_PORT_MAC_CFG);
+	if (rc)
 		goto out;
 
 	if (!(bp->fw_cap & BNXT_FW_CAP_RX_ALL_PKT_TS) && (ptp->tstamp_filters &
@@ -342,15 +344,17 @@ void bnxt_ptp_cfg_tstamp_filters(struct bnxt *bp)
 	req->enables = cpu_to_le32(PORT_MAC_CFG_REQ_ENABLES_RX_TS_CAPTURE_PTP_MSG_TYPE);
 	req->rx_ts_capture_ptp_msg_type = cpu_to_le16(ptp->rxctl);
 
-	if (!hwrm_req_send(bp, req)) {
+	rc = hwrm_req_send(bp, req);
+	if (!rc) {
 		bp->ptp_all_rx_tstamp = !!(ptp->tstamp_filters &
 					   PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_ENABLE);
-		return;
+		return 0;
 	}
 	ptp->tstamp_filters = 0;
 out:
 	bp->ptp_all_rx_tstamp = 0;
 	netdev_warn(bp->dev, "Failed to configure HW packet timestamp filters\n");
+	return rc;
 }
 
 void bnxt_ptp_reapply_pps(struct bnxt *bp)
@@ -494,7 +498,6 @@ static int bnxt_hwrm_ptp_cfg(struct bnxt *bp)
 {
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
 	u32 flags = 0;
-	int rc = 0;
 
 	switch (ptp->rx_filter) {
 	case HWTSTAMP_FILTER_ALL:
@@ -519,19 +522,7 @@ static int bnxt_hwrm_ptp_cfg(struct bnxt *bp)
 
 	ptp->tstamp_filters = flags;
 
-	if (netif_running(bp->dev)) {
-		if (ptp->rx_filter == HWTSTAMP_FILTER_ALL) {
-			rc = bnxt_close_nic(bp, false, false);
-			if (!rc)
-				rc = bnxt_open_nic(bp, false, false);
-		} else {
-			bnxt_ptp_cfg_tstamp_filters(bp);
-		}
-		if (!rc && !ptp->tstamp_filters)
-			rc = -EIO;
-	}
-
-	return rc;
+	return bnxt_ptp_cfg_tstamp_filters(bp);
 }
 
 int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
@@ -650,7 +641,7 @@ static int bnxt_map_ptp_regs(struct bnxt *bp)
 	int rc, i;
 
 	reg_arr = ptp->refclk_regs;
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (BNXT_CHIP_P5(bp)) {
 		rc = bnxt_map_regs(bp, reg_arr, 2, BNXT_PTP_GRC_WIN);
 		if (rc)
 			return rc;
@@ -693,8 +684,8 @@ static void bnxt_stamp_tx_skb(struct bnxt *bp, struct sk_buff *skb)
 		timestamp.hwtstamp = ns_to_ktime(ns);
 		skb_tstamp_tx(ptp->tx_skb, &timestamp);
 	} else {
-		netdev_err(bp->dev, "TS query for TX timer failed rc = %x\n",
-			   rc);
+		netdev_WARN_ONCE(bp->dev,
+				 "TS query for TX timer failed rc = %x\n", rc);
 	}
 
 	dev_kfree_skb_any(ptp->tx_skb);
@@ -967,7 +958,7 @@ int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg)
 		rc = err;
 		goto out;
 	}
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (BNXT_CHIP_P5(bp)) {
 		spin_lock_bh(&ptp->ptp_lock);
 		bnxt_refclk_read(bp, NULL, &ptp->current_time);
 		WRITE_ONCE(ptp->old_time, ptp->current_time);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
index 34162e07a119..fce8dc39a7d0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
@@ -137,7 +137,7 @@ do {						\
 int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id, u16 *hdr_off);
 void bnxt_ptp_update_current_time(struct bnxt *bp);
 void bnxt_ptp_pps_event(struct bnxt *bp, u32 data1, u32 data2);
-void bnxt_ptp_cfg_tstamp_filters(struct bnxt *bp);
+int bnxt_ptp_cfg_tstamp_filters(struct bnxt *bp);
 void bnxt_ptp_reapply_pps(struct bnxt *bp);
 int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr);
 int bnxt_hwtstamp_get(struct net_device *dev, struct ifreq *ifr);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index c722b3b41730..175192ebaa77 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -536,7 +536,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset)
 	if (rc)
 		return rc;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		vf_msix = hw_resc->max_nqs - bnxt_nq_rings_in_use(bp);
 		vf_ring_grps = 0;
 	} else {
@@ -565,7 +565,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset)
 		req->min_l2_ctxs = cpu_to_le16(min);
 		req->min_vnics = cpu_to_le16(min);
 		req->min_stat_ctx = cpu_to_le16(min);
-		if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+		if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 			req->min_hw_ring_grps = cpu_to_le16(min);
 	} else {
 		vf_cp_rings /= num_vfs;
@@ -602,7 +602,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset)
 	req->max_stat_ctx = cpu_to_le16(vf_stat_ctx);
 	req->max_hw_ring_grps = cpu_to_le16(vf_ring_grps);
 	req->max_rsscos_ctx = cpu_to_le16(vf_rss);
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		req->max_msix = cpu_to_le16(vf_msix / num_vfs);
 
 	hwrm_req_hold(bp, req);
@@ -630,7 +630,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset)
 			le16_to_cpu(req->min_rsscos_ctx) * n;
 		hw_resc->max_stat_ctxs -= le16_to_cpu(req->min_stat_ctx) * n;
 		hw_resc->max_vnics -= le16_to_cpu(req->min_vnics) * n;
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 			hw_resc->max_nqs -= vf_msix;
 
 		rc = pf->active_vfs;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index 38d89d80b4a9..273c9ba48f09 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -2075,6 +2075,7 @@ destroy_flow_table:
 	rhashtable_destroy(&tc_info->flow_table);
 free_tc_info:
 	kfree(tc_info);
+	bp->tc_info = NULL;
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 6ba2b9398633..93f9bd55020f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -42,13 +42,10 @@ static void bnxt_fill_msix_vecs(struct bnxt *bp, struct bnxt_msix_entry *ent)
 	for (i = 0; i < num_msix; i++) {
 		ent[i].vector = bp->irq_tbl[idx + i].vector;
 		ent[i].ring_idx = idx + i;
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
-			ent[i].db_offset = DB_PF_OFFSET_P5;
-			if (BNXT_VF(bp))
-				ent[i].db_offset = DB_VF_OFFSET_P5;
-		} else {
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
+			ent[i].db_offset = bp->db_offset;
+		else
 			ent[i].db_offset = (idx + i) * 0x80;
-		}
 	}
 }
 
@@ -333,6 +330,7 @@ static void bnxt_set_edev_info(struct bnxt_en_dev *edev, struct bnxt *bp)
 	edev->pdev = bp->pdev;
 	edev->l2_db_size = bp->db_size;
 	edev->l2_db_size_nc = bp->db_size;
+	edev->l2_db_offset = bp->db_offset;
 
 	if (bp->flags & BNXT_FLAG_ROCEV1_CAP)
 		edev->flags |= BNXT_EN_FLAG_ROCEV1_CAP;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
index 6ff77f082e6c..b9e73de14b57 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
@@ -73,6 +73,10 @@ struct bnxt_en_dev {
 							 * bytes mapped as non-
 							 * cacheable.
 							 */
+	int				l2_db_offset;	/* Doorbell offset in
+							 * bytes within
+							 * l2_db_size_nc.
+							 */
 	u16				chip_num;
 	u16				hw_ring_stats_size;
 	u16				pf_port_id;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 96f5ca778c67..c2b25fc623ec 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -42,24 +42,23 @@ struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp,
 
 	/* fill up the first buffer */
 	prod = txr->tx_prod;
-	tx_buf = &txr->tx_buf_ring[prod];
+	tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
 	tx_buf->nr_frags = num_frags;
 	if (xdp)
 		tx_buf->page = virt_to_head_page(xdp->data);
 
-	txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
+	txbd = &txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
 	flags = (len << TX_BD_LEN_SHIFT) |
 		((num_frags + 1) << TX_BD_FLAGS_BD_CNT_SHIFT) |
 		bnxt_lhint_arr[len >> 9];
 	txbd->tx_bd_len_flags_type = cpu_to_le32(flags);
-	txbd->tx_bd_opaque = prod;
+	txbd->tx_bd_opaque = SET_TX_OPAQUE(bp, txr, prod, 1 + num_frags);
 	txbd->tx_bd_haddr = cpu_to_le64(mapping);
 
 	/* now let us fill up the frags into the next buffers */
 	for (i = 0; i < num_frags ; i++) {
 		skb_frag_t *frag = &sinfo->frags[i];
 		struct bnxt_sw_tx_bd *frag_tx_buf;
-		struct pci_dev *pdev = bp->pdev;
 		dma_addr_t frag_mapping;
 		int frag_len;
 
@@ -67,22 +66,16 @@ struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp,
 		WRITE_ONCE(txr->tx_prod, prod);
 
 		/* first fill up the first buffer */
-		frag_tx_buf = &txr->tx_buf_ring[prod];
+		frag_tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
 		frag_tx_buf->page = skb_frag_page(frag);
 
-		txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
+		txbd = &txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
 
 		frag_len = skb_frag_size(frag);
-		frag_mapping = skb_frag_dma_map(&pdev->dev, frag, 0,
-						frag_len, DMA_TO_DEVICE);
-
-		if (unlikely(dma_mapping_error(&pdev->dev, frag_mapping)))
-			return NULL;
-
-		dma_unmap_addr_set(frag_tx_buf, mapping, frag_mapping);
-
 		flags = frag_len << TX_BD_LEN_SHIFT;
 		txbd->tx_bd_len_flags_type = cpu_to_le32(flags);
+		frag_mapping = page_pool_get_dma_addr(skb_frag_page(frag)) +
+			       skb_frag_off(frag);
 		txbd->tx_bd_haddr = cpu_to_le64(frag_mapping);
 
 		len = frag_len;
@@ -127,20 +120,20 @@ static void __bnxt_xmit_xdp_redirect(struct bnxt *bp,
 
 void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 {
-	struct bnxt_tx_ring_info *txr = bnapi->tx_ring;
+	struct bnxt_tx_ring_info *txr = bnapi->tx_ring[0];
 	struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
+	u16 tx_hw_cons = txr->tx_hw_cons;
 	bool rx_doorbell_needed = false;
-	int nr_pkts = bnapi->tx_pkts;
 	struct bnxt_sw_tx_bd *tx_buf;
 	u16 tx_cons = txr->tx_cons;
 	u16 last_tx_cons = tx_cons;
-	int i, j, frags;
+	int j, frags;
 
 	if (!budget)
 		return;
 
-	for (i = 0; i < nr_pkts; i++) {
-		tx_buf = &txr->tx_buf_ring[tx_cons];
+	while (RING_TX(bp, tx_cons) != tx_hw_cons) {
+		tx_buf = &txr->tx_buf_ring[RING_TX(bp, tx_cons)];
 
 		if (tx_buf->action == XDP_REDIRECT) {
 			struct pci_dev *pdev = bp->pdev;
@@ -160,20 +153,20 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 			frags = tx_buf->nr_frags;
 			for (j = 0; j < frags; j++) {
 				tx_cons = NEXT_TX(tx_cons);
-				tx_buf = &txr->tx_buf_ring[tx_cons];
+				tx_buf = &txr->tx_buf_ring[RING_TX(bp, tx_cons)];
 				page_pool_recycle_direct(rxr->page_pool, tx_buf->page);
 			}
 		} else {
-			bnxt_sched_reset_txr(bp, txr, i);
+			bnxt_sched_reset_txr(bp, txr, tx_cons);
 			return;
 		}
 		tx_cons = NEXT_TX(tx_cons);
 	}
 
-	bnapi->tx_pkts = 0;
+	bnapi->events &= ~BNXT_TX_CMP_EVENT;
 	WRITE_ONCE(txr->tx_cons, tx_cons);
 	if (rx_doorbell_needed) {
-		tx_buf = &txr->tx_buf_ring[last_tx_cons];
+		tx_buf = &txr->tx_buf_ring[RING_TX(bp, last_tx_cons)];
 		bnxt_db_write(bp, &rxr->rx_db, tx_buf->rx_prod);
 
 	}
@@ -249,7 +242,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 	pdev = bp->pdev;
 	offset = bp->rx_offset;
 
-	txr = rxr->bnapi->tx_ring;
+	txr = rxr->bnapi->tx_ring[0];
 	/* BNXT_RX_PAGE_MODE(bp) when XDP enabled */
 	orig_data = xdp.data;
 
@@ -275,7 +268,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 	case XDP_TX:
 		rx_buf = &rxr->rx_buf_ring[cons];
 		mapping = rx_buf->mapping - bp->rx_dma_offset;
-		*event = 0;
+		*event &= BNXT_TX_CMP_EVENT;
 
 		if (unlikely(xdp_buff_has_frags(&xdp))) {
 			struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(&xdp);
@@ -398,7 +391,7 @@ int bnxt_xdp_xmit(struct net_device *dev, int num_frames,
 static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 {
 	struct net_device *dev = bp->dev;
-	int tx_xdp = 0, rc, tc;
+	int tx_xdp = 0, tx_cp, rc, tc;
 	struct bpf_prog *old;
 
 	if (prog && !prog->aux->xdp_has_frags &&
@@ -446,7 +439,8 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 	}
 	bp->tx_nr_rings_xdp = tx_xdp;
 	bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tc + tx_xdp;
-	bp->cp_nr_rings = max_t(int, bp->tx_nr_rings, bp->rx_nr_rings);
+	tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings);
+	bp->cp_nr_rings = max_t(int, tx_cp, bp->rx_nr_rings);
 	bnxt_set_tpa_flags(bp);
 	bnxt_set_ring_params(bp);
 
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 9282403d1bf6..2d7ae71287b1 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2132,8 +2132,10 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 		/* Note: if we ever change from DMA_TX_APPEND_CRC below we
 		 * will need to restore software padding of "runt" packets
 		 */
+		len_stat |= DMA_TX_APPEND_CRC;
+
 		if (!i) {
-			len_stat |= DMA_TX_APPEND_CRC | DMA_SOP;
+			len_stat |= DMA_SOP;
 			if (skb->ip_summed == CHECKSUM_PARTIAL)
 				len_stat |= DMA_TX_DO_CSUM;
 		}
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 1dee27349367..04964bbe08cf 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -6474,6 +6474,14 @@ static void tg3_dump_state(struct tg3 *tp)
 	int i;
 	u32 *regs;
 
+	/* If it is a PCI error, all registers will be 0xffff,
+	 * we don't dump them out, just report the error and return
+	 */
+	if (tp->pdev->error_state != pci_channel_io_normal) {
+		netdev_err(tp->dev, "PCI channel ERROR!\n");
+		return;
+	}
+
 	regs = kzalloc(TG3_REG_BLK_SIZE, GFP_ATOMIC);
 	if (!regs)
 		return;
@@ -6889,7 +6897,7 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget)
 				       desc_idx, *post_ptr);
 		drop_it_no_recycle:
 			/* Other statistics kept track of by card. */
-			tp->rx_dropped++;
+			tnapi->rx_dropped++;
 			goto next_pkt;
 		}
 
@@ -7918,8 +7926,10 @@ static int tg3_tso_bug(struct tg3 *tp, struct tg3_napi *tnapi,
 
 	segs = skb_gso_segment(skb, tp->dev->features &
 				    ~(NETIF_F_TSO | NETIF_F_TSO6));
-	if (IS_ERR(segs) || !segs)
+	if (IS_ERR(segs) || !segs) {
+		tnapi->tx_dropped++;
 		goto tg3_tso_bug_end;
+	}
 
 	skb_list_walk_safe(segs, seg, next) {
 		skb_mark_not_on_list(seg);
@@ -8190,7 +8200,7 @@ dma_error:
 drop:
 	dev_kfree_skb_any(skb);
 drop_nofree:
-	tp->tx_dropped++;
+	tnapi->tx_dropped++;
 	return NETDEV_TX_OK;
 }
 
@@ -9405,7 +9415,7 @@ static void __tg3_set_rx_mode(struct net_device *);
 /* tp->lock is held. */
 static int tg3_halt(struct tg3 *tp, int kind, bool silent)
 {
-	int err;
+	int err, i;
 
 	tg3_stop_fw(tp);
 
@@ -9426,6 +9436,13 @@ static int tg3_halt(struct tg3 *tp, int kind, bool silent)
 
 		/* And make sure the next sample is new data */
 		memset(tp->hw_stats, 0, sizeof(struct tg3_hw_stats));
+
+		for (i = 0; i < TG3_IRQ_MAX_VECS; ++i) {
+			struct tg3_napi *tnapi = &tp->napi[i];
+
+			tnapi->rx_dropped = 0;
+			tnapi->tx_dropped = 0;
+		}
 	}
 
 	return err;
@@ -11250,7 +11267,8 @@ static void tg3_reset_task(struct work_struct *work)
 	rtnl_lock();
 	tg3_full_lock(tp, 0);
 
-	if (tp->pcierr_recovery || !netif_running(tp->dev)) {
+	if (tp->pcierr_recovery || !netif_running(tp->dev) ||
+	    tp->pdev->error_state != pci_channel_io_normal) {
 		tg3_flag_clear(tp, RESET_TASK_PENDING);
 		tg3_full_unlock(tp);
 		rtnl_unlock();
@@ -11975,6 +11993,9 @@ static void tg3_get_nstats(struct tg3 *tp, struct rtnl_link_stats64 *stats)
 {
 	struct rtnl_link_stats64 *old_stats = &tp->net_stats_prev;
 	struct tg3_hw_stats *hw_stats = tp->hw_stats;
+	unsigned long rx_dropped;
+	unsigned long tx_dropped;
+	int i;
 
 	stats->rx_packets = old_stats->rx_packets +
 		get_stat64(&hw_stats->rx_ucast_packets) +
@@ -12021,8 +12042,26 @@ static void tg3_get_nstats(struct tg3 *tp, struct rtnl_link_stats64 *stats)
 	stats->rx_missed_errors = old_stats->rx_missed_errors +
 		get_stat64(&hw_stats->rx_discards);
 
-	stats->rx_dropped = tp->rx_dropped;
-	stats->tx_dropped = tp->tx_dropped;
+	/* Aggregate per-queue counters. The per-queue counters are updated
+	 * by a single writer, race-free. The result computed by this loop
+	 * might not be 100% accurate (counters can be updated in the middle of
+	 * the loop) but the next tg3_get_nstats() will recompute the current
+	 * value so it is acceptable.
+	 *
+	 * Note that these counters wrap around at 4G on 32bit machines.
+	 */
+	rx_dropped = (unsigned long)(old_stats->rx_dropped);
+	tx_dropped = (unsigned long)(old_stats->tx_dropped);
+
+	for (i = 0; i < tp->irq_cnt; i++) {
+		struct tg3_napi *tnapi = &tp->napi[i];
+
+		rx_dropped += tnapi->rx_dropped;
+		tx_dropped += tnapi->tx_dropped;
+	}
+
+	stats->rx_dropped = rx_dropped;
+	stats->tx_dropped = tx_dropped;
 }
 
 static int tg3_get_regs_len(struct net_device *dev)
@@ -12706,24 +12745,23 @@ static u32 tg3_get_rxfh_indir_size(struct net_device *dev)
 	return size;
 }
 
-static int tg3_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, u8 *hfunc)
+static int tg3_get_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh)
 {
 	struct tg3 *tp = netdev_priv(dev);
 	int i;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (!indir)
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (!rxfh->indir)
 		return 0;
 
 	for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++)
-		indir[i] = tp->rss_ind_tbl[i];
+		rxfh->indir[i] = tp->rss_ind_tbl[i];
 
 	return 0;
 }
 
-static int tg3_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key,
-			const u8 hfunc)
+static int tg3_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh,
+			struct netlink_ext_ack *extack)
 {
 	struct tg3 *tp = netdev_priv(dev);
 	size_t i;
@@ -12731,15 +12769,16 @@ static int tg3_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key,
 	/* We require at least one supported parameter to be changed and no
 	 * change in any of the unsupported parameters
 	 */
-	if (key ||
-	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->key ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP))
 		return -EOPNOTSUPP;
 
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
 	for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++)
-		tp->rss_ind_tbl[i] = indir[i];
+		tp->rss_ind_tbl[i] = rxfh->indir[i];
 
 	if (!netif_running(dev) || !tg3_flag(tp, ENABLE_RSS))
 		return 0;
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index ae5c01bd1110..5016475e5005 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -3018,6 +3018,7 @@ struct tg3_napi {
 	u16				*rx_rcb_prod_idx;
 	struct tg3_rx_prodring_set	prodring;
 	struct tg3_rx_buffer_desc	*rx_rcb;
+	unsigned long			rx_dropped;
 
 	u32				tx_prod	____cacheline_aligned;
 	u32				tx_cons;
@@ -3026,6 +3027,7 @@ struct tg3_napi {
 	u32				prodmbox;
 	struct tg3_tx_buffer_desc	*tx_ring;
 	struct tg3_tx_ring_info		*tx_buffers;
+	unsigned long			tx_dropped;
 
 	dma_addr_t			status_mapping;
 	dma_addr_t			rx_rcb_mapping;
@@ -3220,8 +3222,6 @@ struct tg3 {
 
 
 	/* begin "everything else" cacheline(s) section */
-	unsigned long			rx_dropped;
-	unsigned long			tx_dropped;
 	struct rtnl_link_stats64	net_stats_prev;
 	struct tg3_ethtool_stats	estats_prev;
 
diff --git a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
index df10edff5603..d1ad6c9f8140 100644
--- a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
+++ b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
@@ -608,7 +608,7 @@ bnad_get_strings(struct net_device *netdev, u32 stringset, u8 *string)
 
 	for (i = 0; i < BNAD_ETHTOOL_STATS_NUM; i++) {
 		BUG_ON(!(strlen(bnad_net_stats_strings[i]) < ETH_GSTRING_LEN));
-		ethtool_sprintf(&string, bnad_net_stats_strings[i]);
+		ethtool_puts(&string, bnad_net_stats_strings[i]);
 	}
 
 	bmap = bna_tx_rid_mask(&bnad->bna);
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 78c972bb1d96..aa5700ac9c00 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -1165,9 +1165,10 @@ struct macb_ptp_info {
 	int (*get_ts_info)(struct net_device *dev,
 			   struct ethtool_ts_info *info);
 	int (*get_hwtst)(struct net_device *netdev,
-			 struct ifreq *ifr);
+			 struct kernel_hwtstamp_config *tstamp_config);
 	int (*set_hwtst)(struct net_device *netdev,
-			 struct ifreq *ifr, int cmd);
+			 struct kernel_hwtstamp_config *tstamp_config,
+			 struct netlink_ext_ack *extack);
 };
 
 struct macb_pm_data {
@@ -1314,7 +1315,7 @@ struct macb {
 	struct ptp_clock *ptp_clock;
 	struct ptp_clock_info ptp_clock_info;
 	struct tsu_incr tsu_incr;
-	struct hwtstamp_config tstamp_config;
+	struct kernel_hwtstamp_config tstamp_config;
 
 	/* RX queue filer rule set*/
 	struct ethtool_rx_fs_list rx_fs_list;
@@ -1363,8 +1364,12 @@ static inline void gem_ptp_do_rxstamp(struct macb *bp, struct sk_buff *skb, stru
 
 	gem_ptp_rxstamp(bp, skb, desc);
 }
-int gem_get_hwtst(struct net_device *dev, struct ifreq *rq);
-int gem_set_hwtst(struct net_device *dev, struct ifreq *ifr, int cmd);
+
+int gem_get_hwtst(struct net_device *dev,
+		  struct kernel_hwtstamp_config *tstamp_config);
+int gem_set_hwtst(struct net_device *dev,
+		  struct kernel_hwtstamp_config *tstamp_config,
+		  struct netlink_ext_ack *extack);
 #else
 static inline void gem_ptp_init(struct net_device *ndev) { }
 static inline void gem_ptp_remove(struct net_device *ndev) { }
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index cebae0f418f2..898debfd4db3 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -3773,18 +3773,38 @@ static int macb_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	if (!netif_running(dev))
 		return -EINVAL;
 
-	if (bp->ptp_info) {
-		switch (cmd) {
-		case SIOCSHWTSTAMP:
-			return bp->ptp_info->set_hwtst(dev, rq, cmd);
-		case SIOCGHWTSTAMP:
-			return bp->ptp_info->get_hwtst(dev, rq);
-		}
-	}
-
 	return phylink_mii_ioctl(bp->phylink, rq, cmd);
 }
 
+static int macb_hwtstamp_get(struct net_device *dev,
+			     struct kernel_hwtstamp_config *cfg)
+{
+	struct macb *bp = netdev_priv(dev);
+
+	if (!netif_running(dev))
+		return -EINVAL;
+
+	if (!bp->ptp_info)
+		return -EOPNOTSUPP;
+
+	return bp->ptp_info->get_hwtst(dev, cfg);
+}
+
+static int macb_hwtstamp_set(struct net_device *dev,
+			     struct kernel_hwtstamp_config *cfg,
+			     struct netlink_ext_ack *extack)
+{
+	struct macb *bp = netdev_priv(dev);
+
+	if (!netif_running(dev))
+		return -EINVAL;
+
+	if (!bp->ptp_info)
+		return -EOPNOTSUPP;
+
+	return bp->ptp_info->set_hwtst(dev, cfg, extack);
+}
+
 static inline void macb_set_txcsum_feature(struct macb *bp,
 					   netdev_features_t features)
 {
@@ -3884,6 +3904,8 @@ static const struct net_device_ops macb_netdev_ops = {
 #endif
 	.ndo_set_features	= macb_set_features,
 	.ndo_features_check	= macb_features_check,
+	.ndo_hwtstamp_set	= macb_hwtstamp_set,
+	.ndo_hwtstamp_get	= macb_hwtstamp_get,
 };
 
 /* Configure peripheral capabilities according to device tree
@@ -4539,6 +4561,8 @@ static const struct net_device_ops at91ether_netdev_ops = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= at91ether_poll_controller,
 #endif
+	.ndo_hwtstamp_set	= macb_hwtstamp_set,
+	.ndo_hwtstamp_get	= macb_hwtstamp_get,
 };
 
 static int at91ether_clk_init(struct platform_device *pdev, struct clk **pclk,
diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c
index 51d26fa190d7..a63bf29c4fa8 100644
--- a/drivers/net/ethernet/cadence/macb_ptp.c
+++ b/drivers/net/ethernet/cadence/macb_ptp.c
@@ -374,19 +374,16 @@ static int gem_ptp_set_ts_mode(struct macb *bp,
 	return 0;
 }
 
-int gem_get_hwtst(struct net_device *dev, struct ifreq *rq)
+int gem_get_hwtst(struct net_device *dev,
+		  struct kernel_hwtstamp_config *tstamp_config)
 {
-	struct hwtstamp_config *tstamp_config;
 	struct macb *bp = netdev_priv(dev);
 
-	tstamp_config = &bp->tstamp_config;
+	*tstamp_config = bp->tstamp_config;
 	if ((bp->hw_dma_cap & HW_DMA_CAP_PTP) == 0)
 		return -EOPNOTSUPP;
 
-	if (copy_to_user(rq->ifr_data, tstamp_config, sizeof(*tstamp_config)))
-		return -EFAULT;
-	else
-		return 0;
+	return 0;
 }
 
 static void gem_ptp_set_one_step_sync(struct macb *bp, u8 enable)
@@ -401,22 +398,18 @@ static void gem_ptp_set_one_step_sync(struct macb *bp, u8 enable)
 		macb_writel(bp, NCR, reg_val & ~MACB_BIT(OSSMODE));
 }
 
-int gem_set_hwtst(struct net_device *dev, struct ifreq *ifr, int cmd)
+int gem_set_hwtst(struct net_device *dev,
+		  struct kernel_hwtstamp_config *tstamp_config,
+		  struct netlink_ext_ack *extack)
 {
 	enum macb_bd_control tx_bd_control = TSTAMP_DISABLED;
 	enum macb_bd_control rx_bd_control = TSTAMP_DISABLED;
-	struct hwtstamp_config *tstamp_config;
 	struct macb *bp = netdev_priv(dev);
 	u32 regval;
 
-	tstamp_config = &bp->tstamp_config;
 	if ((bp->hw_dma_cap & HW_DMA_CAP_PTP) == 0)
 		return -EOPNOTSUPP;
 
-	if (copy_from_user(tstamp_config, ifr->ifr_data,
-			   sizeof(*tstamp_config)))
-		return -EFAULT;
-
 	switch (tstamp_config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 		break;
@@ -463,12 +456,11 @@ int gem_set_hwtst(struct net_device *dev, struct ifreq *ifr, int cmd)
 		return -ERANGE;
 	}
 
+	bp->tstamp_config = *tstamp_config;
+
 	if (gem_ptp_set_ts_mode(bp, tx_bd_control, rx_bd_control) != 0)
 		return -ERANGE;
 
-	if (copy_to_user(ifr->ifr_data, tstamp_config, sizeof(*tstamp_config)))
-		return -EFAULT;
-	else
-		return 0;
+	return 0;
 }
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index d8d71bf97983..34125b8cd935 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -653,35 +653,36 @@ static u32 nicvf_get_rxfh_indir_size(struct net_device *dev)
 	return nic->rss_info.rss_size;
 }
 
-static int nicvf_get_rxfh(struct net_device *dev, u32 *indir, u8 *hkey,
-			  u8 *hfunc)
+static int nicvf_get_rxfh(struct net_device *dev,
+			  struct ethtool_rxfh_param *rxfh)
 {
 	struct nicvf *nic = netdev_priv(dev);
 	struct nicvf_rss_info *rss = &nic->rss_info;
 	int idx;
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (idx = 0; idx < rss->rss_size; idx++)
-			indir[idx] = rss->ind_tbl[idx];
+			rxfh->indir[idx] = rss->ind_tbl[idx];
 	}
 
-	if (hkey)
-		memcpy(hkey, rss->key, RSS_HASH_KEY_SIZE * sizeof(u64));
+	if (rxfh->key)
+		memcpy(rxfh->key, rss->key, RSS_HASH_KEY_SIZE * sizeof(u64));
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	return 0;
 }
 
-static int nicvf_set_rxfh(struct net_device *dev, const u32 *indir,
-			  const u8 *hkey, const u8 hfunc)
+static int nicvf_set_rxfh(struct net_device *dev,
+			  struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
 {
 	struct nicvf *nic = netdev_priv(dev);
 	struct nicvf_rss_info *rss = &nic->rss_info;
 	int idx;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
 	if (!rss->enable) {
@@ -690,13 +691,13 @@ static int nicvf_set_rxfh(struct net_device *dev, const u32 *indir,
 		return -EIO;
 	}
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (idx = 0; idx < rss->rss_size; idx++)
-			rss->ind_tbl[idx] = indir[idx];
+			rss->ind_tbl[idx] = rxfh->indir[idx];
 	}
 
-	if (hkey) {
-		memcpy(rss->key, hkey, RSS_HASH_KEY_SIZE * sizeof(u64));
+	if (rxfh->key) {
+		memcpy(rss->key, rxfh->key, RSS_HASH_KEY_SIZE * sizeof(u64));
 		nicvf_set_rss_key(nic);
 	}
 
diff --git a/drivers/net/ethernet/chelsio/cxgb3/adapter.h b/drivers/net/ethernet/chelsio/cxgb3/adapter.h
index 6d682b7c7aac..9d11e55981a0 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/adapter.h
+++ b/drivers/net/ethernet/chelsio/cxgb3/adapter.h
@@ -237,7 +237,7 @@ struct adapter {
 	int msix_nvectors;
 	struct {
 		unsigned short vec;
-		char desc[22];
+		char desc[IFNAMSIZ + 1 + 12];	/* Needs space for "%s-%d" */
 	} msix_info[SGE_QSETS + 1];
 
 	/* T3 modules */
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index d117022d15d7..2236f1d35f2b 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -380,19 +380,18 @@ static irqreturn_t t3_async_intr_handler(int irq, void *cookie)
  */
 static void name_msix_vecs(struct adapter *adap)
 {
-	int i, j, msi_idx = 1, n = sizeof(adap->msix_info[0].desc) - 1;
+	int i, j, msi_idx = 1;
 
-	snprintf(adap->msix_info[0].desc, n, "%s", adap->name);
-	adap->msix_info[0].desc[n] = 0;
+	strscpy(adap->msix_info[0].desc, adap->name, sizeof(adap->msix_info[0].desc));
 
 	for_each_port(adap, j) {
 		struct net_device *d = adap->port[j];
 		const struct port_info *pi = netdev_priv(d);
 
 		for (i = 0; i < pi->nqsets; i++, msi_idx++) {
-			snprintf(adap->msix_info[msi_idx].desc, n,
+			snprintf(adap->msix_info[msi_idx].desc,
+				 sizeof(adap->msix_info[0].desc),
 				 "%s-%d", d->name, pi->first_qset + i);
-			adap->msix_info[msi_idx].desc[n] = 0;
 		}
 	}
 }
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index 8477a93cee6b..47eecde36285 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -1588,22 +1588,23 @@ static u32 get_rss_table_size(struct net_device *dev)
 	return pi->rss_size;
 }
 
-static int get_rss_table(struct net_device *dev, u32 *p, u8 *key, u8 *hfunc)
+static int get_rss_table(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh)
 {
 	const struct port_info *pi = netdev_priv(dev);
 	unsigned int n = pi->rss_size;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (!p)
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (!rxfh->indir)
 		return 0;
 	while (n--)
-		p[n] = pi->rss[n];
+		rxfh->indir[n] = pi->rss[n];
 	return 0;
 }
 
-static int set_rss_table(struct net_device *dev, const u32 *p, const u8 *key,
-			 const u8 hfunc)
+static int set_rss_table(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
 	unsigned int i;
 	struct port_info *pi = netdev_priv(dev);
@@ -1611,16 +1612,17 @@ static int set_rss_table(struct net_device *dev, const u32 *p, const u8 *key,
 	/* We require at least one supported parameter to be changed and no
 	 * change in any of the unsupported parameters
 	 */
-	if (key ||
-	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->key ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP))
 		return -EOPNOTSUPP;
-	if (!p)
+	if (!rxfh->indir)
 		return 0;
 
 	/* Interface must be brought up atleast once */
 	if (pi->adapter->flags & CXGB4_FULL_INIT_DONE) {
 		for (i = 0; i < pi->rss_size; i++)
-			pi->rss[i] = p[i];
+			pi->rss[i] = rxfh->indir[i];
 
 		return cxgb4_write_rss(pi, pi->rss);
 	}
diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
index 08b7cc0a1809..241906697019 100644
--- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c
+++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
@@ -568,31 +568,32 @@ static u32 enic_get_rxfh_key_size(struct net_device *netdev)
 	return ENIC_RSS_LEN;
 }
 
-static int enic_get_rxfh(struct net_device *netdev, u32 *indir, u8 *hkey,
-			 u8 *hfunc)
+static int enic_get_rxfh(struct net_device *netdev,
+			 struct ethtool_rxfh_param *rxfh)
 {
 	struct enic *enic = netdev_priv(netdev);
 
-	if (hkey)
-		memcpy(hkey, enic->rss_key, ENIC_RSS_LEN);
+	if (rxfh->key)
+		memcpy(rxfh->key, enic->rss_key, ENIC_RSS_LEN);
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	return 0;
 }
 
-static int enic_set_rxfh(struct net_device *netdev, const u32 *indir,
-			 const u8 *hkey, const u8 hfunc)
+static int enic_set_rxfh(struct net_device *netdev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
 	struct enic *enic = netdev_priv(netdev);
 
-	if ((hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) ||
-	    indir)
+	if (rxfh->indir ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP))
 		return -EINVAL;
 
-	if (hkey)
-		memcpy(enic->rss_key, hkey, ENIC_RSS_LEN);
+	if (rxfh->key)
+		memcpy(enic->rss_key, rxfh->key, ENIC_RSS_LEN);
 
 	return __enic_set_rsskey(enic);
 }
diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 5423fe26b4ef..705c3eb19cd3 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -79,8 +79,7 @@ MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
 #define GMAC0_IRQ4_8 (GMAC0_MIB_INT_BIT | GMAC0_RX_OVERRUN_INT_BIT)
 
 #define GMAC_OFFLOAD_FEATURES (NETIF_F_SG | NETIF_F_IP_CSUM | \
-		NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM | \
-		NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6)
+			       NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM)
 
 /**
  * struct gmac_queue_page - page buffer per-page info
@@ -432,8 +431,8 @@ static const struct gmac_max_framelen gmac_maxlens[] = {
 		.val = CONFIG0_MAXLEN_1536,
 	},
 	{
-		.max_l3_len = 1542,
-		.val = CONFIG0_MAXLEN_1542,
+		.max_l3_len = 1548,
+		.val = CONFIG0_MAXLEN_1548,
 	},
 	{
 		.max_l3_len = 9212,
@@ -1143,25 +1142,37 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
 	struct gmac_txdesc *txd;
 	skb_frag_t *skb_frag;
 	dma_addr_t mapping;
-	unsigned short mtu;
 	void *buffer;
+	int ret;
 
-	mtu  = ETH_HLEN;
-	mtu += netdev->mtu;
-	if (skb->protocol == htons(ETH_P_8021Q))
-		mtu += VLAN_HLEN;
-
+	/* TODO: implement proper TSO using MTU in word3 */
 	word1 = skb->len;
 	word3 = SOF_BIT;
 
-	if (word1 > mtu) {
-		word1 |= TSS_MTU_ENABLE_BIT;
-		word3 |= mtu;
-	}
-
-	if (skb->ip_summed != CHECKSUM_NONE) {
+	if (skb->len >= ETH_FRAME_LEN) {
+		/* Hardware offloaded checksumming isn't working on frames
+		 * bigger than 1514 bytes. A hypothesis about this is that the
+		 * checksum buffer is only 1518 bytes, so when the frames get
+		 * bigger they get truncated, or the last few bytes get
+		 * overwritten by the FCS.
+		 *
+		 * Just use software checksumming and bypass on bigger frames.
+		 */
+		if (skb->ip_summed == CHECKSUM_PARTIAL) {
+			ret = skb_checksum_help(skb);
+			if (ret)
+				return ret;
+		}
+		word1 |= TSS_BYPASS_BIT;
+	} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		int tcp = 0;
 
+		/* We do not switch off the checksumming on non TCP/UDP
+		 * frames: as is shown from tests, the checksumming engine
+		 * is smart enough to see that a frame is not actually TCP
+		 * or UDP and then just pass it through without any changes
+		 * to the frame.
+		 */
 		if (skb->protocol == htons(ETH_P_IP)) {
 			word1 |= TSS_IP_CHKSUM_BIT;
 			tcp = ip_hdr(skb)->protocol == IPPROTO_TCP;
@@ -1978,15 +1989,6 @@ static int gmac_change_mtu(struct net_device *netdev, int new_mtu)
 	return 0;
 }
 
-static netdev_features_t gmac_fix_features(struct net_device *netdev,
-					   netdev_features_t features)
-{
-	if (netdev->mtu + ETH_HLEN + VLAN_HLEN > MTU_SIZE_BIT_MASK)
-		features &= ~GMAC_OFFLOAD_FEATURES;
-
-	return features;
-}
-
 static int gmac_set_features(struct net_device *netdev,
 			     netdev_features_t features)
 {
@@ -2212,7 +2214,6 @@ static const struct net_device_ops gmac_351x_ops = {
 	.ndo_set_mac_address	= gmac_set_mac_address,
 	.ndo_get_stats64	= gmac_get_stats64,
 	.ndo_change_mtu		= gmac_change_mtu,
-	.ndo_fix_features	= gmac_fix_features,
 	.ndo_set_features	= gmac_set_features,
 };
 
@@ -2464,11 +2465,12 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev)
 
 	netdev->hw_features = GMAC_OFFLOAD_FEATURES;
 	netdev->features |= GMAC_OFFLOAD_FEATURES | NETIF_F_GRO;
-	/* We can handle jumbo frames up to 10236 bytes so, let's accept
-	 * payloads of 10236 bytes minus VLAN and ethernet header
+	/* We can receive jumbo frames up to 10236 bytes but only
+	 * transmit 2047 bytes so, let's accept payloads of 2047
+	 * bytes minus VLAN and ethernet header
 	 */
 	netdev->min_mtu = ETH_MIN_MTU;
-	netdev->max_mtu = 10236 - VLAN_ETH_HLEN;
+	netdev->max_mtu = MTU_SIZE_BIT_MASK - VLAN_ETH_HLEN;
 
 	port->freeq_refill = 0;
 	netif_napi_add(netdev, &port->napi, gmac_napi_poll);
diff --git a/drivers/net/ethernet/cortina/gemini.h b/drivers/net/ethernet/cortina/gemini.h
index 9fdf77d5eb37..24bb989981f2 100644
--- a/drivers/net/ethernet/cortina/gemini.h
+++ b/drivers/net/ethernet/cortina/gemini.h
@@ -502,7 +502,7 @@ union gmac_txdesc_3 {
 #define SOF_BIT			0x80000000
 #define EOF_BIT			0x40000000
 #define EOFIE_BIT		BIT(29)
-#define MTU_SIZE_BIT_MASK	0x1fff
+#define MTU_SIZE_BIT_MASK	0x7ff /* Max MTU 2047 bytes */
 
 /* GMAC Tx Descriptor */
 struct gmac_txdesc {
@@ -787,7 +787,7 @@ union gmac_config0 {
 #define  CONFIG0_MAXLEN_1536	0
 #define  CONFIG0_MAXLEN_1518	1
 #define  CONFIG0_MAXLEN_1522	2
-#define  CONFIG0_MAXLEN_1542	3
+#define  CONFIG0_MAXLEN_1548	3
 #define  CONFIG0_MAXLEN_9k	4	/* 9212 */
 #define  CONFIG0_MAXLEN_10k	5	/* 10236 */
 #define  CONFIG0_MAXLEN_1518__6	6
diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index db6615aa921b..7bfeae04b52b 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -565,8 +565,7 @@ static void rio_hw_init(struct net_device *dev)
 	 * too. However, it doesn't work on IP1000A so we use 16-bit access.
 	 */
 	for (i = 0; i < 3; i++)
-		dw16(StationAddr0 + 2 * i,
-		     cpu_to_le16(((const u16 *)dev->dev_addr)[i]));
+		dw16(StationAddr0 + 2 * i, get_unaligned_le16(&dev->dev_addr[2 * i]));
 
 	set_multicast (dev);
 	if (np->coalesce) {
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index a29de29bdf23..f001a649f58f 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -1271,43 +1271,45 @@ static u32 be_get_rxfh_key_size(struct net_device *netdev)
 	return RSS_HASH_KEY_LEN;
 }
 
-static int be_get_rxfh(struct net_device *netdev, u32 *indir, u8 *hkey,
-		       u8 *hfunc)
+static int be_get_rxfh(struct net_device *netdev,
+		       struct ethtool_rxfh_param *rxfh)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	int i;
 	struct rss_info *rss = &adapter->rss_info;
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < RSS_INDIR_TABLE_LEN; i++)
-			indir[i] = rss->rss_queue[i];
+			rxfh->indir[i] = rss->rss_queue[i];
 	}
 
-	if (hkey)
-		memcpy(hkey, rss->rss_hkey, RSS_HASH_KEY_LEN);
+	if (rxfh->key)
+		memcpy(rxfh->key, rss->rss_hkey, RSS_HASH_KEY_LEN);
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	return 0;
 }
 
-static int be_set_rxfh(struct net_device *netdev, const u32 *indir,
-		       const u8 *hkey, const u8 hfunc)
+static int be_set_rxfh(struct net_device *netdev,
+		       struct ethtool_rxfh_param *rxfh,
+		       struct netlink_ext_ack *extack)
 {
 	int rc = 0, i, j;
 	struct be_adapter *adapter = netdev_priv(netdev);
+	u8 *hkey = rxfh->key;
 	u8 rsstable[RSS_INDIR_TABLE_LEN];
 
 	/* We do not allow change in unsupported parameters */
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (indir) {
+	if (rxfh->indir) {
 		struct be_rx_obj *rxo;
 
 		for (i = 0; i < RSS_INDIR_TABLE_LEN; i++) {
-			j = indir[i];
+			j = rxfh->indir[i];
 			rxo = &adapter->rx_obj[j];
 			rsstable[i] = rxo->rss_id;
 			adapter->rss_info.rss_queue[i] = j;
diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c
index 4d7184d46824..07c2b701b5fa 100644
--- a/drivers/net/ethernet/ezchip/nps_enet.c
+++ b/drivers/net/ethernet/ezchip/nps_enet.c
@@ -633,7 +633,7 @@ out_netdev:
 	return err;
 }
 
-static s32 nps_enet_remove(struct platform_device *pdev)
+static void nps_enet_remove(struct platform_device *pdev)
 {
 	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct nps_enet_priv *priv = netdev_priv(ndev);
@@ -641,8 +641,6 @@ static s32 nps_enet_remove(struct platform_device *pdev)
 	unregister_netdev(ndev);
 	netif_napi_del(&priv->napi);
 	free_netdev(ndev);
-
-	return 0;
 }
 
 static const struct of_device_id nps_enet_dt_ids[] = {
@@ -653,7 +651,7 @@ MODULE_DEVICE_TABLE(of, nps_enet_dt_ids);
 
 static struct platform_driver nps_enet_driver = {
 	.probe = nps_enet_probe,
-	.remove = nps_enet_remove,
+	.remove_new = nps_enet_remove,
 	.driver = {
 		.name = DRV_NAME,
 		.of_match_table  = nps_enet_dt_ids,
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 15bab41cee48..888509cf1f21 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -516,8 +516,6 @@ struct sk_buff *dpaa2_eth_alloc_skb(struct dpaa2_eth_priv *priv,
 
 	memcpy(skb->data, fd_vaddr + fd_offset, fd_length);
 
-	dpaa2_eth_recycle_buf(priv, ch, dpaa2_fd_get_addr(fd));
-
 	return skb;
 }
 
@@ -589,6 +587,7 @@ void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 	struct rtnl_link_stats64 *percpu_stats;
 	struct dpaa2_eth_drv_stats *percpu_extras;
 	struct device *dev = priv->net_dev->dev.parent;
+	bool recycle_rx_buf = false;
 	void *buf_data;
 	u32 xdp_act;
 
@@ -618,6 +617,8 @@ void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 			dma_unmap_page(dev, addr, priv->rx_buf_size,
 				       DMA_BIDIRECTIONAL);
 			skb = dpaa2_eth_build_linear_skb(ch, fd, vaddr);
+		} else {
+			recycle_rx_buf = true;
 		}
 	} else if (fd_format == dpaa2_fd_sg) {
 		WARN_ON(priv->xdp_prog);
@@ -637,6 +638,9 @@ void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 		goto err_build_skb;
 
 	dpaa2_eth_receive_skb(priv, ch, fd, vaddr, fq, percpu_stats, skb);
+
+	if (recycle_rx_buf)
+		dpaa2_eth_recycle_buf(priv, ch, dpaa2_fd_get_addr(fd));
 	return;
 
 err_build_skb:
@@ -1073,14 +1077,12 @@ static int dpaa2_eth_build_single_fd(struct dpaa2_eth_priv *priv,
 	dma_addr_t addr;
 
 	buffer_start = skb->data - dpaa2_eth_needed_headroom(skb);
-
-	/* If there's enough room to align the FD address, do it.
-	 * It will help hardware optimize accesses.
-	 */
 	aligned_start = PTR_ALIGN(buffer_start - DPAA2_ETH_TX_BUF_ALIGN,
 				  DPAA2_ETH_TX_BUF_ALIGN);
 	if (aligned_start >= skb->head)
 		buffer_start = aligned_start;
+	else
+		return -ENOMEM;
 
 	/* Store a backpointer to the skb at the beginning of the buffer
 	 * (in the private data area) such that we can release it
@@ -4967,6 +4969,8 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev)
 	if (err)
 		goto err_dl_port_add;
 
+	net_dev->needed_headroom = DPAA2_ETH_SWA_SIZE + DPAA2_ETH_TX_BUF_ALIGN;
+
 	err = register_netdev(net_dev);
 	if (err < 0) {
 		dev_err(dev, "register_netdev() failed\n");
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index bfb6c96c3b2f..834cba8c3a41 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -740,7 +740,7 @@ static inline bool dpaa2_eth_rx_pause_enabled(u64 link_options)
 
 static inline unsigned int dpaa2_eth_needed_headroom(struct sk_buff *skb)
 {
-	unsigned int headroom = DPAA2_ETH_SWA_SIZE;
+	unsigned int headroom = DPAA2_ETH_SWA_SIZE + DPAA2_ETH_TX_BUF_ALIGN;
 
 	/* If we don't have an skb (e.g. XDP buffer), we only need space for
 	 * the software annotation area
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c
index 4798fb7fe35d..b6a534a3e0b1 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c
@@ -139,7 +139,8 @@ int dpaa2_switch_acl_entry_add(struct dpaa2_switch_filter_block *filter_block,
 	err = dpsw_acl_add_entry(ethsw->mc_io, 0, ethsw->dpsw_handle,
 				 filter_block->acl_id, acl_entry_cfg);
 
-	dma_unmap_single(dev, acl_entry_cfg->key_iova, sizeof(cmd_buff),
+	dma_unmap_single(dev, acl_entry_cfg->key_iova,
+			 DPAA2_ETHSW_PORT_ACL_CMD_BUF_SIZE,
 			 DMA_TO_DEVICE);
 	if (err) {
 		dev_err(dev, "dpsw_acl_add_entry() failed %d\n", err);
@@ -181,8 +182,8 @@ dpaa2_switch_acl_entry_remove(struct dpaa2_switch_filter_block *block,
 	err = dpsw_acl_remove_entry(ethsw->mc_io, 0, ethsw->dpsw_handle,
 				    block->acl_id, acl_entry_cfg);
 
-	dma_unmap_single(dev, acl_entry_cfg->key_iova, sizeof(cmd_buff),
-			 DMA_TO_DEVICE);
+	dma_unmap_single(dev, acl_entry_cfg->key_iova,
+			 DPAA2_ETHSW_PORT_ACL_CMD_BUF_SIZE, DMA_TO_DEVICE);
 	if (err) {
 		dev_err(dev, "dpsw_acl_remove_entry() failed %d\n", err);
 		kfree(cmd_buff);
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
index 97d3151076d5..f3543a2df68d 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
@@ -289,7 +289,7 @@ static int dpaa2_switch_port_add_vlan(struct ethsw_port_priv *port_priv,
 	int err;
 
 	if (port_priv->vlans[vid]) {
-		netdev_warn(netdev, "VLAN %d already configured\n", vid);
+		netdev_err(netdev, "VLAN %d already configured\n", vid);
 		return -EEXIST;
 	}
 
@@ -1509,9 +1509,9 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg)
 	struct device *dev = (struct device *)arg;
 	struct ethsw_core *ethsw = dev_get_drvdata(dev);
 	struct ethsw_port_priv *port_priv;
-	u32 status = ~0;
 	int err, if_id;
 	bool had_mac;
+	u32 status;
 
 	err = dpsw_get_irq_status(ethsw->mc_io, 0, ethsw->dpsw_handle,
 				  DPSW_IRQ_INDEX_IF, &status);
@@ -1523,12 +1523,11 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg)
 	if_id = (status & 0xFFFF0000) >> 16;
 	port_priv = ethsw->ports[if_id];
 
-	if (status & DPSW_IRQ_EVENT_LINK_CHANGED) {
+	if (status & DPSW_IRQ_EVENT_LINK_CHANGED)
 		dpaa2_switch_port_link_state_update(port_priv->netdev);
-		dpaa2_switch_port_set_mac_addr(port_priv);
-	}
 
 	if (status & DPSW_IRQ_EVENT_ENDPOINT_CHANGED) {
+		dpaa2_switch_port_set_mac_addr(port_priv);
 		/* We can avoid locking because the "endpoint changed" IRQ
 		 * handler is the only one who changes priv->mac at runtime,
 		 * so we are not racing with anyone.
@@ -1540,20 +1539,20 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg)
 			dpaa2_switch_port_connect_mac(port_priv);
 	}
 
-out:
 	err = dpsw_clear_irq_status(ethsw->mc_io, 0, ethsw->dpsw_handle,
 				    DPSW_IRQ_INDEX_IF, status);
 	if (err)
 		dev_err(dev, "Can't clear irq status (err %d)\n", err);
 
+out:
 	return IRQ_HANDLED;
 }
 
 static int dpaa2_switch_setup_irqs(struct fsl_mc_device *sw_dev)
 {
+	u32 mask = DPSW_IRQ_EVENT_LINK_CHANGED | DPSW_IRQ_EVENT_ENDPOINT_CHANGED;
 	struct device *dev = &sw_dev->dev;
 	struct ethsw_core *ethsw = dev_get_drvdata(dev);
-	u32 mask = DPSW_IRQ_EVENT_LINK_CHANGED;
 	struct fsl_mc_device_irq *irq;
 	int err;
 
@@ -1775,8 +1774,10 @@ int dpaa2_switch_port_vlans_add(struct net_device *netdev,
 	/* Make sure that the VLAN is not already configured
 	 * on the switch port
 	 */
-	if (port_priv->vlans[vlan->vid] & ETHSW_VLAN_MEMBER)
+	if (port_priv->vlans[vlan->vid] & ETHSW_VLAN_MEMBER) {
+		netdev_err(netdev, "VLAN %d already configured\n", vlan->vid);
 		return -EEXIST;
+	}
 
 	/* Check if there is space for a new VLAN */
 	err = dpsw_get_attributes(ethsw->mc_io, 0, ethsw->dpsw_handle,
@@ -1998,33 +1999,16 @@ static int dpaa2_switch_port_attr_set_event(struct net_device *netdev,
 	return notifier_from_errno(err);
 }
 
-static struct notifier_block dpaa2_switch_port_switchdev_nb;
-static struct notifier_block dpaa2_switch_port_switchdev_blocking_nb;
-
 static int dpaa2_switch_port_bridge_join(struct net_device *netdev,
 					 struct net_device *upper_dev,
 					 struct netlink_ext_ack *extack)
 {
 	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+	struct dpaa2_switch_fdb *old_fdb = port_priv->fdb;
 	struct ethsw_core *ethsw = port_priv->ethsw_data;
-	struct ethsw_port_priv *other_port_priv;
-	struct net_device *other_dev;
-	struct list_head *iter;
 	bool learn_ena;
 	int err;
 
-	netdev_for_each_lower_dev(upper_dev, other_dev, iter) {
-		if (!dpaa2_switch_port_dev_check(other_dev))
-			continue;
-
-		other_port_priv = netdev_priv(other_dev);
-		if (other_port_priv->ethsw_data != port_priv->ethsw_data) {
-			NL_SET_ERR_MSG_MOD(extack,
-					   "Interface from a different DPSW is in the bridge already");
-			return -EINVAL;
-		}
-	}
-
 	/* Delete the previously manually installed VLAN 1 */
 	err = dpaa2_switch_port_del_vlan(port_priv, 1);
 	if (err)
@@ -2042,10 +2026,13 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev,
 	if (err)
 		goto err_egress_flood;
 
+	/* Recreate the egress flood domain of the FDB that we just left. */
+	err = dpaa2_switch_fdb_set_egress_flood(ethsw, old_fdb->fdb_id);
+	if (err)
+		goto err_egress_flood;
+
 	err = switchdev_bridge_port_offload(netdev, netdev, NULL,
-					    &dpaa2_switch_port_switchdev_nb,
-					    &dpaa2_switch_port_switchdev_blocking_nb,
-					    false, extack);
+					    NULL, NULL, false, extack);
 	if (err)
 		goto err_switchdev_offload;
 
@@ -2079,9 +2066,7 @@ static int dpaa2_switch_port_restore_rxvlan(struct net_device *vdev, int vid, vo
 
 static void dpaa2_switch_port_pre_bridge_leave(struct net_device *netdev)
 {
-	switchdev_bridge_port_unoffload(netdev, NULL,
-					&dpaa2_switch_port_switchdev_nb,
-					&dpaa2_switch_port_switchdev_blocking_nb);
+	switchdev_bridge_port_unoffload(netdev, NULL, NULL, NULL);
 }
 
 static int dpaa2_switch_port_bridge_leave(struct net_device *netdev)
@@ -2162,6 +2147,10 @@ dpaa2_switch_prechangeupper_sanity_checks(struct net_device *netdev,
 					  struct net_device *upper_dev,
 					  struct netlink_ext_ack *extack)
 {
+	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+	struct ethsw_port_priv *other_port_priv;
+	struct net_device *other_dev;
+	struct list_head *iter;
 	int err;
 
 	if (!br_vlan_enabled(upper_dev)) {
@@ -2176,54 +2165,93 @@ dpaa2_switch_prechangeupper_sanity_checks(struct net_device *netdev,
 		return 0;
 	}
 
+	netdev_for_each_lower_dev(upper_dev, other_dev, iter) {
+		if (!dpaa2_switch_port_dev_check(other_dev))
+			continue;
+
+		other_port_priv = netdev_priv(other_dev);
+		if (other_port_priv->ethsw_data != port_priv->ethsw_data) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Interface from a different DPSW is in the bridge already");
+			return -EINVAL;
+		}
+	}
+
 	return 0;
 }
 
-static int dpaa2_switch_port_netdevice_event(struct notifier_block *nb,
-					     unsigned long event, void *ptr)
+static int dpaa2_switch_port_prechangeupper(struct net_device *netdev,
+					    struct netdev_notifier_changeupper_info *info)
 {
-	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
-	struct netdev_notifier_changeupper_info *info = ptr;
 	struct netlink_ext_ack *extack;
 	struct net_device *upper_dev;
-	int err = 0;
+	int err;
 
 	if (!dpaa2_switch_port_dev_check(netdev))
-		return NOTIFY_DONE;
+		return 0;
 
 	extack = netdev_notifier_info_to_extack(&info->info);
-
-	switch (event) {
-	case NETDEV_PRECHANGEUPPER:
-		upper_dev = info->upper_dev;
-		if (!netif_is_bridge_master(upper_dev))
-			break;
-
+	upper_dev = info->upper_dev;
+	if (netif_is_bridge_master(upper_dev)) {
 		err = dpaa2_switch_prechangeupper_sanity_checks(netdev,
 								upper_dev,
 								extack);
 		if (err)
-			goto out;
+			return err;
 
 		if (!info->linking)
 			dpaa2_switch_port_pre_bridge_leave(netdev);
+	}
+
+	return 0;
+}
+
+static int dpaa2_switch_port_changeupper(struct net_device *netdev,
+					 struct netdev_notifier_changeupper_info *info)
+{
+	struct netlink_ext_ack *extack;
+	struct net_device *upper_dev;
+
+	if (!dpaa2_switch_port_dev_check(netdev))
+		return 0;
+
+	extack = netdev_notifier_info_to_extack(&info->info);
+
+	upper_dev = info->upper_dev;
+	if (netif_is_bridge_master(upper_dev)) {
+		if (info->linking)
+			return dpaa2_switch_port_bridge_join(netdev,
+							     upper_dev,
+							     extack);
+		else
+			return dpaa2_switch_port_bridge_leave(netdev);
+	}
+
+	return 0;
+}
+
+static int dpaa2_switch_port_netdevice_event(struct notifier_block *nb,
+					     unsigned long event, void *ptr)
+{
+	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+	int err = 0;
+
+	switch (event) {
+	case NETDEV_PRECHANGEUPPER:
+		err = dpaa2_switch_port_prechangeupper(netdev, ptr);
+		if (err)
+			return notifier_from_errno(err);
 
 		break;
 	case NETDEV_CHANGEUPPER:
-		upper_dev = info->upper_dev;
-		if (netif_is_bridge_master(upper_dev)) {
-			if (info->linking)
-				err = dpaa2_switch_port_bridge_join(netdev,
-								    upper_dev,
-								    extack);
-			else
-				err = dpaa2_switch_port_bridge_leave(netdev);
-		}
+		err = dpaa2_switch_port_changeupper(netdev, ptr);
+		if (err)
+			return notifier_from_errno(err);
+
 		break;
 	}
 
-out:
-	return notifier_from_errno(err);
+	return NOTIFY_DONE;
 }
 
 struct ethsw_switchdev_event_work {
@@ -3301,6 +3329,7 @@ static int dpaa2_switch_probe_port(struct ethsw_core *ethsw,
 	port_netdev->features = NETIF_F_HW_VLAN_CTAG_FILTER |
 				NETIF_F_HW_VLAN_STAG_FILTER |
 				NETIF_F_HW_TC;
+	port_netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
 	err = dpaa2_switch_port_init(port_priv, port_idx);
 	if (err)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
index e993ed04ab57..f7753ea5b57e 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
@@ -690,25 +690,26 @@ static u32 enetc_get_rxfh_indir_size(struct net_device *ndev)
 	return priv->si->num_rss;
 }
 
-static int enetc_get_rxfh(struct net_device *ndev, u32 *indir, u8 *key,
-			  u8 *hfunc)
+static int enetc_get_rxfh(struct net_device *ndev,
+			  struct ethtool_rxfh_param *rxfh)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	struct enetc_hw *hw = &priv->si->hw;
 	int err = 0, i;
 
 	/* return hash function */
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	/* return hash key */
-	if (key && hw->port)
+	if (rxfh->key && hw->port)
 		for (i = 0; i < ENETC_RSSHASH_KEY_SIZE / 4; i++)
-			((u32 *)key)[i] = enetc_port_rd(hw, ENETC_PRSSK(i));
+			((u32 *)rxfh->key)[i] = enetc_port_rd(hw,
+							      ENETC_PRSSK(i));
 
 	/* return RSS table */
-	if (indir)
-		err = enetc_get_rss_table(priv->si, indir, priv->si->num_rss);
+	if (rxfh->indir)
+		err = enetc_get_rss_table(priv->si, rxfh->indir,
+					  priv->si->num_rss);
 
 	return err;
 }
@@ -722,20 +723,22 @@ void enetc_set_rss_key(struct enetc_hw *hw, const u8 *bytes)
 }
 EXPORT_SYMBOL_GPL(enetc_set_rss_key);
 
-static int enetc_set_rxfh(struct net_device *ndev, const u32 *indir,
-			  const u8 *key, const u8 hfunc)
+static int enetc_set_rxfh(struct net_device *ndev,
+			  struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	struct enetc_hw *hw = &priv->si->hw;
 	int err = 0;
 
 	/* set hash key, if PF */
-	if (key && hw->port)
-		enetc_set_rss_key(hw, key);
+	if (rxfh->key && hw->port)
+		enetc_set_rss_key(hw, rxfh->key);
 
 	/* set RSS table */
-	if (indir)
-		err = enetc_set_rss_table(priv->si, indir, priv->si->num_rss);
+	if (rxfh->indir)
+		err = enetc_set_rss_table(priv->si, rxfh->indir,
+					  priv->si->num_rss);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index c153dc083aff..11b14555802c 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -920,6 +920,7 @@ static void enetc_imdio_remove(struct enetc_pf *pf)
 static bool enetc_port_has_pcs(struct enetc_pf *pf)
 {
 	return (pf->if_mode == PHY_INTERFACE_MODE_SGMII ||
+		pf->if_mode == PHY_INTERFACE_MODE_1000BASEX ||
 		pf->if_mode == PHY_INTERFACE_MODE_2500BASEX ||
 		pf->if_mode == PHY_INTERFACE_MODE_USXGMII);
 }
@@ -1116,6 +1117,8 @@ static int enetc_phylink_create(struct enetc_ndev_priv *priv,
 		  pf->phylink_config.supported_interfaces);
 	__set_bit(PHY_INTERFACE_MODE_SGMII,
 		  pf->phylink_config.supported_interfaces);
+	__set_bit(PHY_INTERFACE_MODE_1000BASEX,
+		  pf->phylink_config.supported_interfaces);
 	__set_bit(PHY_INTERFACE_MODE_2500BASEX,
 		  pf->phylink_config.supported_interfaces);
 	__set_bit(PHY_INTERFACE_MODE_USXGMII,
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index c3b7694a7485..d42594f32275 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2932,10 +2932,10 @@ static void fec_enet_get_strings(struct net_device *netdev,
 	switch (stringset) {
 	case ETH_SS_STATS:
 		for (i = 0; i < ARRAY_SIZE(fec_stats); i++) {
-			ethtool_sprintf(&data, "%s", fec_stats[i].name);
+			ethtool_puts(&data, fec_stats[i].name);
 		}
 		for (i = 0; i < ARRAY_SIZE(fec_xdp_stat_strs); i++) {
-			ethtool_sprintf(&data, "%s", fec_xdp_stat_strs[i]);
+			ethtool_puts(&data, fec_xdp_stat_strs[i]);
 		}
 		page_pool_ethtool_stats_get_strings(data);
 
@@ -3731,31 +3731,26 @@ static int fec_set_features(struct net_device *netdev,
 	return 0;
 }
 
-static u16 fec_enet_get_raw_vlan_tci(struct sk_buff *skb)
-{
-	struct vlan_ethhdr *vhdr;
-	unsigned short vlan_TCI = 0;
-
-	if (skb->protocol == htons(ETH_P_ALL)) {
-		vhdr = (struct vlan_ethhdr *)(skb->data);
-		vlan_TCI = ntohs(vhdr->h_vlan_TCI);
-	}
-
-	return vlan_TCI;
-}
-
 static u16 fec_enet_select_queue(struct net_device *ndev, struct sk_buff *skb,
 				 struct net_device *sb_dev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	u16 vlan_tag;
+	u16 vlan_tag = 0;
 
 	if (!(fep->quirks & FEC_QUIRK_HAS_AVB))
 		return netdev_pick_tx(ndev, skb, NULL);
 
-	vlan_tag = fec_enet_get_raw_vlan_tci(skb);
-	if (!vlan_tag)
+	/* VLAN is present in the payload.*/
+	if (eth_type_vlan(skb->protocol)) {
+		struct vlan_ethhdr *vhdr = skb_vlan_eth_hdr(skb);
+
+		vlan_tag = ntohs(vhdr->h_vlan_TCI);
+	/*  VLAN is present in the skb but not yet pushed in the payload.*/
+	} else if (skb_vlan_tag_present(skb)) {
+		vlan_tag = skb->vlan_tci;
+	} else {
 		return vlan_tag;
+	}
 
 	return fec_enet_vlan_pri_to_queue[vlan_tag >> 13];
 }
diff --git a/drivers/net/ethernet/fungible/funeth/funeth_ethtool.c b/drivers/net/ethernet/fungible/funeth/funeth_ethtool.c
index 31aa185f4d17..4edd0adfc6c7 100644
--- a/drivers/net/ethernet/fungible/funeth/funeth_ethtool.c
+++ b/drivers/net/ethernet/fungible/funeth/funeth_ethtool.c
@@ -655,7 +655,7 @@ static void fun_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 						i);
 		}
 		for (j = 0; j < ARRAY_SIZE(txq_stat_names); j++)
-			ethtool_sprintf(&p, txq_stat_names[j]);
+			ethtool_puts(&p, txq_stat_names[j]);
 
 		for (i = 0; i < fp->num_xdpqs; i++) {
 			for (j = 0; j < ARRAY_SIZE(xdpq_stat_names); j++)
@@ -663,7 +663,7 @@ static void fun_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 						xdpq_stat_names[j], i);
 		}
 		for (j = 0; j < ARRAY_SIZE(xdpq_stat_names); j++)
-			ethtool_sprintf(&p, xdpq_stat_names[j]);
+			ethtool_puts(&p, xdpq_stat_names[j]);
 
 		for (i = 0; i < netdev->real_num_rx_queues; i++) {
 			for (j = 0; j < ARRAY_SIZE(rxq_stat_names); j++)
@@ -671,10 +671,10 @@ static void fun_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 						i);
 		}
 		for (j = 0; j < ARRAY_SIZE(rxq_stat_names); j++)
-			ethtool_sprintf(&p, rxq_stat_names[j]);
+			ethtool_puts(&p, rxq_stat_names[j]);
 
 		for (j = 0; j < ARRAY_SIZE(tls_stat_names); j++)
-			ethtool_sprintf(&p, tls_stat_names[j]);
+			ethtool_puts(&p, tls_stat_names[j]);
 		break;
 	default:
 		break;
@@ -977,44 +977,44 @@ static u32 fun_get_rxfh_key_size(struct net_device *netdev)
 	return sizeof(fp->rss_key);
 }
 
-static int fun_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			u8 *hfunc)
+static int fun_get_rxfh(struct net_device *netdev,
+			struct ethtool_rxfh_param *rxfh)
 {
 	const struct funeth_priv *fp = netdev_priv(netdev);
 
 	if (!fp->rss_cfg)
 		return -EOPNOTSUPP;
 
-	if (indir)
-		memcpy(indir, fp->indir_table,
+	if (rxfh->indir)
+		memcpy(rxfh->indir, fp->indir_table,
 		       sizeof(u32) * fp->indir_table_nentries);
 
-	if (key)
-		memcpy(key, fp->rss_key, sizeof(fp->rss_key));
+	if (rxfh->key)
+		memcpy(rxfh->key, fp->rss_key, sizeof(fp->rss_key));
 
-	if (hfunc)
-		*hfunc = fp->hash_algo == FUN_ETH_RSS_ALG_TOEPLITZ ?
-				ETH_RSS_HASH_TOP : ETH_RSS_HASH_CRC32;
+	rxfh->hfunc = fp->hash_algo == FUN_ETH_RSS_ALG_TOEPLITZ ?
+			ETH_RSS_HASH_TOP : ETH_RSS_HASH_CRC32;
 
 	return 0;
 }
 
-static int fun_set_rxfh(struct net_device *netdev, const u32 *indir,
-			const u8 *key, const u8 hfunc)
+static int fun_set_rxfh(struct net_device *netdev,
+			struct ethtool_rxfh_param *rxfh,
+			struct netlink_ext_ack *extack)
 {
 	struct funeth_priv *fp = netdev_priv(netdev);
-	const u32 *rss_indir = indir ? indir : fp->indir_table;
-	const u8 *rss_key = key ? key : fp->rss_key;
+	const u32 *rss_indir = rxfh->indir ? rxfh->indir : fp->indir_table;
+	const u8 *rss_key = rxfh->key ? rxfh->key : fp->rss_key;
 	enum fun_eth_hash_alg algo;
 
 	if (!fp->rss_cfg)
 		return -EOPNOTSUPP;
 
-	if (hfunc == ETH_RSS_HASH_NO_CHANGE)
+	if (rxfh->hfunc == ETH_RSS_HASH_NO_CHANGE)
 		algo = fp->hash_algo;
-	else if (hfunc == ETH_RSS_HASH_CRC32)
+	else if (rxfh->hfunc == ETH_RSS_HASH_CRC32)
 		algo = FUN_ETH_RSS_ALG_CRC32;
-	else if (hfunc == ETH_RSS_HASH_TOP)
+	else if (rxfh->hfunc == ETH_RSS_HASH_TOP)
 		algo = FUN_ETH_RSS_ALG_TOEPLITZ;
 	else
 		return -EINVAL;
@@ -1031,10 +1031,10 @@ static int fun_set_rxfh(struct net_device *netdev, const u32 *indir,
 	}
 
 	fp->hash_algo = algo;
-	if (key)
-		memcpy(fp->rss_key, key, sizeof(fp->rss_key));
-	if (indir)
-		memcpy(fp->indir_table, indir,
+	if (rxfh->key)
+		memcpy(fp->rss_key, rxfh->key, sizeof(fp->rss_key));
+	if (rxfh->indir)
+		memcpy(fp->indir_table, rxfh->indir,
 		       sizeof(u32) * fp->indir_table_nentries);
 	return 0;
 }
diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index 0d1e681be250..b80349154604 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -8,6 +8,7 @@
 #define _GVE_H_
 
 #include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
 #include <linux/netdevice.h>
 #include <linux/pci.h>
 #include <linux/u64_stats_sync.h>
@@ -41,12 +42,16 @@
 #define NIC_TX_STATS_REPORT_NUM	0
 #define NIC_RX_STATS_REPORT_NUM	4
 
+#define GVE_ADMINQ_BUFFER_SIZE 4096
+
 #define GVE_DATA_SLOT_ADDR_PAGE_MASK (~(PAGE_SIZE - 1))
 
 /* PTYPEs are always 10 bits. */
 #define GVE_NUM_PTYPES	1024
 
-#define GVE_RX_BUFFER_SIZE_DQO 2048
+#define GVE_DEFAULT_RX_BUFFER_SIZE 2048
+
+#define GVE_DEFAULT_RX_BUFFER_OFFSET 2048
 
 #define GVE_XDP_ACTIONS 5
 
@@ -672,6 +677,7 @@ struct gve_priv {
 	/* Admin queue - see gve_adminq.h*/
 	union gve_adminq_command *adminq;
 	dma_addr_t adminq_bus_addr;
+	struct dma_pool *adminq_pool;
 	u32 adminq_mask; /* masks prod_cnt to adminq size */
 	u32 adminq_prod_cnt; /* free-running count of AQ cmds executed */
 	u32 adminq_cmd_fail; /* free-running count of AQ cmds failed */
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c
index 79db7a6d42bc..12fbd723ecc6 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.c
+++ b/drivers/net/ethernet/google/gve/gve_adminq.c
@@ -194,12 +194,19 @@ gve_process_device_options(struct gve_priv *priv,
 
 int gve_adminq_alloc(struct device *dev, struct gve_priv *priv)
 {
-	priv->adminq = dma_alloc_coherent(dev, PAGE_SIZE,
-					  &priv->adminq_bus_addr, GFP_KERNEL);
-	if (unlikely(!priv->adminq))
+	priv->adminq_pool = dma_pool_create("adminq_pool", dev,
+					    GVE_ADMINQ_BUFFER_SIZE, 0, 0);
+	if (unlikely(!priv->adminq_pool))
 		return -ENOMEM;
+	priv->adminq = dma_pool_alloc(priv->adminq_pool, GFP_KERNEL,
+				      &priv->adminq_bus_addr);
+	if (unlikely(!priv->adminq)) {
+		dma_pool_destroy(priv->adminq_pool);
+		return -ENOMEM;
+	}
 
-	priv->adminq_mask = (PAGE_SIZE / sizeof(union gve_adminq_command)) - 1;
+	priv->adminq_mask =
+		(GVE_ADMINQ_BUFFER_SIZE / sizeof(union gve_adminq_command)) - 1;
 	priv->adminq_prod_cnt = 0;
 	priv->adminq_cmd_fail = 0;
 	priv->adminq_timeouts = 0;
@@ -218,9 +225,20 @@ int gve_adminq_alloc(struct device *dev, struct gve_priv *priv)
 	priv->adminq_get_ptype_map_cnt = 0;
 
 	/* Setup Admin queue with the device */
-	iowrite32be(priv->adminq_bus_addr / PAGE_SIZE,
-		    &priv->reg_bar0->adminq_pfn);
-
+	if (priv->pdev->revision < 0x1) {
+		iowrite32be(priv->adminq_bus_addr / PAGE_SIZE,
+			    &priv->reg_bar0->adminq_pfn);
+	} else {
+		iowrite16be(GVE_ADMINQ_BUFFER_SIZE,
+			    &priv->reg_bar0->adminq_length);
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+		iowrite32be(priv->adminq_bus_addr >> 32,
+			    &priv->reg_bar0->adminq_base_address_hi);
+#endif
+		iowrite32be(priv->adminq_bus_addr,
+			    &priv->reg_bar0->adminq_base_address_lo);
+		iowrite32be(GVE_DRIVER_STATUS_RUN_MASK, &priv->reg_bar0->driver_status);
+	}
 	gve_set_admin_queue_ok(priv);
 	return 0;
 }
@@ -230,16 +248,27 @@ void gve_adminq_release(struct gve_priv *priv)
 	int i = 0;
 
 	/* Tell the device the adminq is leaving */
-	iowrite32be(0x0, &priv->reg_bar0->adminq_pfn);
-	while (ioread32be(&priv->reg_bar0->adminq_pfn)) {
-		/* If this is reached the device is unrecoverable and still
-		 * holding memory. Continue looping to avoid memory corruption,
-		 * but WARN so it is visible what is going on.
-		 */
-		if (i == GVE_MAX_ADMINQ_RELEASE_CHECK)
-			WARN(1, "Unrecoverable platform error!");
-		i++;
-		msleep(GVE_ADMINQ_SLEEP_LEN);
+	if (priv->pdev->revision < 0x1) {
+		iowrite32be(0x0, &priv->reg_bar0->adminq_pfn);
+		while (ioread32be(&priv->reg_bar0->adminq_pfn)) {
+			/* If this is reached the device is unrecoverable and still
+			 * holding memory. Continue looping to avoid memory corruption,
+			 * but WARN so it is visible what is going on.
+			 */
+			if (i == GVE_MAX_ADMINQ_RELEASE_CHECK)
+				WARN(1, "Unrecoverable platform error!");
+			i++;
+			msleep(GVE_ADMINQ_SLEEP_LEN);
+		}
+	} else {
+		iowrite32be(GVE_DRIVER_STATUS_RESET_MASK, &priv->reg_bar0->driver_status);
+		while (!(ioread32be(&priv->reg_bar0->device_status)
+				& GVE_DEVICE_STATUS_DEVICE_IS_RESET)) {
+			if (i == GVE_MAX_ADMINQ_RELEASE_CHECK)
+				WARN(1, "Unrecoverable platform error!");
+			i++;
+			msleep(GVE_ADMINQ_SLEEP_LEN);
+		}
 	}
 	gve_clear_device_rings_ok(priv);
 	gve_clear_device_resources_ok(priv);
@@ -251,7 +280,8 @@ void gve_adminq_free(struct device *dev, struct gve_priv *priv)
 	if (!gve_get_admin_queue_ok(priv))
 		return;
 	gve_adminq_release(priv);
-	dma_free_coherent(dev, PAGE_SIZE, priv->adminq, priv->adminq_bus_addr);
+	dma_pool_free(priv->adminq_pool, priv->adminq, priv->adminq_bus_addr);
+	dma_pool_destroy(priv->adminq_pool);
 	gve_clear_admin_queue_ok(priv);
 }
 
@@ -697,18 +727,7 @@ static int gve_set_desc_cnt(struct gve_priv *priv,
 			    struct gve_device_descriptor *descriptor)
 {
 	priv->tx_desc_cnt = be16_to_cpu(descriptor->tx_queue_entries);
-	if (priv->tx_desc_cnt * sizeof(priv->tx->desc[0]) < PAGE_SIZE) {
-		dev_err(&priv->pdev->dev, "Tx desc count %d too low\n",
-			priv->tx_desc_cnt);
-		return -EINVAL;
-	}
 	priv->rx_desc_cnt = be16_to_cpu(descriptor->rx_queue_entries);
-	if (priv->rx_desc_cnt * sizeof(priv->rx->desc.desc_ring[0])
-	    < PAGE_SIZE) {
-		dev_err(&priv->pdev->dev, "Rx desc count %d too low\n",
-			priv->rx_desc_cnt);
-		return -EINVAL;
-	}
 	return 0;
 }
 
@@ -778,8 +797,8 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 	u16 mtu;
 
 	memset(&cmd, 0, sizeof(cmd));
-	descriptor = dma_alloc_coherent(&priv->pdev->dev, PAGE_SIZE,
-					&descriptor_bus, GFP_KERNEL);
+	descriptor = dma_pool_alloc(priv->adminq_pool, GFP_KERNEL,
+				    &descriptor_bus);
 	if (!descriptor)
 		return -ENOMEM;
 	cmd.opcode = cpu_to_be32(GVE_ADMINQ_DESCRIBE_DEVICE);
@@ -787,7 +806,8 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 						cpu_to_be64(descriptor_bus);
 	cmd.describe_device.device_descriptor_version =
 			cpu_to_be32(GVE_ADMINQ_DEVICE_DESCRIPTOR_VERSION);
-	cmd.describe_device.available_length = cpu_to_be32(PAGE_SIZE);
+	cmd.describe_device.available_length =
+		cpu_to_be32(GVE_ADMINQ_BUFFER_SIZE);
 
 	err = gve_adminq_execute_cmd(priv, &cmd);
 	if (err)
@@ -868,8 +888,7 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 				      dev_op_jumbo_frames, dev_op_dqo_qpl);
 
 free_device_descriptor:
-	dma_free_coherent(&priv->pdev->dev, PAGE_SIZE, descriptor,
-			  descriptor_bus);
+	dma_pool_free(priv->adminq_pool, descriptor, descriptor_bus);
 	return err;
 }
 
@@ -898,6 +917,7 @@ int gve_adminq_register_page_list(struct gve_priv *priv,
 		.page_list_id = cpu_to_be32(qpl->id),
 		.num_pages = cpu_to_be32(num_entries),
 		.page_address_list_addr = cpu_to_be64(page_list_bus),
+		.page_size = cpu_to_be64(PAGE_SIZE),
 	};
 
 	err = gve_adminq_execute_cmd(priv, &cmd);
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h
index 38a22279e863..5865ccdccbd0 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.h
+++ b/drivers/net/ethernet/google/gve/gve_adminq.h
@@ -219,9 +219,10 @@ struct gve_adminq_register_page_list {
 	__be32 page_list_id;
 	__be32 num_pages;
 	__be64 page_address_list_addr;
+	__be64 page_size;
 };
 
-static_assert(sizeof(struct gve_adminq_register_page_list) == 16);
+static_assert(sizeof(struct gve_adminq_register_page_list) == 24);
 
 struct gve_adminq_unregister_page_list {
 	__be32 page_list_id;
diff --git a/drivers/net/ethernet/google/gve/gve_dqo.h b/drivers/net/ethernet/google/gve/gve_dqo.h
index 1eb4d5fd8561..c36b93f0de15 100644
--- a/drivers/net/ethernet/google/gve/gve_dqo.h
+++ b/drivers/net/ethernet/google/gve/gve_dqo.h
@@ -33,6 +33,9 @@
 #define GVE_DEALLOCATE_COMPL_TIMEOUT 60
 
 netdev_tx_t gve_tx_dqo(struct sk_buff *skb, struct net_device *dev);
+netdev_features_t gve_features_check_dqo(struct sk_buff *skb,
+					 struct net_device *dev,
+					 netdev_features_t features);
 bool gve_tx_poll_dqo(struct gve_notify_block *block, bool do_clean);
 int gve_rx_poll_dqo(struct gve_notify_block *block, int budget);
 int gve_tx_alloc_rings_dqo(struct gve_priv *priv);
diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
index 233e5946905e..e5397aa1e48f 100644
--- a/drivers/net/ethernet/google/gve/gve_ethtool.c
+++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
@@ -519,7 +519,7 @@ static int gve_set_tunable(struct net_device *netdev,
 	case ETHTOOL_RX_COPYBREAK:
 	{
 		u32 max_copybreak = gve_is_gqi(priv) ?
-			(PAGE_SIZE / 2) : priv->data_buffer_size_dqo;
+			GVE_DEFAULT_RX_BUFFER_SIZE : priv->data_buffer_size_dqo;
 
 		len = *(u32 *)value;
 		if (len > max_copybreak)
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 276f996f95dc..619bf63ec935 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -79,6 +79,18 @@ static int gve_verify_driver_compatibility(struct gve_priv *priv)
 	return err;
 }
 
+static netdev_features_t gve_features_check(struct sk_buff *skb,
+					    struct net_device *dev,
+					    netdev_features_t features)
+{
+	struct gve_priv *priv = netdev_priv(dev);
+
+	if (!gve_is_gqi(priv))
+		return gve_features_check_dqo(skb, dev, features);
+
+	return features;
+}
+
 static netdev_tx_t gve_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct gve_priv *priv = netdev_priv(dev);
@@ -254,10 +266,13 @@ static int gve_napi_poll(struct napi_struct *napi, int budget)
 	if (block->tx) {
 		if (block->tx->q_num < priv->tx_cfg.num_queues)
 			reschedule |= gve_tx_poll(block, budget);
-		else
+		else if (budget)
 			reschedule |= gve_xdp_poll(block, budget);
 	}
 
+	if (!budget)
+		return 0;
+
 	if (block->rx) {
 		work_done = gve_rx_poll(block, budget);
 		reschedule |= work_done == budget;
@@ -298,6 +313,9 @@ static int gve_napi_poll_dqo(struct napi_struct *napi, int budget)
 	if (block->tx)
 		reschedule |= gve_tx_poll_dqo(block, /*do_clean=*/true);
 
+	if (!budget)
+		return 0;
+
 	if (block->rx) {
 		work_done = gve_rx_poll_dqo(block, budget);
 		reschedule |= work_done == budget;
@@ -1310,7 +1328,7 @@ static int gve_open(struct net_device *dev)
 		/* Hard code this for now. This may be tuned in the future for
 		 * performance.
 		 */
-		priv->data_buffer_size_dqo = GVE_RX_BUFFER_SIZE_DQO;
+		priv->data_buffer_size_dqo = GVE_DEFAULT_RX_BUFFER_SIZE;
 	}
 	err = gve_create_rings(priv);
 	if (err)
@@ -1646,7 +1664,7 @@ static int verify_xdp_configuration(struct net_device *dev)
 		return -EOPNOTSUPP;
 	}
 
-	if (dev->mtu > (PAGE_SIZE / 2) - sizeof(struct ethhdr) - GVE_RX_PAD) {
+	if (dev->mtu > GVE_DEFAULT_RX_BUFFER_SIZE - sizeof(struct ethhdr) - GVE_RX_PAD) {
 		netdev_warn(dev, "XDP is not supported for mtu %d.\n",
 			    dev->mtu);
 		return -EOPNOTSUPP;
@@ -1873,6 +1891,7 @@ err:
 
 static const struct net_device_ops gve_netdev_ops = {
 	.ndo_start_xmit		=	gve_start_xmit,
+	.ndo_features_check	=	gve_features_check,
 	.ndo_open		=	gve_open,
 	.ndo_stop		=	gve_close,
 	.ndo_get_stats64	=	gve_get_stats,
diff --git a/drivers/net/ethernet/google/gve/gve_register.h b/drivers/net/ethernet/google/gve/gve_register.h
index fb655463c357..8e72b97008d6 100644
--- a/drivers/net/ethernet/google/gve/gve_register.h
+++ b/drivers/net/ethernet/google/gve/gve_register.h
@@ -18,11 +18,20 @@ struct gve_registers {
 	__be32	adminq_event_counter;
 	u8	reserved[3];
 	u8	driver_version;
+	__be32	adminq_base_address_hi;
+	__be32	adminq_base_address_lo;
+	__be16	adminq_length;
 };
 
 enum gve_device_status_flags {
 	GVE_DEVICE_STATUS_RESET_MASK		= BIT(1),
 	GVE_DEVICE_STATUS_LINK_STATUS_MASK	= BIT(2),
 	GVE_DEVICE_STATUS_REPORT_STATS_MASK	= BIT(3),
+	GVE_DEVICE_STATUS_DEVICE_IS_RESET	= BIT(4),
+};
+
+enum gve_driver_status_flags {
+	GVE_DRIVER_STATUS_RUN_MASK		= BIT(0),
+	GVE_DRIVER_STATUS_RESET_MASK		= BIT(1),
 };
 #endif /* _GVE_REGISTER_H_ */
diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c
index e84a066aa1a4..7a8dc5386fff 100644
--- a/drivers/net/ethernet/google/gve/gve_rx.c
+++ b/drivers/net/ethernet/google/gve/gve_rx.c
@@ -211,9 +211,9 @@ static int gve_rx_alloc_ring(struct gve_priv *priv, int idx)
 {
 	struct gve_rx_ring *rx = &priv->rx[idx];
 	struct device *hdev = &priv->pdev->dev;
-	u32 slots, npages;
 	int filled_pages;
 	size_t bytes;
+	u32 slots;
 	int err;
 
 	netif_dbg(priv, drv, priv->dev, "allocating rx ring\n");
@@ -270,12 +270,6 @@ static int gve_rx_alloc_ring(struct gve_priv *priv, int idx)
 
 	/* alloc rx desc ring */
 	bytes = sizeof(struct gve_rx_desc) * priv->rx_desc_cnt;
-	npages = bytes / PAGE_SIZE;
-	if (npages * PAGE_SIZE != bytes) {
-		err = -EIO;
-		goto abort_with_q_resources;
-	}
-
 	rx->desc.desc_ring = dma_alloc_coherent(hdev, bytes, &rx->desc.bus,
 						GFP_KERNEL);
 	if (!rx->desc.desc_ring) {
@@ -289,7 +283,7 @@ static int gve_rx_alloc_ring(struct gve_priv *priv, int idx)
 	/* Allocating half-page buffers allows page-flipping which is faster
 	 * than copying or allocating new pages.
 	 */
-	rx->packet_buffer_size = PAGE_SIZE / 2;
+	rx->packet_buffer_size = GVE_DEFAULT_RX_BUFFER_SIZE;
 	gve_rx_ctx_clear(&rx->ctx);
 	gve_rx_add_to_block(priv, idx);
 
@@ -405,10 +399,10 @@ static struct sk_buff *gve_rx_add_frags(struct napi_struct *napi,
 
 static void gve_rx_flip_buff(struct gve_rx_slot_page_info *page_info, __be64 *slot_addr)
 {
-	const __be64 offset = cpu_to_be64(PAGE_SIZE / 2);
+	const __be64 offset = cpu_to_be64(GVE_DEFAULT_RX_BUFFER_OFFSET);
 
 	/* "flip" to other packet buffer on this page */
-	page_info->page_offset ^= PAGE_SIZE / 2;
+	page_info->page_offset ^= GVE_DEFAULT_RX_BUFFER_OFFSET;
 	*(slot_addr) ^= offset;
 }
 
@@ -513,8 +507,7 @@ static struct sk_buff *gve_rx_copy_to_pool(struct gve_rx_ring *rx,
 		return NULL;
 
 	gve_dec_pagecnt_bias(copy_page_info);
-	copy_page_info->page_offset += rx->packet_buffer_size;
-	copy_page_info->page_offset &= (PAGE_SIZE - 1);
+	copy_page_info->page_offset ^= GVE_DEFAULT_RX_BUFFER_OFFSET;
 
 	if (copy_page_info->can_flip) {
 		/* We have used both halves of this copy page, it
@@ -1007,10 +1000,6 @@ int gve_rx_poll(struct gve_notify_block *block, int budget)
 
 	feat = block->napi.dev->features;
 
-	/* If budget is 0, do all the work */
-	if (budget == 0)
-		budget = INT_MAX;
-
 	if (budget > 0)
 		work_done = gve_clean_rx_done(rx, budget, feat);
 
diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c
index 6957a865cff3..07ba124780df 100644
--- a/drivers/net/ethernet/google/gve/gve_tx.c
+++ b/drivers/net/ethernet/google/gve/gve_tx.c
@@ -819,7 +819,7 @@ int gve_xdp_xmit_one(struct gve_priv *priv, struct gve_tx_ring *tx,
 	return 0;
 }
 
-#define GVE_TX_START_THRESH	PAGE_SIZE
+#define GVE_TX_START_THRESH	4096
 
 static int gve_clean_tx_done(struct gve_priv *priv, struct gve_tx_ring *tx,
 			     u32 to_do, bool try_to_wake)
@@ -925,10 +925,6 @@ bool gve_xdp_poll(struct gve_notify_block *block, int budget)
 	bool repoll;
 	u32 to_do;
 
-	/* If budget is 0, do all the work */
-	if (budget == 0)
-		budget = INT_MAX;
-
 	/* Find out how much work there is to be done */
 	nic_done = gve_tx_load_event_counter(priv, tx);
 	to_do = min_t(u32, (nic_done - tx->done), budget);
diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
index 1e19b834a613..f59c4710f118 100644
--- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
@@ -843,6 +843,16 @@ static bool gve_can_send_tso(const struct sk_buff *skb)
 	return true;
 }
 
+netdev_features_t gve_features_check_dqo(struct sk_buff *skb,
+					 struct net_device *dev,
+					 netdev_features_t features)
+{
+	if (skb_is_gso(skb) && !gve_can_send_tso(skb))
+		return features & ~NETIF_F_GSO_MASK;
+
+	return features;
+}
+
 /* Attempt to transmit specified SKB.
  *
  * Returns 0 if the SKB was transmitted or dropped.
@@ -854,11 +864,10 @@ static int gve_try_tx_skb(struct gve_priv *priv, struct gve_tx_ring *tx,
 	int num_buffer_descs;
 	int total_num_descs;
 
-	if (tx->dqo.qpl) {
-		if (skb_is_gso(skb))
-			if (unlikely(ipv6_hopopt_jumbo_remove(skb)))
-				goto drop;
+	if (skb_is_gso(skb) && unlikely(ipv6_hopopt_jumbo_remove(skb)))
+		goto drop;
 
+	if (tx->dqo.qpl) {
 		/* We do not need to verify the number of buffers used per
 		 * packet or per segment in case of TSO as with 2K size buffers
 		 * none of the TX packet rules would be violated.
@@ -868,24 +877,8 @@ static int gve_try_tx_skb(struct gve_priv *priv, struct gve_tx_ring *tx,
 		 */
 		num_buffer_descs = DIV_ROUND_UP(skb->len, GVE_TX_BUF_SIZE_DQO);
 	} else {
-		if (skb_is_gso(skb)) {
-			/* If TSO doesn't meet HW requirements, attempt to linearize the
-			 * packet.
-			 */
-			if (unlikely(!gve_can_send_tso(skb) &&
-				     skb_linearize(skb) < 0)) {
-				net_err_ratelimited("%s: Failed to transmit TSO packet\n",
-						    priv->dev->name);
-				goto drop;
-			}
-
-			if (unlikely(ipv6_hopopt_jumbo_remove(skb)))
-				goto drop;
-
-			num_buffer_descs = gve_num_buffer_descs_needed(skb);
-		} else {
-			num_buffer_descs = gve_num_buffer_descs_needed(skb);
-
+		num_buffer_descs = gve_num_buffer_descs_needed(skb);
+		if (!skb_is_gso(skb)) {
 			if (unlikely(num_buffer_descs > GVE_TX_MAX_DATA_DESCS)) {
 				if (unlikely(skb_linearize(skb) < 0))
 					goto drop;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
index 8f391e2adcc0..bdb7afaabdd0 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
@@ -678,7 +678,7 @@ static void hns_gmac_get_strings(u32 stringset, u8 *data)
 		return;
 
 	for (i = 0; i < ARRAY_SIZE(g_gmac_stats_string); i++)
-		ethtool_sprintf(&buff, g_gmac_stats_string[i].desc);
+		ethtool_puts(&buff, g_gmac_stats_string[i].desc);
 }
 
 static int hns_gmac_get_sset_count(int stringset)
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index 928d934cb21a..f75668c47935 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -66,6 +66,27 @@ static enum mac_mode hns_get_enet_interface(const struct hns_mac_cb *mac_cb)
 	}
 }
 
+static u32 hns_mac_link_anti_shake(struct mac_driver *mac_ctrl_drv)
+{
+#define HNS_MAC_LINK_WAIT_TIME 5
+#define HNS_MAC_LINK_WAIT_CNT 40
+
+	u32 link_status = 0;
+	int i;
+
+	if (!mac_ctrl_drv->get_link_status)
+		return link_status;
+
+	for (i = 0; i < HNS_MAC_LINK_WAIT_CNT; i++) {
+		msleep(HNS_MAC_LINK_WAIT_TIME);
+		mac_ctrl_drv->get_link_status(mac_ctrl_drv, &link_status);
+		if (!link_status)
+			break;
+	}
+
+	return link_status;
+}
+
 void hns_mac_get_link_status(struct hns_mac_cb *mac_cb, u32 *link_status)
 {
 	struct mac_driver *mac_ctrl_drv;
@@ -83,6 +104,14 @@ void hns_mac_get_link_status(struct hns_mac_cb *mac_cb, u32 *link_status)
 							       &sfp_prsnt);
 		if (!ret)
 			*link_status = *link_status && sfp_prsnt;
+
+		/* for FIBER port, it may have a fake link up.
+		 * when the link status changes from down to up, we need to do
+		 * anti-shake. the anti-shake time is base on tests.
+		 * only FIBER port need to do this.
+		 */
+		if (*link_status && !mac_cb->link)
+			*link_status = hns_mac_link_anti_shake(mac_ctrl_drv);
 	}
 
 	mac_cb->link = *link_status;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
index fc26ffaae620..c58833eb4830 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
@@ -752,7 +752,7 @@ static void hns_xgmac_get_strings(u32 stringset, u8 *data)
 		return;
 
 	for (i = 0; i < ARRAY_SIZE(g_xgmac_stats_string); i++)
-		ethtool_sprintf(&buff, g_xgmac_stats_string[i].desc);
+		ethtool_puts(&buff, g_xgmac_stats_string[i].desc);
 }
 
 /**
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 0900abf5c508..8a713eed4465 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -142,7 +142,8 @@ MODULE_DEVICE_TABLE(acpi, hns_enet_acpi_match);
 
 static void fill_desc(struct hnae_ring *ring, void *priv,
 		      int size, dma_addr_t dma, int frag_end,
-		      int buf_num, enum hns_desc_type type, int mtu)
+		      int buf_num, enum hns_desc_type type, int mtu,
+		      bool is_gso)
 {
 	struct hnae_desc *desc = &ring->desc[ring->next_to_use];
 	struct hnae_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use];
@@ -275,6 +276,15 @@ static int hns_nic_maybe_stop_tso(
 	return 0;
 }
 
+static int hns_nic_maybe_stop_tx_v2(struct sk_buff **out_skb, int *bnum,
+				    struct hnae_ring *ring)
+{
+	if (skb_is_gso(*out_skb))
+		return hns_nic_maybe_stop_tso(out_skb, bnum, ring);
+	else
+		return hns_nic_maybe_stop_tx(out_skb, bnum, ring);
+}
+
 static void fill_tso_desc(struct hnae_ring *ring, void *priv,
 			  int size, dma_addr_t dma, int frag_end,
 			  int buf_num, enum hns_desc_type type, int mtu)
@@ -300,6 +310,19 @@ static void fill_tso_desc(struct hnae_ring *ring, void *priv,
 				mtu);
 }
 
+static void fill_desc_v2(struct hnae_ring *ring, void *priv,
+			 int size, dma_addr_t dma, int frag_end,
+			 int buf_num, enum hns_desc_type type, int mtu,
+			 bool is_gso)
+{
+	if (is_gso)
+		fill_tso_desc(ring, priv, size, dma, frag_end, buf_num, type,
+			      mtu);
+	else
+		fill_v2_desc(ring, priv, size, dma, frag_end, buf_num, type,
+			     mtu);
+}
+
 netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev,
 				struct sk_buff *skb,
 				struct hns_nic_ring_data *ring_data)
@@ -313,6 +336,7 @@ netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev,
 	int seg_num;
 	dma_addr_t dma;
 	int size, next_to_use;
+	bool is_gso;
 	int i;
 
 	switch (priv->ops.maybe_stop_tx(&skb, &buf_num, ring)) {
@@ -339,8 +363,9 @@ netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev,
 		ring->stats.sw_err_cnt++;
 		goto out_err_tx_ok;
 	}
+	is_gso = skb_is_gso(skb);
 	priv->ops.fill_desc(ring, skb, size, dma, seg_num == 1 ? 1 : 0,
-			    buf_num, DESC_TYPE_SKB, ndev->mtu);
+			    buf_num, DESC_TYPE_SKB, ndev->mtu, is_gso);
 
 	/* fill the fragments */
 	for (i = 1; i < seg_num; i++) {
@@ -354,7 +379,7 @@ netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev,
 		}
 		priv->ops.fill_desc(ring, skb_frag_page(frag), size, dma,
 				    seg_num - 1 == i ? 1 : 0, buf_num,
-				    DESC_TYPE_PAGE, ndev->mtu);
+				    DESC_TYPE_PAGE, ndev->mtu, is_gso);
 	}
 
 	/*complete translate all packets*/
@@ -1776,15 +1801,6 @@ static int hns_nic_set_features(struct net_device *netdev,
 			netdev_info(netdev, "enet v1 do not support tso!\n");
 		break;
 	default:
-		if (features & (NETIF_F_TSO | NETIF_F_TSO6)) {
-			priv->ops.fill_desc = fill_tso_desc;
-			priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tso;
-			/* The chip only support 7*4096 */
-			netif_set_tso_max_size(netdev, 7 * 4096);
-		} else {
-			priv->ops.fill_desc = fill_v2_desc;
-			priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tx;
-		}
 		break;
 	}
 	netdev->features = features;
@@ -2159,16 +2175,9 @@ static void hns_nic_set_priv_ops(struct net_device *netdev)
 		priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tx;
 	} else {
 		priv->ops.get_rxd_bnum = get_v2rx_desc_bnum;
-		if ((netdev->features & NETIF_F_TSO) ||
-		    (netdev->features & NETIF_F_TSO6)) {
-			priv->ops.fill_desc = fill_tso_desc;
-			priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tso;
-			/* This chip only support 7*4096 */
-			netif_set_tso_max_size(netdev, 7 * 4096);
-		} else {
-			priv->ops.fill_desc = fill_v2_desc;
-			priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tx;
-		}
+		priv->ops.fill_desc = fill_desc_v2;
+		priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tx_v2;
+		netif_set_tso_max_size(netdev, 7 * 4096);
 		/* enable tso when init
 		 * control tso on/off through TSE bit in bd
 		 */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.h b/drivers/net/ethernet/hisilicon/hns/hns_enet.h
index ffa9d6573f54..3f3ee032f631 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.h
@@ -44,7 +44,8 @@ struct hns_nic_ring_data {
 struct hns_nic_ops {
 	void (*fill_desc)(struct hnae_ring *ring, void *priv,
 			  int size, dma_addr_t dma, int frag_end,
-			  int buf_num, enum hns_desc_type type, int mtu);
+			  int buf_num, enum hns_desc_type type, int mtu,
+			  bool is_gso);
 	int (*maybe_stop_tx)(struct sk_buff **out_skb,
 			     int *bnum, struct hnae_ring *ring);
 	void (*get_rxd_bnum)(u32 bnum_flag, int *out_bnum);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index b54f3706fb97..a5bb306b2cf1 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -912,42 +912,41 @@ static void hns_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 
 	if (stringset == ETH_SS_TEST) {
 		if (priv->ae_handle->phy_if != PHY_INTERFACE_MODE_XGMII)
-			ethtool_sprintf(&buff,
-					hns_nic_test_strs[MAC_INTERNALLOOP_MAC]);
-		ethtool_sprintf(&buff,
-				hns_nic_test_strs[MAC_INTERNALLOOP_SERDES]);
+			ethtool_puts(&buff,
+				     hns_nic_test_strs[MAC_INTERNALLOOP_MAC]);
+		ethtool_puts(&buff, hns_nic_test_strs[MAC_INTERNALLOOP_SERDES]);
 		if ((netdev->phydev) && (!netdev->phydev->is_c45))
-			ethtool_sprintf(&buff,
-					hns_nic_test_strs[MAC_INTERNALLOOP_PHY]);
+			ethtool_puts(&buff,
+				     hns_nic_test_strs[MAC_INTERNALLOOP_PHY]);
 
 	} else {
-		ethtool_sprintf(&buff, "rx_packets");
-		ethtool_sprintf(&buff, "tx_packets");
-		ethtool_sprintf(&buff, "rx_bytes");
-		ethtool_sprintf(&buff, "tx_bytes");
-		ethtool_sprintf(&buff, "rx_errors");
-		ethtool_sprintf(&buff, "tx_errors");
-		ethtool_sprintf(&buff, "rx_dropped");
-		ethtool_sprintf(&buff, "tx_dropped");
-		ethtool_sprintf(&buff, "multicast");
-		ethtool_sprintf(&buff, "collisions");
-		ethtool_sprintf(&buff, "rx_over_errors");
-		ethtool_sprintf(&buff, "rx_crc_errors");
-		ethtool_sprintf(&buff, "rx_frame_errors");
-		ethtool_sprintf(&buff, "rx_fifo_errors");
-		ethtool_sprintf(&buff, "rx_missed_errors");
-		ethtool_sprintf(&buff, "tx_aborted_errors");
-		ethtool_sprintf(&buff, "tx_carrier_errors");
-		ethtool_sprintf(&buff, "tx_fifo_errors");
-		ethtool_sprintf(&buff, "tx_heartbeat_errors");
-		ethtool_sprintf(&buff, "rx_length_errors");
-		ethtool_sprintf(&buff, "tx_window_errors");
-		ethtool_sprintf(&buff, "rx_compressed");
-		ethtool_sprintf(&buff, "tx_compressed");
-		ethtool_sprintf(&buff, "netdev_rx_dropped");
-		ethtool_sprintf(&buff, "netdev_tx_dropped");
-
-		ethtool_sprintf(&buff, "netdev_tx_timeout");
+		ethtool_puts(&buff, "rx_packets");
+		ethtool_puts(&buff, "tx_packets");
+		ethtool_puts(&buff, "rx_bytes");
+		ethtool_puts(&buff, "tx_bytes");
+		ethtool_puts(&buff, "rx_errors");
+		ethtool_puts(&buff, "tx_errors");
+		ethtool_puts(&buff, "rx_dropped");
+		ethtool_puts(&buff, "tx_dropped");
+		ethtool_puts(&buff, "multicast");
+		ethtool_puts(&buff, "collisions");
+		ethtool_puts(&buff, "rx_over_errors");
+		ethtool_puts(&buff, "rx_crc_errors");
+		ethtool_puts(&buff, "rx_frame_errors");
+		ethtool_puts(&buff, "rx_fifo_errors");
+		ethtool_puts(&buff, "rx_missed_errors");
+		ethtool_puts(&buff, "tx_aborted_errors");
+		ethtool_puts(&buff, "tx_carrier_errors");
+		ethtool_puts(&buff, "tx_fifo_errors");
+		ethtool_puts(&buff, "tx_heartbeat_errors");
+		ethtool_puts(&buff, "rx_length_errors");
+		ethtool_puts(&buff, "tx_window_errors");
+		ethtool_puts(&buff, "rx_compressed");
+		ethtool_puts(&buff, "tx_compressed");
+		ethtool_puts(&buff, "netdev_rx_dropped");
+		ethtool_puts(&buff, "netdev_tx_dropped");
+
+		ethtool_puts(&buff, "netdev_tx_timeout");
 
 		h->dev->ops->get_strings(h, stringset, buff);
 	}
@@ -1187,7 +1186,7 @@ hns_get_rss_indir_size(struct net_device *netdev)
 }
 
 static int
-hns_get_rss(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc)
+hns_get_rss(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
 {
 	struct hns_nic_priv *priv = netdev_priv(netdev);
 	struct hnae_ae_ops *ops;
@@ -1200,15 +1199,16 @@ hns_get_rss(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc)
 
 	ops = priv->ae_handle->dev->ops;
 
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
-	return ops->get_rss(priv->ae_handle, indir, key, hfunc);
+	return ops->get_rss(priv->ae_handle,
+			    rxfh->indir, rxfh->key, &rxfh->hfunc);
 }
 
 static int
-hns_set_rss(struct net_device *netdev, const u32 *indir, const u8 *key,
-	    const u8 hfunc)
+hns_set_rss(struct net_device *netdev, struct ethtool_rxfh_param *rxfh,
+	    struct netlink_ext_ack *extack)
 {
 	struct hns_nic_priv *priv = netdev_priv(netdev);
 	struct hnae_ae_ops *ops;
@@ -1221,12 +1221,14 @@ hns_set_rss(struct net_device *netdev, const u32 *indir, const u8 *key,
 
 	ops = priv->ae_handle->dev->ops;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) {
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP) {
 		netdev_err(netdev, "Invalid hfunc!\n");
 		return -EOPNOTSUPP;
 	}
 
-	return ops->set_rss(priv->ae_handle, indir, key, hfunc);
+	return ops->set_rss(priv->ae_handle,
+			    rxfh->indir, rxfh->key, rxfh->hfunc);
 }
 
 static int hns_get_rxnfc(struct net_device *netdev,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 0b138635bafa..c083d1d10767 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -503,11 +503,14 @@ static void hns3_get_coal_info(struct hns3_enet_tqp_vector *tqp_vector,
 	}
 
 	sprintf(result[j++], "%d", i);
-	sprintf(result[j++], "%s", dim_state_str[dim->state]);
+	sprintf(result[j++], "%s", dim->state < ARRAY_SIZE(dim_state_str) ?
+		dim_state_str[dim->state] : "unknown");
 	sprintf(result[j++], "%u", dim->profile_ix);
-	sprintf(result[j++], "%s", dim_cqe_mode_str[dim->mode]);
+	sprintf(result[j++], "%s", dim->mode < ARRAY_SIZE(dim_cqe_mode_str) ?
+		dim_cqe_mode_str[dim->mode] : "unknown");
 	sprintf(result[j++], "%s",
-		dim_tune_stat_str[dim->tune_state]);
+		dim->tune_state < ARRAY_SIZE(dim_tune_stat_str) ?
+		dim_tune_stat_str[dim->tune_state] : "unknown");
 	sprintf(result[j++], "%u", dim->steps_left);
 	sprintf(result[j++], "%u", dim->steps_right);
 	sprintf(result[j++], "%u", dim->tired);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 06117502001f..f1695c889d3a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1041,7 +1041,7 @@ static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring)
 		return;
 
 	order = get_order(alloc_size);
-	if (order > MAX_ORDER) {
+	if (order > MAX_PAGE_ORDER) {
 		if (net_ratelimit())
 			dev_warn(ring_to_dev(ring), "failed to allocate tx spare buffer, exceed to max order\n");
 		return;
@@ -5139,7 +5139,7 @@ static int hns3_init_mac_addr(struct net_device *netdev)
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	char format_mac_addr[HNAE3_FORMAT_MAC_ADDR_LEN];
 	struct hnae3_handle *h = priv->ae_handle;
-	u8 mac_addr_temp[ETH_ALEN];
+	u8 mac_addr_temp[ETH_ALEN] = {0};
 	int ret = 0;
 
 	if (h->ae_algo->ops->get_mac_addr)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 682239f33082..999a0ee162a6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -941,19 +941,21 @@ static u32 hns3_get_rss_indir_size(struct net_device *netdev)
 	return ae_dev->dev_specs.rss_ind_tbl_size;
 }
 
-static int hns3_get_rss(struct net_device *netdev, u32 *indir, u8 *key,
-			u8 *hfunc)
+static int hns3_get_rss(struct net_device *netdev,
+			struct ethtool_rxfh_param *rxfh)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 
 	if (!h->ae_algo->ops->get_rss)
 		return -EOPNOTSUPP;
 
-	return h->ae_algo->ops->get_rss(h, indir, key, hfunc);
+	return h->ae_algo->ops->get_rss(h, rxfh->indir, rxfh->key,
+					&rxfh->hfunc);
 }
 
-static int hns3_set_rss(struct net_device *netdev, const u32 *indir,
-			const u8 *key, const u8 hfunc)
+static int hns3_set_rss(struct net_device *netdev,
+			struct ethtool_rxfh_param *rxfh,
+			struct netlink_ext_ack *extack)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
@@ -962,19 +964,22 @@ static int hns3_set_rss(struct net_device *netdev, const u32 *indir,
 		return -EOPNOTSUPP;
 
 	if ((ae_dev->dev_version < HNAE3_DEVICE_VERSION_V2 &&
-	     hfunc != ETH_RSS_HASH_TOP) || (hfunc != ETH_RSS_HASH_NO_CHANGE &&
-	     hfunc != ETH_RSS_HASH_TOP && hfunc != ETH_RSS_HASH_XOR)) {
+	     rxfh->hfunc != ETH_RSS_HASH_TOP) ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP &&
+	     rxfh->hfunc != ETH_RSS_HASH_XOR)) {
 		netdev_err(netdev, "hash func not supported\n");
 		return -EOPNOTSUPP;
 	}
 
-	if (!indir) {
+	if (!rxfh->indir) {
 		netdev_err(netdev,
 			   "set rss failed for indir is empty\n");
 		return -EOPNOTSUPP;
 	}
 
-	return h->ae_algo->ops->set_rss(h, indir, key, hfunc);
+	return h->ae_algo->ops->set_rss(h, rxfh->indir, rxfh->key,
+					rxfh->hfunc);
 }
 
 static int hns3_get_rxnfc(struct net_device *netdev,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index ff3f8f424ad9..9ec471ced3d6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -981,19 +981,24 @@ static const struct hclge_dbg_item tm_pri_items[] = {
 
 static int hclge_dbg_dump_tm_pri(struct hclge_dev *hdev, char *buf, int len)
 {
-	char data_str[ARRAY_SIZE(tm_pri_items)][HCLGE_DBG_DATA_STR_LEN];
 	struct hclge_tm_shaper_para c_shaper_para, p_shaper_para;
 	char *result[ARRAY_SIZE(tm_pri_items)], *sch_mode_str;
 	char content[HCLGE_DBG_TM_INFO_LEN];
 	u8 pri_num, sch_mode, weight, i, j;
+	char *data_str;
 	int pos, ret;
 
 	ret = hclge_tm_get_pri_num(hdev, &pri_num);
 	if (ret)
 		return ret;
 
+	data_str = kcalloc(ARRAY_SIZE(tm_pri_items), HCLGE_DBG_DATA_STR_LEN,
+			   GFP_KERNEL);
+	if (!data_str)
+		return -ENOMEM;
+
 	for (i = 0; i < ARRAY_SIZE(tm_pri_items); i++)
-		result[i] = &data_str[i][0];
+		result[i] = &data_str[i * HCLGE_DBG_DATA_STR_LEN];
 
 	hclge_dbg_fill_content(content, sizeof(content), tm_pri_items,
 			       NULL, ARRAY_SIZE(tm_pri_items));
@@ -1002,23 +1007,23 @@ static int hclge_dbg_dump_tm_pri(struct hclge_dev *hdev, char *buf, int len)
 	for (i = 0; i < pri_num; i++) {
 		ret = hclge_tm_get_pri_sch_mode(hdev, i, &sch_mode);
 		if (ret)
-			return ret;
+			goto out;
 
 		ret = hclge_tm_get_pri_weight(hdev, i, &weight);
 		if (ret)
-			return ret;
+			goto out;
 
 		ret = hclge_tm_get_pri_shaper(hdev, i,
 					      HCLGE_OPC_TM_PRI_C_SHAPPING,
 					      &c_shaper_para);
 		if (ret)
-			return ret;
+			goto out;
 
 		ret = hclge_tm_get_pri_shaper(hdev, i,
 					      HCLGE_OPC_TM_PRI_P_SHAPPING,
 					      &p_shaper_para);
 		if (ret)
-			return ret;
+			goto out;
 
 		sch_mode_str = sch_mode & HCLGE_TM_TX_SCHD_DWRR_MSK ? "dwrr" :
 			       "sp";
@@ -1035,7 +1040,9 @@ static int hclge_dbg_dump_tm_pri(struct hclge_dev *hdev, char *buf, int len)
 		pos += scnprintf(buf + pos, len - pos, "%s", content);
 	}
 
-	return 0;
+out:
+	kfree(data_str);
+	return ret;
 }
 
 static const struct hclge_dbg_item tm_qset_items[] = {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 66e5807903a0..5ea9e59569ef 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -61,6 +61,7 @@ static void hclge_sync_fd_table(struct hclge_dev *hdev);
 static void hclge_update_fec_stats(struct hclge_dev *hdev);
 static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret,
 				      int wait_cnt);
+static int hclge_update_port_info(struct hclge_dev *hdev);
 
 static struct hnae3_ae_algo ae_algo;
 
@@ -3041,6 +3042,9 @@ static void hclge_update_link_status(struct hclge_dev *hdev)
 
 	if (state != hdev->hw.mac.link) {
 		hdev->hw.mac.link = state;
+		if (state == HCLGE_LINK_STATUS_UP)
+			hclge_update_port_info(hdev);
+
 		client->ops->link_status_change(handle, state);
 		hclge_config_mac_tnl_int(hdev, state);
 		if (rclient && rclient->ops->link_status_change)
@@ -10025,8 +10029,6 @@ static void hclge_rm_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id,
 	struct hclge_vport_vlan_cfg *vlan, *tmp;
 	struct hclge_dev *hdev = vport->back;
 
-	mutex_lock(&hdev->vport_lock);
-
 	list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) {
 		if (vlan->vlan_id == vlan_id) {
 			if (is_write_tbl && vlan->hd_tbl_status)
@@ -10041,8 +10043,6 @@ static void hclge_rm_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id,
 			break;
 		}
 	}
-
-	mutex_unlock(&hdev->vport_lock);
 }
 
 void hclge_rm_vport_all_vlan_table(struct hclge_vport *vport, bool is_del_list)
@@ -10451,11 +10451,16 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto,
 	 * handle mailbox. Just record the vlan id, and remove it after
 	 * reset finished.
 	 */
+	mutex_lock(&hdev->vport_lock);
 	if ((test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) ||
 	     test_bit(HCLGE_STATE_RST_FAIL, &hdev->state)) && is_kill) {
 		set_bit(vlan_id, vport->vlan_del_fail_bmap);
+		mutex_unlock(&hdev->vport_lock);
 		return -EBUSY;
+	} else if (!is_kill && test_bit(vlan_id, vport->vlan_del_fail_bmap)) {
+		clear_bit(vlan_id, vport->vlan_del_fail_bmap);
 	}
+	mutex_unlock(&hdev->vport_lock);
 
 	/* when port base vlan enabled, we use port base vlan as the vlan
 	 * filter entry. In this case, we don't update vlan filter table
@@ -10470,17 +10475,22 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto,
 	}
 
 	if (!ret) {
-		if (!is_kill)
+		if (!is_kill) {
 			hclge_add_vport_vlan_table(vport, vlan_id,
 						   writen_to_tbl);
-		else if (is_kill && vlan_id != 0)
+		} else if (is_kill && vlan_id != 0) {
+			mutex_lock(&hdev->vport_lock);
 			hclge_rm_vport_vlan_table(vport, vlan_id, false);
+			mutex_unlock(&hdev->vport_lock);
+		}
 	} else if (is_kill) {
 		/* when remove hw vlan filter failed, record the vlan id,
 		 * and try to remove it from hw later, to be consistence
 		 * with stack
 		 */
+		mutex_lock(&hdev->vport_lock);
 		set_bit(vlan_id, vport->vlan_del_fail_bmap);
+		mutex_unlock(&hdev->vport_lock);
 	}
 
 	hclge_set_vport_vlan_fltr_change(vport);
@@ -10520,6 +10530,7 @@ static void hclge_sync_vlan_filter(struct hclge_dev *hdev)
 	int i, ret, sync_cnt = 0;
 	u16 vlan_id;
 
+	mutex_lock(&hdev->vport_lock);
 	/* start from vport 1 for PF is always alive */
 	for (i = 0; i < hdev->num_alloc_vport; i++) {
 		struct hclge_vport *vport = &hdev->vport[i];
@@ -10530,21 +10541,26 @@ static void hclge_sync_vlan_filter(struct hclge_dev *hdev)
 			ret = hclge_set_vlan_filter_hw(hdev, htons(ETH_P_8021Q),
 						       vport->vport_id, vlan_id,
 						       true);
-			if (ret && ret != -EINVAL)
+			if (ret && ret != -EINVAL) {
+				mutex_unlock(&hdev->vport_lock);
 				return;
+			}
 
 			clear_bit(vlan_id, vport->vlan_del_fail_bmap);
 			hclge_rm_vport_vlan_table(vport, vlan_id, false);
 			hclge_set_vport_vlan_fltr_change(vport);
 
 			sync_cnt++;
-			if (sync_cnt >= HCLGE_MAX_SYNC_COUNT)
+			if (sync_cnt >= HCLGE_MAX_SYNC_COUNT) {
+				mutex_unlock(&hdev->vport_lock);
 				return;
+			}
 
 			vlan_id = find_first_bit(vport->vlan_del_fail_bmap,
 						 VLAN_N_VID);
 		}
 	}
+	mutex_unlock(&hdev->vport_lock);
 
 	hclge_sync_vlan_fltr_state(hdev);
 }
@@ -11651,6 +11667,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 		goto err_msi_irq_uninit;
 
 	if (hdev->hw.mac.media_type == HNAE3_MEDIA_TYPE_COPPER) {
+		clear_bit(HNAE3_DEV_SUPPORT_FEC_B, ae_dev->caps);
 		if (hnae3_dev_phy_imp_supported(hdev))
 			ret = hclge_update_tp_port_info(hdev);
 		else
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index a4d68fb216fb..0aa9beefd1c7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1206,6 +1206,8 @@ static int hclgevf_set_vlan_filter(struct hnae3_handle *handle,
 	     test_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state)) && is_kill) {
 		set_bit(vlan_id, hdev->vlan_del_fail_bmap);
 		return -EBUSY;
+	} else if (!is_kill && test_bit(vlan_id, hdev->vlan_del_fail_bmap)) {
+		clear_bit(vlan_id, hdev->vlan_del_fail_bmap);
 	}
 
 	hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_VLAN,
@@ -1233,20 +1235,25 @@ static void hclgevf_sync_vlan_filter(struct hclgevf_dev *hdev)
 	int ret, sync_cnt = 0;
 	u16 vlan_id;
 
+	if (bitmap_empty(hdev->vlan_del_fail_bmap, VLAN_N_VID))
+		return;
+
+	rtnl_lock();
 	vlan_id = find_first_bit(hdev->vlan_del_fail_bmap, VLAN_N_VID);
 	while (vlan_id != VLAN_N_VID) {
 		ret = hclgevf_set_vlan_filter(handle, htons(ETH_P_8021Q),
 					      vlan_id, true);
 		if (ret)
-			return;
+			break;
 
 		clear_bit(vlan_id, hdev->vlan_del_fail_bmap);
 		sync_cnt++;
 		if (sync_cnt >= HCLGEVF_MAX_SYNC_COUNT)
-			return;
+			break;
 
 		vlan_id = find_first_bit(hdev->vlan_del_fail_bmap, VLAN_N_VID);
 	}
+	rtnl_unlock();
 }
 
 static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
@@ -1974,8 +1981,18 @@ static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev,
 	return HCLGEVF_VECTOR0_EVENT_OTHER;
 }
 
+static void hclgevf_reset_timer(struct timer_list *t)
+{
+	struct hclgevf_dev *hdev = from_timer(hdev, t, reset_timer);
+
+	hclgevf_clear_event_cause(hdev, HCLGEVF_VECTOR0_EVENT_RST);
+	hclgevf_reset_task_schedule(hdev);
+}
+
 static irqreturn_t hclgevf_misc_irq_handle(int irq, void *data)
 {
+#define HCLGEVF_RESET_DELAY	5
+
 	enum hclgevf_evt_cause event_cause;
 	struct hclgevf_dev *hdev = data;
 	u32 clearval;
@@ -1987,7 +2004,8 @@ static irqreturn_t hclgevf_misc_irq_handle(int irq, void *data)
 
 	switch (event_cause) {
 	case HCLGEVF_VECTOR0_EVENT_RST:
-		hclgevf_reset_task_schedule(hdev);
+		mod_timer(&hdev->reset_timer,
+			  jiffies + msecs_to_jiffies(HCLGEVF_RESET_DELAY));
 		break;
 	case HCLGEVF_VECTOR0_EVENT_MBX:
 		hclgevf_mbx_handler(hdev);
@@ -2930,6 +2948,7 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 		 HCLGEVF_DRIVER_NAME);
 
 	hclgevf_task_schedule(hdev, round_jiffies_relative(HZ));
+	timer_setup(&hdev->reset_timer, hclgevf_reset_timer, 0);
 
 	return 0;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 81c16b8c8da2..a73f2bf3a56a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -219,6 +219,7 @@ struct hclgevf_dev {
 	enum hnae3_reset_type reset_level;
 	unsigned long reset_pending;
 	enum hnae3_reset_type reset_type;
+	struct timer_list reset_timer;
 
 #define HCLGEVF_RESET_REQUESTED		0
 #define HCLGEVF_RESET_PENDING		1
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
index bbf7b14079de..85c2a634c8f9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
@@ -63,6 +63,9 @@ static int hclgevf_get_mbx_resp(struct hclgevf_dev *hdev, u16 code0, u16 code1,
 		i++;
 	}
 
+	/* ensure additional_info will be seen after received_resp */
+	smp_rmb();
+
 	if (i >= HCLGEVF_MAX_TRY_TIMES) {
 		dev_err(&hdev->pdev->dev,
 			"VF could not get mbx(%u,%u) resp(=%d) from PF in %d tries\n",
@@ -178,6 +181,10 @@ static void hclgevf_handle_mbx_response(struct hclgevf_dev *hdev,
 	resp->resp_status = hclgevf_resp_to_errno(resp_status);
 	memcpy(resp->additional_info, req->msg.resp_data,
 	       HCLGE_MBX_MAX_RESP_DATA_SIZE * sizeof(u8));
+
+	/* ensure additional_info will be seen before setting received_resp */
+	smp_wmb();
+
 	if (match_id) {
 		/* If match_id is not zero, it means PF support match_id.
 		 * if the match_id is right, VF get the right response, or
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
index f4b680286911..0304f03d4093 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
@@ -1137,7 +1137,7 @@ static int hinic_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
 }
 
 static int hinic_get_rxfh(struct net_device *netdev,
-			  u32 *indir, u8 *key, u8 *hfunc)
+			  struct ethtool_rxfh_param *rxfh)
 {
 	struct hinic_dev *nic_dev = netdev_priv(netdev);
 	u8 hash_engine_type = 0;
@@ -1146,32 +1146,33 @@ static int hinic_get_rxfh(struct net_device *netdev,
 	if (!(nic_dev->flags & HINIC_RSS_ENABLE))
 		return -EOPNOTSUPP;
 
-	if (hfunc) {
-		err = hinic_rss_get_hash_engine(nic_dev,
-						nic_dev->rss_tmpl_idx,
-						&hash_engine_type);
-		if (err)
-			return -EFAULT;
+	err = hinic_rss_get_hash_engine(nic_dev,
+					nic_dev->rss_tmpl_idx,
+					&hash_engine_type);
+	if (err)
+		return -EFAULT;
 
-		*hfunc = hash_engine_type ? ETH_RSS_HASH_TOP : ETH_RSS_HASH_XOR;
-	}
+	rxfh->hfunc = hash_engine_type ? ETH_RSS_HASH_TOP : ETH_RSS_HASH_XOR;
 
-	if (indir) {
+	if (rxfh->indir) {
 		err = hinic_rss_get_indir_tbl(nic_dev,
-					      nic_dev->rss_tmpl_idx, indir);
+					      nic_dev->rss_tmpl_idx,
+					      rxfh->indir);
 		if (err)
 			return -EFAULT;
 	}
 
-	if (key)
+	if (rxfh->key)
 		err = hinic_rss_get_template_tbl(nic_dev,
-						 nic_dev->rss_tmpl_idx, key);
+						 nic_dev->rss_tmpl_idx,
+						 rxfh->key);
 
 	return err;
 }
 
-static int hinic_set_rxfh(struct net_device *netdev, const u32 *indir,
-			  const u8 *key, const u8 hfunc)
+static int hinic_set_rxfh(struct net_device *netdev,
+			  struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
 {
 	struct hinic_dev *nic_dev = netdev_priv(netdev);
 	int err = 0;
@@ -1179,11 +1180,12 @@ static int hinic_set_rxfh(struct net_device *netdev, const u32 *indir,
 	if (!(nic_dev->flags & HINIC_RSS_ENABLE))
 		return -EOPNOTSUPP;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE) {
-		if (hfunc != ETH_RSS_HASH_TOP && hfunc != ETH_RSS_HASH_XOR)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE) {
+		if (rxfh->hfunc != ETH_RSS_HASH_TOP &&
+		    rxfh->hfunc != ETH_RSS_HASH_XOR)
 			return -EOPNOTSUPP;
 
-		nic_dev->rss_hash_engine = (hfunc == ETH_RSS_HASH_XOR) ?
+		nic_dev->rss_hash_engine = (rxfh->hfunc == ETH_RSS_HASH_XOR) ?
 			HINIC_RSS_HASH_ENGINE_TYPE_XOR :
 			HINIC_RSS_HASH_ENGINE_TYPE_TOEP;
 		err = hinic_rss_set_hash_engine
@@ -1193,7 +1195,7 @@ static int hinic_set_rxfh(struct net_device *netdev, const u32 *indir,
 			return -EFAULT;
 	}
 
-	err = __set_rss_rxfh(netdev, indir, key);
+	err = __set_rss_rxfh(netdev, rxfh->indir, rxfh->key);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index 4e18b4cefa97..94ac36b1408b 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -48,7 +48,7 @@
  * of 4096 jumbo frames (MTU=9000) we will need about 9K*4K = 36MB plus
  * some padding.
  *
- * But the size of a single DMA region is limited by MAX_ORDER in the
+ * But the size of a single DMA region is limited by MAX_PAGE_ORDER in the
  * kernel (about 16MB currently).  To support say 4K Jumbo frames, we
  * use a set of LTBs (struct ltb_set) per pool.
  *
@@ -75,7 +75,7 @@
  * pool for the 4MB. Thus the 16 Rx and Tx queues require 32 * 5 = 160
  * plus 16 for the TSO pools for a total of 176 LTB mappings per VNIC.
  */
-#define IBMVNIC_ONE_LTB_MAX	((u32)((1 << MAX_ORDER) * PAGE_SIZE))
+#define IBMVNIC_ONE_LTB_MAX	((u32)((1 << MAX_PAGE_ORDER) * PAGE_SIZE))
 #define IBMVNIC_ONE_LTB_SIZE	min((u32)(8 << 20), IBMVNIC_ONE_LTB_MAX)
 #define IBMVNIC_LTB_SET_SIZE	(38 << 20)
 
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 06ddd7147c7f..d55638ad8704 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -299,6 +299,17 @@ config ICE
 	  To compile this driver as a module, choose M here. The module
 	  will be called ice.
 
+config ICE_HWMON
+	bool "Intel(R) Ethernet Connection E800 Series Support HWMON support"
+	default y
+	depends on ICE && HWMON && !(ICE=y && HWMON=m)
+	help
+	  Say Y if you want to expose thermal sensor data on Intel devices.
+
+	  Some of our devices contain internal thermal sensors.
+	  This data is available via the hwmon sysfs interface and exposes
+	  the onboard sensors.
+
 config ICE_SWITCHDEV
 	bool "Switchdev Support"
 	default y
diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.c b/drivers/net/ethernet/intel/e1000/e1000_hw.c
index 4542e2bc28e8..f9328f2e669f 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_hw.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_hw.c
@@ -5,6 +5,7 @@
  * Shared functions for accessing and configuring the MAC
  */
 
+#include <linux/bitfield.h>
 #include "e1000.h"
 
 static s32 e1000_check_downshift(struct e1000_hw *hw);
@@ -3260,8 +3261,7 @@ static s32 e1000_phy_igp_get_info(struct e1000_hw *hw,
 		return ret_val;
 
 	phy_info->mdix_mode =
-	    (e1000_auto_x_mode) ((phy_data & IGP01E1000_PSSR_MDIX) >>
-				 IGP01E1000_PSSR_MDIX_SHIFT);
+	    (e1000_auto_x_mode)FIELD_GET(IGP01E1000_PSSR_MDIX, phy_data);
 
 	if ((phy_data & IGP01E1000_PSSR_SPEED_MASK) ==
 	    IGP01E1000_PSSR_SPEED_1000MBPS) {
@@ -3272,11 +3272,11 @@ static s32 e1000_phy_igp_get_info(struct e1000_hw *hw,
 		if (ret_val)
 			return ret_val;
 
-		phy_info->local_rx = ((phy_data & SR_1000T_LOCAL_RX_STATUS) >>
-				      SR_1000T_LOCAL_RX_STATUS_SHIFT) ?
+		phy_info->local_rx = FIELD_GET(SR_1000T_LOCAL_RX_STATUS,
+					       phy_data) ?
 		    e1000_1000t_rx_status_ok : e1000_1000t_rx_status_not_ok;
-		phy_info->remote_rx = ((phy_data & SR_1000T_REMOTE_RX_STATUS) >>
-				       SR_1000T_REMOTE_RX_STATUS_SHIFT) ?
+		phy_info->remote_rx = FIELD_GET(SR_1000T_REMOTE_RX_STATUS,
+						phy_data) ?
 		    e1000_1000t_rx_status_ok : e1000_1000t_rx_status_not_ok;
 
 		/* Get cable length */
@@ -3326,14 +3326,12 @@ static s32 e1000_phy_m88_get_info(struct e1000_hw *hw,
 		return ret_val;
 
 	phy_info->extended_10bt_distance =
-	    ((phy_data & M88E1000_PSCR_10BT_EXT_DIST_ENABLE) >>
-	     M88E1000_PSCR_10BT_EXT_DIST_ENABLE_SHIFT) ?
+	    FIELD_GET(M88E1000_PSCR_10BT_EXT_DIST_ENABLE, phy_data) ?
 	    e1000_10bt_ext_dist_enable_lower :
 	    e1000_10bt_ext_dist_enable_normal;
 
 	phy_info->polarity_correction =
-	    ((phy_data & M88E1000_PSCR_POLARITY_REVERSAL) >>
-	     M88E1000_PSCR_POLARITY_REVERSAL_SHIFT) ?
+	    FIELD_GET(M88E1000_PSCR_POLARITY_REVERSAL, phy_data) ?
 	    e1000_polarity_reversal_disabled : e1000_polarity_reversal_enabled;
 
 	/* Check polarity status */
@@ -3347,27 +3345,25 @@ static s32 e1000_phy_m88_get_info(struct e1000_hw *hw,
 		return ret_val;
 
 	phy_info->mdix_mode =
-	    (e1000_auto_x_mode) ((phy_data & M88E1000_PSSR_MDIX) >>
-				 M88E1000_PSSR_MDIX_SHIFT);
+	    (e1000_auto_x_mode)FIELD_GET(M88E1000_PSSR_MDIX, phy_data);
 
 	if ((phy_data & M88E1000_PSSR_SPEED) == M88E1000_PSSR_1000MBS) {
 		/* Cable Length Estimation and Local/Remote Receiver Information
 		 * are only valid at 1000 Mbps.
 		 */
 		phy_info->cable_length =
-		    (e1000_cable_length) ((phy_data &
-					   M88E1000_PSSR_CABLE_LENGTH) >>
-					  M88E1000_PSSR_CABLE_LENGTH_SHIFT);
+		    (e1000_cable_length)FIELD_GET(M88E1000_PSSR_CABLE_LENGTH,
+						  phy_data);
 
 		ret_val = e1000_read_phy_reg(hw, PHY_1000T_STATUS, &phy_data);
 		if (ret_val)
 			return ret_val;
 
-		phy_info->local_rx = ((phy_data & SR_1000T_LOCAL_RX_STATUS) >>
-				      SR_1000T_LOCAL_RX_STATUS_SHIFT) ?
+		phy_info->local_rx = FIELD_GET(SR_1000T_LOCAL_RX_STATUS,
+					       phy_data) ?
 		    e1000_1000t_rx_status_ok : e1000_1000t_rx_status_not_ok;
-		phy_info->remote_rx = ((phy_data & SR_1000T_REMOTE_RX_STATUS) >>
-				       SR_1000T_REMOTE_RX_STATUS_SHIFT) ?
+		phy_info->remote_rx = FIELD_GET(SR_1000T_REMOTE_RX_STATUS,
+						phy_data) ?
 		    e1000_1000t_rx_status_ok : e1000_1000t_rx_status_not_ok;
 	}
 
@@ -3515,7 +3511,7 @@ s32 e1000_init_eeprom_params(struct e1000_hw *hw)
 		if (ret_val)
 			return ret_val;
 		eeprom_size =
-		    (eeprom_size & EEPROM_SIZE_MASK) >> EEPROM_SIZE_SHIFT;
+		    FIELD_GET(EEPROM_SIZE_MASK, eeprom_size);
 		/* 256B eeprom size was not supported in earlier hardware, so we
 		 * bump eeprom_size up one to ensure that "1" (which maps to
 		 * 256B) is never the result used in the shifting logic below.
@@ -4891,8 +4887,7 @@ static s32 e1000_get_cable_length(struct e1000_hw *hw, u16 *min_length,
 					     &phy_data);
 		if (ret_val)
 			return ret_val;
-		cable_length = (phy_data & M88E1000_PSSR_CABLE_LENGTH) >>
-		    M88E1000_PSSR_CABLE_LENGTH_SHIFT;
+		cable_length = FIELD_GET(M88E1000_PSSR_CABLE_LENGTH, phy_data);
 
 		/* Convert the enum value to ranged values */
 		switch (cable_length) {
@@ -5001,8 +4996,7 @@ static s32 e1000_check_polarity(struct e1000_hw *hw,
 					     &phy_data);
 		if (ret_val)
 			return ret_val;
-		*polarity = ((phy_data & M88E1000_PSSR_REV_POLARITY) >>
-			     M88E1000_PSSR_REV_POLARITY_SHIFT) ?
+		*polarity = FIELD_GET(M88E1000_PSSR_REV_POLARITY, phy_data) ?
 		    e1000_rev_polarity_reversed : e1000_rev_polarity_normal;
 
 	} else if (hw->phy_type == e1000_phy_igp) {
@@ -5072,8 +5066,8 @@ static s32 e1000_check_downshift(struct e1000_hw *hw)
 		if (ret_val)
 			return ret_val;
 
-		hw->speed_downgraded = (phy_data & M88E1000_PSSR_DOWNSHIFT) >>
-		    M88E1000_PSSR_DOWNSHIFT_SHIFT;
+		hw->speed_downgraded = FIELD_GET(M88E1000_PSSR_DOWNSHIFT,
+						 phy_data);
 	}
 
 	return E1000_SUCCESS;
diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.c b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
index be9c695dde12..4eb1ceaf865a 100644
--- a/drivers/net/ethernet/intel/e1000e/80003es2lan.c
+++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
@@ -92,8 +92,7 @@ static s32 e1000_init_nvm_params_80003es2lan(struct e1000_hw *hw)
 
 	nvm->type = e1000_nvm_eeprom_spi;
 
-	size = (u16)((eecd & E1000_EECD_SIZE_EX_MASK) >>
-		     E1000_EECD_SIZE_EX_SHIFT);
+	size = (u16)FIELD_GET(E1000_EECD_SIZE_EX_MASK, eecd);
 
 	/* Added to a constant, "size" becomes the left-shift value
 	 * for setting word_size.
@@ -1035,17 +1034,18 @@ static s32 e1000_setup_copper_link_80003es2lan(struct e1000_hw *hw)
 	 * iteration and increase the max iterations when
 	 * polling the phy; this fixes erroneous timeouts at 10Mbps.
 	 */
-	ret_val = e1000_write_kmrn_reg_80003es2lan(hw, GG82563_REG(0x34, 4),
-						   0xFFFF);
+	/* these next three accesses were always meant to use page 0x34 using
+	 * GG82563_REG(0x34, N) but never did, so we've just corrected the call
+	 * to not drop bits
+	 */
+	ret_val = e1000_write_kmrn_reg_80003es2lan(hw, 4, 0xFFFF);
 	if (ret_val)
 		return ret_val;
-	ret_val = e1000_read_kmrn_reg_80003es2lan(hw, GG82563_REG(0x34, 9),
-						  &reg_data);
+	ret_val = e1000_read_kmrn_reg_80003es2lan(hw, 9, &reg_data);
 	if (ret_val)
 		return ret_val;
 	reg_data |= 0x3F;
-	ret_val = e1000_write_kmrn_reg_80003es2lan(hw, GG82563_REG(0x34, 9),
-						   reg_data);
+	ret_val = e1000_write_kmrn_reg_80003es2lan(hw, 9, reg_data);
 	if (ret_val)
 		return ret_val;
 	ret_val =
@@ -1209,8 +1209,8 @@ static s32 e1000_read_kmrn_reg_80003es2lan(struct e1000_hw *hw, u32 offset,
 	if (ret_val)
 		return ret_val;
 
-	kmrnctrlsta = ((offset << E1000_KMRNCTRLSTA_OFFSET_SHIFT) &
-		       E1000_KMRNCTRLSTA_OFFSET) | E1000_KMRNCTRLSTA_REN;
+	kmrnctrlsta = FIELD_PREP(E1000_KMRNCTRLSTA_OFFSET, offset) |
+		      E1000_KMRNCTRLSTA_REN;
 	ew32(KMRNCTRLSTA, kmrnctrlsta);
 	e1e_flush();
 
@@ -1244,8 +1244,7 @@ static s32 e1000_write_kmrn_reg_80003es2lan(struct e1000_hw *hw, u32 offset,
 	if (ret_val)
 		return ret_val;
 
-	kmrnctrlsta = ((offset << E1000_KMRNCTRLSTA_OFFSET_SHIFT) &
-		       E1000_KMRNCTRLSTA_OFFSET) | data;
+	kmrnctrlsta = FIELD_PREP(E1000_KMRNCTRLSTA_OFFSET, offset) | data;
 	ew32(KMRNCTRLSTA, kmrnctrlsta);
 	e1e_flush();
 
diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c
index 0b1e890dd583..969f855a79ee 100644
--- a/drivers/net/ethernet/intel/e1000e/82571.c
+++ b/drivers/net/ethernet/intel/e1000e/82571.c
@@ -157,8 +157,7 @@ static s32 e1000_init_nvm_params_82571(struct e1000_hw *hw)
 		fallthrough;
 	default:
 		nvm->type = e1000_nvm_eeprom_spi;
-		size = (u16)((eecd & E1000_EECD_SIZE_EX_MASK) >>
-			     E1000_EECD_SIZE_EX_SHIFT);
+		size = (u16)FIELD_GET(E1000_EECD_SIZE_EX_MASK, eecd);
 		/* Added to a constant, "size" becomes the left-shift value
 		 * for setting word_size.
 		 */
diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h
index 63c3c79380a1..23a58cada43a 100644
--- a/drivers/net/ethernet/intel/e1000e/defines.h
+++ b/drivers/net/ethernet/intel/e1000e/defines.h
@@ -678,11 +678,8 @@
 
 /* PCI/PCI-X/PCI-EX Config space */
 #define PCI_HEADER_TYPE_REGISTER     0x0E
-#define PCIE_LINK_STATUS             0x12
 
 #define PCI_HEADER_TYPE_MULTIFUNC    0x80
-#define PCIE_LINK_WIDTH_MASK         0x3F0
-#define PCIE_LINK_WIDTH_SHIFT        4
 
 #define PHY_REVISION_MASK      0xFFFFFFF0
 #define MAX_PHY_REG_ADDRESS    0x1F  /* 5 bit address bus (0-0x1F) */
diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c
index 9835e6a90d56..fc0f98ea6133 100644
--- a/drivers/net/ethernet/intel/e1000e/ethtool.c
+++ b/drivers/net/ethernet/intel/e1000e/ethtool.c
@@ -654,8 +654,8 @@ static void e1000_get_drvinfo(struct net_device *netdev,
 	 */
 	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
 		 "%d.%d-%d",
-		 (adapter->eeprom_vers & 0xF000) >> 12,
-		 (adapter->eeprom_vers & 0x0FF0) >> 4,
+		 FIELD_GET(0xF000, adapter->eeprom_vers),
+		 FIELD_GET(0x0FF0, adapter->eeprom_vers),
 		 (adapter->eeprom_vers & 0x000F));
 
 	strscpy(drvinfo->bus_info, pci_name(adapter->pdev),
@@ -925,8 +925,7 @@ static int e1000_reg_test(struct e1000_adapter *adapter, u64 *data)
 	}
 
 	if (mac->type >= e1000_pch_lpt)
-		wlock_mac = (er32(FWSM) & E1000_FWSM_WLOCK_MAC_MASK) >>
-		    E1000_FWSM_WLOCK_MAC_SHIFT;
+		wlock_mac = FIELD_GET(E1000_FWSM_WLOCK_MAC_MASK, er32(FWSM));
 
 	for (i = 0; i < mac->rar_entry_count; i++) {
 		if (mac->type >= e1000_pch_lpt) {
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index 39e9fc601bf5..a2788fd5f8bb 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -1072,13 +1072,11 @@ static s32 e1000_platform_pm_pch_lpt(struct e1000_hw *hw, bool link)
 
 		lat_enc_d = (lat_enc & E1000_LTRV_VALUE_MASK) *
 			     (1U << (E1000_LTRV_SCALE_FACTOR *
-			     ((lat_enc & E1000_LTRV_SCALE_MASK)
-			     >> E1000_LTRV_SCALE_SHIFT)));
+			     FIELD_GET(E1000_LTRV_SCALE_MASK, lat_enc)));
 
 		max_ltr_enc_d = (max_ltr_enc & E1000_LTRV_VALUE_MASK) *
-				 (1U << (E1000_LTRV_SCALE_FACTOR *
-				 ((max_ltr_enc & E1000_LTRV_SCALE_MASK)
-				 >> E1000_LTRV_SCALE_SHIFT)));
+			(1U << (E1000_LTRV_SCALE_FACTOR *
+				FIELD_GET(E1000_LTRV_SCALE_MASK, max_ltr_enc)));
 
 		if (lat_enc_d > max_ltr_enc_d)
 			lat_enc = max_ltr_enc;
@@ -2075,8 +2073,7 @@ static s32 e1000_write_smbus_addr(struct e1000_hw *hw)
 {
 	u16 phy_data;
 	u32 strap = er32(STRAP);
-	u32 freq = (strap & E1000_STRAP_SMT_FREQ_MASK) >>
-	    E1000_STRAP_SMT_FREQ_SHIFT;
+	u32 freq = FIELD_GET(E1000_STRAP_SMT_FREQ_MASK, strap);
 	s32 ret_val;
 
 	strap &= E1000_STRAP_SMBUS_ADDRESS_MASK;
@@ -2562,8 +2559,7 @@ void e1000_copy_rx_addrs_to_phy_ich8lan(struct e1000_hw *hw)
 		hw->phy.ops.write_reg_page(hw, BM_RAR_H(i),
 					   (u16)(mac_reg & 0xFFFF));
 		hw->phy.ops.write_reg_page(hw, BM_RAR_CTRL(i),
-					   (u16)((mac_reg & E1000_RAH_AV)
-						 >> 16));
+					   FIELD_GET(E1000_RAH_AV, mac_reg));
 	}
 
 	e1000_disable_phy_wakeup_reg_access_bm(hw, &phy_reg);
@@ -3205,7 +3201,7 @@ static s32 e1000_valid_nvm_bank_detect_ich8lan(struct e1000_hw *hw, u32 *bank)
 							 &nvm_dword);
 		if (ret_val)
 			return ret_val;
-		sig_byte = (u8)((nvm_dword & 0xFF00) >> 8);
+		sig_byte = FIELD_GET(0xFF00, nvm_dword);
 		if ((sig_byte & E1000_ICH_NVM_VALID_SIG_MASK) ==
 		    E1000_ICH_NVM_SIG_VALUE) {
 			*bank = 0;
@@ -3218,7 +3214,7 @@ static s32 e1000_valid_nvm_bank_detect_ich8lan(struct e1000_hw *hw, u32 *bank)
 							 &nvm_dword);
 		if (ret_val)
 			return ret_val;
-		sig_byte = (u8)((nvm_dword & 0xFF00) >> 8);
+		sig_byte = FIELD_GET(0xFF00, nvm_dword);
 		if ((sig_byte & E1000_ICH_NVM_VALID_SIG_MASK) ==
 		    E1000_ICH_NVM_SIG_VALUE) {
 			*bank = 1;
diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c
index 5df7ad93f3d7..d7df2a0ed629 100644
--- a/drivers/net/ethernet/intel/e1000e/mac.c
+++ b/drivers/net/ethernet/intel/e1000e/mac.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 1999 - 2018 Intel Corporation. */
 
+#include <linux/bitfield.h>
+
 #include "e1000.h"
 
 /**
@@ -13,21 +15,17 @@
  **/
 s32 e1000e_get_bus_info_pcie(struct e1000_hw *hw)
 {
+	struct pci_dev *pdev = hw->adapter->pdev;
 	struct e1000_mac_info *mac = &hw->mac;
 	struct e1000_bus_info *bus = &hw->bus;
-	struct e1000_adapter *adapter = hw->adapter;
-	u16 pcie_link_status, cap_offset;
+	u16 pcie_link_status;
 
-	cap_offset = adapter->pdev->pcie_cap;
-	if (!cap_offset) {
+	if (!pci_pcie_cap(pdev)) {
 		bus->width = e1000_bus_width_unknown;
 	} else {
-		pci_read_config_word(adapter->pdev,
-				     cap_offset + PCIE_LINK_STATUS,
-				     &pcie_link_status);
-		bus->width = (enum e1000_bus_width)((pcie_link_status &
-						     PCIE_LINK_WIDTH_MASK) >>
-						    PCIE_LINK_WIDTH_SHIFT);
+		pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &pcie_link_status);
+		bus->width = (enum e1000_bus_width)FIELD_GET(PCI_EXP_LNKSTA_NLW,
+							     pcie_link_status);
 	}
 
 	mac->ops.set_lan_id(hw);
@@ -52,7 +50,7 @@ void e1000_set_lan_id_multi_port_pcie(struct e1000_hw *hw)
 	 * for the device regardless of function swap state.
 	 */
 	reg = er32(STATUS);
-	bus->func = (reg & E1000_STATUS_FUNC_MASK) >> E1000_STATUS_FUNC_SHIFT;
+	bus->func = FIELD_GET(E1000_STATUS_FUNC_MASK, reg);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index f536c856727c..af5d9d97a0d6 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -1788,8 +1788,7 @@ static irqreturn_t e1000_intr_msi(int __always_unused irq, void *data)
 		adapter->corr_errors +=
 		    pbeccsts & E1000_PBECCSTS_CORR_ERR_CNT_MASK;
 		adapter->uncorr_errors +=
-		    (pbeccsts & E1000_PBECCSTS_UNCORR_ERR_CNT_MASK) >>
-		    E1000_PBECCSTS_UNCORR_ERR_CNT_SHIFT;
+		    FIELD_GET(E1000_PBECCSTS_UNCORR_ERR_CNT_MASK, pbeccsts);
 
 		/* Do the reset outside of interrupt context */
 		schedule_work(&adapter->reset_task);
@@ -1868,8 +1867,7 @@ static irqreturn_t e1000_intr(int __always_unused irq, void *data)
 		adapter->corr_errors +=
 		    pbeccsts & E1000_PBECCSTS_CORR_ERR_CNT_MASK;
 		adapter->uncorr_errors +=
-		    (pbeccsts & E1000_PBECCSTS_UNCORR_ERR_CNT_MASK) >>
-		    E1000_PBECCSTS_UNCORR_ERR_CNT_SHIFT;
+		    FIELD_GET(E1000_PBECCSTS_UNCORR_ERR_CNT_MASK, pbeccsts);
 
 		/* Do the reset outside of interrupt context */
 		schedule_work(&adapter->reset_task);
@@ -5031,8 +5029,7 @@ static void e1000e_update_stats(struct e1000_adapter *adapter)
 		adapter->corr_errors +=
 		    pbeccsts & E1000_PBECCSTS_CORR_ERR_CNT_MASK;
 		adapter->uncorr_errors +=
-		    (pbeccsts & E1000_PBECCSTS_UNCORR_ERR_CNT_MASK) >>
-		    E1000_PBECCSTS_UNCORR_ERR_CNT_SHIFT;
+		    FIELD_GET(E1000_PBECCSTS_UNCORR_ERR_CNT_MASK, pbeccsts);
 	}
 }
 
@@ -6249,7 +6246,7 @@ static int e1000_init_phy_wakeup(struct e1000_adapter *adapter, u32 wufc)
 		phy_reg |= BM_RCTL_MPE;
 	phy_reg &= ~(BM_RCTL_MO_MASK);
 	if (mac_reg & E1000_RCTL_MO_3)
-		phy_reg |= (((mac_reg & E1000_RCTL_MO_3) >> E1000_RCTL_MO_SHIFT)
+		phy_reg |= (FIELD_GET(E1000_RCTL_MO_3, mac_reg)
 			    << BM_RCTL_MO_SHIFT);
 	if (mac_reg & E1000_RCTL_BAM)
 		phy_reg |= BM_RCTL_BAM;
diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c
index 08c3d477dd6f..5e329156d1ba 100644
--- a/drivers/net/ethernet/intel/e1000e/phy.c
+++ b/drivers/net/ethernet/intel/e1000e/phy.c
@@ -154,10 +154,9 @@ s32 e1000e_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data)
 		e_dbg("MDI Read PHY Reg Address %d Error\n", offset);
 		return -E1000_ERR_PHY;
 	}
-	if (((mdic & E1000_MDIC_REG_MASK) >> E1000_MDIC_REG_SHIFT) != offset) {
+	if (FIELD_GET(E1000_MDIC_REG_MASK, mdic) != offset) {
 		e_dbg("MDI Read offset error - requested %d, returned %d\n",
-		      offset,
-		      (mdic & E1000_MDIC_REG_MASK) >> E1000_MDIC_REG_SHIFT);
+		      offset, FIELD_GET(E1000_MDIC_REG_MASK, mdic));
 		return -E1000_ERR_PHY;
 	}
 	*data = (u16)mdic;
@@ -167,7 +166,6 @@ s32 e1000e_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data)
 	 */
 	if (hw->mac.type == e1000_pch2lan)
 		udelay(100);
-
 	return 0;
 }
 
@@ -218,10 +216,9 @@ s32 e1000e_write_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 data)
 		e_dbg("MDI Write PHY Red Address %d Error\n", offset);
 		return -E1000_ERR_PHY;
 	}
-	if (((mdic & E1000_MDIC_REG_MASK) >> E1000_MDIC_REG_SHIFT) != offset) {
+	if (FIELD_GET(E1000_MDIC_REG_MASK, mdic) != offset) {
 		e_dbg("MDI Write offset error - requested %d, returned %d\n",
-		      offset,
-		      (mdic & E1000_MDIC_REG_MASK) >> E1000_MDIC_REG_SHIFT);
+		      offset, FIELD_GET(E1000_MDIC_REG_MASK, mdic));
 		return -E1000_ERR_PHY;
 	}
 
@@ -463,8 +460,8 @@ static s32 __e1000_read_kmrn_reg(struct e1000_hw *hw, u32 offset, u16 *data,
 			return ret_val;
 	}
 
-	kmrnctrlsta = ((offset << E1000_KMRNCTRLSTA_OFFSET_SHIFT) &
-		       E1000_KMRNCTRLSTA_OFFSET) | E1000_KMRNCTRLSTA_REN;
+	kmrnctrlsta = FIELD_PREP(E1000_KMRNCTRLSTA_OFFSET, offset) |
+		      E1000_KMRNCTRLSTA_REN;
 	ew32(KMRNCTRLSTA, kmrnctrlsta);
 	e1e_flush();
 
@@ -536,8 +533,7 @@ static s32 __e1000_write_kmrn_reg(struct e1000_hw *hw, u32 offset, u16 data,
 			return ret_val;
 	}
 
-	kmrnctrlsta = ((offset << E1000_KMRNCTRLSTA_OFFSET_SHIFT) &
-		       E1000_KMRNCTRLSTA_OFFSET) | data;
+	kmrnctrlsta = FIELD_PREP(E1000_KMRNCTRLSTA_OFFSET, offset) | data;
 	ew32(KMRNCTRLSTA, kmrnctrlsta);
 	e1e_flush();
 
@@ -1793,8 +1789,7 @@ s32 e1000e_get_cable_length_m88(struct e1000_hw *hw)
 	if (ret_val)
 		return ret_val;
 
-	index = ((phy_data & M88E1000_PSSR_CABLE_LENGTH) >>
-		 M88E1000_PSSR_CABLE_LENGTH_SHIFT);
+	index = FIELD_GET(M88E1000_PSSR_CABLE_LENGTH, phy_data);
 
 	if (index >= M88E1000_CABLE_LENGTH_TABLE_SIZE - 1)
 		return -E1000_ERR_PHY;
@@ -3234,8 +3229,7 @@ s32 e1000_get_cable_length_82577(struct e1000_hw *hw)
 	if (ret_val)
 		return ret_val;
 
-	length = ((phy_data & I82577_DSTATUS_CABLE_LENGTH) >>
-		  I82577_DSTATUS_CABLE_LENGTH_SHIFT);
+	length = FIELD_GET(I82577_DSTATUS_CABLE_LENGTH, phy_data);
 
 	if (length == E1000_CABLE_LENGTH_UNDEFINED)
 		return -E1000_ERR_PHY;
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
index 13a05604dcc0..1bc5b6c0b897 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
@@ -1057,16 +1057,16 @@ static u32 fm10k_get_rssrk_size(struct net_device __always_unused *netdev)
 	return FM10K_RSSRK_SIZE * FM10K_RSSRK_ENTRIES_PER_REG;
 }
 
-static int fm10k_get_rssh(struct net_device *netdev, u32 *indir, u8 *key,
-			  u8 *hfunc)
+static int fm10k_get_rssh(struct net_device *netdev,
+			  struct ethtool_rxfh_param *rxfh)
 {
 	struct fm10k_intfc *interface = netdev_priv(netdev);
+	u8 *key = rxfh->key;
 	int i, err;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
-	err = fm10k_get_reta(netdev, indir);
+	err = fm10k_get_reta(netdev, rxfh->indir);
 	if (err || !key)
 		return err;
 
@@ -1076,23 +1076,25 @@ static int fm10k_get_rssh(struct net_device *netdev, u32 *indir, u8 *key,
 	return 0;
 }
 
-static int fm10k_set_rssh(struct net_device *netdev, const u32 *indir,
-			  const u8 *key, const u8 hfunc)
+static int fm10k_set_rssh(struct net_device *netdev,
+			  struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
 {
 	struct fm10k_intfc *interface = netdev_priv(netdev);
 	struct fm10k_hw *hw = &interface->hw;
 	int i, err;
 
 	/* We do not allow change in unsupported parameters */
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	err = fm10k_set_reta(netdev, indir);
-	if (err || !key)
+	err = fm10k_set_reta(netdev, rxfh->indir);
+	if (err || !rxfh->key)
 		return err;
 
-	for (i = 0; i < FM10K_RSSRK_SIZE; i++, key += 4) {
-		u32 rssrk = le32_to_cpu(*(__le32 *)key);
+	for (i = 0; i < FM10K_RSSRK_SIZE; i++, rxfh->key += 4) {
+		u32 rssrk = le32_to_cpu(*(__le32 *)rxfh->key);
 
 		if (interface->rssrk[i] == rssrk)
 			continue;
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
index af1b0cde3670..98861cc6df7c 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2013 - 2019 Intel Corporation. */
 
+#include <linux/bitfield.h>
 #include "fm10k_pf.h"
 #include "fm10k_vf.h"
 
@@ -865,8 +866,7 @@ static s32 fm10k_iov_assign_default_mac_vlan_pf(struct fm10k_hw *hw,
 	 * register is RO from the VF, so the PF must do this even in the
 	 * case of notifying the VF of a new VID via the mailbox.
 	 */
-	txqctl = ((u32)vf_vid << FM10K_TXQCTL_VID_SHIFT) &
-		 FM10K_TXQCTL_VID_MASK;
+	txqctl = FIELD_PREP(FM10K_TXQCTL_VID_MASK, vf_vid);
 	txqctl |= (vf_idx << FM10K_TXQCTL_TC_SHIFT) |
 		  FM10K_TXQCTL_VF | vf_idx;
 
@@ -1575,8 +1575,7 @@ static s32 fm10k_get_fault_pf(struct fm10k_hw *hw, int type,
 	if (func & FM10K_FAULT_FUNC_PF)
 		fault->func = 0;
 	else
-		fault->func = 1 + ((func & FM10K_FAULT_FUNC_VF_MASK) >>
-				   FM10K_FAULT_FUNC_VF_SHIFT);
+		fault->func = 1 + FIELD_GET(FM10K_FAULT_FUNC_VF_MASK, func);
 
 	/* record fault type */
 	fault->type = func & FM10K_FAULT_FUNC_TYPE_MASK;
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c
index dc8ccd378ec9..7fb1961f2921 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2013 - 2019 Intel Corporation. */
 
+#include <linux/bitfield.h>
 #include "fm10k_vf.h"
 
 /**
@@ -126,15 +127,14 @@ static s32 fm10k_init_hw_vf(struct fm10k_hw *hw)
 	hw->mac.max_queues = i;
 
 	/* fetch default VLAN and ITR scale */
-	hw->mac.default_vid = (fm10k_read_reg(hw, FM10K_TXQCTL(0)) &
-			       FM10K_TXQCTL_VID_MASK) >> FM10K_TXQCTL_VID_SHIFT;
+	hw->mac.default_vid = FIELD_GET(FM10K_TXQCTL_VID_MASK,
+					fm10k_read_reg(hw, FM10K_TXQCTL(0)));
 	/* Read the ITR scale from TDLEN. See the definition of
 	 * FM10K_TDLEN_ITR_SCALE_SHIFT for more information about how TDLEN is
 	 * used here.
 	 */
-	hw->mac.itr_scale = (fm10k_read_reg(hw, FM10K_TDLEN(0)) &
-			     FM10K_TDLEN_ITR_SCALE_MASK) >>
-			    FM10K_TDLEN_ITR_SCALE_SHIFT;
+	hw->mac.itr_scale = FIELD_GET(FM10K_TDLEN_ITR_SCALE_MASK,
+				      fm10k_read_reg(hw, FM10K_TDLEN(0)));
 
 	return 0;
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 1bf424ac3145..9b701615c7c6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -24,6 +24,7 @@
 #define I40E_MAX_VEB			16
 
 #define I40E_MAX_NUM_DESCRIPTORS	4096
+#define I40E_MAX_NUM_DESCRIPTORS_XL710	8160
 #define I40E_MAX_CSR_SPACE		(4 * 1024 * 1024 - 64 * 1024)
 #define I40E_DEFAULT_NUM_DESCRIPTORS	512
 #define I40E_REQ_DESCRIPTOR_MULTIPLE	32
@@ -33,11 +34,11 @@
 #define I40E_MIN_VSI_ALLOC		83 /* LAN, ATR, FCOE, 64 VF */
 /* max 16 qps */
 #define i40e_default_queues_per_vmdq(pf) \
-		(((pf)->hw_features & I40E_HW_RSS_AQ_CAPABLE) ? 4 : 1)
+	(test_bit(I40E_HW_CAP_RSS_AQ, (pf)->hw.caps) ? 4 : 1)
 #define I40E_DEFAULT_QUEUES_PER_VF	4
 #define I40E_MAX_VF_QUEUES		16
 #define i40e_pf_get_max_q_per_tc(pf) \
-		(((pf)->hw_features & I40E_HW_128_QP_RSS_CAPABLE) ? 128 : 64)
+	(test_bit(I40E_HW_CAP_128_QP_RSS, (pf)->hw.caps) ? 128 : 64)
 #define I40E_FDIR_RING_COUNT		32
 #define I40E_MAX_AQ_BUF_SIZE		4096
 #define I40E_AQ_LEN			256
@@ -78,7 +79,7 @@
 #define I40E_MAX_BW_INACTIVE_ACCUM	4 /* accumulate 4 credits max */
 
 /* driver state flags */
-enum i40e_state_t {
+enum i40e_state {
 	__I40E_TESTING,
 	__I40E_CONFIG_BUSY,
 	__I40E_CONFIG_DONE,
@@ -126,7 +127,7 @@ enum i40e_state_t {
 	BIT_ULL(__I40E_PF_RESET_AND_REBUILD_REQUESTED)
 
 /* VSI state flags */
-enum i40e_vsi_state_t {
+enum i40e_vsi_state {
 	__I40E_VSI_DOWN,
 	__I40E_VSI_NEEDS_RESTART,
 	__I40E_VSI_SYNCING_FILTERS,
@@ -138,6 +139,60 @@ enum i40e_vsi_state_t {
 	__I40E_VSI_STATE_SIZE__,
 };
 
+enum i40e_pf_flags {
+	I40E_FLAG_MSI_ENA,
+	I40E_FLAG_MSIX_ENA,
+	I40E_FLAG_RSS_ENA,
+	I40E_FLAG_VMDQ_ENA,
+	I40E_FLAG_SRIOV_ENA,
+	I40E_FLAG_DCB_CAPABLE,
+	I40E_FLAG_DCB_ENA,
+	I40E_FLAG_FD_SB_ENA,
+	I40E_FLAG_FD_ATR_ENA,
+	I40E_FLAG_MFP_ENA,
+	I40E_FLAG_HW_ATR_EVICT_ENA,
+	I40E_FLAG_VEB_MODE_ENA,
+	I40E_FLAG_VEB_STATS_ENA,
+	I40E_FLAG_LINK_POLLING_ENA,
+	I40E_FLAG_TRUE_PROMISC_ENA,
+	I40E_FLAG_LEGACY_RX_ENA,
+	I40E_FLAG_PTP_ENA,
+	I40E_FLAG_IWARP_ENA,
+	I40E_FLAG_LINK_DOWN_ON_CLOSE_ENA,
+	I40E_FLAG_SOURCE_PRUNING_DIS,
+	I40E_FLAG_TC_MQPRIO_ENA,
+	I40E_FLAG_FD_SB_INACTIVE,
+	I40E_FLAG_FD_SB_TO_CLOUD_FILTER,
+	I40E_FLAG_FW_LLDP_DIS,
+	I40E_FLAG_RS_FEC,
+	I40E_FLAG_BASE_R_FEC,
+	/* TOTAL_PORT_SHUTDOWN_ENA
+	 * Allows to physically disable the link on the NIC's port.
+	 * If enabled, (after link down request from the OS)
+	 * no link, traffic or led activity is possible on that port.
+	 *
+	 * If I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENA is set, the
+	 * I40E_FLAG_LINK_DOWN_ON_CLOSE_ENA must be explicitly forced
+	 * to true and cannot be disabled by system admin at that time.
+	 * The functionalities are exclusive in terms of configuration, but
+	 * they also have similar behavior (allowing to disable physical
+	 * link of the port), with following differences:
+	 * - LINK_DOWN_ON_CLOSE_ENA is configurable at host OS run-time and
+	 *   is supported by whole family of 7xx Intel Ethernet Controllers
+	 * - TOTAL_PORT_SHUTDOWN_ENA may be enabled only before OS loads
+	 *   (in BIOS) only if motherboard's BIOS and NIC's FW has support of it
+	 * - when LINK_DOWN_ON_CLOSE_ENABLED is used, the link is being brought
+	 *   down by sending phy_type=0 to NIC's FW
+	 * - when TOTAL_PORT_SHUTDOWN_ENA is used, phy_type is not altered,
+	 *   instead the link is being brought down by clearing
+	 *   bit (I40E_AQ_PHY_ENABLE_LINK) in abilities field of
+	 *   i40e_aq_set_phy_config structure
+	 */
+	I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENA,
+	I40E_FLAG_VF_VLAN_PRUNING_ENA,
+	I40E_PF_FLAGS_NBITS,		/* must be last */
+};
+
 enum i40e_interrupt_policy {
 	I40E_INTERRUPT_BEST_CASE,
 	I40E_INTERRUPT_MEDIUM,
@@ -413,9 +468,7 @@ struct i40e_pf {
 	struct i40e_hw hw;
 	DECLARE_BITMAP(state, __I40E_STATE_SIZE__);
 	struct msix_entry *msix_entries;
-	bool fc_autoneg_status;
 
-	u16 eeprom_version;
 	u16 num_vmdq_vsis;         /* num vmdq vsis this PF has set up */
 	u16 num_vmdq_qps;          /* num queue pairs per vmdq pool */
 	u16 num_vmdq_msix;         /* num queue vectors per vmdq pool */
@@ -431,7 +484,6 @@ struct i40e_pf {
 	u16 rss_size_max;          /* HW defined max RSS queues */
 	u16 fdir_pf_filter_count;  /* num of guaranteed filters for this PF */
 	u16 num_alloc_vsi;         /* num VSIs this driver supports */
-	u8 atr_sample_rate;
 	bool wol_en;
 
 	struct hlist_head fdir_filter_list;
@@ -469,89 +521,16 @@ struct i40e_pf {
 	struct hlist_head cloud_filter_list;
 	u16 num_cloud_filters;
 
-	enum i40e_interrupt_policy int_policy;
 	u16 rx_itr_default;
 	u16 tx_itr_default;
 	u32 msg_enable;
 	char int_name[I40E_INT_NAME_STR_LEN];
-	u16 adminq_work_limit; /* num of admin receive queue desc to process */
 	unsigned long service_timer_period;
 	unsigned long service_timer_previous;
 	struct timer_list service_timer;
 	struct work_struct service_task;
 
-	u32 hw_features;
-#define I40E_HW_RSS_AQ_CAPABLE			BIT(0)
-#define I40E_HW_128_QP_RSS_CAPABLE		BIT(1)
-#define I40E_HW_ATR_EVICT_CAPABLE		BIT(2)
-#define I40E_HW_WB_ON_ITR_CAPABLE		BIT(3)
-#define I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE	BIT(4)
-#define I40E_HW_NO_PCI_LINK_CHECK		BIT(5)
-#define I40E_HW_100M_SGMII_CAPABLE		BIT(6)
-#define I40E_HW_NO_DCB_SUPPORT			BIT(7)
-#define I40E_HW_USE_SET_LLDP_MIB		BIT(8)
-#define I40E_HW_GENEVE_OFFLOAD_CAPABLE		BIT(9)
-#define I40E_HW_PTP_L4_CAPABLE			BIT(10)
-#define I40E_HW_WOL_MC_MAGIC_PKT_WAKE		BIT(11)
-#define I40E_HW_HAVE_CRT_RETIMER		BIT(13)
-#define I40E_HW_OUTER_UDP_CSUM_CAPABLE		BIT(14)
-#define I40E_HW_PHY_CONTROLS_LEDS		BIT(15)
-#define I40E_HW_STOP_FW_LLDP			BIT(16)
-#define I40E_HW_PORT_ID_VALID			BIT(17)
-#define I40E_HW_RESTART_AUTONEG			BIT(18)
-
-	u32 flags;
-#define I40E_FLAG_RX_CSUM_ENABLED		BIT(0)
-#define I40E_FLAG_MSI_ENABLED			BIT(1)
-#define I40E_FLAG_MSIX_ENABLED			BIT(2)
-#define I40E_FLAG_RSS_ENABLED			BIT(3)
-#define I40E_FLAG_VMDQ_ENABLED			BIT(4)
-#define I40E_FLAG_SRIOV_ENABLED			BIT(5)
-#define I40E_FLAG_DCB_CAPABLE			BIT(6)
-#define I40E_FLAG_DCB_ENABLED			BIT(7)
-#define I40E_FLAG_FD_SB_ENABLED			BIT(8)
-#define I40E_FLAG_FD_ATR_ENABLED		BIT(9)
-#define I40E_FLAG_MFP_ENABLED			BIT(10)
-#define I40E_FLAG_HW_ATR_EVICT_ENABLED		BIT(11)
-#define I40E_FLAG_VEB_MODE_ENABLED		BIT(12)
-#define I40E_FLAG_VEB_STATS_ENABLED		BIT(13)
-#define I40E_FLAG_LINK_POLLING_ENABLED		BIT(14)
-#define I40E_FLAG_TRUE_PROMISC_SUPPORT		BIT(15)
-#define I40E_FLAG_LEGACY_RX			BIT(16)
-#define I40E_FLAG_PTP				BIT(17)
-#define I40E_FLAG_IWARP_ENABLED			BIT(18)
-#define I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED	BIT(19)
-#define I40E_FLAG_SOURCE_PRUNING_DISABLED       BIT(20)
-#define I40E_FLAG_TC_MQPRIO			BIT(21)
-#define I40E_FLAG_FD_SB_INACTIVE		BIT(22)
-#define I40E_FLAG_FD_SB_TO_CLOUD_FILTER		BIT(23)
-#define I40E_FLAG_DISABLE_FW_LLDP		BIT(24)
-#define I40E_FLAG_RS_FEC			BIT(25)
-#define I40E_FLAG_BASE_R_FEC			BIT(26)
-/* TOTAL_PORT_SHUTDOWN
- * Allows to physically disable the link on the NIC's port.
- * If enabled, (after link down request from the OS)
- * no link, traffic or led activity is possible on that port.
- *
- * If I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED is set, the
- * I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED must be explicitly forced to true
- * and cannot be disabled by system admin at that time.
- * The functionalities are exclusive in terms of configuration, but they also
- * have similar behavior (allowing to disable physical link of the port),
- * with following differences:
- * - LINK_DOWN_ON_CLOSE_ENABLED is configurable at host OS run-time and is
- *   supported by whole family of 7xx Intel Ethernet Controllers
- * - TOTAL_PORT_SHUTDOWN may be enabled only before OS loads (in BIOS)
- *   only if motherboard's BIOS and NIC's FW has support of it
- * - when LINK_DOWN_ON_CLOSE_ENABLED is used, the link is being brought down
- *   by sending phy_type=0 to NIC's FW
- * - when TOTAL_PORT_SHUTDOWN is used, phy_type is not altered, instead
- *   the link is being brought down by clearing bit (I40E_AQ_PHY_ENABLE_LINK)
- *   in abilities field of i40e_aq_set_phy_config structure
- */
-#define I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED	BIT(27)
-#define I40E_FLAG_VF_VLAN_PRUNING		BIT(28)
-
+	DECLARE_BITMAP(flags, I40E_PF_FLAGS_NBITS);
 	struct i40e_client_instance *cinst;
 	bool stat_offsets_loaded;
 	struct i40e_hw_port_stats stats;
@@ -559,7 +538,6 @@ struct i40e_pf {
 	u32 tx_timeout_count;
 	u32 tx_timeout_recovery_level;
 	unsigned long tx_timeout_last_recovery;
-	u32 tx_sluggish_count;
 	u32 hw_csum_rx_error;
 	u32 led_status;
 	u16 corer_count; /* Core reset count */
@@ -581,17 +559,13 @@ struct i40e_pf {
 	struct i40e_lump_tracking *irq_pile;
 
 	/* switch config info */
-	u16 pf_seid;
 	u16 main_vsi_seid;
 	u16 mac_seid;
-	struct kobject *switch_kobj;
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *i40e_dbg_pf;
 #endif /* CONFIG_DEBUG_FS */
 	bool cur_promisc;
 
-	u16 instance; /* A unique number per i40e_pf instance in the system */
-
 	/* sr-iov config info */
 	struct i40e_vf *vf;
 	int num_alloc_vfs;	/* actual number of VFs allocated */
@@ -685,9 +659,7 @@ struct i40e_pf {
 	unsigned long ptp_tx_start;
 	struct hwtstamp_config tstamp_config;
 	struct timespec64 ptp_prev_hw_time;
-	struct work_struct ptp_pps_work;
 	struct work_struct ptp_extts0_work;
-	struct work_struct ptp_extts1_work;
 	ktime_t ptp_reset_start;
 	struct mutex tmreg_lock; /* Used to protect the SYSTIME registers. */
 	u32 ptp_adj_mult;
@@ -695,10 +667,7 @@ struct i40e_pf {
 	u32 tx_hwtstamp_skipped;
 	u32 rx_hwtstamp_cleared;
 	u32 latch_event_flags;
-	u64 ptp_pps_start;
-	u32 pps_delay;
 	spinlock_t ptp_rx_lock; /* Used to protect Rx timestamp registers. */
-	struct ptp_pin_desc ptp_pin[3];
 	unsigned long latch_events[4];
 	bool ptp_tx;
 	bool ptp_rx;
@@ -711,7 +680,6 @@ struct i40e_pf {
 	u32 fd_inv;
 	u16 phy_led_val;
 
-	u16 override_q_count;
 	u16 last_sw_conf_flags;
 	u16 last_sw_conf_valid_flags;
 	/* List to keep previous DDP profiles to be rolled back in the future */
@@ -1267,7 +1235,7 @@ struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, const u8 *macaddr);
 void i40e_vlan_stripping_enable(struct i40e_vsi *vsi);
 static inline bool i40e_is_sw_dcb(struct i40e_pf *pf)
 {
-	return !!(pf->flags & I40E_FLAG_DISABLE_FW_LLDP);
+	return test_bit(I40E_FLAG_FW_LLDP_DIS, pf->flags);
 }
 
 #ifdef CONFIG_I40E_DCB
@@ -1301,7 +1269,7 @@ int i40e_set_partition_bw_setting(struct i40e_pf *pf);
 int i40e_commit_partition_bw_setting(struct i40e_pf *pf);
 void i40e_print_link_message(struct i40e_vsi *vsi, bool isup);
 
-void i40e_set_fec_in_flags(u8 fec_cfg, u32 *flags);
+void i40e_set_fec_in_flags(u8 fec_cfg, unsigned long *flags);
 
 static inline bool i40e_enabled_xdp_vsi(struct i40e_vsi *vsi)
 {
@@ -1321,13 +1289,13 @@ int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi,
  * i40e_is_tc_mqprio_enabled - check if TC MQPRIO is enabled on PF
  * @pf: pointer to a pf.
  *
- * Check and return value of flag I40E_FLAG_TC_MQPRIO.
+ * Check and return state of flag I40E_FLAG_TC_MQPRIO.
  *
- * Return: I40E_FLAG_TC_MQPRIO set state.
+ * Return: true/false if I40E_FLAG_TC_MQPRIO is set or not
  **/
-static inline u32 i40e_is_tc_mqprio_enabled(struct i40e_pf *pf)
+static inline bool i40e_is_tc_mqprio_enabled(struct i40e_pf *pf)
 {
-	return pf->flags & I40E_FLAG_TC_MQPRIO;
+	return test_bit(I40E_FLAG_TC_MQPRIO_ENA, pf->flags);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index 9ce6e633cc2f..f73f5930fc58 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -9,40 +9,6 @@
 static void i40e_resume_aq(struct i40e_hw *hw);
 
 /**
- *  i40e_adminq_init_regs - Initialize AdminQ registers
- *  @hw: pointer to the hardware structure
- *
- *  This assumes the alloc_asq and alloc_arq functions have already been called
- **/
-static void i40e_adminq_init_regs(struct i40e_hw *hw)
-{
-	/* set head and tail registers in our local struct */
-	if (i40e_is_vf(hw)) {
-		hw->aq.asq.tail = I40E_VF_ATQT1;
-		hw->aq.asq.head = I40E_VF_ATQH1;
-		hw->aq.asq.len  = I40E_VF_ATQLEN1;
-		hw->aq.asq.bal  = I40E_VF_ATQBAL1;
-		hw->aq.asq.bah  = I40E_VF_ATQBAH1;
-		hw->aq.arq.tail = I40E_VF_ARQT1;
-		hw->aq.arq.head = I40E_VF_ARQH1;
-		hw->aq.arq.len  = I40E_VF_ARQLEN1;
-		hw->aq.arq.bal  = I40E_VF_ARQBAL1;
-		hw->aq.arq.bah  = I40E_VF_ARQBAH1;
-	} else {
-		hw->aq.asq.tail = I40E_PF_ATQT;
-		hw->aq.asq.head = I40E_PF_ATQH;
-		hw->aq.asq.len  = I40E_PF_ATQLEN;
-		hw->aq.asq.bal  = I40E_PF_ATQBAL;
-		hw->aq.asq.bah  = I40E_PF_ATQBAH;
-		hw->aq.arq.tail = I40E_PF_ARQT;
-		hw->aq.arq.head = I40E_PF_ARQH;
-		hw->aq.arq.len  = I40E_PF_ARQLEN;
-		hw->aq.arq.bal  = I40E_PF_ARQBAL;
-		hw->aq.arq.bah  = I40E_PF_ARQBAH;
-	}
-}
-
-/**
  *  i40e_alloc_adminq_asq_ring - Allocate Admin Queue send rings
  *  @hw: pointer to the hardware structure
  **/
@@ -267,17 +233,17 @@ static int i40e_config_asq_regs(struct i40e_hw *hw)
 	u32 reg = 0;
 
 	/* Clear Head and Tail */
-	wr32(hw, hw->aq.asq.head, 0);
-	wr32(hw, hw->aq.asq.tail, 0);
+	wr32(hw, I40E_PF_ATQH, 0);
+	wr32(hw, I40E_PF_ATQT, 0);
 
 	/* set starting point */
-	wr32(hw, hw->aq.asq.len, (hw->aq.num_asq_entries |
+	wr32(hw, I40E_PF_ATQLEN, (hw->aq.num_asq_entries |
 				  I40E_PF_ATQLEN_ATQENABLE_MASK));
-	wr32(hw, hw->aq.asq.bal, lower_32_bits(hw->aq.asq.desc_buf.pa));
-	wr32(hw, hw->aq.asq.bah, upper_32_bits(hw->aq.asq.desc_buf.pa));
+	wr32(hw, I40E_PF_ATQBAL, lower_32_bits(hw->aq.asq.desc_buf.pa));
+	wr32(hw, I40E_PF_ATQBAH, upper_32_bits(hw->aq.asq.desc_buf.pa));
 
 	/* Check one register to verify that config was applied */
-	reg = rd32(hw, hw->aq.asq.bal);
+	reg = rd32(hw, I40E_PF_ATQBAL);
 	if (reg != lower_32_bits(hw->aq.asq.desc_buf.pa))
 		ret_code = -EIO;
 
@@ -296,20 +262,20 @@ static int i40e_config_arq_regs(struct i40e_hw *hw)
 	u32 reg = 0;
 
 	/* Clear Head and Tail */
-	wr32(hw, hw->aq.arq.head, 0);
-	wr32(hw, hw->aq.arq.tail, 0);
+	wr32(hw, I40E_PF_ARQH, 0);
+	wr32(hw, I40E_PF_ARQT, 0);
 
 	/* set starting point */
-	wr32(hw, hw->aq.arq.len, (hw->aq.num_arq_entries |
+	wr32(hw, I40E_PF_ARQLEN, (hw->aq.num_arq_entries |
 				  I40E_PF_ARQLEN_ARQENABLE_MASK));
-	wr32(hw, hw->aq.arq.bal, lower_32_bits(hw->aq.arq.desc_buf.pa));
-	wr32(hw, hw->aq.arq.bah, upper_32_bits(hw->aq.arq.desc_buf.pa));
+	wr32(hw, I40E_PF_ARQBAL, lower_32_bits(hw->aq.arq.desc_buf.pa));
+	wr32(hw, I40E_PF_ARQBAH, upper_32_bits(hw->aq.arq.desc_buf.pa));
 
 	/* Update tail in the HW to post pre-allocated buffers */
-	wr32(hw, hw->aq.arq.tail, hw->aq.num_arq_entries - 1);
+	wr32(hw, I40E_PF_ARQT, hw->aq.num_arq_entries - 1);
 
 	/* Check one register to verify that config was applied */
-	reg = rd32(hw, hw->aq.arq.bal);
+	reg = rd32(hw, I40E_PF_ARQBAL);
 	if (reg != lower_32_bits(hw->aq.arq.desc_buf.pa))
 		ret_code = -EIO;
 
@@ -452,11 +418,11 @@ static int i40e_shutdown_asq(struct i40e_hw *hw)
 	}
 
 	/* Stop firmware AdminQ processing */
-	wr32(hw, hw->aq.asq.head, 0);
-	wr32(hw, hw->aq.asq.tail, 0);
-	wr32(hw, hw->aq.asq.len, 0);
-	wr32(hw, hw->aq.asq.bal, 0);
-	wr32(hw, hw->aq.asq.bah, 0);
+	wr32(hw, I40E_PF_ATQH, 0);
+	wr32(hw, I40E_PF_ATQT, 0);
+	wr32(hw, I40E_PF_ATQLEN, 0);
+	wr32(hw, I40E_PF_ATQBAL, 0);
+	wr32(hw, I40E_PF_ATQBAH, 0);
 
 	hw->aq.asq.count = 0; /* to indicate uninitialized queue */
 
@@ -486,11 +452,11 @@ static int i40e_shutdown_arq(struct i40e_hw *hw)
 	}
 
 	/* Stop firmware AdminQ processing */
-	wr32(hw, hw->aq.arq.head, 0);
-	wr32(hw, hw->aq.arq.tail, 0);
-	wr32(hw, hw->aq.arq.len, 0);
-	wr32(hw, hw->aq.arq.bal, 0);
-	wr32(hw, hw->aq.arq.bah, 0);
+	wr32(hw, I40E_PF_ARQH, 0);
+	wr32(hw, I40E_PF_ARQT, 0);
+	wr32(hw, I40E_PF_ARQLEN, 0);
+	wr32(hw, I40E_PF_ARQBAL, 0);
+	wr32(hw, I40E_PF_ARQBAH, 0);
 
 	hw->aq.arq.count = 0; /* to indicate uninitialized queue */
 
@@ -503,44 +469,76 @@ shutdown_arq_out:
 }
 
 /**
- *  i40e_set_hw_flags - set HW flags
+ *  i40e_set_hw_caps - set HW flags
  *  @hw: pointer to the hardware structure
  **/
-static void i40e_set_hw_flags(struct i40e_hw *hw)
+static void i40e_set_hw_caps(struct i40e_hw *hw)
 {
-	struct i40e_adminq_info *aq = &hw->aq;
-
-	hw->flags = 0;
+	bitmap_zero(hw->caps, I40E_HW_CAPS_NBITS);
 
 	switch (hw->mac.type) {
 	case I40E_MAC_XL710:
-		if (aq->api_maj_ver > 1 ||
-		    (aq->api_maj_ver == 1 &&
-		     aq->api_min_ver >= I40E_MINOR_VER_GET_LINK_INFO_XL710)) {
-			hw->flags |= I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE;
-			hw->flags |= I40E_HW_FLAG_FW_LLDP_STOPPABLE;
+		if (i40e_is_aq_api_ver_ge(hw, 1,
+					  I40E_MINOR_VER_GET_LINK_INFO_XL710)) {
+			set_bit(I40E_HW_CAP_AQ_PHY_ACCESS, hw->caps);
+			set_bit(I40E_HW_CAP_FW_LLDP_STOPPABLE, hw->caps);
 			/* The ability to RX (not drop) 802.1ad frames */
-			hw->flags |= I40E_HW_FLAG_802_1AD_CAPABLE;
+			set_bit(I40E_HW_CAP_802_1AD, hw->caps);
+		}
+		if (i40e_is_aq_api_ver_ge(hw, 1, 5)) {
+			/* Supported in FW API version higher than 1.4 */
+			set_bit(I40E_HW_CAP_GENEVE_OFFLOAD, hw->caps);
+		}
+		if (i40e_is_fw_ver_lt(hw, 4, 33)) {
+			set_bit(I40E_HW_CAP_RESTART_AUTONEG, hw->caps);
+			/* No DCB support  for FW < v4.33 */
+			set_bit(I40E_HW_CAP_NO_DCB_SUPPORT, hw->caps);
+		}
+		if (i40e_is_fw_ver_lt(hw, 4, 3)) {
+			/* Disable FW LLDP if FW < v4.3 */
+			set_bit(I40E_HW_CAP_STOP_FW_LLDP, hw->caps);
+		}
+		if (i40e_is_fw_ver_ge(hw, 4, 40)) {
+			/* Use the FW Set LLDP MIB API if FW >= v4.40 */
+			set_bit(I40E_HW_CAP_USE_SET_LLDP_MIB, hw->caps);
+		}
+		if (i40e_is_fw_ver_ge(hw, 6, 0)) {
+			/* Enable PTP L4 if FW > v6.0 */
+			set_bit(I40E_HW_CAP_PTP_L4, hw->caps);
 		}
 		break;
 	case I40E_MAC_X722:
-		hw->flags |= I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE |
-			     I40E_HW_FLAG_NVM_READ_REQUIRES_LOCK;
+		set_bit(I40E_HW_CAP_AQ_SRCTL_ACCESS_ENABLE, hw->caps);
+		set_bit(I40E_HW_CAP_NVM_READ_REQUIRES_LOCK, hw->caps);
+		set_bit(I40E_HW_CAP_RSS_AQ, hw->caps);
+		set_bit(I40E_HW_CAP_128_QP_RSS, hw->caps);
+		set_bit(I40E_HW_CAP_ATR_EVICT, hw->caps);
+		set_bit(I40E_HW_CAP_WB_ON_ITR, hw->caps);
+		set_bit(I40E_HW_CAP_MULTI_TCP_UDP_RSS_PCTYPE, hw->caps);
+		set_bit(I40E_HW_CAP_NO_PCI_LINK_CHECK, hw->caps);
+		set_bit(I40E_HW_CAP_USE_SET_LLDP_MIB, hw->caps);
+		set_bit(I40E_HW_CAP_GENEVE_OFFLOAD, hw->caps);
+		set_bit(I40E_HW_CAP_PTP_L4, hw->caps);
+		set_bit(I40E_HW_CAP_WOL_MC_MAGIC_PKT_WAKE, hw->caps);
+		set_bit(I40E_HW_CAP_OUTER_UDP_CSUM, hw->caps);
+
+		if (rd32(hw, I40E_GLQF_FDEVICTENA(1)) !=
+		    I40E_FDEVICT_PCTYPE_DEFAULT) {
+			hw_warn(hw, "FD EVICT PCTYPES are not right, disable FD HW EVICT\n");
+			clear_bit(I40E_HW_CAP_ATR_EVICT, hw->caps);
+		}
 
-		if (aq->api_maj_ver > 1 ||
-		    (aq->api_maj_ver == 1 &&
-		     aq->api_min_ver >= I40E_MINOR_VER_FW_LLDP_STOPPABLE_X722))
-			hw->flags |= I40E_HW_FLAG_FW_LLDP_STOPPABLE;
+		if (i40e_is_aq_api_ver_ge(hw, 1,
+					  I40E_MINOR_VER_FW_LLDP_STOPPABLE_X722))
+			set_bit(I40E_HW_CAP_FW_LLDP_STOPPABLE, hw->caps);
 
-		if (aq->api_maj_ver > 1 ||
-		    (aq->api_maj_ver == 1 &&
-		     aq->api_min_ver >= I40E_MINOR_VER_GET_LINK_INFO_X722))
-			hw->flags |= I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE;
+		if (i40e_is_aq_api_ver_ge(hw, 1,
+					  I40E_MINOR_VER_GET_LINK_INFO_X722))
+			set_bit(I40E_HW_CAP_AQ_PHY_ACCESS, hw->caps);
 
-		if (aq->api_maj_ver > 1 ||
-		    (aq->api_maj_ver == 1 &&
-		     aq->api_min_ver >= I40E_MINOR_VER_FW_REQUEST_FEC_X722))
-			hw->flags |= I40E_HW_FLAG_X722_FEC_REQUEST_CAPABLE;
+		if (i40e_is_aq_api_ver_ge(hw, 1,
+					  I40E_MINOR_VER_FW_REQUEST_FEC_X722))
+			set_bit(I40E_HW_CAP_X722_FEC_REQUEST, hw->caps);
 
 		fallthrough;
 	default:
@@ -548,22 +546,18 @@ static void i40e_set_hw_flags(struct i40e_hw *hw)
 	}
 
 	/* Newer versions of firmware require lock when reading the NVM */
-	if (aq->api_maj_ver > 1 ||
-	    (aq->api_maj_ver == 1 &&
-	     aq->api_min_ver >= 5))
-		hw->flags |= I40E_HW_FLAG_NVM_READ_REQUIRES_LOCK;
-
-	if (aq->api_maj_ver > 1 ||
-	    (aq->api_maj_ver == 1 &&
-	     aq->api_min_ver >= 8)) {
-		hw->flags |= I40E_HW_FLAG_FW_LLDP_PERSISTENT;
-		hw->flags |= I40E_HW_FLAG_DROP_MODE;
-	}
+	if (i40e_is_aq_api_ver_ge(hw, 1, 5))
+		set_bit(I40E_HW_CAP_NVM_READ_REQUIRES_LOCK, hw->caps);
+
+	/* The ability to RX (not drop) 802.1ad frames was added in API 1.7 */
+	if (i40e_is_aq_api_ver_ge(hw, 1, 7))
+		set_bit(I40E_HW_CAP_802_1AD, hw->caps);
+
+	if (i40e_is_aq_api_ver_ge(hw, 1, 8))
+		set_bit(I40E_HW_CAP_FW_LLDP_PERSISTENT, hw->caps);
 
-	if (aq->api_maj_ver > 1 ||
-	    (aq->api_maj_ver == 1 &&
-	     aq->api_min_ver >= 9))
-		hw->flags |= I40E_HW_FLAG_AQ_PHY_ACCESS_EXTENDED;
+	if (i40e_is_aq_api_ver_ge(hw, 1, 9))
+		set_bit(I40E_HW_CAP_AQ_PHY_ACCESS_EXTENDED, hw->caps);
 }
 
 /**
@@ -593,9 +587,6 @@ int i40e_init_adminq(struct i40e_hw *hw)
 		goto init_adminq_exit;
 	}
 
-	/* Set up register offsets */
-	i40e_adminq_init_regs(hw);
-
 	/* setup ASQ command write back timeout */
 	hw->aq.asq_cmd_timeout = I40E_ASQ_CMD_TIMEOUT;
 
@@ -633,7 +624,7 @@ int i40e_init_adminq(struct i40e_hw *hw)
 	/* Some features were introduced in different FW API version
 	 * for different MAC type.
 	 */
-	i40e_set_hw_flags(hw);
+	i40e_set_hw_caps(hw);
 
 	/* get the NVM version info */
 	i40e_read_nvm_word(hw, I40E_SR_NVM_DEV_STARTER_VERSION,
@@ -648,25 +639,7 @@ int i40e_init_adminq(struct i40e_hw *hw)
 			   &oem_lo);
 	hw->nvm.oem_ver = ((u32)oem_hi << 16) | oem_lo;
 
-	if (hw->mac.type == I40E_MAC_XL710 &&
-	    hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
-	    hw->aq.api_min_ver >= I40E_MINOR_VER_GET_LINK_INFO_XL710) {
-		hw->flags |= I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE;
-		hw->flags |= I40E_HW_FLAG_FW_LLDP_STOPPABLE;
-	}
-	if (hw->mac.type == I40E_MAC_X722 &&
-	    hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
-	    hw->aq.api_min_ver >= I40E_MINOR_VER_FW_LLDP_STOPPABLE_X722) {
-		hw->flags |= I40E_HW_FLAG_FW_LLDP_STOPPABLE;
-	}
-
-	/* The ability to RX (not drop) 802.1ad frames was added in API 1.7 */
-	if (hw->aq.api_maj_ver > 1 ||
-	    (hw->aq.api_maj_ver == 1 &&
-	     hw->aq.api_min_ver >= 7))
-		hw->flags |= I40E_HW_FLAG_802_1AD_CAPABLE;
-
-	if (hw->aq.api_maj_ver > I40E_FW_API_VERSION_MAJOR) {
+	if (i40e_is_aq_api_ver_ge(hw, I40E_FW_API_VERSION_MAJOR + 1, 0)) {
 		ret_code = -EIO;
 		goto init_adminq_free_arq;
 	}
@@ -723,9 +696,9 @@ static u16 i40e_clean_asq(struct i40e_hw *hw)
 
 	desc = I40E_ADMINQ_DESC(*asq, ntc);
 	details = I40E_ADMINQ_DETAILS(*asq, ntc);
-	while (rd32(hw, hw->aq.asq.head) != ntc) {
+	while (rd32(hw, I40E_PF_ATQH) != ntc) {
 		i40e_debug(hw, I40E_DEBUG_AQ_COMMAND,
-			   "ntc %d head %d.\n", ntc, rd32(hw, hw->aq.asq.head));
+			   "ntc %d head %d.\n", ntc, rd32(hw, I40E_PF_ATQH));
 
 		if (details->callback) {
 			I40E_ADMINQ_CALLBACK cb_func =
@@ -759,7 +732,7 @@ static bool i40e_asq_done(struct i40e_hw *hw)
 	/* AQ designers suggest use of head for better
 	 * timing reliability than DD bit
 	 */
-	return rd32(hw, hw->aq.asq.head) == hw->aq.asq.next_to_use;
+	return rd32(hw, I40E_PF_ATQH) == hw->aq.asq.next_to_use;
 
 }
 
@@ -800,7 +773,7 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw,
 
 	hw->aq.asq_last_status = I40E_AQ_RC_OK;
 
-	val = rd32(hw, hw->aq.asq.head);
+	val = rd32(hw, I40E_PF_ATQH);
 	if (val >= hw->aq.num_asq_entries) {
 		i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
 			   "AQTX: head overrun at %d\n", val);
@@ -892,7 +865,7 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw,
 	if (hw->aq.asq.next_to_use == hw->aq.asq.count)
 		hw->aq.asq.next_to_use = 0;
 	if (!details->postpone)
-		wr32(hw, hw->aq.asq.tail, hw->aq.asq.next_to_use);
+		wr32(hw, I40E_PF_ATQT, hw->aq.asq.next_to_use);
 
 	/* if cmd_details are not defined or async flag is not set,
 	 * we need to wait for desc write back
@@ -952,7 +925,7 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw,
 	/* update the error if time out occurred */
 	if ((!cmd_completed) &&
 	    (!details->async && !details->postpone)) {
-		if (rd32(hw, hw->aq.asq.len) & I40E_GL_ATQLEN_ATQCRIT_MASK) {
+		if (rd32(hw, I40E_PF_ATQLEN) & I40E_GL_ATQLEN_ATQCRIT_MASK) {
 			i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
 				   "AQTX: AQ Critical error.\n");
 			status = -EIO;
@@ -1106,7 +1079,7 @@ int i40e_clean_arq_element(struct i40e_hw *hw,
 	}
 
 	/* set next_to_use to head */
-	ntu = rd32(hw, hw->aq.arq.head) & I40E_PF_ARQH_ARQH_MASK;
+	ntu = rd32(hw, I40E_PF_ARQH) & I40E_PF_ARQH_ARQH_MASK;
 	if (ntu == ntc) {
 		/* nothing to do - shouldn't need to update ring's values */
 		ret_code = -EALREADY;
@@ -1154,7 +1127,7 @@ int i40e_clean_arq_element(struct i40e_hw *hw,
 	desc->params.external.addr_low = cpu_to_le32(lower_32_bits(bi->pa));
 
 	/* set tail = the last cleaned desc index. */
-	wr32(hw, hw->aq.arq.tail, ntc);
+	wr32(hw, I40E_PF_ARQT, ntc);
 	/* ntc is updated to tail + 1 */
 	ntc++;
 	if (ntc == hw->aq.num_arq_entries)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.h b/drivers/net/ethernet/intel/i40e/i40e_adminq.h
index 80125bea80a2..ee86d2c53079 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.h
@@ -29,13 +29,6 @@ struct i40e_adminq_ring {
 	/* used for interrupt processing */
 	u16 next_to_use;
 	u16 next_to_clean;
-
-	/* used for queue tracking */
-	u32 head;
-	u32 tail;
-	u32 len;
-	u32 bah;
-	u32 bal;
 };
 
 /* ASQ transaction details */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index d7e24d661724..de6ca6295742 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -2,6 +2,7 @@
 /* Copyright(c) 2013 - 2021 Intel Corporation. */
 
 #include <linux/avf/virtchnl.h>
+#include <linux/bitfield.h>
 #include <linux/delay.h>
 #include <linux/etherdevice.h>
 #include <linux/pci.h>
@@ -195,11 +196,11 @@ void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc,
  **/
 bool i40e_check_asq_alive(struct i40e_hw *hw)
 {
-	if (hw->aq.asq.len)
-		return !!(rd32(hw, hw->aq.asq.len) &
-			  I40E_PF_ATQLEN_ATQENABLE_MASK);
-	else
+	/* Check if the queue is initialized */
+	if (!hw->aq.asq.count)
 		return false;
+
+	return !!(rd32(hw, I40E_PF_ATQLEN) & I40E_PF_ATQLEN_ATQENABLE_MASK);
 }
 
 /**
@@ -248,6 +249,7 @@ static int i40e_aq_get_set_rss_lut(struct i40e_hw *hw,
 	struct i40e_aqc_get_set_rss_lut *cmd_resp =
 		   (struct i40e_aqc_get_set_rss_lut *)&desc.params.raw;
 	int status;
+	u16 flags;
 
 	if (set)
 		i40e_fill_default_direct_cmd_desc(&desc,
@@ -260,23 +262,18 @@ static int i40e_aq_get_set_rss_lut(struct i40e_hw *hw,
 	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
 	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD);
 
-	cmd_resp->vsi_id =
-			cpu_to_le16((u16)((vsi_id <<
-					  I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT) &
-					  I40E_AQC_SET_RSS_LUT_VSI_ID_MASK));
-	cmd_resp->vsi_id |= cpu_to_le16((u16)I40E_AQC_SET_RSS_LUT_VSI_VALID);
+	vsi_id = FIELD_PREP(I40E_AQC_SET_RSS_LUT_VSI_ID_MASK, vsi_id) |
+		 FIELD_PREP(I40E_AQC_SET_RSS_LUT_VSI_VALID, 1);
+	cmd_resp->vsi_id = cpu_to_le16(vsi_id);
 
 	if (pf_lut)
-		cmd_resp->flags |= cpu_to_le16((u16)
-					((I40E_AQC_SET_RSS_LUT_TABLE_TYPE_PF <<
-					I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) &
-					I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK));
+		flags = FIELD_PREP(I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK,
+				   I40E_AQC_SET_RSS_LUT_TABLE_TYPE_PF);
 	else
-		cmd_resp->flags |= cpu_to_le16((u16)
-					((I40E_AQC_SET_RSS_LUT_TABLE_TYPE_VSI <<
-					I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) &
-					I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK));
+		flags = FIELD_PREP(I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK,
+				   I40E_AQC_SET_RSS_LUT_TABLE_TYPE_VSI);
 
+	cmd_resp->flags = cpu_to_le16(flags);
 	status = i40e_asq_send_command(hw, &desc, lut, lut_size, NULL);
 
 	return status;
@@ -346,11 +343,9 @@ static int i40e_aq_get_set_rss_key(struct i40e_hw *hw,
 	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
 	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD);
 
-	cmd_resp->vsi_id =
-			cpu_to_le16((u16)((vsi_id <<
-					  I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT) &
-					  I40E_AQC_SET_RSS_KEY_VSI_ID_MASK));
-	cmd_resp->vsi_id |= cpu_to_le16((u16)I40E_AQC_SET_RSS_KEY_VSI_VALID);
+	vsi_id = FIELD_PREP(I40E_AQC_SET_RSS_KEY_VSI_ID_MASK, vsi_id) |
+		 FIELD_PREP(I40E_AQC_SET_RSS_KEY_VSI_VALID, 1);
+	cmd_resp->vsi_id = cpu_to_le16(vsi_id);
 
 	status = i40e_asq_send_command(hw, &desc, key, key_size, NULL);
 
@@ -669,11 +664,11 @@ int i40e_init_shared_code(struct i40e_hw *hw)
 	hw->phy.get_link_info = true;
 
 	/* Determine port number and PF number*/
-	port = (rd32(hw, I40E_PFGEN_PORTNUM) & I40E_PFGEN_PORTNUM_PORT_NUM_MASK)
-					   >> I40E_PFGEN_PORTNUM_PORT_NUM_SHIFT;
+	port = FIELD_GET(I40E_PFGEN_PORTNUM_PORT_NUM_MASK,
+			 rd32(hw, I40E_PFGEN_PORTNUM));
 	hw->port = (u8)port;
-	ari = (rd32(hw, I40E_GLPCI_CAPSUP) & I40E_GLPCI_CAPSUP_ARI_EN_MASK) >>
-						 I40E_GLPCI_CAPSUP_ARI_EN_SHIFT;
+	ari = FIELD_GET(I40E_GLPCI_CAPSUP_ARI_EN_MASK,
+			rd32(hw, I40E_GLPCI_CAPSUP));
 	func_rid = rd32(hw, I40E_PF_FUNC_RID);
 	if (ari)
 		hw->pf_id = (u8)(func_rid & 0xff);
@@ -991,9 +986,8 @@ int i40e_pf_reset(struct i40e_hw *hw)
 	 * The grst delay value is in 100ms units, and we'll wait a
 	 * couple counts longer to be sure we don't just miss the end.
 	 */
-	grst_del = (rd32(hw, I40E_GLGEN_RSTCTL) &
-		    I40E_GLGEN_RSTCTL_GRSTDEL_MASK) >>
-		    I40E_GLGEN_RSTCTL_GRSTDEL_SHIFT;
+	grst_del = FIELD_GET(I40E_GLGEN_RSTCTL_GRSTDEL_MASK,
+			     rd32(hw, I40E_GLGEN_RSTCTL));
 
 	/* It can take upto 15 secs for GRST steady state.
 	 * Bump it to 16 secs max to be safe.
@@ -1085,26 +1079,20 @@ void i40e_clear_hw(struct i40e_hw *hw)
 
 	/* get number of interrupts, queues, and VFs */
 	val = rd32(hw, I40E_GLPCI_CNF2);
-	num_pf_int = (val & I40E_GLPCI_CNF2_MSI_X_PF_N_MASK) >>
-		     I40E_GLPCI_CNF2_MSI_X_PF_N_SHIFT;
-	num_vf_int = (val & I40E_GLPCI_CNF2_MSI_X_VF_N_MASK) >>
-		     I40E_GLPCI_CNF2_MSI_X_VF_N_SHIFT;
+	num_pf_int = FIELD_GET(I40E_GLPCI_CNF2_MSI_X_PF_N_MASK, val);
+	num_vf_int = FIELD_GET(I40E_GLPCI_CNF2_MSI_X_VF_N_MASK, val);
 
 	val = rd32(hw, I40E_PFLAN_QALLOC);
-	base_queue = (val & I40E_PFLAN_QALLOC_FIRSTQ_MASK) >>
-		     I40E_PFLAN_QALLOC_FIRSTQ_SHIFT;
-	j = (val & I40E_PFLAN_QALLOC_LASTQ_MASK) >>
-	    I40E_PFLAN_QALLOC_LASTQ_SHIFT;
+	base_queue = FIELD_GET(I40E_PFLAN_QALLOC_FIRSTQ_MASK, val);
+	j = FIELD_GET(I40E_PFLAN_QALLOC_LASTQ_MASK, val);
 	if (val & I40E_PFLAN_QALLOC_VALID_MASK && j >= base_queue)
 		num_queues = (j - base_queue) + 1;
 	else
 		num_queues = 0;
 
 	val = rd32(hw, I40E_PF_VT_PFALLOC);
-	i = (val & I40E_PF_VT_PFALLOC_FIRSTVF_MASK) >>
-	    I40E_PF_VT_PFALLOC_FIRSTVF_SHIFT;
-	j = (val & I40E_PF_VT_PFALLOC_LASTVF_MASK) >>
-	    I40E_PF_VT_PFALLOC_LASTVF_SHIFT;
+	i = FIELD_GET(I40E_PF_VT_PFALLOC_FIRSTVF_MASK, val);
+	j = FIELD_GET(I40E_PF_VT_PFALLOC_LASTVF_MASK, val);
 	if (val & I40E_PF_VT_PFALLOC_VALID_MASK && j >= i)
 		num_vfs = (j - i) + 1;
 	else
@@ -1199,8 +1187,7 @@ static u32 i40e_led_is_mine(struct i40e_hw *hw, int idx)
 	    !hw->func_caps.led[idx])
 		return 0;
 	gpio_val = rd32(hw, I40E_GLGEN_GPIO_CTL(idx));
-	port = (gpio_val & I40E_GLGEN_GPIO_CTL_PRT_NUM_MASK) >>
-		I40E_GLGEN_GPIO_CTL_PRT_NUM_SHIFT;
+	port = FIELD_GET(I40E_GLGEN_GPIO_CTL_PRT_NUM_MASK, gpio_val);
 
 	/* if PRT_NUM_NA is 1 then this LED is not port specific, OR
 	 * if it is not our port then ignore
@@ -1244,8 +1231,7 @@ u32 i40e_led_get(struct i40e_hw *hw)
 		if (!gpio_val)
 			continue;
 
-		mode = (gpio_val & I40E_GLGEN_GPIO_CTL_LED_MODE_MASK) >>
-			I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT;
+		mode = FIELD_GET(I40E_GLGEN_GPIO_CTL_LED_MODE_MASK, gpio_val);
 		break;
 	}
 
@@ -1288,14 +1274,14 @@ void i40e_led_set(struct i40e_hw *hw, u32 mode, bool blink)
 				pin_func = I40E_PIN_FUNC_LED;
 
 			gpio_val &= ~I40E_GLGEN_GPIO_CTL_PIN_FUNC_MASK;
-			gpio_val |= ((pin_func <<
-				     I40E_GLGEN_GPIO_CTL_PIN_FUNC_SHIFT) &
-				     I40E_GLGEN_GPIO_CTL_PIN_FUNC_MASK);
+			gpio_val |=
+				FIELD_PREP(I40E_GLGEN_GPIO_CTL_PIN_FUNC_MASK,
+					   pin_func);
 		}
 		gpio_val &= ~I40E_GLGEN_GPIO_CTL_LED_MODE_MASK;
 		/* this & is a bit of paranoia, but serves as a range check */
-		gpio_val |= ((mode << I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT) &
-			     I40E_GLGEN_GPIO_CTL_LED_MODE_MASK);
+		gpio_val |= FIELD_PREP(I40E_GLGEN_GPIO_CTL_LED_MODE_MASK,
+				       mode);
 
 		if (blink)
 			gpio_val |= BIT(I40E_GLGEN_GPIO_CTL_LED_BLINK_SHIFT);
@@ -1374,8 +1360,8 @@ i40e_aq_get_phy_capabilities(struct i40e_hw *hw,
 
 	if (report_init) {
 		if (hw->mac.type ==  I40E_MAC_XL710 &&
-		    hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
-		    hw->aq.api_min_ver >= I40E_MINOR_VER_GET_LINK_INFO_XL710) {
+		    i40e_is_aq_api_ver_ge(hw, I40E_FW_API_VERSION_MAJOR,
+					  I40E_MINOR_VER_GET_LINK_INFO_XL710)) {
 			status = i40e_aq_get_link_info(hw, true, NULL, NULL);
 		} else {
 			hw->phy.phy_types = le32_to_cpu(abilities->phy_type);
@@ -1645,12 +1631,11 @@ int i40e_aq_get_link_info(struct i40e_hw *hw,
 	else
 		hw_link_info->lse_enable = false;
 
-	if ((hw->mac.type == I40E_MAC_XL710) &&
-	    (hw->aq.fw_maj_ver < 4 || (hw->aq.fw_maj_ver == 4 &&
-	     hw->aq.fw_min_ver < 40)) && hw_link_info->phy_type == 0xE)
+	if (hw->mac.type == I40E_MAC_XL710 && i40e_is_fw_ver_lt(hw, 4, 40) &&
+	    hw_link_info->phy_type == 0xE)
 		hw_link_info->phy_type = I40E_PHY_TYPE_10GBASE_SFPP_CU;
 
-	if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE &&
+	if (test_bit(I40E_HW_CAP_AQ_PHY_ACCESS, hw->caps) &&
 	    hw->mac.type != I40E_MAC_X722) {
 		__le32 tmp;
 
@@ -1750,21 +1735,6 @@ int i40e_aq_set_phy_debug(struct i40e_hw *hw, u8 cmd_flags,
 }
 
 /**
- * i40e_is_aq_api_ver_ge
- * @aq: pointer to AdminQ info containing HW API version to compare
- * @maj: API major value
- * @min: API minor value
- *
- * Assert whether current HW API version is greater/equal than provided.
- **/
-static bool i40e_is_aq_api_ver_ge(struct i40e_adminq_info *aq, u16 maj,
-				  u16 min)
-{
-	return (aq->api_maj_ver > maj ||
-		(aq->api_maj_ver == maj && aq->api_min_ver >= min));
-}
-
-/**
  * i40e_aq_add_vsi
  * @hw: pointer to the hw struct
  * @vsi_ctx: pointer to a vsi context struct
@@ -1890,14 +1860,14 @@ int i40e_aq_set_vsi_unicast_promiscuous(struct i40e_hw *hw,
 
 	if (set) {
 		flags |= I40E_AQC_SET_VSI_PROMISC_UNICAST;
-		if (rx_only_promisc && i40e_is_aq_api_ver_ge(&hw->aq, 1, 5))
+		if (rx_only_promisc && i40e_is_aq_api_ver_ge(hw, 1, 5))
 			flags |= I40E_AQC_SET_VSI_PROMISC_RX_ONLY;
 	}
 
 	cmd->promiscuous_flags = cpu_to_le16(flags);
 
 	cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_UNICAST);
-	if (i40e_is_aq_api_ver_ge(&hw->aq, 1, 5))
+	if (i40e_is_aq_api_ver_ge(hw, 1, 5))
 		cmd->valid_flags |=
 			cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_RX_ONLY);
 
@@ -2000,13 +1970,13 @@ int i40e_aq_set_vsi_uc_promisc_on_vlan(struct i40e_hw *hw,
 
 	if (enable) {
 		flags |= I40E_AQC_SET_VSI_PROMISC_UNICAST;
-		if (i40e_is_aq_api_ver_ge(&hw->aq, 1, 5))
+		if (i40e_is_aq_api_ver_ge(hw, 1, 5))
 			flags |= I40E_AQC_SET_VSI_PROMISC_RX_ONLY;
 	}
 
 	cmd->promiscuous_flags = cpu_to_le16(flags);
 	cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_UNICAST);
-	if (i40e_is_aq_api_ver_ge(&hw->aq, 1, 5))
+	if (i40e_is_aq_api_ver_ge(hw, 1, 5))
 		cmd->valid_flags |=
 			cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_RX_ONLY);
 	cmd->seid = cpu_to_le16(seid);
@@ -2253,7 +2223,7 @@ int i40e_aq_set_switch_config(struct i40e_hw *hw,
 	scfg->flags = cpu_to_le16(flags);
 	scfg->valid_flags = cpu_to_le16(valid_flags);
 	scfg->mode = mode;
-	if (hw->flags & I40E_HW_FLAG_802_1AD_CAPABLE) {
+	if (test_bit(I40E_HW_CAP_802_1AD, hw->caps)) {
 		scfg->switch_tag = cpu_to_le16(hw->switch_tag);
 		scfg->first_tag = cpu_to_le16(hw->first_tag);
 		scfg->second_tag = cpu_to_le16(hw->second_tag);
@@ -3530,8 +3500,7 @@ int i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type,
 	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
 
 	cmd->type = mib_type & I40E_AQ_LLDP_MIB_TYPE_MASK;
-	cmd->type |= ((bridge_type << I40E_AQ_LLDP_BRIDGE_TYPE_SHIFT) &
-		       I40E_AQ_LLDP_BRIDGE_TYPE_MASK);
+	cmd->type |= FIELD_PREP(I40E_AQ_LLDP_BRIDGE_TYPE_MASK, bridge_type);
 
 	desc.datalen = cpu_to_le16(buff_size);
 
@@ -3637,7 +3606,7 @@ i40e_aq_restore_lldp(struct i40e_hw *hw, u8 *setting, bool restore,
 		(struct i40e_aqc_lldp_restore *)&desc.params.raw;
 	int status;
 
-	if (!(hw->flags & I40E_HW_FLAG_FW_LLDP_PERSISTENT)) {
+	if (!test_bit(I40E_HW_CAP_FW_LLDP_PERSISTENT, hw->caps)) {
 		i40e_debug(hw, I40E_DEBUG_ALL,
 			   "Restore LLDP not supported by current FW version.\n");
 		return -ENODEV;
@@ -3680,7 +3649,7 @@ int i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent,
 		cmd->command |= I40E_AQ_LLDP_AGENT_SHUTDOWN;
 
 	if (persist) {
-		if (hw->flags & I40E_HW_FLAG_FW_LLDP_PERSISTENT)
+		if (test_bit(I40E_HW_CAP_FW_LLDP_PERSISTENT, hw->caps))
 			cmd->command |= I40E_AQ_LLDP_AGENT_STOP_PERSIST;
 		else
 			i40e_debug(hw, I40E_DEBUG_ALL,
@@ -3713,7 +3682,7 @@ int i40e_aq_start_lldp(struct i40e_hw *hw, bool persist,
 	cmd->command = I40E_AQ_LLDP_AGENT_START;
 
 	if (persist) {
-		if (hw->flags & I40E_HW_FLAG_FW_LLDP_PERSISTENT)
+		if (test_bit(I40E_HW_CAP_FW_LLDP_PERSISTENT, hw->caps))
 			cmd->command |= I40E_AQ_LLDP_AGENT_START_PERSIST;
 		else
 			i40e_debug(hw, I40E_DEBUG_ALL,
@@ -3741,7 +3710,7 @@ i40e_aq_set_dcb_parameters(struct i40e_hw *hw, bool dcb_enable,
 		(struct i40e_aqc_set_dcb_parameters *)&desc.params.raw;
 	int status;
 
-	if (!(hw->flags & I40E_HW_FLAG_FW_LLDP_STOPPABLE))
+	if (!test_bit(I40E_HW_CAP_FW_LLDP_STOPPABLE, hw->caps))
 		return -ENODEV;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
@@ -4212,8 +4181,7 @@ i40e_validate_filter_settings(struct i40e_hw *hw,
 
 	/* FCHSIZE + FCDSIZE should not be greater than PMFCOEFMAX */
 	val = rd32(hw, I40E_GLHMC_FCOEFMAX);
-	fcoe_fmax = (val & I40E_GLHMC_FCOEFMAX_PMFCOEFMAX_MASK)
-		     >> I40E_GLHMC_FCOEFMAX_PMFCOEFMAX_SHIFT;
+	fcoe_fmax = FIELD_GET(I40E_GLHMC_FCOEFMAX_PMFCOEFMAX_MASK, val);
 	if (fcoe_filt_size + fcoe_cntx_size >  fcoe_fmax)
 		return -EINVAL;
 
@@ -4249,30 +4217,25 @@ int i40e_set_filter_control(struct i40e_hw *hw,
 
 	/* Program required PE hash buckets for the PF */
 	val &= ~I40E_PFQF_CTL_0_PEHSIZE_MASK;
-	val |= ((u32)settings->pe_filt_num << I40E_PFQF_CTL_0_PEHSIZE_SHIFT) &
-		I40E_PFQF_CTL_0_PEHSIZE_MASK;
+	val |= FIELD_PREP(I40E_PFQF_CTL_0_PEHSIZE_MASK, settings->pe_filt_num);
 	/* Program required PE contexts for the PF */
 	val &= ~I40E_PFQF_CTL_0_PEDSIZE_MASK;
-	val |= ((u32)settings->pe_cntx_num << I40E_PFQF_CTL_0_PEDSIZE_SHIFT) &
-		I40E_PFQF_CTL_0_PEDSIZE_MASK;
+	val |= FIELD_PREP(I40E_PFQF_CTL_0_PEDSIZE_MASK, settings->pe_cntx_num);
 
 	/* Program required FCoE hash buckets for the PF */
 	val &= ~I40E_PFQF_CTL_0_PFFCHSIZE_MASK;
-	val |= ((u32)settings->fcoe_filt_num <<
-			I40E_PFQF_CTL_0_PFFCHSIZE_SHIFT) &
-		I40E_PFQF_CTL_0_PFFCHSIZE_MASK;
+	val |= FIELD_PREP(I40E_PFQF_CTL_0_PFFCHSIZE_MASK,
+			  settings->fcoe_filt_num);
 	/* Program required FCoE DDP contexts for the PF */
 	val &= ~I40E_PFQF_CTL_0_PFFCDSIZE_MASK;
-	val |= ((u32)settings->fcoe_cntx_num <<
-			I40E_PFQF_CTL_0_PFFCDSIZE_SHIFT) &
-		I40E_PFQF_CTL_0_PFFCDSIZE_MASK;
+	val |= FIELD_PREP(I40E_PFQF_CTL_0_PFFCDSIZE_MASK,
+			  settings->fcoe_cntx_num);
 
 	/* Program Hash LUT size for the PF */
 	val &= ~I40E_PFQF_CTL_0_HASHLUTSIZE_MASK;
 	if (settings->hash_lut_size == I40E_HASH_LUT_SIZE_512)
 		hash_lut_size = 1;
-	val |= (hash_lut_size << I40E_PFQF_CTL_0_HASHLUTSIZE_SHIFT) &
-		I40E_PFQF_CTL_0_HASHLUTSIZE_MASK;
+	val |= FIELD_PREP(I40E_PFQF_CTL_0_HASHLUTSIZE_MASK, hash_lut_size);
 
 	/* Enable FDIR, Ethertype and MACVLAN filters for PF and VFs */
 	if (settings->enable_fdir)
@@ -4673,8 +4636,7 @@ int i40e_read_phy_register_clause22(struct i40e_hw *hw,
 			   "PHY: Can't write command to external PHY.\n");
 	} else {
 		command = rd32(hw, I40E_GLGEN_MSRWD(port_num));
-		*value = (command & I40E_GLGEN_MSRWD_MDIRDDATA_MASK) >>
-			 I40E_GLGEN_MSRWD_MDIRDDATA_SHIFT;
+		*value = FIELD_GET(I40E_GLGEN_MSRWD_MDIRDDATA_MASK, command);
 	}
 
 	return status;
@@ -4783,8 +4745,7 @@ int i40e_read_phy_register_clause45(struct i40e_hw *hw,
 
 	if (!status) {
 		command = rd32(hw, I40E_GLGEN_MSRWD(port_num));
-		*value = (command & I40E_GLGEN_MSRWD_MDIRDDATA_MASK) >>
-			 I40E_GLGEN_MSRWD_MDIRDDATA_SHIFT;
+		*value = FIELD_GET(I40E_GLGEN_MSRWD_MDIRDDATA_MASK, command);
 	} else {
 		i40e_debug(hw, I40E_DEBUG_PHY,
 			   "PHY: Can't read register value from external PHY.\n");
@@ -5043,7 +5004,7 @@ static int i40e_led_get_reg(struct i40e_hw *hw, u16 led_addr,
 	u32 i;
 
 	*reg_val = 0;
-	if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) {
+	if (test_bit(I40E_HW_CAP_AQ_PHY_ACCESS, hw->caps)) {
 		status =
 		       i40e_aq_get_phy_register(hw,
 						I40E_AQ_PHY_REG_ACCESS_EXTERNAL,
@@ -5076,7 +5037,7 @@ static int i40e_led_set_reg(struct i40e_hw *hw, u16 led_addr,
 	int status;
 	u32 i;
 
-	if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) {
+	if (test_bit(I40E_HW_CAP_AQ_PHY_ACCESS, hw->caps)) {
 		status =
 		       i40e_aq_set_phy_register(hw,
 						I40E_AQ_PHY_REG_ACCESS_EXTERNAL,
@@ -5115,7 +5076,7 @@ int i40e_led_get_phy(struct i40e_hw *hw, u16 *led_addr,
 	u8 port_num;
 	u32 i;
 
-	if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) {
+	if (test_bit(I40E_HW_CAP_AQ_PHY_ACCESS, hw->caps)) {
 		status =
 		      i40e_aq_get_phy_register(hw,
 					       I40E_AQ_PHY_REG_ACCESS_EXTERNAL,
@@ -5238,14 +5199,14 @@ int i40e_aq_rx_ctl_read_register(struct i40e_hw *hw,
  **/
 u32 i40e_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr)
 {
-	bool use_register;
+	bool use_register = false;
 	int status = 0;
 	int retry = 5;
 	u32 val = 0;
 
-	use_register = (((hw->aq.api_maj_ver == 1) &&
-			(hw->aq.api_min_ver < 5)) ||
-			(hw->mac.type == I40E_MAC_X722));
+	if (i40e_is_aq_api_ver_lt(hw, 1, 5) || hw->mac.type == I40E_MAC_X722)
+		use_register = true;
+
 	if (!use_register) {
 do_retry:
 		status = i40e_aq_rx_ctl_read_register(hw, reg_addr, &val, NULL);
@@ -5300,13 +5261,13 @@ int i40e_aq_rx_ctl_write_register(struct i40e_hw *hw,
  **/
 void i40e_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val)
 {
-	bool use_register;
+	bool use_register = false;
 	int status = 0;
 	int retry = 5;
 
-	use_register = (((hw->aq.api_maj_ver == 1) &&
-			(hw->aq.api_min_ver < 5)) ||
-			(hw->mac.type == I40E_MAC_X722));
+	if (i40e_is_aq_api_ver_lt(hw, 1, 5) || hw->mac.type == I40E_MAC_X722)
+		use_register = true;
+
 	if (!use_register) {
 do_retry:
 		status = i40e_aq_rx_ctl_write_register(hw, reg_addr,
@@ -5334,16 +5295,17 @@ static void i40e_mdio_if_number_selection(struct i40e_hw *hw, bool set_mdio,
 					  u8 mdio_num,
 					  struct i40e_aqc_phy_register_access *cmd)
 {
-	if (set_mdio && cmd->phy_interface == I40E_AQ_PHY_REG_ACCESS_EXTERNAL) {
-		if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_EXTENDED)
-			cmd->cmd_flags |=
-				I40E_AQ_PHY_REG_ACCESS_SET_MDIO_IF_NUMBER |
-				((mdio_num <<
-				I40E_AQ_PHY_REG_ACCESS_MDIO_IF_NUMBER_SHIFT) &
-				I40E_AQ_PHY_REG_ACCESS_MDIO_IF_NUMBER_MASK);
-		else
-			i40e_debug(hw, I40E_DEBUG_PHY,
-				   "MDIO I/F number selection not supported by current FW version.\n");
+	if (!set_mdio ||
+	    cmd->phy_interface != I40E_AQ_PHY_REG_ACCESS_EXTERNAL)
+		return;
+
+	if (test_bit(I40E_HW_CAP_AQ_PHY_ACCESS_EXTENDED, hw->caps)) {
+		cmd->cmd_flags |=
+			I40E_AQ_PHY_REG_ACCESS_SET_MDIO_IF_NUMBER |
+			FIELD_PREP(I40E_AQ_PHY_REG_ACCESS_MDIO_IF_NUMBER_MASK,
+				   mdio_num);
+	} else {
+		i40e_debug(hw, I40E_DEBUG_PHY, "MDIO I/F number selection not supported by current FW version.\n");
 	}
 }
 
@@ -5928,9 +5890,8 @@ i40e_aq_add_cloud_filters_bb(struct i40e_hw *hw, u16 seid,
 		u16 tnl_type;
 		u32 ti;
 
-		tnl_type = (le16_to_cpu(filters[i].element.flags) &
-			   I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK) >>
-			   I40E_AQC_ADD_CLOUD_TNL_TYPE_SHIFT;
+		tnl_type = le16_get_bits(filters[i].element.flags,
+					 I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK);
 
 		/* Due to hardware eccentricities, the VNI for Geneve is shifted
 		 * one more byte further than normally used for Tenant ID in
@@ -6022,9 +5983,8 @@ i40e_aq_rem_cloud_filters_bb(struct i40e_hw *hw, u16 seid,
 		u16 tnl_type;
 		u32 ti;
 
-		tnl_type = (le16_to_cpu(filters[i].element.flags) &
-			   I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK) >>
-			   I40E_AQC_ADD_CLOUD_TNL_TYPE_SHIFT;
+		tnl_type = le16_get_bits(filters[i].element.flags,
+					 I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK);
 
 		/* Due to hardware eccentricities, the VNI for Geneve is shifted
 		 * one more byte further than normally used for Tenant ID in
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
index 68602fc375f6..9d88ed6105fd 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2013 - 2021 Intel Corporation. */
 
+#include <linux/bitfield.h>
+#include "i40e_adminq.h"
 #include "i40e_alloc.h"
 #include "i40e_dcb.h"
 #include "i40e_prototype.h"
@@ -20,8 +22,7 @@ int i40e_get_dcbx_status(struct i40e_hw *hw, u16 *status)
 		return -EINVAL;
 
 	reg = rd32(hw, I40E_PRTDCB_GENS);
-	*status = (u16)((reg & I40E_PRTDCB_GENS_DCBX_STATUS_MASK) >>
-			I40E_PRTDCB_GENS_DCBX_STATUS_SHIFT);
+	*status = FIELD_GET(I40E_PRTDCB_GENS_DCBX_STATUS_MASK, reg);
 
 	return 0;
 }
@@ -50,12 +51,9 @@ static void i40e_parse_ieee_etscfg_tlv(struct i40e_lldp_org_tlv *tlv,
 	 * |1bit | 1bit|3 bits|3bits|
 	 */
 	etscfg = &dcbcfg->etscfg;
-	etscfg->willing = (u8)((buf[offset] & I40E_IEEE_ETS_WILLING_MASK) >>
-			       I40E_IEEE_ETS_WILLING_SHIFT);
-	etscfg->cbs = (u8)((buf[offset] & I40E_IEEE_ETS_CBS_MASK) >>
-			   I40E_IEEE_ETS_CBS_SHIFT);
-	etscfg->maxtcs = (u8)((buf[offset] & I40E_IEEE_ETS_MAXTC_MASK) >>
-			      I40E_IEEE_ETS_MAXTC_SHIFT);
+	etscfg->willing = FIELD_GET(I40E_IEEE_ETS_WILLING_MASK, buf[offset]);
+	etscfg->cbs = FIELD_GET(I40E_IEEE_ETS_CBS_MASK, buf[offset]);
+	etscfg->maxtcs = FIELD_GET(I40E_IEEE_ETS_MAXTC_MASK, buf[offset]);
 
 	/* Move offset to Priority Assignment Table */
 	offset++;
@@ -69,11 +67,9 @@ static void i40e_parse_ieee_etscfg_tlv(struct i40e_lldp_org_tlv *tlv,
 	 *        -----------------------------------------
 	 */
 	for (i = 0; i < 4; i++) {
-		priority = (u8)((buf[offset] & I40E_IEEE_ETS_PRIO_1_MASK) >>
-				I40E_IEEE_ETS_PRIO_1_SHIFT);
-		etscfg->prioritytable[i * 2] =  priority;
-		priority = (u8)((buf[offset] & I40E_IEEE_ETS_PRIO_0_MASK) >>
-				I40E_IEEE_ETS_PRIO_0_SHIFT);
+		priority = FIELD_GET(I40E_IEEE_ETS_PRIO_1_MASK, buf[offset]);
+		etscfg->prioritytable[i * 2] = priority;
+		priority = FIELD_GET(I40E_IEEE_ETS_PRIO_0_MASK, buf[offset]);
 		etscfg->prioritytable[i * 2 + 1] = priority;
 		offset++;
 	}
@@ -124,12 +120,10 @@ static void i40e_parse_ieee_etsrec_tlv(struct i40e_lldp_org_tlv *tlv,
 	 *        -----------------------------------------
 	 */
 	for (i = 0; i < 4; i++) {
-		priority = (u8)((buf[offset] & I40E_IEEE_ETS_PRIO_1_MASK) >>
-				I40E_IEEE_ETS_PRIO_1_SHIFT);
-		dcbcfg->etsrec.prioritytable[i*2] =  priority;
-		priority = (u8)((buf[offset] & I40E_IEEE_ETS_PRIO_0_MASK) >>
-				I40E_IEEE_ETS_PRIO_0_SHIFT);
-		dcbcfg->etsrec.prioritytable[i*2 + 1] = priority;
+		priority = FIELD_GET(I40E_IEEE_ETS_PRIO_1_MASK, buf[offset]);
+		dcbcfg->etsrec.prioritytable[i * 2] = priority;
+		priority = FIELD_GET(I40E_IEEE_ETS_PRIO_0_MASK, buf[offset]);
+		dcbcfg->etsrec.prioritytable[(i * 2) + 1] = priority;
 		offset++;
 	}
 
@@ -170,12 +164,9 @@ static void i40e_parse_ieee_pfccfg_tlv(struct i40e_lldp_org_tlv *tlv,
 	 * -----------------------------------------
 	 * |1bit | 1bit|2 bits|4bits| 1 octet      |
 	 */
-	dcbcfg->pfc.willing = (u8)((buf[0] & I40E_IEEE_PFC_WILLING_MASK) >>
-				   I40E_IEEE_PFC_WILLING_SHIFT);
-	dcbcfg->pfc.mbc = (u8)((buf[0] & I40E_IEEE_PFC_MBC_MASK) >>
-			       I40E_IEEE_PFC_MBC_SHIFT);
-	dcbcfg->pfc.pfccap = (u8)((buf[0] & I40E_IEEE_PFC_CAP_MASK) >>
-				  I40E_IEEE_PFC_CAP_SHIFT);
+	dcbcfg->pfc.willing = FIELD_GET(I40E_IEEE_PFC_WILLING_MASK, buf[0]);
+	dcbcfg->pfc.mbc = FIELD_GET(I40E_IEEE_PFC_MBC_MASK, buf[0]);
+	dcbcfg->pfc.pfccap = FIELD_GET(I40E_IEEE_PFC_CAP_MASK, buf[0]);
 	dcbcfg->pfc.pfcenable = buf[1];
 }
 
@@ -196,8 +187,7 @@ static void i40e_parse_ieee_app_tlv(struct i40e_lldp_org_tlv *tlv,
 	u8 *buf;
 
 	typelength = ntohs(tlv->typelength);
-	length = (u16)((typelength & I40E_LLDP_TLV_LEN_MASK) >>
-		       I40E_LLDP_TLV_LEN_SHIFT);
+	length = FIELD_GET(I40E_LLDP_TLV_LEN_MASK, typelength);
 	buf = tlv->tlvinfo;
 
 	/* The App priority table starts 5 octets after TLV header */
@@ -215,12 +205,10 @@ static void i40e_parse_ieee_app_tlv(struct i40e_lldp_org_tlv *tlv,
 	 *        -----------------------------------------
 	 */
 	while (offset < length) {
-		dcbcfg->app[i].priority = (u8)((buf[offset] &
-						I40E_IEEE_APP_PRIO_MASK) >>
-					       I40E_IEEE_APP_PRIO_SHIFT);
-		dcbcfg->app[i].selector = (u8)((buf[offset] &
-						I40E_IEEE_APP_SEL_MASK) >>
-					       I40E_IEEE_APP_SEL_SHIFT);
+		dcbcfg->app[i].priority = FIELD_GET(I40E_IEEE_APP_PRIO_MASK,
+						    buf[offset]);
+		dcbcfg->app[i].selector = FIELD_GET(I40E_IEEE_APP_SEL_MASK,
+						    buf[offset]);
 		dcbcfg->app[i].protocolid = (buf[offset + 1] << 0x8) |
 					     buf[offset + 2];
 		/* Move to next app */
@@ -248,8 +236,7 @@ static void i40e_parse_ieee_tlv(struct i40e_lldp_org_tlv *tlv,
 	u8 subtype;
 
 	ouisubtype = ntohl(tlv->ouisubtype);
-	subtype = (u8)((ouisubtype & I40E_LLDP_TLV_SUBTYPE_MASK) >>
-		       I40E_LLDP_TLV_SUBTYPE_SHIFT);
+	subtype = FIELD_GET(I40E_LLDP_TLV_SUBTYPE_MASK, ouisubtype);
 	switch (subtype) {
 	case I40E_IEEE_SUBTYPE_ETS_CFG:
 		i40e_parse_ieee_etscfg_tlv(tlv, dcbcfg);
@@ -299,11 +286,9 @@ static void i40e_parse_cee_pgcfg_tlv(struct i40e_cee_feat_tlv *tlv,
 	 *        -----------------------------------------
 	 */
 	for (i = 0; i < 4; i++) {
-		priority = (u8)((buf[offset] & I40E_CEE_PGID_PRIO_1_MASK) >>
-				 I40E_CEE_PGID_PRIO_1_SHIFT);
-		etscfg->prioritytable[i * 2] =  priority;
-		priority = (u8)((buf[offset] & I40E_CEE_PGID_PRIO_0_MASK) >>
-				 I40E_CEE_PGID_PRIO_0_SHIFT);
+		priority = FIELD_GET(I40E_CEE_PGID_PRIO_1_MASK, buf[offset]);
+		etscfg->prioritytable[i * 2] = priority;
+		priority = FIELD_GET(I40E_CEE_PGID_PRIO_0_MASK, buf[offset]);
 		etscfg->prioritytable[i * 2 + 1] = priority;
 		offset++;
 	}
@@ -360,8 +345,7 @@ static void i40e_parse_cee_app_tlv(struct i40e_cee_feat_tlv *tlv,
 	u8 i;
 
 	typelength = ntohs(tlv->hdr.typelen);
-	length = (u16)((typelength & I40E_LLDP_TLV_LEN_MASK) >>
-		       I40E_LLDP_TLV_LEN_SHIFT);
+	length = FIELD_GET(I40E_LLDP_TLV_LEN_MASK, typelength);
 
 	dcbcfg->numapps = length / sizeof(*app);
 
@@ -417,15 +401,13 @@ static void i40e_parse_cee_tlv(struct i40e_lldp_org_tlv *tlv,
 	u32 ouisubtype;
 
 	ouisubtype = ntohl(tlv->ouisubtype);
-	subtype = (u8)((ouisubtype & I40E_LLDP_TLV_SUBTYPE_MASK) >>
-		       I40E_LLDP_TLV_SUBTYPE_SHIFT);
+	subtype = FIELD_GET(I40E_LLDP_TLV_SUBTYPE_MASK, ouisubtype);
 	/* Return if not CEE DCBX */
 	if (subtype != I40E_CEE_DCBX_TYPE)
 		return;
 
 	typelength = ntohs(tlv->typelength);
-	tlvlen = (u16)((typelength & I40E_LLDP_TLV_LEN_MASK) >>
-			I40E_LLDP_TLV_LEN_SHIFT);
+	tlvlen = FIELD_GET(I40E_LLDP_TLV_LEN_MASK, typelength);
 	len = sizeof(tlv->typelength) + sizeof(ouisubtype) +
 	      sizeof(struct i40e_cee_ctrl_tlv);
 	/* Return if no CEE DCBX Feature TLVs */
@@ -435,11 +417,8 @@ static void i40e_parse_cee_tlv(struct i40e_lldp_org_tlv *tlv,
 	sub_tlv = (struct i40e_cee_feat_tlv *)((char *)tlv + len);
 	while (feat_tlv_count < I40E_CEE_MAX_FEAT_TYPE) {
 		typelength = ntohs(sub_tlv->hdr.typelen);
-		sublen = (u16)((typelength &
-				I40E_LLDP_TLV_LEN_MASK) >>
-				I40E_LLDP_TLV_LEN_SHIFT);
-		subtype = (u8)((typelength & I40E_LLDP_TLV_TYPE_MASK) >>
-				I40E_LLDP_TLV_TYPE_SHIFT);
+		sublen = FIELD_GET(I40E_LLDP_TLV_LEN_MASK, typelength);
+		subtype = FIELD_GET(I40E_LLDP_TLV_TYPE_MASK, typelength);
 		switch (subtype) {
 		case I40E_CEE_SUBTYPE_PG_CFG:
 			i40e_parse_cee_pgcfg_tlv(sub_tlv, dcbcfg);
@@ -476,8 +455,7 @@ static void i40e_parse_org_tlv(struct i40e_lldp_org_tlv *tlv,
 	u32 oui;
 
 	ouisubtype = ntohl(tlv->ouisubtype);
-	oui = (u32)((ouisubtype & I40E_LLDP_TLV_OUI_MASK) >>
-		    I40E_LLDP_TLV_OUI_SHIFT);
+	oui = FIELD_GET(I40E_LLDP_TLV_OUI_MASK, ouisubtype);
 	switch (oui) {
 	case I40E_IEEE_8021QAZ_OUI:
 		i40e_parse_ieee_tlv(tlv, dcbcfg);
@@ -515,10 +493,8 @@ int i40e_lldp_to_dcb_config(u8 *lldpmib,
 	tlv = (struct i40e_lldp_org_tlv *)lldpmib;
 	while (1) {
 		typelength = ntohs(tlv->typelength);
-		type = (u16)((typelength & I40E_LLDP_TLV_TYPE_MASK) >>
-			     I40E_LLDP_TLV_TYPE_SHIFT);
-		length = (u16)((typelength & I40E_LLDP_TLV_LEN_MASK) >>
-			       I40E_LLDP_TLV_LEN_SHIFT);
+		type = FIELD_GET(I40E_LLDP_TLV_TYPE_MASK, typelength);
+		length = FIELD_GET(I40E_LLDP_TLV_LEN_MASK, typelength);
 		offset += sizeof(typelength) + length;
 
 		/* END TLV or beyond LLDPDU size */
@@ -592,7 +568,7 @@ static void i40e_cee_to_dcb_v1_config(
 {
 	u16 status, tlv_status = le16_to_cpu(cee_cfg->tlv_status);
 	u16 app_prio = le16_to_cpu(cee_cfg->oper_app_prio);
-	u8 i, tc, err;
+	u8 i, err;
 
 	/* CEE PG data to ETS config */
 	dcbcfg->etscfg.maxtcs = cee_cfg->oper_num_tc;
@@ -601,13 +577,13 @@ static void i40e_cee_to_dcb_v1_config(
 	 * from those in the CEE Priority Group sub-TLV.
 	 */
 	for (i = 0; i < 4; i++) {
-		tc = (u8)((cee_cfg->oper_prio_tc[i] &
-			 I40E_CEE_PGID_PRIO_0_MASK) >>
-			 I40E_CEE_PGID_PRIO_0_SHIFT);
-		dcbcfg->etscfg.prioritytable[i * 2] =  tc;
-		tc = (u8)((cee_cfg->oper_prio_tc[i] &
-			 I40E_CEE_PGID_PRIO_1_MASK) >>
-			 I40E_CEE_PGID_PRIO_1_SHIFT);
+		u8 tc;
+
+		tc = FIELD_GET(I40E_CEE_PGID_PRIO_0_MASK,
+			       cee_cfg->oper_prio_tc[i]);
+		dcbcfg->etscfg.prioritytable[i * 2] = tc;
+		tc = FIELD_GET(I40E_CEE_PGID_PRIO_1_MASK,
+			       cee_cfg->oper_prio_tc[i]);
 		dcbcfg->etscfg.prioritytable[i*2 + 1] = tc;
 	}
 
@@ -629,8 +605,7 @@ static void i40e_cee_to_dcb_v1_config(
 	dcbcfg->pfc.pfcenable = cee_cfg->oper_pfc_en;
 	dcbcfg->pfc.pfccap = I40E_MAX_TRAFFIC_CLASS;
 
-	status = (tlv_status & I40E_AQC_CEE_APP_STATUS_MASK) >>
-		  I40E_AQC_CEE_APP_STATUS_SHIFT;
+	status = FIELD_GET(I40E_AQC_CEE_APP_STATUS_MASK, tlv_status);
 	err = (status & I40E_TLV_STATUS_ERR) ? 1 : 0;
 	/* Add APPs if Error is False */
 	if (!err) {
@@ -639,22 +614,19 @@ static void i40e_cee_to_dcb_v1_config(
 
 		/* FCoE APP */
 		dcbcfg->app[0].priority =
-			(app_prio & I40E_AQC_CEE_APP_FCOE_MASK) >>
-			 I40E_AQC_CEE_APP_FCOE_SHIFT;
+			FIELD_GET(I40E_AQC_CEE_APP_FCOE_MASK, app_prio);
 		dcbcfg->app[0].selector = I40E_APP_SEL_ETHTYPE;
 		dcbcfg->app[0].protocolid = I40E_APP_PROTOID_FCOE;
 
 		/* iSCSI APP */
 		dcbcfg->app[1].priority =
-			(app_prio & I40E_AQC_CEE_APP_ISCSI_MASK) >>
-			 I40E_AQC_CEE_APP_ISCSI_SHIFT;
+			FIELD_GET(I40E_AQC_CEE_APP_ISCSI_MASK, app_prio);
 		dcbcfg->app[1].selector = I40E_APP_SEL_TCPIP;
 		dcbcfg->app[1].protocolid = I40E_APP_PROTOID_ISCSI;
 
 		/* FIP APP */
 		dcbcfg->app[2].priority =
-			(app_prio & I40E_AQC_CEE_APP_FIP_MASK) >>
-			 I40E_AQC_CEE_APP_FIP_SHIFT;
+			FIELD_GET(I40E_AQC_CEE_APP_FIP_MASK, app_prio);
 		dcbcfg->app[2].selector = I40E_APP_SEL_ETHTYPE;
 		dcbcfg->app[2].protocolid = I40E_APP_PROTOID_FIP;
 	}
@@ -673,7 +645,7 @@ static void i40e_cee_to_dcb_config(
 {
 	u32 status, tlv_status = le32_to_cpu(cee_cfg->tlv_status);
 	u16 app_prio = le16_to_cpu(cee_cfg->oper_app_prio);
-	u8 i, tc, err, sync, oper;
+	u8 i, err, sync, oper;
 
 	/* CEE PG data to ETS config */
 	dcbcfg->etscfg.maxtcs = cee_cfg->oper_num_tc;
@@ -682,13 +654,13 @@ static void i40e_cee_to_dcb_config(
 	 * from those in the CEE Priority Group sub-TLV.
 	 */
 	for (i = 0; i < 4; i++) {
-		tc = (u8)((cee_cfg->oper_prio_tc[i] &
-			 I40E_CEE_PGID_PRIO_0_MASK) >>
-			 I40E_CEE_PGID_PRIO_0_SHIFT);
-		dcbcfg->etscfg.prioritytable[i * 2] =  tc;
-		tc = (u8)((cee_cfg->oper_prio_tc[i] &
-			 I40E_CEE_PGID_PRIO_1_MASK) >>
-			 I40E_CEE_PGID_PRIO_1_SHIFT);
+		u8 tc;
+
+		tc = FIELD_GET(I40E_CEE_PGID_PRIO_0_MASK,
+			       cee_cfg->oper_prio_tc[i]);
+		dcbcfg->etscfg.prioritytable[i * 2] = tc;
+		tc = FIELD_GET(I40E_CEE_PGID_PRIO_1_MASK,
+			       cee_cfg->oper_prio_tc[i]);
 		dcbcfg->etscfg.prioritytable[i * 2 + 1] = tc;
 	}
 
@@ -711,8 +683,7 @@ static void i40e_cee_to_dcb_config(
 	dcbcfg->pfc.pfccap = I40E_MAX_TRAFFIC_CLASS;
 
 	i = 0;
-	status = (tlv_status & I40E_AQC_CEE_FCOE_STATUS_MASK) >>
-		  I40E_AQC_CEE_FCOE_STATUS_SHIFT;
+	status = FIELD_GET(I40E_AQC_CEE_FCOE_STATUS_MASK, tlv_status);
 	err = (status & I40E_TLV_STATUS_ERR) ? 1 : 0;
 	sync = (status & I40E_TLV_STATUS_SYNC) ? 1 : 0;
 	oper = (status & I40E_TLV_STATUS_OPER) ? 1 : 0;
@@ -720,15 +691,13 @@ static void i40e_cee_to_dcb_config(
 	if (!err && sync && oper) {
 		/* FCoE APP */
 		dcbcfg->app[i].priority =
-			(app_prio & I40E_AQC_CEE_APP_FCOE_MASK) >>
-			 I40E_AQC_CEE_APP_FCOE_SHIFT;
+			FIELD_GET(I40E_AQC_CEE_APP_FCOE_MASK, app_prio);
 		dcbcfg->app[i].selector = I40E_APP_SEL_ETHTYPE;
 		dcbcfg->app[i].protocolid = I40E_APP_PROTOID_FCOE;
 		i++;
 	}
 
-	status = (tlv_status & I40E_AQC_CEE_ISCSI_STATUS_MASK) >>
-		  I40E_AQC_CEE_ISCSI_STATUS_SHIFT;
+	status = FIELD_GET(I40E_AQC_CEE_ISCSI_STATUS_MASK, tlv_status);
 	err = (status & I40E_TLV_STATUS_ERR) ? 1 : 0;
 	sync = (status & I40E_TLV_STATUS_SYNC) ? 1 : 0;
 	oper = (status & I40E_TLV_STATUS_OPER) ? 1 : 0;
@@ -736,15 +705,13 @@ static void i40e_cee_to_dcb_config(
 	if (!err && sync && oper) {
 		/* iSCSI APP */
 		dcbcfg->app[i].priority =
-			(app_prio & I40E_AQC_CEE_APP_ISCSI_MASK) >>
-			 I40E_AQC_CEE_APP_ISCSI_SHIFT;
+			FIELD_GET(I40E_AQC_CEE_APP_ISCSI_MASK, app_prio);
 		dcbcfg->app[i].selector = I40E_APP_SEL_TCPIP;
 		dcbcfg->app[i].protocolid = I40E_APP_PROTOID_ISCSI;
 		i++;
 	}
 
-	status = (tlv_status & I40E_AQC_CEE_FIP_STATUS_MASK) >>
-		  I40E_AQC_CEE_FIP_STATUS_SHIFT;
+	status = FIELD_GET(I40E_AQC_CEE_FIP_STATUS_MASK, tlv_status);
 	err = (status & I40E_TLV_STATUS_ERR) ? 1 : 0;
 	sync = (status & I40E_TLV_STATUS_SYNC) ? 1 : 0;
 	oper = (status & I40E_TLV_STATUS_OPER) ? 1 : 0;
@@ -752,8 +719,7 @@ static void i40e_cee_to_dcb_config(
 	if (!err && sync && oper) {
 		/* FIP APP */
 		dcbcfg->app[i].priority =
-			(app_prio & I40E_AQC_CEE_APP_FIP_MASK) >>
-			 I40E_AQC_CEE_APP_FIP_SHIFT;
+			FIELD_GET(I40E_AQC_CEE_APP_FIP_MASK, app_prio);
 		dcbcfg->app[i].selector = I40E_APP_SEL_ETHTYPE;
 		dcbcfg->app[i].protocolid = I40E_APP_PROTOID_FIP;
 		i++;
@@ -804,14 +770,11 @@ int i40e_get_dcb_config(struct i40e_hw *hw)
 	int ret = 0;
 
 	/* If Firmware version < v4.33 on X710/XL710, IEEE only */
-	if ((hw->mac.type == I40E_MAC_XL710) &&
-	    (((hw->aq.fw_maj_ver == 4) && (hw->aq.fw_min_ver < 33)) ||
-	      (hw->aq.fw_maj_ver < 4)))
+	if (hw->mac.type == I40E_MAC_XL710 && i40e_is_fw_ver_lt(hw, 4, 33))
 		return i40e_get_ieee_dcb_config(hw);
 
 	/* If Firmware version == v4.33 on X710/XL710, use old CEE struct */
-	if ((hw->mac.type == I40E_MAC_XL710) &&
-	    ((hw->aq.fw_maj_ver == 4) && (hw->aq.fw_min_ver == 33))) {
+	if (hw->mac.type == I40E_MAC_XL710 && i40e_is_fw_ver_eq(hw, 4, 33)) {
 		ret = i40e_aq_get_cee_dcb_config(hw, &cee_v1_cfg,
 						 sizeof(cee_v1_cfg), NULL);
 		if (!ret) {
@@ -877,7 +840,7 @@ int i40e_init_dcb(struct i40e_hw *hw, bool enable_mib_change)
 		return -EOPNOTSUPP;
 
 	/* Read LLDP NVM area */
-	if (hw->flags & I40E_HW_FLAG_FW_LLDP_PERSISTENT) {
+	if (test_bit(I40E_HW_CAP_FW_LLDP_PERSISTENT, hw->caps)) {
 		u8 offset = 0;
 
 		if (hw->mac.type == I40E_MAC_XL710)
@@ -1189,7 +1152,7 @@ static void i40e_add_ieee_app_pri_tlv(struct i40e_lldp_org_tlv *tlv,
 		selector = dcbcfg->app[i].selector & 0x7;
 		buf[offset] = (priority << I40E_IEEE_APP_PRIO_SHIFT) | selector;
 		buf[offset + 1] = (dcbcfg->app[i].protocolid >> 0x8) & 0xFF;
-		buf[offset + 2] =  dcbcfg->app[i].protocolid & 0xFF;
+		buf[offset + 2] = dcbcfg->app[i].protocolid & 0xFF;
 		/* Move to next app */
 		offset += 3;
 		i++;
@@ -1285,8 +1248,7 @@ int i40e_dcb_config_to_lldp(u8 *lldpmib, u16 *miblen,
 	do {
 		i40e_add_dcb_tlv(tlv, dcbcfg, tlvid++);
 		typelength = ntohs(tlv->typelength);
-		length = (u16)((typelength & I40E_LLDP_TLV_LEN_MASK) >>
-				I40E_LLDP_TLV_LEN_SHIFT);
+		length = FIELD_GET(I40E_LLDP_TLV_LEN_MASK, typelength);
 		if (length)
 			offset += length + I40E_IEEE_TLV_HEADER_LENGTH;
 		/* END TLV or beyond LLDPDU size */
@@ -1321,20 +1283,16 @@ void i40e_dcb_hw_rx_fifo_config(struct i40e_hw *hw,
 	u32 reg = rd32(hw, I40E_PRTDCB_RETSC);
 
 	reg &= ~I40E_PRTDCB_RETSC_ETS_MODE_MASK;
-	reg |= ((u32)ets_mode << I40E_PRTDCB_RETSC_ETS_MODE_SHIFT) &
-		I40E_PRTDCB_RETSC_ETS_MODE_MASK;
+	reg |= FIELD_PREP(I40E_PRTDCB_RETSC_ETS_MODE_MASK, ets_mode);
 
 	reg &= ~I40E_PRTDCB_RETSC_NON_ETS_MODE_MASK;
-	reg |= ((u32)non_ets_mode << I40E_PRTDCB_RETSC_NON_ETS_MODE_SHIFT) &
-		I40E_PRTDCB_RETSC_NON_ETS_MODE_MASK;
+	reg |= FIELD_PREP(I40E_PRTDCB_RETSC_NON_ETS_MODE_MASK, non_ets_mode);
 
 	reg &= ~I40E_PRTDCB_RETSC_ETS_MAX_EXP_MASK;
-	reg |= (max_exponent << I40E_PRTDCB_RETSC_ETS_MAX_EXP_SHIFT) &
-		I40E_PRTDCB_RETSC_ETS_MAX_EXP_MASK;
+	reg |= FIELD_PREP(I40E_PRTDCB_RETSC_ETS_MAX_EXP_MASK, max_exponent);
 
 	reg &= ~I40E_PRTDCB_RETSC_LLTC_MASK;
-	reg |= (lltc_map << I40E_PRTDCB_RETSC_LLTC_SHIFT) &
-		I40E_PRTDCB_RETSC_LLTC_MASK;
+	reg |= FIELD_PREP(I40E_PRTDCB_RETSC_LLTC_MASK, lltc_map);
 	wr32(hw, I40E_PRTDCB_RETSC, reg);
 }
 
@@ -1389,14 +1347,12 @@ void i40e_dcb_hw_rx_cmd_monitor_config(struct i40e_hw *hw,
 	 */
 	reg = rd32(hw, I40E_PRT_SWR_PM_THR);
 	reg &= ~I40E_PRT_SWR_PM_THR_THRESHOLD_MASK;
-	reg |= (threshold << I40E_PRT_SWR_PM_THR_THRESHOLD_SHIFT) &
-		I40E_PRT_SWR_PM_THR_THRESHOLD_MASK;
+	reg |= FIELD_PREP(I40E_PRT_SWR_PM_THR_THRESHOLD_MASK, threshold);
 	wr32(hw, I40E_PRT_SWR_PM_THR, reg);
 
 	reg = rd32(hw, I40E_PRTDCB_RPPMC);
 	reg &= ~I40E_PRTDCB_RPPMC_RX_FIFO_SIZE_MASK;
-	reg |= (fifo_size << I40E_PRTDCB_RPPMC_RX_FIFO_SIZE_SHIFT) &
-		I40E_PRTDCB_RPPMC_RX_FIFO_SIZE_MASK;
+	reg |= FIELD_PREP(I40E_PRTDCB_RPPMC_RX_FIFO_SIZE_MASK, fifo_size);
 	wr32(hw, I40E_PRTDCB_RPPMC, reg);
 }
 
@@ -1438,19 +1394,17 @@ void i40e_dcb_hw_pfc_config(struct i40e_hw *hw,
 		reg &= ~I40E_PRTDCB_MFLCN_RFCE_MASK;
 		reg &= ~I40E_PRTDCB_MFLCN_RPFCE_MASK;
 		if (pfc_en) {
-			reg |= BIT(I40E_PRTDCB_MFLCN_RPFCM_SHIFT) &
-				I40E_PRTDCB_MFLCN_RPFCM_MASK;
-			reg |= ((u32)pfc_en << I40E_PRTDCB_MFLCN_RPFCE_SHIFT) &
-				I40E_PRTDCB_MFLCN_RPFCE_MASK;
+			reg |= FIELD_PREP(I40E_PRTDCB_MFLCN_RPFCM_MASK, 1);
+			reg |= FIELD_PREP(I40E_PRTDCB_MFLCN_RPFCE_MASK,
+					  pfc_en);
 		}
 		wr32(hw, I40E_PRTDCB_MFLCN, reg);
 
 		reg = rd32(hw, I40E_PRTDCB_FCCFG);
 		reg &= ~I40E_PRTDCB_FCCFG_TFCE_MASK;
 		if (pfc_en)
-			reg |= (I40E_DCB_PFC_ENABLED <<
-				I40E_PRTDCB_FCCFG_TFCE_SHIFT) &
-				I40E_PRTDCB_FCCFG_TFCE_MASK;
+			reg |= FIELD_PREP(I40E_PRTDCB_FCCFG_TFCE_MASK,
+					  I40E_DCB_PFC_ENABLED);
 		wr32(hw, I40E_PRTDCB_FCCFG, reg);
 
 		/* FCTTV and FCRTV to be set by default */
@@ -1468,25 +1422,22 @@ void i40e_dcb_hw_pfc_config(struct i40e_hw *hw,
 
 		reg = rd32(hw, I40E_PRTMAC_HSEC_CTL_RX_PAUSE_ENABLE);
 		reg &= ~I40E_PRTMAC_HSEC_CTL_RX_PAUSE_ENABLE_MASK;
-		reg |= ((u32)pfc_en <<
-			   I40E_PRTMAC_HSEC_CTL_RX_PAUSE_ENABLE_SHIFT) &
-			I40E_PRTMAC_HSEC_CTL_RX_PAUSE_ENABLE_MASK;
+		reg |= FIELD_PREP(I40E_PRTMAC_HSEC_CTL_RX_PAUSE_ENABLE_MASK,
+				  pfc_en);
 		wr32(hw, I40E_PRTMAC_HSEC_CTL_RX_PAUSE_ENABLE, reg);
 
 		reg = rd32(hw, I40E_PRTMAC_HSEC_CTL_TX_PAUSE_ENABLE);
 		reg &= ~I40E_PRTMAC_HSEC_CTL_TX_PAUSE_ENABLE_MASK;
-		reg |= ((u32)pfc_en <<
-			   I40E_PRTMAC_HSEC_CTL_TX_PAUSE_ENABLE_SHIFT) &
-			I40E_PRTMAC_HSEC_CTL_TX_PAUSE_ENABLE_MASK;
+		reg |= FIELD_PREP(I40E_PRTMAC_HSEC_CTL_TX_PAUSE_ENABLE_MASK,
+				  pfc_en);
 		wr32(hw, I40E_PRTMAC_HSEC_CTL_TX_PAUSE_ENABLE, reg);
 
 		for (i = 0; i < I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_MAX_INDEX; i++) {
 			reg = rd32(hw, I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER(i));
 			reg &= ~I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_MASK;
 			if (pfc_en) {
-				reg |= ((u32)refresh_time <<
-					I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_SHIFT) &
-					I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_MASK;
+				reg |= FIELD_PREP(I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_MASK,
+						  refresh_time);
 			}
 			wr32(hw, I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER(i), reg);
 		}
@@ -1498,14 +1449,12 @@ void i40e_dcb_hw_pfc_config(struct i40e_hw *hw,
 
 	reg = rd32(hw, I40E_PRTDCB_TC2PFC);
 	reg &= ~I40E_PRTDCB_TC2PFC_TC2PFC_MASK;
-	reg |= ((u32)tc2pfc << I40E_PRTDCB_TC2PFC_TC2PFC_SHIFT) &
-		I40E_PRTDCB_TC2PFC_TC2PFC_MASK;
+	reg |= FIELD_PREP(I40E_PRTDCB_TC2PFC_TC2PFC_MASK, tc2pfc);
 	wr32(hw, I40E_PRTDCB_TC2PFC, reg);
 
 	reg = rd32(hw, I40E_PRTDCB_RUP);
 	reg &= ~I40E_PRTDCB_RUP_NOVLANUP_MASK;
-	reg |= ((u32)first_pfc_prio << I40E_PRTDCB_RUP_NOVLANUP_SHIFT) &
-		 I40E_PRTDCB_RUP_NOVLANUP_MASK;
+	reg |= FIELD_PREP(I40E_PRTDCB_RUP_NOVLANUP_MASK, first_pfc_prio);
 	wr32(hw, I40E_PRTDCB_RUP, reg);
 
 	reg = rd32(hw, I40E_PRTDCB_TDPMC);
@@ -1537,8 +1486,7 @@ void i40e_dcb_hw_set_num_tc(struct i40e_hw *hw, u8 num_tc)
 	u32 reg = rd32(hw, I40E_PRTDCB_GENC);
 
 	reg &= ~I40E_PRTDCB_GENC_NUMTC_MASK;
-	reg |= ((u32)num_tc << I40E_PRTDCB_GENC_NUMTC_SHIFT) &
-		I40E_PRTDCB_GENC_NUMTC_MASK;
+	reg |= FIELD_PREP(I40E_PRTDCB_GENC_NUMTC_MASK, num_tc);
 	wr32(hw, I40E_PRTDCB_GENC, reg);
 }
 
@@ -1552,8 +1500,7 @@ u8 i40e_dcb_hw_get_num_tc(struct i40e_hw *hw)
 {
 	u32 reg = rd32(hw, I40E_PRTDCB_GENC);
 
-	return (u8)((reg & I40E_PRTDCB_GENC_NUMTC_MASK) >>
-		I40E_PRTDCB_GENC_NUMTC_SHIFT);
+	return FIELD_GET(I40E_PRTDCB_GENC_NUMTC_MASK, reg);
 }
 
 /**
@@ -1577,12 +1524,12 @@ void i40e_dcb_hw_rx_ets_bw_config(struct i40e_hw *hw, u8 *bw_share,
 		reg &= ~(I40E_PRTDCB_RETSTCC_BWSHARE_MASK     |
 			 I40E_PRTDCB_RETSTCC_UPINTC_MODE_MASK |
 			 I40E_PRTDCB_RETSTCC_ETSTC_SHIFT);
-		reg |= ((u32)bw_share[i] << I40E_PRTDCB_RETSTCC_BWSHARE_SHIFT) &
-			 I40E_PRTDCB_RETSTCC_BWSHARE_MASK;
-		reg |= ((u32)mode[i] << I40E_PRTDCB_RETSTCC_UPINTC_MODE_SHIFT) &
-			 I40E_PRTDCB_RETSTCC_UPINTC_MODE_MASK;
-		reg |= ((u32)prio_type[i] << I40E_PRTDCB_RETSTCC_ETSTC_SHIFT) &
-			 I40E_PRTDCB_RETSTCC_ETSTC_MASK;
+		reg |= FIELD_PREP(I40E_PRTDCB_RETSTCC_BWSHARE_MASK,
+				  bw_share[i]);
+		reg |= FIELD_PREP(I40E_PRTDCB_RETSTCC_UPINTC_MODE_MASK,
+				  mode[i]);
+		reg |= FIELD_PREP(I40E_PRTDCB_RETSTCC_ETSTC_MASK,
+				  prio_type[i]);
 		wr32(hw, I40E_PRTDCB_RETSTCC(i), reg);
 	}
 }
@@ -1722,8 +1669,7 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw,
 	if (new_val < old_val) {
 		reg = rd32(hw, I40E_PRTRPB_SLW);
 		reg &= ~I40E_PRTRPB_SLW_SLW_MASK;
-		reg |= (new_val << I40E_PRTRPB_SLW_SLW_SHIFT) &
-			I40E_PRTRPB_SLW_SLW_MASK;
+		reg |= FIELD_PREP(I40E_PRTRPB_SLW_SLW_MASK, new_val);
 		wr32(hw, I40E_PRTRPB_SLW, reg);
 	}
 
@@ -1736,8 +1682,8 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw,
 		if (new_val < old_val) {
 			reg = rd32(hw, I40E_PRTRPB_SLT(i));
 			reg &= ~I40E_PRTRPB_SLT_SLT_TCN_MASK;
-			reg |= (new_val << I40E_PRTRPB_SLT_SLT_TCN_SHIFT) &
-				I40E_PRTRPB_SLT_SLT_TCN_MASK;
+			reg |= FIELD_PREP(I40E_PRTRPB_SLT_SLT_TCN_MASK,
+					  new_val);
 			wr32(hw, I40E_PRTRPB_SLT(i), reg);
 		}
 
@@ -1746,8 +1692,8 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw,
 		if (new_val < old_val) {
 			reg = rd32(hw, I40E_PRTRPB_DLW(i));
 			reg &= ~I40E_PRTRPB_DLW_DLW_TCN_MASK;
-			reg |= (new_val << I40E_PRTRPB_DLW_DLW_TCN_SHIFT) &
-				I40E_PRTRPB_DLW_DLW_TCN_MASK;
+			reg |= FIELD_PREP(I40E_PRTRPB_DLW_DLW_TCN_MASK,
+					  new_val);
 			wr32(hw, I40E_PRTRPB_DLW(i), reg);
 		}
 	}
@@ -1758,8 +1704,7 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw,
 	if (new_val < old_val) {
 		reg = rd32(hw, I40E_PRTRPB_SHW);
 		reg &= ~I40E_PRTRPB_SHW_SHW_MASK;
-		reg |= (new_val << I40E_PRTRPB_SHW_SHW_SHIFT) &
-			I40E_PRTRPB_SHW_SHW_MASK;
+		reg |= FIELD_PREP(I40E_PRTRPB_SHW_SHW_MASK, new_val);
 		wr32(hw, I40E_PRTRPB_SHW, reg);
 	}
 
@@ -1772,8 +1717,8 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw,
 		if (new_val < old_val) {
 			reg = rd32(hw, I40E_PRTRPB_SHT(i));
 			reg &= ~I40E_PRTRPB_SHT_SHT_TCN_MASK;
-			reg |= (new_val << I40E_PRTRPB_SHT_SHT_TCN_SHIFT) &
-				I40E_PRTRPB_SHT_SHT_TCN_MASK;
+			reg |= FIELD_PREP(I40E_PRTRPB_SHT_SHT_TCN_MASK,
+					  new_val);
 			wr32(hw, I40E_PRTRPB_SHT(i), reg);
 		}
 
@@ -1782,8 +1727,8 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw,
 		if (new_val < old_val) {
 			reg = rd32(hw, I40E_PRTRPB_DHW(i));
 			reg &= ~I40E_PRTRPB_DHW_DHW_TCN_MASK;
-			reg |= (new_val << I40E_PRTRPB_DHW_DHW_TCN_SHIFT) &
-				I40E_PRTRPB_DHW_DHW_TCN_MASK;
+			reg |= FIELD_PREP(I40E_PRTRPB_DHW_DHW_TCN_MASK,
+					  new_val);
 			wr32(hw, I40E_PRTRPB_DHW(i), reg);
 		}
 	}
@@ -1793,8 +1738,7 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw,
 		new_val = new_pb_cfg->tc_pool_size[i];
 		reg = rd32(hw, I40E_PRTRPB_DPS(i));
 		reg &= ~I40E_PRTRPB_DPS_DPS_TCN_MASK;
-		reg |= (new_val << I40E_PRTRPB_DPS_DPS_TCN_SHIFT) &
-			I40E_PRTRPB_DPS_DPS_TCN_MASK;
+		reg |= FIELD_PREP(I40E_PRTRPB_DPS_DPS_TCN_MASK, new_val);
 		wr32(hw, I40E_PRTRPB_DPS(i), reg);
 	}
 
@@ -1802,8 +1746,7 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw,
 	new_val = new_pb_cfg->shared_pool_size;
 	reg = rd32(hw, I40E_PRTRPB_SPS);
 	reg &= ~I40E_PRTRPB_SPS_SPS_MASK;
-	reg |= (new_val << I40E_PRTRPB_SPS_SPS_SHIFT) &
-		I40E_PRTRPB_SPS_SPS_MASK;
+	reg |= FIELD_PREP(I40E_PRTRPB_SPS_SPS_MASK, new_val);
 	wr32(hw, I40E_PRTRPB_SPS, reg);
 
 	/* Program the shared pool low water mark per port if increasing */
@@ -1812,8 +1755,7 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw,
 	if (new_val > old_val) {
 		reg = rd32(hw, I40E_PRTRPB_SLW);
 		reg &= ~I40E_PRTRPB_SLW_SLW_MASK;
-		reg |= (new_val << I40E_PRTRPB_SLW_SLW_SHIFT) &
-			I40E_PRTRPB_SLW_SLW_MASK;
+		reg |= FIELD_PREP(I40E_PRTRPB_SLW_SLW_MASK, new_val);
 		wr32(hw, I40E_PRTRPB_SLW, reg);
 	}
 
@@ -1826,8 +1768,8 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw,
 		if (new_val > old_val) {
 			reg = rd32(hw, I40E_PRTRPB_SLT(i));
 			reg &= ~I40E_PRTRPB_SLT_SLT_TCN_MASK;
-			reg |= (new_val << I40E_PRTRPB_SLT_SLT_TCN_SHIFT) &
-				I40E_PRTRPB_SLT_SLT_TCN_MASK;
+			reg |= FIELD_PREP(I40E_PRTRPB_SLT_SLT_TCN_MASK,
+					  new_val);
 			wr32(hw, I40E_PRTRPB_SLT(i), reg);
 		}
 
@@ -1836,8 +1778,8 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw,
 		if (new_val > old_val) {
 			reg = rd32(hw, I40E_PRTRPB_DLW(i));
 			reg &= ~I40E_PRTRPB_DLW_DLW_TCN_MASK;
-			reg |= (new_val << I40E_PRTRPB_DLW_DLW_TCN_SHIFT) &
-				I40E_PRTRPB_DLW_DLW_TCN_MASK;
+			reg |= FIELD_PREP(I40E_PRTRPB_DLW_DLW_TCN_MASK,
+					  new_val);
 			wr32(hw, I40E_PRTRPB_DLW(i), reg);
 		}
 	}
@@ -1848,8 +1790,7 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw,
 	if (new_val > old_val) {
 		reg = rd32(hw, I40E_PRTRPB_SHW);
 		reg &= ~I40E_PRTRPB_SHW_SHW_MASK;
-		reg |= (new_val << I40E_PRTRPB_SHW_SHW_SHIFT) &
-			I40E_PRTRPB_SHW_SHW_MASK;
+		reg |= FIELD_PREP(I40E_PRTRPB_SHW_SHW_MASK, new_val);
 		wr32(hw, I40E_PRTRPB_SHW, reg);
 	}
 
@@ -1862,8 +1803,8 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw,
 		if (new_val > old_val) {
 			reg = rd32(hw, I40E_PRTRPB_SHT(i));
 			reg &= ~I40E_PRTRPB_SHT_SHT_TCN_MASK;
-			reg |= (new_val << I40E_PRTRPB_SHT_SHT_TCN_SHIFT) &
-				I40E_PRTRPB_SHT_SHT_TCN_MASK;
+			reg |= FIELD_PREP(I40E_PRTRPB_SHT_SHT_TCN_MASK,
+					  new_val);
 			wr32(hw, I40E_PRTRPB_SHT(i), reg);
 		}
 
@@ -1872,8 +1813,8 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw,
 		if (new_val > old_val) {
 			reg = rd32(hw, I40E_PRTRPB_DHW(i));
 			reg &= ~I40E_PRTRPB_DHW_DHW_TCN_MASK;
-			reg |= (new_val << I40E_PRTRPB_DHW_DHW_TCN_SHIFT) &
-				I40E_PRTRPB_DHW_DHW_TCN_MASK;
+			reg |= FIELD_PREP(I40E_PRTRPB_DHW_DHW_TCN_MASK,
+					  new_val);
 			wr32(hw, I40E_PRTRPB_DHW(i), reg);
 		}
 	}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c b/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c
index 077a95dad32c..b96a92187ab3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c
@@ -21,8 +21,7 @@ static void i40e_get_pfc_delay(struct i40e_hw *hw, u16 *delay)
 	u32 val;
 
 	val = rd32(hw, I40E_PRTDCB_GENC);
-	*delay = (u16)((val & I40E_PRTDCB_GENC_PFCLDA_MASK) >>
-		       I40E_PRTDCB_GENC_PFCLDA_SHIFT);
+	*delay = FIELD_GET(I40E_PRTDCB_GENC_PFCLDA_MASK, val);
 }
 
 /**
@@ -310,8 +309,8 @@ static u8 i40e_dcbnl_getstate(struct net_device *netdev)
 	struct i40e_pf *pf = i40e_netdev_to_pf(netdev);
 
 	dev_dbg(&pf->pdev->dev, "DCB state=%d\n",
-		!!(pf->flags & I40E_FLAG_DCB_ENABLED));
-	return !!(pf->flags & I40E_FLAG_DCB_ENABLED);
+		test_bit(I40E_FLAG_DCB_ENA, pf->flags) ? 1 : 0);
+	return test_bit(I40E_FLAG_DCB_ENA, pf->flags) ? 1 : 0;
 }
 
 /**
@@ -331,19 +330,19 @@ static u8 i40e_dcbnl_setstate(struct net_device *netdev, u8 state)
 		return ret;
 
 	dev_dbg(&pf->pdev->dev, "new state=%d current state=%d\n",
-		state, (pf->flags & I40E_FLAG_DCB_ENABLED) ? 1 : 0);
+		state, test_bit(I40E_FLAG_DCB_ENA, pf->flags) ? 1 : 0);
 	/* Nothing to do */
-	if (!state == !(pf->flags & I40E_FLAG_DCB_ENABLED))
+	if (!state == !test_bit(I40E_FLAG_DCB_ENA, pf->flags))
 		return ret;
 
 	if (i40e_is_sw_dcb(pf)) {
 		if (state) {
-			pf->flags |= I40E_FLAG_DCB_ENABLED;
+			set_bit(I40E_FLAG_DCB_ENA, pf->flags);
 			memcpy(&pf->hw.desired_dcbx_config,
 			       &pf->hw.local_dcbx_config,
 			       sizeof(struct i40e_dcbx_config));
 		} else {
-			pf->flags &= ~I40E_FLAG_DCB_ENABLED;
+			clear_bit(I40E_FLAG_DCB_ENA, pf->flags);
 		}
 	} else {
 		/* Cannot directly manipulate FW LLDP Agent */
@@ -653,7 +652,7 @@ static u8 i40e_dcbnl_get_cap(struct net_device *netdev, int capid, u8 *cap)
 {
 	struct i40e_pf *pf = i40e_netdev_to_pf(netdev);
 
-	if (!(pf->flags & I40E_FLAG_DCB_CAPABLE))
+	if (!test_bit(I40E_FLAG_DCB_CAPABLE, pf->flags))
 		return I40E_DCBNL_STATUS_ERROR;
 
 	switch (capid) {
@@ -693,7 +692,7 @@ static int i40e_dcbnl_getnumtcs(struct net_device *netdev, int tcid, u8 *num)
 {
 	struct i40e_pf *pf = i40e_netdev_to_pf(netdev);
 
-	if (!(pf->flags & I40E_FLAG_DCB_CAPABLE))
+	if (!test_bit(I40E_FLAG_DCB_CAPABLE, pf->flags))
 		return -EINVAL;
 
 	*num = I40E_MAX_TRAFFIC_CLASS;
@@ -827,15 +826,12 @@ static void i40e_dcbnl_get_perm_hw_addr(struct net_device *dev,
 					u8 *perm_addr)
 {
 	struct i40e_pf *pf = i40e_netdev_to_pf(dev);
-	int i, j;
+	int i;
 
 	memset(perm_addr, 0xff, MAX_ADDR_LEN);
 
 	for (i = 0; i < dev->addr_len; i++)
 		perm_addr[i] = pf->hw.mac.perm_addr[i];
-
-	for (j = 0; j < dev->addr_len; j++, i++)
-		perm_addr[i] = pf->hw.mac.san_addr[j];
 }
 
 static const struct dcbnl_rtnl_ops dcbnl_ops = {
@@ -891,11 +887,11 @@ void i40e_dcbnl_set_all(struct i40e_vsi *vsi)
 		return;
 
 	/* DCB not enabled */
-	if (!(pf->flags & I40E_FLAG_DCB_ENABLED))
+	if (!test_bit(I40E_FLAG_DCB_ENA, pf->flags))
 		return;
 
 	/* MFP mode but not an iSCSI PF so return */
-	if ((pf->flags & I40E_FLAG_MFP_ENABLED) && !(hw->func_caps.iscsi))
+	if (test_bit(I40E_FLAG_MFP_ENA, pf->flags) && !(hw->func_caps.iscsi))
 		return;
 
 	dcbxcfg = &hw->local_dcbx_config;
@@ -1002,7 +998,7 @@ void i40e_dcbnl_flush_apps(struct i40e_pf *pf,
 	int i;
 
 	/* MFP mode but not an iSCSI PF so return */
-	if ((pf->flags & I40E_FLAG_MFP_ENABLED) && !(pf->hw.func_caps.iscsi))
+	if (test_bit(I40E_FLAG_MFP_ENA, pf->flags) && !(pf->hw.func_caps.iscsi))
 		return;
 
 	for (i = 0; i < old_cfg->numapps; i++) {
@@ -1025,7 +1021,7 @@ void i40e_dcbnl_setup(struct i40e_vsi *vsi)
 	struct i40e_pf *pf = i40e_netdev_to_pf(dev);
 
 	/* Not DCB capable */
-	if (!(pf->flags & I40E_FLAG_DCB_CAPABLE))
+	if (!test_bit(I40E_FLAG_DCB_CAPABLE, pf->flags))
 		return;
 
 	dev->dcbnl_ops = &dcbnl_ops;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ddp.c b/drivers/net/ethernet/intel/i40e/i40e_ddp.c
index cf25bfc5dc3f..2f53f0f53bc3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ddp.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ddp.c
@@ -81,8 +81,8 @@ static int i40e_ddp_does_profile_exist(struct i40e_hw *hw,
 static bool i40e_ddp_profiles_overlap(struct i40e_profile_info *new,
 				      struct i40e_profile_info *old)
 {
-	unsigned int group_id_old = (u8)((old->track_id & 0x00FF0000) >> 16);
-	unsigned int group_id_new = (u8)((new->track_id & 0x00FF0000) >> 16);
+	unsigned int group_id_old = FIELD_GET(0x00FF0000, old->track_id);
+	unsigned int group_id_new = FIELD_GET(0x00FF0000, new->track_id);
 
 	/* 0x00 group must be only the first */
 	if (group_id_new == 0)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debug.h b/drivers/net/ethernet/intel/i40e/i40e_debug.h
index 27ebc72d8bfe..e9871dfb32bd 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debug.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_debug.h
@@ -37,6 +37,7 @@ struct i40e_hw;
 struct device *i40e_hw_to_dev(struct i40e_hw *hw);
 
 #define hw_dbg(hw, S, A...) dev_dbg(i40e_hw_to_dev(hw), S, ##A)
+#define hw_warn(hw, S, A...) dev_warn(i40e_hw_to_dev(hw), S, ##A)
 
 #define i40e_debug(h, m, s, ...)				\
 do {								\
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index 999c9708def5..ef70ddbe9c2f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -147,9 +147,8 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
 			 "    state[%d] = %08lx\n",
 			 i, vsi->state[i]);
 	if (vsi == pf->vsi[pf->lan_vsi])
-		dev_info(&pf->pdev->dev, "    MAC address: %pM SAN MAC: %pM Port MAC: %pM\n",
+		dev_info(&pf->pdev->dev, "    MAC address: %pM Port MAC: %pM\n",
 			 pf->hw.mac.addr,
-			 pf->hw.mac.san_addr,
 			 pf->hw.mac.port_addr);
 	hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) {
 		dev_info(&pf->pdev->dev,
@@ -820,8 +819,8 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 		/* By default we are in VEPA mode, if this is the first VF/VMDq
 		 * VSI to be added switch to VEB mode.
 		 */
-		if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
-			pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
+		if (!test_bit(I40E_FLAG_VEB_MODE_ENA, pf->flags)) {
+			set_bit(I40E_FLAG_VEB_MODE_ENA, pf->flags);
 			i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG);
 		}
 
@@ -1029,9 +1028,6 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 				 "emp reset count: %d\n", pf->empr_count);
 			dev_info(&pf->pdev->dev,
 				 "pf reset count: %d\n", pf->pfr_count);
-			dev_info(&pf->pdev->dev,
-				 "pf tx sluggish count: %d\n",
-				 pf->tx_sluggish_count);
 		} else if (strncmp(&cmd_buf[5], "port", 4) == 0) {
 			struct i40e_aqc_query_port_ets_config_resp *bw_data;
 			struct i40e_dcbx_config *cfg =
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index fd7163128c4d..c841779713f6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -430,35 +430,35 @@ static const char i40e_gstrings_test[][ETH_GSTRING_LEN] = {
 
 struct i40e_priv_flags {
 	char flag_string[ETH_GSTRING_LEN];
-	u64 flag;
+	u8 bitno;
 	bool read_only;
 };
 
-#define I40E_PRIV_FLAG(_name, _flag, _read_only) { \
+#define I40E_PRIV_FLAG(_name, _bitno, _read_only) { \
 	.flag_string = _name, \
-	.flag = _flag, \
+	.bitno = _bitno, \
 	.read_only = _read_only, \
 }
 
 static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = {
 	/* NOTE: MFP setting cannot be changed */
-	I40E_PRIV_FLAG("MFP", I40E_FLAG_MFP_ENABLED, 1),
+	I40E_PRIV_FLAG("MFP", I40E_FLAG_MFP_ENA, 1),
 	I40E_PRIV_FLAG("total-port-shutdown",
-		       I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED, 1),
-	I40E_PRIV_FLAG("LinkPolling", I40E_FLAG_LINK_POLLING_ENABLED, 0),
-	I40E_PRIV_FLAG("flow-director-atr", I40E_FLAG_FD_ATR_ENABLED, 0),
-	I40E_PRIV_FLAG("veb-stats", I40E_FLAG_VEB_STATS_ENABLED, 0),
-	I40E_PRIV_FLAG("hw-atr-eviction", I40E_FLAG_HW_ATR_EVICT_ENABLED, 0),
+		       I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENA, 1),
+	I40E_PRIV_FLAG("LinkPolling", I40E_FLAG_LINK_POLLING_ENA, 0),
+	I40E_PRIV_FLAG("flow-director-atr", I40E_FLAG_FD_ATR_ENA, 0),
+	I40E_PRIV_FLAG("veb-stats", I40E_FLAG_VEB_STATS_ENA, 0),
+	I40E_PRIV_FLAG("hw-atr-eviction", I40E_FLAG_HW_ATR_EVICT_ENA, 0),
 	I40E_PRIV_FLAG("link-down-on-close",
-		       I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED, 0),
-	I40E_PRIV_FLAG("legacy-rx", I40E_FLAG_LEGACY_RX, 0),
+		       I40E_FLAG_LINK_DOWN_ON_CLOSE_ENA, 0),
+	I40E_PRIV_FLAG("legacy-rx", I40E_FLAG_LEGACY_RX_ENA, 0),
 	I40E_PRIV_FLAG("disable-source-pruning",
-		       I40E_FLAG_SOURCE_PRUNING_DISABLED, 0),
-	I40E_PRIV_FLAG("disable-fw-lldp", I40E_FLAG_DISABLE_FW_LLDP, 0),
+		       I40E_FLAG_SOURCE_PRUNING_DIS, 0),
+	I40E_PRIV_FLAG("disable-fw-lldp", I40E_FLAG_FW_LLDP_DIS, 0),
 	I40E_PRIV_FLAG("rs-fec", I40E_FLAG_RS_FEC, 0),
 	I40E_PRIV_FLAG("base-r-fec", I40E_FLAG_BASE_R_FEC, 0),
 	I40E_PRIV_FLAG("vf-vlan-pruning",
-		       I40E_FLAG_VF_VLAN_PRUNING, 0),
+		       I40E_FLAG_VF_VLAN_PRUNING_ENA, 0),
 };
 
 #define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gstrings_priv_flags)
@@ -466,7 +466,7 @@ static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = {
 /* Private flags with a global effect, restricted to PF 0 */
 static const struct i40e_priv_flags i40e_gl_gstrings_priv_flags[] = {
 	I40E_PRIV_FLAG("vf-true-promisc-support",
-		       I40E_FLAG_TRUE_PROMISC_SUPPORT, 0),
+		       I40E_FLAG_TRUE_PROMISC_ENA, 0),
 };
 
 #define I40E_GL_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gl_gstrings_priv_flags)
@@ -502,7 +502,7 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf,
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     1000baseT_Full);
-		if (pf->hw_features & I40E_HW_100M_SGMII_CAPABLE) {
+		if (test_bit(I40E_HW_CAP_100M_SGMII, pf->hw.caps)) {
 			ethtool_link_ksettings_add_link_mode(ks, supported,
 							     100baseT_Full);
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
@@ -601,7 +601,7 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf,
 							     10000baseKX4_Full);
 	}
 	if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KR &&
-	    !(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) {
+	    !test_bit(I40E_HW_CAP_CRT_RETIMER, pf->hw.caps)) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     10000baseKR_Full);
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
@@ -609,7 +609,7 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf,
 							     10000baseKR_Full);
 	}
 	if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_KX &&
-	    !(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) {
+	    !test_bit(I40E_HW_CAP_CRT_RETIMER, pf->hw.caps)) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     1000baseKX_Full);
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
@@ -917,7 +917,7 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     1000baseT_Full);
-		if (pf->hw_features & I40E_HW_100M_SGMII_CAPABLE) {
+		if (test_bit(I40E_HW_CAP_100M_SGMII, pf->hw.caps)) {
 			ethtool_link_ksettings_add_link_mode(ks, supported,
 							     100baseT_Full);
 			if (hw_link_info->requested_speeds &
@@ -1488,12 +1488,8 @@ static int i40e_set_fec_cfg(struct net_device *netdev, u8 fec_cfg)
 	struct i40e_pf *pf = np->vsi->back;
 	struct i40e_hw *hw = &pf->hw;
 	int status = 0;
-	u32 flags = 0;
 	int err = 0;
 
-	flags = READ_ONCE(pf->flags);
-	i40e_set_fec_in_flags(fec_cfg, &flags);
-
 	/* Get the current phy config */
 	memset(&abilities, 0, sizeof(abilities));
 	status = i40e_aq_get_phy_capabilities(hw, false, false, &abilities,
@@ -1525,7 +1521,7 @@ static int i40e_set_fec_cfg(struct net_device *netdev, u8 fec_cfg)
 			err = -EAGAIN;
 			goto done;
 		}
-		pf->flags = flags;
+		i40e_set_fec_in_flags(fec_cfg, pf->flags);
 		status = i40e_update_link_info(hw);
 		if (status)
 			/* debug level message only due to relation to the link
@@ -1599,7 +1595,7 @@ static int i40e_set_fec_param(struct net_device *netdev,
 		return -EPERM;
 
 	if (hw->mac.type == I40E_MAC_X722 &&
-	    !(hw->flags & I40E_HW_FLAG_X722_FEC_REQUEST_CAPABLE)) {
+	    !test_bit(I40E_HW_CAP_X722_FEC_REQUEST, hw->caps)) {
 		netdev_err(netdev, "Setting FEC encoding not supported by firmware. Please update the NVM image.\n");
 		return -EOPNOTSUPP;
 	}
@@ -1915,7 +1911,7 @@ static int i40e_get_eeprom(struct net_device *netdev,
 			len = eeprom->len - (I40E_NVM_SECTOR_SIZE * i);
 			last = true;
 		}
-		offset = eeprom->offset + (I40E_NVM_SECTOR_SIZE * i),
+		offset = eeprom->offset + (I40E_NVM_SECTOR_SIZE * i);
 		ret_val = i40e_aq_read_nvm(hw, 0x0, offset, len,
 				(u8 *)eeprom_buff + (I40E_NVM_SECTOR_SIZE * i),
 				last, NULL);
@@ -1956,9 +1952,8 @@ static int i40e_get_eeprom_len(struct net_device *netdev)
 		val = X722_EEPROM_SCOPE_LIMIT + 1;
 		return val;
 	}
-	val = (rd32(hw, I40E_GLPCI_LBARCTRL)
-		& I40E_GLPCI_LBARCTRL_FL_SIZE_MASK)
-		>> I40E_GLPCI_LBARCTRL_FL_SIZE_SHIFT;
+	val = FIELD_GET(I40E_GLPCI_LBARCTRL_FL_SIZE_MASK,
+			rd32(hw, I40E_GLPCI_LBARCTRL));
 	/* register returns value in power of 2, 64Kbyte chunks. */
 	val = (64 * 1024) * BIT(val);
 	return val;
@@ -2015,6 +2010,18 @@ static void i40e_get_drvinfo(struct net_device *netdev,
 		drvinfo->n_priv_flags += I40E_GL_PRIV_FLAGS_STR_LEN;
 }
 
+static u32 i40e_get_max_num_descriptors(struct i40e_pf *pf)
+{
+	struct i40e_hw *hw = &pf->hw;
+
+	switch (hw->mac.type) {
+	case I40E_MAC_XL710:
+		return I40E_MAX_NUM_DESCRIPTORS_XL710;
+	default:
+		return I40E_MAX_NUM_DESCRIPTORS;
+	}
+}
+
 static void i40e_get_ringparam(struct net_device *netdev,
 			       struct ethtool_ringparam *ring,
 			       struct kernel_ethtool_ringparam *kernel_ring,
@@ -2024,8 +2031,8 @@ static void i40e_get_ringparam(struct net_device *netdev,
 	struct i40e_pf *pf = np->vsi->back;
 	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
 
-	ring->rx_max_pending = I40E_MAX_NUM_DESCRIPTORS;
-	ring->tx_max_pending = I40E_MAX_NUM_DESCRIPTORS;
+	ring->rx_max_pending = i40e_get_max_num_descriptors(pf);
+	ring->tx_max_pending = i40e_get_max_num_descriptors(pf);
 	ring->rx_mini_max_pending = 0;
 	ring->rx_jumbo_max_pending = 0;
 	ring->rx_pending = vsi->rx_rings[0]->count;
@@ -2050,12 +2057,12 @@ static int i40e_set_ringparam(struct net_device *netdev,
 			      struct kernel_ethtool_ringparam *kernel_ring,
 			      struct netlink_ext_ack *extack)
 {
+	u32 new_rx_count, new_tx_count, max_num_descriptors;
 	struct i40e_ring *tx_rings = NULL, *rx_rings = NULL;
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_hw *hw = &np->vsi->back->hw;
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
-	u32 new_rx_count, new_tx_count;
 	u16 tx_alloc_queue_pairs;
 	int timeout = 50;
 	int i, err = 0;
@@ -2063,14 +2070,15 @@ static int i40e_set_ringparam(struct net_device *netdev,
 	if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
 		return -EINVAL;
 
-	if (ring->tx_pending > I40E_MAX_NUM_DESCRIPTORS ||
+	max_num_descriptors = i40e_get_max_num_descriptors(pf);
+	if (ring->tx_pending > max_num_descriptors ||
 	    ring->tx_pending < I40E_MIN_NUM_DESCRIPTORS ||
-	    ring->rx_pending > I40E_MAX_NUM_DESCRIPTORS ||
+	    ring->rx_pending > max_num_descriptors ||
 	    ring->rx_pending < I40E_MIN_NUM_DESCRIPTORS) {
 		netdev_info(netdev,
 			    "Descriptors requested (Tx: %d / Rx: %d) out of range [%d-%d]\n",
 			    ring->tx_pending, ring->rx_pending,
-			    I40E_MIN_NUM_DESCRIPTORS, I40E_MAX_NUM_DESCRIPTORS);
+			    I40E_MIN_NUM_DESCRIPTORS, max_num_descriptors);
 		return -EINVAL;
 	}
 
@@ -2419,7 +2427,7 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 
 	veb_stats = ((pf->lan_veb != I40E_NO_VEB) &&
 		     (pf->lan_veb < I40E_MAX_VEB) &&
-		     (pf->flags & I40E_FLAG_VEB_STATS_ENABLED));
+		     test_bit(I40E_FLAG_VEB_STATS_ENA, pf->flags));
 
 	if (veb_stats) {
 		veb = pf->veb[pf->lan_veb];
@@ -2514,13 +2522,11 @@ static void i40e_get_priv_flag_strings(struct net_device *netdev, u8 *data)
 	u8 *p = data;
 
 	for (i = 0; i < I40E_PRIV_FLAGS_STR_LEN; i++)
-		ethtool_sprintf(&p, "%s",
-				i40e_gstrings_priv_flags[i].flag_string);
+		ethtool_puts(&p, i40e_gstrings_priv_flags[i].flag_string);
 	if (pf->hw.pf_id != 0)
 		return;
 	for (i = 0; i < I40E_GL_PRIV_FLAGS_STR_LEN; i++)
-		ethtool_sprintf(&p, "%s",
-				i40e_gl_gstrings_priv_flags[i].flag_string);
+		ethtool_puts(&p, i40e_gl_gstrings_priv_flags[i].flag_string);
 }
 
 static void i40e_get_strings(struct net_device *netdev, u32 stringset,
@@ -2548,7 +2554,7 @@ static int i40e_get_ts_info(struct net_device *dev,
 	struct i40e_pf *pf = i40e_netdev_to_pf(dev);
 
 	/* only report HW timestamping if PTP is enabled */
-	if (!(pf->flags & I40E_FLAG_PTP))
+	if (!test_bit(I40E_FLAG_PTP_ENA, pf->flags))
 		return ethtool_op_get_ts_info(dev, info);
 
 	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
@@ -2570,7 +2576,7 @@ static int i40e_get_ts_info(struct net_device *dev,
 			   BIT(HWTSTAMP_FILTER_PTP_V2_L2_SYNC) |
 			   BIT(HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ);
 
-	if (pf->hw_features & I40E_HW_PTP_L4_CAPABLE)
+	if (test_bit(I40E_HW_CAP_PTP_L4, pf->hw.caps))
 		info->rx_filters |= BIT(HWTSTAMP_FILTER_PTP_V1_L4_SYNC) |
 				    BIT(HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) |
 				    BIT(HWTSTAMP_FILTER_PTP_V2_EVENT) |
@@ -2819,10 +2825,10 @@ static int i40e_set_phys_id(struct net_device *netdev,
 
 	switch (state) {
 	case ETHTOOL_ID_ACTIVE:
-		if (!(pf->hw_features & I40E_HW_PHY_CONTROLS_LEDS)) {
+		if (!test_bit(I40E_HW_CAP_PHY_CONTROLS_LEDS, pf->hw.caps)) {
 			pf->led_status = i40e_led_get(hw);
 		} else {
-			if (!(hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE))
+			if (!test_bit(I40E_HW_CAP_AQ_PHY_ACCESS, hw->caps))
 				i40e_aq_set_phy_debug(hw, I40E_PHY_DEBUG_ALL,
 						      NULL);
 			ret = i40e_led_get_phy(hw, &temp_status,
@@ -2831,25 +2837,25 @@ static int i40e_set_phys_id(struct net_device *netdev,
 		}
 		return blink_freq;
 	case ETHTOOL_ID_ON:
-		if (!(pf->hw_features & I40E_HW_PHY_CONTROLS_LEDS))
+		if (!test_bit(I40E_HW_CAP_PHY_CONTROLS_LEDS, pf->hw.caps))
 			i40e_led_set(hw, 0xf, false);
 		else
 			ret = i40e_led_set_phy(hw, true, pf->led_status, 0);
 		break;
 	case ETHTOOL_ID_OFF:
-		if (!(pf->hw_features & I40E_HW_PHY_CONTROLS_LEDS))
+		if (!test_bit(I40E_HW_CAP_PHY_CONTROLS_LEDS, pf->hw.caps))
 			i40e_led_set(hw, 0x0, false);
 		else
 			ret = i40e_led_set_phy(hw, false, pf->led_status, 0);
 		break;
 	case ETHTOOL_ID_INACTIVE:
-		if (!(pf->hw_features & I40E_HW_PHY_CONTROLS_LEDS)) {
+		if (!test_bit(I40E_HW_CAP_PHY_CONTROLS_LEDS, pf->hw.caps)) {
 			i40e_led_set(hw, pf->led_status, false);
 		} else {
 			ret = i40e_led_set_phy(hw, false, pf->led_status,
 					       (pf->phy_led_val |
 					       I40E_PHY_LED_MODE_ORIG));
-			if (!(hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE))
+			if (!test_bit(I40E_HW_CAP_AQ_PHY_ACCESS, hw->caps))
 				i40e_aq_set_phy_debug(hw, 0, NULL);
 		}
 		break;
@@ -2886,7 +2892,6 @@ static int __i40e_get_coalesce(struct net_device *netdev,
 	struct i40e_vsi *vsi = np->vsi;
 
 	ec->tx_max_coalesced_frames_irq = vsi->work_limit;
-	ec->rx_max_coalesced_frames_irq = vsi->work_limit;
 
 	/* rx and tx usecs has per queue value. If user doesn't specify the
 	 * queue, return queue 0's value to represent.
@@ -3020,7 +3025,7 @@ static int __i40e_set_coalesce(struct net_device *netdev,
 	struct i40e_pf *pf = vsi->back;
 	int i;
 
-	if (ec->tx_max_coalesced_frames_irq || ec->rx_max_coalesced_frames_irq)
+	if (ec->tx_max_coalesced_frames_irq)
 		vsi->work_limit = ec->tx_max_coalesced_frames_irq;
 
 	if (queue < 0) {
@@ -3278,7 +3283,7 @@ static int i40e_parse_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp,
 	} else if (valid) {
 		data->flex_word = value & I40E_USERDEF_FLEX_WORD;
 		data->flex_offset =
-			(value & I40E_USERDEF_FLEX_OFFSET) >> 16;
+			FIELD_GET(I40E_USERDEF_FLEX_OFFSET, value);
 		data->flex_filter = true;
 	}
 
@@ -3628,7 +3633,7 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 
 	bitmap_zero(flow_pctypes, FLOW_PCTYPES_SIZE);
 
-	if (pf->flags & I40E_FLAG_MFP_ENABLED) {
+	if (test_bit(I40E_FLAG_MFP_ENA, pf->flags)) {
 		dev_err(&pf->pdev->dev,
 			"Change of RSS hash input set is not supported when MFP mode is enabled\n");
 		return -EOPNOTSUPP;
@@ -3644,19 +3649,22 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 	switch (nfc->flow_type) {
 	case TCP_V4_FLOW:
 		set_bit(I40E_FILTER_PCTYPE_NONF_IPV4_TCP, flow_pctypes);
-		if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE)
+		if (test_bit(I40E_HW_CAP_MULTI_TCP_UDP_RSS_PCTYPE,
+			     pf->hw.caps))
 			set_bit(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK,
 				flow_pctypes);
 		break;
 	case TCP_V6_FLOW:
 		set_bit(I40E_FILTER_PCTYPE_NONF_IPV6_TCP, flow_pctypes);
-		if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE)
+		if (test_bit(I40E_HW_CAP_MULTI_TCP_UDP_RSS_PCTYPE,
+			     pf->hw.caps))
 			set_bit(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK,
 				flow_pctypes);
 		break;
 	case UDP_V4_FLOW:
 		set_bit(I40E_FILTER_PCTYPE_NONF_IPV4_UDP, flow_pctypes);
-		if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) {
+		if (test_bit(I40E_HW_CAP_MULTI_TCP_UDP_RSS_PCTYPE,
+			     pf->hw.caps)) {
 			set_bit(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP,
 				flow_pctypes);
 			set_bit(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP,
@@ -3666,7 +3674,8 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 		break;
 	case UDP_V6_FLOW:
 		set_bit(I40E_FILTER_PCTYPE_NONF_IPV6_UDP, flow_pctypes);
-		if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) {
+		if (test_bit(I40E_HW_CAP_MULTI_TCP_UDP_RSS_PCTYPE,
+			     pf->hw.caps)) {
 			set_bit(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP,
 				flow_pctypes);
 			set_bit(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP,
@@ -4644,7 +4653,7 @@ static int i40e_check_fdir_input_set(struct i40e_vsi *vsi,
 	 * main port cannot change them when in MFP mode as this would impact
 	 * any filters on the other ports.
 	 */
-	if (pf->flags & I40E_FLAG_MFP_ENABLED) {
+	if (test_bit(I40E_FLAG_MFP_ENA, pf->flags)) {
 		netif_err(pf, drv, vsi->netdev, "Cannot change Flow Director input sets while MFP is enabled\n");
 		return -EOPNOTSUPP;
 	}
@@ -4804,7 +4813,7 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
 		return -EINVAL;
 	pf = vsi->back;
 
-	if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED))
+	if (!test_bit(I40E_FLAG_FD_SB_ENA, pf->flags))
 		return -EOPNOTSUPP;
 
 	if (test_bit(__I40E_FD_SB_AUTO_DISABLED, pf->state))
@@ -5001,7 +5010,7 @@ static void i40e_get_channels(struct net_device *dev,
 	ch->max_combined = i40e_max_channels(vsi);
 
 	/* report info for other vector */
-	ch->other_count = (pf->flags & I40E_FLAG_FD_SB_ENABLED) ? 1 : 0;
+	ch->other_count = test_bit(I40E_FLAG_FD_SB_ENA, pf->flags) ? 1 : 0;
 	ch->max_other = ch->other_count;
 
 	/* Note: This code assumes DCB is disabled for now. */
@@ -5044,7 +5053,7 @@ static int i40e_set_channels(struct net_device *dev,
 		return -EINVAL;
 
 	/* verify other_count has not changed */
-	if (ch->other_count != ((pf->flags & I40E_FLAG_FD_SB_ENABLED) ? 1 : 0))
+	if (ch->other_count != (test_bit(I40E_FLAG_FD_SB_ENA, pf->flags) ? 1 : 0))
 		return -EINVAL;
 
 	/* verify the number of channels does not exceed hardware limits */
@@ -5109,15 +5118,13 @@ static u32 i40e_get_rxfh_indir_size(struct net_device *netdev)
 /**
  * i40e_get_rxfh - get the rx flow hash indirection table
  * @netdev: network interface device structure
- * @indir: indirection table
- * @key: hash key
- * @hfunc: hash function
+ * @rxfh: pointer to param struct (indir, key, hfunc)
  *
  * Reads the indirection table directly from the hardware. Returns 0 on
  * success.
  **/
-static int i40e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			 u8 *hfunc)
+static int i40e_get_rxfh(struct net_device *netdev,
+			 struct ethtool_rxfh_param *rxfh)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -5125,13 +5132,12 @@ static int i40e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 	int ret;
 	u16 i;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
-	seed = key;
+	seed = rxfh->key;
 	lut = kzalloc(I40E_HLUT_ARRAY_SIZE, GFP_KERNEL);
 	if (!lut)
 		return -ENOMEM;
@@ -5139,7 +5145,7 @@ static int i40e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 	if (ret)
 		goto out;
 	for (i = 0; i < I40E_HLUT_ARRAY_SIZE; i++)
-		indir[i] = (u32)(lut[i]);
+		rxfh->indir[i] = (u32)(lut[i]);
 
 out:
 	kfree(lut);
@@ -5150,15 +5156,15 @@ out:
 /**
  * i40e_set_rxfh - set the rx flow hash indirection table
  * @netdev: network interface device structure
- * @indir: indirection table
- * @key: hash key
- * @hfunc: hash function to use
+ * @rxfh: pointer to param struct (indir, key, hfunc)
+ * @extack: extended ACK from the Netlink message
  *
  * Returns -EINVAL if the table specifies an invalid queue id, otherwise
  * returns 0 after programming the table.
  **/
-static int i40e_set_rxfh(struct net_device *netdev, const u32 *indir,
-			 const u8 *key, const u8 hfunc)
+static int i40e_set_rxfh(struct net_device *netdev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -5166,17 +5172,18 @@ static int i40e_set_rxfh(struct net_device *netdev, const u32 *indir,
 	u8 *seed = NULL;
 	u16 i;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (key) {
+	if (rxfh->key) {
 		if (!vsi->rss_hkey_user) {
 			vsi->rss_hkey_user = kzalloc(I40E_HKEY_ARRAY_SIZE,
 						     GFP_KERNEL);
 			if (!vsi->rss_hkey_user)
 				return -ENOMEM;
 		}
-		memcpy(vsi->rss_hkey_user, key, I40E_HKEY_ARRAY_SIZE);
+		memcpy(vsi->rss_hkey_user, rxfh->key, I40E_HKEY_ARRAY_SIZE);
 		seed = vsi->rss_hkey_user;
 	}
 	if (!vsi->rss_lut_user) {
@@ -5186,9 +5193,9 @@ static int i40e_set_rxfh(struct net_device *netdev, const u32 *indir,
 	}
 
 	/* Each 32 bits pointed by 'indir' is stored with a lut entry */
-	if (indir)
+	if (rxfh->indir)
 		for (i = 0; i < I40E_HLUT_ARRAY_SIZE; i++)
-			vsi->rss_lut_user[i] = (u8)(indir[i]);
+			vsi->rss_lut_user[i] = (u8)(rxfh->indir[i]);
 	else
 		i40e_fill_rss_lut(pf, vsi->rss_lut_user, I40E_HLUT_ARRAY_SIZE,
 				  vsi->rss_size);
@@ -5215,11 +5222,11 @@ static u32 i40e_get_priv_flags(struct net_device *dev)
 	u32 i, j, ret_flags = 0;
 
 	for (i = 0; i < I40E_PRIV_FLAGS_STR_LEN; i++) {
-		const struct i40e_priv_flags *priv_flags;
+		const struct i40e_priv_flags *priv_flag;
 
-		priv_flags = &i40e_gstrings_priv_flags[i];
+		priv_flag = &i40e_gstrings_priv_flags[i];
 
-		if (priv_flags->flag & pf->flags)
+		if (test_bit(priv_flag->bitno, pf->flags))
 			ret_flags |= BIT(i);
 	}
 
@@ -5227,11 +5234,11 @@ static u32 i40e_get_priv_flags(struct net_device *dev)
 		return ret_flags;
 
 	for (j = 0; j < I40E_GL_PRIV_FLAGS_STR_LEN; j++) {
-		const struct i40e_priv_flags *priv_flags;
+		const struct i40e_priv_flags *priv_flag;
 
-		priv_flags = &i40e_gl_gstrings_priv_flags[j];
+		priv_flag = &i40e_gl_gstrings_priv_flags[j];
 
-		if (priv_flags->flag & pf->flags)
+		if (test_bit(priv_flag->bitno, pf->flags))
 			ret_flags |= BIT(i + j);
 	}
 
@@ -5245,8 +5252,10 @@ static u32 i40e_get_priv_flags(struct net_device *dev)
  **/
 static int i40e_set_priv_flags(struct net_device *dev, u32 flags)
 {
+	DECLARE_BITMAP(changed_flags, I40E_PF_FLAGS_NBITS);
+	DECLARE_BITMAP(orig_flags, I40E_PF_FLAGS_NBITS);
+	DECLARE_BITMAP(new_flags, I40E_PF_FLAGS_NBITS);
 	struct i40e_netdev_priv *np = netdev_priv(dev);
-	u64 orig_flags, new_flags, changed_flags;
 	enum i40e_admin_queue_err adq_err;
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
@@ -5254,51 +5263,57 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags)
 	int status;
 	u32 i, j;
 
-	orig_flags = READ_ONCE(pf->flags);
-	new_flags = orig_flags;
+	bitmap_copy(orig_flags, pf->flags, I40E_PF_FLAGS_NBITS);
+	bitmap_copy(new_flags, pf->flags, I40E_PF_FLAGS_NBITS);
 
 	for (i = 0; i < I40E_PRIV_FLAGS_STR_LEN; i++) {
-		const struct i40e_priv_flags *priv_flags;
-
-		priv_flags = &i40e_gstrings_priv_flags[i];
+		const struct i40e_priv_flags *priv_flag;
+		bool new_val;
 
-		if (flags & BIT(i))
-			new_flags |= priv_flags->flag;
-		else
-			new_flags &= ~(priv_flags->flag);
+		priv_flag = &i40e_gstrings_priv_flags[i];
+		new_val = (flags & BIT(i)) ? true : false;
 
 		/* If this is a read-only flag, it can't be changed */
-		if (priv_flags->read_only &&
-		    ((orig_flags ^ new_flags) & ~BIT(i)))
+		if (priv_flag->read_only &&
+		    test_bit(priv_flag->bitno, orig_flags) != new_val)
 			return -EOPNOTSUPP;
+
+		if (new_val)
+			set_bit(priv_flag->bitno, new_flags);
+		else
+			clear_bit(priv_flag->bitno, new_flags);
 	}
 
 	if (pf->hw.pf_id != 0)
 		goto flags_complete;
 
 	for (j = 0; j < I40E_GL_PRIV_FLAGS_STR_LEN; j++) {
-		const struct i40e_priv_flags *priv_flags;
+		const struct i40e_priv_flags *priv_flag;
+		bool new_val;
 
-		priv_flags = &i40e_gl_gstrings_priv_flags[j];
-
-		if (flags & BIT(i + j))
-			new_flags |= priv_flags->flag;
-		else
-			new_flags &= ~(priv_flags->flag);
+		priv_flag = &i40e_gl_gstrings_priv_flags[j];
+		new_val = (flags & BIT(i + j)) ? true : false;
 
 		/* If this is a read-only flag, it can't be changed */
-		if (priv_flags->read_only &&
-		    ((orig_flags ^ new_flags) & ~BIT(i)))
+		if (priv_flag->read_only &&
+		    test_bit(priv_flag->bitno, orig_flags) != new_val)
 			return -EOPNOTSUPP;
+
+		if (new_val)
+			set_bit(priv_flag->bitno, new_flags);
+		else
+			clear_bit(priv_flag->bitno, new_flags);
 	}
 
 flags_complete:
-	changed_flags = orig_flags ^ new_flags;
+	bitmap_xor(changed_flags, pf->flags, orig_flags, I40E_PF_FLAGS_NBITS);
 
-	if (changed_flags & I40E_FLAG_DISABLE_FW_LLDP)
+	if (test_bit(I40E_FLAG_FW_LLDP_DIS, changed_flags))
 		reset_needed = I40E_PF_RESET_AND_REBUILD_FLAG;
-	if (changed_flags & (I40E_FLAG_VEB_STATS_ENABLED |
-	    I40E_FLAG_LEGACY_RX | I40E_FLAG_SOURCE_PRUNING_DISABLED))
+
+	if (test_bit(I40E_FLAG_VEB_STATS_ENA, changed_flags) ||
+	    test_bit(I40E_FLAG_LEGACY_RX_ENA, changed_flags) ||
+	    test_bit(I40E_FLAG_SOURCE_PRUNING_DIS, changed_flags))
 		reset_needed = BIT(__I40E_PF_RESET_REQUESTED);
 
 	/* Before we finalize any flag changes, we need to perform some
@@ -5306,8 +5321,8 @@ flags_complete:
 	 */
 
 	/* ATR eviction is not supported on all devices */
-	if ((new_flags & I40E_FLAG_HW_ATR_EVICT_ENABLED) &&
-	    !(pf->hw_features & I40E_HW_ATR_EVICT_CAPABLE))
+	if (test_bit(I40E_FLAG_HW_ATR_EVICT_ENA, new_flags) &&
+	    !test_bit(I40E_HW_CAP_ATR_EVICT, pf->hw.caps))
 		return -EOPNOTSUPP;
 
 	/* If the driver detected FW LLDP was disabled on init, this flag could
@@ -5318,15 +5333,14 @@ flags_complete:
 	 * disable LLDP, however we _must_ not allow the user to enable/disable
 	 * LLDP with this flag on unsupported FW versions.
 	 */
-	if (changed_flags & I40E_FLAG_DISABLE_FW_LLDP) {
-		if (!(pf->hw.flags & I40E_HW_FLAG_FW_LLDP_STOPPABLE)) {
-			dev_warn(&pf->pdev->dev,
-				 "Device does not support changing FW LLDP\n");
-			return -EOPNOTSUPP;
-		}
+	if (test_bit(I40E_FLAG_FW_LLDP_DIS, changed_flags) &&
+	    !test_bit(I40E_HW_CAP_FW_LLDP_STOPPABLE, pf->hw.caps)) {
+		dev_warn(&pf->pdev->dev,
+			 "Device does not support changing FW LLDP\n");
+		return -EOPNOTSUPP;
 	}
 
-	if (changed_flags & I40E_FLAG_RS_FEC &&
+	if (test_bit(I40E_FLAG_RS_FEC, changed_flags) &&
 	    pf->hw.device_id != I40E_DEV_ID_25G_SFP28 &&
 	    pf->hw.device_id != I40E_DEV_ID_25G_B) {
 		dev_warn(&pf->pdev->dev,
@@ -5334,7 +5348,7 @@ flags_complete:
 		return -EOPNOTSUPP;
 	}
 
-	if (changed_flags & I40E_FLAG_BASE_R_FEC &&
+	if (test_bit(I40E_FLAG_BASE_R_FEC, changed_flags) &&
 	    pf->hw.device_id != I40E_DEV_ID_25G_SFP28 &&
 	    pf->hw.device_id != I40E_DEV_ID_25G_B &&
 	    pf->hw.device_id != I40E_DEV_ID_KX_X722) {
@@ -5349,17 +5363,17 @@ flags_complete:
 	 */
 
 	/* Flush current ATR settings if ATR was disabled */
-	if ((changed_flags & I40E_FLAG_FD_ATR_ENABLED) &&
-	    !(new_flags & I40E_FLAG_FD_ATR_ENABLED)) {
+	if (test_bit(I40E_FLAG_FD_ATR_ENA, changed_flags) &&
+	    !test_bit(I40E_FLAG_FD_ATR_ENA, new_flags)) {
 		set_bit(__I40E_FD_ATR_AUTO_DISABLED, pf->state);
 		set_bit(__I40E_FD_FLUSH_REQUESTED, pf->state);
 	}
 
-	if (changed_flags & I40E_FLAG_TRUE_PROMISC_SUPPORT) {
+	if (test_bit(I40E_FLAG_TRUE_PROMISC_ENA, changed_flags)) {
 		u16 sw_flags = 0, valid_flags = 0;
 		int ret;
 
-		if (!(new_flags & I40E_FLAG_TRUE_PROMISC_SUPPORT))
+		if (!test_bit(I40E_FLAG_TRUE_PROMISC_ENA, new_flags))
 			sw_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
 		valid_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
 		ret = i40e_aq_set_switch_config(&pf->hw, sw_flags, valid_flags,
@@ -5374,17 +5388,17 @@ flags_complete:
 		}
 	}
 
-	if ((changed_flags & I40E_FLAG_RS_FEC) ||
-	    (changed_flags & I40E_FLAG_BASE_R_FEC)) {
+	if (test_bit(I40E_FLAG_RS_FEC, changed_flags) ||
+	    test_bit(I40E_FLAG_BASE_R_FEC, changed_flags)) {
 		u8 fec_cfg = 0;
 
-		if (new_flags & I40E_FLAG_RS_FEC &&
-		    new_flags & I40E_FLAG_BASE_R_FEC) {
+		if (test_bit(I40E_FLAG_RS_FEC, new_flags) &&
+		    test_bit(I40E_FLAG_BASE_R_FEC, new_flags)) {
 			fec_cfg = I40E_AQ_SET_FEC_AUTO;
-		} else if (new_flags & I40E_FLAG_RS_FEC) {
+		} else if (test_bit(I40E_FLAG_RS_FEC, new_flags)) {
 			fec_cfg = (I40E_AQ_SET_FEC_REQUEST_RS |
 				   I40E_AQ_SET_FEC_ABILITY_RS);
-		} else if (new_flags & I40E_FLAG_BASE_R_FEC) {
+		} else if (test_bit(I40E_FLAG_BASE_R_FEC, new_flags)) {
 			fec_cfg = (I40E_AQ_SET_FEC_REQUEST_KR |
 				   I40E_AQ_SET_FEC_ABILITY_KR);
 		}
@@ -5392,35 +5406,35 @@ flags_complete:
 			dev_warn(&pf->pdev->dev, "Cannot change FEC config\n");
 	}
 
-	if ((changed_flags & I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED) &&
-	    (orig_flags & I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED)) {
+	if (test_bit(I40E_FLAG_LINK_DOWN_ON_CLOSE_ENA, changed_flags) &&
+	    test_bit(I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENA, orig_flags)) {
 		dev_err(&pf->pdev->dev,
 			"Setting link-down-on-close not supported on this port (because total-port-shutdown is enabled)\n");
 		return -EOPNOTSUPP;
 	}
 
-	if ((changed_flags & I40E_FLAG_VF_VLAN_PRUNING) &&
+	if (test_bit(I40E_FLAG_VF_VLAN_PRUNING_ENA, changed_flags) &&
 	    pf->num_alloc_vfs) {
 		dev_warn(&pf->pdev->dev,
 			 "Changing vf-vlan-pruning flag while VF(s) are active is not supported\n");
 		return -EOPNOTSUPP;
 	}
 
-	if ((changed_flags & I40E_FLAG_LEGACY_RX) &&
+	if (test_bit(I40E_FLAG_LEGACY_RX_ENA, changed_flags) &&
 	    I40E_2K_TOO_SMALL_WITH_PADDING) {
 		dev_warn(&pf->pdev->dev,
 			 "2k Rx buffer is too small to fit standard MTU and skb_shared_info\n");
 		return -EOPNOTSUPP;
 	}
 
-	if ((changed_flags & new_flags &
-	     I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED) &&
-	    (new_flags & I40E_FLAG_MFP_ENABLED))
+	if (test_bit(I40E_FLAG_LINK_DOWN_ON_CLOSE_ENA, changed_flags) &&
+	    test_bit(I40E_FLAG_LINK_DOWN_ON_CLOSE_ENA, new_flags) &&
+	    test_bit(I40E_FLAG_MFP_ENA, new_flags))
 		dev_warn(&pf->pdev->dev,
 			 "Turning on link-down-on-close flag may affect other partitions\n");
 
-	if (changed_flags & I40E_FLAG_DISABLE_FW_LLDP) {
-		if (new_flags & I40E_FLAG_DISABLE_FW_LLDP) {
+	if (test_bit(I40E_FLAG_FW_LLDP_DIS, changed_flags)) {
+		if (test_bit(I40E_FLAG_FW_LLDP_DIS, new_flags)) {
 #ifdef CONFIG_I40E_DCB
 			i40e_dcb_sw_default_config(pf);
 #endif /* CONFIG_I40E_DCB */
@@ -5461,7 +5475,7 @@ flags_complete:
 	 * initialization or (b) while holding the RTNL lock, we don't need
 	 * anything fancy here.
 	 */
-	pf->flags = new_flags;
+	bitmap_copy(pf->flags, new_flags, I40E_PF_FLAGS_NBITS);
 
 	/* Issue reset to cause things to take effect, as additional bits
 	 * are added we will need to create a mask of bits requiring reset
@@ -5491,7 +5505,7 @@ static int i40e_get_module_info(struct net_device *netdev,
 	int status;
 
 	/* Check if firmware supports reading module EEPROM. */
-	if (!(hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE)) {
+	if (!test_bit(I40E_HW_CAP_AQ_PHY_ACCESS, hw->caps)) {
 		netdev_err(vsi->netdev, "Module EEPROM memory read not supported. Please update the NVM image.\n");
 		return -EINVAL;
 	}
@@ -5571,8 +5585,8 @@ static int i40e_get_module_info(struct net_device *netdev,
 		modinfo->eeprom_len = I40E_MODULE_QSFP_MAX_LEN;
 		break;
 	default:
-		netdev_err(vsi->netdev, "Module type unrecognized\n");
-		return -EINVAL;
+		netdev_dbg(vsi->netdev, "SFP module type unrecognized or no SFP connector used.\n");
+		return -EOPNOTSUPP;
 	}
 	return 0;
 }
@@ -5768,7 +5782,7 @@ static const struct ethtool_ops i40e_ethtool_recovery_mode_ops = {
 
 static const struct ethtool_ops i40e_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
-				     ETHTOOL_COALESCE_MAX_FRAMES_IRQ |
+				     ETHTOOL_COALESCE_TX_MAX_FRAMES_IRQ |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE |
 				     ETHTOOL_COALESCE_RX_USECS_HIGH |
 				     ETHTOOL_COALESCE_TX_USECS_HIGH,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index f7a332e51524..ae8f9f135725 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -107,12 +107,18 @@ static struct workqueue_struct *i40e_wq;
 static void netdev_hw_addr_refcnt(struct i40e_mac_filter *f,
 				  struct net_device *netdev, int delta)
 {
+	struct netdev_hw_addr_list *ha_list;
 	struct netdev_hw_addr *ha;
 
 	if (!f || !netdev)
 		return;
 
-	netdev_for_each_mc_addr(ha, netdev) {
+	if (is_unicast_ether_addr(f->macaddr) || is_link_local_ether_addr(f->macaddr))
+		ha_list = &netdev->uc;
+	else
+		ha_list = &netdev->mc;
+
+	netdev_hw_addr_list_for_each(ha, ha_list) {
 		if (ether_addr_equal(ha->addr, f->macaddr)) {
 			ha->refcount += delta;
 			if (ha->refcount <= 0)
@@ -371,7 +377,7 @@ static void i40e_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 	if (tx_ring) {
 		head = i40e_get_head(tx_ring);
 		/* Read interrupt register */
-		if (pf->flags & I40E_FLAG_MSIX_ENABLED)
+		if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags))
 			val = rd32(&pf->hw,
 			     I40E_PFINT_DYN_CTLN(tx_ring->q_vector->v_idx +
 						tx_ring->vsi->base_vector - 1));
@@ -1197,11 +1203,9 @@ static void i40e_update_pf_stats(struct i40e_pf *pf)
 
 	val = rd32(hw, I40E_PRTPM_EEE_STAT);
 	nsd->tx_lpi_status =
-		       (val & I40E_PRTPM_EEE_STAT_TX_LPI_STATUS_MASK) >>
-			I40E_PRTPM_EEE_STAT_TX_LPI_STATUS_SHIFT;
+		       FIELD_GET(I40E_PRTPM_EEE_STAT_TX_LPI_STATUS_MASK, val);
 	nsd->rx_lpi_status =
-		       (val & I40E_PRTPM_EEE_STAT_RX_LPI_STATUS_MASK) >>
-			I40E_PRTPM_EEE_STAT_RX_LPI_STATUS_SHIFT;
+		       FIELD_GET(I40E_PRTPM_EEE_STAT_RX_LPI_STATUS_MASK, val);
 	i40e_stat_update32(hw, I40E_PRTPM_TLPIC,
 			   pf->stat_offsets_loaded,
 			   &osd->tx_lpi_count, &nsd->tx_lpi_count);
@@ -1209,13 +1213,13 @@ static void i40e_update_pf_stats(struct i40e_pf *pf)
 			   pf->stat_offsets_loaded,
 			   &osd->rx_lpi_count, &nsd->rx_lpi_count);
 
-	if (pf->flags & I40E_FLAG_FD_SB_ENABLED &&
+	if (test_bit(I40E_FLAG_FD_SB_ENA, pf->flags) &&
 	    !test_bit(__I40E_FD_SB_AUTO_DISABLED, pf->state))
 		nsd->fd_sb_status = true;
 	else
 		nsd->fd_sb_status = false;
 
-	if (pf->flags & I40E_FLAG_FD_ATR_ENABLED &&
+	if (test_bit(I40E_FLAG_FD_ATR_ENA, pf->flags) &&
 	    !test_bit(__I40E_FD_ATR_AUTO_DISABLED, pf->state))
 		nsd->fd_atr_status = true;
 	else
@@ -1485,7 +1489,7 @@ static s16 i40e_get_vf_new_vlan(struct i40e_vsi *vsi,
 		return pvid;
 
 	is_any = (trusted ||
-		  !(pf->flags & I40E_FLAG_VF_VLAN_PRUNING));
+		  !test_bit(I40E_FLAG_VF_VLAN_PRUNING_ENA, pf->flags));
 
 	if ((vlan_filters && f->vlan == I40E_VLAN_ANY) ||
 	    (!is_any && !vlan_filters && f->vlan == I40E_VLAN_ANY) ||
@@ -1890,7 +1894,7 @@ static int i40e_vsi_config_rss(struct i40e_vsi *vsi)
 	u8 *lut;
 	int ret;
 
-	if (!(pf->hw_features & I40E_HW_RSS_AQ_CAPABLE))
+	if (!test_bit(I40E_HW_CAP_RSS_AQ, pf->hw.caps))
 		return 0;
 	if (!vsi->rss_size)
 		vsi->rss_size = min_t(int, pf->alloc_rss_size,
@@ -2045,7 +2049,7 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 		 */
 		if (vsi->req_queue_pairs > 0)
 			vsi->num_queue_pairs = vsi->req_queue_pairs;
-		else if (pf->flags & I40E_FLAG_MSIX_ENABLED)
+		else if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags))
 			vsi->num_queue_pairs = pf->num_lan_msix;
 		else
 			vsi->num_queue_pairs = 1;
@@ -2058,7 +2062,7 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 	else
 		num_tc_qps = vsi->alloc_queue_pairs;
 
-	if (enabled_tc && (vsi->back->flags & I40E_FLAG_DCB_ENABLED)) {
+	if (enabled_tc && test_bit(I40E_FLAG_DCB_ENA, vsi->back->flags)) {
 		/* Find numtc from enabled TC bitmap */
 		for (i = 0, numtc = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
 			if (enabled_tc & BIT(i)) /* TC is enabled */
@@ -2077,7 +2081,7 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 	vsi->tc_config.enabled_tc = enabled_tc ? enabled_tc : 1;
 
 	/* Do not allow use more TC queue pairs than MSI-X vectors exist */
-	if (pf->flags & I40E_FLAG_MSIX_ENABLED)
+	if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags))
 		num_tc_qps = min_t(int, num_tc_qps, pf->num_lan_msix);
 
 	/* Setup queue offset/count for all TCs for given VSI */
@@ -2089,8 +2093,10 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 
 			switch (vsi->type) {
 			case I40E_VSI_MAIN:
-				if (!(pf->flags & (I40E_FLAG_FD_SB_ENABLED |
-				    I40E_FLAG_FD_ATR_ENABLED)) ||
+				if ((!test_bit(I40E_FLAG_FD_SB_ENA,
+					       pf->flags) &&
+				     !test_bit(I40E_FLAG_FD_ATR_ENA,
+					       pf->flags)) ||
 				    vsi->tc_config.enabled_tc != 1) {
 					qcount = min_t(int, pf->alloc_rss_size,
 						       num_tc_qps);
@@ -2476,7 +2482,7 @@ static int i40e_set_promiscuous(struct i40e_pf *pf, bool promisc)
 
 	if (vsi->type == I40E_VSI_MAIN &&
 	    pf->lan_veb != I40E_NO_VEB &&
-	    !(pf->flags & I40E_FLAG_MFP_ENABLED)) {
+	    !test_bit(I40E_FLAG_MFP_ENA, pf->flags)) {
 		/* set defport ON for Main VSI instead of true promisc
 		 * this way we will get all unicast/multicast and VLAN
 		 * promisc behavior but will not get VF or VMDq traffic
@@ -2907,7 +2913,7 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf)
  */
 static u16 i40e_calculate_vsi_rx_buf_len(struct i40e_vsi *vsi)
 {
-	if (!vsi->netdev || (vsi->back->flags & I40E_FLAG_LEGACY_RX))
+	if (!vsi->netdev || test_bit(I40E_FLAG_LEGACY_RX_ENA, vsi->back->flags))
 		return SKB_WITH_OVERHEAD(I40E_RXBUFFER_2048);
 
 	return PAGE_SIZE < 8192 ? I40E_RXBUFFER_3072 : I40E_RXBUFFER_2048;
@@ -3462,8 +3468,8 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring)
 		ring->xsk_pool = i40e_xsk_pool(ring);
 
 	/* some ATR related tx ring init */
-	if (vsi->back->flags & I40E_FLAG_FD_ATR_ENABLED) {
-		ring->atr_sample_rate = vsi->back->atr_sample_rate;
+	if (test_bit(I40E_FLAG_FD_ATR_ENA, vsi->back->flags)) {
+		ring->atr_sample_rate = I40E_DEFAULT_ATR_SAMPLE_RATE;
 		ring->atr_count = 0;
 	} else {
 		ring->atr_sample_rate = 0;
@@ -3478,9 +3484,11 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring)
 	tx_ctx.new_context = 1;
 	tx_ctx.base = (ring->dma / 128);
 	tx_ctx.qlen = ring->count;
-	tx_ctx.fd_ena = !!(vsi->back->flags & (I40E_FLAG_FD_SB_ENABLED |
-					       I40E_FLAG_FD_ATR_ENABLED));
-	tx_ctx.timesync_ena = !!(vsi->back->flags & I40E_FLAG_PTP);
+	if (test_bit(I40E_FLAG_FD_SB_ENA, vsi->back->flags) ||
+	    test_bit(I40E_FLAG_FD_ATR_ENA, vsi->back->flags))
+		tx_ctx.fd_ena = 1;
+	if (test_bit(I40E_FLAG_PTP_ENA, vsi->back->flags))
+		tx_ctx.timesync_ena = 1;
 	/* FDIR VSI tx ring can still use RS bit and writebacks */
 	if (vsi->type != I40E_VSI_FDIR)
 		tx_ctx.head_wb_ena = 1;
@@ -3532,21 +3540,19 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring)
 		else
 			return -EINVAL;
 
-		qtx_ctl |= (ring->ch->vsi_number <<
-			    I40E_QTX_CTL_VFVM_INDX_SHIFT) &
-			    I40E_QTX_CTL_VFVM_INDX_MASK;
+		qtx_ctl |= FIELD_PREP(I40E_QTX_CTL_VFVM_INDX_MASK,
+				      ring->ch->vsi_number);
 	} else {
 		if (vsi->type == I40E_VSI_VMDQ2) {
 			qtx_ctl = I40E_QTX_CTL_VM_QUEUE;
-			qtx_ctl |= ((vsi->id) << I40E_QTX_CTL_VFVM_INDX_SHIFT) &
-				    I40E_QTX_CTL_VFVM_INDX_MASK;
+			qtx_ctl |= FIELD_PREP(I40E_QTX_CTL_VFVM_INDX_MASK,
+					      vsi->id);
 		} else {
 			qtx_ctl = I40E_QTX_CTL_PF_QUEUE;
 		}
 	}
 
-	qtx_ctl |= ((hw->pf_id << I40E_QTX_CTL_PF_INDX_SHIFT) &
-		    I40E_QTX_CTL_PF_INDX_MASK);
+	qtx_ctl |= FIELD_PREP(I40E_QTX_CTL_PF_INDX_MASK, hw->pf_id);
 	wr32(hw, I40E_QTX_CTL(pf_q), qtx_ctl);
 	i40e_flush(hw);
 
@@ -3663,7 +3669,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	}
 
 	/* configure Rx buffer alignment */
-	if (!vsi->netdev || (vsi->back->flags & I40E_FLAG_LEGACY_RX)) {
+	if (!vsi->netdev || test_bit(I40E_FLAG_LEGACY_RX_ENA, vsi->back->flags)) {
 		if (I40E_2K_TOO_SMALL_WITH_PADDING) {
 			dev_info(&vsi->back->pdev->dev,
 				 "2k Rx buffer is too small to fit standard MTU and skb_shared_info\n");
@@ -3761,7 +3767,7 @@ static void i40e_vsi_config_dcb_rings(struct i40e_vsi *vsi)
 	u16 qoffset, qcount;
 	int i, n;
 
-	if (!(vsi->back->flags & I40E_FLAG_DCB_ENABLED)) {
+	if (!test_bit(I40E_FLAG_DCB_ENA, vsi->back->flags)) {
 		/* Reset the TC information */
 		for (i = 0; i < vsi->num_queue_pairs; i++) {
 			rx_ring = vsi->rx_rings[i];
@@ -3828,7 +3834,7 @@ static void i40e_fdir_filter_restore(struct i40e_vsi *vsi)
 	struct i40e_pf *pf = vsi->back;
 	struct hlist_node *node;
 
-	if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED))
+	if (!test_bit(I40E_FLAG_FD_SB_ENA, pf->flags))
 		return;
 
 	/* Reset FDir counters as we're replaying all existing filters */
@@ -3966,10 +3972,10 @@ static void i40e_enable_misc_int_causes(struct i40e_pf *pf)
 	      I40E_PFINT_ICR0_ENA_VFLR_MASK          |
 	      I40E_PFINT_ICR0_ENA_ADMINQ_MASK;
 
-	if (pf->flags & I40E_FLAG_IWARP_ENABLED)
+	if (test_bit(I40E_FLAG_IWARP_ENA, pf->flags))
 		val |= I40E_PFINT_ICR0_ENA_PE_CRITERR_MASK;
 
-	if (pf->flags & I40E_FLAG_PTP)
+	if (test_bit(I40E_FLAG_PTP_ENA, pf->flags))
 		val |= I40E_PFINT_ICR0_ENA_TIMESYNC_MASK;
 
 	wr32(hw, I40E_PFINT_ICR0_ENA, val);
@@ -4205,7 +4211,7 @@ static void i40e_vsi_disable_irq(struct i40e_vsi *vsi)
 	}
 
 	/* disable each interrupt */
-	if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+	if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags)) {
 		for (i = vsi->base_vector;
 		     i < (vsi->num_q_vectors + vsi->base_vector); i++)
 			wr32(hw, I40E_PFINT_DYN_CTLN(i - 1), 0);
@@ -4231,7 +4237,7 @@ static int i40e_vsi_enable_irq(struct i40e_vsi *vsi)
 	struct i40e_pf *pf = vsi->back;
 	int i;
 
-	if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+	if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags)) {
 		for (i = 0; i < vsi->num_q_vectors; i++)
 			i40e_irq_dynamic_enable(vsi, i);
 	} else {
@@ -4252,7 +4258,7 @@ static void i40e_free_misc_vector(struct i40e_pf *pf)
 	wr32(&pf->hw, I40E_PFINT_ICR0_ENA, 0);
 	i40e_flush(&pf->hw);
 
-	if (pf->flags & I40E_FLAG_MSIX_ENABLED && pf->msix_entries) {
+	if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags) && pf->msix_entries) {
 		free_irq(pf->msix_entries[0].vector, pf);
 		clear_bit(__I40E_MISC_IRQ_REQUESTED, pf->state);
 	}
@@ -4287,7 +4293,7 @@ static irqreturn_t i40e_intr(int irq, void *data)
 	    (icr0 & I40E_PFINT_ICR0_SWINT_MASK))
 		pf->sw_int_count++;
 
-	if ((pf->flags & I40E_FLAG_IWARP_ENABLED) &&
+	if (test_bit(I40E_FLAG_IWARP_ENA, pf->flags) &&
 	    (icr0 & I40E_PFINT_ICR0_ENA_PE_CRITERR_MASK)) {
 		ena_mask &= ~I40E_PFINT_ICR0_ENA_PE_CRITERR_MASK;
 		dev_dbg(&pf->pdev->dev, "cleared PE_CRITERR\n");
@@ -4338,8 +4344,7 @@ static irqreturn_t i40e_intr(int irq, void *data)
 			set_bit(__I40E_RESET_INTR_RECEIVED, pf->state);
 		ena_mask &= ~I40E_PFINT_ICR0_ENA_GRST_MASK;
 		val = rd32(hw, I40E_GLGEN_RSTAT);
-		val = (val & I40E_GLGEN_RSTAT_RESET_TYPE_MASK)
-		       >> I40E_GLGEN_RSTAT_RESET_TYPE_SHIFT;
+		val = FIELD_GET(I40E_GLGEN_RSTAT_RESET_TYPE_MASK, val);
 		if (val == I40E_RESET_CORER) {
 			pf->corer_count++;
 		} else if (val == I40E_RESET_GLOBR) {
@@ -4480,7 +4485,7 @@ static bool i40e_clean_fdir_tx_irq(struct i40e_ring *tx_ring, int budget)
 	i += tx_ring->count;
 	tx_ring->next_to_clean = i;
 
-	if (vsi->back->flags & I40E_FLAG_MSIX_ENABLED)
+	if (test_bit(I40E_FLAG_MSIX_ENA, vsi->back->flags))
 		i40e_irq_dynamic_enable(vsi, tx_ring->q_vector->v_idx);
 
 	return budget > 0;
@@ -4593,9 +4598,9 @@ static int i40e_vsi_request_irq(struct i40e_vsi *vsi, char *basename)
 	struct i40e_pf *pf = vsi->back;
 	int err;
 
-	if (pf->flags & I40E_FLAG_MSIX_ENABLED)
+	if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags))
 		err = i40e_vsi_request_irq_msix(vsi, basename);
-	else if (pf->flags & I40E_FLAG_MSI_ENABLED)
+	else if (test_bit(I40E_FLAG_MSI_ENA, pf->flags))
 		err = request_irq(pf->pdev->irq, i40e_intr, 0,
 				  pf->int_name, pf);
 	else
@@ -4627,7 +4632,7 @@ static void i40e_netpoll(struct net_device *netdev)
 	if (test_bit(__I40E_VSI_DOWN, vsi->state))
 		return;
 
-	if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+	if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags)) {
 		for (i = 0; i < vsi->num_q_vectors; i++)
 			i40e_msix_clean_rings(0, vsi->q_vectors[i]);
 	} else {
@@ -4967,7 +4972,7 @@ static void i40e_vsi_free_irq(struct i40e_vsi *vsi)
 	u32 val, qp;
 	int i;
 
-	if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+	if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags)) {
 		if (!vsi->q_vectors)
 			return;
 
@@ -5001,8 +5006,8 @@ static void i40e_vsi_free_irq(struct i40e_vsi *vsi)
 			 * next_q field of the registers.
 			 */
 			val = rd32(hw, I40E_PFINT_LNKLSTN(vector - 1));
-			qp = (val & I40E_PFINT_LNKLSTN_FIRSTQ_INDX_MASK)
-				>> I40E_PFINT_LNKLSTN_FIRSTQ_INDX_SHIFT;
+			qp = FIELD_GET(I40E_PFINT_LNKLSTN_FIRSTQ_INDX_MASK,
+				       val);
 			val |= I40E_QUEUE_END_OF_LIST
 				<< I40E_PFINT_LNKLSTN_FIRSTQ_INDX_SHIFT;
 			wr32(hw, I40E_PFINT_LNKLSTN(vector - 1), val);
@@ -5024,8 +5029,8 @@ static void i40e_vsi_free_irq(struct i40e_vsi *vsi)
 
 				val = rd32(hw, I40E_QINT_TQCTL(qp));
 
-				next = (val & I40E_QINT_TQCTL_NEXTQ_INDX_MASK)
-					>> I40E_QINT_TQCTL_NEXTQ_INDX_SHIFT;
+				next = FIELD_GET(I40E_QINT_TQCTL_NEXTQ_INDX_MASK,
+						 val);
 
 				val &= ~(I40E_QINT_TQCTL_MSIX_INDX_MASK  |
 					 I40E_QINT_TQCTL_MSIX0_INDX_MASK |
@@ -5043,8 +5048,7 @@ static void i40e_vsi_free_irq(struct i40e_vsi *vsi)
 		free_irq(pf->pdev->irq, pf);
 
 		val = rd32(hw, I40E_PFINT_LNKLST0);
-		qp = (val & I40E_PFINT_LNKLSTN_FIRSTQ_INDX_MASK)
-			>> I40E_PFINT_LNKLSTN_FIRSTQ_INDX_SHIFT;
+		qp = FIELD_GET(I40E_PFINT_LNKLSTN_FIRSTQ_INDX_MASK, val);
 		val |= I40E_QUEUE_END_OF_LIST
 			<< I40E_PFINT_LNKLST0_FIRSTQ_INDX_SHIFT;
 		wr32(hw, I40E_PFINT_LNKLST0, val);
@@ -5129,16 +5133,17 @@ static void i40e_vsi_free_q_vectors(struct i40e_vsi *vsi)
 static void i40e_reset_interrupt_capability(struct i40e_pf *pf)
 {
 	/* If we're in Legacy mode, the interrupt was cleaned in vsi_close */
-	if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+	if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags)) {
 		pci_disable_msix(pf->pdev);
 		kfree(pf->msix_entries);
 		pf->msix_entries = NULL;
 		kfree(pf->irq_pile);
 		pf->irq_pile = NULL;
-	} else if (pf->flags & I40E_FLAG_MSI_ENABLED) {
+	} else if (test_bit(I40E_FLAG_MSI_ENA, pf->flags)) {
 		pci_disable_msi(pf->pdev);
 	}
-	pf->flags &= ~(I40E_FLAG_MSIX_ENABLED | I40E_FLAG_MSI_ENABLED);
+	clear_bit(I40E_FLAG_MSI_ENA, pf->flags);
+	clear_bit(I40E_FLAG_MSIX_ENA, pf->flags);
 }
 
 /**
@@ -5478,11 +5483,11 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf)
 		return pf->vsi[pf->lan_vsi]->mqprio_qopt.qopt.num_tc;
 
 	/* If neither MQPRIO nor DCB is enabled, then always use single TC */
-	if (!(pf->flags & I40E_FLAG_DCB_ENABLED))
+	if (!test_bit(I40E_FLAG_DCB_ENA, pf->flags))
 		return 1;
 
 	/* SFP mode will be enabled for all TCs on port */
-	if (!(pf->flags & I40E_FLAG_MFP_ENABLED))
+	if (!test_bit(I40E_FLAG_MFP_ENA, pf->flags))
 		return i40e_dcb_get_num_tc(dcbcfg);
 
 	/* MFP mode return count of enabled TCs for this PF */
@@ -5512,11 +5517,11 @@ static u8 i40e_pf_get_tc_map(struct i40e_pf *pf)
 	/* If neither MQPRIO nor DCB is enabled for this PF then just return
 	 * default TC
 	 */
-	if (!(pf->flags & I40E_FLAG_DCB_ENABLED))
+	if (!test_bit(I40E_FLAG_DCB_ENA, pf->flags))
 		return I40E_DEFAULT_TRAFFIC_CLASS;
 
 	/* SFP mode we want PF to be enabled for all TCs */
-	if (!(pf->flags & I40E_FLAG_MFP_ENABLED))
+	if (!test_bit(I40E_FLAG_MFP_ENA, pf->flags))
 		return i40e_dcb_get_enabled_tc(&pf->hw.local_dcbx_config);
 
 	/* MFP enabled and iSCSI PF type */
@@ -5605,7 +5610,7 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc,
 	/* There is no need to reset BW when mqprio mode is on.  */
 	if (i40e_is_tc_mqprio_enabled(pf))
 		return 0;
-	if (!vsi->mqprio_qopt.qopt.hw && !(pf->flags & I40E_FLAG_DCB_ENABLED)) {
+	if (!vsi->mqprio_qopt.qopt.hw && !test_bit(I40E_FLAG_DCB_ENA, pf->flags)) {
 		ret = i40e_set_bw_limit(vsi, vsi->seid, 0);
 		if (ret)
 			dev_info(&pf->pdev->dev,
@@ -5858,7 +5863,7 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc)
 		}
 		vsi->reconfig_rss = false;
 	}
-	if (vsi->back->flags & I40E_FLAG_IWARP_ENABLED) {
+	if (test_bit(I40E_FLAG_IWARP_ENA, vsi->back->flags)) {
 		ctxt.info.valid_sections |=
 				cpu_to_le16(I40E_AQ_VSI_PROP_QUEUE_OPT_VALID);
 		ctxt.info.queueing_opt_flags |= I40E_AQ_VSI_QUE_OPT_TCP_ENA;
@@ -6271,7 +6276,7 @@ static int i40e_add_channel(struct i40e_pf *pf, u16 uplink_seid,
 	if (ch->type == I40E_VSI_VMDQ2)
 		ctxt.flags = I40E_AQ_VSI_TYPE_VMDQ2;
 
-	if (pf->flags & I40E_FLAG_VEB_MODE_ENABLED) {
+	if (test_bit(I40E_FLAG_VEB_MODE_ENA, pf->flags)) {
 		ctxt.info.valid_sections |=
 		     cpu_to_le16(I40E_AQ_VSI_PROP_SWITCH_VALID);
 		ctxt.info.switch_id =
@@ -6576,8 +6581,8 @@ int i40e_create_queue_channel(struct i40e_vsi *vsi,
 	 * VSI to be added switch to VEB mode.
 	 */
 
-	if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
-		pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
+	if (!test_bit(I40E_FLAG_VEB_MODE_ENA, pf->flags)) {
+		set_bit(I40E_FLAG_VEB_MODE_ENA, pf->flags);
 
 		if (vsi->type == I40E_VSI_MAIN) {
 			if (i40e_is_tc_mqprio_enabled(pf))
@@ -6988,9 +6993,9 @@ int i40e_hw_dcb_config(struct i40e_pf *pf, struct i40e_dcbx_config *new_cfg)
 	if (need_reconfig) {
 		/* Enable DCB tagging only when more than one TC */
 		if (new_numtc > 1)
-			pf->flags |= I40E_FLAG_DCB_ENABLED;
+			set_bit(I40E_FLAG_DCB_ENA, pf->flags);
 		else
-			pf->flags &= ~I40E_FLAG_DCB_ENABLED;
+			clear_bit(I40E_FLAG_DCB_ENA, pf->flags);
 
 		set_bit(__I40E_PORT_SUSPENDED, pf->state);
 		/* Reconfiguration needed quiesce all VSIs */
@@ -7080,7 +7085,7 @@ out:
 			set_bit(__I40E_CLIENT_L2_CHANGE, pf->state);
 		}
 		/* registers are set, lets apply */
-		if (pf->hw_features & I40E_HW_USE_SET_LLDP_MIB)
+		if (test_bit(I40E_HW_CAP_USE_SET_LLDP_MIB, pf->hw.caps))
 			ret = i40e_hw_set_dcb_config(pf, new_cfg);
 	}
 
@@ -7101,7 +7106,7 @@ int i40e_dcb_sw_default_config(struct i40e_pf *pf)
 	struct i40e_hw *hw = &pf->hw;
 	int err;
 
-	if (pf->hw_features & I40E_HW_USE_SET_LLDP_MIB) {
+	if (test_bit(I40E_HW_CAP_USE_SET_LLDP_MIB, pf->hw.caps)) {
 		/* Update the local cached instance with TC0 ETS */
 		memset(&pf->tmp_cfg, 0, sizeof(struct i40e_dcbx_config));
 		pf->tmp_cfg.etscfg.willing = I40E_IEEE_DEFAULT_ETS_WILLING;
@@ -7162,12 +7167,12 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf)
 	/* Do not enable DCB for SW1 and SW2 images even if the FW is capable
 	 * Also do not enable DCBx if FW LLDP agent is disabled
 	 */
-	if (pf->hw_features & I40E_HW_NO_DCB_SUPPORT) {
+	if (test_bit(I40E_HW_CAP_NO_DCB_SUPPORT, pf->hw.caps)) {
 		dev_info(&pf->pdev->dev, "DCB is not supported.\n");
 		err = -EOPNOTSUPP;
 		goto out;
 	}
-	if (pf->flags & I40E_FLAG_DISABLE_FW_LLDP) {
+	if (test_bit(I40E_FLAG_FW_LLDP_DIS, pf->flags)) {
 		dev_info(&pf->pdev->dev, "FW LLDP is disabled, attempting SW DCB\n");
 		err = i40e_dcb_sw_default_config(pf);
 		if (err) {
@@ -7178,8 +7183,8 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf)
 		pf->dcbx_cap = DCB_CAP_DCBX_HOST |
 			       DCB_CAP_DCBX_VER_IEEE;
 		/* at init capable but disabled */
-		pf->flags |= I40E_FLAG_DCB_CAPABLE;
-		pf->flags &= ~I40E_FLAG_DCB_ENABLED;
+		set_bit(I40E_FLAG_DCB_CAPABLE, pf->flags);
+		clear_bit(I40E_FLAG_DCB_ENA, pf->flags);
 		goto out;
 	}
 	err = i40e_init_dcb(hw, true);
@@ -7194,20 +7199,20 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf)
 			pf->dcbx_cap = DCB_CAP_DCBX_LLD_MANAGED |
 				       DCB_CAP_DCBX_VER_IEEE;
 
-			pf->flags |= I40E_FLAG_DCB_CAPABLE;
+			set_bit(I40E_FLAG_DCB_CAPABLE, pf->flags);
 			/* Enable DCB tagging only when more than one TC
 			 * or explicitly disable if only one TC
 			 */
 			if (i40e_dcb_get_num_tc(&hw->local_dcbx_config) > 1)
-				pf->flags |= I40E_FLAG_DCB_ENABLED;
+				set_bit(I40E_FLAG_DCB_ENA, pf->flags);
 			else
-				pf->flags &= ~I40E_FLAG_DCB_ENABLED;
+				clear_bit(I40E_FLAG_DCB_ENA, pf->flags);
 			dev_dbg(&pf->pdev->dev,
 				"DCBX offload is supported for this PF.\n");
 		}
 	} else if (pf->hw.aq.asq_last_status == I40E_AQ_RC_EPERM) {
 		dev_info(&pf->pdev->dev, "FW LLDP disabled for this PF.\n");
-		pf->flags |= I40E_FLAG_DISABLE_FW_LLDP;
+		set_bit(I40E_FLAG_FW_LLDP_DIS, pf->flags);
 	} else {
 		dev_info(&pf->pdev->dev,
 			 "Query for DCB configuration failed, err %pe aq_err %s\n",
@@ -7367,7 +7372,7 @@ static int i40e_up_complete(struct i40e_vsi *vsi)
 	struct i40e_pf *pf = vsi->back;
 	int err;
 
-	if (pf->flags & I40E_FLAG_MSIX_ENABLED)
+	if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags))
 		i40e_vsi_configure_msix(vsi);
 	else
 		i40e_configure_msi_and_legacy(vsi);
@@ -7471,7 +7476,7 @@ static int i40e_force_link_state(struct i40e_pf *pf, bool is_up)
 	 * and its speed values are OK, no need for a flap
 	 * if non_zero_phy_type was set, still need to force up
 	 */
-	if (pf->flags & I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED)
+	if (test_bit(I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENA, pf->flags))
 		non_zero_phy_type = true;
 	else if (is_up && abilities.phy_type != 0 && abilities.link_speed != 0)
 		return 0;
@@ -7487,7 +7492,7 @@ static int i40e_force_link_state(struct i40e_pf *pf, bool is_up)
 		non_zero_phy_type ? (u8)((mask >> 32) & 0xff) : 0;
 	/* Copy the old settings, except of phy_type */
 	config.abilities = abilities.abilities;
-	if (pf->flags & I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED) {
+	if (test_bit(I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENA, pf->flags)) {
 		if (is_up)
 			config.abilities |= I40E_AQ_PHY_ENABLE_LINK;
 		else
@@ -7537,8 +7542,8 @@ int i40e_up(struct i40e_vsi *vsi)
 	int err;
 
 	if (vsi->type == I40E_VSI_MAIN &&
-	    (vsi->back->flags & I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED ||
-	     vsi->back->flags & I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED))
+	    (test_bit(I40E_FLAG_LINK_DOWN_ON_CLOSE_ENA, vsi->back->flags) ||
+	     test_bit(I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENA, vsi->back->flags)))
 		i40e_force_link_state(vsi->back, true);
 
 	err = i40e_vsi_configure(vsi);
@@ -7566,8 +7571,8 @@ void i40e_down(struct i40e_vsi *vsi)
 	i40e_vsi_disable_irq(vsi);
 	i40e_vsi_stop_rings(vsi);
 	if (vsi->type == I40E_VSI_MAIN &&
-	   (vsi->back->flags & I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED ||
-	    vsi->back->flags & I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED))
+	   (test_bit(I40E_FLAG_LINK_DOWN_ON_CLOSE_ENA, vsi->back->flags) ||
+	    test_bit(I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENA, vsi->back->flags)))
 		i40e_force_link_state(vsi->back, false);
 	i40e_napi_disable_all(vsi);
 
@@ -7973,7 +7978,7 @@ static void *i40e_fwd_add(struct net_device *netdev, struct net_device *vdev)
 	struct i40e_fwd_adapter *fwd;
 	int avail_macvlan, ret;
 
-	if ((pf->flags & I40E_FLAG_DCB_ENABLED)) {
+	if (test_bit(I40E_FLAG_DCB_ENA, pf->flags)) {
 		netdev_info(netdev, "Macvlans are not supported when DCB is enabled\n");
 		return ERR_PTR(-EINVAL);
 	}
@@ -8168,23 +8173,23 @@ static int i40e_setup_tc(struct net_device *netdev, void *type_data)
 	hw = mqprio_qopt->qopt.hw;
 	mode = mqprio_qopt->mode;
 	if (!hw) {
-		pf->flags &= ~I40E_FLAG_TC_MQPRIO;
+		clear_bit(I40E_FLAG_TC_MQPRIO_ENA, pf->flags);
 		memcpy(&vsi->mqprio_qopt, mqprio_qopt, sizeof(*mqprio_qopt));
 		goto config_tc;
 	}
 
 	/* Check if MFP enabled */
-	if (pf->flags & I40E_FLAG_MFP_ENABLED) {
+	if (test_bit(I40E_FLAG_MFP_ENA, pf->flags)) {
 		netdev_info(netdev,
 			    "Configuring TC not supported in MFP mode\n");
 		return ret;
 	}
 	switch (mode) {
 	case TC_MQPRIO_MODE_DCB:
-		pf->flags &= ~I40E_FLAG_TC_MQPRIO;
+		clear_bit(I40E_FLAG_TC_MQPRIO_ENA, pf->flags);
 
 		/* Check if DCB enabled to continue */
-		if (!(pf->flags & I40E_FLAG_DCB_ENABLED)) {
+		if (!test_bit(I40E_FLAG_DCB_ENA, pf->flags)) {
 			netdev_info(netdev,
 				    "DCB is not enabled for adapter\n");
 			return ret;
@@ -8198,20 +8203,20 @@ static int i40e_setup_tc(struct net_device *netdev, void *type_data)
 		}
 		break;
 	case TC_MQPRIO_MODE_CHANNEL:
-		if (pf->flags & I40E_FLAG_DCB_ENABLED) {
+		if (test_bit(I40E_FLAG_DCB_ENA, pf->flags)) {
 			netdev_info(netdev,
 				    "Full offload of TC Mqprio options is not supported when DCB is enabled\n");
 			return ret;
 		}
-		if (!(pf->flags & I40E_FLAG_MSIX_ENABLED))
+		if (!test_bit(I40E_FLAG_MSIX_ENA, pf->flags))
 			return ret;
 		ret = i40e_validate_mqprio_qopt(vsi, mqprio_qopt);
 		if (ret)
 			return ret;
 		memcpy(&vsi->mqprio_qopt, mqprio_qopt,
 		       sizeof(*mqprio_qopt));
-		pf->flags |= I40E_FLAG_TC_MQPRIO;
-		pf->flags &= ~I40E_FLAG_DCB_ENABLED;
+		set_bit(I40E_FLAG_TC_MQPRIO_ENA, pf->flags);
+		clear_bit(I40E_FLAG_DCB_ENA, pf->flags);
 		break;
 	default:
 		return -EINVAL;
@@ -8795,11 +8800,11 @@ static int i40e_configure_clsflower(struct i40e_vsi *vsi,
 		return -EINVAL;
 	}
 
-	if (vsi->back->flags & I40E_FLAG_FD_SB_ENABLED) {
+	if (test_bit(I40E_FLAG_FD_SB_ENA, vsi->back->flags)) {
 		dev_err(&vsi->back->pdev->dev,
 			"Disable Flow Director Sideband, configuring Cloud filters via tc-flower\n");
-		vsi->back->flags &= ~I40E_FLAG_FD_SB_ENABLED;
-		vsi->back->flags |= I40E_FLAG_FD_SB_TO_CLOUD_FILTER;
+		clear_bit(I40E_FLAG_FD_SB_ENA, vsi->back->flags);
+		clear_bit(I40E_FLAG_FD_SB_TO_CLOUD_FILTER, vsi->back->flags);
 	}
 
 	filter = kzalloc(sizeof(*filter), GFP_KERNEL);
@@ -8895,11 +8900,11 @@ static int i40e_delete_clsflower(struct i40e_vsi *vsi,
 
 	pf->num_cloud_filters--;
 	if (!pf->num_cloud_filters)
-		if ((pf->flags & I40E_FLAG_FD_SB_TO_CLOUD_FILTER) &&
-		    !(pf->flags & I40E_FLAG_FD_SB_INACTIVE)) {
-			pf->flags |= I40E_FLAG_FD_SB_ENABLED;
-			pf->flags &= ~I40E_FLAG_FD_SB_TO_CLOUD_FILTER;
-			pf->flags &= ~I40E_FLAG_FD_SB_INACTIVE;
+		if (test_bit(I40E_FLAG_FD_SB_TO_CLOUD_FILTER, pf->flags) &&
+		    !test_bit(I40E_FLAG_FD_SB_INACTIVE, pf->flags)) {
+			set_bit(I40E_FLAG_FD_SB_ENA, pf->flags);
+			clear_bit(I40E_FLAG_FD_SB_TO_CLOUD_FILTER, pf->flags);
+			clear_bit(I40E_FLAG_FD_SB_INACTIVE, pf->flags);
 		}
 	return 0;
 }
@@ -9200,11 +9205,11 @@ static void i40e_cloud_filter_exit(struct i40e_pf *pf)
 	}
 	pf->num_cloud_filters = 0;
 
-	if ((pf->flags & I40E_FLAG_FD_SB_TO_CLOUD_FILTER) &&
-	    !(pf->flags & I40E_FLAG_FD_SB_INACTIVE)) {
-		pf->flags |= I40E_FLAG_FD_SB_ENABLED;
-		pf->flags &= ~I40E_FLAG_FD_SB_TO_CLOUD_FILTER;
-		pf->flags &= ~I40E_FLAG_FD_SB_INACTIVE;
+	if (test_bit(I40E_FLAG_FD_SB_TO_CLOUD_FILTER, pf->flags) &&
+	    !test_bit(I40E_FLAG_FD_SB_INACTIVE, pf->flags)) {
+		set_bit(I40E_FLAG_FD_SB_ENA, pf->flags);
+		clear_bit(I40E_FLAG_FD_SB_TO_CLOUD_FILTER, pf->flags);
+		clear_bit(I40E_FLAG_FD_SB_INACTIVE, pf->flags);
 	}
 }
 
@@ -9292,7 +9297,7 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired)
 		i40e_prep_for_reset(pf);
 		i40e_reset_and_rebuild(pf, true, lock_acquired);
 		dev_info(&pf->pdev->dev,
-			 pf->flags & I40E_FLAG_DISABLE_FW_LLDP ?
+			 test_bit(I40E_FLAG_FW_LLDP_DIS, pf->flags) ?
 			 "FW LLDP is disabled\n" :
 			 "FW LLDP is enabled\n");
 
@@ -9407,12 +9412,12 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 	if (I40E_IS_X710TL_DEVICE(hw->device_id) &&
 	    (hw->phy.link_info.link_speed &
 	     ~(I40E_LINK_SPEED_2_5GB | I40E_LINK_SPEED_5GB)) &&
-	     !(pf->flags & I40E_FLAG_DCB_CAPABLE))
+	     !test_bit(I40E_FLAG_DCB_CAPABLE, pf->flags))
 		/* let firmware decide if the DCB should be disabled */
-		pf->flags |= I40E_FLAG_DCB_CAPABLE;
+		set_bit(I40E_FLAG_DCB_CAPABLE, pf->flags);
 
 	/* Not DCB capable or capability disabled */
-	if (!(pf->flags & I40E_FLAG_DCB_CAPABLE))
+	if (!test_bit(I40E_FLAG_DCB_CAPABLE, pf->flags))
 		return ret;
 
 	/* Ignore if event is not for Nearest Bridge */
@@ -9448,7 +9453,7 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 		     (I40E_LINK_SPEED_2_5GB | I40E_LINK_SPEED_5GB))) {
 			dev_warn(&pf->pdev->dev,
 				 "DCB is not supported for X710-T*L 2.5/5G speeds\n");
-			pf->flags &= ~I40E_FLAG_DCB_CAPABLE;
+			clear_bit(I40E_FLAG_DCB_CAPABLE, pf->flags);
 		} else {
 			dev_info(&pf->pdev->dev,
 				 "Failed querying DCB configuration data from firmware, err %pe aq_err %s\n",
@@ -9476,9 +9481,9 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 
 	/* Enable DCB tagging only when more than one TC */
 	if (i40e_dcb_get_num_tc(&hw->local_dcbx_config) > 1)
-		pf->flags |= I40E_FLAG_DCB_ENABLED;
+		set_bit(I40E_FLAG_DCB_ENA, pf->flags);
 	else
-		pf->flags &= ~I40E_FLAG_DCB_ENABLED;
+		clear_bit(I40E_FLAG_DCB_ENA, pf->flags);
 
 	set_bit(__I40E_PORT_SUSPENDED, pf->state);
 	/* Reconfiguration needed quiesce all VSIs */
@@ -9546,18 +9551,18 @@ static void i40e_handle_lan_overflow_event(struct i40e_pf *pf,
 	dev_dbg(&pf->pdev->dev, "overflow Rx Queue Number = %d QTX_CTL=0x%08x\n",
 		queue, qtx_ctl);
 
+	if (FIELD_GET(I40E_QTX_CTL_PFVF_Q_MASK, qtx_ctl) !=
+	    I40E_QTX_CTL_VF_QUEUE)
+		return;
+
 	/* Queue belongs to VF, find the VF and issue VF reset */
-	if (((qtx_ctl & I40E_QTX_CTL_PFVF_Q_MASK)
-	    >> I40E_QTX_CTL_PFVF_Q_SHIFT) == I40E_QTX_CTL_VF_QUEUE) {
-		vf_id = (u16)((qtx_ctl & I40E_QTX_CTL_VFVM_INDX_MASK)
-			 >> I40E_QTX_CTL_VFVM_INDX_SHIFT);
-		vf_id -= hw->func_caps.vf_base_id;
-		vf = &pf->vf[vf_id];
-		i40e_vc_notify_vf_reset(vf);
-		/* Allow VF to process pending reset notification */
-		msleep(20);
-		i40e_reset_vf(vf, false);
-	}
+	vf_id = FIELD_GET(I40E_QTX_CTL_VFVM_INDX_MASK, qtx_ctl);
+	vf_id -= hw->func_caps.vf_base_id;
+	vf = &pf->vf[vf_id];
+	i40e_vc_notify_vf_reset(vf);
+	/* Allow VF to process pending reset notification */
+	msleep(20);
+	i40e_reset_vf(vf, false);
 }
 
 /**
@@ -9583,8 +9588,7 @@ u32 i40e_get_current_fd_count(struct i40e_pf *pf)
 
 	val = rd32(&pf->hw, I40E_PFQF_FDSTAT);
 	fcnt_prog = (val & I40E_PFQF_FDSTAT_GUARANT_CNT_MASK) +
-		    ((val & I40E_PFQF_FDSTAT_BEST_CNT_MASK) >>
-		      I40E_PFQF_FDSTAT_BEST_CNT_SHIFT);
+		    FIELD_GET(I40E_PFQF_FDSTAT_BEST_CNT_MASK, val);
 	return fcnt_prog;
 }
 
@@ -9598,8 +9602,7 @@ u32 i40e_get_global_fd_count(struct i40e_pf *pf)
 
 	val = rd32(&pf->hw, I40E_GLQF_FDCNT_0);
 	fcnt_prog = (val & I40E_GLQF_FDCNT_0_GUARANT_CNT_MASK) +
-		    ((val & I40E_GLQF_FDCNT_0_BESTCNT_MASK) >>
-		     I40E_GLQF_FDCNT_0_BESTCNT_SHIFT);
+		    FIELD_GET(I40E_GLQF_FDCNT_0_BESTCNT_MASK, val);
 	return fcnt_prog;
 }
 
@@ -9610,7 +9613,7 @@ u32 i40e_get_global_fd_count(struct i40e_pf *pf)
 static void i40e_reenable_fdir_sb(struct i40e_pf *pf)
 {
 	if (test_and_clear_bit(__I40E_FD_SB_AUTO_DISABLED, pf->state))
-		if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) &&
+		if (test_bit(I40E_FLAG_FD_SB_ENA, pf->flags) &&
 		    (I40E_DEBUG_FD & pf->hw.debug_mask))
 			dev_info(&pf->pdev->dev, "FD Sideband/ntuple is being enabled since we have space in the table now\n");
 }
@@ -9631,7 +9634,7 @@ static void i40e_reenable_fdir_atr(struct i40e_pf *pf)
 					I40E_L3_SRC_MASK | I40E_L3_DST_MASK |
 					I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
 
-		if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
+		if (test_bit(I40E_FLAG_FD_ATR_ENA, pf->flags) &&
 		    (I40E_DEBUG_FD & pf->hw.debug_mask))
 			dev_info(&pf->pdev->dev, "ATR is being enabled since we have space in the table and there are no conflicting ntuple rules\n");
 	}
@@ -9946,7 +9949,7 @@ static void i40e_link_event(struct i40e_pf *pf)
 	if (pf->vf)
 		i40e_vc_notify_link_state(pf);
 
-	if (pf->flags & I40E_FLAG_PTP)
+	if (test_bit(I40E_FLAG_PTP_ENA, pf->flags))
 		i40e_ptp_set_increment(pf);
 #ifdef CONFIG_I40E_DCB
 	if (new_link == old_link)
@@ -9963,13 +9966,13 @@ static void i40e_link_event(struct i40e_pf *pf)
 		memset(&pf->tmp_cfg, 0, sizeof(pf->tmp_cfg));
 		err = i40e_dcb_sw_default_config(pf);
 		if (err) {
-			pf->flags &= ~(I40E_FLAG_DCB_CAPABLE |
-				       I40E_FLAG_DCB_ENABLED);
+			clear_bit(I40E_FLAG_DCB_CAPABLE, pf->flags);
+			clear_bit(I40E_FLAG_DCB_ENA, pf->flags);
 		} else {
 			pf->dcbx_cap = DCB_CAP_DCBX_HOST |
 				       DCB_CAP_DCBX_VER_IEEE;
-			pf->flags |= I40E_FLAG_DCB_CAPABLE;
-			pf->flags &= ~I40E_FLAG_DCB_ENABLED;
+			set_bit(I40E_FLAG_DCB_CAPABLE, pf->flags);
+			clear_bit(I40E_FLAG_DCB_ENA, pf->flags);
 		}
 	}
 #endif /* CONFIG_I40E_DCB */
@@ -9994,7 +9997,7 @@ static void i40e_watchdog_subtask(struct i40e_pf *pf)
 		return;
 	pf->service_timer_previous = jiffies;
 
-	if ((pf->flags & I40E_FLAG_LINK_POLLING_ENABLED) ||
+	if (test_bit(I40E_FLAG_LINK_POLLING_ENA, pf->flags) ||
 	    test_bit(__I40E_TEMP_LINK_POLLING, pf->state))
 		i40e_link_event(pf);
 
@@ -10005,7 +10008,7 @@ static void i40e_watchdog_subtask(struct i40e_pf *pf)
 		if (pf->vsi[i] && pf->vsi[i]->netdev)
 			i40e_update_stats(pf->vsi[i]);
 
-	if (pf->flags & I40E_FLAG_VEB_STATS_ENABLED) {
+	if (test_bit(I40E_FLAG_VEB_STATS_ENA, pf->flags)) {
 		/* Update the stats for the active switching components */
 		for (i = 0; i < I40E_MAX_VEB; i++)
 			if (pf->veb[i])
@@ -10094,7 +10097,7 @@ static void i40e_handle_link_event(struct i40e_pf *pf,
 		if ((status->link_info & I40E_AQ_MEDIA_AVAILABLE) &&
 		    (!(status->an_info & I40E_AQ_QUALIFIED_MODULE)) &&
 		    (!(status->link_info & I40E_AQ_LINK_UP)) &&
-		    (!(pf->flags & I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED))) {
+		    (!test_bit(I40E_FLAG_LINK_DOWN_ON_CLOSE_ENA, pf->flags))) {
 			dev_err(&pf->pdev->dev,
 				"Rx/Tx is disabled on this device because an unsupported SFP module type was detected.\n");
 			dev_err(&pf->pdev->dev,
@@ -10122,7 +10125,7 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf)
 		return;
 
 	/* check for error indications */
-	val = rd32(&pf->hw, pf->hw.aq.arq.len);
+	val = rd32(&pf->hw, I40E_PF_ARQLEN);
 	oldval = val;
 	if (val & I40E_PF_ARQLEN_ARQVFE_MASK) {
 		if (hw->debug_mask & I40E_DEBUG_AQ)
@@ -10141,9 +10144,9 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf)
 		val &= ~I40E_PF_ARQLEN_ARQCRIT_MASK;
 	}
 	if (oldval != val)
-		wr32(&pf->hw, pf->hw.aq.arq.len, val);
+		wr32(&pf->hw, I40E_PF_ARQLEN, val);
 
-	val = rd32(&pf->hw, pf->hw.aq.asq.len);
+	val = rd32(&pf->hw, I40E_PF_ATQLEN);
 	oldval = val;
 	if (val & I40E_PF_ATQLEN_ATQVFE_MASK) {
 		if (pf->hw.debug_mask & I40E_DEBUG_AQ)
@@ -10161,7 +10164,7 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf)
 		val &= ~I40E_PF_ATQLEN_ATQCRIT_MASK;
 	}
 	if (oldval != val)
-		wr32(&pf->hw, pf->hw.aq.asq.len, val);
+		wr32(&pf->hw, I40E_PF_ATQLEN, val);
 
 	event.buf_len = I40E_MAX_AQ_BUF_SIZE;
 	event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL);
@@ -10221,9 +10224,9 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf)
 				 opcode);
 			break;
 		}
-	} while (i++ < pf->adminq_work_limit);
+	} while (i++ < I40E_AQ_WORK_LIMIT);
 
-	if (i < pf->adminq_work_limit)
+	if (i < I40E_AQ_WORK_LIMIT)
 		clear_bit(__I40E_ADMINQ_EVENT_PENDING, pf->state);
 
 	/* re-enable Admin queue interrupt cause */
@@ -10400,7 +10403,7 @@ static int i40e_reconstitute_veb(struct i40e_veb *veb)
 	if (ret)
 		goto end_reconstitute;
 
-	if (pf->flags & I40E_FLAG_VEB_MODE_ENABLED)
+	if (test_bit(I40E_FLAG_VEB_MODE_ENA, pf->flags))
 		veb->bridge_mode = BRIDGE_MODE_VEB;
 	else
 		veb->bridge_mode = BRIDGE_MODE_VEPA;
@@ -10545,7 +10548,7 @@ static void i40e_fdir_sb_setup(struct i40e_pf *pf)
 			wr32(&pf->hw, I40E_GLQF_HKEY(i), hkey[i]);
 	}
 
-	if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED))
+	if (!test_bit(I40E_FLAG_FD_SB_ENA, pf->flags))
 		return;
 
 	/* find existing VSI and see if it needs configuring */
@@ -10557,8 +10560,8 @@ static void i40e_fdir_sb_setup(struct i40e_pf *pf)
 				     pf->vsi[pf->lan_vsi]->seid, 0);
 		if (!vsi) {
 			dev_info(&pf->pdev->dev, "Couldn't create FDir VSI\n");
-			pf->flags &= ~I40E_FLAG_FD_SB_ENABLED;
-			pf->flags |= I40E_FLAG_FD_SB_INACTIVE;
+			clear_bit(I40E_FLAG_FD_SB_ENA, pf->flags);
+			set_bit(I40E_FLAG_FD_SB_INACTIVE, pf->flags);
 			return;
 		}
 	}
@@ -10936,14 +10939,14 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 			i40e_aq_set_dcb_parameters(hw, false, NULL);
 			dev_warn(&pf->pdev->dev,
 				 "DCB is not supported for X710-T*L 2.5/5G speeds\n");
-			pf->flags &= ~I40E_FLAG_DCB_CAPABLE;
+			clear_bit(I40E_FLAG_DCB_CAPABLE, pf->flags);
 		} else {
 			i40e_aq_set_dcb_parameters(hw, true, NULL);
 			ret = i40e_init_pf_dcb(pf);
 			if (ret) {
 				dev_info(&pf->pdev->dev, "DCB init failed %d, disabled\n",
 					 ret);
-				pf->flags &= ~I40E_FLAG_DCB_CAPABLE;
+				clear_bit(I40E_FLAG_DCB_CAPABLE, pf->flags);
 				/* Continue without DCB enabled */
 			}
 		}
@@ -11064,7 +11067,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 		wr32(hw, I40E_REG_MSS, val);
 	}
 
-	if (pf->hw_features & I40E_HW_RESTART_AUTONEG) {
+	if (test_bit(I40E_HW_CAP_RESTART_AUTONEG, pf->hw.caps)) {
 		msleep(75);
 		ret = i40e_aq_set_link_restart_an(&pf->hw, true, NULL);
 		if (ret)
@@ -11074,7 +11077,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 					     pf->hw.aq.asq_last_status));
 	}
 	/* reinit the misc interrupt */
-	if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+	if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags)) {
 		ret = i40e_setup_misc_vector(pf);
 		if (ret)
 			goto end_unlock;
@@ -11181,14 +11184,10 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 	/* find what triggered the MDD event */
 	reg = rd32(hw, I40E_GL_MDET_TX);
 	if (reg & I40E_GL_MDET_TX_VALID_MASK) {
-		u8 pf_num = (reg & I40E_GL_MDET_TX_PF_NUM_MASK) >>
-				I40E_GL_MDET_TX_PF_NUM_SHIFT;
-		u16 vf_num = (reg & I40E_GL_MDET_TX_VF_NUM_MASK) >>
-				I40E_GL_MDET_TX_VF_NUM_SHIFT;
-		u8 event = (reg & I40E_GL_MDET_TX_EVENT_MASK) >>
-				I40E_GL_MDET_TX_EVENT_SHIFT;
-		u16 queue = ((reg & I40E_GL_MDET_TX_QUEUE_MASK) >>
-				I40E_GL_MDET_TX_QUEUE_SHIFT) -
+		u8 pf_num = FIELD_GET(I40E_GL_MDET_TX_PF_NUM_MASK, reg);
+		u16 vf_num = FIELD_GET(I40E_GL_MDET_TX_VF_NUM_MASK, reg);
+		u8 event = FIELD_GET(I40E_GL_MDET_TX_EVENT_MASK, reg);
+		u16 queue = FIELD_GET(I40E_GL_MDET_TX_QUEUE_MASK, reg) -
 				pf->hw.func_caps.base_queue;
 		if (netif_msg_tx_err(pf))
 			dev_info(&pf->pdev->dev, "Malicious Driver Detection event 0x%02x on TX queue %d PF number 0x%02x VF number 0x%02x\n",
@@ -11198,12 +11197,9 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 	}
 	reg = rd32(hw, I40E_GL_MDET_RX);
 	if (reg & I40E_GL_MDET_RX_VALID_MASK) {
-		u8 func = (reg & I40E_GL_MDET_RX_FUNCTION_MASK) >>
-				I40E_GL_MDET_RX_FUNCTION_SHIFT;
-		u8 event = (reg & I40E_GL_MDET_RX_EVENT_MASK) >>
-				I40E_GL_MDET_RX_EVENT_SHIFT;
-		u16 queue = ((reg & I40E_GL_MDET_RX_QUEUE_MASK) >>
-				I40E_GL_MDET_RX_QUEUE_SHIFT) -
+		u8 func = FIELD_GET(I40E_GL_MDET_RX_FUNCTION_MASK, reg);
+		u8 event = FIELD_GET(I40E_GL_MDET_RX_EVENT_MASK, reg);
+		u16 queue = FIELD_GET(I40E_GL_MDET_RX_QUEUE_MASK, reg) -
 				pf->hw.func_caps.base_queue;
 		if (netif_msg_rx_err(pf))
 			dev_info(&pf->pdev->dev, "Malicious Driver Detection event 0x%02x on RX queue %d of function 0x%02x\n",
@@ -11349,7 +11345,7 @@ static int i40e_set_num_rings_in_vsi(struct i40e_vsi *vsi)
 		if (!vsi->num_rx_desc)
 			vsi->num_rx_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
 						 I40E_REQ_DESCRIPTOR_MULTIPLE);
-		if (pf->flags & I40E_FLAG_MSIX_ENABLED)
+		if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags))
 			vsi->num_q_vectors = pf->num_lan_msix;
 		else
 			vsi->num_q_vectors = 1;
@@ -11667,7 +11663,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi)
 		ring->count = vsi->num_tx_desc;
 		ring->size = 0;
 		ring->dcb_tc = 0;
-		if (vsi->back->hw_features & I40E_HW_WB_ON_ITR_CAPABLE)
+		if (test_bit(I40E_HW_CAP_WB_ON_ITR, vsi->back->hw.caps))
 			ring->flags = I40E_TXR_FLAGS_WB_ON_ITR;
 		ring->itr_setting = pf->tx_itr_default;
 		WRITE_ONCE(vsi->tx_rings[i], ring++);
@@ -11684,7 +11680,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi)
 		ring->count = vsi->num_tx_desc;
 		ring->size = 0;
 		ring->dcb_tc = 0;
-		if (vsi->back->hw_features & I40E_HW_WB_ON_ITR_CAPABLE)
+		if (test_bit(I40E_HW_CAP_WB_ON_ITR, vsi->back->hw.caps))
 			ring->flags = I40E_TXR_FLAGS_WB_ON_ITR;
 		set_ring_xdp(ring);
 		ring->itr_setting = pf->tx_itr_default;
@@ -11748,7 +11744,7 @@ static int i40e_init_msix(struct i40e_pf *pf)
 	int v_actual;
 	int iwarp_requested = 0;
 
-	if (!(pf->flags & I40E_FLAG_MSIX_ENABLED))
+	if (!test_bit(I40E_FLAG_MSIX_ENA, pf->flags))
 		return -ENODEV;
 
 	/* The number of vectors we'll request will be comprised of:
@@ -11787,7 +11783,7 @@ static int i40e_init_msix(struct i40e_pf *pf)
 	vectors_left -= pf->num_lan_msix;
 
 	/* reserve one vector for sideband flow director */
-	if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
+	if (test_bit(I40E_FLAG_FD_SB_ENA, pf->flags)) {
 		if (vectors_left) {
 			pf->num_fdsb_msix = 1;
 			v_budget++;
@@ -11798,7 +11794,7 @@ static int i40e_init_msix(struct i40e_pf *pf)
 	}
 
 	/* can we reserve enough for iWARP? */
-	if (pf->flags & I40E_FLAG_IWARP_ENABLED) {
+	if (test_bit(I40E_FLAG_IWARP_ENA, pf->flags)) {
 		iwarp_requested = pf->num_iwarp_msix;
 
 		if (!vectors_left)
@@ -11810,7 +11806,7 @@ static int i40e_init_msix(struct i40e_pf *pf)
 	}
 
 	/* any vectors left over go for VMDq support */
-	if (pf->flags & I40E_FLAG_VMDQ_ENABLED) {
+	if (test_bit(I40E_FLAG_VMDQ_ENA, pf->flags)) {
 		if (!vectors_left) {
 			pf->num_vmdq_msix = 0;
 			pf->num_vmdq_qps = 0;
@@ -11867,7 +11863,7 @@ static int i40e_init_msix(struct i40e_pf *pf)
 	v_actual = i40e_reserve_msix_vectors(pf, v_budget);
 
 	if (v_actual < I40E_MIN_MSIX) {
-		pf->flags &= ~I40E_FLAG_MSIX_ENABLED;
+		clear_bit(I40E_FLAG_MSIX_ENA, pf->flags);
 		kfree(pf->msix_entries);
 		pf->msix_entries = NULL;
 		pci_disable_msix(pf->pdev);
@@ -11905,7 +11901,7 @@ static int i40e_init_msix(struct i40e_pf *pf)
 			pf->num_lan_msix = 1;
 			break;
 		case 3:
-			if (pf->flags & I40E_FLAG_IWARP_ENABLED) {
+			if (test_bit(I40E_FLAG_IWARP_ENA, pf->flags)) {
 				pf->num_lan_msix = 1;
 				pf->num_iwarp_msix = 1;
 			} else {
@@ -11913,7 +11909,7 @@ static int i40e_init_msix(struct i40e_pf *pf)
 			}
 			break;
 		default:
-			if (pf->flags & I40E_FLAG_IWARP_ENABLED) {
+			if (test_bit(I40E_FLAG_IWARP_ENA, pf->flags)) {
 				pf->num_iwarp_msix = min_t(int, (vec / 3),
 						 iwarp_requested);
 				pf->num_vmdq_vsis = min_t(int, (vec / 3),
@@ -11922,7 +11918,7 @@ static int i40e_init_msix(struct i40e_pf *pf)
 				pf->num_vmdq_vsis = min_t(int, (vec / 2),
 						  I40E_DEFAULT_NUM_VMDQ_VSI);
 			}
-			if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
+			if (test_bit(I40E_FLAG_FD_SB_ENA, pf->flags)) {
 				pf->num_fdsb_msix = 1;
 				vec--;
 			}
@@ -11934,22 +11930,20 @@ static int i40e_init_msix(struct i40e_pf *pf)
 		}
 	}
 
-	if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) &&
-	    (pf->num_fdsb_msix == 0)) {
+	if (test_bit(I40E_FLAG_FD_SB_ENA, pf->flags) && pf->num_fdsb_msix == 0) {
 		dev_info(&pf->pdev->dev, "Sideband Flowdir disabled, not enough MSI-X vectors\n");
-		pf->flags &= ~I40E_FLAG_FD_SB_ENABLED;
-		pf->flags |= I40E_FLAG_FD_SB_INACTIVE;
+		clear_bit(I40E_FLAG_FD_SB_ENA, pf->flags);
+		set_bit(I40E_FLAG_FD_SB_INACTIVE, pf->flags);
 	}
-	if ((pf->flags & I40E_FLAG_VMDQ_ENABLED) &&
-	    (pf->num_vmdq_msix == 0)) {
+	if (test_bit(I40E_FLAG_VMDQ_ENA, pf->flags) && pf->num_vmdq_msix == 0) {
 		dev_info(&pf->pdev->dev, "VMDq disabled, not enough MSI-X vectors\n");
-		pf->flags &= ~I40E_FLAG_VMDQ_ENABLED;
+		clear_bit(I40E_FLAG_VMDQ_ENA, pf->flags);
 	}
 
-	if ((pf->flags & I40E_FLAG_IWARP_ENABLED) &&
-	    (pf->num_iwarp_msix == 0)) {
+	if (test_bit(I40E_FLAG_IWARP_ENA, pf->flags) &&
+	    pf->num_iwarp_msix == 0) {
 		dev_info(&pf->pdev->dev, "IWARP disabled, not enough MSI-X vectors\n");
-		pf->flags &= ~I40E_FLAG_IWARP_ENABLED;
+		clear_bit(I40E_FLAG_IWARP_ENA, pf->flags);
 	}
 	i40e_debug(&pf->hw, I40E_DEBUG_INIT,
 		   "MSI-X vector distribution: PF %d, VMDq %d, FDSB %d, iWARP %d\n",
@@ -12003,7 +11997,7 @@ static int i40e_vsi_alloc_q_vectors(struct i40e_vsi *vsi)
 	int err, v_idx, num_q_vectors;
 
 	/* if not MSIX, give the one vector only to the LAN VSI */
-	if (pf->flags & I40E_FLAG_MSIX_ENABLED)
+	if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags))
 		num_q_vectors = vsi->num_q_vectors;
 	else if (vsi == pf->vsi[pf->lan_vsi])
 		num_q_vectors = 1;
@@ -12034,38 +12028,39 @@ static int i40e_init_interrupt_scheme(struct i40e_pf *pf)
 	int vectors = 0;
 	ssize_t size;
 
-	if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+	if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags)) {
 		vectors = i40e_init_msix(pf);
 		if (vectors < 0) {
-			pf->flags &= ~(I40E_FLAG_MSIX_ENABLED	|
-				       I40E_FLAG_IWARP_ENABLED	|
-				       I40E_FLAG_RSS_ENABLED	|
-				       I40E_FLAG_DCB_CAPABLE	|
-				       I40E_FLAG_DCB_ENABLED	|
-				       I40E_FLAG_SRIOV_ENABLED	|
-				       I40E_FLAG_FD_SB_ENABLED	|
-				       I40E_FLAG_FD_ATR_ENABLED	|
-				       I40E_FLAG_VMDQ_ENABLED);
-			pf->flags |= I40E_FLAG_FD_SB_INACTIVE;
+			clear_bit(I40E_FLAG_MSIX_ENA, pf->flags);
+			clear_bit(I40E_FLAG_IWARP_ENA, pf->flags);
+			clear_bit(I40E_FLAG_RSS_ENA, pf->flags);
+			clear_bit(I40E_FLAG_DCB_CAPABLE, pf->flags);
+			clear_bit(I40E_FLAG_DCB_ENA, pf->flags);
+			clear_bit(I40E_FLAG_SRIOV_ENA, pf->flags);
+			clear_bit(I40E_FLAG_FD_SB_ENA, pf->flags);
+			clear_bit(I40E_FLAG_FD_ATR_ENA, pf->flags);
+			clear_bit(I40E_FLAG_VMDQ_ENA, pf->flags);
+			set_bit(I40E_FLAG_FD_SB_INACTIVE, pf->flags);
 
 			/* rework the queue expectations without MSIX */
 			i40e_determine_queue_usage(pf);
 		}
 	}
 
-	if (!(pf->flags & I40E_FLAG_MSIX_ENABLED) &&
-	    (pf->flags & I40E_FLAG_MSI_ENABLED)) {
+	if (!test_bit(I40E_FLAG_MSIX_ENA, pf->flags) &&
+	    test_bit(I40E_FLAG_MSI_ENA, pf->flags)) {
 		dev_info(&pf->pdev->dev, "MSI-X not available, trying MSI\n");
 		vectors = pci_enable_msi(pf->pdev);
 		if (vectors < 0) {
 			dev_info(&pf->pdev->dev, "MSI init failed - %d\n",
 				 vectors);
-			pf->flags &= ~I40E_FLAG_MSI_ENABLED;
+			clear_bit(I40E_FLAG_MSI_ENA, pf->flags);
 		}
 		vectors = 1;  /* one MSI or Legacy vector */
 	}
 
-	if (!(pf->flags & (I40E_FLAG_MSIX_ENABLED | I40E_FLAG_MSI_ENABLED)))
+	if (!test_bit(I40E_FLAG_MSI_ENA, pf->flags) &&
+	    !test_bit(I40E_FLAG_MSIX_ENA, pf->flags))
 		dev_info(&pf->pdev->dev, "MSI-X and MSI not available, falling back to Legacy IRQ\n");
 
 	/* set up vector assignment tracking */
@@ -12098,7 +12093,8 @@ static int i40e_restore_interrupt_scheme(struct i40e_pf *pf)
 	 * scheme. We need to re-enabled them here in order to attempt to
 	 * re-acquire the MSI or MSI-X vectors
 	 */
-	pf->flags |= (I40E_FLAG_MSIX_ENABLED | I40E_FLAG_MSI_ENABLED);
+	set_bit(I40E_FLAG_MSI_ENA, pf->flags);
+	set_bit(I40E_FLAG_MSIX_ENA, pf->flags);
 
 	err = i40e_init_interrupt_scheme(pf);
 	if (err)
@@ -12120,7 +12116,7 @@ static int i40e_restore_interrupt_scheme(struct i40e_pf *pf)
 	if (err)
 		goto err_unwind;
 
-	if (pf->flags & I40E_FLAG_IWARP_ENABLED)
+	if (test_bit(I40E_FLAG_IWARP_ENA, pf->flags))
 		i40e_client_update_msix_info(pf);
 
 	return 0;
@@ -12148,7 +12144,7 @@ static int i40e_setup_misc_vector_for_recovery_mode(struct i40e_pf *pf)
 {
 	int err;
 
-	if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+	if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags)) {
 		err = i40e_setup_misc_vector(pf);
 
 		if (err) {
@@ -12158,7 +12154,7 @@ static int i40e_setup_misc_vector_for_recovery_mode(struct i40e_pf *pf)
 			return err;
 		}
 	} else {
-		u32 flags = pf->flags & I40E_FLAG_MSI_ENABLED ? 0 : IRQF_SHARED;
+		u32 flags = test_bit(I40E_FLAG_MSI_ENA, pf->flags) ? 0 : IRQF_SHARED;
 
 		err = request_irq(pf->pdev->irq, i40e_intr, flags,
 				  pf->int_name, pf);
@@ -12362,7 +12358,7 @@ int i40e_config_rss(struct i40e_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
 {
 	struct i40e_pf *pf = vsi->back;
 
-	if (pf->hw_features & I40E_HW_RSS_AQ_CAPABLE)
+	if (test_bit(I40E_HW_CAP_RSS_AQ, pf->hw.caps))
 		return i40e_config_rss_aq(vsi, seed, lut, lut_size);
 	else
 		return i40e_config_rss_reg(vsi, seed, lut, lut_size);
@@ -12381,7 +12377,7 @@ int i40e_get_rss(struct i40e_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
 {
 	struct i40e_pf *pf = vsi->back;
 
-	if (pf->hw_features & I40E_HW_RSS_AQ_CAPABLE)
+	if (test_bit(I40E_HW_CAP_RSS_AQ, pf->hw.caps))
 		return i40e_get_rss_aq(vsi, seed, lut, lut_size);
 	else
 		return i40e_get_rss_reg(vsi, seed, lut, lut_size);
@@ -12484,7 +12480,7 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count)
 	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
 	int new_rss_size;
 
-	if (!(pf->flags & I40E_FLAG_RSS_ENABLED))
+	if (!test_bit(I40E_FLAG_RSS_ENA, pf->flags))
 		return 0;
 
 	queue_count = min_t(int, queue_count, num_online_cpus());
@@ -12717,9 +12713,9 @@ static int i40e_sw_init(struct i40e_pf *pf)
 	u16 pow;
 
 	/* Set default capability flags */
-	pf->flags = I40E_FLAG_RX_CSUM_ENABLED |
-		    I40E_FLAG_MSI_ENABLED     |
-		    I40E_FLAG_MSIX_ENABLED;
+	bitmap_zero(pf->flags, I40E_PF_FLAGS_NBITS);
+	set_bit(I40E_FLAG_MSI_ENA, pf->flags);
+	set_bit(I40E_FLAG_MSIX_ENA, pf->flags);
 
 	/* Set default ITR */
 	pf->rx_itr_default = I40E_ITR_RX_DEF;
@@ -12739,14 +12735,14 @@ static int i40e_sw_init(struct i40e_pf *pf)
 	pf->rss_size_max = min_t(int, pf->rss_size_max, pow);
 
 	if (pf->hw.func_caps.rss) {
-		pf->flags |= I40E_FLAG_RSS_ENABLED;
+		set_bit(I40E_FLAG_RSS_ENA, pf->flags);
 		pf->alloc_rss_size = min_t(int, pf->rss_size_max,
 					   num_online_cpus());
 	}
 
 	/* MFP mode enabled */
 	if (pf->hw.func_caps.npar_enable || pf->hw.func_caps.flex10_enable) {
-		pf->flags |= I40E_FLAG_MFP_ENABLED;
+		set_bit(I40E_FLAG_MFP_ENA, pf->flags);
 		dev_info(&pf->pdev->dev, "MFP mode Enabled\n");
 		if (i40e_get_partition_bw_setting(pf)) {
 			dev_warn(&pf->pdev->dev,
@@ -12763,84 +12759,31 @@ static int i40e_sw_init(struct i40e_pf *pf)
 
 	if ((pf->hw.func_caps.fd_filters_guaranteed > 0) ||
 	    (pf->hw.func_caps.fd_filters_best_effort > 0)) {
-		pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
-		pf->atr_sample_rate = I40E_DEFAULT_ATR_SAMPLE_RATE;
-		if (pf->flags & I40E_FLAG_MFP_ENABLED &&
+		set_bit(I40E_FLAG_FD_ATR_ENA, pf->flags);
+		if (test_bit(I40E_FLAG_MFP_ENA, pf->flags) &&
 		    pf->hw.num_partitions > 1)
 			dev_info(&pf->pdev->dev,
 				 "Flow Director Sideband mode Disabled in MFP mode\n");
 		else
-			pf->flags |= I40E_FLAG_FD_SB_ENABLED;
+			set_bit(I40E_FLAG_FD_SB_ENA, pf->flags);
 		pf->fdir_pf_filter_count =
 				 pf->hw.func_caps.fd_filters_guaranteed;
 		pf->hw.fdir_shared_filter_count =
 				 pf->hw.func_caps.fd_filters_best_effort;
 	}
 
-	if (pf->hw.mac.type == I40E_MAC_X722) {
-		pf->hw_features |= (I40E_HW_RSS_AQ_CAPABLE |
-				    I40E_HW_128_QP_RSS_CAPABLE |
-				    I40E_HW_ATR_EVICT_CAPABLE |
-				    I40E_HW_WB_ON_ITR_CAPABLE |
-				    I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE |
-				    I40E_HW_NO_PCI_LINK_CHECK |
-				    I40E_HW_USE_SET_LLDP_MIB |
-				    I40E_HW_GENEVE_OFFLOAD_CAPABLE |
-				    I40E_HW_PTP_L4_CAPABLE |
-				    I40E_HW_WOL_MC_MAGIC_PKT_WAKE |
-				    I40E_HW_OUTER_UDP_CSUM_CAPABLE);
-
-#define I40E_FDEVICT_PCTYPE_DEFAULT 0xc03
-		if (rd32(&pf->hw, I40E_GLQF_FDEVICTENA(1)) !=
-		    I40E_FDEVICT_PCTYPE_DEFAULT) {
-			dev_warn(&pf->pdev->dev,
-				 "FD EVICT PCTYPES are not right, disable FD HW EVICT\n");
-			pf->hw_features &= ~I40E_HW_ATR_EVICT_CAPABLE;
-		}
-	} else if ((pf->hw.aq.api_maj_ver > 1) ||
-		   ((pf->hw.aq.api_maj_ver == 1) &&
-		    (pf->hw.aq.api_min_ver > 4))) {
-		/* Supported in FW API version higher than 1.4 */
-		pf->hw_features |= I40E_HW_GENEVE_OFFLOAD_CAPABLE;
-	}
-
 	/* Enable HW ATR eviction if possible */
-	if (pf->hw_features & I40E_HW_ATR_EVICT_CAPABLE)
-		pf->flags |= I40E_FLAG_HW_ATR_EVICT_ENABLED;
-
-	if ((pf->hw.mac.type == I40E_MAC_XL710) &&
-	    (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 33)) ||
-	    (pf->hw.aq.fw_maj_ver < 4))) {
-		pf->hw_features |= I40E_HW_RESTART_AUTONEG;
-		/* No DCB support  for FW < v4.33 */
-		pf->hw_features |= I40E_HW_NO_DCB_SUPPORT;
-	}
-
-	/* Disable FW LLDP if FW < v4.3 */
-	if ((pf->hw.mac.type == I40E_MAC_XL710) &&
-	    (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 3)) ||
-	    (pf->hw.aq.fw_maj_ver < 4)))
-		pf->hw_features |= I40E_HW_STOP_FW_LLDP;
-
-	/* Use the FW Set LLDP MIB API if FW > v4.40 */
-	if ((pf->hw.mac.type == I40E_MAC_XL710) &&
-	    (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver >= 40)) ||
-	    (pf->hw.aq.fw_maj_ver >= 5)))
-		pf->hw_features |= I40E_HW_USE_SET_LLDP_MIB;
-
-	/* Enable PTP L4 if FW > v6.0 */
-	if (pf->hw.mac.type == I40E_MAC_XL710 &&
-	    pf->hw.aq.fw_maj_ver >= 6)
-		pf->hw_features |= I40E_HW_PTP_L4_CAPABLE;
+	if (test_bit(I40E_HW_CAP_ATR_EVICT, pf->hw.caps))
+		set_bit(I40E_FLAG_HW_ATR_EVICT_ENA, pf->flags);
 
 	if (pf->hw.func_caps.vmdq && num_online_cpus() != 1) {
 		pf->num_vmdq_vsis = I40E_DEFAULT_NUM_VMDQ_VSI;
-		pf->flags |= I40E_FLAG_VMDQ_ENABLED;
+		set_bit(I40E_FLAG_VMDQ_ENA, pf->flags);
 		pf->num_vmdq_qps = i40e_default_queues_per_vmdq(pf);
 	}
 
 	if (pf->hw.func_caps.iwarp && num_online_cpus() != 1) {
-		pf->flags |= I40E_FLAG_IWARP_ENABLED;
+		set_bit(I40E_FLAG_IWARP_ENA, pf->flags);
 		/* IWARP needs one extra vector for CQP just like MISC.*/
 		pf->num_iwarp_msix = (int)num_online_cpus() + 1;
 	}
@@ -12850,25 +12793,23 @@ static int i40e_sw_init(struct i40e_pf *pf)
 	 * if NPAR is functioning so unset this hw flag in this case.
 	 */
 	if (pf->hw.mac.type == I40E_MAC_XL710 &&
-	    pf->hw.func_caps.npar_enable &&
-	    (pf->hw.flags & I40E_HW_FLAG_FW_LLDP_STOPPABLE))
-		pf->hw.flags &= ~I40E_HW_FLAG_FW_LLDP_STOPPABLE;
+	    pf->hw.func_caps.npar_enable)
+		clear_bit(I40E_HW_CAP_FW_LLDP_STOPPABLE, pf->hw.caps);
 
 #ifdef CONFIG_PCI_IOV
 	if (pf->hw.func_caps.num_vfs && pf->hw.partition_id == 1) {
 		pf->num_vf_qps = I40E_DEFAULT_QUEUES_PER_VF;
-		pf->flags |= I40E_FLAG_SRIOV_ENABLED;
+		set_bit(I40E_FLAG_SRIOV_ENA, pf->flags);
 		pf->num_req_vfs = min_t(int,
 					pf->hw.func_caps.num_vfs,
 					I40E_MAX_VF_COUNT);
 	}
 #endif /* CONFIG_PCI_IOV */
-	pf->eeprom_version = 0xDEAD;
 	pf->lan_veb = I40E_NO_VEB;
 	pf->lan_vsi = I40E_NO_VSI;
 
 	/* By default FW has this off for performance reasons */
-	pf->flags &= ~I40E_FLAG_VEB_STATS_ENABLED;
+	clear_bit(I40E_FLAG_VEB_STATS_ENA, pf->flags);
 
 	/* set up queue assignment tracking */
 	size = sizeof(struct i40e_lump_tracking)
@@ -12887,8 +12828,8 @@ static int i40e_sw_init(struct i40e_pf *pf)
 		/* Link down on close must be on when total port shutdown
 		 * is enabled for a given port
 		 */
-		pf->flags |= (I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED |
-			      I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED);
+		set_bit(I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENA, pf->flags);
+		set_bit(I40E_FLAG_LINK_DOWN_ON_CLOSE_ENA, pf->flags);
 		dev_info(&pf->pdev->dev,
 			 "total-port-shutdown was enabled, link-down-on-close is forced on\n");
 	}
@@ -12914,31 +12855,31 @@ bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features)
 	 */
 	if (features & NETIF_F_NTUPLE) {
 		/* Enable filters and mark for reset */
-		if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED))
+		if (!test_bit(I40E_FLAG_FD_SB_ENA, pf->flags))
 			need_reset = true;
 		/* enable FD_SB only if there is MSI-X vector and no cloud
 		 * filters exist
 		 */
 		if (pf->num_fdsb_msix > 0 && !pf->num_cloud_filters) {
-			pf->flags |= I40E_FLAG_FD_SB_ENABLED;
-			pf->flags &= ~I40E_FLAG_FD_SB_INACTIVE;
+			set_bit(I40E_FLAG_FD_SB_ENA, pf->flags);
+			clear_bit(I40E_FLAG_FD_SB_INACTIVE, pf->flags);
 		}
 	} else {
 		/* turn off filters, mark for reset and clear SW filter list */
-		if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
+		if (test_bit(I40E_FLAG_FD_SB_ENA, pf->flags)) {
 			need_reset = true;
 			i40e_fdir_filter_exit(pf);
 		}
-		pf->flags &= ~I40E_FLAG_FD_SB_ENABLED;
+		clear_bit(I40E_FLAG_FD_SB_ENA, pf->flags);
 		clear_bit(__I40E_FD_SB_AUTO_DISABLED, pf->state);
-		pf->flags |= I40E_FLAG_FD_SB_INACTIVE;
+		set_bit(I40E_FLAG_FD_SB_INACTIVE, pf->flags);
 
 		/* reset fd counters */
 		pf->fd_add_err = 0;
 		pf->fd_atr_cnt = 0;
 		/* if ATR was auto disabled it can be re-enabled. */
 		if (test_and_clear_bit(__I40E_FD_ATR_AUTO_DISABLED, pf->state))
-			if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
+			if (test_bit(I40E_FLAG_FD_ATR_ENA, pf->flags) &&
 			    (I40E_DEBUG_FD & pf->hw.debug_mask))
 				dev_info(&pf->pdev->dev, "ATR re-enabled.\n");
 	}
@@ -13087,7 +13028,7 @@ static int i40e_get_phys_port_id(struct net_device *netdev,
 	struct i40e_pf *pf = np->vsi->back;
 	struct i40e_hw *hw = &pf->hw;
 
-	if (!(pf->hw_features & I40E_HW_PORT_ID_VALID))
+	if (!test_bit(I40E_HW_CAP_PORT_ID_VALID, pf->hw.caps))
 		return -EOPNOTSUPP;
 
 	ppid->id_len = min_t(int, sizeof(hw->mac.port_addr), sizeof(ppid->id));
@@ -13116,7 +13057,7 @@ static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	struct i40e_pf *pf = np->vsi->back;
 	int err = 0;
 
-	if (!(pf->flags & I40E_FLAG_SRIOV_ENABLED))
+	if (!test_bit(I40E_FLAG_SRIOV_ENA, pf->flags))
 		return -EOPNOTSUPP;
 
 	if (vid) {
@@ -13216,9 +13157,9 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev,
 			veb->bridge_mode = mode;
 			/* TODO: If no VFs or VMDq VSIs, disallow VEB mode */
 			if (mode == BRIDGE_MODE_VEB)
-				pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
+				set_bit(I40E_FLAG_VEB_MODE_ENA, pf->flags);
 			else
-				pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED;
+				clear_bit(I40E_FLAG_VEB_MODE_ENA, pf->flags);
 			i40e_do_reset(pf, I40E_PF_RESET_FLAG, true);
 			break;
 		}
@@ -13552,7 +13493,7 @@ static void i40e_queue_pair_enable_irq(struct i40e_vsi *vsi, int queue_pair)
 	struct i40e_hw *hw = &pf->hw;
 
 	/* All rings in a qp belong to the same qvector. */
-	if (pf->flags & I40E_FLAG_MSIX_ENABLED)
+	if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags))
 		i40e_irq_dynamic_enable(vsi, rxr->q_vector->v_idx);
 	else
 		i40e_irq_dynamic_enable_icr0(pf);
@@ -13577,7 +13518,7 @@ static void i40e_queue_pair_disable_irq(struct i40e_vsi *vsi, int queue_pair)
 	 *
 	 * All rings in a qp belong to the same qvector.
 	 */
-	if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+	if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags)) {
 		u32 intpf = vsi->base_vector + rxr->q_vector->v_idx;
 
 		wr32(hw, I40E_PFINT_DYN_CTLN(intpf - 1), 0);
@@ -13762,7 +13703,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 			  NETIF_F_RXCSUM		|
 			  0;
 
-	if (!(pf->hw_features & I40E_HW_OUTER_UDP_CSUM_CAPABLE))
+	if (!test_bit(I40E_HW_CAP_OUTER_UDP_CSUM, pf->hw.caps))
 		netdev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
 
 	netdev->udp_tunnel_nic_info = &pf->udp_tunnel_nic;
@@ -13798,7 +13739,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 		      NETIF_F_HW_VLAN_CTAG_TX	|
 		      NETIF_F_HW_VLAN_CTAG_RX;
 
-	if (!(pf->flags & I40E_FLAG_MFP_ENABLED))
+	if (!test_bit(I40E_FLAG_MFP_ENA, pf->flags))
 		hw_features |= NETIF_F_NTUPLE | NETIF_F_HW_TC;
 
 	netdev->hw_features |= hw_features | NETIF_F_LOOPBACK;
@@ -13989,7 +13930,7 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
 		 * negative logic - if it's set, we need to fiddle with
 		 * the VSI to disable source pruning.
 		 */
-		if (pf->flags & I40E_FLAG_SOURCE_PRUNING_DISABLED) {
+		if (test_bit(I40E_FLAG_SOURCE_PRUNING_DIS, pf->flags)) {
 			memset(&ctxt, 0, sizeof(ctxt));
 			ctxt.seid = pf->main_vsi_seid;
 			ctxt.pf_num = pf->hw.pf_id;
@@ -14011,7 +13952,7 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
 		}
 
 		/* MFP mode setup queue map and update VSI */
-		if ((pf->flags & I40E_FLAG_MFP_ENABLED) &&
+		if (test_bit(I40E_FLAG_MFP_ENA, pf->flags) &&
 		    !(pf->hw.func_caps.iscsi)) { /* NIC type PF */
 			memset(&ctxt, 0, sizeof(ctxt));
 			ctxt.seid = pf->main_vsi_seid;
@@ -14059,7 +14000,7 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
 		ctxt.uplink_seid = vsi->uplink_seid;
 		ctxt.connection_type = I40E_AQ_VSI_CONN_TYPE_NORMAL;
 		ctxt.flags = I40E_AQ_VSI_TYPE_PF;
-		if ((pf->flags & I40E_FLAG_VEB_MODE_ENABLED) &&
+		if (test_bit(I40E_FLAG_VEB_MODE_ENA, pf->flags) &&
 		    (i40e_is_vsi_uplink_mode_veb(vsi))) {
 			ctxt.info.valid_sections |=
 			     cpu_to_le16(I40E_AQ_VSI_PROP_SWITCH_VALID);
@@ -14107,7 +14048,7 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
 				cpu_to_le16(I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB);
 		}
 
-		if (vsi->back->flags & I40E_FLAG_IWARP_ENABLED) {
+		if (test_bit(I40E_FLAG_IWARP_ENA, vsi->back->flags)) {
 			ctxt.info.valid_sections |=
 				cpu_to_le16(I40E_AQ_VSI_PROP_QUEUE_OPT_VALID);
 			ctxt.info.queueing_opt_flags |=
@@ -14323,7 +14264,7 @@ static int i40e_vsi_setup_vectors(struct i40e_vsi *vsi)
 	/* In Legacy mode, we do not have to get any other vector since we
 	 * piggyback on the misc/ICR0 for queue interrupts.
 	*/
-	if (!(pf->flags & I40E_FLAG_MSIX_ENABLED))
+	if (!test_bit(I40E_FLAG_MSIX_ENA, pf->flags))
 		return ret;
 	if (vsi->num_q_vectors)
 		vsi->base_vector = i40e_get_lump(pf, pf->irq_pile,
@@ -14490,9 +14431,9 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
 			 * already enabled, in which case we can't force VEPA
 			 * mode.
 			 */
-			if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
+			if (!test_bit(I40E_FLAG_VEB_MODE_ENA, pf->flags)) {
 				veb->bridge_mode = BRIDGE_MODE_VEPA;
-				pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED;
+				clear_bit(I40E_FLAG_VEB_MODE_ENA, pf->flags);
 			}
 			i40e_config_bridge_mode(veb);
 		}
@@ -14588,12 +14529,16 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
 		break;
 	}
 
-	if ((pf->hw_features & I40E_HW_RSS_AQ_CAPABLE) &&
-	    (vsi->type == I40E_VSI_VMDQ2)) {
+	if (test_bit(I40E_HW_CAP_RSS_AQ, pf->hw.caps) &&
+	    vsi->type == I40E_VSI_VMDQ2) {
 		ret = i40e_vsi_config_rss(vsi);
+		if (ret)
+			goto err_config;
 	}
 	return vsi;
 
+err_config:
+	i40e_vsi_clear_rings(vsi);
 err_rings:
 	i40e_vsi_free_q_vectors(vsi);
 err_msix:
@@ -14831,7 +14776,7 @@ void i40e_veb_release(struct i40e_veb *veb)
 static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi)
 {
 	struct i40e_pf *pf = veb->pf;
-	bool enable_stats = !!(pf->flags & I40E_FLAG_VEB_STATS_ENABLED);
+	bool enable_stats = !!test_bit(I40E_FLAG_VEB_STATS_ENA, pf->flags);
 	int ret;
 
 	ret = i40e_aq_add_veb(&pf->hw, veb->uplink_seid, vsi->seid,
@@ -15020,12 +14965,11 @@ static void i40e_setup_pf_switch_element(struct i40e_pf *pf,
 		 * the PF's VSI
 		 */
 		pf->mac_seid = uplink_seid;
-		pf->pf_seid = downlink_seid;
 		pf->main_vsi_seid = seid;
 		if (printconfig)
 			dev_info(&pf->pdev->dev,
 				 "pf_seid=%d main_vsi_seid=%d\n",
-				 pf->pf_seid, pf->main_vsi_seid);
+				 downlink_seid, pf->main_vsi_seid);
 		break;
 	case I40E_SWITCH_ELEMENT_TYPE_PF:
 	case I40E_SWITCH_ELEMENT_TYPE_VF:
@@ -15131,7 +15075,7 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit, bool lock_acqui
 	*/
 
 	if ((pf->hw.pf_id == 0) &&
-	    !(pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT)) {
+	    !test_bit(I40E_FLAG_TRUE_PROMISC_ENA, pf->flags)) {
 		flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
 		pf->last_sw_conf_flags = flags;
 	}
@@ -15198,16 +15142,12 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit, bool lock_acqui
 	/* enable RSS in the HW, even for only one queue, as the stack can use
 	 * the hash
 	 */
-	if ((pf->flags & I40E_FLAG_RSS_ENABLED))
+	if (test_bit(I40E_FLAG_RSS_ENA, pf->flags))
 		i40e_pf_config_rss(pf);
 
 	/* fill in link information and enable LSE reporting */
 	i40e_link_event(pf);
 
-	/* Initialize user-specific link properties */
-	pf->fc_autoneg_status = ((pf->hw.phy.link_info.an_info &
-				  I40E_AQ_AN_COMPLETED) ? true : false);
-
 	i40e_ptp_init(pf);
 
 	if (!lock_acquired)
@@ -15240,42 +15180,42 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 	queues_left = pf->hw.func_caps.num_tx_qp;
 
 	if ((queues_left == 1) ||
-	    !(pf->flags & I40E_FLAG_MSIX_ENABLED)) {
+	    !test_bit(I40E_FLAG_MSIX_ENA, pf->flags)) {
 		/* one qp for PF, no queues for anything else */
 		queues_left = 0;
 		pf->alloc_rss_size = pf->num_lan_qps = 1;
 
 		/* make sure all the fancies are disabled */
-		pf->flags &= ~(I40E_FLAG_RSS_ENABLED	|
-			       I40E_FLAG_IWARP_ENABLED	|
-			       I40E_FLAG_FD_SB_ENABLED	|
-			       I40E_FLAG_FD_ATR_ENABLED	|
-			       I40E_FLAG_DCB_CAPABLE	|
-			       I40E_FLAG_DCB_ENABLED	|
-			       I40E_FLAG_SRIOV_ENABLED	|
-			       I40E_FLAG_VMDQ_ENABLED);
-		pf->flags |= I40E_FLAG_FD_SB_INACTIVE;
-	} else if (!(pf->flags & (I40E_FLAG_RSS_ENABLED |
-				  I40E_FLAG_FD_SB_ENABLED |
-				  I40E_FLAG_FD_ATR_ENABLED |
-				  I40E_FLAG_DCB_CAPABLE))) {
+		clear_bit(I40E_FLAG_RSS_ENA, pf->flags);
+		clear_bit(I40E_FLAG_IWARP_ENA, pf->flags);
+		clear_bit(I40E_FLAG_FD_SB_ENA, pf->flags);
+		clear_bit(I40E_FLAG_FD_ATR_ENA, pf->flags);
+		clear_bit(I40E_FLAG_DCB_CAPABLE, pf->flags);
+		clear_bit(I40E_FLAG_DCB_ENA, pf->flags);
+		clear_bit(I40E_FLAG_SRIOV_ENA, pf->flags);
+		clear_bit(I40E_FLAG_VMDQ_ENA, pf->flags);
+		set_bit(I40E_FLAG_FD_SB_INACTIVE, pf->flags);
+	} else if (!test_bit(I40E_FLAG_RSS_ENA, pf->flags) &&
+		   !test_bit(I40E_FLAG_FD_SB_ENA, pf->flags) &&
+		   !test_bit(I40E_FLAG_FD_ATR_ENA, pf->flags) &&
+		   !test_bit(I40E_FLAG_DCB_CAPABLE, pf->flags)) {
 		/* one qp for PF */
 		pf->alloc_rss_size = pf->num_lan_qps = 1;
 		queues_left -= pf->num_lan_qps;
 
-		pf->flags &= ~(I40E_FLAG_RSS_ENABLED	|
-			       I40E_FLAG_IWARP_ENABLED	|
-			       I40E_FLAG_FD_SB_ENABLED	|
-			       I40E_FLAG_FD_ATR_ENABLED	|
-			       I40E_FLAG_DCB_ENABLED	|
-			       I40E_FLAG_VMDQ_ENABLED);
-		pf->flags |= I40E_FLAG_FD_SB_INACTIVE;
+		clear_bit(I40E_FLAG_RSS_ENA, pf->flags);
+		clear_bit(I40E_FLAG_IWARP_ENA, pf->flags);
+		clear_bit(I40E_FLAG_FD_SB_ENA, pf->flags);
+		clear_bit(I40E_FLAG_FD_ATR_ENA, pf->flags);
+		clear_bit(I40E_FLAG_DCB_ENA, pf->flags);
+		clear_bit(I40E_FLAG_VMDQ_ENA, pf->flags);
+		set_bit(I40E_FLAG_FD_SB_INACTIVE, pf->flags);
 	} else {
 		/* Not enough queues for all TCs */
-		if ((pf->flags & I40E_FLAG_DCB_CAPABLE) &&
-		    (queues_left < I40E_MAX_TRAFFIC_CLASS)) {
-			pf->flags &= ~(I40E_FLAG_DCB_CAPABLE |
-					I40E_FLAG_DCB_ENABLED);
+		if (test_bit(I40E_FLAG_DCB_CAPABLE, pf->flags) &&
+		    queues_left < I40E_MAX_TRAFFIC_CLASS) {
+			clear_bit(I40E_FLAG_DCB_CAPABLE, pf->flags);
+			clear_bit(I40E_FLAG_DCB_ENA, pf->flags);
 			dev_info(&pf->pdev->dev, "not enough queues for DCB. DCB is disabled.\n");
 		}
 
@@ -15288,24 +15228,24 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 		queues_left -= pf->num_lan_qps;
 	}
 
-	if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
+	if (test_bit(I40E_FLAG_FD_SB_ENA, pf->flags)) {
 		if (queues_left > 1) {
 			queues_left -= 1; /* save 1 queue for FD */
 		} else {
-			pf->flags &= ~I40E_FLAG_FD_SB_ENABLED;
-			pf->flags |= I40E_FLAG_FD_SB_INACTIVE;
+			clear_bit(I40E_FLAG_FD_SB_ENA, pf->flags);
+			set_bit(I40E_FLAG_FD_SB_INACTIVE, pf->flags);
 			dev_info(&pf->pdev->dev, "not enough queues for Flow Director. Flow Director feature is disabled\n");
 		}
 	}
 
-	if ((pf->flags & I40E_FLAG_SRIOV_ENABLED) &&
+	if (test_bit(I40E_FLAG_SRIOV_ENA, pf->flags) &&
 	    pf->num_vf_qps && pf->num_req_vfs && queues_left) {
 		pf->num_req_vfs = min_t(int, pf->num_req_vfs,
 					(queues_left / pf->num_vf_qps));
 		queues_left -= (pf->num_req_vfs * pf->num_vf_qps);
 	}
 
-	if ((pf->flags & I40E_FLAG_VMDQ_ENABLED) &&
+	if (test_bit(I40E_FLAG_VMDQ_ENA, pf->flags) &&
 	    pf->num_vmdq_vsis && pf->num_vmdq_qps && queues_left) {
 		pf->num_vmdq_vsis = min_t(int, pf->num_vmdq_vsis,
 					  (queues_left / pf->num_vmdq_qps));
@@ -15316,7 +15256,7 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 	dev_dbg(&pf->pdev->dev,
 		"qs_avail=%d FD SB=%d lan_qs=%d lan_tc0=%d vf=%d*%d vmdq=%d*%d, remaining=%d\n",
 		pf->hw.func_caps.num_tx_qp,
-		!!(pf->flags & I40E_FLAG_FD_SB_ENABLED),
+		!!test_bit(I40E_FLAG_FD_SB_ENA, pf->flags),
 		pf->num_lan_qps, pf->alloc_rss_size, pf->num_req_vfs,
 		pf->num_vf_qps, pf->num_vmdq_vsis, pf->num_vmdq_qps,
 		queues_left);
@@ -15340,7 +15280,8 @@ static int i40e_setup_pf_filter_control(struct i40e_pf *pf)
 	settings->hash_lut_size = I40E_HASH_LUT_SIZE_128;
 
 	/* Flow Director is enabled */
-	if (pf->flags & (I40E_FLAG_FD_SB_ENABLED | I40E_FLAG_FD_ATR_ENABLED))
+	if (test_bit(I40E_FLAG_FD_SB_ENA, pf->flags) ||
+	    test_bit(I40E_FLAG_FD_ATR_ENA, pf->flags))
 		settings->enable_fdir = true;
 
 	/* Ethtype and MACVLAN filters enabled for PF */
@@ -15372,21 +15313,21 @@ static void i40e_print_features(struct i40e_pf *pf)
 	i += scnprintf(&buf[i], REMAIN(i), " VSIs: %d QP: %d",
 		      pf->hw.func_caps.num_vsis,
 		      pf->vsi[pf->lan_vsi]->num_queue_pairs);
-	if (pf->flags & I40E_FLAG_RSS_ENABLED)
+	if (test_bit(I40E_FLAG_RSS_ENA, pf->flags))
 		i += scnprintf(&buf[i], REMAIN(i), " RSS");
-	if (pf->flags & I40E_FLAG_FD_ATR_ENABLED)
+	if (test_bit(I40E_FLAG_FD_ATR_ENA, pf->flags))
 		i += scnprintf(&buf[i], REMAIN(i), " FD_ATR");
-	if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
+	if (test_bit(I40E_FLAG_FD_SB_ENA, pf->flags)) {
 		i += scnprintf(&buf[i], REMAIN(i), " FD_SB");
 		i += scnprintf(&buf[i], REMAIN(i), " NTUPLE");
 	}
-	if (pf->flags & I40E_FLAG_DCB_CAPABLE)
+	if (test_bit(I40E_FLAG_DCB_CAPABLE, pf->flags))
 		i += scnprintf(&buf[i], REMAIN(i), " DCB");
 	i += scnprintf(&buf[i], REMAIN(i), " VxLAN");
 	i += scnprintf(&buf[i], REMAIN(i), " Geneve");
-	if (pf->flags & I40E_FLAG_PTP)
+	if (test_bit(I40E_FLAG_PTP_ENA, pf->flags))
 		i += scnprintf(&buf[i], REMAIN(i), " PTP");
-	if (pf->flags & I40E_FLAG_VEB_MODE_ENABLED)
+	if (test_bit(I40E_FLAG_VEB_MODE_ENA, pf->flags))
 		i += scnprintf(&buf[i], REMAIN(i), " VEB");
 	else
 		i += scnprintf(&buf[i], REMAIN(i), " VEPA");
@@ -15417,22 +15358,26 @@ static void i40e_get_platform_mac_addr(struct pci_dev *pdev, struct i40e_pf *pf)
  * @fec_cfg: FEC option to set in flags
  * @flags: ptr to flags in which we set FEC option
  **/
-void i40e_set_fec_in_flags(u8 fec_cfg, u32 *flags)
+void i40e_set_fec_in_flags(u8 fec_cfg, unsigned long *flags)
 {
-	if (fec_cfg & I40E_AQ_SET_FEC_AUTO)
-		*flags |= I40E_FLAG_RS_FEC | I40E_FLAG_BASE_R_FEC;
+	if (fec_cfg & I40E_AQ_SET_FEC_AUTO) {
+		set_bit(I40E_FLAG_RS_FEC, flags);
+		set_bit(I40E_FLAG_BASE_R_FEC, flags);
+	}
 	if ((fec_cfg & I40E_AQ_SET_FEC_REQUEST_RS) ||
 	    (fec_cfg & I40E_AQ_SET_FEC_ABILITY_RS)) {
-		*flags |= I40E_FLAG_RS_FEC;
-		*flags &= ~I40E_FLAG_BASE_R_FEC;
+		set_bit(I40E_FLAG_RS_FEC, flags);
+		clear_bit(I40E_FLAG_BASE_R_FEC, flags);
 	}
 	if ((fec_cfg & I40E_AQ_SET_FEC_REQUEST_KR) ||
 	    (fec_cfg & I40E_AQ_SET_FEC_ABILITY_KR)) {
-		*flags |= I40E_FLAG_BASE_R_FEC;
-		*flags &= ~I40E_FLAG_RS_FEC;
+		set_bit(I40E_FLAG_BASE_R_FEC, flags);
+		clear_bit(I40E_FLAG_RS_FEC, flags);
+	}
+	if (fec_cfg == 0) {
+		clear_bit(I40E_FLAG_RS_FEC, flags);
+		clear_bit(I40E_FLAG_BASE_R_FEC, flags);
 	}
-	if (fec_cfg == 0)
-		*flags &= ~(I40E_FLAG_RS_FEC | I40E_FLAG_BASE_R_FEC);
 }
 
 /**
@@ -15676,7 +15621,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 #endif /* CONFIG_I40E_DCB */
 	struct i40e_pf *pf;
 	struct i40e_hw *hw;
-	static u16 pfs_found;
 	u16 wol_nvm_bits;
 	char nvm_ver[32];
 	u16 link_status;
@@ -15754,7 +15698,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	hw->bus.device = PCI_SLOT(pdev->devfn);
 	hw->bus.func = PCI_FUNC(pdev->devfn);
 	hw->bus.bus_id = pdev->bus->number;
-	pf->instance = pfs_found;
 
 	/* Select something other than the 802.1ad ethertype for the
 	 * switch to use internally and drop on ingress.
@@ -15816,7 +15759,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 	hw->aq.arq_buf_size = I40E_MAX_AQ_BUF_SIZE;
 	hw->aq.asq_buf_size = I40E_MAX_AQ_BUF_SIZE;
-	pf->adminq_work_limit = I40E_AQ_WORK_LIMIT;
 
 	snprintf(pf->int_name, sizeof(pf->int_name) - 1,
 		 "%s-%s:misc",
@@ -15858,15 +15800,15 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		 hw->vendor_id, hw->device_id, hw->subsystem_vendor_id,
 		 hw->subsystem_device_id);
 
-	if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
-	    hw->aq.api_min_ver > I40E_FW_MINOR_VERSION(hw))
+	if (i40e_is_aq_api_ver_ge(hw, I40E_FW_API_VERSION_MAJOR,
+				  I40E_FW_MINOR_VERSION(hw) + 1))
 		dev_dbg(&pdev->dev,
 			"The driver for the device detected a newer version of the NVM image v%u.%u than v%u.%u.\n",
 			 hw->aq.api_maj_ver,
 			 hw->aq.api_min_ver,
 			 I40E_FW_API_VERSION_MAJOR,
 			 I40E_FW_MINOR_VERSION(hw));
-	else if (hw->aq.api_maj_ver == 1 && hw->aq.api_min_ver < 4)
+	else if (i40e_is_aq_api_ver_lt(hw, 1, 4))
 		dev_info(&pdev->dev,
 			 "The driver for the device detected an older version of the NVM image v%u.%u than expected v%u.%u. Please update the NVM image.\n",
 			 hw->aq.api_maj_ver,
@@ -15913,7 +15855,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 * Ignore error return codes because if it was already disabled via
 	 * hardware settings this will fail
 	 */
-	if (pf->hw_features & I40E_HW_STOP_FW_LLDP) {
+	if (test_bit(I40E_HW_CAP_STOP_FW_LLDP, pf->hw.caps)) {
 		dev_info(&pdev->dev, "Stopping firmware LLDP agent.\n");
 		i40e_aq_stop_lldp(hw, true, false, NULL);
 	}
@@ -15930,7 +15872,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	ether_addr_copy(hw->mac.perm_addr, hw->mac.addr);
 	i40e_get_port_mac_addr(hw, hw->mac.port_addr);
 	if (is_valid_ether_addr(hw->mac.port_addr))
-		pf->hw_features |= I40E_HW_PORT_ID_VALID;
+		set_bit(I40E_HW_CAP_PORT_ID_VALID, pf->hw.caps);
 
 	i40e_ptp_alloc_pins(pf);
 	pci_set_drvdata(pdev, pf);
@@ -15940,10 +15882,10 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	status = i40e_get_fw_lldp_status(&pf->hw, &lldp_status);
 	(!status &&
 	 lldp_status == I40E_GET_FW_LLDP_STATUS_ENABLED) ?
-		(pf->flags &= ~I40E_FLAG_DISABLE_FW_LLDP) :
-		(pf->flags |= I40E_FLAG_DISABLE_FW_LLDP);
+		(clear_bit(I40E_FLAG_FW_LLDP_DIS, pf->flags)) :
+		(set_bit(I40E_FLAG_FW_LLDP_DIS, pf->flags));
 	dev_info(&pdev->dev,
-		 (pf->flags & I40E_FLAG_DISABLE_FW_LLDP) ?
+		 test_bit(I40E_FLAG_FW_LLDP_DIS, pf->flags) ?
 			"FW LLDP is disabled\n" :
 			"FW LLDP is enabled\n");
 
@@ -15953,7 +15895,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	err = i40e_init_pf_dcb(pf);
 	if (err) {
 		dev_info(&pdev->dev, "DCB init failed %d, disabled\n", err);
-		pf->flags &= ~(I40E_FLAG_DCB_CAPABLE | I40E_FLAG_DCB_ENABLED);
+		clear_bit(I40E_FLAG_DCB_CAPABLE, pf->flags);
+		clear_bit(I40E_FLAG_DCB_ENA, pf->flags);
 		/* Continue without DCB enabled */
 	}
 #endif /* CONFIG_I40E_DCB */
@@ -16021,11 +15964,11 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 #ifdef CONFIG_PCI_IOV
 	/* prep for VF support */
-	if ((pf->flags & I40E_FLAG_SRIOV_ENABLED) &&
-	    (pf->flags & I40E_FLAG_MSIX_ENABLED) &&
+	if (test_bit(I40E_FLAG_SRIOV_ENA, pf->flags) &&
+	    test_bit(I40E_FLAG_MSIX_ENA, pf->flags) &&
 	    !test_bit(__I40E_BAD_EEPROM, pf->state)) {
 		if (pci_num_vf(pdev))
-			pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
+			set_bit(I40E_FLAG_VEB_MODE_ENA, pf->flags);
 	}
 #endif
 	err = i40e_setup_pf_switch(pf, false, false);
@@ -16066,7 +16009,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		wr32(hw, I40E_REG_MSS, val);
 	}
 
-	if (pf->hw_features & I40E_HW_RESTART_AUTONEG) {
+	if (test_bit(I40E_HW_CAP_RESTART_AUTONEG, pf->hw.caps)) {
 		msleep(75);
 		err = i40e_aq_set_link_restart_an(&pf->hw, true, NULL);
 		if (err)
@@ -16086,7 +16029,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 * the misc functionality and queue processing is combined in
 	 * the same vector and that gets setup at open.
 	 */
-	if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+	if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags)) {
 		err = i40e_setup_misc_vector(pf);
 		if (err) {
 			dev_info(&pdev->dev,
@@ -16099,8 +16042,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 #ifdef CONFIG_PCI_IOV
 	/* prep for VF support */
-	if ((pf->flags & I40E_FLAG_SRIOV_ENABLED) &&
-	    (pf->flags & I40E_FLAG_MSIX_ENABLED) &&
+	if (test_bit(I40E_FLAG_SRIOV_ENA, pf->flags) &&
+	    test_bit(I40E_FLAG_MSIX_ENA, pf->flags) &&
 	    !test_bit(__I40E_BAD_EEPROM, pf->state)) {
 		/* disable link interrupts for VFs */
 		val = rd32(hw, I40E_PFGEN_PORTMDIO_NUM);
@@ -16120,7 +16063,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 #endif /* CONFIG_PCI_IOV */
 
-	if (pf->flags & I40E_FLAG_IWARP_ENABLED) {
+	if (test_bit(I40E_FLAG_IWARP_ENA, pf->flags)) {
 		pf->iwarp_base_vector = i40e_get_lump(pf, pf->irq_pile,
 						      pf->num_iwarp_msix,
 						      I40E_IWARP_IRQ_PILE_ID);
@@ -16128,7 +16071,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			dev_info(&pdev->dev,
 				 "failed to get tracking for %d vectors for IWARP err=%d\n",
 				 pf->num_iwarp_msix, pf->iwarp_base_vector);
-			pf->flags &= ~I40E_FLAG_IWARP_ENABLED;
+			clear_bit(I40E_FLAG_IWARP_ENA, pf->flags);
 		}
 	}
 
@@ -16142,7 +16085,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		  round_jiffies(jiffies + pf->service_timer_period));
 
 	/* add this PF to client device list and launch a client service task */
-	if (pf->flags & I40E_FLAG_IWARP_ENABLED) {
+	if (test_bit(I40E_FLAG_IWARP_ENA, pf->flags)) {
 		err = i40e_lan_add_device(pf);
 		if (err)
 			dev_info(&pdev->dev, "Failed to add PF to client API service list: %d\n",
@@ -16155,7 +16098,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 * and will report PCI Gen 1 x 1 by default so don't bother
 	 * checking them.
 	 */
-	if (!(pf->hw_features & I40E_HW_NO_PCI_LINK_CHECK)) {
+	if (!test_bit(I40E_HW_CAP_NO_PCI_LINK_CHECK, pf->hw.caps)) {
 		char speed[PCI_SPEED_SIZE] = "Unknown";
 		char width[PCI_WIDTH_SIZE] = "Unknown";
 
@@ -16209,7 +16152,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pf->hw.phy.link_info.requested_speeds = abilities.link_speed;
 
 	/* set the FEC config due to the board capabilities */
-	i40e_set_fec_in_flags(abilities.fec_cfg_curr_mod_ext_info, &pf->flags);
+	i40e_set_fec_in_flags(abilities.fec_cfg_curr_mod_ext_info, pf->flags);
 
 	/* get the supported phy types from the fw */
 	err = i40e_aq_get_phy_capabilities(hw, false, true, &abilities, NULL);
@@ -16220,11 +16163,11 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* make sure the MFS hasn't been set lower than the default */
 #define MAX_FRAME_SIZE_DEFAULT 0x2600
-	val = (rd32(&pf->hw, I40E_PRTGL_SAH) &
-	       I40E_PRTGL_SAH_MFS_MASK) >> I40E_PRTGL_SAH_MFS_SHIFT;
+	val = FIELD_GET(I40E_PRTGL_SAH_MFS_MASK,
+			rd32(&pf->hw, I40E_PRTGL_SAH));
 	if (val < MAX_FRAME_SIZE_DEFAULT)
 		dev_warn(&pdev->dev, "MFS for port %x has been set below the default: %x\n",
-			 i, val);
+			 pf->hw.port, val);
 
 	/* Add a filter to drop all Flow control frames from any VSI from being
 	 * transmitted. By doing so we stop a malicious VF from sending out
@@ -16236,10 +16179,10 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 						       pf->main_vsi_seid);
 
 	if ((pf->hw.device_id == I40E_DEV_ID_10G_BASE_T) ||
-		(pf->hw.device_id == I40E_DEV_ID_10G_BASE_T4))
-		pf->hw_features |= I40E_HW_PHY_CONTROLS_LEDS;
+	    (pf->hw.device_id == I40E_DEV_ID_10G_BASE_T4))
+		set_bit(I40E_HW_CAP_PHY_CONTROLS_LEDS, pf->hw.caps);
 	if (pf->hw.device_id == I40E_DEV_ID_SFP_I_X722)
-		pf->hw_features |= I40E_HW_HAVE_CRT_RETIMER;
+		set_bit(I40E_HW_CAP_CRT_RETIMER, pf->hw.caps);
 	/* print a string summarizing features */
 	i40e_print_features(pf);
 
@@ -16308,10 +16251,10 @@ static void i40e_remove(struct pci_dev *pdev)
 		usleep_range(1000, 2000);
 	set_bit(__I40E_IN_REMOVE, pf->state);
 
-	if (pf->flags & I40E_FLAG_SRIOV_ENABLED) {
+	if (test_bit(I40E_FLAG_SRIOV_ENA, pf->flags)) {
 		set_bit(__I40E_VF_RESETS_DISABLED, pf->state);
 		i40e_free_vfs(pf);
-		pf->flags &= ~I40E_FLAG_SRIOV_ENABLED;
+		clear_bit(I40E_FLAG_SRIOV_ENA, pf->flags);
 	}
 	/* no more scheduling of any task */
 	set_bit(__I40E_SUSPENDED, pf->state);
@@ -16366,7 +16309,7 @@ static void i40e_remove(struct pci_dev *pdev)
 	i40e_cloud_filter_exit(pf);
 
 	/* remove attached clients */
-	if (pf->flags & I40E_FLAG_IWARP_ENABLED) {
+	if (test_bit(I40E_FLAG_IWARP_ENA, pf->flags)) {
 		ret_code = i40e_lan_del_device(pf);
 		if (ret_code)
 			dev_warn(&pdev->dev, "Failed to delete client device: %d\n",
@@ -16385,7 +16328,7 @@ static void i40e_remove(struct pci_dev *pdev)
 unmap:
 	/* Free MSI/legacy interrupt 0 when in recovery mode. */
 	if (test_bit(__I40E_RECOVERY_MODE, pf->state) &&
-	    !(pf->flags & I40E_FLAG_MSIX_ENABLED))
+	    !test_bit(I40E_FLAG_MSIX_ENA, pf->flags))
 		free_irq(pf->pdev->irq, pf);
 
 	/* shutdown the adminq */
@@ -16512,6 +16455,9 @@ static void i40e_pci_error_reset_done(struct pci_dev *pdev)
 		return;
 
 	i40e_reset_and_rebuild(pf, false, false);
+#ifdef CONFIG_PCI_IOV
+	i40e_restore_all_vfs_msi_state(pdev);
+#endif /* CONFIG_PCI_IOV */
 }
 
 /**
@@ -16601,7 +16547,8 @@ static void i40e_shutdown(struct pci_dev *pdev)
 	 */
 	i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false);
 
-	if (pf->wol_en && (pf->hw_features & I40E_HW_WOL_MC_MAGIC_PKT_WAKE))
+	if (test_bit(I40E_HW_CAP_WOL_MC_MAGIC_PKT_WAKE, pf->hw.caps) &&
+	    pf->wol_en)
 		i40e_enable_mc_magic_wake(pf);
 
 	i40e_prep_for_reset(pf);
@@ -16613,7 +16560,7 @@ static void i40e_shutdown(struct pci_dev *pdev)
 
 	/* Free MSI/legacy interrupt 0 when in recovery mode. */
 	if (test_bit(__I40E_RECOVERY_MODE, pf->state) &&
-	    !(pf->flags & I40E_FLAG_MSIX_ENABLED))
+	    !test_bit(I40E_FLAG_MSIX_ENA, pf->flags))
 		free_irq(pf->pdev->irq, pf);
 
 	/* Since we're going to destroy queues during the
@@ -16654,7 +16601,8 @@ static int __maybe_unused i40e_suspend(struct device *dev)
 	 */
 	i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false);
 
-	if (pf->wol_en && (pf->hw_features & I40E_HW_WOL_MC_MAGIC_PKT_WAKE))
+	if (test_bit(I40E_HW_CAP_WOL_MC_MAGIC_PKT_WAKE, pf->hw.caps) &&
+	    pf->wol_en)
 		i40e_enable_mc_magic_wake(pf);
 
 	/* Since we're going to destroy queues during the
diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
index 77cdbfc19d47..605fd82f5d20 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
+#include <linux/bitfield.h>
 #include <linux/delay.h>
 #include "i40e_alloc.h"
 #include "i40e_prototype.h"
@@ -26,8 +27,7 @@ int i40e_init_nvm(struct i40e_hw *hw)
 	 * as the blank mode may be used in the factory line.
 	 */
 	gens = rd32(hw, I40E_GLNVM_GENS);
-	sr_size = ((gens & I40E_GLNVM_GENS_SR_SIZE_MASK) >>
-			   I40E_GLNVM_GENS_SR_SIZE_SHIFT);
+	sr_size = FIELD_GET(I40E_GLNVM_GENS_SR_SIZE_MASK, gens);
 	/* Switching to words (sr_size contains power of 2KB) */
 	nvm->sr_size = BIT(sr_size) * I40E_SR_WORDS_IN_1KB;
 
@@ -193,9 +193,8 @@ static int i40e_read_nvm_word_srctl(struct i40e_hw *hw, u16 offset,
 		ret_code = i40e_poll_sr_srctl_done_bit(hw);
 		if (!ret_code) {
 			sr_reg = rd32(hw, I40E_GLNVM_SRDATA);
-			*data = (u16)((sr_reg &
-				       I40E_GLNVM_SRDATA_RDDATA_MASK)
-				    >> I40E_GLNVM_SRDATA_RDDATA_SHIFT);
+			*data = FIELD_GET(I40E_GLNVM_SRDATA_RDDATA_MASK,
+					  sr_reg);
 		}
 	}
 	if (ret_code)
@@ -291,7 +290,7 @@ static int i40e_read_nvm_word_aq(struct i40e_hw *hw, u16 offset,
 static int __i40e_read_nvm_word(struct i40e_hw *hw,
 				u16 offset, u16 *data)
 {
-	if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE)
+	if (test_bit(I40E_HW_CAP_AQ_SRCTL_ACCESS_ENABLE, hw->caps))
 		return i40e_read_nvm_word_aq(hw, offset, data);
 
 	return i40e_read_nvm_word_srctl(hw, offset, data);
@@ -310,14 +309,14 @@ int i40e_read_nvm_word(struct i40e_hw *hw, u16 offset,
 {
 	int ret_code = 0;
 
-	if (hw->flags & I40E_HW_FLAG_NVM_READ_REQUIRES_LOCK)
+	if (test_bit(I40E_HW_CAP_NVM_READ_REQUIRES_LOCK, hw->caps))
 		ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
 	if (ret_code)
 		return ret_code;
 
 	ret_code = __i40e_read_nvm_word(hw, offset, data);
 
-	if (hw->flags & I40E_HW_FLAG_NVM_READ_REQUIRES_LOCK)
+	if (test_bit(I40E_HW_CAP_NVM_READ_REQUIRES_LOCK, hw->caps))
 		i40e_release_nvm(hw);
 
 	return ret_code;
@@ -499,7 +498,7 @@ static int __i40e_read_nvm_buffer(struct i40e_hw *hw,
 				  u16 offset, u16 *words,
 				  u16 *data)
 {
-	if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE)
+	if (test_bit(I40E_HW_CAP_AQ_SRCTL_ACCESS_ENABLE, hw->caps))
 		return i40e_read_nvm_buffer_aq(hw, offset, words, data);
 
 	return i40e_read_nvm_buffer_srctl(hw, offset, words, data);
@@ -521,7 +520,7 @@ int i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset,
 {
 	int ret_code = 0;
 
-	if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) {
+	if (test_bit(I40E_HW_CAP_AQ_SRCTL_ACCESS_ENABLE, hw->caps)) {
 		ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
 		if (!ret_code) {
 			ret_code = i40e_read_nvm_buffer_aq(hw, offset, words,
@@ -771,13 +770,12 @@ static inline u8 i40e_nvmupd_get_module(u32 val)
 }
 static inline u8 i40e_nvmupd_get_transaction(u32 val)
 {
-	return (u8)((val & I40E_NVM_TRANS_MASK) >> I40E_NVM_TRANS_SHIFT);
+	return FIELD_GET(I40E_NVM_TRANS_MASK, val);
 }
 
 static inline u8 i40e_nvmupd_get_preservation_flags(u32 val)
 {
-	return (u8)((val & I40E_NVM_PRESERVATION_FLAGS_MASK) >>
-		    I40E_NVM_PRESERVATION_FLAGS_SHIFT);
+	return FIELD_GET(I40E_NVM_PRESERVATION_FLAGS_MASK, val);
 }
 
 static const char * const i40e_nvm_update_state_str[] = {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index 001162042050..af4269330581 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -501,4 +501,74 @@ i40e_add_pinfo_to_list(struct i40e_hw *hw,
 /* i40e_ddp */
 int i40e_ddp_flash(struct net_device *netdev, struct ethtool_flash *flash);
 
+/* Firmware and AdminQ version check helpers */
+
+/**
+ * i40e_is_aq_api_ver_ge
+ * @hw: pointer to i40e_hw structure
+ * @maj: API major value to compare
+ * @min: API minor value to compare
+ *
+ * Assert whether current HW API version is greater/equal than provided.
+ **/
+static inline bool i40e_is_aq_api_ver_ge(struct i40e_hw *hw, u16 maj, u16 min)
+{
+	return (hw->aq.api_maj_ver > maj ||
+		(hw->aq.api_maj_ver == maj && hw->aq.api_min_ver >= min));
+}
+
+/**
+ * i40e_is_aq_api_ver_lt
+ * @hw: pointer to i40e_hw structure
+ * @maj: API major value to compare
+ * @min: API minor value to compare
+ *
+ * Assert whether current HW API version is less than provided.
+ **/
+static inline bool i40e_is_aq_api_ver_lt(struct i40e_hw *hw, u16 maj, u16 min)
+{
+	return !i40e_is_aq_api_ver_ge(hw, maj, min);
+}
+
+/**
+ * i40e_is_fw_ver_ge
+ * @hw: pointer to i40e_hw structure
+ * @maj: API major value to compare
+ * @min: API minor value to compare
+ *
+ * Assert whether current firmware version is greater/equal than provided.
+ **/
+static inline bool i40e_is_fw_ver_ge(struct i40e_hw *hw, u16 maj, u16 min)
+{
+	return (hw->aq.fw_maj_ver > maj ||
+		(hw->aq.fw_maj_ver == maj && hw->aq.fw_min_ver >= min));
+}
+
+/**
+ * i40e_is_fw_ver_lt
+ * @hw: pointer to i40e_hw structure
+ * @maj: API major value to compare
+ * @min: API minor value to compare
+ *
+ * Assert whether current firmware version is less than provided.
+ **/
+static inline bool i40e_is_fw_ver_lt(struct i40e_hw *hw, u16 maj, u16 min)
+{
+	return !i40e_is_fw_ver_ge(hw, maj, min);
+}
+
+/**
+ * i40e_is_fw_ver_eq
+ * @hw: pointer to i40e_hw structure
+ * @maj: API major value to compare
+ * @min: API minor value to compare
+ *
+ * Assert whether current firmware version is equal to provided.
+ **/
+static inline bool i40e_is_fw_ver_eq(struct i40e_hw *hw, u16 maj, u16 min)
+{
+	return (hw->aq.fw_maj_ver > maj ||
+		(hw->aq.fw_maj_ver == maj && hw->aq.fw_min_ver == min));
+}
+
 #endif /* _I40E_PROTOTYPE_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
index 20b77398f060..e7ebcb09f23c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
@@ -35,7 +35,7 @@ enum i40e_ptp_pin {
 	GPIO_4
 };
 
-enum i40e_can_set_pins_t {
+enum i40e_can_set_pins {
 	CANT_DO_PINS = -1,
 	CAN_SET_PINS,
 	CAN_DO_PINS
@@ -193,7 +193,7 @@ static bool i40e_is_ptp_pin_dev(struct i40e_hw *hw)
  * return CAN_DO_PINS if pins can be manipulated within a NIC or
  * return CANT_DO_PINS otherwise.
  **/
-static enum i40e_can_set_pins_t i40e_can_set_pins(struct i40e_pf *pf)
+static enum i40e_can_set_pins i40e_can_set_pins(struct i40e_pf *pf)
 {
 	if (!i40e_is_ptp_pin_dev(&pf->hw)) {
 		dev_warn(&pf->pdev->dev,
@@ -680,7 +680,7 @@ void i40e_ptp_rx_hang(struct i40e_pf *pf)
 	 * configured. We don't want to spuriously warn about Rx timestamp
 	 * hangs if we don't care about the timestamps.
 	 */
-	if (!(pf->flags & I40E_FLAG_PTP) || !pf->ptp_rx)
+	if (!test_bit(I40E_FLAG_PTP_ENA, pf->flags) || !pf->ptp_rx)
 		return;
 
 	spin_lock_bh(&pf->ptp_rx_lock);
@@ -733,7 +733,7 @@ void i40e_ptp_tx_hang(struct i40e_pf *pf)
 {
 	struct sk_buff *skb;
 
-	if (!(pf->flags & I40E_FLAG_PTP) || !pf->ptp_tx)
+	if (!test_bit(I40E_FLAG_PTP_ENA, pf->flags) || !pf->ptp_tx)
 		return;
 
 	/* Nothing to do if we're not already waiting for a timestamp */
@@ -771,7 +771,7 @@ void i40e_ptp_tx_hwtstamp(struct i40e_pf *pf)
 	u32 hi, lo;
 	u64 ns;
 
-	if (!(pf->flags & I40E_FLAG_PTP) || !pf->ptp_tx)
+	if (!test_bit(I40E_FLAG_PTP_ENA, pf->flags) || !pf->ptp_tx)
 		return;
 
 	/* don't attempt to timestamp if we don't have an skb */
@@ -818,7 +818,7 @@ void i40e_ptp_rx_hwtstamp(struct i40e_pf *pf, struct sk_buff *skb, u8 index)
 	/* Since we cannot turn off the Rx timestamp logic if the device is
 	 * doing Tx timestamping, check if Rx timestamping is configured.
 	 */
-	if (!(pf->flags & I40E_FLAG_PTP) || !pf->ptp_rx)
+	if (!test_bit(I40E_FLAG_PTP_ENA, pf->flags) || !pf->ptp_rx)
 		return;
 
 	hw = &pf->hw;
@@ -924,7 +924,7 @@ int i40e_ptp_get_ts_config(struct i40e_pf *pf, struct ifreq *ifr)
 {
 	struct hwtstamp_config *config = &pf->tstamp_config;
 
-	if (!(pf->flags & I40E_FLAG_PTP))
+	if (!test_bit(I40E_FLAG_PTP_ENA, pf->flags))
 		return -EOPNOTSUPP;
 
 	return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ?
@@ -1071,7 +1071,7 @@ static void i40e_ptp_set_pins_hw(struct i40e_pf *pf)
 static int i40e_ptp_set_pins(struct i40e_pf *pf,
 			     struct i40e_ptp_pins_settings *pins)
 {
-	enum i40e_can_set_pins_t pin_caps = i40e_can_set_pins(pf);
+	enum i40e_can_set_pins pin_caps = i40e_can_set_pins(pf);
 	int i = 0;
 
 	if (pin_caps == CANT_DO_PINS)
@@ -1211,7 +1211,7 @@ static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf,
 	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
 	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
-		if (!(pf->hw_features & I40E_HW_PTP_L4_CAPABLE))
+		if (!test_bit(I40E_HW_CAP_PTP_L4, pf->hw.caps))
 			return -ERANGE;
 		pf->ptp_rx = true;
 		tsyntype = I40E_PRTTSYN_CTL1_V1MESSTYPE0_MASK |
@@ -1225,7 +1225,7 @@ static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf,
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
-		if (!(pf->hw_features & I40E_HW_PTP_L4_CAPABLE))
+		if (!test_bit(I40E_HW_CAP_PTP_L4, pf->hw.caps))
 			return -ERANGE;
 		fallthrough;
 	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
@@ -1234,7 +1234,7 @@ static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf,
 		pf->ptp_rx = true;
 		tsyntype = I40E_PRTTSYN_CTL1_V2MESSTYPE0_MASK |
 			   I40E_PRTTSYN_CTL1_TSYNTYPE_V2;
-		if (pf->hw_features & I40E_HW_PTP_L4_CAPABLE) {
+		if (test_bit(I40E_HW_CAP_PTP_L4, pf->hw.caps)) {
 			tsyntype |= I40E_PRTTSYN_CTL1_UDP_ENA_MASK;
 			config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		} else {
@@ -1308,7 +1308,7 @@ int i40e_ptp_set_ts_config(struct i40e_pf *pf, struct ifreq *ifr)
 	struct hwtstamp_config config;
 	int err;
 
-	if (!(pf->flags & I40E_FLAG_PTP))
+	if (!test_bit(I40E_FLAG_PTP_ENA, pf->flags))
 		return -EOPNOTSUPP;
 
 	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
@@ -1426,7 +1426,7 @@ static long i40e_ptp_create_clock(struct i40e_pf *pf)
 void i40e_ptp_save_hw_time(struct i40e_pf *pf)
 {
 	/* don't try to access the PTP clock if it's not enabled */
-	if (!(pf->flags & I40E_FLAG_PTP))
+	if (!test_bit(I40E_FLAG_PTP_ENA, pf->flags))
 		return;
 
 	i40e_ptp_gettimex(&pf->ptp_caps, &pf->ptp_prev_hw_time, NULL);
@@ -1480,10 +1480,10 @@ void i40e_ptp_init(struct i40e_pf *pf)
 	/* Only one PF is assigned to control 1588 logic per port. Do not
 	 * enable any support for PFs not assigned via PRTTSYN_CTL0.PF_ID
 	 */
-	pf_id = (rd32(hw, I40E_PRTTSYN_CTL0) & I40E_PRTTSYN_CTL0_PF_ID_MASK) >>
-		I40E_PRTTSYN_CTL0_PF_ID_SHIFT;
+	pf_id = FIELD_GET(I40E_PRTTSYN_CTL0_PF_ID_MASK,
+			  rd32(hw, I40E_PRTTSYN_CTL0));
 	if (hw->pf_id != pf_id) {
-		pf->flags &= ~I40E_FLAG_PTP;
+		clear_bit(I40E_FLAG_PTP_ENA, pf->flags);
 		dev_info(&pf->pdev->dev, "%s: PTP not supported on %s\n",
 			 __func__,
 			 netdev->name);
@@ -1504,7 +1504,7 @@ void i40e_ptp_init(struct i40e_pf *pf)
 
 		if (pf->hw.debug_mask & I40E_DEBUG_LAN)
 			dev_info(&pf->pdev->dev, "PHC enabled\n");
-		pf->flags |= I40E_FLAG_PTP;
+		set_bit(I40E_FLAG_PTP_ENA, pf->flags);
 
 		/* Ensure the clocks are running. */
 		regval = rd32(hw, I40E_PRTTSYN_CTL0);
@@ -1539,7 +1539,7 @@ void i40e_ptp_stop(struct i40e_pf *pf)
 	struct i40e_hw *hw = &pf->hw;
 	u32 regval;
 
-	pf->flags &= ~I40E_FLAG_PTP;
+	clear_bit(I40E_FLAG_PTP_ENA, pf->flags);
 	pf->ptp_tx = false;
 	pf->ptp_rx = false;
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h
index f408fcf23ce8..14ab642cafdb 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_register.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_register.h
@@ -207,7 +207,7 @@
 #define I40E_GLGEN_MSCA_OPCODE_SHIFT 26
 #define I40E_GLGEN_MSCA_OPCODE_MASK(_i) I40E_MASK(_i, I40E_GLGEN_MSCA_OPCODE_SHIFT)
 #define I40E_GLGEN_MSCA_STCODE_SHIFT 28
-#define I40E_GLGEN_MSCA_STCODE_MASK I40E_MASK(0x1, I40E_GLGEN_MSCA_STCODE_SHIFT)
+#define I40E_GLGEN_MSCA_STCODE_MASK(_i) I40E_MASK(_i, I40E_GLGEN_MSCA_STCODE_SHIFT)
 #define I40E_GLGEN_MSCA_MDICMD_SHIFT 30
 #define I40E_GLGEN_MSCA_MDICMD_MASK I40E_MASK(0x1, I40E_GLGEN_MSCA_MDICMD_SHIFT)
 #define I40E_GLGEN_MSCA_MDIINPROGEN_SHIFT 31
@@ -863,16 +863,6 @@
 #define I40E_PFPM_WUFC 0x0006B400 /* Reset: POR */
 #define I40E_PFPM_WUFC_MAG_SHIFT 1
 #define I40E_PFPM_WUFC_MAG_MASK I40E_MASK(0x1, I40E_PFPM_WUFC_MAG_SHIFT)
-#define I40E_VF_ARQBAH1 0x00006000 /* Reset: EMPR */
-#define I40E_VF_ARQBAL1 0x00006C00 /* Reset: EMPR */
-#define I40E_VF_ARQH1 0x00007400 /* Reset: EMPR */
-#define I40E_VF_ARQLEN1 0x00008000 /* Reset: EMPR */
-#define I40E_VF_ARQT1 0x00007000 /* Reset: EMPR */
-#define I40E_VF_ATQBAH1 0x00007800 /* Reset: EMPR */
-#define I40E_VF_ATQBAL1 0x00007C00 /* Reset: EMPR */
-#define I40E_VF_ATQH1 0x00006400 /* Reset: EMPR */
-#define I40E_VF_ATQLEN1 0x00006800 /* Reset: EMPR */
-#define I40E_VF_ATQT1 0x00008400 /* Reset: EMPR */
 #define I40E_VFQF_HLUT_MAX_INDEX 15
 
 
@@ -899,6 +889,7 @@
 #define I40E_GLQF_ORT_FLX_PAYLOAD_SHIFT 7
 #define I40E_GLQF_ORT_FLX_PAYLOAD_MASK I40E_MASK(0x1, I40E_GLQF_ORT_FLX_PAYLOAD_SHIFT)
 #define I40E_GLQF_FDEVICTENA(_i) (0x00270384 + ((_i) * 4)) /* _i=0...1 */ /* Reset: CORER */
+#define I40E_FDEVICT_PCTYPE_DEFAULT 0xc03
 /* Redefined for X722 family */
 #define I40E_GLGEN_STAT_CLEAR 0x00390004 /* Reset: CORER */
 #endif /* _I40E_REGISTER_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index dd410b15000f..971ba3322038 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -33,19 +33,16 @@ static void i40e_fdir(struct i40e_ring *tx_ring,
 	i++;
 	tx_ring->next_to_use = (i < tx_ring->count) ? i : 0;
 
-	flex_ptype = I40E_TXD_FLTR_QW0_QINDEX_MASK &
-		     (fdata->q_index << I40E_TXD_FLTR_QW0_QINDEX_SHIFT);
+	flex_ptype = FIELD_PREP(I40E_TXD_FLTR_QW0_QINDEX_MASK, fdata->q_index);
 
-	flex_ptype |= I40E_TXD_FLTR_QW0_FLEXOFF_MASK &
-		      (fdata->flex_off << I40E_TXD_FLTR_QW0_FLEXOFF_SHIFT);
+	flex_ptype |= FIELD_PREP(I40E_TXD_FLTR_QW0_FLEXOFF_MASK,
+				 fdata->flex_off);
 
-	flex_ptype |= I40E_TXD_FLTR_QW0_PCTYPE_MASK &
-		      (fdata->pctype << I40E_TXD_FLTR_QW0_PCTYPE_SHIFT);
+	flex_ptype |= FIELD_PREP(I40E_TXD_FLTR_QW0_PCTYPE_MASK, fdata->pctype);
 
 	/* Use LAN VSI Id if not programmed by user */
-	flex_ptype |= I40E_TXD_FLTR_QW0_DEST_VSI_MASK &
-		      ((u32)(fdata->dest_vsi ? : pf->vsi[pf->lan_vsi]->id) <<
-		       I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT);
+	flex_ptype |= FIELD_PREP(I40E_TXD_FLTR_QW0_DEST_VSI_MASK,
+				 fdata->dest_vsi ? : pf->vsi[pf->lan_vsi]->id);
 
 	dtype_cmd = I40E_TX_DESC_DTYPE_FILTER_PROG;
 
@@ -55,17 +52,15 @@ static void i40e_fdir(struct i40e_ring *tx_ring,
 		     I40E_FILTER_PROGRAM_DESC_PCMD_REMOVE <<
 		     I40E_TXD_FLTR_QW1_PCMD_SHIFT;
 
-	dtype_cmd |= I40E_TXD_FLTR_QW1_DEST_MASK &
-		     (fdata->dest_ctl << I40E_TXD_FLTR_QW1_DEST_SHIFT);
+	dtype_cmd |= FIELD_PREP(I40E_TXD_FLTR_QW1_DEST_MASK, fdata->dest_ctl);
 
-	dtype_cmd |= I40E_TXD_FLTR_QW1_FD_STATUS_MASK &
-		     (fdata->fd_status << I40E_TXD_FLTR_QW1_FD_STATUS_SHIFT);
+	dtype_cmd |= FIELD_PREP(I40E_TXD_FLTR_QW1_FD_STATUS_MASK,
+				fdata->fd_status);
 
 	if (fdata->cnt_index) {
 		dtype_cmd |= I40E_TXD_FLTR_QW1_CNT_ENA_MASK;
-		dtype_cmd |= I40E_TXD_FLTR_QW1_CNTINDEX_MASK &
-			     ((u32)fdata->cnt_index <<
-			      I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT);
+		dtype_cmd |= FIELD_PREP(I40E_TXD_FLTR_QW1_CNTINDEX_MASK,
+					fdata->cnt_index);
 	}
 
 	fdir_desc->qindex_flex_ptype_vsi = cpu_to_le32(flex_ptype);
@@ -464,7 +459,7 @@ static int i40e_add_del_fdir_tcp(struct i40e_vsi *vsi,
 			       &pf->fd_tcp6_filter_cnt);
 
 	if (add) {
-		if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
+		if (test_bit(I40E_FLAG_FD_ATR_ENA, pf->flags) &&
 		    I40E_DEBUG_FD & pf->hw.debug_mask)
 			dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n");
 		set_bit(__I40E_FD_ATR_AUTO_DISABLED, pf->state);
@@ -691,8 +686,7 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring, u64 qword0_raw,
 	u32 error;
 
 	qw0 = (struct i40e_16b_rx_wb_qw0 *)&qword0_raw;
-	error = (qword1 & I40E_RX_PROG_STATUS_DESC_QW1_ERROR_MASK) >>
-		I40E_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT;
+	error = FIELD_GET(I40E_RX_PROG_STATUS_DESC_QW1_ERROR_MASK, qword1);
 
 	if (error == BIT(I40E_RX_PROG_STATUS_DESC_FD_TBL_FULL_SHIFT)) {
 		pf->fd_inv = le32_to_cpu(qw0->hi_dword.fd_id);
@@ -734,7 +728,7 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring, u64 qword0_raw,
 		 * FD ATR/SB and then re-enable it when there is room.
 		 */
 		if (fcnt_prog >= (fcnt_avail - I40E_FDIR_BUFFER_FULL_MARGIN)) {
-			if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) &&
+			if (test_bit(I40E_FLAG_FD_SB_ENA, pf->flags) &&
 			    !test_and_set_bit(__I40E_FD_SB_AUTO_DISABLED,
 					      pf->state))
 				if (I40E_DEBUG_FD & pf->hw.debug_mask)
@@ -1071,7 +1065,7 @@ static void i40e_enable_wb_on_itr(struct i40e_vsi *vsi,
 	if (q_vector->arm_wb_state)
 		return;
 
-	if (vsi->back->flags & I40E_FLAG_MSIX_ENABLED) {
+	if (test_bit(I40E_FLAG_MSIX_ENA, vsi->back->flags)) {
 		val = I40E_PFINT_DYN_CTLN_WB_ON_ITR_MASK |
 		      I40E_PFINT_DYN_CTLN_ITR_INDX_MASK; /* set noitr */
 
@@ -1095,7 +1089,7 @@ static void i40e_enable_wb_on_itr(struct i40e_vsi *vsi,
  **/
 void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector)
 {
-	if (vsi->back->flags & I40E_FLAG_MSIX_ENABLED) {
+	if (test_bit(I40E_FLAG_MSIX_ENA, vsi->back->flags)) {
 		u32 val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
 			  I40E_PFINT_DYN_CTLN_ITR_INDX_MASK | /* set noitr */
 			  I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK |
@@ -1403,8 +1397,7 @@ void i40e_clean_programming_status(struct i40e_ring *rx_ring, u64 qword0_raw,
 {
 	u8 id;
 
-	id = (qword1 & I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK) >>
-		  I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT;
+	id = FIELD_GET(I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK, qword1);
 
 	if (id == I40E_RX_PROG_STATUS_DESC_FD_FILTER_STATUS)
 		i40e_fd_handle_status(rx_ring, qword0_raw, qword1, id);
@@ -1764,11 +1757,9 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 	u64 qword;
 
 	qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-	ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >> I40E_RXD_QW1_PTYPE_SHIFT;
-	rx_error = (qword & I40E_RXD_QW1_ERROR_MASK) >>
-		   I40E_RXD_QW1_ERROR_SHIFT;
-	rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) >>
-		    I40E_RXD_QW1_STATUS_SHIFT;
+	ptype = FIELD_GET(I40E_RXD_QW1_PTYPE_MASK, qword);
+	rx_error = FIELD_GET(I40E_RXD_QW1_ERROR_MASK, qword);
+	rx_status = FIELD_GET(I40E_RXD_QW1_STATUS_MASK, qword);
 	decoded = decode_rx_desc_ptype(ptype);
 
 	skb->ip_summed = CHECKSUM_NONE;
@@ -1901,13 +1892,10 @@ void i40e_process_skb_fields(struct i40e_ring *rx_ring,
 			     union i40e_rx_desc *rx_desc, struct sk_buff *skb)
 {
 	u64 qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-	u32 rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) >>
-			I40E_RXD_QW1_STATUS_SHIFT;
+	u32 rx_status = FIELD_GET(I40E_RXD_QW1_STATUS_MASK, qword);
 	u32 tsynvalid = rx_status & I40E_RXD_QW1_STATUS_TSYNVALID_MASK;
-	u32 tsyn = (rx_status & I40E_RXD_QW1_STATUS_TSYNINDX_MASK) >>
-		   I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT;
-	u8 rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >>
-		      I40E_RXD_QW1_PTYPE_SHIFT;
+	u32 tsyn = FIELD_GET(I40E_RXD_QW1_STATUS_TSYNINDX_MASK, rx_status);
+	u8 rx_ptype = FIELD_GET(I40E_RXD_QW1_PTYPE_MASK, qword);
 
 	if (unlikely(tsynvalid))
 		i40e_ptp_rx_hwtstamp(rx_ring->vsi->back, skb, tsyn);
@@ -2554,8 +2542,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget,
 			continue;
 		}
 
-		size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
-		       I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
+		size = FIELD_GET(I40E_RXD_QW1_LENGTH_PBUF_MASK, qword);
 		if (!size)
 			break;
 
@@ -2699,7 +2686,7 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
 	u32 intval;
 
 	/* If we don't have MSIX, then we only need to re-enable icr0 */
-	if (!(vsi->back->flags & I40E_FLAG_MSIX_ENABLED)) {
+	if (!test_bit(I40E_FLAG_MSIX_ENA, vsi->back->flags)) {
 		i40e_irq_dynamic_enable_icr0(vsi->back);
 		return;
 	}
@@ -2888,7 +2875,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	u16 i;
 
 	/* make sure ATR is enabled */
-	if (!(pf->flags & I40E_FLAG_FD_ATR_ENABLED))
+	if (!test_bit(I40E_FLAG_FD_ATR_ENA, pf->flags))
 		return;
 
 	if (test_bit(__I40E_FD_ATR_AUTO_DISABLED, pf->state))
@@ -2933,7 +2920,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	/* Due to lack of space, no more new filters can be programmed */
 	if (th->syn && test_bit(__I40E_FD_ATR_AUTO_DISABLED, pf->state))
 		return;
-	if (pf->flags & I40E_FLAG_HW_ATR_EVICT_ENABLED) {
+	if (test_bit(I40E_FLAG_HW_ATR_EVICT_ENA, pf->flags)) {
 		/* HW ATR eviction will take care of removing filters on FIN
 		 * and RST packets.
 		 */
@@ -2959,8 +2946,8 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	i++;
 	tx_ring->next_to_use = (i < tx_ring->count) ? i : 0;
 
-	flex_ptype = (tx_ring->queue_index << I40E_TXD_FLTR_QW0_QINDEX_SHIFT) &
-		      I40E_TXD_FLTR_QW0_QINDEX_MASK;
+	flex_ptype = FIELD_PREP(I40E_TXD_FLTR_QW0_QINDEX_MASK,
+				tx_ring->queue_index);
 	flex_ptype |= (tx_flags & I40E_TX_FLAGS_IPV4) ?
 		      (I40E_FILTER_PCTYPE_NONF_IPV4_TCP <<
 		       I40E_TXD_FLTR_QW0_PCTYPE_SHIFT) :
@@ -2986,16 +2973,14 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	dtype_cmd |= I40E_TXD_FLTR_QW1_CNT_ENA_MASK;
 	if (!(tx_flags & I40E_TX_FLAGS_UDP_TUNNEL))
 		dtype_cmd |=
-			((u32)I40E_FD_ATR_STAT_IDX(pf->hw.pf_id) <<
-			I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) &
-			I40E_TXD_FLTR_QW1_CNTINDEX_MASK;
+			FIELD_PREP(I40E_TXD_FLTR_QW1_CNTINDEX_MASK,
+				   I40E_FD_ATR_STAT_IDX(pf->hw.pf_id));
 	else
 		dtype_cmd |=
-			((u32)I40E_FD_ATR_TUNNEL_STAT_IDX(pf->hw.pf_id) <<
-			I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) &
-			I40E_TXD_FLTR_QW1_CNTINDEX_MASK;
+			FIELD_PREP(I40E_TXD_FLTR_QW1_CNTINDEX_MASK,
+				   I40E_FD_ATR_TUNNEL_STAT_IDX(pf->hw.pf_id));
 
-	if (pf->flags & I40E_FLAG_HW_ATR_EVICT_ENABLED)
+	if (test_bit(I40E_FLAG_HW_ATR_EVICT_ENA, pf->flags))
 		dtype_cmd |= I40E_TXD_FLTR_QW1_ATR_MASK;
 
 	fdir_desc->qindex_flex_ptype_vsi = cpu_to_le32(flex_ptype);
@@ -3053,7 +3038,7 @@ static inline int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
 		tx_flags |= I40E_TX_FLAGS_SW_VLAN;
 	}
 
-	if (!(tx_ring->vsi->back->flags & I40E_FLAG_DCB_ENABLED))
+	if (!test_bit(I40E_FLAG_DCB_ENA, tx_ring->vsi->back->flags))
 		goto out;
 
 	/* Insert 802.1p priority into VLAN header */
@@ -3229,7 +3214,7 @@ static int i40e_tsyn(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	 * we are not already transmitting a packet to be timestamped
 	 */
 	pf = i40e_netdev_to_pf(tx_ring->netdev);
-	if (!(pf->flags & I40E_FLAG_PTP))
+	if (!test_bit(I40E_FLAG_PTP_ENA, pf->flags))
 		return 0;
 
 	if (pf->ptp_tx &&
@@ -3601,8 +3586,7 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 	if (tx_flags & I40E_TX_FLAGS_HW_VLAN) {
 		td_cmd |= I40E_TX_DESC_CMD_IL2TAG1;
-		td_tag = (tx_flags & I40E_TX_FLAGS_VLAN_MASK) >>
-			 I40E_TX_FLAGS_VLAN_SHIFT;
+		td_tag = FIELD_GET(I40E_TX_FLAGS_VLAN_MASK, tx_flags);
 	}
 
 	first->tx_flags = tx_flags;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 421fe5675584..abf15067eb5d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -58,7 +58,7 @@ static inline u16 i40e_intrl_usec_to_reg(int intrl)
  * mentioning ITR_INDX, ITR_NONE cannot be used as an index 'n' into any
  * register but instead is a special value meaning "don't update" ITR0/1/2.
  */
-enum i40e_dyn_idx_t {
+enum i40e_dyn_idx {
 	I40E_IDX_ITR0 = 0,
 	I40E_IDX_ITR1 = 1,
 	I40E_IDX_ITR2 = 2,
@@ -92,8 +92,8 @@ enum i40e_dyn_idx_t {
 	BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
 
 #define i40e_pf_get_default_rss_hena(pf) \
-	(((pf)->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) ? \
-	  I40E_DEFAULT_RSS_HENA_EXPANDED : I40E_DEFAULT_RSS_HENA)
+	(test_bit(I40E_HW_CAP_MULTI_TCP_UDP_RSS_PCTYPE, (pf)->hw.caps) ? \
+	 I40E_DEFAULT_RSS_HENA_EXPANDED : I40E_DEFAULT_RSS_HENA)
 
 /* Supported Rx Buffer Sizes (a multiple of 128) */
 #define I40E_RXBUFFER_256   256
@@ -306,7 +306,7 @@ struct i40e_rx_queue_stats {
 	u64 page_busy_count;
 };
 
-enum i40e_ring_state_t {
+enum i40e_ring_state {
 	__I40E_TX_FDIR_INIT_DONE,
 	__I40E_TX_XPS_INIT_DONE,
 	__I40E_RING_STATE_NBITS /* must be last */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index aff6dc6afbe2..d9031499697e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -37,11 +37,11 @@ typedef void (*I40E_ADMINQ_CALLBACK)(struct i40e_hw *, struct i40e_aq_desc *);
 #define I40E_QTX_CTL_VM_QUEUE	0x1
 #define I40E_QTX_CTL_PF_QUEUE	0x2
 
-#define I40E_MDIO_CLAUSE22_STCODE_MASK		I40E_GLGEN_MSCA_STCODE_MASK
+#define I40E_MDIO_CLAUSE22_STCODE_MASK		I40E_GLGEN_MSCA_STCODE_MASK(1)
 #define I40E_MDIO_CLAUSE22_OPCODE_WRITE_MASK	I40E_GLGEN_MSCA_OPCODE_MASK(1)
 #define I40E_MDIO_CLAUSE22_OPCODE_READ_MASK	I40E_GLGEN_MSCA_OPCODE_MASK(2)
 
-#define I40E_MDIO_CLAUSE45_STCODE_MASK		I40E_GLGEN_MSCA_STCODE_MASK
+#define I40E_MDIO_CLAUSE45_STCODE_MASK		I40E_GLGEN_MSCA_STCODE_MASK(0)
 #define I40E_MDIO_CLAUSE45_OPCODE_ADDRESS_MASK	I40E_GLGEN_MSCA_OPCODE_MASK(0)
 #define I40E_MDIO_CLAUSE45_OPCODE_WRITE_MASK	I40E_GLGEN_MSCA_OPCODE_MASK(1)
 #define I40E_MDIO_CLAUSE45_OPCODE_READ_MASK	I40E_GLGEN_MSCA_OPCODE_MASK(3)
@@ -64,9 +64,7 @@ typedef void (*I40E_ADMINQ_CALLBACK)(struct i40e_hw *, struct i40e_aq_desc *);
 enum i40e_mac_type {
 	I40E_MAC_UNKNOWN = 0,
 	I40E_MAC_XL710,
-	I40E_MAC_VF,
 	I40E_MAC_X722,
-	I40E_MAC_X722_VF,
 	I40E_MAC_GENERIC,
 };
 
@@ -272,9 +270,7 @@ struct i40e_mac_info {
 	enum i40e_mac_type type;
 	u8 addr[ETH_ALEN];
 	u8 perm_addr[ETH_ALEN];
-	u8 san_addr[ETH_ALEN];
 	u8 port_addr[ETH_ALEN];
-	u16 max_fcoeq;
 };
 
 enum i40e_aq_resources_ids {
@@ -482,6 +478,36 @@ struct i40e_dcbx_config {
 	struct i40e_dcb_app_priority_table app[I40E_DCBX_MAX_APPS];
 };
 
+enum i40e_hw_flags {
+	I40E_HW_CAP_AQ_SRCTL_ACCESS_ENABLE,
+	I40E_HW_CAP_802_1AD,
+	I40E_HW_CAP_AQ_PHY_ACCESS,
+	I40E_HW_CAP_NVM_READ_REQUIRES_LOCK,
+	I40E_HW_CAP_FW_LLDP_STOPPABLE,
+	I40E_HW_CAP_FW_LLDP_PERSISTENT,
+	I40E_HW_CAP_AQ_PHY_ACCESS_EXTENDED,
+	I40E_HW_CAP_X722_FEC_REQUEST,
+	I40E_HW_CAP_RSS_AQ,
+	I40E_HW_CAP_128_QP_RSS,
+	I40E_HW_CAP_ATR_EVICT,
+	I40E_HW_CAP_WB_ON_ITR,
+	I40E_HW_CAP_MULTI_TCP_UDP_RSS_PCTYPE,
+	I40E_HW_CAP_NO_PCI_LINK_CHECK,
+	I40E_HW_CAP_100M_SGMII,
+	I40E_HW_CAP_NO_DCB_SUPPORT,
+	I40E_HW_CAP_USE_SET_LLDP_MIB,
+	I40E_HW_CAP_GENEVE_OFFLOAD,
+	I40E_HW_CAP_PTP_L4,
+	I40E_HW_CAP_WOL_MC_MAGIC_PKT_WAKE,
+	I40E_HW_CAP_CRT_RETIMER,
+	I40E_HW_CAP_OUTER_UDP_CSUM,
+	I40E_HW_CAP_PHY_CONTROLS_LEDS,
+	I40E_HW_CAP_STOP_FW_LLDP,
+	I40E_HW_CAP_PORT_ID_VALID,
+	I40E_HW_CAP_RESTART_AUTONEG,
+	I40E_HW_CAPS_NBITS,
+};
+
 /* Port hardware description */
 struct i40e_hw {
 	u8 __iomem *hw_addr;
@@ -546,16 +572,7 @@ struct i40e_hw {
 	struct i40e_dcbx_config remote_dcbx_config; /* Peer Cfg */
 	struct i40e_dcbx_config desired_dcbx_config; /* CEE Desired Cfg */
 
-#define I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE BIT_ULL(0)
-#define I40E_HW_FLAG_802_1AD_CAPABLE        BIT_ULL(1)
-#define I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE  BIT_ULL(2)
-#define I40E_HW_FLAG_NVM_READ_REQUIRES_LOCK BIT_ULL(3)
-#define I40E_HW_FLAG_FW_LLDP_STOPPABLE      BIT_ULL(4)
-#define I40E_HW_FLAG_FW_LLDP_PERSISTENT     BIT_ULL(5)
-#define I40E_HW_FLAG_AQ_PHY_ACCESS_EXTENDED BIT_ULL(6)
-#define I40E_HW_FLAG_DROP_MODE              BIT_ULL(7)
-#define I40E_HW_FLAG_X722_FEC_REQUEST_CAPABLE BIT_ULL(8)
-	u64 flags;
+	DECLARE_BITMAP(caps, I40E_HW_CAPS_NBITS);
 
 	/* Used in set switch config AQ command */
 	u16 switch_tag;
@@ -567,12 +584,6 @@ struct i40e_hw {
 	char err_str[16];
 };
 
-static inline bool i40e_is_vf(struct i40e_hw *hw)
-{
-	return (hw->mac.type == I40E_MAC_VF ||
-		hw->mac.type == I40E_MAC_X722_VF);
-}
-
 struct i40e_driver_version {
 	u8 major_version;
 	u8 minor_version;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 08d7edccfb8d..908cdbd3ec5d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -154,6 +154,32 @@ void i40e_vc_notify_reset(struct i40e_pf *pf)
 			     (u8 *)&pfe, sizeof(struct virtchnl_pf_event));
 }
 
+#ifdef CONFIG_PCI_IOV
+void i40e_restore_all_vfs_msi_state(struct pci_dev *pdev)
+{
+	u16 vf_id;
+	u16 pos;
+
+	/* Continue only if this is a PF */
+	if (!pdev->is_physfn)
+		return;
+
+	if (!pci_num_vf(pdev))
+		return;
+
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV);
+	if (pos) {
+		struct pci_dev *vf_dev = NULL;
+
+		pci_read_config_word(pdev, pos + PCI_SRIOV_VF_DID, &vf_id);
+		while ((vf_dev = pci_get_device(pdev->vendor, vf_id, vf_dev))) {
+			if (vf_dev->is_virtfn && vf_dev->physfn == pdev)
+				pci_restore_msi_state(vf_dev);
+		}
+	}
+}
+#endif /* CONFIG_PCI_IOV */
+
 /**
  * i40e_vc_notify_vf_reset
  * @vf: pointer to the VF structure
@@ -474,10 +500,10 @@ static void i40e_release_rdma_qvlist(struct i40e_vf *vf)
 			 */
 			reg_idx = (msix_vf - 1) * vf->vf_id + qv_info->ceq_idx;
 			reg = rd32(hw, I40E_VPINT_CEQCTL(reg_idx));
-			next_q_index = (reg & I40E_VPINT_CEQCTL_NEXTQ_INDX_MASK)
-					>> I40E_VPINT_CEQCTL_NEXTQ_INDX_SHIFT;
-			next_q_type = (reg & I40E_VPINT_CEQCTL_NEXTQ_TYPE_MASK)
-					>> I40E_VPINT_CEQCTL_NEXTQ_TYPE_SHIFT;
+			next_q_index = FIELD_GET(I40E_VPINT_CEQCTL_NEXTQ_INDX_MASK,
+						 reg);
+			next_q_type = FIELD_GET(I40E_VPINT_CEQCTL_NEXTQ_TYPE_MASK,
+						reg);
 
 			reg_idx = ((msix_vf - 1) * vf->vf_id) + (v_idx - 1);
 			reg = (next_q_index &
@@ -555,10 +581,10 @@ i40e_config_rdma_qvlist(struct i40e_vf *vf,
 		 * queue on top. Also link it with the new queue in CEQCTL.
 		 */
 		reg = rd32(hw, I40E_VPINT_LNKLSTN(reg_idx));
-		next_q_idx = ((reg & I40E_VPINT_LNKLSTN_FIRSTQ_INDX_MASK) >>
-				I40E_VPINT_LNKLSTN_FIRSTQ_INDX_SHIFT);
-		next_q_type = ((reg & I40E_VPINT_LNKLSTN_FIRSTQ_TYPE_MASK) >>
-				I40E_VPINT_LNKLSTN_FIRSTQ_TYPE_SHIFT);
+		next_q_idx = FIELD_GET(I40E_VPINT_LNKLSTN_FIRSTQ_INDX_MASK,
+				       reg);
+		next_q_type = FIELD_GET(I40E_VPINT_LNKLSTN_FIRSTQ_TYPE_MASK,
+					reg);
 
 		if (qv_info->ceq_idx != I40E_QUEUE_INVALID_IDX) {
 			reg_idx = (msix_vf - 1) * vf->vf_id + qv_info->ceq_idx;
@@ -659,11 +685,9 @@ static int i40e_config_vsi_tx_queue(struct i40e_vf *vf, u16 vsi_id,
 
 	/* associate this queue with the PCI VF function */
 	qtx_ctl = I40E_QTX_CTL_VF_QUEUE;
-	qtx_ctl |= ((hw->pf_id << I40E_QTX_CTL_PF_INDX_SHIFT)
-		    & I40E_QTX_CTL_PF_INDX_MASK);
-	qtx_ctl |= (((vf->vf_id + hw->func_caps.vf_base_id)
-		     << I40E_QTX_CTL_VFVM_INDX_SHIFT)
-		    & I40E_QTX_CTL_VFVM_INDX_MASK);
+	qtx_ctl |= FIELD_PREP(I40E_QTX_CTL_PF_INDX_MASK, hw->pf_id);
+	qtx_ctl |= FIELD_PREP(I40E_QTX_CTL_VFVM_INDX_MASK,
+			      vf->vf_id + hw->func_caps.vf_base_id);
 	wr32(hw, I40E_QTX_CTL(pf_queue_id), qtx_ctl);
 	i40e_flush(hw);
 
@@ -1808,7 +1832,7 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs)
 	if (pci_num_vf(pf->pdev) != num_alloc_vfs) {
 		ret = pci_enable_sriov(pf->pdev, num_alloc_vfs);
 		if (ret) {
-			pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED;
+			clear_bit(I40E_FLAG_VEB_MODE_ENA, pf->flags);
 			pf->num_alloc_vfs = 0;
 			goto err_iov;
 		}
@@ -1919,8 +1943,8 @@ int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
 	}
 
 	if (num_vfs) {
-		if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
-			pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
+		if (!test_bit(I40E_FLAG_VEB_MODE_ENA, pf->flags)) {
+			set_bit(I40E_FLAG_VEB_MODE_ENA, pf->flags);
 			i40e_do_reset_safe(pf, I40E_PF_RESET_AND_REBUILD_FLAG);
 		}
 		ret = i40e_pci_sriov_enable(pdev, num_vfs);
@@ -1929,7 +1953,7 @@ int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
 
 	if (!pci_vfs_assigned(pf->pdev)) {
 		i40e_free_vfs(pf);
-		pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED;
+		clear_bit(I40E_FLAG_VEB_MODE_ENA, pf->flags);
 		i40e_do_reset_safe(pf, I40E_PF_RESET_AND_REBUILD_FLAG);
 	} else {
 		dev_warn(&pdev->dev, "Unable to free VFs because some are assigned to VMs.\n");
@@ -2137,14 +2161,14 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) {
 		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PF;
 	} else {
-		if ((pf->hw_features & I40E_HW_RSS_AQ_CAPABLE) &&
+		if (test_bit(I40E_HW_CAP_RSS_AQ, pf->hw.caps) &&
 		    (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_AQ))
 			vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_AQ;
 		else
 			vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_REG;
 	}
 
-	if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) {
+	if (test_bit(I40E_HW_CAP_MULTI_TCP_UDP_RSS_PCTYPE, pf->hw.caps)) {
 		if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2)
 			vfres->vf_cap_flags |=
 				VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2;
@@ -2153,12 +2177,12 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ENCAP)
 		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ENCAP;
 
-	if ((pf->hw_features & I40E_HW_OUTER_UDP_CSUM_CAPABLE) &&
+	if (test_bit(I40E_HW_CAP_OUTER_UDP_CSUM, pf->hw.caps) &&
 	    (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM))
 		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM;
 
 	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RX_POLLING) {
-		if (pf->flags & I40E_FLAG_MFP_ENABLED) {
+		if (test_bit(I40E_FLAG_MFP_ENA, pf->flags)) {
 			dev_err(&pf->pdev->dev,
 				"VF %d requested polling mode: this feature is supported only when the device is running in single function per port (SFP) mode\n",
 				 vf->vf_id);
@@ -2168,7 +2192,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RX_POLLING;
 	}
 
-	if (pf->hw_features & I40E_HW_WB_ON_ITR_CAPABLE) {
+	if (test_bit(I40E_HW_CAP_WB_ON_ITR, pf->hw.caps)) {
 		if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_WB_ON_ITR)
 			vfres->vf_cap_flags |=
 					VIRTCHNL_VF_OFFLOAD_WB_ON_ITR;
@@ -2581,6 +2605,14 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg)
 	int aq_ret = 0;
 	int i;
 
+	if (vf->is_disabled_from_host) {
+		aq_ret = -EPERM;
+		dev_info(&pf->pdev->dev,
+			 "Admin has disabled VF %d, will not enable queues\n",
+			 vf->vf_id);
+		goto error_param;
+	}
+
 	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
 		aq_ret = -EINVAL;
 		goto error_param;
@@ -3521,16 +3553,16 @@ static int i40e_validate_cloud_filter(struct i40e_vf *vf,
 	bool found = false;
 	int bkt;
 
-	if (!tc_filter->action) {
+	if (tc_filter->action != VIRTCHNL_ACTION_TC_REDIRECT) {
 		dev_info(&pf->pdev->dev,
-			 "VF %d: Currently ADq doesn't support Drop Action\n",
-			 vf->vf_id);
+			 "VF %d: ADQ doesn't support this action (%d)\n",
+			 vf->vf_id, tc_filter->action);
 		goto err;
 	}
 
 	/* action_meta is TC number here to which the filter is applied */
 	if (!tc_filter->action_meta ||
-	    tc_filter->action_meta > I40E_MAX_VF_VSI) {
+	    tc_filter->action_meta > vf->num_tc) {
 		dev_info(&pf->pdev->dev, "VF %d: Invalid TC number %u\n",
 			 vf->vf_id, tc_filter->action_meta);
 		goto err;
@@ -3844,7 +3876,7 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_vsi *vsi = NULL;
 	int aq_ret = 0;
-	int i, ret;
+	int i;
 
 	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
 		aq_ret = -EINVAL;
@@ -3868,8 +3900,10 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
 	}
 
 	cfilter = kzalloc(sizeof(*cfilter), GFP_KERNEL);
-	if (!cfilter)
-		return -ENOMEM;
+	if (!cfilter) {
+		aq_ret = -ENOMEM;
+		goto err_out;
+	}
 
 	/* parse destination mac address */
 	for (i = 0; i < ETH_ALEN; i++)
@@ -3917,13 +3951,13 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
 
 	/* Adding cloud filter programmed as TC filter */
 	if (tcf.dst_port)
-		ret = i40e_add_del_cloud_filter_big_buf(vsi, cfilter, true);
+		aq_ret = i40e_add_del_cloud_filter_big_buf(vsi, cfilter, true);
 	else
-		ret = i40e_add_del_cloud_filter(vsi, cfilter, true);
-	if (ret) {
+		aq_ret = i40e_add_del_cloud_filter(vsi, cfilter, true);
+	if (aq_ret) {
 		dev_err(&pf->pdev->dev,
 			"VF %d: Failed to add cloud filter, err %pe aq_err %s\n",
-			vf->vf_id, ERR_PTR(ret),
+			vf->vf_id, ERR_PTR(aq_ret),
 			i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
 		goto err_free;
 	}
@@ -4673,9 +4707,8 @@ int i40e_ndo_get_vf_config(struct net_device *netdev,
 
 	ivi->max_tx_rate = vf->tx_rate;
 	ivi->min_tx_rate = 0;
-	ivi->vlan = le16_to_cpu(vsi->info.pvid) & I40E_VLAN_MASK;
-	ivi->qos = (le16_to_cpu(vsi->info.pvid) & I40E_PRIORITY_MASK) >>
-		   I40E_VLAN_PRIORITY_SHIFT;
+	ivi->vlan = le16_get_bits(vsi->info.pvid, I40E_VLAN_MASK);
+	ivi->qos = le16_get_bits(vsi->info.pvid, I40E_PRIORITY_MASK);
 	if (vf->link_forced == false)
 		ivi->linkstate = IFLA_VF_LINK_STATE_AUTO;
 	else if (vf->link_up == true)
@@ -4706,9 +4739,12 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link)
 	struct i40e_link_status *ls = &pf->hw.phy.link_info;
 	struct virtchnl_pf_event pfe;
 	struct i40e_hw *hw = &pf->hw;
+	struct i40e_vsi *vsi;
+	unsigned long q_map;
 	struct i40e_vf *vf;
 	int abs_vf_id;
 	int ret = 0;
+	int tmp;
 
 	if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
 		dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
@@ -4731,17 +4767,38 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link)
 	switch (link) {
 	case IFLA_VF_LINK_STATE_AUTO:
 		vf->link_forced = false;
+		vf->is_disabled_from_host = false;
+		/* reset needed to reinit VF resources */
+		i40e_vc_reset_vf(vf, true);
 		i40e_set_vf_link_state(vf, &pfe, ls);
 		break;
 	case IFLA_VF_LINK_STATE_ENABLE:
 		vf->link_forced = true;
 		vf->link_up = true;
+		vf->is_disabled_from_host = false;
+		/* reset needed to reinit VF resources */
+		i40e_vc_reset_vf(vf, true);
 		i40e_set_vf_link_state(vf, &pfe, ls);
 		break;
 	case IFLA_VF_LINK_STATE_DISABLE:
 		vf->link_forced = true;
 		vf->link_up = false;
 		i40e_set_vf_link_state(vf, &pfe, ls);
+
+		vsi = pf->vsi[vf->lan_vsi_idx];
+		q_map = BIT(vsi->num_queue_pairs) - 1;
+
+		vf->is_disabled_from_host = true;
+
+		/* Try to stop both Tx&Rx rings even if one of the calls fails
+		 * to ensure we stop the rings even in case of errors.
+		 * If any of them returns with an error then the first
+		 * error that occurred will be returned.
+		 */
+		tmp = i40e_ctrl_vf_tx_rings(vsi, q_map, false);
+		ret = i40e_ctrl_vf_rx_rings(vsi, q_map, false);
+
+		ret = tmp ? tmp : ret;
 		break;
 	default:
 		ret = -EINVAL;
@@ -4841,7 +4898,7 @@ int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting)
 		goto out;
 	}
 
-	if (pf->flags & I40E_FLAG_MFP_ENABLED) {
+	if (test_bit(I40E_FLAG_MFP_ENA, pf->flags)) {
 		dev_err(&pf->pdev->dev, "Trusted VF not supported in MFP mode.\n");
 		ret = -EINVAL;
 		goto out;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index 2ee0f8a23248..66f95e2f3146 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -100,6 +100,7 @@ struct i40e_vf {
 	bool link_forced;
 	bool link_up;		/* only valid if VF link is forced */
 	bool spoofchk;
+	bool is_disabled_from_host; /* PF ctrl of VF enable/disable */
 	u16 num_vlan;
 
 	/* ADq related variables */
@@ -137,6 +138,9 @@ int i40e_ndo_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool enable);
 
 void i40e_vc_notify_link_state(struct i40e_pf *pf);
 void i40e_vc_notify_reset(struct i40e_pf *pf);
+#ifdef CONFIG_PCI_IOV
+void i40e_restore_all_vfs_msi_state(struct pci_dev *pdev);
+#endif /* CONFIG_PCI_IOV */
 int i40e_get_vf_stats(struct net_device *netdev, int vf_id,
 		      struct ifla_vf_stats *vf_stats);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index e99fa854d17f..af7d5fa6cdc1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -476,8 +476,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 			continue;
 		}
 
-		size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
-		       I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
+		size = FIELD_GET(I40E_RXD_QW1_LENGTH_PBUF_MASK, qword);
 		if (!size)
 			break;
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index e7ab89dc883a..db8188c7ac4b 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -292,6 +292,7 @@ struct iavf_adapter {
 #define IAVF_FLAG_QUEUES_DISABLED		BIT(17)
 #define IAVF_FLAG_SETUP_NETDEV_FEATURES		BIT(18)
 #define IAVF_FLAG_REINIT_MSIX_NEEDED		BIT(20)
+#define IAVF_FLAG_FDIR_ENABLED			BIT(21)
 /* duplicates for common code */
 #define IAVF_FLAG_DCB_ENABLED			0
 	/* flags for admin queue service task */
@@ -312,7 +313,8 @@ struct iavf_adapter {
 #define IAVF_FLAG_AQ_SET_HENA			BIT_ULL(12)
 #define IAVF_FLAG_AQ_SET_RSS_KEY		BIT_ULL(13)
 #define IAVF_FLAG_AQ_SET_RSS_LUT		BIT_ULL(14)
-#define IAVF_FLAG_AQ_CONFIGURE_PROMISC_MODE	BIT_ULL(15)
+#define IAVF_FLAG_AQ_SET_RSS_HFUNC		BIT_ULL(15)
+#define IAVF_FLAG_AQ_CONFIGURE_PROMISC_MODE	BIT_ULL(16)
 #define IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING	BIT_ULL(19)
 #define IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING	BIT_ULL(20)
 #define IAVF_FLAG_AQ_ENABLE_CHANNELS		BIT_ULL(21)
@@ -414,6 +416,7 @@ struct iavf_adapter {
 	struct iavf_vsi vsi;
 	u32 aq_wait_count;
 	/* RSS stuff */
+	enum virtchnl_rss_algorithm hfunc;
 	u64 hena;
 	u16 rss_key_size;
 	u16 rss_lut_size;
@@ -539,6 +542,7 @@ void iavf_get_hena(struct iavf_adapter *adapter);
 void iavf_set_hena(struct iavf_adapter *adapter);
 void iavf_set_rss_key(struct iavf_adapter *adapter);
 void iavf_set_rss_lut(struct iavf_adapter *adapter);
+void iavf_set_rss_hfunc(struct iavf_adapter *adapter);
 void iavf_enable_vlan_stripping(struct iavf_adapter *adapter);
 void iavf_disable_vlan_stripping(struct iavf_adapter *adapter);
 void iavf_virtchnl_completion(struct iavf_adapter *adapter,
diff --git a/drivers/net/ethernet/intel/iavf/iavf_adminq.c b/drivers/net/ethernet/intel/iavf/iavf_adminq.c
index 9ffbd24d83cb..82fcd18ad660 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_adminq.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_adminq.c
@@ -8,27 +8,6 @@
 #include "iavf_prototype.h"
 
 /**
- *  iavf_adminq_init_regs - Initialize AdminQ registers
- *  @hw: pointer to the hardware structure
- *
- *  This assumes the alloc_asq and alloc_arq functions have already been called
- **/
-static void iavf_adminq_init_regs(struct iavf_hw *hw)
-{
-	/* set head and tail registers in our local struct */
-	hw->aq.asq.tail = IAVF_VF_ATQT1;
-	hw->aq.asq.head = IAVF_VF_ATQH1;
-	hw->aq.asq.len  = IAVF_VF_ATQLEN1;
-	hw->aq.asq.bal  = IAVF_VF_ATQBAL1;
-	hw->aq.asq.bah  = IAVF_VF_ATQBAH1;
-	hw->aq.arq.tail = IAVF_VF_ARQT1;
-	hw->aq.arq.head = IAVF_VF_ARQH1;
-	hw->aq.arq.len  = IAVF_VF_ARQLEN1;
-	hw->aq.arq.bal  = IAVF_VF_ARQBAL1;
-	hw->aq.arq.bah  = IAVF_VF_ARQBAH1;
-}
-
-/**
  *  iavf_alloc_adminq_asq_ring - Allocate Admin Queue send rings
  *  @hw: pointer to the hardware structure
  **/
@@ -259,17 +238,17 @@ static enum iavf_status iavf_config_asq_regs(struct iavf_hw *hw)
 	u32 reg = 0;
 
 	/* Clear Head and Tail */
-	wr32(hw, hw->aq.asq.head, 0);
-	wr32(hw, hw->aq.asq.tail, 0);
+	wr32(hw, IAVF_VF_ATQH1, 0);
+	wr32(hw, IAVF_VF_ATQT1, 0);
 
 	/* set starting point */
-	wr32(hw, hw->aq.asq.len, (hw->aq.num_asq_entries |
+	wr32(hw, IAVF_VF_ATQLEN1, (hw->aq.num_asq_entries |
 				  IAVF_VF_ATQLEN1_ATQENABLE_MASK));
-	wr32(hw, hw->aq.asq.bal, lower_32_bits(hw->aq.asq.desc_buf.pa));
-	wr32(hw, hw->aq.asq.bah, upper_32_bits(hw->aq.asq.desc_buf.pa));
+	wr32(hw, IAVF_VF_ATQBAL1, lower_32_bits(hw->aq.asq.desc_buf.pa));
+	wr32(hw, IAVF_VF_ATQBAH1, upper_32_bits(hw->aq.asq.desc_buf.pa));
 
 	/* Check one register to verify that config was applied */
-	reg = rd32(hw, hw->aq.asq.bal);
+	reg = rd32(hw, IAVF_VF_ATQBAL1);
 	if (reg != lower_32_bits(hw->aq.asq.desc_buf.pa))
 		ret_code = IAVF_ERR_ADMIN_QUEUE_ERROR;
 
@@ -288,20 +267,20 @@ static enum iavf_status iavf_config_arq_regs(struct iavf_hw *hw)
 	u32 reg = 0;
 
 	/* Clear Head and Tail */
-	wr32(hw, hw->aq.arq.head, 0);
-	wr32(hw, hw->aq.arq.tail, 0);
+	wr32(hw, IAVF_VF_ARQH1, 0);
+	wr32(hw, IAVF_VF_ARQT1, 0);
 
 	/* set starting point */
-	wr32(hw, hw->aq.arq.len, (hw->aq.num_arq_entries |
+	wr32(hw, IAVF_VF_ARQLEN1, (hw->aq.num_arq_entries |
 				  IAVF_VF_ARQLEN1_ARQENABLE_MASK));
-	wr32(hw, hw->aq.arq.bal, lower_32_bits(hw->aq.arq.desc_buf.pa));
-	wr32(hw, hw->aq.arq.bah, upper_32_bits(hw->aq.arq.desc_buf.pa));
+	wr32(hw, IAVF_VF_ARQBAL1, lower_32_bits(hw->aq.arq.desc_buf.pa));
+	wr32(hw, IAVF_VF_ARQBAH1, upper_32_bits(hw->aq.arq.desc_buf.pa));
 
 	/* Update tail in the HW to post pre-allocated buffers */
-	wr32(hw, hw->aq.arq.tail, hw->aq.num_arq_entries - 1);
+	wr32(hw, IAVF_VF_ARQT1, hw->aq.num_arq_entries - 1);
 
 	/* Check one register to verify that config was applied */
-	reg = rd32(hw, hw->aq.arq.bal);
+	reg = rd32(hw, IAVF_VF_ARQBAL1);
 	if (reg != lower_32_bits(hw->aq.arq.desc_buf.pa))
 		ret_code = IAVF_ERR_ADMIN_QUEUE_ERROR;
 
@@ -455,11 +434,11 @@ static enum iavf_status iavf_shutdown_asq(struct iavf_hw *hw)
 	}
 
 	/* Stop firmware AdminQ processing */
-	wr32(hw, hw->aq.asq.head, 0);
-	wr32(hw, hw->aq.asq.tail, 0);
-	wr32(hw, hw->aq.asq.len, 0);
-	wr32(hw, hw->aq.asq.bal, 0);
-	wr32(hw, hw->aq.asq.bah, 0);
+	wr32(hw, IAVF_VF_ATQH1, 0);
+	wr32(hw, IAVF_VF_ATQT1, 0);
+	wr32(hw, IAVF_VF_ATQLEN1, 0);
+	wr32(hw, IAVF_VF_ATQBAL1, 0);
+	wr32(hw, IAVF_VF_ATQBAH1, 0);
 
 	hw->aq.asq.count = 0; /* to indicate uninitialized queue */
 
@@ -489,11 +468,11 @@ static enum iavf_status iavf_shutdown_arq(struct iavf_hw *hw)
 	}
 
 	/* Stop firmware AdminQ processing */
-	wr32(hw, hw->aq.arq.head, 0);
-	wr32(hw, hw->aq.arq.tail, 0);
-	wr32(hw, hw->aq.arq.len, 0);
-	wr32(hw, hw->aq.arq.bal, 0);
-	wr32(hw, hw->aq.arq.bah, 0);
+	wr32(hw, IAVF_VF_ARQH1, 0);
+	wr32(hw, IAVF_VF_ARQT1, 0);
+	wr32(hw, IAVF_VF_ARQLEN1, 0);
+	wr32(hw, IAVF_VF_ARQBAL1, 0);
+	wr32(hw, IAVF_VF_ARQBAH1, 0);
 
 	hw->aq.arq.count = 0; /* to indicate uninitialized queue */
 
@@ -529,9 +508,6 @@ enum iavf_status iavf_init_adminq(struct iavf_hw *hw)
 		goto init_adminq_exit;
 	}
 
-	/* Set up register offsets */
-	iavf_adminq_init_regs(hw);
-
 	/* setup ASQ command write back timeout */
 	hw->aq.asq_cmd_timeout = IAVF_ASQ_CMD_TIMEOUT;
 
@@ -587,9 +563,9 @@ static u16 iavf_clean_asq(struct iavf_hw *hw)
 
 	desc = IAVF_ADMINQ_DESC(*asq, ntc);
 	details = IAVF_ADMINQ_DETAILS(*asq, ntc);
-	while (rd32(hw, hw->aq.asq.head) != ntc) {
+	while (rd32(hw, IAVF_VF_ATQH1) != ntc) {
 		iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE,
-			   "ntc %d head %d.\n", ntc, rd32(hw, hw->aq.asq.head));
+			   "ntc %d head %d.\n", ntc, rd32(hw, IAVF_VF_ATQH1));
 
 		if (details->callback) {
 			IAVF_ADMINQ_CALLBACK cb_func =
@@ -624,7 +600,7 @@ bool iavf_asq_done(struct iavf_hw *hw)
 	/* AQ designers suggest use of head for better
 	 * timing reliability than DD bit
 	 */
-	return rd32(hw, hw->aq.asq.head) == hw->aq.asq.next_to_use;
+	return rd32(hw, IAVF_VF_ATQH1) == hw->aq.asq.next_to_use;
 }
 
 /**
@@ -663,7 +639,7 @@ enum iavf_status iavf_asq_send_command(struct iavf_hw *hw,
 
 	hw->aq.asq_last_status = IAVF_AQ_RC_OK;
 
-	val = rd32(hw, hw->aq.asq.head);
+	val = rd32(hw, IAVF_VF_ATQH1);
 	if (val >= hw->aq.num_asq_entries) {
 		iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE,
 			   "AQTX: head overrun at %d\n", val);
@@ -755,7 +731,7 @@ enum iavf_status iavf_asq_send_command(struct iavf_hw *hw,
 	if (hw->aq.asq.next_to_use == hw->aq.asq.count)
 		hw->aq.asq.next_to_use = 0;
 	if (!details->postpone)
-		wr32(hw, hw->aq.asq.tail, hw->aq.asq.next_to_use);
+		wr32(hw, IAVF_VF_ATQT1, hw->aq.asq.next_to_use);
 
 	/* if cmd_details are not defined or async flag is not set,
 	 * we need to wait for desc write back
@@ -810,7 +786,7 @@ enum iavf_status iavf_asq_send_command(struct iavf_hw *hw,
 	/* update the error if time out occurred */
 	if ((!cmd_completed) &&
 	    (!details->async && !details->postpone)) {
-		if (rd32(hw, hw->aq.asq.len) & IAVF_VF_ATQLEN1_ATQCRIT_MASK) {
+		if (rd32(hw, IAVF_VF_ATQLEN1) & IAVF_VF_ATQLEN1_ATQCRIT_MASK) {
 			iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE,
 				   "AQTX: AQ Critical error.\n");
 			status = IAVF_ERR_ADMIN_QUEUE_CRITICAL_ERROR;
@@ -878,7 +854,7 @@ enum iavf_status iavf_clean_arq_element(struct iavf_hw *hw,
 	}
 
 	/* set next_to_use to head */
-	ntu = rd32(hw, hw->aq.arq.head) & IAVF_VF_ARQH1_ARQH_MASK;
+	ntu = rd32(hw, IAVF_VF_ARQH1) & IAVF_VF_ARQH1_ARQH_MASK;
 	if (ntu == ntc) {
 		/* nothing to do - shouldn't need to update ring's values */
 		ret_code = IAVF_ERR_ADMIN_QUEUE_NO_WORK;
@@ -926,7 +902,7 @@ enum iavf_status iavf_clean_arq_element(struct iavf_hw *hw,
 	desc->params.external.addr_low = cpu_to_le32(lower_32_bits(bi->pa));
 
 	/* set tail = the last cleaned desc index. */
-	wr32(hw, hw->aq.arq.tail, ntc);
+	wr32(hw, IAVF_VF_ARQT1, ntc);
 	/* ntc is updated to tail + 1 */
 	ntc++;
 	if (ntc == hw->aq.num_arq_entries)
diff --git a/drivers/net/ethernet/intel/iavf/iavf_adminq.h b/drivers/net/ethernet/intel/iavf/iavf_adminq.h
index 1f60518eb0e5..406506f64bdd 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_adminq.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_adminq.h
@@ -29,13 +29,6 @@ struct iavf_adminq_ring {
 	/* used for interrupt processing */
 	u16 next_to_use;
 	u16 next_to_clean;
-
-	/* used for queue tracking */
-	u32 head;
-	u32 tail;
-	u32 len;
-	u32 bah;
-	u32 bal;
 };
 
 /* ASQ transaction details */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_adv_rss.c b/drivers/net/ethernet/intel/iavf/iavf_adv_rss.c
index 6edbf134b73f..a9e1da35e248 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_adv_rss.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_adv_rss.c
@@ -95,17 +95,21 @@ iavf_fill_adv_rss_sctp_hdr(struct virtchnl_proto_hdr *hdr, u64 hash_flds)
  * @rss_cfg: the virtchnl message to be filled with RSS configuration setting
  * @packet_hdrs: the RSS configuration protocol header types
  * @hash_flds: the RSS configuration protocol hash fields
+ * @symm: if true, symmetric hash is required
  *
  * Returns 0 if the RSS configuration virtchnl message is filled successfully
  */
 int
 iavf_fill_adv_rss_cfg_msg(struct virtchnl_rss_cfg *rss_cfg,
-			  u32 packet_hdrs, u64 hash_flds)
+			  u32 packet_hdrs, u64 hash_flds, bool symm)
 {
 	struct virtchnl_proto_hdrs *proto_hdrs = &rss_cfg->proto_hdrs;
 	struct virtchnl_proto_hdr *hdr;
 
-	rss_cfg->rss_algorithm = VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC;
+	if (symm)
+		rss_cfg->rss_algorithm = VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC;
+	else
+		rss_cfg->rss_algorithm = VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC;
 
 	proto_hdrs->tunnel_level = 0;	/* always outer layer */
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_adv_rss.h b/drivers/net/ethernet/intel/iavf/iavf_adv_rss.h
index 4d3be11af7aa..e31eb2afebea 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_adv_rss.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_adv_rss.h
@@ -80,13 +80,14 @@ struct iavf_adv_rss {
 
 	u32 packet_hdrs;
 	u64 hash_flds;
+	bool symm;
 
 	struct virtchnl_rss_cfg cfg_msg;
 };
 
 int
 iavf_fill_adv_rss_cfg_msg(struct virtchnl_rss_cfg *rss_cfg,
-			  u32 packet_hdrs, u64 hash_flds);
+			  u32 packet_hdrs, u64 hash_flds, bool symm);
 struct iavf_adv_rss *
 iavf_find_adv_rss_cfg_by_hdrs(struct iavf_adapter *adapter, u32 packet_hdrs);
 void
diff --git a/drivers/net/ethernet/intel/iavf/iavf_common.c b/drivers/net/ethernet/intel/iavf/iavf_common.c
index 8091e6feca01..5a25233a89d5 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_common.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_common.c
@@ -1,10 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
+#include <linux/avf/virtchnl.h>
+#include <linux/bitfield.h>
 #include "iavf_type.h"
 #include "iavf_adminq.h"
 #include "iavf_prototype.h"
-#include <linux/avf/virtchnl.h>
 
 /**
  * iavf_aq_str - convert AQ err code to a string
@@ -279,11 +280,11 @@ void iavf_debug_aq(struct iavf_hw *hw, enum iavf_debug_mask mask, void *desc,
  **/
 bool iavf_check_asq_alive(struct iavf_hw *hw)
 {
-	if (hw->aq.asq.len)
-		return !!(rd32(hw, hw->aq.asq.len) &
-			  IAVF_VF_ATQLEN1_ATQENABLE_MASK);
-	else
+	/* Check if the queue is initialized */
+	if (!hw->aq.asq.count)
 		return false;
+
+	return !!(rd32(hw, IAVF_VF_ATQLEN1) & IAVF_VF_ATQLEN1_ATQENABLE_MASK);
 }
 
 /**
@@ -330,6 +331,7 @@ static enum iavf_status iavf_aq_get_set_rss_lut(struct iavf_hw *hw,
 	struct iavf_aq_desc desc;
 	struct iavf_aqc_get_set_rss_lut *cmd_resp =
 		   (struct iavf_aqc_get_set_rss_lut *)&desc.params.raw;
+	u16 flags;
 
 	if (set)
 		iavf_fill_default_direct_cmd_desc(&desc,
@@ -342,22 +344,18 @@ static enum iavf_status iavf_aq_get_set_rss_lut(struct iavf_hw *hw,
 	desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_BUF);
 	desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_RD);
 
-	cmd_resp->vsi_id =
-			cpu_to_le16((u16)((vsi_id <<
-					  IAVF_AQC_SET_RSS_LUT_VSI_ID_SHIFT) &
-					  IAVF_AQC_SET_RSS_LUT_VSI_ID_MASK));
-	cmd_resp->vsi_id |= cpu_to_le16((u16)IAVF_AQC_SET_RSS_LUT_VSI_VALID);
+	vsi_id = FIELD_PREP(IAVF_AQC_SET_RSS_LUT_VSI_ID_MASK, vsi_id) |
+		 FIELD_PREP(IAVF_AQC_SET_RSS_LUT_VSI_VALID, 1);
+	cmd_resp->vsi_id = cpu_to_le16(vsi_id);
 
 	if (pf_lut)
-		cmd_resp->flags |= cpu_to_le16((u16)
-					((IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_PF <<
-					IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) &
-					IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_MASK));
+		flags = FIELD_PREP(IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_MASK,
+				   IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_PF);
 	else
-		cmd_resp->flags |= cpu_to_le16((u16)
-					((IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_VSI <<
-					IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) &
-					IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_MASK));
+		flags = FIELD_PREP(IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_MASK,
+				   IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_VSI);
+
+	cmd_resp->flags = cpu_to_le16(flags);
 
 	status = iavf_asq_send_command(hw, &desc, lut, lut_size, NULL);
 
@@ -411,11 +409,9 @@ iavf_status iavf_aq_get_set_rss_key(struct iavf_hw *hw, u16 vsi_id,
 	desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_BUF);
 	desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_RD);
 
-	cmd_resp->vsi_id =
-			cpu_to_le16((u16)((vsi_id <<
-					  IAVF_AQC_SET_RSS_KEY_VSI_ID_SHIFT) &
-					  IAVF_AQC_SET_RSS_KEY_VSI_ID_MASK));
-	cmd_resp->vsi_id |= cpu_to_le16((u16)IAVF_AQC_SET_RSS_KEY_VSI_VALID);
+	vsi_id = FIELD_PREP(IAVF_AQC_SET_RSS_KEY_VSI_ID_MASK, vsi_id) |
+		 FIELD_PREP(IAVF_AQC_SET_RSS_KEY_VSI_VALID, 1);
+	cmd_resp->vsi_id = cpu_to_le16(vsi_id);
 
 	status = iavf_asq_send_command(hw, &desc, key, key_size, NULL);
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index 6f236d1a6444..378c3e9ddf9d 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -1,11 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
+#include <linux/bitfield.h>
+#include <linux/uaccess.h>
+
 /* ethtool support for iavf */
 #include "iavf.h"
 
-#include <linux/uaccess.h>
-
 /* ethtool statistics helpers */
 
 /**
@@ -396,8 +397,7 @@ static void iavf_get_priv_flag_strings(struct net_device *netdev, u8 *data)
 	unsigned int i;
 
 	for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++)
-		ethtool_sprintf(&data, "%s",
-				iavf_gstrings_priv_flags[i].flag_string);
+		ethtool_puts(&data, iavf_gstrings_priv_flags[i].flag_string);
 }
 
 /**
@@ -827,18 +827,10 @@ static int __iavf_set_coalesce(struct net_device *netdev,
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 	int i;
 
-	if (ec->rx_coalesce_usecs == 0) {
-		if (ec->use_adaptive_rx_coalesce)
-			netif_info(adapter, drv, netdev, "rx-usecs=0, need to disable adaptive-rx for a complete disable\n");
-	} else if ((ec->rx_coalesce_usecs < IAVF_MIN_ITR) ||
-		   (ec->rx_coalesce_usecs > IAVF_MAX_ITR)) {
+	if (ec->rx_coalesce_usecs > IAVF_MAX_ITR) {
 		netif_info(adapter, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n");
 		return -EINVAL;
-	} else if (ec->tx_coalesce_usecs == 0) {
-		if (ec->use_adaptive_tx_coalesce)
-			netif_info(adapter, drv, netdev, "tx-usecs=0, need to disable adaptive-tx for a complete disable\n");
-	} else if ((ec->tx_coalesce_usecs < IAVF_MIN_ITR) ||
-		   (ec->tx_coalesce_usecs > IAVF_MAX_ITR)) {
+	} else if (ec->tx_coalesce_usecs > IAVF_MAX_ITR) {
 		netif_info(adapter, drv, netdev, "Invalid value, tx-usecs range is 0-8160\n");
 		return -EINVAL;
 	}
@@ -1025,8 +1017,7 @@ iavf_parse_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp,
 #define IAVF_USERDEF_FLEX_MAX_OFFS_VAL 504
 		flex = &fltr->flex_words[cnt++];
 		flex->word = value & IAVF_USERDEF_FLEX_WORD_M;
-		flex->offset = (value & IAVF_USERDEF_FLEX_OFFS_M) >>
-			     IAVF_USERDEF_FLEX_OFFS_S;
+		flex->offset = FIELD_GET(IAVF_USERDEF_FLEX_OFFS_M, value);
 		if (flex->offset > IAVF_USERDEF_FLEX_MAX_OFFS_VAL)
 			return -EINVAL;
 	}
@@ -1069,7 +1060,7 @@ iavf_get_ethtool_fdir_entry(struct iavf_adapter *adapter,
 	struct iavf_fdir_fltr *rule = NULL;
 	int ret = 0;
 
-	if (!FDIR_FLTR_SUPPORT(adapter))
+	if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
 		return -EOPNOTSUPP;
 
 	spin_lock_bh(&adapter->fdir_fltr_lock);
@@ -1211,7 +1202,7 @@ iavf_get_fdir_fltr_ids(struct iavf_adapter *adapter, struct ethtool_rxnfc *cmd,
 	unsigned int cnt = 0;
 	int val = 0;
 
-	if (!FDIR_FLTR_SUPPORT(adapter))
+	if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
 		return -EOPNOTSUPP;
 
 	cmd->data = IAVF_MAX_FDIR_FILTERS;
@@ -1403,7 +1394,7 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 	int count = 50;
 	int err;
 
-	if (!FDIR_FLTR_SUPPORT(adapter))
+	if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
 		return -EOPNOTSUPP;
 
 	if (fsp->flow_type & FLOW_MAC_EXT)
@@ -1444,12 +1435,15 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 	spin_lock_bh(&adapter->fdir_fltr_lock);
 	iavf_fdir_list_add_fltr(adapter, fltr);
 	adapter->fdir_active_fltr++;
-	fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST;
-	adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER;
-	spin_unlock_bh(&adapter->fdir_fltr_lock);
 
-	mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
+	if (adapter->link_up)
+		fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST;
+	else
+		fltr->state = IAVF_FDIR_FLTR_INACTIVE;
+	spin_unlock_bh(&adapter->fdir_fltr_lock);
 
+	if (adapter->link_up)
+		iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_FDIR_FILTER);
 ret:
 	if (err && fltr)
 		kfree(fltr);
@@ -1471,7 +1465,7 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 	struct iavf_fdir_fltr *fltr = NULL;
 	int err = 0;
 
-	if (!FDIR_FLTR_SUPPORT(adapter))
+	if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
 		return -EOPNOTSUPP;
 
 	spin_lock_bh(&adapter->fdir_fltr_lock);
@@ -1479,7 +1473,11 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 	if (fltr) {
 		if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) {
 			fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST;
-			adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER;
+		} else if (fltr->state == IAVF_FDIR_FLTR_INACTIVE) {
+			list_del(&fltr->list);
+			kfree(fltr);
+			adapter->fdir_active_fltr--;
+			fltr = NULL;
 		} else {
 			err = -EBUSY;
 		}
@@ -1489,7 +1487,7 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 	spin_unlock_bh(&adapter->fdir_fltr_lock);
 
 	if (fltr && fltr->state == IAVF_FDIR_FLTR_DEL_REQUEST)
-		mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
+		iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_FDIR_FILTER);
 
 	return err;
 }
@@ -1540,11 +1538,12 @@ static u32 iavf_adv_rss_parse_hdrs(struct ethtool_rxnfc *cmd)
 /**
  * iavf_adv_rss_parse_hash_flds - parses hash fields from RSS hash input
  * @cmd: ethtool rxnfc command
+ * @symm: true if Symmetric Topelitz is set
  *
  * This function parses the rxnfc command and returns intended hash fields for
  * RSS configuration
  */
-static u64 iavf_adv_rss_parse_hash_flds(struct ethtool_rxnfc *cmd)
+static u64 iavf_adv_rss_parse_hash_flds(struct ethtool_rxnfc *cmd, bool symm)
 {
 	u64 hfld = IAVF_ADV_RSS_HASH_INVALID;
 
@@ -1616,17 +1615,20 @@ iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter,
 	struct iavf_adv_rss *rss_old, *rss_new;
 	bool rss_new_add = false;
 	int count = 50, err = 0;
+	bool symm = false;
 	u64 hash_flds;
 	u32 hdrs;
 
 	if (!ADV_RSS_SUPPORT(adapter))
 		return -EOPNOTSUPP;
 
+	symm = !!(adapter->hfunc == VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC);
+
 	hdrs = iavf_adv_rss_parse_hdrs(cmd);
 	if (hdrs == IAVF_ADV_RSS_FLOW_SEG_HDR_NONE)
 		return -EINVAL;
 
-	hash_flds = iavf_adv_rss_parse_hash_flds(cmd);
+	hash_flds = iavf_adv_rss_parse_hash_flds(cmd, symm);
 	if (hash_flds == IAVF_ADV_RSS_HASH_INVALID)
 		return -EINVAL;
 
@@ -1634,7 +1636,8 @@ iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter,
 	if (!rss_new)
 		return -ENOMEM;
 
-	if (iavf_fill_adv_rss_cfg_msg(&rss_new->cfg_msg, hdrs, hash_flds)) {
+	if (iavf_fill_adv_rss_cfg_msg(&rss_new->cfg_msg, hdrs, hash_flds,
+				      symm)) {
 		kfree(rss_new);
 		return -EINVAL;
 	}
@@ -1653,12 +1656,13 @@ iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter,
 	if (rss_old) {
 		if (rss_old->state != IAVF_ADV_RSS_ACTIVE) {
 			err = -EBUSY;
-		} else if (rss_old->hash_flds != hash_flds) {
+		} else if (rss_old->hash_flds != hash_flds ||
+			   rss_old->symm != symm) {
 			rss_old->state = IAVF_ADV_RSS_ADD_REQUEST;
 			rss_old->hash_flds = hash_flds;
+			rss_old->symm = symm;
 			memcpy(&rss_old->cfg_msg, &rss_new->cfg_msg,
 			       sizeof(rss_new->cfg_msg));
-			adapter->aq_required |= IAVF_FLAG_AQ_ADD_ADV_RSS_CFG;
 		} else {
 			err = -EEXIST;
 		}
@@ -1667,13 +1671,13 @@ iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter,
 		rss_new->state = IAVF_ADV_RSS_ADD_REQUEST;
 		rss_new->packet_hdrs = hdrs;
 		rss_new->hash_flds = hash_flds;
+		rss_new->symm = symm;
 		list_add_tail(&rss_new->list, &adapter->adv_rss_list_head);
-		adapter->aq_required |= IAVF_FLAG_AQ_ADD_ADV_RSS_CFG;
 	}
 	spin_unlock_bh(&adapter->adv_rss_lock);
 
 	if (!err)
-		mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
+		iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_ADV_RSS_CFG);
 
 	mutex_unlock(&adapter->crit_lock);
 
@@ -1788,7 +1792,7 @@ static int iavf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
 		ret = 0;
 		break;
 	case ETHTOOL_GRXCLSRLCNT:
-		if (!FDIR_FLTR_SUPPORT(adapter))
+		if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
 			break;
 		spin_lock_bh(&adapter->fdir_fltr_lock);
 		cmd->rule_cnt = adapter->fdir_active_fltr;
@@ -1907,27 +1911,27 @@ static u32 iavf_get_rxfh_indir_size(struct net_device *netdev)
 /**
  * iavf_get_rxfh - get the rx flow hash indirection table
  * @netdev: network interface device structure
- * @indir: indirection table
- * @key: hash key
- * @hfunc: hash function in use
+ * @rxfh: pointer to param struct (indir, key, hfunc)
  *
  * Reads the indirection table directly from the hardware. Always returns 0.
  **/
-static int iavf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			 u8 *hfunc)
+static int iavf_get_rxfh(struct net_device *netdev,
+			 struct ethtool_rxfh_param *rxfh)
 {
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 	u16 i;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (key)
-		memcpy(key, adapter->rss_key, adapter->rss_key_size);
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (adapter->hfunc == VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC)
+		rxfh->input_xfrm |= RXH_XFRM_SYM_XOR;
+
+	if (rxfh->key)
+		memcpy(rxfh->key, adapter->rss_key, adapter->rss_key_size);
 
-	if (indir)
+	if (rxfh->indir)
 		/* Each 32 bits pointed by 'indir' is stored with a lut entry */
 		for (i = 0; i < adapter->rss_lut_size; i++)
-			indir[i] = (u32)adapter->rss_lut[i];
+			rxfh->indir[i] = (u32)adapter->rss_lut[i];
 
 	return 0;
 }
@@ -1935,33 +1939,46 @@ static int iavf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 /**
  * iavf_set_rxfh - set the rx flow hash indirection table
  * @netdev: network interface device structure
- * @indir: indirection table
- * @key: hash key
- * @hfunc: hash function to use
+ * @rxfh: pointer to param struct (indir, key, hfunc)
+ * @extack: extended ACK from the Netlink message
  *
  * Returns -EINVAL if the table specifies an invalid queue id, otherwise
  * returns 0 after programming the table.
  **/
-static int iavf_set_rxfh(struct net_device *netdev, const u32 *indir,
-			 const u8 *key, const u8 hfunc)
+static int iavf_set_rxfh(struct net_device *netdev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 	u16 i;
 
 	/* Only support toeplitz hash function */
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (!key && !indir)
+	if ((rxfh->input_xfrm & RXH_XFRM_SYM_XOR) &&
+	    adapter->hfunc != VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC) {
+		if (!ADV_RSS_SUPPORT(adapter))
+			return -EOPNOTSUPP;
+		adapter->hfunc = VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC;
+		adapter->aq_required |= IAVF_FLAG_AQ_SET_RSS_HFUNC;
+	} else if (!(rxfh->input_xfrm & RXH_XFRM_SYM_XOR) &&
+		    adapter->hfunc != VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC) {
+		adapter->hfunc = VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC;
+		adapter->aq_required |= IAVF_FLAG_AQ_SET_RSS_HFUNC;
+	}
+
+	if (!rxfh->key && !rxfh->indir)
 		return 0;
 
-	if (key)
-		memcpy(adapter->rss_key, key, adapter->rss_key_size);
+	if (rxfh->key)
+		memcpy(adapter->rss_key, rxfh->key, adapter->rss_key_size);
 
-	if (indir) {
+	if (rxfh->indir) {
 		/* Each 32 bits pointed by 'indir' is stored with a lut entry */
 		for (i = 0; i < adapter->rss_lut_size; i++)
-			adapter->rss_lut[i] = (u8)(indir[i]);
+			adapter->rss_lut[i] = (u8)(rxfh->indir[i]);
 	}
 
 	return iavf_config_rss(adapter);
@@ -1970,6 +1987,7 @@ static int iavf_set_rxfh(struct net_device *netdev, const u32 *indir,
 static const struct ethtool_ops iavf_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE,
+	.cap_rss_sym_xor_supported = true,
 	.get_drvinfo		= iavf_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
 	.get_ringparam		= iavf_get_ringparam,
diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.c b/drivers/net/ethernet/intel/iavf/iavf_fdir.c
index 03e774bd2a5b..2d47b0b4640e 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_fdir.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.c
@@ -3,6 +3,7 @@
 
 /* flow director ethtool support for iavf */
 
+#include <linux/bitfield.h>
 #include "iavf.h"
 
 #define GTPU_PORT	2152
@@ -357,7 +358,7 @@ iavf_fill_fdir_ip6_hdr(struct iavf_fdir_fltr *fltr,
 
 	if (fltr->ip_mask.tclass == U8_MAX) {
 		iph->priority = (fltr->ip_data.tclass >> 4) & 0xF;
-		iph->flow_lbl[0] = (fltr->ip_data.tclass << 4) & 0xF0;
+		iph->flow_lbl[0] = FIELD_PREP(0xF0, fltr->ip_data.tclass);
 		VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, IPV6, TC);
 	}
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.h b/drivers/net/ethernet/intel/iavf/iavf_fdir.h
index 9eb9f73f6adf..d31bd923ba8c 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_fdir.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.h
@@ -6,12 +6,25 @@
 
 struct iavf_adapter;
 
-/* State of Flow Director filter */
+/* State of Flow Director filter
+ *
+ * *_REQUEST states are used to mark filter to be sent to PF driver to perform
+ * an action (either add or delete filter). *_PENDING states are an indication
+ * that request was sent to PF and the driver is waiting for response.
+ *
+ * Both DELETE and DISABLE states are being used to delete a filter in PF.
+ * The difference is that after a successful response filter in DEL_PENDING
+ * state is being deleted from VF driver as well and filter in DIS_PENDING state
+ * is being changed to INACTIVE state.
+ */
 enum iavf_fdir_fltr_state_t {
 	IAVF_FDIR_FLTR_ADD_REQUEST,	/* User requests to add filter */
 	IAVF_FDIR_FLTR_ADD_PENDING,	/* Filter pending add by the PF */
 	IAVF_FDIR_FLTR_DEL_REQUEST,	/* User requests to delete filter */
 	IAVF_FDIR_FLTR_DEL_PENDING,	/* Filter pending delete by the PF */
+	IAVF_FDIR_FLTR_DIS_REQUEST,	/* Filter scheduled to be disabled */
+	IAVF_FDIR_FLTR_DIS_PENDING,	/* Filter pending disable by the PF */
+	IAVF_FDIR_FLTR_INACTIVE,	/* Filter inactive on link down */
 	IAVF_FDIR_FLTR_ACTIVE,		/* Filter is active */
 };
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index c862ebcd2e39..335fd13e86f7 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -277,27 +277,6 @@ void iavf_free_virt_mem(struct iavf_hw *hw, struct iavf_virt_mem *mem)
 }
 
 /**
- * iavf_lock_timeout - try to lock mutex but give up after timeout
- * @lock: mutex that should be locked
- * @msecs: timeout in msecs
- *
- * Returns 0 on success, negative on failure
- **/
-static int iavf_lock_timeout(struct mutex *lock, unsigned int msecs)
-{
-	unsigned int wait, delay = 10;
-
-	for (wait = 0; wait < msecs; wait += delay) {
-		if (mutex_trylock(lock))
-			return 0;
-
-		msleep(delay);
-	}
-
-	return -1;
-}
-
-/**
  * iavf_schedule_reset - Set the flags and schedule a reset event
  * @adapter: board private structure
  * @flags: IAVF_FLAG_RESET_PENDING or IAVF_FLAG_RESET_NEEDED
@@ -1059,13 +1038,12 @@ static int iavf_replace_primary_mac(struct iavf_adapter *adapter,
 	 */
 	new_f->is_primary = true;
 	new_f->add = true;
-	adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER;
 	ether_addr_copy(hw->mac.addr, new_mac);
 
 	spin_unlock_bh(&adapter->mac_vlan_list_lock);
 
 	/* schedule the watchdog task to immediately process the request */
-	mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
+	iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_MAC_FILTER);
 	return 0;
 }
 
@@ -1284,8 +1262,7 @@ static void iavf_up_complete(struct iavf_adapter *adapter)
 
 	iavf_napi_enable_all(adapter);
 
-	adapter->aq_required |= IAVF_FLAG_AQ_ENABLE_QUEUES;
-	mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
+	iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ENABLE_QUEUES);
 }
 
 /**
@@ -1353,18 +1330,20 @@ static void iavf_clear_cloud_filters(struct iavf_adapter *adapter)
  **/
 static void iavf_clear_fdir_filters(struct iavf_adapter *adapter)
 {
-	struct iavf_fdir_fltr *fdir, *fdirtmp;
+	struct iavf_fdir_fltr *fdir;
 
 	/* remove all Flow Director filters */
 	spin_lock_bh(&adapter->fdir_fltr_lock);
-	list_for_each_entry_safe(fdir, fdirtmp, &adapter->fdir_list_head,
-				 list) {
+	list_for_each_entry(fdir, &adapter->fdir_list_head, list) {
 		if (fdir->state == IAVF_FDIR_FLTR_ADD_REQUEST) {
-			list_del(&fdir->list);
-			kfree(fdir);
-			adapter->fdir_active_fltr--;
-		} else {
-			fdir->state = IAVF_FDIR_FLTR_DEL_REQUEST;
+			/* Cancel a request, keep filter as inactive */
+			fdir->state = IAVF_FDIR_FLTR_INACTIVE;
+		} else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING ||
+			 fdir->state == IAVF_FDIR_FLTR_ACTIVE) {
+			/* Disable filters which are active or have a pending
+			 * request to PF to be added
+			 */
+			fdir->state = IAVF_FDIR_FLTR_DIS_REQUEST;
 		}
 	}
 	spin_unlock_bh(&adapter->fdir_fltr_lock);
@@ -1439,8 +1418,7 @@ void iavf_down(struct iavf_adapter *adapter)
 			adapter->aq_required |= IAVF_FLAG_AQ_DEL_ADV_RSS_CFG;
 	}
 
-	adapter->aq_required |= IAVF_FLAG_AQ_DISABLE_QUEUES;
-	mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
+	iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DISABLE_QUEUES);
 }
 
 /**
@@ -2169,6 +2147,10 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter)
 		iavf_set_rss_lut(adapter);
 		return 0;
 	}
+	if (adapter->aq_required & IAVF_FLAG_AQ_SET_RSS_HFUNC) {
+		iavf_set_rss_hfunc(adapter);
+		return 0;
+	}
 
 	if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_PROMISC_MODE) {
 		iavf_set_promiscuous(adapter);
@@ -2337,10 +2319,8 @@ iavf_set_vlan_offload_features(struct iavf_adapter *adapter,
 		}
 	}
 
-	if (aq_required) {
-		adapter->aq_required |= aq_required;
-		mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
-	}
+	if (aq_required)
+		iavf_schedule_aq_request(adapter, aq_required);
 }
 
 /**
@@ -3253,7 +3233,7 @@ static void iavf_adminq_task(struct work_struct *work)
 		goto freedom;
 
 	/* check for error indications */
-	val = rd32(hw, hw->aq.arq.len);
+	val = rd32(hw, IAVF_VF_ARQLEN1);
 	if (val == 0xdeadbeef || val == 0xffffffff) /* device in reset */
 		goto freedom;
 	oldval = val;
@@ -3270,9 +3250,9 @@ static void iavf_adminq_task(struct work_struct *work)
 		val &= ~IAVF_VF_ARQLEN1_ARQCRIT_MASK;
 	}
 	if (oldval != val)
-		wr32(hw, hw->aq.arq.len, val);
+		wr32(hw, IAVF_VF_ARQLEN1, val);
 
-	val = rd32(hw, hw->aq.asq.len);
+	val = rd32(hw, IAVF_VF_ATQLEN1);
 	oldval = val;
 	if (val & IAVF_VF_ATQLEN1_ATQVFE_MASK) {
 		dev_info(&adapter->pdev->dev, "ASQ VF Error detected\n");
@@ -3287,7 +3267,7 @@ static void iavf_adminq_task(struct work_struct *work)
 		val &= ~IAVF_VF_ATQLEN1_ATQCRIT_MASK;
 	}
 	if (oldval != val)
-		wr32(hw, hw->aq.asq.len, val);
+		wr32(hw, IAVF_VF_ATQLEN1, val);
 
 freedom:
 	kfree(event.msg_buf);
@@ -4113,6 +4093,33 @@ static int iavf_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 }
 
 /**
+ * iavf_restore_fdir_filters
+ * @adapter: board private structure
+ *
+ * Restore existing FDIR filters when VF netdev comes back up.
+ **/
+static void iavf_restore_fdir_filters(struct iavf_adapter *adapter)
+{
+	struct iavf_fdir_fltr *f;
+
+	spin_lock_bh(&adapter->fdir_fltr_lock);
+	list_for_each_entry(f, &adapter->fdir_list_head, list) {
+		if (f->state == IAVF_FDIR_FLTR_DIS_REQUEST) {
+			/* Cancel a request, keep filter as active */
+			f->state = IAVF_FDIR_FLTR_ACTIVE;
+		} else if (f->state == IAVF_FDIR_FLTR_DIS_PENDING ||
+			   f->state == IAVF_FDIR_FLTR_INACTIVE) {
+			/* Add filters which are inactive or have a pending
+			 * request to PF to be deleted
+			 */
+			f->state = IAVF_FDIR_FLTR_ADD_REQUEST;
+			adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER;
+		}
+	}
+	spin_unlock_bh(&adapter->fdir_fltr_lock);
+}
+
+/**
  * iavf_open - Called when a network interface is made active
  * @netdev: network interface device structure
  *
@@ -4179,8 +4186,9 @@ static int iavf_open(struct net_device *netdev)
 
 	spin_unlock_bh(&adapter->mac_vlan_list_lock);
 
-	/* Restore VLAN filters that were removed with IFF_DOWN */
+	/* Restore filters that were removed with IFF_DOWN */
 	iavf_restore_filters(adapter);
+	iavf_restore_fdir_filters(adapter);
 
 	iavf_configure(adapter);
 
@@ -4311,6 +4319,49 @@ static int iavf_change_mtu(struct net_device *netdev, int new_mtu)
 	return ret;
 }
 
+/**
+ * iavf_disable_fdir - disable Flow Director and clear existing filters
+ * @adapter: board private structure
+ **/
+static void iavf_disable_fdir(struct iavf_adapter *adapter)
+{
+	struct iavf_fdir_fltr *fdir, *fdirtmp;
+	bool del_filters = false;
+
+	adapter->flags &= ~IAVF_FLAG_FDIR_ENABLED;
+
+	/* remove all Flow Director filters */
+	spin_lock_bh(&adapter->fdir_fltr_lock);
+	list_for_each_entry_safe(fdir, fdirtmp, &adapter->fdir_list_head,
+				 list) {
+		if (fdir->state == IAVF_FDIR_FLTR_ADD_REQUEST ||
+		    fdir->state == IAVF_FDIR_FLTR_INACTIVE) {
+			/* Delete filters not registered in PF */
+			list_del(&fdir->list);
+			kfree(fdir);
+			adapter->fdir_active_fltr--;
+		} else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING ||
+			   fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST ||
+			   fdir->state == IAVF_FDIR_FLTR_ACTIVE) {
+			/* Filters registered in PF, schedule their deletion */
+			fdir->state = IAVF_FDIR_FLTR_DEL_REQUEST;
+			del_filters = true;
+		} else if (fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) {
+			/* Request to delete filter already sent to PF, change
+			 * state to DEL_PENDING to delete filter after PF's
+			 * response, not set as INACTIVE
+			 */
+			fdir->state = IAVF_FDIR_FLTR_DEL_PENDING;
+		}
+	}
+	spin_unlock_bh(&adapter->fdir_fltr_lock);
+
+	if (del_filters) {
+		adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER;
+		mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
+	}
+}
+
 #define NETIF_VLAN_OFFLOAD_FEATURES	(NETIF_F_HW_VLAN_CTAG_RX | \
 					 NETIF_F_HW_VLAN_CTAG_TX | \
 					 NETIF_F_HW_VLAN_STAG_RX | \
@@ -4336,6 +4387,13 @@ static int iavf_set_features(struct net_device *netdev,
 	    ((netdev->features & NETIF_F_RXFCS) ^ (features & NETIF_F_RXFCS)))
 		iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED);
 
+	if ((netdev->features & NETIF_F_NTUPLE) ^ (features & NETIF_F_NTUPLE)) {
+		if (features & NETIF_F_NTUPLE)
+			adapter->flags |= IAVF_FLAG_FDIR_ENABLED;
+		else
+			iavf_disable_fdir(adapter);
+	}
+
 	return 0;
 }
 
@@ -4685,6 +4743,9 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev,
 
 	features = iavf_fix_netdev_vlan_features(adapter, features);
 
+	if (!FDIR_FLTR_SUPPORT(adapter))
+		features &= ~NETIF_F_NTUPLE;
+
 	return iavf_fix_strip_features(adapter, features);
 }
 
@@ -4802,6 +4863,12 @@ int iavf_process_config(struct iavf_adapter *adapter)
 	if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
 		netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 
+	if (FDIR_FLTR_SUPPORT(adapter)) {
+		netdev->hw_features |= NETIF_F_NTUPLE;
+		netdev->features |= NETIF_F_NTUPLE;
+		adapter->flags |= IAVF_FLAG_FDIR_ENABLED;
+	}
+
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 
 	/* Do not turn on offloads when they are requested to be turned off.
@@ -4826,34 +4893,6 @@ int iavf_process_config(struct iavf_adapter *adapter)
 }
 
 /**
- * iavf_shutdown - Shutdown the device in preparation for a reboot
- * @pdev: pci device structure
- **/
-static void iavf_shutdown(struct pci_dev *pdev)
-{
-	struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev);
-	struct net_device *netdev = adapter->netdev;
-
-	netif_device_detach(netdev);
-
-	if (netif_running(netdev))
-		iavf_close(netdev);
-
-	if (iavf_lock_timeout(&adapter->crit_lock, 5000))
-		dev_warn(&adapter->pdev->dev, "%s: failed to acquire crit_lock\n", __func__);
-	/* Prevent the watchdog from running. */
-	iavf_change_state(adapter, __IAVF_REMOVE);
-	adapter->aq_required = 0;
-	mutex_unlock(&adapter->crit_lock);
-
-#ifdef CONFIG_PM
-	pci_save_state(pdev);
-
-#endif
-	pci_disable_device(pdev);
-}
-
-/**
  * iavf_probe - Device Initialization Routine
  * @pdev: PCI device information struct
  * @ent: entry in iavf_pci_tbl
@@ -5063,16 +5102,21 @@ static int __maybe_unused iavf_resume(struct device *dev_d)
  **/
 static void iavf_remove(struct pci_dev *pdev)
 {
-	struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev);
 	struct iavf_fdir_fltr *fdir, *fdirtmp;
 	struct iavf_vlan_filter *vlf, *vlftmp;
 	struct iavf_cloud_filter *cf, *cftmp;
 	struct iavf_adv_rss *rss, *rsstmp;
 	struct iavf_mac_filter *f, *ftmp;
+	struct iavf_adapter *adapter;
 	struct net_device *netdev;
 	struct iavf_hw *hw;
 
-	netdev = adapter->netdev;
+	/* Don't proceed with remove if netdev is already freed */
+	netdev = pci_get_drvdata(pdev);
+	if (!netdev)
+		return;
+
+	adapter = iavf_pdev_to_adapter(pdev);
 	hw = &adapter->hw;
 
 	if (test_and_set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section))
@@ -5184,11 +5228,25 @@ static void iavf_remove(struct pci_dev *pdev)
 
 	destroy_workqueue(adapter->wq);
 
+	pci_set_drvdata(pdev, NULL);
+
 	free_netdev(netdev);
 
 	pci_disable_device(pdev);
 }
 
+/**
+ * iavf_shutdown - Shutdown the device in preparation for a reboot
+ * @pdev: pci device structure
+ **/
+static void iavf_shutdown(struct pci_dev *pdev)
+{
+	iavf_remove(pdev);
+
+	if (system_state == SYSTEM_POWER_OFF)
+		pci_set_power_state(pdev, PCI_D3hot);
+}
+
 static SIMPLE_DEV_PM_OPS(iavf_pm_ops, iavf_suspend, iavf_resume);
 
 static struct pci_driver iavf_driver = {
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index d64c4997136b..b71484c87a84 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
+#include <linux/bitfield.h>
 #include <linux/prefetch.h>
 
 #include "iavf.h"
@@ -988,11 +989,9 @@ static void iavf_rx_checksum(struct iavf_vsi *vsi,
 	u64 qword;
 
 	qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-	ptype = (qword & IAVF_RXD_QW1_PTYPE_MASK) >> IAVF_RXD_QW1_PTYPE_SHIFT;
-	rx_error = (qword & IAVF_RXD_QW1_ERROR_MASK) >>
-		   IAVF_RXD_QW1_ERROR_SHIFT;
-	rx_status = (qword & IAVF_RXD_QW1_STATUS_MASK) >>
-		    IAVF_RXD_QW1_STATUS_SHIFT;
+	ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword);
+	rx_error = FIELD_GET(IAVF_RXD_QW1_ERROR_MASK, qword);
+	rx_status = FIELD_GET(IAVF_RXD_QW1_STATUS_MASK, qword);
 	decoded = decode_rx_desc_ptype(ptype);
 
 	skb->ip_summed = CHECKSUM_NONE;
@@ -1533,8 +1532,7 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 		if (!iavf_test_staterr(rx_desc, IAVF_RXD_DD))
 			break;
 
-		size = (qword & IAVF_RXD_QW1_LENGTH_PBUF_MASK) >>
-		       IAVF_RXD_QW1_LENGTH_PBUF_SHIFT;
+		size = FIELD_GET(IAVF_RXD_QW1_LENGTH_PBUF_MASK, qword);
 
 		iavf_trace(clean_rx_irq, rx_ring, rx_desc, skb);
 		rx_buffer = iavf_get_rx_buffer(rx_ring, size);
@@ -1581,8 +1579,7 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 		total_rx_bytes += skb->len;
 
 		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-		rx_ptype = (qword & IAVF_RXD_QW1_PTYPE_MASK) >>
-			   IAVF_RXD_QW1_PTYPE_SHIFT;
+		rx_ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword);
 
 		/* populate checksum, VLAN, and protocol */
 		iavf_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
@@ -2290,8 +2287,7 @@ static void iavf_tx_map(struct iavf_ring *tx_ring, struct sk_buff *skb,
 
 	if (tx_flags & IAVF_TX_FLAGS_HW_VLAN) {
 		td_cmd |= IAVF_TX_DESC_CMD_IL2TAG1;
-		td_tag = (tx_flags & IAVF_TX_FLAGS_VLAN_MASK) >>
-			 IAVF_TX_FLAGS_VLAN_SHIFT;
+		td_tag = FIELD_GET(IAVF_TX_FLAGS_VLAN_MASK, tx_flags);
 	}
 
 	first->tx_flags = tx_flags;
@@ -2467,8 +2463,7 @@ static netdev_tx_t iavf_xmit_frame_ring(struct sk_buff *skb,
 	if (tx_flags & IAVF_TX_FLAGS_HW_OUTER_SINGLE_VLAN) {
 		cd_type_cmd_tso_mss |= IAVF_TX_CTX_DESC_IL2TAG2 <<
 			IAVF_TXD_CTX_QW1_CMD_SHIFT;
-		cd_l2tag2 = (tx_flags & IAVF_TX_FLAGS_VLAN_MASK) >>
-			IAVF_TX_FLAGS_VLAN_SHIFT;
+		cd_l2tag2 = FIELD_GET(IAVF_TX_FLAGS_VLAN_MASK, tx_flags);
 	}
 
 	/* obtain protocol of skb */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
index 7e6ee32d19b6..10ba36602c0c 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
@@ -15,7 +15,6 @@
  */
 #define IAVF_ITR_DYNAMIC	0x8000	/* use top bit as a flag */
 #define IAVF_ITR_MASK		0x1FFE	/* mask for ITR register value */
-#define IAVF_MIN_ITR		     2	/* reg uses 2 usec resolution */
 #define IAVF_ITR_100K		    10	/* all values below must be even */
 #define IAVF_ITR_50K		    20
 #define IAVF_ITR_20K		    50
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 64c4443dbef9..22f2df7c460b 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -1142,6 +1142,34 @@ void iavf_set_rss_lut(struct iavf_adapter *adapter)
 }
 
 /**
+ * iavf_set_rss_hfunc
+ * @adapter: adapter structure
+ *
+ * Request the PF to set our RSS Hash function
+ **/
+void iavf_set_rss_hfunc(struct iavf_adapter *adapter)
+{
+	struct virtchnl_rss_hfunc *vrh;
+	int len = sizeof(*vrh);
+
+	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
+		/* bail because we already have a command pending */
+		dev_err(&adapter->pdev->dev, "Cannot set RSS Hash function, command %d pending\n",
+			adapter->current_op);
+		return;
+	}
+	vrh = kzalloc(len, GFP_KERNEL);
+	if (!vrh)
+		return;
+	vrh->vsi_id = adapter->vsi.id;
+	vrh->rss_algorithm = adapter->hfunc;
+	adapter->current_op = VIRTCHNL_OP_CONFIG_RSS_HFUNC;
+	adapter->aq_required &= ~IAVF_FLAG_AQ_SET_RSS_HFUNC;
+	iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_RSS_HFUNC, (u8 *)vrh, len);
+	kfree(vrh);
+}
+
+/**
  * iavf_enable_vlan_stripping
  * @adapter: adapter structure
  *
@@ -1735,8 +1763,8 @@ void iavf_add_fdir_filter(struct iavf_adapter *adapter)
  **/
 void iavf_del_fdir_filter(struct iavf_adapter *adapter)
 {
+	struct virtchnl_fdir_del f = {};
 	struct iavf_fdir_fltr *fdir;
-	struct virtchnl_fdir_del f;
 	bool process_fltr = false;
 	int len;
 
@@ -1753,11 +1781,16 @@ void iavf_del_fdir_filter(struct iavf_adapter *adapter)
 	list_for_each_entry(fdir, &adapter->fdir_list_head, list) {
 		if (fdir->state == IAVF_FDIR_FLTR_DEL_REQUEST) {
 			process_fltr = true;
-			memset(&f, 0, len);
 			f.vsi_id = fdir->vc_add_msg.vsi_id;
 			f.flow_id = fdir->flow_id;
 			fdir->state = IAVF_FDIR_FLTR_DEL_PENDING;
 			break;
+		} else if (fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST) {
+			process_fltr = true;
+			f.vsi_id = fdir->vc_add_msg.vsi_id;
+			f.flow_id = fdir->flow_id;
+			fdir->state = IAVF_FDIR_FLTR_DIS_PENDING;
+			break;
 		}
 	}
 	spin_unlock_bh(&adapter->fdir_fltr_lock);
@@ -1902,6 +1935,48 @@ static void iavf_netdev_features_vlan_strip_set(struct net_device *netdev,
 }
 
 /**
+ * iavf_activate_fdir_filters - Reactivate all FDIR filters after a reset
+ * @adapter: private adapter structure
+ *
+ * Called after a reset to re-add all FDIR filters and delete some of them
+ * if they were pending to be deleted.
+ */
+static void iavf_activate_fdir_filters(struct iavf_adapter *adapter)
+{
+	struct iavf_fdir_fltr *f, *ftmp;
+	bool add_filters = false;
+
+	spin_lock_bh(&adapter->fdir_fltr_lock);
+	list_for_each_entry_safe(f, ftmp, &adapter->fdir_list_head, list) {
+		if (f->state == IAVF_FDIR_FLTR_ADD_REQUEST ||
+		    f->state == IAVF_FDIR_FLTR_ADD_PENDING ||
+		    f->state == IAVF_FDIR_FLTR_ACTIVE) {
+			/* All filters and requests have been removed in PF,
+			 * restore them
+			 */
+			f->state = IAVF_FDIR_FLTR_ADD_REQUEST;
+			add_filters = true;
+		} else if (f->state == IAVF_FDIR_FLTR_DIS_REQUEST ||
+			   f->state == IAVF_FDIR_FLTR_DIS_PENDING) {
+			/* Link down state, leave filters as inactive */
+			f->state = IAVF_FDIR_FLTR_INACTIVE;
+		} else if (f->state == IAVF_FDIR_FLTR_DEL_REQUEST ||
+			   f->state == IAVF_FDIR_FLTR_DEL_PENDING) {
+			/* Delete filters that were pending to be deleted, the
+			 * list on PF is already cleared after a reset
+			 */
+			list_del(&f->list);
+			kfree(f);
+			adapter->fdir_active_fltr--;
+		}
+	}
+	spin_unlock_bh(&adapter->fdir_fltr_lock);
+
+	if (add_filters)
+		adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER;
+}
+
+/**
  * iavf_virtchnl_completion
  * @adapter: adapter structure
  * @v_opcode: opcode sent by PF
@@ -2078,7 +2153,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 			spin_lock_bh(&adapter->fdir_fltr_lock);
 			list_for_each_entry(fdir, &adapter->fdir_list_head,
 					    list) {
-				if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING) {
+				if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING ||
+				    fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) {
 					fdir->state = IAVF_FDIR_FLTR_ACTIVE;
 					dev_info(&adapter->pdev->dev, "Failed to del Flow Director filter, error %s\n",
 						 iavf_stat_str(&adapter->hw,
@@ -2142,6 +2218,19 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 			dev_warn(&adapter->pdev->dev, "Failed to add VLAN filter, error %s\n",
 				 iavf_stat_str(&adapter->hw, v_retval));
 			break;
+		case VIRTCHNL_OP_CONFIG_RSS_HFUNC:
+			dev_warn(&adapter->pdev->dev, "Failed to configure hash function, error %s\n",
+				 iavf_stat_str(&adapter->hw, v_retval));
+
+			if (adapter->hfunc ==
+					VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC)
+				adapter->hfunc =
+					VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC;
+			else
+				adapter->hfunc =
+					VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC;
+
+			break;
 		default:
 			dev_err(&adapter->pdev->dev, "PF returned error %d (%s) to our request %d\n",
 				v_retval, iavf_stat_str(&adapter->hw, v_retval),
@@ -2214,6 +2303,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 
 		spin_unlock_bh(&adapter->mac_vlan_list_lock);
 
+		iavf_activate_fdir_filters(adapter);
+
 		iavf_parse_vf_resource_msg(adapter);
 
 		/* negotiated VIRTCHNL_VF_OFFLOAD_VLAN_V2, so wait for the
@@ -2390,7 +2481,9 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 		list_for_each_entry_safe(fdir, fdir_tmp, &adapter->fdir_list_head,
 					 list) {
 			if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING) {
-				if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS) {
+				if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS ||
+				    del_fltr->status ==
+				    VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST) {
 					dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is deleted\n",
 						 fdir->loc);
 					list_del(&fdir->list);
@@ -2402,6 +2495,17 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 						 del_fltr->status);
 					iavf_print_fdir_fltr(adapter, fdir);
 				}
+			} else if (fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) {
+				if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS ||
+				    del_fltr->status ==
+				    VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST) {
+					fdir->state = IAVF_FDIR_FLTR_INACTIVE;
+				} else {
+					fdir->state = IAVF_FDIR_FLTR_ACTIVE;
+					dev_info(&adapter->pdev->dev, "Failed to disable Flow Director filter with status: %d\n",
+						 del_fltr->status);
+					iavf_print_fdir_fltr(adapter, fdir);
+				}
 			}
 		}
 		spin_unlock_bh(&adapter->fdir_fltr_lock);
diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile
index 0679907980f7..cddd82d4ca0f 100644
--- a/drivers/net/ethernet/intel/ice/Makefile
+++ b/drivers/net/ethernet/intel/ice/Makefile
@@ -34,7 +34,9 @@ ice-y := ice_main.o	\
 	 ice_lag.o	\
 	 ice_ethtool.o  \
 	 ice_repr.o	\
-	 ice_tc_lib.o
+	 ice_tc_lib.o	\
+	 ice_fwlog.o	\
+	 ice_debugfs.o
 ice-$(CONFIG_PCI_IOV) +=	\
 	ice_sriov.o		\
 	ice_virtchnl.o		\
@@ -49,3 +51,4 @@ ice-$(CONFIG_RFS_ACCEL) += ice_arfs.o
 ice-$(CONFIG_XDP_SOCKETS) += ice_xsk.o
 ice-$(CONFIG_ICE_SWITCHDEV) += ice_eswitch.o ice_eswitch_br.o
 ice-$(CONFIG_GNSS) += ice_gnss.o
+ice-$(CONFIG_ICE_HWMON) += ice_hwmon.o
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 351e0d36df44..367b613d92c0 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -360,6 +360,7 @@ struct ice_vsi {
 	/* RSS config */
 	u16 rss_table_size;	/* HW RSS table size */
 	u16 rss_size;		/* Allocated RSS queues */
+	u8 rss_hfunc;		/* User configured hash type */
 	u8 *rss_hkey_user;	/* User configured hash keys */
 	u8 *rss_lut_user;	/* User configured lookup table entries */
 	u8 rss_lut_type;	/* used to configure Get/Set RSS LUT AQ call */
@@ -517,16 +518,22 @@ enum ice_pf_flags {
 };
 
 enum ice_misc_thread_tasks {
-	ICE_MISC_THREAD_EXTTS_EVENT,
 	ICE_MISC_THREAD_TX_TSTAMP,
 	ICE_MISC_THREAD_NBITS		/* must be last */
 };
 
-struct ice_switchdev_info {
+struct ice_eswitch {
 	struct ice_vsi *control_vsi;
 	struct ice_vsi *uplink_vsi;
 	struct ice_esw_br_offloads *br_offloads;
+	struct xarray reprs;
 	bool is_running;
+	/* struct to allow cp queues management optimization */
+	struct {
+		int to_reach;
+		int value;
+		bool is_reaching;
+	} qs;
 };
 
 struct ice_agg_node {
@@ -563,6 +570,10 @@ struct ice_pf {
 	struct ice_vsi_stats **vsi_stats;
 	struct ice_sw *first_sw;	/* first switch created by firmware */
 	u16 eswitch_mode;		/* current mode of eswitch */
+	struct dentry *ice_debugfs_pf;
+	struct dentry *ice_debugfs_pf_fwlog;
+	/* keep track of all the dentrys for FW log modules */
+	struct dentry **ice_debugfs_pf_fwlog_modules;
 	struct ice_vfs vfs;
 	DECLARE_BITMAP(features, ICE_F_MAX);
 	DECLARE_BITMAP(state, ICE_STATE_NBITS);
@@ -597,6 +608,7 @@ struct ice_pf {
 	u32 hw_csum_rx_error;
 	u32 oicr_err_reg;
 	struct msi_map oicr_irq;	/* Other interrupt cause MSIX vector */
+	struct msi_map ll_ts_irq;	/* LL_TS interrupt MSIX vector */
 	u16 max_pf_txqs;	/* Total Tx queues PF wide */
 	u16 max_pf_rxqs;	/* Total Rx queues PF wide */
 	u16 num_lan_msix;	/* Total MSIX vectors for base driver */
@@ -621,6 +633,7 @@ struct ice_pf {
 	unsigned long tx_timeout_last_recovery;
 	u32 tx_timeout_recovery_level;
 	char int_name[ICE_INT_NAME_STR_LEN];
+	char int_name_ll_ts[ICE_INT_NAME_STR_LEN];
 	struct auxiliary_device *adev;
 	int aux_idx;
 	u32 sw_int_count;
@@ -637,7 +650,7 @@ struct ice_pf {
 	struct ice_link_default_override_tlv link_dflt_override;
 	struct ice_lag *lag; /* Link Aggregation information */
 
-	struct ice_switchdev_info switchdev;
+	struct ice_eswitch eswitch;
 	struct ice_esw_br_port *br_port;
 
 #define ICE_INVALID_AGG_NODE_ID		0
@@ -648,6 +661,7 @@ struct ice_pf {
 #define ICE_MAX_VF_AGG_NODES		32
 	struct ice_agg_node vf_agg_node[ICE_MAX_VF_AGG_NODES];
 	struct ice_dplls dplls;
+	struct device *hwmon_dev;
 };
 
 extern struct workqueue_struct *ice_lag_wq;
@@ -846,7 +860,7 @@ static inline struct ice_vsi *ice_find_vsi(struct ice_pf *pf, u16 vsi_num)
  */
 static inline bool ice_is_switchdev_running(struct ice_pf *pf)
 {
-	return pf->switchdev.is_running;
+	return pf->eswitch.is_running;
 }
 
 #define ICE_FD_STAT_CTR_BLOCK_COUNT	256
@@ -881,6 +895,11 @@ static inline bool ice_is_adq_active(struct ice_pf *pf)
 	return false;
 }
 
+void ice_debugfs_fwlog_init(struct ice_pf *pf);
+void ice_debugfs_init(void);
+void ice_debugfs_exit(void);
+void ice_pf_fwlog_update_module(struct ice_pf *pf, int log_level, int module);
+
 bool netif_is_ice(const struct net_device *dev);
 int ice_vsi_setup_tx_rings(struct ice_vsi *vsi);
 int ice_vsi_setup_rx_rings(struct ice_vsi *vsi);
@@ -912,6 +931,7 @@ int ice_set_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size);
 int ice_get_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size);
 int ice_set_rss_key(struct ice_vsi *vsi, u8 *seed);
 int ice_get_rss_key(struct ice_vsi *vsi, u8 *seed);
+int ice_set_rss_hfunc(struct ice_vsi *vsi, u8 hfunc);
 void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size);
 int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset);
 void ice_print_link_msg(struct ice_vsi *vsi, bool isup);
@@ -989,4 +1009,6 @@ static inline void ice_clear_rdma_cap(struct ice_pf *pf)
 	set_bit(ICE_FLAG_UNPLUG_AUX_DEV, pf->flags);
 	clear_bit(ICE_FLAG_RDMA_ENA, pf->flags);
 }
+
+extern const struct xdp_metadata_ops ice_xdp_md_ops;
 #endif /* _ICE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index d7fdb7ba7268..8040317c9561 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -117,6 +117,7 @@ struct ice_aqc_list_caps_elem {
 #define ICE_AQC_CAPS_NET_VER				0x004C
 #define ICE_AQC_CAPS_PENDING_NET_VER			0x004D
 #define ICE_AQC_CAPS_RDMA				0x0051
+#define ICE_AQC_CAPS_SENSOR_READING			0x0067
 #define ICE_AQC_CAPS_PCIE_RESET_AVOIDANCE		0x0076
 #define ICE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT		0x0077
 #define ICE_AQC_CAPS_NVM_MGMT				0x0080
@@ -421,10 +422,10 @@ struct ice_aqc_vsi_props {
 #define ICE_AQ_VSI_INNER_VLAN_INSERT_PVID	BIT(2)
 #define ICE_AQ_VSI_INNER_VLAN_EMODE_S		3
 #define ICE_AQ_VSI_INNER_VLAN_EMODE_M		(0x3 << ICE_AQ_VSI_INNER_VLAN_EMODE_S)
-#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR_BOTH	(0x0 << ICE_AQ_VSI_INNER_VLAN_EMODE_S)
-#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR_UP	(0x1 << ICE_AQ_VSI_INNER_VLAN_EMODE_S)
-#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR		(0x2 << ICE_AQ_VSI_INNER_VLAN_EMODE_S)
-#define ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING	(0x3 << ICE_AQ_VSI_INNER_VLAN_EMODE_S)
+#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR_BOTH	0x0U
+#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR_UP	0x1U
+#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR		0x2U
+#define ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING	0x3U
 	u8 inner_vlan_reserved2[3];
 	/* ingress egress up sections */
 	__le32 ingress_table; /* bitmap, 3 bits per up */
@@ -490,11 +491,11 @@ struct ice_aqc_vsi_props {
 #define ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_S		2
 #define ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_M		(0xF << ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_S)
 #define ICE_AQ_VSI_Q_OPT_RSS_HASH_S		6
-#define ICE_AQ_VSI_Q_OPT_RSS_HASH_M		(0x3 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S)
-#define ICE_AQ_VSI_Q_OPT_RSS_TPLZ		(0x0 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S)
-#define ICE_AQ_VSI_Q_OPT_RSS_SYM_TPLZ		(0x1 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S)
-#define ICE_AQ_VSI_Q_OPT_RSS_XOR		(0x2 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S)
-#define ICE_AQ_VSI_Q_OPT_RSS_JHASH		(0x3 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S)
+#define ICE_AQ_VSI_Q_OPT_RSS_HASH_M		GENMASK(7, 6)
+#define ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ		0x0U
+#define ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ	0x1U
+#define ICE_AQ_VSI_Q_OPT_RSS_HASH_XOR		0x2U
+#define ICE_AQ_VSI_Q_OPT_RSS_HASH_JHASH		0x3U
 	u8 q_opt_tc;
 #define ICE_AQ_VSI_Q_OPT_TC_OVR_S		0
 #define ICE_AQ_VSI_Q_OPT_TC_OVR_M		(0x1F << ICE_AQ_VSI_Q_OPT_TC_OVR_S)
@@ -1359,8 +1360,9 @@ struct ice_aqc_get_link_status_data {
 	u8 lp_flowcontrol;
 #define ICE_AQ_LINK_LP_PAUSE_ADV       BIT(0)
 #define ICE_AQ_LINK_LP_ASM_DIR_ADV     BIT(1)
+	u8 reserved5[5];
 #define ICE_AQC_LS_DATA_SIZE_V2 \
-	offsetofend(struct ice_aqc_get_link_status_data, lp_flowcontrol)
+	offsetofend(struct ice_aqc_get_link_status_data, reserved5)
 } __packed;
 
 /* Set event mask command (direct 0x0613) */
@@ -1413,6 +1415,30 @@ struct ice_aqc_get_phy_rec_clk_out {
 	__le16 node_handle;
 };
 
+/* Get sensor reading (direct 0x0632) */
+struct ice_aqc_get_sensor_reading {
+	u8 sensor;
+	u8 format;
+	u8 reserved[6];
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* Get sensor reading response (direct 0x0632) */
+struct ice_aqc_get_sensor_reading_resp {
+	union {
+		u8 raw[8];
+		/* Output data for sensor 0x00, format 0x00 */
+		struct _packed {
+			s8 temp;
+			u8 temp_warning_threshold;
+			u8 temp_critical_threshold;
+			u8 temp_fatal_threshold;
+			u8 reserved[4];
+		} s0f0;
+	} data;
+};
+
 struct ice_aqc_link_topo_params {
 	u8 lport_num;
 	u8 lport_num_valid;
@@ -2069,78 +2095,6 @@ struct ice_aqc_add_rdma_qset_data {
 	struct ice_aqc_add_tx_rdma_qset_entry rdma_qsets[];
 };
 
-/* Configure Firmware Logging Command (indirect 0xFF09)
- * Logging Information Read Response (indirect 0xFF10)
- * Note: The 0xFF10 command has no input parameters.
- */
-struct ice_aqc_fw_logging {
-	u8 log_ctrl;
-#define ICE_AQC_FW_LOG_AQ_EN		BIT(0)
-#define ICE_AQC_FW_LOG_UART_EN		BIT(1)
-	u8 rsvd0;
-	u8 log_ctrl_valid; /* Not used by 0xFF10 Response */
-#define ICE_AQC_FW_LOG_AQ_VALID		BIT(0)
-#define ICE_AQC_FW_LOG_UART_VALID	BIT(1)
-	u8 rsvd1[5];
-	__le32 addr_high;
-	__le32 addr_low;
-};
-
-enum ice_aqc_fw_logging_mod {
-	ICE_AQC_FW_LOG_ID_GENERAL = 0,
-	ICE_AQC_FW_LOG_ID_CTRL,
-	ICE_AQC_FW_LOG_ID_LINK,
-	ICE_AQC_FW_LOG_ID_LINK_TOPO,
-	ICE_AQC_FW_LOG_ID_DNL,
-	ICE_AQC_FW_LOG_ID_I2C,
-	ICE_AQC_FW_LOG_ID_SDP,
-	ICE_AQC_FW_LOG_ID_MDIO,
-	ICE_AQC_FW_LOG_ID_ADMINQ,
-	ICE_AQC_FW_LOG_ID_HDMA,
-	ICE_AQC_FW_LOG_ID_LLDP,
-	ICE_AQC_FW_LOG_ID_DCBX,
-	ICE_AQC_FW_LOG_ID_DCB,
-	ICE_AQC_FW_LOG_ID_NETPROXY,
-	ICE_AQC_FW_LOG_ID_NVM,
-	ICE_AQC_FW_LOG_ID_AUTH,
-	ICE_AQC_FW_LOG_ID_VPD,
-	ICE_AQC_FW_LOG_ID_IOSF,
-	ICE_AQC_FW_LOG_ID_PARSER,
-	ICE_AQC_FW_LOG_ID_SW,
-	ICE_AQC_FW_LOG_ID_SCHEDULER,
-	ICE_AQC_FW_LOG_ID_TXQ,
-	ICE_AQC_FW_LOG_ID_RSVD,
-	ICE_AQC_FW_LOG_ID_POST,
-	ICE_AQC_FW_LOG_ID_WATCHDOG,
-	ICE_AQC_FW_LOG_ID_TASK_DISPATCH,
-	ICE_AQC_FW_LOG_ID_MNG,
-	ICE_AQC_FW_LOG_ID_MAX,
-};
-
-/* Defines for both above FW logging command/response buffers */
-#define ICE_AQC_FW_LOG_ID_S		0
-#define ICE_AQC_FW_LOG_ID_M		(0xFFF << ICE_AQC_FW_LOG_ID_S)
-
-#define ICE_AQC_FW_LOG_CONF_SUCCESS	0	/* Used by response */
-#define ICE_AQC_FW_LOG_CONF_BAD_INDX	BIT(12)	/* Used by response */
-
-#define ICE_AQC_FW_LOG_EN_S		12
-#define ICE_AQC_FW_LOG_EN_M		(0xF << ICE_AQC_FW_LOG_EN_S)
-#define ICE_AQC_FW_LOG_INFO_EN		BIT(12)	/* Used by command */
-#define ICE_AQC_FW_LOG_INIT_EN		BIT(13)	/* Used by command */
-#define ICE_AQC_FW_LOG_FLOW_EN		BIT(14)	/* Used by command */
-#define ICE_AQC_FW_LOG_ERR_EN		BIT(15)	/* Used by command */
-
-/* Get/Clear FW Log (indirect 0xFF11) */
-struct ice_aqc_get_clear_fw_log {
-	u8 flags;
-#define ICE_AQC_FW_LOG_CLEAR		BIT(0)
-#define ICE_AQC_FW_LOG_MORE_DATA_AVAIL	BIT(1)
-	u8 rsvd1[7];
-	__le32 addr_high;
-	__le32 addr_low;
-};
-
 /* Download Package (indirect 0x0C40) */
 /* Also used for Update Package (indirect 0x0C41 and 0x0C42) */
 struct ice_aqc_download_pkg {
@@ -2403,6 +2357,84 @@ struct ice_aqc_event_lan_overflow {
 	u8 reserved[8];
 };
 
+enum ice_aqc_fw_logging_mod {
+	ICE_AQC_FW_LOG_ID_GENERAL = 0,
+	ICE_AQC_FW_LOG_ID_CTRL,
+	ICE_AQC_FW_LOG_ID_LINK,
+	ICE_AQC_FW_LOG_ID_LINK_TOPO,
+	ICE_AQC_FW_LOG_ID_DNL,
+	ICE_AQC_FW_LOG_ID_I2C,
+	ICE_AQC_FW_LOG_ID_SDP,
+	ICE_AQC_FW_LOG_ID_MDIO,
+	ICE_AQC_FW_LOG_ID_ADMINQ,
+	ICE_AQC_FW_LOG_ID_HDMA,
+	ICE_AQC_FW_LOG_ID_LLDP,
+	ICE_AQC_FW_LOG_ID_DCBX,
+	ICE_AQC_FW_LOG_ID_DCB,
+	ICE_AQC_FW_LOG_ID_XLR,
+	ICE_AQC_FW_LOG_ID_NVM,
+	ICE_AQC_FW_LOG_ID_AUTH,
+	ICE_AQC_FW_LOG_ID_VPD,
+	ICE_AQC_FW_LOG_ID_IOSF,
+	ICE_AQC_FW_LOG_ID_PARSER,
+	ICE_AQC_FW_LOG_ID_SW,
+	ICE_AQC_FW_LOG_ID_SCHEDULER,
+	ICE_AQC_FW_LOG_ID_TXQ,
+	ICE_AQC_FW_LOG_ID_RSVD,
+	ICE_AQC_FW_LOG_ID_POST,
+	ICE_AQC_FW_LOG_ID_WATCHDOG,
+	ICE_AQC_FW_LOG_ID_TASK_DISPATCH,
+	ICE_AQC_FW_LOG_ID_MNG,
+	ICE_AQC_FW_LOG_ID_SYNCE,
+	ICE_AQC_FW_LOG_ID_HEALTH,
+	ICE_AQC_FW_LOG_ID_TSDRV,
+	ICE_AQC_FW_LOG_ID_PFREG,
+	ICE_AQC_FW_LOG_ID_MDLVER,
+	ICE_AQC_FW_LOG_ID_MAX,
+};
+
+/* Set FW Logging configuration (indirect 0xFF30)
+ * Register for FW Logging (indirect 0xFF31)
+ * Query FW Logging (indirect 0xFF32)
+ * FW Log Event (indirect 0xFF33)
+ */
+struct ice_aqc_fw_log {
+	u8 cmd_flags;
+#define ICE_AQC_FW_LOG_CONF_UART_EN	BIT(0)
+#define ICE_AQC_FW_LOG_CONF_AQ_EN	BIT(1)
+#define ICE_AQC_FW_LOG_QUERY_REGISTERED	BIT(2)
+#define ICE_AQC_FW_LOG_CONF_SET_VALID	BIT(3)
+#define ICE_AQC_FW_LOG_AQ_REGISTER	BIT(0)
+#define ICE_AQC_FW_LOG_AQ_QUERY		BIT(2)
+
+	u8 rsp_flag;
+	__le16 fw_rt_msb;
+	union {
+		struct {
+			__le32 fw_rt_lsb;
+		} sync;
+		struct {
+			__le16 log_resolution;
+#define ICE_AQC_FW_LOG_MIN_RESOLUTION		(1)
+#define ICE_AQC_FW_LOG_MAX_RESOLUTION		(128)
+
+			__le16 mdl_cnt;
+		} cfg;
+	} ops;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* Response Buffer for:
+ *    Set Firmware Logging Configuration (0xFF30)
+ *    Query FW Logging (0xFF32)
+ */
+struct ice_aqc_fw_log_cfg_resp {
+	__le16 module_identifier;
+	u8 log_level;
+	u8 rsvd0;
+};
+
 /**
  * struct ice_aq_desc - Admin Queue (AQ) descriptor
  * @flags: ICE_AQ_FLAG_* flags
@@ -2443,6 +2475,8 @@ struct ice_aq_desc {
 		struct ice_aqc_restart_an restart_an;
 		struct ice_aqc_set_phy_rec_clk_out set_phy_rec_clk_out;
 		struct ice_aqc_get_phy_rec_clk_out get_phy_rec_clk_out;
+		struct ice_aqc_get_sensor_reading get_sensor_reading;
+		struct ice_aqc_get_sensor_reading_resp get_sensor_reading_resp;
 		struct ice_aqc_gpio read_write_gpio;
 		struct ice_aqc_sff_eeprom read_write_sff_param;
 		struct ice_aqc_set_port_id_led set_port_id_led;
@@ -2480,8 +2514,6 @@ struct ice_aq_desc {
 		struct ice_aqc_add_rdma_qset add_rdma_qset;
 		struct ice_aqc_add_get_update_free_vsi vsi_cmd;
 		struct ice_aqc_add_update_free_vsi_resp add_update_free_vsi_res;
-		struct ice_aqc_fw_logging fw_logging;
-		struct ice_aqc_get_clear_fw_log get_clear_fw_log;
 		struct ice_aqc_download_pkg download_pkg;
 		struct ice_aqc_set_cgu_input_config set_cgu_input_config;
 		struct ice_aqc_get_cgu_input_config get_cgu_input_config;
@@ -2493,6 +2525,7 @@ struct ice_aq_desc {
 		struct ice_aqc_get_cgu_ref_prio get_cgu_ref_prio;
 		struct ice_aqc_get_cgu_info get_cgu_info;
 		struct ice_aqc_driver_shared_params drv_shared_params;
+		struct ice_aqc_fw_log fw_log;
 		struct ice_aqc_set_mac_lb set_mac_lb;
 		struct ice_aqc_alloc_free_res_cmd sw_res_ctrl;
 		struct ice_aqc_set_mac_cfg set_mac_cfg;
@@ -2618,6 +2651,7 @@ enum ice_adminq_opc {
 	ice_aqc_opc_set_mac_lb				= 0x0620,
 	ice_aqc_opc_set_phy_rec_clk_out			= 0x0630,
 	ice_aqc_opc_get_phy_rec_clk_out			= 0x0631,
+	ice_aqc_opc_get_sensor_reading			= 0x0632,
 	ice_aqc_opc_get_link_topo			= 0x06E0,
 	ice_aqc_opc_read_i2c				= 0x06E2,
 	ice_aqc_opc_write_i2c				= 0x06E3,
@@ -2690,9 +2724,11 @@ enum ice_adminq_opc {
 	/* Standalone Commands/Events */
 	ice_aqc_opc_event_lan_overflow			= 0x1001,
 
-	/* debug commands */
-	ice_aqc_opc_fw_logging				= 0xFF09,
-	ice_aqc_opc_fw_logging_info			= 0xFF10,
+	/* FW Logging Commands */
+	ice_aqc_opc_fw_logs_config			= 0xFF30,
+	ice_aqc_opc_fw_logs_register			= 0xFF31,
+	ice_aqc_opc_fw_logs_query			= 0xFF32,
+	ice_aqc_opc_fw_logs_event			= 0xFF33,
 };
 
 #endif /* _ICE_ADMINQ_CMD_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 7fa43827a3f0..533b923cae2d 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -189,10 +189,18 @@ static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx)
 	}
 	q_vector = vsi->q_vectors[v_idx];
 
-	ice_for_each_tx_ring(tx_ring, q_vector->tx)
+	ice_for_each_tx_ring(tx_ring, q_vector->tx) {
+		if (vsi->netdev)
+			netif_queue_set_napi(vsi->netdev, tx_ring->q_index,
+					     NETDEV_QUEUE_TYPE_TX, NULL);
 		tx_ring->q_vector = NULL;
-	ice_for_each_rx_ring(rx_ring, q_vector->rx)
+	}
+	ice_for_each_rx_ring(rx_ring, q_vector->rx) {
+		if (vsi->netdev)
+			netif_queue_set_napi(vsi->netdev, rx_ring->q_index,
+					     NETDEV_QUEUE_TYPE_RX, NULL);
 		rx_ring->q_vector = NULL;
+	}
 
 	/* only VSI with an associated netdev is set up with NAPI */
 	if (vsi->netdev)
@@ -224,24 +232,16 @@ static void ice_cfg_itr_gran(struct ice_hw *hw)
 
 	/* no need to update global register if ITR gran is already set */
 	if (!(regval & GLINT_CTL_DIS_AUTOMASK_M) &&
-	    (((regval & GLINT_CTL_ITR_GRAN_200_M) >>
-	     GLINT_CTL_ITR_GRAN_200_S) == ICE_ITR_GRAN_US) &&
-	    (((regval & GLINT_CTL_ITR_GRAN_100_M) >>
-	     GLINT_CTL_ITR_GRAN_100_S) == ICE_ITR_GRAN_US) &&
-	    (((regval & GLINT_CTL_ITR_GRAN_50_M) >>
-	     GLINT_CTL_ITR_GRAN_50_S) == ICE_ITR_GRAN_US) &&
-	    (((regval & GLINT_CTL_ITR_GRAN_25_M) >>
-	      GLINT_CTL_ITR_GRAN_25_S) == ICE_ITR_GRAN_US))
+	    (FIELD_GET(GLINT_CTL_ITR_GRAN_200_M, regval) == ICE_ITR_GRAN_US) &&
+	    (FIELD_GET(GLINT_CTL_ITR_GRAN_100_M, regval) == ICE_ITR_GRAN_US) &&
+	    (FIELD_GET(GLINT_CTL_ITR_GRAN_50_M, regval) == ICE_ITR_GRAN_US) &&
+	    (FIELD_GET(GLINT_CTL_ITR_GRAN_25_M, regval) == ICE_ITR_GRAN_US))
 		return;
 
-	regval = ((ICE_ITR_GRAN_US << GLINT_CTL_ITR_GRAN_200_S) &
-		  GLINT_CTL_ITR_GRAN_200_M) |
-		 ((ICE_ITR_GRAN_US << GLINT_CTL_ITR_GRAN_100_S) &
-		  GLINT_CTL_ITR_GRAN_100_M) |
-		 ((ICE_ITR_GRAN_US << GLINT_CTL_ITR_GRAN_50_S) &
-		  GLINT_CTL_ITR_GRAN_50_M) |
-		 ((ICE_ITR_GRAN_US << GLINT_CTL_ITR_GRAN_25_S) &
-		  GLINT_CTL_ITR_GRAN_25_M);
+	regval = FIELD_PREP(GLINT_CTL_ITR_GRAN_200_M, ICE_ITR_GRAN_US) |
+		 FIELD_PREP(GLINT_CTL_ITR_GRAN_100_M, ICE_ITR_GRAN_US) |
+		 FIELD_PREP(GLINT_CTL_ITR_GRAN_50_M, ICE_ITR_GRAN_US) |
+		 FIELD_PREP(GLINT_CTL_ITR_GRAN_25_M, ICE_ITR_GRAN_US);
 	wr32(hw, GLINT_CTL, regval);
 }
 
@@ -278,7 +278,7 @@ static u16 ice_calc_txq_handle(struct ice_vsi *vsi, struct ice_tx_ring *ring, u8
  */
 static u16 ice_eswitch_calc_txq_handle(struct ice_tx_ring *ring)
 {
-	struct ice_vsi *vsi = ring->vsi;
+	const struct ice_vsi *vsi = ring->vsi;
 	int i;
 
 	ice_for_each_txq(vsi, i) {
@@ -519,6 +519,19 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring)
 	return 0;
 }
 
+static void ice_xsk_pool_fill_cb(struct ice_rx_ring *ring)
+{
+	void *ctx_ptr = &ring->pkt_ctx;
+	struct xsk_cb_desc desc = {};
+
+	XSK_CHECK_PRIV_TYPE(struct ice_xdp_buff);
+	desc.src = &ctx_ptr;
+	desc.off = offsetof(struct ice_xdp_buff, pkt_ctx) -
+		   sizeof(struct xdp_buff);
+	desc.bytes = sizeof(ctx_ptr);
+	xsk_pool_fill_cb(ring->xsk_pool, &desc);
+}
+
 /**
  * ice_vsi_cfg_rxq - Configure an Rx queue
  * @ring: the ring being configured
@@ -553,6 +566,7 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			if (err)
 				return err;
 			xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq);
+			ice_xsk_pool_fill_cb(ring);
 
 			dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
 				 ring->q_index);
@@ -575,6 +589,7 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 
 	xdp_init_buff(&ring->xdp, ice_rx_pg_size(ring) / 2, &ring->xdp_rxq);
 	ring->xdp.data = NULL;
+	ring->xdp_ext.pkt_ctx = &ring->pkt_ctx;
 	err = ice_setup_rx_ctx(ring);
 	if (err) {
 		dev_err(dev, "ice_setup_rx_ctx failed for RxQ %d, err %d\n",
@@ -913,10 +928,10 @@ ice_cfg_txq_interrupt(struct ice_vsi *vsi, u16 txq, u16 msix_idx, u16 itr_idx)
 	struct ice_hw *hw = &pf->hw;
 	u32 val;
 
-	itr_idx = (itr_idx << QINT_TQCTL_ITR_INDX_S) & QINT_TQCTL_ITR_INDX_M;
+	itr_idx = FIELD_PREP(QINT_TQCTL_ITR_INDX_M, itr_idx);
 
 	val = QINT_TQCTL_CAUSE_ENA_M | itr_idx |
-	      ((msix_idx << QINT_TQCTL_MSIX_INDX_S) & QINT_TQCTL_MSIX_INDX_M);
+	      FIELD_PREP(QINT_TQCTL_MSIX_INDX_M, msix_idx);
 
 	wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), val);
 	if (ice_is_xdp_ena_vsi(vsi)) {
@@ -945,10 +960,10 @@ ice_cfg_rxq_interrupt(struct ice_vsi *vsi, u16 rxq, u16 msix_idx, u16 itr_idx)
 	struct ice_hw *hw = &pf->hw;
 	u32 val;
 
-	itr_idx = (itr_idx << QINT_RQCTL_ITR_INDX_S) & QINT_RQCTL_ITR_INDX_M;
+	itr_idx = FIELD_PREP(QINT_RQCTL_ITR_INDX_M, itr_idx);
 
 	val = QINT_RQCTL_CAUSE_ENA_M | itr_idx |
-	      ((msix_idx << QINT_RQCTL_MSIX_INDX_S) & QINT_RQCTL_MSIX_INDX_M);
+	      FIELD_PREP(QINT_RQCTL_MSIX_INDX_M, msix_idx);
 
 	wr32(hw, QINT_RQCTL(vsi->rxq_map[rxq]), val);
 
@@ -960,7 +975,7 @@ ice_cfg_rxq_interrupt(struct ice_vsi *vsi, u16 rxq, u16 msix_idx, u16 itr_idx)
  * @hw: pointer to the HW structure
  * @q_vector: interrupt vector to trigger the software interrupt for
  */
-void ice_trigger_sw_intr(struct ice_hw *hw, struct ice_q_vector *q_vector)
+void ice_trigger_sw_intr(struct ice_hw *hw, const struct ice_q_vector *q_vector)
 {
 	wr32(hw, GLINT_DYN_CTL(q_vector->reg_idx),
 	     (ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S) |
@@ -1035,7 +1050,7 @@ ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
  * are needed for stopping Tx queue
  */
 void
-ice_fill_txq_meta(struct ice_vsi *vsi, struct ice_tx_ring *ring,
+ice_fill_txq_meta(const struct ice_vsi *vsi, struct ice_tx_ring *ring,
 		  struct ice_txq_meta *txq_meta)
 {
 	struct ice_channel *ch = ring->ch;
diff --git a/drivers/net/ethernet/intel/ice/ice_base.h b/drivers/net/ethernet/intel/ice/ice_base.h
index b67dca417acb..17321ba75602 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.h
+++ b/drivers/net/ethernet/intel/ice/ice_base.h
@@ -22,12 +22,12 @@ void
 ice_cfg_txq_interrupt(struct ice_vsi *vsi, u16 txq, u16 msix_idx, u16 itr_idx);
 void
 ice_cfg_rxq_interrupt(struct ice_vsi *vsi, u16 rxq, u16 msix_idx, u16 itr_idx);
-void ice_trigger_sw_intr(struct ice_hw *hw, struct ice_q_vector *q_vector);
+void ice_trigger_sw_intr(struct ice_hw *hw, const struct ice_q_vector *q_vector);
 int
 ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
 		     u16 rel_vmvf_num, struct ice_tx_ring *ring,
 		     struct ice_txq_meta *txq_meta);
 void
-ice_fill_txq_meta(struct ice_vsi *vsi, struct ice_tx_ring *ring,
+ice_fill_txq_meta(const struct ice_vsi *vsi, struct ice_tx_ring *ring,
 		  struct ice_txq_meta *txq_meta);
 #endif /* _ICE_BASE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 9a6c25f98632..10c32cd80fff 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -934,216 +934,6 @@ static void ice_cleanup_fltr_mgmt_struct(struct ice_hw *hw)
 }
 
 /**
- * ice_get_fw_log_cfg - get FW logging configuration
- * @hw: pointer to the HW struct
- */
-static int ice_get_fw_log_cfg(struct ice_hw *hw)
-{
-	struct ice_aq_desc desc;
-	__le16 *config;
-	int status;
-	u16 size;
-
-	size = sizeof(*config) * ICE_AQC_FW_LOG_ID_MAX;
-	config = kzalloc(size, GFP_KERNEL);
-	if (!config)
-		return -ENOMEM;
-
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logging_info);
-
-	status = ice_aq_send_cmd(hw, &desc, config, size, NULL);
-	if (!status) {
-		u16 i;
-
-		/* Save FW logging information into the HW structure */
-		for (i = 0; i < ICE_AQC_FW_LOG_ID_MAX; i++) {
-			u16 v, m, flgs;
-
-			v = le16_to_cpu(config[i]);
-			m = (v & ICE_AQC_FW_LOG_ID_M) >> ICE_AQC_FW_LOG_ID_S;
-			flgs = (v & ICE_AQC_FW_LOG_EN_M) >> ICE_AQC_FW_LOG_EN_S;
-
-			if (m < ICE_AQC_FW_LOG_ID_MAX)
-				hw->fw_log.evnts[m].cur = flgs;
-		}
-	}
-
-	kfree(config);
-
-	return status;
-}
-
-/**
- * ice_cfg_fw_log - configure FW logging
- * @hw: pointer to the HW struct
- * @enable: enable certain FW logging events if true, disable all if false
- *
- * This function enables/disables the FW logging via Rx CQ events and a UART
- * port based on predetermined configurations. FW logging via the Rx CQ can be
- * enabled/disabled for individual PF's. However, FW logging via the UART can
- * only be enabled/disabled for all PFs on the same device.
- *
- * To enable overall FW logging, the "cq_en" and "uart_en" enable bits in
- * hw->fw_log need to be set accordingly, e.g. based on user-provided input,
- * before initializing the device.
- *
- * When re/configuring FW logging, callers need to update the "cfg" elements of
- * the hw->fw_log.evnts array with the desired logging event configurations for
- * modules of interest. When disabling FW logging completely, the callers can
- * just pass false in the "enable" parameter. On completion, the function will
- * update the "cur" element of the hw->fw_log.evnts array with the resulting
- * logging event configurations of the modules that are being re/configured. FW
- * logging modules that are not part of a reconfiguration operation retain their
- * previous states.
- *
- * Before resetting the device, it is recommended that the driver disables FW
- * logging before shutting down the control queue. When disabling FW logging
- * ("enable" = false), the latest configurations of FW logging events stored in
- * hw->fw_log.evnts[] are not overridden to allow them to be reconfigured after
- * a device reset.
- *
- * When enabling FW logging to emit log messages via the Rx CQ during the
- * device's initialization phase, a mechanism alternative to interrupt handlers
- * needs to be used to extract FW log messages from the Rx CQ periodically and
- * to prevent the Rx CQ from being full and stalling other types of control
- * messages from FW to SW. Interrupts are typically disabled during the device's
- * initialization phase.
- */
-static int ice_cfg_fw_log(struct ice_hw *hw, bool enable)
-{
-	struct ice_aqc_fw_logging *cmd;
-	u16 i, chgs = 0, len = 0;
-	struct ice_aq_desc desc;
-	__le16 *data = NULL;
-	u8 actv_evnts = 0;
-	void *buf = NULL;
-	int status = 0;
-
-	if (!hw->fw_log.cq_en && !hw->fw_log.uart_en)
-		return 0;
-
-	/* Disable FW logging only when the control queue is still responsive */
-	if (!enable &&
-	    (!hw->fw_log.actv_evnts || !ice_check_sq_alive(hw, &hw->adminq)))
-		return 0;
-
-	/* Get current FW log settings */
-	status = ice_get_fw_log_cfg(hw);
-	if (status)
-		return status;
-
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logging);
-	cmd = &desc.params.fw_logging;
-
-	/* Indicate which controls are valid */
-	if (hw->fw_log.cq_en)
-		cmd->log_ctrl_valid |= ICE_AQC_FW_LOG_AQ_VALID;
-
-	if (hw->fw_log.uart_en)
-		cmd->log_ctrl_valid |= ICE_AQC_FW_LOG_UART_VALID;
-
-	if (enable) {
-		/* Fill in an array of entries with FW logging modules and
-		 * logging events being reconfigured.
-		 */
-		for (i = 0; i < ICE_AQC_FW_LOG_ID_MAX; i++) {
-			u16 val;
-
-			/* Keep track of enabled event types */
-			actv_evnts |= hw->fw_log.evnts[i].cfg;
-
-			if (hw->fw_log.evnts[i].cfg == hw->fw_log.evnts[i].cur)
-				continue;
-
-			if (!data) {
-				data = devm_kcalloc(ice_hw_to_dev(hw),
-						    ICE_AQC_FW_LOG_ID_MAX,
-						    sizeof(*data),
-						    GFP_KERNEL);
-				if (!data)
-					return -ENOMEM;
-			}
-
-			val = i << ICE_AQC_FW_LOG_ID_S;
-			val |= hw->fw_log.evnts[i].cfg << ICE_AQC_FW_LOG_EN_S;
-			data[chgs++] = cpu_to_le16(val);
-		}
-
-		/* Only enable FW logging if at least one module is specified.
-		 * If FW logging is currently enabled but all modules are not
-		 * enabled to emit log messages, disable FW logging altogether.
-		 */
-		if (actv_evnts) {
-			/* Leave if there is effectively no change */
-			if (!chgs)
-				goto out;
-
-			if (hw->fw_log.cq_en)
-				cmd->log_ctrl |= ICE_AQC_FW_LOG_AQ_EN;
-
-			if (hw->fw_log.uart_en)
-				cmd->log_ctrl |= ICE_AQC_FW_LOG_UART_EN;
-
-			buf = data;
-			len = sizeof(*data) * chgs;
-			desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
-		}
-	}
-
-	status = ice_aq_send_cmd(hw, &desc, buf, len, NULL);
-	if (!status) {
-		/* Update the current configuration to reflect events enabled.
-		 * hw->fw_log.cq_en and hw->fw_log.uart_en indicate if the FW
-		 * logging mode is enabled for the device. They do not reflect
-		 * actual modules being enabled to emit log messages. So, their
-		 * values remain unchanged even when all modules are disabled.
-		 */
-		u16 cnt = enable ? chgs : (u16)ICE_AQC_FW_LOG_ID_MAX;
-
-		hw->fw_log.actv_evnts = actv_evnts;
-		for (i = 0; i < cnt; i++) {
-			u16 v, m;
-
-			if (!enable) {
-				/* When disabling all FW logging events as part
-				 * of device's de-initialization, the original
-				 * configurations are retained, and can be used
-				 * to reconfigure FW logging later if the device
-				 * is re-initialized.
-				 */
-				hw->fw_log.evnts[i].cur = 0;
-				continue;
-			}
-
-			v = le16_to_cpu(data[i]);
-			m = (v & ICE_AQC_FW_LOG_ID_M) >> ICE_AQC_FW_LOG_ID_S;
-			hw->fw_log.evnts[m].cur = hw->fw_log.evnts[m].cfg;
-		}
-	}
-
-out:
-	devm_kfree(ice_hw_to_dev(hw), data);
-
-	return status;
-}
-
-/**
- * ice_output_fw_log
- * @hw: pointer to the HW struct
- * @desc: pointer to the AQ message descriptor
- * @buf: pointer to the buffer accompanying the AQ message
- *
- * Formats a FW Log message and outputs it via the standard driver logs.
- */
-void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf)
-{
-	ice_debug(hw, ICE_DBG_FW_LOG, "[ FW Log Msg Start ]\n");
-	ice_debug_array(hw, ICE_DBG_FW_LOG, 16, 1, (u8 *)buf,
-			le16_to_cpu(desc->datalen));
-	ice_debug(hw, ICE_DBG_FW_LOG, "[ FW Log Msg End ]\n");
-}
-
-/**
  * ice_get_itr_intrl_gran
  * @hw: pointer to the HW struct
  *
@@ -1152,9 +942,8 @@ void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf)
  */
 static void ice_get_itr_intrl_gran(struct ice_hw *hw)
 {
-	u8 max_agg_bw = (rd32(hw, GL_PWR_MODE_CTL) &
-			 GL_PWR_MODE_CTL_CAR_MAX_BW_M) >>
-			GL_PWR_MODE_CTL_CAR_MAX_BW_S;
+	u8 max_agg_bw = FIELD_GET(GL_PWR_MODE_CTL_CAR_MAX_BW_M,
+				  rd32(hw, GL_PWR_MODE_CTL));
 
 	switch (max_agg_bw) {
 	case ICE_MAX_AGG_BW_200G:
@@ -1186,9 +975,7 @@ int ice_init_hw(struct ice_hw *hw)
 	if (status)
 		return status;
 
-	hw->pf_id = (u8)(rd32(hw, PF_FUNC_RID) &
-			 PF_FUNC_RID_FUNC_NUM_M) >>
-		PF_FUNC_RID_FUNC_NUM_S;
+	hw->pf_id = FIELD_GET(PF_FUNC_RID_FUNC_NUM_M, rd32(hw, PF_FUNC_RID));
 
 	status = ice_reset(hw, ICE_RESET_PFR);
 	if (status)
@@ -1200,10 +987,10 @@ int ice_init_hw(struct ice_hw *hw)
 	if (status)
 		goto err_unroll_cqinit;
 
-	/* Enable FW logging. Not fatal if this fails. */
-	status = ice_cfg_fw_log(hw, true);
+	status = ice_fwlog_init(hw);
 	if (status)
-		ice_debug(hw, ICE_DBG_INIT, "Failed to enable FW logging.\n");
+		ice_debug(hw, ICE_DBG_FW_LOG, "Error initializing FW logging: %d\n",
+			  status);
 
 	status = ice_clear_pf_cfg(hw);
 	if (status)
@@ -1354,8 +1141,7 @@ void ice_deinit_hw(struct ice_hw *hw)
 	ice_free_hw_tbls(hw);
 	mutex_destroy(&hw->tnl_lock);
 
-	/* Attempt to disable FW logging before shutting down control queues */
-	ice_cfg_fw_log(hw, false);
+	ice_fwlog_deinit(hw);
 	ice_destroy_all_ctrlq(hw);
 
 	/* Clear VSI contexts if not already cleared */
@@ -1374,8 +1160,8 @@ int ice_check_reset(struct ice_hw *hw)
 	 * or EMPR has occurred. The grst delay value is in 100ms units.
 	 * Add 1sec for outstanding AQ commands that can take a long time.
 	 */
-	grst_timeout = ((rd32(hw, GLGEN_RSTCTL) & GLGEN_RSTCTL_GRSTDEL_M) >>
-			GLGEN_RSTCTL_GRSTDEL_S) + 10;
+	grst_timeout = FIELD_GET(GLGEN_RSTCTL_GRSTDEL_M,
+				 rd32(hw, GLGEN_RSTCTL)) + 10;
 
 	for (cnt = 0; cnt < grst_timeout; cnt++) {
 		mdelay(100);
@@ -2459,7 +2245,7 @@ ice_parse_1588_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
 	info->tmr_index_owned = ((number & ICE_TS_TMR_IDX_OWND_M) != 0);
 	info->tmr_index_assoc = ((number & ICE_TS_TMR_IDX_ASSOC_M) != 0);
 
-	info->clk_freq = (number & ICE_TS_CLK_FREQ_M) >> ICE_TS_CLK_FREQ_S;
+	info->clk_freq = FIELD_GET(ICE_TS_CLK_FREQ_M, number);
 	info->clk_src = ((number & ICE_TS_CLK_SRC_M) != 0);
 
 	if (info->clk_freq < NUM_ICE_TIME_REF_FREQ) {
@@ -2660,11 +2446,12 @@ ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 	info->tmr0_owned = ((number & ICE_TS_TMR0_OWND_M) != 0);
 	info->tmr0_ena = ((number & ICE_TS_TMR0_ENA_M) != 0);
 
-	info->tmr1_owner = (number & ICE_TS_TMR1_OWNR_M) >> ICE_TS_TMR1_OWNR_S;
+	info->tmr1_owner = FIELD_GET(ICE_TS_TMR1_OWNR_M, number);
 	info->tmr1_owned = ((number & ICE_TS_TMR1_OWND_M) != 0);
 	info->tmr1_ena = ((number & ICE_TS_TMR1_ENA_M) != 0);
 
 	info->ts_ll_read = ((number & ICE_TS_LL_TX_TS_READ_M) != 0);
+	info->ts_ll_int_read = ((number & ICE_TS_LL_TX_TS_INT_READ_M) != 0);
 
 	info->ena_ports = logical_id;
 	info->tmr_own_map = phys_id;
@@ -2685,6 +2472,8 @@ ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 		  info->tmr1_ena);
 	ice_debug(hw, ICE_DBG_INIT, "dev caps: ts_ll_read = %u\n",
 		  info->ts_ll_read);
+	ice_debug(hw, ICE_DBG_INIT, "dev caps: ts_ll_int_read = %u\n",
+		  info->ts_ll_int_read);
 	ice_debug(hw, ICE_DBG_INIT, "dev caps: ieee_1588 ena_ports = %u\n",
 		  info->ena_ports);
 	ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr_own_map = %u\n",
@@ -2711,6 +2500,26 @@ ice_parse_fdir_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 }
 
 /**
+ * ice_parse_sensor_reading_cap - Parse ICE_AQC_CAPS_SENSOR_READING cap
+ * @hw: pointer to the HW struct
+ * @dev_p: pointer to device capabilities structure
+ * @cap: capability element to parse
+ *
+ * Parse ICE_AQC_CAPS_SENSOR_READING for device capability for reading
+ * enabled sensors.
+ */
+static void
+ice_parse_sensor_reading_cap(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
+			     struct ice_aqc_list_caps_elem *cap)
+{
+	dev_p->supported_sensors = le32_to_cpu(cap->number);
+
+	ice_debug(hw, ICE_DBG_INIT,
+		  "dev caps: supported sensors (bitmap) = 0x%x\n",
+		  dev_p->supported_sensors);
+}
+
+/**
  * ice_parse_dev_caps - Parse device capabilities
  * @hw: pointer to the HW struct
  * @dev_p: pointer to device capabilities structure
@@ -2755,9 +2564,12 @@ ice_parse_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 		case ICE_AQC_CAPS_1588:
 			ice_parse_1588_dev_caps(hw, dev_p, &cap_resp[i]);
 			break;
-		case  ICE_AQC_CAPS_FD:
+		case ICE_AQC_CAPS_FD:
 			ice_parse_fdir_dev_caps(hw, dev_p, &cap_resp[i]);
 			break;
+		case ICE_AQC_CAPS_SENSOR_READING:
+			ice_parse_sensor_reading_cap(hw, dev_p, &cap_resp[i]);
+			break;
 		default:
 			/* Don't list common capabilities as unknown */
 			if (!found)
@@ -4072,6 +3884,7 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr,
 {
 	struct ice_aqc_sff_eeprom *cmd;
 	struct ice_aq_desc desc;
+	u16 i2c_bus_addr;
 	int status;
 
 	if (!data || (mem_addr & 0xff00))
@@ -4082,15 +3895,13 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr,
 	desc.flags = cpu_to_le16(ICE_AQ_FLAG_RD);
 	cmd->lport_num = (u8)(lport & 0xff);
 	cmd->lport_num_valid = (u8)((lport >> 8) & 0x01);
-	cmd->i2c_bus_addr = cpu_to_le16(((bus_addr >> 1) &
-					 ICE_AQC_SFF_I2CBUS_7BIT_M) |
-					((set_page <<
-					  ICE_AQC_SFF_SET_EEPROM_PAGE_S) &
-					 ICE_AQC_SFF_SET_EEPROM_PAGE_M));
-	cmd->i2c_mem_addr = cpu_to_le16(mem_addr & 0xff);
-	cmd->eeprom_page = cpu_to_le16((u16)page << ICE_AQC_SFF_EEPROM_PAGE_S);
+	i2c_bus_addr = FIELD_PREP(ICE_AQC_SFF_I2CBUS_7BIT_M, bus_addr >> 1) |
+		       FIELD_PREP(ICE_AQC_SFF_SET_EEPROM_PAGE_M, set_page);
 	if (write)
-		cmd->i2c_bus_addr |= cpu_to_le16(ICE_AQC_SFF_IS_WRITE);
+		i2c_bus_addr |= ICE_AQC_SFF_IS_WRITE;
+	cmd->i2c_bus_addr = cpu_to_le16(i2c_bus_addr);
+	cmd->i2c_mem_addr = cpu_to_le16(mem_addr & 0xff);
+	cmd->eeprom_page = le16_encode_bits(page, ICE_AQC_SFF_EEPROM_PAGE_M);
 
 	status = ice_aq_send_cmd(hw, &desc, data, length, cd);
 	return status;
@@ -4345,6 +4156,7 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps,
 	struct ice_aqc_dis_txq_item *item;
 	struct ice_aqc_dis_txqs *cmd;
 	struct ice_aq_desc desc;
+	u16 vmvf_and_timeout;
 	u16 i, sz = 0;
 	int status;
 
@@ -4360,27 +4172,26 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps,
 
 	cmd->num_entries = num_qgrps;
 
-	cmd->vmvf_and_timeout = cpu_to_le16((5 << ICE_AQC_Q_DIS_TIMEOUT_S) &
-					    ICE_AQC_Q_DIS_TIMEOUT_M);
+	vmvf_and_timeout = FIELD_PREP(ICE_AQC_Q_DIS_TIMEOUT_M, 5);
 
 	switch (rst_src) {
 	case ICE_VM_RESET:
 		cmd->cmd_type = ICE_AQC_Q_DIS_CMD_VM_RESET;
-		cmd->vmvf_and_timeout |=
-			cpu_to_le16(vmvf_num & ICE_AQC_Q_DIS_VMVF_NUM_M);
+		vmvf_and_timeout |= vmvf_num & ICE_AQC_Q_DIS_VMVF_NUM_M;
 		break;
 	case ICE_VF_RESET:
 		cmd->cmd_type = ICE_AQC_Q_DIS_CMD_VF_RESET;
 		/* In this case, FW expects vmvf_num to be absolute VF ID */
-		cmd->vmvf_and_timeout |=
-			cpu_to_le16((vmvf_num + hw->func_caps.vf_base_id) &
-				    ICE_AQC_Q_DIS_VMVF_NUM_M);
+		vmvf_and_timeout |= (vmvf_num + hw->func_caps.vf_base_id) &
+				    ICE_AQC_Q_DIS_VMVF_NUM_M;
 		break;
 	case ICE_NO_RESET:
 	default:
 		break;
 	}
 
+	cmd->vmvf_and_timeout = cpu_to_le16(vmvf_and_timeout);
+
 	/* flush pipe on time out */
 	cmd->cmd_type |= ICE_AQC_Q_DIS_CMD_FLUSH_PIPE;
 	/* If no queue group info, we are in a reset flow. Issue the AQ */
@@ -4455,10 +4266,8 @@ ice_aq_cfg_lan_txq(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *buf,
 	cmd->cmd_type = ICE_AQC_Q_CFG_TC_CHNG;
 	cmd->num_qs = num_qs;
 	cmd->port_num_chng = (oldport & ICE_AQC_Q_CFG_SRC_PRT_M);
-	cmd->port_num_chng |= (newport << ICE_AQC_Q_CFG_DST_PRT_S) &
-			      ICE_AQC_Q_CFG_DST_PRT_M;
-	cmd->time_out = (5 << ICE_AQC_Q_CFG_TIMEOUT_S) &
-			ICE_AQC_Q_CFG_TIMEOUT_M;
+	cmd->port_num_chng |= FIELD_PREP(ICE_AQC_Q_CFG_DST_PRT_M, newport);
+	cmd->time_out = FIELD_PREP(ICE_AQC_Q_CFG_TIMEOUT_M, 5);
 	cmd->blocked_cgds = 0;
 
 	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
@@ -5332,7 +5141,6 @@ ice_aq_get_cgu_dpll_status(struct ice_hw *hw, u8 dpll_num, u8 *ref_state,
 			   u8 *eec_mode)
 {
 	struct ice_aqc_get_cgu_dpll_status *cmd;
-	const s64 nsec_per_psec = 1000LL;
 	struct ice_aq_desc desc;
 	int status;
 
@@ -5348,8 +5156,7 @@ ice_aq_get_cgu_dpll_status(struct ice_hw *hw, u8 dpll_num, u8 *ref_state,
 		*phase_offset = le32_to_cpu(cmd->phase_offset_h);
 		*phase_offset <<= 32;
 		*phase_offset += le32_to_cpu(cmd->phase_offset_l);
-		*phase_offset = div64_s64(sign_extend64(*phase_offset, 47),
-					  nsec_per_psec);
+		*phase_offset = sign_extend64(*phase_offset, 47);
 		*eec_mode = cmd->eec_mode;
 	}
 
@@ -5541,6 +5348,35 @@ ice_aq_get_phy_rec_clk_out(struct ice_hw *hw, u8 *phy_output, u8 *port_num,
 }
 
 /**
+ * ice_aq_get_sensor_reading
+ * @hw: pointer to the HW struct
+ * @data: pointer to data to be read from the sensor
+ *
+ * Get sensor reading (0x0632)
+ */
+int ice_aq_get_sensor_reading(struct ice_hw *hw,
+			      struct ice_aqc_get_sensor_reading_resp *data)
+{
+	struct ice_aqc_get_sensor_reading *cmd;
+	struct ice_aq_desc desc;
+	int status;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_sensor_reading);
+	cmd = &desc.params.get_sensor_reading;
+#define ICE_INTERNAL_TEMP_SENSOR_FORMAT	0
+#define ICE_INTERNAL_TEMP_SENSOR	0
+	cmd->sensor = ICE_INTERNAL_TEMP_SENSOR;
+	cmd->format = ICE_INTERNAL_TEMP_SENSOR_FORMAT;
+
+	status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
+	if (!status)
+		memcpy(data, &desc.params.get_sensor_reading_resp,
+		       sizeof(*data));
+
+	return status;
+}
+
+/**
  * ice_replay_pre_init - replay pre initialization
  * @hw: pointer to the HW struct
  *
@@ -5935,7 +5771,7 @@ ice_get_link_default_override(struct ice_link_default_override_tlv *ldo,
 		ice_debug(hw, ICE_DBG_INIT, "Failed to read override link options.\n");
 		return status;
 	}
-	ldo->options = buf & ICE_LINK_OVERRIDE_OPT_M;
+	ldo->options = FIELD_GET(ICE_LINK_OVERRIDE_OPT_M, buf);
 	ldo->phy_config = (buf & ICE_LINK_OVERRIDE_PHY_CFG_M) >>
 		ICE_LINK_OVERRIDE_PHY_CFG_S;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index 31fdcac33986..3e933f75e948 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -6,6 +6,7 @@
 
 #include <linux/bitfield.h>
 
+#include "ice.h"
 #include "ice_type.h"
 #include "ice_nvm.h"
 #include "ice_flex_pipe.h"
@@ -199,7 +200,6 @@ ice_aq_cfg_lan_txq(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *buf,
 		   struct ice_sq_cd *cd);
 int ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle);
 void ice_replay_post(struct ice_hw *hw);
-void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf);
 struct ice_q_ctx *
 ice_get_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 q_handle);
 int ice_sbq_rw_reg(struct ice_hw *hw, struct ice_sbq_msg_input *in);
@@ -241,6 +241,8 @@ ice_aq_set_phy_rec_clk_out(struct ice_hw *hw, u8 phy_output, bool enable,
 int
 ice_aq_get_phy_rec_clk_out(struct ice_hw *hw, u8 *phy_output, u8 *port_num,
 			   u8 *flags, u16 *node_handle);
+int ice_aq_get_sensor_reading(struct ice_hw *hw,
+			      struct ice_aqc_get_sensor_reading_resp *data);
 void
 ice_stat_update40(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
 		  u64 *prev_stat, u64 *cur_stat);
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c
index 396e555023aa..74418c445cc4 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb.c
@@ -35,8 +35,7 @@ ice_aq_get_lldp_mib(struct ice_hw *hw, u8 bridge_type, u8 mib_type, void *buf,
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_get_mib);
 
 	cmd->type = mib_type & ICE_AQ_LLDP_MIB_TYPE_M;
-	cmd->type |= (bridge_type << ICE_AQ_LLDP_BRID_TYPE_S) &
-		ICE_AQ_LLDP_BRID_TYPE_M;
+	cmd->type |= FIELD_PREP(ICE_AQ_LLDP_BRID_TYPE_M, bridge_type);
 
 	desc.datalen = cpu_to_le16(buf_size);
 
@@ -147,8 +146,7 @@ static u8 ice_get_dcbx_status(struct ice_hw *hw)
 	u32 reg;
 
 	reg = rd32(hw, PRTDCB_GENS);
-	return (u8)((reg & PRTDCB_GENS_DCBX_STATUS_M) >>
-		    PRTDCB_GENS_DCBX_STATUS_S);
+	return FIELD_GET(PRTDCB_GENS_DCBX_STATUS_M, reg);
 }
 
 /**
@@ -174,11 +172,9 @@ ice_parse_ieee_ets_common_tlv(u8 *buf, struct ice_dcb_ets_cfg *ets_cfg)
 	 */
 	for (i = 0; i < 4; i++) {
 		ets_cfg->prio_table[i * 2] =
-			((buf[offset] & ICE_IEEE_ETS_PRIO_1_M) >>
-			 ICE_IEEE_ETS_PRIO_1_S);
+			FIELD_GET(ICE_IEEE_ETS_PRIO_1_M, buf[offset]);
 		ets_cfg->prio_table[i * 2 + 1] =
-			((buf[offset] & ICE_IEEE_ETS_PRIO_0_M) >>
-			 ICE_IEEE_ETS_PRIO_0_S);
+			FIELD_GET(ICE_IEEE_ETS_PRIO_0_M, buf[offset]);
 		offset++;
 	}
 
@@ -222,11 +218,9 @@ ice_parse_ieee_etscfg_tlv(struct ice_lldp_org_tlv *tlv,
 	 * |1bit | 1bit|3 bits|3bits|
 	 */
 	etscfg = &dcbcfg->etscfg;
-	etscfg->willing = ((buf[0] & ICE_IEEE_ETS_WILLING_M) >>
-			   ICE_IEEE_ETS_WILLING_S);
-	etscfg->cbs = ((buf[0] & ICE_IEEE_ETS_CBS_M) >> ICE_IEEE_ETS_CBS_S);
-	etscfg->maxtcs = ((buf[0] & ICE_IEEE_ETS_MAXTC_M) >>
-			  ICE_IEEE_ETS_MAXTC_S);
+	etscfg->willing = FIELD_GET(ICE_IEEE_ETS_WILLING_M, buf[0]);
+	etscfg->cbs = FIELD_GET(ICE_IEEE_ETS_CBS_M, buf[0]);
+	etscfg->maxtcs = FIELD_GET(ICE_IEEE_ETS_MAXTC_M, buf[0]);
 
 	/* Begin parsing at Priority Assignment Table (offset 1 in buf) */
 	ice_parse_ieee_ets_common_tlv(&buf[1], etscfg);
@@ -268,11 +262,9 @@ ice_parse_ieee_pfccfg_tlv(struct ice_lldp_org_tlv *tlv,
 	 * -----------------------------------------
 	 * |1bit | 1bit|2 bits|4bits| 1 octet      |
 	 */
-	dcbcfg->pfc.willing = ((buf[0] & ICE_IEEE_PFC_WILLING_M) >>
-			       ICE_IEEE_PFC_WILLING_S);
-	dcbcfg->pfc.mbc = ((buf[0] & ICE_IEEE_PFC_MBC_M) >> ICE_IEEE_PFC_MBC_S);
-	dcbcfg->pfc.pfccap = ((buf[0] & ICE_IEEE_PFC_CAP_M) >>
-			      ICE_IEEE_PFC_CAP_S);
+	dcbcfg->pfc.willing = FIELD_GET(ICE_IEEE_PFC_WILLING_M, buf[0]);
+	dcbcfg->pfc.mbc = FIELD_GET(ICE_IEEE_PFC_MBC_M, buf[0]);
+	dcbcfg->pfc.pfccap = FIELD_GET(ICE_IEEE_PFC_CAP_M, buf[0]);
 	dcbcfg->pfc.pfcena = buf[1];
 }
 
@@ -294,7 +286,7 @@ ice_parse_ieee_app_tlv(struct ice_lldp_org_tlv *tlv,
 	u8 *buf;
 
 	typelen = ntohs(tlv->typelen);
-	len = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S);
+	len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen);
 	buf = tlv->tlvinfo;
 
 	/* Removing sizeof(ouisubtype) and reserved byte from len.
@@ -314,12 +306,10 @@ ice_parse_ieee_app_tlv(struct ice_lldp_org_tlv *tlv,
 	 *        -----------------------------------------
 	 */
 	while (offset < len) {
-		dcbcfg->app[i].priority = ((buf[offset] &
-					    ICE_IEEE_APP_PRIO_M) >>
-					   ICE_IEEE_APP_PRIO_S);
-		dcbcfg->app[i].selector = ((buf[offset] &
-					    ICE_IEEE_APP_SEL_M) >>
-					   ICE_IEEE_APP_SEL_S);
+		dcbcfg->app[i].priority = FIELD_GET(ICE_IEEE_APP_PRIO_M,
+						    buf[offset]);
+		dcbcfg->app[i].selector = FIELD_GET(ICE_IEEE_APP_SEL_M,
+						    buf[offset]);
 		dcbcfg->app[i].prot_id = (buf[offset + 1] << 0x8) |
 			buf[offset + 2];
 		/* Move to next app */
@@ -347,8 +337,7 @@ ice_parse_ieee_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
 	u8 subtype;
 
 	ouisubtype = ntohl(tlv->ouisubtype);
-	subtype = (u8)((ouisubtype & ICE_LLDP_TLV_SUBTYPE_M) >>
-		       ICE_LLDP_TLV_SUBTYPE_S);
+	subtype = FIELD_GET(ICE_LLDP_TLV_SUBTYPE_M, ouisubtype);
 	switch (subtype) {
 	case ICE_IEEE_SUBTYPE_ETS_CFG:
 		ice_parse_ieee_etscfg_tlv(tlv, dcbcfg);
@@ -399,11 +388,9 @@ ice_parse_cee_pgcfg_tlv(struct ice_cee_feat_tlv *tlv,
 	 */
 	for (i = 0; i < 4; i++) {
 		etscfg->prio_table[i * 2] =
-			((buf[offset] & ICE_CEE_PGID_PRIO_1_M) >>
-			 ICE_CEE_PGID_PRIO_1_S);
+			FIELD_GET(ICE_CEE_PGID_PRIO_1_M, buf[offset]);
 		etscfg->prio_table[i * 2 + 1] =
-			((buf[offset] & ICE_CEE_PGID_PRIO_0_M) >>
-			 ICE_CEE_PGID_PRIO_0_S);
+			FIELD_GET(ICE_CEE_PGID_PRIO_0_M, buf[offset]);
 		offset++;
 	}
 
@@ -466,7 +453,7 @@ ice_parse_cee_app_tlv(struct ice_cee_feat_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
 	u8 i;
 
 	typelen = ntohs(tlv->hdr.typelen);
-	len = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S);
+	len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen);
 
 	dcbcfg->numapps = len / sizeof(*app);
 	if (!dcbcfg->numapps)
@@ -521,14 +508,13 @@ ice_parse_cee_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
 	u32 ouisubtype;
 
 	ouisubtype = ntohl(tlv->ouisubtype);
-	subtype = (u8)((ouisubtype & ICE_LLDP_TLV_SUBTYPE_M) >>
-		       ICE_LLDP_TLV_SUBTYPE_S);
+	subtype = FIELD_GET(ICE_LLDP_TLV_SUBTYPE_M, ouisubtype);
 	/* Return if not CEE DCBX */
 	if (subtype != ICE_CEE_DCBX_TYPE)
 		return;
 
 	typelen = ntohs(tlv->typelen);
-	tlvlen = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S);
+	tlvlen = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen);
 	len = sizeof(tlv->typelen) + sizeof(ouisubtype) +
 		sizeof(struct ice_cee_ctrl_tlv);
 	/* Return if no CEE DCBX Feature TLVs */
@@ -540,9 +526,8 @@ ice_parse_cee_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
 		u16 sublen;
 
 		typelen = ntohs(sub_tlv->hdr.typelen);
-		sublen = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S);
-		subtype = (u8)((typelen & ICE_LLDP_TLV_TYPE_M) >>
-			       ICE_LLDP_TLV_TYPE_S);
+		sublen = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen);
+		subtype = FIELD_GET(ICE_LLDP_TLV_TYPE_M, typelen);
 		switch (subtype) {
 		case ICE_CEE_SUBTYPE_PG_CFG:
 			ice_parse_cee_pgcfg_tlv(sub_tlv, dcbcfg);
@@ -579,7 +564,7 @@ ice_parse_org_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
 	u32 oui;
 
 	ouisubtype = ntohl(tlv->ouisubtype);
-	oui = ((ouisubtype & ICE_LLDP_TLV_OUI_M) >> ICE_LLDP_TLV_OUI_S);
+	oui = FIELD_GET(ICE_LLDP_TLV_OUI_M, ouisubtype);
 	switch (oui) {
 	case ICE_IEEE_8021QAZ_OUI:
 		ice_parse_ieee_tlv(tlv, dcbcfg);
@@ -616,8 +601,8 @@ static int ice_lldp_to_dcb_cfg(u8 *lldpmib, struct ice_dcbx_cfg *dcbcfg)
 	tlv = (struct ice_lldp_org_tlv *)lldpmib;
 	while (1) {
 		typelen = ntohs(tlv->typelen);
-		type = ((typelen & ICE_LLDP_TLV_TYPE_M) >> ICE_LLDP_TLV_TYPE_S);
-		len = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S);
+		type = FIELD_GET(ICE_LLDP_TLV_TYPE_M, typelen);
+		len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen);
 		offset += sizeof(typelen) + len;
 
 		/* END TLV or beyond LLDPDU size */
@@ -806,11 +791,11 @@ ice_cee_to_dcb_cfg(struct ice_aqc_get_cee_dcb_cfg_resp *cee_cfg,
 	 */
 	for (i = 0; i < ICE_MAX_TRAFFIC_CLASS / 2; i++) {
 		dcbcfg->etscfg.prio_table[i * 2] =
-			((cee_cfg->oper_prio_tc[i] & ICE_CEE_PGID_PRIO_0_M) >>
-			 ICE_CEE_PGID_PRIO_0_S);
+			FIELD_GET(ICE_CEE_PGID_PRIO_0_M,
+				  cee_cfg->oper_prio_tc[i]);
 		dcbcfg->etscfg.prio_table[i * 2 + 1] =
-			((cee_cfg->oper_prio_tc[i] & ICE_CEE_PGID_PRIO_1_M) >>
-			 ICE_CEE_PGID_PRIO_1_S);
+			FIELD_GET(ICE_CEE_PGID_PRIO_1_M,
+				  cee_cfg->oper_prio_tc[i]);
 	}
 
 	ice_for_each_traffic_class(i) {
@@ -982,7 +967,7 @@ void ice_get_dcb_cfg_from_mib_change(struct ice_port_info *pi,
 
 	mib = (struct ice_aqc_lldp_get_mib *)&event->desc.params.raw;
 
-	change_type = FIELD_GET(ICE_AQ_LLDP_MIB_TYPE_M,  mib->type);
+	change_type = FIELD_GET(ICE_AQ_LLDP_MIB_TYPE_M, mib->type);
 	if (change_type == ICE_AQ_LLDP_MIB_REMOTE)
 		dcbx_cfg = &pi->qos_cfg.remote_dcbx_cfg;
 
@@ -1483,7 +1468,7 @@ ice_dcb_cfg_to_lldp(u8 *lldpmib, u16 *miblen, struct ice_dcbx_cfg *dcbcfg)
 	while (1) {
 		ice_add_dcb_tlv(tlv, dcbcfg, tlvid++);
 		typelen = ntohs(tlv->typelen);
-		len = (typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S;
+		len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen);
 		if (len)
 			offset += len + 2;
 		/* END TLV or beyond LLDPDU size */
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
index 850db8e0e6b0..6e20ee610022 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
@@ -934,7 +934,7 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring,
 	    skb->priority != TC_PRIO_CONTROL) {
 		first->vid &= ~VLAN_PRIO_MASK;
 		/* Mask the lower 3 bits to set the 802.1p priority */
-		first->vid |= (skb->priority << VLAN_PRIO_SHIFT) & VLAN_PRIO_MASK;
+		first->vid |= FIELD_PREP(VLAN_PRIO_MASK, skb->priority);
 		/* if this is not already set it means a VLAN 0 + priority needs
 		 * to be offloaded
 		 */
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
index e1fbc6de452d..6d50b90a7359 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
@@ -227,7 +227,7 @@ static void ice_get_pfc_delay(struct ice_hw *hw, u16 *delay)
 	u32 val;
 
 	val = rd32(hw, PRTDCB_GENC);
-	*delay = (u16)((val & PRTDCB_GENC_PFCLDA_M) >> PRTDCB_GENC_PFCLDA_S);
+	*delay = FIELD_GET(PRTDCB_GENC_PFCLDA_M, val);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c
index cfb1580f5850..8b7504a9df31 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.c
@@ -1479,14 +1479,14 @@ ice_post_dwnld_pkg_actions(struct ice_hw *hw)
 }
 
 /**
- * ice_download_pkg
+ * ice_download_pkg_with_sig_seg
  * @hw: pointer to the hardware structure
  * @pkg_hdr: pointer to package header
  *
  * Handles the download of a complete package.
  */
 static enum ice_ddp_state
-ice_download_pkg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr)
+ice_download_pkg_with_sig_seg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr)
 {
 	enum ice_aq_err aq_err = hw->adminq.sq_last_status;
 	enum ice_ddp_state state = ICE_DDP_PKG_ERR;
@@ -1519,6 +1519,103 @@ ice_download_pkg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr)
 		state = ice_post_dwnld_pkg_actions(hw);
 
 	ice_release_global_cfg_lock(hw);
+
+	return state;
+}
+
+/**
+ * ice_dwnld_cfg_bufs
+ * @hw: pointer to the hardware structure
+ * @bufs: pointer to an array of buffers
+ * @count: the number of buffers in the array
+ *
+ * Obtains global config lock and downloads the package configuration buffers
+ * to the firmware.
+ */
+static enum ice_ddp_state
+ice_dwnld_cfg_bufs(struct ice_hw *hw, struct ice_buf *bufs, u32 count)
+{
+	enum ice_ddp_state state;
+	struct ice_buf_hdr *bh;
+	int status;
+
+	if (!bufs || !count)
+		return ICE_DDP_PKG_ERR;
+
+	/* If the first buffer's first section has its metadata bit set
+	 * then there are no buffers to be downloaded, and the operation is
+	 * considered a success.
+	 */
+	bh = (struct ice_buf_hdr *)bufs;
+	if (le32_to_cpu(bh->section_entry[0].type) & ICE_METADATA_BUF)
+		return ICE_DDP_PKG_SUCCESS;
+
+	status = ice_acquire_global_cfg_lock(hw, ICE_RES_WRITE);
+	if (status) {
+		if (status == -EALREADY)
+			return ICE_DDP_PKG_ALREADY_LOADED;
+		return ice_map_aq_err_to_ddp_state(hw->adminq.sq_last_status);
+	}
+
+	state = ice_dwnld_cfg_bufs_no_lock(hw, bufs, 0, count, true);
+	if (!state)
+		state = ice_post_dwnld_pkg_actions(hw);
+
+	ice_release_global_cfg_lock(hw);
+
+	return state;
+}
+
+/**
+ * ice_download_pkg_without_sig_seg
+ * @hw: pointer to the hardware structure
+ * @ice_seg: pointer to the segment of the package to be downloaded
+ *
+ * Handles the download of a complete package without signature segment.
+ */
+static enum ice_ddp_state
+ice_download_pkg_without_sig_seg(struct ice_hw *hw, struct ice_seg *ice_seg)
+{
+	struct ice_buf_table *ice_buf_tbl;
+
+	ice_debug(hw, ICE_DBG_PKG, "Segment format version: %d.%d.%d.%d\n",
+		  ice_seg->hdr.seg_format_ver.major,
+		  ice_seg->hdr.seg_format_ver.minor,
+		  ice_seg->hdr.seg_format_ver.update,
+		  ice_seg->hdr.seg_format_ver.draft);
+
+	ice_debug(hw, ICE_DBG_PKG, "Seg: type 0x%X, size %d, name %s\n",
+		  le32_to_cpu(ice_seg->hdr.seg_type),
+		  le32_to_cpu(ice_seg->hdr.seg_size), ice_seg->hdr.seg_id);
+
+	ice_buf_tbl = ice_find_buf_table(ice_seg);
+
+	ice_debug(hw, ICE_DBG_PKG, "Seg buf count: %d\n",
+		  le32_to_cpu(ice_buf_tbl->buf_count));
+
+	return ice_dwnld_cfg_bufs(hw, ice_buf_tbl->buf_array,
+				  le32_to_cpu(ice_buf_tbl->buf_count));
+}
+
+/**
+ * ice_download_pkg
+ * @hw: pointer to the hardware structure
+ * @pkg_hdr: pointer to package header
+ * @ice_seg: pointer to the segment of the package to be downloaded
+ *
+ * Handles the download of a complete package.
+ */
+static enum ice_ddp_state
+ice_download_pkg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr,
+		 struct ice_seg *ice_seg)
+{
+	enum ice_ddp_state state;
+
+	if (hw->pkg_has_signing_seg)
+		state = ice_download_pkg_with_sig_seg(hw, pkg_hdr);
+	else
+		state = ice_download_pkg_without_sig_seg(hw, ice_seg);
+
 	ice_post_pkg_dwnld_vlan_mode_cfg(hw);
 
 	return state;
@@ -2083,7 +2180,7 @@ enum ice_ddp_state ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len)
 
 	/* initialize package hints and then download package */
 	ice_init_pkg_hints(hw, seg);
-	state = ice_download_pkg(hw, pkg);
+	state = ice_download_pkg(hw, pkg, seg);
 	if (state == ICE_DDP_PKG_ALREADY_LOADED) {
 		ice_debug(hw, ICE_DBG_INIT,
 			  "package previously loaded - no work.\n");
diff --git a/drivers/net/ethernet/intel/ice/ice_debugfs.c b/drivers/net/ethernet/intel/ice/ice_debugfs.c
new file mode 100644
index 000000000000..c2bfba6b9ead
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_debugfs.c
@@ -0,0 +1,667 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022, Intel Corporation. */
+
+#include <linux/fs.h>
+#include <linux/debugfs.h>
+#include <linux/random.h>
+#include <linux/vmalloc.h>
+#include "ice.h"
+
+static struct dentry *ice_debugfs_root;
+
+/* create a define that has an extra module that doesn't really exist. this
+ * is so we can add a module 'all' to easily enable/disable all the modules
+ */
+#define ICE_NR_FW_LOG_MODULES (ICE_AQC_FW_LOG_ID_MAX + 1)
+
+/* the ordering in this array is important. it matches the ordering of the
+ * values in the FW so the index is the same value as in ice_aqc_fw_logging_mod
+ */
+static const char * const ice_fwlog_module_string[] = {
+	"general",
+	"ctrl",
+	"link",
+	"link_topo",
+	"dnl",
+	"i2c",
+	"sdp",
+	"mdio",
+	"adminq",
+	"hdma",
+	"lldp",
+	"dcbx",
+	"dcb",
+	"xlr",
+	"nvm",
+	"auth",
+	"vpd",
+	"iosf",
+	"parser",
+	"sw",
+	"scheduler",
+	"txq",
+	"rsvd",
+	"post",
+	"watchdog",
+	"task_dispatch",
+	"mng",
+	"synce",
+	"health",
+	"tsdrv",
+	"pfreg",
+	"mdlver",
+	"all",
+};
+
+/* the ordering in this array is important. it matches the ordering of the
+ * values in the FW so the index is the same value as in ice_fwlog_level
+ */
+static const char * const ice_fwlog_level_string[] = {
+	"none",
+	"error",
+	"warning",
+	"normal",
+	"verbose",
+};
+
+/* the order in this array is important. it matches the ordering of the
+ * values in the FW so the index is the same value as in ice_fwlog_level
+ */
+static const char * const ice_fwlog_log_size[] = {
+	"128K",
+	"256K",
+	"512K",
+	"1M",
+	"2M",
+};
+
+/**
+ * ice_fwlog_print_module_cfg - print current FW logging module configuration
+ * @hw: pointer to the HW structure
+ * @module: module to print
+ * @s: the seq file to put data into
+ */
+static void
+ice_fwlog_print_module_cfg(struct ice_hw *hw, int module, struct seq_file *s)
+{
+	struct ice_fwlog_cfg *cfg = &hw->fwlog_cfg;
+	struct ice_fwlog_module_entry *entry;
+
+	if (module != ICE_AQC_FW_LOG_ID_MAX) {
+		entry =	&cfg->module_entries[module];
+
+		seq_printf(s, "\tModule: %s, Log Level: %s\n",
+			   ice_fwlog_module_string[entry->module_id],
+			   ice_fwlog_level_string[entry->log_level]);
+	} else {
+		int i;
+
+		for (i = 0; i < ICE_AQC_FW_LOG_ID_MAX; i++) {
+			entry =	&cfg->module_entries[i];
+
+			seq_printf(s, "\tModule: %s, Log Level: %s\n",
+				   ice_fwlog_module_string[entry->module_id],
+				   ice_fwlog_level_string[entry->log_level]);
+		}
+	}
+}
+
+static int ice_find_module_by_dentry(struct ice_pf *pf, struct dentry *d)
+{
+	int i, module;
+
+	module = -1;
+	/* find the module based on the dentry */
+	for (i = 0; i < ICE_NR_FW_LOG_MODULES; i++) {
+		if (d == pf->ice_debugfs_pf_fwlog_modules[i]) {
+			module = i;
+			break;
+		}
+	}
+
+	return module;
+}
+
+/**
+ * ice_debugfs_module_show - read from 'module' file
+ * @s: the opened file
+ * @v: pointer to the offset
+ */
+static int ice_debugfs_module_show(struct seq_file *s, void *v)
+{
+	const struct file *filp = s->file;
+	struct dentry *dentry;
+	struct ice_pf *pf;
+	int module;
+
+	dentry = file_dentry(filp);
+	pf = s->private;
+
+	module = ice_find_module_by_dentry(pf, dentry);
+	if (module < 0) {
+		dev_info(ice_pf_to_dev(pf), "unknown module\n");
+		return -EINVAL;
+	}
+
+	ice_fwlog_print_module_cfg(&pf->hw, module, s);
+
+	return 0;
+}
+
+static int ice_debugfs_module_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, ice_debugfs_module_show, inode->i_private);
+}
+
+/**
+ * ice_debugfs_module_write - write into 'module' file
+ * @filp: the opened file
+ * @buf: where to find the user's data
+ * @count: the length of the user's data
+ * @ppos: file position offset
+ */
+static ssize_t
+ice_debugfs_module_write(struct file *filp, const char __user *buf,
+			 size_t count, loff_t *ppos)
+{
+	struct ice_pf *pf = file_inode(filp)->i_private;
+	struct dentry *dentry = file_dentry(filp);
+	struct device *dev = ice_pf_to_dev(pf);
+	char user_val[16], *cmd_buf;
+	int module, log_level, cnt;
+
+	/* don't allow partial writes or invalid input */
+	if (*ppos != 0 || count > 8)
+		return -EINVAL;
+
+	cmd_buf = memdup_user(buf, count);
+	if (IS_ERR(cmd_buf))
+		return PTR_ERR(cmd_buf);
+
+	module = ice_find_module_by_dentry(pf, dentry);
+	if (module < 0) {
+		dev_info(dev, "unknown module\n");
+		return -EINVAL;
+	}
+
+	cnt = sscanf(cmd_buf, "%s", user_val);
+	if (cnt != 1)
+		return -EINVAL;
+
+	log_level = sysfs_match_string(ice_fwlog_level_string, user_val);
+	if (log_level < 0) {
+		dev_info(dev, "unknown log level '%s'\n", user_val);
+		return -EINVAL;
+	}
+
+	if (module != ICE_AQC_FW_LOG_ID_MAX) {
+		ice_pf_fwlog_update_module(pf, log_level, module);
+	} else {
+		/* the module 'all' is a shortcut so that we can set
+		 * all of the modules to the same level quickly
+		 */
+		int i;
+
+		for (i = 0; i < ICE_AQC_FW_LOG_ID_MAX; i++)
+			ice_pf_fwlog_update_module(pf, log_level, i);
+	}
+
+	return count;
+}
+
+static const struct file_operations ice_debugfs_module_fops = {
+	.owner = THIS_MODULE,
+	.open  = ice_debugfs_module_open,
+	.read = seq_read,
+	.release = single_release,
+	.write = ice_debugfs_module_write,
+};
+
+/**
+ * ice_debugfs_nr_messages_read - read from 'nr_messages' file
+ * @filp: the opened file
+ * @buffer: where to write the data for the user to read
+ * @count: the size of the user's buffer
+ * @ppos: file position offset
+ */
+static ssize_t ice_debugfs_nr_messages_read(struct file *filp,
+					    char __user *buffer, size_t count,
+					    loff_t *ppos)
+{
+	struct ice_pf *pf = filp->private_data;
+	struct ice_hw *hw = &pf->hw;
+	char buff[32] = {};
+
+	snprintf(buff, sizeof(buff), "%d\n",
+		 hw->fwlog_cfg.log_resolution);
+
+	return simple_read_from_buffer(buffer, count, ppos, buff, strlen(buff));
+}
+
+/**
+ * ice_debugfs_nr_messages_write - write into 'nr_messages' file
+ * @filp: the opened file
+ * @buf: where to find the user's data
+ * @count: the length of the user's data
+ * @ppos: file position offset
+ */
+static ssize_t
+ice_debugfs_nr_messages_write(struct file *filp, const char __user *buf,
+			      size_t count, loff_t *ppos)
+{
+	struct ice_pf *pf = filp->private_data;
+	struct device *dev = ice_pf_to_dev(pf);
+	struct ice_hw *hw = &pf->hw;
+	char user_val[8], *cmd_buf;
+	s16 nr_messages;
+	ssize_t ret;
+
+	/* don't allow partial writes or invalid input */
+	if (*ppos != 0 || count > 4)
+		return -EINVAL;
+
+	cmd_buf = memdup_user(buf, count);
+	if (IS_ERR(cmd_buf))
+		return PTR_ERR(cmd_buf);
+
+	ret = sscanf(cmd_buf, "%s", user_val);
+	if (ret != 1)
+		return -EINVAL;
+
+	ret = kstrtos16(user_val, 0, &nr_messages);
+	if (ret)
+		return ret;
+
+	if (nr_messages < ICE_AQC_FW_LOG_MIN_RESOLUTION ||
+	    nr_messages > ICE_AQC_FW_LOG_MAX_RESOLUTION) {
+		dev_err(dev, "Invalid FW log number of messages %d, value must be between %d - %d\n",
+			nr_messages, ICE_AQC_FW_LOG_MIN_RESOLUTION,
+			ICE_AQC_FW_LOG_MAX_RESOLUTION);
+		return -EINVAL;
+	}
+
+	hw->fwlog_cfg.log_resolution = nr_messages;
+
+	return count;
+}
+
+static const struct file_operations ice_debugfs_nr_messages_fops = {
+	.owner = THIS_MODULE,
+	.open  = simple_open,
+	.read = ice_debugfs_nr_messages_read,
+	.write = ice_debugfs_nr_messages_write,
+};
+
+/**
+ * ice_debugfs_enable_read - read from 'enable' file
+ * @filp: the opened file
+ * @buffer: where to write the data for the user to read
+ * @count: the size of the user's buffer
+ * @ppos: file position offset
+ */
+static ssize_t ice_debugfs_enable_read(struct file *filp,
+				       char __user *buffer, size_t count,
+				       loff_t *ppos)
+{
+	struct ice_pf *pf = filp->private_data;
+	struct ice_hw *hw = &pf->hw;
+	char buff[32] = {};
+
+	snprintf(buff, sizeof(buff), "%u\n",
+		 (u16)(hw->fwlog_cfg.options &
+		 ICE_FWLOG_OPTION_IS_REGISTERED) >> 3);
+
+	return simple_read_from_buffer(buffer, count, ppos, buff, strlen(buff));
+}
+
+/**
+ * ice_debugfs_enable_write - write into 'enable' file
+ * @filp: the opened file
+ * @buf: where to find the user's data
+ * @count: the length of the user's data
+ * @ppos: file position offset
+ */
+static ssize_t
+ice_debugfs_enable_write(struct file *filp, const char __user *buf,
+			 size_t count, loff_t *ppos)
+{
+	struct ice_pf *pf = filp->private_data;
+	struct ice_hw *hw = &pf->hw;
+	char user_val[8], *cmd_buf;
+	bool enable;
+	ssize_t ret;
+
+	/* don't allow partial writes or invalid input */
+	if (*ppos != 0 || count > 2)
+		return -EINVAL;
+
+	cmd_buf = memdup_user(buf, count);
+	if (IS_ERR(cmd_buf))
+		return PTR_ERR(cmd_buf);
+
+	ret = sscanf(cmd_buf, "%s", user_val);
+	if (ret != 1)
+		return -EINVAL;
+
+	ret = kstrtobool(user_val, &enable);
+	if (ret)
+		goto enable_write_error;
+
+	if (enable)
+		hw->fwlog_cfg.options |= ICE_FWLOG_OPTION_ARQ_ENA;
+	else
+		hw->fwlog_cfg.options &= ~ICE_FWLOG_OPTION_ARQ_ENA;
+
+	ret = ice_fwlog_set(hw, &hw->fwlog_cfg);
+	if (ret)
+		goto enable_write_error;
+
+	if (enable)
+		ret = ice_fwlog_register(hw);
+	else
+		ret = ice_fwlog_unregister(hw);
+
+	if (ret)
+		goto enable_write_error;
+
+	/* if we get here, nothing went wrong; return count since we didn't
+	 * really write anything
+	 */
+	ret = (ssize_t)count;
+
+enable_write_error:
+	/* This function always consumes all of the written input, or produces
+	 * an error. Check and enforce this. Otherwise, the write operation
+	 * won't complete properly.
+	 */
+	if (WARN_ON(ret != (ssize_t)count && ret >= 0))
+		ret = -EIO;
+
+	return ret;
+}
+
+static const struct file_operations ice_debugfs_enable_fops = {
+	.owner = THIS_MODULE,
+	.open  = simple_open,
+	.read = ice_debugfs_enable_read,
+	.write = ice_debugfs_enable_write,
+};
+
+/**
+ * ice_debugfs_log_size_read - read from 'log_size' file
+ * @filp: the opened file
+ * @buffer: where to write the data for the user to read
+ * @count: the size of the user's buffer
+ * @ppos: file position offset
+ */
+static ssize_t ice_debugfs_log_size_read(struct file *filp,
+					 char __user *buffer, size_t count,
+					 loff_t *ppos)
+{
+	struct ice_pf *pf = filp->private_data;
+	struct ice_hw *hw = &pf->hw;
+	char buff[32] = {};
+	int index;
+
+	index = hw->fwlog_ring.index;
+	snprintf(buff, sizeof(buff), "%s\n", ice_fwlog_log_size[index]);
+
+	return simple_read_from_buffer(buffer, count, ppos, buff, strlen(buff));
+}
+
+/**
+ * ice_debugfs_log_size_write - write into 'log_size' file
+ * @filp: the opened file
+ * @buf: where to find the user's data
+ * @count: the length of the user's data
+ * @ppos: file position offset
+ */
+static ssize_t
+ice_debugfs_log_size_write(struct file *filp, const char __user *buf,
+			   size_t count, loff_t *ppos)
+{
+	struct ice_pf *pf = filp->private_data;
+	struct device *dev = ice_pf_to_dev(pf);
+	struct ice_hw *hw = &pf->hw;
+	char user_val[8], *cmd_buf;
+	ssize_t ret;
+	int index;
+
+	/* don't allow partial writes or invalid input */
+	if (*ppos != 0 || count > 5)
+		return -EINVAL;
+
+	cmd_buf = memdup_user(buf, count);
+	if (IS_ERR(cmd_buf))
+		return PTR_ERR(cmd_buf);
+
+	ret = sscanf(cmd_buf, "%s", user_val);
+	if (ret != 1)
+		return -EINVAL;
+
+	index = sysfs_match_string(ice_fwlog_log_size, user_val);
+	if (index < 0) {
+		dev_info(dev, "Invalid log size '%s'. The value must be one of 128K, 256K, 512K, 1M, 2M\n",
+			 user_val);
+		ret = -EINVAL;
+		goto log_size_write_error;
+	} else if (hw->fwlog_cfg.options & ICE_FWLOG_OPTION_IS_REGISTERED) {
+		dev_info(dev, "FW logging is currently running. Please disable FW logging to change log_size\n");
+		ret = -EINVAL;
+		goto log_size_write_error;
+	}
+
+	/* free all the buffers and the tracking info and resize */
+	ice_fwlog_realloc_rings(hw, index);
+
+	/* if we get here, nothing went wrong; return count since we didn't
+	 * really write anything
+	 */
+	ret = (ssize_t)count;
+
+log_size_write_error:
+	/* This function always consumes all of the written input, or produces
+	 * an error. Check and enforce this. Otherwise, the write operation
+	 * won't complete properly.
+	 */
+	if (WARN_ON(ret != (ssize_t)count && ret >= 0))
+		ret = -EIO;
+
+	return ret;
+}
+
+static const struct file_operations ice_debugfs_log_size_fops = {
+	.owner = THIS_MODULE,
+	.open  = simple_open,
+	.read = ice_debugfs_log_size_read,
+	.write = ice_debugfs_log_size_write,
+};
+
+/**
+ * ice_debugfs_data_read - read from 'data' file
+ * @filp: the opened file
+ * @buffer: where to write the data for the user to read
+ * @count: the size of the user's buffer
+ * @ppos: file position offset
+ */
+static ssize_t ice_debugfs_data_read(struct file *filp, char __user *buffer,
+				     size_t count, loff_t *ppos)
+{
+	struct ice_pf *pf = filp->private_data;
+	struct ice_hw *hw = &pf->hw;
+	int data_copied = 0;
+	bool done = false;
+
+	if (ice_fwlog_ring_empty(&hw->fwlog_ring))
+		return 0;
+
+	while (!ice_fwlog_ring_empty(&hw->fwlog_ring) && !done) {
+		struct ice_fwlog_data *log;
+		u16 cur_buf_len;
+
+		log = &hw->fwlog_ring.rings[hw->fwlog_ring.head];
+		cur_buf_len = log->data_size;
+		if (cur_buf_len >= count) {
+			done = true;
+			continue;
+		}
+
+		if (copy_to_user(buffer, log->data, cur_buf_len)) {
+			/* if there is an error then bail and return whatever
+			 * the driver has copied so far
+			 */
+			done = true;
+			continue;
+		}
+
+		data_copied += cur_buf_len;
+		buffer += cur_buf_len;
+		count -= cur_buf_len;
+		*ppos += cur_buf_len;
+		ice_fwlog_ring_increment(&hw->fwlog_ring.head,
+					 hw->fwlog_ring.size);
+	}
+
+	return data_copied;
+}
+
+/**
+ * ice_debugfs_data_write - write into 'data' file
+ * @filp: the opened file
+ * @buf: where to find the user's data
+ * @count: the length of the user's data
+ * @ppos: file position offset
+ */
+static ssize_t
+ice_debugfs_data_write(struct file *filp, const char __user *buf, size_t count,
+		       loff_t *ppos)
+{
+	struct ice_pf *pf = filp->private_data;
+	struct device *dev = ice_pf_to_dev(pf);
+	struct ice_hw *hw = &pf->hw;
+	ssize_t ret;
+
+	/* don't allow partial writes */
+	if (*ppos != 0)
+		return 0;
+
+	/* any value is allowed to clear the buffer so no need to even look at
+	 * what the value is
+	 */
+	if (!(hw->fwlog_cfg.options & ICE_FWLOG_OPTION_IS_REGISTERED)) {
+		hw->fwlog_ring.head = 0;
+		hw->fwlog_ring.tail = 0;
+	} else {
+		dev_info(dev, "Can't clear FW log data while FW log running\n");
+		ret = -EINVAL;
+		goto nr_buffs_write_error;
+	}
+
+	/* if we get here, nothing went wrong; return count since we didn't
+	 * really write anything
+	 */
+	ret = (ssize_t)count;
+
+nr_buffs_write_error:
+	/* This function always consumes all of the written input, or produces
+	 * an error. Check and enforce this. Otherwise, the write operation
+	 * won't complete properly.
+	 */
+	if (WARN_ON(ret != (ssize_t)count && ret >= 0))
+		ret = -EIO;
+
+	return ret;
+}
+
+static const struct file_operations ice_debugfs_data_fops = {
+	.owner = THIS_MODULE,
+	.open  = simple_open,
+	.read = ice_debugfs_data_read,
+	.write = ice_debugfs_data_write,
+};
+
+/**
+ * ice_debugfs_fwlog_init - setup the debugfs directory
+ * @pf: the ice that is starting up
+ */
+void ice_debugfs_fwlog_init(struct ice_pf *pf)
+{
+	const char *name = pci_name(pf->pdev);
+	struct dentry *fw_modules_dir;
+	struct dentry **fw_modules;
+	int i;
+
+	/* only support fw log commands on PF 0 */
+	if (pf->hw.bus.func)
+		return;
+
+	/* allocate space for this first because if it fails then we don't
+	 * need to unwind
+	 */
+	fw_modules = kcalloc(ICE_NR_FW_LOG_MODULES, sizeof(*fw_modules),
+			     GFP_KERNEL);
+	if (!fw_modules)
+		return;
+
+	pf->ice_debugfs_pf = debugfs_create_dir(name, ice_debugfs_root);
+	if (IS_ERR(pf->ice_debugfs_pf))
+		goto err_create_module_files;
+
+	pf->ice_debugfs_pf_fwlog = debugfs_create_dir("fwlog",
+						      pf->ice_debugfs_pf);
+	if (IS_ERR(pf->ice_debugfs_pf))
+		goto err_create_module_files;
+
+	fw_modules_dir = debugfs_create_dir("modules",
+					    pf->ice_debugfs_pf_fwlog);
+	if (IS_ERR(fw_modules_dir))
+		goto err_create_module_files;
+
+	for (i = 0; i < ICE_NR_FW_LOG_MODULES; i++) {
+		fw_modules[i] = debugfs_create_file(ice_fwlog_module_string[i],
+						    0600, fw_modules_dir, pf,
+						    &ice_debugfs_module_fops);
+		if (IS_ERR(fw_modules[i]))
+			goto err_create_module_files;
+	}
+
+	debugfs_create_file("nr_messages", 0600,
+			    pf->ice_debugfs_pf_fwlog, pf,
+			    &ice_debugfs_nr_messages_fops);
+
+	pf->ice_debugfs_pf_fwlog_modules = fw_modules;
+
+	debugfs_create_file("enable", 0600, pf->ice_debugfs_pf_fwlog,
+			    pf, &ice_debugfs_enable_fops);
+
+	debugfs_create_file("log_size", 0600, pf->ice_debugfs_pf_fwlog,
+			    pf, &ice_debugfs_log_size_fops);
+
+	debugfs_create_file("data", 0600, pf->ice_debugfs_pf_fwlog,
+			    pf, &ice_debugfs_data_fops);
+
+	return;
+
+err_create_module_files:
+	debugfs_remove_recursive(pf->ice_debugfs_pf_fwlog);
+	kfree(fw_modules);
+}
+
+/**
+ * ice_debugfs_init - create root directory for debugfs entries
+ */
+void ice_debugfs_init(void)
+{
+	ice_debugfs_root = debugfs_create_dir(KBUILD_MODNAME, NULL);
+	if (IS_ERR(ice_debugfs_root))
+		pr_info("init of debugfs failed\n");
+}
+
+/**
+ * ice_debugfs_exit - remove debugfs entries
+ */
+void ice_debugfs_exit(void)
+{
+	debugfs_remove_recursive(ice_debugfs_root);
+	ice_debugfs_root = NULL;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c
index 80dc5445b50d..65be56f2af9e 100644
--- a/drivers/net/ethernet/intel/ice/ice_devlink.c
+++ b/drivers/net/ethernet/intel/ice/ice_devlink.c
@@ -193,6 +193,24 @@ ice_info_pending_netlist_build(struct ice_pf __always_unused *pf,
 		snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", netlist->hash);
 }
 
+static void ice_info_cgu_fw_build(struct ice_pf *pf, struct ice_info_ctx *ctx)
+{
+	u32 id, cfg_ver, fw_ver;
+
+	if (!ice_is_feature_supported(pf, ICE_F_CGU))
+		return;
+	if (ice_aq_get_cgu_info(&pf->hw, &id, &cfg_ver, &fw_ver))
+		return;
+	snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u.%u", id, cfg_ver, fw_ver);
+}
+
+static void ice_info_cgu_id(struct ice_pf *pf, struct ice_info_ctx *ctx)
+{
+	if (!ice_is_feature_supported(pf, ICE_F_CGU))
+		return;
+	snprintf(ctx->buf, sizeof(ctx->buf), "%u", pf->hw.cgu_part_number);
+}
+
 #define fixed(key, getter) { ICE_VERSION_FIXED, key, getter, NULL }
 #define running(key, getter) { ICE_VERSION_RUNNING, key, getter, NULL }
 #define stored(key, getter, fallback) { ICE_VERSION_STORED, key, getter, fallback }
@@ -235,6 +253,8 @@ static const struct ice_devlink_version {
 	running("fw.app.bundle_id", ice_info_ddp_pkg_bundle_id),
 	combined("fw.netlist", ice_info_netlist_ver, ice_info_pending_netlist_ver),
 	combined("fw.netlist.build", ice_info_netlist_build, ice_info_pending_netlist_build),
+	fixed("cgu.id", ice_info_cgu_id),
+	running("fw.cgu", ice_info_cgu_fw_build),
 };
 
 /**
@@ -810,6 +830,10 @@ static void ice_traverse_tx_tree(struct devlink *devlink, struct ice_sched_node
 	struct ice_vf *vf;
 	int i;
 
+	if (node->rate_node)
+		/* already added, skip to the next */
+		goto traverse_children;
+
 	if (node->parent == tc_node) {
 		/* create root node */
 		rate_node = devl_rate_node_create(devlink, node, node->name, NULL);
@@ -831,6 +855,7 @@ static void ice_traverse_tx_tree(struct devlink *devlink, struct ice_sched_node
 	if (rate_node && !IS_ERR(rate_node))
 		node->rate_node = rate_node;
 
+traverse_children:
 	for (i = 0; i < node->num_children; i++)
 		ice_traverse_tx_tree(devlink, node->children[i], tc_node, pf);
 }
@@ -861,6 +886,30 @@ int ice_devlink_rate_init_tx_topology(struct devlink *devlink, struct ice_vsi *v
 	return 0;
 }
 
+static void ice_clear_rate_nodes(struct ice_sched_node *node)
+{
+	node->rate_node = NULL;
+
+	for (int i = 0; i < node->num_children; i++)
+		ice_clear_rate_nodes(node->children[i]);
+}
+
+/**
+ * ice_devlink_rate_clear_tx_topology - clear node->rate_node
+ * @vsi: main vsi struct
+ *
+ * Clear rate_node to cleanup creation of Tx topology.
+ *
+ */
+void ice_devlink_rate_clear_tx_topology(struct ice_vsi *vsi)
+{
+	struct ice_port_info *pi = vsi->port_info;
+
+	mutex_lock(&pi->sched_lock);
+	ice_clear_rate_nodes(pi->root->children[0]);
+	mutex_unlock(&pi->sched_lock);
+}
+
 /**
  * ice_set_object_tx_share - sets node scheduling parameter
  * @pi: devlink struct instance
diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.h b/drivers/net/ethernet/intel/ice/ice_devlink.h
index 6ec96779f52e..d291c0e2e17b 100644
--- a/drivers/net/ethernet/intel/ice/ice_devlink.h
+++ b/drivers/net/ethernet/intel/ice/ice_devlink.h
@@ -20,5 +20,6 @@ void ice_devlink_destroy_regions(struct ice_pf *pf);
 
 int ice_devlink_rate_init_tx_topology(struct devlink *devlink, struct ice_vsi *vsi);
 void ice_tear_down_devlink_rate_tree(struct ice_pf *pf);
+void ice_devlink_rate_clear_tx_topology(struct ice_vsi *vsi);
 
 #endif /* _ICE_DEVLINK_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c
index 835c419ccc74..b9c5eced6326 100644
--- a/drivers/net/ethernet/intel/ice/ice_dpll.c
+++ b/drivers/net/ethernet/intel/ice/ice_dpll.c
@@ -513,31 +513,6 @@ ice_dpll_lock_status_get(const struct dpll_device *dpll, void *dpll_priv,
 }
 
 /**
- * ice_dpll_mode_supported - check if dpll's working mode is supported
- * @dpll: registered dpll pointer
- * @dpll_priv: private data pointer passed on dpll registration
- * @mode: mode to be checked for support
- * @extack: error reporting
- *
- * Dpll subsystem callback. Provides information if working mode is supported
- * by dpll.
- *
- * Return:
- * * true - mode is supported
- * * false - mode is not supported
- */
-static bool ice_dpll_mode_supported(const struct dpll_device *dpll,
-				    void *dpll_priv,
-				    enum dpll_mode mode,
-				    struct netlink_ext_ack *extack)
-{
-	if (mode == DPLL_MODE_AUTOMATIC)
-		return true;
-
-	return false;
-}
-
-/**
  * ice_dpll_mode_get - get dpll's working mode
  * @dpll: registered dpll pointer
  * @dpll_priv: private data pointer passed on dpll registration
@@ -815,12 +790,6 @@ ice_dpll_input_prio_set(const struct dpll_pin *pin, void *pin_priv,
 	struct ice_pf *pf = d->pf;
 	int ret;
 
-	if (prio > ICE_DPLL_PRIO_MAX) {
-		NL_SET_ERR_MSG_FMT(extack, "prio out of supported range 0-%d",
-				   ICE_DPLL_PRIO_MAX);
-		return -EINVAL;
-	}
-
 	mutex_lock(&pf->dplls.lock);
 	ret = ice_dpll_hw_input_prio_set(pf, d, p, prio, extack);
 	mutex_unlock(&pf->dplls.lock);
@@ -1203,7 +1172,6 @@ static const struct dpll_pin_ops ice_dpll_output_ops = {
 
 static const struct dpll_device_ops ice_dpll_ops = {
 	.lock_status_get = ice_dpll_lock_status_get,
-	.mode_supported = ice_dpll_mode_supported,
 	.mode_get = ice_dpll_mode_get,
 };
 
@@ -1756,6 +1724,7 @@ ice_dpll_init_dpll(struct ice_pf *pf, struct ice_dpll *d, bool cgu,
 	}
 	d->pf = pf;
 	if (cgu) {
+		ice_dpll_update_state(pf, d, true);
 		ret = dpll_device_register(d->dpll, type, &ice_dpll_ops, d);
 		if (ret) {
 			dpll_device_put(d->dpll);
@@ -1796,8 +1765,6 @@ static int ice_dpll_init_worker(struct ice_pf *pf)
 	struct ice_dplls *d = &pf->dplls;
 	struct kthread_worker *kworker;
 
-	ice_dpll_update_state(pf, &d->eec, true);
-	ice_dpll_update_state(pf, &d->pps, true);
 	kthread_init_delayed_work(&d->work, ice_dpll_periodic_work);
 	kworker = kthread_create_worker(0, "ice-dplls-%s",
 					dev_name(ice_pf_to_dev(pf)));
@@ -1830,6 +1797,7 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf,
 	int num_pins, i, ret = -EINVAL;
 	struct ice_hw *hw = &pf->hw;
 	struct ice_dpll_pin *pins;
+	unsigned long caps;
 	u8 freq_supp_num;
 	bool input;
 
@@ -1849,6 +1817,7 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf,
 	}
 
 	for (i = 0; i < num_pins; i++) {
+		caps = 0;
 		pins[i].idx = i;
 		pins[i].prop.board_label = ice_cgu_get_pin_name(hw, i, input);
 		pins[i].prop.type = ice_cgu_get_pin_type(hw, i, input);
@@ -1861,8 +1830,8 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf,
 						      &dp->input_prio[i]);
 			if (ret)
 				return ret;
-			pins[i].prop.capabilities |=
-				DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE;
+			caps |= (DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE |
+				 DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE);
 			pins[i].prop.phase_range.min =
 				pf->dplls.input_phase_adj_max;
 			pins[i].prop.phase_range.max =
@@ -1872,9 +1841,11 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf,
 				pf->dplls.output_phase_adj_max;
 			pins[i].prop.phase_range.max =
 				-pf->dplls.output_phase_adj_max;
+			ret = ice_cgu_get_output_pin_state_caps(hw, i, &caps);
+			if (ret)
+				return ret;
 		}
-		pins[i].prop.capabilities |=
-			DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE;
+		pins[i].prop.capabilities = caps;
 		ret = ice_dpll_pin_state_update(pf, &pins[i], pin_type, NULL);
 		if (ret)
 			return ret;
diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.h b/drivers/net/ethernet/intel/ice/ice_dpll.h
index bb32b6d88373..93172e93995b 100644
--- a/drivers/net/ethernet/intel/ice/ice_dpll.h
+++ b/drivers/net/ethernet/intel/ice/ice_dpll.h
@@ -6,7 +6,6 @@
 
 #include "ice.h"
 
-#define ICE_DPLL_PRIO_MAX	0xF
 #define ICE_DPLL_RCLK_NUM_MAX	4
 
 /** ice_dpll_pin - store info about pins
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index a655d499abfa..9069725c71b4 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -11,17 +11,34 @@
 #include "ice_tc_lib.h"
 
 /**
- * ice_eswitch_add_vf_sp_rule - add adv rule with VF's VSI index
+ * ice_eswitch_del_sp_rules - delete adv rules added on PRs
+ * @pf: pointer to the PF struct
+ *
+ * Delete all advanced rules that were used to forward packets with the
+ * device's VSI index to the corresponding eswitch ctrl VSI queue.
+ */
+static void ice_eswitch_del_sp_rules(struct ice_pf *pf)
+{
+	struct ice_repr *repr;
+	unsigned long id;
+
+	xa_for_each(&pf->eswitch.reprs, id, repr) {
+		if (repr->sp_rule.rid)
+			ice_rem_adv_rule_by_id(&pf->hw, &repr->sp_rule);
+	}
+}
+
+/**
+ * ice_eswitch_add_sp_rule - add adv rule with device's VSI index
  * @pf: pointer to PF struct
- * @vf: pointer to VF struct
+ * @repr: pointer to the repr struct
  *
  * This function adds advanced rule that forwards packets with
- * VF's VSI index to the corresponding switchdev ctrl VSI queue.
+ * device's VSI index to the corresponding eswitch ctrl VSI queue.
  */
-static int
-ice_eswitch_add_vf_sp_rule(struct ice_pf *pf, struct ice_vf *vf)
+static int ice_eswitch_add_sp_rule(struct ice_pf *pf, struct ice_repr *repr)
 {
-	struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi;
+	struct ice_vsi *ctrl_vsi = pf->eswitch.control_vsi;
 	struct ice_adv_rule_info rule_info = { 0 };
 	struct ice_adv_lkup_elem *list;
 	struct ice_hw *hw = &pf->hw;
@@ -38,39 +55,42 @@ ice_eswitch_add_vf_sp_rule(struct ice_pf *pf, struct ice_vf *vf)
 	rule_info.sw_act.vsi_handle = ctrl_vsi->idx;
 	rule_info.sw_act.fltr_act = ICE_FWD_TO_Q;
 	rule_info.sw_act.fwd_id.q_id = hw->func_caps.common_cap.rxq_first_id +
-				       ctrl_vsi->rxq_map[vf->vf_id];
+				       ctrl_vsi->rxq_map[repr->q_id];
 	rule_info.flags_info.act |= ICE_SINGLE_ACT_LB_ENABLE;
 	rule_info.flags_info.act_valid = true;
 	rule_info.tun_type = ICE_SW_TUN_AND_NON_TUN;
-	rule_info.src_vsi = vf->lan_vsi_idx;
+	rule_info.src_vsi = repr->src_vsi->idx;
 
 	err = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info,
-			       &vf->repr->sp_rule);
+			       &repr->sp_rule);
 	if (err)
-		dev_err(ice_pf_to_dev(pf), "Unable to add VF slow-path rule in switchdev mode for VF %d",
-			vf->vf_id);
+		dev_err(ice_pf_to_dev(pf), "Unable to add slow-path rule for eswitch for PR %d",
+			repr->id);
 
 	kfree(list);
 	return err;
 }
 
-/**
- * ice_eswitch_del_vf_sp_rule - delete adv rule with VF's VSI index
- * @vf: pointer to the VF struct
- *
- * Delete the advanced rule that was used to forward packets with the VF's VSI
- * index to the corresponding switchdev ctrl VSI queue.
- */
-static void ice_eswitch_del_vf_sp_rule(struct ice_vf *vf)
+static int
+ice_eswitch_add_sp_rules(struct ice_pf *pf)
 {
-	if (!vf->repr)
-		return;
+	struct ice_repr *repr;
+	unsigned long id;
+	int err;
+
+	xa_for_each(&pf->eswitch.reprs, id, repr) {
+		err = ice_eswitch_add_sp_rule(pf, repr);
+		if (err) {
+			ice_eswitch_del_sp_rules(pf);
+			return err;
+		}
+	}
 
-	ice_rem_adv_rule_by_id(&vf->pf->hw, &vf->repr->sp_rule);
+	return 0;
 }
 
 /**
- * ice_eswitch_setup_env - configure switchdev HW filters
+ * ice_eswitch_setup_env - configure eswitch HW filters
  * @pf: pointer to PF struct
  *
  * This function adds HW filters configuration specific for switchdev
@@ -78,18 +98,18 @@ static void ice_eswitch_del_vf_sp_rule(struct ice_vf *vf)
  */
 static int ice_eswitch_setup_env(struct ice_pf *pf)
 {
-	struct ice_vsi *uplink_vsi = pf->switchdev.uplink_vsi;
-	struct net_device *uplink_netdev = uplink_vsi->netdev;
-	struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi;
+	struct ice_vsi *uplink_vsi = pf->eswitch.uplink_vsi;
+	struct ice_vsi *ctrl_vsi = pf->eswitch.control_vsi;
+	struct net_device *netdev = uplink_vsi->netdev;
 	struct ice_vsi_vlan_ops *vlan_ops;
 	bool rule_added = false;
 
 	ice_remove_vsi_fltr(&pf->hw, uplink_vsi->idx);
 
-	netif_addr_lock_bh(uplink_netdev);
-	__dev_uc_unsync(uplink_netdev, NULL);
-	__dev_mc_unsync(uplink_netdev, NULL);
-	netif_addr_unlock_bh(uplink_netdev);
+	netif_addr_lock_bh(netdev);
+	__dev_uc_unsync(netdev, NULL);
+	__dev_mc_unsync(netdev, NULL);
+	netif_addr_unlock_bh(netdev);
 
 	if (ice_vsi_add_vlan_zero(uplink_vsi))
 		goto err_def_rx;
@@ -132,19 +152,20 @@ err_def_rx:
 }
 
 /**
- * ice_eswitch_remap_rings_to_vectors - reconfigure rings of switchdev ctrl VSI
- * @pf: pointer to PF struct
+ * ice_eswitch_remap_rings_to_vectors - reconfigure rings of eswitch ctrl VSI
+ * @eswitch: pointer to eswitch struct
  *
- * In switchdev number of allocated Tx/Rx rings is equal.
+ * In eswitch number of allocated Tx/Rx rings is equal.
  *
  * This function fills q_vectors structures associated with representor and
  * move each ring pairs to port representor netdevs. Each port representor
  * will have dedicated 1 Tx/Rx ring pair, so number of rings pair is equal to
  * number of VFs.
  */
-static void ice_eswitch_remap_rings_to_vectors(struct ice_pf *pf)
+static void ice_eswitch_remap_rings_to_vectors(struct ice_eswitch *eswitch)
 {
-	struct ice_vsi *vsi = pf->switchdev.control_vsi;
+	struct ice_vsi *vsi = eswitch->control_vsi;
+	unsigned long repr_id = 0;
 	int q_id;
 
 	ice_for_each_txq(vsi, q_id) {
@@ -152,13 +173,14 @@ static void ice_eswitch_remap_rings_to_vectors(struct ice_pf *pf)
 		struct ice_tx_ring *tx_ring;
 		struct ice_rx_ring *rx_ring;
 		struct ice_repr *repr;
-		struct ice_vf *vf;
 
-		vf = ice_get_vf_by_id(pf, q_id);
-		if (WARN_ON(!vf))
-			continue;
+		repr = xa_find(&eswitch->reprs, &repr_id, U32_MAX,
+			       XA_PRESENT);
+		if (!repr)
+			break;
 
-		repr = vf->repr;
+		repr_id += 1;
+		repr->q_id = q_id;
 		q_vector = repr->q_vector;
 		tx_ring = vsi->tx_rings[q_id];
 		rx_ring = vsi->rx_rings[q_id];
@@ -181,136 +203,96 @@ static void ice_eswitch_remap_rings_to_vectors(struct ice_pf *pf)
 		rx_ring->q_vector = q_vector;
 		rx_ring->next = NULL;
 		rx_ring->netdev = repr->netdev;
-
-		ice_put_vf(vf);
 	}
 }
 
 /**
- * ice_eswitch_release_reprs - clear PR VSIs configuration
+ * ice_eswitch_release_repr - clear PR VSI configuration
  * @pf: poiner to PF struct
- * @ctrl_vsi: pointer to switchdev control VSI
+ * @repr: pointer to PR
  */
 static void
-ice_eswitch_release_reprs(struct ice_pf *pf, struct ice_vsi *ctrl_vsi)
+ice_eswitch_release_repr(struct ice_pf *pf, struct ice_repr *repr)
 {
-	struct ice_vf *vf;
-	unsigned int bkt;
+	struct ice_vsi *vsi = repr->src_vsi;
 
-	lockdep_assert_held(&pf->vfs.table_lock);
-
-	ice_for_each_vf(pf, bkt, vf) {
-		struct ice_vsi *vsi = vf->repr->src_vsi;
-
-		/* Skip VFs that aren't configured */
-		if (!vf->repr->dst)
-			continue;
+	/* Skip representors that aren't configured */
+	if (!repr->dst)
+		return;
 
-		ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof);
-		metadata_dst_free(vf->repr->dst);
-		vf->repr->dst = NULL;
-		ice_eswitch_del_vf_sp_rule(vf);
-		ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr,
-					       ICE_FWD_TO_VSI);
+	ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof);
+	metadata_dst_free(repr->dst);
+	repr->dst = NULL;
+	ice_fltr_add_mac_and_broadcast(vsi, repr->parent_mac,
+				       ICE_FWD_TO_VSI);
 
-		netif_napi_del(&vf->repr->q_vector->napi);
-	}
+	netif_napi_del(&repr->q_vector->napi);
 }
 
 /**
- * ice_eswitch_setup_reprs - configure port reprs to run in switchdev mode
+ * ice_eswitch_setup_repr - configure PR to run in switchdev mode
  * @pf: pointer to PF struct
+ * @repr: pointer to PR struct
  */
-static int ice_eswitch_setup_reprs(struct ice_pf *pf)
+static int ice_eswitch_setup_repr(struct ice_pf *pf, struct ice_repr *repr)
 {
-	struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi;
-	int max_vsi_num = 0;
-	struct ice_vf *vf;
-	unsigned int bkt;
-
-	lockdep_assert_held(&pf->vfs.table_lock);
-
-	ice_for_each_vf(pf, bkt, vf) {
-		struct ice_vsi *vsi = vf->repr->src_vsi;
-
-		ice_remove_vsi_fltr(&pf->hw, vsi->idx);
-		vf->repr->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX,
-						   GFP_KERNEL);
-		if (!vf->repr->dst) {
-			ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr,
-						       ICE_FWD_TO_VSI);
-			goto err;
-		}
+	struct ice_vsi *ctrl_vsi = pf->eswitch.control_vsi;
+	struct ice_vsi *vsi = repr->src_vsi;
+	struct metadata_dst *dst;
 
-		if (ice_eswitch_add_vf_sp_rule(pf, vf)) {
-			ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr,
-						       ICE_FWD_TO_VSI);
-			goto err;
-		}
+	ice_remove_vsi_fltr(&pf->hw, vsi->idx);
+	repr->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX,
+				       GFP_KERNEL);
+	if (!repr->dst)
+		goto err_add_mac_fltr;
 
-		if (ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof)) {
-			ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr,
-						       ICE_FWD_TO_VSI);
-			ice_eswitch_del_vf_sp_rule(vf);
-			metadata_dst_free(vf->repr->dst);
-			vf->repr->dst = NULL;
-			goto err;
-		}
+	if (ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof))
+		goto err_dst_free;
 
-		if (ice_vsi_add_vlan_zero(vsi)) {
-			ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr,
-						       ICE_FWD_TO_VSI);
-			ice_eswitch_del_vf_sp_rule(vf);
-			metadata_dst_free(vf->repr->dst);
-			vf->repr->dst = NULL;
-			ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof);
-			goto err;
-		}
-
-		if (max_vsi_num < vsi->vsi_num)
-			max_vsi_num = vsi->vsi_num;
+	if (ice_vsi_add_vlan_zero(vsi))
+		goto err_update_security;
 
-		netif_napi_add(vf->repr->netdev, &vf->repr->q_vector->napi,
-			       ice_napi_poll);
+	netif_napi_add(repr->netdev, &repr->q_vector->napi,
+		       ice_napi_poll);
 
-		netif_keep_dst(vf->repr->netdev);
-	}
+	netif_keep_dst(repr->netdev);
 
-	ice_for_each_vf(pf, bkt, vf) {
-		struct ice_repr *repr = vf->repr;
-		struct ice_vsi *vsi = repr->src_vsi;
-		struct metadata_dst *dst;
-
-		dst = repr->dst;
-		dst->u.port_info.port_id = vsi->vsi_num;
-		dst->u.port_info.lower_dev = repr->netdev;
-		ice_repr_set_traffic_vsi(repr, ctrl_vsi);
-	}
+	dst = repr->dst;
+	dst->u.port_info.port_id = vsi->vsi_num;
+	dst->u.port_info.lower_dev = repr->netdev;
+	ice_repr_set_traffic_vsi(repr, ctrl_vsi);
 
 	return 0;
 
-err:
-	ice_eswitch_release_reprs(pf, ctrl_vsi);
+err_update_security:
+	ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof);
+err_dst_free:
+	metadata_dst_free(repr->dst);
+	repr->dst = NULL;
+err_add_mac_fltr:
+	ice_fltr_add_mac_and_broadcast(vsi, repr->parent_mac, ICE_FWD_TO_VSI);
 
 	return -ENODEV;
 }
 
 /**
- * ice_eswitch_update_repr - reconfigure VF port representor
- * @vsi: VF VSI for which port representor is configured
+ * ice_eswitch_update_repr - reconfigure port representor
+ * @repr_id: representor ID
+ * @vsi: VSI for which port representor is configured
  */
-void ice_eswitch_update_repr(struct ice_vsi *vsi)
+void ice_eswitch_update_repr(unsigned long repr_id, struct ice_vsi *vsi)
 {
 	struct ice_pf *pf = vsi->back;
 	struct ice_repr *repr;
-	struct ice_vf *vf;
 	int ret;
 
 	if (!ice_is_switchdev_running(pf))
 		return;
 
-	vf = vsi->vf;
-	repr = vf->repr;
+	repr = xa_load(&pf->eswitch.reprs, repr_id);
+	if (!repr)
+		return;
+
 	repr->src_vsi = vsi;
 	repr->dst->u.port_info.port_id = vsi->vsi_num;
 
@@ -319,9 +301,10 @@ void ice_eswitch_update_repr(struct ice_vsi *vsi)
 
 	ret = ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof);
 	if (ret) {
-		ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, ICE_FWD_TO_VSI);
-		dev_err(ice_pf_to_dev(pf), "Failed to update VF %d port representor",
-			vsi->vf->vf_id);
+		ice_fltr_add_mac_and_broadcast(vsi, repr->parent_mac,
+					       ICE_FWD_TO_VSI);
+		dev_err(ice_pf_to_dev(pf), "Failed to update VSI of port representor %d",
+			repr->id);
 	}
 }
 
@@ -353,13 +336,13 @@ ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 	skb_dst_drop(skb);
 	dst_hold((struct dst_entry *)repr->dst);
 	skb_dst_set(skb, (struct dst_entry *)repr->dst);
-	skb->queue_mapping = repr->vf->vf_id;
+	skb->queue_mapping = repr->q_id;
 
 	return ice_start_xmit(skb, netdev);
 }
 
 /**
- * ice_eswitch_set_target_vsi - set switchdev context in Tx context descriptor
+ * ice_eswitch_set_target_vsi - set eswitch context in Tx context descriptor
  * @skb: pointer to send buffer
  * @off: pointer to offload struct
  */
@@ -375,14 +358,14 @@ ice_eswitch_set_target_vsi(struct sk_buff *skb,
 		off->cd_qw1 |= (cd_cmd | ICE_TX_DESC_DTYPE_CTX);
 	} else {
 		cd_cmd = ICE_TX_CTX_DESC_SWTCH_VSI << ICE_TXD_CTX_QW1_CMD_S;
-		dst_vsi = ((u64)dst->u.port_info.port_id <<
-			   ICE_TXD_CTX_QW1_VSI_S) & ICE_TXD_CTX_QW1_VSI_M;
+		dst_vsi = FIELD_PREP(ICE_TXD_CTX_QW1_VSI_M,
+				     dst->u.port_info.port_id);
 		off->cd_qw1 = cd_cmd | dst_vsi | ICE_TX_DESC_DTYPE_CTX;
 	}
 }
 
 /**
- * ice_eswitch_release_env - clear switchdev HW filters
+ * ice_eswitch_release_env - clear eswitch HW filters
  * @pf: pointer to PF struct
  *
  * This function removes HW filters configuration specific for switchdev
@@ -390,8 +373,8 @@ ice_eswitch_set_target_vsi(struct sk_buff *skb,
  */
 static void ice_eswitch_release_env(struct ice_pf *pf)
 {
-	struct ice_vsi *uplink_vsi = pf->switchdev.uplink_vsi;
-	struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi;
+	struct ice_vsi *uplink_vsi = pf->eswitch.uplink_vsi;
+	struct ice_vsi *ctrl_vsi = pf->eswitch.control_vsi;
 	struct ice_vsi_vlan_ops *vlan_ops;
 
 	vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi);
@@ -407,7 +390,7 @@ static void ice_eswitch_release_env(struct ice_pf *pf)
 }
 
 /**
- * ice_eswitch_vsi_setup - configure switchdev control VSI
+ * ice_eswitch_vsi_setup - configure eswitch control VSI
  * @pf: pointer to PF structure
  * @pi: pointer to port_info structure
  */
@@ -424,48 +407,29 @@ ice_eswitch_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
 }
 
 /**
- * ice_eswitch_napi_del - remove NAPI handle for all port representors
- * @pf: pointer to PF structure
- */
-static void ice_eswitch_napi_del(struct ice_pf *pf)
-{
-	struct ice_vf *vf;
-	unsigned int bkt;
-
-	lockdep_assert_held(&pf->vfs.table_lock);
-
-	ice_for_each_vf(pf, bkt, vf)
-		netif_napi_del(&vf->repr->q_vector->napi);
-}
-
-/**
  * ice_eswitch_napi_enable - enable NAPI for all port representors
- * @pf: pointer to PF structure
+ * @reprs: xarray of reprs
  */
-static void ice_eswitch_napi_enable(struct ice_pf *pf)
+static void ice_eswitch_napi_enable(struct xarray *reprs)
 {
-	struct ice_vf *vf;
-	unsigned int bkt;
-
-	lockdep_assert_held(&pf->vfs.table_lock);
+	struct ice_repr *repr;
+	unsigned long id;
 
-	ice_for_each_vf(pf, bkt, vf)
-		napi_enable(&vf->repr->q_vector->napi);
+	xa_for_each(reprs, id, repr)
+		napi_enable(&repr->q_vector->napi);
 }
 
 /**
  * ice_eswitch_napi_disable - disable NAPI for all port representors
- * @pf: pointer to PF structure
+ * @reprs: xarray of reprs
  */
-static void ice_eswitch_napi_disable(struct ice_pf *pf)
+static void ice_eswitch_napi_disable(struct xarray *reprs)
 {
-	struct ice_vf *vf;
-	unsigned int bkt;
-
-	lockdep_assert_held(&pf->vfs.table_lock);
+	struct ice_repr *repr;
+	unsigned long id;
 
-	ice_for_each_vf(pf, bkt, vf)
-		napi_disable(&vf->repr->q_vector->napi);
+	xa_for_each(reprs, id, repr)
+		napi_disable(&repr->q_vector->napi);
 }
 
 /**
@@ -486,39 +450,26 @@ static int ice_eswitch_enable_switchdev(struct ice_pf *pf)
 		return -EINVAL;
 	}
 
-	pf->switchdev.control_vsi = ice_eswitch_vsi_setup(pf, pf->hw.port_info);
-	if (!pf->switchdev.control_vsi)
+	pf->eswitch.control_vsi = ice_eswitch_vsi_setup(pf, pf->hw.port_info);
+	if (!pf->eswitch.control_vsi)
 		return -ENODEV;
 
-	ctrl_vsi = pf->switchdev.control_vsi;
-	pf->switchdev.uplink_vsi = uplink_vsi;
+	ctrl_vsi = pf->eswitch.control_vsi;
+	/* cp VSI is createad with 1 queue as default */
+	pf->eswitch.qs.value = 1;
+	pf->eswitch.uplink_vsi = uplink_vsi;
 
 	if (ice_eswitch_setup_env(pf))
 		goto err_vsi;
 
-	if (ice_repr_add_for_all_vfs(pf))
-		goto err_repr_add;
-
-	if (ice_eswitch_setup_reprs(pf))
-		goto err_setup_reprs;
-
-	ice_eswitch_remap_rings_to_vectors(pf);
-
-	if (ice_vsi_open(ctrl_vsi))
-		goto err_setup_reprs;
-
 	if (ice_eswitch_br_offloads_init(pf))
 		goto err_br_offloads;
 
-	ice_eswitch_napi_enable(pf);
+	pf->eswitch.is_running = true;
 
 	return 0;
 
 err_br_offloads:
-	ice_vsi_close(ctrl_vsi);
-err_setup_reprs:
-	ice_repr_rem_from_all_vfs(pf);
-err_repr_add:
 	ice_eswitch_release_env(pf);
 err_vsi:
 	ice_vsi_release(ctrl_vsi);
@@ -526,19 +477,19 @@ err_vsi:
 }
 
 /**
- * ice_eswitch_disable_switchdev - disable switchdev resources
+ * ice_eswitch_disable_switchdev - disable eswitch resources
  * @pf: pointer to PF structure
  */
 static void ice_eswitch_disable_switchdev(struct ice_pf *pf)
 {
-	struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi;
+	struct ice_vsi *ctrl_vsi = pf->eswitch.control_vsi;
 
-	ice_eswitch_napi_disable(pf);
 	ice_eswitch_br_offloads_deinit(pf);
 	ice_eswitch_release_env(pf);
-	ice_eswitch_release_reprs(pf, ctrl_vsi);
 	ice_vsi_release(ctrl_vsi);
-	ice_repr_rem_from_all_vfs(pf);
+
+	pf->eswitch.is_running = false;
+	pf->eswitch.qs.is_reaching = false;
 }
 
 /**
@@ -566,6 +517,7 @@ ice_eswitch_mode_set(struct devlink *devlink, u16 mode,
 	case DEVLINK_ESWITCH_MODE_LEGACY:
 		dev_info(ice_pf_to_dev(pf), "PF %d changed eswitch mode to legacy",
 			 pf->hw.pf_id);
+		xa_destroy(&pf->eswitch.reprs);
 		NL_SET_ERR_MSG_MOD(extack, "Changed eswitch mode to legacy");
 		break;
 	case DEVLINK_ESWITCH_MODE_SWITCHDEV:
@@ -578,6 +530,7 @@ ice_eswitch_mode_set(struct devlink *devlink, u16 mode,
 
 		dev_info(ice_pf_to_dev(pf), "PF %d changed eswitch mode to switchdev",
 			 pf->hw.pf_id);
+		xa_init_flags(&pf->eswitch.reprs, XA_FLAGS_ALLOC);
 		NL_SET_ERR_MSG_MOD(extack, "Changed eswitch mode to switchdev");
 		break;
 	}
@@ -616,74 +569,168 @@ bool ice_is_eswitch_mode_switchdev(struct ice_pf *pf)
 }
 
 /**
- * ice_eswitch_release - cleanup eswitch
+ * ice_eswitch_start_all_tx_queues - start Tx queues of all port representors
  * @pf: pointer to PF structure
  */
-void ice_eswitch_release(struct ice_pf *pf)
+static void ice_eswitch_start_all_tx_queues(struct ice_pf *pf)
 {
-	if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_LEGACY)
+	struct ice_repr *repr;
+	unsigned long id;
+
+	if (test_bit(ICE_DOWN, pf->state))
 		return;
 
-	ice_eswitch_disable_switchdev(pf);
-	pf->switchdev.is_running = false;
+	xa_for_each(&pf->eswitch.reprs, id, repr)
+		ice_repr_start_tx_queues(repr);
 }
 
 /**
- * ice_eswitch_configure - configure eswitch
+ * ice_eswitch_stop_all_tx_queues - stop Tx queues of all port representors
  * @pf: pointer to PF structure
  */
-int ice_eswitch_configure(struct ice_pf *pf)
+void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf)
 {
-	int status;
-
-	if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_LEGACY || pf->switchdev.is_running)
-		return 0;
+	struct ice_repr *repr;
+	unsigned long id;
 
-	status = ice_eswitch_enable_switchdev(pf);
-	if (status)
-		return status;
+	if (test_bit(ICE_DOWN, pf->state))
+		return;
 
-	pf->switchdev.is_running = true;
-	return 0;
+	xa_for_each(&pf->eswitch.reprs, id, repr)
+		ice_repr_stop_tx_queues(repr);
 }
 
-/**
- * ice_eswitch_start_all_tx_queues - start Tx queues of all port representors
- * @pf: pointer to PF structure
- */
-static void ice_eswitch_start_all_tx_queues(struct ice_pf *pf)
+static void ice_eswitch_stop_reprs(struct ice_pf *pf)
 {
-	struct ice_vf *vf;
-	unsigned int bkt;
+	ice_eswitch_del_sp_rules(pf);
+	ice_eswitch_stop_all_tx_queues(pf);
+	ice_eswitch_napi_disable(&pf->eswitch.reprs);
+}
 
-	lockdep_assert_held(&pf->vfs.table_lock);
+static void ice_eswitch_start_reprs(struct ice_pf *pf)
+{
+	ice_eswitch_napi_enable(&pf->eswitch.reprs);
+	ice_eswitch_start_all_tx_queues(pf);
+	ice_eswitch_add_sp_rules(pf);
+}
 
-	if (test_bit(ICE_DOWN, pf->state))
-		return;
+static void
+ice_eswitch_cp_change_queues(struct ice_eswitch *eswitch, int change)
+{
+	struct ice_vsi *cp = eswitch->control_vsi;
+	int queues = 0;
+
+	if (eswitch->qs.is_reaching) {
+		if (eswitch->qs.to_reach >= eswitch->qs.value + change) {
+			queues = eswitch->qs.to_reach;
+			eswitch->qs.is_reaching = false;
+		} else {
+			queues = 0;
+		}
+	} else if ((change > 0 && cp->alloc_txq <= eswitch->qs.value) ||
+		   change < 0) {
+		queues = cp->alloc_txq + change;
+	}
 
-	ice_for_each_vf(pf, bkt, vf) {
-		if (vf->repr)
-			ice_repr_start_tx_queues(vf->repr);
+	if (queues) {
+		cp->req_txq = queues;
+		cp->req_rxq = queues;
+		ice_vsi_close(cp);
+		ice_vsi_rebuild(cp, ICE_VSI_FLAG_NO_INIT);
+		ice_vsi_open(cp);
+	} else if (!change) {
+		/* change == 0 means that VSI wasn't open, open it here */
+		ice_vsi_open(cp);
 	}
+
+	eswitch->qs.value += change;
+	ice_eswitch_remap_rings_to_vectors(eswitch);
 }
 
-/**
- * ice_eswitch_stop_all_tx_queues - stop Tx queues of all port representors
- * @pf: pointer to PF structure
- */
-void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf)
+int
+ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf)
 {
-	struct ice_vf *vf;
-	unsigned int bkt;
+	struct ice_repr *repr;
+	int change = 1;
+	int err;
 
-	lockdep_assert_held(&pf->vfs.table_lock);
+	if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_LEGACY)
+		return 0;
 
-	if (test_bit(ICE_DOWN, pf->state))
+	if (xa_empty(&pf->eswitch.reprs)) {
+		err = ice_eswitch_enable_switchdev(pf);
+		if (err)
+			return err;
+		/* Control plane VSI is created with 1 queue as default */
+		pf->eswitch.qs.to_reach -= 1;
+		change = 0;
+	}
+
+	ice_eswitch_stop_reprs(pf);
+
+	repr = ice_repr_add_vf(vf);
+	if (IS_ERR(repr)) {
+		err = PTR_ERR(repr);
+		goto err_create_repr;
+	}
+
+	err = ice_eswitch_setup_repr(pf, repr);
+	if (err)
+		goto err_setup_repr;
+
+	err = xa_alloc(&pf->eswitch.reprs, &repr->id, repr,
+		       XA_LIMIT(1, INT_MAX), GFP_KERNEL);
+	if (err)
+		goto err_xa_alloc;
+
+	vf->repr_id = repr->id;
+
+	ice_eswitch_cp_change_queues(&pf->eswitch, change);
+	ice_eswitch_start_reprs(pf);
+
+	return 0;
+
+err_xa_alloc:
+	ice_eswitch_release_repr(pf, repr);
+err_setup_repr:
+	ice_repr_rem_vf(repr);
+err_create_repr:
+	if (xa_empty(&pf->eswitch.reprs))
+		ice_eswitch_disable_switchdev(pf);
+	ice_eswitch_start_reprs(pf);
+
+	return err;
+}
+
+void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf)
+{
+	struct ice_repr *repr = xa_load(&pf->eswitch.reprs, vf->repr_id);
+	struct devlink *devlink = priv_to_devlink(pf);
+
+	if (!repr)
 		return;
 
-	ice_for_each_vf(pf, bkt, vf) {
-		if (vf->repr)
-			ice_repr_stop_tx_queues(vf->repr);
+	ice_eswitch_stop_reprs(pf);
+	xa_erase(&pf->eswitch.reprs, repr->id);
+
+	if (xa_empty(&pf->eswitch.reprs))
+		ice_eswitch_disable_switchdev(pf);
+	else
+		ice_eswitch_cp_change_queues(&pf->eswitch, -1);
+
+	ice_eswitch_release_repr(pf, repr);
+	ice_repr_rem_vf(repr);
+
+	if (xa_empty(&pf->eswitch.reprs)) {
+		/* since all port representors are destroyed, there is
+		 * no point in keeping the nodes
+		 */
+		ice_devlink_rate_clear_tx_topology(ice_get_main_vsi(pf));
+		devl_lock(devlink);
+		devl_rate_nodes_destroy(devlink);
+		devl_unlock(devlink);
+	} else {
+		ice_eswitch_start_reprs(pf);
 	}
 }
 
@@ -693,30 +740,35 @@ void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf)
  */
 int ice_eswitch_rebuild(struct ice_pf *pf)
 {
-	struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi;
-	int status;
-
-	ice_eswitch_napi_disable(pf);
-	ice_eswitch_napi_del(pf);
-
-	status = ice_eswitch_setup_env(pf);
-	if (status)
-		return status;
+	struct ice_repr *repr;
+	unsigned long id;
+	int err;
 
-	status = ice_eswitch_setup_reprs(pf);
-	if (status)
-		return status;
+	if (!ice_is_switchdev_running(pf))
+		return 0;
 
-	ice_eswitch_remap_rings_to_vectors(pf);
+	err = ice_vsi_rebuild(pf->eswitch.control_vsi, ICE_VSI_FLAG_INIT);
+	if (err)
+		return err;
 
-	ice_replay_tc_fltrs(pf);
+	xa_for_each(&pf->eswitch.reprs, id, repr)
+		ice_eswitch_detach(pf, repr->vf);
 
-	status = ice_vsi_open(ctrl_vsi);
-	if (status)
-		return status;
+	return 0;
+}
 
-	ice_eswitch_napi_enable(pf);
-	ice_eswitch_start_all_tx_queues(pf);
+/**
+ * ice_eswitch_reserve_cp_queues - reserve control plane VSI queues
+ * @pf: pointer to PF structure
+ * @change: how many more (or less) queues is needed
+ *
+ * Remember to call ice_eswitch_attach/detach() the "change" times.
+ */
+void ice_eswitch_reserve_cp_queues(struct ice_pf *pf, int change)
+{
+	if (pf->eswitch.qs.value + change < 0)
+		return;
 
-	return 0;
+	pf->eswitch.qs.to_reach = pf->eswitch.qs.value + change;
+	pf->eswitch.qs.is_reaching = true;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.h b/drivers/net/ethernet/intel/ice/ice_eswitch.h
index b18bf83a2f5b..1a288a03a79a 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.h
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.h
@@ -7,8 +7,9 @@
 #include <net/devlink.h>
 
 #ifdef CONFIG_ICE_SWITCHDEV
-void ice_eswitch_release(struct ice_pf *pf);
-int ice_eswitch_configure(struct ice_pf *pf);
+void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf);
+int
+ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf);
 int ice_eswitch_rebuild(struct ice_pf *pf);
 
 int ice_eswitch_mode_get(struct devlink *devlink, u16 *mode);
@@ -17,7 +18,7 @@ ice_eswitch_mode_set(struct devlink *devlink, u16 mode,
 		     struct netlink_ext_ack *extack);
 bool ice_is_eswitch_mode_switchdev(struct ice_pf *pf);
 
-void ice_eswitch_update_repr(struct ice_vsi *vsi);
+void ice_eswitch_update_repr(unsigned long repr_id, struct ice_vsi *vsi);
 
 void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf);
 
@@ -25,8 +26,15 @@ void ice_eswitch_set_target_vsi(struct sk_buff *skb,
 				struct ice_tx_offload_params *off);
 netdev_tx_t
 ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev);
+void ice_eswitch_reserve_cp_queues(struct ice_pf *pf, int change);
 #else /* CONFIG_ICE_SWITCHDEV */
-static inline void ice_eswitch_release(struct ice_pf *pf) { }
+static inline void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf) { }
+
+static inline int
+ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf)
+{
+	return -EOPNOTSUPP;
+}
 
 static inline void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf) { }
 
@@ -34,7 +42,8 @@ static inline void
 ice_eswitch_set_target_vsi(struct sk_buff *skb,
 			   struct ice_tx_offload_params *off) { }
 
-static inline void ice_eswitch_update_repr(struct ice_vsi *vsi) { }
+static inline void
+ice_eswitch_update_repr(unsigned long repr_id, struct ice_vsi *vsi) { }
 
 static inline int ice_eswitch_configure(struct ice_pf *pf)
 {
@@ -68,5 +77,8 @@ ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 {
 	return NETDEV_TX_BUSY;
 }
+
+static inline void
+ice_eswitch_reserve_cp_queues(struct ice_pf *pf, int change) { }
 #endif /* CONFIG_ICE_SWITCHDEV */
 #endif /* _ICE_ESWITCH_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
index 6ae0269bdf73..ac5beecd028b 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
@@ -893,10 +893,14 @@ ice_eswitch_br_port_deinit(struct ice_esw_br *bridge,
 			ice_eswitch_br_fdb_entry_delete(bridge, fdb_entry);
 	}
 
-	if (br_port->type == ICE_ESWITCH_BR_UPLINK_PORT && vsi->back)
+	if (br_port->type == ICE_ESWITCH_BR_UPLINK_PORT && vsi->back) {
 		vsi->back->br_port = NULL;
-	else if (vsi->vf && vsi->vf->repr)
-		vsi->vf->repr->br_port = NULL;
+	} else {
+		struct ice_repr *repr = ice_repr_get_by_vsi(vsi);
+
+		if (repr)
+			repr->br_port = NULL;
+	}
 
 	xa_erase(&bridge->ports, br_port->vsi_idx);
 	ice_eswitch_br_port_vlans_flush(br_port);
@@ -947,7 +951,7 @@ ice_eswitch_br_vf_repr_port_init(struct ice_esw_br *bridge,
 static int
 ice_eswitch_br_uplink_port_init(struct ice_esw_br *bridge, struct ice_pf *pf)
 {
-	struct ice_vsi *vsi = pf->switchdev.uplink_vsi;
+	struct ice_vsi *vsi = pf->eswitch.uplink_vsi;
 	struct ice_esw_br_port *br_port;
 	int err;
 
@@ -1185,7 +1189,7 @@ ice_eswitch_br_port_event(struct notifier_block *nb,
 static void
 ice_eswitch_br_offloads_dealloc(struct ice_pf *pf)
 {
-	struct ice_esw_br_offloads *br_offloads = pf->switchdev.br_offloads;
+	struct ice_esw_br_offloads *br_offloads = pf->eswitch.br_offloads;
 
 	ASSERT_RTNL();
 
@@ -1194,7 +1198,7 @@ ice_eswitch_br_offloads_dealloc(struct ice_pf *pf)
 
 	ice_eswitch_br_deinit(br_offloads, br_offloads->bridge);
 
-	pf->switchdev.br_offloads = NULL;
+	pf->eswitch.br_offloads = NULL;
 	kfree(br_offloads);
 }
 
@@ -1205,14 +1209,14 @@ ice_eswitch_br_offloads_alloc(struct ice_pf *pf)
 
 	ASSERT_RTNL();
 
-	if (pf->switchdev.br_offloads)
+	if (pf->eswitch.br_offloads)
 		return ERR_PTR(-EEXIST);
 
 	br_offloads = kzalloc(sizeof(*br_offloads), GFP_KERNEL);
 	if (!br_offloads)
 		return ERR_PTR(-ENOMEM);
 
-	pf->switchdev.br_offloads = br_offloads;
+	pf->eswitch.br_offloads = br_offloads;
 	br_offloads->pf = pf;
 
 	return br_offloads;
@@ -1223,7 +1227,7 @@ ice_eswitch_br_offloads_deinit(struct ice_pf *pf)
 {
 	struct ice_esw_br_offloads *br_offloads;
 
-	br_offloads = pf->switchdev.br_offloads;
+	br_offloads = pf->eswitch.br_offloads;
 	if (!br_offloads)
 		return;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index a34083567e6f..a19b06f18e40 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -129,7 +129,6 @@ static const struct ice_stats ice_gstrings_pf_stats[] = {
 	ICE_PF_STAT("rx_oversize.nic", stats.rx_oversize),
 	ICE_PF_STAT("rx_jabber.nic", stats.rx_jabber),
 	ICE_PF_STAT("rx_csum_bad.nic", hw_csum_rx_error),
-	ICE_PF_STAT("rx_length_errors.nic", stats.rx_len_errors),
 	ICE_PF_STAT("rx_dropped.nic", stats.eth.rx_discards),
 	ICE_PF_STAT("rx_crc_errors.nic", stats.crc_errors),
 	ICE_PF_STAT("illegal_bytes.nic", stats.illegal_bytes),
@@ -1142,8 +1141,7 @@ __ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data,
 	switch (stringset) {
 	case ETH_SS_STATS:
 		for (i = 0; i < ICE_VSI_STATS_LEN; i++)
-			ethtool_sprintf(&p, "%s",
-					ice_gstrings_vsi_stats[i].stat_string);
+			ethtool_puts(&p, ice_gstrings_vsi_stats[i].stat_string);
 
 		if (ice_is_port_repr_netdev(netdev))
 			return;
@@ -1162,8 +1160,7 @@ __ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data,
 			return;
 
 		for (i = 0; i < ICE_PF_STATS_LEN; i++)
-			ethtool_sprintf(&p, "%s",
-					ice_gstrings_pf_stats[i].stat_string);
+			ethtool_puts(&p, ice_gstrings_pf_stats[i].stat_string);
 
 		for (i = 0; i < ICE_MAX_USER_PRIORITY; i++) {
 			ethtool_sprintf(&p, "tx_priority_%u_xon.nic", i);
@@ -1179,8 +1176,7 @@ __ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data,
 		break;
 	case ETH_SS_PRIV_FLAGS:
 		for (i = 0; i < ICE_PRIV_FLAG_ARRAY_SIZE; i++)
-			ethtool_sprintf(&p, "%s",
-					ice_gstrings_priv_flags[i].name);
+			ethtool_puts(&p, ice_gstrings_priv_flags[i].name);
 		break;
 	default:
 		break;
@@ -1850,14 +1846,14 @@ ice_phy_type_to_ethtool(struct net_device *netdev,
 	linkmode_zero(ks->link_modes.supported);
 	linkmode_zero(ks->link_modes.advertising);
 
-	for (i = 0; i < BITS_PER_TYPE(u64); i++) {
+	for (i = 0; i < ARRAY_SIZE(phy_type_low_lkup); i++) {
 		if (phy_types_low & BIT_ULL(i))
 			ice_linkmode_set_bit(&phy_type_low_lkup[i], ks,
 					     req_speeds, advert_phy_type_lo,
 					     i);
 	}
 
-	for (i = 0; i < BITS_PER_TYPE(u64); i++) {
+	for (i = 0; i < ARRAY_SIZE(phy_type_high_lkup); i++) {
 		if (phy_types_high & BIT_ULL(i))
 			ice_linkmode_set_bit(&phy_type_high_lkup[i], ks,
 					     req_speeds, advert_phy_type_hi,
@@ -2505,27 +2501,15 @@ static u32 ice_parse_hdrs(struct ethtool_rxnfc *nfc)
 	return hdrs;
 }
 
-#define ICE_FLOW_HASH_FLD_IPV4_SA	BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA)
-#define ICE_FLOW_HASH_FLD_IPV6_SA	BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA)
-#define ICE_FLOW_HASH_FLD_IPV4_DA	BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA)
-#define ICE_FLOW_HASH_FLD_IPV6_DA	BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA)
-#define ICE_FLOW_HASH_FLD_TCP_SRC_PORT	BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_SRC_PORT)
-#define ICE_FLOW_HASH_FLD_TCP_DST_PORT	BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_DST_PORT)
-#define ICE_FLOW_HASH_FLD_UDP_SRC_PORT	BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_SRC_PORT)
-#define ICE_FLOW_HASH_FLD_UDP_DST_PORT	BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_DST_PORT)
-#define ICE_FLOW_HASH_FLD_SCTP_SRC_PORT	\
-	BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT)
-#define ICE_FLOW_HASH_FLD_SCTP_DST_PORT	\
-	BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_DST_PORT)
-
 /**
  * ice_parse_hash_flds - parses hash fields from RSS hash input
  * @nfc: ethtool rxnfc command
+ * @symm: true if Symmetric Topelitz is set
  *
  * This function parses the rxnfc command and returns intended
  * hash fields for RSS configuration
  */
-static u64 ice_parse_hash_flds(struct ethtool_rxnfc *nfc)
+static u64 ice_parse_hash_flds(struct ethtool_rxnfc *nfc, bool symm)
 {
 	u64 hfld = ICE_HASH_INVALID;
 
@@ -2594,9 +2578,11 @@ static int
 ice_set_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc)
 {
 	struct ice_pf *pf = vsi->back;
+	struct ice_rss_hash_cfg cfg;
 	struct device *dev;
 	u64 hashed_flds;
 	int status;
+	bool symm;
 	u32 hdrs;
 
 	dev = ice_pf_to_dev(pf);
@@ -2606,7 +2592,8 @@ ice_set_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc)
 		return -EINVAL;
 	}
 
-	hashed_flds = ice_parse_hash_flds(nfc);
+	symm = !!(vsi->rss_hfunc == ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ);
+	hashed_flds = ice_parse_hash_flds(nfc, symm);
 	if (hashed_flds == ICE_HASH_INVALID) {
 		dev_dbg(dev, "Invalid hash fields, vsi num = %d\n",
 			vsi->vsi_num);
@@ -2620,7 +2607,12 @@ ice_set_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc)
 		return -EINVAL;
 	}
 
-	status = ice_add_rss_cfg(&pf->hw, vsi->idx, hashed_flds, hdrs);
+	cfg.hash_flds = hashed_flds;
+	cfg.addl_hdrs = hdrs;
+	cfg.hdr_type = ICE_RSS_ANY_HEADERS;
+	cfg.symm = symm;
+
+	status = ice_add_rss_cfg(&pf->hw, vsi, &cfg);
 	if (status) {
 		dev_dbg(dev, "ice_add_rss_cfg failed, vsi num = %d, error = %d\n",
 			vsi->vsi_num, status);
@@ -2641,6 +2633,7 @@ ice_get_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc)
 	struct ice_pf *pf = vsi->back;
 	struct device *dev;
 	u64 hash_flds;
+	bool symm;
 	u32 hdrs;
 
 	dev = ice_pf_to_dev(pf);
@@ -2659,7 +2652,7 @@ ice_get_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc)
 		return;
 	}
 
-	hash_flds = ice_get_rss_cfg(&pf->hw, vsi->idx, hdrs);
+	hash_flds = ice_get_rss_cfg(&pf->hw, vsi->idx, hdrs, &symm);
 	if (hash_flds == ICE_HASH_INVALID) {
 		dev_dbg(dev, "No hash fields found for the given header type, vsi num = %d\n",
 			vsi->vsi_num);
@@ -3198,11 +3191,18 @@ static u32 ice_get_rxfh_indir_size(struct net_device *netdev)
 	return np->vsi->rss_table_size;
 }
 
+/**
+ * ice_get_rxfh - get the Rx flow hash indirection table
+ * @netdev: network interface device structure
+ * @rxfh: pointer to param struct (indir, key, hfunc)
+ *
+ * Reads the indirection table directly from the hardware.
+ */
 static int
-ice_get_rxfh_context(struct net_device *netdev, u32 *indir,
-		     u8 *key, u8 *hfunc, u32 rss_context)
+ice_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
+	u32 rss_context = rxfh->rss_context;
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_pf *pf = vsi->back;
 	u16 qcount, offset;
@@ -3233,17 +3233,18 @@ ice_get_rxfh_context(struct net_device *netdev, u32 *indir,
 		vsi = vsi->tc_map_vsi[rss_context];
 	}
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (vsi->rss_hfunc == ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ)
+		rxfh->input_xfrm |= RXH_XFRM_SYM_XOR;
 
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
 	lut = kzalloc(vsi->rss_table_size, GFP_KERNEL);
 	if (!lut)
 		return -ENOMEM;
 
-	err = ice_get_rss_key(vsi, key);
+	err = ice_get_rss_key(vsi, rxfh->key);
 	if (err)
 		goto out;
 
@@ -3253,12 +3254,12 @@ ice_get_rxfh_context(struct net_device *netdev, u32 *indir,
 
 	if (ice_is_adq_active(pf)) {
 		for (i = 0; i < vsi->rss_table_size; i++)
-			indir[i] = offset + lut[i] % qcount;
+			rxfh->indir[i] = offset + lut[i] % qcount;
 		goto out;
 	}
 
 	for (i = 0; i < vsi->rss_table_size; i++)
-		indir[i] = lut[i];
+		rxfh->indir[i] = lut[i];
 
 out:
 	kfree(lut);
@@ -3266,42 +3267,31 @@ out:
 }
 
 /**
- * ice_get_rxfh - get the Rx flow hash indirection table
- * @netdev: network interface device structure
- * @indir: indirection table
- * @key: hash key
- * @hfunc: hash function
- *
- * Reads the indirection table directly from the hardware.
- */
-static int
-ice_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc)
-{
-	return ice_get_rxfh_context(netdev, indir, key, hfunc, 0);
-}
-
-/**
  * ice_set_rxfh - set the Rx flow hash indirection table
  * @netdev: network interface device structure
- * @indir: indirection table
- * @key: hash key
- * @hfunc: hash function
+ * @rxfh: pointer to param struct (indir, key, hfunc)
+ * @extack: extended ACK from the Netlink message
  *
  * Returns -EINVAL if the table specifies an invalid queue ID, otherwise
  * returns 0 after programming the table.
  */
 static int
-ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key,
-	     const u8 hfunc)
+ice_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh,
+	     struct netlink_ext_ack *extack)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
+	u8 hfunc = ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ;
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_pf *pf = vsi->back;
 	struct device *dev;
 	int err;
 
 	dev = ice_pf_to_dev(pf);
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+
+	if (rxfh->rss_context)
 		return -EOPNOTSUPP;
 
 	if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
@@ -3315,7 +3305,15 @@ ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key,
 		return -EOPNOTSUPP;
 	}
 
-	if (key) {
+	/* Update the VSI's hash function */
+	if (rxfh->input_xfrm & RXH_XFRM_SYM_XOR)
+		hfunc = ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ;
+
+	err = ice_set_rss_hfunc(vsi, hfunc);
+	if (err)
+		return err;
+
+	if (rxfh->key) {
 		if (!vsi->rss_hkey_user) {
 			vsi->rss_hkey_user =
 				devm_kzalloc(dev, ICE_VSIQF_HKEY_ARRAY_SIZE,
@@ -3323,7 +3321,8 @@ ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key,
 			if (!vsi->rss_hkey_user)
 				return -ENOMEM;
 		}
-		memcpy(vsi->rss_hkey_user, key, ICE_VSIQF_HKEY_ARRAY_SIZE);
+		memcpy(vsi->rss_hkey_user, rxfh->key,
+		       ICE_VSIQF_HKEY_ARRAY_SIZE);
 
 		err = ice_set_rss_key(vsi, vsi->rss_hkey_user);
 		if (err)
@@ -3338,11 +3337,11 @@ ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key,
 	}
 
 	/* Each 32 bits pointed by 'indir' is stored with a lut entry */
-	if (indir) {
+	if (rxfh->indir) {
 		int i;
 
 		for (i = 0; i < vsi->rss_table_size; i++)
-			vsi->rss_lut_user[i] = (u8)(indir[i]);
+			vsi->rss_lut_user[i] = (u8)(rxfh->indir[i]);
 	} else {
 		ice_fill_rss_lut(vsi->rss_lut_user, vsi->rss_table_size,
 				 vsi->rss_size);
@@ -4220,9 +4219,11 @@ ice_get_module_eeprom(struct net_device *netdev,
 }
 
 static const struct ethtool_ops ice_ethtool_ops = {
+	.cap_rss_ctx_supported  = true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE |
 				     ETHTOOL_COALESCE_RX_USECS_HIGH,
+	.cap_rss_sym_xor_supported = true,
 	.get_link_ksettings	= ice_get_link_ksettings,
 	.set_link_ksettings	= ice_set_link_ksettings,
 	.get_drvinfo		= ice_get_drvinfo,
@@ -4253,7 +4254,6 @@ static const struct ethtool_ops ice_ethtool_ops = {
 	.set_pauseparam		= ice_set_pauseparam,
 	.get_rxfh_key_size	= ice_get_rxfh_key_size,
 	.get_rxfh_indir_size	= ice_get_rxfh_indir_size,
-	.get_rxfh_context	= ice_get_rxfh_context,
 	.get_rxfh		= ice_get_rxfh,
 	.set_rxfh		= ice_set_rxfh,
 	.get_channels		= ice_get_channels,
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
index d151e5bacfec..9a1a04f5f146 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
@@ -302,9 +302,7 @@ void ice_fdir_rem_adq_chnl(struct ice_hw *hw, u16 vsi_idx)
 			continue;
 
 		for (tun = 0; tun < ICE_FD_HW_SEG_MAX; tun++) {
-			u64 prof_id;
-
-			prof_id = flow + tun * ICE_FLTR_PTYPE_MAX;
+			u64 prof_id = prof->prof_id[tun];
 
 			for (i = 0; i < prof->cnt; i++) {
 				if (prof->vsi_h[i] != vsi_idx)
@@ -362,10 +360,9 @@ ice_fdir_erase_flow_from_hw(struct ice_hw *hw, enum ice_block blk, int flow)
 		return;
 
 	for (tun = 0; tun < ICE_FD_HW_SEG_MAX; tun++) {
-		u64 prof_id;
+		u64 prof_id = prof->prof_id[tun];
 		int j;
 
-		prof_id = flow + tun * ICE_FLTR_PTYPE_MAX;
 		for (j = 0; j < prof->cnt; j++) {
 			u16 vsi_num;
 
@@ -439,14 +436,12 @@ void ice_fdir_replay_flows(struct ice_hw *hw)
 		for (tun = 0; tun < ICE_FD_HW_SEG_MAX; tun++) {
 			struct ice_flow_prof *hw_prof;
 			struct ice_fd_hw_prof *prof;
-			u64 prof_id;
 			int j;
 
 			prof = hw->fdir_prof[flow];
-			prof_id = flow + tun * ICE_FLTR_PTYPE_MAX;
-			ice_flow_add_prof(hw, ICE_BLK_FD, ICE_FLOW_RX, prof_id,
+			ice_flow_add_prof(hw, ICE_BLK_FD, ICE_FLOW_RX,
 					  prof->fdir_seg[tun], TNL_SEG_CNT(tun),
-					  &hw_prof);
+					  false, &hw_prof);
 			for (j = 0; j < prof->cnt; j++) {
 				enum ice_flow_priority prio;
 				u64 entry_h = 0;
@@ -454,7 +449,7 @@ void ice_fdir_replay_flows(struct ice_hw *hw)
 
 				prio = ICE_FLOW_PRIO_NORMAL;
 				err = ice_flow_add_entry(hw, ICE_BLK_FD,
-							 prof_id,
+							 hw_prof->id,
 							 prof->vsi_h[0],
 							 prof->vsi_h[j],
 							 prio, prof->fdir_seg,
@@ -464,6 +459,7 @@ void ice_fdir_replay_flows(struct ice_hw *hw)
 						flow);
 					continue;
 				}
+				prof->prof_id[tun] = hw_prof->id;
 				prof->entry_h[j][tun] = entry_h;
 			}
 		}
@@ -507,8 +503,7 @@ ice_parse_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp,
 		return -EINVAL;
 
 	data->flex_word = value & ICE_USERDEF_FLEX_WORD_M;
-	data->flex_offset = (value & ICE_USERDEF_FLEX_OFFS_M) >>
-			     ICE_USERDEF_FLEX_OFFS_S;
+	data->flex_offset = FIELD_GET(ICE_USERDEF_FLEX_OFFS_M, value);
 	if (data->flex_offset > ICE_USERDEF_FLEX_MAX_OFFS_VAL)
 		return -EINVAL;
 
@@ -638,7 +633,6 @@ ice_fdir_set_hw_fltr_rule(struct ice_pf *pf, struct ice_flow_seg_info *seg,
 	u64 entry1_h = 0;
 	u64 entry2_h = 0;
 	bool del_last;
-	u64 prof_id;
 	int err;
 	int idx;
 
@@ -668,7 +662,7 @@ ice_fdir_set_hw_fltr_rule(struct ice_pf *pf, struct ice_flow_seg_info *seg,
 		 * then return error.
 		 */
 		if (hw->fdir_fltr_cnt[flow]) {
-			dev_err(dev, "Failed to add filter.  Flow director filters on each port must have the same input set.\n");
+			dev_err(dev, "Failed to add filter. Flow director filters on each port must have the same input set.\n");
 			return -EINVAL;
 		}
 
@@ -686,23 +680,23 @@ ice_fdir_set_hw_fltr_rule(struct ice_pf *pf, struct ice_flow_seg_info *seg,
 	 * That is the final parameters are 1 header (segment), no
 	 * actions (NULL) and zero actions 0.
 	 */
-	prof_id = flow + tun * ICE_FLTR_PTYPE_MAX;
-	err = ice_flow_add_prof(hw, ICE_BLK_FD, ICE_FLOW_RX, prof_id, seg,
-				TNL_SEG_CNT(tun), &prof);
+	err = ice_flow_add_prof(hw, ICE_BLK_FD, ICE_FLOW_RX, seg,
+				TNL_SEG_CNT(tun), false, &prof);
 	if (err)
 		return err;
-	err = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, main_vsi->idx,
+	err = ice_flow_add_entry(hw, ICE_BLK_FD, prof->id, main_vsi->idx,
 				 main_vsi->idx, ICE_FLOW_PRIO_NORMAL,
 				 seg, &entry1_h);
 	if (err)
 		goto err_prof;
-	err = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, main_vsi->idx,
+	err = ice_flow_add_entry(hw, ICE_BLK_FD, prof->id, main_vsi->idx,
 				 ctrl_vsi->idx, ICE_FLOW_PRIO_NORMAL,
 				 seg, &entry2_h);
 	if (err)
 		goto err_entry;
 
 	hw_prof->fdir_seg[tun] = seg;
+	hw_prof->prof_id[tun] = prof->id;
 	hw_prof->entry_h[0][tun] = entry1_h;
 	hw_prof->entry_h[1][tun] = entry2_h;
 	hw_prof->vsi_h[0] = main_vsi->idx;
@@ -719,7 +713,7 @@ ice_fdir_set_hw_fltr_rule(struct ice_pf *pf, struct ice_flow_seg_info *seg,
 
 		entry1_h = 0;
 		vsi_h = main_vsi->tc_map_vsi[idx]->idx;
-		err = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id,
+		err = ice_flow_add_entry(hw, ICE_BLK_FD, prof->id,
 					 main_vsi->idx, vsi_h,
 					 ICE_FLOW_PRIO_NORMAL, seg,
 					 &entry1_h);
@@ -756,7 +750,7 @@ err_unroll:
 
 		if (!hw_prof->entry_h[idx][tun])
 			continue;
-		ice_rem_prof_id_flow(hw, ICE_BLK_FD, vsi_num, prof_id);
+		ice_rem_prof_id_flow(hw, ICE_BLK_FD, vsi_num, prof->id);
 		ice_flow_rem_entry(hw, ICE_BLK_FD, hw_prof->entry_h[idx][tun]);
 		hw_prof->entry_h[idx][tun] = 0;
 		if (del_last)
@@ -766,11 +760,11 @@ err_unroll:
 		hw_prof->cnt = 0;
 err_entry:
 	ice_rem_prof_id_flow(hw, ICE_BLK_FD,
-			     ice_get_hw_vsi_num(hw, main_vsi->idx), prof_id);
+			     ice_get_hw_vsi_num(hw, main_vsi->idx), prof->id);
 	ice_flow_rem_entry(hw, ICE_BLK_FD, entry1_h);
 err_prof:
-	ice_flow_rem_prof(hw, ICE_BLK_FD, prof_id);
-	dev_err(dev, "Failed to add filter.  Flow director filters on each port must have the same input set.\n");
+	ice_flow_rem_prof(hw, ICE_BLK_FD, prof->id);
+	dev_err(dev, "Failed to add filter. Flow director filters on each port must have the same input set.\n");
 
 	return err;
 }
@@ -1853,6 +1847,7 @@ int ice_add_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd)
 	struct ice_pf *pf;
 	struct ice_hw *hw;
 	int fltrs_needed;
+	u32 max_location;
 	u16 tunnel_port;
 	int ret;
 
@@ -1884,8 +1879,10 @@ int ice_add_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd)
 	if (ret)
 		return ret;
 
-	if (fsp->location >= ice_get_fdir_cnt_all(hw)) {
-		dev_err(dev, "Failed to add filter.  The maximum number of flow director filters has been reached.\n");
+	max_location = ice_get_fdir_cnt_all(hw);
+	if (fsp->location >= max_location) {
+		dev_err(dev, "Failed to add filter. The number of ntuple filters or provided location exceed max %d.\n",
+			max_location);
 		return -ENOSPC;
 	}
 
@@ -1893,7 +1890,7 @@ int ice_add_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd)
 	fltrs_needed = ice_get_open_tunnel_port(hw, &tunnel_port, TNL_ALL) ? 2 : 1;
 	if (!ice_fdir_find_fltr_by_idx(hw, fsp->location) &&
 	    ice_fdir_num_avail_fltr(hw, pf->vsi[vsi->idx]) < fltrs_needed) {
-		dev_err(dev, "Failed to add filter.  The maximum number of flow director filters has been reached.\n");
+		dev_err(dev, "Failed to add filter. The maximum number of flow director filters has been reached.\n");
 		return -ENOSPC;
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.c b/drivers/net/ethernet/intel/ice/ice_fdir.c
index ae089d32ee9d..5840c3e04a5b 100644
--- a/drivers/net/ethernet/intel/ice/ice_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_fdir.c
@@ -604,55 +604,32 @@ ice_set_fd_desc_val(struct ice_fd_fltr_desc_ctx *ctx,
 	u64 qword;
 
 	/* prep QW0 of FD filter programming desc */
-	qword = ((u64)ctx->qindex << ICE_FXD_FLTR_QW0_QINDEX_S) &
-		ICE_FXD_FLTR_QW0_QINDEX_M;
-	qword |= ((u64)ctx->comp_q << ICE_FXD_FLTR_QW0_COMP_Q_S) &
-		 ICE_FXD_FLTR_QW0_COMP_Q_M;
-	qword |= ((u64)ctx->comp_report << ICE_FXD_FLTR_QW0_COMP_REPORT_S) &
-		 ICE_FXD_FLTR_QW0_COMP_REPORT_M;
-	qword |= ((u64)ctx->fd_space << ICE_FXD_FLTR_QW0_FD_SPACE_S) &
-		 ICE_FXD_FLTR_QW0_FD_SPACE_M;
-	qword |= ((u64)ctx->cnt_index << ICE_FXD_FLTR_QW0_STAT_CNT_S) &
-		 ICE_FXD_FLTR_QW0_STAT_CNT_M;
-	qword |= ((u64)ctx->cnt_ena << ICE_FXD_FLTR_QW0_STAT_ENA_S) &
-		 ICE_FXD_FLTR_QW0_STAT_ENA_M;
-	qword |= ((u64)ctx->evict_ena << ICE_FXD_FLTR_QW0_EVICT_ENA_S) &
-		 ICE_FXD_FLTR_QW0_EVICT_ENA_M;
-	qword |= ((u64)ctx->toq << ICE_FXD_FLTR_QW0_TO_Q_S) &
-		 ICE_FXD_FLTR_QW0_TO_Q_M;
-	qword |= ((u64)ctx->toq_prio << ICE_FXD_FLTR_QW0_TO_Q_PRI_S) &
-		 ICE_FXD_FLTR_QW0_TO_Q_PRI_M;
-	qword |= ((u64)ctx->dpu_recipe << ICE_FXD_FLTR_QW0_DPU_RECIPE_S) &
-		 ICE_FXD_FLTR_QW0_DPU_RECIPE_M;
-	qword |= ((u64)ctx->drop << ICE_FXD_FLTR_QW0_DROP_S) &
-		 ICE_FXD_FLTR_QW0_DROP_M;
-	qword |= ((u64)ctx->flex_prio << ICE_FXD_FLTR_QW0_FLEX_PRI_S) &
-		 ICE_FXD_FLTR_QW0_FLEX_PRI_M;
-	qword |= ((u64)ctx->flex_mdid << ICE_FXD_FLTR_QW0_FLEX_MDID_S) &
-		 ICE_FXD_FLTR_QW0_FLEX_MDID_M;
-	qword |= ((u64)ctx->flex_val << ICE_FXD_FLTR_QW0_FLEX_VAL_S) &
-		 ICE_FXD_FLTR_QW0_FLEX_VAL_M;
+	qword = FIELD_PREP(ICE_FXD_FLTR_QW0_QINDEX_M, ctx->qindex);
+	qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_COMP_Q_M, ctx->comp_q);
+	qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_COMP_REPORT_M, ctx->comp_report);
+	qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_FD_SPACE_M, ctx->fd_space);
+	qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_STAT_CNT_M, ctx->cnt_index);
+	qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_STAT_ENA_M, ctx->cnt_ena);
+	qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_EVICT_ENA_M, ctx->evict_ena);
+	qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_TO_Q_M, ctx->toq);
+	qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_TO_Q_PRI_M, ctx->toq_prio);
+	qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_DPU_RECIPE_M, ctx->dpu_recipe);
+	qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_DROP_M, ctx->drop);
+	qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_FLEX_PRI_M, ctx->flex_prio);
+	qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_FLEX_MDID_M, ctx->flex_mdid);
+	qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_FLEX_VAL_M, ctx->flex_val);
 	fdir_desc->qidx_compq_space_stat = cpu_to_le64(qword);
 
 	/* prep QW1 of FD filter programming desc */
-	qword = ((u64)ctx->dtype << ICE_FXD_FLTR_QW1_DTYPE_S) &
-		ICE_FXD_FLTR_QW1_DTYPE_M;
-	qword |= ((u64)ctx->pcmd << ICE_FXD_FLTR_QW1_PCMD_S) &
-		 ICE_FXD_FLTR_QW1_PCMD_M;
-	qword |= ((u64)ctx->desc_prof_prio << ICE_FXD_FLTR_QW1_PROF_PRI_S) &
-		 ICE_FXD_FLTR_QW1_PROF_PRI_M;
-	qword |= ((u64)ctx->desc_prof << ICE_FXD_FLTR_QW1_PROF_S) &
-		 ICE_FXD_FLTR_QW1_PROF_M;
-	qword |= ((u64)ctx->fd_vsi << ICE_FXD_FLTR_QW1_FD_VSI_S) &
-		 ICE_FXD_FLTR_QW1_FD_VSI_M;
-	qword |= ((u64)ctx->swap << ICE_FXD_FLTR_QW1_SWAP_S) &
-		 ICE_FXD_FLTR_QW1_SWAP_M;
-	qword |= ((u64)ctx->fdid_prio << ICE_FXD_FLTR_QW1_FDID_PRI_S) &
-		 ICE_FXD_FLTR_QW1_FDID_PRI_M;
-	qword |= ((u64)ctx->fdid_mdid << ICE_FXD_FLTR_QW1_FDID_MDID_S) &
-		 ICE_FXD_FLTR_QW1_FDID_MDID_M;
-	qword |= ((u64)ctx->fdid << ICE_FXD_FLTR_QW1_FDID_S) &
-		 ICE_FXD_FLTR_QW1_FDID_M;
+	qword = FIELD_PREP(ICE_FXD_FLTR_QW1_DTYPE_M, ctx->dtype);
+	qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_PCMD_M, ctx->pcmd);
+	qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_PROF_PRI_M, ctx->desc_prof_prio);
+	qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_PROF_M, ctx->desc_prof);
+	qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_FD_VSI_M, ctx->fd_vsi);
+	qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_SWAP_M, ctx->swap);
+	qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_FDID_PRI_M, ctx->fdid_prio);
+	qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_FDID_MDID_M, ctx->fdid_mdid);
+	qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_FDID_M, ctx->fdid);
 	fdir_desc->dtype_cmd_vsi_fdid = cpu_to_le64(qword);
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
index 5ce413965930..20d5db88c99f 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
@@ -1218,11 +1218,13 @@ ice_prof_has_mask(struct ice_hw *hw, enum ice_block blk, u8 prof, u16 *masks)
  * @blk: HW block
  * @fv: field vector to search for
  * @masks: masks for FV
+ * @symm: symmetric setting for RSS flows
  * @prof_id: receives the profile ID
  */
 static int
 ice_find_prof_id_with_mask(struct ice_hw *hw, enum ice_block blk,
-			   struct ice_fv_word *fv, u16 *masks, u8 *prof_id)
+			   struct ice_fv_word *fv, u16 *masks, bool symm,
+			   u8 *prof_id)
 {
 	struct ice_es *es = &hw->blk[blk].es;
 	u8 i;
@@ -1236,6 +1238,9 @@ ice_find_prof_id_with_mask(struct ice_hw *hw, enum ice_block blk,
 	for (i = 0; i < (u8)es->count; i++) {
 		u16 off = i * es->fvw;
 
+		if (blk == ICE_BLK_RSS && es->symm[i] != symm)
+			continue;
+
 		if (memcmp(&es->t[off], fv, es->fvw * sizeof(*fv)))
 			continue;
 
@@ -1409,13 +1414,13 @@ ice_write_prof_mask_reg(struct ice_hw *hw, enum ice_block blk, u16 mask_idx,
 	switch (blk) {
 	case ICE_BLK_RSS:
 		offset = GLQF_HMASK(mask_idx);
-		val = (idx << GLQF_HMASK_MSK_INDEX_S) & GLQF_HMASK_MSK_INDEX_M;
-		val |= (mask << GLQF_HMASK_MASK_S) & GLQF_HMASK_MASK_M;
+		val = FIELD_PREP(GLQF_HMASK_MSK_INDEX_M, idx);
+		val |= FIELD_PREP(GLQF_HMASK_MASK_M, mask);
 		break;
 	case ICE_BLK_FD:
 		offset = GLQF_FDMASK(mask_idx);
-		val = (idx << GLQF_FDMASK_MSK_INDEX_S) & GLQF_FDMASK_MSK_INDEX_M;
-		val |= (mask << GLQF_FDMASK_MASK_S) & GLQF_FDMASK_MASK_M;
+		val = FIELD_PREP(GLQF_FDMASK_MSK_INDEX_M, idx);
+		val |= FIELD_PREP(GLQF_FDMASK_MASK_M, mask);
 		break;
 	default:
 		ice_debug(hw, ICE_DBG_PKG, "No profile masks for block %d\n",
@@ -1716,15 +1721,16 @@ ice_update_prof_masking(struct ice_hw *hw, enum ice_block blk, u16 prof_id,
 }
 
 /**
- * ice_write_es - write an extraction sequence to hardware
+ * ice_write_es - write an extraction sequence and symmetric setting to hardware
  * @hw: pointer to the HW struct
  * @blk: the block in which to write the extraction sequence
  * @prof_id: the profile ID to write
  * @fv: pointer to the extraction sequence to write - NULL to clear extraction
+ * @symm: symmetric setting for RSS profiles
  */
 static void
 ice_write_es(struct ice_hw *hw, enum ice_block blk, u8 prof_id,
-	     struct ice_fv_word *fv)
+	     struct ice_fv_word *fv, bool symm)
 {
 	u16 off;
 
@@ -1737,6 +1743,9 @@ ice_write_es(struct ice_hw *hw, enum ice_block blk, u8 prof_id,
 		memcpy(&hw->blk[blk].es.t[off], fv,
 		       hw->blk[blk].es.fvw * sizeof(*fv));
 	}
+
+	if (blk == ICE_BLK_RSS)
+		hw->blk[blk].es.symm[prof_id] = symm;
 }
 
 /**
@@ -1753,7 +1762,7 @@ ice_prof_dec_ref(struct ice_hw *hw, enum ice_block blk, u8 prof_id)
 
 	if (hw->blk[blk].es.ref_count[prof_id] > 0) {
 		if (!--hw->blk[blk].es.ref_count[prof_id]) {
-			ice_write_es(hw, blk, prof_id, NULL);
+			ice_write_es(hw, blk, prof_id, NULL, false);
 			ice_free_prof_masks(hw, blk, prof_id);
 			return ice_free_prof_id(hw, blk, prof_id);
 		}
@@ -2116,8 +2125,10 @@ void ice_free_hw_tbls(struct ice_hw *hw)
 		devm_kfree(ice_hw_to_dev(hw), hw->blk[i].prof_redir.t);
 		devm_kfree(ice_hw_to_dev(hw), hw->blk[i].es.t);
 		devm_kfree(ice_hw_to_dev(hw), hw->blk[i].es.ref_count);
+		devm_kfree(ice_hw_to_dev(hw), hw->blk[i].es.symm);
 		devm_kfree(ice_hw_to_dev(hw), hw->blk[i].es.written);
 		devm_kfree(ice_hw_to_dev(hw), hw->blk[i].es.mask_ena);
+		devm_kfree(ice_hw_to_dev(hw), hw->blk[i].prof_id.id);
 	}
 
 	list_for_each_entry_safe(r, rt, &hw->rss_list_head, l_entry) {
@@ -2150,6 +2161,7 @@ void ice_clear_hw_tbls(struct ice_hw *hw)
 
 	for (i = 0; i < ICE_BLK_COUNT; i++) {
 		struct ice_prof_redir *prof_redir = &hw->blk[i].prof_redir;
+		struct ice_prof_id *prof_id = &hw->blk[i].prof_id;
 		struct ice_prof_tcam *prof = &hw->blk[i].prof;
 		struct ice_xlt1 *xlt1 = &hw->blk[i].xlt1;
 		struct ice_xlt2 *xlt2 = &hw->blk[i].xlt2;
@@ -2178,8 +2190,11 @@ void ice_clear_hw_tbls(struct ice_hw *hw)
 
 		memset(es->t, 0, es->count * sizeof(*es->t) * es->fvw);
 		memset(es->ref_count, 0, es->count * sizeof(*es->ref_count));
+		memset(es->symm, 0, es->count * sizeof(*es->symm));
 		memset(es->written, 0, es->count * sizeof(*es->written));
 		memset(es->mask_ena, 0, es->count * sizeof(*es->mask_ena));
+
+		memset(prof_id->id, 0, prof_id->count * sizeof(*prof_id->id));
 	}
 }
 
@@ -2196,6 +2211,7 @@ int ice_init_hw_tbls(struct ice_hw *hw)
 	ice_init_all_prof_masks(hw);
 	for (i = 0; i < ICE_BLK_COUNT; i++) {
 		struct ice_prof_redir *prof_redir = &hw->blk[i].prof_redir;
+		struct ice_prof_id *prof_id = &hw->blk[i].prof_id;
 		struct ice_prof_tcam *prof = &hw->blk[i].prof;
 		struct ice_xlt1 *xlt1 = &hw->blk[i].xlt1;
 		struct ice_xlt2 *xlt2 = &hw->blk[i].xlt2;
@@ -2292,6 +2308,11 @@ int ice_init_hw_tbls(struct ice_hw *hw)
 		if (!es->ref_count)
 			goto err;
 
+		es->symm = devm_kcalloc(ice_hw_to_dev(hw), es->count,
+					sizeof(*es->symm), GFP_KERNEL);
+		if (!es->symm)
+			goto err;
+
 		es->written = devm_kcalloc(ice_hw_to_dev(hw), es->count,
 					   sizeof(*es->written), GFP_KERNEL);
 		if (!es->written)
@@ -2301,6 +2322,12 @@ int ice_init_hw_tbls(struct ice_hw *hw)
 					    sizeof(*es->mask_ena), GFP_KERNEL);
 		if (!es->mask_ena)
 			goto err;
+
+		prof_id->count = blk_sizes[i].prof_id;
+		prof_id->id = devm_kcalloc(ice_hw_to_dev(hw), prof_id->count,
+					   sizeof(*prof_id->id), GFP_KERNEL);
+		if (!prof_id->id)
+			goto err;
 	}
 	return 0;
 
@@ -2963,6 +2990,7 @@ ice_add_prof_attrib(struct ice_prof_map *prof, u8 ptg, u16 ptype,
  * @attr_cnt: number of elements in attr array
  * @es: extraction sequence (length of array is determined by the block)
  * @masks: mask for extraction sequence
+ * @symm: symmetric setting for RSS profiles
  *
  * This function registers a profile, which matches a set of PTYPES with a
  * particular extraction sequence. While the hardware profile is allocated
@@ -2972,7 +3000,7 @@ ice_add_prof_attrib(struct ice_prof_map *prof, u8 ptg, u16 ptype,
 int
 ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[],
 	     const struct ice_ptype_attributes *attr, u16 attr_cnt,
-	     struct ice_fv_word *es, u16 *masks)
+	     struct ice_fv_word *es, u16 *masks, bool symm)
 {
 	u32 bytes = DIV_ROUND_UP(ICE_FLOW_PTYPE_MAX, BITS_PER_BYTE);
 	DECLARE_BITMAP(ptgs_used, ICE_XLT1_CNT);
@@ -2986,7 +3014,7 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[],
 	mutex_lock(&hw->blk[blk].es.prof_map_lock);
 
 	/* search for existing profile */
-	status = ice_find_prof_id_with_mask(hw, blk, es, masks, &prof_id);
+	status = ice_find_prof_id_with_mask(hw, blk, es, masks, symm, &prof_id);
 	if (status) {
 		/* allocate profile ID */
 		status = ice_alloc_prof_id(hw, blk, &prof_id);
@@ -3009,7 +3037,7 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[],
 			goto err_ice_add_prof;
 
 		/* and write new es */
-		ice_write_es(hw, blk, prof_id, es);
+		ice_write_es(hw, blk, prof_id, es, symm);
 	}
 
 	ice_prof_inc_ref(hw, blk, prof_id);
@@ -3097,7 +3125,7 @@ err_ice_add_prof:
  * This will search for a profile tracking ID which was previously added.
  * The profile map lock should be held before calling this function.
  */
-static struct ice_prof_map *
+struct ice_prof_map *
 ice_search_prof_id(struct ice_hw *hw, enum ice_block blk, u64 id)
 {
 	struct ice_prof_map *entry = NULL;
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
index 7af7c8e9aa4e..b39d7cdc381f 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
@@ -42,7 +42,9 @@ bool ice_hw_ptype_ena(struct ice_hw *hw, u16 ptype);
 int
 ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[],
 	     const struct ice_ptype_attributes *attr, u16 attr_cnt,
-	     struct ice_fv_word *es, u16 *masks);
+	     struct ice_fv_word *es, u16 *masks, bool symm);
+struct ice_prof_map *
+ice_search_prof_id(struct ice_hw *hw, enum ice_block blk, u64 id);
 int
 ice_add_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl);
 int
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h
index 4f42e14ed3ae..d427a79d001a 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h
@@ -146,6 +146,7 @@ struct ice_es {
 	u32 *mask_ena;
 	struct list_head prof_map;
 	struct ice_fv_word *t;
+	u8 *symm;	/* symmetric setting per profile (RSS blk)*/
 	struct mutex prof_map_lock;	/* protect access to profiles list */
 	u8 *written;
 	u8 reverse; /* set to true to reverse FV order */
@@ -304,10 +305,16 @@ struct ice_masks {
 	struct ice_mask masks[ICE_PROF_MASK_COUNT];
 };
 
+struct ice_prof_id {
+	unsigned long *id;
+	int count;
+};
+
 /* Tables per block */
 struct ice_blk_info {
 	struct ice_xlt1 xlt1;
 	struct ice_xlt2 xlt2;
+	struct ice_prof_id prof_id;
 	struct ice_prof_tcam prof;
 	struct ice_prof_redir prof_redir;
 	struct ice_es es;
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c
index fb8b925aaf8b..fc2b58f56279 100644
--- a/drivers/net/ethernet/intel/ice/ice_flow.c
+++ b/drivers/net/ethernet/intel/ice/ice_flow.c
@@ -1235,6 +1235,7 @@ ice_flow_proc_segs(struct ice_hw *hw, struct ice_flow_prof_params *params)
 #define ICE_FLOW_FIND_PROF_CHK_FLDS	0x00000001
 #define ICE_FLOW_FIND_PROF_CHK_VSI	0x00000002
 #define ICE_FLOW_FIND_PROF_NOT_CHK_DIR	0x00000004
+#define ICE_FLOW_FIND_PROF_CHK_SYMM	0x00000008
 
 /**
  * ice_flow_find_prof_conds - Find a profile matching headers and conditions
@@ -1243,13 +1244,14 @@ ice_flow_proc_segs(struct ice_hw *hw, struct ice_flow_prof_params *params)
  * @dir: flow direction
  * @segs: array of one or more packet segments that describe the flow
  * @segs_cnt: number of packet segments provided
+ * @symm: symmetric setting for RSS profiles
  * @vsi_handle: software VSI handle to check VSI (ICE_FLOW_FIND_PROF_CHK_VSI)
  * @conds: additional conditions to be checked (ICE_FLOW_FIND_PROF_CHK_*)
  */
 static struct ice_flow_prof *
 ice_flow_find_prof_conds(struct ice_hw *hw, enum ice_block blk,
 			 enum ice_flow_dir dir, struct ice_flow_seg_info *segs,
-			 u8 segs_cnt, u16 vsi_handle, u32 conds)
+			 u8 segs_cnt, bool symm, u16 vsi_handle, u32 conds)
 {
 	struct ice_flow_prof *p, *prof = NULL;
 
@@ -1265,6 +1267,11 @@ ice_flow_find_prof_conds(struct ice_hw *hw, enum ice_block blk,
 			    !test_bit(vsi_handle, p->vsis))
 				continue;
 
+			/* Check for symmetric settings */
+			if ((conds & ICE_FLOW_FIND_PROF_CHK_SYMM) &&
+			    p->symm != symm)
+				continue;
+
 			/* Protocol headers must be checked. Matched fields are
 			 * checked if specified.
 			 */
@@ -1328,26 +1335,33 @@ ice_flow_rem_entry_sync(struct ice_hw *hw, enum ice_block __always_unused blk,
  * @hw: pointer to the HW struct
  * @blk: classification stage
  * @dir: flow direction
- * @prof_id: unique ID to identify this flow profile
  * @segs: array of one or more packet segments that describe the flow
  * @segs_cnt: number of packet segments provided
+ * @symm: symmetric setting for RSS profiles
  * @prof: stores the returned flow profile added
  *
  * Assumption: the caller has acquired the lock to the profile list
  */
 static int
 ice_flow_add_prof_sync(struct ice_hw *hw, enum ice_block blk,
-		       enum ice_flow_dir dir, u64 prof_id,
+		       enum ice_flow_dir dir,
 		       struct ice_flow_seg_info *segs, u8 segs_cnt,
-		       struct ice_flow_prof **prof)
+		       bool symm, struct ice_flow_prof **prof)
 {
 	struct ice_flow_prof_params *params;
+	struct ice_prof_id *ids;
 	int status;
+	u64 prof_id;
 	u8 i;
 
 	if (!prof)
 		return -EINVAL;
 
+	ids = &hw->blk[blk].prof_id;
+	prof_id = find_first_zero_bit(ids->id, ids->count);
+	if (prof_id >= ids->count)
+		return -ENOSPC;
+
 	params = kzalloc(sizeof(*params), GFP_KERNEL);
 	if (!params)
 		return -ENOMEM;
@@ -1369,6 +1383,7 @@ ice_flow_add_prof_sync(struct ice_hw *hw, enum ice_block blk,
 	params->prof->id = prof_id;
 	params->prof->dir = dir;
 	params->prof->segs_cnt = segs_cnt;
+	params->prof->symm = symm;
 
 	/* Make a copy of the segments that need to be persistent in the flow
 	 * profile instance
@@ -1385,7 +1400,7 @@ ice_flow_add_prof_sync(struct ice_hw *hw, enum ice_block blk,
 	/* Add a HW profile for this flow profile */
 	status = ice_add_prof(hw, blk, prof_id, (u8 *)params->ptypes,
 			      params->attr, params->attr_cnt, params->es,
-			      params->mask);
+			      params->mask, symm);
 	if (status) {
 		ice_debug(hw, ICE_DBG_FLOW, "Error adding a HW flow profile\n");
 		goto out;
@@ -1393,6 +1408,7 @@ ice_flow_add_prof_sync(struct ice_hw *hw, enum ice_block blk,
 
 	INIT_LIST_HEAD(&params->prof->entries);
 	mutex_init(&params->prof->entries_lock);
+	set_bit(prof_id, ids->id);
 	*prof = params->prof;
 
 out:
@@ -1436,6 +1452,7 @@ ice_flow_rem_prof_sync(struct ice_hw *hw, enum ice_block blk,
 	/* Remove all hardware profiles associated with this flow profile */
 	status = ice_rem_prof(hw, blk, prof->id);
 	if (!status) {
+		clear_bit(prof->id, hw->blk[blk].prof_id.id);
 		list_del(&prof->l_entry);
 		mutex_destroy(&prof->entries_lock);
 		devm_kfree(ice_hw_to_dev(hw), prof);
@@ -1511,15 +1528,15 @@ ice_flow_disassoc_prof(struct ice_hw *hw, enum ice_block blk,
  * @hw: pointer to the HW struct
  * @blk: classification stage
  * @dir: flow direction
- * @prof_id: unique ID to identify this flow profile
  * @segs: array of one or more packet segments that describe the flow
  * @segs_cnt: number of packet segments provided
+ * @symm: symmetric setting for RSS profiles
  * @prof: stores the returned flow profile added
  */
 int
 ice_flow_add_prof(struct ice_hw *hw, enum ice_block blk, enum ice_flow_dir dir,
-		  u64 prof_id, struct ice_flow_seg_info *segs, u8 segs_cnt,
-		  struct ice_flow_prof **prof)
+		  struct ice_flow_seg_info *segs, u8 segs_cnt,
+		  bool symm, struct ice_flow_prof **prof)
 {
 	int status;
 
@@ -1538,8 +1555,8 @@ ice_flow_add_prof(struct ice_hw *hw, enum ice_block blk, enum ice_flow_dir dir,
 
 	mutex_lock(&hw->fl_profs_locks[blk]);
 
-	status = ice_flow_add_prof_sync(hw, blk, dir, prof_id, segs, segs_cnt,
-					prof);
+	status = ice_flow_add_prof_sync(hw, blk, dir, segs, segs_cnt,
+					symm, prof);
 	if (!status)
 		list_add(&(*prof)->l_entry, &hw->fl_profs[blk]);
 
@@ -1855,37 +1872,49 @@ int ice_flow_rem_vsi_prof(struct ice_hw *hw, u16 vsi_handle, u64 prof_id)
 /**
  * ice_flow_set_rss_seg_info - setup packet segments for RSS
  * @segs: pointer to the flow field segment(s)
- * @hash_fields: fields to be hashed on for the segment(s)
- * @flow_hdr: protocol header fields within a packet segment
+ * @seg_cnt: segment count
+ * @cfg: configure parameters
  *
  * Helper function to extract fields from hash bitmap and use flow
  * header value to set flow field segment for further use in flow
  * profile entry or removal.
  */
 static int
-ice_flow_set_rss_seg_info(struct ice_flow_seg_info *segs, u64 hash_fields,
-			  u32 flow_hdr)
+ice_flow_set_rss_seg_info(struct ice_flow_seg_info *segs, u8 seg_cnt,
+			  const struct ice_rss_hash_cfg *cfg)
 {
+	struct ice_flow_seg_info *seg;
 	u64 val;
-	u8 i;
+	u16 i;
 
-	for_each_set_bit(i, (unsigned long *)&hash_fields,
-			 ICE_FLOW_FIELD_IDX_MAX)
-		ice_flow_set_fld(segs, (enum ice_flow_field)i,
+	/* set inner most segment */
+	seg = &segs[seg_cnt - 1];
+
+	for_each_set_bit(i, (const unsigned long *)&cfg->hash_flds,
+			 (u16)ICE_FLOW_FIELD_IDX_MAX)
+		ice_flow_set_fld(seg, (enum ice_flow_field)i,
 				 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL,
 				 ICE_FLOW_FLD_OFF_INVAL, false);
 
-	ICE_FLOW_SET_HDRS(segs, flow_hdr);
+	ICE_FLOW_SET_HDRS(seg, cfg->addl_hdrs);
+
+	/* set outer most header */
+	if (cfg->hdr_type == ICE_RSS_INNER_HEADERS_W_OUTER_IPV4)
+		segs[ICE_RSS_OUTER_HEADERS].hdrs |= ICE_FLOW_SEG_HDR_IPV4 |
+						    ICE_FLOW_SEG_HDR_IPV_OTHER;
+	else if (cfg->hdr_type == ICE_RSS_INNER_HEADERS_W_OUTER_IPV6)
+		segs[ICE_RSS_OUTER_HEADERS].hdrs |= ICE_FLOW_SEG_HDR_IPV6 |
+						    ICE_FLOW_SEG_HDR_IPV_OTHER;
 
-	if (segs->hdrs & ~ICE_FLOW_RSS_SEG_HDR_VAL_MASKS &
+	if (seg->hdrs & ~ICE_FLOW_RSS_SEG_HDR_VAL_MASKS &
 	    ~ICE_FLOW_RSS_HDRS_INNER_MASK & ~ICE_FLOW_SEG_HDR_IPV_OTHER)
 		return -EINVAL;
 
-	val = (u64)(segs->hdrs & ICE_FLOW_RSS_SEG_HDR_L3_MASKS);
+	val = (u64)(seg->hdrs & ICE_FLOW_RSS_SEG_HDR_L3_MASKS);
 	if (val && !is_power_of_2(val))
 		return -EIO;
 
-	val = (u64)(segs->hdrs & ICE_FLOW_RSS_SEG_HDR_L4_MASKS);
+	val = (u64)(seg->hdrs & ICE_FLOW_RSS_SEG_HDR_L4_MASKS);
 	if (val && !is_power_of_2(val))
 		return -EIO;
 
@@ -1956,6 +1985,39 @@ int ice_rem_vsi_rss_cfg(struct ice_hw *hw, u16 vsi_handle)
 }
 
 /**
+ * ice_get_rss_hdr_type - get a RSS profile's header type
+ * @prof: RSS flow profile
+ */
+static enum ice_rss_cfg_hdr_type
+ice_get_rss_hdr_type(struct ice_flow_prof *prof)
+{
+	if (prof->segs_cnt == ICE_FLOW_SEG_SINGLE) {
+		return ICE_RSS_OUTER_HEADERS;
+	} else if (prof->segs_cnt == ICE_FLOW_SEG_MAX) {
+		const struct ice_flow_seg_info *s;
+
+		s = &prof->segs[ICE_RSS_OUTER_HEADERS];
+		if (s->hdrs == ICE_FLOW_SEG_HDR_NONE)
+			return ICE_RSS_INNER_HEADERS;
+		if (s->hdrs & ICE_FLOW_SEG_HDR_IPV4)
+			return ICE_RSS_INNER_HEADERS_W_OUTER_IPV4;
+		if (s->hdrs & ICE_FLOW_SEG_HDR_IPV6)
+			return ICE_RSS_INNER_HEADERS_W_OUTER_IPV6;
+	}
+
+	return ICE_RSS_ANY_HEADERS;
+}
+
+static bool
+ice_rss_match_prof(struct ice_rss_cfg *r, struct ice_flow_prof *prof,
+		   enum ice_rss_cfg_hdr_type hdr_type)
+{
+	return (r->hash.hdr_type == hdr_type &&
+		r->hash.hash_flds == prof->segs[prof->segs_cnt - 1].match &&
+		r->hash.addl_hdrs == prof->segs[prof->segs_cnt - 1].hdrs);
+}
+
+/**
  * ice_rem_rss_list - remove RSS configuration from list
  * @hw: pointer to the hardware structure
  * @vsi_handle: software VSI handle
@@ -1966,15 +2028,16 @@ int ice_rem_vsi_rss_cfg(struct ice_hw *hw, u16 vsi_handle)
 static void
 ice_rem_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof)
 {
+	enum ice_rss_cfg_hdr_type hdr_type;
 	struct ice_rss_cfg *r, *tmp;
 
 	/* Search for RSS hash fields associated to the VSI that match the
 	 * hash configurations associated to the flow profile. If found
 	 * remove from the RSS entry list of the VSI context and delete entry.
 	 */
+	hdr_type = ice_get_rss_hdr_type(prof);
 	list_for_each_entry_safe(r, tmp, &hw->rss_list_head, l_entry)
-		if (r->hashed_flds == prof->segs[prof->segs_cnt - 1].match &&
-		    r->packet_hdr == prof->segs[prof->segs_cnt - 1].hdrs) {
+		if (ice_rss_match_prof(r, prof, hdr_type)) {
 			clear_bit(vsi_handle, r->vsis);
 			if (bitmap_empty(r->vsis, ICE_MAX_VSI)) {
 				list_del(&r->l_entry);
@@ -1995,11 +2058,12 @@ ice_rem_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof)
 static int
 ice_add_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof)
 {
+	enum ice_rss_cfg_hdr_type hdr_type;
 	struct ice_rss_cfg *r, *rss_cfg;
 
+	hdr_type = ice_get_rss_hdr_type(prof);
 	list_for_each_entry(r, &hw->rss_list_head, l_entry)
-		if (r->hashed_flds == prof->segs[prof->segs_cnt - 1].match &&
-		    r->packet_hdr == prof->segs[prof->segs_cnt - 1].hdrs) {
+		if (ice_rss_match_prof(r, prof, hdr_type)) {
 			set_bit(vsi_handle, r->vsis);
 			return 0;
 		}
@@ -2009,8 +2073,10 @@ ice_add_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof)
 	if (!rss_cfg)
 		return -ENOMEM;
 
-	rss_cfg->hashed_flds = prof->segs[prof->segs_cnt - 1].match;
-	rss_cfg->packet_hdr = prof->segs[prof->segs_cnt - 1].hdrs;
+	rss_cfg->hash.hash_flds = prof->segs[prof->segs_cnt - 1].match;
+	rss_cfg->hash.addl_hdrs = prof->segs[prof->segs_cnt - 1].hdrs;
+	rss_cfg->hash.hdr_type = hdr_type;
+	rss_cfg->hash.symm = prof->symm;
 	set_bit(vsi_handle, rss_cfg->vsis);
 
 	list_add_tail(&rss_cfg->l_entry, &hw->rss_list_head);
@@ -2018,65 +2084,177 @@ ice_add_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof)
 	return 0;
 }
 
-#define ICE_FLOW_PROF_HASH_S	0
-#define ICE_FLOW_PROF_HASH_M	(0xFFFFFFFFULL << ICE_FLOW_PROF_HASH_S)
-#define ICE_FLOW_PROF_HDR_S	32
-#define ICE_FLOW_PROF_HDR_M	(0x3FFFFFFFULL << ICE_FLOW_PROF_HDR_S)
-#define ICE_FLOW_PROF_ENCAP_S	63
-#define ICE_FLOW_PROF_ENCAP_M	(BIT_ULL(ICE_FLOW_PROF_ENCAP_S))
+/**
+ * ice_rss_config_xor_word - set the HSYMM registers for one input set word
+ * @hw: pointer to the hardware structure
+ * @prof_id: RSS hardware profile id
+ * @src: the FV index used by the protocol's source field
+ * @dst: the FV index used by the protocol's destination field
+ *
+ * Write to the HSYMM register with the index of @src FV the value of the @dst
+ * FV index. This will tell the hardware to XOR HSYMM[src] with INSET[dst]
+ * while calculating the RSS input set.
+ */
+static void
+ice_rss_config_xor_word(struct ice_hw *hw, u8 prof_id, u8 src, u8 dst)
+{
+	u32 val, reg, bits_shift;
+	u8 reg_idx;
+
+	reg_idx = src / GLQF_HSYMM_REG_SIZE;
+	bits_shift = ((src % GLQF_HSYMM_REG_SIZE) << 3);
+	val = dst | GLQF_HSYMM_ENABLE_BIT;
+
+	reg = rd32(hw, GLQF_HSYMM(prof_id, reg_idx));
+	reg = (reg & ~(0xff << bits_shift)) | (val << bits_shift);
+	wr32(hw, GLQF_HSYMM(prof_id, reg_idx), reg);
+}
 
-#define ICE_RSS_OUTER_HEADERS	1
-#define ICE_RSS_INNER_HEADERS	2
+/**
+ * ice_rss_config_xor - set the symmetric registers for a profile's protocol
+ * @hw: pointer to the hardware structure
+ * @prof_id: RSS hardware profile id
+ * @src: the FV index used by the protocol's source field
+ * @dst: the FV index used by the protocol's destination field
+ * @len: length of the source/destination fields in words
+ */
+static void
+ice_rss_config_xor(struct ice_hw *hw, u8 prof_id, u8 src, u8 dst, u8 len)
+{
+	int fv_last_word =
+		ICE_FLOW_SW_FIELD_VECTOR_MAX / ICE_FLOW_FV_EXTRACT_SZ - 1;
+	int i;
+
+	for (i = 0; i < len; i++) {
+		ice_rss_config_xor_word(hw, prof_id,
+					/* Yes, field vector in GLQF_HSYMM and
+					 * GLQF_HINSET is inversed!
+					 */
+					fv_last_word - (src + i),
+					fv_last_word - (dst + i));
+		ice_rss_config_xor_word(hw, prof_id,
+					fv_last_word - (dst + i),
+					fv_last_word - (src + i));
+	}
+}
 
-/* Flow profile ID format:
- * [0:31] - Packet match fields
- * [32:62] - Protocol header
- * [63] - Encapsulation flag, 0 if non-tunneled, 1 if tunneled
+/**
+ * ice_rss_set_symm - set the symmetric settings for an RSS profile
+ * @hw: pointer to the hardware structure
+ * @prof: pointer to flow profile
+ *
+ * The symmetric hash will result from XORing the protocol's fields with
+ * indexes in GLQF_HSYMM and GLQF_HINSET. This function configures the profile's
+ * GLQF_HSYMM registers.
  */
-#define ICE_FLOW_GEN_PROFID(hash, hdr, segs_cnt) \
-	((u64)(((u64)(hash) & ICE_FLOW_PROF_HASH_M) | \
-	       (((u64)(hdr) << ICE_FLOW_PROF_HDR_S) & ICE_FLOW_PROF_HDR_M) | \
-	       ((u8)((segs_cnt) - 1) ? ICE_FLOW_PROF_ENCAP_M : 0)))
+static void ice_rss_set_symm(struct ice_hw *hw, struct ice_flow_prof *prof)
+{
+	struct ice_prof_map *map;
+	u8 prof_id, m;
+
+	mutex_lock(&hw->blk[ICE_BLK_RSS].es.prof_map_lock);
+	map = ice_search_prof_id(hw, ICE_BLK_RSS, prof->id);
+	if (map)
+		prof_id = map->prof_id;
+	mutex_unlock(&hw->blk[ICE_BLK_RSS].es.prof_map_lock);
+
+	if (!map)
+		return;
+
+	/* clear to default */
+	for (m = 0; m < GLQF_HSYMM_REG_PER_PROF; m++)
+		wr32(hw, GLQF_HSYMM(prof_id, m), 0);
+
+	if (prof->symm) {
+		struct ice_flow_seg_xtrct *ipv4_src, *ipv4_dst;
+		struct ice_flow_seg_xtrct *ipv6_src, *ipv6_dst;
+		struct ice_flow_seg_xtrct *sctp_src, *sctp_dst;
+		struct ice_flow_seg_xtrct *tcp_src, *tcp_dst;
+		struct ice_flow_seg_xtrct *udp_src, *udp_dst;
+		struct ice_flow_seg_info *seg;
+
+		seg = &prof->segs[prof->segs_cnt - 1];
+
+		ipv4_src = &seg->fields[ICE_FLOW_FIELD_IDX_IPV4_SA].xtrct;
+		ipv4_dst = &seg->fields[ICE_FLOW_FIELD_IDX_IPV4_DA].xtrct;
+
+		ipv6_src = &seg->fields[ICE_FLOW_FIELD_IDX_IPV6_SA].xtrct;
+		ipv6_dst = &seg->fields[ICE_FLOW_FIELD_IDX_IPV6_DA].xtrct;
+
+		tcp_src = &seg->fields[ICE_FLOW_FIELD_IDX_TCP_SRC_PORT].xtrct;
+		tcp_dst = &seg->fields[ICE_FLOW_FIELD_IDX_TCP_DST_PORT].xtrct;
+
+		udp_src = &seg->fields[ICE_FLOW_FIELD_IDX_UDP_SRC_PORT].xtrct;
+		udp_dst = &seg->fields[ICE_FLOW_FIELD_IDX_UDP_DST_PORT].xtrct;
+
+		sctp_src = &seg->fields[ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT].xtrct;
+		sctp_dst = &seg->fields[ICE_FLOW_FIELD_IDX_SCTP_DST_PORT].xtrct;
+
+		/* xor IPv4 */
+		if (ipv4_src->prot_id != 0 && ipv4_dst->prot_id != 0)
+			ice_rss_config_xor(hw, prof_id,
+					   ipv4_src->idx, ipv4_dst->idx, 2);
+
+		/* xor IPv6 */
+		if (ipv6_src->prot_id != 0 && ipv6_dst->prot_id != 0)
+			ice_rss_config_xor(hw, prof_id,
+					   ipv6_src->idx, ipv6_dst->idx, 8);
+
+		/* xor TCP */
+		if (tcp_src->prot_id != 0 && tcp_dst->prot_id != 0)
+			ice_rss_config_xor(hw, prof_id,
+					   tcp_src->idx, tcp_dst->idx, 1);
+
+		/* xor UDP */
+		if (udp_src->prot_id != 0 && udp_dst->prot_id != 0)
+			ice_rss_config_xor(hw, prof_id,
+					   udp_src->idx, udp_dst->idx, 1);
+
+		/* xor SCTP */
+		if (sctp_src->prot_id != 0 && sctp_dst->prot_id != 0)
+			ice_rss_config_xor(hw, prof_id,
+					   sctp_src->idx, sctp_dst->idx, 1);
+	}
+}
 
 /**
  * ice_add_rss_cfg_sync - add an RSS configuration
  * @hw: pointer to the hardware structure
  * @vsi_handle: software VSI handle
- * @hashed_flds: hash bit fields (ICE_FLOW_HASH_*) to configure
- * @addl_hdrs: protocol header fields
- * @segs_cnt: packet segment count
+ * @cfg: configure parameters
  *
  * Assumption: lock has already been acquired for RSS list
  */
 static int
-ice_add_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
-		     u32 addl_hdrs, u8 segs_cnt)
+ice_add_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle,
+		     const struct ice_rss_hash_cfg *cfg)
 {
 	const enum ice_block blk = ICE_BLK_RSS;
 	struct ice_flow_prof *prof = NULL;
 	struct ice_flow_seg_info *segs;
+	u8 segs_cnt;
 	int status;
 
-	if (!segs_cnt || segs_cnt > ICE_FLOW_SEG_MAX)
-		return -EINVAL;
+	segs_cnt = (cfg->hdr_type == ICE_RSS_OUTER_HEADERS) ?
+			ICE_FLOW_SEG_SINGLE : ICE_FLOW_SEG_MAX;
 
 	segs = kcalloc(segs_cnt, sizeof(*segs), GFP_KERNEL);
 	if (!segs)
 		return -ENOMEM;
 
 	/* Construct the packet segment info from the hashed fields */
-	status = ice_flow_set_rss_seg_info(&segs[segs_cnt - 1], hashed_flds,
-					   addl_hdrs);
+	status = ice_flow_set_rss_seg_info(segs, segs_cnt, cfg);
 	if (status)
 		goto exit;
 
-	/* Search for a flow profile that has matching headers, hash fields
-	 * and has the input VSI associated to it. If found, no further
+	/* Search for a flow profile that has matching headers, hash fields,
+	 * symm and has the input VSI associated to it. If found, no further
 	 * operations required and exit.
 	 */
 	prof = ice_flow_find_prof_conds(hw, blk, ICE_FLOW_RX, segs, segs_cnt,
-					vsi_handle,
+					cfg->symm, vsi_handle,
 					ICE_FLOW_FIND_PROF_CHK_FLDS |
+					ICE_FLOW_FIND_PROF_CHK_SYMM |
 					ICE_FLOW_FIND_PROF_CHK_VSI);
 	if (prof)
 		goto exit;
@@ -2087,7 +2265,8 @@ ice_add_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
 	 * the protocol header and new hash field configuration.
 	 */
 	prof = ice_flow_find_prof_conds(hw, blk, ICE_FLOW_RX, segs, segs_cnt,
-					vsi_handle, ICE_FLOW_FIND_PROF_CHK_VSI);
+					cfg->symm, vsi_handle,
+					ICE_FLOW_FIND_PROF_CHK_VSI);
 	if (prof) {
 		status = ice_flow_disassoc_prof(hw, blk, prof, vsi_handle);
 		if (!status)
@@ -2103,11 +2282,12 @@ ice_add_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
 		}
 	}
 
-	/* Search for a profile that has same match fields only. If this
-	 * exists then associate the VSI to this profile.
+	/* Search for a profile that has the same match fields and symmetric
+	 * setting. If this exists then associate the VSI to this profile.
 	 */
 	prof = ice_flow_find_prof_conds(hw, blk, ICE_FLOW_RX, segs, segs_cnt,
-					vsi_handle,
+					cfg->symm, vsi_handle,
+					ICE_FLOW_FIND_PROF_CHK_SYMM |
 					ICE_FLOW_FIND_PROF_CHK_FLDS);
 	if (prof) {
 		status = ice_flow_assoc_prof(hw, blk, prof, vsi_handle);
@@ -2116,17 +2296,14 @@ ice_add_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
 		goto exit;
 	}
 
-	/* Create a new flow profile with generated profile and packet
-	 * segment information.
-	 */
+	/* Create a new flow profile with packet segment information. */
 	status = ice_flow_add_prof(hw, blk, ICE_FLOW_RX,
-				   ICE_FLOW_GEN_PROFID(hashed_flds,
-						       segs[segs_cnt - 1].hdrs,
-						       segs_cnt),
-				   segs, segs_cnt, &prof);
+				   segs, segs_cnt, cfg->symm, &prof);
 	if (status)
 		goto exit;
 
+	prof->symm = cfg->symm;
+	ice_rss_set_symm(hw, prof);
 	status = ice_flow_assoc_prof(hw, blk, prof, vsi_handle);
 	/* If association to a new flow profile failed then this profile can
 	 * be removed.
@@ -2146,30 +2323,43 @@ exit:
 /**
  * ice_add_rss_cfg - add an RSS configuration with specified hashed fields
  * @hw: pointer to the hardware structure
- * @vsi_handle: software VSI handle
- * @hashed_flds: hash bit fields (ICE_FLOW_HASH_*) to configure
- * @addl_hdrs: protocol header fields
+ * @vsi: VSI to add the RSS configuration to
+ * @cfg: configure parameters
  *
  * This function will generate a flow profile based on fields associated with
  * the input fields to hash on, the flow type and use the VSI number to add
  * a flow entry to the profile.
  */
 int
-ice_add_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
-		u32 addl_hdrs)
+ice_add_rss_cfg(struct ice_hw *hw, struct ice_vsi *vsi,
+		const struct ice_rss_hash_cfg *cfg)
 {
+	struct ice_rss_hash_cfg local_cfg;
+	u16 vsi_handle;
 	int status;
 
-	if (hashed_flds == ICE_HASH_INVALID ||
-	    !ice_is_vsi_valid(hw, vsi_handle))
+	if (!vsi)
+		return -EINVAL;
+
+	vsi_handle = vsi->idx;
+	if (!ice_is_vsi_valid(hw, vsi_handle) ||
+	    !cfg || cfg->hdr_type > ICE_RSS_ANY_HEADERS ||
+	    cfg->hash_flds == ICE_HASH_INVALID)
 		return -EINVAL;
 
 	mutex_lock(&hw->rss_locks);
-	status = ice_add_rss_cfg_sync(hw, vsi_handle, hashed_flds, addl_hdrs,
-				      ICE_RSS_OUTER_HEADERS);
-	if (!status)
-		status = ice_add_rss_cfg_sync(hw, vsi_handle, hashed_flds,
-					      addl_hdrs, ICE_RSS_INNER_HEADERS);
+	local_cfg = *cfg;
+	if (cfg->hdr_type < ICE_RSS_ANY_HEADERS) {
+		status = ice_add_rss_cfg_sync(hw, vsi_handle, &local_cfg);
+	} else {
+		local_cfg.hdr_type = ICE_RSS_OUTER_HEADERS;
+		status = ice_add_rss_cfg_sync(hw, vsi_handle, &local_cfg);
+		if (!status) {
+			local_cfg.hdr_type = ICE_RSS_INNER_HEADERS;
+			status = ice_add_rss_cfg_sync(hw, vsi_handle,
+						      &local_cfg);
+		}
+	}
 	mutex_unlock(&hw->rss_locks);
 
 	return status;
@@ -2179,33 +2369,33 @@ ice_add_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
  * ice_rem_rss_cfg_sync - remove an existing RSS configuration
  * @hw: pointer to the hardware structure
  * @vsi_handle: software VSI handle
- * @hashed_flds: Packet hash types (ICE_FLOW_HASH_*) to remove
- * @addl_hdrs: Protocol header fields within a packet segment
- * @segs_cnt: packet segment count
+ * @cfg: configure parameters
  *
  * Assumption: lock has already been acquired for RSS list
  */
 static int
-ice_rem_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
-		     u32 addl_hdrs, u8 segs_cnt)
+ice_rem_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle,
+		     const struct ice_rss_hash_cfg *cfg)
 {
 	const enum ice_block blk = ICE_BLK_RSS;
 	struct ice_flow_seg_info *segs;
 	struct ice_flow_prof *prof;
+	u8 segs_cnt;
 	int status;
 
+	segs_cnt = (cfg->hdr_type == ICE_RSS_OUTER_HEADERS) ?
+			ICE_FLOW_SEG_SINGLE : ICE_FLOW_SEG_MAX;
 	segs = kcalloc(segs_cnt, sizeof(*segs), GFP_KERNEL);
 	if (!segs)
 		return -ENOMEM;
 
 	/* Construct the packet segment info from the hashed fields */
-	status = ice_flow_set_rss_seg_info(&segs[segs_cnt - 1], hashed_flds,
-					   addl_hdrs);
+	status = ice_flow_set_rss_seg_info(segs, segs_cnt, cfg);
 	if (status)
 		goto out;
 
 	prof = ice_flow_find_prof_conds(hw, blk, ICE_FLOW_RX, segs, segs_cnt,
-					vsi_handle,
+					cfg->symm, vsi_handle,
 					ICE_FLOW_FIND_PROF_CHK_FLDS);
 	if (!prof) {
 		status = -ENOENT;
@@ -2233,31 +2423,39 @@ out:
  * ice_rem_rss_cfg - remove an existing RSS config with matching hashed fields
  * @hw: pointer to the hardware structure
  * @vsi_handle: software VSI handle
- * @hashed_flds: Packet hash types (ICE_FLOW_HASH_*) to remove
- * @addl_hdrs: Protocol header fields within a packet segment
+ * @cfg: configure parameters
  *
  * This function will lookup the flow profile based on the input
  * hash field bitmap, iterate through the profile entry list of
  * that profile and find entry associated with input VSI to be
- * removed. Calls are made to underlying flow s which will APIs
+ * removed. Calls are made to underlying flow apis which will in
  * turn build or update buffers for RSS XLT1 section.
  */
-int __maybe_unused
-ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
-		u32 addl_hdrs)
+int
+ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle,
+		const struct ice_rss_hash_cfg *cfg)
 {
+	struct ice_rss_hash_cfg local_cfg;
 	int status;
 
-	if (hashed_flds == ICE_HASH_INVALID ||
-	    !ice_is_vsi_valid(hw, vsi_handle))
+	if (!ice_is_vsi_valid(hw, vsi_handle) ||
+	    !cfg || cfg->hdr_type > ICE_RSS_ANY_HEADERS ||
+	    cfg->hash_flds == ICE_HASH_INVALID)
 		return -EINVAL;
 
 	mutex_lock(&hw->rss_locks);
-	status = ice_rem_rss_cfg_sync(hw, vsi_handle, hashed_flds, addl_hdrs,
-				      ICE_RSS_OUTER_HEADERS);
-	if (!status)
-		status = ice_rem_rss_cfg_sync(hw, vsi_handle, hashed_flds,
-					      addl_hdrs, ICE_RSS_INNER_HEADERS);
+	local_cfg = *cfg;
+	if (cfg->hdr_type < ICE_RSS_ANY_HEADERS) {
+		status = ice_rem_rss_cfg_sync(hw, vsi_handle, &local_cfg);
+	} else {
+		local_cfg.hdr_type = ICE_RSS_OUTER_HEADERS;
+		status = ice_rem_rss_cfg_sync(hw, vsi_handle, &local_cfg);
+		if (!status) {
+			local_cfg.hdr_type = ICE_RSS_INNER_HEADERS;
+			status = ice_rem_rss_cfg_sync(hw, vsi_handle,
+						      &local_cfg);
+		}
+	}
 	mutex_unlock(&hw->rss_locks);
 
 	return status;
@@ -2298,18 +2496,24 @@ ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
 /**
  * ice_add_avf_rss_cfg - add an RSS configuration for AVF driver
  * @hw: pointer to the hardware structure
- * @vsi_handle: software VSI handle
+ * @vsi: VF's VSI
  * @avf_hash: hash bit fields (ICE_AVF_FLOW_FIELD_*) to configure
  *
  * This function will take the hash bitmap provided by the AVF driver via a
  * message, convert it to ICE-compatible values, and configure RSS flow
  * profiles.
  */
-int ice_add_avf_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 avf_hash)
+int ice_add_avf_rss_cfg(struct ice_hw *hw, struct ice_vsi *vsi, u64 avf_hash)
 {
+	struct ice_rss_hash_cfg hcfg;
+	u16 vsi_handle;
 	int status = 0;
 	u64 hash_flds;
 
+	if (!vsi)
+		return -EINVAL;
+
+	vsi_handle = vsi->idx;
 	if (avf_hash == ICE_AVF_FLOW_FIELD_INVALID ||
 	    !ice_is_vsi_valid(hw, vsi_handle))
 		return -EINVAL;
@@ -2379,8 +2583,11 @@ int ice_add_avf_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 avf_hash)
 		if (rss_hash == ICE_HASH_INVALID)
 			return -EIO;
 
-		status = ice_add_rss_cfg(hw, vsi_handle, rss_hash,
-					 ICE_FLOW_SEG_HDR_NONE);
+		hcfg.addl_hdrs = ICE_FLOW_SEG_HDR_NONE;
+		hcfg.hash_flds = rss_hash;
+		hcfg.hdr_type = ICE_RSS_ANY_HEADERS;
+		hcfg.symm = false;
+		status = ice_add_rss_cfg(hw, vsi, &hcfg);
 		if (status)
 			break;
 	}
@@ -2388,6 +2595,54 @@ int ice_add_avf_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 avf_hash)
 	return status;
 }
 
+static bool rss_cfg_symm_valid(u64 hfld)
+{
+	return !((!!(hfld & ICE_FLOW_HASH_FLD_IPV4_SA) ^
+		  !!(hfld & ICE_FLOW_HASH_FLD_IPV4_DA)) ||
+		 (!!(hfld & ICE_FLOW_HASH_FLD_IPV6_SA) ^
+		  !!(hfld & ICE_FLOW_HASH_FLD_IPV6_DA)) ||
+		 (!!(hfld & ICE_FLOW_HASH_FLD_TCP_SRC_PORT) ^
+		  !!(hfld & ICE_FLOW_HASH_FLD_TCP_DST_PORT)) ||
+		 (!!(hfld & ICE_FLOW_HASH_FLD_UDP_SRC_PORT) ^
+		  !!(hfld & ICE_FLOW_HASH_FLD_UDP_DST_PORT)) ||
+		 (!!(hfld & ICE_FLOW_HASH_FLD_SCTP_SRC_PORT) ^
+		  !!(hfld & ICE_FLOW_HASH_FLD_SCTP_DST_PORT)));
+}
+
+/**
+ * ice_set_rss_cfg_symm - set symmtery for all VSI's RSS configurations
+ * @hw: pointer to the hardware structure
+ * @vsi: VSI to set/unset Symmetric RSS
+ * @symm: TRUE to set Symmetric RSS hashing
+ */
+int ice_set_rss_cfg_symm(struct ice_hw *hw, struct ice_vsi *vsi, bool symm)
+{
+	struct ice_rss_hash_cfg	local;
+	struct ice_rss_cfg *r, *tmp;
+	u16 vsi_handle = vsi->idx;
+	int status = 0;
+
+	if (!ice_is_vsi_valid(hw, vsi_handle))
+		return -EINVAL;
+
+	mutex_lock(&hw->rss_locks);
+	list_for_each_entry_safe(r, tmp, &hw->rss_list_head, l_entry) {
+		if (test_bit(vsi_handle, r->vsis) && r->hash.symm != symm) {
+			local = r->hash;
+			local.symm = symm;
+			if (symm && !rss_cfg_symm_valid(r->hash.hash_flds))
+				continue;
+
+			status = ice_add_rss_cfg_sync(hw, vsi_handle, &local);
+			if (status)
+				break;
+		}
+	}
+	mutex_unlock(&hw->rss_locks);
+
+	return status;
+}
+
 /**
  * ice_replay_rss_cfg - replay RSS configurations associated with VSI
  * @hw: pointer to the hardware structure
@@ -2404,16 +2659,7 @@ int ice_replay_rss_cfg(struct ice_hw *hw, u16 vsi_handle)
 	mutex_lock(&hw->rss_locks);
 	list_for_each_entry(r, &hw->rss_list_head, l_entry) {
 		if (test_bit(vsi_handle, r->vsis)) {
-			status = ice_add_rss_cfg_sync(hw, vsi_handle,
-						      r->hashed_flds,
-						      r->packet_hdr,
-						      ICE_RSS_OUTER_HEADERS);
-			if (status)
-				break;
-			status = ice_add_rss_cfg_sync(hw, vsi_handle,
-						      r->hashed_flds,
-						      r->packet_hdr,
-						      ICE_RSS_INNER_HEADERS);
+			status = ice_add_rss_cfg_sync(hw, vsi_handle, &r->hash);
 			if (status)
 				break;
 		}
@@ -2428,11 +2674,12 @@ int ice_replay_rss_cfg(struct ice_hw *hw, u16 vsi_handle)
  * @hw: pointer to the hardware structure
  * @vsi_handle: software VSI handle
  * @hdrs: protocol header type
+ * @symm: whether the RSS is symmetric (bool, output)
  *
  * This function will return the match fields of the first instance of flow
  * profile having the given header types and containing input VSI
  */
-u64 ice_get_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u32 hdrs)
+u64 ice_get_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u32 hdrs, bool *symm)
 {
 	u64 rss_hash = ICE_HASH_INVALID;
 	struct ice_rss_cfg *r;
@@ -2444,8 +2691,9 @@ u64 ice_get_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u32 hdrs)
 	mutex_lock(&hw->rss_locks);
 	list_for_each_entry(r, &hw->rss_list_head, l_entry)
 		if (test_bit(vsi_handle, r->vsis) &&
-		    r->packet_hdr == hdrs) {
-			rss_hash = r->hashed_flds;
+		    r->hash.addl_hdrs == hdrs) {
+			rss_hash = r->hash.hash_flds;
+			*symm = r->hash.symm;
 			break;
 		}
 	mutex_unlock(&hw->rss_locks);
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h
index 96923ef0a5a8..ff82915ab497 100644
--- a/drivers/net/ethernet/intel/ice/ice_flow.h
+++ b/drivers/net/ethernet/intel/ice/ice_flow.h
@@ -34,6 +34,8 @@
 #define ICE_HASH_TCP_IPV6	(ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_TCP_PORT)
 #define ICE_HASH_UDP_IPV4	(ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_UDP_PORT)
 #define ICE_HASH_UDP_IPV6	(ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_UDP_PORT)
+#define ICE_HASH_SCTP_IPV4	(ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_SCTP_PORT)
+#define ICE_HASH_SCTP_IPV6	(ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_SCTP_PORT)
 
 #define ICE_FLOW_HASH_GTP_TEID \
 	(BIT_ULL(ICE_FLOW_FIELD_IDX_GTPC_TEID))
@@ -227,6 +229,19 @@ enum ice_flow_field {
 	ICE_FLOW_FIELD_IDX_MAX
 };
 
+#define ICE_FLOW_HASH_FLD_IPV4_SA	BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA)
+#define ICE_FLOW_HASH_FLD_IPV6_SA	BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA)
+#define ICE_FLOW_HASH_FLD_IPV4_DA	BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA)
+#define ICE_FLOW_HASH_FLD_IPV6_DA	BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA)
+#define ICE_FLOW_HASH_FLD_TCP_SRC_PORT	BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_SRC_PORT)
+#define ICE_FLOW_HASH_FLD_TCP_DST_PORT	BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_DST_PORT)
+#define ICE_FLOW_HASH_FLD_UDP_SRC_PORT	BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_SRC_PORT)
+#define ICE_FLOW_HASH_FLD_UDP_DST_PORT	BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_DST_PORT)
+#define ICE_FLOW_HASH_FLD_SCTP_SRC_PORT	\
+	BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT)
+#define ICE_FLOW_HASH_FLD_SCTP_DST_PORT	\
+	BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_DST_PORT)
+
 /* Flow headers and fields for AVF support */
 enum ice_flow_avf_hdr_field {
 	/* Values 0 - 28 are reserved for future use */
@@ -279,6 +294,24 @@ enum ice_flow_avf_hdr_field {
 	BIT_ULL(ICE_AVF_FLOW_FIELD_UNICAST_IPV6_UDP) | \
 	BIT_ULL(ICE_AVF_FLOW_FIELD_MULTICAST_IPV6_UDP))
 
+enum ice_rss_cfg_hdr_type {
+	ICE_RSS_OUTER_HEADERS, /* take outer headers as inputset. */
+	ICE_RSS_INNER_HEADERS, /* take inner headers as inputset. */
+	/* take inner headers as inputset for packet with outer ipv4. */
+	ICE_RSS_INNER_HEADERS_W_OUTER_IPV4,
+	/* take inner headers as inputset for packet with outer ipv6. */
+	ICE_RSS_INNER_HEADERS_W_OUTER_IPV6,
+	/* take outer headers first then inner headers as inputset */
+	ICE_RSS_ANY_HEADERS
+};
+
+struct ice_rss_hash_cfg {
+	u32 addl_hdrs; /* protocol header fields */
+	u64 hash_flds; /* hash bit field (ICE_FLOW_HASH_*) to configure */
+	enum ice_rss_cfg_hdr_type hdr_type; /* to specify inner or outer */
+	bool symm; /* symmetric or asymmetric hash */
+};
+
 enum ice_flow_dir {
 	ICE_FLOW_RX		= 0x02,
 };
@@ -289,8 +322,10 @@ enum ice_flow_priority {
 	ICE_FLOW_PRIO_HIGH
 };
 
+#define ICE_FLOW_SEG_SINGLE		1
 #define ICE_FLOW_SEG_MAX		2
 #define ICE_FLOW_SEG_RAW_FLD_MAX	2
+#define ICE_FLOW_SW_FIELD_VECTOR_MAX	48
 #define ICE_FLOW_FV_EXTRACT_SZ		2
 
 #define ICE_FLOW_SET_HDRS(seg, val)	((seg)->hdrs |= (u32)(val))
@@ -372,20 +407,21 @@ struct ice_flow_prof {
 
 	/* software VSI handles referenced by this flow profile */
 	DECLARE_BITMAP(vsis, ICE_MAX_VSI);
+
+	bool symm; /* Symmetric Hash for RSS */
 };
 
 struct ice_rss_cfg {
 	struct list_head l_entry;
 	/* bitmap of VSIs added to the RSS entry */
 	DECLARE_BITMAP(vsis, ICE_MAX_VSI);
-	u64 hashed_flds;
-	u32 packet_hdr;
+	struct ice_rss_hash_cfg hash;
 };
 
 int
 ice_flow_add_prof(struct ice_hw *hw, enum ice_block blk, enum ice_flow_dir dir,
-		  u64 prof_id, struct ice_flow_seg_info *segs, u8 segs_cnt,
-		  struct ice_flow_prof **prof);
+		  struct ice_flow_seg_info *segs, u8 segs_cnt,
+		  bool symm, struct ice_flow_prof **prof);
 int ice_flow_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 prof_id);
 int
 ice_flow_add_entry(struct ice_hw *hw, enum ice_block blk, u64 prof_id,
@@ -401,13 +437,13 @@ ice_flow_add_fld_raw(struct ice_flow_seg_info *seg, u16 off, u8 len,
 int ice_flow_rem_vsi_prof(struct ice_hw *hw, u16 vsi_handle, u64 prof_id);
 void ice_rem_vsi_rss_list(struct ice_hw *hw, u16 vsi_handle);
 int ice_replay_rss_cfg(struct ice_hw *hw, u16 vsi_handle);
-int ice_add_avf_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds);
+int ice_set_rss_cfg_symm(struct ice_hw *hw, struct ice_vsi *vsi, bool symm);
+int ice_add_avf_rss_cfg(struct ice_hw *hw, struct ice_vsi *vsi,
+			u64 hashed_flds);
 int ice_rem_vsi_rss_cfg(struct ice_hw *hw, u16 vsi_handle);
-int
-ice_add_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
-		u32 addl_hdrs);
-int
-ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
-		u32 addl_hdrs);
-u64 ice_get_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u32 hdrs);
+int ice_add_rss_cfg(struct ice_hw *hw, struct ice_vsi *vsi,
+		    const struct ice_rss_hash_cfg *cfg);
+int ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle,
+		    const struct ice_rss_hash_cfg *cfg);
+u64 ice_get_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u32 hdrs, bool *symm);
 #endif /* _ICE_FLOW_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_fwlog.c b/drivers/net/ethernet/intel/ice/ice_fwlog.c
new file mode 100644
index 000000000000..92b5dac481cd
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_fwlog.c
@@ -0,0 +1,470 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022, Intel Corporation. */
+
+#include <linux/vmalloc.h>
+#include "ice.h"
+#include "ice_common.h"
+#include "ice_fwlog.h"
+
+bool ice_fwlog_ring_full(struct ice_fwlog_ring *rings)
+{
+	u16 head, tail;
+
+	head = rings->head;
+	tail = rings->tail;
+
+	if (head < tail && (tail - head == (rings->size - 1)))
+		return true;
+	else if (head > tail && (tail == (head - 1)))
+		return true;
+
+	return false;
+}
+
+bool ice_fwlog_ring_empty(struct ice_fwlog_ring *rings)
+{
+	return rings->head == rings->tail;
+}
+
+void ice_fwlog_ring_increment(u16 *item, u16 size)
+{
+	*item = (*item + 1) & (size - 1);
+}
+
+static int ice_fwlog_alloc_ring_buffs(struct ice_fwlog_ring *rings)
+{
+	int i, nr_bytes;
+	u8 *mem;
+
+	nr_bytes = rings->size * ICE_AQ_MAX_BUF_LEN;
+	mem = vzalloc(nr_bytes);
+	if (!mem)
+		return -ENOMEM;
+
+	for (i = 0; i < rings->size; i++) {
+		struct ice_fwlog_data *ring = &rings->rings[i];
+
+		ring->data_size = ICE_AQ_MAX_BUF_LEN;
+		ring->data = mem;
+		mem += ICE_AQ_MAX_BUF_LEN;
+	}
+
+	return 0;
+}
+
+static void ice_fwlog_free_ring_buffs(struct ice_fwlog_ring *rings)
+{
+	int i;
+
+	for (i = 0; i < rings->size; i++) {
+		struct ice_fwlog_data *ring = &rings->rings[i];
+
+		/* the first ring is the base memory for the whole range so
+		 * free it
+		 */
+		if (!i)
+			vfree(ring->data);
+
+		ring->data = NULL;
+		ring->data_size = 0;
+	}
+}
+
+#define ICE_FWLOG_INDEX_TO_BYTES(n) ((128 * 1024) << (n))
+/**
+ * ice_fwlog_realloc_rings - reallocate the FW log rings
+ * @hw: pointer to the HW structure
+ * @index: the new index to use to allocate memory for the log data
+ *
+ */
+void ice_fwlog_realloc_rings(struct ice_hw *hw, int index)
+{
+	struct ice_fwlog_ring ring;
+	int status, ring_size;
+
+	/* convert the number of bytes into a number of 4K buffers. externally
+	 * the driver presents the interface to the FW log data as a number of
+	 * bytes because that's easy for users to understand. internally the
+	 * driver uses a ring of buffers because the driver doesn't know where
+	 * the beginning and end of any line of log data is so the driver has
+	 * to overwrite data as complete blocks. when the data is returned to
+	 * the user the driver knows that the data is correct and the FW log
+	 * can be correctly parsed by the tools
+	 */
+	ring_size = ICE_FWLOG_INDEX_TO_BYTES(index) / ICE_AQ_MAX_BUF_LEN;
+	if (ring_size == hw->fwlog_ring.size)
+		return;
+
+	/* allocate space for the new rings and buffers then release the
+	 * old rings and buffers. that way if we don't have enough
+	 * memory then we at least have what we had before
+	 */
+	ring.rings = kcalloc(ring_size, sizeof(*ring.rings), GFP_KERNEL);
+	if (!ring.rings)
+		return;
+
+	ring.size = ring_size;
+
+	status = ice_fwlog_alloc_ring_buffs(&ring);
+	if (status) {
+		dev_warn(ice_hw_to_dev(hw), "Unable to allocate memory for FW log ring data buffers\n");
+		ice_fwlog_free_ring_buffs(&ring);
+		kfree(ring.rings);
+		return;
+	}
+
+	ice_fwlog_free_ring_buffs(&hw->fwlog_ring);
+	kfree(hw->fwlog_ring.rings);
+
+	hw->fwlog_ring.rings = ring.rings;
+	hw->fwlog_ring.size = ring.size;
+	hw->fwlog_ring.index = index;
+	hw->fwlog_ring.head = 0;
+	hw->fwlog_ring.tail = 0;
+}
+
+/**
+ * ice_fwlog_init - Initialize FW logging configuration
+ * @hw: pointer to the HW structure
+ *
+ * This function should be called on driver initialization during
+ * ice_init_hw().
+ */
+int ice_fwlog_init(struct ice_hw *hw)
+{
+	/* only support fw log commands on PF 0 */
+	if (hw->bus.func)
+		return -EINVAL;
+
+	ice_fwlog_set_supported(hw);
+
+	if (ice_fwlog_supported(hw)) {
+		int status;
+
+		/* read the current config from the FW and store it */
+		status = ice_fwlog_get(hw, &hw->fwlog_cfg);
+		if (status)
+			return status;
+
+		hw->fwlog_ring.rings = kcalloc(ICE_FWLOG_RING_SIZE_DFLT,
+					       sizeof(*hw->fwlog_ring.rings),
+					       GFP_KERNEL);
+		if (!hw->fwlog_ring.rings) {
+			dev_warn(ice_hw_to_dev(hw), "Unable to allocate memory for FW log rings\n");
+			return -ENOMEM;
+		}
+
+		hw->fwlog_ring.size = ICE_FWLOG_RING_SIZE_DFLT;
+		hw->fwlog_ring.index = ICE_FWLOG_RING_SIZE_INDEX_DFLT;
+
+		status = ice_fwlog_alloc_ring_buffs(&hw->fwlog_ring);
+		if (status) {
+			dev_warn(ice_hw_to_dev(hw), "Unable to allocate memory for FW log ring data buffers\n");
+			ice_fwlog_free_ring_buffs(&hw->fwlog_ring);
+			kfree(hw->fwlog_ring.rings);
+			return status;
+		}
+
+		ice_debugfs_fwlog_init(hw->back);
+	} else {
+		dev_warn(ice_hw_to_dev(hw), "FW logging is not supported in this NVM image. Please update the NVM to get FW log support\n");
+	}
+
+	return 0;
+}
+
+/**
+ * ice_fwlog_deinit - unroll FW logging configuration
+ * @hw: pointer to the HW structure
+ *
+ * This function should be called in ice_deinit_hw().
+ */
+void ice_fwlog_deinit(struct ice_hw *hw)
+{
+	struct ice_pf *pf = hw->back;
+	int status;
+
+	/* only support fw log commands on PF 0 */
+	if (hw->bus.func)
+		return;
+
+	/* make sure FW logging is disabled to not put the FW in a weird state
+	 * for the next driver load
+	 */
+	hw->fwlog_cfg.options &= ~ICE_FWLOG_OPTION_ARQ_ENA;
+	status = ice_fwlog_set(hw, &hw->fwlog_cfg);
+	if (status)
+		dev_warn(ice_hw_to_dev(hw), "Unable to turn off FW logging, status: %d\n",
+			 status);
+
+	kfree(pf->ice_debugfs_pf_fwlog_modules);
+
+	pf->ice_debugfs_pf_fwlog_modules = NULL;
+
+	status = ice_fwlog_unregister(hw);
+	if (status)
+		dev_warn(ice_hw_to_dev(hw), "Unable to unregister FW logging, status: %d\n",
+			 status);
+
+	if (hw->fwlog_ring.rings) {
+		ice_fwlog_free_ring_buffs(&hw->fwlog_ring);
+		kfree(hw->fwlog_ring.rings);
+	}
+}
+
+/**
+ * ice_fwlog_supported - Cached for whether FW supports FW logging or not
+ * @hw: pointer to the HW structure
+ *
+ * This will always return false if called before ice_init_hw(), so it must be
+ * called after ice_init_hw().
+ */
+bool ice_fwlog_supported(struct ice_hw *hw)
+{
+	return hw->fwlog_supported;
+}
+
+/**
+ * ice_aq_fwlog_set - Set FW logging configuration AQ command (0xFF30)
+ * @hw: pointer to the HW structure
+ * @entries: entries to configure
+ * @num_entries: number of @entries
+ * @options: options from ice_fwlog_cfg->options structure
+ * @log_resolution: logging resolution
+ */
+static int
+ice_aq_fwlog_set(struct ice_hw *hw, struct ice_fwlog_module_entry *entries,
+		 u16 num_entries, u16 options, u16 log_resolution)
+{
+	struct ice_aqc_fw_log_cfg_resp *fw_modules;
+	struct ice_aqc_fw_log *cmd;
+	struct ice_aq_desc desc;
+	int status;
+	int i;
+
+	fw_modules = kcalloc(num_entries, sizeof(*fw_modules), GFP_KERNEL);
+	if (!fw_modules)
+		return -ENOMEM;
+
+	for (i = 0; i < num_entries; i++) {
+		fw_modules[i].module_identifier =
+			cpu_to_le16(entries[i].module_id);
+		fw_modules[i].log_level = entries[i].log_level;
+	}
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logs_config);
+	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+
+	cmd = &desc.params.fw_log;
+
+	cmd->cmd_flags = ICE_AQC_FW_LOG_CONF_SET_VALID;
+	cmd->ops.cfg.log_resolution = cpu_to_le16(log_resolution);
+	cmd->ops.cfg.mdl_cnt = cpu_to_le16(num_entries);
+
+	if (options & ICE_FWLOG_OPTION_ARQ_ENA)
+		cmd->cmd_flags |= ICE_AQC_FW_LOG_CONF_AQ_EN;
+	if (options & ICE_FWLOG_OPTION_UART_ENA)
+		cmd->cmd_flags |= ICE_AQC_FW_LOG_CONF_UART_EN;
+
+	status = ice_aq_send_cmd(hw, &desc, fw_modules,
+				 sizeof(*fw_modules) * num_entries,
+				 NULL);
+
+	kfree(fw_modules);
+
+	return status;
+}
+
+/**
+ * ice_fwlog_set - Set the firmware logging settings
+ * @hw: pointer to the HW structure
+ * @cfg: config used to set firmware logging
+ *
+ * This function should be called whenever the driver needs to set the firmware
+ * logging configuration. It can be called on initialization, reset, or during
+ * runtime.
+ *
+ * If the PF wishes to receive FW logging then it must register via
+ * ice_fwlog_register. Note, that ice_fwlog_register does not need to be called
+ * for init.
+ */
+int ice_fwlog_set(struct ice_hw *hw, struct ice_fwlog_cfg *cfg)
+{
+	if (!ice_fwlog_supported(hw))
+		return -EOPNOTSUPP;
+
+	return ice_aq_fwlog_set(hw, cfg->module_entries,
+				ICE_AQC_FW_LOG_ID_MAX, cfg->options,
+				cfg->log_resolution);
+}
+
+/**
+ * ice_aq_fwlog_get - Get the current firmware logging configuration (0xFF32)
+ * @hw: pointer to the HW structure
+ * @cfg: firmware logging configuration to populate
+ */
+static int ice_aq_fwlog_get(struct ice_hw *hw, struct ice_fwlog_cfg *cfg)
+{
+	struct ice_aqc_fw_log_cfg_resp *fw_modules;
+	struct ice_aqc_fw_log *cmd;
+	struct ice_aq_desc desc;
+	u16 module_id_cnt;
+	int status;
+	void *buf;
+	int i;
+
+	memset(cfg, 0, sizeof(*cfg));
+
+	buf = kzalloc(ICE_AQ_MAX_BUF_LEN, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logs_query);
+	cmd = &desc.params.fw_log;
+
+	cmd->cmd_flags = ICE_AQC_FW_LOG_AQ_QUERY;
+
+	status = ice_aq_send_cmd(hw, &desc, buf, ICE_AQ_MAX_BUF_LEN, NULL);
+	if (status) {
+		ice_debug(hw, ICE_DBG_FW_LOG, "Failed to get FW log configuration\n");
+		goto status_out;
+	}
+
+	module_id_cnt = le16_to_cpu(cmd->ops.cfg.mdl_cnt);
+	if (module_id_cnt < ICE_AQC_FW_LOG_ID_MAX) {
+		ice_debug(hw, ICE_DBG_FW_LOG, "FW returned less than the expected number of FW log module IDs\n");
+	} else if (module_id_cnt > ICE_AQC_FW_LOG_ID_MAX) {
+		ice_debug(hw, ICE_DBG_FW_LOG, "FW returned more than expected number of FW log module IDs, setting module_id_cnt to software expected max %u\n",
+			  ICE_AQC_FW_LOG_ID_MAX);
+		module_id_cnt = ICE_AQC_FW_LOG_ID_MAX;
+	}
+
+	cfg->log_resolution = le16_to_cpu(cmd->ops.cfg.log_resolution);
+	if (cmd->cmd_flags & ICE_AQC_FW_LOG_CONF_AQ_EN)
+		cfg->options |= ICE_FWLOG_OPTION_ARQ_ENA;
+	if (cmd->cmd_flags & ICE_AQC_FW_LOG_CONF_UART_EN)
+		cfg->options |= ICE_FWLOG_OPTION_UART_ENA;
+	if (cmd->cmd_flags & ICE_AQC_FW_LOG_QUERY_REGISTERED)
+		cfg->options |= ICE_FWLOG_OPTION_IS_REGISTERED;
+
+	fw_modules = (struct ice_aqc_fw_log_cfg_resp *)buf;
+
+	for (i = 0; i < module_id_cnt; i++) {
+		struct ice_aqc_fw_log_cfg_resp *fw_module = &fw_modules[i];
+
+		cfg->module_entries[i].module_id =
+			le16_to_cpu(fw_module->module_identifier);
+		cfg->module_entries[i].log_level = fw_module->log_level;
+	}
+
+status_out:
+	kfree(buf);
+	return status;
+}
+
+/**
+ * ice_fwlog_get - Get the firmware logging settings
+ * @hw: pointer to the HW structure
+ * @cfg: config to populate based on current firmware logging settings
+ */
+int ice_fwlog_get(struct ice_hw *hw, struct ice_fwlog_cfg *cfg)
+{
+	if (!ice_fwlog_supported(hw))
+		return -EOPNOTSUPP;
+
+	return ice_aq_fwlog_get(hw, cfg);
+}
+
+/**
+ * ice_aq_fwlog_register - Register PF for firmware logging events (0xFF31)
+ * @hw: pointer to the HW structure
+ * @reg: true to register and false to unregister
+ */
+static int ice_aq_fwlog_register(struct ice_hw *hw, bool reg)
+{
+	struct ice_aq_desc desc;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logs_register);
+
+	if (reg)
+		desc.params.fw_log.cmd_flags = ICE_AQC_FW_LOG_AQ_REGISTER;
+
+	return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
+}
+
+/**
+ * ice_fwlog_register - Register the PF for firmware logging
+ * @hw: pointer to the HW structure
+ *
+ * After this call the PF will start to receive firmware logging based on the
+ * configuration set in ice_fwlog_set.
+ */
+int ice_fwlog_register(struct ice_hw *hw)
+{
+	int status;
+
+	if (!ice_fwlog_supported(hw))
+		return -EOPNOTSUPP;
+
+	status = ice_aq_fwlog_register(hw, true);
+	if (status)
+		ice_debug(hw, ICE_DBG_FW_LOG, "Failed to register for firmware logging events over ARQ\n");
+	else
+		hw->fwlog_cfg.options |= ICE_FWLOG_OPTION_IS_REGISTERED;
+
+	return status;
+}
+
+/**
+ * ice_fwlog_unregister - Unregister the PF from firmware logging
+ * @hw: pointer to the HW structure
+ */
+int ice_fwlog_unregister(struct ice_hw *hw)
+{
+	int status;
+
+	if (!ice_fwlog_supported(hw))
+		return -EOPNOTSUPP;
+
+	status = ice_aq_fwlog_register(hw, false);
+	if (status)
+		ice_debug(hw, ICE_DBG_FW_LOG, "Failed to unregister from firmware logging events over ARQ\n");
+	else
+		hw->fwlog_cfg.options &= ~ICE_FWLOG_OPTION_IS_REGISTERED;
+
+	return status;
+}
+
+/**
+ * ice_fwlog_set_supported - Set if FW logging is supported by FW
+ * @hw: pointer to the HW struct
+ *
+ * If FW returns success to the ice_aq_fwlog_get call then it supports FW
+ * logging, else it doesn't. Set the fwlog_supported flag accordingly.
+ *
+ * This function is only meant to be called during driver init to determine if
+ * the FW support FW logging.
+ */
+void ice_fwlog_set_supported(struct ice_hw *hw)
+{
+	struct ice_fwlog_cfg *cfg;
+	int status;
+
+	hw->fwlog_supported = false;
+
+	cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
+	if (!cfg)
+		return;
+
+	/* don't call ice_fwlog_get() because that would check to see if FW
+	 * logging is supported which is what the driver is determining now
+	 */
+	status = ice_aq_fwlog_get(hw, cfg);
+	if (status)
+		ice_debug(hw, ICE_DBG_FW_LOG, "ice_aq_fwlog_get failed, FW logging is not supported on this version of FW, status %d\n",
+			  status);
+	else
+		hw->fwlog_supported = true;
+
+	kfree(cfg);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_fwlog.h b/drivers/net/ethernet/intel/ice/ice_fwlog.h
new file mode 100644
index 000000000000..287e71fa4b86
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_fwlog.h
@@ -0,0 +1,79 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2022, Intel Corporation. */
+
+#ifndef _ICE_FWLOG_H_
+#define _ICE_FWLOG_H_
+#include "ice_adminq_cmd.h"
+
+struct ice_hw;
+
+/* Only a single log level should be set and all log levels under the set value
+ * are enabled, e.g. if log level is set to ICE_FW_LOG_LEVEL_VERBOSE, then all
+ * other log levels are included (except ICE_FW_LOG_LEVEL_NONE)
+ */
+enum ice_fwlog_level {
+	ICE_FWLOG_LEVEL_NONE = 0,
+	ICE_FWLOG_LEVEL_ERROR = 1,
+	ICE_FWLOG_LEVEL_WARNING = 2,
+	ICE_FWLOG_LEVEL_NORMAL = 3,
+	ICE_FWLOG_LEVEL_VERBOSE = 4,
+	ICE_FWLOG_LEVEL_INVALID, /* all values >= this entry are invalid */
+};
+
+struct ice_fwlog_module_entry {
+	/* module ID for the corresponding firmware logging event */
+	u16 module_id;
+	/* verbosity level for the module_id */
+	u8 log_level;
+};
+
+struct ice_fwlog_cfg {
+	/* list of modules for configuring log level */
+	struct ice_fwlog_module_entry module_entries[ICE_AQC_FW_LOG_ID_MAX];
+	/* options used to configure firmware logging */
+	u16 options;
+#define ICE_FWLOG_OPTION_ARQ_ENA		BIT(0)
+#define ICE_FWLOG_OPTION_UART_ENA		BIT(1)
+	/* set before calling ice_fwlog_init() so the PF registers for firmware
+	 * logging on initialization
+	 */
+#define ICE_FWLOG_OPTION_REGISTER_ON_INIT	BIT(2)
+	/* set in the ice_fwlog_get() response if the PF is registered for FW
+	 * logging events over ARQ
+	 */
+#define ICE_FWLOG_OPTION_IS_REGISTERED		BIT(3)
+
+	/* minimum number of log events sent per Admin Receive Queue event */
+	u16 log_resolution;
+};
+
+struct ice_fwlog_data {
+	u16 data_size;
+	u8 *data;
+};
+
+struct ice_fwlog_ring {
+	struct ice_fwlog_data *rings;
+	u16 index;
+	u16 size;
+	u16 head;
+	u16 tail;
+};
+
+#define ICE_FWLOG_RING_SIZE_INDEX_DFLT 3
+#define ICE_FWLOG_RING_SIZE_DFLT 256
+#define ICE_FWLOG_RING_SIZE_MAX 512
+
+bool ice_fwlog_ring_full(struct ice_fwlog_ring *rings);
+bool ice_fwlog_ring_empty(struct ice_fwlog_ring *rings);
+void ice_fwlog_ring_increment(u16 *item, u16 size);
+void ice_fwlog_set_supported(struct ice_hw *hw);
+bool ice_fwlog_supported(struct ice_hw *hw);
+int ice_fwlog_init(struct ice_hw *hw);
+void ice_fwlog_deinit(struct ice_hw *hw);
+int ice_fwlog_set(struct ice_hw *hw, struct ice_fwlog_cfg *cfg);
+int ice_fwlog_get(struct ice_hw *hw, struct ice_fwlog_cfg *cfg);
+int ice_fwlog_register(struct ice_hw *hw);
+int ice_fwlog_unregister(struct ice_hw *hw);
+void ice_fwlog_realloc_rings(struct ice_hw *hw, int index);
+#endif /* _ICE_FWLOG_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index 86936b758ade..cfac1d432c15 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -200,6 +200,8 @@
 #define GLINT_VECT2FUNC_PF_NUM_M		ICE_M(0x7, 12)
 #define GLINT_VECT2FUNC_IS_PF_S			16
 #define GLINT_VECT2FUNC_IS_PF_M			BIT(16)
+#define PFINT_ALLOC				0x001D2600
+#define PFINT_ALLOC_FIRST			ICE_M(0x7FF, 0)
 #define PFINT_FW_CTL				0x0016C800
 #define PFINT_FW_CTL_MSIX_INDX_M		ICE_M(0x7FF, 0)
 #define PFINT_FW_CTL_ITR_INDX_S			11
@@ -404,6 +406,10 @@
 #define GLQF_HMASK_SEL(_i)			(0x00410000 + ((_i) * 4))
 #define GLQF_HMASK_SEL_MAX_INDEX		127
 #define GLQF_HMASK_SEL_MASK_SEL_S		0
+#define GLQF_HSYMM(_i, _j)			(0x0040F000 + ((_i) * 4 + (_j) * 512))
+#define GLQF_HSYMM_REG_SIZE			4
+#define GLQF_HSYMM_REG_PER_PROF			6
+#define GLQF_HSYMM_ENABLE_BIT			BIT(7)
 #define E800_PFQF_FD_CNT_FD_GCNT_M		GENMASK(14, 0)
 #define E830_PFQF_FD_CNT_FD_GCNT_M		GENMASK(15, 0)
 #define E800_PFQF_FD_CNT_FD_BCNT_M		GENMASK(30, 16)
diff --git a/drivers/net/ethernet/intel/ice/ice_hwmon.c b/drivers/net/ethernet/intel/ice/ice_hwmon.c
new file mode 100644
index 000000000000..e4c2c1bff6c0
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_hwmon.c
@@ -0,0 +1,126 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023, Intel Corporation. */
+
+#include "ice.h"
+#include "ice_hwmon.h"
+#include "ice_adminq_cmd.h"
+
+#include <linux/hwmon.h>
+
+#define TEMP_FROM_REG(reg) ((reg) * 1000)
+
+static const struct hwmon_channel_info *ice_hwmon_info[] = {
+	HWMON_CHANNEL_INFO(temp,
+			   HWMON_T_INPUT | HWMON_T_MAX |
+			   HWMON_T_CRIT | HWMON_T_EMERGENCY),
+	NULL
+};
+
+static int ice_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
+			  u32 attr, int channel, long *val)
+{
+	struct ice_aqc_get_sensor_reading_resp resp;
+	struct ice_pf *pf = dev_get_drvdata(dev);
+	int ret;
+
+	if (type != hwmon_temp)
+		return -EOPNOTSUPP;
+
+	ret = ice_aq_get_sensor_reading(&pf->hw, &resp);
+	if (ret) {
+		dev_warn_ratelimited(dev,
+				     "%s HW read failure (%d)\n",
+				     __func__,
+				     ret);
+		return ret;
+	}
+
+	switch (attr) {
+	case hwmon_temp_input:
+		*val = TEMP_FROM_REG(resp.data.s0f0.temp);
+		break;
+	case hwmon_temp_max:
+		*val = TEMP_FROM_REG(resp.data.s0f0.temp_warning_threshold);
+		break;
+	case hwmon_temp_crit:
+		*val = TEMP_FROM_REG(resp.data.s0f0.temp_critical_threshold);
+		break;
+	case hwmon_temp_emergency:
+		*val = TEMP_FROM_REG(resp.data.s0f0.temp_fatal_threshold);
+		break;
+	default:
+		dev_dbg(dev, "%s unsupported attribute (%d)\n",
+			__func__, attr);
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static umode_t ice_hwmon_is_visible(const void *data,
+				    enum hwmon_sensor_types type, u32 attr,
+				    int channel)
+{
+	if (type != hwmon_temp)
+		return 0;
+
+	switch (attr) {
+	case hwmon_temp_input:
+	case hwmon_temp_crit:
+	case hwmon_temp_max:
+	case hwmon_temp_emergency:
+		return 0444;
+	}
+
+	return 0;
+}
+
+static const struct hwmon_ops ice_hwmon_ops = {
+	.is_visible = ice_hwmon_is_visible,
+	.read = ice_hwmon_read
+};
+
+static const struct hwmon_chip_info ice_chip_info = {
+	.ops = &ice_hwmon_ops,
+	.info = ice_hwmon_info
+};
+
+static bool ice_is_internal_reading_supported(struct ice_pf *pf)
+{
+	/* Only the first PF will report temperature for a chip.
+	 * Note that internal temp reading is not supported
+	 * for older FW (< v4.30).
+	 */
+	if (pf->hw.pf_id)
+		return false;
+
+	unsigned long sensors = pf->hw.dev_caps.supported_sensors;
+
+	return _test_bit(ICE_SENSOR_SUPPORT_E810_INT_TEMP_BIT, &sensors);
+};
+
+void ice_hwmon_init(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	struct device *hdev;
+
+	if (!ice_is_internal_reading_supported(pf))
+		return;
+
+	hdev = hwmon_device_register_with_info(dev, "ice", pf, &ice_chip_info,
+					       NULL);
+	if (IS_ERR(hdev)) {
+		dev_warn(dev,
+			 "hwmon_device_register_with_info returns error (%ld)",
+			 PTR_ERR(hdev));
+		return;
+	}
+	pf->hwmon_dev = hdev;
+}
+
+void ice_hwmon_exit(struct ice_pf *pf)
+{
+	if (!pf->hwmon_dev)
+		return;
+	hwmon_device_unregister(pf->hwmon_dev);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_hwmon.h b/drivers/net/ethernet/intel/ice/ice_hwmon.h
new file mode 100644
index 000000000000..d66d40354f5a
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_hwmon.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2023, Intel Corporation. */
+
+#ifndef _ICE_HWMON_H_
+#define _ICE_HWMON_H_
+
+#ifdef CONFIG_ICE_HWMON
+void ice_hwmon_init(struct ice_pf *pf);
+void ice_hwmon_exit(struct ice_pf *pf);
+#else /* CONFIG_ICE_HWMON */
+static inline void ice_hwmon_init(struct ice_pf *pf) { }
+static inline void ice_hwmon_exit(struct ice_pf *pf) { }
+#endif /* CONFIG_ICE_HWMON */
+
+#endif /* _ICE_HWMON_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index cd065ec48c87..2a25323105e5 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -208,8 +208,7 @@ ice_lag_cfg_fltr(struct ice_lag *lag, u32 act, u16 recipe_id, u16 *rule_idx,
 		eth_hdr = s_rule->hdr_data;
 		ice_fill_eth_hdr(eth_hdr);
 
-		act |= (vsi_num << ICE_SINGLE_ACT_VSI_ID_S) &
-			ICE_SINGLE_ACT_VSI_ID_M;
+		act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M, vsi_num);
 
 		s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX);
 		s_rule->recipe_id = cpu_to_le16(recipe_id);
@@ -570,6 +569,50 @@ resume_traffic:
 }
 
 /**
+ * ice_lag_build_netdev_list - populate the lag struct's netdev list
+ * @lag: local lag struct
+ * @ndlist: pointer to netdev list to populate
+ */
+static void ice_lag_build_netdev_list(struct ice_lag *lag,
+				      struct ice_lag_netdev_list *ndlist)
+{
+	struct ice_lag_netdev_list *nl;
+	struct net_device *tmp_nd;
+
+	INIT_LIST_HEAD(&ndlist->node);
+	rcu_read_lock();
+	for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) {
+		nl = kzalloc(sizeof(*nl), GFP_ATOMIC);
+		if (!nl)
+			break;
+
+		nl->netdev = tmp_nd;
+		list_add(&nl->node, &ndlist->node);
+	}
+	rcu_read_unlock();
+	lag->netdev_head = &ndlist->node;
+}
+
+/**
+ * ice_lag_destroy_netdev_list - free lag struct's netdev list
+ * @lag: pointer to local lag struct
+ * @ndlist: pointer to lag struct netdev list
+ */
+static void ice_lag_destroy_netdev_list(struct ice_lag *lag,
+					struct ice_lag_netdev_list *ndlist)
+{
+	struct ice_lag_netdev_list *entry, *n;
+
+	rcu_read_lock();
+	list_for_each_entry_safe(entry, n, &ndlist->node, node) {
+		list_del(&entry->node);
+		kfree(entry);
+	}
+	rcu_read_unlock();
+	lag->netdev_head = NULL;
+}
+
+/**
  * ice_lag_move_single_vf_nodes - Move Tx scheduling nodes for single VF
  * @lag: primary interface LAG struct
  * @oldport: lport of previous interface
@@ -597,7 +640,6 @@ ice_lag_move_single_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport,
 void ice_lag_move_new_vf_nodes(struct ice_vf *vf)
 {
 	struct ice_lag_netdev_list ndlist;
-	struct list_head *tmp, *n;
 	u8 pri_port, act_port;
 	struct ice_lag *lag;
 	struct ice_vsi *vsi;
@@ -621,38 +663,15 @@ void ice_lag_move_new_vf_nodes(struct ice_vf *vf)
 	pri_port = pf->hw.port_info->lport;
 	act_port = lag->active_port;
 
-	if (lag->upper_netdev) {
-		struct ice_lag_netdev_list *nl;
-		struct net_device *tmp_nd;
-
-		INIT_LIST_HEAD(&ndlist.node);
-		rcu_read_lock();
-		for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) {
-			nl = kzalloc(sizeof(*nl), GFP_ATOMIC);
-			if (!nl)
-				break;
-
-			nl->netdev = tmp_nd;
-			list_add(&nl->node, &ndlist.node);
-		}
-		rcu_read_unlock();
-	}
-
-	lag->netdev_head = &ndlist.node;
+	if (lag->upper_netdev)
+		ice_lag_build_netdev_list(lag, &ndlist);
 
 	if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG) &&
 	    lag->bonded && lag->primary && pri_port != act_port &&
 	    !list_empty(lag->netdev_head))
 		ice_lag_move_single_vf_nodes(lag, pri_port, act_port, vsi->idx);
 
-	list_for_each_safe(tmp, n, &ndlist.node) {
-		struct ice_lag_netdev_list *entry;
-
-		entry = list_entry(tmp, struct ice_lag_netdev_list, node);
-		list_del(&entry->node);
-		kfree(entry);
-	}
-	lag->netdev_head = NULL;
+	ice_lag_destroy_netdev_list(lag, &ndlist);
 
 new_vf_unlock:
 	mutex_unlock(&pf->lag_mutex);
@@ -679,6 +698,29 @@ static void ice_lag_move_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport)
 			ice_lag_move_single_vf_nodes(lag, oldport, newport, i);
 }
 
+/**
+ * ice_lag_move_vf_nodes_cfg - move vf nodes outside LAG netdev event context
+ * @lag: local lag struct
+ * @src_prt: lport value for source port
+ * @dst_prt: lport value for destination port
+ *
+ * This function is used to move nodes during an out-of-netdev-event situation,
+ * primarily when the driver needs to reconfigure or recreate resources.
+ *
+ * Must be called while holding the lag_mutex to avoid lag events from
+ * processing while out-of-sync moves are happening.  Also, paired moves,
+ * such as used in a reset flow, should both be called under the same mutex
+ * lock to avoid changes between start of reset and end of reset.
+ */
+void ice_lag_move_vf_nodes_cfg(struct ice_lag *lag, u8 src_prt, u8 dst_prt)
+{
+	struct ice_lag_netdev_list ndlist;
+
+	ice_lag_build_netdev_list(lag, &ndlist);
+	ice_lag_move_vf_nodes(lag, src_prt, dst_prt);
+	ice_lag_destroy_netdev_list(lag, &ndlist);
+}
+
 #define ICE_LAG_SRIOV_CP_RECIPE		10
 #define ICE_LAG_SRIOV_TRAIN_PKT_LEN	16
 
@@ -711,9 +753,7 @@ ice_lag_cfg_cp_fltr(struct ice_lag *lag, bool add)
 		s_rule->act = cpu_to_le32(ICE_FWD_TO_VSI |
 					  ICE_SINGLE_ACT_LAN_ENABLE |
 					  ICE_SINGLE_ACT_VALID_BIT |
-					  ((vsi->vsi_num <<
-					    ICE_SINGLE_ACT_VSI_ID_S) &
-					   ICE_SINGLE_ACT_VSI_ID_M));
+					  FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M, vsi->vsi_num));
 		s_rule->hdr_len = cpu_to_le16(ICE_LAG_SRIOV_TRAIN_PKT_LEN);
 		memcpy(s_rule->hdr_data, lacp_train_pkt, LACP_TRAIN_PKT_LEN);
 		opc = ice_aqc_opc_add_sw_rules;
@@ -1938,6 +1978,8 @@ int ice_init_lag(struct ice_pf *pf)
 	int n, err;
 
 	ice_lag_init_feature_support_flag(pf);
+	if (!ice_is_feature_supported(pf, ICE_F_SRIOV_LAG))
+		return 0;
 
 	pf->lag = kzalloc(sizeof(*lag), GFP_KERNEL);
 	if (!pf->lag)
@@ -2051,7 +2093,6 @@ void ice_lag_rebuild(struct ice_pf *pf)
 {
 	struct ice_lag_netdev_list ndlist;
 	struct ice_lag *lag, *prim_lag;
-	struct list_head *tmp, *n;
 	u8 act_port, loc_port;
 
 	if (!pf->lag || !pf->lag->bonded)
@@ -2063,21 +2104,7 @@ void ice_lag_rebuild(struct ice_pf *pf)
 	if (lag->primary) {
 		prim_lag = lag;
 	} else {
-		struct ice_lag_netdev_list *nl;
-		struct net_device *tmp_nd;
-
-		INIT_LIST_HEAD(&ndlist.node);
-		rcu_read_lock();
-		for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) {
-			nl = kzalloc(sizeof(*nl), GFP_ATOMIC);
-			if (!nl)
-				break;
-
-			nl->netdev = tmp_nd;
-			list_add(&nl->node, &ndlist.node);
-		}
-		rcu_read_unlock();
-		lag->netdev_head = &ndlist.node;
+		ice_lag_build_netdev_list(lag, &ndlist);
 		prim_lag = ice_lag_find_primary(lag);
 	}
 
@@ -2107,13 +2134,7 @@ void ice_lag_rebuild(struct ice_pf *pf)
 
 	ice_clear_rdma_cap(pf);
 lag_rebuild_out:
-	list_for_each_safe(tmp, n, &ndlist.node) {
-		struct ice_lag_netdev_list *entry;
-
-		entry = list_entry(tmp, struct ice_lag_netdev_list, node);
-		list_del(&entry->node);
-		kfree(entry);
-	}
+	ice_lag_destroy_netdev_list(lag, &ndlist);
 	mutex_unlock(&pf->lag_mutex);
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h
index 9557e8605a07..ede833dfa658 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.h
+++ b/drivers/net/ethernet/intel/ice/ice_lag.h
@@ -65,4 +65,5 @@ int ice_init_lag(struct ice_pf *pf);
 void ice_deinit_lag(struct ice_pf *pf);
 void ice_lag_rebuild(struct ice_pf *pf);
 bool ice_lag_is_switchdev_running(struct ice_pf *pf);
+void ice_lag_move_vf_nodes_cfg(struct ice_lag *lag, u8 src_prt, u8 dst_prt);
 #endif /* _ICE_LAG_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
index 89f986a75cc8..d384ddfcb83e 100644
--- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
+++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
@@ -673,6 +673,212 @@ struct ice_tlan_ctx {
  *      Use the enum ice_rx_l2_ptype to decode the packet type
  * ENDIF
  */
+#define ICE_PTYPES								\
+	/* L2 Packet types */							\
+	ICE_PTT_UNUSED_ENTRY(0),						\
+	ICE_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),			\
+	ICE_PTT_UNUSED_ENTRY(2),						\
+	ICE_PTT_UNUSED_ENTRY(3),						\
+	ICE_PTT_UNUSED_ENTRY(4),						\
+	ICE_PTT_UNUSED_ENTRY(5),						\
+	ICE_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),			\
+	ICE_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),			\
+	ICE_PTT_UNUSED_ENTRY(8),						\
+	ICE_PTT_UNUSED_ENTRY(9),						\
+	ICE_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),		\
+	ICE_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),		\
+	ICE_PTT_UNUSED_ENTRY(12),						\
+	ICE_PTT_UNUSED_ENTRY(13),						\
+	ICE_PTT_UNUSED_ENTRY(14),						\
+	ICE_PTT_UNUSED_ENTRY(15),						\
+	ICE_PTT_UNUSED_ENTRY(16),						\
+	ICE_PTT_UNUSED_ENTRY(17),						\
+	ICE_PTT_UNUSED_ENTRY(18),						\
+	ICE_PTT_UNUSED_ENTRY(19),						\
+	ICE_PTT_UNUSED_ENTRY(20),						\
+	ICE_PTT_UNUSED_ENTRY(21),						\
+										\
+	/* Non Tunneled IPv4 */							\
+	ICE_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3),		\
+	ICE_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3),		\
+	ICE_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(25),						\
+	ICE_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP,  PAY4),		\
+	ICE_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4),		\
+	ICE_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4),		\
+										\
+	/* IPv4 --> IPv4 */							\
+	ICE_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3),		\
+	ICE_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3),		\
+	ICE_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(32),						\
+	ICE_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),		\
+	ICE_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),		\
+	ICE_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),		\
+										\
+	/* IPv4 --> IPv6 */							\
+	ICE_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3),		\
+	ICE_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3),		\
+	ICE_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(39),						\
+	ICE_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),		\
+	ICE_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),		\
+	ICE_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),		\
+										\
+	/* IPv4 --> GRE/NAT */							\
+	ICE_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),		\
+										\
+	/* IPv4 --> GRE/NAT --> IPv4 */						\
+	ICE_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),		\
+	ICE_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),		\
+	ICE_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(47),						\
+	ICE_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),		\
+	ICE_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),		\
+	ICE_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),		\
+										\
+	/* IPv4 --> GRE/NAT --> IPv6 */						\
+	ICE_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),		\
+	ICE_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),		\
+	ICE_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(54),						\
+	ICE_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),		\
+	ICE_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),		\
+	ICE_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),		\
+										\
+	/* IPv4 --> GRE/NAT --> MAC */						\
+	ICE_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),	\
+										\
+	/* IPv4 --> GRE/NAT --> MAC --> IPv4 */					\
+	ICE_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),	\
+	ICE_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),	\
+	ICE_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(62),						\
+	ICE_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),	\
+	ICE_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),	\
+	ICE_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),	\
+										\
+	/* IPv4 --> GRE/NAT -> MAC --> IPv6 */					\
+	ICE_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),	\
+	ICE_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),	\
+	ICE_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(69),						\
+	ICE_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),	\
+	ICE_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),	\
+	ICE_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),	\
+										\
+	/* IPv4 --> GRE/NAT --> MAC/VLAN */					\
+	ICE_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),	\
+										\
+	/* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */				\
+	ICE_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),	\
+	ICE_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),	\
+	ICE_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(77),						\
+	ICE_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),	\
+	ICE_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),	\
+	ICE_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),	\
+										\
+	/* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */				\
+	ICE_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),	\
+	ICE_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),	\
+	ICE_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(84),						\
+	ICE_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),	\
+	ICE_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),	\
+	ICE_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),	\
+										\
+	/* Non Tunneled IPv6 */							\
+	ICE_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3),		\
+	ICE_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3),		\
+	ICE_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(91),						\
+	ICE_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP,  PAY4),		\
+	ICE_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4),		\
+	ICE_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4),		\
+										\
+	/* IPv6 --> IPv4 */							\
+	ICE_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3),		\
+	ICE_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3),		\
+	ICE_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(98),						\
+	ICE_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),		\
+	ICE_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),		\
+	ICE_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),		\
+										\
+	/* IPv6 --> IPv6 */							\
+	ICE_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3),		\
+	ICE_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3),		\
+	ICE_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(105),						\
+	ICE_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),		\
+	ICE_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),		\
+	ICE_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),		\
+										\
+	/* IPv6 --> GRE/NAT */							\
+	ICE_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),		\
+										\
+	/* IPv6 --> GRE/NAT -> IPv4 */						\
+	ICE_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),		\
+	ICE_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),		\
+	ICE_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(113),						\
+	ICE_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),		\
+	ICE_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),		\
+	ICE_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),		\
+										\
+	/* IPv6 --> GRE/NAT -> IPv6 */						\
+	ICE_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),		\
+	ICE_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),		\
+	ICE_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(120),						\
+	ICE_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),		\
+	ICE_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),		\
+	ICE_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),		\
+										\
+	/* IPv6 --> GRE/NAT -> MAC */						\
+	ICE_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),	\
+										\
+	/* IPv6 --> GRE/NAT -> MAC -> IPv4 */					\
+	ICE_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),	\
+	ICE_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),	\
+	ICE_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(128),						\
+	ICE_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),	\
+	ICE_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),	\
+	ICE_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),	\
+										\
+	/* IPv6 --> GRE/NAT -> MAC -> IPv6 */					\
+	ICE_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),	\
+	ICE_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),	\
+	ICE_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(135),						\
+	ICE_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),	\
+	ICE_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),	\
+	ICE_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),	\
+										\
+	/* IPv6 --> GRE/NAT -> MAC/VLAN */					\
+	ICE_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),	\
+										\
+	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */				\
+	ICE_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),	\
+	ICE_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),	\
+	ICE_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(143),						\
+	ICE_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),	\
+	ICE_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),	\
+	ICE_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),	\
+										\
+	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */				\
+	ICE_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),	\
+	ICE_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),	\
+	ICE_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(150),						\
+	ICE_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),	\
+	ICE_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),	\
+	ICE_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
+
+#define ICE_NUM_DEFINED_PTYPES	154
 
 /* macro to make the table lines short, use explicit indexing with [PTYPE] */
 #define ICE_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\
@@ -695,212 +901,10 @@ struct ice_tlan_ctx {
 
 /* Lookup table mapping in the 10-bit HW PTYPE to the bit field for decoding */
 static const struct ice_rx_ptype_decoded ice_ptype_lkup[BIT(10)] = {
-	/* L2 Packet types */
-	ICE_PTT_UNUSED_ENTRY(0),
-	ICE_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
-	ICE_PTT_UNUSED_ENTRY(2),
-	ICE_PTT_UNUSED_ENTRY(3),
-	ICE_PTT_UNUSED_ENTRY(4),
-	ICE_PTT_UNUSED_ENTRY(5),
-	ICE_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
-	ICE_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
-	ICE_PTT_UNUSED_ENTRY(8),
-	ICE_PTT_UNUSED_ENTRY(9),
-	ICE_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
-	ICE_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
-	ICE_PTT_UNUSED_ENTRY(12),
-	ICE_PTT_UNUSED_ENTRY(13),
-	ICE_PTT_UNUSED_ENTRY(14),
-	ICE_PTT_UNUSED_ENTRY(15),
-	ICE_PTT_UNUSED_ENTRY(16),
-	ICE_PTT_UNUSED_ENTRY(17),
-	ICE_PTT_UNUSED_ENTRY(18),
-	ICE_PTT_UNUSED_ENTRY(19),
-	ICE_PTT_UNUSED_ENTRY(20),
-	ICE_PTT_UNUSED_ENTRY(21),
-
-	/* Non Tunneled IPv4 */
-	ICE_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3),
-	ICE_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3),
-	ICE_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(25),
-	ICE_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP,  PAY4),
-	ICE_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4),
-	ICE_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4),
-
-	/* IPv4 --> IPv4 */
-	ICE_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(32),
-	ICE_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 --> IPv6 */
-	ICE_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(39),
-	ICE_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT */
-	ICE_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),
-
-	/* IPv4 --> GRE/NAT --> IPv4 */
-	ICE_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(47),
-	ICE_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT --> IPv6 */
-	ICE_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(54),
-	ICE_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT --> MAC */
-	ICE_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),
-
-	/* IPv4 --> GRE/NAT --> MAC --> IPv4 */
-	ICE_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(62),
-	ICE_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT -> MAC --> IPv6 */
-	ICE_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(69),
-	ICE_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT --> MAC/VLAN */
-	ICE_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),
-
-	/* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */
-	ICE_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(77),
-	ICE_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */
-	ICE_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(84),
-	ICE_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
-
-	/* Non Tunneled IPv6 */
-	ICE_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3),
-	ICE_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3),
-	ICE_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(91),
-	ICE_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP,  PAY4),
-	ICE_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4),
-	ICE_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4),
-
-	/* IPv6 --> IPv4 */
-	ICE_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(98),
-	ICE_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> IPv6 */
-	ICE_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(105),
-	ICE_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT */
-	ICE_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),
-
-	/* IPv6 --> GRE/NAT -> IPv4 */
-	ICE_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(113),
-	ICE_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> IPv6 */
-	ICE_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(120),
-	ICE_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC */
-	ICE_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),
-
-	/* IPv6 --> GRE/NAT -> MAC -> IPv4 */
-	ICE_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(128),
-	ICE_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC -> IPv6 */
-	ICE_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(135),
-	ICE_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC/VLAN */
-	ICE_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),
-
-	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */
-	ICE_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(143),
-	ICE_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */
-	ICE_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(150),
-	ICE_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
+	ICE_PTYPES
 
 	/* unused entries */
-	[154 ... 1023] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 }
+	[ICE_NUM_DEFINED_PTYPES ... 1023] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 }
 };
 
 static inline struct ice_rx_ptype_decoded ice_decode_rx_desc_ptype(u16 ptype)
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 4b1e56396293..9be724291ef8 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -212,11 +212,18 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi)
 						 vsi->alloc_txq));
 		break;
 	case ICE_VSI_SWITCHDEV_CTRL:
-		/* The number of queues for ctrl VSI is equal to number of VFs.
+		/* The number of queues for ctrl VSI is equal to number of PRs
 		 * Each ring is associated to the corresponding VF_PR netdev.
+		 * Tx and Rx rings are always equal
 		 */
-		vsi->alloc_txq = ice_get_num_vfs(pf);
-		vsi->alloc_rxq = vsi->alloc_txq;
+		if (vsi->req_txq && vsi->req_rxq) {
+			vsi->alloc_txq = vsi->req_txq;
+			vsi->alloc_rxq = vsi->req_rxq;
+		} else {
+			vsi->alloc_txq = 1;
+			vsi->alloc_rxq = 1;
+		}
+
 		vsi->num_q_vectors = 1;
 		break;
 	case ICE_VSI_VF:
@@ -519,16 +526,14 @@ static irqreturn_t ice_eswitch_msix_clean_rings(int __always_unused irq, void *d
 {
 	struct ice_q_vector *q_vector = (struct ice_q_vector *)data;
 	struct ice_pf *pf = q_vector->vsi->back;
-	struct ice_vf *vf;
-	unsigned int bkt;
+	struct ice_repr *repr;
+	unsigned long id;
 
 	if (!q_vector->tx.tx_ring && !q_vector->rx.rx_ring)
 		return IRQ_HANDLED;
 
-	rcu_read_lock();
-	ice_for_each_vf_rcu(pf, bkt, vf)
-		napi_schedule(&vf->repr->q_vector->napi);
-	rcu_read_unlock();
+	xa_for_each(&pf->eswitch.reprs, id, repr)
+		napi_schedule(&repr->q_vector->napi);
 
 	return IRQ_HANDLED;
 }
@@ -969,9 +974,8 @@ static void ice_set_dflt_vsi_ctx(struct ice_hw *hw, struct ice_vsi_ctx *ctxt)
 	/* Traffic from VSI can be sent to LAN */
 	ctxt->info.sw_flags2 = ICE_AQ_VSI_SW_FLAG_LAN_ENA;
 	/* allow all untagged/tagged packets by default on Tx */
-	ctxt->info.inner_vlan_flags = ((ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL &
-				  ICE_AQ_VSI_INNER_VLAN_TX_MODE_M) >>
-				 ICE_AQ_VSI_INNER_VLAN_TX_MODE_S);
+	ctxt->info.inner_vlan_flags = FIELD_PREP(ICE_AQ_VSI_INNER_VLAN_TX_MODE_M,
+						 ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL);
 	/* SVM - by default bits 3 and 4 in inner_vlan_flags are 0's which
 	 * results in legacy behavior (show VLAN, DEI, and UP) in descriptor.
 	 *
@@ -979,15 +983,14 @@ static void ice_set_dflt_vsi_ctx(struct ice_hw *hw, struct ice_vsi_ctx *ctxt)
 	 */
 	if (ice_is_dvm_ena(hw)) {
 		ctxt->info.inner_vlan_flags |=
-			ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING;
+			FIELD_PREP(ICE_AQ_VSI_INNER_VLAN_EMODE_M,
+				   ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING);
 		ctxt->info.outer_vlan_flags =
-			(ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL <<
-			 ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) &
-			ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M;
+			FIELD_PREP(ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M,
+				   ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL);
 		ctxt->info.outer_vlan_flags |=
-			(ICE_AQ_VSI_OUTER_TAG_VLAN_8100 <<
-			 ICE_AQ_VSI_OUTER_TAG_TYPE_S) &
-			ICE_AQ_VSI_OUTER_TAG_TYPE_M;
+			FIELD_PREP(ICE_AQ_VSI_OUTER_TAG_TYPE_M,
+				   ICE_AQ_VSI_OUTER_TAG_VLAN_8100);
 		ctxt->info.outer_vlan_flags |=
 			FIELD_PREP(ICE_AQ_VSI_OUTER_VLAN_EMODE_M,
 				   ICE_AQ_VSI_OUTER_VLAN_EMODE_NOTHING);
@@ -1066,10 +1069,8 @@ static int ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 		vsi->tc_cfg.tc_info[i].qcount_tx = num_txq_per_tc;
 		vsi->tc_cfg.tc_info[i].netdev_tc = netdev_tc++;
 
-		qmap = ((offset << ICE_AQ_VSI_TC_Q_OFFSET_S) &
-			ICE_AQ_VSI_TC_Q_OFFSET_M) |
-			((pow << ICE_AQ_VSI_TC_Q_NUM_S) &
-			 ICE_AQ_VSI_TC_Q_NUM_M);
+		qmap = FIELD_PREP(ICE_AQ_VSI_TC_Q_OFFSET_M, offset);
+		qmap |= FIELD_PREP(ICE_AQ_VSI_TC_Q_NUM_M, pow);
 		offset += num_rxq_per_tc;
 		tx_count += num_txq_per_tc;
 		ctxt->info.tc_mapping[i] = cpu_to_le16(qmap);
@@ -1152,18 +1153,14 @@ static void ice_set_fd_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi)
 	ctxt->info.max_fd_fltr_shared =
 			cpu_to_le16(vsi->num_bfltr);
 	/* default queue index within the VSI of the default FD */
-	val = ((dflt_q << ICE_AQ_VSI_FD_DEF_Q_S) &
-	       ICE_AQ_VSI_FD_DEF_Q_M);
+	val = FIELD_PREP(ICE_AQ_VSI_FD_DEF_Q_M, dflt_q);
 	/* target queue or queue group to the FD filter */
-	val |= ((dflt_q_group << ICE_AQ_VSI_FD_DEF_GRP_S) &
-		ICE_AQ_VSI_FD_DEF_GRP_M);
+	val |= FIELD_PREP(ICE_AQ_VSI_FD_DEF_GRP_M, dflt_q_group);
 	ctxt->info.fd_def_q = cpu_to_le16(val);
 	/* queue index on which FD filter completion is reported */
-	val = ((report_q << ICE_AQ_VSI_FD_REPORT_Q_S) &
-	       ICE_AQ_VSI_FD_REPORT_Q_M);
+	val = FIELD_PREP(ICE_AQ_VSI_FD_REPORT_Q_M, report_q);
 	/* priority of the default qindex action */
-	val |= ((dflt_q_prio << ICE_AQ_VSI_FD_DEF_PRIORITY_S) &
-		ICE_AQ_VSI_FD_DEF_PRIORITY_M);
+	val |= FIELD_PREP(ICE_AQ_VSI_FD_DEF_PRIORITY_M, dflt_q_prio);
 	ctxt->info.fd_report_opt = cpu_to_le16(val);
 }
 
@@ -1186,12 +1183,10 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi)
 	case ICE_VSI_PF:
 		/* PF VSI will inherit RSS instance of PF */
 		lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_PF;
-		hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ;
 		break;
 	case ICE_VSI_VF:
 		/* VF VSI will gets a small RSS table which is a VSI LUT type */
 		lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI;
-		hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ;
 		break;
 	default:
 		dev_dbg(dev, "Unsupported VSI type %s\n",
@@ -1199,9 +1194,12 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi)
 		return;
 	}
 
-	ctxt->info.q_opt_rss = ((lut_type << ICE_AQ_VSI_Q_OPT_RSS_LUT_S) &
-				ICE_AQ_VSI_Q_OPT_RSS_LUT_M) |
-				(hash_type & ICE_AQ_VSI_Q_OPT_RSS_HASH_M);
+	hash_type = ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ;
+	vsi->rss_hfunc = hash_type;
+
+	ctxt->info.q_opt_rss =
+		FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_LUT_M, lut_type) |
+		FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_HASH_M, hash_type);
 }
 
 static void
@@ -1215,10 +1213,8 @@ ice_chnl_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 	qcount = min_t(int, vsi->num_rxq, pf->num_lan_msix);
 
 	pow = order_base_2(qcount);
-	qmap = ((offset << ICE_AQ_VSI_TC_Q_OFFSET_S) &
-		 ICE_AQ_VSI_TC_Q_OFFSET_M) |
-		 ((pow << ICE_AQ_VSI_TC_Q_NUM_S) &
-		   ICE_AQ_VSI_TC_Q_NUM_M);
+	qmap = FIELD_PREP(ICE_AQ_VSI_TC_Q_OFFSET_M, offset);
+	qmap |= FIELD_PREP(ICE_AQ_VSI_TC_Q_NUM_M, pow);
 
 	ctxt->info.tc_mapping[0] = cpu_to_le16(qmap);
 	ctxt->info.mapping_flags |= cpu_to_le16(ICE_AQ_VSI_Q_MAP_CONTIG);
@@ -1600,12 +1596,44 @@ static void ice_vsi_set_vf_rss_flow_fld(struct ice_vsi *vsi)
 		return;
 	}
 
-	status = ice_add_avf_rss_cfg(&pf->hw, vsi->idx, ICE_DEFAULT_RSS_HENA);
+	status = ice_add_avf_rss_cfg(&pf->hw, vsi, ICE_DEFAULT_RSS_HENA);
 	if (status)
 		dev_dbg(dev, "ice_add_avf_rss_cfg failed for vsi = %d, error = %d\n",
 			vsi->vsi_num, status);
 }
 
+static const struct ice_rss_hash_cfg default_rss_cfgs[] = {
+	/* configure RSS for IPv4 with input set IP src/dst */
+	{ICE_FLOW_SEG_HDR_IPV4, ICE_FLOW_HASH_IPV4, ICE_RSS_ANY_HEADERS, false},
+	/* configure RSS for IPv6 with input set IPv6 src/dst */
+	{ICE_FLOW_SEG_HDR_IPV6, ICE_FLOW_HASH_IPV6, ICE_RSS_ANY_HEADERS, false},
+	/* configure RSS for tcp4 with input set IP src/dst, TCP src/dst */
+	{ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV4,
+				ICE_HASH_TCP_IPV4,  ICE_RSS_ANY_HEADERS, false},
+	/* configure RSS for udp4 with input set IP src/dst, UDP src/dst */
+	{ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV4,
+				ICE_HASH_UDP_IPV4,  ICE_RSS_ANY_HEADERS, false},
+	/* configure RSS for sctp4 with input set IP src/dst - only support
+	 * RSS on SCTPv4 on outer headers (non-tunneled)
+	 */
+	{ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV4,
+		ICE_HASH_SCTP_IPV4, ICE_RSS_OUTER_HEADERS, false},
+	/* configure RSS for tcp6 with input set IPv6 src/dst, TCP src/dst */
+	{ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV6,
+				ICE_HASH_TCP_IPV6,  ICE_RSS_ANY_HEADERS, false},
+	/* configure RSS for udp6 with input set IPv6 src/dst, UDP src/dst */
+	{ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV6,
+				ICE_HASH_UDP_IPV6,  ICE_RSS_ANY_HEADERS, false},
+	/* configure RSS for sctp6 with input set IPv6 src/dst - only support
+	 * RSS on SCTPv6 on outer headers (non-tunneled)
+	 */
+	{ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV6,
+		ICE_HASH_SCTP_IPV6, ICE_RSS_OUTER_HEADERS, false},
+	/* configure RSS for IPSEC ESP SPI with input set MAC_IPV4_SPI */
+	{ICE_FLOW_SEG_HDR_ESP,
+		ICE_FLOW_HASH_ESP_SPI, ICE_RSS_OUTER_HEADERS, false},
+};
+
 /**
  * ice_vsi_set_rss_flow_fld - Sets RSS input set for different flows
  * @vsi: VSI to be configured
@@ -1619,11 +1647,12 @@ static void ice_vsi_set_vf_rss_flow_fld(struct ice_vsi *vsi)
  */
 static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi)
 {
-	u16 vsi_handle = vsi->idx, vsi_num = vsi->vsi_num;
+	u16 vsi_num = vsi->vsi_num;
 	struct ice_pf *pf = vsi->back;
 	struct ice_hw *hw = &pf->hw;
 	struct device *dev;
 	int status;
+	u32 i;
 
 	dev = ice_pf_to_dev(pf);
 	if (ice_is_safe_mode(pf)) {
@@ -1631,67 +1660,15 @@ static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi)
 			vsi_num);
 		return;
 	}
-	/* configure RSS for IPv4 with input set IP src/dst */
-	status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV4,
-				 ICE_FLOW_SEG_HDR_IPV4);
-	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for ipv4 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
-
-	/* configure RSS for IPv6 with input set IPv6 src/dst */
-	status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV6,
-				 ICE_FLOW_SEG_HDR_IPV6);
-	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for ipv6 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
-
-	/* configure RSS for tcp4 with input set IP src/dst, TCP src/dst */
-	status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_TCP_IPV4,
-				 ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV4);
-	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for tcp4 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
+	for (i = 0; i < ARRAY_SIZE(default_rss_cfgs); i++) {
+		const struct ice_rss_hash_cfg *cfg = &default_rss_cfgs[i];
 
-	/* configure RSS for udp4 with input set IP src/dst, UDP src/dst */
-	status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_UDP_IPV4,
-				 ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV4);
-	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for udp4 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
-
-	/* configure RSS for sctp4 with input set IP src/dst */
-	status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV4,
-				 ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV4);
-	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for sctp4 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
-
-	/* configure RSS for tcp6 with input set IPv6 src/dst, TCP src/dst */
-	status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_TCP_IPV6,
-				 ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV6);
-	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for tcp6 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
-
-	/* configure RSS for udp6 with input set IPv6 src/dst, UDP src/dst */
-	status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_UDP_IPV6,
-				 ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV6);
-	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for udp6 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
-
-	/* configure RSS for sctp6 with input set IPv6 src/dst */
-	status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV6,
-				 ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV6);
-	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for sctp6 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
-
-	status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_ESP_SPI,
-				 ICE_FLOW_SEG_HDR_ESP);
-	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for esp/spi flow, vsi = %d, error = %d\n",
-			vsi_num, status);
+		status = ice_add_rss_cfg(hw, vsi, cfg);
+		if (status)
+			dev_dbg(dev, "ice_add_rss_cfg failed, addl_hdrs = %x, hash_flds = %llx, hdr_type = %d, symm = %d\n",
+				cfg->addl_hdrs, cfg->hash_flds,
+				cfg->hdr_type, cfg->symm);
+	}
 }
 
 /**
@@ -1808,11 +1785,8 @@ ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio,
 		    QRXFLXP_CNTXT_RXDID_PRIO_M |
 		    QRXFLXP_CNTXT_TS_M);
 
-	regval |= (rxdid << QRXFLXP_CNTXT_RXDID_IDX_S) &
-		QRXFLXP_CNTXT_RXDID_IDX_M;
-
-	regval |= (prio << QRXFLXP_CNTXT_RXDID_PRIO_S) &
-		QRXFLXP_CNTXT_RXDID_PRIO_M;
+	regval |= FIELD_PREP(QRXFLXP_CNTXT_RXDID_IDX_M, rxdid);
+	regval |= FIELD_PREP(QRXFLXP_CNTXT_RXDID_PRIO_M, prio);
 
 	if (ena_ts)
 		/* Enable TimeSync on this queue */
@@ -2371,6 +2345,9 @@ static int ice_vsi_cfg_tc_lan(struct ice_pf *pf, struct ice_vsi *vsi)
 		} else {
 			max_txqs[i] = vsi->alloc_txq;
 		}
+
+		if (vsi->type == ICE_VSI_PF)
+			max_txqs[i] += vsi->num_xdp_txq;
 	}
 
 	dev_dbg(dev, "vsi->tc_cfg.ena_tc = %d\n", vsi->tc_cfg.ena_tc);
@@ -2447,6 +2424,10 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params)
 			goto unroll_vector_base;
 
 		ice_vsi_map_rings_to_vectors(vsi);
+
+		/* Associate q_vector rings to napi */
+		ice_vsi_set_napi_queues(vsi, true);
+
 		vsi->stat_offsets_loaded = false;
 
 		if (ice_is_xdp_ena_vsi(vsi)) {
@@ -2620,10 +2601,6 @@ void ice_vsi_decfg(struct ice_vsi *vsi)
 	if (vsi->type == ICE_VSI_VF &&
 	    vsi->agg_node && vsi->agg_node->valid)
 		vsi->agg_node->num_vsis--;
-	if (vsi->agg_node) {
-		vsi->agg_node->valid = false;
-		vsi->agg_node->agg_id = 0;
-	}
 }
 
 /**
@@ -2927,6 +2904,71 @@ void ice_vsi_dis_irq(struct ice_vsi *vsi)
 }
 
 /**
+ * ice_queue_set_napi - Set the napi instance for the queue
+ * @dev: device to which NAPI and queue belong
+ * @queue_index: Index of queue
+ * @type: queue type as RX or TX
+ * @napi: NAPI context
+ * @locked: is the rtnl_lock already held
+ *
+ * Set the napi instance for the queue
+ */
+static void
+ice_queue_set_napi(struct net_device *dev, unsigned int queue_index,
+		   enum netdev_queue_type type, struct napi_struct *napi,
+		   bool locked)
+{
+	if (!locked)
+		rtnl_lock();
+	netif_queue_set_napi(dev, queue_index, type, napi);
+	if (!locked)
+		rtnl_unlock();
+}
+
+/**
+ * ice_q_vector_set_napi_queues - Map queue[s] associated with the napi
+ * @q_vector: q_vector pointer
+ * @locked: is the rtnl_lock already held
+ *
+ * Associate the q_vector napi with all the queue[s] on the vector
+ */
+void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked)
+{
+	struct ice_rx_ring *rx_ring;
+	struct ice_tx_ring *tx_ring;
+
+	ice_for_each_rx_ring(rx_ring, q_vector->rx)
+		ice_queue_set_napi(q_vector->vsi->netdev, rx_ring->q_index,
+				   NETDEV_QUEUE_TYPE_RX, &q_vector->napi,
+				   locked);
+
+	ice_for_each_tx_ring(tx_ring, q_vector->tx)
+		ice_queue_set_napi(q_vector->vsi->netdev, tx_ring->q_index,
+				   NETDEV_QUEUE_TYPE_TX, &q_vector->napi,
+				   locked);
+	/* Also set the interrupt number for the NAPI */
+	netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq);
+}
+
+/**
+ * ice_vsi_set_napi_queues
+ * @vsi: VSI pointer
+ * @locked: is the rtnl_lock already held
+ *
+ * Associate queue[s] with napi for all vectors
+ */
+void ice_vsi_set_napi_queues(struct ice_vsi *vsi, bool locked)
+{
+	int i;
+
+	if (!vsi->netdev)
+		return;
+
+	ice_for_each_q_vector(vsi, i)
+		ice_q_vector_set_napi_queues(vsi->q_vectors[i], locked);
+}
+
+/**
  * ice_vsi_release - Delete a VSI and free its resources
  * @vsi: the VSI being removed
  *
@@ -3071,27 +3113,26 @@ ice_vsi_rebuild_set_coalesce(struct ice_vsi *vsi,
 }
 
 /**
- * ice_vsi_realloc_stat_arrays - Frees unused stat structures
+ * ice_vsi_realloc_stat_arrays - Frees unused stat structures or alloc new ones
  * @vsi: VSI pointer
- * @prev_txq: Number of Tx rings before ring reallocation
- * @prev_rxq: Number of Rx rings before ring reallocation
  */
-static void
-ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi, int prev_txq, int prev_rxq)
+static int
+ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi)
 {
+	u16 req_txq = vsi->req_txq ? vsi->req_txq : vsi->alloc_txq;
+	u16 req_rxq = vsi->req_rxq ? vsi->req_rxq : vsi->alloc_rxq;
+	struct ice_ring_stats **tx_ring_stats;
+	struct ice_ring_stats **rx_ring_stats;
 	struct ice_vsi_stats *vsi_stat;
 	struct ice_pf *pf = vsi->back;
+	u16 prev_txq = vsi->alloc_txq;
+	u16 prev_rxq = vsi->alloc_rxq;
 	int i;
 
-	if (!prev_txq || !prev_rxq)
-		return;
-	if (vsi->type == ICE_VSI_CHNL)
-		return;
-
 	vsi_stat = pf->vsi_stats[vsi->idx];
 
-	if (vsi->num_txq < prev_txq) {
-		for (i = vsi->num_txq; i < prev_txq; i++) {
+	if (req_txq < prev_txq) {
+		for (i = req_txq; i < prev_txq; i++) {
 			if (vsi_stat->tx_ring_stats[i]) {
 				kfree_rcu(vsi_stat->tx_ring_stats[i], rcu);
 				WRITE_ONCE(vsi_stat->tx_ring_stats[i], NULL);
@@ -3099,14 +3140,36 @@ ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi, int prev_txq, int prev_rxq)
 		}
 	}
 
-	if (vsi->num_rxq < prev_rxq) {
-		for (i = vsi->num_rxq; i < prev_rxq; i++) {
+	tx_ring_stats = vsi_stat->rx_ring_stats;
+	vsi_stat->tx_ring_stats =
+		krealloc_array(vsi_stat->tx_ring_stats, req_txq,
+			       sizeof(*vsi_stat->tx_ring_stats),
+			       GFP_KERNEL | __GFP_ZERO);
+	if (!vsi_stat->tx_ring_stats) {
+		vsi_stat->tx_ring_stats = tx_ring_stats;
+		return -ENOMEM;
+	}
+
+	if (req_rxq < prev_rxq) {
+		for (i = req_rxq; i < prev_rxq; i++) {
 			if (vsi_stat->rx_ring_stats[i]) {
 				kfree_rcu(vsi_stat->rx_ring_stats[i], rcu);
 				WRITE_ONCE(vsi_stat->rx_ring_stats[i], NULL);
 			}
 		}
 	}
+
+	rx_ring_stats = vsi_stat->rx_ring_stats;
+	vsi_stat->rx_ring_stats =
+		krealloc_array(vsi_stat->rx_ring_stats, req_rxq,
+			       sizeof(*vsi_stat->rx_ring_stats),
+			       GFP_KERNEL | __GFP_ZERO);
+	if (!vsi_stat->rx_ring_stats) {
+		vsi_stat->rx_ring_stats = rx_ring_stats;
+		return -ENOMEM;
+	}
+
+	return 0;
 }
 
 /**
@@ -3123,9 +3186,9 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags)
 {
 	struct ice_vsi_cfg_params params = {};
 	struct ice_coalesce_stored *coalesce;
-	int ret, prev_txq, prev_rxq;
 	int prev_num_q_vectors = 0;
 	struct ice_pf *pf;
+	int ret;
 
 	if (!vsi)
 		return -EINVAL;
@@ -3144,8 +3207,9 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags)
 
 	prev_num_q_vectors = ice_vsi_rebuild_get_coalesce(vsi, coalesce);
 
-	prev_txq = vsi->num_txq;
-	prev_rxq = vsi->num_rxq;
+	ret = ice_vsi_realloc_stat_arrays(vsi);
+	if (ret)
+		goto err_vsi_cfg;
 
 	ice_vsi_decfg(vsi);
 	ret = ice_vsi_cfg_def(vsi, &params);
@@ -3163,8 +3227,6 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags)
 		return ice_schedule_reset(pf, ICE_RESET_PFR);
 	}
 
-	ice_vsi_realloc_stat_arrays(vsi, prev_txq, prev_rxq);
-
 	ice_vsi_rebuild_set_coalesce(vsi, coalesce, prev_num_q_vectors);
 	kfree(coalesce);
 
@@ -3316,9 +3378,8 @@ ice_vsi_setup_q_map_mqprio(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt,
 	vsi->tc_cfg.ena_tc = ena_tc ? ena_tc : 1;
 
 	pow = order_base_2(tc0_qcount);
-	qmap = ((tc0_offset << ICE_AQ_VSI_TC_Q_OFFSET_S) &
-		ICE_AQ_VSI_TC_Q_OFFSET_M) |
-		((pow << ICE_AQ_VSI_TC_Q_NUM_S) & ICE_AQ_VSI_TC_Q_NUM_M);
+	qmap = FIELD_PREP(ICE_AQ_VSI_TC_Q_OFFSET_M, tc0_offset);
+	qmap |= FIELD_PREP(ICE_AQ_VSI_TC_Q_NUM_M, pow);
 
 	ice_for_each_traffic_class(i) {
 		if (!(vsi->tc_cfg.ena_tc & BIT(i))) {
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index f24f5d1e6f9c..71bd27244941 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -91,6 +91,10 @@ void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc);
 struct ice_vsi *
 ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params);
 
+void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked);
+
+void ice_vsi_set_napi_queues(struct ice_vsi *vsi, bool locked);
+
 int ice_vsi_release(struct ice_vsi *vsi);
 
 void ice_vsi_close(struct ice_vsi *vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 6607fa6fe556..dd4a9bc0dfdc 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -14,6 +14,7 @@
 #include "ice_dcb_lib.h"
 #include "ice_dcb_nl.h"
 #include "ice_devlink.h"
+#include "ice_hwmon.h"
 /* Including ice_trace.h with CREATE_TRACE_POINTS defined will generate the
  * ice tracepoint functions. This must be done exactly once across the
  * ice driver.
@@ -979,7 +980,7 @@ static void ice_set_dflt_mib(struct ice_pf *pf)
 	 * Octets 13 - 20 are TSA values - leave as zeros
 	 */
 	buf[5] = 0x64;
-	len = (typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S;
+	len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen);
 	offset += len + 2;
 	tlv = (struct ice_lldp_org_tlv *)
 		((char *)tlv + sizeof(tlv->typelen) + len);
@@ -1013,7 +1014,7 @@ static void ice_set_dflt_mib(struct ice_pf *pf)
 
 	/* Octet 1 left as all zeros - PFC disabled */
 	buf[0] = 0x08;
-	len = (typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S;
+	len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen);
 	offset += len + 2;
 
 	if (ice_aq_set_lldp_mib(hw, mib_type, (void *)lldpmib, offset, NULL))
@@ -1252,6 +1253,32 @@ ice_handle_link_event(struct ice_pf *pf, struct ice_rq_event_info *event)
 }
 
 /**
+ * ice_get_fwlog_data - copy the FW log data from ARQ event
+ * @pf: PF that the FW log event is associated with
+ * @event: event structure containing FW log data
+ */
+static void
+ice_get_fwlog_data(struct ice_pf *pf, struct ice_rq_event_info *event)
+{
+	struct ice_fwlog_data *fwlog;
+	struct ice_hw *hw = &pf->hw;
+
+	fwlog = &hw->fwlog_ring.rings[hw->fwlog_ring.tail];
+
+	memset(fwlog->data, 0, PAGE_SIZE);
+	fwlog->data_size = le16_to_cpu(event->desc.datalen);
+
+	memcpy(fwlog->data, event->msg_buf, fwlog->data_size);
+	ice_fwlog_ring_increment(&hw->fwlog_ring.tail, hw->fwlog_ring.size);
+
+	if (ice_fwlog_ring_full(&hw->fwlog_ring)) {
+		/* the rings are full so bump the head to create room */
+		ice_fwlog_ring_increment(&hw->fwlog_ring.head,
+					 hw->fwlog_ring.size);
+	}
+}
+
+/**
  * ice_aq_prep_for_event - Prepare to wait for an AdminQ event from firmware
  * @pf: pointer to the PF private structure
  * @task: intermediate helper storage and identifier for waiting
@@ -1532,8 +1559,8 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
 
 			ice_vc_process_vf_msg(pf, &event, &data);
 			break;
-		case ice_aqc_opc_fw_logging:
-			ice_output_fw_log(hw, &event.desc, event.msg_buf);
+		case ice_aqc_opc_fw_logs_event:
+			ice_get_fwlog_data(pf, &event);
 			break;
 		case ice_aqc_opc_lldp_set_mib_change:
 			ice_dcb_process_lldp_set_mib_change(pf, &event);
@@ -1744,14 +1771,10 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 	/* find what triggered an MDD event */
 	reg = rd32(hw, GL_MDET_TX_PQM);
 	if (reg & GL_MDET_TX_PQM_VALID_M) {
-		u8 pf_num = (reg & GL_MDET_TX_PQM_PF_NUM_M) >>
-				GL_MDET_TX_PQM_PF_NUM_S;
-		u16 vf_num = (reg & GL_MDET_TX_PQM_VF_NUM_M) >>
-				GL_MDET_TX_PQM_VF_NUM_S;
-		u8 event = (reg & GL_MDET_TX_PQM_MAL_TYPE_M) >>
-				GL_MDET_TX_PQM_MAL_TYPE_S;
-		u16 queue = ((reg & GL_MDET_TX_PQM_QNUM_M) >>
-				GL_MDET_TX_PQM_QNUM_S);
+		u8 pf_num = FIELD_GET(GL_MDET_TX_PQM_PF_NUM_M, reg);
+		u16 vf_num = FIELD_GET(GL_MDET_TX_PQM_VF_NUM_M, reg);
+		u8 event = FIELD_GET(GL_MDET_TX_PQM_MAL_TYPE_M, reg);
+		u16 queue = FIELD_GET(GL_MDET_TX_PQM_QNUM_M, reg);
 
 		if (netif_msg_tx_err(pf))
 			dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
@@ -1761,14 +1784,10 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 
 	reg = rd32(hw, GL_MDET_TX_TCLAN_BY_MAC(hw));
 	if (reg & GL_MDET_TX_TCLAN_VALID_M) {
-		u8 pf_num = (reg & GL_MDET_TX_TCLAN_PF_NUM_M) >>
-				GL_MDET_TX_TCLAN_PF_NUM_S;
-		u16 vf_num = (reg & GL_MDET_TX_TCLAN_VF_NUM_M) >>
-				GL_MDET_TX_TCLAN_VF_NUM_S;
-		u8 event = (reg & GL_MDET_TX_TCLAN_MAL_TYPE_M) >>
-				GL_MDET_TX_TCLAN_MAL_TYPE_S;
-		u16 queue = ((reg & GL_MDET_TX_TCLAN_QNUM_M) >>
-				GL_MDET_TX_TCLAN_QNUM_S);
+		u8 pf_num = FIELD_GET(GL_MDET_TX_TCLAN_PF_NUM_M, reg);
+		u16 vf_num = FIELD_GET(GL_MDET_TX_TCLAN_VF_NUM_M, reg);
+		u8 event = FIELD_GET(GL_MDET_TX_TCLAN_MAL_TYPE_M, reg);
+		u16 queue = FIELD_GET(GL_MDET_TX_TCLAN_QNUM_M, reg);
 
 		if (netif_msg_tx_err(pf))
 			dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
@@ -1778,14 +1797,10 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 
 	reg = rd32(hw, GL_MDET_RX);
 	if (reg & GL_MDET_RX_VALID_M) {
-		u8 pf_num = (reg & GL_MDET_RX_PF_NUM_M) >>
-				GL_MDET_RX_PF_NUM_S;
-		u16 vf_num = (reg & GL_MDET_RX_VF_NUM_M) >>
-				GL_MDET_RX_VF_NUM_S;
-		u8 event = (reg & GL_MDET_RX_MAL_TYPE_M) >>
-				GL_MDET_RX_MAL_TYPE_S;
-		u16 queue = ((reg & GL_MDET_RX_QNUM_M) >>
-				GL_MDET_RX_QNUM_S);
+		u8 pf_num = FIELD_GET(GL_MDET_RX_PF_NUM_M, reg);
+		u16 vf_num = FIELD_GET(GL_MDET_RX_VF_NUM_M, reg);
+		u8 event = FIELD_GET(GL_MDET_RX_MAL_TYPE_M, reg);
+		u16 queue = FIELD_GET(GL_MDET_RX_QNUM_M, reg);
 
 		if (netif_msg_rx_err(pf))
 			dev_info(dev, "Malicious Driver Detection event %d on RX queue %d PF# %d VF# %d\n",
@@ -2146,7 +2161,7 @@ static int ice_configure_phy(struct ice_vsi *vsi)
 
 	/* Ensure we have media as we cannot configure a medialess port */
 	if (!(phy->link_info.link_info & ICE_AQ_MEDIA_AVAILABLE))
-		return -EPERM;
+		return -ENOMEDIUM;
 
 	ice_print_topo_conflict(vsi);
 
@@ -3031,6 +3046,7 @@ static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 static void ice_ena_misc_vector(struct ice_pf *pf)
 {
 	struct ice_hw *hw = &pf->hw;
+	u32 pf_intr_start_offset;
 	u32 val;
 
 	/* Disable anti-spoof detection interrupt to prevent spurious event
@@ -3059,6 +3075,47 @@ static void ice_ena_misc_vector(struct ice_pf *pf)
 	/* SW_ITR_IDX = 0, but don't change INTENA */
 	wr32(hw, GLINT_DYN_CTL(pf->oicr_irq.index),
 	     GLINT_DYN_CTL_SW_ITR_INDX_M | GLINT_DYN_CTL_INTENA_MSK_M);
+
+	if (!pf->hw.dev_caps.ts_dev_info.ts_ll_int_read)
+		return;
+	pf_intr_start_offset = rd32(hw, PFINT_ALLOC) & PFINT_ALLOC_FIRST;
+	wr32(hw, GLINT_DYN_CTL(pf->ll_ts_irq.index + pf_intr_start_offset),
+	     GLINT_DYN_CTL_SW_ITR_INDX_M | GLINT_DYN_CTL_INTENA_MSK_M);
+}
+
+/**
+ * ice_ll_ts_intr - ll_ts interrupt handler
+ * @irq: interrupt number
+ * @data: pointer to a q_vector
+ */
+static irqreturn_t ice_ll_ts_intr(int __always_unused irq, void *data)
+{
+	struct ice_pf *pf = data;
+	u32 pf_intr_start_offset;
+	struct ice_ptp_tx *tx;
+	unsigned long flags;
+	struct ice_hw *hw;
+	u32 val;
+	u8 idx;
+
+	hw = &pf->hw;
+	tx = &pf->ptp.port.tx;
+	spin_lock_irqsave(&tx->lock, flags);
+	ice_ptp_complete_tx_single_tstamp(tx);
+
+	idx = find_next_bit_wrap(tx->in_use, tx->len,
+				 tx->last_ll_ts_idx_read + 1);
+	if (idx != tx->len)
+		ice_ptp_req_tx_single_tstamp(tx, idx);
+	spin_unlock_irqrestore(&tx->lock, flags);
+
+	val = GLINT_DYN_CTL_INTENA_M | GLINT_DYN_CTL_CLEARPBA_M |
+	      (ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S);
+	pf_intr_start_offset = rd32(hw, PFINT_ALLOC) & PFINT_ALLOC_FIRST;
+	wr32(hw, GLINT_DYN_CTL(pf->ll_ts_irq.index + pf_intr_start_offset),
+	     val);
+
+	return IRQ_HANDLED;
 }
 
 /**
@@ -3069,6 +3126,7 @@ static void ice_ena_misc_vector(struct ice_pf *pf)
 static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 {
 	struct ice_pf *pf = (struct ice_pf *)data;
+	irqreturn_t ret = IRQ_HANDLED;
 	struct ice_hw *hw = &pf->hw;
 	struct device *dev;
 	u32 oicr, ena_mask;
@@ -3108,8 +3166,8 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 
 		/* we have a reset warning */
 		ena_mask &= ~PFINT_OICR_GRST_M;
-		reset = (rd32(hw, GLGEN_RSTAT) & GLGEN_RSTAT_RESET_TYPE_M) >>
-			GLGEN_RSTAT_RESET_TYPE_S;
+		reset = FIELD_GET(GLGEN_RSTAT_RESET_TYPE_M,
+				  rd32(hw, GLGEN_RSTAT));
 
 		if (reset == ICE_RESET_CORER)
 			pf->corer_count++;
@@ -3150,8 +3208,22 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 
 	if (oicr & PFINT_OICR_TSYN_TX_M) {
 		ena_mask &= ~PFINT_OICR_TSYN_TX_M;
-		if (!hw->reset_ongoing && ice_ptp_pf_handles_tx_interrupt(pf))
+		if (ice_pf_state_is_nominal(pf) &&
+		    pf->hw.dev_caps.ts_dev_info.ts_ll_int_read) {
+			struct ice_ptp_tx *tx = &pf->ptp.port.tx;
+			unsigned long flags;
+			u8 idx;
+
+			spin_lock_irqsave(&tx->lock, flags);
+			idx = find_next_bit_wrap(tx->in_use, tx->len,
+						 tx->last_ll_ts_idx_read + 1);
+			if (idx != tx->len)
+				ice_ptp_req_tx_single_tstamp(tx, idx);
+			spin_unlock_irqrestore(&tx->lock, flags);
+		} else if (ice_ptp_pf_handles_tx_interrupt(pf)) {
 			set_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread);
+			ret = IRQ_WAKE_THREAD;
+		}
 	}
 
 	if (oicr & PFINT_OICR_TSYN_EVNT_M) {
@@ -3167,7 +3239,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 					       GLTSYN_STAT_EVENT1_M |
 					       GLTSYN_STAT_EVENT2_M);
 
-			set_bit(ICE_MISC_THREAD_EXTTS_EVENT, pf->misc_thread);
+			ice_ptp_extts_event(pf);
 		}
 	}
 
@@ -3190,8 +3262,11 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 			set_bit(ICE_PFR_REQ, pf->state);
 		}
 	}
+	ice_service_task_schedule(pf);
+	if (ret == IRQ_HANDLED)
+		ice_irq_dynamic_ena(hw, NULL, NULL);
 
-	return IRQ_WAKE_THREAD;
+	return ret;
 }
 
 /**
@@ -3207,12 +3282,7 @@ static irqreturn_t ice_misc_intr_thread_fn(int __always_unused irq, void *data)
 	hw = &pf->hw;
 
 	if (ice_is_reset_in_progress(pf->state))
-		return IRQ_HANDLED;
-
-	ice_service_task_schedule(pf);
-
-	if (test_and_clear_bit(ICE_MISC_THREAD_EXTTS_EVENT, pf->misc_thread))
-		ice_ptp_extts_event(pf);
+		goto skip_irq;
 
 	if (test_and_clear_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread)) {
 		/* Process outstanding Tx timestamps. If there is more work,
@@ -3224,6 +3294,7 @@ static irqreturn_t ice_misc_intr_thread_fn(int __always_unused irq, void *data)
 		}
 	}
 
+skip_irq:
 	ice_irq_dynamic_ena(hw, NULL, NULL);
 
 	return IRQ_HANDLED;
@@ -3254,6 +3325,20 @@ static void ice_dis_ctrlq_interrupts(struct ice_hw *hw)
 }
 
 /**
+ * ice_free_irq_msix_ll_ts- Unroll ll_ts vector setup
+ * @pf: board private structure
+ */
+static void ice_free_irq_msix_ll_ts(struct ice_pf *pf)
+{
+	int irq_num = pf->ll_ts_irq.virq;
+
+	synchronize_irq(irq_num);
+	devm_free_irq(ice_pf_to_dev(pf), irq_num, pf);
+
+	ice_free_irq(pf, pf->ll_ts_irq);
+}
+
+/**
  * ice_free_irq_msix_misc - Unroll misc vector setup
  * @pf: board private structure
  */
@@ -3272,6 +3357,8 @@ static void ice_free_irq_msix_misc(struct ice_pf *pf)
 	devm_free_irq(ice_pf_to_dev(pf), misc_irq_num, pf);
 
 	ice_free_irq(pf, pf->oicr_irq);
+	if (pf->hw.dev_caps.ts_dev_info.ts_ll_int_read)
+		ice_free_irq_msix_ll_ts(pf);
 }
 
 /**
@@ -3297,10 +3384,12 @@ static void ice_ena_ctrlq_interrupts(struct ice_hw *hw, u16 reg_idx)
 	       PFINT_MBX_CTL_CAUSE_ENA_M);
 	wr32(hw, PFINT_MBX_CTL, val);
 
-	/* This enables Sideband queue Interrupt causes */
-	val = ((reg_idx & PFINT_SB_CTL_MSIX_INDX_M) |
-	       PFINT_SB_CTL_CAUSE_ENA_M);
-	wr32(hw, PFINT_SB_CTL, val);
+	if (!hw->dev_caps.ts_dev_info.ts_ll_int_read) {
+		/* enable Sideband queue Interrupt causes */
+		val = ((reg_idx & PFINT_SB_CTL_MSIX_INDX_M) |
+		       PFINT_SB_CTL_CAUSE_ENA_M);
+		wr32(hw, PFINT_SB_CTL, val);
+	}
 
 	ice_flush(hw);
 }
@@ -3317,13 +3406,17 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
 {
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
-	struct msi_map oicr_irq;
+	u32 pf_intr_start_offset;
+	struct msi_map irq;
 	int err = 0;
 
 	if (!pf->int_name[0])
 		snprintf(pf->int_name, sizeof(pf->int_name) - 1, "%s-%s:misc",
 			 dev_driver_string(dev), dev_name(dev));
 
+	if (!pf->int_name_ll_ts[0])
+		snprintf(pf->int_name_ll_ts, sizeof(pf->int_name_ll_ts) - 1,
+			 "%s-%s:ll_ts", dev_driver_string(dev), dev_name(dev));
 	/* Do not request IRQ but do enable OICR interrupt since settings are
 	 * lost during reset. Note that this function is called only during
 	 * rebuild path and not while reset is in progress.
@@ -3332,11 +3425,11 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
 		goto skip_req_irq;
 
 	/* reserve one vector in irq_tracker for misc interrupts */
-	oicr_irq = ice_alloc_irq(pf, false);
-	if (oicr_irq.index < 0)
-		return oicr_irq.index;
+	irq = ice_alloc_irq(pf, false);
+	if (irq.index < 0)
+		return irq.index;
 
-	pf->oicr_irq = oicr_irq;
+	pf->oicr_irq = irq;
 	err = devm_request_threaded_irq(dev, pf->oicr_irq.virq, ice_misc_intr,
 					ice_misc_intr_thread_fn, 0,
 					pf->int_name, pf);
@@ -3347,10 +3440,34 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
 		return err;
 	}
 
+	/* reserve one vector in irq_tracker for ll_ts interrupt */
+	if (!pf->hw.dev_caps.ts_dev_info.ts_ll_int_read)
+		goto skip_req_irq;
+
+	irq = ice_alloc_irq(pf, false);
+	if (irq.index < 0)
+		return irq.index;
+
+	pf->ll_ts_irq = irq;
+	err = devm_request_irq(dev, pf->ll_ts_irq.virq, ice_ll_ts_intr, 0,
+			       pf->int_name_ll_ts, pf);
+	if (err) {
+		dev_err(dev, "devm_request_irq for %s failed: %d\n",
+			pf->int_name_ll_ts, err);
+		ice_free_irq(pf, pf->ll_ts_irq);
+		return err;
+	}
+
 skip_req_irq:
 	ice_ena_misc_vector(pf);
 
 	ice_ena_ctrlq_interrupts(hw, pf->oicr_irq.index);
+	/* This enables LL TS interrupt */
+	pf_intr_start_offset = rd32(hw, PFINT_ALLOC) & PFINT_ALLOC_FIRST;
+	if (pf->hw.dev_caps.ts_dev_info.ts_ll_int_read)
+		wr32(hw, PFINT_SB_CTL,
+		     ((pf->ll_ts_irq.index + pf_intr_start_offset) &
+		      PFINT_SB_CTL_MSIX_INDX_M) | PFINT_SB_CTL_CAUSE_ENA_M);
 	wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->oicr_irq.index),
 	     ITR_REG_ALIGN(ICE_ITR_8K) >> ICE_ITR_GRAN_S);
 
@@ -3375,9 +3492,11 @@ static void ice_napi_add(struct ice_vsi *vsi)
 	if (!vsi->netdev)
 		return;
 
-	ice_for_each_q_vector(vsi, v_idx)
+	ice_for_each_q_vector(vsi, v_idx) {
 		netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx]->napi,
 			       ice_napi_poll);
+		ice_q_vector_set_napi_queues(vsi->q_vectors[v_idx], false);
+	}
 }
 
 /**
@@ -3397,6 +3516,7 @@ static void ice_set_ops(struct ice_vsi *vsi)
 
 	netdev->netdev_ops = &ice_netdev_ops;
 	netdev->udp_tunnel_nic_info = &pf->hw.udp_tunnel_nic;
+	netdev->xdp_metadata_ops = &ice_xdp_md_ops;
 	ice_set_ethtool_ops(netdev);
 
 	if (vsi->type != ICE_VSI_PF)
@@ -4361,6 +4481,19 @@ static void ice_print_wake_reason(struct ice_pf *pf)
 }
 
 /**
+ * ice_pf_fwlog_update_module - update 1 module
+ * @pf: pointer to the PF struct
+ * @log_level: log_level to use for the @module
+ * @module: module to update
+ */
+void ice_pf_fwlog_update_module(struct ice_pf *pf, int log_level, int module)
+{
+	struct ice_hw *hw = &pf->hw;
+
+	hw->fwlog_cfg.module_entries[module].log_level = log_level;
+}
+
+/**
  * ice_register_netdev - register netdev
  * @vsi: pointer to the VSI struct
  */
@@ -4685,6 +4818,8 @@ static void ice_init_features(struct ice_pf *pf)
 
 	if (ice_init_lag(pf))
 		dev_warn(dev, "Failed to init link aggregation support\n");
+
+	ice_hwmon_init(pf);
 }
 
 static void ice_deinit_features(struct ice_pf *pf)
@@ -4702,6 +4837,8 @@ static void ice_deinit_features(struct ice_pf *pf)
 		ice_ptp_release(pf);
 	if (test_bit(ICE_FLAG_DPLL, pf->flags))
 		ice_dpll_deinit(pf);
+	if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV)
+		xa_destroy(&pf->eswitch.reprs);
 }
 
 static void ice_init_wakeup(struct ice_pf *pf)
@@ -5203,11 +5340,15 @@ static void ice_remove(struct pci_dev *pdev)
 		msleep(100);
 	}
 
+	ice_debugfs_exit();
+
 	if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) {
 		set_bit(ICE_VF_RESETS_DISABLED, pf->state);
 		ice_free_vfs(pf);
 	}
 
+	ice_hwmon_exit(pf);
+
 	ice_service_task_stop(pf);
 	ice_aq_cancel_waiting_tasks(pf);
 	set_bit(ICE_DOWN, pf->state);
@@ -5672,6 +5813,8 @@ static int __init ice_module_init(void)
 		goto err_dest_wq;
 	}
 
+	ice_debugfs_init();
+
 	status = pci_register_driver(&ice_driver);
 	if (status) {
 		pr_err("failed to register PCI driver, err %d\n", status);
@@ -5682,6 +5825,7 @@ static int __init ice_module_init(void)
 
 err_dest_lag_wq:
 	destroy_workqueue(ice_lag_wq);
+	ice_debugfs_exit();
 err_dest_wq:
 	destroy_workqueue(ice_wq);
 	return status;
@@ -6041,6 +6185,23 @@ ice_fix_features(struct net_device *netdev, netdev_features_t features)
 }
 
 /**
+ * ice_set_rx_rings_vlan_proto - update rings with new stripped VLAN proto
+ * @vsi: PF's VSI
+ * @vlan_ethertype: VLAN ethertype (802.1Q or 802.1ad) in network byte order
+ *
+ * Store current stripped VLAN proto in ring packet context,
+ * so it can be accessed more efficiently by packet processing code.
+ */
+static void
+ice_set_rx_rings_vlan_proto(struct ice_vsi *vsi, __be16 vlan_ethertype)
+{
+	u16 i;
+
+	ice_for_each_alloc_rxq(vsi, i)
+		vsi->rx_rings[i]->pkt_ctx.vlan_proto = vlan_ethertype;
+}
+
+/**
  * ice_set_vlan_offload_features - set VLAN offload features for the PF VSI
  * @vsi: PF's VSI
  * @features: features used to determine VLAN offload settings
@@ -6082,6 +6243,9 @@ ice_set_vlan_offload_features(struct ice_vsi *vsi, netdev_features_t features)
 	if (strip_err || insert_err)
 		return -EIO;
 
+	ice_set_rx_rings_vlan_proto(vsi, enable_stripping ?
+				    htons(vlan_ethertype) : 0);
+
 	return 0;
 }
 
@@ -6670,13 +6834,11 @@ void ice_update_vsi_stats(struct ice_vsi *vsi)
 		cur_ns->rx_crc_errors = pf->stats.crc_errors;
 		cur_ns->rx_errors = pf->stats.crc_errors +
 				    pf->stats.illegal_bytes +
-				    pf->stats.rx_len_errors +
 				    pf->stats.rx_undersize +
 				    pf->hw_csum_rx_error +
 				    pf->stats.rx_jabber +
 				    pf->stats.rx_fragments +
 				    pf->stats.rx_oversize;
-		cur_ns->rx_length_errors = pf->stats.rx_len_errors;
 		/* record drops from the port level */
 		cur_ns->rx_missed_errors = pf->stats.eth.rx_discards;
 	}
@@ -6816,9 +6978,6 @@ void ice_update_pf_stats(struct ice_pf *pf)
 			  &prev_ps->mac_remote_faults,
 			  &cur_ps->mac_remote_faults);
 
-	ice_stat_update32(hw, GLPRT_RLEC(port), pf->stat_prev_loaded,
-			  &prev_ps->rx_len_errors, &cur_ps->rx_len_errors);
-
 	ice_stat_update32(hw, GLPRT_RUC(port), pf->stat_prev_loaded,
 			  &prev_ps->rx_undersize, &cur_ps->rx_undersize);
 
@@ -7401,18 +7560,9 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 		goto err_vsi_rebuild;
 	}
 
-	/* configure PTP timestamping after VSI rebuild */
-	if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) {
-		if (pf->ptp.tx_interrupt_mode == ICE_PTP_TX_INTERRUPT_SELF)
-			ice_ptp_cfg_timestamp(pf, false);
-		else if (pf->ptp.tx_interrupt_mode == ICE_PTP_TX_INTERRUPT_ALL)
-			/* for E82x PHC owner always need to have interrupts */
-			ice_ptp_cfg_timestamp(pf, true);
-	}
-
-	err = ice_vsi_rebuild_by_type(pf, ICE_VSI_SWITCHDEV_CTRL);
+	err = ice_eswitch_rebuild(pf);
 	if (err) {
-		dev_err(dev, "Switchdev CTRL VSI rebuild failed: %d\n", err);
+		dev_err(dev, "Switchdev rebuild failed: %d\n", err);
 		goto err_vsi_rebuild;
 	}
 
@@ -7461,6 +7611,9 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 	ice_plug_aux_dev(pf);
 	if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG))
 		ice_lag_rebuild(pf);
+
+	/* Restore timestamp mode settings after VSI rebuild */
+	ice_ptp_restore_timestamp_mode(pf);
 	return;
 
 err_vsi_rebuild:
@@ -7710,6 +7863,59 @@ int ice_get_rss_key(struct ice_vsi *vsi, u8 *seed)
 }
 
 /**
+ * ice_set_rss_hfunc - Set RSS HASH function
+ * @vsi: Pointer to VSI structure
+ * @hfunc: hash function (ICE_AQ_VSI_Q_OPT_RSS_*)
+ *
+ * Returns 0 on success, negative on failure
+ */
+int ice_set_rss_hfunc(struct ice_vsi *vsi, u8 hfunc)
+{
+	struct ice_hw *hw = &vsi->back->hw;
+	struct ice_vsi_ctx *ctx;
+	bool symm;
+	int err;
+
+	if (hfunc == vsi->rss_hfunc)
+		return 0;
+
+	if (hfunc != ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ &&
+	    hfunc != ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ)
+		return -EOPNOTSUPP;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_Q_OPT_VALID);
+	ctx->info.q_opt_rss = vsi->info.q_opt_rss;
+	ctx->info.q_opt_rss &= ~ICE_AQ_VSI_Q_OPT_RSS_HASH_M;
+	ctx->info.q_opt_rss |=
+		FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_HASH_M, hfunc);
+	ctx->info.q_opt_tc = vsi->info.q_opt_tc;
+	ctx->info.q_opt_flags = vsi->info.q_opt_rss;
+
+	err = ice_update_vsi(hw, vsi->idx, ctx, NULL);
+	if (err) {
+		dev_err(ice_pf_to_dev(vsi->back), "Failed to configure RSS hash for VSI %d, error %d\n",
+			vsi->vsi_num, err);
+	} else {
+		vsi->info.q_opt_rss = ctx->info.q_opt_rss;
+		vsi->rss_hfunc = hfunc;
+		netdev_info(vsi->netdev, "Hash function set to: %sToeplitz\n",
+			    hfunc == ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ ?
+			    "Symmetric " : "");
+	}
+	kfree(ctx);
+	if (err)
+		return err;
+
+	/* Fix the symmetry setting for all existing RSS configurations */
+	symm = !!(hfunc == ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ);
+	return ice_set_rss_cfg_symm(hw, vsi, symm);
+}
+
+/**
  * ice_bridge_getlink - Get the hardware bridge mode
  * @skb: skb buff
  * @pid: process ID
@@ -7895,8 +8101,8 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 		struct ice_hw *hw = &pf->hw;
 		u32 head, val = 0;
 
-		head = (rd32(hw, QTX_COMM_HEAD(vsi->txq_map[txqueue])) &
-			QTX_COMM_HEAD_HEAD_M) >> QTX_COMM_HEAD_HEAD_S;
+		head = FIELD_GET(QTX_COMM_HEAD_HEAD_M,
+				 rd32(hw, QTX_COMM_HEAD(vsi->txq_map[txqueue])));
 		/* Read interrupt register */
 		val = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx));
 
@@ -8144,13 +8350,12 @@ static int ice_add_vsi_to_fdir(struct ice_pf *pf, struct ice_vsi *vsi)
 
 		for (tun = 0; tun < ICE_FD_HW_SEG_MAX; tun++) {
 			enum ice_flow_priority prio;
-			u64 prof_id;
 
 			/* add this VSI to FDir profile for this flow */
 			prio = ICE_FLOW_PRIO_NORMAL;
 			prof = hw->fdir_prof[flow];
-			prof_id = flow + tun * ICE_FLTR_PTYPE_MAX;
-			status = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id,
+			status = ice_flow_add_entry(hw, ICE_BLK_FD,
+						    prof->prof_id[tun],
 						    prof->vsi_h[0], vsi->idx,
 						    prio, prof->fdir_seg[tun],
 						    &entry_h);
@@ -9193,8 +9398,14 @@ int ice_stop(struct net_device *netdev)
 		int link_err = ice_force_phys_link_state(vsi, false);
 
 		if (link_err) {
-			netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n",
-				   vsi->vsi_num, link_err);
+			if (link_err == -ENOMEDIUM)
+				netdev_info(vsi->netdev, "Skipping link reconfig - no media attached, VSI %d\n",
+					    vsi->vsi_num);
+			else
+				netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n",
+					   vsi->vsi_num, link_err);
+
+			ice_vsi_close(vsi);
 			return -EIO;
 		}
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c
index f6f52a248066..d4e05d2cb30c 100644
--- a/drivers/net/ethernet/intel/ice/ice_nvm.c
+++ b/drivers/net/ethernet/intel/ice/ice_nvm.c
@@ -571,8 +571,8 @@ ice_get_nvm_ver_info(struct ice_hw *hw, enum ice_bank_select bank, struct ice_nv
 		return status;
 	}
 
-	nvm->major = (ver & ICE_NVM_VER_HI_MASK) >> ICE_NVM_VER_HI_SHIFT;
-	nvm->minor = (ver & ICE_NVM_VER_LO_MASK) >> ICE_NVM_VER_LO_SHIFT;
+	nvm->major = FIELD_GET(ICE_NVM_VER_HI_MASK, ver);
+	nvm->minor = FIELD_GET(ICE_NVM_VER_LO_MASK, ver);
 
 	status = ice_read_nvm_sr_copy(hw, bank, ICE_SR_NVM_EETRACK_LO, &eetrack_lo);
 	if (status) {
@@ -706,9 +706,9 @@ ice_get_orom_ver_info(struct ice_hw *hw, enum ice_bank_select bank, struct ice_o
 
 	combo_ver = le32_to_cpu(civd.combo_ver);
 
-	orom->major = (u8)((combo_ver & ICE_OROM_VER_MASK) >> ICE_OROM_VER_SHIFT);
-	orom->patch = (u8)(combo_ver & ICE_OROM_VER_PATCH_MASK);
-	orom->build = (u16)((combo_ver & ICE_OROM_VER_BUILD_MASK) >> ICE_OROM_VER_BUILD_SHIFT);
+	orom->major = FIELD_GET(ICE_OROM_VER_MASK, combo_ver);
+	orom->patch = FIELD_GET(ICE_OROM_VER_PATCH_MASK, combo_ver);
+	orom->build = FIELD_GET(ICE_OROM_VER_BUILD_MASK, combo_ver);
 
 	return 0;
 }
@@ -950,7 +950,8 @@ static int ice_determine_active_flash_banks(struct ice_hw *hw)
 	}
 
 	/* Check that the control word indicates validity */
-	if ((ctrl_word & ICE_SR_CTRL_WORD_1_M) >> ICE_SR_CTRL_WORD_1_S != ICE_SR_CTRL_WORD_VALID) {
+	if (FIELD_GET(ICE_SR_CTRL_WORD_1_M, ctrl_word) !=
+	    ICE_SR_CTRL_WORD_VALID) {
 		ice_debug(hw, ICE_DBG_NVM, "Shadow RAM control word is invalid\n");
 		return -EIO;
 	}
@@ -1027,7 +1028,7 @@ int ice_init_nvm(struct ice_hw *hw)
 	 * as the blank mode may be used in the factory line.
 	 */
 	gens_stat = rd32(hw, GLNVM_GENS);
-	sr_size = (gens_stat & GLNVM_GENS_SR_SIZE_M) >> GLNVM_GENS_SR_SIZE_S;
+	sr_size = FIELD_GET(GLNVM_GENS_SR_SIZE_M, gens_stat);
 
 	/* Switching to words (sr_size contains power of 2) */
 	flash->sr_words = BIT(sr_size) * ICE_SR_WORDS_IN_1KB;
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 1eddcbe89b0c..3b6605c8585e 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -7,7 +7,7 @@
 
 #define E810_OUT_PROP_DELAY_NS 1
 
-#define UNKNOWN_INCVAL_E822 0x100000000ULL
+#define UNKNOWN_INCVAL_E82X 0x100000000ULL
 
 static const struct ptp_pin_desc ice_pin_desc_e810t[] = {
 	/* name    idx   func         chan */
@@ -256,48 +256,42 @@ ice_verify_pin_e810t(struct ptp_clock_info *info, unsigned int pin,
 }
 
 /**
- * ice_ptp_configure_tx_tstamp - Enable or disable Tx timestamp interrupt
- * @pf: The PF pointer to search in
- * @on: bool value for whether timestamp interrupt is enabled or disabled
+ * ice_ptp_cfg_tx_interrupt - Configure Tx timestamp interrupt for the device
+ * @pf: Board private structure
+ *
+ * Program the device to respond appropriately to the Tx timestamp interrupt
+ * cause.
  */
-static void ice_ptp_configure_tx_tstamp(struct ice_pf *pf, bool on)
+static void ice_ptp_cfg_tx_interrupt(struct ice_pf *pf)
 {
+	struct ice_hw *hw = &pf->hw;
+	bool enable;
 	u32 val;
 
+	switch (pf->ptp.tx_interrupt_mode) {
+	case ICE_PTP_TX_INTERRUPT_ALL:
+		/* React to interrupts across all quads. */
+		wr32(hw, PFINT_TSYN_MSK + (0x4 * hw->pf_id), (u32)0x1f);
+		enable = true;
+		break;
+	case ICE_PTP_TX_INTERRUPT_NONE:
+		/* Do not react to interrupts on any quad. */
+		wr32(hw, PFINT_TSYN_MSK + (0x4 * hw->pf_id), (u32)0x0);
+		enable = false;
+		break;
+	case ICE_PTP_TX_INTERRUPT_SELF:
+	default:
+		enable = pf->ptp.tstamp_config.tx_type == HWTSTAMP_TX_ON;
+		break;
+	}
+
 	/* Configure the Tx timestamp interrupt */
-	val = rd32(&pf->hw, PFINT_OICR_ENA);
-	if (on)
+	val = rd32(hw, PFINT_OICR_ENA);
+	if (enable)
 		val |= PFINT_OICR_TSYN_TX_M;
 	else
 		val &= ~PFINT_OICR_TSYN_TX_M;
-	wr32(&pf->hw, PFINT_OICR_ENA, val);
-}
-
-/**
- * ice_set_tx_tstamp - Enable or disable Tx timestamping
- * @pf: The PF pointer to search in
- * @on: bool value for whether timestamps are enabled or disabled
- */
-static void ice_set_tx_tstamp(struct ice_pf *pf, bool on)
-{
-	struct ice_vsi *vsi;
-	u16 i;
-
-	vsi = ice_get_main_vsi(pf);
-	if (!vsi)
-		return;
-
-	/* Set the timestamp enable flag for all the Tx rings */
-	ice_for_each_txq(vsi, i) {
-		if (!vsi->tx_rings[i])
-			continue;
-		vsi->tx_rings[i]->ptp_tx = on;
-	}
-
-	if (pf->ptp.tx_interrupt_mode == ICE_PTP_TX_INTERRUPT_SELF)
-		ice_ptp_configure_tx_tstamp(pf, on);
-
-	pf->ptp.tstamp_config.tx_type = on ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	wr32(hw, PFINT_OICR_ENA, val);
 }
 
 /**
@@ -311,7 +305,7 @@ static void ice_set_rx_tstamp(struct ice_pf *pf, bool on)
 	u16 i;
 
 	vsi = ice_get_main_vsi(pf);
-	if (!vsi)
+	if (!vsi || !vsi->rx_rings)
 		return;
 
 	/* Set the timestamp flag for all the Rx rings */
@@ -320,23 +314,50 @@ static void ice_set_rx_tstamp(struct ice_pf *pf, bool on)
 			continue;
 		vsi->rx_rings[i]->ptp_rx = on;
 	}
+}
+
+/**
+ * ice_ptp_disable_timestamp_mode - Disable current timestamp mode
+ * @pf: Board private structure
+ *
+ * Called during preparation for reset to temporarily disable timestamping on
+ * the device. Called during remove to disable timestamping while cleaning up
+ * driver resources.
+ */
+static void ice_ptp_disable_timestamp_mode(struct ice_pf *pf)
+{
+	struct ice_hw *hw = &pf->hw;
+	u32 val;
+
+	val = rd32(hw, PFINT_OICR_ENA);
+	val &= ~PFINT_OICR_TSYN_TX_M;
+	wr32(hw, PFINT_OICR_ENA, val);
 
-	pf->ptp.tstamp_config.rx_filter = on ? HWTSTAMP_FILTER_ALL :
-					       HWTSTAMP_FILTER_NONE;
+	ice_set_rx_tstamp(pf, false);
 }
 
 /**
- * ice_ptp_cfg_timestamp - Configure timestamp for init/deinit
+ * ice_ptp_restore_timestamp_mode - Restore timestamp configuration
  * @pf: Board private structure
- * @ena: bool value to enable or disable time stamp
  *
- * This function will configure timestamping during PTP initialization
- * and deinitialization
+ * Called at the end of rebuild to restore timestamp configuration after
+ * a device reset.
  */
-void ice_ptp_cfg_timestamp(struct ice_pf *pf, bool ena)
+void ice_ptp_restore_timestamp_mode(struct ice_pf *pf)
 {
-	ice_set_tx_tstamp(pf, ena);
-	ice_set_rx_tstamp(pf, ena);
+	struct ice_hw *hw = &pf->hw;
+	bool enable_rx;
+
+	ice_ptp_cfg_tx_interrupt(pf);
+
+	enable_rx = pf->ptp.tstamp_config.rx_filter == HWTSTAMP_FILTER_ALL;
+	ice_set_rx_tstamp(pf, enable_rx);
+
+	/* Trigger an immediate software interrupt to ensure that timestamps
+	 * which occurred during reset are handled now.
+	 */
+	wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M);
+	ice_flush(hw);
 }
 
 /**
@@ -504,6 +525,119 @@ ice_ptp_is_tx_tracker_up(struct ice_ptp_tx *tx)
 }
 
 /**
+ * ice_ptp_req_tx_single_tstamp - Request Tx timestamp for a port from FW
+ * @tx: the PTP Tx timestamp tracker
+ * @idx: index of the timestamp to request
+ */
+void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx)
+{
+	struct ice_ptp_port *ptp_port;
+	struct sk_buff *skb;
+	struct ice_pf *pf;
+
+	if (!tx->init)
+		return;
+
+	ptp_port = container_of(tx, struct ice_ptp_port, tx);
+	pf = ptp_port_to_pf(ptp_port);
+
+	/* Drop packets which have waited for more than 2 seconds */
+	if (time_is_before_jiffies(tx->tstamps[idx].start + 2 * HZ)) {
+		/* Count the number of Tx timestamps that timed out */
+		pf->ptp.tx_hwtstamp_timeouts++;
+
+		skb = tx->tstamps[idx].skb;
+		tx->tstamps[idx].skb = NULL;
+		clear_bit(idx, tx->in_use);
+
+		dev_kfree_skb_any(skb);
+		return;
+	}
+
+	ice_trace(tx_tstamp_fw_req, tx->tstamps[idx].skb, idx);
+
+	/* Write TS index to read to the PF register so the FW can read it */
+	wr32(&pf->hw, PF_SB_ATQBAL,
+	     TS_LL_READ_TS_INTR | FIELD_PREP(TS_LL_READ_TS_IDX, idx) |
+	     TS_LL_READ_TS);
+	tx->last_ll_ts_idx_read = idx;
+}
+
+/**
+ * ice_ptp_complete_tx_single_tstamp - Complete Tx timestamp for a port
+ * @tx: the PTP Tx timestamp tracker
+ */
+void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx)
+{
+	struct skb_shared_hwtstamps shhwtstamps = {};
+	u8 idx = tx->last_ll_ts_idx_read;
+	struct ice_ptp_port *ptp_port;
+	u64 raw_tstamp, tstamp;
+	bool drop_ts = false;
+	struct sk_buff *skb;
+	struct ice_pf *pf;
+	u32 val;
+
+	if (!tx->init || tx->last_ll_ts_idx_read < 0)
+		return;
+
+	ptp_port = container_of(tx, struct ice_ptp_port, tx);
+	pf = ptp_port_to_pf(ptp_port);
+
+	ice_trace(tx_tstamp_fw_done, tx->tstamps[idx].skb, idx);
+
+	val = rd32(&pf->hw, PF_SB_ATQBAL);
+
+	/* When the bit is cleared, the TS is ready in the register */
+	if (val & TS_LL_READ_TS) {
+		dev_err(ice_pf_to_dev(pf), "Failed to get the Tx tstamp - FW not ready");
+		return;
+	}
+
+	/* High 8 bit value of the TS is on the bits 16:23 */
+	raw_tstamp = FIELD_GET(TS_LL_READ_TS_HIGH, val);
+	raw_tstamp <<= 32;
+
+	/* Read the low 32 bit value */
+	raw_tstamp |= (u64)rd32(&pf->hw, PF_SB_ATQBAH);
+
+	/* For PHYs which don't implement a proper timestamp ready bitmap,
+	 * verify that the timestamp value is different from the last cached
+	 * timestamp. If it is not, skip this for now assuming it hasn't yet
+	 * been captured by hardware.
+	 */
+	if (!drop_ts && tx->verify_cached &&
+	    raw_tstamp == tx->tstamps[idx].cached_tstamp)
+		return;
+
+	if (tx->verify_cached && raw_tstamp)
+		tx->tstamps[idx].cached_tstamp = raw_tstamp;
+	clear_bit(idx, tx->in_use);
+	skb = tx->tstamps[idx].skb;
+	tx->tstamps[idx].skb = NULL;
+	if (test_and_clear_bit(idx, tx->stale))
+		drop_ts = true;
+
+	if (!skb)
+		return;
+
+	if (drop_ts) {
+		dev_kfree_skb_any(skb);
+		return;
+	}
+
+	/* Extend the timestamp using cached PHC time */
+	tstamp = ice_ptp_extend_40b_ts(pf, raw_tstamp);
+	if (tstamp) {
+		shhwtstamps.hwtstamp = ns_to_ktime(tstamp);
+		ice_trace(tx_tstamp_complete, skb, idx);
+	}
+
+	skb_tstamp_tx(skb, &shhwtstamps);
+	dev_kfree_skb_any(skb);
+}
+
+/**
  * ice_ptp_process_tx_tstamp - Process Tx timestamps for a port
  * @tx: the PTP Tx timestamp tracker
  *
@@ -554,6 +688,7 @@ ice_ptp_is_tx_tracker_up(struct ice_ptp_tx *tx)
 static void ice_ptp_process_tx_tstamp(struct ice_ptp_tx *tx)
 {
 	struct ice_ptp_port *ptp_port;
+	unsigned long flags;
 	struct ice_pf *pf;
 	struct ice_hw *hw;
 	u64 tstamp_ready;
@@ -625,7 +760,7 @@ static void ice_ptp_process_tx_tstamp(struct ice_ptp_tx *tx)
 			drop_ts = true;
 
 skip_ts_read:
-		spin_lock(&tx->lock);
+		spin_lock_irqsave(&tx->lock, flags);
 		if (tx->verify_cached && raw_tstamp)
 			tx->tstamps[idx].cached_tstamp = raw_tstamp;
 		clear_bit(idx, tx->in_use);
@@ -633,7 +768,7 @@ skip_ts_read:
 		tx->tstamps[idx].skb = NULL;
 		if (test_and_clear_bit(idx, tx->stale))
 			drop_ts = true;
-		spin_unlock(&tx->lock);
+		spin_unlock_irqrestore(&tx->lock, flags);
 
 		/* It is unlikely but possible that the SKB will have been
 		 * flushed at this point due to link change or teardown.
@@ -684,7 +819,9 @@ static enum ice_tx_tstamp_work ice_ptp_tx_tstamp_owner(struct ice_pf *pf)
 
 		/* Read the Tx ready status first */
 		err = ice_get_phy_tx_tstamp_ready(&pf->hw, i, &tstamp_ready);
-		if (err || tstamp_ready)
+		if (err)
+			break;
+		else if (tstamp_ready)
 			return ICE_TX_TSTAMP_WORK_PENDING;
 	}
 
@@ -701,6 +838,7 @@ static enum ice_tx_tstamp_work ice_ptp_tx_tstamp_owner(struct ice_pf *pf)
 static enum ice_tx_tstamp_work ice_ptp_tx_tstamp(struct ice_ptp_tx *tx)
 {
 	bool more_timestamps;
+	unsigned long flags;
 
 	if (!tx->init)
 		return ICE_TX_TSTAMP_WORK_DONE;
@@ -709,9 +847,9 @@ static enum ice_tx_tstamp_work ice_ptp_tx_tstamp(struct ice_ptp_tx *tx)
 	ice_ptp_process_tx_tstamp(tx);
 
 	/* Check if there are outstanding Tx timestamps */
-	spin_lock(&tx->lock);
+	spin_lock_irqsave(&tx->lock, flags);
 	more_timestamps = tx->init && !bitmap_empty(tx->in_use, tx->len);
-	spin_unlock(&tx->lock);
+	spin_unlock_irqrestore(&tx->lock, flags);
 
 	if (more_timestamps)
 		return ICE_TX_TSTAMP_WORK_PENDING;
@@ -748,6 +886,7 @@ ice_ptp_alloc_tx_tracker(struct ice_ptp_tx *tx)
 	tx->in_use = in_use;
 	tx->stale = stale;
 	tx->init = 1;
+	tx->last_ll_ts_idx_read = -1;
 
 	spin_lock_init(&tx->lock);
 
@@ -765,6 +904,7 @@ static void
 ice_ptp_flush_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx)
 {
 	struct ice_hw *hw = &pf->hw;
+	unsigned long flags;
 	u64 tstamp_ready;
 	int err;
 	u8 idx;
@@ -788,12 +928,12 @@ ice_ptp_flush_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx)
 		if (!hw->reset_ongoing && (tstamp_ready & BIT_ULL(phy_idx)))
 			ice_clear_phy_tstamp(hw, tx->block, phy_idx);
 
-		spin_lock(&tx->lock);
+		spin_lock_irqsave(&tx->lock, flags);
 		skb = tx->tstamps[idx].skb;
 		tx->tstamps[idx].skb = NULL;
 		clear_bit(idx, tx->in_use);
 		clear_bit(idx, tx->stale);
-		spin_unlock(&tx->lock);
+		spin_unlock_irqrestore(&tx->lock, flags);
 
 		/* Count the number of Tx timestamps flushed */
 		pf->ptp.tx_hwtstamp_flushed++;
@@ -817,9 +957,11 @@ ice_ptp_flush_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx)
 static void
 ice_ptp_mark_tx_tracker_stale(struct ice_ptp_tx *tx)
 {
-	spin_lock(&tx->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&tx->lock, flags);
 	bitmap_or(tx->stale, tx->stale, tx->in_use, tx->len);
-	spin_unlock(&tx->lock);
+	spin_unlock_irqrestore(&tx->lock, flags);
 }
 
 /**
@@ -832,9 +974,11 @@ ice_ptp_mark_tx_tracker_stale(struct ice_ptp_tx *tx)
 static void
 ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx)
 {
-	spin_lock(&tx->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&tx->lock, flags);
 	tx->init = 0;
-	spin_unlock(&tx->lock);
+	spin_unlock_irqrestore(&tx->lock, flags);
 
 	/* wait for potentially outstanding interrupt to complete */
 	synchronize_irq(pf->oicr_irq.virq);
@@ -854,7 +998,7 @@ ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx)
 }
 
 /**
- * ice_ptp_init_tx_e822 - Initialize tracking for Tx timestamps
+ * ice_ptp_init_tx_e82x - Initialize tracking for Tx timestamps
  * @pf: Board private structure
  * @tx: the Tx tracking structure to initialize
  * @port: the port this structure tracks
@@ -865,11 +1009,11 @@ ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx)
  * registers into chunks based on the port number.
  */
 static int
-ice_ptp_init_tx_e822(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port)
+ice_ptp_init_tx_e82x(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port)
 {
 	tx->block = port / ICE_PORTS_PER_QUAD;
-	tx->offset = (port % ICE_PORTS_PER_QUAD) * INDEX_PER_PORT_E822;
-	tx->len = INDEX_PER_PORT_E822;
+	tx->offset = (port % ICE_PORTS_PER_QUAD) * INDEX_PER_PORT_E82X;
+	tx->len = INDEX_PER_PORT_E82X;
 	tx->verify_cached = 0;
 
 	return ice_ptp_alloc_tx_tracker(tx);
@@ -1072,10 +1216,10 @@ static u64 ice_base_incval(struct ice_pf *pf)
 
 	if (ice_is_e810(hw))
 		incval = ICE_PTP_NOMINAL_INCVAL_E810;
-	else if (ice_e822_time_ref(hw) < NUM_ICE_TIME_REF_FREQ)
-		incval = ice_e822_nominal_incval(ice_e822_time_ref(hw));
+	else if (ice_e82x_time_ref(hw) < NUM_ICE_TIME_REF_FREQ)
+		incval = ice_e82x_nominal_incval(ice_e82x_time_ref(hw));
 	else
-		incval = UNKNOWN_INCVAL_E822;
+		incval = UNKNOWN_INCVAL_E82X;
 
 	dev_dbg(ice_pf_to_dev(pf), "PTP: using base increment value of 0x%016llx\n",
 		incval);
@@ -1104,10 +1248,10 @@ static int ice_ptp_check_tx_fifo(struct ice_ptp_port *port)
 
 	/* need to read FIFO state */
 	if (offs == 0 || offs == 1)
-		err = ice_read_quad_reg_e822(hw, quad, Q_REG_FIFO01_STATUS,
+		err = ice_read_quad_reg_e82x(hw, quad, Q_REG_FIFO01_STATUS,
 					     &val);
 	else
-		err = ice_read_quad_reg_e822(hw, quad, Q_REG_FIFO23_STATUS,
+		err = ice_read_quad_reg_e82x(hw, quad, Q_REG_FIFO23_STATUS,
 					     &val);
 
 	if (err) {
@@ -1117,9 +1261,9 @@ static int ice_ptp_check_tx_fifo(struct ice_ptp_port *port)
 	}
 
 	if (offs & 0x1)
-		phy_sts = (val & Q_REG_FIFO13_M) >> Q_REG_FIFO13_S;
+		phy_sts = FIELD_GET(Q_REG_FIFO13_M, val);
 	else
-		phy_sts = (val & Q_REG_FIFO02_M) >> Q_REG_FIFO02_S;
+		phy_sts = FIELD_GET(Q_REG_FIFO02_M, val);
 
 	if (phy_sts & FIFO_EMPTY) {
 		port->tx_fifo_busy_cnt = FIFO_OK;
@@ -1135,7 +1279,7 @@ static int ice_ptp_check_tx_fifo(struct ice_ptp_port *port)
 		dev_dbg(ice_pf_to_dev(pf),
 			"Port %d Tx FIFO still not empty; resetting quad %d\n",
 			port->port_num, quad);
-		ice_ptp_reset_ts_memory_quad_e822(hw, quad);
+		ice_ptp_reset_ts_memory_quad_e82x(hw, quad);
 		port->tx_fifo_busy_cnt = FIFO_OK;
 		return 0;
 	}
@@ -1180,8 +1324,8 @@ static void ice_ptp_wait_for_offsets(struct kthread_work *work)
 
 	tx_err = ice_ptp_check_tx_fifo(port);
 	if (!tx_err)
-		tx_err = ice_phy_cfg_tx_offset_e822(hw, port->port_num);
-	rx_err = ice_phy_cfg_rx_offset_e822(hw, port->port_num);
+		tx_err = ice_phy_cfg_tx_offset_e82x(hw, port->port_num);
+	rx_err = ice_phy_cfg_rx_offset_e82x(hw, port->port_num);
 	if (tx_err || rx_err) {
 		/* Tx and/or Rx offset not yet configured, try again later */
 		kthread_queue_delayed_work(pf->ptp.kworker,
@@ -1210,7 +1354,7 @@ ice_ptp_port_phy_stop(struct ice_ptp_port *ptp_port)
 
 	kthread_cancel_delayed_work_sync(&ptp_port->ov_work);
 
-	err = ice_stop_phy_timer_e822(hw, port, true);
+	err = ice_stop_phy_timer_e82x(hw, port, true);
 	if (err)
 		dev_err(ice_pf_to_dev(pf), "PTP failed to set PHY port %d down, err %d\n",
 			port, err);
@@ -1234,6 +1378,7 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port)
 	struct ice_pf *pf = ptp_port_to_pf(ptp_port);
 	u8 port = ptp_port->port_num;
 	struct ice_hw *hw = &pf->hw;
+	unsigned long flags;
 	int err;
 
 	if (ice_is_e810(hw))
@@ -1247,20 +1392,20 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port)
 	kthread_cancel_delayed_work_sync(&ptp_port->ov_work);
 
 	/* temporarily disable Tx timestamps while calibrating PHY offset */
-	spin_lock(&ptp_port->tx.lock);
+	spin_lock_irqsave(&ptp_port->tx.lock, flags);
 	ptp_port->tx.calibrating = true;
-	spin_unlock(&ptp_port->tx.lock);
+	spin_unlock_irqrestore(&ptp_port->tx.lock, flags);
 	ptp_port->tx_fifo_busy_cnt = 0;
 
 	/* Start the PHY timer in Vernier mode */
-	err = ice_start_phy_timer_e822(hw, port);
+	err = ice_start_phy_timer_e82x(hw, port);
 	if (err)
 		goto out_unlock;
 
 	/* Enable Tx timestamps right away */
-	spin_lock(&ptp_port->tx.lock);
+	spin_lock_irqsave(&ptp_port->tx.lock, flags);
 	ptp_port->tx.calibrating = false;
-	spin_unlock(&ptp_port->tx.lock);
+	spin_unlock_irqrestore(&ptp_port->tx.lock, flags);
 
 	kthread_queue_delayed_work(pf->ptp.kworker, &ptp_port->ov_work, 0);
 
@@ -1302,7 +1447,7 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup)
 	case ICE_PHY_E810:
 		/* Do not reconfigure E810 PHY */
 		return;
-	case ICE_PHY_E822:
+	case ICE_PHY_E82X:
 		ice_ptp_port_phy_restart(ptp_port);
 		return;
 	default:
@@ -1328,7 +1473,7 @@ static int ice_ptp_tx_ena_intr(struct ice_pf *pf, bool ena, u32 threshold)
 	ice_ptp_reset_ts_memory(hw);
 
 	for (quad = 0; quad < ICE_MAX_QUAD; quad++) {
-		err = ice_read_quad_reg_e822(hw, quad, Q_REG_TX_MEM_GBL_CFG,
+		err = ice_read_quad_reg_e82x(hw, quad, Q_REG_TX_MEM_GBL_CFG,
 					     &val);
 		if (err)
 			break;
@@ -1336,13 +1481,13 @@ static int ice_ptp_tx_ena_intr(struct ice_pf *pf, bool ena, u32 threshold)
 		if (ena) {
 			val |= Q_REG_TX_MEM_GBL_CFG_INTR_ENA_M;
 			val &= ~Q_REG_TX_MEM_GBL_CFG_INTR_THR_M;
-			val |= ((threshold << Q_REG_TX_MEM_GBL_CFG_INTR_THR_S) &
-				Q_REG_TX_MEM_GBL_CFG_INTR_THR_M);
+			val |= FIELD_PREP(Q_REG_TX_MEM_GBL_CFG_INTR_THR_M,
+					  threshold);
 		} else {
 			val &= ~Q_REG_TX_MEM_GBL_CFG_INTR_ENA_M;
 		}
 
-		err = ice_write_quad_reg_e822(hw, quad, Q_REG_TX_MEM_GBL_CFG,
+		err = ice_write_quad_reg_e82x(hw, quad, Q_REG_TX_MEM_GBL_CFG,
 					      val);
 		if (err)
 			break;
@@ -1482,8 +1627,7 @@ ice_ptp_cfg_extts(struct ice_pf *pf, bool ena, unsigned int chan, u32 gpio_pin,
 		 * + num_in_channels * tmr_idx
 		 */
 		func = 1 + chan + (tmr_idx * 3);
-		gpio_reg = ((func << GLGEN_GPIO_CTL_PIN_FUNC_S) &
-			    GLGEN_GPIO_CTL_PIN_FUNC_M);
+		gpio_reg = FIELD_PREP(GLGEN_GPIO_CTL_PIN_FUNC_M, func);
 		pf->ptp.ext_ts_chan |= (1 << chan);
 	} else {
 		/* clear the values we set to reset defaults */
@@ -1580,7 +1724,7 @@ static int ice_ptp_cfg_clkout(struct ice_pf *pf, unsigned int chan,
 	if (ice_is_e810(hw))
 		start_time -= E810_OUT_PROP_DELAY_NS;
 	else
-		start_time -= ice_e822_pps_delay(ice_e822_time_ref(hw));
+		start_time -= ice_e82x_pps_delay(ice_e82x_time_ref(hw));
 
 	/* 2. Write TARGET time */
 	wr32(hw, GLTSYN_TGT_L(chan, tmr_idx), lower_32_bits(start_time));
@@ -1593,7 +1737,7 @@ static int ice_ptp_cfg_clkout(struct ice_pf *pf, unsigned int chan,
 	/* 4. write GPIO CTL reg */
 	func = 8 + chan + (tmr_idx * 4);
 	val = GLGEN_GPIO_CTL_PIN_DIR_M |
-	      ((func << GLGEN_GPIO_CTL_PIN_FUNC_S) & GLGEN_GPIO_CTL_PIN_FUNC_M);
+	      FIELD_PREP(GLGEN_GPIO_CTL_PIN_FUNC_M, func);
 	wr32(hw, GLGEN_GPIO_CTL(gpio_pin), val);
 
 	/* Store the value if requested */
@@ -1819,7 +1963,7 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts)
 	ice_ptp_enable_all_clkout(pf);
 
 	/* Recalibrate and re-enable timestamp blocks for E822/E823 */
-	if (hw->phy_model == ICE_PHY_E822)
+	if (hw->phy_model == ICE_PHY_E82X)
 		ice_ptp_restart_all_phy(pf);
 exit:
 	if (err) {
@@ -2037,10 +2181,10 @@ ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config)
 {
 	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
-		ice_set_tx_tstamp(pf, false);
+		pf->ptp.tstamp_config.tx_type = HWTSTAMP_TX_OFF;
 		break;
 	case HWTSTAMP_TX_ON:
-		ice_set_tx_tstamp(pf, true);
+		pf->ptp.tstamp_config.tx_type = HWTSTAMP_TX_ON;
 		break;
 	default:
 		return -ERANGE;
@@ -2048,7 +2192,7 @@ ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config)
 
 	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
-		ice_set_rx_tstamp(pf, false);
+		pf->ptp.tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
@@ -2064,12 +2208,15 @@ ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config)
 	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
 	case HWTSTAMP_FILTER_NTP_ALL:
 	case HWTSTAMP_FILTER_ALL:
-		ice_set_rx_tstamp(pf, true);
+		pf->ptp.tstamp_config.rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	default:
 		return -ERANGE;
 	}
 
+	/* Immediately update the device timestamping mode */
+	ice_ptp_restore_timestamp_mode(pf);
+
 	return 0;
 }
 
@@ -2103,30 +2250,26 @@ int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr)
 }
 
 /**
- * ice_ptp_rx_hwtstamp - Check for an Rx timestamp
- * @rx_ring: Ring to get the VSI info
+ * ice_ptp_get_rx_hwts - Get packet Rx timestamp in ns
  * @rx_desc: Receive descriptor
- * @skb: Particular skb to send timestamp with
+ * @pkt_ctx: Packet context to get the cached time
  *
  * The driver receives a notification in the receive descriptor with timestamp.
- * The timestamp is in ns, so we must convert the result first.
  */
-void
-ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring,
-		    union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb)
+u64 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc,
+			const struct ice_pkt_ctx *pkt_ctx)
 {
-	struct skb_shared_hwtstamps *hwtstamps;
 	u64 ts_ns, cached_time;
 	u32 ts_high;
 
 	if (!(rx_desc->wb.time_stamp_low & ICE_PTP_TS_VALID))
-		return;
+		return 0;
 
-	cached_time = READ_ONCE(rx_ring->cached_phctime);
+	cached_time = READ_ONCE(pkt_ctx->cached_phctime);
 
 	/* Do not report a timestamp if we don't have a cached PHC time */
 	if (!cached_time)
-		return;
+		return 0;
 
 	/* Use ice_ptp_extend_32b_ts directly, using the ring-specific cached
 	 * PHC value, rather than accessing the PF. This also allows us to
@@ -2137,9 +2280,7 @@ ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring,
 	ts_high = le32_to_cpu(rx_desc->wb.flex_ts.ts_high);
 	ts_ns = ice_ptp_extend_32b_ts(cached_time, ts_high);
 
-	hwtstamps = skb_hwtstamps(skb);
-	memset(hwtstamps, 0, sizeof(*hwtstamps));
-	hwtstamps->hwtstamp = ns_to_ktime(ts_ns);
+	return ts_ns;
 }
 
 /**
@@ -2354,18 +2495,23 @@ static long ice_ptp_create_clock(struct ice_pf *pf)
  */
 s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb)
 {
+	unsigned long flags;
 	u8 idx;
 
-	spin_lock(&tx->lock);
+	spin_lock_irqsave(&tx->lock, flags);
 
 	/* Check that this tracker is accepting new timestamp requests */
 	if (!ice_ptp_is_tx_tracker_up(tx)) {
-		spin_unlock(&tx->lock);
+		spin_unlock_irqrestore(&tx->lock, flags);
 		return -1;
 	}
 
 	/* Find and set the first available index */
-	idx = find_first_zero_bit(tx->in_use, tx->len);
+	idx = find_next_zero_bit(tx->in_use, tx->len,
+				 tx->last_ll_ts_idx_read + 1);
+	if (idx == tx->len)
+		idx = find_first_zero_bit(tx->in_use, tx->len);
+
 	if (idx < tx->len) {
 		/* We got a valid index that no other thread could have set. Store
 		 * a reference to the skb and the start time to allow discarding old
@@ -2379,7 +2525,7 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb)
 		ice_trace(tx_tstamp_request, skb, idx);
 	}
 
-	spin_unlock(&tx->lock);
+	spin_unlock_irqrestore(&tx->lock, flags);
 
 	/* return the appropriate PHY timestamp register index, -1 if no
 	 * indexes were available.
@@ -2416,6 +2562,54 @@ enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf)
 	}
 }
 
+/**
+ * ice_ptp_maybe_trigger_tx_interrupt - Trigger Tx timstamp interrupt
+ * @pf: Board private structure
+ *
+ * The device PHY issues Tx timestamp interrupts to the driver for processing
+ * timestamp data from the PHY. It will not interrupt again until all
+ * current timestamp data is read. In rare circumstances, it is possible that
+ * the driver fails to read all outstanding data.
+ *
+ * To avoid getting permanently stuck, periodically check if the PHY has
+ * outstanding timestamp data. If so, trigger an interrupt from software to
+ * process this data.
+ */
+static void ice_ptp_maybe_trigger_tx_interrupt(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	struct ice_hw *hw = &pf->hw;
+	bool trigger_oicr = false;
+	unsigned int i;
+
+	if (ice_is_e810(hw))
+		return;
+
+	if (!ice_pf_src_tmr_owned(pf))
+		return;
+
+	for (i = 0; i < ICE_MAX_QUAD; i++) {
+		u64 tstamp_ready;
+		int err;
+
+		err = ice_get_phy_tx_tstamp_ready(&pf->hw, i, &tstamp_ready);
+		if (!err && tstamp_ready) {
+			trigger_oicr = true;
+			break;
+		}
+	}
+
+	if (trigger_oicr) {
+		/* Trigger a software interrupt, to ensure this data
+		 * gets processed.
+		 */
+		dev_dbg(dev, "PTP periodic task detected waiting timestamps. Triggering Tx timestamp interrupt now.\n");
+
+		wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M);
+		ice_flush(hw);
+	}
+}
+
 static void ice_ptp_periodic_work(struct kthread_work *work)
 {
 	struct ice_ptp *ptp = container_of(work, struct ice_ptp, work.work);
@@ -2427,6 +2621,8 @@ static void ice_ptp_periodic_work(struct kthread_work *work)
 
 	err = ice_ptp_update_cached_phctime(pf);
 
+	ice_ptp_maybe_trigger_tx_interrupt(pf);
+
 	/* Run twice a second or reschedule if phc update failed */
 	kthread_queue_delayed_work(ptp->kworker, &ptp->work,
 				   msecs_to_jiffies(err ? 10 : 500));
@@ -2444,12 +2640,10 @@ void ice_ptp_reset(struct ice_pf *pf)
 	int err, itr = 1;
 	u64 time_diff;
 
-	if (test_bit(ICE_PFR_REQ, pf->state))
+	if (test_bit(ICE_PFR_REQ, pf->state) ||
+	    !ice_pf_src_tmr_owned(pf))
 		goto pfr;
 
-	if (!ice_pf_src_tmr_owned(pf))
-		goto reset_ts;
-
 	err = ice_ptp_init_phc(hw);
 	if (err)
 		goto err;
@@ -2493,10 +2687,6 @@ void ice_ptp_reset(struct ice_pf *pf)
 			goto err;
 	}
 
-reset_ts:
-	/* Restart the PHY timestamping block */
-	ice_ptp_reset_phy_timestamping(pf);
-
 pfr:
 	/* Init Tx structures */
 	if (ice_is_e810(&pf->hw)) {
@@ -2504,7 +2694,7 @@ pfr:
 	} else {
 		kthread_init_delayed_work(&ptp->port.ov_work,
 					  ice_ptp_wait_for_offsets);
-		err = ice_ptp_init_tx_e822(pf, &ptp->port.tx,
+		err = ice_ptp_init_tx_e82x(pf, &ptp->port.tx,
 					   ptp->port.port_num);
 	}
 	if (err)
@@ -2512,6 +2702,11 @@ pfr:
 
 	set_bit(ICE_FLAG_PTP, pf->flags);
 
+	/* Restart the PHY timestamping block */
+	if (!test_bit(ICE_PFR_REQ, pf->state) &&
+	    ice_pf_src_tmr_owned(pf))
+		ice_ptp_restart_all_phy(pf);
+
 	/* Start periodic work going */
 	kthread_queue_delayed_work(ptp->kworker, &ptp->work, 0);
 
@@ -2668,6 +2863,8 @@ static int ice_ptp_register_auxbus_driver(struct ice_pf *pf)
 	name = devm_kasprintf(dev, GFP_KERNEL, "ptp_aux_dev_%u_%u_clk%u",
 			      pf->pdev->bus->number, PCI_SLOT(pf->pdev->devfn),
 			      ice_get_ptp_src_clock_index(&pf->hw));
+	if (!name)
+		return -ENOMEM;
 
 	aux_driver->name = name;
 	aux_driver->shutdown = ice_ptp_auxbus_shutdown;
@@ -2737,7 +2934,7 @@ void ice_ptp_prepare_for_reset(struct ice_pf *pf)
 	clear_bit(ICE_FLAG_PTP, pf->flags);
 
 	/* Disable timestamping for both Tx and Rx */
-	ice_ptp_cfg_timestamp(pf, false);
+	ice_ptp_disable_timestamp_mode(pf);
 
 	kthread_cancel_delayed_work_sync(&ptp->work);
 
@@ -2803,15 +3000,7 @@ static int ice_ptp_init_owner(struct ice_pf *pf)
 	/* Release the global hardware lock */
 	ice_ptp_unlock(hw);
 
-	if (pf->ptp.tx_interrupt_mode == ICE_PTP_TX_INTERRUPT_ALL) {
-		/* The clock owner for this device type handles the timestamp
-		 * interrupt for all ports.
-		 */
-		ice_ptp_configure_tx_tstamp(pf, true);
-
-		/* React on all quads interrupts for E82x */
-		wr32(hw, PFINT_TSYN_MSK + (0x4 * hw->pf_id), (u32)0x1f);
-
+	if (!ice_is_e810(hw)) {
 		/* Enable quad interrupts */
 		err = ice_ptp_tx_ena_intr(pf, true, itr);
 		if (err)
@@ -2880,18 +3069,11 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port)
 	switch (hw->phy_model) {
 	case ICE_PHY_E810:
 		return ice_ptp_init_tx_e810(pf, &ptp_port->tx);
-	case ICE_PHY_E822:
-		/* Non-owner PFs don't react to any interrupts on E82x,
-		 * neither on own quad nor on others
-		 */
-		if (!ice_ptp_pf_handles_tx_interrupt(pf)) {
-			ice_ptp_configure_tx_tstamp(pf, false);
-			wr32(hw, PFINT_TSYN_MSK + (0x4 * hw->pf_id), (u32)0x0);
-		}
+	case ICE_PHY_E82X:
 		kthread_init_delayed_work(&ptp_port->ov_work,
 					  ice_ptp_wait_for_offsets);
 
-		return ice_ptp_init_tx_e822(pf, &ptp_port->tx,
+		return ice_ptp_init_tx_e82x(pf, &ptp_port->tx,
 					    ptp_port->port_num);
 	default:
 		return -ENODEV;
@@ -2929,6 +3111,8 @@ static int ice_ptp_create_auxbus_device(struct ice_pf *pf)
 	name = devm_kasprintf(dev, GFP_KERNEL, "ptp_aux_dev_%u_%u_clk%u",
 			      pf->pdev->bus->number, PCI_SLOT(pf->pdev->devfn),
 			      ice_get_ptp_src_clock_index(&pf->hw));
+	if (!name)
+		return -ENOMEM;
 
 	aux_dev->name = name;
 	aux_dev->id = id;
@@ -2978,7 +3162,7 @@ static void ice_ptp_remove_auxbus_device(struct ice_pf *pf)
 static void ice_ptp_init_tx_interrupt_mode(struct ice_pf *pf)
 {
 	switch (pf->hw.phy_model) {
-	case ICE_PHY_E822:
+	case ICE_PHY_E82X:
 		/* E822 based PHY has the clock owner process the interrupt
 		 * for all ports.
 		 */
@@ -3032,6 +3216,9 @@ void ice_ptp_init(struct ice_pf *pf)
 	/* Start the PHY timestamping block */
 	ice_ptp_reset_phy_timestamping(pf);
 
+	/* Configure initial Tx interrupt settings */
+	ice_ptp_cfg_tx_interrupt(pf);
+
 	set_bit(ICE_FLAG_PTP, pf->flags);
 	err = ice_ptp_init_work(pf, ptp);
 	if (err)
@@ -3067,7 +3254,7 @@ void ice_ptp_release(struct ice_pf *pf)
 		return;
 
 	/* Disable timestamping for both Tx and Rx */
-	ice_ptp_cfg_timestamp(pf, false);
+	ice_ptp_disable_timestamp_mode(pf);
 
 	ice_ptp_remove_auxbus_device(pf);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h
index 8f6f94392756..087dd32d8762 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.h
@@ -131,6 +131,7 @@ enum ice_tx_tstamp_work {
  * @calibrating: if true, the PHY is calibrating the Tx offset. During this
  *               window, timestamps are temporarily disabled.
  * @verify_cached: if true, verify new timestamp differs from last read value
+ * @last_ll_ts_idx_read: index of the last LL TS read by the FW
  */
 struct ice_ptp_tx {
 	spinlock_t lock; /* lock protecting in_use bitmap */
@@ -143,11 +144,12 @@ struct ice_ptp_tx {
 	u8 init : 1;
 	u8 calibrating : 1;
 	u8 verify_cached : 1;
+	s8 last_ll_ts_idx_read;
 };
 
 /* Quad and port information for initializing timestamp blocks */
 #define INDEX_PER_QUAD			64
-#define INDEX_PER_PORT_E822		16
+#define INDEX_PER_PORT_E82X		16
 #define INDEX_PER_PORT_E810		64
 
 /**
@@ -292,15 +294,16 @@ int ice_ptp_clock_index(struct ice_pf *pf);
 struct ice_pf;
 int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr);
 int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr);
-void ice_ptp_cfg_timestamp(struct ice_pf *pf, bool ena);
+void ice_ptp_restore_timestamp_mode(struct ice_pf *pf);
 
 void ice_ptp_extts_event(struct ice_pf *pf);
 s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb);
+void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx);
+void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx);
 enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf);
 
-void
-ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring,
-		    union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb);
+u64 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc,
+			const struct ice_pkt_ctx *pkt_ctx);
 void ice_ptp_reset(struct ice_pf *pf);
 void ice_ptp_prepare_for_reset(struct ice_pf *pf);
 void ice_ptp_init(struct ice_pf *pf);
@@ -317,8 +320,7 @@ static inline int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr)
 	return -EOPNOTSUPP;
 }
 
-static inline void ice_ptp_cfg_timestamp(struct ice_pf *pf, bool ena) { }
-
+static inline void ice_ptp_restore_timestamp_mode(struct ice_pf *pf) { }
 static inline void ice_ptp_extts_event(struct ice_pf *pf) { }
 static inline s8
 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb)
@@ -326,13 +328,23 @@ ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb)
 	return -1;
 }
 
+static inline void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx)
+{ }
+
+static inline void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx) { }
+
 static inline bool ice_ptp_process_ts(struct ice_pf *pf)
 {
 	return true;
 }
-static inline void
-ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring,
-		    union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb) { }
+
+static inline u64
+ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc,
+		    const struct ice_pkt_ctx *pkt_ctx)
+{
+	return 0;
+}
+
 static inline void ice_ptp_reset(struct ice_pf *pf) { }
 static inline void ice_ptp_prepare_for_reset(struct ice_pf *pf) { }
 static inline void ice_ptp_init(struct ice_pf *pf) { }
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h
index 4109aa3b2fcd..2c4dab0c48ab 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h
@@ -9,17 +9,17 @@
  */
 /* Constants defined for the PTP 1588 clock hardware. */
 
-/* struct ice_time_ref_info_e822
+/* struct ice_time_ref_info_e82x
  *
  * E822 hardware can use different sources as the reference for the PTP
  * hardware clock. Each clock has different characteristics such as a slightly
  * different frequency, etc.
  *
  * This lookup table defines several constants that depend on the current time
- * reference. See the struct ice_time_ref_info_e822 for information about the
+ * reference. See the struct ice_time_ref_info_e82x for information about the
  * meaning of each constant.
  */
-const struct ice_time_ref_info_e822 e822_time_ref[NUM_ICE_TIME_REF_FREQ] = {
+const struct ice_time_ref_info_e82x e822_time_ref[NUM_ICE_TIME_REF_FREQ] = {
 	/* ICE_TIME_REF_FREQ_25_000 -> 25 MHz */
 	{
 		/* pll_freq */
@@ -81,7 +81,7 @@ const struct ice_time_ref_info_e822 e822_time_ref[NUM_ICE_TIME_REF_FREQ] = {
 	},
 };
 
-const struct ice_cgu_pll_params_e822 e822_cgu_params[NUM_ICE_TIME_REF_FREQ] = {
+const struct ice_cgu_pll_params_e82x e822_cgu_params[NUM_ICE_TIME_REF_FREQ] = {
 	/* ICE_TIME_REF_FREQ_25_000 -> 25 MHz */
 	{
 		/* refclk_pre_div */
@@ -155,7 +155,7 @@ const struct ice_cgu_pll_params_e822 e822_cgu_params[NUM_ICE_TIME_REF_FREQ] = {
 	},
 };
 
-/* struct ice_vernier_info_e822
+/* struct ice_vernier_info_e82x
  *
  * E822 hardware calibrates the delay of the timestamp indication from the
  * actual packet transmission or reception during the initialization of the
@@ -168,7 +168,7 @@ const struct ice_cgu_pll_params_e822 e822_cgu_params[NUM_ICE_TIME_REF_FREQ] = {
  * used by this link speed, and that the register should be cleared by writing
  * 0. Other values specify the clock frequency in Hz.
  */
-const struct ice_vernier_info_e822 e822_vernier[NUM_ICE_PTP_LNK_SPD] = {
+const struct ice_vernier_info_e82x e822_vernier[NUM_ICE_PTP_LNK_SPD] = {
 	/* ICE_PTP_LNK_SPD_1G */
 	{
 		/* tx_par_clk */
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index 6d573908de7a..187ce9b54e1a 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -284,19 +284,19 @@ static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw)
  */
 
 /**
- * ice_fill_phy_msg_e822 - Fill message data for a PHY register access
+ * ice_fill_phy_msg_e82x - Fill message data for a PHY register access
  * @msg: the PHY message buffer to fill in
  * @port: the port to access
  * @offset: the register offset
  */
 static void
-ice_fill_phy_msg_e822(struct ice_sbq_msg_input *msg, u8 port, u16 offset)
+ice_fill_phy_msg_e82x(struct ice_sbq_msg_input *msg, u8 port, u16 offset)
 {
 	int phy_port, phy, quadtype;
 
-	phy_port = port % ICE_PORTS_PER_PHY_E822;
-	phy = port / ICE_PORTS_PER_PHY_E822;
-	quadtype = (port / ICE_PORTS_PER_QUAD) % ICE_QUADS_PER_PHY_E822;
+	phy_port = port % ICE_PORTS_PER_PHY_E82X;
+	phy = port / ICE_PORTS_PER_PHY_E82X;
+	quadtype = (port / ICE_PORTS_PER_QUAD) % ICE_QUADS_PER_PHY_E82X;
 
 	if (quadtype == 0) {
 		msg->msg_addr_low = P_Q0_L(P_0_BASE + offset, phy_port);
@@ -315,7 +315,7 @@ ice_fill_phy_msg_e822(struct ice_sbq_msg_input *msg, u8 port, u16 offset)
 }
 
 /**
- * ice_is_64b_phy_reg_e822 - Check if this is a 64bit PHY register
+ * ice_is_64b_phy_reg_e82x - Check if this is a 64bit PHY register
  * @low_addr: the low address to check
  * @high_addr: on return, contains the high address of the 64bit register
  *
@@ -323,7 +323,7 @@ ice_fill_phy_msg_e822(struct ice_sbq_msg_input *msg, u8 port, u16 offset)
  * represented as two 32bit registers. If it is, return the appropriate high
  * register offset to use.
  */
-static bool ice_is_64b_phy_reg_e822(u16 low_addr, u16 *high_addr)
+static bool ice_is_64b_phy_reg_e82x(u16 low_addr, u16 *high_addr)
 {
 	switch (low_addr) {
 	case P_REG_PAR_PCS_TX_OFFSET_L:
@@ -368,7 +368,7 @@ static bool ice_is_64b_phy_reg_e822(u16 low_addr, u16 *high_addr)
 }
 
 /**
- * ice_is_40b_phy_reg_e822 - Check if this is a 40bit PHY register
+ * ice_is_40b_phy_reg_e82x - Check if this is a 40bit PHY register
  * @low_addr: the low address to check
  * @high_addr: on return, contains the high address of the 40bit value
  *
@@ -377,7 +377,7 @@ static bool ice_is_64b_phy_reg_e822(u16 low_addr, u16 *high_addr)
  * upper 32 bits in the high register. If it is, return the appropriate high
  * register offset to use.
  */
-static bool ice_is_40b_phy_reg_e822(u16 low_addr, u16 *high_addr)
+static bool ice_is_40b_phy_reg_e82x(u16 low_addr, u16 *high_addr)
 {
 	switch (low_addr) {
 	case P_REG_TIMETUS_L:
@@ -413,7 +413,7 @@ static bool ice_is_40b_phy_reg_e822(u16 low_addr, u16 *high_addr)
 }
 
 /**
- * ice_read_phy_reg_e822 - Read a PHY register
+ * ice_read_phy_reg_e82x - Read a PHY register
  * @hw: pointer to the HW struct
  * @port: PHY port to read from
  * @offset: PHY register offset to read
@@ -422,12 +422,12 @@ static bool ice_is_40b_phy_reg_e822(u16 low_addr, u16 *high_addr)
  * Read a PHY register for the given port over the device sideband queue.
  */
 static int
-ice_read_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 *val)
+ice_read_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 offset, u32 *val)
 {
 	struct ice_sbq_msg_input msg = {0};
 	int err;
 
-	ice_fill_phy_msg_e822(&msg, port, offset);
+	ice_fill_phy_msg_e82x(&msg, port, offset);
 	msg.opcode = ice_sbq_msg_rd;
 
 	err = ice_sbq_rw_reg(hw, &msg);
@@ -443,7 +443,7 @@ ice_read_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 *val)
 }
 
 /**
- * ice_read_64b_phy_reg_e822 - Read a 64bit value from PHY registers
+ * ice_read_64b_phy_reg_e82x - Read a 64bit value from PHY registers
  * @hw: pointer to the HW struct
  * @port: PHY port to read from
  * @low_addr: offset of the lower register to read from
@@ -455,7 +455,7 @@ ice_read_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 *val)
  * known to be two parts of a 64bit value.
  */
 static int
-ice_read_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 *val)
+ice_read_64b_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 low_addr, u64 *val)
 {
 	u32 low, high;
 	u16 high_addr;
@@ -464,20 +464,20 @@ ice_read_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 *val)
 	/* Only operate on registers known to be split into two 32bit
 	 * registers.
 	 */
-	if (!ice_is_64b_phy_reg_e822(low_addr, &high_addr)) {
+	if (!ice_is_64b_phy_reg_e82x(low_addr, &high_addr)) {
 		ice_debug(hw, ICE_DBG_PTP, "Invalid 64b register addr 0x%08x\n",
 			  low_addr);
 		return -EINVAL;
 	}
 
-	err = ice_read_phy_reg_e822(hw, port, low_addr, &low);
+	err = ice_read_phy_reg_e82x(hw, port, low_addr, &low);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to read from low register 0x%08x\n, err %d",
 			  low_addr, err);
 		return err;
 	}
 
-	err = ice_read_phy_reg_e822(hw, port, high_addr, &high);
+	err = ice_read_phy_reg_e82x(hw, port, high_addr, &high);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to read from high register 0x%08x\n, err %d",
 			  high_addr, err);
@@ -490,7 +490,7 @@ ice_read_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 *val)
 }
 
 /**
- * ice_write_phy_reg_e822 - Write a PHY register
+ * ice_write_phy_reg_e82x - Write a PHY register
  * @hw: pointer to the HW struct
  * @port: PHY port to write to
  * @offset: PHY register offset to write
@@ -499,12 +499,12 @@ ice_read_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 *val)
  * Write a PHY register for the given port over the device sideband queue.
  */
 static int
-ice_write_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 val)
+ice_write_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 offset, u32 val)
 {
 	struct ice_sbq_msg_input msg = {0};
 	int err;
 
-	ice_fill_phy_msg_e822(&msg, port, offset);
+	ice_fill_phy_msg_e82x(&msg, port, offset);
 	msg.opcode = ice_sbq_msg_wr;
 	msg.data = val;
 
@@ -519,7 +519,7 @@ ice_write_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 val)
 }
 
 /**
- * ice_write_40b_phy_reg_e822 - Write a 40b value to the PHY
+ * ice_write_40b_phy_reg_e82x - Write a 40b value to the PHY
  * @hw: pointer to the HW struct
  * @port: port to write to
  * @low_addr: offset of the low register
@@ -529,7 +529,7 @@ ice_write_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 val)
  * it up into two chunks, the lower 8 bits and the upper 32 bits.
  */
 static int
-ice_write_40b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val)
+ice_write_40b_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 low_addr, u64 val)
 {
 	u32 low, high;
 	u16 high_addr;
@@ -538,7 +538,7 @@ ice_write_40b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val)
 	/* Only operate on registers known to be split into a lower 8 bit
 	 * register and an upper 32 bit register.
 	 */
-	if (!ice_is_40b_phy_reg_e822(low_addr, &high_addr)) {
+	if (!ice_is_40b_phy_reg_e82x(low_addr, &high_addr)) {
 		ice_debug(hw, ICE_DBG_PTP, "Invalid 40b register addr 0x%08x\n",
 			  low_addr);
 		return -EINVAL;
@@ -547,14 +547,14 @@ ice_write_40b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val)
 	low = (u32)(val & P_REG_40B_LOW_M);
 	high = (u32)(val >> P_REG_40B_HIGH_S);
 
-	err = ice_write_phy_reg_e822(hw, port, low_addr, low);
+	err = ice_write_phy_reg_e82x(hw, port, low_addr, low);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to write to low register 0x%08x\n, err %d",
 			  low_addr, err);
 		return err;
 	}
 
-	err = ice_write_phy_reg_e822(hw, port, high_addr, high);
+	err = ice_write_phy_reg_e82x(hw, port, high_addr, high);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to write to high register 0x%08x\n, err %d",
 			  high_addr, err);
@@ -565,7 +565,7 @@ ice_write_40b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val)
 }
 
 /**
- * ice_write_64b_phy_reg_e822 - Write a 64bit value to PHY registers
+ * ice_write_64b_phy_reg_e82x - Write a 64bit value to PHY registers
  * @hw: pointer to the HW struct
  * @port: PHY port to read from
  * @low_addr: offset of the lower register to read from
@@ -577,7 +577,7 @@ ice_write_40b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val)
  * a 64bit value.
  */
 static int
-ice_write_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val)
+ice_write_64b_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 low_addr, u64 val)
 {
 	u32 low, high;
 	u16 high_addr;
@@ -586,7 +586,7 @@ ice_write_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val)
 	/* Only operate on registers known to be split into two 32bit
 	 * registers.
 	 */
-	if (!ice_is_64b_phy_reg_e822(low_addr, &high_addr)) {
+	if (!ice_is_64b_phy_reg_e82x(low_addr, &high_addr)) {
 		ice_debug(hw, ICE_DBG_PTP, "Invalid 64b register addr 0x%08x\n",
 			  low_addr);
 		return -EINVAL;
@@ -595,14 +595,14 @@ ice_write_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val)
 	low = lower_32_bits(val);
 	high = upper_32_bits(val);
 
-	err = ice_write_phy_reg_e822(hw, port, low_addr, low);
+	err = ice_write_phy_reg_e82x(hw, port, low_addr, low);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to write to low register 0x%08x\n, err %d",
 			  low_addr, err);
 		return err;
 	}
 
-	err = ice_write_phy_reg_e822(hw, port, high_addr, high);
+	err = ice_write_phy_reg_e82x(hw, port, high_addr, high);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to write to high register 0x%08x\n, err %d",
 			  high_addr, err);
@@ -613,7 +613,7 @@ ice_write_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val)
 }
 
 /**
- * ice_fill_quad_msg_e822 - Fill message data for quad register access
+ * ice_fill_quad_msg_e82x - Fill message data for quad register access
  * @msg: the PHY message buffer to fill in
  * @quad: the quad to access
  * @offset: the register offset
@@ -622,7 +622,7 @@ ice_write_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val)
  * multiple PHYs.
  */
 static int
-ice_fill_quad_msg_e822(struct ice_sbq_msg_input *msg, u8 quad, u16 offset)
+ice_fill_quad_msg_e82x(struct ice_sbq_msg_input *msg, u8 quad, u16 offset)
 {
 	u32 addr;
 
@@ -631,7 +631,7 @@ ice_fill_quad_msg_e822(struct ice_sbq_msg_input *msg, u8 quad, u16 offset)
 
 	msg->dest_dev = rmn_0;
 
-	if ((quad % ICE_QUADS_PER_PHY_E822) == 0)
+	if ((quad % ICE_QUADS_PER_PHY_E82X) == 0)
 		addr = Q_0_BASE + offset;
 	else
 		addr = Q_1_BASE + offset;
@@ -643,7 +643,7 @@ ice_fill_quad_msg_e822(struct ice_sbq_msg_input *msg, u8 quad, u16 offset)
 }
 
 /**
- * ice_read_quad_reg_e822 - Read a PHY quad register
+ * ice_read_quad_reg_e82x - Read a PHY quad register
  * @hw: pointer to the HW struct
  * @quad: quad to read from
  * @offset: quad register offset to read
@@ -653,12 +653,12 @@ ice_fill_quad_msg_e822(struct ice_sbq_msg_input *msg, u8 quad, u16 offset)
  * shared between multiple PHYs.
  */
 int
-ice_read_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 *val)
+ice_read_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 *val)
 {
 	struct ice_sbq_msg_input msg = {0};
 	int err;
 
-	err = ice_fill_quad_msg_e822(&msg, quad, offset);
+	err = ice_fill_quad_msg_e82x(&msg, quad, offset);
 	if (err)
 		return err;
 
@@ -677,7 +677,7 @@ ice_read_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 *val)
 }
 
 /**
- * ice_write_quad_reg_e822 - Write a PHY quad register
+ * ice_write_quad_reg_e82x - Write a PHY quad register
  * @hw: pointer to the HW struct
  * @quad: quad to write to
  * @offset: quad register offset to write
@@ -687,12 +687,12 @@ ice_read_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 *val)
  * shared between multiple PHYs.
  */
 int
-ice_write_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 val)
+ice_write_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 val)
 {
 	struct ice_sbq_msg_input msg = {0};
 	int err;
 
-	err = ice_fill_quad_msg_e822(&msg, quad, offset);
+	err = ice_fill_quad_msg_e82x(&msg, quad, offset);
 	if (err)
 		return err;
 
@@ -710,7 +710,7 @@ ice_write_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 val)
 }
 
 /**
- * ice_read_phy_tstamp_e822 - Read a PHY timestamp out of the quad block
+ * ice_read_phy_tstamp_e82x - Read a PHY timestamp out of the quad block
  * @hw: pointer to the HW struct
  * @quad: the quad to read from
  * @idx: the timestamp index to read
@@ -721,7 +721,7 @@ ice_write_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 val)
  * family of devices.
  */
 static int
-ice_read_phy_tstamp_e822(struct ice_hw *hw, u8 quad, u8 idx, u64 *tstamp)
+ice_read_phy_tstamp_e82x(struct ice_hw *hw, u8 quad, u8 idx, u64 *tstamp)
 {
 	u16 lo_addr, hi_addr;
 	u32 lo, hi;
@@ -730,14 +730,14 @@ ice_read_phy_tstamp_e822(struct ice_hw *hw, u8 quad, u8 idx, u64 *tstamp)
 	lo_addr = (u16)TS_L(Q_REG_TX_MEMORY_BANK_START, idx);
 	hi_addr = (u16)TS_H(Q_REG_TX_MEMORY_BANK_START, idx);
 
-	err = ice_read_quad_reg_e822(hw, quad, lo_addr, &lo);
+	err = ice_read_quad_reg_e82x(hw, quad, lo_addr, &lo);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to read low PTP timestamp register, err %d\n",
 			  err);
 		return err;
 	}
 
-	err = ice_read_quad_reg_e822(hw, quad, hi_addr, &hi);
+	err = ice_read_quad_reg_e82x(hw, quad, hi_addr, &hi);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to read high PTP timestamp register, err %d\n",
 			  err);
@@ -754,7 +754,7 @@ ice_read_phy_tstamp_e822(struct ice_hw *hw, u8 quad, u8 idx, u64 *tstamp)
 }
 
 /**
- * ice_clear_phy_tstamp_e822 - Clear a timestamp from the quad block
+ * ice_clear_phy_tstamp_e82x - Clear a timestamp from the quad block
  * @hw: pointer to the HW struct
  * @quad: the quad to read from
  * @idx: the timestamp index to reset
@@ -770,18 +770,18 @@ ice_read_phy_tstamp_e822(struct ice_hw *hw, u8 quad, u8 idx, u64 *tstamp)
  *
  * To directly clear the contents of the timestamp block entirely, discarding
  * all timestamp data at once, software should instead use
- * ice_ptp_reset_ts_memory_quad_e822().
+ * ice_ptp_reset_ts_memory_quad_e82x().
  *
  * This function should only be called on an idx whose bit is set according to
  * ice_get_phy_tx_tstamp_ready().
  */
 static int
-ice_clear_phy_tstamp_e822(struct ice_hw *hw, u8 quad, u8 idx)
+ice_clear_phy_tstamp_e82x(struct ice_hw *hw, u8 quad, u8 idx)
 {
 	u64 unused_tstamp;
 	int err;
 
-	err = ice_read_phy_tstamp_e822(hw, quad, idx, &unused_tstamp);
+	err = ice_read_phy_tstamp_e82x(hw, quad, idx, &unused_tstamp);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to read the timestamp register for quad %u, idx %u, err %d\n",
 			  quad, idx, err);
@@ -792,33 +792,33 @@ ice_clear_phy_tstamp_e822(struct ice_hw *hw, u8 quad, u8 idx)
 }
 
 /**
- * ice_ptp_reset_ts_memory_quad_e822 - Clear all timestamps from the quad block
+ * ice_ptp_reset_ts_memory_quad_e82x - Clear all timestamps from the quad block
  * @hw: pointer to the HW struct
  * @quad: the quad to read from
  *
  * Clear all timestamps from the PHY quad block that is shared between the
  * internal PHYs on the E822 devices.
  */
-void ice_ptp_reset_ts_memory_quad_e822(struct ice_hw *hw, u8 quad)
+void ice_ptp_reset_ts_memory_quad_e82x(struct ice_hw *hw, u8 quad)
 {
-	ice_write_quad_reg_e822(hw, quad, Q_REG_TS_CTRL, Q_REG_TS_CTRL_M);
-	ice_write_quad_reg_e822(hw, quad, Q_REG_TS_CTRL, ~(u32)Q_REG_TS_CTRL_M);
+	ice_write_quad_reg_e82x(hw, quad, Q_REG_TS_CTRL, Q_REG_TS_CTRL_M);
+	ice_write_quad_reg_e82x(hw, quad, Q_REG_TS_CTRL, ~(u32)Q_REG_TS_CTRL_M);
 }
 
 /**
- * ice_ptp_reset_ts_memory_e822 - Clear all timestamps from all quad blocks
+ * ice_ptp_reset_ts_memory_e82x - Clear all timestamps from all quad blocks
  * @hw: pointer to the HW struct
  */
-static void ice_ptp_reset_ts_memory_e822(struct ice_hw *hw)
+static void ice_ptp_reset_ts_memory_e82x(struct ice_hw *hw)
 {
 	unsigned int quad;
 
 	for (quad = 0; quad < ICE_MAX_QUAD; quad++)
-		ice_ptp_reset_ts_memory_quad_e822(hw, quad);
+		ice_ptp_reset_ts_memory_quad_e82x(hw, quad);
 }
 
 /**
- * ice_read_cgu_reg_e822 - Read a CGU register
+ * ice_read_cgu_reg_e82x - Read a CGU register
  * @hw: pointer to the HW struct
  * @addr: Register address to read
  * @val: storage for register value read
@@ -827,7 +827,7 @@ static void ice_ptp_reset_ts_memory_e822(struct ice_hw *hw)
  * applicable to E822 devices.
  */
 static int
-ice_read_cgu_reg_e822(struct ice_hw *hw, u32 addr, u32 *val)
+ice_read_cgu_reg_e82x(struct ice_hw *hw, u32 addr, u32 *val)
 {
 	struct ice_sbq_msg_input cgu_msg;
 	int err;
@@ -850,7 +850,7 @@ ice_read_cgu_reg_e822(struct ice_hw *hw, u32 addr, u32 *val)
 }
 
 /**
- * ice_write_cgu_reg_e822 - Write a CGU register
+ * ice_write_cgu_reg_e82x - Write a CGU register
  * @hw: pointer to the HW struct
  * @addr: Register address to write
  * @val: value to write into the register
@@ -859,7 +859,7 @@ ice_read_cgu_reg_e822(struct ice_hw *hw, u32 addr, u32 *val)
  * applicable to E822 devices.
  */
 static int
-ice_write_cgu_reg_e822(struct ice_hw *hw, u32 addr, u32 val)
+ice_write_cgu_reg_e82x(struct ice_hw *hw, u32 addr, u32 val)
 {
 	struct ice_sbq_msg_input cgu_msg;
 	int err;
@@ -925,7 +925,7 @@ static const char *ice_clk_src_str(u8 clk_src)
 }
 
 /**
- * ice_cfg_cgu_pll_e822 - Configure the Clock Generation Unit
+ * ice_cfg_cgu_pll_e82x - Configure the Clock Generation Unit
  * @hw: pointer to the HW struct
  * @clk_freq: Clock frequency to program
  * @clk_src: Clock source to select (TIME_REF, or TCX0)
@@ -934,7 +934,7 @@ static const char *ice_clk_src_str(u8 clk_src)
  * time reference, enabling the PLL which drives the PTP hardware clock.
  */
 static int
-ice_cfg_cgu_pll_e822(struct ice_hw *hw, enum ice_time_ref_freq clk_freq,
+ice_cfg_cgu_pll_e82x(struct ice_hw *hw, enum ice_time_ref_freq clk_freq,
 		     enum ice_clk_src clk_src)
 {
 	union tspll_ro_bwm_lf bwm_lf;
@@ -963,15 +963,15 @@ ice_cfg_cgu_pll_e822(struct ice_hw *hw, enum ice_time_ref_freq clk_freq,
 		return -EINVAL;
 	}
 
-	err = ice_read_cgu_reg_e822(hw, NAC_CGU_DWORD9, &dw9.val);
+	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD9, &dw9.val);
 	if (err)
 		return err;
 
-	err = ice_read_cgu_reg_e822(hw, NAC_CGU_DWORD24, &dw24.val);
+	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD24, &dw24.val);
 	if (err)
 		return err;
 
-	err = ice_read_cgu_reg_e822(hw, TSPLL_RO_BWM_LF, &bwm_lf.val);
+	err = ice_read_cgu_reg_e82x(hw, TSPLL_RO_BWM_LF, &bwm_lf.val);
 	if (err)
 		return err;
 
@@ -986,43 +986,43 @@ ice_cfg_cgu_pll_e822(struct ice_hw *hw, enum ice_time_ref_freq clk_freq,
 	if (dw24.field.ts_pll_enable) {
 		dw24.field.ts_pll_enable = 0;
 
-		err = ice_write_cgu_reg_e822(hw, NAC_CGU_DWORD24, dw24.val);
+		err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val);
 		if (err)
 			return err;
 	}
 
 	/* Set the frequency */
 	dw9.field.time_ref_freq_sel = clk_freq;
-	err = ice_write_cgu_reg_e822(hw, NAC_CGU_DWORD9, dw9.val);
+	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD9, dw9.val);
 	if (err)
 		return err;
 
 	/* Configure the TS PLL feedback divisor */
-	err = ice_read_cgu_reg_e822(hw, NAC_CGU_DWORD19, &dw19.val);
+	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD19, &dw19.val);
 	if (err)
 		return err;
 
 	dw19.field.tspll_fbdiv_intgr = e822_cgu_params[clk_freq].feedback_div;
 	dw19.field.tspll_ndivratio = 1;
 
-	err = ice_write_cgu_reg_e822(hw, NAC_CGU_DWORD19, dw19.val);
+	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD19, dw19.val);
 	if (err)
 		return err;
 
 	/* Configure the TS PLL post divisor */
-	err = ice_read_cgu_reg_e822(hw, NAC_CGU_DWORD22, &dw22.val);
+	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD22, &dw22.val);
 	if (err)
 		return err;
 
 	dw22.field.time1588clk_div = e822_cgu_params[clk_freq].post_pll_div;
 	dw22.field.time1588clk_sel_div2 = 0;
 
-	err = ice_write_cgu_reg_e822(hw, NAC_CGU_DWORD22, dw22.val);
+	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD22, dw22.val);
 	if (err)
 		return err;
 
 	/* Configure the TS PLL pre divisor and clock source */
-	err = ice_read_cgu_reg_e822(hw, NAC_CGU_DWORD24, &dw24.val);
+	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD24, &dw24.val);
 	if (err)
 		return err;
 
@@ -1030,21 +1030,21 @@ ice_cfg_cgu_pll_e822(struct ice_hw *hw, enum ice_time_ref_freq clk_freq,
 	dw24.field.tspll_fbdiv_frac = e822_cgu_params[clk_freq].frac_n_div;
 	dw24.field.time_ref_sel = clk_src;
 
-	err = ice_write_cgu_reg_e822(hw, NAC_CGU_DWORD24, dw24.val);
+	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val);
 	if (err)
 		return err;
 
 	/* Finally, enable the PLL */
 	dw24.field.ts_pll_enable = 1;
 
-	err = ice_write_cgu_reg_e822(hw, NAC_CGU_DWORD24, dw24.val);
+	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val);
 	if (err)
 		return err;
 
 	/* Wait to verify if the PLL locks */
 	usleep_range(1000, 5000);
 
-	err = ice_read_cgu_reg_e822(hw, TSPLL_RO_BWM_LF, &bwm_lf.val);
+	err = ice_read_cgu_reg_e82x(hw, TSPLL_RO_BWM_LF, &bwm_lf.val);
 	if (err)
 		return err;
 
@@ -1064,18 +1064,18 @@ ice_cfg_cgu_pll_e822(struct ice_hw *hw, enum ice_time_ref_freq clk_freq,
 }
 
 /**
- * ice_init_cgu_e822 - Initialize CGU with settings from firmware
+ * ice_init_cgu_e82x - Initialize CGU with settings from firmware
  * @hw: pointer to the HW structure
  *
  * Initialize the Clock Generation Unit of the E822 device.
  */
-static int ice_init_cgu_e822(struct ice_hw *hw)
+static int ice_init_cgu_e82x(struct ice_hw *hw)
 {
 	struct ice_ts_func_info *ts_info = &hw->func_caps.ts_func_info;
 	union tspll_cntr_bist_settings cntr_bist;
 	int err;
 
-	err = ice_read_cgu_reg_e822(hw, TSPLL_CNTR_BIST_SETTINGS,
+	err = ice_read_cgu_reg_e82x(hw, TSPLL_CNTR_BIST_SETTINGS,
 				    &cntr_bist.val);
 	if (err)
 		return err;
@@ -1084,7 +1084,7 @@ static int ice_init_cgu_e822(struct ice_hw *hw)
 	cntr_bist.field.i_plllock_sel_0 = 0;
 	cntr_bist.field.i_plllock_sel_1 = 0;
 
-	err = ice_write_cgu_reg_e822(hw, TSPLL_CNTR_BIST_SETTINGS,
+	err = ice_write_cgu_reg_e82x(hw, TSPLL_CNTR_BIST_SETTINGS,
 				     cntr_bist.val);
 	if (err)
 		return err;
@@ -1092,7 +1092,7 @@ static int ice_init_cgu_e822(struct ice_hw *hw)
 	/* Configure the CGU PLL using the parameters from the function
 	 * capabilities.
 	 */
-	err = ice_cfg_cgu_pll_e822(hw, ts_info->time_ref,
+	err = ice_cfg_cgu_pll_e82x(hw, ts_info->time_ref,
 				   (enum ice_clk_src)ts_info->clk_src);
 	if (err)
 		return err;
@@ -1113,7 +1113,7 @@ static int ice_ptp_set_vernier_wl(struct ice_hw *hw)
 	for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) {
 		int err;
 
-		err = ice_write_phy_reg_e822(hw, port, P_REG_WL,
+		err = ice_write_phy_reg_e82x(hw, port, P_REG_WL,
 					     PTP_VERNIER_WL);
 		if (err) {
 			ice_debug(hw, ICE_DBG_PTP, "Failed to set vernier window length for port %u, err %d\n",
@@ -1126,12 +1126,12 @@ static int ice_ptp_set_vernier_wl(struct ice_hw *hw)
 }
 
 /**
- * ice_ptp_init_phc_e822 - Perform E822 specific PHC initialization
+ * ice_ptp_init_phc_e82x - Perform E822 specific PHC initialization
  * @hw: pointer to HW struct
  *
  * Perform PHC initialization steps specific to E822 devices.
  */
-static int ice_ptp_init_phc_e822(struct ice_hw *hw)
+static int ice_ptp_init_phc_e82x(struct ice_hw *hw)
 {
 	int err;
 	u32 regval;
@@ -1145,7 +1145,7 @@ static int ice_ptp_init_phc_e822(struct ice_hw *hw)
 	wr32(hw, PF_SB_REM_DEV_CTL, regval);
 
 	/* Initialize the Clock Generation Unit */
-	err = ice_init_cgu_e822(hw);
+	err = ice_init_cgu_e82x(hw);
 	if (err)
 		return err;
 
@@ -1154,7 +1154,7 @@ static int ice_ptp_init_phc_e822(struct ice_hw *hw)
 }
 
 /**
- * ice_ptp_prep_phy_time_e822 - Prepare PHY port with initial time
+ * ice_ptp_prep_phy_time_e82x - Prepare PHY port with initial time
  * @hw: pointer to the HW struct
  * @time: Time to initialize the PHY port clocks to
  *
@@ -1164,7 +1164,7 @@ static int ice_ptp_init_phc_e822(struct ice_hw *hw)
  * units of nominal nanoseconds.
  */
 static int
-ice_ptp_prep_phy_time_e822(struct ice_hw *hw, u32 time)
+ice_ptp_prep_phy_time_e82x(struct ice_hw *hw, u32 time)
 {
 	u64 phy_time;
 	u8 port;
@@ -1177,14 +1177,14 @@ ice_ptp_prep_phy_time_e822(struct ice_hw *hw, u32 time)
 
 	for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) {
 		/* Tx case */
-		err = ice_write_64b_phy_reg_e822(hw, port,
+		err = ice_write_64b_phy_reg_e82x(hw, port,
 						 P_REG_TX_TIMER_INC_PRE_L,
 						 phy_time);
 		if (err)
 			goto exit_err;
 
 		/* Rx case */
-		err = ice_write_64b_phy_reg_e822(hw, port,
+		err = ice_write_64b_phy_reg_e82x(hw, port,
 						 P_REG_RX_TIMER_INC_PRE_L,
 						 phy_time);
 		if (err)
@@ -1201,7 +1201,7 @@ exit_err:
 }
 
 /**
- * ice_ptp_prep_port_adj_e822 - Prepare a single port for time adjust
+ * ice_ptp_prep_port_adj_e82x - Prepare a single port for time adjust
  * @hw: pointer to HW struct
  * @port: Port number to be programmed
  * @time: time in cycles to adjust the port Tx and Rx clocks
@@ -1216,7 +1216,7 @@ exit_err:
  * Negative adjustments are supported using 2s complement arithmetic.
  */
 static int
-ice_ptp_prep_port_adj_e822(struct ice_hw *hw, u8 port, s64 time)
+ice_ptp_prep_port_adj_e82x(struct ice_hw *hw, u8 port, s64 time)
 {
 	u32 l_time, u_time;
 	int err;
@@ -1225,23 +1225,23 @@ ice_ptp_prep_port_adj_e822(struct ice_hw *hw, u8 port, s64 time)
 	u_time = upper_32_bits(time);
 
 	/* Tx case */
-	err = ice_write_phy_reg_e822(hw, port, P_REG_TX_TIMER_INC_PRE_L,
+	err = ice_write_phy_reg_e82x(hw, port, P_REG_TX_TIMER_INC_PRE_L,
 				     l_time);
 	if (err)
 		goto exit_err;
 
-	err = ice_write_phy_reg_e822(hw, port, P_REG_TX_TIMER_INC_PRE_U,
+	err = ice_write_phy_reg_e82x(hw, port, P_REG_TX_TIMER_INC_PRE_U,
 				     u_time);
 	if (err)
 		goto exit_err;
 
 	/* Rx case */
-	err = ice_write_phy_reg_e822(hw, port, P_REG_RX_TIMER_INC_PRE_L,
+	err = ice_write_phy_reg_e82x(hw, port, P_REG_RX_TIMER_INC_PRE_L,
 				     l_time);
 	if (err)
 		goto exit_err;
 
-	err = ice_write_phy_reg_e822(hw, port, P_REG_RX_TIMER_INC_PRE_U,
+	err = ice_write_phy_reg_e82x(hw, port, P_REG_RX_TIMER_INC_PRE_U,
 				     u_time);
 	if (err)
 		goto exit_err;
@@ -1255,7 +1255,7 @@ exit_err:
 }
 
 /**
- * ice_ptp_prep_phy_adj_e822 - Prep PHY ports for a time adjustment
+ * ice_ptp_prep_phy_adj_e82x - Prep PHY ports for a time adjustment
  * @hw: pointer to HW struct
  * @adj: adjustment in nanoseconds
  *
@@ -1264,7 +1264,7 @@ exit_err:
  * ICE_PTP_ADJ_TIME or ICE_PTP_ADJ_TIME_AT_TIME sync command.
  */
 static int
-ice_ptp_prep_phy_adj_e822(struct ice_hw *hw, s32 adj)
+ice_ptp_prep_phy_adj_e82x(struct ice_hw *hw, s32 adj)
 {
 	s64 cycles;
 	u8 port;
@@ -1281,7 +1281,7 @@ ice_ptp_prep_phy_adj_e822(struct ice_hw *hw, s32 adj)
 	for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) {
 		int err;
 
-		err = ice_ptp_prep_port_adj_e822(hw, port, cycles);
+		err = ice_ptp_prep_port_adj_e82x(hw, port, cycles);
 		if (err)
 			return err;
 	}
@@ -1290,7 +1290,7 @@ ice_ptp_prep_phy_adj_e822(struct ice_hw *hw, s32 adj)
 }
 
 /**
- * ice_ptp_prep_phy_incval_e822 - Prepare PHY ports for time adjustment
+ * ice_ptp_prep_phy_incval_e82x - Prepare PHY ports for time adjustment
  * @hw: pointer to HW struct
  * @incval: new increment value to prepare
  *
@@ -1299,13 +1299,13 @@ ice_ptp_prep_phy_adj_e822(struct ice_hw *hw, s32 adj)
  * issuing an ICE_PTP_INIT_INCVAL command.
  */
 static int
-ice_ptp_prep_phy_incval_e822(struct ice_hw *hw, u64 incval)
+ice_ptp_prep_phy_incval_e82x(struct ice_hw *hw, u64 incval)
 {
 	int err;
 	u8 port;
 
 	for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) {
-		err = ice_write_40b_phy_reg_e822(hw, port, P_REG_TIMETUS_L,
+		err = ice_write_40b_phy_reg_e82x(hw, port, P_REG_TIMETUS_L,
 						 incval);
 		if (err)
 			goto exit_err;
@@ -1337,7 +1337,7 @@ ice_ptp_read_port_capture(struct ice_hw *hw, u8 port, u64 *tx_ts, u64 *rx_ts)
 	int err;
 
 	/* Tx case */
-	err = ice_read_64b_phy_reg_e822(hw, port, P_REG_TX_CAPTURE_L, tx_ts);
+	err = ice_read_64b_phy_reg_e82x(hw, port, P_REG_TX_CAPTURE_L, tx_ts);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to read REG_TX_CAPTURE, err %d\n",
 			  err);
@@ -1348,7 +1348,7 @@ ice_ptp_read_port_capture(struct ice_hw *hw, u8 port, u64 *tx_ts, u64 *rx_ts)
 		  (unsigned long long)*tx_ts);
 
 	/* Rx case */
-	err = ice_read_64b_phy_reg_e822(hw, port, P_REG_RX_CAPTURE_L, rx_ts);
+	err = ice_read_64b_phy_reg_e82x(hw, port, P_REG_RX_CAPTURE_L, rx_ts);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to read RX_CAPTURE, err %d\n",
 			  err);
@@ -1362,7 +1362,7 @@ ice_ptp_read_port_capture(struct ice_hw *hw, u8 port, u64 *tx_ts, u64 *rx_ts)
 }
 
 /**
- * ice_ptp_write_port_cmd_e822 - Prepare a single PHY port for a timer command
+ * ice_ptp_write_port_cmd_e82x - Prepare a single PHY port for a timer command
  * @hw: pointer to HW struct
  * @port: Port to which cmd has to be sent
  * @cmd: Command to be sent to the port
@@ -1372,8 +1372,8 @@ ice_ptp_read_port_capture(struct ice_hw *hw, u8 port, u64 *tx_ts, u64 *rx_ts)
  * Do not use this function directly. If you want to configure exactly one
  * port, use ice_ptp_one_port_cmd() instead.
  */
-static int
-ice_ptp_write_port_cmd_e822(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd)
+static int ice_ptp_write_port_cmd_e82x(struct ice_hw *hw, u8 port,
+				       enum ice_ptp_tmr_cmd cmd)
 {
 	u32 cmd_val, val;
 	u8 tmr_idx;
@@ -1403,7 +1403,7 @@ ice_ptp_write_port_cmd_e822(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd
 
 	/* Tx case */
 	/* Read, modify, write */
-	err = ice_read_phy_reg_e822(hw, port, P_REG_TX_TMR_CMD, &val);
+	err = ice_read_phy_reg_e82x(hw, port, P_REG_TX_TMR_CMD, &val);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to read TX_TMR_CMD, err %d\n",
 			  err);
@@ -1414,7 +1414,7 @@ ice_ptp_write_port_cmd_e822(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd
 	val &= ~TS_CMD_MASK;
 	val |= cmd_val;
 
-	err = ice_write_phy_reg_e822(hw, port, P_REG_TX_TMR_CMD, val);
+	err = ice_write_phy_reg_e82x(hw, port, P_REG_TX_TMR_CMD, val);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to write back TX_TMR_CMD, err %d\n",
 			  err);
@@ -1423,7 +1423,7 @@ ice_ptp_write_port_cmd_e822(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd
 
 	/* Rx case */
 	/* Read, modify, write */
-	err = ice_read_phy_reg_e822(hw, port, P_REG_RX_TMR_CMD, &val);
+	err = ice_read_phy_reg_e82x(hw, port, P_REG_RX_TMR_CMD, &val);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to read RX_TMR_CMD, err %d\n",
 			  err);
@@ -1434,7 +1434,7 @@ ice_ptp_write_port_cmd_e822(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd
 	val &= ~TS_CMD_MASK;
 	val |= cmd_val;
 
-	err = ice_write_phy_reg_e822(hw, port, P_REG_RX_TMR_CMD, val);
+	err = ice_write_phy_reg_e82x(hw, port, P_REG_RX_TMR_CMD, val);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to write back RX_TMR_CMD, err %d\n",
 			  err);
@@ -1469,7 +1469,7 @@ ice_ptp_one_port_cmd(struct ice_hw *hw, u8 configured_port,
 		else
 			cmd = ICE_PTP_NOP;
 
-		err = ice_ptp_write_port_cmd_e822(hw, port, cmd);
+		err = ice_ptp_write_port_cmd_e82x(hw, port, cmd);
 		if (err)
 			return err;
 	}
@@ -1478,7 +1478,7 @@ ice_ptp_one_port_cmd(struct ice_hw *hw, u8 configured_port,
 }
 
 /**
- * ice_ptp_port_cmd_e822 - Prepare all ports for a timer command
+ * ice_ptp_port_cmd_e82x - Prepare all ports for a timer command
  * @hw: pointer to the HW struct
  * @cmd: timer command to prepare
  *
@@ -1486,14 +1486,14 @@ ice_ptp_one_port_cmd(struct ice_hw *hw, u8 configured_port,
  * command.
  */
 static int
-ice_ptp_port_cmd_e822(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
+ice_ptp_port_cmd_e82x(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
 {
 	u8 port;
 
 	for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) {
 		int err;
 
-		err = ice_ptp_write_port_cmd_e822(hw, port, cmd);
+		err = ice_ptp_write_port_cmd_e82x(hw, port, cmd);
 		if (err)
 			return err;
 	}
@@ -1509,7 +1509,7 @@ ice_ptp_port_cmd_e822(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
  */
 
 /**
- * ice_phy_get_speed_and_fec_e822 - Get link speed and FEC based on serdes mode
+ * ice_phy_get_speed_and_fec_e82x - Get link speed and FEC based on serdes mode
  * @hw: pointer to HW struct
  * @port: the port to read from
  * @link_out: if non-NULL, holds link speed on success
@@ -1519,7 +1519,7 @@ ice_ptp_port_cmd_e822(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
  * algorithm.
  */
 static int
-ice_phy_get_speed_and_fec_e822(struct ice_hw *hw, u8 port,
+ice_phy_get_speed_and_fec_e82x(struct ice_hw *hw, u8 port,
 			       enum ice_ptp_link_spd *link_out,
 			       enum ice_ptp_fec_mode *fec_out)
 {
@@ -1528,7 +1528,7 @@ ice_phy_get_speed_and_fec_e822(struct ice_hw *hw, u8 port,
 	u32 serdes;
 	int err;
 
-	err = ice_read_phy_reg_e822(hw, port, P_REG_LINK_SPEED, &serdes);
+	err = ice_read_phy_reg_e82x(hw, port, P_REG_LINK_SPEED, &serdes);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to read serdes info\n");
 		return err;
@@ -1585,18 +1585,18 @@ ice_phy_get_speed_and_fec_e822(struct ice_hw *hw, u8 port,
 }
 
 /**
- * ice_phy_cfg_lane_e822 - Configure PHY quad for single/multi-lane timestamp
+ * ice_phy_cfg_lane_e82x - Configure PHY quad for single/multi-lane timestamp
  * @hw: pointer to HW struct
  * @port: to configure the quad for
  */
-static void ice_phy_cfg_lane_e822(struct ice_hw *hw, u8 port)
+static void ice_phy_cfg_lane_e82x(struct ice_hw *hw, u8 port)
 {
 	enum ice_ptp_link_spd link_spd;
 	int err;
 	u32 val;
 	u8 quad;
 
-	err = ice_phy_get_speed_and_fec_e822(hw, port, &link_spd, NULL);
+	err = ice_phy_get_speed_and_fec_e82x(hw, port, &link_spd, NULL);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to get PHY link speed, err %d\n",
 			  err);
@@ -1605,7 +1605,7 @@ static void ice_phy_cfg_lane_e822(struct ice_hw *hw, u8 port)
 
 	quad = port / ICE_PORTS_PER_QUAD;
 
-	err = ice_read_quad_reg_e822(hw, quad, Q_REG_TX_MEM_GBL_CFG, &val);
+	err = ice_read_quad_reg_e82x(hw, quad, Q_REG_TX_MEM_GBL_CFG, &val);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to read TX_MEM_GLB_CFG, err %d\n",
 			  err);
@@ -1617,7 +1617,7 @@ static void ice_phy_cfg_lane_e822(struct ice_hw *hw, u8 port)
 	else
 		val |= Q_REG_TX_MEM_GBL_CFG_LANE_TYPE_M;
 
-	err = ice_write_quad_reg_e822(hw, quad, Q_REG_TX_MEM_GBL_CFG, val);
+	err = ice_write_quad_reg_e82x(hw, quad, Q_REG_TX_MEM_GBL_CFG, val);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to write back TX_MEM_GBL_CFG, err %d\n",
 			  err);
@@ -1626,7 +1626,7 @@ static void ice_phy_cfg_lane_e822(struct ice_hw *hw, u8 port)
 }
 
 /**
- * ice_phy_cfg_uix_e822 - Configure Serdes UI to TU conversion for E822
+ * ice_phy_cfg_uix_e82x - Configure Serdes UI to TU conversion for E822
  * @hw: pointer to the HW structure
  * @port: the port to configure
  *
@@ -1671,12 +1671,12 @@ static void ice_phy_cfg_lane_e822(struct ice_hw *hw, u8 port)
  * a divide by 390,625,000. This does lose some precision, but avoids
  * miscalculation due to arithmetic overflow.
  */
-static int ice_phy_cfg_uix_e822(struct ice_hw *hw, u8 port)
+static int ice_phy_cfg_uix_e82x(struct ice_hw *hw, u8 port)
 {
 	u64 cur_freq, clk_incval, tu_per_sec, uix;
 	int err;
 
-	cur_freq = ice_e822_pll_freq(ice_e822_time_ref(hw));
+	cur_freq = ice_e82x_pll_freq(ice_e82x_time_ref(hw));
 	clk_incval = ice_ptp_read_src_incval(hw);
 
 	/* Calculate TUs per second divided by 256 */
@@ -1688,7 +1688,7 @@ static int ice_phy_cfg_uix_e822(struct ice_hw *hw, u8 port)
 	/* Program the 10Gb/40Gb conversion ratio */
 	uix = div_u64(tu_per_sec * LINE_UI_10G_40G, 390625000);
 
-	err = ice_write_64b_phy_reg_e822(hw, port, P_REG_UIX66_10G_40G_L,
+	err = ice_write_64b_phy_reg_e82x(hw, port, P_REG_UIX66_10G_40G_L,
 					 uix);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to write UIX66_10G_40G, err %d\n",
@@ -1699,7 +1699,7 @@ static int ice_phy_cfg_uix_e822(struct ice_hw *hw, u8 port)
 	/* Program the 25Gb/100Gb conversion ratio */
 	uix = div_u64(tu_per_sec * LINE_UI_25G_100G, 390625000);
 
-	err = ice_write_64b_phy_reg_e822(hw, port, P_REG_UIX66_25G_100G_L,
+	err = ice_write_64b_phy_reg_e82x(hw, port, P_REG_UIX66_25G_100G_L,
 					 uix);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to write UIX66_25G_100G, err %d\n",
@@ -1711,7 +1711,7 @@ static int ice_phy_cfg_uix_e822(struct ice_hw *hw, u8 port)
 }
 
 /**
- * ice_phy_cfg_parpcs_e822 - Configure TUs per PAR/PCS clock cycle
+ * ice_phy_cfg_parpcs_e82x - Configure TUs per PAR/PCS clock cycle
  * @hw: pointer to the HW struct
  * @port: port to configure
  *
@@ -1753,18 +1753,18 @@ static int ice_phy_cfg_uix_e822(struct ice_hw *hw, u8 port)
  * frequency is ~29 bits, so multiplying them together should fit within the
  * 64 bit arithmetic.
  */
-static int ice_phy_cfg_parpcs_e822(struct ice_hw *hw, u8 port)
+static int ice_phy_cfg_parpcs_e82x(struct ice_hw *hw, u8 port)
 {
 	u64 cur_freq, clk_incval, tu_per_sec, phy_tus;
 	enum ice_ptp_link_spd link_spd;
 	enum ice_ptp_fec_mode fec_mode;
 	int err;
 
-	err = ice_phy_get_speed_and_fec_e822(hw, port, &link_spd, &fec_mode);
+	err = ice_phy_get_speed_and_fec_e82x(hw, port, &link_spd, &fec_mode);
 	if (err)
 		return err;
 
-	cur_freq = ice_e822_pll_freq(ice_e822_time_ref(hw));
+	cur_freq = ice_e82x_pll_freq(ice_e82x_time_ref(hw));
 	clk_incval = ice_ptp_read_src_incval(hw);
 
 	/* Calculate TUs per cycle of the PHC clock */
@@ -1784,7 +1784,7 @@ static int ice_phy_cfg_parpcs_e822(struct ice_hw *hw, u8 port)
 	else
 		phy_tus = 0;
 
-	err = ice_write_40b_phy_reg_e822(hw, port, P_REG_PAR_TX_TUS_L,
+	err = ice_write_40b_phy_reg_e82x(hw, port, P_REG_PAR_TX_TUS_L,
 					 phy_tus);
 	if (err)
 		return err;
@@ -1796,7 +1796,7 @@ static int ice_phy_cfg_parpcs_e822(struct ice_hw *hw, u8 port)
 	else
 		phy_tus = 0;
 
-	err = ice_write_40b_phy_reg_e822(hw, port, P_REG_PAR_RX_TUS_L,
+	err = ice_write_40b_phy_reg_e82x(hw, port, P_REG_PAR_RX_TUS_L,
 					 phy_tus);
 	if (err)
 		return err;
@@ -1808,7 +1808,7 @@ static int ice_phy_cfg_parpcs_e822(struct ice_hw *hw, u8 port)
 	else
 		phy_tus = 0;
 
-	err = ice_write_40b_phy_reg_e822(hw, port, P_REG_PCS_TX_TUS_L,
+	err = ice_write_40b_phy_reg_e82x(hw, port, P_REG_PCS_TX_TUS_L,
 					 phy_tus);
 	if (err)
 		return err;
@@ -1820,7 +1820,7 @@ static int ice_phy_cfg_parpcs_e822(struct ice_hw *hw, u8 port)
 	else
 		phy_tus = 0;
 
-	err = ice_write_40b_phy_reg_e822(hw, port, P_REG_PCS_RX_TUS_L,
+	err = ice_write_40b_phy_reg_e82x(hw, port, P_REG_PCS_RX_TUS_L,
 					 phy_tus);
 	if (err)
 		return err;
@@ -1832,7 +1832,7 @@ static int ice_phy_cfg_parpcs_e822(struct ice_hw *hw, u8 port)
 	else
 		phy_tus = 0;
 
-	err = ice_write_40b_phy_reg_e822(hw, port, P_REG_DESK_PAR_TX_TUS_L,
+	err = ice_write_40b_phy_reg_e82x(hw, port, P_REG_DESK_PAR_TX_TUS_L,
 					 phy_tus);
 	if (err)
 		return err;
@@ -1844,7 +1844,7 @@ static int ice_phy_cfg_parpcs_e822(struct ice_hw *hw, u8 port)
 	else
 		phy_tus = 0;
 
-	err = ice_write_40b_phy_reg_e822(hw, port, P_REG_DESK_PAR_RX_TUS_L,
+	err = ice_write_40b_phy_reg_e82x(hw, port, P_REG_DESK_PAR_RX_TUS_L,
 					 phy_tus);
 	if (err)
 		return err;
@@ -1856,7 +1856,7 @@ static int ice_phy_cfg_parpcs_e822(struct ice_hw *hw, u8 port)
 	else
 		phy_tus = 0;
 
-	err = ice_write_40b_phy_reg_e822(hw, port, P_REG_DESK_PCS_TX_TUS_L,
+	err = ice_write_40b_phy_reg_e82x(hw, port, P_REG_DESK_PCS_TX_TUS_L,
 					 phy_tus);
 	if (err)
 		return err;
@@ -1868,23 +1868,23 @@ static int ice_phy_cfg_parpcs_e822(struct ice_hw *hw, u8 port)
 	else
 		phy_tus = 0;
 
-	return ice_write_40b_phy_reg_e822(hw, port, P_REG_DESK_PCS_RX_TUS_L,
+	return ice_write_40b_phy_reg_e82x(hw, port, P_REG_DESK_PCS_RX_TUS_L,
 					  phy_tus);
 }
 
 /**
- * ice_calc_fixed_tx_offset_e822 - Calculated Fixed Tx offset for a port
+ * ice_calc_fixed_tx_offset_e82x - Calculated Fixed Tx offset for a port
  * @hw: pointer to the HW struct
  * @link_spd: the Link speed to calculate for
  *
  * Calculate the fixed offset due to known static latency data.
  */
 static u64
-ice_calc_fixed_tx_offset_e822(struct ice_hw *hw, enum ice_ptp_link_spd link_spd)
+ice_calc_fixed_tx_offset_e82x(struct ice_hw *hw, enum ice_ptp_link_spd link_spd)
 {
 	u64 cur_freq, clk_incval, tu_per_sec, fixed_offset;
 
-	cur_freq = ice_e822_pll_freq(ice_e822_time_ref(hw));
+	cur_freq = ice_e82x_pll_freq(ice_e82x_time_ref(hw));
 	clk_incval = ice_ptp_read_src_incval(hw);
 
 	/* Calculate TUs per second */
@@ -1904,7 +1904,7 @@ ice_calc_fixed_tx_offset_e822(struct ice_hw *hw, enum ice_ptp_link_spd link_spd)
 }
 
 /**
- * ice_phy_cfg_tx_offset_e822 - Configure total Tx timestamp offset
+ * ice_phy_cfg_tx_offset_e82x - Configure total Tx timestamp offset
  * @hw: pointer to the HW struct
  * @port: the PHY port to configure
  *
@@ -1926,7 +1926,7 @@ ice_calc_fixed_tx_offset_e822(struct ice_hw *hw, enum ice_ptp_link_spd link_spd)
  * Returns zero on success, -EBUSY if the hardware vernier offset
  * calibration has not completed, or another error code on failure.
  */
-int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port)
+int ice_phy_cfg_tx_offset_e82x(struct ice_hw *hw, u8 port)
 {
 	enum ice_ptp_link_spd link_spd;
 	enum ice_ptp_fec_mode fec_mode;
@@ -1935,7 +1935,7 @@ int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port)
 	u32 reg;
 
 	/* Nothing to do if we've already programmed the offset */
-	err = ice_read_phy_reg_e822(hw, port, P_REG_TX_OR, &reg);
+	err = ice_read_phy_reg_e82x(hw, port, P_REG_TX_OR, &reg);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to read TX_OR for port %u, err %d\n",
 			  port, err);
@@ -1945,7 +1945,7 @@ int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port)
 	if (reg)
 		return 0;
 
-	err = ice_read_phy_reg_e822(hw, port, P_REG_TX_OV_STATUS, &reg);
+	err = ice_read_phy_reg_e82x(hw, port, P_REG_TX_OV_STATUS, &reg);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to read TX_OV_STATUS for port %u, err %d\n",
 			  port, err);
@@ -1955,11 +1955,11 @@ int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port)
 	if (!(reg & P_REG_TX_OV_STATUS_OV_M))
 		return -EBUSY;
 
-	err = ice_phy_get_speed_and_fec_e822(hw, port, &link_spd, &fec_mode);
+	err = ice_phy_get_speed_and_fec_e82x(hw, port, &link_spd, &fec_mode);
 	if (err)
 		return err;
 
-	total_offset = ice_calc_fixed_tx_offset_e822(hw, link_spd);
+	total_offset = ice_calc_fixed_tx_offset_e82x(hw, link_spd);
 
 	/* Read the first Vernier offset from the PHY register and add it to
 	 * the total offset.
@@ -1970,7 +1970,7 @@ int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port)
 	    link_spd == ICE_PTP_LNK_SPD_25G_RS ||
 	    link_spd == ICE_PTP_LNK_SPD_40G ||
 	    link_spd == ICE_PTP_LNK_SPD_50G) {
-		err = ice_read_64b_phy_reg_e822(hw, port,
+		err = ice_read_64b_phy_reg_e82x(hw, port,
 						P_REG_PAR_PCS_TX_OFFSET_L,
 						&val);
 		if (err)
@@ -1985,7 +1985,7 @@ int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port)
 	 */
 	if (link_spd == ICE_PTP_LNK_SPD_50G_RS ||
 	    link_spd == ICE_PTP_LNK_SPD_100G_RS) {
-		err = ice_read_64b_phy_reg_e822(hw, port,
+		err = ice_read_64b_phy_reg_e82x(hw, port,
 						P_REG_PAR_TX_TIME_L,
 						&val);
 		if (err)
@@ -1998,12 +1998,12 @@ int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port)
 	 * PHY and indicate that the Tx offset is ready. After this,
 	 * timestamps will be enabled.
 	 */
-	err = ice_write_64b_phy_reg_e822(hw, port, P_REG_TOTAL_TX_OFFSET_L,
+	err = ice_write_64b_phy_reg_e82x(hw, port, P_REG_TOTAL_TX_OFFSET_L,
 					 total_offset);
 	if (err)
 		return err;
 
-	err = ice_write_phy_reg_e822(hw, port, P_REG_TX_OR, 1);
+	err = ice_write_phy_reg_e82x(hw, port, P_REG_TX_OR, 1);
 	if (err)
 		return err;
 
@@ -2014,7 +2014,7 @@ int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port)
 }
 
 /**
- * ice_phy_calc_pmd_adj_e822 - Calculate PMD adjustment for Rx
+ * ice_phy_calc_pmd_adj_e82x - Calculate PMD adjustment for Rx
  * @hw: pointer to the HW struct
  * @port: the PHY port to adjust for
  * @link_spd: the current link speed of the PHY
@@ -2026,7 +2026,7 @@ int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port)
  * various delays caused when receiving a packet.
  */
 static int
-ice_phy_calc_pmd_adj_e822(struct ice_hw *hw, u8 port,
+ice_phy_calc_pmd_adj_e82x(struct ice_hw *hw, u8 port,
 			  enum ice_ptp_link_spd link_spd,
 			  enum ice_ptp_fec_mode fec_mode, u64 *pmd_adj)
 {
@@ -2035,7 +2035,7 @@ ice_phy_calc_pmd_adj_e822(struct ice_hw *hw, u8 port,
 	u32 val;
 	int err;
 
-	err = ice_read_phy_reg_e822(hw, port, P_REG_PMD_ALIGNMENT, &val);
+	err = ice_read_phy_reg_e82x(hw, port, P_REG_PMD_ALIGNMENT, &val);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to read PMD alignment, err %d\n",
 			  err);
@@ -2044,7 +2044,7 @@ ice_phy_calc_pmd_adj_e822(struct ice_hw *hw, u8 port,
 
 	pmd_align = (u8)val;
 
-	cur_freq = ice_e822_pll_freq(ice_e822_time_ref(hw));
+	cur_freq = ice_e82x_pll_freq(ice_e82x_time_ref(hw));
 	clk_incval = ice_ptp_read_src_incval(hw);
 
 	/* Calculate TUs per second */
@@ -2123,7 +2123,7 @@ ice_phy_calc_pmd_adj_e822(struct ice_hw *hw, u8 port,
 		u64 cycle_adj;
 		u8 rx_cycle;
 
-		err = ice_read_phy_reg_e822(hw, port, P_REG_RX_40_TO_160_CNT,
+		err = ice_read_phy_reg_e82x(hw, port, P_REG_RX_40_TO_160_CNT,
 					    &val);
 		if (err) {
 			ice_debug(hw, ICE_DBG_PTP, "Failed to read 25G-RS Rx cycle count, err %d\n",
@@ -2145,7 +2145,7 @@ ice_phy_calc_pmd_adj_e822(struct ice_hw *hw, u8 port,
 		u64 cycle_adj;
 		u8 rx_cycle;
 
-		err = ice_read_phy_reg_e822(hw, port, P_REG_RX_80_TO_160_CNT,
+		err = ice_read_phy_reg_e82x(hw, port, P_REG_RX_80_TO_160_CNT,
 					    &val);
 		if (err) {
 			ice_debug(hw, ICE_DBG_PTP, "Failed to read 50G-RS Rx cycle count, err %d\n",
@@ -2172,18 +2172,18 @@ ice_phy_calc_pmd_adj_e822(struct ice_hw *hw, u8 port,
 }
 
 /**
- * ice_calc_fixed_rx_offset_e822 - Calculated the fixed Rx offset for a port
+ * ice_calc_fixed_rx_offset_e82x - Calculated the fixed Rx offset for a port
  * @hw: pointer to HW struct
  * @link_spd: The Link speed to calculate for
  *
  * Determine the fixed Rx latency for a given link speed.
  */
 static u64
-ice_calc_fixed_rx_offset_e822(struct ice_hw *hw, enum ice_ptp_link_spd link_spd)
+ice_calc_fixed_rx_offset_e82x(struct ice_hw *hw, enum ice_ptp_link_spd link_spd)
 {
 	u64 cur_freq, clk_incval, tu_per_sec, fixed_offset;
 
-	cur_freq = ice_e822_pll_freq(ice_e822_time_ref(hw));
+	cur_freq = ice_e82x_pll_freq(ice_e82x_time_ref(hw));
 	clk_incval = ice_ptp_read_src_incval(hw);
 
 	/* Calculate TUs per second */
@@ -2203,7 +2203,7 @@ ice_calc_fixed_rx_offset_e822(struct ice_hw *hw, enum ice_ptp_link_spd link_spd)
 }
 
 /**
- * ice_phy_cfg_rx_offset_e822 - Configure total Rx timestamp offset
+ * ice_phy_cfg_rx_offset_e82x - Configure total Rx timestamp offset
  * @hw: pointer to the HW struct
  * @port: the PHY port to configure
  *
@@ -2229,7 +2229,7 @@ ice_calc_fixed_rx_offset_e822(struct ice_hw *hw, enum ice_ptp_link_spd link_spd)
  * Returns zero on success, -EBUSY if the hardware vernier offset
  * calibration has not completed, or another error code on failure.
  */
-int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port)
+int ice_phy_cfg_rx_offset_e82x(struct ice_hw *hw, u8 port)
 {
 	enum ice_ptp_link_spd link_spd;
 	enum ice_ptp_fec_mode fec_mode;
@@ -2238,7 +2238,7 @@ int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port)
 	u32 reg;
 
 	/* Nothing to do if we've already programmed the offset */
-	err = ice_read_phy_reg_e822(hw, port, P_REG_RX_OR, &reg);
+	err = ice_read_phy_reg_e82x(hw, port, P_REG_RX_OR, &reg);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to read RX_OR for port %u, err %d\n",
 			  port, err);
@@ -2248,7 +2248,7 @@ int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port)
 	if (reg)
 		return 0;
 
-	err = ice_read_phy_reg_e822(hw, port, P_REG_RX_OV_STATUS, &reg);
+	err = ice_read_phy_reg_e82x(hw, port, P_REG_RX_OV_STATUS, &reg);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to read RX_OV_STATUS for port %u, err %d\n",
 			  port, err);
@@ -2258,16 +2258,16 @@ int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port)
 	if (!(reg & P_REG_RX_OV_STATUS_OV_M))
 		return -EBUSY;
 
-	err = ice_phy_get_speed_and_fec_e822(hw, port, &link_spd, &fec_mode);
+	err = ice_phy_get_speed_and_fec_e82x(hw, port, &link_spd, &fec_mode);
 	if (err)
 		return err;
 
-	total_offset = ice_calc_fixed_rx_offset_e822(hw, link_spd);
+	total_offset = ice_calc_fixed_rx_offset_e82x(hw, link_spd);
 
 	/* Read the first Vernier offset from the PHY register and add it to
 	 * the total offset.
 	 */
-	err = ice_read_64b_phy_reg_e822(hw, port,
+	err = ice_read_64b_phy_reg_e82x(hw, port,
 					P_REG_PAR_PCS_RX_OFFSET_L,
 					&val);
 	if (err)
@@ -2282,7 +2282,7 @@ int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port)
 	    link_spd == ICE_PTP_LNK_SPD_50G ||
 	    link_spd == ICE_PTP_LNK_SPD_50G_RS ||
 	    link_spd == ICE_PTP_LNK_SPD_100G_RS) {
-		err = ice_read_64b_phy_reg_e822(hw, port,
+		err = ice_read_64b_phy_reg_e82x(hw, port,
 						P_REG_PAR_RX_TIME_L,
 						&val);
 		if (err)
@@ -2292,7 +2292,7 @@ int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port)
 	}
 
 	/* In addition, Rx must account for the PMD alignment */
-	err = ice_phy_calc_pmd_adj_e822(hw, port, link_spd, fec_mode, &pmd);
+	err = ice_phy_calc_pmd_adj_e82x(hw, port, link_spd, fec_mode, &pmd);
 	if (err)
 		return err;
 
@@ -2308,12 +2308,12 @@ int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port)
 	 * PHY and indicate that the Rx offset is ready. After this,
 	 * timestamps will be enabled.
 	 */
-	err = ice_write_64b_phy_reg_e822(hw, port, P_REG_TOTAL_RX_OFFSET_L,
+	err = ice_write_64b_phy_reg_e82x(hw, port, P_REG_TOTAL_RX_OFFSET_L,
 					 total_offset);
 	if (err)
 		return err;
 
-	err = ice_write_phy_reg_e822(hw, port, P_REG_RX_OR, 1);
+	err = ice_write_phy_reg_e82x(hw, port, P_REG_RX_OR, 1);
 	if (err)
 		return err;
 
@@ -2324,7 +2324,7 @@ int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port)
 }
 
 /**
- * ice_read_phy_and_phc_time_e822 - Simultaneously capture PHC and PHY time
+ * ice_read_phy_and_phc_time_e82x - Simultaneously capture PHC and PHY time
  * @hw: pointer to the HW struct
  * @port: the PHY port to read
  * @phy_time: on return, the 64bit PHY timer value
@@ -2334,7 +2334,7 @@ int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port)
  * and PHC timer values.
  */
 static int
-ice_read_phy_and_phc_time_e822(struct ice_hw *hw, u8 port, u64 *phy_time,
+ice_read_phy_and_phc_time_e82x(struct ice_hw *hw, u8 port, u64 *phy_time,
 			       u64 *phc_time)
 {
 	u64 tx_time, rx_time;
@@ -2381,7 +2381,7 @@ ice_read_phy_and_phc_time_e822(struct ice_hw *hw, u8 port, u64 *phy_time,
 }
 
 /**
- * ice_sync_phy_timer_e822 - Synchronize the PHY timer with PHC timer
+ * ice_sync_phy_timer_e82x - Synchronize the PHY timer with PHC timer
  * @hw: pointer to the HW struct
  * @port: the PHY port to synchronize
  *
@@ -2392,7 +2392,7 @@ ice_read_phy_and_phc_time_e822(struct ice_hw *hw, u8 port, u64 *phy_time,
  * to the PHY timer in order to ensure it reads the same value as the
  * primary PHC timer.
  */
-static int ice_sync_phy_timer_e822(struct ice_hw *hw, u8 port)
+static int ice_sync_phy_timer_e82x(struct ice_hw *hw, u8 port)
 {
 	u64 phc_time, phy_time, difference;
 	int err;
@@ -2402,7 +2402,7 @@ static int ice_sync_phy_timer_e822(struct ice_hw *hw, u8 port)
 		return -EBUSY;
 	}
 
-	err = ice_read_phy_and_phc_time_e822(hw, port, &phy_time, &phc_time);
+	err = ice_read_phy_and_phc_time_e82x(hw, port, &phy_time, &phc_time);
 	if (err)
 		goto err_unlock;
 
@@ -2416,7 +2416,7 @@ static int ice_sync_phy_timer_e822(struct ice_hw *hw, u8 port)
 	 */
 	difference = phc_time - phy_time;
 
-	err = ice_ptp_prep_port_adj_e822(hw, port, (s64)difference);
+	err = ice_ptp_prep_port_adj_e82x(hw, port, (s64)difference);
 	if (err)
 		goto err_unlock;
 
@@ -2433,7 +2433,7 @@ static int ice_sync_phy_timer_e822(struct ice_hw *hw, u8 port)
 	/* Re-capture the timer values to flush the command registers and
 	 * verify that the time was properly adjusted.
 	 */
-	err = ice_read_phy_and_phc_time_e822(hw, port, &phy_time, &phc_time);
+	err = ice_read_phy_and_phc_time_e82x(hw, port, &phy_time, &phc_time);
 	if (err)
 		goto err_unlock;
 
@@ -2452,7 +2452,7 @@ err_unlock:
 }
 
 /**
- * ice_stop_phy_timer_e822 - Stop the PHY clock timer
+ * ice_stop_phy_timer_e82x - Stop the PHY clock timer
  * @hw: pointer to the HW struct
  * @port: the PHY port to stop
  * @soft_reset: if true, hold the SOFT_RESET bit of P_REG_PS
@@ -2462,36 +2462,36 @@ err_unlock:
  * initialized or when link speed changes.
  */
 int
-ice_stop_phy_timer_e822(struct ice_hw *hw, u8 port, bool soft_reset)
+ice_stop_phy_timer_e82x(struct ice_hw *hw, u8 port, bool soft_reset)
 {
 	int err;
 	u32 val;
 
-	err = ice_write_phy_reg_e822(hw, port, P_REG_TX_OR, 0);
+	err = ice_write_phy_reg_e82x(hw, port, P_REG_TX_OR, 0);
 	if (err)
 		return err;
 
-	err = ice_write_phy_reg_e822(hw, port, P_REG_RX_OR, 0);
+	err = ice_write_phy_reg_e82x(hw, port, P_REG_RX_OR, 0);
 	if (err)
 		return err;
 
-	err = ice_read_phy_reg_e822(hw, port, P_REG_PS, &val);
+	err = ice_read_phy_reg_e82x(hw, port, P_REG_PS, &val);
 	if (err)
 		return err;
 
 	val &= ~P_REG_PS_START_M;
-	err = ice_write_phy_reg_e822(hw, port, P_REG_PS, val);
+	err = ice_write_phy_reg_e82x(hw, port, P_REG_PS, val);
 	if (err)
 		return err;
 
 	val &= ~P_REG_PS_ENA_CLK_M;
-	err = ice_write_phy_reg_e822(hw, port, P_REG_PS, val);
+	err = ice_write_phy_reg_e82x(hw, port, P_REG_PS, val);
 	if (err)
 		return err;
 
 	if (soft_reset) {
 		val |= P_REG_PS_SFT_RESET_M;
-		err = ice_write_phy_reg_e822(hw, port, P_REG_PS, val);
+		err = ice_write_phy_reg_e82x(hw, port, P_REG_PS, val);
 		if (err)
 			return err;
 	}
@@ -2502,7 +2502,7 @@ ice_stop_phy_timer_e822(struct ice_hw *hw, u8 port, bool soft_reset)
 }
 
 /**
- * ice_start_phy_timer_e822 - Start the PHY clock timer
+ * ice_start_phy_timer_e82x - Start the PHY clock timer
  * @hw: pointer to the HW struct
  * @port: the PHY port to start
  *
@@ -2512,7 +2512,7 @@ ice_stop_phy_timer_e822(struct ice_hw *hw, u8 port, bool soft_reset)
  *
  * Hardware will take Vernier measurements on Tx or Rx of packets.
  */
-int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port)
+int ice_start_phy_timer_e82x(struct ice_hw *hw, u8 port)
 {
 	u32 lo, hi, val;
 	u64 incval;
@@ -2521,17 +2521,17 @@ int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port)
 
 	tmr_idx = ice_get_ptp_src_clock_index(hw);
 
-	err = ice_stop_phy_timer_e822(hw, port, false);
+	err = ice_stop_phy_timer_e82x(hw, port, false);
 	if (err)
 		return err;
 
-	ice_phy_cfg_lane_e822(hw, port);
+	ice_phy_cfg_lane_e82x(hw, port);
 
-	err = ice_phy_cfg_uix_e822(hw, port);
+	err = ice_phy_cfg_uix_e82x(hw, port);
 	if (err)
 		return err;
 
-	err = ice_phy_cfg_parpcs_e822(hw, port);
+	err = ice_phy_cfg_parpcs_e82x(hw, port);
 	if (err)
 		return err;
 
@@ -2539,7 +2539,7 @@ int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port)
 	hi = rd32(hw, GLTSYN_INCVAL_H(tmr_idx));
 	incval = (u64)hi << 32 | lo;
 
-	err = ice_write_40b_phy_reg_e822(hw, port, P_REG_TIMETUS_L, incval);
+	err = ice_write_40b_phy_reg_e82x(hw, port, P_REG_TIMETUS_L, incval);
 	if (err)
 		return err;
 
@@ -2552,22 +2552,22 @@ int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port)
 
 	ice_ptp_exec_tmr_cmd(hw);
 
-	err = ice_read_phy_reg_e822(hw, port, P_REG_PS, &val);
+	err = ice_read_phy_reg_e82x(hw, port, P_REG_PS, &val);
 	if (err)
 		return err;
 
 	val |= P_REG_PS_SFT_RESET_M;
-	err = ice_write_phy_reg_e822(hw, port, P_REG_PS, val);
+	err = ice_write_phy_reg_e82x(hw, port, P_REG_PS, val);
 	if (err)
 		return err;
 
 	val |= P_REG_PS_START_M;
-	err = ice_write_phy_reg_e822(hw, port, P_REG_PS, val);
+	err = ice_write_phy_reg_e82x(hw, port, P_REG_PS, val);
 	if (err)
 		return err;
 
 	val &= ~P_REG_PS_SFT_RESET_M;
-	err = ice_write_phy_reg_e822(hw, port, P_REG_PS, val);
+	err = ice_write_phy_reg_e82x(hw, port, P_REG_PS, val);
 	if (err)
 		return err;
 
@@ -2578,18 +2578,18 @@ int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port)
 	ice_ptp_exec_tmr_cmd(hw);
 
 	val |= P_REG_PS_ENA_CLK_M;
-	err = ice_write_phy_reg_e822(hw, port, P_REG_PS, val);
+	err = ice_write_phy_reg_e82x(hw, port, P_REG_PS, val);
 	if (err)
 		return err;
 
 	val |= P_REG_PS_LOAD_OFFSET_M;
-	err = ice_write_phy_reg_e822(hw, port, P_REG_PS, val);
+	err = ice_write_phy_reg_e82x(hw, port, P_REG_PS, val);
 	if (err)
 		return err;
 
 	ice_ptp_exec_tmr_cmd(hw);
 
-	err = ice_sync_phy_timer_e822(hw, port);
+	err = ice_sync_phy_timer_e82x(hw, port);
 	if (err)
 		return err;
 
@@ -2599,7 +2599,7 @@ int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port)
 }
 
 /**
- * ice_get_phy_tx_tstamp_ready_e822 - Read Tx memory status register
+ * ice_get_phy_tx_tstamp_ready_e82x - Read Tx memory status register
  * @hw: pointer to the HW struct
  * @quad: the timestamp quad to read from
  * @tstamp_ready: contents of the Tx memory status register
@@ -2609,19 +2609,19 @@ int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port)
  * ready to be captured from the PHY timestamp block.
  */
 static int
-ice_get_phy_tx_tstamp_ready_e822(struct ice_hw *hw, u8 quad, u64 *tstamp_ready)
+ice_get_phy_tx_tstamp_ready_e82x(struct ice_hw *hw, u8 quad, u64 *tstamp_ready)
 {
 	u32 hi, lo;
 	int err;
 
-	err = ice_read_quad_reg_e822(hw, quad, Q_REG_TX_MEMORY_STATUS_U, &hi);
+	err = ice_read_quad_reg_e82x(hw, quad, Q_REG_TX_MEMORY_STATUS_U, &hi);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to read TX_MEMORY_STATUS_U for quad %u, err %d\n",
 			  quad, err);
 		return err;
 	}
 
-	err = ice_read_quad_reg_e822(hw, quad, Q_REG_TX_MEMORY_STATUS_L, &lo);
+	err = ice_read_quad_reg_e82x(hw, quad, Q_REG_TX_MEMORY_STATUS_L, &lo);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to read TX_MEMORY_STATUS_L for quad %u, err %d\n",
 			  quad, err);
@@ -3307,7 +3307,7 @@ void ice_ptp_init_phy_model(struct ice_hw *hw)
 	if (ice_is_e810(hw))
 		hw->phy_model = ICE_PHY_E810;
 	else
-		hw->phy_model = ICE_PHY_E822;
+		hw->phy_model = ICE_PHY_E82X;
 }
 
 /**
@@ -3332,8 +3332,8 @@ static int ice_ptp_tmr_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
 	case ICE_PHY_E810:
 		err = ice_ptp_port_cmd_e810(hw, cmd);
 		break;
-	case ICE_PHY_E822:
-		err = ice_ptp_port_cmd_e822(hw, cmd);
+	case ICE_PHY_E82X:
+		err = ice_ptp_port_cmd_e82x(hw, cmd);
 		break;
 	default:
 		err = -EOPNOTSUPP;
@@ -3384,8 +3384,8 @@ int ice_ptp_init_time(struct ice_hw *hw, u64 time)
 	case ICE_PHY_E810:
 		err = ice_ptp_prep_phy_time_e810(hw, time & 0xFFFFFFFF);
 		break;
-	case ICE_PHY_E822:
-		err = ice_ptp_prep_phy_time_e822(hw, time & 0xFFFFFFFF);
+	case ICE_PHY_E82X:
+		err = ice_ptp_prep_phy_time_e82x(hw, time & 0xFFFFFFFF);
 		break;
 	default:
 		err = -EOPNOTSUPP;
@@ -3426,8 +3426,8 @@ int ice_ptp_write_incval(struct ice_hw *hw, u64 incval)
 	case ICE_PHY_E810:
 		err = ice_ptp_prep_phy_incval_e810(hw, incval);
 		break;
-	case ICE_PHY_E822:
-		err = ice_ptp_prep_phy_incval_e822(hw, incval);
+	case ICE_PHY_E82X:
+		err = ice_ptp_prep_phy_incval_e82x(hw, incval);
 		break;
 	default:
 		err = -EOPNOTSUPP;
@@ -3492,8 +3492,8 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj)
 	case ICE_PHY_E810:
 		err = ice_ptp_prep_phy_adj_e810(hw, adj);
 		break;
-	case ICE_PHY_E822:
-		err = ice_ptp_prep_phy_adj_e822(hw, adj);
+	case ICE_PHY_E82X:
+		err = ice_ptp_prep_phy_adj_e82x(hw, adj);
 		break;
 	default:
 		err = -EOPNOTSUPP;
@@ -3521,8 +3521,8 @@ int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp)
 	switch (hw->phy_model) {
 	case ICE_PHY_E810:
 		return ice_read_phy_tstamp_e810(hw, block, idx, tstamp);
-	case ICE_PHY_E822:
-		return ice_read_phy_tstamp_e822(hw, block, idx, tstamp);
+	case ICE_PHY_E82X:
+		return ice_read_phy_tstamp_e82x(hw, block, idx, tstamp);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -3549,8 +3549,8 @@ int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx)
 	switch (hw->phy_model) {
 	case ICE_PHY_E810:
 		return ice_clear_phy_tstamp_e810(hw, block, idx);
-	case ICE_PHY_E822:
-		return ice_clear_phy_tstamp_e822(hw, block, idx);
+	case ICE_PHY_E82X:
+		return ice_clear_phy_tstamp_e82x(hw, block, idx);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -3608,8 +3608,8 @@ static int ice_get_pf_c827_idx(struct ice_hw *hw, u8 *idx)
 void ice_ptp_reset_ts_memory(struct ice_hw *hw)
 {
 	switch (hw->phy_model) {
-	case ICE_PHY_E822:
-		ice_ptp_reset_ts_memory_e822(hw);
+	case ICE_PHY_E82X:
+		ice_ptp_reset_ts_memory_e82x(hw);
 		break;
 	case ICE_PHY_E810:
 	default:
@@ -3636,8 +3636,8 @@ int ice_ptp_init_phc(struct ice_hw *hw)
 	switch (hw->phy_model) {
 	case ICE_PHY_E810:
 		return ice_ptp_init_phc_e810(hw);
-	case ICE_PHY_E822:
-		return ice_ptp_init_phc_e822(hw);
+	case ICE_PHY_E82X:
+		return ice_ptp_init_phc_e82x(hw);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -3660,8 +3660,8 @@ int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready)
 	case ICE_PHY_E810:
 		return ice_get_phy_tx_tstamp_ready_e810(hw, block,
 							tstamp_ready);
-	case ICE_PHY_E822:
-		return ice_get_phy_tx_tstamp_ready_e822(hw, block,
+	case ICE_PHY_E82X:
+		return ice_get_phy_tx_tstamp_ready_e82x(hw, block,
 							tstamp_ready);
 		break;
 	default:
@@ -3942,7 +3942,7 @@ int ice_get_cgu_rclk_pin_info(struct ice_hw *hw, u8 *base_idx, u8 *pin_num)
 	case ICE_DEV_ID_E823C_QSFP:
 	case ICE_DEV_ID_E823C_SFP:
 	case ICE_DEV_ID_E823C_SGMII:
-		*pin_num = ICE_E822_RCLK_PINS_NUM;
+		*pin_num = ICE_E82X_RCLK_PINS_NUM;
 		ret = 0;
 		if (hw->cgu_part_number ==
 		    ICE_AQC_GET_LINK_TOPO_NODE_NR_ZL30632_80032)
@@ -3961,3 +3961,57 @@ int ice_get_cgu_rclk_pin_info(struct ice_hw *hw, u8 *base_idx, u8 *pin_num)
 
 	return ret;
 }
+
+/**
+ * ice_cgu_get_output_pin_state_caps - get output pin state capabilities
+ * @hw: pointer to the hw struct
+ * @pin_id: id of a pin
+ * @caps: capabilities to modify
+ *
+ * Return:
+ * * 0 - success, state capabilities were modified
+ * * negative - failure, capabilities were not modified
+ */
+int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id,
+				      unsigned long *caps)
+{
+	bool can_change = true;
+
+	switch (hw->device_id) {
+	case ICE_DEV_ID_E810C_SFP:
+		if (pin_id == ZL_OUT2 || pin_id == ZL_OUT3)
+			can_change = false;
+		break;
+	case ICE_DEV_ID_E810C_QSFP:
+		if (pin_id == ZL_OUT2 || pin_id == ZL_OUT3 || pin_id == ZL_OUT4)
+			can_change = false;
+		break;
+	case ICE_DEV_ID_E823L_10G_BASE_T:
+	case ICE_DEV_ID_E823L_1GBE:
+	case ICE_DEV_ID_E823L_BACKPLANE:
+	case ICE_DEV_ID_E823L_QSFP:
+	case ICE_DEV_ID_E823L_SFP:
+	case ICE_DEV_ID_E823C_10G_BASE_T:
+	case ICE_DEV_ID_E823C_BACKPLANE:
+	case ICE_DEV_ID_E823C_QSFP:
+	case ICE_DEV_ID_E823C_SFP:
+	case ICE_DEV_ID_E823C_SGMII:
+		if (hw->cgu_part_number ==
+		    ICE_AQC_GET_LINK_TOPO_NODE_NR_ZL30632_80032 &&
+		    pin_id == ZL_OUT2)
+			can_change = false;
+		else if (hw->cgu_part_number ==
+			 ICE_AQC_GET_LINK_TOPO_NODE_NR_SI5383_5384 &&
+			 pin_id == SI_OUT1)
+			can_change = false;
+		break;
+	default:
+		return -EINVAL;
+	}
+	if (can_change)
+		*caps |= DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE;
+	else
+		*caps &= ~DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE;
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 36aeeef99ec0..1f3e03124430 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -42,7 +42,7 @@ enum ice_ptp_fec_mode {
 };
 
 /**
- * struct ice_time_ref_info_e822
+ * struct ice_time_ref_info_e82x
  * @pll_freq: Frequency of PLL that drives timer ticks in Hz
  * @nominal_incval: increment to generate nanoseconds in GLTSYN_TIME_L
  * @pps_delay: propagation delay of the PPS output signal
@@ -50,14 +50,14 @@ enum ice_ptp_fec_mode {
  * Characteristic information for the various TIME_REF sources possible in the
  * E822 devices
  */
-struct ice_time_ref_info_e822 {
+struct ice_time_ref_info_e82x {
 	u64 pll_freq;
 	u64 nominal_incval;
 	u8 pps_delay;
 };
 
 /**
- * struct ice_vernier_info_e822
+ * struct ice_vernier_info_e82x
  * @tx_par_clk: Frequency used to calculate P_REG_PAR_TX_TUS
  * @rx_par_clk: Frequency used to calculate P_REG_PAR_RX_TUS
  * @tx_pcs_clk: Frequency used to calculate P_REG_PCS_TX_TUS
@@ -80,7 +80,7 @@ struct ice_time_ref_info_e822 {
  * different link speeds, either the deskew marker for multi-lane link speeds
  * or the Reed Solomon gearbox marker for RS-FEC.
  */
-struct ice_vernier_info_e822 {
+struct ice_vernier_info_e82x {
 	u32 tx_par_clk;
 	u32 rx_par_clk;
 	u32 tx_pcs_clk;
@@ -95,7 +95,7 @@ struct ice_vernier_info_e822 {
 };
 
 /**
- * struct ice_cgu_pll_params_e822
+ * struct ice_cgu_pll_params_e82x
  * @refclk_pre_div: Reference clock pre-divisor
  * @feedback_div: Feedback divisor
  * @frac_n_div: Fractional divisor
@@ -104,7 +104,7 @@ struct ice_vernier_info_e822 {
  * Clock Generation Unit parameters used to program the PLL based on the
  * selected TIME_REF frequency.
  */
-struct ice_cgu_pll_params_e822 {
+struct ice_cgu_pll_params_e82x {
 	u32 refclk_pre_div;
 	u32 feedback_div;
 	u32 frac_n_div;
@@ -124,7 +124,7 @@ enum ice_phy_rclk_pins {
 };
 
 #define ICE_E810_RCLK_PINS_NUM		(ICE_RCLKB_PIN + 1)
-#define ICE_E822_RCLK_PINS_NUM		(ICE_RCLKA_PIN + 1)
+#define ICE_E82X_RCLK_PINS_NUM		(ICE_RCLKA_PIN + 1)
 #define E810T_CGU_INPUT_C827(_phy, _pin) ((_phy) * ICE_E810_RCLK_PINS_NUM + \
 					  (_pin) + ZL_REF1P)
 
@@ -183,16 +183,16 @@ struct ice_cgu_pin_desc {
 };
 
 extern const struct
-ice_cgu_pll_params_e822 e822_cgu_params[NUM_ICE_TIME_REF_FREQ];
+ice_cgu_pll_params_e82x e822_cgu_params[NUM_ICE_TIME_REF_FREQ];
 
 #define E810C_QSFP_C827_0_HANDLE 2
 #define E810C_QSFP_C827_1_HANDLE 3
 
 /* Table of constants related to possible TIME_REF sources */
-extern const struct ice_time_ref_info_e822 e822_time_ref[NUM_ICE_TIME_REF_FREQ];
+extern const struct ice_time_ref_info_e82x e822_time_ref[NUM_ICE_TIME_REF_FREQ];
 
 /* Table of constants for Vernier calibration on E822 */
-extern const struct ice_vernier_info_e822 e822_vernier[NUM_ICE_PTP_LNK_SPD];
+extern const struct ice_vernier_info_e82x e822_vernier[NUM_ICE_PTP_LNK_SPD];
 
 /* Increment value to generate nanoseconds in the GLTSYN_TIME_L register for
  * the E810 devices. Based off of a PLL with an 812.5 MHz frequency.
@@ -215,23 +215,23 @@ int ice_ptp_init_phc(struct ice_hw *hw);
 int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready);
 
 /* E822 family functions */
-int ice_read_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 *val);
-int ice_write_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 val);
-void ice_ptp_reset_ts_memory_quad_e822(struct ice_hw *hw, u8 quad);
+int ice_read_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 *val);
+int ice_write_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 val);
+void ice_ptp_reset_ts_memory_quad_e82x(struct ice_hw *hw, u8 quad);
 
 /**
- * ice_e822_time_ref - Get the current TIME_REF from capabilities
+ * ice_e82x_time_ref - Get the current TIME_REF from capabilities
  * @hw: pointer to the HW structure
  *
  * Returns the current TIME_REF from the capabilities structure.
  */
-static inline enum ice_time_ref_freq ice_e822_time_ref(struct ice_hw *hw)
+static inline enum ice_time_ref_freq ice_e82x_time_ref(struct ice_hw *hw)
 {
 	return hw->func_caps.ts_func_info.time_ref;
 }
 
 /**
- * ice_set_e822_time_ref - Set new TIME_REF
+ * ice_set_e82x_time_ref - Set new TIME_REF
  * @hw: pointer to the HW structure
  * @time_ref: new TIME_REF to set
  *
@@ -239,31 +239,31 @@ static inline enum ice_time_ref_freq ice_e822_time_ref(struct ice_hw *hw)
  * change, such as an update to the CGU registers.
  */
 static inline void
-ice_set_e822_time_ref(struct ice_hw *hw, enum ice_time_ref_freq time_ref)
+ice_set_e82x_time_ref(struct ice_hw *hw, enum ice_time_ref_freq time_ref)
 {
 	hw->func_caps.ts_func_info.time_ref = time_ref;
 }
 
-static inline u64 ice_e822_pll_freq(enum ice_time_ref_freq time_ref)
+static inline u64 ice_e82x_pll_freq(enum ice_time_ref_freq time_ref)
 {
 	return e822_time_ref[time_ref].pll_freq;
 }
 
-static inline u64 ice_e822_nominal_incval(enum ice_time_ref_freq time_ref)
+static inline u64 ice_e82x_nominal_incval(enum ice_time_ref_freq time_ref)
 {
 	return e822_time_ref[time_ref].nominal_incval;
 }
 
-static inline u64 ice_e822_pps_delay(enum ice_time_ref_freq time_ref)
+static inline u64 ice_e82x_pps_delay(enum ice_time_ref_freq time_ref)
 {
 	return e822_time_ref[time_ref].pps_delay;
 }
 
 /* E822 Vernier calibration functions */
-int ice_stop_phy_timer_e822(struct ice_hw *hw, u8 port, bool soft_reset);
-int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port);
-int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port);
-int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port);
+int ice_stop_phy_timer_e82x(struct ice_hw *hw, u8 port, bool soft_reset);
+int ice_start_phy_timer_e82x(struct ice_hw *hw, u8 port);
+int ice_phy_cfg_tx_offset_e82x(struct ice_hw *hw, u8 port);
+int ice_phy_cfg_rx_offset_e82x(struct ice_hw *hw, u8 port);
 
 /* E810 family functions */
 int ice_ptp_init_phy_e810(struct ice_hw *hw);
@@ -282,6 +282,8 @@ int ice_get_cgu_state(struct ice_hw *hw, u8 dpll_idx,
 int ice_get_cgu_rclk_pin_info(struct ice_hw *hw, u8 *base_idx, u8 *pin_num);
 
 void ice_ptp_init_phy_model(struct ice_hw *hw);
+int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id,
+				      unsigned long *caps);
 
 #define PFTSYN_SEM_BYTES	4
 
@@ -507,6 +509,7 @@ void ice_ptp_init_phy_model(struct ice_hw *hw);
 #define TS_LL_READ_RETRIES		200
 #define TS_LL_READ_TS_HIGH		GENMASK(23, 16)
 #define TS_LL_READ_TS_IDX		GENMASK(29, 24)
+#define TS_LL_READ_TS_INTR		BIT(30)
 #define TS_LL_READ_TS			BIT(31)
 
 /* Internal PHY timestamp address */
diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c
index c686ac0935eb..5f30fb131f74 100644
--- a/drivers/net/ethernet/intel/ice/ice_repr.c
+++ b/drivers/net/ethernet/intel/ice/ice_repr.c
@@ -14,7 +14,7 @@
  */
 static int ice_repr_get_sw_port_id(struct ice_repr *repr)
 {
-	return repr->vf->pf->hw.port_info->lport;
+	return repr->src_vsi->back->hw.port_info->lport;
 }
 
 /**
@@ -35,7 +35,7 @@ ice_repr_get_phys_port_name(struct net_device *netdev, char *buf, size_t len)
 		return -EOPNOTSUPP;
 
 	res = snprintf(buf, len, "pf%dvfr%d", ice_repr_get_sw_port_id(repr),
-		       repr->vf->vf_id);
+		       repr->id);
 	if (res <= 0)
 		return -EOPNOTSUPP;
 	return 0;
@@ -278,25 +278,67 @@ ice_repr_reg_netdev(struct net_device *netdev)
 	return register_netdev(netdev);
 }
 
+static void ice_repr_remove_node(struct devlink_port *devlink_port)
+{
+	devl_lock(devlink_port->devlink);
+	devl_rate_leaf_destroy(devlink_port);
+	devl_unlock(devlink_port->devlink);
+}
+
 /**
- * ice_repr_add - add representor for VF
- * @vf: pointer to VF structure
+ * ice_repr_rem - remove representor from VF
+ * @repr: pointer to representor structure
  */
-static int ice_repr_add(struct ice_vf *vf)
+static void ice_repr_rem(struct ice_repr *repr)
+{
+	kfree(repr->q_vector);
+	free_netdev(repr->netdev);
+	kfree(repr);
+}
+
+/**
+ * ice_repr_rem_vf - remove representor from VF
+ * @repr: pointer to representor structure
+ */
+void ice_repr_rem_vf(struct ice_repr *repr)
+{
+	ice_repr_remove_node(&repr->vf->devlink_port);
+	unregister_netdev(repr->netdev);
+	ice_devlink_destroy_vf_port(repr->vf);
+	ice_virtchnl_set_dflt_ops(repr->vf);
+	ice_repr_rem(repr);
+}
+
+static void ice_repr_set_tx_topology(struct ice_pf *pf)
+{
+	struct devlink *devlink;
+
+	/* only export if ADQ and DCB disabled and eswitch enabled*/
+	if (ice_is_adq_active(pf) || ice_is_dcb_active(pf) ||
+	    !ice_is_switchdev_running(pf))
+		return;
+
+	devlink = priv_to_devlink(pf);
+	ice_devlink_rate_init_tx_topology(devlink, ice_get_main_vsi(pf));
+}
+
+/**
+ * ice_repr_add - add representor for generic VSI
+ * @pf: pointer to PF structure
+ * @src_vsi: pointer to VSI structure of device to represent
+ * @parent_mac: device MAC address
+ */
+static struct ice_repr *
+ice_repr_add(struct ice_pf *pf, struct ice_vsi *src_vsi, const u8 *parent_mac)
 {
 	struct ice_q_vector *q_vector;
 	struct ice_netdev_priv *np;
 	struct ice_repr *repr;
-	struct ice_vsi *vsi;
 	int err;
 
-	vsi = ice_get_vf_vsi(vf);
-	if (!vsi)
-		return -EINVAL;
-
 	repr = kzalloc(sizeof(*repr), GFP_KERNEL);
 	if (!repr)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	repr->netdev = alloc_etherdev(sizeof(struct ice_netdev_priv));
 	if (!repr->netdev) {
@@ -304,9 +346,7 @@ static int ice_repr_add(struct ice_vf *vf)
 		goto err_alloc;
 	}
 
-	repr->src_vsi = vsi;
-	repr->vf = vf;
-	vf->repr = repr;
+	repr->src_vsi = src_vsi;
 	np = netdev_priv(repr->netdev);
 	np->repr = repr;
 
@@ -316,10 +356,40 @@ static int ice_repr_add(struct ice_vf *vf)
 		goto err_alloc_q_vector;
 	}
 	repr->q_vector = q_vector;
+	repr->q_id = repr->id;
+
+	ether_addr_copy(repr->parent_mac, parent_mac);
+
+	return repr;
+
+err_alloc_q_vector:
+	free_netdev(repr->netdev);
+err_alloc:
+	kfree(repr);
+	return ERR_PTR(err);
+}
+
+struct ice_repr *ice_repr_add_vf(struct ice_vf *vf)
+{
+	struct ice_repr *repr;
+	struct ice_vsi *vsi;
+	int err;
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi)
+		return ERR_PTR(-ENOENT);
 
 	err = ice_devlink_create_vf_port(vf);
 	if (err)
-		goto err_devlink;
+		return ERR_PTR(err);
+
+	repr = ice_repr_add(vf->pf, vsi, vf->hw_lan_addr);
+	if (IS_ERR(repr)) {
+		err = PTR_ERR(repr);
+		goto err_repr_add;
+	}
+
+	repr->vf = vf;
 
 	repr->netdev->min_mtu = ETH_MIN_MTU;
 	repr->netdev->max_mtu = ICE_MAX_MTU;
@@ -331,100 +401,23 @@ static int ice_repr_add(struct ice_vf *vf)
 		goto err_netdev;
 
 	ice_virtchnl_set_repr_ops(vf);
+	ice_repr_set_tx_topology(vf->pf);
 
-	return 0;
+	return repr;
 
 err_netdev:
+	ice_repr_rem(repr);
+err_repr_add:
 	ice_devlink_destroy_vf_port(vf);
-err_devlink:
-	kfree(repr->q_vector);
-	vf->repr->q_vector = NULL;
-err_alloc_q_vector:
-	free_netdev(repr->netdev);
-	repr->netdev = NULL;
-err_alloc:
-	kfree(repr);
-	vf->repr = NULL;
-	return err;
-}
-
-/**
- * ice_repr_rem - remove representor from VF
- * @vf: pointer to VF structure
- */
-static void ice_repr_rem(struct ice_vf *vf)
-{
-	if (!vf->repr)
-		return;
-
-	kfree(vf->repr->q_vector);
-	vf->repr->q_vector = NULL;
-	unregister_netdev(vf->repr->netdev);
-	ice_devlink_destroy_vf_port(vf);
-	free_netdev(vf->repr->netdev);
-	vf->repr->netdev = NULL;
-	kfree(vf->repr);
-	vf->repr = NULL;
-
-	ice_virtchnl_set_dflt_ops(vf);
-}
-
-/**
- * ice_repr_rem_from_all_vfs - remove port representor for all VFs
- * @pf: pointer to PF structure
- */
-void ice_repr_rem_from_all_vfs(struct ice_pf *pf)
-{
-	struct devlink *devlink;
-	struct ice_vf *vf;
-	unsigned int bkt;
-
-	lockdep_assert_held(&pf->vfs.table_lock);
-
-	ice_for_each_vf(pf, bkt, vf)
-		ice_repr_rem(vf);
-
-	/* since all port representors are destroyed, there is
-	 * no point in keeping the nodes
-	 */
-	devlink = priv_to_devlink(pf);
-	devl_lock(devlink);
-	devl_rate_nodes_destroy(devlink);
-	devl_unlock(devlink);
+	return ERR_PTR(err);
 }
 
-/**
- * ice_repr_add_for_all_vfs - add port representor for all VFs
- * @pf: pointer to PF structure
- */
-int ice_repr_add_for_all_vfs(struct ice_pf *pf)
+struct ice_repr *ice_repr_get_by_vsi(struct ice_vsi *vsi)
 {
-	struct devlink *devlink;
-	struct ice_vf *vf;
-	unsigned int bkt;
-	int err;
-
-	lockdep_assert_held(&pf->vfs.table_lock);
-
-	ice_for_each_vf(pf, bkt, vf) {
-		err = ice_repr_add(vf);
-		if (err)
-			goto err;
-	}
-
-	/* only export if ADQ and DCB disabled */
-	if (ice_is_adq_active(pf) || ice_is_dcb_active(pf))
-		return 0;
-
-	devlink = priv_to_devlink(pf);
-	ice_devlink_rate_init_tx_topology(devlink, ice_get_main_vsi(pf));
-
-	return 0;
-
-err:
-	ice_repr_rem_from_all_vfs(pf);
+	if (!vsi->vf)
+		return NULL;
 
-	return err;
+	return xa_load(&vsi->back->eswitch.reprs, vsi->vf->repr_id);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_repr.h b/drivers/net/ethernet/intel/ice/ice_repr.h
index e1ee2d2c1d2d..f9aede315716 100644
--- a/drivers/net/ethernet/intel/ice/ice_repr.h
+++ b/drivers/net/ethernet/intel/ice/ice_repr.h
@@ -13,14 +13,17 @@ struct ice_repr {
 	struct net_device *netdev;
 	struct metadata_dst *dst;
 	struct ice_esw_br_port *br_port;
+	int q_id;
+	u32 id;
+	u8 parent_mac[ETH_ALEN];
 #ifdef CONFIG_ICE_SWITCHDEV
 	/* info about slow path rule */
 	struct ice_rule_query_data sp_rule;
 #endif
 };
 
-int ice_repr_add_for_all_vfs(struct ice_pf *pf);
-void ice_repr_rem_from_all_vfs(struct ice_pf *pf);
+struct ice_repr *ice_repr_add_vf(struct ice_vf *vf);
+void ice_repr_rem_vf(struct ice_repr *repr);
 
 void ice_repr_start_tx_queues(struct ice_repr *repr);
 void ice_repr_stop_tx_queues(struct ice_repr *repr);
@@ -29,4 +32,6 @@ void ice_repr_set_traffic_vsi(struct ice_repr *repr, struct ice_vsi *vsi);
 
 struct ice_repr *ice_netdev_to_repr(struct net_device *netdev);
 bool ice_is_port_repr_netdev(const struct net_device *netdev);
+
+struct ice_repr *ice_repr_get_by_vsi(struct ice_vsi *vsi);
 #endif
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index 2f4a621254e8..d174a4eeb899 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -1387,8 +1387,7 @@ void ice_sched_get_psm_clk_freq(struct ice_hw *hw)
 	u32 val, clk_src;
 
 	val = rd32(hw, GLGEN_CLKSTAT_SRC);
-	clk_src = (val & GLGEN_CLKSTAT_SRC_PSM_CLK_SRC_M) >>
-		GLGEN_CLKSTAT_SRC_PSM_CLK_SRC_S;
+	clk_src = FIELD_GET(GLGEN_CLKSTAT_SRC_PSM_CLK_SRC_M, val);
 
 #define PSM_CLK_SRC_367_MHZ 0x0
 #define PSM_CLK_SRC_416_MHZ 0x1
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index 2a5e6616cc0a..a94a1c48c3de 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -106,10 +106,8 @@ static void ice_dis_vf_mappings(struct ice_vf *vf)
 	for (v = first; v <= last; v++) {
 		u32 reg;
 
-		reg = (((1 << GLINT_VECT2FUNC_IS_PF_S) &
-			GLINT_VECT2FUNC_IS_PF_M) |
-		       ((hw->pf_id << GLINT_VECT2FUNC_PF_NUM_S) &
-			GLINT_VECT2FUNC_PF_NUM_M));
+		reg = FIELD_PREP(GLINT_VECT2FUNC_IS_PF_M, 1) |
+		      FIELD_PREP(GLINT_VECT2FUNC_PF_NUM_M, hw->pf_id);
 		wr32(hw, GLINT_VECT2FUNC(v), reg);
 	}
 
@@ -172,13 +170,14 @@ void ice_free_vfs(struct ice_pf *pf)
 	else
 		dev_warn(dev, "VFs are assigned - not disabling SR-IOV\n");
 
-	mutex_lock(&vfs->table_lock);
+	ice_eswitch_reserve_cp_queues(pf, -ice_get_num_vfs(pf));
 
-	ice_eswitch_release(pf);
+	mutex_lock(&vfs->table_lock);
 
 	ice_for_each_vf(pf, bkt, vf) {
 		mutex_lock(&vf->cfg_lock);
 
+		ice_eswitch_detach(pf, vf);
 		ice_dis_vf_qs(vf);
 
 		if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) {
@@ -274,24 +273,20 @@ static void ice_ena_vf_msix_mappings(struct ice_vf *vf)
 		(device_based_first_msix + vf->num_msix) - 1;
 	device_based_vf_id = vf->vf_id + hw->func_caps.vf_base_id;
 
-	reg = (((device_based_first_msix << VPINT_ALLOC_FIRST_S) &
-		VPINT_ALLOC_FIRST_M) |
-	       ((device_based_last_msix << VPINT_ALLOC_LAST_S) &
-		VPINT_ALLOC_LAST_M) | VPINT_ALLOC_VALID_M);
+	reg = FIELD_PREP(VPINT_ALLOC_FIRST_M, device_based_first_msix) |
+	      FIELD_PREP(VPINT_ALLOC_LAST_M, device_based_last_msix) |
+	      VPINT_ALLOC_VALID_M;
 	wr32(hw, VPINT_ALLOC(vf->vf_id), reg);
 
-	reg = (((device_based_first_msix << VPINT_ALLOC_PCI_FIRST_S)
-		 & VPINT_ALLOC_PCI_FIRST_M) |
-	       ((device_based_last_msix << VPINT_ALLOC_PCI_LAST_S) &
-		VPINT_ALLOC_PCI_LAST_M) | VPINT_ALLOC_PCI_VALID_M);
+	reg = FIELD_PREP(VPINT_ALLOC_PCI_FIRST_M, device_based_first_msix) |
+	      FIELD_PREP(VPINT_ALLOC_PCI_LAST_M, device_based_last_msix) |
+	      VPINT_ALLOC_PCI_VALID_M;
 	wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), reg);
 
 	/* map the interrupts to its functions */
 	for (v = pf_based_first_msix; v <= pf_based_last_msix; v++) {
-		reg = (((device_based_vf_id << GLINT_VECT2FUNC_VF_NUM_S) &
-			GLINT_VECT2FUNC_VF_NUM_M) |
-		       ((hw->pf_id << GLINT_VECT2FUNC_PF_NUM_S) &
-			GLINT_VECT2FUNC_PF_NUM_M));
+		reg = FIELD_PREP(GLINT_VECT2FUNC_VF_NUM_M, device_based_vf_id) |
+		      FIELD_PREP(GLINT_VECT2FUNC_PF_NUM_M, hw->pf_id);
 		wr32(hw, GLINT_VECT2FUNC(v), reg);
 	}
 
@@ -324,10 +319,8 @@ static void ice_ena_vf_q_mappings(struct ice_vf *vf, u16 max_txq, u16 max_rxq)
 		 * VFNUMQ value should be set to (number of queues - 1). A value
 		 * of 0 means 1 queue and a value of 255 means 256 queues
 		 */
-		reg = (((vsi->txq_map[0] << VPLAN_TX_QBASE_VFFIRSTQ_S) &
-			VPLAN_TX_QBASE_VFFIRSTQ_M) |
-		       (((max_txq - 1) << VPLAN_TX_QBASE_VFNUMQ_S) &
-			VPLAN_TX_QBASE_VFNUMQ_M));
+		reg = FIELD_PREP(VPLAN_TX_QBASE_VFFIRSTQ_M, vsi->txq_map[0]) |
+		      FIELD_PREP(VPLAN_TX_QBASE_VFNUMQ_M, max_txq - 1);
 		wr32(hw, VPLAN_TX_QBASE(vf->vf_id), reg);
 	} else {
 		dev_err(dev, "Scattered mode for VF Tx queues is not yet implemented\n");
@@ -342,10 +335,8 @@ static void ice_ena_vf_q_mappings(struct ice_vf *vf, u16 max_txq, u16 max_rxq)
 		 * VFNUMQ value should be set to (number of queues - 1). A value
 		 * of 0 means 1 queue and a value of 255 means 256 queues
 		 */
-		reg = (((vsi->rxq_map[0] << VPLAN_RX_QBASE_VFFIRSTQ_S) &
-			VPLAN_RX_QBASE_VFFIRSTQ_M) |
-		       (((max_rxq - 1) << VPLAN_RX_QBASE_VFNUMQ_S) &
-			VPLAN_RX_QBASE_VFNUMQ_M));
+		reg = FIELD_PREP(VPLAN_RX_QBASE_VFFIRSTQ_M, vsi->rxq_map[0]) |
+		      FIELD_PREP(VPLAN_RX_QBASE_VFNUMQ_M, max_rxq - 1);
 		wr32(hw, VPLAN_RX_QBASE(vf->vf_id), reg);
 	} else {
 		dev_err(dev, "Scattered mode for VF Rx queues is not yet implemented\n");
@@ -374,16 +365,11 @@ static void ice_ena_vf_mappings(struct ice_vf *vf)
  */
 int ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector)
 {
-	struct ice_pf *pf;
-
 	if (!vf || !q_vector)
 		return -EINVAL;
 
-	pf = vf->pf;
-
 	/* always add one to account for the OICR being the first MSIX */
-	return pf->sriov_base_vector + pf->vfs.num_msix_per * vf->vf_id +
-		q_vector->v_idx + 1;
+	return vf->first_vector_idx + q_vector->v_idx + 1;
 }
 
 /**
@@ -614,6 +600,14 @@ static int ice_start_vfs(struct ice_pf *pf)
 			goto teardown;
 		}
 
+		retval = ice_eswitch_attach(pf, vf);
+		if (retval) {
+			dev_err(ice_pf_to_dev(pf), "Failed to attach VF %d to eswitch, error %d",
+				vf->vf_id, retval);
+			ice_vf_vsi_release(vf);
+			goto teardown;
+		}
+
 		set_bit(ICE_VF_STATE_INIT, vf->vf_states);
 		ice_ena_vf_mappings(vf);
 		wr32(hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_VFACTIVE);
@@ -768,24 +762,6 @@ static void ice_sriov_clear_reset_trigger(struct ice_vf *vf)
 }
 
 /**
- * ice_sriov_create_vsi - Create a new VSI for a VF
- * @vf: VF to create the VSI for
- *
- * This is called by ice_vf_recreate_vsi to create the new VSI after the old
- * VSI has been released.
- */
-static int ice_sriov_create_vsi(struct ice_vf *vf)
-{
-	struct ice_vsi *vsi;
-
-	vsi = ice_vf_vsi_setup(vf);
-	if (!vsi)
-		return -ENOMEM;
-
-	return 0;
-}
-
-/**
  * ice_sriov_post_vsi_rebuild - tasks to do after the VF's VSI have been rebuilt
  * @vf: VF to perform tasks on
  */
@@ -804,7 +780,6 @@ static const struct ice_vf_ops ice_sriov_vf_ops = {
 	.poll_reset_status = ice_sriov_poll_reset_status,
 	.clear_reset_trigger = ice_sriov_clear_reset_trigger,
 	.irq_close = NULL,
-	.create_vsi = ice_sriov_create_vsi,
 	.post_vsi_rebuild = ice_sriov_post_vsi_rebuild,
 };
 
@@ -923,6 +898,7 @@ static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs)
 		goto err_unroll_sriov;
 	}
 
+	ice_eswitch_reserve_cp_queues(pf, num_vfs);
 	ret = ice_start_vfs(pf);
 	if (ret) {
 		dev_err(dev, "Failed to start %d VFs, err %d\n", num_vfs, ret);
@@ -932,12 +908,6 @@ static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs)
 
 	clear_bit(ICE_VF_DIS, pf->state);
 
-	ret = ice_eswitch_configure(pf);
-	if (ret) {
-		dev_err(dev, "Failed to configure eswitch, err %d\n", ret);
-		goto err_unroll_sriov;
-	}
-
 	/* rearm global interrupts */
 	if (test_and_clear_bit(ICE_OICR_INTR_DIS, pf->state))
 		ice_irq_dynamic_ena(hw, NULL, NULL);
@@ -1152,8 +1122,7 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count)
 	if (vf->first_vector_idx < 0)
 		goto unroll;
 
-	ice_vf_vsi_release(vf);
-	if (vf->vf_ops->create_vsi(vf)) {
+	if (ice_vf_reconfig_vsi(vf)) {
 		/* Try to rebuild with previous values */
 		needs_rebuild = true;
 		goto unroll;
@@ -1180,7 +1149,7 @@ unroll:
 		return -EINVAL;
 
 	if (needs_rebuild)
-		vf->vf_ops->create_vsi(vf);
+		ice_vf_reconfig_vsi(vf);
 
 	ice_ena_vf_mappings(vf);
 	ice_put_vf(vf);
@@ -1329,8 +1298,7 @@ ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event)
 	dev_dbg(ice_pf_to_dev(pf), "GLDCB_RTCTQ: 0x%08x\n", gldcb_rtctq);
 
 	/* event returns device global Rx queue number */
-	queue = (gldcb_rtctq & GLDCB_RTCTQ_RXQNUM_M) >>
-		GLDCB_RTCTQ_RXQNUM_S;
+	queue = FIELD_GET(GLDCB_RTCTQ_RXQNUM_M, gldcb_rtctq);
 
 	vf = ice_get_vf_from_pfq(pf, ice_globalq_to_pfq(pf, queue));
 	if (!vf)
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index ee19f3aa3d19..f84bab80ca42 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -2492,25 +2492,24 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info,
 
 	switch (f_info->fltr_act) {
 	case ICE_FWD_TO_VSI:
-		act |= (f_info->fwd_id.hw_vsi_id << ICE_SINGLE_ACT_VSI_ID_S) &
-			ICE_SINGLE_ACT_VSI_ID_M;
+		act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M,
+				  f_info->fwd_id.hw_vsi_id);
 		if (f_info->lkup_type != ICE_SW_LKUP_VLAN)
 			act |= ICE_SINGLE_ACT_VSI_FORWARDING |
 				ICE_SINGLE_ACT_VALID_BIT;
 		break;
 	case ICE_FWD_TO_VSI_LIST:
 		act |= ICE_SINGLE_ACT_VSI_LIST;
-		act |= (f_info->fwd_id.vsi_list_id <<
-			ICE_SINGLE_ACT_VSI_LIST_ID_S) &
-			ICE_SINGLE_ACT_VSI_LIST_ID_M;
+		act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_LIST_ID_M,
+				  f_info->fwd_id.vsi_list_id);
 		if (f_info->lkup_type != ICE_SW_LKUP_VLAN)
 			act |= ICE_SINGLE_ACT_VSI_FORWARDING |
 				ICE_SINGLE_ACT_VALID_BIT;
 		break;
 	case ICE_FWD_TO_Q:
 		act |= ICE_SINGLE_ACT_TO_Q;
-		act |= (f_info->fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) &
-			ICE_SINGLE_ACT_Q_INDEX_M;
+		act |= FIELD_PREP(ICE_SINGLE_ACT_Q_INDEX_M,
+				  f_info->fwd_id.q_id);
 		break;
 	case ICE_DROP_PACKET:
 		act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_DROP |
@@ -2520,10 +2519,9 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info,
 		q_rgn = f_info->qgrp_size > 0 ?
 			(u8)ilog2(f_info->qgrp_size) : 0;
 		act |= ICE_SINGLE_ACT_TO_Q;
-		act |= (f_info->fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) &
-			ICE_SINGLE_ACT_Q_INDEX_M;
-		act |= (q_rgn << ICE_SINGLE_ACT_Q_REGION_S) &
-			ICE_SINGLE_ACT_Q_REGION_M;
+		act |= FIELD_PREP(ICE_SINGLE_ACT_Q_INDEX_M,
+				  f_info->fwd_id.q_id);
+		act |= FIELD_PREP(ICE_SINGLE_ACT_Q_REGION_M, q_rgn);
 		break;
 	default:
 		return;
@@ -2649,7 +2647,7 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent,
 		m_ent->fltr_info.fwd_id.hw_vsi_id;
 
 	act = ICE_LG_ACT_VSI_FORWARDING | ICE_LG_ACT_VALID_BIT;
-	act |= (id << ICE_LG_ACT_VSI_LIST_ID_S) & ICE_LG_ACT_VSI_LIST_ID_M;
+	act |= FIELD_PREP(ICE_LG_ACT_VSI_LIST_ID_M, id);
 	if (m_ent->vsi_count > 1)
 		act |= ICE_LG_ACT_VSI_LIST;
 	lg_act->act[0] = cpu_to_le32(act);
@@ -2657,16 +2655,15 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent,
 	/* Second action descriptor type */
 	act = ICE_LG_ACT_GENERIC;
 
-	act |= (1 << ICE_LG_ACT_GENERIC_VALUE_S) & ICE_LG_ACT_GENERIC_VALUE_M;
+	act |= FIELD_PREP(ICE_LG_ACT_GENERIC_VALUE_M, 1);
 	lg_act->act[1] = cpu_to_le32(act);
 
-	act = (ICE_LG_ACT_GENERIC_OFF_RX_DESC_PROF_IDX <<
-	       ICE_LG_ACT_GENERIC_OFFSET_S) & ICE_LG_ACT_GENERIC_OFFSET_M;
+	act = FIELD_PREP(ICE_LG_ACT_GENERIC_OFFSET_M,
+			 ICE_LG_ACT_GENERIC_OFF_RX_DESC_PROF_IDX);
 
 	/* Third action Marker value */
 	act |= ICE_LG_ACT_GENERIC;
-	act |= (sw_marker << ICE_LG_ACT_GENERIC_VALUE_S) &
-		ICE_LG_ACT_GENERIC_VALUE_M;
+	act |= FIELD_PREP(ICE_LG_ACT_GENERIC_VALUE_M, sw_marker);
 
 	lg_act->act[2] = cpu_to_le32(act);
 
@@ -2675,9 +2672,9 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent,
 			 ice_aqc_opc_update_sw_rules);
 
 	/* Update the action to point to the large action ID */
-	rx_tx->act = cpu_to_le32(ICE_SINGLE_ACT_PTR |
-				 ((l_id << ICE_SINGLE_ACT_PTR_VAL_S) &
-				  ICE_SINGLE_ACT_PTR_VAL_M));
+	act = ICE_SINGLE_ACT_PTR;
+	act |= FIELD_PREP(ICE_SINGLE_ACT_PTR_VAL_M, l_id);
+	rx_tx->act = cpu_to_le32(act);
 
 	/* Use the filter rule ID of the previously created rule with single
 	 * act. Once the update happens, hardware will treat this as large
@@ -4426,8 +4423,8 @@ ice_alloc_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items,
 	int status;
 
 	buf->num_elems = cpu_to_le16(num_items);
-	buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) &
-				      ICE_AQC_RES_TYPE_M) | alloc_shared);
+	buf->res_type = cpu_to_le16(FIELD_PREP(ICE_AQC_RES_TYPE_M, type) |
+				    alloc_shared);
 
 	status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_alloc_res);
 	if (status)
@@ -4454,8 +4451,8 @@ ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items,
 	int status;
 
 	buf->num_elems = cpu_to_le16(num_items);
-	buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) &
-				      ICE_AQC_RES_TYPE_M) | alloc_shared);
+	buf->res_type = cpu_to_le16(FIELD_PREP(ICE_AQC_RES_TYPE_M, type) |
+				    alloc_shared);
 	buf->elem[0].e.sw_resp = cpu_to_le16(counter_id);
 
 	status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_free_res);
@@ -4481,18 +4478,15 @@ int ice_share_res(struct ice_hw *hw, u16 type, u8 shared, u16 res_id)
 {
 	DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, buf, elem, 1);
 	u16 buf_len = __struct_size(buf);
+	u16 res_type;
 	int status;
 
 	buf->num_elems = cpu_to_le16(1);
+	res_type = FIELD_PREP(ICE_AQC_RES_TYPE_M, type);
 	if (shared)
-		buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) &
-					     ICE_AQC_RES_TYPE_M) |
-					    ICE_AQC_RES_TYPE_FLAG_SHARED);
-	else
-		buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) &
-					     ICE_AQC_RES_TYPE_M) &
-					    ~ICE_AQC_RES_TYPE_FLAG_SHARED);
+		res_type |= ICE_AQC_RES_TYPE_FLAG_SHARED;
 
+	buf->res_type = cpu_to_le16(res_type);
 	buf->elem[0].e.sw_resp = cpu_to_le16(res_id);
 	status = ice_aq_alloc_free_res(hw, buf, buf_len,
 				       ice_aqc_opc_share_res);
@@ -5024,8 +5018,8 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm,
 			entry->chain_idx = chain_idx;
 			content->result_indx =
 				ICE_AQ_RECIPE_RESULT_EN |
-				((chain_idx << ICE_AQ_RECIPE_RESULT_DATA_S) &
-				 ICE_AQ_RECIPE_RESULT_DATA_M);
+				FIELD_PREP(ICE_AQ_RECIPE_RESULT_DATA_M,
+					   chain_idx);
 			clear_bit(chain_idx, result_idx_bm);
 			chain_idx = find_first_bit(result_idx_bm,
 						   ICE_MAX_FV_WORDS);
@@ -6065,6 +6059,7 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups,
 	      rinfo->sw_act.fltr_act == ICE_FWD_TO_Q ||
 	      rinfo->sw_act.fltr_act == ICE_FWD_TO_QGRP ||
 	      rinfo->sw_act.fltr_act == ICE_DROP_PACKET ||
+	      rinfo->sw_act.fltr_act == ICE_MIRROR_PACKET ||
 	      rinfo->sw_act.fltr_act == ICE_NOP)) {
 		status = -EIO;
 		goto free_pkt_profile;
@@ -6077,9 +6072,11 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups,
 	}
 
 	if (rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI ||
-	    rinfo->sw_act.fltr_act == ICE_NOP)
+	    rinfo->sw_act.fltr_act == ICE_MIRROR_PACKET ||
+	    rinfo->sw_act.fltr_act == ICE_NOP) {
 		rinfo->sw_act.fwd_id.hw_vsi_id =
 			ice_get_hw_vsi_num(hw, vsi_handle);
+	}
 
 	if (rinfo->src_vsi)
 		rinfo->sw_act.src = ice_get_hw_vsi_num(hw, rinfo->src_vsi);
@@ -6115,38 +6112,45 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups,
 		status = -ENOMEM;
 		goto free_pkt_profile;
 	}
-	if (!rinfo->flags_info.act_valid) {
-		act |= ICE_SINGLE_ACT_LAN_ENABLE;
-		act |= ICE_SINGLE_ACT_LB_ENABLE;
-	} else {
-		act |= rinfo->flags_info.act & (ICE_SINGLE_ACT_LAN_ENABLE |
-						ICE_SINGLE_ACT_LB_ENABLE);
+
+	if (rinfo->sw_act.fltr_act != ICE_MIRROR_PACKET) {
+		if (!rinfo->flags_info.act_valid) {
+			act |= ICE_SINGLE_ACT_LAN_ENABLE;
+			act |= ICE_SINGLE_ACT_LB_ENABLE;
+		} else {
+			act |= rinfo->flags_info.act & (ICE_SINGLE_ACT_LAN_ENABLE |
+							ICE_SINGLE_ACT_LB_ENABLE);
+		}
 	}
 
 	switch (rinfo->sw_act.fltr_act) {
 	case ICE_FWD_TO_VSI:
-		act |= (rinfo->sw_act.fwd_id.hw_vsi_id <<
-			ICE_SINGLE_ACT_VSI_ID_S) & ICE_SINGLE_ACT_VSI_ID_M;
+		act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M,
+				  rinfo->sw_act.fwd_id.hw_vsi_id);
 		act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_VALID_BIT;
 		break;
 	case ICE_FWD_TO_Q:
 		act |= ICE_SINGLE_ACT_TO_Q;
-		act |= (rinfo->sw_act.fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) &
-		       ICE_SINGLE_ACT_Q_INDEX_M;
+		act |= FIELD_PREP(ICE_SINGLE_ACT_Q_INDEX_M,
+				  rinfo->sw_act.fwd_id.q_id);
 		break;
 	case ICE_FWD_TO_QGRP:
 		q_rgn = rinfo->sw_act.qgrp_size > 0 ?
 			(u8)ilog2(rinfo->sw_act.qgrp_size) : 0;
 		act |= ICE_SINGLE_ACT_TO_Q;
-		act |= (rinfo->sw_act.fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) &
-		       ICE_SINGLE_ACT_Q_INDEX_M;
-		act |= (q_rgn << ICE_SINGLE_ACT_Q_REGION_S) &
-		       ICE_SINGLE_ACT_Q_REGION_M;
+		act |= FIELD_PREP(ICE_SINGLE_ACT_Q_INDEX_M,
+				  rinfo->sw_act.fwd_id.q_id);
+		act |= FIELD_PREP(ICE_SINGLE_ACT_Q_REGION_M, q_rgn);
 		break;
 	case ICE_DROP_PACKET:
 		act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_DROP |
 		       ICE_SINGLE_ACT_VALID_BIT;
 		break;
+	case ICE_MIRROR_PACKET:
+		act |= ICE_SINGLE_ACT_OTHER_ACTS;
+		act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M,
+				  rinfo->sw_act.fwd_id.hw_vsi_id);
+		break;
 	case ICE_NOP:
 		act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M,
 				  rinfo->sw_act.fwd_id.hw_vsi_id);
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
index dd03cb69ad26..b890410a2bc0 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
@@ -653,7 +653,7 @@ static int ice_tc_setup_redirect_action(struct net_device *filter_dev,
 		   ice_tc_is_dev_uplink(target_dev)) {
 		repr = ice_netdev_to_repr(filter_dev);
 
-		fltr->dest_vsi = repr->src_vsi->back->switchdev.uplink_vsi;
+		fltr->dest_vsi = repr->src_vsi->back->eswitch.uplink_vsi;
 		fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
 	} else if (ice_tc_is_dev_uplink(filter_dev) &&
 		   ice_is_port_repr_netdev(target_dev)) {
@@ -689,6 +689,41 @@ ice_tc_setup_drop_action(struct net_device *filter_dev,
 	return 0;
 }
 
+static int ice_tc_setup_mirror_action(struct net_device *filter_dev,
+				      struct ice_tc_flower_fltr *fltr,
+				      struct net_device *target_dev)
+{
+	struct ice_repr *repr;
+
+	fltr->action.fltr_act = ICE_MIRROR_PACKET;
+
+	if (ice_is_port_repr_netdev(filter_dev) &&
+	    ice_is_port_repr_netdev(target_dev)) {
+		repr = ice_netdev_to_repr(target_dev);
+
+		fltr->dest_vsi = repr->src_vsi;
+		fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
+	} else if (ice_is_port_repr_netdev(filter_dev) &&
+		   ice_tc_is_dev_uplink(target_dev)) {
+		repr = ice_netdev_to_repr(filter_dev);
+
+		fltr->dest_vsi = repr->src_vsi->back->eswitch.uplink_vsi;
+		fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
+	} else if (ice_tc_is_dev_uplink(filter_dev) &&
+		   ice_is_port_repr_netdev(target_dev)) {
+		repr = ice_netdev_to_repr(target_dev);
+
+		fltr->dest_vsi = repr->src_vsi;
+		fltr->direction = ICE_ESWITCH_FLTR_INGRESS;
+	} else {
+		NL_SET_ERR_MSG_MOD(fltr->extack,
+				   "Unsupported netdevice in switchdev mode");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int ice_eswitch_tc_parse_action(struct net_device *filter_dev,
 				       struct ice_tc_flower_fltr *fltr,
 				       struct flow_action_entry *act)
@@ -710,6 +745,12 @@ static int ice_eswitch_tc_parse_action(struct net_device *filter_dev,
 
 		break;
 
+	case FLOW_ACTION_MIRRED:
+		err = ice_tc_setup_mirror_action(filter_dev, fltr, act->dev);
+		if (err)
+			return err;
+		break;
+
 	default:
 		NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported action in switchdev mode");
 		return -EINVAL;
@@ -765,7 +806,7 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
 		rule_info.sw_act.src = hw->pf_id;
 		rule_info.flags_info.act = ICE_SINGLE_ACT_LB_ENABLE;
 	} else if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS &&
-		   fltr->dest_vsi == vsi->back->switchdev.uplink_vsi) {
+		   fltr->dest_vsi == vsi->back->eswitch.uplink_vsi) {
 		/* VF to Uplink */
 		rule_info.sw_act.flag |= ICE_FLTR_TX;
 		rule_info.sw_act.src = vsi->idx;
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 52d0a126eb61..74d13cc5a3a7 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -557,13 +557,14 @@ ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size)
  * @xdp_prog: XDP program to run
  * @xdp_ring: ring to be used for XDP_TX action
  * @rx_buf: Rx buffer to store the XDP action
+ * @eop_desc: Last descriptor in packet to read metadata from
  *
  * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
  */
 static void
 ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 	    struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
-	    struct ice_rx_buf *rx_buf)
+	    struct ice_rx_buf *rx_buf, union ice_32b_rx_flex_desc *eop_desc)
 {
 	unsigned int ret = ICE_XDP_PASS;
 	u32 act;
@@ -571,6 +572,8 @@ ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 	if (!xdp_prog)
 		goto exit;
 
+	ice_xdp_meta_set_desc(xdp, eop_desc);
+
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
 	switch (act) {
 	case XDP_PASS:
@@ -1180,8 +1183,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 		struct sk_buff *skb;
 		unsigned int size;
 		u16 stat_err_bits;
-		u16 vlan_tag = 0;
-		u16 rx_ptype;
+		u16 vlan_tci;
 
 		/* get the Rx desc from Rx ring based on 'next_to_clean' */
 		rx_desc = ICE_RX_DESC(rx_ring, ntc);
@@ -1241,7 +1243,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 		if (ice_is_non_eop(rx_ring, rx_desc))
 			continue;
 
-		ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf);
+		ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf, rx_desc);
 		if (rx_buf->act == ICE_XDP_PASS)
 			goto construct_skb;
 		total_rx_bytes += xdp_get_buff_len(xdp);
@@ -1276,7 +1278,7 @@ construct_skb:
 			continue;
 		}
 
-		vlan_tag = ice_get_vlan_tag_from_rx_desc(rx_desc);
+		vlan_tci = ice_get_vlan_tci(rx_desc);
 
 		/* pad the skb if needed, to make a valid ethernet frame */
 		if (eth_skb_pad(skb))
@@ -1286,14 +1288,11 @@ construct_skb:
 		total_rx_bytes += skb->len;
 
 		/* populate checksum, VLAN, and protocol */
-		rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) &
-			ICE_RX_FLEX_DESC_PTYPE_M;
-
-		ice_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
+		ice_process_skb_fields(rx_ring, rx_desc, skb);
 
 		ice_trace(clean_rx_irq_indicate, rx_ring, rx_desc, skb);
 		/* send completed skb up the stack */
-		ice_receive_skb(rx_ring, skb, vlan_tag);
+		ice_receive_skb(rx_ring, skb, vlan_tci);
 
 		/* update budget accounting */
 		total_rx_pkts++;
@@ -1494,9 +1493,9 @@ static void ice_set_wb_on_itr(struct ice_q_vector *q_vector)
 	 * be static in non-adaptive mode (user configured)
 	 */
 	wr32(&vsi->back->hw, GLINT_DYN_CTL(q_vector->reg_idx),
-	     ((ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S) &
-	      GLINT_DYN_CTL_ITR_INDX_M) | GLINT_DYN_CTL_INTENA_MSK_M |
-	     GLINT_DYN_CTL_WB_ON_ITR_M);
+	     FIELD_PREP(GLINT_DYN_CTL_ITR_INDX_M, ICE_ITR_NONE) |
+	     FIELD_PREP(GLINT_DYN_CTL_INTENA_MSK_M, 1) |
+	     FIELD_PREP(GLINT_DYN_CTL_WB_ON_ITR_M, 1));
 
 	q_vector->wb_on_itr = true;
 }
@@ -2306,9 +2305,6 @@ ice_tstamp(struct ice_tx_ring *tx_ring, struct sk_buff *skb,
 	if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)))
 		return;
 
-	if (!tx_ring->ptp_tx)
-		return;
-
 	/* Tx timestamps cannot be sampled when doing TSO */
 	if (first->tx_flags & ICE_TX_FLAGS_TSO)
 		return;
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index 166413fc33f4..b3379ff73674 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -257,6 +257,20 @@ enum ice_rx_dtype {
 	ICE_RX_DTYPE_SPLIT_ALWAYS	= 2,
 };
 
+struct ice_pkt_ctx {
+	u64 cached_phctime;
+	__be16 vlan_proto;
+};
+
+struct ice_xdp_buff {
+	struct xdp_buff xdp_buff;
+	const union ice_32b_rx_flex_desc *eop_desc;
+	const struct ice_pkt_ctx *pkt_ctx;
+};
+
+/* Required for compatibility with xdp_buffs from xsk_pool */
+static_assert(offsetof(struct ice_xdp_buff, xdp_buff) == 0);
+
 /* indices into GLINT_ITR registers */
 #define ICE_RX_ITR	ICE_IDX_ITR0
 #define ICE_TX_ITR	ICE_IDX_ITR1
@@ -298,7 +312,6 @@ enum ice_dynamic_itr {
 /* descriptor ring, associated with a VSI */
 struct ice_rx_ring {
 	/* CL1 - 1st cacheline starts here */
-	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
 	void *desc;			/* Descriptor ring memory */
 	struct device *dev;		/* Used for DMA mapping */
 	struct net_device *netdev;	/* netdev ring maps to */
@@ -310,13 +323,24 @@ struct ice_rx_ring {
 	u16 count;			/* Number of descriptors */
 	u16 reg_idx;			/* HW register index of the ring */
 	u16 next_to_alloc;
-	/* CL2 - 2nd cacheline starts here */
+
 	union {
 		struct ice_rx_buf *rx_buf;
 		struct xdp_buff **xdp_buf;
 	};
-	struct xdp_buff xdp;
+	/* CL2 - 2nd cacheline starts here */
+	union {
+		struct ice_xdp_buff xdp_ext;
+		struct xdp_buff xdp;
+	};
 	/* CL3 - 3rd cacheline starts here */
+	union {
+		struct ice_pkt_ctx pkt_ctx;
+		struct {
+			u64 cached_phctime;
+			__be16 vlan_proto;
+		};
+	};
 	struct bpf_prog *xdp_prog;
 	u16 rx_offset;
 
@@ -332,9 +356,9 @@ struct ice_rx_ring {
 	/* CL4 - 4th cacheline starts here */
 	struct ice_channel *ch;
 	struct ice_tx_ring *xdp_ring;
+	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
 	struct xsk_buff_pool *xsk_pool;
 	dma_addr_t dma;			/* physical address of ring */
-	u64 cached_phctime;
 	u16 rx_buf_len;
 	u8 dcb_tc;			/* Traffic class of ring */
 	u8 ptp_rx;
@@ -380,7 +404,6 @@ struct ice_tx_ring {
 #define ICE_TX_FLAGS_RING_VLAN_L2TAG2	BIT(2)
 	u8 flags;
 	u8 dcb_tc;			/* Traffic class of ring */
-	u8 ptp_tx;
 } ____cacheline_internodealigned_in_smp;
 
 static inline bool ice_ring_uses_build_skb(struct ice_rx_ring *ring)
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 7e06373e14d9..839e5da24ad5 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -63,28 +63,42 @@ static enum pkt_hash_types ice_ptype_to_htype(u16 ptype)
 }
 
 /**
- * ice_rx_hash - set the hash value in the skb
+ * ice_get_rx_hash - get RX hash value from descriptor
+ * @rx_desc: specific descriptor
+ *
+ * Returns hash, if present, 0 otherwise.
+ */
+static u32 ice_get_rx_hash(const union ice_32b_rx_flex_desc *rx_desc)
+{
+	const struct ice_32b_rx_flex_desc_nic *nic_mdid;
+
+	if (unlikely(rx_desc->wb.rxdid != ICE_RXDID_FLEX_NIC))
+		return 0;
+
+	nic_mdid = (struct ice_32b_rx_flex_desc_nic *)rx_desc;
+	return le32_to_cpu(nic_mdid->rss_hash);
+}
+
+/**
+ * ice_rx_hash_to_skb - set the hash value in the skb
  * @rx_ring: descriptor ring
  * @rx_desc: specific descriptor
  * @skb: pointer to current skb
  * @rx_ptype: the ptype value from the descriptor
  */
 static void
-ice_rx_hash(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc,
-	    struct sk_buff *skb, u16 rx_ptype)
+ice_rx_hash_to_skb(const struct ice_rx_ring *rx_ring,
+		   const union ice_32b_rx_flex_desc *rx_desc,
+		   struct sk_buff *skb, u16 rx_ptype)
 {
-	struct ice_32b_rx_flex_desc_nic *nic_mdid;
 	u32 hash;
 
 	if (!(rx_ring->netdev->features & NETIF_F_RXHASH))
 		return;
 
-	if (rx_desc->wb.rxdid != ICE_RXDID_FLEX_NIC)
-		return;
-
-	nic_mdid = (struct ice_32b_rx_flex_desc_nic *)rx_desc;
-	hash = le32_to_cpu(nic_mdid->rss_hash);
-	skb_set_hash(skb, hash, ice_ptype_to_htype(rx_ptype));
+	hash = ice_get_rx_hash(rx_desc);
+	if (likely(hash))
+		skb_set_hash(skb, hash, ice_ptype_to_htype(rx_ptype));
 }
 
 /**
@@ -171,11 +185,38 @@ checksum_fail:
 }
 
 /**
+ * ice_ptp_rx_hwts_to_skb - Put RX timestamp into skb
+ * @rx_ring: Ring to get the VSI info
+ * @rx_desc: Receive descriptor
+ * @skb: Particular skb to send timestamp with
+ *
+ * The timestamp is in ns, so we must convert the result first.
+ */
+static void
+ice_ptp_rx_hwts_to_skb(struct ice_rx_ring *rx_ring,
+		       const union ice_32b_rx_flex_desc *rx_desc,
+		       struct sk_buff *skb)
+{
+	u64 ts_ns = ice_ptp_get_rx_hwts(rx_desc, &rx_ring->pkt_ctx);
+
+	skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(ts_ns);
+}
+
+/**
+ * ice_get_ptype - Read HW packet type from the descriptor
+ * @rx_desc: RX descriptor
+ */
+static u16 ice_get_ptype(const union ice_32b_rx_flex_desc *rx_desc)
+{
+	return le16_to_cpu(rx_desc->wb.ptype_flex_flags0) &
+	       ICE_RX_FLEX_DESC_PTYPE_M;
+}
+
+/**
  * ice_process_skb_fields - Populate skb header fields from Rx descriptor
  * @rx_ring: Rx descriptor ring packet is being transacted on
  * @rx_desc: pointer to the EOP Rx descriptor
  * @skb: pointer to current skb being populated
- * @ptype: the packet type decoded by hardware
  *
  * This function checks the ring, descriptor, and packet information in
  * order to populate the hash, checksum, VLAN, protocol, and
@@ -184,9 +225,11 @@ checksum_fail:
 void
 ice_process_skb_fields(struct ice_rx_ring *rx_ring,
 		       union ice_32b_rx_flex_desc *rx_desc,
-		       struct sk_buff *skb, u16 ptype)
+		       struct sk_buff *skb)
 {
-	ice_rx_hash(rx_ring, rx_desc, skb, ptype);
+	u16 ptype = ice_get_ptype(rx_desc);
+
+	ice_rx_hash_to_skb(rx_ring, rx_desc, skb, ptype);
 
 	/* modifies the skb - consumes the enet header */
 	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
@@ -194,28 +237,24 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring,
 	ice_rx_csum(rx_ring, skb, rx_desc, ptype);
 
 	if (rx_ring->ptp_rx)
-		ice_ptp_rx_hwtstamp(rx_ring, rx_desc, skb);
+		ice_ptp_rx_hwts_to_skb(rx_ring, rx_desc, skb);
 }
 
 /**
  * ice_receive_skb - Send a completed packet up the stack
  * @rx_ring: Rx ring in play
  * @skb: packet to send up
- * @vlan_tag: VLAN tag for packet
+ * @vlan_tci: VLAN TCI for packet
  *
  * This function sends the completed packet (via. skb) up the stack using
  * gro receive functions (with/without VLAN tag)
  */
 void
-ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag)
+ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tci)
 {
-	netdev_features_t features = rx_ring->netdev->features;
-	bool non_zero_vlan = !!(vlan_tag & VLAN_VID_MASK);
-
-	if ((features & NETIF_F_HW_VLAN_CTAG_RX) && non_zero_vlan)
-		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
-	else if ((features & NETIF_F_HW_VLAN_STAG_RX) && non_zero_vlan)
-		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021AD), vlan_tag);
+	if ((vlan_tci & VLAN_VID_MASK) && rx_ring->vlan_proto)
+		__vlan_hwaccel_put_tag(skb, rx_ring->vlan_proto,
+				       vlan_tci);
 
 	napi_gro_receive(&rx_ring->q_vector->napi, skb);
 }
@@ -464,3 +503,125 @@ void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res,
 			spin_unlock(&xdp_ring->tx_lock);
 	}
 }
+
+/**
+ * ice_xdp_rx_hw_ts - HW timestamp XDP hint handler
+ * @ctx: XDP buff pointer
+ * @ts_ns: destination address
+ *
+ * Copy HW timestamp (if available) to the destination address.
+ */
+static int ice_xdp_rx_hw_ts(const struct xdp_md *ctx, u64 *ts_ns)
+{
+	const struct ice_xdp_buff *xdp_ext = (void *)ctx;
+
+	*ts_ns = ice_ptp_get_rx_hwts(xdp_ext->eop_desc,
+				     xdp_ext->pkt_ctx);
+	if (!*ts_ns)
+		return -ENODATA;
+
+	return 0;
+}
+
+/* Define a ptype index -> XDP hash type lookup table.
+ * It uses the same ptype definitions as ice_decode_rx_desc_ptype[],
+ * avoiding possible copy-paste errors.
+ */
+#undef ICE_PTT
+#undef ICE_PTT_UNUSED_ENTRY
+
+#define ICE_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\
+	[PTYPE] = XDP_RSS_L3_##OUTER_IP_VER | XDP_RSS_L4_##I | XDP_RSS_TYPE_##PL
+
+#define ICE_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = 0
+
+/* A few supplementary definitions for when XDP hash types do not coincide
+ * with what can be generated from ptype definitions
+ * by means of preprocessor concatenation.
+ */
+#define XDP_RSS_L3_NONE		XDP_RSS_TYPE_NONE
+#define XDP_RSS_L4_NONE		XDP_RSS_TYPE_NONE
+#define XDP_RSS_TYPE_PAY2	XDP_RSS_TYPE_L2
+#define XDP_RSS_TYPE_PAY3	XDP_RSS_TYPE_NONE
+#define XDP_RSS_TYPE_PAY4	XDP_RSS_L4
+
+static const enum xdp_rss_hash_type
+ice_ptype_to_xdp_hash[ICE_NUM_DEFINED_PTYPES] = {
+	ICE_PTYPES
+};
+
+#undef XDP_RSS_L3_NONE
+#undef XDP_RSS_L4_NONE
+#undef XDP_RSS_TYPE_PAY2
+#undef XDP_RSS_TYPE_PAY3
+#undef XDP_RSS_TYPE_PAY4
+
+#undef ICE_PTT
+#undef ICE_PTT_UNUSED_ENTRY
+
+/**
+ * ice_xdp_rx_hash_type - Get XDP-specific hash type from the RX descriptor
+ * @eop_desc: End of Packet descriptor
+ */
+static enum xdp_rss_hash_type
+ice_xdp_rx_hash_type(const union ice_32b_rx_flex_desc *eop_desc)
+{
+	u16 ptype = ice_get_ptype(eop_desc);
+
+	if (unlikely(ptype >= ICE_NUM_DEFINED_PTYPES))
+		return 0;
+
+	return ice_ptype_to_xdp_hash[ptype];
+}
+
+/**
+ * ice_xdp_rx_hash - RX hash XDP hint handler
+ * @ctx: XDP buff pointer
+ * @hash: hash destination address
+ * @rss_type: XDP hash type destination address
+ *
+ * Copy RX hash (if available) and its type to the destination address.
+ */
+static int ice_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
+			   enum xdp_rss_hash_type *rss_type)
+{
+	const struct ice_xdp_buff *xdp_ext = (void *)ctx;
+
+	*hash = ice_get_rx_hash(xdp_ext->eop_desc);
+	*rss_type = ice_xdp_rx_hash_type(xdp_ext->eop_desc);
+	if (!likely(*hash))
+		return -ENODATA;
+
+	return 0;
+}
+
+/**
+ * ice_xdp_rx_vlan_tag - VLAN tag XDP hint handler
+ * @ctx: XDP buff pointer
+ * @vlan_proto: destination address for VLAN protocol
+ * @vlan_tci: destination address for VLAN TCI
+ *
+ * Copy VLAN tag (if was stripped) and corresponding protocol
+ * to the destination address.
+ */
+static int ice_xdp_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto,
+			       u16 *vlan_tci)
+{
+	const struct ice_xdp_buff *xdp_ext = (void *)ctx;
+
+	*vlan_proto = xdp_ext->pkt_ctx->vlan_proto;
+	if (!*vlan_proto)
+		return -ENODATA;
+
+	*vlan_tci = ice_get_vlan_tci(xdp_ext->eop_desc);
+	if (!*vlan_tci)
+		return -ENODATA;
+
+	return 0;
+}
+
+const struct xdp_metadata_ops ice_xdp_md_ops = {
+	.xmo_rx_timestamp		= ice_xdp_rx_hw_ts,
+	.xmo_rx_hash			= ice_xdp_rx_hash,
+	.xmo_rx_vlan_tag		= ice_xdp_rx_vlan_tag,
+};
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
index 115969ecdf7b..762047508619 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
@@ -84,7 +84,7 @@ ice_build_ctob(u64 td_cmd, u64 td_offset, unsigned int size, u64 td_tag)
 }
 
 /**
- * ice_get_vlan_tag_from_rx_desc - get VLAN from Rx flex descriptor
+ * ice_get_vlan_tci - get VLAN TCI from Rx flex descriptor
  * @rx_desc: Rx 32b flex descriptor with RXDID=2
  *
  * The OS and current PF implementation only support stripping a single VLAN tag
@@ -92,7 +92,7 @@ ice_build_ctob(u64 td_cmd, u64 td_offset, unsigned int size, u64 td_tag)
  * one is found return the tag, else return 0 to mean no VLAN tag was found.
  */
 static inline u16
-ice_get_vlan_tag_from_rx_desc(union ice_32b_rx_flex_desc *rx_desc)
+ice_get_vlan_tci(const union ice_32b_rx_flex_desc *rx_desc)
 {
 	u16 stat_err_bits;
 
@@ -148,7 +148,17 @@ void ice_release_rx_desc(struct ice_rx_ring *rx_ring, u16 val);
 void
 ice_process_skb_fields(struct ice_rx_ring *rx_ring,
 		       union ice_32b_rx_flex_desc *rx_desc,
-		       struct sk_buff *skb, u16 ptype);
+		       struct sk_buff *skb);
 void
-ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag);
+ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tci);
+
+static inline void
+ice_xdp_meta_set_desc(struct xdp_buff *xdp,
+		      union ice_32b_rx_flex_desc *eop_desc)
+{
+	struct ice_xdp_buff *xdp_ext = container_of(xdp, struct ice_xdp_buff,
+						    xdp_buff);
+
+	xdp_ext->eop_desc = eop_desc;
+}
 #endif /* !_ICE_TXRX_LIB_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index a18ca0ff879f..41ab6d7bbd9e 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -17,6 +17,7 @@
 #include "ice_protocol_type.h"
 #include "ice_sbq_cmd.h"
 #include "ice_vlan_mode.h"
+#include "ice_fwlog.h"
 
 static inline bool ice_is_tc_ena(unsigned long bitmap, u8 tc)
 {
@@ -246,6 +247,7 @@ struct ice_fd_hw_prof {
 	int cnt;
 	u64 entry_h[ICE_MAX_FDIR_VSI_PER_FILTER][ICE_FD_HW_SEG_MAX];
 	u16 vsi_h[ICE_MAX_FDIR_VSI_PER_FILTER];
+	u64 prof_id[ICE_FD_HW_SEG_MAX];
 };
 
 /* Common HW capabilities for SW use */
@@ -351,6 +353,7 @@ struct ice_ts_func_info {
 #define ICE_TS_TMR0_ENA_M		BIT(25)
 #define ICE_TS_TMR1_ENA_M		BIT(26)
 #define ICE_TS_LL_TX_TS_READ_M		BIT(28)
+#define ICE_TS_LL_TX_TS_INT_READ_M	BIT(29)
 
 struct ice_ts_dev_info {
 	/* Device specific info */
@@ -364,6 +367,7 @@ struct ice_ts_dev_info {
 	u8 tmr0_ena;
 	u8 tmr1_ena;
 	u8 ts_ll_read;
+	u8 ts_ll_int_read;
 };
 
 /* Function specific capabilities */
@@ -377,6 +381,8 @@ struct ice_hw_func_caps {
 	struct ice_ts_func_info ts_func_info;
 };
 
+#define ICE_SENSOR_SUPPORT_E810_INT_TEMP_BIT	0
+
 /* Device wide capabilities */
 struct ice_hw_dev_caps {
 	struct ice_hw_common_caps common_cap;
@@ -385,6 +391,11 @@ struct ice_hw_dev_caps {
 	u32 num_flow_director_fltr;	/* Number of FD filters available */
 	struct ice_ts_dev_info ts_dev_info;
 	u32 num_funcs;
+	/* bitmap of supported sensors
+	 * bit 0 - internal temperature sensor
+	 * bit 31:1 - Reserved
+	 */
+	u32 supported_sensors;
 };
 
 /* MAC info */
@@ -730,24 +741,6 @@ struct ice_switch_info {
 	DECLARE_BITMAP(prof_res_bm[ICE_MAX_NUM_PROFILES], ICE_MAX_FV_WORDS);
 };
 
-/* FW logging configuration */
-struct ice_fw_log_evnt {
-	u8 cfg : 4;	/* New event enables to configure */
-	u8 cur : 4;	/* Current/active event enables */
-};
-
-struct ice_fw_log_cfg {
-	u8 cq_en : 1;    /* FW logging is enabled via the control queue */
-	u8 uart_en : 1;  /* FW logging is enabled via UART for all PFs */
-	u8 actv_evnts;   /* Cumulation of currently enabled log events */
-
-#define ICE_FW_LOG_EVNT_INFO	(ICE_AQC_FW_LOG_INFO_EN >> ICE_AQC_FW_LOG_EN_S)
-#define ICE_FW_LOG_EVNT_INIT	(ICE_AQC_FW_LOG_INIT_EN >> ICE_AQC_FW_LOG_EN_S)
-#define ICE_FW_LOG_EVNT_FLOW	(ICE_AQC_FW_LOG_FLOW_EN >> ICE_AQC_FW_LOG_EN_S)
-#define ICE_FW_LOG_EVNT_ERR	(ICE_AQC_FW_LOG_ERR_EN >> ICE_AQC_FW_LOG_EN_S)
-	struct ice_fw_log_evnt evnts[ICE_AQC_FW_LOG_ID_MAX];
-};
-
 /* Enum defining the different states of the mailbox snapshot in the
  * PF-VF mailbox overflow detection algorithm. The snapshot can be in
  * states:
@@ -827,7 +820,7 @@ struct ice_mbx_data {
 enum ice_phy_model {
 	ICE_PHY_UNSUP = -1,
 	ICE_PHY_E810  = 1,
-	ICE_PHY_E822,
+	ICE_PHY_E82X,
 };
 
 /* Port hardware description */
@@ -889,7 +882,9 @@ struct ice_hw {
 	u8 fw_patch;		/* firmware patch version */
 	u32 fw_build;		/* firmware build number */
 
-	struct ice_fw_log_cfg fw_log;
+	struct ice_fwlog_cfg fwlog_cfg;
+	bool fwlog_supported; /* does hardware support FW logging? */
+	struct ice_fwlog_ring fwlog_ring;
 
 /* Device max aggregate bandwidths corresponding to the GL_PWR_MODE_CTL
  * register. Used for determining the ITR/INTRL granularity during
@@ -910,10 +905,9 @@ struct ice_hw {
 	/* INTRL granularity in 1 us */
 	u8 intrl_gran;
 
-#define ICE_PHY_PER_NAC_E822		1
 #define ICE_MAX_QUAD			2
-#define ICE_QUADS_PER_PHY_E822		2
-#define ICE_PORTS_PER_PHY_E822		8
+#define ICE_QUADS_PER_PHY_E82X		2
+#define ICE_PORTS_PER_PHY_E82X		8
 #define ICE_PORTS_PER_QUAD		4
 #define ICE_PORTS_PER_PHY_E810		4
 #define ICE_NUM_EXTERNAL_PORTS		(ICE_MAX_QUAD * ICE_PORTS_PER_QUAD)
@@ -1009,7 +1003,6 @@ struct ice_hw_port_stats {
 	u64 error_bytes;		/* errbc */
 	u64 mac_local_faults;		/* mlfc */
 	u64 mac_remote_faults;		/* mrfc */
-	u64 rx_len_errors;		/* rlec */
 	u64 link_xon_rx;		/* lxonrxc */
 	u64 link_xoff_rx;		/* lxoffrxc */
 	u64 link_xon_tx;		/* lxontxc */
@@ -1048,6 +1041,7 @@ enum ice_sw_fwd_act_type {
 	ICE_FWD_TO_Q,
 	ICE_FWD_TO_QGRP,
 	ICE_DROP_PACKET,
+	ICE_MIRROR_PACKET,
 	ICE_NOP,
 	ICE_INVAL_ACT
 };
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
index aca1f2ea5034..2ffdae9a82df 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
@@ -248,29 +248,44 @@ static void ice_vf_pre_vsi_rebuild(struct ice_vf *vf)
 }
 
 /**
- * ice_vf_recreate_vsi - Release and re-create the VF's VSI
- * @vf: VF to recreate the VSI for
+ * ice_vf_reconfig_vsi - Reconfigure a VF VSI with the device
+ * @vf: VF to reconfigure the VSI for
  *
- * This is only called when a single VF is being reset (i.e. VVF, VFLR, host
- * VF configuration change, etc)
+ * This is called when a single VF is being reset (i.e. VVF, VFLR, host VF
+ * configuration change, etc).
  *
- * It releases and then re-creates a new VSI.
+ * It brings the VSI down and then reconfigures it with the hardware.
  */
-static int ice_vf_recreate_vsi(struct ice_vf *vf)
+int ice_vf_reconfig_vsi(struct ice_vf *vf)
 {
+	struct ice_vsi *vsi = ice_get_vf_vsi(vf);
+	struct ice_vsi_cfg_params params = {};
 	struct ice_pf *pf = vf->pf;
 	int err;
 
-	ice_vf_vsi_release(vf);
+	if (WARN_ON(!vsi))
+		return -EINVAL;
 
-	err = vf->vf_ops->create_vsi(vf);
+	params = ice_vsi_to_params(vsi);
+	params.flags = ICE_VSI_FLAG_NO_INIT;
+
+	ice_vsi_decfg(vsi);
+	ice_fltr_remove_all(vsi);
+
+	err = ice_vsi_cfg(vsi, &params);
 	if (err) {
 		dev_err(ice_pf_to_dev(pf),
-			"Failed to recreate the VF%u's VSI, error %d\n",
+			"Failed to reconfigure the VF%u's VSI, error %d\n",
 			vf->vf_id, err);
 		return err;
 	}
 
+	/* Update the lan_vsi_num field since it might have been changed. The
+	 * PF lan_vsi_idx number remains the same so we don't need to change
+	 * that.
+	 */
+	vf->lan_vsi_num = vsi->vsi_num;
+
 	return 0;
 }
 
@@ -760,6 +775,7 @@ void ice_reset_all_vfs(struct ice_pf *pf)
 	ice_for_each_vf(pf, bkt, vf) {
 		mutex_lock(&vf->cfg_lock);
 
+		ice_eswitch_detach(pf, vf);
 		vf->driver_caps = 0;
 		ice_vc_set_default_allowlist(vf);
 
@@ -775,13 +791,11 @@ void ice_reset_all_vfs(struct ice_pf *pf)
 		ice_vf_rebuild_vsi(vf);
 		ice_vf_post_vsi_rebuild(vf);
 
+		ice_eswitch_attach(pf, vf);
+
 		mutex_unlock(&vf->cfg_lock);
 	}
 
-	if (ice_is_eswitch_mode_switchdev(pf))
-		if (ice_eswitch_rebuild(pf))
-			dev_warn(dev, "eswitch rebuild failed\n");
-
 	ice_flush(hw);
 	clear_bit(ICE_VF_DIS, pf->state);
 
@@ -829,12 +843,16 @@ static void ice_notify_vf_reset(struct ice_vf *vf)
 int ice_reset_vf(struct ice_vf *vf, u32 flags)
 {
 	struct ice_pf *pf = vf->pf;
+	struct ice_lag *lag;
 	struct ice_vsi *vsi;
+	u8 act_prt, pri_prt;
 	struct device *dev;
 	int err = 0;
 	bool rsd;
 
 	dev = ice_pf_to_dev(pf);
+	act_prt = ICE_LAG_INVALID_PORT;
+	pri_prt = pf->hw.port_info->lport;
 
 	if (flags & ICE_VF_RESET_NOTIFY)
 		ice_notify_vf_reset(vf);
@@ -845,6 +863,17 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags)
 		return 0;
 	}
 
+	lag = pf->lag;
+	mutex_lock(&pf->lag_mutex);
+	if (lag && lag->bonded && lag->primary) {
+		act_prt = lag->active_port;
+		if (act_prt != pri_prt && act_prt != ICE_LAG_INVALID_PORT &&
+		    lag->upper_netdev)
+			ice_lag_move_vf_nodes_cfg(lag, act_prt, pri_prt);
+		else
+			act_prt = ICE_LAG_INVALID_PORT;
+	}
+
 	if (flags & ICE_VF_RESET_LOCK)
 		mutex_lock(&vf->cfg_lock);
 	else
@@ -914,7 +943,7 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags)
 
 	ice_vf_pre_vsi_rebuild(vf);
 
-	if (ice_vf_recreate_vsi(vf)) {
+	if (ice_vf_reconfig_vsi(vf)) {
 		dev_err(dev, "Failed to release and setup the VF%u's VSI\n",
 			vf->vf_id);
 		err = -EFAULT;
@@ -928,7 +957,7 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags)
 		goto out_unlock;
 	}
 
-	ice_eswitch_update_repr(vsi);
+	ice_eswitch_update_repr(vf->repr_id, vsi);
 
 	/* if the VF has been reset allow it to come up again */
 	ice_mbx_clear_malvf(&vf->mbx_info);
@@ -937,6 +966,11 @@ out_unlock:
 	if (flags & ICE_VF_RESET_LOCK)
 		mutex_unlock(&vf->cfg_lock);
 
+	if (lag && lag->bonded && lag->primary &&
+	    act_prt != ICE_LAG_INVALID_PORT)
+		ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt);
+	mutex_unlock(&pf->lag_mutex);
+
 	return err;
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h
index 93c774f2f437..0cc9034065c5 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h
@@ -62,7 +62,6 @@ struct ice_vf_ops {
 	bool (*poll_reset_status)(struct ice_vf *vf);
 	void (*clear_reset_trigger)(struct ice_vf *vf);
 	void (*irq_close)(struct ice_vf *vf);
-	int (*create_vsi)(struct ice_vf *vf);
 	void (*post_vsi_rebuild)(struct ice_vf *vf);
 };
 
@@ -130,7 +129,7 @@ struct ice_vf {
 	struct ice_mdd_vf_events mdd_tx_events;
 	DECLARE_BITMAP(opcodes_allowlist, VIRTCHNL_OP_MAX);
 
-	struct ice_repr *repr;
+	unsigned long repr_id;
 	const struct ice_virtchnl_ops *virtchnl_ops;
 	const struct ice_vf_ops *vf_ops;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
index 0c7e77c0a09f..91ba7fe0eaee 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
@@ -23,6 +23,7 @@
 #warning "Only include ice_vf_lib_private.h in CONFIG_PCI_IOV virtualization files"
 #endif
 
+int ice_vf_reconfig_vsi(struct ice_vf *vf);
 void ice_initialize_vf_entry(struct ice_vf *vf);
 void ice_dis_vf_qs(struct ice_vf *vf);
 int ice_check_vf_init(struct ice_vf *vf);
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c
index d7b10dc67f03..80dc4bcdd3a4 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c
@@ -32,7 +32,6 @@ static void ice_port_vlan_on(struct ice_vsi *vsi)
 		/* setup outer VLAN ops */
 		vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan;
 		vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan;
-		vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan;
 
 		/* setup inner VLAN ops */
 		vlan_ops = &vsi->inner_vlan_ops;
@@ -47,8 +46,13 @@ static void ice_port_vlan_on(struct ice_vsi *vsi)
 
 		vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan;
 		vlan_ops->clear_port_vlan = ice_vsi_clear_inner_port_vlan;
-		vlan_ops->clear_port_vlan = ice_vsi_clear_inner_port_vlan;
 	}
+
+	/* all Rx traffic should be in the domain of the assigned port VLAN,
+	 * so prevent disabling Rx VLAN filtering
+	 */
+	vlan_ops->dis_rx_filtering = noop_vlan;
+
 	vlan_ops->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering;
 }
 
@@ -77,6 +81,8 @@ static void ice_port_vlan_off(struct ice_vsi *vsi)
 		vlan_ops->del_vlan = ice_vsi_del_vlan;
 	}
 
+	vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering;
+
 	if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags))
 		vlan_ops->ena_rx_filtering = noop_vlan;
 	else
@@ -141,7 +147,6 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi)
 		&vsi->outer_vlan_ops : &vsi->inner_vlan_ops;
 
 	vlan_ops->add_vlan = ice_vsi_add_vlan;
-	vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering;
 	vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering;
 	vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index cdf17b1e2f25..c925813ec9ca 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -689,9 +689,7 @@ out:
  * a specific virtchnl RSS cfg
  * @hw: pointer to the hardware
  * @rss_cfg: pointer to the virtchnl RSS cfg
- * @addl_hdrs: pointer to the protocol header fields (ICE_FLOW_SEG_HDR_*)
- * to configure
- * @hash_flds: pointer to the hash bit fields (ICE_FLOW_HASH_*) to configure
+ * @hash_cfg: pointer to the HW hash configuration
  *
  * Return true if all the protocol header and hash fields in the RSS cfg could
  * be parsed, else return false
@@ -699,13 +697,23 @@ out:
  * This function parses the virtchnl RSS cfg to be the intended
  * hash fields and the intended header for RSS configuration
  */
-static bool
-ice_vc_parse_rss_cfg(struct ice_hw *hw, struct virtchnl_rss_cfg *rss_cfg,
-		     u32 *addl_hdrs, u64 *hash_flds)
+static bool ice_vc_parse_rss_cfg(struct ice_hw *hw,
+				 struct virtchnl_rss_cfg *rss_cfg,
+				 struct ice_rss_hash_cfg *hash_cfg)
 {
 	const struct ice_vc_hash_field_match_type *hf_list;
 	const struct ice_vc_hdr_match_type *hdr_list;
 	int i, hf_list_len, hdr_list_len;
+	u32 *addl_hdrs = &hash_cfg->addl_hdrs;
+	u64 *hash_flds = &hash_cfg->hash_flds;
+
+	/* set outer layer RSS as default */
+	hash_cfg->hdr_type = ICE_RSS_OUTER_HEADERS;
+
+	if (rss_cfg->rss_algorithm == VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC)
+		hash_cfg->symm = true;
+	else
+		hash_cfg->symm = false;
 
 	hf_list = ice_vc_hash_field_list;
 	hf_list_len = ARRAY_SIZE(ice_vc_hash_field_list);
@@ -823,8 +831,8 @@ static int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add)
 		int status;
 
 		lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI;
-		hash_type = add ? ICE_AQ_VSI_Q_OPT_RSS_XOR :
-				ICE_AQ_VSI_Q_OPT_RSS_TPLZ;
+		hash_type = add ? ICE_AQ_VSI_Q_OPT_RSS_HASH_XOR :
+				ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ;
 
 		ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 		if (!ctx) {
@@ -832,11 +840,9 @@ static int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add)
 			goto error_param;
 		}
 
-		ctx->info.q_opt_rss = ((lut_type <<
-					ICE_AQ_VSI_Q_OPT_RSS_LUT_S) &
-				       ICE_AQ_VSI_Q_OPT_RSS_LUT_M) |
-				       (hash_type &
-					ICE_AQ_VSI_Q_OPT_RSS_HASH_M);
+		ctx->info.q_opt_rss =
+			FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_LUT_M, lut_type) |
+			FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_HASH_M, hash_type);
 
 		/* Preserve existing queueing option setting */
 		ctx->info.q_opt_rss |= (vsi->info.q_opt_rss &
@@ -858,18 +864,24 @@ static int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add)
 
 		kfree(ctx);
 	} else {
-		u32 addl_hdrs = ICE_FLOW_SEG_HDR_NONE;
-		u64 hash_flds = ICE_HASH_INVALID;
+		struct ice_rss_hash_cfg cfg;
 
-		if (!ice_vc_parse_rss_cfg(hw, rss_cfg, &addl_hdrs,
-					  &hash_flds)) {
+		/* Only check for none raw pattern case */
+		if (!ice_vc_validate_pattern(vf, &rss_cfg->proto_hdrs)) {
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto error_param;
+		}
+		cfg.addl_hdrs = ICE_FLOW_SEG_HDR_NONE;
+		cfg.hash_flds = ICE_HASH_INVALID;
+		cfg.hdr_type = ICE_RSS_ANY_HEADERS;
+
+		if (!ice_vc_parse_rss_cfg(hw, rss_cfg, &cfg)) {
 			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 			goto error_param;
 		}
 
 		if (add) {
-			if (ice_add_rss_cfg(hw, vsi->idx, hash_flds,
-					    addl_hdrs)) {
+			if (ice_add_rss_cfg(hw, vsi, &cfg)) {
 				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 				dev_err(dev, "ice_add_rss_cfg failed for vsi = %d, v_ret = %d\n",
 					vsi->vsi_num, v_ret);
@@ -877,8 +889,7 @@ static int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add)
 		} else {
 			int status;
 
-			status = ice_rem_rss_cfg(hw, vsi->idx, hash_flds,
-						 addl_hdrs);
+			status = ice_rem_rss_cfg(hw, vsi->idx, &cfg);
 			/* We just ignore -ENOENT, because if two configurations
 			 * share the same profile remove one of them actually
 			 * removes both, since the profile is deleted.
@@ -989,6 +1000,51 @@ error_param:
 }
 
 /**
+ * ice_vc_config_rss_hfunc
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * Configure the VF's RSS Hash function
+ */
+static int ice_vc_config_rss_hfunc(struct ice_vf *vf, u8 *msg)
+{
+	struct virtchnl_rss_hfunc *vrh = (struct virtchnl_rss_hfunc *)msg;
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	u8 hfunc = ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ;
+	struct ice_vsi *vsi;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (!ice_vc_isvalid_vsi_id(vf, vrh->vsi_id)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (vrh->rss_algorithm == VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC)
+		hfunc = ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ;
+
+	if (ice_set_rss_hfunc(vsi, hfunc))
+		v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
+error_param:
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_HFUNC, v_ret,
+				     NULL, 0);
+}
+
+/**
  * ice_vc_cfg_promiscuous_mode_msg
  * @vf: pointer to the VF info
  * @msg: pointer to the msg buffer
@@ -1523,7 +1579,6 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg)
 	u16 num_q_vectors_mapped, vsi_id, vector_id;
 	struct virtchnl_irq_map_info *irqmap_info;
 	struct virtchnl_vector_map *map;
-	struct ice_pf *pf = vf->pf;
 	struct ice_vsi *vsi;
 	int i;
 
@@ -1535,7 +1590,7 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg)
 	 * there is actually at least a single VF queue vector mapped
 	 */
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) ||
-	    pf->vfs.num_msix_per < num_q_vectors_mapped ||
+	    vf->num_msix < num_q_vectors_mapped ||
 	    !num_q_vectors_mapped) {
 		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
@@ -1557,7 +1612,7 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg)
 		/* vector_id is always 0-based for each VF, and can never be
 		 * larger than or equal to the max allowed interrupts per VF
 		 */
-		if (!(vector_id < pf->vfs.num_msix_per) ||
+		if (!(vector_id < vf->num_msix) ||
 		    !ice_vc_isvalid_vsi_id(vf, vsi_id) ||
 		    (!vector_id && (map->rxq_map || map->txq_map))) {
 			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
@@ -1603,9 +1658,24 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 	    (struct virtchnl_vsi_queue_config_info *)msg;
 	struct virtchnl_queue_pair_info *qpi;
 	struct ice_pf *pf = vf->pf;
+	struct ice_lag *lag;
 	struct ice_vsi *vsi;
+	u8 act_prt, pri_prt;
 	int i = -1, q_idx;
 
+	lag = pf->lag;
+	mutex_lock(&pf->lag_mutex);
+	act_prt = ICE_LAG_INVALID_PORT;
+	pri_prt = pf->hw.port_info->lport;
+	if (lag && lag->bonded && lag->primary) {
+		act_prt = lag->active_port;
+		if (act_prt != pri_prt && act_prt != ICE_LAG_INVALID_PORT &&
+		    lag->upper_netdev)
+			ice_lag_move_vf_nodes_cfg(lag, act_prt, pri_prt);
+		else
+			act_prt = ICE_LAG_INVALID_PORT;
+	}
+
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
 		goto error_param;
 
@@ -1729,6 +1799,11 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 		}
 	}
 
+	if (lag && lag->bonded && lag->primary &&
+	    act_prt != ICE_LAG_INVALID_PORT)
+		ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt);
+	mutex_unlock(&pf->lag_mutex);
+
 	/* send the response to the VF */
 	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES,
 				     VIRTCHNL_STATUS_SUCCESS, NULL, 0);
@@ -1743,6 +1818,11 @@ error_param:
 				vf->vf_id, i);
 	}
 
+	if (lag && lag->bonded && lag->primary &&
+	    act_prt != ICE_LAG_INVALID_PORT)
+		ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt);
+	mutex_unlock(&pf->lag_mutex);
+
 	ice_lag_move_new_vf_nodes(vf);
 
 	/* send the response to the VF */
@@ -2610,7 +2690,7 @@ static int ice_vc_set_rss_hena(struct ice_vf *vf, u8 *msg)
 	}
 
 	if (vrh->hena) {
-		status = ice_add_avf_rss_cfg(&pf->hw, vsi->idx, vrh->hena);
+		status = ice_add_avf_rss_cfg(&pf->hw, vsi, vrh->hena);
 		v_ret = ice_err_to_virt_err(status);
 	}
 
@@ -3022,7 +3102,7 @@ static struct ice_vlan ice_vc_to_vlan(struct virtchnl_vlan *vc_vlan)
 {
 	struct ice_vlan vlan = { 0 };
 
-	vlan.prio = (vc_vlan->tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
+	vlan.prio = FIELD_GET(VLAN_PRIO_MASK, vc_vlan->tci);
 	vlan.vid = vc_vlan->tci & VLAN_VID_MASK;
 	vlan.tpid = vc_vlan->tpid;
 
@@ -3731,6 +3811,7 @@ static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = {
 	.cfg_irq_map_msg = ice_vc_cfg_irq_map_msg,
 	.config_rss_key = ice_vc_config_rss_key,
 	.config_rss_lut = ice_vc_config_rss_lut,
+	.config_rss_hfunc = ice_vc_config_rss_hfunc,
 	.get_stats_msg = ice_vc_get_stats_msg,
 	.cfg_promiscuous_mode_msg = ice_vc_cfg_promiscuous_mode_msg,
 	.add_vlan_msg = ice_vc_add_vlan_msg,
@@ -3860,6 +3941,7 @@ static const struct ice_virtchnl_ops ice_virtchnl_repr_ops = {
 	.cfg_irq_map_msg = ice_vc_cfg_irq_map_msg,
 	.config_rss_key = ice_vc_config_rss_key,
 	.config_rss_lut = ice_vc_config_rss_lut,
+	.config_rss_hfunc = ice_vc_config_rss_hfunc,
 	.get_stats_msg = ice_vc_get_stats_msg,
 	.cfg_promiscuous_mode_msg = ice_vc_repr_cfg_promiscuous_mode,
 	.add_vlan_msg = ice_vc_add_vlan_msg,
@@ -4042,6 +4124,9 @@ error_handler:
 	case VIRTCHNL_OP_CONFIG_RSS_LUT:
 		err = ops->config_rss_lut(vf, msg);
 		break;
+	case VIRTCHNL_OP_CONFIG_RSS_HFUNC:
+		err = ops->config_rss_hfunc(vf, msg);
+		break;
 	case VIRTCHNL_OP_GET_STATS:
 		err = ops->get_stats_msg(vf, msg);
 		break;
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.h b/drivers/net/ethernet/intel/ice/ice_virtchnl.h
index cd747718de73..60dfbe05980a 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.h
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.h
@@ -32,6 +32,7 @@ struct ice_virtchnl_ops {
 	int (*cfg_irq_map_msg)(struct ice_vf *vf, u8 *msg);
 	int (*config_rss_key)(struct ice_vf *vf, u8 *msg);
 	int (*config_rss_lut)(struct ice_vf *vf, u8 *msg);
+	int (*config_rss_hfunc)(struct ice_vf *vf, u8 *msg);
 	int (*get_stats_msg)(struct ice_vf *vf, u8 *msg);
 	int (*cfg_promiscuous_mode_msg)(struct ice_vf *vf, u8 *msg);
 	int (*add_vlan_msg)(struct ice_vf *vf, u8 *msg);
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
index 7d547fa616fa..5e19d48a05b4 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
@@ -68,6 +68,7 @@ static const u32 vlan_v2_allowlist_opcodes[] = {
 static const u32 rss_pf_allowlist_opcodes[] = {
 	VIRTCHNL_OP_CONFIG_RSS_KEY, VIRTCHNL_OP_CONFIG_RSS_LUT,
 	VIRTCHNL_OP_GET_RSS_HENA_CAPS, VIRTCHNL_OP_SET_RSS_HENA,
+	VIRTCHNL_OP_CONFIG_RSS_HFUNC,
 };
 
 /* VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC */
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
index 24b23b7ef04a..f001553e1a1a 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
@@ -10,19 +10,6 @@
 #define to_fltr_conf_from_desc(p) \
 	container_of(p, struct virtchnl_fdir_fltr_conf, input)
 
-#define ICE_FLOW_PROF_TYPE_S	0
-#define ICE_FLOW_PROF_TYPE_M	(0xFFFFFFFFULL << ICE_FLOW_PROF_TYPE_S)
-#define ICE_FLOW_PROF_VSI_S	32
-#define ICE_FLOW_PROF_VSI_M	(0xFFFFFFFFULL << ICE_FLOW_PROF_VSI_S)
-
-/* Flow profile ID format:
- * [0:31] - flow type, flow + tun_offs
- * [32:63] - VSI index
- */
-#define ICE_FLOW_PROF_FD(vsi, flow, tun_offs) \
-	((u64)(((((flow) + (tun_offs)) & ICE_FLOW_PROF_TYPE_M)) | \
-	      (((u64)(vsi) << ICE_FLOW_PROF_VSI_S) & ICE_FLOW_PROF_VSI_M)))
-
 #define GTPU_TEID_OFFSET 4
 #define GTPU_EH_QFI_OFFSET 1
 #define GTPU_EH_QFI_MASK 0x3F
@@ -493,6 +480,7 @@ ice_vc_fdir_rem_prof(struct ice_vf *vf, enum ice_fltr_ptype flow, int tun)
 		return;
 
 	vf_prof = fdir->fdir_prof[flow];
+	prof_id = vf_prof->prof_id[tun];
 
 	vf_vsi = ice_get_vf_vsi(vf);
 	if (!vf_vsi) {
@@ -503,9 +491,6 @@ ice_vc_fdir_rem_prof(struct ice_vf *vf, enum ice_fltr_ptype flow, int tun)
 	if (!fdir->prof_entry_cnt[flow][tun])
 		return;
 
-	prof_id = ICE_FLOW_PROF_FD(vf_vsi->vsi_num,
-				   flow, tun ? ICE_FLTR_PTYPE_MAX : 0);
-
 	for (i = 0; i < fdir->prof_entry_cnt[flow][tun]; i++)
 		if (vf_prof->entry_h[i][tun]) {
 			u16 vsi_num = ice_get_hw_vsi_num(hw, vf_prof->vsi_h[i]);
@@ -647,7 +632,6 @@ ice_vc_fdir_write_flow_prof(struct ice_vf *vf, enum ice_fltr_ptype flow,
 	struct ice_hw *hw;
 	u64 entry1_h = 0;
 	u64 entry2_h = 0;
-	u64 prof_id;
 	int ret;
 
 	pf = vf->pf;
@@ -681,18 +665,15 @@ ice_vc_fdir_write_flow_prof(struct ice_vf *vf, enum ice_fltr_ptype flow,
 		ice_vc_fdir_rem_prof(vf, flow, tun);
 	}
 
-	prof_id = ICE_FLOW_PROF_FD(vf_vsi->vsi_num, flow,
-				   tun ? ICE_FLTR_PTYPE_MAX : 0);
-
-	ret = ice_flow_add_prof(hw, ICE_BLK_FD, ICE_FLOW_RX, prof_id, seg,
-				tun + 1, &prof);
+	ret = ice_flow_add_prof(hw, ICE_BLK_FD, ICE_FLOW_RX, seg,
+				tun + 1, false, &prof);
 	if (ret) {
 		dev_dbg(dev, "Could not add VSI flow 0x%x for VF %d\n",
 			flow, vf->vf_id);
 		goto err_exit;
 	}
 
-	ret = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, vf_vsi->idx,
+	ret = ice_flow_add_entry(hw, ICE_BLK_FD, prof->id, vf_vsi->idx,
 				 vf_vsi->idx, ICE_FLOW_PRIO_NORMAL,
 				 seg, &entry1_h);
 	if (ret) {
@@ -701,7 +682,7 @@ ice_vc_fdir_write_flow_prof(struct ice_vf *vf, enum ice_fltr_ptype flow,
 		goto err_prof;
 	}
 
-	ret = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, vf_vsi->idx,
+	ret = ice_flow_add_entry(hw, ICE_BLK_FD, prof->id, vf_vsi->idx,
 				 ctrl_vsi->idx, ICE_FLOW_PRIO_NORMAL,
 				 seg, &entry2_h);
 	if (ret) {
@@ -725,14 +706,16 @@ ice_vc_fdir_write_flow_prof(struct ice_vf *vf, enum ice_fltr_ptype flow,
 	vf_prof->cnt++;
 	fdir->prof_entry_cnt[flow][tun]++;
 
+	vf_prof->prof_id[tun] = prof->id;
+
 	return 0;
 
 err_entry_1:
 	ice_rem_prof_id_flow(hw, ICE_BLK_FD,
-			     ice_get_hw_vsi_num(hw, vf_vsi->idx), prof_id);
+			     ice_get_hw_vsi_num(hw, vf_vsi->idx), prof->id);
 	ice_flow_rem_entry(hw, ICE_BLK_FD, entry1_h);
 err_prof:
-	ice_flow_rem_prof(hw, ICE_BLK_FD, prof_id);
+	ice_flow_rem_prof(hw, ICE_BLK_FD, prof->id);
 err_exit:
 	return ret;
 }
@@ -1480,16 +1463,15 @@ ice_vf_verify_rx_desc(struct ice_vf *vf, struct ice_vf_fdir_ctx *ctx,
 	int ret;
 
 	stat_err = le16_to_cpu(ctx->rx_desc.wb.status_error0);
-	if (((stat_err & ICE_FXD_FLTR_WB_QW1_DD_M) >>
-	    ICE_FXD_FLTR_WB_QW1_DD_S) != ICE_FXD_FLTR_WB_QW1_DD_YES) {
+	if (FIELD_GET(ICE_FXD_FLTR_WB_QW1_DD_M, stat_err) !=
+	    ICE_FXD_FLTR_WB_QW1_DD_YES) {
 		*status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE;
 		dev_err(dev, "VF %d: Desc Done not set\n", vf->vf_id);
 		ret = -EINVAL;
 		goto err_exit;
 	}
 
-	prog_id = (stat_err & ICE_FXD_FLTR_WB_QW1_PROG_ID_M) >>
-		ICE_FXD_FLTR_WB_QW1_PROG_ID_S;
+	prog_id = FIELD_GET(ICE_FXD_FLTR_WB_QW1_PROG_ID_M, stat_err);
 	if (prog_id == ICE_FXD_FLTR_WB_QW1_PROG_ADD &&
 	    ctx->v_opcode != VIRTCHNL_OP_ADD_FDIR_FILTER) {
 		dev_err(dev, "VF %d: Desc show add, but ctx not",
@@ -1508,8 +1490,7 @@ ice_vf_verify_rx_desc(struct ice_vf *vf, struct ice_vf_fdir_ctx *ctx,
 		goto err_exit;
 	}
 
-	error = (stat_err & ICE_FXD_FLTR_WB_QW1_FAIL_M) >>
-		ICE_FXD_FLTR_WB_QW1_FAIL_S;
+	error = FIELD_GET(ICE_FXD_FLTR_WB_QW1_FAIL_M, stat_err);
 	if (error == ICE_FXD_FLTR_WB_QW1_FAIL_YES) {
 		if (prog_id == ICE_FXD_FLTR_WB_QW1_PROG_ADD) {
 			dev_err(dev, "VF %d, Failed to add FDIR rule due to no space in the table",
@@ -1524,8 +1505,7 @@ ice_vf_verify_rx_desc(struct ice_vf *vf, struct ice_vf_fdir_ctx *ctx,
 		goto err_exit;
 	}
 
-	error = (stat_err & ICE_FXD_FLTR_WB_QW1_FAIL_PROF_M) >>
-		ICE_FXD_FLTR_WB_QW1_FAIL_PROF_S;
+	error = FIELD_GET(ICE_FXD_FLTR_WB_QW1_FAIL_PROF_M, stat_err);
 	if (error == ICE_FXD_FLTR_WB_QW1_FAIL_PROF_YES) {
 		dev_err(dev, "VF %d: Profile matching error", vf->vf_id);
 		*status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE;
diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c
index 76266e709a39..2e9ad27cb9d1 100644
--- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c
@@ -131,6 +131,7 @@ static int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena)
 {
 	struct ice_hw *hw = &vsi->back->hw;
 	struct ice_vsi_ctx *ctxt;
+	u8 *ivf;
 	int err;
 
 	/* do not allow modifying VLAN stripping when a port VLAN is configured
@@ -143,19 +144,24 @@ static int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena)
 	if (!ctxt)
 		return -ENOMEM;
 
+	ivf = &ctxt->info.inner_vlan_flags;
+
 	/* Here we are configuring what the VSI should do with the VLAN tag in
 	 * the Rx packet. We can either leave the tag in the packet or put it in
 	 * the Rx descriptor.
 	 */
-	if (ena)
+	if (ena) {
 		/* Strip VLAN tag from Rx packet and put it in the desc */
-		ctxt->info.inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_EMODE_STR_BOTH;
-	else
+		*ivf = FIELD_PREP(ICE_AQ_VSI_INNER_VLAN_EMODE_M,
+				  ICE_AQ_VSI_INNER_VLAN_EMODE_STR_BOTH);
+	} else {
 		/* Disable stripping. Leave tag in packet */
-		ctxt->info.inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING;
+		*ivf = FIELD_PREP(ICE_AQ_VSI_INNER_VLAN_EMODE_M,
+				  ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING);
+	}
 
 	/* Allow all packets untagged/tagged */
-	ctxt->info.inner_vlan_flags |= ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL;
+	*ivf |= ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL;
 
 	ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID);
 
@@ -481,10 +487,11 @@ int ice_vsi_ena_outer_stripping(struct ice_vsi *vsi, u16 tpid)
 	ctxt->info.outer_vlan_flags = vsi->info.outer_vlan_flags &
 		~(ICE_AQ_VSI_OUTER_VLAN_EMODE_M | ICE_AQ_VSI_OUTER_TAG_TYPE_M);
 	ctxt->info.outer_vlan_flags |=
-		((ICE_AQ_VSI_OUTER_VLAN_EMODE_SHOW_BOTH <<
-		  ICE_AQ_VSI_OUTER_VLAN_EMODE_S) |
-		 ((tag_type << ICE_AQ_VSI_OUTER_TAG_TYPE_S) &
-		  ICE_AQ_VSI_OUTER_TAG_TYPE_M));
+		/* we want EMODE_SHOW_BOTH, but that value is zero, so the line
+		 * above clears it well enough that we don't need to try to set
+		 * zero here, so just do the tag type
+		 */
+		 FIELD_PREP(ICE_AQ_VSI_OUTER_TAG_TYPE_M, tag_type);
 
 	err = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (err)
@@ -589,11 +596,9 @@ int ice_vsi_ena_outer_insertion(struct ice_vsi *vsi, u16 tpid)
 		  ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M |
 		  ICE_AQ_VSI_OUTER_TAG_TYPE_M);
 	ctxt->info.outer_vlan_flags |=
-		((ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL <<
-		  ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) &
-		 ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M) |
-		((tag_type << ICE_AQ_VSI_OUTER_TAG_TYPE_S) &
-		 ICE_AQ_VSI_OUTER_TAG_TYPE_M);
+		FIELD_PREP(ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M,
+			   ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL) |
+		FIELD_PREP(ICE_AQ_VSI_OUTER_TAG_TYPE_M, tag_type);
 
 	err = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (err)
@@ -642,9 +647,8 @@ int ice_vsi_dis_outer_insertion(struct ice_vsi *vsi)
 		  ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M);
 	ctxt->info.outer_vlan_flags |=
 		ICE_AQ_VSI_OUTER_VLAN_BLOCK_TX_DESC |
-		((ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL <<
-		  ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) &
-		 ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M);
+		FIELD_PREP(ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M,
+			   ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL);
 
 	err = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (err)
@@ -702,8 +706,7 @@ __ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, u16 vlan_info, u16 tpid)
 	ctxt->info.outer_vlan_flags =
 		(ICE_AQ_VSI_OUTER_VLAN_EMODE_SHOW <<
 		 ICE_AQ_VSI_OUTER_VLAN_EMODE_S) |
-		((tag_type << ICE_AQ_VSI_OUTER_TAG_TYPE_S) &
-		 ICE_AQ_VSI_OUTER_TAG_TYPE_M) |
+		FIELD_PREP(ICE_AQ_VSI_OUTER_TAG_TYPE_M, tag_type) |
 		ICE_AQ_VSI_OUTER_VLAN_BLOCK_TX_DESC |
 		(ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ACCEPTUNTAGGED <<
 		 ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) |
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 99954508184f..5d1ae8e4058a 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -458,6 +458,11 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
 		rx_desc->read.pkt_addr = cpu_to_le64(dma);
 		rx_desc->wb.status_error0 = 0;
 
+		/* Put private info that changes on a per-packet basis
+		 * into xdp_buff_xsk->cb.
+		 */
+		ice_xdp_meta_set_desc(*xdp, rx_desc);
+
 		rx_desc++;
 		xdp++;
 	}
@@ -863,8 +868,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		struct xdp_buff *xdp;
 		struct sk_buff *skb;
 		u16 stat_err_bits;
-		u16 vlan_tag = 0;
-		u16 rx_ptype;
+		u16 vlan_tci;
 
 		rx_desc = ICE_RX_DESC(rx_ring, ntc);
 
@@ -942,13 +946,10 @@ construct_skb:
 		total_rx_bytes += skb->len;
 		total_rx_packets++;
 
-		vlan_tag = ice_get_vlan_tag_from_rx_desc(rx_desc);
-
-		rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) &
-				       ICE_RX_FLEX_DESC_PTYPE_M;
+		vlan_tci = ice_get_vlan_tci(rx_desc);
 
-		ice_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
-		ice_receive_skb(rx_ring, skb, vlan_tag);
+		ice_process_skb_fields(rx_ring, rx_desc, skb);
+		ice_receive_skb(rx_ring, skb, vlan_tci);
 	}
 
 	rx_ring->next_to_clean = ntc;
diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h
index bee73353b56a..0acc125decb3 100644
--- a/drivers/net/ethernet/intel/idpf/idpf.h
+++ b/drivers/net/ethernet/intel/idpf/idpf.h
@@ -15,7 +15,7 @@ struct idpf_vport_max_q;
 #include <linux/pci.h>
 #include <linux/bitfield.h>
 #include <linux/sctp.h>
-#include <linux/ethtool.h>
+#include <linux/ethtool_netlink.h>
 #include <net/gro.h>
 #include <linux/dim.h>
 
@@ -418,11 +418,13 @@ struct idpf_vport {
 
 /**
  * enum idpf_user_flags
+ * @__IDPF_USER_FLAG_HSPLIT: header split state
  * @__IDPF_PROMISC_UC: Unicast promiscuous mode
  * @__IDPF_PROMISC_MC: Multicast promiscuous mode
  * @__IDPF_USER_FLAGS_NBITS: Must be last
  */
 enum idpf_user_flags {
+	__IDPF_USER_FLAG_HSPLIT = 0U,
 	__IDPF_PROMISC_UC = 32,
 	__IDPF_PROMISC_MC,
 
@@ -965,4 +967,7 @@ int idpf_send_map_unmap_queue_vector_msg(struct idpf_vport *vport, bool map);
 int idpf_send_set_sriov_vfs_msg(struct idpf_adapter *adapter, u16 num_vfs);
 int idpf_sriov_configure(struct pci_dev *pdev, int num_vfs);
 
+u8 idpf_vport_get_hsplit(const struct idpf_vport *vport);
+bool idpf_vport_set_hsplit(const struct idpf_vport *vport, u8 val);
+
 #endif /* !_IDPF_H_ */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
index 52ea38669f85..986d429d1175 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
@@ -75,14 +75,12 @@ static u32 idpf_get_rxfh_indir_size(struct net_device *netdev)
 /**
  * idpf_get_rxfh - get the rx flow hash indirection table
  * @netdev: network interface device structure
- * @indir: indirection table
- * @key: hash key
- * @hfunc: hash function in use
+ * @rxfh: pointer to param struct (indir, key, hfunc)
  *
  * Reads the indirection table directly from the hardware. Always returns 0.
  */
-static int idpf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			 u8 *hfunc)
+static int idpf_get_rxfh(struct net_device *netdev,
+			 struct ethtool_rxfh_param *rxfh)
 {
 	struct idpf_netdev_priv *np = netdev_priv(netdev);
 	struct idpf_rss_data *rss_data;
@@ -103,15 +101,14 @@ static int idpf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 	if (np->state != __IDPF_VPORT_UP)
 		goto unlock_mutex;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
-	if (key)
-		memcpy(key, rss_data->rss_key, rss_data->rss_key_size);
+	if (rxfh->key)
+		memcpy(rxfh->key, rss_data->rss_key, rss_data->rss_key_size);
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < rss_data->rss_lut_size; i++)
-			indir[i] = rss_data->rss_lut[i];
+			rxfh->indir[i] = rss_data->rss_lut[i];
 	}
 
 unlock_mutex:
@@ -123,15 +120,15 @@ unlock_mutex:
 /**
  * idpf_set_rxfh - set the rx flow hash indirection table
  * @netdev: network interface device structure
- * @indir: indirection table
- * @key: hash key
- * @hfunc: hash function to use
+ * @rxfh: pointer to param struct (indir, key, hfunc)
+ * @extack: extended ACK from the Netlink message
  *
  * Returns -EINVAL if the table specifies an invalid queue id, otherwise
  * returns 0 after programming the table.
  */
-static int idpf_set_rxfh(struct net_device *netdev, const u32 *indir,
-			 const u8 *key, const u8 hfunc)
+static int idpf_set_rxfh(struct net_device *netdev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
 	struct idpf_netdev_priv *np = netdev_priv(netdev);
 	struct idpf_rss_data *rss_data;
@@ -154,17 +151,18 @@ static int idpf_set_rxfh(struct net_device *netdev, const u32 *indir,
 	if (np->state != __IDPF_VPORT_UP)
 		goto unlock_mutex;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) {
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP) {
 		err = -EOPNOTSUPP;
 		goto unlock_mutex;
 	}
 
-	if (key)
-		memcpy(rss_data->rss_key, key, rss_data->rss_key_size);
+	if (rxfh->key)
+		memcpy(rss_data->rss_key, rxfh->key, rss_data->rss_key_size);
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (lut = 0; lut < rss_data->rss_lut_size; lut++)
-			rss_data->rss_lut[lut] = indir[lut];
+			rss_data->rss_lut[lut] = rxfh->indir[lut];
 	}
 
 	err = idpf_config_rss(vport);
@@ -320,6 +318,8 @@ static void idpf_get_ringparam(struct net_device *netdev,
 	ring->rx_pending = vport->rxq_desc_count;
 	ring->tx_pending = vport->txq_desc_count;
 
+	kring->tcp_data_split = idpf_vport_get_hsplit(vport);
+
 	idpf_vport_ctrl_unlock(netdev);
 }
 
@@ -379,6 +379,14 @@ static int idpf_set_ringparam(struct net_device *netdev,
 	    new_rx_count == vport->rxq_desc_count)
 		goto unlock_mutex;
 
+	if (!idpf_vport_set_hsplit(vport, kring->tcp_data_split)) {
+		NL_SET_ERR_MSG_MOD(ext_ack,
+				   "setting TCP data split is not supported");
+		err = -EOPNOTSUPP;
+
+		goto unlock_mutex;
+	}
+
 	config_data = &vport->adapter->vport_config[idx]->user_config;
 	config_data->num_req_txq_desc = new_tx_count;
 	config_data->num_req_rxq_desc = new_rx_count;
@@ -532,7 +540,7 @@ static void idpf_add_stat_strings(u8 **p, const struct idpf_stats *stats,
 	unsigned int i;
 
 	for (i = 0; i < size; i++)
-		ethtool_sprintf(p, "%s", stats[i].stat_string);
+		ethtool_puts(p, stats[i].stat_string);
 }
 
 /**
@@ -1334,6 +1342,7 @@ static int idpf_get_link_ksettings(struct net_device *netdev,
 static const struct ethtool_ops idpf_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE,
+	.supported_ring_params	= ETHTOOL_RING_USE_TCP_DATA_SPLIT,
 	.get_msglevel		= idpf_get_msglevel,
 	.set_msglevel		= idpf_set_msglevel,
 	.get_link		= ethtool_op_get_link,
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index 19809b0ddcd9..5fea2fd957eb 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -1058,6 +1058,71 @@ static void idpf_vport_dealloc(struct idpf_vport *vport)
 }
 
 /**
+ * idpf_is_hsplit_supported - check whether the header split is supported
+ * @vport: virtual port to check the capability for
+ *
+ * Return: true if it's supported by the HW/FW, false if not.
+ */
+static bool idpf_is_hsplit_supported(const struct idpf_vport *vport)
+{
+	return idpf_is_queue_model_split(vport->rxq_model) &&
+	       idpf_is_cap_ena_all(vport->adapter, IDPF_HSPLIT_CAPS,
+				   IDPF_CAP_HSPLIT);
+}
+
+/**
+ * idpf_vport_get_hsplit - get the current header split feature state
+ * @vport: virtual port to query the state for
+ *
+ * Return: ``ETHTOOL_TCP_DATA_SPLIT_UNKNOWN`` if not supported,
+ *         ``ETHTOOL_TCP_DATA_SPLIT_DISABLED`` if disabled,
+ *         ``ETHTOOL_TCP_DATA_SPLIT_ENABLED`` if active.
+ */
+u8 idpf_vport_get_hsplit(const struct idpf_vport *vport)
+{
+	const struct idpf_vport_user_config_data *config;
+
+	if (!idpf_is_hsplit_supported(vport))
+		return ETHTOOL_TCP_DATA_SPLIT_UNKNOWN;
+
+	config = &vport->adapter->vport_config[vport->idx]->user_config;
+
+	return test_bit(__IDPF_USER_FLAG_HSPLIT, config->user_flags) ?
+	       ETHTOOL_TCP_DATA_SPLIT_ENABLED :
+	       ETHTOOL_TCP_DATA_SPLIT_DISABLED;
+}
+
+/**
+ * idpf_vport_set_hsplit - enable or disable header split on a given vport
+ * @vport: virtual port to configure
+ * @val: Ethtool flag controlling the header split state
+ *
+ * Return: true on success, false if not supported by the HW.
+ */
+bool idpf_vport_set_hsplit(const struct idpf_vport *vport, u8 val)
+{
+	struct idpf_vport_user_config_data *config;
+
+	if (!idpf_is_hsplit_supported(vport))
+		return val == ETHTOOL_TCP_DATA_SPLIT_UNKNOWN;
+
+	config = &vport->adapter->vport_config[vport->idx]->user_config;
+
+	switch (val) {
+	case ETHTOOL_TCP_DATA_SPLIT_UNKNOWN:
+		/* Default is to enable */
+	case ETHTOOL_TCP_DATA_SPLIT_ENABLED:
+		__set_bit(__IDPF_USER_FLAG_HSPLIT, config->user_flags);
+		return true;
+	case ETHTOOL_TCP_DATA_SPLIT_DISABLED:
+		__clear_bit(__IDPF_USER_FLAG_HSPLIT, config->user_flags);
+		return true;
+	default:
+		return false;
+	}
+}
+
+/**
  * idpf_vport_alloc - Allocates the next available struct vport in the adapter
  * @adapter: board private structure
  * @max_q: vport max queue info
diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
index 81288a17da2a..27b93592c4ba 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
@@ -328,10 +328,9 @@ static void idpf_tx_singleq_build_ctx_desc(struct idpf_queue *txq,
 
 	if (offload->tso_segs) {
 		qw1 |= IDPF_TX_CTX_DESC_TSO << IDPF_TXD_CTX_QW1_CMD_S;
-		qw1 |= ((u64)offload->tso_len << IDPF_TXD_CTX_QW1_TSO_LEN_S) &
-			IDPF_TXD_CTX_QW1_TSO_LEN_M;
-		qw1 |= ((u64)offload->mss << IDPF_TXD_CTX_QW1_MSS_S) &
-			IDPF_TXD_CTX_QW1_MSS_M;
+		qw1 |= FIELD_PREP(IDPF_TXD_CTX_QW1_TSO_LEN_M,
+				  offload->tso_len);
+		qw1 |= FIELD_PREP(IDPF_TXD_CTX_QW1_MSS_M, offload->mss);
 
 		u64_stats_update_begin(&txq->stats_sync);
 		u64_stats_inc(&txq->q_stats.tx.lso_pkts);
@@ -1044,7 +1043,6 @@ static int idpf_rx_singleq_clean(struct idpf_queue *rx_q, int budget)
 		}
 
 		idpf_rx_sync_for_cpu(rx_buf, fields.size);
-		skb = rx_q->skb;
 		if (skb)
 			idpf_rx_add_frag(rx_buf, skb, fields.size);
 		else
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 1f728a9004d9..2f8ad79ae3f0 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -396,7 +396,7 @@ static void idpf_rx_desc_rel(struct idpf_queue *rxq, bool bufq, s32 q_model)
 	if (!rxq)
 		return;
 
-	if (!bufq && idpf_is_queue_model_split(q_model) && rxq->skb) {
+	if (rxq->skb) {
 		dev_kfree_skb_any(rxq->skb);
 		rxq->skb = NULL;
 	}
@@ -505,9 +505,9 @@ static void idpf_rx_post_buf_refill(struct idpf_sw_queue *refillq, u16 buf_id)
 
 	/* store the buffer ID and the SW maintained GEN bit to the refillq */
 	refillq->ring[nta] =
-		((buf_id << IDPF_RX_BI_BUFID_S) & IDPF_RX_BI_BUFID_M) |
-		(!!(test_bit(__IDPF_Q_GEN_CHK, refillq->flags)) <<
-		 IDPF_RX_BI_GEN_S);
+		FIELD_PREP(IDPF_RX_BI_BUFID_M, buf_id) |
+		FIELD_PREP(IDPF_RX_BI_GEN_M,
+			   test_bit(__IDPF_Q_GEN_CHK, refillq->flags));
 
 	if (unlikely(++nta == refillq->desc_count)) {
 		nta = 0;
@@ -1240,12 +1240,15 @@ static int idpf_rxq_group_alloc(struct idpf_vport *vport, u16 num_rxq)
 	struct idpf_adapter *adapter = vport->adapter;
 	struct idpf_queue *q;
 	int i, k, err = 0;
+	bool hs;
 
 	vport->rxq_grps = kcalloc(vport->num_rxq_grp,
 				  sizeof(struct idpf_rxq_group), GFP_KERNEL);
 	if (!vport->rxq_grps)
 		return -ENOMEM;
 
+	hs = idpf_vport_get_hsplit(vport) == ETHTOOL_TCP_DATA_SPLIT_ENABLED;
+
 	for (i = 0; i < vport->num_rxq_grp; i++) {
 		struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i];
 		int j;
@@ -1298,9 +1301,8 @@ static int idpf_rxq_group_alloc(struct idpf_vport *vport, u16 num_rxq)
 			q->rx_buf_size = vport->bufq_size[j];
 			q->rx_buffer_low_watermark = IDPF_LOW_WATERMARK;
 			q->rx_buf_stride = IDPF_RX_BUF_STRIDE;
-			if (idpf_is_cap_ena_all(adapter, IDPF_HSPLIT_CAPS,
-						IDPF_CAP_HSPLIT) &&
-			    idpf_is_queue_model_split(vport->rxq_model)) {
+
+			if (hs) {
 				q->rx_hsplit_en = true;
 				q->rx_hbuf_size = IDPF_HDR_BUF_SIZE;
 			}
@@ -1344,9 +1346,7 @@ skip_splitq_rx_init:
 				rx_qgrp->splitq.rxq_sets[j]->refillq1 =
 				      &rx_qgrp->splitq.bufq_sets[1].refillqs[j];
 
-			if (idpf_is_cap_ena_all(adapter, IDPF_HSPLIT_CAPS,
-						IDPF_CAP_HSPLIT) &&
-			    idpf_is_queue_model_split(vport->rxq_model)) {
+			if (hs) {
 				q->rx_hsplit_en = true;
 				q->rx_hbuf_size = IDPF_HDR_BUF_SIZE;
 			}
@@ -1825,14 +1825,14 @@ static bool idpf_tx_clean_complq(struct idpf_queue *complq, int budget,
 		u16 gen;
 
 		/* if the descriptor isn't done, no work yet to do */
-		gen = (le16_to_cpu(tx_desc->qid_comptype_gen) &
-		      IDPF_TXD_COMPLQ_GEN_M) >> IDPF_TXD_COMPLQ_GEN_S;
+		gen = le16_get_bits(tx_desc->qid_comptype_gen,
+				    IDPF_TXD_COMPLQ_GEN_M);
 		if (test_bit(__IDPF_Q_GEN_CHK, complq->flags) != gen)
 			break;
 
 		/* Find necessary info of TX queue to clean buffers */
-		rel_tx_qid = (le16_to_cpu(tx_desc->qid_comptype_gen) &
-			 IDPF_TXD_COMPLQ_QID_M) >> IDPF_TXD_COMPLQ_QID_S;
+		rel_tx_qid = le16_get_bits(tx_desc->qid_comptype_gen,
+					   IDPF_TXD_COMPLQ_QID_M);
 		if (rel_tx_qid >= complq->txq_grp->num_txq ||
 		    !complq->txq_grp->txqs[rel_tx_qid]) {
 			dev_err(&complq->vport->adapter->pdev->dev,
@@ -1842,9 +1842,8 @@ static bool idpf_tx_clean_complq(struct idpf_queue *complq, int budget,
 		tx_q = complq->txq_grp->txqs[rel_tx_qid];
 
 		/* Determine completion type */
-		ctype = (le16_to_cpu(tx_desc->qid_comptype_gen) &
-			IDPF_TXD_COMPLQ_COMPL_TYPE_M) >>
-			IDPF_TXD_COMPLQ_COMPL_TYPE_S;
+		ctype = le16_get_bits(tx_desc->qid_comptype_gen,
+				      IDPF_TXD_COMPLQ_COMPL_TYPE_M);
 		switch (ctype) {
 		case IDPF_TXD_COMPLT_RE:
 			hw_head = le16_to_cpu(tx_desc->q_head_compl_tag.q_head);
@@ -1945,11 +1944,10 @@ void idpf_tx_splitq_build_ctb(union idpf_tx_flex_desc *desc,
 			      u16 td_cmd, u16 size)
 {
 	desc->q.qw1.cmd_dtype =
-		cpu_to_le16(params->dtype & IDPF_FLEX_TXD_QW1_DTYPE_M);
+		le16_encode_bits(params->dtype, IDPF_FLEX_TXD_QW1_DTYPE_M);
 	desc->q.qw1.cmd_dtype |=
-		cpu_to_le16((td_cmd << IDPF_FLEX_TXD_QW1_CMD_S) &
-			    IDPF_FLEX_TXD_QW1_CMD_M);
-	desc->q.qw1.buf_size = cpu_to_le16((u16)size);
+		le16_encode_bits(td_cmd, IDPF_FLEX_TXD_QW1_CMD_M);
+	desc->q.qw1.buf_size = cpu_to_le16(size);
 	desc->q.qw1.l2tags.l2tag1 = cpu_to_le16(params->td_tag);
 }
 
@@ -2843,8 +2841,9 @@ static void idpf_rx_splitq_extract_csum_bits(struct virtchnl2_rx_flex_desc_adv_n
 				qword1);
 	csum->ipv6exadd = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_IPV6EXADD_M,
 				    qword0);
-	csum->raw_csum_inv = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_RAW_CSUM_INV_M,
-				       le16_to_cpu(rx_desc->ptype_err_fflags0));
+	csum->raw_csum_inv =
+		le16_get_bits(rx_desc->ptype_err_fflags0,
+			      VIRTCHNL2_RX_FLEX_DESC_ADV_RAW_CSUM_INV_M);
 	csum->raw_csum = le16_to_cpu(rx_desc->misc.raw_cs);
 }
 
@@ -2938,8 +2937,8 @@ static int idpf_rx_process_skb_fields(struct idpf_queue *rxq,
 	struct idpf_rx_ptype_decoded decoded;
 	u16 rx_ptype;
 
-	rx_ptype = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_PTYPE_M,
-			     le16_to_cpu(rx_desc->ptype_err_fflags0));
+	rx_ptype = le16_get_bits(rx_desc->ptype_err_fflags0,
+				 VIRTCHNL2_RX_FLEX_DESC_ADV_PTYPE_M);
 
 	decoded = rxq->vport->rx_ptype_lkup[rx_ptype];
 	/* If we don't know the ptype we can't do anything else with it. Just
@@ -2953,8 +2952,8 @@ static int idpf_rx_process_skb_fields(struct idpf_queue *rxq,
 
 	skb->protocol = eth_type_trans(skb, rxq->vport->netdev);
 
-	if (FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_RSC_M,
-		      le16_to_cpu(rx_desc->hdrlen_flags)))
+	if (le16_get_bits(rx_desc->hdrlen_flags,
+			  VIRTCHNL2_RX_FLEX_DESC_ADV_RSC_M))
 		return idpf_rx_rsc(rxq, skb, rx_desc, &decoded);
 
 	idpf_rx_splitq_extract_csum_bits(rx_desc, &csum_bits);
@@ -3148,8 +3147,8 @@ static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget)
 		dma_rmb();
 
 		/* if the descriptor isn't done, no work yet to do */
-		gen_id = le16_to_cpu(rx_desc->pktlen_gen_bufq_id);
-		gen_id = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_GEN_M, gen_id);
+		gen_id = le16_get_bits(rx_desc->pktlen_gen_bufq_id,
+				       VIRTCHNL2_RX_FLEX_DESC_ADV_GEN_M);
 
 		if (test_bit(__IDPF_Q_GEN_CHK, rxq->flags) != gen_id)
 			break;
@@ -3164,9 +3163,8 @@ static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget)
 			continue;
 		}
 
-		pkt_len = le16_to_cpu(rx_desc->pktlen_gen_bufq_id);
-		pkt_len = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_LEN_PBUF_M,
-				    pkt_len);
+		pkt_len = le16_get_bits(rx_desc->pktlen_gen_bufq_id,
+					VIRTCHNL2_RX_FLEX_DESC_ADV_LEN_PBUF_M);
 
 		hbo = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_HBO_M,
 				rx_desc->status_err0_qw1);
@@ -3183,14 +3181,12 @@ static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget)
 			goto bypass_hsplit;
 		}
 
-		hdr_len = le16_to_cpu(rx_desc->hdrlen_flags);
-		hdr_len = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_LEN_HDR_M,
-				    hdr_len);
+		hdr_len = le16_get_bits(rx_desc->hdrlen_flags,
+					VIRTCHNL2_RX_FLEX_DESC_ADV_LEN_HDR_M);
 
 bypass_hsplit:
-		bufq_id = le16_to_cpu(rx_desc->pktlen_gen_bufq_id);
-		bufq_id = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_BUFQ_ID_M,
-				    bufq_id);
+		bufq_id = le16_get_bits(rx_desc->pktlen_gen_bufq_id,
+					VIRTCHNL2_RX_FLEX_DESC_ADV_BUFQ_ID_M);
 
 		rxq_set = container_of(rxq, struct idpf_rxq_set, rxq);
 		if (!bufq_id)
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index 2c1b051fdc0d..d0cdd63b3d5b 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -3285,6 +3285,8 @@ void idpf_vport_init(struct idpf_vport *vport, struct idpf_vport_max_q *max_q)
 	memcpy(vport->rx_itr_profile, rx_itr, IDPF_DIM_PROFILE_SLOTS);
 	memcpy(vport->tx_itr_profile, tx_itr, IDPF_DIM_PROFILE_SLOTS);
 
+	idpf_vport_set_hsplit(vport, ETHTOOL_TCP_DATA_SPLIT_ENABLED);
+
 	idpf_vport_init_num_qs(vport, vport_msg);
 	idpf_vport_calc_num_q_desc(vport);
 	idpf_vport_calc_num_q_groups(vport);
diff --git a/drivers/net/ethernet/intel/idpf/virtchnl2.h b/drivers/net/ethernet/intel/idpf/virtchnl2.h
index 07e72c72d156..8dc837889723 100644
--- a/drivers/net/ethernet/intel/idpf/virtchnl2.h
+++ b/drivers/net/ethernet/intel/idpf/virtchnl2.h
@@ -1104,9 +1104,9 @@ struct virtchnl2_rss_key {
 	__le32 vport_id;
 	__le16 key_len;
 	u8 pad;
-	__DECLARE_FLEX_ARRAY(u8, key_flex);
-};
-VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_rss_key);
+	u8 key_flex[];
+} __packed;
+VIRTCHNL2_CHECK_STRUCT_LEN(7, virtchnl2_rss_key);
 
 /**
  * struct virtchnl2_queue_chunk - chunk of contiguous queues
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index 8d6e44ee1895..64dfc362d1dc 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -222,8 +222,7 @@ static s32 igb_init_phy_params_82575(struct e1000_hw *hw)
 	}
 
 	/* set lan id */
-	hw->bus.func = (rd32(E1000_STATUS) & E1000_STATUS_FUNC_MASK) >>
-			E1000_STATUS_FUNC_SHIFT;
+	hw->bus.func = FIELD_GET(E1000_STATUS_FUNC_MASK, rd32(E1000_STATUS));
 
 	/* Set phy->phy_addr and phy->id. */
 	ret_val = igb_get_phy_id_82575(hw);
@@ -262,8 +261,8 @@ static s32 igb_init_phy_params_82575(struct e1000_hw *hw)
 			if (ret_val)
 				goto out;
 
-			data = (data & E1000_M88E1112_MAC_CTRL_1_MODE_MASK) >>
-			       E1000_M88E1112_MAC_CTRL_1_MODE_SHIFT;
+			data = FIELD_GET(E1000_M88E1112_MAC_CTRL_1_MODE_MASK,
+					 data);
 			if (data == E1000_M88E1112_AUTO_COPPER_SGMII ||
 			    data == E1000_M88E1112_AUTO_COPPER_BASEX)
 				hw->mac.ops.check_for_link =
@@ -330,8 +329,7 @@ static s32 igb_init_nvm_params_82575(struct e1000_hw *hw)
 	u32 eecd = rd32(E1000_EECD);
 	u16 size;
 
-	size = (u16)((eecd & E1000_EECD_SIZE_EX_MASK) >>
-		     E1000_EECD_SIZE_EX_SHIFT);
+	size = FIELD_GET(E1000_EECD_SIZE_EX_MASK, eecd);
 
 	/* Added to a constant, "size" becomes the left-shift value
 	 * for setting word_size.
@@ -2798,7 +2796,7 @@ static s32 igb_get_thermal_sensor_data_generic(struct e1000_hw *hw)
 		return 0;
 
 	hw->nvm.ops.read(hw, ets_offset, 1, &ets_cfg);
-	if (((ets_cfg & NVM_ETS_TYPE_MASK) >> NVM_ETS_TYPE_SHIFT)
+	if (FIELD_GET(NVM_ETS_TYPE_MASK, ets_cfg)
 	    != NVM_ETS_TYPE_EMC)
 		return E1000_NOT_IMPLEMENTED;
 
@@ -2808,10 +2806,8 @@ static s32 igb_get_thermal_sensor_data_generic(struct e1000_hw *hw)
 
 	for (i = 1; i < num_sensors; i++) {
 		hw->nvm.ops.read(hw, (ets_offset + i), 1, &ets_sensor);
-		sensor_index = ((ets_sensor & NVM_ETS_DATA_INDEX_MASK) >>
-				NVM_ETS_DATA_INDEX_SHIFT);
-		sensor_location = ((ets_sensor & NVM_ETS_DATA_LOC_MASK) >>
-				   NVM_ETS_DATA_LOC_SHIFT);
+		sensor_index = FIELD_GET(NVM_ETS_DATA_INDEX_MASK, ets_sensor);
+		sensor_location = FIELD_GET(NVM_ETS_DATA_LOC_MASK, ets_sensor);
 
 		if (sensor_location != 0)
 			hw->phy.ops.read_i2c_byte(hw,
@@ -2859,20 +2855,17 @@ static s32 igb_init_thermal_sensor_thresh_generic(struct e1000_hw *hw)
 		return 0;
 
 	hw->nvm.ops.read(hw, ets_offset, 1, &ets_cfg);
-	if (((ets_cfg & NVM_ETS_TYPE_MASK) >> NVM_ETS_TYPE_SHIFT)
+	if (FIELD_GET(NVM_ETS_TYPE_MASK, ets_cfg)
 	    != NVM_ETS_TYPE_EMC)
 		return E1000_NOT_IMPLEMENTED;
 
-	low_thresh_delta = ((ets_cfg & NVM_ETS_LTHRES_DELTA_MASK) >>
-			    NVM_ETS_LTHRES_DELTA_SHIFT);
+	low_thresh_delta = FIELD_GET(NVM_ETS_LTHRES_DELTA_MASK, ets_cfg);
 	num_sensors = (ets_cfg & NVM_ETS_NUM_SENSORS_MASK);
 
 	for (i = 1; i <= num_sensors; i++) {
 		hw->nvm.ops.read(hw, (ets_offset + i), 1, &ets_sensor);
-		sensor_index = ((ets_sensor & NVM_ETS_DATA_INDEX_MASK) >>
-				NVM_ETS_DATA_INDEX_SHIFT);
-		sensor_location = ((ets_sensor & NVM_ETS_DATA_LOC_MASK) >>
-				   NVM_ETS_DATA_LOC_SHIFT);
+		sensor_index = FIELD_GET(NVM_ETS_DATA_INDEX_MASK, ets_sensor);
+		sensor_location = FIELD_GET(NVM_ETS_DATA_LOC_MASK, ets_sensor);
 		therm_limit = ets_sensor & NVM_ETS_DATA_HTHRESH_MASK;
 
 		hw->phy.ops.write_i2c_byte(hw,
diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.c b/drivers/net/ethernet/intel/igb/e1000_i210.c
index b9b9d35494d2..503b239868e8 100644
--- a/drivers/net/ethernet/intel/igb/e1000_i210.c
+++ b/drivers/net/ethernet/intel/igb/e1000_i210.c
@@ -5,9 +5,9 @@
  * e1000_i211
  */
 
-#include <linux/types.h>
+#include <linux/bitfield.h>
 #include <linux/if_ether.h>
-
+#include <linux/types.h>
 #include "e1000_hw.h"
 #include "e1000_i210.h"
 
@@ -473,7 +473,7 @@ s32 igb_read_invm_version(struct e1000_hw *hw,
 		/* Check if we have second version location used */
 		else if ((i == 1) &&
 			 ((*record & E1000_INVM_VER_FIELD_TWO) == 0)) {
-			version = (*record & E1000_INVM_VER_FIELD_ONE) >> 3;
+			version = FIELD_GET(E1000_INVM_VER_FIELD_ONE, *record);
 			status = 0;
 			break;
 		}
@@ -483,8 +483,8 @@ s32 igb_read_invm_version(struct e1000_hw *hw,
 		else if ((((*record & E1000_INVM_VER_FIELD_ONE) == 0) &&
 			 ((*record & 0x3) == 0)) || (((*record & 0x3) != 0) &&
 			 (i != 1))) {
-			version = (*next_record & E1000_INVM_VER_FIELD_TWO)
-				  >> 13;
+			version = FIELD_GET(E1000_INVM_VER_FIELD_TWO,
+					    *next_record);
 			status = 0;
 			break;
 		}
@@ -493,15 +493,15 @@ s32 igb_read_invm_version(struct e1000_hw *hw,
 		 */
 		else if (((*record & E1000_INVM_VER_FIELD_TWO) == 0) &&
 			 ((*record & 0x3) == 0)) {
-			version = (*record & E1000_INVM_VER_FIELD_ONE) >> 3;
+			version = FIELD_GET(E1000_INVM_VER_FIELD_ONE, *record);
 			status = 0;
 			break;
 		}
 	}
 
 	if (!status) {
-		invm_ver->invm_major = (version & E1000_INVM_MAJOR_MASK)
-					>> E1000_INVM_MAJOR_SHIFT;
+		invm_ver->invm_major = FIELD_GET(E1000_INVM_MAJOR_MASK,
+						 version);
 		invm_ver->invm_minor = version & E1000_INVM_MINOR_MASK;
 	}
 	/* Read Image Type */
@@ -520,7 +520,8 @@ s32 igb_read_invm_version(struct e1000_hw *hw,
 			 ((*record & E1000_INVM_IMGTYPE_FIELD) == 0)) ||
 			 ((((*record & 0x3) != 0) && (i != 1)))) {
 			invm_ver->invm_img_type =
-				(*next_record & E1000_INVM_IMGTYPE_FIELD) >> 23;
+				FIELD_GET(E1000_INVM_IMGTYPE_FIELD,
+					  *next_record);
 			status = 0;
 			break;
 		}
diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.c b/drivers/net/ethernet/intel/igb/e1000_mac.c
index caf91c6f52b4..fa3dfafd2bb1 100644
--- a/drivers/net/ethernet/intel/igb/e1000_mac.c
+++ b/drivers/net/ethernet/intel/igb/e1000_mac.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2007 - 2018 Intel Corporation. */
 
+#include <linux/bitfield.h>
 #include <linux/if_ether.h>
 #include <linux/delay.h>
 #include <linux/pci.h>
@@ -50,13 +51,12 @@ s32 igb_get_bus_info_pcie(struct e1000_hw *hw)
 			break;
 		}
 
-		bus->width = (enum e1000_bus_width)((pcie_link_status &
-						     PCI_EXP_LNKSTA_NLW) >>
-						     PCI_EXP_LNKSTA_NLW_SHIFT);
+		bus->width = (enum e1000_bus_width)FIELD_GET(PCI_EXP_LNKSTA_NLW,
+							     pcie_link_status);
 	}
 
 	reg = rd32(E1000_STATUS);
-	bus->func = (reg & E1000_STATUS_FUNC_MASK) >> E1000_STATUS_FUNC_SHIFT;
+	bus->func = FIELD_GET(E1000_STATUS_FUNC_MASK, reg);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/igb/e1000_nvm.c b/drivers/net/ethernet/intel/igb/e1000_nvm.c
index fa136e6e9328..2dcd64d6dec3 100644
--- a/drivers/net/ethernet/intel/igb/e1000_nvm.c
+++ b/drivers/net/ethernet/intel/igb/e1000_nvm.c
@@ -1,9 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2007 - 2018 Intel Corporation. */
 
-#include <linux/if_ether.h>
+#include <linux/bitfield.h>
 #include <linux/delay.h>
-
+#include <linux/if_ether.h>
 #include "e1000_mac.h"
 #include "e1000_nvm.h"
 
@@ -708,10 +708,10 @@ void igb_get_fw_version(struct e1000_hw *hw, struct e1000_fw_version *fw_vers)
 		 */
 		if ((etrack_test &  NVM_MAJOR_MASK) != NVM_ETRACK_VALID) {
 			hw->nvm.ops.read(hw, NVM_VERSION, 1, &fw_version);
-			fw_vers->eep_major = (fw_version & NVM_MAJOR_MASK)
-					      >> NVM_MAJOR_SHIFT;
-			fw_vers->eep_minor = (fw_version & NVM_MINOR_MASK)
-					      >> NVM_MINOR_SHIFT;
+			fw_vers->eep_major = FIELD_GET(NVM_MAJOR_MASK,
+						       fw_version);
+			fw_vers->eep_minor = FIELD_GET(NVM_MINOR_MASK,
+						       fw_version);
 			fw_vers->eep_build = (fw_version & NVM_IMAGE_ID_MASK);
 			goto etrack_id;
 		}
@@ -753,15 +753,13 @@ void igb_get_fw_version(struct e1000_hw *hw, struct e1000_fw_version *fw_vers)
 		return;
 	}
 	hw->nvm.ops.read(hw, NVM_VERSION, 1, &fw_version);
-	fw_vers->eep_major = (fw_version & NVM_MAJOR_MASK)
-			      >> NVM_MAJOR_SHIFT;
+	fw_vers->eep_major = FIELD_GET(NVM_MAJOR_MASK, fw_version);
 
 	/* check for old style version format in newer images*/
 	if ((fw_version & NVM_NEW_DEC_MASK) == 0x0) {
 		eeprom_verl = (fw_version & NVM_COMB_VER_MASK);
 	} else {
-		eeprom_verl = (fw_version & NVM_MINOR_MASK)
-				>> NVM_MINOR_SHIFT;
+		eeprom_verl = FIELD_GET(NVM_MINOR_MASK, fw_version);
 	}
 	/* Convert minor value to hex before assigning to output struct
 	 * Val to be converted will not be higher than 99, per tool output
diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c
index a018000f7db9..cd65008c7ef5 100644
--- a/drivers/net/ethernet/intel/igb/e1000_phy.c
+++ b/drivers/net/ethernet/intel/igb/e1000_phy.c
@@ -1,9 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2007 - 2018 Intel Corporation. */
 
-#include <linux/if_ether.h>
+#include <linux/bitfield.h>
 #include <linux/delay.h>
-
+#include <linux/if_ether.h>
 #include "e1000_mac.h"
 #include "e1000_phy.h"
 
@@ -255,7 +255,7 @@ s32 igb_read_phy_reg_i2c(struct e1000_hw *hw, u32 offset, u16 *data)
 	}
 
 	/* Need to byte-swap the 16-bit value. */
-	*data = ((i2ccmd >> 8) & 0x00FF) | ((i2ccmd << 8) & 0xFF00);
+	*data = ((i2ccmd >> 8) & 0x00FF) | FIELD_PREP(0xFF00, i2ccmd);
 
 	return 0;
 }
@@ -282,7 +282,7 @@ s32 igb_write_phy_reg_i2c(struct e1000_hw *hw, u32 offset, u16 data)
 	}
 
 	/* Swap the data bytes for the I2C interface */
-	phy_data_swapped = ((data >> 8) & 0x00FF) | ((data << 8) & 0xFF00);
+	phy_data_swapped = ((data >> 8) & 0x00FF) | FIELD_PREP(0xFF00, data);
 
 	/* Set up Op-code, Phy Address, and register address in the I2CCMD
 	 * register.  The MAC will take care of interfacing with the
@@ -1682,8 +1682,7 @@ s32 igb_get_cable_length_m88(struct e1000_hw *hw)
 	if (ret_val)
 		goto out;
 
-	index = (phy_data & M88E1000_PSSR_CABLE_LENGTH) >>
-		M88E1000_PSSR_CABLE_LENGTH_SHIFT;
+	index = FIELD_GET(M88E1000_PSSR_CABLE_LENGTH, phy_data);
 	if (index >= ARRAY_SIZE(e1000_m88_cable_length_table) - 1) {
 		ret_val = -E1000_ERR_PHY;
 		goto out;
@@ -1796,8 +1795,7 @@ s32 igb_get_cable_length_m88_gen2(struct e1000_hw *hw)
 		if (ret_val)
 			goto out;
 
-		index = (phy_data & M88E1000_PSSR_CABLE_LENGTH) >>
-			M88E1000_PSSR_CABLE_LENGTH_SHIFT;
+		index = FIELD_GET(M88E1000_PSSR_CABLE_LENGTH, phy_data);
 		if (index >= ARRAY_SIZE(e1000_m88_cable_length_table) - 1) {
 			ret_val = -E1000_ERR_PHY;
 			goto out;
@@ -2578,8 +2576,7 @@ s32 igb_get_cable_length_82580(struct e1000_hw *hw)
 	if (ret_val)
 		goto out;
 
-	length = (phy_data & I82580_DSTATUS_CABLE_LENGTH) >>
-		 I82580_DSTATUS_CABLE_LENGTH_SHIFT;
+	length = FIELD_GET(I82580_DSTATUS_CABLE_LENGTH, phy_data);
 
 	if (length == E1000_CABLE_LENGTH_UNDEFINED)
 		ret_val = -E1000_ERR_PHY;
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 16d2a55d5e17..b66199c9bb3a 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -2356,11 +2356,9 @@ static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 		break;
 	case ETH_SS_STATS:
 		for (i = 0; i < IGB_GLOBAL_STATS_LEN; i++)
-			ethtool_sprintf(&p, "%s",
-					igb_gstrings_stats[i].stat_string);
+			ethtool_puts(&p, igb_gstrings_stats[i].stat_string);
 		for (i = 0; i < IGB_NETDEV_STATS_LEN; i++)
-			ethtool_sprintf(&p, "%s",
-					igb_gstrings_net_stats[i].stat_string);
+			ethtool_puts(&p, igb_gstrings_net_stats[i].stat_string);
 		for (i = 0; i < adapter->num_tx_queues; i++) {
 			ethtool_sprintf(&p, "tx_queue_%u_packets", i);
 			ethtool_sprintf(&p, "tx_queue_%u_bytes", i);
@@ -2434,7 +2432,7 @@ static int igb_get_ts_info(struct net_device *dev,
 	}
 }
 
-#define ETHER_TYPE_FULL_MASK ((__force __be16)~0)
+#define ETHER_TYPE_FULL_MASK cpu_to_be16(FIELD_MAX(U16_MAX))
 static int igb_get_ethtool_nfc_entry(struct igb_adapter *adapter,
 				     struct ethtool_rxnfc *cmd)
 {
@@ -2713,8 +2711,7 @@ static int igb_rxnfc_write_etype_filter(struct igb_adapter *adapter,
 	etqf |= (etype & E1000_ETQF_ETYPE_MASK);
 
 	etqf &= ~E1000_ETQF_QUEUE_MASK;
-	etqf |= ((input->action << E1000_ETQF_QUEUE_SHIFT)
-		& E1000_ETQF_QUEUE_MASK);
+	etqf |= FIELD_PREP(E1000_ETQF_QUEUE_MASK, input->action);
 	etqf |= E1000_ETQF_QUEUE_ENABLE;
 
 	wr32(E1000_ETQF(i), etqf);
@@ -2733,8 +2730,8 @@ static int igb_rxnfc_write_vlan_prio_filter(struct igb_adapter *adapter,
 	u32 vlapqf;
 
 	vlapqf = rd32(E1000_VLAPQF);
-	vlan_priority = (ntohs(input->filter.vlan_tci) & VLAN_PRIO_MASK)
-				>> VLAN_PRIO_SHIFT;
+	vlan_priority = FIELD_GET(VLAN_PRIO_MASK,
+				  ntohs(input->filter.vlan_tci));
 	queue_index = (vlapqf >> (vlan_priority * 4)) & E1000_VLAPQF_QUEUE_MASK;
 
 	/* check whether this vlan prio is already set */
@@ -2817,7 +2814,7 @@ static void igb_clear_vlan_prio_filter(struct igb_adapter *adapter,
 	u8 vlan_priority;
 	u32 vlapqf;
 
-	vlan_priority = (vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
+	vlan_priority = FIELD_GET(VLAN_PRIO_MASK, vlan_tci);
 
 	vlapqf = rd32(E1000_VLAPQF);
 	vlapqf &= ~E1000_VLAPQF_P_VALID(vlan_priority);
@@ -3282,18 +3279,17 @@ static u32 igb_get_rxfh_indir_size(struct net_device *netdev)
 	return IGB_RETA_SIZE;
 }
 
-static int igb_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			u8 *hfunc)
+static int igb_get_rxfh(struct net_device *netdev,
+			struct ethtool_rxfh_param *rxfh)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	int i;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (!indir)
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (!rxfh->indir)
 		return 0;
 	for (i = 0; i < IGB_RETA_SIZE; i++)
-		indir[i] = adapter->rss_indir_tbl[i];
+		rxfh->indir[i] = adapter->rss_indir_tbl[i];
 
 	return 0;
 }
@@ -3333,8 +3329,9 @@ void igb_write_rss_indir_tbl(struct igb_adapter *adapter)
 	}
 }
 
-static int igb_set_rxfh(struct net_device *netdev, const u32 *indir,
-			const u8 *key, const u8 hfunc)
+static int igb_set_rxfh(struct net_device *netdev,
+			struct ethtool_rxfh_param *rxfh,
+			struct netlink_ext_ack *extack)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
@@ -3342,10 +3339,11 @@ static int igb_set_rxfh(struct net_device *netdev, const u32 *indir,
 	u32 num_queues;
 
 	/* We do not allow change in unsupported parameters */
-	if (key ||
-	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->key ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP))
 		return -EOPNOTSUPP;
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
 	num_queues = adapter->rss_queues;
@@ -3362,12 +3360,12 @@ static int igb_set_rxfh(struct net_device *netdev, const u32 *indir,
 
 	/* Verify user input. */
 	for (i = 0; i < IGB_RETA_SIZE; i++)
-		if (indir[i] >= num_queues)
+		if (rxfh->indir[i] >= num_queues)
 			return -EINVAL;
 
 
 	for (i = 0; i < IGB_RETA_SIZE; i++)
-		adapter->rss_indir_tbl[i] = indir[i];
+		adapter->rss_indir_tbl[i] = rxfh->indir[i];
 
 	igb_write_rss_indir_tbl(adapter);
 
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index b2295caa2f0a..4df8d4153aa5 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -7295,7 +7295,7 @@ static int igb_set_vf_promisc(struct igb_adapter *adapter, u32 *msgbuf, u32 vf)
 static int igb_set_vf_multicasts(struct igb_adapter *adapter,
 				  u32 *msgbuf, u32 vf)
 {
-	int n = (msgbuf[0] & E1000_VT_MSGINFO_MASK) >> E1000_VT_MSGINFO_SHIFT;
+	int n = FIELD_GET(E1000_VT_MSGINFO_MASK, msgbuf[0]);
 	u16 *hash_list = (u16 *)&msgbuf[1];
 	struct vf_data_storage *vf_data = &adapter->vf_data[vf];
 	int i;
@@ -7555,7 +7555,7 @@ static int igb_ndo_set_vf_vlan(struct net_device *netdev, int vf,
 
 static int igb_set_vf_vlan_msg(struct igb_adapter *adapter, u32 *msgbuf, u32 vf)
 {
-	int add = (msgbuf[0] & E1000_VT_MSGINFO_MASK) >> E1000_VT_MSGINFO_SHIFT;
+	int add = FIELD_GET(E1000_VT_MSGINFO_MASK, msgbuf[0]);
 	int vid = (msgbuf[1] & E1000_VLVF_VLANID_MASK);
 	int ret;
 
@@ -9810,8 +9810,7 @@ static void igb_set_vf_rate_limit(struct e1000_hw *hw, int vf, int tx_rate,
 			 tx_rate;
 
 		bcnrc_val = E1000_RTTBCNRC_RS_ENA;
-		bcnrc_val |= ((rf_int << E1000_RTTBCNRC_RF_INT_SHIFT) &
-			      E1000_RTTBCNRC_RF_INT_MASK);
+		bcnrc_val |= FIELD_PREP(E1000_RTTBCNRC_RF_INT_MASK, rf_int);
 		bcnrc_val |= (rf_dec & E1000_RTTBCNRC_RF_DEC_MASK);
 	} else {
 		bcnrc_val = 0;
@@ -10000,8 +9999,7 @@ static void igb_init_dmac(struct igb_adapter *adapter, u32 pba)
 			hwm = 64 * (pba - 6);
 			reg = rd32(E1000_FCRTC);
 			reg &= ~E1000_FCRTC_RTH_COAL_MASK;
-			reg |= ((hwm << E1000_FCRTC_RTH_COAL_SHIFT)
-				& E1000_FCRTC_RTH_COAL_MASK);
+			reg |= FIELD_PREP(E1000_FCRTC_RTH_COAL_MASK, hwm);
 			wr32(E1000_FCRTC, reg);
 
 			/* Set the DMA Coalescing Rx threshold to PBA - 2 * max
@@ -10010,8 +10008,7 @@ static void igb_init_dmac(struct igb_adapter *adapter, u32 pba)
 			dmac_thr = pba - 10;
 			reg = rd32(E1000_DMACR);
 			reg &= ~E1000_DMACR_DMACTHR_MASK;
-			reg |= ((dmac_thr << E1000_DMACR_DMACTHR_SHIFT)
-				& E1000_DMACR_DMACTHR_MASK);
+			reg |= FIELD_PREP(E1000_DMACR_DMACTHR_MASK, dmac_thr);
 
 			/* transition to L0x or L1 if available..*/
 			reg |= (E1000_DMACR_DMAC_EN | E1000_DMACR_DMAC_LX_MASK);
diff --git a/drivers/net/ethernet/intel/igbvf/mbx.c b/drivers/net/ethernet/intel/igbvf/mbx.c
index a3cd7ac48d4b..d15282ee5ea8 100644
--- a/drivers/net/ethernet/intel/igbvf/mbx.c
+++ b/drivers/net/ethernet/intel/igbvf/mbx.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2009 - 2018 Intel Corporation. */
 
+#include <linux/bitfield.h>
 #include "mbx.h"
 
 /**
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index fd712585af27..a4d4f00e6a87 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -3,25 +3,25 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/pci.h>
-#include <linux/vmalloc.h>
-#include <linux/pagemap.h>
+#include <linux/bitfield.h>
 #include <linux/delay.h>
-#include <linux/netdevice.h>
-#include <linux/tcp.h>
-#include <linux/ipv6.h>
-#include <linux/slab.h>
-#include <net/checksum.h>
-#include <net/ip6_checksum.h>
-#include <linux/mii.h>
 #include <linux/ethtool.h>
 #include <linux/if_vlan.h>
+#include <linux/init.h>
+#include <linux/ipv6.h>
+#include <linux/mii.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/pagemap.h>
+#include <linux/pci.h>
 #include <linux/prefetch.h>
 #include <linux/sctp.h>
-
+#include <linux/slab.h>
+#include <linux/tcp.h>
+#include <linux/types.h>
+#include <linux/vmalloc.h>
+#include <net/checksum.h>
+#include <net/ip6_checksum.h>
 #include "igbvf.h"
 
 char igbvf_driver_name[] = "igbvf";
@@ -273,9 +273,8 @@ static bool igbvf_clean_rx_irq(struct igbvf_adapter *adapter,
 		 * that case, it fills the header buffer and spills the rest
 		 * into the page.
 		 */
-		hlen = (le16_to_cpu(rx_desc->wb.lower.lo_dword.hs_rss.hdr_info)
-		       & E1000_RXDADV_HDRBUFLEN_MASK) >>
-		       E1000_RXDADV_HDRBUFLEN_SHIFT;
+		hlen = le16_get_bits(rx_desc->wb.lower.lo_dword.hs_rss.hdr_info,
+				     E1000_RXDADV_HDRBUFLEN_MASK);
 		if (hlen > adapter->rx_ps_hdr_size)
 			hlen = adapter->rx_ps_hdr_size;
 
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index f48f82d5e274..45430e246e9c 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -81,6 +81,21 @@ struct igc_tx_timestamp_request {
 	u32 flags;             /* flags that should be added to the tx_buffer */
 };
 
+struct igc_inline_rx_tstamps {
+	/* Timestamps are saved in little endian at the beginning of the packet
+	 * buffer following the layout:
+	 *
+	 * DWORD: | 0              | 1              | 2              | 3              |
+	 * Field: | Timer1 SYSTIML | Timer1 SYSTIMH | Timer0 SYSTIML | Timer0 SYSTIMH |
+	 *
+	 * SYSTIML holds the nanoseconds part while SYSTIMH holds the seconds
+	 * part of the timestamp.
+	 *
+	 */
+	__le32 timer1[2];
+	__le32 timer0[2];
+};
+
 struct igc_ring_container {
 	struct igc_ring *ring;          /* pointer to linked list of rings */
 	unsigned int total_bytes;       /* total bytes processed this int */
@@ -261,6 +276,8 @@ struct igc_adapter {
 	unsigned int ptp_flags;
 	/* System time value lock */
 	spinlock_t tmreg_lock;
+	/* Free-running timer lock */
+	spinlock_t free_timer_lock;
 	struct cyclecounter cc;
 	struct timecounter tc;
 	struct timespec64 prev_ptp_time; /* Pre-reset PTP clock */
@@ -469,6 +486,8 @@ enum igc_tx_flags {
 	IGC_TX_FLAGS_TSTAMP_1	= 0x100,
 	IGC_TX_FLAGS_TSTAMP_2	= 0x200,
 	IGC_TX_FLAGS_TSTAMP_3	= 0x400,
+
+	IGC_TX_FLAGS_TSTAMP_TIMER_1 = 0x800,
 };
 
 enum igc_boards {
@@ -531,7 +550,7 @@ struct igc_rx_buffer {
 struct igc_xdp_buff {
 	struct xdp_buff xdp;
 	union igc_adv_rx_desc *rx_desc;
-	ktime_t rx_ts; /* data indication bit IGC_RXDADV_STAT_TSIP */
+	struct igc_inline_rx_tstamps *rx_ts; /* data indication bit IGC_RXDADV_STAT_TSIP */
 };
 
 struct igc_q_vector {
@@ -568,6 +587,7 @@ struct igc_nfc_filter {
 	u16 etype;
 	__be16 vlan_etype;
 	u16 vlan_tci;
+	u16 vlan_tci_mask;
 	u8 src_addr[ETH_ALEN];
 	u8 dst_addr[ETH_ALEN];
 	u8 user_data[8];
diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c
index a1d815af507d..9fae8bdec2a7 100644
--- a/drivers/net/ethernet/intel/igc/igc_base.c
+++ b/drivers/net/ethernet/intel/igc/igc_base.c
@@ -68,8 +68,7 @@ static s32 igc_init_nvm_params_base(struct igc_hw *hw)
 	u32 eecd = rd32(IGC_EECD);
 	u16 size;
 
-	size = (u16)((eecd & IGC_EECD_SIZE_EX_MASK) >>
-		     IGC_EECD_SIZE_EX_SHIFT);
+	size = FIELD_GET(IGC_EECD_SIZE_EX_MASK, eecd);
 
 	/* Added to a constant, "size" becomes the left-shift value
 	 * for setting word_size.
@@ -162,8 +161,7 @@ static s32 igc_init_phy_params_base(struct igc_hw *hw)
 	phy->reset_delay_us	= 100;
 
 	/* set lan id */
-	hw->bus.func = (rd32(IGC_STATUS) & IGC_STATUS_FUNC_MASK) >>
-			IGC_STATUS_FUNC_SHIFT;
+	hw->bus.func = FIELD_GET(IGC_STATUS_FUNC_MASK, rd32(IGC_STATUS));
 
 	/* Make sure the PHY is in a good state. Several people have reported
 	 * firmware leaving the PHY's page select register set to something
diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h
index f7d6491d4c60..bf8cdfbba9ff 100644
--- a/drivers/net/ethernet/intel/igc/igc_base.h
+++ b/drivers/net/ethernet/intel/igc/igc_base.h
@@ -37,6 +37,10 @@ struct igc_adv_tx_context_desc {
 #define IGC_ADVTXD_TSTAMP_REG_1	0x00010000 /* Select register 1 for timestamp */
 #define IGC_ADVTXD_TSTAMP_REG_2	0x00020000 /* Select register 2 for timestamp */
 #define IGC_ADVTXD_TSTAMP_REG_3	0x00030000 /* Select register 3 for timestamp */
+#define IGC_ADVTXD_TSTAMP_TIMER_1	0x00010000 /* Select timer 1 for timestamp */
+#define IGC_ADVTXD_TSTAMP_TIMER_2	0x00020000 /* Select timer 2 for timestamp */
+#define IGC_ADVTXD_TSTAMP_TIMER_3	0x00030000 /* Select timer 3 for timestamp */
+
 #define IGC_ADVTXD_DTYP_CTXT	0x00200000 /* Advanced Context Descriptor */
 #define IGC_ADVTXD_DTYP_DATA	0x00300000 /* Advanced Data Descriptor */
 #define IGC_ADVTXD_DCMD_EOP	0x01000000 /* End of Packet */
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index b3037016f31d..5f92b3c7c3d4 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -317,6 +317,8 @@
 #define IGC_TXD_CMD_TSE		0x04000000 /* TCP Seg enable */
 #define IGC_TXD_EXTCMD_TSTAMP	0x00000010 /* IEEE1588 Timestamp packet */
 
+#define IGC_TXD_PTP2_TIMER_1	0x00000020
+
 /* IPSec Encrypt Enable */
 #define IGC_ADVTXD_L4LEN_SHIFT	8  /* Adv ctxt L4LEN shift */
 #define IGC_ADVTXD_MSS_SHIFT	16 /* Adv ctxt MSS shift */
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 785eaa8e0ba8..b95d2c86e803 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -773,11 +773,9 @@ static void igc_ethtool_get_strings(struct net_device *netdev, u32 stringset,
 		break;
 	case ETH_SS_STATS:
 		for (i = 0; i < IGC_GLOBAL_STATS_LEN; i++)
-			ethtool_sprintf(&p, "%s",
-					igc_gstrings_stats[i].stat_string);
+			ethtool_puts(&p, igc_gstrings_stats[i].stat_string);
 		for (i = 0; i < IGC_NETDEV_STATS_LEN; i++)
-			ethtool_sprintf(&p, "%s",
-					igc_gstrings_net_stats[i].stat_string);
+			ethtool_puts(&p, igc_gstrings_net_stats[i].stat_string);
 		for (i = 0; i < adapter->num_tx_queues; i++) {
 			ethtool_sprintf(&p, "tx_queue_%u_packets", i);
 			ethtool_sprintf(&p, "tx_queue_%u_bytes", i);
@@ -958,6 +956,7 @@ static int igc_ethtool_set_coalesce(struct net_device *netdev,
 }
 
 #define ETHER_TYPE_FULL_MASK ((__force __be16)~0)
+#define VLAN_TCI_FULL_MASK ((__force __be16)~0)
 static int igc_ethtool_get_nfc_rule(struct igc_adapter *adapter,
 				    struct ethtool_rxnfc *cmd)
 {
@@ -980,10 +979,16 @@ static int igc_ethtool_get_nfc_rule(struct igc_adapter *adapter,
 		fsp->m_u.ether_spec.h_proto = ETHER_TYPE_FULL_MASK;
 	}
 
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_ETYPE) {
+		fsp->flow_type |= FLOW_EXT;
+		fsp->h_ext.vlan_etype = rule->filter.vlan_etype;
+		fsp->m_ext.vlan_etype = ETHER_TYPE_FULL_MASK;
+	}
+
 	if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) {
 		fsp->flow_type |= FLOW_EXT;
 		fsp->h_ext.vlan_tci = htons(rule->filter.vlan_tci);
-		fsp->m_ext.vlan_tci = htons(VLAN_PRIO_MASK);
+		fsp->m_ext.vlan_tci = htons(rule->filter.vlan_tci_mask);
 	}
 
 	if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) {
@@ -1218,6 +1223,7 @@ static void igc_ethtool_init_nfc_rule(struct igc_nfc_rule *rule,
 
 	if ((fsp->flow_type & FLOW_EXT) && fsp->m_ext.vlan_tci) {
 		rule->filter.vlan_tci = ntohs(fsp->h_ext.vlan_tci);
+		rule->filter.vlan_tci_mask = ntohs(fsp->m_ext.vlan_tci);
 		rule->filter.match_flags |= IGC_FILTER_FLAG_VLAN_TCI;
 	}
 
@@ -1255,11 +1261,19 @@ static void igc_ethtool_init_nfc_rule(struct igc_nfc_rule *rule,
 		memcpy(rule->filter.user_mask, fsp->m_ext.data, sizeof(fsp->m_ext.data));
 	}
 
-	/* When multiple filter options or user data or vlan etype is set, use a
-	 * flex filter.
+	/* The i225/i226 has various different filters. Flex filters provide a
+	 * way to match up to the first 128 bytes of a packet. Use them for:
+	 *   a) For specific user data
+	 *   b) For VLAN EtherType
+	 *   c) For full TCI match
+	 *   d) Or in case multiple filter criteria are set
+	 *
+	 * Otherwise, use the simple MAC, VLAN PRIO or EtherType filters.
 	 */
 	if ((rule->filter.match_flags & IGC_FILTER_FLAG_USER_DATA) ||
 	    (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_ETYPE) ||
+	    ((rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) &&
+	     rule->filter.vlan_tci_mask == ntohs(VLAN_TCI_FULL_MASK)) ||
 	    (rule->filter.match_flags & (rule->filter.match_flags - 1)))
 		rule->flex = true;
 	else
@@ -1329,6 +1343,26 @@ static int igc_ethtool_add_nfc_rule(struct igc_adapter *adapter,
 		return -EINVAL;
 	}
 
+	/* There are two ways to match the VLAN TCI:
+	 *  1. Match on PCP field and use vlan prio filter for it
+	 *  2. Match on complete TCI field and use flex filter for it
+	 */
+	if ((fsp->flow_type & FLOW_EXT) &&
+	    fsp->m_ext.vlan_tci &&
+	    fsp->m_ext.vlan_tci != htons(VLAN_PRIO_MASK) &&
+	    fsp->m_ext.vlan_tci != VLAN_TCI_FULL_MASK) {
+		netdev_dbg(netdev, "VLAN mask not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* VLAN EtherType can only be matched by full mask. */
+	if ((fsp->flow_type & FLOW_EXT) &&
+	    fsp->m_ext.vlan_etype &&
+	    fsp->m_ext.vlan_etype != ETHER_TYPE_FULL_MASK) {
+		netdev_dbg(netdev, "VLAN EtherType mask not supported\n");
+		return -EOPNOTSUPP;
+	}
+
 	if (fsp->location >= IGC_MAX_RXNFC_RULES) {
 		netdev_dbg(netdev, "Invalid location\n");
 		return -EINVAL;
@@ -1428,45 +1462,46 @@ static u32 igc_ethtool_get_rxfh_indir_size(struct net_device *netdev)
 	return IGC_RETA_SIZE;
 }
 
-static int igc_ethtool_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-				u8 *hfunc)
+static int igc_ethtool_get_rxfh(struct net_device *netdev,
+				struct ethtool_rxfh_param *rxfh)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	int i;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (!indir)
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (!rxfh->indir)
 		return 0;
 	for (i = 0; i < IGC_RETA_SIZE; i++)
-		indir[i] = adapter->rss_indir_tbl[i];
+		rxfh->indir[i] = adapter->rss_indir_tbl[i];
 
 	return 0;
 }
 
-static int igc_ethtool_set_rxfh(struct net_device *netdev, const u32 *indir,
-				const u8 *key, const u8 hfunc)
+static int igc_ethtool_set_rxfh(struct net_device *netdev,
+				struct ethtool_rxfh_param *rxfh,
+				struct netlink_ext_ack *extack)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	u32 num_queues;
 	int i;
 
 	/* We do not allow change in unsupported parameters */
-	if (key ||
-	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->key ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP))
 		return -EOPNOTSUPP;
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
 	num_queues = adapter->rss_queues;
 
 	/* Verify user input. */
 	for (i = 0; i < IGC_RETA_SIZE; i++)
-		if (indir[i] >= num_queues)
+		if (rxfh->indir[i] >= num_queues)
 			return -EINVAL;
 
 	for (i = 0; i < IGC_RETA_SIZE; i++)
-		adapter->rss_indir_tbl[i] = indir[i];
+		adapter->rss_indir_tbl[i] = rxfh->indir[i];
 
 	igc_write_rss_indir_tbl(adapter);
 
diff --git a/drivers/net/ethernet/intel/igc/igc_i225.c b/drivers/net/ethernet/intel/igc/igc_i225.c
index 17546a035ab1..0dd61719f1ed 100644
--- a/drivers/net/ethernet/intel/igc/igc_i225.c
+++ b/drivers/net/ethernet/intel/igc/igc_i225.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c)  2018 Intel Corporation */
 
+#include <linux/bitfield.h>
 #include <linux/delay.h>
 
 #include "igc_hw.h"
@@ -578,9 +579,8 @@ s32 igc_set_ltr_i225(struct igc_hw *hw, bool link)
 
 			/* Calculate tw_system (nsec). */
 			if (speed == SPEED_100) {
-				tw_system = ((rd32(IGC_EEE_SU) &
-					     IGC_TW_SYSTEM_100_MASK) >>
-					     IGC_TW_SYSTEM_100_SHIFT) * 500;
+				tw_system = FIELD_GET(IGC_TW_SYSTEM_100_MASK,
+						      rd32(IGC_EEE_SU)) * 500;
 			} else {
 				tw_system = (rd32(IGC_EEE_SU) &
 					     IGC_TW_SYSTEM_1000_MASK) * 500;
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index e9bb403bbacf..ba8d3fe186ae 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -1299,14 +1299,16 @@ static void igc_tx_olinfo_status(struct igc_ring *tx_ring,
 	u32 olinfo_status = paylen << IGC_ADVTXD_PAYLEN_SHIFT;
 
 	/* insert L4 checksum */
-	olinfo_status |= (tx_flags & IGC_TX_FLAGS_CSUM) *
-			  ((IGC_TXD_POPTS_TXSM << 8) /
-			  IGC_TX_FLAGS_CSUM);
+	olinfo_status |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_CSUM,
+				      (IGC_TXD_POPTS_TXSM << 8));
 
 	/* insert IPv4 checksum */
-	olinfo_status |= (tx_flags & IGC_TX_FLAGS_IPV4) *
-			  (((IGC_TXD_POPTS_IXSM << 8)) /
-			  IGC_TX_FLAGS_IPV4);
+	olinfo_status |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_IPV4,
+				      (IGC_TXD_POPTS_IXSM << 8));
+
+	/* Use the second timer (free running, in general) for the timestamp */
+	olinfo_status |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSTAMP_TIMER_1,
+				      IGC_TXD_PTP2_TIMER_1);
 
 	tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
 }
@@ -1651,6 +1653,8 @@ done:
 		if (igc_request_tx_tstamp(adapter, skb, &tstamp_flags)) {
 			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 			tx_flags |= IGC_TX_FLAGS_TSTAMP | tstamp_flags;
+			if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_USE_CYCLES)
+				tx_flags |= IGC_TX_FLAGS_TSTAMP_TIMER_1;
 		} else {
 			adapter->tx_hwtstamp_skipped++;
 		}
@@ -1963,9 +1967,9 @@ static struct sk_buff *igc_build_skb(struct igc_ring *rx_ring,
 
 static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring,
 					 struct igc_rx_buffer *rx_buffer,
-					 struct xdp_buff *xdp,
-					 ktime_t timestamp)
+					 struct igc_xdp_buff *ctx)
 {
+	struct xdp_buff *xdp = &ctx->xdp;
 	unsigned int metasize = xdp->data - xdp->data_meta;
 	unsigned int size = xdp->data_end - xdp->data;
 	unsigned int truesize = igc_get_rx_frame_truesize(rx_ring, size);
@@ -1982,8 +1986,10 @@ static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring,
 	if (unlikely(!skb))
 		return NULL;
 
-	if (timestamp)
-		skb_hwtstamps(skb)->hwtstamp = timestamp;
+	if (ctx->rx_ts) {
+		skb_shinfo(skb)->tx_flags |= SKBTX_HW_TSTAMP_NETDEV;
+		skb_hwtstamps(skb)->netdev_data = ctx->rx_ts;
+	}
 
 	/* Determine available headroom for copy */
 	headlen = size;
@@ -2583,11 +2589,10 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 	int xdp_status = 0, rx_buffer_pgcnt;
 
 	while (likely(total_packets < budget)) {
-		union igc_adv_rx_desc *rx_desc;
+		struct igc_xdp_buff ctx = { .rx_ts = NULL };
 		struct igc_rx_buffer *rx_buffer;
+		union igc_adv_rx_desc *rx_desc;
 		unsigned int size, truesize;
-		struct igc_xdp_buff ctx;
-		ktime_t timestamp = 0;
 		int pkt_offset = 0;
 		void *pktbuf;
 
@@ -2614,9 +2619,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 		pktbuf = page_address(rx_buffer->page) + rx_buffer->page_offset;
 
 		if (igc_test_staterr(rx_desc, IGC_RXDADV_STAT_TSIP)) {
-			timestamp = igc_ptp_rx_pktstamp(q_vector->adapter,
-							pktbuf);
-			ctx.rx_ts = timestamp;
+			ctx.rx_ts = pktbuf;
 			pkt_offset = IGC_TS_HDR_LEN;
 			size -= IGC_TS_HDR_LEN;
 		}
@@ -2653,8 +2656,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 		else if (ring_uses_build_skb(rx_ring))
 			skb = igc_build_skb(rx_ring, rx_buffer, &ctx.xdp);
 		else
-			skb = igc_construct_skb(rx_ring, rx_buffer, &ctx.xdp,
-						timestamp);
+			skb = igc_construct_skb(rx_ring, rx_buffer, &ctx);
 
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
@@ -2803,9 +2805,7 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 		ctx->rx_desc = desc;
 
 		if (igc_test_staterr(desc, IGC_RXDADV_STAT_TSIP)) {
-			timestamp = igc_ptp_rx_pktstamp(q_vector->adapter,
-							bi->xdp->data);
-			ctx->rx_ts = timestamp;
+			ctx->rx_ts = bi->xdp->data;
 
 			bi->xdp->data += IGC_TS_HDR_LEN;
 
@@ -3452,8 +3452,8 @@ static int igc_write_flex_filter_ll(struct igc_adapter *adapter,
 
 	/* Configure filter */
 	queuing = input->length & IGC_FHFT_LENGTH_MASK;
-	queuing |= (input->rx_queue << IGC_FHFT_QUEUE_SHIFT) & IGC_FHFT_QUEUE_MASK;
-	queuing |= (input->prio << IGC_FHFT_PRIO_SHIFT) & IGC_FHFT_PRIO_MASK;
+	queuing |= FIELD_PREP(IGC_FHFT_QUEUE_MASK, input->rx_queue);
+	queuing |= FIELD_PREP(IGC_FHFT_PRIO_MASK, input->prio);
 
 	if (input->immediate_irq)
 		queuing |= IGC_FHFT_IMM_INT;
@@ -3712,8 +3712,7 @@ static int igc_enable_nfc_rule(struct igc_adapter *adapter,
 	}
 
 	if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) {
-		int prio = (rule->filter.vlan_tci & VLAN_PRIO_MASK) >>
-			   VLAN_PRIO_SHIFT;
+		int prio = FIELD_GET(VLAN_PRIO_MASK, rule->filter.vlan_tci);
 
 		err = igc_add_vlan_prio_filter(adapter, prio, rule->action);
 		if (err)
@@ -3735,8 +3734,7 @@ static void igc_disable_nfc_rule(struct igc_adapter *adapter,
 		igc_del_etype_filter(adapter, rule->filter.etype);
 
 	if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) {
-		int prio = (rule->filter.vlan_tci & VLAN_PRIO_MASK) >>
-			   VLAN_PRIO_SHIFT;
+		int prio = FIELD_GET(VLAN_PRIO_MASK, rule->filter.vlan_tci);
 
 		igc_del_vlan_prio_filter(adapter, prio);
 	}
@@ -6562,6 +6560,24 @@ int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
 	return 0;
 }
 
+static ktime_t igc_get_tstamp(struct net_device *dev,
+			      const struct skb_shared_hwtstamps *hwtstamps,
+			      bool cycles)
+{
+	struct igc_adapter *adapter = netdev_priv(dev);
+	struct igc_inline_rx_tstamps *tstamp;
+	ktime_t timestamp;
+
+	tstamp = hwtstamps->netdev_data;
+
+	if (cycles)
+		timestamp = igc_ptp_rx_pktstamp(adapter, tstamp->timer1);
+	else
+		timestamp = igc_ptp_rx_pktstamp(adapter, tstamp->timer0);
+
+	return timestamp;
+}
+
 static const struct net_device_ops igc_netdev_ops = {
 	.ndo_open		= igc_open,
 	.ndo_stop		= igc_close,
@@ -6579,6 +6595,7 @@ static const struct net_device_ops igc_netdev_ops = {
 	.ndo_bpf		= igc_bpf,
 	.ndo_xdp_xmit		= igc_xdp_xmit,
 	.ndo_xsk_wakeup		= igc_xsk_wakeup,
+	.ndo_get_tstamp		= igc_get_tstamp,
 };
 
 /* PCIe configuration access */
@@ -6682,9 +6699,11 @@ static int igc_xdp_rx_hash(const struct xdp_md *_ctx, u32 *hash,
 static int igc_xdp_rx_timestamp(const struct xdp_md *_ctx, u64 *timestamp)
 {
 	const struct igc_xdp_buff *ctx = (void *)_ctx;
+	struct igc_adapter *adapter = netdev_priv(ctx->xdp.rxq->dev);
+	struct igc_inline_rx_tstamps *tstamp = ctx->rx_ts;
 
 	if (igc_test_staterr(ctx->rx_desc, IGC_RXDADV_STAT_TSIP)) {
-		*timestamp = ctx->rx_ts;
+		*timestamp = igc_ptp_rx_pktstamp(adapter, tstamp->timer0);
 
 		return 0;
 	}
diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c
index 53b77c969c85..7cd8716d2ffa 100644
--- a/drivers/net/ethernet/intel/igc/igc_phy.c
+++ b/drivers/net/ethernet/intel/igc/igc_phy.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c)  2018 Intel Corporation */
 
+#include <linux/bitfield.h>
 #include "igc_phy.h"
 
 /**
@@ -726,7 +727,7 @@ static s32 igc_write_xmdio_reg(struct igc_hw *hw, u16 addr,
  */
 s32 igc_write_phy_reg_gpy(struct igc_hw *hw, u32 offset, u16 data)
 {
-	u8 dev_addr = (offset & GPY_MMD_MASK) >> GPY_MMD_SHIFT;
+	u8 dev_addr = FIELD_GET(GPY_MMD_MASK, offset);
 	s32 ret_val;
 
 	offset = offset & GPY_REG_MASK;
@@ -757,7 +758,7 @@ s32 igc_write_phy_reg_gpy(struct igc_hw *hw, u32 offset, u16 data)
  */
 s32 igc_read_phy_reg_gpy(struct igc_hw *hw, u32 offset, u16 *data)
 {
-	u8 dev_addr = (offset & GPY_MMD_MASK) >> GPY_MMD_SHIFT;
+	u8 dev_addr = FIELD_GET(GPY_MMD_MASK, offset);
 	s32 ret_val;
 
 	offset = offset & GPY_REG_MASK;
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index 928f38792203..885faaa7b9de 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -459,12 +459,10 @@ static int igc_ptp_systim_to_hwtstamp(struct igc_adapter *adapter,
 /**
  * igc_ptp_rx_pktstamp - Retrieve timestamp from Rx packet buffer
  * @adapter: Pointer to adapter the packet buffer belongs to
- * @buf: Pointer to packet buffer
+ * @buf: Pointer to start of timestamp in HW format (2 32-bit words)
  *
- * This function retrieves the timestamp saved in the beginning of packet
- * buffer. While two timestamps are available, one in timer0 reference and the
- * other in timer1 reference, this function considers only the timestamp in
- * timer0 reference.
+ * This function retrieves and converts the timestamp stored at @buf
+ * to ktime_t, adjusting for hardware latencies.
  *
  * Returns timestamp value.
  */
@@ -474,17 +472,8 @@ ktime_t igc_ptp_rx_pktstamp(struct igc_adapter *adapter, __le32 *buf)
 	u32 secs, nsecs;
 	int adjust;
 
-	/* Timestamps are saved in little endian at the beginning of the packet
-	 * buffer following the layout:
-	 *
-	 * DWORD: | 0              | 1              | 2              | 3              |
-	 * Field: | Timer1 SYSTIML | Timer1 SYSTIMH | Timer0 SYSTIML | Timer0 SYSTIMH |
-	 *
-	 * SYSTIML holds the nanoseconds part while SYSTIMH holds the seconds
-	 * part of the timestamp.
-	 */
-	nsecs = le32_to_cpu(buf[2]);
-	secs = le32_to_cpu(buf[3]);
+	nsecs = le32_to_cpu(buf[0]);
+	secs = le32_to_cpu(buf[1]);
 
 	timestamp = ktime_set(secs, nsecs);
 
@@ -542,10 +531,11 @@ static void igc_ptp_enable_rx_timestamp(struct igc_adapter *adapter)
 
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		val = rd32(IGC_SRRCTL(i));
-		/* FIXME: For now, only support retrieving RX timestamps from
-		 * timer 0.
+		/* Enable retrieving timestamps from timer 0, the
+		 * "adjustable clock" and timer 1 the "free running
+		 * clock".
 		 */
-		val |= IGC_SRRCTL_TIMER1SEL(0) | IGC_SRRCTL_TIMER0SEL(0) |
+		val |= IGC_SRRCTL_TIMER1SEL(1) | IGC_SRRCTL_TIMER0SEL(0) |
 		       IGC_SRRCTL_TIMESTAMP;
 		wr32(IGC_SRRCTL(i), val);
 	}
@@ -1035,6 +1025,26 @@ static int igc_ptp_getcrosststamp(struct ptp_clock_info *ptp,
 					     adapter, &adapter->snapshot, cts);
 }
 
+static int igc_ptp_getcyclesx64(struct ptp_clock_info *ptp,
+				struct timespec64 *ts,
+				struct ptp_system_timestamp *sts)
+{
+	struct igc_adapter *igc = container_of(ptp, struct igc_adapter, ptp_caps);
+	struct igc_hw *hw = &igc->hw;
+	unsigned long flags;
+
+	spin_lock_irqsave(&igc->free_timer_lock, flags);
+
+	ptp_read_system_prets(sts);
+	ts->tv_nsec = rd32(IGC_SYSTIML_1);
+	ts->tv_sec = rd32(IGC_SYSTIMH_1);
+	ptp_read_system_postts(sts);
+
+	spin_unlock_irqrestore(&igc->free_timer_lock, flags);
+
+	return 0;
+}
+
 /**
  * igc_ptp_init - Initialize PTP functionality
  * @adapter: Board private structure
@@ -1088,6 +1098,7 @@ void igc_ptp_init(struct igc_adapter *adapter)
 		adapter->ptp_caps.adjfine = igc_ptp_adjfine_i225;
 		adapter->ptp_caps.adjtime = igc_ptp_adjtime_i225;
 		adapter->ptp_caps.gettimex64 = igc_ptp_gettimex64_i225;
+		adapter->ptp_caps.getcyclesx64 = igc_ptp_getcyclesx64;
 		adapter->ptp_caps.settime64 = igc_ptp_settime_i225;
 		adapter->ptp_caps.enable = igc_ptp_feature_enable_i225;
 		adapter->ptp_caps.pps = 1;
@@ -1108,6 +1119,7 @@ void igc_ptp_init(struct igc_adapter *adapter)
 	}
 
 	spin_lock_init(&adapter->ptp_tx_lock);
+	spin_lock_init(&adapter->free_timer_lock);
 	spin_lock_init(&adapter->tmreg_lock);
 
 	adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index 20e17f5fbce3..d38c87d7e5e8 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -243,6 +243,11 @@
 #define IGC_SYSTIMR	0x0B6F8  /* System time register Residue */
 #define IGC_TIMINCA	0x0B608  /* Increment attributes register - RW */
 
+#define IGC_SYSTIML_1	0x0B688  /* System time register Low - RO (timer 1) */
+#define IGC_SYSTIMH_1	0x0B68C  /* System time register High - RO (timer 1) */
+#define IGC_SYSTIMR_1	0x0B684  /* System time register Residue (timer 1) */
+#define IGC_TIMINCA_1	0x0B690  /* Increment attributes register - RW (timer 1) */
+
 /* TX Timestamp Low */
 #define IGC_TXSTMPL_0		0x0B618
 #define IGC_TXSTMPL_1		0x0B698
diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c
index a9c08321aca9..22cefb1eeedf 100644
--- a/drivers/net/ethernet/intel/igc/igc_tsn.c
+++ b/drivers/net/ethernet/intel/igc/igc_tsn.c
@@ -227,7 +227,7 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter)
 			wr32(IGC_TQAVCC(i), tqavcc);
 
 			wr32(IGC_TQAVHC(i),
-			     0x80000000 + ring->hicredit * 0x7735);
+			     0x80000000 + ring->hicredit * 0x7736);
 		} else {
 			/* Disable any CBS for the queue */
 			txqctl &= ~(IGC_TXQCTL_QAV_SEL_MASK);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
index 100388968e4d..6835d5f18753 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
@@ -123,14 +123,14 @@ static s32 ixgbe_init_phy_ops_82598(struct ixgbe_hw *hw)
 		if (ret_val)
 			return ret_val;
 		if (hw->phy.sfp_type == ixgbe_sfp_type_unknown)
-			return IXGBE_ERR_SFP_NOT_SUPPORTED;
+			return -EOPNOTSUPP;
 
 		/* Check to see if SFP+ module is supported */
 		ret_val = ixgbe_get_sfp_init_sequence_offsets(hw,
 							    &list_offset,
 							    &data_offset);
 		if (ret_val)
-			return IXGBE_ERR_SFP_NOT_SUPPORTED;
+			return -EOPNOTSUPP;
 		break;
 	default:
 		break;
@@ -213,7 +213,7 @@ static s32 ixgbe_get_link_capabilities_82598(struct ixgbe_hw *hw,
 		break;
 
 	default:
-		return IXGBE_ERR_LINK_SETUP;
+		return -EIO;
 	}
 
 	return 0;
@@ -283,7 +283,7 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw)
 
 	/* Validate the water mark configuration */
 	if (!hw->fc.pause_time)
-		return IXGBE_ERR_INVALID_LINK_SETTINGS;
+		return -EINVAL;
 
 	/* Low water mark of zero causes XOFF floods */
 	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
@@ -292,7 +292,7 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw)
 			if (!hw->fc.low_water[i] ||
 			    hw->fc.low_water[i] >= hw->fc.high_water[i]) {
 				hw_dbg(hw, "Invalid water mark configuration\n");
-				return IXGBE_ERR_INVALID_LINK_SETTINGS;
+				return -EINVAL;
 			}
 		}
 	}
@@ -369,7 +369,7 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw)
 		break;
 	default:
 		hw_dbg(hw, "Flow control param set incorrectly\n");
-		return IXGBE_ERR_CONFIG;
+		return -EIO;
 	}
 
 	/* Set 802.3x based flow control settings. */
@@ -438,7 +438,7 @@ static s32 ixgbe_start_mac_link_82598(struct ixgbe_hw *hw,
 				msleep(100);
 			}
 			if (!(links_reg & IXGBE_LINKS_KX_AN_COMP)) {
-				status = IXGBE_ERR_AUTONEG_NOT_COMPLETE;
+				status = -EIO;
 				hw_dbg(hw, "Autonegotiation did not complete.\n");
 			}
 		}
@@ -478,7 +478,7 @@ static s32 ixgbe_validate_link_ready(struct ixgbe_hw *hw)
 
 	if (timeout == IXGBE_VALIDATE_LINK_READY_TIMEOUT) {
 		hw_dbg(hw, "Link was indicated but link is down\n");
-		return IXGBE_ERR_LINK_SETUP;
+		return -EIO;
 	}
 
 	return 0;
@@ -594,7 +594,7 @@ static s32 ixgbe_setup_mac_link_82598(struct ixgbe_hw *hw,
 	speed &= link_capabilities;
 
 	if (speed == IXGBE_LINK_SPEED_UNKNOWN)
-		return IXGBE_ERR_LINK_SETUP;
+		return -EINVAL;
 
 	/* Set KX4/KX support according to speed requested */
 	else if (link_mode == IXGBE_AUTOC_LMS_KX4_AN ||
@@ -701,9 +701,9 @@ static s32 ixgbe_reset_hw_82598(struct ixgbe_hw *hw)
 
 		/* Init PHY and function pointers, perform SFP setup */
 		phy_status = hw->phy.ops.init(hw);
-		if (phy_status == IXGBE_ERR_SFP_NOT_SUPPORTED)
+		if (phy_status == -EOPNOTSUPP)
 			return phy_status;
-		if (phy_status == IXGBE_ERR_SFP_NOT_PRESENT)
+		if (phy_status == -ENOENT)
 			goto mac_reset_top;
 
 		hw->phy.ops.reset(hw);
@@ -727,7 +727,7 @@ mac_reset_top:
 		udelay(1);
 	}
 	if (ctrl & IXGBE_CTRL_RST) {
-		status = IXGBE_ERR_RESET_FAILED;
+		status = -EIO;
 		hw_dbg(hw, "Reset polling failed to complete.\n");
 	}
 
@@ -789,12 +789,12 @@ static s32 ixgbe_set_vmdq_82598(struct ixgbe_hw *hw, u32 rar, u32 vmdq)
 	/* Make sure we are using a valid rar index range */
 	if (rar >= rar_entries) {
 		hw_dbg(hw, "RAR index %d is out of range.\n", rar);
-		return IXGBE_ERR_INVALID_ARGUMENT;
+		return -EINVAL;
 	}
 
 	rar_high = IXGBE_READ_REG(hw, IXGBE_RAH(rar));
 	rar_high &= ~IXGBE_RAH_VIND_MASK;
-	rar_high |= ((vmdq << IXGBE_RAH_VIND_SHIFT) & IXGBE_RAH_VIND_MASK);
+	rar_high |= FIELD_PREP(IXGBE_RAH_VIND_MASK, vmdq);
 	IXGBE_WRITE_REG(hw, IXGBE_RAH(rar), rar_high);
 	return 0;
 }
@@ -814,7 +814,7 @@ static s32 ixgbe_clear_vmdq_82598(struct ixgbe_hw *hw, u32 rar, u32 vmdq)
 	/* Make sure we are using a valid rar index range */
 	if (rar >= rar_entries) {
 		hw_dbg(hw, "RAR index %d is out of range.\n", rar);
-		return IXGBE_ERR_INVALID_ARGUMENT;
+		return -EINVAL;
 	}
 
 	rar_high = IXGBE_READ_REG(hw, IXGBE_RAH(rar));
@@ -845,7 +845,7 @@ static s32 ixgbe_set_vfta_82598(struct ixgbe_hw *hw, u32 vlan, u32 vind,
 	u32 vftabyte;
 
 	if (vlan > 4095)
-		return IXGBE_ERR_PARAM;
+		return -EINVAL;
 
 	/* Determine 32-bit word position in array */
 	regindex = (vlan >> 5) & 0x7F;   /* upper seven bits */
@@ -964,7 +964,7 @@ static s32 ixgbe_read_i2c_phy_82598(struct ixgbe_hw *hw, u8 dev_addr,
 		gssr = IXGBE_GSSR_PHY0_SM;
 
 	if (hw->mac.ops.acquire_swfw_sync(hw, gssr) != 0)
-		return IXGBE_ERR_SWFW_SYNC;
+		return -EBUSY;
 
 	if (hw->phy.type == ixgbe_phy_nl) {
 		/*
@@ -993,7 +993,7 @@ static s32 ixgbe_read_i2c_phy_82598(struct ixgbe_hw *hw, u8 dev_addr,
 
 		if (sfp_stat != IXGBE_I2C_EEPROM_STATUS_PASS) {
 			hw_dbg(hw, "EEPROM read did not pass.\n");
-			status = IXGBE_ERR_SFP_NOT_PRESENT;
+			status = -ENOENT;
 			goto out;
 		}
 
@@ -1003,7 +1003,7 @@ static s32 ixgbe_read_i2c_phy_82598(struct ixgbe_hw *hw, u8 dev_addr,
 
 		*eeprom_data = (u8)(sfp_data >> 8);
 	} else {
-		status = IXGBE_ERR_PHY;
+		status = -EIO;
 	}
 
 out:
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
index 58ea959a4482..339e106a5732 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
@@ -117,7 +117,7 @@ static s32 ixgbe_setup_sfp_modules_82599(struct ixgbe_hw *hw)
 		ret_val = hw->mac.ops.acquire_swfw_sync(hw,
 							IXGBE_GSSR_MAC_CSR_SM);
 		if (ret_val)
-			return IXGBE_ERR_SWFW_SYNC;
+			return -EBUSY;
 
 		if (hw->eeprom.ops.read(hw, ++data_offset, &data_value))
 			goto setup_sfp_err;
@@ -144,7 +144,7 @@ static s32 ixgbe_setup_sfp_modules_82599(struct ixgbe_hw *hw)
 
 		if (ret_val) {
 			hw_dbg(hw, " sfp module setup not complete\n");
-			return IXGBE_ERR_SFP_SETUP_NOT_COMPLETE;
+			return -EIO;
 		}
 	}
 
@@ -159,7 +159,7 @@ setup_sfp_err:
 	usleep_range(hw->eeprom.semaphore_delay * 1000,
 		     hw->eeprom.semaphore_delay * 2000);
 	hw_err(hw, "eeprom read at offset %d failed\n", data_offset);
-	return IXGBE_ERR_SFP_SETUP_NOT_COMPLETE;
+	return -EIO;
 }
 
 /**
@@ -184,7 +184,7 @@ static s32 prot_autoc_read_82599(struct ixgbe_hw *hw, bool *locked,
 		ret_val = hw->mac.ops.acquire_swfw_sync(hw,
 					IXGBE_GSSR_MAC_CSR_SM);
 		if (ret_val)
-			return IXGBE_ERR_SWFW_SYNC;
+			return -EBUSY;
 
 		*locked = true;
 	}
@@ -219,7 +219,7 @@ static s32 prot_autoc_write_82599(struct ixgbe_hw *hw, u32 autoc, bool locked)
 		ret_val = hw->mac.ops.acquire_swfw_sync(hw,
 					IXGBE_GSSR_MAC_CSR_SM);
 		if (ret_val)
-			return IXGBE_ERR_SWFW_SYNC;
+			return -EBUSY;
 
 		locked = true;
 	}
@@ -400,7 +400,7 @@ static s32 ixgbe_get_link_capabilities_82599(struct ixgbe_hw *hw,
 		break;
 
 	default:
-		return IXGBE_ERR_LINK_SETUP;
+		return -EIO;
 	}
 
 	if (hw->phy.multispeed_fiber) {
@@ -541,7 +541,7 @@ static s32 ixgbe_start_mac_link_82599(struct ixgbe_hw *hw,
 				msleep(100);
 			}
 			if (!(links_reg & IXGBE_LINKS_KX_AN_COMP)) {
-				status = IXGBE_ERR_AUTONEG_NOT_COMPLETE;
+				status = -EIO;
 				hw_dbg(hw, "Autoneg did not complete.\n");
 			}
 		}
@@ -794,7 +794,7 @@ static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw,
 	speed &= link_capabilities;
 
 	if (speed == IXGBE_LINK_SPEED_UNKNOWN)
-		return IXGBE_ERR_LINK_SETUP;
+		return -EINVAL;
 
 	/* Use stored value (EEPROM defaults) of AUTOC to find KR/KX4 support*/
 	if (hw->mac.orig_link_settings_stored)
@@ -861,8 +861,7 @@ static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw,
 					msleep(100);
 				}
 				if (!(links_reg & IXGBE_LINKS_KX_AN_COMP)) {
-					status =
-						IXGBE_ERR_AUTONEG_NOT_COMPLETE;
+					status = -EIO;
 					hw_dbg(hw, "Autoneg did not complete.\n");
 				}
 			}
@@ -927,7 +926,7 @@ static s32 ixgbe_reset_hw_82599(struct ixgbe_hw *hw)
 	/* Identify PHY and related function pointers */
 	status = hw->phy.ops.init(hw);
 
-	if (status == IXGBE_ERR_SFP_NOT_SUPPORTED)
+	if (status == -EOPNOTSUPP)
 		return status;
 
 	/* Setup SFP module if there is one present. */
@@ -936,7 +935,7 @@ static s32 ixgbe_reset_hw_82599(struct ixgbe_hw *hw)
 		hw->phy.sfp_setup_needed = false;
 	}
 
-	if (status == IXGBE_ERR_SFP_NOT_SUPPORTED)
+	if (status == -EOPNOTSUPP)
 		return status;
 
 	/* Reset PHY */
@@ -974,7 +973,7 @@ mac_reset_top:
 	}
 
 	if (ctrl & IXGBE_CTRL_RST_MASK) {
-		status = IXGBE_ERR_RESET_FAILED;
+		status = -EIO;
 		hw_dbg(hw, "Reset polling failed to complete.\n");
 	}
 
@@ -1093,7 +1092,7 @@ static s32 ixgbe_fdir_check_cmd_complete(struct ixgbe_hw *hw, u32 *fdircmd)
 		udelay(10);
 	}
 
-	return IXGBE_ERR_FDIR_CMD_INCOMPLETE;
+	return -EIO;
 }
 
 /**
@@ -1155,7 +1154,7 @@ s32 ixgbe_reinit_fdir_tables_82599(struct ixgbe_hw *hw)
 	}
 	if (i >= IXGBE_FDIR_INIT_DONE_POLL) {
 		hw_dbg(hw, "Flow Director Signature poll time exceeded!\n");
-		return IXGBE_ERR_FDIR_REINIT_FAILED;
+		return -EIO;
 	}
 
 	/* Clear FDIR statistics registers (read to clear) */
@@ -1387,7 +1386,7 @@ s32 ixgbe_fdir_add_signature_filter_82599(struct ixgbe_hw *hw,
 		break;
 	default:
 		hw_dbg(hw, " Error on flow type input\n");
-		return IXGBE_ERR_CONFIG;
+		return -EIO;
 	}
 
 	/* configure FDIRCMD register */
@@ -1546,7 +1545,7 @@ s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw,
 		break;
 	default:
 		hw_dbg(hw, " Error on vm pool mask\n");
-		return IXGBE_ERR_CONFIG;
+		return -EIO;
 	}
 
 	switch (input_mask->formatted.flow_type & IXGBE_ATR_L4TYPE_MASK) {
@@ -1555,14 +1554,14 @@ s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw,
 		if (input_mask->formatted.dst_port ||
 		    input_mask->formatted.src_port) {
 			hw_dbg(hw, " Error on src/dst port mask\n");
-			return IXGBE_ERR_CONFIG;
+			return -EIO;
 		}
 		break;
 	case IXGBE_ATR_L4TYPE_MASK:
 		break;
 	default:
 		hw_dbg(hw, " Error on flow type mask\n");
-		return IXGBE_ERR_CONFIG;
+		return -EIO;
 	}
 
 	switch (ntohs(input_mask->formatted.vlan_id) & 0xEFFF) {
@@ -1583,7 +1582,7 @@ s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw,
 		break;
 	default:
 		hw_dbg(hw, " Error on VLAN mask\n");
-		return IXGBE_ERR_CONFIG;
+		return -EIO;
 	}
 
 	switch ((__force u16)input_mask->formatted.flex_bytes & 0xFFFF) {
@@ -1595,7 +1594,7 @@ s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw,
 		break;
 	default:
 		hw_dbg(hw, " Error on flexible byte mask\n");
-		return IXGBE_ERR_CONFIG;
+		return -EIO;
 	}
 
 	/* Now mask VM pool and destination IPv6 - bits 5 and 2 */
@@ -1824,7 +1823,7 @@ static s32 ixgbe_identify_phy_82599(struct ixgbe_hw *hw)
 
 	/* Return error if SFP module has been detected but is not supported */
 	if (hw->phy.type == ixgbe_phy_sfp_unsupported)
-		return IXGBE_ERR_SFP_NOT_SUPPORTED;
+		return -EOPNOTSUPP;
 
 	return status;
 }
@@ -1863,13 +1862,13 @@ static s32 ixgbe_enable_rx_dma_82599(struct ixgbe_hw *hw, u32 regval)
  *  Verifies that installed the firmware version is 0.6 or higher
  *  for SFI devices. All 82599 SFI devices should have version 0.6 or higher.
  *
- *  Returns IXGBE_ERR_EEPROM_VERSION if the FW is not present or
- *  if the FW version is not supported.
+ *  Return: -EACCES if the FW is not present or if the FW version is
+ *  not supported.
  **/
 static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw)
 {
-	s32 status = IXGBE_ERR_EEPROM_VERSION;
 	u16 fw_offset, fw_ptp_cfg_offset;
+	s32 status = -EACCES;
 	u16 offset;
 	u16 fw_version = 0;
 
@@ -1883,7 +1882,7 @@ static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw)
 		goto fw_version_err;
 
 	if (fw_offset == 0 || fw_offset == 0xFFFF)
-		return IXGBE_ERR_EEPROM_VERSION;
+		return -EACCES;
 
 	/* get the offset to the Pass Through Patch Configuration block */
 	offset = fw_offset + IXGBE_FW_PASSTHROUGH_PATCH_CONFIG_PTR;
@@ -1891,7 +1890,7 @@ static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw)
 		goto fw_version_err;
 
 	if (fw_ptp_cfg_offset == 0 || fw_ptp_cfg_offset == 0xFFFF)
-		return IXGBE_ERR_EEPROM_VERSION;
+		return -EACCES;
 
 	/* get the firmware version */
 	offset = fw_ptp_cfg_offset + IXGBE_FW_PATCH_VERSION_4;
@@ -1905,7 +1904,7 @@ static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw)
 
 fw_version_err:
 	hw_err(hw, "eeprom read at offset %d failed\n", offset);
-	return IXGBE_ERR_EEPROM_VERSION;
+	return -EACCES;
 }
 
 /**
@@ -2038,7 +2037,7 @@ static s32 ixgbe_reset_pipeline_82599(struct ixgbe_hw *hw)
 
 	if (!(anlp1_reg & IXGBE_ANLP1_AN_STATE_MASK)) {
 		hw_dbg(hw, "auto negotiation not completed\n");
-		ret_val = IXGBE_ERR_RESET_FAILED;
+		ret_val = -EIO;
 		goto reset_pipeline_out;
 	}
 
@@ -2087,7 +2086,7 @@ static s32 ixgbe_read_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset,
 
 		if (!timeout) {
 			hw_dbg(hw, "Driver can't access resource, acquiring I2C bus timeout.\n");
-			status = IXGBE_ERR_I2C;
+			status = -EIO;
 			goto release_i2c_access;
 		}
 	}
@@ -2141,7 +2140,7 @@ static s32 ixgbe_write_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset,
 
 		if (!timeout) {
 			hw_dbg(hw, "Driver can't access resource, acquiring I2C bus timeout.\n");
-			status = IXGBE_ERR_I2C;
+			status = -EIO;
 			goto release_i2c_access;
 		}
 	}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index 878dd8dff528..2e6e0365154a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -124,7 +124,7 @@ s32 ixgbe_setup_fc_generic(struct ixgbe_hw *hw)
 	 */
 	if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) {
 		hw_dbg(hw, "ixgbe_fc_rx_pause not valid in strict IEEE mode\n");
-		return IXGBE_ERR_INVALID_LINK_SETTINGS;
+		return -EINVAL;
 	}
 
 	/*
@@ -215,7 +215,7 @@ s32 ixgbe_setup_fc_generic(struct ixgbe_hw *hw)
 		break;
 	default:
 		hw_dbg(hw, "Flow control param set incorrectly\n");
-		return IXGBE_ERR_CONFIG;
+		return -EIO;
 	}
 
 	if (hw->mac.type != ixgbe_mac_X540) {
@@ -500,7 +500,7 @@ s32 ixgbe_read_pba_string_generic(struct ixgbe_hw *hw, u8 *pba_num,
 
 	if (pba_num == NULL) {
 		hw_dbg(hw, "PBA string buffer was null\n");
-		return IXGBE_ERR_INVALID_ARGUMENT;
+		return -EINVAL;
 	}
 
 	ret_val = hw->eeprom.ops.read(hw, IXGBE_PBANUM0_PTR, &data);
@@ -526,7 +526,7 @@ s32 ixgbe_read_pba_string_generic(struct ixgbe_hw *hw, u8 *pba_num,
 		/* we will need 11 characters to store the PBA */
 		if (pba_num_size < 11) {
 			hw_dbg(hw, "PBA string buffer too small\n");
-			return IXGBE_ERR_NO_SPACE;
+			return -ENOSPC;
 		}
 
 		/* extract hex string from data and pba_ptr */
@@ -563,13 +563,13 @@ s32 ixgbe_read_pba_string_generic(struct ixgbe_hw *hw, u8 *pba_num,
 
 	if (length == 0xFFFF || length == 0) {
 		hw_dbg(hw, "NVM PBA number section invalid length\n");
-		return IXGBE_ERR_PBA_SECTION;
+		return -EIO;
 	}
 
 	/* check if pba_num buffer is big enough */
 	if (pba_num_size  < (((u32)length * 2) - 1)) {
 		hw_dbg(hw, "PBA string buffer too small\n");
-		return IXGBE_ERR_NO_SPACE;
+		return -ENOSPC;
 	}
 
 	/* trim pba length from start of string */
@@ -684,7 +684,7 @@ void ixgbe_set_lan_id_multi_port_pcie(struct ixgbe_hw *hw)
 	u32 reg;
 
 	reg = IXGBE_READ_REG(hw, IXGBE_STATUS);
-	bus->func = (reg & IXGBE_STATUS_LAN_ID) >> IXGBE_STATUS_LAN_ID_SHIFT;
+	bus->func = FIELD_GET(IXGBE_STATUS_LAN_ID, reg);
 	bus->lan_id = bus->func;
 
 	/* check for a port swap */
@@ -695,8 +695,8 @@ void ixgbe_set_lan_id_multi_port_pcie(struct ixgbe_hw *hw)
 	/* Get MAC instance from EEPROM for configuring CS4227 */
 	if (hw->device_id == IXGBE_DEV_ID_X550EM_A_SFP) {
 		hw->eeprom.ops.read(hw, IXGBE_EEPROM_CTRL_4, &ee_ctrl_4);
-		bus->instance_id = (ee_ctrl_4 & IXGBE_EE_CTRL_4_INST_ID) >>
-				   IXGBE_EE_CTRL_4_INST_ID_SHIFT;
+		bus->instance_id = FIELD_GET(IXGBE_EE_CTRL_4_INST_ID,
+					     ee_ctrl_4);
 	}
 }
 
@@ -805,7 +805,7 @@ s32 ixgbe_led_on_generic(struct ixgbe_hw *hw, u32 index)
 	u32 led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL);
 
 	if (index > 3)
-		return IXGBE_ERR_PARAM;
+		return -EINVAL;
 
 	/* To turn on the LED, set mode to ON. */
 	led_reg &= ~IXGBE_LED_MODE_MASK(index);
@@ -826,7 +826,7 @@ s32 ixgbe_led_off_generic(struct ixgbe_hw *hw, u32 index)
 	u32 led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL);
 
 	if (index > 3)
-		return IXGBE_ERR_PARAM;
+		return -EINVAL;
 
 	/* To turn off the LED, set mode to OFF. */
 	led_reg &= ~IXGBE_LED_MODE_MASK(index);
@@ -870,10 +870,9 @@ s32 ixgbe_init_eeprom_params_generic(struct ixgbe_hw *hw)
 			 * SPI EEPROM is assumed here.  This code would need to
 			 * change if a future EEPROM is not SPI.
 			 */
-			eeprom_size = (u16)((eec & IXGBE_EEC_SIZE) >>
-					    IXGBE_EEC_SIZE_SHIFT);
+			eeprom_size = FIELD_GET(IXGBE_EEC_SIZE, eec);
 			eeprom->word_size = BIT(eeprom_size +
-						 IXGBE_EEPROM_WORD_SIZE_SHIFT);
+						IXGBE_EEPROM_WORD_SIZE_SHIFT);
 		}
 
 		if (eec & IXGBE_EEC_ADDR_SIZE)
@@ -904,11 +903,8 @@ s32 ixgbe_write_eeprom_buffer_bit_bang_generic(struct ixgbe_hw *hw, u16 offset,
 
 	hw->eeprom.ops.init_params(hw);
 
-	if (words == 0)
-		return IXGBE_ERR_INVALID_ARGUMENT;
-
-	if (offset + words > hw->eeprom.word_size)
-		return IXGBE_ERR_EEPROM;
+	if (words == 0 || (offset + words > hw->eeprom.word_size))
+		return -EINVAL;
 
 	/*
 	 * The EEPROM page size cannot be queried from the chip. We do lazy
@@ -962,7 +958,7 @@ static s32 ixgbe_write_eeprom_buffer_bit_bang(struct ixgbe_hw *hw, u16 offset,
 
 	if (ixgbe_ready_eeprom(hw) != 0) {
 		ixgbe_release_eeprom(hw);
-		return IXGBE_ERR_EEPROM;
+		return -EIO;
 	}
 
 	for (i = 0; i < words; i++) {
@@ -1028,7 +1024,7 @@ s32 ixgbe_write_eeprom_generic(struct ixgbe_hw *hw, u16 offset, u16 data)
 	hw->eeprom.ops.init_params(hw);
 
 	if (offset >= hw->eeprom.word_size)
-		return IXGBE_ERR_EEPROM;
+		return -EINVAL;
 
 	return ixgbe_write_eeprom_buffer_bit_bang(hw, offset, 1, &data);
 }
@@ -1050,11 +1046,8 @@ s32 ixgbe_read_eeprom_buffer_bit_bang_generic(struct ixgbe_hw *hw, u16 offset,
 
 	hw->eeprom.ops.init_params(hw);
 
-	if (words == 0)
-		return IXGBE_ERR_INVALID_ARGUMENT;
-
-	if (offset + words > hw->eeprom.word_size)
-		return IXGBE_ERR_EEPROM;
+	if (words == 0 || (offset + words > hw->eeprom.word_size))
+		return -EINVAL;
 
 	/*
 	 * We cannot hold synchronization semaphores for too long
@@ -1099,7 +1092,7 @@ static s32 ixgbe_read_eeprom_buffer_bit_bang(struct ixgbe_hw *hw, u16 offset,
 
 	if (ixgbe_ready_eeprom(hw) != 0) {
 		ixgbe_release_eeprom(hw);
-		return IXGBE_ERR_EEPROM;
+		return -EIO;
 	}
 
 	for (i = 0; i < words; i++) {
@@ -1142,7 +1135,7 @@ s32 ixgbe_read_eeprom_bit_bang_generic(struct ixgbe_hw *hw, u16 offset,
 	hw->eeprom.ops.init_params(hw);
 
 	if (offset >= hw->eeprom.word_size)
-		return IXGBE_ERR_EEPROM;
+		return -EINVAL;
 
 	return ixgbe_read_eeprom_buffer_bit_bang(hw, offset, 1, data);
 }
@@ -1165,11 +1158,8 @@ s32 ixgbe_read_eerd_buffer_generic(struct ixgbe_hw *hw, u16 offset,
 
 	hw->eeprom.ops.init_params(hw);
 
-	if (words == 0)
-		return IXGBE_ERR_INVALID_ARGUMENT;
-
-	if (offset >= hw->eeprom.word_size)
-		return IXGBE_ERR_EEPROM;
+	if (words == 0 || offset >= hw->eeprom.word_size)
+		return -EINVAL;
 
 	for (i = 0; i < words; i++) {
 		eerd = ((offset + i) << IXGBE_EEPROM_RW_ADDR_SHIFT) |
@@ -1262,11 +1252,8 @@ s32 ixgbe_write_eewr_buffer_generic(struct ixgbe_hw *hw, u16 offset,
 
 	hw->eeprom.ops.init_params(hw);
 
-	if (words == 0)
-		return IXGBE_ERR_INVALID_ARGUMENT;
-
-	if (offset >= hw->eeprom.word_size)
-		return IXGBE_ERR_EEPROM;
+	if (words == 0 || offset >= hw->eeprom.word_size)
+		return -EINVAL;
 
 	for (i = 0; i < words; i++) {
 		eewr = ((offset + i) << IXGBE_EEPROM_RW_ADDR_SHIFT) |
@@ -1328,7 +1315,7 @@ static s32 ixgbe_poll_eerd_eewr_done(struct ixgbe_hw *hw, u32 ee_reg)
 		}
 		udelay(5);
 	}
-	return IXGBE_ERR_EEPROM;
+	return -EIO;
 }
 
 /**
@@ -1344,7 +1331,7 @@ static s32 ixgbe_acquire_eeprom(struct ixgbe_hw *hw)
 	u32 i;
 
 	if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM) != 0)
-		return IXGBE_ERR_SWFW_SYNC;
+		return -EBUSY;
 
 	eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw));
 
@@ -1366,7 +1353,7 @@ static s32 ixgbe_acquire_eeprom(struct ixgbe_hw *hw)
 		hw_dbg(hw, "Could not acquire EEPROM grant\n");
 
 		hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM);
-		return IXGBE_ERR_EEPROM;
+		return -EIO;
 	}
 
 	/* Setup EEPROM for Read/Write */
@@ -1419,7 +1406,7 @@ static s32 ixgbe_get_eeprom_semaphore(struct ixgbe_hw *hw)
 		swsm = IXGBE_READ_REG(hw, IXGBE_SWSM(hw));
 		if (swsm & IXGBE_SWSM_SMBI) {
 			hw_dbg(hw, "Software semaphore SMBI between device drivers not granted.\n");
-			return IXGBE_ERR_EEPROM;
+			return -EIO;
 		}
 	}
 
@@ -1447,7 +1434,7 @@ static s32 ixgbe_get_eeprom_semaphore(struct ixgbe_hw *hw)
 	if (i >= timeout) {
 		hw_dbg(hw, "SWESMBI Software EEPROM semaphore not granted.\n");
 		ixgbe_release_eeprom_semaphore(hw);
-		return IXGBE_ERR_EEPROM;
+		return -EIO;
 	}
 
 	return 0;
@@ -1503,7 +1490,7 @@ static s32 ixgbe_ready_eeprom(struct ixgbe_hw *hw)
 	 */
 	if (i >= IXGBE_EEPROM_MAX_RETRY_SPI) {
 		hw_dbg(hw, "SPI EEPROM Status error\n");
-		return IXGBE_ERR_EEPROM;
+		return -EIO;
 	}
 
 	return 0;
@@ -1715,7 +1702,7 @@ s32 ixgbe_calc_eeprom_checksum_generic(struct ixgbe_hw *hw)
 	for (i = IXGBE_PCIE_ANALOG_PTR; i < IXGBE_FW_PTR; i++) {
 		if (hw->eeprom.ops.read(hw, i, &pointer)) {
 			hw_dbg(hw, "EEPROM read failed\n");
-			return IXGBE_ERR_EEPROM;
+			return -EIO;
 		}
 
 		/* If the pointer seems invalid */
@@ -1724,7 +1711,7 @@ s32 ixgbe_calc_eeprom_checksum_generic(struct ixgbe_hw *hw)
 
 		if (hw->eeprom.ops.read(hw, pointer, &length)) {
 			hw_dbg(hw, "EEPROM read failed\n");
-			return IXGBE_ERR_EEPROM;
+			return -EIO;
 		}
 
 		if (length == 0xFFFF || length == 0)
@@ -1733,7 +1720,7 @@ s32 ixgbe_calc_eeprom_checksum_generic(struct ixgbe_hw *hw)
 		for (j = pointer + 1; j <= pointer + length; j++) {
 			if (hw->eeprom.ops.read(hw, j, &word)) {
 				hw_dbg(hw, "EEPROM read failed\n");
-				return IXGBE_ERR_EEPROM;
+				return -EIO;
 			}
 			checksum += word;
 		}
@@ -1786,7 +1773,7 @@ s32 ixgbe_validate_eeprom_checksum_generic(struct ixgbe_hw *hw,
 	 * calculated checksum
 	 */
 	if (read_checksum != checksum)
-		status = IXGBE_ERR_EEPROM_CHECKSUM;
+		status = -EIO;
 
 	/* If the user cares, return the calculated checksum */
 	if (checksum_val)
@@ -1845,7 +1832,7 @@ s32 ixgbe_set_rar_generic(struct ixgbe_hw *hw, u32 index, u8 *addr, u32 vmdq,
 	/* Make sure we are using a valid rar index range */
 	if (index >= rar_entries) {
 		hw_dbg(hw, "RAR index %d is out of range.\n", index);
-		return IXGBE_ERR_INVALID_ARGUMENT;
+		return -EINVAL;
 	}
 
 	/* setup VMDq pool selection before this RAR gets enabled */
@@ -1897,7 +1884,7 @@ s32 ixgbe_clear_rar_generic(struct ixgbe_hw *hw, u32 index)
 	/* Make sure we are using a valid rar index range */
 	if (index >= rar_entries) {
 		hw_dbg(hw, "RAR index %d is out of range.\n", index);
-		return IXGBE_ERR_INVALID_ARGUMENT;
+		return -EINVAL;
 	}
 
 	/*
@@ -2146,7 +2133,7 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw)
 
 	/* Validate the water mark configuration. */
 	if (!hw->fc.pause_time)
-		return IXGBE_ERR_INVALID_LINK_SETTINGS;
+		return -EINVAL;
 
 	/* Low water mark of zero causes XOFF floods */
 	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
@@ -2155,7 +2142,7 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw)
 			if (!hw->fc.low_water[i] ||
 			    hw->fc.low_water[i] >= hw->fc.high_water[i]) {
 				hw_dbg(hw, "Invalid water mark configuration\n");
-				return IXGBE_ERR_INVALID_LINK_SETTINGS;
+				return -EINVAL;
 			}
 		}
 	}
@@ -2212,7 +2199,7 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw)
 		break;
 	default:
 		hw_dbg(hw, "Flow control param set incorrectly\n");
-		return IXGBE_ERR_CONFIG;
+		return -EIO;
 	}
 
 	/* Set 802.3x based flow control settings. */
@@ -2269,7 +2256,7 @@ s32 ixgbe_negotiate_fc(struct ixgbe_hw *hw, u32 adv_reg, u32 lp_reg,
 		       u32 adv_sym, u32 adv_asm, u32 lp_sym, u32 lp_asm)
 {
 	if ((!(adv_reg)) ||  (!(lp_reg)))
-		return IXGBE_ERR_FC_NOT_NEGOTIATED;
+		return -EINVAL;
 
 	if ((adv_reg & adv_sym) && (lp_reg & lp_sym)) {
 		/*
@@ -2321,7 +2308,7 @@ static s32 ixgbe_fc_autoneg_fiber(struct ixgbe_hw *hw)
 	linkstat = IXGBE_READ_REG(hw, IXGBE_PCS1GLSTA);
 	if ((!!(linkstat & IXGBE_PCS1GLSTA_AN_COMPLETE) == 0) ||
 	    (!!(linkstat & IXGBE_PCS1GLSTA_AN_TIMED_OUT) == 1))
-		return IXGBE_ERR_FC_NOT_NEGOTIATED;
+		return -EIO;
 
 	pcs_anadv_reg = IXGBE_READ_REG(hw, IXGBE_PCS1GANA);
 	pcs_lpab_reg = IXGBE_READ_REG(hw, IXGBE_PCS1GANLP);
@@ -2353,12 +2340,12 @@ static s32 ixgbe_fc_autoneg_backplane(struct ixgbe_hw *hw)
 	 */
 	links = IXGBE_READ_REG(hw, IXGBE_LINKS);
 	if ((links & IXGBE_LINKS_KX_AN_COMP) == 0)
-		return IXGBE_ERR_FC_NOT_NEGOTIATED;
+		return -EIO;
 
 	if (hw->mac.type == ixgbe_mac_82599EB) {
 		links2 = IXGBE_READ_REG(hw, IXGBE_LINKS2);
 		if ((links2 & IXGBE_LINKS2_AN_SUPPORTED) == 0)
-			return IXGBE_ERR_FC_NOT_NEGOTIATED;
+			return -EIO;
 	}
 	/*
 	 * Read the 10g AN autoc and LP ability registers and resolve
@@ -2407,8 +2394,8 @@ static s32 ixgbe_fc_autoneg_copper(struct ixgbe_hw *hw)
  **/
 void ixgbe_fc_autoneg(struct ixgbe_hw *hw)
 {
-	s32 ret_val = IXGBE_ERR_FC_NOT_NEGOTIATED;
 	ixgbe_link_speed speed;
+	s32 ret_val = -EIO;
 	bool link_up;
 
 	/*
@@ -2510,7 +2497,7 @@ static u32 ixgbe_pcie_timeout_poll(struct ixgbe_hw *hw)
  *  @hw: pointer to hardware structure
  *
  *  Disables PCI-Express primary access and verifies there are no pending
- *  requests. IXGBE_ERR_PRIMARY_REQUESTS_PENDING is returned if primary disable
+ *  requests. -EALREADY is returned if primary disable
  *  bit hasn't caused the primary requests to be disabled, else 0
  *  is returned signifying primary requests disabled.
  **/
@@ -2575,7 +2562,7 @@ gio_disable_fail:
 	}
 
 	hw_dbg(hw, "PCIe transaction pending bit also did not clear.\n");
-	return IXGBE_ERR_PRIMARY_REQUESTS_PENDING;
+	return -EALREADY;
 }
 
 /**
@@ -2600,7 +2587,7 @@ s32 ixgbe_acquire_swfw_sync(struct ixgbe_hw *hw, u32 mask)
 		 * SW_FW_SYNC bits (not just NVM)
 		 */
 		if (ixgbe_get_eeprom_semaphore(hw))
-			return IXGBE_ERR_SWFW_SYNC;
+			return -EBUSY;
 
 		gssr = IXGBE_READ_REG(hw, IXGBE_GSSR);
 		if (!(gssr & (fwmask | swmask))) {
@@ -2620,7 +2607,7 @@ s32 ixgbe_acquire_swfw_sync(struct ixgbe_hw *hw, u32 mask)
 		ixgbe_release_swfw_sync(hw, gssr & (fwmask | swmask));
 
 	usleep_range(5000, 10000);
-	return IXGBE_ERR_SWFW_SYNC;
+	return -EBUSY;
 }
 
 /**
@@ -2757,7 +2744,7 @@ s32 ixgbe_blink_led_start_generic(struct ixgbe_hw *hw, u32 index)
 	s32 ret_val;
 
 	if (index > 3)
-		return IXGBE_ERR_PARAM;
+		return -EINVAL;
 
 	/*
 	 * Link must be up to auto-blink the LEDs;
@@ -2803,7 +2790,7 @@ s32 ixgbe_blink_led_stop_generic(struct ixgbe_hw *hw, u32 index)
 	s32 ret_val;
 
 	if (index > 3)
-		return IXGBE_ERR_PARAM;
+		return -EINVAL;
 
 	ret_val = hw->mac.ops.prot_autoc_read(hw, &locked, &autoc_reg);
 	if (ret_val)
@@ -2963,7 +2950,7 @@ s32 ixgbe_clear_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq)
 	/* Make sure we are using a valid rar index range */
 	if (rar >= rar_entries) {
 		hw_dbg(hw, "RAR index %d is out of range.\n", rar);
-		return IXGBE_ERR_INVALID_ARGUMENT;
+		return -EINVAL;
 	}
 
 	mpsar_lo = IXGBE_READ_REG(hw, IXGBE_MPSAR_LO(rar));
@@ -3014,7 +3001,7 @@ s32 ixgbe_set_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq)
 	/* Make sure we are using a valid rar index range */
 	if (rar >= rar_entries) {
 		hw_dbg(hw, "RAR index %d is out of range.\n", rar);
-		return IXGBE_ERR_INVALID_ARGUMENT;
+		return -EINVAL;
 	}
 
 	if (vmdq < 32) {
@@ -3091,7 +3078,7 @@ static s32 ixgbe_find_vlvf_slot(struct ixgbe_hw *hw, u32 vlan, bool vlvf_bypass)
 	 * will simply bypass the VLVF if there are no entries present in the
 	 * VLVF that contain our VLAN
 	 */
-	first_empty_slot = vlvf_bypass ? IXGBE_ERR_NO_SPACE : 0;
+	first_empty_slot = vlvf_bypass ? -ENOSPC : 0;
 
 	/* add VLAN enable bit for comparison */
 	vlan |= IXGBE_VLVF_VIEN;
@@ -3115,7 +3102,7 @@ static s32 ixgbe_find_vlvf_slot(struct ixgbe_hw *hw, u32 vlan, bool vlvf_bypass)
 	if (!first_empty_slot)
 		hw_dbg(hw, "No space in VLVF.\n");
 
-	return first_empty_slot ? : IXGBE_ERR_NO_SPACE;
+	return first_empty_slot ? : -ENOSPC;
 }
 
 /**
@@ -3135,7 +3122,7 @@ s32 ixgbe_set_vfta_generic(struct ixgbe_hw *hw, u32 vlan, u32 vind,
 	s32 vlvf_index;
 
 	if ((vlan > 4095) || (vind > 63))
-		return IXGBE_ERR_PARAM;
+		return -EINVAL;
 
 	/*
 	 * this is a 2 part operation - first the VFTA, then the
@@ -3611,7 +3598,8 @@ u8 ixgbe_calculate_checksum(u8 *buffer, u32 length)
  *
  *  Communicates with the manageability block. On success return 0
  *  else returns semaphore error when encountering an error acquiring
- *  semaphore or IXGBE_ERR_HOST_INTERFACE_COMMAND when command fails.
+ *  semaphore, -EINVAL when incorrect parameters passed or -EIO when
+ *  command fails.
  *
  *  This function assumes that the IXGBE_GSSR_SW_MNG_SM semaphore is held
  *  by the caller.
@@ -3624,7 +3612,7 @@ s32 ixgbe_hic_unlocked(struct ixgbe_hw *hw, u32 *buffer, u32 length,
 
 	if (!length || length > IXGBE_HI_MAX_BLOCK_BYTE_LENGTH) {
 		hw_dbg(hw, "Buffer length failure buffersize-%d.\n", length);
-		return IXGBE_ERR_HOST_INTERFACE_COMMAND;
+		return -EINVAL;
 	}
 
 	/* Set bit 9 of FWSTS clearing FW reset indication */
@@ -3635,13 +3623,13 @@ s32 ixgbe_hic_unlocked(struct ixgbe_hw *hw, u32 *buffer, u32 length,
 	hicr = IXGBE_READ_REG(hw, IXGBE_HICR);
 	if (!(hicr & IXGBE_HICR_EN)) {
 		hw_dbg(hw, "IXGBE_HOST_EN bit disabled.\n");
-		return IXGBE_ERR_HOST_INTERFACE_COMMAND;
+		return -EIO;
 	}
 
 	/* Calculate length in DWORDs. We must be DWORD aligned */
 	if (length % sizeof(u32)) {
 		hw_dbg(hw, "Buffer length failure, not aligned to dword");
-		return IXGBE_ERR_INVALID_ARGUMENT;
+		return -EINVAL;
 	}
 
 	dword_len = length >> 2;
@@ -3666,7 +3654,7 @@ s32 ixgbe_hic_unlocked(struct ixgbe_hw *hw, u32 *buffer, u32 length,
 	/* Check command successful completion. */
 	if ((timeout && i == timeout) ||
 	    !(IXGBE_READ_REG(hw, IXGBE_HICR) & IXGBE_HICR_SV))
-		return IXGBE_ERR_HOST_INTERFACE_COMMAND;
+		return -EIO;
 
 	return 0;
 }
@@ -3686,7 +3674,7 @@ s32 ixgbe_hic_unlocked(struct ixgbe_hw *hw, u32 *buffer, u32 length,
  *  in these cases.
  *
  *  Communicates with the manageability block.  On success return 0
- *  else return IXGBE_ERR_HOST_INTERFACE_COMMAND.
+ *  else return -EIO or -EINVAL.
  **/
 s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer,
 				 u32 length, u32 timeout,
@@ -3701,7 +3689,7 @@ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer,
 
 	if (!length || length > IXGBE_HI_MAX_BLOCK_BYTE_LENGTH) {
 		hw_dbg(hw, "Buffer length failure buffersize-%d.\n", length);
-		return IXGBE_ERR_HOST_INTERFACE_COMMAND;
+		return -EINVAL;
 	}
 	/* Take management host interface semaphore */
 	status = hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_SW_MNG_SM);
@@ -3731,7 +3719,7 @@ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer,
 
 	if (length < round_up(buf_len, 4) + hdr_size) {
 		hw_dbg(hw, "Buffer not large enough for reply message.\n");
-		status = IXGBE_ERR_HOST_INTERFACE_COMMAND;
+		status = -EIO;
 		goto rel_out;
 	}
 
@@ -3762,8 +3750,8 @@ rel_out:
  *
  *  Sends driver version number to firmware through the manageability
  *  block.  On success return 0
- *  else returns IXGBE_ERR_SWFW_SYNC when encountering an error acquiring
- *  semaphore or IXGBE_ERR_HOST_INTERFACE_COMMAND when command fails.
+ *  else returns -EBUSY when encountering an error acquiring
+ *  semaphore or -EIO when command fails.
  **/
 s32 ixgbe_set_fw_drv_ver_generic(struct ixgbe_hw *hw, u8 maj, u8 min,
 				 u8 build, u8 sub, __always_unused u16 len,
@@ -3799,7 +3787,7 @@ s32 ixgbe_set_fw_drv_ver_generic(struct ixgbe_hw *hw, u8 maj, u8 min,
 		    FW_CEM_RESP_STATUS_SUCCESS)
 			ret_val = 0;
 		else
-			ret_val = IXGBE_ERR_HOST_INTERFACE_COMMAND;
+			ret_val = -EIO;
 
 		break;
 	}
@@ -3897,14 +3885,14 @@ static s32 ixgbe_get_ets_data(struct ixgbe_hw *hw, u16 *ets_cfg,
 		return status;
 
 	if ((*ets_offset == 0x0000) || (*ets_offset == 0xFFFF))
-		return IXGBE_NOT_IMPLEMENTED;
+		return -EOPNOTSUPP;
 
 	status = hw->eeprom.ops.read(hw, *ets_offset, ets_cfg);
 	if (status)
 		return status;
 
 	if ((*ets_cfg & IXGBE_ETS_TYPE_MASK) != IXGBE_ETS_TYPE_EMC_SHIFTED)
-		return IXGBE_NOT_IMPLEMENTED;
+		return -EOPNOTSUPP;
 
 	return 0;
 }
@@ -3927,7 +3915,7 @@ s32 ixgbe_get_thermal_sensor_data_generic(struct ixgbe_hw *hw)
 
 	/* Only support thermal sensors attached to physical port 0 */
 	if ((IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1))
-		return IXGBE_NOT_IMPLEMENTED;
+		return -EOPNOTSUPP;
 
 	status = ixgbe_get_ets_data(hw, &ets_cfg, &ets_offset);
 	if (status)
@@ -3946,10 +3934,10 @@ s32 ixgbe_get_thermal_sensor_data_generic(struct ixgbe_hw *hw)
 		if (status)
 			return status;
 
-		sensor_index = ((ets_sensor & IXGBE_ETS_DATA_INDEX_MASK) >>
-				IXGBE_ETS_DATA_INDEX_SHIFT);
-		sensor_location = ((ets_sensor & IXGBE_ETS_DATA_LOC_MASK) >>
-				   IXGBE_ETS_DATA_LOC_SHIFT);
+		sensor_index = FIELD_GET(IXGBE_ETS_DATA_INDEX_MASK,
+					 ets_sensor);
+		sensor_location = FIELD_GET(IXGBE_ETS_DATA_LOC_MASK,
+					    ets_sensor);
 
 		if (sensor_location != 0) {
 			status = hw->phy.ops.read_i2c_byte(hw,
@@ -3987,14 +3975,13 @@ s32 ixgbe_init_thermal_sensor_thresh_generic(struct ixgbe_hw *hw)
 
 	/* Only support thermal sensors attached to physical port 0 */
 	if ((IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1))
-		return IXGBE_NOT_IMPLEMENTED;
+		return -EOPNOTSUPP;
 
 	status = ixgbe_get_ets_data(hw, &ets_cfg, &ets_offset);
 	if (status)
 		return status;
 
-	low_thresh_delta = ((ets_cfg & IXGBE_ETS_LTHRES_DELTA_MASK) >>
-			     IXGBE_ETS_LTHRES_DELTA_SHIFT);
+	low_thresh_delta = FIELD_GET(IXGBE_ETS_LTHRES_DELTA_MASK, ets_cfg);
 	num_sensors = (ets_cfg & IXGBE_ETS_NUM_SENSORS_MASK);
 	if (num_sensors > IXGBE_MAX_SENSORS)
 		num_sensors = IXGBE_MAX_SENSORS;
@@ -4008,10 +3995,10 @@ s32 ixgbe_init_thermal_sensor_thresh_generic(struct ixgbe_hw *hw)
 			       ets_offset + 1 + i);
 			continue;
 		}
-		sensor_index = ((ets_sensor & IXGBE_ETS_DATA_INDEX_MASK) >>
-				IXGBE_ETS_DATA_INDEX_SHIFT);
-		sensor_location = ((ets_sensor & IXGBE_ETS_DATA_LOC_MASK) >>
-				   IXGBE_ETS_DATA_LOC_SHIFT);
+		sensor_index = FIELD_GET(IXGBE_ETS_DATA_INDEX_MASK,
+					 ets_sensor);
+		sensor_location = FIELD_GET(IXGBE_ETS_DATA_LOC_MASK,
+					    ets_sensor);
 		therm_limit = ets_sensor & IXGBE_ETS_DATA_HTHRESH_MASK;
 
 		hw->phy.ops.write_i2c_byte(hw,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 4dd897806fa5..9a63457712c7 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -1413,12 +1413,11 @@ static void ixgbe_get_strings(struct net_device *netdev, u32 stringset,
 	switch (stringset) {
 	case ETH_SS_TEST:
 		for (i = 0; i < IXGBE_TEST_LEN; i++)
-			ethtool_sprintf(&p, "%s", ixgbe_gstrings_test[i]);
+			ethtool_puts(&p, ixgbe_gstrings_test[i]);
 		break;
 	case ETH_SS_STATS:
 		for (i = 0; i < IXGBE_GLOBAL_STATS_LEN; i++)
-			ethtool_sprintf(&p, "%s",
-					ixgbe_gstrings_stats[i].stat_string);
+			ethtool_puts(&p, ixgbe_gstrings_stats[i].stat_string);
 		for (i = 0; i < netdev->num_tx_queues; i++) {
 			ethtool_sprintf(&p, "tx_queue_%u_packets", i);
 			ethtool_sprintf(&p, "tx_queue_%u_bytes", i);
@@ -3108,35 +3107,37 @@ static void ixgbe_get_reta(struct ixgbe_adapter *adapter, u32 *indir)
 		indir[i] = adapter->rss_indir_tbl[i] & rss_m;
 }
 
-static int ixgbe_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			  u8 *hfunc)
+static int ixgbe_get_rxfh(struct net_device *netdev,
+			  struct ethtool_rxfh_param *rxfh)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
-	if (indir)
-		ixgbe_get_reta(adapter, indir);
+	if (rxfh->indir)
+		ixgbe_get_reta(adapter, rxfh->indir);
 
-	if (key)
-		memcpy(key, adapter->rss_key, ixgbe_get_rxfh_key_size(netdev));
+	if (rxfh->key)
+		memcpy(rxfh->key, adapter->rss_key,
+		       ixgbe_get_rxfh_key_size(netdev));
 
 	return 0;
 }
 
-static int ixgbe_set_rxfh(struct net_device *netdev, const u32 *indir,
-			  const u8 *key, const u8 hfunc)
+static int ixgbe_set_rxfh(struct net_device *netdev,
+			  struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	int i;
 	u32 reta_entries = ixgbe_rss_indir_tbl_entries(adapter);
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
 	/* Fill out the redirection table */
-	if (indir) {
+	if (rxfh->indir) {
 		int max_queues = min_t(int, adapter->num_rx_queues,
 				       ixgbe_rss_indir_tbl_max(adapter));
 
@@ -3147,18 +3148,19 @@ static int ixgbe_set_rxfh(struct net_device *netdev, const u32 *indir,
 
 		/* Verify user input. */
 		for (i = 0; i < reta_entries; i++)
-			if (indir[i] >= max_queues)
+			if (rxfh->indir[i] >= max_queues)
 				return -EINVAL;
 
 		for (i = 0; i < reta_entries; i++)
-			adapter->rss_indir_tbl[i] = indir[i];
+			adapter->rss_indir_tbl[i] = rxfh->indir[i];
 
 		ixgbe_store_reta(adapter);
 	}
 
 	/* Fill out the rss hash key */
-	if (key) {
-		memcpy(adapter->rss_key, key, ixgbe_get_rxfh_key_size(netdev));
+	if (rxfh->key) {
+		memcpy(adapter->rss_key, rxfh->key,
+		       ixgbe_get_rxfh_key_size(netdev));
 		ixgbe_store_key(adapter);
 	}
 
@@ -3370,7 +3372,7 @@ static int ixgbe_get_module_eeprom(struct net_device *dev,
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
-	s32 status = IXGBE_ERR_PHY_ADDR_INVALID;
+	s32 status = -EFAULT;
 	u8 databyte = 0xFF;
 	int i = 0;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
index 7311bd545acf..18d63c8c2ff4 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
@@ -670,8 +670,8 @@ void ixgbe_configure_fcoe(struct ixgbe_adapter *adapter)
 			int fcoe_i_h = fcoe->offset + ((i + fcreta_size) %
 							fcoe->indices);
 			fcoe_q_h = adapter->rx_ring[fcoe_i_h]->reg_idx;
-			fcoe_q_h = (fcoe_q_h << IXGBE_FCRETA_ENTRY_HIGH_SHIFT) &
-				   IXGBE_FCRETA_ENTRY_HIGH_MASK;
+			fcoe_q_h = FIELD_PREP(IXGBE_FCRETA_ENTRY_HIGH_MASK,
+					      fcoe_q_h);
 		}
 
 		fcoe_i = fcoe->offset + (i % fcoe->indices);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 94bde2cad0f4..bd541527c8c7 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2756,7 +2756,6 @@ static void ixgbe_check_overtemp_subtask(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 eicr = adapter->interrupt_event;
-	s32 rc;
 
 	if (test_bit(__IXGBE_DOWN, &adapter->state))
 		return;
@@ -2790,14 +2789,13 @@ static void ixgbe_check_overtemp_subtask(struct ixgbe_adapter *adapter)
 		}
 
 		/* Check if this is not due to overtemp */
-		if (hw->phy.ops.check_overtemp(hw) != IXGBE_ERR_OVERTEMP)
+		if (!hw->phy.ops.check_overtemp(hw))
 			return;
 
 		break;
 	case IXGBE_DEV_ID_X550EM_A_1G_T:
 	case IXGBE_DEV_ID_X550EM_A_1G_T_L:
-		rc = hw->phy.ops.check_overtemp(hw);
-		if (rc != IXGBE_ERR_OVERTEMP)
+		if (!hw->phy.ops.check_overtemp(hw))
 			return;
 		break;
 	default:
@@ -5512,7 +5510,7 @@ static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw)
 {
 	u32 speed;
 	bool autoneg, link_up = false;
-	int ret = IXGBE_ERR_LINK_SETUP;
+	int ret = -EIO;
 
 	if (hw->mac.ops.check_link)
 		ret = hw->mac.ops.check_link(hw, &speed, &link_up, false);
@@ -5983,13 +5981,13 @@ void ixgbe_reset(struct ixgbe_adapter *adapter)
 	err = hw->mac.ops.init_hw(hw);
 	switch (err) {
 	case 0:
-	case IXGBE_ERR_SFP_NOT_PRESENT:
-	case IXGBE_ERR_SFP_NOT_SUPPORTED:
+	case -ENOENT:
+	case -EOPNOTSUPP:
 		break;
-	case IXGBE_ERR_PRIMARY_REQUESTS_PENDING:
+	case -EALREADY:
 		e_dev_err("primary disable timed out\n");
 		break;
-	case IXGBE_ERR_EEPROM_VERSION:
+	case -EACCES:
 		/* We are running on a pre-production device, log a warning */
 		e_dev_warn("This device is a pre-production adapter/LOM. "
 			   "Please be aware there may be issues associated with "
@@ -7829,10 +7827,10 @@ static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter)
 	adapter->sfp_poll_time = jiffies + IXGBE_SFP_POLL_JIFFIES - 1;
 
 	err = hw->phy.ops.identify_sfp(hw);
-	if (err == IXGBE_ERR_SFP_NOT_SUPPORTED)
+	if (err == -EOPNOTSUPP)
 		goto sfp_out;
 
-	if (err == IXGBE_ERR_SFP_NOT_PRESENT) {
+	if (err == -ENOENT) {
 		/* If no cable is present, then we need to reset
 		 * the next time we find a good cable. */
 		adapter->flags2 |= IXGBE_FLAG2_SFP_NEEDS_RESET;
@@ -7858,7 +7856,7 @@ static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter)
 	else
 		err = hw->mac.ops.setup_sfp(hw);
 
-	if (err == IXGBE_ERR_SFP_NOT_SUPPORTED)
+	if (err == -EOPNOTSUPP)
 		goto sfp_out;
 
 	adapter->flags |= IXGBE_FLAG_NEED_LINK_CONFIG;
@@ -7867,8 +7865,8 @@ static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter)
 sfp_out:
 	clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state);
 
-	if ((err == IXGBE_ERR_SFP_NOT_SUPPORTED) &&
-	    (adapter->netdev->reg_state == NETREG_REGISTERED)) {
+	if (err == -EOPNOTSUPP &&
+	    adapter->netdev->reg_state == NETREG_REGISTERED) {
 		e_dev_err("failed to initialize because an unsupported "
 			  "SFP+ module type was detected.\n");
 		e_dev_err("Reload the driver after installing a "
@@ -7938,7 +7936,7 @@ static void ixgbe_service_timer(struct timer_list *t)
 static void ixgbe_phy_interrupt_subtask(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
-	u32 status;
+	bool overtemp;
 
 	if (!(adapter->flags2 & IXGBE_FLAG2_PHY_INTERRUPT))
 		return;
@@ -7948,11 +7946,9 @@ static void ixgbe_phy_interrupt_subtask(struct ixgbe_adapter *adapter)
 	if (!hw->phy.ops.handle_lasi)
 		return;
 
-	status = hw->phy.ops.handle_lasi(&adapter->hw);
-	if (status != IXGBE_ERR_OVERTEMP)
-		return;
-
-	e_crit(drv, "%s\n", ixgbe_overheat_msg);
+	hw->phy.ops.handle_lasi(&adapter->hw, &overtemp);
+	if (overtemp)
+		e_crit(drv, "%s\n", ixgbe_overheat_msg);
 }
 
 static void ixgbe_reset_subtask(struct ixgbe_adapter *adapter)
@@ -10922,9 +10918,9 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	err = hw->mac.ops.reset_hw(hw);
 	hw->phy.reset_if_overtemp = false;
 	ixgbe_set_eee_capable(adapter);
-	if (err == IXGBE_ERR_SFP_NOT_PRESENT) {
+	if (err == -ENOENT) {
 		err = 0;
-	} else if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) {
+	} else if (err == -EOPNOTSUPP) {
 		e_dev_err("failed to load because an unsupported SFP+ or QSFP module type was detected.\n");
 		e_dev_err("Reload the driver after installing a supported module.\n");
 		goto err_sw_init;
@@ -11143,7 +11139,7 @@ skip_sriov:
 
 	/* reset the hardware with the new settings */
 	err = hw->mac.ops.start_hw(hw);
-	if (err == IXGBE_ERR_EEPROM_VERSION) {
+	if (err == -EACCES) {
 		/* We are running on a pre-production device, log a warning */
 		e_dev_warn("This device is a pre-production adapter/LOM. "
 			   "Please be aware there may be issues associated "
@@ -11371,7 +11367,7 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev,
 	if ((pf_func & 1) == (pdev->devfn & 1)) {
 		unsigned int device_id;
 
-		vf = (req_id & 0x7F) >> 1;
+		vf = FIELD_GET(0x7F, req_id);
 		e_dev_err("VF %d has caused a PCIe error\n", vf);
 		e_dev_err("TLP: dw0: %8.8x\tdw1: %8.8x\tdw2: "
 				"%8.8x\tdw3: %8.8x\n",
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c
index 5679293e53f7..fe7ef5773369 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c
@@ -24,7 +24,7 @@ s32 ixgbe_read_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, u16 mbx_id)
 		size = mbx->size;
 
 	if (!mbx->ops)
-		return IXGBE_ERR_MBX;
+		return -EIO;
 
 	return mbx->ops->read(hw, msg, size, mbx_id);
 }
@@ -43,10 +43,10 @@ s32 ixgbe_write_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, u16 mbx_id)
 	struct ixgbe_mbx_info *mbx = &hw->mbx;
 
 	if (size > mbx->size)
-		return IXGBE_ERR_MBX;
+		return -EINVAL;
 
 	if (!mbx->ops)
-		return IXGBE_ERR_MBX;
+		return -EIO;
 
 	return mbx->ops->write(hw, msg, size, mbx_id);
 }
@@ -63,7 +63,7 @@ s32 ixgbe_check_for_msg(struct ixgbe_hw *hw, u16 mbx_id)
 	struct ixgbe_mbx_info *mbx = &hw->mbx;
 
 	if (!mbx->ops)
-		return IXGBE_ERR_MBX;
+		return -EIO;
 
 	return mbx->ops->check_for_msg(hw, mbx_id);
 }
@@ -80,7 +80,7 @@ s32 ixgbe_check_for_ack(struct ixgbe_hw *hw, u16 mbx_id)
 	struct ixgbe_mbx_info *mbx = &hw->mbx;
 
 	if (!mbx->ops)
-		return IXGBE_ERR_MBX;
+		return -EIO;
 
 	return mbx->ops->check_for_ack(hw, mbx_id);
 }
@@ -97,7 +97,7 @@ s32 ixgbe_check_for_rst(struct ixgbe_hw *hw, u16 mbx_id)
 	struct ixgbe_mbx_info *mbx = &hw->mbx;
 
 	if (!mbx->ops)
-		return IXGBE_ERR_MBX;
+		return -EIO;
 
 	return mbx->ops->check_for_rst(hw, mbx_id);
 }
@@ -115,12 +115,12 @@ static s32 ixgbe_poll_for_msg(struct ixgbe_hw *hw, u16 mbx_id)
 	int countdown = mbx->timeout;
 
 	if (!countdown || !mbx->ops)
-		return IXGBE_ERR_MBX;
+		return -EIO;
 
 	while (mbx->ops->check_for_msg(hw, mbx_id)) {
 		countdown--;
 		if (!countdown)
-			return IXGBE_ERR_MBX;
+			return -EIO;
 		udelay(mbx->usec_delay);
 	}
 
@@ -140,12 +140,12 @@ static s32 ixgbe_poll_for_ack(struct ixgbe_hw *hw, u16 mbx_id)
 	int countdown = mbx->timeout;
 
 	if (!countdown || !mbx->ops)
-		return IXGBE_ERR_MBX;
+		return -EIO;
 
 	while (mbx->ops->check_for_ack(hw, mbx_id)) {
 		countdown--;
 		if (!countdown)
-			return IXGBE_ERR_MBX;
+			return -EIO;
 		udelay(mbx->usec_delay);
 	}
 
@@ -169,7 +169,7 @@ static s32 ixgbe_read_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size,
 	s32 ret_val;
 
 	if (!mbx->ops)
-		return IXGBE_ERR_MBX;
+		return -EIO;
 
 	ret_val = ixgbe_poll_for_msg(hw, mbx_id);
 	if (ret_val)
@@ -197,7 +197,7 @@ static s32 ixgbe_write_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size,
 
 	/* exit if either we can't write or there isn't a defined timeout */
 	if (!mbx->ops || !mbx->timeout)
-		return IXGBE_ERR_MBX;
+		return -EIO;
 
 	/* send msg */
 	ret_val = mbx->ops->write(hw, msg, size, mbx_id);
@@ -217,7 +217,7 @@ static s32 ixgbe_check_for_bit_pf(struct ixgbe_hw *hw, u32 mask, s32 index)
 		return 0;
 	}
 
-	return IXGBE_ERR_MBX;
+	return -EIO;
 }
 
 /**
@@ -238,7 +238,7 @@ static s32 ixgbe_check_for_msg_pf(struct ixgbe_hw *hw, u16 vf_number)
 		return 0;
 	}
 
-	return IXGBE_ERR_MBX;
+	return -EIO;
 }
 
 /**
@@ -259,7 +259,7 @@ static s32 ixgbe_check_for_ack_pf(struct ixgbe_hw *hw, u16 vf_number)
 		return 0;
 	}
 
-	return IXGBE_ERR_MBX;
+	return -EIO;
 }
 
 /**
@@ -295,7 +295,7 @@ static s32 ixgbe_check_for_rst_pf(struct ixgbe_hw *hw, u16 vf_number)
 		return 0;
 	}
 
-	return IXGBE_ERR_MBX;
+	return -EIO;
 }
 
 /**
@@ -317,7 +317,7 @@ static s32 ixgbe_obtain_mbx_lock_pf(struct ixgbe_hw *hw, u16 vf_number)
 	if (p2v_mailbox & IXGBE_PFMAILBOX_PFU)
 		return 0;
 
-	return IXGBE_ERR_MBX;
+	return -EIO;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h
index 8f4316b19278..6434c190e7a4 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h
@@ -7,7 +7,6 @@
 #include "ixgbe_type.h"
 
 #define IXGBE_VFMAILBOX_SIZE        16 /* 16 32 bit words - 64 bytes */
-#define IXGBE_ERR_MBX               -100
 
 #define IXGBE_VFMAILBOX             0x002FC
 #define IXGBE_VFMBMEM               0x00200
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
index 689470c1e8ad..f28140a05f09 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
@@ -102,7 +102,7 @@ s32 ixgbe_read_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr,
 	csum = ~csum;
 	do {
 		if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask))
-			return IXGBE_ERR_SWFW_SYNC;
+			return -EBUSY;
 		ixgbe_i2c_start(hw);
 		/* Device Address and write indication */
 		if (ixgbe_out_i2c_byte_ack(hw, addr))
@@ -150,7 +150,7 @@ fail:
 			hw_dbg(hw, "I2C byte read combined error.\n");
 	} while (retry < max_retry);
 
-	return IXGBE_ERR_I2C;
+	return -EIO;
 }
 
 /**
@@ -179,7 +179,7 @@ s32 ixgbe_write_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr,
 	csum = ~csum;
 	do {
 		if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask))
-			return IXGBE_ERR_SWFW_SYNC;
+			return -EBUSY;
 		ixgbe_i2c_start(hw);
 		/* Device Address and write indication */
 		if (ixgbe_out_i2c_byte_ack(hw, addr))
@@ -215,7 +215,7 @@ fail:
 			hw_dbg(hw, "I2C byte write combined error.\n");
 	} while (retry < max_retry);
 
-	return IXGBE_ERR_I2C;
+	return -EIO;
 }
 
 /**
@@ -262,8 +262,8 @@ static bool ixgbe_probe_phy(struct ixgbe_hw *hw, u16 phy_addr)
  **/
 s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw)
 {
+	u32 status = -EFAULT;
 	u32 phy_addr;
-	u32 status = IXGBE_ERR_PHY_ADDR_INVALID;
 
 	if (!hw->phy.phy_semaphore_mask) {
 		if (hw->bus.lan_id)
@@ -276,13 +276,12 @@ s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw)
 		return 0;
 
 	if (hw->phy.nw_mng_if_sel) {
-		phy_addr = (hw->phy.nw_mng_if_sel &
-			    IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD) >>
-			   IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD_SHIFT;
+		phy_addr = FIELD_GET(IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD,
+				     hw->phy.nw_mng_if_sel);
 		if (ixgbe_probe_phy(hw, phy_addr))
 			return 0;
 		else
-			return IXGBE_ERR_PHY_ADDR_INVALID;
+			return -EFAULT;
 	}
 
 	for (phy_addr = 0; phy_addr < IXGBE_MAX_PHY_ADDR; phy_addr++) {
@@ -408,8 +407,7 @@ s32 ixgbe_reset_phy_generic(struct ixgbe_hw *hw)
 		return status;
 
 	/* Don't reset PHY if it's shut down due to overtemp. */
-	if (!hw->phy.reset_if_overtemp &&
-	    (IXGBE_ERR_OVERTEMP == hw->phy.ops.check_overtemp(hw)))
+	if (!hw->phy.reset_if_overtemp && hw->phy.ops.check_overtemp(hw))
 		return 0;
 
 	/* Blocked by MNG FW so bail */
@@ -457,7 +455,7 @@ s32 ixgbe_reset_phy_generic(struct ixgbe_hw *hw)
 
 	if (ctrl & MDIO_CTRL1_RESET) {
 		hw_dbg(hw, "PHY reset polling failed to complete.\n");
-		return IXGBE_ERR_RESET_FAILED;
+		return -EIO;
 	}
 
 	return 0;
@@ -500,7 +498,7 @@ s32 ixgbe_read_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, u32 device_type,
 
 	if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) {
 		hw_dbg(hw, "PHY address command did not complete.\n");
-		return IXGBE_ERR_PHY;
+		return -EIO;
 	}
 
 	/* Address cycle complete, setup and write the read
@@ -527,7 +525,7 @@ s32 ixgbe_read_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, u32 device_type,
 
 	if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) {
 		hw_dbg(hw, "PHY read command didn't complete\n");
-		return IXGBE_ERR_PHY;
+		return -EIO;
 	}
 
 	/* Read operation is complete.  Get the data
@@ -559,7 +557,7 @@ s32 ixgbe_read_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr,
 						phy_data);
 		hw->mac.ops.release_swfw_sync(hw, gssr);
 	} else {
-		return IXGBE_ERR_SWFW_SYNC;
+		return -EBUSY;
 	}
 
 	return status;
@@ -604,7 +602,7 @@ s32 ixgbe_write_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr,
 
 	if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) {
 		hw_dbg(hw, "PHY address cmd didn't complete\n");
-		return IXGBE_ERR_PHY;
+		return -EIO;
 	}
 
 	/*
@@ -632,7 +630,7 @@ s32 ixgbe_write_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr,
 
 	if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) {
 		hw_dbg(hw, "PHY write cmd didn't complete\n");
-		return IXGBE_ERR_PHY;
+		return -EIO;
 	}
 
 	return 0;
@@ -657,7 +655,7 @@ s32 ixgbe_write_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr,
 						 phy_data);
 		hw->mac.ops.release_swfw_sync(hw, gssr);
 	} else {
-		return IXGBE_ERR_SWFW_SYNC;
+		return -EBUSY;
 	}
 
 	return status;
@@ -1430,7 +1428,7 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw)
 
 	if ((phy_data & MDIO_CTRL1_RESET) != 0) {
 		hw_dbg(hw, "PHY reset did not complete.\n");
-		return IXGBE_ERR_PHY;
+		return -EIO;
 	}
 
 	/* Get init offsets */
@@ -1448,8 +1446,7 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw)
 		ret_val = hw->eeprom.ops.read(hw, data_offset, &eword);
 		if (ret_val)
 			goto err_eeprom;
-		control = (eword & IXGBE_CONTROL_MASK_NL) >>
-			   IXGBE_CONTROL_SHIFT_NL;
+		control = FIELD_GET(IXGBE_CONTROL_MASK_NL, eword);
 		edata = eword & IXGBE_DATA_MASK_NL;
 		switch (control) {
 		case IXGBE_DELAY_NL:
@@ -1487,12 +1484,12 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw)
 				hw_dbg(hw, "SOL\n");
 			} else {
 				hw_dbg(hw, "Bad control value\n");
-				return IXGBE_ERR_PHY;
+				return -EIO;
 			}
 			break;
 		default:
 			hw_dbg(hw, "Bad control type\n");
-			return IXGBE_ERR_PHY;
+			return -EIO;
 		}
 	}
 
@@ -1500,7 +1497,7 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw)
 
 err_eeprom:
 	hw_err(hw, "eeprom read at offset %d failed\n", data_offset);
-	return IXGBE_ERR_PHY;
+	return -EIO;
 }
 
 /**
@@ -1518,10 +1515,10 @@ s32 ixgbe_identify_module_generic(struct ixgbe_hw *hw)
 		return ixgbe_identify_qsfp_module_generic(hw);
 	default:
 		hw->phy.sfp_type = ixgbe_sfp_type_not_present;
-		return IXGBE_ERR_SFP_NOT_PRESENT;
+		return -ENOENT;
 	}
 
-	return IXGBE_ERR_SFP_NOT_PRESENT;
+	return -ENOENT;
 }
 
 /**
@@ -1546,7 +1543,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw)
 
 	if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_fiber) {
 		hw->phy.sfp_type = ixgbe_sfp_type_not_present;
-		return IXGBE_ERR_SFP_NOT_PRESENT;
+		return -ENOENT;
 	}
 
 	/* LAN ID is needed for sfp_type determination */
@@ -1561,7 +1558,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw)
 
 	if (identifier != IXGBE_SFF_IDENTIFIER_SFP) {
 		hw->phy.type = ixgbe_phy_sfp_unsupported;
-		return IXGBE_ERR_SFP_NOT_SUPPORTED;
+		return -EOPNOTSUPP;
 	}
 	status = hw->phy.ops.read_i2c_eeprom(hw,
 					     IXGBE_SFF_1GBE_COMP_CODES,
@@ -1752,7 +1749,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw)
 	      hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 ||
 	      hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1)) {
 		hw->phy.type = ixgbe_phy_sfp_unsupported;
-		return IXGBE_ERR_SFP_NOT_SUPPORTED;
+		return -EOPNOTSUPP;
 	}
 
 	/* Anything else 82598-based is supported */
@@ -1776,7 +1773,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw)
 		}
 		hw_dbg(hw, "SFP+ module not supported\n");
 		hw->phy.type = ixgbe_phy_sfp_unsupported;
-		return IXGBE_ERR_SFP_NOT_SUPPORTED;
+		return -EOPNOTSUPP;
 	}
 	return 0;
 
@@ -1786,7 +1783,7 @@ err_read_i2c_eeprom:
 		hw->phy.id = 0;
 		hw->phy.type = ixgbe_phy_unknown;
 	}
-	return IXGBE_ERR_SFP_NOT_PRESENT;
+	return -ENOENT;
 }
 
 /**
@@ -1813,7 +1810,7 @@ static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw)
 
 	if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_fiber_qsfp) {
 		hw->phy.sfp_type = ixgbe_sfp_type_not_present;
-		return IXGBE_ERR_SFP_NOT_PRESENT;
+		return -ENOENT;
 	}
 
 	/* LAN ID is needed for sfp_type determination */
@@ -1827,7 +1824,7 @@ static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw)
 
 	if (identifier != IXGBE_SFF_IDENTIFIER_QSFP_PLUS) {
 		hw->phy.type = ixgbe_phy_sfp_unsupported;
-		return IXGBE_ERR_SFP_NOT_SUPPORTED;
+		return -EOPNOTSUPP;
 	}
 
 	hw->phy.id = identifier;
@@ -1895,7 +1892,7 @@ static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw)
 		} else {
 			/* unsupported module type */
 			hw->phy.type = ixgbe_phy_sfp_unsupported;
-			return IXGBE_ERR_SFP_NOT_SUPPORTED;
+			return -EOPNOTSUPP;
 		}
 	}
 
@@ -1955,7 +1952,7 @@ static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw)
 			}
 			hw_dbg(hw, "QSFP module not supported\n");
 			hw->phy.type = ixgbe_phy_sfp_unsupported;
-			return IXGBE_ERR_SFP_NOT_SUPPORTED;
+			return -EOPNOTSUPP;
 		}
 		return 0;
 	}
@@ -1966,7 +1963,7 @@ err_read_i2c_eeprom:
 	hw->phy.id = 0;
 	hw->phy.type = ixgbe_phy_unknown;
 
-	return IXGBE_ERR_SFP_NOT_PRESENT;
+	return -ENOENT;
 }
 
 /**
@@ -1986,14 +1983,14 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw,
 	u16 sfp_type = hw->phy.sfp_type;
 
 	if (hw->phy.sfp_type == ixgbe_sfp_type_unknown)
-		return IXGBE_ERR_SFP_NOT_SUPPORTED;
+		return -EOPNOTSUPP;
 
 	if (hw->phy.sfp_type == ixgbe_sfp_type_not_present)
-		return IXGBE_ERR_SFP_NOT_PRESENT;
+		return -ENOENT;
 
 	if ((hw->device_id == IXGBE_DEV_ID_82598_SR_DUAL_PORT_EM) &&
 	    (hw->phy.sfp_type == ixgbe_sfp_type_da_cu))
-		return IXGBE_ERR_SFP_NOT_SUPPORTED;
+		return -EOPNOTSUPP;
 
 	/*
 	 * Limiting active cables and 1G Phys must be initialized as
@@ -2014,11 +2011,11 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw,
 	if (hw->eeprom.ops.read(hw, IXGBE_PHY_INIT_OFFSET_NL, list_offset)) {
 		hw_err(hw, "eeprom read at %d failed\n",
 		       IXGBE_PHY_INIT_OFFSET_NL);
-		return IXGBE_ERR_SFP_NO_INIT_SEQ_PRESENT;
+		return -EIO;
 	}
 
 	if ((!*list_offset) || (*list_offset == 0xFFFF))
-		return IXGBE_ERR_SFP_NO_INIT_SEQ_PRESENT;
+		return -EIO;
 
 	/* Shift offset to first ID word */
 	(*list_offset)++;
@@ -2037,7 +2034,7 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw,
 				goto err_phy;
 			if ((!*data_offset) || (*data_offset == 0xFFFF)) {
 				hw_dbg(hw, "SFP+ module not supported\n");
-				return IXGBE_ERR_SFP_NOT_SUPPORTED;
+				return -EOPNOTSUPP;
 			} else {
 				break;
 			}
@@ -2050,14 +2047,14 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw,
 
 	if (sfp_id == IXGBE_PHY_INIT_END_NL) {
 		hw_dbg(hw, "No matching SFP+ module found\n");
-		return IXGBE_ERR_SFP_NOT_SUPPORTED;
+		return -EOPNOTSUPP;
 	}
 
 	return 0;
 
 err_phy:
 	hw_err(hw, "eeprom read at offset %d failed\n", *list_offset);
-	return IXGBE_ERR_PHY;
+	return -EIO;
 }
 
 /**
@@ -2152,7 +2149,7 @@ static s32 ixgbe_read_i2c_byte_generic_int(struct ixgbe_hw *hw, u8 byte_offset,
 
 	do {
 		if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask))
-			return IXGBE_ERR_SWFW_SYNC;
+			return -EBUSY;
 
 		ixgbe_i2c_start(hw);
 
@@ -2268,7 +2265,7 @@ static s32 ixgbe_write_i2c_byte_generic_int(struct ixgbe_hw *hw, u8 byte_offset,
 	u32 swfw_mask = hw->phy.phy_semaphore_mask;
 
 	if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask))
-		return IXGBE_ERR_SWFW_SYNC;
+		return -EBUSY;
 
 	do {
 		ixgbe_i2c_start(hw);
@@ -2510,7 +2507,7 @@ static s32 ixgbe_get_i2c_ack(struct ixgbe_hw *hw)
 
 	if (ack == 1) {
 		hw_dbg(hw, "I2C ack was not received.\n");
-		status = IXGBE_ERR_I2C;
+		status = -EIO;
 	}
 
 	ixgbe_lower_i2c_clk(hw, &i2cctl);
@@ -2582,7 +2579,7 @@ static s32 ixgbe_clock_out_i2c_bit(struct ixgbe_hw *hw, bool data)
 		udelay(IXGBE_I2C_T_LOW);
 	} else {
 		hw_dbg(hw, "I2C data was not set to %X\n", data);
-		return IXGBE_ERR_I2C;
+		return -EIO;
 	}
 
 	return 0;
@@ -2678,7 +2675,7 @@ static s32 ixgbe_set_i2c_data(struct ixgbe_hw *hw, u32 *i2cctl, bool data)
 	*i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw));
 	if (data != ixgbe_get_i2c_data(hw, i2cctl)) {
 		hw_dbg(hw, "Error - I2C data was not set to %X.\n", data);
-		return IXGBE_ERR_I2C;
+		return -EIO;
 	}
 
 	return 0;
@@ -2748,22 +2745,24 @@ static void ixgbe_i2c_bus_clear(struct ixgbe_hw *hw)
  *  @hw: pointer to hardware structure
  *
  *  Checks if the LASI temp alarm status was triggered due to overtemp
+ *
+ *  Return true when an overtemp event detected, otherwise false.
  **/
-s32 ixgbe_tn_check_overtemp(struct ixgbe_hw *hw)
+bool ixgbe_tn_check_overtemp(struct ixgbe_hw *hw)
 {
 	u16 phy_data = 0;
+	u32 status;
 
 	if (hw->device_id != IXGBE_DEV_ID_82599_T3_LOM)
-		return 0;
+		return false;
 
 	/* Check that the LASI temp alarm status was triggered */
-	hw->phy.ops.read_reg(hw, IXGBE_TN_LASI_STATUS_REG,
-			     MDIO_MMD_PMAPMD, &phy_data);
-
-	if (!(phy_data & IXGBE_TN_LASI_STATUS_TEMP_ALARM))
-		return 0;
+	status = hw->phy.ops.read_reg(hw, IXGBE_TN_LASI_STATUS_REG,
+				      MDIO_MMD_PMAPMD, &phy_data);
+	if (status)
+		return false;
 
-	return IXGBE_ERR_OVERTEMP;
+	return !!(phy_data & IXGBE_TN_LASI_STATUS_TEMP_ALARM);
 }
 
 /** ixgbe_set_copper_phy_power - Control power for copper phy
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
index 6544c4539c0d..ef72729d7c93 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
@@ -155,7 +155,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw);
 s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw,
 					u16 *list_offset,
 					u16 *data_offset);
-s32 ixgbe_tn_check_overtemp(struct ixgbe_hw *hw);
+bool ixgbe_tn_check_overtemp(struct ixgbe_hw *hw);
 s32 ixgbe_read_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset,
 				u8 dev_addr, u8 *data);
 s32 ixgbe_read_i2c_byte_generic_unlocked(struct ixgbe_hw *hw, u8 byte_offset,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index 9cfdfa8a4355..7299a830f6e4 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -363,8 +363,7 @@ int ixgbe_pci_sriov_configure(struct pci_dev *dev, int num_vfs)
 static int ixgbe_set_vf_multicasts(struct ixgbe_adapter *adapter,
 				   u32 *msgbuf, u32 vf)
 {
-	int entries = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK)
-		       >> IXGBE_VT_MSGINFO_SHIFT;
+	int entries = FIELD_GET(IXGBE_VT_MSGINFO_MASK, msgbuf[0]);
 	u16 *hash_list = (u16 *)&msgbuf[1];
 	struct vf_data_storage *vfinfo = &adapter->vfinfo[vf];
 	struct ixgbe_hw *hw = &adapter->hw;
@@ -969,7 +968,7 @@ static int ixgbe_set_vf_mac_addr(struct ixgbe_adapter *adapter,
 static int ixgbe_set_vf_vlan_msg(struct ixgbe_adapter *adapter,
 				 u32 *msgbuf, u32 vf)
 {
-	u32 add = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) >> IXGBE_VT_MSGINFO_SHIFT;
+	u32 add = FIELD_GET(IXGBE_VT_MSGINFO_MASK, msgbuf[0]);
 	u32 vid = (msgbuf[1] & IXGBE_VLVF_VLANID_MASK);
 	u8 tcs = adapter->hw_tcs;
 
@@ -992,8 +991,7 @@ static int ixgbe_set_vf_macvlan_msg(struct ixgbe_adapter *adapter,
 				    u32 *msgbuf, u32 vf)
 {
 	u8 *new_mac = ((u8 *)(&msgbuf[1]));
-	int index = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) >>
-		    IXGBE_VT_MSGINFO_SHIFT;
+	int index = FIELD_GET(IXGBE_VT_MSGINFO_MASK, msgbuf[0]);
 	int err;
 
 	if (adapter->vfinfo[vf].pf_set_mac && !adapter->vfinfo[vf].trusted &&
@@ -1327,7 +1325,7 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf)
 		break;
 	default:
 		e_err(drv, "Unhandled Msg %8.8x\n", msgbuf[0]);
-		retval = IXGBE_ERR_MBX;
+		retval = -EIO;
 		break;
 	}
 
@@ -1849,5 +1847,6 @@ int ixgbe_ndo_get_vf_config(struct net_device *netdev,
 	ivi->spoofchk = adapter->vfinfo[vf].spoofchk_enabled;
 	ivi->rss_query_en = adapter->vfinfo[vf].rss_query_enabled;
 	ivi->trusted = adapter->vfinfo[vf].trusted;
+	ivi->linkstate = adapter->vfinfo[vf].link_state;
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
index 2b00db92b08f..61b9774b3d31 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
@@ -3509,10 +3509,10 @@ struct ixgbe_phy_operations {
 	s32 (*read_i2c_sff8472)(struct ixgbe_hw *, u8 , u8 *);
 	s32 (*read_i2c_eeprom)(struct ixgbe_hw *, u8 , u8 *);
 	s32 (*write_i2c_eeprom)(struct ixgbe_hw *, u8, u8);
-	s32 (*check_overtemp)(struct ixgbe_hw *);
+	bool (*check_overtemp)(struct ixgbe_hw *);
 	s32 (*set_phy_power)(struct ixgbe_hw *, bool on);
 	s32 (*enter_lplu)(struct ixgbe_hw *);
-	s32 (*handle_lasi)(struct ixgbe_hw *hw);
+	s32 (*handle_lasi)(struct ixgbe_hw *hw, bool *);
 	s32 (*read_i2c_byte_unlocked)(struct ixgbe_hw *, u8 offset, u8 addr,
 				      u8 *value);
 	s32 (*write_i2c_byte_unlocked)(struct ixgbe_hw *, u8 offset, u8 addr,
@@ -3665,45 +3665,6 @@ struct ixgbe_info {
 	const u32			*mvals;
 };
 
-
-/* Error Codes */
-#define IXGBE_ERR_EEPROM                        -1
-#define IXGBE_ERR_EEPROM_CHECKSUM               -2
-#define IXGBE_ERR_PHY                           -3
-#define IXGBE_ERR_CONFIG                        -4
-#define IXGBE_ERR_PARAM                         -5
-#define IXGBE_ERR_MAC_TYPE                      -6
-#define IXGBE_ERR_UNKNOWN_PHY                   -7
-#define IXGBE_ERR_LINK_SETUP                    -8
-#define IXGBE_ERR_ADAPTER_STOPPED               -9
-#define IXGBE_ERR_INVALID_MAC_ADDR              -10
-#define IXGBE_ERR_DEVICE_NOT_SUPPORTED          -11
-#define IXGBE_ERR_PRIMARY_REQUESTS_PENDING      -12
-#define IXGBE_ERR_INVALID_LINK_SETTINGS         -13
-#define IXGBE_ERR_AUTONEG_NOT_COMPLETE          -14
-#define IXGBE_ERR_RESET_FAILED                  -15
-#define IXGBE_ERR_SWFW_SYNC                     -16
-#define IXGBE_ERR_PHY_ADDR_INVALID              -17
-#define IXGBE_ERR_I2C                           -18
-#define IXGBE_ERR_SFP_NOT_SUPPORTED             -19
-#define IXGBE_ERR_SFP_NOT_PRESENT               -20
-#define IXGBE_ERR_SFP_NO_INIT_SEQ_PRESENT       -21
-#define IXGBE_ERR_NO_SAN_ADDR_PTR               -22
-#define IXGBE_ERR_FDIR_REINIT_FAILED            -23
-#define IXGBE_ERR_EEPROM_VERSION                -24
-#define IXGBE_ERR_NO_SPACE                      -25
-#define IXGBE_ERR_OVERTEMP                      -26
-#define IXGBE_ERR_FC_NOT_NEGOTIATED             -27
-#define IXGBE_ERR_FC_NOT_SUPPORTED              -28
-#define IXGBE_ERR_SFP_SETUP_NOT_COMPLETE        -30
-#define IXGBE_ERR_PBA_SECTION                   -31
-#define IXGBE_ERR_INVALID_ARGUMENT              -32
-#define IXGBE_ERR_HOST_INTERFACE_COMMAND        -33
-#define IXGBE_ERR_FDIR_CMD_INCOMPLETE		-38
-#define IXGBE_ERR_FW_RESP_INVALID		-39
-#define IXGBE_ERR_TOKEN_RETRY			-40
-#define IXGBE_NOT_IMPLEMENTED                   0x7FFFFFFF
-
 #define IXGBE_FUSES0_GROUP(_i)		(0x11158 + ((_i) * 4))
 #define IXGBE_FUSES0_300MHZ		BIT(5)
 #define IXGBE_FUSES0_REV_MASK		(3u << 6)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
index d5cfb51ff648..57a912e4653f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
@@ -84,7 +84,7 @@ mac_reset_top:
 	status = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask);
 	if (status) {
 		hw_dbg(hw, "semaphore failed with %d", status);
-		return IXGBE_ERR_SWFW_SYNC;
+		return -EBUSY;
 	}
 
 	ctrl = IXGBE_CTRL_RST;
@@ -103,7 +103,7 @@ mac_reset_top:
 	}
 
 	if (ctrl & IXGBE_CTRL_RST_MASK) {
-		status = IXGBE_ERR_RESET_FAILED;
+		status = -EIO;
 		hw_dbg(hw, "Reset polling failed to complete.\n");
 	}
 	msleep(100);
@@ -187,16 +187,16 @@ s32 ixgbe_start_hw_X540(struct ixgbe_hw *hw)
 s32 ixgbe_init_eeprom_params_X540(struct ixgbe_hw *hw)
 {
 	struct ixgbe_eeprom_info *eeprom = &hw->eeprom;
-	u32 eec;
-	u16 eeprom_size;
 
 	if (eeprom->type == ixgbe_eeprom_uninitialized) {
+		u16 eeprom_size;
+		u32 eec;
+
 		eeprom->semaphore_delay = 10;
 		eeprom->type = ixgbe_flash;
 
 		eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw));
-		eeprom_size = (u16)((eec & IXGBE_EEC_SIZE) >>
-				    IXGBE_EEC_SIZE_SHIFT);
+		eeprom_size = FIELD_GET(IXGBE_EEC_SIZE, eec);
 		eeprom->word_size = BIT(eeprom_size +
 					IXGBE_EEPROM_WORD_SIZE_SHIFT);
 
@@ -220,7 +220,7 @@ static s32 ixgbe_read_eerd_X540(struct ixgbe_hw *hw, u16 offset, u16 *data)
 	s32 status;
 
 	if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM))
-		return IXGBE_ERR_SWFW_SYNC;
+		return -EBUSY;
 
 	status = ixgbe_read_eerd_generic(hw, offset, data);
 
@@ -243,7 +243,7 @@ static s32 ixgbe_read_eerd_buffer_X540(struct ixgbe_hw *hw,
 	s32 status;
 
 	if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM))
-		return IXGBE_ERR_SWFW_SYNC;
+		return -EBUSY;
 
 	status = ixgbe_read_eerd_buffer_generic(hw, offset, words, data);
 
@@ -264,7 +264,7 @@ static s32 ixgbe_write_eewr_X540(struct ixgbe_hw *hw, u16 offset, u16 data)
 	s32 status;
 
 	if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM))
-		return IXGBE_ERR_SWFW_SYNC;
+		return -EBUSY;
 
 	status = ixgbe_write_eewr_generic(hw, offset, data);
 
@@ -287,7 +287,7 @@ static s32 ixgbe_write_eewr_buffer_X540(struct ixgbe_hw *hw,
 	s32 status;
 
 	if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM))
-		return IXGBE_ERR_SWFW_SYNC;
+		return -EBUSY;
 
 	status = ixgbe_write_eewr_buffer_generic(hw, offset, words, data);
 
@@ -324,7 +324,7 @@ static s32 ixgbe_calc_eeprom_checksum_X540(struct ixgbe_hw *hw)
 	for (i = 0; i < checksum_last_word; i++) {
 		if (ixgbe_read_eerd_generic(hw, i, &word)) {
 			hw_dbg(hw, "EEPROM read failed\n");
-			return IXGBE_ERR_EEPROM;
+			return -EIO;
 		}
 		checksum += word;
 	}
@@ -349,7 +349,7 @@ static s32 ixgbe_calc_eeprom_checksum_X540(struct ixgbe_hw *hw)
 
 		if (ixgbe_read_eerd_generic(hw, pointer, &length)) {
 			hw_dbg(hw, "EEPROM read failed\n");
-			return IXGBE_ERR_EEPROM;
+			return -EIO;
 		}
 
 		/* Skip pointer section if length is invalid. */
@@ -360,7 +360,7 @@ static s32 ixgbe_calc_eeprom_checksum_X540(struct ixgbe_hw *hw)
 		for (j = pointer + 1; j <= pointer + length; j++) {
 			if (ixgbe_read_eerd_generic(hw, j, &word)) {
 				hw_dbg(hw, "EEPROM read failed\n");
-				return IXGBE_ERR_EEPROM;
+				return -EIO;
 			}
 			checksum += word;
 		}
@@ -397,7 +397,7 @@ static s32 ixgbe_validate_eeprom_checksum_X540(struct ixgbe_hw *hw,
 	}
 
 	if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM))
-		return IXGBE_ERR_SWFW_SYNC;
+		return -EBUSY;
 
 	status = hw->eeprom.ops.calc_checksum(hw);
 	if (status < 0)
@@ -418,7 +418,7 @@ static s32 ixgbe_validate_eeprom_checksum_X540(struct ixgbe_hw *hw,
 	 */
 	if (read_checksum != checksum) {
 		hw_dbg(hw, "Invalid EEPROM checksum");
-		status = IXGBE_ERR_EEPROM_CHECKSUM;
+		status = -EIO;
 	}
 
 	/* If the user cares, return the calculated checksum */
@@ -455,7 +455,7 @@ static s32 ixgbe_update_eeprom_checksum_X540(struct ixgbe_hw *hw)
 	}
 
 	if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM))
-		return  IXGBE_ERR_SWFW_SYNC;
+		return  -EBUSY;
 
 	status = hw->eeprom.ops.calc_checksum(hw);
 	if (status < 0)
@@ -490,7 +490,7 @@ static s32 ixgbe_update_flash_X540(struct ixgbe_hw *hw)
 	s32 status;
 
 	status = ixgbe_poll_flash_update_done_X540(hw);
-	if (status == IXGBE_ERR_EEPROM) {
+	if (status == -EIO) {
 		hw_dbg(hw, "Flash update time out\n");
 		return status;
 	}
@@ -540,7 +540,7 @@ static s32 ixgbe_poll_flash_update_done_X540(struct ixgbe_hw *hw)
 			return 0;
 		udelay(5);
 	}
-	return IXGBE_ERR_EEPROM;
+	return -EIO;
 }
 
 /**
@@ -575,7 +575,7 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask)
 		 * SW_FW_SYNC bits (not just NVM)
 		 */
 		if (ixgbe_get_swfw_sync_semaphore(hw))
-			return IXGBE_ERR_SWFW_SYNC;
+			return -EBUSY;
 
 		swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC(hw));
 		if (!(swfw_sync & (fwmask | swmask | hwmask))) {
@@ -599,7 +599,7 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask)
 	 * bits in the SW_FW_SYNC register.
 	 */
 	if (ixgbe_get_swfw_sync_semaphore(hw))
-		return IXGBE_ERR_SWFW_SYNC;
+		return -EBUSY;
 	swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC(hw));
 	if (swfw_sync & (fwmask | hwmask)) {
 		swfw_sync |= swmask;
@@ -622,11 +622,11 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask)
 			rmask |= IXGBE_GSSR_I2C_MASK;
 		ixgbe_release_swfw_sync_X540(hw, rmask);
 		ixgbe_release_swfw_sync_semaphore(hw);
-		return IXGBE_ERR_SWFW_SYNC;
+		return -EBUSY;
 	}
 	ixgbe_release_swfw_sync_semaphore(hw);
 
-	return IXGBE_ERR_SWFW_SYNC;
+	return -EBUSY;
 }
 
 /**
@@ -680,7 +680,7 @@ static s32 ixgbe_get_swfw_sync_semaphore(struct ixgbe_hw *hw)
 	if (i == timeout) {
 		hw_dbg(hw,
 		       "Software semaphore SMBI between device drivers not granted.\n");
-		return IXGBE_ERR_EEPROM;
+		return -EIO;
 	}
 
 	/* Now get the semaphore between SW/FW through the REGSMP bit */
@@ -697,7 +697,7 @@ static s32 ixgbe_get_swfw_sync_semaphore(struct ixgbe_hw *hw)
 	 */
 	hw_dbg(hw, "REGSMP Software NVM semaphore not granted\n");
 	ixgbe_release_swfw_sync_semaphore(hw);
-	return IXGBE_ERR_EEPROM;
+	return -EIO;
 }
 
 /**
@@ -768,7 +768,7 @@ s32 ixgbe_blink_led_start_X540(struct ixgbe_hw *hw, u32 index)
 	bool link_up;
 
 	if (index > 3)
-		return IXGBE_ERR_PARAM;
+		return -EINVAL;
 
 	/* Link should be up in order for the blink bit in the LED control
 	 * register to work. Force link and speed in the MAC if link is down.
@@ -804,7 +804,7 @@ s32 ixgbe_blink_led_stop_X540(struct ixgbe_hw *hw, u32 index)
 	u32 ledctl_reg;
 
 	if (index > 3)
-		return IXGBE_ERR_PARAM;
+		return -EINVAL;
 
 	/* Restore the LED to its default value. */
 	ledctl_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
index aa4bf6c9a2f7..6208923e29a2 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
@@ -206,13 +206,13 @@ static s32 ixgbe_reset_cs4227(struct ixgbe_hw *hw)
 	}
 	if (retry == IXGBE_CS4227_RETRIES) {
 		hw_err(hw, "CS4227 reset did not complete\n");
-		return IXGBE_ERR_PHY;
+		return -EIO;
 	}
 
 	status = ixgbe_read_cs4227(hw, IXGBE_CS4227_EEPROM_STATUS, &value);
 	if (status || !(value & IXGBE_CS4227_EEPROM_LOAD_OK)) {
 		hw_err(hw, "CS4227 EEPROM did not load successfully\n");
-		return IXGBE_ERR_PHY;
+		return -EIO;
 	}
 
 	return 0;
@@ -350,13 +350,13 @@ static s32 ixgbe_identify_phy_x550em(struct ixgbe_hw *hw)
 static s32 ixgbe_read_phy_reg_x550em(struct ixgbe_hw *hw, u32 reg_addr,
 				     u32 device_type, u16 *phy_data)
 {
-	return IXGBE_NOT_IMPLEMENTED;
+	return -EOPNOTSUPP;
 }
 
 static s32 ixgbe_write_phy_reg_x550em(struct ixgbe_hw *hw, u32 reg_addr,
 				      u32 device_type, u16 phy_data)
 {
-	return IXGBE_NOT_IMPLEMENTED;
+	return -EOPNOTSUPP;
 }
 
 /**
@@ -463,7 +463,7 @@ s32 ixgbe_fw_phy_activity(struct ixgbe_hw *hw, u16 activity,
 		--retries;
 	} while (retries > 0);
 
-	return IXGBE_ERR_HOST_INTERFACE_COMMAND;
+	return -EIO;
 }
 
 static const struct {
@@ -511,7 +511,7 @@ static s32 ixgbe_get_phy_id_fw(struct ixgbe_hw *hw)
 	hw->phy.id |= phy_id_lo & IXGBE_PHY_REVISION_MASK;
 	hw->phy.revision = phy_id_lo & ~IXGBE_PHY_REVISION_MASK;
 	if (!hw->phy.id || hw->phy.id == IXGBE_PHY_REVISION_MASK)
-		return IXGBE_ERR_PHY_ADDR_INVALID;
+		return -EFAULT;
 
 	hw->phy.autoneg_advertised = hw->phy.speeds_supported;
 	hw->phy.eee_speeds_supported = IXGBE_LINK_SPEED_100_FULL |
@@ -568,7 +568,7 @@ static s32 ixgbe_setup_fw_link(struct ixgbe_hw *hw)
 
 	if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) {
 		hw_err(hw, "rx_pause not valid in strict IEEE mode\n");
-		return IXGBE_ERR_INVALID_LINK_SETTINGS;
+		return -EINVAL;
 	}
 
 	switch (hw->fc.requested_mode) {
@@ -600,8 +600,10 @@ static s32 ixgbe_setup_fw_link(struct ixgbe_hw *hw)
 	rc = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_SETUP_LINK, &setup);
 	if (rc)
 		return rc;
+
 	if (setup[0] == FW_PHY_ACT_SETUP_LINK_RSP_DOWN)
-		return IXGBE_ERR_OVERTEMP;
+		return -EIO;
+
 	return 0;
 }
 
@@ -628,16 +630,16 @@ static s32 ixgbe_fc_autoneg_fw(struct ixgbe_hw *hw)
 static s32 ixgbe_init_eeprom_params_X550(struct ixgbe_hw *hw)
 {
 	struct ixgbe_eeprom_info *eeprom = &hw->eeprom;
-	u32 eec;
-	u16 eeprom_size;
 
 	if (eeprom->type == ixgbe_eeprom_uninitialized) {
+		u16 eeprom_size;
+		u32 eec;
+
 		eeprom->semaphore_delay = 10;
 		eeprom->type = ixgbe_flash;
 
 		eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw));
-		eeprom_size = (u16)((eec & IXGBE_EEC_SIZE) >>
-				    IXGBE_EEC_SIZE_SHIFT);
+		eeprom_size = FIELD_GET(IXGBE_EEC_SIZE, eec);
 		eeprom->word_size = BIT(eeprom_size +
 					IXGBE_EEPROM_WORD_SIZE_SHIFT);
 
@@ -675,7 +677,7 @@ static s32 ixgbe_iosf_wait(struct ixgbe_hw *hw, u32 *ctrl)
 		*ctrl = command;
 	if (i == IXGBE_MDIO_COMMAND_TIMEOUT) {
 		hw_dbg(hw, "IOSF wait timed out\n");
-		return IXGBE_ERR_PHY;
+		return -EIO;
 	}
 
 	return 0;
@@ -712,10 +714,9 @@ static s32 ixgbe_read_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr,
 	ret = ixgbe_iosf_wait(hw, &command);
 
 	if ((command & IXGBE_SB_IOSF_CTRL_RESP_STAT_MASK) != 0) {
-		error = (command & IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK) >>
-			 IXGBE_SB_IOSF_CTRL_CMPL_ERR_SHIFT;
+		error = FIELD_GET(IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK, command);
 		hw_dbg(hw, "Failed to read, error %x\n", error);
-		return IXGBE_ERR_PHY;
+		return -EIO;
 	}
 
 	if (!ret)
@@ -750,9 +751,9 @@ static s32 ixgbe_get_phy_token(struct ixgbe_hw *hw)
 	if (token_cmd.hdr.cmd_or_resp.ret_status == FW_PHY_TOKEN_OK)
 		return 0;
 	if (token_cmd.hdr.cmd_or_resp.ret_status != FW_PHY_TOKEN_RETRY)
-		return IXGBE_ERR_FW_RESP_INVALID;
+		return -EIO;
 
-	return IXGBE_ERR_TOKEN_RETRY;
+	return -EAGAIN;
 }
 
 /**
@@ -778,7 +779,7 @@ static s32 ixgbe_put_phy_token(struct ixgbe_hw *hw)
 		return status;
 	if (token_cmd.hdr.cmd_or_resp.ret_status == FW_PHY_TOKEN_OK)
 		return 0;
-	return IXGBE_ERR_FW_RESP_INVALID;
+	return -EIO;
 }
 
 /**
@@ -942,7 +943,7 @@ static s32 ixgbe_checksum_ptr_x550(struct ixgbe_hw *hw, u16 ptr,
 		local_buffer = buf;
 	} else {
 		if (buffer_size < ptr)
-			return  IXGBE_ERR_PARAM;
+			return  -EINVAL;
 		local_buffer = &buffer[ptr];
 	}
 
@@ -960,7 +961,7 @@ static s32 ixgbe_checksum_ptr_x550(struct ixgbe_hw *hw, u16 ptr,
 	}
 
 	if (buffer && ((u32)start + (u32)length > buffer_size))
-		return IXGBE_ERR_PARAM;
+		return -EINVAL;
 
 	for (i = start; length; i++, length--) {
 		if (i == bufsz && !buffer) {
@@ -1012,7 +1013,7 @@ static s32 ixgbe_calc_checksum_X550(struct ixgbe_hw *hw, u16 *buffer,
 		local_buffer = eeprom_ptrs;
 	} else {
 		if (buffer_size < IXGBE_EEPROM_LAST_WORD)
-			return IXGBE_ERR_PARAM;
+			return -EINVAL;
 		local_buffer = buffer;
 	}
 
@@ -1148,7 +1149,7 @@ static s32 ixgbe_validate_eeprom_checksum_X550(struct ixgbe_hw *hw,
 	 * calculated checksum
 	 */
 	if (read_checksum != checksum) {
-		status = IXGBE_ERR_EEPROM_CHECKSUM;
+		status = -EIO;
 		hw_dbg(hw, "Invalid EEPROM checksum");
 	}
 
@@ -1203,7 +1204,7 @@ static s32 ixgbe_write_ee_hostif_X550(struct ixgbe_hw *hw, u16 offset, u16 data)
 		hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM);
 	} else {
 		hw_dbg(hw, "write ee hostif failed to get semaphore");
-		status = IXGBE_ERR_SWFW_SYNC;
+		status = -EBUSY;
 	}
 
 	return status;
@@ -1412,10 +1413,9 @@ static s32 ixgbe_write_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr,
 	ret = ixgbe_iosf_wait(hw, &command);
 
 	if ((command & IXGBE_SB_IOSF_CTRL_RESP_STAT_MASK) != 0) {
-		error = (command & IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK) >>
-			 IXGBE_SB_IOSF_CTRL_CMPL_ERR_SHIFT;
+		error = FIELD_GET(IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK, command);
 		hw_dbg(hw, "Failed to write, error %x\n", error);
-		return IXGBE_ERR_PHY;
+		return -EIO;
 	}
 
 out:
@@ -1558,7 +1558,7 @@ static s32 ixgbe_setup_ixfi_x550em(struct ixgbe_hw *hw, ixgbe_link_speed *speed)
 
 	/* iXFI is only supported with X552 */
 	if (mac->type != ixgbe_mac_X550EM_x)
-		return IXGBE_ERR_LINK_SETUP;
+		return -EIO;
 
 	/* Disable AN and force speed to 10G Serial. */
 	status = ixgbe_read_iosf_sb_reg_x550(hw,
@@ -1580,7 +1580,7 @@ static s32 ixgbe_setup_ixfi_x550em(struct ixgbe_hw *hw, ixgbe_link_speed *speed)
 		break;
 	default:
 		/* Other link speeds are not supported by internal KR PHY. */
-		return IXGBE_ERR_LINK_SETUP;
+		return -EINVAL;
 	}
 
 	status = ixgbe_write_iosf_sb_reg_x550(hw,
@@ -1611,7 +1611,7 @@ static s32 ixgbe_supported_sfp_modules_X550em(struct ixgbe_hw *hw, bool *linear)
 {
 	switch (hw->phy.sfp_type) {
 	case ixgbe_sfp_type_not_present:
-		return IXGBE_ERR_SFP_NOT_PRESENT;
+		return -ENOENT;
 	case ixgbe_sfp_type_da_cu_core0:
 	case ixgbe_sfp_type_da_cu_core1:
 		*linear = true;
@@ -1630,7 +1630,7 @@ static s32 ixgbe_supported_sfp_modules_X550em(struct ixgbe_hw *hw, bool *linear)
 	case ixgbe_sfp_type_1g_cu_core0:
 	case ixgbe_sfp_type_1g_cu_core1:
 	default:
-		return IXGBE_ERR_SFP_NOT_SUPPORTED;
+		return -EOPNOTSUPP;
 	}
 
 	return 0;
@@ -1660,7 +1660,7 @@ ixgbe_setup_mac_link_sfp_x550em(struct ixgbe_hw *hw,
 	 * there is no reason to configure CS4227 and SFP not present error is
 	 * not accepted in the setup MAC link flow.
 	 */
-	if (status == IXGBE_ERR_SFP_NOT_PRESENT)
+	if (status == -ENOENT)
 		return 0;
 
 	if (status)
@@ -1718,7 +1718,7 @@ static s32 ixgbe_setup_sfi_x550a(struct ixgbe_hw *hw, ixgbe_link_speed *speed)
 		break;
 	default:
 		/* Other link speeds are not supported by internal PHY. */
-		return IXGBE_ERR_LINK_SETUP;
+		return -EINVAL;
 	}
 
 	(void)mac->ops.write_iosf_sb_reg(hw,
@@ -1803,7 +1803,7 @@ ixgbe_setup_mac_link_sfp_n(struct ixgbe_hw *hw, ixgbe_link_speed speed,
 	/* If no SFP module present, then return success. Return success since
 	 * SFP not present error is not excepted in the setup MAC link flow.
 	 */
-	if (ret_val == IXGBE_ERR_SFP_NOT_PRESENT)
+	if (ret_val == -ENOENT)
 		return 0;
 
 	if (ret_val)
@@ -1853,7 +1853,7 @@ ixgbe_setup_mac_link_sfp_x550a(struct ixgbe_hw *hw, ixgbe_link_speed speed,
 	/* If no SFP module present, then return success. Return success since
 	 * SFP not present error is not excepted in the setup MAC link flow.
 	 */
-	if (ret_val == IXGBE_ERR_SFP_NOT_PRESENT)
+	if (ret_val == -ENOENT)
 		return 0;
 
 	if (ret_val)
@@ -1863,7 +1863,7 @@ ixgbe_setup_mac_link_sfp_x550a(struct ixgbe_hw *hw, ixgbe_link_speed speed,
 	ixgbe_setup_kr_speed_x550em(hw, speed);
 
 	if (hw->phy.mdio.prtad == MDIO_PRTAD_NONE)
-		return IXGBE_ERR_PHY_ADDR_INVALID;
+		return -EFAULT;
 
 	/* Get external PHY SKU id */
 	ret_val = hw->phy.ops.read_reg(hw, IXGBE_CS4227_EFUSE_PDF_SKU,
@@ -1962,7 +1962,7 @@ static s32 ixgbe_check_link_t_X550em(struct ixgbe_hw *hw,
 	u16 i, autoneg_status;
 
 	if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_copper)
-		return IXGBE_ERR_CONFIG;
+		return -EIO;
 
 	status = ixgbe_check_mac_link_generic(hw, speed, link_up,
 					      link_up_wait_to_complete);
@@ -2145,9 +2145,9 @@ static s32 ixgbe_setup_sgmii_fw(struct ixgbe_hw *hw, ixgbe_link_speed speed,
  */
 static void ixgbe_fc_autoneg_sgmii_x550em_a(struct ixgbe_hw *hw)
 {
-	s32 status = IXGBE_ERR_FC_NOT_NEGOTIATED;
 	u32 info[FW_PHY_ACT_DATA_COUNT] = { 0 };
 	ixgbe_link_speed speed;
+	s32 status = -EIO;
 	bool link_up;
 
 	/* AN should have completed when the cable was plugged in.
@@ -2165,7 +2165,7 @@ static void ixgbe_fc_autoneg_sgmii_x550em_a(struct ixgbe_hw *hw)
 	/* Check if auto-negotiation has completed */
 	status = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_GET_LINK_INFO, &info);
 	if (status || !(info[0] & FW_PHY_ACT_GET_LINK_INFO_AN_COMPLETE)) {
-		status = IXGBE_ERR_FC_NOT_NEGOTIATED;
+		status = -EIO;
 		goto out;
 	}
 
@@ -2369,18 +2369,18 @@ static s32 ixgbe_get_link_capabilities_X550em(struct ixgbe_hw *hw,
  * @hw: pointer to hardware structure
  * @lsc: pointer to boolean flag which indicates whether external Base T
  *	 PHY interrupt is lsc
+ * @is_overtemp: indicate whether an overtemp event encountered
  *
  * Determime if external Base T PHY interrupt cause is high temperature
  * failure alarm or link status change.
- *
- * Return IXGBE_ERR_OVERTEMP if interrupt is high temperature
- * failure alarm, else return PHY access status.
  **/
-static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc)
+static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc,
+				       bool *is_overtemp)
 {
 	u32 status;
 	u16 reg;
 
+	*is_overtemp = false;
 	*lsc = false;
 
 	/* Vendor alarm triggered */
@@ -2412,7 +2412,8 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc)
 	if (reg & IXGBE_MDIO_GLOBAL_ALM_1_HI_TMP_FAIL) {
 		/* power down the PHY in case the PHY FW didn't already */
 		ixgbe_set_copper_phy_power(hw, false);
-		return IXGBE_ERR_OVERTEMP;
+		*is_overtemp = true;
+		return -EIO;
 	}
 	if (reg & IXGBE_MDIO_GLOBAL_ALM_1_DEV_FAULT) {
 		/*  device fault alarm triggered */
@@ -2426,7 +2427,8 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc)
 		if (reg == IXGBE_MDIO_GLOBAL_FAULT_MSG_HI_TMP) {
 			/* power down the PHY in case the PHY FW didn't */
 			ixgbe_set_copper_phy_power(hw, false);
-			return IXGBE_ERR_OVERTEMP;
+			*is_overtemp = true;
+			return -EIO;
 		}
 	}
 
@@ -2462,12 +2464,12 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc)
  **/
 static s32 ixgbe_enable_lasi_ext_t_x550em(struct ixgbe_hw *hw)
 {
+	bool lsc, overtemp;
 	u32 status;
 	u16 reg;
-	bool lsc;
 
 	/* Clear interrupt flags */
-	status = ixgbe_get_lasi_ext_t_x550em(hw, &lsc);
+	status = ixgbe_get_lasi_ext_t_x550em(hw, &lsc, &overtemp);
 
 	/* Enable link status change alarm */
 
@@ -2546,21 +2548,20 @@ static s32 ixgbe_enable_lasi_ext_t_x550em(struct ixgbe_hw *hw)
 /**
  * ixgbe_handle_lasi_ext_t_x550em - Handle external Base T PHY interrupt
  * @hw: pointer to hardware structure
+ * @is_overtemp: indicate whether an overtemp event encountered
  *
  * Handle external Base T PHY interrupt. If high temperature
  * failure alarm then return error, else if link status change
  * then setup internal/external PHY link
- *
- * Return IXGBE_ERR_OVERTEMP if interrupt is high temperature
- * failure alarm, else return PHY access status.
  **/
-static s32 ixgbe_handle_lasi_ext_t_x550em(struct ixgbe_hw *hw)
+static s32 ixgbe_handle_lasi_ext_t_x550em(struct ixgbe_hw *hw,
+					  bool *is_overtemp)
 {
 	struct ixgbe_phy_info *phy = &hw->phy;
 	bool lsc;
 	u32 status;
 
-	status = ixgbe_get_lasi_ext_t_x550em(hw, &lsc);
+	status = ixgbe_get_lasi_ext_t_x550em(hw, &lsc, is_overtemp);
 	if (status)
 		return status;
 
@@ -2692,7 +2693,7 @@ static s32 ixgbe_setup_internal_phy_t_x550em(struct ixgbe_hw *hw)
 	u16 speed;
 
 	if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_copper)
-		return IXGBE_ERR_CONFIG;
+		return -EIO;
 
 	if (!(hw->mac.type == ixgbe_mac_X550EM_x &&
 	      !(hw->phy.nw_mng_if_sel & IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE))) {
@@ -2735,7 +2736,7 @@ static s32 ixgbe_setup_internal_phy_t_x550em(struct ixgbe_hw *hw)
 		break;
 	default:
 		/* Internal PHY does not support anything else */
-		return IXGBE_ERR_INVALID_LINK_SETTINGS;
+		return -EINVAL;
 	}
 
 	return ixgbe_setup_ixfi_x550em(hw, &force_speed);
@@ -2767,7 +2768,7 @@ static s32 ixgbe_led_on_t_x550em(struct ixgbe_hw *hw, u32 led_idx)
 	u16 phy_data;
 
 	if (led_idx >= IXGBE_X557_MAX_LED_INDEX)
-		return IXGBE_ERR_PARAM;
+		return -EINVAL;
 
 	/* To turn on the LED, set mode to ON. */
 	hw->phy.ops.read_reg(hw, IXGBE_X557_LED_PROVISIONING + led_idx,
@@ -2789,7 +2790,7 @@ static s32 ixgbe_led_off_t_x550em(struct ixgbe_hw *hw, u32 led_idx)
 	u16 phy_data;
 
 	if (led_idx >= IXGBE_X557_MAX_LED_INDEX)
-		return IXGBE_ERR_PARAM;
+		return -EINVAL;
 
 	/* To turn on the LED, set mode to ON. */
 	hw->phy.ops.read_reg(hw, IXGBE_X557_LED_PROVISIONING + led_idx,
@@ -2813,8 +2814,9 @@ static s32 ixgbe_led_off_t_x550em(struct ixgbe_hw *hw, u32 led_idx)
  *
  *  Sends driver version number to firmware through the manageability
  *  block.  On success return 0
- *  else returns IXGBE_ERR_SWFW_SYNC when encountering an error acquiring
- *  semaphore or IXGBE_ERR_HOST_INTERFACE_COMMAND when command fails.
+ *  else returns -EBUSY when encountering an error acquiring
+ *  semaphore, -EIO when command fails or -ENIVAL when incorrect
+ *  params passed.
  **/
 static s32 ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min,
 				     u8 build, u8 sub, u16 len,
@@ -2825,7 +2827,7 @@ static s32 ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min,
 	int i;
 
 	if (!len || !driver_ver || (len > sizeof(fw_cmd.driver_string)))
-		return IXGBE_ERR_INVALID_ARGUMENT;
+		return -EINVAL;
 
 	fw_cmd.hdr.cmd = FW_CEM_CMD_DRIVER_INFO;
 	fw_cmd.hdr.buf_len = FW_CEM_CMD_DRIVER_INFO_LEN + len;
@@ -2850,7 +2852,7 @@ static s32 ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min,
 
 		if (fw_cmd.hdr.cmd_or_resp.ret_status !=
 		    FW_CEM_RESP_STATUS_SUCCESS)
-			return IXGBE_ERR_HOST_INTERFACE_COMMAND;
+			return -EIO;
 		return 0;
 	}
 
@@ -2907,7 +2909,7 @@ static s32 ixgbe_setup_fc_x550em(struct ixgbe_hw *hw)
 	/* Validate the requested mode */
 	if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) {
 		hw_err(hw, "ixgbe_fc_rx_pause not valid in strict IEEE mode\n");
-		return IXGBE_ERR_INVALID_LINK_SETTINGS;
+		return -EINVAL;
 	}
 
 	/* 10gig parts do not have a word in the EEPROM to determine the
@@ -2942,7 +2944,7 @@ static s32 ixgbe_setup_fc_x550em(struct ixgbe_hw *hw)
 		break;
 	default:
 		hw_err(hw, "Flow control param set incorrectly\n");
-		return IXGBE_ERR_CONFIG;
+		return -EIO;
 	}
 
 	switch (hw->device_id) {
@@ -2986,8 +2988,8 @@ static s32 ixgbe_setup_fc_x550em(struct ixgbe_hw *hw)
 static void ixgbe_fc_autoneg_backplane_x550em_a(struct ixgbe_hw *hw)
 {
 	u32 link_s1, lp_an_page_low, an_cntl_1;
-	s32 status = IXGBE_ERR_FC_NOT_NEGOTIATED;
 	ixgbe_link_speed speed;
+	s32 status = -EIO;
 	bool link_up;
 
 	/* AN should have completed when the cable was plugged in.
@@ -3013,7 +3015,7 @@ static void ixgbe_fc_autoneg_backplane_x550em_a(struct ixgbe_hw *hw)
 
 	if (status || (link_s1 & IXGBE_KRM_LINK_S1_MAC_AN_COMPLETE) == 0) {
 		hw_dbg(hw, "Auto-Negotiation did not complete\n");
-		status = IXGBE_ERR_FC_NOT_NEGOTIATED;
+		status = -EIO;
 		goto out;
 	}
 
@@ -3187,21 +3189,23 @@ static s32 ixgbe_reset_phy_fw(struct ixgbe_hw *hw)
 /**
  * ixgbe_check_overtemp_fw - Check firmware-controlled PHYs for overtemp
  * @hw: pointer to hardware structure
+ *
+ * Return true when an overtemp event detected, otherwise false.
  */
-static s32 ixgbe_check_overtemp_fw(struct ixgbe_hw *hw)
+static bool ixgbe_check_overtemp_fw(struct ixgbe_hw *hw)
 {
 	u32 store[FW_PHY_ACT_DATA_COUNT] = { 0 };
 	s32 rc;
 
 	rc = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_GET_LINK_INFO, &store);
 	if (rc)
-		return rc;
+		return false;
 
 	if (store[0] & FW_PHY_ACT_GET_LINK_INFO_TEMP) {
 		ixgbe_shutdown_fw_phy(hw);
-		return IXGBE_ERR_OVERTEMP;
+		return true;
 	}
-	return 0;
+	return false;
 }
 
 /**
@@ -3222,9 +3226,8 @@ static void ixgbe_read_mng_if_sel_x550em(struct ixgbe_hw *hw)
 	 */
 	if (hw->mac.type == ixgbe_mac_x550em_a &&
 	    hw->phy.nw_mng_if_sel & IXGBE_NW_MNG_IF_SEL_MDIO_ACT) {
-		hw->phy.mdio.prtad = (hw->phy.nw_mng_if_sel &
-				      IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD) >>
-				     IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD_SHIFT;
+		hw->phy.mdio.prtad = FIELD_GET(IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD,
+					       hw->phy.nw_mng_if_sel);
 	}
 }
 
@@ -3251,8 +3254,7 @@ static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw)
 
 	/* Identify the PHY or SFP module */
 	ret_val = phy->ops.identify(hw);
-	if (ret_val == IXGBE_ERR_SFP_NOT_SUPPORTED ||
-	    ret_val == IXGBE_ERR_PHY_ADDR_INVALID)
+	if (ret_val == -EOPNOTSUPP || ret_val == -EFAULT)
 		return ret_val;
 
 	/* Setup function pointers based on detected hardware */
@@ -3460,8 +3462,7 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw)
 
 	/* PHY ops must be identified and initialized prior to reset */
 	status = hw->phy.ops.init(hw);
-	if (status == IXGBE_ERR_SFP_NOT_SUPPORTED ||
-	    status == IXGBE_ERR_PHY_ADDR_INVALID)
+	if (status == -EOPNOTSUPP || status == -EFAULT)
 		return status;
 
 	/* start the external PHY */
@@ -3477,7 +3478,7 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw)
 		hw->phy.sfp_setup_needed = false;
 	}
 
-	if (status == IXGBE_ERR_SFP_NOT_SUPPORTED)
+	if (status == -EOPNOTSUPP)
 		return status;
 
 	/* Reset PHY */
@@ -3501,7 +3502,7 @@ mac_reset_top:
 	status = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask);
 	if (status) {
 		hw_dbg(hw, "semaphore failed with %d", status);
-		return IXGBE_ERR_SWFW_SYNC;
+		return -EBUSY;
 	}
 
 	ctrl |= IXGBE_READ_REG(hw, IXGBE_CTRL);
@@ -3519,7 +3520,7 @@ mac_reset_top:
 	}
 
 	if (ctrl & IXGBE_CTRL_RST_MASK) {
-		status = IXGBE_ERR_RESET_FAILED;
+		status = -EIO;
 		hw_dbg(hw, "Reset polling failed to complete.\n");
 	}
 
@@ -3615,7 +3616,7 @@ static s32 ixgbe_setup_fc_backplane_x550em_a(struct ixgbe_hw *hw)
 	/* Validate the requested mode */
 	if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) {
 		hw_err(hw, "ixgbe_fc_rx_pause not valid in strict IEEE mode\n");
-		return IXGBE_ERR_INVALID_LINK_SETTINGS;
+		return -EINVAL;
 	}
 
 	if (hw->fc.requested_mode == ixgbe_fc_default)
@@ -3672,7 +3673,7 @@ static s32 ixgbe_setup_fc_backplane_x550em_a(struct ixgbe_hw *hw)
 		break;
 	default:
 		hw_err(hw, "Flow control param set incorrectly\n");
-		return IXGBE_ERR_CONFIG;
+		return -EIO;
 	}
 
 	status = hw->mac.ops.write_iosf_sb_reg(hw,
@@ -3768,7 +3769,7 @@ static s32 ixgbe_acquire_swfw_sync_x550em_a(struct ixgbe_hw *hw, u32 mask)
 			return 0;
 		if (hmask)
 			ixgbe_release_swfw_sync_X540(hw, hmask);
-		if (status != IXGBE_ERR_TOKEN_RETRY)
+		if (status != -EAGAIN)
 			return status;
 		msleep(FW_PHY_TOKEN_DELAY);
 	}
@@ -3812,7 +3813,7 @@ static s32 ixgbe_read_phy_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr,
 	s32 status;
 
 	if (hw->mac.ops.acquire_swfw_sync(hw, mask))
-		return IXGBE_ERR_SWFW_SYNC;
+		return -EBUSY;
 
 	status = hw->phy.ops.read_reg_mdi(hw, reg_addr, device_type, phy_data);
 
@@ -3838,7 +3839,7 @@ static s32 ixgbe_write_phy_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr,
 	s32 status;
 
 	if (hw->mac.ops.acquire_swfw_sync(hw, mask))
-		return IXGBE_ERR_SWFW_SYNC;
+		return -EBUSY;
 
 	status = ixgbe_write_phy_reg_mdi(hw, reg_addr, device_type, phy_data);
 	hw->mac.ops.release_swfw_sync(hw, mask);
diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
index 296915414a7c..7ac53171b041 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
@@ -897,40 +897,41 @@ static u32 ixgbevf_get_rxfh_key_size(struct net_device *netdev)
 	return IXGBEVF_RSS_HASH_KEY_SIZE;
 }
 
-static int ixgbevf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			    u8 *hfunc)
+static int ixgbevf_get_rxfh(struct net_device *netdev,
+			    struct ethtool_rxfh_param *rxfh)
 {
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
 	int err = 0;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	if (adapter->hw.mac.type >= ixgbe_mac_X550_vf) {
-		if (key)
-			memcpy(key, adapter->rss_key,
+		if (rxfh->key)
+			memcpy(rxfh->key, adapter->rss_key,
 			       ixgbevf_get_rxfh_key_size(netdev));
 
-		if (indir) {
+		if (rxfh->indir) {
 			int i;
 
 			for (i = 0; i < IXGBEVF_X550_VFRETA_SIZE; i++)
-				indir[i] = adapter->rss_indir_tbl[i];
+				rxfh->indir[i] = adapter->rss_indir_tbl[i];
 		}
 	} else {
 		/* If neither indirection table nor hash key was requested
 		 *  - just return a success avoiding taking any locks.
 		 */
-		if (!indir && !key)
+		if (!rxfh->indir && !rxfh->key)
 			return 0;
 
 		spin_lock_bh(&adapter->mbx_lock);
-		if (indir)
-			err = ixgbevf_get_reta_locked(&adapter->hw, indir,
+		if (rxfh->indir)
+			err = ixgbevf_get_reta_locked(&adapter->hw,
+						      rxfh->indir,
 						      adapter->num_rx_queues);
 
-		if (!err && key)
-			err = ixgbevf_get_rss_key_locked(&adapter->hw, key);
+		if (!err && rxfh->key)
+			err = ixgbevf_get_rss_key_locked(&adapter->hw,
+							 rxfh->key);
 
 		spin_unlock_bh(&adapter->mbx_lock);
 	}
diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index 89f26402f8fb..9190eff6c0bb 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -23,6 +23,7 @@
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
 #include <linux/kernel.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
@@ -52,17 +53,19 @@
 #define  MVMDIO_XSMI_BUSY		BIT(30)
 #define MVMDIO_XSMI_ADDR_REG		0x8
 
+#define MVMDIO_XSMI_CFG_REG		0xc
+#define  MVMDIO_XSMI_CLKDIV_MASK	0x3
+#define  MVMDIO_XSMI_CLKDIV_256		0x0
+#define  MVMDIO_XSMI_CLKDIV_64		0x1
+#define  MVMDIO_XSMI_CLKDIV_32		0x2
+#define  MVMDIO_XSMI_CLKDIV_8		0x3
+
 /*
  * SMI Timeout measurements:
  * - Kirkwood 88F6281 (Globalscale Dreamplug): 45us to 95us (Interrupt)
  * - Armada 370       (Globalscale Mirabox):   41us to 43us (Polled)
  */
 #define MVMDIO_SMI_TIMEOUT		1000 /* 1000us = 1ms */
-#define MVMDIO_SMI_POLL_INTERVAL_MIN	45
-#define MVMDIO_SMI_POLL_INTERVAL_MAX	55
-
-#define MVMDIO_XSMI_POLL_INTERVAL_MIN	150
-#define MVMDIO_XSMI_POLL_INTERVAL_MAX	160
 
 struct orion_mdio_dev {
 	void __iomem *regs;
@@ -84,8 +87,6 @@ enum orion_mdio_bus_type {
 
 struct orion_mdio_ops {
 	int (*is_done)(struct orion_mdio_dev *);
-	unsigned int poll_interval_min;
-	unsigned int poll_interval_max;
 };
 
 /* Wait for the SMI unit to be ready for another operation
@@ -94,34 +95,23 @@ static int orion_mdio_wait_ready(const struct orion_mdio_ops *ops,
 				 struct mii_bus *bus)
 {
 	struct orion_mdio_dev *dev = bus->priv;
-	unsigned long timeout = usecs_to_jiffies(MVMDIO_SMI_TIMEOUT);
-	unsigned long end = jiffies + timeout;
-	int timedout = 0;
+	unsigned long timeout;
+	int done;
 
-	while (1) {
-	        if (ops->is_done(dev))
+	if (dev->err_interrupt <= 0) {
+		if (!read_poll_timeout_atomic(ops->is_done, done, done, 2,
+					      MVMDIO_SMI_TIMEOUT, false, dev))
+			return 0;
+	} else {
+		/* wait_event_timeout does not guarantee a delay of at
+		 * least one whole jiffie, so timeout must be no less
+		 * than two.
+		 */
+		timeout = max(usecs_to_jiffies(MVMDIO_SMI_TIMEOUT), 2);
+
+		if (wait_event_timeout(dev->smi_busy_wait,
+				       ops->is_done(dev), timeout))
 			return 0;
-	        else if (timedout)
-			break;
-
-	        if (dev->err_interrupt <= 0) {
-			usleep_range(ops->poll_interval_min,
-				     ops->poll_interval_max);
-
-			if (time_is_before_jiffies(end))
-				++timedout;
-	        } else {
-			/* wait_event_timeout does not guarantee a delay of at
-			 * least one whole jiffie, so timeout must be no less
-			 * than two.
-			 */
-			if (timeout < 2)
-				timeout = 2;
-			wait_event_timeout(dev->smi_busy_wait,
-				           ops->is_done(dev), timeout);
-
-			++timedout;
-	        }
 	}
 
 	dev_err(bus->parent, "Timeout: SMI busy for too long\n");
@@ -135,8 +125,6 @@ static int orion_mdio_smi_is_done(struct orion_mdio_dev *dev)
 
 static const struct orion_mdio_ops orion_mdio_smi_ops = {
 	.is_done = orion_mdio_smi_is_done,
-	.poll_interval_min = MVMDIO_SMI_POLL_INTERVAL_MIN,
-	.poll_interval_max = MVMDIO_SMI_POLL_INTERVAL_MAX,
 };
 
 static int orion_mdio_smi_read(struct mii_bus *bus, int mii_id,
@@ -194,8 +182,6 @@ static int orion_mdio_xsmi_is_done(struct orion_mdio_dev *dev)
 
 static const struct orion_mdio_ops orion_mdio_xsmi_ops = {
 	.is_done = orion_mdio_xsmi_is_done,
-	.poll_interval_min = MVMDIO_XSMI_POLL_INTERVAL_MIN,
-	.poll_interval_max = MVMDIO_XSMI_POLL_INTERVAL_MAX,
 };
 
 static int orion_mdio_xsmi_read_c45(struct mii_bus *bus, int mii_id,
@@ -246,6 +232,40 @@ static int orion_mdio_xsmi_write_c45(struct mii_bus *bus, int mii_id,
 	return 0;
 }
 
+static void orion_mdio_xsmi_set_mdc_freq(struct mii_bus *bus)
+{
+	struct orion_mdio_dev *dev = bus->priv;
+	struct clk *mg_core;
+	u32 div, freq, cfg;
+
+	if (device_property_read_u32(bus->parent, "clock-frequency", &freq))
+		return;
+
+	mg_core = of_clk_get_by_name(bus->parent->of_node, "mg_core_clk");
+	if (IS_ERR(mg_core)) {
+		dev_err(bus->parent,
+			"MG core clock unknown, not changing MDC frequency");
+		return;
+	}
+
+	div = clk_get_rate(mg_core) / (freq + 1) + 1;
+	clk_put(mg_core);
+
+	if (div <= 8)
+		div = MVMDIO_XSMI_CLKDIV_8;
+	else if (div <= 32)
+		div = MVMDIO_XSMI_CLKDIV_32;
+	else if (div <= 64)
+		div = MVMDIO_XSMI_CLKDIV_64;
+	else
+		div = MVMDIO_XSMI_CLKDIV_256;
+
+	cfg = readl(dev->regs + MVMDIO_XSMI_CFG_REG);
+	cfg &= ~MVMDIO_XSMI_CLKDIV_MASK;
+	cfg |= div;
+	writel(cfg, dev->regs + MVMDIO_XSMI_CFG_REG);
+}
+
 static irqreturn_t orion_mdio_err_irq(int irq, void *dev_id)
 {
 	struct orion_mdio_dev *dev = dev_id;
@@ -324,6 +344,9 @@ static int orion_mdio_probe(struct platform_device *pdev)
 			dev_warn(&pdev->dev,
 				 "unsupported number of clocks, limiting to the first "
 				 __stringify(ARRAY_SIZE(dev->clk)) "\n");
+
+		if (type == BUS_TYPE_XSMI)
+			orion_mdio_xsmi_set_mdc_freq(bus);
 	} else {
 		dev->clk[0] = clk_get(&pdev->dev, NULL);
 		if (PTR_ERR(dev->clk[0]) == -EPROBE_DEFER) {
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 90817136808d..a641b3534ca3 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -4790,14 +4790,17 @@ static void mvneta_ethtool_get_strings(struct net_device *netdev, u32 sset,
 				       u8 *data)
 {
 	if (sset == ETH_SS_STATS) {
+		struct mvneta_port *pp = netdev_priv(netdev);
 		int i;
 
 		for (i = 0; i < ARRAY_SIZE(mvneta_statistics); i++)
 			memcpy(data + i * ETH_GSTRING_LEN,
 			       mvneta_statistics[i].name, ETH_GSTRING_LEN);
 
-		data += ETH_GSTRING_LEN * ARRAY_SIZE(mvneta_statistics);
-		page_pool_ethtool_stats_get_strings(data);
+		if (!pp->bm_priv) {
+			data += ETH_GSTRING_LEN * ARRAY_SIZE(mvneta_statistics);
+			page_pool_ethtool_stats_get_strings(data);
+		}
 	}
 }
 
@@ -4915,8 +4918,10 @@ static void mvneta_ethtool_pp_stats(struct mvneta_port *pp, u64 *data)
 	struct page_pool_stats stats = {};
 	int i;
 
-	for (i = 0; i < rxq_number; i++)
-		page_pool_get_stats(pp->rxqs[i].page_pool, &stats);
+	for (i = 0; i < rxq_number; i++) {
+		if (pp->rxqs[i].page_pool)
+			page_pool_get_stats(pp->rxqs[i].page_pool, &stats);
+	}
 
 	page_pool_ethtool_stats_get(data, &stats);
 }
@@ -4932,14 +4937,21 @@ static void mvneta_ethtool_get_stats(struct net_device *dev,
 	for (i = 0; i < ARRAY_SIZE(mvneta_statistics); i++)
 		*data++ = pp->ethtool_stats[i];
 
-	mvneta_ethtool_pp_stats(pp, data);
+	if (!pp->bm_priv)
+		mvneta_ethtool_pp_stats(pp, data);
 }
 
 static int mvneta_ethtool_get_sset_count(struct net_device *dev, int sset)
 {
-	if (sset == ETH_SS_STATS)
-		return ARRAY_SIZE(mvneta_statistics) +
-		       page_pool_ethtool_stats_get_count();
+	if (sset == ETH_SS_STATS) {
+		int count = ARRAY_SIZE(mvneta_statistics);
+		struct mvneta_port *pp = netdev_priv(dev);
+
+		if (!pp->bm_priv)
+			count += page_pool_ethtool_stats_get_count();
+
+		return count;
+	}
 
 	return -EOPNOTSUPP;
 }
@@ -5018,8 +5030,9 @@ static int  mvneta_config_rss(struct mvneta_port *pp)
 	return 0;
 }
 
-static int mvneta_ethtool_set_rxfh(struct net_device *dev, const u32 *indir,
-				   const u8 *key, const u8 hfunc)
+static int mvneta_ethtool_set_rxfh(struct net_device *dev,
+				   struct ethtool_rxfh_param *rxfh,
+				   struct netlink_ext_ack *extack)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
 
@@ -5030,20 +5043,21 @@ static int mvneta_ethtool_set_rxfh(struct net_device *dev, const u32 *indir,
 	/* We require at least one supported parameter to be changed
 	 * and no change in any of the unsupported parameters
 	 */
-	if (key ||
-	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->key ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP))
 		return -EOPNOTSUPP;
 
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
-	memcpy(pp->indir, indir, MVNETA_RSS_LU_TABLE_SIZE);
+	memcpy(pp->indir, rxfh->indir, MVNETA_RSS_LU_TABLE_SIZE);
 
 	return mvneta_config_rss(pp);
 }
 
-static int mvneta_ethtool_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
-				   u8 *hfunc)
+static int mvneta_ethtool_get_rxfh(struct net_device *dev,
+				   struct ethtool_rxfh_param *rxfh)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
 
@@ -5051,13 +5065,12 @@ static int mvneta_ethtool_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
 	if (pp->neta_armada3700)
 		return -EOPNOTSUPP;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
-	memcpy(indir, pp->indir, MVNETA_RSS_LU_TABLE_SIZE);
+	memcpy(rxfh->indir, pp->indir, MVNETA_RSS_LU_TABLE_SIZE);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 93137606869e..820b1fabe297 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -1513,10 +1513,21 @@ static void mvpp22_gop_init_rgmii(struct mvpp2_port *port)
 	regmap_write(priv->sysctrl_base, GENCONF_PORT_CTRL0, val);
 
 	regmap_read(priv->sysctrl_base, GENCONF_CTRL0, &val);
-	if (port->gop_id == 2)
+	if (port->gop_id == 2) {
 		val |= GENCONF_CTRL0_PORT2_RGMII;
-	else if (port->gop_id == 3)
+	} else if (port->gop_id == 3) {
 		val |= GENCONF_CTRL0_PORT3_RGMII_MII;
+
+		/* According to the specification, GENCONF_CTRL0_PORT3_RGMII
+		 * should be set to 1 for RGMII and 0 for MII. However, tests
+		 * show that it is the other way around. This is also what
+		 * U-Boot does for mvpp2, so it is assumed to be correct.
+		 */
+		if (port->phy_interface == PHY_INTERFACE_MODE_MII)
+			val |= GENCONF_CTRL0_PORT3_RGMII;
+		else
+			val &= ~GENCONF_CTRL0_PORT3_RGMII;
+	}
 	regmap_write(priv->sysctrl_base, GENCONF_CTRL0, val);
 }
 
@@ -1615,6 +1626,7 @@ static int mvpp22_gop_init(struct mvpp2_port *port, phy_interface_t interface)
 		return 0;
 
 	switch (interface) {
+	case PHY_INTERFACE_MODE_MII:
 	case PHY_INTERFACE_MODE_RGMII:
 	case PHY_INTERFACE_MODE_RGMII_ID:
 	case PHY_INTERFACE_MODE_RGMII_RXID:
@@ -5634,49 +5646,11 @@ static u32 mvpp2_ethtool_get_rxfh_indir_size(struct net_device *dev)
 	return mvpp22_rss_is_supported(port) ? MVPP22_RSS_TABLE_ENTRIES : 0;
 }
 
-static int mvpp2_ethtool_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
-				  u8 *hfunc)
-{
-	struct mvpp2_port *port = netdev_priv(dev);
-	int ret = 0;
-
-	if (!mvpp22_rss_is_supported(port))
-		return -EOPNOTSUPP;
-
-	if (indir)
-		ret = mvpp22_port_rss_ctx_indir_get(port, 0, indir);
-
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_CRC32;
-
-	return ret;
-}
-
-static int mvpp2_ethtool_set_rxfh(struct net_device *dev, const u32 *indir,
-				  const u8 *key, const u8 hfunc)
-{
-	struct mvpp2_port *port = netdev_priv(dev);
-	int ret = 0;
-
-	if (!mvpp22_rss_is_supported(port))
-		return -EOPNOTSUPP;
-
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_CRC32)
-		return -EOPNOTSUPP;
-
-	if (key)
-		return -EOPNOTSUPP;
-
-	if (indir)
-		ret = mvpp22_port_rss_ctx_indir_set(port, 0, indir);
-
-	return ret;
-}
-
-static int mvpp2_ethtool_get_rxfh_context(struct net_device *dev, u32 *indir,
-					  u8 *key, u8 *hfunc, u32 rss_context)
+static int mvpp2_ethtool_get_rxfh(struct net_device *dev,
+				  struct ethtool_rxfh_param *rxfh)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
+	u32 rss_context = rxfh->rss_context;
 	int ret = 0;
 
 	if (!mvpp22_rss_is_supported(port))
@@ -5684,33 +5658,34 @@ static int mvpp2_ethtool_get_rxfh_context(struct net_device *dev, u32 *indir,
 	if (rss_context >= MVPP22_N_RSS_TABLES)
 		return -EINVAL;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_CRC32;
+	rxfh->hfunc = ETH_RSS_HASH_CRC32;
 
-	if (indir)
-		ret = mvpp22_port_rss_ctx_indir_get(port, rss_context, indir);
+	if (rxfh->indir)
+		ret = mvpp22_port_rss_ctx_indir_get(port, rss_context,
+						    rxfh->indir);
 
 	return ret;
 }
 
-static int mvpp2_ethtool_set_rxfh_context(struct net_device *dev,
-					  const u32 *indir, const u8 *key,
-					  const u8 hfunc, u32 *rss_context,
-					  bool delete)
+static int mvpp2_ethtool_set_rxfh(struct net_device *dev,
+				  struct ethtool_rxfh_param *rxfh,
+				  struct netlink_ext_ack *extack)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
-	int ret;
+	u32 *rss_context = &rxfh->rss_context;
+	int ret = 0;
 
 	if (!mvpp22_rss_is_supported(port))
 		return -EOPNOTSUPP;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_CRC32)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_CRC32)
 		return -EOPNOTSUPP;
 
-	if (key)
+	if (rxfh->key)
 		return -EOPNOTSUPP;
 
-	if (delete)
+	if (*rss_context && rxfh->rss_delete)
 		return mvpp22_port_rss_ctx_delete(port, *rss_context);
 
 	if (*rss_context == ETH_RXFH_CONTEXT_ALLOC) {
@@ -5719,8 +5694,13 @@ static int mvpp2_ethtool_set_rxfh_context(struct net_device *dev,
 			return ret;
 	}
 
-	return mvpp22_port_rss_ctx_indir_set(port, *rss_context, indir);
+	if (rxfh->indir)
+		ret = mvpp22_port_rss_ctx_indir_set(port, *rss_context,
+						    rxfh->indir);
+
+	return ret;
 }
+
 /* Device ops */
 
 static const struct net_device_ops mvpp2_netdev_ops = {
@@ -5740,6 +5720,7 @@ static const struct net_device_ops mvpp2_netdev_ops = {
 };
 
 static const struct ethtool_ops mvpp2_eth_tool_ops = {
+	.cap_rss_ctx_supported	= true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES,
 	.nway_reset		= mvpp2_ethtool_nway_reset,
@@ -5762,8 +5743,6 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = {
 	.get_rxfh_indir_size	= mvpp2_ethtool_get_rxfh_indir_size,
 	.get_rxfh		= mvpp2_ethtool_get_rxfh,
 	.set_rxfh		= mvpp2_ethtool_set_rxfh,
-	.get_rxfh_context	= mvpp2_ethtool_get_rxfh_context,
-	.set_rxfh_context	= mvpp2_ethtool_set_rxfh_context,
 };
 
 /* Used for PPv2.1, or PPv2.2 with the old Device Tree binding that
@@ -6898,7 +6877,7 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 	dev->min_mtu = ETH_MIN_MTU;
 	/* 9704 == 9728 - 20 and rounding to 8 */
 	dev->max_mtu = MVPP2_BM_JUMBO_PKT_SIZE;
-	dev->dev.of_node = port_node;
+	device_set_node(&dev->dev, port_fwnode);
 
 	port->pcs_gmac.ops = &mvpp2_phylink_gmac_pcs_ops;
 	port->pcs_gmac.neg_mode = true;
@@ -6948,8 +6927,11 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 					MAC_10000FD;
 		}
 
-		if (mvpp2_port_supports_rgmii(port))
+		if (mvpp2_port_supports_rgmii(port)) {
 			phy_interface_set_rgmii(port->phylink_config.supported_interfaces);
+			__set_bit(PHY_INTERFACE_MODE_MII,
+				  port->phylink_config.supported_interfaces);
+		}
 
 		if (comphy) {
 			/* If a COMPHY is present, we can support any of the
diff --git a/drivers/net/ethernet/marvell/octeon_ep/Makefile b/drivers/net/ethernet/marvell/octeon_ep/Makefile
index 2026c8118158..62162ed63f34 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/Makefile
+++ b/drivers/net/ethernet/marvell/octeon_ep/Makefile
@@ -6,4 +6,5 @@
 obj-$(CONFIG_OCTEON_EP) += octeon_ep.o
 
 octeon_ep-y := octep_main.o octep_cn9k_pf.o octep_tx.o octep_rx.o \
-	       octep_ethtool.o octep_ctrl_mbox.o octep_ctrl_net.o
+	       octep_ethtool.o octep_ctrl_mbox.o octep_ctrl_net.o \
+	       octep_pfvf_mbox.o octep_cnxk_pf.o
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_cn9k_pf.c b/drivers/net/ethernet/marvell/octeon_ep/octep_cn9k_pf.c
index d4ee2454675b..b5805969404f 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_cn9k_pf.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_cn9k_pf.c
@@ -216,16 +216,21 @@ static void octep_init_config_cn93_pf(struct octep_device *oct)
 	conf->sriov_cfg.vf_srn = CN93_SDP_EPF_RINFO_SRN(val);
 
 	val = octep_read_csr64(oct, CN93_SDP_MAC_PF_RING_CTL(oct->pcie_port));
-	conf->pf_ring_cfg.srn =  CN93_SDP_MAC_PF_RING_CTL_SRN(val);
-	conf->pf_ring_cfg.max_io_rings = CN93_SDP_MAC_PF_RING_CTL_RPPF(val);
-	conf->pf_ring_cfg.active_io_rings = conf->pf_ring_cfg.max_io_rings;
+	if (oct->chip_id == OCTEP_PCI_DEVICE_ID_CN98_PF) {
+		conf->pf_ring_cfg.srn =  CN98_SDP_MAC_PF_RING_CTL_SRN(val);
+		conf->pf_ring_cfg.max_io_rings = CN98_SDP_MAC_PF_RING_CTL_RPPF(val);
+		conf->pf_ring_cfg.active_io_rings = conf->pf_ring_cfg.max_io_rings;
+	} else {
+		conf->pf_ring_cfg.srn =  CN93_SDP_MAC_PF_RING_CTL_SRN(val);
+		conf->pf_ring_cfg.max_io_rings = CN93_SDP_MAC_PF_RING_CTL_RPPF(val);
+		conf->pf_ring_cfg.active_io_rings = conf->pf_ring_cfg.max_io_rings;
+	}
 	dev_info(&pdev->dev, "pf_srn=%u rpvf=%u nvfs=%u rppf=%u\n",
 		 conf->pf_ring_cfg.srn, conf->sriov_cfg.active_rings_per_vf,
 		 conf->sriov_cfg.active_vfs, conf->pf_ring_cfg.active_io_rings);
 
 	conf->iq.num_descs = OCTEP_IQ_MAX_DESCRIPTORS;
 	conf->iq.instr_type = OCTEP_64BYTE_INSTR;
-	conf->iq.pkind = 0;
 	conf->iq.db_min = OCTEP_DB_MIN;
 	conf->iq.intr_threshold = OCTEP_IQ_INTR_THRESHOLD;
 
@@ -357,16 +362,55 @@ static void octep_setup_mbox_regs_cn93_pf(struct octep_device *oct, int q_no)
 {
 	struct octep_mbox *mbox = oct->mbox[q_no];
 
-	mbox->q_no = q_no;
-
-	/* PF mbox interrupt reg */
-	mbox->mbox_int_reg = oct->mmio[0].hw_addr + CN93_SDP_EPF_MBOX_RINT(0);
-
 	/* PF to VF DATA reg. PF writes into this reg */
-	mbox->mbox_write_reg = oct->mmio[0].hw_addr + CN93_SDP_R_MBOX_PF_VF_DATA(q_no);
+	mbox->pf_vf_data_reg = oct->mmio[0].hw_addr + CN93_SDP_MBOX_PF_VF_DATA(q_no);
 
 	/* VF to PF DATA reg. PF reads from this reg */
-	mbox->mbox_read_reg = oct->mmio[0].hw_addr + CN93_SDP_R_MBOX_VF_PF_DATA(q_no);
+	mbox->vf_pf_data_reg = oct->mmio[0].hw_addr + CN93_SDP_MBOX_VF_PF_DATA(q_no);
+}
+
+/* Poll for mailbox messages from VF */
+static void octep_poll_pfvf_mailbox(struct octep_device *oct)
+{
+	u32 vf, active_vfs, active_rings_per_vf, vf_mbox_queue;
+	u64 reg0, reg1;
+
+	reg0 = octep_read_csr64(oct, CN93_SDP_EPF_MBOX_RINT(0));
+	reg1 = octep_read_csr64(oct, CN93_SDP_EPF_MBOX_RINT(1));
+	if (reg0 || reg1) {
+		active_vfs = CFG_GET_ACTIVE_VFS(oct->conf);
+		active_rings_per_vf = CFG_GET_ACTIVE_RPVF(oct->conf);
+		for (vf = 0; vf < active_vfs; vf++) {
+			vf_mbox_queue = vf * active_rings_per_vf;
+
+			if (vf_mbox_queue < 64) {
+				if (!(reg0 & (0x1UL << vf_mbox_queue)))
+					continue;
+			} else {
+				if (!(reg1 & (0x1UL << (vf_mbox_queue - 64))))
+					continue;
+			}
+
+			if (!oct->mbox[vf_mbox_queue]) {
+				dev_err(&oct->pdev->dev, "bad mbox vf %d\n", vf);
+				continue;
+			}
+			schedule_work(&oct->mbox[vf_mbox_queue]->wk.work);
+		}
+		if (reg0)
+			octep_write_csr64(oct, CN93_SDP_EPF_MBOX_RINT(0), reg0);
+		if (reg1)
+			octep_write_csr64(oct, CN93_SDP_EPF_MBOX_RINT(1), reg1);
+	}
+}
+
+/* PF-VF mailbox interrupt handler */
+static irqreturn_t octep_pfvf_mbox_intr_handler_cn93_pf(void *dev)
+{
+	struct octep_device *oct = (struct octep_device *)dev;
+
+	octep_poll_pfvf_mailbox(oct);
+	return IRQ_HANDLED;
 }
 
 /* Poll OEI events like heartbeat */
@@ -398,6 +442,7 @@ static irqreturn_t octep_oei_intr_handler_cn93_pf(void *dev)
  */
 static void octep_poll_non_ioq_interrupts_cn93_pf(struct octep_device *oct)
 {
+	octep_poll_pfvf_mailbox(oct);
 	octep_poll_oei_cn93_pf(oct);
 }
 
@@ -578,6 +623,13 @@ static irqreturn_t octep_ioq_intr_handler_cn93_pf(void *data)
 	return IRQ_HANDLED;
 }
 
+/* soft reset of 98xx */
+static int octep_soft_reset_cn98_pf(struct octep_device *oct)
+{
+	dev_info(&oct->pdev->dev, "CN98XX: skip soft reset\n");
+	return 0;
+}
+
 /* soft reset of 93xx */
 static int octep_soft_reset_cn93_pf(struct octep_device *oct)
 {
@@ -634,6 +686,8 @@ static void octep_enable_interrupts_cn93_pf(struct octep_device *oct)
 
 	octep_write_csr64(oct, CN93_SDP_EPF_MISC_RINT_ENA_W1S, intr_mask);
 	octep_write_csr64(oct, CN93_SDP_EPF_DMA_RINT_ENA_W1S, intr_mask);
+	octep_write_csr64(oct, CN93_SDP_EPF_MBOX_RINT_ENA_W1S(0), -1ULL);
+	octep_write_csr64(oct, CN93_SDP_EPF_MBOX_RINT_ENA_W1S(1), -1ULL);
 
 	octep_write_csr64(oct, CN93_SDP_EPF_DMA_VF_RINT_ENA_W1S(0), -1ULL);
 	octep_write_csr64(oct, CN93_SDP_EPF_PP_VF_RINT_ENA_W1S(0), -1ULL);
@@ -660,6 +714,8 @@ static void octep_disable_interrupts_cn93_pf(struct octep_device *oct)
 
 	octep_write_csr64(oct, CN93_SDP_EPF_MISC_RINT_ENA_W1C, intr_mask);
 	octep_write_csr64(oct, CN93_SDP_EPF_DMA_RINT_ENA_W1C, intr_mask);
+	octep_write_csr64(oct, CN93_SDP_EPF_MBOX_RINT_ENA_W1C(0), -1ULL);
+	octep_write_csr64(oct, CN93_SDP_EPF_MBOX_RINT_ENA_W1C(1), -1ULL);
 
 	octep_write_csr64(oct, CN93_SDP_EPF_DMA_VF_RINT_ENA_W1C(0), -1ULL);
 	octep_write_csr64(oct, CN93_SDP_EPF_PP_VF_RINT_ENA_W1C(0), -1ULL);
@@ -795,6 +851,7 @@ void octep_device_setup_cn93_pf(struct octep_device *oct)
 	oct->hw_ops.setup_oq_regs = octep_setup_oq_regs_cn93_pf;
 	oct->hw_ops.setup_mbox_regs = octep_setup_mbox_regs_cn93_pf;
 
+	oct->hw_ops.mbox_intr_handler = octep_pfvf_mbox_intr_handler_cn93_pf;
 	oct->hw_ops.oei_intr_handler = octep_oei_intr_handler_cn93_pf;
 	oct->hw_ops.ire_intr_handler = octep_ire_intr_handler_cn93_pf;
 	oct->hw_ops.ore_intr_handler = octep_ore_intr_handler_cn93_pf;
@@ -806,7 +863,10 @@ void octep_device_setup_cn93_pf(struct octep_device *oct)
 	oct->hw_ops.misc_intr_handler = octep_misc_intr_handler_cn93_pf;
 	oct->hw_ops.rsvd_intr_handler = octep_rsvd_intr_handler_cn93_pf;
 	oct->hw_ops.ioq_intr_handler = octep_ioq_intr_handler_cn93_pf;
-	oct->hw_ops.soft_reset = octep_soft_reset_cn93_pf;
+	if (oct->chip_id == OCTEP_PCI_DEVICE_ID_CN98_PF)
+		oct->hw_ops.soft_reset = octep_soft_reset_cn98_pf;
+	else
+		oct->hw_ops.soft_reset = octep_soft_reset_cn93_pf;
 	oct->hw_ops.reinit_regs = octep_reinit_regs_cn93_pf;
 
 	oct->hw_ops.enable_interrupts = octep_enable_interrupts_cn93_pf;
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_cnxk_pf.c b/drivers/net/ethernet/marvell/octeon_ep/octep_cnxk_pf.c
new file mode 100644
index 000000000000..5de0b5ecbc5f
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_cnxk_pf.c
@@ -0,0 +1,925 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell Octeon EP (EndPoint) Ethernet Driver
+ *
+ * Copyright (C) 2020 Marvell.
+ *
+ */
+
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+
+#include "octep_config.h"
+#include "octep_main.h"
+#include "octep_regs_cnxk_pf.h"
+
+/* We will support 128 pf's in control mbox */
+#define CTRL_MBOX_MAX_PF	128
+#define CTRL_MBOX_SZ		((size_t)(0x400000 / CTRL_MBOX_MAX_PF))
+
+/* Names of Hardware non-queue generic interrupts */
+static char *cnxk_non_ioq_msix_names[] = {
+	"epf_ire_rint",
+	"epf_ore_rint",
+	"epf_vfire_rint",
+	"epf_rsvd0",
+	"epf_vfore_rint",
+	"epf_rsvd1",
+	"epf_mbox_rint",
+	"epf_rsvd2_0",
+	"epf_rsvd2_1",
+	"epf_dma_rint",
+	"epf_dma_vf_rint",
+	"epf_rsvd3",
+	"epf_pp_vf_rint",
+	"epf_rsvd3",
+	"epf_misc_rint",
+	"epf_rsvd5",
+	/* Next 16 are for OEI_RINT */
+	"epf_oei_rint0",
+	"epf_oei_rint1",
+	"epf_oei_rint2",
+	"epf_oei_rint3",
+	"epf_oei_rint4",
+	"epf_oei_rint5",
+	"epf_oei_rint6",
+	"epf_oei_rint7",
+	"epf_oei_rint8",
+	"epf_oei_rint9",
+	"epf_oei_rint10",
+	"epf_oei_rint11",
+	"epf_oei_rint12",
+	"epf_oei_rint13",
+	"epf_oei_rint14",
+	"epf_oei_rint15",
+	/* IOQ interrupt */
+	"octeon_ep"
+};
+
+/* Dump useful hardware CSRs for debug purpose */
+static void cnxk_dump_regs(struct octep_device *oct, int qno)
+{
+	struct device *dev = &oct->pdev->dev;
+
+	dev_info(dev, "IQ-%d register dump\n", qno);
+	dev_info(dev, "R[%d]_IN_INSTR_DBELL[0x%llx]: 0x%016llx\n",
+		 qno, CNXK_SDP_R_IN_INSTR_DBELL(qno),
+		 octep_read_csr64(oct, CNXK_SDP_R_IN_INSTR_DBELL(qno)));
+	dev_info(dev, "R[%d]_IN_CONTROL[0x%llx]: 0x%016llx\n",
+		 qno, CNXK_SDP_R_IN_CONTROL(qno),
+		 octep_read_csr64(oct, CNXK_SDP_R_IN_CONTROL(qno)));
+	dev_info(dev, "R[%d]_IN_ENABLE[0x%llx]: 0x%016llx\n",
+		 qno, CNXK_SDP_R_IN_ENABLE(qno),
+		 octep_read_csr64(oct, CNXK_SDP_R_IN_ENABLE(qno)));
+	dev_info(dev, "R[%d]_IN_INSTR_BADDR[0x%llx]: 0x%016llx\n",
+		 qno, CNXK_SDP_R_IN_INSTR_BADDR(qno),
+		 octep_read_csr64(oct, CNXK_SDP_R_IN_INSTR_BADDR(qno)));
+	dev_info(dev, "R[%d]_IN_INSTR_RSIZE[0x%llx]: 0x%016llx\n",
+		 qno, CNXK_SDP_R_IN_INSTR_RSIZE(qno),
+		 octep_read_csr64(oct, CNXK_SDP_R_IN_INSTR_RSIZE(qno)));
+	dev_info(dev, "R[%d]_IN_CNTS[0x%llx]: 0x%016llx\n",
+		 qno, CNXK_SDP_R_IN_CNTS(qno),
+		 octep_read_csr64(oct, CNXK_SDP_R_IN_CNTS(qno)));
+	dev_info(dev, "R[%d]_IN_INT_LEVELS[0x%llx]: 0x%016llx\n",
+		 qno, CNXK_SDP_R_IN_INT_LEVELS(qno),
+		 octep_read_csr64(oct, CNXK_SDP_R_IN_INT_LEVELS(qno)));
+	dev_info(dev, "R[%d]_IN_PKT_CNT[0x%llx]: 0x%016llx\n",
+		 qno, CNXK_SDP_R_IN_PKT_CNT(qno),
+		 octep_read_csr64(oct, CNXK_SDP_R_IN_PKT_CNT(qno)));
+	dev_info(dev, "R[%d]_IN_BYTE_CNT[0x%llx]: 0x%016llx\n",
+		 qno, CNXK_SDP_R_IN_BYTE_CNT(qno),
+		 octep_read_csr64(oct, CNXK_SDP_R_IN_BYTE_CNT(qno)));
+
+	dev_info(dev, "OQ-%d register dump\n", qno);
+	dev_info(dev, "R[%d]_OUT_SLIST_DBELL[0x%llx]: 0x%016llx\n",
+		 qno, CNXK_SDP_R_OUT_SLIST_DBELL(qno),
+		 octep_read_csr64(oct, CNXK_SDP_R_OUT_SLIST_DBELL(qno)));
+	dev_info(dev, "R[%d]_OUT_CONTROL[0x%llx]: 0x%016llx\n",
+		 qno, CNXK_SDP_R_OUT_CONTROL(qno),
+		 octep_read_csr64(oct, CNXK_SDP_R_OUT_CONTROL(qno)));
+	dev_info(dev, "R[%d]_OUT_ENABLE[0x%llx]: 0x%016llx\n",
+		 qno, CNXK_SDP_R_OUT_ENABLE(qno),
+		 octep_read_csr64(oct, CNXK_SDP_R_OUT_ENABLE(qno)));
+	dev_info(dev, "R[%d]_OUT_SLIST_BADDR[0x%llx]: 0x%016llx\n",
+		 qno, CNXK_SDP_R_OUT_SLIST_BADDR(qno),
+		 octep_read_csr64(oct, CNXK_SDP_R_OUT_SLIST_BADDR(qno)));
+	dev_info(dev, "R[%d]_OUT_SLIST_RSIZE[0x%llx]: 0x%016llx\n",
+		 qno, CNXK_SDP_R_OUT_SLIST_RSIZE(qno),
+		 octep_read_csr64(oct, CNXK_SDP_R_OUT_SLIST_RSIZE(qno)));
+	dev_info(dev, "R[%d]_OUT_CNTS[0x%llx]: 0x%016llx\n",
+		 qno, CNXK_SDP_R_OUT_CNTS(qno),
+		 octep_read_csr64(oct, CNXK_SDP_R_OUT_CNTS(qno)));
+	dev_info(dev, "R[%d]_OUT_INT_LEVELS[0x%llx]: 0x%016llx\n",
+		 qno, CNXK_SDP_R_OUT_INT_LEVELS(qno),
+		 octep_read_csr64(oct, CNXK_SDP_R_OUT_INT_LEVELS(qno)));
+	dev_info(dev, "R[%d]_OUT_PKT_CNT[0x%llx]: 0x%016llx\n",
+		 qno, CNXK_SDP_R_OUT_PKT_CNT(qno),
+		 octep_read_csr64(oct, CNXK_SDP_R_OUT_PKT_CNT(qno)));
+	dev_info(dev, "R[%d]_OUT_BYTE_CNT[0x%llx]: 0x%016llx\n",
+		 qno, CNXK_SDP_R_OUT_BYTE_CNT(qno),
+		 octep_read_csr64(oct, CNXK_SDP_R_OUT_BYTE_CNT(qno)));
+	dev_info(dev, "R[%d]_ERR_TYPE[0x%llx]: 0x%016llx\n",
+		 qno, CNXK_SDP_R_ERR_TYPE(qno),
+		 octep_read_csr64(oct, CNXK_SDP_R_ERR_TYPE(qno)));
+}
+
+/* Reset Hardware Tx queue */
+static int cnxk_reset_iq(struct octep_device *oct, int q_no)
+{
+	struct octep_config *conf = oct->conf;
+	u64 val = 0ULL;
+
+	dev_dbg(&oct->pdev->dev, "Reset PF IQ-%d\n", q_no);
+
+	/* Get absolute queue number */
+	q_no += conf->pf_ring_cfg.srn;
+
+	/* Disable the Tx/Instruction Ring */
+	octep_write_csr64(oct, CNXK_SDP_R_IN_ENABLE(q_no), val);
+
+	/* clear the Instruction Ring packet/byte counts and doorbell CSRs */
+	octep_write_csr64(oct, CNXK_SDP_R_IN_CNTS(q_no), val);
+	octep_write_csr64(oct, CNXK_SDP_R_IN_INT_LEVELS(q_no), val);
+	octep_write_csr64(oct, CNXK_SDP_R_IN_PKT_CNT(q_no), val);
+	octep_write_csr64(oct, CNXK_SDP_R_IN_BYTE_CNT(q_no), val);
+	octep_write_csr64(oct, CNXK_SDP_R_IN_INSTR_BADDR(q_no), val);
+	octep_write_csr64(oct, CNXK_SDP_R_IN_INSTR_RSIZE(q_no), val);
+
+	val = 0xFFFFFFFF;
+	octep_write_csr64(oct, CNXK_SDP_R_IN_INSTR_DBELL(q_no), val);
+
+	return 0;
+}
+
+/* Reset Hardware Rx queue */
+static void cnxk_reset_oq(struct octep_device *oct, int q_no)
+{
+	u64 val = 0ULL;
+
+	q_no += CFG_GET_PORTS_PF_SRN(oct->conf);
+
+	/* Disable Output (Rx) Ring */
+	octep_write_csr64(oct, CNXK_SDP_R_OUT_ENABLE(q_no), val);
+	octep_write_csr64(oct, CNXK_SDP_R_OUT_SLIST_BADDR(q_no), val);
+	octep_write_csr64(oct, CNXK_SDP_R_OUT_SLIST_RSIZE(q_no), val);
+	octep_write_csr64(oct, CNXK_SDP_R_OUT_INT_LEVELS(q_no), val);
+
+	/* Clear count CSRs */
+	val = octep_read_csr(oct, CNXK_SDP_R_OUT_CNTS(q_no));
+	octep_write_csr(oct, CNXK_SDP_R_OUT_CNTS(q_no), val);
+
+	octep_write_csr64(oct, CNXK_SDP_R_OUT_PKT_CNT(q_no), 0xFFFFFFFFFULL);
+	octep_write_csr64(oct, CNXK_SDP_R_OUT_SLIST_DBELL(q_no), 0xFFFFFFFF);
+}
+
+/* Reset all hardware Tx/Rx queues */
+static void octep_reset_io_queues_cnxk_pf(struct octep_device *oct)
+{
+	struct pci_dev *pdev = oct->pdev;
+	int q;
+
+	dev_dbg(&pdev->dev, "Reset OCTEP_CNXK PF IO Queues\n");
+
+	for (q = 0; q < CFG_GET_PORTS_ACTIVE_IO_RINGS(oct->conf); q++) {
+		cnxk_reset_iq(oct, q);
+		cnxk_reset_oq(oct, q);
+	}
+}
+
+/* Initialize windowed addresses to access some hardware registers */
+static void octep_setup_pci_window_regs_cnxk_pf(struct octep_device *oct)
+{
+	u8 __iomem *bar0_pciaddr = oct->mmio[0].hw_addr;
+
+	oct->pci_win_regs.pci_win_wr_addr = (u8 __iomem *)(bar0_pciaddr + CNXK_SDP_WIN_WR_ADDR64);
+	oct->pci_win_regs.pci_win_rd_addr = (u8 __iomem *)(bar0_pciaddr + CNXK_SDP_WIN_RD_ADDR64);
+	oct->pci_win_regs.pci_win_wr_data = (u8 __iomem *)(bar0_pciaddr + CNXK_SDP_WIN_WR_DATA64);
+	oct->pci_win_regs.pci_win_rd_data = (u8 __iomem *)(bar0_pciaddr + CNXK_SDP_WIN_RD_DATA64);
+}
+
+/* Configure Hardware mapping: inform hardware which rings belong to PF. */
+static void octep_configure_ring_mapping_cnxk_pf(struct octep_device *oct)
+{
+	struct octep_config *conf = oct->conf;
+	struct pci_dev *pdev = oct->pdev;
+	u64 pf_srn = CFG_GET_PORTS_PF_SRN(oct->conf);
+	int q;
+
+	for (q = 0; q < CFG_GET_PORTS_ACTIVE_IO_RINGS(conf); q++) {
+		u64 regval = 0;
+
+		if (oct->pcie_port)
+			regval = 8 << CNXK_SDP_FUNC_SEL_EPF_BIT_POS;
+
+		octep_write_csr64(oct, CNXK_SDP_EPVF_RING(pf_srn + q), regval);
+
+		regval = octep_read_csr64(oct, CNXK_SDP_EPVF_RING(pf_srn + q));
+		dev_dbg(&pdev->dev, "Write SDP_EPVF_RING[0x%llx] = 0x%llx\n",
+			CNXK_SDP_EPVF_RING(pf_srn + q), regval);
+	}
+}
+
+/* Initialize configuration limits and initial active config */
+static void octep_init_config_cnxk_pf(struct octep_device *oct)
+{
+	struct octep_config *conf = oct->conf;
+	struct pci_dev *pdev = oct->pdev;
+	u8 link = 0;
+	u64 val;
+	int pos;
+
+	/* Read ring configuration:
+	 * PF ring count, number of VFs and rings per VF supported
+	 */
+	val = octep_read_csr64(oct, CNXK_SDP_EPF_RINFO);
+	dev_info(&pdev->dev, "SDP_EPF_RINFO[0x%x]:0x%llx\n", CNXK_SDP_EPF_RINFO, val);
+	conf->sriov_cfg.max_rings_per_vf = CNXK_SDP_EPF_RINFO_RPVF(val);
+	conf->sriov_cfg.active_rings_per_vf = conf->sriov_cfg.max_rings_per_vf;
+	conf->sriov_cfg.max_vfs = CNXK_SDP_EPF_RINFO_NVFS(val);
+	conf->sriov_cfg.active_vfs = conf->sriov_cfg.max_vfs;
+	conf->sriov_cfg.vf_srn = CNXK_SDP_EPF_RINFO_SRN(val);
+
+	val = octep_read_csr64(oct, CNXK_SDP_MAC_PF_RING_CTL(oct->pcie_port));
+	dev_info(&pdev->dev, "SDP_MAC_PF_RING_CTL[%d]:0x%llx\n", oct->pcie_port, val);
+	conf->pf_ring_cfg.srn =  CNXK_SDP_MAC_PF_RING_CTL_SRN(val);
+	conf->pf_ring_cfg.max_io_rings = CNXK_SDP_MAC_PF_RING_CTL_RPPF(val);
+	conf->pf_ring_cfg.active_io_rings = conf->pf_ring_cfg.max_io_rings;
+	dev_info(&pdev->dev, "pf_srn=%u rpvf=%u nvfs=%u rppf=%u\n",
+		 conf->pf_ring_cfg.srn, conf->sriov_cfg.active_rings_per_vf,
+		 conf->sriov_cfg.active_vfs, conf->pf_ring_cfg.active_io_rings);
+
+	conf->iq.num_descs = OCTEP_IQ_MAX_DESCRIPTORS;
+	conf->iq.instr_type = OCTEP_64BYTE_INSTR;
+	conf->iq.db_min = OCTEP_DB_MIN;
+	conf->iq.intr_threshold = OCTEP_IQ_INTR_THRESHOLD;
+
+	conf->oq.num_descs = OCTEP_OQ_MAX_DESCRIPTORS;
+	conf->oq.buf_size = OCTEP_OQ_BUF_SIZE;
+	conf->oq.refill_threshold = OCTEP_OQ_REFILL_THRESHOLD;
+	conf->oq.oq_intr_pkt = OCTEP_OQ_INTR_PKT_THRESHOLD;
+	conf->oq.oq_intr_time = OCTEP_OQ_INTR_TIME_THRESHOLD;
+	conf->oq.wmark = OCTEP_OQ_WMARK_MIN;
+
+	conf->msix_cfg.non_ioq_msix = CNXK_NUM_NON_IOQ_INTR;
+	conf->msix_cfg.ioq_msix = conf->pf_ring_cfg.active_io_rings;
+	conf->msix_cfg.non_ioq_msix_names = cnxk_non_ioq_msix_names;
+
+	pos = pci_find_ext_capability(oct->pdev, PCI_EXT_CAP_ID_SRIOV);
+	if (pos) {
+		pci_read_config_byte(oct->pdev,
+				     pos + PCI_SRIOV_FUNC_LINK,
+				     &link);
+		link = PCI_DEVFN(PCI_SLOT(oct->pdev->devfn), link);
+	}
+	conf->ctrl_mbox_cfg.barmem_addr = (void __iomem *)oct->mmio[2].hw_addr +
+					   CNXK_PEM_BAR4_INDEX_OFFSET +
+					   (link * CTRL_MBOX_SZ);
+
+	conf->fw_info.hb_interval = OCTEP_DEFAULT_FW_HB_INTERVAL;
+	conf->fw_info.hb_miss_count = OCTEP_DEFAULT_FW_HB_MISS_COUNT;
+}
+
+/* Setup registers for a hardware Tx Queue  */
+static void octep_setup_iq_regs_cnxk_pf(struct octep_device *oct, int iq_no)
+{
+	struct octep_iq *iq = oct->iq[iq_no];
+	u32 reset_instr_cnt;
+	u64 reg_val;
+
+	iq_no += CFG_GET_PORTS_PF_SRN(oct->conf);
+	reg_val = octep_read_csr64(oct, CNXK_SDP_R_IN_CONTROL(iq_no));
+
+	/* wait for IDLE to set to 1 */
+	if (!(reg_val & CNXK_R_IN_CTL_IDLE)) {
+		do {
+			reg_val = octep_read_csr64(oct, CNXK_SDP_R_IN_CONTROL(iq_no));
+		} while (!(reg_val & CNXK_R_IN_CTL_IDLE));
+	}
+
+	reg_val |= CNXK_R_IN_CTL_RDSIZE;
+	reg_val |= CNXK_R_IN_CTL_IS_64B;
+	reg_val |= CNXK_R_IN_CTL_ESR;
+	octep_write_csr64(oct, CNXK_SDP_R_IN_CONTROL(iq_no), reg_val);
+
+	/* Write the start of the input queue's ring and its size  */
+	octep_write_csr64(oct, CNXK_SDP_R_IN_INSTR_BADDR(iq_no),
+			  iq->desc_ring_dma);
+	octep_write_csr64(oct, CNXK_SDP_R_IN_INSTR_RSIZE(iq_no),
+			  iq->max_count);
+
+	/* Remember the doorbell & instruction count register addr
+	 * for this queue
+	 */
+	iq->doorbell_reg = oct->mmio[0].hw_addr +
+			   CNXK_SDP_R_IN_INSTR_DBELL(iq_no);
+	iq->inst_cnt_reg = oct->mmio[0].hw_addr +
+			   CNXK_SDP_R_IN_CNTS(iq_no);
+	iq->intr_lvl_reg = oct->mmio[0].hw_addr +
+			   CNXK_SDP_R_IN_INT_LEVELS(iq_no);
+
+	/* Store the current instruction counter (used in flush_iq calculation) */
+	reset_instr_cnt = readl(iq->inst_cnt_reg);
+	writel(reset_instr_cnt, iq->inst_cnt_reg);
+
+	/* INTR_THRESHOLD is set to max(FFFFFFFF) to disable the INTR */
+	reg_val = CFG_GET_IQ_INTR_THRESHOLD(oct->conf) & 0xffffffff;
+	octep_write_csr64(oct, CNXK_SDP_R_IN_INT_LEVELS(iq_no), reg_val);
+}
+
+/* Setup registers for a hardware Rx Queue  */
+static void octep_setup_oq_regs_cnxk_pf(struct octep_device *oct, int oq_no)
+{
+	u64 reg_val;
+	u64 oq_ctl = 0ULL;
+	u32 time_threshold = 0;
+	struct octep_oq *oq = oct->oq[oq_no];
+
+	oq_no += CFG_GET_PORTS_PF_SRN(oct->conf);
+	reg_val = octep_read_csr64(oct, CNXK_SDP_R_OUT_CONTROL(oq_no));
+
+	/* wait for IDLE to set to 1 */
+	if (!(reg_val & CNXK_R_OUT_CTL_IDLE)) {
+		do {
+			reg_val = octep_read_csr64(oct, CNXK_SDP_R_OUT_CONTROL(oq_no));
+		} while (!(reg_val & CNXK_R_OUT_CTL_IDLE));
+	}
+
+	reg_val &= ~(CNXK_R_OUT_CTL_IMODE);
+	reg_val &= ~(CNXK_R_OUT_CTL_ROR_P);
+	reg_val &= ~(CNXK_R_OUT_CTL_NSR_P);
+	reg_val &= ~(CNXK_R_OUT_CTL_ROR_I);
+	reg_val &= ~(CNXK_R_OUT_CTL_NSR_I);
+	reg_val &= ~(CNXK_R_OUT_CTL_ES_I);
+	reg_val &= ~(CNXK_R_OUT_CTL_ROR_D);
+	reg_val &= ~(CNXK_R_OUT_CTL_NSR_D);
+	reg_val &= ~(CNXK_R_OUT_CTL_ES_D);
+	reg_val |= (CNXK_R_OUT_CTL_ES_P);
+
+	octep_write_csr64(oct, CNXK_SDP_R_OUT_CONTROL(oq_no), reg_val);
+	octep_write_csr64(oct, CNXK_SDP_R_OUT_SLIST_BADDR(oq_no),
+			  oq->desc_ring_dma);
+	octep_write_csr64(oct, CNXK_SDP_R_OUT_SLIST_RSIZE(oq_no),
+			  oq->max_count);
+
+	oq_ctl = octep_read_csr64(oct, CNXK_SDP_R_OUT_CONTROL(oq_no));
+
+	/* Clear the ISIZE and BSIZE (22-0) */
+	oq_ctl &= ~0x7fffffULL;
+
+	/* Populate the BSIZE (15-0) */
+	oq_ctl |= (oq->buffer_size & 0xffff);
+	octep_write_csr64(oct, CNXK_SDP_R_OUT_CONTROL(oq_no), oq_ctl);
+
+	/* Get the mapped address of the pkt_sent and pkts_credit regs */
+	oq->pkts_sent_reg = oct->mmio[0].hw_addr + CNXK_SDP_R_OUT_CNTS(oq_no);
+	oq->pkts_credit_reg = oct->mmio[0].hw_addr +
+			      CNXK_SDP_R_OUT_SLIST_DBELL(oq_no);
+
+	time_threshold = CFG_GET_OQ_INTR_TIME(oct->conf);
+	reg_val = ((u64)time_threshold << 32) |
+		  CFG_GET_OQ_INTR_PKT(oct->conf);
+	octep_write_csr64(oct, CNXK_SDP_R_OUT_INT_LEVELS(oq_no), reg_val);
+
+	/* set watermark for backpressure */
+	reg_val = octep_read_csr64(oct, CNXK_SDP_R_OUT_WMARK(oq_no));
+	reg_val &= ~0xFFFFFFFFULL;
+	reg_val |= CFG_GET_OQ_WMARK(oct->conf);
+	octep_write_csr64(oct, CNXK_SDP_R_OUT_WMARK(oq_no), reg_val);
+}
+
+/* Setup registers for a PF mailbox */
+static void octep_setup_mbox_regs_cnxk_pf(struct octep_device *oct, int q_no)
+{
+	struct octep_mbox *mbox = oct->mbox[q_no];
+
+	/* PF to VF DATA reg. PF writes into this reg */
+	mbox->pf_vf_data_reg = oct->mmio[0].hw_addr + CNXK_SDP_MBOX_PF_VF_DATA(q_no);
+
+	/* VF to PF DATA reg. PF reads from this reg */
+	mbox->vf_pf_data_reg = oct->mmio[0].hw_addr + CNXK_SDP_MBOX_VF_PF_DATA(q_no);
+}
+
+static void octep_poll_pfvf_mailbox_cnxk_pf(struct octep_device *oct)
+{
+	u32 vf, active_vfs, active_rings_per_vf, vf_mbox_queue;
+	u64 reg0;
+
+	reg0 = octep_read_csr64(oct, CNXK_SDP_EPF_MBOX_RINT(0));
+	if (reg0) {
+		active_vfs = CFG_GET_ACTIVE_VFS(oct->conf);
+		active_rings_per_vf = CFG_GET_ACTIVE_RPVF(oct->conf);
+		for (vf = 0; vf < active_vfs; vf++) {
+			vf_mbox_queue = vf * active_rings_per_vf;
+			if (!(reg0 & (0x1UL << vf_mbox_queue)))
+				continue;
+
+			if (!oct->mbox[vf_mbox_queue]) {
+				dev_err(&oct->pdev->dev, "bad mbox vf %d\n", vf);
+				continue;
+			}
+			schedule_work(&oct->mbox[vf_mbox_queue]->wk.work);
+		}
+		if (reg0)
+			octep_write_csr64(oct, CNXK_SDP_EPF_MBOX_RINT(0), reg0);
+	}
+}
+
+static irqreturn_t octep_pfvf_mbox_intr_handler_cnxk_pf(void *dev)
+{
+	struct octep_device *oct = (struct octep_device *)dev;
+
+	octep_poll_pfvf_mailbox_cnxk_pf(oct);
+	return IRQ_HANDLED;
+}
+
+/* Poll OEI events like heartbeat */
+static void octep_poll_oei_cnxk_pf(struct octep_device *oct)
+{
+	u64 reg0;
+
+	/* Check for OEI INTR */
+	reg0 = octep_read_csr64(oct, CNXK_SDP_EPF_OEI_RINT);
+	if (reg0) {
+		octep_write_csr64(oct, CNXK_SDP_EPF_OEI_RINT, reg0);
+		if (reg0 & CNXK_SDP_EPF_OEI_RINT_DATA_BIT_MBOX)
+			queue_work(octep_wq, &oct->ctrl_mbox_task);
+		if (reg0 & CNXK_SDP_EPF_OEI_RINT_DATA_BIT_HBEAT)
+			atomic_set(&oct->hb_miss_cnt, 0);
+	}
+}
+
+/* OEI interrupt handler */
+static irqreturn_t octep_oei_intr_handler_cnxk_pf(void *dev)
+{
+	struct octep_device *oct = (struct octep_device *)dev;
+
+	octep_poll_oei_cnxk_pf(oct);
+	return IRQ_HANDLED;
+}
+
+/* Process non-ioq interrupts required to keep pf interface running.
+ * OEI_RINT is needed for control mailbox
+ * MBOX_RINT is needed for pfvf mailbox
+ */
+static void octep_poll_non_ioq_interrupts_cnxk_pf(struct octep_device *oct)
+{
+	octep_poll_pfvf_mailbox_cnxk_pf(oct);
+	octep_poll_oei_cnxk_pf(oct);
+}
+
+/* Interrupt handler for input ring error interrupts. */
+static irqreturn_t octep_ire_intr_handler_cnxk_pf(void *dev)
+{
+	struct octep_device *oct = (struct octep_device *)dev;
+	struct pci_dev *pdev = oct->pdev;
+	u64 reg_val = 0;
+	int i = 0;
+
+	/* Check for IRERR INTR */
+	reg_val = octep_read_csr64(oct, CNXK_SDP_EPF_IRERR_RINT);
+	if (reg_val) {
+		dev_info(&pdev->dev,
+			 "received IRERR_RINT intr: 0x%llx\n", reg_val);
+		octep_write_csr64(oct, CNXK_SDP_EPF_IRERR_RINT, reg_val);
+
+		for (i = 0; i < CFG_GET_PORTS_ACTIVE_IO_RINGS(oct->conf); i++) {
+			reg_val = octep_read_csr64(oct,
+						   CNXK_SDP_R_ERR_TYPE(i));
+			if (reg_val) {
+				dev_info(&pdev->dev,
+					 "Received err type on IQ-%d: 0x%llx\n",
+					 i, reg_val);
+				octep_write_csr64(oct, CNXK_SDP_R_ERR_TYPE(i),
+						  reg_val);
+			}
+		}
+	}
+	return IRQ_HANDLED;
+}
+
+/* Interrupt handler for output ring error interrupts. */
+static irqreturn_t octep_ore_intr_handler_cnxk_pf(void *dev)
+{
+	struct octep_device *oct = (struct octep_device *)dev;
+	struct pci_dev *pdev = oct->pdev;
+	u64 reg_val = 0;
+	int i = 0;
+
+	/* Check for ORERR INTR */
+	reg_val = octep_read_csr64(oct, CNXK_SDP_EPF_ORERR_RINT);
+	if (reg_val) {
+		dev_info(&pdev->dev,
+			 "Received ORERR_RINT intr: 0x%llx\n", reg_val);
+		octep_write_csr64(oct, CNXK_SDP_EPF_ORERR_RINT, reg_val);
+		for (i = 0; i < CFG_GET_PORTS_ACTIVE_IO_RINGS(oct->conf); i++) {
+			reg_val = octep_read_csr64(oct, CNXK_SDP_R_ERR_TYPE(i));
+			if (reg_val) {
+				dev_info(&pdev->dev,
+					 "Received err type on OQ-%d: 0x%llx\n",
+					 i, reg_val);
+				octep_write_csr64(oct, CNXK_SDP_R_ERR_TYPE(i),
+						  reg_val);
+			}
+		}
+	}
+	return IRQ_HANDLED;
+}
+
+/* Interrupt handler for vf input ring error interrupts. */
+static irqreturn_t octep_vfire_intr_handler_cnxk_pf(void *dev)
+{
+	struct octep_device *oct = (struct octep_device *)dev;
+	struct pci_dev *pdev = oct->pdev;
+	u64 reg_val = 0;
+
+	/* Check for VFIRE INTR */
+	reg_val = octep_read_csr64(oct, CNXK_SDP_EPF_VFIRE_RINT(0));
+	if (reg_val) {
+		dev_info(&pdev->dev,
+			 "Received VFIRE_RINT intr: 0x%llx\n", reg_val);
+		octep_write_csr64(oct, CNXK_SDP_EPF_VFIRE_RINT(0), reg_val);
+	}
+	return IRQ_HANDLED;
+}
+
+/* Interrupt handler for vf output ring error interrupts. */
+static irqreturn_t octep_vfore_intr_handler_cnxk_pf(void *dev)
+{
+	struct octep_device *oct = (struct octep_device *)dev;
+	struct pci_dev *pdev = oct->pdev;
+	u64 reg_val = 0;
+
+	/* Check for VFORE INTR */
+	reg_val = octep_read_csr64(oct, CNXK_SDP_EPF_VFORE_RINT(0));
+	if (reg_val) {
+		dev_info(&pdev->dev,
+			 "Received VFORE_RINT intr: 0x%llx\n", reg_val);
+		octep_write_csr64(oct, CNXK_SDP_EPF_VFORE_RINT(0), reg_val);
+	}
+	return IRQ_HANDLED;
+}
+
+/* Interrupt handler for dpi dma related interrupts. */
+static irqreturn_t octep_dma_intr_handler_cnxk_pf(void *dev)
+{
+	struct octep_device *oct = (struct octep_device *)dev;
+	u64 reg_val = 0;
+
+	/* Check for DMA INTR */
+	reg_val = octep_read_csr64(oct, CNXK_SDP_EPF_DMA_RINT);
+	if (reg_val)
+		octep_write_csr64(oct, CNXK_SDP_EPF_DMA_RINT, reg_val);
+
+	return IRQ_HANDLED;
+}
+
+/* Interrupt handler for dpi dma transaction error interrupts for VFs  */
+static irqreturn_t octep_dma_vf_intr_handler_cnxk_pf(void *dev)
+{
+	struct octep_device *oct = (struct octep_device *)dev;
+	struct pci_dev *pdev = oct->pdev;
+	u64 reg_val = 0;
+
+	/* Check for DMA VF INTR */
+	reg_val = octep_read_csr64(oct, CNXK_SDP_EPF_DMA_VF_RINT(0));
+	if (reg_val) {
+		dev_info(&pdev->dev,
+			 "Received DMA_VF_RINT intr: 0x%llx\n", reg_val);
+		octep_write_csr64(oct, CNXK_SDP_EPF_DMA_VF_RINT(0), reg_val);
+	}
+	return IRQ_HANDLED;
+}
+
+/* Interrupt handler for pp transaction error interrupts for VFs  */
+static irqreturn_t octep_pp_vf_intr_handler_cnxk_pf(void *dev)
+{
+	struct octep_device *oct = (struct octep_device *)dev;
+	struct pci_dev *pdev = oct->pdev;
+	u64 reg_val = 0;
+
+	/* Check for PPVF INTR */
+	reg_val = octep_read_csr64(oct, CNXK_SDP_EPF_PP_VF_RINT(0));
+	if (reg_val) {
+		dev_info(&pdev->dev,
+			 "Received PP_VF_RINT intr: 0x%llx\n", reg_val);
+		octep_write_csr64(oct, CNXK_SDP_EPF_PP_VF_RINT(0), reg_val);
+	}
+	return IRQ_HANDLED;
+}
+
+/* Interrupt handler for mac related interrupts. */
+static irqreturn_t octep_misc_intr_handler_cnxk_pf(void *dev)
+{
+	struct octep_device *oct = (struct octep_device *)dev;
+	struct pci_dev *pdev = oct->pdev;
+	u64 reg_val = 0;
+
+	/* Check for MISC INTR */
+	reg_val = octep_read_csr64(oct, CNXK_SDP_EPF_MISC_RINT);
+	if (reg_val) {
+		dev_info(&pdev->dev,
+			 "Received MISC_RINT intr: 0x%llx\n", reg_val);
+		octep_write_csr64(oct, CNXK_SDP_EPF_MISC_RINT, reg_val);
+	}
+	return IRQ_HANDLED;
+}
+
+/* Interrupts handler for all reserved interrupts. */
+static irqreturn_t octep_rsvd_intr_handler_cnxk_pf(void *dev)
+{
+	struct octep_device *oct = (struct octep_device *)dev;
+	struct pci_dev *pdev = oct->pdev;
+
+	dev_info(&pdev->dev, "Reserved interrupts raised; Ignore\n");
+	return IRQ_HANDLED;
+}
+
+/* Tx/Rx queue interrupt handler */
+static irqreturn_t octep_ioq_intr_handler_cnxk_pf(void *data)
+{
+	struct octep_ioq_vector *vector = (struct octep_ioq_vector *)data;
+	struct octep_oq *oq = vector->oq;
+
+	napi_schedule_irqoff(oq->napi);
+	return IRQ_HANDLED;
+}
+
+/* soft reset */
+static int octep_soft_reset_cnxk_pf(struct octep_device *oct)
+{
+	dev_info(&oct->pdev->dev, "CNXKXX: Doing soft reset\n");
+
+	octep_write_csr64(oct, CNXK_SDP_WIN_WR_MASK_REG, 0xFF);
+
+	/* Firmware status CSR is supposed to be cleared by
+	 * core domain reset, but due to a hw bug, it is not.
+	 * Set it to RUNNING right before reset so that it is not
+	 * left in READY (1) state after a reset.  This is required
+	 * in addition to the early setting to handle the case where
+	 * the OcteonTX is unexpectedly reset, reboots, and then
+	 * the module is removed.
+	 */
+	OCTEP_PCI_WIN_WRITE(oct, CNXK_PEMX_PFX_CSX_PFCFGX(0, 0, CNXK_PCIEEP_VSECST_CTL),
+			    FW_STATUS_RUNNING);
+
+	/* Set chip domain reset bit */
+	OCTEP_PCI_WIN_WRITE(oct, CNXK_RST_CHIP_DOMAIN_W1S, 1);
+	/* Wait till Octeon resets. */
+	mdelay(10);
+	/* restore the  reset value */
+	octep_write_csr64(oct, CNXK_SDP_WIN_WR_MASK_REG, 0xFF);
+
+	return 0;
+}
+
+/* Re-initialize Octeon hardware registers */
+static void octep_reinit_regs_cnxk_pf(struct octep_device *oct)
+{
+	u32 i;
+
+	for (i = 0; i < CFG_GET_PORTS_ACTIVE_IO_RINGS(oct->conf); i++)
+		oct->hw_ops.setup_iq_regs(oct, i);
+
+	for (i = 0; i < CFG_GET_PORTS_ACTIVE_IO_RINGS(oct->conf); i++)
+		oct->hw_ops.setup_oq_regs(oct, i);
+
+	oct->hw_ops.enable_interrupts(oct);
+	oct->hw_ops.enable_io_queues(oct);
+
+	for (i = 0; i < CFG_GET_PORTS_ACTIVE_IO_RINGS(oct->conf); i++)
+		writel(oct->oq[i]->max_count, oct->oq[i]->pkts_credit_reg);
+}
+
+/* Enable all interrupts */
+static void octep_enable_interrupts_cnxk_pf(struct octep_device *oct)
+{
+	u64 intr_mask = 0ULL;
+	int srn, num_rings, i;
+
+	srn = CFG_GET_PORTS_PF_SRN(oct->conf);
+	num_rings = CFG_GET_PORTS_ACTIVE_IO_RINGS(oct->conf);
+
+	for (i = 0; i < num_rings; i++)
+		intr_mask |= (0x1ULL << (srn + i));
+
+	octep_write_csr64(oct, CNXK_SDP_EPF_IRERR_RINT_ENA_W1S, intr_mask);
+	octep_write_csr64(oct, CNXK_SDP_EPF_ORERR_RINT_ENA_W1S, intr_mask);
+	octep_write_csr64(oct, CNXK_SDP_EPF_OEI_RINT_ENA_W1S, -1ULL);
+
+	octep_write_csr64(oct, CNXK_SDP_EPF_VFIRE_RINT_ENA_W1S(0), -1ULL);
+	octep_write_csr64(oct, CNXK_SDP_EPF_VFORE_RINT_ENA_W1S(0), -1ULL);
+
+	octep_write_csr64(oct, CNXK_SDP_EPF_MISC_RINT_ENA_W1S, intr_mask);
+	octep_write_csr64(oct, CNXK_SDP_EPF_DMA_RINT_ENA_W1S, intr_mask);
+	octep_write_csr64(oct, CNXK_SDP_EPF_MBOX_RINT_ENA_W1S(0), -1ULL);
+
+	octep_write_csr64(oct, CNXK_SDP_EPF_DMA_VF_RINT_ENA_W1S(0), -1ULL);
+	octep_write_csr64(oct, CNXK_SDP_EPF_PP_VF_RINT_ENA_W1S(0), -1ULL);
+}
+
+/* Disable all interrupts */
+static void octep_disable_interrupts_cnxk_pf(struct octep_device *oct)
+{
+	u64 intr_mask = 0ULL;
+	int srn, num_rings, i;
+
+	srn = CFG_GET_PORTS_PF_SRN(oct->conf);
+	num_rings = CFG_GET_PORTS_ACTIVE_IO_RINGS(oct->conf);
+
+	for (i = 0; i < num_rings; i++)
+		intr_mask |= (0x1ULL << (srn + i));
+
+	octep_write_csr64(oct, CNXK_SDP_EPF_IRERR_RINT_ENA_W1C, intr_mask);
+	octep_write_csr64(oct, CNXK_SDP_EPF_ORERR_RINT_ENA_W1C, intr_mask);
+	octep_write_csr64(oct, CNXK_SDP_EPF_OEI_RINT_ENA_W1C, -1ULL);
+
+	octep_write_csr64(oct, CNXK_SDP_EPF_VFIRE_RINT_ENA_W1C(0), -1ULL);
+	octep_write_csr64(oct, CNXK_SDP_EPF_VFORE_RINT_ENA_W1C(0), -1ULL);
+
+	octep_write_csr64(oct, CNXK_SDP_EPF_MISC_RINT_ENA_W1C, intr_mask);
+	octep_write_csr64(oct, CNXK_SDP_EPF_DMA_RINT_ENA_W1C, intr_mask);
+	octep_write_csr64(oct, CNXK_SDP_EPF_MBOX_RINT_ENA_W1C(0), -1ULL);
+
+	octep_write_csr64(oct, CNXK_SDP_EPF_DMA_VF_RINT_ENA_W1C(0), -1ULL);
+	octep_write_csr64(oct, CNXK_SDP_EPF_PP_VF_RINT_ENA_W1C(0), -1ULL);
+}
+
+/* Get new Octeon Read Index: index of descriptor that Octeon reads next. */
+static u32 octep_update_iq_read_index_cnxk_pf(struct octep_iq *iq)
+{
+	u32 pkt_in_done = readl(iq->inst_cnt_reg);
+	u32 last_done, new_idx;
+
+	last_done = pkt_in_done - iq->pkt_in_done;
+	iq->pkt_in_done = pkt_in_done;
+
+	new_idx = (iq->octep_read_index + last_done) % iq->max_count;
+
+	return new_idx;
+}
+
+/* Enable a hardware Tx Queue */
+static void octep_enable_iq_cnxk_pf(struct octep_device *oct, int iq_no)
+{
+	u64 loop = HZ;
+	u64 reg_val;
+
+	iq_no += CFG_GET_PORTS_PF_SRN(oct->conf);
+
+	octep_write_csr64(oct, CNXK_SDP_R_IN_INSTR_DBELL(iq_no), 0xFFFFFFFF);
+
+	while (octep_read_csr64(oct, CNXK_SDP_R_IN_INSTR_DBELL(iq_no)) &&
+	       loop--) {
+		schedule_timeout_interruptible(1);
+	}
+
+	reg_val = octep_read_csr64(oct,  CNXK_SDP_R_IN_INT_LEVELS(iq_no));
+	reg_val |= (0x1ULL << 62);
+	octep_write_csr64(oct, CNXK_SDP_R_IN_INT_LEVELS(iq_no), reg_val);
+
+	reg_val = octep_read_csr64(oct, CNXK_SDP_R_IN_ENABLE(iq_no));
+	reg_val |= 0x1ULL;
+	octep_write_csr64(oct, CNXK_SDP_R_IN_ENABLE(iq_no), reg_val);
+}
+
+/* Enable a hardware Rx Queue */
+static void octep_enable_oq_cnxk_pf(struct octep_device *oct, int oq_no)
+{
+	u64 reg_val = 0ULL;
+
+	oq_no += CFG_GET_PORTS_PF_SRN(oct->conf);
+
+	reg_val = octep_read_csr64(oct,  CNXK_SDP_R_OUT_INT_LEVELS(oq_no));
+	reg_val |= (0x1ULL << 62);
+	octep_write_csr64(oct, CNXK_SDP_R_OUT_INT_LEVELS(oq_no), reg_val);
+
+	octep_write_csr64(oct, CNXK_SDP_R_OUT_SLIST_DBELL(oq_no), 0xFFFFFFFF);
+
+	reg_val = octep_read_csr64(oct, CNXK_SDP_R_OUT_ENABLE(oq_no));
+	reg_val |= 0x1ULL;
+	octep_write_csr64(oct, CNXK_SDP_R_OUT_ENABLE(oq_no), reg_val);
+}
+
+/* Enable all hardware Tx/Rx Queues assined to PF */
+static void octep_enable_io_queues_cnxk_pf(struct octep_device *oct)
+{
+	u8 q;
+
+	for (q = 0; q < CFG_GET_PORTS_ACTIVE_IO_RINGS(oct->conf); q++) {
+		octep_enable_iq_cnxk_pf(oct, q);
+		octep_enable_oq_cnxk_pf(oct, q);
+	}
+}
+
+/* Disable a hardware Tx Queue assined to PF */
+static void octep_disable_iq_cnxk_pf(struct octep_device *oct, int iq_no)
+{
+	u64 reg_val = 0ULL;
+
+	iq_no += CFG_GET_PORTS_PF_SRN(oct->conf);
+
+	reg_val = octep_read_csr64(oct, CNXK_SDP_R_IN_ENABLE(iq_no));
+	reg_val &= ~0x1ULL;
+	octep_write_csr64(oct, CNXK_SDP_R_IN_ENABLE(iq_no), reg_val);
+}
+
+/* Disable a hardware Rx Queue assined to PF */
+static void octep_disable_oq_cnxk_pf(struct octep_device *oct, int oq_no)
+{
+	u64 reg_val = 0ULL;
+
+	oq_no += CFG_GET_PORTS_PF_SRN(oct->conf);
+	reg_val = octep_read_csr64(oct, CNXK_SDP_R_OUT_ENABLE(oq_no));
+	reg_val &= ~0x1ULL;
+	octep_write_csr64(oct, CNXK_SDP_R_OUT_ENABLE(oq_no), reg_val);
+}
+
+/* Disable all hardware Tx/Rx Queues assined to PF */
+static void octep_disable_io_queues_cnxk_pf(struct octep_device *oct)
+{
+	int q = 0;
+
+	for (q = 0; q < CFG_GET_PORTS_ACTIVE_IO_RINGS(oct->conf); q++) {
+		octep_disable_iq_cnxk_pf(oct, q);
+		octep_disable_oq_cnxk_pf(oct, q);
+	}
+}
+
+/* Dump hardware registers (including Tx/Rx queues) for debugging. */
+static void octep_dump_registers_cnxk_pf(struct octep_device *oct)
+{
+	u8 srn, num_rings, q;
+
+	srn = CFG_GET_PORTS_PF_SRN(oct->conf);
+	num_rings = CFG_GET_PORTS_ACTIVE_IO_RINGS(oct->conf);
+
+	for (q = srn; q < srn + num_rings; q++)
+		cnxk_dump_regs(oct, q);
+}
+
+/**
+ * octep_device_setup_cnxk_pf() - Setup Octeon device.
+ *
+ * @oct: Octeon device private data structure.
+ *
+ * - initialize hardware operations.
+ * - get target side pcie port number for the device.
+ * - setup window access to hardware registers.
+ * - set initial configuration and max limits.
+ * - setup hardware mapping of rings to the PF device.
+ */
+void octep_device_setup_cnxk_pf(struct octep_device *oct)
+{
+	oct->hw_ops.setup_iq_regs = octep_setup_iq_regs_cnxk_pf;
+	oct->hw_ops.setup_oq_regs = octep_setup_oq_regs_cnxk_pf;
+	oct->hw_ops.setup_mbox_regs = octep_setup_mbox_regs_cnxk_pf;
+
+	oct->hw_ops.mbox_intr_handler = octep_pfvf_mbox_intr_handler_cnxk_pf;
+	oct->hw_ops.oei_intr_handler = octep_oei_intr_handler_cnxk_pf;
+	oct->hw_ops.ire_intr_handler = octep_ire_intr_handler_cnxk_pf;
+	oct->hw_ops.ore_intr_handler = octep_ore_intr_handler_cnxk_pf;
+	oct->hw_ops.vfire_intr_handler = octep_vfire_intr_handler_cnxk_pf;
+	oct->hw_ops.vfore_intr_handler = octep_vfore_intr_handler_cnxk_pf;
+	oct->hw_ops.dma_intr_handler = octep_dma_intr_handler_cnxk_pf;
+	oct->hw_ops.dma_vf_intr_handler = octep_dma_vf_intr_handler_cnxk_pf;
+	oct->hw_ops.pp_vf_intr_handler = octep_pp_vf_intr_handler_cnxk_pf;
+	oct->hw_ops.misc_intr_handler = octep_misc_intr_handler_cnxk_pf;
+	oct->hw_ops.rsvd_intr_handler = octep_rsvd_intr_handler_cnxk_pf;
+	oct->hw_ops.ioq_intr_handler = octep_ioq_intr_handler_cnxk_pf;
+	oct->hw_ops.soft_reset = octep_soft_reset_cnxk_pf;
+	oct->hw_ops.reinit_regs = octep_reinit_regs_cnxk_pf;
+
+	oct->hw_ops.enable_interrupts = octep_enable_interrupts_cnxk_pf;
+	oct->hw_ops.disable_interrupts = octep_disable_interrupts_cnxk_pf;
+	oct->hw_ops.poll_non_ioq_interrupts = octep_poll_non_ioq_interrupts_cnxk_pf;
+
+	oct->hw_ops.update_iq_read_idx = octep_update_iq_read_index_cnxk_pf;
+
+	oct->hw_ops.enable_iq = octep_enable_iq_cnxk_pf;
+	oct->hw_ops.enable_oq = octep_enable_oq_cnxk_pf;
+	oct->hw_ops.enable_io_queues = octep_enable_io_queues_cnxk_pf;
+
+	oct->hw_ops.disable_iq = octep_disable_iq_cnxk_pf;
+	oct->hw_ops.disable_oq = octep_disable_oq_cnxk_pf;
+	oct->hw_ops.disable_io_queues = octep_disable_io_queues_cnxk_pf;
+	oct->hw_ops.reset_io_queues = octep_reset_io_queues_cnxk_pf;
+
+	oct->hw_ops.dump_registers = octep_dump_registers_cnxk_pf;
+
+	octep_setup_pci_window_regs_cnxk_pf(oct);
+
+	oct->pcie_port = octep_read_csr64(oct, CNXK_SDP_MAC_NUMBER) & 0xff;
+	dev_info(&oct->pdev->dev,
+		 "Octeon device using PCIE Port %d\n", oct->pcie_port);
+
+	octep_init_config_cnxk_pf(oct);
+	octep_configure_ring_mapping_cnxk_pf(oct);
+
+	/* Firmware status CSR is supposed to be cleared by
+	 * core domain reset, but due to IPBUPEM-38842, it is not.
+	 * Set it to RUNNING early in boot, so that unexpected resets
+	 * leave it in a state that is not READY (1).
+	 */
+	OCTEP_PCI_WIN_WRITE(oct, CNXK_PEMX_PFX_CSX_PFCFGX(0, 0, CNXK_PCIEEP_VSECST_CTL),
+			    FW_STATUS_RUNNING);
+}
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_config.h b/drivers/net/ethernet/marvell/octeon_ep/octep_config.h
index 1622a6ebf036..1627660175c2 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_config.h
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_config.h
@@ -13,12 +13,16 @@
 #define OCTEP_64BYTE_INSTR  64
 
 /* Tx Queue: maximum descriptors per ring */
+/* This needs to be a power of 2 */
 #define OCTEP_IQ_MAX_DESCRIPTORS    1024
 /* Minimum input (Tx) requests to be enqueued to ring doorbell */
-#define OCTEP_DB_MIN                1
+#define OCTEP_DB_MIN                8
 /* Packet threshold for Tx queue interrupt */
 #define OCTEP_IQ_INTR_THRESHOLD     0x0
 
+/* Minimum watermark for backpressure */
+#define OCTEP_OQ_WMARK_MIN 256
+
 /* Rx Queue: maximum descriptors per ring */
 #define OCTEP_OQ_MAX_DESCRIPTORS   1024
 
@@ -44,8 +48,6 @@
 
 /* Minimum MTU supported by Octeon network interface */
 #define OCTEP_MIN_MTU        ETH_MIN_MTU
-/* Maximum MTU supported by Octeon interface*/
-#define OCTEP_MAX_MTU        (10000 - (ETH_HLEN + ETH_FCS_LEN))
 /* Default MTU */
 #define OCTEP_DEFAULT_MTU    1500
 
@@ -58,7 +60,6 @@
 #define CFG_GET_IQ_CFG(cfg)             ((cfg)->iq)
 #define CFG_GET_IQ_NUM_DESC(cfg)        ((cfg)->iq.num_descs)
 #define CFG_GET_IQ_INSTR_TYPE(cfg)      ((cfg)->iq.instr_type)
-#define CFG_GET_IQ_PKIND(cfg)           ((cfg)->iq.pkind)
 #define CFG_GET_IQ_INSTR_SIZE(cfg)      (64)
 #define CFG_GET_IQ_DB_MIN(cfg)          ((cfg)->iq.db_min)
 #define CFG_GET_IQ_INTR_THRESHOLD(cfg)  ((cfg)->iq.intr_threshold)
@@ -68,12 +69,12 @@
 #define CFG_GET_OQ_REFILL_THRESHOLD(cfg)  ((cfg)->oq.refill_threshold)
 #define CFG_GET_OQ_INTR_PKT(cfg)          ((cfg)->oq.oq_intr_pkt)
 #define CFG_GET_OQ_INTR_TIME(cfg)         ((cfg)->oq.oq_intr_time)
+#define CFG_GET_OQ_WMARK(cfg)             ((cfg)->oq.wmark)
 
 #define CFG_GET_PORTS_MAX_IO_RINGS(cfg)    ((cfg)->pf_ring_cfg.max_io_rings)
 #define CFG_GET_PORTS_ACTIVE_IO_RINGS(cfg) ((cfg)->pf_ring_cfg.active_io_rings)
 #define CFG_GET_PORTS_PF_SRN(cfg)          ((cfg)->pf_ring_cfg.srn)
 
-#define CFG_GET_DPI_PKIND(cfg)            ((cfg)->core_cfg.dpi_pkind)
 #define CFG_GET_CORE_TICS_PER_US(cfg)     ((cfg)->core_cfg.core_tics_per_us)
 #define CFG_GET_COPROC_TICS_PER_US(cfg)   ((cfg)->core_cfg.coproc_tics_per_us)
 
@@ -97,9 +98,6 @@ struct octep_iq_config {
 	/* Command size - 32 or 64 bytes */
 	u16 instr_type;
 
-	/* pkind for packets sent to Octeon */
-	u16 pkind;
-
 	/* Minimum number of commands pending to be posted to Octeon before driver
 	 * hits the Input queue doorbell.
 	 */
@@ -137,6 +135,12 @@ struct octep_oq_config {
 	 * default. The time is specified in microseconds.
 	 */
 	u32 oq_intr_time;
+
+	/* Water mark for backpressure.
+	 * Output queue sends backpressure signal to source when
+	 * free buffer count falls below wmark.
+	 */
+	u32 wmark;
 };
 
 /* Tx/Rx configuration */
@@ -189,11 +193,37 @@ struct octep_ctrl_mbox_config {
 /* Info from firmware */
 struct octep_fw_info {
 	/* interface pkind */
-	u16 pkind;
+	u8 pkind;
+
+	/* front size data */
+	u8 fsz;
+
 	/* heartbeat interval in milliseconds */
 	u16 hb_interval;
+
 	/* heartbeat miss count */
 	u16 hb_miss_count;
+
+	/* reserved */
+	u16 reserved1;
+
+	/* supported rx offloads OCTEP_ETH_RX_OFFLOAD_* */
+	u16 rx_ol_flags;
+
+	/* supported tx offloads OCTEP_ETH_TX_OFFLOAD_* */
+	u16 tx_ol_flags;
+
+	/* reserved */
+	u32 reserved_offloads;
+
+	/* extra offload flags */
+	u64 ext_ol_flags;
+
+	/* supported features */
+	u64 features[2];
+
+	/* reserved */
+	u64 reserved2[3];
 };
 
 /* Data Structure to hold configuration limits and active config */
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.h b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.h
index 7f8135788efc..6da32d40f926 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.h
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.h
@@ -16,10 +16,12 @@
  * |reserved (4 bytes)                         |
  * |-------------------------------------------|
  * |host version (8 bytes)                     |
+ * |    low 32 bits                            |
  * |host status (8 bytes)                      |
  * |host reserved (104 bytes)                  |
  * |-------------------------------------------|
- * |fw version (8 bytes)                       |
+ * |fw version's (8 bytes)                     |
+ * |    min=high 32 bits, max=low 32 bits      |
  * |fw status (8 bytes)                        |
  * |fw reserved (104 bytes)                    |
  * |===========================================|
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.c b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.c
index 0594607a2585..01b7be154c38 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.c
@@ -13,6 +13,7 @@
 #include "octep_config.h"
 #include "octep_main.h"
 #include "octep_ctrl_net.h"
+#include "octep_pfvf_mbox.h"
 
 /* Control plane version */
 #define OCTEP_CP_VERSION_CURRENT	OCTEP_CP_VERSION(1, 0, 0)
@@ -22,12 +23,15 @@ static const u32 mtu_sz = sizeof(struct octep_ctrl_net_h2f_req_cmd_mtu);
 static const u32 mac_sz = sizeof(struct octep_ctrl_net_h2f_req_cmd_mac);
 static const u32 state_sz = sizeof(struct octep_ctrl_net_h2f_req_cmd_state);
 static const u32 link_info_sz = sizeof(struct octep_ctrl_net_link_info);
+static const u32 offloads_sz = sizeof(struct octep_ctrl_net_offloads);
 static atomic_t ctrl_net_msg_id;
 
 /* Control plane version in which OCTEP_CTRL_NET_H2F_CMD was added */
 static const u32 octep_ctrl_net_h2f_cmd_versions[OCTEP_CTRL_NET_H2F_CMD_MAX] = {
-	[OCTEP_CTRL_NET_H2F_CMD_INVALID ... OCTEP_CTRL_NET_H2F_CMD_GET_INFO] =
-	 OCTEP_CP_VERSION(1, 0, 0)
+	[OCTEP_CTRL_NET_H2F_CMD_INVALID ... OCTEP_CTRL_NET_H2F_CMD_DEV_REMOVE] =
+	 OCTEP_CP_VERSION(1, 0, 0),
+	[OCTEP_CTRL_NET_H2F_CMD_OFFLOADS] = OCTEP_CP_VERSION(1, 0, 1)
+
 };
 
 /* Control plane version in which OCTEP_CTRL_NET_F2H_CMD was added */
@@ -122,7 +126,7 @@ int octep_ctrl_net_init(struct octep_device *oct)
 
 int octep_ctrl_net_get_link_status(struct octep_device *oct, int vfid)
 {
-	struct octep_ctrl_net_wait_data d = {0};
+	struct octep_ctrl_net_wait_data d = {};
 	struct octep_ctrl_net_h2f_req *req = &d.data.req;
 	int err;
 
@@ -139,7 +143,7 @@ int octep_ctrl_net_get_link_status(struct octep_device *oct, int vfid)
 int octep_ctrl_net_set_link_status(struct octep_device *oct, int vfid, bool up,
 				   bool wait_for_response)
 {
-	struct octep_ctrl_net_wait_data d = {0};
+	struct octep_ctrl_net_wait_data d = {};
 	struct octep_ctrl_net_h2f_req *req = &d.data.req;
 
 	init_send_req(&d.msg, req, state_sz, vfid);
@@ -154,7 +158,7 @@ int octep_ctrl_net_set_link_status(struct octep_device *oct, int vfid, bool up,
 int octep_ctrl_net_set_rx_state(struct octep_device *oct, int vfid, bool up,
 				bool wait_for_response)
 {
-	struct octep_ctrl_net_wait_data d = {0};
+	struct octep_ctrl_net_wait_data d = {};
 	struct octep_ctrl_net_h2f_req *req = &d.data.req;
 
 	init_send_req(&d.msg, req, state_sz, vfid);
@@ -168,7 +172,7 @@ int octep_ctrl_net_set_rx_state(struct octep_device *oct, int vfid, bool up,
 
 int octep_ctrl_net_get_mac_addr(struct octep_device *oct, int vfid, u8 *addr)
 {
-	struct octep_ctrl_net_wait_data d = {0};
+	struct octep_ctrl_net_wait_data d = {};
 	struct octep_ctrl_net_h2f_req *req = &d.data.req;
 	int err;
 
@@ -187,7 +191,7 @@ int octep_ctrl_net_get_mac_addr(struct octep_device *oct, int vfid, u8 *addr)
 int octep_ctrl_net_set_mac_addr(struct octep_device *oct, int vfid, u8 *addr,
 				bool wait_for_response)
 {
-	struct octep_ctrl_net_wait_data d = {0};
+	struct octep_ctrl_net_wait_data d = {};
 	struct octep_ctrl_net_h2f_req *req = &d.data.req;
 
 	init_send_req(&d.msg, req, mac_sz, vfid);
@@ -198,10 +202,28 @@ int octep_ctrl_net_set_mac_addr(struct octep_device *oct, int vfid, u8 *addr,
 	return octep_send_mbox_req(oct, &d, wait_for_response);
 }
 
+int octep_ctrl_net_get_mtu(struct octep_device *oct, int vfid)
+{
+	struct octep_ctrl_net_wait_data d = {};
+	struct octep_ctrl_net_h2f_req *req;
+	int err;
+
+	req = &d.data.req;
+	init_send_req(&d.msg, req, mtu_sz, vfid);
+	req->hdr.s.cmd = OCTEP_CTRL_NET_H2F_CMD_MTU;
+	req->mtu.cmd = OCTEP_CTRL_NET_CMD_GET;
+
+	err = octep_send_mbox_req(oct, &d, true);
+	if (err < 0)
+		return err;
+
+	return d.data.resp.mtu.val;
+}
+
 int octep_ctrl_net_set_mtu(struct octep_device *oct, int vfid, int mtu,
 			   bool wait_for_response)
 {
-	struct octep_ctrl_net_wait_data d = {0};
+	struct octep_ctrl_net_wait_data d = {};
 	struct octep_ctrl_net_h2f_req *req = &d.data.req;
 
 	init_send_req(&d.msg, req, mtu_sz, vfid);
@@ -216,7 +238,7 @@ int octep_ctrl_net_get_if_stats(struct octep_device *oct, int vfid,
 				struct octep_iface_rx_stats *rx_stats,
 				struct octep_iface_tx_stats *tx_stats)
 {
-	struct octep_ctrl_net_wait_data d = {0};
+	struct octep_ctrl_net_wait_data d = {};
 	struct octep_ctrl_net_h2f_req *req = &d.data.req;
 	struct octep_ctrl_net_h2f_resp *resp;
 	int err;
@@ -236,7 +258,7 @@ int octep_ctrl_net_get_if_stats(struct octep_device *oct, int vfid,
 int octep_ctrl_net_get_link_info(struct octep_device *oct, int vfid,
 				 struct octep_iface_link_info *link_info)
 {
-	struct octep_ctrl_net_wait_data d = {0};
+	struct octep_ctrl_net_wait_data d = {};
 	struct octep_ctrl_net_h2f_req *req = &d.data.req;
 	struct octep_ctrl_net_h2f_resp *resp;
 	int err;
@@ -262,7 +284,7 @@ int octep_ctrl_net_set_link_info(struct octep_device *oct, int vfid,
 				 struct octep_iface_link_info *link_info,
 				 bool wait_for_response)
 {
-	struct octep_ctrl_net_wait_data d = {0};
+	struct octep_ctrl_net_wait_data d = {};
 	struct octep_ctrl_net_h2f_req *req = &d.data.req;
 
 	init_send_req(&d.msg, req, link_info_sz, vfid);
@@ -308,6 +330,11 @@ static int process_mbox_notify(struct octep_device *oct,
 	    octep_ctrl_net_f2h_cmd_versions[cmd] < OCTEP_CP_VERSION_CURRENT)
 		return -EOPNOTSUPP;
 
+	if (msg->hdr.s.is_vf) {
+		octep_pfvf_notify(oct, msg);
+		return 0;
+	}
+
 	switch (cmd) {
 	case OCTEP_CTRL_NET_F2H_CMD_LINK_STATUS:
 		if (netif_running(netdev)) {
@@ -331,8 +358,8 @@ static int process_mbox_notify(struct octep_device *oct,
 void octep_ctrl_net_recv_fw_messages(struct octep_device *oct)
 {
 	static u16 msg_sz = sizeof(union octep_ctrl_net_max_data);
-	union octep_ctrl_net_max_data data = {0};
-	struct octep_ctrl_mbox_msg msg = {0};
+	union octep_ctrl_net_max_data data = {};
+	struct octep_ctrl_mbox_msg msg = {};
 	int ret;
 
 	msg.hdr.s.sz = msg_sz;
@@ -356,7 +383,7 @@ void octep_ctrl_net_recv_fw_messages(struct octep_device *oct)
 int octep_ctrl_net_get_info(struct octep_device *oct, int vfid,
 			    struct octep_fw_info *info)
 {
-	struct octep_ctrl_net_wait_data d = {0};
+	struct octep_ctrl_net_wait_data d = {};
 	struct octep_ctrl_net_h2f_resp *resp;
 	struct octep_ctrl_net_h2f_req *req;
 	int err;
@@ -375,10 +402,41 @@ int octep_ctrl_net_get_info(struct octep_device *oct, int vfid,
 	return 0;
 }
 
+int octep_ctrl_net_dev_remove(struct octep_device *oct, int vfid)
+{
+	struct octep_ctrl_net_wait_data d = {};
+	struct octep_ctrl_net_h2f_req *req;
+
+	req = &d.data.req;
+	dev_dbg(&oct->pdev->dev, "Sending dev_unload msg to fw\n");
+	init_send_req(&d.msg, req, sizeof(int), vfid);
+	req->hdr.s.cmd = OCTEP_CTRL_NET_H2F_CMD_DEV_REMOVE;
+
+	return octep_send_mbox_req(oct, &d, false);
+}
+
+int octep_ctrl_net_set_offloads(struct octep_device *oct, int vfid,
+				struct octep_ctrl_net_offloads *offloads,
+				bool wait_for_response)
+{
+	struct octep_ctrl_net_wait_data d = {};
+	struct octep_ctrl_net_h2f_req *req;
+
+	req = &d.data.req;
+	init_send_req(&d.msg, req, offloads_sz, vfid);
+	req->hdr.s.cmd = OCTEP_CTRL_NET_H2F_CMD_OFFLOADS;
+	req->offloads.cmd = OCTEP_CTRL_NET_CMD_SET;
+	req->offloads.offloads = *offloads;
+
+	return octep_send_mbox_req(oct, &d, wait_for_response);
+}
+
 int octep_ctrl_net_uninit(struct octep_device *oct)
 {
 	struct octep_ctrl_net_wait_data *pos, *n;
 
+	octep_ctrl_net_dev_remove(oct, OCTEP_CTRL_NET_INVALID_VFID);
+
 	list_for_each_entry_safe(pos, n, &oct->ctrl_req_wait_list, list)
 		pos->done = 1;
 
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.h b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.h
index b330f370131b..0b823bea9cd8 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.h
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_net.h
@@ -42,6 +42,8 @@ enum octep_ctrl_net_h2f_cmd {
 	OCTEP_CTRL_NET_H2F_CMD_RX_STATE,
 	OCTEP_CTRL_NET_H2F_CMD_LINK_INFO,
 	OCTEP_CTRL_NET_H2F_CMD_GET_INFO,
+	OCTEP_CTRL_NET_H2F_CMD_DEV_REMOVE,
+	OCTEP_CTRL_NET_H2F_CMD_OFFLOADS,
 	OCTEP_CTRL_NET_H2F_CMD_MAX
 };
 
@@ -112,6 +114,26 @@ struct octep_ctrl_net_h2f_req_cmd_link_info {
 	struct octep_ctrl_net_link_info info;
 };
 
+/* offloads */
+struct octep_ctrl_net_offloads {
+	/* supported rx offloads OCTEP_RX_OFFLOAD_* */
+	u16 rx_offloads;
+	/* supported tx offloads OCTEP_TX_OFFLOAD_* */
+	u16 tx_offloads;
+	/* reserved */
+	u32 reserved_offloads;
+	/* extra offloads */
+	u64 ext_offloads;
+};
+
+/* get/set offloads */
+struct octep_ctrl_net_h2f_req_cmd_offloads {
+	/* enum octep_ctrl_net_cmd */
+	u16 cmd;
+	/* struct octep_ctrl_net_offloads */
+	struct octep_ctrl_net_offloads offloads;
+};
+
 /* Host to fw request data */
 struct octep_ctrl_net_h2f_req {
 	union octep_ctrl_net_req_hdr hdr;
@@ -121,6 +143,7 @@ struct octep_ctrl_net_h2f_req {
 		struct octep_ctrl_net_h2f_req_cmd_state link;
 		struct octep_ctrl_net_h2f_req_cmd_state rx;
 		struct octep_ctrl_net_h2f_req_cmd_link_info link_info;
+		struct octep_ctrl_net_h2f_req_cmd_offloads offloads;
 	};
 } __packed;
 
@@ -178,6 +201,7 @@ struct octep_ctrl_net_h2f_resp {
 		struct octep_ctrl_net_h2f_resp_cmd_state rx;
 		struct octep_ctrl_net_link_info link_info;
 		struct octep_ctrl_net_h2f_resp_cmd_get_info info;
+		struct octep_ctrl_net_offloads offloads;
 	};
 } __packed;
 
@@ -218,87 +242,105 @@ struct octep_ctrl_net_wait_data {
 	} data;
 };
 
-/** Initialize data for ctrl net.
+/**
+ * octep_ctrl_net_init() - Initialize data for ctrl net.
  *
- * @param oct: non-null pointer to struct octep_device.
+ * @oct: non-null pointer to struct octep_device.
  *
  * return value: 0 on success, -errno on error.
  */
 int octep_ctrl_net_init(struct octep_device *oct);
 
-/** Get link status from firmware.
+/** 
+ * octep_ctrl_net_get_link_status() - Get link status from firmware.
  *
- * @param oct: non-null pointer to struct octep_device.
- * @param vfid: Index of virtual function.
+ * @oct: non-null pointer to struct octep_device.
+ * @vfid: Index of virtual function.
  *
  * return value: link status 0=down, 1=up.
  */
 int octep_ctrl_net_get_link_status(struct octep_device *oct, int vfid);
 
-/** Set link status in firmware.
+/**
+ * octep_ctrl_net_set_link_status() - Set link status in firmware.
  *
- * @param oct: non-null pointer to struct octep_device.
- * @param vfid: Index of virtual function.
- * @param up: boolean status.
- * @param wait_for_response: poll for response.
+ * @oct: non-null pointer to struct octep_device.
+ * @vfid: Index of virtual function.
+ * @up: boolean status.
+ * @wait_for_response: poll for response.
  *
  * return value: 0 on success, -errno on failure
  */
 int octep_ctrl_net_set_link_status(struct octep_device *oct, int vfid, bool up,
 				   bool wait_for_response);
 
-/** Set rx state in firmware.
+/**
+ * octep_ctrl_net_set_rx_state() - Set rx state in firmware.
  *
- * @param oct: non-null pointer to struct octep_device.
- * @param vfid: Index of virtual function.
- * @param up: boolean status.
- * @param wait_for_response: poll for response.
+ * @oct: non-null pointer to struct octep_device.
+ * @vfid: Index of virtual function.
+ * @up: boolean status.
+ * @wait_for_response: poll for response.
  *
  * return value: 0 on success, -errno on failure.
  */
 int octep_ctrl_net_set_rx_state(struct octep_device *oct, int vfid, bool up,
 				bool wait_for_response);
 
-/** Get mac address from firmware.
+/** 
+ * octep_ctrl_net_get_mac_addr() - Get mac address from firmware.
  *
- * @param oct: non-null pointer to struct octep_device.
- * @param vfid: Index of virtual function.
- * @param addr: non-null pointer to mac address.
+ * @oct: non-null pointer to struct octep_device.
+ * @vfid: Index of virtual function.
+ * @addr: non-null pointer to mac address.
  *
  * return value: 0 on success, -errno on failure.
  */
 int octep_ctrl_net_get_mac_addr(struct octep_device *oct, int vfid, u8 *addr);
 
-/** Set mac address in firmware.
+/**
+ * octep_ctrl_net_set_mac_addr() - Set mac address in firmware.
  *
- * @param oct: non-null pointer to struct octep_device.
- * @param vfid: Index of virtual function.
- * @param addr: non-null pointer to mac address.
- * @param wait_for_response: poll for response.
+ * @oct: non-null pointer to struct octep_device.
+ * @vfid: Index of virtual function.
+ * @addr: non-null pointer to mac address.
+ * @wait_for_response: poll for response.
  *
  * return value: 0 on success, -errno on failure.
  */
 int octep_ctrl_net_set_mac_addr(struct octep_device *oct, int vfid, u8 *addr,
 				bool wait_for_response);
 
-/** Set mtu in firmware.
+/**
+ * octep_ctrl_net_get_mtu() - Get max MTU from firmware.
  *
- * @param oct: non-null pointer to struct octep_device.
- * @param vfid: Index of virtual function.
- * @param mtu: mtu.
- * @param wait_for_response: poll for response.
+ * @oct: non-null pointer to struct octep_device.
+ * @vfid: Index of virtual function.
+ *
+ * return value: mtu on success, -errno on failure.
+ */
+int octep_ctrl_net_get_mtu(struct octep_device *oct, int vfid);
+
+/** 
+ * octep_ctrl_net_set_mtu() - Set mtu in firmware.
+ *
+ * @oct: non-null pointer to struct octep_device.
+ * @vfid: Index of virtual function.
+ * @mtu: mtu.
+ * @wait_for_response: poll for response.
  *
  * return value: 0 on success, -errno on failure.
  */
 int octep_ctrl_net_set_mtu(struct octep_device *oct, int vfid, int mtu,
 			   bool wait_for_response);
 
-/** Get interface statistics from firmware.
+/**
+ * octep_ctrl_net_get_if_stats() - Get interface statistics from firmware.
  *
- * @param oct: non-null pointer to struct octep_device.
- * @param vfid: Index of virtual function.
- * @param rx_stats: non-null pointer struct octep_iface_rx_stats.
- * @param tx_stats: non-null pointer struct octep_iface_tx_stats.
+ * @oct: non-null pointer to struct octep_device.
+ * @vfid: Index of virtual function.
+ * @rx_stats: non-null pointer struct octep_iface_rx_stats.
+ * @tx_stats: non-null pointer struct octep_iface_tx_stats.
  *
  * return value: 0 on success, -errno on failure.
  */
@@ -306,23 +348,25 @@ int octep_ctrl_net_get_if_stats(struct octep_device *oct, int vfid,
 				struct octep_iface_rx_stats *rx_stats,
 				struct octep_iface_tx_stats *tx_stats);
 
-/** Get link info from firmware.
+/**
+ * octep_ctrl_net_get_link_info() - Get link info from firmware.
  *
- * @param oct: non-null pointer to struct octep_device.
- * @param vfid: Index of virtual function.
- * @param link_info: non-null pointer to struct octep_iface_link_info.
+ * @oct: non-null pointer to struct octep_device.
+ * @vfid: Index of virtual function.
+ * @link_info: non-null pointer to struct octep_iface_link_info.
  *
  * return value: 0 on success, -errno on failure.
  */
 int octep_ctrl_net_get_link_info(struct octep_device *oct, int vfid,
 				 struct octep_iface_link_info *link_info);
 
-/** Set link info in firmware.
+/**
+ * octep_ctrl_net_set_link_info() - Set link info in firmware.
  *
- * @param oct: non-null pointer to struct octep_device.
- * @param vfid: Index of virtual function.
- * @param link_info: non-null pointer to struct octep_iface_link_info.
- * @param wait_for_response: poll for response.
+ * @oct: non-null pointer to struct octep_device.
+ * @vfid: Index of virtual function.
+ * @link_info: non-null pointer to struct octep_iface_link_info.
+ * @wait_for_response: poll for response.
  *
  * return value: 0 on success, -errno on failure.
  */
@@ -331,26 +375,53 @@ int octep_ctrl_net_set_link_info(struct octep_device *oct,
 				 struct octep_iface_link_info *link_info,
 				 bool wait_for_response);
 
-/** Poll for firmware messages and process them.
+/**
+ * octep_ctrl_net_recv_fw_messages() - Poll for firmware messages and process them.
  *
- * @param oct: non-null pointer to struct octep_device.
+ * @oct: non-null pointer to struct octep_device.
  */
 void octep_ctrl_net_recv_fw_messages(struct octep_device *oct);
 
-/** Get info from firmware.
+/**
+ * octep_ctrl_net_get_info() - Get info from firmware.
  *
- * @param oct: non-null pointer to struct octep_device.
- * @param vfid: Index of virtual function.
- * @param info: non-null pointer to struct octep_fw_info.
+ * @oct: non-null pointer to struct octep_device.
+ * @vfid: Index of virtual function.
+ * @info: non-null pointer to struct octep_fw_info.
  *
  * return value: 0 on success, -errno on failure.
  */
 int octep_ctrl_net_get_info(struct octep_device *oct, int vfid,
 			    struct octep_fw_info *info);
 
-/** Uninitialize data for ctrl net.
+/**
+ * octep_ctrl_net_dev_remove() - Indicate to firmware that a device unload has happened.
+ *
+ * @oct: non-null pointer to struct octep_device.
+ * @vfid: Index of virtual function.
+ *
+ * return value: 0 on success, -errno on failure.
+ */
+int octep_ctrl_net_dev_remove(struct octep_device *oct, int vfid);
+
+/**
+ * octep_ctrl_net_set_offloads() - Set offloads in firmware.
+ *
+ * @oct: non-null pointer to struct octep_device.
+ * @vfid: Index of virtual function.
+ * @offloads: non-null pointer to struct octep_ctrl_net_offloads.
+ * @wait_for_response: poll for response.
+ *
+ * return value: 0 on success, -errno on failure.
+ */
+int octep_ctrl_net_set_offloads(struct octep_device *oct, int vfid,
+				struct octep_ctrl_net_offloads *offloads,
+				bool wait_for_response);
+
+/**
+ * octep_ctrl_net_uninit() - Uninitialize data for ctrl net.
  *
- * @param oct: non-null pointer to struct octep_device.
+ * @oct: non-null pointer to struct octep_device.
  *
  * return value: 0 on success, -errno on error.
  */
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
index 552970c7dec0..7c9faa714a10 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
@@ -16,14 +16,20 @@
 #include "octep_config.h"
 #include "octep_main.h"
 #include "octep_ctrl_net.h"
+#include "octep_pfvf_mbox.h"
 
 #define OCTEP_INTR_POLL_TIME_MSECS    100
 struct workqueue_struct *octep_wq;
 
 /* Supported Devices */
 static const struct pci_device_id octep_pci_id_tbl[] = {
+	{PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, OCTEP_PCI_DEVICE_ID_CN98_PF)},
 	{PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, OCTEP_PCI_DEVICE_ID_CN93_PF)},
 	{PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, OCTEP_PCI_DEVICE_ID_CNF95N_PF)},
+	{PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, OCTEP_PCI_DEVICE_ID_CN10KA_PF)},
+	{PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, OCTEP_PCI_DEVICE_ID_CNF10KA_PF)},
+	{PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, OCTEP_PCI_DEVICE_ID_CNF10KB_PF)},
+	{PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, OCTEP_PCI_DEVICE_ID_CN10KB_PF)},
 	{0, },
 };
 MODULE_DEVICE_TABLE(pci, octep_pci_id_tbl);
@@ -155,6 +161,21 @@ static void octep_disable_msix(struct octep_device *oct)
 }
 
 /**
+ * octep_mbox_intr_handler() - common handler for pfvf mbox interrupts.
+ *
+ * @irq: Interrupt number.
+ * @data: interrupt data.
+ *
+ * this is common handler for pfvf mbox interrupts.
+ */
+static irqreturn_t octep_mbox_intr_handler(int irq, void *data)
+{
+	struct octep_device *oct = data;
+
+	return oct->hw_ops.mbox_intr_handler(oct);
+}
+
+/**
  * octep_oei_intr_handler() - common handler for output endpoint interrupts.
  *
  * @irq: Interrupt number.
@@ -357,8 +378,12 @@ static int octep_request_irqs(struct octep_device *oct)
 
 		snprintf(irq_name, OCTEP_MSIX_NAME_SIZE,
 			 "%s-%s", netdev->name, non_ioq_msix_names[i]);
-		if (!strncmp(non_ioq_msix_names[i], "epf_oei_rint",
-			     strlen("epf_oei_rint"))) {
+		if (!strncmp(non_ioq_msix_names[i], "epf_mbox_rint", strlen("epf_mbox_rint"))) {
+			ret = request_irq(msix_entry->vector,
+					  octep_mbox_intr_handler, 0,
+					  irq_name, oct);
+		} else if (!strncmp(non_ioq_msix_names[i], "epf_oei_rint",
+			   strlen("epf_oei_rint"))) {
 			ret = request_irq(msix_entry->vector,
 					  octep_oei_intr_handler, 0,
 					  irq_name, oct);
@@ -777,17 +802,24 @@ static int octep_stop(struct net_device *netdev)
  */
 static inline int octep_iq_full_check(struct octep_iq *iq)
 {
-	if (likely((iq->max_count - atomic_read(&iq->instr_pending)) >=
+	if (likely((IQ_INSTR_SPACE(iq)) >
 		   OCTEP_WAKE_QUEUE_THRESHOLD))
 		return 0;
 
 	/* Stop the queue if unable to send */
 	netif_stop_subqueue(iq->netdev, iq->q_no);
 
+	/* Allow for pending updates in write index
+	 * from iq_process_completion in other cpus
+	 * to reflect, in case queue gets free
+	 * entries.
+	 */
+	smp_mb();
+
 	/* check again and restart the queue, in case NAPI has just freed
 	 * enough Tx ring entries.
 	 */
-	if (unlikely((iq->max_count - atomic_read(&iq->instr_pending)) >=
+	if (unlikely(IQ_INSTR_SPACE(iq) >
 		     OCTEP_WAKE_QUEUE_THRESHOLD)) {
 		netif_start_subqueue(iq->netdev, iq->q_no);
 		iq->stats.restart_cnt++;
@@ -810,6 +842,7 @@ static netdev_tx_t octep_start_xmit(struct sk_buff *skb,
 				    struct net_device *netdev)
 {
 	struct octep_device *oct = netdev_priv(netdev);
+	netdev_features_t feat  = netdev->features;
 	struct octep_tx_sglist_desc *sglist;
 	struct octep_tx_buffer *tx_buffer;
 	struct octep_tx_desc_hw *hw_desc;
@@ -818,8 +851,12 @@ static netdev_tx_t octep_start_xmit(struct sk_buff *skb,
 	struct octep_iq *iq;
 	skb_frag_t *frag;
 	u16 nr_frags, si;
+	int xmit_more;
 	u16 q_no, wi;
 
+	if (skb_put_padto(skb, ETH_ZLEN))
+		return NETDEV_TX_OK;
+
 	q_no = skb_get_queue_mapping(skb);
 	if (q_no >= oct->num_iqs) {
 		netdev_err(netdev, "Invalid Tx skb->queue_mapping=%d\n", q_no);
@@ -827,10 +864,6 @@ static netdev_tx_t octep_start_xmit(struct sk_buff *skb,
 	}
 
 	iq = oct->iq[q_no];
-	if (octep_iq_full_check(iq)) {
-		iq->stats.tx_busy++;
-		return NETDEV_TX_BUSY;
-	}
 
 	shinfo = skb_shinfo(skb);
 	nr_frags = shinfo->nr_frags;
@@ -843,8 +876,9 @@ static netdev_tx_t octep_start_xmit(struct sk_buff *skb,
 	tx_buffer->skb = skb;
 
 	ih = &hw_desc->ih;
-	ih->tlen = skb->len;
-	ih->pkind = oct->pkind;
+	ih->pkind = oct->conf->fw_info.pkind;
+	ih->fsz = oct->conf->fw_info.fsz;
+	ih->tlen = skb->len + ih->fsz;
 
 	if (!nr_frags) {
 		tx_buffer->gather = 0;
@@ -869,9 +903,6 @@ static netdev_tx_t octep_start_xmit(struct sk_buff *skb,
 		if (dma_mapping_error(iq->dev, dma))
 			goto dma_map_err;
 
-		dma_sync_single_for_cpu(iq->dev, tx_buffer->sglist_dma,
-					OCTEP_SGLIST_SIZE_PER_PKT,
-					DMA_TO_DEVICE);
 		memset(sglist, 0, OCTEP_SGLIST_SIZE_PER_PKT);
 		sglist[0].len[3] = len;
 		sglist[0].dma_ptr[0] = dma;
@@ -891,26 +922,46 @@ static netdev_tx_t octep_start_xmit(struct sk_buff *skb,
 			frag++;
 			si++;
 		}
-		dma_sync_single_for_device(iq->dev, tx_buffer->sglist_dma,
-					   OCTEP_SGLIST_SIZE_PER_PKT,
-					   DMA_TO_DEVICE);
-
 		hw_desc->dptr = tx_buffer->sglist_dma;
 	}
 
-	netdev_tx_sent_queue(iq->netdev_q, skb->len);
+	if (oct->conf->fw_info.tx_ol_flags) {
+		if ((feat & (NETIF_F_TSO)) && (skb_is_gso(skb))) {
+			hw_desc->txm.ol_flags = OCTEP_TX_OFFLOAD_CKSUM;
+			hw_desc->txm.ol_flags |= OCTEP_TX_OFFLOAD_TSO;
+			hw_desc->txm.gso_size =  skb_shinfo(skb)->gso_size;
+			hw_desc->txm.gso_segs =  skb_shinfo(skb)->gso_segs;
+		} else if (feat & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) {
+			hw_desc->txm.ol_flags = OCTEP_TX_OFFLOAD_CKSUM;
+		}
+		/* due to ESR txm will be swapped by hw */
+		hw_desc->txm64[0] = (__force u64)cpu_to_be64(hw_desc->txm64[0]);
+	}
+
+	xmit_more = netdev_xmit_more();
+
+	__netdev_tx_sent_queue(iq->netdev_q, skb->len, xmit_more);
+
 	skb_tx_timestamp(skb);
-	atomic_inc(&iq->instr_pending);
+	iq->fill_cnt++;
 	wi++;
-	if (wi == iq->max_count)
-		wi = 0;
-	iq->host_write_index = wi;
+	iq->host_write_index = wi & iq->ring_size_mask;
+
+	/* octep_iq_full_check stops the queue and returns
+	 * true if so, in case the queue has become full
+	 * by inserting current packet. If so, we can
+	 * go ahead and ring doorbell.
+	 */
+	if (!octep_iq_full_check(iq) && xmit_more &&
+	    iq->fill_cnt < iq->fill_threshold)
+		return NETDEV_TX_OK;
+
 	/* Flush the hw descriptor before writing to doorbell */
 	wmb();
-
-	/* Ring Doorbell to notify the NIC there is a new packet */
-	writel(1, iq->doorbell_reg);
-	iq->stats.instr_posted++;
+	/* Ring Doorbell to notify the NIC of new packets */
+	writel(iq->fill_cnt, iq->doorbell_reg);
+	iq->stats.instr_posted += iq->fill_cnt;
+	iq->fill_cnt = 0;
 	return NETDEV_TX_OK;
 
 dma_map_sg_err:
@@ -1051,6 +1102,41 @@ static int octep_change_mtu(struct net_device *netdev, int new_mtu)
 	return err;
 }
 
+static int octep_set_features(struct net_device *dev, netdev_features_t features)
+{
+	struct octep_ctrl_net_offloads offloads = { 0 };
+	struct octep_device *oct = netdev_priv(dev);
+	int err;
+
+	/* We only support features received from firmware */
+	if ((features & dev->hw_features) != features)
+		return -EINVAL;
+
+	if (features & NETIF_F_TSO)
+		offloads.tx_offloads |= OCTEP_TX_OFFLOAD_TSO;
+
+	if (features & NETIF_F_TSO6)
+		offloads.tx_offloads |= OCTEP_TX_OFFLOAD_TSO;
+
+	if (features & NETIF_F_IP_CSUM)
+		offloads.tx_offloads |= OCTEP_TX_OFFLOAD_CKSUM;
+
+	if (features & NETIF_F_IPV6_CSUM)
+		offloads.tx_offloads |= OCTEP_TX_OFFLOAD_CKSUM;
+
+	if (features & NETIF_F_RXCSUM)
+		offloads.rx_offloads |= OCTEP_RX_OFFLOAD_CKSUM;
+
+	err = octep_ctrl_net_set_offloads(oct,
+					  OCTEP_CTRL_NET_INVALID_VFID,
+					  &offloads,
+					  true);
+	if (!err)
+		dev->features = features;
+
+	return err;
+}
+
 static const struct net_device_ops octep_netdev_ops = {
 	.ndo_open                = octep_open,
 	.ndo_stop                = octep_stop,
@@ -1059,6 +1145,7 @@ static const struct net_device_ops octep_netdev_ops = {
 	.ndo_tx_timeout          = octep_tx_timeout,
 	.ndo_set_mac_address     = octep_set_mac,
 	.ndo_change_mtu          = octep_change_mtu,
+	.ndo_set_features        = octep_set_features,
 };
 
 /**
@@ -1132,10 +1219,20 @@ static void octep_ctrl_mbox_task(struct work_struct *work)
 static const char *octep_devid_to_str(struct octep_device *oct)
 {
 	switch (oct->chip_id) {
+	case OCTEP_PCI_DEVICE_ID_CN98_PF:
+		return "CN98XX";
 	case OCTEP_PCI_DEVICE_ID_CN93_PF:
 		return "CN93XX";
 	case OCTEP_PCI_DEVICE_ID_CNF95N_PF:
 		return "CNF95N";
+	case OCTEP_PCI_DEVICE_ID_CN10KA_PF:
+		return "CN10KA";
+	case OCTEP_PCI_DEVICE_ID_CNF10KA_PF:
+		return "CNF10KA";
+	case OCTEP_PCI_DEVICE_ID_CNF10KB_PF:
+		return "CNF10KB";
+	case OCTEP_PCI_DEVICE_ID_CN10KB_PF:
+		return "CN10KB";
 	default:
 		return "Unsupported";
 	}
@@ -1174,6 +1271,7 @@ int octep_device_setup(struct octep_device *oct)
 	dev_info(&pdev->dev, "chip_id = 0x%x\n", pdev->device);
 
 	switch (oct->chip_id) {
+	case OCTEP_PCI_DEVICE_ID_CN98_PF:
 	case OCTEP_PCI_DEVICE_ID_CN93_PF:
 	case OCTEP_PCI_DEVICE_ID_CNF95N_PF:
 		dev_info(&pdev->dev, "Setting up OCTEON %s PF PASS%d.%d\n",
@@ -1181,18 +1279,32 @@ int octep_device_setup(struct octep_device *oct)
 			 OCTEP_MINOR_REV(oct));
 		octep_device_setup_cn93_pf(oct);
 		break;
+	case OCTEP_PCI_DEVICE_ID_CNF10KA_PF:
+	case OCTEP_PCI_DEVICE_ID_CN10KA_PF:
+	case OCTEP_PCI_DEVICE_ID_CNF10KB_PF:
+	case OCTEP_PCI_DEVICE_ID_CN10KB_PF:
+		dev_info(&pdev->dev, "Setting up OCTEON %s PF PASS%d.%d\n",
+			 octep_devid_to_str(oct), OCTEP_MAJOR_REV(oct), OCTEP_MINOR_REV(oct));
+		octep_device_setup_cnxk_pf(oct);
+		break;
 	default:
 		dev_err(&pdev->dev,
 			"%s: unsupported device\n", __func__);
 		goto unsupported_dev;
 	}
 
-	oct->pkind = CFG_GET_IQ_PKIND(oct->conf);
 
 	ret = octep_ctrl_net_init(oct);
 	if (ret)
 		return ret;
 
+	INIT_WORK(&oct->tx_timeout_task, octep_tx_timeout_task);
+	INIT_WORK(&oct->ctrl_mbox_task, octep_ctrl_mbox_task);
+	INIT_DELAYED_WORK(&oct->intr_poll_task, octep_intr_poll_task);
+	oct->poll_non_ioq_intr = true;
+	queue_delayed_work(octep_wq, &oct->intr_poll_task,
+			   msecs_to_jiffies(OCTEP_INTR_POLL_TIME_MSECS));
+
 	atomic_set(&oct->hb_miss_cnt, 0);
 	INIT_DELAYED_WORK(&oct->hb_task, octep_hb_timeout_task);
 
@@ -1230,6 +1342,7 @@ static void octep_device_cleanup(struct octep_device *oct)
 		oct->mbox[i] = NULL;
 	}
 
+	octep_delete_pfvf_mbox(oct);
 	octep_ctrl_net_uninit(oct);
 	cancel_delayed_work_sync(&oct->hb_task);
 
@@ -1258,7 +1371,8 @@ static bool get_fw_ready_status(struct pci_dev *pdev)
 
 		pci_read_config_byte(pdev, (pos + 8), &status);
 		dev_info(&pdev->dev, "Firmware ready status = %u\n", status);
-		return status;
+#define FW_STATUS_READY 1ULL
+		return status == FW_STATUS_READY;
 	}
 	return false;
 }
@@ -1276,6 +1390,7 @@ static int octep_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct octep_device *octep_dev = NULL;
 	struct net_device *netdev;
+	int max_rx_pktlen;
 	int err;
 
 	err = pci_enable_device(pdev);
@@ -1325,31 +1440,52 @@ static int octep_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_octep_config;
 	}
 
-	octep_ctrl_net_get_info(octep_dev, OCTEP_CTRL_NET_INVALID_VFID,
-				&octep_dev->conf->fw_info);
+	err = octep_setup_pfvf_mbox(octep_dev);
+	if (err) {
+		dev_err(&pdev->dev, "PF-VF mailbox setup failed\n");
+		goto register_dev_err;
+	}
+
+	err = octep_ctrl_net_get_info(octep_dev, OCTEP_CTRL_NET_INVALID_VFID,
+				      &octep_dev->conf->fw_info);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to get firmware info\n");
+		goto register_dev_err;
+	}
 	dev_info(&octep_dev->pdev->dev, "Heartbeat interval %u msecs Heartbeat miss count %u\n",
 		 octep_dev->conf->fw_info.hb_interval,
 		 octep_dev->conf->fw_info.hb_miss_count);
 	queue_delayed_work(octep_wq, &octep_dev->hb_task,
 			   msecs_to_jiffies(octep_dev->conf->fw_info.hb_interval));
 
-	INIT_WORK(&octep_dev->tx_timeout_task, octep_tx_timeout_task);
-	INIT_WORK(&octep_dev->ctrl_mbox_task, octep_ctrl_mbox_task);
-	INIT_DELAYED_WORK(&octep_dev->intr_poll_task, octep_intr_poll_task);
-	octep_dev->poll_non_ioq_intr = true;
-	queue_delayed_work(octep_wq, &octep_dev->intr_poll_task,
-			   msecs_to_jiffies(OCTEP_INTR_POLL_TIME_MSECS));
-
 	netdev->netdev_ops = &octep_netdev_ops;
 	octep_set_ethtool_ops(netdev);
 	netif_carrier_off(netdev);
 
 	netdev->hw_features = NETIF_F_SG;
-	netdev->features |= netdev->hw_features;
+	if (OCTEP_TX_IP_CSUM(octep_dev->conf->fw_info.tx_ol_flags))
+		netdev->hw_features |= (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
+
+	if (OCTEP_RX_IP_CSUM(octep_dev->conf->fw_info.rx_ol_flags))
+		netdev->hw_features |= NETIF_F_RXCSUM;
+
+	max_rx_pktlen = octep_ctrl_net_get_mtu(octep_dev, OCTEP_CTRL_NET_INVALID_VFID);
+	if (max_rx_pktlen < 0) {
+		dev_err(&octep_dev->pdev->dev,
+			"Failed to get max receive packet size; err = %d\n", max_rx_pktlen);
+		err = max_rx_pktlen;
+		goto register_dev_err;
+	}
 	netdev->min_mtu = OCTEP_MIN_MTU;
-	netdev->max_mtu = OCTEP_MAX_MTU;
+	netdev->max_mtu = max_rx_pktlen - (ETH_HLEN + ETH_FCS_LEN);
 	netdev->mtu = OCTEP_DEFAULT_MTU;
 
+	if (OCTEP_TX_TSO(octep_dev->conf->fw_info.tx_ol_flags)) {
+		netdev->hw_features |= NETIF_F_TSO;
+		netif_set_tso_max_size(netdev, netdev->max_mtu);
+	}
+
+	netdev->features |= netdev->hw_features;
 	err = octep_ctrl_net_get_mac_addr(octep_dev, OCTEP_CTRL_NET_INVALID_VFID,
 					  octep_dev->mac_addr);
 	if (err) {
@@ -1378,6 +1514,21 @@ err_dma_mask:
 	return err;
 }
 
+static int octep_sriov_disable(struct octep_device *oct)
+{
+	struct pci_dev *pdev = oct->pdev;
+
+	if (pci_vfs_assigned(oct->pdev)) {
+		dev_warn(&pdev->dev, "Can't disable SRIOV while VFs are assigned\n");
+		return -EPERM;
+	}
+
+	pci_disable_sriov(pdev);
+	CFG_GET_ACTIVE_VFS(oct->conf) = 0;
+
+	return 0;
+}
+
 /**
  * octep_remove() - Remove Octeon PCI device from driver control.
  *
@@ -1395,6 +1546,7 @@ static void octep_remove(struct pci_dev *pdev)
 		return;
 
 	netdev = oct->netdev;
+	octep_sriov_disable(oct);
 	if (netdev->reg_state == NETREG_REGISTERED)
 		unregister_netdev(netdev);
 
@@ -1405,11 +1557,47 @@ static void octep_remove(struct pci_dev *pdev)
 	pci_disable_device(pdev);
 }
 
+static int octep_sriov_enable(struct octep_device *oct, int num_vfs)
+{
+	struct pci_dev *pdev = oct->pdev;
+	int err;
+
+	CFG_GET_ACTIVE_VFS(oct->conf) = num_vfs;
+	err = pci_enable_sriov(pdev, num_vfs);
+	if (err) {
+		dev_warn(&pdev->dev, "Failed to enable SRIOV err=%d\n", err);
+		CFG_GET_ACTIVE_VFS(oct->conf) = 0;
+		return err;
+	}
+
+	return num_vfs;
+}
+
+static int octep_sriov_configure(struct pci_dev *pdev, int num_vfs)
+{
+	struct octep_device *oct = pci_get_drvdata(pdev);
+	int max_nvfs;
+
+	if (num_vfs == 0)
+		return octep_sriov_disable(oct);
+
+	max_nvfs = CFG_GET_MAX_VFS(oct->conf);
+
+	if (num_vfs > max_nvfs) {
+		dev_err(&pdev->dev, "Invalid VF count Max supported VFs = %d\n",
+			max_nvfs);
+		return -EINVAL;
+	}
+
+	return octep_sriov_enable(oct, num_vfs);
+}
+
 static struct pci_driver octep_driver = {
 	.name = OCTEP_DRV_NAME,
 	.id_table = octep_pci_id_tbl,
 	.probe = octep_probe,
 	.remove = octep_remove,
+	.sriov_configure = octep_sriov_configure,
 };
 
 /**
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.h b/drivers/net/ethernet/marvell/octeon_ep/octep_main.h
index 6df902ebb7f3..fee59e0e0138 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.h
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.h
@@ -18,11 +18,17 @@
 #define  OCTEP_PCIID_CN93_PF  0xB200177d
 #define  OCTEP_PCIID_CN93_VF  0xB203177d
 
+#define  OCTEP_PCI_DEVICE_ID_CN98_PF 0xB100
 #define  OCTEP_PCI_DEVICE_ID_CN93_PF 0xB200
 #define  OCTEP_PCI_DEVICE_ID_CN93_VF 0xB203
 
 #define  OCTEP_PCI_DEVICE_ID_CNF95N_PF 0xB400    //95N PF
 
+#define  OCTEP_PCI_DEVICE_ID_CN10KA_PF  0xB900   //CN10KA PF
+#define  OCTEP_PCI_DEVICE_ID_CNF10KA_PF 0xBA00   //CNF10KA PF
+#define  OCTEP_PCI_DEVICE_ID_CNF10KB_PF 0xBC00   //CNF10KB PF
+#define  OCTEP_PCI_DEVICE_ID_CN10KB_PF  0xBD00   //CN10KB PF
+
 #define  OCTEP_MAX_QUEUES   63
 #define  OCTEP_MAX_IQ       OCTEP_MAX_QUEUES
 #define  OCTEP_MAX_OQ       OCTEP_MAX_QUEUES
@@ -40,6 +46,15 @@
 #define  OCTEP_OQ_INTR_RESEND_BIT  59
 
 #define  OCTEP_MMIO_REGIONS     3
+
+#define  IQ_INSTR_PENDING(iq)  ({ typeof(iq) iq__ = (iq); \
+				  ((iq__)->host_write_index - (iq__)->flush_index) & \
+				  (iq__)->ring_size_mask; \
+				})
+#define  IQ_INSTR_SPACE(iq)    ({ typeof(iq) iq_ = (iq); \
+				  (iq_)->max_count - IQ_INSTR_PENDING(iq_); \
+				})
+
 /* PCI address space mapping information.
  * Each of the 3 address spaces given by BAR0, BAR2 and BAR4 of
  * Octeon gets mapped to different physical address spaces in
@@ -65,6 +80,7 @@ struct octep_hw_ops {
 	void (*setup_oq_regs)(struct octep_device *oct, int q);
 	void (*setup_mbox_regs)(struct octep_device *oct, int mbox);
 
+	irqreturn_t (*mbox_intr_handler)(void *ioq_vector);
 	irqreturn_t (*oei_intr_handler)(void *ioq_vector);
 	irqreturn_t (*ire_intr_handler)(void *ioq_vector);
 	irqreturn_t (*ore_intr_handler)(void *ioq_vector);
@@ -103,28 +119,27 @@ struct octep_mbox_data {
 	u64 *data;
 };
 
+#define MAX_VF_PF_MBOX_DATA_SIZE 384
+/* wrappers around work structs */
+struct octep_pfvf_mbox_wk {
+	struct work_struct work;
+	void *ctxptr;
+	u64 ctxul;
+};
+
 /* Octeon device mailbox */
 struct octep_mbox {
-	/* A spinlock to protect access to this q_mbox. */
-	spinlock_t lock;
-
-	u32 q_no;
-	u32 state;
-
-	/* SLI_MAC_PF_MBOX_INT for PF, SLI_PKT_MBOX_INT for VF. */
-	u8 __iomem *mbox_int_reg;
-
-	/* SLI_PKT_PF_VF_MBOX_SIG(0) for PF,
-	 * SLI_PKT_PF_VF_MBOX_SIG(1) for VF.
-	 */
-	u8 __iomem *mbox_write_reg;
-
-	/* SLI_PKT_PF_VF_MBOX_SIG(1) for PF,
-	 * SLI_PKT_PF_VF_MBOX_SIG(0) for VF.
-	 */
-	u8 __iomem *mbox_read_reg;
-
+	/* A mutex to protect access to this q_mbox. */
+	struct mutex lock;
+	u32 vf_id;
+	u32 config_data_index;
+	u32 message_len;
+	u8 __iomem *pf_vf_data_reg;
+	u8 __iomem *vf_pf_data_reg;
+	struct octep_pfvf_mbox_wk wk;
+	struct octep_device *oct;
 	struct octep_mbox_data mbox_data;
+	u8 config_data[MAX_VF_PF_MBOX_DATA_SIZE];
 };
 
 /* Tx/Rx queue vector per interrupt. */
@@ -202,6 +217,12 @@ struct octep_iface_link_info {
 	u8  oper_up;
 };
 
+/* The Octeon VF device specific info data structure.*/
+struct octep_pfvf_info {
+	u8 mac_addr[ETH_ALEN];
+	u32 mbox_version;
+};
+
 /* The Octeon device specific private data structure.
  * Each Octeon device has this structure to represent all its components.
  */
@@ -232,8 +253,7 @@ struct octep_device {
 
 	/* Tx queues (IQ: Instruction Queue) */
 	u16 num_iqs;
-	/* pkind value to be used in every Tx hardware descriptor */
-	u8 pkind;
+
 	/* Pointers to Octeon Tx queues */
 	struct octep_iq *iq[OCTEP_MAX_IQ];
 
@@ -268,6 +288,8 @@ struct octep_device {
 
 	/* Mailbox to talk to VFs */
 	struct octep_mbox *mbox[OCTEP_MAX_VF];
+	/* VFs info */
+	struct octep_pfvf_info vf_info[OCTEP_MAX_VF];
 
 	/* Work entry to handle Tx timeout */
 	struct work_struct tx_timeout_task;
@@ -377,6 +399,7 @@ int octep_setup_oqs(struct octep_device *oct);
 void octep_free_oqs(struct octep_device *oct);
 void octep_oq_dbell_init(struct octep_device *oct);
 void octep_device_setup_cn93_pf(struct octep_device *oct);
+void octep_device_setup_cnxk_pf(struct octep_device *oct);
 int octep_iq_process_completions(struct octep_iq *iq, u16 budget);
 int octep_oq_process_rx(struct octep_oq *oq, int budget);
 void octep_set_ethtool_ops(struct net_device *netdev);
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c
new file mode 100644
index 000000000000..2e2c3be8a0b4
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c
@@ -0,0 +1,449 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell Octeon EP (EndPoint) Ethernet Driver
+ *
+ * Copyright (C) 2020 Marvell.
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/mutex.h>
+#include <linux/jiffies.h>
+#include <linux/sched.h>
+#include <linux/sched/signal.h>
+#include <linux/io.h>
+#include <linux/pci.h>
+#include <linux/etherdevice.h>
+
+#include "octep_config.h"
+#include "octep_main.h"
+#include "octep_pfvf_mbox.h"
+#include "octep_ctrl_net.h"
+
+/* When a new command is implemented, the below table should be updated
+ * with new command and it's version info.
+ */
+static u32 pfvf_cmd_versions[OCTEP_PFVF_MBOX_CMD_MAX] = {
+	[0 ... OCTEP_PFVF_MBOX_CMD_DEV_REMOVE] = OCTEP_PFVF_MBOX_VERSION_V1,
+	[OCTEP_PFVF_MBOX_CMD_GET_FW_INFO ... OCTEP_PFVF_MBOX_NOTIF_LINK_STATUS] =
+		OCTEP_PFVF_MBOX_VERSION_V2
+};
+
+static void octep_pfvf_validate_version(struct octep_device *oct,  u32 vf_id,
+					union octep_pfvf_mbox_word cmd,
+					union octep_pfvf_mbox_word *rsp)
+{
+	u32 vf_version = (u32)cmd.s_version.version;
+
+	dev_dbg(&oct->pdev->dev, "VF id:%d VF version:%d PF version:%d\n",
+		vf_id, vf_version, OCTEP_PFVF_MBOX_VERSION_CURRENT);
+	if (vf_version < OCTEP_PFVF_MBOX_VERSION_CURRENT)
+		rsp->s_version.version = vf_version;
+	else
+		rsp->s_version.version = OCTEP_PFVF_MBOX_VERSION_CURRENT;
+
+	oct->vf_info[vf_id].mbox_version = rsp->s_version.version;
+	dev_dbg(&oct->pdev->dev, "VF id:%d negotiated VF version:%d\n",
+		vf_id, oct->vf_info[vf_id].mbox_version);
+
+	rsp->s_version.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK;
+}
+
+static void octep_pfvf_get_link_status(struct octep_device *oct, u32 vf_id,
+				       union octep_pfvf_mbox_word cmd,
+				       union octep_pfvf_mbox_word *rsp)
+{
+	int status;
+
+	status = octep_ctrl_net_get_link_status(oct, vf_id);
+	if (status < 0) {
+		rsp->s_link_status.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK;
+		dev_err(&oct->pdev->dev, "Get VF link status failed via host control Mbox\n");
+		return;
+	}
+	rsp->s_link_status.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK;
+	rsp->s_link_status.status = status;
+}
+
+static void octep_pfvf_set_link_status(struct octep_device *oct, u32 vf_id,
+				       union octep_pfvf_mbox_word cmd,
+				       union octep_pfvf_mbox_word *rsp)
+{
+	int err;
+
+	err = octep_ctrl_net_set_link_status(oct, vf_id, cmd.s_link_status.status, true);
+	if (err) {
+		rsp->s_link_status.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK;
+		dev_err(&oct->pdev->dev, "Set VF link status failed via host control Mbox\n");
+		return;
+	}
+	rsp->s_link_status.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK;
+}
+
+static void octep_pfvf_set_rx_state(struct octep_device *oct, u32 vf_id,
+				    union octep_pfvf_mbox_word cmd,
+				    union octep_pfvf_mbox_word *rsp)
+{
+	int err;
+
+	err = octep_ctrl_net_set_rx_state(oct, vf_id, cmd.s_link_state.state, true);
+	if (err) {
+		rsp->s_link_state.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK;
+		dev_err(&oct->pdev->dev, "Set VF Rx link state failed via host control Mbox\n");
+		return;
+	}
+	rsp->s_link_state.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK;
+}
+
+static int octep_send_notification(struct octep_device *oct, u32 vf_id,
+				   union octep_pfvf_mbox_word cmd)
+{
+	u32 max_rings_per_vf, vf_mbox_queue;
+	struct octep_mbox *mbox;
+
+	/* check if VF PF Mailbox is compatible for this notification */
+	if (pfvf_cmd_versions[cmd.s.opcode] > oct->vf_info[vf_id].mbox_version) {
+		dev_dbg(&oct->pdev->dev, "VF Mbox doesn't support Notification:%d on VF ver:%d\n",
+			cmd.s.opcode, oct->vf_info[vf_id].mbox_version);
+		return -EOPNOTSUPP;
+	}
+
+	max_rings_per_vf = CFG_GET_MAX_RPVF(oct->conf);
+	vf_mbox_queue = vf_id * max_rings_per_vf;
+	if (!oct->mbox[vf_mbox_queue]) {
+		dev_err(&oct->pdev->dev, "Notif obtained for bad mbox vf %d\n", vf_id);
+		return -EINVAL;
+	}
+	mbox = oct->mbox[vf_mbox_queue];
+
+	mutex_lock(&mbox->lock);
+	writeq(cmd.u64, mbox->pf_vf_data_reg);
+	mutex_unlock(&mbox->lock);
+
+	return 0;
+}
+
+static void octep_pfvf_set_mtu(struct octep_device *oct, u32 vf_id,
+			       union octep_pfvf_mbox_word cmd,
+			       union octep_pfvf_mbox_word *rsp)
+{
+	int err;
+
+	err = octep_ctrl_net_set_mtu(oct, vf_id, cmd.s_set_mtu.mtu, true);
+	if (err) {
+		rsp->s_set_mtu.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK;
+		dev_err(&oct->pdev->dev, "Set VF MTU failed via host control Mbox\n");
+		return;
+	}
+	rsp->s_set_mtu.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK;
+}
+
+static void octep_pfvf_get_mtu(struct octep_device *oct, u32 vf_id,
+			       union octep_pfvf_mbox_word cmd,
+			       union octep_pfvf_mbox_word *rsp)
+{
+	int max_rx_pktlen = oct->netdev->max_mtu + (ETH_HLEN + ETH_FCS_LEN);
+
+	rsp->s_set_mtu.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK;
+	rsp->s_get_mtu.mtu = max_rx_pktlen;
+}
+
+static void octep_pfvf_set_mac_addr(struct octep_device *oct,  u32 vf_id,
+				    union octep_pfvf_mbox_word cmd,
+				    union octep_pfvf_mbox_word *rsp)
+{
+	int err;
+
+	err = octep_ctrl_net_set_mac_addr(oct, vf_id, cmd.s_set_mac.mac_addr, true);
+	if (err) {
+		rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK;
+		dev_err(&oct->pdev->dev, "Set VF MAC address failed via host control Mbox\n");
+		return;
+	}
+	rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK;
+}
+
+static void octep_pfvf_get_mac_addr(struct octep_device *oct,  u32 vf_id,
+				    union octep_pfvf_mbox_word cmd,
+				    union octep_pfvf_mbox_word *rsp)
+{
+	int err;
+
+	err = octep_ctrl_net_get_mac_addr(oct, vf_id, rsp->s_set_mac.mac_addr);
+	if (err) {
+		rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK;
+		dev_err(&oct->pdev->dev, "Get VF MAC address failed via host control Mbox\n");
+		return;
+	}
+	rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK;
+}
+
+static void octep_pfvf_dev_remove(struct octep_device *oct,  u32 vf_id,
+				  union octep_pfvf_mbox_word cmd,
+				  union octep_pfvf_mbox_word *rsp)
+{
+	int err;
+
+	err = octep_ctrl_net_dev_remove(oct, vf_id);
+	if (err) {
+		rsp->s.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK;
+		dev_err(&oct->pdev->dev, "Failed to acknowledge fw of vf %d removal\n",
+			vf_id);
+		return;
+	}
+	rsp->s.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK;
+}
+
+static void octep_pfvf_get_fw_info(struct octep_device *oct,  u32 vf_id,
+				   union octep_pfvf_mbox_word cmd,
+				   union octep_pfvf_mbox_word *rsp)
+{
+	struct octep_fw_info fw_info;
+	int err;
+
+	err = octep_ctrl_net_get_info(oct, vf_id, &fw_info);
+	if (err) {
+		rsp->s_fw_info.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK;
+		dev_err(&oct->pdev->dev, "Get VF info failed via host control Mbox\n");
+		return;
+	}
+
+	rsp->s_fw_info.pkind = fw_info.pkind;
+	rsp->s_fw_info.fsz = fw_info.fsz;
+	rsp->s_fw_info.rx_ol_flags = fw_info.rx_ol_flags;
+	rsp->s_fw_info.tx_ol_flags = fw_info.tx_ol_flags;
+
+	rsp->s_fw_info.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK;
+}
+
+static void octep_pfvf_set_offloads(struct octep_device *oct, u32 vf_id,
+				    union octep_pfvf_mbox_word cmd,
+				    union octep_pfvf_mbox_word *rsp)
+{
+	struct octep_ctrl_net_offloads offloads = {
+		.rx_offloads = cmd.s_offloads.rx_ol_flags,
+		.tx_offloads = cmd.s_offloads.tx_ol_flags
+	};
+	int err;
+
+	err = octep_ctrl_net_set_offloads(oct, vf_id, &offloads, true);
+	if (err) {
+		rsp->s_offloads.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK;
+		dev_err(&oct->pdev->dev, "Set VF offloads failed via host control Mbox\n");
+		return;
+	}
+	rsp->s_offloads.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK;
+}
+
+int octep_setup_pfvf_mbox(struct octep_device *oct)
+{
+	int i = 0, num_vfs = 0, rings_per_vf = 0;
+	int ring = 0;
+
+	num_vfs = oct->conf->sriov_cfg.active_vfs;
+	rings_per_vf = oct->conf->sriov_cfg.max_rings_per_vf;
+
+	for (i = 0; i < num_vfs; i++) {
+		ring  = rings_per_vf * i;
+		oct->mbox[ring] = vzalloc(sizeof(*oct->mbox[ring]));
+
+		if (!oct->mbox[ring])
+			goto free_mbox;
+
+		memset(oct->mbox[ring], 0, sizeof(struct octep_mbox));
+		memset(&oct->vf_info[i], 0, sizeof(struct octep_pfvf_info));
+		mutex_init(&oct->mbox[ring]->lock);
+		INIT_WORK(&oct->mbox[ring]->wk.work, octep_pfvf_mbox_work);
+		oct->mbox[ring]->wk.ctxptr = oct->mbox[ring];
+		oct->mbox[ring]->oct = oct;
+		oct->mbox[ring]->vf_id = i;
+		oct->hw_ops.setup_mbox_regs(oct, ring);
+	}
+	return 0;
+
+free_mbox:
+	while (i) {
+		i--;
+		ring  = rings_per_vf * i;
+		cancel_work_sync(&oct->mbox[ring]->wk.work);
+		mutex_destroy(&oct->mbox[ring]->lock);
+		vfree(oct->mbox[ring]);
+		oct->mbox[ring] = NULL;
+	}
+	return -ENOMEM;
+}
+
+void octep_delete_pfvf_mbox(struct octep_device *oct)
+{
+	int rings_per_vf = oct->conf->sriov_cfg.max_rings_per_vf;
+	int num_vfs = oct->conf->sriov_cfg.active_vfs;
+	int i = 0, ring = 0, vf_srn = 0;
+
+	for (i = 0; i < num_vfs; i++) {
+		ring  = vf_srn + rings_per_vf * i;
+		if (!oct->mbox[ring])
+			continue;
+
+		if (work_pending(&oct->mbox[ring]->wk.work))
+			cancel_work_sync(&oct->mbox[ring]->wk.work);
+
+		mutex_destroy(&oct->mbox[ring]->lock);
+		vfree(oct->mbox[ring]);
+		oct->mbox[ring] = NULL;
+	}
+}
+
+static void octep_pfvf_pf_get_data(struct octep_device *oct,
+				   struct octep_mbox *mbox, int vf_id,
+				   union octep_pfvf_mbox_word cmd,
+				   union octep_pfvf_mbox_word *rsp)
+{
+	int length = 0;
+	int i = 0;
+	int err;
+	struct octep_iface_link_info link_info;
+	struct octep_iface_rx_stats rx_stats;
+	struct octep_iface_tx_stats tx_stats;
+
+	rsp->s_data.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK;
+
+	if (cmd.s_data.frag != OCTEP_PFVF_MBOX_MORE_FRAG_FLAG) {
+		mbox->config_data_index = 0;
+		memset(mbox->config_data, 0, MAX_VF_PF_MBOX_DATA_SIZE);
+		/* Based on the OPCODE CMD the PF driver
+		 * specific API should be called to fetch
+		 * the requested data
+		 */
+		switch (cmd.s.opcode) {
+		case OCTEP_PFVF_MBOX_CMD_GET_LINK_INFO:
+			memset(&link_info, 0, sizeof(link_info));
+			err = octep_ctrl_net_get_link_info(oct, vf_id, &link_info);
+			if (!err) {
+				mbox->message_len = sizeof(link_info);
+				*((int32_t *)rsp->s_data.data) = mbox->message_len;
+				memcpy(mbox->config_data, (u8 *)&link_info, sizeof(link_info));
+			} else {
+				rsp->s_data.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK;
+				return;
+			}
+			break;
+		case OCTEP_PFVF_MBOX_CMD_GET_STATS:
+			memset(&rx_stats, 0, sizeof(rx_stats));
+			memset(&tx_stats, 0, sizeof(tx_stats));
+			err = octep_ctrl_net_get_if_stats(oct, vf_id, &rx_stats, &tx_stats);
+			if (!err) {
+				mbox->message_len = sizeof(rx_stats) + sizeof(tx_stats);
+				*((int32_t *)rsp->s_data.data) = mbox->message_len;
+				memcpy(mbox->config_data, (u8 *)&rx_stats, sizeof(rx_stats));
+				memcpy(mbox->config_data + sizeof(rx_stats), (u8 *)&tx_stats,
+				       sizeof(tx_stats));
+
+			} else {
+				rsp->s_data.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK;
+				return;
+			}
+			break;
+		}
+		*((int32_t *)rsp->s_data.data) = mbox->message_len;
+		return;
+	}
+
+	if (mbox->message_len > OCTEP_PFVF_MBOX_MAX_DATA_SIZE)
+		length = OCTEP_PFVF_MBOX_MAX_DATA_SIZE;
+	else
+		length = mbox->message_len;
+
+	mbox->message_len -= length;
+
+	for (i = 0; i < length; i++) {
+		rsp->s_data.data[i] =
+			mbox->config_data[mbox->config_data_index];
+		mbox->config_data_index++;
+	}
+}
+
+void octep_pfvf_notify(struct octep_device *oct, struct octep_ctrl_mbox_msg *msg)
+{
+	union octep_pfvf_mbox_word notif = { 0 };
+	struct octep_ctrl_net_f2h_req *req;
+
+	req = (struct octep_ctrl_net_f2h_req *)msg->sg_list[0].msg;
+	switch (req->hdr.s.cmd) {
+	case OCTEP_CTRL_NET_F2H_CMD_LINK_STATUS:
+		notif.s_link_status.opcode = OCTEP_PFVF_MBOX_NOTIF_LINK_STATUS;
+		notif.s_link_status.status = req->link.state;
+		break;
+	default:
+		pr_info("Unknown mbox notif for vf: %u\n",
+			req->hdr.s.cmd);
+		return;
+	}
+
+	notif.s.type = OCTEP_PFVF_MBOX_TYPE_CMD;
+	octep_send_notification(oct, msg->hdr.s.vf_idx, notif);
+}
+
+void octep_pfvf_mbox_work(struct work_struct *work)
+{
+	struct octep_pfvf_mbox_wk *wk = container_of(work, struct octep_pfvf_mbox_wk, work);
+	union octep_pfvf_mbox_word cmd = { 0 };
+	union octep_pfvf_mbox_word rsp = { 0 };
+	struct octep_mbox *mbox = NULL;
+	struct octep_device *oct = NULL;
+	int vf_id;
+
+	mbox = (struct octep_mbox *)wk->ctxptr;
+	oct = (struct octep_device *)mbox->oct;
+	vf_id = mbox->vf_id;
+
+	mutex_lock(&mbox->lock);
+	cmd.u64 = readq(mbox->vf_pf_data_reg);
+	rsp.u64 = 0;
+
+	switch (cmd.s.opcode) {
+	case OCTEP_PFVF_MBOX_CMD_VERSION:
+		octep_pfvf_validate_version(oct, vf_id, cmd, &rsp);
+		break;
+	case OCTEP_PFVF_MBOX_CMD_GET_LINK_STATUS:
+		octep_pfvf_get_link_status(oct, vf_id, cmd, &rsp);
+		break;
+	case OCTEP_PFVF_MBOX_CMD_SET_LINK_STATUS:
+		octep_pfvf_set_link_status(oct, vf_id, cmd, &rsp);
+		break;
+	case OCTEP_PFVF_MBOX_CMD_SET_RX_STATE:
+		octep_pfvf_set_rx_state(oct, vf_id, cmd, &rsp);
+		break;
+	case OCTEP_PFVF_MBOX_CMD_SET_MTU:
+		octep_pfvf_set_mtu(oct, vf_id, cmd, &rsp);
+		break;
+	case OCTEP_PFVF_MBOX_CMD_SET_MAC_ADDR:
+		octep_pfvf_set_mac_addr(oct, vf_id, cmd, &rsp);
+		break;
+	case OCTEP_PFVF_MBOX_CMD_GET_MAC_ADDR:
+		octep_pfvf_get_mac_addr(oct, vf_id, cmd, &rsp);
+		break;
+	case OCTEP_PFVF_MBOX_CMD_GET_LINK_INFO:
+	case OCTEP_PFVF_MBOX_CMD_GET_STATS:
+		octep_pfvf_pf_get_data(oct, mbox, vf_id, cmd, &rsp);
+		break;
+	case OCTEP_PFVF_MBOX_CMD_GET_MTU:
+		octep_pfvf_get_mtu(oct, vf_id, cmd, &rsp);
+		break;
+	case OCTEP_PFVF_MBOX_CMD_DEV_REMOVE:
+		octep_pfvf_dev_remove(oct, vf_id, cmd, &rsp);
+		break;
+	case OCTEP_PFVF_MBOX_CMD_GET_FW_INFO:
+		octep_pfvf_get_fw_info(oct, vf_id, cmd, &rsp);
+		break;
+	case OCTEP_PFVF_MBOX_CMD_SET_OFFLOADS:
+		octep_pfvf_set_offloads(oct, vf_id, cmd, &rsp);
+		break;
+	default:
+		dev_err(&oct->pdev->dev, "PF-VF mailbox: invalid opcode %d\n", cmd.s.opcode);
+		rsp.s.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK;
+		break;
+	}
+	writeq(rsp.u64, mbox->vf_pf_data_reg);
+	mutex_unlock(&mbox->lock);
+}
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.h b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.h
new file mode 100644
index 000000000000..0dc6eead292a
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.h
@@ -0,0 +1,167 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Marvell Octeon EP (EndPoint) Ethernet Driver
+ *
+ * Copyright (C) 2020 Marvell.
+ *
+ */
+
+#ifndef _OCTEP_PFVF_MBOX_H_
+#define _OCTEP_PFVF_MBOX_H_
+
+/* VF flags */
+#define OCTEON_PFVF_FLAG_MAC_SET_BY_PF  BIT_ULL(0) /* PF has set VF MAC address */
+#define OCTEON_SDP_16K_HW_FRS  16380UL
+#define OCTEON_SDP_64K_HW_FRS  65531UL
+
+/* When a new command is implemented,PF Mbox version should be bumped.
+ */
+enum octep_pfvf_mbox_version {
+	OCTEP_PFVF_MBOX_VERSION_V0,
+	OCTEP_PFVF_MBOX_VERSION_V1,
+	OCTEP_PFVF_MBOX_VERSION_V2,
+};
+
+#define OCTEP_PFVF_MBOX_VERSION_CURRENT	OCTEP_PFVF_MBOX_VERSION_V2
+
+enum octep_pfvf_mbox_opcode {
+	OCTEP_PFVF_MBOX_CMD_VERSION,
+	OCTEP_PFVF_MBOX_CMD_SET_MTU,
+	OCTEP_PFVF_MBOX_CMD_SET_MAC_ADDR,
+	OCTEP_PFVF_MBOX_CMD_GET_MAC_ADDR,
+	OCTEP_PFVF_MBOX_CMD_GET_LINK_INFO,
+	OCTEP_PFVF_MBOX_CMD_GET_STATS,
+	OCTEP_PFVF_MBOX_CMD_SET_RX_STATE,
+	OCTEP_PFVF_MBOX_CMD_SET_LINK_STATUS,
+	OCTEP_PFVF_MBOX_CMD_GET_LINK_STATUS,
+	OCTEP_PFVF_MBOX_CMD_GET_MTU,
+	OCTEP_PFVF_MBOX_CMD_DEV_REMOVE,
+	OCTEP_PFVF_MBOX_CMD_GET_FW_INFO,
+	OCTEP_PFVF_MBOX_CMD_SET_OFFLOADS,
+	OCTEP_PFVF_MBOX_NOTIF_LINK_STATUS,
+	OCTEP_PFVF_MBOX_CMD_MAX,
+};
+
+enum octep_pfvf_mbox_word_type {
+	OCTEP_PFVF_MBOX_TYPE_CMD,
+	OCTEP_PFVF_MBOX_TYPE_RSP_ACK,
+	OCTEP_PFVF_MBOX_TYPE_RSP_NACK,
+};
+
+enum octep_pfvf_mbox_cmd_status {
+	OCTEP_PFVF_MBOX_CMD_STATUS_NOT_SETUP = 1,
+	OCTEP_PFVF_MBOX_CMD_STATUS_TIMEDOUT = 2,
+	OCTEP_PFVF_MBOX_CMD_STATUS_NACK = 3,
+	OCTEP_PFVF_MBOX_CMD_STATUS_BUSY = 4
+};
+
+enum octep_pfvf_mbox_state {
+	OCTEP_PFVF_MBOX_STATE_IDLE = 0,
+	OCTEP_PFVF_MBOX_STATE_BUSY = 1,
+};
+
+enum octep_pfvf_link_status {
+	OCTEP_PFVF_LINK_STATUS_DOWN,
+	OCTEP_PFVF_LINK_STATUS_UP,
+};
+
+enum octep_pfvf_link_speed {
+	OCTEP_PFVF_LINK_SPEED_NONE,
+	OCTEP_PFVF_LINK_SPEED_1000,
+	OCTEP_PFVF_LINK_SPEED_10000,
+	OCTEP_PFVF_LINK_SPEED_25000,
+	OCTEP_PFVF_LINK_SPEED_40000,
+	OCTEP_PFVF_LINK_SPEED_50000,
+	OCTEP_PFVF_LINK_SPEED_100000,
+	OCTEP_PFVF_LINK_SPEED_LAST,
+};
+
+enum octep_pfvf_link_duplex {
+	OCTEP_PFVF_LINK_HALF_DUPLEX,
+	OCTEP_PFVF_LINK_FULL_DUPLEX,
+};
+
+enum octep_pfvf_link_autoneg {
+	OCTEP_PFVF_LINK_AUTONEG,
+	OCTEP_PFVF_LINK_FIXED,
+};
+
+#define OCTEP_PFVF_MBOX_TIMEOUT_MS     500
+#define OCTEP_PFVF_MBOX_MAX_RETRIES    2
+#define OCTEP_PFVF_MBOX_MAX_DATA_SIZE  6
+#define OCTEP_PFVF_MBOX_MORE_FRAG_FLAG 1
+#define OCTEP_PFVF_MBOX_WRITE_WAIT_TIME msecs_to_jiffies(1)
+
+union octep_pfvf_mbox_word {
+	u64 u64;
+	struct {
+		u64 opcode:8;
+		u64 type:2;
+		u64 rsvd:6;
+		u64 data:48;
+	} s;
+	struct {
+		u64 opcode:8;
+		u64 type:2;
+		u64 frag:1;
+		u64 rsvd:5;
+		u8 data[6];
+	} s_data;
+	struct {
+		u64 opcode:8;
+		u64 type:2;
+		u64 rsvd:6;
+		u64 version:48;
+	} s_version;
+	struct {
+		u64 opcode:8;
+		u64 type:2;
+		u64 rsvd:6;
+		u8 mac_addr[6];
+	} s_set_mac;
+	struct {
+		u64 opcode:8;
+		u64 type:2;
+		u64 rsvd:6;
+		u64 mtu:48;
+	} s_set_mtu;
+	struct {
+		u64 opcode:8;
+		u64 type:2;
+		u64 rsvd:6;
+		u64 mtu:48;
+	} s_get_mtu;
+	struct {
+		u64 opcode:8;
+		u64 type:2;
+		u64 state:1;
+		u64 rsvd:53;
+	} s_link_state;
+	struct {
+		u64 opcode:8;
+		u64 type:2;
+		u64 status:1;
+		u64 rsvd:53;
+	} s_link_status;
+	struct {
+		u64 opcode:8;
+		u64 type:2;
+		u64 pkind:8;
+		u64 fsz:8;
+		u64 rx_ol_flags:16;
+		u64 tx_ol_flags:16;
+		u64 rsvd:6;
+	} s_fw_info;
+	struct {
+		u64 opcode:8;
+		u64 type:2;
+		u64 rsvd:22;
+		u64 rx_ol_flags:16;
+		u64 tx_ol_flags:16;
+	} s_offloads;
+} __packed;
+
+void octep_pfvf_mbox_work(struct work_struct *work);
+int octep_setup_pfvf_mbox(struct octep_device *oct);
+void octep_delete_pfvf_mbox(struct octep_device *oct);
+void octep_pfvf_notify(struct octep_device *oct, struct octep_ctrl_mbox_msg *msg);
+#endif
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cn9k_pf.h b/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cn9k_pf.h
index 0a43983e9101..ca473502d7a0 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cn9k_pf.h
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cn9k_pf.h
@@ -208,6 +208,9 @@
 #define    CN93_SDP_R_MBOX_PF_VF_INT_START        0x10220
 #define    CN93_SDP_R_MBOX_VF_PF_DATA_START       0x10230
 
+#define    CN93_SDP_MBOX_VF_PF_DATA_START       0x24000
+#define    CN93_SDP_MBOX_PF_VF_DATA_START       0x22000
+
 #define    CN93_SDP_R_MBOX_PF_VF_DATA(ring)		\
 	(CN93_SDP_R_MBOX_PF_VF_DATA_START + ((ring) * CN93_RING_OFFSET))
 
@@ -217,6 +220,12 @@
 #define    CN93_SDP_R_MBOX_VF_PF_DATA(ring)		\
 	(CN93_SDP_R_MBOX_VF_PF_DATA_START + ((ring) * CN93_RING_OFFSET))
 
+#define    CN93_SDP_MBOX_VF_PF_DATA(ring)          \
+	(CN93_SDP_MBOX_VF_PF_DATA_START + ((ring) * CN93_EPVF_RING_OFFSET))
+
+#define    CN93_SDP_MBOX_PF_VF_DATA(ring)      \
+	(CN93_SDP_MBOX_PF_VF_DATA_START + ((ring) * CN93_EPVF_RING_OFFSET))
+
 /* ##################### Interrupt Registers ########################## */
 #define	   CN93_SDP_R_ERR_TYPE_START	          0x10400
 
@@ -362,6 +371,10 @@
 #define    CN93_SDP_MAC_PF_RING_CTL_SRN(val)   (((val) >> 8) & 0xFF)
 #define    CN93_SDP_MAC_PF_RING_CTL_RPPF(val)  (((val) >> 16) & 0x3F)
 
+#define    CN98_SDP_MAC_PF_RING_CTL_NPFS(val)  (((val) >> 48) & 0xF)
+#define    CN98_SDP_MAC_PF_RING_CTL_SRN(val)   ((val) & 0xFF)
+#define    CN98_SDP_MAC_PF_RING_CTL_RPPF(val)  (((val) >> 32) & 0x3F)
+
 /* Number of non-queue interrupts in CN93xx */
 #define    CN93_NUM_NON_IOQ_INTR    16
 
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cnxk_pf.h b/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cnxk_pf.h
new file mode 100644
index 000000000000..e637d7c8224d
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cnxk_pf.h
@@ -0,0 +1,416 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Marvell Octeon EP (EndPoint) Ethernet Driver
+ *
+ * Copyright (C) 2020 Marvell.
+ *
+ */
+
+#ifndef _OCTEP_REGS_CNXK_PF_H_
+#define _OCTEP_REGS_CNXK_PF_H_
+
+/* ############################ RST ######################### */
+#define    CNXK_RST_BOOT               0x000087E006001600ULL
+#define    CNXK_RST_CHIP_DOMAIN_W1S    0x000087E006001810ULL
+#define    CNXK_RST_CORE_DOMAIN_W1S    0x000087E006001820ULL
+#define    CNXK_RST_CORE_DOMAIN_W1C    0x000087E006001828ULL
+
+#define     CNXK_CONFIG_XPANSION_BAR             0x38
+#define     CNXK_CONFIG_PCIE_CAP                 0x70
+#define     CNXK_CONFIG_PCIE_DEVCAP              0x74
+#define     CNXK_CONFIG_PCIE_DEVCTL              0x78
+#define     CNXK_CONFIG_PCIE_LINKCAP             0x7C
+#define     CNXK_CONFIG_PCIE_LINKCTL             0x80
+#define     CNXK_CONFIG_PCIE_SLOTCAP             0x84
+#define     CNXK_CONFIG_PCIE_SLOTCTL             0x88
+
+#define     CNXK_PCIE_SRIOV_FDL                  0x188      /* 0x98 */
+#define     CNXK_PCIE_SRIOV_FDL_BIT_POS          0x10
+#define     CNXK_PCIE_SRIOV_FDL_MASK             0xFF
+
+#define     CNXK_CONFIG_PCIE_FLTMSK              0x720
+
+/* ################# Offsets of RING, EPF, MAC ######################### */
+#define    CNXK_RING_OFFSET                      (0x1ULL << 17)
+#define    CNXK_EPF_OFFSET                       (0x1ULL << 25)
+#define    CNXK_MAC_OFFSET                       (0x1ULL << 4)
+#define    CNXK_BIT_ARRAY_OFFSET                 (0x1ULL << 4)
+#define    CNXK_EPVF_RING_OFFSET                 (0x1ULL << 4)
+
+/* ################# Scratch Registers ######################### */
+#define    CNXK_SDP_EPF_SCRATCH                  0x209E0
+
+/* ################# Window Registers ######################### */
+#define    CNXK_SDP_WIN_WR_ADDR64                0x20000
+#define    CNXK_SDP_WIN_RD_ADDR64                0x20010
+#define    CNXK_SDP_WIN_WR_DATA64                0x20020
+#define    CNXK_SDP_WIN_WR_MASK_REG              0x20030
+#define    CNXK_SDP_WIN_RD_DATA64                0x20040
+
+#define    CNXK_SDP_MAC_NUMBER                   0x2C100
+
+/* ################# Global Previliged registers ######################### */
+#define    CNXK_SDP_EPF_RINFO                    0x209F0
+
+#define    CNXK_SDP_EPF_RINFO_SRN(val)           ((val) & 0x7F)
+#define    CNXK_SDP_EPF_RINFO_RPVF(val)          (((val) >> 32) & 0xF)
+#define    CNXK_SDP_EPF_RINFO_NVFS(val)          (((val) >> 48) & 0x7F)
+
+/* SDP Function select */
+#define    CNXK_SDP_FUNC_SEL_EPF_BIT_POS         7
+#define    CNXK_SDP_FUNC_SEL_FUNC_BIT_POS        0
+
+/* ##### RING IN (Into device from PCI: Tx Ring) REGISTERS #### */
+#define    CNXK_SDP_R_IN_CONTROL_START           0x10000
+#define    CNXK_SDP_R_IN_ENABLE_START            0x10010
+#define    CNXK_SDP_R_IN_INSTR_BADDR_START       0x10020
+#define    CNXK_SDP_R_IN_INSTR_RSIZE_START       0x10030
+#define    CNXK_SDP_R_IN_INSTR_DBELL_START       0x10040
+#define    CNXK_SDP_R_IN_CNTS_START              0x10050
+#define    CNXK_SDP_R_IN_INT_LEVELS_START        0x10060
+#define    CNXK_SDP_R_IN_PKT_CNT_START           0x10080
+#define    CNXK_SDP_R_IN_BYTE_CNT_START          0x10090
+
+#define    CNXK_SDP_R_IN_CONTROL(ring)		\
+	(CNXK_SDP_R_IN_CONTROL_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_IN_ENABLE(ring)		\
+	(CNXK_SDP_R_IN_ENABLE_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_IN_INSTR_BADDR(ring)	\
+	(CNXK_SDP_R_IN_INSTR_BADDR_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_IN_INSTR_RSIZE(ring)	\
+	(CNXK_SDP_R_IN_INSTR_RSIZE_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_IN_INSTR_DBELL(ring)	\
+	(CNXK_SDP_R_IN_INSTR_DBELL_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_IN_CNTS(ring)		\
+	(CNXK_SDP_R_IN_CNTS_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_IN_INT_LEVELS(ring)	\
+	(CNXK_SDP_R_IN_INT_LEVELS_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_IN_PKT_CNT(ring)		\
+	(CNXK_SDP_R_IN_PKT_CNT_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_IN_BYTE_CNT(ring)		\
+	(CNXK_SDP_R_IN_BYTE_CNT_START + ((ring) * CNXK_RING_OFFSET))
+
+/* Rings per Virtual Function */
+#define    CNXK_R_IN_CTL_RPVF_MASK	(0xF)
+#define    CNXK_R_IN_CTL_RPVF_POS	(48)
+
+/* Number of instructions to be read in one MAC read request.
+ * setting to Max value(4)
+ */
+#define    CNXK_R_IN_CTL_IDLE                    (0x1ULL << 28)
+#define    CNXK_R_IN_CTL_RDSIZE                  (0x3ULL << 25)
+#define    CNXK_R_IN_CTL_IS_64B                  (0x1ULL << 24)
+#define    CNXK_R_IN_CTL_D_NSR                   (0x1ULL << 8)
+#define    CNXK_R_IN_CTL_D_ESR                   (0x1ULL << 6)
+#define    CNXK_R_IN_CTL_D_ROR                   (0x1ULL << 5)
+#define    CNXK_R_IN_CTL_NSR                     (0x1ULL << 3)
+#define    CNXK_R_IN_CTL_ESR                     (0x1ULL << 1)
+#define    CNXK_R_IN_CTL_ROR                     (0x1ULL << 0)
+
+#define    CNXK_R_IN_CTL_MASK  (CNXK_R_IN_CTL_RDSIZE | CNXK_R_IN_CTL_IS_64B)
+
+/* ##### RING OUT (out from device to PCI host: Rx Ring) REGISTERS #### */
+#define    CNXK_SDP_R_OUT_CNTS_START              0x10100
+#define    CNXK_SDP_R_OUT_INT_LEVELS_START        0x10110
+#define    CNXK_SDP_R_OUT_SLIST_BADDR_START       0x10120
+#define    CNXK_SDP_R_OUT_SLIST_RSIZE_START       0x10130
+#define    CNXK_SDP_R_OUT_SLIST_DBELL_START       0x10140
+#define    CNXK_SDP_R_OUT_CONTROL_START           0x10150
+#define    CNXK_SDP_R_OUT_WMARK_START             0x10160
+#define    CNXK_SDP_R_OUT_ENABLE_START            0x10170
+#define    CNXK_SDP_R_OUT_PKT_CNT_START           0x10180
+#define    CNXK_SDP_R_OUT_BYTE_CNT_START          0x10190
+
+#define    CNXK_SDP_R_OUT_CONTROL(ring)          \
+	(CNXK_SDP_R_OUT_CONTROL_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_OUT_ENABLE(ring)          \
+	(CNXK_SDP_R_OUT_ENABLE_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_OUT_SLIST_BADDR(ring)          \
+	(CNXK_SDP_R_OUT_SLIST_BADDR_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_OUT_SLIST_RSIZE(ring)          \
+	(CNXK_SDP_R_OUT_SLIST_RSIZE_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_OUT_SLIST_DBELL(ring)          \
+	(CNXK_SDP_R_OUT_SLIST_DBELL_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_OUT_WMARK(ring)         \
+	(CNXK_SDP_R_OUT_WMARK_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_OUT_CNTS(ring)          \
+	(CNXK_SDP_R_OUT_CNTS_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_OUT_INT_LEVELS(ring)          \
+	(CNXK_SDP_R_OUT_INT_LEVELS_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_OUT_PKT_CNT(ring)          \
+	(CNXK_SDP_R_OUT_PKT_CNT_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_OUT_BYTE_CNT(ring)          \
+	(CNXK_SDP_R_OUT_BYTE_CNT_START + ((ring) * CNXK_RING_OFFSET))
+
+/*------------------ R_OUT Masks ----------------*/
+#define    CNXK_R_OUT_INT_LEVELS_BMODE            BIT_ULL(63)
+#define    CNXK_R_OUT_INT_LEVELS_TIMET            (32)
+
+#define    CNXK_R_OUT_CTL_IDLE                    BIT_ULL(40)
+#define    CNXK_R_OUT_CTL_ES_I                    BIT_ULL(34)
+#define    CNXK_R_OUT_CTL_NSR_I                   BIT_ULL(33)
+#define    CNXK_R_OUT_CTL_ROR_I                   BIT_ULL(32)
+#define    CNXK_R_OUT_CTL_ES_D                    BIT_ULL(30)
+#define    CNXK_R_OUT_CTL_NSR_D                   BIT_ULL(29)
+#define    CNXK_R_OUT_CTL_ROR_D                   BIT_ULL(28)
+#define    CNXK_R_OUT_CTL_ES_P                    BIT_ULL(26)
+#define    CNXK_R_OUT_CTL_NSR_P                   BIT_ULL(25)
+#define    CNXK_R_OUT_CTL_ROR_P                   BIT_ULL(24)
+#define    CNXK_R_OUT_CTL_IMODE                   BIT_ULL(23)
+
+/* ############### Interrupt Moderation Registers ############### */
+#define CNXK_SDP_R_IN_INT_MDRT_CTL0_START         0x10280
+#define CNXK_SDP_R_IN_INT_MDRT_CTL1_START         0x102A0
+#define CNXK_SDP_R_IN_INT_MDRT_DBG_START          0x102C0
+
+#define CNXK_SDP_R_OUT_INT_MDRT_CTL0_START        0x10380
+#define CNXK_SDP_R_OUT_INT_MDRT_CTL1_START        0x103A0
+#define CNXK_SDP_R_OUT_INT_MDRT_DBG_START         0x103C0
+
+#define CNXK_SDP_R_MBOX_ISM_START                 0x10500
+#define CNXK_SDP_R_OUT_CNTS_ISM_START             0x10510
+#define CNXK_SDP_R_IN_CNTS_ISM_START              0x10520
+
+#define    CNXK_SDP_R_IN_INT_MDRT_CTL0(ring)		\
+	(CNXK_SDP_R_IN_INT_MDRT_CTL0_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_IN_INT_MDRT_CTL1(ring)		\
+	(CNXK_SDP_R_IN_INT_MDRT_CTL1_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_IN_INT_MDRT_DBG(ring)		\
+	(CNXK_SDP_R_IN_INT_MDRT_DBG_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_OUT_INT_MDRT_CTL0(ring)		\
+	(CNXK_SDP_R_OUT_INT_MDRT_CTL0_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_OUT_INT_MDRT_CTL1(ring)		\
+	(CNXK_SDP_R_OUT_INT_MDRT_CTL1_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_OUT_INT_MDRT_DBG(ring)		\
+	(CNXK_SDP_R_OUT_INT_MDRT_DBG_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_MBOX_ISM(ring)          \
+	(CNXK_SDP_R_MBOX_ISM_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_OUT_CNTS_ISM(ring)          \
+	(CNXK_SDP_R_OUT_CNTS_ISM_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_IN_CNTS_ISM(ring)          \
+	(CNXK_SDP_R_IN_CNTS_ISM_START + ((ring) * CNXK_RING_OFFSET))
+
+/* ##################### Mail Box Registers ########################## */
+/* INT register for VF. when a MBOX write from PF happed to a VF,
+ * corresponding bit will be set in this register as well as in
+ * PF_VF_INT register.
+ *
+ * This is a RO register, the int can be cleared by writing 1 to PF_VF_INT
+ */
+/* Basically first 3 are from PF to VF. The last one is data from VF to PF */
+#define    CNXK_SDP_R_MBOX_PF_VF_DATA_START       0x10210
+#define    CNXK_SDP_R_MBOX_PF_VF_INT_START        0x10220
+#define    CNXK_SDP_R_MBOX_VF_PF_DATA_START       0x10230
+
+#define    CNXK_SDP_MBOX_VF_PF_DATA_START       0x24000
+#define    CNXK_SDP_MBOX_PF_VF_DATA_START       0x22000
+
+#define    CNXK_SDP_R_MBOX_PF_VF_DATA(ring)		\
+	(CNXK_SDP_R_MBOX_PF_VF_DATA_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_MBOX_PF_VF_INT(ring)		\
+	(CNXK_SDP_R_MBOX_PF_VF_INT_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_MBOX_VF_PF_DATA(ring)		\
+	(CNXK_SDP_R_MBOX_VF_PF_DATA_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_MBOX_VF_PF_DATA(ring)          \
+	(CNXK_SDP_MBOX_VF_PF_DATA_START + ((ring) * CNXK_EPVF_RING_OFFSET))
+
+#define    CNXK_SDP_MBOX_PF_VF_DATA(ring)      \
+	(CNXK_SDP_MBOX_PF_VF_DATA_START + ((ring) * CNXK_EPVF_RING_OFFSET))
+
+/* ##################### Interrupt Registers ########################## */
+#define	   CNXK_SDP_R_ERR_TYPE_START	          0x10400
+
+#define    CNXK_SDP_R_ERR_TYPE(ring)		\
+	(CNXK_SDP_R_ERR_TYPE_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_MBOX_ISM_START              0x10500
+#define    CNXK_SDP_R_OUT_CNTS_ISM_START          0x10510
+#define    CNXK_SDP_R_IN_CNTS_ISM_START           0x10520
+
+#define    CNXK_SDP_R_MBOX_ISM(ring)		\
+	(CNXK_SDP_R_MBOX_ISM_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_OUT_CNTS_ISM(ring)	\
+	(CNXK_SDP_R_OUT_CNTS_ISM_START + ((ring) * CNXK_RING_OFFSET))
+
+#define    CNXK_SDP_R_IN_CNTS_ISM(ring)		\
+	(CNXK_SDP_R_IN_CNTS_ISM_START + ((ring) * CNXK_RING_OFFSET))
+
+#define	   CNXK_SDP_EPF_MBOX_RINT_START	          0x20100
+#define	   CNXK_SDP_EPF_MBOX_RINT_W1S_START	  0x20120
+#define	   CNXK_SDP_EPF_MBOX_RINT_ENA_W1C_START   0x20140
+#define	   CNXK_SDP_EPF_MBOX_RINT_ENA_W1S_START   0x20160
+
+#define	   CNXK_SDP_EPF_VFIRE_RINT_START          0x20180
+#define	   CNXK_SDP_EPF_VFIRE_RINT_W1S_START      0x201A0
+#define	   CNXK_SDP_EPF_VFIRE_RINT_ENA_W1C_START  0x201C0
+#define	   CNXK_SDP_EPF_VFIRE_RINT_ENA_W1S_START  0x201E0
+
+#define	   CNXK_SDP_EPF_IRERR_RINT                0x20200
+#define	   CNXK_SDP_EPF_IRERR_RINT_W1S            0x20210
+#define	   CNXK_SDP_EPF_IRERR_RINT_ENA_W1C        0x20220
+#define	   CNXK_SDP_EPF_IRERR_RINT_ENA_W1S        0x20230
+
+#define	   CNXK_SDP_EPF_VFORE_RINT_START          0x20240
+#define	   CNXK_SDP_EPF_VFORE_RINT_W1S_START      0x20260
+#define	   CNXK_SDP_EPF_VFORE_RINT_ENA_W1C_START  0x20280
+#define	   CNXK_SDP_EPF_VFORE_RINT_ENA_W1S_START  0x202A0
+
+#define	   CNXK_SDP_EPF_ORERR_RINT                0x20320
+#define	   CNXK_SDP_EPF_ORERR_RINT_W1S            0x20330
+#define	   CNXK_SDP_EPF_ORERR_RINT_ENA_W1C        0x20340
+#define	   CNXK_SDP_EPF_ORERR_RINT_ENA_W1S        0x20350
+
+#define	   CNXK_SDP_EPF_OEI_RINT                  0x20400
+#define	   CNXK_SDP_EPF_OEI_RINT_W1S              0x20500
+#define	   CNXK_SDP_EPF_OEI_RINT_ENA_W1C          0x20600
+#define	   CNXK_SDP_EPF_OEI_RINT_ENA_W1S          0x20700
+
+#define	   CNXK_SDP_EPF_DMA_RINT                  0x20800
+#define	   CNXK_SDP_EPF_DMA_RINT_W1S              0x20810
+#define	   CNXK_SDP_EPF_DMA_RINT_ENA_W1C          0x20820
+#define	   CNXK_SDP_EPF_DMA_RINT_ENA_W1S          0x20830
+
+#define	   CNXK_SDP_EPF_DMA_INT_LEVEL_START	    0x20840
+#define	   CNXK_SDP_EPF_DMA_CNT_START	            0x20860
+#define	   CNXK_SDP_EPF_DMA_TIM_START	            0x20880
+
+#define	   CNXK_SDP_EPF_MISC_RINT                 0x208A0
+#define	   CNXK_SDP_EPF_MISC_RINT_W1S	            0x208B0
+#define	   CNXK_SDP_EPF_MISC_RINT_ENA_W1C         0x208C0
+#define	   CNXK_SDP_EPF_MISC_RINT_ENA_W1S         0x208D0
+
+#define	   CNXK_SDP_EPF_DMA_VF_RINT_START           0x208E0
+#define	   CNXK_SDP_EPF_DMA_VF_RINT_W1S_START       0x20900
+#define	   CNXK_SDP_EPF_DMA_VF_RINT_ENA_W1C_START   0x20920
+#define	   CNXK_SDP_EPF_DMA_VF_RINT_ENA_W1S_START   0x20940
+
+#define	   CNXK_SDP_EPF_PP_VF_RINT_START            0x20960
+#define	   CNXK_SDP_EPF_PP_VF_RINT_W1S_START        0x20980
+#define	   CNXK_SDP_EPF_PP_VF_RINT_ENA_W1C_START    0x209A0
+#define	   CNXK_SDP_EPF_PP_VF_RINT_ENA_W1S_START    0x209C0
+
+#define	   CNXK_SDP_EPF_MBOX_RINT(index)		\
+		(CNXK_SDP_EPF_MBOX_RINT_START + ((index) * CNXK_BIT_ARRAY_OFFSET))
+#define	   CNXK_SDP_EPF_MBOX_RINT_W1S(index)		\
+		(CNXK_SDP_EPF_MBOX_RINT_W1S_START + ((index) * CNXK_BIT_ARRAY_OFFSET))
+#define	   CNXK_SDP_EPF_MBOX_RINT_ENA_W1C(index)	\
+		(CNXK_SDP_EPF_MBOX_RINT_ENA_W1C_START + ((index) * CNXK_BIT_ARRAY_OFFSET))
+#define	   CNXK_SDP_EPF_MBOX_RINT_ENA_W1S(index)	\
+		(CNXK_SDP_EPF_MBOX_RINT_ENA_W1S_START + ((index) * CNXK_BIT_ARRAY_OFFSET))
+
+#define	   CNXK_SDP_EPF_VFIRE_RINT(index)		\
+		(CNXK_SDP_EPF_VFIRE_RINT_START + ((index) * CNXK_BIT_ARRAY_OFFSET))
+#define	   CNXK_SDP_EPF_VFIRE_RINT_W1S(index)		\
+		(CNXK_SDP_EPF_VFIRE_RINT_W1S_START + ((index) * CNXK_BIT_ARRAY_OFFSET))
+#define	   CNXK_SDP_EPF_VFIRE_RINT_ENA_W1C(index)	\
+		(CNXK_SDP_EPF_VFIRE_RINT_ENA_W1C_START + ((index) * CNXK_BIT_ARRAY_OFFSET))
+#define	   CNXK_SDP_EPF_VFIRE_RINT_ENA_W1S(index)	\
+		(CNXK_SDP_EPF_VFIRE_RINT_ENA_W1S_START + ((index) * CNXK_BIT_ARRAY_OFFSET))
+
+#define	   CNXK_SDP_EPF_VFORE_RINT(index)		\
+		(CNXK_SDP_EPF_VFORE_RINT_START + ((index) * CNXK_BIT_ARRAY_OFFSET))
+#define	   CNXK_SDP_EPF_VFORE_RINT_W1S(index)		\
+		(CNXK_SDP_EPF_VFORE_RINT_W1S_START + ((index) * CNXK_BIT_ARRAY_OFFSET))
+#define	   CNXK_SDP_EPF_VFORE_RINT_ENA_W1C(index)	\
+		(CNXK_SDP_EPF_VFORE_RINT_ENA_W1C_START + ((index) * CNXK_BIT_ARRAY_OFFSET))
+#define	   CNXK_SDP_EPF_VFORE_RINT_ENA_W1S(index)	\
+		(CNXK_SDP_EPF_VFORE_RINT_ENA_W1S_START + ((index) * CNXK_BIT_ARRAY_OFFSET))
+
+#define	   CNXK_SDP_EPF_DMA_VF_RINT(index)		\
+		(CNXK_SDP_EPF_DMA_VF_RINT_START + ((index) + CNXK_BIT_ARRAY_OFFSET))
+#define	   CNXK_SDP_EPF_DMA_VF_RINT_W1S(index)		\
+		(CNXK_SDP_EPF_DMA_VF_RINT_W1S_START + ((index) + CNXK_BIT_ARRAY_OFFSET))
+#define	   CNXK_SDP_EPF_DMA_VF_RINT_ENA_W1C(index)	\
+		(CNXK_SDP_EPF_DMA_VF_RINT_ENA_W1C_START + ((index) + CNXK_BIT_ARRAY_OFFSET))
+#define	   CNXK_SDP_EPF_DMA_VF_RINT_ENA_W1S(index)	\
+		(CNXK_SDP_EPF_DMA_VF_RINT_ENA_W1S_START + ((index) + CNXK_BIT_ARRAY_OFFSET))
+
+#define	   CNXK_SDP_EPF_PP_VF_RINT(index)		\
+		(CNXK_SDP_EPF_PP_VF_RINT_START + ((index) + CNXK_BIT_ARRAY_OFFSET))
+#define	   CNXK_SDP_EPF_PP_VF_RINT_W1S(index)		\
+		(CNXK_SDP_EPF_PP_VF_RINT_W1S_START + ((index) + CNXK_BIT_ARRAY_OFFSET))
+#define	   CNXK_SDP_EPF_PP_VF_RINT_ENA_W1C(index)	\
+		(CNXK_SDP_EPF_PP_VF_RINT_ENA_W1C_START + ((index) + CNXK_BIT_ARRAY_OFFSET))
+#define	   CNXK_SDP_EPF_PP_VF_RINT_ENA_W1S(index)	\
+		(CNXK_SDP_EPF_PP_VF_RINT_ENA_W1S_START + ((index) + CNXK_BIT_ARRAY_OFFSET))
+
+/*------------------ Interrupt Masks ----------------*/
+#define	   CNXK_INTR_R_SEND_ISM       BIT_ULL(63)
+#define	   CNXK_INTR_R_OUT_INT        BIT_ULL(62)
+#define    CNXK_INTR_R_IN_INT         BIT_ULL(61)
+#define    CNXK_INTR_R_MBOX_INT       BIT_ULL(60)
+#define    CNXK_INTR_R_RESEND         BIT_ULL(59)
+#define    CNXK_INTR_R_CLR_TIM        BIT_ULL(58)
+
+/* ####################### Ring Mapping Registers ################################## */
+#define    CNXK_SDP_EPVF_RING_START          0x26000
+#define    CNXK_SDP_IN_RING_TB_MAP_START     0x28000
+#define    CNXK_SDP_IN_RATE_LIMIT_START      0x2A000
+#define    CNXK_SDP_MAC_PF_RING_CTL_START    0x2C000
+
+#define	   CNXK_SDP_EPVF_RING(ring)		\
+		(CNXK_SDP_EPVF_RING_START + ((ring) * CNXK_EPVF_RING_OFFSET))
+#define	   CNXK_SDP_IN_RING_TB_MAP(ring)	\
+		(CNXK_SDP_N_RING_TB_MAP_START + ((ring) * CNXK_EPVF_RING_OFFSET))
+#define	   CNXK_SDP_IN_RATE_LIMIT(ring)		\
+		(CNXK_SDP_IN_RATE_LIMIT_START + ((ring) * CNXK_EPVF_RING_OFFSET))
+#define	   CNXK_SDP_MAC_PF_RING_CTL(mac)	\
+		(CNXK_SDP_MAC_PF_RING_CTL_START + ((mac) * CNXK_MAC_OFFSET))
+
+#define    CNXK_SDP_MAC_PF_RING_CTL_NPFS(val)  ((val) & 0x3)
+#define    CNXK_SDP_MAC_PF_RING_CTL_SRN(val)   (((val) >> 8) & 0x7F)
+#define    CNXK_SDP_MAC_PF_RING_CTL_RPPF(val)  (((val) >> 16) & 0x3F)
+
+/* Number of non-queue interrupts in CNXKxx */
+#define    CNXK_NUM_NON_IOQ_INTR    32
+
+/* bit 0 for control mbox interrupt */
+#define CNXK_SDP_EPF_OEI_RINT_DATA_BIT_MBOX	BIT_ULL(0)
+/* bit 1 for firmware heartbeat interrupt */
+#define CNXK_SDP_EPF_OEI_RINT_DATA_BIT_HBEAT	BIT_ULL(1)
+#define FW_STATUS_RUNNING      2ULL
+#define CNXK_PEMX_PFX_CSX_PFCFGX(pem, pf, offset)      ({ typeof(offset) _off = (offset); \
+							  ((0x8e0000008000 | \
+							    (uint64_t)(pem) << 36 \
+							    | (pf) << 18 \
+							    | ((_off >> 16) & 1) << 16 \
+							    | (_off >> 3) << 3) \
+							   + (((_off >> 2) & 1) << 2)); \
+							})
+
+/* Register defines for use with CNXK_PEMX_PFX_CSX_PFCFGX */
+#define CNXK_PCIEEP_VSECST_CTL  0x418
+
+#define CNXK_PEM_BAR4_INDEX		7
+#define CNXK_PEM_BAR4_INDEX_SIZE	0x400000ULL
+#define CNXK_PEM_BAR4_INDEX_OFFSET	(CNXK_PEM_BAR4_INDEX * CNXK_PEM_BAR4_INDEX_SIZE)
+
+#endif /* _OCTEP_REGS_CNXK_PF_H_ */
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c
index 3c43f8078528..4746a6b258f0 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c
@@ -143,7 +143,7 @@ static int octep_setup_oq(struct octep_device *oct, int q_no)
 	 * additional header is filled-in by Octeon after length field in
 	 * Rx packets. this header contains additional packet information.
 	 */
-	if (oct->caps_enabled)
+	if (oct->conf->fw_info.rx_ol_flags)
 		oq->max_single_buffer_size -= OCTEP_OQ_RESP_HW_EXT_SIZE;
 
 	oq->refill_threshold = CFG_GET_OQ_REFILL_THRESHOLD(oct->conf);
@@ -353,11 +353,13 @@ static int __octep_oq_process_rx(struct octep_device *oct,
 				 struct octep_oq *oq, u16 pkts_to_process)
 {
 	struct octep_oq_resp_hw_ext *resp_hw_ext = NULL;
+	netdev_features_t feat = oq->netdev->features;
 	struct octep_rx_buffer *buff_info;
 	struct octep_oq_resp_hw *resp_hw;
 	u32 pkt, rx_bytes, desc_used;
 	struct sk_buff *skb;
 	u16 data_offset;
+	u16 rx_ol_flags;
 	u32 read_idx;
 
 	read_idx = oq->host_read_idx;
@@ -372,7 +374,7 @@ static int __octep_oq_process_rx(struct octep_device *oct,
 
 		/* Swap the length field that is in Big-Endian to CPU */
 		buff_info->len = be64_to_cpu(resp_hw->length);
-		if (oct->caps_enabled & OCTEP_CAP_RX_CHECKSUM) {
+		if (oct->conf->fw_info.rx_ol_flags) {
 			/* Extended response header is immediately after
 			 * response header (resp_hw)
 			 */
@@ -384,11 +386,13 @@ static int __octep_oq_process_rx(struct octep_device *oct,
 			 */
 			data_offset = OCTEP_OQ_RESP_HW_SIZE +
 				      OCTEP_OQ_RESP_HW_EXT_SIZE;
+			rx_ol_flags = resp_hw_ext->rx_ol_flags;
 		} else {
 			/* Data is immediately after
 			 * Hardware Rx response header.
 			 */
 			data_offset = OCTEP_OQ_RESP_HW_SIZE;
+			rx_ol_flags = 0;
 		}
 		rx_bytes += buff_info->len;
 
@@ -444,8 +448,8 @@ static int __octep_oq_process_rx(struct octep_device *oct,
 
 		skb->dev = oq->netdev;
 		skb->protocol =  eth_type_trans(skb, skb->dev);
-		if (resp_hw_ext &&
-		    resp_hw_ext->csum_verified == OCTEP_CSUM_VERIFIED)
+		if (feat & NETIF_F_RXCSUM &&
+		    OCTEP_RX_CSUM_VERIFIED(rx_ol_flags))
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 		else
 			skb->ip_summed = CHECKSUM_NONE;
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h
index 49feae80d7d2..3b08e2d560dc 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h
@@ -20,13 +20,33 @@ struct octep_oq_desc_hw {
 	dma_addr_t buffer_ptr;
 	u64 info_ptr;
 };
+
 static_assert(sizeof(struct octep_oq_desc_hw) == 16);
 
 #define OCTEP_OQ_DESC_SIZE    (sizeof(struct octep_oq_desc_hw))
 
-#define OCTEP_CSUM_L4_VERIFIED 0x1
-#define OCTEP_CSUM_IP_VERIFIED 0x2
-#define OCTEP_CSUM_VERIFIED (OCTEP_CSUM_L4_VERIFIED | OCTEP_CSUM_IP_VERIFIED)
+/* Rx offload flags */
+#define OCTEP_RX_OFFLOAD_VLAN_STRIP	BIT(0)
+#define OCTEP_RX_OFFLOAD_IPV4_CKSUM	BIT(1)
+#define OCTEP_RX_OFFLOAD_UDP_CKSUM	BIT(2)
+#define OCTEP_RX_OFFLOAD_TCP_CKSUM	BIT(3)
+
+#define OCTEP_RX_OFFLOAD_CKSUM		(OCTEP_RX_OFFLOAD_IPV4_CKSUM | \
+					 OCTEP_RX_OFFLOAD_UDP_CKSUM | \
+					 OCTEP_RX_OFFLOAD_TCP_CKSUM)
+
+#define OCTEP_RX_IP_CSUM(flags)		((flags) & \
+					 (OCTEP_RX_OFFLOAD_IPV4_CKSUM | \
+					  OCTEP_RX_OFFLOAD_TCP_CKSUM | \
+					  OCTEP_RX_OFFLOAD_UDP_CKSUM))
+
+/* bit 0 is vlan strip */
+#define OCTEP_RX_CSUM_IP_VERIFIED	BIT(1)
+#define OCTEP_RX_CSUM_L4_VERIFIED	BIT(2)
+
+#define OCTEP_RX_CSUM_VERIFIED(flags)	((flags) & \
+					 (OCTEP_RX_CSUM_L4_VERIFIED | \
+					  OCTEP_RX_CSUM_IP_VERIFIED))
 
 /* Extended Response Header in packet data received from Hardware.
  * Includes metadata like checksum status.
@@ -35,11 +55,12 @@ static_assert(sizeof(struct octep_oq_desc_hw) == 16);
  */
 struct octep_oq_resp_hw_ext {
 	/* Reserved. */
-	u64 reserved:62;
+	u64 rsvd:48;
 
-	/* checksum verified. */
-	u64 csum_verified:2;
+	/* offload flags */
+	u16 rx_ol_flags;
 };
+
 static_assert(sizeof(struct octep_oq_resp_hw_ext) == 8);
 
 #define  OCTEP_OQ_RESP_HW_EXT_SIZE   (sizeof(struct octep_oq_resp_hw_ext))
@@ -52,6 +73,7 @@ struct octep_oq_resp_hw {
 	/* The Length of the packet. */
 	__be64 length;
 };
+
 static_assert(sizeof(struct octep_oq_resp_hw) == 8);
 
 #define OCTEP_OQ_RESP_HW_SIZE   (sizeof(struct octep_oq_resp_hw))
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c
index d0adb82d65c3..06851b78aa28 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c
@@ -21,7 +21,6 @@ static void octep_iq_reset_indices(struct octep_iq *iq)
 	iq->flush_index = 0;
 	iq->pkts_processed = 0;
 	iq->pkt_in_done = 0;
-	atomic_set(&iq->instr_pending, 0);
 }
 
 /**
@@ -82,7 +81,6 @@ int octep_iq_process_completions(struct octep_iq *iq, u16 budget)
 	}
 
 	iq->pkts_processed += compl_pkts;
-	atomic_sub(compl_pkts, &iq->instr_pending);
 	iq->stats.instr_completed += compl_pkts;
 	iq->stats.bytes_sent += compl_bytes;
 	iq->stats.sgentry_sent += compl_sg;
@@ -91,7 +89,7 @@ int octep_iq_process_completions(struct octep_iq *iq, u16 budget)
 	netdev_tx_completed_queue(iq->netdev_q, compl_pkts, compl_bytes);
 
 	if (unlikely(__netif_subqueue_stopped(iq->netdev, iq->q_no)) &&
-	    ((iq->max_count - atomic_read(&iq->instr_pending)) >
+	    (IQ_INSTR_SPACE(iq) >
 	     OCTEP_WAKE_QUEUE_THRESHOLD))
 		netif_wake_subqueue(iq->netdev, iq->q_no);
 	return !budget;
@@ -144,7 +142,6 @@ static void octep_iq_free_pending(struct octep_iq *iq)
 		dev_kfree_skb_any(skb);
 	}
 
-	atomic_set(&iq->instr_pending, 0);
 	iq->flush_index = fi;
 	netdev_tx_reset_queue(netdev_get_tx_queue(iq->netdev, iq->q_no));
 }
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h
index 86c98b13fc44..875a2c34091f 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h
@@ -36,6 +36,7 @@ struct octep_tx_sglist_desc {
 	u16 len[4];
 	dma_addr_t dma_ptr[4];
 };
+
 static_assert(sizeof(struct octep_tx_sglist_desc) == 40);
 
 /* Each Scatter/Gather entry sent to hardwar hold four pointers.
@@ -60,6 +61,18 @@ struct octep_tx_buffer {
 
 /* Hardware interface Tx statistics */
 struct octep_iface_tx_stats {
+	/* Total frames sent on the interface */
+	u64 pkts;
+
+	/* Total octets sent on the interface */
+	u64 octs;
+
+	/* Packets sent to a broadcast DMAC */
+	u64 bcst;
+
+	/* Packets sent to the multicast DMAC */
+	u64 mcst;
+
 	/* Packets dropped due to excessive collisions */
 	u64 xscol;
 
@@ -76,12 +89,6 @@ struct octep_iface_tx_stats {
 	 */
 	u64 scol;
 
-	/* Total octets sent on the interface */
-	u64 octs;
-
-	/* Total frames sent on the interface */
-	u64 pkts;
-
 	/* Packets sent with an octet count < 64 */
 	u64 hist_lt64;
 
@@ -106,12 +113,6 @@ struct octep_iface_tx_stats {
 	/* Packets sent with an octet count of > 1518 */
 	u64 hist_gt1518;
 
-	/* Packets sent to a broadcast DMAC */
-	u64 bcst;
-
-	/* Packets sent to the multicast DMAC */
-	u64 mcst;
-
 	/* Packets sent that experienced a transmit underflow and were
 	 * truncated
 	 */
@@ -172,9 +173,6 @@ struct octep_iq {
 	/* Statistics for this input queue. */
 	struct octep_iq_stats stats;
 
-	/* This field keeps track of the instructions pending in this queue. */
-	atomic_t instr_pending;
-
 	/* Pointer to the Virtual Base addr of the input ring. */
 	struct octep_tx_desc_hw *desc_ring;
 
@@ -240,32 +238,53 @@ struct octep_instr_hdr {
 	/* Reserved3 */
 	u64 reserved3:1;
 };
+
 static_assert(sizeof(struct octep_instr_hdr) == 8);
 
-/* Hardware Tx completion response header */
-struct octep_instr_resp_hdr {
-	/* Request ID  */
-	u64 rid:16;
+/* Tx offload flags */
+#define OCTEP_TX_OFFLOAD_VLAN_INSERT   BIT(0)
+#define OCTEP_TX_OFFLOAD_IPV4_CKSUM    BIT(1)
+#define OCTEP_TX_OFFLOAD_UDP_CKSUM     BIT(2)
+#define OCTEP_TX_OFFLOAD_TCP_CKSUM     BIT(3)
+#define OCTEP_TX_OFFLOAD_SCTP_CKSUM    BIT(4)
+#define OCTEP_TX_OFFLOAD_TCP_TSO       BIT(5)
+#define OCTEP_TX_OFFLOAD_UDP_TSO       BIT(6)
+
+#define OCTEP_TX_OFFLOAD_CKSUM         (OCTEP_TX_OFFLOAD_IPV4_CKSUM | \
+					OCTEP_TX_OFFLOAD_UDP_CKSUM | \
+					OCTEP_TX_OFFLOAD_TCP_CKSUM)
+
+#define OCTEP_TX_OFFLOAD_TSO           (OCTEP_TX_OFFLOAD_TCP_TSO | \
+					OCTEP_TX_OFFLOAD_UDP_TSO)
+
+#define OCTEP_TX_IP_CSUM(flags)		((flags) & \
+					 (OCTEP_TX_OFFLOAD_IPV4_CKSUM | \
+					  OCTEP_TX_OFFLOAD_TCP_CKSUM | \
+					  OCTEP_TX_OFFLOAD_UDP_CKSUM))
 
-	/* PCIe port to use for response */
-	u64 pcie_port:3;
+#define OCTEP_TX_TSO(flags)		((flags) & \
+					 (OCTEP_TX_OFFLOAD_TCP_TSO | \
+					  OCTEP_TX_OFFLOAD_UDP_TSO))
 
-	/* Scatter indicator  1=scatter */
-	u64 scatter:1;
+struct tx_mdata {
 
-	/* Size of Expected result OR no. of entries in scatter list */
-	u64 rlenssz:14;
+	/* offload flags */
+	u16 ol_flags;
 
-	/* Desired destination port for result */
-	u64 dport:6;
+	/* gso size */
+	u16 gso_size;
 
-	/* Opcode Specific parameters */
-	u64 param:8;
+	/* gso flags */
+	u16 gso_segs;
 
-	/* Opcode for the return packet  */
-	u64 opcode:16;
+	/* reserved */
+	u16 rsvd1;
+
+	/* reserved */
+	u64 rsvd2;
 };
-static_assert(sizeof(struct octep_instr_hdr) == 8);
+
+static_assert(sizeof(struct tx_mdata) == 16);
 
 /* 64-byte Tx instruction format.
  * Format of instruction for a 64-byte mode input queue.
@@ -284,18 +303,14 @@ struct octep_tx_desc_hw {
 		struct octep_instr_hdr ih;
 		u64 ih64;
 	};
-
-	/* Pointer where the response for a RAW mode packet will be written
-	 * by Octeon.
-	 */
-	u64 rptr;
-
-	/* Input Instruction Response Header. */
-	struct octep_instr_resp_hdr irh;
-
+	union  {
+		u64 txm64[2];
+		struct tx_mdata txm;
+	};
 	/* Additional headers available in a 64-byte instruction. */
-	u64 exhdr[4];
+	u64 exthdr[4];
 };
+
 static_assert(sizeof(struct octep_tx_desc_hw) == 64);
 
 #define OCTEP_IQ_DESC_SIZE (sizeof(struct octep_tx_desc_hw))
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 6845556581c3..edeb0f737312 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -304,6 +304,13 @@ M(NIX_BANDPROF_GET_HWINFO, 0x801f, nix_bandprof_get_hwinfo, msg_req,		\
 				nix_bandprof_get_hwinfo_rsp)		    \
 M(NIX_READ_INLINE_IPSEC_CFG, 0x8023, nix_read_inline_ipsec_cfg,		\
 				msg_req, nix_inline_ipsec_cfg)		\
+M(NIX_MCAST_GRP_CREATE,	0x802b, nix_mcast_grp_create, nix_mcast_grp_create_req,	\
+				nix_mcast_grp_create_rsp)			\
+M(NIX_MCAST_GRP_DESTROY, 0x802c, nix_mcast_grp_destroy, nix_mcast_grp_destroy_req,	\
+				msg_rsp)					\
+M(NIX_MCAST_GRP_UPDATE, 0x802d, nix_mcast_grp_update,				\
+				nix_mcast_grp_update_req,			\
+				nix_mcast_grp_update_rsp)			\
 /* MCS mbox IDs (range 0xA000 - 0xBFFF) */					\
 M(MCS_ALLOC_RESOURCES,	0xa000, mcs_alloc_resources, mcs_alloc_rsrc_req,	\
 				mcs_alloc_rsrc_rsp)				\
@@ -830,6 +837,9 @@ enum nix_af_status {
 	NIX_AF_ERR_CQ_CTX_WRITE_ERR  = -429,
 	NIX_AF_ERR_AQ_CTX_RETRY_WRITE  = -430,
 	NIX_AF_ERR_LINK_CREDITS  = -431,
+	NIX_AF_ERR_INVALID_MCAST_GRP	= -436,
+	NIX_AF_ERR_INVALID_MCAST_DEL_REQ = -437,
+	NIX_AF_ERR_NON_CONTIG_MCE_LIST = -438,
 };
 
 /* For NIX RX vtag action  */
@@ -1204,6 +1214,68 @@ struct nix_bp_cfg_rsp {
 	u8	chan_cnt; /* Number of channel for which bpids are assigned */
 };
 
+struct nix_mcast_grp_create_req {
+	struct mbox_msghdr hdr;
+#define NIX_MCAST_INGRESS	0
+#define NIX_MCAST_EGRESS	1
+	u8 dir;
+	u8 reserved[11];
+	/* Reserving few bytes for future requirement */
+};
+
+struct nix_mcast_grp_create_rsp {
+	struct mbox_msghdr hdr;
+	/* This mcast_grp_idx should be passed during MCAM
+	 * write entry for multicast. AF will identify the
+	 * corresponding multicast table index associated
+	 * with the group id and program the same to MCAM entry.
+	 * This group id is also needed during group delete
+	 * and update request.
+	 */
+	u32 mcast_grp_idx;
+};
+
+struct nix_mcast_grp_destroy_req {
+	struct mbox_msghdr hdr;
+	/* Group id returned by nix_mcast_grp_create_rsp */
+	u32 mcast_grp_idx;
+	/* If AF is requesting for destroy, then set
+	 * it to '1'. Otherwise keep it to '0'
+	 */
+	u8 is_af;
+};
+
+struct nix_mcast_grp_update_req {
+	struct mbox_msghdr hdr;
+	/* Group id returned by nix_mcast_grp_create_rsp */
+	u32 mcast_grp_idx;
+	/* Number of multicast/mirror entries requested */
+	u32 num_mce_entry;
+#define NIX_MCE_ENTRY_MAX 64
+#define NIX_RX_RQ	0
+#define NIX_RX_RSS	1
+	/* Receive queue or RSS index within pf_func */
+	u32 rq_rss_index[NIX_MCE_ENTRY_MAX];
+	/* pcifunc is required for both ingress and egress multicast */
+	u16 pcifunc[NIX_MCE_ENTRY_MAX];
+	/* channel is required for egress multicast */
+	u16 channel[NIX_MCE_ENTRY_MAX];
+#define NIX_MCAST_OP_ADD_ENTRY	0
+#define NIX_MCAST_OP_DEL_ENTRY	1
+	/* Destination type. 0:Receive queue, 1:RSS*/
+	u8 dest_type[NIX_MCE_ENTRY_MAX];
+	u8 op;
+	/* If AF is requesting for update, then set
+	 * it to '1'. Otherwise keep it to '0'
+	 */
+	u8 is_af;
+};
+
+struct nix_mcast_grp_update_rsp {
+	struct mbox_msghdr hdr;
+	u32 mce_start_index;
+};
+
 /* Global NIX inline IPSec configuration */
 struct nix_inline_ipsec_cfg {
 	struct mbox_msghdr hdr;
@@ -1479,6 +1551,8 @@ struct flow_msg {
 #define OTX2_FLOWER_MASK_MPLS_TTL		GENMASK(7, 0)
 #define OTX2_FLOWER_MASK_MPLS_NON_TTL		GENMASK(31, 8)
 	u32 mpls_lse[4];
+	u8 icmp_type;
+	u8 icmp_code;
 };
 
 struct npc_install_flow_req {
@@ -1945,7 +2019,7 @@ struct mcs_hw_info {
 	u8 tcam_entries;	/* RX/TX Tcam entries per mcs block */
 	u8 secy_entries;	/* RX/TX SECY entries per mcs block */
 	u8 sc_entries;		/* RX/TX SC CAM entries per mcs block */
-	u8 sa_entries;		/* PN table entries = SA entries */
+	u16 sa_entries;		/* PN table entries = SA entries */
 	u64 rsvd[16];
 };
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c
index c43f19dfbd74..c1775bd01c2b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c
@@ -117,7 +117,7 @@ void mcs_get_rx_secy_stats(struct mcs *mcs, struct mcs_secy_stats *stats, int id
 	reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYTAGGEDCTLX(id);
 	stats->pkt_tagged_ctl_cnt = mcs_reg_read(mcs, reg);
 
-	reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYUNTAGGEDORNOTAGX(id);
+	reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYUNTAGGEDX(id);
 	stats->pkt_untaged_cnt = mcs_reg_read(mcs, reg);
 
 	reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYCTLX(id);
@@ -215,7 +215,7 @@ void mcs_get_sc_stats(struct mcs *mcs, struct mcs_sc_stats *stats,
 		reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSCNOTVALIDX(id);
 		stats->pkt_notvalid_cnt = mcs_reg_read(mcs, reg);
 
-		reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSCUNCHECKEDOROKX(id);
+		reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSCUNCHECKEDX(id);
 		stats->pkt_unchecked_cnt = mcs_reg_read(mcs, reg);
 
 		if (mcs->hw->mcs_blks > 1) {
@@ -1219,6 +1219,17 @@ struct mcs *mcs_get_pdata(int mcs_id)
 	return NULL;
 }
 
+bool is_mcs_bypass(int mcs_id)
+{
+	struct mcs *mcs_dev;
+
+	list_for_each_entry(mcs_dev, &mcs_list, mcs_list) {
+		if (mcs_dev->mcs_id == mcs_id)
+			return mcs_dev->bypass;
+	}
+	return true;
+}
+
 void mcs_set_port_cfg(struct mcs *mcs, struct mcs_port_cfg_set_req *req)
 {
 	u64 val = 0;
@@ -1436,7 +1447,7 @@ static int mcs_x2p_calibration(struct mcs *mcs)
 	return err;
 }
 
-static void mcs_set_external_bypass(struct mcs *mcs, u8 bypass)
+static void mcs_set_external_bypass(struct mcs *mcs, bool bypass)
 {
 	u64 val;
 
@@ -1447,6 +1458,7 @@ static void mcs_set_external_bypass(struct mcs *mcs, u8 bypass)
 	else
 		val &= ~BIT_ULL(6);
 	mcs_reg_write(mcs, MCSX_MIL_GLOBAL, val);
+	mcs->bypass = bypass;
 }
 
 static void mcs_global_cfg(struct mcs *mcs)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs.h b/drivers/net/ethernet/marvell/octeontx2/af/mcs.h
index 0f89dcb76465..f927cc61dfd2 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mcs.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs.h
@@ -149,6 +149,7 @@ struct mcs {
 	u16			num_vec;
 	void			*rvu;
 	u16			*tx_sa_active;
+	bool                      bypass;
 };
 
 struct mcs_ops {
@@ -206,6 +207,7 @@ void mcs_get_custom_tag_cfg(struct mcs *mcs, struct mcs_custom_tag_cfg_get_req *
 int mcs_alloc_ctrlpktrule(struct rsrc_bmap *rsrc, u16 *pf_map, u16 offset, u16 pcifunc);
 int mcs_free_ctrlpktrule(struct mcs *mcs, struct mcs_free_ctrl_pkt_rule_req *req);
 int mcs_ctrlpktrule_write(struct mcs *mcs, struct mcs_ctrl_pkt_rule_write_req *req);
+bool is_mcs_bypass(int mcs_id);
 
 /* CN10K-B APIs */
 void cn10kb_mcs_set_hw_capabilities(struct mcs *mcs);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h
index f3ab01fc363c..f4c6de89002c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h
@@ -810,14 +810,37 @@
 		offset = 0x9d8ull;			\
 	offset; })
 
+#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSCUNCHECKEDX(a) ({	\
+	u64 offset;					\
+							\
+	offset = 0xee80ull;				\
+	if (mcs->hw->mcs_blks > 1)			\
+		offset = 0xe818ull;			\
+	offset += (a) * 0x8ull;				\
+	offset; })
+
+#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYUNTAGGEDX(a) ({	\
+	u64 offset;					\
+							\
+	offset = 0xa680ull;				\
+	if (mcs->hw->mcs_blks > 1)			\
+		offset = 0xd018ull;			\
+	offset += (a) * 0x8ull;				\
+	offset; })
+
+#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSCLATEORDELAYEDX(a)	({	\
+	u64 offset;						\
+								\
+	offset = 0xf680ull;					\
+	if (mcs->hw->mcs_blks > 1)				\
+		offset = 0xe018ull;				\
+	offset += (a) * 0x8ull;					\
+	offset; })
+
 #define MCSX_CSE_RX_MEM_SLAVE_INOCTETSSCDECRYPTEDX(a)	(0xe680ull + (a) * 0x8ull)
 #define MCSX_CSE_RX_MEM_SLAVE_INOCTETSSCVALIDATEX(a)	(0xde80ull + (a) * 0x8ull)
-#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYUNTAGGEDORNOTAGX(a)	(0xa680ull + (a) * 0x8ull)
 #define MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYNOTAGX(a)	(0xd218 + (a) * 0x8ull)
-#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYUNTAGGEDX(a)	(0xd018ull + (a) * 0x8ull)
-#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSCUNCHECKEDOROKX(a)	(0xee80ull + (a) * 0x8ull)
 #define MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYCTLX(a)		(0xb680ull + (a) * 0x8ull)
-#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSCLATEORDELAYEDX(a) (0xf680ull + (a) * 0x8ull)
 #define MCSX_CSE_RX_MEM_SLAVE_INPKTSSAINVALIDX(a)	(0x12680ull + (a) * 0x8ull)
 #define MCSX_CSE_RX_MEM_SLAVE_INPKTSSANOTUSINGSAERRORX(a) (0x15680ull + (a) * 0x8ull)
 #define MCSX_CSE_RX_MEM_SLAVE_INPKTSSANOTVALIDX(a)	(0x13680ull + (a) * 0x8ull)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
index ab3e39eef2eb..b0b4dea548e1 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
@@ -214,6 +214,8 @@ enum key_fields {
 	NPC_MPLS3_TTL,
 	NPC_MPLS4_LBTCBOS,
 	NPC_MPLS4_TTL,
+	NPC_TYPE_ICMP,
+	NPC_CODE_ICMP,
 	NPC_HEADER_FIELDS_MAX,
 	NPC_CHAN = NPC_HEADER_FIELDS_MAX, /* Valid when Rx */
 	NPC_PF_FUNC, /* Valid when Tx */
@@ -528,7 +530,7 @@ struct npc_lt_def {
 	u8	ltype_mask;
 	u8	ltype_match;
 	u8	lid;
-};
+} __packed;
 
 struct npc_lt_def_ipsec {
 	u8	ltype_mask;
@@ -536,7 +538,7 @@ struct npc_lt_def_ipsec {
 	u8	lid;
 	u8	spi_offset;
 	u8	spi_nz;
-};
+} __packed;
 
 struct npc_lt_def_apad {
 	u8	ltype_mask;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
index af21e2030cff..4728ba34b0e3 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
@@ -373,6 +373,11 @@ void rpm_lmac_pause_frm_config(void *rpmd, int lmac_id, bool enable)
 	cfg |= RPMX_MTI_MAC100X_COMMAND_CONFIG_TX_P_DISABLE;
 	rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg);
 
+	/* Disable forward pause to driver */
+	cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG);
+	cfg &= ~RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD;
+	rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg);
+
 	/* Enable channel mask for all LMACS */
 	if (is_dev_rpm2(rpm))
 		rpm_write(rpm, lmac_id, RPM2_CMR_CHAN_MSK_OR, 0xffff);
@@ -616,12 +621,10 @@ int rpm_lmac_pfc_config(void *rpmd, int lmac_id, u8 tx_pause, u8 rx_pause, u16 p
 
 	if (rx_pause) {
 		cfg &= ~(RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE |
-				RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE |
-				RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD);
+			 RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE);
 	} else {
 		cfg |= (RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE |
-				RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE |
-				RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD);
+			RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE);
 	}
 
 	if (tx_pause) {
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 22c395c7d040..5c1d04a3c559 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -156,7 +156,7 @@ int rvu_alloc_rsrc_contig(struct rsrc_bmap *rsrc, int nrsrc)
 	return start;
 }
 
-static void rvu_free_rsrc_contig(struct rsrc_bmap *rsrc, int nrsrc, int start)
+void rvu_free_rsrc_contig(struct rsrc_bmap *rsrc, int nrsrc, int start)
 {
 	if (!rsrc->bmap)
 		return;
@@ -935,6 +935,9 @@ static int rvu_setup_hw_resources(struct rvu *rvu)
 	hw->total_vfs = (cfg >> 20) & 0xFFF;
 	hw->max_vfs_per_pf = (cfg >> 40) & 0xFF;
 
+	if (!is_rvu_otx2(rvu))
+		rvu_apr_block_cn10k_init(rvu);
+
 	/* Init NPA LF's bitmap */
 	block = &hw->block[BLKADDR_NPA];
 	if (!block->implemented)
@@ -2614,6 +2617,10 @@ static void __rvu_flr_handler(struct rvu *rvu, u16 pcifunc)
 	 * 2. Flush and reset SSO/SSOW
 	 * 3. Cleanup pools (NPA)
 	 */
+
+	/* Free multicast/mirror node associated with the 'pcifunc' */
+	rvu_nix_mcast_flr_free_entries(rvu, pcifunc);
+
 	rvu_blklf_teardown(rvu, pcifunc, BLKADDR_NIX0);
 	rvu_blklf_teardown(rvu, pcifunc, BLKADDR_NIX1);
 	rvu_blklf_teardown(rvu, pcifunc, BLKADDR_CPT0);
@@ -2631,6 +2638,9 @@ static void __rvu_flr_handler(struct rvu *rvu, u16 pcifunc)
 	rvu_npc_free_mcam_entries(rvu, pcifunc, -1);
 	rvu_mac_reset(rvu, pcifunc);
 
+	if (rvu->mcs_blk_cnt)
+		rvu_mcs_flr_handler(rvu, pcifunc);
+
 	mutex_unlock(&rvu->flr_lock);
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index c4d999ef5ab4..43be37dd1f32 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -116,11 +116,12 @@ struct rvu_block {
 };
 
 struct nix_mcast {
-	struct qmem	*mce_ctx;
-	struct qmem	*mcast_buf;
-	int		replay_pkind;
-	int		next_free_mce;
-	struct mutex	mce_lock; /* Serialize MCE updates */
+	struct qmem		*mce_ctx;
+	struct qmem		*mcast_buf;
+	int			replay_pkind;
+	struct rsrc_bmap	mce_counter[2];
+	/* Counters for both ingress and egress mcast lists */
+	struct mutex		mce_lock; /* Serialize MCE updates */
 };
 
 struct nix_mce_list {
@@ -129,6 +130,23 @@ struct nix_mce_list {
 	int			max;
 };
 
+struct nix_mcast_grp_elem {
+	struct nix_mce_list	mcast_mce_list;
+	u32			mcast_grp_idx;
+	u32			pcifunc;
+	int			mcam_index;
+	int			mce_start_index;
+	struct list_head	list;
+	u8			dir;
+};
+
+struct nix_mcast_grp {
+	struct list_head	mcast_grp_head;
+	int			count;
+	int			next_grp_index;
+	struct mutex		mcast_grp_lock; /* Serialize MCE updates */
+};
+
 /* layer metadata to uniquely identify a packet header field */
 struct npc_layer_mdata {
 	u8 lid;
@@ -339,12 +357,14 @@ struct nix_hw {
 	struct rvu *rvu;
 	struct nix_txsch txsch[NIX_TXSCH_LVL_CNT]; /* Tx schedulers */
 	struct nix_mcast mcast;
+	struct nix_mcast_grp mcast_grp;
 	struct nix_flowkey flowkey;
 	struct nix_mark_format mark_format;
 	struct nix_lso lso;
 	struct nix_txvlan txvlan;
 	struct nix_ipolicer *ipolicer;
 	u64    *tx_credits;
+	u8	cc_mcs_cnt;
 };
 
 /* RVU block's capabilities or functionality,
@@ -741,6 +761,7 @@ void rvu_free_rsrc(struct rsrc_bmap *rsrc, int id);
 bool is_rsrc_free(struct rsrc_bmap *rsrc, int id);
 int rvu_rsrc_free_count(struct rsrc_bmap *rsrc);
 int rvu_alloc_rsrc_contig(struct rsrc_bmap *rsrc, int nrsrc);
+void rvu_free_rsrc_contig(struct rsrc_bmap *rsrc, int nrsrc, int start);
 bool rvu_rsrc_check_contig(struct rsrc_bmap *rsrc, int nrsrc);
 u16 rvu_get_rsrc_mapcount(struct rvu_pfvf *pfvf, int blkaddr);
 int rvu_get_pf(u16 pcifunc);
@@ -847,6 +868,11 @@ u32 convert_dwrr_mtu_to_bytes(u8 dwrr_mtu);
 u32 convert_bytes_to_dwrr_mtu(u32 bytes);
 void rvu_nix_tx_tl2_cfg(struct rvu *rvu, int blkaddr, u16 pcifunc,
 			struct nix_txsch *txsch, bool enable);
+void rvu_nix_mcast_flr_free_entries(struct rvu *rvu, u16 pcifunc);
+int rvu_nix_mcast_get_mce_index(struct rvu *rvu, u16 pcifunc,
+				u32 mcast_grp_idx);
+int rvu_nix_mcast_update_mcam_entry(struct rvu *rvu, u16 pcifunc,
+				    u32 mcast_grp_idx, u16 mcam_index);
 
 /* NPC APIs */
 void rvu_npc_freemem(struct rvu *rvu);
@@ -895,6 +921,10 @@ void npc_mcam_enable_flows(struct rvu *rvu, u16 target);
 void npc_mcam_disable_flows(struct rvu *rvu, u16 target);
 void npc_enable_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
 			   int blkaddr, int index, bool enable);
+u64 npc_get_mcam_action(struct rvu *rvu, struct npc_mcam *mcam,
+			int blkaddr, int index);
+void npc_set_mcam_action(struct rvu *rvu, struct npc_mcam *mcam,
+			 int blkaddr, int index, u64 cfg);
 void npc_read_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
 			 int blkaddr, u16 src, struct mcam_entry *entry,
 			 u8 *intf, u8 *ena);
@@ -904,6 +934,7 @@ u32  rvu_cgx_get_fifolen(struct rvu *rvu);
 void *rvu_first_cgx_pdata(struct rvu *rvu);
 int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id);
 int rvu_cgx_config_tx(void *cgxd, int lmac_id, bool enable);
+int rvu_cgx_tx_enable(struct rvu *rvu, u16 pcifunc, bool enable);
 int rvu_cgx_prio_flow_ctrl_cfg(struct rvu *rvu, u16 pcifunc, u8 tx_pause, u8 rx_pause,
 			       u16 pfc_en);
 int rvu_cgx_cfg_pause_frm(struct rvu *rvu, u16 pcifunc, u8 tx_pause, u8 rx_pause);
@@ -919,6 +950,8 @@ int npc_install_mcam_drop_rule(struct rvu *rvu, int mcam_idx, u16 *counter_idx,
 			       u64 bcast_mcast_val, u64 bcast_mcast_mask);
 void npc_mcam_rsrcs_reserve(struct rvu *rvu, int blkaddr, int entry_idx);
 bool npc_is_feature_supported(struct rvu *rvu, u64 features, u8 intf);
+int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr);
+void npc_mcam_rsrcs_deinit(struct rvu *rvu);
 
 /* CPT APIs */
 int rvu_cpt_register_interrupts(struct rvu *rvu);
@@ -940,6 +973,7 @@ void rvu_nix_block_cn10k_init(struct rvu *rvu, struct nix_hw *nix_hw);
 
 /* CN10K RVU - LMT*/
 void rvu_reset_lmt_map_tbl(struct rvu *rvu, u16 pcifunc);
+void rvu_apr_block_cn10k_init(struct rvu *rvu);
 
 #ifdef CONFIG_DEBUG_FS
 void rvu_dbg_init(struct rvu *rvu);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index 15a319684ed3..38acdc7a73bb 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -465,6 +465,23 @@ int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start)
 	return mac_ops->mac_rx_tx_enable(cgxd, lmac_id, start);
 }
 
+int rvu_cgx_tx_enable(struct rvu *rvu, u16 pcifunc, bool enable)
+{
+	int pf = rvu_get_pf(pcifunc);
+	struct mac_ops *mac_ops;
+	u8 cgx_id, lmac_id;
+	void *cgxd;
+
+	if (!is_cgx_config_permitted(rvu, pcifunc))
+		return LMAC_AF_ERR_PERM_DENIED;
+
+	rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
+	cgxd = rvu_cgx_pdata(cgx_id, rvu);
+	mac_ops = get_mac_ops(cgxd);
+
+	return mac_ops->mac_tx_enable(cgxd, lmac_id, enable);
+}
+
 int rvu_cgx_config_tx(void *cgxd, int lmac_id, bool enable)
 {
 	struct mac_ops *mac_ops;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
index 0e74c5a2231e..7fa98aeb3663 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
@@ -559,3 +559,12 @@ void rvu_nix_block_cn10k_init(struct rvu *rvu, struct nix_hw *nix_hw)
 	cfg |= BIT_ULL(1) | BIT_ULL(2);
 	rvu_write64(rvu, blkaddr, NIX_AF_CFG, cfg);
 }
+
+void rvu_apr_block_cn10k_init(struct rvu *rvu)
+{
+	u64 reg;
+
+	reg = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_CFG);
+	reg |=	FIELD_PREP(LMTST_THROTTLE_MASK, LMTST_WR_PEND_MAX);
+	rvu_write64(rvu, BLKADDR_APR, APR_AF_LMT_CFG, reg);
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index bd817ee88735..e6d7914ce61c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -1825,6 +1825,8 @@ static void print_nix_rq_ctx(struct seq_file *m, struct nix_aq_enq_rsp *rsp)
 static void print_nix_cq_ctx(struct seq_file *m, struct nix_aq_enq_rsp *rsp)
 {
 	struct nix_cq_ctx_s *cq_ctx = &rsp->cq;
+	struct nix_hw *nix_hw = m->private;
+	struct rvu *rvu = nix_hw->rvu;
 
 	seq_printf(m, "W0: base \t\t\t%llx\n\n", cq_ctx->base);
 
@@ -1836,6 +1838,16 @@ static void print_nix_cq_ctx(struct seq_file *m, struct nix_aq_enq_rsp *rsp)
 	seq_printf(m, "W1: bpid \t\t\t%d\nW1: bp_ena \t\t\t%d\n\n",
 		   cq_ctx->bpid, cq_ctx->bp_ena);
 
+	if (!is_rvu_otx2(rvu)) {
+		seq_printf(m, "W1: lbpid_high \t\t\t0x%03x\n", cq_ctx->lbpid_high);
+		seq_printf(m, "W1: lbpid_med \t\t\t0x%03x\n", cq_ctx->lbpid_med);
+		seq_printf(m, "W1: lbpid_low \t\t\t0x%03x\n", cq_ctx->lbpid_low);
+		seq_printf(m, "(W1: lbpid) \t\t\t0x%03x\n",
+			   cq_ctx->lbpid_high << 6 | cq_ctx->lbpid_med << 3 |
+			   cq_ctx->lbpid_low);
+		seq_printf(m, "W1: lbp_ena \t\t\t\t%d\n\n", cq_ctx->lbp_ena);
+	}
+
 	seq_printf(m, "W2: update_time \t\t%d\nW2:avg_level \t\t\t%d\n",
 		   cq_ctx->update_time, cq_ctx->avg_level);
 	seq_printf(m, "W2: head \t\t\t%d\nW2:tail \t\t\t%d\n\n",
@@ -1847,6 +1859,11 @@ static void print_nix_cq_ctx(struct seq_file *m, struct nix_aq_enq_rsp *rsp)
 		   cq_ctx->qsize, cq_ctx->caching);
 	seq_printf(m, "W3: substream \t\t\t0x%03x\nW3: ena \t\t\t%d\n",
 		   cq_ctx->substream, cq_ctx->ena);
+	if (!is_rvu_otx2(rvu)) {
+		seq_printf(m, "W3: lbp_frac \t\t\t%d\n", cq_ctx->lbp_frac);
+		seq_printf(m, "W3: cpt_drop_err_en \t\t\t%d\n",
+			   cq_ctx->cpt_drop_err_en);
+	}
 	seq_printf(m, "W3: drop_ena \t\t\t%d\nW3: drop \t\t\t%d\n",
 		   cq_ctx->drop_ena, cq_ctx->drop);
 	seq_printf(m, "W3: bp \t\t\t\t%d\n\n", cq_ctx->bp);
@@ -2889,6 +2906,14 @@ static void rvu_dbg_npc_mcam_show_flows(struct seq_file *s,
 			RVU_DBG_PRINT_MPLS_TTL(rule->packet.mpls_lse[3],
 					       rule->mask.mpls_lse[3]);
 			break;
+		case NPC_TYPE_ICMP:
+			seq_printf(s, "%d ", rule->packet.icmp_type);
+			seq_printf(s, "mask 0x%x\n", rule->mask.icmp_type);
+			break;
+		case NPC_CODE_ICMP:
+			seq_printf(s, "%d ", rule->packet.icmp_code);
+			seq_printf(s, "mask 0x%x\n", rule->mask.icmp_code);
+			break;
 		default:
 			seq_puts(s, "\n");
 			break;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
index c70932625d0d..1e6fbd98423d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
@@ -5,7 +5,7 @@
  *
  */
 
-#include<linux/bitfield.h>
+#include <linux/bitfield.h>
 
 #include "rvu.h"
 #include "rvu_reg.h"
@@ -538,7 +538,7 @@ static int rvu_nix_register_reporters(struct rvu_devlink *rvu_dl)
 
 	rvu_dl->devlink_wq = create_workqueue("rvu_devlink_wq");
 	if (!rvu_dl->devlink_wq)
-		goto err;
+		return -ENOMEM;
 
 	INIT_WORK(&rvu_reporters->intr_work, rvu_nix_intr_work);
 	INIT_WORK(&rvu_reporters->gen_work, rvu_nix_gen_work);
@@ -546,9 +546,6 @@ static int rvu_nix_register_reporters(struct rvu_devlink *rvu_dl)
 	INIT_WORK(&rvu_reporters->ras_work, rvu_nix_ras_work);
 
 	return 0;
-err:
-	rvu_nix_health_reporters_destroy(rvu_dl);
-	return -ENOMEM;
 }
 
 static int rvu_nix_health_reporters_create(struct rvu_devlink *rvu_dl)
@@ -1087,7 +1084,7 @@ static int rvu_npa_register_reporters(struct rvu_devlink *rvu_dl)
 
 	rvu_dl->devlink_wq = create_workqueue("rvu_devlink_wq");
 	if (!rvu_dl->devlink_wq)
-		goto err;
+		return -ENOMEM;
 
 	INIT_WORK(&rvu_reporters->intr_work, rvu_npa_intr_work);
 	INIT_WORK(&rvu_reporters->err_work, rvu_npa_err_work);
@@ -1095,9 +1092,6 @@ static int rvu_npa_register_reporters(struct rvu_devlink *rvu_dl)
 	INIT_WORK(&rvu_reporters->ras_work, rvu_npa_ras_work);
 
 	return 0;
-err:
-	rvu_npa_health_reporters_destroy(rvu_dl);
-	return -ENOMEM;
 }
 
 static int rvu_npa_health_reporters_create(struct rvu_devlink *rvu_dl)
@@ -1243,6 +1237,7 @@ enum rvu_af_dl_param_id {
 	RVU_AF_DEVLINK_PARAM_ID_DWRR_MTU,
 	RVU_AF_DEVLINK_PARAM_ID_NPC_EXACT_FEATURE_DISABLE,
 	RVU_AF_DEVLINK_PARAM_ID_NPC_MCAM_ZONE_PERCENT,
+	RVU_AF_DEVLINK_PARAM_ID_NIX_MAXLF,
 };
 
 static int rvu_af_npc_exact_feature_get(struct devlink *devlink, u32 id,
@@ -1360,6 +1355,79 @@ static int rvu_af_dl_npc_mcam_high_zone_percent_validate(struct devlink *devlink
 	return 0;
 }
 
+static int rvu_af_dl_nix_maxlf_get(struct devlink *devlink, u32 id,
+				   struct devlink_param_gset_ctx *ctx)
+{
+	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
+	struct rvu *rvu = rvu_dl->rvu;
+
+	ctx->val.vu16 = (u16)rvu_get_nixlf_count(rvu);
+
+	return 0;
+}
+
+static int rvu_af_dl_nix_maxlf_set(struct devlink *devlink, u32 id,
+				   struct devlink_param_gset_ctx *ctx)
+{
+	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
+	struct rvu *rvu = rvu_dl->rvu;
+	struct rvu_block *block;
+	int blkaddr = 0;
+
+	npc_mcam_rsrcs_deinit(rvu);
+	blkaddr = rvu_get_next_nix_blkaddr(rvu, blkaddr);
+	while (blkaddr) {
+		block = &rvu->hw->block[blkaddr];
+		block->lf.max = ctx->val.vu16;
+		blkaddr = rvu_get_next_nix_blkaddr(rvu, blkaddr);
+	}
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	npc_mcam_rsrcs_init(rvu, blkaddr);
+
+	return 0;
+}
+
+static int rvu_af_dl_nix_maxlf_validate(struct devlink *devlink, u32 id,
+					union devlink_param_value val,
+					struct netlink_ext_ack *extack)
+{
+	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
+	struct rvu *rvu = rvu_dl->rvu;
+	u16 max_nix0_lf, max_nix1_lf;
+	struct npc_mcam *mcam;
+	u64 cfg;
+
+	cfg = rvu_read64(rvu, BLKADDR_NIX0, NIX_AF_CONST2);
+	max_nix0_lf = cfg & 0xFFF;
+	cfg = rvu_read64(rvu, BLKADDR_NIX1, NIX_AF_CONST2);
+	max_nix1_lf = cfg & 0xFFF;
+
+	/* Do not allow user to modify maximum NIX LFs while mcam entries
+	 * have already been assigned.
+	 */
+	mcam = &rvu->hw->mcam;
+	if (mcam->bmap_fcnt < mcam->bmap_entries) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "mcam entries have already been assigned, can't resize");
+		return -EPERM;
+	}
+
+	if (max_nix0_lf && val.vu16 > max_nix0_lf) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "requested nixlf is greater than the max supported nix0_lf");
+		return -EPERM;
+	}
+
+	if (max_nix1_lf && val.vu16 > max_nix1_lf) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "requested nixlf is greater than the max supported nix1_lf");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct devlink_param rvu_af_dl_params[] = {
 	DEVLINK_PARAM_DRIVER(RVU_AF_DEVLINK_PARAM_ID_DWRR_MTU,
 			     "dwrr_mtu", DEVLINK_PARAM_TYPE_U32,
@@ -1381,6 +1449,12 @@ static const struct devlink_param rvu_af_dl_param_exact_match[] = {
 			     rvu_af_dl_npc_mcam_high_zone_percent_get,
 			     rvu_af_dl_npc_mcam_high_zone_percent_set,
 			     rvu_af_dl_npc_mcam_high_zone_percent_validate),
+	DEVLINK_PARAM_DRIVER(RVU_AF_DEVLINK_PARAM_ID_NIX_MAXLF,
+			     "nix_maxlf", DEVLINK_PARAM_TYPE_U16,
+			     BIT(DEVLINK_PARAM_CMODE_RUNTIME),
+			     rvu_af_dl_nix_maxlf_get,
+			     rvu_af_dl_nix_maxlf_set,
+			     rvu_af_dl_nix_maxlf_validate),
 };
 
 /* Devlink switch mode */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 23c2f2ed2fb8..66203a90f052 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -12,6 +12,7 @@
 #include "rvu_reg.h"
 #include "rvu.h"
 #include "npc.h"
+#include "mcs.h"
 #include "cgx.h"
 #include "lmac_common.h"
 #include "rvu_npc_hash.h"
@@ -71,12 +72,19 @@ enum nix_makr_fmt_indexes {
 /* For now considering MC resources needed for broadcast
  * pkt replication only. i.e 256 HWVFs + 12 PFs.
  */
-#define MC_TBL_SIZE	MC_TBL_SZ_512
-#define MC_BUF_CNT	MC_BUF_CNT_128
+#define MC_TBL_SIZE	MC_TBL_SZ_2K
+#define MC_BUF_CNT	MC_BUF_CNT_1024
+
+#define MC_TX_MAX	2048
 
 struct mce {
 	struct hlist_node	node;
+	u32			rq_rss_index;
 	u16			pcifunc;
+	u16			channel;
+	u8			dest_type;
+	u8			is_active;
+	u8			reserved[2];
 };
 
 int rvu_get_next_nix_blkaddr(struct rvu *rvu, int blkaddr)
@@ -164,18 +172,33 @@ static void nix_mce_list_init(struct nix_mce_list *list, int max)
 	list->max = max;
 }
 
-static u16 nix_alloc_mce_list(struct nix_mcast *mcast, int count)
+static int nix_alloc_mce_list(struct nix_mcast *mcast, int count, u8 dir)
 {
+	struct rsrc_bmap *mce_counter;
 	int idx;
 
 	if (!mcast)
-		return 0;
+		return -EINVAL;
 
-	idx = mcast->next_free_mce;
-	mcast->next_free_mce += count;
+	mce_counter = &mcast->mce_counter[dir];
+	if (!rvu_rsrc_check_contig(mce_counter, count))
+		return -ENOSPC;
+
+	idx = rvu_alloc_rsrc_contig(mce_counter, count);
 	return idx;
 }
 
+static void nix_free_mce_list(struct nix_mcast *mcast, int count, int start, u8 dir)
+{
+	struct rsrc_bmap *mce_counter;
+
+	if (!mcast)
+		return;
+
+	mce_counter = &mcast->mce_counter[dir];
+	rvu_free_rsrc_contig(mce_counter, count, start);
+}
+
 struct nix_hw *get_nix_hw(struct rvu_hwinfo *hw, int blkaddr)
 {
 	int nix_blkaddr = 0, i = 0;
@@ -2955,7 +2978,8 @@ int rvu_mbox_handler_nix_vtag_cfg(struct rvu *rvu,
 }
 
 static int nix_blk_setup_mce(struct rvu *rvu, struct nix_hw *nix_hw,
-			     int mce, u8 op, u16 pcifunc, int next, bool eol)
+			     int mce, u8 op, u16 pcifunc, int next,
+			     int index, u8 mce_op, bool eol)
 {
 	struct nix_aq_enq_req aq_req;
 	int err;
@@ -2966,8 +2990,8 @@ static int nix_blk_setup_mce(struct rvu *rvu, struct nix_hw *nix_hw,
 	aq_req.qidx = mce;
 
 	/* Use RSS with RSS index 0 */
-	aq_req.mce.op = 1;
-	aq_req.mce.index = 0;
+	aq_req.mce.op = mce_op;
+	aq_req.mce.index = index;
 	aq_req.mce.eol = eol;
 	aq_req.mce.pf_func = pcifunc;
 	aq_req.mce.next = next;
@@ -2984,6 +3008,206 @@ static int nix_blk_setup_mce(struct rvu *rvu, struct nix_hw *nix_hw,
 	return 0;
 }
 
+static void nix_delete_mcast_mce_list(struct nix_mce_list *mce_list)
+{
+	struct hlist_node *tmp;
+	struct mce *mce;
+
+	/* Scan through the current list */
+	hlist_for_each_entry_safe(mce, tmp, &mce_list->head, node) {
+		hlist_del(&mce->node);
+		kfree(mce);
+	}
+
+	mce_list->count = 0;
+	mce_list->max = 0;
+}
+
+static int nix_get_last_mce_list_index(struct nix_mcast_grp_elem *elem)
+{
+	return elem->mce_start_index + elem->mcast_mce_list.count - 1;
+}
+
+static int nix_update_ingress_mce_list_hw(struct rvu *rvu,
+					  struct nix_hw *nix_hw,
+					  struct nix_mcast_grp_elem *elem)
+{
+	int idx, last_idx, next_idx, err;
+	struct nix_mce_list *mce_list;
+	struct mce *mce, *prev_mce;
+
+	mce_list = &elem->mcast_mce_list;
+	idx = elem->mce_start_index;
+	last_idx = nix_get_last_mce_list_index(elem);
+	hlist_for_each_entry(mce, &mce_list->head, node) {
+		if (idx > last_idx)
+			break;
+
+		if (!mce->is_active) {
+			if (idx == elem->mce_start_index) {
+				idx++;
+				prev_mce = mce;
+				elem->mce_start_index = idx;
+				continue;
+			} else if (idx == last_idx) {
+				err = nix_blk_setup_mce(rvu, nix_hw, idx - 1, NIX_AQ_INSTOP_WRITE,
+							prev_mce->pcifunc, next_idx,
+							prev_mce->rq_rss_index,
+							prev_mce->dest_type,
+							false);
+				if (err)
+					return err;
+
+				break;
+			}
+		}
+
+		next_idx = idx + 1;
+		/* EOL should be set in last MCE */
+		err = nix_blk_setup_mce(rvu, nix_hw, idx, NIX_AQ_INSTOP_WRITE,
+					mce->pcifunc, next_idx,
+					mce->rq_rss_index, mce->dest_type,
+					(next_idx > last_idx) ? true : false);
+		if (err)
+			return err;
+
+		idx++;
+		prev_mce = mce;
+	}
+
+	return 0;
+}
+
+static void nix_update_egress_mce_list_hw(struct rvu *rvu,
+					  struct nix_hw *nix_hw,
+					  struct nix_mcast_grp_elem *elem)
+{
+	struct nix_mce_list *mce_list;
+	int idx, last_idx, next_idx;
+	struct mce *mce, *prev_mce;
+	u64 regval;
+	u8 eol;
+
+	mce_list = &elem->mcast_mce_list;
+	idx = elem->mce_start_index;
+	last_idx = nix_get_last_mce_list_index(elem);
+	hlist_for_each_entry(mce, &mce_list->head, node) {
+		if (idx > last_idx)
+			break;
+
+		if (!mce->is_active) {
+			if (idx == elem->mce_start_index) {
+				idx++;
+				prev_mce = mce;
+				elem->mce_start_index = idx;
+				continue;
+			} else if (idx == last_idx) {
+				regval = (next_idx << 16) | (1 << 12) | prev_mce->channel;
+				rvu_write64(rvu, nix_hw->blkaddr,
+					    NIX_AF_TX_MCASTX(idx - 1),
+					    regval);
+				break;
+			}
+		}
+
+		eol = 0;
+		next_idx = idx + 1;
+		/* EOL should be set in last MCE */
+		if (next_idx > last_idx)
+			eol = 1;
+
+		regval = (next_idx << 16) | (eol << 12) | mce->channel;
+		rvu_write64(rvu, nix_hw->blkaddr,
+			    NIX_AF_TX_MCASTX(idx),
+			    regval);
+		idx++;
+		prev_mce = mce;
+	}
+}
+
+static int nix_del_mce_list_entry(struct rvu *rvu,
+				  struct nix_hw *nix_hw,
+				  struct nix_mcast_grp_elem *elem,
+				  struct nix_mcast_grp_update_req *req)
+{
+	u32 num_entry = req->num_mce_entry;
+	struct nix_mce_list *mce_list;
+	struct mce *mce;
+	bool is_found;
+	int i;
+
+	mce_list = &elem->mcast_mce_list;
+	for (i = 0; i < num_entry; i++) {
+		is_found = false;
+		hlist_for_each_entry(mce, &mce_list->head, node) {
+			/* If already exists, then delete */
+			if (mce->pcifunc == req->pcifunc[i]) {
+				hlist_del(&mce->node);
+				kfree(mce);
+				mce_list->count--;
+				is_found = true;
+				break;
+			}
+		}
+
+		if (!is_found)
+			return NIX_AF_ERR_INVALID_MCAST_DEL_REQ;
+	}
+
+	mce_list->max = mce_list->count;
+	/* Dump the updated list to HW */
+	if (elem->dir == NIX_MCAST_INGRESS)
+		return nix_update_ingress_mce_list_hw(rvu, nix_hw, elem);
+
+	nix_update_egress_mce_list_hw(rvu, nix_hw, elem);
+	return 0;
+}
+
+static int nix_add_mce_list_entry(struct rvu *rvu,
+				  struct nix_hw *nix_hw,
+				  struct nix_mcast_grp_elem *elem,
+				  struct nix_mcast_grp_update_req *req)
+{
+	u32 num_entry = req->num_mce_entry;
+	struct nix_mce_list *mce_list;
+	struct hlist_node *tmp;
+	struct mce *mce;
+	int i;
+
+	mce_list = &elem->mcast_mce_list;
+	for (i = 0; i < num_entry; i++) {
+		mce = kzalloc(sizeof(*mce), GFP_KERNEL);
+		if (!mce)
+			goto free_mce;
+
+		mce->pcifunc = req->pcifunc[i];
+		mce->channel = req->channel[i];
+		mce->rq_rss_index = req->rq_rss_index[i];
+		mce->dest_type = req->dest_type[i];
+		mce->is_active = 1;
+		hlist_add_head(&mce->node, &mce_list->head);
+		mce_list->count++;
+	}
+
+	mce_list->max += num_entry;
+
+	/* Dump the updated list to HW */
+	if (elem->dir == NIX_MCAST_INGRESS)
+		return nix_update_ingress_mce_list_hw(rvu, nix_hw, elem);
+
+	nix_update_egress_mce_list_hw(rvu, nix_hw, elem);
+	return 0;
+
+free_mce:
+	hlist_for_each_entry_safe(mce, tmp, &mce_list->head, node) {
+		hlist_del(&mce->node);
+		kfree(mce);
+		mce_list->count--;
+	}
+
+	return -ENOMEM;
+}
+
 static int nix_update_mce_list_entry(struct nix_mce_list *mce_list,
 				     u16 pcifunc, bool add)
 {
@@ -3079,6 +3303,7 @@ int nix_update_mce_list(struct rvu *rvu, u16 pcifunc,
 		/* EOL should be set in last MCE */
 		err = nix_blk_setup_mce(rvu, nix_hw, idx, NIX_AQ_INSTOP_WRITE,
 					mce->pcifunc, next_idx,
+					0, 1,
 					(next_idx > last_idx) ? true : false);
 		if (err)
 			goto end;
@@ -3159,6 +3384,16 @@ static int nix_update_mce_rule(struct rvu *rvu, u16 pcifunc,
 	return err;
 }
 
+static void nix_setup_mcast_grp(struct nix_hw *nix_hw)
+{
+	struct nix_mcast_grp *mcast_grp = &nix_hw->mcast_grp;
+
+	INIT_LIST_HEAD(&mcast_grp->mcast_grp_head);
+	mutex_init(&mcast_grp->mcast_grp_lock);
+	mcast_grp->next_grp_index = 1;
+	mcast_grp->count = 0;
+}
+
 static int nix_setup_mce_tables(struct rvu *rvu, struct nix_hw *nix_hw)
 {
 	struct nix_mcast *mcast = &nix_hw->mcast;
@@ -3183,15 +3418,15 @@ static int nix_setup_mce_tables(struct rvu *rvu, struct nix_hw *nix_hw)
 			continue;
 
 		/* save start idx of broadcast mce list */
-		pfvf->bcast_mce_idx = nix_alloc_mce_list(mcast, numvfs + 1);
+		pfvf->bcast_mce_idx = nix_alloc_mce_list(mcast, numvfs + 1, NIX_MCAST_INGRESS);
 		nix_mce_list_init(&pfvf->bcast_mce_list, numvfs + 1);
 
 		/* save start idx of multicast mce list */
-		pfvf->mcast_mce_idx = nix_alloc_mce_list(mcast, numvfs + 1);
+		pfvf->mcast_mce_idx = nix_alloc_mce_list(mcast, numvfs + 1, NIX_MCAST_INGRESS);
 		nix_mce_list_init(&pfvf->mcast_mce_list, numvfs + 1);
 
 		/* save the start idx of promisc mce list */
-		pfvf->promisc_mce_idx = nix_alloc_mce_list(mcast, numvfs + 1);
+		pfvf->promisc_mce_idx = nix_alloc_mce_list(mcast, numvfs + 1, NIX_MCAST_INGRESS);
 		nix_mce_list_init(&pfvf->promisc_mce_list, numvfs + 1);
 
 		for (idx = 0; idx < (numvfs + 1); idx++) {
@@ -3206,7 +3441,7 @@ static int nix_setup_mce_tables(struct rvu *rvu, struct nix_hw *nix_hw)
 			err = nix_blk_setup_mce(rvu, nix_hw,
 						pfvf->bcast_mce_idx + idx,
 						NIX_AQ_INSTOP_INIT,
-						pcifunc, 0, true);
+						pcifunc, 0, 0, 1, true);
 			if (err)
 				return err;
 
@@ -3214,7 +3449,7 @@ static int nix_setup_mce_tables(struct rvu *rvu, struct nix_hw *nix_hw)
 			err = nix_blk_setup_mce(rvu, nix_hw,
 						pfvf->mcast_mce_idx + idx,
 						NIX_AQ_INSTOP_INIT,
-						pcifunc, 0, true);
+						pcifunc, 0, 0, 1, true);
 			if (err)
 				return err;
 
@@ -3222,7 +3457,7 @@ static int nix_setup_mce_tables(struct rvu *rvu, struct nix_hw *nix_hw)
 			err = nix_blk_setup_mce(rvu, nix_hw,
 						pfvf->promisc_mce_idx + idx,
 						NIX_AQ_INSTOP_INIT,
-						pcifunc, 0, true);
+						pcifunc, 0, 0, 1, true);
 			if (err)
 				return err;
 		}
@@ -3237,13 +3472,30 @@ static int nix_setup_mcast(struct rvu *rvu, struct nix_hw *nix_hw, int blkaddr)
 	int err, size;
 
 	size = (rvu_read64(rvu, blkaddr, NIX_AF_CONST3) >> 16) & 0x0F;
-	size = (1ULL << size);
+	size = BIT_ULL(size);
+
+	/* Allocate bitmap for rx mce entries */
+	mcast->mce_counter[NIX_MCAST_INGRESS].max = 256UL << MC_TBL_SIZE;
+	err = rvu_alloc_bitmap(&mcast->mce_counter[NIX_MCAST_INGRESS]);
+	if (err)
+		return -ENOMEM;
+
+	/* Allocate bitmap for tx mce entries */
+	mcast->mce_counter[NIX_MCAST_EGRESS].max = MC_TX_MAX;
+	err = rvu_alloc_bitmap(&mcast->mce_counter[NIX_MCAST_EGRESS]);
+	if (err) {
+		rvu_free_bitmap(&mcast->mce_counter[NIX_MCAST_INGRESS]);
+		return -ENOMEM;
+	}
 
 	/* Alloc memory for multicast/mirror replication entries */
 	err = qmem_alloc(rvu->dev, &mcast->mce_ctx,
-			 (256UL << MC_TBL_SIZE), size);
-	if (err)
+			 mcast->mce_counter[NIX_MCAST_INGRESS].max, size);
+	if (err) {
+		rvu_free_bitmap(&mcast->mce_counter[NIX_MCAST_INGRESS]);
+		rvu_free_bitmap(&mcast->mce_counter[NIX_MCAST_EGRESS]);
 		return -ENOMEM;
+	}
 
 	rvu_write64(rvu, blkaddr, NIX_AF_RX_MCAST_BASE,
 		    (u64)mcast->mce_ctx->iova);
@@ -3256,8 +3508,11 @@ static int nix_setup_mcast(struct rvu *rvu, struct nix_hw *nix_hw, int blkaddr)
 	size = rvu_read64(rvu, blkaddr, NIX_AF_MC_MIRROR_CONST) & 0xFFFF;
 	err = qmem_alloc(rvu->dev, &mcast->mcast_buf,
 			 (8UL << MC_BUF_CNT), size);
-	if (err)
+	if (err) {
+		rvu_free_bitmap(&mcast->mce_counter[NIX_MCAST_INGRESS]);
+		rvu_free_bitmap(&mcast->mce_counter[NIX_MCAST_EGRESS]);
 		return -ENOMEM;
+	}
 
 	rvu_write64(rvu, blkaddr, NIX_AF_RX_MCAST_BUF_BASE,
 		    (u64)mcast->mcast_buf->iova);
@@ -3271,6 +3526,8 @@ static int nix_setup_mcast(struct rvu *rvu, struct nix_hw *nix_hw, int blkaddr)
 
 	mutex_init(&mcast->mce_lock);
 
+	nix_setup_mcast_grp(nix_hw);
+
 	return nix_setup_mce_tables(rvu, nix_hw);
 }
 
@@ -4142,90 +4399,18 @@ static void nix_find_link_frs(struct rvu *rvu,
 		req->minlen = minlen;
 }
 
-static int
-nix_config_link_credits(struct rvu *rvu, int blkaddr, int link,
-			u16 pcifunc, u64 tx_credits)
-{
-	struct rvu_hwinfo *hw = rvu->hw;
-	int pf = rvu_get_pf(pcifunc);
-	u8 cgx_id = 0, lmac_id = 0;
-	unsigned long poll_tmo;
-	bool restore_tx_en = 0;
-	struct nix_hw *nix_hw;
-	u64 cfg, sw_xoff = 0;
-	u32 schq = 0;
-	u32 credits;
-	int rc;
-
-	nix_hw = get_nix_hw(rvu->hw, blkaddr);
-	if (!nix_hw)
-		return NIX_AF_ERR_INVALID_NIXBLK;
-
-	if (tx_credits == nix_hw->tx_credits[link])
-		return 0;
-
-	/* Enable cgx tx if disabled for credits to be back */
-	if (is_pf_cgxmapped(rvu, pf)) {
-		rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
-		restore_tx_en = !rvu_cgx_config_tx(rvu_cgx_pdata(cgx_id, rvu),
-						    lmac_id, true);
-	}
-
-	mutex_lock(&rvu->rsrc_lock);
-	/* Disable new traffic to link */
-	if (hw->cap.nix_shaping) {
-		schq = nix_get_tx_link(rvu, pcifunc);
-		sw_xoff = rvu_read64(rvu, blkaddr, NIX_AF_TL1X_SW_XOFF(schq));
-		rvu_write64(rvu, blkaddr,
-			    NIX_AF_TL1X_SW_XOFF(schq), BIT_ULL(0));
-	}
-
-	rc = NIX_AF_ERR_LINK_CREDITS;
-	poll_tmo = jiffies + usecs_to_jiffies(200000);
-	/* Wait for credits to return */
-	do {
-		if (time_after(jiffies, poll_tmo))
-			goto exit;
-		usleep_range(100, 200);
-
-		cfg = rvu_read64(rvu, blkaddr,
-				 NIX_AF_TX_LINKX_NORM_CREDIT(link));
-		credits = (cfg >> 12) & 0xFFFFFULL;
-	} while (credits != nix_hw->tx_credits[link]);
-
-	cfg &= ~(0xFFFFFULL << 12);
-	cfg |= (tx_credits << 12);
-	rvu_write64(rvu, blkaddr, NIX_AF_TX_LINKX_NORM_CREDIT(link), cfg);
-	rc = 0;
-
-	nix_hw->tx_credits[link] = tx_credits;
-
-exit:
-	/* Enable traffic back */
-	if (hw->cap.nix_shaping && !sw_xoff)
-		rvu_write64(rvu, blkaddr, NIX_AF_TL1X_SW_XOFF(schq), 0);
-
-	/* Restore state of cgx tx */
-	if (restore_tx_en)
-		rvu_cgx_config_tx(rvu_cgx_pdata(cgx_id, rvu), lmac_id, false);
-
-	mutex_unlock(&rvu->rsrc_lock);
-	return rc;
-}
-
 int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req,
 				    struct msg_rsp *rsp)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
 	u16 pcifunc = req->hdr.pcifunc;
 	int pf = rvu_get_pf(pcifunc);
-	int blkaddr, schq, link = -1;
-	struct nix_txsch *txsch;
-	u64 cfg, lmac_fifo_len;
+	int blkaddr, link = -1;
 	struct nix_hw *nix_hw;
 	struct rvu_pfvf *pfvf;
 	u8 cgx = 0, lmac = 0;
 	u16 max_mtu;
+	u64 cfg;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
 	if (blkaddr < 0)
@@ -4246,25 +4431,6 @@ int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req,
 	if (req->update_minlen && req->minlen < NIC_HW_MIN_FRS)
 		return NIX_AF_ERR_FRS_INVALID;
 
-	/* Check if requester wants to update SMQ's */
-	if (!req->update_smq)
-		goto rx_frscfg;
-
-	/* Update min/maxlen in each of the SMQ attached to this PF/VF */
-	txsch = &nix_hw->txsch[NIX_TXSCH_LVL_SMQ];
-	mutex_lock(&rvu->rsrc_lock);
-	for (schq = 0; schq < txsch->schq.max; schq++) {
-		if (TXSCH_MAP_FUNC(txsch->pfvf_map[schq]) != pcifunc)
-			continue;
-		cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq));
-		cfg = (cfg & ~(0xFFFFULL << 8)) | ((u64)req->maxlen << 8);
-		if (req->update_minlen)
-			cfg = (cfg & ~0x7FULL) | ((u64)req->minlen & 0x7F);
-		rvu_write64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq), cfg);
-	}
-	mutex_unlock(&rvu->rsrc_lock);
-
-rx_frscfg:
 	/* Check if config is for SDP link */
 	if (req->sdp_link) {
 		if (!hw->sdp_links)
@@ -4287,7 +4453,6 @@ rx_frscfg:
 	if (link < 0)
 		return NIX_AF_ERR_RX_LINK_INVALID;
 
-
 linkcfg:
 	nix_find_link_frs(rvu, req, pcifunc);
 
@@ -4297,19 +4462,7 @@ linkcfg:
 		cfg = (cfg & ~0xFFFFULL) | req->minlen;
 	rvu_write64(rvu, blkaddr, NIX_AF_RX_LINKX_CFG(link), cfg);
 
-	if (req->sdp_link || pf == 0)
-		return 0;
-
-	/* Update transmit credits for CGX links */
-	lmac_fifo_len = rvu_cgx_get_lmac_fifolen(rvu, cgx, lmac);
-	if (!lmac_fifo_len) {
-		dev_err(rvu->dev,
-			"%s: Failed to get CGX/RPM%d:LMAC%d FIFO size\n",
-			__func__, cgx, lmac);
-		return 0;
-	}
-	return nix_config_link_credits(rvu, blkaddr, link, pcifunc,
-				       (lmac_fifo_len - req->maxlen) / 16);
+	return 0;
 }
 
 int rvu_mbox_handler_nix_set_rx_cfg(struct rvu *rvu, struct nix_rx_cfg *req,
@@ -4389,6 +4542,12 @@ static void nix_link_config(struct rvu *rvu, int blkaddr,
 			    SDP_HW_MAX_FRS << 16 | NIC_HW_MIN_FRS);
 	}
 
+	/* Get MCS external bypass status for CN10K-B */
+	if (mcs_get_blkcnt() == 1) {
+		/* Adjust for 2 credits when external bypass is disabled */
+		nix_hw->cc_mcs_cnt = is_mcs_bypass(0) ? 0 : 2;
+	}
+
 	/* Set credits for Tx links assuming max packet length allowed.
 	 * This will be reconfigured based on MTU set for PF/VF.
 	 */
@@ -4412,6 +4571,7 @@ static void nix_link_config(struct rvu *rvu, int blkaddr,
 			tx_credits = (lmac_fifo_len - lmac_max_frs) / 16;
 			/* Enable credits and set credit pkt count to max allowed */
 			cfg =  (tx_credits << 12) | (0x1FF << 2) | BIT_ULL(1);
+			cfg |= FIELD_PREP(NIX_AF_LINKX_MCS_CNT_MASK, nix_hw->cc_mcs_cnt);
 
 			link = iter + slink;
 			nix_hw->tx_credits[link] = tx_credits;
@@ -4794,6 +4954,74 @@ void rvu_nix_freemem(struct rvu *rvu)
 	}
 }
 
+static void nix_mcast_update_action(struct rvu *rvu,
+				    struct nix_mcast_grp_elem *elem)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	struct nix_rx_action rx_action = { 0 };
+	struct nix_tx_action tx_action = { 0 };
+	int npc_blkaddr;
+
+	npc_blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (elem->dir == NIX_MCAST_INGRESS) {
+		*(u64 *)&rx_action = npc_get_mcam_action(rvu, mcam,
+							 npc_blkaddr,
+							 elem->mcam_index);
+		rx_action.index = elem->mce_start_index;
+		npc_set_mcam_action(rvu, mcam, npc_blkaddr, elem->mcam_index,
+				    *(u64 *)&rx_action);
+	} else {
+		*(u64 *)&tx_action = npc_get_mcam_action(rvu, mcam,
+							 npc_blkaddr,
+							 elem->mcam_index);
+		tx_action.index = elem->mce_start_index;
+		npc_set_mcam_action(rvu, mcam, npc_blkaddr, elem->mcam_index,
+				    *(u64 *)&tx_action);
+	}
+}
+
+static void nix_mcast_update_mce_entry(struct rvu *rvu, u16 pcifunc, u8 is_active)
+{
+	struct nix_mcast_grp_elem *elem;
+	struct nix_mcast_grp *mcast_grp;
+	struct nix_hw *nix_hw;
+	int blkaddr;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	nix_hw = get_nix_hw(rvu->hw, blkaddr);
+	if (!nix_hw)
+		return;
+
+	mcast_grp = &nix_hw->mcast_grp;
+
+	mutex_lock(&mcast_grp->mcast_grp_lock);
+	list_for_each_entry(elem, &mcast_grp->mcast_grp_head, list) {
+		struct nix_mce_list *mce_list;
+		struct mce *mce;
+
+		/* Iterate the group elements and disable the element which
+		 * received the disable request.
+		 */
+		mce_list = &elem->mcast_mce_list;
+		hlist_for_each_entry(mce, &mce_list->head, node) {
+			if (mce->pcifunc == pcifunc) {
+				mce->is_active = is_active;
+				break;
+			}
+		}
+
+		/* Dump the updated list to HW */
+		if (elem->dir == NIX_MCAST_INGRESS)
+			nix_update_ingress_mce_list_hw(rvu, nix_hw, elem);
+		else
+			nix_update_egress_mce_list_hw(rvu, nix_hw, elem);
+
+		/* Update the multicast index in NPC rule */
+		nix_mcast_update_action(rvu, elem);
+	}
+	mutex_unlock(&mcast_grp->mcast_grp_lock);
+}
+
 int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req,
 				     struct msg_rsp *rsp)
 {
@@ -4805,6 +5033,9 @@ int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req,
 	if (err)
 		return err;
 
+	/* Enable the interface if it is in any multicast list */
+	nix_mcast_update_mce_entry(rvu, pcifunc, 1);
+
 	rvu_npc_enable_default_entries(rvu, pcifunc, nixlf);
 
 	npc_mcam_enable_flows(rvu, pcifunc);
@@ -4829,11 +5060,20 @@ int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req,
 		return err;
 
 	rvu_npc_disable_mcam_entries(rvu, pcifunc, nixlf);
+	/* Disable the interface if it is in any multicast list */
+	nix_mcast_update_mce_entry(rvu, pcifunc, 0);
+
 
 	pfvf = rvu_get_pfvf(rvu, pcifunc);
 	clear_bit(NIXLF_INITIALIZED, &pfvf->flags);
 
-	return rvu_cgx_start_stop_io(rvu, pcifunc, false);
+	err = rvu_cgx_start_stop_io(rvu, pcifunc, false);
+	if (err)
+		return err;
+
+	rvu_cgx_tx_enable(rvu, pcifunc, true);
+
+	return 0;
 }
 
 #define RX_SA_BASE  GENMASK_ULL(52, 7)
@@ -5505,6 +5745,8 @@ int rvu_mbox_handler_nix_bandprof_free(struct rvu *rvu,
 
 		ipolicer = &nix_hw->ipolicer[layer];
 		for (idx = 0; idx < req->prof_count[layer]; idx++) {
+			if (idx == MAX_BANDPROF_PER_PFFUNC)
+				break;
 			prof_idx = req->prof_idx[layer][idx];
 			if (prof_idx >= ipolicer->band_prof.max ||
 			    ipolicer->pfvf_map[prof_idx] != pcifunc)
@@ -5518,8 +5760,6 @@ int rvu_mbox_handler_nix_bandprof_free(struct rvu *rvu,
 			ipolicer->pfvf_map[prof_idx] = 0x00;
 			ipolicer->match_id[prof_idx] = 0;
 			rvu_free_rsrc(&ipolicer->band_prof, prof_idx);
-			if (idx == MAX_BANDPROF_PER_PFFUNC)
-				break;
 		}
 	}
 	mutex_unlock(&rvu->rsrc_lock);
@@ -5797,3 +6037,361 @@ int rvu_mbox_handler_nix_bandprof_get_hwinfo(struct rvu *rvu, struct msg_req *re
 
 	return 0;
 }
+
+static struct nix_mcast_grp_elem *rvu_nix_mcast_find_grp_elem(struct nix_mcast_grp *mcast_grp,
+							      u32 mcast_grp_idx)
+{
+	struct nix_mcast_grp_elem *iter;
+	bool is_found = false;
+
+	list_for_each_entry(iter, &mcast_grp->mcast_grp_head, list) {
+		if (iter->mcast_grp_idx == mcast_grp_idx) {
+			is_found = true;
+			break;
+		}
+	}
+
+	if (is_found)
+		return iter;
+
+	return NULL;
+}
+
+int rvu_nix_mcast_get_mce_index(struct rvu *rvu, u16 pcifunc, u32 mcast_grp_idx)
+{
+	struct nix_mcast_grp_elem *elem;
+	struct nix_mcast_grp *mcast_grp;
+	struct nix_hw *nix_hw;
+	int blkaddr, ret;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	nix_hw = get_nix_hw(rvu->hw, blkaddr);
+	if (!nix_hw)
+		return NIX_AF_ERR_INVALID_NIXBLK;
+
+	mcast_grp = &nix_hw->mcast_grp;
+	mutex_lock(&mcast_grp->mcast_grp_lock);
+	elem = rvu_nix_mcast_find_grp_elem(mcast_grp, mcast_grp_idx);
+	if (!elem)
+		ret = NIX_AF_ERR_INVALID_MCAST_GRP;
+	else
+		ret = elem->mce_start_index;
+
+	mutex_unlock(&mcast_grp->mcast_grp_lock);
+	return ret;
+}
+
+void rvu_nix_mcast_flr_free_entries(struct rvu *rvu, u16 pcifunc)
+{
+	struct nix_mcast_grp_destroy_req dreq = { 0 };
+	struct nix_mcast_grp_update_req ureq = { 0 };
+	struct nix_mcast_grp_update_rsp ursp = { 0 };
+	struct nix_mcast_grp_elem *elem, *tmp;
+	struct nix_mcast_grp *mcast_grp;
+	struct nix_hw *nix_hw;
+	int blkaddr;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	nix_hw = get_nix_hw(rvu->hw, blkaddr);
+	if (!nix_hw)
+		return;
+
+	mcast_grp = &nix_hw->mcast_grp;
+
+	mutex_lock(&mcast_grp->mcast_grp_lock);
+	list_for_each_entry_safe(elem, tmp, &mcast_grp->mcast_grp_head, list) {
+		struct nix_mce_list *mce_list;
+		struct hlist_node *tmp;
+		struct mce *mce;
+
+		/* If the pcifunc which created the multicast/mirror
+		 * group received an FLR, then delete the entire group.
+		 */
+		if (elem->pcifunc == pcifunc) {
+			/* Delete group */
+			dreq.hdr.pcifunc = elem->pcifunc;
+			dreq.mcast_grp_idx = elem->mcast_grp_idx;
+			dreq.is_af = 1;
+			rvu_mbox_handler_nix_mcast_grp_destroy(rvu, &dreq, NULL);
+			continue;
+		}
+
+		/* Iterate the group elements and delete the element which
+		 * received the FLR.
+		 */
+		mce_list = &elem->mcast_mce_list;
+		hlist_for_each_entry_safe(mce, tmp, &mce_list->head, node) {
+			if (mce->pcifunc == pcifunc) {
+				ureq.hdr.pcifunc = pcifunc;
+				ureq.num_mce_entry = 1;
+				ureq.mcast_grp_idx = elem->mcast_grp_idx;
+				ureq.op = NIX_MCAST_OP_DEL_ENTRY;
+				ureq.pcifunc[0] = pcifunc;
+				ureq.is_af = 1;
+				rvu_mbox_handler_nix_mcast_grp_update(rvu, &ureq, &ursp);
+				break;
+			}
+		}
+	}
+	mutex_unlock(&mcast_grp->mcast_grp_lock);
+}
+
+int rvu_nix_mcast_update_mcam_entry(struct rvu *rvu, u16 pcifunc,
+				    u32 mcast_grp_idx, u16 mcam_index)
+{
+	struct nix_mcast_grp_elem *elem;
+	struct nix_mcast_grp *mcast_grp;
+	struct nix_hw *nix_hw;
+	int blkaddr, ret = 0;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	nix_hw = get_nix_hw(rvu->hw, blkaddr);
+	if (!nix_hw)
+		return NIX_AF_ERR_INVALID_NIXBLK;
+
+	mcast_grp = &nix_hw->mcast_grp;
+	mutex_lock(&mcast_grp->mcast_grp_lock);
+	elem = rvu_nix_mcast_find_grp_elem(mcast_grp, mcast_grp_idx);
+	if (!elem)
+		ret = NIX_AF_ERR_INVALID_MCAST_GRP;
+	else
+		elem->mcam_index = mcam_index;
+
+	mutex_unlock(&mcast_grp->mcast_grp_lock);
+	return ret;
+}
+
+int rvu_mbox_handler_nix_mcast_grp_create(struct rvu *rvu,
+					  struct nix_mcast_grp_create_req *req,
+					  struct nix_mcast_grp_create_rsp *rsp)
+{
+	struct nix_mcast_grp_elem *elem;
+	struct nix_mcast_grp *mcast_grp;
+	struct nix_hw *nix_hw;
+	int blkaddr, err;
+
+	err = nix_get_struct_ptrs(rvu, req->hdr.pcifunc, &nix_hw, &blkaddr);
+	if (err)
+		return err;
+
+	mcast_grp = &nix_hw->mcast_grp;
+	elem = kzalloc(sizeof(*elem), GFP_KERNEL);
+	if (!elem)
+		return -ENOMEM;
+
+	INIT_HLIST_HEAD(&elem->mcast_mce_list.head);
+	elem->mcam_index = -1;
+	elem->mce_start_index = -1;
+	elem->pcifunc = req->hdr.pcifunc;
+	elem->dir = req->dir;
+	elem->mcast_grp_idx = mcast_grp->next_grp_index++;
+
+	mutex_lock(&mcast_grp->mcast_grp_lock);
+	list_add_tail(&elem->list, &mcast_grp->mcast_grp_head);
+	mcast_grp->count++;
+	mutex_unlock(&mcast_grp->mcast_grp_lock);
+
+	rsp->mcast_grp_idx = elem->mcast_grp_idx;
+	return 0;
+}
+
+int rvu_mbox_handler_nix_mcast_grp_destroy(struct rvu *rvu,
+					   struct nix_mcast_grp_destroy_req *req,
+					   struct msg_rsp *rsp)
+{
+	struct npc_delete_flow_req uninstall_req = { 0 };
+	struct npc_delete_flow_rsp uninstall_rsp = { 0 };
+	struct nix_mcast_grp_elem *elem;
+	struct nix_mcast_grp *mcast_grp;
+	int blkaddr, err, ret = 0;
+	struct nix_mcast *mcast;
+	struct nix_hw *nix_hw;
+
+	err = nix_get_struct_ptrs(rvu, req->hdr.pcifunc, &nix_hw, &blkaddr);
+	if (err)
+		return err;
+
+	mcast_grp = &nix_hw->mcast_grp;
+
+	/* If AF is requesting for the deletion,
+	 * then AF is already taking the lock
+	 */
+	if (!req->is_af)
+		mutex_lock(&mcast_grp->mcast_grp_lock);
+
+	elem = rvu_nix_mcast_find_grp_elem(mcast_grp, req->mcast_grp_idx);
+	if (!elem) {
+		ret = NIX_AF_ERR_INVALID_MCAST_GRP;
+		goto unlock_grp;
+	}
+
+	/* If no mce entries are associated with the group
+	 * then just remove it from the global list.
+	 */
+	if (!elem->mcast_mce_list.count)
+		goto delete_grp;
+
+	/* Delete the associated mcam entry and
+	 * remove all mce entries from the group
+	 */
+	mcast = &nix_hw->mcast;
+	mutex_lock(&mcast->mce_lock);
+	if (elem->mcam_index != -1) {
+		uninstall_req.hdr.pcifunc = req->hdr.pcifunc;
+		uninstall_req.entry = elem->mcam_index;
+		rvu_mbox_handler_npc_delete_flow(rvu, &uninstall_req, &uninstall_rsp);
+	}
+
+	nix_free_mce_list(mcast, elem->mcast_mce_list.count,
+			  elem->mce_start_index, elem->dir);
+	nix_delete_mcast_mce_list(&elem->mcast_mce_list);
+	mutex_unlock(&mcast->mce_lock);
+
+delete_grp:
+	list_del(&elem->list);
+	kfree(elem);
+	mcast_grp->count--;
+
+unlock_grp:
+	if (!req->is_af)
+		mutex_unlock(&mcast_grp->mcast_grp_lock);
+
+	return ret;
+}
+
+int rvu_mbox_handler_nix_mcast_grp_update(struct rvu *rvu,
+					  struct nix_mcast_grp_update_req *req,
+					  struct nix_mcast_grp_update_rsp *rsp)
+{
+	struct nix_mcast_grp_destroy_req dreq = { 0 };
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	struct nix_mcast_grp_elem *elem;
+	struct nix_mcast_grp *mcast_grp;
+	int blkaddr, err, npc_blkaddr;
+	u16 prev_count, new_count;
+	struct nix_mcast *mcast;
+	struct nix_hw *nix_hw;
+	int i, ret;
+
+	if (!req->num_mce_entry)
+		return 0;
+
+	err = nix_get_struct_ptrs(rvu, req->hdr.pcifunc, &nix_hw, &blkaddr);
+	if (err)
+		return err;
+
+	mcast_grp = &nix_hw->mcast_grp;
+
+	/* If AF is requesting for the updation,
+	 * then AF is already taking the lock
+	 */
+	if (!req->is_af)
+		mutex_lock(&mcast_grp->mcast_grp_lock);
+
+	elem = rvu_nix_mcast_find_grp_elem(mcast_grp, req->mcast_grp_idx);
+	if (!elem) {
+		ret = NIX_AF_ERR_INVALID_MCAST_GRP;
+		goto unlock_grp;
+	}
+
+	/* If any pcifunc matches the group's pcifunc, then we can
+	 * delete the entire group.
+	 */
+	if (req->op == NIX_MCAST_OP_DEL_ENTRY) {
+		for (i = 0; i < req->num_mce_entry; i++) {
+			if (elem->pcifunc == req->pcifunc[i]) {
+				/* Delete group */
+				dreq.hdr.pcifunc = elem->pcifunc;
+				dreq.mcast_grp_idx = elem->mcast_grp_idx;
+				dreq.is_af = 1;
+				rvu_mbox_handler_nix_mcast_grp_destroy(rvu, &dreq, NULL);
+				ret = 0;
+				goto unlock_grp;
+			}
+		}
+	}
+
+	mcast = &nix_hw->mcast;
+	mutex_lock(&mcast->mce_lock);
+	npc_blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (elem->mcam_index != -1)
+		npc_enable_mcam_entry(rvu, mcam, npc_blkaddr, elem->mcam_index, false);
+
+	prev_count = elem->mcast_mce_list.count;
+	if (req->op == NIX_MCAST_OP_ADD_ENTRY) {
+		new_count = prev_count + req->num_mce_entry;
+		if (prev_count)
+			nix_free_mce_list(mcast, prev_count, elem->mce_start_index, elem->dir);
+
+		elem->mce_start_index = nix_alloc_mce_list(mcast, new_count, elem->dir);
+
+		/* It is possible not to get contiguous memory */
+		if (elem->mce_start_index < 0) {
+			if (elem->mcam_index != -1) {
+				npc_enable_mcam_entry(rvu, mcam, npc_blkaddr,
+						      elem->mcam_index, true);
+				ret = NIX_AF_ERR_NON_CONTIG_MCE_LIST;
+				goto unlock_mce;
+			}
+		}
+
+		ret = nix_add_mce_list_entry(rvu, nix_hw, elem, req);
+		if (ret) {
+			nix_free_mce_list(mcast, new_count, elem->mce_start_index, elem->dir);
+			if (prev_count)
+				elem->mce_start_index = nix_alloc_mce_list(mcast,
+									   prev_count,
+									   elem->dir);
+
+			if (elem->mcam_index != -1)
+				npc_enable_mcam_entry(rvu, mcam, npc_blkaddr,
+						      elem->mcam_index, true);
+
+			goto unlock_mce;
+		}
+	} else {
+		if (!prev_count || prev_count < req->num_mce_entry) {
+			if (elem->mcam_index != -1)
+				npc_enable_mcam_entry(rvu, mcam, npc_blkaddr,
+						      elem->mcam_index, true);
+			ret = NIX_AF_ERR_INVALID_MCAST_DEL_REQ;
+			goto unlock_mce;
+		}
+
+		nix_free_mce_list(mcast, prev_count, elem->mce_start_index, elem->dir);
+		new_count = prev_count - req->num_mce_entry;
+		elem->mce_start_index = nix_alloc_mce_list(mcast, new_count, elem->dir);
+		ret = nix_del_mce_list_entry(rvu, nix_hw, elem, req);
+		if (ret) {
+			nix_free_mce_list(mcast, new_count, elem->mce_start_index, elem->dir);
+			elem->mce_start_index = nix_alloc_mce_list(mcast, prev_count, elem->dir);
+			if (elem->mcam_index != -1)
+				npc_enable_mcam_entry(rvu, mcam,
+						      npc_blkaddr,
+						      elem->mcam_index,
+						      true);
+
+			goto unlock_mce;
+		}
+	}
+
+	if (elem->mcam_index == -1) {
+		rsp->mce_start_index = elem->mce_start_index;
+		ret = 0;
+		goto unlock_mce;
+	}
+
+	nix_mcast_update_action(rvu, elem);
+	npc_enable_mcam_entry(rvu, mcam, npc_blkaddr, elem->mcam_index, true);
+	rsp->mce_start_index = elem->mce_start_index;
+	ret = 0;
+
+unlock_mce:
+	mutex_unlock(&mcast->mce_lock);
+
+unlock_grp:
+	if (!req->is_af)
+		mutex_unlock(&mcast_grp->mcast_grp_lock);
+
+	return ret;
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 16cfc802e348..167145bdcb75 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -389,7 +389,13 @@ static u64 npc_get_default_entry_action(struct rvu *rvu, struct npc_mcam *mcam,
 	int bank, nixlf, index;
 
 	/* get ucast entry rule entry index */
-	nix_get_nixlf(rvu, pf_func, &nixlf, NULL);
+	if (nix_get_nixlf(rvu, pf_func, &nixlf, NULL)) {
+		dev_err(rvu->dev, "%s: nixlf not attached to pcifunc:0x%x\n",
+			__func__, pf_func);
+		/* Action 0 is drop */
+		return 0;
+	}
+
 	index = npc_get_nixlf_mcam_index(mcam, pf_func, nixlf,
 					 NIXLF_UCAST_ENTRY);
 	bank = npc_get_bank(mcam, index);
@@ -589,8 +595,8 @@ static void npc_copy_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
 		    NPC_AF_MCAMEX_BANKX_CFG(dest, dbank), cfg);
 }
 
-static u64 npc_get_mcam_action(struct rvu *rvu, struct npc_mcam *mcam,
-			       int blkaddr, int index)
+u64 npc_get_mcam_action(struct rvu *rvu, struct npc_mcam *mcam,
+			int blkaddr, int index)
 {
 	int bank = npc_get_bank(mcam, index);
 
@@ -599,6 +605,16 @@ static u64 npc_get_mcam_action(struct rvu *rvu, struct npc_mcam *mcam,
 			  NPC_AF_MCAMEX_BANKX_ACTION(index, bank));
 }
 
+void npc_set_mcam_action(struct rvu *rvu, struct npc_mcam *mcam,
+			 int blkaddr, int index, u64 cfg)
+{
+	int bank = npc_get_bank(mcam, index);
+
+	index &= (mcam->banksize - 1);
+	return rvu_write64(rvu, blkaddr,
+			   NPC_AF_MCAMEX_BANKX_ACTION(index, bank), cfg);
+}
+
 void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc,
 				 int nixlf, u64 chan, u8 *mac_addr)
 {
@@ -665,6 +681,7 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 	int blkaddr, ucast_idx, index;
 	struct nix_rx_action action = { 0 };
 	u64 relaxed_mask;
+	u8 flow_key_alg;
 
 	if (!hw->cap.nix_rx_multicast && is_cgx_vf(rvu, pcifunc))
 		return;
@@ -695,6 +712,8 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 		action.op = NIX_RX_ACTIONOP_UCAST;
 	}
 
+	flow_key_alg = action.flow_key_alg;
+
 	/* RX_ACTION set to MCAST for CGX PF's */
 	if (hw->cap.nix_rx_multicast && pfvf->use_mce_list &&
 	    is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) {
@@ -734,7 +753,7 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 	req.vf = pcifunc;
 	req.index = action.index;
 	req.match_id = action.match_id;
-	req.flow_key_alg = action.flow_key_alg;
+	req.flow_key_alg = flow_key_alg;
 
 	rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp);
 }
@@ -848,6 +867,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
 	u8 mac_addr[ETH_ALEN] = { 0 };
 	struct nix_rx_action action = { 0 };
 	struct rvu_pfvf *pfvf;
+	u8 flow_key_alg;
 	u16 vf_func;
 
 	/* Only CGX PF/VF can add allmulticast entry */
@@ -882,6 +902,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
 		*(u64 *)&action = npc_get_mcam_action(rvu, mcam,
 							blkaddr, ucast_idx);
 
+	flow_key_alg = action.flow_key_alg;
 	if (action.op != NIX_RX_ACTIONOP_RSS) {
 		*(u64 *)&action = 0;
 		action.op = NIX_RX_ACTIONOP_UCAST;
@@ -918,7 +939,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
 	req.vf = pcifunc | vf_func;
 	req.index = action.index;
 	req.match_id = action.match_id;
-	req.flow_key_alg = action.flow_key_alg;
+	req.flow_key_alg = flow_key_alg;
 
 	rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp);
 }
@@ -984,11 +1005,38 @@ static void npc_update_vf_flow_entry(struct rvu *rvu, struct npc_mcam *mcam,
 	mutex_unlock(&mcam->lock);
 }
 
+static void npc_update_rx_action_with_alg_idx(struct rvu *rvu, struct nix_rx_action action,
+					      struct rvu_pfvf *pfvf, int mcam_index, int blkaddr,
+					      int alg_idx)
+
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	struct rvu_hwinfo *hw = rvu->hw;
+	int bank, op_rss;
+
+	if (!is_mcam_entry_enabled(rvu, mcam, blkaddr, mcam_index))
+		return;
+
+	op_rss = (!hw->cap.nix_rx_multicast || !pfvf->use_mce_list);
+
+	bank = npc_get_bank(mcam, mcam_index);
+	mcam_index &= (mcam->banksize - 1);
+
+	/* If Rx action is MCAST update only RSS algorithm index */
+	if (!op_rss) {
+		*(u64 *)&action = rvu_read64(rvu, blkaddr,
+				NPC_AF_MCAMEX_BANKX_ACTION(mcam_index, bank));
+
+		action.flow_key_alg = alg_idx;
+	}
+	rvu_write64(rvu, blkaddr,
+		    NPC_AF_MCAMEX_BANKX_ACTION(mcam_index, bank), *(u64 *)&action);
+}
+
 void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
 				    int group, int alg_idx, int mcam_index)
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
-	struct rvu_hwinfo *hw = rvu->hw;
 	struct nix_rx_action action;
 	int blkaddr, index, bank;
 	struct rvu_pfvf *pfvf;
@@ -1044,15 +1092,16 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
 	/* If PF's promiscuous entry is enabled,
 	 * Set RSS action for that entry as well
 	 */
-	if ((!hw->cap.nix_rx_multicast || !pfvf->use_mce_list) &&
-	    is_mcam_entry_enabled(rvu, mcam, blkaddr, index)) {
-		bank = npc_get_bank(mcam, index);
-		index &= (mcam->banksize - 1);
+	npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, blkaddr,
+					  alg_idx);
 
-		rvu_write64(rvu, blkaddr,
-			    NPC_AF_MCAMEX_BANKX_ACTION(index, bank),
-			    *(u64 *)&action);
-	}
+	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
+					 nixlf, NIXLF_ALLMULTI_ENTRY);
+	/* If PF's allmulti  entry is enabled,
+	 * Set RSS action for that entry as well
+	 */
+	npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, blkaddr,
+					  alg_idx);
 }
 
 void npc_enadis_default_mce_entry(struct rvu *rvu, u16 pcifunc,
@@ -1797,7 +1846,21 @@ static void npc_parser_profile_init(struct rvu *rvu, int blkaddr)
 		npc_program_kpu_profile(rvu, blkaddr, idx, &rvu->kpu.kpu[idx]);
 }
 
-static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
+void npc_mcam_rsrcs_deinit(struct rvu *rvu)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+
+	kfree(mcam->bmap);
+	kfree(mcam->bmap_reverse);
+	kfree(mcam->entry2pfvf_map);
+	kfree(mcam->cntr2pfvf_map);
+	kfree(mcam->entry2cntr_map);
+	kfree(mcam->cntr_refcnt);
+	kfree(mcam->entry2target_pffunc);
+	kfree(mcam->counters.bmap);
+}
+
+int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 {
 	int nixlf_count = rvu_get_nixlf_count(rvu);
 	struct npc_mcam *mcam = &rvu->hw->mcam;
@@ -1841,24 +1904,23 @@ static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 	mcam->pf_offset = mcam->nixlf_offset + nixlf_count;
 
 	/* Allocate bitmaps for managing MCAM entries */
-	mcam->bmap = devm_kcalloc(rvu->dev, BITS_TO_LONGS(mcam->bmap_entries),
-				  sizeof(long), GFP_KERNEL);
+	mcam->bmap = kmalloc_array(BITS_TO_LONGS(mcam->bmap_entries),
+				   sizeof(long), GFP_KERNEL);
 	if (!mcam->bmap)
 		return -ENOMEM;
 
-	mcam->bmap_reverse = devm_kcalloc(rvu->dev,
-					  BITS_TO_LONGS(mcam->bmap_entries),
-					  sizeof(long), GFP_KERNEL);
+	mcam->bmap_reverse = kmalloc_array(BITS_TO_LONGS(mcam->bmap_entries),
+					   sizeof(long), GFP_KERNEL);
 	if (!mcam->bmap_reverse)
-		return -ENOMEM;
+		goto free_bmap;
 
 	mcam->bmap_fcnt = mcam->bmap_entries;
 
 	/* Alloc memory for saving entry to RVU PFFUNC allocation mapping */
-	mcam->entry2pfvf_map = devm_kcalloc(rvu->dev, mcam->bmap_entries,
-					    sizeof(u16), GFP_KERNEL);
+	mcam->entry2pfvf_map = kmalloc_array(mcam->bmap_entries,
+					     sizeof(u16), GFP_KERNEL);
 	if (!mcam->entry2pfvf_map)
-		return -ENOMEM;
+		goto free_bmap_reverse;
 
 	/* Reserve 1/8th of MCAM entries at the bottom for low priority
 	 * allocations and another 1/8th at the top for high priority
@@ -1877,31 +1939,31 @@ static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 	 */
 	err = rvu_alloc_bitmap(&mcam->counters);
 	if (err)
-		return err;
+		goto free_entry_map;
 
-	mcam->cntr2pfvf_map = devm_kcalloc(rvu->dev, mcam->counters.max,
-					   sizeof(u16), GFP_KERNEL);
+	mcam->cntr2pfvf_map = kmalloc_array(mcam->counters.max,
+					    sizeof(u16), GFP_KERNEL);
 	if (!mcam->cntr2pfvf_map)
-		goto free_mem;
+		goto free_cntr_bmap;
 
 	/* Alloc memory for MCAM entry to counter mapping and for tracking
 	 * counter's reference count.
 	 */
-	mcam->entry2cntr_map = devm_kcalloc(rvu->dev, mcam->bmap_entries,
-					    sizeof(u16), GFP_KERNEL);
+	mcam->entry2cntr_map = kmalloc_array(mcam->bmap_entries,
+					     sizeof(u16), GFP_KERNEL);
 	if (!mcam->entry2cntr_map)
-		goto free_mem;
+		goto free_cntr_map;
 
-	mcam->cntr_refcnt = devm_kcalloc(rvu->dev, mcam->counters.max,
-					 sizeof(u16), GFP_KERNEL);
+	mcam->cntr_refcnt = kmalloc_array(mcam->counters.max,
+					  sizeof(u16), GFP_KERNEL);
 	if (!mcam->cntr_refcnt)
-		goto free_mem;
+		goto free_entry_cntr_map;
 
 	/* Alloc memory for saving target device of mcam rule */
-	mcam->entry2target_pffunc = devm_kcalloc(rvu->dev, mcam->total_entries,
-						 sizeof(u16), GFP_KERNEL);
+	mcam->entry2target_pffunc = kmalloc_array(mcam->total_entries,
+						  sizeof(u16), GFP_KERNEL);
 	if (!mcam->entry2target_pffunc)
-		goto free_mem;
+		goto free_cntr_refcnt;
 
 	for (index = 0; index < mcam->bmap_entries; index++) {
 		mcam->entry2pfvf_map[index] = NPC_MCAM_INVALID_MAP;
@@ -1915,8 +1977,21 @@ static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 
 	return 0;
 
-free_mem:
+free_cntr_refcnt:
+	kfree(mcam->cntr_refcnt);
+free_entry_cntr_map:
+	kfree(mcam->entry2cntr_map);
+free_cntr_map:
+	kfree(mcam->cntr2pfvf_map);
+free_cntr_bmap:
 	kfree(mcam->counters.bmap);
+free_entry_map:
+	kfree(mcam->entry2pfvf_map);
+free_bmap_reverse:
+	kfree(mcam->bmap_reverse);
+free_bmap:
+	kfree(mcam->bmap);
+
 	return -ENOMEM;
 }
 
@@ -2124,6 +2199,7 @@ void rvu_npc_freemem(struct rvu *rvu)
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 
 	kfree(pkind->rsrc.bmap);
+	npc_mcam_rsrcs_deinit(rvu);
 	kfree(mcam->counters.bmap);
 	if (rvu->kpu_prfl_addr)
 		iounmap(rvu->kpu_prfl_addr);
@@ -2639,18 +2715,17 @@ int rvu_mbox_handler_npc_mcam_alloc_entry(struct rvu *rvu,
 	rsp->entry = NPC_MCAM_ENTRY_INVALID;
 	rsp->free_count = 0;
 
-	/* Check if ref_entry is within range */
-	if (req->priority && req->ref_entry >= mcam->bmap_entries) {
-		dev_err(rvu->dev, "%s: reference entry %d is out of range\n",
-			__func__, req->ref_entry);
-		return NPC_MCAM_INVALID_REQ;
-	}
+	/* Check if ref_entry is greater that the range
+	 * then set it to max value.
+	 */
+	if (req->ref_entry > mcam->bmap_entries)
+		req->ref_entry = mcam->bmap_entries;
 
 	/* ref_entry can't be '0' if requested priority is high.
 	 * Can't be last entry if requested priority is low.
 	 */
 	if ((!req->ref_entry && req->priority == NPC_MCAM_HIGHER_PRIO) ||
-	    ((req->ref_entry == (mcam->bmap_entries - 1)) &&
+	    ((req->ref_entry == mcam->bmap_entries) &&
 	     req->priority == NPC_MCAM_LOWER_PRIO))
 		return NPC_MCAM_INVALID_REQ;
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
index 114e4ec21802..c75669c8fde7 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
@@ -51,6 +51,8 @@ static const char * const npc_flow_names[] = {
 	[NPC_MPLS3_TTL]     = "lse depth 3 ttl",
 	[NPC_MPLS4_LBTCBOS] = "lse depth 4 label tc bos",
 	[NPC_MPLS4_TTL]     = "lse depth 4",
+	[NPC_TYPE_ICMP] = "icmp type",
+	[NPC_CODE_ICMP] = "icmp code",
 	[NPC_UNKNOWN]	= "unknown",
 };
 
@@ -526,6 +528,8 @@ do {									       \
 	NPC_SCAN_HDR(NPC_DPORT_TCP, NPC_LID_LD, NPC_LT_LD_TCP, 2, 2);
 	NPC_SCAN_HDR(NPC_SPORT_SCTP, NPC_LID_LD, NPC_LT_LD_SCTP, 0, 2);
 	NPC_SCAN_HDR(NPC_DPORT_SCTP, NPC_LID_LD, NPC_LT_LD_SCTP, 2, 2);
+	NPC_SCAN_HDR(NPC_TYPE_ICMP, NPC_LID_LD, NPC_LT_LD_ICMP, 0, 1);
+	NPC_SCAN_HDR(NPC_CODE_ICMP, NPC_LID_LD, NPC_LT_LD_ICMP, 1, 1);
 	NPC_SCAN_HDR(NPC_ETYPE_ETHER, NPC_LID_LA, NPC_LT_LA_ETHER, 12, 2);
 	NPC_SCAN_HDR(NPC_ETYPE_TAG1, NPC_LID_LB, NPC_LT_LB_CTAG, 4, 2);
 	NPC_SCAN_HDR(NPC_ETYPE_TAG2, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, 8, 2);
@@ -555,7 +559,7 @@ static void npc_set_features(struct rvu *rvu, int blkaddr, u8 intf)
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	u64 *features = &mcam->rx_features;
-	u64 tcp_udp_sctp;
+	u64 proto_flags;
 	int hdr;
 
 	if (is_npc_intf_tx(intf))
@@ -566,18 +570,21 @@ static void npc_set_features(struct rvu *rvu, int blkaddr, u8 intf)
 			*features |= BIT_ULL(hdr);
 	}
 
-	tcp_udp_sctp = BIT_ULL(NPC_SPORT_TCP) | BIT_ULL(NPC_SPORT_UDP) |
+	proto_flags = BIT_ULL(NPC_SPORT_TCP) | BIT_ULL(NPC_SPORT_UDP) |
 		       BIT_ULL(NPC_DPORT_TCP) | BIT_ULL(NPC_DPORT_UDP) |
-		       BIT_ULL(NPC_SPORT_SCTP) | BIT_ULL(NPC_DPORT_SCTP);
+		       BIT_ULL(NPC_SPORT_SCTP) | BIT_ULL(NPC_DPORT_SCTP) |
+		       BIT_ULL(NPC_SPORT_SCTP) | BIT_ULL(NPC_DPORT_SCTP) |
+		       BIT_ULL(NPC_TYPE_ICMP) | BIT_ULL(NPC_CODE_ICMP);
 
 	/* for tcp/udp/sctp corresponding layer type should be in the key */
-	if (*features & tcp_udp_sctp) {
+	if (*features & proto_flags) {
 		if (!npc_check_field(rvu, blkaddr, NPC_LD, intf))
-			*features &= ~tcp_udp_sctp;
+			*features &= ~proto_flags;
 		else
 			*features |= BIT_ULL(NPC_IPPROTO_TCP) |
 				     BIT_ULL(NPC_IPPROTO_UDP) |
-				     BIT_ULL(NPC_IPPROTO_SCTP);
+				     BIT_ULL(NPC_IPPROTO_SCTP) |
+				     BIT_ULL(NPC_IPPROTO_ICMP);
 	}
 
 	/* for AH/ICMP/ICMPv6/, check if corresponding layer type is present in the key */
@@ -971,6 +978,10 @@ do {									      \
 		       ntohs(mask->sport), 0);
 	NPC_WRITE_FLOW(NPC_DPORT_SCTP, dport, ntohs(pkt->dport), 0,
 		       ntohs(mask->dport), 0);
+	NPC_WRITE_FLOW(NPC_TYPE_ICMP, icmp_type, pkt->icmp_type, 0,
+		       mask->icmp_type, 0);
+	NPC_WRITE_FLOW(NPC_CODE_ICMP, icmp_code, pkt->icmp_code, 0,
+		       mask->icmp_code, 0);
 
 	NPC_WRITE_FLOW(NPC_IPSEC_SPI, spi, ntohl(pkt->spi), 0,
 		       ntohl(mask->spi), 0);
@@ -1106,13 +1117,40 @@ static void rvu_mcam_add_counter_to_rule(struct rvu *rvu, u16 pcifunc,
 	}
 }
 
-static void npc_update_rx_entry(struct rvu *rvu, struct rvu_pfvf *pfvf,
-				struct mcam_entry *entry,
-				struct npc_install_flow_req *req,
-				u16 target, bool pf_set_vfs_mac)
+static int npc_mcast_update_action_index(struct rvu *rvu, struct npc_install_flow_req *req,
+					 u64 op, void *action)
+{
+	int mce_index;
+
+	/* If a PF/VF is installing a multicast rule then it is expected
+	 * that the PF/VF should have created a group for the multicast/mirror
+	 * list. Otherwise reject the configuration.
+	 * During this scenario, req->index is set as multicast/mirror
+	 * group index.
+	 */
+	if (req->hdr.pcifunc &&
+	    (op == NIX_RX_ACTIONOP_MCAST || op == NIX_TX_ACTIONOP_MCAST)) {
+		mce_index = rvu_nix_mcast_get_mce_index(rvu, req->hdr.pcifunc, req->index);
+		if (mce_index < 0)
+			return mce_index;
+
+		if (op == NIX_RX_ACTIONOP_MCAST)
+			((struct nix_rx_action *)action)->index = mce_index;
+		else
+			((struct nix_tx_action *)action)->index = mce_index;
+	}
+
+	return 0;
+}
+
+static int npc_update_rx_entry(struct rvu *rvu, struct rvu_pfvf *pfvf,
+			       struct mcam_entry *entry,
+			       struct npc_install_flow_req *req,
+			       u16 target, bool pf_set_vfs_mac)
 {
 	struct rvu_switch *rswitch = &rvu->rswitch;
 	struct nix_rx_action action;
+	int ret;
 
 	if (rswitch->mode == DEVLINK_ESWITCH_MODE_SWITCHDEV && pf_set_vfs_mac)
 		req->chan_mask = 0x0; /* Do not care channel */
@@ -1124,6 +1162,11 @@ static void npc_update_rx_entry(struct rvu *rvu, struct rvu_pfvf *pfvf,
 	action.pf_func = target;
 	action.op = req->op;
 	action.index = req->index;
+
+	ret = npc_mcast_update_action_index(rvu, req, action.op, (void *)&action);
+	if (ret)
+		return ret;
+
 	action.match_id = req->match_id;
 	action.flow_key_alg = req->flow_key_alg;
 
@@ -1155,14 +1198,17 @@ static void npc_update_rx_entry(struct rvu *rvu, struct rvu_pfvf *pfvf,
 			     FIELD_PREP(RX_VTAG1_TYPE_MASK, req->vtag1_type) |
 			     FIELD_PREP(RX_VTAG1_LID_MASK, NPC_LID_LB) |
 			     FIELD_PREP(RX_VTAG1_RELPTR_MASK, 4);
+
+	return 0;
 }
 
-static void npc_update_tx_entry(struct rvu *rvu, struct rvu_pfvf *pfvf,
-				struct mcam_entry *entry,
-				struct npc_install_flow_req *req, u16 target)
+static int npc_update_tx_entry(struct rvu *rvu, struct rvu_pfvf *pfvf,
+			       struct mcam_entry *entry,
+			       struct npc_install_flow_req *req, u16 target)
 {
 	struct nix_tx_action action;
 	u64 mask = ~0ULL;
+	int ret;
 
 	/* If AF is installing then do not care about
 	 * PF_FUNC in Send Descriptor
@@ -1176,6 +1222,11 @@ static void npc_update_tx_entry(struct rvu *rvu, struct rvu_pfvf *pfvf,
 	*(u64 *)&action = 0x00;
 	action.op = req->op;
 	action.index = req->index;
+
+	ret = npc_mcast_update_action_index(rvu, req, action.op, (void *)&action);
+	if (ret)
+		return ret;
+
 	action.match_id = req->match_id;
 
 	entry->action = *(u64 *)&action;
@@ -1191,6 +1242,8 @@ static void npc_update_tx_entry(struct rvu *rvu, struct rvu_pfvf *pfvf,
 			     FIELD_PREP(TX_VTAG1_OP_MASK, req->vtag1_op) |
 			     FIELD_PREP(TX_VTAG1_LID_MASK, NPC_LID_LA) |
 			     FIELD_PREP(TX_VTAG1_RELPTR_MASK, 24);
+
+	return 0;
 }
 
 static int npc_install_flow(struct rvu *rvu, int blkaddr, u16 target,
@@ -1220,10 +1273,15 @@ static int npc_install_flow(struct rvu *rvu, int blkaddr, u16 target,
 	npc_update_flow(rvu, entry, features, &req->packet, &req->mask, &dummy,
 			req->intf, blkaddr);
 
-	if (is_npc_intf_rx(req->intf))
-		npc_update_rx_entry(rvu, pfvf, entry, req, target, pf_set_vfs_mac);
-	else
-		npc_update_tx_entry(rvu, pfvf, entry, req, target);
+	if (is_npc_intf_rx(req->intf)) {
+		err = npc_update_rx_entry(rvu, pfvf, entry, req, target, pf_set_vfs_mac);
+		if (err)
+			return err;
+	} else {
+		err = npc_update_tx_entry(rvu, pfvf, entry, req, target);
+		if (err)
+			return err;
+	}
 
 	/* Default unicast rules do not exist for TX */
 	if (is_npc_intf_tx(req->intf))
@@ -1340,6 +1398,10 @@ find_rule:
 		return rvu_nix_setup_ratelimit_aggr(rvu, req->hdr.pcifunc,
 					     req->index, req->match_id);
 
+	if (owner && req->op == NIX_RX_ACTIONOP_MCAST)
+		return rvu_nix_mcast_update_mcam_entry(rvu, req->hdr.pcifunc,
+						       req->index, entry_index);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c
index b3150f053291..d46ac29adb96 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c
@@ -31,8 +31,8 @@ static struct hw_reg_map txsch_reg_map[NIX_TXSCH_LVL_CNT] = {
 	{NIX_TXSCH_LVL_TL4, 3, 0xFFFF, {{0x0B00, 0x0B08}, {0x0B10, 0x0B18},
 			      {0x1200, 0x12E0} } },
 	{NIX_TXSCH_LVL_TL3, 4, 0xFFFF, {{0x1000, 0x10E0}, {0x1600, 0x1608},
-			      {0x1610, 0x1618}, {0x1700, 0x17B0} } },
-	{NIX_TXSCH_LVL_TL2, 2, 0xFFFF, {{0x0E00, 0x0EE0}, {0x1700, 0x17B0} } },
+			      {0x1610, 0x1618}, {0x1700, 0x17C8} } },
+	{NIX_TXSCH_LVL_TL2, 2, 0xFFFF, {{0x0E00, 0x0EE0}, {0x1700, 0x17C8} } },
 	{NIX_TXSCH_LVL_TL1, 1, 0xFFFF, {{0x0C00, 0x0D98} } },
 };
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
index b42e631e52d0..6f73ad9807f0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
@@ -437,6 +437,7 @@
 
 #define NIX_AF_LINKX_BASE_MASK		GENMASK_ULL(11, 0)
 #define NIX_AF_LINKX_RANGE_MASK		GENMASK_ULL(19, 16)
+#define NIX_AF_LINKX_MCS_CNT_MASK	GENMASK_ULL(33, 32)
 
 /* SSO */
 #define SSO_AF_CONST			(0x1000)
@@ -733,5 +734,7 @@
 #define APR_LMT_MAP_ENT_DIS_SCH_CMP_SHIFT	23
 #define APR_LMT_MAP_ENT_SCH_ENA_SHIFT		22
 #define APR_LMT_MAP_ENT_DIS_LINE_PREF_SHIFT	21
+#define LMTST_THROTTLE_MASK		GENMASK_ULL(38, 35)
+#define LMTST_WR_PEND_MAX		15
 
 #endif /* RVU_REG_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
index edc9367b1b95..5ef406c7e8a4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
@@ -340,11 +340,12 @@ struct nix_aq_res_s {
 /* NIX Completion queue context structure */
 struct nix_cq_ctx_s {
 	u64 base;
-	u64 rsvd_64_67		: 4;
+	u64 lbp_ena             : 1;
+	u64 lbpid_low           : 3;
 	u64 bp_ena		: 1;
-	u64 rsvd_69_71		: 3;
+	u64 lbpid_med           : 3;
 	u64 bpid		: 9;
-	u64 rsvd_81_83		: 3;
+	u64 lbpid_high          : 3;
 	u64 qint_idx		: 7;
 	u64 cq_err		: 1;
 	u64 cint_idx		: 7;
@@ -358,10 +359,14 @@ struct nix_cq_ctx_s {
 	u64 drop		: 8;
 	u64 drop_ena		: 1;
 	u64 ena			: 1;
-	u64 rsvd_210_211	: 2;
-	u64 substream		: 20;
+	u64 cpt_drop_err_en     : 1;
+	u64 rsvd_211	        : 1;
+	u64 substream           : 12;
+	u64 stash_thresh        : 4;
+	u64 lbp_frac            : 4;
 	u64 caching		: 1;
-	u64 rsvd_233_235	: 3;
+	u64 stashing            : 1;
+	u64 rsvd_234_235	: 2;
 	u64 qsize		: 4;
 	u64 cq_err_int		: 8;
 	u64 cq_err_int_ena	: 8;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
index a4a258da8dd5..c1c99d7054f8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
@@ -450,6 +450,9 @@ int cn10k_set_ipolicer_rate(struct otx2_nic *pfvf, u16 profile,
 	aq->prof.pebs_mantissa = 0;
 	aq->prof_mask.pebs_mantissa = 0xFF;
 
+	aq->prof.hl_en = 0;
+	aq->prof_mask.hl_en = 1;
+
 	/* Fill AQ info */
 	aq->qidx = profile;
 	aq->ctype = NIX_AQ_CTYPE_BANDPROF;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index e7c69b57147e..06910307085e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -1070,6 +1070,8 @@ int otx2_init_tc(struct otx2_nic *nic);
 void otx2_shutdown_tc(struct otx2_nic *nic);
 int otx2_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 		  void *type_data);
+void otx2_tc_apply_ingress_police_rules(struct otx2_nic *nic);
+
 /* CGX/RPM DMAC filters support */
 int otx2_dmacflt_get_max_cnt(struct otx2_nic *pf);
 int otx2_dmacflt_add(struct otx2_nic *pf, const u8 *mac, u32 bit_pos);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c
index bfddbff7bcdf..28fb643d2917 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c
@@ -399,9 +399,10 @@ static int otx2_dcbnl_ieee_getpfc(struct net_device *dev, struct ieee_pfc *pfc)
 static int otx2_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc)
 {
 	struct otx2_nic *pfvf = netdev_priv(dev);
+	u8 old_pfc_en;
 	int err;
 
-	/* Save PFC configuration to interface */
+	old_pfc_en = pfvf->pfc_en;
 	pfvf->pfc_en = pfc->pfc_en;
 
 	if (pfvf->hw.tx_queues >= NIX_PF_PFC_PRIO_MAX)
@@ -411,13 +412,17 @@ static int otx2_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc)
 	 * supported by the tx queue configuration
 	 */
 	err = otx2_check_pfc_config(pfvf);
-	if (err)
+	if (err) {
+		pfvf->pfc_en = old_pfc_en;
 		return err;
+	}
 
 process_pfc:
 	err = otx2_config_priority_flow_ctrl(pfvf);
-	if (err)
+	if (err) {
+		pfvf->pfc_en = old_pfc_en;
 		return err;
+	}
 
 	/* Request Per channel Bpids */
 	if (pfc->pfc_en)
@@ -425,6 +430,12 @@ process_pfc:
 
 	err = otx2_pfc_txschq_update(pfvf);
 	if (err) {
+		if (pfc->pfc_en)
+			otx2_nix_config_bp(pfvf, false);
+
+		otx2_pfc_txschq_stop(pfvf);
+		pfvf->pfc_en = old_pfc_en;
+		otx2_config_priority_flow_ctrl(pfvf);
 		dev_err(pfvf->dev, "%s failed to update TX schedulers\n", __func__);
 		return err;
 	}
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
index 9efcec549834..2928898c7f8d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
@@ -334,9 +334,12 @@ static void otx2_get_pauseparam(struct net_device *netdev,
 	if (is_otx2_lbkvf(pfvf->pdev))
 		return;
 
+	mutex_lock(&pfvf->mbox.lock);
 	req = otx2_mbox_alloc_msg_cgx_cfg_pause_frm(&pfvf->mbox);
-	if (!req)
+	if (!req) {
+		mutex_unlock(&pfvf->mbox.lock);
 		return;
+	}
 
 	if (!otx2_sync_mbox_msg(&pfvf->mbox)) {
 		rsp = (struct cgx_pause_frm_cfg *)
@@ -344,6 +347,7 @@ static void otx2_get_pauseparam(struct net_device *netdev,
 		pause->rx_pause = rsp->rx_pause;
 		pause->tx_pause = rsp->tx_pause;
 	}
+	mutex_unlock(&pfvf->mbox.lock);
 }
 
 static int otx2_set_pauseparam(struct net_device *netdev,
@@ -831,21 +835,26 @@ static int otx2_rss_ctx_create(struct otx2_nic *pfvf,
 	return 0;
 }
 
-/* RSS context configuration */
-static int otx2_set_rxfh_context(struct net_device *dev, const u32 *indir,
-				 const u8 *hkey, const u8 hfunc,
-				 u32 *rss_context, bool delete)
+/* Configure RSS table and hash key */
+static int otx2_set_rxfh(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
+	u32 rss_context = DEFAULT_RSS_CONTEXT_GROUP;
 	struct otx2_nic *pfvf = netdev_priv(dev);
 	struct otx2_rss_ctx *rss_ctx;
 	struct otx2_rss_info *rss;
 	int ret, idx;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (*rss_context != ETH_RXFH_CONTEXT_ALLOC &&
-	    *rss_context >= MAX_RSS_GROUPS)
+	if (rxfh->rss_context)
+		rss_context = rxfh->rss_context;
+
+	if (rss_context != ETH_RXFH_CONTEXT_ALLOC &&
+	    rss_context >= MAX_RSS_GROUPS)
 		return -EINVAL;
 
 	rss = &pfvf->hw.rss_info;
@@ -855,40 +864,45 @@ static int otx2_set_rxfh_context(struct net_device *dev, const u32 *indir,
 		return -EIO;
 	}
 
-	if (hkey) {
-		memcpy(rss->key, hkey, sizeof(rss->key));
+	if (rxfh->key) {
+		memcpy(rss->key, rxfh->key, sizeof(rss->key));
 		otx2_set_rss_key(pfvf);
 	}
-	if (delete)
-		return otx2_rss_ctx_delete(pfvf, *rss_context);
+	if (rxfh->rss_delete)
+		return otx2_rss_ctx_delete(pfvf, rss_context);
 
-	if (*rss_context == ETH_RXFH_CONTEXT_ALLOC) {
-		ret = otx2_rss_ctx_create(pfvf, rss_context);
+	if (rss_context == ETH_RXFH_CONTEXT_ALLOC) {
+		ret = otx2_rss_ctx_create(pfvf, &rss_context);
+		rxfh->rss_context = rss_context;
 		if (ret)
 			return ret;
 	}
-	if (indir) {
-		rss_ctx = rss->rss_ctx[*rss_context];
+	if (rxfh->indir) {
+		rss_ctx = rss->rss_ctx[rss_context];
 		for (idx = 0; idx < rss->rss_size; idx++)
-			rss_ctx->ind_tbl[idx] = indir[idx];
+			rss_ctx->ind_tbl[idx] = rxfh->indir[idx];
 	}
-	otx2_set_rss_table(pfvf, *rss_context);
+	otx2_set_rss_table(pfvf, rss_context);
 
 	return 0;
 }
 
-static int otx2_get_rxfh_context(struct net_device *dev, u32 *indir,
-				 u8 *hkey, u8 *hfunc, u32 rss_context)
+/* Get RSS configuration */
+static int otx2_get_rxfh(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh)
 {
+	u32 rss_context = DEFAULT_RSS_CONTEXT_GROUP;
 	struct otx2_nic *pfvf = netdev_priv(dev);
 	struct otx2_rss_ctx *rss_ctx;
 	struct otx2_rss_info *rss;
+	u32 *indir = rxfh->indir;
 	int idx, rx_queues;
 
 	rss = &pfvf->hw.rss_info;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (rxfh->rss_context)
+		rss_context = rxfh->rss_context;
 
 	if (!indir)
 		return 0;
@@ -910,30 +924,12 @@ static int otx2_get_rxfh_context(struct net_device *dev, u32 *indir,
 		for (idx = 0; idx < rss->rss_size; idx++)
 			indir[idx] = rss_ctx->ind_tbl[idx];
 	}
-	if (hkey)
-		memcpy(hkey, rss->key, sizeof(rss->key));
+	if (rxfh->key)
+		memcpy(rxfh->key, rss->key, sizeof(rss->key));
 
 	return 0;
 }
 
-/* Get RSS configuration */
-static int otx2_get_rxfh(struct net_device *dev, u32 *indir,
-			 u8 *hkey, u8 *hfunc)
-{
-	return otx2_get_rxfh_context(dev, indir, hkey, hfunc,
-				     DEFAULT_RSS_CONTEXT_GROUP);
-}
-
-/* Configure RSS table and hash key */
-static int otx2_set_rxfh(struct net_device *dev, const u32 *indir,
-			 const u8 *hkey, const u8 hfunc)
-{
-
-	u32 rss_context = DEFAULT_RSS_CONTEXT_GROUP;
-
-	return otx2_set_rxfh_context(dev, indir, hkey, hfunc, &rss_context, 0);
-}
-
 static u32 otx2_get_msglevel(struct net_device *netdev)
 {
 	struct otx2_nic *pfvf = netdev_priv(netdev);
@@ -1314,6 +1310,7 @@ static void otx2_get_fec_stats(struct net_device *netdev,
 }
 
 static const struct ethtool_ops otx2_ethtool_ops = {
+	.cap_rss_ctx_supported	= true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE,
@@ -1336,8 +1333,6 @@ static const struct ethtool_ops otx2_ethtool_ops = {
 	.get_rxfh_indir_size	= otx2_get_rxfh_indir_size,
 	.get_rxfh		= otx2_get_rxfh,
 	.set_rxfh		= otx2_set_rxfh,
-	.get_rxfh_context	= otx2_get_rxfh_context,
-	.set_rxfh_context	= otx2_set_rxfh_context,
 	.get_msglevel		= otx2_get_msglevel,
 	.set_msglevel		= otx2_set_msglevel,
 	.get_pauseparam		= otx2_get_pauseparam,
@@ -1437,6 +1432,7 @@ static int otx2vf_get_link_ksettings(struct net_device *netdev,
 }
 
 static const struct ethtool_ops otx2vf_ethtool_ops = {
+	.cap_rss_ctx_supported	= true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE,
@@ -1455,8 +1451,6 @@ static const struct ethtool_ops otx2vf_ethtool_ops = {
 	.get_rxfh_indir_size	= otx2_get_rxfh_indir_size,
 	.get_rxfh		= otx2_get_rxfh,
 	.set_rxfh		= otx2_set_rxfh,
-	.get_rxfh_context	= otx2_get_rxfh_context,
-	.set_rxfh_context	= otx2_set_rxfh_context,
 	.get_ringparam		= otx2_get_ringparam,
 	.set_ringparam		= otx2_set_ringparam,
 	.get_coalesce		= otx2_get_coalesce,
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
index 4762dbea64a1..97a71e9b8563 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
@@ -1088,6 +1088,7 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc)
 	struct ethhdr *eth_hdr;
 	bool new = false;
 	int err = 0;
+	u64 vf_num;
 	u32 ring;
 
 	if (!flow_cfg->max_flows) {
@@ -1100,7 +1101,21 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc)
 	if (!(pfvf->flags & OTX2_FLAG_NTUPLE_SUPPORT))
 		return -ENOMEM;
 
-	if (ring >= pfvf->hw.rx_queues && fsp->ring_cookie != RX_CLS_FLOW_DISC)
+	/* Number of queues on a VF can be greater or less than
+	 * the PF's queue. Hence no need to check for the
+	 * queue count. Hence no need to check queue count if PF
+	 * is installing for its VF. Below is the expected vf_num value
+	 * based on the ethtool commands.
+	 *
+	 * e.g.
+	 * 1. ethtool -U <netdev> ... action -1  ==> vf_num:255
+	 * 2. ethtool -U <netdev> ... action <queue_num>  ==> vf_num:0
+	 * 3. ethtool -U <netdev> ... vf <vf_idx> queue <queue_num>  ==>
+	 *    vf_num:vf_idx+1
+	 */
+	vf_num = ethtool_get_flow_spec_ring_vf(fsp->ring_cookie);
+	if (!is_otx2_vf(pfvf->pcifunc) && !vf_num &&
+	    ring >= pfvf->hw.rx_queues && fsp->ring_cookie != RX_CLS_FLOW_DISC)
 		return -EINVAL;
 
 	if (fsp->location >= otx2_get_maxflows(flow_cfg))
@@ -1182,6 +1197,9 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc)
 		flow_cfg->nr_flows++;
 	}
 
+	if (flow->is_vf)
+		netdev_info(pfvf->netdev,
+			    "Make sure that VF's queue number is within its queue limit\n");
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index 91b99fd70361..a57455aebff6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -566,7 +566,9 @@ static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq)
 		otx2_write64(pf, RVU_PF_VFPF_MBOX_INTX(1), intr);
 		otx2_queue_work(mbox, pf->mbox_pfvf_wq, 64, vfs, intr,
 				TYPE_PFVF);
-		vfs -= 64;
+		if (intr)
+			trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr);
+		vfs = 64;
 	}
 
 	intr = otx2_read64(pf, RVU_PF_VFPF_MBOX_INTX(0));
@@ -574,7 +576,8 @@ static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq)
 
 	otx2_queue_work(mbox, pf->mbox_pfvf_wq, 0, vfs, intr, TYPE_PFVF);
 
-	trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr);
+	if (intr)
+		trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr);
 
 	return IRQ_HANDLED;
 }
@@ -1647,6 +1650,21 @@ static void otx2_free_hw_resources(struct otx2_nic *pf)
 	mutex_unlock(&mbox->lock);
 }
 
+static bool otx2_promisc_use_mce_list(struct otx2_nic *pfvf)
+{
+	int vf;
+
+	/* The AF driver will determine whether to allow the VF netdev or not */
+	if (is_otx2_vf(pfvf->pcifunc))
+		return true;
+
+	/* check if there are any trusted VFs associated with the PF netdev */
+	for (vf = 0; vf < pci_num_vf(pfvf->pdev); vf++)
+		if (pfvf->vf_configs[vf].trusted)
+			return true;
+	return false;
+}
+
 static void otx2_do_set_rx_mode(struct otx2_nic *pf)
 {
 	struct net_device *netdev = pf->netdev;
@@ -1679,12 +1697,21 @@ static void otx2_do_set_rx_mode(struct otx2_nic *pf)
 	if (netdev->flags & (IFF_ALLMULTI | IFF_MULTICAST))
 		req->mode |= NIX_RX_MODE_ALLMULTI;
 
-	req->mode |= NIX_RX_MODE_USE_MCE;
+	if (otx2_promisc_use_mce_list(pf))
+		req->mode |= NIX_RX_MODE_USE_MCE;
 
 	otx2_sync_mbox_msg(&pf->mbox);
 	mutex_unlock(&pf->mbox.lock);
 }
 
+static void otx2_set_irq_coalesce(struct otx2_nic *pfvf)
+{
+	int cint;
+
+	for (cint = 0; cint < pfvf->hw.cint_cnt; cint++)
+		otx2_config_irq_coalescing(pfvf, cint);
+}
+
 static void otx2_dim_work(struct work_struct *w)
 {
 	struct dim_cq_moder cur_moder;
@@ -1700,6 +1727,7 @@ static void otx2_dim_work(struct work_struct *w)
 		CQ_TIMER_THRESH_MAX : cur_moder.usec;
 	pfvf->hw.cq_ecount_wait = (cur_moder.pkts > NAPI_POLL_WEIGHT) ?
 		NAPI_POLL_WEIGHT : cur_moder.pkts;
+	otx2_set_irq_coalesce(pfvf);
 	dim->state = DIM_START_MEASURE;
 }
 
@@ -1870,6 +1898,8 @@ int otx2_open(struct net_device *netdev)
 	if (pf->flags & OTX2_FLAG_DMACFLTR_SUPPORT)
 		otx2_dmacflt_reinstall_flows(pf);
 
+	otx2_tc_apply_ingress_police_rules(pf);
+
 	err = otx2_rxtx_enable(pf, true);
 	/* If a mbox communication error happens at this point then interface
 	 * will end up in a state such that it is in down state but hardware
@@ -1934,6 +1964,8 @@ int otx2_stop(struct net_device *netdev)
 	/* Clear RSS enable flag */
 	rss = &pf->hw.rss_info;
 	rss->enable = false;
+	if (!netif_is_rxfh_configured(netdev))
+		kfree(rss->rss_ctx[DEFAULT_RSS_CONTEXT_GROUP]);
 
 	/* Cleanup Queue IRQ */
 	vec = pci_irq_vector(pf->pdev,
@@ -2675,11 +2707,14 @@ static int otx2_ndo_set_vf_trust(struct net_device *netdev, int vf,
 	pf->vf_configs[vf].trusted = enable;
 	rc = otx2_set_vf_permissions(pf, vf, OTX2_TRUSTED_VF);
 
-	if (rc)
+	if (rc) {
 		pf->vf_configs[vf].trusted = !enable;
-	else
+	} else {
 		netdev_info(pf->netdev, "VF %d is %strusted\n",
 			    vf, enable ? "" : "not ");
+		otx2_set_rx_mode(netdev);
+	}
+
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
index 8a5e3987a482..4fd44b6eecea 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
@@ -29,6 +29,8 @@
 
 #define OTX2_UNSUPP_LSE_DEPTH		GENMASK(6, 4)
 
+#define MCAST_INVALID_GRP		(-1U)
+
 struct otx2_tc_flow_stats {
 	u64 bytes;
 	u64 pkts;
@@ -47,6 +49,10 @@ struct otx2_tc_flow {
 	bool				is_act_police;
 	u32				prio;
 	struct npc_install_flow_req	req;
+	u32				mcast_grp_idx;
+	u64				rate;
+	u32				burst;
+	bool				is_pps;
 };
 
 static void otx2_get_egress_burst_cfg(struct otx2_nic *nic, u32 burst,
@@ -284,6 +290,41 @@ static int otx2_tc_egress_matchall_delete(struct otx2_nic *nic,
 	return err;
 }
 
+static int otx2_tc_act_set_hw_police(struct otx2_nic *nic,
+				     struct otx2_tc_flow *node)
+{
+	int rc;
+
+	mutex_lock(&nic->mbox.lock);
+
+	rc = cn10k_alloc_leaf_profile(nic, &node->leaf_profile);
+	if (rc) {
+		mutex_unlock(&nic->mbox.lock);
+		return rc;
+	}
+
+	rc = cn10k_set_ipolicer_rate(nic, node->leaf_profile,
+				     node->burst, node->rate, node->is_pps);
+	if (rc)
+		goto free_leaf;
+
+	rc = cn10k_map_unmap_rq_policer(nic, node->rq, node->leaf_profile, true);
+	if (rc)
+		goto free_leaf;
+
+	mutex_unlock(&nic->mbox.lock);
+
+	return 0;
+
+free_leaf:
+	if (cn10k_free_leaf_profile(nic, node->leaf_profile))
+		netdev_err(nic->netdev,
+			   "Unable to free leaf bandwidth profile(%d)\n",
+			   node->leaf_profile);
+	mutex_unlock(&nic->mbox.lock);
+	return rc;
+}
+
 static int otx2_tc_act_set_police(struct otx2_nic *nic,
 				  struct otx2_tc_flow *node,
 				  struct flow_cls_offload *f,
@@ -300,38 +341,92 @@ static int otx2_tc_act_set_police(struct otx2_nic *nic,
 		return -EINVAL;
 	}
 
+	req->match_id = mark & 0xFFFFULL;
+	req->index = rq_idx;
+	req->op = NIX_RX_ACTIONOP_UCAST;
+
+	node->is_act_police = true;
+	node->rq = rq_idx;
+	node->burst = burst;
+	node->rate = rate;
+	node->is_pps = pps;
+
+	rc = otx2_tc_act_set_hw_police(nic, node);
+	if (!rc)
+		set_bit(rq_idx, &nic->rq_bmap);
+
+	return rc;
+}
+
+static int otx2_tc_update_mcast(struct otx2_nic *nic,
+				struct npc_install_flow_req *req,
+				struct netlink_ext_ack *extack,
+				struct otx2_tc_flow *node,
+				struct nix_mcast_grp_update_req *ureq,
+				u8 num_intf)
+{
+	struct nix_mcast_grp_update_req *grp_update_req;
+	struct nix_mcast_grp_create_req *creq;
+	struct nix_mcast_grp_create_rsp *crsp;
+	u32 grp_index;
+	int rc;
+
 	mutex_lock(&nic->mbox.lock);
+	creq = otx2_mbox_alloc_msg_nix_mcast_grp_create(&nic->mbox);
+	if (!creq) {
+		rc = -ENOMEM;
+		goto error;
+	}
 
-	rc = cn10k_alloc_leaf_profile(nic, &node->leaf_profile);
+	creq->dir = NIX_MCAST_INGRESS;
+	/* Send message to AF */
+	rc = otx2_sync_mbox_msg(&nic->mbox);
 	if (rc) {
-		mutex_unlock(&nic->mbox.lock);
-		return rc;
+		NL_SET_ERR_MSG_MOD(extack, "Failed to create multicast group");
+		goto error;
 	}
 
-	rc = cn10k_set_ipolicer_rate(nic, node->leaf_profile, burst, rate, pps);
-	if (rc)
-		goto free_leaf;
+	crsp = (struct nix_mcast_grp_create_rsp *)otx2_mbox_get_rsp(&nic->mbox.mbox,
+			0,
+			&creq->hdr);
+	if (IS_ERR(crsp)) {
+		rc = PTR_ERR(crsp);
+		goto error;
+	}
 
-	rc = cn10k_map_unmap_rq_policer(nic, rq_idx, node->leaf_profile, true);
-	if (rc)
-		goto free_leaf;
+	grp_index = crsp->mcast_grp_idx;
+	grp_update_req = otx2_mbox_alloc_msg_nix_mcast_grp_update(&nic->mbox);
+	if (!grp_update_req) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to update multicast group");
+		rc = -ENOMEM;
+		goto error;
+	}
 
-	mutex_unlock(&nic->mbox.lock);
+	ureq->op = NIX_MCAST_OP_ADD_ENTRY;
+	ureq->mcast_grp_idx = grp_index;
+	ureq->num_mce_entry = num_intf;
+	ureq->pcifunc[0] = nic->pcifunc;
+	ureq->channel[0] = nic->hw.tx_chan_base;
 
-	req->match_id = mark & 0xFFFFULL;
-	req->index = rq_idx;
-	req->op = NIX_RX_ACTIONOP_UCAST;
-	set_bit(rq_idx, &nic->rq_bmap);
-	node->is_act_police = true;
-	node->rq = rq_idx;
+	ureq->dest_type[0] = NIX_RX_RSS;
+	ureq->rq_rss_index[0] = 0;
+	memcpy(&ureq->hdr, &grp_update_req->hdr, sizeof(struct mbox_msghdr));
+	memcpy(grp_update_req, ureq, sizeof(struct nix_mcast_grp_update_req));
+
+	/* Send message to AF */
+	rc = otx2_sync_mbox_msg(&nic->mbox);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to update multicast group");
+		goto error;
+	}
 
+	mutex_unlock(&nic->mbox.lock);
+	req->op = NIX_RX_ACTIONOP_MCAST;
+	req->index = grp_index;
+	node->mcast_grp_idx = grp_index;
 	return 0;
 
-free_leaf:
-	if (cn10k_free_leaf_profile(nic, node->leaf_profile))
-		netdev_err(nic->netdev,
-			   "Unable to free leaf bandwidth profile(%d)\n",
-			   node->leaf_profile);
+error:
 	mutex_unlock(&nic->mbox.lock);
 	return rc;
 }
@@ -342,16 +437,17 @@ static int otx2_tc_parse_actions(struct otx2_nic *nic,
 				 struct flow_cls_offload *f,
 				 struct otx2_tc_flow *node)
 {
+	struct nix_mcast_grp_update_req dummy_grp_update_req = { 0 };
 	struct netlink_ext_ack *extack = f->common.extack;
+	bool pps = false, mcast = false;
 	struct flow_action_entry *act;
 	struct net_device *target;
 	struct otx2_nic *priv;
 	u32 burst, mark = 0;
 	u8 nr_police = 0;
-	bool pps = false;
+	u8 num_intf = 1;
+	int err, i;
 	u64 rate;
-	int err;
-	int i;
 
 	if (!flow_action_has_entries(flow_action)) {
 		NL_SET_ERR_MSG_MOD(extack, "no tc actions specified");
@@ -423,11 +519,30 @@ static int otx2_tc_parse_actions(struct otx2_nic *nic,
 			req->index = act->rx_queue;
 			break;
 
+		case FLOW_ACTION_MIRRED_INGRESS:
+			target = act->dev;
+			priv = netdev_priv(target);
+			dummy_grp_update_req.pcifunc[num_intf] = priv->pcifunc;
+			dummy_grp_update_req.channel[num_intf] = priv->hw.tx_chan_base;
+			dummy_grp_update_req.dest_type[num_intf] = NIX_RX_RSS;
+			dummy_grp_update_req.rq_rss_index[num_intf] = 0;
+			mcast = true;
+			num_intf++;
+			break;
+
 		default:
 			return -EOPNOTSUPP;
 		}
 	}
 
+	if (mcast) {
+		err = otx2_tc_update_mcast(nic, req, extack, node,
+					   &dummy_grp_update_req,
+					   num_intf);
+		if (err)
+			return err;
+	}
+
 	if (nr_police > 1) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "rate limit police offload requires a single action");
@@ -522,6 +637,7 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node,
 	      BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) |
 	      BIT(FLOW_DISSECTOR_KEY_IPSEC) |
 	      BIT_ULL(FLOW_DISSECTOR_KEY_MPLS) |
+	      BIT_ULL(FLOW_DISSECTOR_KEY_ICMP) |
 	      BIT_ULL(FLOW_DISSECTOR_KEY_IP))))  {
 		netdev_info(nic->netdev, "unsupported flow used key 0x%llx",
 			    dissector->used_keys);
@@ -796,6 +912,19 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node,
 		}
 	}
 
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ICMP)) {
+		struct flow_match_icmp match;
+
+		flow_rule_match_icmp(rule, &match);
+
+		flow_spec->icmp_type = match.key->type;
+		flow_mask->icmp_type = match.mask->type;
+		req->features |= BIT_ULL(NPC_TYPE_ICMP);
+
+		flow_spec->icmp_code = match.key->code;
+		flow_mask->icmp_code = match.mask->code;
+		req->features |= BIT_ULL(NPC_CODE_ICMP);
+	}
 	return otx2_tc_parse_actions(nic, &rule->action, req, f, node);
 }
 
@@ -1033,6 +1162,7 @@ static int otx2_tc_del_flow(struct otx2_nic *nic,
 			    struct flow_cls_offload *tc_flow_cmd)
 {
 	struct otx2_flow_config *flow_cfg = nic->flow_cfg;
+	struct nix_mcast_grp_destroy_req *grp_destroy_req;
 	struct otx2_tc_flow *flow_node;
 	int err;
 
@@ -1044,6 +1174,11 @@ static int otx2_tc_del_flow(struct otx2_nic *nic,
 	}
 
 	if (flow_node->is_act_police) {
+		__clear_bit(flow_node->rq, &nic->rq_bmap);
+
+		if (nic->flags & OTX2_FLAG_INTF_DOWN)
+			goto free_mcam_flow;
+
 		mutex_lock(&nic->mbox.lock);
 
 		err = cn10k_map_unmap_rq_policer(nic, flow_node->rq,
@@ -1059,11 +1194,19 @@ static int otx2_tc_del_flow(struct otx2_nic *nic,
 				   "Unable to free leaf bandwidth profile(%d)\n",
 				   flow_node->leaf_profile);
 
-		__clear_bit(flow_node->rq, &nic->rq_bmap);
-
 		mutex_unlock(&nic->mbox.lock);
 	}
+	/* Remove the multicast/mirror related nodes */
+	if (flow_node->mcast_grp_idx != MCAST_INVALID_GRP) {
+		mutex_lock(&nic->mbox.lock);
+		grp_destroy_req = otx2_mbox_alloc_msg_nix_mcast_grp_destroy(&nic->mbox);
+		grp_destroy_req->mcast_grp_idx = flow_node->mcast_grp_idx;
+		otx2_sync_mbox_msg(&nic->mbox);
+		mutex_unlock(&nic->mbox.lock);
+	}
+
 
+free_mcam_flow:
 	otx2_del_mcam_flow_entry(nic, flow_node->entry, NULL);
 	otx2_tc_update_mcam_table(nic, flow_cfg, flow_node, false);
 	kfree_rcu(flow_node, rcu);
@@ -1083,6 +1226,11 @@ static int otx2_tc_add_flow(struct otx2_nic *nic,
 	if (!(nic->flags & OTX2_FLAG_TC_FLOWER_SUPPORT))
 		return -ENOMEM;
 
+	if (nic->flags & OTX2_FLAG_INTF_DOWN) {
+		NL_SET_ERR_MSG_MOD(extack, "Interface not initialized");
+		return -EINVAL;
+	}
+
 	if (flow_cfg->nr_flows == flow_cfg->max_flows) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Free MCAM entry not available to add the flow");
@@ -1096,6 +1244,7 @@ static int otx2_tc_add_flow(struct otx2_nic *nic,
 	spin_lock_init(&new_node->lock);
 	new_node->cookie = tc_flow_cmd->cookie;
 	new_node->prio = tc_flow_cmd->common.prio;
+	new_node->mcast_grp_idx = MCAST_INVALID_GRP;
 
 	memset(&dummy, 0, sizeof(struct npc_install_flow_req));
 
@@ -1442,3 +1591,45 @@ void otx2_shutdown_tc(struct otx2_nic *nic)
 	otx2_destroy_tc_flow_list(nic);
 }
 EXPORT_SYMBOL(otx2_shutdown_tc);
+
+static void otx2_tc_config_ingress_rule(struct otx2_nic *nic,
+					struct otx2_tc_flow *node)
+{
+	struct npc_install_flow_req *req;
+
+	if (otx2_tc_act_set_hw_police(nic, node))
+		return;
+
+	mutex_lock(&nic->mbox.lock);
+
+	req = otx2_mbox_alloc_msg_npc_install_flow(&nic->mbox);
+	if (!req)
+		goto err;
+
+	memcpy(req, &node->req, sizeof(struct npc_install_flow_req));
+
+	if (otx2_sync_mbox_msg(&nic->mbox))
+		netdev_err(nic->netdev,
+			   "Failed to install MCAM flow entry for ingress rule");
+err:
+	mutex_unlock(&nic->mbox.lock);
+}
+
+void otx2_tc_apply_ingress_police_rules(struct otx2_nic *nic)
+{
+	struct otx2_flow_config *flow_cfg = nic->flow_cfg;
+	struct otx2_tc_flow *node;
+
+	/* If any ingress policer rules exist for the interface then
+	 * apply those rules. Ingress policer rules depend on bandwidth
+	 * profiles linked to the receive queues. Since no receive queues
+	 * exist when interface is down, ingress policer rules are stored
+	 * and configured in hardware after all receive queues are allocated
+	 * in otx2_open.
+	 */
+	list_for_each_entry(node, &flow_cfg->flow_list_tc, list) {
+		if (node->is_act_police)
+			otx2_tc_config_ingress_rule(nic, node);
+	}
+}
+EXPORT_SYMBOL(otx2_tc_apply_ingress_police_rules);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index 6ee15f3c25ed..4d519ea833b2 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -512,11 +512,18 @@ static void otx2_adjust_adaptive_coalese(struct otx2_nic *pfvf, struct otx2_cq_p
 {
 	struct dim_sample dim_sample;
 	u64 rx_frames, rx_bytes;
+	u64 tx_frames, tx_bytes;
 
 	rx_frames = OTX2_GET_RX_STATS(RX_BCAST) + OTX2_GET_RX_STATS(RX_MCAST) +
 		OTX2_GET_RX_STATS(RX_UCAST);
 	rx_bytes = OTX2_GET_RX_STATS(RX_OCTS);
-	dim_update_sample(pfvf->napi_events, rx_frames, rx_bytes, &dim_sample);
+	tx_bytes = OTX2_GET_TX_STATS(TX_OCTS);
+	tx_frames = OTX2_GET_TX_STATS(TX_UCAST);
+
+	dim_update_sample(pfvf->napi_events,
+			  rx_frames + tx_frames,
+			  rx_bytes + tx_bytes,
+			  &dim_sample);
 	net_dim(&cq_poll->dim, dim_sample);
 }
 
@@ -558,16 +565,9 @@ int otx2_napi_handler(struct napi_struct *napi, int budget)
 		if (pfvf->flags & OTX2_FLAG_INTF_DOWN)
 			return workdone;
 
-		/* Check for adaptive interrupt coalesce */
-		if (workdone != 0 &&
-		    ((pfvf->flags & OTX2_FLAG_ADPTV_INT_COAL_ENABLED) ==
-		     OTX2_FLAG_ADPTV_INT_COAL_ENABLED)) {
-			/* Adjust irq coalese using net_dim */
+		/* Adjust irq coalese using net_dim */
+		if (pfvf->flags & OTX2_FLAG_ADPTV_INT_COAL_ENABLED)
 			otx2_adjust_adaptive_coalese(pfvf, cq_poll);
-			/* Update irq coalescing */
-			for (i = 0; i < pfvf->hw.cint_cnt; i++)
-				otx2_config_irq_coalescing(pfvf, i);
-		}
 
 		if (unlikely(!filled_cnt)) {
 			struct refill_work *work;
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 3cf6589cfdac..a6e91573f8da 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -1159,15 +1159,18 @@ static int mtk_init_fq_dma(struct mtk_eth *eth)
 	phy_ring_tail = eth->phy_scratch_ring + soc->txrx.txd_size * (cnt - 1);
 
 	for (i = 0; i < cnt; i++) {
+		dma_addr_t addr = dma_addr + i * MTK_QDMA_PAGE_SIZE;
 		struct mtk_tx_dma_v2 *txd;
 
 		txd = eth->scratch_ring + i * soc->txrx.txd_size;
-		txd->txd1 = dma_addr + i * MTK_QDMA_PAGE_SIZE;
+		txd->txd1 = addr;
 		if (i < cnt - 1)
 			txd->txd2 = eth->phy_scratch_ring +
 				    (i + 1) * soc->txrx.txd_size;
 
 		txd->txd3 = TX_DMA_PLEN0(MTK_QDMA_PAGE_SIZE);
+		if (MTK_HAS_CAPS(soc->caps, MTK_36BIT_DMA))
+			txd->txd3 |= TX_DMA_PREP_ADDR64(addr);
 		txd->txd4 = 0;
 		if (mtk_is_netsys_v2_or_greater(eth)) {
 			txd->txd5 = 0;
diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c
index 9a6744c0d458..c895e265ae0e 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed.c
+++ b/drivers/net/ethernet/mediatek/mtk_wed.c
@@ -670,7 +670,7 @@ mtk_wed_tx_buffer_alloc(struct mtk_wed_device *dev)
 		void *buf;
 		int s;
 
-		page = __dev_alloc_pages(GFP_KERNEL, 0);
+		page = __dev_alloc_page(GFP_KERNEL);
 		if (!page)
 			return -ENOMEM;
 
@@ -691,10 +691,11 @@ mtk_wed_tx_buffer_alloc(struct mtk_wed_device *dev)
 
 		for (s = 0; s < MTK_WED_BUF_PER_PAGE; s++) {
 			struct mtk_wdma_desc *desc = desc_ptr;
+			u32 ctrl;
 
 			desc->buf0 = cpu_to_le32(buf_phys);
 			if (!mtk_wed_is_v3_or_greater(dev->hw)) {
-				u32 txd_size, ctrl;
+				u32 txd_size;
 
 				txd_size = dev->wlan.init_buf(buf, buf_phys,
 							      token++);
@@ -708,11 +709,11 @@ mtk_wed_tx_buffer_alloc(struct mtk_wed_device *dev)
 					ctrl |= MTK_WDMA_DESC_CTRL_LAST_SEG0 |
 						FIELD_PREP(MTK_WDMA_DESC_CTRL_LEN1_V2,
 							   MTK_WED_BUF_SIZE - txd_size);
-				desc->ctrl = cpu_to_le32(ctrl);
 				desc->info = 0;
 			} else {
-				desc->ctrl = cpu_to_le32(token << 16);
+				ctrl = token << 16 | TX_DMA_PREP_ADDR64(buf_phys);
 			}
+			desc->ctrl = cpu_to_le32(ctrl);
 
 			desc_ptr += desc_size;
 			buf += MTK_WED_BUF_SIZE;
@@ -811,6 +812,7 @@ mtk_wed_hwrro_buffer_alloc(struct mtk_wed_device *dev)
 		buf_phys = page_phys;
 		for (s = 0; s < MTK_WED_RX_BUF_PER_PAGE; s++) {
 			desc->buf0 = cpu_to_le32(buf_phys);
+			desc->token = cpu_to_le32(RX_DMA_PREP_ADDR64(buf_phys));
 			buf_phys += MTK_WED_PAGE_BUF_SIZE;
 			desc++;
 		}
diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.c b/drivers/net/ethernet/mediatek/mtk_wed_wo.c
index 3bd51a3d6650..d58b07e7e123 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed_wo.c
+++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.c
@@ -142,7 +142,8 @@ mtk_wed_wo_queue_refill(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q,
 		dma_addr_t addr;
 		void *buf;
 
-		buf = page_frag_alloc(&q->cache, q->buf_size, GFP_ATOMIC);
+		buf = page_frag_alloc(&q->cache, q->buf_size,
+				      GFP_ATOMIC | GFP_DMA32);
 		if (!buf)
 			break;
 
@@ -291,6 +292,9 @@ mtk_wed_wo_queue_tx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q)
 	for (i = 0; i < q->n_desc; i++) {
 		struct mtk_wed_wo_queue_entry *entry = &q->entry[i];
 
+		if (!entry->buf)
+			continue;
+
 		dma_unmap_single(wo->hw->dev, entry->addr, entry->len,
 				 DMA_TO_DEVICE);
 		skb_free_frag(entry->buf);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 164a13272faa..619e1c3ef7f9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1258,8 +1258,8 @@ static int mlx4_en_check_rxfh_func(struct net_device *dev, u8 hfunc)
 	return -EINVAL;
 }
 
-static int mlx4_en_get_rxfh(struct net_device *dev, u32 *ring_index, u8 *key,
-			    u8 *hfunc)
+static int mlx4_en_get_rxfh(struct net_device *dev,
+			    struct ethtool_rxfh_param *rxfh)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	u32 n = mlx4_en_get_rxfh_indir_size(dev);
@@ -1269,19 +1269,19 @@ static int mlx4_en_get_rxfh(struct net_device *dev, u32 *ring_index, u8 *key,
 	rss_rings = rounddown_pow_of_two(rss_rings);
 
 	for (i = 0; i < n; i++) {
-		if (!ring_index)
+		if (!rxfh->indir)
 			break;
-		ring_index[i] = i % rss_rings;
+		rxfh->indir[i] = i % rss_rings;
 	}
-	if (key)
-		memcpy(key, priv->rss_key, MLX4_EN_RSS_KEY_SIZE);
-	if (hfunc)
-		*hfunc = priv->rss_hash_fn;
+	if (rxfh->key)
+		memcpy(rxfh->key, priv->rss_key, MLX4_EN_RSS_KEY_SIZE);
+	rxfh->hfunc = priv->rss_hash_fn;
 	return 0;
 }
 
-static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index,
-			    const u8 *key, const u8 hfunc)
+static int mlx4_en_set_rxfh(struct net_device *dev,
+			    struct ethtool_rxfh_param *rxfh,
+			    struct netlink_ext_ack *extack)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	u32 n = mlx4_en_get_rxfh_indir_size(dev);
@@ -1295,12 +1295,12 @@ static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index,
 	 * between rings
 	 */
 	for (i = 0; i < n; i++) {
-		if (!ring_index)
+		if (!rxfh->indir)
 			break;
-		if (i > 0 && !ring_index[i] && !rss_rings)
+		if (i > 0 && !rxfh->indir[i] && !rss_rings)
 			rss_rings = i;
 
-		if (ring_index[i] != (i % (rss_rings ?: n)))
+		if (rxfh->indir[i] != (i % (rss_rings ?: n)))
 			return -EINVAL;
 	}
 
@@ -1311,8 +1311,8 @@ static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index,
 	if (!is_power_of_2(rss_rings))
 		return -EINVAL;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE) {
-		err = mlx4_en_check_rxfh_func(dev, hfunc);
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE) {
+		err = mlx4_en_check_rxfh_func(dev, rxfh->hfunc);
 		if (err)
 			return err;
 	}
@@ -1323,12 +1323,12 @@ static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index,
 		mlx4_en_stop_port(dev, 1);
 	}
 
-	if (ring_index)
+	if (rxfh->indir)
 		priv->prof->rss_rings = rss_rings;
-	if (key)
-		memcpy(priv->rss_key, key, MLX4_EN_RSS_KEY_SIZE);
-	if (hfunc !=  ETH_RSS_HASH_NO_CHANGE)
-		priv->rss_hash_fn = hfunc;
+	if (rxfh->key)
+		memcpy(priv->rss_key, rxfh->key, MLX4_EN_RSS_KEY_SIZE);
+	if (rxfh->hfunc !=  ETH_RSS_HASH_NO_CHANGE)
+		priv->rss_hash_fn = rxfh->hfunc;
 
 	if (port_up) {
 		err = mlx4_en_start_port(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index f8f0a712c943..a7b1f9686c09 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -156,15 +156,18 @@ static u8 alloc_token(struct mlx5_cmd *cmd)
 	return token;
 }
 
-static int cmd_alloc_index(struct mlx5_cmd *cmd)
+static int cmd_alloc_index(struct mlx5_cmd *cmd, struct mlx5_cmd_work_ent *ent)
 {
 	unsigned long flags;
 	int ret;
 
 	spin_lock_irqsave(&cmd->alloc_lock, flags);
 	ret = find_first_bit(&cmd->vars.bitmask, cmd->vars.max_reg_cmds);
-	if (ret < cmd->vars.max_reg_cmds)
+	if (ret < cmd->vars.max_reg_cmds) {
 		clear_bit(ret, &cmd->vars.bitmask);
+		ent->idx = ret;
+		cmd->ent_arr[ent->idx] = ent;
+	}
 	spin_unlock_irqrestore(&cmd->alloc_lock, flags);
 
 	return ret < cmd->vars.max_reg_cmds ? ret : -ENOMEM;
@@ -979,7 +982,7 @@ static void cmd_work_handler(struct work_struct *work)
 	sem = ent->page_queue ? &cmd->vars.pages_sem : &cmd->vars.sem;
 	down(sem);
 	if (!ent->page_queue) {
-		alloc_ret = cmd_alloc_index(cmd);
+		alloc_ret = cmd_alloc_index(cmd, ent);
 		if (alloc_ret < 0) {
 			mlx5_core_err_rl(dev, "failed to allocate command entry\n");
 			if (ent->callback) {
@@ -994,15 +997,14 @@ static void cmd_work_handler(struct work_struct *work)
 			up(sem);
 			return;
 		}
-		ent->idx = alloc_ret;
 	} else {
 		ent->idx = cmd->vars.max_reg_cmds;
 		spin_lock_irqsave(&cmd->alloc_lock, flags);
 		clear_bit(ent->idx, &cmd->vars.bitmask);
+		cmd->ent_arr[ent->idx] = ent;
 		spin_unlock_irqrestore(&cmd->alloc_lock, flags);
 	}
 
-	cmd->ent_arr[ent->idx] = ent;
 	lay = get_inst(cmd, ent->idx);
 	ent->lay = lay;
 	memset(lay, 0, sizeof(*lay));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/crdump.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/crdump.c
index 28d02749d3c4..7659ad21e6e5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/crdump.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/crdump.c
@@ -55,7 +55,10 @@ int mlx5_crdump_collect(struct mlx5_core_dev *dev, u32 *cr_data)
 	ret = mlx5_vsc_sem_set_space(dev, MLX5_SEMAPHORE_SW_RESET,
 				     MLX5_VSC_LOCK);
 	if (ret) {
-		mlx5_core_warn(dev, "Failed to lock SW reset semaphore\n");
+		if (ret == -EBUSY)
+			mlx5_core_info(dev, "SW reset semaphore is already in use\n");
+		else
+			mlx5_core_warn(dev, "Failed to lock SW reset semaphore\n");
 		goto unlock_gw;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index 76d27d2ee40c..080e7eab52c7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -718,7 +718,7 @@ static void mlx5_fw_tracer_handle_traces(struct work_struct *work)
 
 	while (block_timestamp > tracer->last_timestamp) {
 		/* Check block override if it's not the first block */
-		if (!tracer->last_timestamp) {
+		if (tracer->last_timestamp) {
 			u64 *ts_event;
 			/* To avoid block override be the HW in case of buffer
 			 * wraparound, the time stamp of the previous block
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
index 2cd81bb32c66..18fed2b34fb1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
@@ -36,11 +36,17 @@ static int mlx5_dpll_clock_id_get(struct mlx5_core_dev *mdev, u64 *clock_id)
 	return 0;
 }
 
+struct mlx5_dpll_synce_status {
+	enum mlx5_msees_admin_status admin_status;
+	enum mlx5_msees_oper_status oper_status;
+	bool ho_acq;
+	bool oper_freq_measure;
+	s32 frequency_diff;
+};
+
 static int
 mlx5_dpll_synce_status_get(struct mlx5_core_dev *mdev,
-			   enum mlx5_msees_admin_status *admin_status,
-			   enum mlx5_msees_oper_status *oper_status,
-			   bool *ho_acq)
+			   struct mlx5_dpll_synce_status *synce_status)
 {
 	u32 out[MLX5_ST_SZ_DW(msees_reg)] = {};
 	u32 in[MLX5_ST_SZ_DW(msees_reg)] = {};
@@ -50,11 +56,11 @@ mlx5_dpll_synce_status_get(struct mlx5_core_dev *mdev,
 				   MLX5_REG_MSEES, 0, 0);
 	if (err)
 		return err;
-	if (admin_status)
-		*admin_status = MLX5_GET(msees_reg, out, admin_status);
-	*oper_status = MLX5_GET(msees_reg, out, oper_status);
-	if (ho_acq)
-		*ho_acq = MLX5_GET(msees_reg, out, ho_acq);
+	synce_status->admin_status = MLX5_GET(msees_reg, out, admin_status);
+	synce_status->oper_status = MLX5_GET(msees_reg, out, oper_status);
+	synce_status->ho_acq = MLX5_GET(msees_reg, out, ho_acq);
+	synce_status->oper_freq_measure = MLX5_GET(msees_reg, out, oper_freq_measure);
+	synce_status->frequency_diff = MLX5_GET(msees_reg, out, frequency_diff);
 	return 0;
 }
 
@@ -67,21 +73,23 @@ mlx5_dpll_synce_status_set(struct mlx5_core_dev *mdev,
 
 	MLX5_SET(msees_reg, in, field_select,
 		 MLX5_MSEES_FIELD_SELECT_ENABLE |
+		 MLX5_MSEES_FIELD_SELECT_ADMIN_FREQ_MEASURE |
 		 MLX5_MSEES_FIELD_SELECT_ADMIN_STATUS);
 	MLX5_SET(msees_reg, in, admin_status, admin_status);
+	MLX5_SET(msees_reg, in, admin_freq_measure, true);
 	return mlx5_core_access_reg(mdev, in, sizeof(in), out, sizeof(out),
 				    MLX5_REG_MSEES, 0, 1);
 }
 
 static enum dpll_lock_status
-mlx5_dpll_lock_status_get(enum mlx5_msees_oper_status oper_status, bool ho_acq)
+mlx5_dpll_lock_status_get(struct mlx5_dpll_synce_status *synce_status)
 {
-	switch (oper_status) {
+	switch (synce_status->oper_status) {
 	case MLX5_MSEES_OPER_STATUS_SELF_TRACK:
 		fallthrough;
 	case MLX5_MSEES_OPER_STATUS_OTHER_TRACK:
-		return ho_acq ? DPLL_LOCK_STATUS_LOCKED_HO_ACQ :
-				DPLL_LOCK_STATUS_LOCKED;
+		return synce_status->ho_acq ? DPLL_LOCK_STATUS_LOCKED_HO_ACQ :
+					      DPLL_LOCK_STATUS_LOCKED;
 	case MLX5_MSEES_OPER_STATUS_HOLDOVER:
 		fallthrough;
 	case MLX5_MSEES_OPER_STATUS_FAIL_HOLDOVER:
@@ -92,31 +100,37 @@ mlx5_dpll_lock_status_get(enum mlx5_msees_oper_status oper_status, bool ho_acq)
 }
 
 static enum dpll_pin_state
-mlx5_dpll_pin_state_get(enum mlx5_msees_admin_status admin_status,
-			enum mlx5_msees_oper_status oper_status)
+mlx5_dpll_pin_state_get(struct mlx5_dpll_synce_status *synce_status)
 {
-	return (admin_status == MLX5_MSEES_ADMIN_STATUS_TRACK &&
-		(oper_status == MLX5_MSEES_OPER_STATUS_SELF_TRACK ||
-		 oper_status == MLX5_MSEES_OPER_STATUS_OTHER_TRACK)) ?
+	return (synce_status->admin_status == MLX5_MSEES_ADMIN_STATUS_TRACK &&
+		(synce_status->oper_status == MLX5_MSEES_OPER_STATUS_SELF_TRACK ||
+		 synce_status->oper_status == MLX5_MSEES_OPER_STATUS_OTHER_TRACK)) ?
 	       DPLL_PIN_STATE_CONNECTED : DPLL_PIN_STATE_DISCONNECTED;
 }
 
+static int
+mlx5_dpll_pin_ffo_get(struct mlx5_dpll_synce_status *synce_status,
+		      s64 *ffo)
+{
+	if (!synce_status->oper_freq_measure)
+		return -ENODATA;
+	*ffo = synce_status->frequency_diff;
+	return 0;
+}
+
 static int mlx5_dpll_device_lock_status_get(const struct dpll_device *dpll,
 					    void *priv,
 					    enum dpll_lock_status *status,
 					    struct netlink_ext_ack *extack)
 {
-	enum mlx5_msees_oper_status oper_status;
+	struct mlx5_dpll_synce_status synce_status;
 	struct mlx5_dpll *mdpll = priv;
-	bool ho_acq;
 	int err;
 
-	err = mlx5_dpll_synce_status_get(mdpll->mdev, NULL,
-					 &oper_status, &ho_acq);
+	err = mlx5_dpll_synce_status_get(mdpll->mdev, &synce_status);
 	if (err)
 		return err;
-
-	*status = mlx5_dpll_lock_status_get(oper_status, ho_acq);
+	*status = mlx5_dpll_lock_status_get(&synce_status);
 	return 0;
 }
 
@@ -128,18 +142,9 @@ static int mlx5_dpll_device_mode_get(const struct dpll_device *dpll,
 	return 0;
 }
 
-static bool mlx5_dpll_device_mode_supported(const struct dpll_device *dpll,
-					    void *priv,
-					    enum dpll_mode mode,
-					    struct netlink_ext_ack *extack)
-{
-	return mode == DPLL_MODE_MANUAL;
-}
-
 static const struct dpll_device_ops mlx5_dpll_device_ops = {
 	.lock_status_get = mlx5_dpll_device_lock_status_get,
 	.mode_get = mlx5_dpll_device_mode_get,
-	.mode_supported = mlx5_dpll_device_mode_supported,
 };
 
 static int mlx5_dpll_pin_direction_get(const struct dpll_pin *pin,
@@ -160,16 +165,14 @@ static int mlx5_dpll_state_on_dpll_get(const struct dpll_pin *pin,
 				       enum dpll_pin_state *state,
 				       struct netlink_ext_ack *extack)
 {
-	enum mlx5_msees_admin_status admin_status;
-	enum mlx5_msees_oper_status oper_status;
+	struct mlx5_dpll_synce_status synce_status;
 	struct mlx5_dpll *mdpll = pin_priv;
 	int err;
 
-	err = mlx5_dpll_synce_status_get(mdpll->mdev, &admin_status,
-					 &oper_status, NULL);
+	err = mlx5_dpll_synce_status_get(mdpll->mdev, &synce_status);
 	if (err)
 		return err;
-	*state = mlx5_dpll_pin_state_get(admin_status, oper_status);
+	*state = mlx5_dpll_pin_state_get(&synce_status);
 	return 0;
 }
 
@@ -188,10 +191,25 @@ static int mlx5_dpll_state_on_dpll_set(const struct dpll_pin *pin,
 					  MLX5_MSEES_ADMIN_STATUS_FREE_RUNNING);
 }
 
+static int mlx5_dpll_ffo_get(const struct dpll_pin *pin, void *pin_priv,
+			     const struct dpll_device *dpll, void *dpll_priv,
+			     s64 *ffo, struct netlink_ext_ack *extack)
+{
+	struct mlx5_dpll_synce_status synce_status;
+	struct mlx5_dpll *mdpll = pin_priv;
+	int err;
+
+	err = mlx5_dpll_synce_status_get(mdpll->mdev, &synce_status);
+	if (err)
+		return err;
+	return mlx5_dpll_pin_ffo_get(&synce_status, ffo);
+}
+
 static const struct dpll_pin_ops mlx5_dpll_pins_ops = {
 	.direction_get = mlx5_dpll_pin_direction_get,
 	.state_on_dpll_get = mlx5_dpll_state_on_dpll_get,
 	.state_on_dpll_set = mlx5_dpll_state_on_dpll_set,
+	.ffo_get = mlx5_dpll_ffo_get,
 };
 
 static const struct dpll_pin_properties mlx5_dpll_pin_properties = {
@@ -211,19 +229,16 @@ static void mlx5_dpll_periodic_work(struct work_struct *work)
 {
 	struct mlx5_dpll *mdpll = container_of(work, struct mlx5_dpll,
 					       work.work);
-	enum mlx5_msees_admin_status admin_status;
-	enum mlx5_msees_oper_status oper_status;
+	struct mlx5_dpll_synce_status synce_status;
 	enum dpll_lock_status lock_status;
 	enum dpll_pin_state pin_state;
-	bool ho_acq;
 	int err;
 
-	err = mlx5_dpll_synce_status_get(mdpll->mdev, &admin_status,
-					 &oper_status, &ho_acq);
+	err = mlx5_dpll_synce_status_get(mdpll->mdev, &synce_status);
 	if (err)
 		goto err_out;
-	lock_status = mlx5_dpll_lock_status_get(oper_status, ho_acq);
-	pin_state = mlx5_dpll_pin_state_get(admin_status, oper_status);
+	lock_status = mlx5_dpll_lock_status_get(&synce_status);
+	pin_state = mlx5_dpll_pin_state_get(&synce_status);
 
 	if (!mdpll->last.valid)
 		goto invalid_out;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index b2a5da9739d2..0bfe1ca8a364 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -72,7 +72,6 @@ struct page_pool;
 #define MLX5E_HW2SW_MTU(params, hwmtu) ((hwmtu) - ((params)->hard_mtu))
 #define MLX5E_SW2HW_MTU(params, swmtu) ((swmtu) + ((params)->hard_mtu))
 
-#define MLX5E_MAX_NUM_TC	8
 #define MLX5E_MAX_NUM_MQPRIO_CH_TC TC_QOPT_MAX_QUEUE
 
 #define MLX5_RX_HEADROOM NET_SKB_PAD
@@ -364,7 +363,7 @@ struct mlx5e_cq {
 	/* control */
 	struct net_device         *netdev;
 	struct mlx5_core_dev      *mdev;
-	struct mlx5e_priv         *priv;
+	struct workqueue_struct   *workqueue;
 	struct mlx5_wq_ctrl        wq_ctrl;
 } ____cacheline_aligned_in_smp;
 
@@ -484,10 +483,12 @@ struct mlx5e_xdp_info_fifo {
 
 struct mlx5e_xdpsq;
 struct mlx5e_xmit_data;
+struct xsk_tx_metadata;
 typedef int (*mlx5e_fp_xmit_xdp_frame_check)(struct mlx5e_xdpsq *);
 typedef bool (*mlx5e_fp_xmit_xdp_frame)(struct mlx5e_xdpsq *,
 					struct mlx5e_xmit_data *,
-					int);
+					int,
+					struct xsk_tx_metadata *);
 
 struct mlx5e_xdpsq {
 	/* data path */
@@ -756,7 +757,7 @@ struct mlx5e_channel {
 	/* data path */
 	struct mlx5e_rq            rq;
 	struct mlx5e_xdpsq         rq_xdpsq;
-	struct mlx5e_txqsq         sq[MLX5E_MAX_NUM_TC];
+	struct mlx5e_txqsq         sq[MLX5_MAX_NUM_TC];
 	struct mlx5e_icosq         icosq;   /* internal control operations */
 	struct mlx5e_txqsq __rcu * __rcu *qos_sqs;
 	bool                       xdp;
@@ -806,7 +807,7 @@ struct mlx5e_channels {
 
 struct mlx5e_channel_stats {
 	struct mlx5e_ch_stats ch;
-	struct mlx5e_sq_stats sq[MLX5E_MAX_NUM_TC];
+	struct mlx5e_sq_stats sq[MLX5_MAX_NUM_TC];
 	struct mlx5e_rq_stats rq;
 	struct mlx5e_rq_stats xskrq;
 	struct mlx5e_xdpsq_stats rq_xdpsq;
@@ -816,8 +817,8 @@ struct mlx5e_channel_stats {
 
 struct mlx5e_ptp_stats {
 	struct mlx5e_ch_stats ch;
-	struct mlx5e_sq_stats sq[MLX5E_MAX_NUM_TC];
-	struct mlx5e_ptp_cq_stats cq[MLX5E_MAX_NUM_TC];
+	struct mlx5e_sq_stats sq[MLX5_MAX_NUM_TC];
+	struct mlx5e_ptp_cq_stats cq[MLX5_MAX_NUM_TC];
 	struct mlx5e_rq_stats rq;
 } ____cacheline_aligned_in_smp;
 
@@ -826,6 +827,7 @@ enum {
 	MLX5E_STATE_DESTROYING,
 	MLX5E_STATE_XDP_TX_ENABLED,
 	MLX5E_STATE_XDP_ACTIVE,
+	MLX5E_STATE_CHANNELS_ACTIVE,
 };
 
 struct mlx5e_modify_sq_param {
@@ -884,7 +886,6 @@ struct mlx5e_priv {
 	struct mlx5e_rq            drop_rq;
 
 	struct mlx5e_channels      channels;
-	u32                        tisn[MLX5_MAX_PORTS][MLX5E_MAX_NUM_TC];
 	struct mlx5e_rx_res       *rx_res;
 	u32                       *tx_rates;
 
@@ -982,6 +983,8 @@ struct mlx5e_profile {
 	void	(*update_stats)(struct mlx5e_priv *priv);
 	void	(*update_carrier)(struct mlx5e_priv *priv);
 	int	(*max_nch_limit)(struct mlx5_core_dev *mdev);
+	u32	(*get_tisn)(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv,
+			    u8 lag_port, u8 tc);
 	unsigned int (*stats_grps_num)(struct mlx5e_priv *priv);
 	mlx5e_stats_grp_t *stats_grps;
 	const struct mlx5e_rx_handlers *rx_handlers;
@@ -989,6 +992,11 @@ struct mlx5e_profile {
 	u32     features;
 };
 
+u32 mlx5e_profile_get_tisn(struct mlx5_core_dev *mdev,
+			   struct mlx5e_priv *priv,
+			   const struct mlx5e_profile *profile,
+			   u8 lag_port, u8 tc);
+
 #define mlx5e_profile_feature_cap(profile, feature)	\
 	((profile)->features & BIT(MLX5E_PROFILE_FEATURE_##feature))
 
@@ -1036,6 +1044,8 @@ int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
 void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq);
 
 struct mlx5e_create_cq_param {
+	struct net_device *netdev;
+	struct workqueue_struct *wq;
 	struct napi_struct *napi;
 	struct mlx5e_ch_stats *ch_stats;
 	int node;
@@ -1043,7 +1053,7 @@ struct mlx5e_create_cq_param {
 };
 
 struct mlx5e_cq_param;
-int mlx5e_open_cq(struct mlx5e_priv *priv, struct dim_cq_moder moder,
+int mlx5e_open_cq(struct mlx5_core_dev *mdev, struct dim_cq_moder moder,
 		  struct mlx5e_cq_param *param, struct mlx5e_create_cq_param *ccp,
 		  struct mlx5e_cq *cq);
 void mlx5e_close_cq(struct mlx5e_cq *cq);
@@ -1130,8 +1140,6 @@ void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq);
 int mlx5e_create_tis(struct mlx5_core_dev *mdev, void *in, u32 *tisn);
 void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn);
 
-int mlx5e_create_tises(struct mlx5e_priv *priv);
-void mlx5e_destroy_tises(struct mlx5e_priv *priv);
 int mlx5e_update_nic_rx(struct mlx5e_priv *priv);
 void mlx5e_update_carrier(struct mlx5e_priv *priv);
 int mlx5e_close(struct net_device *netdev);
@@ -1173,9 +1181,9 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
 				     struct ethtool_link_ksettings *link_ksettings);
 int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 				     const struct ethtool_link_ksettings *link_ksettings);
-int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc);
-int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key,
-		   const u8 hfunc);
+int mlx5e_get_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh);
+int mlx5e_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh,
+		   struct netlink_ext_ack *extack);
 u32 mlx5e_ethtool_get_rxfh_key_size(struct mlx5e_priv *priv);
 u32 mlx5e_ethtool_get_rxfh_indir_size(struct mlx5e_priv *priv);
 int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c
index be83ad9db82a..e1283531e0b8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c
@@ -154,6 +154,7 @@ static int fs_udp_create_groups(struct mlx5e_flow_table *ft, enum fs_udp_type ty
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if  (!in || !ft->g) {
 		kfree(ft->g);
+		ft->g = NULL;
 		kvfree(in);
 		return -ENOMEM;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
index 254c84739046..40c8df111754 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
@@ -36,7 +36,7 @@ int mlx5e_monitor_counter_supported(struct mlx5e_priv *priv)
 	return true;
 }
 
-void mlx5e_monitor_counter_arm(struct mlx5e_priv *priv)
+static void mlx5e_monitor_counter_arm(struct mlx5e_priv *priv)
 {
 	u32 in[MLX5_ST_SZ_DW(arm_monitor_counter_in)] = {};
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.h
index e1ac4b3d22fb..6beba7f075c1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.h
@@ -7,6 +7,5 @@
 int  mlx5e_monitor_counter_supported(struct mlx5e_priv *priv);
 void mlx5e_monitor_counter_init(struct mlx5e_priv *priv);
 void mlx5e_monitor_counter_cleanup(struct mlx5e_priv *priv);
-void mlx5e_monitor_counter_arm(struct mlx5e_priv *priv);
 
 #endif /* __MLX5_MONITOR_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index e097f336e1c4..284253b79266 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -669,6 +669,8 @@ void mlx5e_build_rq_params(struct mlx5_core_dev *mdev,
 void mlx5e_build_create_cq_param(struct mlx5e_create_cq_param *ccp, struct mlx5e_channel *c)
 {
 	*ccp = (struct mlx5e_create_cq_param) {
+		.netdev = c->netdev,
+		.wq = c->priv->wq,
 		.napi = &c->napi,
 		.ch_stats = c->stats,
 		.node = cpu_to_node(c->cpu),
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index bb11e644d24f..c206cc0a8483 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -177,6 +177,8 @@ static void mlx5e_ptpsq_mark_ts_cqes_undelivered(struct mlx5e_ptpsq *ptpsq,
 
 static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq,
 				    struct mlx5_cqe64 *cqe,
+				    u8 *md_buff,
+				    u8 *md_buff_sz,
 				    int budget)
 {
 	struct mlx5e_ptp_port_ts_cqe_list *pending_cqe_list = ptpsq->ts_cqe_pending_list;
@@ -211,19 +213,24 @@ static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq,
 	mlx5e_ptpsq_mark_ts_cqes_undelivered(ptpsq, hwtstamp);
 out:
 	napi_consume_skb(skb, budget);
-	mlx5e_ptp_metadata_fifo_push(&ptpsq->metadata_freelist, metadata_id);
+	md_buff[*md_buff_sz++] = metadata_id;
 	if (unlikely(mlx5e_ptp_metadata_map_unhealthy(&ptpsq->metadata_map)) &&
 	    !test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
 		queue_work(ptpsq->txqsq.priv->wq, &ptpsq->report_unhealthy_work);
 }
 
-static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget)
+static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int napi_budget)
 {
 	struct mlx5e_ptpsq *ptpsq = container_of(cq, struct mlx5e_ptpsq, ts_cq);
-	struct mlx5_cqwq *cqwq = &cq->wq;
+	int budget = min(napi_budget, MLX5E_TX_CQ_POLL_BUDGET);
+	u8 metadata_buff[MLX5E_TX_CQ_POLL_BUDGET];
+	u8 metadata_buff_sz = 0;
+	struct mlx5_cqwq *cqwq;
 	struct mlx5_cqe64 *cqe;
 	int work_done = 0;
 
+	cqwq = &cq->wq;
+
 	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &ptpsq->txqsq.state)))
 		return false;
 
@@ -234,7 +241,8 @@ static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget)
 	do {
 		mlx5_cqwq_pop(cqwq);
 
-		mlx5e_ptp_handle_ts_cqe(ptpsq, cqe, budget);
+		mlx5e_ptp_handle_ts_cqe(ptpsq, cqe,
+					metadata_buff, &metadata_buff_sz, napi_budget);
 	} while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq)));
 
 	mlx5_cqwq_update_db_record(cqwq);
@@ -242,6 +250,10 @@ static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget)
 	/* ensure cq space is freed before enabling more cqes */
 	wmb();
 
+	while (metadata_buff_sz > 0)
+		mlx5e_ptp_metadata_fifo_push(&ptpsq->metadata_freelist,
+					     metadata_buff[--metadata_buff_sz]);
+
 	mlx5e_txqsq_wake(&ptpsq->txqsq);
 
 	return work_done == budget;
@@ -506,9 +518,11 @@ static int mlx5e_ptp_open_txqsqs(struct mlx5e_ptp *c,
 
 	for (tc = 0; tc < num_tc; tc++) {
 		int txq_ix = ix_base + tc;
+		u32 tisn;
 
-		err = mlx5e_ptp_open_txqsq(c, c->priv->tisn[c->lag_port][tc], txq_ix,
-					   cparams, tc, &c->ptpsq[tc]);
+		tisn = mlx5e_profile_get_tisn(c->mdev, c->priv, c->priv->profile,
+					      c->lag_port, tc);
+		err = mlx5e_ptp_open_txqsq(c, tisn, txq_ix, cparams, tc, &c->ptpsq[tc]);
 		if (err)
 			goto close_txqsq;
 	}
@@ -543,6 +557,8 @@ static int mlx5e_ptp_open_tx_cqs(struct mlx5e_ptp *c,
 
 	num_tc = mlx5e_get_dcb_num_tc(params);
 
+	ccp.netdev   = c->netdev;
+	ccp.wq       = c->priv->wq;
 	ccp.node     = dev_to_node(mlx5_core_dma_dev(c->mdev));
 	ccp.ch_stats = c->stats;
 	ccp.napi     = &c->napi;
@@ -553,7 +569,7 @@ static int mlx5e_ptp_open_tx_cqs(struct mlx5e_ptp *c,
 	for (tc = 0; tc < num_tc; tc++) {
 		struct mlx5e_cq *cq = &c->ptpsq[tc].txqsq.cq;
 
-		err = mlx5e_open_cq(c->priv, ptp_moder, cq_param, &ccp, cq);
+		err = mlx5e_open_cq(c->mdev, ptp_moder, cq_param, &ccp, cq);
 		if (err)
 			goto out_err_txqsq_cq;
 	}
@@ -562,7 +578,7 @@ static int mlx5e_ptp_open_tx_cqs(struct mlx5e_ptp *c,
 		struct mlx5e_cq *cq = &c->ptpsq[tc].ts_cq;
 		struct mlx5e_ptpsq *ptpsq = &c->ptpsq[tc];
 
-		err = mlx5e_open_cq(c->priv, ptp_moder, cq_param, &ccp, cq);
+		err = mlx5e_open_cq(c->mdev, ptp_moder, cq_param, &ccp, cq);
 		if (err)
 			goto out_err_ts_cq;
 
@@ -590,6 +606,8 @@ static int mlx5e_ptp_open_rx_cq(struct mlx5e_ptp *c,
 	struct mlx5e_cq_param *cq_param;
 	struct mlx5e_cq *cq = &c->rq.cq;
 
+	ccp.netdev   = c->netdev;
+	ccp.wq       = c->priv->wq;
 	ccp.node     = dev_to_node(mlx5_core_dma_dev(c->mdev));
 	ccp.ch_stats = c->stats;
 	ccp.napi     = &c->napi;
@@ -597,7 +615,7 @@ static int mlx5e_ptp_open_rx_cq(struct mlx5e_ptp *c,
 
 	cq_param = &cparams->rq_param.cqp;
 
-	return mlx5e_open_cq(c->priv, ptp_moder, cq_param, &ccp, cq);
+	return mlx5e_open_cq(c->mdev, ptp_moder, cq_param, &ccp, cq);
 }
 
 static void mlx5e_ptp_close_tx_cqs(struct mlx5e_ptp *c)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
index 7b700d0f956a..86f1854698b4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
@@ -49,7 +49,7 @@ enum {
 
 struct mlx5e_ptp {
 	/* data path */
-	struct mlx5e_ptpsq         ptpsq[MLX5E_MAX_NUM_TC];
+	struct mlx5e_ptpsq         ptpsq[MLX5_MAX_NUM_TC];
 	struct mlx5e_rq            rq;
 	struct napi_struct         napi;
 	struct device             *pdev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
index 244bc15a42ab..34adf8c3f81a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
@@ -77,6 +77,7 @@ int mlx5e_open_qos_sq(struct mlx5e_priv *priv, struct mlx5e_channels *chs,
 	struct mlx5e_params *params;
 	struct mlx5e_channel *c;
 	struct mlx5e_txqsq *sq;
+	u32 tisn;
 
 	params = &chs->params;
 
@@ -123,11 +124,13 @@ int mlx5e_open_qos_sq(struct mlx5e_priv *priv, struct mlx5e_channels *chs,
 	memset(&param_cq, 0, sizeof(param_cq));
 	mlx5e_build_sq_param(priv->mdev, params, &param_sq);
 	mlx5e_build_tx_cq_param(priv->mdev, params, &param_cq);
-	err = mlx5e_open_cq(priv, params->tx_cq_moderation, &param_cq, &ccp, &sq->cq);
+	err = mlx5e_open_cq(c->mdev, params->tx_cq_moderation, &param_cq, &ccp, &sq->cq);
 	if (err)
 		goto err_free_sq;
-	err = mlx5e_open_txqsq(c, priv->tisn[c->lag_port][0], txq_ix, params,
-			       &param_sq, sq, 0, hw_id,
+
+	tisn = mlx5e_profile_get_tisn(c->mdev, c->priv, c->priv->profile,
+				      c->lag_port, 0);
+	err = mlx5e_open_txqsq(c, tisn, txq_ix, params, &param_sq, sq, 0, hw_id,
 			       priv->htb_qos_sq_stats[node_qid]);
 	if (err)
 		goto err_close_cq;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
index b12fe3c5a258..a55452c69f06 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -147,6 +147,20 @@ mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv,
 	}
 }
 
+static void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv,
+				    struct tc_cls_matchall_offload *ma)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	u64 dbytes;
+	u64 dpkts;
+
+	dpkts = priv->stats.rep_stats.vport_rx_packets - rpriv->prev_vf_vport_stats.rx_packets;
+	dbytes = priv->stats.rep_stats.vport_rx_bytes - rpriv->prev_vf_vport_stats.rx_bytes;
+	mlx5e_stats_copy_rep_stats(&rpriv->prev_vf_vport_stats, &priv->stats.rep_stats);
+	flow_stats_update(&ma->stats, dbytes, dpkts, 0, jiffies,
+			  FLOW_ACTION_HW_STATS_DELAYED);
+}
+
 static
 int mlx5e_rep_setup_tc_cls_matchall(struct mlx5e_priv *priv,
 				    struct tc_cls_matchall_offload *ma)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
index fea8c0a5fe89..4358798d6ce1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -492,11 +492,11 @@ static int mlx5e_rx_reporter_dump(struct devlink_health_reporter *reporter,
 
 void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq)
 {
-	char icosq_str[MLX5E_REPORTER_PER_Q_MAX_LEN] = {};
 	char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN];
 	struct mlx5e_icosq *icosq = rq->icosq;
 	struct mlx5e_priv *priv = rq->priv;
 	struct mlx5e_err_ctx err_ctx = {};
+	char icosq_str[32] = {};
 
 	err_ctx.ctx = rq;
 	err_ctx.recover = mlx5e_rx_reporter_timeout_recover;
@@ -505,7 +505,7 @@ void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq)
 	if (icosq)
 		snprintf(icosq_str, sizeof(icosq_str), "ICOSQ: 0x%x, ", icosq->sqn);
 	snprintf(err_str, sizeof(err_str),
-		 "RX timeout on channel: %d, %sRQ: 0x%x, CQ: 0x%x",
+		 "RX timeout on channel: %d, %s RQ: 0x%x, CQ: 0x%x",
 		 rq->ix, icosq_str, rq->rqn, rq->cq.mcq.cqn);
 
 	mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c
index f63402c48028..1b418095b79a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c
@@ -197,7 +197,7 @@ parse_mirred_encap(struct mlx5e_tc_act_parse_state *parse_state,
 	}
 	esw_attr->dests[esw_attr->out_count].flags |= MLX5_ESW_DEST_ENCAP;
 	esw_attr->out_count++;
-	/* attr->dests[].rep is resolved when we handle encap */
+	/* attr->dests[].vport is resolved when we handle encap */
 
 	return 0;
 }
@@ -270,7 +270,8 @@ parse_mirred(struct mlx5e_tc_act_parse_state *parse_state,
 
 	out_priv = netdev_priv(out_dev);
 	rpriv = out_priv->ppriv;
-	esw_attr->dests[esw_attr->out_count].rep = rpriv->rep;
+	esw_attr->dests[esw_attr->out_count].vport_valid = true;
+	esw_attr->dests[esw_attr->out_count].vport = rpriv->rep->vport;
 	esw_attr->dests[esw_attr->out_count].mdev = out_priv->mdev;
 
 	esw_attr->out_count++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c
index 368a95fa77d3..b14cd62edffc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c
@@ -48,7 +48,8 @@ mlx5e_tc_act_pedit_parse_action(struct mlx5e_priv *priv,
 				struct pedit_headers_action *hdrs,
 				struct netlink_ext_ack *extack)
 {
-	u8 cmd = (act->id == FLOW_ACTION_MANGLE) ? 0 : 1;
+	u8 cmd = (act->id == FLOW_ACTION_MANGLE) ? TCA_PEDIT_KEY_EX_CMD_SET :
+						   TCA_PEDIT_KEY_EX_CMD_ADD;
 	u8 htype = act->mangle.htype;
 	int err = -EOPNOTSUPP;
 	u32 mask, val, offset;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c
index 4e923a2874ae..86bf007fd05b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c
@@ -83,6 +83,9 @@ mlx5e_tc_post_act_offload(struct mlx5e_post_act *post_act,
 	struct mlx5_flow_spec *spec;
 	int err;
 
+	if (IS_ERR(post_act))
+		return PTR_ERR(post_act);
+
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
 	if (!spec)
 		return -ENOMEM;
@@ -111,6 +114,9 @@ mlx5e_tc_post_act_add(struct mlx5e_post_act *post_act, struct mlx5_flow_attr *po
 	struct mlx5e_post_act_handle *handle;
 	int err;
 
+	if (IS_ERR(post_act))
+		return ERR_CAST(post_act);
+
 	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
 	if (!handle)
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 00a04fdd756f..8dfb57f712b0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -302,6 +302,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 
 	e->encap_size = ipv4_encap_size;
 	e->encap_header = encap_header;
+	encap_header = NULL;
 
 	if (!(nud_state & NUD_VALID)) {
 		neigh_event_send(attr.n, NULL);
@@ -313,8 +314,8 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 
 	memset(&reformat_params, 0, sizeof(reformat_params));
 	reformat_params.type = e->reformat_type;
-	reformat_params.size = ipv4_encap_size;
-	reformat_params.data = encap_header;
+	reformat_params.size = e->encap_size;
+	reformat_params.data = e->encap_header;
 	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params,
 						     MLX5_FLOW_NAMESPACE_FDB);
 	if (IS_ERR(e->pkt_reformat)) {
@@ -407,6 +408,7 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv,
 	e->encap_size = ipv4_encap_size;
 	kfree(e->encap_header);
 	e->encap_header = encap_header;
+	encap_header = NULL;
 
 	if (!(nud_state & NUD_VALID)) {
 		neigh_event_send(attr.n, NULL);
@@ -418,8 +420,8 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv,
 
 	memset(&reformat_params, 0, sizeof(reformat_params));
 	reformat_params.type = e->reformat_type;
-	reformat_params.size = ipv4_encap_size;
-	reformat_params.data = encap_header;
+	reformat_params.size = e->encap_size;
+	reformat_params.data = e->encap_header;
 	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params,
 						     MLX5_FLOW_NAMESPACE_FDB);
 	if (IS_ERR(e->pkt_reformat)) {
@@ -570,6 +572,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 
 	e->encap_size = ipv6_encap_size;
 	e->encap_header = encap_header;
+	encap_header = NULL;
 
 	if (!(nud_state & NUD_VALID)) {
 		neigh_event_send(attr.n, NULL);
@@ -581,8 +584,8 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 
 	memset(&reformat_params, 0, sizeof(reformat_params));
 	reformat_params.type = e->reformat_type;
-	reformat_params.size = ipv6_encap_size;
-	reformat_params.data = encap_header;
+	reformat_params.size = e->encap_size;
+	reformat_params.data = e->encap_header;
 	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params,
 						     MLX5_FLOW_NAMESPACE_FDB);
 	if (IS_ERR(e->pkt_reformat)) {
@@ -674,6 +677,7 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv,
 	e->encap_size = ipv6_encap_size;
 	kfree(e->encap_header);
 	e->encap_header = encap_header;
+	encap_header = NULL;
 
 	if (!(nud_state & NUD_VALID)) {
 		neigh_event_send(attr.n, NULL);
@@ -685,8 +689,8 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv,
 
 	memset(&reformat_params, 0, sizeof(reformat_params));
 	reformat_params.type = e->reformat_type;
-	reformat_params.size = ipv6_encap_size;
-	reformat_params.data = encap_header;
+	reformat_params.size = e->encap_size;
+	reformat_params.data = e->encap_header;
 	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params,
 						     MLX5_FLOW_NAMESPACE_FDB);
 	if (IS_ERR(e->pkt_reformat)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
index b10e40e1a9c1..f1d1e1542e81 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
@@ -1064,7 +1064,8 @@ int mlx5e_tc_tun_encap_dests_set(struct mlx5e_priv *priv,
 
 		out_priv = netdev_priv(encap_dev);
 		rpriv = out_priv->ppriv;
-		esw_attr->dests[out_index].rep = rpriv->rep;
+		esw_attr->dests[out_index].vport_valid = true;
+		esw_attr->dests[out_index].vport = rpriv->rep->vport;
 		esw_attr->dests[out_index].mdev = out_priv->mdev;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
index 5620d9f97518..ac458a8d10e0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
@@ -68,11 +68,13 @@ static int mlx5e_open_trap_rq(struct mlx5e_priv *priv, struct mlx5e_trap *t)
 
 	node = dev_to_node(mdev->device);
 
+	ccp.netdev   = priv->netdev;
+	ccp.wq       = priv->wq;
 	ccp.node     = node;
 	ccp.ch_stats = t->stats;
 	ccp.napi     = &t->napi;
 	ccp.ix       = 0;
-	err = mlx5e_open_cq(priv, trap_moder, &rq_param->cqp, &ccp, &rq->cq);
+	err = mlx5e_open_cq(priv->mdev, trap_moder, &rq_param->cqp, &ccp, &rq->cq);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 7decc81ed33a..82b5ca1be4f3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -103,7 +103,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq,
 		xdptxd->dma_addr = dma_addr;
 
 		if (unlikely(!INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe,
-					      mlx5e_xmit_xdp_frame, sq, xdptxd, 0)))
+					      mlx5e_xmit_xdp_frame, sq, xdptxd, 0, NULL)))
 			return false;
 
 		/* xmit_mode == MLX5E_XDP_XMIT_MODE_FRAME */
@@ -145,7 +145,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq,
 	xdptxd->dma_addr = dma_addr;
 
 	if (unlikely(!INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe,
-				      mlx5e_xmit_xdp_frame, sq, xdptxd, 0)))
+				      mlx5e_xmit_xdp_frame, sq, xdptxd, 0, NULL)))
 		return false;
 
 	/* xmit_mode == MLX5E_XDP_XMIT_MODE_PAGE */
@@ -256,9 +256,55 @@ static int mlx5e_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
 	return 0;
 }
 
+static int mlx5e_xdp_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto,
+				 u16 *vlan_tci)
+{
+	const struct mlx5e_xdp_buff *_ctx = (void *)ctx;
+	const struct mlx5_cqe64 *cqe = _ctx->cqe;
+
+	if (!cqe_has_vlan(cqe))
+		return -ENODATA;
+
+	*vlan_proto = htons(ETH_P_8021Q);
+	*vlan_tci = be16_to_cpu(cqe->vlan_info);
+	return 0;
+}
+
 const struct xdp_metadata_ops mlx5e_xdp_metadata_ops = {
 	.xmo_rx_timestamp		= mlx5e_xdp_rx_timestamp,
 	.xmo_rx_hash			= mlx5e_xdp_rx_hash,
+	.xmo_rx_vlan_tag		= mlx5e_xdp_rx_vlan_tag,
+};
+
+struct mlx5e_xsk_tx_complete {
+	struct mlx5_cqe64 *cqe;
+	struct mlx5e_cq *cq;
+};
+
+static u64 mlx5e_xsk_fill_timestamp(void *_priv)
+{
+	struct mlx5e_xsk_tx_complete *priv = _priv;
+	u64 ts;
+
+	ts = get_cqe_ts(priv->cqe);
+
+	if (mlx5_is_real_time_rq(priv->cq->mdev) || mlx5_is_real_time_sq(priv->cq->mdev))
+		return mlx5_real_time_cyc2time(&priv->cq->mdev->clock, ts);
+
+	return  mlx5_timecounter_cyc2time(&priv->cq->mdev->clock, ts);
+}
+
+static void mlx5e_xsk_request_checksum(u16 csum_start, u16 csum_offset, void *priv)
+{
+	struct mlx5_wqe_eth_seg *eseg = priv;
+
+	/* HW/FW is doing parsing, so offsets are largely ignored. */
+	eseg->cs_flags |= MLX5_ETH_WQE_L3_CSUM | MLX5_ETH_WQE_L4_CSUM;
+}
+
+const struct xsk_tx_metadata_ops mlx5e_xsk_tx_metadata_ops = {
+	.tmo_fill_timestamp		= mlx5e_xsk_fill_timestamp,
+	.tmo_request_checksum		= mlx5e_xsk_request_checksum,
 };
 
 /* returns true if packet was consumed by xdp */
@@ -398,11 +444,11 @@ INDIRECT_CALLABLE_SCOPE int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq
 
 INDIRECT_CALLABLE_SCOPE bool
 mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
-		     int check_result);
+		     int check_result, struct xsk_tx_metadata *meta);
 
 INDIRECT_CALLABLE_SCOPE bool
 mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
-			   int check_result)
+			   int check_result, struct xsk_tx_metadata *meta)
 {
 	struct mlx5e_tx_mpwqe *session = &sq->mpwqe;
 	struct mlx5e_xdpsq_stats *stats = sq->stats;
@@ -420,7 +466,7 @@ mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptx
 			 */
 			if (unlikely(sq->mpwqe.wqe))
 				mlx5e_xdp_mpwqe_complete(sq);
-			return mlx5e_xmit_xdp_frame(sq, xdptxd, 0);
+			return mlx5e_xmit_xdp_frame(sq, xdptxd, 0, meta);
 		}
 		if (!xdptxd->len) {
 			skb_frag_t *frag = &xdptxdf->sinfo->frags[0];
@@ -450,6 +496,7 @@ mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptx
 		 * and it's safe to complete it at any time.
 		 */
 		mlx5e_xdp_mpwqe_session_start(sq);
+		xsk_tx_metadata_request(meta, &mlx5e_xsk_tx_metadata_ops, &session->wqe->eth);
 	}
 
 	mlx5e_xdp_mpwqe_add_dseg(sq, p, stats);
@@ -480,7 +527,7 @@ INDIRECT_CALLABLE_SCOPE int mlx5e_xmit_xdp_frame_check(struct mlx5e_xdpsq *sq)
 
 INDIRECT_CALLABLE_SCOPE bool
 mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
-		     int check_result)
+		     int check_result, struct xsk_tx_metadata *meta)
 {
 	struct mlx5e_xmit_data_frags *xdptxdf =
 		container_of(xdptxd, struct mlx5e_xmit_data_frags, xd);
@@ -493,6 +540,7 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 	dma_addr_t dma_addr = xdptxd->dma_addr;
 	u32 dma_len = xdptxd->len;
 	u16 ds_cnt, inline_hdr_sz;
+	unsigned int frags_size;
 	u8 num_wqebbs = 1;
 	int num_frags = 0;
 	bool inline_ok;
@@ -503,8 +551,9 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 
 	inline_ok = sq->min_inline_mode == MLX5_INLINE_MODE_NONE ||
 		dma_len >= MLX5E_XDP_MIN_INLINE;
+	frags_size = xdptxd->has_frags ? xdptxdf->sinfo->xdp_frags_size : 0;
 
-	if (unlikely(!inline_ok || sq->hw_mtu < dma_len)) {
+	if (unlikely(!inline_ok || sq->hw_mtu < dma_len + frags_size)) {
 		stats->err++;
 		return false;
 	}
@@ -599,6 +648,8 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 		sq->pc++;
 	}
 
+	xsk_tx_metadata_request(meta, &mlx5e_xsk_tx_metadata_ops, eseg);
+
 	sq->doorbell_cseg = cseg;
 
 	stats->xmit++;
@@ -608,7 +659,9 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
 				  struct mlx5e_xdp_wqe_info *wi,
 				  u32 *xsk_frames,
-				  struct xdp_frame_bulk *bq)
+				  struct xdp_frame_bulk *bq,
+				  struct mlx5e_cq *cq,
+				  struct mlx5_cqe64 *cqe)
 {
 	struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo;
 	u16 i;
@@ -668,10 +721,24 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
 
 			break;
 		}
-		case MLX5E_XDP_XMIT_MODE_XSK:
+		case MLX5E_XDP_XMIT_MODE_XSK: {
 			/* AF_XDP send */
+			struct xsk_tx_metadata_compl *compl = NULL;
+			struct mlx5e_xsk_tx_complete priv = {
+				.cqe = cqe,
+				.cq = cq,
+			};
+
+			if (xp_tx_metadata_enabled(sq->xsk_pool)) {
+				xdpi = mlx5e_xdpi_fifo_pop(xdpi_fifo);
+				compl = &xdpi.xsk_meta;
+
+				xsk_tx_metadata_complete(compl, &mlx5e_xsk_tx_metadata_ops, &priv);
+			}
+
 			(*xsk_frames)++;
 			break;
+		}
 		default:
 			WARN_ON_ONCE(true);
 		}
@@ -720,7 +787,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 
 			sqcc += wi->num_wqebbs;
 
-			mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, &bq);
+			mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, &bq, cq, cqe);
 		} while (!last_wqe);
 
 		if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) {
@@ -767,7 +834,7 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
 
 		sq->cc += wi->num_wqebbs;
 
-		mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, &bq);
+		mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, &bq, NULL, NULL);
 	}
 
 	xdp_flush_frame_bulk(&bq);
@@ -840,7 +907,7 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		}
 
 		ret = INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe,
-				      mlx5e_xmit_xdp_frame, sq, xdptxd, 0);
+				      mlx5e_xmit_xdp_frame, sq, xdptxd, 0, NULL);
 		if (unlikely(!ret)) {
 			int j;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index ecfe93a479da..e054db1e10f8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -33,6 +33,7 @@
 #define __MLX5_EN_XDP_H__
 
 #include <linux/indirect_call_wrapper.h>
+#include <net/xdp_sock.h>
 
 #include "en.h"
 #include "en/txrx.h"
@@ -82,7 +83,7 @@ enum mlx5e_xdp_xmit_mode {
  *    num, page_1, page_2, ... , page_num.
  *
  * MLX5E_XDP_XMIT_MODE_XSK:
- *    none.
+ *    frame.xsk_meta.
  */
 #define MLX5E_XDP_FIFO_ENTRIES2DS_MAX_RATIO 4
 
@@ -97,6 +98,7 @@ union mlx5e_xdp_info {
 		u8 num;
 		struct page *page;
 	} page;
+	struct xsk_tx_metadata_compl xsk_meta;
 };
 
 struct mlx5e_xsk_param;
@@ -112,13 +114,16 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		   u32 flags);
 
 extern const struct xdp_metadata_ops mlx5e_xdp_metadata_ops;
+extern const struct xsk_tx_metadata_ops mlx5e_xsk_tx_metadata_ops;
 
 INDIRECT_CALLABLE_DECLARE(bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
 							  struct mlx5e_xmit_data *xdptxd,
-							  int check_result));
+							  int check_result,
+							  struct xsk_tx_metadata *meta));
 INDIRECT_CALLABLE_DECLARE(bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq,
 						    struct mlx5e_xmit_data *xdptxd,
-						    int check_result));
+						    int check_result,
+						    struct xsk_tx_metadata *meta));
 INDIRECT_CALLABLE_DECLARE(int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq));
 INDIRECT_CALLABLE_DECLARE(int mlx5e_xmit_xdp_frame_check(struct mlx5e_xdpsq *sq));
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index 36826b582484..82e6abbc1734 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -127,7 +127,7 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params,
 
 	mlx5e_build_xsk_cparam(priv->mdev, params, xsk, priv->q_counter, cparam);
 
-	err = mlx5e_open_cq(c->priv, params->rx_cq_moderation, &cparam->rq.cqp, &ccp,
+	err = mlx5e_open_cq(c->mdev, params->rx_cq_moderation, &cparam->rq.cqp, &ccp,
 			    &c->xskrq.cq);
 	if (unlikely(err))
 		goto err_free_cparam;
@@ -136,7 +136,7 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params,
 	if (unlikely(err))
 		goto err_close_rx_cq;
 
-	err = mlx5e_open_cq(c->priv, params->tx_cq_moderation, &cparam->xdp_sq.cqp, &ccp,
+	err = mlx5e_open_cq(c->mdev, params->tx_cq_moderation, &cparam->xdp_sq.cqp, &ccp,
 			    &c->xsksq.cq);
 	if (unlikely(err))
 		goto err_close_rq;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
index 597f319d4770..a59199ed590d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
@@ -55,12 +55,16 @@ static void mlx5e_xsk_tx_post_err(struct mlx5e_xdpsq *sq,
 
 	nopwqe = mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc);
 	mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, *xdpi);
+	if (xp_tx_metadata_enabled(sq->xsk_pool))
+		mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo,
+				     (union mlx5e_xdp_info) { .xsk_meta = {} });
 	sq->doorbell_cseg = &nopwqe->ctrl;
 }
 
 bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget)
 {
 	struct xsk_buff_pool *pool = sq->xsk_pool;
+	struct xsk_tx_metadata *meta = NULL;
 	union mlx5e_xdp_info xdpi;
 	bool work_done = true;
 	bool flush = false;
@@ -93,12 +97,13 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget)
 		xdptxd.dma_addr = xsk_buff_raw_get_dma(pool, desc.addr);
 		xdptxd.data = xsk_buff_raw_get_data(pool, desc.addr);
 		xdptxd.len = desc.len;
+		meta = xsk_buff_get_metadata(pool, desc.addr);
 
 		xsk_buff_raw_dma_sync_for_device(pool, xdptxd.dma_addr, xdptxd.len);
 
 		ret = INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe,
 				      mlx5e_xmit_xdp_frame, sq, &xdptxd,
-				      check_result);
+				      check_result, meta);
 		if (unlikely(!ret)) {
 			if (sq->mpwqe.wqe)
 				mlx5e_xdp_mpwqe_complete(sq);
@@ -106,6 +111,16 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget)
 			mlx5e_xsk_tx_post_err(sq, &xdpi);
 		} else {
 			mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi);
+			if (xp_tx_metadata_enabled(sq->xsk_pool)) {
+				struct xsk_tx_metadata_compl compl;
+
+				xsk_tx_metadata_to_compl(meta, &compl);
+				XSK_TX_COMPL_FITS(void *);
+
+				mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo,
+						     (union mlx5e_xdp_info)
+						     { .xsk_meta = compl });
+			}
 		}
 
 		flush = true;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 655496598c68..161c5190c236 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -121,7 +121,14 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry)
 	if (x->xso.type == XFRM_DEV_OFFLOAD_CRYPTO)
 		esn_msb = xfrm_replay_seqhi(x, htonl(seq_bottom));
 
-	sa_entry->esn_state.esn = esn;
+	if (sa_entry->esn_state.esn_msb)
+		sa_entry->esn_state.esn = esn;
+	else
+		/* According to RFC4303, section "3.3.3. Sequence Number Generation",
+		 * the first packet sent using a given SA will contain a sequence
+		 * number of 1.
+		 */
+		sa_entry->esn_state.esn = max_t(u32, esn, 1);
 	sa_entry->esn_state.esn_msb = esn_msb;
 
 	if (unlikely(overlap && seq_bottom < MLX5E_IPSEC_ESN_SCOPE_MID)) {
@@ -335,6 +342,27 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry,
 		attrs->replay_esn.esn = sa_entry->esn_state.esn;
 		attrs->replay_esn.esn_msb = sa_entry->esn_state.esn_msb;
 		attrs->replay_esn.overlap = sa_entry->esn_state.overlap;
+		switch (x->replay_esn->replay_window) {
+		case 32:
+			attrs->replay_esn.replay_window =
+				MLX5_IPSEC_ASO_REPLAY_WIN_32BIT;
+			break;
+		case 64:
+			attrs->replay_esn.replay_window =
+				MLX5_IPSEC_ASO_REPLAY_WIN_64BIT;
+			break;
+		case 128:
+			attrs->replay_esn.replay_window =
+				MLX5_IPSEC_ASO_REPLAY_WIN_128BIT;
+			break;
+		case 256:
+			attrs->replay_esn.replay_window =
+				MLX5_IPSEC_ASO_REPLAY_WIN_256BIT;
+			break;
+		default:
+			WARN_ON(true);
+			return;
+		}
 	}
 
 	attrs->dir = x->xso.dir;
@@ -907,9 +935,11 @@ void mlx5e_ipsec_cleanup(struct mlx5e_priv *priv)
 		return;
 
 	mlx5e_accel_ipsec_fs_cleanup(ipsec);
-	if (mlx5_ipsec_device_caps(priv->mdev) & MLX5_IPSEC_CAP_TUNNEL)
+	if (ipsec->netevent_nb.notifier_call) {
 		unregister_netevent_notifier(&ipsec->netevent_nb);
-	if (mlx5_ipsec_device_caps(priv->mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD)
+		ipsec->netevent_nb.notifier_call = NULL;
+	}
+	if (ipsec->aso)
 		mlx5e_ipsec_aso_cleanup(ipsec);
 	destroy_workqueue(ipsec->wq);
 	kfree(ipsec);
@@ -1018,6 +1048,12 @@ static int mlx5e_xfrm_validate_policy(struct mlx5_core_dev *mdev,
 		}
 	}
 
+	if (x->xdo.type == XFRM_DEV_OFFLOAD_PACKET &&
+	    !(mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD)) {
+		NL_SET_ERR_MSG_MOD(extack, "Packet offload is not supported");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -1113,14 +1149,6 @@ static const struct xfrmdev_ops mlx5e_ipsec_xfrmdev_ops = {
 	.xdo_dev_state_free	= mlx5e_xfrm_free_state,
 	.xdo_dev_offload_ok	= mlx5e_ipsec_offload_ok,
 	.xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state,
-};
-
-static const struct xfrmdev_ops mlx5e_ipsec_packet_xfrmdev_ops = {
-	.xdo_dev_state_add	= mlx5e_xfrm_add_state,
-	.xdo_dev_state_delete	= mlx5e_xfrm_del_state,
-	.xdo_dev_state_free	= mlx5e_xfrm_free_state,
-	.xdo_dev_offload_ok	= mlx5e_ipsec_offload_ok,
-	.xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state,
 
 	.xdo_dev_state_update_curlft = mlx5e_xfrm_update_curlft,
 	.xdo_dev_policy_add = mlx5e_xfrm_add_policy,
@@ -1138,11 +1166,7 @@ void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv)
 
 	mlx5_core_info(mdev, "mlx5e: IPSec ESP acceleration enabled\n");
 
-	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD)
-		netdev->xfrmdev_ops = &mlx5e_ipsec_packet_xfrmdev_ops;
-	else
-		netdev->xfrmdev_ops = &mlx5e_ipsec_xfrmdev_ops;
-
+	netdev->xfrmdev_ops = &mlx5e_ipsec_xfrmdev_ops;
 	netdev->features |= NETIF_F_HW_ESP;
 	netdev->hw_enc_features |= NETIF_F_HW_ESP;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index 8f4a37bceaf4..adaea3493193 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -189,11 +189,19 @@ struct mlx5e_ipsec_ft {
 	u32 refcnt;
 };
 
+struct mlx5e_ipsec_drop {
+	struct mlx5_flow_handle *rule;
+	struct mlx5_fc *fc;
+};
+
 struct mlx5e_ipsec_rule {
 	struct mlx5_flow_handle *rule;
 	struct mlx5_modify_hdr *modify_hdr;
 	struct mlx5_pkt_reformat *pkt_reformat;
 	struct mlx5_fc *fc;
+	struct mlx5e_ipsec_drop replay;
+	struct mlx5e_ipsec_drop auth;
+	struct mlx5e_ipsec_drop trailer;
 };
 
 struct mlx5e_ipsec_miss {
@@ -201,19 +209,6 @@ struct mlx5e_ipsec_miss {
 	struct mlx5_flow_handle *rule;
 };
 
-struct mlx5e_ipsec_rx {
-	struct mlx5e_ipsec_ft ft;
-	struct mlx5e_ipsec_miss pol;
-	struct mlx5e_ipsec_miss sa;
-	struct mlx5e_ipsec_rule status;
-	struct mlx5e_ipsec_miss status_drop;
-	struct mlx5_fc *status_drop_cnt;
-	struct mlx5e_ipsec_fc *fc;
-	struct mlx5_fs_chains *chains;
-	u8 allow_tunnel_mode : 1;
-	struct xarray ipsec_obj_id_map;
-};
-
 struct mlx5e_ipsec_tx_create_attr {
 	int prio;
 	int pol_level;
@@ -248,6 +243,7 @@ struct mlx5e_ipsec {
 	struct mlx5_ipsec_fs *roce;
 	u8 is_uplink_rep: 1;
 	struct mlx5e_ipsec_mpv_work mpv_work;
+	struct xarray ipsec_obj_id_map;
 };
 
 struct mlx5e_ipsec_esn_state {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index f41c976dc33f..41a2543a52cd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -32,6 +32,22 @@ struct mlx5e_ipsec_tx {
 	u8 allow_tunnel_mode : 1;
 };
 
+struct mlx5e_ipsec_status_checks {
+	struct mlx5_flow_group *drop_all_group;
+	struct mlx5e_ipsec_drop all;
+};
+
+struct mlx5e_ipsec_rx {
+	struct mlx5e_ipsec_ft ft;
+	struct mlx5e_ipsec_miss pol;
+	struct mlx5e_ipsec_miss sa;
+	struct mlx5e_ipsec_rule status;
+	struct mlx5e_ipsec_status_checks status_drops;
+	struct mlx5e_ipsec_fc *fc;
+	struct mlx5_fs_chains *chains;
+	u8 allow_tunnel_mode : 1;
+};
+
 /* IPsec RX flow steering */
 static enum mlx5_traffic_types family2tt(u32 family)
 {
@@ -128,14 +144,37 @@ static struct mlx5_flow_table *ipsec_ft_create(struct mlx5_flow_namespace *ns,
 	return mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
 }
 
-static int ipsec_status_rule(struct mlx5_core_dev *mdev,
-			     struct mlx5e_ipsec_rx *rx,
-			     struct mlx5_flow_destination *dest)
+static void ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec,
+					 struct mlx5e_ipsec_rx *rx)
+{
+	mlx5_del_flow_rules(rx->status_drops.all.rule);
+	mlx5_fc_destroy(ipsec->mdev, rx->status_drops.all.fc);
+	mlx5_destroy_flow_group(rx->status_drops.drop_all_group);
+}
+
+static void ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec,
+					 struct mlx5e_ipsec_rx *rx)
 {
-	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
+	mlx5_del_flow_rules(rx->status.rule);
+
+	if (rx != ipsec->rx_esw)
+		return;
+
+#ifdef CONFIG_MLX5_ESWITCH
+	mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0);
+#endif
+}
+
+static int rx_add_rule_drop_auth_trailer(struct mlx5e_ipsec_sa_entry *sa_entry,
+					 struct mlx5e_ipsec_rx *rx)
+{
+	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
+	struct mlx5_flow_table *ft = rx->ft.status;
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_flow_destination dest = {};
 	struct mlx5_flow_act flow_act = {};
-	struct mlx5_modify_hdr *modify_hdr;
-	struct mlx5_flow_handle *fte;
+	struct mlx5_flow_handle *rule;
+	struct mlx5_fc *flow_counter;
 	struct mlx5_flow_spec *spec;
 	int err;
 
@@ -143,48 +182,273 @@ static int ipsec_status_rule(struct mlx5_core_dev *mdev,
 	if (!spec)
 		return -ENOMEM;
 
-	/* Action to copy 7 bit ipsec_syndrome to regB[24:30] */
-	MLX5_SET(copy_action_in, action, action_type, MLX5_ACTION_TYPE_COPY);
-	MLX5_SET(copy_action_in, action, src_field, MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME);
-	MLX5_SET(copy_action_in, action, src_offset, 0);
-	MLX5_SET(copy_action_in, action, length, 7);
-	MLX5_SET(copy_action_in, action, dst_field, MLX5_ACTION_IN_FIELD_METADATA_REG_B);
-	MLX5_SET(copy_action_in, action, dst_offset, 24);
+	flow_counter = mlx5_fc_create(mdev, true);
+	if (IS_ERR(flow_counter)) {
+		err = PTR_ERR(flow_counter);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule counter, err=%d\n", err);
+		goto err_cnt;
+	}
+	sa_entry->ipsec_rule.auth.fc = flow_counter;
 
-	modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_KERNEL,
-					      1, action);
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	flow_act.flags = FLOW_ACT_NO_APPEND;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest.counter_id = mlx5_fc_id(flow_counter);
+	if (rx == ipsec->rx_esw)
+		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
 
-	if (IS_ERR(modify_hdr)) {
-		err = PTR_ERR(modify_hdr);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.ipsec_syndrome);
+	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.ipsec_syndrome, 1);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 misc_parameters_2.metadata_reg_c_2,
+		 sa_entry->ipsec_obj_id | BIT(31));
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
 		mlx5_core_err(mdev,
-			      "fail to alloc ipsec copy modify_header_id err=%d\n", err);
-		goto out_spec;
+			      "Failed to add ipsec rx status drop rule, err=%d\n", err);
+		goto err_rule;
 	}
+	sa_entry->ipsec_rule.auth.rule = rule;
 
-	/* create fte */
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR |
-			  MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+	flow_counter = mlx5_fc_create(mdev, true);
+	if (IS_ERR(flow_counter)) {
+		err = PTR_ERR(flow_counter);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule counter, err=%d\n", err);
+		goto err_cnt_2;
+	}
+	sa_entry->ipsec_rule.trailer.fc = flow_counter;
+
+	dest.counter_id = mlx5_fc_id(flow_counter);
+	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.ipsec_syndrome, 2);
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule, err=%d\n", err);
+		goto err_rule_2;
+	}
+	sa_entry->ipsec_rule.trailer.rule = rule;
+
+	kvfree(spec);
+	return 0;
+
+err_rule_2:
+	mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.trailer.fc);
+err_cnt_2:
+	mlx5_del_flow_rules(sa_entry->ipsec_rule.auth.rule);
+err_rule:
+	mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.auth.fc);
+err_cnt:
+	kvfree(spec);
+	return err;
+}
+
+static int rx_add_rule_drop_replay(struct mlx5e_ipsec_sa_entry *sa_entry, struct mlx5e_ipsec_rx *rx)
+{
+	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
+	struct mlx5_flow_table *ft = rx->ft.status;
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_flow_destination dest = {};
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *rule;
+	struct mlx5_fc *flow_counter;
+	struct mlx5_flow_spec *spec;
+	int err;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	flow_counter = mlx5_fc_create(mdev, true);
+	if (IS_ERR(flow_counter)) {
+		err = PTR_ERR(flow_counter);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule counter, err=%d\n", err);
+		goto err_cnt;
+	}
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	flow_act.flags = FLOW_ACT_NO_APPEND;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest.counter_id = mlx5_fc_id(flow_counter);
+	if (rx == ipsec->rx_esw)
+		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_4);
+	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_c_4, 1);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2);
+	MLX5_SET(fte_match_param, spec->match_value,  misc_parameters_2.metadata_reg_c_2,
+		 sa_entry->ipsec_obj_id | BIT(31));
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule, err=%d\n", err);
+		goto err_rule;
+	}
+
+	sa_entry->ipsec_rule.replay.rule = rule;
+	sa_entry->ipsec_rule.replay.fc = flow_counter;
+
+	kvfree(spec);
+	return 0;
+
+err_rule:
+	mlx5_fc_destroy(mdev, flow_counter);
+err_cnt:
+	kvfree(spec);
+	return err;
+}
+
+static int ipsec_rx_status_drop_all_create(struct mlx5e_ipsec *ipsec,
+					   struct mlx5e_ipsec_rx *rx)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_table *ft = rx->ft.status;
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_flow_destination dest = {};
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *rule;
+	struct mlx5_fc *flow_counter;
+	struct mlx5_flow_spec *spec;
+	struct mlx5_flow_group *g;
+	u32 *flow_group_in;
+	int err = 0;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!flow_group_in || !spec) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ft->max_fte - 1);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ft->max_fte - 1);
+	g = mlx5_create_flow_group(ft, flow_group_in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop flow group, err=%d\n", err);
+		goto err_out;
+	}
+
+	flow_counter = mlx5_fc_create(mdev, false);
+	if (IS_ERR(flow_counter)) {
+		err = PTR_ERR(flow_counter);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule counter, err=%d\n", err);
+		goto err_cnt;
+	}
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest.counter_id = mlx5_fc_id(flow_counter);
+	if (rx == ipsec->rx_esw)
+		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule, err=%d\n", err);
+		goto err_rule;
+	}
+
+	rx->status_drops.drop_all_group = g;
+	rx->status_drops.all.rule = rule;
+	rx->status_drops.all.fc = flow_counter;
+
+	kvfree(flow_group_in);
+	kvfree(spec);
+	return 0;
+
+err_rule:
+	mlx5_fc_destroy(mdev, flow_counter);
+err_cnt:
+	mlx5_destroy_flow_group(g);
+err_out:
+	kvfree(flow_group_in);
+	kvfree(spec);
+	return err;
+}
+
+static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_rx *rx,
+				       struct mlx5_flow_destination *dest)
+{
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
+	int err;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+			 misc_parameters_2.ipsec_syndrome);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+			 misc_parameters_2.metadata_reg_c_4);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 misc_parameters_2.ipsec_syndrome, 0);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 misc_parameters_2.metadata_reg_c_4, 0);
+	if (rx == ipsec->rx_esw)
+		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	flow_act.flags = FLOW_ACT_NO_APPEND;
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
 			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
-	flow_act.modify_hdr = modify_hdr;
-	fte = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2);
-	if (IS_ERR(fte)) {
-		err = PTR_ERR(fte);
-		mlx5_core_err(mdev, "fail to add ipsec rx err copy rule err=%d\n", err);
-		goto out;
+	rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_warn(ipsec->mdev,
+			       "Failed to add ipsec rx status pass rule, err=%d\n", err);
+		goto err_rule;
 	}
 
+	rx->status.rule = rule;
 	kvfree(spec);
-	rx->status.rule = fte;
-	rx->status.modify_hdr = modify_hdr;
 	return 0;
 
-out:
-	mlx5_modify_header_dealloc(mdev, modify_hdr);
-out_spec:
+err_rule:
 	kvfree(spec);
 	return err;
 }
 
+static void mlx5_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
+					 struct mlx5e_ipsec_rx *rx)
+{
+	ipsec_rx_status_pass_destroy(ipsec, rx);
+	ipsec_rx_status_drop_destroy(ipsec, rx);
+}
+
+static int mlx5_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_rx *rx,
+				       struct mlx5_flow_destination *dest)
+{
+	int err;
+
+	err = ipsec_rx_status_drop_all_create(ipsec, rx);
+	if (err)
+		return err;
+
+	err = ipsec_rx_status_pass_create(ipsec, rx, dest);
+	if (err)
+		goto err_pass_create;
+
+	return 0;
+
+err_pass_create:
+	ipsec_rx_status_drop_destroy(ipsec, rx);
+	return err;
+}
+
 static int ipsec_miss_create(struct mlx5_core_dev *mdev,
 			     struct mlx5_flow_table *ft,
 			     struct mlx5e_ipsec_miss *miss,
@@ -333,12 +597,7 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	mlx5_destroy_flow_table(rx->ft.sa);
 	if (rx->allow_tunnel_mode)
 		mlx5_eswitch_unblock_encap(mdev);
-	if (rx == ipsec->rx_esw) {
-		mlx5_esw_ipsec_rx_status_destroy(ipsec, rx);
-	} else {
-		mlx5_del_flow_rules(rx->status.rule);
-		mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr);
-	}
+	mlx5_ipsec_rx_status_destroy(ipsec, rx);
 	mlx5_destroy_flow_table(rx->ft.status);
 
 	mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family, mdev);
@@ -419,7 +678,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (err)
 		return err;
 
-	ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 1, 0);
+	ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 3, 0);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_fs_ft_status;
@@ -428,10 +687,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 
 	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
 	dest[1].counter_id = mlx5_fc_id(rx->fc->cnt);
-	if (rx == ipsec->rx_esw)
-		err = mlx5_esw_ipsec_rx_status_create(ipsec, rx, dest);
-	else
-		err = ipsec_status_rule(mdev, rx, dest);
+	err = mlx5_ipsec_rx_status_create(ipsec, rx, dest);
 	if (err)
 		goto err_add;
 
@@ -956,13 +1212,22 @@ static void setup_fte_esp(struct mlx5_flow_spec *spec)
 	MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_protocol, IPPROTO_ESP);
 }
 
-static void setup_fte_spi(struct mlx5_flow_spec *spec, u32 spi)
+static void setup_fte_spi(struct mlx5_flow_spec *spec, u32 spi, bool encap)
 {
 	/* SPI number */
 	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS;
 
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters.outer_esp_spi);
-	MLX5_SET(fte_match_param, spec->match_value, misc_parameters.outer_esp_spi, spi);
+	if (encap) {
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+				 misc_parameters.inner_esp_spi);
+		MLX5_SET(fte_match_param, spec->match_value,
+			 misc_parameters.inner_esp_spi, spi);
+	} else {
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+				 misc_parameters.outer_esp_spi);
+		MLX5_SET(fte_match_param, spec->match_value,
+			 misc_parameters.outer_esp_spi, spi);
+	}
 }
 
 static void setup_fte_no_frags(struct mlx5_flow_spec *spec)
@@ -1052,29 +1317,48 @@ static int setup_modify_header(struct mlx5e_ipsec *ipsec, int type, u32 val, u8
 			       struct mlx5_flow_act *flow_act)
 {
 	enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, type, dir);
-	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
+	u8 action[3][MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
 	struct mlx5_core_dev *mdev = ipsec->mdev;
 	struct mlx5_modify_hdr *modify_hdr;
+	u8 num_of_actions = 1;
 
-	MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
+	MLX5_SET(set_action_in, action[0], action_type, MLX5_ACTION_TYPE_SET);
 	switch (dir) {
 	case XFRM_DEV_OFFLOAD_IN:
-		MLX5_SET(set_action_in, action, field,
+		MLX5_SET(set_action_in, action[0], field,
 			 MLX5_ACTION_IN_FIELD_METADATA_REG_B);
+
+		num_of_actions++;
+		MLX5_SET(set_action_in, action[1], action_type, MLX5_ACTION_TYPE_SET);
+		MLX5_SET(set_action_in, action[1], field, MLX5_ACTION_IN_FIELD_METADATA_REG_C_2);
+		MLX5_SET(set_action_in, action[1], data, val);
+		MLX5_SET(set_action_in, action[1], offset, 0);
+		MLX5_SET(set_action_in, action[1], length, 32);
+
+		if (type == XFRM_DEV_OFFLOAD_CRYPTO) {
+			num_of_actions++;
+			MLX5_SET(set_action_in, action[2], action_type,
+				 MLX5_ACTION_TYPE_SET);
+			MLX5_SET(set_action_in, action[2], field,
+				 MLX5_ACTION_IN_FIELD_METADATA_REG_C_4);
+			MLX5_SET(set_action_in, action[2], data, 0);
+			MLX5_SET(set_action_in, action[2], offset, 0);
+			MLX5_SET(set_action_in, action[2], length, 32);
+		}
 		break;
 	case XFRM_DEV_OFFLOAD_OUT:
-		MLX5_SET(set_action_in, action, field,
+		MLX5_SET(set_action_in, action[0], field,
 			 MLX5_ACTION_IN_FIELD_METADATA_REG_C_4);
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	MLX5_SET(set_action_in, action, data, val);
-	MLX5_SET(set_action_in, action, offset, 0);
-	MLX5_SET(set_action_in, action, length, 32);
+	MLX5_SET(set_action_in, action[0], data, val);
+	MLX5_SET(set_action_in, action[0], offset, 0);
+	MLX5_SET(set_action_in, action[0], length, 32);
 
-	modify_hdr = mlx5_modify_header_alloc(mdev, ns_type, 1, action);
+	modify_hdr = mlx5_modify_header_alloc(mdev, ns_type, num_of_actions, action);
 	if (IS_ERR(modify_hdr)) {
 		mlx5_core_err(mdev, "Failed to allocate modify_header %ld\n",
 			      PTR_ERR(modify_hdr));
@@ -1321,8 +1605,9 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	else
 		setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6);
 
-	setup_fte_spi(spec, attrs->spi);
-	setup_fte_esp(spec);
+	setup_fte_spi(spec, attrs->spi, attrs->encap);
+	if (!attrs->encap)
+		setup_fte_esp(spec);
 	setup_fte_no_frags(spec);
 	setup_fte_upper_proto_match(spec, &attrs->upspec);
 
@@ -1372,6 +1657,15 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 		mlx5_core_err(mdev, "fail to add RX ipsec rule err=%d\n", err);
 		goto err_add_flow;
 	}
+	if (attrs->type == XFRM_DEV_OFFLOAD_PACKET)
+		err = rx_add_rule_drop_replay(sa_entry, rx);
+	if (err)
+		goto err_add_replay;
+
+	err = rx_add_rule_drop_auth_trailer(sa_entry, rx);
+	if (err)
+		goto err_drop_reason;
+
 	kvfree(spec);
 
 	sa_entry->ipsec_rule.rule = rule;
@@ -1380,6 +1674,13 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	sa_entry->ipsec_rule.pkt_reformat = flow_act.pkt_reformat;
 	return 0;
 
+err_drop_reason:
+	if (sa_entry->ipsec_rule.replay.rule) {
+		mlx5_del_flow_rules(sa_entry->ipsec_rule.replay.rule);
+		mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.replay.fc);
+	}
+err_add_replay:
+	mlx5_del_flow_rules(rule);
 err_add_flow:
 	mlx5_fc_destroy(mdev, counter);
 err_add_cnt:
@@ -1428,7 +1729,7 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 
 	switch (attrs->type) {
 	case XFRM_DEV_OFFLOAD_CRYPTO:
-		setup_fte_spi(spec, attrs->spi);
+		setup_fte_spi(spec, attrs->spi, false);
 		setup_fte_esp(spec);
 		setup_fte_reg_a(spec);
 		break;
@@ -1809,8 +2110,11 @@ static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev)
 	struct mlx5_eswitch *esw = mdev->priv.eswitch;
 	int err = 0;
 
-	if (esw)
-		down_write(&esw->mode_lock);
+	if (esw) {
+		err = mlx5_esw_lock(esw);
+		if (err)
+			return err;
+	}
 
 	if (mdev->num_block_ipsec) {
 		err = -EBUSY;
@@ -1821,7 +2125,7 @@ static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev)
 
 unlock:
 	if (esw)
-		up_write(&esw->mode_lock);
+		mlx5_esw_unlock(esw);
 
 	return err;
 }
@@ -1838,7 +2142,7 @@ static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev)
 
 static void mlx5e_ipsec_unblock_tc_offload(struct mlx5_core_dev *mdev)
 {
-	mdev->num_block_tc++;
+	mdev->num_block_tc--;
 }
 
 int mlx5e_accel_ipsec_fs_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
@@ -1887,6 +2191,17 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 
 	if (ipsec_rule->modify_hdr)
 		mlx5_modify_header_dealloc(mdev, ipsec_rule->modify_hdr);
+
+	mlx5_del_flow_rules(ipsec_rule->trailer.rule);
+	mlx5_fc_destroy(mdev, ipsec_rule->trailer.fc);
+
+	mlx5_del_flow_rules(ipsec_rule->auth.rule);
+	mlx5_fc_destroy(mdev, ipsec_rule->auth.fc);
+
+	if (ipsec_rule->replay.rule) {
+		mlx5_del_flow_rules(ipsec_rule->replay.rule);
+		mlx5_fc_destroy(mdev, ipsec_rule->replay.fc);
+	}
 	mlx5_esw_ipsec_rx_id_mapping_remove(sa_entry);
 	rx_ft_put(sa_entry->ipsec, sa_entry->attrs.family, sa_entry->attrs.type);
 }
@@ -1957,7 +2272,7 @@ void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_ipsec *ipsec)
 	kfree(ipsec->rx_ipv6);
 
 	if (ipsec->is_uplink_rep) {
-		xa_destroy(&ipsec->rx_esw->ipsec_obj_id_map);
+		xa_destroy(&ipsec->ipsec_obj_id_map);
 
 		mutex_destroy(&ipsec->tx_esw->ft.mutex);
 		WARN_ON(ipsec->tx_esw->ft.refcnt);
@@ -2020,7 +2335,7 @@ int mlx5e_accel_ipsec_fs_init(struct mlx5e_ipsec *ipsec,
 		mutex_init(&ipsec->tx_esw->ft.mutex);
 		mutex_init(&ipsec->rx_esw->ft.mutex);
 		ipsec->tx_esw->ns = ns_esw;
-		xa_init_flags(&ipsec->rx_esw->ipsec_obj_id_map, XA_FLAGS_ALLOC1);
+		xa_init_flags(&ipsec->ipsec_obj_id_map, XA_FLAGS_ALLOC1);
 	} else if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_ROCE) {
 		ipsec->roce = mlx5_ipsec_fs_roce_init(mdev, devcom);
 	} else {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index a91f772dc981..6e00afe4671b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -6,6 +6,8 @@
 #include "ipsec.h"
 #include "lib/crypto.h"
 #include "lib/ipsec_fs_roce.h"
+#include "fs_core.h"
+#include "eswitch.h"
 
 enum {
 	MLX5_IPSEC_ASO_REMOVE_FLOW_PKT_CNT_OFFSET,
@@ -38,7 +40,10 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
 	    MLX5_CAP_ETH(mdev, insert_trailer) && MLX5_CAP_ETH(mdev, swp))
 		caps |= MLX5_IPSEC_CAP_CRYPTO;
 
-	if (MLX5_CAP_IPSEC(mdev, ipsec_full_offload)) {
+	if (MLX5_CAP_IPSEC(mdev, ipsec_full_offload) &&
+	    (mdev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_DMFS ||
+	     (mdev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS &&
+	     is_mdev_legacy_mode(mdev)))) {
 		if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev,
 					      reformat_add_esp_trasport) &&
 		    MLX5_CAP_FLOWTABLE_NIC_RX(mdev,
@@ -95,7 +100,7 @@ static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn,
 
 		if (attrs->dir == XFRM_DEV_OFFLOAD_IN) {
 			MLX5_SET(ipsec_aso, aso_ctx, window_sz,
-				 attrs->replay_esn.replay_window / 64);
+				 attrs->replay_esn.replay_window);
 			MLX5_SET(ipsec_aso, aso_ctx, mode,
 				 MLX5_IPSEC_ASO_REPLAY_PROTECTION);
 		}
@@ -559,6 +564,7 @@ void mlx5e_ipsec_aso_cleanup(struct mlx5e_ipsec *ipsec)
 	dma_unmap_single(pdev, aso->dma_addr, sizeof(aso->ctx),
 			 DMA_BIDIRECTIONAL);
 	kfree(aso);
+	ipsec->aso = NULL;
 }
 
 static void mlx5e_ipsec_aso_copy(struct mlx5_wqe_aso_ctrl_seg *ctrl,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 41c396e76457..67f546683e85 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -74,6 +74,72 @@ int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey)
 	return err;
 }
 
+int mlx5e_create_tis(struct mlx5_core_dev *mdev, void *in, u32 *tisn)
+{
+	void *tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
+
+	MLX5_SET(tisc, tisc, transport_domain, mdev->mlx5e_res.hw_objs.td.tdn);
+
+	if (mlx5_lag_is_lacp_owner(mdev))
+		MLX5_SET(tisc, tisc, strict_lag_tx_port_affinity, 1);
+
+	return mlx5_core_create_tis(mdev, in, tisn);
+}
+
+void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn)
+{
+	mlx5_core_destroy_tis(mdev, tisn);
+}
+
+static void mlx5e_destroy_tises(struct mlx5_core_dev *mdev, u32 tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC])
+{
+	int tc, i;
+
+	for (i = 0; i < MLX5_MAX_PORTS; i++)
+		for (tc = 0; tc < MLX5_MAX_NUM_TC; tc++)
+			mlx5e_destroy_tis(mdev, tisn[i][tc]);
+}
+
+static bool mlx5_lag_should_assign_affinity(struct mlx5_core_dev *mdev)
+{
+	return MLX5_CAP_GEN(mdev, lag_tx_port_affinity) && mlx5e_get_num_lag_ports(mdev) > 1;
+}
+
+static int mlx5e_create_tises(struct mlx5_core_dev *mdev, u32 tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC])
+{
+	int tc, i;
+	int err;
+
+	for (i = 0; i < MLX5_MAX_PORTS; i++) {
+		for (tc = 0; tc < MLX5_MAX_NUM_TC; tc++) {
+			u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {};
+			void *tisc;
+
+			tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
+
+			MLX5_SET(tisc, tisc, prio, tc << 1);
+
+			if (mlx5_lag_should_assign_affinity(mdev))
+				MLX5_SET(tisc, tisc, lag_tx_port_affinity, i + 1);
+
+			err = mlx5e_create_tis(mdev, in, &tisn[i][tc]);
+			if (err)
+				goto err_close_tises;
+		}
+	}
+
+	return 0;
+
+err_close_tises:
+	for (; i >= 0; i--) {
+		for (tc--; tc >= 0; tc--)
+			mlx5e_destroy_tis(mdev, tisn[i][tc]);
+		tc = MLX5_MAX_NUM_TC;
+	}
+
+	return err;
+}
+
 int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
 {
 	struct mlx5e_hw_objs *res = &mdev->mlx5e_res.hw_objs;
@@ -103,6 +169,11 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
 		goto err_destroy_mkey;
 	}
 
+	err = mlx5e_create_tises(mdev, res->tisn);
+	if (err) {
+		mlx5_core_err(mdev, "alloc tises failed, %d\n", err);
+		goto err_destroy_bfreg;
+	}
 	INIT_LIST_HEAD(&res->td.tirs_list);
 	mutex_init(&res->td.list_lock);
 
@@ -115,6 +186,8 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
 
 	return 0;
 
+err_destroy_bfreg:
+	mlx5_free_bfreg(mdev, &res->bfreg);
 err_destroy_mkey:
 	mlx5_core_destroy_mkey(mdev, res->mkey);
 err_dealloc_transport_domain:
@@ -130,6 +203,7 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev)
 
 	mlx5_crypto_dek_cleanup(mdev->mlx5e_res.dek_priv);
 	mdev->mlx5e_res.dek_priv = NULL;
+	mlx5e_destroy_tises(mdev, res->tisn);
 	mlx5_free_bfreg(mdev, &res->bfreg);
 	mlx5_core_destroy_mkey(mdev, res->mkey);
 	mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 215261a69255..cc51ce16df14 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -43,12 +43,17 @@ void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
 			       struct ethtool_drvinfo *drvinfo)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
+	int count;
 
 	strscpy(drvinfo->driver, KBUILD_MODNAME, sizeof(drvinfo->driver));
-	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
-		 "%d.%d.%04d (%.16s)",
-		 fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev),
-		 mdev->board_id);
+	count = snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+			 "%d.%d.%04d (%.16s)", fw_rev_maj(mdev),
+			 fw_rev_min(mdev), fw_rev_sub(mdev), mdev->board_id);
+	if (count >= sizeof(drvinfo->fw_version))
+		snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+			 "%d.%d.%04d", fw_rev_maj(mdev),
+			 fw_rev_min(mdev), fw_rev_sub(mdev));
+
 	strscpy(drvinfo->bus_info, dev_name(mdev->device),
 		sizeof(drvinfo->bus_info));
 }
@@ -1257,27 +1262,29 @@ static u32 mlx5e_get_rxfh_indir_size(struct net_device *netdev)
 	return mlx5e_ethtool_get_rxfh_indir_size(priv);
 }
 
-static int mlx5e_get_rxfh_context(struct net_device *dev, u32 *indir,
-				  u8 *key, u8 *hfunc, u32 rss_context)
+int mlx5e_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
 {
-	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	u32 rss_context = rxfh->rss_context;
 	int err;
 
 	mutex_lock(&priv->state_lock);
-	err = mlx5e_rx_res_rss_get_rxfh(priv->rx_res, rss_context, indir, key, hfunc);
+	err = mlx5e_rx_res_rss_get_rxfh(priv->rx_res, rss_context,
+					rxfh->indir, rxfh->key, &rxfh->hfunc);
 	mutex_unlock(&priv->state_lock);
 	return err;
 }
 
-static int mlx5e_set_rxfh_context(struct net_device *dev, const u32 *indir,
-				  const u8 *key, const u8 hfunc,
-				  u32 *rss_context, bool delete)
+int mlx5e_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh,
+		   struct netlink_ext_ack *extack)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
+	u32 *rss_context = &rxfh->rss_context;
+	u8 hfunc = rxfh->hfunc;
 	int err;
 
 	mutex_lock(&priv->state_lock);
-	if (delete) {
+	if (*rss_context && rxfh->rss_delete) {
 		err = mlx5e_rx_res_rss_destroy(priv->rx_res, *rss_context);
 		goto unlock;
 	}
@@ -1290,7 +1297,8 @@ static int mlx5e_set_rxfh_context(struct net_device *dev, const u32 *indir,
 			goto unlock;
 	}
 
-	err = mlx5e_rx_res_rss_set_rxfh(priv->rx_res, *rss_context, indir, key,
+	err = mlx5e_rx_res_rss_set_rxfh(priv->rx_res, *rss_context,
+					rxfh->indir, rxfh->key,
 					hfunc == ETH_RSS_HASH_NO_CHANGE ? NULL : &hfunc);
 
 unlock:
@@ -1298,25 +1306,6 @@ unlock:
 	return err;
 }
 
-int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-		   u8 *hfunc)
-{
-	return mlx5e_get_rxfh_context(netdev, indir, key, hfunc, 0);
-}
-
-int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
-		   const u8 *key, const u8 hfunc)
-{
-	struct mlx5e_priv *priv = netdev_priv(dev);
-	int err;
-
-	mutex_lock(&priv->state_lock);
-	err = mlx5e_rx_res_rss_set_rxfh(priv->rx_res, 0, indir, key,
-					hfunc == ETH_RSS_HASH_NO_CHANGE ? NULL : &hfunc);
-	mutex_unlock(&priv->state_lock);
-	return err;
-}
-
 #define MLX5E_PFC_PREVEN_AUTO_TOUT_MSEC		100
 #define MLX5E_PFC_PREVEN_TOUT_MAX_MSEC		8000
 #define MLX5E_PFC_PREVEN_MINOR_PRECENT		85
@@ -2393,6 +2382,7 @@ static void mlx5e_get_rmon_stats(struct net_device *netdev,
 }
 
 const struct ethtool_ops mlx5e_ethtool_ops = {
+	.cap_rss_ctx_supported	= true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE |
@@ -2415,8 +2405,6 @@ const struct ethtool_ops mlx5e_ethtool_ops = {
 	.get_rxfh_indir_size = mlx5e_get_rxfh_indir_size,
 	.get_rxfh          = mlx5e_get_rxfh,
 	.set_rxfh          = mlx5e_set_rxfh,
-	.get_rxfh_context  = mlx5e_get_rxfh_context,
-	.set_rxfh_context  = mlx5e_set_rxfh_context,
 	.get_rxnfc         = mlx5e_get_rxnfc,
 	.set_rxnfc         = mlx5e_set_rxnfc,
 	.get_tunable       = mlx5e_get_tunable,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index ea58c6917433..b5f1c4ca38ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -902,6 +902,7 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params,
 		pp_params.nid       = node;
 		pp_params.dev       = rq->pdev;
 		pp_params.napi      = rq->cq.napi;
+		pp_params.netdev    = rq->netdev;
 		pp_params.dma_dir   = rq->buff.map_dir;
 		pp_params.max_len   = PAGE_SIZE;
 
@@ -1351,6 +1352,17 @@ void mlx5e_close_rq(struct mlx5e_rq *rq)
 	mlx5e_free_rq(rq);
 }
 
+u32 mlx5e_profile_get_tisn(struct mlx5_core_dev *mdev,
+			   struct mlx5e_priv *priv,
+			   const struct mlx5e_profile *profile,
+			   u8 lag_port, u8 tc)
+{
+	if (profile->get_tisn)
+		return profile->get_tisn(mdev, priv, lag_port, tc);
+
+	return mdev->mlx5e_res.hw_objs.tisn[lag_port][tc];
+}
+
 static void mlx5e_free_xdpsq_db(struct mlx5e_xdpsq *sq)
 {
 	kvfree(sq->db.xdpi_fifo.xi);
@@ -1919,7 +1931,8 @@ int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
 		return err;
 
 	csp.tis_lst_sz      = 1;
-	csp.tisn            = c->priv->tisn[c->lag_port][0]; /* tc = 0 */
+	csp.tisn            = mlx5e_profile_get_tisn(c->mdev, c->priv, c->priv->profile,
+						     c->lag_port, 0); /* tc = 0 */
 	csp.cqn             = sq->cq.mcq.cqn;
 	csp.wq_ctrl         = &sq->wq_ctrl;
 	csp.min_inline_mode = sq->min_inline_mode;
@@ -1981,11 +1994,12 @@ void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq)
 	mlx5e_free_xdpsq(sq);
 }
 
-static int mlx5e_alloc_cq_common(struct mlx5e_priv *priv,
+static int mlx5e_alloc_cq_common(struct mlx5_core_dev *mdev,
+				 struct net_device *netdev,
+				 struct workqueue_struct *workqueue,
 				 struct mlx5e_cq_param *param,
 				 struct mlx5e_cq *cq)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5_core_cq *mcq = &cq->mcq;
 	int err;
 	u32 i;
@@ -2012,13 +2026,13 @@ static int mlx5e_alloc_cq_common(struct mlx5e_priv *priv,
 	}
 
 	cq->mdev = mdev;
-	cq->netdev = priv->netdev;
-	cq->priv = priv;
+	cq->netdev = netdev;
+	cq->workqueue = workqueue;
 
 	return 0;
 }
 
-static int mlx5e_alloc_cq(struct mlx5e_priv *priv,
+static int mlx5e_alloc_cq(struct mlx5_core_dev *mdev,
 			  struct mlx5e_cq_param *param,
 			  struct mlx5e_create_cq_param *ccp,
 			  struct mlx5e_cq *cq)
@@ -2029,7 +2043,7 @@ static int mlx5e_alloc_cq(struct mlx5e_priv *priv,
 	param->wq.db_numa_node  = ccp->node;
 	param->eq_ix            = ccp->ix;
 
-	err = mlx5e_alloc_cq_common(priv, param, cq);
+	err = mlx5e_alloc_cq_common(mdev, ccp->netdev, ccp->wq, param, cq);
 
 	cq->napi     = ccp->napi;
 	cq->ch_stats = ccp->ch_stats;
@@ -2095,14 +2109,13 @@ static void mlx5e_destroy_cq(struct mlx5e_cq *cq)
 	mlx5_core_destroy_cq(cq->mdev, &cq->mcq);
 }
 
-int mlx5e_open_cq(struct mlx5e_priv *priv, struct dim_cq_moder moder,
+int mlx5e_open_cq(struct mlx5_core_dev *mdev, struct dim_cq_moder moder,
 		  struct mlx5e_cq_param *param, struct mlx5e_create_cq_param *ccp,
 		  struct mlx5e_cq *cq)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
 	int err;
 
-	err = mlx5e_alloc_cq(priv, param, ccp, cq);
+	err = mlx5e_alloc_cq(mdev, param, ccp, cq);
 	if (err)
 		return err;
 
@@ -2135,7 +2148,7 @@ static int mlx5e_open_tx_cqs(struct mlx5e_channel *c,
 	int tc;
 
 	for (tc = 0; tc < c->num_tc; tc++) {
-		err = mlx5e_open_cq(c->priv, params->tx_cq_moderation, &cparam->txq_sq.cqp,
+		err = mlx5e_open_cq(c->mdev, params->tx_cq_moderation, &cparam->txq_sq.cqp,
 				    ccp, &c->sq[tc].cq);
 		if (err)
 			goto err_close_tx_cqs;
@@ -2203,12 +2216,15 @@ static int mlx5e_open_sqs(struct mlx5e_channel *c,
 	for (tc = 0; tc < mlx5e_get_dcb_num_tc(params); tc++) {
 		int txq_ix = c->ix + tc * params->num_channels;
 		u32 qos_queue_group_id;
+		u32 tisn;
 
+		tisn = mlx5e_profile_get_tisn(c->mdev, c->priv, c->priv->profile,
+					      c->lag_port, tc);
 		err = mlx5e_txq_get_qos_node_hw_id(params, txq_ix, &qos_queue_group_id);
 		if (err)
 			goto err_close_sqs;
 
-		err = mlx5e_open_txqsq(c, c->priv->tisn[c->lag_port][tc], txq_ix,
+		err = mlx5e_open_txqsq(c, tisn, txq_ix,
 				       params, &cparam->txq_sq, &c->sq[tc], tc,
 				       qos_queue_group_id,
 				       &c->priv->channel_stats[c->ix]->sq[tc]);
@@ -2336,12 +2352,12 @@ static int mlx5e_open_queues(struct mlx5e_channel *c,
 
 	mlx5e_build_create_cq_param(&ccp, c);
 
-	err = mlx5e_open_cq(c->priv, icocq_moder, &cparam->async_icosq.cqp, &ccp,
+	err = mlx5e_open_cq(c->mdev, icocq_moder, &cparam->async_icosq.cqp, &ccp,
 			    &c->async_icosq.cq);
 	if (err)
 		return err;
 
-	err = mlx5e_open_cq(c->priv, icocq_moder, &cparam->icosq.cqp, &ccp,
+	err = mlx5e_open_cq(c->mdev, icocq_moder, &cparam->icosq.cqp, &ccp,
 			    &c->icosq.cq);
 	if (err)
 		goto err_close_async_icosq_cq;
@@ -2350,17 +2366,17 @@ static int mlx5e_open_queues(struct mlx5e_channel *c,
 	if (err)
 		goto err_close_icosq_cq;
 
-	err = mlx5e_open_cq(c->priv, params->tx_cq_moderation, &cparam->xdp_sq.cqp, &ccp,
+	err = mlx5e_open_cq(c->mdev, params->tx_cq_moderation, &cparam->xdp_sq.cqp, &ccp,
 			    &c->xdpsq.cq);
 	if (err)
 		goto err_close_tx_cqs;
 
-	err = mlx5e_open_cq(c->priv, params->rx_cq_moderation, &cparam->rq.cqp, &ccp,
+	err = mlx5e_open_cq(c->mdev, params->rx_cq_moderation, &cparam->rq.cqp, &ccp,
 			    &c->rq.cq);
 	if (err)
 		goto err_close_xdp_tx_cqs;
 
-	err = c->xdp ? mlx5e_open_cq(c->priv, params->tx_cq_moderation, &cparam->xdp_sq.cqp,
+	err = c->xdp ? mlx5e_open_cq(c->mdev, params->tx_cq_moderation, &cparam->xdp_sq.cqp,
 				     &ccp, &c->rq_xdpsq.cq) : 0;
 	if (err)
 		goto err_close_rx_cq;
@@ -2731,6 +2747,7 @@ void mlx5e_close_channels(struct mlx5e_channels *chs)
 {
 	int i;
 
+	ASSERT_RTNL();
 	if (chs->ptp) {
 		mlx5e_ptp_close(chs->ptp);
 		chs->ptp = NULL;
@@ -3012,17 +3029,29 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 	if (mlx5e_is_vport_rep(priv))
 		mlx5e_rep_activate_channels(priv);
 
+	set_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state);
+
 	mlx5e_wait_channels_min_rx_wqes(&priv->channels);
 
 	if (priv->rx_res)
 		mlx5e_rx_res_channels_activate(priv->rx_res, &priv->channels);
 }
 
+static void mlx5e_cancel_tx_timeout_work(struct mlx5e_priv *priv)
+{
+	WARN_ON_ONCE(test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state));
+	if (current_work() != &priv->tx_timeout_work)
+		cancel_work_sync(&priv->tx_timeout_work);
+}
+
 void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
 {
 	if (priv->rx_res)
 		mlx5e_rx_res_channels_deactivate(priv->rx_res);
 
+	clear_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state);
+	mlx5e_cancel_tx_timeout_work(priv);
+
 	if (mlx5e_is_vport_rep(priv))
 		mlx5e_rep_deactivate_channels(priv);
 
@@ -3294,7 +3323,7 @@ static int mlx5e_alloc_drop_cq(struct mlx5e_priv *priv,
 	param->wq.buf_numa_node = dev_to_node(mlx5_core_dma_dev(mdev));
 	param->wq.db_numa_node  = dev_to_node(mlx5_core_dma_dev(mdev));
 
-	return mlx5e_alloc_cq_common(priv, param, cq);
+	return mlx5e_alloc_cq_common(priv->mdev, priv->netdev, priv->wq, param, cq);
 }
 
 int mlx5e_open_drop_rq(struct mlx5e_priv *priv,
@@ -3350,75 +3379,6 @@ void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq)
 	mlx5e_free_cq(&drop_rq->cq);
 }
 
-int mlx5e_create_tis(struct mlx5_core_dev *mdev, void *in, u32 *tisn)
-{
-	void *tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
-
-	MLX5_SET(tisc, tisc, transport_domain, mdev->mlx5e_res.hw_objs.td.tdn);
-
-	if (MLX5_GET(tisc, tisc, tls_en))
-		MLX5_SET(tisc, tisc, pd, mdev->mlx5e_res.hw_objs.pdn);
-
-	if (mlx5_lag_is_lacp_owner(mdev))
-		MLX5_SET(tisc, tisc, strict_lag_tx_port_affinity, 1);
-
-	return mlx5_core_create_tis(mdev, in, tisn);
-}
-
-void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn)
-{
-	mlx5_core_destroy_tis(mdev, tisn);
-}
-
-void mlx5e_destroy_tises(struct mlx5e_priv *priv)
-{
-	int tc, i;
-
-	for (i = 0; i < mlx5e_get_num_lag_ports(priv->mdev); i++)
-		for (tc = 0; tc < priv->profile->max_tc; tc++)
-			mlx5e_destroy_tis(priv->mdev, priv->tisn[i][tc]);
-}
-
-static bool mlx5e_lag_should_assign_affinity(struct mlx5_core_dev *mdev)
-{
-	return MLX5_CAP_GEN(mdev, lag_tx_port_affinity) && mlx5e_get_num_lag_ports(mdev) > 1;
-}
-
-int mlx5e_create_tises(struct mlx5e_priv *priv)
-{
-	int tc, i;
-	int err;
-
-	for (i = 0; i < mlx5e_get_num_lag_ports(priv->mdev); i++) {
-		for (tc = 0; tc < priv->profile->max_tc; tc++) {
-			u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {};
-			void *tisc;
-
-			tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
-
-			MLX5_SET(tisc, tisc, prio, tc << 1);
-
-			if (mlx5e_lag_should_assign_affinity(priv->mdev))
-				MLX5_SET(tisc, tisc, lag_tx_port_affinity, i + 1);
-
-			err = mlx5e_create_tis(priv->mdev, in, &priv->tisn[i][tc]);
-			if (err)
-				goto err_close_tises;
-		}
-	}
-
-	return 0;
-
-err_close_tises:
-	for (; i >= 0; i--) {
-		for (tc--; tc >= 0; tc--)
-			mlx5e_destroy_tis(priv->mdev, priv->tisn[i][tc]);
-		tc = priv->profile->max_tc;
-	}
-
-	return err;
-}
-
 static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv)
 {
 	if (priv->mqprio_rl) {
@@ -3427,7 +3387,6 @@ static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv)
 		priv->mqprio_rl = NULL;
 	}
 	mlx5e_accel_cleanup_tx(priv);
-	mlx5e_destroy_tises(priv);
 }
 
 static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd)
@@ -3529,7 +3488,7 @@ static int mlx5e_setup_tc_mqprio_dcb(struct mlx5e_priv *priv,
 
 	mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
 
-	if (tc && tc != MLX5E_MAX_NUM_TC)
+	if (tc && tc != MLX5_MAX_NUM_TC)
 		return -EINVAL;
 
 	new_params = priv->channels.params;
@@ -4801,8 +4760,17 @@ static void mlx5e_tx_timeout_work(struct work_struct *work)
 	struct net_device *netdev = priv->netdev;
 	int i;
 
-	rtnl_lock();
-	mutex_lock(&priv->state_lock);
+	/* Take rtnl_lock to ensure no change in netdev->real_num_tx_queues
+	 * through this flow. However, channel closing flows have to wait for
+	 * this work to finish while holding rtnl lock too. So either get the
+	 * lock or find that channels are being closed for other reason and
+	 * this work is not relevant anymore.
+	 */
+	while (!rtnl_trylock()) {
+		if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state))
+			return;
+		msleep(20);
+	}
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
 		goto unlock;
@@ -4821,7 +4789,6 @@ static void mlx5e_tx_timeout_work(struct work_struct *work)
 	}
 
 unlock:
-	mutex_unlock(&priv->state_lock);
 	rtnl_unlock();
 }
 
@@ -5164,6 +5131,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 
 	netdev->netdev_ops = &mlx5e_netdev_ops;
 	netdev->xdp_metadata_ops = &mlx5e_xdp_metadata_ops;
+	netdev->xsk_tx_metadata_ops = &mlx5e_xsk_tx_metadata_ops;
 
 	mlx5e_dcbnl_build_netdev(netdev);
 
@@ -5244,7 +5212,6 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 
 	netdev->gso_partial_features             |= NETIF_F_GSO_UDP_L4;
 	netdev->hw_features                      |= NETIF_F_GSO_UDP_L4;
-	netdev->features                         |= NETIF_F_GSO_UDP_L4;
 
 	mlx5_query_port_fcs(mdev, &fcs_supported, &fcs_enabled);
 
@@ -5484,23 +5451,13 @@ static int mlx5e_init_nic_tx(struct mlx5e_priv *priv)
 {
 	int err;
 
-	err = mlx5e_create_tises(priv);
-	if (err) {
-		mlx5_core_warn(priv->mdev, "create tises failed, %d\n", err);
-		return err;
-	}
-
 	err = mlx5e_accel_init_tx(priv);
 	if (err)
-		goto err_destroy_tises;
+		return err;
 
 	mlx5e_set_mqprio_rl(priv);
 	mlx5e_dcbnl_initialize(priv);
 	return 0;
-
-err_destroy_tises:
-	mlx5e_destroy_tises(priv);
-	return err;
 }
 
 static void mlx5e_nic_enable(struct mlx5e_priv *priv)
@@ -5595,7 +5552,7 @@ static const struct mlx5e_profile mlx5e_nic_profile = {
 	.update_stats	   = mlx5e_stats_update_ndo_stats,
 	.update_carrier	   = mlx5e_update_carrier,
 	.rx_handlers       = &mlx5e_rx_handlers_nic,
-	.max_tc		   = MLX5E_MAX_NUM_TC,
+	.max_tc		   = MLX5_MAX_NUM_TC,
 	.stats_grps	   = mlx5e_nic_stats_grps,
 	.stats_grps_num	   = mlx5e_nic_stats_grps_num,
 	.features          = BIT(MLX5E_PROFILE_FEATURE_PTP_RX) |
@@ -6048,7 +6005,7 @@ static int mlx5e_resume(struct auxiliary_device *adev)
 	return 0;
 }
 
-static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state)
+static int _mlx5e_suspend(struct auxiliary_device *adev)
 {
 	struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev);
 	struct mlx5e_priv *priv = mlx5e_dev->priv;
@@ -6066,15 +6023,18 @@ static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state)
 	return 0;
 }
 
-static int mlx5e_probe(struct auxiliary_device *adev,
-		       const struct auxiliary_device_id *id)
+static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state)
+{
+	return _mlx5e_suspend(adev);
+}
+
+static int _mlx5e_probe(struct auxiliary_device *adev)
 {
 	struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev);
 	const struct mlx5e_profile *profile = &mlx5e_nic_profile;
 	struct mlx5_core_dev *mdev = edev->mdev;
 	struct mlx5e_dev *mlx5e_dev;
 	struct net_device *netdev;
-	pm_message_t state = {};
 	struct mlx5e_priv *priv;
 	int err;
 
@@ -6129,7 +6089,7 @@ static int mlx5e_probe(struct auxiliary_device *adev,
 	return 0;
 
 err_resume:
-	mlx5e_suspend(adev, state);
+	_mlx5e_suspend(adev);
 err_profile_cleanup:
 	profile->cleanup(priv);
 err_destroy_netdev:
@@ -6141,16 +6101,21 @@ err_devlink_unregister:
 	return err;
 }
 
+static int mlx5e_probe(struct auxiliary_device *adev,
+		       const struct auxiliary_device_id *id)
+{
+	return _mlx5e_probe(adev);
+}
+
 static void mlx5e_remove(struct auxiliary_device *adev)
 {
 	struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev);
 	struct mlx5e_priv *priv = mlx5e_dev->priv;
-	pm_message_t state = {};
 
 	mlx5_core_uplink_netdev_set(priv->mdev, NULL);
 	mlx5e_dcbnl_delete_app(priv);
 	unregister_netdev(priv->netdev);
-	mlx5e_suspend(adev, state);
+	_mlx5e_suspend(adev);
 	priv->profile->cleanup(priv);
 	mlx5e_destroy_netdev(priv);
 	mlx5e_devlink_port_unregister(mlx5e_dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 693e55b010d9..05527418fa64 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -71,13 +71,17 @@ static void mlx5e_rep_get_drvinfo(struct net_device *dev,
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
+	int count;
 
 	strscpy(drvinfo->driver, mlx5e_rep_driver_name,
 		sizeof(drvinfo->driver));
-	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
-		 "%d.%d.%04d (%.16s)",
-		 fw_rev_maj(mdev), fw_rev_min(mdev),
-		 fw_rev_sub(mdev), mdev->board_id);
+	count = snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+			 "%d.%d.%04d (%.16s)", fw_rev_maj(mdev),
+			 fw_rev_min(mdev), fw_rev_sub(mdev), mdev->board_id);
+	if (count >= sizeof(drvinfo->fw_version))
+		snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+			 "%d.%d.%04d", fw_rev_maj(mdev),
+			 fw_rev_min(mdev), fw_rev_sub(mdev));
 }
 
 static const struct counter_desc sw_rep_stats_desc[] = {
@@ -108,8 +112,18 @@ static const struct counter_desc vport_rep_stats_desc[] = {
 			     tx_vport_rdma_multicast_bytes) },
 };
 
+static const struct counter_desc vport_rep_loopback_stats_desc[] = {
+	{ MLX5E_DECLARE_STAT(struct mlx5e_rep_stats,
+			     vport_loopback_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_rep_stats,
+			     vport_loopback_bytes) },
+};
+
 #define NUM_VPORT_REP_SW_COUNTERS ARRAY_SIZE(sw_rep_stats_desc)
 #define NUM_VPORT_REP_HW_COUNTERS ARRAY_SIZE(vport_rep_stats_desc)
+#define NUM_VPORT_REP_LOOPBACK_COUNTERS(dev) \
+	(MLX5_CAP_GEN(dev, vport_counter_local_loopback) ? \
+	 ARRAY_SIZE(vport_rep_loopback_stats_desc) : 0)
 
 static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(sw_rep)
 {
@@ -153,7 +167,8 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw_rep)
 
 static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(vport_rep)
 {
-	return NUM_VPORT_REP_HW_COUNTERS;
+	return NUM_VPORT_REP_HW_COUNTERS +
+	       NUM_VPORT_REP_LOOPBACK_COUNTERS(priv->mdev);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(vport_rep)
@@ -162,6 +177,9 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(vport_rep)
 
 	for (i = 0; i < NUM_VPORT_REP_HW_COUNTERS; i++)
 		strcpy(data + (idx++) * ETH_GSTRING_LEN, vport_rep_stats_desc[i].format);
+	for (i = 0; i < NUM_VPORT_REP_LOOPBACK_COUNTERS(priv->mdev); i++)
+		strcpy(data + (idx++) * ETH_GSTRING_LEN,
+		       vport_rep_loopback_stats_desc[i].format);
 	return idx;
 }
 
@@ -172,6 +190,9 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(vport_rep)
 	for (i = 0; i < NUM_VPORT_REP_HW_COUNTERS; i++)
 		data[idx++] = MLX5E_READ_CTR64_CPU(&priv->stats.rep_stats,
 						   vport_rep_stats_desc, i);
+	for (i = 0; i < NUM_VPORT_REP_LOOPBACK_COUNTERS(priv->mdev); i++)
+		data[idx++] = MLX5E_READ_CTR64_CPU(&priv->stats.rep_stats,
+						   vport_rep_loopback_stats_desc, i);
 	return idx;
 }
 
@@ -243,6 +264,13 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(vport_rep)
 	rep_stats->tx_vport_rdma_multicast_bytes =
 		MLX5_GET_CTR(out, received_ib_multicast.octets);
 
+	if (MLX5_CAP_GEN(priv->mdev, vport_counter_local_loopback)) {
+		rep_stats->vport_loopback_packets =
+			MLX5_GET_CTR(out, local_loopback.packets);
+		rep_stats->vport_loopback_bytes =
+			MLX5_GET_CTR(out, local_loopback.octets);
+	}
+
 out:
 	kvfree(out);
 }
@@ -1152,12 +1180,6 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv)
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	int err;
 
-	err = mlx5e_create_tises(priv);
-	if (err) {
-		mlx5_core_warn(priv->mdev, "create tises failed, %d\n", err);
-		return err;
-	}
-
 	err = mlx5e_rep_neigh_init(rpriv);
 	if (err)
 		goto err_neigh_init;
@@ -1180,7 +1202,6 @@ err_ht_init:
 err_init_tx:
 	mlx5e_rep_neigh_cleanup(rpriv);
 err_neigh_init:
-	mlx5e_destroy_tises(priv);
 	return err;
 }
 
@@ -1194,7 +1215,6 @@ static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv)
 		mlx5e_cleanup_uplink_rep_tx(rpriv);
 
 	mlx5e_rep_neigh_cleanup(rpriv);
-	mlx5e_destroy_tises(priv);
 }
 
 static void mlx5e_rep_enable(struct mlx5e_priv *priv)
@@ -1424,7 +1444,7 @@ static const struct mlx5e_profile mlx5e_uplink_rep_profile = {
 	.update_stats           = mlx5e_stats_update_ndo_stats,
 	.update_carrier	        = mlx5e_update_carrier,
 	.rx_handlers            = &mlx5e_rx_handlers_rep,
-	.max_tc			= MLX5E_MAX_NUM_TC,
+	.max_tc			= MLX5_MAX_NUM_TC,
 	.stats_grps		= mlx5e_ul_rep_stats_grps,
 	.stats_grps_num		= mlx5e_ul_rep_stats_grps_num,
 };
@@ -1493,7 +1513,7 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 
 	dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch,
 						 rpriv->rep->vport);
-	if (dl_port) {
+	if (!IS_ERR(dl_port)) {
 		SET_NETDEV_DEVLINK_PORT(netdev, dl_port);
 		mlx5e_rep_vnic_reporter_create(priv, dl_port);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 8d9743a5e42c..d601b5faaed5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -298,8 +298,8 @@ static void mlx5e_page_release_fragmented(struct mlx5e_rq *rq,
 	u16 drain_count = MLX5E_PAGECNT_BIAS_MAX - frag_page->frags;
 	struct page *page = frag_page->page;
 
-	if (page_pool_defrag_page(page, drain_count) == 0)
-		page_pool_put_defragged_page(rq->page_pool, page, -1, true);
+	if (page_pool_unref_page(page, drain_count) == 0)
+		page_pool_put_unrefed_page(rq->page_pool, page, -1, true);
 }
 
 static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq,
@@ -1039,7 +1039,7 @@ int mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 						     (struct mlx5_err_cqe *)cqe);
 				mlx5_wq_cyc_wqe_dump(&sq->wq, ci, wi->num_wqebbs);
 				if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
-					queue_work(cq->priv->wq, &sq->recover_work);
+					queue_work(cq->workqueue, &sq->recover_work);
 				break;
 			}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 477c547dcc04..12b3607afecd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -476,6 +476,8 @@ struct mlx5e_rep_stats {
 	u64 tx_vport_rdma_multicast_packets;
 	u64 rx_vport_rdma_multicast_bytes;
 	u64 tx_vport_rdma_multicast_bytes;
+	u64 vport_loopback_packets;
+	u64 vport_loopback_bytes;
 };
 
 struct mlx5e_stats {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 9a5a5c2c7da9..30932c9c9a8f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -444,6 +444,9 @@ mlx5e_tc_add_flow_meter(struct mlx5e_priv *priv,
 	struct mlx5e_flow_meter_handle *meter;
 	enum mlx5e_post_meter_type type;
 
+	if (IS_ERR(post_act))
+		return PTR_ERR(post_act);
+
 	meter = mlx5e_tc_meter_replace(priv->mdev, &attr->meter_attr.params);
 	if (IS_ERR(meter)) {
 		mlx5_core_err(priv->mdev, "Failed to get flow meter\n");
@@ -3147,7 +3150,7 @@ static struct mlx5_fields fields[] = {
 	OFFLOAD(DIPV6_31_0,   32, U32_MAX, ip6.daddr.s6_addr32[3], 0,
 		dst_ipv4_dst_ipv6.ipv6_layout.ipv6[12]),
 	OFFLOAD(IPV6_HOPLIMIT, 8,  U8_MAX, ip6.hop_limit, 0, ttl_hoplimit),
-	OFFLOAD(IP_DSCP, 16,  0xc00f, ip6, 0, ip_dscp),
+	OFFLOAD(IP_DSCP, 16,  0x0fc0, ip6, 0, ip_dscp),
 
 	OFFLOAD(TCP_SPORT, 16, U16_MAX, tcp.source,  0, tcp_sport),
 	OFFLOAD(TCP_DPORT, 16, U16_MAX, tcp.dest,    0, tcp_dport),
@@ -3158,21 +3161,31 @@ static struct mlx5_fields fields[] = {
 	OFFLOAD(UDP_DPORT, 16, U16_MAX, udp.dest,   0, udp_dport),
 };
 
-static unsigned long mask_to_le(unsigned long mask, int size)
+static u32 mask_field_get(void *mask, struct mlx5_fields *f)
 {
-	__be32 mask_be32;
-	__be16 mask_be16;
-
-	if (size == 32) {
-		mask_be32 = (__force __be32)(mask);
-		mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32));
-	} else if (size == 16) {
-		mask_be32 = (__force __be32)(mask);
-		mask_be16 = *(__be16 *)&mask_be32;
-		mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16));
+	switch (f->field_bsize) {
+	case 32:
+		return be32_to_cpu(*(__be32 *)mask) & f->field_mask;
+	case 16:
+		return be16_to_cpu(*(__be16 *)mask) & (u16)f->field_mask;
+	default:
+		return *(u8 *)mask & (u8)f->field_mask;
 	}
+}
 
-	return mask;
+static void mask_field_clear(void *mask, struct mlx5_fields *f)
+{
+	switch (f->field_bsize) {
+	case 32:
+		*(__be32 *)mask &= ~cpu_to_be32(f->field_mask);
+		break;
+	case 16:
+		*(__be16 *)mask &= ~cpu_to_be16((u16)f->field_mask);
+		break;
+	default:
+		*(u8 *)mask &= ~(u8)f->field_mask;
+		break;
+	}
 }
 
 static int offload_pedit_fields(struct mlx5e_priv *priv,
@@ -3184,35 +3197,32 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 	struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals;
 	struct pedit_headers_action *hdrs = parse_attr->hdrs;
 	void *headers_c, *headers_v, *action, *vals_p;
-	u32 *s_masks_p, *a_masks_p, s_mask, a_mask;
 	struct mlx5e_tc_mod_hdr_acts *mod_acts;
-	unsigned long mask, field_mask;
+	void *s_masks_p, *a_masks_p;
 	int i, first, last, next_z;
 	struct mlx5_fields *f;
+	unsigned long mask;
+	u32 s_mask, a_mask;
 	u8 cmd;
 
 	mod_acts = &parse_attr->mod_hdr_acts;
 	headers_c = mlx5e_get_match_headers_criteria(*action_flags, &parse_attr->spec);
 	headers_v = mlx5e_get_match_headers_value(*action_flags, &parse_attr->spec);
 
-	set_masks = &hdrs[0].masks;
-	add_masks = &hdrs[1].masks;
-	set_vals = &hdrs[0].vals;
-	add_vals = &hdrs[1].vals;
+	set_masks = &hdrs[TCA_PEDIT_KEY_EX_CMD_SET].masks;
+	add_masks = &hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].masks;
+	set_vals = &hdrs[TCA_PEDIT_KEY_EX_CMD_SET].vals;
+	add_vals = &hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].vals;
 
 	for (i = 0; i < ARRAY_SIZE(fields); i++) {
 		bool skip;
 
 		f = &fields[i];
-		/* avoid seeing bits set from previous iterations */
-		s_mask = 0;
-		a_mask = 0;
-
 		s_masks_p = (void *)set_masks + f->offset;
 		a_masks_p = (void *)add_masks + f->offset;
 
-		s_mask = *s_masks_p & f->field_mask;
-		a_mask = *a_masks_p & f->field_mask;
+		s_mask = mask_field_get(s_masks_p, f);
+		a_mask = mask_field_get(a_masks_p, f);
 
 		if (!s_mask && !a_mask) /* nothing to offload here */
 			continue;
@@ -3239,22 +3249,20 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 					 match_mask, f->field_bsize))
 				skip = true;
 			/* clear to denote we consumed this field */
-			*s_masks_p &= ~f->field_mask;
+			mask_field_clear(s_masks_p, f);
 		} else {
 			cmd  = MLX5_ACTION_TYPE_ADD;
 			mask = a_mask;
 			vals_p = (void *)add_vals + f->offset;
 			/* add 0 is no change */
-			if ((*(u32 *)vals_p & f->field_mask) == 0)
+			if (!mask_field_get(vals_p, f))
 				skip = true;
 			/* clear to denote we consumed this field */
-			*a_masks_p &= ~f->field_mask;
+			mask_field_clear(a_masks_p, f);
 		}
 		if (skip)
 			continue;
 
-		mask = mask_to_le(mask, f->field_bsize);
-
 		first = find_first_bit(&mask, f->field_bsize);
 		next_z = find_next_zero_bit(&mask, f->field_bsize, first);
 		last  = find_last_bit(&mask, f->field_bsize);
@@ -3281,10 +3289,9 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 		MLX5_SET(set_action_in, action, field, f->field);
 
 		if (cmd == MLX5_ACTION_TYPE_SET) {
+			unsigned long field_mask = f->field_mask;
 			int start;
 
-			field_mask = mask_to_le(f->field_mask, f->field_bsize);
-
 			/* if field is bit sized it can start not from first bit */
 			start = find_first_bit(&field_mask, f->field_bsize);
 
@@ -3735,6 +3742,20 @@ out_free:
 }
 
 static int
+set_branch_dest_ft(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr)
+{
+	struct mlx5e_post_act *post_act = get_post_action(priv);
+
+	if (IS_ERR(post_act))
+		return PTR_ERR(post_act);
+
+	attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	attr->dest_ft = mlx5e_tc_post_act_get_ft(post_act);
+
+	return 0;
+}
+
+static int
 alloc_branch_attr(struct mlx5e_tc_flow *flow,
 		  struct mlx5e_tc_act_branch_ctrl *cond,
 		  struct mlx5_flow_attr **cond_attr,
@@ -3757,8 +3778,9 @@ alloc_branch_attr(struct mlx5e_tc_flow *flow,
 		break;
 	case FLOW_ACTION_ACCEPT:
 	case FLOW_ACTION_PIPE:
-		attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-		attr->dest_ft = mlx5e_tc_post_act_get_ft(get_post_action(flow->priv));
+		err = set_branch_dest_ft(flow->priv, attr);
+		if (err)
+			goto out_err;
 		break;
 	case FLOW_ACTION_JUMP:
 		if (*jump_count) {
@@ -3767,8 +3789,9 @@ alloc_branch_attr(struct mlx5e_tc_flow *flow,
 			goto out_err;
 		}
 		*jump_count = cond->extval;
-		attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-		attr->dest_ft = mlx5e_tc_post_act_get_ft(get_post_action(flow->priv));
+		err = set_branch_dest_ft(flow->priv, attr);
+		if (err)
+			goto out_err;
 		break;
 	default:
 		err = -EOPNOTSUPP;
@@ -5007,22 +5030,6 @@ int mlx5e_tc_delete_matchall(struct mlx5e_priv *priv,
 	return apply_police_params(priv, 0, extack);
 }
 
-void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv,
-			     struct tc_cls_matchall_offload *ma)
-{
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-	struct rtnl_link_stats64 cur_stats;
-	u64 dbytes;
-	u64 dpkts;
-
-	mlx5e_stats_copy_rep_stats(&cur_stats, &priv->stats.rep_stats);
-	dpkts = cur_stats.rx_packets - rpriv->prev_vf_vport_stats.rx_packets;
-	dbytes = cur_stats.rx_bytes - rpriv->prev_vf_vport_stats.rx_bytes;
-	rpriv->prev_vf_vport_stats = cur_stats;
-	flow_stats_update(&ma->stats, dbytes, dpkts, 0, jiffies,
-			  FLOW_ACTION_HW_STATS_DELAYED);
-}
-
 static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv,
 					      struct mlx5e_priv *peer_priv)
 {
@@ -5715,8 +5722,10 @@ int mlx5e_tc_action_miss_mapping_get(struct mlx5e_priv *priv, struct mlx5_flow_a
 
 	esw = priv->mdev->priv.eswitch;
 	attr->act_id_restore_rule = esw_add_restore_rule(esw, *act_miss_mapping);
-	if (IS_ERR(attr->act_id_restore_rule))
+	if (IS_ERR(attr->act_id_restore_rule)) {
+		err = PTR_ERR(attr->act_id_restore_rule);
 		goto err_rule;
+	}
 
 	return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index adb39e30f90f..c24bda56b2b5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -203,8 +203,6 @@ int mlx5e_tc_configure_matchall(struct mlx5e_priv *priv,
 				struct tc_cls_matchall_offload *f);
 int mlx5e_tc_delete_matchall(struct mlx5e_priv *priv,
 			     struct tc_cls_matchall_offload *f);
-void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv,
-			     struct tc_cls_matchall_offload *ma);
 
 struct mlx5e_encap_entry;
 void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index d41435c22ce5..5c166d9d2dca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -399,9 +399,9 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		u8 metadata_index = be32_to_cpu(eseg->flow_table_metadata);
 
 		mlx5e_skb_cb_hwtstamp_init(skb);
-		mlx5e_ptpsq_track_metadata(sq->ptpsq, metadata_index);
 		mlx5e_ptp_metadata_map_put(&sq->ptpsq->metadata_map, skb,
 					   metadata_index);
+		mlx5e_ptpsq_track_metadata(sq->ptpsq, metadata_index);
 		if (!netif_tx_queue_stopped(sq->txq) &&
 		    mlx5e_ptpsq_metadata_freelist_empty(sq->ptpsq)) {
 			netif_tx_stop_queue(sq->txq);
@@ -494,10 +494,10 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 
 err_drop:
 	stats->dropped++;
-	dev_kfree_skb_any(skb);
 	if (unlikely(sq->ptpsq && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)))
 		mlx5e_ptp_metadata_fifo_push(&sq->ptpsq->metadata_freelist,
 					     be32_to_cpu(eseg->flow_table_metadata));
+	dev_kfree_skb_any(skb);
 	mlx5e_tx_flush(sq);
 }
 
@@ -861,7 +861,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 				mlx5e_dump_error_cqe(&sq->cq, sq->sqn,
 						     (struct mlx5_err_cqe *)cqe);
 				mlx5_wq_cyc_wqe_dump(&sq->wq, ci, wi->num_wqebbs);
-				queue_work(cq->priv->wq, &sq->recover_work);
+				queue_work(cq->workqueue, &sq->recover_work);
 			}
 			stats->cqe_err++;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index ea0405e0a43f..40a6cb052a2d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -885,11 +885,14 @@ static void comp_irq_release_sf(struct mlx5_core_dev *dev, u16 vecidx)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
 	struct mlx5_irq *irq;
+	int cpu;
 
 	irq = xa_load(&table->comp_irqs, vecidx);
 	if (!irq)
 		return;
 
+	cpu = cpumask_first(mlx5_irq_get_affinity_mask(irq));
+	cpumask_clear_cpu(cpu, &table->used_cpus);
 	xa_erase(&table->comp_irqs, vecidx);
 	mlx5_irq_affinity_irq_release(dev, irq);
 }
@@ -897,16 +900,26 @@ static void comp_irq_release_sf(struct mlx5_core_dev *dev, u16 vecidx)
 static int comp_irq_request_sf(struct mlx5_core_dev *dev, u16 vecidx)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
+	struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev);
+	struct irq_affinity_desc af_desc = {};
 	struct mlx5_irq *irq;
 
-	irq = mlx5_irq_affinity_irq_request_auto(dev, &table->used_cpus, vecidx);
-	if (IS_ERR(irq)) {
-		/* In case SF irq pool does not exist, fallback to the PF irqs*/
-		if (PTR_ERR(irq) == -ENOENT)
-			return comp_irq_request_pci(dev, vecidx);
+	/* In case SF irq pool does not exist, fallback to the PF irqs*/
+	if (!mlx5_irq_pool_is_sf_pool(pool))
+		return comp_irq_request_pci(dev, vecidx);
 
+	af_desc.is_managed = 1;
+	cpumask_copy(&af_desc.mask, cpu_online_mask);
+	cpumask_andnot(&af_desc.mask, &af_desc.mask, &table->used_cpus);
+	irq = mlx5_irq_affinity_request(pool, &af_desc);
+	if (IS_ERR(irq))
 		return PTR_ERR(irq);
-	}
+
+	cpumask_or(&table->used_cpus, &table->used_cpus, mlx5_irq_get_affinity_mask(irq));
+	mlx5_core_dbg(pool->dev, "IRQ %u mapped to cpu %*pbl, %u EQs on this irq\n",
+		      pci_irq_vector(dev->pdev, mlx5_irq_get_index(irq)),
+		      cpumask_pr_args(mlx5_irq_get_affinity_mask(irq)),
+		      mlx5_irq_read_locked(irq) / MLX5_EQ_REFS_PER_IRQ);
 
 	return xa_err(xa_store(&table->comp_irqs, vecidx, irq, GFP_KERNEL));
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
index 095f31f380fa..190f10aba170 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
@@ -21,158 +21,6 @@ enum {
 	MLX5_ESW_IPSEC_TX_ESP_FT_CNT_LEVEL,
 };
 
-static void esw_ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec,
-					     struct mlx5e_ipsec_rx *rx)
-{
-	mlx5_del_flow_rules(rx->status_drop.rule);
-	mlx5_destroy_flow_group(rx->status_drop.group);
-	mlx5_fc_destroy(ipsec->mdev, rx->status_drop_cnt);
-}
-
-static void esw_ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec,
-					     struct mlx5e_ipsec_rx *rx)
-{
-	mlx5_del_flow_rules(rx->status.rule);
-	mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0);
-}
-
-static int esw_ipsec_rx_status_drop_create(struct mlx5e_ipsec *ipsec,
-					   struct mlx5e_ipsec_rx *rx)
-{
-	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
-	struct mlx5_flow_table *ft = rx->ft.status;
-	struct mlx5_core_dev *mdev = ipsec->mdev;
-	struct mlx5_flow_destination dest = {};
-	struct mlx5_flow_act flow_act = {};
-	struct mlx5_flow_handle *rule;
-	struct mlx5_fc *flow_counter;
-	struct mlx5_flow_spec *spec;
-	struct mlx5_flow_group *g;
-	u32 *flow_group_in;
-	int err = 0;
-
-	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
-	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
-	if (!flow_group_in || !spec) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-
-	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ft->max_fte - 1);
-	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ft->max_fte - 1);
-	g = mlx5_create_flow_group(ft, flow_group_in);
-	if (IS_ERR(g)) {
-		err = PTR_ERR(g);
-		mlx5_core_err(mdev,
-			      "Failed to add ipsec rx status drop flow group, err=%d\n", err);
-		goto err_out;
-	}
-
-	flow_counter = mlx5_fc_create(mdev, false);
-	if (IS_ERR(flow_counter)) {
-		err = PTR_ERR(flow_counter);
-		mlx5_core_err(mdev,
-			      "Failed to add ipsec rx status drop rule counter, err=%d\n", err);
-		goto err_cnt;
-	}
-
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
-	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dest.counter_id = mlx5_fc_id(flow_counter);
-	spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
-	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
-	if (IS_ERR(rule)) {
-		err = PTR_ERR(rule);
-		mlx5_core_err(mdev,
-			      "Failed to add ipsec rx status drop rule, err=%d\n", err);
-		goto err_rule;
-	}
-
-	rx->status_drop.group = g;
-	rx->status_drop.rule = rule;
-	rx->status_drop_cnt = flow_counter;
-
-	kvfree(flow_group_in);
-	kvfree(spec);
-	return 0;
-
-err_rule:
-	mlx5_fc_destroy(mdev, flow_counter);
-err_cnt:
-	mlx5_destroy_flow_group(g);
-err_out:
-	kvfree(flow_group_in);
-	kvfree(spec);
-	return err;
-}
-
-static int esw_ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
-					   struct mlx5e_ipsec_rx *rx,
-					   struct mlx5_flow_destination *dest)
-{
-	struct mlx5_flow_act flow_act = {};
-	struct mlx5_flow_handle *rule;
-	struct mlx5_flow_spec *spec;
-	int err;
-
-	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
-	if (!spec)
-		return -ENOMEM;
-
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
-			 misc_parameters_2.ipsec_syndrome);
-	MLX5_SET(fte_match_param, spec->match_value,
-		 misc_parameters_2.ipsec_syndrome, 0);
-	spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
-	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
-	flow_act.flags = FLOW_ACT_NO_APPEND;
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
-			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
-	rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2);
-	if (IS_ERR(rule)) {
-		err = PTR_ERR(rule);
-		mlx5_core_warn(ipsec->mdev,
-			       "Failed to add ipsec rx status pass rule, err=%d\n", err);
-		goto err_rule;
-	}
-
-	rx->status.rule = rule;
-	kvfree(spec);
-	return 0;
-
-err_rule:
-	kvfree(spec);
-	return err;
-}
-
-void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
-				      struct mlx5e_ipsec_rx *rx)
-{
-	esw_ipsec_rx_status_pass_destroy(ipsec, rx);
-	esw_ipsec_rx_status_drop_destroy(ipsec, rx);
-}
-
-int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
-				    struct mlx5e_ipsec_rx *rx,
-				    struct mlx5_flow_destination *dest)
-{
-	int err;
-
-	err = esw_ipsec_rx_status_drop_create(ipsec, rx);
-	if (err)
-		return err;
-
-	err = esw_ipsec_rx_status_pass_create(ipsec, rx, dest);
-	if (err)
-		goto err_pass_create;
-
-	return 0;
-
-err_pass_create:
-	esw_ipsec_rx_status_drop_destroy(ipsec, rx);
-	return err;
-}
-
 void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				       struct mlx5e_ipsec_rx_create_attr *attr)
 {
@@ -202,7 +50,7 @@ int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry,
 	u32 mapped_id;
 	int err;
 
-	err = xa_alloc_bh(&ipsec->rx_esw->ipsec_obj_id_map, &mapped_id,
+	err = xa_alloc_bh(&ipsec->ipsec_obj_id_map, &mapped_id,
 			  xa_mk_value(sa_entry->ipsec_obj_id),
 			  XA_LIMIT(1, ESW_IPSEC_RX_MAPPED_ID_MASK), 0);
 	if (err)
@@ -233,7 +81,7 @@ int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry,
 	return 0;
 
 err_header_alloc:
-	xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map, mapped_id);
+	xa_erase_bh(&ipsec->ipsec_obj_id_map, mapped_id);
 	return err;
 }
 
@@ -242,7 +90,7 @@ void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry)
 	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
 
 	if (sa_entry->rx_mapped_id)
-		xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map,
+		xa_erase_bh(&ipsec->ipsec_obj_id_map,
 			    sa_entry->rx_mapped_id);
 }
 
@@ -252,7 +100,7 @@ int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
 	struct mlx5e_ipsec *ipsec = priv->ipsec;
 	void *val;
 
-	val = xa_load(&ipsec->rx_esw->ipsec_obj_id_map, id);
+	val = xa_load(&ipsec->ipsec_obj_id_map, id);
 	if (!val)
 		return -ENOENT;
 
@@ -304,7 +152,7 @@ void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev)
 
 	xa_for_each(&esw->offloads.vport_reps, i, rep) {
 		rpriv = rep->rep_data[REP_ETH].priv;
-		if (!rpriv || !rpriv->netdev)
+		if (!rpriv || !rpriv->netdev || !atomic_read(&rpriv->tc_ht.nelems))
 			continue;
 
 		rhashtable_walk_enter(&rpriv->tc_ht, &iter);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
index 0c90f7a8b0d3..ac9c65b89166 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
@@ -8,11 +8,6 @@ struct mlx5e_ipsec;
 struct mlx5e_ipsec_sa_entry;
 
 #ifdef CONFIG_MLX5_ESWITCH
-void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
-				      struct mlx5e_ipsec_rx *rx);
-int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
-				    struct mlx5e_ipsec_rx *rx,
-				    struct mlx5_flow_destination *dest);
 void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				       struct mlx5e_ipsec_rx_create_attr *attr);
 int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
@@ -26,16 +21,6 @@ void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				       struct mlx5e_ipsec_tx_create_attr *attr);
 void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev);
 #else
-static inline void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
-						    struct mlx5e_ipsec_rx *rx) {}
-
-static inline int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
-						  struct mlx5e_ipsec_rx *rx,
-						  struct mlx5_flow_destination *dest)
-{
-	return  -EINVAL;
-}
-
 static inline void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
 						     struct mlx5e_ipsec_rx_create_attr *attr) {}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 8d0b915a3121..3047d7015c52 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1463,7 +1463,7 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int num_vfs)
 {
 	int err;
 
-	lockdep_assert_held(&esw->mode_lock);
+	devl_assert_locked(priv_to_devlink(esw->dev));
 
 	if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) {
 		esw_warn(esw->dev, "FDB is not supported, aborting ...\n");
@@ -1531,7 +1531,6 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs)
 	if (toggle_lag)
 		mlx5_lag_disable_change(esw->dev);
 
-	down_write(&esw->mode_lock);
 	if (!mlx5_esw_is_fdb_created(esw)) {
 		ret = mlx5_eswitch_enable_locked(esw, num_vfs);
 	} else {
@@ -1554,8 +1553,6 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs)
 		}
 	}
 
-	up_write(&esw->mode_lock);
-
 	if (toggle_lag)
 		mlx5_lag_enable_change(esw->dev);
 
@@ -1569,12 +1566,11 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf)
 		return;
 
 	devl_assert_locked(priv_to_devlink(esw->dev));
-	down_write(&esw->mode_lock);
 	/* If driver is unloaded, this function is called twice by remove_one()
 	 * and mlx5_unload(). Prevent the second call.
 	 */
 	if (!esw->esw_funcs.num_vfs && !esw->esw_funcs.num_ec_vfs && !clear_vf)
-		goto unlock;
+		return;
 
 	esw_info(esw->dev, "Unload vfs: mode(%s), nvfs(%d), necvfs(%d), active vports(%d)\n",
 		 esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS",
@@ -1603,9 +1599,6 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf)
 		esw->esw_funcs.num_vfs = 0;
 	else
 		esw->esw_funcs.num_ec_vfs = 0;
-
-unlock:
-	up_write(&esw->mode_lock);
 }
 
 /* Free resources for corresponding eswitch mode. It is called by devlink
@@ -1647,10 +1640,8 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw)
 
 	devl_assert_locked(priv_to_devlink(esw->dev));
 	mlx5_lag_disable_change(esw->dev);
-	down_write(&esw->mode_lock);
 	mlx5_eswitch_disable_locked(esw);
 	esw->mode = MLX5_ESWITCH_LEGACY;
-	up_write(&esw->mode_lock);
 	mlx5_lag_enable_change(esw->dev);
 }
 
@@ -2254,8 +2245,13 @@ bool mlx5_esw_hold(struct mlx5_core_dev *mdev)
 	if (!mlx5_esw_allowed(esw))
 		return true;
 
-	if (down_read_trylock(&esw->mode_lock) != 0)
+	if (down_read_trylock(&esw->mode_lock) != 0) {
+		if (esw->eswitch_operation_in_progress) {
+			up_read(&esw->mode_lock);
+			return false;
+		}
 		return true;
+	}
 
 	return false;
 }
@@ -2312,7 +2308,8 @@ int mlx5_esw_try_lock(struct mlx5_eswitch *esw)
 	if (down_write_trylock(&esw->mode_lock) == 0)
 		return -EINVAL;
 
-	if (atomic64_read(&esw->user_count) > 0) {
+	if (esw->eswitch_operation_in_progress ||
+	    atomic64_read(&esw->user_count) > 0) {
 		up_write(&esw->mode_lock);
 		return -EBUSY;
 	}
@@ -2320,6 +2317,18 @@ int mlx5_esw_try_lock(struct mlx5_eswitch *esw)
 	return esw->mode;
 }
 
+int mlx5_esw_lock(struct mlx5_eswitch *esw)
+{
+	down_write(&esw->mode_lock);
+
+	if (esw->eswitch_operation_in_progress) {
+		up_write(&esw->mode_lock);
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
 /**
  * mlx5_esw_unlock() - Release write lock on esw mode lock
  * @esw: eswitch device.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 37ab66e7b403..b4eb17141edf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -383,6 +383,7 @@ struct mlx5_eswitch {
 	struct xarray paired;
 	struct mlx5_devcom_comp_dev *devcom;
 	u16 enabled_ipsec_vf_count;
+	bool eswitch_operation_in_progress;
 };
 
 void esw_offloads_disable(struct mlx5_eswitch *esw);
@@ -525,7 +526,8 @@ struct mlx5_esw_flow_attr {
 	u8	total_vlan;
 	struct {
 		u32 flags;
-		struct mlx5_eswitch_rep *rep;
+		bool vport_valid;
+		u16 vport;
 		struct mlx5_pkt_reformat *pkt_reformat;
 		struct mlx5_core_dev *mdev;
 		struct mlx5_termtbl_handle *termtbl;
@@ -827,6 +829,7 @@ void mlx5_esw_release(struct mlx5_core_dev *dev);
 void mlx5_esw_get(struct mlx5_core_dev *dev);
 void mlx5_esw_put(struct mlx5_core_dev *dev);
 int mlx5_esw_try_lock(struct mlx5_eswitch *esw);
+int mlx5_esw_lock(struct mlx5_eswitch *esw);
 void mlx5_esw_unlock(struct mlx5_eswitch *esw);
 
 void esw_vport_change_handle_locked(struct mlx5_vport *vport);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index b296ac52a439..b0455134c98e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -287,10 +287,9 @@ static void esw_put_dest_tables_loop(struct mlx5_eswitch *esw, struct mlx5_flow_
 	for (i = from; i < to; i++)
 		if (esw_attr->dests[i].flags & MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE)
 			mlx5_chains_put_table(chains, 0, 1, 0);
-		else if (mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].rep->vport,
+		else if (mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].vport,
 						     esw_attr->dests[i].mdev))
-			mlx5_esw_indir_table_put(esw, esw_attr->dests[i].rep->vport,
-						 false);
+			mlx5_esw_indir_table_put(esw, esw_attr->dests[i].vport, false);
 }
 
 static bool
@@ -358,8 +357,8 @@ esw_is_indir_table(struct mlx5_eswitch *esw, struct mlx5_flow_attr *attr)
 	 * this criteria.
 	 */
 	for (i = esw_attr->split_count; i < esw_attr->out_count; i++) {
-		if (esw_attr->dests[i].rep &&
-		    mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].rep->vport,
+		if (esw_attr->dests[i].vport_valid &&
+		    mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].vport,
 						esw_attr->dests[i].mdev)) {
 			result = true;
 		} else {
@@ -388,7 +387,7 @@ esw_setup_indir_table(struct mlx5_flow_destination *dest,
 		dest[*i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 
 		dest[*i].ft = mlx5_esw_indir_table_get(esw, attr,
-						       esw_attr->dests[j].rep->vport, false);
+						       esw_attr->dests[j].vport, false);
 		if (IS_ERR(dest[*i].ft)) {
 			err = PTR_ERR(dest[*i].ft);
 			goto err_indir_tbl_get;
@@ -432,11 +431,11 @@ static bool esw_setup_uplink_fwd_ipsec_needed(struct mlx5_eswitch *esw,
 					      int attr_idx)
 {
 	if (esw->offloads.ft_ipsec_tx_pol &&
-	    esw_attr->dests[attr_idx].rep &&
-	    esw_attr->dests[attr_idx].rep->vport == MLX5_VPORT_UPLINK &&
+	    esw_attr->dests[attr_idx].vport_valid &&
+	    esw_attr->dests[attr_idx].vport == MLX5_VPORT_UPLINK &&
 	    /* To be aligned with software, encryption is needed only for tunnel device */
 	    (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP_VALID) &&
-	    esw_attr->dests[attr_idx].rep != esw_attr->in_rep &&
+	    esw_attr->dests[attr_idx].vport != esw_attr->in_rep->vport &&
 	    esw_same_vhca_id(esw_attr->dests[attr_idx].mdev, esw->dev))
 		return true;
 
@@ -469,7 +468,7 @@ esw_setup_dest_fwd_vport(struct mlx5_flow_destination *dest, struct mlx5_flow_ac
 			 int attr_idx, int dest_idx, bool pkt_reformat)
 {
 	dest[dest_idx].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
-	dest[dest_idx].vport.num = esw_attr->dests[attr_idx].rep->vport;
+	dest[dest_idx].vport.num = esw_attr->dests[attr_idx].vport;
 	if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) {
 		dest[dest_idx].vport.vhca_id =
 			MLX5_CAP_GEN(esw_attr->dests[attr_idx].mdev, vhca_id);
@@ -984,7 +983,8 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw,
 	dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 
-	if (rep->vport == MLX5_VPORT_UPLINK && on_esw->offloads.ft_ipsec_tx_pol) {
+	if (rep->vport == MLX5_VPORT_UPLINK &&
+	    on_esw == from_esw && on_esw->offloads.ft_ipsec_tx_pol) {
 		dest.ft = on_esw->offloads.ft_ipsec_tx_pol;
 		flow_act.flags = FLOW_ACT_IGNORE_FLOW_LEVEL;
 		dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
@@ -1176,9 +1176,9 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 	struct mlx5_flow_handle *flow;
 	struct mlx5_flow_spec *spec;
 	struct mlx5_vport *vport;
+	int err, pfindex;
 	unsigned long i;
 	void *misc;
-	int err;
 
 	if (!MLX5_VPORT_MANAGER(esw->dev) && !mlx5_core_is_ecpf_esw_manager(esw->dev))
 		return 0;
@@ -1254,7 +1254,15 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 			flows[vport->index] = flow;
 		}
 	}
-	esw->fdb_table.offloads.peer_miss_rules[mlx5_get_dev_index(peer_dev)] = flows;
+
+	pfindex = mlx5_get_dev_index(peer_dev);
+	if (pfindex >= MLX5_MAX_PORTS) {
+		esw_warn(esw->dev, "Peer dev index(%d) is over the max num defined(%d)\n",
+			 pfindex, MLX5_MAX_PORTS);
+		err = -EINVAL;
+		goto add_ec_vf_flow_err;
+	}
+	esw->fdb_table.offloads.peer_miss_rules[pfindex] = flows;
 
 	kvfree(spec);
 	return 0;
@@ -3652,14 +3660,18 @@ static int esw_inline_mode_to_devlink(u8 mlx5_mode, u8 *mode)
 
 static bool esw_offloads_devlink_ns_eq_netdev_ns(struct devlink *devlink)
 {
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
 	struct net *devl_net, *netdev_net;
-	struct mlx5_eswitch *esw;
-
-	esw = mlx5_devlink_eswitch_nocheck_get(devlink);
-	netdev_net = dev_net(esw->dev->mlx5e_res.uplink_netdev);
-	devl_net = devlink_net(devlink);
+	bool ret = false;
 
-	return net_eq(devl_net, netdev_net);
+	mutex_lock(&dev->mlx5e_res.uplink_netdev_lock);
+	if (dev->mlx5e_res.uplink_netdev) {
+		netdev_net = dev_net(dev->mlx5e_res.uplink_netdev);
+		devl_net = devlink_net(devlink);
+		ret = net_eq(devl_net, netdev_net);
+	}
+	mutex_unlock(&dev->mlx5e_res.uplink_netdev_lock);
+	return ret;
 }
 
 int mlx5_eswitch_block_mode(struct mlx5_core_dev *dev)
@@ -3732,13 +3744,16 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 		goto unlock;
 	}
 
+	esw->eswitch_operation_in_progress = true;
+	up_write(&esw->mode_lock);
+
 	mlx5_eswitch_disable_locked(esw);
 	if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) {
 		if (mlx5_devlink_trap_get_num_active(esw->dev)) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Can't change mode while devlink traps are active");
 			err = -EOPNOTSUPP;
-			goto unlock;
+			goto skip;
 		}
 		err = esw_offloads_start(esw, extack);
 	} else if (mode == DEVLINK_ESWITCH_MODE_LEGACY) {
@@ -3748,6 +3763,9 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 		err = -EINVAL;
 	}
 
+skip:
+	down_write(&esw->mode_lock);
+	esw->eswitch_operation_in_progress = false;
 unlock:
 	mlx5_esw_unlock(esw);
 enable_lag:
@@ -3758,16 +3776,12 @@ enable_lag:
 int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
 {
 	struct mlx5_eswitch *esw;
-	int err;
 
 	esw = mlx5_devlink_eswitch_get(devlink);
 	if (IS_ERR(esw))
 		return PTR_ERR(esw);
 
-	down_read(&esw->mode_lock);
-	err = esw_mode_to_devlink(esw->mode, mode);
-	up_read(&esw->mode_lock);
-	return err;
+	return esw_mode_to_devlink(esw->mode, mode);
 }
 
 static int mlx5_esw_vports_inline_set(struct mlx5_eswitch *esw, u8 mlx5_mode,
@@ -3861,11 +3875,15 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode,
 	if (err)
 		goto out;
 
+	esw->eswitch_operation_in_progress = true;
+	up_write(&esw->mode_lock);
+
 	err = mlx5_esw_vports_inline_set(esw, mlx5_mode, extack);
-	if (err)
-		goto out;
+	if (!err)
+		esw->offloads.inline_mode = mlx5_mode;
 
-	esw->offloads.inline_mode = mlx5_mode;
+	down_write(&esw->mode_lock);
+	esw->eswitch_operation_in_progress = false;
 	up_write(&esw->mode_lock);
 	return 0;
 
@@ -3877,16 +3895,12 @@ out:
 int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode)
 {
 	struct mlx5_eswitch *esw;
-	int err;
 
 	esw = mlx5_devlink_eswitch_get(devlink);
 	if (IS_ERR(esw))
 		return PTR_ERR(esw);
 
-	down_read(&esw->mode_lock);
-	err = esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode);
-	up_read(&esw->mode_lock);
-	return err;
+	return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode);
 }
 
 bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev)
@@ -3968,6 +3982,9 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink,
 		goto unlock;
 	}
 
+	esw->eswitch_operation_in_progress = true;
+	up_write(&esw->mode_lock);
+
 	esw_destroy_offloads_fdb_tables(esw);
 
 	esw->offloads.encap = encap;
@@ -3981,6 +3998,9 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink,
 		(void)esw_create_offloads_fdb_tables(esw);
 	}
 
+	down_write(&esw->mode_lock);
+	esw->eswitch_operation_in_progress = false;
+
 unlock:
 	up_write(&esw->mode_lock);
 	return err;
@@ -3995,9 +4015,7 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink,
 	if (IS_ERR(esw))
 		return PTR_ERR(esw);
 
-	down_read(&esw->mode_lock);
 	*encap = esw->offloads.encap;
-	up_read(&esw->mode_lock);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
index edd910258314..40bdc677f051 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
@@ -233,8 +233,8 @@ mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw,
 
 	/* hairpin */
 	for (i = esw_attr->split_count; i < esw_attr->out_count; i++)
-		if (!esw_attr->dest_int_port && esw_attr->dests[i].rep &&
-		    esw_attr->dests[i].rep->vport == MLX5_VPORT_UPLINK)
+		if (!esw_attr->dest_int_port && esw_attr->dests[i].vport_valid &&
+		    esw_attr->dests[i].vport == MLX5_VPORT_UPLINK)
 			return true;
 
 	return false;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index a4b925331661..1616a6144f7b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -1144,3 +1144,37 @@ const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type typ
 		return mlx5_fs_cmd_get_stub_cmds();
 	}
 }
+
+int mlx5_fs_cmd_set_l2table_entry_silent(struct mlx5_core_dev *dev, u8 silent_mode)
+{
+	u32 in[MLX5_ST_SZ_DW(set_l2_table_entry_in)] = {};
+
+	if (silent_mode && !MLX5_CAP_GEN(dev, silent_mode))
+		return -EOPNOTSUPP;
+
+	MLX5_SET(set_l2_table_entry_in, in, opcode, MLX5_CMD_OP_SET_L2_TABLE_ENTRY);
+	MLX5_SET(set_l2_table_entry_in, in, silent_mode_valid, 1);
+	MLX5_SET(set_l2_table_entry_in, in, silent_mode, silent_mode);
+
+	return mlx5_cmd_exec_in(dev, set_l2_table_entry, in);
+}
+
+int mlx5_fs_cmd_set_tx_flow_table_root(struct mlx5_core_dev *dev, u32 ft_id, bool disconnect)
+{
+	u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)] = {};
+
+	if (disconnect && MLX5_CAP_FLOWTABLE_NIC_TX(dev, reset_root_to_default))
+		return -EOPNOTSUPP;
+
+	MLX5_SET(set_flow_table_root_in, in, opcode,
+		 MLX5_CMD_OP_SET_FLOW_TABLE_ROOT);
+	MLX5_SET(set_flow_table_root_in, in, table_type,
+		 FS_FT_NIC_TX);
+	if (disconnect)
+		MLX5_SET(set_flow_table_root_in, in, op_mod, 1);
+	else
+		MLX5_SET(set_flow_table_root_in, in, table_id, ft_id);
+
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
index 7790ae5531e1..53e0e5137d3f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
@@ -122,4 +122,6 @@ int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len,
 const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type type);
 const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void);
 
+int mlx5_fs_cmd_set_l2table_entry_silent(struct mlx5_core_dev *dev, u8 silent_mode);
+int mlx5_fs_cmd_set_tx_flow_table_root(struct mlx5_core_dev *dev, u32 ft_id, bool disconnect);
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 4aed1768b85f..78eb6b7097e1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -181,7 +181,7 @@ struct mlx5_flow_rule {
 
 struct mlx5_flow_handle {
 	int num_rules;
-	struct mlx5_flow_rule *rule[];
+	struct mlx5_flow_rule *rule[] __counted_by(num_rules);
 };
 
 /* Type of children is mlx5_flow_group */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index 17fe30a4c06c..0c26d707eed2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -539,7 +539,7 @@ struct mlx5_fc_bulk {
 	u32 base_id;
 	int bulk_len;
 	unsigned long *bitmask;
-	struct mlx5_fc fcs[];
+	struct mlx5_fc fcs[] __counted_by(bulk_len);
 };
 
 static void mlx5_fc_init(struct mlx5_fc *counter, struct mlx5_fc_bulk *bulk,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index b568988e92e3..f27eab6e4929 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -325,6 +325,48 @@ static void mlx5_fw_live_patch_event(struct work_struct *work)
 		mlx5_core_err(dev, "Failed to reload FW tracer\n");
 }
 
+#if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)
+static int mlx5_check_hotplug_interrupt(struct mlx5_core_dev *dev)
+{
+	struct pci_dev *bridge = dev->pdev->bus->self;
+	u16 reg16;
+	int err;
+
+	if (!bridge)
+		return -EOPNOTSUPP;
+
+	err = pcie_capability_read_word(bridge, PCI_EXP_SLTCTL, &reg16);
+	if (err)
+		return err;
+
+	if ((reg16 & PCI_EXP_SLTCTL_HPIE) && (reg16 & PCI_EXP_SLTCTL_DLLSCE)) {
+		mlx5_core_warn(dev, "FW reset is not supported as HotPlug is enabled\n");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+#endif
+
+static const struct pci_device_id mgt_ifc_device_ids[] = {
+	{ PCI_VDEVICE(MELLANOX, 0xc2d2) }, /* BlueField1 MGT interface device ID */
+	{ PCI_VDEVICE(MELLANOX, 0xc2d3) }, /* BlueField2 MGT interface device ID */
+	{ PCI_VDEVICE(MELLANOX, 0xc2d4) }, /* BlueField3-Lx MGT interface device ID */
+	{ PCI_VDEVICE(MELLANOX, 0xc2d5) }, /* BlueField3 MGT interface device ID */
+	{ PCI_VDEVICE(MELLANOX, 0xc2d6) }, /* BlueField4 MGT interface device ID */
+};
+
+static bool mlx5_is_mgt_ifc_pci_device(struct mlx5_core_dev *dev, u16 dev_id)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(mgt_ifc_device_ids); ++i)
+		if (mgt_ifc_device_ids[i].device == dev_id)
+			return true;
+
+	return false;
+}
+
 static int mlx5_check_dev_ids(struct mlx5_core_dev *dev, u16 dev_id)
 {
 	struct pci_bus *bridge_bus = dev->pdev->bus;
@@ -339,10 +381,15 @@ static int mlx5_check_dev_ids(struct mlx5_core_dev *dev, u16 dev_id)
 		err = pci_read_config_word(sdev, PCI_DEVICE_ID, &sdev_id);
 		if (err)
 			return pcibios_err_to_errno(err);
-		if (sdev_id != dev_id) {
-			mlx5_core_warn(dev, "unrecognized dev_id (0x%x)\n", sdev_id);
-			return -EPERM;
-		}
+
+		if (sdev_id == dev_id)
+			continue;
+
+		if (mlx5_is_mgt_ifc_pci_device(dev, sdev_id))
+			continue;
+
+		mlx5_core_warn(dev, "unrecognized dev_id (0x%x)\n", sdev_id);
+		return -EPERM;
 	}
 	return 0;
 }
@@ -357,6 +404,12 @@ static bool mlx5_is_reset_now_capable(struct mlx5_core_dev *dev)
 		return false;
 	}
 
+#if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)
+	err = mlx5_check_hotplug_interrupt(dev);
+	if (err)
+		return false;
+#endif
+
 	err = pci_read_config_word(dev->pdev, PCI_DEVICE_ID, &dev_id);
 	if (err)
 		return false;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 2bf77a5251b4..58845121954c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -339,7 +339,7 @@ static int mlx5i_init_tx(struct mlx5e_priv *priv)
 		return err;
 	}
 
-	err = mlx5i_create_tis(priv->mdev, ipriv->qpn, &priv->tisn[0][0]);
+	err = mlx5i_create_tis(priv->mdev, ipriv->qpn, &ipriv->tisn);
 	if (err) {
 		mlx5_core_warn(priv->mdev, "create tis failed, %d\n", err);
 		goto err_destroy_underlay_qp;
@@ -356,7 +356,7 @@ static void mlx5i_cleanup_tx(struct mlx5e_priv *priv)
 {
 	struct mlx5i_priv *ipriv = priv->ppriv;
 
-	mlx5e_destroy_tis(priv->mdev, priv->tisn[0][0]);
+	mlx5e_destroy_tis(priv->mdev, ipriv->tisn);
 	mlx5i_destroy_underlay_qp(priv->mdev, ipriv->qpn);
 }
 
@@ -483,6 +483,18 @@ static unsigned int mlx5i_stats_grps_num(struct mlx5e_priv *priv)
 	return ARRAY_SIZE(mlx5i_stats_grps);
 }
 
+u32 mlx5i_get_tisn(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv, u8 lag_port, u8 tc)
+{
+	struct mlx5i_priv *ipriv = priv->ppriv;
+
+	if (WARN(lag_port || tc,
+		 "IPoIB unexpected non-zero value: lag_port (%u), tc (%u)\n",
+		 lag_port, tc))
+		return 0;
+
+	return ipriv->tisn;
+}
+
 static const struct mlx5e_profile mlx5i_nic_profile = {
 	.init		   = mlx5i_init,
 	.cleanup	   = mlx5i_cleanup,
@@ -499,6 +511,7 @@ static const struct mlx5e_profile mlx5i_nic_profile = {
 	.max_tc		   = MLX5I_MAX_NUM_TC,
 	.stats_grps        = mlx5i_stats_grps,
 	.stats_grps_num    = mlx5i_stats_grps_num,
+	.get_tisn          = mlx5i_get_tisn,
 };
 
 /* mlx5i netdev NDos */
@@ -829,7 +842,7 @@ int mlx5_rdma_rn_get_params(struct mlx5_core_dev *mdev,
 	*params = (struct rdma_netdev_alloc_params){
 		.sizeof_priv = sizeof(struct mlx5i_priv) +
 			       sizeof(struct mlx5e_priv),
-		.txqs = nch * MLX5E_MAX_NUM_TC,
+		.txqs = nch * MLX5_MAX_NUM_TC,
 		.rxqs = nch,
 		.param = mdev,
 		.initialize_rdma_netdev = mlx5_rdma_setup_rn,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
index f3f2af972020..2ab6437a1c49 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
@@ -53,6 +53,7 @@ extern const struct mlx5e_rx_handlers mlx5i_rx_handlers;
 struct mlx5i_priv {
 	struct rdma_netdev rn; /* keep this first */
 	u32 qpn;
+	u32 tisn;
 	bool   sub_interface;
 	u32    num_sub_interfaces;
 	u32    qkey;
@@ -63,6 +64,7 @@ struct mlx5i_priv {
 };
 
 int mlx5i_create_tis(struct mlx5_core_dev *mdev, u32 underlay_qpn, u32 *tisn);
+u32 mlx5i_get_tisn(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv, u8 lag_port, u8 tc);
 
 /* Underlay QP create/destroy functions */
 int mlx5i_create_underlay_qp(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
index 03e681297937..f87471306f6b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
@@ -218,7 +218,7 @@ static int mlx5i_pkey_open(struct net_device *netdev)
 		goto err_unint_underlay_qp;
 	}
 
-	err = mlx5i_create_tis(mdev, ipriv->qpn, &epriv->tisn[0][0]);
+	err = mlx5i_create_tis(mdev, ipriv->qpn, &ipriv->tisn);
 	if (err) {
 		mlx5_core_warn(mdev, "create child tis failed, %d\n", err);
 		goto err_remove_rx_uderlay_qp;
@@ -240,7 +240,7 @@ static int mlx5i_pkey_open(struct net_device *netdev)
 err_close_channels:
 	mlx5e_close_channels(&epriv->channels);
 err_clear_state_opened_flag:
-	mlx5e_destroy_tis(mdev, epriv->tisn[0][0]);
+	mlx5e_destroy_tis(mdev, ipriv->tisn);
 err_remove_rx_uderlay_qp:
 	mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qpn);
 err_unint_underlay_qp:
@@ -269,7 +269,7 @@ static int mlx5i_pkey_close(struct net_device *netdev)
 	mlx5i_uninit_underlay_qp(priv);
 	mlx5e_deactivate_priv_channels(priv);
 	mlx5e_close_channels(&priv->channels);
-	mlx5e_destroy_tis(mdev, priv->tisn[0][0]);
+	mlx5e_destroy_tis(mdev, ipriv->tisn);
 unlock:
 	mutex_unlock(&priv->state_lock);
 	return 0;
@@ -361,6 +361,7 @@ static const struct mlx5e_profile mlx5i_pkey_nic_profile = {
 	.update_stats	   = NULL,
 	.rx_handlers       = &mlx5i_rx_handlers,
 	.max_tc		   = MLX5I_MAX_NUM_TC,
+	.get_tisn          = mlx5i_get_tisn,
 };
 
 const struct mlx5e_profile *mlx5i_pkey_get_profile(void)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
index 047d5fed5f89..612e666ec263 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
@@ -168,45 +168,3 @@ void mlx5_irq_affinity_irq_release(struct mlx5_core_dev *dev, struct mlx5_irq *i
 		if (pool->irqs_per_cpu)
 			cpu_put(pool, cpu);
 }
-
-/**
- * mlx5_irq_affinity_irq_request_auto - request one IRQ for mlx5 device.
- * @dev: mlx5 device that is requesting the IRQ.
- * @used_cpus: cpumask of bounded cpus by the device
- * @vecidx: vector index to request an IRQ for.
- *
- * Each IRQ is bounded to at most 1 CPU.
- * This function is requesting an IRQ according to the default assignment.
- * The default assignment policy is:
- * - request the least loaded IRQ which is not bound to any
- *   CPU of the previous IRQs requested.
- *
- * On success, this function updates used_cpus mask and returns an irq pointer.
- * In case of an error, an appropriate error pointer is returned.
- */
-struct mlx5_irq *mlx5_irq_affinity_irq_request_auto(struct mlx5_core_dev *dev,
-						    struct cpumask *used_cpus, u16 vecidx)
-{
-	struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev);
-	struct irq_affinity_desc af_desc = {};
-	struct mlx5_irq *irq;
-
-	if (!mlx5_irq_pool_is_sf_pool(pool))
-		return ERR_PTR(-ENOENT);
-
-	af_desc.is_managed = 1;
-	cpumask_copy(&af_desc.mask, cpu_online_mask);
-	cpumask_andnot(&af_desc.mask, &af_desc.mask, used_cpus);
-	irq = mlx5_irq_affinity_request(pool, &af_desc);
-
-	if (IS_ERR(irq))
-		return irq;
-
-	cpumask_or(used_cpus, used_cpus, mlx5_irq_get_affinity_mask(irq));
-	mlx5_core_dbg(pool->dev, "IRQ %u mapped to cpu %*pbl, %u EQs on this irq\n",
-		      pci_irq_vector(dev->pdev, mlx5_irq_get_index(irq)),
-		      cpumask_pr_args(mlx5_irq_get_affinity_mask(irq)),
-		      mlx5_irq_read_locked(irq) / MLX5_EQ_REFS_PER_IRQ);
-
-	return irq;
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index aa29f09e8356..0361741632a6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -266,9 +266,6 @@ static int mlx5_ptp_settime_real_time(struct mlx5_core_dev *mdev,
 {
 	u32 in[MLX5_ST_SZ_DW(mtutc_reg)] = {};
 
-	if (!mlx5_modify_mtutc_allowed(mdev))
-		return 0;
-
 	if (ts->tv_sec < 0 || ts->tv_sec > U32_MAX ||
 	    ts->tv_nsec < 0 || ts->tv_nsec > NSEC_PER_SEC)
 		return -EINVAL;
@@ -286,12 +283,15 @@ static int mlx5_ptp_settime(struct ptp_clock_info *ptp, const struct timespec64
 	struct mlx5_timer *timer = &clock->timer;
 	struct mlx5_core_dev *mdev;
 	unsigned long flags;
-	int err;
 
 	mdev = container_of(clock, struct mlx5_core_dev, clock);
-	err = mlx5_ptp_settime_real_time(mdev, ts);
-	if (err)
-		return err;
+
+	if (mlx5_modify_mtutc_allowed(mdev)) {
+		int err = mlx5_ptp_settime_real_time(mdev, ts);
+
+		if (err)
+			return err;
+	}
 
 	write_seqlock_irqsave(&clock->lock, flags);
 	timecounter_init(&timer->tc, &timer->cycles, timespec64_to_ns(ts));
@@ -341,9 +341,6 @@ static int mlx5_ptp_adjtime_real_time(struct mlx5_core_dev *mdev, s64 delta)
 {
 	u32 in[MLX5_ST_SZ_DW(mtutc_reg)] = {};
 
-	if (!mlx5_modify_mtutc_allowed(mdev))
-		return 0;
-
 	/* HW time adjustment range is checked. If out of range, settime instead */
 	if (!mlx5_is_mtutc_time_adj_cap(mdev, delta)) {
 		struct timespec64 ts;
@@ -367,13 +364,16 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 	struct mlx5_timer *timer = &clock->timer;
 	struct mlx5_core_dev *mdev;
 	unsigned long flags;
-	int err;
 
 	mdev = container_of(clock, struct mlx5_core_dev, clock);
 
-	err = mlx5_ptp_adjtime_real_time(mdev, delta);
-	if (err)
-		return err;
+	if (mlx5_modify_mtutc_allowed(mdev)) {
+		int err = mlx5_ptp_adjtime_real_time(mdev, delta);
+
+		if (err)
+			return err;
+	}
+
 	write_seqlock_irqsave(&clock->lock, flags);
 	timecounter_adjtime(&timer->tc, delta);
 	mlx5_update_clock_info_page(mdev);
@@ -384,22 +384,26 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 
 static int mlx5_ptp_adjphase(struct ptp_clock_info *ptp, s32 delta)
 {
-	return mlx5_ptp_adjtime(ptp, delta);
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
+	struct mlx5_core_dev *mdev;
+
+	mdev = container_of(clock, struct mlx5_core_dev, clock);
+
+	return mlx5_ptp_adjtime_real_time(mdev, delta);
 }
 
 static int mlx5_ptp_freq_adj_real_time(struct mlx5_core_dev *mdev, long scaled_ppm)
 {
 	u32 in[MLX5_ST_SZ_DW(mtutc_reg)] = {};
 
-	if (!mlx5_modify_mtutc_allowed(mdev))
-		return 0;
-
 	MLX5_SET(mtutc_reg, in, operation, MLX5_MTUTC_OPERATION_ADJUST_FREQ_UTC);
 
-	if (MLX5_CAP_MCAM_FEATURE(mdev, mtutc_freq_adj_units)) {
+	if (MLX5_CAP_MCAM_FEATURE(mdev, mtutc_freq_adj_units) &&
+	    scaled_ppm <= S32_MAX && scaled_ppm >= S32_MIN) {
+		/* HW scaled_ppm support on mlx5 devices only supports a 32-bit value */
 		MLX5_SET(mtutc_reg, in, freq_adj_units,
 			 MLX5_MTUTC_FREQ_ADJ_UNITS_SCALED_PPM);
-		MLX5_SET(mtutc_reg, in, freq_adjustment, scaled_ppm);
+		MLX5_SET(mtutc_reg, in, freq_adjustment, (s32)scaled_ppm);
 	} else {
 		MLX5_SET(mtutc_reg, in, freq_adj_units, MLX5_MTUTC_FREQ_ADJ_UNITS_PPB);
 		MLX5_SET(mtutc_reg, in, freq_adjustment, scaled_ppm_to_ppb(scaled_ppm));
@@ -415,13 +419,15 @@ static int mlx5_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 	struct mlx5_core_dev *mdev;
 	unsigned long flags;
 	u32 mult;
-	int err;
 
 	mdev = container_of(clock, struct mlx5_core_dev, clock);
 
-	err = mlx5_ptp_freq_adj_real_time(mdev, scaled_ppm);
-	if (err)
-		return err;
+	if (mlx5_modify_mtutc_allowed(mdev)) {
+		int err = mlx5_ptp_freq_adj_real_time(mdev, scaled_ppm);
+
+		if (err)
+			return err;
+	}
 
 	mult = (u32)adjust_by_scaled_ppm(timer->nominal_c_mult, scaled_ppm);
 
@@ -999,14 +1005,38 @@ static void mlx5_init_clock_info(struct mlx5_core_dev *mdev)
 	info->frac = timer->tc.frac;
 }
 
+static void mlx5_init_timer_max_freq_adjustment(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_clock *clock = &mdev->clock;
+	u32 out[MLX5_ST_SZ_DW(mtutc_reg)] = {};
+	u32 in[MLX5_ST_SZ_DW(mtutc_reg)] = {};
+	u8 log_max_freq_adjustment = 0;
+	int err;
+
+	err = mlx5_core_access_reg(mdev, in, sizeof(in), out, sizeof(out),
+				   MLX5_REG_MTUTC, 0, 0);
+	if (!err)
+		log_max_freq_adjustment =
+			MLX5_GET(mtutc_reg, out, log_max_freq_adjustment);
+
+	if (log_max_freq_adjustment)
+		clock->ptp_info.max_adj =
+			min(S32_MAX, 1 << log_max_freq_adjustment);
+}
+
 static void mlx5_init_timer_clock(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_clock *clock = &mdev->clock;
 
+	/* Configure the PHC */
+	clock->ptp_info = mlx5_ptp_clock_info;
+
+	if (MLX5_CAP_MCAM_REG(mdev, mtutc))
+		mlx5_init_timer_max_freq_adjustment(mdev);
+
 	mlx5_timecounter_init(mdev);
 	mlx5_init_clock_info(mdev);
 	mlx5_init_overflow_period(clock);
-	clock->ptp_info = mlx5_ptp_clock_info;
 
 	if (mlx5_real_time_mode(mdev)) {
 		struct timespec64 ts;
@@ -1037,11 +1067,10 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev)
 	}
 
 	seqlock_init(&clock->lock);
-	mlx5_init_timer_clock(mdev);
 	INIT_WORK(&clock->pps_info.out_work, mlx5_pps_out);
 
-	/* Configure the PHC */
-	clock->ptp_info = mlx5_ptp_clock_info;
+	/* Initialize the device clock */
+	mlx5_init_timer_clock(mdev);
 
 	/* Initialize 1PPS data structures */
 	mlx5_init_pps(mdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
index e8e50563e956..e7d59cfa8708 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
@@ -256,6 +256,13 @@ void mlx5_devcom_unregister_component(struct mlx5_devcom_comp_dev *devcom)
 		devcom_free_comp_dev(devcom);
 }
 
+int mlx5_devcom_comp_get_size(struct mlx5_devcom_comp_dev *devcom)
+{
+	struct mlx5_devcom_comp *comp = devcom->comp;
+
+	return kref_read(&comp->ref);
+}
+
 int mlx5_devcom_send_event(struct mlx5_devcom_comp_dev *devcom,
 			   int event, int rollback_event,
 			   void *event_data)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
index fc23bbef87b4..ec32b686f586 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
@@ -31,6 +31,7 @@ void mlx5_devcom_unregister_component(struct mlx5_devcom_comp_dev *devcom);
 int mlx5_devcom_send_event(struct mlx5_devcom_comp_dev *devcom,
 			   int event, int rollback_event,
 			   void *event_data);
+int mlx5_devcom_comp_get_size(struct mlx5_devcom_comp_dev *devcom);
 
 void mlx5_devcom_comp_set_ready(struct mlx5_devcom_comp_dev *devcom, bool ready);
 bool mlx5_devcom_comp_is_ready(struct mlx5_devcom_comp_dev *devcom);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index a17152c1cbb2..bccf6e53556c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -219,7 +219,6 @@ static void mlx5_set_driver_version(struct mlx5_core_dev *dev)
 	int driver_ver_sz = MLX5_FLD_SZ_BYTES(set_driver_version_in,
 					      driver_version);
 	u8 in[MLX5_ST_SZ_BYTES(set_driver_version_in)] = {};
-	int remaining_size = driver_ver_sz;
 	char *string;
 
 	if (!MLX5_CAP_GEN(dev, driver_version))
@@ -227,22 +226,9 @@ static void mlx5_set_driver_version(struct mlx5_core_dev *dev)
 
 	string = MLX5_ADDR_OF(set_driver_version_in, in, driver_version);
 
-	strncpy(string, "Linux", remaining_size);
-
-	remaining_size = max_t(int, 0, driver_ver_sz - strlen(string));
-	strncat(string, ",", remaining_size);
-
-	remaining_size = max_t(int, 0, driver_ver_sz - strlen(string));
-	strncat(string, KBUILD_MODNAME, remaining_size);
-
-	remaining_size = max_t(int, 0, driver_ver_sz - strlen(string));
-	strncat(string, ",", remaining_size);
-
-	remaining_size = max_t(int, 0, driver_ver_sz - strlen(string));
-
-	snprintf(string + strlen(string), remaining_size, "%u.%u.%u",
-		LINUX_VERSION_MAJOR, LINUX_VERSION_PATCHLEVEL,
-		LINUX_VERSION_SUBLEVEL);
+	snprintf(string, driver_ver_sz, "Linux,%s,%u.%u.%u",
+		 KBUILD_MODNAME, LINUX_VERSION_MAJOR,
+		 LINUX_VERSION_PATCHLEVEL, LINUX_VERSION_SUBLEVEL);
 
 	/*Send the command*/
 	MLX5_SET(set_driver_version_in, in, opcode,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 6b14e347d914..a79b7959361b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -243,6 +243,7 @@ int mlx5_query_mcam_reg(struct mlx5_core_dev *dev, u32 *mcap, u8 feature_group,
 			u8 access_reg_group);
 int mlx5_query_qcam_reg(struct mlx5_core_dev *mdev, u32 *qcam,
 			u8 feature_group, u8 access_reg_group);
+int mlx5_query_mpir_reg(struct mlx5_core_dev *dev, u32 *mpir);
 
 void mlx5_lag_add_netdev(struct mlx5_core_dev *dev, struct net_device *netdev);
 void mlx5_lag_remove_netdev(struct mlx5_core_dev *dev, struct net_device *netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 653648216730..4dcf995cb1a2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -28,7 +28,7 @@
 struct mlx5_irq {
 	struct atomic_notifier_head nh;
 	cpumask_var_t mask;
-	char name[MLX5_MAX_IRQ_NAME];
+	char name[MLX5_MAX_IRQ_FORMATTED_NAME];
 	struct mlx5_irq_pool *pool;
 	int refcount;
 	struct msi_map map;
@@ -292,8 +292,8 @@ struct mlx5_irq *mlx5_irq_alloc(struct mlx5_irq_pool *pool, int i,
 	else
 		irq_sf_set_name(pool, name, i);
 	ATOMIC_INIT_NOTIFIER_HEAD(&irq->nh);
-	snprintf(irq->name, MLX5_MAX_IRQ_NAME,
-		 "%s@pci:%s", name, pci_name(dev->pdev));
+	snprintf(irq->name, MLX5_MAX_IRQ_FORMATTED_NAME,
+		 MLX5_IRQ_NAME_FORMAT_STR, name, pci_name(dev->pdev));
 	err = request_irq(irq->map.virq, irq_int_handler, 0, irq->name,
 			  &irq->nh);
 	if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h
index d3a77a0ab848..c4d377f8df30 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h
@@ -7,6 +7,9 @@
 #include <linux/mlx5/driver.h>
 
 #define MLX5_MAX_IRQ_NAME (32)
+#define MLX5_IRQ_NAME_FORMAT_STR ("%s@pci:%s")
+#define MLX5_MAX_IRQ_FORMATTED_NAME \
+	(MLX5_MAX_IRQ_NAME + sizeof(MLX5_IRQ_NAME_FORMAT_STR))
 /* max irq_index is 2047, so four chars */
 #define MLX5_MAX_IRQ_IDX_CHARS (4)
 #define MLX5_EQ_REFS_PER_IRQ (2)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 7d8c732818f2..7fba1c46e2ac 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -1206,3 +1206,13 @@ int mlx5_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 	*speed = max_speed;
 	return 0;
 }
+
+int mlx5_query_mpir_reg(struct mlx5_core_dev *dev, u32 *mpir)
+{
+	u32 in[MLX5_ST_SZ_DW(mpir_reg)] = {};
+	int sz = MLX5_ST_SZ_BYTES(mpir_reg);
+
+	MLX5_SET(mpir_reg, in, local_port, 1);
+
+	return mlx5_core_access_reg(dev, in, sz, mpir, sz, MLX5_REG_MPIR, 0, 0);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
index 6ea88a581804..6f9790e97fed 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
@@ -57,7 +57,8 @@ static const char *dr_action_id_to_str(enum mlx5dr_action_type action_id)
 
 static bool mlx5dr_action_supp_fwd_fdb_multi_ft(struct mlx5_core_dev *dev)
 {
-	return (MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_any_table_limit_regc) ||
+	return (MLX5_CAP_GEN(dev, steering_format_version) < MLX5_STEERING_FORMAT_CONNECTX_6DX ||
+		MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_any_table_limit_regc) ||
 		MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_any_table));
 }
 
@@ -1169,7 +1170,6 @@ mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn,
 				   bool ignore_flow_level,
 				   u32 flow_source)
 {
-	struct mlx5dr_cmd_flow_destination_hw_info tmp_hw_dest;
 	struct mlx5dr_cmd_flow_destination_hw_info *hw_dests;
 	struct mlx5dr_action **ref_actions;
 	struct mlx5dr_action *action;
@@ -1248,11 +1248,8 @@ mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn,
 	 * one that done in the TX.
 	 * So, if one of the ft target is wire, put it at the end of the dest list.
 	 */
-	if (is_ft_wire && num_dst_ft > 1) {
-		tmp_hw_dest = hw_dests[last_dest];
-		hw_dests[last_dest] = hw_dests[num_of_dests - 1];
-		hw_dests[num_of_dests - 1] = tmp_hw_dest;
-	}
+	if (is_ft_wire && num_dst_ft > 1)
+		swap(hw_dests[last_dest], hw_dests[num_of_dests - 1]);
 
 	action = dr_action_create_generic(DR_ACTION_TYP_FT);
 	if (!action)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index 4e8527a724f5..6fa06ba2d346 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -52,7 +52,6 @@ struct dr_qp_init_attr {
 	u32 cqn;
 	u32 pdn;
 	u32 max_send_wr;
-	u32 max_send_sge;
 	struct mlx5_uars_page *uar;
 	u8 isolate_vl_tc:1;
 };
@@ -247,37 +246,6 @@ static int dr_poll_cq(struct mlx5dr_cq *dr_cq, int ne)
 	return err == CQ_POLL_ERR ? err : npolled;
 }
 
-static int dr_qp_get_args_update_send_wqe_size(struct dr_qp_init_attr *attr)
-{
-	return roundup_pow_of_two(sizeof(struct mlx5_wqe_ctrl_seg) +
-				  sizeof(struct mlx5_wqe_flow_update_ctrl_seg) +
-				  sizeof(struct mlx5_wqe_header_modify_argument_update_seg));
-}
-
-/* We calculate for specific RC QP with the required functionality */
-static int dr_qp_calc_rc_send_wqe(struct dr_qp_init_attr *attr)
-{
-	int update_arg_size;
-	int inl_size = 0;
-	int tot_size;
-	int size;
-
-	update_arg_size = dr_qp_get_args_update_send_wqe_size(attr);
-
-	size = sizeof(struct mlx5_wqe_ctrl_seg) +
-	       sizeof(struct mlx5_wqe_raddr_seg);
-	inl_size = size + ALIGN(sizeof(struct mlx5_wqe_inline_seg) +
-				DR_STE_SIZE, 16);
-
-	size += attr->max_send_sge * sizeof(struct mlx5_wqe_data_seg);
-
-	size = max(size, update_arg_size);
-
-	tot_size = max(size, inl_size);
-
-	return ALIGN(tot_size, MLX5_SEND_WQE_BB);
-}
-
 static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
 					 struct dr_qp_init_attr *attr)
 {
@@ -285,7 +253,6 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
 	u32 temp_qpc[MLX5_ST_SZ_DW(qpc)] = {};
 	struct mlx5_wq_param wqp;
 	struct mlx5dr_qp *dr_qp;
-	int wqe_size;
 	int inlen;
 	void *qpc;
 	void *in;
@@ -365,15 +332,6 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
 	if (err)
 		goto err_in;
 	dr_qp->uar = attr->uar;
-	wqe_size = dr_qp_calc_rc_send_wqe(attr);
-	dr_qp->max_inline_data = min(wqe_size -
-				     (sizeof(struct mlx5_wqe_ctrl_seg) +
-				      sizeof(struct mlx5_wqe_raddr_seg) +
-				      sizeof(struct mlx5_wqe_inline_seg)),
-				     (2 * MLX5_SEND_WQE_BB -
-				      (sizeof(struct mlx5_wqe_ctrl_seg) +
-				       sizeof(struct mlx5_wqe_raddr_seg) +
-				       sizeof(struct mlx5_wqe_inline_seg))));
 
 	return dr_qp;
 
@@ -437,48 +395,8 @@ dr_rdma_handle_flow_access_arg_segments(struct mlx5_wqe_ctrl_seg *wq_ctrl,
 		MLX5_SEND_WQE_DS;
 }
 
-static int dr_set_data_inl_seg(struct mlx5dr_qp *dr_qp,
-			       struct dr_data_seg *data_seg, void *wqe)
-{
-	int inline_header_size = sizeof(struct mlx5_wqe_ctrl_seg) +
-				sizeof(struct mlx5_wqe_raddr_seg) +
-				sizeof(struct mlx5_wqe_inline_seg);
-	struct mlx5_wqe_inline_seg *seg;
-	int left_space;
-	int inl = 0;
-	void *addr;
-	int len;
-	int idx;
-
-	seg = wqe;
-	wqe += sizeof(*seg);
-	addr = (void *)(unsigned long)(data_seg->addr);
-	len  = data_seg->length;
-	inl += len;
-	left_space = MLX5_SEND_WQE_BB - inline_header_size;
-
-	if (likely(len > left_space)) {
-		memcpy(wqe, addr, left_space);
-		len -= left_space;
-		addr += left_space;
-		idx = (dr_qp->sq.pc + 1) & (dr_qp->sq.wqe_cnt - 1);
-		wqe = mlx5_wq_cyc_get_wqe(&dr_qp->wq.sq, idx);
-	}
-
-	memcpy(wqe, addr, len);
-
-	if (likely(inl)) {
-		seg->byte_count = cpu_to_be32(inl | MLX5_INLINE_SEG);
-		return DIV_ROUND_UP(inl + sizeof(seg->byte_count),
-				    MLX5_SEND_WQE_DS);
-	} else {
-		return 0;
-	}
-}
-
 static void
-dr_rdma_handle_icm_write_segments(struct mlx5dr_qp *dr_qp,
-				  struct mlx5_wqe_ctrl_seg *wq_ctrl,
+dr_rdma_handle_icm_write_segments(struct mlx5_wqe_ctrl_seg *wq_ctrl,
 				  u64 remote_addr,
 				  u32 rkey,
 				  struct dr_data_seg *data_seg,
@@ -494,17 +412,15 @@ dr_rdma_handle_icm_write_segments(struct mlx5dr_qp *dr_qp,
 	wq_raddr->reserved = 0;
 
 	wq_dseg = (void *)(wq_raddr + 1);
-	/* WQE ctrl segment + WQE remote addr segment */
-	*size = (sizeof(*wq_ctrl) + sizeof(*wq_raddr)) / MLX5_SEND_WQE_DS;
 
-	if (data_seg->send_flags & IB_SEND_INLINE) {
-		*size += dr_set_data_inl_seg(dr_qp, data_seg, wq_dseg);
-	} else {
-		wq_dseg->byte_count = cpu_to_be32(data_seg->length);
-		wq_dseg->lkey = cpu_to_be32(data_seg->lkey);
-		wq_dseg->addr = cpu_to_be64(data_seg->addr);
-		*size += sizeof(*wq_dseg) / MLX5_SEND_WQE_DS;  /* WQE data segment */
-	}
+	wq_dseg->byte_count = cpu_to_be32(data_seg->length);
+	wq_dseg->lkey = cpu_to_be32(data_seg->lkey);
+	wq_dseg->addr = cpu_to_be64(data_seg->addr);
+
+	*size = (sizeof(*wq_ctrl) +    /* WQE ctrl segment */
+		 sizeof(*wq_dseg) +    /* WQE data segment */
+		 sizeof(*wq_raddr)) /  /* WQE remote addr segment */
+		MLX5_SEND_WQE_DS;
 }
 
 static void dr_set_ctrl_seg(struct mlx5_wqe_ctrl_seg *wq_ctrl,
@@ -535,7 +451,7 @@ static void dr_rdma_segments(struct mlx5dr_qp *dr_qp, u64 remote_addr,
 	switch (opcode) {
 	case MLX5_OPCODE_RDMA_READ:
 	case MLX5_OPCODE_RDMA_WRITE:
-		dr_rdma_handle_icm_write_segments(dr_qp, wq_ctrl, remote_addr,
+		dr_rdma_handle_icm_write_segments(wq_ctrl, remote_addr,
 						  rkey, data_seg, &size);
 		break;
 	case MLX5_OPCODE_FLOW_TBL_ACCESS:
@@ -656,7 +572,7 @@ static void dr_fill_write_args_segs(struct mlx5dr_send_ring *send_ring,
 	if (send_ring->pending_wqe % send_ring->signal_th == 0)
 		send_info->write.send_flags |= IB_SEND_SIGNALED;
 	else
-		send_info->write.send_flags &= ~IB_SEND_SIGNALED;
+		send_info->write.send_flags = 0;
 }
 
 static void dr_fill_write_icm_segs(struct mlx5dr_domain *dmn,
@@ -680,13 +596,9 @@ static void dr_fill_write_icm_segs(struct mlx5dr_domain *dmn,
 	}
 
 	send_ring->pending_wqe++;
-	if (!send_info->write.lkey)
-		send_info->write.send_flags |= IB_SEND_INLINE;
 
 	if (send_ring->pending_wqe % send_ring->signal_th == 0)
 		send_info->write.send_flags |= IB_SEND_SIGNALED;
-	else
-		send_info->write.send_flags &= ~IB_SEND_SIGNALED;
 
 	send_ring->pending_wqe++;
 	send_info->read.length = send_info->write.length;
@@ -696,9 +608,9 @@ static void dr_fill_write_icm_segs(struct mlx5dr_domain *dmn,
 	send_info->read.lkey = send_ring->sync_mr->mkey;
 
 	if (send_ring->pending_wqe % send_ring->signal_th == 0)
-		send_info->read.send_flags |= IB_SEND_SIGNALED;
+		send_info->read.send_flags = IB_SEND_SIGNALED;
 	else
-		send_info->read.send_flags &= ~IB_SEND_SIGNALED;
+		send_info->read.send_flags = 0;
 }
 
 static void dr_fill_data_segs(struct mlx5dr_domain *dmn,
@@ -1345,7 +1257,6 @@ int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn)
 	dmn->send_ring->cq->qp = dmn->send_ring->qp;
 
 	dmn->info.max_send_wr = QUEUE_SIZE;
-	init_attr.max_send_sge = 1;
 	dmn->info.max_inline_size = min(dmn->send_ring->qp->max_inline_data,
 					DR_STE_SIZE);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 5a31fb47ffa5..21753f327868 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -277,7 +277,7 @@ int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev,
 		req_list_size = max_list_size;
 	}
 
-	out_sz = MLX5_ST_SZ_BYTES(query_nic_vport_context_in) +
+	out_sz = MLX5_ST_SZ_BYTES(query_nic_vport_context_out) +
 			req_list_size * MLX5_ST_SZ_BYTES(mac_address_layout);
 
 	out = kvzalloc(out_sz, GFP_KERNEL);
diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
index 954ba0826c61..3d09fa54598f 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
@@ -130,9 +130,15 @@ static int mlxbf_gige_open(struct net_device *netdev)
 {
 	struct mlxbf_gige *priv = netdev_priv(netdev);
 	struct phy_device *phydev = netdev->phydev;
+	u64 control;
 	u64 int_en;
 	int err;
 
+	/* Perform general init of GigE block */
+	control = readq(priv->base + MLXBF_GIGE_CONTROL);
+	control |= MLXBF_GIGE_CONTROL_PORT_EN;
+	writeq(control, priv->base + MLXBF_GIGE_CONTROL);
+
 	err = mlxbf_gige_request_irqs(priv);
 	if (err)
 		return err;
@@ -147,14 +153,14 @@ static int mlxbf_gige_open(struct net_device *netdev)
 	 */
 	priv->valid_polarity = 0;
 
-	err = mlxbf_gige_rx_init(priv);
+	phy_start(phydev);
+
+	err = mlxbf_gige_tx_init(priv);
 	if (err)
 		goto free_irqs;
-	err = mlxbf_gige_tx_init(priv);
+	err = mlxbf_gige_rx_init(priv);
 	if (err)
-		goto rx_deinit;
-
-	phy_start(phydev);
+		goto tx_deinit;
 
 	netif_napi_add(netdev, &priv->napi, mlxbf_gige_poll);
 	napi_enable(&priv->napi);
@@ -176,8 +182,8 @@ static int mlxbf_gige_open(struct net_device *netdev)
 
 	return 0;
 
-rx_deinit:
-	mlxbf_gige_rx_deinit(priv);
+tx_deinit:
+	mlxbf_gige_tx_deinit(priv);
 
 free_irqs:
 	mlxbf_gige_free_irqs(priv);
@@ -365,7 +371,6 @@ static int mlxbf_gige_probe(struct platform_device *pdev)
 	void __iomem *plu_base;
 	void __iomem *base;
 	int addr, phy_irq;
-	u64 control;
 	int err;
 
 	base = devm_platform_ioremap_resource(pdev, MLXBF_GIGE_RES_MAC);
@@ -380,11 +385,6 @@ static int mlxbf_gige_probe(struct platform_device *pdev)
 	if (IS_ERR(plu_base))
 		return PTR_ERR(plu_base);
 
-	/* Perform general init of GigE block */
-	control = readq(base + MLXBF_GIGE_CONTROL);
-	control |= MLXBF_GIGE_CONTROL_PORT_EN;
-	writeq(control, base + MLXBF_GIGE_CONTROL);
-
 	netdev = devm_alloc_etherdev(&pdev->dev, sizeof(*priv));
 	if (!netdev)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c
index 0d5a41a2ae01..699984358493 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c
@@ -142,6 +142,9 @@ int mlxbf_gige_rx_init(struct mlxbf_gige *priv)
 	writeq(MLXBF_GIGE_RX_MAC_FILTER_COUNT_PASS_EN,
 	       priv->base + MLXBF_GIGE_RX_MAC_FILTER_COUNT_PASS);
 
+	writeq(ilog2(priv->rx_q_entries),
+	       priv->base + MLXBF_GIGE_RX_WQE_SIZE_LOG2);
+
 	/* Clear MLXBF_GIGE_INT_MASK 'receive pkt' bit to
 	 * indicate readiness to receive interrupts
 	 */
@@ -154,9 +157,6 @@ int mlxbf_gige_rx_init(struct mlxbf_gige *priv)
 	data |= MLXBF_GIGE_RX_DMA_EN;
 	writeq(data, priv->base + MLXBF_GIGE_RX_DMA);
 
-	writeq(ilog2(priv->rx_q_entries),
-	       priv->base + MLXBF_GIGE_RX_WQE_SIZE_LOG2);
-
 	return 0;
 
 free_wqe_and_skb:
@@ -267,6 +267,13 @@ static bool mlxbf_gige_rx_packet(struct mlxbf_gige *priv, int *rx_pkts)
 		priv->stats.rx_truncate_errors++;
 	}
 
+	/* Read receive consumer index before replenish so that this routine
+	 * returns accurate return value even if packet is received into
+	 * just-replenished buffer prior to exiting this routine.
+	 */
+	rx_ci = readq(priv->base + MLXBF_GIGE_RX_CQE_PACKET_CI);
+	rx_ci_rem = rx_ci % priv->rx_q_entries;
+
 	/* Let hardware know we've replenished one buffer */
 	rx_pi++;
 
@@ -279,8 +286,6 @@ static bool mlxbf_gige_rx_packet(struct mlxbf_gige *priv, int *rx_pkts)
 	rx_pi_rem = rx_pi % priv->rx_q_entries;
 	if (rx_pi_rem == 0)
 		priv->valid_polarity ^= 1;
-	rx_ci = readq(priv->base + MLXBF_GIGE_RX_CQE_PACKET_CI);
-	rx_ci_rem = rx_ci % priv->rx_q_entries;
 
 	if (skb)
 		netif_receive_skb(skb);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/cmd.h b/drivers/net/ethernet/mellanox/mlxsw/cmd.h
index e827c78be114..e3271c845ee6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/cmd.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/cmd.h
@@ -282,6 +282,12 @@ MLXSW_ITEM32(cmd_mbox, query_fw, fw_day, 0x14, 0, 8);
  */
 MLXSW_ITEM32(cmd_mbox, query_fw, lag_mode_support, 0x18, 1, 1);
 
+/* cmd_mbox_query_fw_cff_support
+ * 0: CONFIG_PROFILE.flood_mode = 5 (CFF) is not supported by FW
+ * 1: CONFIG_PROFILE.flood_mode = 5 (CFF) is supported by FW
+ */
+MLXSW_ITEM32(cmd_mbox, query_fw, cff_support, 0x18, 2, 1);
+
 /* cmd_mbox_query_fw_clr_int_base_offset
  * Clear Interrupt register's offset from clr_int_bar register
  * in PCI address space.
@@ -779,6 +785,11 @@ enum mlxsw_cmd_mbox_config_profile_flood_mode {
 	 * used.
 	 */
 	MLXSW_CMD_MBOX_CONFIG_PROFILE_FLOOD_MODE_CONTROLLED = 4,
+	/* CFF - Compressed FID Flood (CFF) mode.
+	 * Reserved when legacy bridge model is used.
+	 * Supported only by Spectrum-2+.
+	 */
+	MLXSW_CMD_MBOX_CONFIG_PROFILE_FLOOD_MODE_CFF = 5,
 };
 
 /* cmd_mbox_config_profile_flood_mode
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index f23421f038f3..e4d7739bd7c8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -211,6 +211,13 @@ mlxsw_core_lag_mode(struct mlxsw_core *mlxsw_core)
 }
 EXPORT_SYMBOL(mlxsw_core_lag_mode);
 
+enum mlxsw_cmd_mbox_config_profile_flood_mode
+mlxsw_core_flood_mode(struct mlxsw_core *mlxsw_core)
+{
+	return mlxsw_core->bus->flood_mode(mlxsw_core->bus_priv);
+}
+EXPORT_SYMBOL(mlxsw_core_flood_mode);
+
 void *mlxsw_core_driver_priv(struct mlxsw_core *mlxsw_core)
 {
 	return mlxsw_core->driver_priv;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index 764d14bd5bc0..6d11225594dd 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -38,6 +38,8 @@ unsigned int mlxsw_core_max_ports(const struct mlxsw_core *mlxsw_core);
 int mlxsw_core_max_lag(struct mlxsw_core *mlxsw_core, u16 *p_max_lag);
 enum mlxsw_cmd_mbox_config_profile_lag_mode
 mlxsw_core_lag_mode(struct mlxsw_core *mlxsw_core);
+enum mlxsw_cmd_mbox_config_profile_flood_mode
+mlxsw_core_flood_mode(struct mlxsw_core *mlxsw_core);
 
 void *mlxsw_core_driver_priv(struct mlxsw_core *mlxsw_core);
 
@@ -322,7 +324,12 @@ struct mlxsw_config_profile {
 	u16	max_regions;
 	u8	max_flood_tables;
 	u8	max_vid_flood_tables;
+
+	/* Flood mode to use if used_flood_mode. If flood_mode_prefer_cff,
+	 * the backup flood mode (if any) when CFF unsupported.
+	 */
 	u8	flood_mode;
+
 	u8	max_fid_offset_flood_tables;
 	u16	fid_offset_flood_table_size;
 	u8	max_fid_flood_tables;
@@ -338,6 +345,7 @@ struct mlxsw_config_profile {
 	u8	kvd_hash_double_parts;
 	u8	cqe_time_stamp_type;
 	bool	lag_mode_prefer_sw;
+	bool	flood_mode_prefer_cff;
 	struct mlxsw_swid_config swid_config[MLXSW_CONFIG_PROFILE_SWID_COUNT];
 };
 
@@ -489,6 +497,7 @@ struct mlxsw_bus {
 	u32 (*read_utc_sec)(void *bus_priv);
 	u32 (*read_utc_nsec)(void *bus_priv);
 	enum mlxsw_cmd_mbox_config_profile_lag_mode (*lag_mode)(void *bus_priv);
+	enum mlxsw_cmd_mbox_config_profile_flood_mode (*flood_mode)(void *priv);
 	u8 features;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index e4b25e187467..af99bf17eb36 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -106,7 +106,9 @@ struct mlxsw_pci {
 	u64 utc_sec_offset;
 	u64 utc_nsec_offset;
 	bool lag_mode_support;
+	bool cff_support;
 	enum mlxsw_cmd_mbox_config_profile_lag_mode lag_mode;
+	enum mlxsw_cmd_mbox_config_profile_flood_mode flood_mode;
 	struct mlxsw_pci_queue_type_group queues[MLXSW_PCI_QUEUE_TYPE_COUNT];
 	u32 doorbell_offset;
 	struct mlxsw_core *core;
@@ -130,6 +132,7 @@ struct mlxsw_pci {
 	const struct pci_device_id *id;
 	enum mlxsw_pci_cqe_v max_cqe_ver; /* Maximal supported CQE version */
 	u8 num_sdq_cqs; /* Number of CQs used for SDQs */
+	bool skip_reset;
 };
 
 static void mlxsw_pci_queue_tasklet_schedule(struct mlxsw_pci_queue *q)
@@ -1245,11 +1248,22 @@ static int mlxsw_pci_config_profile(struct mlxsw_pci *mlxsw_pci, char *mbox,
 		mlxsw_cmd_mbox_config_profile_fid_flood_table_size_set(
 			mbox, profile->fid_flood_table_size);
 	}
-	if (profile->used_flood_mode) {
+	if (profile->flood_mode_prefer_cff && mlxsw_pci->cff_support) {
+		enum mlxsw_cmd_mbox_config_profile_flood_mode flood_mode =
+			MLXSW_CMD_MBOX_CONFIG_PROFILE_FLOOD_MODE_CFF;
+
+		mlxsw_cmd_mbox_config_profile_set_flood_mode_set(mbox, 1);
+		mlxsw_cmd_mbox_config_profile_flood_mode_set(mbox, flood_mode);
+		mlxsw_pci->flood_mode = flood_mode;
+	} else if (profile->used_flood_mode) {
 		mlxsw_cmd_mbox_config_profile_set_flood_mode_set(
 			mbox, 1);
 		mlxsw_cmd_mbox_config_profile_flood_mode_set(
 			mbox, profile->flood_mode);
+		mlxsw_pci->flood_mode = profile->flood_mode;
+	} else {
+		WARN_ON(1);
+		return -EINVAL;
 	}
 	if (profile->used_max_ib_mc) {
 		mlxsw_cmd_mbox_config_profile_set_max_ib_mc_set(
@@ -1476,11 +1490,47 @@ static int mlxsw_pci_sys_ready_wait(struct mlxsw_pci *mlxsw_pci,
 	return -EBUSY;
 }
 
-static int mlxsw_pci_sw_reset(struct mlxsw_pci *mlxsw_pci,
-			      const struct pci_device_id *id)
+static int mlxsw_pci_reset_at_pci_disable(struct mlxsw_pci *mlxsw_pci)
 {
 	struct pci_dev *pdev = mlxsw_pci->pdev;
 	char mrsr_pl[MLXSW_REG_MRSR_LEN];
+	int err;
+
+	mlxsw_reg_mrsr_pack(mrsr_pl,
+			    MLXSW_REG_MRSR_COMMAND_RESET_AT_PCI_DISABLE);
+	err = mlxsw_reg_write(mlxsw_pci->core, MLXSW_REG(mrsr), mrsr_pl);
+	if (err)
+		return err;
+
+	device_lock_assert(&pdev->dev);
+
+	pci_cfg_access_lock(pdev);
+	pci_save_state(pdev);
+
+	err = __pci_reset_function_locked(pdev);
+	if (err)
+		pci_err(pdev, "PCI function reset failed with %d\n", err);
+
+	pci_restore_state(pdev);
+	pci_cfg_access_unlock(pdev);
+
+	return err;
+}
+
+static int mlxsw_pci_reset_sw(struct mlxsw_pci *mlxsw_pci)
+{
+	char mrsr_pl[MLXSW_REG_MRSR_LEN];
+
+	mlxsw_reg_mrsr_pack(mrsr_pl, MLXSW_REG_MRSR_COMMAND_SOFTWARE_RESET);
+	return mlxsw_reg_write(mlxsw_pci->core, MLXSW_REG(mrsr), mrsr_pl);
+}
+
+static int
+mlxsw_pci_reset(struct mlxsw_pci *mlxsw_pci, const struct pci_device_id *id)
+{
+	struct pci_dev *pdev = mlxsw_pci->pdev;
+	char mcam_pl[MLXSW_REG_MCAM_LEN];
+	bool pci_reset_supported;
 	u32 sys_status;
 	int err;
 
@@ -1491,8 +1541,26 @@ static int mlxsw_pci_sw_reset(struct mlxsw_pci *mlxsw_pci,
 		return err;
 	}
 
-	mlxsw_reg_mrsr_pack(mrsr_pl);
-	err = mlxsw_reg_write(mlxsw_pci->core, MLXSW_REG(mrsr), mrsr_pl);
+	/* PCI core already issued a PCI reset, do not issue another reset. */
+	if (mlxsw_pci->skip_reset)
+		return 0;
+
+	mlxsw_reg_mcam_pack(mcam_pl,
+			    MLXSW_REG_MCAM_FEATURE_GROUP_ENHANCED_FEATURES);
+	err = mlxsw_reg_query(mlxsw_pci->core, MLXSW_REG(mcam), mcam_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_mcam_unpack(mcam_pl, MLXSW_REG_MCAM_PCI_RESET,
+			      &pci_reset_supported);
+
+	if (pci_reset_supported) {
+		pci_dbg(pdev, "Starting PCI reset flow\n");
+		err = mlxsw_pci_reset_at_pci_disable(mlxsw_pci);
+	} else {
+		pci_dbg(pdev, "Starting software reset flow\n");
+		err = mlxsw_pci_reset_sw(mlxsw_pci);
+	}
 	if (err)
 		return err;
 
@@ -1537,9 +1605,9 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core,
 	if (!mbox)
 		return -ENOMEM;
 
-	err = mlxsw_pci_sw_reset(mlxsw_pci, mlxsw_pci->id);
+	err = mlxsw_pci_reset(mlxsw_pci, mlxsw_pci->id);
 	if (err)
-		goto err_sw_reset;
+		goto err_reset;
 
 	err = mlxsw_pci_alloc_irq_vectors(mlxsw_pci);
 	if (err < 0) {
@@ -1601,6 +1669,9 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core,
 
 	mlxsw_pci->lag_mode_support =
 		mlxsw_cmd_mbox_query_fw_lag_mode_support_get(mbox);
+	mlxsw_pci->cff_support =
+		mlxsw_cmd_mbox_query_fw_cff_support_get(mbox);
+
 	num_pages = mlxsw_cmd_mbox_query_fw_fw_pages_get(mbox);
 	err = mlxsw_pci_fw_area_init(mlxsw_pci, mbox, num_pages);
 	if (err)
@@ -1672,7 +1743,7 @@ err_iface_rev:
 err_query_fw:
 	mlxsw_pci_free_irq_vectors(mlxsw_pci);
 err_alloc_irq:
-err_sw_reset:
+err_reset:
 mbox_put:
 	mlxsw_cmd_mbox_free(mbox);
 	return err;
@@ -1917,6 +1988,14 @@ mlxsw_pci_lag_mode(void *bus_priv)
 	return mlxsw_pci->lag_mode;
 }
 
+static enum mlxsw_cmd_mbox_config_profile_flood_mode
+mlxsw_pci_flood_mode(void *bus_priv)
+{
+	struct mlxsw_pci *mlxsw_pci = bus_priv;
+
+	return mlxsw_pci->flood_mode;
+}
+
 static const struct mlxsw_bus mlxsw_pci_bus = {
 	.kind			= "pci",
 	.init			= mlxsw_pci_init,
@@ -1929,6 +2008,7 @@ static const struct mlxsw_bus mlxsw_pci_bus = {
 	.read_utc_sec		= mlxsw_pci_read_utc_sec,
 	.read_utc_nsec		= mlxsw_pci_read_utc_nsec,
 	.lag_mode		= mlxsw_pci_lag_mode,
+	.flood_mode		= mlxsw_pci_flood_mode,
 	.features		= MLXSW_BUS_F_TXRX | MLXSW_BUS_F_RESET,
 };
 
@@ -2059,11 +2139,34 @@ static void mlxsw_pci_remove(struct pci_dev *pdev)
 	kfree(mlxsw_pci);
 }
 
+static void mlxsw_pci_reset_prepare(struct pci_dev *pdev)
+{
+	struct mlxsw_pci *mlxsw_pci = pci_get_drvdata(pdev);
+
+	mlxsw_core_bus_device_unregister(mlxsw_pci->core, false);
+}
+
+static void mlxsw_pci_reset_done(struct pci_dev *pdev)
+{
+	struct mlxsw_pci *mlxsw_pci = pci_get_drvdata(pdev);
+
+	mlxsw_pci->skip_reset = true;
+	mlxsw_core_bus_device_register(&mlxsw_pci->bus_info, &mlxsw_pci_bus,
+				       mlxsw_pci, false, NULL, NULL);
+	mlxsw_pci->skip_reset = false;
+}
+
+static const struct pci_error_handlers mlxsw_pci_err_handler = {
+	.reset_prepare = mlxsw_pci_reset_prepare,
+	.reset_done = mlxsw_pci_reset_done,
+};
+
 int mlxsw_pci_driver_register(struct pci_driver *pci_driver)
 {
 	pci_driver->probe = mlxsw_pci_probe;
 	pci_driver->remove = mlxsw_pci_remove;
 	pci_driver->shutdown = mlxsw_pci_remove;
+	pci_driver->err_handler = &mlxsw_pci_err_handler;
 	return pci_register_driver(pci_driver);
 }
 EXPORT_SYMBOL(mlxsw_pci_driver_register);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 25b294fdeb3d..8892654c685f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -1024,6 +1024,8 @@ static inline void mlxsw_reg_spaft_pack(char *payload, u16 local_port,
  * ------------------------------------------
  * The following register controls the association of flooding tables and MIDs
  * to packet types used for flooding.
+ *
+ * Reserved when CONFIG_PROFILE.flood_mode = CFF.
  */
 #define MLXSW_REG_SFGC_ID 0x2011
 #define MLXSW_REG_SFGC_LEN 0x14
@@ -1862,6 +1864,7 @@ MLXSW_ITEM32(reg, sfmr, fid, 0x00, 0, 16);
  * Access: RW
  *
  * Note: Reserved when legacy bridge model is used.
+ * Reserved when CONFIG_PROFILE.flood_mode = CFF.
  */
 MLXSW_ITEM32(reg, sfmr, flood_rsp, 0x08, 31, 1);
 
@@ -1872,6 +1875,7 @@ MLXSW_ITEM32(reg, sfmr, flood_rsp, 0x08, 31, 1);
  * Access: RW
  *
  * Note: Reserved when legacy bridge model is used and when flood_rsp=1.
+ * Reserved when CONFIG_PROFILE.flood_mode = CFF
  */
 MLXSW_ITEM32(reg, sfmr, flood_bridge_type, 0x08, 28, 1);
 
@@ -1880,6 +1884,8 @@ MLXSW_ITEM32(reg, sfmr, flood_bridge_type, 0x08, 28, 1);
  * Used to point into the flooding table selected by SFGC register if
  * the table is of type FID-Offset. Otherwise, this field is reserved.
  * Access: RW
+ *
+ * Note: Reserved when CONFIG_PROFILE.flood_mode = CFF
  */
 MLXSW_ITEM32(reg, sfmr, fid_offset, 0x08, 0, 16);
 
@@ -1938,6 +1944,35 @@ MLXSW_ITEM32(reg, sfmr, irif_v, 0x14, 24, 1);
  */
 MLXSW_ITEM32(reg, sfmr, irif, 0x14, 0, 16);
 
+/* reg_sfmr_cff_mid_base
+ * Pointer to PGT table.
+ * Range: 0..(cap_max_pgt-1)
+ * Access: RW
+ *
+ * Note: Reserved when SwitchX/-2 and Spectrum-1.
+ * Supported when CONFIG_PROFILE.flood_mode = CFF.
+ */
+MLXSW_ITEM32(reg, sfmr, cff_mid_base, 0x20, 0, 16);
+
+/* reg_sfmr_nve_flood_prf_id
+ * FID flooding profile_id for NVE Encap
+ * Range 0..(max_cap_nve_flood_prf-1)
+ * Access: RW
+ *
+ * Note: Reserved when SwitchX/-2 and Spectrum-1
+ */
+MLXSW_ITEM32(reg, sfmr, nve_flood_prf_id, 0x24, 8, 2);
+
+/* reg_sfmr_cff_prf_id
+ * Compressed Fid Flooding profile_id
+ * Range 0..(max_cap_nve_flood_prf-1)
+ * Access: RW
+ *
+ * Note: Reserved when SwitchX/-2 and Spectrum-1
+ * Supported only when CONFIG_PROFLE.flood_mode = CFF.
+ */
+MLXSW_ITEM32(reg, sfmr, cff_prf_id, 0x24, 0, 2);
+
 /* reg_sfmr_smpe_valid
  * SMPE is valid.
  * Access: RW
@@ -1959,18 +1994,11 @@ MLXSW_ITEM32(reg, sfmr, smpe, 0x28, 0, 16);
 
 static inline void mlxsw_reg_sfmr_pack(char *payload,
 				       enum mlxsw_reg_sfmr_op op, u16 fid,
-				       u16 fid_offset, bool flood_rsp,
-				       enum mlxsw_reg_bridge_type bridge_type,
 				       bool smpe_valid, u16 smpe)
 {
 	MLXSW_REG_ZERO(sfmr, payload);
 	mlxsw_reg_sfmr_op_set(payload, op);
 	mlxsw_reg_sfmr_fid_set(payload, fid);
-	mlxsw_reg_sfmr_fid_offset_set(payload, fid_offset);
-	mlxsw_reg_sfmr_vtfp_set(payload, false);
-	mlxsw_reg_sfmr_vv_set(payload, false);
-	mlxsw_reg_sfmr_flood_rsp_set(payload, flood_rsp);
-	mlxsw_reg_sfmr_flood_bridge_type_set(payload, bridge_type);
 	mlxsw_reg_sfmr_smpe_valid_set(payload, smpe_valid);
 	mlxsw_reg_sfmr_smpe_set(payload, smpe);
 }
@@ -2168,6 +2196,50 @@ static inline void mlxsw_reg_spvc_pack(char *payload, u16 local_port, bool et1,
 	mlxsw_reg_spvc_et0_set(payload, et0);
 }
 
+/* SFFP - Switch FID Flooding Profiles Register
+ * --------------------------------------------
+ * The SFFP register populates the fid flooding profile tables used for the NVE
+ * flooding and Compressed-FID Flooding (CFF).
+ *
+ * Reserved on Spectrum-1.
+ */
+#define MLXSW_REG_SFFP_ID 0x2029
+#define MLXSW_REG_SFFP_LEN 0x0C
+
+MLXSW_REG_DEFINE(sffp, MLXSW_REG_SFFP_ID, MLXSW_REG_SFFP_LEN);
+
+/* reg_sffp_profile_id
+ * Profile ID a.k.a. SFMR.nve_flood_prf_id or SFMR.cff_prf_id
+ * Range 0..max_cap_nve_flood_prf-1
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, sffp, profile_id, 0x00, 16, 2);
+
+/* reg_sffp_type
+ * The traffic type to reach the flooding table.
+ * Same as SFGC.type
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, sffp, type, 0x00, 0, 4);
+
+/* reg_sffp_flood_offset
+ * Flood offset. Offset to add to SFMR.cff_mid_base to get the final PGT address
+ * for FID flood; or offset to add to SFMR.nve_tunnel_flood_ptr to get KVD
+ * pointer for NVE underlay.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, sffp, flood_offset, 0x04, 0, 3);
+
+static inline void mlxsw_reg_sffp_pack(char *payload, u8 profile_id,
+				       enum mlxsw_reg_sfgc_type type,
+				       u8 flood_offset)
+{
+	MLXSW_REG_ZERO(sffp, payload);
+	mlxsw_reg_sffp_profile_id_set(payload, profile_id);
+	mlxsw_reg_sffp_type_set(payload, type);
+	mlxsw_reg_sffp_flood_offset_set(payload, flood_offset);
+}
+
 /* SPEVET - Switch Port Egress VLAN EtherType
  * ------------------------------------------
  * The switch port egress VLAN EtherType configures which EtherType to push at
@@ -10122,6 +10194,15 @@ mlxsw_reg_mgir_unpack(char *payload, u32 *hw_rev, char *fw_info_psid,
 
 MLXSW_REG_DEFINE(mrsr, MLXSW_REG_MRSR_ID, MLXSW_REG_MRSR_LEN);
 
+enum mlxsw_reg_mrsr_command {
+	/* Switch soft reset, does not reset PCI firmware. */
+	MLXSW_REG_MRSR_COMMAND_SOFTWARE_RESET = 1,
+	/* Reset will be done when PCI link will be disabled.
+	 * This command will reset PCI firmware also.
+	 */
+	MLXSW_REG_MRSR_COMMAND_RESET_AT_PCI_DISABLE = 6,
+};
+
 /* reg_mrsr_command
  * Reset/shutdown command
  * 0 - do nothing
@@ -10130,10 +10211,11 @@ MLXSW_REG_DEFINE(mrsr, MLXSW_REG_MRSR_ID, MLXSW_REG_MRSR_LEN);
  */
 MLXSW_ITEM32(reg, mrsr, command, 0x00, 0, 4);
 
-static inline void mlxsw_reg_mrsr_pack(char *payload)
+static inline void mlxsw_reg_mrsr_pack(char *payload,
+				       enum mlxsw_reg_mrsr_command command)
 {
 	MLXSW_REG_ZERO(mrsr, payload);
-	mlxsw_reg_mrsr_command_set(payload, 1);
+	mlxsw_reg_mrsr_command_set(payload, command);
 }
 
 /* MLCR - Management LED Control Register
@@ -10584,6 +10666,8 @@ MLXSW_ITEM32(reg, mcam, feature_group, 0x00, 16, 8);
 enum mlxsw_reg_mcam_mng_feature_cap_mask_bits {
 	/* If set, MCIA supports 128 bytes payloads. Otherwise, 48 bytes. */
 	MLXSW_REG_MCAM_MCIA_128B = 34,
+	/* If set, MRSR.command=6 is supported. */
+	MLXSW_REG_MCAM_PCI_RESET = 48,
 };
 
 #define MLXSW_REG_BYTES_PER_DWORD 0x4
@@ -12934,6 +13018,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(spvmlr),
 	MLXSW_REG(spfsr),
 	MLXSW_REG(spvc),
+	MLXSW_REG(sffp),
 	MLXSW_REG(spevet),
 	MLXSW_REG(smpe),
 	MLXSW_REG(smid2),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h
index 89dd2777ec4d..9d7977ebe186 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/resources.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h
@@ -27,6 +27,7 @@ enum mlxsw_res_id {
 	MLXSW_RES_ID_FID,
 	MLXSW_RES_ID_MAX_LAG,
 	MLXSW_RES_ID_MAX_LAG_MEMBERS,
+	MLXSW_RES_ID_MAX_NVE_FLOOD_PRF,
 	MLXSW_RES_ID_GUARANTEED_SHARED_BUFFER,
 	MLXSW_RES_ID_CELL_SIZE,
 	MLXSW_RES_ID_MAX_HEADROOM_SIZE,
@@ -88,6 +89,7 @@ static u16 mlxsw_res_ids[] = {
 	[MLXSW_RES_ID_FID] = 0x2512,
 	[MLXSW_RES_ID_MAX_LAG] = 0x2520,
 	[MLXSW_RES_ID_MAX_LAG_MEMBERS] = 0x2521,
+	[MLXSW_RES_ID_MAX_NVE_FLOOD_PRF] = 0x2522,
 	[MLXSW_RES_ID_GUARANTEED_SHARED_BUFFER] = 0x2805,	/* Bytes */
 	[MLXSW_RES_ID_CELL_SIZE] = 0x2803,	/* Bytes */
 	[MLXSW_RES_ID_MAX_HEADROOM_SIZE] = 0x2811,	/* Bytes */
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index cec72d99d9c9..5d3413636a62 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3190,10 +3190,10 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 		goto err_lag_init;
 	}
 
-	err = mlxsw_sp_fids_init(mlxsw_sp);
+	err = mlxsw_sp->fid_core_ops->init(mlxsw_sp);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize FIDs\n");
-		goto err_fids_init;
+		goto err_fid_core_init;
 	}
 
 	err = mlxsw_sp_policers_init(mlxsw_sp);
@@ -3379,8 +3379,8 @@ err_devlink_traps_init:
 err_traps_init:
 	mlxsw_sp_policers_fini(mlxsw_sp);
 err_policers_init:
-	mlxsw_sp_fids_fini(mlxsw_sp);
-err_fids_init:
+	mlxsw_sp->fid_core_ops->fini(mlxsw_sp);
+err_fid_core_init:
 	mlxsw_sp_lag_fini(mlxsw_sp);
 err_lag_init:
 	mlxsw_sp_pgt_fini(mlxsw_sp);
@@ -3416,7 +3416,7 @@ static int mlxsw_sp1_init(struct mlxsw_core *mlxsw_core,
 	mlxsw_sp->router_ops = &mlxsw_sp1_router_ops;
 	mlxsw_sp->listeners = mlxsw_sp1_listener;
 	mlxsw_sp->listeners_count = ARRAY_SIZE(mlxsw_sp1_listener);
-	mlxsw_sp->fid_family_arr = mlxsw_sp1_fid_family_arr;
+	mlxsw_sp->fid_core_ops = &mlxsw_sp1_fid_core_ops;
 	mlxsw_sp->lowest_shaper_bs = MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP1;
 	mlxsw_sp->pgt_smpe_index_valid = true;
 
@@ -3450,7 +3450,7 @@ static int mlxsw_sp2_init(struct mlxsw_core *mlxsw_core,
 	mlxsw_sp->router_ops = &mlxsw_sp2_router_ops;
 	mlxsw_sp->listeners = mlxsw_sp2_listener;
 	mlxsw_sp->listeners_count = ARRAY_SIZE(mlxsw_sp2_listener);
-	mlxsw_sp->fid_family_arr = mlxsw_sp2_fid_family_arr;
+	mlxsw_sp->fid_core_ops = &mlxsw_sp2_fid_core_ops;
 	mlxsw_sp->lowest_shaper_bs = MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP2;
 	mlxsw_sp->pgt_smpe_index_valid = false;
 
@@ -3484,7 +3484,7 @@ static int mlxsw_sp3_init(struct mlxsw_core *mlxsw_core,
 	mlxsw_sp->router_ops = &mlxsw_sp2_router_ops;
 	mlxsw_sp->listeners = mlxsw_sp2_listener;
 	mlxsw_sp->listeners_count = ARRAY_SIZE(mlxsw_sp2_listener);
-	mlxsw_sp->fid_family_arr = mlxsw_sp2_fid_family_arr;
+	mlxsw_sp->fid_core_ops = &mlxsw_sp2_fid_core_ops;
 	mlxsw_sp->lowest_shaper_bs = MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP3;
 	mlxsw_sp->pgt_smpe_index_valid = false;
 
@@ -3518,7 +3518,7 @@ static int mlxsw_sp4_init(struct mlxsw_core *mlxsw_core,
 	mlxsw_sp->router_ops = &mlxsw_sp2_router_ops;
 	mlxsw_sp->listeners = mlxsw_sp2_listener;
 	mlxsw_sp->listeners_count = ARRAY_SIZE(mlxsw_sp2_listener);
-	mlxsw_sp->fid_family_arr = mlxsw_sp2_fid_family_arr;
+	mlxsw_sp->fid_core_ops = &mlxsw_sp2_fid_core_ops;
 	mlxsw_sp->lowest_shaper_bs = MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP4;
 	mlxsw_sp->pgt_smpe_index_valid = false;
 
@@ -3552,7 +3552,7 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
 	mlxsw_sp_devlink_traps_fini(mlxsw_sp);
 	mlxsw_sp_traps_fini(mlxsw_sp);
 	mlxsw_sp_policers_fini(mlxsw_sp);
-	mlxsw_sp_fids_fini(mlxsw_sp);
+	mlxsw_sp->fid_core_ops->fini(mlxsw_sp);
 	mlxsw_sp_lag_fini(mlxsw_sp);
 	mlxsw_sp_pgt_fini(mlxsw_sp);
 	mlxsw_sp_kvdl_fini(mlxsw_sp);
@@ -3598,6 +3598,7 @@ static const struct mlxsw_config_profile mlxsw_sp2_config_profile = {
 	.used_cqe_time_stamp_type	= 1,
 	.cqe_time_stamp_type		= MLXSW_CMD_MBOX_CONFIG_PROFILE_CQE_TIME_STAMP_TYPE_UTC,
 	.lag_mode_prefer_sw		= true,
+	.flood_mode_prefer_cff		= true,
 };
 
 /* Reduce number of LAGs from full capacity (256) to the maximum supported LAGs
@@ -3626,6 +3627,7 @@ static const struct mlxsw_config_profile mlxsw_sp4_config_profile = {
 	.used_cqe_time_stamp_type	= 1,
 	.cqe_time_stamp_type		= MLXSW_CMD_MBOX_CONFIG_PROFILE_CQE_TIME_STAMP_TYPE_UTC,
 	.lag_mode_prefer_sw		= true,
+	.flood_mode_prefer_cff		= true,
 };
 
 static void
@@ -4515,6 +4517,10 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_port->lagged = 1;
 	lag->ref_count++;
 
+	err = mlxsw_sp_fid_port_join_lag(mlxsw_sp_port);
+	if (err)
+		goto err_fid_port_join_lag;
+
 	/* Port is no longer usable as a router interface */
 	if (mlxsw_sp_port->default_vlan->fid)
 		mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port->default_vlan);
@@ -4534,6 +4540,8 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
 err_replay:
 	mlxsw_sp_router_port_leave_lag(mlxsw_sp_port, lag_dev);
 err_router_join:
+	mlxsw_sp_fid_port_leave_lag(mlxsw_sp_port);
+err_fid_port_join_lag:
 	lag->ref_count--;
 	mlxsw_sp_port->lagged = 0;
 	mlxsw_core_lag_mapping_clear(mlxsw_sp->core, lag_id,
@@ -4569,6 +4577,8 @@ static void mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 	 */
 	mlxsw_sp_port_lag_uppers_cleanup(mlxsw_sp_port, lag_dev);
 
+	mlxsw_sp_fid_port_leave_lag(mlxsw_sp_port);
+
 	if (lag->ref_count == 1)
 		mlxsw_sp_lag_destroy(mlxsw_sp, lag_id);
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index c70333b460ea..a0c9775fa955 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -205,7 +205,7 @@ struct mlxsw_sp {
 	const struct mlxsw_sp_mall_ops *mall_ops;
 	const struct mlxsw_sp_router_ops *router_ops;
 	const struct mlxsw_listener *listeners;
-	const struct mlxsw_sp_fid_family **fid_family_arr;
+	const struct mlxsw_sp_fid_core_ops *fid_core_ops;
 	size_t listeners_count;
 	u32 lowest_shaper_bs;
 	struct rhashtable ipv6_addr_ht;
@@ -252,6 +252,11 @@ struct mlxsw_sp_ptp_ops {
 			       const struct mlxsw_tx_info *tx_info);
 };
 
+struct mlxsw_sp_fid_core_ops {
+	int (*init)(struct mlxsw_sp *mlxsw_sp);
+	void (*fini)(struct mlxsw_sp *mlxsw_sp);
+};
+
 static inline struct mlxsw_sp_upper *
 mlxsw_sp_lag_get(struct mlxsw_sp *mlxsw_sp, u16 lag_id)
 {
@@ -508,6 +513,10 @@ enum mlxsw_sp_flood_type {
 	MLXSW_SP_FLOOD_TYPE_UC,
 	MLXSW_SP_FLOOD_TYPE_BC,
 	MLXSW_SP_FLOOD_TYPE_MC,
+	/* For RSP FIDs in CFF mode. */
+	MLXSW_SP_FLOOD_TYPE_NOT_UC,
+	/* For NVE traffic. */
+	MLXSW_SP_FLOOD_TYPE_ANY,
 };
 
 int mlxsw_sp_port_get_stats_raw(struct net_device *dev, int grp,
@@ -753,6 +762,8 @@ union mlxsw_sp_l3addr {
 };
 
 u16 mlxsw_sp_rif_index(const struct mlxsw_sp_rif *rif);
+int mlxsw_sp_rif_subport_port(const struct mlxsw_sp_rif *rif,
+			      u16 *port, bool *is_lag);
 int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp,
 			 struct netlink_ext_ack *extack);
 void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp);
@@ -1319,11 +1330,11 @@ struct mlxsw_sp_fid *mlxsw_sp_fid_dummy_get(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_fid_put(struct mlxsw_sp_fid *fid);
 int mlxsw_sp_port_fids_init(struct mlxsw_sp_port *mlxsw_sp_port);
 void mlxsw_sp_port_fids_fini(struct mlxsw_sp_port *mlxsw_sp_port);
-int mlxsw_sp_fids_init(struct mlxsw_sp *mlxsw_sp);
-void mlxsw_sp_fids_fini(struct mlxsw_sp *mlxsw_sp);
+int mlxsw_sp_fid_port_join_lag(const struct mlxsw_sp_port *mlxsw_sp_port);
+void mlxsw_sp_fid_port_leave_lag(const struct mlxsw_sp_port *mlxsw_sp_port);
 
-extern const struct mlxsw_sp_fid_family *mlxsw_sp1_fid_family_arr[];
-extern const struct mlxsw_sp_fid_family *mlxsw_sp2_fid_family_arr[];
+extern const struct mlxsw_sp_fid_core_ops mlxsw_sp1_fid_core_ops;
+extern const struct mlxsw_sp_fid_core_ops mlxsw_sp2_fid_core_ops;
 
 /* spectrum_mr.c */
 enum mlxsw_sp_mr_route_prio {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
index e954b8cd2ee8..65562ab208b3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
@@ -11,6 +11,7 @@
 #include <linux/refcount.h>
 
 #include "spectrum.h"
+#include "spectrum_router.h"
 #include "reg.h"
 
 struct mlxsw_sp_fid_family;
@@ -71,12 +72,12 @@ static const struct rhashtable_params mlxsw_sp_fid_vni_ht_params = {
 
 struct mlxsw_sp_flood_table {
 	enum mlxsw_sp_flood_type packet_type;
-	enum mlxsw_flood_table_type table_type;
+	enum mlxsw_flood_table_type table_type;	/* For flood_mode!=CFF. */
 	int table_index;
 };
 
 struct mlxsw_sp_fid_ops {
-	void (*setup)(struct mlxsw_sp_fid *fid, const void *arg);
+	int (*setup)(struct mlxsw_sp_fid *fid, const void *arg);
 	int (*configure)(struct mlxsw_sp_fid *fid);
 	void (*deconfigure)(struct mlxsw_sp_fid *fid);
 	int (*index_alloc)(struct mlxsw_sp_fid *fid, const void *arg,
@@ -95,6 +96,34 @@ struct mlxsw_sp_fid_ops {
 				  const struct net_device *nve_dev);
 	int (*vid_to_fid_rif_update)(const struct mlxsw_sp_fid *fid,
 				     const struct mlxsw_sp_rif *rif);
+	int (*flood_table_init)(struct mlxsw_sp_fid_family *fid_family,
+				const struct mlxsw_sp_flood_table *flood_table);
+	int (*pgt_size)(const struct mlxsw_sp_fid_family *fid_family,
+			u16 *p_pgt_size);
+	u16 (*fid_mid)(const struct mlxsw_sp_fid *fid,
+		       const struct mlxsw_sp_flood_table *flood_table);
+	void (*fid_pack)(char *sfmr_pl, const struct mlxsw_sp_fid *fid,
+			 enum mlxsw_reg_sfmr_op op);
+
+	/* These are specific to RFID families and we assume are only
+	 * implemented by RFID families, if at all.
+	 */
+	int (*fid_port_init)(const struct mlxsw_sp_fid_family *fid_family,
+			     const struct mlxsw_sp_port *mlxsw_sp_port);
+	void (*fid_port_fini)(const struct mlxsw_sp_fid_family *fid_family,
+			      const struct mlxsw_sp_port *mlxsw_sp_port);
+};
+
+enum mlxsw_sp_fid_flood_profile_id {
+	MLXSW_SP_FID_FLOOD_PROFILE_ID_BRIDGE = 1,
+	MLXSW_SP_FID_FLOOD_PROFILE_ID_RSP,
+	MLXSW_SP_FID_FLOOD_PROFILE_ID_NVE,
+};
+
+struct mlxsw_sp_fid_flood_profile {
+	const struct mlxsw_sp_flood_table *flood_tables;
+	int nr_flood_tables;
+	const enum mlxsw_sp_fid_flood_profile_id profile_id; /* For CFF mode. */
 };
 
 struct mlxsw_sp_fid_family {
@@ -104,12 +133,11 @@ struct mlxsw_sp_fid_family {
 	u16 end_index;
 	struct list_head fids_list;
 	unsigned long *fids_bitmap;
-	const struct mlxsw_sp_flood_table *flood_tables;
-	int nr_flood_tables;
+	const struct mlxsw_sp_fid_flood_profile *flood_profile;
 	enum mlxsw_sp_rif_type rif_type;
 	const struct mlxsw_sp_fid_ops *ops;
 	struct mlxsw_sp *mlxsw_sp;
-	bool flood_rsp;
+	bool flood_rsp;	/* For flood_mode!=CFF. */
 	enum mlxsw_reg_bridge_type bridge_type;
 	u16 pgt_base;
 	bool smpe_index_valid;
@@ -131,10 +159,31 @@ static const int mlxsw_sp_sfgc_mc_packet_types[MLXSW_REG_SFGC_TYPE_MAX] = {
 	[MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV4]	= 1,
 };
 
+static const int mlxsw_sp_sfgc_not_uc_packet_types[MLXSW_REG_SFGC_TYPE_MAX] = {
+	[MLXSW_REG_SFGC_TYPE_BROADCAST]				= 1,
+	[MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_NON_IP]	= 1,
+	[MLXSW_REG_SFGC_TYPE_IPV4_LINK_LOCAL]			= 1,
+	[MLXSW_REG_SFGC_TYPE_IPV6_ALL_HOST]			= 1,
+	[MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV6]	= 1,
+	[MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV4]	= 1,
+};
+
+static const int mlxsw_sp_sfgc_any_packet_types[MLXSW_REG_SFGC_TYPE_MAX] = {
+	[MLXSW_REG_SFGC_TYPE_UNKNOWN_UNICAST]			= 1,
+	[MLXSW_REG_SFGC_TYPE_BROADCAST]				= 1,
+	[MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_NON_IP]	= 1,
+	[MLXSW_REG_SFGC_TYPE_IPV4_LINK_LOCAL]			= 1,
+	[MLXSW_REG_SFGC_TYPE_IPV6_ALL_HOST]			= 1,
+	[MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV6]	= 1,
+	[MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV4]	= 1,
+};
+
 static const int *mlxsw_sp_packet_type_sfgc_types[] = {
 	[MLXSW_SP_FLOOD_TYPE_UC]	= mlxsw_sp_sfgc_uc_packet_types,
 	[MLXSW_SP_FLOOD_TYPE_BC]	= mlxsw_sp_sfgc_bc_packet_types,
 	[MLXSW_SP_FLOOD_TYPE_MC]	= mlxsw_sp_sfgc_mc_packet_types,
+	[MLXSW_SP_FLOOD_TYPE_NOT_UC]	= mlxsw_sp_sfgc_not_uc_packet_types,
+	[MLXSW_SP_FLOOD_TYPE_ANY]	= mlxsw_sp_sfgc_any_packet_types,
 };
 
 struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_index(struct mlxsw_sp *mlxsw_sp,
@@ -305,10 +354,13 @@ mlxsw_sp_fid_flood_table_lookup(const struct mlxsw_sp_fid *fid,
 	struct mlxsw_sp_fid_family *fid_family = fid->fid_family;
 	int i;
 
-	for (i = 0; i < fid_family->nr_flood_tables; i++) {
-		if (fid_family->flood_tables[i].packet_type != packet_type)
+	for (i = 0; i < fid_family->flood_profile->nr_flood_tables; i++) {
+		const struct mlxsw_sp_flood_table *flood_table;
+
+		flood_table = &fid_family->flood_profile->flood_tables[i];
+		if (flood_table->packet_type != packet_type)
 			continue;
-		return &fid_family->flood_tables[i];
+		return flood_table;
 	}
 
 	return NULL;
@@ -320,24 +372,62 @@ mlxsw_sp_fid_family_num_fids(const struct mlxsw_sp_fid_family *fid_family)
 	return fid_family->end_index - fid_family->start_index + 1;
 }
 
-static u16
-mlxsw_sp_fid_family_pgt_size(const struct mlxsw_sp_fid_family *fid_family)
+static int
+mlxsw_sp_fid_8021d_pgt_size(const struct mlxsw_sp_fid_family *fid_family,
+			    u16 *p_pgt_size)
 {
 	u16 num_fids = mlxsw_sp_fid_family_num_fids(fid_family);
 
-	return num_fids * fid_family->nr_flood_tables;
+	*p_pgt_size = num_fids * fid_family->flood_profile->nr_flood_tables;
+	return 0;
+}
+
+static unsigned int mlxsw_sp_fid_rfid_port_offset_cff(unsigned int local_port)
+{
+	/* Port 0 is the CPU port. Since we never create RIFs based off that
+	 * port, we don't need to count it.
+	 */
+	return WARN_ON_ONCE(!local_port) ? 0 : local_port - 1;
+}
+
+static int
+mlxsw_sp_fid_rfid_pgt_size_cff(const struct mlxsw_sp_fid_family *fid_family,
+			       u16 *p_pgt_size)
+{
+	struct mlxsw_core *core = fid_family->mlxsw_sp->core;
+	unsigned int max_ports;
+	u16 pgt_size;
+	u16 max_lags;
+	int err;
+
+	max_ports = mlxsw_core_max_ports(core);
+
+	err = mlxsw_core_max_lag(core, &max_lags);
+	if (err)
+		return err;
+
+	pgt_size = (mlxsw_sp_fid_rfid_port_offset_cff(max_ports) + max_lags) *
+		   fid_family->flood_profile->nr_flood_tables;
+	*p_pgt_size = pgt_size;
+	return 0;
 }
 
 static u16
-mlxsw_sp_fid_flood_table_mid(const struct mlxsw_sp_fid_family *fid_family,
-			     const struct mlxsw_sp_flood_table *flood_table,
-			     u16 fid_offset)
+mlxsw_sp_fid_pgt_base_ctl(const struct mlxsw_sp_fid_family *fid_family,
+			  const struct mlxsw_sp_flood_table *flood_table)
 {
 	u16 num_fids;
 
 	num_fids = mlxsw_sp_fid_family_num_fids(fid_family);
-	return fid_family->pgt_base + num_fids * flood_table->table_index +
-	       fid_offset;
+	return fid_family->pgt_base + num_fids * flood_table->table_index;
+}
+
+static u16
+mlxsw_sp_fid_fid_mid_ctl(const struct mlxsw_sp_fid *fid,
+			 const struct mlxsw_sp_flood_table *flood_table)
+{
+	return mlxsw_sp_fid_pgt_base_ctl(fid->fid_family, flood_table) +
+	       fid->fid_offset;
 }
 
 int mlxsw_sp_fid_flood_set(struct mlxsw_sp_fid *fid,
@@ -348,15 +438,14 @@ int mlxsw_sp_fid_flood_set(struct mlxsw_sp_fid *fid,
 	const struct mlxsw_sp_flood_table *flood_table;
 	u16 mid_index;
 
-	if (WARN_ON(!fid_family->flood_tables))
+	if (WARN_ON(!fid_family->flood_profile))
 		return -EINVAL;
 
 	flood_table = mlxsw_sp_fid_flood_table_lookup(fid, packet_type);
 	if (!flood_table)
 		return -ESRCH;
 
-	mid_index = mlxsw_sp_fid_flood_table_mid(fid_family, flood_table,
-						 fid->fid_offset);
+	mid_index = fid_family->ops->fid_mid(fid, flood_table);
 	return mlxsw_sp_pgt_entry_port_set(fid_family->mlxsw_sp, mid_index,
 					   fid->fid_index, local_port, member);
 }
@@ -410,12 +499,13 @@ u16 mlxsw_sp_fid_8021q_vid(const struct mlxsw_sp_fid *fid)
 	return mlxsw_sp_fid_8021q_fid(fid)->vid;
 }
 
-static void mlxsw_sp_fid_8021q_setup(struct mlxsw_sp_fid *fid, const void *arg)
+static int mlxsw_sp_fid_8021q_setup(struct mlxsw_sp_fid *fid, const void *arg)
 {
 	u16 vid = *(u16 *) arg;
 
 	mlxsw_sp_fid_8021q_fid(fid)->vid = vid;
 	fid->fid_offset = fid->fid_index - fid->fid_family->start_index;
+	return 0;
 }
 
 static enum mlxsw_reg_sfmr_op mlxsw_sp_sfmr_op(bool valid)
@@ -424,18 +514,76 @@ static enum mlxsw_reg_sfmr_op mlxsw_sp_sfmr_op(bool valid)
 		       MLXSW_REG_SFMR_OP_DESTROY_FID;
 }
 
-static int mlxsw_sp_fid_op(const struct mlxsw_sp_fid *fid, bool valid)
+static void mlxsw_sp_fid_pack(char *sfmr_pl,
+			      const struct mlxsw_sp_fid *fid,
+			      enum mlxsw_reg_sfmr_op op)
 {
-	struct mlxsw_sp *mlxsw_sp = fid->fid_family->mlxsw_sp;
-	char sfmr_pl[MLXSW_REG_SFMR_LEN];
 	u16 smpe;
 
 	smpe = fid->fid_family->smpe_index_valid ? fid->fid_index : 0;
 
-	mlxsw_reg_sfmr_pack(sfmr_pl, mlxsw_sp_sfmr_op(valid), fid->fid_index,
-			    fid->fid_offset, fid->fid_family->flood_rsp,
-			    fid->fid_family->bridge_type,
+	mlxsw_reg_sfmr_pack(sfmr_pl, op, fid->fid_index,
 			    fid->fid_family->smpe_index_valid, smpe);
+}
+
+static void mlxsw_sp_fid_pack_ctl(char *sfmr_pl,
+				  const struct mlxsw_sp_fid *fid,
+				  enum mlxsw_reg_sfmr_op op)
+{
+	mlxsw_sp_fid_pack(sfmr_pl, fid, op);
+	mlxsw_reg_sfmr_fid_offset_set(sfmr_pl, fid->fid_offset);
+	mlxsw_reg_sfmr_flood_rsp_set(sfmr_pl, fid->fid_family->flood_rsp);
+	mlxsw_reg_sfmr_flood_bridge_type_set(sfmr_pl,
+					     fid->fid_family->bridge_type);
+}
+
+static u16
+mlxsw_sp_fid_off_pgt_base_cff(const struct mlxsw_sp_fid_family *fid_family,
+			      u16 fid_offset)
+{
+	return fid_family->pgt_base +
+		fid_offset * fid_family->flood_profile->nr_flood_tables;
+}
+
+static u16 mlxsw_sp_fid_pgt_base_cff(const struct mlxsw_sp_fid *fid)
+{
+	return mlxsw_sp_fid_off_pgt_base_cff(fid->fid_family, fid->fid_offset);
+}
+
+static void mlxsw_sp_fid_fid_pack_cff(char *sfmr_pl,
+				      const struct mlxsw_sp_fid *fid,
+				      enum mlxsw_reg_sfmr_op op)
+{
+	struct mlxsw_sp_fid_family *fid_family = fid->fid_family;
+	u16 pgt_base = mlxsw_sp_fid_pgt_base_cff(fid);
+
+	mlxsw_sp_fid_pack(sfmr_pl, fid, op);
+	mlxsw_reg_sfmr_cff_mid_base_set(sfmr_pl, pgt_base);
+	mlxsw_reg_sfmr_cff_prf_id_set(sfmr_pl,
+				      fid_family->flood_profile->profile_id);
+	mlxsw_reg_sfmr_nve_flood_prf_id_set(sfmr_pl,
+					    MLXSW_SP_FID_FLOOD_PROFILE_ID_NVE);
+}
+
+static u16 mlxsw_sp_fid_rfid_fid_offset_cff(struct mlxsw_sp *mlxsw_sp,
+					    u16 port_lag_id, bool is_lag)
+{
+	u16 max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
+
+	if (is_lag)
+		return mlxsw_sp_fid_rfid_port_offset_cff(max_ports) +
+		       port_lag_id;
+	else
+		return mlxsw_sp_fid_rfid_port_offset_cff(port_lag_id);
+}
+
+static int mlxsw_sp_fid_op(const struct mlxsw_sp_fid *fid, bool valid)
+{
+	struct mlxsw_sp *mlxsw_sp = fid->fid_family->mlxsw_sp;
+	char sfmr_pl[MLXSW_REG_SFMR_LEN];
+
+	fid->fid_family->ops->fid_pack(sfmr_pl, fid,
+				       mlxsw_sp_sfmr_op(valid));
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl);
 }
 
@@ -444,15 +592,10 @@ static int mlxsw_sp_fid_edit_op(const struct mlxsw_sp_fid *fid,
 {
 	struct mlxsw_sp *mlxsw_sp = fid->fid_family->mlxsw_sp;
 	char sfmr_pl[MLXSW_REG_SFMR_LEN];
-	u16 smpe;
 
-	smpe = fid->fid_family->smpe_index_valid ? fid->fid_index : 0;
+	fid->fid_family->ops->fid_pack(sfmr_pl, fid,
+				       MLXSW_REG_SFMR_OP_CREATE_FID);
 
-	mlxsw_reg_sfmr_pack(sfmr_pl, MLXSW_REG_SFMR_OP_CREATE_FID,
-			    fid->fid_index, fid->fid_offset,
-			    fid->fid_family->flood_rsp,
-			    fid->fid_family->bridge_type,
-			    fid->fid_family->smpe_index_valid, smpe);
 	mlxsw_reg_sfmr_vv_set(sfmr_pl, fid->vni_valid);
 	mlxsw_reg_sfmr_vni_set(sfmr_pl, be32_to_cpu(fid->vni));
 	mlxsw_reg_sfmr_vtfp_set(sfmr_pl, fid->nve_flood_index_valid);
@@ -768,12 +911,13 @@ mlxsw_sp_fid_8021d_fid(const struct mlxsw_sp_fid *fid)
 	return container_of(fid, struct mlxsw_sp_fid_8021d, common);
 }
 
-static void mlxsw_sp_fid_8021d_setup(struct mlxsw_sp_fid *fid, const void *arg)
+static int mlxsw_sp_fid_8021d_setup(struct mlxsw_sp_fid *fid, const void *arg)
 {
 	int br_ifindex = *(int *) arg;
 
 	mlxsw_sp_fid_8021d_fid(fid)->br_ifindex = br_ifindex;
 	fid->fid_offset = fid->fid_index - fid->fid_family->start_index;
+	return 0;
 }
 
 static int mlxsw_sp_fid_8021d_configure(struct mlxsw_sp_fid *fid)
@@ -1058,7 +1202,37 @@ mlxsw_sp_fid_8021d_vid_to_fid_rif_update(const struct mlxsw_sp_fid *fid,
 	return 0;
 }
 
-static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_8021d_ops = {
+static int
+mlxsw_sp_fid_flood_table_init_ctl(struct mlxsw_sp_fid_family *fid_family,
+				  const struct mlxsw_sp_flood_table *flood_table)
+{
+	enum mlxsw_sp_flood_type packet_type = flood_table->packet_type;
+	struct mlxsw_sp *mlxsw_sp = fid_family->mlxsw_sp;
+	const int *sfgc_packet_types;
+	u16 mid_base;
+	int err, i;
+
+	mid_base = mlxsw_sp_fid_pgt_base_ctl(fid_family, flood_table);
+
+	sfgc_packet_types = mlxsw_sp_packet_type_sfgc_types[packet_type];
+	for (i = 0; i < MLXSW_REG_SFGC_TYPE_MAX; i++) {
+		char sfgc_pl[MLXSW_REG_SFGC_LEN];
+
+		if (!sfgc_packet_types[i])
+			continue;
+
+		mlxsw_reg_sfgc_pack(sfgc_pl, i, fid_family->bridge_type,
+				    flood_table->table_type, 0, mid_base);
+
+		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfgc), sfgc_pl);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_8021d_ops_ctl = {
 	.setup			= mlxsw_sp_fid_8021d_setup,
 	.configure		= mlxsw_sp_fid_8021d_configure,
 	.deconfigure		= mlxsw_sp_fid_8021d_deconfigure,
@@ -1072,6 +1246,36 @@ static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_8021d_ops = {
 	.nve_flood_index_clear	= mlxsw_sp_fid_8021d_nve_flood_index_clear,
 	.fdb_clear_offload	= mlxsw_sp_fid_8021d_fdb_clear_offload,
 	.vid_to_fid_rif_update  = mlxsw_sp_fid_8021d_vid_to_fid_rif_update,
+	.flood_table_init	= mlxsw_sp_fid_flood_table_init_ctl,
+	.pgt_size		= mlxsw_sp_fid_8021d_pgt_size,
+	.fid_mid		= mlxsw_sp_fid_fid_mid_ctl,
+	.fid_pack		= mlxsw_sp_fid_pack_ctl,
+};
+
+static u16
+mlxsw_sp_fid_fid_mid_cff(const struct mlxsw_sp_fid *fid,
+			 const struct mlxsw_sp_flood_table *flood_table)
+{
+	return mlxsw_sp_fid_pgt_base_cff(fid) + flood_table->table_index;
+}
+
+static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_8021d_ops_cff = {
+	.setup			= mlxsw_sp_fid_8021d_setup,
+	.configure		= mlxsw_sp_fid_8021d_configure,
+	.deconfigure		= mlxsw_sp_fid_8021d_deconfigure,
+	.index_alloc		= mlxsw_sp_fid_8021d_index_alloc,
+	.compare		= mlxsw_sp_fid_8021d_compare,
+	.port_vid_map		= mlxsw_sp_fid_8021d_port_vid_map,
+	.port_vid_unmap		= mlxsw_sp_fid_8021d_port_vid_unmap,
+	.vni_set		= mlxsw_sp_fid_8021d_vni_set,
+	.vni_clear		= mlxsw_sp_fid_8021d_vni_clear,
+	.nve_flood_index_set	= mlxsw_sp_fid_8021d_nve_flood_index_set,
+	.nve_flood_index_clear	= mlxsw_sp_fid_8021d_nve_flood_index_clear,
+	.fdb_clear_offload	= mlxsw_sp_fid_8021d_fdb_clear_offload,
+	.vid_to_fid_rif_update	= mlxsw_sp_fid_8021d_vid_to_fid_rif_update,
+	.pgt_size		= mlxsw_sp_fid_8021d_pgt_size,
+	.fid_mid		= mlxsw_sp_fid_fid_mid_cff,
+	.fid_pack		= mlxsw_sp_fid_fid_pack_cff,
 };
 
 #define MLXSW_SP_FID_8021Q_MAX (VLAN_N_VID - 2)
@@ -1095,6 +1299,45 @@ static const struct mlxsw_sp_flood_table mlxsw_sp_fid_8021d_flood_tables[] = {
 	},
 };
 
+static const
+struct mlxsw_sp_fid_flood_profile mlxsw_sp_fid_8021d_flood_profile = {
+	.flood_tables		= mlxsw_sp_fid_8021d_flood_tables,
+	.nr_flood_tables	= ARRAY_SIZE(mlxsw_sp_fid_8021d_flood_tables),
+	.profile_id		= MLXSW_SP_FID_FLOOD_PROFILE_ID_BRIDGE,
+};
+
+static const struct mlxsw_sp_flood_table mlxsw_sp_fid_rsp_flood_tables_cff[] = {
+	{
+		.packet_type	= MLXSW_SP_FLOOD_TYPE_UC,
+		.table_index	= 0,
+	},
+	{
+		.packet_type	= MLXSW_SP_FLOOD_TYPE_NOT_UC,
+		.table_index	= 1,
+	},
+};
+
+static const
+struct mlxsw_sp_fid_flood_profile mlxsw_sp_fid_rsp_flood_profile_cff = {
+	.flood_tables		= mlxsw_sp_fid_rsp_flood_tables_cff,
+	.nr_flood_tables	= ARRAY_SIZE(mlxsw_sp_fid_rsp_flood_tables_cff),
+	.profile_id		= MLXSW_SP_FID_FLOOD_PROFILE_ID_RSP,
+};
+
+static const struct mlxsw_sp_flood_table mlxsw_sp_fid_nve_flood_tables_cff[] = {
+	{
+		.packet_type	= MLXSW_SP_FLOOD_TYPE_ANY,
+		.table_index	= 0,
+	},
+};
+
+static const
+struct mlxsw_sp_fid_flood_profile mlxsw_sp_fid_nve_flood_profile_cff = {
+	.flood_tables		= mlxsw_sp_fid_nve_flood_tables_cff,
+	.nr_flood_tables	= ARRAY_SIZE(mlxsw_sp_fid_nve_flood_tables_cff),
+	.profile_id		= MLXSW_SP_FID_FLOOD_PROFILE_ID_NVE,
+};
+
 static bool
 mlxsw_sp_fid_8021q_compare(const struct mlxsw_sp_fid *fid, const void *arg)
 {
@@ -1110,9 +1353,35 @@ mlxsw_sp_fid_8021q_fdb_clear_offload(const struct mlxsw_sp_fid *fid,
 	br_fdb_clear_offload(nve_dev, mlxsw_sp_fid_8021q_vid(fid));
 }
 
-static void mlxsw_sp_fid_rfid_setup(struct mlxsw_sp_fid *fid, const void *arg)
+static int mlxsw_sp_fid_rfid_setup_ctl(struct mlxsw_sp_fid *fid,
+				       const void *arg)
 {
+	/* In controlled mode, the FW takes care of FID placement. */
 	fid->fid_offset = 0;
+	return 0;
+}
+
+static int mlxsw_sp_fid_rfid_setup_cff(struct mlxsw_sp_fid *fid,
+				       const void *arg)
+{
+	struct mlxsw_sp *mlxsw_sp = fid->fid_family->mlxsw_sp;
+	u16 rif_index = *(const u16 *)arg;
+	struct mlxsw_sp_rif *rif;
+	bool is_lag;
+	u16 port;
+	int err;
+
+	rif = mlxsw_sp_rif_by_index(mlxsw_sp, rif_index);
+	if (!rif)
+		return -ENOENT;
+
+	err = mlxsw_sp_rif_subport_port(rif, &port, &is_lag);
+	if (err)
+		return err;
+
+	fid->fid_offset = mlxsw_sp_fid_rfid_fid_offset_cff(mlxsw_sp, port,
+							   is_lag);
+	return 0;
 }
 
 static int mlxsw_sp_fid_rfid_configure(struct mlxsw_sp_fid *fid)
@@ -1238,8 +1507,8 @@ mlxsw_sp_fid_rfid_vid_to_fid_rif_update(const struct mlxsw_sp_fid *fid,
 	return 0;
 }
 
-static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_rfid_ops = {
-	.setup			= mlxsw_sp_fid_rfid_setup,
+static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_rfid_ops_ctl = {
+	.setup			= mlxsw_sp_fid_rfid_setup_ctl,
 	.configure		= mlxsw_sp_fid_rfid_configure,
 	.deconfigure		= mlxsw_sp_fid_rfid_deconfigure,
 	.index_alloc		= mlxsw_sp_fid_rfid_index_alloc,
@@ -1251,11 +1520,146 @@ static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_rfid_ops = {
 	.nve_flood_index_set	= mlxsw_sp_fid_rfid_nve_flood_index_set,
 	.nve_flood_index_clear	= mlxsw_sp_fid_rfid_nve_flood_index_clear,
 	.vid_to_fid_rif_update  = mlxsw_sp_fid_rfid_vid_to_fid_rif_update,
+	.fid_pack		= mlxsw_sp_fid_pack_ctl,
+};
+
+static int
+mlxsw_sp_fid_rfid_port_add_cff(struct mlxsw_sp *mlxsw_sp,
+			       const struct mlxsw_sp_flood_table *flood_table,
+			       u16 pgt_addr, u16 smpe, unsigned int local_port)
+{
+	int err;
+
+	err = mlxsw_sp_pgt_entry_port_set(mlxsw_sp, pgt_addr, smpe,
+					  local_port, true);
+	if (err)
+		return err;
+
+	if (flood_table->packet_type == MLXSW_SP_FLOOD_TYPE_NOT_UC) {
+		u16 router_port = mlxsw_sp_router_port(mlxsw_sp);
+
+		err = mlxsw_sp_pgt_entry_port_set(mlxsw_sp, pgt_addr, smpe,
+						  router_port, true);
+		if (err)
+			goto err_entry_port_set;
+	}
+
+	return 0;
+
+err_entry_port_set:
+	mlxsw_sp_pgt_entry_port_set(mlxsw_sp, pgt_addr, smpe, local_port,
+				    false);
+	return err;
+}
+
+static void
+mlxsw_sp_fid_rfid_port_del_cff(struct mlxsw_sp *mlxsw_sp,
+			       const struct mlxsw_sp_flood_table *flood_table,
+			       u16 pgt_addr, u16 smpe, u16 local_port)
+{
+	if (flood_table->packet_type == MLXSW_SP_FLOOD_TYPE_NOT_UC) {
+		u16 router_port = mlxsw_sp_router_port(mlxsw_sp);
+
+		mlxsw_sp_pgt_entry_port_set(mlxsw_sp, pgt_addr, smpe,
+					    router_port, false);
+	}
+	mlxsw_sp_pgt_entry_port_set(mlxsw_sp, pgt_addr, smpe, local_port,
+				    false);
+}
+
+static int
+mlxsw_sp_fid_rfid_port_memb_ft_cff(const struct mlxsw_sp_fid_family *fid_family,
+				   const struct mlxsw_sp_flood_table *flood_table,
+				   const struct mlxsw_sp_port *mlxsw_sp_port,
+				   bool member)
+{
+	struct mlxsw_sp *mlxsw_sp = fid_family->mlxsw_sp;
+	u16 local_port = mlxsw_sp_port->local_port;
+	u16 fid_pgt_base;
+	u16 fid_offset;
+	u16 pgt_addr;
+	u16 smpe;
+	u16 port;
+
+	/* In-PGT SMPE is only valid on Spectrum-1, CFF only on Spectrum>1. */
+	smpe = 0;
+
+	port = mlxsw_sp_port->lagged ? mlxsw_sp_port->lag_id : local_port;
+	fid_offset = mlxsw_sp_fid_rfid_fid_offset_cff(mlxsw_sp, port,
+						      mlxsw_sp_port->lagged);
+	fid_pgt_base = mlxsw_sp_fid_off_pgt_base_cff(fid_family, fid_offset);
+	pgt_addr = fid_pgt_base + flood_table->table_index;
+
+	if (member)
+		return mlxsw_sp_fid_rfid_port_add_cff(mlxsw_sp, flood_table,
+						      pgt_addr, smpe,
+						      local_port);
+
+	mlxsw_sp_fid_rfid_port_del_cff(mlxsw_sp, flood_table, pgt_addr, smpe,
+				       local_port);
+	return 0;
+}
+
+static int
+mlxsw_sp_fid_rfid_port_memb_cff(const struct mlxsw_sp_fid_family *fid_family,
+				const struct mlxsw_sp_port *mlxsw_sp_port,
+				bool member)
+{
+	int i;
+
+	for (i = 0; i < fid_family->flood_profile->nr_flood_tables; i++) {
+		const struct mlxsw_sp_flood_table *flood_table =
+			&fid_family->flood_profile->flood_tables[i];
+		int err;
+
+		err = mlxsw_sp_fid_rfid_port_memb_ft_cff(fid_family,
+							 flood_table,
+							 mlxsw_sp_port, member);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int
+mlxsw_sp_fid_rfid_port_init_cff(const struct mlxsw_sp_fid_family *fid_family,
+				const struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	return mlxsw_sp_fid_rfid_port_memb_cff(fid_family, mlxsw_sp_port, true);
+}
+
+static void
+mlxsw_sp_fid_rfid_port_fini_cff(const struct mlxsw_sp_fid_family *fid_family,
+				const struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	mlxsw_sp_fid_rfid_port_memb_cff(fid_family, mlxsw_sp_port, false);
+}
+
+static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_rfid_ops_cff = {
+	.setup			= mlxsw_sp_fid_rfid_setup_cff,
+	.configure		= mlxsw_sp_fid_rfid_configure,
+	.deconfigure		= mlxsw_sp_fid_rfid_deconfigure,
+	.index_alloc		= mlxsw_sp_fid_rfid_index_alloc,
+	.compare		= mlxsw_sp_fid_rfid_compare,
+	.port_vid_map		= mlxsw_sp_fid_rfid_port_vid_map,
+	.port_vid_unmap		= mlxsw_sp_fid_rfid_port_vid_unmap,
+	.vni_set		= mlxsw_sp_fid_rfid_vni_set,
+	.vni_clear		= mlxsw_sp_fid_rfid_vni_clear,
+	.nve_flood_index_set	= mlxsw_sp_fid_rfid_nve_flood_index_set,
+	.nve_flood_index_clear	= mlxsw_sp_fid_rfid_nve_flood_index_clear,
+	.vid_to_fid_rif_update	= mlxsw_sp_fid_rfid_vid_to_fid_rif_update,
+	.pgt_size		= mlxsw_sp_fid_rfid_pgt_size_cff,
+	.fid_port_init		= mlxsw_sp_fid_rfid_port_init_cff,
+	.fid_port_fini		= mlxsw_sp_fid_rfid_port_fini_cff,
+	.fid_mid		= mlxsw_sp_fid_fid_mid_cff,
+	.fid_pack		= mlxsw_sp_fid_fid_pack_cff,
 };
 
-static void mlxsw_sp_fid_dummy_setup(struct mlxsw_sp_fid *fid, const void *arg)
+static int mlxsw_sp_fid_dummy_setup(struct mlxsw_sp_fid *fid, const void *arg)
 {
 	fid->fid_offset = 0;
+	return 0;
 }
 
 static int mlxsw_sp_fid_dummy_configure(struct mlxsw_sp_fid *fid)
@@ -1312,6 +1716,7 @@ static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_dummy_ops = {
 	.vni_clear		= mlxsw_sp_fid_dummy_vni_clear,
 	.nve_flood_index_set	= mlxsw_sp_fid_dummy_nve_flood_index_set,
 	.nve_flood_index_clear	= mlxsw_sp_fid_dummy_nve_flood_index_clear,
+	.fid_pack		= mlxsw_sp_fid_pack,
 };
 
 static int mlxsw_sp_fid_8021q_configure(struct mlxsw_sp_fid *fid)
@@ -1395,7 +1800,7 @@ mlxsw_sp_fid_8021q_port_vid_unmap(struct mlxsw_sp_fid *fid,
 		__mlxsw_sp_fid_port_vid_map(fid, local_port, vid, false);
 }
 
-static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_8021q_ops = {
+static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_8021q_ops_ctl = {
 	.setup			= mlxsw_sp_fid_8021q_setup,
 	.configure		= mlxsw_sp_fid_8021q_configure,
 	.deconfigure		= mlxsw_sp_fid_8021q_deconfigure,
@@ -1409,6 +1814,29 @@ static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_8021q_ops = {
 	.nve_flood_index_clear	= mlxsw_sp_fid_8021d_nve_flood_index_clear,
 	.fdb_clear_offload	= mlxsw_sp_fid_8021q_fdb_clear_offload,
 	.vid_to_fid_rif_update  = mlxsw_sp_fid_8021q_vid_to_fid_rif_update,
+	.flood_table_init	= mlxsw_sp_fid_flood_table_init_ctl,
+	.pgt_size		= mlxsw_sp_fid_8021d_pgt_size,
+	.fid_mid		= mlxsw_sp_fid_fid_mid_ctl,
+	.fid_pack		= mlxsw_sp_fid_pack_ctl,
+};
+
+static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_8021q_ops_cff = {
+	.setup			= mlxsw_sp_fid_8021q_setup,
+	.configure		= mlxsw_sp_fid_8021q_configure,
+	.deconfigure		= mlxsw_sp_fid_8021q_deconfigure,
+	.index_alloc		= mlxsw_sp_fid_8021d_index_alloc,
+	.compare		= mlxsw_sp_fid_8021q_compare,
+	.port_vid_map		= mlxsw_sp_fid_8021q_port_vid_map,
+	.port_vid_unmap		= mlxsw_sp_fid_8021q_port_vid_unmap,
+	.vni_set		= mlxsw_sp_fid_8021d_vni_set,
+	.vni_clear		= mlxsw_sp_fid_8021d_vni_clear,
+	.nve_flood_index_set	= mlxsw_sp_fid_8021d_nve_flood_index_set,
+	.nve_flood_index_clear	= mlxsw_sp_fid_8021d_nve_flood_index_clear,
+	.fdb_clear_offload	= mlxsw_sp_fid_8021q_fdb_clear_offload,
+	.vid_to_fid_rif_update	= mlxsw_sp_fid_8021q_vid_to_fid_rif_update,
+	.pgt_size		= mlxsw_sp_fid_8021d_pgt_size,
+	.fid_mid		= mlxsw_sp_fid_fid_mid_cff,
+	.fid_pack		= mlxsw_sp_fid_fid_pack_cff,
 };
 
 /* There are 4K-2 802.1Q FIDs */
@@ -1434,10 +1862,9 @@ static const struct mlxsw_sp_fid_family mlxsw_sp1_fid_8021q_family = {
 	.fid_size		= sizeof(struct mlxsw_sp_fid_8021q),
 	.start_index		= MLXSW_SP_FID_8021Q_START,
 	.end_index		= MLXSW_SP_FID_8021Q_END,
-	.flood_tables		= mlxsw_sp_fid_8021d_flood_tables,
-	.nr_flood_tables	= ARRAY_SIZE(mlxsw_sp_fid_8021d_flood_tables),
+	.flood_profile		= &mlxsw_sp_fid_8021d_flood_profile,
 	.rif_type		= MLXSW_SP_RIF_TYPE_VLAN,
-	.ops			= &mlxsw_sp_fid_8021q_ops,
+	.ops			= &mlxsw_sp_fid_8021q_ops_ctl,
 	.flood_rsp              = false,
 	.bridge_type            = MLXSW_REG_BRIDGE_TYPE_0,
 	.smpe_index_valid	= false,
@@ -1448,10 +1875,9 @@ static const struct mlxsw_sp_fid_family mlxsw_sp1_fid_8021d_family = {
 	.fid_size		= sizeof(struct mlxsw_sp_fid_8021d),
 	.start_index		= MLXSW_SP_FID_8021D_START,
 	.end_index		= MLXSW_SP_FID_8021D_END,
-	.flood_tables		= mlxsw_sp_fid_8021d_flood_tables,
-	.nr_flood_tables	= ARRAY_SIZE(mlxsw_sp_fid_8021d_flood_tables),
+	.flood_profile		= &mlxsw_sp_fid_8021d_flood_profile,
 	.rif_type		= MLXSW_SP_RIF_TYPE_FID,
-	.ops			= &mlxsw_sp_fid_8021d_ops,
+	.ops			= &mlxsw_sp_fid_8021d_ops_ctl,
 	.bridge_type            = MLXSW_REG_BRIDGE_TYPE_1,
 	.smpe_index_valid       = false,
 };
@@ -1465,47 +1891,45 @@ static const struct mlxsw_sp_fid_family mlxsw_sp1_fid_dummy_family = {
 	.smpe_index_valid       = false,
 };
 
-static const struct mlxsw_sp_fid_family mlxsw_sp_fid_rfid_family = {
+static const struct mlxsw_sp_fid_family mlxsw_sp_fid_rfid_family_ctl = {
 	.type			= MLXSW_SP_FID_TYPE_RFID,
 	.fid_size		= sizeof(struct mlxsw_sp_fid),
 	.start_index		= MLXSW_SP_RFID_START,
 	.end_index		= MLXSW_SP_RFID_END,
 	.rif_type		= MLXSW_SP_RIF_TYPE_SUBPORT,
-	.ops			= &mlxsw_sp_fid_rfid_ops,
+	.ops			= &mlxsw_sp_fid_rfid_ops_ctl,
 	.flood_rsp              = true,
 	.smpe_index_valid       = false,
 };
 
-const struct mlxsw_sp_fid_family *mlxsw_sp1_fid_family_arr[] = {
+static const struct mlxsw_sp_fid_family *mlxsw_sp1_fid_family_arr[] = {
 	[MLXSW_SP_FID_TYPE_8021Q]	= &mlxsw_sp1_fid_8021q_family,
 	[MLXSW_SP_FID_TYPE_8021D]	= &mlxsw_sp1_fid_8021d_family,
 	[MLXSW_SP_FID_TYPE_DUMMY]	= &mlxsw_sp1_fid_dummy_family,
-	[MLXSW_SP_FID_TYPE_RFID]	= &mlxsw_sp_fid_rfid_family,
+	[MLXSW_SP_FID_TYPE_RFID]	= &mlxsw_sp_fid_rfid_family_ctl,
 };
 
-static const struct mlxsw_sp_fid_family mlxsw_sp2_fid_8021q_family = {
+static const struct mlxsw_sp_fid_family mlxsw_sp2_fid_8021q_family_ctl = {
 	.type			= MLXSW_SP_FID_TYPE_8021Q,
 	.fid_size		= sizeof(struct mlxsw_sp_fid_8021q),
 	.start_index		= MLXSW_SP_FID_8021Q_START,
 	.end_index		= MLXSW_SP_FID_8021Q_END,
-	.flood_tables		= mlxsw_sp_fid_8021d_flood_tables,
-	.nr_flood_tables	= ARRAY_SIZE(mlxsw_sp_fid_8021d_flood_tables),
+	.flood_profile		= &mlxsw_sp_fid_8021d_flood_profile,
 	.rif_type		= MLXSW_SP_RIF_TYPE_VLAN,
-	.ops			= &mlxsw_sp_fid_8021q_ops,
+	.ops			= &mlxsw_sp_fid_8021q_ops_ctl,
 	.flood_rsp              = false,
 	.bridge_type            = MLXSW_REG_BRIDGE_TYPE_0,
 	.smpe_index_valid	= true,
 };
 
-static const struct mlxsw_sp_fid_family mlxsw_sp2_fid_8021d_family = {
+static const struct mlxsw_sp_fid_family mlxsw_sp2_fid_8021d_family_ctl = {
 	.type			= MLXSW_SP_FID_TYPE_8021D,
 	.fid_size		= sizeof(struct mlxsw_sp_fid_8021d),
 	.start_index		= MLXSW_SP_FID_8021D_START,
 	.end_index		= MLXSW_SP_FID_8021D_END,
-	.flood_tables		= mlxsw_sp_fid_8021d_flood_tables,
-	.nr_flood_tables	= ARRAY_SIZE(mlxsw_sp_fid_8021d_flood_tables),
+	.flood_profile		= &mlxsw_sp_fid_8021d_flood_profile,
 	.rif_type		= MLXSW_SP_RIF_TYPE_FID,
-	.ops			= &mlxsw_sp_fid_8021d_ops,
+	.ops			= &mlxsw_sp_fid_8021d_ops_ctl,
 	.bridge_type            = MLXSW_REG_BRIDGE_TYPE_1,
 	.smpe_index_valid       = true,
 };
@@ -1519,11 +1943,51 @@ static const struct mlxsw_sp_fid_family mlxsw_sp2_fid_dummy_family = {
 	.smpe_index_valid       = false,
 };
 
-const struct mlxsw_sp_fid_family *mlxsw_sp2_fid_family_arr[] = {
-	[MLXSW_SP_FID_TYPE_8021Q]	= &mlxsw_sp2_fid_8021q_family,
-	[MLXSW_SP_FID_TYPE_8021D]	= &mlxsw_sp2_fid_8021d_family,
+static const struct mlxsw_sp_fid_family *mlxsw_sp2_fid_family_arr_ctl[] = {
+	[MLXSW_SP_FID_TYPE_8021Q]	= &mlxsw_sp2_fid_8021q_family_ctl,
+	[MLXSW_SP_FID_TYPE_8021D]	= &mlxsw_sp2_fid_8021d_family_ctl,
 	[MLXSW_SP_FID_TYPE_DUMMY]	= &mlxsw_sp2_fid_dummy_family,
-	[MLXSW_SP_FID_TYPE_RFID]	= &mlxsw_sp_fid_rfid_family,
+	[MLXSW_SP_FID_TYPE_RFID]	= &mlxsw_sp_fid_rfid_family_ctl,
+};
+
+static const struct mlxsw_sp_fid_family mlxsw_sp2_fid_8021q_family_cff = {
+	.type			= MLXSW_SP_FID_TYPE_8021Q,
+	.fid_size		= sizeof(struct mlxsw_sp_fid_8021q),
+	.start_index		= MLXSW_SP_FID_8021Q_START,
+	.end_index		= MLXSW_SP_FID_8021Q_END,
+	.flood_profile		= &mlxsw_sp_fid_8021d_flood_profile,
+	.rif_type		= MLXSW_SP_RIF_TYPE_VLAN,
+	.ops			= &mlxsw_sp_fid_8021q_ops_cff,
+	.smpe_index_valid	= true,
+};
+
+static const struct mlxsw_sp_fid_family mlxsw_sp2_fid_8021d_family_cff = {
+	.type			= MLXSW_SP_FID_TYPE_8021D,
+	.fid_size		= sizeof(struct mlxsw_sp_fid_8021d),
+	.start_index		= MLXSW_SP_FID_8021D_START,
+	.end_index		= MLXSW_SP_FID_8021D_END,
+	.flood_profile		= &mlxsw_sp_fid_8021d_flood_profile,
+	.rif_type		= MLXSW_SP_RIF_TYPE_FID,
+	.ops			= &mlxsw_sp_fid_8021d_ops_cff,
+	.smpe_index_valid	= true,
+};
+
+static const struct mlxsw_sp_fid_family mlxsw_sp_fid_rfid_family_cff = {
+	.type			= MLXSW_SP_FID_TYPE_RFID,
+	.fid_size		= sizeof(struct mlxsw_sp_fid),
+	.start_index		= MLXSW_SP_RFID_START,
+	.end_index		= MLXSW_SP_RFID_END,
+	.flood_profile		= &mlxsw_sp_fid_rsp_flood_profile_cff,
+	.rif_type		= MLXSW_SP_RIF_TYPE_SUBPORT,
+	.ops			= &mlxsw_sp_fid_rfid_ops_cff,
+	.smpe_index_valid	= false,
+};
+
+static const struct mlxsw_sp_fid_family *mlxsw_sp2_fid_family_arr_cff[] = {
+	[MLXSW_SP_FID_TYPE_8021Q]	= &mlxsw_sp2_fid_8021q_family_cff,
+	[MLXSW_SP_FID_TYPE_8021D]	= &mlxsw_sp2_fid_8021d_family_cff,
+	[MLXSW_SP_FID_TYPE_DUMMY]	= &mlxsw_sp2_fid_dummy_family,
+	[MLXSW_SP_FID_TYPE_RFID]	= &mlxsw_sp_fid_rfid_family_cff,
 };
 
 static struct mlxsw_sp_fid *mlxsw_sp_fid_lookup(struct mlxsw_sp *mlxsw_sp,
@@ -1571,7 +2035,9 @@ static struct mlxsw_sp_fid *mlxsw_sp_fid_get(struct mlxsw_sp *mlxsw_sp,
 	fid->fid_index = fid_index;
 	__set_bit(fid_index - fid_family->start_index, fid_family->fids_bitmap);
 
-	fid->fid_family->ops->setup(fid, arg);
+	err = fid->fid_family->ops->setup(fid, arg);
+	if (err)
+		goto err_setup;
 
 	err = fid->fid_family->ops->configure(fid);
 	if (err)
@@ -1589,6 +2055,7 @@ static struct mlxsw_sp_fid *mlxsw_sp_fid_get(struct mlxsw_sp *mlxsw_sp,
 err_rhashtable_insert:
 	fid->fid_family->ops->deconfigure(fid);
 err_configure:
+err_setup:
 	__clear_bit(fid_index - fid_family->start_index,
 		    fid_family->fids_bitmap);
 err_index_alloc:
@@ -1650,36 +2117,6 @@ struct mlxsw_sp_fid *mlxsw_sp_fid_dummy_get(struct mlxsw_sp *mlxsw_sp)
 }
 
 static int
-mlxsw_sp_fid_flood_table_init(struct mlxsw_sp_fid_family *fid_family,
-			      const struct mlxsw_sp_flood_table *flood_table)
-{
-	enum mlxsw_sp_flood_type packet_type = flood_table->packet_type;
-	struct mlxsw_sp *mlxsw_sp = fid_family->mlxsw_sp;
-	const int *sfgc_packet_types;
-	u16 mid_base;
-	int err, i;
-
-	mid_base = mlxsw_sp_fid_flood_table_mid(fid_family, flood_table, 0);
-
-	sfgc_packet_types = mlxsw_sp_packet_type_sfgc_types[packet_type];
-	for (i = 0; i < MLXSW_REG_SFGC_TYPE_MAX; i++) {
-		char sfgc_pl[MLXSW_REG_SFGC_LEN];
-
-		if (!sfgc_packet_types[i])
-			continue;
-
-		mlxsw_reg_sfgc_pack(sfgc_pl, i, fid_family->bridge_type,
-				    flood_table->table_type, 0, mid_base);
-
-		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfgc), sfgc_pl);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-static int
 mlxsw_sp_fid_flood_tables_init(struct mlxsw_sp_fid_family *fid_family)
 {
 	struct mlxsw_sp *mlxsw_sp = fid_family->mlxsw_sp;
@@ -1687,22 +2124,28 @@ mlxsw_sp_fid_flood_tables_init(struct mlxsw_sp_fid_family *fid_family)
 	int err;
 	int i;
 
-	if (!fid_family->nr_flood_tables)
-		return 0;
+	err = fid_family->ops->pgt_size(fid_family, &pgt_size);
+	if (err)
+		return err;
 
-	pgt_size = mlxsw_sp_fid_family_pgt_size(fid_family);
 	err = mlxsw_sp_pgt_mid_alloc_range(mlxsw_sp, &fid_family->pgt_base,
 					   pgt_size);
 	if (err)
 		return err;
 
-	for (i = 0; i < fid_family->nr_flood_tables; i++) {
+	if (!fid_family->flood_profile)
+		return 0;
+
+	for (i = 0; i < fid_family->flood_profile->nr_flood_tables; i++) {
 		const struct mlxsw_sp_flood_table *flood_table;
 
-		flood_table = &fid_family->flood_tables[i];
-		err = mlxsw_sp_fid_flood_table_init(fid_family, flood_table);
-		if (err)
-			goto err_flood_table_init;
+		flood_table = &fid_family->flood_profile->flood_tables[i];
+		if (fid_family->ops->flood_table_init) {
+			err = fid_family->ops->flood_table_init(fid_family,
+								flood_table);
+			if (err)
+				goto err_flood_table_init;
+		}
 	}
 
 	return 0;
@@ -1717,11 +2160,12 @@ mlxsw_sp_fid_flood_tables_fini(struct mlxsw_sp_fid_family *fid_family)
 {
 	struct mlxsw_sp *mlxsw_sp = fid_family->mlxsw_sp;
 	u16 pgt_size;
+	int err;
 
-	if (!fid_family->nr_flood_tables)
+	err = fid_family->ops->pgt_size(fid_family, &pgt_size);
+	if (WARN_ON_ONCE(err))
 		return;
 
-	pgt_size = mlxsw_sp_fid_family_pgt_size(fid_family);
 	mlxsw_sp_pgt_mid_free_range(mlxsw_sp, fid_family->pgt_base, pgt_size);
 }
 
@@ -1744,7 +2188,7 @@ static int mlxsw_sp_fid_family_register(struct mlxsw_sp *mlxsw_sp,
 		goto err_alloc_fids_bitmap;
 	}
 
-	if (fid_family->flood_tables) {
+	if (fid_family->flood_profile) {
 		err = mlxsw_sp_fid_flood_tables_init(fid_family);
 		if (err)
 			goto err_fid_flood_tables_init;
@@ -1767,7 +2211,7 @@ mlxsw_sp_fid_family_unregister(struct mlxsw_sp *mlxsw_sp,
 {
 	mlxsw_sp->fid_core->fid_family_arr[fid_family->type] = NULL;
 
-	if (fid_family->flood_tables)
+	if (fid_family->flood_profile)
 		mlxsw_sp_fid_flood_tables_fini(fid_family);
 
 	bitmap_free(fid_family->fids_bitmap);
@@ -1775,9 +2219,34 @@ mlxsw_sp_fid_family_unregister(struct mlxsw_sp *mlxsw_sp,
 	kfree(fid_family);
 }
 
+static int mlxsw_sp_fid_port_init(const struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	const enum mlxsw_sp_fid_type type_rfid = MLXSW_SP_FID_TYPE_RFID;
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_fid_family *rfid_family;
+
+	rfid_family = mlxsw_sp->fid_core->fid_family_arr[type_rfid];
+	if (rfid_family->ops->fid_port_init)
+		return rfid_family->ops->fid_port_init(rfid_family,
+						       mlxsw_sp_port);
+	return 0;
+}
+
+static void mlxsw_sp_fid_port_fini(const struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	const enum mlxsw_sp_fid_type type_rfid = MLXSW_SP_FID_TYPE_RFID;
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_fid_family *rfid_family;
+
+	rfid_family = mlxsw_sp->fid_core->fid_family_arr[type_rfid];
+	if (rfid_family->ops->fid_port_fini)
+		rfid_family->ops->fid_port_fini(rfid_family, mlxsw_sp_port);
+}
+
 int mlxsw_sp_port_fids_init(struct mlxsw_sp_port *mlxsw_sp_port)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	int err;
 
 	/* Track number of FIDs configured on the port with mapping type
 	 * PORT_VID_TO_FID, so that we know when to transition the port
@@ -1785,17 +2254,42 @@ int mlxsw_sp_port_fids_init(struct mlxsw_sp_port *mlxsw_sp_port)
 	 */
 	mlxsw_sp->fid_core->port_fid_mappings[mlxsw_sp_port->local_port] = 0;
 
-	return mlxsw_sp_port_vp_mode_set(mlxsw_sp_port, false);
+	err = mlxsw_sp_fid_port_init(mlxsw_sp_port);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_port_vp_mode_set(mlxsw_sp_port, false);
+	if (err)
+		goto err_vp_mode_set;
+
+	return 0;
+
+err_vp_mode_set:
+	mlxsw_sp_fid_port_fini(mlxsw_sp_port);
+	return err;
 }
 
 void mlxsw_sp_port_fids_fini(struct mlxsw_sp_port *mlxsw_sp_port)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 
+	mlxsw_sp_fid_port_fini(mlxsw_sp_port);
 	mlxsw_sp->fid_core->port_fid_mappings[mlxsw_sp_port->local_port] = 0;
 }
 
-int mlxsw_sp_fids_init(struct mlxsw_sp *mlxsw_sp)
+int mlxsw_sp_fid_port_join_lag(const struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	return mlxsw_sp_fid_port_init(mlxsw_sp_port);
+}
+
+void mlxsw_sp_fid_port_leave_lag(const struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	mlxsw_sp_fid_port_fini(mlxsw_sp_port);
+}
+
+static int
+mlxsw_sp_fids_init(struct mlxsw_sp *mlxsw_sp,
+		   const struct mlxsw_sp_fid_family *fid_family_arr[])
 {
 	unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
 	struct mlxsw_sp_fid_core *fid_core;
@@ -1822,8 +2316,7 @@ int mlxsw_sp_fids_init(struct mlxsw_sp *mlxsw_sp)
 	}
 
 	for (i = 0; i < MLXSW_SP_FID_TYPE_MAX; i++) {
-		err = mlxsw_sp_fid_family_register(mlxsw_sp,
-						   mlxsw_sp->fid_family_arr[i]);
+		err = mlxsw_sp_fid_family_register(mlxsw_sp, fid_family_arr[i]);
 
 		if (err)
 			goto err_fid_ops_register;
@@ -1848,7 +2341,7 @@ err_rhashtable_fid_init:
 	return err;
 }
 
-void mlxsw_sp_fids_fini(struct mlxsw_sp *mlxsw_sp)
+static void mlxsw_sp_fids_fini(struct mlxsw_sp *mlxsw_sp)
 {
 	struct mlxsw_sp_fid_core *fid_core = mlxsw_sp->fid_core;
 	int i;
@@ -1861,3 +2354,143 @@ void mlxsw_sp_fids_fini(struct mlxsw_sp *mlxsw_sp)
 	rhashtable_destroy(&fid_core->fid_ht);
 	kfree(fid_core);
 }
+
+static int mlxsw_sp1_fids_init(struct mlxsw_sp *mlxsw_sp)
+{
+	return mlxsw_sp_fids_init(mlxsw_sp, mlxsw_sp1_fid_family_arr);
+}
+
+const struct mlxsw_sp_fid_core_ops mlxsw_sp1_fid_core_ops = {
+	.init = mlxsw_sp1_fids_init,
+	.fini = mlxsw_sp_fids_fini,
+};
+
+static int mlxsw_sp_fid_check_flood_profile_id(struct mlxsw_sp *mlxsw_sp,
+					       int profile_id)
+{
+	u32 max_profiles;
+
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_NVE_FLOOD_PRF))
+		return -EIO;
+
+	max_profiles = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_NVE_FLOOD_PRF);
+	if (WARN_ON_ONCE(!profile_id) ||
+	    WARN_ON_ONCE(profile_id >= max_profiles))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int
+mlxsw_sp2_fids_init_flood_table(struct mlxsw_sp *mlxsw_sp,
+				enum mlxsw_sp_fid_flood_profile_id profile_id,
+				const struct mlxsw_sp_flood_table *flood_table)
+{
+	enum mlxsw_sp_flood_type packet_type = flood_table->packet_type;
+	const int *sfgc_packet_types;
+	int err;
+	int i;
+
+	sfgc_packet_types = mlxsw_sp_packet_type_sfgc_types[packet_type];
+	for (i = 0; i < MLXSW_REG_SFGC_TYPE_MAX; i++) {
+		char sffp_pl[MLXSW_REG_SFFP_LEN];
+
+		if (!sfgc_packet_types[i])
+			continue;
+
+		mlxsw_reg_sffp_pack(sffp_pl, profile_id, i,
+				    flood_table->table_index);
+		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sffp), sffp_pl);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int
+mlxsw_sp2_fids_init_flood_profile(struct mlxsw_sp *mlxsw_sp,
+				  const struct mlxsw_sp_fid_flood_profile *
+					flood_profile)
+{
+	int err;
+	int i;
+
+	err = mlxsw_sp_fid_check_flood_profile_id(mlxsw_sp,
+						  flood_profile->profile_id);
+	if (err)
+		return err;
+
+	for (i = 0; i < flood_profile->nr_flood_tables; i++) {
+		const struct mlxsw_sp_flood_table *flood_table;
+
+		flood_table = &flood_profile->flood_tables[i];
+		err = mlxsw_sp2_fids_init_flood_table(mlxsw_sp,
+						      flood_profile->profile_id,
+						      flood_table);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static const
+struct mlxsw_sp_fid_flood_profile *mlxsw_sp_fid_flood_profiles[] = {
+	&mlxsw_sp_fid_8021d_flood_profile,
+	&mlxsw_sp_fid_rsp_flood_profile_cff,
+	&mlxsw_sp_fid_nve_flood_profile_cff,
+};
+
+static int
+mlxsw_sp2_fids_init_flood_profiles(struct mlxsw_sp *mlxsw_sp)
+{
+	int err;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(mlxsw_sp_fid_flood_profiles); i++) {
+		const struct mlxsw_sp_fid_flood_profile *flood_profile;
+
+		flood_profile = mlxsw_sp_fid_flood_profiles[i];
+		err = mlxsw_sp2_fids_init_flood_profile(mlxsw_sp,
+							flood_profile);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int mlxsw_sp2_fids_init_ctl(struct mlxsw_sp *mlxsw_sp)
+{
+	return mlxsw_sp_fids_init(mlxsw_sp, mlxsw_sp2_fid_family_arr_ctl);
+}
+
+static int mlxsw_sp2_fids_init_cff(struct mlxsw_sp *mlxsw_sp)
+{
+	int err;
+
+	err = mlxsw_sp2_fids_init_flood_profiles(mlxsw_sp);
+	if (err)
+		return err;
+
+	return mlxsw_sp_fids_init(mlxsw_sp, mlxsw_sp2_fid_family_arr_cff);
+}
+
+static int mlxsw_sp2_fids_init(struct mlxsw_sp *mlxsw_sp)
+{
+	switch (mlxsw_core_flood_mode(mlxsw_sp->core)) {
+	case MLXSW_CMD_MBOX_CONFIG_PROFILE_FLOOD_MODE_CONTROLLED:
+		return mlxsw_sp2_fids_init_ctl(mlxsw_sp);
+	case MLXSW_CMD_MBOX_CONFIG_PROFILE_FLOOD_MODE_CFF:
+		return mlxsw_sp2_fids_init_cff(mlxsw_sp);
+	default:
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+}
+
+const struct mlxsw_sp_fid_core_ops mlxsw_sp2_fid_core_ops = {
+	.init = mlxsw_sp2_fids_init,
+	.fini = mlxsw_sp_fids_fini,
+};
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 82a95125d9ca..2c255ed9b8a9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -8419,6 +8419,9 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 	rif->ops = ops;
 	rif->rif_entries = rif_entries;
 
+	if (ops->setup)
+		ops->setup(rif, params);
+
 	if (ops->fid_get) {
 		fid = ops->fid_get(rif, params, extack);
 		if (IS_ERR(fid)) {
@@ -8428,9 +8431,6 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 		rif->fid = fid;
 	}
 
-	if (ops->setup)
-		ops->setup(rif, params);
-
 	err = ops->configure(rif, extack);
 	if (err)
 		goto err_configure;
@@ -8660,6 +8660,20 @@ mlxsw_sp_rif_subport_rif(const struct mlxsw_sp_rif *rif)
 	return container_of(rif, struct mlxsw_sp_rif_subport, common);
 }
 
+int mlxsw_sp_rif_subport_port(const struct mlxsw_sp_rif *rif,
+			      u16 *port, bool *is_lag)
+{
+	struct mlxsw_sp_rif_subport *rif_subport;
+
+	if (WARN_ON(rif->ops->type != MLXSW_SP_RIF_TYPE_SUBPORT))
+		return -EINVAL;
+
+	rif_subport = mlxsw_sp_rif_subport_rif(rif);
+	*is_lag = rif_subport->lag;
+	*port = *is_lag ? rif_subport->lag_id : rif_subport->system_port;
+	return 0;
+}
+
 static struct mlxsw_sp_rif *
 mlxsw_sp_rif_subport_get(struct mlxsw_sp *mlxsw_sp,
 			 const struct mlxsw_sp_rif_params *params,
diff --git a/drivers/net/ethernet/micrel/ks8851.h b/drivers/net/ethernet/micrel/ks8851.h
index fecd43754cea..e5ec0a363aff 100644
--- a/drivers/net/ethernet/micrel/ks8851.h
+++ b/drivers/net/ethernet/micrel/ks8851.h
@@ -350,6 +350,8 @@ union ks8851_tx_hdr {
  * @rxd: Space for receiving SPI data, in DMA-able space.
  * @txd: Space for transmitting SPI data, in DMA-able space.
  * @msg_enable: The message flags controlling driver output (see ethtool).
+ * @tx_space: Free space in the hardware TX buffer (cached copy of KS_TXMIR).
+ * @queued_len: Space required in hardware TX buffer for queued packets in txq.
  * @fid: Incrementing frame id tag.
  * @rc_ier: Cached copy of KS_IER.
  * @rc_ccr: Cached copy of KS_CCR.
@@ -399,6 +401,7 @@ struct ks8851_net {
 	struct work_struct	rxctrl_work;
 
 	struct sk_buff_head	txq;
+	unsigned int		queued_len;
 
 	struct eeprom_93cx6	eeprom;
 	struct regulator	*vdd_reg;
diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c
index cfbc900d4aeb..0bf13b38b8f5 100644
--- a/drivers/net/ethernet/micrel/ks8851_common.c
+++ b/drivers/net/ethernet/micrel/ks8851_common.c
@@ -362,16 +362,18 @@ static irqreturn_t ks8851_irq(int irq, void *_ks)
 		handled |= IRQ_RXPSI;
 
 	if (status & IRQ_TXI) {
-		handled |= IRQ_TXI;
+		unsigned short tx_space = ks8851_rdreg16(ks, KS_TXMIR);
 
-		/* no lock here, tx queue should have been stopped */
+		netif_dbg(ks, intr, ks->netdev,
+			  "%s: txspace %d\n", __func__, tx_space);
 
-		/* update our idea of how much tx space is available to the
-		 * system */
-		ks->tx_space = ks8851_rdreg16(ks, KS_TXMIR);
+		spin_lock(&ks->statelock);
+		ks->tx_space = tx_space;
+		if (netif_queue_stopped(ks->netdev))
+			netif_wake_queue(ks->netdev);
+		spin_unlock(&ks->statelock);
 
-		netif_dbg(ks, intr, ks->netdev,
-			  "%s: txspace %d\n", __func__, ks->tx_space);
+		handled |= IRQ_TXI;
 	}
 
 	if (status & IRQ_RXI)
@@ -414,9 +416,6 @@ static irqreturn_t ks8851_irq(int irq, void *_ks)
 	if (status & IRQ_LCI)
 		mii_check_link(&ks->mii);
 
-	if (status & IRQ_TXI)
-		netif_wake_queue(ks->netdev);
-
 	return IRQ_HANDLED;
 }
 
@@ -500,6 +499,7 @@ static int ks8851_net_open(struct net_device *dev)
 	ks8851_wrreg16(ks, KS_ISR, ks->rc_ier);
 	ks8851_wrreg16(ks, KS_IER, ks->rc_ier);
 
+	ks->queued_len = 0;
 	netif_start_queue(ks->netdev);
 
 	netif_dbg(ks, ifup, ks->netdev, "network device up\n");
diff --git a/drivers/net/ethernet/micrel/ks8851_spi.c b/drivers/net/ethernet/micrel/ks8851_spi.c
index 70bc7253454f..54f2eac11a63 100644
--- a/drivers/net/ethernet/micrel/ks8851_spi.c
+++ b/drivers/net/ethernet/micrel/ks8851_spi.c
@@ -156,7 +156,7 @@ static void ks8851_rdreg(struct ks8851_net *ks, unsigned int op,
 
 	txb[0] = cpu_to_le16(op | KS_SPIOP_RD);
 
-	if (kss->spidev->master->flags & SPI_MASTER_HALF_DUPLEX) {
+	if (kss->spidev->master->flags & SPI_CONTROLLER_HALF_DUPLEX) {
 		msg = &kss->spi_msg2;
 		xfer = kss->spi_xfer2;
 
@@ -180,7 +180,7 @@ static void ks8851_rdreg(struct ks8851_net *ks, unsigned int op,
 	ret = spi_sync(kss->spidev, msg);
 	if (ret < 0)
 		netdev_err(ks->netdev, "read: spi_sync() failed\n");
-	else if (kss->spidev->master->flags & SPI_MASTER_HALF_DUPLEX)
+	else if (kss->spidev->master->flags & SPI_CONTROLLER_HALF_DUPLEX)
 		memcpy(rxb, trx, rxl);
 	else
 		memcpy(rxb, trx + 2, rxl);
@@ -287,6 +287,18 @@ static void ks8851_wrfifo_spi(struct ks8851_net *ks, struct sk_buff *txp,
 }
 
 /**
+ * calc_txlen - calculate size of message to send packet
+ * @len: Length of data
+ *
+ * Returns the size of the TXFIFO message needed to send
+ * this packet.
+ */
+static unsigned int calc_txlen(unsigned int len)
+{
+	return ALIGN(len + 4, 4);
+}
+
+/**
  * ks8851_rx_skb_spi - receive skbuff
  * @ks: The device state
  * @skb: The skbuff
@@ -305,7 +317,9 @@ static void ks8851_rx_skb_spi(struct ks8851_net *ks, struct sk_buff *skb)
  */
 static void ks8851_tx_work(struct work_struct *work)
 {
+	unsigned int dequeued_len = 0;
 	struct ks8851_net_spi *kss;
+	unsigned short tx_space;
 	struct ks8851_net *ks;
 	unsigned long flags;
 	struct sk_buff *txb;
@@ -322,6 +336,8 @@ static void ks8851_tx_work(struct work_struct *work)
 		last = skb_queue_empty(&ks->txq);
 
 		if (txb) {
+			dequeued_len += calc_txlen(txb->len);
+
 			ks8851_wrreg16_spi(ks, KS_RXQCR,
 					   ks->rc_rxqcr | RXQCR_SDA);
 			ks8851_wrfifo_spi(ks, txb, last);
@@ -332,6 +348,13 @@ static void ks8851_tx_work(struct work_struct *work)
 		}
 	}
 
+	tx_space = ks8851_rdreg16_spi(ks, KS_TXMIR);
+
+	spin_lock(&ks->statelock);
+	ks->queued_len -= dequeued_len;
+	ks->tx_space = tx_space;
+	spin_unlock(&ks->statelock);
+
 	ks8851_unlock_spi(ks, &flags);
 }
 
@@ -347,18 +370,6 @@ static void ks8851_flush_tx_work_spi(struct ks8851_net *ks)
 }
 
 /**
- * calc_txlen - calculate size of message to send packet
- * @len: Length of data
- *
- * Returns the size of the TXFIFO message needed to send
- * this packet.
- */
-static unsigned int calc_txlen(unsigned int len)
-{
-	return ALIGN(len + 4, 4);
-}
-
-/**
  * ks8851_start_xmit_spi - transmit packet using SPI
  * @skb: The buffer to transmit
  * @dev: The device used to transmit the packet.
@@ -386,16 +397,17 @@ static netdev_tx_t ks8851_start_xmit_spi(struct sk_buff *skb,
 
 	spin_lock(&ks->statelock);
 
-	if (needed > ks->tx_space) {
+	if (ks->queued_len + needed > ks->tx_space) {
 		netif_stop_queue(dev);
 		ret = NETDEV_TX_BUSY;
 	} else {
-		ks->tx_space -= needed;
+		ks->queued_len += needed;
 		skb_queue_tail(&ks->txq, skb);
 	}
 
 	spin_unlock(&ks->statelock);
-	schedule_work(&kss->tx_work);
+	if (ret == NETDEV_TX_OK)
+		schedule_work(&kss->tx_work);
 
 	return ret;
 }
diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c
index 6961cfc55fb9..a2b3f4433ca8 100644
--- a/drivers/net/ethernet/microchip/lan743x_ethtool.c
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c
@@ -934,11 +934,11 @@ static u32 lan743x_ethtool_get_rxfh_indir_size(struct net_device *netdev)
 }
 
 static int lan743x_ethtool_get_rxfh(struct net_device *netdev,
-				    u32 *indir, u8 *key, u8 *hfunc)
+				    struct ethtool_rxfh_param *rxfh)
 {
 	struct lan743x_adapter *adapter = netdev_priv(netdev);
 
-	if (indir) {
+	if (rxfh->indir) {
 		int dw_index;
 		int byte_index = 0;
 
@@ -947,17 +947,17 @@ static int lan743x_ethtool_get_rxfh(struct net_device *netdev,
 				lan743x_csr_read(adapter, RFE_INDX(dw_index));
 
 			byte_index = dw_index << 2;
-			indir[byte_index + 0] =
+			rxfh->indir[byte_index + 0] =
 				((four_entries >> 0) & 0x000000FF);
-			indir[byte_index + 1] =
+			rxfh->indir[byte_index + 1] =
 				((four_entries >> 8) & 0x000000FF);
-			indir[byte_index + 2] =
+			rxfh->indir[byte_index + 2] =
 				((four_entries >> 16) & 0x000000FF);
-			indir[byte_index + 3] =
+			rxfh->indir[byte_index + 3] =
 				((four_entries >> 24) & 0x000000FF);
 		}
 	}
-	if (key) {
+	if (rxfh->key) {
 		int dword_index;
 		int byte_index = 0;
 
@@ -967,28 +967,30 @@ static int lan743x_ethtool_get_rxfh(struct net_device *netdev,
 						 RFE_HASH_KEY(dword_index));
 
 			byte_index = dword_index << 2;
-			key[byte_index + 0] =
+			rxfh->key[byte_index + 0] =
 				((four_entries >> 0) & 0x000000FF);
-			key[byte_index + 1] =
+			rxfh->key[byte_index + 1] =
 				((four_entries >> 8) & 0x000000FF);
-			key[byte_index + 2] =
+			rxfh->key[byte_index + 2] =
 				((four_entries >> 16) & 0x000000FF);
-			key[byte_index + 3] =
+			rxfh->key[byte_index + 3] =
 				((four_entries >> 24) & 0x000000FF);
 		}
 	}
-	if (hfunc)
-		(*hfunc) = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 	return 0;
 }
 
 static int lan743x_ethtool_set_rxfh(struct net_device *netdev,
-				    const u32 *indir, const u8 *key,
-				    const u8 hfunc)
+				    struct ethtool_rxfh_param *rxfh,
+				    struct netlink_ext_ack *extack)
 {
 	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	u32 *indir = rxfh->indir;
+	u8 *key = rxfh->key;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
 	if (indir) {
@@ -1075,7 +1077,6 @@ static int lan743x_ethtool_get_eee(struct net_device *netdev,
 	buf = lan743x_csr_read(adapter, MAC_CR);
 	if (buf & MAC_CR_EEE_EN_) {
 		eee->eee_enabled = true;
-		eee->eee_active = !!(eee->advertised & eee->lp_advertised);
 		eee->tx_lpi_enabled = true;
 		/* EEE_TX_LPI_REQ_DLY & tx_lpi_timer are same uSec unit */
 		buf = lan743x_csr_read(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT);
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index b648461787d2..be79cb0ae5af 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -1075,7 +1075,7 @@ struct lan743x_adapter {
 #define DMA_DESCRIPTOR_SPACING_32       (32)
 #define DMA_DESCRIPTOR_SPACING_64       (64)
 #define DMA_DESCRIPTOR_SPACING_128      (128)
-#define DEFAULT_DMA_DESCRIPTOR_SPACING  (L1_CACHE_BYTES)
+#define DEFAULT_DMA_DESCRIPTOR_SPACING  (DMA_DESCRIPTOR_SPACING_16)
 
 #define DMAC_CHANNEL_STATE_SET(start_bit, stop_bit) \
 	(((start_bit) ? 2 : 0) | ((stop_bit) ? 1 : 0))
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_ethtool.c b/drivers/net/ethernet/microchip/sparx5/sparx5_ethtool.c
index 37d2584b48a7..a06dc5a9b355 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_ethtool.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_ethtool.c
@@ -1012,7 +1012,7 @@ static void sparx5_get_sset_strings(struct net_device *ndev, u32 sset, u8 *data)
 		return;
 
 	for (idx = 0; idx < sparx5->num_ethtool_stats; idx++)
-		ethtool_sprintf(&data, "%s", sparx5->stats_layout[idx]);
+		ethtool_puts(&data, sparx5->stats_layout[idx]);
 }
 
 static void sparx5_get_sset_data(struct net_device *ndev,
diff --git a/drivers/net/ethernet/microsoft/Kconfig b/drivers/net/ethernet/microsoft/Kconfig
index 090e6b983243..01eb7445ead9 100644
--- a/drivers/net/ethernet/microsoft/Kconfig
+++ b/drivers/net/ethernet/microsoft/Kconfig
@@ -20,6 +20,7 @@ config MICROSOFT_MANA
 	depends on PCI_MSI && X86_64
 	depends on PCI_HYPERV
 	select AUXILIARY_BUS
+	select PAGE_POOL
 	help
 	  This driver supports Microsoft Azure Network Adapter (MANA).
 	  So far, the driver is only supported on X86_64.
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 6367de0c2c2e..a6863011d682 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -414,8 +414,12 @@ static void mana_gd_process_eq_events(void *arg)
 
 		old_bits = (eq->head / num_eqe - 1) & GDMA_EQE_OWNER_MASK;
 		/* No more entries */
-		if (owner_bits == old_bits)
+		if (owner_bits == old_bits) {
+			/* return here without ringing the doorbell */
+			if (i == 0)
+				return;
 			break;
+		}
 
 		new_bits = (eq->head / num_eqe) & GDMA_EQE_OWNER_MASK;
 		if (owner_bits != new_bits) {
@@ -445,42 +449,29 @@ static int mana_gd_register_irq(struct gdma_queue *queue,
 	struct gdma_dev *gd = queue->gdma_dev;
 	struct gdma_irq_context *gic;
 	struct gdma_context *gc;
-	struct gdma_resource *r;
 	unsigned int msi_index;
 	unsigned long flags;
 	struct device *dev;
 	int err = 0;
 
 	gc = gd->gdma_context;
-	r = &gc->msix_resource;
 	dev = gc->dev;
+	msi_index = spec->eq.msix_index;
 
-	spin_lock_irqsave(&r->lock, flags);
-
-	msi_index = find_first_zero_bit(r->map, r->size);
-	if (msi_index >= r->size || msi_index >= gc->num_msix_usable) {
+	if (msi_index >= gc->num_msix_usable) {
 		err = -ENOSPC;
-	} else {
-		bitmap_set(r->map, msi_index, 1);
-		queue->eq.msix_index = msi_index;
-	}
-
-	spin_unlock_irqrestore(&r->lock, flags);
-
-	if (err) {
-		dev_err(dev, "Register IRQ err:%d, msi:%u rsize:%u, nMSI:%u",
-			err, msi_index, r->size, gc->num_msix_usable);
+		dev_err(dev, "Register IRQ err:%d, msi:%u nMSI:%u",
+			err, msi_index, gc->num_msix_usable);
 
 		return err;
 	}
 
+	queue->eq.msix_index = msi_index;
 	gic = &gc->irq_contexts[msi_index];
 
-	WARN_ON(gic->handler || gic->arg);
-
-	gic->arg = queue;
-
-	gic->handler = mana_gd_process_eq_events;
+	spin_lock_irqsave(&gic->lock, flags);
+	list_add_rcu(&queue->entry, &gic->eq_list);
+	spin_unlock_irqrestore(&gic->lock, flags);
 
 	return 0;
 }
@@ -490,12 +481,11 @@ static void mana_gd_deregiser_irq(struct gdma_queue *queue)
 	struct gdma_dev *gd = queue->gdma_dev;
 	struct gdma_irq_context *gic;
 	struct gdma_context *gc;
-	struct gdma_resource *r;
 	unsigned int msix_index;
 	unsigned long flags;
+	struct gdma_queue *eq;
 
 	gc = gd->gdma_context;
-	r = &gc->msix_resource;
 
 	/* At most num_online_cpus() + 1 interrupts are used. */
 	msix_index = queue->eq.msix_index;
@@ -503,14 +493,17 @@ static void mana_gd_deregiser_irq(struct gdma_queue *queue)
 		return;
 
 	gic = &gc->irq_contexts[msix_index];
-	gic->handler = NULL;
-	gic->arg = NULL;
-
-	spin_lock_irqsave(&r->lock, flags);
-	bitmap_clear(r->map, msix_index, 1);
-	spin_unlock_irqrestore(&r->lock, flags);
+	spin_lock_irqsave(&gic->lock, flags);
+	list_for_each_entry_rcu(eq, &gic->eq_list, entry) {
+		if (queue == eq) {
+			list_del_rcu(&eq->entry);
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&gic->lock, flags);
 
 	queue->eq.msix_index = INVALID_PCI_MSIX_INDEX;
+	synchronize_rcu();
 }
 
 int mana_gd_test_eq(struct gdma_context *gc, struct gdma_queue *eq)
@@ -588,6 +581,7 @@ static int mana_gd_create_eq(struct gdma_dev *gd,
 	int err;
 
 	queue->eq.msix_index = INVALID_PCI_MSIX_INDEX;
+	queue->id = INVALID_QUEUE_ID;
 
 	log2_num_entries = ilog2(queue->queue_size / GDMA_EQE_SIZE);
 
@@ -819,6 +813,7 @@ free_q:
 	kfree(queue);
 	return err;
 }
+EXPORT_SYMBOL_NS(mana_gd_create_mana_eq, NET_MANA);
 
 int mana_gd_create_mana_wq_cq(struct gdma_dev *gd,
 			      const struct gdma_queue_spec *spec,
@@ -895,6 +890,7 @@ void mana_gd_destroy_queue(struct gdma_context *gc, struct gdma_queue *queue)
 	mana_gd_free_memory(gmi);
 	kfree(queue);
 }
+EXPORT_SYMBOL_NS(mana_gd_destroy_queue, NET_MANA);
 
 int mana_gd_verify_vf_version(struct pci_dev *pdev)
 {
@@ -1217,9 +1213,14 @@ int mana_gd_poll_cq(struct gdma_queue *cq, struct gdma_comp *comp, int num_cqe)
 static irqreturn_t mana_gd_intr(int irq, void *arg)
 {
 	struct gdma_irq_context *gic = arg;
+	struct list_head *eq_list = &gic->eq_list;
+	struct gdma_queue *eq;
 
-	if (gic->handler)
-		gic->handler(gic->arg);
+	rcu_read_lock();
+	list_for_each_entry_rcu(eq, eq_list, entry) {
+		gic->handler(eq);
+	}
+	rcu_read_unlock();
 
 	return IRQ_HANDLED;
 }
@@ -1271,8 +1272,9 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev)
 
 	for (i = 0; i < nvec; i++) {
 		gic = &gc->irq_contexts[i];
-		gic->handler = NULL;
-		gic->arg = NULL;
+		gic->handler = mana_gd_process_eq_events;
+		INIT_LIST_HEAD(&gic->eq_list);
+		spin_lock_init(&gic->lock);
 
 		if (!i)
 			snprintf(gic->name, MANA_IRQ_NAME_SZ, "mana_hwc@pci:%s",
@@ -1295,10 +1297,6 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev)
 		irq_set_affinity_and_hint(irq, cpumask_of(cpu));
 	}
 
-	err = mana_gd_alloc_res_map(nvec, &gc->msix_resource);
-	if (err)
-		goto free_irq;
-
 	gc->max_num_msix = nvec;
 	gc->num_msix_usable = nvec;
 
@@ -1329,8 +1327,6 @@ static void mana_gd_remove_irqs(struct pci_dev *pdev)
 	if (gc->max_num_msix < 1)
 		return;
 
-	mana_gd_free_res_map(&gc->msix_resource);
-
 	for (i = 0; i < gc->max_num_msix; i++) {
 		irq = pci_irq_vector(pdev, i);
 		if (irq < 0)
diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c
index 9d1cd3bfcf66..2729a2c5acf9 100644
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@@ -300,6 +300,7 @@ static int mana_hwc_create_gdma_eq(struct hw_channel_context *hwc,
 	spec.eq.context = ctx;
 	spec.eq.callback = cb;
 	spec.eq.log2_throttle_limit = DEFAULT_LOG2_THROTTLING_FOR_ERROR_EQ;
+	spec.eq.msix_index = 0;
 
 	return mana_gd_create_hwc_queue(hwc->gdma_dev, &spec, queue);
 }
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index fc3d2903a80f..59287c6e6cee 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1244,6 +1244,7 @@ static int mana_create_eq(struct mana_context *ac)
 	spec.eq.log2_throttle_limit = LOG2_EQ_THROTTLE;
 
 	for (i = 0; i < gc->max_num_queues; i++) {
+		spec.eq.msix_index = (i + 1) % gc->num_msix_usable;
 		err = mana_gd_create_mana_eq(gd, &spec, &ac->eqs[i].eq);
 		if (err)
 			goto out;
@@ -2137,6 +2138,7 @@ static int mana_create_page_pool(struct mana_rxq *rxq, struct gdma_context *gc)
 	pprm.pool_size = RX_BUFFERS_PER_QUEUE;
 	pprm.nid = gc->numa_node;
 	pprm.napi = &rxq->rx_cq.napi;
+	pprm.netdev = rxq->ndev;
 
 	rxq->page_pool = page_pool_create(&pprm);
 
@@ -2385,13 +2387,33 @@ void mana_query_gf_stats(struct mana_port_context *apc)
 
 	mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_GF_STAT,
 			     sizeof(req), sizeof(resp));
-	req.req_stats = STATISTICS_FLAGS_HC_TX_BYTES |
+	req.req_stats = STATISTICS_FLAGS_RX_DISCARDS_NO_WQE |
+			STATISTICS_FLAGS_RX_ERRORS_VPORT_DISABLED |
+			STATISTICS_FLAGS_HC_RX_BYTES |
+			STATISTICS_FLAGS_HC_RX_UCAST_PACKETS |
+			STATISTICS_FLAGS_HC_RX_UCAST_BYTES |
+			STATISTICS_FLAGS_HC_RX_MCAST_PACKETS |
+			STATISTICS_FLAGS_HC_RX_MCAST_BYTES |
+			STATISTICS_FLAGS_HC_RX_BCAST_PACKETS |
+			STATISTICS_FLAGS_HC_RX_BCAST_BYTES |
+			STATISTICS_FLAGS_TX_ERRORS_GF_DISABLED |
+			STATISTICS_FLAGS_TX_ERRORS_VPORT_DISABLED |
+			STATISTICS_FLAGS_TX_ERRORS_INVAL_VPORT_OFFSET_PACKETS |
+			STATISTICS_FLAGS_TX_ERRORS_VLAN_ENFORCEMENT |
+			STATISTICS_FLAGS_TX_ERRORS_ETH_TYPE_ENFORCEMENT |
+			STATISTICS_FLAGS_TX_ERRORS_SA_ENFORCEMENT |
+			STATISTICS_FLAGS_TX_ERRORS_SQPDID_ENFORCEMENT |
+			STATISTICS_FLAGS_TX_ERRORS_CQPDID_ENFORCEMENT |
+			STATISTICS_FLAGS_TX_ERRORS_MTU_VIOLATION |
+			STATISTICS_FLAGS_TX_ERRORS_INVALID_OOB |
+			STATISTICS_FLAGS_HC_TX_BYTES |
 			STATISTICS_FLAGS_HC_TX_UCAST_PACKETS |
 			STATISTICS_FLAGS_HC_TX_UCAST_BYTES |
 			STATISTICS_FLAGS_HC_TX_MCAST_PACKETS |
 			STATISTICS_FLAGS_HC_TX_MCAST_BYTES |
 			STATISTICS_FLAGS_HC_TX_BCAST_PACKETS |
-			STATISTICS_FLAGS_HC_TX_BCAST_BYTES;
+			STATISTICS_FLAGS_HC_TX_BCAST_BYTES |
+			STATISTICS_FLAGS_TX_ERRORS_GDMA_ERROR;
 
 	err = mana_send_request(apc->ac, &req, sizeof(req), &resp,
 				sizeof(resp));
@@ -2407,6 +2429,30 @@ void mana_query_gf_stats(struct mana_port_context *apc)
 		return;
 	}
 
+	apc->eth_stats.hc_rx_discards_no_wqe = resp.rx_discards_nowqe;
+	apc->eth_stats.hc_rx_err_vport_disabled = resp.rx_err_vport_disabled;
+	apc->eth_stats.hc_rx_bytes = resp.hc_rx_bytes;
+	apc->eth_stats.hc_rx_ucast_pkts = resp.hc_rx_ucast_pkts;
+	apc->eth_stats.hc_rx_ucast_bytes = resp.hc_rx_ucast_bytes;
+	apc->eth_stats.hc_rx_bcast_pkts = resp.hc_rx_bcast_pkts;
+	apc->eth_stats.hc_rx_bcast_bytes = resp.hc_rx_bcast_bytes;
+	apc->eth_stats.hc_rx_mcast_pkts = resp.hc_rx_mcast_pkts;
+	apc->eth_stats.hc_rx_mcast_bytes = resp.hc_rx_mcast_bytes;
+	apc->eth_stats.hc_tx_err_gf_disabled = resp.tx_err_gf_disabled;
+	apc->eth_stats.hc_tx_err_vport_disabled = resp.tx_err_vport_disabled;
+	apc->eth_stats.hc_tx_err_inval_vportoffset_pkt =
+					     resp.tx_err_inval_vport_offset_pkt;
+	apc->eth_stats.hc_tx_err_vlan_enforcement =
+					     resp.tx_err_vlan_enforcement;
+	apc->eth_stats.hc_tx_err_eth_type_enforcement =
+					     resp.tx_err_ethtype_enforcement;
+	apc->eth_stats.hc_tx_err_sa_enforcement = resp.tx_err_SA_enforcement;
+	apc->eth_stats.hc_tx_err_sqpdid_enforcement =
+					     resp.tx_err_SQPDID_enforcement;
+	apc->eth_stats.hc_tx_err_cqpdid_enforcement =
+					     resp.tx_err_CQPDID_enforcement;
+	apc->eth_stats.hc_tx_err_mtu_violation = resp.tx_err_mtu_violation;
+	apc->eth_stats.hc_tx_err_inval_oob = resp.tx_err_inval_oob;
 	apc->eth_stats.hc_tx_bytes = resp.hc_tx_bytes;
 	apc->eth_stats.hc_tx_ucast_pkts = resp.hc_tx_ucast_pkts;
 	apc->eth_stats.hc_tx_ucast_bytes = resp.hc_tx_ucast_bytes;
@@ -2414,6 +2460,7 @@ void mana_query_gf_stats(struct mana_port_context *apc)
 	apc->eth_stats.hc_tx_bcast_bytes = resp.hc_tx_bcast_bytes;
 	apc->eth_stats.hc_tx_mcast_pkts = resp.hc_tx_mcast_pkts;
 	apc->eth_stats.hc_tx_mcast_bytes = resp.hc_tx_mcast_bytes;
+	apc->eth_stats.hc_tx_err_gdma = resp.tx_err_gdma;
 }
 
 static int mana_init_port(struct net_device *ndev)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index 607150165ab4..ab2413d71f6c 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -13,6 +13,46 @@ static const struct {
 } mana_eth_stats[] = {
 	{"stop_queue", offsetof(struct mana_ethtool_stats, stop_queue)},
 	{"wake_queue", offsetof(struct mana_ethtool_stats, wake_queue)},
+	{"hc_rx_discards_no_wqe", offsetof(struct mana_ethtool_stats,
+					   hc_rx_discards_no_wqe)},
+	{"hc_rx_err_vport_disabled", offsetof(struct mana_ethtool_stats,
+					      hc_rx_err_vport_disabled)},
+	{"hc_rx_bytes", offsetof(struct mana_ethtool_stats, hc_rx_bytes)},
+	{"hc_rx_ucast_pkts", offsetof(struct mana_ethtool_stats,
+				      hc_rx_ucast_pkts)},
+	{"hc_rx_ucast_bytes", offsetof(struct mana_ethtool_stats,
+				       hc_rx_ucast_bytes)},
+	{"hc_rx_bcast_pkts", offsetof(struct mana_ethtool_stats,
+				      hc_rx_bcast_pkts)},
+	{"hc_rx_bcast_bytes", offsetof(struct mana_ethtool_stats,
+				       hc_rx_bcast_bytes)},
+	{"hc_rx_mcast_pkts", offsetof(struct mana_ethtool_stats,
+			hc_rx_mcast_pkts)},
+	{"hc_rx_mcast_bytes", offsetof(struct mana_ethtool_stats,
+				       hc_rx_mcast_bytes)},
+	{"hc_tx_err_gf_disabled", offsetof(struct mana_ethtool_stats,
+					   hc_tx_err_gf_disabled)},
+	{"hc_tx_err_vport_disabled", offsetof(struct mana_ethtool_stats,
+					      hc_tx_err_vport_disabled)},
+	{"hc_tx_err_inval_vportoffset_pkt",
+	 offsetof(struct mana_ethtool_stats,
+		  hc_tx_err_inval_vportoffset_pkt)},
+	{"hc_tx_err_vlan_enforcement", offsetof(struct mana_ethtool_stats,
+						hc_tx_err_vlan_enforcement)},
+	{"hc_tx_err_eth_type_enforcement",
+	 offsetof(struct mana_ethtool_stats, hc_tx_err_eth_type_enforcement)},
+	{"hc_tx_err_sa_enforcement", offsetof(struct mana_ethtool_stats,
+					      hc_tx_err_sa_enforcement)},
+	{"hc_tx_err_sqpdid_enforcement",
+	 offsetof(struct mana_ethtool_stats, hc_tx_err_sqpdid_enforcement)},
+	{"hc_tx_err_cqpdid_enforcement",
+	 offsetof(struct mana_ethtool_stats, hc_tx_err_cqpdid_enforcement)},
+	{"hc_tx_err_mtu_violation", offsetof(struct mana_ethtool_stats,
+					     hc_tx_err_mtu_violation)},
+	{"hc_tx_err_inval_oob", offsetof(struct mana_ethtool_stats,
+					 hc_tx_err_inval_oob)},
+	{"hc_tx_err_gdma", offsetof(struct mana_ethtool_stats,
+				    hc_tx_err_gdma)},
 	{"hc_tx_bytes", offsetof(struct mana_ethtool_stats, hc_tx_bytes)},
 	{"hc_tx_ucast_pkts", offsetof(struct mana_ethtool_stats,
 					hc_tx_ucast_pkts)},
@@ -208,28 +248,28 @@ static u32 mana_rss_indir_size(struct net_device *ndev)
 	return MANA_INDIRECT_TABLE_SIZE;
 }
 
-static int mana_get_rxfh(struct net_device *ndev, u32 *indir, u8 *key,
-			 u8 *hfunc)
+static int mana_get_rxfh(struct net_device *ndev,
+			 struct ethtool_rxfh_param *rxfh)
 {
 	struct mana_port_context *apc = netdev_priv(ndev);
 	int i;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP; /* Toeplitz */
+	rxfh->hfunc = ETH_RSS_HASH_TOP; /* Toeplitz */
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < MANA_INDIRECT_TABLE_SIZE; i++)
-			indir[i] = apc->indir_table[i];
+			rxfh->indir[i] = apc->indir_table[i];
 	}
 
-	if (key)
-		memcpy(key, apc->hashkey, MANA_HASH_KEY_SIZE);
+	if (rxfh->key)
+		memcpy(rxfh->key, apc->hashkey, MANA_HASH_KEY_SIZE);
 
 	return 0;
 }
 
-static int mana_set_rxfh(struct net_device *ndev, const u32 *indir,
-			 const u8 *key, const u8 hfunc)
+static int mana_set_rxfh(struct net_device *ndev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
 	struct mana_port_context *apc = netdev_priv(ndev);
 	bool update_hash = false, update_table = false;
@@ -240,25 +280,26 @@ static int mana_set_rxfh(struct net_device *ndev, const u32 *indir,
 	if (!apc->port_is_up)
 		return -EOPNOTSUPP;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < MANA_INDIRECT_TABLE_SIZE; i++)
-			if (indir[i] >= apc->num_queues)
+			if (rxfh->indir[i] >= apc->num_queues)
 				return -EINVAL;
 
 		update_table = true;
 		for (i = 0; i < MANA_INDIRECT_TABLE_SIZE; i++) {
 			save_table[i] = apc->indir_table[i];
-			apc->indir_table[i] = indir[i];
+			apc->indir_table[i] = rxfh->indir[i];
 		}
 	}
 
-	if (key) {
+	if (rxfh->key) {
 		update_hash = true;
 		memcpy(save_key, apc->hashkey, MANA_HASH_KEY_SIZE);
-		memcpy(apc->hashkey, key, MANA_HASH_KEY_SIZE);
+		memcpy(apc->hashkey, rxfh->key, MANA_HASH_KEY_SIZE);
 	}
 
 	err = mana_config_rss(apc, TRI_STATE_TRUE, update_hash, update_table);
diff --git a/drivers/net/ethernet/mscc/ocelot_stats.c b/drivers/net/ethernet/mscc/ocelot_stats.c
index 5c55197c7327..c018783757fb 100644
--- a/drivers/net/ethernet/mscc/ocelot_stats.c
+++ b/drivers/net/ethernet/mscc/ocelot_stats.c
@@ -582,10 +582,10 @@ static void ocelot_port_rmon_stats_cb(struct ocelot *ocelot, int port, void *pri
 	rmon_stats->hist_tx[0] = s[OCELOT_STAT_TX_64];
 	rmon_stats->hist_tx[1] = s[OCELOT_STAT_TX_65_127];
 	rmon_stats->hist_tx[2] = s[OCELOT_STAT_TX_128_255];
-	rmon_stats->hist_tx[3] = s[OCELOT_STAT_TX_128_255];
-	rmon_stats->hist_tx[4] = s[OCELOT_STAT_TX_256_511];
-	rmon_stats->hist_tx[5] = s[OCELOT_STAT_TX_512_1023];
-	rmon_stats->hist_tx[6] = s[OCELOT_STAT_TX_1024_1526];
+	rmon_stats->hist_tx[3] = s[OCELOT_STAT_TX_256_511];
+	rmon_stats->hist_tx[4] = s[OCELOT_STAT_TX_512_1023];
+	rmon_stats->hist_tx[5] = s[OCELOT_STAT_TX_1024_1526];
+	rmon_stats->hist_tx[6] = s[OCELOT_STAT_TX_1527_MAX];
 }
 
 static void ocelot_port_pmac_rmon_stats_cb(struct ocelot *ocelot, int port,
@@ -610,10 +610,10 @@ static void ocelot_port_pmac_rmon_stats_cb(struct ocelot *ocelot, int port,
 	rmon_stats->hist_tx[0] = s[OCELOT_STAT_TX_PMAC_64];
 	rmon_stats->hist_tx[1] = s[OCELOT_STAT_TX_PMAC_65_127];
 	rmon_stats->hist_tx[2] = s[OCELOT_STAT_TX_PMAC_128_255];
-	rmon_stats->hist_tx[3] = s[OCELOT_STAT_TX_PMAC_128_255];
-	rmon_stats->hist_tx[4] = s[OCELOT_STAT_TX_PMAC_256_511];
-	rmon_stats->hist_tx[5] = s[OCELOT_STAT_TX_PMAC_512_1023];
-	rmon_stats->hist_tx[6] = s[OCELOT_STAT_TX_PMAC_1024_1526];
+	rmon_stats->hist_tx[3] = s[OCELOT_STAT_TX_PMAC_256_511];
+	rmon_stats->hist_tx[4] = s[OCELOT_STAT_TX_PMAC_512_1023];
+	rmon_stats->hist_tx[5] = s[OCELOT_STAT_TX_PMAC_1024_1526];
+	rmon_stats->hist_tx[6] = s[OCELOT_STAT_TX_PMAC_1527_MAX];
 }
 
 void ocelot_port_get_rmon_stats(struct ocelot *ocelot, int port,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
index 88d6d992e7d0..361d7c495e2d 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
@@ -76,7 +76,7 @@ struct nfp_fl_lag_group {
 /* Use this ID with zero members to ack a batch config */
 #define NFP_FL_LAG_SYNC_ID		0
 #define NFP_FL_LAG_GROUP_MIN		1 /* ID 0 reserved */
-#define NFP_FL_LAG_GROUP_MAX		32 /* IDs 1 to 31 are valid */
+#define NFP_FL_LAG_GROUP_MAX		31 /* IDs 1 to 31 are valid */
 
 /* wait for more config */
 #define NFP_FL_LAG_DELAY		(msecs_to_jiffies(2))
@@ -111,8 +111,8 @@ nfp_fl_lag_group_create(struct nfp_fl_lag *lag, struct net_device *master)
 
 	priv = container_of(lag, struct nfp_flower_priv, nfp_lag);
 
-	id = ida_simple_get(&lag->ida_handle, NFP_FL_LAG_GROUP_MIN,
-			    NFP_FL_LAG_GROUP_MAX, GFP_KERNEL);
+	id = ida_alloc_range(&lag->ida_handle, NFP_FL_LAG_GROUP_MIN,
+			     NFP_FL_LAG_GROUP_MAX, GFP_KERNEL);
 	if (id < 0) {
 		nfp_flower_cmsg_warn(priv->app,
 				     "No more bonding groups available\n");
@@ -121,7 +121,7 @@ nfp_fl_lag_group_create(struct nfp_fl_lag *lag, struct net_device *master)
 
 	group = kmalloc(sizeof(*group), GFP_KERNEL);
 	if (!group) {
-		ida_simple_remove(&lag->ida_handle, id);
+		ida_free(&lag->ida_handle, id);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -328,8 +328,7 @@ static void nfp_fl_lag_do_work(struct work_struct *work)
 			}
 
 			if (entry->to_destroy) {
-				ida_simple_remove(&lag->ida_handle,
-						  entry->group_id);
+				ida_free(&lag->ida_handle, entry->group_id);
 				list_del(&entry->list);
 				kfree(entry);
 			}
@@ -415,7 +414,7 @@ nfp_fl_lag_put_unprocessed(struct nfp_fl_lag *lag, struct sk_buff *skb)
 	struct nfp_flower_cmsg_lag_config *cmsg_payload;
 
 	cmsg_payload = nfp_flower_cmsg_get_data(skb);
-	if (be32_to_cpu(cmsg_payload->group_id) >= NFP_FL_LAG_GROUP_MAX)
+	if (be32_to_cpu(cmsg_payload->group_id) > NFP_FL_LAG_GROUP_MAX)
 		return -EINVAL;
 
 	/* Drop cmsg retrans if storage limit is exceeded to prevent
diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
index 060a77f2265d..e522845c7c21 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -160,6 +160,18 @@ struct nfp_tun_mac_addr_offload {
 	u8 addr[ETH_ALEN];
 };
 
+/**
+ * struct nfp_neigh_update_work - update neighbour information to nfp
+ * @work:	Work queue for writing neigh to the nfp
+ * @n:		neighbour entry
+ * @app:	Back pointer to app
+ */
+struct nfp_neigh_update_work {
+	struct work_struct work;
+	struct neighbour *n;
+	struct nfp_app *app;
+};
+
 enum nfp_flower_mac_offload_cmd {
 	NFP_TUNNEL_MAC_OFFLOAD_ADD =		0,
 	NFP_TUNNEL_MAC_OFFLOAD_DEL =		1,
@@ -607,38 +619,30 @@ err:
 	nfp_flower_cmsg_warn(app, "Neighbour configuration failed.\n");
 }
 
-static int
-nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event,
-			    void *ptr)
+static void
+nfp_tun_release_neigh_update_work(struct nfp_neigh_update_work *update_work)
 {
-	struct nfp_flower_priv *app_priv;
-	struct netevent_redirect *redir;
-	struct neighbour *n;
+	neigh_release(update_work->n);
+	kfree(update_work);
+}
+
+static void nfp_tun_neigh_update(struct work_struct *work)
+{
+	struct nfp_neigh_update_work *update_work;
 	struct nfp_app *app;
+	struct neighbour *n;
 	bool neigh_invalid;
 	int err;
 
-	switch (event) {
-	case NETEVENT_REDIRECT:
-		redir = (struct netevent_redirect *)ptr;
-		n = redir->neigh;
-		break;
-	case NETEVENT_NEIGH_UPDATE:
-		n = (struct neighbour *)ptr;
-		break;
-	default:
-		return NOTIFY_DONE;
-	}
-
-	neigh_invalid = !(n->nud_state & NUD_VALID) || n->dead;
-
-	app_priv = container_of(nb, struct nfp_flower_priv, tun.neigh_nb);
-	app = app_priv->app;
+	update_work = container_of(work, struct nfp_neigh_update_work, work);
+	app = update_work->app;
+	n = update_work->n;
 
 	if (!nfp_flower_get_port_id_from_netdev(app, n->dev))
-		return NOTIFY_DONE;
+		goto out;
 
 #if IS_ENABLED(CONFIG_INET)
+	neigh_invalid = !(n->nud_state & NUD_VALID) || n->dead;
 	if (n->tbl->family == AF_INET6) {
 #if IS_ENABLED(CONFIG_IPV6)
 		struct flowi6 flow6 = {};
@@ -655,13 +659,11 @@ nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event,
 			dst = ip6_dst_lookup_flow(dev_net(n->dev), NULL,
 						  &flow6, NULL);
 			if (IS_ERR(dst))
-				return NOTIFY_DONE;
+				goto out;
 
 			dst_release(dst);
 		}
 		nfp_tun_write_neigh(n->dev, app, &flow6, n, true, false);
-#else
-		return NOTIFY_DONE;
 #endif /* CONFIG_IPV6 */
 	} else {
 		struct flowi4 flow4 = {};
@@ -678,17 +680,71 @@ nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event,
 			rt = ip_route_output_key(dev_net(n->dev), &flow4);
 			err = PTR_ERR_OR_ZERO(rt);
 			if (err)
-				return NOTIFY_DONE;
+				goto out;
 
 			ip_rt_put(rt);
 		}
 		nfp_tun_write_neigh(n->dev, app, &flow4, n, false, false);
 	}
-#else
-	return NOTIFY_DONE;
 #endif /* CONFIG_INET */
+out:
+	nfp_tun_release_neigh_update_work(update_work);
+}
 
-	return NOTIFY_OK;
+static struct nfp_neigh_update_work *
+nfp_tun_alloc_neigh_update_work(struct nfp_app *app, struct neighbour *n)
+{
+	struct nfp_neigh_update_work *update_work;
+
+	update_work = kzalloc(sizeof(*update_work), GFP_ATOMIC);
+	if (!update_work)
+		return NULL;
+
+	INIT_WORK(&update_work->work, nfp_tun_neigh_update);
+	neigh_hold(n);
+	update_work->n = n;
+	update_work->app = app;
+
+	return update_work;
+}
+
+static int
+nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event,
+			    void *ptr)
+{
+	struct nfp_neigh_update_work *update_work;
+	struct nfp_flower_priv *app_priv;
+	struct netevent_redirect *redir;
+	struct neighbour *n;
+	struct nfp_app *app;
+
+	switch (event) {
+	case NETEVENT_REDIRECT:
+		redir = (struct netevent_redirect *)ptr;
+		n = redir->neigh;
+		break;
+	case NETEVENT_NEIGH_UPDATE:
+		n = (struct neighbour *)ptr;
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+#if IS_ENABLED(CONFIG_IPV6)
+	if (n->tbl != ipv6_stub->nd_tbl && n->tbl != &arp_tbl)
+#else
+	if (n->tbl != &arp_tbl)
+#endif
+		return NOTIFY_DONE;
+
+	app_priv = container_of(nb, struct nfp_flower_priv, tun.neigh_nb);
+	app = app_priv->app;
+	update_work = nfp_tun_alloc_neigh_update_work(app, n);
+	if (!update_work)
+		return NOTIFY_DONE;
+
+	queue_work(system_highpri_wq, &update_work->work);
+
+	return NOTIFY_DONE;
 }
 
 void nfp_tunnel_request_route_v4(struct nfp_app *app, struct sk_buff *skb)
@@ -706,6 +762,7 @@ void nfp_tunnel_request_route_v4(struct nfp_app *app, struct sk_buff *skb)
 	netdev = nfp_app_dev_get(app, be32_to_cpu(payload->ingress_port), NULL);
 	if (!netdev)
 		goto fail_rcu_unlock;
+	dev_hold(netdev);
 
 	flow.daddr = payload->ipv4_addr;
 	flow.flowi4_proto = IPPROTO_UDP;
@@ -725,13 +782,16 @@ void nfp_tunnel_request_route_v4(struct nfp_app *app, struct sk_buff *skb)
 	ip_rt_put(rt);
 	if (!n)
 		goto fail_rcu_unlock;
+	rcu_read_unlock();
+
 	nfp_tun_write_neigh(n->dev, app, &flow, n, false, true);
 	neigh_release(n);
-	rcu_read_unlock();
+	dev_put(netdev);
 	return;
 
 fail_rcu_unlock:
 	rcu_read_unlock();
+	dev_put(netdev);
 	nfp_flower_cmsg_warn(app, "Requested route not found.\n");
 }
 
@@ -749,6 +809,7 @@ void nfp_tunnel_request_route_v6(struct nfp_app *app, struct sk_buff *skb)
 	netdev = nfp_app_dev_get(app, be32_to_cpu(payload->ingress_port), NULL);
 	if (!netdev)
 		goto fail_rcu_unlock;
+	dev_hold(netdev);
 
 	flow.daddr = payload->ipv6_addr;
 	flow.flowi6_proto = IPPROTO_UDP;
@@ -766,14 +827,16 @@ void nfp_tunnel_request_route_v6(struct nfp_app *app, struct sk_buff *skb)
 	dst_release(dst);
 	if (!n)
 		goto fail_rcu_unlock;
+	rcu_read_unlock();
 
 	nfp_tun_write_neigh(n->dev, app, &flow, n, true, true);
 	neigh_release(n);
-	rcu_read_unlock();
+	dev_put(netdev);
 	return;
 
 fail_rcu_unlock:
 	rcu_read_unlock();
+	dev_put(netdev);
 	nfp_flower_cmsg_warn(app, "Requested IPv6 route not found.\n");
 }
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfd3/dp.c b/drivers/net/ethernet/netronome/nfp/nfd3/dp.c
index 17381bfc15d7..d215efc6cad0 100644
--- a/drivers/net/ethernet/netronome/nfp/nfd3/dp.c
+++ b/drivers/net/ethernet/netronome/nfp/nfd3/dp.c
@@ -74,7 +74,7 @@ static void
 nfp_nfd3_tx_tso(struct nfp_net_r_vector *r_vec, struct nfp_nfd3_tx_buf *txbuf,
 		struct nfp_nfd3_tx_desc *txd, struct sk_buff *skb, u32 md_bytes)
 {
-	u32 l3_offset, l4_offset, hdrlen;
+	u32 l3_offset, l4_offset, hdrlen, l4_hdrlen;
 	u16 mss;
 
 	if (!skb_is_gso(skb))
@@ -83,13 +83,16 @@ nfp_nfd3_tx_tso(struct nfp_net_r_vector *r_vec, struct nfp_nfd3_tx_buf *txbuf,
 	if (!skb->encapsulation) {
 		l3_offset = skb_network_offset(skb);
 		l4_offset = skb_transport_offset(skb);
-		hdrlen = skb_tcp_all_headers(skb);
+		l4_hdrlen = (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) ?
+			    sizeof(struct udphdr) : tcp_hdrlen(skb);
 	} else {
 		l3_offset = skb_inner_network_offset(skb);
 		l4_offset = skb_inner_transport_offset(skb);
-		hdrlen = skb_inner_tcp_all_headers(skb);
+		l4_hdrlen = (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) ?
+			    sizeof(struct udphdr) : inner_tcp_hdrlen(skb);
 	}
 
+	hdrlen = l4_offset + l4_hdrlen;
 	txbuf->pkt_cnt = skb_shinfo(skb)->gso_segs;
 	txbuf->real_len += hdrlen * (txbuf->pkt_cnt - 1);
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfdk/dp.c b/drivers/net/ethernet/netronome/nfp/nfdk/dp.c
index 8d78c6faefa8..dae5af7d1845 100644
--- a/drivers/net/ethernet/netronome/nfp/nfdk/dp.c
+++ b/drivers/net/ethernet/netronome/nfp/nfdk/dp.c
@@ -40,20 +40,23 @@ static __le64
 nfp_nfdk_tx_tso(struct nfp_net_r_vector *r_vec, struct nfp_nfdk_tx_buf *txbuf,
 		struct sk_buff *skb)
 {
-	u32 segs, hdrlen, l3_offset, l4_offset;
+	u32 segs, hdrlen, l3_offset, l4_offset, l4_hdrlen;
 	struct nfp_nfdk_tx_desc txd;
 	u16 mss;
 
 	if (!skb->encapsulation) {
 		l3_offset = skb_network_offset(skb);
 		l4_offset = skb_transport_offset(skb);
-		hdrlen = skb_tcp_all_headers(skb);
+		l4_hdrlen = (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) ?
+			    sizeof(struct udphdr) : tcp_hdrlen(skb);
 	} else {
 		l3_offset = skb_inner_network_offset(skb);
 		l4_offset = skb_inner_transport_offset(skb);
-		hdrlen = skb_inner_tcp_all_headers(skb);
+		l4_hdrlen = (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) ?
+			    sizeof(struct udphdr) : inner_tcp_hdrlen(skb);
 	}
 
+	hdrlen = l4_offset + l4_hdrlen;
 	segs = skb_shinfo(skb)->gso_segs;
 	mss = skb_shinfo(skb)->gso_size & NFDK_DESC_TX_MSS_MASK;
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
index 8c6954c58a88..635d33c0d6d3 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
@@ -75,8 +75,10 @@ nfp_devlink_port_split(struct devlink *devlink, struct devlink_port *port,
 	if (ret)
 		return ret;
 
-	if (eth_port.port_lanes % count)
+	if (eth_port.port_lanes % count) {
+		NL_SET_ERR_MSG_MOD(extack, "invalid count");
 		return -EINVAL;
+	}
 
 	/* Special case the 100G CXP -> 2x40G split */
 	lanes = eth_port.port_lanes / count;
@@ -101,8 +103,10 @@ nfp_devlink_port_unsplit(struct devlink *devlink, struct devlink_port *port,
 	if (ret)
 		return ret;
 
-	if (!eth_port.is_split)
+	if (!eth_port.is_split) {
+		NL_SET_ERR_MSG_MOD(extack, "port is not split");
 		return -EINVAL;
+	}
 
 	/* Special case the 100G CXP -> 2x40G unsplit */
 	lanes = eth_port.port_lanes;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index 939cfce15830..46764aeccb37 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -621,6 +621,9 @@ struct nfp_net_dp {
  * @mbox_amsg.lock:	Protect message list
  * @mbox_amsg.list:	List of message to process
  * @mbox_amsg.work:	Work to process message asynchronously
+ * @fs:			Flow steering
+ * @fs.count:		Flow count
+ * @fs.list:		List of flows
  * @app_priv:		APP private data for this vNIC
  */
 struct nfp_net {
@@ -728,9 +731,39 @@ struct nfp_net {
 		struct work_struct work;
 	} mbox_amsg;
 
+	struct {
+		u16 count;
+		struct list_head list;
+	} fs;
+
 	void *app_priv;
 };
 
+struct nfp_fs_entry {
+	struct list_head node;
+	u32 flow_type;
+	u32 loc;
+	struct {
+		union {
+			struct {
+				__be32 sip4;
+				__be32 dip4;
+			};
+			struct {
+				__be32 sip6[4];
+				__be32 dip6[4];
+			};
+		};
+		union {
+			__be16 l3_proto;
+			u8 l4_proto;
+		};
+		__be16 sport;
+		__be16 dport;
+	} key, msk;
+	u64 action;
+};
+
 struct nfp_mbox_amsg_entry {
 	struct list_head list;
 	int (*cfg)(struct nfp_net *nn, struct nfp_mbox_amsg_entry *entry);
@@ -933,9 +966,9 @@ static inline bool nfp_netdev_is_nfp_net(struct net_device *netdev)
 	       netdev->netdev_ops == &nfp_nfdk_netdev_ops;
 }
 
-static inline int nfp_net_coalesce_para_check(u32 usecs, u32 pkts)
+static inline int nfp_net_coalesce_para_check(u32 param)
 {
-	if ((usecs >= ((1 << 16) - 1)) || (pkts >= ((1 << 16) - 1)))
+	if (param >= ((1 << 16) - 1))
 		return -EINVAL;
 
 	return 0;
@@ -987,6 +1020,9 @@ struct nfp_net_dp *nfp_net_clone_dp(struct nfp_net *nn);
 int nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *new,
 			  struct netlink_ext_ack *extack);
 
+int nfp_net_fs_add_hw(struct nfp_net *nn, struct nfp_fs_entry *entry);
+int nfp_net_fs_del_hw(struct nfp_net *nn, struct nfp_fs_entry *entry);
+
 #ifdef CONFIG_NFP_DEBUG
 void nfp_net_debugfs_create(void);
 void nfp_net_debugfs_destroy(void);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index de0a5d5ded30..3b3210d823e8 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1176,7 +1176,8 @@ static void nfp_net_rx_dim_work(struct work_struct *work)
 	 * count.
 	 */
 	factor = nn->tlv_caps.me_freq_mhz / 16;
-	if (nfp_net_coalesce_para_check(factor * moder.usec, moder.pkts))
+	if (nfp_net_coalesce_para_check(factor * moder.usec) ||
+	    nfp_net_coalesce_para_check(moder.pkts))
 		return;
 
 	/* copy RX interrupt coalesce parameters */
@@ -1205,7 +1206,8 @@ static void nfp_net_tx_dim_work(struct work_struct *work)
 	 * count.
 	 */
 	factor = nn->tlv_caps.me_freq_mhz / 16;
-	if (nfp_net_coalesce_para_check(factor * moder.usec, moder.pkts))
+	if (nfp_net_coalesce_para_check(factor * moder.usec) ||
+	    nfp_net_coalesce_para_check(moder.pkts))
 		return;
 
 	/* copy TX interrupt coalesce parameters */
@@ -1763,6 +1765,186 @@ nfp_net_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid)
 	return nfp_net_mbox_reconfig_and_unlock(nn, cmd);
 }
 
+static void
+nfp_net_fs_fill_v4(struct nfp_net *nn, struct nfp_fs_entry *entry, u32 op, u32 *addr)
+{
+	unsigned int i;
+
+	union {
+		struct {
+			__be16 loc;
+			u8 k_proto, m_proto;
+			__be32 k_sip, m_sip, k_dip, m_dip;
+			__be16 k_sport, m_sport, k_dport, m_dport;
+		};
+		__be32 val[7];
+	} v4_rule;
+
+	nn_writel(nn, *addr, op);
+	*addr += sizeof(u32);
+
+	v4_rule.loc     = cpu_to_be16(entry->loc);
+	v4_rule.k_proto = entry->key.l4_proto;
+	v4_rule.m_proto = entry->msk.l4_proto;
+	v4_rule.k_sip   = entry->key.sip4;
+	v4_rule.m_sip   = entry->msk.sip4;
+	v4_rule.k_dip   = entry->key.dip4;
+	v4_rule.m_dip   = entry->msk.dip4;
+	v4_rule.k_sport = entry->key.sport;
+	v4_rule.m_sport = entry->msk.sport;
+	v4_rule.k_dport = entry->key.dport;
+	v4_rule.m_dport = entry->msk.dport;
+
+	for (i = 0; i < ARRAY_SIZE(v4_rule.val); i++, *addr += sizeof(__be32))
+		nn_writel(nn, *addr, be32_to_cpu(v4_rule.val[i]));
+}
+
+static void
+nfp_net_fs_fill_v6(struct nfp_net *nn, struct nfp_fs_entry *entry, u32 op, u32 *addr)
+{
+	unsigned int i;
+
+	union {
+		struct {
+			__be16 loc;
+			u8 k_proto, m_proto;
+			__be32 k_sip[4], m_sip[4], k_dip[4], m_dip[4];
+			__be16 k_sport, m_sport, k_dport, m_dport;
+		};
+		__be32 val[19];
+	} v6_rule;
+
+	nn_writel(nn, *addr, op);
+	*addr += sizeof(u32);
+
+	v6_rule.loc     = cpu_to_be16(entry->loc);
+	v6_rule.k_proto = entry->key.l4_proto;
+	v6_rule.m_proto = entry->msk.l4_proto;
+	for (i = 0; i < 4; i++) {
+		v6_rule.k_sip[i] = entry->key.sip6[i];
+		v6_rule.m_sip[i] = entry->msk.sip6[i];
+		v6_rule.k_dip[i] = entry->key.dip6[i];
+		v6_rule.m_dip[i] = entry->msk.dip6[i];
+	}
+	v6_rule.k_sport = entry->key.sport;
+	v6_rule.m_sport = entry->msk.sport;
+	v6_rule.k_dport = entry->key.dport;
+	v6_rule.m_dport = entry->msk.dport;
+
+	for (i = 0; i < ARRAY_SIZE(v6_rule.val); i++, *addr += sizeof(__be32))
+		nn_writel(nn, *addr, be32_to_cpu(v6_rule.val[i]));
+}
+
+#define NFP_FS_QUEUE_ID	GENMASK(22, 16)
+#define NFP_FS_ACT	GENMASK(15, 0)
+#define NFP_FS_ACT_DROP	BIT(0)
+#define NFP_FS_ACT_Q	BIT(1)
+static void
+nfp_net_fs_fill_act(struct nfp_net *nn, struct nfp_fs_entry *entry, u32 addr)
+{
+	u32 action = 0; /* 0 means default passthrough */
+
+	if (entry->action == RX_CLS_FLOW_DISC)
+		action = NFP_FS_ACT_DROP;
+	else if (!(entry->flow_type & FLOW_RSS))
+		action = FIELD_PREP(NFP_FS_QUEUE_ID, entry->action) | NFP_FS_ACT_Q;
+
+	nn_writel(nn, addr, action);
+}
+
+int nfp_net_fs_add_hw(struct nfp_net *nn, struct nfp_fs_entry *entry)
+{
+	u32 addr = nn->tlv_caps.mbox_off + NFP_NET_CFG_MBOX_SIMPLE_VAL;
+	int err;
+
+	err = nfp_net_mbox_lock(nn, NFP_NET_CFG_FS_SZ);
+	if (err)
+		return err;
+
+	switch (entry->flow_type & ~FLOW_RSS) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+	case SCTP_V4_FLOW:
+	case IPV4_USER_FLOW:
+		nfp_net_fs_fill_v4(nn, entry, NFP_NET_CFG_MBOX_CMD_FS_ADD_V4, &addr);
+		break;
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+	case SCTP_V6_FLOW:
+	case IPV6_USER_FLOW:
+		nfp_net_fs_fill_v6(nn, entry, NFP_NET_CFG_MBOX_CMD_FS_ADD_V6, &addr);
+		break;
+	case ETHER_FLOW:
+		nn_writel(nn, addr, NFP_NET_CFG_MBOX_CMD_FS_ADD_ETHTYPE);
+		addr += sizeof(u32);
+		nn_writew(nn, addr, be16_to_cpu(entry->key.l3_proto));
+		addr += sizeof(u32);
+		break;
+	}
+
+	nfp_net_fs_fill_act(nn, entry, addr);
+
+	err = nfp_net_mbox_reconfig_and_unlock(nn, NFP_NET_CFG_MBOX_CMD_FLOW_STEER);
+	if (err) {
+		nn_err(nn, "Add new fs rule failed with %d\n", err);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+int nfp_net_fs_del_hw(struct nfp_net *nn, struct nfp_fs_entry *entry)
+{
+	u32 addr = nn->tlv_caps.mbox_off + NFP_NET_CFG_MBOX_SIMPLE_VAL;
+	int err;
+
+	err = nfp_net_mbox_lock(nn, NFP_NET_CFG_FS_SZ);
+	if (err)
+		return err;
+
+	switch (entry->flow_type & ~FLOW_RSS) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+	case SCTP_V4_FLOW:
+	case IPV4_USER_FLOW:
+		nfp_net_fs_fill_v4(nn, entry, NFP_NET_CFG_MBOX_CMD_FS_DEL_V4, &addr);
+		break;
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+	case SCTP_V6_FLOW:
+	case IPV6_USER_FLOW:
+		nfp_net_fs_fill_v6(nn, entry, NFP_NET_CFG_MBOX_CMD_FS_DEL_V6, &addr);
+		break;
+	case ETHER_FLOW:
+		nn_writel(nn, addr, NFP_NET_CFG_MBOX_CMD_FS_DEL_ETHTYPE);
+		addr += sizeof(u32);
+		nn_writew(nn, addr, be16_to_cpu(entry->key.l3_proto));
+		addr += sizeof(u32);
+		break;
+	}
+
+	nfp_net_fs_fill_act(nn, entry, addr);
+
+	err = nfp_net_mbox_reconfig_and_unlock(nn, NFP_NET_CFG_MBOX_CMD_FLOW_STEER);
+	if (err) {
+		nn_err(nn, "Delete fs rule failed with %d\n", err);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static void nfp_net_fs_clean(struct nfp_net *nn)
+{
+	struct nfp_fs_entry *entry, *tmp;
+
+	list_for_each_entry_safe(entry, tmp, &nn->fs.list, node) {
+		nfp_net_fs_del_hw(nn, entry);
+		list_del(&entry->node);
+		kfree(entry);
+	}
+}
+
 static void nfp_net_stat64(struct net_device *netdev,
 			   struct rtnl_link_stats64 *stats)
 {
@@ -1934,7 +2116,10 @@ nfp_net_features_check(struct sk_buff *skb, struct net_device *dev,
 	if (skb_is_gso(skb)) {
 		u32 hdrlen;
 
-		hdrlen = skb_inner_tcp_all_headers(skb);
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
+			hdrlen = skb_inner_transport_offset(skb) + sizeof(struct udphdr);
+		else
+			hdrlen = skb_inner_tcp_all_headers(skb);
 
 		/* Assume worst case scenario of having longest possible
 		 * metadata prepend - 8B
@@ -2237,7 +2422,7 @@ void nfp_net_info(struct nfp_net *nn)
 		nn->fw_ver.extend, nn->fw_ver.class,
 		nn->fw_ver.major, nn->fw_ver.minor,
 		nn->max_mtu);
-	nn_info(nn, "CAP: %#x %s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n",
+	nn_info(nn, "CAP: %#x %s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n",
 		nn->cap,
 		nn->cap & NFP_NET_CFG_CTRL_PROMISC  ? "PROMISC "  : "",
 		nn->cap & NFP_NET_CFG_CTRL_L2BC     ? "L2BCFILT " : "",
@@ -2266,6 +2451,7 @@ void nfp_net_info(struct nfp_net *nn)
 						      "RXCSUM_COMPLETE " : "",
 		nn->cap & NFP_NET_CFG_CTRL_LIVE_ADDR ? "LIVE_ADDR " : "",
 		nn->cap_w1 & NFP_NET_CFG_CTRL_MCAST_FILTER ? "MULTICAST_FILTER " : "",
+		nn->cap_w1 & NFP_NET_CFG_CTRL_USO ? "USO " : "",
 		nfp_app_extra_cap(nn->app, nn));
 }
 
@@ -2514,6 +2700,8 @@ static void nfp_net_netdev_init(struct nfp_net *nn)
 	if ((nn->cap & NFP_NET_CFG_CTRL_LSO && nn->fw_ver.major > 2) ||
 	    nn->cap & NFP_NET_CFG_CTRL_LSO2) {
 		netdev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6;
+		if (nn->cap_w1 & NFP_NET_CFG_CTRL_USO)
+			netdev->hw_features |= NETIF_F_GSO_UDP_L4;
 		nn->dp.ctrl |= nn->cap & NFP_NET_CFG_CTRL_LSO2 ?:
 					 NFP_NET_CFG_CTRL_LSO;
 	}
@@ -2740,6 +2928,8 @@ int nfp_net_init(struct nfp_net *nn)
 	INIT_LIST_HEAD(&nn->mbox_amsg.list);
 	INIT_WORK(&nn->mbox_amsg.work, nfp_net_mbox_amsg_work);
 
+	INIT_LIST_HEAD(&nn->fs.list);
+
 	return register_netdev(nn->dp.netdev);
 
 err_clean_mbox:
@@ -2759,6 +2949,7 @@ void nfp_net_clean(struct nfp_net *nn)
 	unregister_netdev(nn->dp.netdev);
 	nfp_net_ipsec_clean(nn);
 	nfp_ccm_mbox_clean(nn);
+	nfp_net_fs_clean(nn);
 	flush_work(&nn->mbox_amsg.work);
 	nfp_net_reconfig_wait_posted(nn);
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
index 3e63f6d6a563..634c63c7f7eb 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
@@ -269,6 +269,8 @@
 #define   NFP_NET_CFG_CTRL_IPSEC	  (0x1 << 1) /* IPsec offload */
 #define   NFP_NET_CFG_CTRL_MCAST_FILTER	  (0x1 << 2) /* Multicast Filter */
 #define   NFP_NET_CFG_CTRL_FREELIST_EN	  (0x1 << 6) /* Freelist enable flag bit */
+#define   NFP_NET_CFG_CTRL_FLOW_STEER	  (0x1 << 8) /* Flow steering */
+#define   NFP_NET_CFG_CTRL_USO		  (0x1 << 16) /* UDP segmentation offload */
 
 #define NFP_NET_CFG_CAP_WORD1		0x00a4
 
@@ -418,6 +420,8 @@
 #define NFP_NET_CFG_MBOX_CMD_MULTICAST_ADD		8
 #define NFP_NET_CFG_MBOX_CMD_MULTICAST_DEL		9
 
+#define NFP_NET_CFG_MBOX_CMD_FLOW_STEER			10
+
 /* VLAN filtering using general use mailbox
  * %NFP_NET_CFG_VLAN_FILTER:		Base address of VLAN filter mailbox
  * %NFP_NET_CFG_VLAN_FILTER_VID:	VLAN ID to filter
@@ -440,6 +444,18 @@
 #define NFP_NET_CFG_MULTICAST_MAC_LO	(NFP_NET_CFG_MULTICAST + 6)
 #define NFP_NET_CFG_MULTICAST_SZ	0x0006
 
+/* Max size of FS rules in bytes */
+#define NFP_NET_CFG_FS_SZ		0x0054
+/* Sub commands for FS */
+enum {
+	NFP_NET_CFG_MBOX_CMD_FS_ADD_V4,
+	NFP_NET_CFG_MBOX_CMD_FS_DEL_V4,
+	NFP_NET_CFG_MBOX_CMD_FS_ADD_V6,
+	NFP_NET_CFG_MBOX_CMD_FS_DEL_V6,
+	NFP_NET_CFG_MBOX_CMD_FS_ADD_ETHTYPE,
+	NFP_NET_CFG_MBOX_CMD_FS_DEL_ETHTYPE,
+};
+
 /* TLV capabilities
  * %NFP_NET_CFG_TLV_TYPE:	Offset of type within the TLV
  * %NFP_NET_CFG_TLV_TYPE_REQUIRED: Driver must be able to parse the TLV
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index e75cbb287625..fbca8d0efd85 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -633,7 +633,8 @@ static void nfp_net_get_ringparam(struct net_device *netdev,
 	ring->tx_pending = nn->dp.txd_cnt;
 }
 
-static int nfp_net_set_ring_size(struct nfp_net *nn, u32 rxd_cnt, u32 txd_cnt)
+static int nfp_net_set_ring_size(struct nfp_net *nn, u32 rxd_cnt, u32 txd_cnt,
+				 struct netlink_ext_ack *extack)
 {
 	struct nfp_net_dp *dp;
 
@@ -644,7 +645,7 @@ static int nfp_net_set_ring_size(struct nfp_net *nn, u32 rxd_cnt, u32 txd_cnt)
 	dp->rxd_cnt = rxd_cnt;
 	dp->txd_cnt = txd_cnt;
 
-	return nfp_net_ring_reconfig(nn, dp, NULL);
+	return nfp_net_ring_reconfig(nn, dp, extack);
 }
 
 static int nfp_net_set_ringparam(struct net_device *netdev,
@@ -657,7 +658,7 @@ static int nfp_net_set_ringparam(struct net_device *netdev,
 
 	/* We don't have separate queues/rings for small/large frames. */
 	if (ring->rx_mini_pending || ring->rx_jumbo_pending)
-		return -EINVAL;
+		return -EOPNOTSUPP;
 
 	qc_min = nn->dev_info->min_qc_size;
 	qc_max = nn->dev_info->max_qc_size;
@@ -666,9 +667,15 @@ static int nfp_net_set_ringparam(struct net_device *netdev,
 	rxd_cnt = roundup_pow_of_two(ring->rx_pending);
 	txd_cnt = roundup_pow_of_two(ring->tx_pending);
 
-	if (rxd_cnt < qc_min || rxd_cnt > qc_max ||
-	    txd_cnt < qc_min / tx_dpp || txd_cnt > qc_max / tx_dpp)
+	if (rxd_cnt < qc_min || rxd_cnt > qc_max) {
+		NL_SET_ERR_MSG_MOD(extack, "rx parameter out of bounds");
 		return -EINVAL;
+	}
+
+	if (txd_cnt < qc_min / tx_dpp || txd_cnt > qc_max / tx_dpp) {
+		NL_SET_ERR_MSG_MOD(extack, "tx parameter out of bounds");
+		return -EINVAL;
+	}
 
 	if (nn->dp.rxd_cnt == rxd_cnt && nn->dp.txd_cnt == txd_cnt)
 		return 0;
@@ -676,7 +683,7 @@ static int nfp_net_set_ringparam(struct net_device *netdev,
 	nn_dbg(nn, "Change ring size: RxQ %u->%u, TxQ %u->%u\n",
 	       nn->dp.rxd_cnt, rxd_cnt, nn->dp.txd_cnt, txd_cnt);
 
-	return nfp_net_set_ring_size(nn, rxd_cnt, txd_cnt);
+	return nfp_net_set_ring_size(nn, rxd_cnt, txd_cnt, extack);
 }
 
 static int nfp_test_link(struct net_device *netdev)
@@ -800,7 +807,7 @@ static void nfp_get_self_test_strings(struct net_device *netdev, u8 *data)
 
 	for (i = 0; i < NFP_TEST_TOTAL_NUM; i++)
 		if (nfp_self_test[i].is_supported(netdev))
-			ethtool_sprintf(&data, nfp_self_test[i].name);
+			ethtool_puts(&data, nfp_self_test[i].name);
 }
 
 static int nfp_get_self_test_count(struct net_device *netdev)
@@ -852,24 +859,24 @@ static u8 *nfp_vnic_get_sw_stats_strings(struct net_device *netdev, u8 *data)
 		ethtool_sprintf(&data, "rvec_%u_tx_busy", i);
 	}
 
-	ethtool_sprintf(&data, "hw_rx_csum_ok");
-	ethtool_sprintf(&data, "hw_rx_csum_inner_ok");
-	ethtool_sprintf(&data, "hw_rx_csum_complete");
-	ethtool_sprintf(&data, "hw_rx_csum_err");
-	ethtool_sprintf(&data, "rx_replace_buf_alloc_fail");
-	ethtool_sprintf(&data, "rx_tls_decrypted_packets");
-	ethtool_sprintf(&data, "hw_tx_csum");
-	ethtool_sprintf(&data, "hw_tx_inner_csum");
-	ethtool_sprintf(&data, "tx_gather");
-	ethtool_sprintf(&data, "tx_lso");
-	ethtool_sprintf(&data, "tx_tls_encrypted_packets");
-	ethtool_sprintf(&data, "tx_tls_ooo");
-	ethtool_sprintf(&data, "tx_tls_drop_no_sync_data");
-
-	ethtool_sprintf(&data, "hw_tls_no_space");
-	ethtool_sprintf(&data, "rx_tls_resync_req_ok");
-	ethtool_sprintf(&data, "rx_tls_resync_req_ign");
-	ethtool_sprintf(&data, "rx_tls_resync_sent");
+	ethtool_puts(&data, "hw_rx_csum_ok");
+	ethtool_puts(&data, "hw_rx_csum_inner_ok");
+	ethtool_puts(&data, "hw_rx_csum_complete");
+	ethtool_puts(&data, "hw_rx_csum_err");
+	ethtool_puts(&data, "rx_replace_buf_alloc_fail");
+	ethtool_puts(&data, "rx_tls_decrypted_packets");
+	ethtool_puts(&data, "hw_tx_csum");
+	ethtool_puts(&data, "hw_tx_inner_csum");
+	ethtool_puts(&data, "tx_gather");
+	ethtool_puts(&data, "tx_lso");
+	ethtool_puts(&data, "tx_tls_encrypted_packets");
+	ethtool_puts(&data, "tx_tls_ooo");
+	ethtool_puts(&data, "tx_tls_drop_no_sync_data");
+
+	ethtool_puts(&data, "hw_tls_no_space");
+	ethtool_puts(&data, "rx_tls_resync_req_ok");
+	ethtool_puts(&data, "rx_tls_resync_req_ign");
+	ethtool_puts(&data, "rx_tls_resync_sent");
 
 	return data;
 }
@@ -943,13 +950,13 @@ nfp_vnic_get_hw_stats_strings(u8 *data, unsigned int num_vecs, bool repr)
 	swap_off = repr * NN_ET_SWITCH_STATS_LEN;
 
 	for (i = 0; i < NN_ET_SWITCH_STATS_LEN; i++)
-		ethtool_sprintf(&data, nfp_net_et_stats[i + swap_off].name);
+		ethtool_puts(&data, nfp_net_et_stats[i + swap_off].name);
 
 	for (i = NN_ET_SWITCH_STATS_LEN; i < NN_ET_SWITCH_STATS_LEN * 2; i++)
-		ethtool_sprintf(&data, nfp_net_et_stats[i - swap_off].name);
+		ethtool_puts(&data, nfp_net_et_stats[i - swap_off].name);
 
 	for (i = NN_ET_SWITCH_STATS_LEN * 2; i < NN_ET_GLOBAL_STATS_LEN; i++)
-		ethtool_sprintf(&data, nfp_net_et_stats[i].name);
+		ethtool_puts(&data, nfp_net_et_stats[i].name);
 
 	for (i = 0; i < num_vecs; i++) {
 		ethtool_sprintf(&data, "rxq_%u_pkts", i);
@@ -1317,6 +1324,116 @@ static int nfp_net_get_rss_hash_opts(struct nfp_net *nn,
 	return 0;
 }
 
+#define NFP_FS_MAX_ENTRY	1024
+
+static int nfp_net_fs_to_ethtool(struct nfp_fs_entry *entry, struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_rx_flow_spec *fs = &cmd->fs;
+	unsigned int i;
+
+	switch (entry->flow_type & ~FLOW_RSS) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+	case SCTP_V4_FLOW:
+		fs->h_u.tcp_ip4_spec.ip4src = entry->key.sip4;
+		fs->h_u.tcp_ip4_spec.ip4dst = entry->key.dip4;
+		fs->h_u.tcp_ip4_spec.psrc   = entry->key.sport;
+		fs->h_u.tcp_ip4_spec.pdst   = entry->key.dport;
+		fs->m_u.tcp_ip4_spec.ip4src = entry->msk.sip4;
+		fs->m_u.tcp_ip4_spec.ip4dst = entry->msk.dip4;
+		fs->m_u.tcp_ip4_spec.psrc   = entry->msk.sport;
+		fs->m_u.tcp_ip4_spec.pdst   = entry->msk.dport;
+		break;
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+	case SCTP_V6_FLOW:
+		for (i = 0; i < 4; i++) {
+			fs->h_u.tcp_ip6_spec.ip6src[i] = entry->key.sip6[i];
+			fs->h_u.tcp_ip6_spec.ip6dst[i] = entry->key.dip6[i];
+			fs->m_u.tcp_ip6_spec.ip6src[i] = entry->msk.sip6[i];
+			fs->m_u.tcp_ip6_spec.ip6dst[i] = entry->msk.dip6[i];
+		}
+		fs->h_u.tcp_ip6_spec.psrc = entry->key.sport;
+		fs->h_u.tcp_ip6_spec.pdst = entry->key.dport;
+		fs->m_u.tcp_ip6_spec.psrc = entry->msk.sport;
+		fs->m_u.tcp_ip6_spec.pdst = entry->msk.dport;
+		break;
+	case IPV4_USER_FLOW:
+		fs->h_u.usr_ip4_spec.ip_ver = ETH_RX_NFC_IP4;
+		fs->h_u.usr_ip4_spec.ip4src = entry->key.sip4;
+		fs->h_u.usr_ip4_spec.ip4dst = entry->key.dip4;
+		fs->h_u.usr_ip4_spec.proto  = entry->key.l4_proto;
+		fs->m_u.usr_ip4_spec.ip4src = entry->msk.sip4;
+		fs->m_u.usr_ip4_spec.ip4dst = entry->msk.dip4;
+		fs->m_u.usr_ip4_spec.proto  = entry->msk.l4_proto;
+		break;
+	case IPV6_USER_FLOW:
+		for (i = 0; i < 4; i++) {
+			fs->h_u.usr_ip6_spec.ip6src[i] = entry->key.sip6[i];
+			fs->h_u.usr_ip6_spec.ip6dst[i] = entry->key.dip6[i];
+			fs->m_u.usr_ip6_spec.ip6src[i] = entry->msk.sip6[i];
+			fs->m_u.usr_ip6_spec.ip6dst[i] = entry->msk.dip6[i];
+		}
+		fs->h_u.usr_ip6_spec.l4_proto = entry->key.l4_proto;
+		fs->m_u.usr_ip6_spec.l4_proto = entry->msk.l4_proto;
+		break;
+	case ETHER_FLOW:
+		fs->h_u.ether_spec.h_proto = entry->key.l3_proto;
+		fs->m_u.ether_spec.h_proto = entry->msk.l3_proto;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	fs->flow_type   = entry->flow_type;
+	fs->ring_cookie = entry->action;
+
+	if (fs->flow_type & FLOW_RSS) {
+		/* Only rss_context of 0 is supported. */
+		cmd->rss_context = 0;
+		/* RSS is used, mask the ring. */
+		fs->ring_cookie |= ETHTOOL_RX_FLOW_SPEC_RING;
+	}
+
+	return 0;
+}
+
+static int nfp_net_get_fs_rule(struct nfp_net *nn, struct ethtool_rxnfc *cmd)
+{
+	struct nfp_fs_entry *entry;
+
+	if (!(nn->cap_w1 & NFP_NET_CFG_CTRL_FLOW_STEER))
+		return -EOPNOTSUPP;
+
+	if (cmd->fs.location >= NFP_FS_MAX_ENTRY)
+		return -EINVAL;
+
+	list_for_each_entry(entry, &nn->fs.list, node) {
+		if (entry->loc == cmd->fs.location)
+			return nfp_net_fs_to_ethtool(entry, cmd);
+
+		if (entry->loc > cmd->fs.location)
+			/* no need to continue */
+			return -ENOENT;
+	}
+
+	return -ENOENT;
+}
+
+static int nfp_net_get_fs_loc(struct nfp_net *nn, u32 *rule_locs)
+{
+	struct nfp_fs_entry *entry;
+	u32 count = 0;
+
+	if (!(nn->cap_w1 & NFP_NET_CFG_CTRL_FLOW_STEER))
+		return -EOPNOTSUPP;
+
+	list_for_each_entry(entry, &nn->fs.list, node)
+		rule_locs[count++] = entry->loc;
+
+	return 0;
+}
+
 static int nfp_net_get_rxnfc(struct net_device *netdev,
 			     struct ethtool_rxnfc *cmd, u32 *rule_locs)
 {
@@ -1326,6 +1443,14 @@ static int nfp_net_get_rxnfc(struct net_device *netdev,
 	case ETHTOOL_GRXRINGS:
 		cmd->data = nn->dp.num_rx_rings;
 		return 0;
+	case ETHTOOL_GRXCLSRLCNT:
+		cmd->rule_cnt = nn->fs.count;
+		return 0;
+	case ETHTOOL_GRXCLSRULE:
+		return nfp_net_get_fs_rule(nn, cmd);
+	case ETHTOOL_GRXCLSRLALL:
+		cmd->data = NFP_FS_MAX_ENTRY;
+		return nfp_net_get_fs_loc(nn, rule_locs);
 	case ETHTOOL_GRXFH:
 		return nfp_net_get_rss_hash_opts(nn, cmd);
 	default:
@@ -1385,6 +1510,253 @@ static int nfp_net_set_rss_hash_opt(struct nfp_net *nn,
 	return 0;
 }
 
+static int nfp_net_fs_from_ethtool(struct nfp_fs_entry *entry, struct ethtool_rx_flow_spec *fs)
+{
+	unsigned int i;
+
+	/* FLOW_EXT/FLOW_MAC_EXT is not supported. */
+	switch (fs->flow_type & ~FLOW_RSS) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+	case SCTP_V4_FLOW:
+		entry->msk.sip4  = fs->m_u.tcp_ip4_spec.ip4src;
+		entry->msk.dip4  = fs->m_u.tcp_ip4_spec.ip4dst;
+		entry->msk.sport = fs->m_u.tcp_ip4_spec.psrc;
+		entry->msk.dport = fs->m_u.tcp_ip4_spec.pdst;
+		entry->key.sip4  = fs->h_u.tcp_ip4_spec.ip4src & entry->msk.sip4;
+		entry->key.dip4  = fs->h_u.tcp_ip4_spec.ip4dst & entry->msk.dip4;
+		entry->key.sport = fs->h_u.tcp_ip4_spec.psrc & entry->msk.sport;
+		entry->key.dport = fs->h_u.tcp_ip4_spec.pdst & entry->msk.dport;
+		break;
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+	case SCTP_V6_FLOW:
+		for (i = 0; i < 4; i++) {
+			entry->msk.sip6[i] = fs->m_u.tcp_ip6_spec.ip6src[i];
+			entry->msk.dip6[i] = fs->m_u.tcp_ip6_spec.ip6dst[i];
+			entry->key.sip6[i] = fs->h_u.tcp_ip6_spec.ip6src[i] & entry->msk.sip6[i];
+			entry->key.dip6[i] = fs->h_u.tcp_ip6_spec.ip6dst[i] & entry->msk.dip6[i];
+		}
+		entry->msk.sport = fs->m_u.tcp_ip6_spec.psrc;
+		entry->msk.dport = fs->m_u.tcp_ip6_spec.pdst;
+		entry->key.sport = fs->h_u.tcp_ip6_spec.psrc & entry->msk.sport;
+		entry->key.dport = fs->h_u.tcp_ip6_spec.pdst & entry->msk.dport;
+		break;
+	case IPV4_USER_FLOW:
+		entry->msk.sip4     = fs->m_u.usr_ip4_spec.ip4src;
+		entry->msk.dip4     = fs->m_u.usr_ip4_spec.ip4dst;
+		entry->msk.l4_proto = fs->m_u.usr_ip4_spec.proto;
+		entry->key.sip4     = fs->h_u.usr_ip4_spec.ip4src & entry->msk.sip4;
+		entry->key.dip4     = fs->h_u.usr_ip4_spec.ip4dst & entry->msk.dip4;
+		entry->key.l4_proto = fs->h_u.usr_ip4_spec.proto & entry->msk.l4_proto;
+		break;
+	case IPV6_USER_FLOW:
+		for (i = 0; i < 4; i++) {
+			entry->msk.sip6[i] = fs->m_u.usr_ip6_spec.ip6src[i];
+			entry->msk.dip6[i] = fs->m_u.usr_ip6_spec.ip6dst[i];
+			entry->key.sip6[i] = fs->h_u.usr_ip6_spec.ip6src[i] & entry->msk.sip6[i];
+			entry->key.dip6[i] = fs->h_u.usr_ip6_spec.ip6dst[i] & entry->msk.dip6[i];
+		}
+		entry->msk.l4_proto = fs->m_u.usr_ip6_spec.l4_proto;
+		entry->key.l4_proto = fs->h_u.usr_ip6_spec.l4_proto & entry->msk.l4_proto;
+		break;
+	case ETHER_FLOW:
+		entry->msk.l3_proto = fs->m_u.ether_spec.h_proto;
+		entry->key.l3_proto = fs->h_u.ether_spec.h_proto & entry->msk.l3_proto;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (fs->flow_type & ~FLOW_RSS) {
+	case TCP_V4_FLOW:
+	case TCP_V6_FLOW:
+		entry->key.l4_proto = IPPROTO_TCP;
+		entry->msk.l4_proto = 0xff;
+		break;
+	case UDP_V4_FLOW:
+	case UDP_V6_FLOW:
+		entry->key.l4_proto = IPPROTO_UDP;
+		entry->msk.l4_proto = 0xff;
+		break;
+	case SCTP_V4_FLOW:
+	case SCTP_V6_FLOW:
+		entry->key.l4_proto = IPPROTO_SCTP;
+		entry->msk.l4_proto = 0xff;
+		break;
+	}
+
+	entry->flow_type = fs->flow_type;
+	entry->action    = fs->ring_cookie;
+	entry->loc       = fs->location;
+
+	return 0;
+}
+
+static int nfp_net_fs_check_existing(struct nfp_net *nn, struct nfp_fs_entry *new)
+{
+	struct nfp_fs_entry *entry;
+
+	list_for_each_entry(entry, &nn->fs.list, node) {
+		if (new->loc != entry->loc &&
+		    !((new->flow_type ^ entry->flow_type) & ~FLOW_RSS) &&
+		    !memcmp(&new->key, &entry->key, sizeof(new->key)) &&
+		    !memcmp(&new->msk, &entry->msk, sizeof(new->msk)))
+			return entry->loc;
+	}
+
+	/* -1 means no duplicates */
+	return -1;
+}
+
+static int nfp_net_fs_add(struct nfp_net *nn, struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_rx_flow_spec *fs = &cmd->fs;
+	struct nfp_fs_entry *new, *entry;
+	bool unsupp_mask;
+	int err, id;
+
+	if (!(nn->cap_w1 & NFP_NET_CFG_CTRL_FLOW_STEER))
+		return -EOPNOTSUPP;
+
+	/* Only default RSS context(0) is supported. */
+	if ((fs->flow_type & FLOW_RSS) && cmd->rss_context)
+		return -EOPNOTSUPP;
+
+	if (fs->location >= NFP_FS_MAX_ENTRY)
+		return -EINVAL;
+
+	if (fs->ring_cookie != RX_CLS_FLOW_DISC &&
+	    fs->ring_cookie >= nn->dp.num_rx_rings)
+		return -EINVAL;
+
+	/* FLOW_EXT/FLOW_MAC_EXT is not supported. */
+	switch (fs->flow_type & ~FLOW_RSS) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+	case SCTP_V4_FLOW:
+		unsupp_mask = !!fs->m_u.tcp_ip4_spec.tos;
+		break;
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+	case SCTP_V6_FLOW:
+		unsupp_mask = !!fs->m_u.tcp_ip6_spec.tclass;
+		break;
+	case IPV4_USER_FLOW:
+		unsupp_mask = !!fs->m_u.usr_ip4_spec.l4_4_bytes ||
+			      !!fs->m_u.usr_ip4_spec.tos ||
+			      !!fs->m_u.usr_ip4_spec.ip_ver;
+		/* ip_ver must be ETH_RX_NFC_IP4. */
+		unsupp_mask |= fs->h_u.usr_ip4_spec.ip_ver != ETH_RX_NFC_IP4;
+		break;
+	case IPV6_USER_FLOW:
+		unsupp_mask = !!fs->m_u.usr_ip6_spec.l4_4_bytes ||
+			      !!fs->m_u.usr_ip6_spec.tclass;
+		break;
+	case ETHER_FLOW:
+		if (fs->h_u.ether_spec.h_proto == htons(ETH_P_IP) ||
+		    fs->h_u.ether_spec.h_proto == htons(ETH_P_IPV6)) {
+			nn_err(nn, "Please use ip4/ip6 flow type instead.\n");
+			return -EOPNOTSUPP;
+		}
+		/* Only unmasked ethtype is supported. */
+		unsupp_mask = !is_zero_ether_addr(fs->m_u.ether_spec.h_dest) ||
+			      !is_zero_ether_addr(fs->m_u.ether_spec.h_source) ||
+			      (fs->m_u.ether_spec.h_proto != htons(0xffff));
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	if (unsupp_mask)
+		return -EOPNOTSUPP;
+
+	new = kzalloc(sizeof(*new), GFP_KERNEL);
+	if (!new)
+		return -ENOMEM;
+
+	nfp_net_fs_from_ethtool(new, fs);
+
+	id = nfp_net_fs_check_existing(nn, new);
+	if (id >= 0) {
+		nn_err(nn, "Identical rule is existing in %d.\n", id);
+		err = -EINVAL;
+		goto err;
+	}
+
+	/* Insert to list in ascending order of location. */
+	list_for_each_entry(entry, &nn->fs.list, node) {
+		if (entry->loc == fs->location) {
+			err = nfp_net_fs_del_hw(nn, entry);
+			if (err)
+				goto err;
+
+			nn->fs.count--;
+			err = nfp_net_fs_add_hw(nn, new);
+			if (err)
+				goto err;
+
+			nn->fs.count++;
+			list_replace(&entry->node, &new->node);
+			kfree(entry);
+
+			return 0;
+		}
+
+		if (entry->loc > fs->location)
+			break;
+	}
+
+	if (nn->fs.count == NFP_FS_MAX_ENTRY) {
+		err = -ENOSPC;
+		goto err;
+	}
+
+	err = nfp_net_fs_add_hw(nn, new);
+	if (err)
+		goto err;
+
+	list_add_tail(&new->node, &entry->node);
+	nn->fs.count++;
+
+	return 0;
+
+err:
+	kfree(new);
+	return err;
+}
+
+static int nfp_net_fs_del(struct nfp_net *nn, struct ethtool_rxnfc *cmd)
+{
+	struct nfp_fs_entry *entry;
+	int err;
+
+	if (!(nn->cap_w1 & NFP_NET_CFG_CTRL_FLOW_STEER))
+		return -EOPNOTSUPP;
+
+	if (!nn->fs.count || cmd->fs.location >= NFP_FS_MAX_ENTRY)
+		return -EINVAL;
+
+	list_for_each_entry(entry, &nn->fs.list, node) {
+		if (entry->loc == cmd->fs.location) {
+			err = nfp_net_fs_del_hw(nn, entry);
+			if (err)
+				return err;
+
+			list_del(&entry->node);
+			kfree(entry);
+			nn->fs.count--;
+
+			return 0;
+		} else if (entry->loc > cmd->fs.location) {
+			/* no need to continue */
+			break;
+		}
+	}
+
+	return -ENOENT;
+}
+
 static int nfp_net_set_rxnfc(struct net_device *netdev,
 			     struct ethtool_rxnfc *cmd)
 {
@@ -1393,6 +1765,10 @@ static int nfp_net_set_rxnfc(struct net_device *netdev,
 	switch (cmd->cmd) {
 	case ETHTOOL_SRXFH:
 		return nfp_net_set_rss_hash_opt(nn, cmd);
+	case ETHTOOL_SRXCLSRLINS:
+		return nfp_net_fs_add(nn, cmd);
+	case ETHTOOL_SRXCLSRLDEL:
+		return nfp_net_fs_del(nn, cmd);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -1418,8 +1794,8 @@ static u32 nfp_net_get_rxfh_key_size(struct net_device *netdev)
 	return nfp_net_rss_key_sz(nn);
 }
 
-static int nfp_net_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			    u8 *hfunc)
+static int nfp_net_get_rxfh(struct net_device *netdev,
+			    struct ethtool_rxfh_param *rxfh)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 	int i;
@@ -1427,41 +1803,41 @@ static int nfp_net_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 	if (!(nn->cap & NFP_NET_CFG_CTRL_RSS_ANY))
 		return -EOPNOTSUPP;
 
-	if (indir)
+	if (rxfh->indir)
 		for (i = 0; i < ARRAY_SIZE(nn->rss_itbl); i++)
-			indir[i] = nn->rss_itbl[i];
-	if (key)
-		memcpy(key, nn->rss_key, nfp_net_rss_key_sz(nn));
-	if (hfunc) {
-		*hfunc = nn->rss_hfunc;
-		if (*hfunc >= 1 << ETH_RSS_HASH_FUNCS_COUNT)
-			*hfunc = ETH_RSS_HASH_UNKNOWN;
-	}
+			rxfh->indir[i] = nn->rss_itbl[i];
+	if (rxfh->key)
+		memcpy(rxfh->key, nn->rss_key, nfp_net_rss_key_sz(nn));
+
+	rxfh->hfunc = nn->rss_hfunc;
+	if (rxfh->hfunc >= 1 << ETH_RSS_HASH_FUNCS_COUNT)
+		rxfh->hfunc = ETH_RSS_HASH_UNKNOWN;
 
 	return 0;
 }
 
 static int nfp_net_set_rxfh(struct net_device *netdev,
-			    const u32 *indir, const u8 *key,
-			    const u8 hfunc)
+			    struct ethtool_rxfh_param *rxfh,
+			    struct netlink_ext_ack *extack)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 	int i;
 
 	if (!(nn->cap & NFP_NET_CFG_CTRL_RSS_ANY) ||
-	    !(hfunc == ETH_RSS_HASH_NO_CHANGE || hfunc == nn->rss_hfunc))
+	    !(rxfh->hfunc == ETH_RSS_HASH_NO_CHANGE ||
+	      rxfh->hfunc == nn->rss_hfunc))
 		return -EOPNOTSUPP;
 
-	if (!key && !indir)
+	if (!rxfh->key && !rxfh->indir)
 		return 0;
 
-	if (key) {
-		memcpy(nn->rss_key, key, nfp_net_rss_key_sz(nn));
+	if (rxfh->key) {
+		memcpy(nn->rss_key, rxfh->key, nfp_net_rss_key_sz(nn));
 		nfp_net_rss_write_key(nn);
 	}
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < ARRAY_SIZE(nn->rss_itbl); i++)
-			nn->rss_itbl[i] = indir[i];
+			nn->rss_itbl[i] = rxfh->indir[i];
 
 		nfp_net_rss_write_itbl(nn);
 	}
@@ -1497,7 +1873,7 @@ static int nfp_net_get_coalesce(struct net_device *netdev,
 	struct nfp_net *nn = netdev_priv(netdev);
 
 	if (!(nn->cap & NFP_NET_CFG_CTRL_IRQMOD))
-		return -EINVAL;
+		return -EOPNOTSUPP;
 
 	ec->use_adaptive_rx_coalesce = nn->rx_coalesce_adapt_on;
 	ec->use_adaptive_tx_coalesce = nn->tx_coalesce_adapt_on;
@@ -1776,22 +2152,40 @@ static int nfp_net_set_coalesce(struct net_device *netdev,
 	 */
 
 	if (!(nn->cap & NFP_NET_CFG_CTRL_IRQMOD))
-		return -EINVAL;
+		return -EOPNOTSUPP;
 
 	/* ensure valid configuration */
-	if (!ec->rx_coalesce_usecs && !ec->rx_max_coalesced_frames)
+	if (!ec->rx_coalesce_usecs && !ec->rx_max_coalesced_frames) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "rx-usecs and rx-frames cannot both be zero");
 		return -EINVAL;
+	}
 
-	if (!ec->tx_coalesce_usecs && !ec->tx_max_coalesced_frames)
+	if (!ec->tx_coalesce_usecs && !ec->tx_max_coalesced_frames) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "tx-usecs and tx-frames cannot both be zero");
 		return -EINVAL;
+	}
 
-	if (nfp_net_coalesce_para_check(ec->rx_coalesce_usecs * factor,
-					ec->rx_max_coalesced_frames))
+	if (nfp_net_coalesce_para_check(ec->rx_coalesce_usecs * factor)) {
+		NL_SET_ERR_MSG_MOD(extack, "rx-usecs too large");
 		return -EINVAL;
+	}
 
-	if (nfp_net_coalesce_para_check(ec->tx_coalesce_usecs * factor,
-					ec->tx_max_coalesced_frames))
+	if (nfp_net_coalesce_para_check(ec->rx_max_coalesced_frames)) {
+		NL_SET_ERR_MSG_MOD(extack, "rx-frames too large");
 		return -EINVAL;
+	}
+
+	if (nfp_net_coalesce_para_check(ec->tx_coalesce_usecs * factor)) {
+		NL_SET_ERR_MSG_MOD(extack, "tx-usecs too large");
+		return -EINVAL;
+	}
+
+	if (nfp_net_coalesce_para_check(ec->tx_max_coalesced_frames)) {
+		NL_SET_ERR_MSG_MOD(extack, "tx-frames too large");
+		return -EINVAL;
+	}
 
 	/* configuration is valid */
 	nn->rx_coalesce_adapt_on = !!ec->use_adaptive_rx_coalesce;
@@ -1866,6 +2260,30 @@ static int nfp_net_set_channels(struct net_device *netdev,
 	return nfp_net_set_num_rings(nn, total_rx, total_tx);
 }
 
+static int nfp_port_set_pauseparam(struct net_device *netdev,
+				   struct ethtool_pauseparam *pause)
+{
+	struct nfp_eth_table_port *eth_port;
+	struct nfp_port *port;
+	int err;
+
+	port = nfp_port_from_netdev(netdev);
+	eth_port = nfp_port_get_eth_port(port);
+	if (!eth_port)
+		return -EOPNOTSUPP;
+
+	if (pause->autoneg != AUTONEG_DISABLE)
+		return -EOPNOTSUPP;
+
+	err = nfp_eth_set_pauseparam(port->app->cpp, eth_port->index,
+				     pause->tx_pause, pause->rx_pause);
+	if (!err)
+		/* Only refresh if we did something */
+		nfp_net_refresh_port_table(port);
+
+	return err < 0 ? err : 0;
+}
+
 static void nfp_port_get_pauseparam(struct net_device *netdev,
 				    struct ethtool_pauseparam *pause)
 {
@@ -1877,10 +2295,10 @@ static void nfp_port_get_pauseparam(struct net_device *netdev,
 	if (!eth_port)
 		return;
 
-	/* Currently pause frame support is fixed */
+	/* Currently pause frame autoneg is fixed */
 	pause->autoneg = AUTONEG_DISABLE;
-	pause->rx_pause = 1;
-	pause->tx_pause = 1;
+	pause->rx_pause = eth_port->rx_pause;
+	pause->tx_pause = eth_port->tx_pause;
 }
 
 static int nfp_net_set_phys_id(struct net_device *netdev,
@@ -2106,8 +2524,10 @@ static const struct ethtool_ops nfp_net_ethtool_ops = {
 	.set_link_ksettings	= nfp_net_set_link_ksettings,
 	.get_fecparam		= nfp_port_get_fecparam,
 	.set_fecparam		= nfp_port_set_fecparam,
+	.set_pauseparam		= nfp_port_set_pauseparam,
 	.get_pauseparam		= nfp_port_get_pauseparam,
 	.set_phys_id		= nfp_net_set_phys_id,
+	.get_ts_info		= ethtool_op_get_ts_info,
 };
 
 const struct ethtool_ops nfp_port_ethtool_ops = {
@@ -2130,6 +2550,7 @@ const struct ethtool_ops nfp_port_ethtool_ops = {
 	.set_link_ksettings	= nfp_net_set_link_ksettings,
 	.get_fecparam		= nfp_port_get_fecparam,
 	.set_fecparam		= nfp_port_set_fecparam,
+	.set_pauseparam		= nfp_port_set_pauseparam,
 	.get_pauseparam		= nfp_port_get_pauseparam,
 	.set_phys_id		= nfp_net_set_phys_id,
 };
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h
index 00264af13b49..dc0e405c1349 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h
@@ -189,6 +189,8 @@ enum nfp_ethtool_link_mode_list {
  * @ports.enabled:	is enabled?
  * @ports.tx_enabled:	is TX enabled?
  * @ports.rx_enabled:	is RX enabled?
+ * @ports.rx_pause:	Switch of RX pause frame
+ * @ports.tx_pause:	Switch of Tx pause frame
  * @ports.override_changed: is media reconfig pending?
  *
  * @ports.port_type:	one of %PORT_* defines for ethtool
@@ -227,6 +229,8 @@ struct nfp_eth_table {
 		bool tx_enabled;
 		bool rx_enabled;
 		bool supp_aneg;
+		bool rx_pause;
+		bool tx_pause;
 
 		bool override_changed;
 
@@ -255,6 +259,8 @@ int
 nfp_eth_set_fec(struct nfp_cpp *cpp, unsigned int idx, enum nfp_eth_fec mode);
 
 int nfp_eth_set_idmode(struct nfp_cpp *cpp, unsigned int idx, bool state);
+int nfp_eth_set_pauseparam(struct nfp_cpp *cpp, unsigned int idx,
+			   unsigned int tx_pause, unsigned int rx_pause);
 
 static inline bool nfp_eth_can_support_fec(struct nfp_eth_table_port *eth_port)
 {
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c
index 9d62085d772a..5cfddc9a5d87 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c
@@ -42,6 +42,8 @@
 #define NSP_ETH_STATE_ANEG		GENMASK_ULL(25, 23)
 #define NSP_ETH_STATE_FEC		GENMASK_ULL(27, 26)
 #define NSP_ETH_STATE_ACT_FEC		GENMASK_ULL(29, 28)
+#define NSP_ETH_STATE_TX_PAUSE		BIT_ULL(31)
+#define NSP_ETH_STATE_RX_PAUSE		BIT_ULL(32)
 
 #define NSP_ETH_CTRL_CONFIGURED		BIT_ULL(0)
 #define NSP_ETH_CTRL_ENABLED		BIT_ULL(1)
@@ -52,6 +54,8 @@
 #define NSP_ETH_CTRL_SET_ANEG		BIT_ULL(6)
 #define NSP_ETH_CTRL_SET_FEC		BIT_ULL(7)
 #define NSP_ETH_CTRL_SET_IDMODE		BIT_ULL(8)
+#define NSP_ETH_CTRL_SET_TX_PAUSE	BIT_ULL(10)
+#define NSP_ETH_CTRL_SET_RX_PAUSE	BIT_ULL(11)
 
 enum nfp_eth_raw {
 	NSP_ETH_RAW_PORT = 0,
@@ -180,6 +184,15 @@ nfp_eth_port_translate(struct nfp_nsp *nsp, const union eth_table_entry *src,
 
 	dst->act_fec = FIELD_GET(NSP_ETH_STATE_ACT_FEC, state);
 	dst->supp_aneg = FIELD_GET(NSP_ETH_PORT_SUPP_ANEG, port);
+
+	if (nfp_nsp_get_abi_ver_minor(nsp) < 37) {
+		dst->tx_pause = true;
+		dst->rx_pause = true;
+		return;
+	}
+
+	dst->tx_pause = FIELD_GET(NSP_ETH_STATE_TX_PAUSE, state);
+	dst->rx_pause = FIELD_GET(NSP_ETH_STATE_RX_PAUSE, state);
 }
 
 static void
@@ -497,7 +510,7 @@ int nfp_eth_set_configured(struct nfp_cpp *cpp, unsigned int idx, bool configed)
 static int
 nfp_eth_set_bit_config(struct nfp_nsp *nsp, unsigned int raw_idx,
 		       const u64 mask, const unsigned int shift,
-		       unsigned int val, const u64 ctrl_bit)
+		       u64 val, const u64 ctrl_bit)
 {
 	union eth_table_entry *entries = nfp_nsp_config_entries(nsp);
 	unsigned int idx = nfp_nsp_config_idx(nsp);
@@ -630,6 +643,81 @@ nfp_eth_set_fec(struct nfp_cpp *cpp, unsigned int idx, enum nfp_eth_fec mode)
 }
 
 /**
+ * __nfp_eth_set_txpause() - set tx pause control bit
+ * @nsp:	NFP NSP handle returned from nfp_eth_config_start()
+ * @tx_pause:	TX pause switch
+ *
+ * Set TX pause switch.
+ *
+ * Return: 0 or -ERRNO.
+ */
+static int __nfp_eth_set_txpause(struct nfp_nsp *nsp, unsigned int tx_pause)
+{
+	return NFP_ETH_SET_BIT_CONFIG(nsp, NSP_ETH_RAW_STATE, NSP_ETH_STATE_TX_PAUSE,
+				      tx_pause, NSP_ETH_CTRL_SET_TX_PAUSE);
+}
+
+/**
+ * __nfp_eth_set_rxpause() - set rx pause control bit
+ * @nsp:	NFP NSP handle returned from nfp_eth_config_start()
+ * @rx_pause:	RX pause switch
+ *
+ * Set RX pause switch.
+ *
+ * Return: 0 or -ERRNO.
+ */
+static int __nfp_eth_set_rxpause(struct nfp_nsp *nsp, unsigned int rx_pause)
+{
+	return NFP_ETH_SET_BIT_CONFIG(nsp, NSP_ETH_RAW_STATE, NSP_ETH_STATE_RX_PAUSE,
+				      rx_pause, NSP_ETH_CTRL_SET_RX_PAUSE);
+}
+
+/**
+ * nfp_eth_set_pauseparam() - Set TX/RX pause switch.
+ * @cpp:	NFP CPP handle
+ * @idx:	NFP chip-wide port index
+ * @tx_pause:	TX pause switch
+ * @rx_pause:	RX pause switch
+ *
+ * Return:
+ * 0 - configuration successful;
+ * 1 - no changes were needed;
+ * -ERRNO - configuration failed.
+ */
+int
+nfp_eth_set_pauseparam(struct nfp_cpp *cpp, unsigned int idx,
+		       unsigned int tx_pause, unsigned int rx_pause)
+{
+	struct nfp_nsp *nsp;
+	int err;
+
+	nsp = nfp_eth_config_start(cpp, idx);
+	if (IS_ERR(nsp))
+		return PTR_ERR(nsp);
+
+	if (nfp_nsp_get_abi_ver_minor(nsp) < 37) {
+		nfp_err(nfp_nsp_cpp(nsp),
+			"set pause parameter operation not supported, please update flash\n");
+		nfp_eth_config_cleanup_end(nsp);
+		return -EOPNOTSUPP;
+	}
+
+	err = __nfp_eth_set_txpause(nsp, tx_pause);
+	if (err) {
+		nfp_eth_config_cleanup_end(nsp);
+		return err;
+	}
+
+	err = __nfp_eth_set_rxpause(nsp, rx_pause);
+	if (err) {
+		nfp_eth_config_cleanup_end(nsp);
+		return err;
+	}
+
+	return nfp_eth_config_commit_end(nsp);
+}
+
+/**
  * __nfp_eth_set_speed() - set interface speed/rate
  * @nsp:	NFP NSP handle returned from nfp_eth_config_start()
  * @speed:	Desired speed (per lane)
diff --git a/drivers/net/ethernet/pensando/ionic/ionic.h b/drivers/net/ethernet/pensando/ionic/ionic.h
index 2453a40f6ee8..9ffef2e06885 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic.h
@@ -91,6 +91,4 @@ int ionic_port_identify(struct ionic *ionic);
 int ionic_port_init(struct ionic *ionic);
 int ionic_port_reset(struct ionic *ionic);
 
-const char *ionic_vf_attr_to_str(enum ionic_vf_attr attr);
-
 #endif /* _IONIC_H_ */
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
index d6ce113a4210..c49aa358e424 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
@@ -215,9 +215,16 @@ out:
 
 static void ionic_clear_pci(struct ionic *ionic)
 {
+	ionic->idev.dev_info_regs = NULL;
+	ionic->idev.dev_cmd_regs = NULL;
+	ionic->idev.intr_status = NULL;
+	ionic->idev.intr_ctrl = NULL;
+
 	ionic_unmap_bars(ionic);
 	pci_release_regions(ionic->pdev);
-	pci_disable_device(ionic->pdev);
+
+	if (atomic_read(&ionic->pdev->enable_cnt) > 0)
+		pci_disable_device(ionic->pdev);
 }
 
 static int ionic_setup_one(struct ionic *ionic)
@@ -389,9 +396,13 @@ static void ionic_remove(struct pci_dev *pdev)
 {
 	struct ionic *ionic = pci_get_drvdata(pdev);
 
-	del_timer_sync(&ionic->watchdog_timer);
+	timer_shutdown_sync(&ionic->watchdog_timer);
 
 	if (ionic->lif) {
+		/* prevent adminq cmds if already known as down */
+		if (test_and_clear_bit(IONIC_LIF_F_FW_RESET, ionic->lif->state))
+			set_bit(IONIC_LIF_F_FW_STOPPING, ionic->lif->state);
+
 		ionic_lif_unregister(ionic->lif);
 		ionic_devlink_unregister(ionic);
 		ionic_lif_deinit(ionic->lif);
@@ -416,6 +427,8 @@ static void ionic_reset_prepare(struct pci_dev *pdev)
 
 	dev_dbg(ionic->dev, "%s: device stopping\n", __func__);
 
+	set_bit(IONIC_LIF_F_FW_RESET, lif->state);
+
 	del_timer_sync(&ionic->watchdog_timer);
 	cancel_work_sync(&lif->deferred.work);
 
@@ -424,6 +437,7 @@ static void ionic_reset_prepare(struct pci_dev *pdev)
 	ionic_txrx_free(lif);
 	ionic_lif_deinit(lif);
 	ionic_qcqs_free(lif);
+	ionic_debugfs_del_lif(lif);
 	mutex_unlock(&lif->queue_lock);
 
 	ionic_dev_teardown(ionic);
@@ -455,10 +469,35 @@ err_out:
 		__func__, err ? "failed" : "done");
 }
 
+static pci_ers_result_t ionic_pci_error_detected(struct pci_dev *pdev,
+						 pci_channel_state_t error)
+{
+	if (error == pci_channel_io_frozen) {
+		ionic_reset_prepare(pdev);
+		return PCI_ERS_RESULT_NEED_RESET;
+	}
+
+	return PCI_ERS_RESULT_NONE;
+}
+
+static void ionic_pci_error_resume(struct pci_dev *pdev)
+{
+	struct ionic *ionic = pci_get_drvdata(pdev);
+	struct ionic_lif *lif = ionic->lif;
+
+	if (lif && test_bit(IONIC_LIF_F_FW_RESET, lif->state))
+		pci_reset_function_locked(pdev);
+}
+
 static const struct pci_error_handlers ionic_err_handler = {
 	/* FLR handling */
 	.reset_prepare      = ionic_reset_prepare,
 	.reset_done         = ionic_reset_done,
+
+	/* PCI bus error detected on this device */
+	.error_detected     = ionic_pci_error_detected,
+	.resume		    = ionic_pci_error_resume,
+
 };
 
 static struct pci_driver ionic_driver = {
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c
index c58217027564..91327ef670c7 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c
@@ -287,6 +287,9 @@ void ionic_debugfs_add_lif(struct ionic_lif *lif)
 
 void ionic_debugfs_del_lif(struct ionic_lif *lif)
 {
+	if (!lif->dentry)
+		return;
+
 	debugfs_remove_recursive(lif->dentry);
 	lif->dentry = NULL;
 }
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
index c06576f43916..1e7c71f7f081 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
@@ -165,9 +165,19 @@ void ionic_dev_teardown(struct ionic *ionic)
 }
 
 /* Devcmd Interface */
-bool ionic_is_fw_running(struct ionic_dev *idev)
+static bool __ionic_is_fw_running(struct ionic_dev *idev, u8 *status_ptr)
 {
-	u8 fw_status = ioread8(&idev->dev_info_regs->fw_status);
+	u8 fw_status;
+
+	if (!idev->dev_info_regs) {
+		if (status_ptr)
+			*status_ptr = 0xff;
+		return false;
+	}
+
+	fw_status = ioread8(&idev->dev_info_regs->fw_status);
+	if (status_ptr)
+		*status_ptr = fw_status;
 
 	/* firmware is useful only if the running bit is set and
 	 * fw_status != 0xff (bad PCI read)
@@ -175,6 +185,11 @@ bool ionic_is_fw_running(struct ionic_dev *idev)
 	return (fw_status != 0xff) && (fw_status & IONIC_FW_STS_F_RUNNING);
 }
 
+bool ionic_is_fw_running(struct ionic_dev *idev)
+{
+	return __ionic_is_fw_running(idev, NULL);
+}
+
 int ionic_heartbeat_check(struct ionic *ionic)
 {
 	unsigned long check_time, last_check_time;
@@ -199,10 +214,8 @@ do_check_time:
 		goto do_check_time;
 	}
 
-	fw_status = ioread8(&idev->dev_info_regs->fw_status);
-
 	/* If fw_status is not ready don't bother with the generation */
-	if (!ionic_is_fw_running(idev)) {
+	if (!__ionic_is_fw_running(idev, &fw_status)) {
 		fw_status_ready = false;
 	} else {
 		fw_generation = fw_status & IONIC_FW_STS_F_GENERATION;
@@ -321,6 +334,7 @@ void ionic_dev_cmd_comp(struct ionic_dev *idev, union ionic_dev_cmd_comp *comp)
 
 void ionic_dev_cmd_go(struct ionic_dev *idev, union ionic_dev_cmd *cmd)
 {
+	idev->opcode = cmd->cmd.opcode;
 	memcpy_toio(&idev->dev_cmd_regs->cmd, cmd, sizeof(*cmd));
 	iowrite32(0, &idev->dev_cmd_regs->done);
 	iowrite32(1, &idev->dev_cmd_regs->doorbell);
@@ -469,46 +483,6 @@ int ionic_set_vf_config(struct ionic *ionic, int vf,
 	return err;
 }
 
-int ionic_dev_cmd_vf_getattr(struct ionic *ionic, int vf, u8 attr,
-			     struct ionic_vf_getattr_comp *comp)
-{
-	union ionic_dev_cmd cmd = {
-		.vf_getattr.opcode = IONIC_CMD_VF_GETATTR,
-		.vf_getattr.attr = attr,
-		.vf_getattr.vf_index = cpu_to_le16(vf),
-	};
-	int err;
-
-	if (vf >= ionic->num_vfs)
-		return -EINVAL;
-
-	switch (attr) {
-	case IONIC_VF_ATTR_SPOOFCHK:
-	case IONIC_VF_ATTR_TRUST:
-	case IONIC_VF_ATTR_LINKSTATE:
-	case IONIC_VF_ATTR_MAC:
-	case IONIC_VF_ATTR_VLAN:
-	case IONIC_VF_ATTR_RATE:
-		break;
-	case IONIC_VF_ATTR_STATSADDR:
-	default:
-		return -EINVAL;
-	}
-
-	mutex_lock(&ionic->dev_cmd_lock);
-	ionic_dev_cmd_go(&ionic->idev, &cmd);
-	err = ionic_dev_cmd_wait_nomsg(ionic, DEVCMD_TIMEOUT);
-	memcpy_fromio(comp, &ionic->idev.dev_cmd_regs->comp.vf_getattr,
-		      sizeof(*comp));
-	mutex_unlock(&ionic->dev_cmd_lock);
-
-	if (err && comp->status != IONIC_RC_ENOSUPP)
-		ionic_dev_cmd_dev_err_print(ionic, cmd.vf_getattr.opcode,
-					    comp->status, err);
-
-	return err;
-}
-
 void ionic_vf_start(struct ionic *ionic)
 {
 	union ionic_dev_cmd cmd = {
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
index 1dbc3cb50b1d..2667e1cde16b 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
@@ -153,6 +153,7 @@ struct ionic_dev {
 	bool fw_hb_ready;
 	bool fw_status_ready;
 	u8 fw_generation;
+	u8 opcode;
 
 	u64 __iomem *db_pages;
 	dma_addr_t phy_db_pages;
@@ -223,7 +224,7 @@ struct ionic_desc_info {
 	void *cb_arg;
 };
 
-#define IONIC_QUEUE_NAME_MAX_SZ		32
+#define IONIC_QUEUE_NAME_MAX_SZ		16
 
 struct ionic_queue {
 	struct device *dev;
@@ -269,12 +270,12 @@ struct ionic_queue {
 
 struct ionic_intr_info {
 	char name[IONIC_INTR_NAME_MAX_SZ];
+	u64 rearm_count;
 	unsigned int index;
 	unsigned int vector;
-	u64 rearm_count;
 	unsigned int cpu;
-	cpumask_t affinity_mask;
 	u32 dim_coal_hw;
+	cpumask_t affinity_mask;
 };
 
 struct ionic_cq {
@@ -341,8 +342,7 @@ void ionic_dev_cmd_port_pause(struct ionic_dev *idev, u8 pause_type);
 
 int ionic_set_vf_config(struct ionic *ionic, int vf,
 			struct ionic_vf_setattr_cmd *vfc);
-int ionic_dev_cmd_vf_getattr(struct ionic *ionic, int vf, u8 attr,
-			     struct ionic_vf_getattr_comp *comp);
+
 void ionic_dev_cmd_queue_identify(struct ionic_dev *idev,
 				  u16 lif_type, u8 qtype, u8 qver);
 void ionic_vf_start(struct ionic *ionic);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
index 3a6b0a9bc241..cd3c0b01402e 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
@@ -823,36 +823,38 @@ static u32 ionic_get_rxfh_key_size(struct net_device *netdev)
 	return IONIC_RSS_HASH_KEY_SIZE;
 }
 
-static int ionic_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			  u8 *hfunc)
+static int ionic_get_rxfh(struct net_device *netdev,
+			  struct ethtool_rxfh_param *rxfh)
 {
 	struct ionic_lif *lif = netdev_priv(netdev);
 	unsigned int i, tbl_sz;
 
-	if (indir) {
+	if (rxfh->indir) {
 		tbl_sz = le16_to_cpu(lif->ionic->ident.lif.eth.rss_ind_tbl_sz);
 		for (i = 0; i < tbl_sz; i++)
-			indir[i] = lif->rss_ind_tbl[i];
+			rxfh->indir[i] = lif->rss_ind_tbl[i];
 	}
 
-	if (key)
-		memcpy(key, lif->rss_hash_key, IONIC_RSS_HASH_KEY_SIZE);
+	if (rxfh->key)
+		memcpy(rxfh->key, lif->rss_hash_key, IONIC_RSS_HASH_KEY_SIZE);
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	return 0;
 }
 
-static int ionic_set_rxfh(struct net_device *netdev, const u32 *indir,
-			  const u8 *key, const u8 hfunc)
+static int ionic_set_rxfh(struct net_device *netdev,
+			  struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
 {
 	struct ionic_lif *lif = netdev_priv(netdev);
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	return ionic_lif_rss_config(lif, lif->rss_types, key, indir);
+	return ionic_lif_rss_config(lif, lif->rss_types,
+				    rxfh->key, rxfh->indir);
 }
 
 static int ionic_set_tunable(struct net_device *dev,
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index edc14730ce88..cf2d5ad7b68c 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -49,24 +49,24 @@ static void ionic_lif_queue_identify(struct ionic_lif *lif);
 static void ionic_dim_work(struct work_struct *work)
 {
 	struct dim *dim = container_of(work, struct dim, work);
+	struct ionic_intr_info *intr;
 	struct dim_cq_moder cur_moder;
 	struct ionic_qcq *qcq;
+	struct ionic_lif *lif;
 	u32 new_coal;
 
 	cur_moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
 	qcq = container_of(dim, struct ionic_qcq, dim);
-	new_coal = ionic_coal_usec_to_hw(qcq->q.lif->ionic, cur_moder.usec);
+	lif = qcq->q.lif;
+	new_coal = ionic_coal_usec_to_hw(lif->ionic, cur_moder.usec);
 	new_coal = new_coal ? new_coal : 1;
 
-	if (qcq->intr.dim_coal_hw != new_coal) {
-		unsigned int qi = qcq->cq.bound_q->index;
-		struct ionic_lif *lif = qcq->q.lif;
-
-		qcq->intr.dim_coal_hw = new_coal;
+	intr = &qcq->intr;
+	if (intr->dim_coal_hw != new_coal) {
+		intr->dim_coal_hw = new_coal;
 
 		ionic_intr_coal_init(lif->ionic->idev.intr_ctrl,
-				     lif->rxqcqs[qi]->intr.index,
-				     qcq->intr.dim_coal_hw);
+				     intr->index, intr->dim_coal_hw);
 	}
 
 	dim->state = DIM_START_MEASURE;
@@ -424,14 +424,10 @@ static void ionic_qcq_free(struct ionic_lif *lif, struct ionic_qcq *qcq)
 
 	ionic_qcq_intr_free(lif, qcq);
 
-	if (qcq->cq.info) {
-		vfree(qcq->cq.info);
-		qcq->cq.info = NULL;
-	}
-	if (qcq->q.info) {
-		vfree(qcq->q.info);
-		qcq->q.info = NULL;
-	}
+	vfree(qcq->cq.info);
+	qcq->cq.info = NULL;
+	vfree(qcq->q.info);
+	qcq->q.info = NULL;
 }
 
 void ionic_qcqs_free(struct ionic_lif *lif)
@@ -2332,82 +2328,11 @@ static int ionic_eth_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd
 	}
 }
 
-static int ionic_get_fw_vf_config(struct ionic *ionic, int vf, struct ionic_vf *vfdata)
-{
-	struct ionic_vf_getattr_comp comp = { 0 };
-	int err;
-	u8 attr;
-
-	attr = IONIC_VF_ATTR_VLAN;
-	err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp);
-	if (err && comp.status != IONIC_RC_ENOSUPP)
-		goto err_out;
-	if (!err)
-		vfdata->vlanid = comp.vlanid;
-
-	attr = IONIC_VF_ATTR_SPOOFCHK;
-	err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp);
-	if (err && comp.status != IONIC_RC_ENOSUPP)
-		goto err_out;
-	if (!err)
-		vfdata->spoofchk = comp.spoofchk;
-
-	attr = IONIC_VF_ATTR_LINKSTATE;
-	err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp);
-	if (err && comp.status != IONIC_RC_ENOSUPP)
-		goto err_out;
-	if (!err) {
-		switch (comp.linkstate) {
-		case IONIC_VF_LINK_STATUS_UP:
-			vfdata->linkstate = IFLA_VF_LINK_STATE_ENABLE;
-			break;
-		case IONIC_VF_LINK_STATUS_DOWN:
-			vfdata->linkstate = IFLA_VF_LINK_STATE_DISABLE;
-			break;
-		case IONIC_VF_LINK_STATUS_AUTO:
-			vfdata->linkstate = IFLA_VF_LINK_STATE_AUTO;
-			break;
-		default:
-			dev_warn(ionic->dev, "Unexpected link state %u\n", comp.linkstate);
-			break;
-		}
-	}
-
-	attr = IONIC_VF_ATTR_RATE;
-	err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp);
-	if (err && comp.status != IONIC_RC_ENOSUPP)
-		goto err_out;
-	if (!err)
-		vfdata->maxrate = comp.maxrate;
-
-	attr = IONIC_VF_ATTR_TRUST;
-	err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp);
-	if (err && comp.status != IONIC_RC_ENOSUPP)
-		goto err_out;
-	if (!err)
-		vfdata->trusted = comp.trust;
-
-	attr = IONIC_VF_ATTR_MAC;
-	err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp);
-	if (err && comp.status != IONIC_RC_ENOSUPP)
-		goto err_out;
-	if (!err)
-		ether_addr_copy(vfdata->macaddr, comp.macaddr);
-
-err_out:
-	if (err)
-		dev_err(ionic->dev, "Failed to get %s for VF %d\n",
-			ionic_vf_attr_to_str(attr), vf);
-
-	return err;
-}
-
 static int ionic_get_vf_config(struct net_device *netdev,
 			       int vf, struct ifla_vf_info *ivf)
 {
 	struct ionic_lif *lif = netdev_priv(netdev);
 	struct ionic *ionic = lif->ionic;
-	struct ionic_vf vfdata = { 0 };
 	int ret = 0;
 
 	if (!netif_device_present(netdev))
@@ -2418,18 +2343,16 @@ static int ionic_get_vf_config(struct net_device *netdev,
 	if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
 		ret = -EINVAL;
 	} else {
-		ivf->vf = vf;
-		ivf->qos = 0;
-
-		ret = ionic_get_fw_vf_config(ionic, vf, &vfdata);
-		if (!ret) {
-			ivf->vlan         = le16_to_cpu(vfdata.vlanid);
-			ivf->spoofchk     = vfdata.spoofchk;
-			ivf->linkstate    = vfdata.linkstate;
-			ivf->max_tx_rate  = le32_to_cpu(vfdata.maxrate);
-			ivf->trusted      = vfdata.trusted;
-			ether_addr_copy(ivf->mac, vfdata.macaddr);
-		}
+		struct ionic_vf *vfdata = &ionic->vfs[vf];
+
+		ivf->vf		  = vf;
+		ivf->qos	  = 0;
+		ivf->vlan         = le16_to_cpu(vfdata->vlanid);
+		ivf->spoofchk     = vfdata->spoofchk;
+		ivf->linkstate    = vfdata->linkstate;
+		ivf->max_tx_rate  = le32_to_cpu(vfdata->maxrate);
+		ivf->trusted      = vfdata->trusted;
+		ether_addr_copy(ivf->mac, vfdata->macaddr);
 	}
 
 	up_read(&ionic->vf_op_lock);
@@ -3127,6 +3050,7 @@ int ionic_lif_alloc(struct ionic *ionic)
 	lif = netdev_priv(netdev);
 	lif->netdev = netdev;
 	ionic->lif = lif;
+	lif->ionic = ionic;
 	netdev->netdev_ops = &ionic_netdev_ops;
 	ionic_ethtool_set_ops(netdev);
 
@@ -3149,7 +3073,6 @@ int ionic_lif_alloc(struct ionic *ionic)
 	lif->neqs = ionic->neqs_per_lif;
 	lif->nxqs = ionic->ntxqs_per_lif;
 
-	lif->ionic = ionic;
 	lif->index = 0;
 
 	if (is_kdump_kernel()) {
@@ -3238,6 +3161,9 @@ static void ionic_lif_reset(struct ionic_lif *lif)
 {
 	struct ionic_dev *idev = &lif->ionic->idev;
 
+	if (!ionic_is_fw_running(idev))
+		return;
+
 	mutex_lock(&lif->ionic->dev_cmd_lock);
 	ionic_dev_cmd_lif_reset(idev, lif->index);
 	ionic_dev_cmd_wait(lif->ionic, DEVCMD_TIMEOUT);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
index 457c24195ca6..61548b3eea93 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
@@ -312,6 +312,11 @@ static inline u32 ionic_coal_usec_to_hw(struct ionic *ionic, u32 usecs)
 	return (usecs * mult) / div;
 }
 
+static inline bool ionic_txq_hwstamp_enabled(struct ionic_queue *q)
+{
+	return unlikely(q->features & IONIC_TXQ_F_HWSTAMP);
+}
+
 void ionic_link_status_check_request(struct ionic_lif *lif, bool can_sleep);
 void ionic_get_stats64(struct net_device *netdev,
 		       struct rtnl_link_stats64 *ns);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
index 835577392178..165ab08ad2dd 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
@@ -188,28 +188,6 @@ static const char *ionic_opcode_to_str(enum ionic_cmd_opcode opcode)
 	}
 }
 
-const char *ionic_vf_attr_to_str(enum ionic_vf_attr attr)
-{
-	switch (attr) {
-	case IONIC_VF_ATTR_SPOOFCHK:
-		return "IONIC_VF_ATTR_SPOOFCHK";
-	case IONIC_VF_ATTR_TRUST:
-		return "IONIC_VF_ATTR_TRUST";
-	case IONIC_VF_ATTR_LINKSTATE:
-		return "IONIC_VF_ATTR_LINKSTATE";
-	case IONIC_VF_ATTR_MAC:
-		return "IONIC_VF_ATTR_MAC";
-	case IONIC_VF_ATTR_VLAN:
-		return "IONIC_VF_ATTR_VLAN";
-	case IONIC_VF_ATTR_RATE:
-		return "IONIC_VF_ATTR_RATE";
-	case IONIC_VF_ATTR_STATSADDR:
-		return "IONIC_VF_ATTR_STATSADDR";
-	default:
-		return "IONIC_VF_ATTR_UNKNOWN";
-	}
-}
-
 static void ionic_adminq_flush(struct ionic_lif *lif)
 {
 	struct ionic_desc_info *desc_info;
@@ -410,22 +388,28 @@ int ionic_adminq_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx,
 				      do_msg);
 }
 
-int ionic_adminq_post_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx)
+static int __ionic_adminq_post_wait(struct ionic_lif *lif,
+				    struct ionic_admin_ctx *ctx,
+				    const bool do_msg)
 {
 	int err;
 
+	if (!ionic_is_fw_running(&lif->ionic->idev))
+		return 0;
+
 	err = ionic_adminq_post(lif, ctx);
 
-	return ionic_adminq_wait(lif, ctx, err, true);
+	return ionic_adminq_wait(lif, ctx, err, do_msg);
 }
 
-int ionic_adminq_post_wait_nomsg(struct ionic_lif *lif, struct ionic_admin_ctx *ctx)
+int ionic_adminq_post_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx)
 {
-	int err;
-
-	err = ionic_adminq_post(lif, ctx);
+	return __ionic_adminq_post_wait(lif, ctx, true);
+}
 
-	return ionic_adminq_wait(lif, ctx, err, false);
+int ionic_adminq_post_wait_nomsg(struct ionic_lif *lif, struct ionic_admin_ctx *ctx)
+{
+	return __ionic_adminq_post_wait(lif, ctx, false);
 }
 
 static void ionic_dev_cmd_clean(struct ionic *ionic)
@@ -465,7 +449,7 @@ static int __ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds,
 	 */
 	max_wait = jiffies + (max_seconds * HZ);
 try_again:
-	opcode = readb(&idev->dev_cmd_regs->cmd.cmd.opcode);
+	opcode = idev->opcode;
 	start_time = jiffies;
 	for (fw_up = ionic_is_fw_running(idev);
 	     !done && fw_up && time_before(jiffies, max_wait);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_stats.c b/drivers/net/ethernet/pensando/ionic/ionic_stats.c
index 9859a4432985..1f6022fb7679 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_stats.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_stats.c
@@ -258,10 +258,10 @@ static void ionic_sw_stats_get_strings(struct ionic_lif *lif, u8 **buf)
 	int i, q_num;
 
 	for (i = 0; i < IONIC_NUM_LIF_STATS; i++)
-		ethtool_sprintf(buf, ionic_lif_stats_desc[i].name);
+		ethtool_puts(buf, ionic_lif_stats_desc[i].name);
 
 	for (i = 0; i < IONIC_NUM_PORT_STATS; i++)
-		ethtool_sprintf(buf, ionic_port_stats_desc[i].name);
+		ethtool_puts(buf, ionic_port_stats_desc[i].name);
 
 	for (q_num = 0; q_num < MAX_Q(lif); q_num++)
 		ionic_sw_stats_get_tx_strings(lif, buf, q_num);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index ccc1b1d407e4..54cd96b035d6 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -803,7 +803,7 @@ static void ionic_tx_clean(struct ionic_queue *q,
 
 	qi = skb_get_queue_mapping(skb);
 
-	if (unlikely(q->features & IONIC_TXQ_F_HWSTAMP)) {
+	if (ionic_txq_hwstamp_enabled(q)) {
 		if (cq_info) {
 			struct skb_shared_hwtstamps hwts = {};
 			__le64 *cq_desc_hwstamp;
@@ -870,7 +870,7 @@ bool ionic_tx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info)
 		desc_info->cb_arg = NULL;
 	} while (index != le16_to_cpu(comp->comp_index));
 
-	if (pkts && bytes && !unlikely(q->features & IONIC_TXQ_F_HWSTAMP))
+	if (pkts && bytes && !ionic_txq_hwstamp_enabled(q))
 		netdev_tx_completed_queue(q_to_ndq(q), pkts, bytes);
 
 	return true;
@@ -908,7 +908,7 @@ void ionic_tx_empty(struct ionic_queue *q)
 		desc_info->cb_arg = NULL;
 	}
 
-	if (pkts && bytes && !unlikely(q->features & IONIC_TXQ_F_HWSTAMP))
+	if (pkts && bytes && !ionic_txq_hwstamp_enabled(q))
 		netdev_tx_completed_queue(q_to_ndq(q), pkts, bytes);
 }
 
@@ -986,7 +986,7 @@ static void ionic_tx_tso_post(struct ionic_queue *q,
 
 	if (start) {
 		skb_tx_timestamp(skb);
-		if (!unlikely(q->features & IONIC_TXQ_F_HWSTAMP))
+		if (!ionic_txq_hwstamp_enabled(q))
 			netdev_tx_sent_queue(q_to_ndq(q), skb->len);
 		ionic_txq_post(q, false, ionic_tx_clean, skb);
 	} else {
@@ -1233,7 +1233,7 @@ static int ionic_tx(struct ionic_queue *q, struct sk_buff *skb)
 	stats->pkts++;
 	stats->bytes += skb->len;
 
-	if (!unlikely(q->features & IONIC_TXQ_F_HWSTAMP))
+	if (!ionic_txq_hwstamp_enabled(q))
 		netdev_tx_sent_queue(q_to_ndq(q), skb->len);
 	ionic_txq_post(q, !netdev_xmit_more(), ionic_tx_clean, skb);
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index 65e20693c549..33f4f58ee51c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -933,6 +933,7 @@ static void qed_ilt_shadow_free(struct qed_hwfn *p_hwfn)
 		p_dma->virt_addr = NULL;
 	}
 	kfree(p_mngr->ilt_shadow);
+	p_mngr->ilt_shadow = NULL;
 }
 
 static int qed_ilt_blk_alloc(struct qed_hwfn *p_hwfn,
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index b6b849a079ed..0e240b5ab8d4 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -1370,28 +1370,29 @@ static u32 qede_get_rxfh_key_size(struct net_device *dev)
 	return sizeof(edev->rss_key);
 }
 
-static int qede_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, u8 *hfunc)
+static int qede_get_rxfh(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh)
 {
 	struct qede_dev *edev = netdev_priv(dev);
 	int i;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
 	for (i = 0; i < QED_RSS_IND_TABLE_SIZE; i++)
-		indir[i] = edev->rss_ind_table[i];
+		rxfh->indir[i] = edev->rss_ind_table[i];
 
-	if (key)
-		memcpy(key, edev->rss_key, qede_get_rxfh_key_size(dev));
+	if (rxfh->key)
+		memcpy(rxfh->key, edev->rss_key, qede_get_rxfh_key_size(dev));
 
 	return 0;
 }
 
-static int qede_set_rxfh(struct net_device *dev, const u32 *indir,
-			 const u8 *key, const u8 hfunc)
+static int qede_set_rxfh(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
 	struct qed_update_vport_params *vport_update_params;
 	struct qede_dev *edev = netdev_priv(dev);
@@ -1403,20 +1404,21 @@ static int qede_set_rxfh(struct net_device *dev, const u32 *indir,
 		return -EOPNOTSUPP;
 	}
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (!indir && !key)
+	if (!rxfh->indir && !rxfh->key)
 		return 0;
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < QED_RSS_IND_TABLE_SIZE; i++)
-			edev->rss_ind_table[i] = indir[i];
+			edev->rss_ind_table[i] = rxfh->indir[i];
 		edev->rss_params_inited |= QEDE_RSS_INDIR_INITED;
 	}
 
-	if (key) {
-		memcpy(&edev->rss_key, key, qede_get_rxfh_key_size(dev));
+	if (rxfh->key) {
+		memcpy(&edev->rss_key, rxfh->key, qede_get_rxfh_key_size(dev));
 		edev->rss_params_inited |= QEDE_RSS_KEY_INITED;
 	}
 
diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c
index 0d57ffcedf0c..fc78bc959ded 100644
--- a/drivers/net/ethernet/qlogic/qla3xxx.c
+++ b/drivers/net/ethernet/qlogic/qla3xxx.c
@@ -2591,6 +2591,7 @@ static int ql_alloc_buffer_queues(struct ql3_adapter *qdev)
 
 	if (qdev->lrg_buf_q_alloc_virt_addr == NULL) {
 		netdev_err(qdev->ndev, "lBufQ failed\n");
+		kfree(qdev->lrg_buf);
 		return -ENOMEM;
 	}
 	qdev->lrg_buf_q_virt_addr = qdev->lrg_buf_q_alloc_virt_addr;
@@ -2615,6 +2616,7 @@ static int ql_alloc_buffer_queues(struct ql3_adapter *qdev)
 				  qdev->lrg_buf_q_alloc_size,
 				  qdev->lrg_buf_q_alloc_virt_addr,
 				  qdev->lrg_buf_q_alloc_phy_addr);
+		kfree(qdev->lrg_buf);
 		return -ENOMEM;
 	}
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
index c95d56e56c59..b733374b4dc5 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
@@ -2092,8 +2092,8 @@ static int qlcnic_83xx_run_post(struct qlcnic_adapter *adapter)
 		return -EINVAL;
 	}
 
-	strncpy(fw_info->fw_file_name, QLC_83XX_POST_FW_FILE_NAME,
-		QLC_FW_FILE_NAME_LEN);
+	strscpy(fw_info->fw_file_name, QLC_83XX_POST_FW_FILE_NAME,
+		sizeof(fw_info->fw_file_name));
 
 	ret = request_firmware(&fw_info->fw, fw_info->fw_file_name, dev);
 	if (ret) {
@@ -2396,12 +2396,12 @@ static int qlcnic_83xx_get_fw_info(struct qlcnic_adapter *adapter)
 		switch (pdev->device) {
 		case PCI_DEVICE_ID_QLOGIC_QLE834X:
 		case PCI_DEVICE_ID_QLOGIC_QLE8830:
-			strncpy(fw_info->fw_file_name, QLC_83XX_FW_FILE_NAME,
-				QLC_FW_FILE_NAME_LEN);
+			strscpy(fw_info->fw_file_name, QLC_83XX_FW_FILE_NAME,
+				sizeof(fw_info->fw_file_name));
 			break;
 		case PCI_DEVICE_ID_QLOGIC_QLE844X:
-			strncpy(fw_info->fw_file_name, QLC_84XX_FW_FILE_NAME,
-				QLC_FW_FILE_NAME_LEN);
+			strscpy(fw_info->fw_file_name, QLC_84XX_FW_FILE_NAME,
+				sizeof(fw_info->fw_file_name));
 			break;
 		default:
 			dev_err(&pdev->dev, "%s: Invalid device id\n",
diff --git a/drivers/net/ethernet/qualcomm/qca_debug.c b/drivers/net/ethernet/qualcomm/qca_debug.c
index 6f2fa2a42770..1822f2ad8f0d 100644
--- a/drivers/net/ethernet/qualcomm/qca_debug.c
+++ b/drivers/net/ethernet/qualcomm/qca_debug.c
@@ -30,6 +30,8 @@
 
 #define QCASPI_MAX_REGS 0x20
 
+#define QCASPI_RX_MAX_FRAMES 4
+
 static const u16 qcaspi_spi_regs[] = {
 	SPI_REG_BFR_SIZE,
 	SPI_REG_WRBUF_SPC_AVA,
@@ -252,9 +254,9 @@ qcaspi_get_ringparam(struct net_device *dev, struct ethtool_ringparam *ring,
 {
 	struct qcaspi *qca = netdev_priv(dev);
 
-	ring->rx_max_pending = 4;
+	ring->rx_max_pending = QCASPI_RX_MAX_FRAMES;
 	ring->tx_max_pending = TX_RING_MAX_LEN;
-	ring->rx_pending = 4;
+	ring->rx_pending = QCASPI_RX_MAX_FRAMES;
 	ring->tx_pending = qca->txr.count;
 }
 
@@ -263,22 +265,21 @@ qcaspi_set_ringparam(struct net_device *dev, struct ethtool_ringparam *ring,
 		     struct kernel_ethtool_ringparam *kernel_ring,
 		     struct netlink_ext_ack *extack)
 {
-	const struct net_device_ops *ops = dev->netdev_ops;
 	struct qcaspi *qca = netdev_priv(dev);
 
-	if ((ring->rx_pending) ||
+	if (ring->rx_pending != QCASPI_RX_MAX_FRAMES ||
 	    (ring->rx_mini_pending) ||
 	    (ring->rx_jumbo_pending))
 		return -EINVAL;
 
-	if (netif_running(dev))
-		ops->ndo_stop(dev);
+	if (qca->spi_thread)
+		kthread_park(qca->spi_thread);
 
 	qca->txr.count = max_t(u32, ring->tx_pending, TX_RING_MIN_LEN);
 	qca->txr.count = min_t(u16, qca->txr.count, TX_RING_MAX_LEN);
 
-	if (netif_running(dev))
-		ops->ndo_open(dev);
+	if (qca->spi_thread)
+		kthread_unpark(qca->spi_thread);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index bec723028e96..5f3c11fb3fa2 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -580,6 +580,18 @@ qcaspi_spi_thread(void *data)
 	netdev_info(qca->net_dev, "SPI thread created\n");
 	while (!kthread_should_stop()) {
 		set_current_state(TASK_INTERRUPTIBLE);
+		if (kthread_should_park()) {
+			netif_tx_disable(qca->net_dev);
+			netif_carrier_off(qca->net_dev);
+			qcaspi_flush_tx_ring(qca);
+			kthread_parkme();
+			if (qca->sync == QCASPI_SYNC_READY) {
+				netif_carrier_on(qca->net_dev);
+				netif_wake_queue(qca->net_dev);
+			}
+			continue;
+		}
+
 		if ((qca->intr_req == qca->intr_svc) &&
 		    !qca->txr.skb[qca->txr.head])
 			schedule();
@@ -608,11 +620,17 @@ qcaspi_spi_thread(void *data)
 			if (intr_cause & SPI_INT_CPU_ON) {
 				qcaspi_qca7k_sync(qca, QCASPI_EVENT_CPUON);
 
+				/* Frame decoding in progress */
+				if (qca->frm_handle.state != qca->frm_handle.init)
+					qca->net_dev->stats.rx_dropped++;
+
+				qcafrm_fsm_init_spi(&qca->frm_handle);
+				qca->stats.device_reset++;
+
 				/* not synced. */
 				if (qca->sync != QCASPI_SYNC_READY)
 					continue;
 
-				qca->stats.device_reset++;
 				netif_wake_queue(qca->net_dev);
 				netif_carrier_on(qca->net_dev);
 			}
diff --git a/drivers/net/ethernet/realtek/Kconfig b/drivers/net/ethernet/realtek/Kconfig
index 93d9df55b361..03015b665f4e 100644
--- a/drivers/net/ethernet/realtek/Kconfig
+++ b/drivers/net/ethernet/realtek/Kconfig
@@ -113,4 +113,11 @@ config R8169
 	  To compile this driver as a module, choose M here: the module
 	  will be called r8169.  This is recommended.
 
+config R8169_LEDS
+	def_bool R8169 && LEDS_TRIGGER_NETDEV
+	depends on !(R8169=y && LEDS_CLASS=m)
+	help
+	  Optional support for controlling the NIC LED's with the netdev
+	  LED trigger.
+
 endif # NET_VENDOR_REALTEK
diff --git a/drivers/net/ethernet/realtek/Makefile b/drivers/net/ethernet/realtek/Makefile
index 2e1d78b106b0..635491d8826e 100644
--- a/drivers/net/ethernet/realtek/Makefile
+++ b/drivers/net/ethernet/realtek/Makefile
@@ -6,5 +6,6 @@
 obj-$(CONFIG_8139CP) += 8139cp.o
 obj-$(CONFIG_8139TOO) += 8139too.o
 obj-$(CONFIG_ATP) += atp.o
-r8169-objs += r8169_main.o r8169_firmware.o r8169_phy_config.o
+r8169-y += r8169_main.o r8169_firmware.o r8169_phy_config.o
+r8169-$(CONFIG_R8169_LEDS) += r8169_leds.o
 obj-$(CONFIG_R8169) += r8169.o
diff --git a/drivers/net/ethernet/realtek/r8169.h b/drivers/net/ethernet/realtek/r8169.h
index 55ef8251feb5..81567fcf3957 100644
--- a/drivers/net/ethernet/realtek/r8169.h
+++ b/drivers/net/ethernet/realtek/r8169.h
@@ -8,6 +8,7 @@
  * See MAINTAINERS file for support contact information.
  */
 
+#include <linux/netdevice.h>
 #include <linux/types.h>
 #include <linux/phy.h>
 
@@ -77,3 +78,9 @@ u16 rtl8168h_2_get_adc_bias_ioffset(struct rtl8169_private *tp);
 u8 rtl8168d_efuse_read(struct rtl8169_private *tp, int reg_addr);
 void r8169_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev,
 			 enum mac_version ver);
+
+void r8169_get_led_name(struct rtl8169_private *tp, int idx,
+			char *buf, int buf_len);
+int rtl8168_get_led_mode(struct rtl8169_private *tp);
+int rtl8168_led_mod_ctrl(struct rtl8169_private *tp, u16 mask, u16 val);
+void rtl8168_init_leds(struct net_device *ndev);
diff --git a/drivers/net/ethernet/realtek/r8169_firmware.c b/drivers/net/ethernet/realtek/r8169_firmware.c
index cbc6b846ded5..ed6e721b1555 100644
--- a/drivers/net/ethernet/realtek/r8169_firmware.c
+++ b/drivers/net/ethernet/realtek/r8169_firmware.c
@@ -151,9 +151,6 @@ void rtl_fw_write_firmware(struct rtl8169_private *tp, struct rtl_fw *rtl_fw)
 		u32 regno = (action & 0x0fff0000) >> 16;
 		enum rtl_fw_opcode opcode = action >> 28;
 
-		if (!action)
-			break;
-
 		switch (opcode) {
 		case PHY_READ:
 			predata = fw_read(tp, regno);
diff --git a/drivers/net/ethernet/realtek/r8169_leds.c b/drivers/net/ethernet/realtek/r8169_leds.c
new file mode 100644
index 000000000000..007d077edcad
--- /dev/null
+++ b/drivers/net/ethernet/realtek/r8169_leds.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* r8169_leds.c: Realtek 8169/8168/8101/8125 ethernet driver.
+ *
+ * Copyright (c) 2023 Heiner Kallweit <hkallweit1@gmail.com>
+ *
+ * See MAINTAINERS file for support contact information.
+ */
+
+#include <linux/leds.h>
+#include <linux/netdevice.h>
+#include <uapi/linux/uleds.h>
+
+#include "r8169.h"
+
+#define RTL8168_LED_CTRL_OPTION2	BIT(15)
+#define RTL8168_LED_CTRL_ACT		BIT(3)
+#define RTL8168_LED_CTRL_LINK_1000	BIT(2)
+#define RTL8168_LED_CTRL_LINK_100	BIT(1)
+#define RTL8168_LED_CTRL_LINK_10	BIT(0)
+
+#define RTL8168_NUM_LEDS		3
+
+#define RTL8168_SUPPORTED_MODES \
+	(BIT(TRIGGER_NETDEV_LINK_1000) | BIT(TRIGGER_NETDEV_LINK_100) | \
+	 BIT(TRIGGER_NETDEV_LINK_10) | BIT(TRIGGER_NETDEV_RX) | \
+	 BIT(TRIGGER_NETDEV_TX))
+
+struct r8169_led_classdev {
+	struct led_classdev led;
+	struct net_device *ndev;
+	int index;
+};
+
+#define lcdev_to_r8169_ldev(lcdev) container_of(lcdev, struct r8169_led_classdev, led)
+
+static int rtl8168_led_hw_control_is_supported(struct led_classdev *led_cdev,
+					       unsigned long flags)
+{
+	struct r8169_led_classdev *ldev = lcdev_to_r8169_ldev(led_cdev);
+	struct rtl8169_private *tp = netdev_priv(ldev->ndev);
+	int shift = ldev->index * 4;
+	bool rx, tx;
+
+	if (flags & ~RTL8168_SUPPORTED_MODES)
+		goto nosupp;
+
+	rx = flags & BIT(TRIGGER_NETDEV_RX);
+	tx = flags & BIT(TRIGGER_NETDEV_TX);
+	if (rx != tx)
+		goto nosupp;
+
+	return 0;
+
+nosupp:
+	/* Switch LED off to indicate that mode isn't supported */
+	rtl8168_led_mod_ctrl(tp, 0x000f << shift, 0);
+	return -EOPNOTSUPP;
+}
+
+static int rtl8168_led_hw_control_set(struct led_classdev *led_cdev,
+				      unsigned long flags)
+{
+	struct r8169_led_classdev *ldev = lcdev_to_r8169_ldev(led_cdev);
+	struct rtl8169_private *tp = netdev_priv(ldev->ndev);
+	int shift = ldev->index * 4;
+	u16 mode = 0;
+
+	if (flags & BIT(TRIGGER_NETDEV_LINK_10))
+		mode |= RTL8168_LED_CTRL_LINK_10;
+	if (flags & BIT(TRIGGER_NETDEV_LINK_100))
+		mode |= RTL8168_LED_CTRL_LINK_100;
+	if (flags & BIT(TRIGGER_NETDEV_LINK_1000))
+		mode |= RTL8168_LED_CTRL_LINK_1000;
+	if (flags & BIT(TRIGGER_NETDEV_TX))
+		mode |= RTL8168_LED_CTRL_ACT;
+
+	return rtl8168_led_mod_ctrl(tp, 0x000f << shift, mode << shift);
+}
+
+static int rtl8168_led_hw_control_get(struct led_classdev *led_cdev,
+				      unsigned long *flags)
+{
+	struct r8169_led_classdev *ldev = lcdev_to_r8169_ldev(led_cdev);
+	struct rtl8169_private *tp = netdev_priv(ldev->ndev);
+	int shift = ldev->index * 4;
+	int mode;
+
+	mode = rtl8168_get_led_mode(tp);
+	if (mode < 0)
+		return mode;
+
+	if (mode & RTL8168_LED_CTRL_OPTION2) {
+		rtl8168_led_mod_ctrl(tp, RTL8168_LED_CTRL_OPTION2, 0);
+		netdev_notice(ldev->ndev, "Deactivating unsupported Option2 LED mode\n");
+	}
+
+	mode = (mode >> shift) & 0x000f;
+
+	if (mode & RTL8168_LED_CTRL_ACT)
+		*flags |= BIT(TRIGGER_NETDEV_TX) | BIT(TRIGGER_NETDEV_RX);
+
+	if (mode & RTL8168_LED_CTRL_LINK_10)
+		*flags |= BIT(TRIGGER_NETDEV_LINK_10);
+	if (mode & RTL8168_LED_CTRL_LINK_100)
+		*flags |= BIT(TRIGGER_NETDEV_LINK_100);
+	if (mode & RTL8168_LED_CTRL_LINK_1000)
+		*flags |= BIT(TRIGGER_NETDEV_LINK_1000);
+
+	return 0;
+}
+
+static struct device *
+	r8169_led_hw_control_get_device(struct led_classdev *led_cdev)
+{
+	struct r8169_led_classdev *ldev = lcdev_to_r8169_ldev(led_cdev);
+
+	return &ldev->ndev->dev;
+}
+
+static void rtl8168_setup_ldev(struct r8169_led_classdev *ldev,
+			       struct net_device *ndev, int index)
+{
+	struct rtl8169_private *tp = netdev_priv(ndev);
+	struct led_classdev *led_cdev = &ldev->led;
+	char led_name[LED_MAX_NAME_SIZE];
+
+	ldev->ndev = ndev;
+	ldev->index = index;
+
+	r8169_get_led_name(tp, index, led_name, LED_MAX_NAME_SIZE);
+	led_cdev->name = led_name;
+	led_cdev->default_trigger = "netdev";
+	led_cdev->hw_control_trigger = "netdev";
+	led_cdev->flags |= LED_RETAIN_AT_SHUTDOWN;
+	led_cdev->hw_control_is_supported = rtl8168_led_hw_control_is_supported;
+	led_cdev->hw_control_set = rtl8168_led_hw_control_set;
+	led_cdev->hw_control_get = rtl8168_led_hw_control_get;
+	led_cdev->hw_control_get_device = r8169_led_hw_control_get_device;
+
+	/* ignore errors */
+	devm_led_classdev_register(&ndev->dev, led_cdev);
+}
+
+void rtl8168_init_leds(struct net_device *ndev)
+{
+	/* bind resource mgmt to netdev */
+	struct device *dev = &ndev->dev;
+	struct r8169_led_classdev *leds;
+	int i;
+
+	leds = devm_kcalloc(dev, RTL8168_NUM_LEDS, sizeof(*leds), GFP_KERNEL);
+	if (!leds)
+		return;
+
+	for (i = 0; i < RTL8168_NUM_LEDS; i++)
+		rtl8168_setup_ldev(leds + i, ndev, i);
+}
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 0c76c162b8a9..dd73df6b17b0 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -56,10 +56,6 @@
 #define FIRMWARE_8125A_3	"rtl_nic/rtl8125a-3.fw"
 #define FIRMWARE_8125B_2	"rtl_nic/rtl8125b-2.fw"
 
-/* Maximum number of multicast addresses to filter (vs. Rx-all-multicast).
-   The RTL chips use a 64 element hash table based on the Ethernet CRC. */
-#define	MC_FILTER_LIMIT	32
-
 #define TX_DMA_BURST	7	/* Maximum PCI burst, '7' is unlimited */
 #define InterFrameGap	0x03	/* 3 means InterFrameGap = the shortest one */
 
@@ -196,6 +192,7 @@ enum rtl_registers {
 					/* No threshold before first PCI xfer */
 #define	RX_FIFO_THRESH			(7 << RXCFG_FIFO_SHIFT)
 #define	RX_EARLY_OFF			(1 << 11)
+#define	RX_PAUSE_SLOT_ON		(1 << 11)	/* 8125b and later */
 #define	RXCFG_DMA_SHIFT			8
 					/* Unlimited maximum PCI burst. */
 #define	RX_DMA_BURST			(7 << RXCFG_DMA_SHIFT)
@@ -288,6 +285,7 @@ enum rtl8168_8101_registers {
 };
 
 enum rtl8168_registers {
+	LED_CTRL		= 0x18,
 	LED_FREQ		= 0x1a,
 	EEE_LED			= 0x1b,
 	ERIDR			= 0x70,
@@ -579,6 +577,7 @@ struct rtl8169_tc_offsets {
 enum rtl_flag {
 	RTL_FLAG_TASK_ENABLED = 0,
 	RTL_FLAG_TASK_RESET_PENDING,
+	RTL_FLAG_TASK_RESET_NO_QUEUE_WAKE,
 	RTL_FLAG_TASK_TX_TIMEOUT,
 	RTL_FLAG_MAX
 };
@@ -618,12 +617,14 @@ struct rtl8169_private {
 
 	raw_spinlock_t config25_lock;
 	raw_spinlock_t mac_ocp_lock;
+	struct mutex led_lock;	/* serialize LED ctrl RMW access */
 
 	raw_spinlock_t cfg9346_usage_lock;
 	int cfg9346_usage_count;
 
 	unsigned supports_gmii:1;
 	unsigned aspm_manageable:1;
+	unsigned dash_enabled:1;
 	dma_addr_t counters_phys_addr;
 	struct rtl8169_counters *counters;
 	struct rtl8169_tc_offsets tc_offset;
@@ -789,6 +790,62 @@ static const struct rtl_cond name = {			\
 							\
 static bool name ## _check(struct rtl8169_private *tp)
 
+int rtl8168_led_mod_ctrl(struct rtl8169_private *tp, u16 mask, u16 val)
+{
+	struct device *dev = tp_to_dev(tp);
+	int ret;
+
+	ret = pm_runtime_resume_and_get(dev);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&tp->led_lock);
+	RTL_W16(tp, LED_CTRL, (RTL_R16(tp, LED_CTRL) & ~mask) | val);
+	mutex_unlock(&tp->led_lock);
+
+	pm_runtime_put_sync(dev);
+
+	return 0;
+}
+
+int rtl8168_get_led_mode(struct rtl8169_private *tp)
+{
+	struct device *dev = tp_to_dev(tp);
+	int ret;
+
+	ret = pm_runtime_resume_and_get(dev);
+	if (ret < 0)
+		return ret;
+
+	ret = RTL_R16(tp, LED_CTRL);
+
+	pm_runtime_put_sync(dev);
+
+	return ret;
+}
+
+void r8169_get_led_name(struct rtl8169_private *tp, int idx,
+			char *buf, int buf_len)
+{
+	struct pci_dev *pdev = tp->pci_dev;
+	char pdom[8], pfun[8];
+	int domain;
+
+	domain = pci_domain_nr(pdev->bus);
+	if (domain)
+		snprintf(pdom, sizeof(pdom), "P%d", domain);
+	else
+		pdom[0] = '\0';
+
+	if (pdev->multifunction)
+		snprintf(pfun, sizeof(pfun), "f%d", PCI_FUNC(pdev->devfn));
+	else
+		pfun[0] = '\0';
+
+	snprintf(buf, buf_len, "en%sp%ds%d%s-%d::lan", pdom, pdev->bus->number,
+		 PCI_SLOT(pdev->devfn), pfun, idx);
+}
+
 static void r8168fp_adjust_ocp_cmd(struct rtl8169_private *tp, u32 *cmd, int type)
 {
 	/* based on RTL8168FP_OOBMAC_BASE in vendor driver */
@@ -1208,7 +1265,7 @@ static void rtl8168ep_driver_start(struct rtl8169_private *tp)
 {
 	r8168ep_ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_START);
 	r8168ep_ocp_write(tp, 0x01, 0x30, r8168ep_ocp_read(tp, 0x30) | 0x01);
-	rtl_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 10);
+	rtl_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 30);
 }
 
 static void rtl8168_driver_start(struct rtl8169_private *tp)
@@ -1253,14 +1310,26 @@ static bool r8168ep_check_dash(struct rtl8169_private *tp)
 	return r8168ep_ocp_read(tp, 0x128) & BIT(0);
 }
 
-static enum rtl_dash_type rtl_check_dash(struct rtl8169_private *tp)
+static bool rtl_dash_is_enabled(struct rtl8169_private *tp)
+{
+	switch (tp->dash_type) {
+	case RTL_DASH_DP:
+		return r8168dp_check_dash(tp);
+	case RTL_DASH_EP:
+		return r8168ep_check_dash(tp);
+	default:
+		return false;
+	}
+}
+
+static enum rtl_dash_type rtl_get_dash_type(struct rtl8169_private *tp)
 {
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_28:
 	case RTL_GIGA_MAC_VER_31:
-		return r8168dp_check_dash(tp) ? RTL_DASH_DP : RTL_DASH_NONE;
+		return RTL_DASH_DP;
 	case RTL_GIGA_MAC_VER_51 ... RTL_GIGA_MAC_VER_53:
-		return r8168ep_check_dash(tp) ? RTL_DASH_EP : RTL_DASH_NONE;
+		return RTL_DASH_EP;
 	default:
 		return RTL_DASH_NONE;
 	}
@@ -1453,7 +1522,7 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
 
 	device_set_wakeup_enable(tp_to_dev(tp), wolopts);
 
-	if (tp->dash_type == RTL_DASH_NONE) {
+	if (!tp->dash_enabled) {
 		rtl_set_d3_pll_down(tp, !wolopts);
 		tp->dev->wol_enabled = wolopts ? 1 : 0;
 	}
@@ -2218,6 +2287,9 @@ u16 rtl8168h_2_get_adc_bias_ioffset(struct rtl8169_private *tp)
 
 static void rtl_schedule_task(struct rtl8169_private *tp, enum rtl_flag flag)
 {
+	if (!test_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags))
+		return;
+
 	set_bit(flag, tp->wk.flags);
 	schedule_work(&tp->wk.work);
 }
@@ -2292,9 +2364,13 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_53:
 		RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF);
 		break;
-	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_63:
+	case RTL_GIGA_MAC_VER_61:
 		RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST);
 		break;
+	case RTL_GIGA_MAC_VER_63:
+		RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST |
+			RX_PAUSE_SLOT_ON);
+		break;
 	default:
 		RTL_W32(tp, RxConfig, RX128_INT_EN | RX_DMA_BURST);
 		break;
@@ -2512,7 +2588,7 @@ static void rtl_wol_enable_rx(struct rtl8169_private *tp)
 
 static void rtl_prepare_power_down(struct rtl8169_private *tp)
 {
-	if (tp->dash_type != RTL_DASH_NONE)
+	if (tp->dash_enabled)
 		return;
 
 	if (tp->mac_version == RTL_GIGA_MAC_VER_32 ||
@@ -2584,11 +2660,8 @@ static void rtl_set_rx_mode(struct net_device *dev)
 		rx_mode |= AcceptAllPhys;
 	} else if (!(dev->flags & IFF_MULTICAST)) {
 		rx_mode &= ~AcceptMulticast;
-	} else if (netdev_mc_count(dev) > MC_FILTER_LIMIT ||
-		   dev->flags & IFF_ALLMULTI ||
-		   tp->mac_version == RTL_GIGA_MAC_VER_35 ||
-		   tp->mac_version == RTL_GIGA_MAC_VER_46 ||
-		   tp->mac_version == RTL_GIGA_MAC_VER_48) {
+	} else if (dev->flags & IFF_ALLMULTI ||
+		   tp->mac_version == RTL_GIGA_MAC_VER_35) {
 		/* accept all multicasts */
 	} else if (netdev_mc_empty(dev)) {
 		rx_mode &= ~AcceptMulticast;
@@ -3089,6 +3162,33 @@ static void rtl_hw_start_8168g_2(struct rtl8169_private *tp)
 	rtl_ephy_init(tp, e_info_8168g_2);
 }
 
+static void rtl8411b_fix_phy_down(struct rtl8169_private *tp)
+{
+	static const u16 fix_data[] = {
+/* 0xf800 */ 0xe008, 0xe00a, 0xe00c, 0xe00e, 0xe027, 0xe04f, 0xe05e, 0xe065,
+/* 0xf810 */ 0xc602, 0xbe00, 0x0000, 0xc502, 0xbd00, 0x074c, 0xc302, 0xbb00,
+/* 0xf820 */ 0x080a, 0x6420, 0x48c2, 0x8c20, 0xc516, 0x64a4, 0x49c0, 0xf009,
+/* 0xf830 */ 0x74a2, 0x8ca5, 0x74a0, 0xc50e, 0x9ca2, 0x1c11, 0x9ca0, 0xe006,
+/* 0xf840 */ 0x74f8, 0x48c4, 0x8cf8, 0xc404, 0xbc00, 0xc403, 0xbc00, 0x0bf2,
+/* 0xf850 */ 0x0c0a, 0xe434, 0xd3c0, 0x49d9, 0xf01f, 0xc526, 0x64a5, 0x1400,
+/* 0xf860 */ 0xf007, 0x0c01, 0x8ca5, 0x1c15, 0xc51b, 0x9ca0, 0xe013, 0xc519,
+/* 0xf870 */ 0x74a0, 0x48c4, 0x8ca0, 0xc516, 0x74a4, 0x48c8, 0x48ca, 0x9ca4,
+/* 0xf880 */ 0xc512, 0x1b00, 0x9ba0, 0x1b1c, 0x483f, 0x9ba2, 0x1b04, 0xc508,
+/* 0xf890 */ 0x9ba0, 0xc505, 0xbd00, 0xc502, 0xbd00, 0x0300, 0x051e, 0xe434,
+/* 0xf8a0 */ 0xe018, 0xe092, 0xde20, 0xd3c0, 0xc50f, 0x76a4, 0x49e3, 0xf007,
+/* 0xf8b0 */ 0x49c0, 0xf103, 0xc607, 0xbe00, 0xc606, 0xbe00, 0xc602, 0xbe00,
+/* 0xf8c0 */ 0x0c4c, 0x0c28, 0x0c2c, 0xdc00, 0xc707, 0x1d00, 0x8de2, 0x48c1,
+/* 0xf8d0 */ 0xc502, 0xbd00, 0x00aa, 0xe0c0, 0xc502, 0xbd00, 0x0132
+	};
+	unsigned long flags;
+	int i;
+
+	raw_spin_lock_irqsave(&tp->mac_ocp_lock, flags);
+	for (i = 0; i < ARRAY_SIZE(fix_data); i++)
+		__r8168_mac_ocp_write(tp, 0xf800 + 2 * i, fix_data[i]);
+	raw_spin_unlock_irqrestore(&tp->mac_ocp_lock, flags);
+}
+
 static void rtl_hw_start_8411_2(struct rtl8169_private *tp)
 {
 	static const struct ephy_info e_info_8411_2[] = {
@@ -3122,117 +3222,7 @@ static void rtl_hw_start_8411_2(struct rtl8169_private *tp)
 	mdelay(3);
 	r8168_mac_ocp_write(tp, 0xFC26, 0x0000);
 
-	r8168_mac_ocp_write(tp, 0xF800, 0xE008);
-	r8168_mac_ocp_write(tp, 0xF802, 0xE00A);
-	r8168_mac_ocp_write(tp, 0xF804, 0xE00C);
-	r8168_mac_ocp_write(tp, 0xF806, 0xE00E);
-	r8168_mac_ocp_write(tp, 0xF808, 0xE027);
-	r8168_mac_ocp_write(tp, 0xF80A, 0xE04F);
-	r8168_mac_ocp_write(tp, 0xF80C, 0xE05E);
-	r8168_mac_ocp_write(tp, 0xF80E, 0xE065);
-	r8168_mac_ocp_write(tp, 0xF810, 0xC602);
-	r8168_mac_ocp_write(tp, 0xF812, 0xBE00);
-	r8168_mac_ocp_write(tp, 0xF814, 0x0000);
-	r8168_mac_ocp_write(tp, 0xF816, 0xC502);
-	r8168_mac_ocp_write(tp, 0xF818, 0xBD00);
-	r8168_mac_ocp_write(tp, 0xF81A, 0x074C);
-	r8168_mac_ocp_write(tp, 0xF81C, 0xC302);
-	r8168_mac_ocp_write(tp, 0xF81E, 0xBB00);
-	r8168_mac_ocp_write(tp, 0xF820, 0x080A);
-	r8168_mac_ocp_write(tp, 0xF822, 0x6420);
-	r8168_mac_ocp_write(tp, 0xF824, 0x48C2);
-	r8168_mac_ocp_write(tp, 0xF826, 0x8C20);
-	r8168_mac_ocp_write(tp, 0xF828, 0xC516);
-	r8168_mac_ocp_write(tp, 0xF82A, 0x64A4);
-	r8168_mac_ocp_write(tp, 0xF82C, 0x49C0);
-	r8168_mac_ocp_write(tp, 0xF82E, 0xF009);
-	r8168_mac_ocp_write(tp, 0xF830, 0x74A2);
-	r8168_mac_ocp_write(tp, 0xF832, 0x8CA5);
-	r8168_mac_ocp_write(tp, 0xF834, 0x74A0);
-	r8168_mac_ocp_write(tp, 0xF836, 0xC50E);
-	r8168_mac_ocp_write(tp, 0xF838, 0x9CA2);
-	r8168_mac_ocp_write(tp, 0xF83A, 0x1C11);
-	r8168_mac_ocp_write(tp, 0xF83C, 0x9CA0);
-	r8168_mac_ocp_write(tp, 0xF83E, 0xE006);
-	r8168_mac_ocp_write(tp, 0xF840, 0x74F8);
-	r8168_mac_ocp_write(tp, 0xF842, 0x48C4);
-	r8168_mac_ocp_write(tp, 0xF844, 0x8CF8);
-	r8168_mac_ocp_write(tp, 0xF846, 0xC404);
-	r8168_mac_ocp_write(tp, 0xF848, 0xBC00);
-	r8168_mac_ocp_write(tp, 0xF84A, 0xC403);
-	r8168_mac_ocp_write(tp, 0xF84C, 0xBC00);
-	r8168_mac_ocp_write(tp, 0xF84E, 0x0BF2);
-	r8168_mac_ocp_write(tp, 0xF850, 0x0C0A);
-	r8168_mac_ocp_write(tp, 0xF852, 0xE434);
-	r8168_mac_ocp_write(tp, 0xF854, 0xD3C0);
-	r8168_mac_ocp_write(tp, 0xF856, 0x49D9);
-	r8168_mac_ocp_write(tp, 0xF858, 0xF01F);
-	r8168_mac_ocp_write(tp, 0xF85A, 0xC526);
-	r8168_mac_ocp_write(tp, 0xF85C, 0x64A5);
-	r8168_mac_ocp_write(tp, 0xF85E, 0x1400);
-	r8168_mac_ocp_write(tp, 0xF860, 0xF007);
-	r8168_mac_ocp_write(tp, 0xF862, 0x0C01);
-	r8168_mac_ocp_write(tp, 0xF864, 0x8CA5);
-	r8168_mac_ocp_write(tp, 0xF866, 0x1C15);
-	r8168_mac_ocp_write(tp, 0xF868, 0xC51B);
-	r8168_mac_ocp_write(tp, 0xF86A, 0x9CA0);
-	r8168_mac_ocp_write(tp, 0xF86C, 0xE013);
-	r8168_mac_ocp_write(tp, 0xF86E, 0xC519);
-	r8168_mac_ocp_write(tp, 0xF870, 0x74A0);
-	r8168_mac_ocp_write(tp, 0xF872, 0x48C4);
-	r8168_mac_ocp_write(tp, 0xF874, 0x8CA0);
-	r8168_mac_ocp_write(tp, 0xF876, 0xC516);
-	r8168_mac_ocp_write(tp, 0xF878, 0x74A4);
-	r8168_mac_ocp_write(tp, 0xF87A, 0x48C8);
-	r8168_mac_ocp_write(tp, 0xF87C, 0x48CA);
-	r8168_mac_ocp_write(tp, 0xF87E, 0x9CA4);
-	r8168_mac_ocp_write(tp, 0xF880, 0xC512);
-	r8168_mac_ocp_write(tp, 0xF882, 0x1B00);
-	r8168_mac_ocp_write(tp, 0xF884, 0x9BA0);
-	r8168_mac_ocp_write(tp, 0xF886, 0x1B1C);
-	r8168_mac_ocp_write(tp, 0xF888, 0x483F);
-	r8168_mac_ocp_write(tp, 0xF88A, 0x9BA2);
-	r8168_mac_ocp_write(tp, 0xF88C, 0x1B04);
-	r8168_mac_ocp_write(tp, 0xF88E, 0xC508);
-	r8168_mac_ocp_write(tp, 0xF890, 0x9BA0);
-	r8168_mac_ocp_write(tp, 0xF892, 0xC505);
-	r8168_mac_ocp_write(tp, 0xF894, 0xBD00);
-	r8168_mac_ocp_write(tp, 0xF896, 0xC502);
-	r8168_mac_ocp_write(tp, 0xF898, 0xBD00);
-	r8168_mac_ocp_write(tp, 0xF89A, 0x0300);
-	r8168_mac_ocp_write(tp, 0xF89C, 0x051E);
-	r8168_mac_ocp_write(tp, 0xF89E, 0xE434);
-	r8168_mac_ocp_write(tp, 0xF8A0, 0xE018);
-	r8168_mac_ocp_write(tp, 0xF8A2, 0xE092);
-	r8168_mac_ocp_write(tp, 0xF8A4, 0xDE20);
-	r8168_mac_ocp_write(tp, 0xF8A6, 0xD3C0);
-	r8168_mac_ocp_write(tp, 0xF8A8, 0xC50F);
-	r8168_mac_ocp_write(tp, 0xF8AA, 0x76A4);
-	r8168_mac_ocp_write(tp, 0xF8AC, 0x49E3);
-	r8168_mac_ocp_write(tp, 0xF8AE, 0xF007);
-	r8168_mac_ocp_write(tp, 0xF8B0, 0x49C0);
-	r8168_mac_ocp_write(tp, 0xF8B2, 0xF103);
-	r8168_mac_ocp_write(tp, 0xF8B4, 0xC607);
-	r8168_mac_ocp_write(tp, 0xF8B6, 0xBE00);
-	r8168_mac_ocp_write(tp, 0xF8B8, 0xC606);
-	r8168_mac_ocp_write(tp, 0xF8BA, 0xBE00);
-	r8168_mac_ocp_write(tp, 0xF8BC, 0xC602);
-	r8168_mac_ocp_write(tp, 0xF8BE, 0xBE00);
-	r8168_mac_ocp_write(tp, 0xF8C0, 0x0C4C);
-	r8168_mac_ocp_write(tp, 0xF8C2, 0x0C28);
-	r8168_mac_ocp_write(tp, 0xF8C4, 0x0C2C);
-	r8168_mac_ocp_write(tp, 0xF8C6, 0xDC00);
-	r8168_mac_ocp_write(tp, 0xF8C8, 0xC707);
-	r8168_mac_ocp_write(tp, 0xF8CA, 0x1D00);
-	r8168_mac_ocp_write(tp, 0xF8CC, 0x8DE2);
-	r8168_mac_ocp_write(tp, 0xF8CE, 0x48C1);
-	r8168_mac_ocp_write(tp, 0xF8D0, 0xC502);
-	r8168_mac_ocp_write(tp, 0xF8D2, 0xBD00);
-	r8168_mac_ocp_write(tp, 0xF8D4, 0x00AA);
-	r8168_mac_ocp_write(tp, 0xF8D6, 0xE0C0);
-	r8168_mac_ocp_write(tp, 0xF8D8, 0xC502);
-	r8168_mac_ocp_write(tp, 0xF8DA, 0xBD00);
-	r8168_mac_ocp_write(tp, 0xF8DC, 0x0132);
+	rtl8411b_fix_phy_down(tp);
 
 	r8168_mac_ocp_write(tp, 0xFC26, 0x8000);
 
@@ -4544,8 +4534,7 @@ static void rtl_task(struct work_struct *work)
 
 	rtnl_lock();
 
-	if (!netif_running(tp->dev) ||
-	    !test_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags))
+	if (!test_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags))
 		goto out_unlock;
 
 	if (test_and_clear_bit(RTL_FLAG_TASK_TX_TIMEOUT, tp->wk.flags)) {
@@ -4571,6 +4560,8 @@ static void rtl_task(struct work_struct *work)
 reset:
 		rtl_reset_work(tp);
 		netif_wake_queue(tp->dev);
+	} else if (test_and_clear_bit(RTL_FLAG_TASK_RESET_NO_QUEUE_WAKE, tp->wk.flags)) {
+		rtl_reset_work(tp);
 	}
 out_unlock:
 	rtnl_unlock();
@@ -4604,7 +4595,7 @@ static void r8169_phylink_handler(struct net_device *ndev)
 	} else {
 		/* In few cases rx is broken after link-down otherwise */
 		if (rtl_is_8125(tp))
-			rtl_reset_work(tp);
+			rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_NO_QUEUE_WAKE);
 		pm_runtime_idle(d);
 	}
 
@@ -4648,10 +4639,16 @@ static void rtl8169_down(struct rtl8169_private *tp)
 	rtl8169_cleanup(tp);
 	rtl_disable_exit_l1(tp);
 	rtl_prepare_power_down(tp);
+
+	if (tp->dash_type != RTL_DASH_NONE)
+		rtl8168_driver_stop(tp);
 }
 
 static void rtl8169_up(struct rtl8169_private *tp)
 {
+	if (tp->dash_type != RTL_DASH_NONE)
+		rtl8168_driver_start(tp);
+
 	pci_set_master(tp->pci_dev);
 	phy_init_hw(tp->phydev);
 	phy_resume(tp->phydev);
@@ -4674,7 +4671,7 @@ static int rtl8169_close(struct net_device *dev)
 	rtl8169_down(tp);
 	rtl8169_rx_clear(tp);
 
-	cancel_work_sync(&tp->wk.work);
+	cancel_work(&tp->wk.work);
 
 	free_irq(tp->irq, tp);
 
@@ -4869,7 +4866,7 @@ static int rtl8169_runtime_idle(struct device *device)
 {
 	struct rtl8169_private *tp = dev_get_drvdata(device);
 
-	if (tp->dash_type != RTL_DASH_NONE)
+	if (tp->dash_enabled)
 		return -EBUSY;
 
 	if (!netif_running(tp->dev) || !netif_carrier_ok(tp->dev))
@@ -4895,8 +4892,7 @@ static void rtl_shutdown(struct pci_dev *pdev)
 	/* Restore original MAC address */
 	rtl_rar_set(tp, tp->dev->perm_addr);
 
-	if (system_state == SYSTEM_POWER_OFF &&
-	    tp->dash_type == RTL_DASH_NONE) {
+	if (system_state == SYSTEM_POWER_OFF && !tp->dash_enabled) {
 		pci_wake_from_d3(pdev, tp->saved_wolopts);
 		pci_set_power_state(pdev, PCI_D3hot);
 	}
@@ -4909,6 +4905,8 @@ static void rtl_remove_one(struct pci_dev *pdev)
 	if (pci_dev_run_wake(pdev))
 		pm_runtime_get_noresume(&pdev->dev);
 
+	cancel_work_sync(&tp->wk.work);
+
 	unregister_netdev(tp->dev);
 
 	if (tp->dash_type != RTL_DASH_NONE)
@@ -5201,6 +5199,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	raw_spin_lock_init(&tp->cfg9346_usage_lock);
 	raw_spin_lock_init(&tp->config25_lock);
 	raw_spin_lock_init(&tp->mac_ocp_lock);
+	mutex_init(&tp->led_lock);
 
 	dev->tstats = devm_netdev_alloc_pcpu_stats(&pdev->dev,
 						   struct pcpu_sw_netstats);
@@ -5254,7 +5253,8 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1);
 	tp->aspm_manageable = !rc;
 
-	tp->dash_type = rtl_check_dash(tp);
+	tp->dash_type = rtl_get_dash_type(tp);
+	tp->dash_enabled = rtl_dash_is_enabled(tp);
 
 	tp->cp_cmd = RTL_R16(tp, CPlusCmd) & CPCMD_MASK;
 
@@ -5325,7 +5325,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* configure chip for default features */
 	rtl8169_set_features(dev, dev->features);
 
-	if (tp->dash_type == RTL_DASH_NONE) {
+	if (!tp->dash_enabled) {
 		rtl_set_d3_pll_down(tp, true);
 	} else {
 		rtl_set_d3_pll_down(tp, false);
@@ -5356,6 +5356,11 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		return rc;
 
+	if (IS_ENABLED(CONFIG_R8169_LEDS) &&
+	    tp->mac_version > RTL_GIGA_MAC_VER_06 &&
+	    tp->mac_version < RTL_GIGA_MAC_VER_61)
+		rtl8168_init_leds(dev);
+
 	netdev_info(dev, "%s, %pM, XID %03x, IRQ %d\n",
 		    rtl_chip_infos[chipset].name, dev->dev_addr, xid, tp->irq);
 
@@ -5365,7 +5370,8 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			    "ok" : "ko");
 
 	if (tp->dash_type != RTL_DASH_NONE) {
-		netdev_info(dev, "DASH enabled\n");
+		netdev_info(dev, "DASH %s\n",
+			    tp->dash_enabled ? "enabled" : "disabled");
 		rtl8168_driver_start(tp);
 	}
 
diff --git a/drivers/net/ethernet/renesas/Kconfig b/drivers/net/ethernet/renesas/Kconfig
index 8ef5b0241e64..d6136fe5c206 100644
--- a/drivers/net/ethernet/renesas/Kconfig
+++ b/drivers/net/ethernet/renesas/Kconfig
@@ -40,11 +40,21 @@ config RAVB
 config RENESAS_ETHER_SWITCH
 	tristate "Renesas Ethernet Switch support"
 	depends on ARCH_RENESAS || COMPILE_TEST
-	depends on PTP_1588_CLOCK_OPTIONAL
+	depends on PTP_1588_CLOCK
 	select CRC32
 	select MII
 	select PHYLINK
+	select RENESAS_GEN4_PTP
 	help
 	  Renesas Ethernet Switch device driver.
 
+config RENESAS_GEN4_PTP
+	tristate "Renesas R-Car Gen4 gPTP support" if COMPILE_TEST
+	depends on PTP_1588_CLOCK
+	select CRC32
+	select MII
+	select PHYLIB
+	help
+	  Renesas R-Car Gen4 gPTP device driver.
+
 endif # NET_VENDOR_RENESAS
diff --git a/drivers/net/ethernet/renesas/Makefile b/drivers/net/ethernet/renesas/Makefile
index e8fd85b5fe8f..9070acfd6aaf 100644
--- a/drivers/net/ethernet/renesas/Makefile
+++ b/drivers/net/ethernet/renesas/Makefile
@@ -8,5 +8,6 @@ obj-$(CONFIG_SH_ETH) += sh_eth.o
 ravb-objs := ravb_main.o ravb_ptp.o
 obj-$(CONFIG_RAVB) += ravb.o
 
-rswitch_drv-objs := rswitch.o rcar_gen4_ptp.o
-obj-$(CONFIG_RENESAS_ETHER_SWITCH) += rswitch_drv.o
+obj-$(CONFIG_RENESAS_ETHER_SWITCH) += rswitch.o
+
+obj-$(CONFIG_RENESAS_GEN4_PTP) += rcar_gen4_ptp.o
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index c70cff80cc99..8649b3e90edb 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -66,16 +66,27 @@ int ravb_wait(struct net_device *ndev, enum ravb_reg reg, u32 mask, u32 value)
 	return -ETIMEDOUT;
 }
 
-static int ravb_config(struct net_device *ndev)
+static int ravb_set_opmode(struct net_device *ndev, u32 opmode)
 {
+	u32 csr_ops = 1U << (opmode & CCC_OPC);
+	u32 ccc_mask = CCC_OPC;
 	int error;
 
-	/* Set config mode */
-	ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG);
-	/* Check if the operating mode is changed to the config mode */
-	error = ravb_wait(ndev, CSR, CSR_OPS, CSR_OPS_CONFIG);
-	if (error)
-		netdev_err(ndev, "failed to switch device to config mode\n");
+	/* If gPTP active in config mode is supported it needs to be configured
+	 * along with CSEL and operating mode in the same access. This is a
+	 * hardware limitation.
+	 */
+	if (opmode & CCC_GAC)
+		ccc_mask |= CCC_GAC | CCC_CSEL;
+
+	/* Set operating mode */
+	ravb_modify(ndev, CCC, ccc_mask, opmode);
+	/* Check if the operating mode is changed to the requested one */
+	error = ravb_wait(ndev, CSR, CSR_OPS, csr_ops);
+	if (error) {
+		netdev_err(ndev, "failed to switch device to requested mode (%u)\n",
+			   opmode & CCC_OPC);
+	}
 
 	return error;
 }
@@ -515,6 +526,15 @@ static void ravb_emac_init_gbeth(struct net_device *ndev)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
 
+	if (priv->phy_interface == PHY_INTERFACE_MODE_MII) {
+		ravb_write(ndev, (1000 << 16) | CXR35_SEL_XMII_MII, CXR35);
+		ravb_modify(ndev, CXR31, CXR31_SEL_LINK0 | CXR31_SEL_LINK1, 0);
+	} else {
+		ravb_write(ndev, (1000 << 16) | CXR35_SEL_XMII_RGMII, CXR35);
+		ravb_modify(ndev, CXR31, CXR31_SEL_LINK0 | CXR31_SEL_LINK1,
+			    CXR31_SEL_LINK0);
+	}
+
 	/* Receive frame limit set register */
 	ravb_write(ndev, GBETH_RX_BUFF_MAX + ETH_FCS_LEN, RFLR);
 
@@ -537,14 +557,6 @@ static void ravb_emac_init_gbeth(struct net_device *ndev)
 
 	/* E-MAC interrupt enable register */
 	ravb_write(ndev, ECSIPR_ICDIP, ECSIPR);
-
-	if (priv->phy_interface == PHY_INTERFACE_MODE_MII) {
-		ravb_modify(ndev, CXR31, CXR31_SEL_LINK0 | CXR31_SEL_LINK1, 0);
-		ravb_write(ndev, (1000 << 16) | CXR35_SEL_XMII_MII, CXR35);
-	} else {
-		ravb_modify(ndev, CXR31, CXR31_SEL_LINK0 | CXR31_SEL_LINK1,
-			    CXR31_SEL_LINK0);
-	}
 }
 
 static void ravb_emac_init_rcar(struct net_device *ndev)
@@ -672,7 +684,7 @@ static int ravb_dmac_init(struct net_device *ndev)
 	int error;
 
 	/* Set CONFIG mode */
-	error = ravb_config(ndev);
+	error = ravb_set_opmode(ndev, CCC_OPC_CONFIG);
 	if (error)
 		return error;
 
@@ -681,9 +693,7 @@ static int ravb_dmac_init(struct net_device *ndev)
 		return error;
 
 	/* Setting the control will start the AVB-DMAC process. */
-	ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_OPERATION);
-
-	return 0;
+	return ravb_set_opmode(ndev, CCC_OPC_OPERATION);
 }
 
 static void ravb_get_tx_tstamp(struct net_device *ndev)
@@ -1045,7 +1055,7 @@ static int ravb_stop_dma(struct net_device *ndev)
 		return error;
 
 	/* Stop AVB-DMAC process */
-	return ravb_config(ndev);
+	return ravb_set_opmode(ndev, CCC_OPC_CONFIG);
 }
 
 /* E-MAC interrupt handler */
@@ -1811,19 +1821,20 @@ static int ravb_open(struct net_device *ndev)
 	if (info->gptp)
 		ravb_ptp_init(ndev, priv->pdev);
 
-	netif_tx_start_all_queues(ndev);
-
 	/* PHY control start */
 	error = ravb_phy_start(ndev);
 	if (error)
 		goto out_ptp_stop;
 
+	netif_tx_start_all_queues(ndev);
+
 	return 0;
 
 out_ptp_stop:
 	/* Stop PTP Clock driver */
 	if (info->gptp)
 		ravb_ptp_stop(ndev);
+	ravb_stop_dma(ndev);
 out_free_irq_mgmta:
 	if (!info->multi_irqs)
 		goto out_free_irq;
@@ -1874,6 +1885,12 @@ static void ravb_tx_timeout_work(struct work_struct *work)
 	struct net_device *ndev = priv->ndev;
 	int error;
 
+	if (!rtnl_trylock()) {
+		usleep_range(1000, 2000);
+		schedule_work(&priv->work);
+		return;
+	}
+
 	netif_tx_stop_all_queues(ndev);
 
 	/* Stop PTP Clock driver */
@@ -1907,7 +1924,7 @@ static void ravb_tx_timeout_work(struct work_struct *work)
 		 */
 		netdev_err(ndev, "%s: ravb_dmac_init() failed, error %d\n",
 			   __func__, error);
-		return;
+		goto out_unlock;
 	}
 	ravb_emac_init(ndev);
 
@@ -1917,6 +1934,9 @@ out:
 		ravb_ptp_init(ndev, priv->pdev);
 
 	netif_tx_start_all_queues(ndev);
+
+out_unlock:
+	rtnl_unlock();
 }
 
 /* Packet transmit function for Ethernet AVB */
@@ -2549,21 +2569,25 @@ static int ravb_set_gti(struct net_device *ndev)
 	return 0;
 }
 
-static void ravb_set_config_mode(struct net_device *ndev)
+static int ravb_set_config_mode(struct net_device *ndev)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
 	const struct ravb_hw_info *info = priv->info;
+	int error;
 
 	if (info->gptp) {
-		ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG);
+		error = ravb_set_opmode(ndev, CCC_OPC_CONFIG);
+		if (error)
+			return error;
 		/* Set CSEL value */
 		ravb_modify(ndev, CCC, CCC_CSEL, CCC_CSEL_HPB);
 	} else if (info->ccc_gac) {
-		ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG |
-			    CCC_GAC | CCC_CSEL_HPB);
+		error = ravb_set_opmode(ndev, CCC_OPC_CONFIG | CCC_GAC | CCC_CSEL_HPB);
 	} else {
-		ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG);
+		error = ravb_set_opmode(ndev, CCC_OPC_CONFIG);
 	}
+
+	return error;
 }
 
 /* Set tx and rx clock internal delay modes */
@@ -2645,9 +2669,14 @@ static int ravb_probe(struct platform_device *pdev)
 	ndev->features = info->net_features;
 	ndev->hw_features = info->net_hw_features;
 
-	reset_control_deassert(rstc);
+	error = reset_control_deassert(rstc);
+	if (error)
+		goto out_free_netdev;
+
 	pm_runtime_enable(&pdev->dev);
-	pm_runtime_get_sync(&pdev->dev);
+	error = pm_runtime_resume_and_get(&pdev->dev);
+	if (error < 0)
+		goto out_rpm_disable;
 
 	if (info->multi_irqs) {
 		if (info->err_mgmt_irqs)
@@ -2778,7 +2807,9 @@ static int ravb_probe(struct platform_device *pdev)
 	ndev->ethtool_ops = &ravb_ethtool_ops;
 
 	/* Set AVB config mode */
-	ravb_set_config_mode(ndev);
+	error = ravb_set_config_mode(ndev);
+	if (error)
+		goto out_disable_gptp_clk;
 
 	if (info->gptp || info->ccc_gac) {
 		/* Set GTI value */
@@ -2872,11 +2903,12 @@ out_disable_gptp_clk:
 out_disable_refclk:
 	clk_disable_unprepare(priv->refclk);
 out_release:
-	free_netdev(ndev);
-
 	pm_runtime_put(&pdev->dev);
+out_rpm_disable:
 	pm_runtime_disable(&pdev->dev);
 	reset_control_assert(rstc);
+out_free_netdev:
+	free_netdev(ndev);
 	return error;
 }
 
@@ -2886,22 +2918,25 @@ static void ravb_remove(struct platform_device *pdev)
 	struct ravb_private *priv = netdev_priv(ndev);
 	const struct ravb_hw_info *info = priv->info;
 
-	/* Stop PTP Clock driver */
-	if (info->ccc_gac)
-		ravb_ptp_stop(ndev);
-
-	clk_disable_unprepare(priv->gptp_clk);
-	clk_disable_unprepare(priv->refclk);
-
-	/* Set reset mode */
-	ravb_write(ndev, CCC_OPC_RESET, CCC);
 	unregister_netdev(ndev);
 	if (info->nc_queues)
 		netif_napi_del(&priv->napi[RAVB_NC]);
 	netif_napi_del(&priv->napi[RAVB_BE]);
+
 	ravb_mdio_release(priv);
+
+	/* Stop PTP Clock driver */
+	if (info->ccc_gac)
+		ravb_ptp_stop(ndev);
+
 	dma_free_coherent(ndev->dev.parent, priv->desc_bat_size, priv->desc_bat,
 			  priv->desc_bat_dma);
+
+	ravb_set_opmode(ndev, CCC_OPC_RESET);
+
+	clk_disable_unprepare(priv->gptp_clk);
+	clk_disable_unprepare(priv->refclk);
+
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	reset_control_assert(priv->rstc);
@@ -2979,8 +3014,11 @@ static int __maybe_unused ravb_resume(struct device *dev)
 	int ret = 0;
 
 	/* If WoL is enabled set reset mode to rearm the WoL logic */
-	if (priv->wol_enabled)
-		ravb_write(ndev, CCC_OPC_RESET, CCC);
+	if (priv->wol_enabled) {
+		ret = ravb_set_opmode(ndev, CCC_OPC_RESET);
+		if (ret)
+			return ret;
+	}
 
 	/* All register have been reset to default values.
 	 * Restore all registers which where setup at probe time and
@@ -2988,7 +3026,9 @@ static int __maybe_unused ravb_resume(struct device *dev)
 	 */
 
 	/* Set AVB config mode */
-	ravb_set_config_mode(ndev);
+	ret = ravb_set_config_mode(ndev);
+	if (ret)
+		return ret;
 
 	if (info->gptp || info->ccc_gac) {
 		/* Set GTI value */
diff --git a/drivers/net/ethernet/renesas/rcar_gen4_ptp.c b/drivers/net/ethernet/renesas/rcar_gen4_ptp.c
index c007e33c47e1..72e7fcc56693 100644
--- a/drivers/net/ethernet/renesas/rcar_gen4_ptp.c
+++ b/drivers/net/ethernet/renesas/rcar_gen4_ptp.c
@@ -14,7 +14,7 @@
 #include "rcar_gen4_ptp.h"
 #define ptp_to_priv(ptp)	container_of(ptp, struct rcar_gen4_ptp_private, info)
 
-static const struct rcar_gen4_ptp_reg_offset s4_offs = {
+static const struct rcar_gen4_ptp_reg_offset gen4_offs = {
 	.enable = PTPTMEC,
 	.disable = PTPTMDC,
 	.increment = PTPTIVC0,
@@ -130,25 +130,42 @@ static struct ptp_clock_info rcar_gen4_ptp_info = {
 	.enable = rcar_gen4_ptp_enable,
 };
 
-static void rcar_gen4_ptp_set_offs(struct rcar_gen4_ptp_private *ptp_priv,
-				   enum rcar_gen4_ptp_reg_layout layout)
+static int rcar_gen4_ptp_set_offs(struct rcar_gen4_ptp_private *ptp_priv,
+				  enum rcar_gen4_ptp_reg_layout layout)
 {
-	WARN_ON(layout != RCAR_GEN4_PTP_REG_LAYOUT_S4);
+	if (layout != RCAR_GEN4_PTP_REG_LAYOUT)
+		return -EINVAL;
 
-	ptp_priv->offs = &s4_offs;
+	ptp_priv->offs = &gen4_offs;
+
+	return 0;
+}
+
+static s64 rcar_gen4_ptp_rate_to_increment(u32 rate)
+{
+	/* Timer increment in ns.
+	 * bit[31:27] - integer
+	 * bit[26:0]  - decimal
+	 * increment[ns] = perid[ns] * 2^27 => (1ns * 2^27) / rate[hz]
+	 */
+	return div_s64(1000000000LL << 27, rate);
 }
 
 int rcar_gen4_ptp_register(struct rcar_gen4_ptp_private *ptp_priv,
-			   enum rcar_gen4_ptp_reg_layout layout, u32 clock)
+			   enum rcar_gen4_ptp_reg_layout layout, u32 rate)
 {
+	int ret;
+
 	if (ptp_priv->initialized)
 		return 0;
 
 	spin_lock_init(&ptp_priv->lock);
 
-	rcar_gen4_ptp_set_offs(ptp_priv, layout);
+	ret = rcar_gen4_ptp_set_offs(ptp_priv, layout);
+	if (ret)
+		return ret;
 
-	ptp_priv->default_addend = clock;
+	ptp_priv->default_addend = rcar_gen4_ptp_rate_to_increment(rate);
 	iowrite32(ptp_priv->default_addend, ptp_priv->addr + ptp_priv->offs->increment);
 	ptp_priv->clock = ptp_clock_register(&ptp_priv->info, NULL);
 	if (IS_ERR(ptp_priv->clock))
@@ -159,6 +176,7 @@ int rcar_gen4_ptp_register(struct rcar_gen4_ptp_private *ptp_priv,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(rcar_gen4_ptp_register);
 
 int rcar_gen4_ptp_unregister(struct rcar_gen4_ptp_private *ptp_priv)
 {
@@ -166,6 +184,7 @@ int rcar_gen4_ptp_unregister(struct rcar_gen4_ptp_private *ptp_priv)
 
 	return ptp_clock_unregister(ptp_priv->clock);
 }
+EXPORT_SYMBOL_GPL(rcar_gen4_ptp_unregister);
 
 struct rcar_gen4_ptp_private *rcar_gen4_ptp_alloc(struct platform_device *pdev)
 {
@@ -179,3 +198,8 @@ struct rcar_gen4_ptp_private *rcar_gen4_ptp_alloc(struct platform_device *pdev)
 
 	return ptp;
 }
+EXPORT_SYMBOL_GPL(rcar_gen4_ptp_alloc);
+
+MODULE_AUTHOR("Yoshihiro Shimoda");
+MODULE_DESCRIPTION("Renesas R-Car Gen4 gPTP driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/renesas/rcar_gen4_ptp.h b/drivers/net/ethernet/renesas/rcar_gen4_ptp.h
index b1bbea8d3a52..e22da5acd53d 100644
--- a/drivers/net/ethernet/renesas/rcar_gen4_ptp.h
+++ b/drivers/net/ethernet/renesas/rcar_gen4_ptp.h
@@ -9,13 +9,10 @@
 
 #include <linux/ptp_clock_kernel.h>
 
-#define PTPTIVC_INIT			0x19000000	/* 320MHz */
-#define RCAR_GEN4_PTP_CLOCK_S4		PTPTIVC_INIT
 #define RCAR_GEN4_GPTP_OFFSET_S4	0x00018000
 
-/* for rcar_gen4_ptp_init */
 enum rcar_gen4_ptp_reg_layout {
-	RCAR_GEN4_PTP_REG_LAYOUT_S4
+	RCAR_GEN4_PTP_REG_LAYOUT
 };
 
 /* driver's definitions */
@@ -28,7 +25,7 @@ enum rcar_gen4_ptp_reg_layout {
 
 #define PTPRO				0
 
-enum rcar_gen4_ptp_reg_s4 {
+enum rcar_gen4_ptp_reg {
 	PTPTMEC		= PTPRO + 0x0010,
 	PTPTMDC		= PTPRO + 0x0014,
 	PTPTIVC0	= PTPRO + 0x0020,
@@ -65,7 +62,7 @@ struct rcar_gen4_ptp_private {
 };
 
 int rcar_gen4_ptp_register(struct rcar_gen4_ptp_private *ptp_priv,
-			   enum rcar_gen4_ptp_reg_layout layout, u32 clock);
+			   enum rcar_gen4_ptp_reg_layout layout, u32 rate);
 int rcar_gen4_ptp_unregister(struct rcar_gen4_ptp_private *ptp_priv);
 struct rcar_gen4_ptp_private *rcar_gen4_ptp_alloc(struct platform_device *pdev);
 
diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c
index 43a7795d6591..dcab638c57fe 100644
--- a/drivers/net/ethernet/renesas/rswitch.c
+++ b/drivers/net/ethernet/renesas/rswitch.c
@@ -56,7 +56,8 @@ static void rswitch_clock_disable(struct rswitch_private *priv)
 	iowrite32(RCDC_RCD, priv->addr + RCDC);
 }
 
-static bool rswitch_agent_clock_is_enabled(void __iomem *coma_addr, int port)
+static bool rswitch_agent_clock_is_enabled(void __iomem *coma_addr,
+					   unsigned int port)
 {
 	u32 val = ioread32(coma_addr + RCEC);
 
@@ -66,7 +67,8 @@ static bool rswitch_agent_clock_is_enabled(void __iomem *coma_addr, int port)
 		return false;
 }
 
-static void rswitch_agent_clock_ctrl(void __iomem *coma_addr, int port, int enable)
+static void rswitch_agent_clock_ctrl(void __iomem *coma_addr, unsigned int port,
+				     int enable)
 {
 	u32 val;
 
@@ -100,7 +102,7 @@ static void rswitch_coma_init(struct rswitch_private *priv)
 /* R-Switch-2 block (TOP) */
 static void rswitch_top_init(struct rswitch_private *priv)
 {
-	int i;
+	unsigned int i;
 
 	for (i = 0; i < RSWITCH_MAX_NUM_QUEUES; i++)
 		iowrite32((i / 16) << (GWCA_INDEX * 8), priv->addr + TPEMIMC7(i));
@@ -109,7 +111,7 @@ static void rswitch_top_init(struct rswitch_private *priv)
 /* Forwarding engine block (MFWD) */
 static void rswitch_fwd_init(struct rswitch_private *priv)
 {
-	int i;
+	unsigned int i;
 
 	/* For ETHA */
 	for (i = 0; i < RSWITCH_NUM_PORTS; i++) {
@@ -166,7 +168,7 @@ static int rswitch_gwca_axi_ram_reset(struct rswitch_private *priv)
 static bool rswitch_is_any_data_irq(struct rswitch_private *priv, u32 *dis, bool tx)
 {
 	u32 *mask = tx ? priv->gwca.tx_irq_bits : priv->gwca.rx_irq_bits;
-	int i;
+	unsigned int i;
 
 	for (i = 0; i < RSWITCH_NUM_IRQ_REGS; i++) {
 		if (dis[i] & mask[i])
@@ -178,7 +180,7 @@ static bool rswitch_is_any_data_irq(struct rswitch_private *priv, u32 *dis, bool
 
 static void rswitch_get_data_irq_status(struct rswitch_private *priv, u32 *dis)
 {
-	int i;
+	unsigned int i;
 
 	for (i = 0; i < RSWITCH_NUM_IRQ_REGS; i++) {
 		dis[i] = ioread32(priv->addr + GWDIS(i));
@@ -186,23 +188,26 @@ static void rswitch_get_data_irq_status(struct rswitch_private *priv, u32 *dis)
 	}
 }
 
-static void rswitch_enadis_data_irq(struct rswitch_private *priv, int index, bool enable)
+static void rswitch_enadis_data_irq(struct rswitch_private *priv,
+				    unsigned int index, bool enable)
 {
 	u32 offs = enable ? GWDIE(index / 32) : GWDID(index / 32);
 
 	iowrite32(BIT(index % 32), priv->addr + offs);
 }
 
-static void rswitch_ack_data_irq(struct rswitch_private *priv, int index)
+static void rswitch_ack_data_irq(struct rswitch_private *priv,
+				 unsigned int index)
 {
 	u32 offs = GWDIS(index / 32);
 
 	iowrite32(BIT(index % 32), priv->addr + offs);
 }
 
-static int rswitch_next_queue_index(struct rswitch_gwca_queue *gq, bool cur, int num)
+static unsigned int rswitch_next_queue_index(struct rswitch_gwca_queue *gq,
+					     bool cur, unsigned int num)
 {
-	int index = cur ? gq->cur : gq->dirty;
+	unsigned int index = cur ? gq->cur : gq->dirty;
 
 	if (index + num >= gq->ring_size)
 		index = (index + num) % gq->ring_size;
@@ -212,7 +217,7 @@ static int rswitch_next_queue_index(struct rswitch_gwca_queue *gq, bool cur, int
 	return index;
 }
 
-static int rswitch_get_num_cur_queues(struct rswitch_gwca_queue *gq)
+static unsigned int rswitch_get_num_cur_queues(struct rswitch_gwca_queue *gq)
 {
 	if (gq->cur >= gq->dirty)
 		return gq->cur - gq->dirty;
@@ -230,28 +235,28 @@ static bool rswitch_is_queue_rxed(struct rswitch_gwca_queue *gq)
 	return false;
 }
 
-static int rswitch_gwca_queue_alloc_skb(struct rswitch_gwca_queue *gq,
-					int start_index, int num)
+static int rswitch_gwca_queue_alloc_rx_buf(struct rswitch_gwca_queue *gq,
+					   unsigned int start_index,
+					   unsigned int num)
 {
-	int i, index;
+	unsigned int i, index;
 
 	for (i = 0; i < num; i++) {
 		index = (i + start_index) % gq->ring_size;
-		if (gq->skbs[index])
+		if (gq->rx_bufs[index])
 			continue;
-		gq->skbs[index] = netdev_alloc_skb_ip_align(gq->ndev,
-							    PKT_BUF_SZ + RSWITCH_ALIGN - 1);
-		if (!gq->skbs[index])
+		gq->rx_bufs[index] = netdev_alloc_frag(RSWITCH_BUF_SIZE);
+		if (!gq->rx_bufs[index])
 			goto err;
 	}
 
 	return 0;
 
 err:
-	for (i--; i >= 0; i--) {
+	for (; i-- > 0; ) {
 		index = (i + start_index) % gq->ring_size;
-		dev_kfree_skb(gq->skbs[index]);
-		gq->skbs[index] = NULL;
+		skb_free_frag(gq->rx_bufs[index]);
+		gq->rx_bufs[index] = NULL;
 	}
 
 	return -ENOMEM;
@@ -260,7 +265,7 @@ err:
 static void rswitch_gwca_queue_free(struct net_device *ndev,
 				    struct rswitch_gwca_queue *gq)
 {
-	int i;
+	unsigned int i;
 
 	if (!gq->dir_tx) {
 		dma_free_coherent(ndev->dev.parent,
@@ -269,16 +274,19 @@ static void rswitch_gwca_queue_free(struct net_device *ndev,
 		gq->rx_ring = NULL;
 
 		for (i = 0; i < gq->ring_size; i++)
-			dev_kfree_skb(gq->skbs[i]);
+			skb_free_frag(gq->rx_bufs[i]);
+		kfree(gq->rx_bufs);
+		gq->rx_bufs = NULL;
 	} else {
 		dma_free_coherent(ndev->dev.parent,
 				  sizeof(struct rswitch_ext_desc) *
 				  (gq->ring_size + 1), gq->tx_ring, gq->ring_dma);
 		gq->tx_ring = NULL;
+		kfree(gq->skbs);
+		gq->skbs = NULL;
+		kfree(gq->unmap_addrs);
+		gq->unmap_addrs = NULL;
 	}
-
-	kfree(gq->skbs);
-	gq->skbs = NULL;
 }
 
 static void rswitch_gwca_ts_queue_free(struct rswitch_private *priv)
@@ -294,25 +302,31 @@ static void rswitch_gwca_ts_queue_free(struct rswitch_private *priv)
 static int rswitch_gwca_queue_alloc(struct net_device *ndev,
 				    struct rswitch_private *priv,
 				    struct rswitch_gwca_queue *gq,
-				    bool dir_tx, int ring_size)
+				    bool dir_tx, unsigned int ring_size)
 {
-	int i, bit;
+	unsigned int i, bit;
 
 	gq->dir_tx = dir_tx;
 	gq->ring_size = ring_size;
 	gq->ndev = ndev;
 
-	gq->skbs = kcalloc(gq->ring_size, sizeof(*gq->skbs), GFP_KERNEL);
-	if (!gq->skbs)
-		return -ENOMEM;
-
 	if (!dir_tx) {
-		rswitch_gwca_queue_alloc_skb(gq, 0, gq->ring_size);
+		gq->rx_bufs = kcalloc(gq->ring_size, sizeof(*gq->rx_bufs), GFP_KERNEL);
+		if (!gq->rx_bufs)
+			return -ENOMEM;
+		if (rswitch_gwca_queue_alloc_rx_buf(gq, 0, gq->ring_size) < 0)
+			goto out;
 
 		gq->rx_ring = dma_alloc_coherent(ndev->dev.parent,
 						 sizeof(struct rswitch_ext_ts_desc) *
 						 (gq->ring_size + 1), &gq->ring_dma, GFP_KERNEL);
 	} else {
+		gq->skbs = kcalloc(gq->ring_size, sizeof(*gq->skbs), GFP_KERNEL);
+		if (!gq->skbs)
+			return -ENOMEM;
+		gq->unmap_addrs = kcalloc(gq->ring_size, sizeof(*gq->unmap_addrs), GFP_KERNEL);
+		if (!gq->unmap_addrs)
+			goto out;
 		gq->tx_ring = dma_alloc_coherent(ndev->dev.parent,
 						 sizeof(struct rswitch_ext_desc) *
 						 (gq->ring_size + 1), &gq->ring_dma, GFP_KERNEL);
@@ -351,22 +365,23 @@ static int rswitch_gwca_queue_format(struct net_device *ndev,
 				     struct rswitch_private *priv,
 				     struct rswitch_gwca_queue *gq)
 {
-	int ring_size = sizeof(struct rswitch_ext_desc) * gq->ring_size;
+	unsigned int ring_size = sizeof(struct rswitch_ext_desc) * gq->ring_size;
 	struct rswitch_ext_desc *desc;
 	struct rswitch_desc *linkfix;
 	dma_addr_t dma_addr;
-	int i;
+	unsigned int i;
 
 	memset(gq->tx_ring, 0, ring_size);
 	for (i = 0, desc = gq->tx_ring; i < gq->ring_size; i++, desc++) {
 		if (!gq->dir_tx) {
 			dma_addr = dma_map_single(ndev->dev.parent,
-						  gq->skbs[i]->data, PKT_BUF_SZ,
+						  gq->rx_bufs[i] + RSWITCH_HEADROOM,
+						  RSWITCH_MAP_BUF_SIZE,
 						  DMA_FROM_DEVICE);
 			if (dma_mapping_error(ndev->dev.parent, dma_addr))
 				goto err;
 
-			desc->desc.info_ds = cpu_to_le16(PKT_BUF_SZ);
+			desc->desc.info_ds = cpu_to_le16(RSWITCH_DESC_BUF_SIZE);
 			rswitch_desc_set_dptr(&desc->desc, dma_addr);
 			desc->desc.die_dt = DT_FEMPTY | DIE;
 		} else {
@@ -387,10 +402,10 @@ static int rswitch_gwca_queue_format(struct net_device *ndev,
 
 err:
 	if (!gq->dir_tx) {
-		for (i--, desc = gq->tx_ring; i >= 0; i--, desc++) {
+		for (desc = gq->tx_ring; i-- > 0; desc++) {
 			dma_addr = rswitch_desc_get_dptr(&desc->desc);
-			dma_unmap_single(ndev->dev.parent, dma_addr, PKT_BUF_SZ,
-					 DMA_FROM_DEVICE);
+			dma_unmap_single(ndev->dev.parent, dma_addr,
+					 RSWITCH_MAP_BUF_SIZE, DMA_FROM_DEVICE);
 		}
 	}
 
@@ -398,11 +413,12 @@ err:
 }
 
 static void rswitch_gwca_ts_queue_fill(struct rswitch_private *priv,
-				       int start_index, int num)
+				       unsigned int start_index,
+				       unsigned int num)
 {
 	struct rswitch_gwca_queue *gq = &priv->gwca.ts_queue;
 	struct rswitch_ts_desc *desc;
-	int i, index;
+	unsigned int i, index;
 
 	for (i = 0; i < num; i++) {
 		index = (i + start_index) % gq->ring_size;
@@ -413,24 +429,26 @@ static void rswitch_gwca_ts_queue_fill(struct rswitch_private *priv,
 
 static int rswitch_gwca_queue_ext_ts_fill(struct net_device *ndev,
 					  struct rswitch_gwca_queue *gq,
-					  int start_index, int num)
+					  unsigned int start_index,
+					  unsigned int num)
 {
 	struct rswitch_device *rdev = netdev_priv(ndev);
 	struct rswitch_ext_ts_desc *desc;
+	unsigned int i, index;
 	dma_addr_t dma_addr;
-	int i, index;
 
 	for (i = 0; i < num; i++) {
 		index = (i + start_index) % gq->ring_size;
 		desc = &gq->rx_ring[index];
 		if (!gq->dir_tx) {
 			dma_addr = dma_map_single(ndev->dev.parent,
-						  gq->skbs[index]->data, PKT_BUF_SZ,
+						  gq->rx_bufs[index] + RSWITCH_HEADROOM,
+						  RSWITCH_MAP_BUF_SIZE,
 						  DMA_FROM_DEVICE);
 			if (dma_mapping_error(ndev->dev.parent, dma_addr))
 				goto err;
 
-			desc->desc.info_ds = cpu_to_le16(PKT_BUF_SZ);
+			desc->desc.info_ds = cpu_to_le16(RSWITCH_DESC_BUF_SIZE);
 			rswitch_desc_set_dptr(&desc->desc, dma_addr);
 			dma_wmb();
 			desc->desc.die_dt = DT_FEMPTY | DIE;
@@ -444,12 +462,12 @@ static int rswitch_gwca_queue_ext_ts_fill(struct net_device *ndev,
 
 err:
 	if (!gq->dir_tx) {
-		for (i--; i >= 0; i--) {
+		for (; i-- > 0; ) {
 			index = (i + start_index) % gq->ring_size;
 			desc = &gq->rx_ring[index];
 			dma_addr = rswitch_desc_get_dptr(&desc->desc);
-			dma_unmap_single(ndev->dev.parent, dma_addr, PKT_BUF_SZ,
-					 DMA_FROM_DEVICE);
+			dma_unmap_single(ndev->dev.parent, dma_addr,
+					 RSWITCH_MAP_BUF_SIZE, DMA_FROM_DEVICE);
 		}
 	}
 
@@ -460,7 +478,7 @@ static int rswitch_gwca_queue_ext_ts_format(struct net_device *ndev,
 					    struct rswitch_private *priv,
 					    struct rswitch_gwca_queue *gq)
 {
-	int ring_size = sizeof(struct rswitch_ext_ts_desc) * gq->ring_size;
+	unsigned int ring_size = sizeof(struct rswitch_ext_ts_desc) * gq->ring_size;
 	struct rswitch_ext_ts_desc *desc;
 	struct rswitch_desc *linkfix;
 	int err;
@@ -487,7 +505,7 @@ static int rswitch_gwca_queue_ext_ts_format(struct net_device *ndev,
 
 static int rswitch_gwca_linkfix_alloc(struct rswitch_private *priv)
 {
-	int i, num_queues = priv->gwca.num_queues;
+	unsigned int i, num_queues = priv->gwca.num_queues;
 	struct rswitch_gwca *gwca = &priv->gwca;
 	struct device *dev = &priv->pdev->dev;
 
@@ -537,7 +555,7 @@ static int rswitch_gwca_ts_queue_alloc(struct rswitch_private *priv)
 static struct rswitch_gwca_queue *rswitch_gwca_get(struct rswitch_private *priv)
 {
 	struct rswitch_gwca_queue *gq;
-	int index;
+	unsigned int index;
 
 	index = find_first_zero_bit(priv->gwca.used, priv->gwca.num_queues);
 	if (index >= priv->gwca.num_queues)
@@ -583,7 +601,7 @@ static void rswitch_txdmac_free(struct net_device *ndev)
 	rswitch_gwca_put(rdev->priv, rdev->tx_queue);
 }
 
-static int rswitch_txdmac_init(struct rswitch_private *priv, int index)
+static int rswitch_txdmac_init(struct rswitch_private *priv, unsigned int index)
 {
 	struct rswitch_device *rdev = priv->rdev[index];
 
@@ -617,7 +635,7 @@ static void rswitch_rxdmac_free(struct net_device *ndev)
 	rswitch_gwca_put(rdev->priv, rdev->rx_queue);
 }
 
-static int rswitch_rxdmac_init(struct rswitch_private *priv, int index)
+static int rswitch_rxdmac_init(struct rswitch_private *priv, unsigned int index)
 {
 	struct rswitch_device *rdev = priv->rdev[index];
 	struct net_device *ndev = rdev->ndev;
@@ -627,7 +645,8 @@ static int rswitch_rxdmac_init(struct rswitch_private *priv, int index)
 
 static int rswitch_gwca_hw_init(struct rswitch_private *priv)
 {
-	int i, err;
+	unsigned int i;
+	int err;
 
 	err = rswitch_gwca_change_mode(priv, GWMC_OPC_DISABLE);
 	if (err < 0)
@@ -649,6 +668,8 @@ static int rswitch_gwca_hw_init(struct rswitch_private *priv)
 	iowrite32(upper_32_bits(priv->gwca.linkfix_table_dma), priv->addr + GWDCBAC0);
 	iowrite32(lower_32_bits(priv->gwca.ts_queue.ring_dma), priv->addr + GWTDCAC10);
 	iowrite32(upper_32_bits(priv->gwca.ts_queue.ring_dma), priv->addr + GWTDCAC00);
+	iowrite32(GWMDNC_TSDMN(1) | GWMDNC_TXDMN(0x1e) | GWMDNC_RXDMN(0x1f),
+		  priv->addr + GWMDNC);
 	iowrite32(GWCA_TS_IRQ_BIT, priv->addr + GWTSDCC0);
 
 	iowrite32(GWTPC_PPPL(GWCA_IPV_NUM), priv->addr + GWTPC0);
@@ -693,15 +714,88 @@ static int rswitch_gwca_halt(struct rswitch_private *priv)
 	return err;
 }
 
+static struct sk_buff *rswitch_rx_handle_desc(struct net_device *ndev,
+					      struct rswitch_gwca_queue *gq,
+					      struct rswitch_ext_ts_desc *desc)
+{
+	dma_addr_t dma_addr = rswitch_desc_get_dptr(&desc->desc);
+	u16 pkt_len = le16_to_cpu(desc->desc.info_ds) & RX_DS;
+	u8 die_dt = desc->desc.die_dt & DT_MASK;
+	struct sk_buff *skb = NULL;
+
+	dma_unmap_single(ndev->dev.parent, dma_addr, RSWITCH_MAP_BUF_SIZE,
+			 DMA_FROM_DEVICE);
+
+	/* The RX descriptor order will be one of the following:
+	 * - FSINGLE
+	 * - FSTART -> FEND
+	 * - FSTART -> FMID -> FEND
+	 */
+
+	/* Check whether the descriptor is unexpected order */
+	switch (die_dt) {
+	case DT_FSTART:
+	case DT_FSINGLE:
+		if (gq->skb_fstart) {
+			dev_kfree_skb_any(gq->skb_fstart);
+			gq->skb_fstart = NULL;
+			ndev->stats.rx_dropped++;
+		}
+		break;
+	case DT_FMID:
+	case DT_FEND:
+		if (!gq->skb_fstart) {
+			ndev->stats.rx_dropped++;
+			return NULL;
+		}
+		break;
+	default:
+		break;
+	}
+
+	/* Handle the descriptor */
+	switch (die_dt) {
+	case DT_FSTART:
+	case DT_FSINGLE:
+		skb = build_skb(gq->rx_bufs[gq->cur], RSWITCH_BUF_SIZE);
+		if (skb) {
+			skb_reserve(skb, RSWITCH_HEADROOM);
+			skb_put(skb, pkt_len);
+			gq->pkt_len = pkt_len;
+			if (die_dt == DT_FSTART) {
+				gq->skb_fstart = skb;
+				skb = NULL;
+			}
+		}
+		break;
+	case DT_FMID:
+	case DT_FEND:
+		skb_add_rx_frag(gq->skb_fstart, skb_shinfo(gq->skb_fstart)->nr_frags,
+				virt_to_page(gq->rx_bufs[gq->cur]),
+				offset_in_page(gq->rx_bufs[gq->cur]) + RSWITCH_HEADROOM,
+				pkt_len, RSWITCH_BUF_SIZE);
+		if (die_dt == DT_FEND) {
+			skb = gq->skb_fstart;
+			gq->skb_fstart = NULL;
+		}
+		gq->pkt_len += pkt_len;
+		break;
+	default:
+		netdev_err(ndev, "%s: unexpected value (%x)\n", __func__, die_dt);
+		break;
+	}
+
+	return skb;
+}
+
 static bool rswitch_rx(struct net_device *ndev, int *quota)
 {
 	struct rswitch_device *rdev = netdev_priv(ndev);
 	struct rswitch_gwca_queue *gq = rdev->rx_queue;
 	struct rswitch_ext_ts_desc *desc;
-	int limit, boguscnt, num, ret;
+	int limit, boguscnt, ret;
 	struct sk_buff *skb;
-	dma_addr_t dma_addr;
-	u16 pkt_len;
+	unsigned int num;
 	u32 get_ts;
 
 	if (*quota <= 0)
@@ -713,11 +807,10 @@ static bool rswitch_rx(struct net_device *ndev, int *quota)
 	desc = &gq->rx_ring[gq->cur];
 	while ((desc->desc.die_dt & DT_MASK) != DT_FEMPTY) {
 		dma_rmb();
-		pkt_len = le16_to_cpu(desc->desc.info_ds) & RX_DS;
-		skb = gq->skbs[gq->cur];
-		gq->skbs[gq->cur] = NULL;
-		dma_addr = rswitch_desc_get_dptr(&desc->desc);
-		dma_unmap_single(ndev->dev.parent, dma_addr, PKT_BUF_SZ, DMA_FROM_DEVICE);
+		skb = rswitch_rx_handle_desc(ndev, gq, desc);
+		if (!skb)
+			goto out;
+
 		get_ts = rdev->priv->ptp_priv->tstamp_rx_ctrl & RCAR_GEN4_RXTSTAMP_TYPE_V2_L2_EVENT;
 		if (get_ts) {
 			struct skb_shared_hwtstamps *shhwtstamps;
@@ -729,12 +822,13 @@ static bool rswitch_rx(struct net_device *ndev, int *quota)
 			ts.tv_nsec = __le32_to_cpu(desc->ts_nsec & cpu_to_le32(0x3fffffff));
 			shhwtstamps->hwtstamp = timespec64_to_ktime(ts);
 		}
-		skb_put(skb, pkt_len);
 		skb->protocol = eth_type_trans(skb, ndev);
 		napi_gro_receive(&rdev->napi, skb);
 		rdev->ndev->stats.rx_packets++;
-		rdev->ndev->stats.rx_bytes += pkt_len;
+		rdev->ndev->stats.rx_bytes += gq->pkt_len;
 
+out:
+		gq->rx_bufs[gq->cur] = NULL;
 		gq->cur = rswitch_next_queue_index(gq, true, 1);
 		desc = &gq->rx_ring[gq->cur];
 
@@ -743,7 +837,7 @@ static bool rswitch_rx(struct net_device *ndev, int *quota)
 	}
 
 	num = rswitch_get_num_cur_queues(gq);
-	ret = rswitch_gwca_queue_alloc_skb(gq, gq->dirty, num);
+	ret = rswitch_gwca_queue_alloc_rx_buf(gq, gq->dirty, num);
 	if (ret < 0)
 		goto err;
 	ret = rswitch_gwca_queue_ext_ts_fill(ndev, gq, gq->dirty, num);
@@ -761,39 +855,32 @@ err:
 	return 0;
 }
 
-static int rswitch_tx_free(struct net_device *ndev, bool free_txed_only)
+static void rswitch_tx_free(struct net_device *ndev)
 {
 	struct rswitch_device *rdev = netdev_priv(ndev);
 	struct rswitch_gwca_queue *gq = rdev->tx_queue;
 	struct rswitch_ext_desc *desc;
-	dma_addr_t dma_addr;
 	struct sk_buff *skb;
-	int free_num = 0;
-	int size;
 
 	for (; rswitch_get_num_cur_queues(gq) > 0;
 	     gq->dirty = rswitch_next_queue_index(gq, false, 1)) {
 		desc = &gq->tx_ring[gq->dirty];
-		if (free_txed_only && (desc->desc.die_dt & DT_MASK) != DT_FEMPTY)
+		if ((desc->desc.die_dt & DT_MASK) != DT_FEMPTY)
 			break;
 
 		dma_rmb();
-		size = le16_to_cpu(desc->desc.info_ds) & TX_DS;
 		skb = gq->skbs[gq->dirty];
 		if (skb) {
-			dma_addr = rswitch_desc_get_dptr(&desc->desc);
-			dma_unmap_single(ndev->dev.parent, dma_addr,
-					 size, DMA_TO_DEVICE);
+			dma_unmap_single(ndev->dev.parent,
+					 gq->unmap_addrs[gq->dirty],
+					 skb->len, DMA_TO_DEVICE);
 			dev_kfree_skb_any(gq->skbs[gq->dirty]);
 			gq->skbs[gq->dirty] = NULL;
-			free_num++;
+			rdev->ndev->stats.tx_packets++;
+			rdev->ndev->stats.tx_bytes += skb->len;
 		}
 		desc->desc.die_dt = DT_EEMPTY;
-		rdev->ndev->stats.tx_packets++;
-		rdev->ndev->stats.tx_bytes += size;
 	}
-
-	return free_num;
 }
 
 static int rswitch_poll(struct napi_struct *napi, int budget)
@@ -808,7 +895,7 @@ static int rswitch_poll(struct napi_struct *napi, int budget)
 	priv = rdev->priv;
 
 retry:
-	rswitch_tx_free(ndev, true);
+	rswitch_tx_free(ndev);
 
 	if (rswitch_rx(ndev, &quota))
 		goto out;
@@ -851,7 +938,7 @@ static void rswitch_queue_interrupt(struct net_device *ndev)
 static irqreturn_t rswitch_data_irq(struct rswitch_private *priv, u32 *dis)
 {
 	struct rswitch_gwca_queue *gq;
-	int i, index, bit;
+	unsigned int i, index, bit;
 
 	for (i = 0; i < priv->gwca.num_queues; i++) {
 		gq = &priv->gwca.queues[i];
@@ -918,8 +1005,8 @@ static void rswitch_ts(struct rswitch_private *priv)
 	struct skb_shared_hwtstamps shhwtstamps;
 	struct rswitch_ts_desc *desc;
 	struct timespec64 ts;
+	unsigned int num;
 	u32 tag, port;
-	int num;
 
 	desc = &gq->ts_ring[gq->cur];
 	while ((desc->desc.die_dt & DT_MASK) != DT_FEMPTY_ND) {
@@ -1438,7 +1525,7 @@ err_init_one:
 
 static void rswitch_ether_port_deinit_all(struct rswitch_private *priv)
 {
-	int i;
+	unsigned int i;
 
 	for (i = 0; i < RSWITCH_NUM_PORTS; i++) {
 		phy_exit(priv->rdev[i]->serdes);
@@ -1500,43 +1587,18 @@ static int rswitch_stop(struct net_device *ndev)
 	return 0;
 };
 
-static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+static bool rswitch_ext_desc_set_info1(struct rswitch_device *rdev,
+				       struct sk_buff *skb,
+				       struct rswitch_ext_desc *desc)
 {
-	struct rswitch_device *rdev = netdev_priv(ndev);
-	struct rswitch_gwca_queue *gq = rdev->tx_queue;
-	struct rswitch_ext_desc *desc;
-	int ret = NETDEV_TX_OK;
-	dma_addr_t dma_addr;
-
-	if (rswitch_get_num_cur_queues(gq) >= gq->ring_size - 1) {
-		netif_stop_subqueue(ndev, 0);
-		return NETDEV_TX_BUSY;
-	}
-
-	if (skb_put_padto(skb, ETH_ZLEN))
-		return ret;
-
-	dma_addr = dma_map_single(ndev->dev.parent, skb->data, skb->len, DMA_TO_DEVICE);
-	if (dma_mapping_error(ndev->dev.parent, dma_addr)) {
-		dev_kfree_skb_any(skb);
-		return ret;
-	}
-
-	gq->skbs[gq->cur] = skb;
-	desc = &gq->tx_ring[gq->cur];
-	rswitch_desc_set_dptr(&desc->desc, dma_addr);
-	desc->desc.info_ds = cpu_to_le16(skb->len);
-
 	desc->info1 = cpu_to_le64(INFO1_DV(BIT(rdev->etha->index)) |
 				  INFO1_IPV(GWCA_IPV_NUM) | INFO1_FMT);
 	if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) {
 		struct rswitch_gwca_ts_info *ts_info;
 
 		ts_info = kzalloc(sizeof(*ts_info), GFP_ATOMIC);
-		if (!ts_info) {
-			dma_unmap_single(ndev->dev.parent, dma_addr, skb->len, DMA_TO_DEVICE);
-			return -ENOMEM;
-		}
+		if (!ts_info)
+			return false;
 
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 		rdev->ts_tag++;
@@ -1550,15 +1612,102 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd
 		skb_tx_timestamp(skb);
 	}
 
+	return true;
+}
+
+static bool rswitch_ext_desc_set(struct rswitch_device *rdev,
+				 struct sk_buff *skb,
+				 struct rswitch_ext_desc *desc,
+				 dma_addr_t dma_addr, u16 len, u8 die_dt)
+{
+	rswitch_desc_set_dptr(&desc->desc, dma_addr);
+	desc->desc.info_ds = cpu_to_le16(len);
+	if (!rswitch_ext_desc_set_info1(rdev, skb, desc))
+		return false;
+
 	dma_wmb();
 
-	desc->desc.die_dt = DT_FSINGLE | DIE;
+	desc->desc.die_dt = die_dt;
+
+	return true;
+}
+
+static u8 rswitch_ext_desc_get_die_dt(unsigned int nr_desc, unsigned int index)
+{
+	if (nr_desc == 1)
+		return DT_FSINGLE | DIE;
+	if (index == 0)
+		return DT_FSTART;
+	if (nr_desc - 1 == index)
+		return DT_FEND | DIE;
+	return DT_FMID;
+}
+
+static u16 rswitch_ext_desc_get_len(u8 die_dt, unsigned int orig_len)
+{
+	switch (die_dt & DT_MASK) {
+	case DT_FSINGLE:
+	case DT_FEND:
+		return (orig_len % RSWITCH_DESC_BUF_SIZE) ?: RSWITCH_DESC_BUF_SIZE;
+	case DT_FSTART:
+	case DT_FMID:
+		return RSWITCH_DESC_BUF_SIZE;
+	default:
+		return 0;
+	}
+}
+
+static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct rswitch_device *rdev = netdev_priv(ndev);
+	struct rswitch_gwca_queue *gq = rdev->tx_queue;
+	dma_addr_t dma_addr, dma_addr_orig;
+	netdev_tx_t ret = NETDEV_TX_OK;
+	struct rswitch_ext_desc *desc;
+	unsigned int i, nr_desc;
+	u8 die_dt;
+	u16 len;
+
+	nr_desc = (skb->len - 1) / RSWITCH_DESC_BUF_SIZE + 1;
+	if (rswitch_get_num_cur_queues(gq) >= gq->ring_size - nr_desc) {
+		netif_stop_subqueue(ndev, 0);
+		return NETDEV_TX_BUSY;
+	}
+
+	if (skb_put_padto(skb, ETH_ZLEN))
+		return ret;
+
+	dma_addr_orig = dma_map_single(ndev->dev.parent, skb->data, skb->len, DMA_TO_DEVICE);
+	if (dma_mapping_error(ndev->dev.parent, dma_addr_orig))
+		goto err_kfree;
+
+	gq->skbs[gq->cur] = skb;
+	gq->unmap_addrs[gq->cur] = dma_addr_orig;
+
+	/* DT_FSTART should be set at last. So, this is reverse order. */
+	for (i = nr_desc; i-- > 0; ) {
+		desc = &gq->tx_ring[rswitch_next_queue_index(gq, true, i)];
+		die_dt = rswitch_ext_desc_get_die_dt(nr_desc, i);
+		dma_addr = dma_addr_orig + i * RSWITCH_DESC_BUF_SIZE;
+		len = rswitch_ext_desc_get_len(die_dt, skb->len);
+		if (!rswitch_ext_desc_set(rdev, skb, desc, dma_addr, len, die_dt))
+			goto err_unmap;
+	}
+
 	wmb();	/* gq->cur must be incremented after die_dt was set */
 
-	gq->cur = rswitch_next_queue_index(gq, true, 1);
+	gq->cur = rswitch_next_queue_index(gq, true, nr_desc);
 	rswitch_modify(rdev->addr, GWTRC(gq->index), 0, BIT(gq->index % 32));
 
 	return ret;
+
+err_unmap:
+	dma_unmap_single(ndev->dev.parent, dma_addr_orig, skb->len, DMA_TO_DEVICE);
+
+err_kfree:
+	dev_kfree_skb_any(skb);
+
+	return ret;
 }
 
 static struct net_device_stats *rswitch_get_stats(struct net_device *ndev)
@@ -1689,7 +1838,7 @@ static const struct of_device_id renesas_eth_sw_of_table[] = {
 };
 MODULE_DEVICE_TABLE(of, renesas_eth_sw_of_table);
 
-static void rswitch_etha_init(struct rswitch_private *priv, int index)
+static void rswitch_etha_init(struct rswitch_private *priv, unsigned int index)
 {
 	struct rswitch_etha *etha = &priv->etha[index];
 
@@ -1705,7 +1854,7 @@ static void rswitch_etha_init(struct rswitch_private *priv, int index)
 	etha->psmcs = clk_get_rate(priv->clk) / 100000 / (25 * 2) - 1;
 }
 
-static int rswitch_device_alloc(struct rswitch_private *priv, int index)
+static int rswitch_device_alloc(struct rswitch_private *priv, unsigned int index)
 {
 	struct platform_device *pdev = priv->pdev;
 	struct rswitch_device *rdev;
@@ -1734,6 +1883,8 @@ static int rswitch_device_alloc(struct rswitch_private *priv, int index)
 	snprintf(ndev->name, IFNAMSIZ, "tsn%d", index);
 	ndev->netdev_ops = &rswitch_netdev_ops;
 	ndev->ethtool_ops = &rswitch_ethtool_ops;
+	ndev->max_mtu = RSWITCH_MAX_MTU;
+	ndev->min_mtu = ETH_MIN_MTU;
 
 	netif_napi_add(ndev, &rdev->napi, rswitch_poll);
 
@@ -1776,7 +1927,7 @@ out_get_params:
 	return err;
 }
 
-static void rswitch_device_free(struct rswitch_private *priv, int index)
+static void rswitch_device_free(struct rswitch_private *priv, unsigned int index)
 {
 	struct rswitch_device *rdev = priv->rdev[index];
 	struct net_device *ndev = rdev->ndev;
@@ -1828,8 +1979,8 @@ static int rswitch_init(struct rswitch_private *priv)
 
 	rswitch_fwd_init(priv);
 
-	err = rcar_gen4_ptp_register(priv->ptp_priv, RCAR_GEN4_PTP_REG_LAYOUT_S4,
-				     RCAR_GEN4_PTP_CLOCK_S4);
+	err = rcar_gen4_ptp_register(priv->ptp_priv, RCAR_GEN4_PTP_REG_LAYOUT,
+				     clk_get_rate(priv->clk));
 	if (err < 0)
 		goto err_ptp_register;
 
diff --git a/drivers/net/ethernet/renesas/rswitch.h b/drivers/net/ethernet/renesas/rswitch.h
index 27c9d3872c0e..72e3ff596d31 100644
--- a/drivers/net/ethernet/renesas/rswitch.h
+++ b/drivers/net/ethernet/renesas/rswitch.h
@@ -26,11 +26,17 @@
 		else
 
 #define TX_RING_SIZE		1024
-#define RX_RING_SIZE		1024
+#define RX_RING_SIZE		4096
 #define TS_RING_SIZE		(TX_RING_SIZE * RSWITCH_NUM_PORTS)
 
-#define PKT_BUF_SZ		1584
+#define RSWITCH_MAX_MTU		9600
+#define RSWITCH_HEADROOM	(NET_SKB_PAD + NET_IP_ALIGN)
+#define RSWITCH_DESC_BUF_SIZE	2048
+#define RSWITCH_TAILROOM	SKB_DATA_ALIGN(sizeof(struct skb_shared_info))
 #define RSWITCH_ALIGN		128
+#define RSWITCH_BUF_SIZE	(RSWITCH_HEADROOM + RSWITCH_DESC_BUF_SIZE + \
+				 RSWITCH_TAILROOM + RSWITCH_ALIGN)
+#define RSWITCH_MAP_BUF_SIZE	(RSWITCH_BUF_SIZE - RSWITCH_HEADROOM)
 #define RSWITCH_MAX_CTAG_PCP	7
 
 #define RSWITCH_TIMEOUT_US	100000
@@ -768,6 +774,10 @@ enum rswitch_gwca_mode {
 #define GWARIRM_ARIOG		BIT(0)
 #define GWARIRM_ARR		BIT(1)
 
+#define GWMDNC_TSDMN(num)	(((num) << 16) & GENMASK(17, 16))
+#define GWMDNC_TXDMN(num)	(((num) << 8) & GENMASK(12, 8))
+#define GWMDNC_RXDMN(num)	((num) & GENMASK(4, 0))
+
 #define GWDCC_BALR		BIT(24)
 #define GWDCC_DCP_MASK		GENMASK(18, 16)
 #define GWDCC_DCP(prio)		FIELD_PREP(GWDCC_DCP_MASK, (prio))
@@ -909,7 +919,7 @@ struct rswitch_ext_ts_desc {
 } __packed;
 
 struct rswitch_etha {
-	int index;
+	unsigned int index;
 	void __iomem *addr;
 	void __iomem *coma_addr;
 	bool external_phy;
@@ -938,15 +948,28 @@ struct rswitch_gwca_queue {
 
 	/* Common */
 	dma_addr_t ring_dma;
-	int ring_size;
-	int cur;
-	int dirty;
+	unsigned int ring_size;
+	unsigned int cur;
+	unsigned int dirty;
 
-	/* For [rt]_ring */
-	int index;
+	/* For [rt]x_ring */
+	unsigned int index;
 	bool dir_tx;
-	struct sk_buff **skbs;
 	struct net_device *ndev;	/* queue to ndev for irq */
+
+	union {
+		/* For TX */
+		struct {
+			struct sk_buff **skbs;
+			dma_addr_t *unmap_addrs;
+		};
+		/* For RX */
+		struct {
+			void **rx_bufs;
+			struct sk_buff *skb_fstart;
+			u16 pkt_len;
+		};
+	};
 };
 
 struct rswitch_gwca_ts_info {
@@ -959,7 +982,7 @@ struct rswitch_gwca_ts_info {
 
 #define RSWITCH_NUM_IRQ_REGS	(RSWITCH_MAX_NUM_QUEUES / BITS_PER_TYPE(u32))
 struct rswitch_gwca {
-	int index;
+	unsigned int index;
 	struct rswitch_desc *linkfix_table;
 	dma_addr_t linkfix_table_dma;
 	u32 linkfix_table_size;
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 6dfa062feebc..8fa6c0e9195b 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -3706,13 +3706,13 @@ static int efx_ef10_ptp_set_ts_sync_events(struct efx_nic *efx, bool en,
 }
 
 static int efx_ef10_ptp_set_ts_config_vf(struct efx_nic *efx,
-					 struct hwtstamp_config *init)
+					 struct kernel_hwtstamp_config *init)
 {
 	return -EOPNOTSUPP;
 }
 
 static int efx_ef10_ptp_set_ts_config(struct efx_nic *efx,
-				      struct hwtstamp_config *init)
+				      struct kernel_hwtstamp_config *init)
 {
 	int rc;
 
diff --git a/drivers/net/ethernet/sfc/ef100_ethtool.c b/drivers/net/ethernet/sfc/ef100_ethtool.c
index 702abbe59b76..cf55202b3a7b 100644
--- a/drivers/net/ethernet/sfc/ef100_ethtool.c
+++ b/drivers/net/ethernet/sfc/ef100_ethtool.c
@@ -37,6 +37,7 @@ ef100_ethtool_get_ringparam(struct net_device *net_dev,
 /*	Ethtool options available
  */
 const struct ethtool_ops ef100_ethtool_ops = {
+	.cap_rss_ctx_supported	= true,
 	.get_drvinfo		= efx_ethtool_get_drvinfo,
 	.get_msglevel		= efx_ethtool_get_msglevel,
 	.set_msglevel		= efx_ethtool_set_msglevel,
@@ -60,8 +61,6 @@ const struct ethtool_ops ef100_ethtool_ops = {
 	.get_rxfh_key_size	= efx_ethtool_get_rxfh_key_size,
 	.get_rxfh		= efx_ethtool_get_rxfh,
 	.set_rxfh		= efx_ethtool_set_rxfh,
-	.get_rxfh_context	= efx_ethtool_get_rxfh_context,
-	.set_rxfh_context	= efx_ethtool_set_rxfh_context,
 
 	.get_module_info	= efx_ethtool_get_module_info,
 	.get_module_eeprom	= efx_ethtool_get_module_eeprom,
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 19f4b4d0b851..e9d9de8e648a 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -495,11 +495,6 @@ static int efx_ioctl(struct net_device *net_dev, struct ifreq *ifr, int cmd)
 	struct efx_nic *efx = efx_netdev_priv(net_dev);
 	struct mii_ioctl_data *data = if_mii(ifr);
 
-	if (cmd == SIOCSHWTSTAMP)
-		return efx_ptp_set_ts_config(efx, ifr);
-	if (cmd == SIOCGHWTSTAMP)
-		return efx_ptp_get_ts_config(efx, ifr);
-
 	/* Convert phy_id from older PRTAD/DEVAD format */
 	if ((cmd == SIOCGMIIREG || cmd == SIOCSMIIREG) &&
 	    (data->phy_id & 0xfc00) == 0x0400)
@@ -581,6 +576,23 @@ static int efx_vlan_rx_kill_vid(struct net_device *net_dev, __be16 proto, u16 vi
 		return -EOPNOTSUPP;
 }
 
+static int efx_hwtstamp_set(struct net_device *net_dev,
+			    struct kernel_hwtstamp_config *config,
+			    struct netlink_ext_ack *extack)
+{
+	struct efx_nic *efx = efx_netdev_priv(net_dev);
+
+	return efx_ptp_set_ts_config(efx, config, extack);
+}
+
+static int efx_hwtstamp_get(struct net_device *net_dev,
+			    struct kernel_hwtstamp_config *config)
+{
+	struct efx_nic *efx = efx_netdev_priv(net_dev);
+
+	return efx_ptp_get_ts_config(efx, config);
+}
+
 static const struct net_device_ops efx_netdev_ops = {
 	.ndo_open		= efx_net_open,
 	.ndo_stop		= efx_net_stop,
@@ -596,6 +608,8 @@ static const struct net_device_ops efx_netdev_ops = {
 	.ndo_features_check	= efx_features_check,
 	.ndo_vlan_rx_add_vid	= efx_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= efx_vlan_rx_kill_vid,
+	.ndo_hwtstamp_set	= efx_hwtstamp_set,
+	.ndo_hwtstamp_get	= efx_hwtstamp_get,
 #ifdef CONFIG_SFC_SRIOV
 	.ndo_set_vf_mac		= efx_sriov_set_vf_mac,
 	.ndo_set_vf_vlan	= efx_sriov_set_vf_vlan,
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 364323599f7b..37c69c8d90b1 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -240,6 +240,7 @@ static int efx_ethtool_get_ts_info(struct net_device *net_dev,
 }
 
 const struct ethtool_ops efx_ethtool_ops = {
+	.cap_rss_ctx_supported	= true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_USECS_IRQ |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE_RX,
@@ -269,8 +270,6 @@ const struct ethtool_ops efx_ethtool_ops = {
 	.get_rxfh_key_size	= efx_ethtool_get_rxfh_key_size,
 	.get_rxfh		= efx_ethtool_get_rxfh,
 	.set_rxfh		= efx_ethtool_set_rxfh,
-	.get_rxfh_context	= efx_ethtool_get_rxfh_context,
-	.set_rxfh_context	= efx_ethtool_set_rxfh_context,
 	.get_ts_info		= efx_ethtool_get_ts_info,
 	.get_module_info	= efx_ethtool_get_module_info,
 	.get_module_eeprom	= efx_ethtool_get_module_eeprom,
diff --git a/drivers/net/ethernet/sfc/ethtool_common.c b/drivers/net/ethernet/sfc/ethtool_common.c
index a8cbceeb301b..7d5e5db4eac5 100644
--- a/drivers/net/ethernet/sfc/ethtool_common.c
+++ b/drivers/net/ethernet/sfc/ethtool_common.c
@@ -1163,48 +1163,8 @@ u32 efx_ethtool_get_rxfh_key_size(struct net_device *net_dev)
 	return efx->type->rx_hash_key_size;
 }
 
-int efx_ethtool_get_rxfh(struct net_device *net_dev, u32 *indir, u8 *key,
-			 u8 *hfunc)
-{
-	struct efx_nic *efx = efx_netdev_priv(net_dev);
-	int rc;
-
-	rc = efx->type->rx_pull_rss_config(efx);
-	if (rc)
-		return rc;
-
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (indir)
-		memcpy(indir, efx->rss_context.rx_indir_table,
-		       sizeof(efx->rss_context.rx_indir_table));
-	if (key)
-		memcpy(key, efx->rss_context.rx_hash_key,
-		       efx->type->rx_hash_key_size);
-	return 0;
-}
-
-int efx_ethtool_set_rxfh(struct net_device *net_dev, const u32 *indir,
-			 const u8 *key, const u8 hfunc)
-{
-	struct efx_nic *efx = efx_netdev_priv(net_dev);
-
-	/* Hash function is Toeplitz, cannot be changed */
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
-		return -EOPNOTSUPP;
-	if (!indir && !key)
-		return 0;
-
-	if (!key)
-		key = efx->rss_context.rx_hash_key;
-	if (!indir)
-		indir = efx->rss_context.rx_indir_table;
-
-	return efx->type->rx_push_rss_config(efx, true, indir, key);
-}
-
-int efx_ethtool_get_rxfh_context(struct net_device *net_dev, u32 *indir,
-				 u8 *key, u8 *hfunc, u32 rss_context)
+static int efx_ethtool_get_rxfh_context(struct net_device *net_dev,
+					struct ethtool_rxfh_param *rxfh)
 {
 	struct efx_nic *efx = efx_netdev_priv(net_dev);
 	struct efx_rss_context *ctx;
@@ -1214,7 +1174,7 @@ int efx_ethtool_get_rxfh_context(struct net_device *net_dev, u32 *indir,
 		return -EOPNOTSUPP;
 
 	mutex_lock(&efx->rss_lock);
-	ctx = efx_find_rss_context_entry(efx, rss_context);
+	ctx = efx_find_rss_context_entry(efx, rxfh->rss_context);
 	if (!ctx) {
 		rc = -ENOENT;
 		goto out_unlock;
@@ -1223,37 +1183,60 @@ int efx_ethtool_get_rxfh_context(struct net_device *net_dev, u32 *indir,
 	if (rc)
 		goto out_unlock;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (indir)
-		memcpy(indir, ctx->rx_indir_table, sizeof(ctx->rx_indir_table));
-	if (key)
-		memcpy(key, ctx->rx_hash_key, efx->type->rx_hash_key_size);
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (rxfh->indir)
+		memcpy(rxfh->indir, ctx->rx_indir_table,
+		       sizeof(ctx->rx_indir_table));
+	if (rxfh->key)
+		memcpy(rxfh->key, ctx->rx_hash_key,
+		       efx->type->rx_hash_key_size);
 out_unlock:
 	mutex_unlock(&efx->rss_lock);
 	return rc;
 }
 
-int efx_ethtool_set_rxfh_context(struct net_device *net_dev,
-				 const u32 *indir, const u8 *key,
-				 const u8 hfunc, u32 *rss_context,
-				 bool delete)
+int efx_ethtool_get_rxfh(struct net_device *net_dev,
+			 struct ethtool_rxfh_param *rxfh)
+{
+	struct efx_nic *efx = efx_netdev_priv(net_dev);
+	int rc;
+
+	if (rxfh->rss_context)
+		return efx_ethtool_get_rxfh_context(net_dev, rxfh);
+
+	rc = efx->type->rx_pull_rss_config(efx);
+	if (rc)
+		return rc;
+
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (rxfh->indir)
+		memcpy(rxfh->indir, efx->rss_context.rx_indir_table,
+		       sizeof(efx->rss_context.rx_indir_table));
+	if (rxfh->key)
+		memcpy(rxfh->key, efx->rss_context.rx_hash_key,
+		       efx->type->rx_hash_key_size);
+	return 0;
+}
+
+static int efx_ethtool_set_rxfh_context(struct net_device *net_dev,
+					struct ethtool_rxfh_param *rxfh,
+					struct netlink_ext_ack *extack)
 {
 	struct efx_nic *efx = efx_netdev_priv(net_dev);
+	u32 *rss_context = &rxfh->rss_context;
 	struct efx_rss_context *ctx;
+	u32 *indir = rxfh->indir;
 	bool allocated = false;
+	u8 *key = rxfh->key;
 	int rc;
 
 	if (!efx->type->rx_push_rss_context_config)
 		return -EOPNOTSUPP;
-	/* Hash function is Toeplitz, cannot be changed */
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
-		return -EOPNOTSUPP;
 
 	mutex_lock(&efx->rss_lock);
 
 	if (*rss_context == ETH_RXFH_CONTEXT_ALLOC) {
-		if (delete) {
+		if (rxfh->rss_delete) {
 			/* alloc + delete == Nothing to do */
 			rc = -EINVAL;
 			goto out_unlock;
@@ -1276,7 +1259,7 @@ int efx_ethtool_set_rxfh_context(struct net_device *net_dev,
 		}
 	}
 
-	if (delete) {
+	if (rxfh->rss_delete) {
 		/* delete this context */
 		rc = efx->type->rx_push_rss_context_config(efx, ctx, NULL, NULL);
 		if (!rc)
@@ -1299,6 +1282,33 @@ out_unlock:
 	return rc;
 }
 
+int efx_ethtool_set_rxfh(struct net_device *net_dev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
+{
+	struct efx_nic *efx = efx_netdev_priv(net_dev);
+	u32 *indir = rxfh->indir;
+	u8 *key = rxfh->key;
+
+	/* Hash function is Toeplitz, cannot be changed */
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+
+	if (rxfh->rss_context)
+		return efx_ethtool_set_rxfh_context(net_dev, rxfh, extack);
+
+	if (!indir && !key)
+		return 0;
+
+	if (!key)
+		key = efx->rss_context.rx_hash_key;
+	if (!indir)
+		indir = efx->rss_context.rx_indir_table;
+
+	return efx->type->rx_push_rss_config(efx, true, indir, key);
+}
+
 int efx_ethtool_reset(struct net_device *net_dev, u32 *flags)
 {
 	struct efx_nic *efx = efx_netdev_priv(net_dev);
diff --git a/drivers/net/ethernet/sfc/ethtool_common.h b/drivers/net/ethernet/sfc/ethtool_common.h
index 659491932101..a680e5980213 100644
--- a/drivers/net/ethernet/sfc/ethtool_common.h
+++ b/drivers/net/ethernet/sfc/ethtool_common.h
@@ -44,16 +44,11 @@ int efx_ethtool_set_rxnfc(struct net_device *net_dev,
 			  struct ethtool_rxnfc *info);
 u32 efx_ethtool_get_rxfh_indir_size(struct net_device *net_dev);
 u32 efx_ethtool_get_rxfh_key_size(struct net_device *net_dev);
-int efx_ethtool_get_rxfh(struct net_device *net_dev, u32 *indir, u8 *key,
-			 u8 *hfunc);
+int efx_ethtool_get_rxfh(struct net_device *net_dev,
+			 struct ethtool_rxfh_param *rxfh);
 int efx_ethtool_set_rxfh(struct net_device *net_dev,
-			 const u32 *indir, const u8 *key, const u8 hfunc);
-int efx_ethtool_get_rxfh_context(struct net_device *net_dev, u32 *indir,
-				 u8 *key, u8 *hfunc, u32 rss_context);
-int efx_ethtool_set_rxfh_context(struct net_device *net_dev,
-				 const u32 *indir, const u8 *key,
-				 const u8 hfunc, u32 *rss_context,
-				 bool delete);
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack);
 int efx_ethtool_reset(struct net_device *net_dev, u32 *flags);
 int efx_ethtool_get_module_eeprom(struct net_device *net_dev,
 				  struct ethtool_eeprom *ee,
diff --git a/drivers/net/ethernet/sfc/falcon/ethtool.c b/drivers/net/ethernet/sfc/falcon/ethtool.c
index 3976a333f7e3..f4db683b80f7 100644
--- a/drivers/net/ethernet/sfc/falcon/ethtool.c
+++ b/drivers/net/ethernet/sfc/falcon/ethtool.c
@@ -1257,31 +1257,33 @@ static u32 ef4_ethtool_get_rxfh_indir_size(struct net_device *net_dev)
 		0 : ARRAY_SIZE(efx->rx_indir_table));
 }
 
-static int ef4_ethtool_get_rxfh(struct net_device *net_dev, u32 *indir, u8 *key,
-				u8 *hfunc)
+static int ef4_ethtool_get_rxfh(struct net_device *net_dev,
+				struct ethtool_rxfh_param *rxfh)
 {
 	struct ef4_nic *efx = netdev_priv(net_dev);
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (indir)
-		memcpy(indir, efx->rx_indir_table, sizeof(efx->rx_indir_table));
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (rxfh->indir)
+		memcpy(rxfh->indir, efx->rx_indir_table,
+		       sizeof(efx->rx_indir_table));
 	return 0;
 }
 
-static int ef4_ethtool_set_rxfh(struct net_device *net_dev, const u32 *indir,
-				const u8 *key, const u8 hfunc)
+static int ef4_ethtool_set_rxfh(struct net_device *net_dev,
+				struct ethtool_rxfh_param *rxfh,
+				struct netlink_ext_ack *extack)
 {
 	struct ef4_nic *efx = netdev_priv(net_dev);
 
 	/* We do not allow change in unsupported parameters */
-	if (key ||
-	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->key ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP))
 		return -EOPNOTSUPP;
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
-	return efx->type->rx_push_rss_config(efx, true, indir);
+	return efx->type->rx_push_rss_config(efx, true, rxfh->indir);
 }
 
 static int ef4_ethtool_get_module_eeprom(struct net_device *net_dev,
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 27d86e90a3bb..f2dd7feb0e0c 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -1473,7 +1473,7 @@ struct efx_nic_type {
 	void (*ptp_write_host_time)(struct efx_nic *efx, u32 host_time);
 	int (*ptp_set_ts_sync_events)(struct efx_nic *efx, bool en, bool temp);
 	int (*ptp_set_ts_config)(struct efx_nic *efx,
-				 struct hwtstamp_config *init);
+				 struct kernel_hwtstamp_config *init);
 	int (*sriov_configure)(struct efx_nic *efx, int num_vfs);
 	int (*vlan_rx_add_vid)(struct efx_nic *efx, __be16 proto, u16 vid);
 	int (*vlan_rx_kill_vid)(struct efx_nic *efx, __be16 proto, u16 vid);
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index b04fdbb8aece..c3bffbf0ba2b 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -301,7 +301,7 @@ struct efx_ptp_data {
 	bool reset_required;
 	struct list_head rxfilters_mcast;
 	struct list_head rxfilters_ucast;
-	struct hwtstamp_config config;
+	struct kernel_hwtstamp_config config;
 	bool enabled;
 	unsigned int mode;
 	void (*ns_to_nic_time)(s64 ns, u32 *nic_major, u32 *nic_minor);
@@ -1848,7 +1848,7 @@ int efx_ptp_change_mode(struct efx_nic *efx, bool enable_wanted,
 	return 0;
 }
 
-static int efx_ptp_ts_init(struct efx_nic *efx, struct hwtstamp_config *init)
+static int efx_ptp_ts_init(struct efx_nic *efx, struct kernel_hwtstamp_config *init)
 {
 	int rc;
 
@@ -1895,33 +1895,25 @@ void efx_ptp_get_ts_info(struct efx_nic *efx, struct ethtool_ts_info *ts_info)
 	ts_info->rx_filters = ptp->efx->type->hwtstamp_filters;
 }
 
-int efx_ptp_set_ts_config(struct efx_nic *efx, struct ifreq *ifr)
+int efx_ptp_set_ts_config(struct efx_nic *efx,
+			  struct kernel_hwtstamp_config *config,
+			  struct netlink_ext_ack __always_unused *extack)
 {
-	struct hwtstamp_config config;
-	int rc;
-
 	/* Not a PTP enabled port */
 	if (!efx->ptp_data)
 		return -EOPNOTSUPP;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	rc = efx_ptp_ts_init(efx, &config);
-	if (rc != 0)
-		return rc;
-
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config))
-		? -EFAULT : 0;
+	return efx_ptp_ts_init(efx, config);
 }
 
-int efx_ptp_get_ts_config(struct efx_nic *efx, struct ifreq *ifr)
+int efx_ptp_get_ts_config(struct efx_nic *efx,
+			  struct kernel_hwtstamp_config *config)
 {
+	/* Not a PTP enabled port */
 	if (!efx->ptp_data)
 		return -EOPNOTSUPP;
-
-	return copy_to_user(ifr->ifr_data, &efx->ptp_data->config,
-			    sizeof(efx->ptp_data->config)) ? -EFAULT : 0;
+	*config = efx->ptp_data->config;
+	return 0;
 }
 
 static void ptp_event_failure(struct efx_nic *efx, int expected_frag_len)
diff --git a/drivers/net/ethernet/sfc/ptp.h b/drivers/net/ethernet/sfc/ptp.h
index 7b1ef7002b3f..2f30dbb490d2 100644
--- a/drivers/net/ethernet/sfc/ptp.h
+++ b/drivers/net/ethernet/sfc/ptp.h
@@ -18,8 +18,11 @@ void efx_ptp_defer_probe_with_channel(struct efx_nic *efx);
 struct efx_channel *efx_ptp_channel(struct efx_nic *efx);
 void efx_ptp_update_channel(struct efx_nic *efx, struct efx_channel *channel);
 void efx_ptp_remove(struct efx_nic *efx);
-int efx_ptp_set_ts_config(struct efx_nic *efx, struct ifreq *ifr);
-int efx_ptp_get_ts_config(struct efx_nic *efx, struct ifreq *ifr);
+int efx_ptp_set_ts_config(struct efx_nic *efx,
+			  struct kernel_hwtstamp_config *config,
+			  struct netlink_ext_ack *extack);
+int efx_ptp_get_ts_config(struct efx_nic *efx,
+			  struct kernel_hwtstamp_config *config);
 void efx_ptp_get_ts_info(struct efx_nic *efx, struct ethtool_ts_info *ts_info);
 bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb);
 int efx_ptp_get_mode(struct efx_nic *efx);
diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c
index d2f35ee15eff..fac227d372db 100644
--- a/drivers/net/ethernet/sfc/rx_common.c
+++ b/drivers/net/ethernet/sfc/rx_common.c
@@ -823,8 +823,10 @@ int efx_probe_filters(struct efx_nic *efx)
 		}
 
 		if (!success) {
-			efx_for_each_channel(channel, efx)
+			efx_for_each_channel(channel, efx) {
 				kfree(channel->rps_flow_id);
+				channel->rps_flow_id = NULL;
+			}
 			efx->type->filter_table_remove(efx);
 			rc = -ENOMEM;
 			goto out_unlock;
diff --git a/drivers/net/ethernet/sfc/siena/efx.c b/drivers/net/ethernet/sfc/siena/efx.c
index 8c557f6a183c..59d3a6043379 100644
--- a/drivers/net/ethernet/sfc/siena/efx.c
+++ b/drivers/net/ethernet/sfc/siena/efx.c
@@ -495,11 +495,6 @@ static int efx_ioctl(struct net_device *net_dev, struct ifreq *ifr, int cmd)
 	struct efx_nic *efx = netdev_priv(net_dev);
 	struct mii_ioctl_data *data = if_mii(ifr);
 
-	if (cmd == SIOCSHWTSTAMP)
-		return efx_siena_ptp_set_ts_config(efx, ifr);
-	if (cmd == SIOCGHWTSTAMP)
-		return efx_siena_ptp_get_ts_config(efx, ifr);
-
 	/* Convert phy_id from older PRTAD/DEVAD format */
 	if ((cmd == SIOCGMIIREG || cmd == SIOCSMIIREG) &&
 	    (data->phy_id & 0xfc00) == 0x0400)
@@ -579,6 +574,23 @@ static int efx_vlan_rx_kill_vid(struct net_device *net_dev, __be16 proto, u16 vi
 		return -EOPNOTSUPP;
 }
 
+static int efx_siena_hwtstamp_set(struct net_device *net_dev,
+				  struct kernel_hwtstamp_config *config,
+				  struct netlink_ext_ack *extack)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+
+	return efx_siena_ptp_set_ts_config(efx, config, extack);
+}
+
+static int efx_siena_hwtstamp_get(struct net_device *net_dev,
+				  struct kernel_hwtstamp_config *config)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+
+	return efx_siena_ptp_get_ts_config(efx, config);
+}
+
 static const struct net_device_ops efx_netdev_ops = {
 	.ndo_open		= efx_net_open,
 	.ndo_stop		= efx_net_stop,
@@ -594,6 +606,8 @@ static const struct net_device_ops efx_netdev_ops = {
 	.ndo_features_check	= efx_siena_features_check,
 	.ndo_vlan_rx_add_vid	= efx_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= efx_vlan_rx_kill_vid,
+	.ndo_hwtstamp_set	= efx_siena_hwtstamp_set,
+	.ndo_hwtstamp_get	= efx_siena_hwtstamp_get,
 #ifdef CONFIG_SFC_SIENA_SRIOV
 	.ndo_set_vf_mac		= efx_sriov_set_vf_mac,
 	.ndo_set_vf_vlan	= efx_sriov_set_vf_vlan,
diff --git a/drivers/net/ethernet/sfc/siena/ethtool.c b/drivers/net/ethernet/sfc/siena/ethtool.c
index e4ec589216c1..14dd3893bdef 100644
--- a/drivers/net/ethernet/sfc/siena/ethtool.c
+++ b/drivers/net/ethernet/sfc/siena/ethtool.c
@@ -240,6 +240,7 @@ static int efx_ethtool_get_ts_info(struct net_device *net_dev,
 }
 
 const struct ethtool_ops efx_siena_ethtool_ops = {
+	.cap_rss_ctx_supported	= true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_USECS_IRQ |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE_RX,
@@ -269,8 +270,6 @@ const struct ethtool_ops efx_siena_ethtool_ops = {
 	.get_rxfh_key_size	= efx_siena_ethtool_get_rxfh_key_size,
 	.get_rxfh		= efx_siena_ethtool_get_rxfh,
 	.set_rxfh		= efx_siena_ethtool_set_rxfh,
-	.get_rxfh_context	= efx_siena_ethtool_get_rxfh_context,
-	.set_rxfh_context	= efx_siena_ethtool_set_rxfh_context,
 	.get_ts_info		= efx_ethtool_get_ts_info,
 	.get_module_info	= efx_siena_ethtool_get_module_info,
 	.get_module_eeprom	= efx_siena_ethtool_get_module_eeprom,
diff --git a/drivers/net/ethernet/sfc/siena/ethtool_common.c b/drivers/net/ethernet/sfc/siena/ethtool_common.c
index f590e87e5a23..5f0a8127e967 100644
--- a/drivers/net/ethernet/sfc/siena/ethtool_common.c
+++ b/drivers/net/ethernet/sfc/siena/ethtool_common.c
@@ -1164,48 +1164,8 @@ u32 efx_siena_ethtool_get_rxfh_key_size(struct net_device *net_dev)
 	return efx->type->rx_hash_key_size;
 }
 
-int efx_siena_ethtool_get_rxfh(struct net_device *net_dev, u32 *indir, u8 *key,
-			       u8 *hfunc)
-{
-	struct efx_nic *efx = netdev_priv(net_dev);
-	int rc;
-
-	rc = efx->type->rx_pull_rss_config(efx);
-	if (rc)
-		return rc;
-
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (indir)
-		memcpy(indir, efx->rss_context.rx_indir_table,
-		       sizeof(efx->rss_context.rx_indir_table));
-	if (key)
-		memcpy(key, efx->rss_context.rx_hash_key,
-		       efx->type->rx_hash_key_size);
-	return 0;
-}
-
-int efx_siena_ethtool_set_rxfh(struct net_device *net_dev, const u32 *indir,
-			       const u8 *key, const u8 hfunc)
-{
-	struct efx_nic *efx = netdev_priv(net_dev);
-
-	/* Hash function is Toeplitz, cannot be changed */
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
-		return -EOPNOTSUPP;
-	if (!indir && !key)
-		return 0;
-
-	if (!key)
-		key = efx->rss_context.rx_hash_key;
-	if (!indir)
-		indir = efx->rss_context.rx_indir_table;
-
-	return efx->type->rx_push_rss_config(efx, true, indir, key);
-}
-
-int efx_siena_ethtool_get_rxfh_context(struct net_device *net_dev, u32 *indir,
-				       u8 *key, u8 *hfunc, u32 rss_context)
+static int efx_siena_ethtool_get_rxfh_context(struct net_device *net_dev,
+					      struct ethtool_rxfh_param *rxfh)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 	struct efx_rss_context *ctx;
@@ -1215,7 +1175,7 @@ int efx_siena_ethtool_get_rxfh_context(struct net_device *net_dev, u32 *indir,
 		return -EOPNOTSUPP;
 
 	mutex_lock(&efx->rss_lock);
-	ctx = efx_siena_find_rss_context_entry(efx, rss_context);
+	ctx = efx_siena_find_rss_context_entry(efx, rxfh->rss_context);
 	if (!ctx) {
 		rc = -ENOENT;
 		goto out_unlock;
@@ -1224,37 +1184,60 @@ int efx_siena_ethtool_get_rxfh_context(struct net_device *net_dev, u32 *indir,
 	if (rc)
 		goto out_unlock;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (indir)
-		memcpy(indir, ctx->rx_indir_table, sizeof(ctx->rx_indir_table));
-	if (key)
-		memcpy(key, ctx->rx_hash_key, efx->type->rx_hash_key_size);
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (rxfh->indir)
+		memcpy(rxfh->indir, ctx->rx_indir_table,
+		       sizeof(ctx->rx_indir_table));
+	if (rxfh->key)
+		memcpy(rxfh->key, ctx->rx_hash_key,
+		       efx->type->rx_hash_key_size);
 out_unlock:
 	mutex_unlock(&efx->rss_lock);
 	return rc;
 }
 
-int efx_siena_ethtool_set_rxfh_context(struct net_device *net_dev,
-				       const u32 *indir, const u8 *key,
-				       const u8 hfunc, u32 *rss_context,
-				       bool delete)
+int efx_siena_ethtool_get_rxfh(struct net_device *net_dev,
+			       struct ethtool_rxfh_param *rxfh)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+	int rc;
+
+	if (rxfh->rss_context)
+		return efx_siena_ethtool_get_rxfh_context(net_dev, rxfh);
+
+	rc = efx->type->rx_pull_rss_config(efx);
+	if (rc)
+		return rc;
+
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (rxfh->indir)
+		memcpy(rxfh->indir, efx->rss_context.rx_indir_table,
+		       sizeof(efx->rss_context.rx_indir_table));
+	if (rxfh->key)
+		memcpy(rxfh->key, efx->rss_context.rx_hash_key,
+		       efx->type->rx_hash_key_size);
+	return 0;
+}
+
+static int efx_siena_ethtool_set_rxfh_context(struct net_device *net_dev,
+					      struct ethtool_rxfh_param *rxfh,
+					      struct netlink_ext_ack *extack)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
+	u32 *rss_context = &rxfh->rss_context;
 	struct efx_rss_context *ctx;
+	u32 *indir = rxfh->indir;
 	bool allocated = false;
+	u8 *key = rxfh->key;
 	int rc;
 
 	if (!efx->type->rx_push_rss_context_config)
 		return -EOPNOTSUPP;
-	/* Hash function is Toeplitz, cannot be changed */
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
-		return -EOPNOTSUPP;
 
 	mutex_lock(&efx->rss_lock);
 
 	if (*rss_context == ETH_RXFH_CONTEXT_ALLOC) {
-		if (delete) {
+		if (rxfh->rss_delete) {
 			/* alloc + delete == Nothing to do */
 			rc = -EINVAL;
 			goto out_unlock;
@@ -1277,7 +1260,7 @@ int efx_siena_ethtool_set_rxfh_context(struct net_device *net_dev,
 		}
 	}
 
-	if (delete) {
+	if (rxfh->rss_delete) {
 		/* delete this context */
 		rc = efx->type->rx_push_rss_context_config(efx, ctx, NULL, NULL);
 		if (!rc)
@@ -1300,6 +1283,33 @@ out_unlock:
 	return rc;
 }
 
+int efx_siena_ethtool_set_rxfh(struct net_device *net_dev,
+			       struct ethtool_rxfh_param *rxfh,
+			       struct netlink_ext_ack *extack)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+	u32 *indir = rxfh->indir;
+	u8 *key = rxfh->key;
+
+	/* Hash function is Toeplitz, cannot be changed */
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+
+	if (rxfh->rss_context)
+		efx_siena_ethtool_set_rxfh_context(net_dev, rxfh, extack);
+
+	if (!indir && !key)
+		return 0;
+
+	if (!key)
+		key = efx->rss_context.rx_hash_key;
+	if (!indir)
+		indir = efx->rss_context.rx_indir_table;
+
+	return efx->type->rx_push_rss_config(efx, true, indir, key);
+}
+
 int efx_siena_ethtool_reset(struct net_device *net_dev, u32 *flags)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
diff --git a/drivers/net/ethernet/sfc/siena/ethtool_common.h b/drivers/net/ethernet/sfc/siena/ethtool_common.h
index 04b375dc6800..d674bab0f65b 100644
--- a/drivers/net/ethernet/sfc/siena/ethtool_common.h
+++ b/drivers/net/ethernet/sfc/siena/ethtool_common.h
@@ -41,16 +41,11 @@ int efx_siena_ethtool_set_rxnfc(struct net_device *net_dev,
 				struct ethtool_rxnfc *info);
 u32 efx_siena_ethtool_get_rxfh_indir_size(struct net_device *net_dev);
 u32 efx_siena_ethtool_get_rxfh_key_size(struct net_device *net_dev);
-int efx_siena_ethtool_get_rxfh(struct net_device *net_dev, u32 *indir, u8 *key,
-			       u8 *hfunc);
+int efx_siena_ethtool_get_rxfh(struct net_device *net_dev,
+			       struct ethtool_rxfh_param *rxfh);
 int efx_siena_ethtool_set_rxfh(struct net_device *net_dev,
-			       const u32 *indir, const u8 *key, const u8 hfunc);
-int efx_siena_ethtool_get_rxfh_context(struct net_device *net_dev, u32 *indir,
-				       u8 *key, u8 *hfunc, u32 rss_context);
-int efx_siena_ethtool_set_rxfh_context(struct net_device *net_dev,
-				       const u32 *indir, const u8 *key,
-				       const u8 hfunc, u32 *rss_context,
-				       bool delete);
+			       struct ethtool_rxfh_param *rxfh,
+			       struct netlink_ext_ack *extack);
 int efx_siena_ethtool_reset(struct net_device *net_dev, u32 *flags);
 int efx_siena_ethtool_get_module_eeprom(struct net_device *net_dev,
 					struct ethtool_eeprom *ee,
diff --git a/drivers/net/ethernet/sfc/siena/net_driver.h b/drivers/net/ethernet/sfc/siena/net_driver.h
index ff7bbc325952..94152f595acd 100644
--- a/drivers/net/ethernet/sfc/siena/net_driver.h
+++ b/drivers/net/ethernet/sfc/siena/net_driver.h
@@ -1424,7 +1424,7 @@ struct efx_nic_type {
 	void (*ptp_write_host_time)(struct efx_nic *efx, u32 host_time);
 	int (*ptp_set_ts_sync_events)(struct efx_nic *efx, bool en, bool temp);
 	int (*ptp_set_ts_config)(struct efx_nic *efx,
-				 struct hwtstamp_config *init);
+				 struct kernel_hwtstamp_config *init);
 	int (*sriov_configure)(struct efx_nic *efx, int num_vfs);
 	int (*vlan_rx_add_vid)(struct efx_nic *efx, __be16 proto, u16 vid);
 	int (*vlan_rx_kill_vid)(struct efx_nic *efx, __be16 proto, u16 vid);
diff --git a/drivers/net/ethernet/sfc/siena/ptp.c b/drivers/net/ethernet/sfc/siena/ptp.c
index 38e666561bcd..4b5e2f0ba350 100644
--- a/drivers/net/ethernet/sfc/siena/ptp.c
+++ b/drivers/net/ethernet/sfc/siena/ptp.c
@@ -297,7 +297,7 @@ struct efx_ptp_data {
 	u32 rxfilter_event;
 	u32 rxfilter_general;
 	bool rxfilter_installed;
-	struct hwtstamp_config config;
+	struct kernel_hwtstamp_config config;
 	bool enabled;
 	unsigned int mode;
 	void (*ns_to_nic_time)(s64 ns, u32 *nic_major, u32 *nic_minor);
@@ -1762,7 +1762,8 @@ int efx_siena_ptp_change_mode(struct efx_nic *efx, bool enable_wanted,
 	return 0;
 }
 
-static int efx_ptp_ts_init(struct efx_nic *efx, struct hwtstamp_config *init)
+static int efx_ptp_ts_init(struct efx_nic *efx,
+			   struct kernel_hwtstamp_config *init)
 {
 	int rc;
 
@@ -1799,33 +1800,26 @@ void efx_siena_ptp_get_ts_info(struct efx_nic *efx,
 	ts_info->rx_filters = ptp->efx->type->hwtstamp_filters;
 }
 
-int efx_siena_ptp_set_ts_config(struct efx_nic *efx, struct ifreq *ifr)
+int efx_siena_ptp_set_ts_config(struct efx_nic *efx,
+				struct kernel_hwtstamp_config *config,
+				struct netlink_ext_ack __always_unused *extack)
 {
-	struct hwtstamp_config config;
-	int rc;
-
 	/* Not a PTP enabled port */
 	if (!efx->ptp_data)
 		return -EOPNOTSUPP;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	rc = efx_ptp_ts_init(efx, &config);
-	if (rc != 0)
-		return rc;
-
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config))
-		? -EFAULT : 0;
+	return efx_ptp_ts_init(efx, config);
 }
 
-int efx_siena_ptp_get_ts_config(struct efx_nic *efx, struct ifreq *ifr)
+int efx_siena_ptp_get_ts_config(struct efx_nic *efx,
+				struct kernel_hwtstamp_config *config)
 {
+	/* Not a PTP enabled port */
 	if (!efx->ptp_data)
 		return -EOPNOTSUPP;
 
-	return copy_to_user(ifr->ifr_data, &efx->ptp_data->config,
-			    sizeof(efx->ptp_data->config)) ? -EFAULT : 0;
+	*config = efx->ptp_data->config;
+	return 0;
 }
 
 static void ptp_event_failure(struct efx_nic *efx, int expected_frag_len)
diff --git a/drivers/net/ethernet/sfc/siena/ptp.h b/drivers/net/ethernet/sfc/siena/ptp.h
index 4172f90e9f6f..6352f84424f6 100644
--- a/drivers/net/ethernet/sfc/siena/ptp.h
+++ b/drivers/net/ethernet/sfc/siena/ptp.h
@@ -15,8 +15,11 @@
 struct ethtool_ts_info;
 void efx_siena_ptp_defer_probe_with_channel(struct efx_nic *efx);
 struct efx_channel *efx_siena_ptp_channel(struct efx_nic *efx);
-int efx_siena_ptp_set_ts_config(struct efx_nic *efx, struct ifreq *ifr);
-int efx_siena_ptp_get_ts_config(struct efx_nic *efx, struct ifreq *ifr);
+int efx_siena_ptp_set_ts_config(struct efx_nic *efx,
+				struct kernel_hwtstamp_config *config,
+				struct netlink_ext_ack *extack);
+int efx_siena_ptp_get_ts_config(struct efx_nic *efx,
+				struct kernel_hwtstamp_config *config);
 void efx_siena_ptp_get_ts_info(struct efx_nic *efx,
 			       struct ethtool_ts_info *ts_info);
 bool efx_siena_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb);
diff --git a/drivers/net/ethernet/sfc/siena/siena.c b/drivers/net/ethernet/sfc/siena/siena.c
index a44c8fa25748..ca33dc08e555 100644
--- a/drivers/net/ethernet/sfc/siena/siena.c
+++ b/drivers/net/ethernet/sfc/siena/siena.c
@@ -136,7 +136,7 @@ static void siena_ptp_write_host_time(struct efx_nic *efx, u32 host_time)
 }
 
 static int siena_ptp_set_ts_config(struct efx_nic *efx,
-				   struct hwtstamp_config *init)
+				   struct kernel_hwtstamp_config *init)
 {
 	int rc;
 
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 0891e9e49ecb..5ab8b81b84e6 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -1302,6 +1302,8 @@ static int netsec_setup_rx_dring(struct netsec_priv *priv)
 		.dma_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE,
 		.offset = NETSEC_RXBUF_HEADROOM,
 		.max_len = NETSEC_RX_BUF_SIZE,
+		.napi = &priv->napi,
+		.netdev = priv->ndev,
 	};
 	int i, err;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index a2b9e289aa36..85dcda51df05 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -280,7 +280,7 @@ config DWMAC_INTEL
 config DWMAC_LOONGSON
 	tristate "Loongson PCI DWMAC support"
 	default MACH_LOONGSON64
-	depends on STMMAC_ETH && PCI
+	depends on (MACH_LOONGSON64 || COMPILE_TEST) && STMMAC_ETH && PCI
 	depends on COMMON_CLK
 	help
 	  This selects the LOONGSON PCI bus support for the stmmac driver,
diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index 80e598bd4255..26cad4344701 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -6,7 +6,7 @@ stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o ring_mode.o	\
 	      mmc_core.o stmmac_hwtstamp.o stmmac_ptp.o dwmac4_descs.o	\
 	      dwmac4_dma.o dwmac4_lib.o dwmac4_core.o dwmac5.o hwif.o \
 	      stmmac_tc.o dwxgmac2_core.o dwxgmac2_dma.o dwxgmac2_descs.o \
-	      stmmac_xdp.o \
+	      stmmac_xdp.o stmmac_est.o \
 	      $(stmmac-y)
 
 stmmac-$(CONFIG_STMMAC_SELFTESTS) += stmmac_selftests.o
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index e3f650e88f82..721c1f8e892f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -563,6 +563,7 @@ struct mac_device_info {
 	const struct stmmac_hwtimestamp *ptp;
 	const struct stmmac_tc_ops *tc;
 	const struct stmmac_mmc_ops *mmc;
+	const struct stmmac_est_ops *est;
 	struct dw_xpcs *xpcs;
 	struct phylink_pcs *lynx_pcs; /* Lynx external PCS */
 	struct mii_regs mii;	/* MII register Addresses */
@@ -580,6 +581,7 @@ struct mac_device_info {
 	u32 vlan_filter[32];
 	bool vlan_fail_q_en;
 	u8 vlan_fail_q;
+	bool hw_vlan_en;
 };
 
 struct stmmac_rx_routing {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index 2cd6fce5c993..9e40c28d453a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -59,26 +59,19 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 		return -ENODEV;
 	}
 
-	if (!of_device_is_compatible(np, "loongson, pci-gmac")) {
-		pr_info("dwmac_loongson_pci: Incompatible OF node\n");
-		return -ENODEV;
-	}
-
 	plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL);
 	if (!plat)
 		return -ENOMEM;
 
+	plat->mdio_bus_data = devm_kzalloc(&pdev->dev,
+					   sizeof(*plat->mdio_bus_data),
+					   GFP_KERNEL);
+	if (!plat->mdio_bus_data)
+		return -ENOMEM;
+
 	plat->mdio_node = of_get_child_by_name(np, "mdio");
 	if (plat->mdio_node) {
 		dev_info(&pdev->dev, "Found MDIO subnode\n");
-
-		plat->mdio_bus_data = devm_kzalloc(&pdev->dev,
-						   sizeof(*plat->mdio_bus_data),
-						   GFP_KERNEL);
-		if (!plat->mdio_bus_data) {
-			ret = -ENOMEM;
-			goto err_put_node;
-		}
 		plat->mdio_bus_data->needs_reset = true;
 	}
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index d3bf42d0fceb..31631e3f89d0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -34,6 +34,7 @@
 #define RGMII_CONFIG_LOOPBACK_EN		BIT(2)
 #define RGMII_CONFIG_PROG_SWAP			BIT(1)
 #define RGMII_CONFIG_DDR_MODE			BIT(0)
+#define RGMII_CONFIG_SGMII_CLK_DVDR		GENMASK(18, 10)
 
 /* SDCC_HC_REG_DLL_CONFIG fields */
 #define SDCC_DLL_CONFIG_DLL_RST			BIT(30)
@@ -78,6 +79,8 @@
 #define ETHQOS_MAC_CTRL_SPEED_MODE		BIT(14)
 #define ETHQOS_MAC_CTRL_PORT_SEL		BIT(15)
 
+#define SGMII_10M_RX_CLK_DVDR			0x31
+
 struct ethqos_emac_por {
 	unsigned int offset;
 	unsigned int value;
@@ -598,6 +601,9 @@ static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos)
 	return 0;
 }
 
+/* On interface toggle MAC registers gets reset.
+ * Configure MAC block for SGMII on ethernet phy link up
+ */
 static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos)
 {
 	int val;
@@ -617,6 +623,10 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos)
 	case SPEED_10:
 		val |= ETHQOS_MAC_CTRL_PORT_SEL;
 		val &= ~ETHQOS_MAC_CTRL_SPEED_MODE;
+		rgmii_updatel(ethqos, RGMII_CONFIG_SGMII_CLK_DVDR,
+			      FIELD_PREP(RGMII_CONFIG_SGMII_CLK_DVDR,
+					 SGMII_10M_RX_CLK_DVDR),
+			      RGMII_IO_MACRO_CONFIG);
 		break;
 	}
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index c6ff1fa0e04d..6b6d0de09619 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -1134,6 +1134,35 @@ static int dwmac4_config_l4_filter(struct mac_device_info *hw, u32 filter_no,
 	return 0;
 }
 
+static void dwmac4_rx_hw_vlan(struct mac_device_info *hw,
+			      struct dma_desc *rx_desc, struct sk_buff *skb)
+{
+	if (hw->desc->get_rx_vlan_valid(rx_desc)) {
+		u16 vid = hw->desc->get_rx_vlan_tci(rx_desc);
+
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid);
+	}
+}
+
+static void dwmac4_set_hw_vlan_mode(struct mac_device_info *hw)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value = readl(ioaddr + GMAC_VLAN_TAG);
+
+	value &= ~GMAC_VLAN_TAG_CTRL_EVLS_MASK;
+
+	if (hw->hw_vlan_en)
+		/* Always strip VLAN on Receive */
+		value |= GMAC_VLAN_TAG_STRIP_ALL;
+	else
+		/* Do not strip VLAN on Receive */
+		value |= GMAC_VLAN_TAG_STRIP_NONE;
+
+	/* Enable outer VLAN Tag in Rx DMA descriptor */
+	value |= GMAC_VLAN_TAG_CTRL_EVLRXS;
+	writel(value, ioaddr + GMAC_VLAN_TAG);
+}
+
 const struct stmmac_ops dwmac4_ops = {
 	.core_init = dwmac4_core_init,
 	.phylink_get_caps = dwmac4_phylink_get_caps,
@@ -1175,6 +1204,8 @@ const struct stmmac_ops dwmac4_ops = {
 	.add_hw_vlan_rx_fltr = dwmac4_add_hw_vlan_rx_fltr,
 	.del_hw_vlan_rx_fltr = dwmac4_del_hw_vlan_rx_fltr,
 	.restore_hw_vlan_rx_fltr = dwmac4_restore_hw_vlan_rx_fltr,
+	.rx_hw_vlan = dwmac4_rx_hw_vlan,
+	.set_hw_vlan_mode = dwmac4_set_hw_vlan_mode,
 };
 
 const struct stmmac_ops dwmac410_ops = {
@@ -1216,14 +1247,14 @@ const struct stmmac_ops dwmac410_ops = {
 	.set_arp_offload = dwmac4_set_arp_offload,
 	.config_l3_filter = dwmac4_config_l3_filter,
 	.config_l4_filter = dwmac4_config_l4_filter,
-	.est_configure = dwmac5_est_configure,
-	.est_irq_status = dwmac5_est_irq_status,
 	.fpe_configure = dwmac5_fpe_configure,
 	.fpe_send_mpacket = dwmac5_fpe_send_mpacket,
 	.fpe_irq_status = dwmac5_fpe_irq_status,
 	.add_hw_vlan_rx_fltr = dwmac4_add_hw_vlan_rx_fltr,
 	.del_hw_vlan_rx_fltr = dwmac4_del_hw_vlan_rx_fltr,
 	.restore_hw_vlan_rx_fltr = dwmac4_restore_hw_vlan_rx_fltr,
+	.rx_hw_vlan = dwmac4_rx_hw_vlan,
+	.set_hw_vlan_mode = dwmac4_set_hw_vlan_mode,
 };
 
 const struct stmmac_ops dwmac510_ops = {
@@ -1269,14 +1300,14 @@ const struct stmmac_ops dwmac510_ops = {
 	.set_arp_offload = dwmac4_set_arp_offload,
 	.config_l3_filter = dwmac4_config_l3_filter,
 	.config_l4_filter = dwmac4_config_l4_filter,
-	.est_configure = dwmac5_est_configure,
-	.est_irq_status = dwmac5_est_irq_status,
 	.fpe_configure = dwmac5_fpe_configure,
 	.fpe_send_mpacket = dwmac5_fpe_send_mpacket,
 	.fpe_irq_status = dwmac5_fpe_irq_status,
 	.add_hw_vlan_rx_fltr = dwmac4_add_hw_vlan_rx_fltr,
 	.del_hw_vlan_rx_fltr = dwmac4_del_hw_vlan_rx_fltr,
 	.restore_hw_vlan_rx_fltr = dwmac4_restore_hw_vlan_rx_fltr,
+	.rx_hw_vlan = dwmac4_rx_hw_vlan,
+	.set_hw_vlan_mode = dwmac4_set_hw_vlan_mode,
 };
 
 static u32 dwmac4_get_num_vlan(void __iomem *ioaddr)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index 89a14084c611..1c5802e0d7f4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -198,6 +198,17 @@ static int dwmac4_get_tx_ls(struct dma_desc *p)
 		>> TDES3_LAST_DESCRIPTOR_SHIFT;
 }
 
+static u16 dwmac4_wrback_get_rx_vlan_tci(struct dma_desc *p)
+{
+	return (le32_to_cpu(p->des0) & RDES0_VLAN_TAG_MASK);
+}
+
+static bool dwmac4_wrback_get_rx_vlan_valid(struct dma_desc *p)
+{
+	return ((le32_to_cpu(p->des3) & RDES3_LAST_DESCRIPTOR) &&
+		(le32_to_cpu(p->des3) & RDES3_RDES0_VALID));
+}
+
 static int dwmac4_wrback_get_rx_frame_len(struct dma_desc *p, int rx_coe)
 {
 	return (le32_to_cpu(p->des3) & RDES3_PACKET_SIZE_MASK);
@@ -551,6 +562,8 @@ const struct stmmac_desc_ops dwmac4_desc_ops = {
 	.set_tx_owner = dwmac4_set_tx_owner,
 	.set_rx_owner = dwmac4_set_rx_owner,
 	.get_tx_ls = dwmac4_get_tx_ls,
+	.get_rx_vlan_tci = dwmac4_wrback_get_rx_vlan_tci,
+	.get_rx_vlan_valid = dwmac4_wrback_get_rx_vlan_valid,
 	.get_rx_frame_len = dwmac4_wrback_get_rx_frame_len,
 	.enable_tx_timestamp = dwmac4_rd_enable_tx_timestamp,
 	.get_tx_timestamp_status = dwmac4_wrback_get_tx_timestamp_status,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
index e95d35f1e5a0..e02cebc3f1b7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
@@ -573,165 +573,22 @@ int dwmac5_flex_pps_config(void __iomem *ioaddr, int index,
 	return 0;
 }
 
-static int dwmac5_est_write(void __iomem *ioaddr, u32 reg, u32 val, bool gcl)
-{
-	u32 ctrl;
-
-	writel(val, ioaddr + MTL_EST_GCL_DATA);
-
-	ctrl = (reg << ADDR_SHIFT);
-	ctrl |= gcl ? 0 : GCRR;
-
-	writel(ctrl, ioaddr + MTL_EST_GCL_CONTROL);
-
-	ctrl |= SRWO;
-	writel(ctrl, ioaddr + MTL_EST_GCL_CONTROL);
-
-	return readl_poll_timeout(ioaddr + MTL_EST_GCL_CONTROL,
-				  ctrl, !(ctrl & SRWO), 100, 5000);
-}
-
-int dwmac5_est_configure(void __iomem *ioaddr, struct stmmac_est *cfg,
-			 unsigned int ptp_rate)
-{
-	int i, ret = 0x0;
-	u32 ctrl;
-
-	ret |= dwmac5_est_write(ioaddr, BTR_LOW, cfg->btr[0], false);
-	ret |= dwmac5_est_write(ioaddr, BTR_HIGH, cfg->btr[1], false);
-	ret |= dwmac5_est_write(ioaddr, TER, cfg->ter, false);
-	ret |= dwmac5_est_write(ioaddr, LLR, cfg->gcl_size, false);
-	ret |= dwmac5_est_write(ioaddr, CTR_LOW, cfg->ctr[0], false);
-	ret |= dwmac5_est_write(ioaddr, CTR_HIGH, cfg->ctr[1], false);
-	if (ret)
-		return ret;
-
-	for (i = 0; i < cfg->gcl_size; i++) {
-		ret = dwmac5_est_write(ioaddr, i, cfg->gcl[i], true);
-		if (ret)
-			return ret;
-	}
-
-	ctrl = readl(ioaddr + MTL_EST_CONTROL);
-	ctrl &= ~PTOV;
-	ctrl |= ((1000000000 / ptp_rate) * 6) << PTOV_SHIFT;
-	if (cfg->enable)
-		ctrl |= EEST | SSWL;
-	else
-		ctrl &= ~EEST;
-
-	writel(ctrl, ioaddr + MTL_EST_CONTROL);
-
-	/* Configure EST interrupt */
-	if (cfg->enable)
-		ctrl = (IECGCE | IEHS | IEHF | IEBE | IECC);
-	else
-		ctrl = 0;
-
-	writel(ctrl, ioaddr + MTL_EST_INT_EN);
-
-	return 0;
-}
-
-void dwmac5_est_irq_status(void __iomem *ioaddr, struct net_device *dev,
-			  struct stmmac_extra_stats *x, u32 txqcnt)
-{
-	u32 status, value, feqn, hbfq, hbfs, btrl;
-	u32 txqcnt_mask = (1 << txqcnt) - 1;
-
-	status = readl(ioaddr + MTL_EST_STATUS);
-
-	value = (CGCE | HLBS | HLBF | BTRE | SWLC);
-
-	/* Return if there is no error */
-	if (!(status & value))
-		return;
-
-	if (status & CGCE) {
-		/* Clear Interrupt */
-		writel(CGCE, ioaddr + MTL_EST_STATUS);
-
-		x->mtl_est_cgce++;
-	}
-
-	if (status & HLBS) {
-		value = readl(ioaddr + MTL_EST_SCH_ERR);
-		value &= txqcnt_mask;
-
-		x->mtl_est_hlbs++;
-
-		/* Clear Interrupt */
-		writel(value, ioaddr + MTL_EST_SCH_ERR);
-
-		/* Collecting info to shows all the queues that has HLBS
-		 * issue. The only way to clear this is to clear the
-		 * statistic
-		 */
-		if (net_ratelimit())
-			netdev_err(dev, "EST: HLB(sched) Queue 0x%x\n", value);
-	}
-
-	if (status & HLBF) {
-		value = readl(ioaddr + MTL_EST_FRM_SZ_ERR);
-		feqn = value & txqcnt_mask;
-
-		value = readl(ioaddr + MTL_EST_FRM_SZ_CAP);
-		hbfq = (value & SZ_CAP_HBFQ_MASK(txqcnt)) >> SZ_CAP_HBFQ_SHIFT;
-		hbfs = value & SZ_CAP_HBFS_MASK;
-
-		x->mtl_est_hlbf++;
-
-		/* Clear Interrupt */
-		writel(feqn, ioaddr + MTL_EST_FRM_SZ_ERR);
-
-		if (net_ratelimit())
-			netdev_err(dev, "EST: HLB(size) Queue %u Size %u\n",
-				   hbfq, hbfs);
-	}
-
-	if (status & BTRE) {
-		if ((status & BTRL) == BTRL_MAX)
-			x->mtl_est_btrlm++;
-		else
-			x->mtl_est_btre++;
-
-		btrl = (status & BTRL) >> BTRL_SHIFT;
-
-		if (net_ratelimit())
-			netdev_info(dev, "EST: BTR Error Loop Count %u\n",
-				    btrl);
-
-		writel(BTRE, ioaddr + MTL_EST_STATUS);
-	}
-
-	if (status & SWLC) {
-		writel(SWLC, ioaddr + MTL_EST_STATUS);
-		netdev_info(dev, "EST: SWOL has been switched\n");
-	}
-}
-
-void dwmac5_fpe_configure(void __iomem *ioaddr, u32 num_txq, u32 num_rxq,
+void dwmac5_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg,
+			  u32 num_txq, u32 num_rxq,
 			  bool enable)
 {
 	u32 value;
 
-	if (!enable) {
-		value = readl(ioaddr + MAC_FPE_CTRL_STS);
-
-		value &= ~EFPE;
-
-		writel(value, ioaddr + MAC_FPE_CTRL_STS);
-		return;
+	if (enable) {
+		cfg->fpe_csr = EFPE;
+		value = readl(ioaddr + GMAC_RXQ_CTRL1);
+		value &= ~GMAC_RXQCTRL_FPRQ;
+		value |= (num_rxq - 1) << GMAC_RXQCTRL_FPRQ_SHIFT;
+		writel(value, ioaddr + GMAC_RXQ_CTRL1);
+	} else {
+		cfg->fpe_csr = 0;
 	}
-
-	value = readl(ioaddr + GMAC_RXQ_CTRL1);
-	value &= ~GMAC_RXQCTRL_FPRQ;
-	value |= (num_rxq - 1) << GMAC_RXQCTRL_FPRQ_SHIFT;
-	writel(value, ioaddr + GMAC_RXQ_CTRL1);
-
-	value = readl(ioaddr + MAC_FPE_CTRL_STS);
-	value |= EFPE;
-	writel(value, ioaddr + MAC_FPE_CTRL_STS);
+	writel(cfg->fpe_csr, ioaddr + MAC_FPE_CTRL_STS);
 }
 
 int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev)
@@ -741,6 +598,9 @@ int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev)
 
 	status = FPE_EVENT_UNKNOWN;
 
+	/* Reads from the MAC_FPE_CTRL_STS register should only be performed
+	 * here, since the status flags of MAC_FPE_CTRL_STS are "clear on read"
+	 */
 	value = readl(ioaddr + MAC_FPE_CTRL_STS);
 
 	if (value & TRSP) {
@@ -766,19 +626,15 @@ int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev)
 	return status;
 }
 
-void dwmac5_fpe_send_mpacket(void __iomem *ioaddr, enum stmmac_mpacket_type type)
+void dwmac5_fpe_send_mpacket(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg,
+			     enum stmmac_mpacket_type type)
 {
-	u32 value;
+	u32 value = cfg->fpe_csr;
 
-	value = readl(ioaddr + MAC_FPE_CTRL_STS);
-
-	if (type == MPACKET_VERIFY) {
-		value &= ~SRSP;
+	if (type == MPACKET_VERIFY)
 		value |= SVER;
-	} else {
-		value &= ~SVER;
+	else if (type == MPACKET_RESPONSE)
 		value |= SRSP;
-	}
 
 	writel(value, ioaddr + MAC_FPE_CTRL_STS);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
index 53c138d0ff48..bf33a51d229e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
@@ -39,53 +39,6 @@
 #define MAC_PPSx_INTERVAL(x)		(0x00000b88 + ((x) * 0x10))
 #define MAC_PPSx_WIDTH(x)		(0x00000b8c + ((x) * 0x10))
 
-#define MTL_EST_CONTROL			0x00000c50
-#define PTOV				GENMASK(31, 24)
-#define PTOV_SHIFT			24
-#define SSWL				BIT(1)
-#define EEST				BIT(0)
-
-#define MTL_EST_STATUS			0x00000c58
-#define BTRL				GENMASK(11, 8)
-#define BTRL_SHIFT			8
-#define BTRL_MAX			(0xF << BTRL_SHIFT)
-#define SWOL				BIT(7)
-#define SWOL_SHIFT			7
-#define CGCE				BIT(4)
-#define HLBS				BIT(3)
-#define HLBF				BIT(2)
-#define BTRE				BIT(1)
-#define SWLC				BIT(0)
-
-#define MTL_EST_SCH_ERR			0x00000c60
-#define MTL_EST_FRM_SZ_ERR		0x00000c64
-#define MTL_EST_FRM_SZ_CAP		0x00000c68
-#define SZ_CAP_HBFS_MASK		GENMASK(14, 0)
-#define SZ_CAP_HBFQ_SHIFT		16
-#define SZ_CAP_HBFQ_MASK(_val)		({ typeof(_val) (val) = (_val);	\
-					((val) > 4 ? GENMASK(18, 16) :	\
-					 (val) > 2 ? GENMASK(17, 16) :	\
-					 BIT(16)); })
-
-#define MTL_EST_INT_EN			0x00000c70
-#define IECGCE				CGCE
-#define IEHS				HLBS
-#define IEHF				HLBF
-#define IEBE				BTRE
-#define IECC				SWLC
-
-#define MTL_EST_GCL_CONTROL		0x00000c80
-#define BTR_LOW				0x0
-#define BTR_HIGH			0x1
-#define CTR_LOW				0x2
-#define CTR_HIGH			0x3
-#define TER				0x4
-#define LLR				0x5
-#define ADDR_SHIFT			8
-#define GCRR				BIT(2)
-#define SRWO				BIT(0)
-#define MTL_EST_GCL_DATA		0x00000c84
-
 #define MTL_RXP_CONTROL_STATUS		0x00000ca0
 #define RXPI				BIT(31)
 #define NPE				GENMASK(23, 16)
@@ -149,13 +102,11 @@ int dwmac5_rxp_config(void __iomem *ioaddr, struct stmmac_tc_entry *entries,
 int dwmac5_flex_pps_config(void __iomem *ioaddr, int index,
 			   struct stmmac_pps_cfg *cfg, bool enable,
 			   u32 sub_second_inc, u32 systime_flags);
-int dwmac5_est_configure(void __iomem *ioaddr, struct stmmac_est *cfg,
-			 unsigned int ptp_rate);
-void dwmac5_est_irq_status(void __iomem *ioaddr, struct net_device *dev,
-			   struct stmmac_extra_stats *x, u32 txqcnt);
-void dwmac5_fpe_configure(void __iomem *ioaddr, u32 num_txq, u32 num_rxq,
+void dwmac5_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg,
+			  u32 num_txq, u32 num_rxq,
 			  bool enable);
 void dwmac5_fpe_send_mpacket(void __iomem *ioaddr,
+			     struct stmmac_fpe_cfg *cfg,
 			     enum stmmac_mpacket_type type);
 int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index a4e8b498dea9..207ff1799f2c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -284,22 +284,6 @@
 #define XGMAC_TC_PRTY_MAP1		0x00001044
 #define XGMAC_PSTC(x)			GENMASK((x) * 8 + 7, (x) * 8)
 #define XGMAC_PSTC_SHIFT(x)		((x) * 8)
-#define XGMAC_MTL_EST_CONTROL		0x00001050
-#define XGMAC_PTOV			GENMASK(31, 23)
-#define XGMAC_PTOV_SHIFT		23
-#define XGMAC_SSWL			BIT(1)
-#define XGMAC_EEST			BIT(0)
-#define XGMAC_MTL_EST_GCL_CONTROL	0x00001080
-#define XGMAC_BTR_LOW			0x0
-#define XGMAC_BTR_HIGH			0x1
-#define XGMAC_CTR_LOW			0x2
-#define XGMAC_CTR_HIGH			0x3
-#define XGMAC_TER			0x4
-#define XGMAC_LLR			0x5
-#define XGMAC_ADDR_SHIFT		8
-#define XGMAC_GCRR			BIT(2)
-#define XGMAC_SRWO			BIT(0)
-#define XGMAC_MTL_EST_GCL_DATA		0x00001084
 #define XGMAC_MTL_RXP_CONTROL_STATUS	0x000010a0
 #define XGMAC_RXPI			BIT(31)
 #define XGMAC_NPE			GENMASK(23, 16)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 453e88b75be0..eb48211d9b0e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -1433,58 +1433,8 @@ static void dwxgmac2_set_arp_offload(struct mac_device_info *hw, bool en,
 	writel(value, ioaddr + XGMAC_RX_CONFIG);
 }
 
-static int dwxgmac3_est_write(void __iomem *ioaddr, u32 reg, u32 val, bool gcl)
-{
-	u32 ctrl;
-
-	writel(val, ioaddr + XGMAC_MTL_EST_GCL_DATA);
-
-	ctrl = (reg << XGMAC_ADDR_SHIFT);
-	ctrl |= gcl ? 0 : XGMAC_GCRR;
-
-	writel(ctrl, ioaddr + XGMAC_MTL_EST_GCL_CONTROL);
-
-	ctrl |= XGMAC_SRWO;
-	writel(ctrl, ioaddr + XGMAC_MTL_EST_GCL_CONTROL);
-
-	return readl_poll_timeout_atomic(ioaddr + XGMAC_MTL_EST_GCL_CONTROL,
-					 ctrl, !(ctrl & XGMAC_SRWO), 100, 5000);
-}
-
-static int dwxgmac3_est_configure(void __iomem *ioaddr, struct stmmac_est *cfg,
-				  unsigned int ptp_rate)
-{
-	int i, ret = 0x0;
-	u32 ctrl;
-
-	ret |= dwxgmac3_est_write(ioaddr, XGMAC_BTR_LOW, cfg->btr[0], false);
-	ret |= dwxgmac3_est_write(ioaddr, XGMAC_BTR_HIGH, cfg->btr[1], false);
-	ret |= dwxgmac3_est_write(ioaddr, XGMAC_TER, cfg->ter, false);
-	ret |= dwxgmac3_est_write(ioaddr, XGMAC_LLR, cfg->gcl_size, false);
-	ret |= dwxgmac3_est_write(ioaddr, XGMAC_CTR_LOW, cfg->ctr[0], false);
-	ret |= dwxgmac3_est_write(ioaddr, XGMAC_CTR_HIGH, cfg->ctr[1], false);
-	if (ret)
-		return ret;
-
-	for (i = 0; i < cfg->gcl_size; i++) {
-		ret = dwxgmac3_est_write(ioaddr, i, cfg->gcl[i], true);
-		if (ret)
-			return ret;
-	}
-
-	ctrl = readl(ioaddr + XGMAC_MTL_EST_CONTROL);
-	ctrl &= ~XGMAC_PTOV;
-	ctrl |= ((1000000000 / ptp_rate) * 9) << XGMAC_PTOV_SHIFT;
-	if (cfg->enable)
-		ctrl |= XGMAC_EEST | XGMAC_SSWL;
-	else
-		ctrl &= ~XGMAC_EEST;
-
-	writel(ctrl, ioaddr + XGMAC_MTL_EST_CONTROL);
-	return 0;
-}
-
-static void dwxgmac3_fpe_configure(void __iomem *ioaddr, u32 num_txq,
+static void dwxgmac3_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg,
+				   u32 num_txq,
 				   u32 num_rxq, bool enable)
 {
 	u32 value;
@@ -1552,7 +1502,6 @@ const struct stmmac_ops dwxgmac210_ops = {
 	.config_l3_filter = dwxgmac2_config_l3_filter,
 	.config_l4_filter = dwxgmac2_config_l4_filter,
 	.set_arp_offload = dwxgmac2_set_arp_offload,
-	.est_configure = dwxgmac3_est_configure,
 	.fpe_configure = dwxgmac3_fpe_configure,
 };
 
@@ -1614,7 +1563,6 @@ const struct stmmac_ops dwxlgmac2_ops = {
 	.config_l3_filter = dwxgmac2_config_l3_filter,
 	.config_l4_filter = dwxgmac2_config_l4_filter,
 	.set_arp_offload = dwxgmac2_set_arp_offload,
-	.est_configure = dwxgmac3_est_configure,
 	.fpe_configure = dwxgmac3_fpe_configure,
 };
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c
index b8ba8f2d8041..1bd34b2a47e8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.c
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c
@@ -7,6 +7,7 @@
 #include "common.h"
 #include "stmmac.h"
 #include "stmmac_ptp.h"
+#include "stmmac_est.h"
 
 static u32 stmmac_get_id(struct stmmac_priv *priv, u32 id_reg)
 {
@@ -114,6 +115,7 @@ static const struct stmmac_hwif_entry {
 	const void *mode;
 	const void *tc;
 	const void *mmc;
+	const void *est;
 	int (*setup)(struct stmmac_priv *priv);
 	int (*quirks)(struct stmmac_priv *priv);
 } stmmac_hw[] = {
@@ -162,6 +164,7 @@ static const struct stmmac_hwif_entry {
 		.regs = {
 			.ptp_off = PTP_GMAC4_OFFSET,
 			.mmc_off = MMC_GMAC4_OFFSET,
+			.est_off = EST_GMAC4_OFFSET,
 		},
 		.desc = &dwmac4_desc_ops,
 		.dma = &dwmac4_dma_ops,
@@ -170,6 +173,7 @@ static const struct stmmac_hwif_entry {
 		.mode = NULL,
 		.tc = &dwmac510_tc_ops,
 		.mmc = &dwmac_mmc_ops,
+		.est = &dwmac510_est_ops,
 		.setup = dwmac4_setup,
 		.quirks = stmmac_dwmac4_quirks,
 	}, {
@@ -180,6 +184,7 @@ static const struct stmmac_hwif_entry {
 		.regs = {
 			.ptp_off = PTP_GMAC4_OFFSET,
 			.mmc_off = MMC_GMAC4_OFFSET,
+			.est_off = EST_GMAC4_OFFSET,
 		},
 		.desc = &dwmac4_desc_ops,
 		.dma = &dwmac4_dma_ops,
@@ -188,6 +193,7 @@ static const struct stmmac_hwif_entry {
 		.mode = &dwmac4_ring_mode_ops,
 		.tc = &dwmac510_tc_ops,
 		.mmc = &dwmac_mmc_ops,
+		.est = &dwmac510_est_ops,
 		.setup = dwmac4_setup,
 		.quirks = NULL,
 	}, {
@@ -198,6 +204,7 @@ static const struct stmmac_hwif_entry {
 		.regs = {
 			.ptp_off = PTP_GMAC4_OFFSET,
 			.mmc_off = MMC_GMAC4_OFFSET,
+			.est_off = EST_GMAC4_OFFSET,
 		},
 		.desc = &dwmac4_desc_ops,
 		.dma = &dwmac410_dma_ops,
@@ -206,6 +213,7 @@ static const struct stmmac_hwif_entry {
 		.mode = &dwmac4_ring_mode_ops,
 		.tc = &dwmac510_tc_ops,
 		.mmc = &dwmac_mmc_ops,
+		.est = &dwmac510_est_ops,
 		.setup = dwmac4_setup,
 		.quirks = NULL,
 	}, {
@@ -216,6 +224,7 @@ static const struct stmmac_hwif_entry {
 		.regs = {
 			.ptp_off = PTP_GMAC4_OFFSET,
 			.mmc_off = MMC_GMAC4_OFFSET,
+			.est_off = EST_XGMAC_OFFSET,
 		},
 		.desc = &dwmac4_desc_ops,
 		.dma = &dwmac410_dma_ops,
@@ -224,6 +233,7 @@ static const struct stmmac_hwif_entry {
 		.mode = &dwmac4_ring_mode_ops,
 		.tc = &dwmac510_tc_ops,
 		.mmc = &dwmac_mmc_ops,
+		.est = &dwmac510_est_ops,
 		.setup = dwmac4_setup,
 		.quirks = NULL,
 	}, {
@@ -235,6 +245,7 @@ static const struct stmmac_hwif_entry {
 		.regs = {
 			.ptp_off = PTP_XGMAC_OFFSET,
 			.mmc_off = MMC_XGMAC_OFFSET,
+			.est_off = EST_XGMAC_OFFSET,
 		},
 		.desc = &dwxgmac210_desc_ops,
 		.dma = &dwxgmac210_dma_ops,
@@ -243,6 +254,7 @@ static const struct stmmac_hwif_entry {
 		.mode = NULL,
 		.tc = &dwmac510_tc_ops,
 		.mmc = &dwxgmac_mmc_ops,
+		.est = &dwmac510_est_ops,
 		.setup = dwxgmac2_setup,
 		.quirks = NULL,
 	}, {
@@ -254,6 +266,7 @@ static const struct stmmac_hwif_entry {
 		.regs = {
 			.ptp_off = PTP_XGMAC_OFFSET,
 			.mmc_off = MMC_XGMAC_OFFSET,
+			.est_off = EST_XGMAC_OFFSET,
 		},
 		.desc = &dwxgmac210_desc_ops,
 		.dma = &dwxgmac210_dma_ops,
@@ -262,6 +275,7 @@ static const struct stmmac_hwif_entry {
 		.mode = NULL,
 		.tc = &dwmac510_tc_ops,
 		.mmc = &dwxgmac_mmc_ops,
+		.est = &dwmac510_est_ops,
 		.setup = dwxlgmac2_setup,
 		.quirks = stmmac_dwxlgmac_quirks,
 	},
@@ -296,6 +310,10 @@ int stmmac_hwif_init(struct stmmac_priv *priv)
 		(needs_gmac4 ? PTP_GMAC4_OFFSET : PTP_GMAC3_X_OFFSET);
 	priv->mmcaddr = priv->ioaddr +
 		(needs_gmac4 ? MMC_GMAC4_OFFSET : MMC_GMAC3_X_OFFSET);
+	if (needs_gmac4)
+		priv->estaddr = priv->ioaddr + EST_GMAC4_OFFSET;
+	else if (needs_xgmac)
+		priv->estaddr = priv->ioaddr + EST_XGMAC_OFFSET;
 
 	/* Check for HW specific setup first */
 	if (priv->plat->setup) {
@@ -332,10 +350,13 @@ int stmmac_hwif_init(struct stmmac_priv *priv)
 		mac->mode = mac->mode ? : entry->mode;
 		mac->tc = mac->tc ? : entry->tc;
 		mac->mmc = mac->mmc ? : entry->mmc;
+		mac->est = mac->est ? : entry->est;
 
 		priv->hw = mac;
 		priv->ptpaddr = priv->ioaddr + entry->regs.ptp_off;
 		priv->mmcaddr = priv->ioaddr + entry->regs.mmc_off;
+		if (entry->est)
+			priv->estaddr = priv->ioaddr + entry->regs.est_off;
 
 		/* Entry found */
 		if (needs_setup) {
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index b95d3e137813..7be04b54738b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -56,6 +56,10 @@ struct stmmac_desc_ops {
 	void (*set_tx_ic)(struct dma_desc *p);
 	/* Last tx segment reports the transmit status */
 	int (*get_tx_ls)(struct dma_desc *p);
+	/* Get the tag of the descriptor */
+	u16 (*get_rx_vlan_tci)(struct dma_desc *p);
+	/* Get the valid status of descriptor */
+	bool (*get_rx_vlan_valid)(struct dma_desc *p);
 	/* Return the transmit status looking at the TDES1 */
 	int (*tx_status)(struct stmmac_extra_stats *x,
 			 struct dma_desc *p, void __iomem *ioaddr);
@@ -117,6 +121,10 @@ struct stmmac_desc_ops {
 	stmmac_do_void_callback(__priv, desc, set_tx_ic, __args)
 #define stmmac_get_tx_ls(__priv, __args...) \
 	stmmac_do_callback(__priv, desc, get_tx_ls, __args)
+#define stmmac_get_rx_vlan_tci(__priv, __args...) \
+	stmmac_do_callback(__priv, desc, get_rx_vlan_tci, __args)
+#define stmmac_get_rx_vlan_valid(__priv, __args...) \
+	stmmac_do_callback(__priv, desc, get_rx_vlan_valid, __args)
 #define stmmac_tx_status(__priv, __args...) \
 	stmmac_do_callback(__priv, desc, tx_status, __args)
 #define stmmac_get_tx_len(__priv, __args...) \
@@ -388,6 +396,9 @@ struct stmmac_ops {
 	void (*update_vlan_hash)(struct mac_device_info *hw, u32 hash,
 				 __le16 perfect_match, bool is_double);
 	void (*enable_vlan)(struct mac_device_info *hw, u32 type);
+	void (*rx_hw_vlan)(struct mac_device_info *hw, struct dma_desc *rx_desc,
+			   struct sk_buff *skb);
+	void (*set_hw_vlan_mode)(struct mac_device_info *hw);
 	int (*add_hw_vlan_rx_fltr)(struct net_device *dev,
 				   struct mac_device_info *hw,
 				   __be16 proto, u16 vid);
@@ -408,13 +419,11 @@ struct stmmac_ops {
 				bool en, bool udp, bool sa, bool inv,
 				u32 match);
 	void (*set_arp_offload)(struct mac_device_info *hw, bool en, u32 addr);
-	int (*est_configure)(void __iomem *ioaddr, struct stmmac_est *cfg,
-			     unsigned int ptp_rate);
-	void (*est_irq_status)(void __iomem *ioaddr, struct net_device *dev,
-			       struct stmmac_extra_stats *x, u32 txqcnt);
-	void (*fpe_configure)(void __iomem *ioaddr, u32 num_txq, u32 num_rxq,
+	void (*fpe_configure)(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg,
+			      u32 num_txq, u32 num_rxq,
 			      bool enable);
 	void (*fpe_send_mpacket)(void __iomem *ioaddr,
+				 struct stmmac_fpe_cfg *cfg,
 				 enum stmmac_mpacket_type type);
 	int (*fpe_irq_status)(void __iomem *ioaddr, struct net_device *dev);
 };
@@ -497,6 +506,10 @@ struct stmmac_ops {
 	stmmac_do_void_callback(__priv, mac, update_vlan_hash, __args)
 #define stmmac_enable_vlan(__priv, __args...) \
 	stmmac_do_void_callback(__priv, mac, enable_vlan, __args)
+#define stmmac_rx_hw_vlan(__priv, __args...) \
+	stmmac_do_void_callback(__priv, mac, rx_hw_vlan, __args)
+#define stmmac_set_hw_vlan_mode(__priv, __args...) \
+	stmmac_do_void_callback(__priv, mac, set_hw_vlan_mode, __args)
 #define stmmac_add_hw_vlan_rx_fltr(__priv, __args...) \
 	stmmac_do_callback(__priv, mac, add_hw_vlan_rx_fltr, __args)
 #define stmmac_del_hw_vlan_rx_fltr(__priv, __args...) \
@@ -513,10 +526,6 @@ struct stmmac_ops {
 	stmmac_do_callback(__priv, mac, config_l4_filter, __args)
 #define stmmac_set_arp_offload(__priv, __args...) \
 	stmmac_do_void_callback(__priv, mac, set_arp_offload, __args)
-#define stmmac_est_configure(__priv, __args...) \
-	stmmac_do_callback(__priv, mac, est_configure, __args)
-#define stmmac_est_irq_status(__priv, __args...) \
-	stmmac_do_void_callback(__priv, mac, est_irq_status, __args)
 #define stmmac_fpe_configure(__priv, __args...) \
 	stmmac_do_void_callback(__priv, mac, fpe_configure, __args)
 #define stmmac_fpe_send_mpacket(__priv, __args...) \
@@ -642,9 +651,22 @@ struct stmmac_mmc_ops {
 #define stmmac_mmc_read(__priv, __args...) \
 	stmmac_do_void_callback(__priv, mmc, read, __args)
 
+struct stmmac_est_ops {
+	int (*configure)(struct stmmac_priv *priv, struct stmmac_est *cfg,
+			 unsigned int ptp_rate);
+	void (*irq_status)(struct stmmac_priv *priv, struct net_device *dev,
+			   struct stmmac_extra_stats *x, u32 txqcnt);
+};
+
+#define stmmac_est_configure(__priv, __args...) \
+	stmmac_do_callback(__priv, est, configure, __args)
+#define stmmac_est_irq_status(__priv, __args...) \
+	stmmac_do_void_callback(__priv, est, irq_status, __args)
+
 struct stmmac_regs_off {
 	u32 ptp_off;
 	u32 mmc_off;
+	u32 est_off;
 };
 
 extern const struct stmmac_ops dwmac100_ops;
@@ -663,6 +685,7 @@ extern const struct stmmac_dma_ops dwxgmac210_dma_ops;
 extern const struct stmmac_desc_ops dwxgmac210_desc_ops;
 extern const struct stmmac_mmc_ops dwmac_mmc_ops;
 extern const struct stmmac_mmc_ops dwxgmac_mmc_ops;
+extern const struct stmmac_est_ops dwmac510_est_ops;
 
 #define GMAC_VERSION		0x00000020	/* GMAC CORE Version */
 #define GMAC4_VERSION		0x00000110	/* GMAC4+ CORE Version */
diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc.h b/drivers/net/ethernet/stmicro/stmmac/mmc.h
index a0c05925883e..14c9d2637dfe 100644
--- a/drivers/net/ethernet/stmicro/stmmac/mmc.h
+++ b/drivers/net/ethernet/stmicro/stmmac/mmc.h
@@ -52,6 +52,8 @@ struct stmmac_counters {
 	unsigned int mmc_tx_excessdef;
 	unsigned int mmc_tx_pause_frame;
 	unsigned int mmc_tx_vlan_frame_g;
+	unsigned int mmc_tx_lpi_usec;
+	unsigned int mmc_tx_lpi_tran;
 
 	/* MMC RX counter registers */
 	unsigned int mmc_rx_framecount_gb;
@@ -78,9 +80,16 @@ struct stmmac_counters {
 	unsigned int mmc_rx_fifo_overflow;
 	unsigned int mmc_rx_vlan_frames_gb;
 	unsigned int mmc_rx_watchdog_error;
+	unsigned int mmc_rx_lpi_usec;
+	unsigned int mmc_rx_lpi_tran;
+	unsigned int mmc_rx_discard_frames_gb;
+	unsigned int mmc_rx_discard_octets_gb;
+	unsigned int mmc_rx_align_err_frames;
+
 	/* IPC */
 	unsigned int mmc_rx_ipc_intr_mask;
 	unsigned int mmc_rx_ipc_intr;
+
 	/* IPv4 */
 	unsigned int mmc_rx_ipv4_gd;
 	unsigned int mmc_rx_ipv4_hderr;
@@ -118,9 +127,14 @@ struct stmmac_counters {
 	unsigned int mmc_rx_icmp_gd_octets;
 	unsigned int mmc_rx_icmp_err_octets;
 
+	/* Stream-Gate Filter */
+	unsigned int mmc_sgf_pass_fragment_cntr;
+	unsigned int mmc_sgf_fail_fragment_cntr;
+
 	/* FPE */
 	unsigned int mmc_tx_fpe_fragment_cntr;
 	unsigned int mmc_tx_hold_req_cntr;
+	unsigned int mmc_tx_gate_overrun_cntr;
 	unsigned int mmc_rx_packet_assembly_err_cntr;
 	unsigned int mmc_rx_packet_smd_err_cntr;
 	unsigned int mmc_rx_packet_assembly_ok_cntr;
diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
index ea4910ae0921..8597c6abae8d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
@@ -177,14 +177,53 @@
 #define MMC_XGMAC_RX_DISCARD_OCT_GB	0x1b4
 #define MMC_XGMAC_RX_ALIGN_ERR_PKT	0x1bc
 
+#define MMC_XGMAC_SGF_PASS_PKT		0x1f0
+#define MMC_XGMAC_SGF_FAIL_PKT		0x1f4
+#define MMC_XGMAC_TX_FPE_INTR_MASK	0x204
 #define MMC_XGMAC_TX_FPE_FRAG		0x208
 #define MMC_XGMAC_TX_HOLD_REQ		0x20c
+#define MMC_XGMAC_TX_GATE_OVERRUN	0x210
+#define MMC_XGMAC_RX_FPE_INTR_MASK	0x224
 #define MMC_XGMAC_RX_PKT_ASSEMBLY_ERR	0x228
 #define MMC_XGMAC_RX_PKT_SMD_ERR	0x22c
 #define MMC_XGMAC_RX_PKT_ASSEMBLY_OK	0x230
 #define MMC_XGMAC_RX_FPE_FRAG		0x234
 #define MMC_XGMAC_RX_IPC_INTR_MASK	0x25c
 
+#define MMC_XGMAC_RX_IPV4_GD		0x264
+#define MMC_XGMAC_RX_IPV4_HDERR		0x26c
+#define MMC_XGMAC_RX_IPV4_NOPAY		0x274
+#define MMC_XGMAC_RX_IPV4_FRAG		0x27c
+#define MMC_XGMAC_RX_IPV4_UDSBL		0x284
+
+#define MMC_XGMAC_RX_IPV6_GD		0x28c
+#define MMC_XGMAC_RX_IPV6_HDERR		0x294
+#define MMC_XGMAC_RX_IPV6_NOPAY		0x29c
+
+#define MMC_XGMAC_RX_UDP_GD		0x2a4
+#define MMC_XGMAC_RX_UDP_ERR		0x2ac
+#define MMC_XGMAC_RX_TCP_GD		0x2b4
+#define MMC_XGMAC_RX_TCP_ERR		0x2bc
+#define MMC_XGMAC_RX_ICMP_GD		0x2c4
+#define MMC_XGMAC_RX_ICMP_ERR		0x2cc
+
+#define MMC_XGMAC_RX_IPV4_GD_OCTETS	0x2d4
+#define MMC_XGMAC_RX_IPV4_HDERR_OCTETS	0x2dc
+#define MMC_XGMAC_RX_IPV4_NOPAY_OCTETS	0x2e4
+#define MMC_XGMAC_RX_IPV4_FRAG_OCTETS	0x2ec
+#define MMC_XGMAC_RX_IPV4_UDSBL_OCTETS	0x2f4
+
+#define MMC_XGMAC_RX_IPV6_GD_OCTETS	0x2fc
+#define MMC_XGMAC_RX_IPV6_HDERR_OCTETS	0x304
+#define MMC_XGMAC_RX_IPV6_NOPAY_OCTETS	0x30c
+
+#define MMC_XGMAC_RX_UDP_GD_OCTETS	0x314
+#define MMC_XGMAC_RX_UDP_ERR_OCTETS	0x31c
+#define MMC_XGMAC_RX_TCP_GD_OCTETS	0x324
+#define MMC_XGMAC_RX_TCP_ERR_OCTETS	0x32c
+#define MMC_XGMAC_RX_ICMP_GD_OCTETS	0x334
+#define MMC_XGMAC_RX_ICMP_ERR_OCTETS	0x33c
+
 static void dwmac_mmc_ctrl(void __iomem *mmcaddr, unsigned int mode)
 {
 	u32 value = readl(mmcaddr + MMC_CNTRL);
@@ -352,6 +391,8 @@ static void dwxgmac_mmc_intr_all_mask(void __iomem *mmcaddr)
 {
 	writel(0x0, mmcaddr + MMC_RX_INTR_MASK);
 	writel(0x0, mmcaddr + MMC_TX_INTR_MASK);
+	writel(MMC_DEFAULT_MASK, mmcaddr + MMC_XGMAC_TX_FPE_INTR_MASK);
+	writel(MMC_DEFAULT_MASK, mmcaddr + MMC_XGMAC_RX_FPE_INTR_MASK);
 	writel(MMC_DEFAULT_MASK, mmcaddr + MMC_XGMAC_RX_IPC_INTR_MASK);
 }
 
@@ -410,6 +451,8 @@ static void dwxgmac_mmc_read(void __iomem *mmcaddr, struct stmmac_counters *mmc)
 			     &mmc->mmc_tx_pause_frame);
 	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_VLAN_PKT_G,
 			     &mmc->mmc_tx_vlan_frame_g);
+	mmc->mmc_tx_lpi_usec += readl(mmcaddr + MMC_XGMAC_TX_LPI_USEC);
+	mmc->mmc_tx_lpi_tran += readl(mmcaddr + MMC_XGMAC_TX_LPI_TRAN);
 
 	/* MMC RX counter registers */
 	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_PKT_GB,
@@ -455,9 +498,23 @@ static void dwxgmac_mmc_read(void __iomem *mmcaddr, struct stmmac_counters *mmc)
 	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_VLAN_PKT_GB,
 			     &mmc->mmc_rx_vlan_frames_gb);
 	mmc->mmc_rx_watchdog_error += readl(mmcaddr + MMC_XGMAC_RX_WATCHDOG_ERR);
-
+	mmc->mmc_rx_lpi_usec += readl(mmcaddr + MMC_XGMAC_RX_LPI_USEC);
+	mmc->mmc_rx_lpi_tran += readl(mmcaddr + MMC_XGMAC_RX_LPI_TRAN);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_DISCARD_PKT_GB,
+			     &mmc->mmc_rx_discard_frames_gb);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_DISCARD_OCT_GB,
+			     &mmc->mmc_rx_discard_octets_gb);
+	mmc->mmc_rx_align_err_frames +=
+		readl(mmcaddr + MMC_XGMAC_RX_ALIGN_ERR_PKT);
+
+	mmc->mmc_sgf_pass_fragment_cntr +=
+		readl(mmcaddr + MMC_XGMAC_SGF_PASS_PKT);
+	mmc->mmc_sgf_fail_fragment_cntr +=
+		readl(mmcaddr + MMC_XGMAC_SGF_FAIL_PKT);
 	mmc->mmc_tx_fpe_fragment_cntr += readl(mmcaddr + MMC_XGMAC_TX_FPE_FRAG);
 	mmc->mmc_tx_hold_req_cntr += readl(mmcaddr + MMC_XGMAC_TX_HOLD_REQ);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_GATE_OVERRUN,
+			     &mmc->mmc_tx_gate_overrun_cntr);
 	mmc->mmc_rx_packet_assembly_err_cntr +=
 		readl(mmcaddr + MMC_XGMAC_RX_PKT_ASSEMBLY_ERR);
 	mmc->mmc_rx_packet_smd_err_cntr +=
@@ -466,6 +523,68 @@ static void dwxgmac_mmc_read(void __iomem *mmcaddr, struct stmmac_counters *mmc)
 		readl(mmcaddr + MMC_XGMAC_RX_PKT_ASSEMBLY_OK);
 	mmc->mmc_rx_fpe_fragment_cntr +=
 		readl(mmcaddr + MMC_XGMAC_RX_FPE_FRAG);
+
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_IPV4_GD,
+			     &mmc->mmc_rx_ipv4_gd);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_IPV4_HDERR,
+			     &mmc->mmc_rx_ipv4_hderr);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_IPV4_NOPAY,
+			     &mmc->mmc_rx_ipv4_nopay);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_IPV4_FRAG,
+			     &mmc->mmc_rx_ipv4_frag);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_IPV4_UDSBL,
+			     &mmc->mmc_rx_ipv4_udsbl);
+
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_IPV6_GD,
+			     &mmc->mmc_rx_ipv6_gd);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_IPV6_HDERR,
+			     &mmc->mmc_rx_ipv6_hderr);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_IPV6_NOPAY,
+			     &mmc->mmc_rx_ipv6_nopay);
+
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_UDP_GD,
+			     &mmc->mmc_rx_udp_gd);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_UDP_ERR,
+			     &mmc->mmc_rx_udp_err);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_TCP_GD,
+			     &mmc->mmc_rx_tcp_gd);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_TCP_ERR,
+			     &mmc->mmc_rx_tcp_err);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_ICMP_GD,
+			     &mmc->mmc_rx_icmp_gd);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_ICMP_ERR,
+			     &mmc->mmc_rx_icmp_err);
+
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_IPV4_GD_OCTETS,
+			     &mmc->mmc_rx_ipv4_gd_octets);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_IPV4_HDERR_OCTETS,
+			     &mmc->mmc_rx_ipv4_hderr_octets);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_IPV4_NOPAY_OCTETS,
+			     &mmc->mmc_rx_ipv4_nopay_octets);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_IPV4_FRAG_OCTETS,
+			     &mmc->mmc_rx_ipv4_frag_octets);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_IPV4_UDSBL_OCTETS,
+			     &mmc->mmc_rx_ipv4_udsbl_octets);
+
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_IPV6_GD_OCTETS,
+			     &mmc->mmc_rx_ipv6_gd_octets);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_IPV6_HDERR_OCTETS,
+			     &mmc->mmc_rx_ipv6_hderr_octets);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_IPV6_NOPAY_OCTETS,
+			     &mmc->mmc_rx_ipv6_nopay_octets);
+
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_UDP_GD_OCTETS,
+			     &mmc->mmc_rx_udp_gd_octets);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_UDP_ERR_OCTETS,
+			     &mmc->mmc_rx_udp_err_octets);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_TCP_GD_OCTETS,
+			     &mmc->mmc_rx_tcp_gd_octets);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_TCP_ERR_OCTETS,
+			     &mmc->mmc_rx_tcp_err_octets);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_ICMP_GD_OCTETS,
+			     &mmc->mmc_rx_icmp_gd_octets);
+	dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_ICMP_ERR_OCTETS,
+			     &mmc->mmc_rx_icmp_err_octets);
 }
 
 const struct stmmac_mmc_ops dwxgmac_mmc_ops = {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index cd7a9768de5f..9f89acf31050 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -51,6 +51,7 @@ struct stmmac_tx_info {
 	bool last_segment;
 	bool is_jumbo;
 	enum stmmac_txbuf_type buf_type;
+	struct xsk_tx_metadata_compl xsk_meta;
 };
 
 #define STMMAC_TBS_AVAIL	BIT(0)
@@ -100,6 +101,17 @@ struct stmmac_xdp_buff {
 	struct dma_desc *ndesc;
 };
 
+struct stmmac_metadata_request {
+	struct stmmac_priv *priv;
+	struct dma_desc *tx_desc;
+	bool *set_ic;
+};
+
+struct stmmac_xsk_tx_complete {
+	struct stmmac_priv *priv;
+	struct dma_desc *desc;
+};
+
 struct stmmac_rx_queue {
 	u32 rx_count_frames;
 	u32 queue_index;
@@ -283,6 +295,7 @@ struct stmmac_priv {
 
 	void __iomem *mmcaddr;
 	void __iomem *ptpaddr;
+	void __iomem *estaddr;
 	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
 	int sfty_ce_irq;
 	int sfty_ue_irq;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c
new file mode 100644
index 000000000000..4da6ccc17c20
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023, Intel Corporation
+ * stmmac EST(802.3 Qbv) handling
+ */
+#include <linux/iopoll.h>
+#include <linux/types.h>
+#include "stmmac.h"
+#include "stmmac_est.h"
+
+static int est_write(void __iomem *est_addr, u32 reg, u32 val, bool gcl)
+{
+	u32 ctrl;
+
+	writel(val, est_addr + EST_GCL_DATA);
+
+	ctrl = (reg << EST_ADDR_SHIFT);
+	ctrl |= gcl ? 0 : EST_GCRR;
+	writel(ctrl, est_addr + EST_GCL_CONTROL);
+
+	ctrl |= EST_SRWO;
+	writel(ctrl, est_addr + EST_GCL_CONTROL);
+
+	return readl_poll_timeout(est_addr + EST_GCL_CONTROL, ctrl,
+				  !(ctrl & EST_SRWO), 100, 5000);
+}
+
+static int est_configure(struct stmmac_priv *priv, struct stmmac_est *cfg,
+			 unsigned int ptp_rate)
+{
+	void __iomem *est_addr = priv->estaddr;
+	int i, ret = 0;
+	u32 ctrl;
+
+	ret |= est_write(est_addr, EST_BTR_LOW, cfg->btr[0], false);
+	ret |= est_write(est_addr, EST_BTR_HIGH, cfg->btr[1], false);
+	ret |= est_write(est_addr, EST_TER, cfg->ter, false);
+	ret |= est_write(est_addr, EST_LLR, cfg->gcl_size, false);
+	ret |= est_write(est_addr, EST_CTR_LOW, cfg->ctr[0], false);
+	ret |= est_write(est_addr, EST_CTR_HIGH, cfg->ctr[1], false);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < cfg->gcl_size; i++) {
+		ret = est_write(est_addr, i, cfg->gcl[i], true);
+		if (ret)
+			return ret;
+	}
+
+	ctrl = readl(est_addr + EST_CONTROL);
+	if (priv->plat->has_xgmac) {
+		ctrl &= ~EST_XGMAC_PTOV;
+		ctrl |= ((NSEC_PER_SEC / ptp_rate) * EST_XGMAC_PTOV_MUL) <<
+			 EST_XGMAC_PTOV_SHIFT;
+	} else {
+		ctrl &= ~EST_GMAC5_PTOV;
+		ctrl |= ((NSEC_PER_SEC / ptp_rate) * EST_GMAC5_PTOV_MUL) <<
+			 EST_GMAC5_PTOV_SHIFT;
+	}
+	if (cfg->enable)
+		ctrl |= EST_EEST | EST_SSWL;
+	else
+		ctrl &= ~EST_EEST;
+
+	writel(ctrl, est_addr + EST_CONTROL);
+
+	/* Configure EST interrupt */
+	if (cfg->enable)
+		ctrl = EST_IECGCE | EST_IEHS | EST_IEHF | EST_IEBE | EST_IECC;
+	else
+		ctrl = 0;
+
+	writel(ctrl, est_addr + EST_INT_EN);
+
+	return 0;
+}
+
+static void est_irq_status(struct stmmac_priv *priv, struct net_device *dev,
+			   struct stmmac_extra_stats *x, u32 txqcnt)
+{
+	u32 status, value, feqn, hbfq, hbfs, btrl, btrl_max;
+	void __iomem *est_addr = priv->estaddr;
+	u32 txqcnt_mask = BIT(txqcnt) - 1;
+
+	status = readl(est_addr + EST_STATUS);
+
+	value = EST_CGCE | EST_HLBS | EST_HLBF | EST_BTRE | EST_SWLC;
+
+	/* Return if there is no error */
+	if (!(status & value))
+		return;
+
+	if (status & EST_CGCE) {
+		/* Clear Interrupt */
+		writel(EST_CGCE, est_addr + EST_STATUS);
+
+		x->mtl_est_cgce++;
+	}
+
+	if (status & EST_HLBS) {
+		value = readl(est_addr + EST_SCH_ERR);
+		value &= txqcnt_mask;
+
+		x->mtl_est_hlbs++;
+
+		/* Clear Interrupt */
+		writel(value, est_addr + EST_SCH_ERR);
+
+		/* Collecting info to shows all the queues that has HLBS
+		 * issue. The only way to clear this is to clear the
+		 * statistic
+		 */
+		if (net_ratelimit())
+			netdev_err(dev, "EST: HLB(sched) Queue 0x%x\n", value);
+	}
+
+	if (status & EST_HLBF) {
+		value = readl(est_addr + EST_FRM_SZ_ERR);
+		feqn = value & txqcnt_mask;
+
+		value = readl(est_addr + EST_FRM_SZ_CAP);
+		hbfq = (value & EST_SZ_CAP_HBFQ_MASK(txqcnt)) >>
+			EST_SZ_CAP_HBFQ_SHIFT;
+		hbfs = value & EST_SZ_CAP_HBFS_MASK;
+
+		x->mtl_est_hlbf++;
+
+		/* Clear Interrupt */
+		writel(feqn, est_addr + EST_FRM_SZ_ERR);
+
+		if (net_ratelimit())
+			netdev_err(dev, "EST: HLB(size) Queue %u Size %u\n",
+				   hbfq, hbfs);
+	}
+
+	if (status & EST_BTRE) {
+		if (priv->plat->has_xgmac) {
+			btrl = FIELD_GET(EST_XGMAC_BTRL, status);
+			btrl_max = FIELD_MAX(EST_XGMAC_BTRL);
+		} else {
+			btrl = FIELD_GET(EST_GMAC5_BTRL, status);
+			btrl_max = FIELD_MAX(EST_GMAC5_BTRL);
+		}
+		if (btrl == btrl_max)
+			x->mtl_est_btrlm++;
+		else
+			x->mtl_est_btre++;
+
+		if (net_ratelimit())
+			netdev_info(dev, "EST: BTR Error Loop Count %u\n",
+				    btrl);
+
+		writel(EST_BTRE, est_addr + EST_STATUS);
+	}
+
+	if (status & EST_SWLC) {
+		writel(EST_SWLC, est_addr + EST_STATUS);
+		netdev_info(dev, "EST: SWOL has been switched\n");
+	}
+}
+
+const struct stmmac_est_ops dwmac510_est_ops = {
+	.configure = est_configure,
+	.irq_status = est_irq_status,
+};
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_est.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_est.h
new file mode 100644
index 000000000000..7a858c566e7e
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_est.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023, Intel Corporation
+ * stmmac EST(802.3 Qbv) handling
+ */
+
+#define EST_GMAC4_OFFSET		0x00000c50
+#define EST_XGMAC_OFFSET		0x00001050
+
+#define EST_CONTROL			0x00000000
+#define EST_GMAC5_PTOV			GENMASK(31, 24)
+#define EST_GMAC5_PTOV_SHIFT		24
+#define EST_GMAC5_PTOV_MUL		6
+#define EST_XGMAC_PTOV			GENMASK(31, 23)
+#define EST_XGMAC_PTOV_SHIFT		23
+#define EST_XGMAC_PTOV_MUL		9
+#define EST_SSWL			BIT(1)
+#define EST_EEST			BIT(0)
+
+#define EST_STATUS			0x00000008
+#define EST_GMAC5_BTRL			GENMASK(11, 8)
+#define EST_XGMAC_BTRL			GENMASK(15, 8)
+#define EST_SWOL			BIT(7)
+#define EST_SWOL_SHIFT			7
+#define EST_CGCE			BIT(4)
+#define EST_HLBS			BIT(3)
+#define EST_HLBF			BIT(2)
+#define EST_BTRE			BIT(1)
+#define EST_SWLC			BIT(0)
+
+#define EST_SCH_ERR			0x00000010
+
+#define EST_FRM_SZ_ERR			0x00000014
+
+#define EST_FRM_SZ_CAP			0x00000018
+#define EST_SZ_CAP_HBFS_MASK		GENMASK(14, 0)
+#define EST_SZ_CAP_HBFQ_SHIFT		16
+#define EST_SZ_CAP_HBFQ_MASK(val)		\
+	({					\
+		typeof(val) _val = (val);	\
+		(_val > 4 ? GENMASK(18, 16) :	\
+		 _val > 2 ? GENMASK(17, 16) :	\
+		 BIT(16));			\
+	})
+
+#define EST_INT_EN			0x00000020
+#define EST_IECGCE			EST_CGCE
+#define EST_IEHS			EST_HLBS
+#define EST_IEHF			EST_HLBF
+#define EST_IEBE			EST_BTRE
+#define EST_IECC			EST_SWLC
+
+#define EST_GCL_CONTROL			0x00000030
+#define EST_BTR_LOW			0x0
+#define EST_BTR_HIGH			0x1
+#define EST_CTR_LOW			0x2
+#define EST_CTR_HIGH			0x3
+#define EST_TER				0x4
+#define EST_LLR				0x5
+#define EST_ADDR_SHIFT			8
+#define EST_GCRR			BIT(2)
+#define EST_SRWO			BIT(0)
+
+#define EST_GCL_DATA			0x00000034
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index f628411ae4ae..dd05437b51f9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -212,6 +212,8 @@ static const struct stmmac_stats stmmac_mmc[] = {
 	STMMAC_MMC_STAT(mmc_tx_excessdef),
 	STMMAC_MMC_STAT(mmc_tx_pause_frame),
 	STMMAC_MMC_STAT(mmc_tx_vlan_frame_g),
+	STMMAC_MMC_STAT(mmc_tx_lpi_usec),
+	STMMAC_MMC_STAT(mmc_tx_lpi_tran),
 	STMMAC_MMC_STAT(mmc_rx_framecount_gb),
 	STMMAC_MMC_STAT(mmc_rx_octetcount_gb),
 	STMMAC_MMC_STAT(mmc_rx_octetcount_g),
@@ -236,6 +238,11 @@ static const struct stmmac_stats stmmac_mmc[] = {
 	STMMAC_MMC_STAT(mmc_rx_fifo_overflow),
 	STMMAC_MMC_STAT(mmc_rx_vlan_frames_gb),
 	STMMAC_MMC_STAT(mmc_rx_watchdog_error),
+	STMMAC_MMC_STAT(mmc_rx_lpi_usec),
+	STMMAC_MMC_STAT(mmc_rx_lpi_tran),
+	STMMAC_MMC_STAT(mmc_rx_discard_frames_gb),
+	STMMAC_MMC_STAT(mmc_rx_discard_octets_gb),
+	STMMAC_MMC_STAT(mmc_rx_align_err_frames),
 	STMMAC_MMC_STAT(mmc_rx_ipc_intr_mask),
 	STMMAC_MMC_STAT(mmc_rx_ipc_intr),
 	STMMAC_MMC_STAT(mmc_rx_ipv4_gd),
@@ -266,8 +273,11 @@ static const struct stmmac_stats stmmac_mmc[] = {
 	STMMAC_MMC_STAT(mmc_rx_tcp_err_octets),
 	STMMAC_MMC_STAT(mmc_rx_icmp_gd_octets),
 	STMMAC_MMC_STAT(mmc_rx_icmp_err_octets),
+	STMMAC_MMC_STAT(mmc_sgf_pass_fragment_cntr),
+	STMMAC_MMC_STAT(mmc_sgf_fail_fragment_cntr),
 	STMMAC_MMC_STAT(mmc_tx_fpe_fragment_cntr),
 	STMMAC_MMC_STAT(mmc_tx_hold_req_cntr),
+	STMMAC_MMC_STAT(mmc_tx_gate_overrun_cntr),
 	STMMAC_MMC_STAT(mmc_rx_packet_assembly_err_cntr),
 	STMMAC_MMC_STAT(mmc_rx_packet_smd_err_cntr),
 	STMMAC_MMC_STAT(mmc_rx_packet_assembly_ok_cntr),
@@ -543,15 +553,12 @@ static void stmmac_get_per_qstats(struct stmmac_priv *priv, u64 *data)
 	u32 rx_cnt = priv->plat->rx_queues_to_use;
 	unsigned int start;
 	int q, stat;
-	u64 *pos;
 	char *p;
 
-	pos = data;
 	for (q = 0; q < tx_cnt; q++) {
 		struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[q];
 		struct stmmac_txq_stats snapshot;
 
-		data = pos;
 		do {
 			start = u64_stats_fetch_begin(&txq_stats->syncp);
 			snapshot = *txq_stats;
@@ -559,17 +566,15 @@ static void stmmac_get_per_qstats(struct stmmac_priv *priv, u64 *data)
 
 		p = (char *)&snapshot + offsetof(struct stmmac_txq_stats, tx_pkt_n);
 		for (stat = 0; stat < STMMAC_TXQ_STATS; stat++) {
-			*data++ += (*(u64 *)p);
+			*data++ = (*(u64 *)p);
 			p += sizeof(u64);
 		}
 	}
 
-	pos = data;
 	for (q = 0; q < rx_cnt; q++) {
 		struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[q];
 		struct stmmac_rxq_stats snapshot;
 
-		data = pos;
 		do {
 			start = u64_stats_fetch_begin(&rxq_stats->syncp);
 			snapshot = *rxq_stats;
@@ -577,7 +582,7 @@ static void stmmac_get_per_qstats(struct stmmac_priv *priv, u64 *data)
 
 		p = (char *)&snapshot + offsetof(struct stmmac_rxq_stats, rx_pkt_n);
 		for (stat = 0; stat < STMMAC_RXQ_STATS; stat++) {
-			*data++ += (*(u64 *)p);
+			*data++ = (*(u64 *)p);
 			p += sizeof(u64);
 		}
 	}
@@ -1077,41 +1082,42 @@ static u32 stmmac_get_rxfh_indir_size(struct net_device *dev)
 	return ARRAY_SIZE(priv->rss.table);
 }
 
-static int stmmac_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
-			   u8 *hfunc)
+static int stmmac_get_rxfh(struct net_device *dev,
+			   struct ethtool_rxfh_param *rxfh)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 	int i;
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < ARRAY_SIZE(priv->rss.table); i++)
-			indir[i] = priv->rss.table[i];
+			rxfh->indir[i] = priv->rss.table[i];
 	}
 
-	if (key)
-		memcpy(key, priv->rss.key, sizeof(priv->rss.key));
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	if (rxfh->key)
+		memcpy(rxfh->key, priv->rss.key, sizeof(priv->rss.key));
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	return 0;
 }
 
-static int stmmac_set_rxfh(struct net_device *dev, const u32 *indir,
-			   const u8 *key, const u8 hfunc)
+static int stmmac_set_rxfh(struct net_device *dev,
+			   struct ethtool_rxfh_param *rxfh,
+			   struct netlink_ext_ack *extack)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 	int i;
 
-	if ((hfunc != ETH_RSS_HASH_NO_CHANGE) && (hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < ARRAY_SIZE(priv->rss.table); i++)
-			priv->rss.table[i] = indir[i];
+			priv->rss.table[i] = rxfh->indir[i];
 	}
 
-	if (key)
-		memcpy(priv->rss.key, key, sizeof(priv->rss.key));
+	if (rxfh->key)
+		memcpy(priv->rss.key, rxfh->key, sizeof(priv->rss.key));
 
 	return stmmac_rss_configure(priv, priv->hw, &priv->rss,
 				    priv->plat->rx_queues_to_use);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
index 540f6a4ec0b8..f05bd757dfe5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
@@ -237,7 +237,7 @@ static void timestamp_interrupt(struct stmmac_priv *priv)
 	 */
 	ts_status = readl(priv->ioaddr + GMAC_TIMESTAMP_STATUS);
 
-	if (priv->plat->flags & STMMAC_FLAG_EXT_SNAPSHOT_EN)
+	if (!(priv->plat->flags & STMMAC_FLAG_EXT_SNAPSHOT_EN))
 		return;
 
 	num_snapshot = (ts_status & GMAC_TIMESTAMP_ATSNS_MASK) >>
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 3e50fd53a617..47de466e432c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -964,7 +964,8 @@ static void stmmac_fpe_link_state_handle(struct stmmac_priv *priv, bool is_up)
 	bool *hs_enable = &fpe_cfg->hs_enable;
 
 	if (is_up && *hs_enable) {
-		stmmac_fpe_send_mpacket(priv, priv->ioaddr, MPACKET_VERIFY);
+		stmmac_fpe_send_mpacket(priv, priv->ioaddr, fpe_cfg,
+					MPACKET_VERIFY);
 	} else {
 		*lo_state = FPE_STATE_OFF;
 		*lp_state = FPE_STATE_OFF;
@@ -2430,6 +2431,46 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
 	}
 }
 
+static void stmmac_xsk_request_timestamp(void *_priv)
+{
+	struct stmmac_metadata_request *meta_req = _priv;
+
+	stmmac_enable_tx_timestamp(meta_req->priv, meta_req->tx_desc);
+	*meta_req->set_ic = true;
+}
+
+static u64 stmmac_xsk_fill_timestamp(void *_priv)
+{
+	struct stmmac_xsk_tx_complete *tx_compl = _priv;
+	struct stmmac_priv *priv = tx_compl->priv;
+	struct dma_desc *desc = tx_compl->desc;
+	bool found = false;
+	u64 ns = 0;
+
+	if (!priv->hwts_tx_en)
+		return 0;
+
+	/* check tx tstamp status */
+	if (stmmac_get_tx_timestamp_status(priv, desc)) {
+		stmmac_get_timestamp(priv, desc, priv->adv_ts, &ns);
+		found = true;
+	} else if (!stmmac_get_mac_tx_timestamp(priv, priv->hw, &ns)) {
+		found = true;
+	}
+
+	if (found) {
+		ns -= priv->plat->cdc_error_adj;
+		return ns_to_ktime(ns);
+	}
+
+	return 0;
+}
+
+static const struct xsk_tx_metadata_ops stmmac_xsk_tx_metadata_ops = {
+	.tmo_request_timestamp		= stmmac_xsk_request_timestamp,
+	.tmo_fill_timestamp		= stmmac_xsk_fill_timestamp,
+};
+
 static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 {
 	struct netdev_queue *nq = netdev_get_tx_queue(priv->dev, queue);
@@ -2449,6 +2490,8 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 	budget = min(budget, stmmac_tx_avail(priv, queue));
 
 	while (budget-- > 0) {
+		struct stmmac_metadata_request meta_req;
+		struct xsk_tx_metadata *meta = NULL;
 		dma_addr_t dma_addr;
 		bool set_ic;
 
@@ -2472,6 +2515,7 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 			tx_desc = tx_q->dma_tx + entry;
 
 		dma_addr = xsk_buff_raw_get_dma(pool, xdp_desc.addr);
+		meta = xsk_buff_get_metadata(pool, xdp_desc.addr);
 		xsk_buff_raw_dma_sync_for_device(pool, dma_addr, xdp_desc.len);
 
 		tx_q->tx_skbuff_dma[entry].buf_type = STMMAC_TXBUF_T_XSK_TX;
@@ -2499,6 +2543,11 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 		else
 			set_ic = false;
 
+		meta_req.priv = priv;
+		meta_req.tx_desc = tx_desc;
+		meta_req.set_ic = &set_ic;
+		xsk_tx_metadata_request(meta, &stmmac_xsk_tx_metadata_ops,
+					&meta_req);
 		if (set_ic) {
 			tx_q->tx_count_frames = 0;
 			stmmac_set_tx_ic(priv, tx_desc);
@@ -2511,6 +2560,9 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 
 		stmmac_enable_dma_transmission(priv, priv->ioaddr);
 
+		xsk_tx_metadata_to_compl(meta,
+					 &tx_q->tx_skbuff_dma[entry].xsk_meta);
+
 		tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, priv->dma_conf.dma_tx_size);
 		entry = tx_q->cur_tx;
 	}
@@ -2620,8 +2672,18 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue,
 			} else {
 				tx_packets++;
 			}
-			if (skb)
+			if (skb) {
 				stmmac_get_tx_hwtstamp(priv, p, skb);
+			} else {
+				struct stmmac_xsk_tx_complete tx_compl = {
+					.priv = priv,
+					.desc = p,
+				};
+
+				xsk_tx_metadata_complete(&tx_q->tx_skbuff_dma[entry].xsk_meta,
+							 &stmmac_xsk_tx_metadata_ops,
+							 &tx_compl);
+			}
 		}
 
 		if (likely(tx_q->tx_skbuff_dma[entry].buf &&
@@ -3469,6 +3531,8 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register)
 	/* Start the ball rolling... */
 	stmmac_start_all_dma(priv);
 
+	stmmac_set_hw_vlan_mode(priv, priv->hw);
+
 	if (priv->dma_cap.fpesel) {
 		stmmac_fpe_start_wq(priv);
 
@@ -4993,7 +5057,12 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue,
 	}
 
 	stmmac_get_rx_hwtstamp(priv, p, np, skb);
-	stmmac_rx_vlan(priv->dev, skb);
+	if (priv->hw->hw_vlan_en)
+		/* MAC level stripping. */
+		stmmac_rx_hw_vlan(priv, priv->hw, p, skb);
+	else
+		/* Driver level stripping. */
+		stmmac_rx_vlan(priv->dev, skb);
 	skb->protocol = eth_type_trans(skb, priv->dev);
 
 	if (unlikely(!coe))
@@ -5293,6 +5362,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 
 	dma_dir = page_pool_get_dma_dir(rx_q->page_pool);
 	buf_sz = DIV_ROUND_UP(priv->dma_conf.dma_buf_sz, PAGE_SIZE) * PAGE_SIZE;
+	limit = min(priv->dma_conf.dma_rx_size - 1, (unsigned int)limit);
 
 	if (netif_msg_rx_status(priv)) {
 		void *rx_head;
@@ -5328,10 +5398,10 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			len = 0;
 		}
 
+read_again:
 		if (count >= limit)
 			break;
 
-read_again:
 		buf1_len = 0;
 		buf2_len = 0;
 		entry = next_entry;
@@ -5508,7 +5578,14 @@ drain_data:
 		/* Got entire packet into SKB. Finish it. */
 
 		stmmac_get_rx_hwtstamp(priv, p, np, skb);
-		stmmac_rx_vlan(priv->dev, skb);
+
+		if (priv->hw->hw_vlan_en)
+			/* MAC level stripping. */
+			stmmac_rx_hw_vlan(priv, priv->hw, p, skb);
+		else
+			/* Driver level stripping. */
+			stmmac_rx_vlan(priv->dev, skb);
+
 		skb->protocol = eth_type_trans(skb, priv->dev);
 
 		if (unlikely(!coe))
@@ -5817,6 +5894,13 @@ static int stmmac_set_features(struct net_device *netdev,
 			stmmac_enable_sph(priv, priv->ioaddr, sph_en, chan);
 	}
 
+	if (features & NETIF_F_HW_VLAN_CTAG_RX)
+		priv->hw->hw_vlan_en = true;
+	else
+		priv->hw->hw_vlan_en = false;
+
+	stmmac_set_hw_vlan_mode(priv, priv->hw);
+
 	return 0;
 }
 
@@ -5838,6 +5922,7 @@ static void stmmac_fpe_event_status(struct stmmac_priv *priv, int status)
 		/* If user has requested FPE enable, quickly response */
 		if (*hs_enable)
 			stmmac_fpe_send_mpacket(priv, priv->ioaddr,
+						fpe_cfg,
 						MPACKET_RESPONSE);
 	}
 
@@ -5877,7 +5962,7 @@ static void stmmac_common_interrupt(struct stmmac_priv *priv)
 		pm_wakeup_event(priv->device, 0);
 
 	if (priv->dma_cap.estsel)
-		stmmac_est_irq_status(priv, priv->ioaddr, priv->dev,
+		stmmac_est_irq_status(priv, priv, priv->dev,
 				      &priv->xstats, tx_cnt);
 
 	if (priv->dma_cap.fpesel) {
@@ -6179,30 +6264,23 @@ static struct dentry *stmmac_fs_dir;
 static void sysfs_display_ring(void *head, int size, int extend_desc,
 			       struct seq_file *seq, dma_addr_t dma_phy_addr)
 {
-	int i;
 	struct dma_extended_desc *ep = (struct dma_extended_desc *)head;
 	struct dma_desc *p = (struct dma_desc *)head;
+	unsigned int desc_size;
 	dma_addr_t dma_addr;
+	int i;
 
+	desc_size = extend_desc ? sizeof(*ep) : sizeof(*p);
 	for (i = 0; i < size; i++) {
-		if (extend_desc) {
-			dma_addr = dma_phy_addr + i * sizeof(*ep);
-			seq_printf(seq, "%d [%pad]: 0x%x 0x%x 0x%x 0x%x\n",
-				   i, &dma_addr,
-				   le32_to_cpu(ep->basic.des0),
-				   le32_to_cpu(ep->basic.des1),
-				   le32_to_cpu(ep->basic.des2),
-				   le32_to_cpu(ep->basic.des3));
-			ep++;
-		} else {
-			dma_addr = dma_phy_addr + i * sizeof(*p);
-			seq_printf(seq, "%d [%pad]: 0x%x 0x%x 0x%x 0x%x\n",
-				   i, &dma_addr,
-				   le32_to_cpu(p->des0), le32_to_cpu(p->des1),
-				   le32_to_cpu(p->des2), le32_to_cpu(p->des3));
+		dma_addr = dma_phy_addr + i * desc_size;
+		seq_printf(seq, "%d [%pad]: 0x%x 0x%x 0x%x 0x%x\n",
+				i, &dma_addr,
+				le32_to_cpu(p->des0), le32_to_cpu(p->des1),
+				le32_to_cpu(p->des2), le32_to_cpu(p->des3));
+		if (extend_desc)
+			p = &(++ep)->basic;
+		else
 			p++;
-		}
-		seq_printf(seq, "\n");
 	}
 }
 
@@ -7262,6 +7340,7 @@ static void stmmac_fpe_lp_task(struct work_struct *work)
 		if (*lo_state == FPE_STATE_ENTERING_ON &&
 		    *lp_state == FPE_STATE_ENTERING_ON) {
 			stmmac_fpe_configure(priv, priv->ioaddr,
+					     fpe_cfg,
 					     priv->plat->tx_queues_to_use,
 					     priv->plat->rx_queues_to_use,
 					     *enable);
@@ -7280,6 +7359,7 @@ static void stmmac_fpe_lp_task(struct work_struct *work)
 			netdev_info(priv->dev, SEND_VERIFY_MPAKCET_FMT,
 				    *lo_state, *lp_state);
 			stmmac_fpe_send_mpacket(priv, priv->ioaddr,
+						fpe_cfg,
 						MPACKET_VERIFY);
 		}
 		/* Sleep then retry */
@@ -7294,6 +7374,7 @@ void stmmac_fpe_handshake(struct stmmac_priv *priv, bool enable)
 	if (priv->plat->fpe_cfg->hs_enable != enable) {
 		if (enable) {
 			stmmac_fpe_send_mpacket(priv, priv->ioaddr,
+						priv->plat->fpe_cfg,
 						MPACKET_VERIFY);
 		} else {
 			priv->plat->fpe_cfg->lo_fpe_state = FPE_STATE_OFF;
@@ -7449,6 +7530,7 @@ int stmmac_dvr_probe(struct device *device,
 	ndev->netdev_ops = &stmmac_netdev_ops;
 
 	ndev->xdp_metadata_ops = &stmmac_xdp_metadata_ops;
+	ndev->xsk_tx_metadata_ops = &stmmac_xsk_tx_metadata_ops;
 
 	ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 			    NETIF_F_RXCSUM;
@@ -7515,6 +7597,9 @@ int stmmac_dvr_probe(struct device *device,
 #ifdef STMMAC_VLAN_TAG_USED
 	/* Both mac100 and gmac support receive VLAN tag detection */
 	ndev->features |= NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX;
+	ndev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX;
+	priv->hw->hw_vlan_en = true;
+
 	if (priv->dma_cap.vlhash) {
 		ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 		ndev->features |= NETIF_F_HW_VLAN_STAG_FILTER;
@@ -7754,6 +7839,7 @@ int stmmac_suspend(struct device *dev)
 	if (priv->dma_cap.fpesel) {
 		/* Disable FPE */
 		stmmac_fpe_configure(priv, priv->ioaddr,
+				     priv->plat->fpe_cfg,
 				     priv->plat->tx_queues_to_use,
 				     priv->plat->rx_queues_to_use, false);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index fa9e7e7040b9..0542cfd1817e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -591,7 +591,11 @@ int stmmac_mdio_register(struct net_device *ndev)
 	new_bus->parent = priv->device;
 
 	err = of_mdiobus_register(new_bus, mdio_node);
-	if (err != 0) {
+	if (err == -ENODEV) {
+		err = 0;
+		dev_info(dev, "MDIO bus is disabled\n");
+		goto bus_register_fail;
+	} else if (err) {
 		dev_err_probe(dev, err, "Cannot register the MDIO bus\n");
 		goto bus_register_fail;
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 1ffde555da47..70eadc83ca68 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -296,62 +296,80 @@ out:
 }
 
 /**
- * stmmac_dt_phy - parse device-tree driver parameters to allocate PHY resources
- * @plat: driver data platform structure
- * @np: device tree node
- * @dev: device pointer
- * Description:
- * The mdio bus will be allocated in case of a phy transceiver is on board;
- * it will be NULL if the fixed-link is configured.
- * If there is the "snps,dwmac-mdio" sub-node the mdio will be allocated
- * in any case (for DSA, mdio must be registered even if fixed-link).
- * The table below sums the supported configurations:
- *	-------------------------------
- *	snps,phy-addr	|     Y
- *	-------------------------------
- *	phy-handle	|     Y
- *	-------------------------------
- *	fixed-link	|     N
- *	-------------------------------
- *	snps,dwmac-mdio	|
- *	  even if	|     Y
- *	fixed-link	|
- *	-------------------------------
+ * stmmac_of_get_mdio() - Gets the MDIO bus from the devicetree.
+ * @np: devicetree node
  *
- * It returns 0 in case of success otherwise -ENODEV.
+ * The MDIO bus will be searched for in the following ways:
+ * 1. The compatible is "snps,dwc-qos-ethernet-4.10" && a "mdio" named
+ *    child node exists
+ * 2. A child node with the "snps,dwmac-mdio" compatible is present
+ *
+ * Return: The MDIO node if present otherwise NULL
  */
-static int stmmac_dt_phy(struct plat_stmmacenet_data *plat,
-			 struct device_node *np, struct device *dev)
+static struct device_node *stmmac_of_get_mdio(struct device_node *np)
 {
-	bool mdio = !of_phy_is_fixed_link(np);
 	static const struct of_device_id need_mdio_ids[] = {
 		{ .compatible = "snps,dwc-qos-ethernet-4.10" },
 		{},
 	};
+	struct device_node *mdio_node = NULL;
 
 	if (of_match_node(need_mdio_ids, np)) {
-		plat->mdio_node = of_get_child_by_name(np, "mdio");
+		mdio_node = of_get_child_by_name(np, "mdio");
 	} else {
 		/**
 		 * If snps,dwmac-mdio is passed from DT, always register
 		 * the MDIO
 		 */
-		for_each_child_of_node(np, plat->mdio_node) {
-			if (of_device_is_compatible(plat->mdio_node,
+		for_each_child_of_node(np, mdio_node) {
+			if (of_device_is_compatible(mdio_node,
 						    "snps,dwmac-mdio"))
 				break;
 		}
 	}
 
-	if (plat->mdio_node) {
+	return mdio_node;
+}
+
+/**
+ * stmmac_mdio_setup() - Populate platform related MDIO structures.
+ * @plat: driver data platform structure
+ * @np: devicetree node
+ * @dev: device pointer
+ *
+ * This searches for MDIO information from the devicetree.
+ * If an MDIO node is found, it's assigned to plat->mdio_node and
+ * plat->mdio_bus_data is allocated.
+ * If no connection can be determined, just plat->mdio_bus_data is allocated
+ * to indicate a bus should be created and scanned for a phy.
+ * If it's determined there's no MDIO bus needed, both are left NULL.
+ *
+ * This expects that plat->phy_node has already been searched for.
+ *
+ * Return: 0 on success, errno otherwise.
+ */
+static int stmmac_mdio_setup(struct plat_stmmacenet_data *plat,
+			     struct device_node *np, struct device *dev)
+{
+	bool legacy_mdio;
+
+	plat->mdio_node = stmmac_of_get_mdio(np);
+	if (plat->mdio_node)
 		dev_dbg(dev, "Found MDIO subnode\n");
-		mdio = true;
-	}
 
-	if (mdio) {
-		plat->mdio_bus_data =
-			devm_kzalloc(dev, sizeof(struct stmmac_mdio_bus_data),
-				     GFP_KERNEL);
+	/* Legacy devicetrees allowed for no MDIO bus description and expect
+	 * the bus to be scanned for devices. If there's no phy or fixed-link
+	 * described assume this is the case since there must be something
+	 * connected to the MAC.
+	 */
+	legacy_mdio = !of_phy_is_fixed_link(np) && !plat->phy_node;
+	if (legacy_mdio)
+		dev_info(dev, "Deprecated MDIO bus assumption used\n");
+
+	if (plat->mdio_node || legacy_mdio) {
+		plat->mdio_bus_data = devm_kzalloc(dev,
+						   sizeof(*plat->mdio_bus_data),
+						   GFP_KERNEL);
 		if (!plat->mdio_bus_data)
 			return -ENOMEM;
 
@@ -471,8 +489,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 	if (of_property_read_u32(np, "snps,phy-addr", &plat->phy_addr) == 0)
 		dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n");
 
-	/* To Configure PHY by using all device-tree supported properties */
-	rc = stmmac_dt_phy(plat, np, &pdev->dev);
+	rc = stmmac_mdio_setup(plat, np, &pdev->dev);
 	if (rc)
 		return ERR_PTR(rc);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
index bffa5c017032..e04830a3a1fb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
@@ -72,7 +72,7 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta)
 		est_rst = true;
 		mutex_lock(&priv->plat->est->lock);
 		priv->plat->est->enable = false;
-		stmmac_est_configure(priv, priv->ioaddr, priv->plat->est,
+		stmmac_est_configure(priv, priv, priv->plat->est,
 				     priv->plat->clk_ptp_rate);
 		mutex_unlock(&priv->plat->est->lock);
 	}
@@ -102,7 +102,7 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta)
 		priv->plat->est->btr[0] = (u32)time.tv_nsec;
 		priv->plat->est->btr[1] = (u32)time.tv_sec;
 		priv->plat->est->enable = true;
-		ret = stmmac_est_configure(priv, priv->ioaddr, priv->plat->est,
+		ret = stmmac_est_configure(priv, priv, priv->plat->est,
 					   priv->plat->clk_ptp_rate);
 		mutex_unlock(&priv->plat->est->lock);
 		if (ret)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index ac41ef4cbd2f..26fa33e5ec34 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -975,6 +975,8 @@ static int tc_setup_taprio(struct stmmac_priv *priv,
 		return -EINVAL;
 	if (!qopt->cycle_time)
 		return -ERANGE;
+	if (qopt->cycle_time_extension >= BIT(wid + 7))
+		return -ERANGE;
 
 	if (!plat->est) {
 		plat->est = devm_kzalloc(priv->device, sizeof(*plat->est),
@@ -1041,6 +1043,8 @@ static int tc_setup_taprio(struct stmmac_priv *priv,
 	priv->plat->est->ctr[0] = do_div(ctr, NSEC_PER_SEC);
 	priv->plat->est->ctr[1] = (u32)ctr;
 
+	priv->plat->est->ter = qopt->cycle_time_extension;
+
 	if (fpe && !priv->dma_cap.fpesel) {
 		mutex_unlock(&priv->plat->est->lock);
 		return -EOPNOTSUPP;
@@ -1051,7 +1055,7 @@ static int tc_setup_taprio(struct stmmac_priv *priv,
 	 */
 	priv->plat->fpe_cfg->enable = fpe;
 
-	ret = stmmac_est_configure(priv, priv->ioaddr, priv->plat->est,
+	ret = stmmac_est_configure(priv, priv, priv->plat->est,
 				   priv->plat->clk_ptp_rate);
 	mutex_unlock(&priv->plat->est->lock);
 	if (ret) {
@@ -1072,13 +1076,14 @@ disable:
 	if (priv->plat->est) {
 		mutex_lock(&priv->plat->est->lock);
 		priv->plat->est->enable = false;
-		stmmac_est_configure(priv, priv->ioaddr, priv->plat->est,
+		stmmac_est_configure(priv, priv, priv->plat->est,
 				     priv->plat->clk_ptp_rate);
 		mutex_unlock(&priv->plat->est->lock);
 	}
 
 	priv->plat->fpe_cfg->enable = false;
 	stmmac_fpe_configure(priv, priv->ioaddr,
+			     priv->plat->fpe_cfg,
 			     priv->plat->tx_queues_to_use,
 			     priv->plat->rx_queues_to_use,
 			     false);
diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index e60b557d59b9..be01450c20dc 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -134,14 +134,16 @@ config TI_K3_AM65_CPTS
 	  protocol, Ethernet Enhanced Scheduled Traffic Operations (CPTS_ESTFn)
 	  and PCIe Subsystem Precision Time Measurement (PTM).
 
-config TI_AM65_CPSW_TAS
-	bool "Enable TAS offload in AM65 CPSW"
+config TI_AM65_CPSW_QOS
+	bool "Enable QoS offload features in AM65 CPSW"
 	depends on TI_K3_AM65_CPSW_NUSS && NET_SCH_TAPRIO && TI_K3_AM65_CPTS
 	help
-	  Say y here to support Time Aware Shaper(TAS) offload in AM65 CPSW.
-	  AM65 CPSW hardware supports Enhanced Scheduled Traffic (EST)
-	  defined in IEEE 802.1Q 2018. The EST scheduler runs on CPTS and the
-	  TAS/EST schedule is updated in the Fetch RAM memory of the CPSW.
+	  This option enables QoS offload features in AM65 CPSW like
+	  Time Aware Shaper (TAS) / Enhanced Scheduled Traffic (EST),
+	  MQPRIO qdisc offload and Frame-Preemption MAC Merge / Interspersing
+	  Express Traffic (IET).
+	  The EST scheduler runs on CPTS and the TAS/EST schedule is
+	  updated in the Fetch RAM memory of the CPSW.
 
 config TI_KEYSTONE_NETCP
 	tristate "TI Keystone NETCP Core Support"
diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile
index 27de1d697134..d8590304f3df 100644
--- a/drivers/net/ethernet/ti/Makefile
+++ b/drivers/net/ethernet/ti/Makefile
@@ -26,7 +26,8 @@ keystone_netcp_ethss-y := netcp_ethss.o netcp_sgmii.o netcp_xgbepcsr.o cpsw_ale.
 obj-$(CONFIG_TI_K3_CPPI_DESC_POOL) += k3-cppi-desc-pool.o
 
 obj-$(CONFIG_TI_K3_AM65_CPSW_NUSS) += ti-am65-cpsw-nuss.o
-ti-am65-cpsw-nuss-y := am65-cpsw-nuss.o cpsw_sl.o am65-cpsw-ethtool.o cpsw_ale.o am65-cpsw-qos.o
+ti-am65-cpsw-nuss-y := am65-cpsw-nuss.o cpsw_sl.o am65-cpsw-ethtool.o cpsw_ale.o
+ti-am65-cpsw-nuss-$(CONFIG_TI_AM65_CPSW_QOS) += am65-cpsw-qos.o
 ti-am65-cpsw-nuss-$(CONFIG_TI_K3_AM65_CPSW_SWITCHDEV) += am65-cpsw-switchdev.o
 obj-$(CONFIG_TI_K3_AM65_CPTS) += am65-cpts.o
 
diff --git a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c
index c51e2af91f69..35fceba01ea4 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c
@@ -11,6 +11,7 @@
 #include <linux/pm_runtime.h>
 
 #include "am65-cpsw-nuss.h"
+#include "am65-cpsw-qos.h"
 #include "cpsw_ale.h"
 #include "am65-cpts.h"
 
@@ -662,6 +663,34 @@ static void am65_cpsw_get_ethtool_stats(struct net_device *ndev,
 					hw_stats[i].offset);
 }
 
+static void am65_cpsw_get_eth_mac_stats(struct net_device *ndev,
+					struct ethtool_eth_mac_stats *s)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	struct am65_cpsw_stats_regs __iomem *stats;
+
+	stats = port->stat_base;
+
+	if (s->src != ETHTOOL_MAC_STATS_SRC_AGGREGATE)
+		return;
+
+	s->FramesTransmittedOK = readl_relaxed(&stats->tx_good_frames);
+	s->SingleCollisionFrames = readl_relaxed(&stats->tx_single_coll_frames);
+	s->MultipleCollisionFrames = readl_relaxed(&stats->tx_mult_coll_frames);
+	s->FramesReceivedOK = readl_relaxed(&stats->rx_good_frames);
+	s->FrameCheckSequenceErrors = readl_relaxed(&stats->rx_crc_errors);
+	s->AlignmentErrors = readl_relaxed(&stats->rx_align_code_errors);
+	s->OctetsTransmittedOK = readl_relaxed(&stats->tx_octets);
+	s->FramesWithDeferredXmissions = readl_relaxed(&stats->tx_deferred_frames);
+	s->LateCollisions = readl_relaxed(&stats->tx_late_collisions);
+	s->CarrierSenseErrors = readl_relaxed(&stats->tx_carrier_sense_errors);
+	s->OctetsReceivedOK = readl_relaxed(&stats->rx_octets);
+	s->MulticastFramesXmittedOK = readl_relaxed(&stats->tx_multicast_frames);
+	s->BroadcastFramesXmittedOK = readl_relaxed(&stats->tx_broadcast_frames);
+	s->MulticastFramesReceivedOK = readl_relaxed(&stats->rx_multicast_frames);
+	s->BroadcastFramesReceivedOK = readl_relaxed(&stats->rx_broadcast_frames);
+};
+
 static int am65_cpsw_get_ethtool_ts_info(struct net_device *ndev,
 					 struct ethtool_ts_info *info)
 {
@@ -715,6 +744,240 @@ static int am65_cpsw_set_ethtool_priv_flags(struct net_device *ndev, u32 flags)
 	return 0;
 }
 
+static void am65_cpsw_port_iet_rx_enable(struct am65_cpsw_port *port, bool enable)
+{
+	u32 val;
+
+	val = readl(port->port_base + AM65_CPSW_PN_REG_CTL);
+	if (enable)
+		val |= AM65_CPSW_PN_CTL_IET_PORT_EN;
+	else
+		val &= ~AM65_CPSW_PN_CTL_IET_PORT_EN;
+
+	writel(val, port->port_base + AM65_CPSW_PN_REG_CTL);
+	am65_cpsw_iet_common_enable(port->common);
+}
+
+static void am65_cpsw_port_iet_tx_enable(struct am65_cpsw_port *port, bool enable)
+{
+	u32 val;
+
+	val = readl(port->port_base + AM65_CPSW_PN_REG_IET_CTRL);
+	if (enable)
+		val |= AM65_CPSW_PN_IET_MAC_PENABLE;
+	else
+		val &= ~AM65_CPSW_PN_IET_MAC_PENABLE;
+
+	writel(val, port->port_base + AM65_CPSW_PN_REG_IET_CTRL);
+}
+
+static int am65_cpsw_get_mm(struct net_device *ndev, struct ethtool_mm_state *state)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	struct am65_cpsw_ndev_priv *priv = netdev_priv(ndev);
+	u32 port_ctrl, iet_ctrl, iet_status;
+	u32 add_frag_size;
+
+	if (!IS_ENABLED(CONFIG_TI_AM65_CPSW_QOS))
+		return -EOPNOTSUPP;
+
+	mutex_lock(&priv->mm_lock);
+
+	iet_ctrl = readl(port->port_base + AM65_CPSW_PN_REG_IET_CTRL);
+	port_ctrl = readl(port->port_base + AM65_CPSW_PN_REG_CTL);
+
+	state->tx_enabled = !!(iet_ctrl & AM65_CPSW_PN_IET_MAC_PENABLE);
+	state->pmac_enabled = !!(port_ctrl & AM65_CPSW_PN_CTL_IET_PORT_EN);
+
+	iet_status = readl(port->port_base + AM65_CPSW_PN_REG_IET_STATUS);
+
+	if (iet_ctrl & AM65_CPSW_PN_IET_MAC_DISABLEVERIFY)
+		state->verify_status = ETHTOOL_MM_VERIFY_STATUS_DISABLED;
+	else if (iet_status & AM65_CPSW_PN_MAC_VERIFIED)
+		state->verify_status = ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED;
+	else if (iet_status & AM65_CPSW_PN_MAC_VERIFY_FAIL)
+		state->verify_status = ETHTOOL_MM_VERIFY_STATUS_FAILED;
+	else
+		state->verify_status = ETHTOOL_MM_VERIFY_STATUS_UNKNOWN;
+
+	add_frag_size = AM65_CPSW_PN_IET_MAC_GET_ADDFRAGSIZE(iet_ctrl);
+	state->tx_min_frag_size = ethtool_mm_frag_size_add_to_min(add_frag_size);
+
+	/* Errata i2208: RX min fragment size cannot be less than 124 */
+	state->rx_min_frag_size = 124;
+
+	/* FPE active if common tx_enabled and verification success or disabled (forced) */
+	state->tx_active = state->tx_enabled &&
+			   (state->verify_status == ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED ||
+			    state->verify_status == ETHTOOL_MM_VERIFY_STATUS_DISABLED);
+	state->verify_enabled = !(iet_ctrl & AM65_CPSW_PN_IET_MAC_DISABLEVERIFY);
+
+	state->verify_time = port->qos.iet.verify_time_ms;
+
+	/* 802.3-2018 clause 30.14.1.6, says that the aMACMergeVerifyTime
+	 * variable has a range between 1 and 128 ms inclusive. Limit to that.
+	 */
+	state->max_verify_time = 128;
+
+	mutex_unlock(&priv->mm_lock);
+
+	return 0;
+}
+
+static int am65_cpsw_set_mm(struct net_device *ndev, struct ethtool_mm_cfg *cfg,
+			    struct netlink_ext_ack *extack)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	struct am65_cpsw_ndev_priv *priv = netdev_priv(ndev);
+	struct am65_cpsw_iet *iet = &port->qos.iet;
+	u32 val, add_frag_size;
+	int err;
+
+	if (!IS_ENABLED(CONFIG_TI_AM65_CPSW_QOS))
+		return -EOPNOTSUPP;
+
+	err = ethtool_mm_frag_size_min_to_add(cfg->tx_min_frag_size, &add_frag_size, extack);
+	if (err)
+		return err;
+
+	mutex_lock(&priv->mm_lock);
+
+	if (cfg->pmac_enabled) {
+		/* change TX & RX FIFO MAX_BLKS as per TRM recommendation */
+		if (!iet->original_max_blks)
+			iet->original_max_blks = readl(port->port_base + AM65_CPSW_PN_REG_MAX_BLKS);
+
+		writel(AM65_CPSW_PN_TX_RX_MAX_BLKS_IET,
+		       port->port_base + AM65_CPSW_PN_REG_MAX_BLKS);
+	} else if (iet->original_max_blks) {
+		/* restore RX & TX FIFO MAX_BLKS */
+		writel(iet->original_max_blks,
+		       port->port_base + AM65_CPSW_PN_REG_MAX_BLKS);
+	}
+
+	am65_cpsw_port_iet_rx_enable(port, cfg->pmac_enabled);
+	am65_cpsw_port_iet_tx_enable(port, cfg->tx_enabled);
+
+	val = readl(port->port_base + AM65_CPSW_PN_REG_IET_CTRL);
+	if (cfg->verify_enabled) {
+		val &= ~AM65_CPSW_PN_IET_MAC_DISABLEVERIFY;
+		/* Reset Verify state machine. Verification won't start here.
+		 * Verification will be done once link-up.
+		 */
+		val |= AM65_CPSW_PN_IET_MAC_LINKFAIL;
+	} else {
+		val |= AM65_CPSW_PN_IET_MAC_DISABLEVERIFY;
+		/* Clear LINKFAIL to allow verify/response packets */
+		val &= ~AM65_CPSW_PN_IET_MAC_LINKFAIL;
+	}
+
+	val &= ~AM65_CPSW_PN_IET_MAC_MAC_ADDFRAGSIZE_MASK;
+	val |= AM65_CPSW_PN_IET_MAC_SET_ADDFRAGSIZE(add_frag_size);
+	writel(val, port->port_base + AM65_CPSW_PN_REG_IET_CTRL);
+
+	/* verify_timeout_count can only be set at valid link */
+	port->qos.iet.verify_time_ms = cfg->verify_time;
+
+	/* enable/disable preemption based on link status */
+	am65_cpsw_iet_commit_preemptible_tcs(port);
+
+	mutex_unlock(&priv->mm_lock);
+
+	return 0;
+}
+
+static void am65_cpsw_get_mm_stats(struct net_device *ndev,
+				   struct ethtool_mm_stats *s)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	void __iomem *base = port->stat_base;
+
+	s->MACMergeFrameAssOkCount = readl(base + AM65_CPSW_STATN_IET_RX_ASSEMBLY_OK);
+	s->MACMergeFrameAssErrorCount = readl(base + AM65_CPSW_STATN_IET_RX_ASSEMBLY_ERROR);
+	s->MACMergeFrameSmdErrorCount = readl(base + AM65_CPSW_STATN_IET_RX_SMD_ERROR);
+	/* CPSW Functional Spec states:
+	 * "The IET stat aMACMergeFragCountRx is derived by adding the
+	 *  Receive Assembly Error count to this value. i.e. AM65_CPSW_STATN_IET_RX_FRAG"
+	 */
+	s->MACMergeFragCountRx = readl(base + AM65_CPSW_STATN_IET_RX_FRAG) + s->MACMergeFrameAssErrorCount;
+	s->MACMergeFragCountTx = readl(base + AM65_CPSW_STATN_IET_TX_FRAG);
+	s->MACMergeHoldCount = readl(base + AM65_CPSW_STATN_IET_TX_HOLD);
+}
+
+static int am65_cpsw_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal,
+				  struct kernel_ethtool_coalesce *kernel_coal,
+				  struct netlink_ext_ack *extack)
+{
+	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
+	struct am65_cpsw_tx_chn *tx_chn;
+
+	tx_chn = &common->tx_chns[0];
+
+	coal->rx_coalesce_usecs = common->rx_pace_timeout / 1000;
+	coal->tx_coalesce_usecs = tx_chn->tx_pace_timeout / 1000;
+
+	return 0;
+}
+
+static int am65_cpsw_get_per_queue_coalesce(struct net_device *ndev, u32 queue,
+					    struct ethtool_coalesce *coal)
+{
+	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
+	struct am65_cpsw_tx_chn *tx_chn;
+
+	if (queue >= AM65_CPSW_MAX_TX_QUEUES)
+		return -EINVAL;
+
+	tx_chn = &common->tx_chns[queue];
+
+	coal->tx_coalesce_usecs = tx_chn->tx_pace_timeout / 1000;
+
+	return 0;
+}
+
+static int am65_cpsw_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal,
+				  struct kernel_ethtool_coalesce *kernel_coal,
+				  struct netlink_ext_ack *extack)
+{
+	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
+	struct am65_cpsw_tx_chn *tx_chn;
+
+	tx_chn = &common->tx_chns[0];
+
+	if (coal->rx_coalesce_usecs && coal->rx_coalesce_usecs < 20)
+		return -EINVAL;
+
+	if (coal->tx_coalesce_usecs && coal->tx_coalesce_usecs < 20)
+		return -EINVAL;
+
+	common->rx_pace_timeout = coal->rx_coalesce_usecs * 1000;
+	tx_chn->tx_pace_timeout = coal->tx_coalesce_usecs * 1000;
+
+	return 0;
+}
+
+static int am65_cpsw_set_per_queue_coalesce(struct net_device *ndev, u32 queue,
+					    struct ethtool_coalesce *coal)
+{
+	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
+	struct am65_cpsw_tx_chn *tx_chn;
+
+	if (queue >= AM65_CPSW_MAX_TX_QUEUES)
+		return -EINVAL;
+
+	tx_chn = &common->tx_chns[queue];
+
+	if (coal->tx_coalesce_usecs && coal->tx_coalesce_usecs < 20) {
+		dev_info(common->dev, "defaulting to min value of 20us for tx-usecs for tx-%u\n",
+			 queue);
+		coal->tx_coalesce_usecs = 20;
+	}
+
+	tx_chn->tx_pace_timeout = coal->tx_coalesce_usecs * 1000;
+
+	return 0;
+}
+
 const struct ethtool_ops am65_cpsw_ethtool_ops_slave = {
 	.begin			= am65_cpsw_ethtool_op_begin,
 	.complete		= am65_cpsw_ethtool_op_complete,
@@ -729,9 +992,15 @@ const struct ethtool_ops am65_cpsw_ethtool_ops_slave = {
 	.get_sset_count		= am65_cpsw_get_sset_count,
 	.get_strings		= am65_cpsw_get_strings,
 	.get_ethtool_stats	= am65_cpsw_get_ethtool_stats,
+	.get_eth_mac_stats	= am65_cpsw_get_eth_mac_stats,
 	.get_ts_info		= am65_cpsw_get_ethtool_ts_info,
 	.get_priv_flags		= am65_cpsw_get_ethtool_priv_flags,
 	.set_priv_flags		= am65_cpsw_set_ethtool_priv_flags,
+	.supported_coalesce_params = ETHTOOL_COALESCE_USECS,
+	.get_coalesce           = am65_cpsw_get_coalesce,
+	.set_coalesce           = am65_cpsw_set_coalesce,
+	.get_per_queue_coalesce = am65_cpsw_get_per_queue_coalesce,
+	.set_per_queue_coalesce = am65_cpsw_set_per_queue_coalesce,
 
 	.get_link		= ethtool_op_get_link,
 	.get_link_ksettings	= am65_cpsw_get_link_ksettings,
@@ -743,4 +1012,7 @@ const struct ethtool_ops am65_cpsw_ethtool_ops_slave = {
 	.get_eee		= am65_cpsw_get_eee,
 	.set_eee		= am65_cpsw_set_eee,
 	.nway_reset		= am65_cpsw_nway_reset,
+	.get_mm			= am65_cpsw_get_mm,
+	.set_mm			= am65_cpsw_set_mm,
+	.get_mm_stats		= am65_cpsw_get_mm_stats,
 };
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index ece9f8df98ae..faa0561e988e 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -136,6 +136,8 @@
 			 NETIF_MSG_IFUP	| NETIF_MSG_PROBE | NETIF_MSG_IFDOWN | \
 			 NETIF_MSG_RX_ERR | NETIF_MSG_TX_ERR)
 
+#define AM65_CPSW_DEFAULT_TX_CHNS	8
+
 static void am65_cpsw_port_set_sl_mac(struct am65_cpsw_port *slave,
 				      const u8 *dev_addr)
 {
@@ -367,10 +369,81 @@ static void am65_cpsw_init_host_port_emac(struct am65_cpsw_common *common);
 static void am65_cpsw_init_port_switch_ale(struct am65_cpsw_port *port);
 static void am65_cpsw_init_port_emac_ale(struct am65_cpsw_port *port);
 
+static void am65_cpsw_nuss_rx_cleanup(void *data, dma_addr_t desc_dma)
+{
+	struct am65_cpsw_rx_chn *rx_chn = data;
+	struct cppi5_host_desc_t *desc_rx;
+	struct sk_buff *skb;
+	dma_addr_t buf_dma;
+	u32 buf_dma_len;
+	void **swdata;
+
+	desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma);
+	swdata = cppi5_hdesc_get_swdata(desc_rx);
+	skb = *swdata;
+	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
+	k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma);
+
+	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE);
+	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
+
+	dev_kfree_skb_any(skb);
+}
+
+static void am65_cpsw_nuss_xmit_free(struct am65_cpsw_tx_chn *tx_chn,
+				     struct cppi5_host_desc_t *desc)
+{
+	struct cppi5_host_desc_t *first_desc, *next_desc;
+	dma_addr_t buf_dma, next_desc_dma;
+	u32 buf_dma_len;
+
+	first_desc = desc;
+	next_desc = first_desc;
+
+	cppi5_hdesc_get_obuf(first_desc, &buf_dma, &buf_dma_len);
+	k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma);
+
+	dma_unmap_single(tx_chn->dma_dev, buf_dma, buf_dma_len, DMA_TO_DEVICE);
+
+	next_desc_dma = cppi5_hdesc_get_next_hbdesc(first_desc);
+	k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &next_desc_dma);
+	while (next_desc_dma) {
+		next_desc = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool,
+						       next_desc_dma);
+		cppi5_hdesc_get_obuf(next_desc, &buf_dma, &buf_dma_len);
+		k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma);
+
+		dma_unmap_page(tx_chn->dma_dev, buf_dma, buf_dma_len,
+			       DMA_TO_DEVICE);
+
+		next_desc_dma = cppi5_hdesc_get_next_hbdesc(next_desc);
+		k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &next_desc_dma);
+
+		k3_cppi_desc_pool_free(tx_chn->desc_pool, next_desc);
+	}
+
+	k3_cppi_desc_pool_free(tx_chn->desc_pool, first_desc);
+}
+
+static void am65_cpsw_nuss_tx_cleanup(void *data, dma_addr_t desc_dma)
+{
+	struct am65_cpsw_tx_chn *tx_chn = data;
+	struct cppi5_host_desc_t *desc_tx;
+	struct sk_buff *skb;
+	void **swdata;
+
+	desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma);
+	swdata = cppi5_hdesc_get_swdata(desc_tx);
+	skb = *(swdata);
+	am65_cpsw_nuss_xmit_free(tx_chn, desc_tx);
+
+	dev_kfree_skb_any(skb);
+}
+
 static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common)
 {
 	struct am65_cpsw_host *host_p = am65_common_get_host(common);
-	int port_idx, i, ret;
+	int port_idx, i, ret, tx;
 	struct sk_buff *skb;
 	u32 val, port_mask;
 
@@ -437,8 +510,12 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common)
 						  AM65_CPSW_MAX_PACKET_SIZE,
 						  GFP_KERNEL);
 		if (!skb) {
+			ret = -ENOMEM;
 			dev_err(common->dev, "cannot allocate skb\n");
-			return -ENOMEM;
+			if (i)
+				goto fail_rx;
+
+			return ret;
 		}
 
 		ret = am65_cpsw_nuss_rx_push(common, skb);
@@ -447,17 +524,28 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common)
 				"cannot submit skb to channel rx, error %d\n",
 				ret);
 			kfree_skb(skb);
+			if (i)
+				goto fail_rx;
+
 			return ret;
 		}
-		kmemleak_not_leak(skb);
 	}
-	k3_udma_glue_enable_rx_chn(common->rx_chns.rx_chn);
 
-	for (i = 0; i < common->tx_ch_num; i++) {
-		ret = k3_udma_glue_enable_tx_chn(common->tx_chns[i].tx_chn);
-		if (ret)
-			return ret;
-		napi_enable(&common->tx_chns[i].napi_tx);
+	ret = k3_udma_glue_enable_rx_chn(common->rx_chns.rx_chn);
+	if (ret) {
+		dev_err(common->dev, "couldn't enable rx chn: %d\n", ret);
+		goto fail_rx;
+	}
+
+	for (tx = 0; tx < common->tx_ch_num; tx++) {
+		ret = k3_udma_glue_enable_tx_chn(common->tx_chns[tx].tx_chn);
+		if (ret) {
+			dev_err(common->dev, "couldn't enable tx chn %d: %d\n",
+				tx, ret);
+			tx--;
+			goto fail_tx;
+		}
+		napi_enable(&common->tx_chns[tx].napi_tx);
 	}
 
 	napi_enable(&common->napi_rx);
@@ -468,10 +556,22 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common)
 
 	dev_dbg(common->dev, "cpsw_nuss started\n");
 	return 0;
-}
 
-static void am65_cpsw_nuss_tx_cleanup(void *data, dma_addr_t desc_dma);
-static void am65_cpsw_nuss_rx_cleanup(void *data, dma_addr_t desc_dma);
+fail_tx:
+	while (tx >= 0) {
+		napi_disable(&common->tx_chns[tx].napi_tx);
+		k3_udma_glue_disable_tx_chn(common->tx_chns[tx].tx_chn);
+		tx--;
+	}
+
+	k3_udma_glue_disable_rx_chn(common->rx_chns.rx_chn);
+
+fail_rx:
+	k3_udma_glue_reset_rx_chn(common->rx_chns.rx_chn, 0,
+				  &common->rx_chns,
+				  am65_cpsw_nuss_rx_cleanup, 0);
+	return ret;
+}
 
 static int am65_cpsw_nuss_common_stop(struct am65_cpsw_common *common)
 {
@@ -496,8 +596,10 @@ static int am65_cpsw_nuss_common_stop(struct am65_cpsw_common *common)
 					msecs_to_jiffies(1000));
 	if (!i)
 		dev_err(common->dev, "tx timeout\n");
-	for (i = 0; i < common->tx_ch_num; i++)
+	for (i = 0; i < common->tx_ch_num; i++) {
 		napi_disable(&common->tx_chns[i].napi_tx);
+		hrtimer_cancel(&common->tx_chns[i].tx_hrtimer);
+	}
 
 	for (i = 0; i < common->tx_ch_num; i++) {
 		k3_udma_glue_reset_tx_chn(common->tx_chns[i].tx_chn,
@@ -516,6 +618,7 @@ static int am65_cpsw_nuss_common_stop(struct am65_cpsw_common *common)
 	}
 
 	napi_disable(&common->napi_rx);
+	hrtimer_cancel(&common->rx_hrtimer);
 
 	for (i = 0; i < AM65_CPSW_MAX_RX_FLOWS; i++)
 		k3_udma_glue_reset_rx_chn(common->rx_chns.rx_chn, i,
@@ -646,27 +749,6 @@ runtime_put:
 	return ret;
 }
 
-static void am65_cpsw_nuss_rx_cleanup(void *data, dma_addr_t desc_dma)
-{
-	struct am65_cpsw_rx_chn *rx_chn = data;
-	struct cppi5_host_desc_t *desc_rx;
-	struct sk_buff *skb;
-	dma_addr_t buf_dma;
-	u32 buf_dma_len;
-	void **swdata;
-
-	desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma);
-	swdata = cppi5_hdesc_get_swdata(desc_rx);
-	skb = *swdata;
-	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
-	k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma);
-
-	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE);
-	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
-
-	dev_kfree_skb_any(skb);
-}
-
 static void am65_cpsw_nuss_rx_ts(struct sk_buff *skb, u32 *psdata)
 {
 	struct skb_shared_hwtstamps *ssh;
@@ -806,6 +888,15 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common,
 	return ret;
 }
 
+static enum hrtimer_restart am65_cpsw_nuss_rx_timer_callback(struct hrtimer *timer)
+{
+	struct am65_cpsw_common *common =
+			container_of(timer, struct am65_cpsw_common, rx_hrtimer);
+
+	enable_irq(common->rx_chns.irq);
+	return HRTIMER_NORESTART;
+}
+
 static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget)
 {
 	struct am65_cpsw_common *common = am65_cpsw_napi_to_common(napi_rx);
@@ -833,63 +924,19 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget)
 	if (num_rx < budget && napi_complete_done(napi_rx, num_rx)) {
 		if (common->rx_irq_disabled) {
 			common->rx_irq_disabled = false;
-			enable_irq(common->rx_chns.irq);
+			if (unlikely(common->rx_pace_timeout)) {
+				hrtimer_start(&common->rx_hrtimer,
+					      ns_to_ktime(common->rx_pace_timeout),
+					      HRTIMER_MODE_REL_PINNED);
+			} else {
+				enable_irq(common->rx_chns.irq);
+			}
 		}
 	}
 
 	return num_rx;
 }
 
-static void am65_cpsw_nuss_xmit_free(struct am65_cpsw_tx_chn *tx_chn,
-				     struct cppi5_host_desc_t *desc)
-{
-	struct cppi5_host_desc_t *first_desc, *next_desc;
-	dma_addr_t buf_dma, next_desc_dma;
-	u32 buf_dma_len;
-
-	first_desc = desc;
-	next_desc = first_desc;
-
-	cppi5_hdesc_get_obuf(first_desc, &buf_dma, &buf_dma_len);
-	k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma);
-
-	dma_unmap_single(tx_chn->dma_dev, buf_dma, buf_dma_len, DMA_TO_DEVICE);
-
-	next_desc_dma = cppi5_hdesc_get_next_hbdesc(first_desc);
-	k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &next_desc_dma);
-	while (next_desc_dma) {
-		next_desc = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool,
-						       next_desc_dma);
-		cppi5_hdesc_get_obuf(next_desc, &buf_dma, &buf_dma_len);
-		k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma);
-
-		dma_unmap_page(tx_chn->dma_dev, buf_dma, buf_dma_len,
-			       DMA_TO_DEVICE);
-
-		next_desc_dma = cppi5_hdesc_get_next_hbdesc(next_desc);
-		k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &next_desc_dma);
-
-		k3_cppi_desc_pool_free(tx_chn->desc_pool, next_desc);
-	}
-
-	k3_cppi_desc_pool_free(tx_chn->desc_pool, first_desc);
-}
-
-static void am65_cpsw_nuss_tx_cleanup(void *data, dma_addr_t desc_dma)
-{
-	struct am65_cpsw_tx_chn *tx_chn = data;
-	struct cppi5_host_desc_t *desc_tx;
-	struct sk_buff *skb;
-	void **swdata;
-
-	desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma);
-	swdata = cppi5_hdesc_get_swdata(desc_tx);
-	skb = *(swdata);
-	am65_cpsw_nuss_xmit_free(tx_chn, desc_tx);
-
-	dev_kfree_skb_any(skb);
-}
-
 static struct sk_buff *
 am65_cpsw_nuss_tx_compl_packet(struct am65_cpsw_tx_chn *tx_chn,
 			       dma_addr_t desc_dma)
@@ -939,7 +986,7 @@ static void am65_cpsw_nuss_tx_wake(struct am65_cpsw_tx_chn *tx_chn, struct net_d
 }
 
 static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
-					   int chn, unsigned int budget)
+					   int chn, unsigned int budget, bool *tdown)
 {
 	struct device *dev = common->dev;
 	struct am65_cpsw_tx_chn *tx_chn;
@@ -962,6 +1009,7 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 		if (cppi5_desc_is_tdcm(desc_dma)) {
 			if (atomic_dec_and_test(&common->tdown_cnt))
 				complete(&common->tdown_complete);
+			*tdown = true;
 			break;
 		}
 
@@ -984,7 +1032,7 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 }
 
 static int am65_cpsw_nuss_tx_compl_packets_2g(struct am65_cpsw_common *common,
-					      int chn, unsigned int budget)
+					      int chn, unsigned int budget, bool *tdown)
 {
 	struct device *dev = common->dev;
 	struct am65_cpsw_tx_chn *tx_chn;
@@ -1005,6 +1053,7 @@ static int am65_cpsw_nuss_tx_compl_packets_2g(struct am65_cpsw_common *common,
 		if (cppi5_desc_is_tdcm(desc_dma)) {
 			if (atomic_dec_and_test(&common->tdown_cnt))
 				complete(&common->tdown_complete);
+			*tdown = true;
 			break;
 		}
 
@@ -1030,21 +1079,40 @@ static int am65_cpsw_nuss_tx_compl_packets_2g(struct am65_cpsw_common *common,
 	return num_tx;
 }
 
+static enum hrtimer_restart am65_cpsw_nuss_tx_timer_callback(struct hrtimer *timer)
+{
+	struct am65_cpsw_tx_chn *tx_chns =
+			container_of(timer, struct am65_cpsw_tx_chn, tx_hrtimer);
+
+	enable_irq(tx_chns->irq);
+	return HRTIMER_NORESTART;
+}
+
 static int am65_cpsw_nuss_tx_poll(struct napi_struct *napi_tx, int budget)
 {
 	struct am65_cpsw_tx_chn *tx_chn = am65_cpsw_napi_to_tx_chn(napi_tx);
+	bool tdown = false;
 	int num_tx;
 
 	if (AM65_CPSW_IS_CPSW2G(tx_chn->common))
-		num_tx = am65_cpsw_nuss_tx_compl_packets_2g(tx_chn->common, tx_chn->id, budget);
+		num_tx = am65_cpsw_nuss_tx_compl_packets_2g(tx_chn->common, tx_chn->id,
+							    budget, &tdown);
 	else
-		num_tx = am65_cpsw_nuss_tx_compl_packets(tx_chn->common, tx_chn->id, budget);
+		num_tx = am65_cpsw_nuss_tx_compl_packets(tx_chn->common,
+							 tx_chn->id, budget, &tdown);
 
 	if (num_tx >= budget)
 		return budget;
 
-	if (napi_complete_done(napi_tx, num_tx))
-		enable_irq(tx_chn->irq);
+	if (napi_complete_done(napi_tx, num_tx)) {
+		if (unlikely(tx_chn->tx_pace_timeout && !tdown)) {
+			hrtimer_start(&tx_chn->tx_hrtimer,
+				      ns_to_ktime(tx_chn->tx_pace_timeout),
+				      HRTIMER_MODE_REL_PINNED);
+		} else {
+			enable_irq(tx_chn->irq);
+		}
+	}
 
 	return 0;
 }
@@ -1676,6 +1744,8 @@ static int am65_cpsw_nuss_ndev_add_tx_napi(struct am65_cpsw_common *common)
 
 		netif_napi_add_tx(common->dma_ndev, &tx_chn->napi_tx,
 				  am65_cpsw_nuss_tx_poll);
+		hrtimer_init(&tx_chn->tx_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
+		tx_chn->tx_hrtimer.function = &am65_cpsw_nuss_tx_timer_callback;
 
 		ret = devm_request_irq(dev, tx_chn->irq,
 				       am65_cpsw_nuss_tx_irq,
@@ -1901,6 +1971,8 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 
 	netif_napi_add(common->dma_ndev, &common->napi_rx,
 		       am65_cpsw_nuss_rx_poll);
+	hrtimer_init(&common->rx_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
+	common->rx_hrtimer.function = &am65_cpsw_nuss_rx_timer_callback;
 
 	ret = devm_request_irq(dev, rx_chn->irq,
 			       am65_cpsw_nuss_rx_irq,
@@ -2098,6 +2170,9 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 				dev_err(dev, "Use random MAC address\n");
 			}
 		}
+
+		/* Reset all Queue priorities to 0 */
+		writel(0, port->port_base + AM65_CPSW_PN_REG_TX_PRI_MAP);
 	}
 	of_node_put(node);
 
@@ -2162,6 +2237,8 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx)
 	ndev_priv = netdev_priv(port->ndev);
 	ndev_priv->port = port;
 	ndev_priv->msg_enable = AM65_CPSW_DEBUG;
+	mutex_init(&ndev_priv->mm_lock);
+	port->qos.link_speed = SPEED_UNKNOWN;
 	SET_NETDEV_DEV(port->ndev, dev);
 
 	eth_hw_addr_set(port->ndev, port->slave.mac_addr);
@@ -2897,7 +2974,7 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 
 	common->rx_flow_id_base = -1;
 	init_completion(&common->tdown_complete);
-	common->tx_ch_num = 1;
+	common->tx_ch_num = AM65_CPSW_DEFAULT_TX_CHNS;
 	common->pf_p0_rx_ptype_rrobin = false;
 	common->default_vlan = 1;
 
@@ -2999,7 +3076,7 @@ err_pm_clear:
 	return ret;
 }
 
-static int am65_cpsw_nuss_remove(struct platform_device *pdev)
+static void am65_cpsw_nuss_remove(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct am65_cpsw_common *common;
@@ -3008,8 +3085,14 @@ static int am65_cpsw_nuss_remove(struct platform_device *pdev)
 	common = dev_get_drvdata(dev);
 
 	ret = pm_runtime_resume_and_get(&pdev->dev);
-	if (ret < 0)
-		return ret;
+	if (ret < 0) {
+		/* Note, if this error path is taken, we're leaking some
+		 * resources.
+		 */
+		dev_err(&pdev->dev, "Failed to resume device (%pe)\n",
+			ERR_PTR(ret));
+		return;
+	}
 
 	am65_cpsw_unregister_devlink(common);
 	am65_cpsw_unregister_notifiers(common);
@@ -3027,7 +3110,6 @@ static int am65_cpsw_nuss_remove(struct platform_device *pdev)
 
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-	return 0;
 }
 
 static int am65_cpsw_nuss_suspend(struct device *dev)
@@ -3127,7 +3209,7 @@ static struct platform_driver am65_cpsw_nuss_driver = {
 		.pm = &am65_cpsw_nuss_dev_pm_ops,
 	},
 	.probe = am65_cpsw_nuss_probe,
-	.remove = am65_cpsw_nuss_remove,
+	.remove_new = am65_cpsw_nuss_remove,
 };
 
 module_platform_driver(am65_cpsw_nuss_driver);
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
index f3dad2ab9828..7da0492dc091 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
@@ -75,6 +75,8 @@ struct am65_cpsw_tx_chn {
 	struct k3_cppi_desc_pool *desc_pool;
 	struct k3_udma_glue_tx_channel *tx_chn;
 	spinlock_t lock; /* protect TX rings in multi-port mode */
+	struct hrtimer tx_hrtimer;
+	unsigned long tx_pace_timeout;
 	int irq;
 	u32 id;
 	u32 descs_num;
@@ -138,6 +140,8 @@ struct am65_cpsw_common {
 	struct napi_struct	napi_rx;
 
 	bool			rx_irq_disabled;
+	struct hrtimer		rx_hrtimer;
+	unsigned long		rx_pace_timeout;
 
 	u32			nuss_ver;
 	u32			cpsw_ver;
@@ -145,6 +149,7 @@ struct am65_cpsw_common {
 	bool			pf_p0_rx_ptype_rrobin;
 	struct am65_cpts	*cpts;
 	int			est_enabled;
+	bool			iet_enabled;
 
 	bool		is_emac_mode;
 	u16			br_members;
@@ -170,6 +175,10 @@ struct am65_cpsw_ndev_priv {
 	struct am65_cpsw_port	*port;
 	struct am65_cpsw_ndev_stats __percpu *stats;
 	bool offload_fwd_mark;
+	/* Serialize access to MAC Merge state between ethtool requests
+	 * and link state updates
+	 */
+	struct mutex		mm_lock;
 };
 
 #define am65_ndev_to_priv(ndev) \
diff --git a/drivers/net/ethernet/ti/am65-cpsw-qos.c b/drivers/net/ethernet/ti/am65-cpsw-qos.c
index 9ac2ff05d501..816e73a3d6e4 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-qos.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-qos.c
@@ -4,10 +4,13 @@
  *
  * quality of service module includes:
  * Enhanced Scheduler Traffic (EST - P802.1Qbv/D2.2)
+ * Interspersed Express Traffic (IET - P802.3br/D2.0)
  */
 
 #include <linux/pm_runtime.h>
+#include <linux/math.h>
 #include <linux/time.h>
+#include <linux/units.h>
 #include <net/pkt_cls.h>
 
 #include "am65-cpsw-nuss.h"
@@ -15,40 +18,7 @@
 #include "am65-cpts.h"
 #include "cpsw_ale.h"
 
-#define AM65_CPSW_REG_CTL			0x004
-#define AM65_CPSW_PN_REG_CTL			0x004
-#define AM65_CPSW_PN_REG_FIFO_STATUS		0x050
-#define AM65_CPSW_PN_REG_EST_CTL		0x060
-#define AM65_CPSW_PN_REG_PRI_CIR(pri)		(0x140 + 4 * (pri))
-
-/* AM65_CPSW_REG_CTL register fields */
-#define AM65_CPSW_CTL_EST_EN			BIT(18)
-
-/* AM65_CPSW_PN_REG_CTL register fields */
-#define AM65_CPSW_PN_CTL_EST_PORT_EN		BIT(17)
-
-/* AM65_CPSW_PN_REG_EST_CTL register fields */
-#define AM65_CPSW_PN_EST_ONEBUF			BIT(0)
-#define AM65_CPSW_PN_EST_BUFSEL			BIT(1)
-#define AM65_CPSW_PN_EST_TS_EN			BIT(2)
-#define AM65_CPSW_PN_EST_TS_FIRST		BIT(3)
-#define AM65_CPSW_PN_EST_ONEPRI			BIT(4)
-#define AM65_CPSW_PN_EST_TS_PRI_MSK		GENMASK(7, 5)
-
-/* AM65_CPSW_PN_REG_FIFO_STATUS register fields */
-#define AM65_CPSW_PN_FST_TX_PRI_ACTIVE_MSK	GENMASK(7, 0)
-#define AM65_CPSW_PN_FST_TX_E_MAC_ALLOW_MSK	GENMASK(15, 8)
-#define AM65_CPSW_PN_FST_EST_CNT_ERR		BIT(16)
-#define AM65_CPSW_PN_FST_EST_ADD_ERR		BIT(17)
-#define AM65_CPSW_PN_FST_EST_BUFACT		BIT(18)
-
-/* EST FETCH COMMAND RAM */
-#define AM65_CPSW_FETCH_RAM_CMD_NUM		0x80
-#define AM65_CPSW_FETCH_CNT_MSK			GENMASK(21, 8)
-#define AM65_CPSW_FETCH_CNT_MAX			(AM65_CPSW_FETCH_CNT_MSK >> 8)
-#define AM65_CPSW_FETCH_CNT_OFFSET		8
-#define AM65_CPSW_FETCH_ALLOW_MSK		GENMASK(7, 0)
-#define AM65_CPSW_FETCH_ALLOW_MAX		AM65_CPSW_FETCH_ALLOW_MSK
+#define TO_MBPS(x)	DIV_ROUND_UP((x), BYTES_PER_MBIT)
 
 enum timer_act {
 	TACT_PROG,		/* need program timer */
@@ -56,6 +26,412 @@ enum timer_act {
 	TACT_SKIP_PROG,		/* just buffer can be updated */
 };
 
+static void am65_cpsw_iet_change_preemptible_tcs(struct am65_cpsw_port *port, u8 preemptible_tcs);
+
+static u32
+am65_cpsw_qos_tx_rate_calc(u32 rate_mbps, unsigned long bus_freq)
+{
+	u32 ir;
+
+	bus_freq /= 1000000;
+	ir = DIV_ROUND_UP(((u64)rate_mbps * 32768),  bus_freq);
+	return ir;
+}
+
+static void am65_cpsw_tx_pn_shaper_reset(struct am65_cpsw_port *port)
+{
+	int prio;
+
+	for (prio = 0; prio < AM65_CPSW_PN_FIFO_PRIO_NUM; prio++) {
+		writel(0, port->port_base + AM65_CPSW_PN_REG_PRI_CIR(prio));
+		writel(0, port->port_base + AM65_CPSW_PN_REG_PRI_EIR(prio));
+	}
+}
+
+static void am65_cpsw_tx_pn_shaper_apply(struct am65_cpsw_port *port)
+{
+	struct am65_cpsw_mqprio *p_mqprio = &port->qos.mqprio;
+	struct am65_cpsw_common *common = port->common;
+	struct tc_mqprio_qopt_offload *mqprio;
+	bool enable, shaper_susp = false;
+	u32 rate_mbps;
+	int tc, prio;
+
+	mqprio = &p_mqprio->mqprio_hw;
+	/* takes care of no link case as well */
+	if (p_mqprio->max_rate_total > port->qos.link_speed)
+		shaper_susp = true;
+
+	am65_cpsw_tx_pn_shaper_reset(port);
+
+	enable = p_mqprio->shaper_en && !shaper_susp;
+	if (!enable)
+		return;
+
+	/* Rate limit is specified per Traffic Class but
+	 * for CPSW, rate limit can be applied per priority
+	 * at port FIFO.
+	 *
+	 * We have assigned the same priority (TCn) to all queues
+	 * of a Traffic Class so they share the same shaper
+	 * bandwidth.
+	 */
+	for (tc = 0; tc < mqprio->qopt.num_tc; tc++) {
+		prio = tc;
+
+		rate_mbps = TO_MBPS(mqprio->min_rate[tc]);
+		rate_mbps = am65_cpsw_qos_tx_rate_calc(rate_mbps,
+						       common->bus_freq);
+		writel(rate_mbps,
+		       port->port_base + AM65_CPSW_PN_REG_PRI_CIR(prio));
+
+		rate_mbps = 0;
+
+		if (mqprio->max_rate[tc]) {
+			rate_mbps = mqprio->max_rate[tc] - mqprio->min_rate[tc];
+			rate_mbps = TO_MBPS(rate_mbps);
+			rate_mbps = am65_cpsw_qos_tx_rate_calc(rate_mbps,
+							       common->bus_freq);
+		}
+
+		writel(rate_mbps,
+		       port->port_base + AM65_CPSW_PN_REG_PRI_EIR(prio));
+	}
+}
+
+static int am65_cpsw_mqprio_verify_shaper(struct am65_cpsw_port *port,
+					  struct tc_mqprio_qopt_offload *mqprio)
+{
+	struct am65_cpsw_mqprio *p_mqprio = &port->qos.mqprio;
+	struct netlink_ext_ack *extack = mqprio->extack;
+	u64 min_rate_total = 0, max_rate_total = 0;
+	u32 min_rate_msk = 0, max_rate_msk = 0;
+	bool has_min_rate, has_max_rate;
+	int num_tc, i;
+
+	if (!(mqprio->flags & TC_MQPRIO_F_SHAPER))
+		return 0;
+
+	if (mqprio->shaper != TC_MQPRIO_SHAPER_BW_RATE)
+		return 0;
+
+	has_min_rate = !!(mqprio->flags & TC_MQPRIO_F_MIN_RATE);
+	has_max_rate = !!(mqprio->flags & TC_MQPRIO_F_MAX_RATE);
+
+	if (!has_min_rate && has_max_rate) {
+		NL_SET_ERR_MSG_MOD(extack, "min_rate is required with max_rate");
+		return -EOPNOTSUPP;
+	}
+
+	if (!has_min_rate)
+		return 0;
+
+	num_tc = mqprio->qopt.num_tc;
+
+	for (i = num_tc - 1; i >= 0; i--) {
+		u32 ch_msk;
+
+		if (mqprio->min_rate[i])
+			min_rate_msk |= BIT(i);
+		min_rate_total +=  mqprio->min_rate[i];
+
+		if (has_max_rate) {
+			if (mqprio->max_rate[i])
+				max_rate_msk |= BIT(i);
+			max_rate_total +=  mqprio->max_rate[i];
+
+			if (!mqprio->min_rate[i] && mqprio->max_rate[i]) {
+				NL_SET_ERR_MSG_FMT_MOD(extack,
+						       "TX tc%d rate max>0 but min=0",
+						       i);
+				return -EINVAL;
+			}
+
+			if (mqprio->max_rate[i] &&
+			    mqprio->max_rate[i] < mqprio->min_rate[i]) {
+				NL_SET_ERR_MSG_FMT_MOD(extack,
+						       "TX tc%d rate min(%llu)>max(%llu)",
+						       i, mqprio->min_rate[i],
+						       mqprio->max_rate[i]);
+				return -EINVAL;
+			}
+		}
+
+		ch_msk = GENMASK(num_tc - 1, i);
+		if ((min_rate_msk & BIT(i)) && (min_rate_msk ^ ch_msk)) {
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "Min rate must be set sequentially hi->lo tx_rate_msk%x",
+					       min_rate_msk);
+			return -EINVAL;
+		}
+
+		if ((max_rate_msk & BIT(i)) && (max_rate_msk ^ ch_msk)) {
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "Max rate must be set sequentially hi->lo tx_rate_msk%x",
+					       max_rate_msk);
+			return -EINVAL;
+		}
+	}
+
+	min_rate_total = TO_MBPS(min_rate_total);
+	max_rate_total = TO_MBPS(max_rate_total);
+
+	p_mqprio->shaper_en = true;
+	p_mqprio->max_rate_total = max_t(u64, min_rate_total, max_rate_total);
+
+	return 0;
+}
+
+static void am65_cpsw_reset_tc_mqprio(struct net_device *ndev)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	struct am65_cpsw_mqprio *p_mqprio = &port->qos.mqprio;
+
+	p_mqprio->shaper_en = false;
+	p_mqprio->max_rate_total = 0;
+
+	am65_cpsw_tx_pn_shaper_reset(port);
+	netdev_reset_tc(ndev);
+
+	/* Reset all Queue priorities to 0 */
+	writel(0, port->port_base + AM65_CPSW_PN_REG_TX_PRI_MAP);
+
+	am65_cpsw_iet_change_preemptible_tcs(port, 0);
+}
+
+static int am65_cpsw_setup_mqprio(struct net_device *ndev, void *type_data)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	struct am65_cpsw_mqprio *p_mqprio = &port->qos.mqprio;
+	struct tc_mqprio_qopt_offload *mqprio = type_data;
+	struct am65_cpsw_common *common = port->common;
+	struct tc_mqprio_qopt *qopt = &mqprio->qopt;
+	int i, tc, offset, count, prio, ret;
+	u8 num_tc = qopt->num_tc;
+	u32 tx_prio_map = 0;
+
+	memcpy(&p_mqprio->mqprio_hw, mqprio, sizeof(*mqprio));
+
+	ret = pm_runtime_get_sync(common->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(common->dev);
+		return ret;
+	}
+
+	if (!num_tc) {
+		am65_cpsw_reset_tc_mqprio(ndev);
+		ret = 0;
+		goto exit_put;
+	}
+
+	ret = am65_cpsw_mqprio_verify_shaper(port, mqprio);
+	if (ret)
+		goto exit_put;
+
+	netdev_set_num_tc(ndev, num_tc);
+
+	/* Multiple Linux priorities can map to a Traffic Class
+	 * A Traffic Class can have multiple contiguous Queues,
+	 * Queues get mapped to Channels (thread_id),
+	 *	if not VLAN tagged, thread_id is used as packet_priority
+	 *	if VLAN tagged. VLAN priority is used as packet_priority
+	 * packet_priority gets mapped to header_priority in p0_rx_pri_map,
+	 * header_priority gets mapped to switch_priority in pn_tx_pri_map.
+	 * As p0_rx_pri_map is left at defaults (0x76543210), we can
+	 * assume that Queue_n gets mapped to header_priority_n. We can then
+	 * set the switch priority in pn_tx_pri_map.
+	 */
+
+	for (tc = 0; tc < num_tc; tc++) {
+		prio = tc;
+
+		/* For simplicity we assign the same priority (TCn) to
+		 * all queues of a Traffic Class.
+		 */
+		for (i = qopt->offset[tc]; i < qopt->offset[tc] + qopt->count[tc]; i++)
+			tx_prio_map |= prio << (4 * i);
+
+		count = qopt->count[tc];
+		offset = qopt->offset[tc];
+		netdev_set_tc_queue(ndev, tc, count, offset);
+	}
+
+	writel(tx_prio_map, port->port_base + AM65_CPSW_PN_REG_TX_PRI_MAP);
+
+	am65_cpsw_tx_pn_shaper_apply(port);
+	am65_cpsw_iet_change_preemptible_tcs(port, mqprio->preemptible_tcs);
+
+exit_put:
+	pm_runtime_put(common->dev);
+
+	return ret;
+}
+
+static int am65_cpsw_iet_set_verify_timeout_count(struct am65_cpsw_port *port)
+{
+	int verify_time_ms = port->qos.iet.verify_time_ms;
+	u32 val;
+
+	/* The number of wireside clocks contained in the verify
+	 * timeout counter. The default is 0x1312d0
+	 * (10ms at 125Mhz in 1G mode).
+	 */
+	val = 125 * HZ_PER_MHZ;	/* assuming 125MHz wireside clock */
+
+	val /= MILLIHZ_PER_HZ;		/* count per ms timeout */
+	val *= verify_time_ms;		/* count for timeout ms */
+
+	if (val > AM65_CPSW_PN_MAC_VERIFY_CNT_MASK)
+		return -EINVAL;
+
+	writel(val, port->port_base + AM65_CPSW_PN_REG_IET_VERIFY);
+
+	return 0;
+}
+
+static int am65_cpsw_iet_verify_wait(struct am65_cpsw_port *port)
+{
+	u32 ctrl, status;
+	int try;
+
+	try = 20;
+	do {
+		/* Reset the verify state machine by writing 1
+		 * to LINKFAIL
+		 */
+		ctrl = readl(port->port_base + AM65_CPSW_PN_REG_IET_CTRL);
+		ctrl |= AM65_CPSW_PN_IET_MAC_LINKFAIL;
+		writel(ctrl, port->port_base + AM65_CPSW_PN_REG_IET_CTRL);
+
+		/* Clear MAC_LINKFAIL bit to start Verify. */
+		ctrl = readl(port->port_base + AM65_CPSW_PN_REG_IET_CTRL);
+		ctrl &= ~AM65_CPSW_PN_IET_MAC_LINKFAIL;
+		writel(ctrl, port->port_base + AM65_CPSW_PN_REG_IET_CTRL);
+
+		msleep(port->qos.iet.verify_time_ms);
+
+		status = readl(port->port_base + AM65_CPSW_PN_REG_IET_STATUS);
+		if (status & AM65_CPSW_PN_MAC_VERIFIED)
+			return 0;
+
+		if (status & AM65_CPSW_PN_MAC_VERIFY_FAIL) {
+			netdev_dbg(port->ndev,
+				   "MAC Merge verify failed, trying again\n");
+			continue;
+		}
+
+		if (status & AM65_CPSW_PN_MAC_RESPOND_ERR) {
+			netdev_dbg(port->ndev, "MAC Merge respond error\n");
+			return -ENODEV;
+		}
+
+		if (status & AM65_CPSW_PN_MAC_VERIFY_ERR) {
+			netdev_dbg(port->ndev, "MAC Merge verify error\n");
+			return -ENODEV;
+		}
+	} while (try-- > 0);
+
+	netdev_dbg(port->ndev, "MAC Merge verify timeout\n");
+	return -ETIMEDOUT;
+}
+
+static void am65_cpsw_iet_set_preempt_mask(struct am65_cpsw_port *port, u8 preemptible_tcs)
+{
+	u32 val;
+
+	val = readl(port->port_base + AM65_CPSW_PN_REG_IET_CTRL);
+	val &= ~AM65_CPSW_PN_IET_MAC_PREMPT_MASK;
+	val |= AM65_CPSW_PN_IET_MAC_SET_PREEMPT(preemptible_tcs);
+	writel(val, port->port_base + AM65_CPSW_PN_REG_IET_CTRL);
+}
+
+/* enable common IET_ENABLE only if at least 1 port has rx IET enabled.
+ * UAPI doesn't allow tx enable without rx enable.
+ */
+void am65_cpsw_iet_common_enable(struct am65_cpsw_common *common)
+{
+	struct am65_cpsw_port *port;
+	bool rx_enable = false;
+	u32 val;
+	int i;
+
+	for (i = 0; i < common->port_num; i++) {
+		port = &common->ports[i];
+		val = readl(port->port_base + AM65_CPSW_PN_REG_CTL);
+		rx_enable = !!(val & AM65_CPSW_PN_CTL_IET_PORT_EN);
+		if (rx_enable)
+			break;
+	}
+
+	val = readl(common->cpsw_base + AM65_CPSW_REG_CTL);
+
+	if (rx_enable)
+		val |= AM65_CPSW_CTL_IET_EN;
+	else
+		val &= ~AM65_CPSW_CTL_IET_EN;
+
+	writel(val, common->cpsw_base + AM65_CPSW_REG_CTL);
+	common->iet_enabled = rx_enable;
+}
+
+/* CPSW does not have an IRQ to notify changes to the MAC Merge TX status
+ * (active/inactive), but the preemptible traffic classes should only be
+ * committed to hardware once TX is active. Resort to polling.
+ */
+void am65_cpsw_iet_commit_preemptible_tcs(struct am65_cpsw_port *port)
+{
+	u8 preemptible_tcs;
+	int err;
+	u32 val;
+
+	if (port->qos.link_speed == SPEED_UNKNOWN)
+		return;
+
+	val = readl(port->port_base + AM65_CPSW_PN_REG_CTL);
+	if (!(val & AM65_CPSW_PN_CTL_IET_PORT_EN))
+		return;
+
+	/* update common IET enable */
+	am65_cpsw_iet_common_enable(port->common);
+
+	/* update verify count */
+	err = am65_cpsw_iet_set_verify_timeout_count(port);
+	if (err) {
+		netdev_err(port->ndev, "couldn't set verify count: %d\n", err);
+		return;
+	}
+
+	val = readl(port->port_base + AM65_CPSW_PN_REG_IET_CTRL);
+	if (!(val & AM65_CPSW_PN_IET_MAC_DISABLEVERIFY)) {
+		err = am65_cpsw_iet_verify_wait(port);
+		if (err)
+			return;
+	}
+
+	preemptible_tcs = port->qos.iet.preemptible_tcs;
+	am65_cpsw_iet_set_preempt_mask(port, preemptible_tcs);
+}
+
+static void am65_cpsw_iet_change_preemptible_tcs(struct am65_cpsw_port *port, u8 preemptible_tcs)
+{
+	struct am65_cpsw_ndev_priv *priv = am65_ndev_to_priv(port->ndev);
+
+	port->qos.iet.preemptible_tcs = preemptible_tcs;
+	mutex_lock(&priv->mm_lock);
+	am65_cpsw_iet_commit_preemptible_tcs(port);
+	mutex_unlock(&priv->mm_lock);
+}
+
+static void am65_cpsw_iet_link_state_update(struct net_device *ndev)
+{
+	struct am65_cpsw_ndev_priv *priv = am65_ndev_to_priv(ndev);
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+
+	mutex_lock(&priv->mm_lock);
+	am65_cpsw_iet_commit_preemptible_tcs(port);
+	mutex_unlock(&priv->mm_lock);
+}
+
 static int am65_cpsw_port_est_enabled(struct am65_cpsw_port *port)
 {
 	return port->qos.est_oper || port->qos.est_admin;
@@ -428,7 +804,7 @@ static void am65_cpsw_stop_est(struct net_device *ndev)
 	am65_cpsw_timer_stop(ndev);
 }
 
-static void am65_cpsw_purge_est(struct net_device *ndev)
+static void am65_cpsw_taprio_destroy(struct net_device *ndev)
 {
 	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
 
@@ -439,31 +815,74 @@ static void am65_cpsw_purge_est(struct net_device *ndev)
 
 	port->qos.est_oper = NULL;
 	port->qos.est_admin = NULL;
+
+	am65_cpsw_reset_tc_mqprio(ndev);
 }
 
-static int am65_cpsw_configure_taprio(struct net_device *ndev,
-				      struct am65_cpsw_est *est_new)
+static void am65_cpsw_cp_taprio(struct tc_taprio_qopt_offload *from,
+				struct tc_taprio_qopt_offload *to)
+{
+	int i;
+
+	*to = *from;
+	for (i = 0; i < from->num_entries; i++)
+		to->entries[i] = from->entries[i];
+}
+
+static int am65_cpsw_taprio_replace(struct net_device *ndev,
+				    struct tc_taprio_qopt_offload *taprio)
 {
 	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
+	struct netlink_ext_ack *extack = taprio->mqprio.extack;
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
 	struct am65_cpts *cpts = common->cpts;
-	int ret = 0, tact = TACT_PROG;
+	struct am65_cpsw_est *est_new;
+	int ret, tact;
 
-	am65_cpsw_est_update_state(ndev);
+	if (!netif_running(ndev)) {
+		NL_SET_ERR_MSG_MOD(extack, "interface is down, link speed unknown");
+		return -ENETDOWN;
+	}
 
-	if (est_new->taprio.cmd == TAPRIO_CMD_DESTROY) {
-		am65_cpsw_stop_est(ndev);
-		return ret;
+	if (common->pf_p0_rx_ptype_rrobin) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "p0-rx-ptype-rrobin flag conflicts with taprio qdisc");
+		return -EINVAL;
 	}
 
+	if (port->qos.link_speed == SPEED_UNKNOWN)
+		return -ENOLINK;
+
+	if (taprio->cycle_time_extension) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "cycle time extension not supported");
+		return -EOPNOTSUPP;
+	}
+
+	est_new = devm_kzalloc(&ndev->dev,
+			       struct_size(est_new, taprio.entries, taprio->num_entries),
+			       GFP_KERNEL);
+	if (!est_new)
+		return -ENOMEM;
+
+	ret = am65_cpsw_setup_mqprio(ndev, &taprio->mqprio);
+	if (ret)
+		return ret;
+
+	am65_cpsw_cp_taprio(taprio, &est_new->taprio);
+
+	am65_cpsw_est_update_state(ndev);
+
 	ret = am65_cpsw_est_check_scheds(ndev, est_new);
 	if (ret < 0)
-		return ret;
+		goto fail;
 
 	tact = am65_cpsw_timer_act(ndev, est_new);
 	if (tact == TACT_NEED_STOP) {
-		dev_err(&ndev->dev,
-			"Can't toggle estf timer, stop taprio first");
-		return -EINVAL;
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Can't toggle estf timer, stop taprio first");
+		ret = -EINVAL;
+		goto fail;
 	}
 
 	if (tact == TACT_PROG)
@@ -476,62 +895,26 @@ static int am65_cpsw_configure_taprio(struct net_device *ndev,
 	am65_cpsw_est_set_sched_list(ndev, est_new);
 	am65_cpsw_port_est_assign_buf_num(ndev, est_new->buf);
 
-	am65_cpsw_est_set(ndev, est_new->taprio.cmd == TAPRIO_CMD_REPLACE);
+	am65_cpsw_est_set(ndev, 1);
 
 	if (tact == TACT_PROG) {
 		ret = am65_cpsw_timer_set(ndev, est_new);
 		if (ret) {
-			dev_err(&ndev->dev, "Failed to set cycle time");
-			return ret;
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Failed to set cycle time");
+			goto fail;
 		}
 	}
 
-	return ret;
-}
-
-static void am65_cpsw_cp_taprio(struct tc_taprio_qopt_offload *from,
-				struct tc_taprio_qopt_offload *to)
-{
-	int i;
-
-	*to = *from;
-	for (i = 0; i < from->num_entries; i++)
-		to->entries[i] = from->entries[i];
-}
-
-static int am65_cpsw_set_taprio(struct net_device *ndev, void *type_data)
-{
-	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
-	struct tc_taprio_qopt_offload *taprio = type_data;
-	struct am65_cpsw_est *est_new;
-	int ret = 0;
-
-	if (taprio->cycle_time_extension) {
-		dev_err(&ndev->dev, "Failed to set cycle time extension");
-		return -EOPNOTSUPP;
-	}
-
-	est_new = devm_kzalloc(&ndev->dev,
-			       struct_size(est_new, taprio.entries, taprio->num_entries),
-			       GFP_KERNEL);
-	if (!est_new)
-		return -ENOMEM;
-
-	am65_cpsw_cp_taprio(taprio, &est_new->taprio);
-	ret = am65_cpsw_configure_taprio(ndev, est_new);
-	if (!ret) {
-		if (taprio->cmd == TAPRIO_CMD_REPLACE) {
-			devm_kfree(&ndev->dev, port->qos.est_admin);
+	devm_kfree(&ndev->dev, port->qos.est_admin);
+	port->qos.est_admin = est_new;
+	am65_cpsw_iet_change_preemptible_tcs(port, taprio->mqprio.preemptible_tcs);
 
-			port->qos.est_admin = est_new;
-		} else {
-			devm_kfree(&ndev->dev, est_new);
-			am65_cpsw_purge_est(ndev);
-		}
-	} else {
-		devm_kfree(&ndev->dev, est_new);
-	}
+	return 0;
 
+fail:
+	am65_cpsw_reset_tc_mqprio(ndev);
+	devm_kfree(&ndev->dev, est_new);
 	return ret;
 }
 
@@ -541,7 +924,6 @@ static void am65_cpsw_est_link_up(struct net_device *ndev, int link_speed)
 	ktime_t cur_time;
 	s64 delta;
 
-	port->qos.link_speed = link_speed;
 	if (!am65_cpsw_port_est_enabled(port))
 		return;
 
@@ -558,37 +940,26 @@ static void am65_cpsw_est_link_up(struct net_device *ndev, int link_speed)
 	return;
 
 purge_est:
-	am65_cpsw_purge_est(ndev);
+	am65_cpsw_taprio_destroy(ndev);
 }
 
 static int am65_cpsw_setup_taprio(struct net_device *ndev, void *type_data)
 {
-	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
 	struct tc_taprio_qopt_offload *taprio = type_data;
-	struct am65_cpsw_common *common = port->common;
-
-	if (taprio->cmd != TAPRIO_CMD_REPLACE &&
-	    taprio->cmd != TAPRIO_CMD_DESTROY)
-		return -EOPNOTSUPP;
-
-	if (!IS_ENABLED(CONFIG_TI_AM65_CPSW_TAS))
-		return -ENODEV;
-
-	if (!netif_running(ndev)) {
-		dev_err(&ndev->dev, "interface is down, link speed unknown\n");
-		return -ENETDOWN;
-	}
-
-	if (common->pf_p0_rx_ptype_rrobin) {
-		dev_err(&ndev->dev,
-			"p0-rx-ptype-rrobin flag conflicts with taprio qdisc\n");
-		return -EINVAL;
+	int err = 0;
+
+	switch (taprio->cmd) {
+	case TAPRIO_CMD_REPLACE:
+		err = am65_cpsw_taprio_replace(ndev, taprio);
+		break;
+	case TAPRIO_CMD_DESTROY:
+		am65_cpsw_taprio_destroy(ndev);
+		break;
+	default:
+		err = -EOPNOTSUPP;
 	}
 
-	if (port->qos.link_speed == SPEED_UNKNOWN)
-		return -ENOLINK;
-
-	return am65_cpsw_set_taprio(ndev, type_data);
+	return err;
 }
 
 static int am65_cpsw_tc_query_caps(struct net_device *ndev, void *type_data)
@@ -596,12 +967,17 @@ static int am65_cpsw_tc_query_caps(struct net_device *ndev, void *type_data)
 	struct tc_query_caps_base *base = type_data;
 
 	switch (base->type) {
+	case TC_SETUP_QDISC_MQPRIO: {
+		struct tc_mqprio_caps *caps = base->caps;
+
+		caps->validate_queue_counts = true;
+
+		return 0;
+	}
+
 	case TC_SETUP_QDISC_TAPRIO: {
 		struct tc_taprio_caps *caps = base->caps;
 
-		if (!IS_ENABLED(CONFIG_TI_AM65_CPSW_TAS))
-			return -EOPNOTSUPP;
-
 		caps->gate_mask_per_txq = true;
 
 		return 0;
@@ -787,55 +1163,6 @@ static int am65_cpsw_qos_setup_tc_block(struct net_device *ndev, struct flow_blo
 					  port, port, true);
 }
 
-int am65_cpsw_qos_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
-			       void *type_data)
-{
-	switch (type) {
-	case TC_QUERY_CAPS:
-		return am65_cpsw_tc_query_caps(ndev, type_data);
-	case TC_SETUP_QDISC_TAPRIO:
-		return am65_cpsw_setup_taprio(ndev, type_data);
-	case TC_SETUP_BLOCK:
-		return am65_cpsw_qos_setup_tc_block(ndev, type_data);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-void am65_cpsw_qos_link_up(struct net_device *ndev, int link_speed)
-{
-	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
-
-	if (!IS_ENABLED(CONFIG_TI_AM65_CPSW_TAS))
-		return;
-
-	am65_cpsw_est_link_up(ndev, link_speed);
-	port->qos.link_down_time = 0;
-}
-
-void am65_cpsw_qos_link_down(struct net_device *ndev)
-{
-	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
-
-	if (!IS_ENABLED(CONFIG_TI_AM65_CPSW_TAS))
-		return;
-
-	if (!port->qos.link_down_time)
-		port->qos.link_down_time = ktime_get();
-
-	port->qos.link_speed = SPEED_UNKNOWN;
-}
-
-static u32
-am65_cpsw_qos_tx_rate_calc(u32 rate_mbps, unsigned long bus_freq)
-{
-	u32 ir;
-
-	bus_freq /= 1000000;
-	ir = DIV_ROUND_UP(((u64)rate_mbps * 32768),  bus_freq);
-	return ir;
-}
-
 static void
 am65_cpsw_qos_tx_p0_rate_apply(struct am65_cpsw_common *common,
 			       int tx_ch, u32 rate_mbps)
@@ -937,3 +1264,44 @@ void am65_cpsw_qos_tx_p0_rate_init(struct am65_cpsw_common *common)
 		       host->port_base + AM65_CPSW_PN_REG_PRI_CIR(tx_ch));
 	}
 }
+
+int am65_cpsw_qos_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
+			       void *type_data)
+{
+	switch (type) {
+	case TC_QUERY_CAPS:
+		return am65_cpsw_tc_query_caps(ndev, type_data);
+	case TC_SETUP_QDISC_TAPRIO:
+		return am65_cpsw_setup_taprio(ndev, type_data);
+	case TC_SETUP_QDISC_MQPRIO:
+		return am65_cpsw_setup_mqprio(ndev, type_data);
+	case TC_SETUP_BLOCK:
+		return am65_cpsw_qos_setup_tc_block(ndev, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+void am65_cpsw_qos_link_up(struct net_device *ndev, int link_speed)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+
+	port->qos.link_speed = link_speed;
+	am65_cpsw_tx_pn_shaper_apply(port);
+	am65_cpsw_iet_link_state_update(ndev);
+
+	am65_cpsw_est_link_up(ndev, link_speed);
+	port->qos.link_down_time = 0;
+}
+
+void am65_cpsw_qos_link_down(struct net_device *ndev)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+
+	port->qos.link_speed = SPEED_UNKNOWN;
+	am65_cpsw_tx_pn_shaper_apply(port);
+	am65_cpsw_iet_link_state_update(ndev);
+
+	if (!port->qos.link_down_time)
+		port->qos.link_down_time = ktime_get();
+}
diff --git a/drivers/net/ethernet/ti/am65-cpsw-qos.h b/drivers/net/ethernet/ti/am65-cpsw-qos.h
index 0cc2a3b3d7f9..b328e56c5b2b 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-qos.h
+++ b/drivers/net/ethernet/ti/am65-cpsw-qos.h
@@ -9,6 +9,7 @@
 #include <net/pkt_sched.h>
 
 struct am65_cpsw_common;
+struct am65_cpsw_port;
 
 struct am65_cpsw_est {
 	int buf;
@@ -16,6 +17,18 @@ struct am65_cpsw_est {
 	struct tc_taprio_qopt_offload taprio;
 };
 
+struct am65_cpsw_mqprio {
+	struct tc_mqprio_qopt_offload mqprio_hw;
+	u64 max_rate_total;
+	bool shaper_en;
+};
+
+struct am65_cpsw_iet {
+	u8 preemptible_tcs;
+	u32 original_max_blks;
+	int verify_time_ms;
+};
+
 struct am65_cpsw_ale_ratelimit {
 	unsigned long cookie;
 	u64 rate_packet_ps;
@@ -26,16 +39,189 @@ struct am65_cpsw_qos {
 	struct am65_cpsw_est *est_oper;
 	ktime_t link_down_time;
 	int link_speed;
+	struct am65_cpsw_mqprio mqprio;
+	struct am65_cpsw_iet iet;
 
 	struct am65_cpsw_ale_ratelimit ale_bc_ratelimit;
 	struct am65_cpsw_ale_ratelimit ale_mc_ratelimit;
 };
 
+#define AM65_CPSW_REG_CTL			0x004
+#define AM65_CPSW_PN_REG_CTL			0x004
+#define AM65_CPSW_PN_REG_FIFO_STATUS		0x050
+#define AM65_CPSW_PN_REG_EST_CTL		0x060
+#define AM65_CPSW_PN_REG_PRI_CIR(pri)		(0x140 + 4 * (pri))
+#define AM65_CPSW_P0_REG_PRI_EIR(pri)		(0x160 + 4 * (pri))
+
+#define AM65_CPSW_PN_REG_CTL			0x004
+#define AM65_CPSW_PN_REG_TX_PRI_MAP		0x018
+#define AM65_CPSW_PN_REG_RX_PRI_MAP		0x020
+#define AM65_CPSW_PN_REG_FIFO_STATUS		0x050
+#define AM65_CPSW_PN_REG_EST_CTL		0x060
+#define AM65_CPSW_PN_REG_PRI_CIR(pri)		(0x140 + 4 * (pri))
+#define AM65_CPSW_PN_REG_PRI_EIR(pri)		(0x160 + 4 * (pri))
+
+/* AM65_CPSW_REG_CTL register fields */
+#define AM65_CPSW_CTL_EST_EN			BIT(18)
+
+/* AM65_CPSW_PN_REG_CTL register fields */
+#define AM65_CPSW_PN_CTL_EST_PORT_EN		BIT(17)
+
+/* AM65_CPSW_PN_REG_EST_CTL register fields */
+#define AM65_CPSW_PN_EST_ONEBUF			BIT(0)
+#define AM65_CPSW_PN_EST_BUFSEL			BIT(1)
+#define AM65_CPSW_PN_EST_TS_EN			BIT(2)
+#define AM65_CPSW_PN_EST_TS_FIRST		BIT(3)
+#define AM65_CPSW_PN_EST_ONEPRI			BIT(4)
+#define AM65_CPSW_PN_EST_TS_PRI_MSK		GENMASK(7, 5)
+
+/* AM65_CPSW_PN_REG_FIFO_STATUS register fields */
+#define AM65_CPSW_PN_FST_TX_PRI_ACTIVE_MSK	GENMASK(7, 0)
+#define AM65_CPSW_PN_FST_TX_E_MAC_ALLOW_MSK	GENMASK(15, 8)
+#define AM65_CPSW_PN_FST_EST_CNT_ERR		BIT(16)
+#define AM65_CPSW_PN_FST_EST_ADD_ERR		BIT(17)
+#define AM65_CPSW_PN_FST_EST_BUFACT		BIT(18)
+
+/* EST FETCH COMMAND RAM */
+#define AM65_CPSW_FETCH_RAM_CMD_NUM		0x80
+#define AM65_CPSW_FETCH_CNT_MSK			GENMASK(21, 8)
+#define AM65_CPSW_FETCH_CNT_MAX			(AM65_CPSW_FETCH_CNT_MSK >> 8)
+#define AM65_CPSW_FETCH_CNT_OFFSET		8
+#define AM65_CPSW_FETCH_ALLOW_MSK		GENMASK(7, 0)
+#define AM65_CPSW_FETCH_ALLOW_MAX		AM65_CPSW_FETCH_ALLOW_MSK
+
+/* number of priority queues per port FIFO */
+#define AM65_CPSW_PN_FIFO_PRIO_NUM		8
+
+#if IS_ENABLED(CONFIG_TI_AM65_CPSW_QOS)
 int am65_cpsw_qos_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 			       void *type_data);
 void am65_cpsw_qos_link_up(struct net_device *ndev, int link_speed);
 void am65_cpsw_qos_link_down(struct net_device *ndev);
 int am65_cpsw_qos_ndo_tx_p0_set_maxrate(struct net_device *ndev, int queue, u32 rate_mbps);
 void am65_cpsw_qos_tx_p0_rate_init(struct am65_cpsw_common *common);
+void am65_cpsw_iet_commit_preemptible_tcs(struct am65_cpsw_port *port);
+void am65_cpsw_iet_common_enable(struct am65_cpsw_common *common);
+#else
+static inline int am65_cpsw_qos_ndo_setup_tc(struct net_device *ndev,
+					     enum tc_setup_type type,
+					     void *type_data)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void am65_cpsw_qos_link_up(struct net_device *ndev,
+					 int link_speed)
+{ }
+
+static inline void am65_cpsw_qos_link_down(struct net_device *ndev)
+{ }
+
+static inline int am65_cpsw_qos_ndo_tx_p0_set_maxrate(struct net_device *ndev,
+						      int queue,
+						      u32 rate_mbps)
+{
+	return 0;
+}
+
+static inline void am65_cpsw_qos_tx_p0_rate_init(struct am65_cpsw_common *common)
+{ }
+static inline void am65_cpsw_iet_commit_preemptible_tcs(struct am65_cpsw_port *port)
+{ }
+static inline void am65_cpsw_iet_common_enable(struct am65_cpsw_common *common)
+{ }
+#endif
+
+#define AM65_CPSW_REG_CTL			0x004
+#define AM65_CPSW_PN_REG_CTL			0x004
+#define AM65_CPSW_PN_REG_MAX_BLKS		0x008
+#define AM65_CPSW_PN_REG_TX_PRI_MAP		0x018
+#define AM65_CPSW_PN_REG_RX_PRI_MAP		0x020
+#define AM65_CPSW_PN_REG_IET_CTRL		0x040
+#define AM65_CPSW_PN_REG_IET_STATUS		0x044
+#define AM65_CPSW_PN_REG_IET_VERIFY		0x048
+#define AM65_CPSW_PN_REG_FIFO_STATUS		0x050
+#define AM65_CPSW_PN_REG_EST_CTL		0x060
+#define AM65_CPSW_PN_REG_PRI_CIR(pri)		(0x140 + 4 * (pri))
+#define AM65_CPSW_PN_REG_PRI_EIR(pri)		(0x160 + 4 * (pri))
+
+/* AM65_CPSW_REG_CTL register fields */
+#define AM65_CPSW_CTL_IET_EN			BIT(17)
+#define AM65_CPSW_CTL_EST_EN			BIT(18)
+
+/* AM65_CPSW_PN_REG_CTL register fields */
+#define AM65_CPSW_PN_CTL_IET_PORT_EN		BIT(16)
+#define AM65_CPSW_PN_CTL_EST_PORT_EN		BIT(17)
+
+/* AM65_CPSW_PN_REG_EST_CTL register fields */
+#define AM65_CPSW_PN_EST_ONEBUF			BIT(0)
+#define AM65_CPSW_PN_EST_BUFSEL			BIT(1)
+#define AM65_CPSW_PN_EST_TS_EN			BIT(2)
+#define AM65_CPSW_PN_EST_TS_FIRST		BIT(3)
+#define AM65_CPSW_PN_EST_ONEPRI			BIT(4)
+#define AM65_CPSW_PN_EST_TS_PRI_MSK		GENMASK(7, 5)
+
+/* AM65_CPSW_PN_REG_IET_CTRL register fields */
+#define AM65_CPSW_PN_IET_MAC_PENABLE		BIT(0)
+#define AM65_CPSW_PN_IET_MAC_DISABLEVERIFY	BIT(2)
+#define AM65_CPSW_PN_IET_MAC_LINKFAIL		BIT(3)
+#define AM65_CPSW_PN_IET_MAC_MAC_ADDFRAGSIZE_MASK	GENMASK(10, 8)
+#define AM65_CPSW_PN_IET_MAC_MAC_ADDFRAGSIZE_OFFSET	8
+#define AM65_CPSW_PN_IET_MAC_PREMPT_MASK		GENMASK(23, 16)
+#define AM65_CPSW_PN_IET_MAC_PREMPT_OFFSET		16
+
+#define AM65_CPSW_PN_IET_MAC_SET_ADDFRAGSIZE(n)	(((n) << AM65_CPSW_PN_IET_MAC_MAC_ADDFRAGSIZE_OFFSET) & \
+						  AM65_CPSW_PN_IET_MAC_MAC_ADDFRAGSIZE_MASK)
+#define AM65_CPSW_PN_IET_MAC_GET_ADDFRAGSIZE(n)	(((n) & AM65_CPSW_PN_IET_MAC_MAC_ADDFRAGSIZE_MASK) >> \
+						  AM65_CPSW_PN_IET_MAC_MAC_ADDFRAGSIZE_OFFSET)
+#define AM65_CPSW_PN_IET_MAC_SET_PREEMPT(n)	(((n) << AM65_CPSW_PN_IET_MAC_PREMPT_OFFSET) & \
+						 AM65_CPSW_PN_IET_MAC_PREMPT_MASK)
+#define AM65_CPSW_PN_IET_MAC_GET_PREEMPT(n)	(((n) & AM65_CPSW_PN_IET_MAC_PREMPT_MASK) >> \
+						 AM65_CPSW_PN_IET_MAC_PREMPT_OFFSET)
+
+/* AM65_CPSW_PN_REG_IET_STATUS register fields */
+#define AM65_CPSW_PN_MAC_STATUS			GENMASK(3, 0)
+#define AM65_CPSW_PN_MAC_VERIFIED		BIT(0)
+#define AM65_CPSW_PN_MAC_VERIFY_FAIL		BIT(1)
+#define AM65_CPSW_PN_MAC_RESPOND_ERR		BIT(2)
+#define AM65_CPSW_PN_MAC_VERIFY_ERR		BIT(3)
+
+/* AM65_CPSW_PN_REG_IET_VERIFY register fields */
+#define AM65_CPSW_PN_MAC_VERIFY_CNT_MASK	GENMASK(23, 0)
+#define AM65_CPSW_PN_MAC_GET_VERIFY_CNT(n)	((n) & AM65_CPSW_PN_MAC_VERIFY_CNT_MASK)
+/* 10 msec converted to NSEC */
+#define AM65_CPSW_IET_VERIFY_CNT_MS		(10)
+#define AM65_CPSW_IET_VERIFY_CNT_NS		(AM65_CPSW_IET_VERIFY_CNT_MS * \
+						 NSEC_PER_MSEC)
+
+/* AM65_CPSW_PN_REG_FIFO_STATUS register fields */
+#define AM65_CPSW_PN_FST_TX_PRI_ACTIVE_MSK	GENMASK(7, 0)
+#define AM65_CPSW_PN_FST_TX_E_MAC_ALLOW_MSK	GENMASK(15, 8)
+#define AM65_CPSW_PN_FST_EST_CNT_ERR		BIT(16)
+#define AM65_CPSW_PN_FST_EST_ADD_ERR		BIT(17)
+#define AM65_CPSW_PN_FST_EST_BUFACT		BIT(18)
+
+/* EST FETCH COMMAND RAM */
+#define AM65_CPSW_FETCH_RAM_CMD_NUM		0x80
+#define AM65_CPSW_FETCH_CNT_MSK			GENMASK(21, 8)
+#define AM65_CPSW_FETCH_CNT_MAX			(AM65_CPSW_FETCH_CNT_MSK >> 8)
+#define AM65_CPSW_FETCH_CNT_OFFSET		8
+#define AM65_CPSW_FETCH_ALLOW_MSK		GENMASK(7, 0)
+#define AM65_CPSW_FETCH_ALLOW_MAX		AM65_CPSW_FETCH_ALLOW_MSK
+
+/* AM65_CPSW_PN_REG_MAX_BLKS fields for IET and No IET cases */
+/* 7 blocks for pn_rx_max_blks, 13 for pn_tx_max_blks*/
+#define AM65_CPSW_PN_TX_RX_MAX_BLKS_IET		0xD07
+
+/* Slave IET Stats. register offsets */
+#define AM65_CPSW_STATN_IET_RX_ASSEMBLY_ERROR	0x140
+#define AM65_CPSW_STATN_IET_RX_ASSEMBLY_OK	0x144
+#define AM65_CPSW_STATN_IET_RX_SMD_ERROR	0x148
+#define AM65_CPSW_STATN_IET_RX_FRAG		0x14c
+#define AM65_CPSW_STATN_IET_TX_HOLD		0x150
+#define AM65_CPSW_STATN_IET_TX_FRAG		0x154
+
+/* number of priority queues per port FIFO */
+#define AM65_CPSW_PN_FIFO_PRIO_NUM		8
 
 #endif /* AM65_CPSW_QOS_H_ */
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index ca4d4548f85e..ea85c6dd5484 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1722,14 +1722,20 @@ clean_runtime_disable_ret:
 	return ret;
 }
 
-static int cpsw_remove(struct platform_device *pdev)
+static void cpsw_remove(struct platform_device *pdev)
 {
 	struct cpsw_common *cpsw = platform_get_drvdata(pdev);
 	int i, ret;
 
 	ret = pm_runtime_resume_and_get(&pdev->dev);
-	if (ret < 0)
-		return ret;
+	if (ret < 0) {
+		/* Note, if this error path is taken, we're leaking some
+		 * resources.
+		 */
+		dev_err(&pdev->dev, "Failed to resume device (%pe)\n",
+			ERR_PTR(ret));
+		return;
+	}
 
 	for (i = 0; i < cpsw->data.slaves; i++)
 		if (cpsw->slaves[i].ndev)
@@ -1740,7 +1746,6 @@ static int cpsw_remove(struct platform_device *pdev)
 	cpsw_remove_dt(pdev);
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -1795,7 +1800,7 @@ static struct platform_driver cpsw_driver = {
 		.of_match_table = cpsw_of_mtable,
 	},
 	.probe = cpsw_probe,
-	.remove = cpsw_remove,
+	.remove_new = cpsw_remove,
 };
 
 module_platform_driver(cpsw_driver);
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index 0e4f526b1753..498c50c6d1a7 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -2037,14 +2037,20 @@ clean_dt_ret:
 	return ret;
 }
 
-static int cpsw_remove(struct platform_device *pdev)
+static void cpsw_remove(struct platform_device *pdev)
 {
 	struct cpsw_common *cpsw = platform_get_drvdata(pdev);
 	int ret;
 
 	ret = pm_runtime_resume_and_get(&pdev->dev);
-	if (ret < 0)
-		return ret;
+	if (ret < 0) {
+		/* Note, if this error path is taken, we're leaking some
+		 * resources.
+		 */
+		dev_err(&pdev->dev, "Failed to resume device (%pe)\n",
+			ERR_PTR(ret));
+		return;
+	}
 
 	cpsw_unregister_notifiers(cpsw);
 	cpsw_unregister_devlink(cpsw);
@@ -2055,7 +2061,6 @@ static int cpsw_remove(struct platform_device *pdev)
 	cpsw_remove_dt(cpsw);
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-	return 0;
 }
 
 static int __maybe_unused cpsw_suspend(struct device *dev)
@@ -2116,7 +2121,7 @@ static struct platform_driver cpsw_driver = {
 		.of_match_table = cpsw_of_mtable,
 	},
 	.probe = cpsw_probe,
-	.remove = cpsw_remove,
+	.remove_new = cpsw_remove,
 };
 
 module_platform_driver(cpsw_driver);
diff --git a/drivers/net/ethernet/ti/davinci_mdio.c b/drivers/net/ethernet/ti/davinci_mdio.c
index 628c87dc1d28..8e07d4a1b6ba 100644
--- a/drivers/net/ethernet/ti/davinci_mdio.c
+++ b/drivers/net/ethernet/ti/davinci_mdio.c
@@ -511,16 +511,12 @@ static const struct k3_mdio_soc_data am65_mdio_soc_data = {
 };
 
 static const struct soc_device_attribute k3_mdio_socinfo[] = {
-	{ .family = "AM62X", .revision = "SR1.0", .data = &am65_mdio_soc_data },
-	{ .family = "AM64X", .revision = "SR1.0", .data = &am65_mdio_soc_data },
-	{ .family = "AM64X", .revision = "SR2.0", .data = &am65_mdio_soc_data },
-	{ .family = "AM65X", .revision = "SR1.0", .data = &am65_mdio_soc_data },
-	{ .family = "AM65X", .revision = "SR2.0", .data = &am65_mdio_soc_data },
-	{ .family = "J7200", .revision = "SR1.0", .data = &am65_mdio_soc_data },
-	{ .family = "J7200", .revision = "SR2.0", .data = &am65_mdio_soc_data },
-	{ .family = "J721E", .revision = "SR1.0", .data = &am65_mdio_soc_data },
-	{ .family = "J721E", .revision = "SR2.0", .data = &am65_mdio_soc_data },
-	{ .family = "J721S2", .revision = "SR1.0", .data = &am65_mdio_soc_data},
+	{ .family = "AM62X", .data = &am65_mdio_soc_data },
+	{ .family = "AM64X", .data = &am65_mdio_soc_data },
+	{ .family = "AM65X", .data = &am65_mdio_soc_data },
+	{ .family = "J7200", .data = &am65_mdio_soc_data },
+	{ .family = "J721E", .data = &am65_mdio_soc_data },
+	{ .family = "J721S2", .data = &am65_mdio_soc_data },
 	{ /* sentinel */ },
 };
 
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 6c4b64227ac8..411898a4f38c 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -2063,7 +2063,7 @@ static int prueth_probe(struct platform_device *pdev)
 				       &prueth->shram);
 	if (ret) {
 		dev_err(dev, "unable to get PRUSS SHRD RAM2: %d\n", ret);
-		pruss_put(prueth->pruss);
+		goto put_pruss;
 	}
 
 	prueth->sram_pool = of_gen_pool_get(np, "sram", 0);
@@ -2105,10 +2105,7 @@ static int prueth_probe(struct platform_device *pdev)
 	prueth->iep1 = icss_iep_get_idx(np, 1);
 	if (IS_ERR(prueth->iep1)) {
 		ret = dev_err_probe(dev, PTR_ERR(prueth->iep1), "iep1 get failed\n");
-		icss_iep_put(prueth->iep0);
-		prueth->iep0 = NULL;
-		prueth->iep1 = NULL;
-		goto free_pool;
+		goto put_iep0;
 	}
 
 	if (prueth->pdata.quirk_10m_link_issue) {
@@ -2205,6 +2202,12 @@ netdev_exit:
 exit_iep:
 	if (prueth->pdata.quirk_10m_link_issue)
 		icss_iep_exit_fw(prueth->iep1);
+	icss_iep_put(prueth->iep1);
+
+put_iep0:
+	icss_iep_put(prueth->iep0);
+	prueth->iep0 = NULL;
+	prueth->iep1 = NULL;
 
 free_pool:
 	gen_pool_free(prueth->sram_pool,
@@ -2212,6 +2215,8 @@ free_pool:
 
 put_mem:
 	pruss_release_mem_region(prueth->pruss, &prueth->shram);
+
+put_pruss:
 	pruss_put(prueth->pruss);
 
 put_cores:
diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
index 9d535ae59626..d5b75af163d3 100644
--- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c
+++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
@@ -93,12 +93,13 @@ static void gelic_card_get_ether_port_status(struct gelic_card *card,
  * gelic_descr_get_status -- returns the status of a descriptor
  * @descr: descriptor to look at
  *
- * returns the status as in the dmac_cmd_status field of the descriptor
+ * returns the status as in the hw_regs.dmac_cmd_status field of the descriptor
  */
 static enum gelic_descr_dma_status
 gelic_descr_get_status(struct gelic_descr *descr)
 {
-	return be32_to_cpu(descr->dmac_cmd_status) & GELIC_DESCR_DMA_STAT_MASK;
+	return be32_to_cpu(descr->hw_regs.dmac_cmd_status) &
+		GELIC_DESCR_DMA_STAT_MASK;
 }
 
 static int gelic_card_set_link_mode(struct gelic_card *card, int mode)
@@ -152,15 +153,15 @@ static void gelic_card_enable_rxdmac(struct gelic_card *card)
 	if (gelic_descr_get_status(card->rx_chain.head) !=
 	    GELIC_DESCR_DMA_CARDOWNED) {
 		printk(KERN_ERR "%s: status=%x\n", __func__,
-		       be32_to_cpu(card->rx_chain.head->dmac_cmd_status));
+		       be32_to_cpu(card->rx_chain.head->hw_regs.dmac_cmd_status));
 		printk(KERN_ERR "%s: nextphy=%x\n", __func__,
-		       be32_to_cpu(card->rx_chain.head->next_descr_addr));
+		       be32_to_cpu(card->rx_chain.head->hw_regs.next_descr_addr));
 		printk(KERN_ERR "%s: head=%p\n", __func__,
 		       card->rx_chain.head);
 	}
 #endif
 	status = lv1_net_start_rx_dma(bus_id(card), dev_id(card),
-				card->rx_chain.head->bus_addr, 0);
+				card->rx_chain.head->link.cpu_addr, 0);
 	if (status)
 		dev_info(ctodev(card),
 			 "lv1_net_start_rx_dma failed, status=%d\n", status);
@@ -195,8 +196,8 @@ static void gelic_card_disable_rxdmac(struct gelic_card *card)
 static void gelic_descr_set_status(struct gelic_descr *descr,
 				   enum gelic_descr_dma_status status)
 {
-	descr->dmac_cmd_status = cpu_to_be32(status |
-			(be32_to_cpu(descr->dmac_cmd_status) &
+	descr->hw_regs.dmac_cmd_status = cpu_to_be32(status |
+			(be32_to_cpu(descr->hw_regs.dmac_cmd_status) &
 			 ~GELIC_DESCR_DMA_STAT_MASK));
 	/*
 	 * dma_cmd_status field is used to indicate whether the descriptor
@@ -224,13 +225,14 @@ static void gelic_card_reset_chain(struct gelic_card *card,
 
 	for (descr = start_descr; start_descr != descr->next; descr++) {
 		gelic_descr_set_status(descr, GELIC_DESCR_DMA_CARDOWNED);
-		descr->next_descr_addr = cpu_to_be32(descr->next->bus_addr);
+		descr->hw_regs.next_descr_addr
+			= cpu_to_be32(descr->next->link.cpu_addr);
 	}
 
 	chain->head = start_descr;
 	chain->tail = (descr - 1);
 
-	(descr - 1)->next_descr_addr = 0;
+	(descr - 1)->hw_regs.next_descr_addr = 0;
 }
 
 void gelic_card_up(struct gelic_card *card)
@@ -286,10 +288,12 @@ static void gelic_card_free_chain(struct gelic_card *card,
 {
 	struct gelic_descr *descr;
 
-	for (descr = descr_in; descr && descr->bus_addr; descr = descr->next) {
-		dma_unmap_single(ctodev(card), descr->bus_addr,
-				 GELIC_DESCR_SIZE, DMA_BIDIRECTIONAL);
-		descr->bus_addr = 0;
+	for (descr = descr_in; descr && descr->link.cpu_addr;
+		descr = descr->next) {
+		dma_unmap_single(ctodev(card), descr->link.cpu_addr,
+				 descr->link.size, DMA_BIDIRECTIONAL);
+		descr->link.cpu_addr = 0;
+		descr->link.size = 0;
 	}
 }
 
@@ -317,17 +321,21 @@ static int gelic_card_init_chain(struct gelic_card *card,
 
 	/* set up the hardware pointers in each descriptor */
 	for (i = 0; i < no; i++, descr++) {
-		dma_addr_t cpu_addr;
-
 		gelic_descr_set_status(descr, GELIC_DESCR_DMA_NOT_IN_USE);
 
-		cpu_addr = dma_map_single(ctodev(card), descr,
-					  GELIC_DESCR_SIZE, DMA_BIDIRECTIONAL);
+		descr->link.size = sizeof(struct gelic_hw_regs);
+		descr->link.cpu_addr = dma_map_single(ctodev(card), descr,
+					  descr->link.size, DMA_BIDIRECTIONAL);
 
-		if (dma_mapping_error(ctodev(card), cpu_addr))
-			goto iommu_error;
+		if (dma_mapping_error(ctodev(card), descr->link.cpu_addr)) {
+			for (i--, descr--; 0 <= i; i--, descr--) {
+				dma_unmap_single(ctodev(card),
+					descr->link.cpu_addr, descr->link.size,
+					DMA_BIDIRECTIONAL);
+			}
+			return -ENOMEM;
+		}
 
-		descr->bus_addr = cpu_to_be32(cpu_addr);
 		descr->next = descr + 1;
 		descr->prev = descr - 1;
 	}
@@ -338,24 +346,17 @@ static int gelic_card_init_chain(struct gelic_card *card,
 	/* chain bus addr of hw descriptor */
 	descr = start_descr;
 	for (i = 0; i < no; i++, descr++) {
-		descr->next_descr_addr = cpu_to_be32(descr->next->bus_addr);
+		descr->hw_regs.next_descr_addr =
+			cpu_to_be32(descr->next->link.cpu_addr);
 	}
 
 	chain->head = start_descr;
 	chain->tail = start_descr;
 
 	/* do not chain last hw descriptor */
-	(descr - 1)->next_descr_addr = 0;
+	(descr - 1)->hw_regs.next_descr_addr = 0;
 
 	return 0;
-
-iommu_error:
-	for (i--, descr--; 0 <= i; i--, descr--)
-		if (descr->bus_addr)
-			dma_unmap_single(ctodev(card), descr->bus_addr,
-					 GELIC_DESCR_SIZE,
-					 DMA_BIDIRECTIONAL);
-	return -ENOMEM;
 }
 
 /**
@@ -385,14 +386,16 @@ static int gelic_descr_prepare_rx(struct gelic_card *card,
 
 	descr->skb = netdev_alloc_skb(*card->netdev, rx_skb_size);
 	if (!descr->skb) {
-		descr->buf_addr = 0; /* tell DMAC don't touch memory */
+		descr->hw_regs.payload.dev_addr = 0; /* tell DMAC don't touch memory */
 		return -ENOMEM;
 	}
-	descr->buf_size = cpu_to_be32(rx_skb_size);
-	descr->dmac_cmd_status = 0;
-	descr->result_size = 0;
-	descr->valid_size = 0;
-	descr->data_error = 0;
+	descr->hw_regs.dmac_cmd_status = 0;
+	descr->hw_regs.result_size = 0;
+	descr->hw_regs.valid_size = 0;
+	descr->hw_regs.data_error = 0;
+	descr->hw_regs.payload.dev_addr = 0;
+	descr->hw_regs.payload.size = 0;
+	descr->skb = NULL;
 
 	offset = ((unsigned long)descr->skb->data) &
 		(GELIC_NET_RXBUF_ALIGN - 1);
@@ -401,7 +404,7 @@ static int gelic_descr_prepare_rx(struct gelic_card *card,
 	/* io-mmu-map the skb */
 	cpu_addr = dma_map_single(ctodev(card), descr->skb->data,
 				  GELIC_NET_MAX_FRAME, DMA_FROM_DEVICE);
-	descr->buf_addr = cpu_to_be32(cpu_addr);
+	descr->hw_regs.payload.dev_addr = cpu_to_be32(cpu_addr);
 	if (dma_mapping_error(ctodev(card), cpu_addr)) {
 		dev_kfree_skb_any(descr->skb);
 		descr->skb = NULL;
@@ -409,10 +412,14 @@ static int gelic_descr_prepare_rx(struct gelic_card *card,
 			 "%s:Could not iommu-map rx buffer\n", __func__);
 		gelic_descr_set_status(descr, GELIC_DESCR_DMA_NOT_IN_USE);
 		return -ENOMEM;
-	} else {
-		gelic_descr_set_status(descr, GELIC_DESCR_DMA_CARDOWNED);
-		return 0;
 	}
+
+	descr->hw_regs.payload.size = cpu_to_be32(GELIC_NET_MAX_FRAME);
+	descr->hw_regs.payload.dev_addr = cpu_to_be32(cpu_addr);
+
+	gelic_descr_set_status(descr, GELIC_DESCR_DMA_CARDOWNED);
+
+	return 0;
 }
 
 /**
@@ -427,14 +434,15 @@ static void gelic_card_release_rx_chain(struct gelic_card *card)
 	do {
 		if (descr->skb) {
 			dma_unmap_single(ctodev(card),
-					 be32_to_cpu(descr->buf_addr),
-					 descr->skb->len,
-					 DMA_FROM_DEVICE);
-			descr->buf_addr = 0;
+				be32_to_cpu(descr->hw_regs.payload.dev_addr),
+				descr->skb->len,
+				DMA_FROM_DEVICE);
+			descr->hw_regs.payload.dev_addr = 0;
+			descr->hw_regs.payload.size = 0;
 			dev_kfree_skb_any(descr->skb);
 			descr->skb = NULL;
 			gelic_descr_set_status(descr,
-					       GELIC_DESCR_DMA_NOT_IN_USE);
+				GELIC_DESCR_DMA_NOT_IN_USE);
 		}
 		descr = descr->next;
 	} while (descr != card->rx_chain.head);
@@ -496,19 +504,20 @@ static void gelic_descr_release_tx(struct gelic_card *card,
 {
 	struct sk_buff *skb = descr->skb;
 
-	BUG_ON(!(be32_to_cpu(descr->data_status) & GELIC_DESCR_TX_TAIL));
+	BUG_ON(!(be32_to_cpu(descr->hw_regs.data_status) & GELIC_DESCR_TX_TAIL));
 
-	dma_unmap_single(ctodev(card), be32_to_cpu(descr->buf_addr), skb->len,
-			 DMA_TO_DEVICE);
+	dma_unmap_single(ctodev(card),
+		be32_to_cpu(descr->hw_regs.payload.dev_addr), skb->len,
+		DMA_TO_DEVICE);
 	dev_kfree_skb_any(skb);
 
-	descr->buf_addr = 0;
-	descr->buf_size = 0;
-	descr->next_descr_addr = 0;
-	descr->result_size = 0;
-	descr->valid_size = 0;
-	descr->data_status = 0;
-	descr->data_error = 0;
+	descr->hw_regs.payload.dev_addr = 0;
+	descr->hw_regs.payload.size = 0;
+	descr->hw_regs.next_descr_addr = 0;
+	descr->hw_regs.result_size = 0;
+	descr->hw_regs.valid_size = 0;
+	descr->hw_regs.data_status = 0;
+	descr->hw_regs.data_error = 0;
 	descr->skb = NULL;
 
 	/* set descr status */
@@ -701,7 +710,7 @@ static void gelic_descr_set_tx_cmdstat(struct gelic_descr *descr,
 				       struct sk_buff *skb)
 {
 	if (skb->ip_summed != CHECKSUM_PARTIAL)
-		descr->dmac_cmd_status =
+		descr->hw_regs.dmac_cmd_status =
 			cpu_to_be32(GELIC_DESCR_DMA_CMD_NO_CHKSUM |
 				    GELIC_DESCR_TX_DMA_FRAME_TAIL);
 	else {
@@ -709,19 +718,19 @@ static void gelic_descr_set_tx_cmdstat(struct gelic_descr *descr,
 		 * if yes: tcp? udp? */
 		if (skb->protocol == htons(ETH_P_IP)) {
 			if (ip_hdr(skb)->protocol == IPPROTO_TCP)
-				descr->dmac_cmd_status =
+				descr->hw_regs.dmac_cmd_status =
 				cpu_to_be32(GELIC_DESCR_DMA_CMD_TCP_CHKSUM |
 					    GELIC_DESCR_TX_DMA_FRAME_TAIL);
 
 			else if (ip_hdr(skb)->protocol == IPPROTO_UDP)
-				descr->dmac_cmd_status =
+				descr->hw_regs.dmac_cmd_status =
 				cpu_to_be32(GELIC_DESCR_DMA_CMD_UDP_CHKSUM |
 					    GELIC_DESCR_TX_DMA_FRAME_TAIL);
 			else	/*
 				 * the stack should checksum non-tcp and non-udp
 				 * packets on his own: NETIF_F_IP_CSUM
 				 */
-				descr->dmac_cmd_status =
+				descr->hw_regs.dmac_cmd_status =
 				cpu_to_be32(GELIC_DESCR_DMA_CMD_NO_CHKSUM |
 					    GELIC_DESCR_TX_DMA_FRAME_TAIL);
 		}
@@ -789,11 +798,11 @@ static int gelic_descr_prepare_tx(struct gelic_card *card,
 		return -ENOMEM;
 	}
 
-	descr->buf_addr = cpu_to_be32(buf);
-	descr->buf_size = cpu_to_be32(skb->len);
+	descr->hw_regs.payload.dev_addr = cpu_to_be32(buf);
+	descr->hw_regs.payload.size = cpu_to_be32(skb->len);
 	descr->skb = skb;
-	descr->data_status = 0;
-	descr->next_descr_addr = 0; /* terminate hw descr */
+	descr->hw_regs.data_status = 0;
+	descr->hw_regs.next_descr_addr = 0; /* terminate hw descr */
 	gelic_descr_set_tx_cmdstat(descr, skb);
 
 	/* bump free descriptor pointer */
@@ -818,7 +827,7 @@ static int gelic_card_kick_txdma(struct gelic_card *card,
 	if (gelic_descr_get_status(descr) == GELIC_DESCR_DMA_CARDOWNED) {
 		card->tx_dma_progress = 1;
 		status = lv1_net_start_tx_dma(bus_id(card), dev_id(card),
-					      descr->bus_addr, 0);
+			descr->link.cpu_addr, 0);
 		if (status) {
 			card->tx_dma_progress = 0;
 			dev_info(ctodev(card), "lv1_net_start_txdma failed," \
@@ -871,7 +880,8 @@ netdev_tx_t gelic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 	 * link this prepared descriptor to previous one
 	 * to achieve high performance
 	 */
-	descr->prev->next_descr_addr = cpu_to_be32(descr->bus_addr);
+	descr->prev->hw_regs.next_descr_addr =
+		cpu_to_be32(descr->link.cpu_addr);
 	/*
 	 * as hardware descriptor is modified in the above lines,
 	 * ensure that the hardware sees it
@@ -884,12 +894,12 @@ netdev_tx_t gelic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 		 */
 		netdev->stats.tx_dropped++;
 		/* don't trigger BUG_ON() in gelic_descr_release_tx */
-		descr->data_status = cpu_to_be32(GELIC_DESCR_TX_TAIL);
+		descr->hw_regs.data_status = cpu_to_be32(GELIC_DESCR_TX_TAIL);
 		gelic_descr_release_tx(card, descr);
 		/* reset head */
 		card->tx_chain.head = descr;
 		/* reset hw termination */
-		descr->prev->next_descr_addr = 0;
+		descr->prev->hw_regs.next_descr_addr = 0;
 		dev_info(ctodev(card), "%s: kick failure\n", __func__);
 	}
 
@@ -914,21 +924,21 @@ static void gelic_net_pass_skb_up(struct gelic_descr *descr,
 	struct sk_buff *skb = descr->skb;
 	u32 data_status, data_error;
 
-	data_status = be32_to_cpu(descr->data_status);
-	data_error = be32_to_cpu(descr->data_error);
+	data_status = be32_to_cpu(descr->hw_regs.data_status);
+	data_error = be32_to_cpu(descr->hw_regs.data_error);
 	/* unmap skb buffer */
-	dma_unmap_single(ctodev(card), be32_to_cpu(descr->buf_addr),
-			 GELIC_NET_MAX_FRAME,
-			 DMA_FROM_DEVICE);
-
-	skb_put(skb, be32_to_cpu(descr->valid_size)?
-		be32_to_cpu(descr->valid_size) :
-		be32_to_cpu(descr->result_size));
-	if (!descr->valid_size)
+	dma_unmap_single(ctodev(card),
+		be32_to_cpu(descr->hw_regs.payload.dev_addr),
+		be32_to_cpu(descr->hw_regs.payload.size), DMA_FROM_DEVICE);
+
+	skb_put(skb, be32_to_cpu(descr->hw_regs.valid_size)?
+		be32_to_cpu(descr->hw_regs.valid_size) :
+		be32_to_cpu(descr->hw_regs.result_size));
+	if (!descr->hw_regs.valid_size)
 		dev_info(ctodev(card), "buffer full %x %x %x\n",
-			 be32_to_cpu(descr->result_size),
-			 be32_to_cpu(descr->buf_size),
-			 be32_to_cpu(descr->dmac_cmd_status));
+			 be32_to_cpu(descr->hw_regs.result_size),
+			 be32_to_cpu(descr->hw_regs.payload.size),
+			 be32_to_cpu(descr->hw_regs.dmac_cmd_status));
 
 	descr->skb = NULL;
 	/*
@@ -1039,14 +1049,14 @@ refill:
 
 	/* is the current descriptor terminated with next_descr == NULL? */
 	dmac_chain_ended =
-		be32_to_cpu(descr->dmac_cmd_status) &
+		be32_to_cpu(descr->hw_regs.dmac_cmd_status) &
 		GELIC_DESCR_RX_DMA_CHAIN_END;
 	/*
 	 * So that always DMAC can see the end
 	 * of the descriptor chain to avoid
 	 * from unwanted DMAC overrun.
 	 */
-	descr->next_descr_addr = 0;
+	descr->hw_regs.next_descr_addr = 0;
 
 	/* change the descriptor state: */
 	gelic_descr_set_status(descr, GELIC_DESCR_DMA_NOT_IN_USE);
@@ -1063,7 +1073,8 @@ refill:
 	/*
 	 * Set this descriptor the end of the chain.
 	 */
-	descr->prev->next_descr_addr = cpu_to_be32(descr->bus_addr);
+	descr->prev->hw_regs.next_descr_addr =
+		cpu_to_be32(descr->link.cpu_addr);
 
 	/*
 	 * If dmac chain was met, DMAC stopped.
diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.h b/drivers/net/ethernet/toshiba/ps3_gelic_net.h
index 0d98defb011e..f7d7931e51b7 100644
--- a/drivers/net/ethernet/toshiba/ps3_gelic_net.h
+++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.h
@@ -221,29 +221,35 @@ enum gelic_lv1_phy {
 	GELIC_LV1_PHY_ETHERNET_0	= 0x0000000000000002L,
 };
 
-/* size of hardware part of gelic descriptor */
-#define GELIC_DESCR_SIZE	(32)
-
 enum gelic_port_type {
 	GELIC_PORT_ETHERNET_0	= 0,
 	GELIC_PORT_WIRELESS	= 1,
 	GELIC_PORT_MAX
 };
 
-struct gelic_descr {
-	/* as defined by the hardware */
-	__be32 buf_addr;
-	__be32 buf_size;
+/* As defined by the gelic hardware device. */
+struct gelic_hw_regs {
+	struct  {
+		__be32 dev_addr;
+		__be32 size;
+	} __packed payload;
 	__be32 next_descr_addr;
 	__be32 dmac_cmd_status;
 	__be32 result_size;
 	__be32 valid_size;	/* all zeroes for tx */
 	__be32 data_status;
 	__be32 data_error;	/* all zeroes for tx */
+} __packed;
+
+struct gelic_chain_link {
+	dma_addr_t cpu_addr;
+	unsigned int size;
+};
 
-	/* used in the driver */
+struct gelic_descr {
+	struct gelic_hw_regs hw_regs;
+	struct gelic_chain_link link;
 	struct sk_buff *skb;
-	dma_addr_t bus_addr;
 	struct gelic_descr *next;
 	struct gelic_descr *prev;
 } __attribute__((aligned(32)));
@@ -346,12 +352,6 @@ static inline void *port_priv(struct gelic_port *port)
 	return port->priv;
 }
 
-#ifdef CONFIG_PPC_EARLY_DEBUG_PS3GELIC
-void udbg_shutdown_ps3gelic(void);
-#else
-static inline void udbg_shutdown_ps3gelic(void) {}
-#endif
-
 int gelic_card_set_irq_mask(struct gelic_card *card, u64 mask);
 /* shared netdev ops */
 void gelic_card_up(struct gelic_card *card);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
index ddc5f6d20b9c..cc3bec42ed8e 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
@@ -8,6 +8,7 @@
 #include "wx_type.h"
 #include "wx_ethtool.h"
 #include "wx_hw.h"
+#include "wx_lib.h"
 
 struct wx_stats {
 	char stat_string[ETH_GSTRING_LEN];
@@ -75,7 +76,7 @@ void wx_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 	switch (stringset) {
 	case ETH_SS_STATS:
 		for (i = 0; i < WX_GLOBAL_STATS_LEN; i++)
-			ethtool_sprintf(&p, wx_gstrings_stats[i].stat_string);
+			ethtool_puts(&p, wx_gstrings_stats[i].stat_string);
 		for (i = 0; i < netdev->num_tx_queues; i++) {
 			ethtool_sprintf(&p, "tx_queue_%u_packets", i);
 			ethtool_sprintf(&p, "tx_queue_%u_bytes", i);
@@ -185,3 +186,238 @@ void wx_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *info)
 	}
 }
 EXPORT_SYMBOL(wx_get_drvinfo);
+
+int wx_nway_reset(struct net_device *netdev)
+{
+	struct wx *wx = netdev_priv(netdev);
+
+	return phylink_ethtool_nway_reset(wx->phylink);
+}
+EXPORT_SYMBOL(wx_nway_reset);
+
+int wx_get_link_ksettings(struct net_device *netdev,
+			  struct ethtool_link_ksettings *cmd)
+{
+	struct wx *wx = netdev_priv(netdev);
+
+	return phylink_ethtool_ksettings_get(wx->phylink, cmd);
+}
+EXPORT_SYMBOL(wx_get_link_ksettings);
+
+int wx_set_link_ksettings(struct net_device *netdev,
+			  const struct ethtool_link_ksettings *cmd)
+{
+	struct wx *wx = netdev_priv(netdev);
+
+	return phylink_ethtool_ksettings_set(wx->phylink, cmd);
+}
+EXPORT_SYMBOL(wx_set_link_ksettings);
+
+void wx_get_pauseparam(struct net_device *netdev,
+		       struct ethtool_pauseparam *pause)
+{
+	struct wx *wx = netdev_priv(netdev);
+
+	phylink_ethtool_get_pauseparam(wx->phylink, pause);
+}
+EXPORT_SYMBOL(wx_get_pauseparam);
+
+int wx_set_pauseparam(struct net_device *netdev,
+		      struct ethtool_pauseparam *pause)
+{
+	struct wx *wx = netdev_priv(netdev);
+
+	return phylink_ethtool_set_pauseparam(wx->phylink, pause);
+}
+EXPORT_SYMBOL(wx_set_pauseparam);
+
+void wx_get_ringparam(struct net_device *netdev,
+		      struct ethtool_ringparam *ring,
+		      struct kernel_ethtool_ringparam *kernel_ring,
+		      struct netlink_ext_ack *extack)
+{
+	struct wx *wx = netdev_priv(netdev);
+
+	ring->rx_max_pending = WX_MAX_RXD;
+	ring->tx_max_pending = WX_MAX_TXD;
+	ring->rx_mini_max_pending = 0;
+	ring->rx_jumbo_max_pending = 0;
+	ring->rx_pending = wx->rx_ring_count;
+	ring->tx_pending = wx->tx_ring_count;
+	ring->rx_mini_pending = 0;
+	ring->rx_jumbo_pending = 0;
+}
+EXPORT_SYMBOL(wx_get_ringparam);
+
+int wx_get_coalesce(struct net_device *netdev,
+		    struct ethtool_coalesce *ec,
+		    struct kernel_ethtool_coalesce *kernel_coal,
+		    struct netlink_ext_ack *extack)
+{
+	struct wx *wx = netdev_priv(netdev);
+
+	ec->tx_max_coalesced_frames_irq = wx->tx_work_limit;
+	/* only valid if in constant ITR mode */
+	if (wx->rx_itr_setting <= 1)
+		ec->rx_coalesce_usecs = wx->rx_itr_setting;
+	else
+		ec->rx_coalesce_usecs = wx->rx_itr_setting >> 2;
+
+	/* if in mixed tx/rx queues per vector mode, report only rx settings */
+	if (wx->q_vector[0]->tx.count && wx->q_vector[0]->rx.count)
+		return 0;
+
+	/* only valid if in constant ITR mode */
+	if (wx->tx_itr_setting <= 1)
+		ec->tx_coalesce_usecs = wx->tx_itr_setting;
+	else
+		ec->tx_coalesce_usecs = wx->tx_itr_setting >> 2;
+
+	return 0;
+}
+EXPORT_SYMBOL(wx_get_coalesce);
+
+int wx_set_coalesce(struct net_device *netdev,
+		    struct ethtool_coalesce *ec,
+		    struct kernel_ethtool_coalesce *kernel_coal,
+		    struct netlink_ext_ack *extack)
+{
+	struct wx *wx = netdev_priv(netdev);
+	u16 tx_itr_param, rx_itr_param;
+	struct wx_q_vector *q_vector;
+	u16 max_eitr;
+	int i;
+
+	if (wx->q_vector[0]->tx.count && wx->q_vector[0]->rx.count) {
+		/* reject Tx specific changes in case of mixed RxTx vectors */
+		if (ec->tx_coalesce_usecs)
+			return -EOPNOTSUPP;
+	}
+
+	if (ec->tx_max_coalesced_frames_irq)
+		wx->tx_work_limit = ec->tx_max_coalesced_frames_irq;
+
+	if (wx->mac.type == wx_mac_sp)
+		max_eitr = WX_SP_MAX_EITR;
+	else
+		max_eitr = WX_EM_MAX_EITR;
+
+	if ((ec->rx_coalesce_usecs > (max_eitr >> 2)) ||
+	    (ec->tx_coalesce_usecs > (max_eitr >> 2)))
+		return -EINVAL;
+
+	if (ec->rx_coalesce_usecs > 1)
+		wx->rx_itr_setting = ec->rx_coalesce_usecs << 2;
+	else
+		wx->rx_itr_setting = ec->rx_coalesce_usecs;
+
+	if (wx->rx_itr_setting == 1)
+		rx_itr_param = WX_20K_ITR;
+	else
+		rx_itr_param = wx->rx_itr_setting;
+
+	if (ec->tx_coalesce_usecs > 1)
+		wx->tx_itr_setting = ec->tx_coalesce_usecs << 2;
+	else
+		wx->tx_itr_setting = ec->tx_coalesce_usecs;
+
+	if (wx->tx_itr_setting == 1) {
+		if (wx->mac.type == wx_mac_sp)
+			tx_itr_param = WX_12K_ITR;
+		else
+			tx_itr_param = WX_20K_ITR;
+	} else {
+		tx_itr_param = wx->tx_itr_setting;
+	}
+
+	/* mixed Rx/Tx */
+	if (wx->q_vector[0]->tx.count && wx->q_vector[0]->rx.count)
+		wx->tx_itr_setting = wx->rx_itr_setting;
+
+	for (i = 0; i < wx->num_q_vectors; i++) {
+		q_vector = wx->q_vector[i];
+		if (q_vector->tx.count && !q_vector->rx.count)
+			/* tx only */
+			q_vector->itr = tx_itr_param;
+		else
+			/* rx only or mixed */
+			q_vector->itr = rx_itr_param;
+		wx_write_eitr(q_vector);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(wx_set_coalesce);
+
+static unsigned int wx_max_channels(struct wx *wx)
+{
+	unsigned int max_combined;
+
+	if (!wx->msix_q_entries) {
+		/* We only support one q_vector without MSI-X */
+		max_combined = 1;
+	} else {
+		/* support up to max allowed queues with RSS */
+		if (wx->mac.type == wx_mac_sp)
+			max_combined = 63;
+		else
+			max_combined = 8;
+	}
+
+	return max_combined;
+}
+
+void wx_get_channels(struct net_device *dev,
+		     struct ethtool_channels *ch)
+{
+	struct wx *wx = netdev_priv(dev);
+
+	/* report maximum channels */
+	ch->max_combined = wx_max_channels(wx);
+
+	/* report info for other vector */
+	if (wx->msix_q_entries) {
+		ch->max_other = 1;
+		ch->other_count = 1;
+	}
+
+	/* record RSS queues */
+	ch->combined_count = wx->ring_feature[RING_F_RSS].indices;
+}
+EXPORT_SYMBOL(wx_get_channels);
+
+int wx_set_channels(struct net_device *dev,
+		    struct ethtool_channels *ch)
+{
+	unsigned int count = ch->combined_count;
+	struct wx *wx = netdev_priv(dev);
+
+	/* verify other_count has not changed */
+	if (ch->other_count != 1)
+		return -EINVAL;
+
+	/* verify the number of channels does not exceed hardware limits */
+	if (count > wx_max_channels(wx))
+		return -EINVAL;
+
+	wx->ring_feature[RING_F_RSS].limit = count;
+
+	return 0;
+}
+EXPORT_SYMBOL(wx_set_channels);
+
+u32 wx_get_msglevel(struct net_device *netdev)
+{
+	struct wx *wx = netdev_priv(netdev);
+
+	return wx->msg_enable;
+}
+EXPORT_SYMBOL(wx_get_msglevel);
+
+void wx_set_msglevel(struct net_device *netdev, u32 data)
+{
+	struct wx *wx = netdev_priv(netdev);
+
+	wx->msg_enable = data;
+}
+EXPORT_SYMBOL(wx_set_msglevel);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.h b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.h
index 16d1a09369a6..600c3b597d1a 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.h
@@ -13,4 +13,31 @@ void wx_get_mac_stats(struct net_device *netdev,
 void wx_get_pause_stats(struct net_device *netdev,
 			struct ethtool_pause_stats *stats);
 void wx_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *info);
+int wx_nway_reset(struct net_device *netdev);
+int wx_get_link_ksettings(struct net_device *netdev,
+			  struct ethtool_link_ksettings *cmd);
+int wx_set_link_ksettings(struct net_device *netdev,
+			  const struct ethtool_link_ksettings *cmd);
+void wx_get_pauseparam(struct net_device *netdev,
+		       struct ethtool_pauseparam *pause);
+int wx_set_pauseparam(struct net_device *netdev,
+		      struct ethtool_pauseparam *pause);
+void wx_get_ringparam(struct net_device *netdev,
+		      struct ethtool_ringparam *ring,
+		      struct kernel_ethtool_ringparam *kernel_ring,
+		      struct netlink_ext_ack *extack);
+int wx_get_coalesce(struct net_device *netdev,
+		    struct ethtool_coalesce *ec,
+		    struct kernel_ethtool_coalesce *kernel_coal,
+		    struct netlink_ext_ack *extack);
+int wx_set_coalesce(struct net_device *netdev,
+		    struct ethtool_coalesce *ec,
+		    struct kernel_ethtool_coalesce *kernel_coal,
+		    struct netlink_ext_ack *extack);
+void wx_get_channels(struct net_device *dev,
+		     struct ethtool_channels *ch);
+int wx_set_channels(struct net_device *dev,
+		    struct ethtool_channels *ch);
+u32 wx_get_msglevel(struct net_device *netdev);
+void wx_set_msglevel(struct net_device *netdev, u32 data);
 #endif /* _WX_ETHTOOL_H_ */
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
index a3c5de9d547a..1db754615cca 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
@@ -149,9 +149,9 @@ void wx_irq_disable(struct wx *wx)
 		int vector;
 
 		for (vector = 0; vector < wx->num_q_vectors; vector++)
-			synchronize_irq(wx->msix_entries[vector].vector);
+			synchronize_irq(wx->msix_q_entries[vector].vector);
 
-		synchronize_irq(wx->msix_entries[vector].vector);
+		synchronize_irq(wx->msix_entry->vector);
 	} else {
 		synchronize_irq(pdev->irq);
 	}
@@ -1158,6 +1158,81 @@ static void wx_set_rxpba(struct wx *wx)
 	wr32(wx, WX_TDM_PB_THRE(0), txpbthresh);
 }
 
+#define WX_ETH_FRAMING 20
+
+/**
+ * wx_hpbthresh - calculate high water mark for flow control
+ *
+ * @wx: board private structure to calculate for
+ **/
+static int wx_hpbthresh(struct wx *wx)
+{
+	struct net_device *dev = wx->netdev;
+	int link, tc, kb, marker;
+	u32 dv_id, rx_pba;
+
+	/* Calculate max LAN frame size */
+	link = dev->mtu + ETH_HLEN + ETH_FCS_LEN + WX_ETH_FRAMING;
+	tc = link;
+
+	/* Calculate delay value for device */
+	dv_id = WX_DV(link, tc);
+
+	/* Delay value is calculated in bit times convert to KB */
+	kb = WX_BT2KB(dv_id);
+	rx_pba = rd32(wx, WX_RDB_PB_SZ(0)) >> WX_RDB_PB_SZ_SHIFT;
+
+	marker = rx_pba - kb;
+
+	/* It is possible that the packet buffer is not large enough
+	 * to provide required headroom. In this case throw an error
+	 * to user and a do the best we can.
+	 */
+	if (marker < 0) {
+		dev_warn(&wx->pdev->dev,
+			 "Packet Buffer can not provide enough headroom to support flow control. Decrease MTU or number of traffic classes\n");
+		marker = tc + 1;
+	}
+
+	return marker;
+}
+
+/**
+ * wx_lpbthresh - calculate low water mark for flow control
+ *
+ * @wx: board private structure to calculate for
+ **/
+static int wx_lpbthresh(struct wx *wx)
+{
+	struct net_device *dev = wx->netdev;
+	u32 dv_id;
+	int tc;
+
+	/* Calculate max LAN frame size */
+	tc = dev->mtu + ETH_HLEN + ETH_FCS_LEN;
+
+	/* Calculate delay value for device */
+	dv_id = WX_LOW_DV(tc);
+
+	/* Delay value is calculated in bit times convert to KB */
+	return WX_BT2KB(dv_id);
+}
+
+/**
+ * wx_pbthresh_setup - calculate and setup high low water marks
+ *
+ * @wx: board private structure to calculate for
+ **/
+static void wx_pbthresh_setup(struct wx *wx)
+{
+	wx->fc.high_water = wx_hpbthresh(wx);
+	wx->fc.low_water = wx_lpbthresh(wx);
+
+	/* Low water marks must not be larger than high water marks */
+	if (wx->fc.low_water > wx->fc.high_water)
+		wx->fc.low_water = 0;
+}
+
 static void wx_configure_port(struct wx *wx)
 {
 	u32 value, i;
@@ -1522,6 +1597,72 @@ static void wx_restore_vlan(struct wx *wx)
 		wx_vlan_rx_add_vid(wx->netdev, htons(ETH_P_8021Q), vid);
 }
 
+static void wx_store_reta(struct wx *wx)
+{
+	u8 *indir_tbl = wx->rss_indir_tbl;
+	u32 reta = 0;
+	u32 i;
+
+	/* Fill out the redirection table as follows:
+	 *  - 8 bit wide entries containing 4 bit RSS index
+	 */
+	for (i = 0; i < WX_MAX_RETA_ENTRIES; i++) {
+		reta |= indir_tbl[i] << (i & 0x3) * 8;
+		if ((i & 3) == 3) {
+			wr32(wx, WX_RDB_RSSTBL(i >> 2), reta);
+			reta = 0;
+		}
+	}
+}
+
+static void wx_setup_reta(struct wx *wx)
+{
+	u16 rss_i = wx->ring_feature[RING_F_RSS].indices;
+	u32 random_key_size = WX_RSS_KEY_SIZE / 4;
+	u32 i, j;
+
+	/* Fill out hash function seeds */
+	for (i = 0; i < random_key_size; i++)
+		wr32(wx, WX_RDB_RSSRK(i), wx->rss_key[i]);
+
+	/* Fill out redirection table */
+	memset(wx->rss_indir_tbl, 0, sizeof(wx->rss_indir_tbl));
+
+	for (i = 0, j = 0; i < WX_MAX_RETA_ENTRIES; i++, j++) {
+		if (j == rss_i)
+			j = 0;
+
+		wx->rss_indir_tbl[i] = j;
+	}
+
+	wx_store_reta(wx);
+}
+
+static void wx_setup_mrqc(struct wx *wx)
+{
+	u32 rss_field = 0;
+
+	/* Disable indicating checksum in descriptor, enables RSS hash */
+	wr32m(wx, WX_PSR_CTL, WX_PSR_CTL_PCSD, WX_PSR_CTL_PCSD);
+
+	/* Perform hash on these packet types */
+	rss_field = WX_RDB_RA_CTL_RSS_IPV4 |
+		    WX_RDB_RA_CTL_RSS_IPV4_TCP |
+		    WX_RDB_RA_CTL_RSS_IPV4_UDP |
+		    WX_RDB_RA_CTL_RSS_IPV6 |
+		    WX_RDB_RA_CTL_RSS_IPV6_TCP |
+		    WX_RDB_RA_CTL_RSS_IPV6_UDP;
+
+	netdev_rss_key_fill(wx->rss_key, sizeof(wx->rss_key));
+
+	wx_setup_reta(wx);
+
+	if (wx->rss_enabled)
+		rss_field |= WX_RDB_RA_CTL_RSS_EN;
+
+	wr32(wx, WX_RDB_RA_CTL, rss_field);
+}
+
 /**
  * wx_configure_rx - Configure Receive Unit after Reset
  * @wx: pointer to private structure
@@ -1554,6 +1695,8 @@ void wx_configure_rx(struct wx *wx)
 		wr32(wx, WX_PSR_CTL, psrctl);
 	}
 
+	wx_setup_mrqc(wx);
+
 	/* set_rx_buffer_len must be called before ring initialization */
 	wx_set_rx_buffer_len(wx);
 
@@ -1584,6 +1727,7 @@ static void wx_configure_isb(struct wx *wx)
 void wx_configure(struct wx *wx)
 {
 	wx_set_rxpba(wx);
+	wx_pbthresh_setup(wx);
 	wx_configure_port(wx);
 
 	wx_set_rx_mode(wx->netdev);
@@ -1750,6 +1894,28 @@ int wx_get_pcie_msix_counts(struct wx *wx, u16 *msix_count, u16 max_msix_count)
 }
 EXPORT_SYMBOL(wx_get_pcie_msix_counts);
 
+/**
+ * wx_init_rss_key - Initialize wx RSS key
+ * @wx: device handle
+ *
+ * Allocates and initializes the RSS key if it is not allocated.
+ **/
+static int wx_init_rss_key(struct wx *wx)
+{
+	u32 *rss_key;
+
+	if (!wx->rss_key) {
+		rss_key = kzalloc(WX_RSS_KEY_SIZE, GFP_KERNEL);
+		if (unlikely(!rss_key))
+			return -ENOMEM;
+
+		netdev_rss_key_fill(rss_key, WX_RSS_KEY_SIZE);
+		wx->rss_key = rss_key;
+	}
+
+	return 0;
+}
+
 int wx_sw_init(struct wx *wx)
 {
 	struct pci_dev *pdev = wx->pdev;
@@ -1769,9 +1935,17 @@ int wx_sw_init(struct wx *wx)
 		wx->subsystem_device_id = pdev->subsystem_device;
 	} else {
 		err = wx_flash_read_dword(wx, 0xfffdc, &ssid);
-		if (!err)
-			wx->subsystem_device_id = swab16((u16)ssid);
+		if (err < 0) {
+			wx_err(wx, "read of internal subsystem device id failed\n");
+			return err;
+		}
 
+		wx->subsystem_device_id = swab16((u16)ssid);
+	}
+
+	err = wx_init_rss_key(wx);
+	if (err < 0) {
+		wx_err(wx, "rss key allocation failed\n");
 		return err;
 	}
 
@@ -1780,9 +1954,12 @@ int wx_sw_init(struct wx *wx)
 				GFP_KERNEL);
 	if (!wx->mac_table) {
 		wx_err(wx, "mac_table allocation failed\n");
+		kfree(wx->rss_key);
 		return -ENOMEM;
 	}
 
+	wx->msix_in_use = false;
+
 	return 0;
 }
 EXPORT_SYMBOL(wx_sw_init);
@@ -2001,6 +2178,102 @@ int wx_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid)
 }
 EXPORT_SYMBOL(wx_vlan_rx_kill_vid);
 
+static void wx_enable_rx_drop(struct wx *wx, struct wx_ring *ring)
+{
+	u16 reg_idx = ring->reg_idx;
+	u32 srrctl;
+
+	srrctl = rd32(wx, WX_PX_RR_CFG(reg_idx));
+	srrctl |= WX_PX_RR_CFG_DROP_EN;
+
+	wr32(wx, WX_PX_RR_CFG(reg_idx), srrctl);
+}
+
+static void wx_disable_rx_drop(struct wx *wx, struct wx_ring *ring)
+{
+	u16 reg_idx = ring->reg_idx;
+	u32 srrctl;
+
+	srrctl = rd32(wx, WX_PX_RR_CFG(reg_idx));
+	srrctl &= ~WX_PX_RR_CFG_DROP_EN;
+
+	wr32(wx, WX_PX_RR_CFG(reg_idx), srrctl);
+}
+
+int wx_fc_enable(struct wx *wx, bool tx_pause, bool rx_pause)
+{
+	u16 pause_time = WX_DEFAULT_FCPAUSE;
+	u32 mflcn_reg, fccfg_reg, reg;
+	u32 fcrtl, fcrth;
+	int i;
+
+	/* Low water mark of zero causes XOFF floods */
+	if (tx_pause && wx->fc.high_water) {
+		if (!wx->fc.low_water || wx->fc.low_water >= wx->fc.high_water) {
+			wx_err(wx, "Invalid water mark configuration\n");
+			return -EINVAL;
+		}
+	}
+
+	/* Disable any previous flow control settings */
+	mflcn_reg = rd32(wx, WX_MAC_RX_FLOW_CTRL);
+	mflcn_reg &= ~WX_MAC_RX_FLOW_CTRL_RFE;
+
+	fccfg_reg = rd32(wx, WX_RDB_RFCC);
+	fccfg_reg &= ~WX_RDB_RFCC_RFCE_802_3X;
+
+	if (rx_pause)
+		mflcn_reg |= WX_MAC_RX_FLOW_CTRL_RFE;
+	if (tx_pause)
+		fccfg_reg |= WX_RDB_RFCC_RFCE_802_3X;
+
+	/* Set 802.3x based flow control settings. */
+	wr32(wx, WX_MAC_RX_FLOW_CTRL, mflcn_reg);
+	wr32(wx, WX_RDB_RFCC, fccfg_reg);
+
+	/* Set up and enable Rx high/low water mark thresholds, enable XON. */
+	if (tx_pause && wx->fc.high_water) {
+		fcrtl = (wx->fc.low_water << 10) | WX_RDB_RFCL_XONE;
+		wr32(wx, WX_RDB_RFCL, fcrtl);
+		fcrth = (wx->fc.high_water << 10) | WX_RDB_RFCH_XOFFE;
+	} else {
+		wr32(wx, WX_RDB_RFCL, 0);
+		/* In order to prevent Tx hangs when the internal Tx
+		 * switch is enabled we must set the high water mark
+		 * to the Rx packet buffer size - 24KB.  This allows
+		 * the Tx switch to function even under heavy Rx
+		 * workloads.
+		 */
+		fcrth = rd32(wx, WX_RDB_PB_SZ(0)) - 24576;
+	}
+
+	wr32(wx, WX_RDB_RFCH, fcrth);
+
+	/* Configure pause time */
+	reg = pause_time * 0x00010001;
+	wr32(wx, WX_RDB_RFCV, reg);
+
+	/* Configure flow control refresh threshold value */
+	wr32(wx, WX_RDB_RFCRT, pause_time / 2);
+
+	/*  We should set the drop enable bit if:
+	 *  Number of Rx queues > 1 and flow control is disabled
+	 *
+	 *  This allows us to avoid head of line blocking for security
+	 *  and performance reasons.
+	 */
+	if (wx->num_rx_queues > 1 && !tx_pause) {
+		for (i = 0; i < wx->num_rx_queues; i++)
+			wx_enable_rx_drop(wx, wx->rx_ring[i]);
+	} else {
+		for (i = 0; i < wx->num_rx_queues; i++)
+			wx_disable_rx_drop(wx, wx->rx_ring[i]);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(wx_fc_enable);
+
 /**
  * wx_update_stats - Update the board statistics counters.
  * @wx: board private structure
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.h b/drivers/net/ethernet/wangxun/libwx/wx_hw.h
index 12c20a7c364d..9e219fa717a2 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.h
@@ -41,6 +41,7 @@ int wx_get_pcie_msix_counts(struct wx *wx, u16 *msix_count, u16 max_msix_count);
 int wx_sw_init(struct wx *wx);
 int wx_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid);
 int wx_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid);
+int wx_fc_enable(struct wx *wx, bool tx_pause, bool rx_pause);
 void wx_update_stats(struct wx *wx);
 void wx_clear_hw_cntrs(struct wx *wx);
 
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index 2823861e5a92..23355cc408fd 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -160,60 +160,6 @@ static __le32 wx_test_staterr(union wx_rx_desc *rx_desc,
 	return rx_desc->wb.upper.status_error & cpu_to_le32(stat_err_bits);
 }
 
-static bool wx_can_reuse_rx_page(struct wx_rx_buffer *rx_buffer,
-				 int rx_buffer_pgcnt)
-{
-	unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
-	struct page *page = rx_buffer->page;
-
-	/* avoid re-using remote and pfmemalloc pages */
-	if (!dev_page_is_reusable(page))
-		return false;
-
-#if (PAGE_SIZE < 8192)
-	/* if we are only owner of page we can reuse it */
-	if (unlikely((rx_buffer_pgcnt - pagecnt_bias) > 1))
-		return false;
-#endif
-
-	/* If we have drained the page fragment pool we need to update
-	 * the pagecnt_bias and page count so that we fully restock the
-	 * number of references the driver holds.
-	 */
-	if (unlikely(pagecnt_bias == 1)) {
-		page_ref_add(page, USHRT_MAX - 1);
-		rx_buffer->pagecnt_bias = USHRT_MAX;
-	}
-
-	return true;
-}
-
-/**
- * wx_reuse_rx_page - page flip buffer and store it back on the ring
- * @rx_ring: rx descriptor ring to store buffers on
- * @old_buff: donor buffer to have page reused
- *
- * Synchronizes page for reuse by the adapter
- **/
-static void wx_reuse_rx_page(struct wx_ring *rx_ring,
-			     struct wx_rx_buffer *old_buff)
-{
-	u16 nta = rx_ring->next_to_alloc;
-	struct wx_rx_buffer *new_buff;
-
-	new_buff = &rx_ring->rx_buffer_info[nta];
-
-	/* update, and store next to alloc */
-	nta++;
-	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
-
-	/* transfer page from old buffer to new buffer */
-	new_buff->page = old_buff->page;
-	new_buff->page_dma = old_buff->page_dma;
-	new_buff->page_offset = old_buff->page_offset;
-	new_buff->pagecnt_bias	= old_buff->pagecnt_bias;
-}
-
 static void wx_dma_sync_frag(struct wx_ring *rx_ring,
 			     struct wx_rx_buffer *rx_buffer)
 {
@@ -270,8 +216,6 @@ static struct wx_rx_buffer *wx_get_rx_buffer(struct wx_ring *rx_ring,
 				      size,
 				      DMA_FROM_DEVICE);
 skip_sync:
-	rx_buffer->pagecnt_bias--;
-
 	return rx_buffer;
 }
 
@@ -280,19 +224,9 @@ static void wx_put_rx_buffer(struct wx_ring *rx_ring,
 			     struct sk_buff *skb,
 			     int rx_buffer_pgcnt)
 {
-	if (wx_can_reuse_rx_page(rx_buffer, rx_buffer_pgcnt)) {
-		/* hand second half of page back to the ring */
-		wx_reuse_rx_page(rx_ring, rx_buffer);
-	} else {
-		if (!IS_ERR(skb) && WX_CB(skb)->dma == rx_buffer->dma)
-			/* the page has been released from the ring */
-			WX_CB(skb)->page_released = true;
-		else
-			page_pool_put_full_page(rx_ring->page_pool, rx_buffer->page, false);
-
-		__page_frag_cache_drain(rx_buffer->page,
-					rx_buffer->pagecnt_bias);
-	}
+	if (!IS_ERR(skb) && WX_CB(skb)->dma == rx_buffer->dma)
+		/* the page has been released from the ring */
+		WX_CB(skb)->page_released = true;
 
 	/* clear contents of rx_buffer */
 	rx_buffer->page = NULL;
@@ -335,11 +269,12 @@ static struct sk_buff *wx_build_skb(struct wx_ring *rx_ring,
 		if (size <= WX_RXBUFFER_256) {
 			memcpy(__skb_put(skb, size), page_addr,
 			       ALIGN(size, sizeof(long)));
-			rx_buffer->pagecnt_bias++;
-
+			page_pool_put_full_page(rx_ring->page_pool, rx_buffer->page, true);
 			return skb;
 		}
 
+		skb_mark_for_recycle(skb);
+
 		if (!wx_test_staterr(rx_desc, WX_RXD_STAT_EOP))
 			WX_CB(skb)->dma = rx_buffer->dma;
 
@@ -382,8 +317,6 @@ static bool wx_alloc_mapped_page(struct wx_ring *rx_ring,
 	bi->page_dma = dma;
 	bi->page = page;
 	bi->page_offset = 0;
-	page_ref_add(page, USHRT_MAX - 1);
-	bi->pagecnt_bias = USHRT_MAX;
 
 	return true;
 }
@@ -723,7 +656,6 @@ static int wx_clean_rx_irq(struct wx_q_vector *q_vector,
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
 			rx_ring->rx_stats.alloc_rx_buff_failed++;
-			rx_buffer->pagecnt_bias++;
 			break;
 		}
 
@@ -1636,8 +1568,14 @@ EXPORT_SYMBOL(wx_napi_disable_all);
  **/
 static void wx_set_rss_queues(struct wx *wx)
 {
-	wx->num_rx_queues = wx->mac.max_rx_queues;
-	wx->num_tx_queues = wx->mac.max_tx_queues;
+	struct wx_ring_feature *f;
+
+	/* set mask for 16 queue limit of RSS */
+	f = &wx->ring_feature[RING_F_RSS];
+	f->indices = f->limit;
+
+	wx->num_rx_queues = f->limit;
+	wx->num_tx_queues = f->limit;
 }
 
 static void wx_set_num_queues(struct wx *wx)
@@ -1663,35 +1601,51 @@ static int wx_acquire_msix_vectors(struct wx *wx)
 	struct irq_affinity affd = {0, };
 	int nvecs, i;
 
-	nvecs = min_t(int, num_online_cpus(), wx->mac.max_msix_vectors);
+	/* We start by asking for one vector per queue pair */
+	nvecs = max(wx->num_rx_queues, wx->num_tx_queues);
+	nvecs = min_t(int, nvecs, num_online_cpus());
+	nvecs = min_t(int, nvecs, wx->mac.max_msix_vectors);
 
-	wx->msix_entries = kcalloc(nvecs,
-				   sizeof(struct msix_entry),
-				   GFP_KERNEL);
-	if (!wx->msix_entries)
+	wx->msix_q_entries = kcalloc(nvecs, sizeof(struct msix_entry),
+				     GFP_KERNEL);
+	if (!wx->msix_q_entries)
 		return -ENOMEM;
 
+	/* One for non-queue interrupts */
+	nvecs += 1;
+
+	if (!wx->msix_in_use) {
+		wx->msix_entry = kcalloc(1, sizeof(struct msix_entry),
+					 GFP_KERNEL);
+		if (!wx->msix_entry) {
+			kfree(wx->msix_q_entries);
+			wx->msix_q_entries = NULL;
+			return -ENOMEM;
+		}
+	}
+
 	nvecs = pci_alloc_irq_vectors_affinity(wx->pdev, nvecs,
 					       nvecs,
 					       PCI_IRQ_MSIX | PCI_IRQ_AFFINITY,
 					       &affd);
 	if (nvecs < 0) {
 		wx_err(wx, "Failed to allocate MSI-X interrupts. Err: %d\n", nvecs);
-		kfree(wx->msix_entries);
-		wx->msix_entries = NULL;
+		kfree(wx->msix_q_entries);
+		wx->msix_q_entries = NULL;
+		kfree(wx->msix_entry);
+		wx->msix_entry = NULL;
 		return nvecs;
 	}
 
+	wx->msix_entry->entry = 0;
+	wx->msix_entry->vector = pci_irq_vector(wx->pdev, 0);
+	nvecs -= 1;
 	for (i = 0; i < nvecs; i++) {
-		wx->msix_entries[i].entry = i;
-		wx->msix_entries[i].vector = pci_irq_vector(wx->pdev, i);
+		wx->msix_q_entries[i].entry = i;
+		wx->msix_q_entries[i].vector = pci_irq_vector(wx->pdev, i + 1);
 	}
 
-	/* one for msix_other */
-	nvecs -= 1;
 	wx->num_q_vectors = nvecs;
-	wx->num_rx_queues = nvecs;
-	wx->num_tx_queues = nvecs;
 
 	return 0;
 }
@@ -1713,9 +1667,11 @@ static int wx_set_interrupt_capability(struct wx *wx)
 	if (ret == 0 || (ret == -ENOMEM))
 		return ret;
 
-	wx->num_rx_queues = 1;
-	wx->num_tx_queues = 1;
-	wx->num_q_vectors = 1;
+	/* Disable RSS */
+	dev_warn(&wx->pdev->dev, "Disabling RSS support\n");
+	wx->ring_feature[RING_F_RSS].limit = 1;
+
+	wx_set_num_queues(wx);
 
 	/* minmum one for queue, one for misc*/
 	nvecs = 1;
@@ -1972,11 +1928,15 @@ void wx_reset_interrupt_capability(struct wx *wx)
 	if (!pdev->msi_enabled && !pdev->msix_enabled)
 		return;
 
-	pci_free_irq_vectors(wx->pdev);
 	if (pdev->msix_enabled) {
-		kfree(wx->msix_entries);
-		wx->msix_entries = NULL;
+		kfree(wx->msix_q_entries);
+		wx->msix_q_entries = NULL;
+		if (!wx->msix_in_use) {
+			kfree(wx->msix_entry);
+			wx->msix_entry = NULL;
+		}
 	}
+	pci_free_irq_vectors(wx->pdev);
 }
 EXPORT_SYMBOL(wx_reset_interrupt_capability);
 
@@ -2046,7 +2006,7 @@ void wx_free_irq(struct wx *wx)
 
 	for (vector = 0; vector < wx->num_q_vectors; vector++) {
 		struct wx_q_vector *q_vector = wx->q_vector[vector];
-		struct msix_entry *entry = &wx->msix_entries[vector];
+		struct msix_entry *entry = &wx->msix_q_entries[vector];
 
 		/* free only the irqs that were actually requested */
 		if (!q_vector->rx.ring && !q_vector->tx.ring)
@@ -2056,7 +2016,7 @@ void wx_free_irq(struct wx *wx)
 	}
 
 	if (wx->mac.type == wx_mac_em)
-		free_irq(wx->msix_entries[vector].vector, wx);
+		free_irq(wx->msix_entry->vector, wx);
 }
 EXPORT_SYMBOL(wx_free_irq);
 
@@ -2133,6 +2093,7 @@ static void wx_set_ivar(struct wx *wx, s8 direction,
 		wr32(wx, WX_PX_MISC_IVAR, ivar);
 	} else {
 		/* tx or rx causes */
+		msix_vector += 1; /* offset for queue vectors */
 		msix_vector |= WX_PX_IVAR_ALLOC_VAL;
 		index = ((16 * (queue & 1)) + (8 * direction));
 		ivar = rd32(wx, WX_PX_IVAR(queue >> 1));
@@ -2150,7 +2111,7 @@ static void wx_set_ivar(struct wx *wx, s8 direction,
  * when it needs to update EITR registers at runtime.  Hardware
  * specific quirks/differences are taken care of here.
  */
-static void wx_write_eitr(struct wx_q_vector *q_vector)
+void wx_write_eitr(struct wx_q_vector *q_vector)
 {
 	struct wx *wx = q_vector->wx;
 	int v_idx = q_vector->v_idx;
@@ -2163,7 +2124,7 @@ static void wx_write_eitr(struct wx_q_vector *q_vector)
 
 	itr_reg |= WX_PX_ITR_CNT_WDIS;
 
-	wr32(wx, WX_PX_ITR(v_idx), itr_reg);
+	wr32(wx, WX_PX_ITR(v_idx + 1), itr_reg);
 }
 
 /**
@@ -2209,9 +2170,9 @@ void wx_configure_vectors(struct wx *wx)
 		wx_write_eitr(q_vector);
 	}
 
-	wx_set_ivar(wx, -1, 0, v_idx);
+	wx_set_ivar(wx, -1, 0, 0);
 	if (pdev->msix_enabled)
-		wr32(wx, WX_PX_ITR(v_idx), 1950);
+		wr32(wx, WX_PX_ITR(0), 1950);
 }
 EXPORT_SYMBOL(wx_configure_vectors);
 
@@ -2248,8 +2209,6 @@ static void wx_clean_rx_ring(struct wx_ring *rx_ring)
 
 		/* free resources associated with mapping */
 		page_pool_put_full_page(rx_ring->page_pool, rx_buffer->page, false);
-		__page_frag_cache_drain(rx_buffer->page,
-					rx_buffer->pagecnt_bias);
 
 		i++;
 		rx_buffer++;
@@ -2726,11 +2685,14 @@ int wx_set_features(struct net_device *netdev, netdev_features_t features)
 	netdev_features_t changed = netdev->features ^ features;
 	struct wx *wx = netdev_priv(netdev);
 
-	if (changed & NETIF_F_RXHASH)
+	if (features & NETIF_F_RXHASH) {
 		wr32m(wx, WX_RDB_RA_CTL, WX_RDB_RA_CTL_RSS_EN,
 		      WX_RDB_RA_CTL_RSS_EN);
-	else
+		wx->rss_enabled = true;
+	} else {
 		wr32m(wx, WX_RDB_RA_CTL, WX_RDB_RA_CTL_RSS_EN, 0);
+		wx->rss_enabled = false;
+	}
 
 	if (changed &
 	    (NETIF_F_HW_VLAN_CTAG_RX |
@@ -2741,4 +2703,70 @@ int wx_set_features(struct net_device *netdev, netdev_features_t features)
 }
 EXPORT_SYMBOL(wx_set_features);
 
+void wx_set_ring(struct wx *wx, u32 new_tx_count,
+		 u32 new_rx_count, struct wx_ring *temp_ring)
+{
+	int i, err = 0;
+
+	/* Setup new Tx resources and free the old Tx resources in that order.
+	 * We can then assign the new resources to the rings via a memcpy.
+	 * The advantage to this approach is that we are guaranteed to still
+	 * have resources even in the case of an allocation failure.
+	 */
+	if (new_tx_count != wx->tx_ring_count) {
+		for (i = 0; i < wx->num_tx_queues; i++) {
+			memcpy(&temp_ring[i], wx->tx_ring[i],
+			       sizeof(struct wx_ring));
+
+			temp_ring[i].count = new_tx_count;
+			err = wx_setup_tx_resources(&temp_ring[i]);
+			if (err) {
+				wx_err(wx, "setup new tx resources failed, keep using the old config\n");
+				while (i) {
+					i--;
+					wx_free_tx_resources(&temp_ring[i]);
+				}
+				return;
+			}
+		}
+
+		for (i = 0; i < wx->num_tx_queues; i++) {
+			wx_free_tx_resources(wx->tx_ring[i]);
+
+			memcpy(wx->tx_ring[i], &temp_ring[i],
+			       sizeof(struct wx_ring));
+		}
+
+		wx->tx_ring_count = new_tx_count;
+	}
+
+	/* Repeat the process for the Rx rings if needed */
+	if (new_rx_count != wx->rx_ring_count) {
+		for (i = 0; i < wx->num_rx_queues; i++) {
+			memcpy(&temp_ring[i], wx->rx_ring[i],
+			       sizeof(struct wx_ring));
+
+			temp_ring[i].count = new_rx_count;
+			err = wx_setup_rx_resources(&temp_ring[i]);
+			if (err) {
+				wx_err(wx, "setup new rx resources failed, keep using the old config\n");
+				while (i) {
+					i--;
+					wx_free_rx_resources(&temp_ring[i]);
+				}
+				return;
+			}
+		}
+
+		for (i = 0; i < wx->num_rx_queues; i++) {
+			wx_free_rx_resources(wx->rx_ring[i]);
+			memcpy(wx->rx_ring[i], &temp_ring[i],
+			       sizeof(struct wx_ring));
+		}
+
+		wx->rx_ring_count = new_rx_count;
+	}
+}
+EXPORT_SYMBOL(wx_set_ring);
+
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.h b/drivers/net/ethernet/wangxun/libwx/wx_lib.h
index df1f4a5951f0..ec909e876720 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.h
@@ -21,6 +21,7 @@ void wx_free_irq(struct wx *wx);
 int wx_setup_isb_resources(struct wx *wx);
 void wx_free_isb_resources(struct wx *wx);
 u32 wx_misc_isb(struct wx *wx, enum wx_isb_idx idx);
+void wx_write_eitr(struct wx_q_vector *q_vector);
 void wx_configure_vectors(struct wx *wx);
 void wx_clean_all_rx_rings(struct wx *wx);
 void wx_clean_all_tx_rings(struct wx *wx);
@@ -29,5 +30,7 @@ int wx_setup_resources(struct wx *wx);
 void wx_get_stats64(struct net_device *netdev,
 		    struct rtnl_link_stats64 *stats);
 int wx_set_features(struct net_device *netdev, netdev_features_t features);
+void wx_set_ring(struct wx *wx, u32 new_tx_count,
+		 u32 new_rx_count, struct wx_ring *temp_ring);
 
 #endif /* _NGBE_LIB_H_ */
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index 165e82de772e..b4dc4f341117 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -7,6 +7,7 @@
 #include <linux/bitfield.h>
 #include <linux/netdevice.h>
 #include <linux/if_vlan.h>
+#include <linux/phylink.h>
 #include <net/ip.h>
 
 #define WX_NCSI_SUP                             0x8000
@@ -130,6 +131,15 @@
 #define WX_RDB_PFCMACDAH             0x19214
 #define WX_RDB_LXOFFTXC              0x19218
 #define WX_RDB_LXONTXC               0x1921C
+/* Flow Control Registers */
+#define WX_RDB_RFCV                  0x19200
+#define WX_RDB_RFCL                  0x19220
+#define WX_RDB_RFCL_XONE             BIT(31)
+#define WX_RDB_RFCH                  0x19260
+#define WX_RDB_RFCH_XOFFE            BIT(31)
+#define WX_RDB_RFCRT                 0x192A0
+#define WX_RDB_RFCC                  0x192A4
+#define WX_RDB_RFCC_RFCE_802_3X      BIT(3)
 /* ring assignment */
 #define WX_RDB_PL_CFG(_i)            (0x19300 + ((_i) * 4))
 #define WX_RDB_PL_CFG_L4HDR          BIT(1)
@@ -137,8 +147,16 @@
 #define WX_RDB_PL_CFG_L2HDR          BIT(3)
 #define WX_RDB_PL_CFG_TUN_TUNHDR     BIT(4)
 #define WX_RDB_PL_CFG_TUN_OUTL2HDR   BIT(5)
+#define WX_RDB_RSSTBL(_i)            (0x19400 + ((_i) * 4))
+#define WX_RDB_RSSRK(_i)             (0x19480 + ((_i) * 4))
 #define WX_RDB_RA_CTL                0x194F4
 #define WX_RDB_RA_CTL_RSS_EN         BIT(2) /* RSS Enable */
+#define WX_RDB_RA_CTL_RSS_IPV4_TCP   BIT(16)
+#define WX_RDB_RA_CTL_RSS_IPV4       BIT(17)
+#define WX_RDB_RA_CTL_RSS_IPV6       BIT(20)
+#define WX_RDB_RA_CTL_RSS_IPV6_TCP   BIT(21)
+#define WX_RDB_RA_CTL_RSS_IPV4_UDP   BIT(22)
+#define WX_RDB_RA_CTL_RSS_IPV6_UDP   BIT(23)
 
 /******************************* PSR Registers *******************************/
 /* psr control */
@@ -305,6 +323,7 @@ enum WX_MSCA_CMD_value {
 #define WX_PX_IVAR_ALLOC_VAL         0x80 /* Interrupt Allocation valid */
 #define WX_7K_ITR                    595
 #define WX_12K_ITR                   336
+#define WX_20K_ITR                   200
 #define WX_SP_MAX_EITR               0x00000FF8U
 #define WX_EM_MAX_EITR               0x00007FFCU
 
@@ -330,6 +349,7 @@ enum WX_MSCA_CMD_value {
 #define WX_PX_MPRC(_i)               (0x01020 + ((_i) * 0x40))
 /* PX_RR_CFG bit definitions */
 #define WX_PX_RR_CFG_VLAN            BIT(31)
+#define WX_PX_RR_CFG_DROP_EN         BIT(30)
 #define WX_PX_RR_CFG_SPLIT_MODE      BIT(26)
 #define WX_PX_RR_CFG_RR_THER_SHIFT   16
 #define WX_PX_RR_CFG_RR_HDR_SZ       GENMASK(15, 12)
@@ -367,8 +387,46 @@ enum WX_MSCA_CMD_value {
 #define WX_MAC_STATE_MODIFIED        0x2
 #define WX_MAC_STATE_IN_USE          0x4
 
+/* BitTimes (BT) conversion */
+#define WX_BT2KB(BT)         (((BT) + (8 * 1024 - 1)) / (8 * 1024))
+#define WX_B2BT(BT)          ((BT) * 8)
+
+/* Calculate Delay to respond to PFC */
+#define WX_PFC_D     672
+/* Calculate Cable Delay */
+#define WX_CABLE_DC  5556 /* Delay Copper */
+/* Calculate Delay incurred from higher layer */
+#define WX_HD        6144
+
+/* Calculate Interface Delay */
+#define WX_PHY_D     12800
+#define WX_MAC_D     4096
+#define WX_XAUI_D    (2 * 1024)
+#define WX_ID        (WX_MAC_D + WX_XAUI_D + WX_PHY_D)
+/* Calculate PCI Bus delay for low thresholds */
+#define WX_PCI_DELAY 10000
+
+/* Calculate delay value in bit times */
+#define WX_DV(_max_frame_link, _max_frame_tc) \
+	((36 * (WX_B2BT(_max_frame_link) + WX_PFC_D + \
+		(2 * WX_CABLE_DC) + (2 * WX_ID) + WX_HD) / 25 + 1) + \
+	 2 * WX_B2BT(_max_frame_tc))
+
+/* Calculate low threshold delay values */
+#define WX_LOW_DV(_max_frame_tc) \
+	(2 * (2 * WX_B2BT(_max_frame_tc) + (36 * WX_PCI_DELAY / 25) + 1))
+
+/* flow control */
+#define WX_DEFAULT_FCPAUSE           0xFFFF
+
 #define WX_MAX_RXD                   8192
 #define WX_MAX_TXD                   8192
+#define WX_MIN_RXD                   128
+#define WX_MIN_TXD                   128
+
+/* Number of Transmit and Receive Descriptors must be a multiple of 8 */
+#define WX_REQ_RX_DESCRIPTOR_MULTIPLE   8
+#define WX_REQ_TX_DESCRIPTOR_MULTIPLE   8
 
 #define WX_MAX_JUMBO_FRAME_SIZE      9432 /* max payload 9414 */
 #define VMDQ_P(p)                    p
@@ -787,7 +845,6 @@ struct wx_rx_buffer {
 	dma_addr_t page_dma;
 	struct page *page;
 	unsigned int page_offset;
-	u16 pagecnt_bias;
 };
 
 struct wx_queue_stats {
@@ -872,6 +929,19 @@ struct wx_q_vector {
 	struct wx_ring ring[] ____cacheline_internodealigned_in_smp;
 };
 
+struct wx_ring_feature {
+	u16 limit;      /* upper limit on feature indices */
+	u16 indices;    /* current value of indices */
+	u16 mask;       /* Mask used for feature to ring mapping */
+	u16 offset;     /* offset to start of feature */
+};
+
+enum wx_ring_f_enum {
+	RING_F_NONE = 0,
+	RING_F_RSS,
+	RING_F_ARRAY_SIZE  /* must be last in enum set */
+};
+
 enum wx_isb_idx {
 	WX_ISB_HEADER,
 	WX_ISB_MISC,
@@ -880,6 +950,11 @@ enum wx_isb_idx {
 	WX_ISB_MAX
 };
 
+struct wx_fc_info {
+	u32 high_water; /* Flow Ctrl High-water */
+	u32 low_water; /* Flow Ctrl Low-water */
+};
+
 /* Statistics counters collected by the MAC */
 struct wx_hw_stats {
 	u64 gprc;
@@ -920,6 +995,7 @@ struct wx {
 	enum sp_media_type media_type;
 	struct wx_eeprom_info eeprom;
 	struct wx_addr_filter_info addr_ctrl;
+	struct wx_fc_info fc;
 	struct wx_mac_addr *mac_table;
 	u16 device_id;
 	u16 vendor_id;
@@ -940,6 +1016,8 @@ struct wx {
 	int speed;
 	int duplex;
 	struct phy_device *phydev;
+	struct phylink *phylink;
+	struct phylink_config phylink_config;
 
 	bool wol_hw_supported;
 	bool ncsi_enabled;
@@ -967,7 +1045,10 @@ struct wx {
 	struct wx_q_vector *q_vector[64];
 
 	unsigned int queues_per_pool;
-	struct msix_entry *msix_entries;
+	struct msix_entry *msix_q_entries;
+	struct msix_entry *msix_entry;
+	bool msix_in_use;
+	struct wx_ring_feature ring_feature[RING_F_ARRAY_SIZE];
 
 	/* misc interrupt status block */
 	dma_addr_t isb_dma;
@@ -975,8 +1056,9 @@ struct wx {
 	u32 isb_tag[WX_ISB_MAX];
 
 #define WX_MAX_RETA_ENTRIES 128
+#define WX_RSS_INDIR_TBL_MAX 64
 	u8 rss_indir_tbl[WX_MAX_RETA_ENTRIES];
-
+	bool rss_enabled;
 #define WX_RSS_KEY_SIZE     40  /* size of RSS Hash Key in bytes */
 	u32 *rss_key;
 	u32 wol;
@@ -993,7 +1075,7 @@ struct wx {
 };
 
 #define WX_INTR_ALL (~0ULL)
-#define WX_INTR_Q(i) BIT(i)
+#define WX_INTR_Q(i) BIT((i) + 1)
 
 /* register operations */
 #define wr32(a, reg, value)	writel((value), ((a)->hw_addr + (reg)))
@@ -1045,4 +1127,9 @@ rd64(struct wx *wx, u32 reg)
 #define wx_dbg(wx, fmt, arg...) \
 	dev_dbg(&(wx)->pdev->dev, fmt, ##arg)
 
+static inline struct wx *phylink_to_wx(struct phylink_config *config)
+{
+	return container_of(config, struct wx, phylink_config);
+}
+
 #endif /* _WX_TYPE_H_ */
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c
index afbdf6919071..786a652ae64f 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c
@@ -7,7 +7,10 @@
 
 #include "../libwx/wx_ethtool.h"
 #include "../libwx/wx_type.h"
+#include "../libwx/wx_lib.h"
+#include "../libwx/wx_hw.h"
 #include "ngbe_ethtool.h"
+#include "ngbe_type.h"
 
 static void ngbe_get_wol(struct net_device *netdev,
 			 struct ethtool_wolinfo *wol)
@@ -41,12 +44,75 @@ static int ngbe_set_wol(struct net_device *netdev,
 	return 0;
 }
 
+static int ngbe_set_ringparam(struct net_device *netdev,
+			      struct ethtool_ringparam *ring,
+			      struct kernel_ethtool_ringparam *kernel_ring,
+			      struct netlink_ext_ack *extack)
+{
+	struct wx *wx = netdev_priv(netdev);
+	u32 new_rx_count, new_tx_count;
+	struct wx_ring *temp_ring;
+	int i;
+
+	new_tx_count = clamp_t(u32, ring->tx_pending, WX_MIN_TXD, WX_MAX_TXD);
+	new_tx_count = ALIGN(new_tx_count, WX_REQ_TX_DESCRIPTOR_MULTIPLE);
+
+	new_rx_count = clamp_t(u32, ring->rx_pending, WX_MIN_RXD, WX_MAX_RXD);
+	new_rx_count = ALIGN(new_rx_count, WX_REQ_RX_DESCRIPTOR_MULTIPLE);
+
+	if (new_tx_count == wx->tx_ring_count &&
+	    new_rx_count == wx->rx_ring_count)
+		return 0;
+
+	if (!netif_running(wx->netdev)) {
+		for (i = 0; i < wx->num_tx_queues; i++)
+			wx->tx_ring[i]->count = new_tx_count;
+		for (i = 0; i < wx->num_rx_queues; i++)
+			wx->rx_ring[i]->count = new_rx_count;
+		wx->tx_ring_count = new_tx_count;
+		wx->rx_ring_count = new_rx_count;
+
+		return 0;
+	}
+
+	/* allocate temporary buffer to store rings in */
+	i = max_t(int, wx->num_tx_queues, wx->num_rx_queues);
+	temp_ring = kvmalloc_array(i, sizeof(struct wx_ring), GFP_KERNEL);
+	if (!temp_ring)
+		return -ENOMEM;
+
+	ngbe_down(wx);
+
+	wx_set_ring(wx, new_tx_count, new_rx_count, temp_ring);
+	kvfree(temp_ring);
+
+	wx_configure(wx);
+	ngbe_up(wx);
+
+	return 0;
+}
+
+static int ngbe_set_channels(struct net_device *dev,
+			     struct ethtool_channels *ch)
+{
+	int err;
+
+	err = wx_set_channels(dev, ch);
+	if (err < 0)
+		return err;
+
+	/* use setup TC to update any traffic class queue mapping */
+	return ngbe_setup_tc(dev, netdev_get_num_tc(dev));
+}
+
 static const struct ethtool_ops ngbe_ethtool_ops = {
+	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
+				     ETHTOOL_COALESCE_TX_MAX_FRAMES_IRQ,
 	.get_drvinfo		= wx_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
-	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
-	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
-	.nway_reset		= phy_ethtool_nway_reset,
+	.get_link_ksettings	= wx_get_link_ksettings,
+	.set_link_ksettings	= wx_set_link_ksettings,
+	.nway_reset		= wx_nway_reset,
 	.get_wol		= ngbe_get_wol,
 	.set_wol		= ngbe_set_wol,
 	.get_sset_count		= wx_get_sset_count,
@@ -54,6 +120,16 @@ static const struct ethtool_ops ngbe_ethtool_ops = {
 	.get_ethtool_stats	= wx_get_ethtool_stats,
 	.get_eth_mac_stats	= wx_get_mac_stats,
 	.get_pause_stats	= wx_get_pause_stats,
+	.get_pauseparam		= wx_get_pauseparam,
+	.set_pauseparam		= wx_set_pauseparam,
+	.get_ringparam		= wx_get_ringparam,
+	.set_ringparam		= ngbe_set_ringparam,
+	.get_coalesce		= wx_get_coalesce,
+	.set_coalesce		= wx_set_coalesce,
+	.get_channels		= wx_get_channels,
+	.set_channels		= ngbe_set_channels,
+	.get_msglevel		= wx_get_msglevel,
+	.set_msglevel		= wx_set_msglevel,
 };
 
 void ngbe_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
index 3d43f808c86b..fdd6b4f70b7a 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
@@ -80,28 +80,6 @@ static void ngbe_init_type_code(struct wx *wx)
 }
 
 /**
- * ngbe_init_rss_key - Initialize wx RSS key
- * @wx: device handle
- *
- * Allocates and initializes the RSS key if it is not allocated.
- **/
-static inline int ngbe_init_rss_key(struct wx *wx)
-{
-	u32 *rss_key;
-
-	if (!wx->rss_key) {
-		rss_key = kzalloc(WX_RSS_KEY_SIZE, GFP_KERNEL);
-		if (unlikely(!rss_key))
-			return -ENOMEM;
-
-		netdev_rss_key_fill(rss_key, WX_RSS_KEY_SIZE);
-		wx->rss_key = rss_key;
-	}
-
-	return 0;
-}
-
-/**
  * ngbe_sw_init - Initialize general software structures
  * @wx: board private structure to initialize
  **/
@@ -121,10 +99,8 @@ static int ngbe_sw_init(struct wx *wx)
 
 	/* PCI config space info */
 	err = wx_sw_init(wx);
-	if (err < 0) {
-		wx_err(wx, "read of internal subsystem device id failed\n");
+	if (err < 0)
 		return err;
-	}
 
 	/* mac type, phy type , oem type */
 	ngbe_init_type_code(wx);
@@ -136,8 +112,9 @@ static int ngbe_sw_init(struct wx *wx)
 		dev_err(&pdev->dev, "Do not support MSI-X\n");
 	wx->mac.max_msix_vectors = msix_count;
 
-	if (ngbe_init_rss_key(wx))
-		return -ENOMEM;
+	wx->ring_feature[RING_F_RSS].limit = min_t(int, NGBE_MAX_RSS_INDICES,
+						   num_online_cpus());
+	wx->rss_enabled = true;
 
 	/* enable itr by default in dynamic mode */
 	wx->rx_itr_setting = 1;
@@ -177,7 +154,7 @@ static void ngbe_irq_enable(struct wx *wx, bool queues)
 	if (queues)
 		wx_intr_enable(wx, NGBE_INTR_ALL);
 	else
-		wx_intr_enable(wx, NGBE_INTR_MISC(wx));
+		wx_intr_enable(wx, NGBE_INTR_MISC);
 }
 
 /**
@@ -243,7 +220,7 @@ static int ngbe_request_msix_irqs(struct wx *wx)
 
 	for (vector = 0; vector < wx->num_q_vectors; vector++) {
 		struct wx_q_vector *q_vector = wx->q_vector[vector];
-		struct msix_entry *entry = &wx->msix_entries[vector];
+		struct msix_entry *entry = &wx->msix_q_entries[vector];
 
 		if (q_vector->tx.ring && q_vector->rx.ring)
 			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
@@ -261,7 +238,7 @@ static int ngbe_request_msix_irqs(struct wx *wx)
 		}
 	}
 
-	err = request_irq(wx->msix_entries[vector].vector,
+	err = request_irq(wx->msix_entry->vector,
 			  ngbe_msix_other, 0, netdev->name, wx);
 
 	if (err) {
@@ -274,7 +251,7 @@ static int ngbe_request_msix_irqs(struct wx *wx)
 free_queue_irqs:
 	while (vector) {
 		vector--;
-		free_irq(wx->msix_entries[vector].vector,
+		free_irq(wx->msix_q_entries[vector].vector,
 			 wx->q_vector[vector]);
 	}
 	wx_reset_interrupt_capability(wx);
@@ -336,15 +313,15 @@ static void ngbe_disable_device(struct wx *wx)
 	wx_update_stats(wx);
 }
 
-static void ngbe_down(struct wx *wx)
+void ngbe_down(struct wx *wx)
 {
-	phy_stop(wx->phydev);
+	phylink_stop(wx->phylink);
 	ngbe_disable_device(wx);
 	wx_clean_all_tx_rings(wx);
 	wx_clean_all_rx_rings(wx);
 }
 
-static void ngbe_up(struct wx *wx)
+void ngbe_up(struct wx *wx)
 {
 	wx_configure_vectors(wx);
 
@@ -361,7 +338,7 @@ static void ngbe_up(struct wx *wx)
 	if (wx->gpio_ctrl)
 		ngbe_sfp_modules_txrx_powerctl(wx, true);
 
-	phy_start(wx->phydev);
+	phylink_start(wx->phylink);
 }
 
 /**
@@ -390,7 +367,7 @@ static int ngbe_open(struct net_device *netdev)
 	if (err)
 		goto err_free_resources;
 
-	err = ngbe_phy_connect(wx);
+	err = phylink_connect_phy(wx->phylink, wx->phydev);
 	if (err)
 		goto err_free_irq;
 
@@ -406,7 +383,7 @@ static int ngbe_open(struct net_device *netdev)
 
 	return 0;
 err_dis_phy:
-	phy_disconnect(wx->phydev);
+	phylink_disconnect_phy(wx->phylink);
 err_free_irq:
 	wx_free_irq(wx);
 err_free_resources:
@@ -432,7 +409,7 @@ static int ngbe_close(struct net_device *netdev)
 	ngbe_down(wx);
 	wx_free_irq(wx);
 	wx_free_resources(wx);
-	phy_disconnect(wx->phydev);
+	phylink_disconnect_phy(wx->phylink);
 	wx_control_hw(wx, false);
 
 	return 0;
@@ -482,6 +459,39 @@ static void ngbe_shutdown(struct pci_dev *pdev)
 	}
 }
 
+/**
+ * ngbe_setup_tc - routine to configure net_device for multiple traffic
+ * classes.
+ *
+ * @dev: net device to configure
+ * @tc: number of traffic classes to enable
+ */
+int ngbe_setup_tc(struct net_device *dev, u8 tc)
+{
+	struct wx *wx = netdev_priv(dev);
+
+	/* Hardware has to reinitialize queues and interrupts to
+	 * match packet buffer alignment. Unfortunately, the
+	 * hardware is not flexible enough to do this dynamically.
+	 */
+	if (netif_running(dev))
+		ngbe_close(dev);
+
+	wx_clear_interrupt_scheme(wx);
+
+	if (tc)
+		netdev_set_num_tc(dev, tc);
+	else
+		netdev_reset_tc(dev);
+
+	wx_init_interrupt_scheme(wx);
+
+	if (netif_running(dev))
+		ngbe_open(dev);
+
+	return 0;
+}
+
 static const struct net_device_ops ngbe_netdev_ops = {
 	.ndo_open               = ngbe_open,
 	.ndo_stop               = ngbe_close,
@@ -584,6 +594,7 @@ static int ngbe_probe(struct pci_dev *pdev,
 
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 	netdev->priv_flags |= IFF_SUPP_NOFCS;
+	netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
 	netdev->min_mtu = ETH_MIN_MTU;
 	netdev->max_mtu = WX_MAX_JUMBO_FRAME_SIZE -
@@ -682,6 +693,7 @@ static int ngbe_probe(struct pci_dev *pdev,
 	return 0;
 
 err_register:
+	phylink_destroy(wx->phylink);
 	wx_control_hw(wx, false);
 err_clear_interrupt_scheme:
 	wx_clear_interrupt_scheme(wx);
@@ -711,9 +723,11 @@ static void ngbe_remove(struct pci_dev *pdev)
 
 	netdev = wx->netdev;
 	unregister_netdev(netdev);
+	phylink_destroy(wx->phylink);
 	pci_release_selected_regions(pdev,
 				     pci_select_bars(pdev, IORESOURCE_MEM));
 
+	kfree(wx->rss_key);
 	kfree(wx->mac_table);
 	wx_clear_interrupt_scheme(wx);
 
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
index 6302ecca71bb..ec54b18c5fe7 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
@@ -56,22 +56,28 @@ static int ngbe_phy_write_reg_c22(struct mii_bus *bus, int phy_addr,
 	return ret;
 }
 
-static void ngbe_handle_link_change(struct net_device *dev)
+static void ngbe_mac_config(struct phylink_config *config, unsigned int mode,
+			    const struct phylink_link_state *state)
 {
-	struct wx *wx = netdev_priv(dev);
-	struct phy_device *phydev;
+}
+
+static void ngbe_mac_link_down(struct phylink_config *config,
+			       unsigned int mode, phy_interface_t interface)
+{
+}
+
+static void ngbe_mac_link_up(struct phylink_config *config,
+			     struct phy_device *phy,
+			     unsigned int mode, phy_interface_t interface,
+			     int speed, int duplex,
+			     bool tx_pause, bool rx_pause)
+{
+	struct wx *wx = phylink_to_wx(config);
 	u32 lan_speed, reg;
 
-	phydev = wx->phydev;
-	if (!(wx->link != phydev->link ||
-	      wx->speed != phydev->speed ||
-	      wx->duplex != phydev->duplex))
-		return;
+	wx_fc_enable(wx, tx_pause, rx_pause);
 
-	wx->link = phydev->link;
-	wx->speed = phydev->speed;
-	wx->duplex = phydev->duplex;
-	switch (phydev->speed) {
+	switch (speed) {
 	case SPEED_10:
 		lan_speed = 0;
 		break;
@@ -83,54 +89,51 @@ static void ngbe_handle_link_change(struct net_device *dev)
 		lan_speed = 2;
 		break;
 	}
+
 	wr32m(wx, NGBE_CFG_LAN_SPEED, 0x3, lan_speed);
 
-	if (phydev->link) {
-		reg = rd32(wx, WX_MAC_TX_CFG);
-		reg &= ~WX_MAC_TX_CFG_SPEED_MASK;
-		reg |= WX_MAC_TX_CFG_SPEED_1G | WX_MAC_TX_CFG_TE;
-		wr32(wx, WX_MAC_TX_CFG, reg);
-		/* Re configure MAC RX */
-		reg = rd32(wx, WX_MAC_RX_CFG);
-		wr32(wx, WX_MAC_RX_CFG, reg);
-		wr32(wx, WX_MAC_PKT_FLT, WX_MAC_PKT_FLT_PR);
-		reg = rd32(wx, WX_MAC_WDG_TIMEOUT);
-		wr32(wx, WX_MAC_WDG_TIMEOUT, reg);
-	}
-	phy_print_status(phydev);
+	reg = rd32(wx, WX_MAC_TX_CFG);
+	reg &= ~WX_MAC_TX_CFG_SPEED_MASK;
+	reg |= WX_MAC_TX_CFG_SPEED_1G | WX_MAC_TX_CFG_TE;
+	wr32(wx, WX_MAC_TX_CFG, reg);
+
+	/* Re configure MAC Rx */
+	reg = rd32(wx, WX_MAC_RX_CFG);
+	wr32(wx, WX_MAC_RX_CFG, reg);
+	wr32(wx, WX_MAC_PKT_FLT, WX_MAC_PKT_FLT_PR);
+	reg = rd32(wx, WX_MAC_WDG_TIMEOUT);
+	wr32(wx, WX_MAC_WDG_TIMEOUT, reg);
 }
 
-int ngbe_phy_connect(struct wx *wx)
+static const struct phylink_mac_ops ngbe_mac_ops = {
+	.mac_config = ngbe_mac_config,
+	.mac_link_down = ngbe_mac_link_down,
+	.mac_link_up = ngbe_mac_link_up,
+};
+
+static int ngbe_phylink_init(struct wx *wx)
 {
-	int ret;
+	struct phylink_config *config;
+	phy_interface_t phy_mode;
+	struct phylink *phylink;
 
-	ret = phy_connect_direct(wx->netdev,
-				 wx->phydev,
-				 ngbe_handle_link_change,
-				 PHY_INTERFACE_MODE_RGMII_ID);
-	if (ret) {
-		wx_err(wx, "PHY connect failed.\n");
-		return ret;
-	}
+	config = &wx->phylink_config;
+	config->dev = &wx->netdev->dev;
+	config->type = PHYLINK_NETDEV;
+	config->mac_capabilities = MAC_1000FD | MAC_100FD | MAC_10FD |
+				   MAC_SYM_PAUSE | MAC_ASYM_PAUSE;
+	config->mac_managed_pm = true;
 
-	return 0;
-}
+	phy_mode = PHY_INTERFACE_MODE_RGMII_ID;
+	__set_bit(PHY_INTERFACE_MODE_RGMII_ID, config->supported_interfaces);
 
-static void ngbe_phy_fixup(struct wx *wx)
-{
-	struct phy_device *phydev = wx->phydev;
-	struct ethtool_eee eee;
-
-	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Half_BIT);
-	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT);
-	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
-
-	phydev->mac_managed_pm = true;
-	if (wx->mac_type != em_mac_type_mdi)
-		return;
-	/* disable EEE, internal phy does not support eee */
-	memset(&eee, 0, sizeof(eee));
-	phy_ethtool_set_eee(phydev, &eee);
+	phylink = phylink_create(config, NULL, phy_mode, &ngbe_mac_ops);
+	if (IS_ERR(phylink))
+		return PTR_ERR(phylink);
+
+	wx->phylink = phylink;
+
+	return 0;
 }
 
 int ngbe_mdio_init(struct wx *wx)
@@ -165,11 +168,16 @@ int ngbe_mdio_init(struct wx *wx)
 		return -ENODEV;
 
 	phy_attached_info(wx->phydev);
-	ngbe_phy_fixup(wx);
 
 	wx->link = 0;
 	wx->speed = 0;
 	wx->duplex = 0;
 
+	ret = ngbe_phylink_init(wx);
+	if (ret) {
+		wx_err(wx, "failed to init phylink: %d\n", ret);
+		return ret;
+	}
+
 	return 0;
 }
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.h b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.h
index 0a6400dd89c4..f610b771888a 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.h
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.h
@@ -7,6 +7,5 @@
 #ifndef _NGBE_MDIO_H_
 #define _NGBE_MDIO_H_
 
-int ngbe_phy_connect(struct wx *wx);
 int ngbe_mdio_init(struct wx *wx);
 #endif /* _NGBE_MDIO_H_ */
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
index ff754d69bdf6..f48ed7fc1805 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
@@ -80,7 +80,7 @@
 				NGBE_PX_MISC_IEN_GPIO)
 
 #define NGBE_INTR_ALL				0x1FF
-#define NGBE_INTR_MISC(A)			BIT((A)->num_q_vectors)
+#define NGBE_INTR_MISC				BIT(0)
 
 #define NGBE_PHY_CONFIG(reg_offset)		(0x14000 + ((reg_offset) * 4))
 #define NGBE_CFG_LAN_SPEED			0x14440
@@ -105,6 +105,7 @@
 #define NGBE_FW_CMD_ST_FAIL			0x70657376
 
 #define NGBE_MAX_FDIR_INDICES			7
+#define NGBE_MAX_RSS_INDICES			8
 
 #define NGBE_MAX_RX_QUEUES			(NGBE_MAX_FDIR_INDICES + 1)
 #define NGBE_MAX_TX_QUEUES			(NGBE_MAX_FDIR_INDICES + 1)
@@ -130,4 +131,8 @@
 
 extern char ngbe_driver_name[];
 
+void ngbe_down(struct wx *wx);
+void ngbe_up(struct wx *wx);
+int ngbe_setup_tc(struct net_device *dev, u8 tc);
+
 #endif /* _NGBE_TYPE_H_ */
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c
index 3f336a088e43..db675512ce4d 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c
@@ -7,43 +7,93 @@
 
 #include "../libwx/wx_ethtool.h"
 #include "../libwx/wx_type.h"
+#include "../libwx/wx_lib.h"
 #include "txgbe_type.h"
 #include "txgbe_ethtool.h"
 
-static int txgbe_nway_reset(struct net_device *netdev)
+static int txgbe_set_ringparam(struct net_device *netdev,
+			       struct ethtool_ringparam *ring,
+			       struct kernel_ethtool_ringparam *kernel_ring,
+			       struct netlink_ext_ack *extack)
 {
-	struct txgbe *txgbe = netdev_to_txgbe(netdev);
+	struct wx *wx = netdev_priv(netdev);
+	u32 new_rx_count, new_tx_count;
+	struct wx_ring *temp_ring;
+	int i;
 
-	return phylink_ethtool_nway_reset(txgbe->phylink);
-}
+	new_tx_count = clamp_t(u32, ring->tx_pending, WX_MIN_TXD, WX_MAX_TXD);
+	new_tx_count = ALIGN(new_tx_count, WX_REQ_TX_DESCRIPTOR_MULTIPLE);
 
-static int txgbe_get_link_ksettings(struct net_device *netdev,
-				    struct ethtool_link_ksettings *cmd)
-{
-	struct txgbe *txgbe = netdev_to_txgbe(netdev);
+	new_rx_count = clamp_t(u32, ring->rx_pending, WX_MIN_RXD, WX_MAX_RXD);
+	new_rx_count = ALIGN(new_rx_count, WX_REQ_RX_DESCRIPTOR_MULTIPLE);
+
+	if (new_tx_count == wx->tx_ring_count &&
+	    new_rx_count == wx->rx_ring_count)
+		return 0;
+
+	if (!netif_running(wx->netdev)) {
+		for (i = 0; i < wx->num_tx_queues; i++)
+			wx->tx_ring[i]->count = new_tx_count;
+		for (i = 0; i < wx->num_rx_queues; i++)
+			wx->rx_ring[i]->count = new_rx_count;
+		wx->tx_ring_count = new_tx_count;
+		wx->rx_ring_count = new_rx_count;
+
+		return 0;
+	}
 
-	return phylink_ethtool_ksettings_get(txgbe->phylink, cmd);
+	/* allocate temporary buffer to store rings in */
+	i = max_t(int, wx->num_tx_queues, wx->num_rx_queues);
+	temp_ring = kvmalloc_array(i, sizeof(struct wx_ring), GFP_KERNEL);
+	if (!temp_ring)
+		return -ENOMEM;
+
+	txgbe_down(wx);
+
+	wx_set_ring(wx, new_tx_count, new_rx_count, temp_ring);
+	kvfree(temp_ring);
+
+	txgbe_up(wx);
+
+	return 0;
 }
 
-static int txgbe_set_link_ksettings(struct net_device *netdev,
-				    const struct ethtool_link_ksettings *cmd)
+static int txgbe_set_channels(struct net_device *dev,
+			      struct ethtool_channels *ch)
 {
-	struct txgbe *txgbe = netdev_to_txgbe(netdev);
+	int err;
+
+	err = wx_set_channels(dev, ch);
+	if (err < 0)
+		return err;
 
-	return phylink_ethtool_ksettings_set(txgbe->phylink, cmd);
+	/* use setup TC to update any traffic class queue mapping */
+	return txgbe_setup_tc(dev, netdev_get_num_tc(dev));
 }
 
 static const struct ethtool_ops txgbe_ethtool_ops = {
+	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
+				     ETHTOOL_COALESCE_TX_MAX_FRAMES_IRQ,
 	.get_drvinfo		= wx_get_drvinfo,
-	.nway_reset		= txgbe_nway_reset,
+	.nway_reset		= wx_nway_reset,
 	.get_link		= ethtool_op_get_link,
-	.get_link_ksettings	= txgbe_get_link_ksettings,
-	.set_link_ksettings	= txgbe_set_link_ksettings,
+	.get_link_ksettings	= wx_get_link_ksettings,
+	.set_link_ksettings	= wx_set_link_ksettings,
 	.get_sset_count		= wx_get_sset_count,
 	.get_strings		= wx_get_strings,
 	.get_ethtool_stats	= wx_get_ethtool_stats,
 	.get_eth_mac_stats	= wx_get_mac_stats,
 	.get_pause_stats	= wx_get_pause_stats,
+	.get_pauseparam		= wx_get_pauseparam,
+	.set_pauseparam		= wx_set_pauseparam,
+	.get_ringparam		= wx_get_ringparam,
+	.set_ringparam		= txgbe_set_ringparam,
+	.get_coalesce		= wx_get_coalesce,
+	.set_coalesce		= wx_set_coalesce,
+	.get_channels		= wx_get_channels,
+	.set_channels		= txgbe_set_channels,
+	.get_msglevel		= wx_get_msglevel,
+	.set_msglevel		= wx_set_msglevel,
 };
 
 void txgbe_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
index 70f0b5c01dac..3b151c410a5c 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
@@ -86,7 +86,7 @@ static void txgbe_irq_enable(struct wx *wx, bool queues)
 	wr32(wx, WX_PX_MISC_IEN, TXGBE_PX_MISC_IEN_MASK);
 
 	/* unmask interrupt */
-	wx_intr_enable(wx, TXGBE_INTR_MISC(wx));
+	wx_intr_enable(wx, TXGBE_INTR_MISC);
 	if (queues)
 		wx_intr_enable(wx, TXGBE_INTR_QALL(wx));
 }
@@ -145,7 +145,7 @@ static int txgbe_request_msix_irqs(struct wx *wx)
 
 	for (vector = 0; vector < wx->num_q_vectors; vector++) {
 		struct wx_q_vector *q_vector = wx->q_vector[vector];
-		struct msix_entry *entry = &wx->msix_entries[vector];
+		struct msix_entry *entry = &wx->msix_q_entries[vector];
 
 		if (q_vector->tx.ring && q_vector->rx.ring)
 			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
@@ -168,7 +168,7 @@ static int txgbe_request_msix_irqs(struct wx *wx)
 free_queue_irqs:
 	while (vector) {
 		vector--;
-		free_irq(wx->msix_entries[vector].vector,
+		free_irq(wx->msix_q_entries[vector].vector,
 			 wx->q_vector[vector]);
 	}
 	wx_reset_interrupt_capability(wx);
@@ -206,7 +206,6 @@ static int txgbe_request_irq(struct wx *wx)
 static void txgbe_up_complete(struct wx *wx)
 {
 	struct net_device *netdev = wx->netdev;
-	struct txgbe *txgbe;
 
 	wx_control_hw(wx, true);
 	wx_configure_vectors(wx);
@@ -215,8 +214,7 @@ static void txgbe_up_complete(struct wx *wx)
 	smp_mb__before_atomic();
 	wx_napi_enable_all(wx);
 
-	txgbe = netdev_to_txgbe(netdev);
-	phylink_start(txgbe->phylink);
+	phylink_start(wx->phylink);
 
 	/* clear any pending interrupts, may auto mask */
 	rd32(wx, WX_PX_IC(0));
@@ -290,18 +288,22 @@ static void txgbe_disable_device(struct wx *wx)
 	wx_update_stats(wx);
 }
 
-static void txgbe_down(struct wx *wx)
+void txgbe_down(struct wx *wx)
 {
-	struct txgbe *txgbe = netdev_to_txgbe(wx->netdev);
-
 	txgbe_disable_device(wx);
 	txgbe_reset(wx);
-	phylink_stop(txgbe->phylink);
+	phylink_stop(wx->phylink);
 
 	wx_clean_all_tx_rings(wx);
 	wx_clean_all_rx_rings(wx);
 }
 
+void txgbe_up(struct wx *wx)
+{
+	wx_configure(wx);
+	txgbe_up_complete(wx);
+}
+
 /**
  *  txgbe_init_type_code - Initialize the shared code
  *  @wx: pointer to hardware structure
@@ -364,10 +366,8 @@ static int txgbe_sw_init(struct wx *wx)
 
 	/* PCI config space info */
 	err = wx_sw_init(wx);
-	if (err < 0) {
-		wx_err(wx, "read of internal subsystem device id failed\n");
+	if (err < 0)
 		return err;
-	}
 
 	txgbe_init_type_code(wx);
 
@@ -378,6 +378,10 @@ static int txgbe_sw_init(struct wx *wx)
 		wx_err(wx, "Do not support MSI-X\n");
 	wx->mac.max_msix_vectors = msix_count;
 
+	wx->ring_feature[RING_F_RSS].limit = min_t(int, TXGBE_MAX_RSS_INDICES,
+						   num_online_cpus());
+	wx->rss_enabled = true;
+
 	/* enable itr by default in dynamic mode */
 	wx->rx_itr_setting = 1;
 	wx->tx_itr_setting = 1;
@@ -504,6 +508,41 @@ static void txgbe_shutdown(struct pci_dev *pdev)
 	}
 }
 
+/**
+ * txgbe_setup_tc - routine to configure net_device for multiple traffic
+ * classes.
+ *
+ * @dev: net device to configure
+ * @tc: number of traffic classes to enable
+ */
+int txgbe_setup_tc(struct net_device *dev, u8 tc)
+{
+	struct wx *wx = netdev_priv(dev);
+
+	/* Hardware has to reinitialize queues and interrupts to
+	 * match packet buffer alignment. Unfortunately, the
+	 * hardware is not flexible enough to do this dynamically.
+	 */
+	if (netif_running(dev))
+		txgbe_close(dev);
+	else
+		txgbe_reset(wx);
+
+	wx_clear_interrupt_scheme(wx);
+
+	if (tc)
+		netdev_set_num_tc(dev, tc);
+	else
+		netdev_reset_tc(dev);
+
+	wx_init_interrupt_scheme(wx);
+
+	if (netif_running(dev))
+		txgbe_open(dev);
+
+	return 0;
+}
+
 static const struct net_device_ops txgbe_netdev_ops = {
 	.ndo_open               = txgbe_open,
 	.ndo_stop               = txgbe_close,
@@ -640,6 +679,7 @@ static int txgbe_probe(struct pci_dev *pdev,
 
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 	netdev->priv_flags |= IFF_SUPP_NOFCS;
+	netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
 	netdev->min_mtu = ETH_MIN_MTU;
 	netdev->max_mtu = WX_MAX_JUMBO_FRAME_SIZE -
@@ -777,6 +817,7 @@ static void txgbe_remove(struct pci_dev *pdev)
 	pci_release_selected_regions(pdev,
 				     pci_select_bars(pdev, IORESOURCE_MEM));
 
+	kfree(wx->rss_key);
 	kfree(wx->mac_table);
 	wx_clear_interrupt_scheme(wx);
 
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
index b6c06adb8656..1b84d495d14e 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
@@ -159,7 +159,8 @@ static int txgbe_mdio_pcs_init(struct txgbe *txgbe)
 static struct phylink_pcs *txgbe_phylink_mac_select(struct phylink_config *config,
 						    phy_interface_t interface)
 {
-	struct txgbe *txgbe = netdev_to_txgbe(to_net_dev(config->dev));
+	struct wx *wx = phylink_to_wx(config);
+	struct txgbe *txgbe = wx->priv;
 
 	if (interface == PHY_INTERFACE_MODE_10GBASER)
 		return &txgbe->xpcs->pcs;
@@ -175,7 +176,7 @@ static void txgbe_mac_config(struct phylink_config *config, unsigned int mode,
 static void txgbe_mac_link_down(struct phylink_config *config,
 				unsigned int mode, phy_interface_t interface)
 {
-	struct wx *wx = netdev_priv(to_net_dev(config->dev));
+	struct wx *wx = phylink_to_wx(config);
 
 	wr32m(wx, WX_MAC_TX_CFG, WX_MAC_TX_CFG_TE, 0);
 }
@@ -186,9 +187,11 @@ static void txgbe_mac_link_up(struct phylink_config *config,
 			      int speed, int duplex,
 			      bool tx_pause, bool rx_pause)
 {
-	struct wx *wx = netdev_priv(to_net_dev(config->dev));
+	struct wx *wx = phylink_to_wx(config);
 	u32 txcfg, wdg;
 
+	wx_fc_enable(wx, tx_pause, rx_pause);
+
 	txcfg = rd32(wx, WX_MAC_TX_CFG);
 	txcfg &= ~WX_MAC_TX_CFG_SPEED_MASK;
 
@@ -217,7 +220,7 @@ static void txgbe_mac_link_up(struct phylink_config *config,
 static int txgbe_mac_prepare(struct phylink_config *config, unsigned int mode,
 			     phy_interface_t interface)
 {
-	struct wx *wx = netdev_priv(to_net_dev(config->dev));
+	struct wx *wx = phylink_to_wx(config);
 
 	wr32m(wx, WX_MAC_TX_CFG, WX_MAC_TX_CFG_TE, 0);
 	wr32m(wx, WX_MAC_RX_CFG, WX_MAC_RX_CFG_RE, 0);
@@ -228,7 +231,7 @@ static int txgbe_mac_prepare(struct phylink_config *config, unsigned int mode,
 static int txgbe_mac_finish(struct phylink_config *config, unsigned int mode,
 			    phy_interface_t interface)
 {
-	struct wx *wx = netdev_priv(to_net_dev(config->dev));
+	struct wx *wx = phylink_to_wx(config);
 
 	txgbe_enable_sec_tx_path(wx);
 	wr32m(wx, WX_MAC_RX_CFG, WX_MAC_RX_CFG_RE, WX_MAC_RX_CFG_RE);
@@ -253,10 +256,7 @@ static int txgbe_phylink_init(struct txgbe *txgbe)
 	phy_interface_t phy_mode;
 	struct phylink *phylink;
 
-	config = devm_kzalloc(&wx->pdev->dev, sizeof(*config), GFP_KERNEL);
-	if (!config)
-		return -ENOMEM;
-
+	config = &wx->phylink_config;
 	config->dev = &wx->netdev->dev;
 	config->type = PHYLINK_NETDEV;
 	config->mac_capabilities = MAC_10000FD | MAC_1000FD | MAC_100FD |
@@ -287,7 +287,7 @@ static int txgbe_phylink_init(struct txgbe *txgbe)
 		}
 	}
 
-	txgbe->phylink = phylink;
+	wx->phylink = phylink;
 
 	return 0;
 }
@@ -483,11 +483,11 @@ static void txgbe_irq_handler(struct irq_desc *desc)
 		    TXGBE_PX_MISC_ETH_AN)) {
 		u32 reg = rd32(wx, TXGBE_CFG_PORT_ST);
 
-		phylink_mac_change(txgbe->phylink, !!(reg & TXGBE_CFG_PORT_ST_LINK_UP));
+		phylink_mac_change(wx->phylink, !!(reg & TXGBE_CFG_PORT_ST_LINK_UP));
 	}
 
 	/* unmask interrupt */
-	wx_intr_enable(wx, TXGBE_INTR_MISC(wx));
+	wx_intr_enable(wx, TXGBE_INTR_MISC);
 }
 
 static int txgbe_gpio_init(struct txgbe *txgbe)
@@ -531,7 +531,12 @@ static int txgbe_gpio_init(struct txgbe *txgbe)
 				     sizeof(*girq->parents), GFP_KERNEL);
 	if (!girq->parents)
 		return -ENOMEM;
-	girq->parents[0] = wx->msix_entries[wx->num_q_vectors].vector;
+
+	/* now only suuported on MSI-X interrupt */
+	if (!wx->msix_entry)
+		return -EPERM;
+
+	girq->parents[0] = wx->msix_entry->vector;
 	girq->default_type = IRQ_TYPE_NONE;
 	girq->handler = handle_bad_irq;
 
@@ -701,6 +706,7 @@ static int txgbe_ext_phy_init(struct txgbe *txgbe)
 
 int txgbe_init_phy(struct txgbe *txgbe)
 {
+	struct wx *wx = txgbe->wx;
 	int ret;
 
 	if (txgbe->wx->media_type == sp_media_copper)
@@ -708,46 +714,48 @@ int txgbe_init_phy(struct txgbe *txgbe)
 
 	ret = txgbe_swnodes_register(txgbe);
 	if (ret) {
-		wx_err(txgbe->wx, "failed to register software nodes\n");
+		wx_err(wx, "failed to register software nodes\n");
 		return ret;
 	}
 
 	ret = txgbe_mdio_pcs_init(txgbe);
 	if (ret) {
-		wx_err(txgbe->wx, "failed to init mdio pcs: %d\n", ret);
+		wx_err(wx, "failed to init mdio pcs: %d\n", ret);
 		goto err_unregister_swnode;
 	}
 
 	ret = txgbe_phylink_init(txgbe);
 	if (ret) {
-		wx_err(txgbe->wx, "failed to init phylink\n");
+		wx_err(wx, "failed to init phylink\n");
 		goto err_destroy_xpcs;
 	}
 
 	ret = txgbe_gpio_init(txgbe);
 	if (ret) {
-		wx_err(txgbe->wx, "failed to init gpio\n");
+		wx_err(wx, "failed to init gpio\n");
 		goto err_destroy_phylink;
 	}
 
 	ret = txgbe_clock_register(txgbe);
 	if (ret) {
-		wx_err(txgbe->wx, "failed to register clock: %d\n", ret);
+		wx_err(wx, "failed to register clock: %d\n", ret);
 		goto err_destroy_phylink;
 	}
 
 	ret = txgbe_i2c_register(txgbe);
 	if (ret) {
-		wx_err(txgbe->wx, "failed to init i2c interface: %d\n", ret);
+		wx_err(wx, "failed to init i2c interface: %d\n", ret);
 		goto err_unregister_clk;
 	}
 
 	ret = txgbe_sfp_register(txgbe);
 	if (ret) {
-		wx_err(txgbe->wx, "failed to register sfp\n");
+		wx_err(wx, "failed to register sfp\n");
 		goto err_unregister_i2c;
 	}
 
+	wx->msix_in_use = true;
+
 	return 0;
 
 err_unregister_i2c:
@@ -756,7 +764,7 @@ err_unregister_clk:
 	clkdev_drop(txgbe->clock);
 	clk_unregister(txgbe->clk);
 err_destroy_phylink:
-	phylink_destroy(txgbe->phylink);
+	phylink_destroy(wx->phylink);
 err_destroy_xpcs:
 	xpcs_destroy(txgbe->xpcs);
 err_unregister_swnode:
@@ -768,8 +776,8 @@ err_unregister_swnode:
 void txgbe_remove_phy(struct txgbe *txgbe)
 {
 	if (txgbe->wx->media_type == sp_media_copper) {
-		phylink_disconnect_phy(txgbe->phylink);
-		phylink_destroy(txgbe->phylink);
+		phylink_disconnect_phy(txgbe->wx->phylink);
+		phylink_destroy(txgbe->wx->phylink);
 		return;
 	}
 
@@ -777,7 +785,8 @@ void txgbe_remove_phy(struct txgbe *txgbe)
 	platform_device_unregister(txgbe->i2c_dev);
 	clkdev_drop(txgbe->clock);
 	clk_unregister(txgbe->clk);
-	phylink_destroy(txgbe->phylink);
+	phylink_destroy(txgbe->wx->phylink);
 	xpcs_destroy(txgbe->xpcs);
 	software_node_unregister_node_group(txgbe->nodes.group);
+	txgbe->wx->msix_in_use = false;
 }
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
index 3ba9ce43f394..270a6fd9ad0b 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
@@ -98,6 +98,7 @@
 
 #define TXGBE_MAX_MSIX_VECTORS          64
 #define TXGBE_MAX_FDIR_INDICES          63
+#define TXGBE_MAX_RSS_INDICES           63
 
 #define TXGBE_MAX_RX_QUEUES   (TXGBE_MAX_FDIR_INDICES + 1)
 #define TXGBE_MAX_TX_QUEUES   (TXGBE_MAX_FDIR_INDICES + 1)
@@ -122,19 +123,16 @@
 #define TXGBE_DEFAULT_RX_WORK           128
 #endif
 
-#define TXGBE_INTR_MISC(A)    BIT((A)->num_q_vectors)
-#define TXGBE_INTR_QALL(A)    (TXGBE_INTR_MISC(A) - 1)
+#define TXGBE_INTR_MISC       BIT(0)
+#define TXGBE_INTR_QALL(A)    GENMASK((A)->num_q_vectors, 1)
 
 #define TXGBE_MAX_EITR        GENMASK(11, 3)
 
 extern char txgbe_driver_name[];
 
-static inline struct txgbe *netdev_to_txgbe(struct net_device *netdev)
-{
-	struct wx *wx = netdev_priv(netdev);
-
-	return wx->priv;
-}
+void txgbe_down(struct wx *wx);
+void txgbe_up(struct wx *wx);
+int txgbe_setup_tc(struct net_device *dev, u8 tc);
 
 #define NODE_PROP(_NAME, _PROP)			\
 	(const struct software_node) {		\
@@ -175,7 +173,6 @@ struct txgbe {
 	struct wx *wx;
 	struct txgbe_nodes nodes;
 	struct dw_xpcs *xpcs;
-	struct phylink *phylink;
 	struct platform_device *sfp_dev;
 	struct platform_device *i2c_dev;
 	struct clk_lookup *clock;
diff --git a/drivers/net/ethernet/xilinx/Kconfig b/drivers/net/ethernet/xilinx/Kconfig
index 0014729b8865..35d96c633a33 100644
--- a/drivers/net/ethernet/xilinx/Kconfig
+++ b/drivers/net/ethernet/xilinx/Kconfig
@@ -26,6 +26,7 @@ config XILINX_EMACLITE
 config XILINX_AXI_EMAC
 	tristate "Xilinx 10/100/1000 AXI Ethernet support"
 	depends on HAS_IOMEM
+	depends on XILINX_DMA
 	select PHYLINK
 	help
 	  This driver supports the 10/100/1000 Ethernet from Xilinx for the
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h
index 575ff9de8985..807ead678551 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet.h
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h
@@ -14,6 +14,7 @@
 #include <linux/interrupt.h>
 #include <linux/if_vlan.h>
 #include <linux/phylink.h>
+#include <linux/skbuff.h>
 
 /* Packet size info */
 #define XAE_HDR_SIZE			14 /* Size of Ethernet header */
@@ -379,6 +380,22 @@ struct axidma_bd {
 #define XAE_NUM_MISC_CLOCKS 3
 
 /**
+ * struct skbuf_dma_descriptor - skb for each dma descriptor
+ * @sgl: Pointer for sglist.
+ * @desc: Pointer to dma descriptor.
+ * @dma_address: dma address of sglist.
+ * @skb: Pointer to SKB transferred using DMA
+ * @sg_len: number of entries in the sglist.
+ */
+struct skbuf_dma_descriptor {
+	struct scatterlist sgl[MAX_SKB_FRAGS + 1];
+	struct dma_async_tx_descriptor *desc;
+	dma_addr_t dma_address;
+	struct sk_buff *skb;
+	int sg_len;
+};
+
+/**
  * struct axienet_local - axienet private per device data
  * @ndev:	Pointer for net_device to which it will be attached.
  * @dev:	Pointer to device structure
@@ -435,6 +452,15 @@ struct axidma_bd {
  * @coalesce_usec_rx:	IRQ coalesce delay for RX
  * @coalesce_count_tx:	Store the irq coalesce on TX side.
  * @coalesce_usec_tx:	IRQ coalesce delay for TX
+ * @use_dmaengine: flag to check dmaengine framework usage.
+ * @tx_chan:	TX DMA channel.
+ * @rx_chan:	RX DMA channel.
+ * @tx_skb_ring: Pointer to TX skb ring buffer array.
+ * @rx_skb_ring: Pointer to RX skb ring buffer array.
+ * @tx_ring_head: TX skb ring buffer head index.
+ * @tx_ring_tail: TX skb ring buffer tail index.
+ * @rx_ring_head: RX skb ring buffer head index.
+ * @rx_ring_tail: RX skb ring buffer tail index.
  */
 struct axienet_local {
 	struct net_device *ndev;
@@ -499,6 +525,15 @@ struct axienet_local {
 	u32 coalesce_usec_rx;
 	u32 coalesce_count_tx;
 	u32 coalesce_usec_tx;
+	u8  use_dmaengine;
+	struct dma_chan *tx_chan;
+	struct dma_chan *rx_chan;
+	struct skbuf_dma_descriptor **tx_skb_ring;
+	struct skbuf_dma_descriptor **rx_skb_ring;
+	int tx_ring_head;
+	int tx_ring_tail;
+	int rx_ring_head;
+	int rx_ring_tail;
 };
 
 /**
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 82d0d44b2b02..aaf780fd4f5e 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -38,6 +38,11 @@
 #include <linux/phy.h>
 #include <linux/mii.h>
 #include <linux/ethtool.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/dma/xilinx_dma.h>
+#include <linux/circ_buf.h>
+#include <net/netdev_queues.h>
 
 #include "xilinx_axienet.h"
 
@@ -47,6 +52,9 @@
 #define TX_BD_NUM_MIN			(MAX_SKB_FRAGS + 1)
 #define TX_BD_NUM_MAX			4096
 #define RX_BD_NUM_MAX			4096
+#define DMA_NUM_APP_WORDS		5
+#define LEN_APP				4
+#define RX_BUF_NUM_DEFAULT		128
 
 /* Must be shorter than length of ethtool_drvinfo.driver field to fit */
 #define DRIVER_NAME		"xaxienet"
@@ -55,6 +63,8 @@
 
 #define AXIENET_REGS_N		40
 
+static void axienet_rx_submit_desc(struct net_device *ndev);
+
 /* Match table for of_platform binding */
 static const struct of_device_id axienet_of_match[] = {
 	{ .compatible = "xlnx,axi-ethernet-1.00.a", },
@@ -120,6 +130,16 @@ static struct axienet_option axienet_options[] = {
 	{}
 };
 
+static struct skbuf_dma_descriptor *axienet_get_rx_desc(struct axienet_local *lp, int i)
+{
+	return lp->rx_skb_ring[i & (RX_BUF_NUM_DEFAULT - 1)];
+}
+
+static struct skbuf_dma_descriptor *axienet_get_tx_desc(struct axienet_local *lp, int i)
+{
+	return lp->tx_skb_ring[i & (TX_BD_NUM_MAX - 1)];
+}
+
 /**
  * axienet_dma_in32 - Memory mapped Axi DMA register read
  * @lp:		Pointer to axienet local structure
@@ -589,10 +609,6 @@ static int axienet_device_reset(struct net_device *ndev)
 	struct axienet_local *lp = netdev_priv(ndev);
 	int ret;
 
-	ret = __axienet_device_reset(lp);
-	if (ret)
-		return ret;
-
 	lp->max_frm_size = XAE_MAX_VLAN_FRAME_SIZE;
 	lp->options |= XAE_OPTION_VLAN;
 	lp->options &= (~XAE_OPTION_JUMBO);
@@ -606,11 +622,17 @@ static int axienet_device_reset(struct net_device *ndev)
 			lp->options |= XAE_OPTION_JUMBO;
 	}
 
-	ret = axienet_dma_bd_init(ndev);
-	if (ret) {
-		netdev_err(ndev, "%s: descriptor allocation failed\n",
-			   __func__);
-		return ret;
+	if (!lp->use_dmaengine) {
+		ret = __axienet_device_reset(lp);
+		if (ret)
+			return ret;
+
+		ret = axienet_dma_bd_init(ndev);
+		if (ret) {
+			netdev_err(ndev, "%s: descriptor allocation failed\n",
+				   __func__);
+			return ret;
+		}
 	}
 
 	axienet_status = axienet_ior(lp, XAE_RCW1_OFFSET);
@@ -726,6 +748,128 @@ static inline int axienet_check_tx_bd_space(struct axienet_local *lp,
 }
 
 /**
+ * axienet_dma_tx_cb - DMA engine callback for TX channel.
+ * @data:       Pointer to the axienet_local structure.
+ * @result:     error reporting through dmaengine_result.
+ * This function is called by dmaengine driver for TX channel to notify
+ * that the transmit is done.
+ */
+static void axienet_dma_tx_cb(void *data, const struct dmaengine_result *result)
+{
+	struct skbuf_dma_descriptor *skbuf_dma;
+	struct axienet_local *lp = data;
+	struct netdev_queue *txq;
+	int len;
+
+	skbuf_dma = axienet_get_tx_desc(lp, lp->tx_ring_tail++);
+	len = skbuf_dma->skb->len;
+	txq = skb_get_tx_queue(lp->ndev, skbuf_dma->skb);
+	u64_stats_update_begin(&lp->tx_stat_sync);
+	u64_stats_add(&lp->tx_bytes, len);
+	u64_stats_add(&lp->tx_packets, 1);
+	u64_stats_update_end(&lp->tx_stat_sync);
+	dma_unmap_sg(lp->dev, skbuf_dma->sgl, skbuf_dma->sg_len, DMA_TO_DEVICE);
+	dev_consume_skb_any(skbuf_dma->skb);
+	netif_txq_completed_wake(txq, 1, len,
+				 CIRC_SPACE(lp->tx_ring_head, lp->tx_ring_tail, TX_BD_NUM_MAX),
+				 2 * MAX_SKB_FRAGS);
+}
+
+/**
+ * axienet_start_xmit_dmaengine - Starts the transmission.
+ * @skb:        sk_buff pointer that contains data to be Txed.
+ * @ndev:       Pointer to net_device structure.
+ *
+ * Return: NETDEV_TX_OK on success or any non space errors.
+ *         NETDEV_TX_BUSY when free element in TX skb ring buffer
+ *         is not available.
+ *
+ * This function is invoked to initiate transmission. The
+ * function sets the skbs, register dma callback API and submit
+ * the dma transaction.
+ * Additionally if checksum offloading is supported,
+ * it populates AXI Stream Control fields with appropriate values.
+ */
+static netdev_tx_t
+axienet_start_xmit_dmaengine(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct dma_async_tx_descriptor *dma_tx_desc = NULL;
+	struct axienet_local *lp = netdev_priv(ndev);
+	u32 app_metadata[DMA_NUM_APP_WORDS] = {0};
+	struct skbuf_dma_descriptor *skbuf_dma;
+	struct dma_device *dma_dev;
+	struct netdev_queue *txq;
+	u32 csum_start_off;
+	u32 csum_index_off;
+	int sg_len;
+	int ret;
+
+	dma_dev = lp->tx_chan->device;
+	sg_len = skb_shinfo(skb)->nr_frags + 1;
+	if (CIRC_SPACE(lp->tx_ring_head, lp->tx_ring_tail, TX_BD_NUM_MAX) <= sg_len) {
+		netif_stop_queue(ndev);
+		if (net_ratelimit())
+			netdev_warn(ndev, "TX ring unexpectedly full\n");
+		return NETDEV_TX_BUSY;
+	}
+
+	skbuf_dma = axienet_get_tx_desc(lp, lp->tx_ring_head);
+	if (!skbuf_dma)
+		goto xmit_error_drop_skb;
+
+	lp->tx_ring_head++;
+	sg_init_table(skbuf_dma->sgl, sg_len);
+	ret = skb_to_sgvec(skb, skbuf_dma->sgl, 0, skb->len);
+	if (ret < 0)
+		goto xmit_error_drop_skb;
+
+	ret = dma_map_sg(lp->dev, skbuf_dma->sgl, sg_len, DMA_TO_DEVICE);
+	if (!ret)
+		goto xmit_error_drop_skb;
+
+	/* Fill up app fields for checksum */
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		if (lp->features & XAE_FEATURE_FULL_TX_CSUM) {
+			/* Tx Full Checksum Offload Enabled */
+			app_metadata[0] |= 2;
+		} else if (lp->features & XAE_FEATURE_PARTIAL_TX_CSUM) {
+			csum_start_off = skb_transport_offset(skb);
+			csum_index_off = csum_start_off + skb->csum_offset;
+			/* Tx Partial Checksum Offload Enabled */
+			app_metadata[0] |= 1;
+			app_metadata[1] = (csum_start_off << 16) | csum_index_off;
+		}
+	} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
+		app_metadata[0] |= 2; /* Tx Full Checksum Offload Enabled */
+	}
+
+	dma_tx_desc = dma_dev->device_prep_slave_sg(lp->tx_chan, skbuf_dma->sgl,
+			sg_len, DMA_MEM_TO_DEV,
+			DMA_PREP_INTERRUPT, (void *)app_metadata);
+	if (!dma_tx_desc)
+		goto xmit_error_unmap_sg;
+
+	skbuf_dma->skb = skb;
+	skbuf_dma->sg_len = sg_len;
+	dma_tx_desc->callback_param = lp;
+	dma_tx_desc->callback_result = axienet_dma_tx_cb;
+	dmaengine_submit(dma_tx_desc);
+	dma_async_issue_pending(lp->tx_chan);
+	txq = skb_get_tx_queue(lp->ndev, skb);
+	netdev_tx_sent_queue(txq, skb->len);
+	netif_txq_maybe_stop(txq, CIRC_SPACE(lp->tx_ring_head, lp->tx_ring_tail, TX_BD_NUM_MAX),
+			     MAX_SKB_FRAGS + 1, 2 * MAX_SKB_FRAGS);
+
+	return NETDEV_TX_OK;
+
+xmit_error_unmap_sg:
+	dma_unmap_sg(lp->dev, skbuf_dma->sgl, sg_len, DMA_TO_DEVICE);
+xmit_error_drop_skb:
+	dev_kfree_skb_any(skb);
+	return NETDEV_TX_OK;
+}
+
+/**
  * axienet_tx_poll - Invoked once a transmit is completed by the
  * Axi DMA Tx channel.
  * @napi:	Pointer to NAPI structure.
@@ -822,7 +966,7 @@ axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		if (lp->features & XAE_FEATURE_FULL_TX_CSUM) {
 			/* Tx Full Checksum Offload Enabled */
 			cur_p->app0 |= 2;
-		} else if (lp->features & XAE_FEATURE_PARTIAL_RX_CSUM) {
+		} else if (lp->features & XAE_FEATURE_PARTIAL_TX_CSUM) {
 			csum_start_off = skb_transport_offset(skb);
 			csum_index_off = csum_start_off + skb->csum_offset;
 			/* Tx Partial Checksum Offload Enabled */
@@ -892,6 +1036,42 @@ axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 }
 
 /**
+ * axienet_dma_rx_cb - DMA engine callback for RX channel.
+ * @data:       Pointer to the skbuf_dma_descriptor structure.
+ * @result:     error reporting through dmaengine_result.
+ * This function is called by dmaengine driver for RX channel to notify
+ * that the packet is received.
+ */
+static void axienet_dma_rx_cb(void *data, const struct dmaengine_result *result)
+{
+	struct skbuf_dma_descriptor *skbuf_dma;
+	size_t meta_len, meta_max_len, rx_len;
+	struct axienet_local *lp = data;
+	struct sk_buff *skb;
+	u32 *app_metadata;
+
+	skbuf_dma = axienet_get_rx_desc(lp, lp->rx_ring_tail++);
+	skb = skbuf_dma->skb;
+	app_metadata = dmaengine_desc_get_metadata_ptr(skbuf_dma->desc, &meta_len,
+						       &meta_max_len);
+	dma_unmap_single(lp->dev, skbuf_dma->dma_address, lp->max_frm_size,
+			 DMA_FROM_DEVICE);
+	/* TODO: Derive app word index programmatically */
+	rx_len = (app_metadata[LEN_APP] & 0xFFFF);
+	skb_put(skb, rx_len);
+	skb->protocol = eth_type_trans(skb, lp->ndev);
+	skb->ip_summed = CHECKSUM_NONE;
+
+	__netif_rx(skb);
+	u64_stats_update_begin(&lp->rx_stat_sync);
+	u64_stats_add(&lp->rx_packets, 1);
+	u64_stats_add(&lp->rx_bytes, rx_len);
+	u64_stats_update_end(&lp->rx_stat_sync);
+	axienet_rx_submit_desc(lp->ndev);
+	dma_async_issue_pending(lp->rx_chan);
+}
+
+/**
  * axienet_rx_poll - Triggered by RX ISR to complete the BD processing.
  * @napi:	Pointer to NAPI structure.
  * @budget:	Max number of RX packets to process.
@@ -1125,40 +1305,158 @@ static irqreturn_t axienet_eth_irq(int irq, void *_ndev)
 static void axienet_dma_err_handler(struct work_struct *work);
 
 /**
- * axienet_open - Driver open routine.
- * @ndev:	Pointer to net_device structure
+ * axienet_rx_submit_desc - Submit the rx descriptors to dmaengine.
+ * allocate skbuff, map the scatterlist and obtain a descriptor
+ * and then add the callback information and submit descriptor.
+ *
+ * @ndev:	net_device pointer
+ *
+ */
+static void axienet_rx_submit_desc(struct net_device *ndev)
+{
+	struct dma_async_tx_descriptor *dma_rx_desc = NULL;
+	struct axienet_local *lp = netdev_priv(ndev);
+	struct skbuf_dma_descriptor *skbuf_dma;
+	struct sk_buff *skb;
+	dma_addr_t addr;
+
+	skbuf_dma = axienet_get_rx_desc(lp, lp->rx_ring_head);
+	if (!skbuf_dma)
+		return;
+
+	lp->rx_ring_head++;
+	skb = netdev_alloc_skb(ndev, lp->max_frm_size);
+	if (!skb)
+		return;
+
+	sg_init_table(skbuf_dma->sgl, 1);
+	addr = dma_map_single(lp->dev, skb->data, lp->max_frm_size, DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(lp->dev, addr))) {
+		if (net_ratelimit())
+			netdev_err(ndev, "DMA mapping error\n");
+		goto rx_submit_err_free_skb;
+	}
+	sg_dma_address(skbuf_dma->sgl) = addr;
+	sg_dma_len(skbuf_dma->sgl) = lp->max_frm_size;
+	dma_rx_desc = dmaengine_prep_slave_sg(lp->rx_chan, skbuf_dma->sgl,
+					      1, DMA_DEV_TO_MEM,
+					      DMA_PREP_INTERRUPT);
+	if (!dma_rx_desc)
+		goto rx_submit_err_unmap_skb;
+
+	skbuf_dma->skb = skb;
+	skbuf_dma->dma_address = sg_dma_address(skbuf_dma->sgl);
+	skbuf_dma->desc = dma_rx_desc;
+	dma_rx_desc->callback_param = lp;
+	dma_rx_desc->callback_result = axienet_dma_rx_cb;
+	dmaengine_submit(dma_rx_desc);
+
+	return;
+
+rx_submit_err_unmap_skb:
+	dma_unmap_single(lp->dev, addr, lp->max_frm_size, DMA_FROM_DEVICE);
+rx_submit_err_free_skb:
+	dev_kfree_skb(skb);
+}
+
+/**
+ * axienet_init_dmaengine - init the dmaengine code.
+ * @ndev:       Pointer to net_device structure
  *
  * Return: 0, on success.
- *	    non-zero error value on failure
+ *          non-zero error value on failure
  *
- * This is the driver open routine. It calls phylink_start to start the
- * PHY device.
- * It also allocates interrupt service routines, enables the interrupt lines
- * and ISR handling. Axi Ethernet core is reset through Axi DMA core. Buffer
- * descriptors are initialized.
+ * This is the dmaengine initialization code.
  */
-static int axienet_open(struct net_device *ndev)
+static int axienet_init_dmaengine(struct net_device *ndev)
 {
-	int ret;
 	struct axienet_local *lp = netdev_priv(ndev);
+	struct skbuf_dma_descriptor *skbuf_dma;
+	int i, ret;
 
-	dev_dbg(&ndev->dev, "axienet_open()\n");
+	lp->tx_chan = dma_request_chan(lp->dev, "tx_chan0");
+	if (IS_ERR(lp->tx_chan)) {
+		dev_err(lp->dev, "No Ethernet DMA (TX) channel found\n");
+		return PTR_ERR(lp->tx_chan);
+	}
 
-	/* When we do an Axi Ethernet reset, it resets the complete core
-	 * including the MDIO. MDIO must be disabled before resetting.
-	 * Hold MDIO bus lock to avoid MDIO accesses during the reset.
-	 */
-	axienet_lock_mii(lp);
-	ret = axienet_device_reset(ndev);
-	axienet_unlock_mii(lp);
+	lp->rx_chan = dma_request_chan(lp->dev, "rx_chan0");
+	if (IS_ERR(lp->rx_chan)) {
+		ret = PTR_ERR(lp->rx_chan);
+		dev_err(lp->dev, "No Ethernet DMA (RX) channel found\n");
+		goto err_dma_release_tx;
+	}
 
-	ret = phylink_of_phy_connect(lp->phylink, lp->dev->of_node, 0);
-	if (ret) {
-		dev_err(lp->dev, "phylink_of_phy_connect() failed: %d\n", ret);
-		return ret;
+	lp->tx_ring_tail = 0;
+	lp->tx_ring_head = 0;
+	lp->rx_ring_tail = 0;
+	lp->rx_ring_head = 0;
+	lp->tx_skb_ring = kcalloc(TX_BD_NUM_MAX, sizeof(*lp->tx_skb_ring),
+				  GFP_KERNEL);
+	if (!lp->tx_skb_ring) {
+		ret = -ENOMEM;
+		goto err_dma_release_rx;
+	}
+	for (i = 0; i < TX_BD_NUM_MAX; i++) {
+		skbuf_dma = kzalloc(sizeof(*skbuf_dma), GFP_KERNEL);
+		if (!skbuf_dma) {
+			ret = -ENOMEM;
+			goto err_free_tx_skb_ring;
+		}
+		lp->tx_skb_ring[i] = skbuf_dma;
 	}
 
-	phylink_start(lp->phylink);
+	lp->rx_skb_ring = kcalloc(RX_BUF_NUM_DEFAULT, sizeof(*lp->rx_skb_ring),
+				  GFP_KERNEL);
+	if (!lp->rx_skb_ring) {
+		ret = -ENOMEM;
+		goto err_free_tx_skb_ring;
+	}
+	for (i = 0; i < RX_BUF_NUM_DEFAULT; i++) {
+		skbuf_dma = kzalloc(sizeof(*skbuf_dma), GFP_KERNEL);
+		if (!skbuf_dma) {
+			ret = -ENOMEM;
+			goto err_free_rx_skb_ring;
+		}
+		lp->rx_skb_ring[i] = skbuf_dma;
+	}
+	/* TODO: Instead of BD_NUM_DEFAULT use runtime support */
+	for (i = 0; i < RX_BUF_NUM_DEFAULT; i++)
+		axienet_rx_submit_desc(ndev);
+	dma_async_issue_pending(lp->rx_chan);
+
+	return 0;
+
+err_free_rx_skb_ring:
+	for (i = 0; i < RX_BUF_NUM_DEFAULT; i++)
+		kfree(lp->rx_skb_ring[i]);
+	kfree(lp->rx_skb_ring);
+err_free_tx_skb_ring:
+	for (i = 0; i < TX_BD_NUM_MAX; i++)
+		kfree(lp->tx_skb_ring[i]);
+	kfree(lp->tx_skb_ring);
+err_dma_release_rx:
+	dma_release_channel(lp->rx_chan);
+err_dma_release_tx:
+	dma_release_channel(lp->tx_chan);
+	return ret;
+}
+
+/**
+ * axienet_init_legacy_dma - init the dma legacy code.
+ * @ndev:       Pointer to net_device structure
+ *
+ * Return: 0, on success.
+ *          non-zero error value on failure
+ *
+ * This is the dma  initialization code. It also allocates interrupt
+ * service routines, enables the interrupt lines and ISR handling.
+ *
+ */
+static int axienet_init_legacy_dma(struct net_device *ndev)
+{
+	int ret;
+	struct axienet_local *lp = netdev_priv(ndev);
 
 	/* Enable worker thread for Axi DMA error handling */
 	INIT_WORK(&lp->dma_err_task, axienet_dma_err_handler);
@@ -1193,14 +1491,77 @@ err_rx_irq:
 err_tx_irq:
 	napi_disable(&lp->napi_tx);
 	napi_disable(&lp->napi_rx);
-	phylink_stop(lp->phylink);
-	phylink_disconnect_phy(lp->phylink);
 	cancel_work_sync(&lp->dma_err_task);
 	dev_err(lp->dev, "request_irq() failed\n");
 	return ret;
 }
 
 /**
+ * axienet_open - Driver open routine.
+ * @ndev:	Pointer to net_device structure
+ *
+ * Return: 0, on success.
+ *	    non-zero error value on failure
+ *
+ * This is the driver open routine. It calls phylink_start to start the
+ * PHY device.
+ * It also allocates interrupt service routines, enables the interrupt lines
+ * and ISR handling. Axi Ethernet core is reset through Axi DMA core. Buffer
+ * descriptors are initialized.
+ */
+static int axienet_open(struct net_device *ndev)
+{
+	int ret;
+	struct axienet_local *lp = netdev_priv(ndev);
+
+	dev_dbg(&ndev->dev, "%s\n", __func__);
+
+	/* When we do an Axi Ethernet reset, it resets the complete core
+	 * including the MDIO. MDIO must be disabled before resetting.
+	 * Hold MDIO bus lock to avoid MDIO accesses during the reset.
+	 */
+	axienet_lock_mii(lp);
+	ret = axienet_device_reset(ndev);
+	axienet_unlock_mii(lp);
+
+	ret = phylink_of_phy_connect(lp->phylink, lp->dev->of_node, 0);
+	if (ret) {
+		dev_err(lp->dev, "phylink_of_phy_connect() failed: %d\n", ret);
+		return ret;
+	}
+
+	phylink_start(lp->phylink);
+
+	if (lp->use_dmaengine) {
+		/* Enable interrupts for Axi Ethernet core (if defined) */
+		if (lp->eth_irq > 0) {
+			ret = request_irq(lp->eth_irq, axienet_eth_irq, IRQF_SHARED,
+					  ndev->name, ndev);
+			if (ret)
+				goto err_phy;
+		}
+
+		ret = axienet_init_dmaengine(ndev);
+		if (ret < 0)
+			goto err_free_eth_irq;
+	} else {
+		ret = axienet_init_legacy_dma(ndev);
+		if (ret)
+			goto err_phy;
+	}
+
+	return 0;
+
+err_free_eth_irq:
+	if (lp->eth_irq > 0)
+		free_irq(lp->eth_irq, ndev);
+err_phy:
+	phylink_stop(lp->phylink);
+	phylink_disconnect_phy(lp->phylink);
+	return ret;
+}
+
+/**
  * axienet_stop - Driver stop routine.
  * @ndev:	Pointer to net_device structure
  *
@@ -1213,11 +1574,14 @@ err_tx_irq:
 static int axienet_stop(struct net_device *ndev)
 {
 	struct axienet_local *lp = netdev_priv(ndev);
+	int i;
 
 	dev_dbg(&ndev->dev, "axienet_close()\n");
 
-	napi_disable(&lp->napi_tx);
-	napi_disable(&lp->napi_rx);
+	if (!lp->use_dmaengine) {
+		napi_disable(&lp->napi_tx);
+		napi_disable(&lp->napi_rx);
+	}
 
 	phylink_stop(lp->phylink);
 	phylink_disconnect_phy(lp->phylink);
@@ -1225,18 +1589,33 @@ static int axienet_stop(struct net_device *ndev)
 	axienet_setoptions(ndev, lp->options &
 			   ~(XAE_OPTION_TXEN | XAE_OPTION_RXEN));
 
-	axienet_dma_stop(lp);
+	if (!lp->use_dmaengine) {
+		axienet_dma_stop(lp);
+		cancel_work_sync(&lp->dma_err_task);
+		free_irq(lp->tx_irq, ndev);
+		free_irq(lp->rx_irq, ndev);
+		axienet_dma_bd_release(ndev);
+	} else {
+		dmaengine_terminate_sync(lp->tx_chan);
+		dmaengine_synchronize(lp->tx_chan);
+		dmaengine_terminate_sync(lp->rx_chan);
+		dmaengine_synchronize(lp->rx_chan);
+
+		for (i = 0; i < TX_BD_NUM_MAX; i++)
+			kfree(lp->tx_skb_ring[i]);
+		kfree(lp->tx_skb_ring);
+		for (i = 0; i < RX_BUF_NUM_DEFAULT; i++)
+			kfree(lp->rx_skb_ring[i]);
+		kfree(lp->rx_skb_ring);
+
+		dma_release_channel(lp->rx_chan);
+		dma_release_channel(lp->tx_chan);
+	}
 
 	axienet_iow(lp, XAE_IE_OFFSET, 0);
 
-	cancel_work_sync(&lp->dma_err_task);
-
 	if (lp->eth_irq > 0)
 		free_irq(lp->eth_irq, ndev);
-	free_irq(lp->tx_irq, ndev);
-	free_irq(lp->rx_irq, ndev);
-
-	axienet_dma_bd_release(ndev);
 	return 0;
 }
 
@@ -1333,6 +1712,18 @@ static const struct net_device_ops axienet_netdev_ops = {
 #endif
 };
 
+static const struct net_device_ops axienet_netdev_dmaengine_ops = {
+	.ndo_open = axienet_open,
+	.ndo_stop = axienet_stop,
+	.ndo_start_xmit = axienet_start_xmit_dmaengine,
+	.ndo_get_stats64 = axienet_get_stats64,
+	.ndo_change_mtu	= axienet_change_mtu,
+	.ndo_set_mac_address = netdev_set_mac_address,
+	.ndo_validate_addr = eth_validate_addr,
+	.ndo_eth_ioctl = axienet_ioctl,
+	.ndo_set_rx_mode = axienet_set_multicast_list,
+};
+
 /**
  * axienet_ethtools_get_drvinfo - Get various Axi Ethernet driver information.
  * @ndev:	Pointer to net_device structure
@@ -1412,14 +1803,16 @@ static void axienet_ethtools_get_regs(struct net_device *ndev,
 	data[29] = axienet_ior(lp, XAE_FMI_OFFSET);
 	data[30] = axienet_ior(lp, XAE_AF0_OFFSET);
 	data[31] = axienet_ior(lp, XAE_AF1_OFFSET);
-	data[32] = axienet_dma_in32(lp, XAXIDMA_TX_CR_OFFSET);
-	data[33] = axienet_dma_in32(lp, XAXIDMA_TX_SR_OFFSET);
-	data[34] = axienet_dma_in32(lp, XAXIDMA_TX_CDESC_OFFSET);
-	data[35] = axienet_dma_in32(lp, XAXIDMA_TX_TDESC_OFFSET);
-	data[36] = axienet_dma_in32(lp, XAXIDMA_RX_CR_OFFSET);
-	data[37] = axienet_dma_in32(lp, XAXIDMA_RX_SR_OFFSET);
-	data[38] = axienet_dma_in32(lp, XAXIDMA_RX_CDESC_OFFSET);
-	data[39] = axienet_dma_in32(lp, XAXIDMA_RX_TDESC_OFFSET);
+	if (!lp->use_dmaengine) {
+		data[32] = axienet_dma_in32(lp, XAXIDMA_TX_CR_OFFSET);
+		data[33] = axienet_dma_in32(lp, XAXIDMA_TX_SR_OFFSET);
+		data[34] = axienet_dma_in32(lp, XAXIDMA_TX_CDESC_OFFSET);
+		data[35] = axienet_dma_in32(lp, XAXIDMA_TX_TDESC_OFFSET);
+		data[36] = axienet_dma_in32(lp, XAXIDMA_RX_CR_OFFSET);
+		data[37] = axienet_dma_in32(lp, XAXIDMA_RX_SR_OFFSET);
+		data[38] = axienet_dma_in32(lp, XAXIDMA_RX_CDESC_OFFSET);
+		data[39] = axienet_dma_in32(lp, XAXIDMA_RX_TDESC_OFFSET);
+	}
 }
 
 static void
@@ -1863,7 +2256,6 @@ static int axienet_probe(struct platform_device *pdev)
 	SET_NETDEV_DEV(ndev, &pdev->dev);
 	ndev->flags &= ~IFF_MULTICAST;  /* clear multicast */
 	ndev->features = NETIF_F_SG;
-	ndev->netdev_ops = &axienet_netdev_ops;
 	ndev->ethtool_ops = &axienet_ethtool_ops;
 
 	/* MTU range: 64 - 9000 */
@@ -1880,9 +2272,6 @@ static int axienet_probe(struct platform_device *pdev)
 	u64_stats_init(&lp->rx_stat_sync);
 	u64_stats_init(&lp->tx_stat_sync);
 
-	netif_napi_add(ndev, &lp->napi_rx, axienet_rx_poll);
-	netif_napi_add(ndev, &lp->napi_tx, axienet_tx_poll);
-
 	lp->axi_clk = devm_clk_get_optional(&pdev->dev, "s_axi_lite_clk");
 	if (!lp->axi_clk) {
 		/* For backward compatibility, if named AXI clock is not present,
@@ -2008,82 +2397,118 @@ static int axienet_probe(struct platform_device *pdev)
 		goto cleanup_clk;
 	}
 
-	/* Find the DMA node, map the DMA registers, and decode the DMA IRQs */
-	np = of_parse_phandle(pdev->dev.of_node, "axistream-connected", 0);
-	if (np) {
-		struct resource dmares;
+	if (!of_find_property(pdev->dev.of_node, "dmas", NULL)) {
+		/* Find the DMA node, map the DMA registers, and decode the DMA IRQs */
+		np = of_parse_phandle(pdev->dev.of_node, "axistream-connected", 0);
 
-		ret = of_address_to_resource(np, 0, &dmares);
-		if (ret) {
-			dev_err(&pdev->dev,
-				"unable to get DMA resource\n");
+		if (np) {
+			struct resource dmares;
+
+			ret = of_address_to_resource(np, 0, &dmares);
+			if (ret) {
+				dev_err(&pdev->dev,
+					"unable to get DMA resource\n");
+				of_node_put(np);
+				goto cleanup_clk;
+			}
+			lp->dma_regs = devm_ioremap_resource(&pdev->dev,
+							     &dmares);
+			lp->rx_irq = irq_of_parse_and_map(np, 1);
+			lp->tx_irq = irq_of_parse_and_map(np, 0);
 			of_node_put(np);
+			lp->eth_irq = platform_get_irq_optional(pdev, 0);
+		} else {
+			/* Check for these resources directly on the Ethernet node. */
+			lp->dma_regs = devm_platform_get_and_ioremap_resource(pdev, 1, NULL);
+			lp->rx_irq = platform_get_irq(pdev, 1);
+			lp->tx_irq = platform_get_irq(pdev, 0);
+			lp->eth_irq = platform_get_irq_optional(pdev, 2);
+		}
+		if (IS_ERR(lp->dma_regs)) {
+			dev_err(&pdev->dev, "could not map DMA regs\n");
+			ret = PTR_ERR(lp->dma_regs);
+			goto cleanup_clk;
+		}
+		if (lp->rx_irq <= 0 || lp->tx_irq <= 0) {
+			dev_err(&pdev->dev, "could not determine irqs\n");
+			ret = -ENOMEM;
 			goto cleanup_clk;
 		}
-		lp->dma_regs = devm_ioremap_resource(&pdev->dev,
-						     &dmares);
-		lp->rx_irq = irq_of_parse_and_map(np, 1);
-		lp->tx_irq = irq_of_parse_and_map(np, 0);
-		of_node_put(np);
-		lp->eth_irq = platform_get_irq_optional(pdev, 0);
-	} else {
-		/* Check for these resources directly on the Ethernet node. */
-		lp->dma_regs = devm_platform_get_and_ioremap_resource(pdev, 1, NULL);
-		lp->rx_irq = platform_get_irq(pdev, 1);
-		lp->tx_irq = platform_get_irq(pdev, 0);
-		lp->eth_irq = platform_get_irq_optional(pdev, 2);
-	}
-	if (IS_ERR(lp->dma_regs)) {
-		dev_err(&pdev->dev, "could not map DMA regs\n");
-		ret = PTR_ERR(lp->dma_regs);
-		goto cleanup_clk;
-	}
-	if ((lp->rx_irq <= 0) || (lp->tx_irq <= 0)) {
-		dev_err(&pdev->dev, "could not determine irqs\n");
-		ret = -ENOMEM;
-		goto cleanup_clk;
-	}
 
-	/* Reset core now that clocks are enabled, prior to accessing MDIO */
-	ret = __axienet_device_reset(lp);
-	if (ret)
-		goto cleanup_clk;
+		/* Reset core now that clocks are enabled, prior to accessing MDIO */
+		ret = __axienet_device_reset(lp);
+		if (ret)
+			goto cleanup_clk;
+
+		/* Autodetect the need for 64-bit DMA pointers.
+		 * When the IP is configured for a bus width bigger than 32 bits,
+		 * writing the MSB registers is mandatory, even if they are all 0.
+		 * We can detect this case by writing all 1's to one such register
+		 * and see if that sticks: when the IP is configured for 32 bits
+		 * only, those registers are RES0.
+		 * Those MSB registers were introduced in IP v7.1, which we check first.
+		 */
+		if ((axienet_ior(lp, XAE_ID_OFFSET) >> 24) >= 0x9) {
+			void __iomem *desc = lp->dma_regs + XAXIDMA_TX_CDESC_OFFSET + 4;
 
-	/* Autodetect the need for 64-bit DMA pointers.
-	 * When the IP is configured for a bus width bigger than 32 bits,
-	 * writing the MSB registers is mandatory, even if they are all 0.
-	 * We can detect this case by writing all 1's to one such register
-	 * and see if that sticks: when the IP is configured for 32 bits
-	 * only, those registers are RES0.
-	 * Those MSB registers were introduced in IP v7.1, which we check first.
-	 */
-	if ((axienet_ior(lp, XAE_ID_OFFSET) >> 24) >= 0x9) {
-		void __iomem *desc = lp->dma_regs + XAXIDMA_TX_CDESC_OFFSET + 4;
-
-		iowrite32(0x0, desc);
-		if (ioread32(desc) == 0) {	/* sanity check */
-			iowrite32(0xffffffff, desc);
-			if (ioread32(desc) > 0) {
-				lp->features |= XAE_FEATURE_DMA_64BIT;
-				addr_width = 64;
-				dev_info(&pdev->dev,
-					 "autodetected 64-bit DMA range\n");
-			}
 			iowrite32(0x0, desc);
+			if (ioread32(desc) == 0) {	/* sanity check */
+				iowrite32(0xffffffff, desc);
+				if (ioread32(desc) > 0) {
+					lp->features |= XAE_FEATURE_DMA_64BIT;
+					addr_width = 64;
+					dev_info(&pdev->dev,
+						 "autodetected 64-bit DMA range\n");
+				}
+				iowrite32(0x0, desc);
+			}
+		}
+		if (!IS_ENABLED(CONFIG_64BIT) && lp->features & XAE_FEATURE_DMA_64BIT) {
+			dev_err(&pdev->dev, "64-bit addressable DMA is not compatible with 32-bit archecture\n");
+			ret = -EINVAL;
+			goto cleanup_clk;
 		}
-	}
-	if (!IS_ENABLED(CONFIG_64BIT) && lp->features & XAE_FEATURE_DMA_64BIT) {
-		dev_err(&pdev->dev, "64-bit addressable DMA is not compatible with 32-bit archecture\n");
-		ret = -EINVAL;
-		goto cleanup_clk;
-	}
 
-	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(addr_width));
-	if (ret) {
-		dev_err(&pdev->dev, "No suitable DMA available\n");
-		goto cleanup_clk;
+		ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(addr_width));
+		if (ret) {
+			dev_err(&pdev->dev, "No suitable DMA available\n");
+			goto cleanup_clk;
+		}
+		netif_napi_add(ndev, &lp->napi_rx, axienet_rx_poll);
+		netif_napi_add(ndev, &lp->napi_tx, axienet_tx_poll);
+	} else {
+		struct xilinx_vdma_config cfg;
+		struct dma_chan *tx_chan;
+
+		lp->eth_irq = platform_get_irq_optional(pdev, 0);
+		if (lp->eth_irq < 0 && lp->eth_irq != -ENXIO) {
+			ret = lp->eth_irq;
+			goto cleanup_clk;
+		}
+		tx_chan = dma_request_chan(lp->dev, "tx_chan0");
+		if (IS_ERR(tx_chan)) {
+			ret = PTR_ERR(tx_chan);
+			dev_err_probe(lp->dev, ret, "No Ethernet DMA (TX) channel found\n");
+			goto cleanup_clk;
+		}
+
+		cfg.reset = 1;
+		/* As name says VDMA but it has support for DMA channel reset */
+		ret = xilinx_vdma_channel_set_config(tx_chan, &cfg);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "Reset channel failed\n");
+			dma_release_channel(tx_chan);
+			goto cleanup_clk;
+		}
+
+		dma_release_channel(tx_chan);
+		lp->use_dmaengine = 1;
 	}
 
+	if (lp->use_dmaengine)
+		ndev->netdev_ops = &axienet_netdev_dmaengine_ops;
+	else
+		ndev->netdev_ops = &axienet_netdev_ops;
 	/* Check for Ethernet core IRQ (optional) */
 	if (lp->eth_irq <= 0)
 		dev_info(&pdev->dev, "Ethernet core IRQ not defined\n");
@@ -2099,8 +2524,8 @@ static int axienet_probe(struct platform_device *pdev)
 	}
 
 	lp->coalesce_count_rx = XAXIDMA_DFT_RX_THRESHOLD;
-	lp->coalesce_usec_rx = XAXIDMA_DFT_RX_USEC;
 	lp->coalesce_count_tx = XAXIDMA_DFT_TX_THRESHOLD;
+	lp->coalesce_usec_rx = XAXIDMA_DFT_RX_USEC;
 	lp->coalesce_usec_tx = XAXIDMA_DFT_TX_USEC;
 
 	ret = axienet_mdio_setup(lp);
diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c
index cd8cf08477ec..5fbe33a09bb0 100644
--- a/drivers/net/fjes/fjes_main.c
+++ b/drivers/net/fjes/fjes_main.c
@@ -1438,7 +1438,7 @@ err_out:
 }
 
 /* fjes_remove - Device Removal Routine */
-static int fjes_remove(struct platform_device *plat_dev)
+static void fjes_remove(struct platform_device *plat_dev)
 {
 	struct net_device *netdev = dev_get_drvdata(&plat_dev->dev);
 	struct fjes_adapter *adapter = netdev_priv(netdev);
@@ -1462,8 +1462,6 @@ static int fjes_remove(struct platform_device *plat_dev)
 	netif_napi_del(&adapter->napi);
 
 	free_netdev(netdev);
-
-	return 0;
 }
 
 static struct platform_driver fjes_driver = {
@@ -1471,7 +1469,7 @@ static struct platform_driver fjes_driver = {
 		.name = DRV_NAME,
 	},
 	.probe = fjes_probe,
-	.remove = fjes_remove,
+	.remove_new = fjes_remove,
 };
 
 static acpi_status
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index acd9c615d1f4..32c51c244153 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -234,7 +234,7 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs,
 					 vni_to_tunnel_id(gnvh->vni),
 					 gnvh->opt_len * 4);
 		if (!tun_dst) {
-			geneve->dev->stats.rx_dropped++;
+			DEV_STATS_INC(geneve->dev, rx_dropped);
 			goto drop;
 		}
 		/* Update tunnel dst according to Geneve options. */
@@ -246,8 +246,8 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs,
 		 * since we don't support any...
 		 */
 		if (gnvh->critical) {
-			geneve->dev->stats.rx_frame_errors++;
-			geneve->dev->stats.rx_errors++;
+			DEV_STATS_INC(geneve->dev, rx_frame_errors);
+			DEV_STATS_INC(geneve->dev, rx_errors);
 			goto drop;
 		}
 	}
@@ -263,7 +263,7 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs,
 		/* Ignore packet loops (and multicast echo) */
 		if (ether_addr_equal(eth_hdr(skb)->h_source,
 				     geneve->dev->dev_addr)) {
-			geneve->dev->stats.rx_errors++;
+			DEV_STATS_INC(geneve->dev, rx_errors);
 			goto drop;
 		}
 	} else {
@@ -296,8 +296,8 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs,
 #endif
 		}
 		if (err > 1) {
-			++geneve->dev->stats.rx_frame_errors;
-			++geneve->dev->stats.rx_errors;
+			DEV_STATS_INC(geneve->dev, rx_frame_errors);
+			DEV_STATS_INC(geneve->dev, rx_errors);
 			goto drop;
 		}
 	}
@@ -377,14 +377,14 @@ static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 
 	if (unlikely((!geneve->cfg.inner_proto_inherit &&
 		      inner_proto != htons(ETH_P_TEB)))) {
-		geneve->dev->stats.rx_dropped++;
+		DEV_STATS_INC(geneve->dev, rx_dropped);
 		goto drop;
 	}
 
 	opts_len = geneveh->opt_len * 4;
 	if (iptunnel_pull_header(skb, GENEVE_BASE_HLEN + opts_len, inner_proto,
 				 !net_eq(geneve->net, dev_net(geneve->dev)))) {
-		geneve->dev->stats.rx_dropped++;
+		DEV_STATS_INC(geneve->dev, rx_dropped);
 		goto drop;
 	}
 
@@ -1007,7 +1007,7 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 		if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) {
 			netdev_dbg(dev, "no tunnel metadata\n");
 			dev_kfree_skb(skb);
-			dev->stats.tx_dropped++;
+			DEV_STATS_INC(dev, tx_dropped);
 			return NETDEV_TX_OK;
 		}
 	} else {
@@ -1030,11 +1030,11 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 		dev_kfree_skb(skb);
 
 	if (err == -ELOOP)
-		dev->stats.collisions++;
+		DEV_STATS_INC(dev, collisions);
 	else if (err == -ENETUNREACH)
-		dev->stats.tx_carrier_errors++;
+		DEV_STATS_INC(dev, tx_carrier_errors);
 
-	dev->stats.tx_errors++;
+	DEV_STATS_INC(dev, tx_errors);
 	return NETDEV_TX_OK;
 }
 
diff --git a/drivers/net/hyperv/Kconfig b/drivers/net/hyperv/Kconfig
index ca7bf7f897d3..c8cbd85adcf9 100644
--- a/drivers/net/hyperv/Kconfig
+++ b/drivers/net/hyperv/Kconfig
@@ -3,5 +3,6 @@ config HYPERV_NET
 	tristate "Microsoft Hyper-V virtual network driver"
 	depends on HYPERV
 	select UCS2_STRING
+	select NLS
 	help
 	  Select this option to enable the Hyper-V virtual network driver.
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 3ba3c8fb28a5..4406427d4617 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -1582,10 +1582,10 @@ static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 	switch (stringset) {
 	case ETH_SS_STATS:
 		for (i = 0; i < ARRAY_SIZE(netvsc_stats); i++)
-			ethtool_sprintf(&p, netvsc_stats[i].name);
+			ethtool_puts(&p, netvsc_stats[i].name);
 
 		for (i = 0; i < ARRAY_SIZE(vf_stats); i++)
-			ethtool_sprintf(&p, vf_stats[i].name);
+			ethtool_puts(&p, vf_stats[i].name);
 
 		for (i = 0; i < nvdev->num_chn; i++) {
 			ethtool_sprintf(&p, "tx_queue_%u_packets", i);
@@ -1752,8 +1752,8 @@ static u32 netvsc_rss_indir_size(struct net_device *dev)
 	return ndc->rx_table_sz;
 }
 
-static int netvsc_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
-			   u8 *hfunc)
+static int netvsc_get_rxfh(struct net_device *dev,
+			   struct ethtool_rxfh_param *rxfh)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
 	struct netvsc_device *ndev = rtnl_dereference(ndc->nvdev);
@@ -1763,47 +1763,49 @@ static int netvsc_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
 	if (!ndev)
 		return -ENODEV;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;	/* Toeplitz */
+	rxfh->hfunc = ETH_RSS_HASH_TOP;	/* Toeplitz */
 
 	rndis_dev = ndev->extension;
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < ndc->rx_table_sz; i++)
-			indir[i] = ndc->rx_table[i];
+			rxfh->indir[i] = ndc->rx_table[i];
 	}
 
-	if (key)
-		memcpy(key, rndis_dev->rss_key, NETVSC_HASH_KEYLEN);
+	if (rxfh->key)
+		memcpy(rxfh->key, rndis_dev->rss_key, NETVSC_HASH_KEYLEN);
 
 	return 0;
 }
 
-static int netvsc_set_rxfh(struct net_device *dev, const u32 *indir,
-			   const u8 *key, const u8 hfunc)
+static int netvsc_set_rxfh(struct net_device *dev,
+			   struct ethtool_rxfh_param *rxfh,
+			   struct netlink_ext_ack *extack)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
 	struct netvsc_device *ndev = rtnl_dereference(ndc->nvdev);
 	struct rndis_device *rndis_dev;
+	u8 *key = rxfh->key;
 	int i;
 
 	if (!ndev)
 		return -ENODEV;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
 	rndis_dev = ndev->extension;
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < ndc->rx_table_sz; i++)
-			if (indir[i] >= ndev->num_chn)
+			if (rxfh->indir[i] >= ndev->num_chn)
 				return -EINVAL;
 
 		for (i = 0; i < ndc->rx_table_sz; i++)
-			ndc->rx_table[i] = indir[i];
+			ndc->rx_table[i] = rxfh->indir[i];
 	}
 
 	if (!key) {
-		if (!indir)
+		if (!rxfh->indir)
 			return 0;
 
 		key = rndis_dev->rss_key;
@@ -2206,9 +2208,6 @@ static int netvsc_vf_join(struct net_device *vf_netdev,
 		goto upper_link_failed;
 	}
 
-	/* set slave flag before open to prevent IPv6 addrconf */
-	vf_netdev->flags |= IFF_SLAVE;
-
 	schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
 
 	call_netdevice_notifiers(NETDEV_JOIN, vf_netdev);
@@ -2315,16 +2314,18 @@ static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev)
 
 	}
 
-	/* Fallback path to check synthetic vf with
-	 * help of mac addr
+	/* Fallback path to check synthetic vf with help of mac addr.
+	 * Because this function can be called before vf_netdev is
+	 * initialized (NETDEV_POST_INIT) when its perm_addr has not been copied
+	 * from dev_addr, also try to match to its dev_addr.
+	 * Note: On Hyper-V and Azure, it's not possible to set a MAC address
+	 * on a VF that matches to the MAC of a unrelated NETVSC device.
 	 */
 	list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) {
 		ndev = hv_get_drvdata(ndev_ctx->device_ctx);
-		if (ether_addr_equal(vf_netdev->perm_addr, ndev->perm_addr)) {
-			netdev_notice(vf_netdev,
-				      "falling back to mac addr based matching\n");
+		if (ether_addr_equal(vf_netdev->perm_addr, ndev->perm_addr) ||
+		    ether_addr_equal(vf_netdev->dev_addr, ndev->perm_addr))
 			return ndev;
-		}
 	}
 
 	netdev_notice(vf_netdev,
@@ -2332,6 +2333,19 @@ static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev)
 	return NULL;
 }
 
+static int netvsc_prepare_bonding(struct net_device *vf_netdev)
+{
+	struct net_device *ndev;
+
+	ndev = get_netvsc_byslot(vf_netdev);
+	if (!ndev)
+		return NOTIFY_DONE;
+
+	/* set slave flag before open to prevent IPv6 addrconf */
+	vf_netdev->flags |= IFF_SLAVE;
+	return NOTIFY_DONE;
+}
+
 static int netvsc_register_vf(struct net_device *vf_netdev)
 {
 	struct net_device_context *net_device_ctx;
@@ -2531,15 +2545,6 @@ static int netvsc_probe(struct hv_device *dev,
 		goto devinfo_failed;
 	}
 
-	nvdev = rndis_filter_device_add(dev, device_info);
-	if (IS_ERR(nvdev)) {
-		ret = PTR_ERR(nvdev);
-		netdev_err(net, "unable to add netvsc device (ret %d)\n", ret);
-		goto rndis_failed;
-	}
-
-	eth_hw_addr_set(net, device_info->mac_adr);
-
 	/* We must get rtnl lock before scheduling nvdev->subchan_work,
 	 * otherwise netvsc_subchan_work() can get rtnl lock first and wait
 	 * all subchannels to show up, but that may not happen because
@@ -2547,9 +2552,23 @@ static int netvsc_probe(struct hv_device *dev,
 	 * -> ... -> device_add() -> ... -> __device_attach() can't get
 	 * the device lock, so all the subchannels can't be processed --
 	 * finally netvsc_subchan_work() hangs forever.
+	 *
+	 * The rtnl lock also needs to be held before rndis_filter_device_add()
+	 * which advertises nvsp_2_vsc_capability / sriov bit, and triggers
+	 * VF NIC offering and registering. If VF NIC finished register_netdev()
+	 * earlier it may cause name based config failure.
 	 */
 	rtnl_lock();
 
+	nvdev = rndis_filter_device_add(dev, device_info);
+	if (IS_ERR(nvdev)) {
+		ret = PTR_ERR(nvdev);
+		netdev_err(net, "unable to add netvsc device (ret %d)\n", ret);
+		goto rndis_failed;
+	}
+
+	eth_hw_addr_set(net, device_info->mac_adr);
+
 	if (nvdev->num_chn > 1)
 		schedule_work(&nvdev->subchan_work);
 
@@ -2586,9 +2605,9 @@ static int netvsc_probe(struct hv_device *dev,
 	return 0;
 
 register_failed:
-	rtnl_unlock();
 	rndis_filter_device_remove(dev, nvdev);
 rndis_failed:
+	rtnl_unlock();
 	netvsc_devinfo_put(device_info);
 devinfo_failed:
 	free_percpu(net_device_ctx->vf_stats);
@@ -2753,6 +2772,8 @@ static int netvsc_netdev_event(struct notifier_block *this,
 		return NOTIFY_DONE;
 
 	switch (event) {
+	case NETDEV_POST_INIT:
+		return netvsc_prepare_bonding(event_dev);
 	case NETDEV_REGISTER:
 		return netvsc_register_vf(event_dev);
 	case NETDEV_UNREGISTER:
@@ -2788,12 +2809,17 @@ static int __init netvsc_drv_init(void)
 	}
 	netvsc_ring_bytes = ring_size * PAGE_SIZE;
 
+	register_netdevice_notifier(&netvsc_netdev_notifier);
+
 	ret = vmbus_driver_register(&netvsc_drv);
 	if (ret)
-		return ret;
+		goto err_vmbus_reg;
 
-	register_netdevice_notifier(&netvsc_netdev_notifier);
 	return 0;
+
+err_vmbus_reg:
+	unregister_netdevice_notifier(&netvsc_netdev_notifier);
+	return ret;
 }
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index af95947a87c5..ecc2128ca9b7 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -21,7 +21,6 @@
 #include <linux/rtnetlink.h>
 #include <linux/ucs2_string.h>
 #include <linux/string.h>
-#include <linux/slab.h>
 
 #include "hyperv_net.h"
 #include "netvsc_trace.h"
diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c
index 523d13ee02bf..35e55f198e05 100644
--- a/drivers/net/ieee802154/fakelb.c
+++ b/drivers/net/ieee802154/fakelb.c
@@ -221,7 +221,7 @@ err_slave:
 	return err;
 }
 
-static int fakelb_remove(struct platform_device *pdev)
+static void fakelb_remove(struct platform_device *pdev)
 {
 	struct fakelb_phy *phy, *tmp;
 
@@ -229,14 +229,13 @@ static int fakelb_remove(struct platform_device *pdev)
 	list_for_each_entry_safe(phy, tmp, &fakelb_phys, list)
 		fakelb_del(phy);
 	mutex_unlock(&fakelb_phys_lock);
-	return 0;
 }
 
 static struct platform_device *ieee802154fake_dev;
 
 static struct platform_driver ieee802154fake_driver = {
 	.probe = fakelb_probe,
-	.remove = fakelb_remove,
+	.remove_new = fakelb_remove,
 	.driver = {
 			.name = "ieee802154fakelb",
 	},
diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c
index 31cba9aa7636..2c2483bbe780 100644
--- a/drivers/net/ieee802154/mac802154_hwsim.c
+++ b/drivers/net/ieee802154/mac802154_hwsim.c
@@ -1035,7 +1035,7 @@ err_slave:
 	return err;
 }
 
-static int hwsim_remove(struct platform_device *pdev)
+static void hwsim_remove(struct platform_device *pdev)
 {
 	struct hwsim_phy *phy, *tmp;
 
@@ -1043,13 +1043,11 @@ static int hwsim_remove(struct platform_device *pdev)
 	list_for_each_entry_safe(phy, tmp, &hwsim_phys, list)
 		hwsim_del(phy);
 	mutex_unlock(&hwsim_phys_lock);
-
-	return 0;
 }
 
 static struct platform_driver mac802154hwsim_driver = {
 	.probe = hwsim_probe,
-	.remove = hwsim_remove,
+	.remove_new = hwsim_remove,
 	.driver = {
 			.name = "mac802154_hwsim",
 	},
diff --git a/drivers/net/ipa/Makefile b/drivers/net/ipa/Makefile
index 7293d5cc2b2b..d3abb38633e0 100644
--- a/drivers/net/ipa/Makefile
+++ b/drivers/net/ipa/Makefile
@@ -2,12 +2,12 @@
 #
 # Makefile for the Qualcomm IPA driver.
 
-IPA_REG_VERSIONS	:=	3.1 3.5.1 4.2 4.5 4.7 4.9 4.11 5.0
+IPA_REG_VERSIONS	:=	3.1 3.5.1 4.2 4.5 4.7 4.9 4.11 5.0 5.5
 
 # Some IPA versions can reuse another set of GSI register definitions.
 GSI_REG_VERSIONS	:=	3.1 3.5.1 4.0 4.5 4.9 4.11 5.0
 
-IPA_DATA_VERSIONS	:=	3.1 3.5.1 4.2 4.5 4.7 4.9 4.11 5.0
+IPA_DATA_VERSIONS	:=	3.1 3.5.1 4.2 4.5 4.7 4.9 4.11 5.0 5.5
 
 obj-$(CONFIG_QCOM_IPA)	+=	ipa.o
 
diff --git a/drivers/net/ipa/data/ipa_data-v5.5.c b/drivers/net/ipa/data/ipa_data-v5.5.c
new file mode 100644
index 000000000000..2c6390f11354
--- /dev/null
+++ b/drivers/net/ipa/data/ipa_data-v5.5.c
@@ -0,0 +1,487 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Copyright (C) 2023 Linaro Ltd. */
+
+#include <linux/kernel.h>
+#include <linux/log2.h>
+
+#include "../ipa_data.h"
+#include "../ipa_endpoint.h"
+#include "../ipa_mem.h"
+
+/** enum ipa_resource_type - IPA resource types for an SoC having IPA v5.5 */
+enum ipa_resource_type {
+	/* Source resource types; first must have value 0 */
+	IPA_RESOURCE_TYPE_SRC_PKT_CONTEXTS		= 0,
+	IPA_RESOURCE_TYPE_SRC_DESCRIPTOR_LISTS,
+	IPA_RESOURCE_TYPE_SRC_DESCRIPTOR_BUFF,
+	IPA_RESOURCE_TYPE_SRC_HPS_DMARS,
+	IPA_RESOURCE_TYPE_SRC_ACK_ENTRIES,
+
+	/* Destination resource types; first must have value 0 */
+	IPA_RESOURCE_TYPE_DST_DATA_SECTORS		= 0,
+	IPA_RESOURCE_TYPE_DST_DPS_DMARS,
+	IPA_RESOURCE_TYPE_DST_ULSO_SEGMENTS,
+};
+
+/* Resource groups used for an SoC having IPA v5.5 */
+enum ipa_rsrc_group_id {
+	/* Source resource group identifiers */
+	IPA_RSRC_GROUP_SRC_UL				= 0,
+	IPA_RSRC_GROUP_SRC_DL,
+	IPA_RSRC_GROUP_SRC_UNUSED_2,
+	IPA_RSRC_GROUP_SRC_UNUSED_3,
+	IPA_RSRC_GROUP_SRC_URLLC,
+	IPA_RSRC_GROUP_SRC_U_RX_QC,
+	IPA_RSRC_GROUP_SRC_COUNT,	/* Last in set; not a source group */
+
+	/* Destination resource group identifiers */
+	IPA_RSRC_GROUP_DST_UL				= 0,
+	IPA_RSRC_GROUP_DST_DL,
+	IPA_RSRC_GROUP_DST_UNUSED_2,
+	IPA_RSRC_GROUP_DST_UNUSED_3,
+	IPA_RSRC_GROUP_DST_UNUSED_4,
+	IPA_RSRC_GROUP_DST_UC,
+	IPA_RSRC_GROUP_DST_DRB_IP,
+	IPA_RSRC_GROUP_DST_COUNT,	/* Last; not a destination group */
+};
+
+/* QSB configuration data for an SoC having IPA v5.5 */
+static const struct ipa_qsb_data ipa_qsb_data[] = {
+	[IPA_QSB_MASTER_DDR] = {
+		.max_writes		= 0,	/* Unlimited */
+		.max_reads		= 12,
+		.max_reads_beats	= 0,
+	},
+	[IPA_QSB_MASTER_PCIE] = {
+		.max_writes		= 0,	/* Unlimited */
+		.max_reads		= 8,
+		.max_reads_beats	= 0,
+	},
+};
+
+/* Endpoint configuration data for an SoC having IPA v5.5 */
+static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = {
+	[IPA_ENDPOINT_AP_COMMAND_TX] = {
+		.ee_id		= GSI_EE_AP,
+		.channel_id	= 12,
+		.endpoint_id	= 14,
+		.toward_ipa	= true,
+		.channel = {
+			.tre_count	= 256,
+			.event_count	= 256,
+			.tlv_count	= 20,
+		},
+		.endpoint = {
+			.config = {
+				.resource_group	= IPA_RSRC_GROUP_SRC_UL,
+				.dma_mode	= true,
+				.dma_endpoint	= IPA_ENDPOINT_AP_LAN_RX,
+				.tx = {
+					.seq_type = IPA_SEQ_DMA,
+				},
+			},
+		},
+	},
+	[IPA_ENDPOINT_AP_LAN_RX] = {
+		.ee_id		= GSI_EE_AP,
+		.channel_id	= 13,
+		.endpoint_id	= 16,
+		.toward_ipa	= false,
+		.channel = {
+			.tre_count	= 256,
+			.event_count	= 256,
+			.tlv_count	= 9,
+		},
+		.endpoint = {
+			.config = {
+				.resource_group	= IPA_RSRC_GROUP_DST_UL,
+				.aggregation	= true,
+				.status_enable	= true,
+				.rx = {
+					.buffer_size	= 8192,
+					.pad_align	= ilog2(sizeof(u32)),
+					.aggr_time_limit = 500,
+				},
+			},
+		},
+	},
+	[IPA_ENDPOINT_AP_MODEM_TX] = {
+		.ee_id		= GSI_EE_AP,
+		.channel_id	= 11,
+		.endpoint_id	= 2,
+		.toward_ipa	= true,
+		.channel = {
+			.tre_count	= 512,
+			.event_count	= 512,
+			.tlv_count	= 25,
+		},
+		.endpoint = {
+			.filter_support	= true,
+			.config = {
+				.resource_group	= IPA_RSRC_GROUP_SRC_UL,
+				.checksum       = true,
+				.qmap		= true,
+				.status_enable	= true,
+				.tx = {
+					.seq_type = IPA_SEQ_2_PASS_SKIP_LAST_UC,
+					.status_endpoint =
+						IPA_ENDPOINT_MODEM_AP_RX,
+				},
+			},
+		},
+	},
+	[IPA_ENDPOINT_AP_MODEM_RX] = {
+		.ee_id		= GSI_EE_AP,
+		.channel_id	= 1,
+		.endpoint_id	= 23,
+		.toward_ipa	= false,
+		.channel = {
+			.tre_count	= 256,
+			.event_count	= 256,
+			.tlv_count	= 9,
+		},
+		.endpoint = {
+			.config = {
+				.resource_group	= IPA_RSRC_GROUP_DST_DL,
+				.checksum       = true,
+				.qmap		= true,
+				.aggregation	= true,
+				.rx = {
+					.buffer_size	= 8192,
+					.aggr_time_limit = 500,
+					.aggr_close_eof	= true,
+				},
+			},
+		},
+	},
+	[IPA_ENDPOINT_MODEM_AP_TX] = {
+		.ee_id		= GSI_EE_MODEM,
+		.channel_id	= 0,
+		.endpoint_id	= 12,
+		.toward_ipa	= true,
+		.endpoint = {
+			.filter_support	= true,
+		},
+	},
+	[IPA_ENDPOINT_MODEM_AP_RX] = {
+		.ee_id		= GSI_EE_MODEM,
+		.channel_id	= 7,
+		.endpoint_id	= 21,
+		.toward_ipa	= false,
+	},
+	[IPA_ENDPOINT_MODEM_DL_NLO_TX] = {
+		.ee_id		= GSI_EE_MODEM,
+		.channel_id	= 2,
+		.endpoint_id	= 15,
+		.toward_ipa	= true,
+		.endpoint = {
+			.filter_support	= true,
+		},
+	},
+};
+
+/* Source resource configuration data for an SoC having IPA v5.5 */
+static const struct ipa_resource ipa_resource_src[] = {
+	[IPA_RESOURCE_TYPE_SRC_PKT_CONTEXTS] = {
+		.limits[IPA_RSRC_GROUP_SRC_UL] = {
+			.min = 3,	.max = 9,
+		},
+		.limits[IPA_RSRC_GROUP_SRC_DL] = {
+			.min = 4,	.max = 10,
+		},
+		.limits[IPA_RSRC_GROUP_SRC_URLLC] = {
+			.min = 1,	.max = 63,
+		},
+		.limits[IPA_RSRC_GROUP_SRC_U_RX_QC] = {
+			.min = 0,	.max = 63,
+		},
+	},
+	[IPA_RESOURCE_TYPE_SRC_DESCRIPTOR_LISTS] = {
+		.limits[IPA_RSRC_GROUP_SRC_UL] = {
+			.min = 9,	.max = 9,
+		},
+		.limits[IPA_RSRC_GROUP_SRC_DL] = {
+			.min = 12,	.max = 12,
+		},
+		.limits[IPA_RSRC_GROUP_SRC_URLLC] = {
+			.min = 10,	.max = 10,
+		},
+	},
+	[IPA_RESOURCE_TYPE_SRC_DESCRIPTOR_BUFF] = {
+		.limits[IPA_RSRC_GROUP_SRC_UL] = {
+			.min = 9,	.max = 9,
+		},
+		.limits[IPA_RSRC_GROUP_SRC_DL] = {
+			.min = 24,	.max = 24,
+		},
+		.limits[IPA_RSRC_GROUP_SRC_URLLC] = {
+			.min = 20,	.max = 20,
+		},
+	},
+	[IPA_RESOURCE_TYPE_SRC_HPS_DMARS] = {
+		.limits[IPA_RSRC_GROUP_SRC_UL] = {
+			.min = 0,	.max = 63,
+		},
+		.limits[IPA_RSRC_GROUP_SRC_DL] = {
+			.min = 0,	.max = 63,
+		},
+		.limits[IPA_RSRC_GROUP_SRC_URLLC] = {
+			.min = 1,	.max = 63,
+		},
+		.limits[IPA_RSRC_GROUP_SRC_U_RX_QC] = {
+			.min = 0,	.max = 63,
+		},
+	},
+	[IPA_RESOURCE_TYPE_SRC_ACK_ENTRIES] = {
+		.limits[IPA_RSRC_GROUP_SRC_UL] = {
+			.min = 22,	.max = 22,
+		},
+		.limits[IPA_RSRC_GROUP_SRC_DL] = {
+			.min = 16,	.max = 16,
+		},
+		.limits[IPA_RSRC_GROUP_SRC_URLLC] = {
+			.min = 16,	.max = 16,
+		},
+	},
+};
+
+/* Destination resource configuration data for an SoC having IPA v5.5 */
+static const struct ipa_resource ipa_resource_dst[] = {
+	[IPA_RESOURCE_TYPE_DST_DATA_SECTORS] = {
+		.limits[IPA_RSRC_GROUP_DST_UL] = {
+			.min = 6,	.max = 6,
+		},
+		.limits[IPA_RSRC_GROUP_DST_DL] = {
+			.min = 5,	.max = 5,
+		},
+		.limits[IPA_RSRC_GROUP_DST_DRB_IP] = {
+			.min = 39,	.max = 39,
+		},
+	},
+	[IPA_RESOURCE_TYPE_DST_DPS_DMARS] = {
+		.limits[IPA_RSRC_GROUP_DST_UL] = {
+			.min = 0,	.max = 3,
+		},
+		.limits[IPA_RSRC_GROUP_DST_DL] = {
+			.min = 0,	.max = 3,
+		},
+	},
+	[IPA_RESOURCE_TYPE_DST_ULSO_SEGMENTS] = {
+		.limits[IPA_RSRC_GROUP_DST_UL] = {
+			.min = 0,	.max = 63,
+		},
+		.limits[IPA_RSRC_GROUP_DST_DL] = {
+			.min = 0,	.max = 63,
+		},
+	},
+};
+
+/* Resource configuration data for an SoC having IPA v5.5 */
+static const struct ipa_resource_data ipa_resource_data = {
+	.rsrc_group_dst_count	= IPA_RSRC_GROUP_DST_COUNT,
+	.rsrc_group_src_count	= IPA_RSRC_GROUP_SRC_COUNT,
+	.resource_src_count	= ARRAY_SIZE(ipa_resource_src),
+	.resource_src		= ipa_resource_src,
+	.resource_dst_count	= ARRAY_SIZE(ipa_resource_dst),
+	.resource_dst		= ipa_resource_dst,
+};
+
+/* IPA-resident memory region data for an SoC having IPA v5.5 */
+static const struct ipa_mem ipa_mem_local_data[] = {
+	{
+		.id		= IPA_MEM_UC_EVENT_RING,
+		.offset		= 0x0000,
+		.size		= 0x1000,
+		.canary_count	= 0,
+	},
+	{
+		.id		= IPA_MEM_UC_SHARED,
+		.offset		= 0x1000,
+		.size		= 0x0080,
+		.canary_count	= 0,
+	},
+	{
+		.id		= IPA_MEM_UC_INFO,
+		.offset		= 0x1080,
+		.size		= 0x0200,
+		.canary_count	= 0,
+	},
+	{
+		.id		= IPA_MEM_V4_FILTER_HASHED,
+		.offset		= 0x1288,
+		.size		= 0x0078,
+		.canary_count	= 2,
+	},
+	{
+		.id		= IPA_MEM_V4_FILTER,
+		.offset		= 0x1308,
+		.size		= 0x0078,
+		.canary_count	= 2,
+	},
+	{
+		.id		= IPA_MEM_V6_FILTER_HASHED,
+		.offset		= 0x1388,
+		.size		= 0x0078,
+		.canary_count	= 2,
+	},
+	{
+		.id		= IPA_MEM_V6_FILTER,
+		.offset		= 0x1408,
+		.size		= 0x0078,
+		.canary_count	= 2,
+	},
+	{
+		.id		= IPA_MEM_V4_ROUTE_HASHED,
+		.offset		= 0x1488,
+		.size		= 0x0098,
+		.canary_count	= 2,
+	},
+	{
+		.id		= IPA_MEM_V4_ROUTE,
+		.offset		= 0x1528,
+		.size		= 0x0098,
+		.canary_count	= 2,
+	},
+	{
+		.id		= IPA_MEM_V6_ROUTE_HASHED,
+		.offset		= 0x15c8,
+		.size		= 0x0098,
+		.canary_count	= 2,
+	},
+	{
+		.id		= IPA_MEM_V6_ROUTE,
+		.offset		= 0x1668,
+		.size		= 0x0098,
+		.canary_count	= 2,
+	},
+	{
+		.id		= IPA_MEM_MODEM_HEADER,
+		.offset		= 0x1708,
+		.size		= 0x0240,
+		.canary_count	= 2,
+	},
+	{
+		.id		= IPA_MEM_AP_HEADER,
+		.offset		= 0x1948,
+		.size		= 0x01e0,
+		.canary_count	= 0,
+	},
+	{
+		.id		= IPA_MEM_MODEM_PROC_CTX,
+		.offset		= 0x1b40,
+		.size		= 0x0b20,
+		.canary_count	= 2,
+	},
+	{
+		.id		= IPA_MEM_AP_PROC_CTX,
+		.offset		= 0x2660,
+		.size		= 0x0200,
+		.canary_count	= 0,
+	},
+	{
+		.id		= IPA_MEM_STATS_QUOTA_MODEM,
+		.offset		= 0x2868,
+		.size		= 0x0060,
+		.canary_count	= 2,
+	},
+	{
+		.id		= IPA_MEM_STATS_QUOTA_AP,
+		.offset		= 0x28c8,
+		.size		= 0x0048,
+		.canary_count	= 0,
+	},
+	{
+		.id		= IPA_MEM_STATS_TETHERING,
+		.offset		= 0x2910,
+		.size		= 0x03c0,
+		.canary_count	= 0,
+	},
+	{
+		.id		= IPA_MEM_AP_V4_FILTER,
+		.offset		= 0x29b8,
+		.size		= 0x0188,
+		.canary_count	= 2,
+	},
+	{
+		.id		= IPA_MEM_AP_V6_FILTER,
+		.offset		= 0x2b40,
+		.size		= 0x0228,
+		.canary_count	= 0,
+	},
+	{
+		.id		= IPA_MEM_STATS_FILTER_ROUTE,
+		.offset		= 0x2cd0,
+		.size		= 0x0ba0,
+		.canary_count	= 2,
+	},
+	{
+		.id		= IPA_MEM_STATS_DROP,
+		.offset		= 0x3870,
+		.size		= 0x0020,
+		.canary_count	= 0,
+	},
+	{
+		.id		= IPA_MEM_MODEM,
+		.offset		= 0x3898,
+		.size		= 0x0d48,
+		.canary_count	= 2,
+	},
+	{
+		.id		= IPA_MEM_NAT_TABLE,
+		.offset		= 0x45e0,
+		.size		= 0x0900,
+		.canary_count	= 0,
+	},
+	{
+		.id		= IPA_MEM_PDN_CONFIG,
+		.offset		= 0x4ee8,
+		.size		= 0x0100,
+		.canary_count	= 2,
+	},
+};
+
+/* Memory configuration data for an SoC having IPA v5.5 */
+static const struct ipa_mem_data ipa_mem_data = {
+	.local_count	= ARRAY_SIZE(ipa_mem_local_data),
+	.local		= ipa_mem_local_data,
+	.imem_addr	= 0x14688000,
+	.imem_size	= 0x00002000,
+	.smem_id	= 497,
+	.smem_size	= 0x0000b000,
+};
+
+/* Interconnect rates are in 1000 byte/second units */
+static const struct ipa_interconnect_data ipa_interconnect_data[] = {
+	{
+		.name			= "memory",
+		.peak_bandwidth		= 1900000,	/* 1.9 GBps */
+		.average_bandwidth	= 600000,	/* 600 MBps */
+	},
+	/* Average rate is unused for the next interconnect */
+	{
+		.name			= "config",
+		.peak_bandwidth		= 76800,	/* 76.8 MBps */
+		.average_bandwidth	= 0,		/* unused */
+	},
+};
+
+/* Clock and interconnect configuration data for an SoC having IPA v5.5 */
+static const struct ipa_power_data ipa_power_data = {
+	.core_clock_rate	= 120 * 1000 * 1000,	/* Hz */
+	.interconnect_count	= ARRAY_SIZE(ipa_interconnect_data),
+	.interconnect_data	= ipa_interconnect_data,
+};
+
+/* Configuration data for an SoC having IPA v5.5. */
+const struct ipa_data ipa_data_v5_5 = {
+	.version		= IPA_VERSION_5_5,
+	.qsb_count		= ARRAY_SIZE(ipa_qsb_data),
+	.qsb_data		= ipa_qsb_data,
+	.modem_route_count	= 11,
+	.endpoint_count		= ARRAY_SIZE(ipa_gsi_endpoint_data),
+	.endpoint_data		= ipa_gsi_endpoint_data,
+	.resource_data		= &ipa_resource_data,
+	.mem_data		= &ipa_mem_data,
+	.power_data		= &ipa_power_data,
+};
diff --git a/drivers/net/ipa/gsi_reg.c b/drivers/net/ipa/gsi_reg.c
index c5458e28b12f..106c43884aef 100644
--- a/drivers/net/ipa/gsi_reg.c
+++ b/drivers/net/ipa/gsi_reg.c
@@ -110,6 +110,7 @@ static const struct regs *gsi_regs(struct gsi *gsi)
 		return &gsi_regs_v4_11;
 
 	case IPA_VERSION_5_0:
+	case IPA_VERSION_5_5:
 		return &gsi_regs_v5_0;
 
 	default:
diff --git a/drivers/net/ipa/ipa_data.h b/drivers/net/ipa/ipa_data.h
index ce82b00fdc49..2a1605e67b65 100644
--- a/drivers/net/ipa/ipa_data.h
+++ b/drivers/net/ipa/ipa_data.h
@@ -250,5 +250,6 @@ extern const struct ipa_data ipa_data_v4_7;
 extern const struct ipa_data ipa_data_v4_9;
 extern const struct ipa_data ipa_data_v4_11;
 extern const struct ipa_data ipa_data_v5_0;
+extern const struct ipa_data ipa_data_v5_5;
 
 #endif /* _IPA_DATA_H_ */
diff --git a/drivers/net/ipa/ipa_main.c b/drivers/net/ipa/ipa_main.c
index da853353a5c7..00475fd7a205 100644
--- a/drivers/net/ipa/ipa_main.c
+++ b/drivers/net/ipa/ipa_main.c
@@ -74,6 +74,7 @@
 #define IPA_PAS_ID		15
 
 /* Shift of 19.2 MHz timestamp to achieve lower resolution timestamps */
+/* IPA v5.5+ does not specify Qtime timestamp config for DPL */
 #define DPL_TIMESTAMP_SHIFT	14	/* ~1.172 kHz, ~853 usec per tick */
 #define TAG_TIMESTAMP_SHIFT	14
 #define NAT_TIMESTAMP_SHIFT	24	/* ~1.144 Hz, ~874 msec per tick */
@@ -376,9 +377,11 @@ static void ipa_qtime_config(struct ipa *ipa)
 	iowrite32(0, ipa->reg_virt + reg_offset(reg));
 
 	reg = ipa_reg(ipa, QTIME_TIMESTAMP_CFG);
-	/* Set DPL time stamp resolution to use Qtime (instead of 1 msec) */
-	val = reg_encode(reg, DPL_TIMESTAMP_LSB, DPL_TIMESTAMP_SHIFT);
-	val |= reg_bit(reg, DPL_TIMESTAMP_SEL);
+	if (ipa->version < IPA_VERSION_5_5) {
+		/* Set DPL time stamp resolution to use Qtime (not 1 msec) */
+		val = reg_encode(reg, DPL_TIMESTAMP_LSB, DPL_TIMESTAMP_SHIFT);
+		val |= reg_bit(reg, DPL_TIMESTAMP_SEL);
+	}
 	/* Configure tag and NAT Qtime timestamp resolution as well */
 	val = reg_encode(reg, TAG_TIMESTAMP_LSB, TAG_TIMESTAMP_SHIFT);
 	val = reg_encode(reg, NAT_TIMESTAMP_LSB, NAT_TIMESTAMP_SHIFT);
@@ -688,6 +691,10 @@ static const struct of_device_id ipa_match[] = {
 		.compatible	= "qcom,sdx65-ipa",
 		.data		= &ipa_data_v5_0,
 	},
+	{
+		.compatible	= "qcom,sm8550-ipa",
+		.data		= &ipa_data_v5_5,
+	},
 	{ },
 };
 MODULE_DEVICE_TABLE(of, ipa_match);
@@ -936,7 +943,7 @@ err_power_exit:
 	return ret;
 }
 
-static int ipa_remove(struct platform_device *pdev)
+static void ipa_remove(struct platform_device *pdev)
 {
 	struct ipa *ipa = dev_get_drvdata(&pdev->dev);
 	struct ipa_power *power = ipa->power;
@@ -959,8 +966,16 @@ static int ipa_remove(struct platform_device *pdev)
 			usleep_range(USEC_PER_MSEC, 2 * USEC_PER_MSEC);
 			ret = ipa_modem_stop(ipa);
 		}
-		if (ret)
-			return ret;
+		if (ret) {
+			/*
+			 * Not cleaning up here properly might also yield a
+			 * crash later on. As the device is still unregistered
+			 * in this case, this might even yield a crash later on.
+			 */
+			dev_err(dev, "Failed to stop modem (%pe), leaking resources\n",
+				ERR_PTR(ret));
+			return;
+		}
 
 		ipa_teardown(ipa);
 	}
@@ -978,17 +993,6 @@ out_power_put:
 	ipa_power_exit(power);
 
 	dev_info(dev, "IPA driver removed");
-
-	return 0;
-}
-
-static void ipa_shutdown(struct platform_device *pdev)
-{
-	int ret;
-
-	ret = ipa_remove(pdev);
-	if (ret)
-		dev_err(&pdev->dev, "shutdown: remove returned %d\n", ret);
 }
 
 static const struct attribute_group *ipa_attribute_groups[] = {
@@ -1001,8 +1005,8 @@ static const struct attribute_group *ipa_attribute_groups[] = {
 
 static struct platform_driver ipa_driver = {
 	.probe		= ipa_probe,
-	.remove		= ipa_remove,
-	.shutdown	= ipa_shutdown,
+	.remove_new	= ipa_remove,
+	.shutdown	= ipa_remove,
 	.driver	= {
 		.name		= "ipa",
 		.pm		= &ipa_pm_ops,
diff --git a/drivers/net/ipa/ipa_mem.c b/drivers/net/ipa/ipa_mem.c
index db6ada2343af..694960537ecd 100644
--- a/drivers/net/ipa/ipa_mem.c
+++ b/drivers/net/ipa/ipa_mem.c
@@ -165,7 +165,7 @@ static bool ipa_mem_id_valid(struct ipa *ipa, enum ipa_mem_id mem_id)
 
 	case IPA_MEM_AP_V4_FILTER:
 	case IPA_MEM_AP_V6_FILTER:
-		if (version != IPA_VERSION_5_0)
+		if (version < IPA_VERSION_5_0)
 			return false;
 		break;
 
diff --git a/drivers/net/ipa/ipa_reg.c b/drivers/net/ipa/ipa_reg.c
index 818a84f7c42d..6a3203ae6f1e 100644
--- a/drivers/net/ipa/ipa_reg.c
+++ b/drivers/net/ipa/ipa_reg.c
@@ -44,12 +44,12 @@ static bool ipa_reg_id_valid(struct ipa *ipa, enum ipa_reg_id reg_id)
 	case DST_RSRC_GRP_45_RSRC_TYPE:
 		return version <= IPA_VERSION_3_1 ||
 		       version == IPA_VERSION_4_5 ||
-		       version == IPA_VERSION_5_0;
+		       version >= IPA_VERSION_5_0;
 
 	case SRC_RSRC_GRP_67_RSRC_TYPE:
 	case DST_RSRC_GRP_67_RSRC_TYPE:
 		return version <= IPA_VERSION_3_1 ||
-		       version == IPA_VERSION_5_0;
+		       version >= IPA_VERSION_5_0;
 
 	case ENDP_FILTER_ROUTER_HSH_CFG:
 		return version < IPA_VERSION_5_0 &&
@@ -125,6 +125,8 @@ static const struct regs *ipa_regs(enum ipa_version version)
 		return &ipa_regs_v4_11;
 	case IPA_VERSION_5_0:
 		return &ipa_regs_v5_0;
+	case IPA_VERSION_5_5:
+		return &ipa_regs_v5_5;
 	default:
 		return NULL;
 	}
diff --git a/drivers/net/ipa/ipa_reg.h b/drivers/net/ipa/ipa_reg.h
index 3ac48dea865b..2998f115f12c 100644
--- a/drivers/net/ipa/ipa_reg.h
+++ b/drivers/net/ipa/ipa_reg.h
@@ -240,25 +240,25 @@ enum ipa_reg_local_pkt_proc_cntxt_field_id {
 
 /* COUNTER_CFG register */
 enum ipa_reg_counter_cfg_field_id {
-	EOT_COAL_GRANULARITY,				/* Not v3.5+ */
+	EOT_COAL_GRANULARITY,				/* Not IPA v3.5+ */
 	AGGR_GRANULARITY,
 };
 
 /* IPA_TX_CFG register */
 enum ipa_reg_ipa_tx_cfg_field_id {
-	TX0_PREFETCH_DISABLE,				/* Not v4.0+ */
-	TX1_PREFETCH_DISABLE,				/* Not v4.0+ */
-	PREFETCH_ALMOST_EMPTY_SIZE,			/* Not v4.0+ */
-	PREFETCH_ALMOST_EMPTY_SIZE_TX0,			/* v4.0+ */
-	DMAW_SCND_OUTSD_PRED_THRESHOLD,			/* v4.0+ */
-	DMAW_SCND_OUTSD_PRED_EN,			/* v4.0+ */
-	DMAW_MAX_BEATS_256_DIS,				/* v4.0+ */
-	PA_MASK_EN,					/* v4.0+ */
-	PREFETCH_ALMOST_EMPTY_SIZE_TX1,			/* v4.0+ */
-	DUAL_TX_ENABLE,					/* v4.5+ */
-	SSPND_PA_NO_START_STATE,			/* v4,2+, not v4.5 */
-	SSPND_PA_NO_BQ_STATE,				/* v4.2 only */
-	HOLB_STICKY_DROP_EN,				/* v5.0+ */
+	TX0_PREFETCH_DISABLE,				/* Not IPA v4.0+ */
+	TX1_PREFETCH_DISABLE,				/* Not IPA v4.0+ */
+	PREFETCH_ALMOST_EMPTY_SIZE,			/* Not IPA v4.0+ */
+	PREFETCH_ALMOST_EMPTY_SIZE_TX0,			/* IPA v4.0+ */
+	DMAW_SCND_OUTSD_PRED_THRESHOLD,			/* IPA v4.0+ */
+	DMAW_SCND_OUTSD_PRED_EN,			/* IPA v4.0+ */
+	DMAW_MAX_BEATS_256_DIS,				/* IPA v4.0+ */
+	PA_MASK_EN,					/* IPA v4.0+ */
+	PREFETCH_ALMOST_EMPTY_SIZE_TX1,			/* IPA v4.0+ */
+	DUAL_TX_ENABLE,					/* IPA v4.5+ */
+	SSPND_PA_NO_START_STATE,		/* IPA v4,2+, not IPA v4.5 */
+	SSPND_PA_NO_BQ_STATE,				/* IPA v4.2 only */
+	HOLB_STICKY_DROP_EN,				/* IPA v5.0+ */
 };
 
 /* FLAVOR_0 register */
@@ -277,8 +277,8 @@ enum ipa_reg_idle_indication_cfg_field_id {
 
 /* QTIME_TIMESTAMP_CFG register */
 enum ipa_reg_qtime_timestamp_cfg_field_id {
-	DPL_TIMESTAMP_LSB,
-	DPL_TIMESTAMP_SEL,
+	DPL_TIMESTAMP_LSB,				/* Not IPA v5.5+ */
+	DPL_TIMESTAMP_SEL,				/* Not IPA v5.5+ */
 	TAG_TIMESTAMP_LSB,
 	NAT_TIMESTAMP_LSB,
 };
@@ -319,8 +319,8 @@ enum ipa_reg_rsrc_grp_rsrc_type_field_id {
 
 /* ENDP_INIT_CTRL register */
 enum ipa_reg_endp_init_ctrl_field_id {
-	ENDP_SUSPEND,					/* Not v4.0+ */
-	ENDP_DELAY,					/* Not v4.2+ */
+	ENDP_SUSPEND,					/* Not IPA v4.0+ */
+	ENDP_DELAY,					/* Not IPA v4.2+ */
 };
 
 /* ENDP_INIT_CFG register */
@@ -329,6 +329,7 @@ enum ipa_reg_endp_init_cfg_field_id {
 	CS_OFFLOAD_EN,
 	CS_METADATA_HDR_OFFSET,
 	CS_GEN_QMB_MASTER_SEL,
+	PIPE_REPLICATE_EN,				/* IPA v5.5+ */
 };
 
 /** enum ipa_cs_offload_en - ENDP_INIT_CFG register CS_OFFLOAD_EN field value */
@@ -359,11 +360,11 @@ enum ipa_reg_endp_init_hdr_field_id {
 	HDR_ADDITIONAL_CONST_LEN,
 	HDR_OFST_PKT_SIZE_VALID,
 	HDR_OFST_PKT_SIZE,
-	HDR_A5_MUX,					/* Not v4.9+ */
+	HDR_A5_MUX,					/* Not IPA v4.9+ */
 	HDR_LEN_INC_DEAGG_HDR,
-	HDR_METADATA_REG_VALID,				/* Not v4.5+ */
-	HDR_LEN_MSB,					/* v4.5+ */
-	HDR_OFST_METADATA_MSB,				/* v4.5+ */
+	HDR_METADATA_REG_VALID,				/* Not IPA v4.5+ */
+	HDR_LEN_MSB,					/* IPA v4.5+ */
+	HDR_OFST_METADATA_MSB,				/* IPA v4.5+ */
 };
 
 /* ENDP_INIT_HDR_EXT register */
@@ -374,23 +375,23 @@ enum ipa_reg_endp_init_hdr_ext_field_id {
 	HDR_PAYLOAD_LEN_INC_PADDING,
 	HDR_TOTAL_LEN_OR_PAD_OFFSET,
 	HDR_PAD_TO_ALIGNMENT,
-	HDR_TOTAL_LEN_OR_PAD_OFFSET_MSB,		/* v4.5+ */
-	HDR_OFST_PKT_SIZE_MSB,				/* v4.5+ */
-	HDR_ADDITIONAL_CONST_LEN_MSB,			/* v4.5+ */
-	HDR_BYTES_TO_REMOVE_VALID,			/* v5.0+ */
-	HDR_BYTES_TO_REMOVE,				/* v5.0+ */
+	HDR_TOTAL_LEN_OR_PAD_OFFSET_MSB,		/* IPA v4.5+ */
+	HDR_OFST_PKT_SIZE_MSB,				/* IPA v4.5+ */
+	HDR_ADDITIONAL_CONST_LEN_MSB,			/* IPA v4.5+ */
+	HDR_BYTES_TO_REMOVE_VALID,			/* IPA v5.0+ */
+	HDR_BYTES_TO_REMOVE,				/* IPA v5.0+ */
 };
 
 /* ENDP_INIT_MODE register */
 enum ipa_reg_endp_init_mode_field_id {
 	ENDP_MODE,
-	DCPH_ENABLE,					/* v4.5+ */
+	DCPH_ENABLE,					/* IPA v4.5+ */
 	DEST_PIPE_INDEX,
 	BYTE_THRESHOLD,
-	PIPE_REPLICATION_EN,
+	PIPE_REPLICATION_EN,				/* Not IPA v5.5+ */
 	PAD_EN,
-	HDR_FTCH_DISABLE,				/* v4.5+ */
-	DRBIP_ACL_ENABLE,				/* v4.9+ */
+	HDR_FTCH_DISABLE,				/* IPA v4.5+ */
+	DRBIP_ACL_ENABLE,				/* IPA v4.9+ */
 };
 
 /** enum ipa_mode - ENDP_INIT_MODE register MODE field value */
@@ -412,6 +413,7 @@ enum ipa_reg_endp_init_aggr_field_id {
 	FORCE_CLOSE,
 	HARD_BYTE_LIMIT_EN,
 	AGGR_GRAN_SEL,
+	AGGR_COAL_L2,					/* IPA v5.5+ */
 };
 
 /** enum ipa_aggr_en - ENDP_INIT_AGGR register AGGR_EN field value */
@@ -439,10 +441,10 @@ enum ipa_reg_endp_init_hol_block_en_field_id {
 
 /* ENDP_INIT_HOL_BLOCK_TIMER register */
 enum ipa_reg_endp_init_hol_block_timer_field_id {
-	TIMER_BASE_VALUE,				/* Not v4.5+ */
-	TIMER_SCALE,					/* v4.2 only */
-	TIMER_LIMIT,					/* v4.5+ */
-	TIMER_GRAN_SEL,					/* v4.5+ */
+	TIMER_BASE_VALUE,				/* Not IPA v4.5+ */
+	TIMER_SCALE,					/* IPA v4.2 only */
+	TIMER_LIMIT,					/* IPA v4.5+ */
+	TIMER_GRAN_SEL,					/* IPA v4.5+ */
 };
 
 /* ENDP_INIT_DEAGGR register */
@@ -463,7 +465,7 @@ enum ipa_reg_endp_init_rsrc_grp_field_id {
 /* ENDP_INIT_SEQ register */
 enum ipa_reg_endp_init_seq_field_id {
 	SEQ_TYPE,
-	SEQ_REP_TYPE,					/* Not v4.5+ */
+	SEQ_REP_TYPE,					/* Not IPA v4.5+ */
 };
 
 /**
@@ -512,8 +514,8 @@ enum ipa_seq_rep_type {
 enum ipa_reg_endp_status_field_id {
 	STATUS_EN,
 	STATUS_ENDP,
-	STATUS_LOCATION,				/* Not v4.5+ */
-	STATUS_PKT_SUPPRESS,				/* v4.0+ */
+	STATUS_LOCATION,				/* Not IPA v4.5+ */
+	STATUS_PKT_SUPPRESS,				/* IPA v4.0+ */
 };
 
 /* ENDP_FILTER_ROUTER_HSH_CFG register */
@@ -585,11 +587,12 @@ enum ipa_reg_endp_cache_cfg_field_id {
  * @IPA_IRQ_DRBIP_PKT_EXCEED_MAX_SIZE_EN: (Not currently used)
  * @IPA_IRQ_DRBIP_DATA_SCTR_CFG_ERROR_EN: (Not currently used)
  * @IPA_IRQ_DRBIP_IMM_CMD_NO_FLSH_HZRD_EN: (Not currently used)
+ * @IPA_IRQ_ERROR_NON_FATAL:		(Not currently used)
+ * @IPA_IRQ_ERROR_FATAL:		(Not currently used)
  */
 enum ipa_irq_id {
-	IPA_IRQ_BAD_SNOC_ACCESS			= 0x0,
-	/* The next bit is not present for IPA v3.5+ */
-	IPA_IRQ_EOT_COAL			= 0x1,
+	IPA_IRQ_BAD_SNOC_ACCESS			= 0x0,	/* Not IPA v5.5+ */
+	IPA_IRQ_EOT_COAL			= 0x1,	/* Not IPA v3.5+ */
 	IPA_IRQ_UC_0				= 0x2,
 	IPA_IRQ_UC_1				= 0x3,
 	IPA_IRQ_UC_2				= 0x4,
@@ -597,11 +600,11 @@ enum ipa_irq_id {
 	IPA_IRQ_UC_IN_Q_NOT_EMPTY		= 0x6,
 	IPA_IRQ_UC_RX_CMD_Q_NOT_FULL		= 0x7,
 	IPA_IRQ_PROC_UC_ACK_Q_NOT_EMPTY		= 0x8,
-	IPA_IRQ_RX_ERR				= 0x9,
-	IPA_IRQ_DEAGGR_ERR			= 0xa,
-	IPA_IRQ_TX_ERR				= 0xb,
-	IPA_IRQ_STEP_MODE			= 0xc,
-	IPA_IRQ_PROC_ERR			= 0xd,
+	IPA_IRQ_RX_ERR				= 0x9,	/* Not IPA v5.5+ */
+	IPA_IRQ_DEAGGR_ERR			= 0xa,	/* Not IPA v5.5+ */
+	IPA_IRQ_TX_ERR				= 0xb,	/* Not IPA v5.5+ */
+	IPA_IRQ_STEP_MODE			= 0xc,	/* Not IPA v5.5+ */
+	IPA_IRQ_PROC_ERR			= 0xd,	/* Not IPA v5.5+ */
 	IPA_IRQ_TX_SUSPEND			= 0xe,
 	IPA_IRQ_TX_HOLB_DROP			= 0xf,
 	IPA_IRQ_BAM_GSI_IDLE			= 0x10,
@@ -610,17 +613,16 @@ enum ipa_irq_id {
 	IPA_IRQ_PIPE_YELLOW_ABOVE		= 0x13,
 	IPA_IRQ_PIPE_RED_ABOVE			= 0x14,
 	IPA_IRQ_UCP				= 0x15,
-	/* The next bit is not present for IPA v4.5+ */
-	IPA_IRQ_DCMP				= 0x16,
+	IPA_IRQ_DCMP				= 0x16,	/* Not IPA v4.5+ */
 	IPA_IRQ_GSI_EE				= 0x17,
 	IPA_IRQ_GSI_IPA_IF_TLV_RCVD		= 0x18,
 	IPA_IRQ_GSI_UC				= 0x19,
-	/* The next bit is present for IPA v4.5+ */
-	IPA_IRQ_TLV_LEN_MIN_DSM			= 0x1a,
-	/* The next three bits are present for IPA v4.9+ */
-	IPA_IRQ_DRBIP_PKT_EXCEED_MAX_SIZE_EN	= 0x1b,
-	IPA_IRQ_DRBIP_DATA_SCTR_CFG_ERROR_EN	= 0x1c,
-	IPA_IRQ_DRBIP_IMM_CMD_NO_FLSH_HZRD_EN	= 0x1d,
+	IPA_IRQ_TLV_LEN_MIN_DSM			= 0x1a,	/* IPA v4.5-v5.2 */
+	IPA_IRQ_DRBIP_PKT_EXCEED_MAX_SIZE_EN	= 0x1b,	/* IPA v4.9-v5.2 */
+	IPA_IRQ_DRBIP_DATA_SCTR_CFG_ERROR_EN	= 0x1c,	/* IPA v4.9-v5.2 */
+	IPA_IRQ_DRBIP_IMM_CMD_NO_FLSH_HZRD_EN	= 0x1d,	/* IPA v4.9-v5.2 */
+	IPA_IRQ_ERROR_NON_FATAL			= 0x1e,	/* IPA v5.5+ */
+	IPA_IRQ_ERROR_FATAL			= 0x1f,	/* IPA v5.5+ */
 	IPA_IRQ_COUNT,				/* Last; not an id */
 };
 
@@ -637,6 +639,7 @@ extern const struct regs ipa_regs_v4_7;
 extern const struct regs ipa_regs_v4_9;
 extern const struct regs ipa_regs_v4_11;
 extern const struct regs ipa_regs_v5_0;
+extern const struct regs ipa_regs_v5_5;
 
 const struct reg *ipa_reg(struct ipa *ipa, enum ipa_reg_id reg_id);
 
diff --git a/drivers/net/ipa/ipa_version.h b/drivers/net/ipa/ipa_version.h
index 06e75b8ece7e..38150345b607 100644
--- a/drivers/net/ipa/ipa_version.h
+++ b/drivers/net/ipa/ipa_version.h
@@ -56,6 +56,7 @@ static inline bool ipa_version_supported(enum ipa_version version)
 	case IPA_VERSION_4_9:
 	case IPA_VERSION_4_11:
 	case IPA_VERSION_5_0:
+	case IPA_VERSION_5_5:
 		return true;
 	default:
 		return false;
diff --git a/drivers/net/ipa/reg/gsi_reg-v5.0.c b/drivers/net/ipa/reg/gsi_reg-v5.0.c
index d7b81a36d673..145eb0bd096d 100644
--- a/drivers/net/ipa/reg/gsi_reg-v5.0.c
+++ b/drivers/net/ipa/reg/gsi_reg-v5.0.c
@@ -78,7 +78,7 @@ REG_STRIDE_FIELDS(EV_CH_E_CNTXT_0, ev_ch_e_cntxt_0,
 		  0x0001c000 + 0x12000 * GSI_EE_AP, 0x80);
 
 static const u32 reg_ev_ch_e_cntxt_1_fmask[] = {
-	[R_LENGTH]					= GENMASK(19, 0),
+	[R_LENGTH]					= GENMASK(23, 0),
 };
 
 REG_STRIDE_FIELDS(EV_CH_E_CNTXT_1, ev_ch_e_cntxt_1,
diff --git a/drivers/net/ipa/reg/ipa_reg-v5.5.c b/drivers/net/ipa/reg/ipa_reg-v5.5.c
new file mode 100644
index 000000000000..26ca9c9bac59
--- /dev/null
+++ b/drivers/net/ipa/reg/ipa_reg-v5.5.c
@@ -0,0 +1,565 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Copyright (C) 2023 Linaro Ltd. */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/bits.h>
+
+#include "../ipa_reg.h"
+#include "../ipa_version.h"
+
+static const u32 reg_flavor_0_fmask[] = {
+	[MAX_PIPES]					= GENMASK(7, 0),
+	[MAX_CONS_PIPES]				= GENMASK(15, 8),
+	[MAX_PROD_PIPES]				= GENMASK(23, 16),
+	[PROD_LOWEST]					= GENMASK(31, 24),
+};
+
+REG_FIELDS(FLAVOR_0, flavor_0, 0x00000000);
+
+static const u32 reg_comp_cfg_fmask[] = {
+	[RAM_ARB_PRI_CLIENT_SAMP_FIX_DIS]		= BIT(0),
+	[GSI_SNOC_BYPASS_DIS]				= BIT(1),
+	[GEN_QMB_0_SNOC_BYPASS_DIS]			= BIT(2),
+	[GEN_QMB_1_SNOC_BYPASS_DIS]			= BIT(3),
+						/* Bit 4 reserved */
+	[IPA_QMB_SELECT_CONS_EN]			= BIT(5),
+	[IPA_QMB_SELECT_PROD_EN]			= BIT(6),
+	[GSI_MULTI_INORDER_RD_DIS]			= BIT(7),
+	[GSI_MULTI_INORDER_WR_DIS]			= BIT(8),
+	[GEN_QMB_0_MULTI_INORDER_RD_DIS]		= BIT(9),
+	[GEN_QMB_1_MULTI_INORDER_RD_DIS]		= BIT(10),
+	[GEN_QMB_0_MULTI_INORDER_WR_DIS]		= BIT(11),
+	[GEN_QMB_1_MULTI_INORDER_WR_DIS]		= BIT(12),
+	[GEN_QMB_0_SNOC_CNOC_LOOP_PROT_DIS]		= BIT(13),
+	[GSI_SNOC_CNOC_LOOP_PROT_DISABLE]		= BIT(14),
+	[GSI_MULTI_AXI_MASTERS_DIS]			= BIT(15),
+	[IPA_QMB_SELECT_GLOBAL_EN]			= BIT(16),
+						/* Bits 17-18 reserved */
+	[QMB_RAM_RD_CACHE_DISABLE]			= BIT(19),
+	[GENQMB_AOOOWR]					= BIT(20),
+	[IF_OUT_OF_BUF_STOP_RESET_MASK_EN]		= BIT(21),
+	[ATOMIC_FETCHER_ARB_LOCK_DIS]			= GENMASK(27, 22),
+						/* Bits 28-29 reserved */
+	[GEN_QMB_1_DYNAMIC_ASIZE]			= BIT(30),
+	[GEN_QMB_0_DYNAMIC_ASIZE]			= BIT(31),
+};
+
+REG_FIELDS(COMP_CFG, comp_cfg, 0x00000048);
+
+static const u32 reg_clkon_cfg_fmask[] = {
+	[CLKON_RX]					= BIT(0),
+	[CLKON_PROC]					= BIT(1),
+	[TX_WRAPPER]					= BIT(2),
+	[CLKON_MISC]					= BIT(3),
+	[RAM_ARB]					= BIT(4),
+	[FTCH_HPS]					= BIT(5),
+	[FTCH_DPS]					= BIT(6),
+	[CLKON_HPS]					= BIT(7),
+	[CLKON_DPS]					= BIT(8),
+	[RX_HPS_CMDQS]					= BIT(9),
+	[HPS_DPS_CMDQS]					= BIT(10),
+	[DPS_TX_CMDQS]					= BIT(11),
+	[RSRC_MNGR]					= BIT(12),
+	[CTX_HANDLER]					= BIT(13),
+	[ACK_MNGR]					= BIT(14),
+	[D_DCPH]					= BIT(15),
+	[H_DCPH]					= BIT(16),
+						/* Bit 17 reserved */
+	[NTF_TX_CMDQS]					= BIT(18),
+	[CLKON_TX_0]					= BIT(19),
+	[CLKON_TX_1]					= BIT(20),
+	[CLKON_FNR]					= BIT(21),
+	[QSB2AXI_CMDQ_L]				= BIT(22),
+	[AGGR_WRAPPER]					= BIT(23),
+	[RAM_SLAVEWAY]					= BIT(24),
+	[CLKON_QMB]					= BIT(25),
+	[WEIGHT_ARB]					= BIT(26),
+	[GSI_IF]					= BIT(27),
+	[CLKON_GLOBAL]					= BIT(28),
+	[GLOBAL_2X_CLK]					= BIT(29),
+	[DPL_FIFO]					= BIT(30),
+	[DRBIP]						= BIT(31),
+};
+
+REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000050);
+
+static const u32 reg_route_fmask[] = {
+	[ROUTE_DEF_PIPE]				= GENMASK(7, 0),
+	[ROUTE_FRAG_DEF_PIPE]				= GENMASK(15, 8),
+	[ROUTE_DEF_HDR_OFST]				= GENMASK(25, 16),
+	[ROUTE_DEF_HDR_TABLE]				= BIT(26),
+	[ROUTE_DEF_RETAIN_HDR]				= BIT(27),
+	[ROUTE_DIS]					= BIT(28),
+						/* Bits 29-31 reserved */
+};
+
+REG_FIELDS(ROUTE, route, 0x00000054);
+
+static const u32 reg_shared_mem_size_fmask[] = {
+	[MEM_SIZE]					= GENMASK(15, 0),
+	[MEM_BADDR]					= GENMASK(31, 16),
+};
+
+REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x0000005c);
+
+static const u32 reg_qsb_max_writes_fmask[] = {
+	[GEN_QMB_0_MAX_WRITES]				= GENMASK(3, 0),
+	[GEN_QMB_1_MAX_WRITES]				= GENMASK(7, 4),
+						/* Bits 8-31 reserved */
+};
+
+REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000070);
+
+static const u32 reg_qsb_max_reads_fmask[] = {
+	[GEN_QMB_0_MAX_READS]				= GENMASK(3, 0),
+	[GEN_QMB_1_MAX_READS]				= GENMASK(7, 4),
+						/* Bits 8-15 reserved */
+	[GEN_QMB_0_MAX_READS_BEATS]			= GENMASK(23, 16),
+	[GEN_QMB_1_MAX_READS_BEATS]			= GENMASK(31, 24),
+};
+
+REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000074);
+
+/* Valid bits defined by ipa->available */
+
+REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x00000120, 0x0004);
+
+static const u32 reg_filt_rout_cache_flush_fmask[] = {
+	[ROUTER_CACHE]					= BIT(0),
+						/* Bits 1-3 reserved */
+	[FILTER_CACHE]					= BIT(4),
+						/* Bits 5-31 reserved */
+};
+
+REG_FIELDS(FILT_ROUT_CACHE_FLUSH, filt_rout_cache_flush, 0x0000404);
+
+static const u32 reg_local_pkt_proc_cntxt_fmask[] = {
+	[IPA_BASE_ADDR]					= GENMASK(17, 0),
+						/* Bits 18-31 reserved */
+};
+
+/* Offset must be a multiple of 8 */
+REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x00000478);
+
+static const u32 reg_ipa_tx_cfg_fmask[] = {
+						/* Bits 0-1 reserved */
+	[PREFETCH_ALMOST_EMPTY_SIZE_TX0]		= GENMASK(5, 2),
+	[DMAW_SCND_OUTSD_PRED_THRESHOLD]		= GENMASK(9, 6),
+	[DMAW_SCND_OUTSD_PRED_EN]			= BIT(10),
+	[DMAW_MAX_BEATS_256_DIS]			= BIT(11),
+	[PA_MASK_EN]					= BIT(12),
+	[PREFETCH_ALMOST_EMPTY_SIZE_TX1]		= GENMASK(16, 13),
+	[DUAL_TX_ENABLE]				= BIT(17),
+	[SSPND_PA_NO_START_STATE]			= BIT(18),
+						/* Bit 19 reserved */
+	[HOLB_STICKY_DROP_EN]				= BIT(20),
+						/* Bits 21-31 reserved */
+};
+
+REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x00000488);
+
+static const u32 reg_idle_indication_cfg_fmask[] = {
+	[ENTER_IDLE_DEBOUNCE_THRESH]			= GENMASK(15, 0),
+	[CONST_NON_IDLE_ENABLE]				= BIT(16),
+						/* Bits 17-31 reserved */
+};
+
+REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x000004a8);
+
+static const u32 reg_qtime_timestamp_cfg_fmask[] = {
+						/* Bits 0-7 reserved */
+	[TAG_TIMESTAMP_LSB]				= GENMASK(12, 8),
+						/* Bits 13-15 reserved */
+	[NAT_TIMESTAMP_LSB]				= GENMASK(20, 16),
+						/* Bits 21-31 reserved */
+};
+
+REG_FIELDS(QTIME_TIMESTAMP_CFG, qtime_timestamp_cfg, 0x000004ac);
+
+static const u32 reg_timers_xo_clk_div_cfg_fmask[] = {
+	[DIV_VALUE]					= GENMASK(8, 0),
+						/* Bits 9-30 reserved */
+	[DIV_ENABLE]					= BIT(31),
+};
+
+REG_FIELDS(TIMERS_XO_CLK_DIV_CFG, timers_xo_clk_div_cfg, 0x000004b0);
+
+static const u32 reg_timers_pulse_gran_cfg_fmask[] = {
+	[PULSE_GRAN_0]					= GENMASK(2, 0),
+	[PULSE_GRAN_1]					= GENMASK(5, 3),
+	[PULSE_GRAN_2]					= GENMASK(8, 6),
+	[PULSE_GRAN_3]					= GENMASK(11, 9),
+						/* Bits 12-31 reserved */
+};
+
+REG_FIELDS(TIMERS_PULSE_GRAN_CFG, timers_pulse_gran_cfg, 0x000004b4);
+
+static const u32 reg_src_rsrc_grp_01_rsrc_type_fmask[] = {
+	[X_MIN_LIM]					= GENMASK(5, 0),
+						/* Bits 6-7 reserved */
+	[X_MAX_LIM]					= GENMASK(13, 8),
+						/* Bits 14-15 reserved */
+	[Y_MIN_LIM]					= GENMASK(21, 16),
+						/* Bits 22-23 reserved */
+	[Y_MAX_LIM]					= GENMASK(29, 24),
+						/* Bits 30-31 reserved */
+};
+
+REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type,
+		  0x00000500, 0x0020);
+
+static const u32 reg_src_rsrc_grp_23_rsrc_type_fmask[] = {
+	[X_MIN_LIM]					= GENMASK(5, 0),
+						/* Bits 6-7 reserved */
+	[X_MAX_LIM]					= GENMASK(13, 8),
+						/* Bits 14-15 reserved */
+	[Y_MIN_LIM]					= GENMASK(21, 16),
+						/* Bits 22-23 reserved */
+	[Y_MAX_LIM]					= GENMASK(29, 24),
+						/* Bits 30-31 reserved */
+};
+
+REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type,
+		  0x00000504, 0x0020);
+
+static const u32 reg_src_rsrc_grp_45_rsrc_type_fmask[] = {
+	[X_MIN_LIM]					= GENMASK(5, 0),
+						/* Bits 6-7 reserved */
+	[X_MAX_LIM]					= GENMASK(13, 8),
+						/* Bits 14-15 reserved */
+	[Y_MIN_LIM]					= GENMASK(21, 16),
+						/* Bits 22-23 reserved */
+	[Y_MAX_LIM]					= GENMASK(29, 24),
+						/* Bits 30-31 reserved */
+};
+
+REG_STRIDE_FIELDS(SRC_RSRC_GRP_45_RSRC_TYPE, src_rsrc_grp_45_rsrc_type,
+		  0x00000508, 0x0020);
+
+static const u32 reg_src_rsrc_grp_67_rsrc_type_fmask[] = {
+	[X_MIN_LIM]					= GENMASK(5, 0),
+						/* Bits 6-7 reserved */
+	[X_MAX_LIM]					= GENMASK(13, 8),
+						/* Bits 14-15 reserved */
+	[Y_MIN_LIM]					= GENMASK(21, 16),
+						/* Bits 22-23 reserved */
+	[Y_MAX_LIM]					= GENMASK(29, 24),
+						/* Bits 30-31 reserved */
+};
+
+REG_STRIDE_FIELDS(SRC_RSRC_GRP_67_RSRC_TYPE, src_rsrc_grp_67_rsrc_type,
+		  0x0000050c, 0x0020);
+
+static const u32 reg_dst_rsrc_grp_01_rsrc_type_fmask[] = {
+	[X_MIN_LIM]					= GENMASK(5, 0),
+						/* Bits 6-7 reserved */
+	[X_MAX_LIM]					= GENMASK(13, 8),
+						/* Bits 14-15 reserved */
+	[Y_MIN_LIM]					= GENMASK(21, 16),
+						/* Bits 22-23 reserved */
+	[Y_MAX_LIM]					= GENMASK(29, 24),
+						/* Bits 30-31 reserved */
+};
+
+REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type,
+		  0x00000600, 0x0020);
+
+static const u32 reg_dst_rsrc_grp_23_rsrc_type_fmask[] = {
+	[X_MIN_LIM]					= GENMASK(5, 0),
+						/* Bits 6-7 reserved */
+	[X_MAX_LIM]					= GENMASK(13, 8),
+						/* Bits 14-15 reserved */
+	[Y_MIN_LIM]					= GENMASK(21, 16),
+						/* Bits 22-23 reserved */
+	[Y_MAX_LIM]					= GENMASK(29, 24),
+						/* Bits 30-31 reserved */
+};
+
+REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type,
+		  0x00000604, 0x0020);
+
+static const u32 reg_dst_rsrc_grp_45_rsrc_type_fmask[] = {
+	[X_MIN_LIM]					= GENMASK(5, 0),
+						/* Bits 6-7 reserved */
+	[X_MAX_LIM]					= GENMASK(13, 8),
+						/* Bits 14-15 reserved */
+	[Y_MIN_LIM]					= GENMASK(21, 16),
+						/* Bits 22-23 reserved */
+	[Y_MAX_LIM]					= GENMASK(29, 24),
+						/* Bits 30-31 reserved */
+};
+
+REG_STRIDE_FIELDS(DST_RSRC_GRP_45_RSRC_TYPE, dst_rsrc_grp_45_rsrc_type,
+		  0x00000608, 0x0020);
+
+static const u32 reg_dst_rsrc_grp_67_rsrc_type_fmask[] = {
+	[X_MIN_LIM]					= GENMASK(5, 0),
+						/* Bits 6-7 reserved */
+	[X_MAX_LIM]					= GENMASK(13, 8),
+						/* Bits 14-15 reserved */
+	[Y_MIN_LIM]					= GENMASK(21, 16),
+						/* Bits 22-23 reserved */
+	[Y_MAX_LIM]					= GENMASK(29, 24),
+						/* Bits 30-31 reserved */
+};
+
+REG_STRIDE_FIELDS(DST_RSRC_GRP_67_RSRC_TYPE, dst_rsrc_grp_67_rsrc_type,
+		  0x0000060c, 0x0020);
+
+/* Valid bits defined by ipa->available */
+
+REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000006b0, 0x0004);
+
+static const u32 reg_endp_init_cfg_fmask[] = {
+	[FRAG_OFFLOAD_EN]				= BIT(0),
+	[CS_OFFLOAD_EN]					= GENMASK(2, 1),
+	[CS_METADATA_HDR_OFFSET]			= GENMASK(6, 3),
+						/* Bit 7 reserved */
+	[CS_GEN_QMB_MASTER_SEL]				= BIT(8),
+	[PIPE_REPLICATE_EN]				= BIT(9),
+						/* Bits 10-31 reserved */
+};
+
+REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00001008, 0x0080);
+
+static const u32 reg_endp_init_nat_fmask[] = {
+	[NAT_EN]					= GENMASK(1, 0),
+						/* Bits 2-31 reserved */
+};
+
+REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000100c, 0x0080);
+
+static const u32 reg_endp_init_hdr_fmask[] = {
+	[HDR_LEN]					= GENMASK(5, 0),
+	[HDR_OFST_METADATA_VALID]			= BIT(6),
+	[HDR_OFST_METADATA]				= GENMASK(12, 7),
+	[HDR_ADDITIONAL_CONST_LEN]			= GENMASK(18, 13),
+	[HDR_OFST_PKT_SIZE_VALID]			= BIT(19),
+	[HDR_OFST_PKT_SIZE]				= GENMASK(25, 20),
+						/* Bit 26 reserved */
+	[HDR_LEN_INC_DEAGG_HDR]				= BIT(27),
+	[HDR_LEN_MSB]					= GENMASK(29, 28),
+	[HDR_OFST_METADATA_MSB]				= GENMASK(31, 30),
+};
+
+REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00001010, 0x0080);
+
+static const u32 reg_endp_init_hdr_ext_fmask[] = {
+	[HDR_ENDIANNESS]				= BIT(0),
+	[HDR_TOTAL_LEN_OR_PAD_VALID]			= BIT(1),
+	[HDR_TOTAL_LEN_OR_PAD]				= BIT(2),
+	[HDR_PAYLOAD_LEN_INC_PADDING]			= BIT(3),
+	[HDR_TOTAL_LEN_OR_PAD_OFFSET]			= GENMASK(9, 4),
+	[HDR_PAD_TO_ALIGNMENT]				= GENMASK(13, 10),
+						/* Bits 14-15 reserved */
+	[HDR_TOTAL_LEN_OR_PAD_OFFSET_MSB]		= GENMASK(17, 16),
+	[HDR_OFST_PKT_SIZE_MSB]				= GENMASK(19, 18),
+	[HDR_ADDITIONAL_CONST_LEN_MSB]			= GENMASK(21, 20),
+	[HDR_BYTES_TO_REMOVE_VALID]			= BIT(22),
+						/* Bit 23 reserved */
+	[HDR_BYTES_TO_REMOVE]				= GENMASK(31, 24),
+};
+
+REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00001014, 0x0080);
+
+REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask,
+	   0x00001018, 0x0080);
+
+static const u32 reg_endp_init_mode_fmask[] = {
+	[ENDP_MODE]					= GENMASK(2, 0),
+	[DCPH_ENABLE]					= BIT(3),
+	[DEST_PIPE_INDEX]				= GENMASK(11, 4),
+	[BYTE_THRESHOLD]				= GENMASK(27, 12),
+						/* Bit 28 reserved */
+	[PAD_EN]					= BIT(29),
+	[DRBIP_ACL_ENABLE]				= BIT(30),
+						/* Bit 31 reserved */
+};
+
+REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00001020, 0x0080);
+
+static const u32 reg_endp_init_aggr_fmask[] = {
+	[AGGR_EN]					= GENMASK(1, 0),
+	[AGGR_TYPE]					= GENMASK(4, 2),
+	[BYTE_LIMIT]					= GENMASK(10, 5),
+						/* Bit 11 reserved */
+	[TIME_LIMIT]					= GENMASK(16, 12),
+	[PKT_LIMIT]					= GENMASK(22, 17),
+	[SW_EOF_ACTIVE]					= BIT(23),
+	[FORCE_CLOSE]					= BIT(24),
+						/* Bit 25 reserved */
+	[HARD_BYTE_LIMIT_EN]				= BIT(26),
+	[AGGR_GRAN_SEL]					= BIT(27),
+	[AGGR_COAL_L2]					= BIT(28),
+						/* Bits 27-31 reserved */
+};
+
+REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00001024, 0x0080);
+
+static const u32 reg_endp_init_hol_block_en_fmask[] = {
+	[HOL_BLOCK_EN]					= BIT(0),
+						/* Bits 1-31 reserved */
+};
+
+REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en,
+		  0x0000102c, 0x0080);
+
+static const u32 reg_endp_init_hol_block_timer_fmask[] = {
+	[TIMER_LIMIT]					= GENMASK(4, 0),
+						/* Bits 5-7 reserved */
+	[TIMER_GRAN_SEL]				= GENMASK(9, 8),
+						/* Bits 10-31 reserved */
+};
+
+REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer,
+		  0x00001030, 0x0080);
+
+static const u32 reg_endp_init_deaggr_fmask[] = {
+	[DEAGGR_HDR_LEN]				= GENMASK(5, 0),
+	[SYSPIPE_ERR_DETECTION]				= BIT(6),
+	[PACKET_OFFSET_VALID]				= BIT(7),
+	[PACKET_OFFSET_LOCATION]			= GENMASK(13, 8),
+	[IGNORE_MIN_PKT_ERR]				= BIT(14),
+						/* Bit 15 reserved */
+	[MAX_PACKET_LEN]				= GENMASK(31, 16),
+};
+
+REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00001034, 0x0080);
+
+static const u32 reg_endp_init_rsrc_grp_fmask[] = {
+	[ENDP_RSRC_GRP]					= GENMASK(2, 0),
+						/* Bits 3-31 reserved */
+};
+
+REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, 0x00001038, 0x0080);
+
+static const u32 reg_endp_init_seq_fmask[] = {
+	[SEQ_TYPE]					= GENMASK(7, 0),
+						/* Bits 8-31 reserved */
+};
+
+REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000103c, 0x0080);
+
+static const u32 reg_endp_status_fmask[] = {
+	[STATUS_EN]					= BIT(0),
+	[STATUS_ENDP]					= GENMASK(8, 1),
+	[STATUS_PKT_SUPPRESS]				= BIT(9),
+						/* Bits 10-31 reserved */
+};
+
+REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00001040, 0x0080);
+
+static const u32 reg_endp_filter_cache_cfg_fmask[] = {
+	[CACHE_MSK_SRC_ID]				= BIT(0),
+	[CACHE_MSK_SRC_IP]				= BIT(1),
+	[CACHE_MSK_DST_IP]				= BIT(2),
+	[CACHE_MSK_SRC_PORT]				= BIT(3),
+	[CACHE_MSK_DST_PORT]				= BIT(4),
+	[CACHE_MSK_PROTOCOL]				= BIT(5),
+	[CACHE_MSK_METADATA]				= BIT(6),
+						/* Bits 7-31 reserved */
+};
+
+REG_STRIDE_FIELDS(ENDP_FILTER_CACHE_CFG, endp_filter_cache_cfg,
+		  0x0000105c, 0x0080);
+
+static const u32 reg_endp_router_cache_cfg_fmask[] = {
+	[CACHE_MSK_SRC_ID]				= BIT(0),
+	[CACHE_MSK_SRC_IP]				= BIT(1),
+	[CACHE_MSK_DST_IP]				= BIT(2),
+	[CACHE_MSK_SRC_PORT]				= BIT(3),
+	[CACHE_MSK_DST_PORT]				= BIT(4),
+	[CACHE_MSK_PROTOCOL]				= BIT(5),
+	[CACHE_MSK_METADATA]				= BIT(6),
+						/* Bits 7-31 reserved */
+};
+
+REG_STRIDE_FIELDS(ENDP_ROUTER_CACHE_CFG, endp_router_cache_cfg,
+		  0x00001060, 0x0080);
+
+/* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */
+REG(IPA_IRQ_STTS, ipa_irq_stts, 0x0000c008 + 0x1000 * GSI_EE_AP);
+
+/* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */
+REG(IPA_IRQ_EN, ipa_irq_en, 0x0000c00c + 0x1000 * GSI_EE_AP);
+
+/* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */
+REG(IPA_IRQ_CLR, ipa_irq_clr, 0x0000c010 + 0x1000 * GSI_EE_AP);
+
+static const u32 reg_ipa_irq_uc_fmask[] = {
+	[UC_INTR]					= BIT(0),
+						/* Bits 1-31 reserved */
+};
+
+REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000c01c + 0x1000 * GSI_EE_AP);
+
+/* Valid bits defined by ipa->available */
+
+REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info,
+	   0x0000c030 + 0x1000 * GSI_EE_AP, 0x0004);
+
+/* Valid bits defined by ipa->available */
+
+REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en,
+	   0x0000c050 + 0x1000 * GSI_EE_AP, 0x0004);
+
+/* Valid bits defined by ipa->available */
+
+REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr,
+	   0x0000c070 + 0x1000 * GSI_EE_AP, 0x0004);
+
+static const struct reg *reg_array[] = {
+	[COMP_CFG]			= &reg_comp_cfg,
+	[CLKON_CFG]			= &reg_clkon_cfg,
+	[ROUTE]				= &reg_route,
+	[SHARED_MEM_SIZE]		= &reg_shared_mem_size,
+	[QSB_MAX_WRITES]		= &reg_qsb_max_writes,
+	[QSB_MAX_READS]			= &reg_qsb_max_reads,
+	[FILT_ROUT_CACHE_FLUSH]		= &reg_filt_rout_cache_flush,
+	[STATE_AGGR_ACTIVE]		= &reg_state_aggr_active,
+	[LOCAL_PKT_PROC_CNTXT]		= &reg_local_pkt_proc_cntxt,
+	[AGGR_FORCE_CLOSE]		= &reg_aggr_force_close,
+	[IPA_TX_CFG]			= &reg_ipa_tx_cfg,
+	[FLAVOR_0]			= &reg_flavor_0,
+	[IDLE_INDICATION_CFG]		= &reg_idle_indication_cfg,
+	[QTIME_TIMESTAMP_CFG]		= &reg_qtime_timestamp_cfg,
+	[TIMERS_XO_CLK_DIV_CFG]		= &reg_timers_xo_clk_div_cfg,
+	[TIMERS_PULSE_GRAN_CFG]		= &reg_timers_pulse_gran_cfg,
+	[SRC_RSRC_GRP_01_RSRC_TYPE]	= &reg_src_rsrc_grp_01_rsrc_type,
+	[SRC_RSRC_GRP_23_RSRC_TYPE]	= &reg_src_rsrc_grp_23_rsrc_type,
+	[SRC_RSRC_GRP_45_RSRC_TYPE]	= &reg_src_rsrc_grp_45_rsrc_type,
+	[SRC_RSRC_GRP_67_RSRC_TYPE]	= &reg_src_rsrc_grp_67_rsrc_type,
+	[DST_RSRC_GRP_01_RSRC_TYPE]	= &reg_dst_rsrc_grp_01_rsrc_type,
+	[DST_RSRC_GRP_23_RSRC_TYPE]	= &reg_dst_rsrc_grp_23_rsrc_type,
+	[DST_RSRC_GRP_45_RSRC_TYPE]	= &reg_dst_rsrc_grp_45_rsrc_type,
+	[DST_RSRC_GRP_67_RSRC_TYPE]	= &reg_dst_rsrc_grp_67_rsrc_type,
+	[ENDP_INIT_CFG]			= &reg_endp_init_cfg,
+	[ENDP_INIT_NAT]			= &reg_endp_init_nat,
+	[ENDP_INIT_HDR]			= &reg_endp_init_hdr,
+	[ENDP_INIT_HDR_EXT]		= &reg_endp_init_hdr_ext,
+	[ENDP_INIT_HDR_METADATA_MASK]	= &reg_endp_init_hdr_metadata_mask,
+	[ENDP_INIT_MODE]		= &reg_endp_init_mode,
+	[ENDP_INIT_AGGR]		= &reg_endp_init_aggr,
+	[ENDP_INIT_HOL_BLOCK_EN]	= &reg_endp_init_hol_block_en,
+	[ENDP_INIT_HOL_BLOCK_TIMER]	= &reg_endp_init_hol_block_timer,
+	[ENDP_INIT_DEAGGR]		= &reg_endp_init_deaggr,
+	[ENDP_INIT_RSRC_GRP]		= &reg_endp_init_rsrc_grp,
+	[ENDP_INIT_SEQ]			= &reg_endp_init_seq,
+	[ENDP_STATUS]			= &reg_endp_status,
+	[ENDP_FILTER_CACHE_CFG]		= &reg_endp_filter_cache_cfg,
+	[ENDP_ROUTER_CACHE_CFG]		= &reg_endp_router_cache_cfg,
+	[IPA_IRQ_STTS]			= &reg_ipa_irq_stts,
+	[IPA_IRQ_EN]			= &reg_ipa_irq_en,
+	[IPA_IRQ_CLR]			= &reg_ipa_irq_clr,
+	[IPA_IRQ_UC]			= &reg_ipa_irq_uc,
+	[IRQ_SUSPEND_INFO]		= &reg_irq_suspend_info,
+	[IRQ_SUSPEND_EN]		= &reg_irq_suspend_en,
+	[IRQ_SUSPEND_CLR]		= &reg_irq_suspend_clr,
+};
+
+const struct regs ipa_regs_v5_5 = {
+	.reg_count	= ARRAY_SIZE(reg_array),
+	.reg		= reg_array,
+};
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 21e9cac73121..2d5b021b4ea6 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -411,7 +411,7 @@ struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h,
 	return addr;
 }
 
-static int ipvlan_process_v4_outbound(struct sk_buff *skb)
+static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb)
 {
 	const struct iphdr *ip4h = ip_hdr(skb);
 	struct net_device *dev = skb->dev;
@@ -453,13 +453,11 @@ out:
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-static int ipvlan_process_v6_outbound(struct sk_buff *skb)
+
+static noinline_for_stack int
+ipvlan_route_v6_outbound(struct net_device *dev, struct sk_buff *skb)
 {
 	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
-	struct net_device *dev = skb->dev;
-	struct net *net = dev_net(dev);
-	struct dst_entry *dst;
-	int err, ret = NET_XMIT_DROP;
 	struct flowi6 fl6 = {
 		.flowi6_oif = dev->ifindex,
 		.daddr = ip6h->daddr,
@@ -469,27 +467,38 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb)
 		.flowi6_mark = skb->mark,
 		.flowi6_proto = ip6h->nexthdr,
 	};
+	struct dst_entry *dst;
+	int err;
 
-	dst = ip6_route_output(net, NULL, &fl6);
-	if (dst->error) {
-		ret = dst->error;
+	dst = ip6_route_output(dev_net(dev), NULL, &fl6);
+	err = dst->error;
+	if (err) {
 		dst_release(dst);
-		goto err;
+		return err;
 	}
 	skb_dst_set(skb, dst);
+	return 0;
+}
+
+static int ipvlan_process_v6_outbound(struct sk_buff *skb)
+{
+	struct net_device *dev = skb->dev;
+	int err, ret = NET_XMIT_DROP;
+
+	err = ipvlan_route_v6_outbound(dev, skb);
+	if (unlikely(err)) {
+		DEV_STATS_INC(dev, tx_errors);
+		kfree_skb(skb);
+		return err;
+	}
 
 	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
 
-	err = ip6_local_out(net, skb->sk, skb);
+	err = ip6_local_out(dev_net(dev), skb->sk, skb);
 	if (unlikely(net_xmit_eval(err)))
 		DEV_STATS_INC(dev, tx_errors);
 	else
 		ret = NET_XMIT_SUCCESS;
-	goto out;
-err:
-	DEV_STATS_INC(dev, tx_errors);
-	kfree_skb(skb);
-out:
 	return ret;
 }
 #else
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 57c79f5f2991..df7c43a109e1 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -387,6 +387,7 @@ static const struct header_ops ipvlan_header_ops = {
 	.parse		= eth_header_parse,
 	.cache		= eth_header_cache,
 	.cache_update	= eth_header_cache_update,
+	.parse_protocol	= eth_header_parse_protocol,
 };
 
 static void ipvlan_adjust_mtu(struct ipvl_dev *ipvlan, struct net_device *dev)
@@ -600,15 +601,15 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev,
 		port->dev_id_start = 0x1;
 
 	/* Since L2 address is shared among all IPvlan slaves including
-	 * master, use unique 16 bit dev-ids to diffentiate among them.
+	 * master, use unique 16 bit dev-ids to differentiate among them.
 	 * Assign IDs between 0x1 and 0xFFFE (used by the master) to each
 	 * slave link [see addrconf_ifid_eui48()].
 	 */
-	err = ida_simple_get(&port->ida, port->dev_id_start, 0xFFFE,
-			     GFP_KERNEL);
+	err = ida_alloc_range(&port->ida, port->dev_id_start, 0xFFFD,
+			      GFP_KERNEL);
 	if (err < 0)
-		err = ida_simple_get(&port->ida, 0x1, port->dev_id_start,
-				     GFP_KERNEL);
+		err = ida_alloc_range(&port->ida, 0x1, port->dev_id_start - 1,
+				      GFP_KERNEL);
 	if (err < 0)
 		goto unregister_netdev;
 	dev->dev_id = err;
@@ -640,7 +641,7 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev,
 unlink_netdev:
 	netdev_upper_dev_unlink(phy_dev, dev);
 remove_ida:
-	ida_simple_remove(&port->ida, dev->dev_id);
+	ida_free(&port->ida, dev->dev_id);
 unregister_netdev:
 	unregister_netdevice(dev);
 	return err;
@@ -660,7 +661,7 @@ void ipvlan_link_delete(struct net_device *dev, struct list_head *head)
 	}
 	spin_unlock_bh(&ipvlan->addrs_lock);
 
-	ida_simple_remove(&ipvlan->port->ida, dev->dev_id);
+	ida_free(&ipvlan->port->ida, dev->dev_id);
 	list_del_rcu(&ipvlan->pnode);
 	unregister_netdevice_queue(dev, head);
 	netdev_upper_dev_unlink(ipvlan->phy_dev, dev);
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 9663050a852d..e34816638569 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -93,6 +93,8 @@ struct pcpu_secy_stats {
  * @secys: linked list of SecY's on the underlying device
  * @gro_cells: pointer to the Generic Receive Offload cell
  * @offload: status of offloading on the MACsec device
+ * @insert_tx_tag: when offloading, device requires to insert an
+ *	additional tag
  */
 struct macsec_dev {
 	struct macsec_secy secy;
@@ -102,6 +104,7 @@ struct macsec_dev {
 	struct list_head secys;
 	struct gro_cells gro_cells;
 	enum macsec_offload offload;
+	bool insert_tx_tag;
 };
 
 /**
@@ -604,26 +607,11 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
 		return ERR_PTR(-EINVAL);
 	}
 
-	if (unlikely(skb_headroom(skb) < MACSEC_NEEDED_HEADROOM ||
-		     skb_tailroom(skb) < MACSEC_NEEDED_TAILROOM)) {
-		struct sk_buff *nskb = skb_copy_expand(skb,
-						       MACSEC_NEEDED_HEADROOM,
-						       MACSEC_NEEDED_TAILROOM,
-						       GFP_ATOMIC);
-		if (likely(nskb)) {
-			consume_skb(skb);
-			skb = nskb;
-		} else {
-			macsec_txsa_put(tx_sa);
-			kfree_skb(skb);
-			return ERR_PTR(-ENOMEM);
-		}
-	} else {
-		skb = skb_unshare(skb, GFP_ATOMIC);
-		if (!skb) {
-			macsec_txsa_put(tx_sa);
-			return ERR_PTR(-ENOMEM);
-		}
+	ret = skb_ensure_writable_head_tail(skb, dev);
+	if (unlikely(ret < 0)) {
+		macsec_txsa_put(tx_sa);
+		kfree_skb(skb);
+		return ERR_PTR(ret);
 	}
 
 	unprotected_len = skb->len;
@@ -2583,6 +2571,33 @@ static bool macsec_is_configured(struct macsec_dev *macsec)
 	return false;
 }
 
+static bool macsec_needs_tx_tag(struct macsec_dev *macsec,
+				const struct macsec_ops *ops)
+{
+	return macsec->offload == MACSEC_OFFLOAD_PHY &&
+		ops->mdo_insert_tx_tag;
+}
+
+static void macsec_set_head_tail_room(struct net_device *dev)
+{
+	struct macsec_dev *macsec = macsec_priv(dev);
+	struct net_device *real_dev = macsec->real_dev;
+	int needed_headroom, needed_tailroom;
+	const struct macsec_ops *ops;
+
+	ops = macsec_get_ops(macsec, NULL);
+	if (ops) {
+		needed_headroom = ops->needed_headroom;
+		needed_tailroom = ops->needed_tailroom;
+	} else {
+		needed_headroom = MACSEC_NEEDED_HEADROOM;
+		needed_tailroom = MACSEC_NEEDED_TAILROOM;
+	}
+
+	dev->needed_headroom = real_dev->needed_headroom + needed_headroom;
+	dev->needed_tailroom = real_dev->needed_tailroom + needed_tailroom;
+}
+
 static int macsec_update_offload(struct net_device *dev, enum macsec_offload offload)
 {
 	enum macsec_offload prev_offload;
@@ -2620,8 +2635,13 @@ static int macsec_update_offload(struct net_device *dev, enum macsec_offload off
 	ctx.secy = &macsec->secy;
 	ret = offload == MACSEC_OFFLOAD_OFF ? macsec_offload(ops->mdo_del_secy, &ctx)
 					    : macsec_offload(ops->mdo_add_secy, &ctx);
-	if (ret)
+	if (ret) {
 		macsec->offload = prev_offload;
+		return ret;
+	}
+
+	macsec_set_head_tail_room(dev);
+	macsec->insert_tx_tag = macsec_needs_tx_tag(macsec, ops);
 
 	return ret;
 }
@@ -3379,6 +3399,40 @@ static struct genl_family macsec_fam __ro_after_init = {
 	.resv_start_op	= MACSEC_CMD_UPD_OFFLOAD + 1,
 };
 
+static struct sk_buff *macsec_insert_tx_tag(struct sk_buff *skb,
+					    struct net_device *dev)
+{
+	struct macsec_dev *macsec = macsec_priv(dev);
+	const struct macsec_ops *ops;
+	struct phy_device *phydev;
+	struct macsec_context ctx;
+	int skb_final_len;
+	int err;
+
+	ops = macsec_get_ops(macsec, &ctx);
+	skb_final_len = skb->len - ETH_HLEN + ops->needed_headroom +
+		ops->needed_tailroom;
+	if (unlikely(skb_final_len > macsec->real_dev->mtu)) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	phydev = macsec->real_dev->phydev;
+
+	err = skb_ensure_writable_head_tail(skb, dev);
+	if (unlikely(err < 0))
+		goto cleanup;
+
+	err = ops->mdo_insert_tx_tag(phydev, skb);
+	if (unlikely(err))
+		goto cleanup;
+
+	return skb;
+cleanup:
+	kfree_skb(skb);
+	return ERR_PTR(err);
+}
+
 static netdev_tx_t macsec_start_xmit(struct sk_buff *skb,
 				     struct net_device *dev)
 {
@@ -3393,6 +3447,15 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb,
 		skb_dst_drop(skb);
 		dst_hold(&md_dst->dst);
 		skb_dst_set(skb, &md_dst->dst);
+
+		if (macsec->insert_tx_tag) {
+			skb = macsec_insert_tx_tag(skb, dev);
+			if (IS_ERR(skb)) {
+				DEV_STATS_INC(dev, tx_dropped);
+				return NETDEV_TX_OK;
+			}
+		}
+
 		skb->dev = macsec->real_dev;
 		return dev_queue_xmit(skb);
 	}
@@ -3454,10 +3517,7 @@ static int macsec_dev_init(struct net_device *dev)
 	dev->features = real_dev->features & MACSEC_FEATURES;
 	dev->features |= NETIF_F_LLTX | NETIF_F_GSO_SOFTWARE;
 
-	dev->needed_headroom = real_dev->needed_headroom +
-			       MACSEC_NEEDED_HEADROOM;
-	dev->needed_tailroom = real_dev->needed_tailroom +
-			       MACSEC_NEEDED_TAILROOM;
+	macsec_set_head_tail_room(dev);
 
 	if (is_zero_ether_addr(dev->dev_addr))
 		eth_hw_addr_inherit(dev, real_dev);
@@ -3604,21 +3664,19 @@ static int macsec_set_mac_address(struct net_device *dev, void *p)
 	struct macsec_dev *macsec = macsec_priv(dev);
 	struct net_device *real_dev = macsec->real_dev;
 	struct sockaddr *addr = p;
+	u8  old_addr[ETH_ALEN];
 	int err;
 
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
-	if (!(dev->flags & IFF_UP))
-		goto out;
-
-	err = dev_uc_add(real_dev, addr->sa_data);
-	if (err < 0)
-		return err;
-
-	dev_uc_del(real_dev, dev->dev_addr);
+	if (dev->flags & IFF_UP) {
+		err = dev_uc_add(real_dev, addr->sa_data);
+		if (err < 0)
+			return err;
+	}
 
-out:
+	ether_addr_copy(old_addr, dev->dev_addr);
 	eth_hw_addr_set(dev, addr->sa_data);
 
 	/* If h/w offloading is available, propagate to the device */
@@ -3627,13 +3685,29 @@ out:
 		struct macsec_context ctx;
 
 		ops = macsec_get_ops(macsec, &ctx);
-		if (ops) {
-			ctx.secy = &macsec->secy;
-			macsec_offload(ops->mdo_upd_secy, &ctx);
+		if (!ops) {
+			err = -EOPNOTSUPP;
+			goto restore_old_addr;
 		}
+
+		ctx.secy = &macsec->secy;
+		err = macsec_offload(ops->mdo_upd_secy, &ctx);
+		if (err)
+			goto restore_old_addr;
 	}
 
+	if (dev->flags & IFF_UP)
+		dev_uc_del(real_dev, old_addr);
+
 	return 0;
+
+restore_old_addr:
+	if (dev->flags & IFF_UP)
+		dev_uc_del(real_dev, addr->sa_data);
+
+	eth_hw_addr_set(dev, old_addr);
+
+	return err;
 }
 
 static int macsec_change_mtu(struct net_device *dev, int new_mtu)
@@ -4126,6 +4200,9 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
 			err = macsec_offload(ops->mdo_add_secy, &ctx);
 			if (err)
 				goto del_dev;
+
+			macsec->insert_tx_tag =
+				macsec_needs_tx_tag(macsec, ops);
 		}
 	}
 
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 02bd201bc7e5..a3cc665757e8 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -609,6 +609,7 @@ static const struct header_ops macvlan_hard_header_ops = {
 	.parse		= eth_header_parse,
 	.cache		= eth_header_cache,
 	.cache_update	= eth_header_cache_update,
+	.parse_protocol	= eth_header_parse_protocol,
 };
 
 static int macvlan_open(struct net_device *dev)
@@ -780,7 +781,7 @@ static void macvlan_change_rx_flags(struct net_device *dev, int change)
 	if (dev->flags & IFF_UP) {
 		if (change & IFF_ALLMULTI)
 			dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1);
-		if (change & IFF_PROMISC)
+		if (!macvlan_passthru(vlan->port) && change & IFF_PROMISC)
 			dev_set_promiscuity(lowerdev,
 					    dev->flags & IFF_PROMISC ? 1 : -1);
 
@@ -1086,20 +1087,8 @@ static int macvlan_ethtool_get_ts_info(struct net_device *dev,
 				       struct ethtool_ts_info *info)
 {
 	struct net_device *real_dev = macvlan_dev_real_dev(dev);
-	const struct ethtool_ops *ops = real_dev->ethtool_ops;
-	struct phy_device *phydev = real_dev->phydev;
 
-	if (phy_has_tsinfo(phydev)) {
-		return phy_ts_info(phydev, info);
-	} else if (ops->get_ts_info) {
-		return ops->get_ts_info(real_dev, info);
-	} else {
-		info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
-			SOF_TIMESTAMPING_SOFTWARE;
-		info->phc_index = -1;
-	}
-
-	return 0;
+	return ethtool_get_ts_info_by_layer(real_dev, info);
 }
 
 static netdev_features_t macvlan_fix_features(struct net_device *dev,
diff --git a/drivers/net/mdio/mdio-bcm-unimac.c b/drivers/net/mdio/mdio-bcm-unimac.c
index e8cd8eef319b..68f8ee0ec8ba 100644
--- a/drivers/net/mdio/mdio-bcm-unimac.c
+++ b/drivers/net/mdio/mdio-bcm-unimac.c
@@ -73,24 +73,19 @@ static inline void unimac_mdio_start(struct unimac_mdio_priv *priv)
 	unimac_mdio_writel(priv, reg, MDIO_CMD);
 }
 
-static inline unsigned int unimac_mdio_busy(struct unimac_mdio_priv *priv)
-{
-	return unimac_mdio_readl(priv, MDIO_CMD) & MDIO_START_BUSY;
-}
-
 static int unimac_mdio_poll(void *wait_func_data)
 {
 	struct unimac_mdio_priv *priv = wait_func_data;
-	unsigned int timeout = 1000;
+	u32 val;
 
-	do {
-		if (!unimac_mdio_busy(priv))
-			return 0;
-
-		usleep_range(1000, 2000);
-	} while (--timeout);
+	/*
+	 * C22 transactions should take ~25 usec, will need to adjust
+	 * if C45 support is added.
+	 */
+	udelay(30);
 
-	return -ETIMEDOUT;
+	return read_poll_timeout(unimac_mdio_readl, val, !(val & MDIO_START_BUSY),
+				 2000, 100000, false, priv, MDIO_CMD);
 }
 
 static int unimac_mdio_read(struct mii_bus *bus, int phy_id, int reg)
diff --git a/drivers/net/mdio/mdio-gpio.c b/drivers/net/mdio/mdio-gpio.c
index 897b88c50bbb..778db310a28d 100644
--- a/drivers/net/mdio/mdio-gpio.c
+++ b/drivers/net/mdio/mdio-gpio.c
@@ -123,9 +123,9 @@ static struct mii_bus *mdio_gpio_bus_init(struct device *dev,
 	new_bus->parent = dev;
 
 	if (bus_id != -1)
-		snprintf(new_bus->id, MII_BUS_ID_SIZE, "gpio-%x", bus_id);
+		snprintf(new_bus->id, sizeof(new_bus->id), "gpio-%x", bus_id);
 	else
-		strncpy(new_bus->id, "gpio", MII_BUS_ID_SIZE);
+		strscpy(new_bus->id, "gpio", sizeof(new_bus->id));
 
 	if (pdata) {
 		new_bus->phy_mask = pdata->phy_mask;
diff --git a/drivers/net/mdio/mdio-mux-bcm-iproc.c b/drivers/net/mdio/mdio-mux-bcm-iproc.c
index a750bd4c77a0..1ce7d67ba72e 100644
--- a/drivers/net/mdio/mdio-mux-bcm-iproc.c
+++ b/drivers/net/mdio/mdio-mux-bcm-iproc.c
@@ -2,6 +2,7 @@
 /*
  * Copyright 2016 Broadcom
  */
+#include <linux/align.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/device.h>
@@ -11,6 +12,7 @@
 #include <linux/of_mdio.h>
 #include <linux/phy.h>
 #include <linux/platform_device.h>
+#include <linux/sizes.h>
 
 #define MDIO_RATE_ADJ_EXT_OFFSET	0x000
 #define MDIO_RATE_ADJ_INT_OFFSET	0x004
@@ -220,12 +222,12 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev)
 	md->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(md->base))
 		return PTR_ERR(md->base);
-	if (res->start & 0xfff) {
+	if (!IS_ALIGNED(res->start, SZ_4K)) {
 		/* For backward compatibility in case the
 		 * base address is specified with an offset.
 		 */
 		dev_info(&pdev->dev, "fix base address in dt-blob\n");
-		res->start &= ~0xfff;
+		res->start = ALIGN_DOWN(res->start, SZ_4K);
 		res->end = res->start + MDIO_REG_ADDR_SPACE_SIZE - 1;
 	}
 
diff --git a/drivers/net/mdio/mdio-mux.c b/drivers/net/mdio/mdio-mux.c
index bef4cce71287..fe0e46bd7964 100644
--- a/drivers/net/mdio/mdio-mux.c
+++ b/drivers/net/mdio/mdio-mux.c
@@ -190,8 +190,8 @@ int mdio_mux_init(struct device *dev,
 		r = of_property_read_u32(child_bus_node, "reg", &v);
 		if (r) {
 			dev_err(dev,
-				"Error: Failed to find reg for child %pOF\n",
-				child_bus_node);
+				"Error: Failed to find reg for child %pOF: %pe\n",
+				child_bus_node, ERR_PTR(r));
 			continue;
 		}
 
@@ -214,8 +214,10 @@ int mdio_mux_init(struct device *dev,
 		snprintf(cb->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x.%x",
 			 cb->mii_bus->name, pb->parent_id, v);
 		cb->mii_bus->parent = dev;
-		cb->mii_bus->read = mdio_mux_read;
-		cb->mii_bus->write = mdio_mux_write;
+		if (parent_bus->read)
+			cb->mii_bus->read = mdio_mux_read;
+		if (parent_bus->write)
+			cb->mii_bus->write = mdio_mux_write;
 		if (parent_bus->read_c45)
 			cb->mii_bus->read_c45 = mdio_mux_read_c45;
 		if (parent_bus->write_c45)
@@ -229,8 +231,8 @@ int mdio_mux_init(struct device *dev,
 			}
 			devm_kfree(dev, cb);
 			dev_err(dev,
-				"Error: Failed to register MDIO bus for child %pOF\n",
-				child_bus_node);
+				"Error: Failed to register MDIO bus for child %pOF: %pe\n",
+				child_bus_node, ERR_PTR(r));
 		} else {
 			cb->next = pb->children;
 			pb->children = cb;
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index f60eb97e3a62..608953d4f98d 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -93,7 +93,7 @@ static void nsim_prog_set_loaded(struct bpf_prog *prog, bool loaded)
 {
 	struct nsim_bpf_bound_prog *state;
 
-	if (!prog || !prog->aux->offload)
+	if (!prog || !bpf_prog_is_offloaded(prog->aux))
 		return;
 
 	state = prog->aux->offload->dev_priv;
@@ -311,7 +311,7 @@ nsim_setup_prog_hw_checks(struct netdevsim *ns, struct netdev_bpf *bpf)
 	if (!bpf->prog)
 		return 0;
 
-	if (!bpf->prog->aux->offload) {
+	if (!bpf_prog_is_offloaded(bpf->prog->aux)) {
 		NSIM_EA(bpf->extack, "xdpoffload of non-bound program");
 		return -EINVAL;
 	}
diff --git a/drivers/net/netdevsim/macsec.c b/drivers/net/netdevsim/macsec.c
index 0d5f50430dd3..aa007b1e4b78 100644
--- a/drivers/net/netdevsim/macsec.c
+++ b/drivers/net/netdevsim/macsec.c
@@ -3,11 +3,6 @@
 #include <net/macsec.h>
 #include "netdevsim.h"
 
-static inline u64 sci_to_cpu(sci_t sci)
-{
-	return be64_to_cpu((__force __be64)sci);
-}
-
 static int nsim_macsec_find_secy(struct netdevsim *ns, sci_t sci)
 {
 	int i;
diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c
index 5a0f86f38f09..39171380ccf2 100644
--- a/drivers/net/netkit.c
+++ b/drivers/net/netkit.c
@@ -7,6 +7,7 @@
 #include <linux/filter.h>
 #include <linux/netfilter_netdev.h>
 #include <linux/bpf_mprog.h>
+#include <linux/indirect_call_wrapper.h>
 
 #include <net/netkit.h>
 #include <net/dst.h>
@@ -68,6 +69,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev)
 	netdev_tx_t ret_dev = NET_XMIT_SUCCESS;
 	const struct bpf_mprog_entry *entry;
 	struct net_device *peer;
+	int len = skb->len;
 
 	rcu_read_lock();
 	peer = rcu_dereference(nk->peer);
@@ -85,15 +87,22 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev)
 	case NETKIT_PASS:
 		skb->protocol = eth_type_trans(skb, skb->dev);
 		skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
-		__netif_rx(skb);
+		if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) {
+			dev_sw_netstats_tx_add(dev, 1, len);
+			dev_sw_netstats_rx_add(peer, len);
+		} else {
+			goto drop_stats;
+		}
 		break;
 	case NETKIT_REDIRECT:
+		dev_sw_netstats_tx_add(dev, 1, len);
 		skb_do_redirect(skb);
 		break;
 	case NETKIT_DROP:
 	default:
 drop:
 		kfree_skb(skb);
+drop_stats:
 		dev_core_stats_tx_dropped_inc(dev);
 		ret_dev = NET_XMIT_DROP;
 		break;
@@ -169,11 +178,18 @@ out:
 	rcu_read_unlock();
 }
 
-static struct net_device *netkit_peer_dev(struct net_device *dev)
+INDIRECT_CALLABLE_SCOPE struct net_device *netkit_peer_dev(struct net_device *dev)
 {
 	return rcu_dereference(netkit_priv(dev)->peer);
 }
 
+static void netkit_get_stats(struct net_device *dev,
+			     struct rtnl_link_stats64 *stats)
+{
+	dev_fetch_sw_netstats(stats, dev->tstats);
+	stats->tx_dropped = DEV_STATS_READ(dev, tx_dropped);
+}
+
 static void netkit_uninit(struct net_device *dev);
 
 static const struct net_device_ops netkit_netdev_ops = {
@@ -184,6 +200,7 @@ static const struct net_device_ops netkit_netdev_ops = {
 	.ndo_set_rx_headroom	= netkit_set_headroom,
 	.ndo_get_iflink		= netkit_get_iflink,
 	.ndo_get_peer_dev	= netkit_peer_dev,
+	.ndo_get_stats64	= netkit_get_stats,
 	.ndo_uninit		= netkit_uninit,
 	.ndo_features_check	= passthru_features_check,
 };
@@ -218,6 +235,7 @@ static void netkit_setup(struct net_device *dev)
 
 	ether_setup(dev);
 	dev->max_mtu = ETH_MAX_MTU;
+	dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
 
 	dev->flags |= IFF_NOARP;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
@@ -833,6 +851,12 @@ static int netkit_change_link(struct net_device *dev, struct nlattr *tb[],
 		return -EACCES;
 	}
 
+	if (data[IFLA_NETKIT_PEER_INFO]) {
+		NL_SET_ERR_MSG_ATTR(extack, data[IFLA_NETKIT_PEER_INFO],
+				    "netkit peer info cannot be changed after device creation");
+		return -EINVAL;
+	}
+
 	if (data[IFLA_NETKIT_POLICY]) {
 		attr = data[IFLA_NETKIT_POLICY];
 		policy = nla_get_u32(attr);
diff --git a/drivers/net/pcs/pcs-rzn1-miic.c b/drivers/net/pcs/pcs-rzn1-miic.c
index 97139c07130f..d93f84fbb1fd 100644
--- a/drivers/net/pcs/pcs-rzn1-miic.c
+++ b/drivers/net/pcs/pcs-rzn1-miic.c
@@ -505,11 +505,9 @@ disable_runtime_pm:
 	return ret;
 }
 
-static int miic_remove(struct platform_device *pdev)
+static void miic_remove(struct platform_device *pdev)
 {
 	pm_runtime_put(&pdev->dev);
-
-	return 0;
 }
 
 static const struct of_device_id miic_of_mtable[] = {
@@ -525,7 +523,7 @@ static struct platform_driver miic_driver = {
 		.of_match_table = miic_of_mtable,
 	},
 	.probe = miic_probe,
-	.remove = miic_remove,
+	.remove_new = miic_remove,
 };
 module_platform_driver(miic_driver);
 
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 421d2b62918f..9e2672800f0b 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -60,6 +60,14 @@ config FIXED_PHY
 
 	  Currently tested with mpc866ads and mpc8349e-mitx.
 
+config RUST_PHYLIB_ABSTRACTIONS
+        bool "Rust PHYLIB abstractions support"
+        depends on RUST
+        depends on PHYLIB=y
+        help
+          Adds support needed for PHY drivers written in Rust. It provides
+          a wrapper around the C phylib core.
+
 config SFP
 	tristate "SFP cage support"
 	depends on I2C && PHYLINK
@@ -96,10 +104,7 @@ config ADIN1100_PHY
 	  Currently supports the:
 	  - ADIN1100 - Robust,Industrial, Low Power 10BASE-T1L Ethernet PHY
 
-config AQUANTIA_PHY
-	tristate "Aquantia PHYs"
-	help
-	  Currently supports the Aquantia AQ1202, AQ2104, AQR105, AQR405
+source "drivers/net/phy/aquantia/Kconfig"
 
 config AX88796B_PHY
 	tristate "Asix PHYs"
@@ -107,6 +112,14 @@ config AX88796B_PHY
 	  Currently supports the Asix Electronics PHY found in the X-Surf 100
 	  AX88796B package.
 
+config AX88796B_RUST_PHY
+	bool "Rust reference driver for Asix PHYs"
+	depends on RUST_PHYLIB_ABSTRACTIONS && AX88796B_PHY
+	help
+	  Uses the Rust reference driver for Asix PHYs (ax88796b_rust.ko).
+	  The features are equivalent. It supports the Asix Electronics PHY
+	  found in the X-Surf 100 AX88796B package.
+
 config BROADCOM_PHY
 	tristate "Broadcom 54XX PHYs"
 	select BCM_NET_PHYLIB
@@ -304,9 +317,10 @@ config NXP_CBTX_PHY
 config NXP_C45_TJA11XX_PHY
 	tristate "NXP C45 TJA11XX PHYs"
 	depends on PTP_1588_CLOCK_OPTIONAL
+	depends on MACSEC || !MACSEC
 	help
 	  Enable support for NXP C45 TJA11XX PHYs.
-	  Currently supports the TJA1103 and TJA1120 PHYs.
+	  Currently supports the TJA1103, TJA1104 and TJA1120 PHYs.
 
 config NXP_TJA11XX_PHY
 	tristate "NXP TJA11xx PHYs support"
@@ -397,6 +411,19 @@ config DP83TD510_PHY
 	  Support for the DP83TD510 Ethernet 10Base-T1L PHY. This PHY supports
 	  a 10M single pair Ethernet connection for up to 1000 meter cable.
 
+config DP83TG720_PHY
+	tristate "Texas Instruments DP83TG720 Ethernet 1000Base-T1 PHY"
+	help
+	  The DP83TG720S-Q1 is an automotive Ethernet physical layer
+	  transceiver compliant with IEEE 802.3bp and Open Alliance
+	  standards. It supports key functions necessary for
+	  transmitting and receiving data over both unshielded and
+	  shielded single twisted-pair cables. This device offers
+	  flexible xMII interface options, including support for both
+	  RGMII and SGMII MAC interfaces. It's suitable for applications
+	  requiring high-speed data transmission in automotive
+	  networking environments.
+
 config VITESSE_PHY
 	tristate "Vitesse PHYs"
 	help
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index c945ed9bd14b..6097afd44392 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -35,13 +35,13 @@ obj-y				+= $(sfp-obj-y) $(sfp-obj-m)
 obj-$(CONFIG_ADIN_PHY)		+= adin.o
 obj-$(CONFIG_ADIN1100_PHY)	+= adin1100.o
 obj-$(CONFIG_AMD_PHY)		+= amd.o
-aquantia-objs			+= aquantia_main.o
-ifdef CONFIG_HWMON
-aquantia-objs			+= aquantia_hwmon.o
-endif
-obj-$(CONFIG_AQUANTIA_PHY)	+= aquantia.o
+obj-$(CONFIG_AQUANTIA_PHY)	+= aquantia/
 obj-$(CONFIG_AT803X_PHY)	+= at803x.o
-obj-$(CONFIG_AX88796B_PHY)	+= ax88796b.o
+ifdef CONFIG_AX88796B_RUST_PHY
+  obj-$(CONFIG_AX88796B_PHY)	+= ax88796b_rust.o
+else
+  obj-$(CONFIG_AX88796B_PHY)	+= ax88796b.o
+endif
 obj-$(CONFIG_BCM54140_PHY)	+= bcm54140.o
 obj-$(CONFIG_BCM63XX_PHY)	+= bcm63xx.o
 obj-$(CONFIG_BCM7XXX_PHY)	+= bcm7xxx.o
@@ -61,6 +61,7 @@ obj-$(CONFIG_DP83867_PHY)	+= dp83867.o
 obj-$(CONFIG_DP83869_PHY)	+= dp83869.o
 obj-$(CONFIG_DP83TC811_PHY)	+= dp83tc811.o
 obj-$(CONFIG_DP83TD510_PHY)	+= dp83td510.o
+obj-$(CONFIG_DP83TG720_PHY)	+= dp83tg720.o
 obj-$(CONFIG_FIXED_PHY)		+= fixed_phy.o
 obj-$(CONFIG_ICPLUS_PHY)	+= icplus.o
 obj-$(CONFIG_INTEL_XWAY_PHY)	+= intel-xway.o
@@ -83,7 +84,11 @@ obj-$(CONFIG_MICROSEMI_PHY)	+= mscc/
 obj-$(CONFIG_MOTORCOMM_PHY)	+= motorcomm.o
 obj-$(CONFIG_NATIONAL_PHY)	+= national.o
 obj-$(CONFIG_NCN26000_PHY)	+= ncn26000.o
-obj-$(CONFIG_NXP_C45_TJA11XX_PHY)	+= nxp-c45-tja11xx.o
+nxp-c45-tja-objs		+= nxp-c45-tja11xx.o
+ifdef CONFIG_MACSEC
+nxp-c45-tja-objs		+= nxp-c45-tja11xx-macsec.o
+endif
+obj-$(CONFIG_NXP_C45_TJA11XX_PHY)	+= nxp-c45-tja.o
 obj-$(CONFIG_NXP_CBTX_PHY)	+= nxp-cbtx.o
 obj-$(CONFIG_NXP_TJA11XX_PHY)	+= nxp-tja11xx.o
 obj-$(CONFIG_QSEMI_PHY)		+= qsemi.o
diff --git a/drivers/net/phy/adin.c b/drivers/net/phy/adin.c
index 134637584a83..2e1a46e121d9 100644
--- a/drivers/net/phy/adin.c
+++ b/drivers/net/phy/adin.c
@@ -68,6 +68,24 @@
 #define ADIN1300_EEE_CAP_REG			0x8000
 #define ADIN1300_EEE_ADV_REG			0x8001
 #define ADIN1300_EEE_LPABLE_REG			0x8002
+
+#define ADIN1300_FLD_EN_REG			0x8E27
+#define   ADIN1300_FLD_PCS_ERR_100_EN		BIT(7)
+#define   ADIN1300_FLD_PCS_ERR_1000_EN		BIT(6)
+#define   ADIN1300_FLD_SLCR_OUT_STUCK_100_EN	BIT(5)
+#define   ADIN1300_FLD_SLCR_OUT_STUCK_1000_EN	BIT(4)
+#define   ADIN1300_FLD_SLCR_IN_ZDET_100_EN	BIT(3)
+#define   ADIN1300_FLD_SLCR_IN_ZDET_1000_EN	BIT(2)
+#define   ADIN1300_FLD_SLCR_IN_INVLD_100_EN	BIT(1)
+#define   ADIN1300_FLD_SLCR_IN_INVLD_1000_EN	BIT(0)
+/* These bits are the ones which are enabled by default. */
+#define ADIN1300_FLD_EN_ON	\
+	(ADIN1300_FLD_SLCR_OUT_STUCK_100_EN | \
+	 ADIN1300_FLD_SLCR_OUT_STUCK_1000_EN | \
+	 ADIN1300_FLD_SLCR_IN_ZDET_100_EN | \
+	 ADIN1300_FLD_SLCR_IN_ZDET_1000_EN | \
+	 ADIN1300_FLD_SLCR_IN_INVLD_1000_EN)
+
 #define ADIN1300_CLOCK_STOP_REG			0x9400
 #define ADIN1300_LPI_WAKE_ERR_CNT_REG		0xa000
 
@@ -416,6 +434,37 @@ static int adin_set_edpd(struct phy_device *phydev, u16 tx_interval)
 			  val);
 }
 
+static int adin_get_fast_down(struct phy_device *phydev, u8 *msecs)
+{
+	int reg;
+
+	reg = phy_read_mmd(phydev, MDIO_MMD_VEND1, ADIN1300_FLD_EN_REG);
+	if (reg < 0)
+		return reg;
+
+	if (reg & ADIN1300_FLD_EN_ON)
+		*msecs = ETHTOOL_PHY_FAST_LINK_DOWN_ON;
+	else
+		*msecs = ETHTOOL_PHY_FAST_LINK_DOWN_OFF;
+
+	return 0;
+}
+
+static int adin_set_fast_down(struct phy_device *phydev, const u8 *msecs)
+{
+	if (*msecs == ETHTOOL_PHY_FAST_LINK_DOWN_ON)
+		return phy_set_bits_mmd(phydev, MDIO_MMD_VEND1,
+					ADIN1300_FLD_EN_REG,
+					ADIN1300_FLD_EN_ON);
+
+	if (*msecs == ETHTOOL_PHY_FAST_LINK_DOWN_OFF)
+		return phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
+					  ADIN1300_FLD_EN_REG,
+					  ADIN1300_FLD_EN_ON);
+
+	return -EINVAL;
+}
+
 static int adin_get_tunable(struct phy_device *phydev,
 			    struct ethtool_tunable *tuna, void *data)
 {
@@ -424,6 +473,8 @@ static int adin_get_tunable(struct phy_device *phydev,
 		return adin_get_downshift(phydev, data);
 	case ETHTOOL_PHY_EDPD:
 		return adin_get_edpd(phydev, data);
+	case ETHTOOL_PHY_FAST_LINK_DOWN:
+		return adin_get_fast_down(phydev, data);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -437,6 +488,8 @@ static int adin_set_tunable(struct phy_device *phydev,
 		return adin_set_downshift(phydev, *(const u8 *)data);
 	case ETHTOOL_PHY_EDPD:
 		return adin_set_edpd(phydev, *(const u16 *)data);
+	case ETHTOOL_PHY_FAST_LINK_DOWN:
+		return adin_set_fast_down(phydev, data);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/phy/aquantia.h b/drivers/net/phy/aquantia.h
deleted file mode 100644
index c684b65c642c..000000000000
--- a/drivers/net/phy/aquantia.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* HWMON driver for Aquantia PHY
- *
- * Author: Nikita Yushchenko <nikita.yoush@cogentembedded.com>
- * Author: Andrew Lunn <andrew@lunn.ch>
- * Author: Heiner Kallweit <hkallweit1@gmail.com>
- */
-
-#include <linux/device.h>
-#include <linux/phy.h>
-
-#if IS_REACHABLE(CONFIG_HWMON)
-int aqr_hwmon_probe(struct phy_device *phydev);
-#else
-static inline int aqr_hwmon_probe(struct phy_device *phydev) { return 0; }
-#endif
diff --git a/drivers/net/phy/aquantia/Kconfig b/drivers/net/phy/aquantia/Kconfig
new file mode 100644
index 000000000000..1a65678583cf
--- /dev/null
+++ b/drivers/net/phy/aquantia/Kconfig
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config AQUANTIA_PHY
+	tristate "Aquantia PHYs"
+	select CRC_ITU_T
+	help
+	  Currently supports the Aquantia AQ1202, AQ2104, AQR105, AQR405
diff --git a/drivers/net/phy/aquantia/Makefile b/drivers/net/phy/aquantia/Makefile
new file mode 100644
index 000000000000..aa77fb63c8ec
--- /dev/null
+++ b/drivers/net/phy/aquantia/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+aquantia-objs			+= aquantia_main.o aquantia_firmware.o
+ifdef CONFIG_HWMON
+aquantia-objs			+= aquantia_hwmon.o
+endif
+obj-$(CONFIG_AQUANTIA_PHY)	+= aquantia.o
diff --git a/drivers/net/phy/aquantia/aquantia.h b/drivers/net/phy/aquantia/aquantia.h
new file mode 100644
index 000000000000..1c19ae74ad2b
--- /dev/null
+++ b/drivers/net/phy/aquantia/aquantia.h
@@ -0,0 +1,122 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* HWMON driver for Aquantia PHY
+ *
+ * Author: Nikita Yushchenko <nikita.yoush@cogentembedded.com>
+ * Author: Andrew Lunn <andrew@lunn.ch>
+ * Author: Heiner Kallweit <hkallweit1@gmail.com>
+ */
+
+#include <linux/device.h>
+#include <linux/phy.h>
+
+/* Vendor specific 1, MDIO_MMD_VEND1 */
+#define VEND1_GLOBAL_SC				0x0
+#define VEND1_GLOBAL_SC_SOFT_RESET		BIT(15)
+#define VEND1_GLOBAL_SC_LOW_POWER		BIT(11)
+
+#define VEND1_GLOBAL_FW_ID			0x0020
+#define VEND1_GLOBAL_FW_ID_MAJOR		GENMASK(15, 8)
+#define VEND1_GLOBAL_FW_ID_MINOR		GENMASK(7, 0)
+
+#define VEND1_GLOBAL_MAILBOX_INTERFACE1			0x0200
+#define VEND1_GLOBAL_MAILBOX_INTERFACE1_EXECUTE		BIT(15)
+#define VEND1_GLOBAL_MAILBOX_INTERFACE1_WRITE		BIT(14)
+#define VEND1_GLOBAL_MAILBOX_INTERFACE1_CRC_RESET	BIT(12)
+#define VEND1_GLOBAL_MAILBOX_INTERFACE1_BUSY		BIT(8)
+
+#define VEND1_GLOBAL_MAILBOX_INTERFACE2			0x0201
+#define VEND1_GLOBAL_MAILBOX_INTERFACE3			0x0202
+#define VEND1_GLOBAL_MAILBOX_INTERFACE3_MSW_ADDR_MASK	GENMASK(15, 0)
+#define VEND1_GLOBAL_MAILBOX_INTERFACE3_MSW_ADDR(x)	FIELD_PREP(VEND1_GLOBAL_MAILBOX_INTERFACE3_MSW_ADDR_MASK, (u16)((x) >> 16))
+#define VEND1_GLOBAL_MAILBOX_INTERFACE4			0x0203
+#define VEND1_GLOBAL_MAILBOX_INTERFACE4_LSW_ADDR_MASK	GENMASK(15, 2)
+#define VEND1_GLOBAL_MAILBOX_INTERFACE4_LSW_ADDR(x)	FIELD_PREP(VEND1_GLOBAL_MAILBOX_INTERFACE4_LSW_ADDR_MASK, (u16)(x))
+
+#define VEND1_GLOBAL_MAILBOX_INTERFACE5			0x0204
+#define VEND1_GLOBAL_MAILBOX_INTERFACE5_MSW_DATA_MASK	GENMASK(15, 0)
+#define VEND1_GLOBAL_MAILBOX_INTERFACE5_MSW_DATA(x)	FIELD_PREP(VEND1_GLOBAL_MAILBOX_INTERFACE5_MSW_DATA_MASK, (u16)((x) >> 16))
+#define VEND1_GLOBAL_MAILBOX_INTERFACE6			0x0205
+#define VEND1_GLOBAL_MAILBOX_INTERFACE6_LSW_DATA_MASK	GENMASK(15, 0)
+#define VEND1_GLOBAL_MAILBOX_INTERFACE6_LSW_DATA(x)	FIELD_PREP(VEND1_GLOBAL_MAILBOX_INTERFACE6_LSW_DATA_MASK, (u16)(x))
+
+/* The following registers all have similar layouts; first the registers... */
+#define VEND1_GLOBAL_CFG_10M			0x0310
+#define VEND1_GLOBAL_CFG_100M			0x031b
+#define VEND1_GLOBAL_CFG_1G			0x031c
+#define VEND1_GLOBAL_CFG_2_5G			0x031d
+#define VEND1_GLOBAL_CFG_5G			0x031e
+#define VEND1_GLOBAL_CFG_10G			0x031f
+/* ...and now the fields */
+#define VEND1_GLOBAL_CFG_SERDES_MODE		GENMASK(2, 0)
+#define VEND1_GLOBAL_CFG_SERDES_MODE_XFI	0
+#define VEND1_GLOBAL_CFG_SERDES_MODE_SGMII	3
+#define VEND1_GLOBAL_CFG_SERDES_MODE_OCSGMII	4
+#define VEND1_GLOBAL_CFG_SERDES_MODE_XFI5G	6
+#define VEND1_GLOBAL_CFG_RATE_ADAPT		GENMASK(8, 7)
+#define VEND1_GLOBAL_CFG_RATE_ADAPT_NONE	0
+#define VEND1_GLOBAL_CFG_RATE_ADAPT_USX		1
+#define VEND1_GLOBAL_CFG_RATE_ADAPT_PAUSE	2
+
+/* Vendor specific 1, MDIO_MMD_VEND2 */
+#define VEND1_GLOBAL_CONTROL2			0xc001
+#define VEND1_GLOBAL_CONTROL2_UP_RUN_STALL_RST	BIT(15)
+#define VEND1_GLOBAL_CONTROL2_UP_RUN_STALL_OVD	BIT(6)
+#define VEND1_GLOBAL_CONTROL2_UP_RUN_STALL	BIT(0)
+
+#define VEND1_THERMAL_PROV_HIGH_TEMP_FAIL	0xc421
+#define VEND1_THERMAL_PROV_LOW_TEMP_FAIL	0xc422
+#define VEND1_THERMAL_PROV_HIGH_TEMP_WARN	0xc423
+#define VEND1_THERMAL_PROV_LOW_TEMP_WARN	0xc424
+#define VEND1_THERMAL_STAT1			0xc820
+#define VEND1_THERMAL_STAT2			0xc821
+#define VEND1_THERMAL_STAT2_VALID		BIT(0)
+#define VEND1_GENERAL_STAT1			0xc830
+#define VEND1_GENERAL_STAT1_HIGH_TEMP_FAIL	BIT(14)
+#define VEND1_GENERAL_STAT1_LOW_TEMP_FAIL	BIT(13)
+#define VEND1_GENERAL_STAT1_HIGH_TEMP_WARN	BIT(12)
+#define VEND1_GENERAL_STAT1_LOW_TEMP_WARN	BIT(11)
+
+#define VEND1_GLOBAL_GEN_STAT2			0xc831
+#define VEND1_GLOBAL_GEN_STAT2_OP_IN_PROG	BIT(15)
+
+#define VEND1_GLOBAL_RSVD_STAT1			0xc885
+#define VEND1_GLOBAL_RSVD_STAT1_FW_BUILD_ID	GENMASK(7, 4)
+#define VEND1_GLOBAL_RSVD_STAT1_PROV_ID		GENMASK(3, 0)
+
+#define VEND1_GLOBAL_RSVD_STAT9			0xc88d
+#define VEND1_GLOBAL_RSVD_STAT9_MODE		GENMASK(7, 0)
+#define VEND1_GLOBAL_RSVD_STAT9_1000BT2		0x23
+
+#define VEND1_GLOBAL_INT_STD_STATUS		0xfc00
+#define VEND1_GLOBAL_INT_VEND_STATUS		0xfc01
+
+#define VEND1_GLOBAL_INT_STD_MASK		0xff00
+#define VEND1_GLOBAL_INT_STD_MASK_PMA1		BIT(15)
+#define VEND1_GLOBAL_INT_STD_MASK_PMA2		BIT(14)
+#define VEND1_GLOBAL_INT_STD_MASK_PCS1		BIT(13)
+#define VEND1_GLOBAL_INT_STD_MASK_PCS2		BIT(12)
+#define VEND1_GLOBAL_INT_STD_MASK_PCS3		BIT(11)
+#define VEND1_GLOBAL_INT_STD_MASK_PHY_XS1	BIT(10)
+#define VEND1_GLOBAL_INT_STD_MASK_PHY_XS2	BIT(9)
+#define VEND1_GLOBAL_INT_STD_MASK_AN1		BIT(8)
+#define VEND1_GLOBAL_INT_STD_MASK_AN2		BIT(7)
+#define VEND1_GLOBAL_INT_STD_MASK_GBE		BIT(6)
+#define VEND1_GLOBAL_INT_STD_MASK_ALL		BIT(0)
+
+#define VEND1_GLOBAL_INT_VEND_MASK		0xff01
+#define VEND1_GLOBAL_INT_VEND_MASK_PMA		BIT(15)
+#define VEND1_GLOBAL_INT_VEND_MASK_PCS		BIT(14)
+#define VEND1_GLOBAL_INT_VEND_MASK_PHY_XS	BIT(13)
+#define VEND1_GLOBAL_INT_VEND_MASK_AN		BIT(12)
+#define VEND1_GLOBAL_INT_VEND_MASK_GBE		BIT(11)
+#define VEND1_GLOBAL_INT_VEND_MASK_GLOBAL1	BIT(2)
+#define VEND1_GLOBAL_INT_VEND_MASK_GLOBAL2	BIT(1)
+#define VEND1_GLOBAL_INT_VEND_MASK_GLOBAL3	BIT(0)
+
+#if IS_REACHABLE(CONFIG_HWMON)
+int aqr_hwmon_probe(struct phy_device *phydev);
+#else
+static inline int aqr_hwmon_probe(struct phy_device *phydev) { return 0; }
+#endif
+
+int aqr_firmware_load(struct phy_device *phydev);
diff --git a/drivers/net/phy/aquantia/aquantia_firmware.c b/drivers/net/phy/aquantia/aquantia_firmware.c
new file mode 100644
index 000000000000..0c9640ef153b
--- /dev/null
+++ b/drivers/net/phy/aquantia/aquantia_firmware.c
@@ -0,0 +1,374 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bitfield.h>
+#include <linux/of.h>
+#include <linux/firmware.h>
+#include <linux/crc-itu-t.h>
+#include <linux/nvmem-consumer.h>
+
+#include <asm/unaligned.h>
+
+#include "aquantia.h"
+
+#define UP_RESET_SLEEP		100
+
+/* addresses of memory segments in the phy */
+#define DRAM_BASE_ADDR		0x3FFE0000
+#define IRAM_BASE_ADDR		0x40000000
+
+/* firmware image format constants */
+#define VERSION_STRING_SIZE		0x40
+#define VERSION_STRING_OFFSET		0x0200
+/* primary offset is written at an offset from the start of the fw blob */
+#define PRIMARY_OFFSET_OFFSET		0x8
+/* primary offset needs to be then added to a base offset */
+#define PRIMARY_OFFSET_SHIFT		12
+#define PRIMARY_OFFSET(x)		((x) << PRIMARY_OFFSET_SHIFT)
+#define HEADER_OFFSET			0x300
+
+struct aqr_fw_header {
+	u32 padding;
+	u8 iram_offset[3];
+	u8 iram_size[3];
+	u8 dram_offset[3];
+	u8 dram_size[3];
+} __packed;
+
+enum aqr_fw_src {
+	AQR_FW_SRC_NVMEM = 0,
+	AQR_FW_SRC_FS,
+};
+
+static const char * const aqr_fw_src_string[] = {
+	[AQR_FW_SRC_NVMEM] = "NVMEM",
+	[AQR_FW_SRC_FS] = "FS",
+};
+
+/* AQR firmware doesn't have fixed offsets for iram and dram section
+ * but instead provide an header with the offset to use on reading
+ * and parsing the firmware.
+ *
+ * AQR firmware can't be trusted and each offset is validated to be
+ * not negative and be in the size of the firmware itself.
+ */
+static bool aqr_fw_validate_get(size_t size, size_t offset, size_t get_size)
+{
+	return offset + get_size <= size;
+}
+
+static int aqr_fw_get_be16(const u8 *data, size_t offset, size_t size, u16 *value)
+{
+	if (!aqr_fw_validate_get(size, offset, sizeof(u16)))
+		return -EINVAL;
+
+	*value = get_unaligned_be16(data + offset);
+
+	return 0;
+}
+
+static int aqr_fw_get_le16(const u8 *data, size_t offset, size_t size, u16 *value)
+{
+	if (!aqr_fw_validate_get(size, offset, sizeof(u16)))
+		return -EINVAL;
+
+	*value = get_unaligned_le16(data + offset);
+
+	return 0;
+}
+
+static int aqr_fw_get_le24(const u8 *data, size_t offset, size_t size, u32 *value)
+{
+	if (!aqr_fw_validate_get(size, offset, sizeof(u8) * 3))
+		return -EINVAL;
+
+	*value = get_unaligned_le24(data + offset);
+
+	return 0;
+}
+
+/* load data into the phy's memory */
+static int aqr_fw_load_memory(struct phy_device *phydev, u32 addr,
+			      const u8 *data, size_t len)
+{
+	u16 crc = 0, up_crc;
+	size_t pos;
+
+	phy_write_mmd(phydev, MDIO_MMD_VEND1,
+		      VEND1_GLOBAL_MAILBOX_INTERFACE1,
+		      VEND1_GLOBAL_MAILBOX_INTERFACE1_CRC_RESET);
+	phy_write_mmd(phydev, MDIO_MMD_VEND1,
+		      VEND1_GLOBAL_MAILBOX_INTERFACE3,
+		      VEND1_GLOBAL_MAILBOX_INTERFACE3_MSW_ADDR(addr));
+	phy_write_mmd(phydev, MDIO_MMD_VEND1,
+		      VEND1_GLOBAL_MAILBOX_INTERFACE4,
+		      VEND1_GLOBAL_MAILBOX_INTERFACE4_LSW_ADDR(addr));
+
+	/* We assume and enforce the size to be word aligned.
+	 * If a firmware that is not word aligned is found, please report upstream.
+	 */
+	for (pos = 0; pos < len; pos += sizeof(u32)) {
+		u8 crc_data[4];
+		u32 word;
+
+		/* FW data is always stored in little-endian */
+		word = get_unaligned_le32((const u32 *)(data + pos));
+
+		phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_GLOBAL_MAILBOX_INTERFACE5,
+			      VEND1_GLOBAL_MAILBOX_INTERFACE5_MSW_DATA(word));
+		phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_GLOBAL_MAILBOX_INTERFACE6,
+			      VEND1_GLOBAL_MAILBOX_INTERFACE6_LSW_DATA(word));
+
+		phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_GLOBAL_MAILBOX_INTERFACE1,
+			      VEND1_GLOBAL_MAILBOX_INTERFACE1_EXECUTE |
+			      VEND1_GLOBAL_MAILBOX_INTERFACE1_WRITE);
+
+		/* Word is swapped internally and MAILBOX CRC is calculated
+		 * using big-endian order. Mimic what the PHY does to have a
+		 * matching CRC...
+		 */
+		crc_data[0] = word >> 24;
+		crc_data[1] = word >> 16;
+		crc_data[2] = word >> 8;
+		crc_data[3] = word;
+
+		/* ...calculate CRC as we load data... */
+		crc = crc_itu_t(crc, crc_data, sizeof(crc_data));
+	}
+	/* ...gets CRC from MAILBOX after we have loaded the entire section... */
+	up_crc = phy_read_mmd(phydev, MDIO_MMD_VEND1, VEND1_GLOBAL_MAILBOX_INTERFACE2);
+	/* ...and make sure it does match our calculated CRC */
+	if (crc != up_crc) {
+		phydev_err(phydev, "CRC mismatch: calculated 0x%04x PHY 0x%04x\n",
+			   crc, up_crc);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int aqr_fw_boot(struct phy_device *phydev, const u8 *data, size_t size,
+		       enum aqr_fw_src fw_src)
+{
+	u16 calculated_crc, read_crc, read_primary_offset;
+	u32 iram_offset = 0, iram_size = 0;
+	u32 dram_offset = 0, dram_size = 0;
+	char version[VERSION_STRING_SIZE];
+	u32 primary_offset = 0;
+	int ret;
+
+	/* extract saved CRC at the end of the fw
+	 * CRC is saved in big-endian as PHY is BE
+	 */
+	ret = aqr_fw_get_be16(data, size - sizeof(u16), size, &read_crc);
+	if (ret) {
+		phydev_err(phydev, "bad firmware CRC in firmware\n");
+		return ret;
+	}
+	calculated_crc = crc_itu_t(0, data, size - sizeof(u16));
+	if (read_crc != calculated_crc) {
+		phydev_err(phydev, "bad firmware CRC: file 0x%04x calculated 0x%04x\n",
+			   read_crc, calculated_crc);
+		return -EINVAL;
+	}
+
+	/* Get the primary offset to extract DRAM and IRAM sections. */
+	ret = aqr_fw_get_le16(data, PRIMARY_OFFSET_OFFSET, size, &read_primary_offset);
+	if (ret) {
+		phydev_err(phydev, "bad primary offset in firmware\n");
+		return ret;
+	}
+	primary_offset = PRIMARY_OFFSET(read_primary_offset);
+
+	/* Find the DRAM and IRAM sections within the firmware file.
+	 * Make sure the fw_header is correctly in the firmware.
+	 */
+	if (!aqr_fw_validate_get(size, primary_offset + HEADER_OFFSET,
+				 sizeof(struct aqr_fw_header))) {
+		phydev_err(phydev, "bad fw_header in firmware\n");
+		return -EINVAL;
+	}
+
+	/* offset are in LE and values needs to be converted to cpu endian */
+	ret = aqr_fw_get_le24(data, primary_offset + HEADER_OFFSET +
+			      offsetof(struct aqr_fw_header, iram_offset),
+			      size, &iram_offset);
+	if (ret) {
+		phydev_err(phydev, "bad iram offset in firmware\n");
+		return ret;
+	}
+	ret = aqr_fw_get_le24(data, primary_offset + HEADER_OFFSET +
+			      offsetof(struct aqr_fw_header, iram_size),
+			      size, &iram_size);
+	if (ret) {
+		phydev_err(phydev, "invalid iram size in firmware\n");
+		return ret;
+	}
+	ret = aqr_fw_get_le24(data, primary_offset + HEADER_OFFSET +
+			      offsetof(struct aqr_fw_header, dram_offset),
+			      size, &dram_offset);
+	if (ret) {
+		phydev_err(phydev, "bad dram offset in firmware\n");
+		return ret;
+	}
+	ret = aqr_fw_get_le24(data, primary_offset + HEADER_OFFSET +
+			      offsetof(struct aqr_fw_header, dram_size),
+			      size, &dram_size);
+	if (ret) {
+		phydev_err(phydev, "invalid dram size in firmware\n");
+		return ret;
+	}
+
+	/* Increment the offset with the primary offset.
+	 * Validate iram/dram offset and size.
+	 */
+	iram_offset += primary_offset;
+	if (iram_size % sizeof(u32)) {
+		phydev_err(phydev, "iram size if not aligned to word size. Please report this upstream!\n");
+		return -EINVAL;
+	}
+	if (!aqr_fw_validate_get(size, iram_offset, iram_size)) {
+		phydev_err(phydev, "invalid iram offset for iram size\n");
+		return -EINVAL;
+	}
+
+	dram_offset += primary_offset;
+	if (dram_size % sizeof(u32)) {
+		phydev_err(phydev, "dram size if not aligned to word size. Please report this upstream!\n");
+		return -EINVAL;
+	}
+	if (!aqr_fw_validate_get(size, dram_offset, dram_size)) {
+		phydev_err(phydev, "invalid iram offset for iram size\n");
+		return -EINVAL;
+	}
+
+	phydev_dbg(phydev, "primary %d IRAM offset=%d size=%d DRAM offset=%d size=%d\n",
+		   primary_offset, iram_offset, iram_size, dram_offset, dram_size);
+
+	if (!aqr_fw_validate_get(size, dram_offset + VERSION_STRING_OFFSET,
+				 VERSION_STRING_SIZE)) {
+		phydev_err(phydev, "invalid version in firmware\n");
+		return -EINVAL;
+	}
+	strscpy(version, (char *)data + dram_offset + VERSION_STRING_OFFSET,
+		VERSION_STRING_SIZE);
+	if (version[0] == '\0') {
+		phydev_err(phydev, "invalid version in firmware\n");
+		return -EINVAL;
+	}
+	phydev_info(phydev, "loading firmware version '%s' from '%s'\n", version,
+		    aqr_fw_src_string[fw_src]);
+
+	/* stall the microcprocessor */
+	phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_GLOBAL_CONTROL2,
+		      VEND1_GLOBAL_CONTROL2_UP_RUN_STALL | VEND1_GLOBAL_CONTROL2_UP_RUN_STALL_OVD);
+
+	phydev_dbg(phydev, "loading DRAM 0x%08x from offset=%d size=%d\n",
+		   DRAM_BASE_ADDR, dram_offset, dram_size);
+	ret = aqr_fw_load_memory(phydev, DRAM_BASE_ADDR, data + dram_offset,
+				 dram_size);
+	if (ret)
+		return ret;
+
+	phydev_dbg(phydev, "loading IRAM 0x%08x from offset=%d size=%d\n",
+		   IRAM_BASE_ADDR, iram_offset, iram_size);
+	ret = aqr_fw_load_memory(phydev, IRAM_BASE_ADDR, data + iram_offset,
+				 iram_size);
+	if (ret)
+		return ret;
+
+	/* make sure soft reset and low power mode are clear */
+	phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_GLOBAL_SC,
+			   VEND1_GLOBAL_SC_SOFT_RESET | VEND1_GLOBAL_SC_LOW_POWER);
+
+	/* Release the microprocessor. UP_RESET must be held for 100 usec. */
+	phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_GLOBAL_CONTROL2,
+		      VEND1_GLOBAL_CONTROL2_UP_RUN_STALL |
+		      VEND1_GLOBAL_CONTROL2_UP_RUN_STALL_OVD |
+		      VEND1_GLOBAL_CONTROL2_UP_RUN_STALL_RST);
+	usleep_range(UP_RESET_SLEEP, UP_RESET_SLEEP * 2);
+
+	phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_GLOBAL_CONTROL2,
+		      VEND1_GLOBAL_CONTROL2_UP_RUN_STALL_OVD);
+
+	return 0;
+}
+
+static int aqr_firmware_load_nvmem(struct phy_device *phydev)
+{
+	struct nvmem_cell *cell;
+	size_t size;
+	u8 *buf;
+	int ret;
+
+	cell = nvmem_cell_get(&phydev->mdio.dev, "firmware");
+	if (IS_ERR(cell))
+		return PTR_ERR(cell);
+
+	buf = nvmem_cell_read(cell, &size);
+	if (IS_ERR(buf)) {
+		ret = PTR_ERR(buf);
+		goto exit;
+	}
+
+	ret = aqr_fw_boot(phydev, buf, size, AQR_FW_SRC_NVMEM);
+	if (ret)
+		phydev_err(phydev, "firmware loading failed: %d\n", ret);
+
+	kfree(buf);
+exit:
+	nvmem_cell_put(cell);
+
+	return ret;
+}
+
+static int aqr_firmware_load_fs(struct phy_device *phydev)
+{
+	struct device *dev = &phydev->mdio.dev;
+	const struct firmware *fw;
+	const char *fw_name;
+	int ret;
+
+	ret = of_property_read_string(dev->of_node, "firmware-name",
+				      &fw_name);
+	if (ret)
+		return ret;
+
+	ret = request_firmware(&fw, fw_name, dev);
+	if (ret) {
+		phydev_err(phydev, "failed to find FW file %s (%d)\n",
+			   fw_name, ret);
+		return ret;
+	}
+
+	ret = aqr_fw_boot(phydev, fw->data, fw->size, AQR_FW_SRC_FS);
+	if (ret)
+		phydev_err(phydev, "firmware loading failed: %d\n", ret);
+
+	release_firmware(fw);
+
+	return ret;
+}
+
+int aqr_firmware_load(struct phy_device *phydev)
+{
+	int ret;
+
+	/* Check if the firmware is not already loaded by pooling
+	 * the current version returned by the PHY. If 0 is returned,
+	 * no firmware is loaded.
+	 */
+	ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, VEND1_GLOBAL_FW_ID);
+	if (ret > 0)
+		goto exit;
+
+	ret = aqr_firmware_load_nvmem(phydev);
+	if (!ret)
+		goto exit;
+
+	ret = aqr_firmware_load_fs(phydev);
+	if (ret)
+		return ret;
+
+exit:
+	return 0;
+}
diff --git a/drivers/net/phy/aquantia_hwmon.c b/drivers/net/phy/aquantia/aquantia_hwmon.c
index 0da451e46f69..7b3c49c3bf49 100644
--- a/drivers/net/phy/aquantia_hwmon.c
+++ b/drivers/net/phy/aquantia/aquantia_hwmon.c
@@ -13,20 +13,6 @@
 
 #include "aquantia.h"
 
-/* Vendor specific 1, MDIO_MMD_VEND2 */
-#define VEND1_THERMAL_PROV_HIGH_TEMP_FAIL	0xc421
-#define VEND1_THERMAL_PROV_LOW_TEMP_FAIL	0xc422
-#define VEND1_THERMAL_PROV_HIGH_TEMP_WARN	0xc423
-#define VEND1_THERMAL_PROV_LOW_TEMP_WARN	0xc424
-#define VEND1_THERMAL_STAT1			0xc820
-#define VEND1_THERMAL_STAT2			0xc821
-#define VEND1_THERMAL_STAT2_VALID		BIT(0)
-#define VEND1_GENERAL_STAT1			0xc830
-#define VEND1_GENERAL_STAT1_HIGH_TEMP_FAIL	BIT(14)
-#define VEND1_GENERAL_STAT1_LOW_TEMP_FAIL	BIT(13)
-#define VEND1_GENERAL_STAT1_HIGH_TEMP_WARN	BIT(12)
-#define VEND1_GENERAL_STAT1_LOW_TEMP_WARN	BIT(11)
-
 #if IS_REACHABLE(CONFIG_HWMON)
 
 static umode_t aqr_hwmon_is_visible(const void *data,
diff --git a/drivers/net/phy/aquantia_main.c b/drivers/net/phy/aquantia/aquantia_main.c
index 334a6904ca5a..97a2fafa15ca 100644
--- a/drivers/net/phy/aquantia_main.c
+++ b/drivers/net/phy/aquantia/aquantia_main.c
@@ -91,61 +91,6 @@
 #define MDIO_C22EXT_STAT_SGMII_TX_FRAME_ALIGN_ERR	0xd31a
 #define MDIO_C22EXT_STAT_SGMII_TX_RUNT_FRAMES		0xd31b
 
-/* Vendor specific 1, MDIO_MMD_VEND1 */
-#define VEND1_GLOBAL_FW_ID			0x0020
-#define VEND1_GLOBAL_FW_ID_MAJOR		GENMASK(15, 8)
-#define VEND1_GLOBAL_FW_ID_MINOR		GENMASK(7, 0)
-
-#define VEND1_GLOBAL_GEN_STAT2			0xc831
-#define VEND1_GLOBAL_GEN_STAT2_OP_IN_PROG	BIT(15)
-
-/* The following registers all have similar layouts; first the registers... */
-#define VEND1_GLOBAL_CFG_10M			0x0310
-#define VEND1_GLOBAL_CFG_100M			0x031b
-#define VEND1_GLOBAL_CFG_1G			0x031c
-#define VEND1_GLOBAL_CFG_2_5G			0x031d
-#define VEND1_GLOBAL_CFG_5G			0x031e
-#define VEND1_GLOBAL_CFG_10G			0x031f
-/* ...and now the fields */
-#define VEND1_GLOBAL_CFG_RATE_ADAPT		GENMASK(8, 7)
-#define VEND1_GLOBAL_CFG_RATE_ADAPT_NONE	0
-#define VEND1_GLOBAL_CFG_RATE_ADAPT_USX		1
-#define VEND1_GLOBAL_CFG_RATE_ADAPT_PAUSE	2
-
-#define VEND1_GLOBAL_RSVD_STAT1			0xc885
-#define VEND1_GLOBAL_RSVD_STAT1_FW_BUILD_ID	GENMASK(7, 4)
-#define VEND1_GLOBAL_RSVD_STAT1_PROV_ID		GENMASK(3, 0)
-
-#define VEND1_GLOBAL_RSVD_STAT9			0xc88d
-#define VEND1_GLOBAL_RSVD_STAT9_MODE		GENMASK(7, 0)
-#define VEND1_GLOBAL_RSVD_STAT9_1000BT2		0x23
-
-#define VEND1_GLOBAL_INT_STD_STATUS		0xfc00
-#define VEND1_GLOBAL_INT_VEND_STATUS		0xfc01
-
-#define VEND1_GLOBAL_INT_STD_MASK		0xff00
-#define VEND1_GLOBAL_INT_STD_MASK_PMA1		BIT(15)
-#define VEND1_GLOBAL_INT_STD_MASK_PMA2		BIT(14)
-#define VEND1_GLOBAL_INT_STD_MASK_PCS1		BIT(13)
-#define VEND1_GLOBAL_INT_STD_MASK_PCS2		BIT(12)
-#define VEND1_GLOBAL_INT_STD_MASK_PCS3		BIT(11)
-#define VEND1_GLOBAL_INT_STD_MASK_PHY_XS1	BIT(10)
-#define VEND1_GLOBAL_INT_STD_MASK_PHY_XS2	BIT(9)
-#define VEND1_GLOBAL_INT_STD_MASK_AN1		BIT(8)
-#define VEND1_GLOBAL_INT_STD_MASK_AN2		BIT(7)
-#define VEND1_GLOBAL_INT_STD_MASK_GBE		BIT(6)
-#define VEND1_GLOBAL_INT_STD_MASK_ALL		BIT(0)
-
-#define VEND1_GLOBAL_INT_VEND_MASK		0xff01
-#define VEND1_GLOBAL_INT_VEND_MASK_PMA		BIT(15)
-#define VEND1_GLOBAL_INT_VEND_MASK_PCS		BIT(14)
-#define VEND1_GLOBAL_INT_VEND_MASK_PHY_XS	BIT(13)
-#define VEND1_GLOBAL_INT_VEND_MASK_AN		BIT(12)
-#define VEND1_GLOBAL_INT_VEND_MASK_GBE		BIT(11)
-#define VEND1_GLOBAL_INT_VEND_MASK_GLOBAL1	BIT(2)
-#define VEND1_GLOBAL_INT_VEND_MASK_GLOBAL2	BIT(1)
-#define VEND1_GLOBAL_INT_VEND_MASK_GLOBAL3	BIT(0)
-
 /* Sleep and timeout for checking if the Processor-Intensive
  * MDIO operation is finished
  */
@@ -711,13 +656,93 @@ static int aqr107_resume(struct phy_device *phydev)
 	return aqr107_wait_processor_intensive_op(phydev);
 }
 
+static const u16 aqr_global_cfg_regs[] = {
+	VEND1_GLOBAL_CFG_10M,
+	VEND1_GLOBAL_CFG_100M,
+	VEND1_GLOBAL_CFG_1G,
+	VEND1_GLOBAL_CFG_2_5G,
+	VEND1_GLOBAL_CFG_5G,
+	VEND1_GLOBAL_CFG_10G
+};
+
+static int aqr107_fill_interface_modes(struct phy_device *phydev)
+{
+	unsigned long *possible = phydev->possible_interfaces;
+	unsigned int serdes_mode, rate_adapt;
+	phy_interface_t interface;
+	int i, val;
+
+	/* Walk the media-speed configuration registers to determine which
+	 * host-side serdes modes may be used by the PHY depending on the
+	 * negotiated media speed.
+	 */
+	for (i = 0; i < ARRAY_SIZE(aqr_global_cfg_regs); i++) {
+		val = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+				   aqr_global_cfg_regs[i]);
+		if (val < 0)
+			return val;
+
+		serdes_mode = FIELD_GET(VEND1_GLOBAL_CFG_SERDES_MODE, val);
+		rate_adapt = FIELD_GET(VEND1_GLOBAL_CFG_RATE_ADAPT, val);
+
+		switch (serdes_mode) {
+		case VEND1_GLOBAL_CFG_SERDES_MODE_XFI:
+			if (rate_adapt == VEND1_GLOBAL_CFG_RATE_ADAPT_USX)
+				interface = PHY_INTERFACE_MODE_USXGMII;
+			else
+				interface = PHY_INTERFACE_MODE_10GBASER;
+			break;
+
+		case VEND1_GLOBAL_CFG_SERDES_MODE_XFI5G:
+			interface = PHY_INTERFACE_MODE_5GBASER;
+			break;
+
+		case VEND1_GLOBAL_CFG_SERDES_MODE_OCSGMII:
+			interface = PHY_INTERFACE_MODE_2500BASEX;
+			break;
+
+		case VEND1_GLOBAL_CFG_SERDES_MODE_SGMII:
+			interface = PHY_INTERFACE_MODE_SGMII;
+			break;
+
+		default:
+			phydev_warn(phydev, "unrecognised serdes mode %u\n",
+				    serdes_mode);
+			interface = PHY_INTERFACE_MODE_NA;
+			break;
+		}
+
+		if (interface != PHY_INTERFACE_MODE_NA)
+			__set_bit(interface, possible);
+	}
+
+	return 0;
+}
+
+static int aqr113c_config_init(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = aqr107_config_init(phydev);
+	if (ret < 0)
+		return ret;
+
+	return aqr107_fill_interface_modes(phydev);
+}
+
 static int aqr107_probe(struct phy_device *phydev)
 {
+	int ret;
+
 	phydev->priv = devm_kzalloc(&phydev->mdio.dev,
 				    sizeof(struct aqr107_priv), GFP_KERNEL);
 	if (!phydev->priv)
 		return -ENOMEM;
 
+	ret = aqr_firmware_load(phydev);
+	if (ret)
+		return ret;
+
 	return aqr_hwmon_probe(phydev);
 }
 
@@ -843,7 +868,7 @@ static struct phy_driver aqr_driver[] = {
 	.name           = "Aquantia AQR113C",
 	.probe          = aqr107_probe,
 	.get_rate_matching = aqr107_get_rate_matching,
-	.config_init    = aqr107_config_init,
+	.config_init    = aqr113c_config_init,
 	.config_aneg    = aqr_config_aneg,
 	.config_intr    = aqr_config_intr,
 	.handle_interrupt       = aqr_handle_interrupt,
diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index 37fb033e1c29..a62442a55774 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -254,6 +254,7 @@
 
 #define QCA808X_CDT_ENABLE_TEST			BIT(15)
 #define QCA808X_CDT_INTER_CHECK_DIS		BIT(13)
+#define QCA808X_CDT_STATUS			BIT(11)
 #define QCA808X_CDT_LENGTH_UNIT			BIT(10)
 
 #define QCA808X_MMD3_CDT_STATUS			0x8064
@@ -261,16 +262,44 @@
 #define QCA808X_MMD3_CDT_DIAG_PAIR_B		0x8066
 #define QCA808X_MMD3_CDT_DIAG_PAIR_C		0x8067
 #define QCA808X_MMD3_CDT_DIAG_PAIR_D		0x8068
-#define QCA808X_CDT_DIAG_LENGTH			GENMASK(7, 0)
+#define QCA808X_CDT_DIAG_LENGTH_SAME_SHORT	GENMASK(15, 8)
+#define QCA808X_CDT_DIAG_LENGTH_CROSS_SHORT	GENMASK(7, 0)
 
 #define QCA808X_CDT_CODE_PAIR_A			GENMASK(15, 12)
 #define QCA808X_CDT_CODE_PAIR_B			GENMASK(11, 8)
 #define QCA808X_CDT_CODE_PAIR_C			GENMASK(7, 4)
 #define QCA808X_CDT_CODE_PAIR_D			GENMASK(3, 0)
-#define QCA808X_CDT_STATUS_STAT_FAIL		0
-#define QCA808X_CDT_STATUS_STAT_NORMAL		1
-#define QCA808X_CDT_STATUS_STAT_OPEN		2
-#define QCA808X_CDT_STATUS_STAT_SHORT		3
+
+#define QCA808X_CDT_STATUS_STAT_TYPE		GENMASK(1, 0)
+#define QCA808X_CDT_STATUS_STAT_FAIL		FIELD_PREP_CONST(QCA808X_CDT_STATUS_STAT_TYPE, 0)
+#define QCA808X_CDT_STATUS_STAT_NORMAL		FIELD_PREP_CONST(QCA808X_CDT_STATUS_STAT_TYPE, 1)
+#define QCA808X_CDT_STATUS_STAT_SAME_OPEN	FIELD_PREP_CONST(QCA808X_CDT_STATUS_STAT_TYPE, 2)
+#define QCA808X_CDT_STATUS_STAT_SAME_SHORT	FIELD_PREP_CONST(QCA808X_CDT_STATUS_STAT_TYPE, 3)
+
+#define QCA808X_CDT_STATUS_STAT_MDI		GENMASK(3, 2)
+#define QCA808X_CDT_STATUS_STAT_MDI1		FIELD_PREP_CONST(QCA808X_CDT_STATUS_STAT_MDI, 1)
+#define QCA808X_CDT_STATUS_STAT_MDI2		FIELD_PREP_CONST(QCA808X_CDT_STATUS_STAT_MDI, 2)
+#define QCA808X_CDT_STATUS_STAT_MDI3		FIELD_PREP_CONST(QCA808X_CDT_STATUS_STAT_MDI, 3)
+
+/* NORMAL are MDI with type set to 0 */
+#define QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI1_SAME_NORMAL	QCA808X_CDT_STATUS_STAT_MDI1
+#define QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI1_SAME_OPEN		(QCA808X_CDT_STATUS_STAT_SAME_OPEN |\
+									 QCA808X_CDT_STATUS_STAT_MDI1)
+#define QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI1_SAME_SHORT	(QCA808X_CDT_STATUS_STAT_SAME_SHORT |\
+									 QCA808X_CDT_STATUS_STAT_MDI1)
+#define QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI2_SAME_NORMAL	QCA808X_CDT_STATUS_STAT_MDI2
+#define QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI2_SAME_OPEN		(QCA808X_CDT_STATUS_STAT_SAME_OPEN |\
+									 QCA808X_CDT_STATUS_STAT_MDI2)
+#define QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI2_SAME_SHORT	(QCA808X_CDT_STATUS_STAT_SAME_SHORT |\
+									 QCA808X_CDT_STATUS_STAT_MDI2)
+#define QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI3_SAME_NORMAL	QCA808X_CDT_STATUS_STAT_MDI3
+#define QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI3_SAME_OPEN		(QCA808X_CDT_STATUS_STAT_SAME_OPEN |\
+									 QCA808X_CDT_STATUS_STAT_MDI3)
+#define QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI3_SAME_SHORT	(QCA808X_CDT_STATUS_STAT_SAME_SHORT |\
+									 QCA808X_CDT_STATUS_STAT_MDI3)
+
+/* Added for reference of existence but should be handled by wait_for_completion already */
+#define QCA808X_CDT_STATUS_STAT_BUSY		(BIT(1) | BIT(3))
 
 /* QCA808X 1G chip type */
 #define QCA808X_PHY_MMD7_CHIP_TYPE		0x901d
@@ -295,12 +324,17 @@ struct at803x_hw_stat {
 	enum stat_access_type access_type;
 };
 
-static struct at803x_hw_stat at803x_hw_stats[] = {
+static struct at803x_hw_stat qca83xx_hw_stats[] = {
 	{ "phy_idle_errors", 0xa, GENMASK(7, 0), PHY},
 	{ "phy_receive_errors", 0x15, GENMASK(15, 0), PHY},
 	{ "eee_wake_errors", 0x16, GENMASK(15, 0), MMD},
 };
 
+struct at803x_ss_mask {
+	u16 speed_mask;
+	u8 speed_shift;
+};
+
 struct at803x_priv {
 	int flags;
 	u16 clk_25m_reg;
@@ -311,7 +345,7 @@ struct at803x_priv {
 	bool is_1000basex;
 	struct regulator_dev *vddio_rdev;
 	struct regulator_dev *vddh_rdev;
-	u64 stats[ARRAY_SIZE(at803x_hw_stats)];
+	u64 stats[ARRAY_SIZE(qca83xx_hw_stats)];
 };
 
 struct at803x_context {
@@ -457,7 +491,7 @@ static int at803x_set_wol(struct phy_device *phydev,
 		if (!ndev)
 			return -ENODEV;
 
-		mac = (const u8 *) ndev->dev_addr;
+		mac = (const u8 *)ndev->dev_addr;
 
 		if (!is_valid_ether_addr(mac))
 			return -EINVAL;
@@ -466,27 +500,11 @@ static int at803x_set_wol(struct phy_device *phydev,
 			phy_write_mmd(phydev, MDIO_MMD_PCS, offsets[i],
 				      mac[(i * 2) + 1] | (mac[(i * 2)] << 8));
 
-		/* Enable WOL function for 1588 */
-		if (phydev->drv->phy_id == ATH8031_PHY_ID) {
-			ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
-					     AT803X_PHY_MMD3_WOL_CTRL,
-					     0, AT803X_WOL_EN);
-			if (ret)
-				return ret;
-		}
 		/* Enable WOL interrupt */
 		ret = phy_modify(phydev, AT803X_INTR_ENABLE, 0, AT803X_INTR_ENABLE_WOL);
 		if (ret)
 			return ret;
 	} else {
-		/* Disable WoL function for 1588 */
-		if (phydev->drv->phy_id == ATH8031_PHY_ID) {
-			ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
-					     AT803X_PHY_MMD3_WOL_CTRL,
-					     AT803X_WOL_EN, 0);
-			if (ret)
-				return ret;
-		}
 		/* Disable WOL interrupt */
 		ret = phy_modify(phydev, AT803X_INTR_ENABLE, AT803X_INTR_ENABLE_WOL, 0);
 		if (ret)
@@ -529,24 +547,24 @@ static void at803x_get_wol(struct phy_device *phydev,
 		wol->wolopts |= WAKE_MAGIC;
 }
 
-static int at803x_get_sset_count(struct phy_device *phydev)
+static int qca83xx_get_sset_count(struct phy_device *phydev)
 {
-	return ARRAY_SIZE(at803x_hw_stats);
+	return ARRAY_SIZE(qca83xx_hw_stats);
 }
 
-static void at803x_get_strings(struct phy_device *phydev, u8 *data)
+static void qca83xx_get_strings(struct phy_device *phydev, u8 *data)
 {
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(at803x_hw_stats); i++) {
+	for (i = 0; i < ARRAY_SIZE(qca83xx_hw_stats); i++) {
 		strscpy(data + i * ETH_GSTRING_LEN,
-			at803x_hw_stats[i].string, ETH_GSTRING_LEN);
+			qca83xx_hw_stats[i].string, ETH_GSTRING_LEN);
 	}
 }
 
-static u64 at803x_get_stat(struct phy_device *phydev, int i)
+static u64 qca83xx_get_stat(struct phy_device *phydev, int i)
 {
-	struct at803x_hw_stat stat = at803x_hw_stats[i];
+	struct at803x_hw_stat stat = qca83xx_hw_stats[i];
 	struct at803x_priv *priv = phydev->priv;
 	int val;
 	u64 ret;
@@ -567,13 +585,13 @@ static u64 at803x_get_stat(struct phy_device *phydev, int i)
 	return ret;
 }
 
-static void at803x_get_stats(struct phy_device *phydev,
-			     struct ethtool_stats *stats, u64 *data)
+static void qca83xx_get_stats(struct phy_device *phydev,
+			      struct ethtool_stats *stats, u64 *data)
 {
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(at803x_hw_stats); i++)
-		data[i] = at803x_get_stat(phydev, i);
+	for (i = 0; i < ARRAY_SIZE(qca83xx_hw_stats); i++)
+		data[i] = qca83xx_get_stat(phydev, i);
 }
 
 static int at803x_suspend(struct phy_device *phydev)
@@ -599,139 +617,6 @@ static int at803x_resume(struct phy_device *phydev)
 	return phy_modify(phydev, MII_BMCR, BMCR_PDOWN | BMCR_ISOLATE, 0);
 }
 
-static int at803x_rgmii_reg_set_voltage_sel(struct regulator_dev *rdev,
-					    unsigned int selector)
-{
-	struct phy_device *phydev = rdev_get_drvdata(rdev);
-
-	if (selector)
-		return at803x_debug_reg_mask(phydev, AT803X_DEBUG_REG_1F,
-					     0, AT803X_DEBUG_RGMII_1V8);
-	else
-		return at803x_debug_reg_mask(phydev, AT803X_DEBUG_REG_1F,
-					     AT803X_DEBUG_RGMII_1V8, 0);
-}
-
-static int at803x_rgmii_reg_get_voltage_sel(struct regulator_dev *rdev)
-{
-	struct phy_device *phydev = rdev_get_drvdata(rdev);
-	int val;
-
-	val = at803x_debug_reg_read(phydev, AT803X_DEBUG_REG_1F);
-	if (val < 0)
-		return val;
-
-	return (val & AT803X_DEBUG_RGMII_1V8) ? 1 : 0;
-}
-
-static const struct regulator_ops vddio_regulator_ops = {
-	.list_voltage = regulator_list_voltage_table,
-	.set_voltage_sel = at803x_rgmii_reg_set_voltage_sel,
-	.get_voltage_sel = at803x_rgmii_reg_get_voltage_sel,
-};
-
-static const unsigned int vddio_voltage_table[] = {
-	1500000,
-	1800000,
-};
-
-static const struct regulator_desc vddio_desc = {
-	.name = "vddio",
-	.of_match = of_match_ptr("vddio-regulator"),
-	.n_voltages = ARRAY_SIZE(vddio_voltage_table),
-	.volt_table = vddio_voltage_table,
-	.ops = &vddio_regulator_ops,
-	.type = REGULATOR_VOLTAGE,
-	.owner = THIS_MODULE,
-};
-
-static const struct regulator_ops vddh_regulator_ops = {
-};
-
-static const struct regulator_desc vddh_desc = {
-	.name = "vddh",
-	.of_match = of_match_ptr("vddh-regulator"),
-	.n_voltages = 1,
-	.fixed_uV = 2500000,
-	.ops = &vddh_regulator_ops,
-	.type = REGULATOR_VOLTAGE,
-	.owner = THIS_MODULE,
-};
-
-static int at8031_register_regulators(struct phy_device *phydev)
-{
-	struct at803x_priv *priv = phydev->priv;
-	struct device *dev = &phydev->mdio.dev;
-	struct regulator_config config = { };
-
-	config.dev = dev;
-	config.driver_data = phydev;
-
-	priv->vddio_rdev = devm_regulator_register(dev, &vddio_desc, &config);
-	if (IS_ERR(priv->vddio_rdev)) {
-		phydev_err(phydev, "failed to register VDDIO regulator\n");
-		return PTR_ERR(priv->vddio_rdev);
-	}
-
-	priv->vddh_rdev = devm_regulator_register(dev, &vddh_desc, &config);
-	if (IS_ERR(priv->vddh_rdev)) {
-		phydev_err(phydev, "failed to register VDDH regulator\n");
-		return PTR_ERR(priv->vddh_rdev);
-	}
-
-	return 0;
-}
-
-static int at803x_sfp_insert(void *upstream, const struct sfp_eeprom_id *id)
-{
-	struct phy_device *phydev = upstream;
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(phy_support);
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(sfp_support);
-	DECLARE_PHY_INTERFACE_MASK(interfaces);
-	phy_interface_t iface;
-
-	linkmode_zero(phy_support);
-	phylink_set(phy_support, 1000baseX_Full);
-	phylink_set(phy_support, 1000baseT_Full);
-	phylink_set(phy_support, Autoneg);
-	phylink_set(phy_support, Pause);
-	phylink_set(phy_support, Asym_Pause);
-
-	linkmode_zero(sfp_support);
-	sfp_parse_support(phydev->sfp_bus, id, sfp_support, interfaces);
-	/* Some modules support 10G modes as well as others we support.
-	 * Mask out non-supported modes so the correct interface is picked.
-	 */
-	linkmode_and(sfp_support, phy_support, sfp_support);
-
-	if (linkmode_empty(sfp_support)) {
-		dev_err(&phydev->mdio.dev, "incompatible SFP module inserted\n");
-		return -EINVAL;
-	}
-
-	iface = sfp_select_interface(phydev->sfp_bus, sfp_support);
-
-	/* Only 1000Base-X is supported by AR8031/8033 as the downstream SerDes
-	 * interface for use with SFP modules.
-	 * However, some copper modules detected as having a preferred SGMII
-	 * interface do default to and function in 1000Base-X mode, so just
-	 * print a warning and allow such modules, as they may have some chance
-	 * of working.
-	 */
-	if (iface == PHY_INTERFACE_MODE_SGMII)
-		dev_warn(&phydev->mdio.dev, "module may not function if 1000Base-X not supported\n");
-	else if (iface != PHY_INTERFACE_MODE_1000BASEX)
-		return -EINVAL;
-
-	return 0;
-}
-
-static const struct sfp_upstream_ops at803x_sfp_ops = {
-	.attach = phy_sfp_attach,
-	.detach = phy_sfp_detach,
-	.module_insert = at803x_sfp_insert,
-};
-
 static int at803x_parse_dt(struct phy_device *phydev)
 {
 	struct device_node *node = phydev->mdio.dev.of_node;
@@ -787,23 +672,6 @@ static int at803x_parse_dt(struct phy_device *phydev)
 
 		priv->clk_25m_reg |= FIELD_PREP(AT803X_CLK_OUT_MASK, sel);
 		priv->clk_25m_mask |= AT803X_CLK_OUT_MASK;
-
-		/* Fixup for the AR8030/AR8035. This chip has another mask and
-		 * doesn't support the DSP reference. Eg. the lowest bit of the
-		 * mask. The upper two bits select the same frequencies. Mask
-		 * the lowest bit here.
-		 *
-		 * Warning:
-		 *   There was no datasheet for the AR8030 available so this is
-		 *   just a guess. But the AR8035 is listed as pin compatible
-		 *   to the AR8030 so there might be a good chance it works on
-		 *   the AR8030 too.
-		 */
-		if (phydev->drv->phy_id == ATH8030_PHY_ID ||
-		    phydev->drv->phy_id == ATH8035_PHY_ID) {
-			priv->clk_25m_reg &= AT8035_CLK_OUT_MASK;
-			priv->clk_25m_mask &= AT8035_CLK_OUT_MASK;
-		}
 	}
 
 	ret = of_property_read_u32(node, "qca,clk-out-strength", &strength);
@@ -825,30 +693,6 @@ static int at803x_parse_dt(struct phy_device *phydev)
 		}
 	}
 
-	/* Only supported on AR8031/AR8033, the AR8030/AR8035 use strapping
-	 * options.
-	 */
-	if (phydev->drv->phy_id == ATH8031_PHY_ID) {
-		if (of_property_read_bool(node, "qca,keep-pll-enabled"))
-			priv->flags |= AT803X_KEEP_PLL_ENABLED;
-
-		ret = at8031_register_regulators(phydev);
-		if (ret < 0)
-			return ret;
-
-		ret = devm_regulator_get_enable_optional(&phydev->mdio.dev,
-							 "vddio");
-		if (ret) {
-			phydev_err(phydev, "failed to get VDDIO regulator\n");
-			return ret;
-		}
-
-		/* Only AR8031/8033 support 1000Base-X for SFP modules */
-		ret = phy_sfp_probe(phydev, &at803x_sfp_ops);
-		if (ret < 0)
-			return ret;
-	}
-
 	return 0;
 }
 
@@ -868,35 +712,6 @@ static int at803x_probe(struct phy_device *phydev)
 	if (ret)
 		return ret;
 
-	if (phydev->drv->phy_id == ATH8031_PHY_ID) {
-		int ccr = phy_read(phydev, AT803X_REG_CHIP_CONFIG);
-		int mode_cfg;
-
-		if (ccr < 0)
-			return ccr;
-		mode_cfg = ccr & AT803X_MODE_CFG_MASK;
-
-		switch (mode_cfg) {
-		case AT803X_MODE_CFG_BX1000_RGMII_50OHM:
-		case AT803X_MODE_CFG_BX1000_RGMII_75OHM:
-			priv->is_1000basex = true;
-			fallthrough;
-		case AT803X_MODE_CFG_FX100_RGMII_50OHM:
-		case AT803X_MODE_CFG_FX100_RGMII_75OHM:
-			priv->is_fiber = true;
-			break;
-		}
-
-		/* Disable WoL in 1588 register which is enabled
-		 * by default
-		 */
-		ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
-				     AT803X_PHY_MMD3_WOL_CTRL,
-				     AT803X_WOL_EN, 0);
-		if (ret)
-			return ret;
-	}
-
 	return 0;
 }
 
@@ -1004,27 +819,8 @@ static int at803x_hibernation_mode_config(struct phy_device *phydev)
 
 static int at803x_config_init(struct phy_device *phydev)
 {
-	struct at803x_priv *priv = phydev->priv;
 	int ret;
 
-	if (phydev->drv->phy_id == ATH8031_PHY_ID) {
-		/* Some bootloaders leave the fiber page selected.
-		 * Switch to the appropriate page (fiber or copper), as otherwise we
-		 * read the PHY capabilities from the wrong page.
-		 */
-		phy_lock_mdio_bus(phydev);
-		ret = at803x_write_page(phydev,
-					priv->is_fiber ? AT803X_PAGE_FIBER :
-							 AT803X_PAGE_COPPER);
-		phy_unlock_mdio_bus(phydev);
-		if (ret)
-			return ret;
-
-		ret = at8031_pll_config(phydev);
-		if (ret < 0)
-			return ret;
-	}
-
 	/* The RX and TX delay default is:
 	 *   after HW reset: RX delay enabled and TX delay disabled
 	 *   after SW reset: RX delay enabled, while TX delay retains the
@@ -1078,7 +874,6 @@ static int at803x_ack_interrupt(struct phy_device *phydev)
 
 static int at803x_config_intr(struct phy_device *phydev)
 {
-	struct at803x_priv *priv = phydev->priv;
 	int err;
 	int value;
 
@@ -1095,10 +890,6 @@ static int at803x_config_intr(struct phy_device *phydev)
 		value |= AT803X_INTR_ENABLE_DUPLEX_CHANGED;
 		value |= AT803X_INTR_ENABLE_LINK_FAIL;
 		value |= AT803X_INTR_ENABLE_LINK_SUCCESS;
-		if (priv->is_fiber) {
-			value |= AT803X_INTR_ENABLE_LINK_FAIL_BX;
-			value |= AT803X_INTR_ENABLE_LINK_SUCCESS_BX;
-		}
 
 		err = phy_write(phydev, AT803X_INTR_ENABLE, value);
 	} else {
@@ -1154,9 +945,9 @@ static void at803x_link_change_notify(struct phy_device *phydev)
 		at803x_context_save(phydev, &context);
 
 		phy_device_reset(phydev, 1);
-		msleep(1);
+		usleep_range(1000, 2000);
 		phy_device_reset(phydev, 0);
-		msleep(1);
+		usleep_range(1000, 2000);
 
 		at803x_context_restore(phydev, &context);
 
@@ -1164,7 +955,8 @@ static void at803x_link_change_notify(struct phy_device *phydev)
 	}
 }
 
-static int at803x_read_specific_status(struct phy_device *phydev)
+static int at803x_read_specific_status(struct phy_device *phydev,
+				       struct at803x_ss_mask ss_mask)
 {
 	int ss;
 
@@ -1183,11 +975,8 @@ static int at803x_read_specific_status(struct phy_device *phydev)
 		if (sfc < 0)
 			return sfc;
 
-		/* qca8081 takes the different bits for speed value from at803x */
-		if (phydev->drv->phy_id == QCA8081_PHY_ID)
-			speed = FIELD_GET(QCA808X_SS_SPEED_MASK, ss);
-		else
-			speed = FIELD_GET(AT803X_SS_SPEED_MASK, ss);
+		speed = ss & ss_mask.speed_mask;
+		speed >>= ss_mask.speed_shift;
 
 		switch (speed) {
 		case AT803X_SS_SPEED_10:
@@ -1231,12 +1020,9 @@ static int at803x_read_specific_status(struct phy_device *phydev)
 
 static int at803x_read_status(struct phy_device *phydev)
 {
-	struct at803x_priv *priv = phydev->priv;
+	struct at803x_ss_mask ss_mask = { 0 };
 	int err, old_link = phydev->link;
 
-	if (priv->is_1000basex)
-		return genphy_c37_read_status(phydev);
-
 	/* Update the link, but return if there was an error */
 	err = genphy_update_link(phydev);
 	if (err)
@@ -1255,7 +1041,9 @@ static int at803x_read_status(struct phy_device *phydev)
 	if (err < 0)
 		return err;
 
-	err = at803x_read_specific_status(phydev);
+	ss_mask.speed_mask = AT803X_SS_SPEED_MASK;
+	ss_mask.speed_shift = __bf_shf(AT803X_SS_SPEED_MASK);
+	err = at803x_read_specific_status(phydev, ss_mask);
 	if (err < 0)
 		return err;
 
@@ -1288,9 +1076,8 @@ static int at803x_config_mdix(struct phy_device *phydev, u8 ctrl)
 			  FIELD_PREP(AT803X_SFC_MDI_CROSSOVER_MODE_M, val));
 }
 
-static int at803x_config_aneg(struct phy_device *phydev)
+static int at803x_prepare_config_aneg(struct phy_device *phydev)
 {
-	struct at803x_priv *priv = phydev->priv;
 	int ret;
 
 	ret = at803x_config_mdix(phydev, phydev->mdix_ctrl);
@@ -1307,33 +1094,22 @@ static int at803x_config_aneg(struct phy_device *phydev)
 			return ret;
 	}
 
-	if (priv->is_1000basex)
-		return genphy_c37_config_aneg(phydev);
-
-	/* Do not restart auto-negotiation by setting ret to 0 defautly,
-	 * when calling __genphy_config_aneg later.
-	 */
-	ret = 0;
-
-	if (phydev->drv->phy_id == QCA8081_PHY_ID) {
-		int phy_ctrl = 0;
+	return 0;
+}
 
-		/* The reg MII_BMCR also needs to be configured for force mode, the
-		 * genphy_config_aneg is also needed.
-		 */
-		if (phydev->autoneg == AUTONEG_DISABLE)
-			genphy_c45_pma_setup_forced(phydev);
+static int at803x_config_aneg(struct phy_device *phydev)
+{
+	struct at803x_priv *priv = phydev->priv;
+	int ret;
 
-		if (linkmode_test_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, phydev->advertising))
-			phy_ctrl = MDIO_AN_10GBT_CTRL_ADV2_5G;
+	ret = at803x_prepare_config_aneg(phydev);
+	if (ret)
+		return ret;
 
-		ret = phy_modify_mmd_changed(phydev, MDIO_MMD_AN, MDIO_AN_10GBT_CTRL,
-				MDIO_AN_10GBT_CTRL_ADV2_5G, phy_ctrl);
-		if (ret < 0)
-			return ret;
-	}
+	if (priv->is_1000basex)
+		return genphy_c37_config_aneg(phydev);
 
-	return __genphy_config_aneg(phydev, ret);
+	return genphy_config_aneg(phydev);
 }
 
 static int at803x_get_downshift(struct phy_device *phydev, u8 *d)
@@ -1441,10 +1217,8 @@ static bool at803x_cdt_fault_length_valid(u16 status)
 	return false;
 }
 
-static int at803x_cdt_fault_length(u16 status)
+static int at803x_cdt_fault_length(int dt)
 {
-	int dt;
-
 	/* According to the datasheet the distance to the fault is
 	 * DELTA_TIME * 0.824 meters.
 	 *
@@ -1460,36 +1234,19 @@ static int at803x_cdt_fault_length(u16 status)
 	 * With a VF of 0.69 we get the factor 0.824 mentioned in the
 	 * datasheet.
 	 */
-	dt = FIELD_GET(AT803X_CDT_STATUS_DELTA_TIME_MASK, status);
-
 	return (dt * 824) / 10;
 }
 
-static int at803x_cdt_start(struct phy_device *phydev, int pair)
+static int at803x_cdt_start(struct phy_device *phydev,
+			    u32 cdt_start)
 {
-	u16 cdt;
-
-	/* qca8081 takes the different bit 15 to enable CDT test */
-	if (phydev->drv->phy_id == QCA8081_PHY_ID)
-		cdt = QCA808X_CDT_ENABLE_TEST |
-			QCA808X_CDT_LENGTH_UNIT |
-			QCA808X_CDT_INTER_CHECK_DIS;
-	else
-		cdt = FIELD_PREP(AT803X_CDT_MDI_PAIR_MASK, pair) |
-			AT803X_CDT_ENABLE_TEST;
-
-	return phy_write(phydev, AT803X_CDT, cdt);
+	return phy_write(phydev, AT803X_CDT, cdt_start);
 }
 
-static int at803x_cdt_wait_for_completion(struct phy_device *phydev)
+static int at803x_cdt_wait_for_completion(struct phy_device *phydev,
+					  u32 cdt_en)
 {
 	int val, ret;
-	u16 cdt_en;
-
-	if (phydev->drv->phy_id == QCA8081_PHY_ID)
-		cdt_en = QCA808X_CDT_ENABLE_TEST;
-	else
-		cdt_en = AT803X_CDT_ENABLE_TEST;
 
 	/* One test run takes about 25ms */
 	ret = phy_read_poll_timeout(phydev, AT803X_CDT, val,
@@ -1509,11 +1266,13 @@ static int at803x_cable_test_one_pair(struct phy_device *phydev, int pair)
 	};
 	int ret, val;
 
-	ret = at803x_cdt_start(phydev, pair);
+	val = FIELD_PREP(AT803X_CDT_MDI_PAIR_MASK, pair) |
+	      AT803X_CDT_ENABLE_TEST;
+	ret = at803x_cdt_start(phydev, val);
 	if (ret)
 		return ret;
 
-	ret = at803x_cdt_wait_for_completion(phydev);
+	ret = at803x_cdt_wait_for_completion(phydev, AT803X_CDT_ENABLE_TEST);
 	if (ret)
 		return ret;
 
@@ -1527,27 +1286,21 @@ static int at803x_cable_test_one_pair(struct phy_device *phydev, int pair)
 	ethnl_cable_test_result(phydev, ethtool_pair[pair],
 				at803x_cable_test_result_trans(val));
 
-	if (at803x_cdt_fault_length_valid(val))
+	if (at803x_cdt_fault_length_valid(val)) {
+		val = FIELD_GET(AT803X_CDT_STATUS_DELTA_TIME_MASK, val);
 		ethnl_cable_test_fault_length(phydev, ethtool_pair[pair],
 					      at803x_cdt_fault_length(val));
+	}
 
 	return 1;
 }
 
 static int at803x_cable_test_get_status(struct phy_device *phydev,
-					bool *finished)
+					bool *finished, unsigned long pair_mask)
 {
-	unsigned long pair_mask;
 	int retries = 20;
 	int pair, ret;
 
-	if (phydev->phy_id == ATH9331_PHY_ID ||
-	    phydev->phy_id == ATH8032_PHY_ID ||
-	    phydev->phy_id == QCA9561_PHY_ID)
-		pair_mask = 0x3;
-	else
-		pair_mask = 0xf;
-
 	*finished = false;
 
 	/* According to the datasheet the CDT can be performed when
@@ -1574,7 +1327,7 @@ static int at803x_cable_test_get_status(struct phy_device *phydev,
 	return 0;
 }
 
-static int at803x_cable_test_start(struct phy_device *phydev)
+static void at803x_cable_test_autoneg(struct phy_device *phydev)
 {
 	/* Enable auto-negotiation, but advertise no capabilities, no link
 	 * will be established. A restart of the auto-negotiation is not
@@ -1582,15 +1335,358 @@ static int at803x_cable_test_start(struct phy_device *phydev)
 	 */
 	phy_write(phydev, MII_BMCR, BMCR_ANENABLE);
 	phy_write(phydev, MII_ADVERTISE, ADVERTISE_CSMA);
-	if (phydev->phy_id != ATH9331_PHY_ID &&
-	    phydev->phy_id != ATH8032_PHY_ID &&
-	    phydev->phy_id != QCA9561_PHY_ID)
-		phy_write(phydev, MII_CTRL1000, 0);
+}
+
+static int at803x_cable_test_start(struct phy_device *phydev)
+{
+	at803x_cable_test_autoneg(phydev);
+	/* we do all the (time consuming) work later */
+	return 0;
+}
+
+static int at8031_rgmii_reg_set_voltage_sel(struct regulator_dev *rdev,
+					    unsigned int selector)
+{
+	struct phy_device *phydev = rdev_get_drvdata(rdev);
+
+	if (selector)
+		return at803x_debug_reg_mask(phydev, AT803X_DEBUG_REG_1F,
+					     0, AT803X_DEBUG_RGMII_1V8);
+	else
+		return at803x_debug_reg_mask(phydev, AT803X_DEBUG_REG_1F,
+					     AT803X_DEBUG_RGMII_1V8, 0);
+}
+
+static int at8031_rgmii_reg_get_voltage_sel(struct regulator_dev *rdev)
+{
+	struct phy_device *phydev = rdev_get_drvdata(rdev);
+	int val;
+
+	val = at803x_debug_reg_read(phydev, AT803X_DEBUG_REG_1F);
+	if (val < 0)
+		return val;
+
+	return (val & AT803X_DEBUG_RGMII_1V8) ? 1 : 0;
+}
+
+static const struct regulator_ops vddio_regulator_ops = {
+	.list_voltage = regulator_list_voltage_table,
+	.set_voltage_sel = at8031_rgmii_reg_set_voltage_sel,
+	.get_voltage_sel = at8031_rgmii_reg_get_voltage_sel,
+};
+
+static const unsigned int vddio_voltage_table[] = {
+	1500000,
+	1800000,
+};
+
+static const struct regulator_desc vddio_desc = {
+	.name = "vddio",
+	.of_match = of_match_ptr("vddio-regulator"),
+	.n_voltages = ARRAY_SIZE(vddio_voltage_table),
+	.volt_table = vddio_voltage_table,
+	.ops = &vddio_regulator_ops,
+	.type = REGULATOR_VOLTAGE,
+	.owner = THIS_MODULE,
+};
+
+static const struct regulator_ops vddh_regulator_ops = {
+};
+
+static const struct regulator_desc vddh_desc = {
+	.name = "vddh",
+	.of_match = of_match_ptr("vddh-regulator"),
+	.n_voltages = 1,
+	.fixed_uV = 2500000,
+	.ops = &vddh_regulator_ops,
+	.type = REGULATOR_VOLTAGE,
+	.owner = THIS_MODULE,
+};
+
+static int at8031_register_regulators(struct phy_device *phydev)
+{
+	struct at803x_priv *priv = phydev->priv;
+	struct device *dev = &phydev->mdio.dev;
+	struct regulator_config config = { };
+
+	config.dev = dev;
+	config.driver_data = phydev;
+
+	priv->vddio_rdev = devm_regulator_register(dev, &vddio_desc, &config);
+	if (IS_ERR(priv->vddio_rdev)) {
+		phydev_err(phydev, "failed to register VDDIO regulator\n");
+		return PTR_ERR(priv->vddio_rdev);
+	}
+
+	priv->vddh_rdev = devm_regulator_register(dev, &vddh_desc, &config);
+	if (IS_ERR(priv->vddh_rdev)) {
+		phydev_err(phydev, "failed to register VDDH regulator\n");
+		return PTR_ERR(priv->vddh_rdev);
+	}
+
+	return 0;
+}
+
+static int at8031_sfp_insert(void *upstream, const struct sfp_eeprom_id *id)
+{
+	struct phy_device *phydev = upstream;
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(phy_support);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(sfp_support);
+	DECLARE_PHY_INTERFACE_MASK(interfaces);
+	phy_interface_t iface;
+
+	linkmode_zero(phy_support);
+	phylink_set(phy_support, 1000baseX_Full);
+	phylink_set(phy_support, 1000baseT_Full);
+	phylink_set(phy_support, Autoneg);
+	phylink_set(phy_support, Pause);
+	phylink_set(phy_support, Asym_Pause);
+
+	linkmode_zero(sfp_support);
+	sfp_parse_support(phydev->sfp_bus, id, sfp_support, interfaces);
+	/* Some modules support 10G modes as well as others we support.
+	 * Mask out non-supported modes so the correct interface is picked.
+	 */
+	linkmode_and(sfp_support, phy_support, sfp_support);
+
+	if (linkmode_empty(sfp_support)) {
+		dev_err(&phydev->mdio.dev, "incompatible SFP module inserted\n");
+		return -EINVAL;
+	}
+
+	iface = sfp_select_interface(phydev->sfp_bus, sfp_support);
+
+	/* Only 1000Base-X is supported by AR8031/8033 as the downstream SerDes
+	 * interface for use with SFP modules.
+	 * However, some copper modules detected as having a preferred SGMII
+	 * interface do default to and function in 1000Base-X mode, so just
+	 * print a warning and allow such modules, as they may have some chance
+	 * of working.
+	 */
+	if (iface == PHY_INTERFACE_MODE_SGMII)
+		dev_warn(&phydev->mdio.dev, "module may not function if 1000Base-X not supported\n");
+	else if (iface != PHY_INTERFACE_MODE_1000BASEX)
+		return -EINVAL;
+
+	return 0;
+}
+
+static const struct sfp_upstream_ops at8031_sfp_ops = {
+	.attach = phy_sfp_attach,
+	.detach = phy_sfp_detach,
+	.module_insert = at8031_sfp_insert,
+};
+
+static int at8031_parse_dt(struct phy_device *phydev)
+{
+	struct device_node *node = phydev->mdio.dev.of_node;
+	struct at803x_priv *priv = phydev->priv;
+	int ret;
+
+	if (of_property_read_bool(node, "qca,keep-pll-enabled"))
+		priv->flags |= AT803X_KEEP_PLL_ENABLED;
+
+	ret = at8031_register_regulators(phydev);
+	if (ret < 0)
+		return ret;
+
+	ret = devm_regulator_get_enable_optional(&phydev->mdio.dev,
+						 "vddio");
+	if (ret) {
+		phydev_err(phydev, "failed to get VDDIO regulator\n");
+		return ret;
+	}
+
+	/* Only AR8031/8033 support 1000Base-X for SFP modules */
+	return phy_sfp_probe(phydev, &at8031_sfp_ops);
+}
+
+static int at8031_probe(struct phy_device *phydev)
+{
+	struct at803x_priv *priv = phydev->priv;
+	int mode_cfg;
+	int ccr;
+	int ret;
+
+	ret = at803x_probe(phydev);
+	if (ret)
+		return ret;
+
+	/* Only supported on AR8031/AR8033, the AR8030/AR8035 use strapping
+	 * options.
+	 */
+	ret = at8031_parse_dt(phydev);
+	if (ret)
+		return ret;
+
+	ccr = phy_read(phydev, AT803X_REG_CHIP_CONFIG);
+	if (ccr < 0)
+		return ccr;
+	mode_cfg = ccr & AT803X_MODE_CFG_MASK;
+
+	switch (mode_cfg) {
+	case AT803X_MODE_CFG_BX1000_RGMII_50OHM:
+	case AT803X_MODE_CFG_BX1000_RGMII_75OHM:
+		priv->is_1000basex = true;
+		fallthrough;
+	case AT803X_MODE_CFG_FX100_RGMII_50OHM:
+	case AT803X_MODE_CFG_FX100_RGMII_75OHM:
+		priv->is_fiber = true;
+		break;
+	}
+
+	/* Disable WoL in 1588 register which is enabled
+	 * by default
+	 */
+	return phy_modify_mmd(phydev, MDIO_MMD_PCS,
+			      AT803X_PHY_MMD3_WOL_CTRL,
+			      AT803X_WOL_EN, 0);
+}
+
+static int at8031_config_init(struct phy_device *phydev)
+{
+	struct at803x_priv *priv = phydev->priv;
+	int ret;
+
+	/* Some bootloaders leave the fiber page selected.
+	 * Switch to the appropriate page (fiber or copper), as otherwise we
+	 * read the PHY capabilities from the wrong page.
+	 */
+	phy_lock_mdio_bus(phydev);
+	ret = at803x_write_page(phydev,
+				priv->is_fiber ? AT803X_PAGE_FIBER :
+						 AT803X_PAGE_COPPER);
+	phy_unlock_mdio_bus(phydev);
+	if (ret)
+		return ret;
+
+	ret = at8031_pll_config(phydev);
+	if (ret < 0)
+		return ret;
+
+	return at803x_config_init(phydev);
+}
+
+static int at8031_set_wol(struct phy_device *phydev,
+			  struct ethtool_wolinfo *wol)
+{
+	int ret;
+
+	/* First setup MAC address and enable WOL interrupt */
+	ret = at803x_set_wol(phydev, wol);
+	if (ret)
+		return ret;
+
+	if (wol->wolopts & WAKE_MAGIC)
+		/* Enable WOL function for 1588 */
+		ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
+				     AT803X_PHY_MMD3_WOL_CTRL,
+				     0, AT803X_WOL_EN);
+	else
+		/* Disable WoL function for 1588 */
+		ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
+				     AT803X_PHY_MMD3_WOL_CTRL,
+				     AT803X_WOL_EN, 0);
+
+	return ret;
+}
+
+static int at8031_config_intr(struct phy_device *phydev)
+{
+	struct at803x_priv *priv = phydev->priv;
+	int err, value = 0;
+
+	if (phydev->interrupts == PHY_INTERRUPT_ENABLED &&
+	    priv->is_fiber) {
+		/* Clear any pending interrupts */
+		err = at803x_ack_interrupt(phydev);
+		if (err)
+			return err;
+
+		value |= AT803X_INTR_ENABLE_LINK_FAIL_BX;
+		value |= AT803X_INTR_ENABLE_LINK_SUCCESS_BX;
+
+		err = phy_set_bits(phydev, AT803X_INTR_ENABLE, value);
+		if (err)
+			return err;
+	}
+
+	return at803x_config_intr(phydev);
+}
+
+/* AR8031 and AR8033 share the same read status logic */
+static int at8031_read_status(struct phy_device *phydev)
+{
+	struct at803x_priv *priv = phydev->priv;
+
+	if (priv->is_1000basex)
+		return genphy_c37_read_status(phydev);
 
+	return at803x_read_status(phydev);
+}
+
+/* AR8031 and AR8035 share the same cable test get status reg */
+static int at8031_cable_test_get_status(struct phy_device *phydev,
+					bool *finished)
+{
+	return at803x_cable_test_get_status(phydev, finished, 0xf);
+}
+
+/* AR8031 and AR8035 share the same cable test start logic */
+static int at8031_cable_test_start(struct phy_device *phydev)
+{
+	at803x_cable_test_autoneg(phydev);
+	phy_write(phydev, MII_CTRL1000, 0);
 	/* we do all the (time consuming) work later */
 	return 0;
 }
 
+/* AR8032, AR9331 and QCA9561 share the same cable test get status reg */
+static int at8032_cable_test_get_status(struct phy_device *phydev,
+					bool *finished)
+{
+	return at803x_cable_test_get_status(phydev, finished, 0x3);
+}
+
+static int at8035_parse_dt(struct phy_device *phydev)
+{
+	struct at803x_priv *priv = phydev->priv;
+
+	/* Mask is set by the generic at803x_parse_dt
+	 * if property is set. Assume property is set
+	 * with the mask not zero.
+	 */
+	if (priv->clk_25m_mask) {
+		/* Fixup for the AR8030/AR8035. This chip has another mask and
+		 * doesn't support the DSP reference. Eg. the lowest bit of the
+		 * mask. The upper two bits select the same frequencies. Mask
+		 * the lowest bit here.
+		 *
+		 * Warning:
+		 *   There was no datasheet for the AR8030 available so this is
+		 *   just a guess. But the AR8035 is listed as pin compatible
+		 *   to the AR8030 so there might be a good chance it works on
+		 *   the AR8030 too.
+		 */
+		priv->clk_25m_reg &= AT8035_CLK_OUT_MASK;
+		priv->clk_25m_mask &= AT8035_CLK_OUT_MASK;
+	}
+
+	return 0;
+}
+
+/* AR8030 and AR8035 shared the same special mask for clk_25m */
+static int at8035_probe(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = at803x_probe(phydev);
+	if (ret)
+		return ret;
+
+	return at8035_parse_dt(phydev);
+}
+
 static int qca83xx_config_init(struct phy_device *phydev)
 {
 	u8 switch_revision;
@@ -1616,27 +1712,26 @@ static int qca83xx_config_init(struct phy_device *phydev)
 		break;
 	}
 
+	/* Following original QCA sourcecode set port to prefer master */
+	phy_set_bits(phydev, MII_CTRL1000, CTL1000_PREFER_MASTER);
+
+	return 0;
+}
+
+static int qca8327_config_init(struct phy_device *phydev)
+{
 	/* QCA8327 require DAC amplitude adjustment for 100m set to +6%.
 	 * Disable on init and enable only with 100m speed following
 	 * qca original source code.
 	 */
-	if (phydev->drv->phy_id == QCA8327_A_PHY_ID ||
-	    phydev->drv->phy_id == QCA8327_B_PHY_ID)
-		at803x_debug_reg_mask(phydev, AT803X_DEBUG_ANALOG_TEST_CTRL,
-				      QCA8327_DEBUG_MANU_CTRL_EN, 0);
+	at803x_debug_reg_mask(phydev, AT803X_DEBUG_ANALOG_TEST_CTRL,
+			      QCA8327_DEBUG_MANU_CTRL_EN, 0);
 
-	/* Following original QCA sourcecode set port to prefer master */
-	phy_set_bits(phydev, MII_CTRL1000, CTL1000_PREFER_MASTER);
-
-	return 0;
+	return qca83xx_config_init(phydev);
 }
 
 static void qca83xx_link_change_notify(struct phy_device *phydev)
 {
-	/* QCA8337 doesn't require DAC Amplitude adjustement */
-	if (phydev->drv->phy_id == QCA8337_PHY_ID)
-		return;
-
 	/* Set DAC Amplitude adjustment to +6% for 100m on link running */
 	if (phydev->state == PHY_RUNNING) {
 		if (phydev->speed == SPEED_100)
@@ -1672,26 +1767,13 @@ static int qca83xx_resume(struct phy_device *phydev)
 	if (ret)
 		return ret;
 
-	msleep(1);
+	usleep_range(1000, 2000);
 
 	return 0;
 }
 
 static int qca83xx_suspend(struct phy_device *phydev)
 {
-	u16 mask = 0;
-
-	/* Only QCA8337 support actual suspend.
-	 * QCA8327 cause port unreliability when phy suspend
-	 * is set.
-	 */
-	if (phydev->drv->phy_id == QCA8337_PHY_ID) {
-		genphy_suspend(phydev);
-	} else {
-		mask |= ~(BMCR_SPEED1000 | BMCR_FULLDPLX);
-		phy_modify(phydev, MII_BMCR, mask, 0);
-	}
-
 	at803x_debug_reg_mask(phydev, AT803X_DEBUG_REG_GREEN,
 			      AT803X_DEBUG_GATE_CLK_IN1000, 0);
 
@@ -1702,6 +1784,27 @@ static int qca83xx_suspend(struct phy_device *phydev)
 	return 0;
 }
 
+static int qca8337_suspend(struct phy_device *phydev)
+{
+	/* Only QCA8337 support actual suspend. */
+	genphy_suspend(phydev);
+
+	return qca83xx_suspend(phydev);
+}
+
+static int qca8327_suspend(struct phy_device *phydev)
+{
+	u16 mask = 0;
+
+	/* QCA8327 cause port unreliability when phy suspend
+	 * is set.
+	 */
+	mask |= ~(BMCR_SPEED1000 | BMCR_FULLDPLX);
+	phy_modify(phydev, MII_BMCR, mask, 0);
+
+	return qca83xx_suspend(phydev);
+}
+
 static int qca808x_phy_fast_retrain_config(struct phy_device *phydev)
 {
 	int ret;
@@ -1712,27 +1815,27 @@ static int qca808x_phy_fast_retrain_config(struct phy_device *phydev)
 		return ret;
 
 	phy_write_mmd(phydev, MDIO_MMD_AN, QCA808X_PHY_MMD7_TOP_OPTION1,
-			QCA808X_TOP_OPTION1_DATA);
+		      QCA808X_TOP_OPTION1_DATA);
 	phy_write_mmd(phydev, MDIO_MMD_PMAPMD, QCA808X_PHY_MMD1_MSE_THRESHOLD_20DB,
-			QCA808X_MSE_THRESHOLD_20DB_VALUE);
+		      QCA808X_MSE_THRESHOLD_20DB_VALUE);
 	phy_write_mmd(phydev, MDIO_MMD_PMAPMD, QCA808X_PHY_MMD1_MSE_THRESHOLD_17DB,
-			QCA808X_MSE_THRESHOLD_17DB_VALUE);
+		      QCA808X_MSE_THRESHOLD_17DB_VALUE);
 	phy_write_mmd(phydev, MDIO_MMD_PMAPMD, QCA808X_PHY_MMD1_MSE_THRESHOLD_27DB,
-			QCA808X_MSE_THRESHOLD_27DB_VALUE);
+		      QCA808X_MSE_THRESHOLD_27DB_VALUE);
 	phy_write_mmd(phydev, MDIO_MMD_PMAPMD, QCA808X_PHY_MMD1_MSE_THRESHOLD_28DB,
-			QCA808X_MSE_THRESHOLD_28DB_VALUE);
+		      QCA808X_MSE_THRESHOLD_28DB_VALUE);
 	phy_write_mmd(phydev, MDIO_MMD_PCS, QCA808X_PHY_MMD3_DEBUG_1,
-			QCA808X_MMD3_DEBUG_1_VALUE);
+		      QCA808X_MMD3_DEBUG_1_VALUE);
 	phy_write_mmd(phydev, MDIO_MMD_PCS, QCA808X_PHY_MMD3_DEBUG_4,
-			QCA808X_MMD3_DEBUG_4_VALUE);
+		      QCA808X_MMD3_DEBUG_4_VALUE);
 	phy_write_mmd(phydev, MDIO_MMD_PCS, QCA808X_PHY_MMD3_DEBUG_5,
-			QCA808X_MMD3_DEBUG_5_VALUE);
+		      QCA808X_MMD3_DEBUG_5_VALUE);
 	phy_write_mmd(phydev, MDIO_MMD_PCS, QCA808X_PHY_MMD3_DEBUG_3,
-			QCA808X_MMD3_DEBUG_3_VALUE);
+		      QCA808X_MMD3_DEBUG_3_VALUE);
 	phy_write_mmd(phydev, MDIO_MMD_PCS, QCA808X_PHY_MMD3_DEBUG_6,
-			QCA808X_MMD3_DEBUG_6_VALUE);
+		      QCA808X_MMD3_DEBUG_6_VALUE);
 	phy_write_mmd(phydev, MDIO_MMD_PCS, QCA808X_PHY_MMD3_DEBUG_2,
-			QCA808X_MMD3_DEBUG_2_VALUE);
+		      QCA808X_MMD3_DEBUG_2_VALUE);
 
 	return 0;
 }
@@ -1769,13 +1872,14 @@ static int qca808x_config_init(struct phy_device *phydev)
 
 	/* Active adc&vga on 802.3az for the link 1000M and 100M */
 	ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, QCA808X_PHY_MMD3_ADDR_CLD_CTRL7,
-			QCA808X_8023AZ_AFE_CTRL_MASK, QCA808X_8023AZ_AFE_EN);
+			     QCA808X_8023AZ_AFE_CTRL_MASK, QCA808X_8023AZ_AFE_EN);
 	if (ret)
 		return ret;
 
 	/* Adjust the threshold on 802.3az for the link 1000M */
 	ret = phy_write_mmd(phydev, MDIO_MMD_PCS,
-			QCA808X_PHY_MMD3_AZ_TRAINING_CTRL, QCA808X_MMD3_AZ_TRAINING_VAL);
+			    QCA808X_PHY_MMD3_AZ_TRAINING_CTRL,
+			    QCA808X_MMD3_AZ_TRAINING_VAL);
 	if (ret)
 		return ret;
 
@@ -1801,11 +1905,13 @@ static int qca808x_config_init(struct phy_device *phydev)
 
 	/* Configure adc threshold as 100mv for the link 10M */
 	return at803x_debug_reg_mask(phydev, QCA808X_PHY_DEBUG_ADC_THRESHOLD,
-			QCA808X_ADC_THRESHOLD_MASK, QCA808X_ADC_THRESHOLD_100MV);
+				     QCA808X_ADC_THRESHOLD_MASK,
+				     QCA808X_ADC_THRESHOLD_100MV);
 }
 
 static int qca808x_read_status(struct phy_device *phydev)
 {
+	struct at803x_ss_mask ss_mask = { 0 };
 	int ret;
 
 	ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_10GBT_STAT);
@@ -1813,13 +1919,16 @@ static int qca808x_read_status(struct phy_device *phydev)
 		return ret;
 
 	linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, phydev->lp_advertising,
-			ret & MDIO_AN_10GBT_STAT_LP2_5G);
+			 ret & MDIO_AN_10GBT_STAT_LP2_5G);
 
 	ret = genphy_read_status(phydev);
 	if (ret)
 		return ret;
 
-	ret = at803x_read_specific_status(phydev);
+	/* qca8081 takes the different bits for speed value from at803x */
+	ss_mask.speed_mask = QCA808X_SS_SPEED_MASK;
+	ss_mask.speed_shift = __bf_shf(QCA808X_SS_SPEED_MASK);
+	ret = at803x_read_specific_status(phydev, ss_mask);
 	if (ret < 0)
 		return ret;
 
@@ -1840,7 +1949,7 @@ static int qca808x_read_status(struct phy_device *phydev)
 		 */
 		if (qca808x_has_fast_retrain_or_slave_seed(phydev)) {
 			if (phydev->master_slave_state == MASTER_SLAVE_STATE_ERR ||
-					qca808x_is_prefer_master(phydev)) {
+			    qca808x_is_prefer_master(phydev)) {
 				qca808x_phy_ms_seed_enable(phydev, false);
 			} else {
 				qca808x_phy_ms_seed_enable(phydev, true);
@@ -1868,8 +1977,17 @@ static int qca808x_soft_reset(struct phy_device *phydev)
 static bool qca808x_cdt_fault_length_valid(int cdt_code)
 {
 	switch (cdt_code) {
-	case QCA808X_CDT_STATUS_STAT_SHORT:
-	case QCA808X_CDT_STATUS_STAT_OPEN:
+	case QCA808X_CDT_STATUS_STAT_SAME_SHORT:
+	case QCA808X_CDT_STATUS_STAT_SAME_OPEN:
+	case QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI1_SAME_NORMAL:
+	case QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI1_SAME_OPEN:
+	case QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI1_SAME_SHORT:
+	case QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI2_SAME_NORMAL:
+	case QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI2_SAME_OPEN:
+	case QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI2_SAME_SHORT:
+	case QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI3_SAME_NORMAL:
+	case QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI3_SAME_OPEN:
+	case QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI3_SAME_SHORT:
 		return true;
 	default:
 		return false;
@@ -1881,17 +1999,28 @@ static int qca808x_cable_test_result_trans(int cdt_code)
 	switch (cdt_code) {
 	case QCA808X_CDT_STATUS_STAT_NORMAL:
 		return ETHTOOL_A_CABLE_RESULT_CODE_OK;
-	case QCA808X_CDT_STATUS_STAT_SHORT:
+	case QCA808X_CDT_STATUS_STAT_SAME_SHORT:
 		return ETHTOOL_A_CABLE_RESULT_CODE_SAME_SHORT;
-	case QCA808X_CDT_STATUS_STAT_OPEN:
+	case QCA808X_CDT_STATUS_STAT_SAME_OPEN:
 		return ETHTOOL_A_CABLE_RESULT_CODE_OPEN;
+	case QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI1_SAME_NORMAL:
+	case QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI1_SAME_OPEN:
+	case QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI1_SAME_SHORT:
+	case QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI2_SAME_NORMAL:
+	case QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI2_SAME_OPEN:
+	case QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI2_SAME_SHORT:
+	case QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI3_SAME_NORMAL:
+	case QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI3_SAME_OPEN:
+	case QCA808X_CDT_STATUS_STAT_CROSS_SHORT_WITH_MDI3_SAME_SHORT:
+		return ETHTOOL_A_CABLE_RESULT_CODE_CROSS_SHORT;
 	case QCA808X_CDT_STATUS_STAT_FAIL:
 	default:
 		return ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC;
 	}
 }
 
-static int qca808x_cdt_fault_length(struct phy_device *phydev, int pair)
+static int qca808x_cdt_fault_length(struct phy_device *phydev, int pair,
+				    int result)
 {
 	int val;
 	u32 cdt_length_reg = 0;
@@ -1917,7 +2046,12 @@ static int qca808x_cdt_fault_length(struct phy_device *phydev, int pair)
 	if (val < 0)
 		return val;
 
-	return (FIELD_GET(QCA808X_CDT_DIAG_LENGTH, val) * 824) / 10;
+	if (result == ETHTOOL_A_CABLE_RESULT_CODE_SAME_SHORT)
+		val = FIELD_GET(QCA808X_CDT_DIAG_LENGTH_SAME_SHORT, val);
+	else
+		val = FIELD_GET(QCA808X_CDT_DIAG_LENGTH_CROSS_SHORT, val);
+
+	return at803x_cdt_fault_length(val);
 }
 
 static int qca808x_cable_test_start(struct phy_device *phydev)
@@ -1961,18 +2095,53 @@ static int qca808x_cable_test_start(struct phy_device *phydev)
 	return 0;
 }
 
+static int qca808x_cable_test_get_pair_status(struct phy_device *phydev, u8 pair,
+					      u16 status)
+{
+	int length, result;
+	u16 pair_code;
+
+	switch (pair) {
+	case ETHTOOL_A_CABLE_PAIR_A:
+		pair_code = FIELD_GET(QCA808X_CDT_CODE_PAIR_A, status);
+		break;
+	case ETHTOOL_A_CABLE_PAIR_B:
+		pair_code = FIELD_GET(QCA808X_CDT_CODE_PAIR_B, status);
+		break;
+	case ETHTOOL_A_CABLE_PAIR_C:
+		pair_code = FIELD_GET(QCA808X_CDT_CODE_PAIR_C, status);
+		break;
+	case ETHTOOL_A_CABLE_PAIR_D:
+		pair_code = FIELD_GET(QCA808X_CDT_CODE_PAIR_D, status);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	result = qca808x_cable_test_result_trans(pair_code);
+	ethnl_cable_test_result(phydev, pair, result);
+
+	if (qca808x_cdt_fault_length_valid(pair_code)) {
+		length = qca808x_cdt_fault_length(phydev, pair, result);
+		ethnl_cable_test_fault_length(phydev, pair, length);
+	}
+
+	return 0;
+}
+
 static int qca808x_cable_test_get_status(struct phy_device *phydev, bool *finished)
 {
 	int ret, val;
-	int pair_a, pair_b, pair_c, pair_d;
 
 	*finished = false;
 
-	ret = at803x_cdt_start(phydev, 0);
+	val = QCA808X_CDT_ENABLE_TEST |
+	      QCA808X_CDT_LENGTH_UNIT;
+	ret = at803x_cdt_start(phydev, val);
 	if (ret)
 		return ret;
 
-	ret = at803x_cdt_wait_for_completion(phydev);
+	ret = at803x_cdt_wait_for_completion(phydev, QCA808X_CDT_ENABLE_TEST);
 	if (ret)
 		return ret;
 
@@ -1980,32 +2149,21 @@ static int qca808x_cable_test_get_status(struct phy_device *phydev, bool *finish
 	if (val < 0)
 		return val;
 
-	pair_a = FIELD_GET(QCA808X_CDT_CODE_PAIR_A, val);
-	pair_b = FIELD_GET(QCA808X_CDT_CODE_PAIR_B, val);
-	pair_c = FIELD_GET(QCA808X_CDT_CODE_PAIR_C, val);
-	pair_d = FIELD_GET(QCA808X_CDT_CODE_PAIR_D, val);
-
-	ethnl_cable_test_result(phydev, ETHTOOL_A_CABLE_PAIR_A,
-				qca808x_cable_test_result_trans(pair_a));
-	ethnl_cable_test_result(phydev, ETHTOOL_A_CABLE_PAIR_B,
-				qca808x_cable_test_result_trans(pair_b));
-	ethnl_cable_test_result(phydev, ETHTOOL_A_CABLE_PAIR_C,
-				qca808x_cable_test_result_trans(pair_c));
-	ethnl_cable_test_result(phydev, ETHTOOL_A_CABLE_PAIR_D,
-				qca808x_cable_test_result_trans(pair_d));
-
-	if (qca808x_cdt_fault_length_valid(pair_a))
-		ethnl_cable_test_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_A,
-				qca808x_cdt_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_A));
-	if (qca808x_cdt_fault_length_valid(pair_b))
-		ethnl_cable_test_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_B,
-				qca808x_cdt_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_B));
-	if (qca808x_cdt_fault_length_valid(pair_c))
-		ethnl_cable_test_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_C,
-				qca808x_cdt_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_C));
-	if (qca808x_cdt_fault_length_valid(pair_d))
-		ethnl_cable_test_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_D,
-				qca808x_cdt_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_D));
+	ret = qca808x_cable_test_get_pair_status(phydev, ETHTOOL_A_CABLE_PAIR_A, val);
+	if (ret)
+		return ret;
+
+	ret = qca808x_cable_test_get_pair_status(phydev, ETHTOOL_A_CABLE_PAIR_B, val);
+	if (ret)
+		return ret;
+
+	ret = qca808x_cable_test_get_pair_status(phydev, ETHTOOL_A_CABLE_PAIR_C, val);
+	if (ret)
+		return ret;
+
+	ret = qca808x_cable_test_get_pair_status(phydev, ETHTOOL_A_CABLE_PAIR_D, val);
+	if (ret)
+		return ret;
 
 	*finished = true;
 
@@ -2040,14 +2198,41 @@ static int qca808x_get_features(struct phy_device *phydev)
 	return 0;
 }
 
+static int qca808x_config_aneg(struct phy_device *phydev)
+{
+	int phy_ctrl = 0;
+	int ret;
+
+	ret = at803x_prepare_config_aneg(phydev);
+	if (ret)
+		return ret;
+
+	/* The reg MII_BMCR also needs to be configured for force mode, the
+	 * genphy_config_aneg is also needed.
+	 */
+	if (phydev->autoneg == AUTONEG_DISABLE)
+		genphy_c45_pma_setup_forced(phydev);
+
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, phydev->advertising))
+		phy_ctrl = MDIO_AN_10GBT_CTRL_ADV2_5G;
+
+	ret = phy_modify_mmd_changed(phydev, MDIO_MMD_AN, MDIO_AN_10GBT_CTRL,
+				     MDIO_AN_10GBT_CTRL_ADV2_5G, phy_ctrl);
+	if (ret < 0)
+		return ret;
+
+	return __genphy_config_aneg(phydev, ret);
+}
+
 static void qca808x_link_change_notify(struct phy_device *phydev)
 {
 	/* Assert interface sgmii fifo on link down, deassert it on link up,
 	 * the interface device address is always phy address added by 1.
 	 */
 	mdiobus_c45_modify_changed(phydev->mdio.bus, phydev->mdio.addr + 1,
-			MDIO_MMD_PMAPMD, QCA8081_PHY_SERDES_MMD1_FIFO_CTRL,
-			QCA8081_PHY_FIFO_RSTN, phydev->link ? QCA8081_PHY_FIFO_RSTN : 0);
+				   MDIO_MMD_PMAPMD, QCA8081_PHY_SERDES_MMD1_FIFO_CTRL,
+				   QCA8081_PHY_FIFO_RSTN,
+				   phydev->link ? QCA8081_PHY_FIFO_RSTN : 0);
 }
 
 static struct phy_driver at803x_driver[] = {
@@ -2056,7 +2241,7 @@ static struct phy_driver at803x_driver[] = {
 	PHY_ID_MATCH_EXACT(ATH8035_PHY_ID),
 	.name			= "Qualcomm Atheros AR8035",
 	.flags			= PHY_POLL_CABLE_TEST,
-	.probe			= at803x_probe,
+	.probe			= at8035_probe,
 	.config_aneg		= at803x_config_aneg,
 	.config_init		= at803x_config_init,
 	.soft_reset		= genphy_soft_reset,
@@ -2070,14 +2255,14 @@ static struct phy_driver at803x_driver[] = {
 	.handle_interrupt	= at803x_handle_interrupt,
 	.get_tunable		= at803x_get_tunable,
 	.set_tunable		= at803x_set_tunable,
-	.cable_test_start	= at803x_cable_test_start,
-	.cable_test_get_status	= at803x_cable_test_get_status,
+	.cable_test_start	= at8031_cable_test_start,
+	.cable_test_get_status	= at8031_cable_test_get_status,
 }, {
 	/* Qualcomm Atheros AR8030 */
 	.phy_id			= ATH8030_PHY_ID,
 	.name			= "Qualcomm Atheros AR8030",
 	.phy_id_mask		= AT8030_PHY_ID_MASK,
-	.probe			= at803x_probe,
+	.probe			= at8035_probe,
 	.config_init		= at803x_config_init,
 	.link_change_notify	= at803x_link_change_notify,
 	.set_wol		= at803x_set_wol,
@@ -2092,24 +2277,24 @@ static struct phy_driver at803x_driver[] = {
 	PHY_ID_MATCH_EXACT(ATH8031_PHY_ID),
 	.name			= "Qualcomm Atheros AR8031/AR8033",
 	.flags			= PHY_POLL_CABLE_TEST,
-	.probe			= at803x_probe,
-	.config_init		= at803x_config_init,
+	.probe			= at8031_probe,
+	.config_init		= at8031_config_init,
 	.config_aneg		= at803x_config_aneg,
 	.soft_reset		= genphy_soft_reset,
-	.set_wol		= at803x_set_wol,
+	.set_wol		= at8031_set_wol,
 	.get_wol		= at803x_get_wol,
 	.suspend		= at803x_suspend,
 	.resume			= at803x_resume,
 	.read_page		= at803x_read_page,
 	.write_page		= at803x_write_page,
 	.get_features		= at803x_get_features,
-	.read_status		= at803x_read_status,
-	.config_intr		= &at803x_config_intr,
+	.read_status		= at8031_read_status,
+	.config_intr		= at8031_config_intr,
 	.handle_interrupt	= at803x_handle_interrupt,
 	.get_tunable		= at803x_get_tunable,
 	.set_tunable		= at803x_set_tunable,
-	.cable_test_start	= at803x_cable_test_start,
-	.cable_test_get_status	= at803x_cable_test_get_status,
+	.cable_test_start	= at8031_cable_test_start,
+	.cable_test_get_status	= at8031_cable_test_get_status,
 }, {
 	/* Qualcomm Atheros AR8032 */
 	PHY_ID_MATCH_EXACT(ATH8032_PHY_ID),
@@ -2124,7 +2309,7 @@ static struct phy_driver at803x_driver[] = {
 	.config_intr		= at803x_config_intr,
 	.handle_interrupt	= at803x_handle_interrupt,
 	.cable_test_start	= at803x_cable_test_start,
-	.cable_test_get_status	= at803x_cable_test_get_status,
+	.cable_test_get_status	= at8032_cable_test_get_status,
 }, {
 	/* ATHEROS AR9331 */
 	PHY_ID_MATCH_EXACT(ATH9331_PHY_ID),
@@ -2134,10 +2319,10 @@ static struct phy_driver at803x_driver[] = {
 	.resume			= at803x_resume,
 	.flags			= PHY_POLL_CABLE_TEST,
 	/* PHY_BASIC_FEATURES */
-	.config_intr		= &at803x_config_intr,
+	.config_intr		= at803x_config_intr,
 	.handle_interrupt	= at803x_handle_interrupt,
 	.cable_test_start	= at803x_cable_test_start,
-	.cable_test_get_status	= at803x_cable_test_get_status,
+	.cable_test_get_status	= at8032_cable_test_get_status,
 	.read_status		= at803x_read_status,
 	.soft_reset		= genphy_soft_reset,
 	.config_aneg		= at803x_config_aneg,
@@ -2150,10 +2335,10 @@ static struct phy_driver at803x_driver[] = {
 	.resume			= at803x_resume,
 	.flags			= PHY_POLL_CABLE_TEST,
 	/* PHY_BASIC_FEATURES */
-	.config_intr		= &at803x_config_intr,
+	.config_intr		= at803x_config_intr,
 	.handle_interrupt	= at803x_handle_interrupt,
 	.cable_test_start	= at803x_cable_test_start,
-	.cable_test_get_status	= at803x_cable_test_get_status,
+	.cable_test_get_status	= at8032_cable_test_get_status,
 	.read_status		= at803x_read_status,
 	.soft_reset		= genphy_soft_reset,
 	.config_aneg		= at803x_config_aneg,
@@ -2163,15 +2348,14 @@ static struct phy_driver at803x_driver[] = {
 	.phy_id_mask		= QCA8K_PHY_ID_MASK,
 	.name			= "Qualcomm Atheros 8337 internal PHY",
 	/* PHY_GBIT_FEATURES */
-	.link_change_notify	= qca83xx_link_change_notify,
 	.probe			= at803x_probe,
 	.flags			= PHY_IS_INTERNAL,
 	.config_init		= qca83xx_config_init,
 	.soft_reset		= genphy_soft_reset,
-	.get_sset_count		= at803x_get_sset_count,
-	.get_strings		= at803x_get_strings,
-	.get_stats		= at803x_get_stats,
-	.suspend		= qca83xx_suspend,
+	.get_sset_count		= qca83xx_get_sset_count,
+	.get_strings		= qca83xx_get_strings,
+	.get_stats		= qca83xx_get_stats,
+	.suspend		= qca8337_suspend,
 	.resume			= qca83xx_resume,
 }, {
 	/* QCA8327-A from switch QCA8327-AL1A */
@@ -2182,12 +2366,12 @@ static struct phy_driver at803x_driver[] = {
 	.link_change_notify	= qca83xx_link_change_notify,
 	.probe			= at803x_probe,
 	.flags			= PHY_IS_INTERNAL,
-	.config_init		= qca83xx_config_init,
+	.config_init		= qca8327_config_init,
 	.soft_reset		= genphy_soft_reset,
-	.get_sset_count		= at803x_get_sset_count,
-	.get_strings		= at803x_get_strings,
-	.get_stats		= at803x_get_stats,
-	.suspend		= qca83xx_suspend,
+	.get_sset_count		= qca83xx_get_sset_count,
+	.get_strings		= qca83xx_get_strings,
+	.get_stats		= qca83xx_get_stats,
+	.suspend		= qca8327_suspend,
 	.resume			= qca83xx_resume,
 }, {
 	/* QCA8327-B from switch QCA8327-BL1A */
@@ -2198,12 +2382,12 @@ static struct phy_driver at803x_driver[] = {
 	.link_change_notify	= qca83xx_link_change_notify,
 	.probe			= at803x_probe,
 	.flags			= PHY_IS_INTERNAL,
-	.config_init		= qca83xx_config_init,
+	.config_init		= qca8327_config_init,
 	.soft_reset		= genphy_soft_reset,
-	.get_sset_count		= at803x_get_sset_count,
-	.get_strings		= at803x_get_strings,
-	.get_stats		= at803x_get_stats,
-	.suspend		= qca83xx_suspend,
+	.get_sset_count		= qca83xx_get_sset_count,
+	.get_strings		= qca83xx_get_strings,
+	.get_stats		= qca83xx_get_stats,
+	.suspend		= qca8327_suspend,
 	.resume			= qca83xx_resume,
 }, {
 	/* Qualcomm QCA8081 */
@@ -2218,7 +2402,7 @@ static struct phy_driver at803x_driver[] = {
 	.set_wol		= at803x_set_wol,
 	.get_wol		= at803x_get_wol,
 	.get_features		= qca808x_get_features,
-	.config_aneg		= at803x_config_aneg,
+	.config_aneg		= qca808x_config_aneg,
 	.suspend		= genphy_suspend,
 	.resume			= genphy_resume,
 	.read_status		= qca808x_read_status,
diff --git a/drivers/net/phy/ax88796b_rust.rs b/drivers/net/phy/ax88796b_rust.rs
new file mode 100644
index 000000000000..5c92572962dc
--- /dev/null
+++ b/drivers/net/phy/ax88796b_rust.rs
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2023 FUJITA Tomonori <fujita.tomonori@gmail.com>
+
+//! Rust Asix PHYs driver
+//!
+//! C version of this driver: [`drivers/net/phy/ax88796b.c`](./ax88796b.c)
+use kernel::{
+    c_str,
+    net::phy::{self, DeviceId, Driver},
+    prelude::*,
+    uapi,
+};
+
+kernel::module_phy_driver! {
+    drivers: [PhyAX88772A, PhyAX88772C, PhyAX88796B],
+    device_table: [
+        DeviceId::new_with_driver::<PhyAX88772A>(),
+        DeviceId::new_with_driver::<PhyAX88772C>(),
+        DeviceId::new_with_driver::<PhyAX88796B>()
+    ],
+    name: "rust_asix_phy",
+    author: "FUJITA Tomonori <fujita.tomonori@gmail.com>",
+    description: "Rust Asix PHYs driver",
+    license: "GPL",
+}
+
+const MII_BMCR: u16 = uapi::MII_BMCR as u16;
+const BMCR_SPEED100: u16 = uapi::BMCR_SPEED100 as u16;
+const BMCR_FULLDPLX: u16 = uapi::BMCR_FULLDPLX as u16;
+
+// Performs a software PHY reset using the standard
+// BMCR_RESET bit and poll for the reset bit to be cleared.
+// Toggle BMCR_RESET bit off to accommodate broken AX8796B PHY implementation
+// such as used on the Individual Computers' X-Surf 100 Zorro card.
+fn asix_soft_reset(dev: &mut phy::Device) -> Result {
+    dev.write(uapi::MII_BMCR as u16, 0)?;
+    dev.genphy_soft_reset()
+}
+
+struct PhyAX88772A;
+
+#[vtable]
+impl Driver for PhyAX88772A {
+    const FLAGS: u32 = phy::flags::IS_INTERNAL;
+    const NAME: &'static CStr = c_str!("Asix Electronics AX88772A");
+    const PHY_DEVICE_ID: DeviceId = DeviceId::new_with_exact_mask(0x003b1861);
+
+    // AX88772A is not working properly with some old switches (NETGEAR EN 108TP):
+    // after autoneg is done and the link status is reported as active, the MII_LPA
+    // register is 0. This issue is not reproducible on AX88772C.
+    fn read_status(dev: &mut phy::Device) -> Result<u16> {
+        dev.genphy_update_link()?;
+        if !dev.is_link_up() {
+            return Ok(0);
+        }
+        // If MII_LPA is 0, phy_resolve_aneg_linkmode() will fail to resolve
+        // linkmode so use MII_BMCR as default values.
+        let ret = dev.read(MII_BMCR)?;
+
+        if ret & BMCR_SPEED100 != 0 {
+            dev.set_speed(uapi::SPEED_100);
+        } else {
+            dev.set_speed(uapi::SPEED_10);
+        }
+
+        let duplex = if ret & BMCR_FULLDPLX != 0 {
+            phy::DuplexMode::Full
+        } else {
+            phy::DuplexMode::Half
+        };
+        dev.set_duplex(duplex);
+
+        dev.genphy_read_lpa()?;
+
+        if dev.is_autoneg_enabled() && dev.is_autoneg_completed() {
+            dev.resolve_aneg_linkmode();
+        }
+
+        Ok(0)
+    }
+
+    fn suspend(dev: &mut phy::Device) -> Result {
+        dev.genphy_suspend()
+    }
+
+    fn resume(dev: &mut phy::Device) -> Result {
+        dev.genphy_resume()
+    }
+
+    fn soft_reset(dev: &mut phy::Device) -> Result {
+        asix_soft_reset(dev)
+    }
+
+    fn link_change_notify(dev: &mut phy::Device) {
+        // Reset PHY, otherwise MII_LPA will provide outdated information.
+        // This issue is reproducible only with some link partner PHYs.
+        if dev.state() == phy::DeviceState::NoLink {
+            let _ = dev.init_hw();
+            let _ = dev.start_aneg();
+        }
+    }
+}
+
+struct PhyAX88772C;
+
+#[vtable]
+impl Driver for PhyAX88772C {
+    const FLAGS: u32 = phy::flags::IS_INTERNAL;
+    const NAME: &'static CStr = c_str!("Asix Electronics AX88772C");
+    const PHY_DEVICE_ID: DeviceId = DeviceId::new_with_exact_mask(0x003b1881);
+
+    fn suspend(dev: &mut phy::Device) -> Result {
+        dev.genphy_suspend()
+    }
+
+    fn resume(dev: &mut phy::Device) -> Result {
+        dev.genphy_resume()
+    }
+
+    fn soft_reset(dev: &mut phy::Device) -> Result {
+        asix_soft_reset(dev)
+    }
+}
+
+struct PhyAX88796B;
+
+#[vtable]
+impl Driver for PhyAX88796B {
+    const NAME: &'static CStr = c_str!("Asix Electronics AX88796B");
+    const PHY_DEVICE_ID: DeviceId = DeviceId::new_with_model_mask(0x003b1841);
+
+    fn soft_reset(dev: &mut phy::Device) -> Result {
+        asix_soft_reset(dev)
+    }
+}
diff --git a/drivers/net/phy/bcm-phy-ptp.c b/drivers/net/phy/bcm-phy-ptp.c
index cb4b91af5e17..617d384d4551 100644
--- a/drivers/net/phy/bcm-phy-ptp.c
+++ b/drivers/net/phy/bcm-phy-ptp.c
@@ -782,16 +782,13 @@ out:
 }
 
 static int bcm_ptp_hwtstamp(struct mii_timestamper *mii_ts,
-			    struct ifreq *ifr)
+			    struct kernel_hwtstamp_config *cfg,
+			    struct netlink_ext_ack *extack)
 {
 	struct bcm_ptp_private *priv = mii2priv(mii_ts);
-	struct hwtstamp_config cfg;
 	u16 mode, ctrl;
 
-	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
-		return -EFAULT;
-
-	switch (cfg.rx_filter) {
+	switch (cfg->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		priv->hwts_rx = false;
 		break;
@@ -804,14 +801,14 @@ static int bcm_ptp_hwtstamp(struct mii_timestamper *mii_ts,
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		priv->hwts_rx = true;
 		break;
 	default:
 		return -ERANGE;
 	}
 
-	priv->tx_type = cfg.tx_type;
+	priv->tx_type = cfg->tx_type;
 
 	ctrl  = priv->hwts_rx ? SLICE_RX_EN : 0;
 	ctrl |= priv->tx_type != HWTSTAMP_TX_OFF ? SLICE_TX_EN : 0;
@@ -840,7 +837,7 @@ static int bcm_ptp_hwtstamp(struct mii_timestamper *mii_ts,
 	/* purge existing data */
 	skb_queue_purge(&priv->tx_queue);
 
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	return 0;
 }
 
 static int bcm_ptp_ts_info(struct mii_timestamper *mii_ts,
diff --git a/drivers/net/phy/bcm54140.c b/drivers/net/phy/bcm54140.c
index d43076592f81..2eea3d09b1e6 100644
--- a/drivers/net/phy/bcm54140.c
+++ b/drivers/net/phy/bcm54140.c
@@ -128,6 +128,10 @@
 #define BCM54140_DEFAULT_DOWNSHIFT 5
 #define BCM54140_MAX_DOWNSHIFT 9
 
+enum bcm54140_global_phy {
+	BCM54140_BASE_ADDR = 0,
+};
+
 struct bcm54140_priv {
 	int port;
 	int base_addr;
@@ -429,11 +433,13 @@ static int bcm54140_base_read_rdb(struct phy_device *phydev, u16 rdb)
 	int ret;
 
 	phy_lock_mdio_bus(phydev);
-	ret = __phy_package_write(phydev, MII_BCM54XX_RDB_ADDR, rdb);
+	ret = __phy_package_write(phydev, BCM54140_BASE_ADDR,
+				  MII_BCM54XX_RDB_ADDR, rdb);
 	if (ret < 0)
 		goto out;
 
-	ret = __phy_package_read(phydev, MII_BCM54XX_RDB_DATA);
+	ret = __phy_package_read(phydev, BCM54140_BASE_ADDR,
+				 MII_BCM54XX_RDB_DATA);
 
 out:
 	phy_unlock_mdio_bus(phydev);
@@ -446,11 +452,13 @@ static int bcm54140_base_write_rdb(struct phy_device *phydev,
 	int ret;
 
 	phy_lock_mdio_bus(phydev);
-	ret = __phy_package_write(phydev, MII_BCM54XX_RDB_ADDR, rdb);
+	ret = __phy_package_write(phydev, BCM54140_BASE_ADDR,
+				  MII_BCM54XX_RDB_ADDR, rdb);
 	if (ret < 0)
 		goto out;
 
-	ret = __phy_package_write(phydev, MII_BCM54XX_RDB_DATA, val);
+	ret = __phy_package_write(phydev, BCM54140_BASE_ADDR,
+				  MII_BCM54XX_RDB_DATA, val);
 
 out:
 	phy_unlock_mdio_bus(phydev);
diff --git a/drivers/net/phy/bcm84881.c b/drivers/net/phy/bcm84881.c
index 9717a1626f3f..f1d47c264058 100644
--- a/drivers/net/phy/bcm84881.c
+++ b/drivers/net/phy/bcm84881.c
@@ -29,8 +29,19 @@ static int bcm84881_wait_init(struct phy_device *phydev)
 					 100000, 2000000, false);
 }
 
+static void bcm84881_fill_possible_interfaces(struct phy_device *phydev)
+{
+	unsigned long *possible = phydev->possible_interfaces;
+
+	__set_bit(PHY_INTERFACE_MODE_SGMII, possible);
+	__set_bit(PHY_INTERFACE_MODE_2500BASEX, possible);
+	__set_bit(PHY_INTERFACE_MODE_10GBASER, possible);
+}
+
 static int bcm84881_config_init(struct phy_device *phydev)
 {
+	bcm84881_fill_possible_interfaces(phydev);
+
 	switch (phydev->interface) {
 	case PHY_INTERFACE_MODE_SGMII:
 	case PHY_INTERFACE_MODE_2500BASEX:
@@ -39,6 +50,7 @@ static int bcm84881_config_init(struct phy_device *phydev)
 	default:
 		return -ENODEV;
 	}
+
 	return 0;
 }
 
diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 3a627105675a..312a8bb35d78 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -1135,6 +1135,8 @@ static struct phy_driver broadcom_drivers[] = {
 	.handle_interrupt = bcm_phy_handle_interrupt,
 	.link_change_notify	= bcm54xx_link_change_notify,
 	.led_brightness_set	= bcm_phy_led_brightness_set,
+	.suspend	= bcm54xx_suspend,
+	.resume		= bcm54xx_resume,
 }, {
 	.phy_id		= PHY_ID_BCM54616S,
 	.phy_id_mask	= 0xfffffff0,
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 2657be7cc049..5c42c47dc564 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -1207,22 +1207,20 @@ static irqreturn_t dp83640_handle_interrupt(struct phy_device *phydev)
 	return IRQ_HANDLED;
 }
 
-static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
+static int dp83640_hwtstamp(struct mii_timestamper *mii_ts,
+			    struct kernel_hwtstamp_config *cfg,
+			    struct netlink_ext_ack *extack)
 {
 	struct dp83640_private *dp83640 =
 		container_of(mii_ts, struct dp83640_private, mii_ts);
-	struct hwtstamp_config cfg;
 	u16 txcfg0, rxcfg0;
 
-	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
-		return -EFAULT;
-
-	if (cfg.tx_type < 0 || cfg.tx_type > HWTSTAMP_TX_ONESTEP_SYNC)
+	if (cfg->tx_type < 0 || cfg->tx_type > HWTSTAMP_TX_ONESTEP_SYNC)
 		return -ERANGE;
 
-	dp83640->hwts_tx_en = cfg.tx_type;
+	dp83640->hwts_tx_en = cfg->tx_type;
 
-	switch (cfg.rx_filter) {
+	switch (cfg->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		dp83640->hwts_rx_en = 0;
 		dp83640->layer = 0;
@@ -1234,7 +1232,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L4;
 		dp83640->version = PTP_CLASS_V1;
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
@@ -1242,7 +1240,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L4;
 		dp83640->version = PTP_CLASS_V2;
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
@@ -1250,7 +1248,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L2;
 		dp83640->version = PTP_CLASS_V2;
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
@@ -1258,7 +1256,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L4 | PTP_CLASS_L2;
 		dp83640->version = PTP_CLASS_V2;
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		break;
 	default:
 		return -ERANGE;
@@ -1292,7 +1290,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 
 	mutex_unlock(&dp83640->clock->extreg_lock);
 
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	return 0;
 }
 
 static void rx_timestamp_work(struct work_struct *work)
diff --git a/drivers/net/phy/dp83tg720.c b/drivers/net/phy/dp83tg720.c
new file mode 100644
index 000000000000..326c9770a6dc
--- /dev/null
+++ b/drivers/net/phy/dp83tg720.c
@@ -0,0 +1,188 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Driver for the Texas Instruments DP83TG720 PHY
+ * Copyright (c) 2023 Pengutronix, Oleksij Rempel <kernel@pengutronix.de>
+ */
+#include <linux/bitfield.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/phy.h>
+
+#define DP83TG720S_PHY_ID			0x2000a284
+
+/* MDIO_MMD_VEND2 registers */
+#define DP83TG720S_MII_REG_10			0x10
+#define DP83TG720S_STS_MII_INT			BIT(7)
+#define DP83TG720S_LINK_STATUS			BIT(0)
+
+#define DP83TG720S_PHY_RESET			0x1f
+#define DP83TG720S_HW_RESET			BIT(15)
+
+#define DP83TG720S_RGMII_DELAY_CTRL		0x602
+/* In RGMII mode, Enable or disable the internal delay for RXD */
+#define DP83TG720S_RGMII_RX_CLK_SEL		BIT(1)
+/* In RGMII mode, Enable or disable the internal delay for TXD */
+#define DP83TG720S_RGMII_TX_CLK_SEL		BIT(0)
+
+#define DP83TG720S_SQI_REG_1			0x871
+#define DP83TG720S_SQI_OUT_WORST		GENMASK(7, 5)
+#define DP83TG720S_SQI_OUT			GENMASK(3, 1)
+
+#define DP83TG720_SQI_MAX			7
+
+static int dp83tg720_config_aneg(struct phy_device *phydev)
+{
+	/* Autoneg is not supported and this PHY supports only one speed.
+	 * We need to care only about master/slave configuration if it was
+	 * changed by user.
+	 */
+	return genphy_c45_pma_baset1_setup_master_slave(phydev);
+}
+
+static int dp83tg720_read_status(struct phy_device *phydev)
+{
+	u16 phy_sts;
+	int ret;
+
+	phydev->pause = 0;
+	phydev->asym_pause = 0;
+
+	/* Most of Clause 45 registers are not present, so we can't use
+	 * genphy_c45_read_status() here.
+	 */
+	phy_sts = phy_read(phydev, DP83TG720S_MII_REG_10);
+	phydev->link = !!(phy_sts & DP83TG720S_LINK_STATUS);
+	if (!phydev->link) {
+		/* According to the "DP83TC81x, DP83TG72x Software
+		 * Implementation Guide", the PHY needs to be reset after a
+		 * link loss or if no link is created after at least 100ms.
+		 *
+		 * Currently we are polling with the PHY_STATE_TIME (1000ms)
+		 * interval, which is still enough for not automotive use cases.
+		 */
+		ret = phy_init_hw(phydev);
+		if (ret)
+			return ret;
+
+		/* After HW reset we need to restore master/slave configuration.
+		 */
+		ret = dp83tg720_config_aneg(phydev);
+		if (ret)
+			return ret;
+
+		phydev->speed = SPEED_UNKNOWN;
+		phydev->duplex = DUPLEX_UNKNOWN;
+	} else {
+		/* PMA/PMD control 1 register (Register 1.0) is present, but it
+		 * doesn't contain the link speed information.
+		 * So genphy_c45_read_pma() can't be used here.
+		 */
+		ret = genphy_c45_pma_baset1_read_master_slave(phydev);
+		if (ret)
+			return ret;
+
+		phydev->duplex = DUPLEX_FULL;
+		phydev->speed = SPEED_1000;
+	}
+
+	return 0;
+}
+
+static int dp83tg720_get_sqi(struct phy_device *phydev)
+{
+	int ret;
+
+	if (!phydev->link)
+		return 0;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_SQI_REG_1);
+	if (ret < 0)
+		return ret;
+
+	return FIELD_GET(DP83TG720S_SQI_OUT, ret);
+}
+
+static int dp83tg720_get_sqi_max(struct phy_device *phydev)
+{
+	return DP83TG720_SQI_MAX;
+}
+
+static int dp83tg720_config_rgmii_delay(struct phy_device *phydev)
+{
+	u16 rgmii_delay_mask;
+	u16 rgmii_delay = 0;
+
+	switch (phydev->interface) {
+	case PHY_INTERFACE_MODE_RGMII:
+		rgmii_delay = 0;
+		break;
+	case PHY_INTERFACE_MODE_RGMII_ID:
+		rgmii_delay = DP83TG720S_RGMII_RX_CLK_SEL |
+				DP83TG720S_RGMII_TX_CLK_SEL;
+		break;
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+		rgmii_delay = DP83TG720S_RGMII_RX_CLK_SEL;
+		break;
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+		rgmii_delay = DP83TG720S_RGMII_TX_CLK_SEL;
+		break;
+	default:
+		return 0;
+	}
+
+	rgmii_delay_mask = DP83TG720S_RGMII_RX_CLK_SEL |
+		DP83TG720S_RGMII_TX_CLK_SEL;
+
+	return phy_modify_mmd(phydev, MDIO_MMD_VEND2,
+			      DP83TG720S_RGMII_DELAY_CTRL, rgmii_delay_mask,
+			      rgmii_delay);
+}
+
+static int dp83tg720_config_init(struct phy_device *phydev)
+{
+	int ret;
+
+	/* Software Restart is not enough to recover from a link failure.
+	 * Using Hardware Reset instead.
+	 */
+	ret = phy_write(phydev, DP83TG720S_PHY_RESET, DP83TG720S_HW_RESET);
+	if (ret)
+		return ret;
+
+	/* Wait until MDC can be used again.
+	 * The wait value of one 1ms is documented in "DP83TG720S-Q1 1000BASE-T1
+	 * Automotive Ethernet PHY with SGMII and RGMII" datasheet.
+	 */
+	usleep_range(1000, 2000);
+
+	if (phy_interface_is_rgmii(phydev))
+		return dp83tg720_config_rgmii_delay(phydev);
+
+	return 0;
+}
+
+static struct phy_driver dp83tg720_driver[] = {
+{
+	PHY_ID_MATCH_MODEL(DP83TG720S_PHY_ID),
+	.name		= "TI DP83TG720S",
+
+	.config_aneg	= dp83tg720_config_aneg,
+	.read_status	= dp83tg720_read_status,
+	.get_features	= genphy_c45_pma_read_ext_abilities,
+	.config_init	= dp83tg720_config_init,
+	.get_sqi	= dp83tg720_get_sqi,
+	.get_sqi_max	= dp83tg720_get_sqi_max,
+
+	.suspend	= genphy_suspend,
+	.resume		= genphy_resume,
+} };
+module_phy_driver(dp83tg720_driver);
+
+static struct mdio_device_id __maybe_unused dp83tg720_tbl[] = {
+	{ PHY_ID_MATCH_MODEL(DP83TG720S_PHY_ID) },
+	{ }
+};
+MODULE_DEVICE_TABLE(mdio, dp83tg720_tbl);
+
+MODULE_DESCRIPTION("Texas Instruments DP83TG720S PHY driver");
+MODULE_AUTHOR("Oleksij Rempel <kernel@pengutronix.de>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c
index d4bb90d76881..ad43e280930c 100644
--- a/drivers/net/phy/marvell10g.c
+++ b/drivers/net/phy/marvell10g.c
@@ -141,13 +141,21 @@ enum {
 	MV_V2_TEMP_UNKNOWN	= 0x9600, /* unknown function */
 };
 
+struct mv3310_mactype {
+	bool valid;
+	bool fixed_interface;
+	phy_interface_t interface_10g;
+};
+
 struct mv3310_chip {
 	bool (*has_downshift)(struct phy_device *phydev);
 	void (*init_supported_interfaces)(unsigned long *mask);
 	int (*get_mactype)(struct phy_device *phydev);
 	int (*set_mactype)(struct phy_device *phydev, int mactype);
 	int (*select_mactype)(unsigned long *interfaces);
-	int (*init_interface)(struct phy_device *phydev, int mactype);
+
+	const struct mv3310_mactype *mactypes;
+	size_t n_mactypes;
 
 #ifdef CONFIG_HWMON
 	int (*hwmon_read_temp_reg)(struct phy_device *phydev);
@@ -156,11 +164,10 @@ struct mv3310_chip {
 
 struct mv3310_priv {
 	DECLARE_BITMAP(supported_interfaces, PHY_INTERFACE_MODE_MAX);
+	const struct mv3310_mactype *mactype;
 
 	u32 firmware_ver;
 	bool has_downshift;
-	bool rate_match;
-	phy_interface_t const_interface;
 
 	struct device *hwmon_dev;
 	char *hwmon_name;
@@ -702,70 +709,114 @@ static int mv3310_select_mactype(unsigned long *interfaces)
 		return -1;
 }
 
-static int mv2110_init_interface(struct phy_device *phydev, int mactype)
-{
-	struct mv3310_priv *priv = dev_get_drvdata(&phydev->mdio.dev);
-
-	priv->rate_match = false;
-
-	if (mactype == MV_PMA_21X0_PORT_CTRL_MACTYPE_10GBASER_RATE_MATCH)
-		priv->rate_match = true;
-
-	if (mactype == MV_PMA_21X0_PORT_CTRL_MACTYPE_USXGMII)
-		priv->const_interface = PHY_INTERFACE_MODE_USXGMII;
-	else if (mactype == MV_PMA_21X0_PORT_CTRL_MACTYPE_10GBASER_RATE_MATCH)
-		priv->const_interface = PHY_INTERFACE_MODE_10GBASER;
-	else if (mactype == MV_PMA_21X0_PORT_CTRL_MACTYPE_5GBASER ||
-		 mactype == MV_PMA_21X0_PORT_CTRL_MACTYPE_5GBASER_NO_SGMII_AN)
-		priv->const_interface = PHY_INTERFACE_MODE_NA;
-	else
-		return -EINVAL;
-
-	return 0;
-}
-
-static int mv3310_init_interface(struct phy_device *phydev, int mactype)
-{
-	struct mv3310_priv *priv = dev_get_drvdata(&phydev->mdio.dev);
+static const struct mv3310_mactype mv2110_mactypes[] = {
+	[MV_PMA_21X0_PORT_CTRL_MACTYPE_USXGMII] = {
+		.valid = true,
+		.fixed_interface = true,
+		.interface_10g = PHY_INTERFACE_MODE_USXGMII,
+	},
+	[MV_PMA_21X0_PORT_CTRL_MACTYPE_5GBASER] = {
+		.valid = true,
+		.interface_10g = PHY_INTERFACE_MODE_NA,
+	},
+	[MV_PMA_21X0_PORT_CTRL_MACTYPE_5GBASER_NO_SGMII_AN] = {
+		.valid = true,
+		.interface_10g = PHY_INTERFACE_MODE_NA,
+	},
+	[MV_PMA_21X0_PORT_CTRL_MACTYPE_10GBASER_RATE_MATCH] = {
+		.valid = true,
+		.fixed_interface = true,
+		.interface_10g = PHY_INTERFACE_MODE_10GBASER,
+	},
+};
 
-	priv->rate_match = false;
-
-	if (mactype == MV_V2_33X0_PORT_CTRL_MACTYPE_10GBASER_RATE_MATCH ||
-	    mactype == MV_V2_33X0_PORT_CTRL_MACTYPE_RXAUI_RATE_MATCH ||
-	    mactype == MV_V2_3310_PORT_CTRL_MACTYPE_XAUI_RATE_MATCH)
-		priv->rate_match = true;
-
-	if (mactype == MV_V2_33X0_PORT_CTRL_MACTYPE_USXGMII)
-		priv->const_interface = PHY_INTERFACE_MODE_USXGMII;
-	else if (mactype == MV_V2_33X0_PORT_CTRL_MACTYPE_10GBASER_RATE_MATCH ||
-		 mactype == MV_V2_33X0_PORT_CTRL_MACTYPE_10GBASER_NO_SGMII_AN ||
-		 mactype == MV_V2_33X0_PORT_CTRL_MACTYPE_10GBASER)
-		priv->const_interface = PHY_INTERFACE_MODE_10GBASER;
-	else if (mactype == MV_V2_33X0_PORT_CTRL_MACTYPE_RXAUI_RATE_MATCH ||
-		 mactype == MV_V2_33X0_PORT_CTRL_MACTYPE_RXAUI)
-		priv->const_interface = PHY_INTERFACE_MODE_RXAUI;
-	else if (mactype == MV_V2_3310_PORT_CTRL_MACTYPE_XAUI_RATE_MATCH ||
-		 mactype == MV_V2_3310_PORT_CTRL_MACTYPE_XAUI)
-		priv->const_interface = PHY_INTERFACE_MODE_XAUI;
-	else
-		return -EINVAL;
+static const struct mv3310_mactype mv3310_mactypes[] = {
+	[MV_V2_33X0_PORT_CTRL_MACTYPE_RXAUI] = {
+		.valid = true,
+		.interface_10g = PHY_INTERFACE_MODE_RXAUI,
+	},
+	[MV_V2_3310_PORT_CTRL_MACTYPE_XAUI_RATE_MATCH] = {
+		.valid = true,
+		.fixed_interface = true,
+		.interface_10g = PHY_INTERFACE_MODE_XAUI,
+	},
+	[MV_V2_33X0_PORT_CTRL_MACTYPE_RXAUI_RATE_MATCH] = {
+		.valid = true,
+		.fixed_interface = true,
+		.interface_10g = PHY_INTERFACE_MODE_RXAUI,
+	},
+	[MV_V2_3310_PORT_CTRL_MACTYPE_XAUI] = {
+		.valid = true,
+		.interface_10g = PHY_INTERFACE_MODE_XAUI,
+	},
+	[MV_V2_33X0_PORT_CTRL_MACTYPE_10GBASER] = {
+		.valid = true,
+		.interface_10g = PHY_INTERFACE_MODE_10GBASER,
+	},
+	[MV_V2_33X0_PORT_CTRL_MACTYPE_10GBASER_NO_SGMII_AN] = {
+		.valid = true,
+		.interface_10g = PHY_INTERFACE_MODE_10GBASER,
+	},
+	[MV_V2_33X0_PORT_CTRL_MACTYPE_10GBASER_RATE_MATCH] = {
+		.valid = true,
+		.fixed_interface = true,
+		.interface_10g = PHY_INTERFACE_MODE_10GBASER,
+	},
+	[MV_V2_33X0_PORT_CTRL_MACTYPE_USXGMII] = {
+		.valid = true,
+		.fixed_interface = true,
+		.interface_10g = PHY_INTERFACE_MODE_USXGMII,
+	},
+};
 
-	return 0;
-}
+static const struct mv3310_mactype mv3340_mactypes[] = {
+	[MV_V2_33X0_PORT_CTRL_MACTYPE_RXAUI] = {
+		.valid = true,
+		.interface_10g = PHY_INTERFACE_MODE_RXAUI,
+	},
+	[MV_V2_3340_PORT_CTRL_MACTYPE_RXAUI_NO_SGMII_AN] = {
+		.valid = true,
+		.interface_10g = PHY_INTERFACE_MODE_RXAUI,
+	},
+	[MV_V2_33X0_PORT_CTRL_MACTYPE_RXAUI_RATE_MATCH] = {
+		.valid = true,
+		.fixed_interface = true,
+		.interface_10g = PHY_INTERFACE_MODE_RXAUI,
+	},
+	[MV_V2_33X0_PORT_CTRL_MACTYPE_10GBASER] = {
+		.valid = true,
+		.interface_10g = PHY_INTERFACE_MODE_10GBASER,
+	},
+	[MV_V2_33X0_PORT_CTRL_MACTYPE_10GBASER_NO_SGMII_AN] = {
+		.valid = true,
+		.interface_10g = PHY_INTERFACE_MODE_10GBASER,
+	},
+	[MV_V2_33X0_PORT_CTRL_MACTYPE_10GBASER_RATE_MATCH] = {
+		.valid = true,
+		.fixed_interface = true,
+		.interface_10g = PHY_INTERFACE_MODE_10GBASER,
+	},
+	[MV_V2_33X0_PORT_CTRL_MACTYPE_USXGMII] = {
+		.valid = true,
+		.fixed_interface = true,
+		.interface_10g = PHY_INTERFACE_MODE_USXGMII,
+	},
+};
 
-static int mv3340_init_interface(struct phy_device *phydev, int mactype)
+static void mv3310_fill_possible_interfaces(struct phy_device *phydev)
 {
 	struct mv3310_priv *priv = dev_get_drvdata(&phydev->mdio.dev);
-	int err = 0;
-
-	priv->rate_match = false;
+	unsigned long *possible = phydev->possible_interfaces;
+	const struct mv3310_mactype *mactype = priv->mactype;
 
-	if (mactype == MV_V2_3340_PORT_CTRL_MACTYPE_RXAUI_NO_SGMII_AN)
-		priv->const_interface = PHY_INTERFACE_MODE_RXAUI;
-	else
-		err = mv3310_init_interface(phydev, mactype);
+	if (mactype->interface_10g != PHY_INTERFACE_MODE_NA)
+		__set_bit(priv->mactype->interface_10g, possible);
 
-	return err;
+	if (!mactype->fixed_interface) {
+		__set_bit(PHY_INTERFACE_MODE_5GBASER, possible);
+		__set_bit(PHY_INTERFACE_MODE_2500BASEX, possible);
+		__set_bit(PHY_INTERFACE_MODE_SGMII, possible);
+	}
 }
 
 static int mv3310_config_init(struct phy_device *phydev)
@@ -803,12 +854,15 @@ static int mv3310_config_init(struct phy_device *phydev)
 	if (mactype < 0)
 		return mactype;
 
-	err = chip->init_interface(phydev, mactype);
-	if (err) {
+	if (mactype >= chip->n_mactypes || !chip->mactypes[mactype].valid) {
 		phydev_err(phydev, "MACTYPE configuration invalid\n");
-		return err;
+		return -EINVAL;
 	}
 
+	priv->mactype = &chip->mactypes[mactype];
+
+	mv3310_fill_possible_interfaces(phydev);
+
 	/* Enable EDPD mode - saving 600mW */
 	err = mv3310_set_edpd(phydev, ETHTOOL_PHY_EDPD_DFLT_TX_MSECS);
 	if (err)
@@ -935,9 +989,8 @@ static void mv3310_update_interface(struct phy_device *phydev)
 	 *
 	 * In USXGMII mode the PHY interface mode is also fixed.
 	 */
-	if (priv->rate_match ||
-	    priv->const_interface == PHY_INTERFACE_MODE_USXGMII) {
-		phydev->interface = priv->const_interface;
+	if (priv->mactype->fixed_interface) {
+		phydev->interface = priv->mactype->interface_10g;
 		return;
 	}
 
@@ -949,7 +1002,7 @@ static void mv3310_update_interface(struct phy_device *phydev)
 	 */
 	switch (phydev->speed) {
 	case SPEED_10000:
-		phydev->interface = priv->const_interface;
+		phydev->interface = priv->mactype->interface_10g;
 		break;
 	case SPEED_5000:
 		phydev->interface = PHY_INTERFACE_MODE_5GBASER;
@@ -1163,7 +1216,9 @@ static const struct mv3310_chip mv3310_type = {
 	.get_mactype = mv3310_get_mactype,
 	.set_mactype = mv3310_set_mactype,
 	.select_mactype = mv3310_select_mactype,
-	.init_interface = mv3310_init_interface,
+
+	.mactypes = mv3310_mactypes,
+	.n_mactypes = ARRAY_SIZE(mv3310_mactypes),
 
 #ifdef CONFIG_HWMON
 	.hwmon_read_temp_reg = mv3310_hwmon_read_temp_reg,
@@ -1176,7 +1231,9 @@ static const struct mv3310_chip mv3340_type = {
 	.get_mactype = mv3310_get_mactype,
 	.set_mactype = mv3310_set_mactype,
 	.select_mactype = mv3310_select_mactype,
-	.init_interface = mv3340_init_interface,
+
+	.mactypes = mv3340_mactypes,
+	.n_mactypes = ARRAY_SIZE(mv3340_mactypes),
 
 #ifdef CONFIG_HWMON
 	.hwmon_read_temp_reg = mv3310_hwmon_read_temp_reg,
@@ -1188,7 +1245,9 @@ static const struct mv3310_chip mv2110_type = {
 	.get_mactype = mv2110_get_mactype,
 	.set_mactype = mv2110_set_mactype,
 	.select_mactype = mv2110_select_mactype,
-	.init_interface = mv2110_init_interface,
+
+	.mactypes = mv2110_mactypes,
+	.n_mactypes = ARRAY_SIZE(mv2110_mactypes),
 
 #ifdef CONFIG_HWMON
 	.hwmon_read_temp_reg = mv2110_hwmon_read_temp_reg,
@@ -1200,7 +1259,9 @@ static const struct mv3310_chip mv2111_type = {
 	.get_mactype = mv2110_get_mactype,
 	.set_mactype = mv2110_set_mactype,
 	.select_mactype = mv2110_select_mactype,
-	.init_interface = mv2110_init_interface,
+
+	.mactypes = mv2110_mactypes,
+	.n_mactypes = ARRAY_SIZE(mv2110_mactypes),
 
 #ifdef CONFIG_HWMON
 	.hwmon_read_temp_reg = mv2110_hwmon_read_temp_reg,
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 25dcaa49ab8b..afbad1ad8683 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -193,6 +193,10 @@ static void mdiobus_release(struct device *d)
 	     bus->state != MDIOBUS_ALLOCATED,
 	     "%s: not in RELEASED or ALLOCATED state\n",
 	     bus->id);
+
+	if (bus->state == MDIOBUS_RELEASED)
+		fwnode_handle_put(dev_fwnode(d));
+
 	kfree(bus);
 }
 
@@ -506,7 +510,7 @@ static int mdiobus_create_device(struct mii_bus *bus,
 	if (IS_ERR(mdiodev))
 		return -ENODEV;
 
-	strncpy(mdiodev->modalias, bi->modalias,
+	strscpy(mdiodev->modalias, bi->modalias,
 		sizeof(mdiodev->modalias));
 	mdiodev->bus_match = mdio_device_bus_match;
 	mdiodev->dev.platform_data = (void *)bi->platform_data;
@@ -684,6 +688,15 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner)
 	bus->dev.groups = NULL;
 	dev_set_name(&bus->dev, "%s", bus->id);
 
+	/* If the bus state is allocated, we're registering a fresh bus
+	 * that may have a fwnode associated with it. Grab a reference
+	 * to the fwnode. This will be dropped when the bus is released.
+	 * If the bus was set to unregistered, it means that the bus was
+	 * previously registered, and we've already grabbed a reference.
+	 */
+	if (bus->state == MDIOBUS_ALLOCATED)
+		fwnode_handle_get(dev_fwnode(&bus->dev));
+
 	/* We need to set state to MDIOBUS_UNREGISTERED to correctly release
 	 * the device in mdiobus_free()
 	 *
diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c
index 044828d081d2..73f6539b9e50 100644
--- a/drivers/net/phy/mdio_device.c
+++ b/drivers/net/phy/mdio_device.c
@@ -62,6 +62,7 @@ struct mdio_device *mdio_device_create(struct mii_bus *bus, int addr)
 	mdiodev->device_remove = mdio_device_remove;
 	mdiodev->bus = bus;
 	mdiodev->addr = addr;
+	mdiodev->reset_state = -1;
 
 	dev_set_name(&mdiodev->dev, PHY_ID_FMT, bus->id, addr);
 
@@ -122,6 +123,9 @@ void mdio_device_reset(struct mdio_device *mdiodev, int value)
 	if (!mdiodev->reset_gpio && !mdiodev->reset_ctrl)
 		return;
 
+	if (mdiodev->reset_state == value)
+		return;
+
 	if (mdiodev->reset_gpio)
 		gpiod_set_value_cansleep(mdiodev->reset_gpio, value);
 
@@ -135,6 +139,8 @@ void mdio_device_reset(struct mdio_device *mdiodev, int value)
 	d = value ? mdiodev->reset_assert_delay : mdiodev->reset_deassert_delay;
 	if (d)
 		fsleep(d);
+
+	mdiodev->reset_state = value;
 }
 EXPORT_SYMBOL(mdio_device_reset);
 
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 08e3915001c3..d2aa3d0695e3 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -2001,7 +2001,7 @@ static int kszphy_probe(struct phy_device *phydev)
 
 	kszphy_parse_led_mode(phydev);
 
-	clk = devm_clk_get(&phydev->mdio.dev, "rmii-ref");
+	clk = devm_clk_get_optional_enabled(&phydev->mdio.dev, "rmii-ref");
 	/* NOTE: clk may be NULL if building without CONFIG_HAVE_CLK */
 	if (!IS_ERR_OR_NULL(clk)) {
 		unsigned long rate = clk_get_rate(clk);
@@ -2021,6 +2021,11 @@ static int kszphy_probe(struct phy_device *phydev)
 				   rate);
 			return -EINVAL;
 		}
+	} else if (!clk) {
+		/* unnamed clock from the generic ethernet-phy binding */
+		clk = devm_clk_get_optional_enabled(&phydev->mdio.dev, NULL);
+		if (IS_ERR(clk))
+			return PTR_ERR(clk);
 	}
 
 	if (ksz8041_fiber_mode(phydev))
@@ -2395,24 +2400,22 @@ static void lan8814_flush_fifo(struct phy_device *phydev, bool egress)
 	lanphy_read_page_reg(phydev, 5, PTP_TSU_INT_STS);
 }
 
-static int lan8814_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
+static int lan8814_hwtstamp(struct mii_timestamper *mii_ts,
+			    struct kernel_hwtstamp_config *config,
+			    struct netlink_ext_ack *extack)
 {
 	struct kszphy_ptp_priv *ptp_priv =
 			  container_of(mii_ts, struct kszphy_ptp_priv, mii_ts);
 	struct phy_device *phydev = ptp_priv->phydev;
 	struct lan8814_shared_priv *shared = phydev->shared->priv;
 	struct lan8814_ptp_rx_ts *rx_ts, *tmp;
-	struct hwtstamp_config config;
 	int txcfg = 0, rxcfg = 0;
 	int pkt_ts_enable;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
+	ptp_priv->hwts_tx_type = config->tx_type;
+	ptp_priv->rx_filter = config->rx_filter;
 
-	ptp_priv->hwts_tx_type = config.tx_type;
-	ptp_priv->rx_filter = config.rx_filter;
-
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		ptp_priv->layer = 0;
 		ptp_priv->version = 0;
@@ -2458,13 +2461,13 @@ static int lan8814_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 		lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_TX_MOD,
 				      PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_);
 
-	if (config.rx_filter != HWTSTAMP_FILTER_NONE)
+	if (config->rx_filter != HWTSTAMP_FILTER_NONE)
 		lan8814_config_ts_intr(ptp_priv->phydev, true);
 	else
 		lan8814_config_ts_intr(ptp_priv->phydev, false);
 
 	mutex_lock(&shared->shared_lock);
-	if (config.rx_filter != HWTSTAMP_FILTER_NONE)
+	if (config->rx_filter != HWTSTAMP_FILTER_NONE)
 		shared->ref++;
 	else
 		shared->ref--;
@@ -2488,7 +2491,7 @@ static int lan8814_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 	lan8814_flush_fifo(ptp_priv->phydev, false);
 	lan8814_flush_fifo(ptp_priv->phydev, true);
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? -EFAULT : 0;
+	return 0;
 }
 
 static void lan8814_txtstamp(struct mii_timestamper *mii_ts,
@@ -3631,12 +3634,8 @@ static int lan8841_ts_info(struct mii_timestamper *mii_ts,
 
 	info->phc_index = ptp_priv->ptp_clock ?
 				ptp_clock_index(ptp_priv->ptp_clock) : -1;
-	if (info->phc_index == -1) {
-		info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE |
-					 SOF_TIMESTAMPING_RX_SOFTWARE |
-					 SOF_TIMESTAMPING_SOFTWARE;
+	if (info->phc_index == -1)
 		return 0;
-	}
 
 	info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
 				SOF_TIMESTAMPING_RX_HARDWARE |
@@ -3703,21 +3702,19 @@ static void lan8841_ptp_enable_processing(struct kszphy_ptp_priv *ptp_priv,
 #define LAN8841_PTP_TX_TIMESTAMP_EN		443
 #define LAN8841_PTP_TX_MOD			445
 
-static int lan8841_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
+static int lan8841_hwtstamp(struct mii_timestamper *mii_ts,
+			    struct kernel_hwtstamp_config *config,
+			    struct netlink_ext_ack *extack)
 {
 	struct kszphy_ptp_priv *ptp_priv = container_of(mii_ts, struct kszphy_ptp_priv, mii_ts);
 	struct phy_device *phydev = ptp_priv->phydev;
-	struct hwtstamp_config config;
 	int txcfg = 0, rxcfg = 0;
 	int pkt_ts_enable;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
+	ptp_priv->hwts_tx_type = config->tx_type;
+	ptp_priv->rx_filter = config->rx_filter;
 
-	ptp_priv->hwts_tx_type = config.tx_type;
-	ptp_priv->rx_filter = config.rx_filter;
-
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		ptp_priv->layer = 0;
 		ptp_priv->version = 0;
@@ -3771,13 +3768,13 @@ static int lan8841_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 
 	/* Now enable/disable the timestamping */
 	lan8841_ptp_enable_processing(ptp_priv,
-				      config.rx_filter != HWTSTAMP_FILTER_NONE);
+				      config->rx_filter != HWTSTAMP_FILTER_NONE);
 
 	skb_queue_purge(&ptp_priv->tx_queue);
 
 	lan8841_ptp_flush_fifo(ptp_priv);
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? -EFAULT : 0;
+	return 0;
 }
 
 static bool lan8841_rxtstamp(struct mii_timestamper *mii_ts,
diff --git a/drivers/net/phy/mscc/mscc.h b/drivers/net/phy/mscc/mscc.h
index 7a962050a4d4..6a3d8a754eb8 100644
--- a/drivers/net/phy/mscc/mscc.h
+++ b/drivers/net/phy/mscc/mscc.h
@@ -416,6 +416,11 @@ struct vsc8531_private {
  * gpio_lock: used for PHC operations. Common for all PHYs as the load/save GPIO
  * is shared.
  */
+
+enum vsc85xx_global_phy {
+	VSC88XX_BASE_ADDR = 0,
+};
+
 struct vsc85xx_shared_private {
 	struct mutex gpio_lock;
 };
diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c
index 4171f01d34e5..6f74ce0ab1aa 100644
--- a/drivers/net/phy/mscc/mscc_main.c
+++ b/drivers/net/phy/mscc/mscc_main.c
@@ -711,7 +711,7 @@ int phy_base_write(struct phy_device *phydev, u32 regnum, u16 val)
 		dump_stack();
 	}
 
-	return __phy_package_write(phydev, regnum, val);
+	return __phy_package_write(phydev, VSC88XX_BASE_ADDR, regnum, val);
 }
 
 /* phydev->bus->mdio_lock should be locked when using this function */
@@ -722,7 +722,7 @@ int phy_base_read(struct phy_device *phydev, u32 regnum)
 		dump_stack();
 	}
 
-	return __phy_package_read(phydev, regnum);
+	return __phy_package_read(phydev, VSC88XX_BASE_ADDR, regnum);
 }
 
 u32 vsc85xx_csr_read(struct phy_device *phydev,
diff --git a/drivers/net/phy/mscc/mscc_ptp.c b/drivers/net/phy/mscc/mscc_ptp.c
index cf728bfd83e2..eb0b032cb613 100644
--- a/drivers/net/phy/mscc/mscc_ptp.c
+++ b/drivers/net/phy/mscc/mscc_ptp.c
@@ -1045,19 +1045,17 @@ static void vsc85xx_ts_reset_fifo(struct phy_device *phydev)
 			     val);
 }
 
-static int vsc85xx_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
+static int vsc85xx_hwtstamp(struct mii_timestamper *mii_ts,
+			    struct kernel_hwtstamp_config *cfg,
+			    struct netlink_ext_ack *extack)
 {
 	struct vsc8531_private *vsc8531 =
 		container_of(mii_ts, struct vsc8531_private, mii_ts);
 	struct phy_device *phydev = vsc8531->ptp->phydev;
-	struct hwtstamp_config cfg;
 	bool one_step = false;
 	u32 val;
 
-	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
-		return -EFAULT;
-
-	switch (cfg.tx_type) {
+	switch (cfg->tx_type) {
 	case HWTSTAMP_TX_ONESTEP_SYNC:
 		one_step = true;
 		break;
@@ -1069,9 +1067,9 @@ static int vsc85xx_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	vsc8531->ptp->tx_type = cfg.tx_type;
+	vsc8531->ptp->tx_type = cfg->tx_type;
 
-	switch (cfg.rx_filter) {
+	switch (cfg->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
@@ -1084,7 +1082,7 @@ static int vsc85xx_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	vsc8531->ptp->rx_filter = cfg.rx_filter;
+	vsc8531->ptp->rx_filter = cfg->rx_filter;
 
 	mutex_lock(&vsc8531->ts_lock);
 
@@ -1132,7 +1130,7 @@ static int vsc85xx_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 	vsc8531->ptp->configured = 1;
 	mutex_unlock(&vsc8531->ts_lock);
 
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	return 0;
 }
 
 static int vsc85xx_ts_info(struct mii_timestamper *mii_ts,
diff --git a/drivers/net/phy/nxp-c45-tja11xx-macsec.c b/drivers/net/phy/nxp-c45-tja11xx-macsec.c
new file mode 100644
index 000000000000..550ef08970f4
--- /dev/null
+++ b/drivers/net/phy/nxp-c45-tja11xx-macsec.c
@@ -0,0 +1,1729 @@
+// SPDX-License-Identifier: GPL-2.0
+/* NXP C45 PTP PHY driver interface
+ * Copyright 2023 NXP
+ * Author: Radu Pirea <radu-nicolae.pirea@oss.nxp.com>
+ */
+
+#include <linux/delay.h>
+#include <linux/ethtool_netlink.h>
+#include <linux/kernel.h>
+#include <linux/mii.h>
+#include <linux/module.h>
+#include <linux/phy.h>
+#include <linux/processor.h>
+#include <net/dst_metadata.h>
+#include <net/macsec.h>
+
+#include "nxp-c45-tja11xx.h"
+
+#define MACSEC_REG_SIZE			32
+#define TX_SC_MAX			4
+
+#define TX_SC_BIT(secy_id)		BIT(MACSEC_REG_SIZE - (secy_id) - 1)
+
+#define VEND1_MACSEC_BASE		0x9000
+
+#define MACSEC_CFG			0x0000
+#define MACSEC_CFG_BYPASS		BIT(1)
+#define MACSEC_CFG_S0I			BIT(0)
+
+#define MACSEC_TPNET			0x0044
+#define PN_WRAP_THRESHOLD		0xffffffff
+
+#define MACSEC_RXSCA			0x0080
+#define MACSEC_RXSCKA			0x0084
+
+#define MACSEC_TXSCA			0x00C0
+#define MACSEC_TXSCKA			0x00C4
+
+#define MACSEC_RXSC_SCI_1H		0x0100
+
+#define MACSEC_RXSC_CFG			0x0128
+#define MACSEC_RXSC_CFG_XPN		BIT(25)
+#define MACSEC_RXSC_CFG_AES_256		BIT(24)
+#define MACSEC_RXSC_CFG_SCI_EN		BIT(11)
+#define MACSEC_RXSC_CFG_RP		BIT(10)
+#define MACSEC_RXSC_CFG_VF_MASK		GENMASK(9, 8)
+#define MACSEC_RXSC_CFG_VF_OFF		8
+
+#define MACSEC_RPW			0x012C
+
+#define MACSEC_RXSA_A_CS		0x0180
+#define MACSEC_RXSA_A_NPN		0x0184
+#define MACSEC_RXSA_A_XNPN		0x0188
+#define MACSEC_RXSA_A_LNPN		0x018C
+#define MACSEC_RXSA_A_LXNPN		0x0190
+
+#define MACSEC_RXSA_B_CS		0x01C0
+#define MACSEC_RXSA_B_NPN		0x01C4
+#define MACSEC_RXSA_B_XNPN		0x01C8
+#define MACSEC_RXSA_B_LNPN		0x01CC
+#define MACSEC_RXSA_B_LXNPN		0x01D0
+
+#define MACSEC_RXSA_CS_AN_OFF		1
+#define MACSEC_RXSA_CS_EN		BIT(0)
+
+#define MACSEC_TXSC_SCI_1H		0x0200
+#define MACSEC_TXSC_CFG			0x0228
+#define MACSEC_TXSC_CFG_XPN		BIT(25)
+#define MACSEC_TXSC_CFG_AES_256		BIT(24)
+#define MACSEC_TXSC_CFG_AN_MASK		GENMASK(19, 18)
+#define MACSEC_TXSC_CFG_AN_OFF		18
+#define MACSEC_TXSC_CFG_ASA		BIT(17)
+#define MACSEC_TXSC_CFG_SCE		BIT(16)
+#define MACSEC_TXSC_CFG_ENCRYPT		BIT(4)
+#define MACSEC_TXSC_CFG_PROTECT		BIT(3)
+#define MACSEC_TXSC_CFG_SEND_SCI	BIT(2)
+#define MACSEC_TXSC_CFG_END_STATION	BIT(1)
+#define MACSEC_TXSC_CFG_SCB		BIT(0)
+
+#define MACSEC_TXSA_A_CS		0x0280
+#define MACSEC_TXSA_A_NPN		0x0284
+#define MACSEC_TXSA_A_XNPN		0x0288
+
+#define MACSEC_TXSA_B_CS		0x02C0
+#define MACSEC_TXSA_B_NPN		0x02C4
+#define MACSEC_TXSA_B_XNPN		0x02C8
+
+#define MACSEC_SA_CS_A			BIT(31)
+
+#define MACSEC_EVR			0x0400
+#define MACSEC_EVER			0x0404
+
+#define MACSEC_RXSA_A_KA		0x0700
+#define MACSEC_RXSA_A_SSCI		0x0720
+#define MACSEC_RXSA_A_SALT		0x0724
+
+#define MACSEC_RXSA_B_KA		0x0740
+#define MACSEC_RXSA_B_SSCI		0x0760
+#define MACSEC_RXSA_B_SALT		0x0764
+
+#define MACSEC_TXSA_A_KA		0x0780
+#define MACSEC_TXSA_A_SSCI		0x07A0
+#define MACSEC_TXSA_A_SALT		0x07A4
+
+#define MACSEC_TXSA_B_KA		0x07C0
+#define MACSEC_TXSA_B_SSCI		0x07E0
+#define MACSEC_TXSA_B_SALT		0x07E4
+
+#define MACSEC_UPFR0D2			0x0A08
+#define MACSEC_UPFR0M1			0x0A10
+#define MACSEC_OVP			BIT(12)
+
+#define	MACSEC_UPFR0M2			0x0A14
+#define ETYPE_MASK			0xffff
+
+#define MACSEC_UPFR0R			0x0A18
+#define MACSEC_UPFR_EN			BIT(0)
+
+#define ADPTR_CNTRL			0x0F00
+#define ADPTR_CNTRL_CONFIG_EN		BIT(14)
+#define ADPTR_CNTRL_ADPTR_EN		BIT(12)
+#define ADPTR_TX_TAG_CNTRL		0x0F0C
+#define ADPTR_TX_TAG_CNTRL_ENA		BIT(31)
+
+#define TX_SC_FLT_BASE			0x800
+#define TX_SC_FLT_SIZE			0x10
+#define TX_FLT_BASE(flt_id)		(TX_SC_FLT_BASE + \
+	TX_SC_FLT_SIZE * (flt_id))
+
+#define TX_SC_FLT_OFF_MAC_DA_SA		0x04
+#define TX_SC_FLT_OFF_MAC_SA		0x08
+#define TX_SC_FLT_OFF_MAC_CFG		0x0C
+#define TX_SC_FLT_BY_SA			BIT(14)
+#define TX_SC_FLT_EN			BIT(8)
+
+#define TX_SC_FLT_MAC_DA_SA(base)	((base) + TX_SC_FLT_OFF_MAC_DA_SA)
+#define TX_SC_FLT_MAC_SA(base)		((base) + TX_SC_FLT_OFF_MAC_SA)
+#define TX_SC_FLT_MAC_CFG(base)		((base) + TX_SC_FLT_OFF_MAC_CFG)
+
+#define ADAPTER_EN	BIT(6)
+#define MACSEC_EN	BIT(5)
+
+#define MACSEC_INOV1HS			0x0140
+#define MACSEC_INOV2HS			0x0144
+#define MACSEC_INOD1HS			0x0148
+#define MACSEC_INOD2HS			0x014C
+#define MACSEC_RXSCIPUS			0x0150
+#define MACSEC_RXSCIPDS			0x0154
+#define MACSEC_RXSCIPLS			0x0158
+#define MACSEC_RXAN0INUSS		0x0160
+#define MACSEC_RXAN0IPUSS		0x0170
+#define MACSEC_RXSA_A_IPOS		0x0194
+#define MACSEC_RXSA_A_IPIS		0x01B0
+#define MACSEC_RXSA_A_IPNVS		0x01B4
+#define MACSEC_RXSA_B_IPOS		0x01D4
+#define MACSEC_RXSA_B_IPIS		0x01F0
+#define MACSEC_RXSA_B_IPNVS		0x01F4
+#define MACSEC_OPUS			0x021C
+#define MACSEC_OPTLS			0x022C
+#define MACSEC_OOP1HS			0x0240
+#define MACSEC_OOP2HS			0x0244
+#define MACSEC_OOE1HS			0x0248
+#define MACSEC_OOE2HS			0x024C
+#define MACSEC_TXSA_A_OPPS		0x028C
+#define MACSEC_TXSA_A_OPES		0x0290
+#define MACSEC_TXSA_B_OPPS		0x02CC
+#define MACSEC_TXSA_B_OPES		0x02D0
+#define MACSEC_INPWTS			0x0630
+#define MACSEC_INPBTS			0x0638
+#define MACSEC_IPSNFS			0x063C
+
+#define TJA11XX_TLV_TX_NEEDED_HEADROOM	(32)
+#define TJA11XX_TLV_NEEDED_TAILROOM	(0)
+
+#define ETH_P_TJA11XX_TLV		(0x4e58)
+
+enum nxp_c45_sa_type {
+	TX_SA,
+	RX_SA,
+};
+
+struct nxp_c45_sa {
+	void *sa;
+	const struct nxp_c45_sa_regs *regs;
+	enum nxp_c45_sa_type type;
+	bool is_key_a;
+	u8 an;
+	struct list_head list;
+};
+
+struct nxp_c45_secy {
+	struct macsec_secy *secy;
+	struct macsec_rx_sc *rx_sc;
+	struct list_head sa_list;
+	int secy_id;
+	bool rx_sc0_impl;
+	struct list_head list;
+};
+
+struct nxp_c45_macsec {
+	struct list_head secy_list;
+	DECLARE_BITMAP(secy_bitmap, TX_SC_MAX);
+	DECLARE_BITMAP(tx_sc_bitmap, TX_SC_MAX);
+};
+
+struct nxp_c45_sa_regs {
+	u16 cs;
+	u16 npn;
+	u16 xnpn;
+	u16 lnpn;
+	u16 lxnpn;
+	u16 ka;
+	u16 ssci;
+	u16 salt;
+	u16 ipis;
+	u16 ipnvs;
+	u16 ipos;
+	u16 opps;
+	u16 opes;
+};
+
+static const struct nxp_c45_sa_regs rx_sa_a_regs = {
+	.cs	= MACSEC_RXSA_A_CS,
+	.npn	= MACSEC_RXSA_A_NPN,
+	.xnpn	= MACSEC_RXSA_A_XNPN,
+	.lnpn	= MACSEC_RXSA_A_LNPN,
+	.lxnpn	= MACSEC_RXSA_A_LXNPN,
+	.ka	= MACSEC_RXSA_A_KA,
+	.ssci	= MACSEC_RXSA_A_SSCI,
+	.salt	= MACSEC_RXSA_A_SALT,
+	.ipis	= MACSEC_RXSA_A_IPIS,
+	.ipnvs	= MACSEC_RXSA_A_IPNVS,
+	.ipos	= MACSEC_RXSA_A_IPOS,
+};
+
+static const struct nxp_c45_sa_regs rx_sa_b_regs = {
+	.cs	= MACSEC_RXSA_B_CS,
+	.npn	= MACSEC_RXSA_B_NPN,
+	.xnpn	= MACSEC_RXSA_B_XNPN,
+	.lnpn	= MACSEC_RXSA_B_LNPN,
+	.lxnpn	= MACSEC_RXSA_B_LXNPN,
+	.ka	= MACSEC_RXSA_B_KA,
+	.ssci	= MACSEC_RXSA_B_SSCI,
+	.salt	= MACSEC_RXSA_B_SALT,
+	.ipis	= MACSEC_RXSA_B_IPIS,
+	.ipnvs	= MACSEC_RXSA_B_IPNVS,
+	.ipos	= MACSEC_RXSA_B_IPOS,
+};
+
+static const struct nxp_c45_sa_regs tx_sa_a_regs = {
+	.cs	= MACSEC_TXSA_A_CS,
+	.npn	= MACSEC_TXSA_A_NPN,
+	.xnpn	= MACSEC_TXSA_A_XNPN,
+	.ka	= MACSEC_TXSA_A_KA,
+	.ssci	= MACSEC_TXSA_A_SSCI,
+	.salt	= MACSEC_TXSA_A_SALT,
+	.opps	= MACSEC_TXSA_A_OPPS,
+	.opes	= MACSEC_TXSA_A_OPES,
+};
+
+static const struct nxp_c45_sa_regs tx_sa_b_regs = {
+	.cs	= MACSEC_TXSA_B_CS,
+	.npn	= MACSEC_TXSA_B_NPN,
+	.xnpn	= MACSEC_TXSA_B_XNPN,
+	.ka	= MACSEC_TXSA_B_KA,
+	.ssci	= MACSEC_TXSA_B_SSCI,
+	.salt	= MACSEC_TXSA_B_SALT,
+	.opps	= MACSEC_TXSA_B_OPPS,
+	.opes	= MACSEC_TXSA_B_OPES,
+};
+
+static const
+struct nxp_c45_sa_regs *nxp_c45_sa_regs_get(enum nxp_c45_sa_type sa_type,
+					    bool key_a)
+{
+	if (sa_type == RX_SA)
+		if (key_a)
+			return &rx_sa_a_regs;
+		else
+			return &rx_sa_b_regs;
+	else if (sa_type == TX_SA)
+		if (key_a)
+			return &tx_sa_a_regs;
+		else
+			return &tx_sa_b_regs;
+	else
+		return NULL;
+}
+
+static int nxp_c45_macsec_write(struct phy_device *phydev, u16 addr, u32 value)
+{
+	u32 lvalue = value;
+	u16 laddr;
+	int ret;
+
+	WARN_ON_ONCE(addr % 4);
+
+	phydev_dbg(phydev, "write addr 0x%x value 0x%x\n", addr, value);
+
+	laddr = VEND1_MACSEC_BASE + addr / 2;
+	ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, laddr, lvalue);
+	if (ret)
+		return ret;
+
+	laddr += 1;
+	lvalue >>= 16;
+	ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, laddr, lvalue);
+
+	return ret;
+}
+
+static int nxp_c45_macsec_read(struct phy_device *phydev, u16 addr, u32 *value)
+{
+	u32 lvalue;
+	u16 laddr;
+	int ret;
+
+	WARN_ON_ONCE(addr % 4);
+
+	laddr = VEND1_MACSEC_BASE + addr / 2;
+	ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, laddr);
+	if (ret < 0)
+		return ret;
+
+	laddr += 1;
+	lvalue = (u32)ret & 0xffff;
+	ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, laddr);
+	if (ret < 0)
+		return ret;
+
+	lvalue |= (u32)ret << 16;
+	*value = lvalue;
+
+	phydev_dbg(phydev, "read addr 0x%x value 0x%x\n", addr, *value);
+
+	return 0;
+}
+
+static void nxp_c45_macsec_read32_64(struct phy_device *phydev, u16 addr,
+				     u64 *value)
+{
+	u32 lvalue;
+
+	nxp_c45_macsec_read(phydev, addr, &lvalue);
+	*value = lvalue;
+}
+
+static void nxp_c45_macsec_read64(struct phy_device *phydev, u16 addr,
+				  u64 *value)
+{
+	u32 lvalue;
+
+	nxp_c45_macsec_read(phydev, addr, &lvalue);
+	*value = (u64)lvalue << 32;
+	nxp_c45_macsec_read(phydev, addr + 4, &lvalue);
+	*value |= lvalue;
+}
+
+static void nxp_c45_secy_irq_en(struct phy_device *phydev,
+				struct nxp_c45_secy *phy_secy, bool en)
+{
+	u32 reg;
+
+	nxp_c45_macsec_read(phydev, MACSEC_EVER, &reg);
+	if (en)
+		reg |= TX_SC_BIT(phy_secy->secy_id);
+	else
+		reg &= ~TX_SC_BIT(phy_secy->secy_id);
+	nxp_c45_macsec_write(phydev, MACSEC_EVER, reg);
+}
+
+static struct nxp_c45_secy *nxp_c45_find_secy(struct list_head *secy_list,
+					      sci_t sci)
+{
+	struct nxp_c45_secy *pos, *tmp;
+
+	list_for_each_entry_safe(pos, tmp, secy_list, list)
+		if (pos->secy->sci == sci)
+			return pos;
+
+	return ERR_PTR(-EINVAL);
+}
+
+static struct
+nxp_c45_secy *nxp_c45_find_secy_by_id(struct list_head *secy_list,
+				      int id)
+{
+	struct nxp_c45_secy *pos, *tmp;
+
+	list_for_each_entry_safe(pos, tmp, secy_list, list)
+		if (pos->secy_id == id)
+			return pos;
+
+	return ERR_PTR(-EINVAL);
+}
+
+static void nxp_c45_secy_free(struct nxp_c45_secy *phy_secy)
+{
+	list_del(&phy_secy->list);
+	kfree(phy_secy);
+}
+
+static struct nxp_c45_sa *nxp_c45_find_sa(struct list_head *sa_list,
+					  enum nxp_c45_sa_type sa_type, u8 an)
+{
+	struct nxp_c45_sa *pos, *tmp;
+
+	list_for_each_entry_safe(pos, tmp, sa_list, list)
+		if (pos->an == an && pos->type == sa_type)
+			return pos;
+
+	return ERR_PTR(-EINVAL);
+}
+
+static struct nxp_c45_sa *nxp_c45_sa_alloc(struct list_head *sa_list, void *sa,
+					   enum nxp_c45_sa_type sa_type, u8 an)
+{
+	struct nxp_c45_sa *first = NULL, *pos, *tmp;
+	int occurrences = 0;
+
+	list_for_each_entry_safe(pos, tmp, sa_list, list) {
+		if (pos->type != sa_type)
+			continue;
+
+		if (pos->an == an)
+			return ERR_PTR(-EINVAL);
+
+		first = pos;
+		occurrences++;
+		if (occurrences >= 2)
+			return ERR_PTR(-ENOSPC);
+	}
+
+	tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
+	if (!tmp)
+		return ERR_PTR(-ENOMEM);
+
+	if (first)
+		tmp->is_key_a = !first->is_key_a;
+	else
+		tmp->is_key_a = true;
+
+	tmp->sa = sa;
+	tmp->type = sa_type;
+	tmp->an = an;
+	tmp->regs = nxp_c45_sa_regs_get(tmp->type, tmp->is_key_a);
+	list_add_tail(&tmp->list, sa_list);
+
+	return tmp;
+}
+
+static void nxp_c45_sa_free(struct nxp_c45_sa *sa)
+{
+	list_del(&sa->list);
+	kfree(sa);
+}
+
+static void nxp_c45_sa_list_free(struct list_head *sa_list)
+{
+	struct nxp_c45_sa *pos, *tmp;
+
+	list_for_each_entry_safe(pos, tmp, sa_list, list)
+		nxp_c45_sa_free(pos);
+}
+
+static void nxp_c45_sa_set_pn(struct phy_device *phydev,
+			      struct nxp_c45_sa *sa, u64 pn,
+			      u32 replay_window)
+{
+	const struct nxp_c45_sa_regs *sa_regs = sa->regs;
+	pn_t npn = {.full64 = pn};
+	pn_t lnpn;
+
+	nxp_c45_macsec_write(phydev, sa_regs->npn, npn.lower);
+	nxp_c45_macsec_write(phydev, sa_regs->xnpn, npn.upper);
+	if (sa->type != RX_SA)
+		return;
+
+	if (pn > replay_window)
+		lnpn.full64 = pn - replay_window;
+	else
+		lnpn.full64 = 1;
+
+	nxp_c45_macsec_write(phydev, sa_regs->lnpn, lnpn.lower);
+	nxp_c45_macsec_write(phydev, sa_regs->lxnpn, lnpn.upper);
+}
+
+static void nxp_c45_sa_set_key(struct macsec_context *ctx,
+			       const struct nxp_c45_sa_regs *sa_regs,
+			       u8 *salt, ssci_t ssci)
+{
+	struct phy_device *phydev = ctx->phydev;
+	u32 key_size = ctx->secy->key_len / 4;
+	u32 salt_size = MACSEC_SALT_LEN / 4;
+	u32 *key_u32 = (u32 *)ctx->sa.key;
+	u32 *salt_u32 = (u32 *)salt;
+	u32 reg, value;
+	int i;
+
+	for (i = 0; i < key_size; i++) {
+		reg = sa_regs->ka + i * 4;
+		value = (__force u32)cpu_to_be32(key_u32[i]);
+		nxp_c45_macsec_write(phydev, reg, value);
+	}
+
+	if (ctx->secy->xpn) {
+		for (i = 0; i < salt_size; i++) {
+			reg = sa_regs->salt + (2 - i) * 4;
+			value = (__force u32)cpu_to_be32(salt_u32[i]);
+			nxp_c45_macsec_write(phydev, reg, value);
+		}
+
+		value = (__force u32)cpu_to_be32((__force u32)ssci);
+		nxp_c45_macsec_write(phydev, sa_regs->ssci, value);
+	}
+
+	nxp_c45_macsec_write(phydev, sa_regs->cs, MACSEC_SA_CS_A);
+}
+
+static void nxp_c45_rx_sa_clear_stats(struct phy_device *phydev,
+				      struct nxp_c45_sa *sa)
+{
+	nxp_c45_macsec_write(phydev, sa->regs->ipis, 0);
+	nxp_c45_macsec_write(phydev, sa->regs->ipnvs, 0);
+	nxp_c45_macsec_write(phydev, sa->regs->ipos, 0);
+
+	nxp_c45_macsec_write(phydev, MACSEC_RXAN0INUSS + sa->an * 4, 0);
+	nxp_c45_macsec_write(phydev, MACSEC_RXAN0IPUSS + sa->an * 4, 0);
+}
+
+static void nxp_c45_rx_sa_read_stats(struct phy_device *phydev,
+				     struct nxp_c45_sa *sa,
+				     struct macsec_rx_sa_stats *stats)
+{
+	nxp_c45_macsec_read(phydev, sa->regs->ipis, &stats->InPktsInvalid);
+	nxp_c45_macsec_read(phydev, sa->regs->ipnvs, &stats->InPktsNotValid);
+	nxp_c45_macsec_read(phydev, sa->regs->ipos, &stats->InPktsOK);
+}
+
+static void nxp_c45_tx_sa_clear_stats(struct phy_device *phydev,
+				      struct nxp_c45_sa *sa)
+{
+	nxp_c45_macsec_write(phydev, sa->regs->opps, 0);
+	nxp_c45_macsec_write(phydev, sa->regs->opes, 0);
+}
+
+static void nxp_c45_tx_sa_read_stats(struct phy_device *phydev,
+				     struct nxp_c45_sa *sa,
+				     struct macsec_tx_sa_stats *stats)
+{
+	nxp_c45_macsec_read(phydev, sa->regs->opps, &stats->OutPktsProtected);
+	nxp_c45_macsec_read(phydev, sa->regs->opes, &stats->OutPktsEncrypted);
+}
+
+static void nxp_c45_rx_sa_update(struct phy_device *phydev,
+				 struct nxp_c45_sa *sa, bool en)
+{
+	const struct nxp_c45_sa_regs *sa_regs = sa->regs;
+	u32 cfg;
+
+	cfg = sa->an << MACSEC_RXSA_CS_AN_OFF;
+	cfg |= en ? MACSEC_RXSA_CS_EN : 0;
+	nxp_c45_macsec_write(phydev, sa_regs->cs, cfg);
+}
+
+static void nxp_c45_tx_sa_update(struct phy_device *phydev,
+				 struct nxp_c45_sa *sa, bool en)
+{
+	u32 cfg = 0;
+
+	nxp_c45_macsec_read(phydev, MACSEC_TXSC_CFG, &cfg);
+
+	cfg &= ~MACSEC_TXSC_CFG_AN_MASK;
+	cfg |= sa->an << MACSEC_TXSC_CFG_AN_OFF;
+
+	if (sa->is_key_a)
+		cfg &= ~MACSEC_TXSC_CFG_ASA;
+	else
+		cfg |= MACSEC_TXSC_CFG_ASA;
+
+	if (en)
+		cfg |= MACSEC_TXSC_CFG_SCE;
+	else
+		cfg &= ~MACSEC_TXSC_CFG_SCE;
+
+	nxp_c45_macsec_write(phydev, MACSEC_TXSC_CFG, cfg);
+}
+
+static void nxp_c45_set_sci(struct phy_device *phydev, u16 sci_base_addr,
+			    sci_t sci)
+{
+	u64 lsci = sci_to_cpu(sci);
+
+	nxp_c45_macsec_write(phydev, sci_base_addr, lsci >> 32);
+	nxp_c45_macsec_write(phydev, sci_base_addr + 4, lsci);
+}
+
+static bool nxp_c45_port_is_1(sci_t sci)
+{
+	u16 port = sci_to_cpu(sci);
+
+	return port == 1;
+}
+
+static void nxp_c45_select_secy(struct phy_device *phydev, u8 id)
+{
+	nxp_c45_macsec_write(phydev, MACSEC_RXSCA, id);
+	nxp_c45_macsec_write(phydev, MACSEC_RXSCKA, id);
+	nxp_c45_macsec_write(phydev, MACSEC_TXSCA, id);
+	nxp_c45_macsec_write(phydev, MACSEC_TXSCKA, id);
+}
+
+static bool nxp_c45_secy_valid(struct nxp_c45_secy *phy_secy,
+			       bool can_rx_sc0_impl)
+{
+	bool end_station = phy_secy->secy->tx_sc.end_station;
+	bool scb = phy_secy->secy->tx_sc.scb;
+
+	phy_secy->rx_sc0_impl = false;
+
+	if (end_station) {
+		if (!nxp_c45_port_is_1(phy_secy->secy->sci))
+			return false;
+		if (!phy_secy->rx_sc)
+			return true;
+		return nxp_c45_port_is_1(phy_secy->rx_sc->sci);
+	}
+
+	if (scb)
+		return false;
+
+	if (!can_rx_sc0_impl)
+		return false;
+
+	if (phy_secy->secy_id != 0)
+		return false;
+
+	phy_secy->rx_sc0_impl = true;
+
+	return true;
+}
+
+static bool nxp_c45_rx_sc0_impl(struct nxp_c45_secy *phy_secy)
+{
+	bool end_station = phy_secy->secy->tx_sc.end_station;
+	bool send_sci = phy_secy->secy->tx_sc.send_sci;
+	bool scb = phy_secy->secy->tx_sc.scb;
+
+	return !end_station && !send_sci && !scb;
+}
+
+static bool nxp_c45_mac_addr_free(struct macsec_context *ctx)
+{
+	struct nxp_c45_phy *priv = ctx->phydev->priv;
+	struct nxp_c45_secy *pos, *tmp;
+
+	list_for_each_entry_safe(pos, tmp, &priv->macsec->secy_list, list) {
+		if (pos->secy == ctx->secy)
+			continue;
+
+		if (memcmp(pos->secy->netdev->dev_addr,
+			   ctx->secy->netdev->dev_addr, ETH_ALEN) == 0)
+			return false;
+	}
+
+	return true;
+}
+
+static void nxp_c45_tx_sc_en_flt(struct phy_device *phydev, int secy_id,
+				 bool en)
+{
+	u32 tx_flt_base = TX_FLT_BASE(secy_id);
+	u32 reg = 0;
+
+	nxp_c45_macsec_read(phydev, TX_SC_FLT_MAC_CFG(tx_flt_base), &reg);
+	if (en)
+		reg |= TX_SC_FLT_EN;
+	else
+		reg &= ~TX_SC_FLT_EN;
+	nxp_c45_macsec_write(phydev, TX_SC_FLT_MAC_CFG(tx_flt_base), reg);
+}
+
+static void nxp_c45_tx_sc_set_flt(struct phy_device *phydev,
+				  struct nxp_c45_secy *phy_secy)
+{
+	const u8 *dev_addr = phy_secy->secy->netdev->dev_addr;
+	u32 tx_flt_base = TX_FLT_BASE(phy_secy->secy_id);
+	u32 reg;
+
+	reg = dev_addr[0] << 8 | dev_addr[1];
+	nxp_c45_macsec_write(phydev, TX_SC_FLT_MAC_DA_SA(tx_flt_base), reg);
+	reg = dev_addr[5] | dev_addr[4] << 8 | dev_addr[3] << 16 |
+		dev_addr[2] << 24;
+
+	nxp_c45_macsec_write(phydev, TX_SC_FLT_MAC_SA(tx_flt_base), reg);
+	nxp_c45_macsec_read(phydev, TX_SC_FLT_MAC_CFG(tx_flt_base), &reg);
+	reg &= TX_SC_FLT_EN;
+	reg |= TX_SC_FLT_BY_SA | phy_secy->secy_id;
+	nxp_c45_macsec_write(phydev, TX_SC_FLT_MAC_CFG(tx_flt_base), reg);
+}
+
+static void nxp_c45_tx_sc_update(struct phy_device *phydev,
+				 struct nxp_c45_secy *phy_secy)
+{
+	u32 cfg = 0;
+
+	nxp_c45_macsec_read(phydev, MACSEC_TXSC_CFG, &cfg);
+
+	phydev_dbg(phydev, "XPN %s\n", phy_secy->secy->xpn ? "on" : "off");
+	if (phy_secy->secy->xpn)
+		cfg |= MACSEC_TXSC_CFG_XPN;
+	else
+		cfg &= ~MACSEC_TXSC_CFG_XPN;
+
+	phydev_dbg(phydev, "key len %u\n", phy_secy->secy->key_len);
+	if (phy_secy->secy->key_len == 32)
+		cfg |= MACSEC_TXSC_CFG_AES_256;
+	else
+		cfg &= ~MACSEC_TXSC_CFG_AES_256;
+
+	phydev_dbg(phydev, "encryption %s\n",
+		   phy_secy->secy->tx_sc.encrypt ? "on" : "off");
+	if (phy_secy->secy->tx_sc.encrypt)
+		cfg |= MACSEC_TXSC_CFG_ENCRYPT;
+	else
+		cfg &= ~MACSEC_TXSC_CFG_ENCRYPT;
+
+	phydev_dbg(phydev, "protect frames %s\n",
+		   phy_secy->secy->protect_frames ? "on" : "off");
+	if (phy_secy->secy->protect_frames)
+		cfg |= MACSEC_TXSC_CFG_PROTECT;
+	else
+		cfg &= ~MACSEC_TXSC_CFG_PROTECT;
+
+	phydev_dbg(phydev, "send sci %s\n",
+		   phy_secy->secy->tx_sc.send_sci ? "on" : "off");
+	if (phy_secy->secy->tx_sc.send_sci)
+		cfg |= MACSEC_TXSC_CFG_SEND_SCI;
+	else
+		cfg &= ~MACSEC_TXSC_CFG_SEND_SCI;
+
+	phydev_dbg(phydev, "end station %s\n",
+		   phy_secy->secy->tx_sc.end_station ? "on" : "off");
+	if (phy_secy->secy->tx_sc.end_station)
+		cfg |= MACSEC_TXSC_CFG_END_STATION;
+	else
+		cfg &= ~MACSEC_TXSC_CFG_END_STATION;
+
+	phydev_dbg(phydev, "scb %s\n",
+		   phy_secy->secy->tx_sc.scb ? "on" : "off");
+	if (phy_secy->secy->tx_sc.scb)
+		cfg |= MACSEC_TXSC_CFG_SCB;
+	else
+		cfg &= ~MACSEC_TXSC_CFG_SCB;
+
+	nxp_c45_macsec_write(phydev, MACSEC_TXSC_CFG, cfg);
+}
+
+static void nxp_c45_tx_sc_clear_stats(struct phy_device *phydev,
+				      struct nxp_c45_secy *phy_secy)
+{
+	struct nxp_c45_sa *pos, *tmp;
+
+	list_for_each_entry_safe(pos, tmp, &phy_secy->sa_list, list)
+		if (pos->type == TX_SA)
+			nxp_c45_tx_sa_clear_stats(phydev, pos);
+
+	nxp_c45_macsec_write(phydev, MACSEC_OPUS, 0);
+	nxp_c45_macsec_write(phydev, MACSEC_OPTLS, 0);
+	nxp_c45_macsec_write(phydev, MACSEC_OOP1HS, 0);
+	nxp_c45_macsec_write(phydev, MACSEC_OOP2HS, 0);
+	nxp_c45_macsec_write(phydev, MACSEC_OOE1HS, 0);
+	nxp_c45_macsec_write(phydev, MACSEC_OOE2HS, 0);
+}
+
+static void nxp_c45_set_rx_sc0_impl(struct phy_device *phydev,
+				    bool enable)
+{
+	u32 reg = 0;
+
+	nxp_c45_macsec_read(phydev, MACSEC_CFG, &reg);
+	if (enable)
+		reg |= MACSEC_CFG_S0I;
+	else
+		reg &= ~MACSEC_CFG_S0I;
+	nxp_c45_macsec_write(phydev, MACSEC_CFG, reg);
+}
+
+static bool nxp_c45_is_rx_sc0_impl(struct list_head *secy_list)
+{
+	struct nxp_c45_secy *pos, *tmp;
+
+	list_for_each_entry_safe(pos, tmp, secy_list, list)
+		if (pos->rx_sc0_impl)
+			return pos->rx_sc0_impl;
+
+	return false;
+}
+
+static void nxp_c45_rx_sc_en(struct phy_device *phydev,
+			     struct macsec_rx_sc *rx_sc, bool en)
+{
+	u32 reg = 0;
+
+	nxp_c45_macsec_read(phydev, MACSEC_RXSC_CFG, &reg);
+	if (rx_sc->active && en)
+		reg |= MACSEC_RXSC_CFG_SCI_EN;
+	else
+		reg &= ~MACSEC_RXSC_CFG_SCI_EN;
+	nxp_c45_macsec_write(phydev, MACSEC_RXSC_CFG, reg);
+}
+
+static void nxp_c45_rx_sc_update(struct phy_device *phydev,
+				 struct nxp_c45_secy *phy_secy)
+{
+	struct macsec_rx_sc *rx_sc = phy_secy->rx_sc;
+	struct nxp_c45_phy *priv = phydev->priv;
+	u32 cfg = 0;
+
+	nxp_c45_macsec_read(phydev, MACSEC_RXSC_CFG, &cfg);
+	cfg &= ~MACSEC_RXSC_CFG_VF_MASK;
+	cfg = phy_secy->secy->validate_frames << MACSEC_RXSC_CFG_VF_OFF;
+
+	phydev_dbg(phydev, "validate frames %u\n",
+		   phy_secy->secy->validate_frames);
+	phydev_dbg(phydev, "replay_protect %s window %u\n",
+		   phy_secy->secy->replay_protect ? "on" : "off",
+		   phy_secy->secy->replay_window);
+	if (phy_secy->secy->replay_protect) {
+		cfg |= MACSEC_RXSC_CFG_RP;
+		nxp_c45_macsec_write(phydev, MACSEC_RPW,
+				     phy_secy->secy->replay_window);
+	} else {
+		cfg &= ~MACSEC_RXSC_CFG_RP;
+	}
+
+	phydev_dbg(phydev, "rx_sc->active %s\n",
+		   rx_sc->active ? "on" : "off");
+	if (rx_sc->active &&
+	    test_bit(phy_secy->secy_id, priv->macsec->secy_bitmap))
+		cfg |= MACSEC_RXSC_CFG_SCI_EN;
+	else
+		cfg &= ~MACSEC_RXSC_CFG_SCI_EN;
+
+	phydev_dbg(phydev, "key len %u\n", phy_secy->secy->key_len);
+	if (phy_secy->secy->key_len == 32)
+		cfg |= MACSEC_RXSC_CFG_AES_256;
+	else
+		cfg &= ~MACSEC_RXSC_CFG_AES_256;
+
+	phydev_dbg(phydev, "XPN %s\n", phy_secy->secy->xpn ? "on" : "off");
+	if (phy_secy->secy->xpn)
+		cfg |= MACSEC_RXSC_CFG_XPN;
+	else
+		cfg &= ~MACSEC_RXSC_CFG_XPN;
+
+	nxp_c45_macsec_write(phydev, MACSEC_RXSC_CFG, cfg);
+}
+
+static void nxp_c45_rx_sc_clear_stats(struct phy_device *phydev,
+				      struct nxp_c45_secy *phy_secy)
+{
+	struct nxp_c45_sa *pos, *tmp;
+	int i;
+
+	list_for_each_entry_safe(pos, tmp, &phy_secy->sa_list, list)
+		if (pos->type == RX_SA)
+			nxp_c45_rx_sa_clear_stats(phydev, pos);
+
+	nxp_c45_macsec_write(phydev, MACSEC_INOD1HS, 0);
+	nxp_c45_macsec_write(phydev, MACSEC_INOD2HS, 0);
+
+	nxp_c45_macsec_write(phydev, MACSEC_INOV1HS, 0);
+	nxp_c45_macsec_write(phydev, MACSEC_INOV2HS, 0);
+
+	nxp_c45_macsec_write(phydev, MACSEC_RXSCIPDS, 0);
+	nxp_c45_macsec_write(phydev, MACSEC_RXSCIPLS, 0);
+	nxp_c45_macsec_write(phydev, MACSEC_RXSCIPUS, 0);
+
+	for (i = 0; i < MACSEC_NUM_AN; i++) {
+		nxp_c45_macsec_write(phydev, MACSEC_RXAN0INUSS + i * 4, 0);
+		nxp_c45_macsec_write(phydev, MACSEC_RXAN0IPUSS + i * 4, 0);
+	}
+}
+
+static void nxp_c45_rx_sc_del(struct phy_device *phydev,
+			      struct nxp_c45_secy *phy_secy)
+{
+	struct nxp_c45_sa *pos, *tmp;
+
+	nxp_c45_macsec_write(phydev, MACSEC_RXSC_CFG, 0);
+	nxp_c45_macsec_write(phydev, MACSEC_RPW, 0);
+	nxp_c45_set_sci(phydev, MACSEC_RXSC_SCI_1H, 0);
+
+	nxp_c45_rx_sc_clear_stats(phydev, phy_secy);
+
+	list_for_each_entry_safe(pos, tmp, &phy_secy->sa_list, list) {
+		if (pos->type == RX_SA) {
+			nxp_c45_rx_sa_update(phydev, pos, false);
+			nxp_c45_sa_free(pos);
+		}
+	}
+}
+
+static void nxp_c45_clear_global_stats(struct phy_device *phydev)
+{
+	nxp_c45_macsec_write(phydev, MACSEC_INPBTS, 0);
+	nxp_c45_macsec_write(phydev, MACSEC_INPWTS, 0);
+	nxp_c45_macsec_write(phydev, MACSEC_IPSNFS, 0);
+}
+
+static void nxp_c45_macsec_en(struct phy_device *phydev, bool en)
+{
+	u32 reg;
+
+	nxp_c45_macsec_read(phydev, MACSEC_CFG, &reg);
+	if (en)
+		reg |= MACSEC_CFG_BYPASS;
+	else
+		reg &= ~MACSEC_CFG_BYPASS;
+	nxp_c45_macsec_write(phydev, MACSEC_CFG, reg);
+}
+
+static int nxp_c45_mdo_dev_open(struct macsec_context *ctx)
+{
+	struct phy_device *phydev = ctx->phydev;
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct nxp_c45_secy *phy_secy;
+	int any_bit_set;
+
+	phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci);
+	if (IS_ERR(phy_secy))
+		return PTR_ERR(phy_secy);
+
+	nxp_c45_select_secy(phydev, phy_secy->secy_id);
+
+	nxp_c45_tx_sc_en_flt(phydev, phy_secy->secy_id, true);
+	nxp_c45_set_rx_sc0_impl(phydev, phy_secy->rx_sc0_impl);
+	if (phy_secy->rx_sc)
+		nxp_c45_rx_sc_en(phydev, phy_secy->rx_sc, true);
+
+	any_bit_set = find_first_bit(priv->macsec->secy_bitmap, TX_SC_MAX);
+	if (any_bit_set == TX_SC_MAX)
+		nxp_c45_macsec_en(phydev, true);
+
+	set_bit(phy_secy->secy_id, priv->macsec->secy_bitmap);
+
+	return 0;
+}
+
+static int nxp_c45_mdo_dev_stop(struct macsec_context *ctx)
+{
+	struct phy_device *phydev = ctx->phydev;
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct nxp_c45_secy *phy_secy;
+	int any_bit_set;
+
+	phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci);
+	if (IS_ERR(phy_secy))
+		return PTR_ERR(phy_secy);
+
+	nxp_c45_select_secy(phydev, phy_secy->secy_id);
+
+	nxp_c45_tx_sc_en_flt(phydev, phy_secy->secy_id, false);
+	if (phy_secy->rx_sc)
+		nxp_c45_rx_sc_en(phydev, phy_secy->rx_sc, false);
+	nxp_c45_set_rx_sc0_impl(phydev, false);
+
+	clear_bit(phy_secy->secy_id, priv->macsec->secy_bitmap);
+	any_bit_set = find_first_bit(priv->macsec->secy_bitmap, TX_SC_MAX);
+	if (any_bit_set == TX_SC_MAX)
+		nxp_c45_macsec_en(phydev, false);
+
+	return 0;
+}
+
+static int nxp_c45_mdo_add_secy(struct macsec_context *ctx)
+{
+	struct phy_device *phydev = ctx->phydev;
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct nxp_c45_secy *phy_secy;
+	bool can_rx_sc0_impl;
+	int idx;
+
+	phydev_dbg(phydev, "add SecY SCI %016llx\n",
+		   sci_to_cpu(ctx->secy->sci));
+
+	if (!nxp_c45_mac_addr_free(ctx))
+		return -EBUSY;
+
+	if (nxp_c45_is_rx_sc0_impl(&priv->macsec->secy_list))
+		return -EBUSY;
+
+	idx = find_first_zero_bit(priv->macsec->tx_sc_bitmap, TX_SC_MAX);
+	if (idx == TX_SC_MAX)
+		return -ENOSPC;
+
+	phy_secy = kzalloc(sizeof(*phy_secy), GFP_KERNEL);
+	if (!phy_secy)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&phy_secy->sa_list);
+	phy_secy->secy = ctx->secy;
+	phy_secy->secy_id = idx;
+
+	/* If the point to point mode should be enabled, we should have no
+	 * SecY added yet.
+	 */
+	can_rx_sc0_impl = list_count_nodes(&priv->macsec->secy_list) == 0;
+	if (!nxp_c45_secy_valid(phy_secy, can_rx_sc0_impl)) {
+		kfree(phy_secy);
+		return -EINVAL;
+	}
+
+	phy_secy->rx_sc0_impl = nxp_c45_rx_sc0_impl(phy_secy);
+
+	nxp_c45_select_secy(phydev, phy_secy->secy_id);
+	nxp_c45_set_sci(phydev, MACSEC_TXSC_SCI_1H, ctx->secy->sci);
+	nxp_c45_tx_sc_set_flt(phydev, phy_secy);
+	nxp_c45_tx_sc_update(phydev, phy_secy);
+	if (phy_interrupt_is_valid(phydev))
+		nxp_c45_secy_irq_en(phydev, phy_secy, true);
+
+	set_bit(idx, priv->macsec->tx_sc_bitmap);
+	list_add_tail(&phy_secy->list, &priv->macsec->secy_list);
+
+	return 0;
+}
+
+static void nxp_c45_tx_sa_next(struct nxp_c45_secy *phy_secy,
+			       struct nxp_c45_sa *next_sa, u8 encoding_sa)
+{
+	struct nxp_c45_sa *sa;
+
+	sa = nxp_c45_find_sa(&phy_secy->sa_list, TX_SA, encoding_sa);
+	if (!IS_ERR(sa)) {
+		memcpy(next_sa, sa, sizeof(*sa));
+	} else {
+		next_sa->is_key_a = true;
+		next_sa->an = encoding_sa;
+	}
+}
+
+static int nxp_c45_mdo_upd_secy(struct macsec_context *ctx)
+{
+	u8 encoding_sa = ctx->secy->tx_sc.encoding_sa;
+	struct phy_device *phydev = ctx->phydev;
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct nxp_c45_secy *phy_secy;
+	struct nxp_c45_sa next_sa;
+	bool can_rx_sc0_impl;
+
+	phydev_dbg(phydev, "update SecY SCI %016llx\n",
+		   sci_to_cpu(ctx->secy->sci));
+
+	phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci);
+	if (IS_ERR(phy_secy))
+		return PTR_ERR(phy_secy);
+
+	if (!nxp_c45_mac_addr_free(ctx))
+		return -EBUSY;
+
+	/* If the point to point mode should be enabled, we should have only
+	 * one SecY added, respectively the updated one.
+	 */
+	can_rx_sc0_impl = list_count_nodes(&priv->macsec->secy_list) == 1;
+	if (!nxp_c45_secy_valid(phy_secy, can_rx_sc0_impl))
+		return -EINVAL;
+	phy_secy->rx_sc0_impl = nxp_c45_rx_sc0_impl(phy_secy);
+
+	nxp_c45_select_secy(phydev, phy_secy->secy_id);
+	nxp_c45_tx_sc_set_flt(phydev, phy_secy);
+	nxp_c45_tx_sc_update(phydev, phy_secy);
+	nxp_c45_tx_sa_next(phy_secy, &next_sa, encoding_sa);
+	nxp_c45_tx_sa_update(phydev, &next_sa, ctx->secy->operational);
+
+	nxp_c45_set_rx_sc0_impl(phydev, phy_secy->rx_sc0_impl);
+	if (phy_secy->rx_sc)
+		nxp_c45_rx_sc_update(phydev, phy_secy);
+
+	return 0;
+}
+
+static int nxp_c45_mdo_del_secy(struct macsec_context *ctx)
+{
+	u8 encoding_sa = ctx->secy->tx_sc.encoding_sa;
+	struct phy_device *phydev = ctx->phydev;
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct nxp_c45_secy *phy_secy;
+	struct nxp_c45_sa next_sa;
+
+	phydev_dbg(phydev, "delete SecY SCI %016llx\n",
+		   sci_to_cpu(ctx->secy->sci));
+
+	phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci);
+	if (IS_ERR(phy_secy))
+		return PTR_ERR(phy_secy);
+	nxp_c45_select_secy(phydev, phy_secy->secy_id);
+
+	nxp_c45_mdo_dev_stop(ctx);
+	nxp_c45_tx_sa_next(phy_secy, &next_sa, encoding_sa);
+	nxp_c45_tx_sa_update(phydev, &next_sa, false);
+	nxp_c45_tx_sc_clear_stats(phydev, phy_secy);
+	if (phy_secy->rx_sc)
+		nxp_c45_rx_sc_del(phydev, phy_secy);
+
+	nxp_c45_sa_list_free(&phy_secy->sa_list);
+	if (phy_interrupt_is_valid(phydev))
+		nxp_c45_secy_irq_en(phydev, phy_secy, false);
+
+	clear_bit(phy_secy->secy_id, priv->macsec->tx_sc_bitmap);
+	nxp_c45_secy_free(phy_secy);
+
+	if (list_empty(&priv->macsec->secy_list))
+		nxp_c45_clear_global_stats(phydev);
+
+	return 0;
+}
+
+static int nxp_c45_mdo_add_rxsc(struct macsec_context *ctx)
+{
+	struct phy_device *phydev = ctx->phydev;
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct nxp_c45_secy *phy_secy;
+
+	phydev_dbg(phydev, "add RX SC SCI %016llx %s\n",
+		   sci_to_cpu(ctx->rx_sc->sci),
+		   ctx->rx_sc->active ? "enabled" : "disabled");
+
+	phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci);
+	if (IS_ERR(phy_secy))
+		return PTR_ERR(phy_secy);
+
+	if (phy_secy->rx_sc)
+		return -ENOSPC;
+
+	if (phy_secy->secy->tx_sc.end_station &&
+	    !nxp_c45_port_is_1(ctx->rx_sc->sci))
+		return -EINVAL;
+
+	phy_secy->rx_sc = ctx->rx_sc;
+
+	nxp_c45_select_secy(phydev, phy_secy->secy_id);
+	nxp_c45_set_sci(phydev, MACSEC_RXSC_SCI_1H, ctx->rx_sc->sci);
+	nxp_c45_rx_sc_update(phydev, phy_secy);
+
+	return 0;
+}
+
+static int nxp_c45_mdo_upd_rxsc(struct macsec_context *ctx)
+{
+	struct phy_device *phydev = ctx->phydev;
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct nxp_c45_secy *phy_secy;
+
+	phydev_dbg(phydev, "update RX SC SCI %016llx %s\n",
+		   sci_to_cpu(ctx->rx_sc->sci),
+		   ctx->rx_sc->active ? "enabled" : "disabled");
+
+	phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci);
+	if (IS_ERR(phy_secy))
+		return PTR_ERR(phy_secy);
+
+	nxp_c45_select_secy(phydev, phy_secy->secy_id);
+	nxp_c45_rx_sc_update(phydev, phy_secy);
+
+	return 0;
+}
+
+static int nxp_c45_mdo_del_rxsc(struct macsec_context *ctx)
+{
+	struct phy_device *phydev = ctx->phydev;
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct nxp_c45_secy *phy_secy;
+
+	phydev_dbg(phydev, "delete RX SC SCI %016llx %s\n",
+		   sci_to_cpu(ctx->rx_sc->sci),
+		   ctx->rx_sc->active ? "enabled" : "disabled");
+
+	phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci);
+	if (IS_ERR(phy_secy))
+		return PTR_ERR(phy_secy);
+
+	nxp_c45_select_secy(phydev, phy_secy->secy_id);
+	nxp_c45_rx_sc_del(phydev, phy_secy);
+	phy_secy->rx_sc = NULL;
+
+	return 0;
+}
+
+static int nxp_c45_mdo_add_rxsa(struct macsec_context *ctx)
+{
+	struct macsec_rx_sa *rx_sa = ctx->sa.rx_sa;
+	struct phy_device *phydev = ctx->phydev;
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct nxp_c45_secy *phy_secy;
+	u8 an = ctx->sa.assoc_num;
+	struct nxp_c45_sa *sa;
+
+	phydev_dbg(phydev, "add RX SA %u %s to RX SC SCI %016llx\n",
+		   an, rx_sa->active ? "enabled" : "disabled",
+		   sci_to_cpu(rx_sa->sc->sci));
+
+	phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci);
+	if (IS_ERR(phy_secy))
+		return PTR_ERR(phy_secy);
+
+	sa = nxp_c45_sa_alloc(&phy_secy->sa_list, rx_sa, RX_SA, an);
+	if (IS_ERR(sa))
+		return PTR_ERR(sa);
+
+	nxp_c45_select_secy(phydev, phy_secy->secy_id);
+	nxp_c45_sa_set_pn(phydev, sa, rx_sa->next_pn,
+			  ctx->secy->replay_window);
+	nxp_c45_sa_set_key(ctx, sa->regs, rx_sa->key.salt.bytes, rx_sa->ssci);
+	nxp_c45_rx_sa_update(phydev, sa, rx_sa->active);
+
+	return 0;
+}
+
+static int nxp_c45_mdo_upd_rxsa(struct macsec_context *ctx)
+{
+	struct macsec_rx_sa *rx_sa = ctx->sa.rx_sa;
+	struct phy_device *phydev = ctx->phydev;
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct nxp_c45_secy *phy_secy;
+	u8 an = ctx->sa.assoc_num;
+	struct nxp_c45_sa *sa;
+
+	phydev_dbg(phydev, "update RX SA %u %s to RX SC SCI %016llx\n",
+		   an, rx_sa->active ? "enabled" : "disabled",
+		   sci_to_cpu(rx_sa->sc->sci));
+
+	phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci);
+	if (IS_ERR(phy_secy))
+		return PTR_ERR(phy_secy);
+
+	sa = nxp_c45_find_sa(&phy_secy->sa_list, RX_SA, an);
+	if (IS_ERR(sa))
+		return PTR_ERR(sa);
+
+	nxp_c45_select_secy(phydev, phy_secy->secy_id);
+	if (ctx->sa.update_pn)
+		nxp_c45_sa_set_pn(phydev, sa, rx_sa->next_pn,
+				  ctx->secy->replay_window);
+	nxp_c45_rx_sa_update(phydev, sa, rx_sa->active);
+
+	return 0;
+}
+
+static int nxp_c45_mdo_del_rxsa(struct macsec_context *ctx)
+{
+	struct macsec_rx_sa *rx_sa = ctx->sa.rx_sa;
+	struct phy_device *phydev = ctx->phydev;
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct nxp_c45_secy *phy_secy;
+	u8 an = ctx->sa.assoc_num;
+	struct nxp_c45_sa *sa;
+
+	phydev_dbg(phydev, "delete RX SA %u %s to RX SC SCI %016llx\n",
+		   an, rx_sa->active ? "enabled" : "disabled",
+		   sci_to_cpu(rx_sa->sc->sci));
+
+	phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci);
+	if (IS_ERR(phy_secy))
+		return PTR_ERR(phy_secy);
+
+	sa = nxp_c45_find_sa(&phy_secy->sa_list, RX_SA, an);
+	if (IS_ERR(sa))
+		return PTR_ERR(sa);
+
+	nxp_c45_select_secy(phydev, phy_secy->secy_id);
+	nxp_c45_rx_sa_update(phydev, sa, false);
+	nxp_c45_rx_sa_clear_stats(phydev, sa);
+
+	nxp_c45_sa_free(sa);
+
+	return 0;
+}
+
+static int nxp_c45_mdo_add_txsa(struct macsec_context *ctx)
+{
+	struct macsec_tx_sa *tx_sa = ctx->sa.tx_sa;
+	struct phy_device *phydev = ctx->phydev;
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct nxp_c45_secy *phy_secy;
+	u8 an = ctx->sa.assoc_num;
+	struct nxp_c45_sa *sa;
+
+	phydev_dbg(phydev, "add TX SA %u %s to TX SC %016llx\n",
+		   an, ctx->sa.tx_sa->active ? "enabled" : "disabled",
+		   sci_to_cpu(ctx->secy->sci));
+
+	phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci);
+	if (IS_ERR(phy_secy))
+		return PTR_ERR(phy_secy);
+
+	sa = nxp_c45_sa_alloc(&phy_secy->sa_list, tx_sa, TX_SA, an);
+	if (IS_ERR(sa))
+		return PTR_ERR(sa);
+
+	nxp_c45_select_secy(phydev, phy_secy->secy_id);
+	nxp_c45_sa_set_pn(phydev, sa, tx_sa->next_pn, 0);
+	nxp_c45_sa_set_key(ctx, sa->regs, tx_sa->key.salt.bytes, tx_sa->ssci);
+	if (ctx->secy->tx_sc.encoding_sa == sa->an)
+		nxp_c45_tx_sa_update(phydev, sa, tx_sa->active);
+
+	return 0;
+}
+
+static int nxp_c45_mdo_upd_txsa(struct macsec_context *ctx)
+{
+	struct macsec_tx_sa *tx_sa = ctx->sa.tx_sa;
+	struct phy_device *phydev = ctx->phydev;
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct nxp_c45_secy *phy_secy;
+	u8 an = ctx->sa.assoc_num;
+	struct nxp_c45_sa *sa;
+
+	phydev_dbg(phydev, "update TX SA %u %s to TX SC %016llx\n",
+		   an, ctx->sa.tx_sa->active ? "enabled" : "disabled",
+		   sci_to_cpu(ctx->secy->sci));
+
+	phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci);
+	if (IS_ERR(phy_secy))
+		return PTR_ERR(phy_secy);
+
+	sa = nxp_c45_find_sa(&phy_secy->sa_list, TX_SA, an);
+	if (IS_ERR(sa))
+		return PTR_ERR(sa);
+
+	nxp_c45_select_secy(phydev, phy_secy->secy_id);
+	if (ctx->sa.update_pn)
+		nxp_c45_sa_set_pn(phydev, sa, tx_sa->next_pn, 0);
+	if (ctx->secy->tx_sc.encoding_sa == sa->an)
+		nxp_c45_tx_sa_update(phydev, sa, tx_sa->active);
+
+	return 0;
+}
+
+static int nxp_c45_mdo_del_txsa(struct macsec_context *ctx)
+{
+	struct phy_device *phydev = ctx->phydev;
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct nxp_c45_secy *phy_secy;
+	u8 an = ctx->sa.assoc_num;
+	struct nxp_c45_sa *sa;
+
+	phydev_dbg(phydev, "delete TX SA %u %s to TX SC %016llx\n",
+		   an, ctx->sa.tx_sa->active ? "enabled" : "disabled",
+		   sci_to_cpu(ctx->secy->sci));
+
+	phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci);
+	if (IS_ERR(phy_secy))
+		return PTR_ERR(phy_secy);
+
+	sa = nxp_c45_find_sa(&phy_secy->sa_list, TX_SA, an);
+	if (IS_ERR(sa))
+		return PTR_ERR(sa);
+
+	nxp_c45_select_secy(phydev, phy_secy->secy_id);
+	if (ctx->secy->tx_sc.encoding_sa == sa->an)
+		nxp_c45_tx_sa_update(phydev, sa, false);
+	nxp_c45_tx_sa_clear_stats(phydev, sa);
+
+	nxp_c45_sa_free(sa);
+
+	return 0;
+}
+
+static int nxp_c45_mdo_get_dev_stats(struct macsec_context *ctx)
+{
+	struct phy_device *phydev = ctx->phydev;
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct macsec_dev_stats  *dev_stats;
+	struct nxp_c45_secy *phy_secy;
+
+	phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci);
+	if (IS_ERR(phy_secy))
+		return PTR_ERR(phy_secy);
+
+	dev_stats = ctx->stats.dev_stats;
+	nxp_c45_select_secy(phydev, phy_secy->secy_id);
+
+	nxp_c45_macsec_read32_64(phydev, MACSEC_OPUS,
+				 &dev_stats->OutPktsUntagged);
+	nxp_c45_macsec_read32_64(phydev, MACSEC_OPTLS,
+				 &dev_stats->OutPktsTooLong);
+	nxp_c45_macsec_read32_64(phydev, MACSEC_INPBTS,
+				 &dev_stats->InPktsBadTag);
+
+	if (phy_secy->secy->validate_frames == MACSEC_VALIDATE_STRICT)
+		nxp_c45_macsec_read32_64(phydev, MACSEC_INPWTS,
+					 &dev_stats->InPktsNoTag);
+	else
+		nxp_c45_macsec_read32_64(phydev, MACSEC_INPWTS,
+					 &dev_stats->InPktsUntagged);
+
+	if (phy_secy->secy->validate_frames == MACSEC_VALIDATE_STRICT)
+		nxp_c45_macsec_read32_64(phydev, MACSEC_IPSNFS,
+					 &dev_stats->InPktsNoSCI);
+	else
+		nxp_c45_macsec_read32_64(phydev, MACSEC_IPSNFS,
+					 &dev_stats->InPktsUnknownSCI);
+
+	/* Always 0. */
+	dev_stats->InPktsOverrun = 0;
+
+	return 0;
+}
+
+static int nxp_c45_mdo_get_tx_sc_stats(struct macsec_context *ctx)
+{
+	struct phy_device *phydev = ctx->phydev;
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct macsec_tx_sa_stats tx_sa_stats;
+	struct macsec_tx_sc_stats *stats;
+	struct nxp_c45_secy *phy_secy;
+	struct nxp_c45_sa *pos, *tmp;
+
+	phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci);
+	if (IS_ERR(phy_secy))
+		return PTR_ERR(phy_secy);
+
+	stats = ctx->stats.tx_sc_stats;
+	nxp_c45_select_secy(phydev, phy_secy->secy_id);
+
+	nxp_c45_macsec_read64(phydev, MACSEC_OOE1HS,
+			      &stats->OutOctetsEncrypted);
+	nxp_c45_macsec_read64(phydev, MACSEC_OOP1HS,
+			      &stats->OutOctetsProtected);
+	list_for_each_entry_safe(pos, tmp, &phy_secy->sa_list, list) {
+		if (pos->type != TX_SA)
+			continue;
+
+		memset(&tx_sa_stats, 0, sizeof(tx_sa_stats));
+		nxp_c45_tx_sa_read_stats(phydev, pos, &tx_sa_stats);
+
+		stats->OutPktsEncrypted += tx_sa_stats.OutPktsEncrypted;
+		stats->OutPktsProtected += tx_sa_stats.OutPktsProtected;
+	}
+
+	return 0;
+}
+
+static int nxp_c45_mdo_get_tx_sa_stats(struct macsec_context *ctx)
+{
+	struct phy_device *phydev = ctx->phydev;
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct macsec_tx_sa_stats *stats;
+	struct nxp_c45_secy *phy_secy;
+	u8 an = ctx->sa.assoc_num;
+	struct nxp_c45_sa *sa;
+
+	phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci);
+	if (IS_ERR(phy_secy))
+		return PTR_ERR(phy_secy);
+
+	sa = nxp_c45_find_sa(&phy_secy->sa_list, TX_SA, an);
+	if (IS_ERR(sa))
+		return PTR_ERR(sa);
+
+	stats = ctx->stats.tx_sa_stats;
+	nxp_c45_select_secy(phydev, phy_secy->secy_id);
+	nxp_c45_tx_sa_read_stats(phydev, sa, stats);
+
+	return 0;
+}
+
+static int nxp_c45_mdo_get_rx_sc_stats(struct macsec_context *ctx)
+{
+	struct phy_device *phydev = ctx->phydev;
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct macsec_rx_sa_stats rx_sa_stats;
+	struct macsec_rx_sc_stats *stats;
+	struct nxp_c45_secy *phy_secy;
+	struct nxp_c45_sa *pos, *tmp;
+	u32 reg = 0;
+	int i;
+
+	phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci);
+	if (IS_ERR(phy_secy))
+		return PTR_ERR(phy_secy);
+
+	if (phy_secy->rx_sc != ctx->rx_sc)
+		return -EINVAL;
+
+	stats = ctx->stats.rx_sc_stats;
+	nxp_c45_select_secy(phydev, phy_secy->secy_id);
+
+	list_for_each_entry_safe(pos, tmp, &phy_secy->sa_list, list) {
+		if (pos->type != RX_SA)
+			continue;
+
+		memset(&rx_sa_stats, 0, sizeof(rx_sa_stats));
+		nxp_c45_rx_sa_read_stats(phydev, pos, &rx_sa_stats);
+
+		stats->InPktsInvalid += rx_sa_stats.InPktsInvalid;
+		stats->InPktsNotValid += rx_sa_stats.InPktsNotValid;
+		stats->InPktsOK += rx_sa_stats.InPktsOK;
+	}
+
+	for (i = 0; i < MACSEC_NUM_AN; i++) {
+		nxp_c45_macsec_read(phydev, MACSEC_RXAN0INUSS + i * 4, &reg);
+		stats->InPktsNotUsingSA += reg;
+		nxp_c45_macsec_read(phydev, MACSEC_RXAN0IPUSS + i * 4, &reg);
+		stats->InPktsUnusedSA += reg;
+	}
+
+	nxp_c45_macsec_read64(phydev, MACSEC_INOD1HS,
+			      &stats->InOctetsDecrypted);
+	nxp_c45_macsec_read64(phydev, MACSEC_INOV1HS,
+			      &stats->InOctetsValidated);
+
+	nxp_c45_macsec_read32_64(phydev, MACSEC_RXSCIPDS,
+				 &stats->InPktsDelayed);
+	nxp_c45_macsec_read32_64(phydev, MACSEC_RXSCIPLS,
+				 &stats->InPktsLate);
+	nxp_c45_macsec_read32_64(phydev, MACSEC_RXSCIPUS,
+				 &stats->InPktsUnchecked);
+
+	return 0;
+}
+
+static int nxp_c45_mdo_get_rx_sa_stats(struct macsec_context *ctx)
+{
+	struct phy_device *phydev = ctx->phydev;
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct macsec_rx_sa_stats *stats;
+	struct nxp_c45_secy *phy_secy;
+	u8 an = ctx->sa.assoc_num;
+	struct nxp_c45_sa *sa;
+
+	phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci);
+	if (IS_ERR(phy_secy))
+		return PTR_ERR(phy_secy);
+
+	sa = nxp_c45_find_sa(&phy_secy->sa_list, RX_SA, an);
+	if (IS_ERR(sa))
+		return PTR_ERR(sa);
+
+	stats = ctx->stats.rx_sa_stats;
+	nxp_c45_select_secy(phydev, phy_secy->secy_id);
+
+	nxp_c45_rx_sa_read_stats(phydev, sa, stats);
+	nxp_c45_macsec_read(phydev, MACSEC_RXAN0INUSS + an * 4,
+			    &stats->InPktsNotUsingSA);
+	nxp_c45_macsec_read(phydev, MACSEC_RXAN0IPUSS + an * 4,
+			    &stats->InPktsUnusedSA);
+
+	return 0;
+}
+
+struct tja11xx_tlv_header {
+	struct ethhdr eth;
+	u8 subtype;
+	u8 len;
+	u8 payload[28];
+};
+
+static int nxp_c45_mdo_insert_tx_tag(struct phy_device *phydev,
+				     struct sk_buff *skb)
+{
+	struct tja11xx_tlv_header *tlv;
+	struct ethhdr *eth;
+
+	eth = eth_hdr(skb);
+	tlv = skb_push(skb, TJA11XX_TLV_TX_NEEDED_HEADROOM);
+	memmove(tlv, eth, sizeof(*eth));
+	skb_reset_mac_header(skb);
+	tlv->eth.h_proto = htons(ETH_P_TJA11XX_TLV);
+	tlv->subtype = 1;
+	tlv->len = sizeof(tlv->payload);
+	memset(tlv->payload, 0, sizeof(tlv->payload));
+
+	return 0;
+}
+
+static const struct macsec_ops nxp_c45_macsec_ops = {
+	.mdo_dev_open = nxp_c45_mdo_dev_open,
+	.mdo_dev_stop = nxp_c45_mdo_dev_stop,
+	.mdo_add_secy = nxp_c45_mdo_add_secy,
+	.mdo_upd_secy = nxp_c45_mdo_upd_secy,
+	.mdo_del_secy = nxp_c45_mdo_del_secy,
+	.mdo_add_rxsc = nxp_c45_mdo_add_rxsc,
+	.mdo_upd_rxsc = nxp_c45_mdo_upd_rxsc,
+	.mdo_del_rxsc = nxp_c45_mdo_del_rxsc,
+	.mdo_add_rxsa = nxp_c45_mdo_add_rxsa,
+	.mdo_upd_rxsa = nxp_c45_mdo_upd_rxsa,
+	.mdo_del_rxsa = nxp_c45_mdo_del_rxsa,
+	.mdo_add_txsa = nxp_c45_mdo_add_txsa,
+	.mdo_upd_txsa = nxp_c45_mdo_upd_txsa,
+	.mdo_del_txsa = nxp_c45_mdo_del_txsa,
+	.mdo_get_dev_stats = nxp_c45_mdo_get_dev_stats,
+	.mdo_get_tx_sc_stats = nxp_c45_mdo_get_tx_sc_stats,
+	.mdo_get_tx_sa_stats = nxp_c45_mdo_get_tx_sa_stats,
+	.mdo_get_rx_sc_stats = nxp_c45_mdo_get_rx_sc_stats,
+	.mdo_get_rx_sa_stats = nxp_c45_mdo_get_rx_sa_stats,
+	.mdo_insert_tx_tag = nxp_c45_mdo_insert_tx_tag,
+	.needed_headroom = TJA11XX_TLV_TX_NEEDED_HEADROOM,
+	.needed_tailroom = TJA11XX_TLV_NEEDED_TAILROOM,
+};
+
+int nxp_c45_macsec_config_init(struct phy_device *phydev)
+{
+	struct nxp_c45_phy *priv = phydev->priv;
+	int ret;
+
+	if (!priv->macsec)
+		return 0;
+
+	ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_PORT_FUNC_ENABLES,
+			       MACSEC_EN | ADAPTER_EN);
+	if (ret)
+		return ret;
+
+	ret = nxp_c45_macsec_write(phydev, ADPTR_CNTRL, ADPTR_CNTRL_CONFIG_EN |
+				   ADPTR_CNTRL_ADPTR_EN);
+	if (ret)
+		return ret;
+
+	ret = nxp_c45_macsec_write(phydev, ADPTR_TX_TAG_CNTRL,
+				   ADPTR_TX_TAG_CNTRL_ENA);
+	if (ret)
+		return ret;
+
+	ret = nxp_c45_macsec_write(phydev, ADPTR_CNTRL, ADPTR_CNTRL_ADPTR_EN);
+	if (ret)
+		return ret;
+
+	ret = nxp_c45_macsec_write(phydev, MACSEC_TPNET, PN_WRAP_THRESHOLD);
+	if (ret)
+		return ret;
+
+	/* Set MKA filter. */
+	ret = nxp_c45_macsec_write(phydev, MACSEC_UPFR0D2, ETH_P_PAE);
+	if (ret)
+		return ret;
+
+	ret = nxp_c45_macsec_write(phydev, MACSEC_UPFR0M1, MACSEC_OVP);
+	if (ret)
+		return ret;
+
+	ret = nxp_c45_macsec_write(phydev, MACSEC_UPFR0M2, ETYPE_MASK);
+	if (ret)
+		return ret;
+
+	ret = nxp_c45_macsec_write(phydev, MACSEC_UPFR0R, MACSEC_UPFR_EN);
+
+	return ret;
+}
+
+int nxp_c45_macsec_probe(struct phy_device *phydev)
+{
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct device *dev = &phydev->mdio.dev;
+
+	priv->macsec = devm_kzalloc(dev, sizeof(*priv->macsec), GFP_KERNEL);
+	if (!priv->macsec)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&priv->macsec->secy_list);
+	phydev->macsec_ops = &nxp_c45_macsec_ops;
+
+	return 0;
+}
+
+void nxp_c45_macsec_remove(struct phy_device *phydev)
+{
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct nxp_c45_secy *secy_p, *secy_t;
+	struct nxp_c45_sa *sa_p, *sa_t;
+	struct list_head *secy_list;
+
+	if (!priv->macsec)
+		return;
+
+	secy_list = &priv->macsec->secy_list;
+	nxp_c45_macsec_en(phydev, false);
+
+	list_for_each_entry_safe(secy_p, secy_t, secy_list, list) {
+		list_for_each_entry_safe(sa_p, sa_t, &secy_p->sa_list, list)
+			nxp_c45_sa_free(sa_p);
+		nxp_c45_secy_free(secy_p);
+	}
+}
+
+void nxp_c45_handle_macsec_interrupt(struct phy_device *phydev,
+				     irqreturn_t *ret)
+{
+	struct nxp_c45_phy *priv = phydev->priv;
+	struct nxp_c45_secy *secy;
+	struct nxp_c45_sa *sa;
+	u8 encoding_sa;
+	int secy_id;
+	u32 reg = 0;
+
+	if (!priv->macsec)
+		return;
+
+	do {
+		nxp_c45_macsec_read(phydev, MACSEC_EVR, &reg);
+		if (!reg)
+			return;
+
+		secy_id = MACSEC_REG_SIZE - ffs(reg);
+		secy = nxp_c45_find_secy_by_id(&priv->macsec->secy_list,
+					       secy_id);
+		if (IS_ERR(secy)) {
+			WARN_ON(1);
+			goto macsec_ack_irq;
+		}
+
+		encoding_sa = secy->secy->tx_sc.encoding_sa;
+		phydev_dbg(phydev, "pn_wrapped: TX SC %d, encoding_sa %u\n",
+			   secy->secy_id, encoding_sa);
+
+		sa = nxp_c45_find_sa(&secy->sa_list, TX_SA, encoding_sa);
+		if (!IS_ERR(sa))
+			macsec_pn_wrapped(secy->secy, sa->sa);
+		else
+			WARN_ON(1);
+
+macsec_ack_irq:
+		nxp_c45_macsec_write(phydev, MACSEC_EVR,
+				     TX_SC_BIT(secy_id));
+		*ret = IRQ_HANDLED;
+	} while (reg);
+}
diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index 7ab080ff02df..3cf614b4cd52 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* NXP C45 PHY driver
- * Copyright (C) 2021 NXP
+ * Copyright 2021-2023 NXP
  * Author: Radu Pirea <radu-nicolae.pirea@oss.nxp.com>
  */
 
@@ -14,9 +14,10 @@
 #include <linux/processor.h>
 #include <linux/property.h>
 #include <linux/ptp_classify.h>
-#include <linux/ptp_clock_kernel.h>
 #include <linux/net_tstamp.h>
 
+#include "nxp-c45-tja11xx.h"
+
 #define PHY_ID_TJA_1103			0x001BB010
 #define PHY_ID_TJA_1120			0x001BB031
 
@@ -75,9 +76,11 @@
 #define PORT_CONTROL_EN			BIT(14)
 
 #define VEND1_PORT_ABILITIES		0x8046
+#define MACSEC_ABILITY			BIT(5)
 #define PTP_ABILITY			BIT(3)
 
 #define VEND1_PORT_FUNC_IRQ_EN		0x807A
+#define MACSEC_IRQS			BIT(5)
 #define PTP_IRQS			BIT(3)
 
 #define VEND1_PTP_IRQ_ACK		0x9008
@@ -148,7 +151,6 @@
 
 #define TS_SEC_MASK			GENMASK(1, 0)
 
-#define VEND1_PORT_FUNC_ENABLES		0x8048
 #define PTP_ENABLE			BIT(3)
 #define PHY_TEST_ENABLE			BIT(0)
 
@@ -281,25 +283,6 @@ struct nxp_c45_phy_data {
 			    irqreturn_t *irq_status);
 };
 
-struct nxp_c45_phy {
-	const struct nxp_c45_phy_data *phy_data;
-	struct phy_device *phydev;
-	struct mii_timestamper mii_ts;
-	struct ptp_clock *ptp_clock;
-	struct ptp_clock_info caps;
-	struct sk_buff_head tx_queue;
-	struct sk_buff_head rx_queue;
-	/* used to access the PTP registers atomic */
-	struct mutex ptp_lock;
-	int hwts_tx;
-	int hwts_rx;
-	u32 tx_delay;
-	u32 rx_delay;
-	struct timespec64 extts_ts;
-	int extts_index;
-	bool extts;
-};
-
 static const
 struct nxp_c45_phy_data *nxp_c45_get_data(struct phy_device *phydev)
 {
@@ -1022,24 +1005,21 @@ static bool nxp_c45_rxtstamp(struct mii_timestamper *mii_ts,
 }
 
 static int nxp_c45_hwtstamp(struct mii_timestamper *mii_ts,
-			    struct ifreq *ifreq)
+			    struct kernel_hwtstamp_config *cfg,
+			    struct netlink_ext_ack *extack)
 {
 	struct nxp_c45_phy *priv = container_of(mii_ts, struct nxp_c45_phy,
 						mii_ts);
 	struct phy_device *phydev = priv->phydev;
 	const struct nxp_c45_phy_data *data;
-	struct hwtstamp_config cfg;
-
-	if (copy_from_user(&cfg, ifreq->ifr_data, sizeof(cfg)))
-		return -EFAULT;
 
-	if (cfg.tx_type < 0 || cfg.tx_type > HWTSTAMP_TX_ON)
+	if (cfg->tx_type < 0 || cfg->tx_type > HWTSTAMP_TX_ON)
 		return -ERANGE;
 
 	data = nxp_c45_get_data(phydev);
-	priv->hwts_tx = cfg.tx_type;
+	priv->hwts_tx = cfg->tx_type;
 
-	switch (cfg.rx_filter) {
+	switch (cfg->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		priv->hwts_rx = 0;
 		break;
@@ -1047,7 +1027,7 @@ static int nxp_c45_hwtstamp(struct mii_timestamper *mii_ts,
 	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
 		priv->hwts_rx = 1;
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
 		break;
 	default:
 		return -ERANGE;
@@ -1074,7 +1054,7 @@ static int nxp_c45_hwtstamp(struct mii_timestamper *mii_ts,
 		nxp_c45_clear_reg_field(phydev, &data->regmap->irq_egr_ts_en);
 
 nxp_c45_no_ptp_irq:
-	return copy_to_user(ifreq->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	return 0;
 }
 
 static int nxp_c45_ts_info(struct mii_timestamper *mii_ts,
@@ -1218,12 +1198,25 @@ static int nxp_c45_start_op(struct phy_device *phydev)
 
 static int nxp_c45_config_intr(struct phy_device *phydev)
 {
-	if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+	int ret;
+
+	if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+		ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND1,
+				       VEND1_PORT_FUNC_IRQ_EN, MACSEC_IRQS);
+		if (ret)
+			return ret;
+
 		return phy_set_bits_mmd(phydev, MDIO_MMD_VEND1,
 					VEND1_PHY_IRQ_EN, PHY_IRQ_LINK_EVENT);
-	else
-		return phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
-					  VEND1_PHY_IRQ_EN, PHY_IRQ_LINK_EVENT);
+	}
+
+	ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
+				 VEND1_PORT_FUNC_IRQ_EN, MACSEC_IRQS);
+	if (ret)
+		return ret;
+
+	return phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
+				  VEND1_PHY_IRQ_EN, PHY_IRQ_LINK_EVENT);
 }
 
 static int tja1103_config_intr(struct phy_device *phydev)
@@ -1289,6 +1282,7 @@ static irqreturn_t nxp_c45_handle_interrupt(struct phy_device *phydev)
 	}
 
 	data->nmi_handler(phydev, &ret);
+	nxp_c45_handle_macsec_interrupt(phydev, &ret);
 
 	return ret;
 }
@@ -1614,6 +1608,9 @@ static int nxp_c45_config_init(struct phy_device *phydev)
 
 	nxp_c45_counters_enable(phydev);
 	nxp_c45_ptp_init(phydev);
+	ret = nxp_c45_macsec_config_init(phydev);
+	if (ret)
+		return ret;
 
 	return nxp_c45_start_op(phydev);
 }
@@ -1629,7 +1626,9 @@ static int nxp_c45_get_features(struct phy_device *phydev)
 static int nxp_c45_probe(struct phy_device *phydev)
 {
 	struct nxp_c45_phy *priv;
-	int ptp_ability;
+	bool macsec_ability;
+	int phy_abilities;
+	bool ptp_ability;
 	int ret = 0;
 
 	priv = devm_kzalloc(&phydev->mdio.dev, sizeof(*priv), GFP_KERNEL);
@@ -1645,9 +1644,9 @@ static int nxp_c45_probe(struct phy_device *phydev)
 
 	mutex_init(&priv->ptp_lock);
 
-	ptp_ability = phy_read_mmd(phydev, MDIO_MMD_VEND1,
-				   VEND1_PORT_ABILITIES);
-	ptp_ability = !!(ptp_ability & PTP_ABILITY);
+	phy_abilities = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+				     VEND1_PORT_ABILITIES);
+	ptp_ability = !!(phy_abilities & PTP_ABILITY);
 	if (!ptp_ability) {
 		phydev_dbg(phydev, "the phy does not support PTP");
 		goto no_ptp_support;
@@ -1666,6 +1665,20 @@ static int nxp_c45_probe(struct phy_device *phydev)
 	}
 
 no_ptp_support:
+	macsec_ability = !!(phy_abilities & MACSEC_ABILITY);
+	if (!macsec_ability) {
+		phydev_info(phydev, "the phy does not support MACsec\n");
+		goto no_macsec_support;
+	}
+
+	if (IS_ENABLED(CONFIG_MACSEC)) {
+		ret = nxp_c45_macsec_probe(phydev);
+		phydev_dbg(phydev, "MACsec support enabled.");
+	} else {
+		phydev_dbg(phydev, "MACsec support not enabled even if the phy supports it");
+	}
+
+no_macsec_support:
 
 	return ret;
 }
@@ -1679,6 +1692,7 @@ static void nxp_c45_remove(struct phy_device *phydev)
 
 	skb_queue_purge(&priv->tx_queue);
 	skb_queue_purge(&priv->rx_queue);
+	nxp_c45_macsec_remove(phydev);
 }
 
 static void tja1103_counters_enable(struct phy_device *phydev)
diff --git a/drivers/net/phy/nxp-c45-tja11xx.h b/drivers/net/phy/nxp-c45-tja11xx.h
new file mode 100644
index 000000000000..f364fca68f0b
--- /dev/null
+++ b/drivers/net/phy/nxp-c45-tja11xx.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* NXP C45 PHY driver header file
+ * Copyright 2023 NXP
+ * Author: Radu Pirea <radu-nicolae.pirea@oss.nxp.com>
+ */
+
+#include <linux/ptp_clock_kernel.h>
+
+#define VEND1_PORT_FUNC_ENABLES		0x8048
+
+struct nxp_c45_macsec;
+
+struct nxp_c45_phy {
+	const struct nxp_c45_phy_data *phy_data;
+	struct phy_device *phydev;
+	struct mii_timestamper mii_ts;
+	struct ptp_clock *ptp_clock;
+	struct ptp_clock_info caps;
+	struct sk_buff_head tx_queue;
+	struct sk_buff_head rx_queue;
+	/* used to access the PTP registers atomic */
+	struct mutex ptp_lock;
+	int hwts_tx;
+	int hwts_rx;
+	u32 tx_delay;
+	u32 rx_delay;
+	struct timespec64 extts_ts;
+	int extts_index;
+	bool extts;
+	struct nxp_c45_macsec *macsec;
+};
+
+#if IS_ENABLED(CONFIG_MACSEC)
+int nxp_c45_macsec_config_init(struct phy_device *phydev);
+int nxp_c45_macsec_probe(struct phy_device *phydev);
+void nxp_c45_macsec_remove(struct phy_device *phydev);
+void nxp_c45_handle_macsec_interrupt(struct phy_device *phydev,
+				     irqreturn_t *ret);
+#else
+static inline
+int nxp_c45_macsec_config_init(struct phy_device *phydev)
+{
+	return 0;
+}
+
+static inline
+int nxp_c45_macsec_probe(struct phy_device *phydev)
+{
+	return 0;
+}
+
+static inline
+void nxp_c45_macsec_remove(struct phy_device *phydev)
+{
+}
+
+static inline
+void nxp_c45_handle_macsec_interrupt(struct phy_device *phydev,
+				     irqreturn_t *ret)
+{
+}
+#endif
diff --git a/drivers/net/phy/nxp-tja11xx.c b/drivers/net/phy/nxp-tja11xx.c
index a71399965142..2c263ae44b4f 100644
--- a/drivers/net/phy/nxp-tja11xx.c
+++ b/drivers/net/phy/nxp-tja11xx.c
@@ -415,7 +415,7 @@ static void tja11xx_get_strings(struct phy_device *phydev, u8 *data)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(tja11xx_hw_stats); i++)
-		ethtool_sprintf(&data, "%s", tja11xx_hw_stats[i].string);
+		ethtool_puts(&data, tja11xx_hw_stats[i].string);
 }
 
 static void tja11xx_get_stats(struct phy_device *phydev,
diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index 8e6fd4962c48..747d14bf152c 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -920,6 +920,79 @@ int genphy_c45_pma_baset1_read_abilities(struct phy_device *phydev)
 EXPORT_SYMBOL_GPL(genphy_c45_pma_baset1_read_abilities);
 
 /**
+ * genphy_c45_pma_read_ext_abilities - read supported link modes from PMA
+ * @phydev: target phy_device struct
+ *
+ * Read the supported link modes from the PMA/PMD extended ability register
+ * (Register 1.11).
+ */
+int genphy_c45_pma_read_ext_abilities(struct phy_device *phydev)
+{
+	int val;
+
+	val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_EXTABLE);
+	if (val < 0)
+		return val;
+
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_EXTABLE_10GBLRM);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_EXTABLE_10GBT);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_EXTABLE_10GBKX4);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_EXTABLE_10GBKR);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_EXTABLE_1000BT);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_EXTABLE_1000BKX);
+
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_EXTABLE_100BTX);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_EXTABLE_100BTX);
+
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_EXTABLE_10BT);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_EXTABLE_10BT);
+
+	if (val & MDIO_PMA_EXTABLE_NBT) {
+		val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD,
+				   MDIO_PMA_NG_EXTABLE);
+		if (val < 0)
+			return val;
+
+		linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT,
+				 phydev->supported,
+				 val & MDIO_PMA_NG_EXTABLE_2_5GBT);
+
+		linkmode_mod_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT,
+				 phydev->supported,
+				 val & MDIO_PMA_NG_EXTABLE_5GBT);
+	}
+
+	if (val & MDIO_PMA_EXTABLE_BT1) {
+		val = genphy_c45_pma_baset1_read_abilities(phydev);
+		if (val < 0)
+			return val;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(genphy_c45_pma_read_ext_abilities);
+
+/**
  * genphy_c45_pma_read_abilities - read supported link modes from PMA
  * @phydev: target phy_device struct
  *
@@ -962,63 +1035,9 @@ int genphy_c45_pma_read_abilities(struct phy_device *phydev)
 			 val & MDIO_PMA_STAT2_10GBER);
 
 	if (val & MDIO_PMA_STAT2_EXTABLE) {
-		val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_EXTABLE);
+		val = genphy_c45_pma_read_ext_abilities(phydev);
 		if (val < 0)
 			return val;
-
-		linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT,
-				 phydev->supported,
-				 val & MDIO_PMA_EXTABLE_10GBLRM);
-		linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
-				 phydev->supported,
-				 val & MDIO_PMA_EXTABLE_10GBT);
-		linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT,
-				 phydev->supported,
-				 val & MDIO_PMA_EXTABLE_10GBKX4);
-		linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
-				 phydev->supported,
-				 val & MDIO_PMA_EXTABLE_10GBKR);
-		linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
-				 phydev->supported,
-				 val & MDIO_PMA_EXTABLE_1000BT);
-		linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
-				 phydev->supported,
-				 val & MDIO_PMA_EXTABLE_1000BKX);
-
-		linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
-				 phydev->supported,
-				 val & MDIO_PMA_EXTABLE_100BTX);
-		linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT,
-				 phydev->supported,
-				 val & MDIO_PMA_EXTABLE_100BTX);
-
-		linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT,
-				 phydev->supported,
-				 val & MDIO_PMA_EXTABLE_10BT);
-		linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT,
-				 phydev->supported,
-				 val & MDIO_PMA_EXTABLE_10BT);
-
-		if (val & MDIO_PMA_EXTABLE_NBT) {
-			val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD,
-					   MDIO_PMA_NG_EXTABLE);
-			if (val < 0)
-				return val;
-
-			linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT,
-					 phydev->supported,
-					 val & MDIO_PMA_NG_EXTABLE_2_5GBT);
-
-			linkmode_mod_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT,
-					 phydev->supported,
-					 val & MDIO_PMA_NG_EXTABLE_5GBT);
-		}
-
-		if (val & MDIO_PMA_EXTABLE_BT1) {
-			val = genphy_c45_pma_baset1_read_abilities(phydev);
-			if (val < 0)
-				return val;
-		}
 	}
 
 	/* This is optional functionality. If not supported, we may get an error
diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index 966c93cbe616..15f349e5995a 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -540,6 +540,28 @@ static void mmd_phy_indirect(struct mii_bus *bus, int phy_addr, int devad,
 			devad | MII_MMD_CTRL_NOINCR);
 }
 
+static int mmd_phy_read(struct mii_bus *bus, int phy_addr, bool is_c45,
+			int devad, u32 regnum)
+{
+	if (is_c45)
+		return __mdiobus_c45_read(bus, phy_addr, devad, regnum);
+
+	mmd_phy_indirect(bus, phy_addr, devad, regnum);
+	/* Read the content of the MMD's selected register */
+	return __mdiobus_read(bus, phy_addr, MII_MMD_DATA);
+}
+
+static int mmd_phy_write(struct mii_bus *bus, int phy_addr, bool is_c45,
+			 int devad, u32 regnum, u16 val)
+{
+	if (is_c45)
+		return __mdiobus_c45_write(bus, phy_addr, devad, regnum, val);
+
+	mmd_phy_indirect(bus, phy_addr, devad, regnum);
+	/* Write the data into MMD's selected register */
+	return __mdiobus_write(bus, phy_addr, MII_MMD_DATA, val);
+}
+
 /**
  * __phy_read_mmd - Convenience function for reading a register
  * from an MMD on a given PHY.
@@ -551,26 +573,14 @@ static void mmd_phy_indirect(struct mii_bus *bus, int phy_addr, int devad,
  */
 int __phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum)
 {
-	int val;
-
 	if (regnum > (u16)~0 || devad > 32)
 		return -EINVAL;
 
-	if (phydev->drv && phydev->drv->read_mmd) {
-		val = phydev->drv->read_mmd(phydev, devad, regnum);
-	} else if (phydev->is_c45) {
-		val = __mdiobus_c45_read(phydev->mdio.bus, phydev->mdio.addr,
-					 devad, regnum);
-	} else {
-		struct mii_bus *bus = phydev->mdio.bus;
-		int phy_addr = phydev->mdio.addr;
-
-		mmd_phy_indirect(bus, phy_addr, devad, regnum);
+	if (phydev->drv && phydev->drv->read_mmd)
+		return phydev->drv->read_mmd(phydev, devad, regnum);
 
-		/* Read the content of the MMD's selected register */
-		val = __mdiobus_read(bus, phy_addr, MII_MMD_DATA);
-	}
-	return val;
+	return mmd_phy_read(phydev->mdio.bus, phydev->mdio.addr,
+			    phydev->is_c45, devad, regnum);
 }
 EXPORT_SYMBOL(__phy_read_mmd);
 
@@ -607,28 +617,14 @@ EXPORT_SYMBOL(phy_read_mmd);
  */
 int __phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val)
 {
-	int ret;
-
 	if (regnum > (u16)~0 || devad > 32)
 		return -EINVAL;
 
-	if (phydev->drv && phydev->drv->write_mmd) {
-		ret = phydev->drv->write_mmd(phydev, devad, regnum, val);
-	} else if (phydev->is_c45) {
-		ret = __mdiobus_c45_write(phydev->mdio.bus, phydev->mdio.addr,
-					  devad, regnum, val);
-	} else {
-		struct mii_bus *bus = phydev->mdio.bus;
-		int phy_addr = phydev->mdio.addr;
-
-		mmd_phy_indirect(bus, phy_addr, devad, regnum);
+	if (phydev->drv && phydev->drv->write_mmd)
+		return phydev->drv->write_mmd(phydev, devad, regnum, val);
 
-		/* Write the data into MMD's selected register */
-		__mdiobus_write(bus, phy_addr, MII_MMD_DATA, val);
-
-		ret = 0;
-	}
-	return ret;
+	return mmd_phy_write(phydev->mdio.bus, phydev->mdio.addr,
+			     phydev->is_c45, devad, regnum, val);
 }
 EXPORT_SYMBOL(__phy_write_mmd);
 
@@ -655,6 +651,146 @@ int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val)
 EXPORT_SYMBOL(phy_write_mmd);
 
 /**
+ * __phy_package_read_mmd - read MMD reg relative to PHY package base addr
+ * @phydev: The phy_device struct
+ * @addr_offset: The offset to be added to PHY package base_addr
+ * @devad: The MMD to read from
+ * @regnum: The register on the MMD to read
+ *
+ * Convenience helper for reading a register of an MMD on a given PHY
+ * using the PHY package base address. The base address is added to
+ * the addr_offset value.
+ *
+ * Same calling rules as for __phy_read();
+ *
+ * NOTE: It's assumed that the entire PHY package is either C22 or C45.
+ */
+int __phy_package_read_mmd(struct phy_device *phydev,
+			   unsigned int addr_offset, int devad,
+			   u32 regnum)
+{
+	int addr = phy_package_address(phydev, addr_offset);
+
+	if (addr < 0)
+		return addr;
+
+	if (regnum > (u16)~0 || devad > 32)
+		return -EINVAL;
+
+	return mmd_phy_read(phydev->mdio.bus, addr, phydev->is_c45, devad,
+			    regnum);
+}
+EXPORT_SYMBOL(__phy_package_read_mmd);
+
+/**
+ * phy_package_read_mmd - read MMD reg relative to PHY package base addr
+ * @phydev: The phy_device struct
+ * @addr_offset: The offset to be added to PHY package base_addr
+ * @devad: The MMD to read from
+ * @regnum: The register on the MMD to read
+ *
+ * Convenience helper for reading a register of an MMD on a given PHY
+ * using the PHY package base address. The base address is added to
+ * the addr_offset value.
+ *
+ * Same calling rules as for phy_read();
+ *
+ * NOTE: It's assumed that the entire PHY package is either C22 or C45.
+ */
+int phy_package_read_mmd(struct phy_device *phydev,
+			 unsigned int addr_offset, int devad,
+			 u32 regnum)
+{
+	int addr = phy_package_address(phydev, addr_offset);
+	int val;
+
+	if (addr < 0)
+		return addr;
+
+	if (regnum > (u16)~0 || devad > 32)
+		return -EINVAL;
+
+	phy_lock_mdio_bus(phydev);
+	val = mmd_phy_read(phydev->mdio.bus, addr, phydev->is_c45, devad,
+			   regnum);
+	phy_unlock_mdio_bus(phydev);
+
+	return val;
+}
+EXPORT_SYMBOL(phy_package_read_mmd);
+
+/**
+ * __phy_package_write_mmd - write MMD reg relative to PHY package base addr
+ * @phydev: The phy_device struct
+ * @addr_offset: The offset to be added to PHY package base_addr
+ * @devad: The MMD to write to
+ * @regnum: The register on the MMD to write
+ * @val: value to write to @regnum
+ *
+ * Convenience helper for writing a register of an MMD on a given PHY
+ * using the PHY package base address. The base address is added to
+ * the addr_offset value.
+ *
+ * Same calling rules as for __phy_write();
+ *
+ * NOTE: It's assumed that the entire PHY package is either C22 or C45.
+ */
+int __phy_package_write_mmd(struct phy_device *phydev,
+			    unsigned int addr_offset, int devad,
+			    u32 regnum, u16 val)
+{
+	int addr = phy_package_address(phydev, addr_offset);
+
+	if (addr < 0)
+		return addr;
+
+	if (regnum > (u16)~0 || devad > 32)
+		return -EINVAL;
+
+	return mmd_phy_write(phydev->mdio.bus, addr, phydev->is_c45, devad,
+			     regnum, val);
+}
+EXPORT_SYMBOL(__phy_package_write_mmd);
+
+/**
+ * phy_package_write_mmd - write MMD reg relative to PHY package base addr
+ * @phydev: The phy_device struct
+ * @addr_offset: The offset to be added to PHY package base_addr
+ * @devad: The MMD to write to
+ * @regnum: The register on the MMD to write
+ * @val: value to write to @regnum
+ *
+ * Convenience helper for writing a register of an MMD on a given PHY
+ * using the PHY package base address. The base address is added to
+ * the addr_offset value.
+ *
+ * Same calling rules as for phy_write();
+ *
+ * NOTE: It's assumed that the entire PHY package is either C22 or C45.
+ */
+int phy_package_write_mmd(struct phy_device *phydev,
+			  unsigned int addr_offset, int devad,
+			  u32 regnum, u16 val)
+{
+	int addr = phy_package_address(phydev, addr_offset);
+	int ret;
+
+	if (addr < 0)
+		return addr;
+
+	if (regnum > (u16)~0 || devad > 32)
+		return -EINVAL;
+
+	phy_lock_mdio_bus(phydev);
+	ret = mmd_phy_write(phydev->mdio.bus, addr, phydev->is_c45, devad,
+			    regnum, val);
+	phy_unlock_mdio_bus(phydev);
+
+	return ret;
+}
+EXPORT_SYMBOL(phy_package_write_mmd);
+
+/**
  * phy_modify_changed - Function for modifying a PHY register
  * @phydev: the phy_device struct
  * @regnum: register number to modify
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index a5fa077650e8..3376e58e2b88 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -325,9 +325,13 @@ EXPORT_SYMBOL(phy_ethtool_ksettings_get);
 int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd)
 {
 	struct mii_ioctl_data *mii_data = if_mii(ifr);
+	struct kernel_hwtstamp_config kernel_cfg;
+	struct netlink_ext_ack extack = {};
 	u16 val = mii_data->val_in;
 	bool change_autoneg = false;
+	struct hwtstamp_config cfg;
 	int prtad, devad;
+	int ret;
 
 	switch (cmd) {
 	case SIOCGMIIPHY:
@@ -411,8 +415,21 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd)
 		return 0;
 
 	case SIOCSHWTSTAMP:
-		if (phydev->mii_ts && phydev->mii_ts->hwtstamp)
-			return phydev->mii_ts->hwtstamp(phydev->mii_ts, ifr);
+		if (phydev->mii_ts && phydev->mii_ts->hwtstamp) {
+			if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
+				return -EFAULT;
+
+			hwtstamp_config_to_kernel(&kernel_cfg, &cfg);
+			ret = phydev->mii_ts->hwtstamp(phydev->mii_ts, &kernel_cfg, &extack);
+			if (ret)
+				return ret;
+
+			hwtstamp_config_from_kernel(&cfg, &kernel_cfg);
+			if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)))
+				return -EFAULT;
+
+			return 0;
+		}
 		fallthrough;
 
 	default:
@@ -469,7 +486,7 @@ int __phy_hwtstamp_get(struct phy_device *phydev,
 	if (!phydev)
 		return -ENODEV;
 
-	return phy_mii_ioctl(phydev, config->ifr, SIOCGHWTSTAMP);
+	return -EOPNOTSUPP;
 }
 
 /**
@@ -486,7 +503,10 @@ int __phy_hwtstamp_set(struct phy_device *phydev,
 	if (!phydev)
 		return -ENODEV;
 
-	return phy_mii_ioctl(phydev, config->ifr, SIOCSHWTSTAMP);
+	if (phydev->mii_ts && phydev->mii_ts->hwtstamp)
+		return phydev->mii_ts->hwtstamp(phydev->mii_ts, config, extack);
+
+	return -EOPNOTSUPP;
 }
 
 /**
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 2ce74593d6e4..3611ea64875e 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -654,6 +654,7 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id,
 	mdiodev->flags = MDIO_DEVICE_FLAG_PHY;
 	mdiodev->device_free = phy_mdio_device_free;
 	mdiodev->device_remove = phy_mdio_device_remove;
+	mdiodev->reset_state = -1;
 
 	dev->speed = SPEED_UNKNOWN;
 	dev->duplex = DUPLEX_UNKNOWN;
@@ -1235,18 +1236,19 @@ int phy_init_hw(struct phy_device *phydev)
 
 	if (phydev->drv->soft_reset) {
 		ret = phydev->drv->soft_reset(phydev);
+		if (ret < 0)
+			return ret;
+
 		/* see comment in genphy_soft_reset for an explanation */
-		if (!ret)
-			phydev->suspended = 0;
+		phydev->suspended = 0;
 	}
 
-	if (ret < 0)
-		return ret;
-
 	ret = phy_scan_fixups(phydev);
 	if (ret < 0)
 		return ret;
 
+	phy_interface_zero(phydev->possible_interfaces);
+
 	if (phydev->drv->config_init) {
 		ret = phydev->drv->config_init(phydev);
 		if (ret < 0)
@@ -1548,7 +1550,8 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 		goto error;
 
 	phy_resume(phydev);
-	phy_led_triggers_register(phydev);
+	if (!phydev->is_on_sfp_module)
+		phy_led_triggers_register(phydev);
 
 	/**
 	 * If the external phy used by current mac interface is managed by
@@ -1649,20 +1652,22 @@ EXPORT_SYMBOL_GPL(phy_driver_is_genphy_10g);
 /**
  * phy_package_join - join a common PHY group
  * @phydev: target phy_device struct
- * @addr: cookie and PHY address for global register access
+ * @base_addr: cookie and base PHY address of PHY package for offset
+ *   calculation of global register access
  * @priv_size: if non-zero allocate this amount of bytes for private data
  *
  * This joins a PHY group and provides a shared storage for all phydevs in
  * this group. This is intended to be used for packages which contain
  * more than one PHY, for example a quad PHY transceiver.
  *
- * The addr parameter serves as a cookie which has to have the same value
- * for all members of one group and as a PHY address to access generic
- * registers of a PHY package. Usually, one of the PHY addresses of the
- * different PHYs in the package provides access to these global registers.
+ * The base_addr parameter serves as cookie which has to have the same values
+ * for all members of one group and as the base PHY address of the PHY package
+ * for offset calculation to access generic registers of a PHY package.
+ * Usually, one of the PHY addresses of the different PHYs in the package
+ * provides access to these global registers.
  * The address which is given here, will be used in the phy_package_read()
- * and phy_package_write() convenience functions. If your PHY doesn't have
- * global registers you can just pick any of the PHY addresses.
+ * and phy_package_write() convenience functions as base and added to the
+ * passed offset in those functions.
  *
  * This will set the shared pointer of the phydev to the shared storage.
  * If this is the first call for a this cookie the shared storage will be
@@ -1672,17 +1677,17 @@ EXPORT_SYMBOL_GPL(phy_driver_is_genphy_10g);
  * Returns < 1 on error, 0 on success. Esp. calling phy_package_join()
  * with the same cookie but a different priv_size is an error.
  */
-int phy_package_join(struct phy_device *phydev, int addr, size_t priv_size)
+int phy_package_join(struct phy_device *phydev, int base_addr, size_t priv_size)
 {
 	struct mii_bus *bus = phydev->mdio.bus;
 	struct phy_package_shared *shared;
 	int ret;
 
-	if (addr < 0 || addr >= PHY_MAX_ADDR)
+	if (base_addr < 0 || base_addr >= PHY_MAX_ADDR)
 		return -EINVAL;
 
 	mutex_lock(&bus->shared_lock);
-	shared = bus->shared[addr];
+	shared = bus->shared[base_addr];
 	if (!shared) {
 		ret = -ENOMEM;
 		shared = kzalloc(sizeof(*shared), GFP_KERNEL);
@@ -1694,9 +1699,9 @@ int phy_package_join(struct phy_device *phydev, int addr, size_t priv_size)
 				goto err_free;
 			shared->priv_size = priv_size;
 		}
-		shared->addr = addr;
+		shared->base_addr = base_addr;
 		refcount_set(&shared->refcnt, 1);
-		bus->shared[addr] = shared;
+		bus->shared[base_addr] = shared;
 	} else {
 		ret = -EINVAL;
 		if (priv_size && priv_size != shared->priv_size)
@@ -1734,7 +1739,7 @@ void phy_package_leave(struct phy_device *phydev)
 		return;
 
 	if (refcount_dec_and_mutex_lock(&shared->refcnt, &bus->shared_lock)) {
-		bus->shared[shared->addr] = NULL;
+		bus->shared[shared->base_addr] = NULL;
 		mutex_unlock(&bus->shared_lock);
 		kfree(shared->priv);
 		kfree(shared);
@@ -1753,7 +1758,8 @@ static void devm_phy_package_leave(struct device *dev, void *res)
  * devm_phy_package_join - resource managed phy_package_join()
  * @dev: device that is registering this PHY package
  * @phydev: target phy_device struct
- * @addr: cookie and PHY address for global register access
+ * @base_addr: cookie and base PHY address of PHY package for offset
+ *   calculation of global register access
  * @priv_size: if non-zero allocate this amount of bytes for private data
  *
  * Managed phy_package_join(). Shared storage fetched by this function,
@@ -1761,7 +1767,7 @@ static void devm_phy_package_leave(struct device *dev, void *res)
  * phy_package_join() for more information.
  */
 int devm_phy_package_join(struct device *dev, struct phy_device *phydev,
-			  int addr, size_t priv_size)
+			  int base_addr, size_t priv_size)
 {
 	struct phy_device **ptr;
 	int ret;
@@ -1771,7 +1777,7 @@ int devm_phy_package_join(struct device *dev, struct phy_device *phydev,
 	if (!ptr)
 		return -ENOMEM;
 
-	ret = phy_package_join(phydev, addr, priv_size);
+	ret = phy_package_join(phydev, base_addr, priv_size);
 
 	if (!ret) {
 		*ptr = phydev;
@@ -1817,7 +1823,8 @@ void phy_detach(struct phy_device *phydev)
 	}
 	phydev->phylink = NULL;
 
-	phy_led_triggers_unregister(phydev);
+	if (!phydev->is_on_sfp_module)
+		phy_led_triggers_unregister(phydev);
 
 	if (phydev->mdio.dev.driver)
 		module_put(phydev->mdio.dev.driver->owner);
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 25c19496a336..ed0b4ccaa6a6 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -121,6 +121,19 @@ do {									\
 })
 #endif
 
+static const phy_interface_t phylink_sfp_interface_preference[] = {
+	PHY_INTERFACE_MODE_25GBASER,
+	PHY_INTERFACE_MODE_USXGMII,
+	PHY_INTERFACE_MODE_10GBASER,
+	PHY_INTERFACE_MODE_5GBASER,
+	PHY_INTERFACE_MODE_2500BASEX,
+	PHY_INTERFACE_MODE_SGMII,
+	PHY_INTERFACE_MODE_1000BASEX,
+	PHY_INTERFACE_MODE_100BASEX,
+};
+
+static DECLARE_PHY_INTERFACE_MASK(phylink_sfp_interfaces);
+
 /**
  * phylink_set_port_modes() - set the port type modes in the ethtool mask
  * @mask: ethtool link mode mask
@@ -689,28 +702,48 @@ static int phylink_validate_mac_and_pcs(struct phylink *pl,
 	return phylink_is_empty_linkmode(supported) ? -EINVAL : 0;
 }
 
-static int phylink_validate_mask(struct phylink *pl, unsigned long *supported,
+static void phylink_validate_one(struct phylink *pl, struct phy_device *phy,
+				 const unsigned long *supported,
+				 const struct phylink_link_state *state,
+				 phy_interface_t interface,
+				 unsigned long *accum_supported,
+				 unsigned long *accum_advertising)
+{
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(tmp_supported);
+	struct phylink_link_state tmp_state;
+
+	linkmode_copy(tmp_supported, supported);
+
+	tmp_state = *state;
+	tmp_state.interface = interface;
+
+	if (phy)
+		tmp_state.rate_matching = phy_get_rate_matching(phy, interface);
+
+	if (!phylink_validate_mac_and_pcs(pl, tmp_supported, &tmp_state)) {
+		phylink_dbg(pl, " interface %u (%s) rate match %s supports %*pbl\n",
+			    interface, phy_modes(interface),
+			    phy_rate_matching_to_str(tmp_state.rate_matching),
+			    __ETHTOOL_LINK_MODE_MASK_NBITS, tmp_supported);
+
+		linkmode_or(accum_supported, accum_supported, tmp_supported);
+		linkmode_or(accum_advertising, accum_advertising,
+			    tmp_state.advertising);
+	}
+}
+
+static int phylink_validate_mask(struct phylink *pl, struct phy_device *phy,
+				 unsigned long *supported,
 				 struct phylink_link_state *state,
 				 const unsigned long *interfaces)
 {
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(all_adv) = { 0, };
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(all_s) = { 0, };
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(s);
-	struct phylink_link_state t;
-	int intf;
-
-	for (intf = 0; intf < PHY_INTERFACE_MODE_MAX; intf++) {
-		if (test_bit(intf, interfaces)) {
-			linkmode_copy(s, supported);
-
-			t = *state;
-			t.interface = intf;
-			if (!phylink_validate_mac_and_pcs(pl, s, &t)) {
-				linkmode_or(all_s, all_s, s);
-				linkmode_or(all_adv, all_adv, t.advertising);
-			}
-		}
-	}
+	int interface;
+
+	for_each_set_bit(interface, interfaces, PHY_INTERFACE_MODE_MAX)
+		phylink_validate_one(pl, phy, supported, state, interface,
+				     all_s, all_adv);
 
 	linkmode_copy(supported, all_s);
 	linkmode_copy(state->advertising, all_adv);
@@ -724,7 +757,8 @@ static int phylink_validate(struct phylink *pl, unsigned long *supported,
 	const unsigned long *interfaces = pl->config->supported_interfaces;
 
 	if (state->interface == PHY_INTERFACE_MODE_NA)
-		return phylink_validate_mask(pl, supported, state, interfaces);
+		return phylink_validate_mask(pl, NULL, supported, state,
+					     interfaces);
 
 	if (!test_bit(state->interface, interfaces))
 		return -EINVAL;
@@ -805,7 +839,7 @@ static int phylink_parse_fixedlink(struct phylink *pl,
 		phylink_warn(pl, "fixed link specifies half duplex for %dMbps link?\n",
 			     pl->link_config.speed);
 
-	bitmap_fill(pl->supported, __ETHTOOL_LINK_MODE_MASK_NBITS);
+	linkmode_fill(pl->supported);
 	linkmode_copy(pl->link_config.advertising, pl->supported);
 	phylink_validate(pl, pl->supported, &pl->link_config);
 
@@ -849,6 +883,7 @@ static int phylink_parse_mode(struct phylink *pl,
 {
 	struct fwnode_handle *dn;
 	const char *managed;
+	unsigned long caps;
 
 	dn = fwnode_get_named_child_node(fwnode, "fixed-link");
 	if (dn || fwnode_property_present(fwnode, "fixed-link"))
@@ -881,80 +916,18 @@ static int phylink_parse_mode(struct phylink *pl,
 		case PHY_INTERFACE_MODE_RGMII_RXID:
 		case PHY_INTERFACE_MODE_RGMII_TXID:
 		case PHY_INTERFACE_MODE_RTBI:
-			phylink_set(pl->supported, 10baseT_Half);
-			phylink_set(pl->supported, 10baseT_Full);
-			phylink_set(pl->supported, 100baseT_Half);
-			phylink_set(pl->supported, 100baseT_Full);
-			phylink_set(pl->supported, 1000baseT_Half);
-			phylink_set(pl->supported, 1000baseT_Full);
-			break;
-
 		case PHY_INTERFACE_MODE_1000BASEX:
-			phylink_set(pl->supported, 1000baseX_Full);
-			break;
-
 		case PHY_INTERFACE_MODE_2500BASEX:
-			phylink_set(pl->supported, 2500baseX_Full);
-			break;
-
 		case PHY_INTERFACE_MODE_5GBASER:
-			phylink_set(pl->supported, 5000baseT_Full);
-			break;
-
 		case PHY_INTERFACE_MODE_25GBASER:
-			phylink_set(pl->supported, 25000baseCR_Full);
-			phylink_set(pl->supported, 25000baseKR_Full);
-			phylink_set(pl->supported, 25000baseSR_Full);
-			fallthrough;
 		case PHY_INTERFACE_MODE_USXGMII:
 		case PHY_INTERFACE_MODE_10GKR:
 		case PHY_INTERFACE_MODE_10GBASER:
-			phylink_set(pl->supported, 10baseT_Half);
-			phylink_set(pl->supported, 10baseT_Full);
-			phylink_set(pl->supported, 100baseT_Half);
-			phylink_set(pl->supported, 100baseT_Full);
-			phylink_set(pl->supported, 1000baseT_Half);
-			phylink_set(pl->supported, 1000baseT_Full);
-			phylink_set(pl->supported, 1000baseX_Full);
-			phylink_set(pl->supported, 1000baseKX_Full);
-			phylink_set(pl->supported, 2500baseT_Full);
-			phylink_set(pl->supported, 2500baseX_Full);
-			phylink_set(pl->supported, 5000baseT_Full);
-			phylink_set(pl->supported, 10000baseT_Full);
-			phylink_set(pl->supported, 10000baseKR_Full);
-			phylink_set(pl->supported, 10000baseKX4_Full);
-			phylink_set(pl->supported, 10000baseCR_Full);
-			phylink_set(pl->supported, 10000baseSR_Full);
-			phylink_set(pl->supported, 10000baseLR_Full);
-			phylink_set(pl->supported, 10000baseLRM_Full);
-			phylink_set(pl->supported, 10000baseER_Full);
-			break;
-
 		case PHY_INTERFACE_MODE_XLGMII:
-			phylink_set(pl->supported, 25000baseCR_Full);
-			phylink_set(pl->supported, 25000baseKR_Full);
-			phylink_set(pl->supported, 25000baseSR_Full);
-			phylink_set(pl->supported, 40000baseKR4_Full);
-			phylink_set(pl->supported, 40000baseCR4_Full);
-			phylink_set(pl->supported, 40000baseSR4_Full);
-			phylink_set(pl->supported, 40000baseLR4_Full);
-			phylink_set(pl->supported, 50000baseCR2_Full);
-			phylink_set(pl->supported, 50000baseKR2_Full);
-			phylink_set(pl->supported, 50000baseSR2_Full);
-			phylink_set(pl->supported, 50000baseKR_Full);
-			phylink_set(pl->supported, 50000baseSR_Full);
-			phylink_set(pl->supported, 50000baseCR_Full);
-			phylink_set(pl->supported, 50000baseLR_ER_FR_Full);
-			phylink_set(pl->supported, 50000baseDR_Full);
-			phylink_set(pl->supported, 100000baseKR4_Full);
-			phylink_set(pl->supported, 100000baseSR4_Full);
-			phylink_set(pl->supported, 100000baseCR4_Full);
-			phylink_set(pl->supported, 100000baseLR4_ER4_Full);
-			phylink_set(pl->supported, 100000baseKR2_Full);
-			phylink_set(pl->supported, 100000baseSR2_Full);
-			phylink_set(pl->supported, 100000baseCR2_Full);
-			phylink_set(pl->supported, 100000baseLR2_ER2_FR2_Full);
-			phylink_set(pl->supported, 100000baseDR2_Full);
+			caps = ~(MAC_SYM_PAUSE | MAC_ASYM_PAUSE);
+			caps = phylink_get_capabilities(pl->link_config.interface, caps,
+							RATE_MATCH_NONE);
+			phylink_caps_to_linkmodes(pl->supported, caps);
 			break;
 
 		default:
@@ -1101,6 +1074,72 @@ static void phylink_pcs_an_restart(struct phylink *pl)
 		pl->pcs->ops->pcs_an_restart(pl->pcs);
 }
 
+/**
+ * phylink_pcs_neg_mode() - helper to determine PCS inband mode
+ * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND.
+ * @interface: interface mode to be used
+ * @advertising: adertisement ethtool link mode mask
+ *
+ * Determines the negotiation mode to be used by the PCS, and returns
+ * one of:
+ *
+ * - %PHYLINK_PCS_NEG_NONE: interface mode does not support inband
+ * - %PHYLINK_PCS_NEG_OUTBAND: an out of band mode (e.g. reading the PHY)
+ *   will be used.
+ * - %PHYLINK_PCS_NEG_INBAND_DISABLED: inband mode selected but autoneg
+ *   disabled
+ * - %PHYLINK_PCS_NEG_INBAND_ENABLED: inband mode selected and autoneg enabled
+ *
+ * Note: this is for cases where the PCS itself is involved in negotiation
+ * (e.g. Clause 37, SGMII and similar) not Clause 73.
+ */
+static unsigned int phylink_pcs_neg_mode(unsigned int mode,
+					 phy_interface_t interface,
+					 const unsigned long *advertising)
+{
+	unsigned int neg_mode;
+
+	switch (interface) {
+	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_QSGMII:
+	case PHY_INTERFACE_MODE_QUSGMII:
+	case PHY_INTERFACE_MODE_USXGMII:
+		/* These protocols are designed for use with a PHY which
+		 * communicates its negotiation result back to the MAC via
+		 * inband communication. Note: there exist PHYs that run
+		 * with SGMII but do not send the inband data.
+		 */
+		if (!phylink_autoneg_inband(mode))
+			neg_mode = PHYLINK_PCS_NEG_OUTBAND;
+		else
+			neg_mode = PHYLINK_PCS_NEG_INBAND_ENABLED;
+		break;
+
+	case PHY_INTERFACE_MODE_1000BASEX:
+	case PHY_INTERFACE_MODE_2500BASEX:
+		/* 1000base-X is designed for use media-side for Fibre
+		 * connections, and thus the Autoneg bit needs to be
+		 * taken into account. We also do this for 2500base-X
+		 * as well, but drivers may not support this, so may
+		 * need to override this.
+		 */
+		if (!phylink_autoneg_inband(mode))
+			neg_mode = PHYLINK_PCS_NEG_OUTBAND;
+		else if (linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+					   advertising))
+			neg_mode = PHYLINK_PCS_NEG_INBAND_ENABLED;
+		else
+			neg_mode = PHYLINK_PCS_NEG_INBAND_DISABLED;
+		break;
+
+	default:
+		neg_mode = PHYLINK_PCS_NEG_NONE;
+		break;
+	}
+
+	return neg_mode;
+}
+
 static void phylink_major_config(struct phylink *pl, bool restart,
 				  const struct phylink_link_state *state)
 {
@@ -1640,7 +1679,7 @@ struct phylink *phylink_create(struct phylink_config *config,
 	__set_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state);
 	timer_setup(&pl->link_poll, phylink_fixed_poll, 0);
 
-	bitmap_fill(pl->supported, __ETHTOOL_LINK_MODE_MASK_NBITS);
+	linkmode_fill(pl->supported);
 	linkmode_copy(pl->link_config.advertising, pl->supported);
 	phylink_validate(pl, pl->supported, &pl->link_config);
 
@@ -1739,31 +1778,55 @@ static void phylink_phy_change(struct phy_device *phydev, bool up)
 		    phylink_pause_to_str(pl->phy_state.pause));
 }
 
-static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy,
-			       phy_interface_t interface)
+static int phylink_validate_phy(struct phylink *pl, struct phy_device *phy,
+				unsigned long *supported,
+				struct phylink_link_state *state)
 {
-	struct phylink_link_state config;
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported);
-	char *irq_str;
-	int ret;
+	DECLARE_PHY_INTERFACE_MASK(interfaces);
 
-	/*
-	 * This is the new way of dealing with flow control for PHYs,
-	 * as described by Timur Tabi in commit 529ed1275263 ("net: phy:
-	 * phy drivers should not set SUPPORTED_[Asym_]Pause") except
-	 * using our validate call to the MAC, we rely upon the MAC
-	 * clearing the bits from both supported and advertising fields.
+	/* If the PHY provides a bitmap of the interfaces it will be using
+	 * depending on the negotiated media speeds, use this to validate
+	 * which ethtool link modes can be used.
 	 */
-	phy_support_asym_pause(phy);
+	if (!phy_interface_empty(phy->possible_interfaces)) {
+		/* We only care about the union of the PHY's interfaces and
+		 * those which the host supports.
+		 */
+		phy_interface_and(interfaces, phy->possible_interfaces,
+				  pl->config->supported_interfaces);
 
-	memset(&config, 0, sizeof(config));
-	linkmode_copy(supported, phy->supported);
-	linkmode_copy(config.advertising, phy->advertising);
+		if (phy_interface_empty(interfaces)) {
+			phylink_err(pl, "PHY has no common interfaces\n");
+			return -EINVAL;
+		}
+
+		if (phy_on_sfp(phy)) {
+			/* If the PHY is on a SFP, limit the interfaces to
+			 * those that can be used with a SFP module.
+			 */
+			phy_interface_and(interfaces, interfaces,
+					  phylink_sfp_interfaces);
+
+			if (phy_interface_empty(interfaces)) {
+				phylink_err(pl, "SFP PHY's possible interfaces becomes empty\n");
+				return -EINVAL;
+			}
+		}
+
+		phylink_dbg(pl, "PHY %s uses interfaces %*pbl, validating %*pbl\n",
+			    phydev_name(phy),
+			    (int)PHY_INTERFACE_MODE_MAX,
+			    phy->possible_interfaces,
+			    (int)PHY_INTERFACE_MODE_MAX, interfaces);
+
+		return phylink_validate_mask(pl, phy, supported, state,
+					     interfaces);
+	}
 
 	/* Check whether we would use rate matching for the proposed interface
 	 * mode.
 	 */
-	config.rate_matching = phy_get_rate_matching(phy, interface);
+	state->rate_matching = phy_get_rate_matching(phy, state->interface);
 
 	/* Clause 45 PHYs may switch their Serdes lane between, e.g. 10GBASE-R,
 	 * 5GBASE-R, 2500BASE-X and SGMII if they are not using rate matching.
@@ -1776,15 +1839,38 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy,
 	 * against all interface modes, which may lead to more ethtool link
 	 * modes being advertised than are actually supported.
 	 */
-	if (phy->is_c45 && config.rate_matching == RATE_MATCH_NONE &&
-	    interface != PHY_INTERFACE_MODE_RXAUI &&
-	    interface != PHY_INTERFACE_MODE_XAUI &&
-	    interface != PHY_INTERFACE_MODE_USXGMII)
-		config.interface = PHY_INTERFACE_MODE_NA;
-	else
-		config.interface = interface;
+	if (phy->is_c45 && state->rate_matching == RATE_MATCH_NONE &&
+	    state->interface != PHY_INTERFACE_MODE_RXAUI &&
+	    state->interface != PHY_INTERFACE_MODE_XAUI &&
+	    state->interface != PHY_INTERFACE_MODE_USXGMII)
+		state->interface = PHY_INTERFACE_MODE_NA;
 
-	ret = phylink_validate(pl, supported, &config);
+	return phylink_validate(pl, supported, state);
+}
+
+static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy,
+			       phy_interface_t interface)
+{
+	struct phylink_link_state config;
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported);
+	char *irq_str;
+	int ret;
+
+	/*
+	 * This is the new way of dealing with flow control for PHYs,
+	 * as described by Timur Tabi in commit 529ed1275263 ("net: phy:
+	 * phy drivers should not set SUPPORTED_[Asym_]Pause") except
+	 * using our validate call to the MAC, we rely upon the MAC
+	 * clearing the bits from both supported and advertising fields.
+	 */
+	phy_support_asym_pause(phy);
+
+	memset(&config, 0, sizeof(config));
+	linkmode_copy(supported, phy->supported);
+	linkmode_copy(config.advertising, phy->advertising);
+	config.interface = interface;
+
+	ret = phylink_validate_phy(pl, phy, supported, &config);
 	if (ret) {
 		phylink_warn(pl, "validation of %s with support %*pb and advertisement %*pb failed: %pe\n",
 			     phy_modes(config.interface),
@@ -3005,19 +3091,6 @@ static void phylink_sfp_detach(void *upstream, struct sfp_bus *bus)
 	pl->netdev->sfp_bus = NULL;
 }
 
-static const phy_interface_t phylink_sfp_interface_preference[] = {
-	PHY_INTERFACE_MODE_25GBASER,
-	PHY_INTERFACE_MODE_USXGMII,
-	PHY_INTERFACE_MODE_10GBASER,
-	PHY_INTERFACE_MODE_5GBASER,
-	PHY_INTERFACE_MODE_2500BASEX,
-	PHY_INTERFACE_MODE_SGMII,
-	PHY_INTERFACE_MODE_1000BASEX,
-	PHY_INTERFACE_MODE_100BASEX,
-};
-
-static DECLARE_PHY_INTERFACE_MASK(phylink_sfp_interfaces);
-
 static phy_interface_t phylink_choose_sfp_interface(struct phylink *pl,
 						    const unsigned long *intf)
 {
@@ -3160,7 +3233,8 @@ static int phylink_sfp_config_optical(struct phylink *pl)
 	/* For all the interfaces that are supported, reduce the sfp_support
 	 * mask to only those link modes that can be supported.
 	 */
-	ret = phylink_validate_mask(pl, pl->sfp_support, &config, interfaces);
+	ret = phylink_validate_mask(pl, NULL, pl->sfp_support, &config,
+				    interfaces);
 	if (ret) {
 		phylink_err(pl, "unsupported SFP module: validation with support %*pb failed\n",
 			    __ETHTOOL_LINK_MODE_MASK_NBITS, support);
diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index 208a9393c2df..6fa679b36290 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -328,7 +328,7 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id,
 	 * modules use 2500Mbaud rather than 3100 or 3200Mbaud for
 	 * 2500BASE-X, so we allow some slack here.
 	 */
-	if (bitmap_empty(modes, __ETHTOOL_LINK_MODE_MASK_NBITS) && br_nom) {
+	if (linkmode_empty(modes) && br_nom) {
 		if (br_min <= 1300 && br_max >= 1200) {
 			phylink_set(modes, 1000baseX_Full);
 			__set_bit(PHY_INTERFACE_MODE_1000BASEX, interfaces);
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index 5468bd209fab..f75c9eb3958e 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -191,7 +191,7 @@ static const enum gpiod_flags gpio_flags[] = {
  * R_PHY_RETRY is the number of attempts.
  */
 #define T_PHY_RETRY		msecs_to_jiffies(50)
-#define R_PHY_RETRY		12
+#define R_PHY_RETRY		25
 
 /* SFP module presence detection is poor: the three MOD DEF signals are
  * the same length on the PCB, which means it's possible for MOD DEF 0 to
@@ -275,6 +275,7 @@ struct sfp {
 	unsigned int module_power_mW;
 	unsigned int module_t_start_up;
 	unsigned int module_t_wait;
+	unsigned int phy_t_retry;
 
 	unsigned int rate_kbd;
 	unsigned int rs_threshold_kbd;
@@ -372,18 +373,28 @@ static void sfp_fixup_10gbaset_30m(struct sfp *sfp)
 	sfp->id.base.extended_cc = SFF8024_ECC_10GBASE_T_SR;
 }
 
-static void sfp_fixup_rollball_proto(struct sfp *sfp, unsigned int secs)
+static void sfp_fixup_rollball(struct sfp *sfp)
 {
 	sfp->mdio_protocol = MDIO_I2C_ROLLBALL;
-	sfp->module_t_wait = msecs_to_jiffies(secs * 1000);
+
+	/* RollBall modules may disallow access to PHY registers for up to 25
+	 * seconds, and the reads return 0xffff before that. Increase the time
+	 * between PHY probe retries from 50ms to 1s so that we will wait for
+	 * the PHY for a sufficient amount of time.
+	 */
+	sfp->phy_t_retry = msecs_to_jiffies(1000);
 }
 
 static void sfp_fixup_fs_10gt(struct sfp *sfp)
 {
 	sfp_fixup_10gbaset_30m(sfp);
+	sfp_fixup_rollball(sfp);
 
-	// These SFPs need 4 seconds before the PHY can be accessed
-	sfp_fixup_rollball_proto(sfp, 4);
+	/* The RollBall fixup is not enough for FS modules, the AQR chip inside
+	 * them does not return 0xffff for PHY ID registers in all MMDs for the
+	 * while initializing. They need a 4 second wait before accessing PHY.
+	 */
+	sfp->module_t_wait = msecs_to_jiffies(4000);
 }
 
 static void sfp_fixup_halny_gsfp(struct sfp *sfp)
@@ -395,12 +406,6 @@ static void sfp_fixup_halny_gsfp(struct sfp *sfp)
 	sfp->state_hw_mask &= ~(SFP_F_TX_FAULT | SFP_F_LOS);
 }
 
-static void sfp_fixup_rollball(struct sfp *sfp)
-{
-	// Rollball SFPs need 25 seconds before the PHY can be accessed
-	sfp_fixup_rollball_proto(sfp, 25);
-}
-
 static void sfp_fixup_rollball_cc(struct sfp *sfp)
 {
 	sfp_fixup_rollball(sfp);
@@ -2332,6 +2337,7 @@ static int sfp_sm_mod_probe(struct sfp *sfp, bool report)
 
 	sfp->module_t_start_up = T_START_UP;
 	sfp->module_t_wait = T_WAIT;
+	sfp->phy_t_retry = T_PHY_RETRY;
 
 	sfp->state_ignore_mask = 0;
 
@@ -2629,7 +2635,11 @@ static void sfp_sm_main(struct sfp *sfp, unsigned int event)
 		ret = sfp_sm_probe_for_phy(sfp);
 		if (ret == -ENODEV) {
 			if (--sfp->sm_phy_retries) {
-				sfp_sm_next(sfp, SFP_S_INIT_PHY, T_PHY_RETRY);
+				sfp_sm_next(sfp, SFP_S_INIT_PHY,
+					    sfp->phy_t_retry);
+				dev_dbg(sfp->dev,
+					"no PHY detected, %u tries left\n",
+					sfp->sm_phy_retries);
 				break;
 			} else {
 				dev_info(sfp->dev, "no PHY detected\n");
@@ -3096,7 +3106,7 @@ static int sfp_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int sfp_remove(struct platform_device *pdev)
+static void sfp_remove(struct platform_device *pdev)
 {
 	struct sfp *sfp = platform_get_drvdata(pdev);
 
@@ -3106,8 +3116,6 @@ static int sfp_remove(struct platform_device *pdev)
 	rtnl_lock();
 	sfp_sm_event(sfp, SFP_E_REMOVE);
 	rtnl_unlock();
-
-	return 0;
 }
 
 static void sfp_shutdown(struct platform_device *pdev)
@@ -3128,7 +3136,7 @@ static void sfp_shutdown(struct platform_device *pdev)
 
 static struct platform_driver sfp_driver = {
 	.probe = sfp_probe,
-	.remove = sfp_remove,
+	.remove_new = sfp_remove,
 	.shutdown = sfp_shutdown,
 	.driver = {
 		.name = "sfp",
diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index 1c7306a1af13..150aea7c9c36 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -508,7 +508,7 @@ static void smsc_get_strings(struct phy_device *phydev, u8 *data)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(smsc_hw_stats); i++)
-		ethtool_sprintf(&data, "%s", smsc_hw_stats[i].string);
+		ethtool_puts(&data, smsc_hw_stats[i].string);
 }
 
 static u64 smsc_get_stat(struct phy_device *phydev, int i)
diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c
index fbaaa8c102a1..840da924708b 100644
--- a/drivers/net/ppp/ppp_async.c
+++ b/drivers/net/ppp/ppp_async.c
@@ -533,7 +533,7 @@ ppp_async_encode(struct asyncppp *ap)
 	proto = get_unaligned_be16(data);
 
 	/*
-	 * LCP packets with code values between 1 (configure-reqest)
+	 * LCP packets with code values between 1 (configure-request)
 	 * and 7 (code-reject) must be sent as though no options
 	 * had been negotiated.
 	 */
diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c
index ebcdffdf4f0e..52d05ce4a281 100644
--- a/drivers/net/ppp/ppp_synctty.c
+++ b/drivers/net/ppp/ppp_synctty.c
@@ -453,6 +453,10 @@ ppp_sync_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg)
 	case PPPIOCSMRU:
 		if (get_user(val, (int __user *) argp))
 			break;
+		if (val > U16_MAX) {
+			err = -EINVAL;
+			break;
+		}
 		if (val < PPP_MRU)
 			val = PPP_MRU;
 		ap->mru = val;
@@ -687,7 +691,7 @@ ppp_sync_input(struct syncppp *ap, const u8 *buf, const u8 *flags, int count)
 
 	/* strip address/control field if present */
 	p = skb->data;
-	if (p[0] == PPP_ALLSTATIONS && p[1] == PPP_UI) {
+	if (skb->len >= 2 && p[0] == PPP_ALLSTATIONS && p[1] == PPP_UI) {
 		/* chop off address/control */
 		if (skb->len < 3)
 			goto err;
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 508d9a392ab1..f575f225d417 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -281,8 +281,10 @@ static int __team_options_register(struct team *team,
 	return 0;
 
 inst_rollback:
-	for (i--; i >= 0; i--)
+	for (i--; i >= 0; i--) {
 		__team_option_inst_del_option(team, dst_opts[i]);
+		list_del(&dst_opts[i]->list);
+	}
 
 	i = option_count;
 alloc_rollback:
diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index a017e9de2119..7b8afa589a53 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -1079,17 +1079,17 @@ static int aqc111_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 	u16 pkt_count = 0;
 	u64 desc_hdr = 0;
 	u16 vlan_tag = 0;
-	u32 skb_len = 0;
+	u32 skb_len;
 
 	if (!skb)
 		goto err;
 
-	if (skb->len == 0)
+	skb_len = skb->len;
+	if (skb_len < sizeof(desc_hdr))
 		goto err;
 
-	skb_len = skb->len;
 	/* RX Descriptor Header */
-	skb_trim(skb, skb->len - sizeof(desc_hdr));
+	skb_trim(skb, skb_len - sizeof(desc_hdr));
 	desc_hdr = le64_to_cpup((u64 *)skb_tail_pointer(skb));
 
 	/* Check these packets */
diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c
index 3777c7e2e6fc..e47bb125048d 100644
--- a/drivers/net/usb/ax88172a.c
+++ b/drivers/net/usb/ax88172a.c
@@ -161,7 +161,9 @@ static int ax88172a_bind(struct usbnet *dev, struct usb_interface *intf)
 	u8 buf[ETH_ALEN];
 	struct ax88172a_private *priv;
 
-	usbnet_get_endpoints(dev, intf);
+	ret = usbnet_get_endpoints(dev, intf);
+	if (ret)
+		return ret;
 
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv)
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index aff39bf3161d..d837c1887416 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -173,6 +173,7 @@ struct ax88179_data {
 	u8 in_pm;
 	u32 wol_supported;
 	u32 wolopts;
+	u8 disconnecting;
 };
 
 struct ax88179_int_data {
@@ -208,6 +209,7 @@ static int __ax88179_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index,
 {
 	int ret;
 	int (*fn)(struct usbnet *, u8, u8, u16, u16, void *, u16);
+	struct ax88179_data *ax179_data = dev->driver_priv;
 
 	BUG_ON(!dev);
 
@@ -219,7 +221,7 @@ static int __ax88179_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index,
 	ret = fn(dev, cmd, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
 		 value, index, data, size);
 
-	if (unlikely(ret < 0))
+	if (unlikely((ret < 0) && !(ret == -ENODEV && ax179_data->disconnecting)))
 		netdev_warn(dev->net, "Failed to read reg index 0x%04x: %d\n",
 			    index, ret);
 
@@ -231,6 +233,7 @@ static int __ax88179_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index,
 {
 	int ret;
 	int (*fn)(struct usbnet *, u8, u8, u16, u16, const void *, u16);
+	struct ax88179_data *ax179_data = dev->driver_priv;
 
 	BUG_ON(!dev);
 
@@ -242,7 +245,7 @@ static int __ax88179_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index,
 	ret = fn(dev, cmd, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
 		 value, index, data, size);
 
-	if (unlikely(ret < 0))
+	if (unlikely((ret < 0) && !(ret == -ENODEV && ax179_data->disconnecting)))
 		netdev_warn(dev->net, "Failed to write reg index 0x%04x: %d\n",
 			    index, ret);
 
@@ -492,6 +495,20 @@ static int ax88179_resume(struct usb_interface *intf)
 	return usbnet_resume(intf);
 }
 
+static void ax88179_disconnect(struct usb_interface *intf)
+{
+	struct usbnet *dev = usb_get_intfdata(intf);
+	struct ax88179_data *ax179_data;
+
+	if (!dev)
+		return;
+
+	ax179_data = dev->driver_priv;
+	ax179_data->disconnecting = 1;
+
+	usbnet_disconnect(intf);
+}
+
 static void
 ax88179_get_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo)
 {
@@ -1298,8 +1315,6 @@ static int ax88179_bind(struct usbnet *dev, struct usb_interface *intf)
 
 	netif_set_tso_max_size(dev->net, 16384);
 
-	ax88179_reset(dev);
-
 	return 0;
 }
 
@@ -1583,11 +1598,11 @@ static int ax88179_reset(struct usbnet *dev)
 
 	*tmp16 = AX_PHYPWR_RSTCTL_IPRL;
 	ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_PHYPWR_RSTCTL, 2, 2, tmp16);
-	msleep(200);
+	msleep(500);
 
 	*tmp = AX_CLK_SELECT_ACS | AX_CLK_SELECT_BCS;
 	ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_CLK_SELECT, 1, 1, tmp);
-	msleep(100);
+	msleep(200);
 
 	/* Ethernet PHY Auto Detach*/
 	ax88179_auto_detach(dev);
@@ -1906,7 +1921,7 @@ static struct usb_driver ax88179_178a_driver = {
 	.suspend =	ax88179_suspend,
 	.resume =	ax88179_resume,
 	.reset_resume =	ax88179_resume,
-	.disconnect =	usbnet_disconnect,
+	.disconnect =	ax88179_disconnect,
 	.supports_autosuspend = 1,
 	.disable_hub_initiated_lpm = 1,
 };
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 5add4145d9fc..a6d653ff552a 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -1691,8 +1691,6 @@ static int lan78xx_get_eee(struct net_device *net, struct ethtool_eee *edata)
 	ret = lan78xx_read_reg(dev, MAC_CR, &buf);
 	if (buf & MAC_CR_EEE_EN_) {
 		edata->eee_enabled = true;
-		edata->eee_active = !!(edata->advertised &
-				       edata->lp_advertised);
 		edata->tx_lpi_enabled = true;
 		/* EEE_TX_LPI_REQ_DLY & tx_lpi_timer are same uSec unit */
 		ret = lan78xx_read_reg(dev, EEE_TX_LPI_REQ_DLY, &buf);
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 344af3c5c836..e2e181378f41 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1289,6 +1289,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x19d2, 0x0168, 4)},
 	{QMI_FIXED_INTF(0x19d2, 0x0176, 3)},
 	{QMI_FIXED_INTF(0x19d2, 0x0178, 3)},
+	{QMI_FIXED_INTF(0x19d2, 0x0189, 4)},    /* ZTE MF290 */
 	{QMI_FIXED_INTF(0x19d2, 0x0191, 4)},	/* ZTE EuFi890 */
 	{QMI_FIXED_INTF(0x19d2, 0x0199, 1)},	/* ZTE MF820S */
 	{QMI_FIXED_INTF(0x19d2, 0x0200, 1)},
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 2c5c1e91ded6..9bf2140fd0a1 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -3000,6 +3000,8 @@ static void rtl8152_nic_reset(struct r8152 *tp)
 		ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CR, CR_RST);
 
 		for (i = 0; i < 1000; i++) {
+			if (test_bit(RTL8152_INACCESSIBLE, &tp->flags))
+				break;
 			if (!(ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CR) & CR_RST))
 				break;
 			usleep_range(100, 400);
@@ -3329,6 +3331,8 @@ static void rtl_disable(struct r8152 *tp)
 	rxdy_gated_en(tp, true);
 
 	for (i = 0; i < 1000; i++) {
+		if (test_bit(RTL8152_INACCESSIBLE, &tp->flags))
+			break;
 		ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL);
 		if ((ocp_data & FIFO_EMPTY) == FIFO_EMPTY)
 			break;
@@ -3336,6 +3340,8 @@ static void rtl_disable(struct r8152 *tp)
 	}
 
 	for (i = 0; i < 1000; i++) {
+		if (test_bit(RTL8152_INACCESSIBLE, &tp->flags))
+			break;
 		if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_TCR0) & TCR0_TX_EMPTY)
 			break;
 		usleep_range(1000, 2000);
@@ -5499,6 +5505,8 @@ static void wait_oob_link_list_ready(struct r8152 *tp)
 	int i;
 
 	for (i = 0; i < 1000; i++) {
+		if (test_bit(RTL8152_INACCESSIBLE, &tp->flags))
+			break;
 		ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL);
 		if (ocp_data & LINK_LIST_READY)
 			break;
@@ -5513,6 +5521,8 @@ static void r8156b_wait_loading_flash(struct r8152 *tp)
 		int i;
 
 		for (i = 0; i < 100; i++) {
+			if (test_bit(RTL8152_INACCESSIBLE, &tp->flags))
+				break;
 			if (ocp_read_word(tp, MCU_TYPE_USB, USB_GPHY_CTRL) & GPHY_PATCH_DONE)
 				break;
 			usleep_range(1000, 2000);
@@ -5635,6 +5645,8 @@ static int r8153_pre_firmware_1(struct r8152 *tp)
 	for (i = 0; i < 104; i++) {
 		u32 ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, USB_WDT1_CTRL);
 
+		if (test_bit(RTL8152_INACCESSIBLE, &tp->flags))
+			return -ENODEV;
 		if (!(ocp_data & WTD1_EN))
 			break;
 		usleep_range(1000, 2000);
@@ -5791,6 +5803,8 @@ static void r8153_aldps_en(struct r8152 *tp, bool enable)
 		data &= ~EN_ALDPS;
 		ocp_reg_write(tp, OCP_POWER_CFG, data);
 		for (i = 0; i < 20; i++) {
+			if (test_bit(RTL8152_INACCESSIBLE, &tp->flags))
+				return;
 			usleep_range(1000, 2000);
 			if (ocp_read_word(tp, MCU_TYPE_PLA, 0xe000) & 0x0100)
 				break;
@@ -8397,6 +8411,8 @@ static int rtl8152_pre_reset(struct usb_interface *intf)
 	struct r8152 *tp = usb_get_intfdata(intf);
 	struct net_device *netdev;
 
+	rtnl_lock();
+
 	if (!tp || !test_bit(PROBED_WITH_NO_ERRORS, &tp->flags))
 		return 0;
 
@@ -8428,20 +8444,17 @@ static int rtl8152_post_reset(struct usb_interface *intf)
 	struct sockaddr sa;
 
 	if (!tp || !test_bit(PROBED_WITH_NO_ERRORS, &tp->flags))
-		return 0;
+		goto exit;
 
 	rtl_set_accessible(tp);
 
 	/* reset the MAC address in case of policy change */
-	if (determine_ethernet_addr(tp, &sa) >= 0) {
-		rtnl_lock();
+	if (determine_ethernet_addr(tp, &sa) >= 0)
 		dev_set_mac_address (tp->netdev, &sa, NULL);
-		rtnl_unlock();
-	}
 
 	netdev = tp->netdev;
 	if (!netif_running(netdev))
-		return 0;
+		goto exit;
 
 	set_bit(WORK_ENABLE, &tp->flags);
 	if (netif_carrier_ok(netdev)) {
@@ -8460,6 +8473,8 @@ static int rtl8152_post_reset(struct usb_interface *intf)
 	if (!list_empty(&tp->rx_done))
 		napi_schedule(&tp->napi);
 
+exit:
+	rtnl_unlock();
 	return 0;
 }
 
@@ -10034,6 +10049,7 @@ static const struct usb_device_id rtl8152_table[] = {
 	{ USB_DEVICE(VENDOR_ID_NVIDIA,  0x09ff) },
 	{ USB_DEVICE(VENDOR_ID_TPLINK,  0x0601) },
 	{ USB_DEVICE(VENDOR_ID_DLINK,   0xb301) },
+	{ USB_DEVICE(VENDOR_ID_ASUS,    0x1976) },
 	{}
 };
 
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 9980517ed8b0..578e36ea1589 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -236,8 +236,8 @@ static void veth_get_ethtool_stats(struct net_device *dev,
 				data[tx_idx + j] += *(u64 *)(base + offset);
 			}
 		} while (u64_stats_fetch_retry(&rq_stats->syncp, start));
-		pp_idx = tx_idx + VETH_TQ_STATS_LEN;
 	}
+	pp_idx = idx + dev->real_num_tx_queues * VETH_TQ_STATS_LEN;
 
 page_pool_stats:
 	veth_get_page_pool_stats(dev, &data[pp_idx]);
@@ -373,7 +373,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 	skb_tx_timestamp(skb);
 	if (likely(veth_forward_skb(rcv, skb, rq, use_napi) == NET_RX_SUCCESS)) {
 		if (!use_napi)
-			dev_lstats_add(dev, length);
+			dev_sw_netstats_tx_add(dev, 1, length);
 		else
 			__veth_xdp_flush(rq);
 	} else {
@@ -387,14 +387,6 @@ drop:
 	return ret;
 }
 
-static u64 veth_stats_tx(struct net_device *dev, u64 *packets, u64 *bytes)
-{
-	struct veth_priv *priv = netdev_priv(dev);
-
-	dev_lstats_read(dev, packets, bytes);
-	return atomic64_read(&priv->dropped);
-}
-
 static void veth_stats_rx(struct veth_stats *result, struct net_device *dev)
 {
 	struct veth_priv *priv = netdev_priv(dev);
@@ -432,24 +424,24 @@ static void veth_get_stats64(struct net_device *dev,
 	struct veth_priv *priv = netdev_priv(dev);
 	struct net_device *peer;
 	struct veth_stats rx;
-	u64 packets, bytes;
 
-	tot->tx_dropped = veth_stats_tx(dev, &packets, &bytes);
-	tot->tx_bytes = bytes;
-	tot->tx_packets = packets;
+	tot->tx_dropped = atomic64_read(&priv->dropped);
+	dev_fetch_sw_netstats(tot, dev->tstats);
 
 	veth_stats_rx(&rx, dev);
 	tot->tx_dropped += rx.xdp_tx_err;
 	tot->rx_dropped = rx.rx_drops + rx.peer_tq_xdp_xmit_err;
-	tot->rx_bytes = rx.xdp_bytes;
-	tot->rx_packets = rx.xdp_packets;
+	tot->rx_bytes += rx.xdp_bytes;
+	tot->rx_packets += rx.xdp_packets;
 
 	rcu_read_lock();
 	peer = rcu_dereference(priv->peer);
 	if (peer) {
-		veth_stats_tx(peer, &packets, &bytes);
-		tot->rx_bytes += bytes;
-		tot->rx_packets += packets;
+		struct rtnl_link_stats64 tot_peer = {};
+
+		dev_fetch_sw_netstats(&tot_peer, peer->tstats);
+		tot->rx_bytes += tot_peer.tx_bytes;
+		tot->rx_packets += tot_peer.tx_packets;
 
 		veth_stats_rx(&rx, peer);
 		tot->tx_dropped += rx.peer_tq_xdp_xmit_err;
@@ -798,7 +790,8 @@ static int veth_convert_skb_to_xdp_buff(struct veth_rq *rq,
 
 			skb_add_rx_frag(nskb, i, page, page_offset, size,
 					truesize);
-			if (skb_copy_bits(skb, off, page_address(page),
+			if (skb_copy_bits(skb, off,
+					  page_address(page) + page_offset,
 					  size)) {
 				consume_skb(nskb);
 				goto drop;
@@ -1506,25 +1499,12 @@ static void veth_free_queues(struct net_device *dev)
 
 static int veth_dev_init(struct net_device *dev)
 {
-	int err;
-
-	dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats);
-	if (!dev->lstats)
-		return -ENOMEM;
-
-	err = veth_alloc_queues(dev);
-	if (err) {
-		free_percpu(dev->lstats);
-		return err;
-	}
-
-	return 0;
+	return veth_alloc_queues(dev);
 }
 
 static void veth_dev_free(struct net_device *dev)
 {
 	veth_free_queues(dev);
-	free_percpu(dev->lstats);
 }
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -1743,6 +1723,24 @@ static int veth_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
 	return 0;
 }
 
+static int veth_xdp_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto,
+				u16 *vlan_tci)
+{
+	const struct veth_xdp_buff *_ctx = (void *)ctx;
+	const struct sk_buff *skb = _ctx->skb;
+	int err;
+
+	if (!skb)
+		return -ENODATA;
+
+	err = __vlan_hwaccel_get_tag(skb, vlan_tci);
+	if (err)
+		return err;
+
+	*vlan_proto = skb->vlan_proto;
+	return err;
+}
+
 static const struct net_device_ops veth_netdev_ops = {
 	.ndo_init            = veth_dev_init,
 	.ndo_open            = veth_open,
@@ -1767,6 +1765,7 @@ static const struct net_device_ops veth_netdev_ops = {
 static const struct xdp_metadata_ops veth_xdp_metadata_ops = {
 	.xmo_rx_timestamp		= veth_xdp_rx_timestamp,
 	.xmo_rx_hash			= veth_xdp_rx_hash,
+	.xmo_rx_vlan_tag		= veth_xdp_rx_vlan_tag,
 };
 
 #define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \
@@ -1796,6 +1795,7 @@ static void veth_setup(struct net_device *dev)
 			       NETIF_F_HW_VLAN_STAG_RX);
 	dev->needs_free_netdev = true;
 	dev->priv_destructor = veth_dev_free;
+	dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
 	dev->max_mtu = ETH_MAX_MTU;
 
 	dev->hw_features = VETH_FEATURES;
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index d16f592c2061..3cb8aa193884 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -19,6 +19,7 @@
 #include <linux/average.h>
 #include <linux/filter.h>
 #include <linux/kernel.h>
+#include <linux/dim.h>
 #include <net/route.h>
 #include <net/xdp.h>
 #include <net/net_failover.h>
@@ -172,6 +173,17 @@ struct receive_queue {
 
 	struct virtnet_rq_stats stats;
 
+	/* The number of rx notifications */
+	u16 calls;
+
+	/* Is dynamic interrupt moderation enabled? */
+	bool dim_enabled;
+
+	/* Dynamic Interrupt Moderation */
+	struct dim dim;
+
+	u32 packets_in_napi;
+
 	struct virtnet_interrupt_coalesce intr_coal;
 
 	/* Chain pages by the private ptr. */
@@ -305,6 +317,9 @@ struct virtnet_info {
 	u8 duplex;
 	u32 speed;
 
+	/* Is rx dynamic interrupt moderation enabled? */
+	bool rx_dim_enabled;
+
 	/* Interrupt coalescing settings */
 	struct virtnet_interrupt_coalesce intr_coal_tx;
 	struct virtnet_interrupt_coalesce intr_coal_rx;
@@ -334,7 +349,6 @@ struct virtio_net_common_hdr {
 	};
 };
 
-static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf);
 static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf);
 
 static bool is_xdp_frame(void *ptr)
@@ -408,6 +422,17 @@ static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask)
 	return p;
 }
 
+static void virtnet_rq_free_buf(struct virtnet_info *vi,
+				struct receive_queue *rq, void *buf)
+{
+	if (vi->mergeable_rx_bufs)
+		put_page(virt_to_head_page(buf));
+	else if (vi->big_packets)
+		give_pages(rq, buf);
+	else
+		put_page(virt_to_head_page(buf));
+}
+
 static void enable_delayed_refill(struct virtnet_info *vi)
 {
 	spin_lock_bh(&vi->refill_lock);
@@ -431,7 +456,7 @@ static void virtqueue_napi_schedule(struct napi_struct *napi,
 	}
 }
 
-static void virtqueue_napi_complete(struct napi_struct *napi,
+static bool virtqueue_napi_complete(struct napi_struct *napi,
 				    struct virtqueue *vq, int processed)
 {
 	int opaque;
@@ -440,9 +465,13 @@ static void virtqueue_napi_complete(struct napi_struct *napi,
 	if (napi_complete_done(napi, processed)) {
 		if (unlikely(virtqueue_poll(vq, opaque)))
 			virtqueue_napi_schedule(napi, vq);
+		else
+			return true;
 	} else {
 		virtqueue_disable_cb(vq);
 	}
+
+	return false;
 }
 
 static void skb_xmit_done(struct virtqueue *vq)
@@ -634,17 +663,6 @@ static void *virtnet_rq_get_buf(struct receive_queue *rq, u32 *len, void **ctx)
 	return buf;
 }
 
-static void *virtnet_rq_detach_unused_buf(struct receive_queue *rq)
-{
-	void *buf;
-
-	buf = virtqueue_detach_unused_buf(rq->vq);
-	if (buf && rq->do_dma)
-		virtnet_rq_unmap(rq, buf, 0);
-
-	return buf;
-}
-
 static void virtnet_rq_init_one_sg(struct receive_queue *rq, void *buf, u32 len)
 {
 	struct virtnet_rq_dma *dma;
@@ -744,6 +762,20 @@ static void virtnet_rq_set_premapped(struct virtnet_info *vi)
 	}
 }
 
+static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf)
+{
+	struct virtnet_info *vi = vq->vdev->priv;
+	struct receive_queue *rq;
+	int i = vq2rxq(vq);
+
+	rq = &vi->rq[i];
+
+	if (rq->do_dma)
+		virtnet_rq_unmap(rq, buf, 0);
+
+	virtnet_rq_free_buf(vi, rq, buf);
+}
+
 static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi)
 {
 	unsigned int len;
@@ -1764,7 +1796,7 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 	if (unlikely(len < vi->hdr_len + ETH_HLEN)) {
 		pr_debug("%s: short packet %i\n", dev->name, len);
 		DEV_STATS_INC(dev, rx_length_errors);
-		virtnet_rq_free_unused_buf(rq->vq, buf);
+		virtnet_rq_free_buf(vi, rq, buf);
 		return;
 	}
 
@@ -1997,6 +2029,7 @@ static void skb_recv_done(struct virtqueue *rvq)
 	struct virtnet_info *vi = rvq->vdev->priv;
 	struct receive_queue *rq = &vi->rq[vq2rxq(rvq)];
 
+	rq->calls++;
 	virtqueue_napi_schedule(&rq->napi, rvq);
 }
 
@@ -2137,6 +2170,24 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
 	}
 }
 
+static void virtnet_rx_dim_update(struct virtnet_info *vi, struct receive_queue *rq)
+{
+	struct dim_sample cur_sample = {};
+
+	if (!rq->packets_in_napi)
+		return;
+
+	u64_stats_update_begin(&rq->stats.syncp);
+	dim_update_sample(rq->calls,
+			  u64_stats_read(&rq->stats.packets),
+			  u64_stats_read(&rq->stats.bytes),
+			  &cur_sample);
+	u64_stats_update_end(&rq->stats.syncp);
+
+	net_dim(&rq->dim, cur_sample);
+	rq->packets_in_napi = 0;
+}
+
 static int virtnet_poll(struct napi_struct *napi, int budget)
 {
 	struct receive_queue *rq =
@@ -2145,17 +2196,22 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 	struct send_queue *sq;
 	unsigned int received;
 	unsigned int xdp_xmit = 0;
+	bool napi_complete;
 
 	virtnet_poll_cleantx(rq);
 
 	received = virtnet_receive(rq, budget, &xdp_xmit);
+	rq->packets_in_napi += received;
 
 	if (xdp_xmit & VIRTIO_XDP_REDIR)
 		xdp_do_flush();
 
 	/* Out of packets? */
-	if (received < budget)
-		virtqueue_napi_complete(napi, rq->vq, received);
+	if (received < budget) {
+		napi_complete = virtqueue_napi_complete(napi, rq->vq, received);
+		if (napi_complete && rq->dim_enabled)
+			virtnet_rx_dim_update(vi, rq);
+	}
 
 	if (xdp_xmit & VIRTIO_XDP_TX) {
 		sq = virtnet_xdp_get_sq(vi);
@@ -2226,8 +2282,11 @@ err_enable_qp:
 	disable_delayed_refill(vi);
 	cancel_delayed_work_sync(&vi->refill);
 
-	for (i--; i >= 0; i--)
+	for (i--; i >= 0; i--) {
 		virtnet_disable_queue_pair(vi, i);
+		cancel_work_sync(&vi->rq[i].dim.work);
+	}
+
 	return err;
 }
 
@@ -2389,10 +2448,12 @@ static int virtnet_rx_resize(struct virtnet_info *vi,
 
 	qindex = rq - vi->rq;
 
-	if (running)
+	if (running) {
 		napi_disable(&rq->napi);
+		cancel_work_sync(&rq->dim.work);
+	}
 
-	err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_free_unused_buf);
+	err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_unmap_free_buf);
 	if (err)
 		netdev_err(vi->dev, "resize rx fail: rx queue index: %d err: %d\n", qindex, err);
 
@@ -2637,8 +2698,10 @@ static int virtnet_close(struct net_device *dev)
 	/* Make sure refill_work doesn't re-enable napi! */
 	cancel_delayed_work_sync(&vi->refill);
 
-	for (i = 0; i < vi->max_queue_pairs; i++)
+	for (i = 0; i < vi->max_queue_pairs; i++) {
 		virtnet_disable_queue_pair(vi, i);
+		cancel_work_sync(&vi->rq[i].dim.work);
+	}
 
 	return 0;
 }
@@ -2845,6 +2908,58 @@ static void virtnet_cpu_notif_remove(struct virtnet_info *vi)
 					    &vi->node_dead);
 }
 
+static int virtnet_send_ctrl_coal_vq_cmd(struct virtnet_info *vi,
+					 u16 vqn, u32 max_usecs, u32 max_packets)
+{
+	struct scatterlist sgs;
+
+	vi->ctrl->coal_vq.vqn = cpu_to_le16(vqn);
+	vi->ctrl->coal_vq.coal.max_usecs = cpu_to_le32(max_usecs);
+	vi->ctrl->coal_vq.coal.max_packets = cpu_to_le32(max_packets);
+	sg_init_one(&sgs, &vi->ctrl->coal_vq, sizeof(vi->ctrl->coal_vq));
+
+	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL,
+				  VIRTIO_NET_CTRL_NOTF_COAL_VQ_SET,
+				  &sgs))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int virtnet_send_rx_ctrl_coal_vq_cmd(struct virtnet_info *vi,
+					    u16 queue, u32 max_usecs,
+					    u32 max_packets)
+{
+	int err;
+
+	err = virtnet_send_ctrl_coal_vq_cmd(vi, rxq2vq(queue),
+					    max_usecs, max_packets);
+	if (err)
+		return err;
+
+	vi->rq[queue].intr_coal.max_usecs = max_usecs;
+	vi->rq[queue].intr_coal.max_packets = max_packets;
+
+	return 0;
+}
+
+static int virtnet_send_tx_ctrl_coal_vq_cmd(struct virtnet_info *vi,
+					    u16 queue, u32 max_usecs,
+					    u32 max_packets)
+{
+	int err;
+
+	err = virtnet_send_ctrl_coal_vq_cmd(vi, txq2vq(queue),
+					    max_usecs, max_packets);
+	if (err)
+		return err;
+
+	vi->sq[queue].intr_coal.max_usecs = max_usecs;
+	vi->sq[queue].intr_coal.max_packets = max_packets;
+
+	return 0;
+}
+
 static void virtnet_get_ringparam(struct net_device *dev,
 				  struct ethtool_ringparam *ring,
 				  struct kernel_ethtool_ringparam *kernel_ring,
@@ -2858,9 +2973,6 @@ static void virtnet_get_ringparam(struct net_device *dev,
 	ring->tx_pending = virtqueue_get_vring_size(vi->sq[0].vq);
 }
 
-static int virtnet_send_ctrl_coal_vq_cmd(struct virtnet_info *vi,
-					 u16 vqn, u32 max_usecs, u32 max_packets);
-
 static int virtnet_set_ringparam(struct net_device *dev,
 				 struct ethtool_ringparam *ring,
 				 struct kernel_ethtool_ringparam *kernel_ring,
@@ -2902,14 +3014,11 @@ static int virtnet_set_ringparam(struct net_device *dev,
 			 * through the VIRTIO_NET_CTRL_NOTF_COAL_TX_SET command, or, if the driver
 			 * did not set any TX coalescing parameters, to 0.
 			 */
-			err = virtnet_send_ctrl_coal_vq_cmd(vi, txq2vq(i),
-							    vi->intr_coal_tx.max_usecs,
-							    vi->intr_coal_tx.max_packets);
+			err = virtnet_send_tx_ctrl_coal_vq_cmd(vi, i,
+							       vi->intr_coal_tx.max_usecs,
+							       vi->intr_coal_tx.max_packets);
 			if (err)
 				return err;
-
-			vi->sq[i].intr_coal.max_usecs = vi->intr_coal_tx.max_usecs;
-			vi->sq[i].intr_coal.max_packets = vi->intr_coal_tx.max_packets;
 		}
 
 		if (ring->rx_pending != rx_pending) {
@@ -2918,14 +3027,11 @@ static int virtnet_set_ringparam(struct net_device *dev,
 				return err;
 
 			/* The reason is same as the transmit virtqueue reset */
-			err = virtnet_send_ctrl_coal_vq_cmd(vi, rxq2vq(i),
-							    vi->intr_coal_rx.max_usecs,
-							    vi->intr_coal_rx.max_packets);
+			err = virtnet_send_rx_ctrl_coal_vq_cmd(vi, i,
+							       vi->intr_coal_rx.max_usecs,
+							       vi->intr_coal_rx.max_packets);
 			if (err)
 				return err;
-
-			vi->rq[i].intr_coal.max_usecs = vi->intr_coal_rx.max_usecs;
-			vi->rq[i].intr_coal.max_packets = vi->intr_coal_rx.max_packets;
 		}
 	}
 
@@ -3262,10 +3368,10 @@ static int virtnet_get_link_ksettings(struct net_device *dev,
 	return 0;
 }
 
-static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi,
-				       struct ethtool_coalesce *ec)
+static int virtnet_send_tx_notf_coal_cmds(struct virtnet_info *vi,
+					  struct ethtool_coalesce *ec)
 {
-	struct scatterlist sgs_tx, sgs_rx;
+	struct scatterlist sgs_tx;
 	int i;
 
 	vi->ctrl->coal_tx.tx_usecs = cpu_to_le32(ec->tx_coalesce_usecs);
@@ -3277,7 +3383,6 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi,
 				  &sgs_tx))
 		return -EINVAL;
 
-	/* Save parameters */
 	vi->intr_coal_tx.max_usecs = ec->tx_coalesce_usecs;
 	vi->intr_coal_tx.max_packets = ec->tx_max_coalesced_frames;
 	for (i = 0; i < vi->max_queue_pairs; i++) {
@@ -3285,6 +3390,40 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi,
 		vi->sq[i].intr_coal.max_packets = ec->tx_max_coalesced_frames;
 	}
 
+	return 0;
+}
+
+static int virtnet_send_rx_notf_coal_cmds(struct virtnet_info *vi,
+					  struct ethtool_coalesce *ec)
+{
+	bool rx_ctrl_dim_on = !!ec->use_adaptive_rx_coalesce;
+	struct scatterlist sgs_rx;
+	int i;
+
+	if (rx_ctrl_dim_on && !virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL))
+		return -EOPNOTSUPP;
+
+	if (rx_ctrl_dim_on && (ec->rx_coalesce_usecs != vi->intr_coal_rx.max_usecs ||
+			       ec->rx_max_coalesced_frames != vi->intr_coal_rx.max_packets))
+		return -EINVAL;
+
+	if (rx_ctrl_dim_on && !vi->rx_dim_enabled) {
+		vi->rx_dim_enabled = true;
+		for (i = 0; i < vi->max_queue_pairs; i++)
+			vi->rq[i].dim_enabled = true;
+		return 0;
+	}
+
+	if (!rx_ctrl_dim_on && vi->rx_dim_enabled) {
+		vi->rx_dim_enabled = false;
+		for (i = 0; i < vi->max_queue_pairs; i++)
+			vi->rq[i].dim_enabled = false;
+	}
+
+	/* Since the per-queue coalescing params can be set,
+	 * we need apply the global new params even if they
+	 * are not updated.
+	 */
 	vi->ctrl->coal_rx.rx_usecs = cpu_to_le32(ec->rx_coalesce_usecs);
 	vi->ctrl->coal_rx.rx_max_packets = cpu_to_le32(ec->rx_max_coalesced_frames);
 	sg_init_one(&sgs_rx, &vi->ctrl->coal_rx, sizeof(vi->ctrl->coal_rx));
@@ -3294,7 +3433,6 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi,
 				  &sgs_rx))
 		return -EINVAL;
 
-	/* Save parameters */
 	vi->intr_coal_rx.max_usecs = ec->rx_coalesce_usecs;
 	vi->intr_coal_rx.max_packets = ec->rx_max_coalesced_frames;
 	for (i = 0; i < vi->max_queue_pairs; i++) {
@@ -3305,21 +3443,55 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi,
 	return 0;
 }
 
-static int virtnet_send_ctrl_coal_vq_cmd(struct virtnet_info *vi,
-					 u16 vqn, u32 max_usecs, u32 max_packets)
+static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi,
+				       struct ethtool_coalesce *ec)
 {
-	struct scatterlist sgs;
+	int err;
 
-	vi->ctrl->coal_vq.vqn = cpu_to_le16(vqn);
-	vi->ctrl->coal_vq.coal.max_usecs = cpu_to_le32(max_usecs);
-	vi->ctrl->coal_vq.coal.max_packets = cpu_to_le32(max_packets);
-	sg_init_one(&sgs, &vi->ctrl->coal_vq, sizeof(vi->ctrl->coal_vq));
+	err = virtnet_send_tx_notf_coal_cmds(vi, ec);
+	if (err)
+		return err;
 
-	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL,
-				  VIRTIO_NET_CTRL_NOTF_COAL_VQ_SET,
-				  &sgs))
+	err = virtnet_send_rx_notf_coal_cmds(vi, ec);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int virtnet_send_rx_notf_coal_vq_cmds(struct virtnet_info *vi,
+					     struct ethtool_coalesce *ec,
+					     u16 queue)
+{
+	bool rx_ctrl_dim_on = !!ec->use_adaptive_rx_coalesce;
+	bool cur_rx_dim = vi->rq[queue].dim_enabled;
+	u32 max_usecs, max_packets;
+	int err;
+
+	max_usecs = vi->rq[queue].intr_coal.max_usecs;
+	max_packets = vi->rq[queue].intr_coal.max_packets;
+
+	if (rx_ctrl_dim_on && (ec->rx_coalesce_usecs != max_usecs ||
+			       ec->rx_max_coalesced_frames != max_packets))
 		return -EINVAL;
 
+	if (rx_ctrl_dim_on && !cur_rx_dim) {
+		vi->rq[queue].dim_enabled = true;
+		return 0;
+	}
+
+	if (!rx_ctrl_dim_on && cur_rx_dim)
+		vi->rq[queue].dim_enabled = false;
+
+	/* If no params are updated, userspace ethtool will
+	 * reject the modification.
+	 */
+	err = virtnet_send_rx_ctrl_coal_vq_cmd(vi, queue,
+					       ec->rx_coalesce_usecs,
+					       ec->rx_max_coalesced_frames);
+	if (err)
+		return err;
+
 	return 0;
 }
 
@@ -3329,27 +3501,62 @@ static int virtnet_send_notf_coal_vq_cmds(struct virtnet_info *vi,
 {
 	int err;
 
-	err = virtnet_send_ctrl_coal_vq_cmd(vi, rxq2vq(queue),
-					    ec->rx_coalesce_usecs,
-					    ec->rx_max_coalesced_frames);
+	err = virtnet_send_rx_notf_coal_vq_cmds(vi, ec, queue);
 	if (err)
 		return err;
 
-	vi->rq[queue].intr_coal.max_usecs = ec->rx_coalesce_usecs;
-	vi->rq[queue].intr_coal.max_packets = ec->rx_max_coalesced_frames;
-
-	err = virtnet_send_ctrl_coal_vq_cmd(vi, txq2vq(queue),
-					    ec->tx_coalesce_usecs,
-					    ec->tx_max_coalesced_frames);
+	err = virtnet_send_tx_ctrl_coal_vq_cmd(vi, queue,
+					       ec->tx_coalesce_usecs,
+					       ec->tx_max_coalesced_frames);
 	if (err)
 		return err;
 
-	vi->sq[queue].intr_coal.max_usecs = ec->tx_coalesce_usecs;
-	vi->sq[queue].intr_coal.max_packets = ec->tx_max_coalesced_frames;
-
 	return 0;
 }
 
+static void virtnet_rx_dim_work(struct work_struct *work)
+{
+	struct dim *dim = container_of(work, struct dim, work);
+	struct receive_queue *rq = container_of(dim,
+			struct receive_queue, dim);
+	struct virtnet_info *vi = rq->vq->vdev->priv;
+	struct net_device *dev = vi->dev;
+	struct dim_cq_moder update_moder;
+	int i, qnum, err;
+
+	if (!rtnl_trylock())
+		return;
+
+	/* Each rxq's work is queued by "net_dim()->schedule_work()"
+	 * in response to NAPI traffic changes. Note that dim->profile_ix
+	 * for each rxq is updated prior to the queuing action.
+	 * So we only need to traverse and update profiles for all rxqs
+	 * in the work which is holding rtnl_lock.
+	 */
+	for (i = 0; i < vi->curr_queue_pairs; i++) {
+		rq = &vi->rq[i];
+		dim = &rq->dim;
+		qnum = rq - vi->rq;
+
+		if (!rq->dim_enabled)
+			continue;
+
+		update_moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
+		if (update_moder.usec != rq->intr_coal.max_usecs ||
+		    update_moder.pkts != rq->intr_coal.max_packets) {
+			err = virtnet_send_rx_ctrl_coal_vq_cmd(vi, qnum,
+							       update_moder.usec,
+							       update_moder.pkts);
+			if (err)
+				pr_debug("%s: Failed to send dim parameters on rxq%d\n",
+					 dev->name, qnum);
+			dim->state = DIM_START_MEASURE;
+		}
+	}
+
+	rtnl_unlock();
+}
+
 static int virtnet_coal_params_supported(struct ethtool_coalesce *ec)
 {
 	/* usecs coalescing is supported only if VIRTIO_NET_F_NOTF_COAL
@@ -3431,6 +3638,7 @@ static int virtnet_get_coalesce(struct net_device *dev,
 		ec->tx_coalesce_usecs = vi->intr_coal_tx.max_usecs;
 		ec->tx_max_coalesced_frames = vi->intr_coal_tx.max_packets;
 		ec->rx_max_coalesced_frames = vi->intr_coal_rx.max_packets;
+		ec->use_adaptive_rx_coalesce = vi->rx_dim_enabled;
 	} else {
 		ec->rx_max_coalesced_frames = 1;
 
@@ -3488,6 +3696,7 @@ static int virtnet_get_per_queue_coalesce(struct net_device *dev,
 		ec->tx_coalesce_usecs = vi->sq[queue].intr_coal.max_usecs;
 		ec->tx_max_coalesced_frames = vi->sq[queue].intr_coal.max_packets;
 		ec->rx_max_coalesced_frames = vi->rq[queue].intr_coal.max_packets;
+		ec->use_adaptive_rx_coalesce = vi->rq[queue].dim_enabled;
 	} else {
 		ec->rx_max_coalesced_frames = 1;
 
@@ -3535,39 +3744,42 @@ static u32 virtnet_get_rxfh_indir_size(struct net_device *dev)
 	return ((struct virtnet_info *)netdev_priv(dev))->rss_indir_table_size;
 }
 
-static int virtnet_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, u8 *hfunc)
+static int virtnet_get_rxfh(struct net_device *dev,
+			    struct ethtool_rxfh_param *rxfh)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
 	int i;
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < vi->rss_indir_table_size; ++i)
-			indir[i] = vi->ctrl->rss.indirection_table[i];
+			rxfh->indir[i] = vi->ctrl->rss.indirection_table[i];
 	}
 
-	if (key)
-		memcpy(key, vi->ctrl->rss.key, vi->rss_key_size);
+	if (rxfh->key)
+		memcpy(rxfh->key, vi->ctrl->rss.key, vi->rss_key_size);
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	return 0;
 }
 
-static int virtnet_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key, const u8 hfunc)
+static int virtnet_set_rxfh(struct net_device *dev,
+			    struct ethtool_rxfh_param *rxfh,
+			    struct netlink_ext_ack *extack)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
 	int i;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < vi->rss_indir_table_size; ++i)
-			vi->ctrl->rss.indirection_table[i] = indir[i];
+			vi->ctrl->rss.indirection_table[i] = rxfh->indir[i];
 	}
-	if (key)
-		memcpy(vi->ctrl->rss.key, key, vi->rss_key_size);
+	if (rxfh->key)
+		memcpy(vi->ctrl->rss.key, rxfh->key, vi->rss_key_size);
 
 	virtnet_commit_rss_command(vi);
 
@@ -3613,7 +3825,7 @@ static int virtnet_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info)
 
 static const struct ethtool_ops virtnet_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_MAX_FRAMES |
-		ETHTOOL_COALESCE_USECS,
+		ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_USE_ADAPTIVE_RX,
 	.get_drvinfo = virtnet_get_drvinfo,
 	.get_link = ethtool_op_get_link,
 	.get_ringparam = virtnet_get_ringparam,
@@ -4031,19 +4243,6 @@ static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf)
 		xdp_return_frame(ptr_to_xdp(buf));
 }
 
-static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf)
-{
-	struct virtnet_info *vi = vq->vdev->priv;
-	int i = vq2rxq(vq);
-
-	if (vi->mergeable_rx_bufs)
-		put_page(virt_to_head_page(buf));
-	else if (vi->big_packets)
-		give_pages(&vi->rq[i], buf);
-	else
-		put_page(virt_to_head_page(buf));
-}
-
 static void free_unused_bufs(struct virtnet_info *vi)
 {
 	void *buf;
@@ -4057,10 +4256,10 @@ static void free_unused_bufs(struct virtnet_info *vi)
 	}
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
-		struct receive_queue *rq = &vi->rq[i];
+		struct virtqueue *vq = vi->rq[i].vq;
 
-		while ((buf = virtnet_rq_detach_unused_buf(rq)) != NULL)
-			virtnet_rq_free_unused_buf(rq->vq, buf);
+		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
+			virtnet_rq_unmap_free_buf(vq, buf);
 		cond_resched();
 	}
 }
@@ -4203,6 +4402,9 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
 					 virtnet_poll_tx,
 					 napi_tx ? napi_weight : 0);
 
+		INIT_WORK(&vi->rq[i].dim.work, virtnet_rx_dim_work);
+		vi->rq[i].dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+
 		sg_init_table(vi->rq[i].sg, ARRAY_SIZE(vi->rq[i].sg));
 		ewma_pkt_len_init(&vi->rq[i].mrg_avg_pkt_len);
 		sg_init_table(vi->sq[i].sg, ARRAY_SIZE(vi->sq[i].sg));
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index 98c22d7d87a2..7e8008d5378a 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -245,20 +245,20 @@ vmxnet3_get_strings(struct net_device *netdev, u32 stringset, u8 *buf)
 
 	for (j = 0; j < adapter->num_tx_queues; j++) {
 		for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_dev_stats); i++)
-			ethtool_sprintf(&buf, vmxnet3_tq_dev_stats[i].desc);
+			ethtool_puts(&buf, vmxnet3_tq_dev_stats[i].desc);
 		for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_driver_stats); i++)
-			ethtool_sprintf(&buf, vmxnet3_tq_driver_stats[i].desc);
+			ethtool_puts(&buf, vmxnet3_tq_driver_stats[i].desc);
 	}
 
 	for (j = 0; j < adapter->num_rx_queues; j++) {
 		for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_dev_stats); i++)
-			ethtool_sprintf(&buf, vmxnet3_rq_dev_stats[i].desc);
+			ethtool_puts(&buf, vmxnet3_rq_dev_stats[i].desc);
 		for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_driver_stats); i++)
-			ethtool_sprintf(&buf, vmxnet3_rq_driver_stats[i].desc);
+			ethtool_puts(&buf, vmxnet3_rq_driver_stats[i].desc);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(vmxnet3_global_stats); i++)
-		ethtool_sprintf(&buf, vmxnet3_global_stats[i].desc);
+		ethtool_puts(&buf, vmxnet3_global_stats[i].desc);
 }
 
 netdev_features_t vmxnet3_fix_features(struct net_device *netdev,
@@ -1136,27 +1136,26 @@ vmxnet3_get_rss_indir_size(struct net_device *netdev)
 }
 
 static int
-vmxnet3_get_rss(struct net_device *netdev, u32 *p, u8 *key, u8 *hfunc)
+vmxnet3_get_rss(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 	struct UPT1_RSSConf *rssConf = adapter->rss_conf;
 	unsigned int n = rssConf->indTableSize;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (!p)
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (!rxfh->indir)
 		return 0;
 	if (n > UPT1_RSS_MAX_IND_TABLE_SIZE)
 		return 0;
 	while (n--)
-		p[n] = rssConf->indTable[n];
+		rxfh->indir[n] = rssConf->indTable[n];
 	return 0;
 
 }
 
 static int
-vmxnet3_set_rss(struct net_device *netdev, const u32 *p, const u8 *key,
-		const u8 hfunc)
+vmxnet3_set_rss(struct net_device *netdev, struct ethtool_rxfh_param *rxfh,
+		struct netlink_ext_ack *extack)
 {
 	unsigned int i;
 	unsigned long flags;
@@ -1164,13 +1163,14 @@ vmxnet3_set_rss(struct net_device *netdev, const u32 *p, const u8 *key,
 	struct UPT1_RSSConf *rssConf = adapter->rss_conf;
 
 	/* We do not allow change in unsupported parameters */
-	if (key ||
-	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->key ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP))
 		return -EOPNOTSUPP;
-	if (!p)
+	if (!rxfh->indir)
 		return 0;
 	for (i = 0; i < rssConf->indTableSize; i++)
-		rssConf->indTable[i] = p[i];
+		rssConf->indTable[i] = rxfh->indir[i];
 
 	spin_lock_irqsave(&adapter->cmd_lock, flags);
 	VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index db766941b78f..bb95ce43cd97 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -121,22 +121,12 @@ struct net_vrf {
 	int			ifindex;
 };
 
-struct pcpu_dstats {
-	u64			tx_pkts;
-	u64			tx_bytes;
-	u64			tx_drps;
-	u64			rx_pkts;
-	u64			rx_bytes;
-	u64			rx_drps;
-	struct u64_stats_sync	syncp;
-};
-
 static void vrf_rx_stats(struct net_device *dev, int len)
 {
 	struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
 
 	u64_stats_update_begin(&dstats->syncp);
-	dstats->rx_pkts++;
+	dstats->rx_packets++;
 	dstats->rx_bytes += len;
 	u64_stats_update_end(&dstats->syncp);
 }
@@ -161,10 +151,10 @@ static void vrf_get_stats64(struct net_device *dev,
 		do {
 			start = u64_stats_fetch_begin(&dstats->syncp);
 			tbytes = dstats->tx_bytes;
-			tpkts = dstats->tx_pkts;
-			tdrops = dstats->tx_drps;
+			tpkts = dstats->tx_packets;
+			tdrops = dstats->tx_drops;
 			rbytes = dstats->rx_bytes;
-			rpkts = dstats->rx_pkts;
+			rpkts = dstats->rx_packets;
 		} while (u64_stats_fetch_retry(&dstats->syncp, start));
 		stats->tx_bytes += tbytes;
 		stats->tx_packets += tpkts;
@@ -421,7 +411,7 @@ static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev,
 	if (likely(__netif_rx(skb) == NET_RX_SUCCESS))
 		vrf_rx_stats(dev, len);
 	else
-		this_cpu_inc(dev->dstats->rx_drps);
+		this_cpu_inc(dev->dstats->rx_drops);
 
 	return NETDEV_TX_OK;
 }
@@ -616,11 +606,11 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
 		struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
 
 		u64_stats_update_begin(&dstats->syncp);
-		dstats->tx_pkts++;
+		dstats->tx_packets++;
 		dstats->tx_bytes += len;
 		u64_stats_update_end(&dstats->syncp);
 	} else {
-		this_cpu_inc(dev->dstats->tx_drps);
+		this_cpu_inc(dev->dstats->tx_drops);
 	}
 
 	return ret;
@@ -1174,22 +1164,15 @@ static void vrf_dev_uninit(struct net_device *dev)
 
 	vrf_rtable_release(dev, vrf);
 	vrf_rt6_release(dev, vrf);
-
-	free_percpu(dev->dstats);
-	dev->dstats = NULL;
 }
 
 static int vrf_dev_init(struct net_device *dev)
 {
 	struct net_vrf *vrf = netdev_priv(dev);
 
-	dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats);
-	if (!dev->dstats)
-		goto out_nomem;
-
 	/* create the default dst which points back to us */
 	if (vrf_rtable_create(dev) != 0)
-		goto out_stats;
+		goto out_nomem;
 
 	if (vrf_rt6_create(dev) != 0)
 		goto out_rth;
@@ -1203,9 +1186,6 @@ static int vrf_dev_init(struct net_device *dev)
 
 out_rth:
 	vrf_rtable_release(dev, vrf);
-out_stats:
-	free_percpu(dev->dstats);
-	dev->dstats = NULL;
 out_nomem:
 	return -ENOMEM;
 }
@@ -1704,6 +1684,8 @@ static void vrf_setup(struct net_device *dev)
 	dev->min_mtu = IPV6_MIN_MTU;
 	dev->max_mtu = IP6_MAX_MTU;
 	dev->mtu = dev->max_mtu;
+
+	dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS;
 }
 
 static int vrf_validate(struct nlattr *tb[], struct nlattr *data[],
diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 412c3c0b6990..16106e088c63 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -2379,7 +2379,17 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		else
 			udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX);
 #if IS_ENABLED(CONFIG_IPV6)
-		key.label = vxlan->cfg.label;
+		switch (vxlan->cfg.label_policy) {
+		case VXLAN_LABEL_FIXED:
+			key.label = vxlan->cfg.label;
+			break;
+		case VXLAN_LABEL_INHERIT:
+			key.label = ip_tunnel_get_flowlabel(old_iph, skb);
+			break;
+		default:
+			DEBUG_NET_WARN_ON_ONCE(1);
+			goto drop;
+		}
 #endif
 	} else {
 		if (!info) {
@@ -3225,6 +3235,7 @@ static const struct net_device_ops vxlan_netdev_ether_ops = {
 	.ndo_fdb_get		= vxlan_fdb_get,
 	.ndo_mdb_add		= vxlan_mdb_add,
 	.ndo_mdb_del		= vxlan_mdb_del,
+	.ndo_mdb_del_bulk	= vxlan_mdb_del_bulk,
 	.ndo_mdb_dump		= vxlan_mdb_dump,
 	.ndo_mdb_get		= vxlan_mdb_get,
 	.ndo_fill_metadata_dst	= vxlan_fill_metadata_dst,
@@ -3366,6 +3377,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = {
 	[IFLA_VXLAN_DF]		= { .type = NLA_U8 },
 	[IFLA_VXLAN_VNIFILTER]	= { .type = NLA_U8 },
 	[IFLA_VXLAN_LOCALBYPASS]	= NLA_POLICY_MAX(NLA_U8, 1),
+	[IFLA_VXLAN_LABEL_POLICY]       = NLA_POLICY_MAX(NLA_U32, VXLAN_LABEL_MAX),
 };
 
 static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
@@ -3740,6 +3752,12 @@ static int vxlan_config_validate(struct net *src_net, struct vxlan_config *conf,
 		return -EINVAL;
 	}
 
+	if (conf->label_policy && !use_ipv6) {
+		NL_SET_ERR_MSG(extack,
+			       "Label policy only applies to IPv6 VXLAN devices");
+		return -EINVAL;
+	}
+
 	if (conf->remote_ifindex) {
 		struct net_device *lowerdev;
 
@@ -4082,6 +4100,8 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
 	if (data[IFLA_VXLAN_LABEL])
 		conf->label = nla_get_be32(data[IFLA_VXLAN_LABEL]) &
 			     IPV6_FLOWLABEL_MASK;
+	if (data[IFLA_VXLAN_LABEL_POLICY])
+		conf->label_policy = nla_get_u32(data[IFLA_VXLAN_LABEL_POLICY]);
 
 	if (data[IFLA_VXLAN_LEARNING]) {
 		err = vxlan_nl2flag(conf, data, IFLA_VXLAN_LEARNING,
@@ -4398,6 +4418,7 @@ static size_t vxlan_get_size(const struct net_device *dev)
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_TOS */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_DF */
 		nla_total_size(sizeof(__be32)) + /* IFLA_VXLAN_LABEL */
+		nla_total_size(sizeof(__u32)) +  /* IFLA_VXLAN_LABEL_POLICY */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_LEARNING */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_PROXY */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_RSC */
@@ -4471,6 +4492,7 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) ||
 	    nla_put_u8(skb, IFLA_VXLAN_DF, vxlan->cfg.df) ||
 	    nla_put_be32(skb, IFLA_VXLAN_LABEL, vxlan->cfg.label) ||
+	    nla_put_u32(skb, IFLA_VXLAN_LABEL_POLICY, vxlan->cfg.label_policy) ||
 	    nla_put_u8(skb, IFLA_VXLAN_LEARNING,
 		       !!(vxlan->cfg.flags & VXLAN_F_LEARN)) ||
 	    nla_put_u8(skb, IFLA_VXLAN_PROXY,
diff --git a/drivers/net/vxlan/vxlan_mdb.c b/drivers/net/vxlan/vxlan_mdb.c
index eb4c580b5cee..60eb95a06d55 100644
--- a/drivers/net/vxlan/vxlan_mdb.c
+++ b/drivers/net/vxlan/vxlan_mdb.c
@@ -74,6 +74,14 @@ struct vxlan_mdb_config {
 	u8 rt_protocol;
 };
 
+struct vxlan_mdb_flush_desc {
+	union vxlan_addr remote_ip;
+	__be32 src_vni;
+	__be32 remote_vni;
+	__be16 remote_port;
+	u8 rt_protocol;
+};
+
 static const struct rhashtable_params vxlan_mdb_rht_params = {
 	.head_offset = offsetof(struct vxlan_mdb_entry, rhnode),
 	.key_offset = offsetof(struct vxlan_mdb_entry, key),
@@ -1306,6 +1314,145 @@ int vxlan_mdb_del(struct net_device *dev, struct nlattr *tb[],
 	return err;
 }
 
+static const struct nla_policy
+vxlan_mdbe_attrs_del_bulk_pol[MDBE_ATTR_MAX + 1] = {
+	[MDBE_ATTR_RTPROT] = NLA_POLICY_MIN(NLA_U8, RTPROT_STATIC),
+	[MDBE_ATTR_DST] = NLA_POLICY_RANGE(NLA_BINARY,
+					   sizeof(struct in_addr),
+					   sizeof(struct in6_addr)),
+	[MDBE_ATTR_DST_PORT] = { .type = NLA_U16 },
+	[MDBE_ATTR_VNI] = NLA_POLICY_FULL_RANGE(NLA_U32, &vni_range),
+	[MDBE_ATTR_SRC_VNI] = NLA_POLICY_FULL_RANGE(NLA_U32, &vni_range),
+	[MDBE_ATTR_STATE_MASK] = NLA_POLICY_MASK(NLA_U8, MDB_PERMANENT),
+};
+
+static int vxlan_mdb_flush_desc_init(struct vxlan_dev *vxlan,
+				     struct vxlan_mdb_flush_desc *desc,
+				     struct nlattr *tb[],
+				     struct netlink_ext_ack *extack)
+{
+	struct br_mdb_entry *entry = nla_data(tb[MDBA_SET_ENTRY]);
+	struct nlattr *mdbe_attrs[MDBE_ATTR_MAX + 1];
+	int err;
+
+	if (entry->ifindex && entry->ifindex != vxlan->dev->ifindex) {
+		NL_SET_ERR_MSG_MOD(extack, "Invalid port net device");
+		return -EINVAL;
+	}
+
+	if (entry->vid) {
+		NL_SET_ERR_MSG_MOD(extack, "VID must not be specified");
+		return -EINVAL;
+	}
+
+	if (!tb[MDBA_SET_ENTRY_ATTRS])
+		return 0;
+
+	err = nla_parse_nested(mdbe_attrs, MDBE_ATTR_MAX,
+			       tb[MDBA_SET_ENTRY_ATTRS],
+			       vxlan_mdbe_attrs_del_bulk_pol, extack);
+	if (err)
+		return err;
+
+	if (mdbe_attrs[MDBE_ATTR_STATE_MASK]) {
+		u8 state_mask = nla_get_u8(mdbe_attrs[MDBE_ATTR_STATE_MASK]);
+
+		if ((state_mask & MDB_PERMANENT) && !(entry->state & MDB_PERMANENT)) {
+			NL_SET_ERR_MSG_MOD(extack, "Only permanent MDB entries are supported");
+			return -EINVAL;
+		}
+	}
+
+	if (mdbe_attrs[MDBE_ATTR_RTPROT])
+		desc->rt_protocol = nla_get_u8(mdbe_attrs[MDBE_ATTR_RTPROT]);
+
+	if (mdbe_attrs[MDBE_ATTR_DST])
+		vxlan_nla_get_addr(&desc->remote_ip, mdbe_attrs[MDBE_ATTR_DST]);
+
+	if (mdbe_attrs[MDBE_ATTR_DST_PORT])
+		desc->remote_port =
+			cpu_to_be16(nla_get_u16(mdbe_attrs[MDBE_ATTR_DST_PORT]));
+
+	if (mdbe_attrs[MDBE_ATTR_VNI])
+		desc->remote_vni =
+			cpu_to_be32(nla_get_u32(mdbe_attrs[MDBE_ATTR_VNI]));
+
+	if (mdbe_attrs[MDBE_ATTR_SRC_VNI])
+		desc->src_vni =
+			cpu_to_be32(nla_get_u32(mdbe_attrs[MDBE_ATTR_SRC_VNI]));
+
+	return 0;
+}
+
+static void vxlan_mdb_remotes_flush(struct vxlan_dev *vxlan,
+				    struct vxlan_mdb_entry *mdb_entry,
+				    const struct vxlan_mdb_flush_desc *desc)
+{
+	struct vxlan_mdb_remote *remote, *tmp;
+
+	list_for_each_entry_safe(remote, tmp, &mdb_entry->remotes, list) {
+		struct vxlan_rdst *rd = rtnl_dereference(remote->rd);
+		__be32 remote_vni;
+
+		if (desc->remote_ip.sa.sa_family &&
+		    !vxlan_addr_equal(&desc->remote_ip, &rd->remote_ip))
+			continue;
+
+		/* Encapsulation is performed with source VNI if remote VNI
+		 * is not set.
+		 */
+		remote_vni = rd->remote_vni ? : mdb_entry->key.vni;
+		if (desc->remote_vni && desc->remote_vni != remote_vni)
+			continue;
+
+		if (desc->remote_port && desc->remote_port != rd->remote_port)
+			continue;
+
+		if (desc->rt_protocol &&
+		    desc->rt_protocol != remote->rt_protocol)
+			continue;
+
+		vxlan_mdb_remote_del(vxlan, mdb_entry, remote);
+	}
+}
+
+static void vxlan_mdb_flush(struct vxlan_dev *vxlan,
+			    const struct vxlan_mdb_flush_desc *desc)
+{
+	struct vxlan_mdb_entry *mdb_entry;
+	struct hlist_node *tmp;
+
+	/* The removal of an entry cannot trigger the removal of another entry
+	 * since entries are always added to the head of the list.
+	 */
+	hlist_for_each_entry_safe(mdb_entry, tmp, &vxlan->mdb_list, mdb_node) {
+		if (desc->src_vni && desc->src_vni != mdb_entry->key.vni)
+			continue;
+
+		vxlan_mdb_remotes_flush(vxlan, mdb_entry, desc);
+		/* Entry will only be removed if its remotes list is empty. */
+		vxlan_mdb_entry_put(vxlan, mdb_entry);
+	}
+}
+
+int vxlan_mdb_del_bulk(struct net_device *dev, struct nlattr *tb[],
+		       struct netlink_ext_ack *extack)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_mdb_flush_desc desc = {};
+	int err;
+
+	ASSERT_RTNL();
+
+	err = vxlan_mdb_flush_desc_init(vxlan, &desc, tb, extack);
+	if (err)
+		return err;
+
+	vxlan_mdb_flush(vxlan, &desc);
+
+	return 0;
+}
+
 static const struct nla_policy vxlan_mdbe_attrs_get_pol[MDBE_ATTR_MAX + 1] = {
 	[MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY,
 					      sizeof(struct in_addr),
@@ -1575,29 +1722,6 @@ static void vxlan_mdb_check_empty(void *ptr, void *arg)
 	WARN_ON_ONCE(1);
 }
 
-static void vxlan_mdb_remotes_flush(struct vxlan_dev *vxlan,
-				    struct vxlan_mdb_entry *mdb_entry)
-{
-	struct vxlan_mdb_remote *remote, *tmp;
-
-	list_for_each_entry_safe(remote, tmp, &mdb_entry->remotes, list)
-		vxlan_mdb_remote_del(vxlan, mdb_entry, remote);
-}
-
-static void vxlan_mdb_entries_flush(struct vxlan_dev *vxlan)
-{
-	struct vxlan_mdb_entry *mdb_entry;
-	struct hlist_node *tmp;
-
-	/* The removal of an entry cannot trigger the removal of another entry
-	 * since entries are always added to the head of the list.
-	 */
-	hlist_for_each_entry_safe(mdb_entry, tmp, &vxlan->mdb_list, mdb_node) {
-		vxlan_mdb_remotes_flush(vxlan, mdb_entry);
-		vxlan_mdb_entry_put(vxlan, mdb_entry);
-	}
-}
-
 int vxlan_mdb_init(struct vxlan_dev *vxlan)
 {
 	int err;
@@ -1613,7 +1737,9 @@ int vxlan_mdb_init(struct vxlan_dev *vxlan)
 
 void vxlan_mdb_fini(struct vxlan_dev *vxlan)
 {
-	vxlan_mdb_entries_flush(vxlan);
+	struct vxlan_mdb_flush_desc desc = {};
+
+	vxlan_mdb_flush(vxlan, &desc);
 	WARN_ON_ONCE(vxlan->cfg.flags & VXLAN_F_MDB);
 	rhashtable_free_and_destroy(&vxlan->mdb_tbl, vxlan_mdb_check_empty,
 				    NULL);
diff --git a/drivers/net/vxlan/vxlan_private.h b/drivers/net/vxlan/vxlan_private.h
index db679c380955..b35d96b78843 100644
--- a/drivers/net/vxlan/vxlan_private.h
+++ b/drivers/net/vxlan/vxlan_private.h
@@ -235,6 +235,8 @@ int vxlan_mdb_add(struct net_device *dev, struct nlattr *tb[], u16 nlmsg_flags,
 		  struct netlink_ext_ack *extack);
 int vxlan_mdb_del(struct net_device *dev, struct nlattr *tb[],
 		  struct netlink_ext_ack *extack);
+int vxlan_mdb_del_bulk(struct net_device *dev, struct nlattr *tb[],
+		       struct netlink_ext_ack *extack);
 int vxlan_mdb_get(struct net_device *dev, struct nlattr *tb[], u32 portid,
 		  u32 seq, struct netlink_ext_ack *extack);
 struct vxlan_mdb_entry *vxlan_mdb_entry_skb_get(struct vxlan_dev *vxlan,
diff --git a/drivers/net/wan/Kconfig b/drivers/net/wan/Kconfig
index dcb069dde66b..7dda87756d3f 100644
--- a/drivers/net/wan/Kconfig
+++ b/drivers/net/wan/Kconfig
@@ -95,6 +95,8 @@ config HDLC_X25
 comment "X.25/LAPB support is disabled"
 	depends on HDLC && (LAPB!=m || HDLC!=m) && LAPB!=y
 
+source "drivers/net/wan/framer/Kconfig"
+
 config PCI200SYN
 	tristate "Goramo PCI200SYN support"
 	depends on HDLC && PCI
diff --git a/drivers/net/wan/Makefile b/drivers/net/wan/Makefile
index 5bec8fae47f8..8119b49d1da9 100644
--- a/drivers/net/wan/Makefile
+++ b/drivers/net/wan/Makefile
@@ -14,6 +14,8 @@ obj-$(CONFIG_HDLC_FR)		+= hdlc_fr.o
 obj-$(CONFIG_HDLC_PPP)		+= hdlc_ppp.o
 obj-$(CONFIG_HDLC_X25)		+= hdlc_x25.o
 
+obj-y				+= framer/
+
 obj-$(CONFIG_FARSYNC)		+= farsync.o
 
 obj-$(CONFIG_LAPBETHER)		+= lapbether.o
diff --git a/drivers/net/wan/framer/Kconfig b/drivers/net/wan/framer/Kconfig
new file mode 100644
index 000000000000..dc83caef9485
--- /dev/null
+++ b/drivers/net/wan/framer/Kconfig
@@ -0,0 +1,42 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# FRAMER
+#
+
+menuconfig FRAMER
+	tristate "Framer Subsystem"
+	help
+	  A framer is a component in charge of an E1/T1 line interface.
+	  Connected usually to a TDM bus, it converts TDM frames to/from E1/T1
+	  frames. It also provides information related to the E1/T1 line.
+	  Used with HDLC, the network can be reached through the E1/T1 line.
+
+	  This framework is designed to provide a generic interface for framer
+	  devices present in the kernel. This layer will have the generic
+	  API by which framer drivers can create framer using the framer
+	  framework and framer users can obtain reference to the framer.
+	  All the users of this framework should select this config.
+
+if FRAMER
+
+config GENERIC_FRAMER
+	bool
+
+config FRAMER_PEF2256
+	tristate "Lantiq PEF2256"
+	depends on OF
+	depends on HAS_IOMEM
+	select GENERIC_FRAMER
+	select MFD_CORE
+	select REGMAP_MMIO
+	help
+	  Enable support for the Lantiq PEF2256 (FALC56) framer.
+	  The PEF2256 is a framer and line interface between analog E1/T1/J1
+	  line and a digital PCM bus.
+
+	  If unsure, say N.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called framer-pef2256.
+
+endif # FRAMER
diff --git a/drivers/net/wan/framer/Makefile b/drivers/net/wan/framer/Makefile
new file mode 100644
index 000000000000..3403f2b14534
--- /dev/null
+++ b/drivers/net/wan/framer/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the framer drivers.
+#
+
+obj-$(CONFIG_GENERIC_FRAMER)			+= framer-core.o
+obj-$(CONFIG_FRAMER_PEF2256)			+= pef2256/
diff --git a/drivers/net/wan/framer/framer-core.c b/drivers/net/wan/framer/framer-core.c
new file mode 100644
index 000000000000..c04dc88bda6c
--- /dev/null
+++ b/drivers/net/wan/framer/framer-core.c
@@ -0,0 +1,882 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Generic Framer framework.
+ *
+ * Copyright 2023 CS GROUP France
+ *
+ * Author: Herve Codina <herve.codina@bootlin.com>
+ */
+
+#include <linux/device.h>
+#include <linux/framer/framer.h>
+#include <linux/framer/framer-provider.h>
+#include <linux/idr.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+#include <linux/of.h>
+#include <linux/pm_runtime.h>
+#include <linux/regulator/consumer.h>
+#include <linux/slab.h>
+
+static struct class *framer_class;
+static DEFINE_MUTEX(framer_provider_mutex);
+static LIST_HEAD(framer_provider_list);
+static DEFINE_IDA(framer_ida);
+
+#define dev_to_framer(a)	(container_of((a), struct framer, dev))
+
+int framer_pm_runtime_get(struct framer *framer)
+{
+	int ret;
+
+	if (!pm_runtime_enabled(&framer->dev))
+		return -EOPNOTSUPP;
+
+	ret = pm_runtime_get(&framer->dev);
+	if (ret < 0 && ret != -EINPROGRESS)
+		pm_runtime_put_noidle(&framer->dev);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(framer_pm_runtime_get);
+
+int framer_pm_runtime_get_sync(struct framer *framer)
+{
+	int ret;
+
+	if (!pm_runtime_enabled(&framer->dev))
+		return -EOPNOTSUPP;
+
+	ret = pm_runtime_get_sync(&framer->dev);
+	if (ret < 0)
+		pm_runtime_put_sync(&framer->dev);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(framer_pm_runtime_get_sync);
+
+int framer_pm_runtime_put(struct framer *framer)
+{
+	if (!pm_runtime_enabled(&framer->dev))
+		return -EOPNOTSUPP;
+
+	return pm_runtime_put(&framer->dev);
+}
+EXPORT_SYMBOL_GPL(framer_pm_runtime_put);
+
+int framer_pm_runtime_put_sync(struct framer *framer)
+{
+	if (!pm_runtime_enabled(&framer->dev))
+		return -EOPNOTSUPP;
+
+	return pm_runtime_put_sync(&framer->dev);
+}
+EXPORT_SYMBOL_GPL(framer_pm_runtime_put_sync);
+
+/**
+ * framer_init - framer internal initialization before framer operation
+ * @framer: the framer returned by framer_get()
+ *
+ * Used to allow framer's driver to perform framer internal initialization,
+ * such as PLL block powering, clock initialization or anything that's
+ * is required by the framer to perform the start of operation.
+ * Must be called before framer_power_on().
+ *
+ * Return: %0 if successful, a negative error code otherwise
+ */
+int framer_init(struct framer *framer)
+{
+	bool start_polling = false;
+	int ret;
+
+	ret = framer_pm_runtime_get_sync(framer);
+	if (ret < 0 && ret != -EOPNOTSUPP)
+		return ret;
+	ret = 0; /* Override possible ret == -EOPNOTSUPP */
+
+	mutex_lock(&framer->mutex);
+	if (framer->power_count > framer->init_count)
+		dev_warn(&framer->dev, "framer_power_on was called before framer init\n");
+
+	if (framer->init_count == 0) {
+		if (framer->ops->init) {
+			ret = framer->ops->init(framer);
+			if (ret < 0) {
+				dev_err(&framer->dev, "framer init failed --> %d\n", ret);
+				goto out;
+			}
+		}
+		if (framer->ops->flags & FRAMER_FLAG_POLL_STATUS)
+			start_polling = true;
+	}
+	++framer->init_count;
+
+out:
+	mutex_unlock(&framer->mutex);
+
+	if (!ret && start_polling) {
+		ret = framer_get_status(framer, &framer->prev_status);
+		if (ret < 0) {
+			dev_warn(&framer->dev, "framer get status failed --> %d\n", ret);
+			/* Will be retried on polling_work */
+			ret = 0;
+		}
+		queue_delayed_work(system_power_efficient_wq, &framer->polling_work, 1 * HZ);
+	}
+
+	framer_pm_runtime_put(framer);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(framer_init);
+
+/**
+ * framer_exit - Framer internal un-initialization
+ * @framer: the framer returned by framer_get()
+ *
+ * Must be called after framer_power_off().
+ */
+int framer_exit(struct framer *framer)
+{
+	int ret;
+
+	ret = framer_pm_runtime_get_sync(framer);
+	if (ret < 0 && ret != -EOPNOTSUPP)
+		return ret;
+	ret = 0; /* Override possible ret == -EOPNOTSUPP */
+
+	mutex_lock(&framer->mutex);
+	--framer->init_count;
+	if (framer->init_count == 0) {
+		if (framer->ops->flags & FRAMER_FLAG_POLL_STATUS) {
+			mutex_unlock(&framer->mutex);
+			cancel_delayed_work_sync(&framer->polling_work);
+			mutex_lock(&framer->mutex);
+		}
+
+		if (framer->ops->exit)
+			framer->ops->exit(framer);
+	}
+
+	mutex_unlock(&framer->mutex);
+	framer_pm_runtime_put(framer);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(framer_exit);
+
+/**
+ * framer_power_on - Enable the framer and enter proper operation
+ * @framer: the framer returned by framer_get()
+ *
+ * Must be called after framer_init().
+ *
+ * Return: %0 if successful, a negative error code otherwise
+ */
+int framer_power_on(struct framer *framer)
+{
+	int ret;
+
+	if (framer->pwr) {
+		ret = regulator_enable(framer->pwr);
+		if (ret)
+			return ret;
+	}
+
+	ret = framer_pm_runtime_get_sync(framer);
+	if (ret < 0 && ret != -EOPNOTSUPP)
+		goto err_pm_sync;
+
+	mutex_lock(&framer->mutex);
+	if (framer->power_count == 0 && framer->ops->power_on) {
+		ret = framer->ops->power_on(framer);
+		if (ret < 0) {
+			dev_err(&framer->dev, "framer poweron failed --> %d\n", ret);
+			goto err_pwr_on;
+		}
+	}
+	++framer->power_count;
+	mutex_unlock(&framer->mutex);
+	return 0;
+
+err_pwr_on:
+	mutex_unlock(&framer->mutex);
+	framer_pm_runtime_put_sync(framer);
+err_pm_sync:
+	if (framer->pwr)
+		regulator_disable(framer->pwr);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(framer_power_on);
+
+/**
+ * framer_power_off - Disable the framer.
+ * @framer: the framer returned by framer_get()
+ *
+ * Must be called before framer_exit().
+ *
+ * Return: %0 if successful, a negative error code otherwise
+ */
+int framer_power_off(struct framer *framer)
+{
+	int ret;
+
+	mutex_lock(&framer->mutex);
+	if (framer->power_count == 1 && framer->ops->power_off) {
+		ret = framer->ops->power_off(framer);
+		if (ret < 0) {
+			dev_err(&framer->dev, "framer poweroff failed --> %d\n", ret);
+			mutex_unlock(&framer->mutex);
+			return ret;
+		}
+	}
+	--framer->power_count;
+	mutex_unlock(&framer->mutex);
+	framer_pm_runtime_put(framer);
+
+	if (framer->pwr)
+		regulator_disable(framer->pwr);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(framer_power_off);
+
+/**
+ * framer_get_status() - Gets the framer status
+ * @framer: the framer returned by framer_get()
+ * @status: the status to retrieve
+ *
+ * Used to get the framer status. framer_init() must have been called
+ * on the framer.
+ *
+ * Return: %0 if successful, a negative error code otherwise
+ */
+int framer_get_status(struct framer *framer, struct framer_status *status)
+{
+	int ret;
+
+	if (!framer->ops->get_status)
+		return -EOPNOTSUPP;
+
+	/* Be sure to have known values (struct padding and future extensions) */
+	memset(status, 0, sizeof(*status));
+
+	mutex_lock(&framer->mutex);
+	ret = framer->ops->get_status(framer, status);
+	mutex_unlock(&framer->mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(framer_get_status);
+
+/**
+ * framer_set_config() - Sets the framer configuration
+ * @framer: the framer returned by framer_get()
+ * @config: the configuration to set
+ *
+ * Used to set the framer configuration. framer_init() must have been called
+ * on the framer.
+ *
+ * Return: %0 if successful, a negative error code otherwise
+ */
+int framer_set_config(struct framer *framer, const struct framer_config *config)
+{
+	int ret;
+
+	if (!framer->ops->set_config)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&framer->mutex);
+	ret = framer->ops->set_config(framer, config);
+	mutex_unlock(&framer->mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(framer_set_config);
+
+/**
+ * framer_get_config() - Gets the framer configuration
+ * @framer: the framer returned by framer_get()
+ * @config: the configuration to retrieve
+ *
+ * Used to get the framer configuration. framer_init() must have been called
+ * on the framer.
+ *
+ * Return: %0 if successful, a negative error code otherwise
+ */
+int framer_get_config(struct framer *framer, struct framer_config *config)
+{
+	int ret;
+
+	if (!framer->ops->get_config)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&framer->mutex);
+	ret = framer->ops->get_config(framer, config);
+	mutex_unlock(&framer->mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(framer_get_config);
+
+static void framer_polling_work(struct work_struct *work)
+{
+	struct framer *framer = container_of(work, struct framer, polling_work.work);
+	struct framer_status status;
+	int ret;
+
+	ret = framer_get_status(framer, &status);
+	if (ret) {
+		dev_err(&framer->dev, "polling, get status failed (%d)\n", ret);
+		goto end;
+	}
+	if (memcmp(&framer->prev_status, &status, sizeof(status))) {
+		blocking_notifier_call_chain(&framer->notifier_list,
+					     FRAMER_EVENT_STATUS, NULL);
+		memcpy(&framer->prev_status, &status, sizeof(status));
+	}
+
+end:
+	/* Re-schedule task in 1 sec */
+	queue_delayed_work(system_power_efficient_wq, &framer->polling_work, 1 * HZ);
+}
+
+/**
+ * framer_notifier_register() - Registers a notifier
+ * @framer: the framer returned by framer_get()
+ * @nb: the notifier block to register
+ *
+ * Used to register a notifier block on framer events. framer_init() must have
+ * been called on the framer.
+ * The available framer events are present in enum framer_events.
+ *
+ * Return: %0 if successful, a negative error code otherwise
+ */
+int framer_notifier_register(struct framer *framer, struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&framer->notifier_list, nb);
+}
+EXPORT_SYMBOL_GPL(framer_notifier_register);
+
+/**
+ * framer_notifier_unregister() - Unregisters a notifier
+ * @framer: the framer returned by framer_get()
+ * @nb: the notifier block to unregister
+ *
+ * Used to unregister a notifier block. framer_init() must have
+ * been called on the framer.
+ *
+ * Return: %0 if successful, a negative error code otherwise
+ */
+int framer_notifier_unregister(struct framer *framer, struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(&framer->notifier_list, nb);
+}
+EXPORT_SYMBOL_GPL(framer_notifier_unregister);
+
+static struct framer_provider *framer_provider_of_lookup(const struct device_node *node)
+{
+	struct framer_provider *framer_provider;
+
+	list_for_each_entry(framer_provider, &framer_provider_list, list) {
+		if (device_match_of_node(framer_provider->dev, node))
+			return framer_provider;
+	}
+
+	return ERR_PTR(-EPROBE_DEFER);
+}
+
+static struct framer *framer_of_get_from_provider(struct of_phandle_args *args)
+{
+	struct framer_provider *framer_provider;
+	struct framer *framer;
+
+	mutex_lock(&framer_provider_mutex);
+	framer_provider = framer_provider_of_lookup(args->np);
+	if (IS_ERR(framer_provider) || !try_module_get(framer_provider->owner)) {
+		framer = ERR_PTR(-EPROBE_DEFER);
+		goto end;
+	}
+
+	framer = framer_provider->of_xlate(framer_provider->dev, args);
+
+	module_put(framer_provider->owner);
+
+end:
+	mutex_unlock(&framer_provider_mutex);
+
+	return framer;
+}
+
+static struct framer *framer_of_get_byphandle(struct device_node *np, const char *propname,
+					      int index)
+{
+	struct of_phandle_args args;
+	struct framer *framer;
+	int ret;
+
+	ret = of_parse_phandle_with_optional_args(np, propname, "#framer-cells", index, &args);
+	if (ret)
+		return ERR_PTR(-ENODEV);
+
+	if (!of_device_is_available(args.np)) {
+		framer = ERR_PTR(-ENODEV);
+		goto out_node_put;
+	}
+
+	framer = framer_of_get_from_provider(&args);
+
+out_node_put:
+	of_node_put(args.np);
+
+	return framer;
+}
+
+static struct framer *framer_of_get_byparent(struct device_node *np, int index)
+{
+	struct of_phandle_args args;
+	struct framer *framer;
+
+	args.np = of_get_parent(np);
+	args.args_count = 1;
+	args.args[0] = index;
+
+	while (args.np) {
+		framer = framer_of_get_from_provider(&args);
+		if (IS_ERR(framer) && PTR_ERR(framer) != -EPROBE_DEFER) {
+			args.np = of_get_next_parent(args.np);
+			continue;
+		}
+		of_node_put(args.np);
+		return framer;
+	}
+
+	return ERR_PTR(-ENODEV);
+}
+
+/**
+ * framer_get() - lookup and obtain a reference to a framer.
+ * @dev: device that requests the framer
+ * @con_id: name of the framer from device's point of view
+ *
+ * Returns the framer driver, after getting a refcount to it; or
+ * -ENODEV if there is no such framer. The caller is responsible for
+ * calling framer_put() to release that count.
+ */
+struct framer *framer_get(struct device *dev, const char *con_id)
+{
+	struct framer *framer = ERR_PTR(-ENODEV);
+	struct device_link *link;
+	int ret;
+
+	if (dev->of_node) {
+		if (con_id)
+			framer = framer_of_get_byphandle(dev->of_node, con_id, 0);
+		else
+			framer = framer_of_get_byparent(dev->of_node, 0);
+	}
+
+	if (IS_ERR(framer))
+		return framer;
+
+	get_device(&framer->dev);
+
+	if (!try_module_get(framer->ops->owner)) {
+		ret = -EPROBE_DEFER;
+		goto err_put_device;
+	}
+
+	link = device_link_add(dev, &framer->dev, DL_FLAG_STATELESS);
+	if (!link) {
+		dev_err(dev, "failed to create device_link to %s\n", dev_name(&framer->dev));
+		ret = -EPROBE_DEFER;
+		goto err_module_put;
+	}
+
+	return framer;
+
+err_module_put:
+	module_put(framer->ops->owner);
+err_put_device:
+	put_device(&framer->dev);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(framer_get);
+
+/**
+ * framer_put() - release the framer
+ * @dev: device that wants to release this framer
+ * @framer: the framer returned by framer_get()
+ *
+ * Releases a refcount the caller received from framer_get().
+ */
+void framer_put(struct device *dev, struct framer *framer)
+{
+	device_link_remove(dev, &framer->dev);
+
+	module_put(framer->ops->owner);
+	put_device(&framer->dev);
+}
+EXPORT_SYMBOL_GPL(framer_put);
+
+static void devm_framer_put(struct device *dev, void *res)
+{
+	struct framer *framer = *(struct framer **)res;
+
+	framer_put(dev, framer);
+}
+
+/**
+ * devm_framer_get() - lookup and obtain a reference to a framer.
+ * @dev: device that requests this framer
+ * @con_id: name of the framer from device's point of view
+ *
+ * Gets the framer using framer_get(), and associates a device with it using
+ * devres. On driver detach, framer_put() function is invoked on the devres
+ * data, then, devres data is freed.
+ */
+struct framer *devm_framer_get(struct device *dev, const char *con_id)
+{
+	struct framer **ptr, *framer;
+
+	ptr = devres_alloc(devm_framer_put, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	framer = framer_get(dev, con_id);
+	if (!IS_ERR(framer)) {
+		*ptr = framer;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+		return framer;
+	}
+
+	return framer;
+}
+EXPORT_SYMBOL_GPL(devm_framer_get);
+
+/**
+ * devm_framer_optional_get() - lookup and obtain a reference to an optional
+ * framer.
+ * @dev: device that requests this framer
+ * @con_id: name of the framer from device's point of view
+ *
+ * Same as devm_framer_get() except that if the framer does not exist, it is not
+ * considered an error and -ENODEV will not be returned. Instead the NULL framer
+ * is returned.
+ */
+struct framer *devm_framer_optional_get(struct device *dev, const char *con_id)
+{
+	struct framer *framer = devm_framer_get(dev, con_id);
+
+	if (PTR_ERR(framer) == -ENODEV)
+		framer = NULL;
+
+	return framer;
+}
+EXPORT_SYMBOL_GPL(devm_framer_optional_get);
+
+static void framer_notify_status_work(struct work_struct *work)
+{
+	struct framer *framer = container_of(work, struct framer, notify_status_work);
+
+	blocking_notifier_call_chain(&framer->notifier_list, FRAMER_EVENT_STATUS, NULL);
+}
+
+void framer_notify_status_change(struct framer *framer)
+{
+	/* Can be called from atomic context -> just schedule a task to call
+	 * blocking notifiers
+	 */
+	queue_work(system_power_efficient_wq, &framer->notify_status_work);
+}
+EXPORT_SYMBOL_GPL(framer_notify_status_change);
+
+/**
+ * framer_create() - create a new framer
+ * @dev: device that is creating the new framer
+ * @node: device node of the framer. default to dev->of_node.
+ * @ops: function pointers for performing framer operations
+ *
+ * Called to create a framer using framer framework.
+ */
+struct framer *framer_create(struct device *dev, struct device_node *node,
+			     const struct framer_ops *ops)
+{
+	struct framer *framer;
+	int ret;
+	int id;
+
+	/* get_status() is mandatory if the provider ask for polling status */
+	if (WARN_ON((ops->flags & FRAMER_FLAG_POLL_STATUS) && !ops->get_status))
+		return ERR_PTR(-EINVAL);
+
+	framer = kzalloc(sizeof(*framer), GFP_KERNEL);
+	if (!framer)
+		return ERR_PTR(-ENOMEM);
+
+	id = ida_alloc(&framer_ida, GFP_KERNEL);
+	if (id < 0) {
+		dev_err(dev, "unable to get id\n");
+		ret = id;
+		goto free_framer;
+	}
+
+	device_initialize(&framer->dev);
+	mutex_init(&framer->mutex);
+	INIT_WORK(&framer->notify_status_work, framer_notify_status_work);
+	INIT_DELAYED_WORK(&framer->polling_work, framer_polling_work);
+	BLOCKING_INIT_NOTIFIER_HEAD(&framer->notifier_list);
+
+	framer->dev.class = framer_class;
+	framer->dev.parent = dev;
+	framer->dev.of_node = node ? node : dev->of_node;
+	framer->id = id;
+	framer->ops = ops;
+
+	ret = dev_set_name(&framer->dev, "framer-%s.%d", dev_name(dev), id);
+	if (ret)
+		goto put_dev;
+
+	/* framer-supply */
+	framer->pwr = regulator_get_optional(&framer->dev, "framer");
+	if (IS_ERR(framer->pwr)) {
+		ret = PTR_ERR(framer->pwr);
+		if (ret == -EPROBE_DEFER)
+			goto put_dev;
+
+		framer->pwr = NULL;
+	}
+
+	ret = device_add(&framer->dev);
+	if (ret)
+		goto put_dev;
+
+	if (pm_runtime_enabled(dev)) {
+		pm_runtime_enable(&framer->dev);
+		pm_runtime_no_callbacks(&framer->dev);
+	}
+
+	return framer;
+
+put_dev:
+	put_device(&framer->dev);  /* calls framer_release() which frees resources */
+	return ERR_PTR(ret);
+
+free_framer:
+	kfree(framer);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(framer_create);
+
+/**
+ * framer_destroy() - destroy the framer
+ * @framer: the framer to be destroyed
+ *
+ * Called to destroy the framer.
+ */
+void framer_destroy(struct framer *framer)
+{
+	/* polling_work should already be stopped but if framer_exit() was not
+	 * called (bug), here it's the last time to do that ...
+	 */
+	cancel_delayed_work_sync(&framer->polling_work);
+	cancel_work_sync(&framer->notify_status_work);
+	pm_runtime_disable(&framer->dev);
+	device_unregister(&framer->dev); /* calls framer_release() which frees resources */
+}
+EXPORT_SYMBOL_GPL(framer_destroy);
+
+static void devm_framer_destroy(struct device *dev, void *res)
+{
+	struct framer *framer = *(struct framer **)res;
+
+	framer_destroy(framer);
+}
+
+/**
+ * devm_framer_create() - create a new framer
+ * @dev: device that is creating the new framer
+ * @node: device node of the framer
+ * @ops: function pointers for performing framer operations
+ *
+ * Creates a new framer device adding it to the framer class.
+ * While at that, it also associates the device with the framer using devres.
+ * On driver detach, release function is invoked on the devres data,
+ * then, devres data is freed.
+ */
+struct framer *devm_framer_create(struct device *dev, struct device_node *node,
+				  const struct framer_ops *ops)
+{
+	struct framer **ptr, *framer;
+
+	ptr = devres_alloc(devm_framer_destroy, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	framer = framer_create(dev, node, ops);
+	if (!IS_ERR(framer)) {
+		*ptr = framer;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return framer;
+}
+EXPORT_SYMBOL_GPL(devm_framer_create);
+
+/**
+ * framer_provider_simple_of_xlate() - returns the framer instance from framer provider
+ * @dev: the framer provider device
+ * @args: of_phandle_args (not used here)
+ *
+ * Intended to be used by framer provider for the common case where #framer-cells is
+ * 0. For other cases where #framer-cells is greater than '0', the framer provider
+ * should provide a custom of_xlate function that reads the *args* and returns
+ * the appropriate framer.
+ */
+struct framer *framer_provider_simple_of_xlate(struct device *dev, struct of_phandle_args *args)
+{
+	struct class_dev_iter iter;
+	struct framer *framer;
+
+	class_dev_iter_init(&iter, framer_class, NULL, NULL);
+	while ((dev = class_dev_iter_next(&iter))) {
+		framer = dev_to_framer(dev);
+		if (args->np != framer->dev.of_node)
+			continue;
+
+		class_dev_iter_exit(&iter);
+		return framer;
+	}
+
+	class_dev_iter_exit(&iter);
+	return ERR_PTR(-ENODEV);
+}
+EXPORT_SYMBOL_GPL(framer_provider_simple_of_xlate);
+
+/**
+ * __framer_provider_of_register() - create/register framer provider with the framework
+ * @dev: struct device of the framer provider
+ * @owner: the module owner containing of_xlate
+ * @of_xlate: function pointer to obtain framer instance from framer provider
+ *
+ * Creates struct framer_provider from dev and of_xlate function pointer.
+ * This is used in the case of dt boot for finding the framer instance from
+ * framer provider.
+ */
+struct framer_provider *
+__framer_provider_of_register(struct device *dev, struct module *owner,
+			      struct framer *(*of_xlate)(struct device *dev,
+							 struct of_phandle_args *args))
+{
+	struct framer_provider *framer_provider;
+
+	framer_provider = kzalloc(sizeof(*framer_provider), GFP_KERNEL);
+	if (!framer_provider)
+		return ERR_PTR(-ENOMEM);
+
+	framer_provider->dev = dev;
+	framer_provider->owner = owner;
+	framer_provider->of_xlate = of_xlate;
+
+	of_node_get(framer_provider->dev->of_node);
+
+	mutex_lock(&framer_provider_mutex);
+	list_add_tail(&framer_provider->list, &framer_provider_list);
+	mutex_unlock(&framer_provider_mutex);
+
+	return framer_provider;
+}
+EXPORT_SYMBOL_GPL(__framer_provider_of_register);
+
+/**
+ * framer_provider_of_unregister() - unregister framer provider from the framework
+ * @framer_provider: framer provider returned by framer_provider_of_register()
+ *
+ * Removes the framer_provider created using framer_provider_of_register().
+ */
+void framer_provider_of_unregister(struct framer_provider *framer_provider)
+{
+	mutex_lock(&framer_provider_mutex);
+	list_del(&framer_provider->list);
+	mutex_unlock(&framer_provider_mutex);
+
+	of_node_put(framer_provider->dev->of_node);
+	kfree(framer_provider);
+}
+EXPORT_SYMBOL_GPL(framer_provider_of_unregister);
+
+static void devm_framer_provider_of_unregister(struct device *dev, void *res)
+{
+	struct framer_provider *framer_provider = *(struct framer_provider **)res;
+
+	framer_provider_of_unregister(framer_provider);
+}
+
+/**
+ * __devm_framer_provider_of_register() - create/register framer provider with
+ * the framework
+ * @dev: struct device of the framer provider
+ * @owner: the module owner containing of_xlate
+ * @of_xlate: function pointer to obtain framer instance from framer provider
+ *
+ * Creates struct framer_provider from dev and of_xlate function pointer.
+ * This is used in the case of dt boot for finding the framer instance from
+ * framer provider. While at that, it also associates the device with the
+ * framer provider using devres. On driver detach, release function is invoked
+ * on the devres data, then, devres data is freed.
+ */
+struct framer_provider *
+__devm_framer_provider_of_register(struct device *dev, struct module *owner,
+				   struct framer *(*of_xlate)(struct device *dev,
+							      struct of_phandle_args *args))
+{
+	struct framer_provider **ptr, *framer_provider;
+
+	ptr = devres_alloc(devm_framer_provider_of_unregister, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	framer_provider = __framer_provider_of_register(dev, owner, of_xlate);
+	if (!IS_ERR(framer_provider)) {
+		*ptr = framer_provider;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return framer_provider;
+}
+EXPORT_SYMBOL_GPL(__devm_framer_provider_of_register);
+
+/**
+ * framer_release() - release the framer
+ * @dev: the dev member within framer
+ *
+ * When the last reference to the device is removed, it is called
+ * from the embedded kobject as release method.
+ */
+static void framer_release(struct device *dev)
+{
+	struct framer *framer;
+
+	framer = dev_to_framer(dev);
+	regulator_put(framer->pwr);
+	ida_free(&framer_ida, framer->id);
+	kfree(framer);
+}
+
+static int __init framer_core_init(void)
+{
+	framer_class = class_create("framer");
+	if (IS_ERR(framer_class)) {
+		pr_err("failed to create framer class (%pe)\n", framer_class);
+		return PTR_ERR(framer_class);
+	}
+
+	framer_class->dev_release = framer_release;
+
+	return 0;
+}
+device_initcall(framer_core_init);
diff --git a/drivers/net/wan/framer/pef2256/Makefile b/drivers/net/wan/framer/pef2256/Makefile
new file mode 100644
index 000000000000..f4d1208dd8a4
--- /dev/null
+++ b/drivers/net/wan/framer/pef2256/Makefile
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the pef2256 driver.
+#
+
+obj-$(CONFIG_FRAMER_PEF2256)		+= framer-pef2256.o
+
+framer-pef2256-objs	:= pef2256.o
diff --git a/drivers/net/wan/framer/pef2256/pef2256-regs.h b/drivers/net/wan/framer/pef2256/pef2256-regs.h
new file mode 100644
index 000000000000..5d3183c91714
--- /dev/null
+++ b/drivers/net/wan/framer/pef2256/pef2256-regs.h
@@ -0,0 +1,250 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * PEF2256 registers definition
+ *
+ * Copyright 2023 CS GROUP France
+ *
+ * Author: Herve Codina <herve.codina@bootlin.com>
+ */
+#ifndef __PEF2256_REGS_H__
+#define __PEF2256_REGS_H__
+
+#include "linux/bitfield.h"
+
+/* Command Register */
+#define PEF2256_CMDR		0x02
+#define PEF2256_CMDR_RRES	BIT(6)
+#define PEF2256_CMDR_XRES	BIT(4)
+#define PEF2256_CMDR_SRES	BIT(0)
+
+/* Interrupt Mask Register 0..5 */
+#define PEF2256_IMR0	        0x14
+#define PEF2256_IMR1	        0x15
+#define PEF2256_IMR2	        0x16
+#define PEF2256_IMR3	        0x17
+#define PEF2256_IMR4	        0x18
+#define PEF2256_IMR5	        0x19
+
+/* Framer Mode Register 0 */
+#define PEF2256_FMR0		0x1C
+#define PEF2256_FMR0_XC_MASK	GENMASK(7, 6)
+#define PEF2256_FMR0_XC_NRZ	FIELD_PREP_CONST(PEF2256_FMR0_XC_MASK, 0x0)
+#define PEF2256_FMR0_XC_CMI	FIELD_PREP_CONST(PEF2256_FMR0_XC_MASK, 0x1)
+#define PEF2256_FMR0_XC_AMI	FIELD_PREP_CONST(PEF2256_FMR0_XC_MASK, 0x2)
+#define PEF2256_FMR0_XC_HDB3	FIELD_PREP_CONST(PEF2256_FMR0_XC_MASK, 0x3)
+#define PEF2256_FMR0_RC_MASK	GENMASK(5, 4)
+#define PEF2256_FMR0_RC_NRZ	FIELD_PREP_CONST(PEF2256_FMR0_RC_MASK, 0x0)
+#define PEF2256_FMR0_RC_CMI	FIELD_PREP_CONST(PEF2256_FMR0_RC_MASK, 0x1)
+#define PEF2256_FMR0_RC_AMI	FIELD_PREP_CONST(PEF2256_FMR0_RC_MASK, 0x2)
+#define PEF2256_FMR0_RC_HDB3	FIELD_PREP_CONST(PEF2256_FMR0_RC_MASK, 0x3)
+
+/* Framer Mode Register 1 */
+#define PEF2256_FMR1		0x1D
+#define PEF2256_FMR1_XFS	BIT(3)
+#define PEF2256_FMR1_ECM	BIT(2)
+/* SSD is defined on 2 bits. The other bit is on SIC1 register */
+#define PEF2256_FMR1_SSD_MASK	GENMASK(1, 1)
+#define PEF2256_FMR1_SSD_2048	FIELD_PREP_CONST(PEF2256_FMR1_SSD_MASK, 0x0)
+#define PEF2256_FMR1_SSD_4096	FIELD_PREP_CONST(PEF2256_FMR1_SSD_MASK, 0x1)
+#define PEF2256_FMR1_SSD_8192	FIELD_PREP_CONST(PEF2256_FMR1_SSD_MASK, 0x0)
+#define PEF2256_FMR1_SSD_16384	FIELD_PREP_CONST(PEF2256_FMR1_SSD_MASK, 0x1)
+
+/* Framer Mode Register 2 */
+#define PEF2256_FMR2			  0x1E
+#define PEF2256_FMR2_RFS_MASK		  GENMASK(7, 6)
+#define PEF2256_FMR2_RFS_DOUBLEFRAME	  FIELD_PREP_CONST(PEF2256_FMR2_RFS_MASK, 0x0)
+#define PEF2256_FMR2_RFS_CRC4_MULTIFRAME  FIELD_PREP_CONST(PEF2256_FMR2_RFS_MASK, 0x2)
+#define PEF2256_FMR2_RFS_AUTO_MULTIFRAME  FIELD_PREP_CONST(PEF2256_FMR2_RFS_MASK, 0x3)
+#define PEF2256_FMR2_AXRA		  BIT(1)
+
+/* Transmit Service Word */
+#define PEF2256_XSW		0x20
+#define PEF2256_XSW_XSIS	BIT(7)
+#define PEF2256_XSW_XTM		BIT(6)
+#define PEF2256_XSW_XY_MASK	GENMASK(5, 0)
+#define PEF2256_XSW_XY(_v)	FIELD_PREP(PEF2256_XSW_XY_MASK, _v)
+
+/* Transmit Spare Bits */
+#define PEF2256_XSP	        0x21
+#define PEF2256_XSP_XSIF	BIT(2)
+
+/* Transmit Control 0..1 */
+#define PEF2256_XC0		0x22
+#define PEF2256_XC1		0x23
+
+/* Receive Control 0 */
+#define PEF2256_RC0		0x24
+#define PEF2256_RC0_SWD		BIT(7)
+#define PEF2256_RC0_ASY4	BIT(6)
+
+/* Receive Control 1 */
+#define PEF2256_RC1		0x25
+
+/* Transmit Pulse Mask 0..1 */
+#define PEF2256_XPM0		0x26
+#define PEF2256_XPM1		0x27
+
+/* Transmit Pulse Mask 2 */
+#define PEF2256_XPM2		0x28
+#define PEF2256_XPM2_XLT	BIT(6)
+
+/* Transparent Service Word Mask */
+#define PEF2256_TSWM		0x29
+
+/* Line Interface Mode 0 */
+#define PEF2256_LIM0		0x36
+#define PEF2256_2X_LIM0_BIT3	BIT(3) /* v2.x, described as a forced '1' bit */
+#define PEF2256_LIM0_MAS	BIT(0)
+
+/* Line Interface Mode 1 */
+#define PEF2256_LIM1		  0x37
+#define PEF2256_12_LIM1_RIL_MASK  GENMASK(6, 4)
+#define PEF2256_12_LIM1_RIL_910	  FIELD_PREP_CONST(PEF2256_12_LIM1_RIL_MASK, 0x0)
+#define PEF2256_12_LIM1_RIL_740	  FIELD_PREP_CONST(PEF2256_12_LIM1_RIL_MASK, 0x1)
+#define PEF2256_12_LIM1_RIL_590	  FIELD_PREP_CONST(PEF2256_12_LIM1_RIL_MASK, 0x2)
+#define PEF2256_12_LIM1_RIL_420	  FIELD_PREP_CONST(PEF2256_12_LIM1_RIL_MASK, 0x3)
+#define PEF2256_12_LIM1_RIL_320	  FIELD_PREP_CONST(PEF2256_12_LIM1_RIL_MASK, 0x4)
+#define PEF2256_12_LIM1_RIL_210	  FIELD_PREP_CONST(PEF2256_12_LIM1_RIL_MASK, 0x5)
+#define PEF2256_12_LIM1_RIL_160	  FIELD_PREP_CONST(PEF2256_12_LIM1_RIL_MASK, 0x6)
+#define PEF2256_12_LIM1_RIL_100	  FIELD_PREP_CONST(PEF2256_12_LIM1_RIL_MASK, 0x7)
+#define PEF2256_2X_LIM1_RIL_MASK  GENMASK(6, 4)
+#define PEF2256_2X_LIM1_RIL_2250  FIELD_PREP_CONST(PEF2256_2X_LIM1_RIL_MASK, 0x0)
+#define PEF2256_2X_LIM1_RIL_1100  FIELD_PREP_CONST(PEF2256_2X_LIM1_RIL_MASK, 0x1)
+#define PEF2256_2X_LIM1_RIL_600	  FIELD_PREP_CONST(PEF2256_2X_LIM1_RIL_MASK, 0x2)
+#define PEF2256_2X_LIM1_RIL_350	  FIELD_PREP_CONST(PEF2256_2X_LIM1_RIL_MASK, 0x3)
+#define PEF2256_2X_LIM1_RIL_210	  FIELD_PREP_CONST(PEF2256_2X_LIM1_RIL_MASK, 0x4)
+#define PEF2256_2X_LIM1_RIL_140	  FIELD_PREP_CONST(PEF2256_2X_LIM1_RIL_MASK, 0x5)
+#define PEF2256_2X_LIM1_RIL_100	  FIELD_PREP_CONST(PEF2256_2X_LIM1_RIL_MASK, 0x6)
+#define PEF2256_2X_LIM1_RIL_50	  FIELD_PREP_CONST(PEF2256_2X_LIM1_RIL_MASK, 0x7)
+
+/* Pulse Count Detection */
+#define PEF2256_PCD		0x38
+
+ /* Pulse Count Recovery */
+#define PEF2256_PCR		0x39
+
+ /* Line Interface Mode 2 */
+#define PEF2256_LIM2		0x3A
+#define PEF2256_LIM2_SLT_MASK	GENMASK(5, 4)
+#define PEF2256_LIM2_SLT_THR55	FIELD_PREP_CONST(PEF2256_LIM2_SLT_MASK, 0x0)
+#define PEF2256_LIM2_SLT_THR67	FIELD_PREP_CONST(PEF2256_LIM2_SLT_MASK, 0x1)
+#define PEF2256_LIM2_SLT_THR50	FIELD_PREP_CONST(PEF2256_LIM2_SLT_MASK, 0x2)
+#define PEF2256_LIM2_SLT_THR45	FIELD_PREP_CONST(PEF2256_LIM2_SLT_MASK, 0x3)
+#define PEF2256_LIM2_ELT	BIT(2)
+
+/* System Interface Control 1 */
+#define PEF2256_SIC1	          0x3E
+#define PEF2256_SIC1_SSC_MASK	  (BIT(7) |  BIT(3))
+#define PEF2256_SIC1_SSC_2048	  (0)
+#define PEF2256_SIC1_SSC_4096	  BIT(3)
+#define PEF2256_SIC1_SSC_8192	  BIT(7)
+#define PEF2256_SIC1_SSC_16384	  (BIT(7) |  BIT(3))
+/* SSD is defined on 2 bits. The other bit is on FMR1 register */
+#define PEF2256_SIC1_SSD_MASK	  GENMASK(6, 6)
+#define PEF2256_SIC1_SSD_2048	  FIELD_PREP_CONST(PEF2256_SIC1_SSD_MASK, 0x0)
+#define PEF2256_SIC1_SSD_4096	  FIELD_PREP_CONST(PEF2256_SIC1_SSD_MASK, 0x0)
+#define PEF2256_SIC1_SSD_8192	  FIELD_PREP_CONST(PEF2256_SIC1_SSD_MASK, 0x1)
+#define PEF2256_SIC1_SSD_16384	  FIELD_PREP_CONST(PEF2256_SIC1_SSD_MASK, 0x1)
+#define PEF2256_SIC1_RBS_MASK	  GENMASK(5, 4)
+#define PEF2256_SIC1_RBS_2FRAMES  FIELD_PREP_CONST(PEF2256_SIC1_RBS_MASK, 0x0)
+#define PEF2256_SIC1_RBS_1FRAME	  FIELD_PREP_CONST(PEF2256_SIC1_RBS_MASK, 0x1)
+#define PEF2256_SIC1_RBS_96BITS	  FIELD_PREP_CONST(PEF2256_SIC1_RBS_MASK, 0x2)
+#define PEF2256_SIC1_RBS_BYPASS	  FIELD_PREP_CONST(PEF2256_SIC1_RBS_MASK, 0x3)
+#define PEF2256_SIC1_XBS_MASK	  GENMASK(1, 0)
+#define PEF2256_SIC1_XBS_BYPASS	  FIELD_PREP_CONST(PEF2256_SIC1_XBS_MASK, 0x0)
+#define PEF2256_SIC1_XBS_1FRAME	  FIELD_PREP_CONST(PEF2256_SIC1_XBS_MASK, 0x1)
+#define PEF2256_SIC1_XBS_2FRAMES  FIELD_PREP_CONST(PEF2256_SIC1_XBS_MASK, 0x2)
+#define PEF2256_SIC1_XBS_96BITS	  FIELD_PREP_CONST(PEF2256_SIC1_XBS_MASK, 0x3)
+
+/* System Interface Control 2 */
+#define PEF2256_SIC2		0x3F
+#define PEF2256_SIC2_SICS_MASK	GENMASK(3, 1)
+#define PEF2256_SIC2_SICS(_v)	FIELD_PREP(PEF2256_SIC2_SICS_MASK, _v)
+
+/* System Interface Control 3 */
+#define PEF2256_SIC3		0x40
+#define PEF2256_SIC3_RTRI	BIT(5)
+#define PEF2256_SIC3_RESX	BIT(3)
+#define PEF2256_SIC3_RESR	BIT(2)
+
+/* Clock Mode Register 1 */
+#define PEF2256_CMR1			0x44
+#define PEF2256_CMR1_RS_MASK		GENMASK(5, 4)
+#define PEF2256_CMR1_RS_DPLL		FIELD_PREP_CONST(PEF2256_CMR1_RS_MASK, 0x0)
+#define PEF2256_CMR1_RS_DPLL_LOS_HIGH	FIELD_PREP_CONST(PEF2256_CMR1_RS_MASK, 0x1)
+#define PEF2256_CMR1_RS_DCOR_2048	FIELD_PREP_CONST(PEF2256_CMR1_RS_MASK, 0x2)
+#define PEF2256_CMR1_RS_DCOR_8192	FIELD_PREP_CONST(PEF2256_CMR1_RS_MASK, 0x3)
+#define PEF2256_CMR1_DCS		BIT(3)
+
+/* Clock Mode Register 2 */
+#define PEF2256_CMR2		0x45
+#define PEF2256_CMR2_DCOXC	BIT(5)
+
+/* Global Configuration Register */
+#define PEF2256_GCR		0x46
+#define PEF2256_GCR_SCI		BIT(6)
+#define PEF2256_GCR_ECMC	BIT(4)
+
+/* Port Configuration 5 */
+#define PEF2256_PC5		0x84
+#define PEF2256_PC5_CRP         BIT(0)
+
+/* Global Port Configuration 1 */
+#define PEF2256_GPC1			0x85
+#define PEF2256_GPC1_CSFP_MASK		GENMASK(7, 5)
+#define PEF2256_GPC1_CSFP_SEC_IN_HIGH	FIELD_PREP_CONST(PEF2256_GPC1_CSFP_MASK, 0x0)
+#define PEF2256_GPC1_CSFP_SEC_OUT_HIGH	FIELD_PREP_CONST(PEF2256_GPC1_CSFP_MASK, 0x1)
+#define PEF2256_GPC1_CSFP_FSC_OUT_HIGH	FIELD_PREP_CONST(PEF2256_GPC1_CSFP_MASK, 0x2)
+#define PEF2256_GPC1_CSFP_FSC_OUT_LOW	FIELD_PREP_CONST(PEF2256_GPC1_CSFP_MASK, 0x3)
+
+/* Port Configuration 6 */
+#define PEF2256_PC6		0x86
+
+/* Global Counter Mode n=1..8 */
+#define PEF2256_GCM(_n)         (0x92 + (_n) - 1)
+#define PEF2256_GCM1	        0x92
+#define PEF2256_GCM2	        0x93
+#define PEF2256_GCM3	        0x94
+#define PEF2256_GCM4	        0x95
+#define PEF2256_GCM5	        0x96
+#define PEF2256_GCM6	        0x97
+#define PEF2256_GCM7	        0x98
+#define PEF2256_GCM8	        0x99
+
+/* Version Status Register */
+#define PEF2256_VSTR		 0x4A
+#define PEF2256_VSTR_VERSION_12	 0x00
+#define PEF2256_VSTR_VERSION_21	 0x10
+#define PEF2256_VSTR_VERSION_2x	 0x05
+
+/* Framer Receive Status 0 */
+#define PEF2256_FRS0		0x4C
+#define PEF2256_FRS0_LOS	BIT(7)
+#define PEF2256_FRS0_AIS	BIT(6)
+
+/* Interrupt Status Register 0..5 */
+#define PEF2256_ISR(_n)		(0x68 + (_n))
+#define PEF2256_ISR0		0x68
+#define PEF2256_ISR1		0x69
+#define PEF2256_ISR2		0x6A
+#define PEF2256_ISR3		0x6B
+#define PEF2256_ISR4		0x6C
+#define PEF2256_ISR5		0x6D
+
+/* Global Interrupt Status */
+#define PEF2256_GIS		0x6E
+#define PEF2256_GIS_ISR(_n)	BIT(_n)
+
+/* Wafer Identification Register */
+#define PEF2256_WID		   0xEC
+#define PEF2256_12_WID_MASK	   GENMASK(1, 0)
+#define PEF2256_12_WID_VERSION_12  FIELD_PREP_CONST(PEF2256_12_WID_MASK, 0x3)
+#define PEF2256_2X_WID_MASK	   GENMASK(7, 6)
+#define PEF2256_2X_WID_VERSION_21  FIELD_PREP_CONST(PEF2256_2X_WID_MASK, 0x0)
+#define PEF2256_2X_WID_VERSION_22  FIELD_PREP_CONST(PEF2256_2X_WID_MASK, 0x1)
+
+/* IMR2/ISR2 Interrupts common bits */
+#define PEF2256_INT2_AIS	BIT(3)
+#define PEF2256_INT2_LOS	BIT(2)
+
+#endif /* __PEF2256_REGS_H__ */
diff --git a/drivers/net/wan/framer/pef2256/pef2256.c b/drivers/net/wan/framer/pef2256/pef2256.c
new file mode 100644
index 000000000000..4f81053ee4f0
--- /dev/null
+++ b/drivers/net/wan/framer/pef2256/pef2256.c
@@ -0,0 +1,880 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * PEF2256 also known as FALC56 driver
+ *
+ * Copyright 2023 CS GROUP France
+ *
+ * Author: Herve Codina <herve.codina@bootlin.com>
+ */
+
+#include <linux/framer/pef2256.h>
+#include <linux/clk.h>
+#include <linux/framer/framer-provider.h>
+#include <linux/gpio/consumer.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/mfd/core.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include "pef2256-regs.h"
+
+enum pef2256_frame_type {
+	PEF2256_FRAME_E1_DOUBLEFRAME,
+	PEF2256_FRAME_E1_CRC4_MULTIFRAME,
+	PEF2256_FRAME_E1_AUTO_MULTIFRAME,
+	PEF2256_FRAME_T1J1_4FRAME,
+	PEF2256_FRAME_T1J1_12FRAME,
+	PEF2256_FRAME_T1J1_24FRAME,
+	PEF2256_FRAME_T1J1_72FRAME,
+};
+
+struct pef2256 {
+	struct device *dev;
+	struct regmap *regmap;
+	enum pef2256_version version;
+	struct clk *mclk;
+	struct clk *sclkr;
+	struct clk *sclkx;
+	struct gpio_desc *reset_gpio;
+	unsigned long sysclk_rate;
+	u32 data_rate;
+	bool is_tx_falling_edge;
+	bool is_subordinate;
+	enum pef2256_frame_type frame_type;
+	u8 channel_phase;
+	atomic_t carrier;
+	struct framer *framer;
+};
+
+static u8 pef2256_read8(struct pef2256 *pef2256, int offset)
+{
+	int val;
+
+	regmap_read(pef2256->regmap, offset, &val);
+	return val;
+}
+
+static void pef2256_write8(struct pef2256 *pef2256, int offset, u8 val)
+{
+	regmap_write(pef2256->regmap, offset, val);
+}
+
+static void pef2256_clrbits8(struct pef2256 *pef2256, int offset, u8 clr)
+{
+	regmap_clear_bits(pef2256->regmap, offset, clr);
+}
+
+static void pef2256_setbits8(struct pef2256 *pef2256, int offset, u8 set)
+{
+	regmap_set_bits(pef2256->regmap, offset, set);
+}
+
+static void pef2256_clrsetbits8(struct pef2256 *pef2256, int offset, u8 clr, u8 set)
+{
+	regmap_update_bits(pef2256->regmap, offset, clr | set, set);
+}
+
+enum pef2256_version pef2256_get_version(struct pef2256 *pef2256)
+{
+	enum pef2256_version version = PEF2256_VERSION_UNKNOWN;
+	u8 vstr, wid;
+
+	vstr = pef2256_read8(pef2256, PEF2256_VSTR);
+	wid = pef2256_read8(pef2256, PEF2256_WID);
+
+	switch (vstr) {
+	case PEF2256_VSTR_VERSION_12:
+		if ((wid & PEF2256_12_WID_MASK) == PEF2256_12_WID_VERSION_12)
+			version = PEF2256_VERSION_1_2;
+		break;
+	case PEF2256_VSTR_VERSION_2x:
+		switch (wid & PEF2256_2X_WID_MASK) {
+		case PEF2256_2X_WID_VERSION_21:
+			version = PEF2256_VERSION_2_1;
+			break;
+		case PEF2256_2X_WID_VERSION_22:
+			version = PEF2256_VERSION_2_2;
+			break;
+		}
+		break;
+	case PEF2256_VSTR_VERSION_21:
+		version = PEF2256_VERSION_2_1;
+		break;
+	}
+
+	if (version == PEF2256_VERSION_UNKNOWN)
+		dev_err(pef2256->dev, "Unknown version (0x%02x, 0x%02x)\n", vstr, wid);
+
+	return version;
+}
+EXPORT_SYMBOL_GPL(pef2256_get_version);
+
+enum pef2256_gcm_config_item {
+	PEF2256_GCM_CONFIG_1544000 = 0,
+	PEF2256_GCM_CONFIG_2048000,
+	PEF2256_GCM_CONFIG_8192000,
+	PEF2256_GCM_CONFIG_10000000,
+	PEF2256_GCM_CONFIG_12352000,
+	PEF2256_GCM_CONFIG_16384000,
+};
+
+struct pef2256_gcm_config {
+	u8 gcm_12[6];
+	u8 gcm_2x[8];
+};
+
+static const struct pef2256_gcm_config pef2256_gcm_configs[] = {
+	[PEF2256_GCM_CONFIG_1544000] = {
+		.gcm_12 = {0xF0, 0x51, 0x00, 0x80, 0x00, 0x15},
+		.gcm_2x = {0x00, 0x15, 0x00, 0x08, 0x00, 0x3F, 0x9C, 0xDF},
+	},
+	[PEF2256_GCM_CONFIG_2048000] = {
+		.gcm_12 = {0x00, 0x58, 0xD2, 0xC2, 0x00, 0x10},
+		.gcm_2x = {0x00, 0x18, 0xFB, 0x0B, 0x00, 0x2F, 0xDB, 0xDF},
+	},
+	[PEF2256_GCM_CONFIG_8192000] = {
+		.gcm_12 = {0x00, 0x58, 0xD2, 0xC2, 0x03, 0x10},
+		.gcm_2x = {0x00, 0x18, 0xFB, 0x0B, 0x00, 0x0B, 0xDB, 0xDF},
+	},
+	[PEF2256_GCM_CONFIG_10000000] = {
+		.gcm_12 = {0x90, 0x51, 0x81, 0x8F, 0x04, 0x10},
+		.gcm_2x = {0x40, 0x1B, 0x3D, 0x0A, 0x00, 0x07, 0xC9, 0xDC},
+	},
+	[PEF2256_GCM_CONFIG_12352000] = {
+		.gcm_12 = {0xF0, 0x51, 0x00, 0x80, 0x07, 0x15},
+		.gcm_2x = {0x00, 0x19, 0x00, 0x08, 0x01, 0x0A, 0x98, 0xDA},
+	},
+	[PEF2256_GCM_CONFIG_16384000] = {
+		.gcm_12 = {0x00, 0x58, 0xD2, 0xC2, 0x07, 0x10},
+		.gcm_2x = {0x00, 0x18, 0xFB, 0x0B, 0x01, 0x0B, 0xDB, 0xDF},
+	},
+};
+
+static int pef2256_setup_gcm(struct pef2256 *pef2256)
+{
+	enum pef2256_gcm_config_item item;
+	unsigned long mclk_rate;
+	const u8 *gcm;
+	int i, count;
+
+	mclk_rate = clk_get_rate(pef2256->mclk);
+	switch (mclk_rate) {
+	case 1544000:
+		item = PEF2256_GCM_CONFIG_1544000;
+		break;
+	case 2048000:
+		item = PEF2256_GCM_CONFIG_2048000;
+		break;
+	case 8192000:
+		item = PEF2256_GCM_CONFIG_8192000;
+		break;
+	case 10000000:
+		item = PEF2256_GCM_CONFIG_10000000;
+		break;
+	case 12352000:
+		item = PEF2256_GCM_CONFIG_12352000;
+		break;
+	case 16384000:
+		item = PEF2256_GCM_CONFIG_16384000;
+		break;
+	default:
+		dev_err(pef2256->dev, "Unsupported v2.x MCLK rate %lu\n", mclk_rate);
+		return -EINVAL;
+	}
+
+	BUILD_BUG_ON(item >= ARRAY_SIZE(pef2256_gcm_configs));
+
+	if (pef2256->version == PEF2256_VERSION_1_2) {
+		gcm = pef2256_gcm_configs[item].gcm_12;
+		count = ARRAY_SIZE(pef2256_gcm_configs[item].gcm_12);
+	} else {
+		gcm = pef2256_gcm_configs[item].gcm_2x;
+		count = ARRAY_SIZE(pef2256_gcm_configs[item].gcm_2x);
+	}
+
+	for (i = 0; i < count; i++)
+		pef2256_write8(pef2256, PEF2256_GCM(i + 1), *(gcm + i));
+
+	return 0;
+}
+
+static int pef2256_setup_e1_line(struct pef2256 *pef2256)
+{
+	u8 fmr1, fmr2;
+
+	/* RCLK output : DPLL clock, DCO-X enabled, DCO-X internal ref clock */
+	pef2256_write8(pef2256, PEF2256_CMR1, 0x00);
+
+	/* SCLKR selected, SCLKX selected,
+	 * receive synchro pulse sourced by SYPR,
+	 * transmit synchro pulse sourced by SYPX,
+	 * DCO-X center frequency enabled
+	 */
+	pef2256_write8(pef2256, PEF2256_CMR2, PEF2256_CMR2_DCOXC);
+
+	if (pef2256->is_subordinate) {
+		/* select RCLK source = 2M,  disable switching from RCLK to SYNC */
+		pef2256_clrsetbits8(pef2256, PEF2256_CMR1, PEF2256_CMR1_RS_MASK,
+				    PEF2256_CMR1_RS_DCOR_2048 | PEF2256_CMR1_DCS);
+	}
+
+	/* slave mode, local loop off, mode short-haul
+	 * In v2.x, bit3 is a forced 1 bit in the datasheet -> Need to be set.
+	 */
+	if (pef2256->version == PEF2256_VERSION_1_2)
+		pef2256_write8(pef2256, PEF2256_LIM0, 0x00);
+	else
+		pef2256_write8(pef2256, PEF2256_LIM0, PEF2256_2X_LIM0_BIT3);
+
+	/* "master" mode */
+	if (!pef2256->is_subordinate)
+		pef2256_setbits8(pef2256, PEF2256_LIM0, PEF2256_LIM0_MAS);
+
+	/* analog interface selected, remote loop off */
+	pef2256_write8(pef2256, PEF2256_LIM1, 0x00);
+
+	/* receive input threshold = 0,21V */
+	if (pef2256->version == PEF2256_VERSION_1_2)
+		pef2256_clrsetbits8(pef2256, PEF2256_LIM1, PEF2256_12_LIM1_RIL_MASK,
+				    PEF2256_12_LIM1_RIL_210);
+	else
+		pef2256_clrsetbits8(pef2256, PEF2256_LIM1, PEF2256_2X_LIM1_RIL_MASK,
+				    PEF2256_2X_LIM1_RIL_210);
+
+	/* transmit pulse mask, default value from datasheet
+	 * transmit line in normal operation
+	 */
+	if (pef2256->version == PEF2256_VERSION_1_2)
+		pef2256_write8(pef2256, PEF2256_XPM0, 0x7B);
+	else
+		pef2256_write8(pef2256, PEF2256_XPM0, 0x9C);
+	pef2256_write8(pef2256, PEF2256_XPM1, 0x03);
+	pef2256_write8(pef2256, PEF2256_XPM2, 0x00);
+
+	/* HDB3 coding, no alarm simulation */
+	pef2256_write8(pef2256, PEF2256_FMR0, PEF2256_FMR0_XC_HDB3 | PEF2256_FMR0_RC_HDB3);
+
+	/* E1, frame format, 2 Mbit/s system data rate, no AIS
+	 * transmission to remote end or system interface, payload loop
+	 * off, transmit remote alarm on
+	 */
+	fmr1 = 0x00;
+	fmr2 = PEF2256_FMR2_AXRA;
+	switch (pef2256->frame_type) {
+	case PEF2256_FRAME_E1_DOUBLEFRAME:
+		fmr2 |= PEF2256_FMR2_RFS_DOUBLEFRAME;
+		break;
+	case PEF2256_FRAME_E1_CRC4_MULTIFRAME:
+		fmr1 |= PEF2256_FMR1_XFS;
+		fmr2 |= PEF2256_FMR2_RFS_CRC4_MULTIFRAME;
+		break;
+	case PEF2256_FRAME_E1_AUTO_MULTIFRAME:
+		fmr1 |= PEF2256_FMR1_XFS;
+		fmr2 |= PEF2256_FMR2_RFS_AUTO_MULTIFRAME;
+		break;
+	default:
+		dev_err(pef2256->dev, "Unsupported frame type %d\n", pef2256->frame_type);
+		return -EINVAL;
+	}
+	pef2256_clrsetbits8(pef2256, PEF2256_FMR1, PEF2256_FMR1_XFS, fmr1);
+	pef2256_write8(pef2256, PEF2256_FMR2, fmr2);
+
+	if (!pef2256->is_subordinate) {
+		/* SEC input, active high */
+		pef2256_write8(pef2256, PEF2256_GPC1, PEF2256_GPC1_CSFP_SEC_IN_HIGH);
+	} else {
+		/* FSC output, active high */
+		pef2256_write8(pef2256, PEF2256_GPC1, PEF2256_GPC1_CSFP_FSC_OUT_HIGH);
+	}
+
+	/* SCLKR, SCLKX, RCLK configured to inputs,
+	 * XFMS active low, CLK1 and CLK2 pin configuration
+	 */
+	pef2256_write8(pef2256, PEF2256_PC5, 0x00);
+	pef2256_write8(pef2256, PEF2256_PC6, 0x00);
+
+	/* port RCLK is output */
+	pef2256_setbits8(pef2256, PEF2256_PC5, PEF2256_PC5_CRP);
+
+	return 0;
+}
+
+static void pef2256_setup_e1_los(struct pef2256 *pef2256)
+{
+	/* detection of LOS alarm = 176 pulses (ie (10 + 1) * 16) */
+	pef2256_write8(pef2256, PEF2256_PCD, 10);
+	/* recovery of LOS alarm = 22 pulses (ie 21 + 1) */
+	pef2256_write8(pef2256, PEF2256_PCR, 21);
+	/* E1 default for the receive slicer threshold */
+	pef2256_write8(pef2256, PEF2256_LIM2, PEF2256_LIM2_SLT_THR50);
+	if (pef2256->is_subordinate) {
+		/* Loop-timed */
+		pef2256_setbits8(pef2256, PEF2256_LIM2, PEF2256_LIM2_ELT);
+	}
+}
+
+static int pef2256_setup_e1_system(struct pef2256 *pef2256)
+{
+	u8 sic1, fmr1;
+
+	/* 2.048 MHz system clocking rate, receive buffer 2 frames, transmit
+	 * buffer bypass, data sampled and transmitted on the falling edge of
+	 * SCLKR/X, automatic freeze signaling, data is active in the first
+	 * channel phase
+	 */
+	pef2256_write8(pef2256, PEF2256_SIC1, 0x00);
+	pef2256_write8(pef2256, PEF2256_SIC2, 0x00);
+	pef2256_write8(pef2256, PEF2256_SIC3, 0x00);
+
+	if (pef2256->is_subordinate) {
+		/* transmit buffer size = 2 frames, transparent mode */
+		pef2256_clrsetbits8(pef2256, PEF2256_SIC1, PEF2256_SIC1_XBS_MASK,
+				    PEF2256_SIC1_XBS_2FRAMES);
+	}
+
+	if (pef2256->version != PEF2256_VERSION_1_2) {
+		/* during inactive channel phase switch RDO/RSIG into tri-state */
+		pef2256_setbits8(pef2256, PEF2256_SIC3, PEF2256_SIC3_RTRI);
+	}
+
+	if (pef2256->is_tx_falling_edge) {
+		/* falling edge sync pulse transmit, rising edge sync pulse receive */
+		pef2256_clrsetbits8(pef2256, PEF2256_SIC3, PEF2256_SIC3_RESX, PEF2256_SIC3_RESR);
+	} else {
+		/* rising edge sync pulse transmit, falling edge sync pulse receive */
+		pef2256_clrsetbits8(pef2256, PEF2256_SIC3, PEF2256_SIC3_RESR, PEF2256_SIC3_RESX);
+	}
+
+	/* transmit offset counter (XCO10..0) = 4 */
+	pef2256_write8(pef2256, PEF2256_XC0, 0);
+	pef2256_write8(pef2256, PEF2256_XC1, 4);
+	/* receive offset counter (RCO10..0) = 4 */
+	pef2256_write8(pef2256, PEF2256_RC0, 0);
+	pef2256_write8(pef2256, PEF2256_RC1, 4);
+
+	/* system clock rate */
+	switch (pef2256->sysclk_rate) {
+	case 2048000:
+		sic1 = PEF2256_SIC1_SSC_2048;
+		break;
+	case 4096000:
+		sic1 = PEF2256_SIC1_SSC_4096;
+		break;
+	case 8192000:
+		sic1 = PEF2256_SIC1_SSC_8192;
+		break;
+	case 16384000:
+		sic1 = PEF2256_SIC1_SSC_16384;
+		break;
+	default:
+		dev_err(pef2256->dev, "Unsupported sysclk rate %lu\n", pef2256->sysclk_rate);
+		return -EINVAL;
+	}
+	pef2256_clrsetbits8(pef2256, PEF2256_SIC1, PEF2256_SIC1_SSC_MASK, sic1);
+
+	/* data clock rate */
+	switch (pef2256->data_rate) {
+	case 2048000:
+		fmr1 = PEF2256_FMR1_SSD_2048;
+		sic1 = PEF2256_SIC1_SSD_2048;
+		break;
+	case 4096000:
+		fmr1 = PEF2256_FMR1_SSD_4096;
+		sic1 = PEF2256_SIC1_SSD_4096;
+		break;
+	case 8192000:
+		fmr1 = PEF2256_FMR1_SSD_8192;
+		sic1 = PEF2256_SIC1_SSD_8192;
+		break;
+	case 16384000:
+		fmr1 = PEF2256_FMR1_SSD_16384;
+		sic1 = PEF2256_SIC1_SSD_16384;
+		break;
+	default:
+		dev_err(pef2256->dev, "Unsupported data rate %u\n", pef2256->data_rate);
+		return -EINVAL;
+	}
+	pef2256_clrsetbits8(pef2256, PEF2256_FMR1, PEF2256_FMR1_SSD_MASK, fmr1);
+	pef2256_clrsetbits8(pef2256, PEF2256_SIC1, PEF2256_SIC1_SSD_MASK, sic1);
+
+	/* channel phase */
+	pef2256_clrsetbits8(pef2256, PEF2256_SIC2, PEF2256_SIC2_SICS_MASK,
+			    PEF2256_SIC2_SICS(pef2256->channel_phase));
+
+	return 0;
+}
+
+static void pef2256_setup_e1_signaling(struct pef2256 *pef2256)
+{
+	/* All bits of the transmitted service word are cleared */
+	pef2256_write8(pef2256, PEF2256_XSW, PEF2256_XSW_XY(0x1F));
+
+	/* CAS disabled and clear spare bit values */
+	pef2256_write8(pef2256, PEF2256_XSP, 0x00);
+
+	if (pef2256->is_subordinate) {
+		/* transparent mode */
+		pef2256_setbits8(pef2256, PEF2256_XSW, PEF2256_XSW_XTM);
+	}
+
+	/* Si-Bit, Spare bit For International, FAS word */
+	pef2256_setbits8(pef2256, PEF2256_XSW, PEF2256_XSW_XSIS);
+	pef2256_setbits8(pef2256, PEF2256_XSP, PEF2256_XSP_XSIF);
+
+	/* no transparent mode active */
+	pef2256_write8(pef2256, PEF2256_TSWM, 0x00);
+}
+
+static void pef2256_setup_e1_errors(struct pef2256 *pef2256)
+{
+	/* error counter latched every 1s */
+	pef2256_setbits8(pef2256, PEF2256_FMR1, PEF2256_FMR1_ECM);
+
+	/* error counter mode COFA */
+	pef2256_setbits8(pef2256, PEF2256_GCR, PEF2256_GCR_ECMC);
+
+	/* errors in service words have no influence */
+	pef2256_setbits8(pef2256, PEF2256_RC0, PEF2256_RC0_SWD);
+
+	/* 4 consecutive incorrect FAS causes loss of sync */
+	pef2256_setbits8(pef2256, PEF2256_RC0, PEF2256_RC0_ASY4);
+}
+
+static int pef2256_setup_e1(struct pef2256 *pef2256)
+{
+	int ret;
+
+	/* Setup, Master clocking mode (GCM8..1) */
+	ret = pef2256_setup_gcm(pef2256);
+	if (ret)
+		return ret;
+
+	/* Select E1 mode */
+	pef2256_write8(pef2256, PEF2256_FMR1, 0x00);
+
+	/* internal second timer, power on */
+	pef2256_write8(pef2256, PEF2256_GCR, 0x00);
+
+	/* Setup line interface */
+	ret = pef2256_setup_e1_line(pef2256);
+	if (ret)
+		return ret;
+
+	/* Setup Loss-of-signal detection and recovery */
+	pef2256_setup_e1_los(pef2256);
+
+	/* Setup system interface */
+	ret = pef2256_setup_e1_system(pef2256);
+	if (ret)
+		return ret;
+
+	/* Setup signaling */
+	pef2256_setup_e1_signaling(pef2256);
+
+	/* Setup errors counters and condition */
+	pef2256_setup_e1_errors(pef2256);
+
+	/* status changed interrupt at both up and down */
+	pef2256_setbits8(pef2256, PEF2256_GCR, PEF2256_GCR_SCI);
+
+	/* Clear any ISR2 pending interrupts and unmask needed interrupts */
+	pef2256_read8(pef2256, PEF2256_ISR2);
+	pef2256_clrbits8(pef2256, PEF2256_IMR2, PEF2256_INT2_LOS | PEF2256_INT2_AIS);
+
+	/* reset lines */
+	pef2256_write8(pef2256, PEF2256_CMDR, PEF2256_CMDR_RRES | PEF2256_CMDR_XRES);
+	return 0;
+}
+
+static void pef2256_isr_default_handler(struct pef2256 *pef2256, u8 nbr, u8 isr)
+{
+	dev_warn_ratelimited(pef2256->dev, "ISR%u: 0x%02x not handled\n", nbr, isr);
+}
+
+static bool pef2256_is_carrier_on(struct pef2256 *pef2256)
+{
+	u8 frs0;
+
+	frs0 = pef2256_read8(pef2256, PEF2256_FRS0);
+	return !(frs0 & (PEF2256_FRS0_LOS | PEF2256_FRS0_AIS));
+}
+
+static void pef2256_isr2_handler(struct pef2256 *pef2256, u8 nbr, u8 isr)
+{
+	bool carrier;
+
+	if (isr & (PEF2256_INT2_LOS | PEF2256_INT2_AIS)) {
+		carrier = pef2256_is_carrier_on(pef2256);
+		if (atomic_xchg(&pef2256->carrier, carrier) != carrier)
+			framer_notify_status_change(pef2256->framer);
+	}
+}
+
+static irqreturn_t pef2256_irq_handler(int irq, void *priv)
+{
+	static void (*pef2256_isr_handler[])(struct pef2256 *, u8, u8) = {
+		[0] = pef2256_isr_default_handler,
+		[1] = pef2256_isr_default_handler,
+		[2] = pef2256_isr2_handler,
+		[3] = pef2256_isr_default_handler,
+		[4] = pef2256_isr_default_handler,
+		[5] = pef2256_isr_default_handler
+	};
+	struct pef2256 *pef2256 = (struct pef2256 *)priv;
+	u8 gis;
+	u8 isr;
+	u8 n;
+
+	gis = pef2256_read8(pef2256, PEF2256_GIS);
+
+	for (n = 0; n < ARRAY_SIZE(pef2256_isr_handler); n++) {
+		if (gis & PEF2256_GIS_ISR(n)) {
+			isr = pef2256_read8(pef2256, PEF2256_ISR(n));
+			pef2256_isr_handler[n](pef2256, n, isr);
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int pef2256_check_rates(struct pef2256 *pef2256, unsigned long sysclk_rate,
+			       unsigned long data_rate)
+{
+	unsigned long rate;
+
+	switch (sysclk_rate) {
+	case 2048000:
+	case 4096000:
+	case 8192000:
+	case 16384000:
+		break;
+	default:
+		dev_err(pef2256->dev, "Unsupported system clock rate %lu\n", sysclk_rate);
+		return -EINVAL;
+	}
+
+	for (rate = data_rate; rate <= data_rate * 4; rate *= 2) {
+		if (rate == sysclk_rate)
+			return 0;
+	}
+	dev_err(pef2256->dev, "Unsupported data rate %lu with system clock rate %lu\n",
+		data_rate, sysclk_rate);
+	return -EINVAL;
+}
+
+static int pef2556_of_parse(struct pef2256 *pef2256, struct device_node *np)
+{
+	int ret;
+
+	pef2256->data_rate = 2048000;
+	ret = of_property_read_u32(np, "lantiq,data-rate-bps", &pef2256->data_rate);
+	if (ret && ret != -EINVAL) {
+		dev_err(pef2256->dev, "%pOF: failed to read lantiq,data-rate-bps\n", np);
+		return ret;
+	}
+
+	ret =  pef2256_check_rates(pef2256, pef2256->sysclk_rate, pef2256->data_rate);
+	if (ret)
+		return ret;
+
+	pef2256->is_tx_falling_edge = of_property_read_bool(np, "lantiq,clock-falling-edge");
+
+	pef2256->channel_phase = 0;
+	ret = of_property_read_u8(np, "lantiq,channel-phase", &pef2256->channel_phase);
+	if (ret && ret != -EINVAL) {
+		dev_err(pef2256->dev, "%pOF: failed to read lantiq,channel-phase\n",
+			np);
+		return ret;
+	}
+	if (pef2256->channel_phase >= pef2256->sysclk_rate / pef2256->data_rate) {
+		dev_err(pef2256->dev, "%pOF: Invalid lantiq,channel-phase %u\n",
+			np, pef2256->channel_phase);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct regmap_config pef2256_regmap_config = {
+	.reg_bits = 32,
+	.val_bits = 8,
+	.max_register = 0xff,
+};
+
+static const struct mfd_cell pef2256_devs[] = {
+	{ .name = "lantiq-pef2256-pinctrl", },
+};
+
+static int pef2256_add_audio_devices(struct pef2256 *pef2256)
+{
+	const char *compatible = "lantiq,pef2256-codec";
+	struct mfd_cell *audio_devs;
+	struct device_node *np;
+	unsigned int count = 0;
+	unsigned int i;
+	int ret;
+
+	for_each_available_child_of_node(pef2256->dev->of_node, np) {
+		if (of_device_is_compatible(np, compatible))
+			count++;
+	}
+
+	if (!count)
+		return 0;
+
+	audio_devs = kcalloc(count, sizeof(*audio_devs), GFP_KERNEL);
+	if (!audio_devs)
+		return -ENOMEM;
+
+	for (i = 0; i < count; i++) {
+		audio_devs[i].name = "framer-codec";
+		audio_devs[i].of_compatible = compatible;
+		audio_devs[i].id = i;
+	}
+
+	ret = mfd_add_devices(pef2256->dev, 0, audio_devs, count, NULL, 0, NULL);
+	kfree(audio_devs);
+	return ret;
+}
+
+static int pef2256_framer_get_status(struct framer *framer, struct framer_status *status)
+{
+	struct pef2256 *pef2256 = framer_get_drvdata(framer);
+
+	status->link_is_on = !!atomic_read(&pef2256->carrier);
+	return 0;
+}
+
+static int pef2256_framer_set_config(struct framer *framer, const struct framer_config *config)
+{
+	struct pef2256 *pef2256 = framer_get_drvdata(framer);
+
+	if (config->iface != FRAMER_IFACE_E1) {
+		dev_err(pef2256->dev, "Only E1 line is currently supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	switch (config->clock_type) {
+	case FRAMER_CLOCK_EXT:
+		pef2256->is_subordinate = true;
+		break;
+	case FRAMER_CLOCK_INT:
+		pef2256->is_subordinate = false;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Apply the new settings */
+	return pef2256_setup_e1(pef2256);
+}
+
+static int pef2256_framer_get_config(struct framer *framer, struct framer_config *config)
+{
+	struct pef2256 *pef2256 = framer_get_drvdata(framer);
+
+	config->iface = FRAMER_IFACE_E1;
+	config->clock_type = pef2256->is_subordinate ? FRAMER_CLOCK_EXT : FRAMER_CLOCK_INT;
+	config->line_clock_rate = 2048000;
+	return 0;
+}
+
+static const struct framer_ops pef2256_framer_ops = {
+	.owner = THIS_MODULE,
+	.get_status = pef2256_framer_get_status,
+	.get_config = pef2256_framer_get_config,
+	.set_config = pef2256_framer_set_config,
+};
+
+static int pef2256_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	unsigned long sclkr_rate, sclkx_rate;
+	struct framer_provider *framer_provider;
+	struct pef2256 *pef2256;
+	const char *version_txt;
+	void __iomem *iomem;
+	int ret;
+	int irq;
+
+	pef2256 = devm_kzalloc(&pdev->dev, sizeof(*pef2256), GFP_KERNEL);
+	if (!pef2256)
+		return -ENOMEM;
+
+	pef2256->dev = &pdev->dev;
+	atomic_set(&pef2256->carrier, 0);
+
+	pef2256->is_subordinate = true;
+	pef2256->frame_type = PEF2256_FRAME_E1_DOUBLEFRAME;
+
+	iomem = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(iomem))
+		return PTR_ERR(iomem);
+
+	pef2256->regmap = devm_regmap_init_mmio(&pdev->dev, iomem,
+						&pef2256_regmap_config);
+	if (IS_ERR(pef2256->regmap)) {
+		dev_err(&pdev->dev, "Failed to initialise Regmap (%ld)\n",
+			PTR_ERR(pef2256->regmap));
+		return PTR_ERR(pef2256->regmap);
+	}
+
+	pef2256->mclk = devm_clk_get_enabled(&pdev->dev, "mclk");
+	if (IS_ERR(pef2256->mclk))
+		return PTR_ERR(pef2256->mclk);
+
+	pef2256->sclkr = devm_clk_get_enabled(&pdev->dev, "sclkr");
+	if (IS_ERR(pef2256->sclkr))
+		return PTR_ERR(pef2256->sclkr);
+
+	pef2256->sclkx = devm_clk_get_enabled(&pdev->dev, "sclkx");
+	if (IS_ERR(pef2256->sclkx))
+		return PTR_ERR(pef2256->sclkx);
+
+	/* Both SCLKR (receive) and SCLKX (transmit) must have the same rate,
+	 * stored as sysclk_rate.
+	 * The exact value will be checked at pef2256_check_rates()
+	 */
+	sclkr_rate = clk_get_rate(pef2256->sclkr);
+	sclkx_rate = clk_get_rate(pef2256->sclkx);
+	if (sclkr_rate != sclkx_rate) {
+		dev_err(pef2256->dev, "clk rate mismatch. sclkr %lu Hz, sclkx %lu Hz\n",
+			sclkr_rate, sclkx_rate);
+		return -EINVAL;
+	}
+	pef2256->sysclk_rate = sclkr_rate;
+
+	/* Reset the component. The MCLK clock must be active during reset */
+	pef2256->reset_gpio = devm_gpiod_get_optional(&pdev->dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(pef2256->reset_gpio))
+		return PTR_ERR(pef2256->reset_gpio);
+	if (pef2256->reset_gpio) {
+		gpiod_set_value_cansleep(pef2256->reset_gpio, 1);
+		usleep_range(10, 20);
+		gpiod_set_value_cansleep(pef2256->reset_gpio, 0);
+		usleep_range(10, 20);
+	}
+
+	pef2256->version = pef2256_get_version(pef2256);
+	switch (pef2256->version) {
+	case PEF2256_VERSION_1_2:
+		version_txt = "1.2";
+		break;
+	case PEF2256_VERSION_2_1:
+		version_txt = "2.1";
+		break;
+	case PEF2256_VERSION_2_2:
+		version_txt = "2.2";
+		break;
+	default:
+		return -ENODEV;
+	}
+	dev_info(pef2256->dev, "Version %s detected\n", version_txt);
+
+	ret = pef2556_of_parse(pef2256, np);
+	if (ret)
+		return ret;
+
+	/* Create the framer. It can be used on interrupts */
+	pef2256->framer = devm_framer_create(pef2256->dev, NULL, &pef2256_framer_ops);
+	if (IS_ERR(pef2256->framer))
+		return PTR_ERR(pef2256->framer);
+
+	framer_set_drvdata(pef2256->framer, pef2256);
+
+	/* Disable interrupts */
+	pef2256_write8(pef2256, PEF2256_IMR0, 0xff);
+	pef2256_write8(pef2256, PEF2256_IMR1, 0xff);
+	pef2256_write8(pef2256, PEF2256_IMR2, 0xff);
+	pef2256_write8(pef2256, PEF2256_IMR3, 0xff);
+	pef2256_write8(pef2256, PEF2256_IMR4, 0xff);
+	pef2256_write8(pef2256, PEF2256_IMR5, 0xff);
+
+	/* Clear any pending interrupts */
+	pef2256_read8(pef2256, PEF2256_ISR0);
+	pef2256_read8(pef2256, PEF2256_ISR1);
+	pef2256_read8(pef2256, PEF2256_ISR2);
+	pef2256_read8(pef2256, PEF2256_ISR3);
+	pef2256_read8(pef2256, PEF2256_ISR4);
+	pef2256_read8(pef2256, PEF2256_ISR5);
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+	ret = devm_request_irq(pef2256->dev, irq, pef2256_irq_handler, 0, "pef2256", pef2256);
+	if (ret < 0)
+		return ret;
+
+	platform_set_drvdata(pdev, pef2256);
+
+	ret = mfd_add_devices(pef2256->dev, 0, pef2256_devs,
+			      ARRAY_SIZE(pef2256_devs), NULL, 0, NULL);
+	if (ret) {
+		dev_err(pef2256->dev, "add devices failed (%d)\n", ret);
+		return ret;
+	}
+
+	ret = pef2256_setup_e1(pef2256);
+	if (ret)
+		return ret;
+
+	framer_provider = devm_framer_provider_of_register(pef2256->dev,
+							   framer_provider_simple_of_xlate);
+	if (IS_ERR(framer_provider))
+		return PTR_ERR(framer_provider);
+
+	/* Add audio devices */
+	ret = pef2256_add_audio_devices(pef2256);
+	if (ret < 0) {
+		dev_err(pef2256->dev, "add audio devices failed (%d)\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int pef2256_remove(struct platform_device *pdev)
+{
+	struct pef2256 *pef2256 = platform_get_drvdata(pdev);
+
+	/* Disable interrupts */
+	pef2256_write8(pef2256, PEF2256_IMR0, 0xff);
+	pef2256_write8(pef2256, PEF2256_IMR1, 0xff);
+	pef2256_write8(pef2256, PEF2256_IMR2, 0xff);
+	pef2256_write8(pef2256, PEF2256_IMR3, 0xff);
+	pef2256_write8(pef2256, PEF2256_IMR4, 0xff);
+	pef2256_write8(pef2256, PEF2256_IMR5, 0xff);
+
+	return 0;
+}
+
+static const struct of_device_id pef2256_id_table[] = {
+	{ .compatible = "lantiq,pef2256" },
+	{} /* sentinel */
+};
+MODULE_DEVICE_TABLE(of, pef2256_id_table);
+
+static struct platform_driver pef2256_driver = {
+	.driver = {
+		.name = "lantiq-pef2256",
+		.of_match_table = pef2256_id_table,
+	},
+	.probe = pef2256_probe,
+	.remove = pef2256_remove,
+};
+module_platform_driver(pef2256_driver);
+
+struct regmap *pef2256_get_regmap(struct pef2256 *pef2256)
+{
+	return pef2256->regmap;
+}
+EXPORT_SYMBOL_GPL(pef2256_get_regmap);
+
+MODULE_AUTHOR("Herve Codina <herve.codina@bootlin.com>");
+MODULE_DESCRIPTION("PEF2256 driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
index fd50bb313b92..605e70f7baac 100644
--- a/drivers/net/wan/fsl_ucc_hdlc.c
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -1259,7 +1259,7 @@ free_uhdlc_priv:
 	return ret;
 }
 
-static int ucc_hdlc_remove(struct platform_device *pdev)
+static void ucc_hdlc_remove(struct platform_device *pdev)
 {
 	struct ucc_hdlc_private *priv = dev_get_drvdata(&pdev->dev);
 
@@ -1277,8 +1277,6 @@ static int ucc_hdlc_remove(struct platform_device *pdev)
 	kfree(priv);
 
 	dev_info(&pdev->dev, "UCC based hdlc module removed\n");
-
-	return 0;
 }
 
 static const struct of_device_id fsl_ucc_hdlc_of_match[] = {
@@ -1292,7 +1290,7 @@ MODULE_DEVICE_TABLE(of, fsl_ucc_hdlc_of_match);
 
 static struct platform_driver ucc_hdlc_driver = {
 	.probe	= ucc_hdlc_probe,
-	.remove	= ucc_hdlc_remove,
+	.remove_new = ucc_hdlc_remove,
 	.driver	= {
 		.name		= DRV_NAME,
 		.pm		= HDLC_PM_OPS,
diff --git a/drivers/net/wan/ixp4xx_hss.c b/drivers/net/wan/ixp4xx_hss.c
index b09f4c235142..931c5ca79ea5 100644
--- a/drivers/net/wan/ixp4xx_hss.c
+++ b/drivers/net/wan/ixp4xx_hss.c
@@ -1522,20 +1522,19 @@ err_plat:
 	return err;
 }
 
-static int ixp4xx_hss_remove(struct platform_device *pdev)
+static void ixp4xx_hss_remove(struct platform_device *pdev)
 {
 	struct port *port = platform_get_drvdata(pdev);
 
 	unregister_hdlc_device(port->netdev);
 	free_netdev(port->netdev);
 	npe_release(port->npe);
-	return 0;
 }
 
 static struct platform_driver ixp4xx_hss_driver = {
 	.driver.name	= DRV_NAME,
 	.probe		= ixp4xx_hss_probe,
-	.remove		= ixp4xx_hss_remove,
+	.remove_new	= ixp4xx_hss_remove,
 };
 module_platform_driver(ixp4xx_hss_driver);
 
diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c
index 258dcc103921..deb9636b0ecf 100644
--- a/drivers/net/wireguard/device.c
+++ b/drivers/net/wireguard/device.c
@@ -210,7 +210,7 @@ static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev)
 	 */
 	while (skb_queue_len(&peer->staged_packet_queue) > MAX_STAGED_PACKETS) {
 		dev_kfree_skb(__skb_dequeue(&peer->staged_packet_queue));
-		++dev->stats.tx_dropped;
+		DEV_STATS_INC(dev, tx_dropped);
 	}
 	skb_queue_splice_tail(&packets, &peer->staged_packet_queue);
 	spin_unlock_bh(&peer->staged_packet_queue.lock);
@@ -228,7 +228,7 @@ err_icmp:
 	else if (skb->protocol == htons(ETH_P_IPV6))
 		icmpv6_ndo_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
 err:
-	++dev->stats.tx_errors;
+	DEV_STATS_INC(dev, tx_errors);
 	kfree_skb(skb);
 	return ret;
 }
diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c
index 0b3f0c843550..a176653c8861 100644
--- a/drivers/net/wireguard/receive.c
+++ b/drivers/net/wireguard/receive.c
@@ -416,20 +416,20 @@ dishonest_packet_peer:
 	net_dbg_skb_ratelimited("%s: Packet has unallowed src IP (%pISc) from peer %llu (%pISpfsc)\n",
 				dev->name, skb, peer->internal_id,
 				&peer->endpoint.addr);
-	++dev->stats.rx_errors;
-	++dev->stats.rx_frame_errors;
+	DEV_STATS_INC(dev, rx_errors);
+	DEV_STATS_INC(dev, rx_frame_errors);
 	goto packet_processed;
 dishonest_packet_type:
 	net_dbg_ratelimited("%s: Packet is neither ipv4 nor ipv6 from peer %llu (%pISpfsc)\n",
 			    dev->name, peer->internal_id, &peer->endpoint.addr);
-	++dev->stats.rx_errors;
-	++dev->stats.rx_frame_errors;
+	DEV_STATS_INC(dev, rx_errors);
+	DEV_STATS_INC(dev, rx_frame_errors);
 	goto packet_processed;
 dishonest_packet_size:
 	net_dbg_ratelimited("%s: Packet has incorrect size from peer %llu (%pISpfsc)\n",
 			    dev->name, peer->internal_id, &peer->endpoint.addr);
-	++dev->stats.rx_errors;
-	++dev->stats.rx_length_errors;
+	DEV_STATS_INC(dev, rx_errors);
+	DEV_STATS_INC(dev, rx_length_errors);
 	goto packet_processed;
 packet_processed:
 	dev_kfree_skb(skb);
diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c
index 95c853b59e1d..0d48e0f4a1ba 100644
--- a/drivers/net/wireguard/send.c
+++ b/drivers/net/wireguard/send.c
@@ -333,7 +333,8 @@ err:
 void wg_packet_purge_staged_packets(struct wg_peer *peer)
 {
 	spin_lock_bh(&peer->staged_packet_queue.lock);
-	peer->device->dev->stats.tx_dropped += peer->staged_packet_queue.qlen;
+	DEV_STATS_ADD(peer->device->dev, tx_dropped,
+		      peer->staged_packet_queue.qlen);
 	__skb_queue_purge(&peer->staged_packet_queue);
 	spin_unlock_bh(&peer->staged_packet_queue.lock);
 }
diff --git a/drivers/net/wireless/Kconfig b/drivers/net/wireless/Kconfig
index 7555af5195ec..c6599594dc99 100644
--- a/drivers/net/wireless/Kconfig
+++ b/drivers/net/wireless/Kconfig
@@ -22,7 +22,6 @@ source "drivers/net/wireless/admtek/Kconfig"
 source "drivers/net/wireless/ath/Kconfig"
 source "drivers/net/wireless/atmel/Kconfig"
 source "drivers/net/wireless/broadcom/Kconfig"
-source "drivers/net/wireless/cisco/Kconfig"
 source "drivers/net/wireless/intel/Kconfig"
 source "drivers/net/wireless/intersil/Kconfig"
 source "drivers/net/wireless/marvell/Kconfig"
@@ -38,8 +37,6 @@ source "drivers/net/wireless/ti/Kconfig"
 source "drivers/net/wireless/zydas/Kconfig"
 source "drivers/net/wireless/quantenna/Kconfig"
 
-source "drivers/net/wireless/legacy/Kconfig"
-
 source "drivers/net/wireless/virtual/Kconfig"
 
 endif # WLAN
diff --git a/drivers/net/wireless/Makefile b/drivers/net/wireless/Makefile
index 4d7374d567d1..e1c4141c6004 100644
--- a/drivers/net/wireless/Makefile
+++ b/drivers/net/wireless/Makefile
@@ -7,7 +7,6 @@ obj-$(CONFIG_WLAN_VENDOR_ADMTEK) += admtek/
 obj-$(CONFIG_WLAN_VENDOR_ATH) += ath/
 obj-$(CONFIG_WLAN_VENDOR_ATMEL) += atmel/
 obj-$(CONFIG_WLAN_VENDOR_BROADCOM) += broadcom/
-obj-$(CONFIG_WLAN_VENDOR_CISCO) += cisco/
 obj-$(CONFIG_WLAN_VENDOR_INTEL) += intel/
 obj-$(CONFIG_WLAN_VENDOR_INTERSIL) += intersil/
 obj-$(CONFIG_WLAN_VENDOR_MARVELL) += marvell/
@@ -23,5 +22,4 @@ obj-$(CONFIG_WLAN_VENDOR_ST) += st/
 obj-$(CONFIG_WLAN_VENDOR_TI) += ti/
 obj-$(CONFIG_WLAN_VENDOR_ZYDAS) += zydas/
 
-obj-$(CONFIG_WLAN) += legacy/
 obj-$(CONFIG_WLAN) += virtual/
diff --git a/drivers/net/wireless/ath/ath10k/bmi.c b/drivers/net/wireless/ath/ath10k/bmi.c
index af6546572df2..9a4f8e815412 100644
--- a/drivers/net/wireless/ath/ath10k/bmi.c
+++ b/drivers/net/wireless/ath/ath10k/bmi.c
@@ -2,6 +2,7 @@
 /*
  * Copyright (c) 2005-2011 Atheros Communications Inc.
  * Copyright (c) 2011-2014,2016-2017 Qualcomm Atheros, Inc.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "bmi.h"
diff --git a/drivers/net/wireless/ath/ath10k/ce.c b/drivers/net/wireless/ath/ath10k/ce.c
index c27b8204718a..afae4a8027f8 100644
--- a/drivers/net/wireless/ath/ath10k/ce.c
+++ b/drivers/net/wireless/ath/ath10k/ce.c
@@ -3,6 +3,7 @@
  * Copyright (c) 2005-2011 Atheros Communications Inc.
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
  * Copyright (c) 2018 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "hif.h"
diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index 6cdb225b7eac..0032f8aa892f 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -3,6 +3,7 @@
  * Copyright (c) 2005-2011 Atheros Communications Inc.
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
  * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/module.h>
@@ -100,6 +101,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_restart_disconnect = false,
 		.use_fw_tx_credits = true,
 		.delay_unmap_buffer = false,
+		.mcast_frame_registration = false,
 	},
 	{
 		.id = QCA988X_HW_2_0_VERSION,
@@ -140,6 +142,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_restart_disconnect = false,
 		.use_fw_tx_credits = true,
 		.delay_unmap_buffer = false,
+		.mcast_frame_registration = false,
 	},
 	{
 		.id = QCA9887_HW_1_0_VERSION,
@@ -181,6 +184,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_restart_disconnect = false,
 		.use_fw_tx_credits = true,
 		.delay_unmap_buffer = false,
+		.mcast_frame_registration = false,
 	},
 	{
 		.id = QCA6174_HW_3_2_VERSION,
@@ -217,6 +221,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_restart_disconnect = false,
 		.use_fw_tx_credits = true,
 		.delay_unmap_buffer = false,
+		.mcast_frame_registration = false,
 	},
 	{
 		.id = QCA6174_HW_2_1_VERSION,
@@ -257,6 +262,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_restart_disconnect = false,
 		.use_fw_tx_credits = true,
 		.delay_unmap_buffer = false,
+		.mcast_frame_registration = false,
 	},
 	{
 		.id = QCA6174_HW_2_1_VERSION,
@@ -297,6 +303,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_restart_disconnect = false,
 		.use_fw_tx_credits = true,
 		.delay_unmap_buffer = false,
+		.mcast_frame_registration = false,
 	},
 	{
 		.id = QCA6174_HW_3_0_VERSION,
@@ -337,6 +344,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_restart_disconnect = false,
 		.use_fw_tx_credits = true,
 		.delay_unmap_buffer = false,
+		.mcast_frame_registration = false,
 	},
 	{
 		.id = QCA6174_HW_3_2_VERSION,
@@ -381,6 +389,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_restart_disconnect = false,
 		.use_fw_tx_credits = true,
 		.delay_unmap_buffer = false,
+		.mcast_frame_registration = true,
 	},
 	{
 		.id = QCA99X0_HW_2_0_DEV_VERSION,
@@ -427,6 +436,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_restart_disconnect = false,
 		.use_fw_tx_credits = true,
 		.delay_unmap_buffer = false,
+		.mcast_frame_registration = false,
 	},
 	{
 		.id = QCA9984_HW_1_0_DEV_VERSION,
@@ -480,6 +490,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_restart_disconnect = false,
 		.use_fw_tx_credits = true,
 		.delay_unmap_buffer = false,
+		.mcast_frame_registration = false,
 	},
 	{
 		.id = QCA9888_HW_2_0_DEV_VERSION,
@@ -530,6 +541,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_restart_disconnect = false,
 		.use_fw_tx_credits = true,
 		.delay_unmap_buffer = false,
+		.mcast_frame_registration = false,
 	},
 	{
 		.id = QCA9377_HW_1_0_DEV_VERSION,
@@ -570,6 +582,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_restart_disconnect = false,
 		.use_fw_tx_credits = true,
 		.delay_unmap_buffer = false,
+		.mcast_frame_registration = false,
 	},
 	{
 		.id = QCA9377_HW_1_1_DEV_VERSION,
@@ -612,6 +625,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_restart_disconnect = false,
 		.use_fw_tx_credits = true,
 		.delay_unmap_buffer = false,
+		.mcast_frame_registration = false,
 	},
 	{
 		.id = QCA9377_HW_1_1_DEV_VERSION,
@@ -645,6 +659,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_restart_disconnect = false,
 		.use_fw_tx_credits = true,
 		.delay_unmap_buffer = false,
+		.mcast_frame_registration = false,
 	},
 	{
 		.id = QCA4019_HW_1_0_DEV_VERSION,
@@ -692,6 +707,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_restart_disconnect = false,
 		.use_fw_tx_credits = true,
 		.delay_unmap_buffer = false,
+		.mcast_frame_registration = false,
 	},
 	{
 		.id = WCN3990_HW_1_0_DEV_VERSION,
@@ -725,6 +741,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_restart_disconnect = true,
 		.use_fw_tx_credits = false,
 		.delay_unmap_buffer = true,
+		.mcast_frame_registration = false,
 	},
 };
 
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index 4b5239de4018..c110d15528bd 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -3,6 +3,7 @@
  * Copyright (c) 2005-2011 Atheros Communications Inc.
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
  * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef _CORE_H_
@@ -607,7 +608,7 @@ struct ath10k_vif {
 			u8 tim_bitmap[64];
 			u8 tim_len;
 			u32 ssid_len;
-			u8 ssid[IEEE80211_MAX_SSID_LEN];
+			u8 ssid[IEEE80211_MAX_SSID_LEN] __nonstring;
 			bool hidden_ssid;
 			/* P2P_IE with NoA attribute for P2P_GO case */
 			u32 noa_len;
diff --git a/drivers/net/wireless/ath/ath10k/coredump.c b/drivers/net/wireless/ath/ath10k/coredump.c
index 2d1634a890dd..bb3a276b7ed5 100644
--- a/drivers/net/wireless/ath/ath10k/coredump.c
+++ b/drivers/net/wireless/ath/ath10k/coredump.c
@@ -2,6 +2,7 @@
 /*
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
  * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "coredump.h"
diff --git a/drivers/net/wireless/ath/ath10k/coredump.h b/drivers/net/wireless/ath/ath10k/coredump.h
index 437b9759f05d..e5ef0352e319 100644
--- a/drivers/net/wireless/ath/ath10k/coredump.h
+++ b/drivers/net/wireless/ath/ath10k/coredump.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: ISC */
 /*
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef _COREDUMP_H_
diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c
index ad9cf953a2fc..b93a64bf8190 100644
--- a/drivers/net/wireless/ath/ath10k/debug.c
+++ b/drivers/net/wireless/ath/ath10k/debug.c
@@ -3,6 +3,7 @@
  * Copyright (c) 2005-2011 Atheros Communications Inc.
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
  * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/module.h>
diff --git a/drivers/net/wireless/ath/ath10k/debugfs_sta.c b/drivers/net/wireless/ath/ath10k/debugfs_sta.c
index 87a3365330ff..394bf3c32abf 100644
--- a/drivers/net/wireless/ath/ath10k/debugfs_sta.c
+++ b/drivers/net/wireless/ath/ath10k/debugfs_sta.c
@@ -2,6 +2,7 @@
 /*
  * Copyright (c) 2014-2017 Qualcomm Atheros, Inc.
  * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "core.h"
diff --git a/drivers/net/wireless/ath/ath10k/htc.c b/drivers/net/wireless/ath/ath10k/htc.c
index 5bfeecb95fca..a6e21ce90bad 100644
--- a/drivers/net/wireless/ath/ath10k/htc.c
+++ b/drivers/net/wireless/ath/ath10k/htc.c
@@ -2,6 +2,7 @@
 /*
  * Copyright (c) 2005-2011 Atheros Communications Inc.
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "core.h"
diff --git a/drivers/net/wireless/ath/ath10k/htc.h b/drivers/net/wireless/ath/ath10k/htc.h
index 0d180faf3b77..7ff665020015 100644
--- a/drivers/net/wireless/ath/ath10k/htc.h
+++ b/drivers/net/wireless/ath/ath10k/htc.h
@@ -246,26 +246,12 @@ struct ath10k_htc_lookahead_bundle {
 struct ath10k_htc_record {
 	struct ath10k_ath10k_htc_record_hdr hdr;
 	union {
-		struct ath10k_htc_credit_report credit_report[0];
-		struct ath10k_htc_lookahead_report lookahead_report[0];
-		struct ath10k_htc_lookahead_bundle lookahead_bundle[0];
-		u8 pauload[0];
+		DECLARE_FLEX_ARRAY(struct ath10k_htc_credit_report, credit_report);
+		DECLARE_FLEX_ARRAY(struct ath10k_htc_lookahead_report, lookahead_report);
+		DECLARE_FLEX_ARRAY(struct ath10k_htc_lookahead_bundle, lookahead_bundle);
 	};
 } __packed __aligned(4);
 
-/*
- * note: the trailer offset is dynamic depending
- * on payload length. this is only a struct layout draft
- */
-struct ath10k_htc_frame {
-	struct ath10k_htc_hdr hdr;
-	union {
-		struct ath10k_htc_msg msg;
-		u8 payload[0];
-	};
-	struct ath10k_htc_record trailer[0];
-} __packed __aligned(4);
-
 /*******************/
 /* Host-side stuff */
 /*******************/
diff --git a/drivers/net/wireless/ath/ath10k/htt.h b/drivers/net/wireless/ath/ath10k/htt.h
index c80470e8886a..4a9270e2a4c8 100644
--- a/drivers/net/wireless/ath/ath10k/htt.h
+++ b/drivers/net/wireless/ath/ath10k/htt.h
@@ -3,6 +3,7 @@
  * Copyright (c) 2005-2011 Atheros Communications Inc.
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
  * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021, 2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef _HTT_H_
diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index b261d6371c0f..7d28ae5453cf 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -3,6 +3,7 @@
  * Copyright (c) 2005-2011 Atheros Communications Inc.
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
  * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "core.h"
@@ -1294,7 +1295,7 @@ static void ath10k_htt_rx_h_ppdu(struct ath10k *ar,
 		status->encoding = RX_ENC_LEGACY;
 		status->bw = RATE_INFO_BW_20;
 
-		status->flag &= ~RX_FLAG_MACTIME_END;
+		status->flag &= ~RX_FLAG_MACTIME;
 		status->flag |= RX_FLAG_NO_SIGNAL_VAL;
 
 		status->flag &= ~(RX_FLAG_AMPDU_IS_LAST);
diff --git a/drivers/net/wireless/ath/ath10k/htt_tx.c b/drivers/net/wireless/ath/ath10k/htt_tx.c
index be4d4536aaa8..9725feecefd6 100644
--- a/drivers/net/wireless/ath/ath10k/htt_tx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_tx.c
@@ -2,6 +2,7 @@
 /*
  * Copyright (c) 2005-2011 Atheros Communications Inc.
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/etherdevice.h>
@@ -40,7 +41,6 @@ static void __ath10k_htt_tx_txq_recalc(struct ieee80211_hw *hw,
 	struct ath10k *ar = hw->priv;
 	struct ath10k_sta *arsta;
 	struct ath10k_vif *arvif = (void *)txq->vif->drv_priv;
-	unsigned long frame_cnt;
 	unsigned long byte_cnt;
 	int idx;
 	u32 bit;
@@ -67,7 +67,7 @@ static void __ath10k_htt_tx_txq_recalc(struct ieee80211_hw *hw,
 	bit = BIT(peer_id % 32);
 	idx = peer_id / 32;
 
-	ieee80211_txq_get_depth(txq, &frame_cnt, &byte_cnt);
+	ieee80211_txq_get_depth(txq, NULL, &byte_cnt);
 	count = ath10k_htt_tx_txq_calc_size(byte_cnt);
 
 	if (unlikely(peer_id >= ar->htt.tx_q_state.num_peers) ||
diff --git a/drivers/net/wireless/ath/ath10k/hw.c b/drivers/net/wireless/ath/ath10k/hw.c
index 6d32b43a4da6..8fafe096adff 100644
--- a/drivers/net/wireless/ath/ath10k/hw.c
+++ b/drivers/net/wireless/ath/ath10k/hw.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: ISC
 /*
  * Copyright (c) 2014-2017 Qualcomm Atheros, Inc.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/wireless/ath/ath10k/hw.h b/drivers/net/wireless/ath/ath10k/hw.h
index 9643031a4427..93c073091996 100644
--- a/drivers/net/wireless/ath/ath10k/hw.h
+++ b/drivers/net/wireless/ath/ath10k/hw.h
@@ -3,6 +3,7 @@
  * Copyright (c) 2005-2011 Atheros Communications Inc.
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
  * Copyright (c) 2018 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef _HW_H_
@@ -639,6 +640,9 @@ struct ath10k_hw_params {
 	bool use_fw_tx_credits;
 
 	bool delay_unmap_buffer;
+
+	/* The hardware support multicast frame registrations */
+	bool mcast_frame_registration;
 };
 
 struct htt_resp;
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 2cf693f3fea9..090bcf148d0c 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -3,6 +3,7 @@
  * Copyright (c) 2005-2011 Atheros Communications Inc.
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
  * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "mac.h"
@@ -1242,7 +1243,7 @@ static bool ath10k_mac_monitor_vdev_is_needed(struct ath10k *ar)
 	return ar->monitor ||
 	       (!test_bit(ATH10K_FW_FEATURE_ALLOWS_MESH_BCAST,
 			  ar->running_fw->fw_file.fw_features) &&
-		(ar->filter_flags & FIF_OTHER_BSS)) ||
+		(ar->filter_flags & (FIF_OTHER_BSS | FIF_MCAST_ACTION))) ||
 	       test_bit(ATH10K_CAC_RUNNING, &ar->dev_flags);
 }
 
@@ -6025,10 +6026,15 @@ static void ath10k_configure_filter(struct ieee80211_hw *hw,
 {
 	struct ath10k *ar = hw->priv;
 	int ret;
+	unsigned int supported = SUPPORTED_FILTERS;
 
 	mutex_lock(&ar->conf_mutex);
 
-	*total_flags &= SUPPORTED_FILTERS;
+	if (ar->hw_params.mcast_frame_registration)
+		supported |= FIF_MCAST_ACTION;
+
+	*total_flags &= supported;
+
 	ar->filter_flags = *total_flags;
 
 	ret = ath10k_monitor_recalc(ar);
@@ -6121,9 +6127,8 @@ static void ath10k_bss_info_changed(struct ieee80211_hw *hw,
 
 		if (ieee80211_vif_is_mesh(vif)) {
 			/* mesh doesn't use SSID but firmware needs it */
-			strncpy(arvif->u.ap.ssid, "mesh",
-				sizeof(arvif->u.ap.ssid));
 			arvif->u.ap.ssid_len = 4;
+			memcpy(arvif->u.ap.ssid, "mesh", arvif->u.ap.ssid_len);
 		}
 	}
 
@@ -10118,6 +10123,10 @@ int ath10k_mac_register(struct ath10k *ar)
 			      NL80211_EXT_FEATURE_SET_SCAN_DWELL);
 	wiphy_ext_feature_set(ar->hw->wiphy, NL80211_EXT_FEATURE_AQL);
 
+	if (ar->hw_params.mcast_frame_registration)
+		wiphy_ext_feature_set(ar->hw->wiphy,
+				      NL80211_EXT_FEATURE_MULTICAST_REGISTRATIONS);
+
 	if (test_bit(WMI_SERVICE_TX_DATA_ACK_RSSI, ar->wmi.svc_map) ||
 	    test_bit(WMI_SERVICE_HTT_MGMT_TX_COMP_VALID_FLAGS, ar->wmi.svc_map))
 		wiphy_ext_feature_set(ar->hw->wiphy,
diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c
index 2f8c785277af..3de2de6d44bc 100644
--- a/drivers/net/wireless/ath/ath10k/pci.c
+++ b/drivers/net/wireless/ath/ath10k/pci.c
@@ -2,6 +2,7 @@
 /*
  * Copyright (c) 2005-2011 Atheros Communications Inc.
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
+ * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/pci.h>
diff --git a/drivers/net/wireless/ath/ath10k/pci.h b/drivers/net/wireless/ath/ath10k/pci.h
index 480cd97ab739..27bb4cf2dfea 100644
--- a/drivers/net/wireless/ath/ath10k/pci.h
+++ b/drivers/net/wireless/ath/ath10k/pci.h
@@ -2,6 +2,7 @@
 /*
  * Copyright (c) 2005-2011 Atheros Communications Inc.
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef _PCI_H_
diff --git a/drivers/net/wireless/ath/ath10k/qmi.c b/drivers/net/wireless/ath/ath10k/qmi.c
index 52c1a3de8da6..38e939f572a9 100644
--- a/drivers/net/wireless/ath/ath10k/qmi.c
+++ b/drivers/net/wireless/ath/ath10k/qmi.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: ISC
 /*
  * Copyright (c) 2018 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/completion.h>
diff --git a/drivers/net/wireless/ath/ath10k/qmi_wlfw_v01.c b/drivers/net/wireless/ath/ath10k/qmi_wlfw_v01.c
index 1c81e454f943..0e85c75d2278 100644
--- a/drivers/net/wireless/ath/ath10k/qmi_wlfw_v01.c
+++ b/drivers/net/wireless/ath/ath10k/qmi_wlfw_v01.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: ISC
 /*
  * Copyright (c) 2018 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/soc/qcom/qmi.h>
diff --git a/drivers/net/wireless/ath/ath10k/qmi_wlfw_v01.h b/drivers/net/wireless/ath/ath10k/qmi_wlfw_v01.h
index f0db991408dc..9f311f3bc9e7 100644
--- a/drivers/net/wireless/ath/ath10k/qmi_wlfw_v01.h
+++ b/drivers/net/wireless/ath/ath10k/qmi_wlfw_v01.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: ISC */
 /*
  * Copyright (c) 2018 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef WCN3990_QMI_SVC_V01_H
diff --git a/drivers/net/wireless/ath/ath10k/rx_desc.h b/drivers/net/wireless/ath/ath10k/rx_desc.h
index 777e53aa69dc..564293df1e9a 100644
--- a/drivers/net/wireless/ath/ath10k/rx_desc.h
+++ b/drivers/net/wireless/ath/ath10k/rx_desc.h
@@ -2,6 +2,7 @@
 /*
  * Copyright (c) 2005-2011 Atheros Communications Inc.
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef _RX_DESC_H_
diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c
index 56fbcfb80bf8..0ab5433f6cf6 100644
--- a/drivers/net/wireless/ath/ath10k/sdio.c
+++ b/drivers/net/wireless/ath/ath10k/sdio.c
@@ -3,6 +3,7 @@
  * Copyright (c) 2004-2011 Atheros Communications Inc.
  * Copyright (c) 2011-2012,2017 Qualcomm Atheros, Inc.
  * Copyright (c) 2016-2017 Erik Stromdahl <erik.stromdahl@gmail.com>
+ * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/module.h>
diff --git a/drivers/net/wireless/ath/ath10k/thermal.c b/drivers/net/wireless/ath/ath10k/thermal.c
index cefd97323dfe..31c8d7fbb095 100644
--- a/drivers/net/wireless/ath/ath10k/thermal.c
+++ b/drivers/net/wireless/ath/ath10k/thermal.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: ISC
 /*
  * Copyright (c) 2014-2015 Qualcomm Atheros, Inc.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/device.h>
diff --git a/drivers/net/wireless/ath/ath10k/usb.h b/drivers/net/wireless/ath/ath10k/usb.h
index 48e066ba8162..7e4cfbb673c9 100644
--- a/drivers/net/wireless/ath/ath10k/usb.h
+++ b/drivers/net/wireless/ath/ath10k/usb.h
@@ -3,6 +3,7 @@
  * Copyright (c) 2004-2011 Atheros Communications Inc.
  * Copyright (c) 2011-2012 Qualcomm Atheros, Inc.
  * Copyright (c) 2016-2017 Erik Stromdahl <erik.stromdahl@gmail.com>
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef _USB_H_
diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.h b/drivers/net/wireless/ath/ath10k/wmi-tlv.h
index dbb48d70f2e9..83a8f07a687f 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-tlv.h
+++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.h
@@ -3,6 +3,7 @@
  * Copyright (c) 2005-2011 Atheros Communications Inc.
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
  * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #ifndef _WMI_TLV_H
 #define _WMI_TLV_H
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index 05fa7d4c0e1a..88befe92f95d 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -3,6 +3,7 @@
  * Copyright (c) 2005-2011 Atheros Communications Inc.
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
  * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/skbuff.h>
diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h
index b112e8826093..9146df98fcee 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.h
+++ b/drivers/net/wireless/ath/ath10k/wmi.h
@@ -3,6 +3,7 @@
  * Copyright (c) 2005-2011 Atheros Communications Inc.
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
  * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef _WMI_H_
diff --git a/drivers/net/wireless/ath/ath10k/wow.c b/drivers/net/wireless/ath/ath10k/wow.c
index 20b9aa8ddf7d..aa7b2e703f3d 100644
--- a/drivers/net/wireless/ath/ath10k/wow.c
+++ b/drivers/net/wireless/ath/ath10k/wow.c
@@ -2,6 +2,7 @@
 /*
  * Copyright (c) 2015-2017 Qualcomm Atheros, Inc.
  * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "mac.h"
diff --git a/drivers/net/wireless/ath/ath11k/Kconfig b/drivers/net/wireless/ath/ath11k/Kconfig
index ad5cc6cac05b..27f0523bf967 100644
--- a/drivers/net/wireless/ath/ath11k/Kconfig
+++ b/drivers/net/wireless/ath/ath11k/Kconfig
@@ -2,7 +2,7 @@
 config ATH11K
 	tristate "Qualcomm Technologies 802.11ax chipset support"
 	depends on MAC80211 && HAS_DMA
-	depends on CRYPTO_MICHAEL_MIC
+	select CRYPTO_MICHAEL_MIC
 	select ATH_COMMON
 	select QCOM_QMI_HELPERS
 	help
diff --git a/drivers/net/wireless/ath/ath11k/ahb.c b/drivers/net/wireless/ath/ath11k/ahb.c
index 235336ef2a7a..7c0a23517949 100644
--- a/drivers/net/wireless/ath/ath11k/ahb.c
+++ b/drivers/net/wireless/ath/ath11k/ahb.c
@@ -803,8 +803,8 @@ static int ath11k_core_get_rproc(struct ath11k_base *ab)
 
 	prproc = rproc_get_by_phandle(rproc_phandle);
 	if (!prproc) {
-		ath11k_err(ab, "failed to get rproc\n");
-		return -EINVAL;
+		ath11k_dbg(ab, ATH11K_DBG_AHB, "failed to get rproc, deferring\n");
+		return -EPROBE_DEFER;
 	}
 	ab_ahb->tgt_rproc = prproc;
 
@@ -1251,7 +1251,7 @@ static void ath11k_ahb_free_resources(struct ath11k_base *ab)
 	platform_set_drvdata(pdev, NULL);
 }
 
-static int ath11k_ahb_remove(struct platform_device *pdev)
+static void ath11k_ahb_remove(struct platform_device *pdev)
 {
 	struct ath11k_base *ab = platform_get_drvdata(pdev);
 
@@ -1267,8 +1267,6 @@ static int ath11k_ahb_remove(struct platform_device *pdev)
 
 qmi_fail:
 	ath11k_ahb_free_resources(ab);
-
-	return 0;
 }
 
 static void ath11k_ahb_shutdown(struct platform_device *pdev)
@@ -1296,7 +1294,7 @@ static struct platform_driver ath11k_ahb_driver = {
 		.of_match_table = ath11k_ahb_of_match,
 	},
 	.probe  = ath11k_ahb_probe,
-	.remove = ath11k_ahb_remove,
+	.remove_new = ath11k_ahb_remove,
 	.shutdown = ath11k_ahb_shutdown,
 };
 
diff --git a/drivers/net/wireless/ath/ath11k/ce.c b/drivers/net/wireless/ath/ath11k/ce.c
index 289d47ae92af..e66e86bdec20 100644
--- a/drivers/net/wireless/ath/ath11k/ce.c
+++ b/drivers/net/wireless/ath/ath11k/ce.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021, Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "dp_rx.h"
diff --git a/drivers/net/wireless/ath/ath11k/ce.h b/drivers/net/wireless/ath/ath11k/ce.h
index c0f6a0ba86df..69946fc70077 100644
--- a/drivers/net/wireless/ath/ath11k/ce.h
+++ b/drivers/net/wireless/ath/ath11k/ce.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_CE_H
diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index f12b606e2d2e..7e3b6779f4e9 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -599,7 +599,6 @@ struct ath11k {
 	struct ath11k_base *ab;
 	struct ath11k_pdev *pdev;
 	struct ieee80211_hw *hw;
-	struct ieee80211_ops *ops;
 	struct ath11k_pdev_wmi *wmi;
 	struct ath11k_pdev_dp dp;
 	u8 mac_addr[ETH_ALEN];
diff --git a/drivers/net/wireless/ath/ath11k/dbring.c b/drivers/net/wireless/ath/ath11k/dbring.c
index 5536e8642331..fbb6e8d8a476 100644
--- a/drivers/net/wireless/ath/ath11k/dbring.c
+++ b/drivers/net/wireless/ath/ath11k/dbring.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2019-2020 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "core.h"
diff --git a/drivers/net/wireless/ath/ath11k/dbring.h b/drivers/net/wireless/ath/ath11k/dbring.h
index ef906c687b8c..2f93b78a50df 100644
--- a/drivers/net/wireless/ath/ath11k/dbring.h
+++ b/drivers/net/wireless/ath/ath11k/dbring.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2019-2020 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_DBRING_H
diff --git a/drivers/net/wireless/ath/ath11k/debug.c b/drivers/net/wireless/ath/ath11k/debug.c
index f5c8a34c8802..2b8544355fc1 100644
--- a/drivers/net/wireless/ath/ath11k/debug.c
+++ b/drivers/net/wireless/ath/ath11k/debug.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/vmalloc.h>
diff --git a/drivers/net/wireless/ath/ath11k/debug.h b/drivers/net/wireless/ath/ath11k/debug.h
index 9c52804ef8ac..cc8934d15697 100644
--- a/drivers/net/wireless/ath/ath11k/debug.h
+++ b/drivers/net/wireless/ath/ath11k/debug.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef _ATH11K_DEBUG_H_
diff --git a/drivers/net/wireless/ath/ath11k/debugfs.c b/drivers/net/wireless/ath/ath11k/debugfs.c
index be76e7d1c436..a847bc0d50c0 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs.c
+++ b/drivers/net/wireless/ath/ath11k/debugfs.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2020 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/vmalloc.h>
diff --git a/drivers/net/wireless/ath/ath11k/debugfs.h b/drivers/net/wireless/ath/ath11k/debugfs.h
index 3af0169f6cf2..44d15845f39a 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs.h
+++ b/drivers/net/wireless/ath/ath11k/debugfs.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef _ATH11K_DEBUGFS_H_
diff --git a/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.c b/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.c
index 0207fc4910f3..870e86a31bf8 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.c
+++ b/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/vmalloc.h>
diff --git a/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.h b/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.h
index 96219301f05b..476689bbd4da 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.h
+++ b/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef DEBUG_HTT_STATS_H
diff --git a/drivers/net/wireless/ath/ath11k/debugfs_sta.c b/drivers/net/wireless/ath/ath11k/debugfs_sta.c
index 8c177fba6f14..f56a24b6c8da 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs_sta.c
+++ b/drivers/net/wireless/ath/ath11k/debugfs_sta.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/vmalloc.h>
diff --git a/drivers/net/wireless/ath/ath11k/debugfs_sta.h b/drivers/net/wireless/ath/ath11k/debugfs_sta.h
index e6c11b3a40aa..ace877e19275 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs_sta.h
+++ b/drivers/net/wireless/ath/ath11k/debugfs_sta.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2020 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef _ATH11K_DEBUGFS_STA_H_
diff --git a/drivers/net/wireless/ath/ath11k/dp.c b/drivers/net/wireless/ath/ath11k/dp.c
index a7252b52555c..8975dc57ad77 100644
--- a/drivers/net/wireless/ath/ath11k/dp.c
+++ b/drivers/net/wireless/ath/ath11k/dp.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <crypto/hash.h>
diff --git a/drivers/net/wireless/ath/ath11k/dp.h b/drivers/net/wireless/ath/ath11k/dp.h
index 15815af453b2..2f6dd69d3be2 100644
--- a/drivers/net/wireless/ath/ath11k/dp.h
+++ b/drivers/net/wireless/ath/ath11k/dp.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_DP_H
diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c
index 7eac93ce7a1d..afd481f5858f 100644
--- a/drivers/net/wireless/ath/ath11k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_rx.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/ieee80211.h>
diff --git a/drivers/net/wireless/ath/ath11k/dp_tx.c b/drivers/net/wireless/ath/ath11k/dp_tx.c
index a5fa08bc623b..c1072e66e3e8 100644
--- a/drivers/net/wireless/ath/ath11k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_tx.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "core.h"
diff --git a/drivers/net/wireless/ath/ath11k/dp_tx.h b/drivers/net/wireless/ath/ath11k/dp_tx.h
index 68a21ea9b934..61be2265e09f 100644
--- a/drivers/net/wireless/ath/ath11k/dp_tx.h
+++ b/drivers/net/wireless/ath/ath11k/dp_tx.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021, 2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_DP_TX_H
diff --git a/drivers/net/wireless/ath/ath11k/fw.c b/drivers/net/wireless/ath/ath11k/fw.c
index 8f84fba29886..4e36292a79db 100644
--- a/drivers/net/wireless/ath/ath11k/fw.c
+++ b/drivers/net/wireless/ath/ath11k/fw.c
@@ -133,7 +133,7 @@ static int ath11k_fw_request_firmware_api_n(struct ath11k_base *ab,
 
 		len -= ie_len;
 		data += ie_len;
-	};
+	}
 
 	return 0;
 
diff --git a/drivers/net/wireless/ath/ath11k/hal.c b/drivers/net/wireless/ath/ath11k/hal.c
index 23f3af8e372d..c060c4b5c0cc 100644
--- a/drivers/net/wireless/ath/ath11k/hal.c
+++ b/drivers/net/wireless/ath/ath11k/hal.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #include <linux/dma-mapping.h>
 #include "hal_tx.h"
diff --git a/drivers/net/wireless/ath/ath11k/hal.h b/drivers/net/wireless/ath/ath11k/hal.h
index 1942d41d6de5..80447f488954 100644
--- a/drivers/net/wireless/ath/ath11k/hal.h
+++ b/drivers/net/wireless/ath/ath11k/hal.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_HAL_H
diff --git a/drivers/net/wireless/ath/ath11k/hal_desc.h b/drivers/net/wireless/ath/ath11k/hal_desc.h
index d895ea878d9f..b2fd180bd28e 100644
--- a/drivers/net/wireless/ath/ath11k/hal_desc.h
+++ b/drivers/net/wireless/ath/ath11k/hal_desc.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #include "core.h"
 
diff --git a/drivers/net/wireless/ath/ath11k/hal_rx.c b/drivers/net/wireless/ath/ath11k/hal_rx.c
index 41946795d620..e758ee8e17c9 100644
--- a/drivers/net/wireless/ath/ath11k/hal_rx.c
+++ b/drivers/net/wireless/ath/ath11k/hal_rx.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "debug.h"
diff --git a/drivers/net/wireless/ath/ath11k/hal_rx.h b/drivers/net/wireless/ath/ath11k/hal_rx.h
index 472a52cf5889..0fa9aef9d533 100644
--- a/drivers/net/wireless/ath/ath11k/hal_rx.h
+++ b/drivers/net/wireless/ath/ath11k/hal_rx.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_HAL_RX_H
diff --git a/drivers/net/wireless/ath/ath11k/hif.h b/drivers/net/wireless/ath/ath11k/hif.h
index d68ed4214dec..877a4073fed6 100644
--- a/drivers/net/wireless/ath/ath11k/hif.h
+++ b/drivers/net/wireless/ath/ath11k/hif.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2019-2020 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef _HIF_H_
diff --git a/drivers/net/wireless/ath/ath11k/htc.c b/drivers/net/wireless/ath/ath11k/htc.c
index 2c2e425c8665..23054ab29a5e 100644
--- a/drivers/net/wireless/ath/ath11k/htc.c
+++ b/drivers/net/wireless/ath/ath11k/htc.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #include <linux/skbuff.h>
 #include <linux/ctype.h>
diff --git a/drivers/net/wireless/ath/ath11k/htc.h b/drivers/net/wireless/ath/ath11k/htc.h
index d31e501c807c..86f77eacaea7 100644
--- a/drivers/net/wireless/ath/ath11k/htc.h
+++ b/drivers/net/wireless/ath/ath11k/htc.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_HTC_H
@@ -150,10 +151,7 @@ struct ath11k_htc_credit_report {
 
 struct ath11k_htc_record {
 	struct ath11k_htc_record_hdr hdr;
-	union {
-		struct ath11k_htc_credit_report credit_report[0];
-		u8 pauload[0];
-	};
+	struct ath11k_htc_credit_report credit_report[];
 } __packed __aligned(4);
 
 enum ath11k_htc_svc_gid {
diff --git a/drivers/net/wireless/ath/ath11k/hw.c b/drivers/net/wireless/ath/ath11k/hw.c
index d7b5ec6e6904..77d8f9237680 100644
--- a/drivers/net/wireless/ath/ath11k/hw.c
+++ b/drivers/net/wireless/ath/ath11k/hw.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2020 The Linux Foundation. All rights reserved.
- * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/wireless/ath/ath11k/hw.h b/drivers/net/wireless/ath/ath11k/hw.h
index d51a99669dd6..1b070747a5db 100644
--- a/drivers/net/wireless/ath/ath11k/hw.h
+++ b/drivers/net/wireless/ath/ath11k/hw.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022, Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_HW_H
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 7f7b39817773..db241589424d 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -4654,6 +4654,14 @@ static int ath11k_station_disassoc(struct ath11k *ar,
 	return 0;
 }
 
+static u32 ath11k_mac_max_nss(const u8 *ht_mcs_mask, const u16 *vht_mcs_mask,
+			      const u16 *he_mcs_mask)
+{
+	return max3(ath11k_mac_max_ht_nss(ht_mcs_mask),
+		    ath11k_mac_max_vht_nss(vht_mcs_mask),
+		    ath11k_mac_max_he_nss(he_mcs_mask));
+}
+
 static void ath11k_sta_rc_update_wk(struct work_struct *wk)
 {
 	struct ath11k *ar;
@@ -4699,9 +4707,7 @@ static void ath11k_sta_rc_update_wk(struct work_struct *wk)
 	mutex_lock(&ar->conf_mutex);
 
 	nss = max_t(u32, 1, nss);
-	nss = min(nss, max(max(ath11k_mac_max_ht_nss(ht_mcs_mask),
-			       ath11k_mac_max_vht_nss(vht_mcs_mask)),
-			   ath11k_mac_max_he_nss(he_mcs_mask)));
+	nss = min(nss, ath11k_mac_max_nss(ht_mcs_mask, vht_mcs_mask, he_mcs_mask));
 
 	if (changed & IEEE80211_RC_BW_CHANGED) {
 		/* Get the peer phymode */
@@ -8391,9 +8397,7 @@ ath11k_mac_op_set_bitrate_mask(struct ieee80211_hw *hw,
 			ath11k_warn(ar->ab,
 				    "could not update fixed rate settings to all peers due to mcs/nss incompatibility\n");
 		nss = min_t(u32, ar->num_tx_chains,
-			    max(max(ath11k_mac_max_ht_nss(ht_mcs_mask),
-				    ath11k_mac_max_vht_nss(vht_mcs_mask)),
-				ath11k_mac_max_he_nss(he_mcs_mask)));
+			    ath11k_mac_max_nss(ht_mcs_mask, vht_mcs_mask, he_mcs_mask));
 
 		/* If multiple rates across different preambles are given
 		 * we can reconfigure this info with all peers using PEER_ASSOC
diff --git a/drivers/net/wireless/ath/ath11k/mac.h b/drivers/net/wireless/ath/ath11k/mac.h
index 0231783ad754..0dfdeed5177b 100644
--- a/drivers/net/wireless/ath/ath11k/mac.h
+++ b/drivers/net/wireless/ath/ath11k/mac.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_MAC_H
diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c
index afeabd6ecc67..6835c14b82cc 100644
--- a/drivers/net/wireless/ath/ath11k/mhi.c
+++ b/drivers/net/wireless/ath/ath11k/mhi.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2020 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022, Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/msi.h>
diff --git a/drivers/net/wireless/ath/ath11k/mhi.h b/drivers/net/wireless/ath/ath11k/mhi.h
index 8d9f852da695..f81fba2644a4 100644
--- a/drivers/net/wireless/ath/ath11k/mhi.h
+++ b/drivers/net/wireless/ath/ath11k/mhi.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2020 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #ifndef _ATH11K_MHI_H
 #define _ATH11K_MHI_H
diff --git a/drivers/net/wireless/ath/ath11k/pcic.c b/drivers/net/wireless/ath/ath11k/pcic.c
index 16d1e332193f..15e2ceb22a44 100644
--- a/drivers/net/wireless/ath/ath11k/pcic.c
+++ b/drivers/net/wireless/ath/ath11k/pcic.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2019-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022, Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "core.h"
@@ -460,8 +460,6 @@ void ath11k_pcic_ext_irq_enable(struct ath11k_base *ab)
 {
 	int i;
 
-	set_bit(ATH11K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags);
-
 	for (i = 0; i < ATH11K_EXT_IRQ_GRP_NUM_MAX; i++) {
 		struct ath11k_ext_irq_grp *irq_grp = &ab->ext_irq_grp[i];
 
@@ -471,6 +469,8 @@ void ath11k_pcic_ext_irq_enable(struct ath11k_base *ab)
 		}
 		ath11k_pcic_ext_grp_enable(irq_grp);
 	}
+
+	set_bit(ATH11K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags);
 }
 EXPORT_SYMBOL(ath11k_pcic_ext_irq_enable);
 
diff --git a/drivers/net/wireless/ath/ath11k/peer.c b/drivers/net/wireless/ath/ath11k/peer.c
index 1c79a932d17f..6d0126c39301 100644
--- a/drivers/net/wireless/ath/ath11k/peer.c
+++ b/drivers/net/wireless/ath/ath11k/peer.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "core.h"
diff --git a/drivers/net/wireless/ath/ath11k/peer.h b/drivers/net/wireless/ath/ath11k/peer.h
index 9bd385d0a38c..3ad2f3355b14 100644
--- a/drivers/net/wireless/ath/ath11k/peer.h
+++ b/drivers/net/wireless/ath/ath11k/peer.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_PEER_H
diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c
index c270dc46d506..2c7cab62b9bb 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.c
+++ b/drivers/net/wireless/ath/ath11k/qmi.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/elf.h>
diff --git a/drivers/net/wireless/ath/ath11k/qmi.h b/drivers/net/wireless/ath/ath11k/qmi.h
index d477e2be814b..7e06d100af57 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.h
+++ b/drivers/net/wireless/ath/ath11k/qmi.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_QMI_H
diff --git a/drivers/net/wireless/ath/ath11k/reg.c b/drivers/net/wireless/ath/ath11k/reg.c
index 3c7debae800a..b4fd4d2107c7 100644
--- a/drivers/net/wireless/ath/ath11k/reg.c
+++ b/drivers/net/wireless/ath/ath11k/reg.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #include <linux/rtnetlink.h>
 
diff --git a/drivers/net/wireless/ath/ath11k/reg.h b/drivers/net/wireless/ath/ath11k/reg.h
index 84daa6543b6a..f28902f85e41 100644
--- a/drivers/net/wireless/ath/ath11k/reg.h
+++ b/drivers/net/wireless/ath/ath11k/reg.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2019 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_REG_H
diff --git a/drivers/net/wireless/ath/ath11k/rx_desc.h b/drivers/net/wireless/ath/ath11k/rx_desc.h
index 786d5f36f5e5..2da6da727278 100644
--- a/drivers/net/wireless/ath/ath11k/rx_desc.h
+++ b/drivers/net/wireless/ath/ath11k/rx_desc.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #ifndef ATH11K_RX_DESC_H
 #define ATH11K_RX_DESC_H
diff --git a/drivers/net/wireless/ath/ath11k/spectral.c b/drivers/net/wireless/ath/ath11k/spectral.c
index 0b7b7122cc05..79e091134515 100644
--- a/drivers/net/wireless/ath/ath11k/spectral.c
+++ b/drivers/net/wireless/ath/ath11k/spectral.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2019-2020 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/relay.h>
diff --git a/drivers/net/wireless/ath/ath11k/spectral.h b/drivers/net/wireless/ath/ath11k/spectral.h
index 96bfa16e18e9..789cff7c64a7 100644
--- a/drivers/net/wireless/ath/ath11k/spectral.h
+++ b/drivers/net/wireless/ath/ath11k/spectral.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2019-2020 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_SPECTRAL_H
diff --git a/drivers/net/wireless/ath/ath11k/thermal.c b/drivers/net/wireless/ath/ath11k/thermal.c
index c9b012f97ba5..c29b11ab5bfa 100644
--- a/drivers/net/wireless/ath/ath11k/thermal.c
+++ b/drivers/net/wireless/ath/ath11k/thermal.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2020 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/device.h>
diff --git a/drivers/net/wireless/ath/ath11k/thermal.h b/drivers/net/wireless/ath/ath11k/thermal.h
index 83cb67686733..cdaf4e01d92e 100644
--- a/drivers/net/wireless/ath/ath11k/thermal.h
+++ b/drivers/net/wireless/ath/ath11k/thermal.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2020 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef _ATH11K_THERMAL_
diff --git a/drivers/net/wireless/ath/ath11k/trace.h b/drivers/net/wireless/ath/ath11k/trace.h
index 9535745fe026..235ab8ea715f 100644
--- a/drivers/net/wireless/ath/ath11k/trace.h
+++ b/drivers/net/wireless/ath/ath11k/trace.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2019 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #if !defined(_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c
index 2845b4313d3a..8a65fa04b48d 100644
--- a/drivers/net/wireless/ath/ath11k/wmi.c
+++ b/drivers/net/wireless/ath/ath11k/wmi.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021, 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #include <linux/skbuff.h>
 #include <linux/ctype.h>
diff --git a/drivers/net/wireless/ath/ath11k/wmi.h b/drivers/net/wireless/ath/ath11k/wmi.h
index 100bb816b592..ff0a9a92beeb 100644
--- a/drivers/net/wireless/ath/ath11k/wmi.h
+++ b/drivers/net/wireless/ath/ath11k/wmi.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_WMI_H
@@ -1096,25 +1096,27 @@ enum wmi_tlv_vdev_param {
 };
 
 enum wmi_tlv_peer_flags {
-	WMI_TLV_PEER_AUTH = 0x00000001,
-	WMI_TLV_PEER_QOS = 0x00000002,
-	WMI_TLV_PEER_NEED_PTK_4_WAY = 0x00000004,
-	WMI_TLV_PEER_NEED_GTK_2_WAY = 0x00000010,
-	WMI_TLV_PEER_APSD = 0x00000800,
-	WMI_TLV_PEER_HT = 0x00001000,
-	WMI_TLV_PEER_40MHZ = 0x00002000,
-	WMI_TLV_PEER_STBC = 0x00008000,
-	WMI_TLV_PEER_LDPC = 0x00010000,
-	WMI_TLV_PEER_DYN_MIMOPS = 0x00020000,
-	WMI_TLV_PEER_STATIC_MIMOPS = 0x00040000,
-	WMI_TLV_PEER_SPATIAL_MUX = 0x00200000,
-	WMI_TLV_PEER_VHT = 0x02000000,
-	WMI_TLV_PEER_80MHZ = 0x04000000,
-	WMI_TLV_PEER_PMF = 0x08000000,
+	WMI_PEER_AUTH		= 0x00000001,
+	WMI_PEER_QOS		= 0x00000002,
+	WMI_PEER_NEED_PTK_4_WAY	= 0x00000004,
+	WMI_PEER_NEED_GTK_2_WAY	= 0x00000010,
+	WMI_PEER_HE		= 0x00000400,
+	WMI_PEER_APSD		= 0x00000800,
+	WMI_PEER_HT		= 0x00001000,
+	WMI_PEER_40MHZ		= 0x00002000,
+	WMI_PEER_STBC		= 0x00008000,
+	WMI_PEER_LDPC		= 0x00010000,
+	WMI_PEER_DYN_MIMOPS	= 0x00020000,
+	WMI_PEER_STATIC_MIMOPS	= 0x00040000,
+	WMI_PEER_SPATIAL_MUX	= 0x00200000,
+	WMI_PEER_TWT_REQ	= 0x00400000,
+	WMI_PEER_TWT_RESP	= 0x00800000,
+	WMI_PEER_VHT		= 0x02000000,
+	WMI_PEER_80MHZ		= 0x04000000,
+	WMI_PEER_PMF		= 0x08000000,
 	WMI_PEER_IS_P2P_CAPABLE = 0x20000000,
 	WMI_PEER_160MHZ         = 0x40000000,
 	WMI_PEER_SAFEMODE_EN    = 0x80000000,
-
 };
 
 /** Enum list of TLV Tags for each parameter structure type. */
@@ -2580,7 +2582,6 @@ struct wmi_service_available_event {
 struct ath11k_pdev_wmi {
 	struct ath11k_wmi_base *wmi_ab;
 	enum ath11k_htc_ep_id eid;
-	const struct wmi_peer_flags_map *peer_flags;
 	u32 rx_decap_mode;
 	wait_queue_head_t tx_ce_desc_wq;
 };
@@ -4062,31 +4063,6 @@ struct wmi_unit_test_cmd {
 
 #define MAX_SUPPORTED_RATES 128
 
-#define WMI_PEER_AUTH		0x00000001
-#define WMI_PEER_QOS		0x00000002
-#define WMI_PEER_NEED_PTK_4_WAY	0x00000004
-#define WMI_PEER_NEED_GTK_2_WAY	0x00000010
-#define WMI_PEER_HE		0x00000400
-#define WMI_PEER_APSD		0x00000800
-#define WMI_PEER_HT		0x00001000
-#define WMI_PEER_40MHZ		0x00002000
-#define WMI_PEER_STBC		0x00008000
-#define WMI_PEER_LDPC		0x00010000
-#define WMI_PEER_DYN_MIMOPS	0x00020000
-#define WMI_PEER_STATIC_MIMOPS	0x00040000
-#define WMI_PEER_SPATIAL_MUX	0x00200000
-#define WMI_PEER_TWT_REQ	0x00400000
-#define WMI_PEER_TWT_RESP	0x00800000
-#define WMI_PEER_VHT		0x02000000
-#define WMI_PEER_80MHZ		0x04000000
-#define WMI_PEER_PMF		0x08000000
-/* TODO: Place holder for WLAN_PEER_F_PS_PRESEND_REQUIRED = 0x10000000.
- * Need to be cleaned up
- */
-#define WMI_PEER_IS_P2P_CAPABLE	0x20000000
-#define WMI_PEER_160MHZ		0x40000000
-#define WMI_PEER_SAFEMODE_EN	0x80000000
-
 struct beacon_tmpl_params {
 	u8 vdev_id;
 	u32 tim_ie_offset;
@@ -5754,7 +5730,6 @@ struct ath11k_wmi_base {
 	struct completion unified_ready;
 	DECLARE_BITMAP(svc_map, WMI_MAX_EXT2_SERVICE);
 	wait_queue_head_t tx_credits_wq;
-	const struct wmi_peer_flags_map *peer_flags;
 	u32 num_mem_chunks;
 	u32 rx_decap_mode;
 	struct wmi_host_mem_chunk mem_chunks[WMI_MAX_MEM_REQS];
diff --git a/drivers/net/wireless/ath/ath11k/wow.h b/drivers/net/wireless/ath/ath11k/wow.h
index 553ba850d910..c85811e3f42b 100644
--- a/drivers/net/wireless/ath/ath11k/wow.h
+++ b/drivers/net/wireless/ath/ath11k/wow.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2020 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef _WOW_H_
diff --git a/drivers/net/wireless/ath/ath12k/Kconfig b/drivers/net/wireless/ath/ath12k/Kconfig
index 4f9c514c13e7..e135d2b1b61d 100644
--- a/drivers/net/wireless/ath/ath12k/Kconfig
+++ b/drivers/net/wireless/ath/ath12k/Kconfig
@@ -2,7 +2,7 @@
 config ATH12K
 	tristate "Qualcomm Technologies Wi-Fi 7 support (ath12k)"
 	depends on MAC80211 && HAS_DMA && PCI
-	depends on CRYPTO_MICHAEL_MIC
+	select CRYPTO_MICHAEL_MIC
 	select QCOM_QMI_HELPERS
 	select MHI_BUS
 	select QRTR
diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index b936760b5140..6c01b282fcd3 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/module.h>
@@ -698,13 +698,15 @@ int ath12k_core_qmi_firmware_ready(struct ath12k_base *ab)
 	ret = ath12k_core_rfkill_config(ab);
 	if (ret && ret != -EOPNOTSUPP) {
 		ath12k_err(ab, "failed to config rfkill: %d\n", ret);
-		goto err_core_stop;
+		goto err_core_pdev_destroy;
 	}
 
 	mutex_unlock(&ab->core_lock);
 
 	return 0;
 
+err_core_pdev_destroy:
+	ath12k_core_pdev_destroy(ab);
 err_core_stop:
 	ath12k_core_stop(ab);
 	ath12k_mac_destroy(ab);
diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 68c42ca44fcb..8458dc292821 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_CORE_H
@@ -199,6 +199,8 @@ enum ath12k_dev_flags {
 	ATH12K_FLAG_REGISTERED,
 	ATH12K_FLAG_QMI_FAIL,
 	ATH12K_FLAG_HTC_SUSPEND_COMPLETE,
+	ATH12K_FLAG_CE_IRQ_ENABLED,
+	ATH12K_FLAG_EXT_IRQ_ENABLED,
 };
 
 enum ath12k_monitor_flags {
@@ -467,7 +469,6 @@ struct ath12k {
 	struct ath12k_base *ab;
 	struct ath12k_pdev *pdev;
 	struct ieee80211_hw *hw;
-	struct ieee80211_ops *ops;
 	struct ath12k_wmi_pdev *wmi;
 	struct ath12k_pdev_dp dp;
 	u8 mac_addr[ETH_ALEN];
diff --git a/drivers/net/wireless/ath/ath12k/dbring.c b/drivers/net/wireless/ath/ath12k/dbring.c
index 8fbf868e6f7e..788160c84c68 100644
--- a/drivers/net/wireless/ath/ath12k/dbring.c
+++ b/drivers/net/wireless/ath/ath12k/dbring.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2019-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "core.h"
diff --git a/drivers/net/wireless/ath/ath12k/debug.c b/drivers/net/wireless/ath/ath12k/debug.c
index 45d33279e665..fe5a732ba9ec 100644
--- a/drivers/net/wireless/ath/ath12k/debug.c
+++ b/drivers/net/wireless/ath/ath12k/debug.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/vmalloc.h>
diff --git a/drivers/net/wireless/ath/ath12k/dp.c b/drivers/net/wireless/ath/ath12k/dp.c
index 6893466f61f0..a6f81f2f97ef 100644
--- a/drivers/net/wireless/ath/ath12k/dp.c
+++ b/drivers/net/wireless/ath/ath12k/dp.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <crypto/hash.h>
@@ -961,9 +961,7 @@ int ath12k_dp_service_srng(struct ath12k_base *ab,
 		struct ath12k_dp *dp = &ab->dp;
 		struct dp_rxdma_ring *rx_ring = &dp->rx_refill_buf_ring;
 
-		ath12k_dp_rx_bufs_replenish(ab, 0, rx_ring, 0,
-					    ab->hw_params->hal_params->rx_buf_rbm,
-					    true);
+		ath12k_dp_rx_bufs_replenish(ab, rx_ring, 0);
 	}
 
 	/* TODO: Implement handler for other interrupts */
diff --git a/drivers/net/wireless/ath/ath12k/dp.h b/drivers/net/wireless/ath/ath12k/dp.h
index 61f765432516..1df3cdd46140 100644
--- a/drivers/net/wireless/ath/ath12k/dp.h
+++ b/drivers/net/wireless/ath/ath12k/dp.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_DP_H
@@ -31,7 +31,7 @@ struct dp_srng {
 	u32 ring_id;
 };
 
-struct dp_rxdma_ring {
+struct dp_rxdma_mon_ring {
 	struct dp_srng refill_buf_ring;
 	struct idr bufs_idr;
 	/* Protects bufs_idr */
@@ -39,6 +39,11 @@ struct dp_rxdma_ring {
 	int bufs_max;
 };
 
+struct dp_rxdma_ring {
+	struct dp_srng refill_buf_ring;
+	int bufs_max;
+};
+
 #define ATH12K_TX_COMPL_NEXT(x)	(((x) + 1) % DP_TX_COMP_RING_SIZE)
 
 struct dp_tx_ring {
@@ -353,8 +358,8 @@ struct ath12k_dp {
 	struct dp_rxdma_ring rx_refill_buf_ring;
 	struct dp_srng rx_mac_buf_ring[MAX_RXDMA_PER_PDEV];
 	struct dp_srng rxdma_err_dst_ring[MAX_RXDMA_PER_PDEV];
-	struct dp_rxdma_ring rxdma_mon_buf_ring;
-	struct dp_rxdma_ring tx_mon_buf_ring;
+	struct dp_rxdma_mon_ring rxdma_mon_buf_ring;
+	struct dp_rxdma_mon_ring tx_mon_buf_ring;
 	struct ath12k_reo_q_addr_lut reoq_lut;
 };
 
diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index f44bc5494ce7..be4b39f5fa80 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2019-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "dp_mon.h"
@@ -797,7 +797,7 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k_base *ab,
 		/* TODO: add msdu start parsing logic */
 		break;
 	case HAL_MON_BUF_ADDR: {
-		struct dp_rxdma_ring *buf_ring = &ab->dp.rxdma_mon_buf_ring;
+		struct dp_rxdma_mon_ring *buf_ring = &ab->dp.rxdma_mon_buf_ring;
 		struct dp_mon_packet_info *packet_info =
 			(struct dp_mon_packet_info *)tlv_data;
 		int buf_id = u32_get_bits(packet_info->cookie,
@@ -1091,7 +1091,7 @@ static void ath12k_dp_mon_rx_deliver_msdu(struct ath12k *ar, struct napi_struct
 	spin_unlock_bh(&ar->ab->base_lock);
 
 	ath12k_dbg(ar->ab, ATH12K_DBG_DATA,
-		   "rx skb %pK len %u peer %pM %u %s %s%s%s%s%s%s%s %srate_idx %u vht_nss %u freq %u band %u flag 0x%x fcs-err %i mic-err %i amsdu-more %i\n",
+		   "rx skb %pK len %u peer %pM %u %s %s%s%s%s%s%s%s%s %srate_idx %u vht_nss %u freq %u band %u flag 0x%x fcs-err %i mic-err %i amsdu-more %i\n",
 		   msdu,
 		   msdu->len,
 		   peer ? peer->addr : NULL,
@@ -1104,6 +1104,7 @@ static void ath12k_dp_mon_rx_deliver_msdu(struct ath12k *ar, struct napi_struct
 		   (status->bw == RATE_INFO_BW_40) ? "40" : "",
 		   (status->bw == RATE_INFO_BW_80) ? "80" : "",
 		   (status->bw == RATE_INFO_BW_160) ? "160" : "",
+		   (status->bw == RATE_INFO_BW_320) ? "320" : "",
 		   status->enc_flags & RX_ENC_FLAG_SHORT_GI ? "sgi " : "",
 		   status->rate_idx,
 		   status->nss,
@@ -1259,7 +1260,7 @@ ath12k_dp_mon_rx_parse_mon_status(struct ath12k *ar,
 }
 
 int ath12k_dp_mon_buf_replenish(struct ath12k_base *ab,
-				struct dp_rxdma_ring *buf_ring,
+				struct dp_rxdma_mon_ring *buf_ring,
 				int req_entries)
 {
 	struct hal_mon_buf_ring *mon_buf;
@@ -1902,7 +1903,7 @@ ath12k_dp_mon_tx_parse_status_tlv(struct ath12k_base *ab,
 	}
 
 	case HAL_MON_BUF_ADDR: {
-		struct dp_rxdma_ring *buf_ring = &ab->dp.tx_mon_buf_ring;
+		struct dp_rxdma_mon_ring *buf_ring = &ab->dp.tx_mon_buf_ring;
 		struct dp_mon_packet_info *packet_info =
 			(struct dp_mon_packet_info *)tlv_data;
 		int buf_id = u32_get_bits(packet_info->cookie,
@@ -2067,7 +2068,7 @@ int ath12k_dp_mon_srng_process(struct ath12k *ar, int mac_id, int *budget,
 	struct ath12k_skb_rxcb *rxcb;
 	struct dp_srng *mon_dst_ring;
 	struct hal_srng *srng;
-	struct dp_rxdma_ring *buf_ring;
+	struct dp_rxdma_mon_ring *buf_ring;
 	u64 cookie;
 	u32 ppdu_id;
 	int num_buffs_reaped = 0, srng_id, buf_id;
@@ -2480,7 +2481,7 @@ int ath12k_dp_mon_rx_process_stats(struct ath12k *ar, int mac_id,
 	struct ath12k_skb_rxcb *rxcb;
 	struct dp_srng *mon_dst_ring;
 	struct hal_srng *srng;
-	struct dp_rxdma_ring *buf_ring;
+	struct dp_rxdma_mon_ring *buf_ring;
 	struct ath12k_sta *arsta = NULL;
 	struct ath12k_peer *peer;
 	u64 cookie;
diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.h b/drivers/net/wireless/ath/ath12k/dp_mon.h
index c18c385798a1..fb9e9c176ce5 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.h
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2019-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_DP_MON_H
@@ -80,7 +80,7 @@ ath12k_dp_mon_rx_parse_mon_status(struct ath12k *ar,
 				  int mac_id, struct sk_buff *skb,
 				  struct napi_struct *napi);
 int ath12k_dp_mon_buf_replenish(struct ath12k_base *ab,
-				struct dp_rxdma_ring *buf_ring,
+				struct dp_rxdma_mon_ring *buf_ring,
 				int req_entries);
 int ath12k_dp_mon_srng_process(struct ath12k *ar, int mac_id,
 			       int *budget, enum dp_monitor_mode monitor_mode,
diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
index 3543fadac4a5..1ee83f765929 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/ieee80211.h>
@@ -256,22 +256,20 @@ static int ath12k_dp_purge_mon_ring(struct ath12k_base *ab)
 }
 
 /* Returns number of Rx buffers replenished */
-int ath12k_dp_rx_bufs_replenish(struct ath12k_base *ab, int mac_id,
+int ath12k_dp_rx_bufs_replenish(struct ath12k_base *ab,
 				struct dp_rxdma_ring *rx_ring,
-				int req_entries,
-				enum hal_rx_buf_return_buf_manager mgr,
-				bool hw_cc)
+				int req_entries)
 {
 	struct ath12k_buffer_addr *desc;
 	struct hal_srng *srng;
 	struct sk_buff *skb;
 	int num_free;
 	int num_remain;
-	int buf_id;
 	u32 cookie;
 	dma_addr_t paddr;
 	struct ath12k_dp *dp = &ab->dp;
 	struct ath12k_rx_desc_info *rx_desc;
+	enum hal_rx_buf_return_buf_manager mgr = ab->hw_params->hal_params->rx_buf_rbm;
 
 	req_entries = min(req_entries, rx_ring->bufs_max);
 
@@ -307,42 +305,29 @@ int ath12k_dp_rx_bufs_replenish(struct ath12k_base *ab, int mac_id,
 		if (dma_mapping_error(ab->dev, paddr))
 			goto fail_free_skb;
 
-		if (hw_cc) {
-			spin_lock_bh(&dp->rx_desc_lock);
-
-			/* Get desc from free list and store in used list
-			 * for cleanup purposes
-			 *
-			 * TODO: pass the removed descs rather than
-			 * add/read to optimize
-			 */
-			rx_desc = list_first_entry_or_null(&dp->rx_desc_free_list,
-							   struct ath12k_rx_desc_info,
-							   list);
-			if (!rx_desc) {
-				spin_unlock_bh(&dp->rx_desc_lock);
-				goto fail_dma_unmap;
-			}
-
-			rx_desc->skb = skb;
-			cookie = rx_desc->cookie;
-			list_del(&rx_desc->list);
-			list_add_tail(&rx_desc->list, &dp->rx_desc_used_list);
+		spin_lock_bh(&dp->rx_desc_lock);
 
+		/* Get desc from free list and store in used list
+		 * for cleanup purposes
+		 *
+		 * TODO: pass the removed descs rather than
+		 * add/read to optimize
+		 */
+		rx_desc = list_first_entry_or_null(&dp->rx_desc_free_list,
+						   struct ath12k_rx_desc_info,
+						   list);
+		if (!rx_desc) {
 			spin_unlock_bh(&dp->rx_desc_lock);
-		} else {
-			spin_lock_bh(&rx_ring->idr_lock);
-			buf_id = idr_alloc(&rx_ring->bufs_idr, skb, 0,
-					   rx_ring->bufs_max * 3, GFP_ATOMIC);
-			spin_unlock_bh(&rx_ring->idr_lock);
-			if (buf_id < 0)
-				goto fail_dma_unmap;
-			cookie = u32_encode_bits(mac_id,
-						 DP_RXDMA_BUF_COOKIE_PDEV_ID) |
-				 u32_encode_bits(buf_id,
-						 DP_RXDMA_BUF_COOKIE_BUF_ID);
+			goto fail_dma_unmap;
 		}
 
+		rx_desc->skb = skb;
+		cookie = rx_desc->cookie;
+		list_del(&rx_desc->list);
+		list_add_tail(&rx_desc->list, &dp->rx_desc_used_list);
+
+		spin_unlock_bh(&dp->rx_desc_lock);
+
 		desc = ath12k_hal_srng_src_get_next_entry(ab, srng);
 		if (!desc)
 			goto fail_buf_unassign;
@@ -361,17 +346,11 @@ int ath12k_dp_rx_bufs_replenish(struct ath12k_base *ab, int mac_id,
 	return req_entries - num_remain;
 
 fail_buf_unassign:
-	if (hw_cc) {
-		spin_lock_bh(&dp->rx_desc_lock);
-		list_del(&rx_desc->list);
-		list_add_tail(&rx_desc->list, &dp->rx_desc_free_list);
-		rx_desc->skb = NULL;
-		spin_unlock_bh(&dp->rx_desc_lock);
-	} else {
-		spin_lock_bh(&rx_ring->idr_lock);
-		idr_remove(&rx_ring->bufs_idr, buf_id);
-		spin_unlock_bh(&rx_ring->idr_lock);
-	}
+	spin_lock_bh(&dp->rx_desc_lock);
+	list_del(&rx_desc->list);
+	list_add_tail(&rx_desc->list, &dp->rx_desc_free_list);
+	rx_desc->skb = NULL;
+	spin_unlock_bh(&dp->rx_desc_lock);
 fail_dma_unmap:
 	dma_unmap_single(ab->dev, paddr, skb->len + skb_tailroom(skb),
 			 DMA_FROM_DEVICE);
@@ -385,8 +364,8 @@ fail_free_skb:
 	return req_entries - num_remain;
 }
 
-static int ath12k_dp_rxdma_buf_ring_free(struct ath12k_base *ab,
-					 struct dp_rxdma_ring *rx_ring)
+static int ath12k_dp_rxdma_mon_buf_ring_free(struct ath12k_base *ab,
+					     struct dp_rxdma_mon_ring *rx_ring)
 {
 	struct sk_buff *skb;
 	int buf_id;
@@ -411,46 +390,49 @@ static int ath12k_dp_rxdma_buf_ring_free(struct ath12k_base *ab,
 static int ath12k_dp_rxdma_buf_free(struct ath12k_base *ab)
 {
 	struct ath12k_dp *dp = &ab->dp;
-	struct dp_rxdma_ring *rx_ring = &dp->rx_refill_buf_ring;
 
-	ath12k_dp_rxdma_buf_ring_free(ab, rx_ring);
+	ath12k_dp_rxdma_mon_buf_ring_free(ab, &dp->rxdma_mon_buf_ring);
+
+	ath12k_dp_rxdma_mon_buf_ring_free(ab, &dp->tx_mon_buf_ring);
+
+	return 0;
+}
 
-	rx_ring = &dp->rxdma_mon_buf_ring;
-	ath12k_dp_rxdma_buf_ring_free(ab, rx_ring);
+static int ath12k_dp_rxdma_mon_ring_buf_setup(struct ath12k_base *ab,
+					      struct dp_rxdma_mon_ring *rx_ring,
+					      u32 ringtype)
+{
+	int num_entries;
 
-	rx_ring = &dp->tx_mon_buf_ring;
-	ath12k_dp_rxdma_buf_ring_free(ab, rx_ring);
+	num_entries = rx_ring->refill_buf_ring.size /
+		ath12k_hal_srng_get_entrysize(ab, ringtype);
+
+	rx_ring->bufs_max = num_entries;
+	ath12k_dp_mon_buf_replenish(ab, rx_ring, num_entries);
 
 	return 0;
 }
 
 static int ath12k_dp_rxdma_ring_buf_setup(struct ath12k_base *ab,
-					  struct dp_rxdma_ring *rx_ring,
-					  u32 ringtype)
+					  struct dp_rxdma_ring *rx_ring)
 {
 	int num_entries;
 
 	num_entries = rx_ring->refill_buf_ring.size /
-		ath12k_hal_srng_get_entrysize(ab, ringtype);
+		ath12k_hal_srng_get_entrysize(ab, HAL_RXDMA_BUF);
 
 	rx_ring->bufs_max = num_entries;
-	if ((ringtype == HAL_RXDMA_MONITOR_BUF) || (ringtype == HAL_TX_MONITOR_BUF))
-		ath12k_dp_mon_buf_replenish(ab, rx_ring, num_entries);
-	else
-		ath12k_dp_rx_bufs_replenish(ab, 0, rx_ring, num_entries,
-					    ab->hw_params->hal_params->rx_buf_rbm,
-					    ringtype == HAL_RXDMA_BUF);
+	ath12k_dp_rx_bufs_replenish(ab, rx_ring, num_entries);
+
 	return 0;
 }
 
 static int ath12k_dp_rxdma_buf_setup(struct ath12k_base *ab)
 {
 	struct ath12k_dp *dp = &ab->dp;
-	struct dp_rxdma_ring *rx_ring = &dp->rx_refill_buf_ring;
 	int ret;
 
-	ret = ath12k_dp_rxdma_ring_buf_setup(ab, rx_ring,
-					     HAL_RXDMA_BUF);
+	ret = ath12k_dp_rxdma_ring_buf_setup(ab, &dp->rx_refill_buf_ring);
 	if (ret) {
 		ath12k_warn(ab,
 			    "failed to setup HAL_RXDMA_BUF\n");
@@ -458,18 +440,18 @@ static int ath12k_dp_rxdma_buf_setup(struct ath12k_base *ab)
 	}
 
 	if (ab->hw_params->rxdma1_enable) {
-		rx_ring = &dp->rxdma_mon_buf_ring;
-		ret = ath12k_dp_rxdma_ring_buf_setup(ab, rx_ring,
-						     HAL_RXDMA_MONITOR_BUF);
+		ret = ath12k_dp_rxdma_mon_ring_buf_setup(ab,
+							 &dp->rxdma_mon_buf_ring,
+							 HAL_RXDMA_MONITOR_BUF);
 		if (ret) {
 			ath12k_warn(ab,
 				    "failed to setup HAL_RXDMA_MONITOR_BUF\n");
 			return ret;
 		}
 
-		rx_ring = &dp->tx_mon_buf_ring;
-		ret = ath12k_dp_rxdma_ring_buf_setup(ab, rx_ring,
-						     HAL_TX_MONITOR_BUF);
+		ret = ath12k_dp_rxdma_mon_ring_buf_setup(ab,
+							 &dp->tx_mon_buf_ring,
+							 HAL_TX_MONITOR_BUF);
 		if (ret) {
 			ath12k_warn(ab,
 				    "failed to setup HAL_TX_MONITOR_BUF\n");
@@ -1339,9 +1321,6 @@ ath12k_update_per_peer_tx_stats(struct ath12k *ar,
 	u8 tid = HTT_PPDU_STATS_NON_QOS_TID;
 	bool is_ampdu = false;
 
-	if (!usr_stats)
-		return;
-
 	if (!(usr_stats->tlv_flags & BIT(HTT_PPDU_STATS_TAG_USR_RATE)))
 		return;
 
@@ -2438,7 +2417,7 @@ static void ath12k_dp_rx_deliver_msdu(struct ath12k *ar, struct napi_struct *nap
 	spin_unlock_bh(&ab->base_lock);
 
 	ath12k_dbg(ab, ATH12K_DBG_DATA,
-		   "rx skb %pK len %u peer %pM %d %s sn %u %s%s%s%s%s%s%s%s rate_idx %u vht_nss %u freq %u band %u flag 0x%x fcs-err %i mic-err %i amsdu-more %i\n",
+		   "rx skb %pK len %u peer %pM %d %s sn %u %s%s%s%s%s%s%s%s%s rate_idx %u vht_nss %u freq %u band %u flag 0x%x fcs-err %i mic-err %i amsdu-more %i\n",
 		   msdu,
 		   msdu->len,
 		   peer ? peer->addr : NULL,
@@ -2452,6 +2431,7 @@ static void ath12k_dp_rx_deliver_msdu(struct ath12k *ar, struct napi_struct *nap
 		   (status->bw == RATE_INFO_BW_40) ? "40" : "",
 		   (status->bw == RATE_INFO_BW_80) ? "80" : "",
 		   (status->bw == RATE_INFO_BW_160) ? "160" : "",
+		   (status->bw == RATE_INFO_BW_320) ? "320" : "",
 		   status->enc_flags & RX_ENC_FLAG_SHORT_GI ? "sgi " : "",
 		   status->rate_idx,
 		   status->nss,
@@ -2714,9 +2694,7 @@ try_again:
 	if (!total_msdu_reaped)
 		goto exit;
 
-	/* TODO: Move to implicit BM? */
-	ath12k_dp_rx_bufs_replenish(ab, 0, rx_ring, num_buffs_reaped,
-				    ab->hw_params->hal_params->rx_buf_rbm, true);
+	ath12k_dp_rx_bufs_replenish(ab, rx_ring, num_buffs_reaped);
 
 	ath12k_dp_rx_process_received_packets(ab, napi, &msdu_list,
 					      ring_id);
@@ -3494,8 +3472,7 @@ exit:
 
 	rx_ring = &dp->rx_refill_buf_ring;
 
-	ath12k_dp_rx_bufs_replenish(ab, 0, rx_ring, tot_n_bufs_reaped,
-				    ab->hw_params->hal_params->rx_buf_rbm, true);
+	ath12k_dp_rx_bufs_replenish(ab, rx_ring, tot_n_bufs_reaped);
 
 	return tot_n_bufs_reaped;
 }
@@ -3808,8 +3785,7 @@ int ath12k_dp_rx_process_wbm_err(struct ath12k_base *ab,
 	if (!num_buffs_reaped)
 		goto done;
 
-	ath12k_dp_rx_bufs_replenish(ab, 0, rx_ring, num_buffs_reaped,
-				    ab->hw_params->hal_params->rx_buf_rbm, true);
+	ath12k_dp_rx_bufs_replenish(ab, rx_ring, num_buffs_reaped);
 
 	rcu_read_lock();
 	for (i = 0; i <  ab->num_radios; i++) {
@@ -4090,9 +4066,6 @@ int ath12k_dp_rx_alloc(struct ath12k_base *ab)
 	struct ath12k_dp *dp = &ab->dp;
 	int i, ret;
 
-	idr_init(&dp->rx_refill_buf_ring.bufs_idr);
-	spin_lock_init(&dp->rx_refill_buf_ring.idr_lock);
-
 	idr_init(&dp->rxdma_mon_buf_ring.bufs_idr);
 	spin_lock_init(&dp->rxdma_mon_buf_ring.idr_lock);
 
diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.h b/drivers/net/wireless/ath/ath12k/dp_rx.h
index c955b5c859d1..05b3d5581dbe 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.h
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #ifndef ATH12K_DP_RX_H
 #define ATH12K_DP_RX_H
@@ -116,11 +116,9 @@ int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi,
 int ath12k_dp_rx_process(struct ath12k_base *ab, int mac_id,
 			 struct napi_struct *napi,
 			 int budget);
-int ath12k_dp_rx_bufs_replenish(struct ath12k_base *ab, int mac_id,
+int ath12k_dp_rx_bufs_replenish(struct ath12k_base *ab,
 				struct dp_rxdma_ring *rx_ring,
-				int req_entries,
-				enum hal_rx_buf_return_buf_manager mgr,
-				bool hw_cc);
+				int req_entries);
 int ath12k_dp_rx_pdev_mon_attach(struct ath12k *ar);
 int ath12k_dp_rx_peer_frag_setup(struct ath12k *ar, const u8 *peer_mac, int vdev_id);
 
diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index 492ca6ce6714..62f9cdbb811c 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "core.h"
diff --git a/drivers/net/wireless/ath/ath12k/hal.c b/drivers/net/wireless/ath/ath12k/hal.c
index eca86fc25a60..a489369d8068 100644
--- a/drivers/net/wireless/ath/ath12k/hal.c
+++ b/drivers/net/wireless/ath/ath12k/hal.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #include <linux/dma-mapping.h>
 #include "hal_tx.h"
@@ -889,8 +889,8 @@ static u8 *ath12k_hw_wcn7850_rx_desc_mpdu_start_addr2(struct hal_rx_desc *desc)
 
 static bool ath12k_hw_wcn7850_rx_desc_is_da_mcbc(struct hal_rx_desc *desc)
 {
-	return __le16_to_cpu(desc->u.wcn7850.msdu_end.info5) &
-	       RX_MSDU_END_INFO5_DA_IS_MCBC;
+	return __le32_to_cpu(desc->u.wcn7850.msdu_end.info13) &
+	       RX_MSDU_END_INFO13_MCAST_BCAST;
 }
 
 static void ath12k_hw_wcn7850_rx_desc_get_dot11_hdr(struct hal_rx_desc *desc,
diff --git a/drivers/net/wireless/ath/ath12k/hal.h b/drivers/net/wireless/ath/ath12k/hal.h
index 66035a787c72..fc47e7e6b498 100644
--- a/drivers/net/wireless/ath/ath12k/hal.h
+++ b/drivers/net/wireless/ath/ath12k/hal.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_HAL_H
diff --git a/drivers/net/wireless/ath/ath12k/hal_rx.c b/drivers/net/wireless/ath/ath12k/hal_rx.c
index f6afbd8196bf..4f25eb9f7745 100644
--- a/drivers/net/wireless/ath/ath12k/hal_rx.c
+++ b/drivers/net/wireless/ath/ath12k/hal_rx.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "debug.h"
diff --git a/drivers/net/wireless/ath/ath12k/hal_rx.h b/drivers/net/wireless/ath/ath12k/hal_rx.h
index fcfb6c819047..095216eabc01 100644
--- a/drivers/net/wireless/ath/ath12k/hal_rx.h
+++ b/drivers/net/wireless/ath/ath12k/hal_rx.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_HAL_RX_H
@@ -61,6 +61,7 @@ enum hal_rx_bw {
 	HAL_RX_BW_40MHZ,
 	HAL_RX_BW_80MHZ,
 	HAL_RX_BW_160MHZ,
+	HAL_RX_BW_320MHZ,
 	HAL_RX_BW_MAX,
 };
 
diff --git a/drivers/net/wireless/ath/ath12k/hif.h b/drivers/net/wireless/ath/ath12k/hif.h
index 4095fd82b1b3..c653ca1f59b2 100644
--- a/drivers/net/wireless/ath/ath12k/hif.h
+++ b/drivers/net/wireless/ath/ath12k/hif.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2019-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_HIF_H
diff --git a/drivers/net/wireless/ath/ath12k/hw.c b/drivers/net/wireless/ath/ath12k/hw.c
index 2245fb510ba2..de60d988d860 100644
--- a/drivers/net/wireless/ath/ath12k/hw.c
+++ b/drivers/net/wireless/ath/ath12k/hw.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/types.h>
@@ -949,7 +949,8 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 		.rx_mac_buf_ring = true,
 		.vdev_start_delay = true,
 
-		.interface_modes = BIT(NL80211_IFTYPE_STATION),
+		.interface_modes = BIT(NL80211_IFTYPE_STATION) |
+				   BIT(NL80211_IFTYPE_AP),
 		.supports_monitor = false,
 
 		.idle_ps = true,
diff --git a/drivers/net/wireless/ath/ath12k/hw.h b/drivers/net/wireless/ath/ath12k/hw.h
index 2d6427cf41a4..d2622bfef942 100644
--- a/drivers/net/wireless/ath/ath12k/hw.h
+++ b/drivers/net/wireless/ath/ath12k/hw.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_HW_H
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index fc0d14ea328e..88cec54c6c2e 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <net/mac80211.h>
@@ -343,6 +343,9 @@ ath12k_mac_bw_to_mac80211_bw(enum ath12k_supported_bw bw)
 	case ATH12K_BW_160:
 		ret = RATE_INFO_BW_160;
 		break;
+	case ATH12K_BW_320:
+		ret = RATE_INFO_BW_320;
+		break;
 	}
 
 	return ret;
@@ -359,6 +362,8 @@ enum ath12k_supported_bw ath12k_mac_mac80211_bw_to_ath12k_bw(enum rate_info_bw b
 		return ATH12K_BW_80;
 	case RATE_INFO_BW_160:
 		return ATH12K_BW_160;
+	case RATE_INFO_BW_320:
+		return ATH12K_BW_320;
 	default:
 		return ATH12K_BW_20;
 	}
@@ -3726,6 +3731,9 @@ static u32 ath12k_mac_ieee80211_sta_bw_to_wmi(struct ath12k *ar,
 	case IEEE80211_STA_RX_BW_160:
 		bw = WMI_PEER_CHWIDTH_160MHZ;
 		break;
+	case IEEE80211_STA_RX_BW_320:
+		bw = WMI_PEER_CHWIDTH_320MHZ;
+		break;
 	default:
 		ath12k_warn(ar->ab, "Invalid bandwidth %d in rc update for %pM\n",
 			    sta->deflink.bandwidth, sta->addr);
@@ -4987,7 +4995,7 @@ static void ath12k_mac_op_tx(struct ieee80211_hw *hw,
 		if (ret) {
 			ath12k_warn(ar->ab, "failed to queue management frame %d\n",
 				    ret);
-			ieee80211_free_txskb(ar->hw, skb);
+			ieee80211_free_txskb(hw, skb);
 		}
 		return;
 	}
@@ -4995,7 +5003,7 @@ static void ath12k_mac_op_tx(struct ieee80211_hw *hw,
 	ret = ath12k_dp_tx(ar, arvif, skb);
 	if (ret) {
 		ath12k_warn(ar->ab, "failed to transmit frame %d\n", ret);
-		ieee80211_free_txskb(ar->hw, skb);
+		ieee80211_free_txskb(hw, skb);
 	}
 }
 
@@ -5596,7 +5604,7 @@ static int ath12k_mac_op_add_interface(struct ieee80211_hw *hw,
 		goto err_peer_del;
 
 	param_id = WMI_VDEV_PARAM_RTS_THRESHOLD;
-	param_value = ar->hw->wiphy->rts_threshold;
+	param_value = hw->wiphy->rts_threshold;
 	ret = ath12k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id,
 					    param_id, param_value);
 	if (ret) {
@@ -6258,10 +6266,11 @@ ath12k_mac_update_active_vif_chan(struct ath12k *ar,
 				  struct ieee80211_chanctx_conf *ctx)
 {
 	struct ath12k_mac_change_chanctx_arg arg = { .ctx = ctx };
+	struct ieee80211_hw *hw = ar->hw;
 
 	lockdep_assert_held(&ar->conf_mutex);
 
-	ieee80211_iterate_active_interfaces_atomic(ar->hw,
+	ieee80211_iterate_active_interfaces_atomic(hw,
 						   IEEE80211_IFACE_ITER_NORMAL,
 						   ath12k_mac_change_chanctx_cnt_iter,
 						   &arg);
@@ -6272,7 +6281,7 @@ ath12k_mac_update_active_vif_chan(struct ath12k *ar,
 	if (!arg.vifs)
 		return;
 
-	ieee80211_iterate_active_interfaces_atomic(ar->hw,
+	ieee80211_iterate_active_interfaces_atomic(hw,
 						   IEEE80211_IFACE_ITER_NORMAL,
 						   ath12k_mac_change_chanctx_fill_iter,
 						   &arg);
@@ -6380,8 +6389,8 @@ ath12k_mac_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 	}
 
 	if (ab->hw_params->vdev_start_delay &&
-	    (arvif->vdev_type == WMI_VDEV_TYPE_AP ||
-	    arvif->vdev_type == WMI_VDEV_TYPE_MONITOR)) {
+	    arvif->vdev_type != WMI_VDEV_TYPE_AP &&
+	    arvif->vdev_type != WMI_VDEV_TYPE_MONITOR) {
 		param.vdev_id = arvif->vdev_id;
 		param.peer_type = WMI_PEER_TYPE_DEFAULT;
 		param.peer_addr = ar->mac_addr;
@@ -6836,7 +6845,7 @@ ath12k_mac_op_set_bitrate_mask(struct ieee80211_hw *hw,
 				    arvif->vdev_id, ret);
 			return ret;
 		}
-		ieee80211_iterate_stations_atomic(ar->hw,
+		ieee80211_iterate_stations_atomic(hw,
 						  ath12k_mac_disable_peer_fixed_rate,
 						  arvif);
 	} else if (ath12k_mac_bitrate_mask_get_single_nss(ar, band, mask,
@@ -6882,14 +6891,14 @@ ath12k_mac_op_set_bitrate_mask(struct ieee80211_hw *hw,
 			return -EINVAL;
 		}
 
-		ieee80211_iterate_stations_atomic(ar->hw,
+		ieee80211_iterate_stations_atomic(hw,
 						  ath12k_mac_disable_peer_fixed_rate,
 						  arvif);
 
 		mutex_lock(&ar->conf_mutex);
 
 		arvif->bitrate_mask = *mask;
-		ieee80211_iterate_stations_atomic(ar->hw,
+		ieee80211_iterate_stations_atomic(hw,
 						  ath12k_mac_set_bitrate_mask_iter,
 						  arvif);
 
@@ -6927,7 +6936,7 @@ ath12k_mac_op_reconfig_complete(struct ieee80211_hw *hw,
 		ath12k_warn(ar->ab, "pdev %d successfully recovered\n",
 			    ar->pdev->pdev_id);
 		ar->state = ATH12K_STATE_ON;
-		ieee80211_wake_queues(ar->hw);
+		ieee80211_wake_queues(hw);
 
 		if (ab->is_reset) {
 			recovery_count = atomic_inc_return(&ab->recovery_count);
@@ -7151,6 +7160,7 @@ static u32 ath12k_get_phy_id(struct ath12k *ar, u32 band)
 static int ath12k_mac_setup_channels_rates(struct ath12k *ar,
 					   u32 supported_bands)
 {
+	struct ieee80211_hw *hw = ar->hw;
 	struct ieee80211_supported_band *band;
 	struct ath12k_wmi_hal_reg_capabilities_ext_arg *reg_cap;
 	void *channels;
@@ -7176,7 +7186,7 @@ static int ath12k_mac_setup_channels_rates(struct ath12k *ar,
 		band->channels = channels;
 		band->n_bitrates = ath12k_g_rates_size;
 		band->bitrates = ath12k_g_rates;
-		ar->hw->wiphy->bands[NL80211_BAND_2GHZ] = band;
+		hw->wiphy->bands[NL80211_BAND_2GHZ] = band;
 
 		if (ar->ab->hw_params->single_pdev_only) {
 			phy_id = ath12k_get_phy_id(ar, WMI_HOST_WLAN_2G_CAP);
@@ -7203,7 +7213,7 @@ static int ath12k_mac_setup_channels_rates(struct ath12k *ar,
 			band->channels = channels;
 			band->n_bitrates = ath12k_a_rates_size;
 			band->bitrates = ath12k_a_rates;
-			ar->hw->wiphy->bands[NL80211_BAND_6GHZ] = band;
+			hw->wiphy->bands[NL80211_BAND_6GHZ] = band;
 			ath12k_mac_update_ch_list(ar, band,
 						  reg_cap->low_5ghz_chan,
 						  reg_cap->high_5ghz_chan);
@@ -7225,7 +7235,7 @@ static int ath12k_mac_setup_channels_rates(struct ath12k *ar,
 			band->channels = channels;
 			band->n_bitrates = ath12k_a_rates_size;
 			band->bitrates = ath12k_a_rates;
-			ar->hw->wiphy->bands[NL80211_BAND_5GHZ] = band;
+			hw->wiphy->bands[NL80211_BAND_5GHZ] = band;
 
 			if (ar->ab->hw_params->single_pdev_only) {
 				phy_id = ath12k_get_phy_id(ar, WMI_HOST_WLAN_5G_CAP);
@@ -7244,6 +7254,8 @@ static int ath12k_mac_setup_channels_rates(struct ath12k *ar,
 static int ath12k_mac_setup_iface_combinations(struct ath12k *ar)
 {
 	struct ath12k_base *ab = ar->ab;
+	struct ieee80211_hw *hw = ar->hw;
+	struct wiphy *wiphy = hw->wiphy;
 	struct ieee80211_iface_combination *combinations;
 	struct ieee80211_iface_limit *limits;
 	int n_limits, max_interfaces;
@@ -7294,8 +7306,8 @@ static int ath12k_mac_setup_iface_combinations(struct ath12k *ar)
 						BIT(NL80211_CHAN_WIDTH_40) |
 						BIT(NL80211_CHAN_WIDTH_80);
 
-	ar->hw->wiphy->iface_combinations = combinations;
-	ar->hw->wiphy->n_iface_combinations = 1;
+	wiphy->iface_combinations = combinations;
+	wiphy->n_iface_combinations = 1;
 
 	return 0;
 }
@@ -7339,9 +7351,12 @@ static const struct wiphy_iftype_ext_capab ath12k_iftypes_ext_capa[] = {
 
 static void __ath12k_mac_unregister(struct ath12k *ar)
 {
+	struct ieee80211_hw *hw = ar->hw;
+	struct wiphy *wiphy = hw->wiphy;
+
 	cancel_work_sync(&ar->regd_update_work);
 
-	ieee80211_unregister_hw(ar->hw);
+	ieee80211_unregister_hw(hw);
 
 	idr_for_each(&ar->txmgmt_idr, ath12k_mac_tx_mgmt_pending_free, ar);
 	idr_destroy(&ar->txmgmt_idr);
@@ -7350,10 +7365,10 @@ static void __ath12k_mac_unregister(struct ath12k *ar)
 	kfree(ar->mac.sbands[NL80211_BAND_5GHZ].channels);
 	kfree(ar->mac.sbands[NL80211_BAND_6GHZ].channels);
 
-	kfree(ar->hw->wiphy->iface_combinations[0].limits);
-	kfree(ar->hw->wiphy->iface_combinations);
+	kfree(wiphy->iface_combinations[0].limits);
+	kfree(wiphy->iface_combinations);
 
-	SET_IEEE80211_DEV(ar->hw, NULL);
+	SET_IEEE80211_DEV(hw, NULL);
 }
 
 void ath12k_mac_unregister(struct ath12k_base *ab)
@@ -7375,6 +7390,8 @@ void ath12k_mac_unregister(struct ath12k_base *ab)
 static int __ath12k_mac_register(struct ath12k *ar)
 {
 	struct ath12k_base *ab = ar->ab;
+	struct ieee80211_hw *hw = ar->hw;
+	struct wiphy *wiphy = hw->wiphy;
 	struct ath12k_pdev_cap *cap = &ar->pdev->cap;
 	static const u32 cipher_suites[] = {
 		WLAN_CIPHER_SUITE_TKIP,
@@ -7392,9 +7409,9 @@ static int __ath12k_mac_register(struct ath12k *ar)
 
 	ath12k_pdev_caps_update(ar);
 
-	SET_IEEE80211_PERM_ADDR(ar->hw, ar->mac_addr);
+	SET_IEEE80211_PERM_ADDR(hw, ar->mac_addr);
 
-	SET_IEEE80211_DEV(ar->hw, ab->dev);
+	SET_IEEE80211_DEV(hw, ab->dev);
 
 	ret = ath12k_mac_setup_channels_rates(ar,
 					      cap->supported_bands);
@@ -7410,103 +7427,102 @@ static int __ath12k_mac_register(struct ath12k *ar)
 		goto err_free_channels;
 	}
 
-	ar->hw->wiphy->available_antennas_rx = cap->rx_chain_mask;
-	ar->hw->wiphy->available_antennas_tx = cap->tx_chain_mask;
+	wiphy->available_antennas_rx = cap->rx_chain_mask;
+	wiphy->available_antennas_tx = cap->tx_chain_mask;
 
-	ar->hw->wiphy->interface_modes = ab->hw_params->interface_modes;
+	wiphy->interface_modes = ab->hw_params->interface_modes;
 
-	if (ar->hw->wiphy->bands[NL80211_BAND_2GHZ] &&
-	    ar->hw->wiphy->bands[NL80211_BAND_5GHZ] &&
-	    ar->hw->wiphy->bands[NL80211_BAND_6GHZ])
-		ieee80211_hw_set(ar->hw, SINGLE_SCAN_ON_ALL_BANDS);
+	if (wiphy->bands[NL80211_BAND_2GHZ] &&
+	    wiphy->bands[NL80211_BAND_5GHZ] &&
+	    wiphy->bands[NL80211_BAND_6GHZ])
+		ieee80211_hw_set(hw, SINGLE_SCAN_ON_ALL_BANDS);
 
-	ieee80211_hw_set(ar->hw, SIGNAL_DBM);
-	ieee80211_hw_set(ar->hw, SUPPORTS_PS);
-	ieee80211_hw_set(ar->hw, SUPPORTS_DYNAMIC_PS);
-	ieee80211_hw_set(ar->hw, MFP_CAPABLE);
-	ieee80211_hw_set(ar->hw, REPORTS_TX_ACK_STATUS);
-	ieee80211_hw_set(ar->hw, HAS_RATE_CONTROL);
-	ieee80211_hw_set(ar->hw, AP_LINK_PS);
-	ieee80211_hw_set(ar->hw, SPECTRUM_MGMT);
-	ieee80211_hw_set(ar->hw, CONNECTION_MONITOR);
-	ieee80211_hw_set(ar->hw, SUPPORTS_PER_STA_GTK);
-	ieee80211_hw_set(ar->hw, CHANCTX_STA_CSA);
-	ieee80211_hw_set(ar->hw, QUEUE_CONTROL);
-	ieee80211_hw_set(ar->hw, SUPPORTS_TX_FRAG);
-	ieee80211_hw_set(ar->hw, REPORTS_LOW_ACK);
+	ieee80211_hw_set(hw, SIGNAL_DBM);
+	ieee80211_hw_set(hw, SUPPORTS_PS);
+	ieee80211_hw_set(hw, SUPPORTS_DYNAMIC_PS);
+	ieee80211_hw_set(hw, MFP_CAPABLE);
+	ieee80211_hw_set(hw, REPORTS_TX_ACK_STATUS);
+	ieee80211_hw_set(hw, HAS_RATE_CONTROL);
+	ieee80211_hw_set(hw, AP_LINK_PS);
+	ieee80211_hw_set(hw, SPECTRUM_MGMT);
+	ieee80211_hw_set(hw, CONNECTION_MONITOR);
+	ieee80211_hw_set(hw, SUPPORTS_PER_STA_GTK);
+	ieee80211_hw_set(hw, CHANCTX_STA_CSA);
+	ieee80211_hw_set(hw, QUEUE_CONTROL);
+	ieee80211_hw_set(hw, SUPPORTS_TX_FRAG);
+	ieee80211_hw_set(hw, REPORTS_LOW_ACK);
 
 	if (ht_cap & WMI_HT_CAP_ENABLED) {
-		ieee80211_hw_set(ar->hw, AMPDU_AGGREGATION);
-		ieee80211_hw_set(ar->hw, TX_AMPDU_SETUP_IN_HW);
-		ieee80211_hw_set(ar->hw, SUPPORTS_REORDERING_BUFFER);
-		ieee80211_hw_set(ar->hw, SUPPORTS_AMSDU_IN_AMPDU);
-		ieee80211_hw_set(ar->hw, USES_RSS);
+		ieee80211_hw_set(hw, AMPDU_AGGREGATION);
+		ieee80211_hw_set(hw, TX_AMPDU_SETUP_IN_HW);
+		ieee80211_hw_set(hw, SUPPORTS_REORDERING_BUFFER);
+		ieee80211_hw_set(hw, SUPPORTS_AMSDU_IN_AMPDU);
+		ieee80211_hw_set(hw, USES_RSS);
 	}
 
-	ar->hw->wiphy->features |= NL80211_FEATURE_STATIC_SMPS;
-	ar->hw->wiphy->flags |= WIPHY_FLAG_IBSS_RSN;
+	wiphy->features |= NL80211_FEATURE_STATIC_SMPS;
+	wiphy->flags |= WIPHY_FLAG_IBSS_RSN;
 
 	/* TODO: Check if HT capability advertised from firmware is different
 	 * for each band for a dual band capable radio. It will be tricky to
 	 * handle it when the ht capability different for each band.
 	 */
 	if (ht_cap & WMI_HT_CAP_DYNAMIC_SMPS)
-		ar->hw->wiphy->features |= NL80211_FEATURE_DYNAMIC_SMPS;
+		wiphy->features |= NL80211_FEATURE_DYNAMIC_SMPS;
 
-	ar->hw->wiphy->max_scan_ssids = WLAN_SCAN_PARAMS_MAX_SSID;
-	ar->hw->wiphy->max_scan_ie_len = WLAN_SCAN_PARAMS_MAX_IE_LEN;
+	wiphy->max_scan_ssids = WLAN_SCAN_PARAMS_MAX_SSID;
+	wiphy->max_scan_ie_len = WLAN_SCAN_PARAMS_MAX_IE_LEN;
 
-	ar->hw->max_listen_interval = ATH12K_MAX_HW_LISTEN_INTERVAL;
+	hw->max_listen_interval = ATH12K_MAX_HW_LISTEN_INTERVAL;
 
-	ar->hw->wiphy->flags |= WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL;
-	ar->hw->wiphy->flags |= WIPHY_FLAG_HAS_CHANNEL_SWITCH;
-	ar->hw->wiphy->max_remain_on_channel_duration = 5000;
+	wiphy->flags |= WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL;
+	wiphy->flags |= WIPHY_FLAG_HAS_CHANNEL_SWITCH;
+	wiphy->max_remain_on_channel_duration = 5000;
 
-	ar->hw->wiphy->flags |= WIPHY_FLAG_AP_UAPSD;
-	ar->hw->wiphy->features |= NL80211_FEATURE_AP_MODE_CHAN_WIDTH_CHANGE |
+	wiphy->flags |= WIPHY_FLAG_AP_UAPSD;
+	wiphy->features |= NL80211_FEATURE_AP_MODE_CHAN_WIDTH_CHANGE |
 				   NL80211_FEATURE_AP_SCAN;
 
 	ar->max_num_stations = TARGET_NUM_STATIONS;
 	ar->max_num_peers = TARGET_NUM_PEERS_PDEV;
 
-	ar->hw->wiphy->max_ap_assoc_sta = ar->max_num_stations;
+	wiphy->max_ap_assoc_sta = ar->max_num_stations;
 
-	ar->hw->queues = ATH12K_HW_MAX_QUEUES;
-	ar->hw->wiphy->tx_queue_len = ATH12K_QUEUE_LEN;
-	ar->hw->offchannel_tx_hw_queue = ATH12K_HW_MAX_QUEUES - 1;
-	ar->hw->max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_HE;
+	hw->queues = ATH12K_HW_MAX_QUEUES;
+	wiphy->tx_queue_len = ATH12K_QUEUE_LEN;
+	hw->offchannel_tx_hw_queue = ATH12K_HW_MAX_QUEUES - 1;
+	hw->max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_HE;
 
-	ar->hw->vif_data_size = sizeof(struct ath12k_vif);
-	ar->hw->sta_data_size = sizeof(struct ath12k_sta);
+	hw->vif_data_size = sizeof(struct ath12k_vif);
+	hw->sta_data_size = sizeof(struct ath12k_sta);
 
-	wiphy_ext_feature_set(ar->hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
-	wiphy_ext_feature_set(ar->hw->wiphy, NL80211_EXT_FEATURE_STA_TX_PWR);
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_STA_TX_PWR);
 
-	ar->hw->wiphy->cipher_suites = cipher_suites;
-	ar->hw->wiphy->n_cipher_suites = ARRAY_SIZE(cipher_suites);
+	wiphy->cipher_suites = cipher_suites;
+	wiphy->n_cipher_suites = ARRAY_SIZE(cipher_suites);
 
-	ar->hw->wiphy->iftype_ext_capab = ath12k_iftypes_ext_capa;
-	ar->hw->wiphy->num_iftype_ext_capab =
-		ARRAY_SIZE(ath12k_iftypes_ext_capa);
+	wiphy->iftype_ext_capab = ath12k_iftypes_ext_capa;
+	wiphy->num_iftype_ext_capab = ARRAY_SIZE(ath12k_iftypes_ext_capa);
 
 	if (ar->supports_6ghz) {
-		wiphy_ext_feature_set(ar->hw->wiphy,
+		wiphy_ext_feature_set(wiphy,
 				      NL80211_EXT_FEATURE_FILS_DISCOVERY);
-		wiphy_ext_feature_set(ar->hw->wiphy,
+		wiphy_ext_feature_set(wiphy,
 				      NL80211_EXT_FEATURE_UNSOL_BCAST_PROBE_RESP);
 	}
 
-	wiphy_ext_feature_set(ar->hw->wiphy, NL80211_EXT_FEATURE_PUNCT);
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_PUNCT);
 
-	ath12k_reg_init(ar);
+	ath12k_reg_init(hw);
 
 	if (!test_bit(ATH12K_FLAG_RAW_MODE, &ab->dev_flags)) {
-		ar->hw->netdev_features = NETIF_F_HW_CSUM;
-		ieee80211_hw_set(ar->hw, SW_CRYPTO_CONTROL);
-		ieee80211_hw_set(ar->hw, SUPPORT_FAST_XMIT);
+		hw->netdev_features = NETIF_F_HW_CSUM;
+		ieee80211_hw_set(hw, SW_CRYPTO_CONTROL);
+		ieee80211_hw_set(hw, SUPPORT_FAST_XMIT);
 	}
 
-	ret = ieee80211_register_hw(ar->hw);
+	ret = ieee80211_register_hw(hw);
 	if (ret) {
 		ath12k_err(ar->ab, "ieee80211 registration failed: %d\n", ret);
 		goto err_free_if_combs;
@@ -7518,7 +7534,7 @@ static int __ath12k_mac_register(struct ath12k *ar)
 		 * while. But that time is so short and in practise it make
 		 * a difference in real life.
 		 */
-		ar->hw->wiphy->interface_modes &= ~BIT(NL80211_IFTYPE_MONITOR);
+		wiphy->interface_modes &= ~BIT(NL80211_IFTYPE_MONITOR);
 
 	/* Apply the regd received during initialization */
 	ret = ath12k_regd_update(ar, true);
@@ -7530,11 +7546,11 @@ static int __ath12k_mac_register(struct ath12k *ar)
 	return 0;
 
 err_unregister_hw:
-	ieee80211_unregister_hw(ar->hw);
+	ieee80211_unregister_hw(hw);
 
 err_free_if_combs:
-	kfree(ar->hw->wiphy->iface_combinations[0].limits);
-	kfree(ar->hw->wiphy->iface_combinations);
+	kfree(wiphy->iface_combinations[0].limits);
+	kfree(wiphy->iface_combinations);
 
 err_free_channels:
 	kfree(ar->mac.sbands[NL80211_BAND_2GHZ].channels);
@@ -7542,7 +7558,7 @@ err_free_channels:
 	kfree(ar->mac.sbands[NL80211_BAND_6GHZ].channels);
 
 err:
-	SET_IEEE80211_DEV(ar->hw, NULL);
+	SET_IEEE80211_DEV(hw, NULL);
 	return ret;
 }
 
diff --git a/drivers/net/wireless/ath/ath12k/mac.h b/drivers/net/wireless/ath/ath12k/mac.h
index 59b4e8f5eee0..7c63bb628adc 100644
--- a/drivers/net/wireless/ath/ath12k/mac.h
+++ b/drivers/net/wireless/ath/ath12k/mac.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_MAC_H
@@ -43,6 +43,7 @@ enum ath12k_supported_bw {
 	ATH12K_BW_40    = 1,
 	ATH12K_BW_80    = 2,
 	ATH12K_BW_160   = 3,
+	ATH12K_BW_320   = 4,
 };
 
 extern const struct htt_rx_ring_tlv_filter ath12k_mac_mon_status_filter_default;
diff --git a/drivers/net/wireless/ath/ath12k/mhi.c b/drivers/net/wireless/ath/ath12k/mhi.c
index 39e640293cdc..d5441ddb374b 100644
--- a/drivers/net/wireless/ath/ath12k/mhi.c
+++ b/drivers/net/wireless/ath/ath12k/mhi.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2020-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/msi.h>
@@ -251,6 +251,7 @@ static int ath12k_mhi_get_msi(struct ath12k_pci *ab_pci)
 	u32 user_base_data, base_vector;
 	int ret, num_vectors, i;
 	int *irq;
+	unsigned int msi_data;
 
 	ret = ath12k_pci_get_user_msi_assignment(ab,
 						 "MHI", &num_vectors,
@@ -265,9 +266,15 @@ static int ath12k_mhi_get_msi(struct ath12k_pci *ab_pci)
 	if (!irq)
 		return -ENOMEM;
 
-	for (i = 0; i < num_vectors; i++)
-		irq[i] = ath12k_pci_get_msi_irq(ab->dev,
-						base_vector + i);
+	msi_data = base_vector;
+	for (i = 0; i < num_vectors; i++) {
+		if (test_bit(ATH12K_PCI_FLAG_MULTI_MSI_VECTORS, &ab_pci->flags))
+			irq[i] = ath12k_pci_get_msi_irq(ab->dev,
+							msi_data++);
+		else
+			irq[i] = ath12k_pci_get_msi_irq(ab->dev,
+							msi_data);
+	}
 
 	ab_pci->mhi_ctrl->irq = irq;
 	ab_pci->mhi_ctrl->nr_irqs = num_vectors;
@@ -374,6 +381,9 @@ int ath12k_mhi_register(struct ath12k_pci *ab_pci)
 		goto free_controller;
 	}
 
+	if (!test_bit(ATH12K_PCI_FLAG_MULTI_MSI_VECTORS, &ab_pci->flags))
+		mhi_ctrl->irq_flags = IRQF_SHARED | IRQF_NOBALANCING;
+
 	mhi_ctrl->iova_start = 0;
 	mhi_ctrl->iova_stop = 0xffffffff;
 	mhi_ctrl->sbl_size = SZ_512K;
diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c
index 3006cd3fbe11..f0d2e2d8719c 100644
--- a/drivers/net/wireless/ath/ath12k/pci.c
+++ b/drivers/net/wireless/ath/ath12k/pci.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2019-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/module.h>
@@ -60,6 +60,17 @@ static const struct ath12k_msi_config ath12k_msi_config[] = {
 	},
 };
 
+static const struct ath12k_msi_config msi_config_one_msi = {
+	.total_vectors = 1,
+	.total_users = 4,
+	.users = (struct ath12k_msi_user[]) {
+		{ .name = "MHI", .num_vectors = 3, .base_vector = 0 },
+		{ .name = "CE", .num_vectors = 1, .base_vector = 0 },
+		{ .name = "WAKE", .num_vectors = 1, .base_vector = 0 },
+		{ .name = "DP", .num_vectors = 1, .base_vector = 0 },
+	},
+};
+
 static const char *irq_name[ATH12K_IRQ_NUM_MAX] = {
 	"bhi",
 	"mhi-er0",
@@ -355,16 +366,30 @@ static void ath12k_pci_free_irq(struct ath12k_base *ab)
 
 static void ath12k_pci_ce_irq_enable(struct ath12k_base *ab, u16 ce_id)
 {
+	struct ath12k_pci *ab_pci = ath12k_pci_priv(ab);
 	u32 irq_idx;
 
+	/* In case of one MSI vector, we handle irq enable/disable in a
+	 * uniform way since we only have one irq
+	 */
+	if (!test_bit(ATH12K_PCI_FLAG_MULTI_MSI_VECTORS, &ab_pci->flags))
+		return;
+
 	irq_idx = ATH12K_PCI_IRQ_CE0_OFFSET + ce_id;
 	enable_irq(ab->irq_num[irq_idx]);
 }
 
 static void ath12k_pci_ce_irq_disable(struct ath12k_base *ab, u16 ce_id)
 {
+	struct ath12k_pci *ab_pci = ath12k_pci_priv(ab);
 	u32 irq_idx;
 
+	/* In case of one MSI vector, we handle irq enable/disable in a
+	 * uniform way since we only have one irq
+	 */
+	if (!test_bit(ATH12K_PCI_FLAG_MULTI_MSI_VECTORS, &ab_pci->flags))
+		return;
+
 	irq_idx = ATH12K_PCI_IRQ_CE0_OFFSET + ce_id;
 	disable_irq_nosync(ab->irq_num[irq_idx]);
 }
@@ -373,6 +398,8 @@ static void ath12k_pci_ce_irqs_disable(struct ath12k_base *ab)
 {
 	int i;
 
+	clear_bit(ATH12K_FLAG_CE_IRQ_ENABLED, &ab->dev_flags);
+
 	for (i = 0; i < ab->hw_params->ce_count; i++) {
 		if (ath12k_ce_get_attr_flags(ab, i) & CE_ATTR_DIS_INTR)
 			continue;
@@ -397,20 +424,27 @@ static void ath12k_pci_sync_ce_irqs(struct ath12k_base *ab)
 static void ath12k_pci_ce_tasklet(struct tasklet_struct *t)
 {
 	struct ath12k_ce_pipe *ce_pipe = from_tasklet(ce_pipe, t, intr_tq);
+	int irq_idx = ATH12K_PCI_IRQ_CE0_OFFSET + ce_pipe->pipe_num;
 
 	ath12k_ce_per_engine_service(ce_pipe->ab, ce_pipe->pipe_num);
 
-	ath12k_pci_ce_irq_enable(ce_pipe->ab, ce_pipe->pipe_num);
+	enable_irq(ce_pipe->ab->irq_num[irq_idx]);
 }
 
 static irqreturn_t ath12k_pci_ce_interrupt_handler(int irq, void *arg)
 {
 	struct ath12k_ce_pipe *ce_pipe = arg;
+	struct ath12k_base *ab = ce_pipe->ab;
+	int irq_idx = ATH12K_PCI_IRQ_CE0_OFFSET + ce_pipe->pipe_num;
+
+	if (!test_bit(ATH12K_FLAG_CE_IRQ_ENABLED, &ab->dev_flags))
+		return IRQ_HANDLED;
 
 	/* last interrupt received for this CE */
 	ce_pipe->timestamp = jiffies;
 
-	ath12k_pci_ce_irq_disable(ce_pipe->ab, ce_pipe->pipe_num);
+	disable_irq_nosync(ab->irq_num[irq_idx]);
+
 	tasklet_schedule(&ce_pipe->intr_tq);
 
 	return IRQ_HANDLED;
@@ -418,8 +452,15 @@ static irqreturn_t ath12k_pci_ce_interrupt_handler(int irq, void *arg)
 
 static void ath12k_pci_ext_grp_disable(struct ath12k_ext_irq_grp *irq_grp)
 {
+	struct ath12k_pci *ab_pci = ath12k_pci_priv(irq_grp->ab);
 	int i;
 
+	/* In case of one MSI vector, we handle irq enable/disable
+	 * in a uniform way since we only have one irq
+	 */
+	if (!test_bit(ATH12K_PCI_FLAG_MULTI_MSI_VECTORS, &ab_pci->flags))
+		return;
+
 	for (i = 0; i < irq_grp->num_irq; i++)
 		disable_irq_nosync(irq_grp->ab->irq_num[irq_grp->irqs[i]]);
 }
@@ -428,6 +469,8 @@ static void __ath12k_pci_ext_irq_disable(struct ath12k_base *ab)
 {
 	int i;
 
+	clear_bit(ATH12K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags);
+
 	for (i = 0; i < ATH12K_EXT_IRQ_GRP_NUM_MAX; i++) {
 		struct ath12k_ext_irq_grp *irq_grp = &ab->ext_irq_grp[i];
 
@@ -440,8 +483,15 @@ static void __ath12k_pci_ext_irq_disable(struct ath12k_base *ab)
 
 static void ath12k_pci_ext_grp_enable(struct ath12k_ext_irq_grp *irq_grp)
 {
+	struct ath12k_pci *ab_pci = ath12k_pci_priv(irq_grp->ab);
 	int i;
 
+	/* In case of one MSI vector, we handle irq enable/disable in a
+	 * uniform way since we only have one irq
+	 */
+	if (!test_bit(ATH12K_PCI_FLAG_MULTI_MSI_VECTORS, &ab_pci->flags))
+		return;
+
 	for (i = 0; i < irq_grp->num_irq; i++)
 		enable_irq(irq_grp->ab->irq_num[irq_grp->irqs[i]]);
 }
@@ -467,11 +517,13 @@ static int ath12k_pci_ext_grp_napi_poll(struct napi_struct *napi, int budget)
 						napi);
 	struct ath12k_base *ab = irq_grp->ab;
 	int work_done;
+	int i;
 
 	work_done = ath12k_dp_service_srng(ab, irq_grp, budget);
 	if (work_done < budget) {
 		napi_complete_done(napi, work_done);
-		ath12k_pci_ext_grp_enable(irq_grp);
+		for (i = 0; i < irq_grp->num_irq; i++)
+			enable_irq(irq_grp->ab->irq_num[irq_grp->irqs[i]]);
 	}
 
 	if (work_done > budget)
@@ -483,13 +535,19 @@ static int ath12k_pci_ext_grp_napi_poll(struct napi_struct *napi, int budget)
 static irqreturn_t ath12k_pci_ext_interrupt_handler(int irq, void *arg)
 {
 	struct ath12k_ext_irq_grp *irq_grp = arg;
+	struct ath12k_base *ab = irq_grp->ab;
+	int i;
+
+	if (!test_bit(ATH12K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags))
+		return IRQ_HANDLED;
 
 	ath12k_dbg(irq_grp->ab, ATH12K_DBG_PCI, "ext irq:%d\n", irq);
 
 	/* last interrupt received for this group */
 	irq_grp->timestamp = jiffies;
 
-	ath12k_pci_ext_grp_disable(irq_grp);
+	for (i = 0; i < irq_grp->num_irq; i++)
+		disable_irq_nosync(irq_grp->ab->irq_num[irq_grp->irqs[i]]);
 
 	napi_schedule(&irq_grp->napi);
 
@@ -498,6 +556,7 @@ static irqreturn_t ath12k_pci_ext_interrupt_handler(int irq, void *arg)
 
 static int ath12k_pci_ext_irq_config(struct ath12k_base *ab)
 {
+	struct ath12k_pci *ab_pci = ath12k_pci_priv(ab);
 	int i, j, ret, num_vectors = 0;
 	u32 user_base_data = 0, base_vector = 0, base_idx;
 
@@ -544,23 +603,32 @@ static int ath12k_pci_ext_irq_config(struct ath12k_base *ab)
 
 			irq_set_status_flags(irq, IRQ_DISABLE_UNLAZY);
 			ret = request_irq(irq, ath12k_pci_ext_interrupt_handler,
-					  IRQF_SHARED,
+					  ab_pci->irq_flags,
 					  "DP_EXT_IRQ", irq_grp);
 			if (ret) {
 				ath12k_err(ab, "failed request irq %d: %d\n",
 					   vector, ret);
 				return ret;
 			}
-
-			disable_irq_nosync(ab->irq_num[irq_idx]);
 		}
+		ath12k_pci_ext_grp_disable(irq_grp);
 	}
 
 	return 0;
 }
 
+static int ath12k_pci_set_irq_affinity_hint(struct ath12k_pci *ab_pci,
+					    const struct cpumask *m)
+{
+	if (test_bit(ATH12K_PCI_FLAG_MULTI_MSI_VECTORS, &ab_pci->flags))
+		return 0;
+
+	return irq_set_affinity_hint(ab_pci->pdev->irq, m);
+}
+
 static int ath12k_pci_config_irq(struct ath12k_base *ab)
 {
+	struct ath12k_pci *ab_pci = ath12k_pci_priv(ab);
 	struct ath12k_ce_pipe *ce_pipe;
 	u32 msi_data_start;
 	u32 msi_data_count, msi_data_idx;
@@ -589,7 +657,7 @@ static int ath12k_pci_config_irq(struct ath12k_base *ab)
 		tasklet_setup(&ce_pipe->intr_tq, ath12k_pci_ce_tasklet);
 
 		ret = request_irq(irq, ath12k_pci_ce_interrupt_handler,
-				  IRQF_SHARED, irq_name[irq_idx],
+				  ab_pci->irq_flags, irq_name[irq_idx],
 				  ce_pipe);
 		if (ret) {
 			ath12k_err(ab, "failed to request irq %d: %d\n",
@@ -626,6 +694,8 @@ static void ath12k_pci_ce_irqs_enable(struct ath12k_base *ab)
 {
 	int i;
 
+	set_bit(ATH12K_FLAG_CE_IRQ_ENABLED, &ab->dev_flags);
+
 	for (i = 0; i < ab->hw_params->ce_count; i++) {
 		if (ath12k_ce_get_attr_flags(ab, i) & CE_ATTR_DIS_INTR)
 			continue;
@@ -670,16 +740,27 @@ static int ath12k_pci_msi_alloc(struct ath12k_pci *ab_pci)
 					    msi_config->total_vectors,
 					    msi_config->total_vectors,
 					    PCI_IRQ_MSI);
-	if (num_vectors != msi_config->total_vectors) {
-		ath12k_err(ab, "failed to get %d MSI vectors, only %d available",
-			   msi_config->total_vectors, num_vectors);
 
-		if (num_vectors >= 0)
-			return -EINVAL;
-		else
-			return num_vectors;
+	if (num_vectors == msi_config->total_vectors) {
+		set_bit(ATH12K_PCI_FLAG_MULTI_MSI_VECTORS, &ab_pci->flags);
+		ab_pci->irq_flags = IRQF_SHARED;
+	} else {
+		num_vectors = pci_alloc_irq_vectors(ab_pci->pdev,
+						    1,
+						    1,
+						    PCI_IRQ_MSI);
+		if (num_vectors < 0) {
+			ret = -EINVAL;
+			goto reset_msi_config;
+		}
+		clear_bit(ATH12K_PCI_FLAG_MULTI_MSI_VECTORS, &ab_pci->flags);
+		ab_pci->msi_config = &msi_config_one_msi;
+		ab_pci->irq_flags = IRQF_SHARED | IRQF_NOBALANCING;
+		ath12k_dbg(ab, ATH12K_DBG_PCI, "request MSI one vector\n");
 	}
 
+	ath12k_info(ab, "MSI vectors: %d\n", num_vectors);
+
 	ath12k_pci_msi_disable(ab_pci);
 
 	msi_desc = irq_get_msi_desc(ab_pci->pdev->irq);
@@ -700,6 +781,7 @@ static int ath12k_pci_msi_alloc(struct ath12k_pci *ab_pci)
 free_msi_vector:
 	pci_free_irq_vectors(ab_pci->pdev);
 
+reset_msi_config:
 	return ret;
 }
 
@@ -708,6 +790,25 @@ static void ath12k_pci_msi_free(struct ath12k_pci *ab_pci)
 	pci_free_irq_vectors(ab_pci->pdev);
 }
 
+static int ath12k_pci_config_msi_data(struct ath12k_pci *ab_pci)
+{
+	struct msi_desc *msi_desc;
+
+	msi_desc = irq_get_msi_desc(ab_pci->pdev->irq);
+	if (!msi_desc) {
+		ath12k_err(ab_pci->ab, "msi_desc is NULL!\n");
+		pci_free_irq_vectors(ab_pci->pdev);
+		return -EINVAL;
+	}
+
+	ab_pci->msi_ep_base_data = msi_desc->msg.data;
+
+	ath12k_dbg(ab_pci->ab, ATH12K_DBG_PCI, "pci after request_irq msi_ep_base_data %d\n",
+		   ab_pci->msi_ep_base_data);
+
+	return 0;
+}
+
 static int ath12k_pci_claim(struct ath12k_pci *ab_pci, struct pci_dev *pdev)
 {
 	struct ath12k_base *ab = ab_pci->ab;
@@ -891,11 +992,11 @@ int ath12k_pci_get_user_msi_assignment(struct ath12k_base *ab, char *user_name,
 	for (idx = 0; idx < msi_config->total_users; idx++) {
 		if (strcmp(user_name, msi_config->users[idx].name) == 0) {
 			*num_vectors = msi_config->users[idx].num_vectors;
-			*user_base_data = msi_config->users[idx].base_vector
-				+ ab_pci->msi_ep_base_data;
-			*base_vector = msi_config->users[idx].base_vector;
+			*base_vector =  msi_config->users[idx].base_vector;
+			*user_base_data = *base_vector + ab_pci->msi_ep_base_data;
 
-			ath12k_dbg(ab, ATH12K_DBG_PCI, "Assign MSI to user: %s, num_vectors: %d, user_base_data: %u, base_vector: %u\n",
+			ath12k_dbg(ab, ATH12K_DBG_PCI,
+				   "Assign MSI to user: %s, num_vectors: %d, user_base_data: %u, base_vector: %u\n",
 				   user_name, *num_vectors, *user_base_data,
 				   *base_vector);
 
@@ -956,6 +1057,8 @@ void ath12k_pci_ext_irq_enable(struct ath12k_base *ab)
 {
 	int i;
 
+	set_bit(ATH12K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags);
+
 	for (i = 0; i < ATH12K_EXT_IRQ_GRP_NUM_MAX; i++) {
 		struct ath12k_ext_irq_grp *irq_grp = &ab->ext_irq_grp[i];
 
@@ -1000,7 +1103,10 @@ int ath12k_pci_start(struct ath12k_base *ab)
 
 	set_bit(ATH12K_PCI_FLAG_INIT_DONE, &ab_pci->flags);
 
-	ath12k_pci_aspm_restore(ab_pci);
+	if (test_bit(ATH12K_PCI_FLAG_MULTI_MSI_VECTORS, &ab_pci->flags))
+		ath12k_pci_aspm_restore(ab_pci);
+	else
+		ath12k_info(ab, "leaving PCI ASPM disabled to avoid MHI M2 problems\n");
 
 	ath12k_pci_ce_irqs_enable(ab);
 	ath12k_ce_rx_post_buf(ab);
@@ -1262,10 +1368,16 @@ static int ath12k_pci_probe(struct pci_dev *pdev,
 	if (ret)
 		goto err_pci_msi_free;
 
+	ret = ath12k_pci_set_irq_affinity_hint(ab_pci, cpumask_of(0));
+	if (ret) {
+		ath12k_err(ab, "failed to set irq affinity %d\n", ret);
+		goto err_pci_msi_free;
+	}
+
 	ret = ath12k_mhi_register(ab_pci);
 	if (ret) {
 		ath12k_err(ab, "failed to register mhi: %d\n", ret);
-		goto err_pci_msi_free;
+		goto err_irq_affinity_cleanup;
 	}
 
 	ret = ath12k_hal_srng_init(ab);
@@ -1286,6 +1398,17 @@ static int ath12k_pci_probe(struct pci_dev *pdev,
 		goto err_ce_free;
 	}
 
+	/* kernel may allocate a dummy vector before request_irq and
+	 * then allocate a real vector when request_irq is called.
+	 * So get msi_data here again to avoid spurious interrupt
+	 * as msi_data will configured to srngs.
+	 */
+	ret = ath12k_pci_config_msi_data(ab_pci);
+	if (ret) {
+		ath12k_err(ab, "failed to config msi_data: %d\n", ret);
+		goto err_free_irq;
+	}
+
 	ret = ath12k_core_init(ab);
 	if (ret) {
 		ath12k_err(ab, "failed to init core: %d\n", ret);
@@ -1308,6 +1431,9 @@ err_mhi_unregister:
 err_pci_msi_free:
 	ath12k_pci_msi_free(ab_pci);
 
+err_irq_affinity_cleanup:
+	ath12k_pci_set_irq_affinity_hint(ab_pci, NULL);
+
 err_pci_free_region:
 	ath12k_pci_free_region(ab_pci);
 
@@ -1322,6 +1448,8 @@ static void ath12k_pci_remove(struct pci_dev *pdev)
 	struct ath12k_base *ab = pci_get_drvdata(pdev);
 	struct ath12k_pci *ab_pci = ath12k_pci_priv(ab);
 
+	ath12k_pci_set_irq_affinity_hint(ab_pci, NULL);
+
 	if (test_bit(ATH12K_FLAG_QMI_FAIL, &ab->dev_flags)) {
 		ath12k_pci_power_down(ab);
 		ath12k_qmi_deinit_service(ab);
@@ -1348,7 +1476,9 @@ qmi_fail:
 static void ath12k_pci_shutdown(struct pci_dev *pdev)
 {
 	struct ath12k_base *ab = pci_get_drvdata(pdev);
+	struct ath12k_pci *ab_pci = ath12k_pci_priv(ab);
 
+	ath12k_pci_set_irq_affinity_hint(ab_pci, NULL);
 	ath12k_pci_power_down(ab);
 }
 
diff --git a/drivers/net/wireless/ath/ath12k/pci.h b/drivers/net/wireless/ath/ath12k/pci.h
index 0f24fd9395cd..b2edf32ada20 100644
--- a/drivers/net/wireless/ath/ath12k/pci.h
+++ b/drivers/net/wireless/ath/ath12k/pci.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2019-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #ifndef ATH12K_PCI_H
 #define ATH12K_PCI_H
@@ -84,6 +84,7 @@ enum ath12k_pci_flags {
 	ATH12K_PCI_FLAG_INIT_DONE,
 	ATH12K_PCI_FLAG_IS_MSI_64,
 	ATH12K_PCI_ASPM_RESTORE,
+	ATH12K_PCI_FLAG_MULTI_MSI_VECTORS,
 };
 
 struct ath12k_pci_ops {
@@ -108,6 +109,7 @@ struct ath12k_pci {
 	/* enum ath12k_pci_flags */
 	unsigned long flags;
 	u16 link_ctl;
+	unsigned long irq_flags;
 	const struct ath12k_pci_ops *pci_ops;
 };
 
diff --git a/drivers/net/wireless/ath/ath12k/peer.h b/drivers/net/wireless/ath/ath12k/peer.h
index c6edb24cbedd..7b3500b5c8c2 100644
--- a/drivers/net/wireless/ath/ath12k/peer.h
+++ b/drivers/net/wireless/ath/ath12k/peer.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_PEER_H
diff --git a/drivers/net/wireless/ath/ath12k/qmi.c b/drivers/net/wireless/ath/ath12k/qmi.c
index f6e949c618d0..77a132f6bbd1 100644
--- a/drivers/net/wireless/ath/ath12k/qmi.c
+++ b/drivers/net/wireless/ath/ath12k/qmi.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/elf.h>
diff --git a/drivers/net/wireless/ath/ath12k/qmi.h b/drivers/net/wireless/ath/ath12k/qmi.h
index e20d6511d1ca..e25bbaa125e8 100644
--- a/drivers/net/wireless/ath/ath12k/qmi.h
+++ b/drivers/net/wireless/ath/ath12k/qmi.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_QMI_H
diff --git a/drivers/net/wireless/ath/ath12k/reg.c b/drivers/net/wireless/ath/ath12k/reg.c
index 5c006256c82a..f924bc13ccff 100644
--- a/drivers/net/wireless/ath/ath12k/reg.c
+++ b/drivers/net/wireless/ath/ath12k/reg.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #include <linux/rtnetlink.h>
 #include "core.h"
@@ -28,11 +28,11 @@ static const struct ieee80211_regdomain ath12k_world_regd = {
 	}
 };
 
-static bool ath12k_regdom_changes(struct ath12k *ar, char *alpha2)
+static bool ath12k_regdom_changes(struct ieee80211_hw *hw, char *alpha2)
 {
 	const struct ieee80211_regdomain *regd;
 
-	regd = rcu_dereference_rtnl(ar->hw->wiphy->regd);
+	regd = rcu_dereference_rtnl(hw->wiphy->regd);
 	/* This can happen during wiphy registration where the previous
 	 * user request is received before we update the regd received
 	 * from firmware.
@@ -71,7 +71,7 @@ ath12k_reg_notifier(struct wiphy *wiphy, struct regulatory_request *request)
 		return;
 	}
 
-	if (!ath12k_regdom_changes(ar, request->alpha2)) {
+	if (!ath12k_regdom_changes(hw, request->alpha2)) {
 		ath12k_dbg(ar->ab, ATH12K_DBG_REG, "Country is already set\n");
 		return;
 	}
@@ -199,6 +199,7 @@ static void ath12k_copy_regd(struct ieee80211_regdomain *regd_orig,
 
 int ath12k_regd_update(struct ath12k *ar, bool init)
 {
+	struct ieee80211_hw *hw = ar->hw;
 	struct ieee80211_regdomain *regd, *regd_copy = NULL;
 	int ret, regd_len, pdev_id;
 	struct ath12k_base *ab;
@@ -246,9 +247,9 @@ int ath12k_regd_update(struct ath12k *ar, bool init)
 	}
 
 	rtnl_lock();
-	wiphy_lock(ar->hw->wiphy);
-	ret = regulatory_set_wiphy_regd_sync(ar->hw->wiphy, regd_copy);
-	wiphy_unlock(ar->hw->wiphy);
+	wiphy_lock(hw->wiphy);
+	ret = regulatory_set_wiphy_regd_sync(hw->wiphy, regd_copy);
+	wiphy_unlock(hw->wiphy);
 	rtnl_unlock();
 
 	kfree(regd_copy);
@@ -729,10 +730,10 @@ void ath12k_regd_update_work(struct work_struct *work)
 	}
 }
 
-void ath12k_reg_init(struct ath12k *ar)
+void ath12k_reg_init(struct ieee80211_hw *hw)
 {
-	ar->hw->wiphy->regulatory_flags = REGULATORY_WIPHY_SELF_MANAGED;
-	ar->hw->wiphy->reg_notifier = ath12k_reg_notifier;
+	hw->wiphy->regulatory_flags = REGULATORY_WIPHY_SELF_MANAGED;
+	hw->wiphy->reg_notifier = ath12k_reg_notifier;
 }
 
 void ath12k_reg_free(struct ath12k_base *ab)
diff --git a/drivers/net/wireless/ath/ath12k/reg.h b/drivers/net/wireless/ath/ath12k/reg.h
index 35569f03042d..29c7ec3260da 100644
--- a/drivers/net/wireless/ath/ath12k/reg.h
+++ b/drivers/net/wireless/ath/ath12k/reg.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2019-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_REG_H
@@ -89,7 +89,7 @@ enum ath12k_reg_phy_bitmap {
 	ATH12K_REG_PHY_BITMAP_NO11BE	= BIT(6),
 };
 
-void ath12k_reg_init(struct ath12k *ar);
+void ath12k_reg_init(struct ieee80211_hw *hw);
 void ath12k_reg_free(struct ath12k_base *ab);
 void ath12k_regd_update_work(struct work_struct *work);
 struct ieee80211_regdomain *ath12k_reg_build_regd(struct ath12k_base *ab,
diff --git a/drivers/net/wireless/ath/ath12k/rx_desc.h b/drivers/net/wireless/ath/ath12k/rx_desc.h
index c4058abc516e..55f20c446ca9 100644
--- a/drivers/net/wireless/ath/ath12k/rx_desc.h
+++ b/drivers/net/wireless/ath/ath12k/rx_desc.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #ifndef ATH12K_RX_DESC_H
 #define ATH12K_RX_DESC_H
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 0e5bf5ce8d4c..11cc3005c0f9 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #include <linux/skbuff.h>
 #include <linux/ctype.h>
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 629373d67421..06e5b9b4049b 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_WMI_H
@@ -1146,25 +1146,27 @@ enum wmi_tlv_vdev_param {
 };
 
 enum wmi_tlv_peer_flags {
-	WMI_TLV_PEER_AUTH = 0x00000001,
-	WMI_TLV_PEER_QOS = 0x00000002,
-	WMI_TLV_PEER_NEED_PTK_4_WAY = 0x00000004,
-	WMI_TLV_PEER_NEED_GTK_2_WAY = 0x00000010,
-	WMI_TLV_PEER_APSD = 0x00000800,
-	WMI_TLV_PEER_HT = 0x00001000,
-	WMI_TLV_PEER_40MHZ = 0x00002000,
-	WMI_TLV_PEER_STBC = 0x00008000,
-	WMI_TLV_PEER_LDPC = 0x00010000,
-	WMI_TLV_PEER_DYN_MIMOPS = 0x00020000,
-	WMI_TLV_PEER_STATIC_MIMOPS = 0x00040000,
-	WMI_TLV_PEER_SPATIAL_MUX = 0x00200000,
-	WMI_TLV_PEER_VHT = 0x02000000,
-	WMI_TLV_PEER_80MHZ = 0x04000000,
-	WMI_TLV_PEER_PMF = 0x08000000,
+	WMI_PEER_AUTH		= 0x00000001,
+	WMI_PEER_QOS		= 0x00000002,
+	WMI_PEER_NEED_PTK_4_WAY	= 0x00000004,
+	WMI_PEER_NEED_GTK_2_WAY	= 0x00000010,
+	WMI_PEER_HE		= 0x00000400,
+	WMI_PEER_APSD		= 0x00000800,
+	WMI_PEER_HT		= 0x00001000,
+	WMI_PEER_40MHZ		= 0x00002000,
+	WMI_PEER_STBC		= 0x00008000,
+	WMI_PEER_LDPC		= 0x00010000,
+	WMI_PEER_DYN_MIMOPS	= 0x00020000,
+	WMI_PEER_STATIC_MIMOPS	= 0x00040000,
+	WMI_PEER_SPATIAL_MUX	= 0x00200000,
+	WMI_PEER_TWT_REQ	= 0x00400000,
+	WMI_PEER_TWT_RESP	= 0x00800000,
+	WMI_PEER_VHT		= 0x02000000,
+	WMI_PEER_80MHZ		= 0x04000000,
+	WMI_PEER_PMF		= 0x08000000,
 	WMI_PEER_IS_P2P_CAPABLE = 0x20000000,
 	WMI_PEER_160MHZ         = 0x40000000,
 	WMI_PEER_SAFEMODE_EN    = 0x80000000,
-
 };
 
 enum wmi_tlv_peer_flags_ext {
@@ -2220,6 +2222,7 @@ enum wmi_peer_chwidth {
 	WMI_PEER_CHWIDTH_40MHZ = 1,
 	WMI_PEER_CHWIDTH_80MHZ = 2,
 	WMI_PEER_CHWIDTH_160MHZ = 3,
+	WMI_PEER_CHWIDTH_320MHZ = 4,
 };
 
 enum wmi_beacon_gen_mode {
@@ -3844,31 +3847,6 @@ struct wmi_unit_test_cmd {
 
 #define MAX_SUPPORTED_RATES 128
 
-#define WMI_PEER_AUTH		0x00000001
-#define WMI_PEER_QOS		0x00000002
-#define WMI_PEER_NEED_PTK_4_WAY	0x00000004
-#define WMI_PEER_NEED_GTK_2_WAY	0x00000010
-#define WMI_PEER_HE		0x00000400
-#define WMI_PEER_APSD		0x00000800
-#define WMI_PEER_HT		0x00001000
-#define WMI_PEER_40MHZ		0x00002000
-#define WMI_PEER_STBC		0x00008000
-#define WMI_PEER_LDPC		0x00010000
-#define WMI_PEER_DYN_MIMOPS	0x00020000
-#define WMI_PEER_STATIC_MIMOPS	0x00040000
-#define WMI_PEER_SPATIAL_MUX	0x00200000
-#define WMI_PEER_TWT_REQ	0x00400000
-#define WMI_PEER_TWT_RESP	0x00800000
-#define WMI_PEER_VHT		0x02000000
-#define WMI_PEER_80MHZ		0x04000000
-#define WMI_PEER_PMF		0x08000000
-/* TODO: Place holder for WLAN_PEER_F_PS_PRESEND_REQUIRED = 0x10000000.
- * Need to be cleaned up
- */
-#define WMI_PEER_IS_P2P_CAPABLE	0x20000000
-#define WMI_PEER_160MHZ		0x40000000
-#define WMI_PEER_SAFEMODE_EN	0x80000000
-
 struct ath12k_wmi_vht_rate_set_params {
 	__le32 tlv_header;
 	__le32 rx_max_rate;
@@ -4770,7 +4748,6 @@ struct wmi_probe_tmpl_cmd {
 struct ath12k_wmi_pdev {
 	struct ath12k_wmi_base *wmi_ab;
 	enum ath12k_htc_ep_id eid;
-	const struct wmi_peer_flags_map *peer_flags;
 	u32 rx_decap_mode;
 };
 
@@ -4784,7 +4761,6 @@ struct ath12k_wmi_base {
 	struct completion unified_ready;
 	DECLARE_BITMAP(svc_map, WMI_MAX_EXT2_SERVICE);
 	wait_queue_head_t tx_credits_wq;
-	const struct wmi_peer_flags_map *peer_flags;
 	u32 num_mem_chunks;
 	u32 rx_decap_mode;
 	struct ath12k_wmi_host_mem_chunk_arg mem_chunks[WMI_MAX_MEM_REQS];
diff --git a/drivers/net/wireless/ath/ath5k/ahb.c b/drivers/net/wireless/ath/ath5k/ahb.c
index 08bd5d3b00f1..f27308ccb2f1 100644
--- a/drivers/net/wireless/ath/ath5k/ahb.c
+++ b/drivers/net/wireless/ath/ath5k/ahb.c
@@ -185,7 +185,7 @@ static int ath_ahb_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int ath_ahb_remove(struct platform_device *pdev)
+static void ath_ahb_remove(struct platform_device *pdev)
 {
 	struct ar231x_board_config *bcfg = dev_get_platdata(&pdev->dev);
 	struct ieee80211_hw *hw = platform_get_drvdata(pdev);
@@ -193,7 +193,7 @@ static int ath_ahb_remove(struct platform_device *pdev)
 	u32 reg;
 
 	if (!hw)
-		return 0;
+		return;
 
 	ah = hw->priv;
 
@@ -215,13 +215,11 @@ static int ath_ahb_remove(struct platform_device *pdev)
 	ath5k_deinit_ah(ah);
 	iounmap(ah->iobase);
 	ieee80211_free_hw(hw);
-
-	return 0;
 }
 
 static struct platform_driver ath_ahb_driver = {
 	.probe      = ath_ahb_probe,
-	.remove     = ath_ahb_remove,
+	.remove_new = ath_ahb_remove,
 	.driver		= {
 		.name	= "ar231x-wmac",
 	},
diff --git a/drivers/net/wireless/ath/ath5k/eeprom.h b/drivers/net/wireless/ath/ath5k/eeprom.h
index 693296ee9693..e85b713950b1 100644
--- a/drivers/net/wireless/ath/ath5k/eeprom.h
+++ b/drivers/net/wireless/ath/ath5k/eeprom.h
@@ -489,7 +489,4 @@ struct ath5k_eeprom_info {
 
 	/* Spur mitigation data (fbin values for spur channels) */
 	u16	ee_spur_chans[AR5K_EEPROM_N_SPUR_CHANS][AR5K_EEPROM_N_FREQ_BANDS];
-
-	/* Antenna raw switch tables */
-	u32	ee_antenna[AR5K_EEPROM_N_MODES][AR5K_ANT_MAX];
 };
diff --git a/drivers/net/wireless/ath/ath9k/Kconfig b/drivers/net/wireless/ath/ath9k/Kconfig
index e150d82eddb6..0c47be06c153 100644
--- a/drivers/net/wireless/ath/ath9k/Kconfig
+++ b/drivers/net/wireless/ath/ath9k/Kconfig
@@ -57,8 +57,7 @@ config ATH9K_AHB
 
 config ATH9K_DEBUGFS
 	bool "Atheros ath9k debugging"
-	depends on ATH9K && DEBUG_FS
-	select MAC80211_DEBUGFS
+	depends on ATH9K && DEBUG_FS && MAC80211_DEBUGFS
 	select ATH9K_COMMON_DEBUG
 	help
 	  Say Y, if you need access to ath9k's statistics for
@@ -70,7 +69,6 @@ config ATH9K_DEBUGFS
 config ATH9K_STATION_STATISTICS
 	bool "Detailed station statistics"
 	depends on ATH9K && ATH9K_DEBUGFS && DEBUG_FS
-	select MAC80211_DEBUGFS
 	default n
 	help
 	  This option enables detailed statistics for association stations.
diff --git a/drivers/net/wireless/ath/ath9k/ath9k_pci_owl_loader.c b/drivers/net/wireless/ath/ath9k/ath9k_pci_owl_loader.c
index 708c8969b503..a5eb43f30320 100644
--- a/drivers/net/wireless/ath/ath9k/ath9k_pci_owl_loader.c
+++ b/drivers/net/wireless/ath/ath9k/ath9k_pci_owl_loader.c
@@ -125,7 +125,7 @@ static void owl_rescan(struct pci_dev *pdev)
 
 static void owl_fw_cb(const struct firmware *fw, void *context)
 {
-	struct owl_ctx *ctx = (struct owl_ctx *)context;
+	struct owl_ctx *ctx = context;
 
 	complete(&ctx->eeprom_load);
 
diff --git a/drivers/net/wireless/ath/ath9k/common-init.c b/drivers/net/wireless/ath/ath9k/common-init.c
index 82de0fadbc95..7c13a1deb3ac 100644
--- a/drivers/net/wireless/ath/ath9k/common-init.c
+++ b/drivers/net/wireless/ath/ath9k/common-init.c
@@ -124,7 +124,7 @@ static struct ieee80211_rate ath9k_legacy_rates[] = {
 
 int ath9k_cmn_init_channels_rates(struct ath_common *common)
 {
-	struct ath_hw *ah = (struct ath_hw *)common->ah;
+	struct ath_hw *ah = common->ah;
 	void *channels;
 
 	BUILD_BUG_ON(ARRAY_SIZE(ath9k_2ghz_chantable) +
diff --git a/drivers/net/wireless/ath/ath9k/common-spectral.c b/drivers/net/wireless/ath/ath9k/common-spectral.c
index a5349c72c332..4b27445a5fb8 100644
--- a/drivers/net/wireless/ath/ath9k/common-spectral.c
+++ b/drivers/net/wireless/ath/ath9k/common-spectral.c
@@ -471,7 +471,7 @@ int ath_cmn_process_fft(struct ath_spec_scan_priv *spec_priv, struct ieee80211_h
 	u8 sample_buf[SPECTRAL_SAMPLE_MAX_LEN] = {0};
 	struct ath_hw *ah = spec_priv->ah;
 	struct ath_common *common = ath9k_hw_common(spec_priv->ah);
-	struct ath_softc *sc = (struct ath_softc *)common->priv;
+	struct ath_softc *sc = common->priv;
 	u8 num_bins, *vdata = (u8 *)hdr;
 	struct ath_radar_info *radar_info;
 	int len = rs->rs_datalen;
diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c
index a0376a6787b8..d84e3ee7b5d9 100644
--- a/drivers/net/wireless/ath/ath9k/debug.c
+++ b/drivers/net/wireless/ath/ath9k/debug.c
@@ -1376,7 +1376,7 @@ void ath9k_deinit_debug(struct ath_softc *sc)
 int ath9k_init_debug(struct ath_hw *ah)
 {
 	struct ath_common *common = ath9k_hw_common(ah);
-	struct ath_softc *sc = (struct ath_softc *) common->priv;
+	struct ath_softc *sc = common->priv;
 
 	sc->debug.debugfs_phy = debugfs_create_dir("ath9k",
 						   sc->hw->wiphy->debugfsdir);
diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c
index 90cfe39aa433..0c7841f95228 100644
--- a/drivers/net/wireless/ath/ath9k/hif_usb.c
+++ b/drivers/net/wireless/ath/ath9k/hif_usb.c
@@ -70,7 +70,7 @@ static int __hif_usb_tx(struct hif_device_usb *hif_dev);
 
 static void hif_usb_regout_cb(struct urb *urb)
 {
-	struct cmd_buf *cmd = (struct cmd_buf *)urb->context;
+	struct cmd_buf *cmd = urb->context;
 
 	switch (urb->status) {
 	case 0:
@@ -134,7 +134,7 @@ static int hif_usb_send_regout(struct hif_device_usb *hif_dev,
 
 static void hif_usb_mgmt_cb(struct urb *urb)
 {
-	struct cmd_buf *cmd = (struct cmd_buf *)urb->context;
+	struct cmd_buf *cmd = urb->context;
 	struct hif_device_usb *hif_dev;
 	unsigned long flags;
 	bool txok = true;
@@ -252,7 +252,7 @@ static inline void ath9k_skb_queue_complete(struct hif_device_usb *hif_dev,
 
 static void hif_usb_tx_cb(struct urb *urb)
 {
-	struct tx_buf *tx_buf = (struct tx_buf *) urb->context;
+	struct tx_buf *tx_buf = urb->context;
 	struct hif_device_usb *hif_dev;
 	bool txok = true;
 
@@ -687,7 +687,7 @@ invalid_pkt:
 
 static void ath9k_hif_usb_rx_cb(struct urb *urb)
 {
-	struct rx_buf *rx_buf = (struct rx_buf *)urb->context;
+	struct rx_buf *rx_buf = urb->context;
 	struct hif_device_usb *hif_dev = rx_buf->hif_dev;
 	struct sk_buff *skb = rx_buf->skb;
 	int ret;
@@ -734,7 +734,7 @@ free:
 
 static void ath9k_hif_usb_reg_in_cb(struct urb *urb)
 {
-	struct rx_buf *rx_buf = (struct rx_buf *)urb->context;
+	struct rx_buf *rx_buf = urb->context;
 	struct hif_device_usb *hif_dev = rx_buf->hif_dev;
 	struct sk_buff *skb = rx_buf->skb;
 	int ret;
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
index 278ddc713fdc..f7c6d9bc9311 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
@@ -482,7 +482,7 @@ void ath9k_htc_deinit_debug(struct ath9k_htc_priv *priv)
 int ath9k_htc_init_debug(struct ath_hw *ah)
 {
 	struct ath_common *common = ath9k_hw_common(ah);
-	struct ath9k_htc_priv *priv = (struct ath9k_htc_priv *) common->priv;
+	struct ath9k_htc_priv *priv = common->priv;
 
 	priv->debug.debugfs_phy = debugfs_create_dir(KBUILD_MODNAME,
 					     priv->hw->wiphy->debugfsdir);
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
index dae3d9c7b640..0aa5bdeb44a1 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
@@ -63,12 +63,12 @@ static const struct ieee80211_tpt_blink ath9k_htc_tpt_blink[] = {
 
 static void ath9k_htc_op_ps_wakeup(struct ath_common *common)
 {
-	ath9k_htc_ps_wakeup((struct ath9k_htc_priv *) common->priv);
+	ath9k_htc_ps_wakeup(common->priv);
 }
 
 static void ath9k_htc_op_ps_restore(struct ath_common *common)
 {
-	ath9k_htc_ps_restore((struct ath9k_htc_priv *) common->priv);
+	ath9k_htc_ps_restore(common->priv);
 }
 
 static const struct ath_ps_ops ath9k_htc_ps_ops = {
@@ -235,7 +235,7 @@ static unsigned int ath9k_regread(void *hw_priv, u32 reg_offset)
 {
 	struct ath_hw *ah = hw_priv;
 	struct ath_common *common = ath9k_hw_common(ah);
-	struct ath9k_htc_priv *priv = (struct ath9k_htc_priv *) common->priv;
+	struct ath9k_htc_priv *priv = common->priv;
 	__be32 val, reg = cpu_to_be32(reg_offset);
 	int r;
 
@@ -257,7 +257,7 @@ static void ath9k_multi_regread(void *hw_priv, u32 *addr,
 {
 	struct ath_hw *ah = hw_priv;
 	struct ath_common *common = ath9k_hw_common(ah);
-	struct ath9k_htc_priv *priv = (struct ath9k_htc_priv *) common->priv;
+	struct ath9k_htc_priv *priv = common->priv;
 	__be32 tmpaddr[8];
 	__be32 tmpval[8];
 	int i, ret;
@@ -282,7 +282,7 @@ static void ath9k_multi_regread(void *hw_priv, u32 *addr,
 
 static void ath9k_regwrite_multi(struct ath_common *common)
 {
-	struct ath9k_htc_priv *priv = (struct ath9k_htc_priv *) common->priv;
+	struct ath9k_htc_priv *priv = common->priv;
 	u32 rsp_status;
 	int r;
 
@@ -303,7 +303,7 @@ static void ath9k_regwrite_single(void *hw_priv, u32 val, u32 reg_offset)
 {
 	struct ath_hw *ah = hw_priv;
 	struct ath_common *common = ath9k_hw_common(ah);
-	struct ath9k_htc_priv *priv = (struct ath9k_htc_priv *) common->priv;
+	struct ath9k_htc_priv *priv = common->priv;
 	const __be32 buf[2] = {
 		cpu_to_be32(reg_offset),
 		cpu_to_be32(val),
@@ -324,7 +324,7 @@ static void ath9k_regwrite_buffer(void *hw_priv, u32 val, u32 reg_offset)
 {
 	struct ath_hw *ah = hw_priv;
 	struct ath_common *common = ath9k_hw_common(ah);
-	struct ath9k_htc_priv *priv = (struct ath9k_htc_priv *) common->priv;
+	struct ath9k_htc_priv *priv = common->priv;
 
 	mutex_lock(&priv->wmi->multi_write_mutex);
 
@@ -347,7 +347,7 @@ static void ath9k_regwrite(void *hw_priv, u32 val, u32 reg_offset)
 {
 	struct ath_hw *ah = hw_priv;
 	struct ath_common *common = ath9k_hw_common(ah);
-	struct ath9k_htc_priv *priv = (struct ath9k_htc_priv *) common->priv;
+	struct ath9k_htc_priv *priv = common->priv;
 
 	if (atomic_read(&priv->wmi->mwrite_cnt))
 		ath9k_regwrite_buffer(hw_priv, val, reg_offset);
@@ -359,7 +359,7 @@ static void ath9k_enable_regwrite_buffer(void *hw_priv)
 {
 	struct ath_hw *ah = hw_priv;
 	struct ath_common *common = ath9k_hw_common(ah);
-	struct ath9k_htc_priv *priv = (struct ath9k_htc_priv *) common->priv;
+	struct ath9k_htc_priv *priv = common->priv;
 
 	atomic_inc(&priv->wmi->mwrite_cnt);
 }
@@ -368,7 +368,7 @@ static void ath9k_regwrite_flush(void *hw_priv)
 {
 	struct ath_hw *ah = hw_priv;
 	struct ath_common *common = ath9k_hw_common(ah);
-	struct ath9k_htc_priv *priv = (struct ath9k_htc_priv *) common->priv;
+	struct ath9k_htc_priv *priv = common->priv;
 
 	atomic_dec(&priv->wmi->mwrite_cnt);
 
@@ -385,7 +385,7 @@ static void ath9k_reg_rmw_buffer(void *hw_priv,
 {
 	struct ath_hw *ah = hw_priv;
 	struct ath_common *common = ath9k_hw_common(ah);
-	struct ath9k_htc_priv *priv = (struct ath9k_htc_priv *) common->priv;
+	struct ath9k_htc_priv *priv = common->priv;
 	u32 rsp_status;
 	int r;
 
@@ -423,7 +423,7 @@ static void ath9k_reg_rmw_flush(void *hw_priv)
 {
 	struct ath_hw *ah = hw_priv;
 	struct ath_common *common = ath9k_hw_common(ah);
-	struct ath9k_htc_priv *priv = (struct ath9k_htc_priv *) common->priv;
+	struct ath9k_htc_priv *priv = common->priv;
 	u32 rsp_status;
 	int r;
 
@@ -455,7 +455,7 @@ static void ath9k_enable_rmw_buffer(void *hw_priv)
 {
 	struct ath_hw *ah = hw_priv;
 	struct ath_common *common = ath9k_hw_common(ah);
-	struct ath9k_htc_priv *priv = (struct ath9k_htc_priv *) common->priv;
+	struct ath9k_htc_priv *priv = common->priv;
 
 	if (test_bit(HTC_FWFLAG_NO_RMW, &priv->fw_flags))
 		return;
@@ -468,7 +468,7 @@ static void ath9k_reg_rmw_single(void *hw_priv,
 {
 	struct ath_hw *ah = hw_priv;
 	struct ath_common *common = ath9k_hw_common(ah);
-	struct ath9k_htc_priv *priv = (struct ath9k_htc_priv *) common->priv;
+	struct ath9k_htc_priv *priv = common->priv;
 	struct register_rmw buf, buf_ret;
 	int ret;
 
@@ -490,7 +490,7 @@ static u32 ath9k_reg_rmw(void *hw_priv, u32 reg_offset, u32 set, u32 clr)
 {
 	struct ath_hw *ah = hw_priv;
 	struct ath_common *common = ath9k_hw_common(ah);
-	struct ath9k_htc_priv *priv = (struct ath9k_htc_priv *) common->priv;
+	struct ath9k_htc_priv *priv = common->priv;
 
 	if (test_bit(HTC_FWFLAG_NO_RMW, &priv->fw_flags)) {
 		u32 val;
@@ -518,7 +518,7 @@ static void ath_usb_read_cachesize(struct ath_common *common, int *csz)
 
 static bool ath_usb_eeprom_read(struct ath_common *common, u32 off, u16 *data)
 {
-	struct ath_hw *ah = (struct ath_hw *) common->ah;
+	struct ath_hw *ah = common->ah;
 
 	(void)REG_READ(ah, AR5416_EEPROM_OFFSET + (off << AR5416_EEPROM_S));
 
@@ -970,7 +970,7 @@ int ath9k_htc_probe_device(struct htc_target *htc_handle, struct device *dev,
 
 err_init:
 	ath9k_stop_wmi(priv);
-	hif_dev = (struct hif_device_usb *)htc_handle->hif_dev;
+	hif_dev = htc_handle->hif_dev;
 	ath9k_hif_usb_dealloc_urbs(hif_dev);
 	ath9k_destroy_wmi(priv);
 err_free:
@@ -988,7 +988,7 @@ void ath9k_htc_disconnect_device(struct htc_target *htc_handle, bool hotunplug)
 
 		ath9k_deinit_device(htc_handle->drv_priv);
 		ath9k_stop_wmi(htc_handle->drv_priv);
-		ath9k_hif_usb_dealloc_urbs((struct hif_device_usb *)htc_handle->hif_dev);
+		ath9k_hif_usb_dealloc_urbs(htc_handle->hif_dev);
 		ath9k_destroy_wmi(htc_handle->drv_priv);
 		ieee80211_free_hw(htc_handle->drv_priv->hw);
 	}
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
index 800177021baf..efcaeccb055a 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
@@ -652,9 +652,10 @@ void ath9k_htc_txstatus(struct ath9k_htc_priv *priv, void *wmi_event)
 	struct ath9k_htc_tx_event *tx_pend;
 	int i;
 
-	for (i = 0; i < txs->cnt; i++) {
-		WARN_ON(txs->cnt > HTC_MAX_TX_STATUS);
+	if (WARN_ON_ONCE(txs->cnt > HTC_MAX_TX_STATUS))
+		return;
 
+	for (i = 0; i < txs->cnt; i++) {
 		__txs = &txs->txstatus[i];
 
 		skb = ath9k_htc_tx_get_packet(priv, __txs);
diff --git a/drivers/net/wireless/ath/ath9k/htc_hst.c b/drivers/net/wireless/ath/ath9k/htc_hst.c
index 99667aba289d..eb631fd3336d 100644
--- a/drivers/net/wireless/ath/ath9k/htc_hst.c
+++ b/drivers/net/wireless/ath/ath9k/htc_hst.c
@@ -89,7 +89,7 @@ static void htc_process_target_rdy(struct htc_target *target,
 				   void *buf)
 {
 	struct htc_endpoint *endpoint;
-	struct htc_ready_msg *htc_ready_msg = (struct htc_ready_msg *) buf;
+	struct htc_ready_msg *htc_ready_msg = buf;
 
 	target->credit_size = be16_to_cpu(htc_ready_msg->credit_size);
 
diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c
index 4f00400c7ffb..7fad7e75af6a 100644
--- a/drivers/net/wireless/ath/ath9k/init.c
+++ b/drivers/net/wireless/ath/ath9k/init.c
@@ -151,12 +151,12 @@ static void ath9k_deinit_softc(struct ath_softc *sc);
 
 static void ath9k_op_ps_wakeup(struct ath_common *common)
 {
-	ath9k_ps_wakeup((struct ath_softc *) common->priv);
+	ath9k_ps_wakeup(common->priv);
 }
 
 static void ath9k_op_ps_restore(struct ath_common *common)
 {
-	ath9k_ps_restore((struct ath_softc *) common->priv);
+	ath9k_ps_restore(common->priv);
 }
 
 static const struct ath_ps_ops ath9k_ps_ops = {
@@ -174,7 +174,7 @@ static void ath9k_iowrite32(void *hw_priv, u32 val, u32 reg_offset)
 {
 	struct ath_hw *ah = hw_priv;
 	struct ath_common *common = ath9k_hw_common(ah);
-	struct ath_softc *sc = (struct ath_softc *) common->priv;
+	struct ath_softc *sc = common->priv;
 
 	if (NR_CPUS > 1 && ah->config.serialize_regmode == SER_REG_MODE_ON) {
 		unsigned long flags;
@@ -189,7 +189,7 @@ static unsigned int ath9k_ioread32(void *hw_priv, u32 reg_offset)
 {
 	struct ath_hw *ah = hw_priv;
 	struct ath_common *common = ath9k_hw_common(ah);
-	struct ath_softc *sc = (struct ath_softc *) common->priv;
+	struct ath_softc *sc = common->priv;
 	u32 val;
 
 	if (NR_CPUS > 1 && ah->config.serialize_regmode == SER_REG_MODE_ON) {
@@ -229,7 +229,7 @@ static unsigned int ath9k_reg_rmw(void *hw_priv, u32 reg_offset, u32 set, u32 cl
 {
 	struct ath_hw *ah = hw_priv;
 	struct ath_common *common = ath9k_hw_common(ah);
-	struct ath_softc *sc = (struct ath_softc *) common->priv;
+	struct ath_softc *sc = common->priv;
 	unsigned long flags;
 	u32 val;
 
@@ -608,7 +608,7 @@ static int ath9k_nvmem_request_eeprom(struct ath_softc *sc)
 	}
 
 	/* devres manages the calibration values release on shutdown */
-	ah->nvmem_blob = (u16 *)devm_kmemdup(sc->dev, buf, len, GFP_KERNEL);
+	ah->nvmem_blob = devm_kmemdup(sc->dev, buf, len, GFP_KERNEL);
 	kfree(buf);
 	if (!ah->nvmem_blob)
 		return -ENOMEM;
diff --git a/drivers/net/wireless/ath/ath9k/link.c b/drivers/net/wireless/ath/ath9k/link.c
index 9d84003db800..d1e5767aab3c 100644
--- a/drivers/net/wireless/ath/ath9k/link.c
+++ b/drivers/net/wireless/ath/ath9k/link.c
@@ -304,7 +304,7 @@ fail_paprd:
 void ath_ani_calibrate(struct timer_list *t)
 {
 	struct ath_common *common = from_timer(common, t, ani.timer);
-	struct ath_softc *sc = (struct ath_softc *)common->priv;
+	struct ath_softc *sc = common->priv;
 	struct ath_hw *ah = sc->sc_ah;
 	bool longcal = false;
 	bool shortcal = false;
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index 1494feedb27d..c48ff0ffbfef 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -2383,7 +2383,22 @@ static void ath9k_sw_scan_start(struct ieee80211_hw *hw,
 {
 	struct ath_softc *sc = hw->priv;
 	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
+	struct cfg80211_chan_def *chandef = &sc->cur_chan->chandef;
+	struct ieee80211_channel *chan = chandef->chan;
+	int pos = chan->hw_value;
 	set_bit(ATH_OP_SCANNING, &common->op_flags);
+
+	/* Reset current survey */
+	if (!sc->cur_chan->offchannel) {
+		if (sc->cur_survey != &sc->survey[pos]) {
+			if (sc->cur_survey)
+				sc->cur_survey->filled &= ~SURVEY_INFO_IN_USE;
+			sc->cur_survey = &sc->survey[pos];
+		}
+
+		memset(sc->cur_survey, 0, sizeof(struct survey_info));
+		sc->cur_survey->filled |= SURVEY_INFO_IN_USE;
+	}
 }
 
 static void ath9k_sw_scan_complete(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/ath/ath9k/pci.c b/drivers/net/wireless/ath/ath9k/pci.c
index 0633589b85c2..e655cd8bbf94 100644
--- a/drivers/net/wireless/ath/ath9k/pci.c
+++ b/drivers/net/wireless/ath/ath9k/pci.c
@@ -781,7 +781,7 @@ static const struct pci_device_id ath_pci_id_table[] = {
 /* return bus cachesize in 4B word units */
 static void ath_pci_read_cachesize(struct ath_common *common, int *csz)
 {
-	struct ath_softc *sc = (struct ath_softc *) common->priv;
+	struct ath_softc *sc = common->priv;
 	u8 u8tmp;
 
 	pci_read_config_byte(to_pci_dev(sc->dev), PCI_CACHE_LINE_SIZE, &u8tmp);
@@ -799,7 +799,7 @@ static void ath_pci_read_cachesize(struct ath_common *common, int *csz)
 
 static bool ath_pci_eeprom_read(struct ath_common *common, u32 off, u16 *data)
 {
-	struct ath_hw *ah = (struct ath_hw *) common->ah;
+	struct ath_hw *ah = common->ah;
 
 	common->ops->read(ah, AR5416_EEPROM_OFFSET + (off << AR5416_EEPROM_S));
 
@@ -820,7 +820,7 @@ static bool ath_pci_eeprom_read(struct ath_common *common, u32 off, u16 *data)
 /* Need to be called after we discover btcoex capabilities */
 static void ath_pci_aspm_init(struct ath_common *common)
 {
-	struct ath_softc *sc = (struct ath_softc *) common->priv;
+	struct ath_softc *sc = common->priv;
 	struct ath_hw *ah = sc->sc_ah;
 	struct pci_dev *pdev = to_pci_dev(sc->dev);
 	struct pci_dev *parent;
diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index 2bd1163177f0..41119fb177e3 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -1644,7 +1644,7 @@ out_err:
 	return ret;
 }
 
-static int wcn36xx_remove(struct platform_device *pdev)
+static void wcn36xx_remove(struct platform_device *pdev)
 {
 	struct ieee80211_hw *hw = platform_get_drvdata(pdev);
 	struct wcn36xx *wcn = hw->priv;
@@ -1666,8 +1666,6 @@ static int wcn36xx_remove(struct platform_device *pdev)
 
 	mutex_destroy(&wcn->hal_mutex);
 	ieee80211_free_hw(hw);
-
-	return 0;
 }
 
 static const struct of_device_id wcn36xx_of_match[] = {
@@ -1678,7 +1676,7 @@ MODULE_DEVICE_TABLE(of, wcn36xx_of_match);
 
 static struct platform_driver wcn36xx_driver = {
 	.probe      = wcn36xx_probe,
-	.remove     = wcn36xx_remove,
+	.remove_new = wcn36xx_remove,
 	.driver         = {
 		.name   = "wcn36xx",
 		.of_match_table = wcn36xx_of_match,
diff --git a/drivers/net/wireless/atmel/Kconfig b/drivers/net/wireless/atmel/Kconfig
index bafdd57b049a..7a2bb7a58ab7 100644
--- a/drivers/net/wireless/atmel/Kconfig
+++ b/drivers/net/wireless/atmel/Kconfig
@@ -12,41 +12,6 @@ config WLAN_VENDOR_ATMEL
 
 if WLAN_VENDOR_ATMEL
 
-config ATMEL
-	tristate "Atmel at76c50x chipset  802.11b support"
-	depends on CFG80211 && (PCI || PCMCIA) && HAS_IOPORT
-	select WIRELESS_EXT
-	select WEXT_PRIV
-	select FW_LOADER
-	select CRC32
-	help
-	  A driver 802.11b wireless cards based on the Atmel fast-vnet
-	  chips. This driver supports standard Linux wireless extensions.
-
-	  Many  cards based on this chipset do not have flash memory
-	  and need their firmware loaded at start-up. If yours is
-	  one of these, you will need to provide a firmware image
-	  to be loaded into the card by the driver. The Atmel
-	  firmware package can be downloaded from
-	  <http://www.thekelleys.org.uk/atmel>
-
-config PCI_ATMEL
-	tristate "Atmel at76c506 PCI cards"
-	depends on ATMEL && PCI
-	help
-	  Enable support for PCI and mini-PCI cards containing the
-	  Atmel at76c506 chip.
-
-config PCMCIA_ATMEL
-	tristate "Atmel at76c502/at76c504 PCMCIA cards"
-	depends on ATMEL && PCMCIA
-	select WIRELESS_EXT
-	select FW_LOADER
-	select CRC32
-	help
-	  Enable support for PCMCIA cards containing the
-	  Atmel at76c502 and at76c504 chips.
-
 config AT76C50X_USB
 	tristate "Atmel at76c503/at76c505/at76c505a USB cards"
 	depends on MAC80211 && USB
diff --git a/drivers/net/wireless/atmel/Makefile b/drivers/net/wireless/atmel/Makefile
index 17e62805677d..8338d7098ba6 100644
--- a/drivers/net/wireless/atmel/Makefile
+++ b/drivers/net/wireless/atmel/Makefile
@@ -1,6 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_ATMEL)             += atmel.o
-obj-$(CONFIG_PCI_ATMEL)         += atmel_pci.o 
-obj-$(CONFIG_PCMCIA_ATMEL)      += atmel_cs.o
-
 obj-$(CONFIG_AT76C50X_USB)      += at76c50x-usb.o
diff --git a/drivers/net/wireless/atmel/atmel.c b/drivers/net/wireless/atmel/atmel.c
deleted file mode 100644
index 461dce21de2b..000000000000
--- a/drivers/net/wireless/atmel/atmel.c
+++ /dev/null
@@ -1,4452 +0,0 @@
-/*** -*- linux-c -*- **********************************************************
-
-     Driver for Atmel at76c502 at76c504 and at76c506 wireless cards.
-
-	Copyright 2000-2001 ATMEL Corporation.
-	Copyright 2003-2004 Simon Kelley.
-
-    This code was developed from version 2.1.1 of the Atmel drivers,
-    released by Atmel corp. under the GPL in December 2002. It also
-    includes code from the Linux aironet drivers (C) Benjamin Reed,
-    and the Linux PCMCIA package, (C) David Hinds and the Linux wireless
-    extensions, (C) Jean Tourrilhes.
-
-    The firmware module for reading the MAC address of the card comes from
-    net.russotto.AtmelMACFW, written by Matthew T. Russotto and copyright
-    by him. net.russotto.AtmelMACFW is used under the GPL license version 2.
-    This file contains the module in binary form and, under the terms
-    of the GPL, in source form. The source is located at the end of the file.
-
-    This program is free software; you can redistribute it and/or modify
-    it under the terms of the GNU General Public License as published by
-    the Free Software Foundation; either version 2 of the License, or
-    (at your option) any later version.
-
-    This software is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
-
-    You should have received a copy of the GNU General Public License
-    along with Atmel wireless lan drivers; if not, see
-    <http://www.gnu.org/licenses/>.
-
-    For all queries about this code, please contact the current author,
-    Simon Kelley <simon@thekelleys.org.uk> and not Atmel Corporation.
-
-    Credit is due to HP UK and Cambridge Online Systems Ltd for supplying
-    hardware used during development of this driver.
-
-******************************************************************************/
-
-#include <linux/interrupt.h>
-
-#include <linux/kernel.h>
-#include <linux/ptrace.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/timer.h>
-#include <asm/byteorder.h>
-#include <asm/io.h>
-#include <linux/uaccess.h>
-#include <linux/module.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/skbuff.h>
-#include <linux/if_arp.h>
-#include <linux/ioport.h>
-#include <linux/fcntl.h>
-#include <linux/delay.h>
-#include <linux/wireless.h>
-#include <net/iw_handler.h>
-#include <linux/crc32.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/device.h>
-#include <linux/moduleparam.h>
-#include <linux/firmware.h>
-#include <linux/jiffies.h>
-#include <net/cfg80211.h>
-#include "atmel.h"
-
-#define DRIVER_MAJOR 0
-#define DRIVER_MINOR 98
-
-MODULE_AUTHOR("Simon Kelley");
-MODULE_DESCRIPTION("Support for Atmel at76c50x 802.11 wireless ethernet cards.");
-MODULE_LICENSE("GPL");
-
-/* The name of the firmware file to be loaded
-   over-rides any automatic selection */
-static char *firmware = NULL;
-module_param(firmware, charp, 0);
-
-/* table of firmware file names */
-static struct {
-	AtmelFWType fw_type;
-	const char *fw_file;
-	const char *fw_file_ext;
-} fw_table[] = {
-	{ ATMEL_FW_TYPE_502,		"atmel_at76c502",	"bin" },
-	{ ATMEL_FW_TYPE_502D,		"atmel_at76c502d",	"bin" },
-	{ ATMEL_FW_TYPE_502E,		"atmel_at76c502e",	"bin" },
-	{ ATMEL_FW_TYPE_502_3COM,	"atmel_at76c502_3com",	"bin" },
-	{ ATMEL_FW_TYPE_504,		"atmel_at76c504",	"bin" },
-	{ ATMEL_FW_TYPE_504_2958,	"atmel_at76c504_2958",	"bin" },
-	{ ATMEL_FW_TYPE_504A_2958,	"atmel_at76c504a_2958",	"bin" },
-	{ ATMEL_FW_TYPE_506,		"atmel_at76c506",	"bin" },
-	{ ATMEL_FW_TYPE_NONE,		NULL,			NULL }
-};
-MODULE_FIRMWARE("atmel_at76c502-wpa.bin");
-MODULE_FIRMWARE("atmel_at76c502.bin");
-MODULE_FIRMWARE("atmel_at76c502d-wpa.bin");
-MODULE_FIRMWARE("atmel_at76c502d.bin");
-MODULE_FIRMWARE("atmel_at76c502e-wpa.bin");
-MODULE_FIRMWARE("atmel_at76c502e.bin");
-MODULE_FIRMWARE("atmel_at76c502_3com-wpa.bin");
-MODULE_FIRMWARE("atmel_at76c502_3com.bin");
-MODULE_FIRMWARE("atmel_at76c504-wpa.bin");
-MODULE_FIRMWARE("atmel_at76c504.bin");
-MODULE_FIRMWARE("atmel_at76c504_2958-wpa.bin");
-MODULE_FIRMWARE("atmel_at76c504_2958.bin");
-MODULE_FIRMWARE("atmel_at76c504a_2958-wpa.bin");
-MODULE_FIRMWARE("atmel_at76c504a_2958.bin");
-MODULE_FIRMWARE("atmel_at76c506-wpa.bin");
-MODULE_FIRMWARE("atmel_at76c506.bin");
-
-#define MAX_SSID_LENGTH 32
-#define MGMT_JIFFIES (256 * HZ / 100)
-
-#define MAX_BSS_ENTRIES	64
-
-/* registers */
-#define GCR  0x00    /* (SIR0)  General Configuration Register */
-#define BSR  0x02    /* (SIR1)  Bank Switching Select Register */
-#define AR   0x04
-#define DR   0x08
-#define MR1  0x12    /* Mirror Register 1 */
-#define MR2  0x14    /* Mirror Register 2 */
-#define MR3  0x16    /* Mirror Register 3 */
-#define MR4  0x18    /* Mirror Register 4 */
-
-#define GPR1                            0x0c
-#define GPR2                            0x0e
-#define GPR3                            0x10
-/*
- * Constants for the GCR register.
- */
-#define GCR_REMAP     0x0400          /* Remap internal SRAM to 0 */
-#define GCR_SWRES     0x0080          /* BIU reset (ARM and PAI are NOT reset) */
-#define GCR_CORES     0x0060          /* Core Reset (ARM and PAI are reset) */
-#define GCR_ENINT     0x0002          /* Enable Interrupts */
-#define GCR_ACKINT    0x0008          /* Acknowledge Interrupts */
-
-#define BSS_SRAM      0x0200          /* AMBA module selection --> SRAM */
-#define BSS_IRAM      0x0100          /* AMBA module selection --> IRAM */
-/*
- *Constants for the MR registers.
- */
-#define MAC_INIT_COMPLETE       0x0001        /* MAC init has been completed */
-#define MAC_BOOT_COMPLETE       0x0010        /* MAC boot has been completed */
-#define MAC_INIT_OK             0x0002        /* MAC boot has been completed */
-
-#define MIB_MAX_DATA_BYTES    212
-#define MIB_HEADER_SIZE       4    /* first four fields */
-
-struct get_set_mib {
-	u8 type;
-	u8 size;
-	u8 index;
-	u8 reserved;
-	u8 data[MIB_MAX_DATA_BYTES];
-};
-
-struct rx_desc {
-	u32          Next;
-	u16          MsduPos;
-	u16          MsduSize;
-
-	u8           State;
-	u8           Status;
-	u8           Rate;
-	u8           Rssi;
-	u8           LinkQuality;
-	u8           PreambleType;
-	u16          Duration;
-	u32          RxTime;
-};
-
-#define RX_DESC_FLAG_VALID       0x80
-#define RX_DESC_FLAG_CONSUMED    0x40
-#define RX_DESC_FLAG_IDLE        0x00
-
-#define RX_STATUS_SUCCESS        0x00
-
-#define RX_DESC_MSDU_POS_OFFSET      4
-#define RX_DESC_MSDU_SIZE_OFFSET     6
-#define RX_DESC_FLAGS_OFFSET         8
-#define RX_DESC_STATUS_OFFSET        9
-#define RX_DESC_RSSI_OFFSET          11
-#define RX_DESC_LINK_QUALITY_OFFSET  12
-#define RX_DESC_PREAMBLE_TYPE_OFFSET 13
-#define RX_DESC_DURATION_OFFSET      14
-#define RX_DESC_RX_TIME_OFFSET       16
-
-struct tx_desc {
-	u32       NextDescriptor;
-	u16       TxStartOfFrame;
-	u16       TxLength;
-
-	u8        TxState;
-	u8        TxStatus;
-	u8        RetryCount;
-
-	u8        TxRate;
-
-	u8        KeyIndex;
-	u8        ChiperType;
-	u8        ChipreLength;
-	u8        Reserved1;
-
-	u8        Reserved;
-	u8        PacketType;
-	u16       HostTxLength;
-};
-
-#define TX_DESC_NEXT_OFFSET          0
-#define TX_DESC_POS_OFFSET           4
-#define TX_DESC_SIZE_OFFSET          6
-#define TX_DESC_FLAGS_OFFSET         8
-#define TX_DESC_STATUS_OFFSET        9
-#define TX_DESC_RETRY_OFFSET         10
-#define TX_DESC_RATE_OFFSET          11
-#define TX_DESC_KEY_INDEX_OFFSET     12
-#define TX_DESC_CIPHER_TYPE_OFFSET   13
-#define TX_DESC_CIPHER_LENGTH_OFFSET 14
-#define TX_DESC_PACKET_TYPE_OFFSET   17
-#define TX_DESC_HOST_LENGTH_OFFSET   18
-
-/*
- * Host-MAC interface
- */
-
-#define TX_STATUS_SUCCESS       0x00
-
-#define TX_FIRM_OWN             0x80
-#define TX_DONE                 0x40
-
-#define TX_ERROR                0x01
-
-#define TX_PACKET_TYPE_DATA     0x01
-#define TX_PACKET_TYPE_MGMT     0x02
-
-#define ISR_EMPTY               0x00        /* no bits set in ISR */
-#define ISR_TxCOMPLETE          0x01        /* packet transmitted */
-#define ISR_RxCOMPLETE          0x02        /* packet received */
-#define ISR_RxFRAMELOST         0x04        /* Rx Frame lost */
-#define ISR_FATAL_ERROR         0x08        /* Fatal error */
-#define ISR_COMMAND_COMPLETE    0x10        /* command completed */
-#define ISR_OUT_OF_RANGE        0x20        /* command completed */
-#define ISR_IBSS_MERGE          0x40        /* (4.1.2.30): IBSS merge */
-#define ISR_GENERIC_IRQ         0x80
-
-#define Local_Mib_Type          0x01
-#define Mac_Address_Mib_Type    0x02
-#define Mac_Mib_Type            0x03
-#define Statistics_Mib_Type     0x04
-#define Mac_Mgmt_Mib_Type       0x05
-#define Mac_Wep_Mib_Type        0x06
-#define Phy_Mib_Type            0x07
-#define Multi_Domain_MIB        0x08
-
-#define MAC_MGMT_MIB_CUR_BSSID_POS            14
-#define MAC_MIB_FRAG_THRESHOLD_POS            8
-#define MAC_MIB_RTS_THRESHOLD_POS             10
-#define MAC_MIB_SHORT_RETRY_POS               16
-#define MAC_MIB_LONG_RETRY_POS                17
-#define MAC_MIB_SHORT_RETRY_LIMIT_POS         16
-#define MAC_MGMT_MIB_BEACON_PER_POS           0
-#define MAC_MGMT_MIB_STATION_ID_POS           6
-#define MAC_MGMT_MIB_CUR_PRIVACY_POS          11
-#define MAC_MGMT_MIB_CUR_BSSID_POS            14
-#define MAC_MGMT_MIB_PS_MODE_POS              53
-#define MAC_MGMT_MIB_LISTEN_INTERVAL_POS      54
-#define MAC_MGMT_MIB_MULTI_DOMAIN_IMPLEMENTED 56
-#define MAC_MGMT_MIB_MULTI_DOMAIN_ENABLED     57
-#define PHY_MIB_CHANNEL_POS                   14
-#define PHY_MIB_RATE_SET_POS                  20
-#define PHY_MIB_REG_DOMAIN_POS                26
-#define LOCAL_MIB_AUTO_TX_RATE_POS            3
-#define LOCAL_MIB_SSID_SIZE                   5
-#define LOCAL_MIB_TX_PROMISCUOUS_POS          6
-#define LOCAL_MIB_TX_MGMT_RATE_POS            7
-#define LOCAL_MIB_TX_CONTROL_RATE_POS         8
-#define LOCAL_MIB_PREAMBLE_TYPE               9
-#define MAC_ADDR_MIB_MAC_ADDR_POS             0
-
-#define         CMD_Set_MIB_Vars              0x01
-#define         CMD_Get_MIB_Vars              0x02
-#define         CMD_Scan                      0x03
-#define         CMD_Join                      0x04
-#define         CMD_Start                     0x05
-#define         CMD_EnableRadio               0x06
-#define         CMD_DisableRadio              0x07
-#define         CMD_SiteSurvey                0x0B
-
-#define         CMD_STATUS_IDLE                   0x00
-#define         CMD_STATUS_COMPLETE               0x01
-#define         CMD_STATUS_UNKNOWN                0x02
-#define         CMD_STATUS_INVALID_PARAMETER      0x03
-#define         CMD_STATUS_FUNCTION_NOT_SUPPORTED 0x04
-#define         CMD_STATUS_TIME_OUT               0x07
-#define         CMD_STATUS_IN_PROGRESS            0x08
-#define         CMD_STATUS_REJECTED_RADIO_OFF     0x09
-#define         CMD_STATUS_HOST_ERROR             0xFF
-#define         CMD_STATUS_BUSY                   0xFE
-
-#define CMD_BLOCK_COMMAND_OFFSET        0
-#define CMD_BLOCK_STATUS_OFFSET         1
-#define CMD_BLOCK_PARAMETERS_OFFSET     4
-
-#define SCAN_OPTIONS_SITE_SURVEY        0x80
-
-#define MGMT_FRAME_BODY_OFFSET		24
-#define MAX_AUTHENTICATION_RETRIES	3
-#define MAX_ASSOCIATION_RETRIES		3
-
-#define AUTHENTICATION_RESPONSE_TIME_OUT  1000
-
-#define MAX_WIRELESS_BODY  2316 /* mtu is 2312, CRC is 4 */
-#define LOOP_RETRY_LIMIT   500000
-
-#define ACTIVE_MODE	1
-#define PS_MODE		2
-
-#define MAX_ENCRYPTION_KEYS 4
-#define MAX_ENCRYPTION_KEY_SIZE 40
-
-/*
- * 802.11 related definitions
- */
-
-/*
- * Regulatory Domains
- */
-
-#define REG_DOMAIN_FCC		0x10	/* Channels	1-11	USA				*/
-#define REG_DOMAIN_DOC		0x20	/* Channel	1-11	Canada				*/
-#define REG_DOMAIN_ETSI		0x30	/* Channel	1-13	Europe (ex Spain/France)	*/
-#define REG_DOMAIN_SPAIN	0x31	/* Channel	10-11	Spain				*/
-#define REG_DOMAIN_FRANCE	0x32	/* Channel	10-13	France				*/
-#define REG_DOMAIN_MKK		0x40	/* Channel	14	Japan				*/
-#define REG_DOMAIN_MKK1		0x41	/* Channel	1-14	Japan(MKK1)			*/
-#define REG_DOMAIN_ISRAEL	0x50	/* Channel	3-9	ISRAEL				*/
-
-#define BSS_TYPE_AD_HOC		1
-#define BSS_TYPE_INFRASTRUCTURE 2
-
-#define SCAN_TYPE_ACTIVE	0
-#define SCAN_TYPE_PASSIVE	1
-
-#define LONG_PREAMBLE		0
-#define SHORT_PREAMBLE		1
-#define AUTO_PREAMBLE		2
-
-#define DATA_FRAME_WS_HEADER_SIZE   30
-
-/* promiscuous mode control */
-#define PROM_MODE_OFF			0x0
-#define PROM_MODE_UNKNOWN		0x1
-#define PROM_MODE_CRC_FAILED		0x2
-#define PROM_MODE_DUPLICATED		0x4
-#define PROM_MODE_MGMT			0x8
-#define PROM_MODE_CTRL			0x10
-#define PROM_MODE_BAD_PROTOCOL		0x20
-
-#define IFACE_INT_STATUS_OFFSET		0
-#define IFACE_INT_MASK_OFFSET		1
-#define IFACE_LOCKOUT_HOST_OFFSET	2
-#define IFACE_LOCKOUT_MAC_OFFSET	3
-#define IFACE_FUNC_CTRL_OFFSET		28
-#define IFACE_MAC_STAT_OFFSET		30
-#define IFACE_GENERIC_INT_TYPE_OFFSET	32
-
-#define CIPHER_SUITE_NONE     0
-#define CIPHER_SUITE_WEP_64   1
-#define CIPHER_SUITE_TKIP     2
-#define CIPHER_SUITE_AES      3
-#define CIPHER_SUITE_CCX      4
-#define CIPHER_SUITE_WEP_128  5
-
-/*
- * IFACE MACROS & definitions
- */
-
-/*
- * FuncCtrl field:
- */
-#define FUNC_CTRL_TxENABLE		0x10
-#define FUNC_CTRL_RxENABLE		0x20
-#define FUNC_CTRL_INIT_COMPLETE		0x01
-
-/* A stub firmware image which reads the MAC address from NVRAM on the card.
-   For copyright information and source see the end of this file. */
-static u8 mac_reader[] = {
-	0x06, 0x00, 0x00, 0xea, 0x04, 0x00, 0x00, 0xea, 0x03, 0x00, 0x00, 0xea, 0x02, 0x00, 0x00, 0xea,
-	0x01, 0x00, 0x00, 0xea, 0x00, 0x00, 0x00, 0xea, 0xff, 0xff, 0xff, 0xea, 0xfe, 0xff, 0xff, 0xea,
-	0xd3, 0x00, 0xa0, 0xe3, 0x00, 0xf0, 0x21, 0xe1, 0x0e, 0x04, 0xa0, 0xe3, 0x00, 0x10, 0xa0, 0xe3,
-	0x81, 0x11, 0xa0, 0xe1, 0x00, 0x10, 0x81, 0xe3, 0x00, 0x10, 0x80, 0xe5, 0x1c, 0x10, 0x90, 0xe5,
-	0x10, 0x10, 0xc1, 0xe3, 0x1c, 0x10, 0x80, 0xe5, 0x01, 0x10, 0xa0, 0xe3, 0x08, 0x10, 0x80, 0xe5,
-	0x02, 0x03, 0xa0, 0xe3, 0x00, 0x10, 0xa0, 0xe3, 0xb0, 0x10, 0xc0, 0xe1, 0xb4, 0x10, 0xc0, 0xe1,
-	0xb8, 0x10, 0xc0, 0xe1, 0xbc, 0x10, 0xc0, 0xe1, 0x56, 0xdc, 0xa0, 0xe3, 0x21, 0x00, 0x00, 0xeb,
-	0x0a, 0x00, 0xa0, 0xe3, 0x1a, 0x00, 0x00, 0xeb, 0x10, 0x00, 0x00, 0xeb, 0x07, 0x00, 0x00, 0xeb,
-	0x02, 0x03, 0xa0, 0xe3, 0x02, 0x14, 0xa0, 0xe3, 0xb4, 0x10, 0xc0, 0xe1, 0x4c, 0x10, 0x9f, 0xe5,
-	0xbc, 0x10, 0xc0, 0xe1, 0x10, 0x10, 0xa0, 0xe3, 0xb8, 0x10, 0xc0, 0xe1, 0xfe, 0xff, 0xff, 0xea,
-	0x00, 0x40, 0x2d, 0xe9, 0x00, 0x20, 0xa0, 0xe3, 0x02, 0x3c, 0xa0, 0xe3, 0x00, 0x10, 0xa0, 0xe3,
-	0x28, 0x00, 0x9f, 0xe5, 0x37, 0x00, 0x00, 0xeb, 0x00, 0x40, 0xbd, 0xe8, 0x1e, 0xff, 0x2f, 0xe1,
-	0x00, 0x40, 0x2d, 0xe9, 0x12, 0x2e, 0xa0, 0xe3, 0x06, 0x30, 0xa0, 0xe3, 0x00, 0x10, 0xa0, 0xe3,
-	0x02, 0x04, 0xa0, 0xe3, 0x2f, 0x00, 0x00, 0xeb, 0x00, 0x40, 0xbd, 0xe8, 0x1e, 0xff, 0x2f, 0xe1,
-	0x00, 0x02, 0x00, 0x02, 0x80, 0x01, 0x90, 0xe0, 0x01, 0x00, 0x00, 0x0a, 0x01, 0x00, 0x50, 0xe2,
-	0xfc, 0xff, 0xff, 0xea, 0x1e, 0xff, 0x2f, 0xe1, 0x80, 0x10, 0xa0, 0xe3, 0xf3, 0x06, 0xa0, 0xe3,
-	0x00, 0x10, 0x80, 0xe5, 0x00, 0x10, 0xa0, 0xe3, 0x00, 0x10, 0x80, 0xe5, 0x01, 0x10, 0xa0, 0xe3,
-	0x04, 0x10, 0x80, 0xe5, 0x00, 0x10, 0x80, 0xe5, 0x0e, 0x34, 0xa0, 0xe3, 0x1c, 0x10, 0x93, 0xe5,
-	0x02, 0x1a, 0x81, 0xe3, 0x1c, 0x10, 0x83, 0xe5, 0x58, 0x11, 0x9f, 0xe5, 0x30, 0x10, 0x80, 0xe5,
-	0x54, 0x11, 0x9f, 0xe5, 0x34, 0x10, 0x80, 0xe5, 0x38, 0x10, 0x80, 0xe5, 0x3c, 0x10, 0x80, 0xe5,
-	0x10, 0x10, 0x90, 0xe5, 0x08, 0x00, 0x90, 0xe5, 0x1e, 0xff, 0x2f, 0xe1, 0xf3, 0x16, 0xa0, 0xe3,
-	0x08, 0x00, 0x91, 0xe5, 0x05, 0x00, 0xa0, 0xe3, 0x0c, 0x00, 0x81, 0xe5, 0x10, 0x00, 0x91, 0xe5,
-	0x02, 0x00, 0x10, 0xe3, 0xfc, 0xff, 0xff, 0x0a, 0xff, 0x00, 0xa0, 0xe3, 0x0c, 0x00, 0x81, 0xe5,
-	0x10, 0x00, 0x91, 0xe5, 0x02, 0x00, 0x10, 0xe3, 0xfc, 0xff, 0xff, 0x0a, 0x08, 0x00, 0x91, 0xe5,
-	0x10, 0x00, 0x91, 0xe5, 0x01, 0x00, 0x10, 0xe3, 0xfc, 0xff, 0xff, 0x0a, 0x08, 0x00, 0x91, 0xe5,
-	0xff, 0x00, 0x00, 0xe2, 0x1e, 0xff, 0x2f, 0xe1, 0x30, 0x40, 0x2d, 0xe9, 0x00, 0x50, 0xa0, 0xe1,
-	0x03, 0x40, 0xa0, 0xe1, 0xa2, 0x02, 0xa0, 0xe1, 0x08, 0x00, 0x00, 0xe2, 0x03, 0x00, 0x80, 0xe2,
-	0xd8, 0x10, 0x9f, 0xe5, 0x00, 0x00, 0xc1, 0xe5, 0x01, 0x20, 0xc1, 0xe5, 0xe2, 0xff, 0xff, 0xeb,
-	0x01, 0x00, 0x10, 0xe3, 0xfc, 0xff, 0xff, 0x1a, 0x14, 0x00, 0xa0, 0xe3, 0xc4, 0xff, 0xff, 0xeb,
-	0x04, 0x20, 0xa0, 0xe1, 0x05, 0x10, 0xa0, 0xe1, 0x02, 0x00, 0xa0, 0xe3, 0x01, 0x00, 0x00, 0xeb,
-	0x30, 0x40, 0xbd, 0xe8, 0x1e, 0xff, 0x2f, 0xe1, 0x70, 0x40, 0x2d, 0xe9, 0xf3, 0x46, 0xa0, 0xe3,
-	0x00, 0x30, 0xa0, 0xe3, 0x00, 0x00, 0x50, 0xe3, 0x08, 0x00, 0x00, 0x9a, 0x8c, 0x50, 0x9f, 0xe5,
-	0x03, 0x60, 0xd5, 0xe7, 0x0c, 0x60, 0x84, 0xe5, 0x10, 0x60, 0x94, 0xe5, 0x02, 0x00, 0x16, 0xe3,
-	0xfc, 0xff, 0xff, 0x0a, 0x01, 0x30, 0x83, 0xe2, 0x00, 0x00, 0x53, 0xe1, 0xf7, 0xff, 0xff, 0x3a,
-	0xff, 0x30, 0xa0, 0xe3, 0x0c, 0x30, 0x84, 0xe5, 0x08, 0x00, 0x94, 0xe5, 0x10, 0x00, 0x94, 0xe5,
-	0x01, 0x00, 0x10, 0xe3, 0xfc, 0xff, 0xff, 0x0a, 0x08, 0x00, 0x94, 0xe5, 0x00, 0x00, 0xa0, 0xe3,
-	0x00, 0x00, 0x52, 0xe3, 0x0b, 0x00, 0x00, 0x9a, 0x10, 0x50, 0x94, 0xe5, 0x02, 0x00, 0x15, 0xe3,
-	0xfc, 0xff, 0xff, 0x0a, 0x0c, 0x30, 0x84, 0xe5, 0x10, 0x50, 0x94, 0xe5, 0x01, 0x00, 0x15, 0xe3,
-	0xfc, 0xff, 0xff, 0x0a, 0x08, 0x50, 0x94, 0xe5, 0x01, 0x50, 0xc1, 0xe4, 0x01, 0x00, 0x80, 0xe2,
-	0x02, 0x00, 0x50, 0xe1, 0xf3, 0xff, 0xff, 0x3a, 0xc8, 0x00, 0xa0, 0xe3, 0x98, 0xff, 0xff, 0xeb,
-	0x70, 0x40, 0xbd, 0xe8, 0x1e, 0xff, 0x2f, 0xe1, 0x01, 0x0c, 0x00, 0x02, 0x01, 0x02, 0x00, 0x02,
-	0x00, 0x01, 0x00, 0x02
-};
-
-struct atmel_private {
-	void *card; /* Bus dependent structure varies for PCcard */
-	int (*present_callback)(void *); /* And callback which uses it */
-	char firmware_id[32];
-	AtmelFWType firmware_type;
-	u8 *firmware;
-	int firmware_length;
-	struct timer_list management_timer;
-	struct net_device *dev;
-	struct device *sys_dev;
-	struct iw_statistics wstats;
-	spinlock_t irqlock, timerlock;	/* spinlocks */
-	enum { BUS_TYPE_PCCARD, BUS_TYPE_PCI } bus_type;
-	enum {
-		CARD_TYPE_PARALLEL_FLASH,
-		CARD_TYPE_SPI_FLASH,
-		CARD_TYPE_EEPROM
-	} card_type;
-	int do_rx_crc; /* If we need to CRC incoming packets */
-	int probe_crc; /* set if we don't yet know */
-	int crc_ok_cnt, crc_ko_cnt; /* counters for probing */
-	u16 rx_desc_head;
-	u16 tx_desc_free, tx_desc_head, tx_desc_tail, tx_desc_previous;
-	u16 tx_free_mem, tx_buff_head, tx_buff_tail;
-
-	u16 frag_seq, frag_len, frag_no;
-	u8 frag_source[6];
-
-	u8 wep_is_on, default_key, exclude_unencrypted, encryption_level;
-	u8 group_cipher_suite, pairwise_cipher_suite;
-	u8 wep_keys[MAX_ENCRYPTION_KEYS][MAX_ENCRYPTION_KEY_SIZE];
-	int wep_key_len[MAX_ENCRYPTION_KEYS];
-	int use_wpa, radio_on_broken; /* firmware dependent stuff. */
-
-	u16 host_info_base;
-	struct host_info_struct {
-		/* NB this is matched to the hardware, don't change. */
-		u8 volatile int_status;
-		u8 volatile int_mask;
-		u8 volatile lockout_host;
-		u8 volatile lockout_mac;
-
-		u16 tx_buff_pos;
-		u16 tx_buff_size;
-		u16 tx_desc_pos;
-		u16 tx_desc_count;
-
-		u16 rx_buff_pos;
-		u16 rx_buff_size;
-		u16 rx_desc_pos;
-		u16 rx_desc_count;
-
-		u16 build_version;
-		u16 command_pos;
-
-		u16 major_version;
-		u16 minor_version;
-
-		u16 func_ctrl;
-		u16 mac_status;
-		u16 generic_IRQ_type;
-		u8  reserved[2];
-	} host_info;
-
-	enum {
-		STATION_STATE_SCANNING,
-		STATION_STATE_JOINNING,
-		STATION_STATE_AUTHENTICATING,
-		STATION_STATE_ASSOCIATING,
-		STATION_STATE_READY,
-		STATION_STATE_REASSOCIATING,
-		STATION_STATE_DOWN,
-		STATION_STATE_MGMT_ERROR
-	} station_state;
-
-	int operating_mode, power_mode;
-	unsigned long last_qual;
-	int beacons_this_sec;
-	int channel;
-	int reg_domain, config_reg_domain;
-	int tx_rate;
-	int auto_tx_rate;
-	int rts_threshold;
-	int frag_threshold;
-	int long_retry, short_retry;
-	int preamble;
-	int default_beacon_period, beacon_period, listen_interval;
-	int CurrentAuthentTransactionSeqNum, ExpectedAuthentTransactionSeqNum;
-	int AuthenticationRequestRetryCnt, AssociationRequestRetryCnt, ReAssociationRequestRetryCnt;
-	enum {
-		SITE_SURVEY_IDLE,
-		SITE_SURVEY_IN_PROGRESS,
-		SITE_SURVEY_COMPLETED
-	} site_survey_state;
-	unsigned long last_survey;
-
-	int station_was_associated, station_is_associated;
-	int fast_scan;
-
-	struct bss_info {
-		int channel;
-		int SSIDsize;
-		int RSSI;
-		int UsingWEP;
-		int preamble;
-		int beacon_period;
-		int BSStype;
-		u8 BSSID[6];
-		u8 SSID[MAX_SSID_LENGTH];
-	} BSSinfo[MAX_BSS_ENTRIES];
-	int BSS_list_entries, current_BSS;
-	int connect_to_any_BSS;
-	int SSID_size, new_SSID_size;
-	u8 CurrentBSSID[6], BSSID[6];
-	u8 SSID[MAX_SSID_LENGTH], new_SSID[MAX_SSID_LENGTH];
-	u64 last_beacon_timestamp;
-	u8 rx_buf[MAX_WIRELESS_BODY];
-};
-
-static u8 atmel_basic_rates[4] = {0x82, 0x84, 0x0b, 0x16};
-
-static const struct {
-	int reg_domain;
-	int min, max;
-	char *name;
-} channel_table[] = { { REG_DOMAIN_FCC, 1, 11, "USA" },
-		      { REG_DOMAIN_DOC, 1, 11, "Canada" },
-		      { REG_DOMAIN_ETSI, 1, 13, "Europe" },
-		      { REG_DOMAIN_SPAIN, 10, 11, "Spain" },
-		      { REG_DOMAIN_FRANCE, 10, 13, "France" },
-		      { REG_DOMAIN_MKK, 14, 14, "MKK" },
-		      { REG_DOMAIN_MKK1, 1, 14, "MKK1" },
-		      { REG_DOMAIN_ISRAEL, 3, 9, "Israel"} };
-
-static void build_wpa_mib(struct atmel_private *priv);
-static void atmel_copy_to_card(struct net_device *dev, u16 dest,
-			       const unsigned char *src, u16 len);
-static void atmel_copy_to_host(struct net_device *dev, unsigned char *dest,
-			       u16 src, u16 len);
-static void atmel_set_gcr(struct net_device *dev, u16 mask);
-static void atmel_clear_gcr(struct net_device *dev, u16 mask);
-static int atmel_lock_mac(struct atmel_private *priv);
-static void atmel_wmem32(struct atmel_private *priv, u16 pos, u32 data);
-static void atmel_command_irq(struct atmel_private *priv);
-static int atmel_validate_channel(struct atmel_private *priv, int channel);
-static void atmel_management_frame(struct atmel_private *priv,
-				   struct ieee80211_hdr *header,
-				   u16 frame_len, u8 rssi);
-static void atmel_management_timer(struct timer_list *t);
-static void atmel_send_command(struct atmel_private *priv, int command,
-			       void *cmd, int cmd_size);
-static int atmel_send_command_wait(struct atmel_private *priv, int command,
-				   void *cmd, int cmd_size);
-static void atmel_transmit_management_frame(struct atmel_private *priv,
-					    struct ieee80211_hdr *header,
-					    u8 *body, int body_len);
-
-static u8 atmel_get_mib8(struct atmel_private *priv, u8 type, u8 index);
-static void atmel_set_mib8(struct atmel_private *priv, u8 type, u8 index,
-			   u8 data);
-static void atmel_set_mib16(struct atmel_private *priv, u8 type, u8 index,
-			    u16 data);
-static void atmel_set_mib(struct atmel_private *priv, u8 type, u8 index,
-			  const u8 *data, int data_len);
-static void atmel_get_mib(struct atmel_private *priv, u8 type, u8 index,
-			  u8 *data, int data_len);
-static void atmel_scan(struct atmel_private *priv, int specific_ssid);
-static void atmel_join_bss(struct atmel_private *priv, int bss_index);
-static void atmel_smooth_qual(struct atmel_private *priv);
-static void atmel_writeAR(struct net_device *dev, u16 data);
-static int probe_atmel_card(struct net_device *dev);
-static int reset_atmel_card(struct net_device *dev);
-static void atmel_enter_state(struct atmel_private *priv, int new_state);
-int atmel_open (struct net_device *dev);
-
-static inline u16 atmel_hi(struct atmel_private *priv, u16 offset)
-{
-	return priv->host_info_base + offset;
-}
-
-static inline u16 atmel_co(struct atmel_private *priv, u16 offset)
-{
-	return priv->host_info.command_pos + offset;
-}
-
-static inline u16 atmel_rx(struct atmel_private *priv, u16 offset, u16 desc)
-{
-	return priv->host_info.rx_desc_pos + (sizeof(struct rx_desc) * desc) + offset;
-}
-
-static inline u16 atmel_tx(struct atmel_private *priv, u16 offset, u16 desc)
-{
-	return priv->host_info.tx_desc_pos + (sizeof(struct tx_desc) * desc) + offset;
-}
-
-static inline u8 atmel_read8(struct net_device *dev, u16 offset)
-{
-	return inb(dev->base_addr + offset);
-}
-
-static inline void atmel_write8(struct net_device *dev, u16 offset, u8 data)
-{
-	outb(data, dev->base_addr + offset);
-}
-
-static inline u16 atmel_read16(struct net_device *dev, u16 offset)
-{
-	return inw(dev->base_addr + offset);
-}
-
-static inline void atmel_write16(struct net_device *dev, u16 offset, u16 data)
-{
-	outw(data, dev->base_addr + offset);
-}
-
-static inline u8 atmel_rmem8(struct atmel_private *priv, u16 pos)
-{
-	atmel_writeAR(priv->dev, pos);
-	return atmel_read8(priv->dev, DR);
-}
-
-static inline void atmel_wmem8(struct atmel_private *priv, u16 pos, u16 data)
-{
-	atmel_writeAR(priv->dev, pos);
-	atmel_write8(priv->dev, DR, data);
-}
-
-static inline u16 atmel_rmem16(struct atmel_private *priv, u16 pos)
-{
-	atmel_writeAR(priv->dev, pos);
-	return atmel_read16(priv->dev, DR);
-}
-
-static inline void atmel_wmem16(struct atmel_private *priv, u16 pos, u16 data)
-{
-	atmel_writeAR(priv->dev, pos);
-	atmel_write16(priv->dev, DR, data);
-}
-
-static const struct iw_handler_def atmel_handler_def;
-
-static void tx_done_irq(struct atmel_private *priv)
-{
-	int i;
-
-	for (i = 0;
-	     atmel_rmem8(priv, atmel_tx(priv, TX_DESC_FLAGS_OFFSET, priv->tx_desc_head)) == TX_DONE &&
-		     i < priv->host_info.tx_desc_count;
-	     i++) {
-		u8 status = atmel_rmem8(priv, atmel_tx(priv, TX_DESC_STATUS_OFFSET, priv->tx_desc_head));
-		u16 msdu_size = atmel_rmem16(priv, atmel_tx(priv, TX_DESC_SIZE_OFFSET, priv->tx_desc_head));
-		u8 type = atmel_rmem8(priv, atmel_tx(priv, TX_DESC_PACKET_TYPE_OFFSET, priv->tx_desc_head));
-
-		atmel_wmem8(priv, atmel_tx(priv, TX_DESC_FLAGS_OFFSET, priv->tx_desc_head), 0);
-
-		priv->tx_free_mem += msdu_size;
-		priv->tx_desc_free++;
-
-		if (priv->tx_buff_head + msdu_size > (priv->host_info.tx_buff_pos + priv->host_info.tx_buff_size))
-			priv->tx_buff_head = 0;
-		else
-			priv->tx_buff_head += msdu_size;
-
-		if (priv->tx_desc_head < (priv->host_info.tx_desc_count - 1))
-			priv->tx_desc_head++ ;
-		else
-			priv->tx_desc_head = 0;
-
-		if (type == TX_PACKET_TYPE_DATA) {
-			if (status == TX_STATUS_SUCCESS)
-				priv->dev->stats.tx_packets++;
-			else
-				priv->dev->stats.tx_errors++;
-			netif_wake_queue(priv->dev);
-		}
-	}
-}
-
-static u16 find_tx_buff(struct atmel_private *priv, u16 len)
-{
-	u16 bottom_free = priv->host_info.tx_buff_size - priv->tx_buff_tail;
-
-	if (priv->tx_desc_free == 3 || priv->tx_free_mem < len)
-		return 0;
-
-	if (bottom_free >= len)
-		return priv->host_info.tx_buff_pos + priv->tx_buff_tail;
-
-	if (priv->tx_free_mem - bottom_free >= len) {
-		priv->tx_buff_tail = 0;
-		return priv->host_info.tx_buff_pos;
-	}
-
-	return 0;
-}
-
-static void tx_update_descriptor(struct atmel_private *priv, int is_bcast,
-				 u16 len, u16 buff, u8 type)
-{
-	atmel_wmem16(priv, atmel_tx(priv, TX_DESC_POS_OFFSET, priv->tx_desc_tail), buff);
-	atmel_wmem16(priv, atmel_tx(priv, TX_DESC_SIZE_OFFSET, priv->tx_desc_tail), len);
-	if (!priv->use_wpa)
-		atmel_wmem16(priv, atmel_tx(priv, TX_DESC_HOST_LENGTH_OFFSET, priv->tx_desc_tail), len);
-	atmel_wmem8(priv, atmel_tx(priv, TX_DESC_PACKET_TYPE_OFFSET, priv->tx_desc_tail), type);
-	atmel_wmem8(priv, atmel_tx(priv, TX_DESC_RATE_OFFSET, priv->tx_desc_tail), priv->tx_rate);
-	atmel_wmem8(priv, atmel_tx(priv, TX_DESC_RETRY_OFFSET, priv->tx_desc_tail), 0);
-	if (priv->use_wpa) {
-		int cipher_type, cipher_length;
-		if (is_bcast) {
-			cipher_type = priv->group_cipher_suite;
-			if (cipher_type == CIPHER_SUITE_WEP_64 ||
-			    cipher_type == CIPHER_SUITE_WEP_128)
-				cipher_length = 8;
-			else if (cipher_type == CIPHER_SUITE_TKIP)
-				cipher_length = 12;
-			else if (priv->pairwise_cipher_suite == CIPHER_SUITE_WEP_64 ||
-				 priv->pairwise_cipher_suite == CIPHER_SUITE_WEP_128) {
-				cipher_type = priv->pairwise_cipher_suite;
-				cipher_length = 8;
-			} else {
-				cipher_type = CIPHER_SUITE_NONE;
-				cipher_length = 0;
-			}
-		} else {
-			cipher_type = priv->pairwise_cipher_suite;
-			if (cipher_type == CIPHER_SUITE_WEP_64 ||
-			    cipher_type == CIPHER_SUITE_WEP_128)
-				cipher_length = 8;
-			else if (cipher_type == CIPHER_SUITE_TKIP)
-				cipher_length = 12;
-			else if (priv->group_cipher_suite == CIPHER_SUITE_WEP_64 ||
-				 priv->group_cipher_suite == CIPHER_SUITE_WEP_128) {
-				cipher_type = priv->group_cipher_suite;
-				cipher_length = 8;
-			} else {
-				cipher_type = CIPHER_SUITE_NONE;
-				cipher_length = 0;
-			}
-		}
-
-		atmel_wmem8(priv, atmel_tx(priv, TX_DESC_CIPHER_TYPE_OFFSET, priv->tx_desc_tail),
-			    cipher_type);
-		atmel_wmem8(priv, atmel_tx(priv, TX_DESC_CIPHER_LENGTH_OFFSET, priv->tx_desc_tail),
-			    cipher_length);
-	}
-	atmel_wmem32(priv, atmel_tx(priv, TX_DESC_NEXT_OFFSET, priv->tx_desc_tail), 0x80000000L);
-	atmel_wmem8(priv, atmel_tx(priv, TX_DESC_FLAGS_OFFSET, priv->tx_desc_tail), TX_FIRM_OWN);
-	if (priv->tx_desc_previous != priv->tx_desc_tail)
-		atmel_wmem32(priv, atmel_tx(priv, TX_DESC_NEXT_OFFSET, priv->tx_desc_previous), 0);
-	priv->tx_desc_previous = priv->tx_desc_tail;
-	if (priv->tx_desc_tail < (priv->host_info.tx_desc_count - 1))
-		priv->tx_desc_tail++;
-	else
-		priv->tx_desc_tail = 0;
-	priv->tx_desc_free--;
-	priv->tx_free_mem -= len;
-}
-
-static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev)
-{
-	struct atmel_private *priv = netdev_priv(dev);
-	struct ieee80211_hdr header;
-	unsigned long flags;
-	u16 buff, frame_ctl, len = (ETH_ZLEN < skb->len) ? skb->len : ETH_ZLEN;
-
-	if (priv->card && priv->present_callback &&
-	    !(*priv->present_callback)(priv->card)) {
-		dev->stats.tx_errors++;
-		dev_kfree_skb(skb);
-		return NETDEV_TX_OK;
-	}
-
-	if (priv->station_state != STATION_STATE_READY) {
-		dev->stats.tx_errors++;
-		dev_kfree_skb(skb);
-		return NETDEV_TX_OK;
-	}
-
-	/* first ensure the timer func cannot run */
-	spin_lock_bh(&priv->timerlock);
-	/* then stop the hardware ISR */
-	spin_lock_irqsave(&priv->irqlock, flags);
-	/* nb doing the above in the opposite order will deadlock */
-
-	/* The Wireless Header is 30 bytes. In the Ethernet packet we "cut" the
-	   12 first bytes (containing DA/SA) and put them in the appropriate
-	   fields of the Wireless Header. Thus the packet length is then the
-	   initial + 18 (+30-12) */
-
-	if (!(buff = find_tx_buff(priv, len + 18))) {
-		dev->stats.tx_dropped++;
-		spin_unlock_irqrestore(&priv->irqlock, flags);
-		spin_unlock_bh(&priv->timerlock);
-		netif_stop_queue(dev);
-		return NETDEV_TX_BUSY;
-	}
-
-	frame_ctl = IEEE80211_FTYPE_DATA;
-	header.duration_id = 0;
-	header.seq_ctrl = 0;
-	if (priv->wep_is_on)
-		frame_ctl |= IEEE80211_FCTL_PROTECTED;
-	if (priv->operating_mode == IW_MODE_ADHOC) {
-		skb_copy_from_linear_data(skb, &header.addr1, ETH_ALEN);
-		memcpy(&header.addr2, dev->dev_addr, ETH_ALEN);
-		memcpy(&header.addr3, priv->BSSID, ETH_ALEN);
-	} else {
-		frame_ctl |= IEEE80211_FCTL_TODS;
-		memcpy(&header.addr1, priv->CurrentBSSID, ETH_ALEN);
-		memcpy(&header.addr2, dev->dev_addr, ETH_ALEN);
-		skb_copy_from_linear_data(skb, &header.addr3, ETH_ALEN);
-	}
-
-	if (priv->use_wpa)
-		memcpy(&header.addr4, rfc1042_header, ETH_ALEN);
-
-	header.frame_control = cpu_to_le16(frame_ctl);
-	/* Copy the wireless header into the card */
-	atmel_copy_to_card(dev, buff, (unsigned char *)&header, DATA_FRAME_WS_HEADER_SIZE);
-	/* Copy the packet sans its 802.3 header addresses which have been replaced */
-	atmel_copy_to_card(dev, buff + DATA_FRAME_WS_HEADER_SIZE, skb->data + 12, len - 12);
-	priv->tx_buff_tail += len - 12 + DATA_FRAME_WS_HEADER_SIZE;
-
-	/* low bit of first byte of destination tells us if broadcast */
-	tx_update_descriptor(priv, *(skb->data) & 0x01, len + 18, buff, TX_PACKET_TYPE_DATA);
-	dev->stats.tx_bytes += len;
-
-	spin_unlock_irqrestore(&priv->irqlock, flags);
-	spin_unlock_bh(&priv->timerlock);
-	dev_kfree_skb(skb);
-
-	return NETDEV_TX_OK;
-}
-
-static void atmel_transmit_management_frame(struct atmel_private *priv,
-					    struct ieee80211_hdr *header,
-					    u8 *body, int body_len)
-{
-	u16 buff;
-	int len = MGMT_FRAME_BODY_OFFSET + body_len;
-
-	if (!(buff = find_tx_buff(priv, len)))
-		return;
-
-	atmel_copy_to_card(priv->dev, buff, (u8 *)header, MGMT_FRAME_BODY_OFFSET);
-	atmel_copy_to_card(priv->dev, buff + MGMT_FRAME_BODY_OFFSET, body, body_len);
-	priv->tx_buff_tail += len;
-	tx_update_descriptor(priv, header->addr1[0] & 0x01, len, buff, TX_PACKET_TYPE_MGMT);
-}
-
-static void fast_rx_path(struct atmel_private *priv,
-			 struct ieee80211_hdr *header,
-			 u16 msdu_size, u16 rx_packet_loc, u32 crc)
-{
-	/* fast path: unfragmented packet copy directly into skbuf */
-	u8 mac4[6];
-	struct sk_buff	*skb;
-	unsigned char *skbp;
-
-	/* get the final, mac 4 header field, this tells us encapsulation */
-	atmel_copy_to_host(priv->dev, mac4, rx_packet_loc + 24, 6);
-	msdu_size -= 6;
-
-	if (priv->do_rx_crc) {
-		crc = crc32_le(crc, mac4, 6);
-		msdu_size -= 4;
-	}
-
-	if (!(skb = dev_alloc_skb(msdu_size + 14))) {
-		priv->dev->stats.rx_dropped++;
-		return;
-	}
-
-	skb_reserve(skb, 2);
-	skbp = skb_put(skb, msdu_size + 12);
-	atmel_copy_to_host(priv->dev, skbp + 12, rx_packet_loc + 30, msdu_size);
-
-	if (priv->do_rx_crc) {
-		u32 netcrc;
-		crc = crc32_le(crc, skbp + 12, msdu_size);
-		atmel_copy_to_host(priv->dev, (void *)&netcrc, rx_packet_loc + 30 + msdu_size, 4);
-		if ((crc ^ 0xffffffff) != netcrc) {
-			priv->dev->stats.rx_crc_errors++;
-			dev_kfree_skb(skb);
-			return;
-		}
-	}
-
-	memcpy(skbp, header->addr1, ETH_ALEN); /* destination address */
-	if (le16_to_cpu(header->frame_control) & IEEE80211_FCTL_FROMDS)
-		memcpy(&skbp[ETH_ALEN], header->addr3, ETH_ALEN);
-	else
-		memcpy(&skbp[ETH_ALEN], header->addr2, ETH_ALEN); /* source address */
-
-	skb->protocol = eth_type_trans(skb, priv->dev);
-	skb->ip_summed = CHECKSUM_NONE;
-	netif_rx(skb);
-	priv->dev->stats.rx_bytes += 12 + msdu_size;
-	priv->dev->stats.rx_packets++;
-}
-
-/* Test to see if the packet in card memory at packet_loc has a valid CRC
-   It doesn't matter that this is slow: it is only used to proble the first few
-   packets. */
-static int probe_crc(struct atmel_private *priv, u16 packet_loc, u16 msdu_size)
-{
-	int i = msdu_size - 4;
-	u32 netcrc, crc = 0xffffffff;
-
-	if (msdu_size < 4)
-		return 0;
-
-	atmel_copy_to_host(priv->dev, (void *)&netcrc, packet_loc + i, 4);
-
-	atmel_writeAR(priv->dev, packet_loc);
-	while (i--) {
-		u8 octet = atmel_read8(priv->dev, DR);
-		crc = crc32_le(crc, &octet, 1);
-	}
-
-	return (crc ^ 0xffffffff) == netcrc;
-}
-
-static void frag_rx_path(struct atmel_private *priv,
-			 struct ieee80211_hdr *header,
-			 u16 msdu_size, u16 rx_packet_loc, u32 crc, u16 seq_no,
-			 u8 frag_no, int more_frags)
-{
-	u8 mac4[ETH_ALEN];
-	u8 source[ETH_ALEN];
-	struct sk_buff *skb;
-
-	if (le16_to_cpu(header->frame_control) & IEEE80211_FCTL_FROMDS)
-		memcpy(source, header->addr3, ETH_ALEN);
-	else
-		memcpy(source, header->addr2, ETH_ALEN);
-
-	rx_packet_loc += 24; /* skip header */
-
-	if (priv->do_rx_crc)
-		msdu_size -= 4;
-
-	if (frag_no == 0) { /* first fragment */
-		atmel_copy_to_host(priv->dev, mac4, rx_packet_loc, ETH_ALEN);
-		msdu_size -= ETH_ALEN;
-		rx_packet_loc += ETH_ALEN;
-
-		if (priv->do_rx_crc)
-			crc = crc32_le(crc, mac4, 6);
-
-		priv->frag_seq = seq_no;
-		priv->frag_no = 1;
-		priv->frag_len = msdu_size;
-		memcpy(priv->frag_source, source, ETH_ALEN);
-		memcpy(&priv->rx_buf[ETH_ALEN], source, ETH_ALEN);
-		memcpy(priv->rx_buf, header->addr1, ETH_ALEN);
-
-		atmel_copy_to_host(priv->dev, &priv->rx_buf[12], rx_packet_loc, msdu_size);
-
-		if (priv->do_rx_crc) {
-			u32 netcrc;
-			crc = crc32_le(crc, &priv->rx_buf[12], msdu_size);
-			atmel_copy_to_host(priv->dev, (void *)&netcrc, rx_packet_loc + msdu_size, 4);
-			if ((crc ^ 0xffffffff) != netcrc) {
-				priv->dev->stats.rx_crc_errors++;
-				eth_broadcast_addr(priv->frag_source);
-			}
-		}
-
-	} else if (priv->frag_no == frag_no &&
-		   priv->frag_seq == seq_no &&
-		   memcmp(priv->frag_source, source, ETH_ALEN) == 0) {
-
-		atmel_copy_to_host(priv->dev, &priv->rx_buf[12 + priv->frag_len],
-				   rx_packet_loc, msdu_size);
-		if (priv->do_rx_crc) {
-			u32 netcrc;
-			crc = crc32_le(crc,
-				       &priv->rx_buf[12 + priv->frag_len],
-				       msdu_size);
-			atmel_copy_to_host(priv->dev, (void *)&netcrc, rx_packet_loc + msdu_size, 4);
-			if ((crc ^ 0xffffffff) != netcrc) {
-				priv->dev->stats.rx_crc_errors++;
-				eth_broadcast_addr(priv->frag_source);
-				more_frags = 1; /* don't send broken assembly */
-			}
-		}
-
-		priv->frag_len += msdu_size;
-		priv->frag_no++;
-
-		if (!more_frags) { /* last one */
-			eth_broadcast_addr(priv->frag_source);
-			if (!(skb = dev_alloc_skb(priv->frag_len + 14))) {
-				priv->dev->stats.rx_dropped++;
-			} else {
-				skb_reserve(skb, 2);
-				skb_put_data(skb, priv->rx_buf,
-				             priv->frag_len + 12);
-				skb->protocol = eth_type_trans(skb, priv->dev);
-				skb->ip_summed = CHECKSUM_NONE;
-				netif_rx(skb);
-				priv->dev->stats.rx_bytes += priv->frag_len + 12;
-				priv->dev->stats.rx_packets++;
-			}
-		}
-	} else
-		priv->wstats.discard.fragment++;
-}
-
-static void rx_done_irq(struct atmel_private *priv)
-{
-	int i;
-	struct ieee80211_hdr header;
-
-	for (i = 0;
-	     atmel_rmem8(priv, atmel_rx(priv, RX_DESC_FLAGS_OFFSET, priv->rx_desc_head)) == RX_DESC_FLAG_VALID &&
-		     i < priv->host_info.rx_desc_count;
-	     i++) {
-
-		u16 msdu_size, rx_packet_loc, frame_ctl, seq_control;
-		u8 status = atmel_rmem8(priv, atmel_rx(priv, RX_DESC_STATUS_OFFSET, priv->rx_desc_head));
-		u32 crc = 0xffffffff;
-
-		if (status != RX_STATUS_SUCCESS) {
-			if (status == 0xc1) /* determined by experiment */
-				priv->wstats.discard.nwid++;
-			else
-				priv->dev->stats.rx_errors++;
-			goto next;
-		}
-
-		msdu_size = atmel_rmem16(priv, atmel_rx(priv, RX_DESC_MSDU_SIZE_OFFSET, priv->rx_desc_head));
-		rx_packet_loc = atmel_rmem16(priv, atmel_rx(priv, RX_DESC_MSDU_POS_OFFSET, priv->rx_desc_head));
-
-		if (msdu_size < 30) {
-			priv->dev->stats.rx_errors++;
-			goto next;
-		}
-
-		/* Get header as far as end of seq_ctrl */
-		atmel_copy_to_host(priv->dev, (char *)&header, rx_packet_loc, 24);
-		frame_ctl = le16_to_cpu(header.frame_control);
-		seq_control = le16_to_cpu(header.seq_ctrl);
-
-		/* probe for CRC use here if needed  once five packets have
-		   arrived with the same crc status, we assume we know what's
-		   happening and stop probing */
-		if (priv->probe_crc) {
-			if (!priv->wep_is_on || !(frame_ctl & IEEE80211_FCTL_PROTECTED)) {
-				priv->do_rx_crc = probe_crc(priv, rx_packet_loc, msdu_size);
-			} else {
-				priv->do_rx_crc = probe_crc(priv, rx_packet_loc + 24, msdu_size - 24);
-			}
-			if (priv->do_rx_crc) {
-				if (priv->crc_ok_cnt++ > 5)
-					priv->probe_crc = 0;
-			} else {
-				if (priv->crc_ko_cnt++ > 5)
-					priv->probe_crc = 0;
-			}
-		}
-
-		/* don't CRC header when WEP in use */
-		if (priv->do_rx_crc && (!priv->wep_is_on || !(frame_ctl & IEEE80211_FCTL_PROTECTED))) {
-			crc = crc32_le(0xffffffff, (unsigned char *)&header, 24);
-		}
-		msdu_size -= 24; /* header */
-
-		if ((frame_ctl & IEEE80211_FCTL_FTYPE) == IEEE80211_FTYPE_DATA) {
-			int more_fragments = frame_ctl & IEEE80211_FCTL_MOREFRAGS;
-			u8 packet_fragment_no = seq_control & IEEE80211_SCTL_FRAG;
-			u16 packet_sequence_no = (seq_control & IEEE80211_SCTL_SEQ) >> 4;
-
-			if (!more_fragments && packet_fragment_no == 0) {
-				fast_rx_path(priv, &header, msdu_size, rx_packet_loc, crc);
-			} else {
-				frag_rx_path(priv, &header, msdu_size, rx_packet_loc, crc,
-					     packet_sequence_no, packet_fragment_no, more_fragments);
-			}
-		}
-
-		if ((frame_ctl & IEEE80211_FCTL_FTYPE) == IEEE80211_FTYPE_MGMT) {
-			/* copy rest of packet into buffer */
-			atmel_copy_to_host(priv->dev, (unsigned char *)&priv->rx_buf, rx_packet_loc + 24, msdu_size);
-
-			/* we use the same buffer for frag reassembly and control packets */
-			eth_broadcast_addr(priv->frag_source);
-
-			if (priv->do_rx_crc) {
-				/* last 4 octets is crc */
-				msdu_size -= 4;
-				crc = crc32_le(crc, (unsigned char *)&priv->rx_buf, msdu_size);
-				if ((crc ^ 0xffffffff) != (*((u32 *)&priv->rx_buf[msdu_size]))) {
-					priv->dev->stats.rx_crc_errors++;
-					goto next;
-				}
-			}
-
-			atmel_management_frame(priv, &header, msdu_size,
-					       atmel_rmem8(priv, atmel_rx(priv, RX_DESC_RSSI_OFFSET, priv->rx_desc_head)));
-		}
-
-next:
-		/* release descriptor */
-		atmel_wmem8(priv, atmel_rx(priv, RX_DESC_FLAGS_OFFSET, priv->rx_desc_head), RX_DESC_FLAG_CONSUMED);
-
-		if (priv->rx_desc_head < (priv->host_info.rx_desc_count - 1))
-			priv->rx_desc_head++;
-		else
-			priv->rx_desc_head = 0;
-	}
-}
-
-static irqreturn_t service_interrupt(int irq, void *dev_id)
-{
-	struct net_device *dev = (struct net_device *) dev_id;
-	struct atmel_private *priv = netdev_priv(dev);
-	u8 isr;
-	int i = -1;
-	static const u8 irq_order[] = {
-		ISR_OUT_OF_RANGE,
-		ISR_RxCOMPLETE,
-		ISR_TxCOMPLETE,
-		ISR_RxFRAMELOST,
-		ISR_FATAL_ERROR,
-		ISR_COMMAND_COMPLETE,
-		ISR_IBSS_MERGE,
-		ISR_GENERIC_IRQ
-	};
-
-	if (priv->card && priv->present_callback &&
-	    !(*priv->present_callback)(priv->card))
-		return IRQ_HANDLED;
-
-	/* In this state upper-level code assumes it can mess with
-	   the card unhampered by interrupts which may change register state.
-	   Note that even though the card shouldn't generate interrupts
-	   the inturrupt line may be shared. This allows card setup
-	   to go on without disabling interrupts for a long time. */
-	if (priv->station_state == STATION_STATE_DOWN)
-		return IRQ_NONE;
-
-	atmel_clear_gcr(dev, GCR_ENINT); /* disable interrupts */
-
-	while (1) {
-		if (!atmel_lock_mac(priv)) {
-			/* failed to contact card */
-			printk(KERN_ALERT "%s: failed to contact MAC.\n", dev->name);
-			return IRQ_HANDLED;
-		}
-
-		isr = atmel_rmem8(priv, atmel_hi(priv, IFACE_INT_STATUS_OFFSET));
-		atmel_wmem8(priv, atmel_hi(priv, IFACE_LOCKOUT_MAC_OFFSET), 0);
-
-		if (!isr) {
-			atmel_set_gcr(dev, GCR_ENINT); /* enable interrupts */
-			return i == -1 ? IRQ_NONE : IRQ_HANDLED;
-		}
-
-		atmel_set_gcr(dev, GCR_ACKINT); /* acknowledge interrupt */
-
-		for (i = 0; i < ARRAY_SIZE(irq_order); i++)
-			if (isr & irq_order[i])
-				break;
-
-		if (!atmel_lock_mac(priv)) {
-			/* failed to contact card */
-			printk(KERN_ALERT "%s: failed to contact MAC.\n", dev->name);
-			return IRQ_HANDLED;
-		}
-
-		isr = atmel_rmem8(priv, atmel_hi(priv, IFACE_INT_STATUS_OFFSET));
-		isr ^= irq_order[i];
-		atmel_wmem8(priv, atmel_hi(priv, IFACE_INT_STATUS_OFFSET), isr);
-		atmel_wmem8(priv, atmel_hi(priv, IFACE_LOCKOUT_MAC_OFFSET), 0);
-
-		switch (irq_order[i]) {
-
-		case ISR_OUT_OF_RANGE:
-			if (priv->operating_mode == IW_MODE_INFRA &&
-			    priv->station_state == STATION_STATE_READY) {
-				priv->station_is_associated = 0;
-				atmel_scan(priv, 1);
-			}
-			break;
-
-		case ISR_RxFRAMELOST:
-			priv->wstats.discard.misc++;
-			fallthrough;
-		case ISR_RxCOMPLETE:
-			rx_done_irq(priv);
-			break;
-
-		case ISR_TxCOMPLETE:
-			tx_done_irq(priv);
-			break;
-
-		case ISR_FATAL_ERROR:
-			printk(KERN_ALERT "%s: *** FATAL error interrupt ***\n", dev->name);
-			atmel_enter_state(priv, STATION_STATE_MGMT_ERROR);
-			break;
-
-		case ISR_COMMAND_COMPLETE:
-			atmel_command_irq(priv);
-			break;
-
-		case ISR_IBSS_MERGE:
-			atmel_get_mib(priv, Mac_Mgmt_Mib_Type, MAC_MGMT_MIB_CUR_BSSID_POS,
-				      priv->CurrentBSSID, 6);
-			/* The WPA stuff cares about the current AP address */
-			if (priv->use_wpa)
-				build_wpa_mib(priv);
-			break;
-		case ISR_GENERIC_IRQ:
-			printk(KERN_INFO "%s: Generic_irq received.\n", dev->name);
-			break;
-		}
-	}
-}
-
-static struct iw_statistics *atmel_get_wireless_stats(struct net_device *dev)
-{
-	struct atmel_private *priv = netdev_priv(dev);
-
-	/* update the link quality here in case we are seeing no beacons
-	   at all to drive the process */
-	atmel_smooth_qual(priv);
-
-	priv->wstats.status = priv->station_state;
-
-	if (priv->operating_mode == IW_MODE_INFRA) {
-		if (priv->station_state != STATION_STATE_READY) {
-			priv->wstats.qual.qual = 0;
-			priv->wstats.qual.level = 0;
-			priv->wstats.qual.updated = (IW_QUAL_QUAL_INVALID
-					| IW_QUAL_LEVEL_INVALID);
-		}
-		priv->wstats.qual.noise = 0;
-		priv->wstats.qual.updated |= IW_QUAL_NOISE_INVALID;
-	} else {
-		/* Quality levels cannot be determined in ad-hoc mode,
-		   because we can 'hear' more that one remote station. */
-		priv->wstats.qual.qual = 0;
-		priv->wstats.qual.level	= 0;
-		priv->wstats.qual.noise	= 0;
-		priv->wstats.qual.updated = IW_QUAL_QUAL_INVALID
-					| IW_QUAL_LEVEL_INVALID
-					| IW_QUAL_NOISE_INVALID;
-		priv->wstats.miss.beacon = 0;
-	}
-
-	return &priv->wstats;
-}
-
-static int atmel_set_mac_address(struct net_device *dev, void *p)
-{
-	struct sockaddr *addr = p;
-
-	eth_hw_addr_set(dev, addr->sa_data);
-	return atmel_open(dev);
-}
-
-EXPORT_SYMBOL(atmel_open);
-
-int atmel_open(struct net_device *dev)
-{
-	struct atmel_private *priv = netdev_priv(dev);
-	int i, channel, err;
-
-	/* any scheduled timer is no longer needed and might screw things up.. */
-	del_timer_sync(&priv->management_timer);
-
-	/* Interrupts will not touch the card once in this state... */
-	priv->station_state = STATION_STATE_DOWN;
-
-	if (priv->new_SSID_size) {
-		memcpy(priv->SSID, priv->new_SSID, priv->new_SSID_size);
-		priv->SSID_size = priv->new_SSID_size;
-		priv->new_SSID_size = 0;
-	}
-	priv->BSS_list_entries = 0;
-
-	priv->AuthenticationRequestRetryCnt = 0;
-	priv->AssociationRequestRetryCnt = 0;
-	priv->ReAssociationRequestRetryCnt = 0;
-	priv->CurrentAuthentTransactionSeqNum = 0x0001;
-	priv->ExpectedAuthentTransactionSeqNum = 0x0002;
-
-	priv->site_survey_state = SITE_SURVEY_IDLE;
-	priv->station_is_associated = 0;
-
-	err = reset_atmel_card(dev);
-	if (err)
-		return err;
-
-	if (priv->config_reg_domain) {
-		priv->reg_domain = priv->config_reg_domain;
-		atmel_set_mib8(priv, Phy_Mib_Type, PHY_MIB_REG_DOMAIN_POS, priv->reg_domain);
-	} else {
-		priv->reg_domain = atmel_get_mib8(priv, Phy_Mib_Type, PHY_MIB_REG_DOMAIN_POS);
-		for (i = 0; i < ARRAY_SIZE(channel_table); i++)
-			if (priv->reg_domain == channel_table[i].reg_domain)
-				break;
-		if (i == ARRAY_SIZE(channel_table)) {
-			priv->reg_domain = REG_DOMAIN_MKK1;
-			printk(KERN_ALERT "%s: failed to get regulatory domain: assuming MKK1.\n", dev->name);
-		}
-	}
-
-	if ((channel = atmel_validate_channel(priv, priv->channel)))
-		priv->channel = channel;
-
-	/* this moves station_state on.... */
-	atmel_scan(priv, 1);
-
-	atmel_set_gcr(priv->dev, GCR_ENINT); /* enable interrupts */
-	return 0;
-}
-
-static int atmel_close(struct net_device *dev)
-{
-	struct atmel_private *priv = netdev_priv(dev);
-
-	/* Send event to userspace that we are disassociating */
-	if (priv->station_state == STATION_STATE_READY) {
-		union iwreq_data wrqu;
-
-		wrqu.data.length = 0;
-		wrqu.data.flags = 0;
-		wrqu.ap_addr.sa_family = ARPHRD_ETHER;
-		eth_zero_addr(wrqu.ap_addr.sa_data);
-		wireless_send_event(priv->dev, SIOCGIWAP, &wrqu, NULL);
-	}
-
-	atmel_enter_state(priv, STATION_STATE_DOWN);
-
-	if (priv->bus_type == BUS_TYPE_PCCARD)
-		atmel_write16(dev, GCR, 0x0060);
-	atmel_write16(dev, GCR, 0x0040);
-	return 0;
-}
-
-static int atmel_validate_channel(struct atmel_private *priv, int channel)
-{
-	/* check that channel is OK, if so return zero,
-	   else return suitable default channel */
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(channel_table); i++)
-		if (priv->reg_domain == channel_table[i].reg_domain) {
-			if (channel >= channel_table[i].min &&
-			    channel <= channel_table[i].max)
-				return 0;
-			else
-				return channel_table[i].min;
-		}
-	return 0;
-}
-
-#ifdef CONFIG_PROC_FS
-static int atmel_proc_show(struct seq_file *m, void *v)
-{
-	struct atmel_private *priv = m->private;
-	int i;
-	char *s, *r, *c;
-
-	seq_printf(m, "Driver version:\t\t%d.%d\n", DRIVER_MAJOR, DRIVER_MINOR);
-
-	if (priv->station_state != STATION_STATE_DOWN) {
-		seq_printf(m,
-			   "Firmware version:\t%d.%d build %d\n"
-			   "Firmware location:\t",
-			   priv->host_info.major_version,
-			   priv->host_info.minor_version,
-			   priv->host_info.build_version);
-
-		if (priv->card_type != CARD_TYPE_EEPROM)
-			seq_puts(m, "on card\n");
-		else if (priv->firmware)
-			seq_printf(m, "%s loaded by host\n", priv->firmware_id);
-		else
-			seq_printf(m, "%s loaded by hotplug\n", priv->firmware_id);
-
-		switch (priv->card_type) {
-		case CARD_TYPE_PARALLEL_FLASH:
-			c = "Parallel flash";
-			break;
-		case CARD_TYPE_SPI_FLASH:
-			c = "SPI flash\n";
-			break;
-		case CARD_TYPE_EEPROM:
-			c = "EEPROM";
-			break;
-		default:
-			c = "<unknown>";
-		}
-
-		r = "<unknown>";
-		for (i = 0; i < ARRAY_SIZE(channel_table); i++)
-			if (priv->reg_domain == channel_table[i].reg_domain)
-				r = channel_table[i].name;
-
-		seq_printf(m, "MAC memory type:\t%s\n", c);
-		seq_printf(m, "Regulatory domain:\t%s\n", r);
-		seq_printf(m, "Host CRC checking:\t%s\n",
-			 priv->do_rx_crc ? "On" : "Off");
-		seq_printf(m, "WPA-capable firmware:\t%s\n",
-			 priv->use_wpa ? "Yes" : "No");
-	}
-
-	switch (priv->station_state) {
-	case STATION_STATE_SCANNING:
-		s = "Scanning";
-		break;
-	case STATION_STATE_JOINNING:
-		s = "Joining";
-		break;
-	case STATION_STATE_AUTHENTICATING:
-		s = "Authenticating";
-		break;
-	case STATION_STATE_ASSOCIATING:
-		s = "Associating";
-		break;
-	case STATION_STATE_READY:
-		s = "Ready";
-		break;
-	case STATION_STATE_REASSOCIATING:
-		s = "Reassociating";
-		break;
-	case STATION_STATE_MGMT_ERROR:
-		s = "Management error";
-		break;
-	case STATION_STATE_DOWN:
-		s = "Down";
-		break;
-	default:
-		s = "<unknown>";
-	}
-
-	seq_printf(m, "Current state:\t\t%s\n", s);
-	return 0;
-}
-#endif
-
-static const struct net_device_ops atmel_netdev_ops = {
-	.ndo_open 		= atmel_open,
-	.ndo_stop		= atmel_close,
-	.ndo_set_mac_address 	= atmel_set_mac_address,
-	.ndo_start_xmit 	= start_tx,
-	.ndo_validate_addr	= eth_validate_addr,
-};
-
-struct net_device *init_atmel_card(unsigned short irq, unsigned long port,
-				   const AtmelFWType fw_type,
-				   struct device *sys_dev,
-				   int (*card_present)(void *), void *card)
-{
-	struct net_device *dev;
-	struct atmel_private *priv;
-	int rc;
-
-	/* Create the network device object. */
-	dev = alloc_etherdev(sizeof(*priv));
-	if (!dev)
-		return NULL;
-
-	if (dev_alloc_name(dev, dev->name) < 0) {
-		printk(KERN_ERR "atmel: Couldn't get name!\n");
-		goto err_out_free;
-	}
-
-	priv = netdev_priv(dev);
-	priv->dev = dev;
-	priv->sys_dev = sys_dev;
-	priv->present_callback = card_present;
-	priv->card = card;
-	priv->firmware = NULL;
-	priv->firmware_type = fw_type;
-	if (firmware) /* module parameter */
-		strscpy(priv->firmware_id, firmware, sizeof(priv->firmware_id));
-	priv->bus_type = card_present ? BUS_TYPE_PCCARD : BUS_TYPE_PCI;
-	priv->station_state = STATION_STATE_DOWN;
-	priv->do_rx_crc = 0;
-	/* For PCMCIA cards, some chips need CRC, some don't
-	   so we have to probe. */
-	if (priv->bus_type == BUS_TYPE_PCCARD) {
-		priv->probe_crc = 1;
-		priv->crc_ok_cnt = priv->crc_ko_cnt = 0;
-	} else
-		priv->probe_crc = 0;
-	priv->last_qual = jiffies;
-	priv->last_beacon_timestamp = 0;
-	memset(priv->frag_source, 0xff, sizeof(priv->frag_source));
-	eth_zero_addr(priv->BSSID);
-	priv->CurrentBSSID[0] = 0xFF; /* Initialize to something invalid.... */
-	priv->station_was_associated = 0;
-
-	priv->last_survey = jiffies;
-	priv->preamble = LONG_PREAMBLE;
-	priv->operating_mode = IW_MODE_INFRA;
-	priv->connect_to_any_BSS = 0;
-	priv->config_reg_domain = 0;
-	priv->reg_domain = 0;
-	priv->tx_rate = 3;
-	priv->auto_tx_rate = 1;
-	priv->channel = 4;
-	priv->power_mode = 0;
-	priv->SSID[0] = '\0';
-	priv->SSID_size = 0;
-	priv->new_SSID_size = 0;
-	priv->frag_threshold = 2346;
-	priv->rts_threshold = 2347;
-	priv->short_retry = 7;
-	priv->long_retry = 4;
-
-	priv->wep_is_on = 0;
-	priv->default_key = 0;
-	priv->encryption_level = 0;
-	priv->exclude_unencrypted = 0;
-	priv->group_cipher_suite = priv->pairwise_cipher_suite = CIPHER_SUITE_NONE;
-	priv->use_wpa = 0;
-	memset(priv->wep_keys, 0, sizeof(priv->wep_keys));
-	memset(priv->wep_key_len, 0, sizeof(priv->wep_key_len));
-
-	priv->default_beacon_period = priv->beacon_period = 100;
-	priv->listen_interval = 1;
-
-	timer_setup(&priv->management_timer, atmel_management_timer, 0);
-	spin_lock_init(&priv->irqlock);
-	spin_lock_init(&priv->timerlock);
-
-	dev->netdev_ops = &atmel_netdev_ops;
-	dev->wireless_handlers = &atmel_handler_def;
-	dev->irq = irq;
-	dev->base_addr = port;
-
-	/* MTU range: 68 - 2312 */
-	dev->min_mtu = 68;
-	dev->max_mtu = MAX_WIRELESS_BODY - ETH_FCS_LEN;
-
-	SET_NETDEV_DEV(dev, sys_dev);
-
-	if ((rc = request_irq(dev->irq, service_interrupt, IRQF_SHARED, dev->name, dev))) {
-		printk(KERN_ERR "%s: register interrupt %d failed, rc %d\n", dev->name, irq, rc);
-		goto err_out_free;
-	}
-
-	if (!request_region(dev->base_addr, 32,
-			    priv->bus_type == BUS_TYPE_PCCARD ?  "atmel_cs" : "atmel_pci")) {
-		goto err_out_irq;
-	}
-
-	if (register_netdev(dev))
-		goto err_out_res;
-
-	if (!probe_atmel_card(dev)) {
-		unregister_netdev(dev);
-		goto err_out_res;
-	}
-
-	netif_carrier_off(dev);
-
-	if (!proc_create_single_data("driver/atmel", 0, NULL, atmel_proc_show,
-			priv))
-		printk(KERN_WARNING "atmel: unable to create /proc entry.\n");
-
-	printk(KERN_INFO "%s: Atmel at76c50x. Version %d.%d. MAC %pM\n",
-	       dev->name, DRIVER_MAJOR, DRIVER_MINOR, dev->dev_addr);
-
-	return dev;
-
-err_out_res:
-	release_region(dev->base_addr, 32);
-err_out_irq:
-	free_irq(dev->irq, dev);
-err_out_free:
-	free_netdev(dev);
-	return NULL;
-}
-
-EXPORT_SYMBOL(init_atmel_card);
-
-void stop_atmel_card(struct net_device *dev)
-{
-	struct atmel_private *priv = netdev_priv(dev);
-
-	/* put a brick on it... */
-	if (priv->bus_type == BUS_TYPE_PCCARD)
-		atmel_write16(dev, GCR, 0x0060);
-	atmel_write16(dev, GCR, 0x0040);
-
-	del_timer_sync(&priv->management_timer);
-	unregister_netdev(dev);
-	remove_proc_entry("driver/atmel", NULL);
-	free_irq(dev->irq, dev);
-	kfree(priv->firmware);
-	release_region(dev->base_addr, 32);
-	free_netdev(dev);
-}
-
-EXPORT_SYMBOL(stop_atmel_card);
-
-static int atmel_set_essid(struct net_device *dev,
-			   struct iw_request_info *info,
-			   union iwreq_data *wrqu,
-			   char *extra)
-{
-	struct iw_point *dwrq = &wrqu->essid;
-	struct atmel_private *priv = netdev_priv(dev);
-
-	/* Check if we asked for `any' */
-	if (dwrq->flags == 0) {
-		priv->connect_to_any_BSS = 1;
-	} else {
-		int index = (dwrq->flags & IW_ENCODE_INDEX) - 1;
-
-		priv->connect_to_any_BSS = 0;
-
-		/* Check the size of the string */
-		if (dwrq->length > MAX_SSID_LENGTH)
-			 return -E2BIG;
-		if (index != 0)
-			return -EINVAL;
-
-		memcpy(priv->new_SSID, extra, dwrq->length);
-		priv->new_SSID_size = dwrq->length;
-	}
-
-	return -EINPROGRESS;
-}
-
-static int atmel_get_essid(struct net_device *dev,
-			   struct iw_request_info *info,
-			   union iwreq_data *wrqu,
-			   char *extra)
-{
-	struct iw_point *dwrq = &wrqu->essid;
-	struct atmel_private *priv = netdev_priv(dev);
-
-	/* Get the current SSID */
-	if (priv->new_SSID_size != 0) {
-		memcpy(extra, priv->new_SSID, priv->new_SSID_size);
-		dwrq->length = priv->new_SSID_size;
-	} else {
-		memcpy(extra, priv->SSID, priv->SSID_size);
-		dwrq->length = priv->SSID_size;
-	}
-
-	dwrq->flags = !priv->connect_to_any_BSS; /* active */
-
-	return 0;
-}
-
-static int atmel_get_wap(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *wrqu,
-			 char *extra)
-{
-	struct sockaddr *awrq = &wrqu->ap_addr;
-	struct atmel_private *priv = netdev_priv(dev);
-	memcpy(awrq->sa_data, priv->CurrentBSSID, ETH_ALEN);
-	awrq->sa_family = ARPHRD_ETHER;
-
-	return 0;
-}
-
-static int atmel_set_encode(struct net_device *dev,
-			    struct iw_request_info *info,
-			    union iwreq_data *wrqu,
-			    char *extra)
-{
-	struct iw_point *dwrq = &wrqu->encoding;
-	struct atmel_private *priv = netdev_priv(dev);
-
-	/* Basic checking: do we have a key to set ?
-	 * Note : with the new API, it's impossible to get a NULL pointer.
-	 * Therefore, we need to check a key size == 0 instead.
-	 * New version of iwconfig properly set the IW_ENCODE_NOKEY flag
-	 * when no key is present (only change flags), but older versions
-	 * don't do it. - Jean II */
-	if (dwrq->length > 0) {
-		int index = (dwrq->flags & IW_ENCODE_INDEX) - 1;
-		int current_index = priv->default_key;
-		/* Check the size of the key */
-		if (dwrq->length > 13) {
-			return -EINVAL;
-		}
-		/* Check the index (none -> use current) */
-		if (index < 0 || index >= 4)
-			index = current_index;
-		else
-			priv->default_key = index;
-		/* Set the length */
-		if (dwrq->length > 5)
-			priv->wep_key_len[index] = 13;
-		else
-			if (dwrq->length > 0)
-				priv->wep_key_len[index] = 5;
-			else
-				/* Disable the key */
-				priv->wep_key_len[index] = 0;
-		/* Check if the key is not marked as invalid */
-		if (!(dwrq->flags & IW_ENCODE_NOKEY)) {
-			/* Cleanup */
-			memset(priv->wep_keys[index], 0, 13);
-			/* Copy the key in the driver */
-			memcpy(priv->wep_keys[index], extra, dwrq->length);
-		}
-		/* WE specify that if a valid key is set, encryption
-		 * should be enabled (user may turn it off later)
-		 * This is also how "iwconfig ethX key on" works */
-		if (index == current_index &&
-		    priv->wep_key_len[index] > 0) {
-			priv->wep_is_on = 1;
-			priv->exclude_unencrypted = 1;
-			if (priv->wep_key_len[index] > 5) {
-				priv->pairwise_cipher_suite = CIPHER_SUITE_WEP_128;
-				priv->encryption_level = 2;
-			} else {
-				priv->pairwise_cipher_suite = CIPHER_SUITE_WEP_64;
-				priv->encryption_level = 1;
-			}
-		}
-	} else {
-		/* Do we want to just set the transmit key index ? */
-		int index = (dwrq->flags & IW_ENCODE_INDEX) - 1;
-		if (index >= 0 && index < 4) {
-			priv->default_key = index;
-		} else
-			/* Don't complain if only change the mode */
-			if (!(dwrq->flags & IW_ENCODE_MODE))
-				return -EINVAL;
-	}
-	/* Read the flags */
-	if (dwrq->flags & IW_ENCODE_DISABLED) {
-		priv->wep_is_on = 0;
-		priv->encryption_level = 0;
-		priv->pairwise_cipher_suite = CIPHER_SUITE_NONE;
-	} else {
-		priv->wep_is_on = 1;
-		if (priv->wep_key_len[priv->default_key] > 5) {
-			priv->pairwise_cipher_suite = CIPHER_SUITE_WEP_128;
-			priv->encryption_level = 2;
-		} else {
-			priv->pairwise_cipher_suite = CIPHER_SUITE_WEP_64;
-			priv->encryption_level = 1;
-		}
-	}
-	if (dwrq->flags & IW_ENCODE_RESTRICTED)
-		priv->exclude_unencrypted = 1;
-	if (dwrq->flags & IW_ENCODE_OPEN)
-		priv->exclude_unencrypted = 0;
-
-	return -EINPROGRESS;		/* Call commit handler */
-}
-
-static int atmel_get_encode(struct net_device *dev,
-			    struct iw_request_info *info,
-			    union iwreq_data *wrqu,
-			    char *extra)
-{
-	struct iw_point *dwrq = &wrqu->encoding;
-	struct atmel_private *priv = netdev_priv(dev);
-	int index = (dwrq->flags & IW_ENCODE_INDEX) - 1;
-
-	if (!priv->wep_is_on)
-		dwrq->flags = IW_ENCODE_DISABLED;
-	else {
-		if (priv->exclude_unencrypted)
-			dwrq->flags = IW_ENCODE_RESTRICTED;
-		else
-			dwrq->flags = IW_ENCODE_OPEN;
-	}
-		/* Which key do we want ? -1 -> tx index */
-	if (index < 0 || index >= 4)
-		index = priv->default_key;
-	dwrq->flags |= index + 1;
-	/* Copy the key to the user buffer */
-	dwrq->length = priv->wep_key_len[index];
-	if (dwrq->length > 16) {
-		dwrq->length = 0;
-	} else {
-		memset(extra, 0, 16);
-		memcpy(extra, priv->wep_keys[index], dwrq->length);
-	}
-
-	return 0;
-}
-
-static int atmel_set_encodeext(struct net_device *dev,
-			    struct iw_request_info *info,
-			    union iwreq_data *wrqu,
-			    char *extra)
-{
-	struct atmel_private *priv = netdev_priv(dev);
-	struct iw_point *encoding = &wrqu->encoding;
-	struct iw_encode_ext *ext = (struct iw_encode_ext *)extra;
-	int idx, key_len, alg = ext->alg, set_key = 1;
-
-	/* Determine and validate the key index */
-	idx = encoding->flags & IW_ENCODE_INDEX;
-	if (idx) {
-		if (idx < 1 || idx > 4)
-			return -EINVAL;
-		idx--;
-	} else
-		idx = priv->default_key;
-
-	if (encoding->flags & IW_ENCODE_DISABLED)
-	    alg = IW_ENCODE_ALG_NONE;
-
-	if (ext->ext_flags & IW_ENCODE_EXT_SET_TX_KEY) {
-		priv->default_key = idx;
-		set_key = ext->key_len > 0 ? 1 : 0;
-	}
-
-	if (set_key) {
-		/* Set the requested key first */
-		switch (alg) {
-		case IW_ENCODE_ALG_NONE:
-			priv->wep_is_on = 0;
-			priv->encryption_level = 0;
-			priv->pairwise_cipher_suite = CIPHER_SUITE_NONE;
-			break;
-		case IW_ENCODE_ALG_WEP:
-			if (ext->key_len > 5) {
-				priv->wep_key_len[idx] = 13;
-				priv->pairwise_cipher_suite = CIPHER_SUITE_WEP_128;
-				priv->encryption_level = 2;
-			} else if (ext->key_len > 0) {
-				priv->wep_key_len[idx] = 5;
-				priv->pairwise_cipher_suite = CIPHER_SUITE_WEP_64;
-				priv->encryption_level = 1;
-			} else {
-				return -EINVAL;
-			}
-			priv->wep_is_on = 1;
-			memset(priv->wep_keys[idx], 0, 13);
-			key_len = min ((int)ext->key_len, priv->wep_key_len[idx]);
-			memcpy(priv->wep_keys[idx], ext->key, key_len);
-			break;
-		default:
-			return -EINVAL;
-		}
-	}
-
-	return -EINPROGRESS;
-}
-
-static int atmel_get_encodeext(struct net_device *dev,
-			    struct iw_request_info *info,
-			    union iwreq_data *wrqu,
-			    char *extra)
-{
-	struct atmel_private *priv = netdev_priv(dev);
-	struct iw_point *encoding = &wrqu->encoding;
-	struct iw_encode_ext *ext = (struct iw_encode_ext *)extra;
-	int idx, max_key_len;
-
-	max_key_len = encoding->length - sizeof(*ext);
-	if (max_key_len < 0)
-		return -EINVAL;
-
-	idx = encoding->flags & IW_ENCODE_INDEX;
-	if (idx) {
-		if (idx < 1 || idx > 4)
-			return -EINVAL;
-		idx--;
-	} else
-		idx = priv->default_key;
-
-	encoding->flags = idx + 1;
-	memset(ext, 0, sizeof(*ext));
-
-	if (!priv->wep_is_on) {
-		ext->alg = IW_ENCODE_ALG_NONE;
-		ext->key_len = 0;
-		encoding->flags |= IW_ENCODE_DISABLED;
-	} else {
-		if (priv->encryption_level > 0)
-			ext->alg = IW_ENCODE_ALG_WEP;
-		else
-			return -EINVAL;
-
-		ext->key_len = priv->wep_key_len[idx];
-		memcpy(ext->key, priv->wep_keys[idx], ext->key_len);
-		encoding->flags |= IW_ENCODE_ENABLED;
-	}
-
-	return 0;
-}
-
-static int atmel_set_auth(struct net_device *dev,
-			       struct iw_request_info *info,
-			       union iwreq_data *wrqu, char *extra)
-{
-	struct atmel_private *priv = netdev_priv(dev);
-	struct iw_param *param = &wrqu->param;
-
-	switch (param->flags & IW_AUTH_INDEX) {
-	case IW_AUTH_WPA_VERSION:
-	case IW_AUTH_CIPHER_PAIRWISE:
-	case IW_AUTH_CIPHER_GROUP:
-	case IW_AUTH_KEY_MGMT:
-	case IW_AUTH_RX_UNENCRYPTED_EAPOL:
-	case IW_AUTH_PRIVACY_INVOKED:
-		/*
-		 * atmel does not use these parameters
-		 */
-		break;
-
-	case IW_AUTH_DROP_UNENCRYPTED:
-		priv->exclude_unencrypted = param->value ? 1 : 0;
-		break;
-
-	case IW_AUTH_80211_AUTH_ALG: {
-			if (param->value & IW_AUTH_ALG_SHARED_KEY) {
-				priv->exclude_unencrypted = 1;
-			} else if (param->value & IW_AUTH_ALG_OPEN_SYSTEM) {
-				priv->exclude_unencrypted = 0;
-			} else
-				return -EINVAL;
-			break;
-		}
-
-	case IW_AUTH_WPA_ENABLED:
-		/* Silently accept disable of WPA */
-		if (param->value > 0)
-			return -EOPNOTSUPP;
-		break;
-
-	default:
-		return -EOPNOTSUPP;
-	}
-	return -EINPROGRESS;
-}
-
-static int atmel_get_auth(struct net_device *dev,
-			       struct iw_request_info *info,
-			       union iwreq_data *wrqu, char *extra)
-{
-	struct atmel_private *priv = netdev_priv(dev);
-	struct iw_param *param = &wrqu->param;
-
-	switch (param->flags & IW_AUTH_INDEX) {
-	case IW_AUTH_DROP_UNENCRYPTED:
-		param->value = priv->exclude_unencrypted;
-		break;
-
-	case IW_AUTH_80211_AUTH_ALG:
-		if (priv->exclude_unencrypted == 1)
-			param->value = IW_AUTH_ALG_SHARED_KEY;
-		else
-			param->value = IW_AUTH_ALG_OPEN_SYSTEM;
-		break;
-
-	case IW_AUTH_WPA_ENABLED:
-		param->value = 0;
-		break;
-
-	default:
-		return -EOPNOTSUPP;
-	}
-	return 0;
-}
-
-
-static int atmel_get_name(struct net_device *dev,
-			  struct iw_request_info *info,
-			  union iwreq_data *wrqu,
-			  char *extra)
-{
-	strcpy(wrqu->name, "IEEE 802.11-DS");
-	return 0;
-}
-
-static int atmel_set_rate(struct net_device *dev,
-			  struct iw_request_info *info,
-			  union iwreq_data *wrqu,
-			  char *extra)
-{
-	struct iw_param *vwrq = &wrqu->bitrate;
-	struct atmel_private *priv = netdev_priv(dev);
-
-	if (vwrq->fixed == 0) {
-		priv->tx_rate = 3;
-		priv->auto_tx_rate = 1;
-	} else {
-		priv->auto_tx_rate = 0;
-
-		/* Which type of value ? */
-		if ((vwrq->value < 4) && (vwrq->value >= 0)) {
-			/* Setting by rate index */
-			priv->tx_rate = vwrq->value;
-		} else {
-		/* Setting by frequency value */
-			switch (vwrq->value) {
-			case  1000000:
-				priv->tx_rate = 0;
-				break;
-			case  2000000:
-				priv->tx_rate = 1;
-				break;
-			case  5500000:
-				priv->tx_rate = 2;
-				break;
-			case 11000000:
-				priv->tx_rate = 3;
-				break;
-			default:
-				return -EINVAL;
-			}
-		}
-	}
-
-	return -EINPROGRESS;
-}
-
-static int atmel_set_mode(struct net_device *dev,
-			  struct iw_request_info *info,
-			  union iwreq_data *wrqu,
-			  char *extra)
-{
-	__u32 *uwrq = &wrqu->mode;
-	struct atmel_private *priv = netdev_priv(dev);
-
-	if (*uwrq != IW_MODE_ADHOC && *uwrq != IW_MODE_INFRA)
-		return -EINVAL;
-
-	priv->operating_mode = *uwrq;
-	return -EINPROGRESS;
-}
-
-static int atmel_get_mode(struct net_device *dev,
-			  struct iw_request_info *info,
-			  union iwreq_data *wrqu,
-			  char *extra)
-{
-	__u32 *uwrq = &wrqu->mode;
-	struct atmel_private *priv = netdev_priv(dev);
-
-	*uwrq = priv->operating_mode;
-	return 0;
-}
-
-static int atmel_get_rate(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *wrqu,
-			 char *extra)
-{
-	struct iw_param *vwrq = &wrqu->bitrate;
-	struct atmel_private *priv = netdev_priv(dev);
-
-	if (priv->auto_tx_rate) {
-		vwrq->fixed = 0;
-		vwrq->value = 11000000;
-	} else {
-		vwrq->fixed = 1;
-		switch (priv->tx_rate) {
-		case 0:
-			vwrq->value =  1000000;
-			break;
-		case 1:
-			vwrq->value =  2000000;
-			break;
-		case 2:
-			vwrq->value =  5500000;
-			break;
-		case 3:
-			vwrq->value = 11000000;
-			break;
-		}
-	}
-	return 0;
-}
-
-static int atmel_set_power(struct net_device *dev,
-			   struct iw_request_info *info,
-			   union iwreq_data *wrqu,
-			   char *extra)
-{
-	struct iw_param *vwrq = &wrqu->power;
-	struct atmel_private *priv = netdev_priv(dev);
-	priv->power_mode = vwrq->disabled ? 0 : 1;
-	return -EINPROGRESS;
-}
-
-static int atmel_get_power(struct net_device *dev,
-			   struct iw_request_info *info,
-			   union iwreq_data *wrqu,
-			   char *extra)
-{
-	struct iw_param *vwrq = &wrqu->power;
-	struct atmel_private *priv = netdev_priv(dev);
-	vwrq->disabled = priv->power_mode ? 0 : 1;
-	vwrq->flags = IW_POWER_ON;
-	return 0;
-}
-
-static int atmel_set_retry(struct net_device *dev,
-			   struct iw_request_info *info,
-			   union iwreq_data *wrqu,
-			   char *extra)
-{
-	struct iw_param *vwrq = &wrqu->retry;
-	struct atmel_private *priv = netdev_priv(dev);
-
-	if (!vwrq->disabled && (vwrq->flags & IW_RETRY_LIMIT)) {
-		if (vwrq->flags & IW_RETRY_LONG)
-			priv->long_retry = vwrq->value;
-		else if (vwrq->flags & IW_RETRY_SHORT)
-			priv->short_retry = vwrq->value;
-		else {
-			/* No modifier : set both */
-			priv->long_retry = vwrq->value;
-			priv->short_retry = vwrq->value;
-		}
-		return -EINPROGRESS;
-	}
-
-	return -EINVAL;
-}
-
-static int atmel_get_retry(struct net_device *dev,
-			   struct iw_request_info *info,
-			   union iwreq_data *wrqu,
-			   char *extra)
-{
-	struct iw_param *vwrq = &wrqu->retry;
-	struct atmel_private *priv = netdev_priv(dev);
-
-	vwrq->disabled = 0;      /* Can't be disabled */
-
-	/* Note : by default, display the short retry number */
-	if (vwrq->flags & IW_RETRY_LONG) {
-		vwrq->flags = IW_RETRY_LIMIT | IW_RETRY_LONG;
-		vwrq->value = priv->long_retry;
-	} else {
-		vwrq->flags = IW_RETRY_LIMIT;
-		vwrq->value = priv->short_retry;
-		if (priv->long_retry != priv->short_retry)
-			vwrq->flags |= IW_RETRY_SHORT;
-	}
-
-	return 0;
-}
-
-static int atmel_set_rts(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *wrqu,
-			 char *extra)
-{
-	struct iw_param *vwrq = &wrqu->rts;
-	struct atmel_private *priv = netdev_priv(dev);
-	int rthr = vwrq->value;
-
-	if (vwrq->disabled)
-		rthr = 2347;
-	if ((rthr < 0) || (rthr > 2347)) {
-		return -EINVAL;
-	}
-	priv->rts_threshold = rthr;
-
-	return -EINPROGRESS;		/* Call commit handler */
-}
-
-static int atmel_get_rts(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *wrqu,
-			 char *extra)
-{
-	struct iw_param *vwrq = &wrqu->rts;
-	struct atmel_private *priv = netdev_priv(dev);
-
-	vwrq->value = priv->rts_threshold;
-	vwrq->disabled = (vwrq->value >= 2347);
-	vwrq->fixed = 1;
-
-	return 0;
-}
-
-static int atmel_set_frag(struct net_device *dev,
-			  struct iw_request_info *info,
-			  union iwreq_data *wrqu,
-			  char *extra)
-{
-	struct iw_param *vwrq = &wrqu->frag;
-	struct atmel_private *priv = netdev_priv(dev);
-	int fthr = vwrq->value;
-
-	if (vwrq->disabled)
-		fthr = 2346;
-	if ((fthr < 256) || (fthr > 2346)) {
-		return -EINVAL;
-	}
-	fthr &= ~0x1;	/* Get an even value - is it really needed ??? */
-	priv->frag_threshold = fthr;
-
-	return -EINPROGRESS;		/* Call commit handler */
-}
-
-static int atmel_get_frag(struct net_device *dev,
-			  struct iw_request_info *info,
-			  union iwreq_data *wrqu,
-			  char *extra)
-{
-	struct iw_param *vwrq = &wrqu->frag;
-	struct atmel_private *priv = netdev_priv(dev);
-
-	vwrq->value = priv->frag_threshold;
-	vwrq->disabled = (vwrq->value >= 2346);
-	vwrq->fixed = 1;
-
-	return 0;
-}
-
-static int atmel_set_freq(struct net_device *dev,
-			  struct iw_request_info *info,
-			  union iwreq_data *wrqu,
-			  char *extra)
-{
-	struct iw_freq *fwrq = &wrqu->freq;
-	struct atmel_private *priv = netdev_priv(dev);
-	int rc = -EINPROGRESS;		/* Call commit handler */
-
-	/* If setting by frequency, convert to a channel */
-	if (fwrq->e == 1) {
-		int f = fwrq->m / 100000;
-
-		/* Hack to fall through... */
-		fwrq->e = 0;
-		fwrq->m = ieee80211_frequency_to_channel(f);
-	}
-	/* Setting by channel number */
-	if (fwrq->m < 0 || fwrq->m > 1000 || fwrq->e > 0)
-		rc = -EOPNOTSUPP;
-	else {
-		int channel = fwrq->m;
-		if (atmel_validate_channel(priv, channel) == 0) {
-			priv->channel = channel;
-		} else {
-			rc = -EINVAL;
-		}
-	}
-	return rc;
-}
-
-static int atmel_get_freq(struct net_device *dev,
-			  struct iw_request_info *info,
-			  union iwreq_data *wrqu,
-			  char *extra)
-{
-	struct iw_freq *fwrq = &wrqu->freq;
-	struct atmel_private *priv = netdev_priv(dev);
-
-	fwrq->m = priv->channel;
-	fwrq->e = 0;
-	return 0;
-}
-
-static int atmel_set_scan(struct net_device *dev,
-			  struct iw_request_info *info,
-			  union iwreq_data *dwrq,
-			  char *extra)
-{
-	struct atmel_private *priv = netdev_priv(dev);
-	unsigned long flags;
-
-	/* Note : you may have realised that, as this is a SET operation,
-	 * this is privileged and therefore a normal user can't
-	 * perform scanning.
-	 * This is not an error, while the device perform scanning,
-	 * traffic doesn't flow, so it's a perfect DoS...
-	 * Jean II */
-
-	if (priv->station_state == STATION_STATE_DOWN)
-		return -EAGAIN;
-
-	/* Timeout old surveys. */
-	if (time_after(jiffies, priv->last_survey + 20 * HZ))
-		priv->site_survey_state = SITE_SURVEY_IDLE;
-	priv->last_survey = jiffies;
-
-	/* Initiate a scan command */
-	if (priv->site_survey_state == SITE_SURVEY_IN_PROGRESS)
-		return -EBUSY;
-
-	del_timer_sync(&priv->management_timer);
-	spin_lock_irqsave(&priv->irqlock, flags);
-
-	priv->site_survey_state = SITE_SURVEY_IN_PROGRESS;
-	priv->fast_scan = 0;
-	atmel_scan(priv, 0);
-	spin_unlock_irqrestore(&priv->irqlock, flags);
-
-	return 0;
-}
-
-static int atmel_get_scan(struct net_device *dev,
-			  struct iw_request_info *info,
-			  union iwreq_data *wrqu,
-			  char *extra)
-{
-	struct iw_point *dwrq = &wrqu->data;
-	struct atmel_private *priv = netdev_priv(dev);
-	int i;
-	char *current_ev = extra;
-	struct iw_event	iwe;
-
-	if (priv->site_survey_state != SITE_SURVEY_COMPLETED)
-		return -EAGAIN;
-
-	for (i = 0; i < priv->BSS_list_entries; i++) {
-		iwe.cmd = SIOCGIWAP;
-		iwe.u.ap_addr.sa_family = ARPHRD_ETHER;
-		memcpy(iwe.u.ap_addr.sa_data, priv->BSSinfo[i].BSSID, ETH_ALEN);
-		current_ev = iwe_stream_add_event(info, current_ev,
-						  extra + IW_SCAN_MAX_DATA,
-						  &iwe, IW_EV_ADDR_LEN);
-
-		iwe.u.data.length =  priv->BSSinfo[i].SSIDsize;
-		if (iwe.u.data.length > 32)
-			iwe.u.data.length = 32;
-		iwe.cmd = SIOCGIWESSID;
-		iwe.u.data.flags = 1;
-		current_ev = iwe_stream_add_point(info, current_ev,
-						  extra + IW_SCAN_MAX_DATA,
-						  &iwe, priv->BSSinfo[i].SSID);
-
-		iwe.cmd = SIOCGIWMODE;
-		iwe.u.mode = priv->BSSinfo[i].BSStype;
-		current_ev = iwe_stream_add_event(info, current_ev,
-						  extra + IW_SCAN_MAX_DATA,
-						  &iwe, IW_EV_UINT_LEN);
-
-		iwe.cmd = SIOCGIWFREQ;
-		iwe.u.freq.m = priv->BSSinfo[i].channel;
-		iwe.u.freq.e = 0;
-		current_ev = iwe_stream_add_event(info, current_ev,
-						  extra + IW_SCAN_MAX_DATA,
-						  &iwe, IW_EV_FREQ_LEN);
-
-		/* Add quality statistics */
-		iwe.cmd = IWEVQUAL;
-		iwe.u.qual.level = priv->BSSinfo[i].RSSI;
-		iwe.u.qual.qual  = iwe.u.qual.level;
-		/* iwe.u.qual.noise  = SOMETHING */
-		current_ev = iwe_stream_add_event(info, current_ev,
-						  extra + IW_SCAN_MAX_DATA,
-						  &iwe, IW_EV_QUAL_LEN);
-
-
-		iwe.cmd = SIOCGIWENCODE;
-		if (priv->BSSinfo[i].UsingWEP)
-			iwe.u.data.flags = IW_ENCODE_ENABLED | IW_ENCODE_NOKEY;
-		else
-			iwe.u.data.flags = IW_ENCODE_DISABLED;
-		iwe.u.data.length = 0;
-		current_ev = iwe_stream_add_point(info, current_ev,
-						  extra + IW_SCAN_MAX_DATA,
-						  &iwe, NULL);
-	}
-
-	/* Length of data */
-	dwrq->length = (current_ev - extra);
-	dwrq->flags = 0;
-
-	return 0;
-}
-
-static int atmel_get_range(struct net_device *dev,
-			   struct iw_request_info *info,
-			   union iwreq_data *wrqu,
-			   char *extra)
-{
-	struct iw_point *dwrq = &wrqu->data;
-	struct atmel_private *priv = netdev_priv(dev);
-	struct iw_range *range = (struct iw_range *) extra;
-	int k, i, j;
-
-	dwrq->length = sizeof(struct iw_range);
-	memset(range, 0, sizeof(struct iw_range));
-	range->min_nwid = 0x0000;
-	range->max_nwid = 0x0000;
-	range->num_channels = 0;
-	for (j = 0; j < ARRAY_SIZE(channel_table); j++)
-		if (priv->reg_domain == channel_table[j].reg_domain) {
-			range->num_channels = channel_table[j].max - channel_table[j].min + 1;
-			break;
-		}
-	if (range->num_channels != 0) {
-		for (k = 0, i = channel_table[j].min; i <= channel_table[j].max; i++) {
-			range->freq[k].i = i; /* List index */
-
-			/* Values in MHz -> * 10^5 * 10 */
-			range->freq[k].m = 100000 *
-			 ieee80211_channel_to_frequency(i, NL80211_BAND_2GHZ);
-			range->freq[k++].e = 1;
-		}
-		range->num_frequency = k;
-	}
-
-	range->max_qual.qual = 100;
-	range->max_qual.level = 100;
-	range->max_qual.noise = 0;
-	range->max_qual.updated = IW_QUAL_NOISE_INVALID;
-
-	range->avg_qual.qual = 50;
-	range->avg_qual.level = 50;
-	range->avg_qual.noise = 0;
-	range->avg_qual.updated = IW_QUAL_NOISE_INVALID;
-
-	range->sensitivity = 0;
-
-	range->bitrate[0] =  1000000;
-	range->bitrate[1] =  2000000;
-	range->bitrate[2] =  5500000;
-	range->bitrate[3] = 11000000;
-	range->num_bitrates = 4;
-
-	range->min_rts = 0;
-	range->max_rts = 2347;
-	range->min_frag = 256;
-	range->max_frag = 2346;
-
-	range->encoding_size[0] = 5;
-	range->encoding_size[1] = 13;
-	range->num_encoding_sizes = 2;
-	range->max_encoding_tokens = 4;
-
-	range->pmp_flags = IW_POWER_ON;
-	range->pmt_flags = IW_POWER_ON;
-	range->pm_capa = 0;
-
-	range->we_version_source = WIRELESS_EXT;
-	range->we_version_compiled = WIRELESS_EXT;
-	range->retry_capa = IW_RETRY_LIMIT ;
-	range->retry_flags = IW_RETRY_LIMIT;
-	range->r_time_flags = 0;
-	range->min_retry = 1;
-	range->max_retry = 65535;
-
-	return 0;
-}
-
-static int atmel_set_wap(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *wrqu,
-			 char *extra)
-{
-	struct sockaddr *awrq = &wrqu->ap_addr;
-	struct atmel_private *priv = netdev_priv(dev);
-	int i;
-	static const u8 any[] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF };
-	static const u8 off[] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
-	unsigned long flags;
-
-	if (awrq->sa_family != ARPHRD_ETHER)
-		return -EINVAL;
-
-	if (!memcmp(any, awrq->sa_data, 6) ||
-	    !memcmp(off, awrq->sa_data, 6)) {
-		del_timer_sync(&priv->management_timer);
-		spin_lock_irqsave(&priv->irqlock, flags);
-		atmel_scan(priv, 1);
-		spin_unlock_irqrestore(&priv->irqlock, flags);
-		return 0;
-	}
-
-	for (i = 0; i < priv->BSS_list_entries; i++) {
-		if (memcmp(priv->BSSinfo[i].BSSID, awrq->sa_data, 6) == 0) {
-			if (!priv->wep_is_on && priv->BSSinfo[i].UsingWEP) {
-				return -EINVAL;
-			} else if  (priv->wep_is_on && !priv->BSSinfo[i].UsingWEP) {
-				return -EINVAL;
-			} else {
-				del_timer_sync(&priv->management_timer);
-				spin_lock_irqsave(&priv->irqlock, flags);
-				atmel_join_bss(priv, i);
-				spin_unlock_irqrestore(&priv->irqlock, flags);
-				return 0;
-			}
-		}
-	}
-
-	return -EINVAL;
-}
-
-static int atmel_config_commit(struct net_device *dev,
-			       struct iw_request_info *info,	/* NULL */
-			       union iwreq_data *zwrq,		/* NULL */
-			       char *extra)			/* NULL */
-{
-	return atmel_open(dev);
-}
-
-static const iw_handler atmel_handler[] =
-{
-	IW_HANDLER(SIOCSIWCOMMIT,	atmel_config_commit),
-	IW_HANDLER(SIOCGIWNAME,		atmel_get_name),
-	IW_HANDLER(SIOCSIWFREQ,		atmel_set_freq),
-	IW_HANDLER(SIOCGIWFREQ,		atmel_get_freq),
-	IW_HANDLER(SIOCSIWMODE,		atmel_set_mode),
-	IW_HANDLER(SIOCGIWMODE,		atmel_get_mode),
-	IW_HANDLER(SIOCGIWRANGE,	atmel_get_range),
-	IW_HANDLER(SIOCSIWAP,		atmel_set_wap),
-	IW_HANDLER(SIOCGIWAP,		atmel_get_wap),
-	IW_HANDLER(SIOCSIWSCAN,		atmel_set_scan),
-	IW_HANDLER(SIOCGIWSCAN,		atmel_get_scan),
-	IW_HANDLER(SIOCSIWESSID,	atmel_set_essid),
-	IW_HANDLER(SIOCGIWESSID,	atmel_get_essid),
-	IW_HANDLER(SIOCSIWRATE,		atmel_set_rate),
-	IW_HANDLER(SIOCGIWRATE,		atmel_get_rate),
-	IW_HANDLER(SIOCSIWRTS,		atmel_set_rts),
-	IW_HANDLER(SIOCGIWRTS,		atmel_get_rts),
-	IW_HANDLER(SIOCSIWFRAG,		atmel_set_frag),
-	IW_HANDLER(SIOCGIWFRAG,		atmel_get_frag),
-	IW_HANDLER(SIOCSIWRETRY,	atmel_set_retry),
-	IW_HANDLER(SIOCGIWRETRY,	atmel_get_retry),
-	IW_HANDLER(SIOCSIWENCODE,	atmel_set_encode),
-	IW_HANDLER(SIOCGIWENCODE,	atmel_get_encode),
-	IW_HANDLER(SIOCSIWPOWER,	atmel_set_power),
-	IW_HANDLER(SIOCGIWPOWER,	atmel_get_power),
-	IW_HANDLER(SIOCSIWAUTH,		atmel_set_auth),
-	IW_HANDLER(SIOCGIWAUTH,		atmel_get_auth),
-	IW_HANDLER(SIOCSIWENCODEEXT,	atmel_set_encodeext),
-	IW_HANDLER(SIOCGIWENCODEEXT,	atmel_get_encodeext),
-};
-
-static const iw_handler atmel_private_handler[] =
-{
-	NULL,				/* SIOCIWFIRSTPRIV */
-};
-
-struct atmel_priv_ioctl {
-	char id[32];
-	unsigned char __user *data;
-	unsigned short len;
-};
-
-#define ATMELFWL	SIOCIWFIRSTPRIV
-#define ATMELIDIFC	ATMELFWL + 1
-#define ATMELRD		ATMELFWL + 2
-#define ATMELMAGIC 0x51807
-#define REGDOMAINSZ 20
-
-static const struct iw_priv_args atmel_private_args[] = {
-	{
-		.cmd = ATMELFWL,
-		.set_args = IW_PRIV_TYPE_BYTE
-				| IW_PRIV_SIZE_FIXED
-				| sizeof(struct atmel_priv_ioctl),
-		.get_args = IW_PRIV_TYPE_NONE,
-		.name = "atmelfwl"
-	}, {
-		.cmd = ATMELIDIFC,
-		.set_args = IW_PRIV_TYPE_NONE,
-		.get_args = IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1,
-		.name = "atmelidifc"
-	}, {
-		.cmd = ATMELRD,
-		.set_args = IW_PRIV_TYPE_CHAR | REGDOMAINSZ,
-		.get_args = IW_PRIV_TYPE_NONE,
-		.name = "regdomain"
-	},
-};
-
-static const struct iw_handler_def atmel_handler_def = {
-	.num_standard	= ARRAY_SIZE(atmel_handler),
-	.num_private	= ARRAY_SIZE(atmel_private_handler),
-	.num_private_args = ARRAY_SIZE(atmel_private_args),
-	.standard	= atmel_handler,
-	.private	= atmel_private_handler,
-	.private_args	= (struct iw_priv_args *) atmel_private_args,
-	.get_wireless_stats = atmel_get_wireless_stats
-};
-
-struct auth_body {
-	__le16 alg;
-	__le16 trans_seq;
-	__le16 status;
-	u8 el_id;
-	u8 chall_text_len;
-	u8 chall_text[253];
-};
-
-static void atmel_enter_state(struct atmel_private *priv, int new_state)
-{
-	int old_state = priv->station_state;
-
-	if (new_state == old_state)
-		return;
-
-	priv->station_state = new_state;
-
-	if (new_state == STATION_STATE_READY) {
-		netif_start_queue(priv->dev);
-		netif_carrier_on(priv->dev);
-	}
-
-	if (old_state == STATION_STATE_READY) {
-		netif_carrier_off(priv->dev);
-		if (netif_running(priv->dev))
-			netif_stop_queue(priv->dev);
-		priv->last_beacon_timestamp = 0;
-	}
-}
-
-static void atmel_scan(struct atmel_private *priv, int specific_ssid)
-{
-	struct {
-		u8 BSSID[ETH_ALEN];
-		u8 SSID[MAX_SSID_LENGTH];
-		u8 scan_type;
-		u8 channel;
-		__le16 BSS_type;
-		__le16 min_channel_time;
-		__le16 max_channel_time;
-		u8 options;
-		u8 SSID_size;
-	} cmd;
-
-	eth_broadcast_addr(cmd.BSSID);
-
-	if (priv->fast_scan) {
-		cmd.SSID_size = priv->SSID_size;
-		memcpy(cmd.SSID, priv->SSID, priv->SSID_size);
-		cmd.min_channel_time = cpu_to_le16(10);
-		cmd.max_channel_time = cpu_to_le16(50);
-	} else {
-		priv->BSS_list_entries = 0;
-		cmd.SSID_size = 0;
-		cmd.min_channel_time = cpu_to_le16(10);
-		cmd.max_channel_time = cpu_to_le16(120);
-	}
-
-	cmd.options = 0;
-
-	if (!specific_ssid)
-		cmd.options |= SCAN_OPTIONS_SITE_SURVEY;
-
-	cmd.channel = (priv->channel & 0x7f);
-	cmd.scan_type = SCAN_TYPE_ACTIVE;
-	cmd.BSS_type = cpu_to_le16(priv->operating_mode == IW_MODE_ADHOC ?
-		BSS_TYPE_AD_HOC : BSS_TYPE_INFRASTRUCTURE);
-
-	atmel_send_command(priv, CMD_Scan, &cmd, sizeof(cmd));
-
-	/* This must come after all hardware access to avoid being messed up
-	   by stuff happening in interrupt context after we leave STATE_DOWN */
-	atmel_enter_state(priv, STATION_STATE_SCANNING);
-}
-
-static void join(struct atmel_private *priv, int type)
-{
-	struct {
-		u8 BSSID[6];
-		u8 SSID[MAX_SSID_LENGTH];
-		u8 BSS_type; /* this is a short in a scan command - weird */
-		u8 channel;
-		__le16 timeout;
-		u8 SSID_size;
-		u8 reserved;
-	} cmd;
-
-	cmd.SSID_size = priv->SSID_size;
-	memcpy(cmd.SSID, priv->SSID, priv->SSID_size);
-	memcpy(cmd.BSSID, priv->CurrentBSSID, ETH_ALEN);
-	cmd.channel = (priv->channel & 0x7f);
-	cmd.BSS_type = type;
-	cmd.timeout = cpu_to_le16(2000);
-
-	atmel_send_command(priv, CMD_Join, &cmd, sizeof(cmd));
-}
-
-static void start(struct atmel_private *priv, int type)
-{
-	struct {
-		u8 BSSID[6];
-		u8 SSID[MAX_SSID_LENGTH];
-		u8 BSS_type;
-		u8 channel;
-		u8 SSID_size;
-		u8 reserved[3];
-	} cmd;
-
-	cmd.SSID_size = priv->SSID_size;
-	memcpy(cmd.SSID, priv->SSID, priv->SSID_size);
-	memcpy(cmd.BSSID, priv->BSSID, ETH_ALEN);
-	cmd.BSS_type = type;
-	cmd.channel = (priv->channel & 0x7f);
-
-	atmel_send_command(priv, CMD_Start, &cmd, sizeof(cmd));
-}
-
-static void handle_beacon_probe(struct atmel_private *priv, u16 capability,
-				u8 channel)
-{
-	int rejoin = 0;
-	int new = capability & WLAN_CAPABILITY_SHORT_PREAMBLE ?
-		SHORT_PREAMBLE : LONG_PREAMBLE;
-
-	if (priv->preamble != new) {
-		priv->preamble = new;
-		rejoin = 1;
-		atmel_set_mib8(priv, Local_Mib_Type, LOCAL_MIB_PREAMBLE_TYPE, new);
-	}
-
-	if (priv->channel != channel) {
-		priv->channel = channel;
-		rejoin = 1;
-		atmel_set_mib8(priv, Phy_Mib_Type, PHY_MIB_CHANNEL_POS, channel);
-	}
-
-	if (rejoin) {
-		priv->station_is_associated = 0;
-		atmel_enter_state(priv, STATION_STATE_JOINNING);
-
-		if (priv->operating_mode == IW_MODE_INFRA)
-			join(priv, BSS_TYPE_INFRASTRUCTURE);
-		else
-			join(priv, BSS_TYPE_AD_HOC);
-	}
-}
-
-static void send_authentication_request(struct atmel_private *priv, u16 system,
-					u8 *challenge, int challenge_len)
-{
-	struct ieee80211_hdr header;
-	struct auth_body auth;
-
-	header.frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_AUTH);
-	header.duration_id = cpu_to_le16(0x8000);
-	header.seq_ctrl = 0;
-	memcpy(header.addr1, priv->CurrentBSSID, ETH_ALEN);
-	memcpy(header.addr2, priv->dev->dev_addr, ETH_ALEN);
-	memcpy(header.addr3, priv->CurrentBSSID, ETH_ALEN);
-
-	if (priv->wep_is_on && priv->CurrentAuthentTransactionSeqNum != 1)
-		/* no WEP for authentication frames with TrSeqNo 1 */
-		header.frame_control |=  cpu_to_le16(IEEE80211_FCTL_PROTECTED);
-
-	auth.alg = cpu_to_le16(system);
-
-	auth.status = 0;
-	auth.trans_seq = cpu_to_le16(priv->CurrentAuthentTransactionSeqNum);
-	priv->ExpectedAuthentTransactionSeqNum = priv->CurrentAuthentTransactionSeqNum+1;
-	priv->CurrentAuthentTransactionSeqNum += 2;
-
-	if (challenge_len != 0)	{
-		auth.el_id = 16; /* challenge_text */
-		auth.chall_text_len = challenge_len;
-		memcpy(auth.chall_text, challenge, challenge_len);
-		atmel_transmit_management_frame(priv, &header, (u8 *)&auth, 8 + challenge_len);
-	} else {
-		atmel_transmit_management_frame(priv, &header, (u8 *)&auth, 6);
-	}
-}
-
-static void send_association_request(struct atmel_private *priv, int is_reassoc)
-{
-	u8 *ssid_el_p;
-	int bodysize;
-	struct ieee80211_hdr header;
-	struct ass_req_format {
-		__le16 capability;
-		__le16 listen_interval;
-		u8 ap[ETH_ALEN]; /* nothing after here directly accessible */
-		u8 ssid_el_id;
-		u8 ssid_len;
-		u8 ssid[MAX_SSID_LENGTH];
-		u8 sup_rates_el_id;
-		u8 sup_rates_len;
-		u8 rates[4];
-	} body;
-
-	header.frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
-		(is_reassoc ? IEEE80211_STYPE_REASSOC_REQ : IEEE80211_STYPE_ASSOC_REQ));
-	header.duration_id = cpu_to_le16(0x8000);
-	header.seq_ctrl = 0;
-
-	memcpy(header.addr1, priv->CurrentBSSID, ETH_ALEN);
-	memcpy(header.addr2, priv->dev->dev_addr, ETH_ALEN);
-	memcpy(header.addr3, priv->CurrentBSSID, ETH_ALEN);
-
-	body.capability = cpu_to_le16(WLAN_CAPABILITY_ESS);
-	if (priv->wep_is_on)
-		body.capability |= cpu_to_le16(WLAN_CAPABILITY_PRIVACY);
-	if (priv->preamble == SHORT_PREAMBLE)
-		body.capability |= cpu_to_le16(WLAN_CAPABILITY_SHORT_PREAMBLE);
-
-	body.listen_interval = cpu_to_le16(priv->listen_interval * priv->beacon_period);
-
-	/* current AP address - only in reassoc frame */
-	if (is_reassoc) {
-		memcpy(body.ap, priv->CurrentBSSID, ETH_ALEN);
-		ssid_el_p = &body.ssid_el_id;
-		bodysize = 18 + priv->SSID_size;
-	} else {
-		ssid_el_p = &body.ap[0];
-		bodysize = 12 + priv->SSID_size;
-	}
-
-	ssid_el_p[0] = WLAN_EID_SSID;
-	ssid_el_p[1] = priv->SSID_size;
-	memcpy(ssid_el_p + 2, priv->SSID, priv->SSID_size);
-	ssid_el_p[2 + priv->SSID_size] = WLAN_EID_SUPP_RATES;
-	ssid_el_p[3 + priv->SSID_size] = 4; /* len of supported rates */
-	memcpy(ssid_el_p + 4 + priv->SSID_size, atmel_basic_rates, 4);
-
-	atmel_transmit_management_frame(priv, &header, (void *)&body, bodysize);
-}
-
-static int is_frame_from_current_bss(struct atmel_private *priv,
-				     struct ieee80211_hdr *header)
-{
-	if (le16_to_cpu(header->frame_control) & IEEE80211_FCTL_FROMDS)
-		return memcmp(header->addr3, priv->CurrentBSSID, 6) == 0;
-	else
-		return memcmp(header->addr2, priv->CurrentBSSID, 6) == 0;
-}
-
-static int retrieve_bss(struct atmel_private *priv)
-{
-	int i;
-	int max_rssi = -128;
-	int max_index = -1;
-
-	if (priv->BSS_list_entries == 0)
-		return -1;
-
-	if (priv->connect_to_any_BSS) {
-		/* Select a BSS with the max-RSSI but of the same type and of
-		   the same WEP mode and that it is not marked as 'bad' (i.e.
-		   we had previously failed to connect to this BSS with the
-		   settings that we currently use) */
-		priv->current_BSS = 0;
-		for (i = 0; i < priv->BSS_list_entries; i++) {
-			if (priv->operating_mode == priv->BSSinfo[i].BSStype &&
-			    ((!priv->wep_is_on && !priv->BSSinfo[i].UsingWEP) ||
-			     (priv->wep_is_on && priv->BSSinfo[i].UsingWEP)) &&
-			    !(priv->BSSinfo[i].channel & 0x80)) {
-				max_rssi = priv->BSSinfo[i].RSSI;
-				priv->current_BSS = max_index = i;
-			}
-		}
-		return max_index;
-	}
-
-	for (i = 0; i < priv->BSS_list_entries; i++) {
-		if (priv->SSID_size == priv->BSSinfo[i].SSIDsize &&
-		    memcmp(priv->SSID, priv->BSSinfo[i].SSID, priv->SSID_size) == 0 &&
-		    priv->operating_mode == priv->BSSinfo[i].BSStype &&
-		    atmel_validate_channel(priv, priv->BSSinfo[i].channel) == 0) {
-			if (priv->BSSinfo[i].RSSI >= max_rssi) {
-				max_rssi = priv->BSSinfo[i].RSSI;
-				max_index = i;
-			}
-		}
-	}
-	return max_index;
-}
-
-static void store_bss_info(struct atmel_private *priv,
-			   struct ieee80211_hdr *header, u16 capability,
-			   u16 beacon_period, u8 channel, u8 rssi, u8 ssid_len,
-			   u8 *ssid, int is_beacon)
-{
-	u8 *bss = capability & WLAN_CAPABILITY_ESS ? header->addr2 : header->addr3;
-	int i, index;
-
-	for (index = -1, i = 0; i < priv->BSS_list_entries; i++)
-		if (memcmp(bss, priv->BSSinfo[i].BSSID, ETH_ALEN) == 0)
-			index = i;
-
-	/* If we process a probe and an entry from this BSS exists
-	   we will update the BSS entry with the info from this BSS.
-	   If we process a beacon we will only update RSSI */
-
-	if (index == -1) {
-		if (priv->BSS_list_entries == MAX_BSS_ENTRIES)
-			return;
-		index = priv->BSS_list_entries++;
-		memcpy(priv->BSSinfo[index].BSSID, bss, ETH_ALEN);
-		priv->BSSinfo[index].RSSI = rssi;
-	} else {
-		if (rssi > priv->BSSinfo[index].RSSI)
-			priv->BSSinfo[index].RSSI = rssi;
-		if (is_beacon)
-			return;
-	}
-
-	priv->BSSinfo[index].channel = channel;
-	priv->BSSinfo[index].beacon_period = beacon_period;
-	priv->BSSinfo[index].UsingWEP = capability & WLAN_CAPABILITY_PRIVACY;
-	memcpy(priv->BSSinfo[index].SSID, ssid, ssid_len);
-	priv->BSSinfo[index].SSIDsize = ssid_len;
-
-	if (capability & WLAN_CAPABILITY_IBSS)
-		priv->BSSinfo[index].BSStype = IW_MODE_ADHOC;
-	else if (capability & WLAN_CAPABILITY_ESS)
-		priv->BSSinfo[index].BSStype = IW_MODE_INFRA;
-
-	priv->BSSinfo[index].preamble = capability & WLAN_CAPABILITY_SHORT_PREAMBLE ?
-		SHORT_PREAMBLE : LONG_PREAMBLE;
-}
-
-static void authenticate(struct atmel_private *priv, u16 frame_len)
-{
-	struct auth_body *auth = (struct auth_body *)priv->rx_buf;
-	u16 status = le16_to_cpu(auth->status);
-	u16 trans_seq_no = le16_to_cpu(auth->trans_seq);
-	u16 system = le16_to_cpu(auth->alg);
-
-	if (status == WLAN_STATUS_SUCCESS && !priv->wep_is_on) {
-		/* no WEP */
-		if (priv->station_was_associated) {
-			atmel_enter_state(priv, STATION_STATE_REASSOCIATING);
-			send_association_request(priv, 1);
-			return;
-		} else {
-			atmel_enter_state(priv, STATION_STATE_ASSOCIATING);
-			send_association_request(priv, 0);
-			return;
-		}
-	}
-
-	if (status == WLAN_STATUS_SUCCESS && priv->wep_is_on) {
-		int should_associate = 0;
-		/* WEP */
-		if (trans_seq_no != priv->ExpectedAuthentTransactionSeqNum)
-			return;
-
-		if (system == WLAN_AUTH_OPEN) {
-			if (trans_seq_no == 0x0002) {
-				should_associate = 1;
-			}
-		} else if (system == WLAN_AUTH_SHARED_KEY) {
-			if (trans_seq_no == 0x0002 &&
-			    auth->el_id == WLAN_EID_CHALLENGE) {
-				send_authentication_request(priv, system, auth->chall_text, auth->chall_text_len);
-				return;
-			} else if (trans_seq_no == 0x0004) {
-				should_associate = 1;
-			}
-		}
-
-		if (should_associate) {
-			if (priv->station_was_associated) {
-				atmel_enter_state(priv, STATION_STATE_REASSOCIATING);
-				send_association_request(priv, 1);
-				return;
-			} else {
-				atmel_enter_state(priv, STATION_STATE_ASSOCIATING);
-				send_association_request(priv, 0);
-				return;
-			}
-		}
-	}
-
-	if (status == WLAN_STATUS_NOT_SUPPORTED_AUTH_ALG) {
-		/* Flip back and forth between WEP auth modes until the max
-		 * authentication tries has been exceeded.
-		 */
-		if (system == WLAN_AUTH_OPEN) {
-			priv->CurrentAuthentTransactionSeqNum = 0x001;
-			priv->exclude_unencrypted = 1;
-			send_authentication_request(priv, WLAN_AUTH_SHARED_KEY, NULL, 0);
-			return;
-		} else if (system == WLAN_AUTH_SHARED_KEY
-			   && priv->wep_is_on) {
-			priv->CurrentAuthentTransactionSeqNum = 0x001;
-			priv->exclude_unencrypted = 0;
-			send_authentication_request(priv, WLAN_AUTH_OPEN, NULL, 0);
-			return;
-		} else if (priv->connect_to_any_BSS) {
-			int bss_index;
-
-			priv->BSSinfo[(int)(priv->current_BSS)].channel |= 0x80;
-
-			if ((bss_index  = retrieve_bss(priv)) != -1) {
-				atmel_join_bss(priv, bss_index);
-				return;
-			}
-		}
-	}
-
-	priv->AuthenticationRequestRetryCnt = 0;
-	atmel_enter_state(priv,  STATION_STATE_MGMT_ERROR);
-	priv->station_is_associated = 0;
-}
-
-static void associate(struct atmel_private *priv, u16 frame_len, u16 subtype)
-{
-	struct ass_resp_format {
-		__le16 capability;
-		__le16 status;
-		__le16 ass_id;
-		u8 el_id;
-		u8 length;
-		u8 rates[4];
-	} *ass_resp = (struct ass_resp_format *)priv->rx_buf;
-
-	u16 status = le16_to_cpu(ass_resp->status);
-	u16 ass_id = le16_to_cpu(ass_resp->ass_id);
-	u16 rates_len = ass_resp->length > 4 ? 4 : ass_resp->length;
-
-	union iwreq_data wrqu;
-
-	if (frame_len < 8 + rates_len)
-		return;
-
-	if (status == WLAN_STATUS_SUCCESS) {
-		if (subtype == IEEE80211_STYPE_ASSOC_RESP)
-			priv->AssociationRequestRetryCnt = 0;
-		else
-			priv->ReAssociationRequestRetryCnt = 0;
-
-		atmel_set_mib16(priv, Mac_Mgmt_Mib_Type,
-				MAC_MGMT_MIB_STATION_ID_POS, ass_id & 0x3fff);
-		atmel_set_mib(priv, Phy_Mib_Type,
-			      PHY_MIB_RATE_SET_POS, ass_resp->rates, rates_len);
-		if (priv->power_mode == 0) {
-			priv->listen_interval = 1;
-			atmel_set_mib8(priv, Mac_Mgmt_Mib_Type,
-				       MAC_MGMT_MIB_PS_MODE_POS, ACTIVE_MODE);
-			atmel_set_mib16(priv, Mac_Mgmt_Mib_Type,
-					MAC_MGMT_MIB_LISTEN_INTERVAL_POS, 1);
-		} else {
-			priv->listen_interval = 2;
-			atmel_set_mib8(priv, Mac_Mgmt_Mib_Type,
-				       MAC_MGMT_MIB_PS_MODE_POS,  PS_MODE);
-			atmel_set_mib16(priv, Mac_Mgmt_Mib_Type,
-					MAC_MGMT_MIB_LISTEN_INTERVAL_POS, 2);
-		}
-
-		priv->station_is_associated = 1;
-		priv->station_was_associated = 1;
-		atmel_enter_state(priv, STATION_STATE_READY);
-
-		/* Send association event to userspace */
-		wrqu.data.length = 0;
-		wrqu.data.flags = 0;
-		memcpy(wrqu.ap_addr.sa_data, priv->CurrentBSSID, ETH_ALEN);
-		wrqu.ap_addr.sa_family = ARPHRD_ETHER;
-		wireless_send_event(priv->dev, SIOCGIWAP, &wrqu, NULL);
-
-		return;
-	}
-
-	if (subtype == IEEE80211_STYPE_ASSOC_RESP &&
-	    status != WLAN_STATUS_ASSOC_DENIED_RATES &&
-	    status != WLAN_STATUS_CAPS_UNSUPPORTED &&
-	    priv->AssociationRequestRetryCnt < MAX_ASSOCIATION_RETRIES) {
-		mod_timer(&priv->management_timer, jiffies + MGMT_JIFFIES);
-		priv->AssociationRequestRetryCnt++;
-		send_association_request(priv, 0);
-		return;
-	}
-
-	if (subtype == IEEE80211_STYPE_REASSOC_RESP &&
-	    status != WLAN_STATUS_ASSOC_DENIED_RATES &&
-	    status != WLAN_STATUS_CAPS_UNSUPPORTED &&
-	    priv->ReAssociationRequestRetryCnt < MAX_ASSOCIATION_RETRIES) {
-		mod_timer(&priv->management_timer, jiffies + MGMT_JIFFIES);
-		priv->ReAssociationRequestRetryCnt++;
-		send_association_request(priv, 1);
-		return;
-	}
-
-	atmel_enter_state(priv,  STATION_STATE_MGMT_ERROR);
-	priv->station_is_associated = 0;
-
-	if (priv->connect_to_any_BSS) {
-		int bss_index;
-		priv->BSSinfo[(int)(priv->current_BSS)].channel |= 0x80;
-
-		if ((bss_index = retrieve_bss(priv)) != -1)
-			atmel_join_bss(priv, bss_index);
-	}
-}
-
-static void atmel_join_bss(struct atmel_private *priv, int bss_index)
-{
-	struct bss_info *bss =  &priv->BSSinfo[bss_index];
-
-	memcpy(priv->CurrentBSSID, bss->BSSID, ETH_ALEN);
-	memcpy(priv->SSID, bss->SSID, priv->SSID_size = bss->SSIDsize);
-
-	/* The WPA stuff cares about the current AP address */
-	if (priv->use_wpa)
-		build_wpa_mib(priv);
-
-	/* When switching to AdHoc turn OFF Power Save if needed */
-
-	if (bss->BSStype == IW_MODE_ADHOC &&
-	    priv->operating_mode != IW_MODE_ADHOC &&
-	    priv->power_mode) {
-		priv->power_mode = 0;
-		priv->listen_interval = 1;
-		atmel_set_mib8(priv, Mac_Mgmt_Mib_Type,
-			       MAC_MGMT_MIB_PS_MODE_POS,  ACTIVE_MODE);
-		atmel_set_mib16(priv, Mac_Mgmt_Mib_Type,
-				MAC_MGMT_MIB_LISTEN_INTERVAL_POS, 1);
-	}
-
-	priv->operating_mode = bss->BSStype;
-	priv->channel = bss->channel & 0x7f;
-	priv->beacon_period = bss->beacon_period;
-
-	if (priv->preamble != bss->preamble) {
-		priv->preamble = bss->preamble;
-		atmel_set_mib8(priv, Local_Mib_Type,
-			       LOCAL_MIB_PREAMBLE_TYPE, bss->preamble);
-	}
-
-	if (!priv->wep_is_on && bss->UsingWEP) {
-		atmel_enter_state(priv, STATION_STATE_MGMT_ERROR);
-		priv->station_is_associated = 0;
-		return;
-	}
-
-	if (priv->wep_is_on && !bss->UsingWEP) {
-		atmel_enter_state(priv, STATION_STATE_MGMT_ERROR);
-		priv->station_is_associated = 0;
-		return;
-	}
-
-	atmel_enter_state(priv, STATION_STATE_JOINNING);
-
-	if (priv->operating_mode == IW_MODE_INFRA)
-		join(priv, BSS_TYPE_INFRASTRUCTURE);
-	else
-		join(priv, BSS_TYPE_AD_HOC);
-}
-
-static void restart_search(struct atmel_private *priv)
-{
-	int bss_index;
-
-	if (!priv->connect_to_any_BSS) {
-		atmel_scan(priv, 1);
-	} else {
-		priv->BSSinfo[(int)(priv->current_BSS)].channel |= 0x80;
-
-		if ((bss_index = retrieve_bss(priv)) != -1)
-			atmel_join_bss(priv, bss_index);
-		else
-			atmel_scan(priv, 0);
-	}
-}
-
-static void smooth_rssi(struct atmel_private *priv, u8 rssi)
-{
-	u8 old = priv->wstats.qual.level;
-	u8 max_rssi = 42; /* 502-rmfd-revd max by experiment, default for now */
-
-	switch (priv->firmware_type) {
-	case ATMEL_FW_TYPE_502E:
-		max_rssi = 63; /* 502-rmfd-reve max by experiment */
-		break;
-	default:
-		break;
-	}
-
-	rssi = rssi * 100 / max_rssi;
-	if ((rssi + old) % 2)
-		priv->wstats.qual.level = (rssi + old) / 2 + 1;
-	else
-		priv->wstats.qual.level = (rssi + old) / 2;
-	priv->wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED;
-	priv->wstats.qual.updated &= ~IW_QUAL_LEVEL_INVALID;
-}
-
-static void atmel_smooth_qual(struct atmel_private *priv)
-{
-	unsigned long time_diff = (jiffies - priv->last_qual) / HZ;
-	while (time_diff--) {
-		priv->last_qual += HZ;
-		priv->wstats.qual.qual = priv->wstats.qual.qual / 2;
-		priv->wstats.qual.qual +=
-			priv->beacons_this_sec * priv->beacon_period * (priv->wstats.qual.level + 100) / 4000;
-		priv->beacons_this_sec = 0;
-	}
-	priv->wstats.qual.updated |= IW_QUAL_QUAL_UPDATED;
-	priv->wstats.qual.updated &= ~IW_QUAL_QUAL_INVALID;
-}
-
-/* deals with incoming management frames. */
-static void atmel_management_frame(struct atmel_private *priv,
-				   struct ieee80211_hdr *header,
-				   u16 frame_len, u8 rssi)
-{
-	u16 subtype;
-
-	subtype = le16_to_cpu(header->frame_control) & IEEE80211_FCTL_STYPE;
-	switch (subtype) {
-	case IEEE80211_STYPE_BEACON:
-	case IEEE80211_STYPE_PROBE_RESP:
-
-		/* beacon frame has multiple variable-length fields -
-		   never let an engineer loose with a data structure design. */
-		{
-			struct beacon_format {
-				__le64 timestamp;
-				__le16 interval;
-				__le16 capability;
-				u8 ssid_el_id;
-				u8 ssid_length;
-				/* ssid here */
-				u8 rates_el_id;
-				u8 rates_length;
-				/* rates here */
-				u8 ds_el_id;
-				u8 ds_length;
-				/* ds here */
-			} *beacon = (struct beacon_format *)priv->rx_buf;
-
-			u8 channel, rates_length, ssid_length;
-			u64 timestamp = le64_to_cpu(beacon->timestamp);
-			u16 beacon_interval = le16_to_cpu(beacon->interval);
-			u16 capability = le16_to_cpu(beacon->capability);
-			u8 *beaconp = priv->rx_buf;
-			ssid_length = beacon->ssid_length;
-			/* this blows chunks. */
-			if (frame_len < 14 || frame_len < ssid_length + 15)
-				return;
-			rates_length = beaconp[beacon->ssid_length + 15];
-			if (frame_len < ssid_length + rates_length + 18)
-				return;
-			if (ssid_length >  MAX_SSID_LENGTH)
-				return;
-			channel = beaconp[ssid_length + rates_length + 18];
-
-			if (priv->station_state == STATION_STATE_READY) {
-				smooth_rssi(priv, rssi);
-				if (is_frame_from_current_bss(priv, header)) {
-					priv->beacons_this_sec++;
-					atmel_smooth_qual(priv);
-					if (priv->last_beacon_timestamp) {
-						/* Note truncate this to 32 bits - kernel can't divide a long */
-						u32 beacon_delay = timestamp - priv->last_beacon_timestamp;
-						int beacons = beacon_delay / (beacon_interval * 1000);
-						if (beacons > 1)
-							priv->wstats.miss.beacon += beacons - 1;
-					}
-					priv->last_beacon_timestamp = timestamp;
-					handle_beacon_probe(priv, capability, channel);
-				}
-			}
-
-			if (priv->station_state == STATION_STATE_SCANNING)
-				store_bss_info(priv, header, capability,
-					       beacon_interval, channel, rssi,
-					       ssid_length,
-					       &beacon->rates_el_id,
-					       subtype == IEEE80211_STYPE_BEACON);
-		}
-		break;
-
-	case IEEE80211_STYPE_AUTH:
-
-		if (priv->station_state == STATION_STATE_AUTHENTICATING)
-			authenticate(priv, frame_len);
-
-		break;
-
-	case IEEE80211_STYPE_ASSOC_RESP:
-	case IEEE80211_STYPE_REASSOC_RESP:
-
-		if (priv->station_state == STATION_STATE_ASSOCIATING ||
-		    priv->station_state == STATION_STATE_REASSOCIATING)
-			associate(priv, frame_len, subtype);
-
-		break;
-
-	case IEEE80211_STYPE_DISASSOC:
-		if (priv->station_is_associated &&
-		    priv->operating_mode == IW_MODE_INFRA &&
-		    is_frame_from_current_bss(priv, header)) {
-			priv->station_was_associated = 0;
-			priv->station_is_associated = 0;
-
-			atmel_enter_state(priv, STATION_STATE_JOINNING);
-			join(priv, BSS_TYPE_INFRASTRUCTURE);
-		}
-
-		break;
-
-	case IEEE80211_STYPE_DEAUTH:
-		if (priv->operating_mode == IW_MODE_INFRA &&
-		    is_frame_from_current_bss(priv, header)) {
-			priv->station_was_associated = 0;
-
-			atmel_enter_state(priv, STATION_STATE_JOINNING);
-			join(priv, BSS_TYPE_INFRASTRUCTURE);
-		}
-
-		break;
-	}
-}
-
-/* run when timer expires */
-static void atmel_management_timer(struct timer_list *t)
-{
-	struct atmel_private *priv = from_timer(priv, t, management_timer);
-	unsigned long flags;
-
-	/* Check if the card has been yanked. */
-	if (priv->card && priv->present_callback &&
-		!(*priv->present_callback)(priv->card))
-		return;
-
-	spin_lock_irqsave(&priv->irqlock, flags);
-
-	switch (priv->station_state) {
-
-	case STATION_STATE_AUTHENTICATING:
-		if (priv->AuthenticationRequestRetryCnt >= MAX_AUTHENTICATION_RETRIES) {
-			atmel_enter_state(priv, STATION_STATE_MGMT_ERROR);
-			priv->station_is_associated = 0;
-			priv->AuthenticationRequestRetryCnt = 0;
-			restart_search(priv);
-		} else {
-			int auth = WLAN_AUTH_OPEN;
-			priv->AuthenticationRequestRetryCnt++;
-			priv->CurrentAuthentTransactionSeqNum = 0x0001;
-			mod_timer(&priv->management_timer, jiffies + MGMT_JIFFIES);
-			if (priv->wep_is_on && priv->exclude_unencrypted)
-				auth = WLAN_AUTH_SHARED_KEY;
-			send_authentication_request(priv, auth, NULL, 0);
-	  }
-	  break;
-
-	case STATION_STATE_ASSOCIATING:
-		if (priv->AssociationRequestRetryCnt == MAX_ASSOCIATION_RETRIES) {
-			atmel_enter_state(priv, STATION_STATE_MGMT_ERROR);
-			priv->station_is_associated = 0;
-			priv->AssociationRequestRetryCnt = 0;
-			restart_search(priv);
-		} else {
-			priv->AssociationRequestRetryCnt++;
-			mod_timer(&priv->management_timer, jiffies + MGMT_JIFFIES);
-			send_association_request(priv, 0);
-		}
-	  break;
-
-	case STATION_STATE_REASSOCIATING:
-		if (priv->ReAssociationRequestRetryCnt == MAX_ASSOCIATION_RETRIES) {
-			atmel_enter_state(priv, STATION_STATE_MGMT_ERROR);
-			priv->station_is_associated = 0;
-			priv->ReAssociationRequestRetryCnt = 0;
-			restart_search(priv);
-		} else {
-			priv->ReAssociationRequestRetryCnt++;
-			mod_timer(&priv->management_timer, jiffies + MGMT_JIFFIES);
-			send_association_request(priv, 1);
-		}
-		break;
-
-	default:
-		break;
-	}
-
-	spin_unlock_irqrestore(&priv->irqlock, flags);
-}
-
-static void atmel_command_irq(struct atmel_private *priv)
-{
-	u8 status = atmel_rmem8(priv, atmel_co(priv, CMD_BLOCK_STATUS_OFFSET));
-	u8 command = atmel_rmem8(priv, atmel_co(priv, CMD_BLOCK_COMMAND_OFFSET));
-	int fast_scan;
-	union iwreq_data wrqu;
-
-	if (status == CMD_STATUS_IDLE ||
-	    status == CMD_STATUS_IN_PROGRESS)
-		return;
-
-	switch (command) {
-	case CMD_Start:
-		if (status == CMD_STATUS_COMPLETE) {
-			priv->station_was_associated = priv->station_is_associated;
-			atmel_get_mib(priv, Mac_Mgmt_Mib_Type, MAC_MGMT_MIB_CUR_BSSID_POS,
-				      (u8 *)priv->CurrentBSSID, 6);
-			atmel_enter_state(priv, STATION_STATE_READY);
-		}
-		break;
-
-	case CMD_Scan:
-		fast_scan = priv->fast_scan;
-		priv->fast_scan = 0;
-
-		if (status != CMD_STATUS_COMPLETE) {
-			atmel_scan(priv, 1);
-		} else {
-			int bss_index = retrieve_bss(priv);
-			int notify_scan_complete = 1;
-			if (bss_index != -1) {
-				atmel_join_bss(priv, bss_index);
-			} else if (priv->operating_mode == IW_MODE_ADHOC &&
-				   priv->SSID_size != 0) {
-				start(priv, BSS_TYPE_AD_HOC);
-			} else {
-				priv->fast_scan = !fast_scan;
-				atmel_scan(priv, 1);
-				notify_scan_complete = 0;
-			}
-			priv->site_survey_state = SITE_SURVEY_COMPLETED;
-			if (notify_scan_complete) {
-				wrqu.data.length = 0;
-				wrqu.data.flags = 0;
-				wireless_send_event(priv->dev, SIOCGIWSCAN, &wrqu, NULL);
-			}
-		}
-		break;
-
-	case CMD_SiteSurvey:
-		priv->fast_scan = 0;
-
-		if (status != CMD_STATUS_COMPLETE)
-			return;
-
-		priv->site_survey_state = SITE_SURVEY_COMPLETED;
-		if (priv->station_is_associated) {
-			atmel_enter_state(priv, STATION_STATE_READY);
-			wrqu.data.length = 0;
-			wrqu.data.flags = 0;
-			wireless_send_event(priv->dev, SIOCGIWSCAN, &wrqu, NULL);
-		} else {
-			atmel_scan(priv, 1);
-		}
-		break;
-
-	case CMD_Join:
-		if (status == CMD_STATUS_COMPLETE) {
-			if (priv->operating_mode == IW_MODE_ADHOC) {
-				priv->station_was_associated = priv->station_is_associated;
-				atmel_enter_state(priv, STATION_STATE_READY);
-			} else {
-				int auth = WLAN_AUTH_OPEN;
-				priv->AuthenticationRequestRetryCnt = 0;
-				atmel_enter_state(priv, STATION_STATE_AUTHENTICATING);
-
-				mod_timer(&priv->management_timer, jiffies + MGMT_JIFFIES);
-				priv->CurrentAuthentTransactionSeqNum = 0x0001;
-				if (priv->wep_is_on && priv->exclude_unencrypted)
-					auth = WLAN_AUTH_SHARED_KEY;
-				send_authentication_request(priv, auth, NULL, 0);
-			}
-			return;
-		}
-
-		atmel_scan(priv, 1);
-	}
-}
-
-static int atmel_wakeup_firmware(struct atmel_private *priv)
-{
-	struct host_info_struct *iface = &priv->host_info;
-	u16 mr1, mr3;
-	int i;
-
-	if (priv->card_type == CARD_TYPE_SPI_FLASH)
-		atmel_set_gcr(priv->dev, GCR_REMAP);
-
-	/* wake up on-board processor */
-	atmel_clear_gcr(priv->dev, 0x0040);
-	atmel_write16(priv->dev, BSR, BSS_SRAM);
-
-	if (priv->card_type == CARD_TYPE_SPI_FLASH)
-		mdelay(100);
-
-	/* and wait for it */
-	for (i = LOOP_RETRY_LIMIT; i; i--) {
-		mr1 = atmel_read16(priv->dev, MR1);
-		mr3 = atmel_read16(priv->dev, MR3);
-
-		if (mr3 & MAC_BOOT_COMPLETE)
-			break;
-		if (mr1 & MAC_BOOT_COMPLETE &&
-		    priv->bus_type == BUS_TYPE_PCCARD)
-			break;
-	}
-
-	if (i == 0) {
-		printk(KERN_ALERT "%s: MAC failed to boot.\n", priv->dev->name);
-		return -EIO;
-	}
-
-	if ((priv->host_info_base = atmel_read16(priv->dev, MR2)) == 0xffff) {
-		printk(KERN_ALERT "%s: card missing.\n", priv->dev->name);
-		return -ENODEV;
-	}
-
-	/* now check for completion of MAC initialization through
-	   the FunCtrl field of the IFACE, poll MR1 to detect completion of
-	   MAC initialization, check completion status, set interrupt mask,
-	   enables interrupts and calls Tx and Rx initialization functions */
-
-	atmel_wmem8(priv, atmel_hi(priv, IFACE_FUNC_CTRL_OFFSET), FUNC_CTRL_INIT_COMPLETE);
-
-	for (i = LOOP_RETRY_LIMIT; i; i--) {
-		mr1 = atmel_read16(priv->dev, MR1);
-		mr3 = atmel_read16(priv->dev, MR3);
-
-		if (mr3 & MAC_INIT_COMPLETE)
-			break;
-		if (mr1 & MAC_INIT_COMPLETE &&
-		    priv->bus_type == BUS_TYPE_PCCARD)
-			break;
-	}
-
-	if (i == 0) {
-		printk(KERN_ALERT "%s: MAC failed to initialise.\n",
-				priv->dev->name);
-		return -EIO;
-	}
-
-	/* Check for MAC_INIT_OK only on the register that the MAC_INIT_OK was set */
-	if ((mr3 & MAC_INIT_COMPLETE) &&
-	    !(atmel_read16(priv->dev, MR3) & MAC_INIT_OK)) {
-		printk(KERN_ALERT "%s: MAC failed MR3 self-test.\n", priv->dev->name);
-		return -EIO;
-	}
-	if ((mr1 & MAC_INIT_COMPLETE) &&
-	    !(atmel_read16(priv->dev, MR1) & MAC_INIT_OK)) {
-		printk(KERN_ALERT "%s: MAC failed MR1 self-test.\n", priv->dev->name);
-		return -EIO;
-	}
-
-	atmel_copy_to_host(priv->dev, (unsigned char *)iface,
-			   priv->host_info_base, sizeof(*iface));
-
-	iface->tx_buff_pos = le16_to_cpu(iface->tx_buff_pos);
-	iface->tx_buff_size = le16_to_cpu(iface->tx_buff_size);
-	iface->tx_desc_pos = le16_to_cpu(iface->tx_desc_pos);
-	iface->tx_desc_count = le16_to_cpu(iface->tx_desc_count);
-	iface->rx_buff_pos = le16_to_cpu(iface->rx_buff_pos);
-	iface->rx_buff_size = le16_to_cpu(iface->rx_buff_size);
-	iface->rx_desc_pos = le16_to_cpu(iface->rx_desc_pos);
-	iface->rx_desc_count = le16_to_cpu(iface->rx_desc_count);
-	iface->build_version = le16_to_cpu(iface->build_version);
-	iface->command_pos = le16_to_cpu(iface->command_pos);
-	iface->major_version = le16_to_cpu(iface->major_version);
-	iface->minor_version = le16_to_cpu(iface->minor_version);
-	iface->func_ctrl = le16_to_cpu(iface->func_ctrl);
-	iface->mac_status = le16_to_cpu(iface->mac_status);
-
-	return 0;
-}
-
-/* determine type of memory and MAC address */
-static int probe_atmel_card(struct net_device *dev)
-{
-	int rc = 0;
-	struct atmel_private *priv = netdev_priv(dev);
-	u8 addr[ETH_ALEN] = {};
-
-	/* reset pccard */
-	if (priv->bus_type == BUS_TYPE_PCCARD)
-		atmel_write16(dev, GCR, 0x0060);
-
-	atmel_write16(dev, GCR, 0x0040);
-	msleep(500);
-
-	if (atmel_read16(dev, MR2) == 0) {
-		/* No stored firmware so load a small stub which just
-		   tells us the MAC address */
-		int i;
-		priv->card_type = CARD_TYPE_EEPROM;
-		atmel_write16(dev, BSR, BSS_IRAM);
-		atmel_copy_to_card(dev, 0, mac_reader, sizeof(mac_reader));
-		atmel_set_gcr(dev, GCR_REMAP);
-		atmel_clear_gcr(priv->dev, 0x0040);
-		atmel_write16(dev, BSR, BSS_SRAM);
-		for (i = LOOP_RETRY_LIMIT; i; i--)
-			if (atmel_read16(dev, MR3) & MAC_BOOT_COMPLETE)
-				break;
-		if (i == 0) {
-			printk(KERN_ALERT "%s: MAC failed to boot MAC address reader.\n", dev->name);
-		} else {
-
-			atmel_copy_to_host(dev, addr, atmel_read16(dev, MR2), 6);
-			eth_hw_addr_set(dev, addr);
-			/* got address, now squash it again until the network
-			   interface is opened */
-			if (priv->bus_type == BUS_TYPE_PCCARD)
-				atmel_write16(dev, GCR, 0x0060);
-			atmel_write16(dev, GCR, 0x0040);
-			rc = 1;
-		}
-	} else if (atmel_read16(dev, MR4) == 0) {
-		/* Mac address easy in this case. */
-		priv->card_type = CARD_TYPE_PARALLEL_FLASH;
-		atmel_write16(dev,  BSR, 1);
-		atmel_copy_to_host(dev, addr, 0xc000, 6);
-		eth_hw_addr_set(dev, addr);
-		atmel_write16(dev,  BSR, 0x200);
-		rc = 1;
-	} else {
-		/* Standard firmware in flash, boot it up and ask
-		   for the Mac Address */
-		priv->card_type = CARD_TYPE_SPI_FLASH;
-		if (atmel_wakeup_firmware(priv) == 0) {
-			atmel_get_mib(priv, Mac_Address_Mib_Type, 0, addr, 6);
-			eth_hw_addr_set(dev, addr);
-
-			/* got address, now squash it again until the network
-			   interface is opened */
-			if (priv->bus_type == BUS_TYPE_PCCARD)
-				atmel_write16(dev, GCR, 0x0060);
-			atmel_write16(dev, GCR, 0x0040);
-			rc = 1;
-		}
-	}
-
-	if (rc) {
-		if (dev->dev_addr[0] == 0xFF) {
-			static const u8 default_mac[] = {
-				0x00, 0x04, 0x25, 0x00, 0x00, 0x00
-			};
-			printk(KERN_ALERT "%s: *** Invalid MAC address. UPGRADE Firmware ****\n", dev->name);
-			eth_hw_addr_set(dev, default_mac);
-		}
-	}
-
-	return rc;
-}
-
-/* Move the encyption information on the MIB structure.
-   This routine is for the pre-WPA firmware: later firmware has
-   a different format MIB and a different routine. */
-static void build_wep_mib(struct atmel_private *priv)
-{
-	struct { /* NB this is matched to the hardware, don't change. */
-		u8 wep_is_on;
-		u8 default_key; /* 0..3 */
-		u8 reserved;
-		u8 exclude_unencrypted;
-
-		u32 WEPICV_error_count;
-		u32 WEP_excluded_count;
-
-		u8 wep_keys[MAX_ENCRYPTION_KEYS][13];
-		u8 encryption_level; /* 0, 1, 2 */
-		u8 reserved2[3];
-	} mib;
-	int i;
-
-	mib.wep_is_on = priv->wep_is_on;
-	if (priv->wep_is_on) {
-		if (priv->wep_key_len[priv->default_key] > 5)
-			mib.encryption_level = 2;
-		else
-			mib.encryption_level = 1;
-	} else {
-		mib.encryption_level = 0;
-	}
-
-	mib.default_key = priv->default_key;
-	mib.exclude_unencrypted = priv->exclude_unencrypted;
-
-	for (i = 0; i < MAX_ENCRYPTION_KEYS; i++)
-		memcpy(mib.wep_keys[i], priv->wep_keys[i], 13);
-
-	atmel_set_mib(priv, Mac_Wep_Mib_Type, 0, (u8 *)&mib, sizeof(mib));
-}
-
-static void build_wpa_mib(struct atmel_private *priv)
-{
-	/* This is for the later (WPA enabled) firmware. */
-
-	struct { /* NB this is matched to the hardware, don't change. */
-		u8 cipher_default_key_value[MAX_ENCRYPTION_KEYS][MAX_ENCRYPTION_KEY_SIZE];
-		u8 receiver_address[ETH_ALEN];
-		u8 wep_is_on;
-		u8 default_key; /* 0..3 */
-		u8 group_key;
-		u8 exclude_unencrypted;
-		u8 encryption_type;
-		u8 reserved;
-
-		u32 WEPICV_error_count;
-		u32 WEP_excluded_count;
-
-		u8 key_RSC[4][8];
-	} mib;
-
-	int i;
-
-	mib.wep_is_on = priv->wep_is_on;
-	mib.exclude_unencrypted = priv->exclude_unencrypted;
-	memcpy(mib.receiver_address, priv->CurrentBSSID, ETH_ALEN);
-
-	/* zero all the keys before adding in valid ones. */
-	memset(mib.cipher_default_key_value, 0, sizeof(mib.cipher_default_key_value));
-
-	if (priv->wep_is_on) {
-		/* There's a comment in the Atmel code to the effect that this
-		   is only valid when still using WEP, it may need to be set to
-		   something to use WPA */
-		memset(mib.key_RSC, 0, sizeof(mib.key_RSC));
-
-		mib.default_key = mib.group_key = 255;
-		for (i = 0; i < MAX_ENCRYPTION_KEYS; i++) {
-			if (priv->wep_key_len[i] > 0) {
-				memcpy(mib.cipher_default_key_value[i], priv->wep_keys[i], MAX_ENCRYPTION_KEY_SIZE);
-				if (i == priv->default_key) {
-					mib.default_key = i;
-					mib.cipher_default_key_value[i][MAX_ENCRYPTION_KEY_SIZE-1] = 7;
-					mib.cipher_default_key_value[i][MAX_ENCRYPTION_KEY_SIZE-2] = priv->pairwise_cipher_suite;
-				} else {
-					mib.group_key = i;
-					priv->group_cipher_suite = priv->pairwise_cipher_suite;
-					mib.cipher_default_key_value[i][MAX_ENCRYPTION_KEY_SIZE-1] = 1;
-					mib.cipher_default_key_value[i][MAX_ENCRYPTION_KEY_SIZE-2] = priv->group_cipher_suite;
-				}
-			}
-		}
-		if (mib.default_key == 255)
-			mib.default_key = mib.group_key != 255 ? mib.group_key : 0;
-		if (mib.group_key == 255)
-			mib.group_key = mib.default_key;
-
-	}
-
-	atmel_set_mib(priv, Mac_Wep_Mib_Type, 0, (u8 *)&mib, sizeof(mib));
-}
-
-static int reset_atmel_card(struct net_device *dev)
-{
-	/* do everything necessary to wake up the hardware, including
-	   waiting for the lightning strike and throwing the knife switch....
-
-	   set all the Mib values which matter in the card to match
-	   their settings in the atmel_private structure. Some of these
-	   can be altered on the fly, but many (WEP, infrastructure or ad-hoc)
-	   can only be changed by tearing down the world and coming back through
-	   here.
-
-	   This routine is also responsible for initialising some
-	   hardware-specific fields in the atmel_private structure,
-	   including a copy of the firmware's hostinfo structure
-	   which is the route into the rest of the firmware datastructures. */
-
-	struct atmel_private *priv = netdev_priv(dev);
-	u8 configuration;
-	int old_state = priv->station_state;
-	int err = 0;
-
-	/* data to add to the firmware names, in priority order
-	   this implemenents firmware versioning */
-
-	static char *firmware_modifier[] = {
-		"-wpa",
-		"",
-		NULL
-	};
-
-	/* reset pccard */
-	if (priv->bus_type == BUS_TYPE_PCCARD)
-		atmel_write16(priv->dev, GCR, 0x0060);
-
-	/* stop card , disable interrupts */
-	atmel_write16(priv->dev, GCR, 0x0040);
-
-	if (priv->card_type == CARD_TYPE_EEPROM) {
-		/* copy in firmware if needed */
-		const struct firmware *fw_entry = NULL;
-		const unsigned char *fw;
-		int len = priv->firmware_length;
-		if (!(fw = priv->firmware)) {
-			if (priv->firmware_type == ATMEL_FW_TYPE_NONE) {
-				if (strlen(priv->firmware_id) == 0) {
-					printk(KERN_INFO
-					       "%s: card type is unknown: assuming at76c502 firmware is OK.\n",
-					       dev->name);
-					printk(KERN_INFO
-					       "%s: if not, use the firmware= module parameter.\n",
-					       dev->name);
-					strcpy(priv->firmware_id, "atmel_at76c502.bin");
-				}
-				err = request_firmware(&fw_entry, priv->firmware_id, priv->sys_dev);
-				if (err != 0) {
-					printk(KERN_ALERT
-					       "%s: firmware %s is missing, cannot continue.\n",
-					       dev->name, priv->firmware_id);
-					return err;
-				}
-			} else {
-				int fw_index = 0;
-				int success = 0;
-
-				/* get firmware filename entry based on firmware type ID */
-				while (fw_table[fw_index].fw_type != priv->firmware_type
-						&& fw_table[fw_index].fw_type != ATMEL_FW_TYPE_NONE)
-					fw_index++;
-
-				/* construct the actual firmware file name */
-				if (fw_table[fw_index].fw_type != ATMEL_FW_TYPE_NONE) {
-					int i;
-					for (i = 0; firmware_modifier[i]; i++) {
-						snprintf(priv->firmware_id, 32, "%s%s.%s", fw_table[fw_index].fw_file,
-							firmware_modifier[i], fw_table[fw_index].fw_file_ext);
-						priv->firmware_id[31] = '\0';
-						if (request_firmware(&fw_entry, priv->firmware_id, priv->sys_dev) == 0) {
-							success = 1;
-							break;
-						}
-					}
-				}
-				if (!success) {
-					printk(KERN_ALERT
-					       "%s: firmware %s is missing, cannot start.\n",
-					       dev->name, priv->firmware_id);
-					priv->firmware_id[0] = '\0';
-					return -ENOENT;
-				}
-			}
-
-			fw = fw_entry->data;
-			len = fw_entry->size;
-		}
-
-		if (len <= 0x6000) {
-			atmel_write16(priv->dev, BSR, BSS_IRAM);
-			atmel_copy_to_card(priv->dev, 0, fw, len);
-			atmel_set_gcr(priv->dev, GCR_REMAP);
-		} else {
-			/* Remap */
-			atmel_set_gcr(priv->dev, GCR_REMAP);
-			atmel_write16(priv->dev, BSR, BSS_IRAM);
-			atmel_copy_to_card(priv->dev, 0, fw, 0x6000);
-			atmel_write16(priv->dev, BSR, 0x2ff);
-			atmel_copy_to_card(priv->dev, 0x8000, &fw[0x6000], len - 0x6000);
-		}
-
-		release_firmware(fw_entry);
-	}
-
-	err = atmel_wakeup_firmware(priv);
-	if (err != 0)
-		return err;
-
-	/* Check the version and set the correct flag for wpa stuff,
-	   old and new firmware is incompatible.
-	   The pre-wpa 3com firmware reports major version 5,
-	   the wpa 3com firmware is major version 4 and doesn't need
-	   the 3com broken-ness filter. */
-	priv->use_wpa = (priv->host_info.major_version == 4);
-	priv->radio_on_broken = (priv->host_info.major_version == 5);
-
-	/* unmask all irq sources */
-	atmel_wmem8(priv, atmel_hi(priv, IFACE_INT_MASK_OFFSET), 0xff);
-
-	/* int Tx system and enable Tx */
-	atmel_wmem8(priv, atmel_tx(priv, TX_DESC_FLAGS_OFFSET, 0), 0);
-	atmel_wmem32(priv, atmel_tx(priv, TX_DESC_NEXT_OFFSET, 0), 0x80000000L);
-	atmel_wmem16(priv, atmel_tx(priv, TX_DESC_POS_OFFSET, 0), 0);
-	atmel_wmem16(priv, atmel_tx(priv, TX_DESC_SIZE_OFFSET, 0), 0);
-
-	priv->tx_desc_free = priv->host_info.tx_desc_count;
-	priv->tx_desc_head = 0;
-	priv->tx_desc_tail = 0;
-	priv->tx_desc_previous = 0;
-	priv->tx_free_mem = priv->host_info.tx_buff_size;
-	priv->tx_buff_head = 0;
-	priv->tx_buff_tail = 0;
-
-	configuration = atmel_rmem8(priv, atmel_hi(priv, IFACE_FUNC_CTRL_OFFSET));
-	atmel_wmem8(priv, atmel_hi(priv, IFACE_FUNC_CTRL_OFFSET),
-				   configuration | FUNC_CTRL_TxENABLE);
-
-	/* init Rx system and enable */
-	priv->rx_desc_head = 0;
-
-	configuration = atmel_rmem8(priv, atmel_hi(priv, IFACE_FUNC_CTRL_OFFSET));
-	atmel_wmem8(priv, atmel_hi(priv, IFACE_FUNC_CTRL_OFFSET),
-				   configuration | FUNC_CTRL_RxENABLE);
-
-	if (!priv->radio_on_broken) {
-		if (atmel_send_command_wait(priv, CMD_EnableRadio, NULL, 0) ==
-		    CMD_STATUS_REJECTED_RADIO_OFF) {
-			printk(KERN_INFO "%s: cannot turn the radio on.\n",
-			       dev->name);
-			return -EIO;
-		}
-	}
-
-	/* set up enough MIB values to run. */
-	atmel_set_mib8(priv, Local_Mib_Type, LOCAL_MIB_AUTO_TX_RATE_POS, priv->auto_tx_rate);
-	atmel_set_mib8(priv, Local_Mib_Type,  LOCAL_MIB_TX_PROMISCUOUS_POS,  PROM_MODE_OFF);
-	atmel_set_mib16(priv, Mac_Mib_Type, MAC_MIB_RTS_THRESHOLD_POS, priv->rts_threshold);
-	atmel_set_mib16(priv, Mac_Mib_Type, MAC_MIB_FRAG_THRESHOLD_POS, priv->frag_threshold);
-	atmel_set_mib8(priv, Mac_Mib_Type, MAC_MIB_SHORT_RETRY_POS, priv->short_retry);
-	atmel_set_mib8(priv, Mac_Mib_Type, MAC_MIB_LONG_RETRY_POS, priv->long_retry);
-	atmel_set_mib8(priv, Local_Mib_Type, LOCAL_MIB_PREAMBLE_TYPE, priv->preamble);
-	atmel_set_mib(priv, Mac_Address_Mib_Type, MAC_ADDR_MIB_MAC_ADDR_POS,
-		      priv->dev->dev_addr, 6);
-	atmel_set_mib8(priv, Mac_Mgmt_Mib_Type, MAC_MGMT_MIB_PS_MODE_POS, ACTIVE_MODE);
-	atmel_set_mib16(priv, Mac_Mgmt_Mib_Type, MAC_MGMT_MIB_LISTEN_INTERVAL_POS, 1);
-	atmel_set_mib16(priv, Mac_Mgmt_Mib_Type, MAC_MGMT_MIB_BEACON_PER_POS, priv->default_beacon_period);
-	atmel_set_mib(priv, Phy_Mib_Type, PHY_MIB_RATE_SET_POS, atmel_basic_rates, 4);
-	atmel_set_mib8(priv, Mac_Mgmt_Mib_Type, MAC_MGMT_MIB_CUR_PRIVACY_POS, priv->wep_is_on);
-	if (priv->use_wpa)
-		build_wpa_mib(priv);
-	else
-		build_wep_mib(priv);
-
-	if (old_state == STATION_STATE_READY) {
-		union iwreq_data wrqu;
-
-		wrqu.data.length = 0;
-		wrqu.data.flags = 0;
-		wrqu.ap_addr.sa_family = ARPHRD_ETHER;
-		eth_zero_addr(wrqu.ap_addr.sa_data);
-		wireless_send_event(priv->dev, SIOCGIWAP, &wrqu, NULL);
-	}
-
-	return 0;
-}
-
-static void atmel_send_command(struct atmel_private *priv, int command,
-			       void *cmd, int cmd_size)
-{
-	if (cmd)
-		atmel_copy_to_card(priv->dev, atmel_co(priv, CMD_BLOCK_PARAMETERS_OFFSET),
-				   cmd, cmd_size);
-
-	atmel_wmem8(priv, atmel_co(priv, CMD_BLOCK_COMMAND_OFFSET), command);
-	atmel_wmem8(priv, atmel_co(priv, CMD_BLOCK_STATUS_OFFSET), 0);
-}
-
-static int atmel_send_command_wait(struct atmel_private *priv, int command,
-				   void *cmd, int cmd_size)
-{
-	int i, status;
-
-	atmel_send_command(priv, command, cmd, cmd_size);
-
-	for (i = 5000; i; i--) {
-		status = atmel_rmem8(priv, atmel_co(priv, CMD_BLOCK_STATUS_OFFSET));
-		if (status != CMD_STATUS_IDLE &&
-		    status != CMD_STATUS_IN_PROGRESS)
-			break;
-		udelay(20);
-	}
-
-	if (i == 0) {
-		printk(KERN_ALERT "%s: failed to contact MAC.\n", priv->dev->name);
-		status =  CMD_STATUS_HOST_ERROR;
-	} else {
-		if (command != CMD_EnableRadio)
-			status = CMD_STATUS_COMPLETE;
-	}
-
-	return status;
-}
-
-static u8 atmel_get_mib8(struct atmel_private *priv, u8 type, u8 index)
-{
-	struct get_set_mib m;
-	m.type = type;
-	m.size = 1;
-	m.index = index;
-
-	atmel_send_command_wait(priv, CMD_Get_MIB_Vars, &m, MIB_HEADER_SIZE + 1);
-	return atmel_rmem8(priv, atmel_co(priv, CMD_BLOCK_PARAMETERS_OFFSET + MIB_HEADER_SIZE));
-}
-
-static void atmel_set_mib8(struct atmel_private *priv, u8 type, u8 index, u8 data)
-{
-	struct get_set_mib m;
-	m.type = type;
-	m.size = 1;
-	m.index = index;
-	m.data[0] = data;
-
-	atmel_send_command_wait(priv, CMD_Set_MIB_Vars, &m, MIB_HEADER_SIZE + 1);
-}
-
-static void atmel_set_mib16(struct atmel_private *priv, u8 type, u8 index,
-			    u16 data)
-{
-	struct get_set_mib m;
-	m.type = type;
-	m.size = 2;
-	m.index = index;
-	m.data[0] = data;
-	m.data[1] = data >> 8;
-
-	atmel_send_command_wait(priv, CMD_Set_MIB_Vars, &m, MIB_HEADER_SIZE + 2);
-}
-
-static void atmel_set_mib(struct atmel_private *priv, u8 type, u8 index,
-			  const u8 *data, int data_len)
-{
-	struct get_set_mib m;
-	m.type = type;
-	m.size = data_len;
-	m.index = index;
-
-	if (data_len > MIB_MAX_DATA_BYTES)
-		printk(KERN_ALERT "%s: MIB buffer too small.\n", priv->dev->name);
-
-	memcpy(m.data, data, data_len);
-	atmel_send_command_wait(priv, CMD_Set_MIB_Vars, &m, MIB_HEADER_SIZE + data_len);
-}
-
-static void atmel_get_mib(struct atmel_private *priv, u8 type, u8 index,
-			  u8 *data, int data_len)
-{
-	struct get_set_mib m;
-	m.type = type;
-	m.size = data_len;
-	m.index = index;
-
-	if (data_len > MIB_MAX_DATA_BYTES)
-		printk(KERN_ALERT "%s: MIB buffer too small.\n", priv->dev->name);
-
-	atmel_send_command_wait(priv, CMD_Get_MIB_Vars, &m, MIB_HEADER_SIZE + data_len);
-	atmel_copy_to_host(priv->dev, data,
-			   atmel_co(priv, CMD_BLOCK_PARAMETERS_OFFSET + MIB_HEADER_SIZE), data_len);
-}
-
-static void atmel_writeAR(struct net_device *dev, u16 data)
-{
-	int i;
-	outw(data, dev->base_addr + AR);
-	/* Address register appears to need some convincing..... */
-	for (i = 0; data != inw(dev->base_addr + AR) && i < 10; i++)
-		outw(data, dev->base_addr + AR);
-}
-
-static void atmel_copy_to_card(struct net_device *dev, u16 dest,
-			       const unsigned char *src, u16 len)
-{
-	int i;
-	atmel_writeAR(dev, dest);
-	if (dest % 2) {
-		atmel_write8(dev, DR, *src);
-		src++; len--;
-	}
-	for (i = len; i > 1 ; i -= 2) {
-		u8 lb = *src++;
-		u8 hb = *src++;
-		atmel_write16(dev, DR, lb | (hb << 8));
-	}
-	if (i)
-		atmel_write8(dev, DR, *src);
-}
-
-static void atmel_copy_to_host(struct net_device *dev, unsigned char *dest,
-			       u16 src, u16 len)
-{
-	int i;
-	atmel_writeAR(dev, src);
-	if (src % 2) {
-		*dest = atmel_read8(dev, DR);
-		dest++; len--;
-	}
-	for (i = len; i > 1 ; i -= 2) {
-		u16 hw = atmel_read16(dev, DR);
-		*dest++ = hw;
-		*dest++ = hw >> 8;
-	}
-	if (i)
-		*dest = atmel_read8(dev, DR);
-}
-
-static void atmel_set_gcr(struct net_device *dev, u16 mask)
-{
-	outw(inw(dev->base_addr + GCR) | mask, dev->base_addr + GCR);
-}
-
-static void atmel_clear_gcr(struct net_device *dev, u16 mask)
-{
-	outw(inw(dev->base_addr + GCR) & ~mask, dev->base_addr + GCR);
-}
-
-static int atmel_lock_mac(struct atmel_private *priv)
-{
-	int i, j = 20;
- retry:
-	for (i = 5000; i; i--) {
-		if (!atmel_rmem8(priv, atmel_hi(priv, IFACE_LOCKOUT_HOST_OFFSET)))
-			break;
-		udelay(20);
-	}
-
-	if (!i)
-		return 0; /* timed out */
-
-	atmel_wmem8(priv, atmel_hi(priv, IFACE_LOCKOUT_MAC_OFFSET), 1);
-	if (atmel_rmem8(priv, atmel_hi(priv, IFACE_LOCKOUT_HOST_OFFSET))) {
-		atmel_wmem8(priv, atmel_hi(priv, IFACE_LOCKOUT_MAC_OFFSET), 0);
-		if (!j--)
-			return 0; /* timed out */
-		goto retry;
-	}
-
-	return 1;
-}
-
-static void atmel_wmem32(struct atmel_private *priv, u16 pos, u32 data)
-{
-	atmel_writeAR(priv->dev, pos);
-	atmel_write16(priv->dev, DR, data); /* card is little-endian */
-	atmel_write16(priv->dev, DR, data >> 16);
-}
-
-/***************************************************************************/
-/* There follows the source form of the MAC address reading firmware       */
-/***************************************************************************/
-#if 0
-
-/* Copyright 2003 Matthew T. Russotto                                      */
-/* But derived from the Atmel 76C502 firmware written by Atmel and         */
-/* included in "atmel wireless lan drivers" package                        */
-/*
-    This file is part of net.russotto.AtmelMACFW, hereto referred to
-    as AtmelMACFW
-
-    AtmelMACFW is free software; you can redistribute it and/or modify
-    it under the terms of the GNU General Public License version 2
-    as published by the Free Software Foundation.
-
-    AtmelMACFW is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
-
-    You should have received a copy of the GNU General Public License
-    along with AtmelMACFW; if not, see <http://www.gnu.org/licenses/>.
-
-****************************************************************************/
-/* This firmware should work on the 76C502 RFMD, RFMD_D, and RFMD_E        */
-/* It will probably work on the 76C504 and 76C502 RFMD_3COM                */
-/* It only works on SPI EEPROM versions of the card.                       */
-
-/* This firmware initializes the SPI controller and clock, reads the MAC   */
-/* address from the EEPROM into SRAM, and puts the SRAM offset of the MAC  */
-/* address in MR2, and sets MR3 to 0x10 to indicate it is done             */
-/* It also puts a complete copy of the EEPROM in SRAM with the offset in   */
-/* MR4, for investigational purposes (maybe we can determine chip type     */
-/* from that?)                                                             */
-
-	.org 0
-    .set MRBASE, 0x8000000
-	.set CPSR_INITIAL, 0xD3 /* IRQ/FIQ disabled, ARM mode, Supervisor state */
-	.set CPSR_USER, 0xD1 /* IRQ/FIQ disabled, ARM mode, USER state */
-	.set SRAM_BASE,  0x02000000
-	.set SP_BASE,    0x0F300000
-	.set UNK_BASE,   0x0F000000 /* Some internal device, but which one? */
-	.set SPI_CGEN_BASE,  0x0E000000 /* Some internal device, but which one? */
-	.set UNK3_BASE,  0x02014000 /* Some internal device, but which one? */
-	.set STACK_BASE, 0x5600
-	.set SP_SR, 0x10
-	.set SP_TDRE, 2 /* status register bit -- TDR empty */
-	.set SP_RDRF, 1 /* status register bit -- RDR full */
-	.set SP_SWRST, 0x80
-	.set SP_SPIEN, 0x1
-	.set SP_CR, 0   /* control register */
-	.set SP_MR, 4   /* mode register */
-	.set SP_RDR, 0x08 /* Read Data Register */
-	.set SP_TDR, 0x0C /* Transmit Data Register */
-	.set SP_CSR0, 0x30 /* chip select registers */
-	.set SP_CSR1, 0x34
-	.set SP_CSR2, 0x38
-	.set SP_CSR3, 0x3C
-	.set NVRAM_CMD_RDSR, 5 /* read status register */
-	.set NVRAM_CMD_READ, 3 /* read data */
-	.set NVRAM_SR_RDY, 1 /* RDY bit.  This bit is inverted */
-	.set SPI_8CLOCKS, 0xFF /* Writing this to the TDR doesn't do anything to the
-				  serial output, since SO is normally high.  But it
-				  does cause 8 clock cycles and thus 8 bits to be
-				  clocked in to the chip.  See Atmel's SPI
-				  controller (e.g. AT91M55800) timing and 4K
-				  SPI EEPROM manuals */
-
-	.set NVRAM_SCRATCH, 0x02000100  /* arbitrary area for scratchpad memory */
-	.set NVRAM_IMAGE, 0x02000200
-	.set NVRAM_LENGTH, 0x0200
-	.set MAC_ADDRESS_MIB, SRAM_BASE
-	.set MAC_ADDRESS_LENGTH, 6
-	.set MAC_BOOT_FLAG, 0x10
-	.set MR1, 0
-	.set MR2, 4
-	.set MR3, 8
-	.set MR4, 0xC
-RESET_VECTOR:
-	b RESET_HANDLER
-UNDEF_VECTOR:
-	b HALT1
-SWI_VECTOR:
-	b HALT1
-IABORT_VECTOR:
-	b HALT1
-DABORT_VECTOR:
-RESERVED_VECTOR:
-	b HALT1
-IRQ_VECTOR:
-	b HALT1
-FIQ_VECTOR:
-	b HALT1
-HALT1:	b HALT1
-RESET_HANDLER:
-	mov     r0, #CPSR_INITIAL
-	msr	CPSR_c, r0	/* This is probably unnecessary */
-
-/* I'm guessing this is initializing clock generator electronics for SPI */
-	ldr	r0, =SPI_CGEN_BASE
-	mov	r1, #0
-	mov	r1, r1, lsl #3
-	orr	r1, r1, #0
-	str	r1, [r0]
-	ldr	r1, [r0, #28]
-	bic	r1, r1, #16
-	str	r1, [r0, #28]
-	mov	r1, #1
-	str	r1, [r0, #8]
-
-	ldr	r0, =MRBASE
-	mov	r1, #0
-	strh	r1, [r0, #MR1]
-	strh	r1, [r0, #MR2]
-	strh	r1, [r0, #MR3]
-	strh	r1, [r0, #MR4]
-
-	mov	sp, #STACK_BASE
-	bl	SP_INIT
-	mov	r0, #10
-	bl	DELAY9
-	bl	GET_MAC_ADDR
-	bl	GET_WHOLE_NVRAM
-	ldr	r0, =MRBASE
-	ldr	r1, =MAC_ADDRESS_MIB
-	strh	r1, [r0, #MR2]
-	ldr	r1, =NVRAM_IMAGE
-	strh	r1, [r0, #MR4]
-	mov	r1, #MAC_BOOT_FLAG
-	strh	r1, [r0, #MR3]
-HALT2:	b HALT2
-.func Get_Whole_NVRAM, GET_WHOLE_NVRAM
-GET_WHOLE_NVRAM:
-	stmdb	sp!, {lr}
-	mov	r2, #0 /* 0th bytes of NVRAM */
-	mov	r3, #NVRAM_LENGTH
-	mov	r1, #0		/* not used in routine */
-	ldr	r0, =NVRAM_IMAGE
-	bl	NVRAM_XFER
-	ldmia	sp!, {lr}
-	bx	lr
-.endfunc
-
-.func Get_MAC_Addr, GET_MAC_ADDR
-GET_MAC_ADDR:
-	stmdb	sp!, {lr}
-	mov	r2, #0x120	/* address of MAC Address within NVRAM */
-	mov	r3, #MAC_ADDRESS_LENGTH
-	mov	r1, #0		/* not used in routine */
-	ldr	r0, =MAC_ADDRESS_MIB
-	bl	NVRAM_XFER
-	ldmia	sp!, {lr}
-	bx	lr
-.endfunc
-.ltorg
-.func Delay9, DELAY9
-DELAY9:
-	adds	r0, r0, r0, LSL #3   /* r0 = r0 * 9 */
-DELAYLOOP:
-	beq	DELAY9_done
-	subs	r0, r0, #1
-	b	DELAYLOOP
-DELAY9_done:
-	bx	lr
-.endfunc
-
-.func SP_Init, SP_INIT
-SP_INIT:
-	mov	r1, #SP_SWRST
-	ldr	r0, =SP_BASE
-	str	r1, [r0, #SP_CR] /* reset the SPI */
-	mov	r1, #0
-	str	r1, [r0, #SP_CR] /* release SPI from reset state */
-	mov	r1, #SP_SPIEN
-	str	r1, [r0, #SP_MR] /* set the SPI to MASTER mode*/
-	str	r1, [r0, #SP_CR] /* enable the SPI */
-
-/*  My guess would be this turns on the SPI clock */
-	ldr	r3, =SPI_CGEN_BASE
-	ldr	r1, [r3, #28]
-	orr	r1, r1, #0x2000
-	str	r1, [r3, #28]
-
-	ldr	r1, =0x2000c01
-	str	r1, [r0, #SP_CSR0]
-	ldr	r1, =0x2000201
-	str	r1, [r0, #SP_CSR1]
-	str	r1, [r0, #SP_CSR2]
-	str	r1, [r0, #SP_CSR3]
-	ldr	r1, [r0, #SP_SR]
-	ldr	r0, [r0, #SP_RDR]
-	bx	lr
-.endfunc
-.func NVRAM_Init, NVRAM_INIT
-NVRAM_INIT:
-	ldr	r1, =SP_BASE
-	ldr	r0, [r1, #SP_RDR]
-	mov	r0, #NVRAM_CMD_RDSR
-	str	r0, [r1, #SP_TDR]
-SP_loop1:
-	ldr	r0, [r1, #SP_SR]
-	tst	r0, #SP_TDRE
-	beq	SP_loop1
-
-	mov	r0, #SPI_8CLOCKS
-	str	r0, [r1, #SP_TDR]
-SP_loop2:
-	ldr	r0, [r1, #SP_SR]
-	tst	r0, #SP_TDRE
-	beq	SP_loop2
-
-	ldr	r0, [r1, #SP_RDR]
-SP_loop3:
-	ldr	r0, [r1, #SP_SR]
-	tst	r0, #SP_RDRF
-	beq	SP_loop3
-
-	ldr	r0, [r1, #SP_RDR]
-	and	r0, r0, #255
-	bx	lr
-.endfunc
-
-.func NVRAM_Xfer, NVRAM_XFER
-	/* r0 = dest address */
-	/* r1 = not used */
-	/* r2 = src address within NVRAM */
-	/* r3 = length */
-NVRAM_XFER:
-	stmdb	sp!, {r4, r5, lr}
-	mov	r5, r0		/* save r0 (dest address) */
-	mov	r4, r3		/* save r3 (length) */
-	mov	r0, r2, LSR #5 /*  SPI memories put A8 in the command field */
-	and	r0, r0, #8
-	add	r0, r0, #NVRAM_CMD_READ
-	ldr	r1, =NVRAM_SCRATCH
-	strb	r0, [r1, #0]	/* save command in NVRAM_SCRATCH[0] */
-	strb	r2, [r1, #1]    /* save low byte of source address in NVRAM_SCRATCH[1] */
-_local1:
-	bl	NVRAM_INIT
-	tst	r0, #NVRAM_SR_RDY
-	bne	_local1
-	mov	r0, #20
-	bl	DELAY9
-	mov	r2, r4		/* length */
-	mov	r1, r5		/* dest address */
-	mov	r0, #2		/* bytes to transfer in command */
-	bl	NVRAM_XFER2
-	ldmia	sp!, {r4, r5, lr}
-	bx	lr
-.endfunc
-
-.func NVRAM_Xfer2, NVRAM_XFER2
-NVRAM_XFER2:
-	stmdb	sp!, {r4, r5, r6, lr}
-	ldr	r4, =SP_BASE
-	mov	r3, #0
-	cmp	r0, #0
-	bls	_local2
-	ldr	r5, =NVRAM_SCRATCH
-_local4:
-	ldrb	r6, [r5, r3]
-	str	r6, [r4, #SP_TDR]
-_local3:
-	ldr	r6, [r4, #SP_SR]
-	tst	r6, #SP_TDRE
-	beq	_local3
-	add	r3, r3, #1
-	cmp	r3, r0 /* r0 is # of bytes to send out (command+addr) */
-	blo	_local4
-_local2:
-	mov	r3, #SPI_8CLOCKS
-	str	r3, [r4, #SP_TDR]
-	ldr	r0, [r4, #SP_RDR]
-_local5:
-	ldr	r0, [r4, #SP_SR]
-	tst	r0, #SP_RDRF
-	beq	_local5
-	ldr	r0, [r4, #SP_RDR] /* what's this byte?  It's the byte read while writing the TDR -- nonsense, because the NVRAM doesn't read and write at the same time */
-	mov	r0, #0
-	cmp	r2, #0  /* r2 is # of bytes to copy in */
-	bls	_local6
-_local7:
-	ldr	r5, [r4, #SP_SR]
-	tst	r5, #SP_TDRE
-	beq	_local7
-	str	r3, [r4, #SP_TDR]  /* r3 has SPI_8CLOCKS */
-_local8:
-	ldr	r5, [r4, #SP_SR]
-	tst	r5, #SP_RDRF
-	beq	_local8
-	ldr	r5, [r4, #SP_RDR] /* but didn't we read this byte above? */
-	strb	r5, [r1], #1 /* postindexed */
-	add	r0, r0, #1
-	cmp	r0, r2
-	blo	_local7 /* since we don't send another address, the NVRAM must be capable of sequential reads */
-_local6:
-	mov	r0, #200
-	bl	DELAY9
-	ldmia	sp!, {r4, r5, r6, lr}
-	bx	lr
-#endif
diff --git a/drivers/net/wireless/atmel/atmel.h b/drivers/net/wireless/atmel/atmel.h
deleted file mode 100644
index d2aa52cf6e8b..000000000000
--- a/drivers/net/wireless/atmel/atmel.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*** -*- linux-c -*- **********************************************************
-
-     Driver for Atmel at76c502 at76c504 and at76c506 wireless cards.
-
-         Copyright 2005 Dan Williams and Red Hat, Inc.
-
-
-******************************************************************************/
-
-#ifndef _ATMEL_H
-#define _ATMEL_H
-
-typedef enum {
-	ATMEL_FW_TYPE_NONE = 0,
-	ATMEL_FW_TYPE_502,
-	ATMEL_FW_TYPE_502D,
-	ATMEL_FW_TYPE_502E,
-	ATMEL_FW_TYPE_502_3COM,
-	ATMEL_FW_TYPE_504,
-	ATMEL_FW_TYPE_504_2958,
-	ATMEL_FW_TYPE_504A_2958,
-	ATMEL_FW_TYPE_506
-} AtmelFWType;
-
-struct net_device *init_atmel_card(unsigned short, unsigned long, const AtmelFWType, struct device *, 
-				    int (*present_func)(void *), void * );
-void stop_atmel_card( struct net_device *);
-int atmel_open( struct net_device * );
-
-#endif
diff --git a/drivers/net/wireless/atmel/atmel_cs.c b/drivers/net/wireless/atmel/atmel_cs.c
deleted file mode 100644
index 58bba9875d36..000000000000
--- a/drivers/net/wireless/atmel/atmel_cs.c
+++ /dev/null
@@ -1,292 +0,0 @@
-/*** -*- linux-c -*- **********************************************************
-
-     Driver for Atmel at76c502 at76c504 and at76c506 wireless cards.
-
-        Copyright 2000-2001 ATMEL Corporation.
-        Copyright 2003 Simon Kelley.
-
-    This code was developed from version 2.1.1 of the Atmel drivers,
-    released by Atmel corp. under the GPL in December 2002. It also
-    includes code from the Linux aironet drivers (C) Benjamin Reed,
-    and the Linux PCMCIA package, (C) David Hinds.
-
-    For all queries about this code, please contact the current author,
-    Simon Kelley <simon@thekelleys.org.uk> and not Atmel Corporation.
-
-    This program is free software; you can redistribute it and/or modify
-    it under the terms of the GNU General Public License as published by
-    the Free Software Foundation; either version 2 of the License, or
-    (at your option) any later version.
-
-    This software is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
-
-    You should have received a copy of the GNU General Public License
-    along with Atmel wireless lan drivers; if not, see
-    <http://www.gnu.org/licenses/>.
-
-******************************************************************************/
-
-#ifdef __IN_PCMCIA_PACKAGE__
-#include <pcmcia/k_compat.h>
-#endif
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/ptrace.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/netdevice.h>
-#include <linux/moduleparam.h>
-#include <linux/device.h>
-
-#include <pcmcia/cistpl.h>
-#include <pcmcia/cisreg.h>
-#include <pcmcia/ds.h>
-#include <pcmcia/ciscode.h>
-
-#include <asm/io.h>
-#include <linux/wireless.h>
-
-#include "atmel.h"
-
-
-/*====================================================================*/
-
-MODULE_AUTHOR("Simon Kelley");
-MODULE_DESCRIPTION("Support for Atmel at76c50x 802.11 wireless ethernet cards.");
-MODULE_LICENSE("GPL");
-
-/*====================================================================*/
-
-static int atmel_config(struct pcmcia_device *link);
-static void atmel_release(struct pcmcia_device *link);
-
-static void atmel_detach(struct pcmcia_device *p_dev);
-
-struct local_info {
-	struct net_device *eth_dev;
-};
-
-static int atmel_probe(struct pcmcia_device *p_dev)
-{
-	struct local_info *local;
-	int ret;
-
-	dev_dbg(&p_dev->dev, "atmel_attach()\n");
-
-	/* Allocate space for private device-specific data */
-	local = kzalloc(sizeof(*local), GFP_KERNEL);
-	if (!local)
-		return -ENOMEM;
-
-	p_dev->priv = local;
-
-	ret = atmel_config(p_dev);
-	if (ret)
-		goto err_free_priv;
-
-	return 0;
-
-err_free_priv:
-	kfree(p_dev->priv);
-	return ret;
-}
-
-static void atmel_detach(struct pcmcia_device *link)
-{
-	dev_dbg(&link->dev, "atmel_detach\n");
-
-	atmel_release(link);
-
-	kfree(link->priv);
-}
-
-/* Call-back function to interrogate PCMCIA-specific information
-   about the current existence of the card */
-static int card_present(void *arg)
-{
-	struct pcmcia_device *link = (struct pcmcia_device *)arg;
-
-	if (pcmcia_dev_present(link))
-		return 1;
-
-	return 0;
-}
-
-static int atmel_config_check(struct pcmcia_device *p_dev, void *priv_data)
-{
-	if (p_dev->config_index == 0)
-		return -EINVAL;
-
-	return pcmcia_request_io(p_dev);
-}
-
-static int atmel_config(struct pcmcia_device *link)
-{
-	int ret;
-	const struct pcmcia_device_id *did;
-
-	did = dev_get_drvdata(&link->dev);
-
-	dev_dbg(&link->dev, "atmel_config\n");
-
-	link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_VPP |
-		CONF_AUTO_AUDIO | CONF_AUTO_SET_IO;
-
-	if (pcmcia_loop_config(link, atmel_config_check, NULL))
-		goto failed;
-
-	if (!link->irq) {
-		dev_err(&link->dev, "atmel: cannot assign IRQ: check that CONFIG_ISA is set in kernel config.");
-		goto failed;
-	}
-
-	ret = pcmcia_enable_device(link);
-	if (ret)
-		goto failed;
-
-	((struct local_info *)link->priv)->eth_dev =
-		init_atmel_card(link->irq,
-				link->resource[0]->start,
-				did ? did->driver_info : ATMEL_FW_TYPE_NONE,
-				&link->dev,
-				card_present,
-				link);
-	if (!((struct local_info *)link->priv)->eth_dev)
-			goto failed;
-
-
-	return 0;
-
- failed:
-	atmel_release(link);
-	return -ENODEV;
-}
-
-static void atmel_release(struct pcmcia_device *link)
-{
-	struct net_device *dev = ((struct local_info *)link->priv)->eth_dev;
-
-	dev_dbg(&link->dev, "atmel_release\n");
-
-	if (dev)
-		stop_atmel_card(dev);
-	((struct local_info *)link->priv)->eth_dev = NULL;
-
-	pcmcia_disable_device(link);
-}
-
-static int atmel_suspend(struct pcmcia_device *link)
-{
-	struct local_info *local = link->priv;
-
-	netif_device_detach(local->eth_dev);
-
-	return 0;
-}
-
-static int atmel_resume(struct pcmcia_device *link)
-{
-	struct local_info *local = link->priv;
-
-	atmel_open(local->eth_dev);
-	netif_device_attach(local->eth_dev);
-
-	return 0;
-}
-
-/*====================================================================*/
-/* We use the driver_info field to store the correct firmware type for a card. */
-
-#define PCMCIA_DEVICE_MANF_CARD_INFO(manf, card, info) { \
-	.match_flags = PCMCIA_DEV_ID_MATCH_MANF_ID| \
-			PCMCIA_DEV_ID_MATCH_CARD_ID, \
-	.manf_id = (manf), \
-	.card_id = (card), \
-        .driver_info = (kernel_ulong_t)(info), }
-
-#define PCMCIA_DEVICE_PROD_ID12_INFO(v1, v2, vh1, vh2, info) { \
-	.match_flags = PCMCIA_DEV_ID_MATCH_PROD_ID1| \
-			PCMCIA_DEV_ID_MATCH_PROD_ID2, \
-	.prod_id = { (v1), (v2), NULL, NULL }, \
-	.prod_id_hash = { (vh1), (vh2), 0, 0 }, \
-        .driver_info = (kernel_ulong_t)(info), }
-
-static const struct pcmcia_device_id atmel_ids[] = {
-	PCMCIA_DEVICE_MANF_CARD_INFO(0x0101, 0x0620, ATMEL_FW_TYPE_502_3COM),
-	PCMCIA_DEVICE_MANF_CARD_INFO(0x0101, 0x0696, ATMEL_FW_TYPE_502_3COM),
-	PCMCIA_DEVICE_MANF_CARD_INFO(0x01bf, 0x3302, ATMEL_FW_TYPE_502E),
-	PCMCIA_DEVICE_MANF_CARD_INFO(0xd601, 0x0007, ATMEL_FW_TYPE_502),
-	PCMCIA_DEVICE_PROD_ID12_INFO("11WAVE", "11WP611AL-E", 0x9eb2da1f, 0xc9a0d3f9, ATMEL_FW_TYPE_502E),
-	PCMCIA_DEVICE_PROD_ID12_INFO("ATMEL", "AT76C502AR", 0xabda4164, 0x41b37e1f, ATMEL_FW_TYPE_502),
-	PCMCIA_DEVICE_PROD_ID12_INFO("ATMEL", "AT76C502AR_D", 0xabda4164, 0x3675d704, ATMEL_FW_TYPE_502D),
-	PCMCIA_DEVICE_PROD_ID12_INFO("ATMEL", "AT76C502AR_E", 0xabda4164, 0x4172e792, ATMEL_FW_TYPE_502E),
-	PCMCIA_DEVICE_PROD_ID12_INFO("ATMEL", "AT76C504_R", 0xabda4164, 0x917f3d72, ATMEL_FW_TYPE_504_2958),
-	PCMCIA_DEVICE_PROD_ID12_INFO("ATMEL", "AT76C504", 0xabda4164, 0x5040670a, ATMEL_FW_TYPE_504),
-	PCMCIA_DEVICE_PROD_ID12_INFO("ATMEL", "AT76C504A", 0xabda4164, 0xe15ed87f, ATMEL_FW_TYPE_504A_2958),
-	PCMCIA_DEVICE_PROD_ID12_INFO("BT", "Voyager 1020 Laptop Adapter", 0xae49b86a, 0x1e957cd5, ATMEL_FW_TYPE_502),
-	PCMCIA_DEVICE_PROD_ID12_INFO("CNet", "CNWLC 11Mbps Wireless PC Card V-5", 0xbc477dde, 0x502fae6b, ATMEL_FW_TYPE_502E),
-	PCMCIA_DEVICE_PROD_ID12_INFO("IEEE 802.11b", "Wireless LAN PC Card", 0x5b878724, 0x122f1df6, ATMEL_FW_TYPE_502),
-	PCMCIA_DEVICE_PROD_ID12_INFO("IEEE 802.11b", "Wireless LAN Card S", 0x5b878724, 0x5fba533a, ATMEL_FW_TYPE_504_2958),
-	PCMCIA_DEVICE_PROD_ID12_INFO("OEM", "11Mbps Wireless LAN PC Card V-3", 0xfea54c90, 0x1c5b0f68, ATMEL_FW_TYPE_502),
-	PCMCIA_DEVICE_PROD_ID12_INFO("SMC", "2632W", 0xc4f8b18b, 0x30f38774, ATMEL_FW_TYPE_502D),
-	PCMCIA_DEVICE_PROD_ID12_INFO("SMC", "2632W-V2", 0xc4f8b18b, 0x172d1377, ATMEL_FW_TYPE_502),
-	PCMCIA_DEVICE_PROD_ID12_INFO("Wireless", "PC_CARD", 0xa407ecdd, 0x119f6314, ATMEL_FW_TYPE_502D),
-	PCMCIA_DEVICE_PROD_ID12_INFO("WLAN", "802.11b PC CARD", 0x575c516c, 0xb1f6dbc4, ATMEL_FW_TYPE_502D),
-	PCMCIA_DEVICE_PROD_ID12_INFO("LG", "LW2100N", 0xb474d43a, 0x6b1fec94, ATMEL_FW_TYPE_502E),
-	PCMCIA_DEVICE_NULL
-};
-
-MODULE_DEVICE_TABLE(pcmcia, atmel_ids);
-
-static struct pcmcia_driver atmel_driver = {
-	.owner		= THIS_MODULE,
-	.name		= "atmel_cs",
-	.probe          = atmel_probe,
-	.remove		= atmel_detach,
-	.id_table	= atmel_ids,
-	.suspend	= atmel_suspend,
-	.resume		= atmel_resume,
-};
-module_pcmcia_driver(atmel_driver);
-
-/*
-    This program is free software; you can redistribute it and/or
-    modify it under the terms of the GNU General Public License
-    as published by the Free Software Foundation; either version 2
-    of the License, or (at your option) any later version.
-
-    This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
-
-    In addition:
-
-    Redistribution and use in source and binary forms, with or without
-    modification, are permitted provided that the following conditions
-    are met:
-
-    1. Redistributions of source code must retain the above copyright
-       notice, this list of conditions and the following disclaimer.
-    2. Redistributions in binary form must reproduce the above copyright
-       notice, this list of conditions and the following disclaimer in the
-       documentation and/or other materials provided with the distribution.
-    3. The name of the author may not be used to endorse or promote
-       products derived from this software without specific prior written
-       permission.
-
-    THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
-    IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-    WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
-    ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT,
-    INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
-    (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-    SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
-    HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
-    STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
-    IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
-    POSSIBILITY OF SUCH DAMAGE.
-*/
diff --git a/drivers/net/wireless/atmel/atmel_pci.c b/drivers/net/wireless/atmel/atmel_pci.c
deleted file mode 100644
index f428dc79d916..000000000000
--- a/drivers/net/wireless/atmel/atmel_pci.c
+++ /dev/null
@@ -1,65 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*** -*- linux-c -*- **********************************************************
-
-     Driver for Atmel at76c502 at76c504 and at76c506 wireless cards.
-
-         Copyright 2004 Simon Kelley.
-
-
-******************************************************************************/
-#include <linux/pci.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/netdevice.h>
-#include "atmel.h"
-
-MODULE_AUTHOR("Simon Kelley");
-MODULE_DESCRIPTION("Support for Atmel at76c50x 802.11 wireless ethernet cards.");
-MODULE_LICENSE("GPL");
-
-static const struct pci_device_id card_ids[] = {
-	{ 0x1114, 0x0506, PCI_ANY_ID, PCI_ANY_ID },
-	{ 0, }
-};
-
-MODULE_DEVICE_TABLE(pci, card_ids);
-
-static int atmel_pci_probe(struct pci_dev *, const struct pci_device_id *);
-static void atmel_pci_remove(struct pci_dev *);
-
-static struct pci_driver atmel_driver = {
-	.name     = "atmel",
-	.id_table = card_ids,
-	.probe    = atmel_pci_probe,
-	.remove   = atmel_pci_remove,
-};
-
-
-static int atmel_pci_probe(struct pci_dev *pdev,
-				     const struct pci_device_id *pent)
-{
-	struct net_device *dev;
-
-	if (pci_enable_device(pdev))
-		return -ENODEV;
-
-	pci_set_master(pdev);
-
-	dev = init_atmel_card(pdev->irq, pdev->resource[1].start,
-			      ATMEL_FW_TYPE_506,
-			      &pdev->dev, NULL, NULL);
-	if (!dev) {
-		pci_disable_device(pdev);
-		return -ENODEV;
-	}
-
-	pci_set_drvdata(pdev, dev);
-	return 0;
-}
-
-static void atmel_pci_remove(struct pci_dev *pdev)
-{
-	stop_atmel_card(pci_get_drvdata(pdev));
-}
-
-module_pci_driver(atmel_driver);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 667462369a32..133c5ea6429c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -866,7 +866,7 @@ struct wireless_dev *brcmf_apsta_add_vif(struct wiphy *wiphy, const char *name,
 		goto fail;
 	}
 
-	strncpy(ifp->ndev->name, name, sizeof(ifp->ndev->name) - 1);
+	strscpy(ifp->ndev->name, name, sizeof(ifp->ndev->name));
 	err = brcmf_net_attach(ifp, true);
 	if (err) {
 		bphy_err(drvr, "Registering netdevice failed\n");
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
index a194b0e68eb5..b6d458e022fa 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
@@ -578,18 +578,16 @@ static int __init brcmf_common_pd_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int brcmf_common_pd_remove(struct platform_device *pdev)
+static void brcmf_common_pd_remove(struct platform_device *pdev)
 {
 	brcmf_dbg(INFO, "Enter\n");
 
 	if (brcmfmac_pdata->power_off)
 		brcmfmac_pdata->power_off();
-
-	return 0;
 }
 
 static struct platform_driver brcmf_pd = {
-	.remove		= brcmf_common_pd_remove,
+	.remove_new	= brcmf_common_pd_remove,
 	.driver		= {
 		.name	= BRCMFMAC_PDATA_NAME,
 	}
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
index d4492d02e4ea..6e0c90f4718b 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
@@ -2334,7 +2334,7 @@ struct wireless_dev *brcmf_p2p_add_vif(struct wiphy *wiphy, const char *name,
 		goto fail;
 	}
 
-	strncpy(ifp->ndev->name, name, sizeof(ifp->ndev->name) - 1);
+	strscpy(ifp->ndev->name, name, sizeof(ifp->ndev->name));
 	ifp->ndev->name_assign_type = name_assign_type;
 	err = brcmf_net_attach(ifp, true);
 	if (err) {
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/channel.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/channel.c
index 5a6d9c86552a..f6962e558d7c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/channel.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/channel.c
@@ -341,7 +341,7 @@ struct brcms_cm_info *brcms_c_channel_mgr_attach(struct brcms_c_info *wlc)
 	/* store the country code for passing up as a regulatory hint */
 	wlc_cm->world_regd = brcms_world_regd(ccode, ccode_len);
 	if (brcms_c_country_valid(ccode))
-		strncpy(wlc->pub->srom_ccode, ccode, ccode_len);
+		memcpy(wlc->pub->srom_ccode, ccode, ccode_len);
 
 	/*
 	 * If no custom world domain is found in the SROM, use the
@@ -354,10 +354,10 @@ struct brcms_cm_info *brcms_c_channel_mgr_attach(struct brcms_c_info *wlc)
 	}
 
 	/* save default country for exiting 11d regulatory mode */
-	strncpy(wlc->country_default, ccode, ccode_len);
+	memcpy(wlc->country_default, ccode, ccode_len);
 
 	/* initialize autocountry_default to driver default */
-	strncpy(wlc->autocountry_default, ccode, ccode_len);
+	memcpy(wlc->autocountry_default, ccode, ccode_len);
 
 	brcms_c_set_country(wlc_cm, wlc_cm->world_regd);
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c
index b7df576bb84d..3d5c1ef8f7f2 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c
@@ -584,8 +584,7 @@ struct dma_pub *dma_attach(char *name, struct brcms_c_info *wlc,
 		      rxextheadroom, nrxpost, rxoffset, txregbase, rxregbase);
 
 	/* make a private copy of our callers name */
-	strncpy(di->name, name, MAXNAMEL);
-	di->name[MAXNAMEL - 1] = '\0';
+	strscpy(di->name, name, sizeof(di->name));
 
 	di->dmadev = core->dma_dev;
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
index b3663c5ef382..34460b5815d0 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
@@ -5551,8 +5551,8 @@ int brcms_c_module_register(struct brcms_pub *pub,
 	/* find an empty entry and just add, no duplication check! */
 	for (i = 0; i < BRCMS_MAXMODULES; i++) {
 		if (wlc->modulecb[i].name[0] == '\0') {
-			strncpy(wlc->modulecb[i].name, name,
-				sizeof(wlc->modulecb[i].name) - 1);
+			strscpy(wlc->modulecb[i].name, name,
+				sizeof(wlc->modulecb[i].name));
 			wlc->modulecb[i].hdl = hdl;
 			wlc->modulecb[i].down_fn = d_fn;
 			return 0;
diff --git a/drivers/net/wireless/cisco/Kconfig b/drivers/net/wireless/cisco/Kconfig
deleted file mode 100644
index b40ee25aca99..000000000000
--- a/drivers/net/wireless/cisco/Kconfig
+++ /dev/null
@@ -1,59 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-config WLAN_VENDOR_CISCO
-	bool "Cisco devices"
-	default y
-	help
-	  If you have a wireless card belonging to this class, say Y.
-
-	  Note that the answer to this question doesn't directly affect the
-	  kernel: saying N will just cause the configurator to skip all the
-	  questions about these cards. If you say Y, you will be asked for
-	  your specific card in the following questions.
-
-if WLAN_VENDOR_CISCO
-
-config AIRO
-	tristate "Cisco/Aironet 34X/35X/4500/4800 ISA and PCI cards"
-	depends on CFG80211 && (PCI || BROKEN)
-	select WIRELESS_EXT
-	select CRYPTO
-	select CRYPTO_SKCIPHER
-	select WEXT_SPY
-	select WEXT_PRIV
-	help
-	  This is the standard Linux driver to support Cisco/Aironet ISA and
-	  PCI 802.11 wireless cards.
-	  It supports the new 802.11b cards from Cisco (Cisco 34X, Cisco 35X
-	  - with or without encryption) as well as card before the Cisco
-	  acquisition (Aironet 4500, Aironet 4800, Aironet 4800B).
-
-	  This driver support both the standard Linux Wireless Extensions
-	  and Cisco proprietary API, so both the Linux Wireless Tools and the
-	  Cisco Linux utilities can be used to configure the card.
-
-	  The driver can be compiled as a module and will be named "airo".
-
-config AIRO_CS
-	tristate "Cisco/Aironet 34X/35X/4500/4800 PCMCIA cards"
-	depends on CFG80211 && PCMCIA
-	select WIRELESS_EXT
-	select WEXT_SPY
-	select WEXT_PRIV
-	select CRYPTO
-	select CRYPTO_AES
-	select CRYPTO_CTR
-	help
-	  This is the standard Linux driver to support Cisco/Aironet PCMCIA
-	  802.11 wireless cards.  This driver is the same as the Aironet
-	  driver part of the Linux Pcmcia package.
-	  It supports the new 802.11b cards from Cisco (Cisco 34X, Cisco 35X
-	  - with or without encryption) as well as card before the Cisco
-	  acquisition (Aironet 4500, Aironet 4800, Aironet 4800B). It also
-	  supports OEM of Cisco such as the DELL TrueMobile 4800 and Xircom
-	  802.11b cards.
-
-	  This driver support both the standard Linux Wireless Extensions
-	  and Cisco proprietary API, so both the Linux Wireless Tools and the
-	  Cisco Linux utilities can be used to configure the card.
-
-endif # WLAN_VENDOR_CISCO
diff --git a/drivers/net/wireless/cisco/Makefile b/drivers/net/wireless/cisco/Makefile
deleted file mode 100644
index 506a19ce375f..000000000000
--- a/drivers/net/wireless/cisco/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_AIRO)		+= airo.o
-obj-$(CONFIG_AIRO_CS)		+= airo_cs.o airo.o
diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c
deleted file mode 100644
index dbd13f7aa3e6..000000000000
--- a/drivers/net/wireless/cisco/airo.c
+++ /dev/null
@@ -1,8288 +0,0 @@
-/*======================================================================
-
-    Aironet driver for 4500 and 4800 series cards
-
-    This code is released under both the GPL version 2 and BSD licenses.
-    Either license may be used.  The respective licenses are found at
-    the end of this file.
-
-    This code was developed by Benjamin Reed <breed@users.sourceforge.net>
-    including portions of which come from the Aironet PC4500
-    Developer's Reference Manual and used with permission.  Copyright
-    (C) 1999 Benjamin Reed.  All Rights Reserved.  Permission to use
-    code in the Developer's manual was granted for this driver by
-    Aironet.  Major code contributions were received from Javier Achirica
-    <achirica@users.sourceforge.net> and Jean Tourrilhes <jt@hpl.hp.com>.
-    Code was also integrated from the Cisco Aironet driver for Linux.
-    Support for MPI350 cards was added by Fabrice Bellet
-    <fabrice@bellet.info>.
-
-======================================================================*/
-
-#include <linux/err.h>
-#include <linux/init.h>
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/proc_fs.h>
-
-#include <linux/sched.h>
-#include <linux/ptrace.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/timer.h>
-#include <linux/interrupt.h>
-#include <linux/in.h>
-#include <linux/bitops.h>
-#include <linux/scatterlist.h>
-#include <linux/crypto.h>
-#include <linux/io.h>
-#include <asm/unaligned.h>
-
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/skbuff.h>
-#include <linux/if_arp.h>
-#include <linux/ioport.h>
-#include <linux/pci.h>
-#include <linux/uaccess.h>
-#include <linux/kthread.h>
-#include <linux/freezer.h>
-
-#include <crypto/aes.h>
-#include <crypto/skcipher.h>
-
-#include <net/cfg80211.h>
-#include <net/iw_handler.h>
-
-#include "airo.h"
-
-#define DRV_NAME "airo"
-
-#ifdef CONFIG_PCI
-static const struct pci_device_id card_ids[] = {
-	{ 0x14b9, 1, PCI_ANY_ID, PCI_ANY_ID, },
-	{ 0x14b9, 0x4500, PCI_ANY_ID, PCI_ANY_ID },
-	{ 0x14b9, 0x4800, PCI_ANY_ID, PCI_ANY_ID, },
-	{ 0x14b9, 0x0340, PCI_ANY_ID, PCI_ANY_ID, },
-	{ 0x14b9, 0x0350, PCI_ANY_ID, PCI_ANY_ID, },
-	{ 0x14b9, 0x5000, PCI_ANY_ID, PCI_ANY_ID, },
-	{ 0x14b9, 0xa504, PCI_ANY_ID, PCI_ANY_ID, },
-	{ 0, }
-};
-MODULE_DEVICE_TABLE(pci, card_ids);
-
-static int airo_pci_probe(struct pci_dev *, const struct pci_device_id *);
-static void airo_pci_remove(struct pci_dev *);
-static int __maybe_unused airo_pci_suspend(struct device *dev);
-static int __maybe_unused airo_pci_resume(struct device *dev);
-
-static SIMPLE_DEV_PM_OPS(airo_pci_pm_ops,
-			 airo_pci_suspend,
-			 airo_pci_resume);
-
-static struct pci_driver airo_driver = {
-	.name      = DRV_NAME,
-	.id_table  = card_ids,
-	.probe     = airo_pci_probe,
-	.remove    = airo_pci_remove,
-	.driver.pm = &airo_pci_pm_ops,
-};
-#endif /* CONFIG_PCI */
-
-/* Include Wireless Extension definition and check version - Jean II */
-#include <linux/wireless.h>
-#define WIRELESS_SPY		/* enable iwspy support */
-
-#define CISCO_EXT		/* enable Cisco extensions */
-#ifdef CISCO_EXT
-#include <linux/delay.h>
-#endif
-
-/* Hack to do some power saving */
-#define POWER_ON_DOWN
-
-/* As you can see this list is HUGH!
-   I really don't know what a lot of these counts are about, but they
-   are all here for completeness.  If the IGNLABEL macro is put in
-   infront of the label, that statistic will not be included in the list
-   of statistics in the /proc filesystem */
-
-#define IGNLABEL(comment) NULL
-static const char *statsLabels[] = {
-	"RxOverrun",
-	IGNLABEL("RxPlcpCrcErr"),
-	IGNLABEL("RxPlcpFormatErr"),
-	IGNLABEL("RxPlcpLengthErr"),
-	"RxMacCrcErr",
-	"RxMacCrcOk",
-	"RxWepErr",
-	"RxWepOk",
-	"RetryLong",
-	"RetryShort",
-	"MaxRetries",
-	"NoAck",
-	"NoCts",
-	"RxAck",
-	"RxCts",
-	"TxAck",
-	"TxRts",
-	"TxCts",
-	"TxMc",
-	"TxBc",
-	"TxUcFrags",
-	"TxUcPackets",
-	"TxBeacon",
-	"RxBeacon",
-	"TxSinColl",
-	"TxMulColl",
-	"DefersNo",
-	"DefersProt",
-	"DefersEngy",
-	"DupFram",
-	"RxFragDisc",
-	"TxAged",
-	"RxAged",
-	"LostSync-MaxRetry",
-	"LostSync-MissedBeacons",
-	"LostSync-ArlExceeded",
-	"LostSync-Deauth",
-	"LostSync-Disassoced",
-	"LostSync-TsfTiming",
-	"HostTxMc",
-	"HostTxBc",
-	"HostTxUc",
-	"HostTxFail",
-	"HostRxMc",
-	"HostRxBc",
-	"HostRxUc",
-	"HostRxDiscard",
-	IGNLABEL("HmacTxMc"),
-	IGNLABEL("HmacTxBc"),
-	IGNLABEL("HmacTxUc"),
-	IGNLABEL("HmacTxFail"),
-	IGNLABEL("HmacRxMc"),
-	IGNLABEL("HmacRxBc"),
-	IGNLABEL("HmacRxUc"),
-	IGNLABEL("HmacRxDiscard"),
-	IGNLABEL("HmacRxAccepted"),
-	"SsidMismatch",
-	"ApMismatch",
-	"RatesMismatch",
-	"AuthReject",
-	"AuthTimeout",
-	"AssocReject",
-	"AssocTimeout",
-	IGNLABEL("ReasonOutsideTable"),
-	IGNLABEL("ReasonStatus1"),
-	IGNLABEL("ReasonStatus2"),
-	IGNLABEL("ReasonStatus3"),
-	IGNLABEL("ReasonStatus4"),
-	IGNLABEL("ReasonStatus5"),
-	IGNLABEL("ReasonStatus6"),
-	IGNLABEL("ReasonStatus7"),
-	IGNLABEL("ReasonStatus8"),
-	IGNLABEL("ReasonStatus9"),
-	IGNLABEL("ReasonStatus10"),
-	IGNLABEL("ReasonStatus11"),
-	IGNLABEL("ReasonStatus12"),
-	IGNLABEL("ReasonStatus13"),
-	IGNLABEL("ReasonStatus14"),
-	IGNLABEL("ReasonStatus15"),
-	IGNLABEL("ReasonStatus16"),
-	IGNLABEL("ReasonStatus17"),
-	IGNLABEL("ReasonStatus18"),
-	IGNLABEL("ReasonStatus19"),
-	"RxMan",
-	"TxMan",
-	"RxRefresh",
-	"TxRefresh",
-	"RxPoll",
-	"TxPoll",
-	"HostRetries",
-	"LostSync-HostReq",
-	"HostTxBytes",
-	"HostRxBytes",
-	"ElapsedUsec",
-	"ElapsedSec",
-	"LostSyncBetterAP",
-	"PrivacyMismatch",
-	"Jammed",
-	"DiscRxNotWepped",
-	"PhyEleMismatch",
-	(char*)-1 };
-#ifndef RUN_AT
-#define RUN_AT(x) (jiffies+(x))
-#endif
-
-
-/* These variables are for insmod, since it seems that the rates
-   can only be set in setup_card.  Rates should be a comma separated
-   (no spaces) list of rates (up to 8). */
-
-static int rates[8];
-static char *ssids[3];
-
-static int io[4];
-static int irq[4];
-
-static
-int maxencrypt /* = 0 */; /* The highest rate that the card can encrypt at.
-		       0 means no limit.  For old cards this was 4 */
-
-static int auto_wep /* = 0 */; /* If set, it tries to figure out the wep mode */
-static int aux_bap /* = 0 */; /* Checks to see if the aux ports are needed to read
-		    the bap, needed on some older cards and buses. */
-static int adhoc;
-
-static int probe = 1;
-
-static kuid_t proc_kuid;
-static int proc_uid /* = 0 */;
-
-static kgid_t proc_kgid;
-static int proc_gid /* = 0 */;
-
-static int airo_perm = 0555;
-
-static int proc_perm = 0644;
-
-MODULE_AUTHOR("Benjamin Reed");
-MODULE_DESCRIPTION("Support for Cisco/Aironet 802.11 wireless ethernet cards.  "
-		   "Direct support for ISA/PCI/MPI cards and support for PCMCIA when used with airo_cs.");
-MODULE_LICENSE("Dual BSD/GPL");
-module_param_hw_array(io, int, ioport, NULL, 0);
-module_param_hw_array(irq, int, irq, NULL, 0);
-module_param_array(rates, int, NULL, 0);
-module_param_array(ssids, charp, NULL, 0);
-module_param(auto_wep, int, 0);
-MODULE_PARM_DESC(auto_wep,
-		 "If non-zero, the driver will keep looping through the authentication options until an association is made.  "
-		 "The value of auto_wep is number of the wep keys to check.  "
-		 "A value of 2 will try using the key at index 0 and index 1.");
-module_param(aux_bap, int, 0);
-MODULE_PARM_DESC(aux_bap,
-		 "If non-zero, the driver will switch into a mode that seems to work better for older cards with some older buses.  "
-		 "Before switching it checks that the switch is needed.");
-module_param(maxencrypt, int, 0);
-MODULE_PARM_DESC(maxencrypt,
-		 "The maximum speed that the card can do encryption.  "
-		 "Units are in 512kbs.  "
-		 "Zero (default) means there is no limit.  "
-		 "Older cards used to be limited to 2mbs (4).");
-module_param(adhoc, int, 0);
-MODULE_PARM_DESC(adhoc, "If non-zero, the card will start in adhoc mode.");
-module_param(probe, int, 0);
-MODULE_PARM_DESC(probe, "If zero, the driver won't start the card.");
-
-module_param(proc_uid, int, 0);
-MODULE_PARM_DESC(proc_uid, "The uid that the /proc files will belong to.");
-module_param(proc_gid, int, 0);
-MODULE_PARM_DESC(proc_gid, "The gid that the /proc files will belong to.");
-module_param(airo_perm, int, 0);
-MODULE_PARM_DESC(airo_perm, "The permission bits of /proc/[driver/]aironet.");
-module_param(proc_perm, int, 0);
-MODULE_PARM_DESC(proc_perm, "The permission bits of the files in /proc");
-
-/* This is a kind of sloppy hack to get this information to OUT4500 and
-   IN4500.  I would be extremely interested in the situation where this
-   doesn't work though!!! */
-static int do8bitIO /* = 0 */;
-
-/* Return codes */
-#define SUCCESS 0
-#define ERROR -1
-#define NO_PACKET -2
-
-/* Commands */
-#define NOP2		0x0000
-#define MAC_ENABLE	0x0001
-#define MAC_DISABLE	0x0002
-#define CMD_LOSE_SYNC	0x0003 /* Not sure what this does... */
-#define CMD_SOFTRESET	0x0004
-#define HOSTSLEEP	0x0005
-#define CMD_MAGIC_PKT	0x0006
-#define CMD_SETWAKEMASK	0x0007
-#define CMD_READCFG	0x0008
-#define CMD_SETMODE	0x0009
-#define CMD_ALLOCATETX	0x000a
-#define CMD_TRANSMIT	0x000b
-#define CMD_DEALLOCATETX 0x000c
-#define NOP		0x0010
-#define CMD_WORKAROUND	0x0011
-#define CMD_ALLOCATEAUX 0x0020
-#define CMD_ACCESS	0x0021
-#define CMD_PCIBAP	0x0022
-#define CMD_PCIAUX	0x0023
-#define CMD_ALLOCBUF	0x0028
-#define CMD_GETTLV	0x0029
-#define CMD_PUTTLV	0x002a
-#define CMD_DELTLV	0x002b
-#define CMD_FINDNEXTTLV	0x002c
-#define CMD_PSPNODES	0x0030
-#define CMD_SETCW	0x0031
-#define CMD_SETPCF	0x0032
-#define CMD_SETPHYREG	0x003e
-#define CMD_TXTEST	0x003f
-#define MAC_ENABLETX	0x0101
-#define CMD_LISTBSS	0x0103
-#define CMD_SAVECFG	0x0108
-#define CMD_ENABLEAUX	0x0111
-#define CMD_WRITERID	0x0121
-#define CMD_USEPSPNODES	0x0130
-#define MAC_ENABLERX	0x0201
-
-/* Command errors */
-#define ERROR_QUALIF 0x00
-#define ERROR_ILLCMD 0x01
-#define ERROR_ILLFMT 0x02
-#define ERROR_INVFID 0x03
-#define ERROR_INVRID 0x04
-#define ERROR_LARGE 0x05
-#define ERROR_NDISABL 0x06
-#define ERROR_ALLOCBSY 0x07
-#define ERROR_NORD 0x0B
-#define ERROR_NOWR 0x0C
-#define ERROR_INVFIDTX 0x0D
-#define ERROR_TESTACT 0x0E
-#define ERROR_TAGNFND 0x12
-#define ERROR_DECODE 0x20
-#define ERROR_DESCUNAV 0x21
-#define ERROR_BADLEN 0x22
-#define ERROR_MODE 0x80
-#define ERROR_HOP 0x81
-#define ERROR_BINTER 0x82
-#define ERROR_RXMODE 0x83
-#define ERROR_MACADDR 0x84
-#define ERROR_RATES 0x85
-#define ERROR_ORDER 0x86
-#define ERROR_SCAN 0x87
-#define ERROR_AUTH 0x88
-#define ERROR_PSMODE 0x89
-#define ERROR_RTYPE 0x8A
-#define ERROR_DIVER 0x8B
-#define ERROR_SSID 0x8C
-#define ERROR_APLIST 0x8D
-#define ERROR_AUTOWAKE 0x8E
-#define ERROR_LEAP 0x8F
-
-/* Registers */
-#define COMMAND 0x00
-#define PARAM0 0x02
-#define PARAM1 0x04
-#define PARAM2 0x06
-#define STATUS 0x08
-#define RESP0 0x0a
-#define RESP1 0x0c
-#define RESP2 0x0e
-#define LINKSTAT 0x10
-#define SELECT0 0x18
-#define OFFSET0 0x1c
-#define RXFID 0x20
-#define TXALLOCFID 0x22
-#define TXCOMPLFID 0x24
-#define DATA0 0x36
-#define EVSTAT 0x30
-#define EVINTEN 0x32
-#define EVACK 0x34
-#define SWS0 0x28
-#define SWS1 0x2a
-#define SWS2 0x2c
-#define SWS3 0x2e
-#define AUXPAGE 0x3A
-#define AUXOFF 0x3C
-#define AUXDATA 0x3E
-
-#define FID_TX 1
-#define FID_RX 2
-/* Offset into aux memory for descriptors */
-#define AUX_OFFSET 0x800
-/* Size of allocated packets */
-#define PKTSIZE 1840
-#define RIDSIZE 2048
-/* Size of the transmit queue */
-#define MAXTXQ 64
-
-/* BAP selectors */
-#define BAP0 0 /* Used for receiving packets */
-#define BAP1 2 /* Used for xmiting packets and working with RIDS */
-
-/* Flags */
-#define COMMAND_BUSY 0x8000
-
-#define BAP_BUSY 0x8000
-#define BAP_ERR 0x4000
-#define BAP_DONE 0x2000
-
-#define PROMISC 0xffff
-#define NOPROMISC 0x0000
-
-#define EV_CMD 0x10
-#define EV_CLEARCOMMANDBUSY 0x4000
-#define EV_RX 0x01
-#define EV_TX 0x02
-#define EV_TXEXC 0x04
-#define EV_ALLOC 0x08
-#define EV_LINK 0x80
-#define EV_AWAKE 0x100
-#define EV_TXCPY 0x400
-#define EV_UNKNOWN 0x800
-#define EV_MIC 0x1000 /* Message Integrity Check Interrupt */
-#define EV_AWAKEN 0x2000
-#define STATUS_INTS (EV_AWAKE|EV_LINK|EV_TXEXC|EV_TX|EV_TXCPY|EV_RX|EV_MIC)
-
-#ifdef CHECK_UNKNOWN_INTS
-#define IGNORE_INTS (EV_CMD | EV_UNKNOWN)
-#else
-#define IGNORE_INTS (~STATUS_INTS)
-#endif
-
-/* RID TYPES */
-#define RID_RW 0x20
-
-/* The RIDs */
-#define RID_CAPABILITIES 0xFF00
-#define RID_APINFO     0xFF01
-#define RID_RADIOINFO  0xFF02
-#define RID_UNKNOWN3   0xFF03
-#define RID_RSSI       0xFF04
-#define RID_CONFIG     0xFF10
-#define RID_SSID       0xFF11
-#define RID_APLIST     0xFF12
-#define RID_DRVNAME    0xFF13
-#define RID_ETHERENCAP 0xFF14
-#define RID_WEP_TEMP   0xFF15
-#define RID_WEP_PERM   0xFF16
-#define RID_MODULATION 0xFF17
-#define RID_OPTIONS    0xFF18
-#define RID_ACTUALCONFIG 0xFF20 /*readonly*/
-#define RID_FACTORYCONFIG 0xFF21
-#define RID_UNKNOWN22  0xFF22
-#define RID_LEAPUSERNAME 0xFF23
-#define RID_LEAPPASSWORD 0xFF24
-#define RID_STATUS     0xFF50
-#define RID_BEACON_HST 0xFF51
-#define RID_BUSY_HST   0xFF52
-#define RID_RETRIES_HST 0xFF53
-#define RID_UNKNOWN54  0xFF54
-#define RID_UNKNOWN55  0xFF55
-#define RID_UNKNOWN56  0xFF56
-#define RID_MIC        0xFF57
-#define RID_STATS16    0xFF60
-#define RID_STATS16DELTA 0xFF61
-#define RID_STATS16DELTACLEAR 0xFF62
-#define RID_STATS      0xFF68
-#define RID_STATSDELTA 0xFF69
-#define RID_STATSDELTACLEAR 0xFF6A
-#define RID_ECHOTEST_RID 0xFF70
-#define RID_ECHOTEST_RESULTS 0xFF71
-#define RID_BSSLISTFIRST 0xFF72
-#define RID_BSSLISTNEXT  0xFF73
-#define RID_WPA_BSSLISTFIRST 0xFF74
-#define RID_WPA_BSSLISTNEXT  0xFF75
-
-typedef struct {
-	u16 cmd;
-	u16 parm0;
-	u16 parm1;
-	u16 parm2;
-} Cmd;
-
-typedef struct {
-	u16 status;
-	u16 rsp0;
-	u16 rsp1;
-	u16 rsp2;
-} Resp;
-
-/*
- * Rids and endian-ness:  The Rids will always be in cpu endian, since
- * this all the patches from the big-endian guys end up doing that.
- * so all rid access should use the read/writeXXXRid routines.
- */
-
-/* This structure came from an email sent to me from an engineer at
-   aironet for inclusion into this driver */
-typedef struct WepKeyRid WepKeyRid;
-struct WepKeyRid {
-	__le16 len;
-	__le16 kindex;
-	u8 mac[ETH_ALEN];
-	__le16 klen;
-	u8 key[16];
-} __packed;
-
-/* These structures are from the Aironet's PC4500 Developers Manual */
-typedef struct Ssid Ssid;
-struct Ssid {
-	__le16 len;
-	u8 ssid[32];
-} __packed;
-
-typedef struct SsidRid SsidRid;
-struct SsidRid {
-	__le16 len;
-	Ssid ssids[3];
-} __packed;
-
-typedef struct ModulationRid ModulationRid;
-struct ModulationRid {
-        __le16 len;
-        __le16 modulation;
-#define MOD_DEFAULT cpu_to_le16(0)
-#define MOD_CCK cpu_to_le16(1)
-#define MOD_MOK cpu_to_le16(2)
-} __packed;
-
-typedef struct ConfigRid ConfigRid;
-struct ConfigRid {
-	__le16 len; /* sizeof(ConfigRid) */
-	__le16 opmode; /* operating mode */
-#define MODE_STA_IBSS cpu_to_le16(0)
-#define MODE_STA_ESS cpu_to_le16(1)
-#define MODE_AP cpu_to_le16(2)
-#define MODE_AP_RPTR cpu_to_le16(3)
-#define MODE_CFG_MASK cpu_to_le16(0xff)
-#define MODE_ETHERNET_HOST cpu_to_le16(0<<8) /* rx payloads converted */
-#define MODE_LLC_HOST cpu_to_le16(1<<8) /* rx payloads left as is */
-#define MODE_AIRONET_EXTEND cpu_to_le16(1<<9) /* enable Aironet extensions */
-#define MODE_AP_INTERFACE cpu_to_le16(1<<10) /* enable ap interface extensions */
-#define MODE_ANTENNA_ALIGN cpu_to_le16(1<<11) /* enable antenna alignment */
-#define MODE_ETHER_LLC cpu_to_le16(1<<12) /* enable ethernet LLC */
-#define MODE_LEAF_NODE cpu_to_le16(1<<13) /* enable leaf node bridge */
-#define MODE_CF_POLLABLE cpu_to_le16(1<<14) /* enable CF pollable */
-#define MODE_MIC cpu_to_le16(1<<15) /* enable MIC */
-	__le16 rmode; /* receive mode */
-#define RXMODE_BC_MC_ADDR cpu_to_le16(0)
-#define RXMODE_BC_ADDR cpu_to_le16(1) /* ignore multicasts */
-#define RXMODE_ADDR cpu_to_le16(2) /* ignore multicast and broadcast */
-#define RXMODE_RFMON cpu_to_le16(3) /* wireless monitor mode */
-#define RXMODE_RFMON_ANYBSS cpu_to_le16(4)
-#define RXMODE_LANMON cpu_to_le16(5) /* lan style monitor -- data packets only */
-#define RXMODE_MASK cpu_to_le16(255)
-#define RXMODE_DISABLE_802_3_HEADER cpu_to_le16(1<<8) /* disables 802.3 header on rx */
-#define RXMODE_FULL_MASK (RXMODE_MASK | RXMODE_DISABLE_802_3_HEADER)
-#define RXMODE_NORMALIZED_RSSI cpu_to_le16(1<<9) /* return normalized RSSI */
-	__le16 fragThresh;
-	__le16 rtsThres;
-	u8 macAddr[ETH_ALEN];
-	u8 rates[8];
-	__le16 shortRetryLimit;
-	__le16 longRetryLimit;
-	__le16 txLifetime; /* in kusec */
-	__le16 rxLifetime; /* in kusec */
-	__le16 stationary;
-	__le16 ordering;
-	__le16 u16deviceType; /* for overriding device type */
-	__le16 cfpRate;
-	__le16 cfpDuration;
-	__le16 _reserved1[3];
-	/*---------- Scanning/Associating ----------*/
-	__le16 scanMode;
-#define SCANMODE_ACTIVE cpu_to_le16(0)
-#define SCANMODE_PASSIVE cpu_to_le16(1)
-#define SCANMODE_AIROSCAN cpu_to_le16(2)
-	__le16 probeDelay; /* in kusec */
-	__le16 probeEnergyTimeout; /* in kusec */
-        __le16 probeResponseTimeout;
-	__le16 beaconListenTimeout;
-	__le16 joinNetTimeout;
-	__le16 authTimeout;
-	__le16 authType;
-#define AUTH_OPEN cpu_to_le16(0x1)
-#define AUTH_ENCRYPT cpu_to_le16(0x101)
-#define AUTH_SHAREDKEY cpu_to_le16(0x102)
-#define AUTH_ALLOW_UNENCRYPTED cpu_to_le16(0x200)
-	__le16 associationTimeout;
-	__le16 specifiedApTimeout;
-	__le16 offlineScanInterval;
-	__le16 offlineScanDuration;
-	__le16 linkLossDelay;
-	__le16 maxBeaconLostTime;
-	__le16 refreshInterval;
-#define DISABLE_REFRESH cpu_to_le16(0xFFFF)
-	__le16 _reserved1a[1];
-	/*---------- Power save operation ----------*/
-	__le16 powerSaveMode;
-#define POWERSAVE_CAM cpu_to_le16(0)
-#define POWERSAVE_PSP cpu_to_le16(1)
-#define POWERSAVE_PSPCAM cpu_to_le16(2)
-	__le16 sleepForDtims;
-	__le16 listenInterval;
-	__le16 fastListenInterval;
-	__le16 listenDecay;
-	__le16 fastListenDelay;
-	__le16 _reserved2[2];
-	/*---------- Ap/Ibss config items ----------*/
-	__le16 beaconPeriod;
-	__le16 atimDuration;
-	__le16 hopPeriod;
-	__le16 channelSet;
-	__le16 channel;
-	__le16 dtimPeriod;
-	__le16 bridgeDistance;
-	__le16 radioID;
-	/*---------- Radio configuration ----------*/
-	__le16 radioType;
-#define RADIOTYPE_DEFAULT cpu_to_le16(0)
-#define RADIOTYPE_802_11 cpu_to_le16(1)
-#define RADIOTYPE_LEGACY cpu_to_le16(2)
-	u8 rxDiversity;
-	u8 txDiversity;
-	__le16 txPower;
-#define TXPOWER_DEFAULT 0
-	__le16 rssiThreshold;
-#define RSSI_DEFAULT 0
-        __le16 modulation;
-#define PREAMBLE_AUTO cpu_to_le16(0)
-#define PREAMBLE_LONG cpu_to_le16(1)
-#define PREAMBLE_SHORT cpu_to_le16(2)
-	__le16 preamble;
-	__le16 homeProduct;
-	__le16 radioSpecific;
-	/*---------- Aironet Extensions ----------*/
-	u8 nodeName[16];
-	__le16 arlThreshold;
-	__le16 arlDecay;
-	__le16 arlDelay;
-	__le16 _reserved4[1];
-	/*---------- Aironet Extensions ----------*/
-	u8 magicAction;
-#define MAGIC_ACTION_STSCHG 1
-#define MAGIC_ACTION_RESUME 2
-#define MAGIC_IGNORE_MCAST (1<<8)
-#define MAGIC_IGNORE_BCAST (1<<9)
-#define MAGIC_SWITCH_TO_PSP (0<<10)
-#define MAGIC_STAY_IN_CAM (1<<10)
-	u8 magicControl;
-	__le16 autoWake;
-} __packed;
-
-typedef struct StatusRid StatusRid;
-struct StatusRid {
-	__le16 len;
-	u8 mac[ETH_ALEN];
-	__le16 mode;
-	__le16 errorCode;
-	__le16 sigQuality;
-	__le16 SSIDlen;
-	char SSID[32];
-	char apName[16];
-	u8 bssid[4][ETH_ALEN];
-	__le16 beaconPeriod;
-	__le16 dimPeriod;
-	__le16 atimDuration;
-	__le16 hopPeriod;
-	__le16 channelSet;
-	__le16 channel;
-	__le16 hopsToBackbone;
-	__le16 apTotalLoad;
-	__le16 generatedLoad;
-	__le16 accumulatedArl;
-	__le16 signalQuality;
-	__le16 currentXmitRate;
-	__le16 apDevExtensions;
-	__le16 normalizedSignalStrength;
-	__le16 shortPreamble;
-	u8 apIP[4];
-	u8 noisePercent; /* Noise percent in last second */
-	u8 noisedBm; /* Noise dBm in last second */
-	u8 noiseAvePercent; /* Noise percent in last minute */
-	u8 noiseAvedBm; /* Noise dBm in last minute */
-	u8 noiseMaxPercent; /* Highest noise percent in last minute */
-	u8 noiseMaxdBm; /* Highest noise dbm in last minute */
-	__le16 load;
-	u8 carrier[4];
-	__le16 assocStatus;
-#define STAT_NOPACKETS 0
-#define STAT_NOCARRIERSET 10
-#define STAT_GOTCARRIERSET 11
-#define STAT_WRONGSSID 20
-#define STAT_BADCHANNEL 25
-#define STAT_BADBITRATES 30
-#define STAT_BADPRIVACY 35
-#define STAT_APFOUND 40
-#define STAT_APREJECTED 50
-#define STAT_AUTHENTICATING 60
-#define STAT_DEAUTHENTICATED 61
-#define STAT_AUTHTIMEOUT 62
-#define STAT_ASSOCIATING 70
-#define STAT_DEASSOCIATED 71
-#define STAT_ASSOCTIMEOUT 72
-#define STAT_NOTAIROAP 73
-#define STAT_ASSOCIATED 80
-#define STAT_LEAPING 90
-#define STAT_LEAPFAILED 91
-#define STAT_LEAPTIMEDOUT 92
-#define STAT_LEAPCOMPLETE 93
-} __packed;
-
-typedef struct StatsRid StatsRid;
-struct StatsRid {
-	__le16 len;
-	__le16 spacer;
-	__le32 vals[100];
-} __packed;
-
-typedef struct APListRid APListRid;
-struct APListRid {
-	__le16 len;
-	u8 ap[4][ETH_ALEN];
-} __packed;
-
-typedef struct CapabilityRid CapabilityRid;
-struct CapabilityRid {
-	__le16 len;
-	char oui[3];
-	char zero;
-	__le16 prodNum;
-	char manName[32];
-	char prodName[16];
-	char prodVer[8];
-	char factoryAddr[ETH_ALEN];
-	char aironetAddr[ETH_ALEN];
-	__le16 radioType;
-	__le16 country;
-	char callid[ETH_ALEN];
-	char supportedRates[8];
-	char rxDiversity;
-	char txDiversity;
-	__le16 txPowerLevels[8];
-	__le16 hardVer;
-	__le16 hardCap;
-	__le16 tempRange;
-	__le16 softVer;
-	__le16 softSubVer;
-	__le16 interfaceVer;
-	__le16 softCap;
-	__le16 bootBlockVer;
-	__le16 requiredHard;
-	__le16 extSoftCap;
-} __packed;
-
-/* Only present on firmware >= 5.30.17 */
-typedef struct BSSListRidExtra BSSListRidExtra;
-struct BSSListRidExtra {
-  __le16 unknown[4];
-  u8 fixed[12]; /* WLAN management frame */
-  u8 iep[624];
-} __packed;
-
-typedef struct BSSListRid BSSListRid;
-struct BSSListRid {
-  __le16 len;
-  __le16 index; /* First is 0 and 0xffff means end of list */
-#define RADIO_FH 1 /* Frequency hopping radio type */
-#define RADIO_DS 2 /* Direct sequence radio type */
-#define RADIO_TMA 4 /* Proprietary radio used in old cards (2500) */
-  __le16 radioType;
-  u8 bssid[ETH_ALEN]; /* Mac address of the BSS */
-  u8 zero;
-  u8 ssidLen;
-  u8 ssid[32];
-  __le16 dBm;
-#define CAP_ESS cpu_to_le16(1<<0)
-#define CAP_IBSS cpu_to_le16(1<<1)
-#define CAP_PRIVACY cpu_to_le16(1<<4)
-#define CAP_SHORTHDR cpu_to_le16(1<<5)
-  __le16 cap;
-  __le16 beaconInterval;
-  u8 rates[8]; /* Same as rates for config rid */
-  struct { /* For frequency hopping only */
-    __le16 dwell;
-    u8 hopSet;
-    u8 hopPattern;
-    u8 hopIndex;
-    u8 fill;
-  } fh;
-  __le16 dsChannel;
-  __le16 atimWindow;
-
-  /* Only present on firmware >= 5.30.17 */
-  BSSListRidExtra extra;
-} __packed;
-
-typedef struct {
-  BSSListRid bss;
-  struct list_head list;
-} BSSListElement;
-
-typedef struct tdsRssiEntry tdsRssiEntry;
-struct tdsRssiEntry {
-  u8 rssipct;
-  u8 rssidBm;
-} __packed;
-
-typedef struct tdsRssiRid tdsRssiRid;
-struct tdsRssiRid {
-  u16 len;
-  tdsRssiEntry x[256];
-} __packed;
-
-typedef struct MICRid MICRid;
-struct MICRid {
-	__le16 len;
-	__le16 state;
-	__le16 multicastValid;
-	u8  multicast[16];
-	__le16 unicastValid;
-	u8  unicast[16];
-} __packed;
-
-typedef struct MICBuffer MICBuffer;
-struct MICBuffer {
-	__be16 typelen;
-
-	union {
-	    u8 snap[8];
-	    struct {
-		u8 dsap;
-		u8 ssap;
-		u8 control;
-		u8 orgcode[3];
-		u8 fieldtype[2];
-	    } llc;
-	} u;
-	__be32 mic;
-	__be32 seq;
-} __packed;
-
-typedef struct {
-	u8 da[ETH_ALEN];
-	u8 sa[ETH_ALEN];
-} etherHead;
-
-#define TXCTL_TXOK (1<<1) /* report if tx is ok */
-#define TXCTL_TXEX (1<<2) /* report if tx fails */
-#define TXCTL_802_3 (0<<3) /* 802.3 packet */
-#define TXCTL_802_11 (1<<3) /* 802.11 mac packet */
-#define TXCTL_ETHERNET (0<<4) /* payload has ethertype */
-#define TXCTL_LLC (1<<4) /* payload is llc */
-#define TXCTL_RELEASE (0<<5) /* release after completion */
-#define TXCTL_NORELEASE (1<<5) /* on completion returns to host */
-
-#define BUSY_FID 0x10000
-
-#ifdef CISCO_EXT
-#define AIROMAGIC	0xa55a
-/* Warning : SIOCDEVPRIVATE may disapear during 2.5.X - Jean II */
-#ifdef SIOCIWFIRSTPRIV
-#ifdef SIOCDEVPRIVATE
-#define AIROOLDIOCTL	SIOCDEVPRIVATE
-#define AIROOLDIDIFC 	AIROOLDIOCTL + 1
-#endif /* SIOCDEVPRIVATE */
-#else /* SIOCIWFIRSTPRIV */
-#define SIOCIWFIRSTPRIV SIOCDEVPRIVATE
-#endif /* SIOCIWFIRSTPRIV */
-/* This may be wrong. When using the new SIOCIWFIRSTPRIV range, we probably
- * should use only "GET" ioctls (last bit set to 1). "SET" ioctls are root
- * only and don't return the modified struct ifreq to the application which
- * is usually a problem. - Jean II */
-#define AIROIOCTL	SIOCIWFIRSTPRIV
-#define AIROIDIFC 	AIROIOCTL + 1
-
-/* Ioctl constants to be used in airo_ioctl.command */
-
-#define	AIROGCAP  		0	// Capability rid
-#define AIROGCFG		1       // USED A LOT
-#define AIROGSLIST		2	// System ID list
-#define AIROGVLIST		3       // List of specified AP's
-#define AIROGDRVNAM		4	//  NOTUSED
-#define AIROGEHTENC		5	// NOTUSED
-#define AIROGWEPKTMP		6
-#define AIROGWEPKNV		7
-#define AIROGSTAT		8
-#define AIROGSTATSC32		9
-#define AIROGSTATSD32		10
-#define AIROGMICRID		11
-#define AIROGMICSTATS		12
-#define AIROGFLAGS		13
-#define AIROGID			14
-#define AIRORRID		15
-#define AIRORSWVERSION		17
-
-/* Leave gap of 40 commands after AIROGSTATSD32 for future */
-
-#define AIROPCAP               	AIROGSTATSD32 + 40
-#define AIROPVLIST              AIROPCAP      + 1
-#define AIROPSLIST		AIROPVLIST    + 1
-#define AIROPCFG		AIROPSLIST    + 1
-#define AIROPSIDS		AIROPCFG      + 1
-#define AIROPAPLIST		AIROPSIDS     + 1
-#define AIROPMACON		AIROPAPLIST   + 1	/* Enable mac  */
-#define AIROPMACOFF		AIROPMACON    + 1 	/* Disable mac */
-#define AIROPSTCLR		AIROPMACOFF   + 1
-#define AIROPWEPKEY		AIROPSTCLR    + 1
-#define AIROPWEPKEYNV		AIROPWEPKEY   + 1
-#define AIROPLEAPPWD            AIROPWEPKEYNV + 1
-#define AIROPLEAPUSR            AIROPLEAPPWD  + 1
-
-/* Flash codes */
-
-#define AIROFLSHRST	       AIROPWEPKEYNV  + 40
-#define AIROFLSHGCHR           AIROFLSHRST    + 1
-#define AIROFLSHSTFL           AIROFLSHGCHR   + 1
-#define AIROFLSHPCHR           AIROFLSHSTFL   + 1
-#define AIROFLPUTBUF           AIROFLSHPCHR   + 1
-#define AIRORESTART            AIROFLPUTBUF   + 1
-
-#define FLASHSIZE	32768
-#define AUXMEMSIZE	(256 * 1024)
-
-typedef struct aironet_ioctl {
-	unsigned short command;		// What to do
-	unsigned short len;		// Len of data
-	unsigned short ridnum;		// rid number
-	unsigned char __user *data;	// d-data
-} aironet_ioctl;
-
-static const char swversion[] = "2.1";
-#endif /* CISCO_EXT */
-
-#define NUM_MODULES       2
-#define MIC_MSGLEN_MAX    2400
-#define EMMH32_MSGLEN_MAX MIC_MSGLEN_MAX
-#define AIRO_DEF_MTU      2312
-
-typedef struct {
-	u32   size;            // size
-	u8    enabled;         // MIC enabled or not
-	u32   rxSuccess;       // successful packets received
-	u32   rxIncorrectMIC;  // pkts dropped due to incorrect MIC comparison
-	u32   rxNotMICed;      // pkts dropped due to not being MIC'd
-	u32   rxMICPlummed;    // pkts dropped due to not having a MIC plummed
-	u32   rxWrongSequence; // pkts dropped due to sequence number violation
-	u32   reserve[32];
-} mic_statistics;
-
-typedef struct {
-	__be32 coeff[((EMMH32_MSGLEN_MAX)+3)>>2];
-	u64 accum;	// accumulated mic, reduced to u32 in final()
-	int position;	// current position (byte offset) in message
-	union {
-		u8  d8[4];
-		__be32 d32;
-	} part;	// saves partial message word across update() calls
-} emmh32_context;
-
-typedef struct {
-	emmh32_context seed;	    // Context - the seed
-	u32		 rx;	    // Received sequence number
-	u32		 tx;	    // Tx sequence number
-	u32		 window;    // Start of window
-	u8		 valid;	    // Flag to say if context is valid or not
-	u8		 key[16];
-} miccntx;
-
-typedef struct {
-	miccntx mCtx;		// Multicast context
-	miccntx uCtx;		// Unicast context
-} mic_module;
-
-typedef struct {
-	unsigned int  rid: 16;
-	unsigned int  len: 15;
-	unsigned int  valid: 1;
-	dma_addr_t host_addr;
-} Rid;
-
-typedef struct {
-	unsigned int  offset: 15;
-	unsigned int  eoc: 1;
-	unsigned int  len: 15;
-	unsigned int  valid: 1;
-	dma_addr_t host_addr;
-} TxFid;
-
-struct rx_hdr {
-	__le16 status, len;
-	u8 rssi[2];
-	u8 rate;
-	u8 freq;
-	__le16 tmp[4];
-} __packed;
-
-typedef struct {
-	unsigned int  ctl: 15;
-	unsigned int  rdy: 1;
-	unsigned int  len: 15;
-	unsigned int  valid: 1;
-	dma_addr_t host_addr;
-} RxFid;
-
-/*
- * Host receive descriptor
- */
-typedef struct {
-	unsigned char __iomem *card_ram_off; /* offset into card memory of the
-						desc */
-	RxFid         rx_desc;		     /* card receive descriptor */
-	char          *virtual_host_addr;    /* virtual address of host receive
-					        buffer */
-	int           pending;
-} HostRxDesc;
-
-/*
- * Host transmit descriptor
- */
-typedef struct {
-	unsigned char __iomem *card_ram_off;	     /* offset into card memory of the
-						desc */
-	TxFid         tx_desc;		     /* card transmit descriptor */
-	char          *virtual_host_addr;    /* virtual address of host receive
-					        buffer */
-	int           pending;
-} HostTxDesc;
-
-/*
- * Host RID descriptor
- */
-typedef struct {
-	unsigned char __iomem *card_ram_off;      /* offset into card memory of the
-					     descriptor */
-	Rid           rid_desc;		  /* card RID descriptor */
-	char          *virtual_host_addr; /* virtual address of host receive
-					     buffer */
-} HostRidDesc;
-
-typedef struct {
-	u16 sw0;
-	u16 sw1;
-	u16 status;
-	u16 len;
-#define HOST_SET (1 << 0)
-#define HOST_INT_TX (1 << 1) /* Interrupt on successful TX */
-#define HOST_INT_TXERR (1 << 2) /* Interrupt on unseccessful TX */
-#define HOST_LCC_PAYLOAD (1 << 4) /* LLC payload, 0 = Ethertype */
-#define HOST_DONT_RLSE (1 << 5) /* Don't release buffer when done */
-#define HOST_DONT_RETRY (1 << 6) /* Don't retry trasmit */
-#define HOST_CLR_AID (1 << 7) /* clear AID failure */
-#define HOST_RTS (1 << 9) /* Force RTS use */
-#define HOST_SHORT (1 << 10) /* Do short preamble */
-	u16 ctl;
-	u16 aid;
-	u16 retries;
-	u16 fill;
-} TxCtlHdr;
-
-typedef struct {
-        u16 ctl;
-        u16 duration;
-        char addr1[6];
-        char addr2[6];
-        char addr3[6];
-        u16 seq;
-        char addr4[6];
-} WifiHdr;
-
-
-typedef struct {
-	TxCtlHdr ctlhdr;
-	u16 fill1;
-	u16 fill2;
-	WifiHdr wifihdr;
-	u16 gaplen;
-	u16 status;
-} WifiCtlHdr;
-
-static WifiCtlHdr wifictlhdr8023 = {
-	.ctlhdr = {
-		.ctl	= HOST_DONT_RLSE,
-	}
-};
-
-// A few details needed for WEP (Wireless Equivalent Privacy)
-#define MAX_KEY_SIZE 13			// 128 (?) bits
-#define MIN_KEY_SIZE  5			// 40 bits RC4 - WEP
-typedef struct wep_key_t {
-	u16	len;
-	u8	key[16];	/* 40-bit and 104-bit keys */
-} wep_key_t;
-
-/* List of Wireless Handlers (new API) */
-static const struct iw_handler_def	airo_handler_def;
-
-static const char version[] = "airo.c 0.6 (Ben Reed & Javier Achirica)";
-
-struct airo_info;
-
-static int get_dec_u16(char *buffer, int *start, int limit);
-static void OUT4500(struct airo_info *, u16 reg, u16 value);
-static unsigned short IN4500(struct airo_info *, u16 reg);
-static u16 setup_card(struct airo_info*, struct net_device *dev, int lock);
-static int enable_MAC(struct airo_info *ai, int lock);
-static void disable_MAC(struct airo_info *ai, int lock);
-static void enable_interrupts(struct airo_info*);
-static void disable_interrupts(struct airo_info*);
-static u16 issuecommand(struct airo_info*, Cmd *pCmd, Resp *pRsp,
-			bool may_sleep);
-static int bap_setup(struct airo_info*, u16 rid, u16 offset, int whichbap);
-static int aux_bap_read(struct airo_info*, __le16 *pu16Dst, int bytelen,
-			int whichbap);
-static int fast_bap_read(struct airo_info*, __le16 *pu16Dst, int bytelen,
-			 int whichbap);
-static int bap_write(struct airo_info*, const __le16 *pu16Src, int bytelen,
-		     int whichbap);
-static int PC4500_accessrid(struct airo_info*, u16 rid, u16 accmd);
-static int PC4500_readrid(struct airo_info*, u16 rid, void *pBuf, int len, int lock);
-static int PC4500_writerid(struct airo_info*, u16 rid, const void
-			   *pBuf, int len, int lock);
-static int do_writerid(struct airo_info*, u16 rid, const void *rid_data,
-			int len, int dummy);
-static u16 transmit_allocate(struct airo_info*, int lenPayload, int raw);
-static int transmit_802_3_packet(struct airo_info*, int len, char *pPacket,
-				 bool may_sleep);
-static int transmit_802_11_packet(struct airo_info*, int len, char *pPacket,
-				  bool may_sleep);
-
-static int mpi_send_packet(struct net_device *dev);
-static void mpi_unmap_card(struct pci_dev *pci);
-static void mpi_receive_802_3(struct airo_info *ai);
-static void mpi_receive_802_11(struct airo_info *ai);
-static int waitbusy(struct airo_info *ai);
-
-static irqreturn_t airo_interrupt(int irq, void* dev_id);
-static int airo_thread(void *data);
-static void timer_func(struct net_device *dev);
-static int airo_siocdevprivate(struct net_device *dev, struct ifreq *rq, void __user *, int cmd);
-static struct iw_statistics *airo_get_wireless_stats(struct net_device *dev);
-#ifdef CISCO_EXT
-static int readrids(struct net_device *dev, aironet_ioctl *comp);
-static int writerids(struct net_device *dev, aironet_ioctl *comp);
-static int flashcard(struct net_device *dev, aironet_ioctl *comp);
-#endif /* CISCO_EXT */
-static void micinit(struct airo_info *ai);
-static int micsetup(struct airo_info *ai);
-static int encapsulate(struct airo_info *ai, etherHead *pPacket, MICBuffer *buffer, int len);
-static int decapsulate(struct airo_info *ai, MICBuffer *mic, etherHead *pPacket, u16 payLen);
-
-static u8 airo_rssi_to_dbm(tdsRssiEntry *rssi_rid, u8 rssi);
-static u8 airo_dbm_to_pct(tdsRssiEntry *rssi_rid, u8 dbm);
-
-static void airo_networks_free(struct airo_info *ai);
-
-struct airo_info {
-	struct net_device             *dev;
-	struct list_head              dev_list;
-	/* Note, we can have MAX_FIDS outstanding.  FIDs are 16-bits, so we
-	   use the high bit to mark whether it is in use. */
-#define MAX_FIDS 6
-#define MPI_MAX_FIDS 1
-	u32                           fids[MAX_FIDS];
-	ConfigRid config;
-	char keyindex; // Used with auto wep
-	char defindex; // Used with auto wep
-	struct proc_dir_entry *proc_entry;
-        spinlock_t aux_lock;
-#define FLAG_RADIO_OFF	0	/* User disabling of MAC */
-#define FLAG_RADIO_DOWN	1	/* ifup/ifdown disabling of MAC */
-#define FLAG_RADIO_MASK 0x03
-#define FLAG_ENABLED	2
-#define FLAG_ADHOC	3	/* Needed by MIC */
-#define FLAG_MIC_CAPABLE 4
-#define FLAG_UPDATE_MULTI 5
-#define FLAG_UPDATE_UNI 6
-#define FLAG_802_11	7
-#define FLAG_PROMISC	8	/* IFF_PROMISC 0x100 - include/linux/if.h */
-#define FLAG_PENDING_XMIT 9
-#define FLAG_PENDING_XMIT11 10
-#define FLAG_MPI	11
-#define FLAG_REGISTERED	12
-#define FLAG_COMMIT	13
-#define FLAG_RESET	14
-#define FLAG_FLASHING	15
-#define FLAG_WPA_CAPABLE	16
-	unsigned long flags;
-#define JOB_DIE	0
-#define JOB_XMIT	1
-#define JOB_XMIT11	2
-#define JOB_STATS	3
-#define JOB_PROMISC	4
-#define JOB_MIC	5
-#define JOB_EVENT	6
-#define JOB_AUTOWEP	7
-#define JOB_SCAN_RESULTS  9
-	unsigned long jobs;
-	int (*bap_read)(struct airo_info*, __le16 *pu16Dst, int bytelen,
-			int whichbap);
-	unsigned short *flash;
-	tdsRssiEntry *rssi;
-	struct task_struct *list_bss_task;
-	struct task_struct *airo_thread_task;
-	struct semaphore sem;
-	wait_queue_head_t thr_wait;
-	unsigned long expires;
-	struct {
-		struct sk_buff *skb;
-		int fid;
-	} xmit, xmit11;
-	struct net_device *wifidev;
-	struct iw_statistics	wstats;		// wireless stats
-	unsigned long		scan_timeout;	/* Time scan should be read */
-	struct iw_spy_data	spy_data;
-	struct iw_public_data	wireless_data;
-	/* MIC stuff */
-	struct crypto_sync_skcipher	*tfm;
-	mic_module		mod[2];
-	mic_statistics		micstats;
-	HostRxDesc rxfids[MPI_MAX_FIDS]; // rx/tx/config MPI350 descriptors
-	HostTxDesc txfids[MPI_MAX_FIDS];
-	HostRidDesc config_desc;
-	unsigned long ridbus; // phys addr of config_desc
-	struct sk_buff_head txq;// tx queue used by mpi350 code
-	struct pci_dev          *pci;
-	unsigned char		__iomem *pcimem;
-	unsigned char		__iomem *pciaux;
-	unsigned char		*shared;
-	dma_addr_t		shared_dma;
-	pm_message_t		power;
-	SsidRid			*SSID;
-	APListRid		APList;
-#define	PCI_SHARED_LEN		2*MPI_MAX_FIDS*PKTSIZE+RIDSIZE
-	char			proc_name[IFNAMSIZ];
-
-	int			wep_capable;
-	int			max_wep_idx;
-	int			last_auth;
-
-	/* WPA-related stuff */
-	unsigned int bssListFirst;
-	unsigned int bssListNext;
-	unsigned int bssListRidLen;
-
-	struct list_head network_list;
-	struct list_head network_free_list;
-	BSSListElement *networks;
-};
-
-static inline int bap_read(struct airo_info *ai, __le16 *pu16Dst, int bytelen,
-			   int whichbap)
-{
-	return ai->bap_read(ai, pu16Dst, bytelen, whichbap);
-}
-
-static int setup_proc_entry(struct net_device *dev,
-			     struct airo_info *apriv);
-static int takedown_proc_entry(struct net_device *dev,
-				struct airo_info *apriv);
-
-static int cmdreset(struct airo_info *ai);
-static int setflashmode(struct airo_info *ai);
-static int flashgchar(struct airo_info *ai, int matchbyte, int dwelltime);
-static int flashputbuf(struct airo_info *ai);
-static int flashrestart(struct airo_info *ai, struct net_device *dev);
-
-#define airo_print(type, name, fmt, args...) \
-	printk(type DRV_NAME "(%s): " fmt "\n", name, ##args)
-
-#define airo_print_info(name, fmt, args...) \
-	airo_print(KERN_INFO, name, fmt, ##args)
-
-#define airo_print_dbg(name, fmt, args...) \
-	airo_print(KERN_DEBUG, name, fmt, ##args)
-
-#define airo_print_warn(name, fmt, args...) \
-	airo_print(KERN_WARNING, name, fmt, ##args)
-
-#define airo_print_err(name, fmt, args...) \
-	airo_print(KERN_ERR, name, fmt, ##args)
-
-#define AIRO_FLASH(dev) (((struct airo_info *)dev->ml_priv)->flash)
-
-/***********************************************************************
- *                              MIC ROUTINES                           *
- ***********************************************************************
- */
-
-static int RxSeqValid(struct airo_info *ai, miccntx *context, int mcast, u32 micSeq);
-static void MoveWindow(miccntx *context, u32 micSeq);
-static void emmh32_setseed(emmh32_context *context, u8 *pkey, int keylen,
-			   struct crypto_sync_skcipher *tfm);
-static void emmh32_init(emmh32_context *context);
-static void emmh32_update(emmh32_context *context, u8 *pOctets, int len);
-static void emmh32_final(emmh32_context *context, u8 digest[4]);
-static int flashpchar(struct airo_info *ai, int byte, int dwelltime);
-
-static void age_mic_context(miccntx *cur, miccntx *old, u8 *key, int key_len,
-			    struct crypto_sync_skcipher *tfm)
-{
-	/* If the current MIC context is valid and its key is the same as
-	 * the MIC register, there's nothing to do.
-	 */
-	if (cur->valid && (memcmp(cur->key, key, key_len) == 0))
-		return;
-
-	/* Age current mic Context */
-	memcpy(old, cur, sizeof(*cur));
-
-	/* Initialize new context */
-	memcpy(cur->key, key, key_len);
-	cur->window  = 33; /* Window always points to the middle */
-	cur->rx      = 0;  /* Rx Sequence numbers */
-	cur->tx      = 0;  /* Tx sequence numbers */
-	cur->valid   = 1;  /* Key is now valid */
-
-	/* Give key to mic seed */
-	emmh32_setseed(&cur->seed, key, key_len, tfm);
-}
-
-/* micinit - Initialize mic seed */
-
-static void micinit(struct airo_info *ai)
-{
-	MICRid mic_rid;
-
-	clear_bit(JOB_MIC, &ai->jobs);
-	PC4500_readrid(ai, RID_MIC, &mic_rid, sizeof(mic_rid), 0);
-	up(&ai->sem);
-
-	ai->micstats.enabled = (le16_to_cpu(mic_rid.state) & 0x00FF) ? 1 : 0;
-	if (!ai->micstats.enabled) {
-		/* So next time we have a valid key and mic is enabled, we will
-		 * update the sequence number if the key is the same as before.
-		 */
-		ai->mod[0].uCtx.valid = 0;
-		ai->mod[0].mCtx.valid = 0;
-		return;
-	}
-
-	if (mic_rid.multicastValid) {
-		age_mic_context(&ai->mod[0].mCtx, &ai->mod[1].mCtx,
-		                mic_rid.multicast, sizeof(mic_rid.multicast),
-		                ai->tfm);
-	}
-
-	if (mic_rid.unicastValid) {
-		age_mic_context(&ai->mod[0].uCtx, &ai->mod[1].uCtx,
-				mic_rid.unicast, sizeof(mic_rid.unicast),
-				ai->tfm);
-	}
-}
-
-/* micsetup - Get ready for business */
-
-static int micsetup(struct airo_info *ai)
-{
-	int i;
-
-	if (ai->tfm == NULL)
-		ai->tfm = crypto_alloc_sync_skcipher("ctr(aes)", 0, 0);
-
-        if (IS_ERR(ai->tfm)) {
-                airo_print_err(ai->dev->name, "failed to load transform for AES");
-                ai->tfm = NULL;
-                return ERROR;
-        }
-
-	for (i = 0; i < NUM_MODULES; i++) {
-		memset(&ai->mod[i].mCtx, 0, sizeof(miccntx));
-		memset(&ai->mod[i].uCtx, 0, sizeof(miccntx));
-	}
-	return SUCCESS;
-}
-
-static const u8 micsnap[] = {0xAA, 0xAA, 0x03, 0x00, 0x40, 0x96, 0x00, 0x02};
-
-/*===========================================================================
- * Description: Mic a packet
- *
- *      Inputs: etherHead * pointer to an 802.3 frame
- *
- *     Returns: BOOLEAN if successful, otherwise false.
- *             PacketTxLen will be updated with the mic'd packets size.
- *
- *    Caveats: It is assumed that the frame buffer will already
- *             be big enough to hold the largets mic message possible.
- *            (No memory allocation is done here).
- *
- *    Author: sbraneky (10/15/01)
- *    Merciless hacks by rwilcher (1/14/02)
- */
-
-static int encapsulate(struct airo_info *ai, etherHead *frame, MICBuffer *mic, int payLen)
-{
-	miccntx   *context;
-
-	// Determine correct context
-	// If not adhoc, always use unicast key
-
-	if (test_bit(FLAG_ADHOC, &ai->flags) && (frame->da[0] & 0x1))
-		context = &ai->mod[0].mCtx;
-	else
-		context = &ai->mod[0].uCtx;
-
-	if (!context->valid)
-		return ERROR;
-
-	mic->typelen = htons(payLen + 16); //Length of Mic'd packet
-
-	memcpy(&mic->u.snap, micsnap, sizeof(micsnap)); // Add Snap
-
-	// Add Tx sequence
-	mic->seq = htonl(context->tx);
-	context->tx += 2;
-
-	emmh32_init(&context->seed); // Mic the packet
-	emmh32_update(&context->seed, frame->da, ETH_ALEN * 2); // DA, SA
-	emmh32_update(&context->seed, (u8*)&mic->typelen, 10); // Type/Length and Snap
-	emmh32_update(&context->seed, (u8*)&mic->seq, sizeof(mic->seq)); //SEQ
-	emmh32_update(&context->seed, (u8*)(frame + 1), payLen); //payload
-	emmh32_final(&context->seed, (u8*)&mic->mic);
-
-	/*    New Type/length ?????????? */
-	mic->typelen = 0; //Let NIC know it could be an oversized packet
-	return SUCCESS;
-}
-
-typedef enum {
-    NONE,
-    NOMIC,
-    NOMICPLUMMED,
-    SEQUENCE,
-    INCORRECTMIC,
-} mic_error;
-
-/*===========================================================================
- *  Description: Decapsulates a MIC'd packet and returns the 802.3 packet
- *               (removes the MIC stuff) if packet is a valid packet.
- *
- *       Inputs: etherHead  pointer to the 802.3 packet
- *
- *      Returns: BOOLEAN - TRUE if packet should be dropped otherwise FALSE
- *
- *      Author: sbraneky (10/15/01)
- *    Merciless hacks by rwilcher (1/14/02)
- *---------------------------------------------------------------------------
- */
-
-static int decapsulate(struct airo_info *ai, MICBuffer *mic, etherHead *eth, u16 payLen)
-{
-	int      i;
-	u32      micSEQ;
-	miccntx  *context;
-	u8       digest[4];
-	mic_error micError = NONE;
-
-	// Check if the packet is a Mic'd packet
-
-	if (!ai->micstats.enabled) {
-		//No Mic set or Mic OFF but we received a MIC'd packet.
-		if (memcmp ((u8*)eth + 14, micsnap, sizeof(micsnap)) == 0) {
-			ai->micstats.rxMICPlummed++;
-			return ERROR;
-		}
-		return SUCCESS;
-	}
-
-	if (ntohs(mic->typelen) == 0x888E)
-		return SUCCESS;
-
-	if (memcmp (mic->u.snap, micsnap, sizeof(micsnap)) != 0) {
-	    // Mic enabled but packet isn't Mic'd
-		ai->micstats.rxMICPlummed++;
-	    	return ERROR;
-	}
-
-	micSEQ = ntohl(mic->seq);            //store SEQ as CPU order
-
-	//At this point we a have a mic'd packet and mic is enabled
-	//Now do the mic error checking.
-
-	//Receive seq must be odd
-	if ((micSEQ & 1) == 0) {
-		ai->micstats.rxWrongSequence++;
-		return ERROR;
-	}
-
-	for (i = 0; i < NUM_MODULES; i++) {
-		int mcast = eth->da[0] & 1;
-		//Determine proper context
-		context = mcast ? &ai->mod[i].mCtx : &ai->mod[i].uCtx;
-
-		//Make sure context is valid
-		if (!context->valid) {
-			if (i == 0)
-				micError = NOMICPLUMMED;
-			continue;
-		}
-		//DeMic it
-
-		if (!mic->typelen)
-			mic->typelen = htons(payLen + sizeof(MICBuffer) - 2);
-
-		emmh32_init(&context->seed);
-		emmh32_update(&context->seed, eth->da, ETH_ALEN*2);
-		emmh32_update(&context->seed, (u8 *)&mic->typelen, sizeof(mic->typelen)+sizeof(mic->u.snap));
-		emmh32_update(&context->seed, (u8 *)&mic->seq, sizeof(mic->seq));
-		emmh32_update(&context->seed, (u8 *)(eth + 1), payLen);
-		//Calculate MIC
-		emmh32_final(&context->seed, digest);
-
-		if (memcmp(digest, &mic->mic, 4)) { //Make sure the mics match
-		  //Invalid Mic
-			if (i == 0)
-				micError = INCORRECTMIC;
-			continue;
-		}
-
-		//Check Sequence number if mics pass
-		if (RxSeqValid(ai, context, mcast, micSEQ) == SUCCESS) {
-			ai->micstats.rxSuccess++;
-			return SUCCESS;
-		}
-		if (i == 0)
-			micError = SEQUENCE;
-	}
-
-	// Update statistics
-	switch (micError) {
-		case NOMICPLUMMED: ai->micstats.rxMICPlummed++;   break;
-		case SEQUENCE:    ai->micstats.rxWrongSequence++; break;
-		case INCORRECTMIC: ai->micstats.rxIncorrectMIC++; break;
-		case NONE:  break;
-		case NOMIC: break;
-	}
-	return ERROR;
-}
-
-/*===========================================================================
- * Description:  Checks the Rx Seq number to make sure it is valid
- *               and hasn't already been received
- *
- *     Inputs: miccntx - mic context to check seq against
- *             micSeq  - the Mic seq number
- *
- *    Returns: TRUE if valid otherwise FALSE.
- *
- *    Author: sbraneky (10/15/01)
- *    Merciless hacks by rwilcher (1/14/02)
- *---------------------------------------------------------------------------
- */
-
-static int RxSeqValid(struct airo_info *ai, miccntx *context, int mcast, u32 micSeq)
-{
-	u32 seq, index;
-
-	//Allow for the ap being rebooted - if it is then use the next
-	//sequence number of the current sequence number - might go backwards
-
-	if (mcast) {
-		if (test_bit(FLAG_UPDATE_MULTI, &ai->flags)) {
-			clear_bit (FLAG_UPDATE_MULTI, &ai->flags);
-			context->window = (micSeq > 33) ? micSeq : 33;
-			context->rx     = 0;        // Reset rx
-		}
-	} else if (test_bit(FLAG_UPDATE_UNI, &ai->flags)) {
-		clear_bit (FLAG_UPDATE_UNI, &ai->flags);
-		context->window = (micSeq > 33) ? micSeq : 33; // Move window
-		context->rx     = 0;        // Reset rx
-	}
-
-	//Make sequence number relative to START of window
-	seq = micSeq - (context->window - 33);
-
-	//Too old of a SEQ number to check.
-	if ((s32)seq < 0)
-		return ERROR;
-
-	if (seq > 64) {
-		//Window is infinite forward
-		MoveWindow(context, micSeq);
-		return SUCCESS;
-	}
-
-	// We are in the window. Now check the context rx bit to see if it was already sent
-	seq >>= 1;         //divide by 2 because we only have odd numbers
-	index = 1 << seq;  //Get an index number
-
-	if (!(context->rx & index)) {
-		//micSEQ falls inside the window.
-		//Add seqence number to the list of received numbers.
-		context->rx |= index;
-
-		MoveWindow(context, micSeq);
-
-		return SUCCESS;
-	}
-	return ERROR;
-}
-
-static void MoveWindow(miccntx *context, u32 micSeq)
-{
-	u32 shift;
-
-	//Move window if seq greater than the middle of the window
-	if (micSeq > context->window) {
-		shift = (micSeq - context->window) >> 1;
-
-		    //Shift out old
-		if (shift < 32)
-			context->rx >>= shift;
-		else
-			context->rx = 0;
-
-		context->window = micSeq;      //Move window
-	}
-}
-
-/*==============================================*/
-/*========== EMMH ROUTINES  ====================*/
-/*==============================================*/
-
-/* mic accumulate */
-#define MIC_ACCUM(val)	\
-	context->accum += (u64)(val) * be32_to_cpu(context->coeff[coeff_position++]);
-
-/* expand the key to fill the MMH coefficient array */
-static void emmh32_setseed(emmh32_context *context, u8 *pkey, int keylen,
-			   struct crypto_sync_skcipher *tfm)
-{
-  /* take the keying material, expand if necessary, truncate at 16-bytes */
-  /* run through AES counter mode to generate context->coeff[] */
-
-	SYNC_SKCIPHER_REQUEST_ON_STACK(req, tfm);
-	struct scatterlist sg;
-	u8 iv[AES_BLOCK_SIZE] = {};
-	int ret;
-
-	crypto_sync_skcipher_setkey(tfm, pkey, 16);
-
-	memset(context->coeff, 0, sizeof(context->coeff));
-	sg_init_one(&sg, context->coeff, sizeof(context->coeff));
-
-	skcipher_request_set_sync_tfm(req, tfm);
-	skcipher_request_set_callback(req, 0, NULL, NULL);
-	skcipher_request_set_crypt(req, &sg, &sg, sizeof(context->coeff), iv);
-
-	ret = crypto_skcipher_encrypt(req);
-	WARN_ON_ONCE(ret);
-}
-
-/* prepare for calculation of a new mic */
-static void emmh32_init(emmh32_context *context)
-{
-	/* prepare for new mic calculation */
-	context->accum = 0;
-	context->position = 0;
-}
-
-/* add some bytes to the mic calculation */
-static void emmh32_update(emmh32_context *context, u8 *pOctets, int len)
-{
-	int	coeff_position, byte_position;
-
-	if (len == 0) return;
-
-	coeff_position = context->position >> 2;
-
-	/* deal with partial 32-bit word left over from last update */
-	byte_position = context->position & 3;
-	if (byte_position) {
-		/* have a partial word in part to deal with */
-		do {
-			if (len == 0) return;
-			context->part.d8[byte_position++] = *pOctets++;
-			context->position++;
-			len--;
-		} while (byte_position < 4);
-		MIC_ACCUM(ntohl(context->part.d32));
-	}
-
-	/* deal with full 32-bit words */
-	while (len >= 4) {
-		MIC_ACCUM(ntohl(*(__be32 *)pOctets));
-		context->position += 4;
-		pOctets += 4;
-		len -= 4;
-	}
-
-	/* deal with partial 32-bit word that will be left over from this update */
-	byte_position = 0;
-	while (len > 0) {
-		context->part.d8[byte_position++] = *pOctets++;
-		context->position++;
-		len--;
-	}
-}
-
-/* mask used to zero empty bytes for final partial word */
-static u32 mask32[4] = { 0x00000000L, 0xFF000000L, 0xFFFF0000L, 0xFFFFFF00L };
-
-/* calculate the mic */
-static void emmh32_final(emmh32_context *context, u8 digest[4])
-{
-	int	coeff_position, byte_position;
-	u32	val;
-
-	u64 sum, utmp;
-	s64 stmp;
-
-	coeff_position = context->position >> 2;
-
-	/* deal with partial 32-bit word left over from last update */
-	byte_position = context->position & 3;
-	if (byte_position) {
-		/* have a partial word in part to deal with */
-		val = ntohl(context->part.d32);
-		MIC_ACCUM(val & mask32[byte_position]);	/* zero empty bytes */
-	}
-
-	/* reduce the accumulated u64 to a 32-bit MIC */
-	sum = context->accum;
-	stmp = (sum  & 0xffffffffLL) - ((sum >> 32)  * 15);
-	utmp = (stmp & 0xffffffffLL) - ((stmp >> 32) * 15);
-	sum = utmp & 0xffffffffLL;
-	if (utmp > 0x10000000fLL)
-		sum -= 15;
-
-	val = (u32)sum;
-	digest[0] = (val>>24) & 0xFF;
-	digest[1] = (val>>16) & 0xFF;
-	digest[2] = (val>>8) & 0xFF;
-	digest[3] = val & 0xFF;
-}
-
-static int readBSSListRid(struct airo_info *ai, int first,
-		      BSSListRid *list)
-{
-	Cmd cmd;
-	Resp rsp;
-
-	if (first == 1) {
-		if (ai->flags & FLAG_RADIO_MASK) return -ENETDOWN;
-		memset(&cmd, 0, sizeof(cmd));
-		cmd.cmd = CMD_LISTBSS;
-		if (down_interruptible(&ai->sem))
-			return -ERESTARTSYS;
-		ai->list_bss_task = current;
-		issuecommand(ai, &cmd, &rsp, true);
-		up(&ai->sem);
-		/* Let the command take effect */
-		schedule_timeout_uninterruptible(3 * HZ);
-		ai->list_bss_task = NULL;
-	}
-	return PC4500_readrid(ai, first ? ai->bssListFirst : ai->bssListNext,
-			    list, ai->bssListRidLen, 1);
-}
-
-static int readWepKeyRid(struct airo_info *ai, WepKeyRid *wkr, int temp, int lock)
-{
-	return PC4500_readrid(ai, temp ? RID_WEP_TEMP : RID_WEP_PERM,
-				wkr, sizeof(*wkr), lock);
-}
-
-static int writeWepKeyRid(struct airo_info *ai, WepKeyRid *wkr, int perm, int lock)
-{
-	int rc;
-	rc = PC4500_writerid(ai, RID_WEP_TEMP, wkr, sizeof(*wkr), lock);
-	if (rc!=SUCCESS)
-		airo_print_err(ai->dev->name, "WEP_TEMP set %x", rc);
-	if (perm) {
-		rc = PC4500_writerid(ai, RID_WEP_PERM, wkr, sizeof(*wkr), lock);
-		if (rc!=SUCCESS)
-			airo_print_err(ai->dev->name, "WEP_PERM set %x", rc);
-	}
-	return rc;
-}
-
-static int readSsidRid(struct airo_info*ai, SsidRid *ssidr)
-{
-	return PC4500_readrid(ai, RID_SSID, ssidr, sizeof(*ssidr), 1);
-}
-
-static int writeSsidRid(struct airo_info*ai, SsidRid *pssidr, int lock)
-{
-	return PC4500_writerid(ai, RID_SSID, pssidr, sizeof(*pssidr), lock);
-}
-
-static int readConfigRid(struct airo_info *ai, int lock)
-{
-	int rc;
-	ConfigRid cfg;
-
-	if (ai->config.len)
-		return SUCCESS;
-
-	rc = PC4500_readrid(ai, RID_ACTUALCONFIG, &cfg, sizeof(cfg), lock);
-	if (rc != SUCCESS)
-		return rc;
-
-	ai->config = cfg;
-	return SUCCESS;
-}
-
-static inline void checkThrottle(struct airo_info *ai)
-{
-	int i;
-/* Old hardware had a limit on encryption speed */
-	if (ai->config.authType != AUTH_OPEN && maxencrypt) {
-		for (i = 0; i<8; i++) {
-			if (ai->config.rates[i] > maxencrypt) {
-				ai->config.rates[i] = 0;
-			}
-		}
-	}
-}
-
-static int writeConfigRid(struct airo_info *ai, int lock)
-{
-	ConfigRid cfgr;
-
-	if (!test_bit (FLAG_COMMIT, &ai->flags))
-		return SUCCESS;
-
-	clear_bit (FLAG_COMMIT, &ai->flags);
-	clear_bit (FLAG_RESET, &ai->flags);
-	checkThrottle(ai);
-	cfgr = ai->config;
-
-	if ((cfgr.opmode & MODE_CFG_MASK) == MODE_STA_IBSS)
-		set_bit(FLAG_ADHOC, &ai->flags);
-	else
-		clear_bit(FLAG_ADHOC, &ai->flags);
-
-	return PC4500_writerid(ai, RID_CONFIG, &cfgr, sizeof(cfgr), lock);
-}
-
-static int readStatusRid(struct airo_info *ai, StatusRid *statr, int lock)
-{
-	return PC4500_readrid(ai, RID_STATUS, statr, sizeof(*statr), lock);
-}
-
-static int writeAPListRid(struct airo_info *ai, APListRid *aplr, int lock)
-{
-	return PC4500_writerid(ai, RID_APLIST, aplr, sizeof(*aplr), lock);
-}
-
-static int readCapabilityRid(struct airo_info *ai, CapabilityRid *capr, int lock)
-{
-	return PC4500_readrid(ai, RID_CAPABILITIES, capr, sizeof(*capr), lock);
-}
-
-static int readStatsRid(struct airo_info*ai, StatsRid *sr, int rid, int lock)
-{
-	return PC4500_readrid(ai, rid, sr, sizeof(*sr), lock);
-}
-
-static void try_auto_wep(struct airo_info *ai)
-{
-	if (auto_wep && !test_bit(FLAG_RADIO_DOWN, &ai->flags)) {
-		ai->expires = RUN_AT(3*HZ);
-		wake_up_interruptible(&ai->thr_wait);
-	}
-}
-
-static int airo_open(struct net_device *dev)
-{
-	struct airo_info *ai = dev->ml_priv;
-	int rc = 0;
-
-	if (test_bit(FLAG_FLASHING, &ai->flags))
-		return -EIO;
-
-	/* Make sure the card is configured.
-	 * Wireless Extensions may postpone config changes until the card
-	 * is open (to pipeline changes and speed-up card setup). If
-	 * those changes are not yet committed, do it now - Jean II */
-	if (test_bit(FLAG_COMMIT, &ai->flags)) {
-		disable_MAC(ai, 1);
-		writeConfigRid(ai, 1);
-	}
-
-	if (ai->wifidev != dev) {
-		clear_bit(JOB_DIE, &ai->jobs);
-		ai->airo_thread_task = kthread_run(airo_thread, dev, "%s",
-						   dev->name);
-		if (IS_ERR(ai->airo_thread_task))
-			return (int)PTR_ERR(ai->airo_thread_task);
-
-		rc = request_irq(dev->irq, airo_interrupt, IRQF_SHARED,
-			dev->name, dev);
-		if (rc) {
-			airo_print_err(dev->name,
-				"register interrupt %d failed, rc %d",
-				dev->irq, rc);
-			set_bit(JOB_DIE, &ai->jobs);
-			kthread_stop(ai->airo_thread_task);
-			return rc;
-		}
-
-		/* Power on the MAC controller (which may have been disabled) */
-		clear_bit(FLAG_RADIO_DOWN, &ai->flags);
-		enable_interrupts(ai);
-
-		try_auto_wep(ai);
-	}
-	enable_MAC(ai, 1);
-
-	netif_start_queue(dev);
-	return 0;
-}
-
-static netdev_tx_t mpi_start_xmit(struct sk_buff *skb,
-					struct net_device *dev)
-{
-	int npacks, pending;
-	unsigned long flags;
-	struct airo_info *ai = dev->ml_priv;
-
-	if (!skb) {
-		airo_print_err(dev->name, "%s: skb == NULL!",__func__);
-		return NETDEV_TX_OK;
-	}
-	if (skb_padto(skb, ETH_ZLEN)) {
-		dev->stats.tx_dropped++;
-		return NETDEV_TX_OK;
-	}
-	npacks = skb_queue_len (&ai->txq);
-
-	if (npacks >= MAXTXQ - 1) {
-		netif_stop_queue (dev);
-		if (npacks > MAXTXQ) {
-			dev->stats.tx_fifo_errors++;
-			return NETDEV_TX_BUSY;
-		}
-		skb_queue_tail (&ai->txq, skb);
-		return NETDEV_TX_OK;
-	}
-
-	spin_lock_irqsave(&ai->aux_lock, flags);
-	skb_queue_tail (&ai->txq, skb);
-	pending = test_bit(FLAG_PENDING_XMIT, &ai->flags);
-	spin_unlock_irqrestore(&ai->aux_lock, flags);
-	netif_wake_queue (dev);
-
-	if (pending == 0) {
-		set_bit(FLAG_PENDING_XMIT, &ai->flags);
-		mpi_send_packet (dev);
-	}
-	return NETDEV_TX_OK;
-}
-
-/*
- * @mpi_send_packet
- *
- * Attempt to transmit a packet. Can be called from interrupt
- * or transmit . return number of packets we tried to send
- */
-
-static int mpi_send_packet (struct net_device *dev)
-{
-	struct sk_buff *skb;
-	unsigned char *buffer;
-	s16 len;
-	__le16 *payloadLen;
-	struct airo_info *ai = dev->ml_priv;
-	u8 *sendbuf;
-
-	/* get a packet to send */
-
-	if ((skb = skb_dequeue(&ai->txq)) == NULL) {
-		airo_print_err(dev->name,
-			"%s: Dequeue'd zero in send_packet()",
-			__func__);
-		return 0;
-	}
-
-	/* check min length*/
-	len = ETH_ZLEN < skb->len ? skb->len : ETH_ZLEN;
-	buffer = skb->data;
-
-	ai->txfids[0].tx_desc.offset = 0;
-	ai->txfids[0].tx_desc.valid = 1;
-	ai->txfids[0].tx_desc.eoc = 1;
-	ai->txfids[0].tx_desc.len =len+sizeof(WifiHdr);
-
-/*
- * Magic, the cards firmware needs a length count (2 bytes) in the host buffer
- * right after  TXFID_HDR.The TXFID_HDR contains the status short so payloadlen
- * is immediately after it. ------------------------------------------------
- *                         |TXFIDHDR+STATUS|PAYLOADLEN|802.3HDR|PACKETDATA|
- *                         ------------------------------------------------
- */
-
-	memcpy(ai->txfids[0].virtual_host_addr,
-		(char *)&wifictlhdr8023, sizeof(wifictlhdr8023));
-
-	payloadLen = (__le16 *)(ai->txfids[0].virtual_host_addr +
-		sizeof(wifictlhdr8023));
-	sendbuf = ai->txfids[0].virtual_host_addr +
-		sizeof(wifictlhdr8023) + 2 ;
-
-	/*
-	 * Firmware automatically puts 802 header on so
-	 * we don't need to account for it in the length
-	 */
-	if (test_bit(FLAG_MIC_CAPABLE, &ai->flags) && ai->micstats.enabled &&
-		(ntohs(((__be16 *)buffer)[6]) != 0x888E)) {
-		MICBuffer pMic;
-
-		if (encapsulate(ai, (etherHead *)buffer, &pMic, len - sizeof(etherHead)) != SUCCESS)
-			return ERROR;
-
-		*payloadLen = cpu_to_le16(len-sizeof(etherHead)+sizeof(pMic));
-		ai->txfids[0].tx_desc.len += sizeof(pMic);
-		/* copy data into airo dma buffer */
-		memcpy (sendbuf, buffer, sizeof(etherHead));
-		buffer += sizeof(etherHead);
-		sendbuf += sizeof(etherHead);
-		memcpy (sendbuf, &pMic, sizeof(pMic));
-		sendbuf += sizeof(pMic);
-		memcpy (sendbuf, buffer, len - sizeof(etherHead));
-	} else {
-		*payloadLen = cpu_to_le16(len - sizeof(etherHead));
-
-		netif_trans_update(dev);
-
-		/* copy data into airo dma buffer */
-		memcpy(sendbuf, buffer, len);
-	}
-
-	memcpy_toio(ai->txfids[0].card_ram_off,
-		&ai->txfids[0].tx_desc, sizeof(TxFid));
-
-	OUT4500(ai, EVACK, 8);
-
-	dev_kfree_skb_any(skb);
-	return 1;
-}
-
-static void get_tx_error(struct airo_info *ai, s32 fid)
-{
-	__le16 status;
-
-	if (fid < 0)
-		status = ((WifiCtlHdr *)ai->txfids[0].virtual_host_addr)->ctlhdr.status;
-	else {
-		if (bap_setup(ai, ai->fids[fid] & 0xffff, 4, BAP0) != SUCCESS)
-			return;
-		bap_read(ai, &status, 2, BAP0);
-	}
-	if (le16_to_cpu(status) & 2) /* Too many retries */
-		ai->dev->stats.tx_aborted_errors++;
-	if (le16_to_cpu(status) & 4) /* Transmit lifetime exceeded */
-		ai->dev->stats.tx_heartbeat_errors++;
-	if (le16_to_cpu(status) & 8) /* Aid fail */
-		{ }
-	if (le16_to_cpu(status) & 0x10) /* MAC disabled */
-		ai->dev->stats.tx_carrier_errors++;
-	if (le16_to_cpu(status) & 0x20) /* Association lost */
-		{ }
-	/* We produce a TXDROP event only for retry or lifetime
-	 * exceeded, because that's the only status that really mean
-	 * that this particular node went away.
-	 * Other errors means that *we* screwed up. - Jean II */
-	if ((le16_to_cpu(status) & 2) ||
-	     (le16_to_cpu(status) & 4)) {
-		union iwreq_data	wrqu;
-		char junk[0x18];
-
-		/* Faster to skip over useless data than to do
-		 * another bap_setup(). We are at offset 0x6 and
-		 * need to go to 0x18 and read 6 bytes - Jean II */
-		bap_read(ai, (__le16 *) junk, 0x18, BAP0);
-
-		/* Copy 802.11 dest address.
-		 * We use the 802.11 header because the frame may
-		 * not be 802.3 or may be mangled...
-		 * In Ad-Hoc mode, it will be the node address.
-		 * In managed mode, it will be most likely the AP addr
-		 * User space will figure out how to convert it to
-		 * whatever it needs (IP address or else).
-		 * - Jean II */
-		memcpy(wrqu.addr.sa_data, junk + 0x12, ETH_ALEN);
-		wrqu.addr.sa_family = ARPHRD_ETHER;
-
-		/* Send event to user space */
-		wireless_send_event(ai->dev, IWEVTXDROP, &wrqu, NULL);
-	}
-}
-
-static void airo_end_xmit(struct net_device *dev, bool may_sleep)
-{
-	u16 status;
-	int i;
-	struct airo_info *priv = dev->ml_priv;
-	struct sk_buff *skb = priv->xmit.skb;
-	int fid = priv->xmit.fid;
-	u32 *fids = priv->fids;
-
-	clear_bit(JOB_XMIT, &priv->jobs);
-	clear_bit(FLAG_PENDING_XMIT, &priv->flags);
-	status = transmit_802_3_packet(priv, fids[fid], skb->data, may_sleep);
-	up(&priv->sem);
-
-	i = 0;
-	if (status == SUCCESS) {
-		netif_trans_update(dev);
-		for (; i < MAX_FIDS / 2 && (priv->fids[i] & 0xffff0000); i++);
-	} else {
-		priv->fids[fid] &= 0xffff;
-		dev->stats.tx_window_errors++;
-	}
-	if (i < MAX_FIDS / 2)
-		netif_wake_queue(dev);
-	dev_kfree_skb(skb);
-}
-
-static netdev_tx_t airo_start_xmit(struct sk_buff *skb,
-					 struct net_device *dev)
-{
-	s16 len;
-	int i, j;
-	struct airo_info *priv = dev->ml_priv;
-	u32 *fids = priv->fids;
-
-	if (skb == NULL) {
-		airo_print_err(dev->name, "%s: skb == NULL!", __func__);
-		return NETDEV_TX_OK;
-	}
-	if (skb_padto(skb, ETH_ZLEN)) {
-		dev->stats.tx_dropped++;
-		return NETDEV_TX_OK;
-	}
-
-	/* Find a vacant FID */
-	for (i = 0; i < MAX_FIDS / 2 && (fids[i] & 0xffff0000); i++);
-	for (j = i + 1; j < MAX_FIDS / 2 && (fids[j] & 0xffff0000); j++);
-
-	if (j >= MAX_FIDS / 2) {
-		netif_stop_queue(dev);
-
-		if (i == MAX_FIDS / 2) {
-			dev->stats.tx_fifo_errors++;
-			return NETDEV_TX_BUSY;
-		}
-	}
-	/* check min length*/
-	len = ETH_ZLEN < skb->len ? skb->len : ETH_ZLEN;
-        /* Mark fid as used & save length for later */
-	fids[i] |= (len << 16);
-	priv->xmit.skb = skb;
-	priv->xmit.fid = i;
-	if (down_trylock(&priv->sem) != 0) {
-		set_bit(FLAG_PENDING_XMIT, &priv->flags);
-		netif_stop_queue(dev);
-		set_bit(JOB_XMIT, &priv->jobs);
-		wake_up_interruptible(&priv->thr_wait);
-	} else
-		airo_end_xmit(dev, false);
-	return NETDEV_TX_OK;
-}
-
-static void airo_end_xmit11(struct net_device *dev, bool may_sleep)
-{
-	u16 status;
-	int i;
-	struct airo_info *priv = dev->ml_priv;
-	struct sk_buff *skb = priv->xmit11.skb;
-	int fid = priv->xmit11.fid;
-	u32 *fids = priv->fids;
-
-	clear_bit(JOB_XMIT11, &priv->jobs);
-	clear_bit(FLAG_PENDING_XMIT11, &priv->flags);
-	status = transmit_802_11_packet(priv, fids[fid], skb->data, may_sleep);
-	up(&priv->sem);
-
-	i = MAX_FIDS / 2;
-	if (status == SUCCESS) {
-		netif_trans_update(dev);
-		for (; i < MAX_FIDS && (priv->fids[i] & 0xffff0000); i++);
-	} else {
-		priv->fids[fid] &= 0xffff;
-		dev->stats.tx_window_errors++;
-	}
-	if (i < MAX_FIDS)
-		netif_wake_queue(dev);
-	dev_kfree_skb(skb);
-}
-
-static netdev_tx_t airo_start_xmit11(struct sk_buff *skb,
-					   struct net_device *dev)
-{
-	s16 len;
-	int i, j;
-	struct airo_info *priv = dev->ml_priv;
-	u32 *fids = priv->fids;
-
-	if (test_bit(FLAG_MPI, &priv->flags)) {
-		/* Not implemented yet for MPI350 */
-		netif_stop_queue(dev);
-		dev_kfree_skb_any(skb);
-		return NETDEV_TX_OK;
-	}
-
-	if (skb == NULL) {
-		airo_print_err(dev->name, "%s: skb == NULL!", __func__);
-		return NETDEV_TX_OK;
-	}
-	if (skb_padto(skb, ETH_ZLEN)) {
-		dev->stats.tx_dropped++;
-		return NETDEV_TX_OK;
-	}
-
-	/* Find a vacant FID */
-	for (i = MAX_FIDS / 2; i < MAX_FIDS && (fids[i] & 0xffff0000); i++);
-	for (j = i + 1; j < MAX_FIDS && (fids[j] & 0xffff0000); j++);
-
-	if (j >= MAX_FIDS) {
-		netif_stop_queue(dev);
-
-		if (i == MAX_FIDS) {
-			dev->stats.tx_fifo_errors++;
-			return NETDEV_TX_BUSY;
-		}
-	}
-	/* check min length*/
-	len = ETH_ZLEN < skb->len ? skb->len : ETH_ZLEN;
-        /* Mark fid as used & save length for later */
-	fids[i] |= (len << 16);
-	priv->xmit11.skb = skb;
-	priv->xmit11.fid = i;
-	if (down_trylock(&priv->sem) != 0) {
-		set_bit(FLAG_PENDING_XMIT11, &priv->flags);
-		netif_stop_queue(dev);
-		set_bit(JOB_XMIT11, &priv->jobs);
-		wake_up_interruptible(&priv->thr_wait);
-	} else
-		airo_end_xmit11(dev, false);
-	return NETDEV_TX_OK;
-}
-
-static void airo_read_stats(struct net_device *dev)
-{
-	struct airo_info *ai = dev->ml_priv;
-	StatsRid stats_rid;
-	__le32 *vals = stats_rid.vals;
-
-	clear_bit(JOB_STATS, &ai->jobs);
-	if (ai->power.event) {
-		up(&ai->sem);
-		return;
-	}
-	readStatsRid(ai, &stats_rid, RID_STATS, 0);
-	up(&ai->sem);
-
-	dev->stats.rx_packets = le32_to_cpu(vals[43]) + le32_to_cpu(vals[44]) +
-			       le32_to_cpu(vals[45]);
-	dev->stats.tx_packets = le32_to_cpu(vals[39]) + le32_to_cpu(vals[40]) +
-			       le32_to_cpu(vals[41]);
-	dev->stats.rx_bytes = le32_to_cpu(vals[92]);
-	dev->stats.tx_bytes = le32_to_cpu(vals[91]);
-	dev->stats.rx_errors = le32_to_cpu(vals[0]) + le32_to_cpu(vals[2]) +
-			      le32_to_cpu(vals[3]) + le32_to_cpu(vals[4]);
-	dev->stats.tx_errors = le32_to_cpu(vals[42]) +
-			      dev->stats.tx_fifo_errors;
-	dev->stats.multicast = le32_to_cpu(vals[43]);
-	dev->stats.collisions = le32_to_cpu(vals[89]);
-
-	/* detailed rx_errors: */
-	dev->stats.rx_length_errors = le32_to_cpu(vals[3]);
-	dev->stats.rx_crc_errors = le32_to_cpu(vals[4]);
-	dev->stats.rx_frame_errors = le32_to_cpu(vals[2]);
-	dev->stats.rx_fifo_errors = le32_to_cpu(vals[0]);
-}
-
-static struct net_device_stats *airo_get_stats(struct net_device *dev)
-{
-	struct airo_info *local =  dev->ml_priv;
-
-	if (!test_bit(JOB_STATS, &local->jobs)) {
-		set_bit(JOB_STATS, &local->jobs);
-		wake_up_interruptible(&local->thr_wait);
-	}
-
-	return &dev->stats;
-}
-
-static void airo_set_promisc(struct airo_info *ai, bool may_sleep)
-{
-	Cmd cmd;
-	Resp rsp;
-
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.cmd = CMD_SETMODE;
-	clear_bit(JOB_PROMISC, &ai->jobs);
-	cmd.parm0=(ai->flags&IFF_PROMISC) ? PROMISC : NOPROMISC;
-	issuecommand(ai, &cmd, &rsp, may_sleep);
-	up(&ai->sem);
-}
-
-static void airo_set_multicast_list(struct net_device *dev)
-{
-	struct airo_info *ai = dev->ml_priv;
-
-	if ((dev->flags ^ ai->flags) & IFF_PROMISC) {
-		change_bit(FLAG_PROMISC, &ai->flags);
-		if (down_trylock(&ai->sem) != 0) {
-			set_bit(JOB_PROMISC, &ai->jobs);
-			wake_up_interruptible(&ai->thr_wait);
-		} else
-			airo_set_promisc(ai, false);
-	}
-
-	if ((dev->flags&IFF_ALLMULTI) || !netdev_mc_empty(dev)) {
-		/* Turn on multicast.  (Should be already setup...) */
-	}
-}
-
-static int airo_set_mac_address(struct net_device *dev, void *p)
-{
-	struct airo_info *ai = dev->ml_priv;
-	struct sockaddr *addr = p;
-
-	readConfigRid(ai, 1);
-	memcpy (ai->config.macAddr, addr->sa_data, dev->addr_len);
-	set_bit (FLAG_COMMIT, &ai->flags);
-	disable_MAC(ai, 1);
-	writeConfigRid (ai, 1);
-	enable_MAC(ai, 1);
-	dev_addr_set(ai->dev, addr->sa_data);
-	if (ai->wifidev)
-		dev_addr_set(ai->wifidev, addr->sa_data);
-	return 0;
-}
-
-static LIST_HEAD(airo_devices);
-
-static void add_airo_dev(struct airo_info *ai)
-{
-	/* Upper layers already keep track of PCI devices,
-	 * so we only need to remember our non-PCI cards. */
-	if (!ai->pci)
-		list_add_tail(&ai->dev_list, &airo_devices);
-}
-
-static void del_airo_dev(struct airo_info *ai)
-{
-	if (!ai->pci)
-		list_del(&ai->dev_list);
-}
-
-static int airo_close(struct net_device *dev)
-{
-	struct airo_info *ai = dev->ml_priv;
-
-	netif_stop_queue(dev);
-
-	if (ai->wifidev != dev) {
-#ifdef POWER_ON_DOWN
-		/* Shut power to the card. The idea is that the user can save
-		 * power when he doesn't need the card with "ifconfig down".
-		 * That's the method that is most friendly towards the network
-		 * stack (i.e. the network stack won't try to broadcast
-		 * anything on the interface and routes are gone. Jean II */
-		set_bit(FLAG_RADIO_DOWN, &ai->flags);
-		disable_MAC(ai, 1);
-#endif
-		disable_interrupts(ai);
-
-		free_irq(dev->irq, dev);
-
-		set_bit(JOB_DIE, &ai->jobs);
-		kthread_stop(ai->airo_thread_task);
-	}
-	return 0;
-}
-
-void stop_airo_card(struct net_device *dev, int freeres)
-{
-	struct airo_info *ai = dev->ml_priv;
-
-	set_bit(FLAG_RADIO_DOWN, &ai->flags);
-	disable_MAC(ai, 1);
-	disable_interrupts(ai);
-	takedown_proc_entry(dev, ai);
-	if (test_bit(FLAG_REGISTERED, &ai->flags)) {
-		unregister_netdev(dev);
-		if (ai->wifidev) {
-			unregister_netdev(ai->wifidev);
-			free_netdev(ai->wifidev);
-			ai->wifidev = NULL;
-		}
-		clear_bit(FLAG_REGISTERED, &ai->flags);
-	}
-	/*
-	 * Clean out tx queue
-	 */
-	if (test_bit(FLAG_MPI, &ai->flags) && !skb_queue_empty(&ai->txq)) {
-		struct sk_buff *skb = NULL;
-		for (;(skb = skb_dequeue(&ai->txq));)
-			dev_kfree_skb(skb);
-	}
-
-	airo_networks_free (ai);
-
-	kfree(ai->flash);
-	kfree(ai->rssi);
-	kfree(ai->SSID);
-	if (freeres) {
-		/* PCMCIA frees this stuff, so only for PCI and ISA */
-		release_region(dev->base_addr, 64);
-		if (test_bit(FLAG_MPI, &ai->flags)) {
-			if (ai->pci)
-				mpi_unmap_card(ai->pci);
-			if (ai->pcimem)
-				iounmap(ai->pcimem);
-			if (ai->pciaux)
-				iounmap(ai->pciaux);
-			dma_free_coherent(&ai->pci->dev, PCI_SHARED_LEN,
-					  ai->shared, ai->shared_dma);
-		}
-        }
-	crypto_free_sync_skcipher(ai->tfm);
-	del_airo_dev(ai);
-	free_netdev(dev);
-}
-
-EXPORT_SYMBOL(stop_airo_card);
-
-static int wll_header_parse(const struct sk_buff *skb, unsigned char *haddr)
-{
-	memcpy(haddr, skb_mac_header(skb) + 10, ETH_ALEN);
-	return ETH_ALEN;
-}
-
-static void mpi_unmap_card(struct pci_dev *pci)
-{
-	unsigned long mem_start = pci_resource_start(pci, 1);
-	unsigned long mem_len = pci_resource_len(pci, 1);
-	unsigned long aux_start = pci_resource_start(pci, 2);
-	unsigned long aux_len = AUXMEMSIZE;
-
-	release_mem_region(aux_start, aux_len);
-	release_mem_region(mem_start, mem_len);
-}
-
-/*************************************************************
- *  This routine assumes that descriptors have been setup .
- *  Run at insmod time or after reset when the descriptors
- *  have been initialized . Returns 0 if all is well nz
- *  otherwise . Does not allocate memory but sets up card
- *  using previously allocated descriptors.
- */
-static int mpi_init_descriptors (struct airo_info *ai)
-{
-	Cmd cmd;
-	Resp rsp;
-	int i;
-	int rc = SUCCESS;
-
-	/* Alloc  card RX descriptors */
-	netif_stop_queue(ai->dev);
-
-	memset(&rsp, 0, sizeof(rsp));
-	memset(&cmd, 0, sizeof(cmd));
-
-	cmd.cmd = CMD_ALLOCATEAUX;
-	cmd.parm0 = FID_RX;
-	cmd.parm1 = (ai->rxfids[0].card_ram_off - ai->pciaux);
-	cmd.parm2 = MPI_MAX_FIDS;
-	rc = issuecommand(ai, &cmd, &rsp, true);
-	if (rc != SUCCESS) {
-		airo_print_err(ai->dev->name, "Couldn't allocate RX FID");
-		return rc;
-	}
-
-	for (i = 0; i<MPI_MAX_FIDS; i++) {
-		memcpy_toio(ai->rxfids[i].card_ram_off,
-			&ai->rxfids[i].rx_desc, sizeof(RxFid));
-	}
-
-	/* Alloc card TX descriptors */
-
-	memset(&rsp, 0, sizeof(rsp));
-	memset(&cmd, 0, sizeof(cmd));
-
-	cmd.cmd = CMD_ALLOCATEAUX;
-	cmd.parm0 = FID_TX;
-	cmd.parm1 = (ai->txfids[0].card_ram_off - ai->pciaux);
-	cmd.parm2 = MPI_MAX_FIDS;
-
-	for (i = 0; i<MPI_MAX_FIDS; i++) {
-		ai->txfids[i].tx_desc.valid = 1;
-		memcpy_toio(ai->txfids[i].card_ram_off,
-			&ai->txfids[i].tx_desc, sizeof(TxFid));
-	}
-	ai->txfids[i-1].tx_desc.eoc = 1; /* Last descriptor has EOC set */
-
-	rc = issuecommand(ai, &cmd, &rsp, true);
-	if (rc != SUCCESS) {
-		airo_print_err(ai->dev->name, "Couldn't allocate TX FID");
-		return rc;
-	}
-
-	/* Alloc card Rid descriptor */
-	memset(&rsp, 0, sizeof(rsp));
-	memset(&cmd, 0, sizeof(cmd));
-
-	cmd.cmd = CMD_ALLOCATEAUX;
-	cmd.parm0 = RID_RW;
-	cmd.parm1 = (ai->config_desc.card_ram_off - ai->pciaux);
-	cmd.parm2 = 1; /* Magic number... */
-	rc = issuecommand(ai, &cmd, &rsp, true);
-	if (rc != SUCCESS) {
-		airo_print_err(ai->dev->name, "Couldn't allocate RID");
-		return rc;
-	}
-
-	memcpy_toio(ai->config_desc.card_ram_off,
-		&ai->config_desc.rid_desc, sizeof(Rid));
-
-	return rc;
-}
-
-/*
- * We are setting up three things here:
- * 1) Map AUX memory for descriptors: Rid, TxFid, or RxFid.
- * 2) Map PCI memory for issuing commands.
- * 3) Allocate memory (shared) to send and receive ethernet frames.
- */
-static int mpi_map_card(struct airo_info *ai, struct pci_dev *pci)
-{
-	unsigned long mem_start, mem_len, aux_start, aux_len;
-	int rc = -1;
-	int i;
-	dma_addr_t busaddroff;
-	unsigned char *vpackoff;
-	unsigned char __iomem *pciaddroff;
-
-	mem_start = pci_resource_start(pci, 1);
-	mem_len = pci_resource_len(pci, 1);
-	aux_start = pci_resource_start(pci, 2);
-	aux_len = AUXMEMSIZE;
-
-	if (!request_mem_region(mem_start, mem_len, DRV_NAME)) {
-		airo_print_err("", "Couldn't get region %x[%x]",
-			(int)mem_start, (int)mem_len);
-		goto out;
-	}
-	if (!request_mem_region(aux_start, aux_len, DRV_NAME)) {
-		airo_print_err("", "Couldn't get region %x[%x]",
-			(int)aux_start, (int)aux_len);
-		goto free_region1;
-	}
-
-	ai->pcimem = ioremap(mem_start, mem_len);
-	if (!ai->pcimem) {
-		airo_print_err("", "Couldn't map region %x[%x]",
-			(int)mem_start, (int)mem_len);
-		goto free_region2;
-	}
-	ai->pciaux = ioremap(aux_start, aux_len);
-	if (!ai->pciaux) {
-		airo_print_err("", "Couldn't map region %x[%x]",
-			(int)aux_start, (int)aux_len);
-		goto free_memmap;
-	}
-
-	/* Reserve PKTSIZE for each fid and 2K for the Rids */
-	ai->shared = dma_alloc_coherent(&pci->dev, PCI_SHARED_LEN,
-					&ai->shared_dma, GFP_KERNEL);
-	if (!ai->shared) {
-		airo_print_err("", "Couldn't alloc_coherent %d",
-			PCI_SHARED_LEN);
-		goto free_auxmap;
-	}
-
-	/*
-	 * Setup descriptor RX, TX, CONFIG
-	 */
-	busaddroff = ai->shared_dma;
-	pciaddroff = ai->pciaux + AUX_OFFSET;
-	vpackoff   = ai->shared;
-
-	/* RX descriptor setup */
-	for (i = 0; i < MPI_MAX_FIDS; i++) {
-		ai->rxfids[i].pending = 0;
-		ai->rxfids[i].card_ram_off = pciaddroff;
-		ai->rxfids[i].virtual_host_addr = vpackoff;
-		ai->rxfids[i].rx_desc.host_addr = busaddroff;
-		ai->rxfids[i].rx_desc.valid = 1;
-		ai->rxfids[i].rx_desc.len = PKTSIZE;
-		ai->rxfids[i].rx_desc.rdy = 0;
-
-		pciaddroff += sizeof(RxFid);
-		busaddroff += PKTSIZE;
-		vpackoff   += PKTSIZE;
-	}
-
-	/* TX descriptor setup */
-	for (i = 0; i < MPI_MAX_FIDS; i++) {
-		ai->txfids[i].card_ram_off = pciaddroff;
-		ai->txfids[i].virtual_host_addr = vpackoff;
-		ai->txfids[i].tx_desc.valid = 1;
-		ai->txfids[i].tx_desc.host_addr = busaddroff;
-		memcpy(ai->txfids[i].virtual_host_addr,
-			&wifictlhdr8023, sizeof(wifictlhdr8023));
-
-		pciaddroff += sizeof(TxFid);
-		busaddroff += PKTSIZE;
-		vpackoff   += PKTSIZE;
-	}
-	ai->txfids[i-1].tx_desc.eoc = 1; /* Last descriptor has EOC set */
-
-	/* Rid descriptor setup */
-	ai->config_desc.card_ram_off = pciaddroff;
-	ai->config_desc.virtual_host_addr = vpackoff;
-	ai->config_desc.rid_desc.host_addr = busaddroff;
-	ai->ridbus = busaddroff;
-	ai->config_desc.rid_desc.rid = 0;
-	ai->config_desc.rid_desc.len = RIDSIZE;
-	ai->config_desc.rid_desc.valid = 1;
-	pciaddroff += sizeof(Rid);
-	busaddroff += RIDSIZE;
-	vpackoff   += RIDSIZE;
-
-	/* Tell card about descriptors */
-	if (mpi_init_descriptors (ai) != SUCCESS)
-		goto free_shared;
-
-	return 0;
- free_shared:
-	dma_free_coherent(&pci->dev, PCI_SHARED_LEN, ai->shared,
-			  ai->shared_dma);
- free_auxmap:
-	iounmap(ai->pciaux);
- free_memmap:
-	iounmap(ai->pcimem);
- free_region2:
-	release_mem_region(aux_start, aux_len);
- free_region1:
-	release_mem_region(mem_start, mem_len);
- out:
-	return rc;
-}
-
-static const struct header_ops airo_header_ops = {
-	.parse = wll_header_parse,
-};
-
-static const struct net_device_ops airo11_netdev_ops = {
-	.ndo_open 		= airo_open,
-	.ndo_stop 		= airo_close,
-	.ndo_start_xmit 	= airo_start_xmit11,
-	.ndo_get_stats 		= airo_get_stats,
-	.ndo_set_mac_address	= airo_set_mac_address,
-	.ndo_siocdevprivate	= airo_siocdevprivate,
-};
-
-static void wifi_setup(struct net_device *dev)
-{
-	dev->netdev_ops = &airo11_netdev_ops;
-	dev->header_ops = &airo_header_ops;
-	dev->wireless_handlers = &airo_handler_def;
-
-	dev->type               = ARPHRD_IEEE80211;
-	dev->hard_header_len    = ETH_HLEN;
-	dev->mtu                = AIRO_DEF_MTU;
-	dev->min_mtu            = 68;
-	dev->max_mtu            = MIC_MSGLEN_MAX;
-	dev->addr_len           = ETH_ALEN;
-	dev->tx_queue_len       = 100;
-
-	eth_broadcast_addr(dev->broadcast);
-
-	dev->flags              = IFF_BROADCAST|IFF_MULTICAST;
-}
-
-static struct net_device *init_wifidev(struct airo_info *ai,
-					struct net_device *ethdev)
-{
-	int err;
-	struct net_device *dev = alloc_netdev(0, "wifi%d", NET_NAME_UNKNOWN,
-					      wifi_setup);
-	if (!dev)
-		return NULL;
-	dev->ml_priv = ethdev->ml_priv;
-	dev->irq = ethdev->irq;
-	dev->base_addr = ethdev->base_addr;
-	dev->wireless_data = ethdev->wireless_data;
-	SET_NETDEV_DEV(dev, ethdev->dev.parent);
-	eth_hw_addr_inherit(dev, ethdev);
-	err = register_netdev(dev);
-	if (err<0) {
-		free_netdev(dev);
-		return NULL;
-	}
-	return dev;
-}
-
-static int reset_card(struct net_device *dev, int lock)
-{
-	struct airo_info *ai = dev->ml_priv;
-
-	if (lock && down_interruptible(&ai->sem))
-		return -1;
-	waitbusy (ai);
-	OUT4500(ai, COMMAND, CMD_SOFTRESET);
-	msleep(200);
-	waitbusy (ai);
-	msleep(200);
-	if (lock)
-		up(&ai->sem);
-	return 0;
-}
-
-#define AIRO_MAX_NETWORK_COUNT	64
-static int airo_networks_allocate(struct airo_info *ai)
-{
-	if (ai->networks)
-		return 0;
-
-	ai->networks = kcalloc(AIRO_MAX_NETWORK_COUNT, sizeof(BSSListElement),
-			       GFP_KERNEL);
-	if (!ai->networks) {
-		airo_print_warn("", "Out of memory allocating beacons");
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-static void airo_networks_free(struct airo_info *ai)
-{
-	kfree(ai->networks);
-	ai->networks = NULL;
-}
-
-static void airo_networks_initialize(struct airo_info *ai)
-{
-	int i;
-
-	INIT_LIST_HEAD(&ai->network_free_list);
-	INIT_LIST_HEAD(&ai->network_list);
-	for (i = 0; i < AIRO_MAX_NETWORK_COUNT; i++)
-		list_add_tail(&ai->networks[i].list,
-			      &ai->network_free_list);
-}
-
-static const struct net_device_ops airo_netdev_ops = {
-	.ndo_open		= airo_open,
-	.ndo_stop		= airo_close,
-	.ndo_start_xmit		= airo_start_xmit,
-	.ndo_get_stats		= airo_get_stats,
-	.ndo_set_rx_mode	= airo_set_multicast_list,
-	.ndo_set_mac_address	= airo_set_mac_address,
-	.ndo_siocdevprivate	= airo_siocdevprivate,
-	.ndo_validate_addr	= eth_validate_addr,
-};
-
-static const struct net_device_ops mpi_netdev_ops = {
-	.ndo_open		= airo_open,
-	.ndo_stop		= airo_close,
-	.ndo_start_xmit		= mpi_start_xmit,
-	.ndo_get_stats		= airo_get_stats,
-	.ndo_set_rx_mode	= airo_set_multicast_list,
-	.ndo_set_mac_address	= airo_set_mac_address,
-	.ndo_siocdevprivate	= airo_siocdevprivate,
-	.ndo_validate_addr	= eth_validate_addr,
-};
-
-
-static struct net_device *_init_airo_card(unsigned short irq, int port,
-					   int is_pcmcia, struct pci_dev *pci,
-					   struct device *dmdev)
-{
-	struct net_device *dev;
-	struct airo_info *ai;
-	int i, rc;
-	CapabilityRid cap_rid;
-
-	/* Create the network device object. */
-	dev = alloc_netdev(sizeof(*ai), "", NET_NAME_UNKNOWN, ether_setup);
-	if (!dev) {
-		airo_print_err("", "Couldn't alloc_etherdev");
-		return NULL;
-	}
-
-	ai = dev->ml_priv = netdev_priv(dev);
-	ai->wifidev = NULL;
-	ai->flags = 1 << FLAG_RADIO_DOWN;
-	ai->jobs = 0;
-	ai->dev = dev;
-	if (pci && (pci->device == 0x5000 || pci->device == 0xa504)) {
-		airo_print_dbg("", "Found an MPI350 card");
-		set_bit(FLAG_MPI, &ai->flags);
-	}
-	spin_lock_init(&ai->aux_lock);
-	sema_init(&ai->sem, 1);
-	ai->config.len = 0;
-	ai->pci = pci;
-	init_waitqueue_head (&ai->thr_wait);
-	ai->tfm = NULL;
-	add_airo_dev(ai);
-	ai->APList.len = cpu_to_le16(sizeof(struct APListRid));
-
-	if (airo_networks_allocate (ai))
-		goto err_out_free;
-	airo_networks_initialize (ai);
-
-	skb_queue_head_init (&ai->txq);
-
-	/* The Airo-specific entries in the device structure. */
-	if (test_bit(FLAG_MPI,&ai->flags))
-		dev->netdev_ops = &mpi_netdev_ops;
-	else
-		dev->netdev_ops = &airo_netdev_ops;
-	dev->wireless_handlers = &airo_handler_def;
-	ai->wireless_data.spy_data = &ai->spy_data;
-	dev->wireless_data = &ai->wireless_data;
-	dev->irq = irq;
-	dev->base_addr = port;
-	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
-	dev->max_mtu = MIC_MSGLEN_MAX;
-
-	SET_NETDEV_DEV(dev, dmdev);
-
-	reset_card (dev, 1);
-	msleep(400);
-
-	if (!is_pcmcia) {
-		if (!request_region(dev->base_addr, 64, DRV_NAME)) {
-			rc = -EBUSY;
-			airo_print_err(dev->name, "Couldn't request region");
-			goto err_out_nets;
-		}
-	}
-
-	if (test_bit(FLAG_MPI,&ai->flags)) {
-		if (mpi_map_card(ai, pci)) {
-			airo_print_err("", "Could not map memory");
-			goto err_out_res;
-		}
-	}
-
-	if (probe) {
-		if (setup_card(ai, dev, 1) != SUCCESS) {
-			airo_print_err(dev->name, "MAC could not be enabled");
-			rc = -EIO;
-			goto err_out_map;
-		}
-	} else if (!test_bit(FLAG_MPI,&ai->flags)) {
-		ai->bap_read = fast_bap_read;
-		set_bit(FLAG_FLASHING, &ai->flags);
-	}
-
-	strcpy(dev->name, "eth%d");
-	rc = register_netdev(dev);
-	if (rc) {
-		airo_print_err(dev->name, "Couldn't register_netdev");
-		goto err_out_map;
-	}
-	ai->wifidev = init_wifidev(ai, dev);
-	if (!ai->wifidev)
-		goto err_out_reg;
-
-	rc = readCapabilityRid(ai, &cap_rid, 1);
-	if (rc != SUCCESS) {
-		rc = -EIO;
-		goto err_out_wifi;
-	}
-	/* WEP capability discovery */
-	ai->wep_capable = (cap_rid.softCap & cpu_to_le16(0x02)) ? 1 : 0;
-	ai->max_wep_idx = (cap_rid.softCap & cpu_to_le16(0x80)) ? 3 : 0;
-
-	airo_print_info(dev->name, "Firmware version %x.%x.%02d",
-	                ((le16_to_cpu(cap_rid.softVer) >> 8) & 0xF),
-	                (le16_to_cpu(cap_rid.softVer) & 0xFF),
-	                le16_to_cpu(cap_rid.softSubVer));
-
-	/* Test for WPA support */
-	/* Only firmware versions 5.30.17 or better can do WPA */
-	if (le16_to_cpu(cap_rid.softVer) > 0x530
-	 || (le16_to_cpu(cap_rid.softVer) == 0x530
-	      && le16_to_cpu(cap_rid.softSubVer) >= 17)) {
-		airo_print_info(ai->dev->name, "WPA supported.");
-
-		set_bit(FLAG_WPA_CAPABLE, &ai->flags);
-		ai->bssListFirst = RID_WPA_BSSLISTFIRST;
-		ai->bssListNext = RID_WPA_BSSLISTNEXT;
-		ai->bssListRidLen = sizeof(BSSListRid);
-	} else {
-		airo_print_info(ai->dev->name, "WPA unsupported with firmware "
-			"versions older than 5.30.17.");
-
-		ai->bssListFirst = RID_BSSLISTFIRST;
-		ai->bssListNext = RID_BSSLISTNEXT;
-		ai->bssListRidLen = sizeof(BSSListRid) - sizeof(BSSListRidExtra);
-	}
-
-	set_bit(FLAG_REGISTERED,&ai->flags);
-	airo_print_info(dev->name, "MAC enabled %pM", dev->dev_addr);
-
-	/* Allocate the transmit buffers */
-	if (probe && !test_bit(FLAG_MPI,&ai->flags))
-		for (i = 0; i < MAX_FIDS; i++)
-			ai->fids[i] = transmit_allocate(ai, AIRO_DEF_MTU, i>=MAX_FIDS/2);
-
-	if (setup_proc_entry(dev, dev->ml_priv) < 0)
-		goto err_out_wifi;
-
-	return dev;
-
-err_out_wifi:
-	unregister_netdev(ai->wifidev);
-	free_netdev(ai->wifidev);
-err_out_reg:
-	unregister_netdev(dev);
-err_out_map:
-	if (test_bit(FLAG_MPI,&ai->flags) && pci) {
-		dma_free_coherent(&pci->dev, PCI_SHARED_LEN, ai->shared,
-				  ai->shared_dma);
-		iounmap(ai->pciaux);
-		iounmap(ai->pcimem);
-		mpi_unmap_card(ai->pci);
-	}
-err_out_res:
-	if (!is_pcmcia)
-		release_region(dev->base_addr, 64);
-err_out_nets:
-	airo_networks_free(ai);
-err_out_free:
-	del_airo_dev(ai);
-	free_netdev(dev);
-	return NULL;
-}
-
-struct net_device *init_airo_card(unsigned short irq, int port, int is_pcmcia,
-				  struct device *dmdev)
-{
-	return _init_airo_card (irq, port, is_pcmcia, NULL, dmdev);
-}
-
-EXPORT_SYMBOL(init_airo_card);
-
-static int waitbusy (struct airo_info *ai)
-{
-	int delay = 0;
-	while ((IN4500(ai, COMMAND) & COMMAND_BUSY) && (delay < 10000)) {
-		udelay (10);
-		if ((++delay % 20) == 0)
-			OUT4500(ai, EVACK, EV_CLEARCOMMANDBUSY);
-	}
-	return delay < 10000;
-}
-
-int reset_airo_card(struct net_device *dev)
-{
-	int i;
-	struct airo_info *ai = dev->ml_priv;
-
-	if (reset_card (dev, 1))
-		return -1;
-
-	if (setup_card(ai, dev, 1) != SUCCESS) {
-		airo_print_err(dev->name, "MAC could not be enabled");
-		return -1;
-	}
-	airo_print_info(dev->name, "MAC enabled %pM", dev->dev_addr);
-	/* Allocate the transmit buffers if needed */
-	if (!test_bit(FLAG_MPI,&ai->flags))
-		for (i = 0; i < MAX_FIDS; i++)
-			ai->fids[i] = transmit_allocate (ai, AIRO_DEF_MTU, i>=MAX_FIDS/2);
-
-	enable_interrupts(ai);
-	netif_wake_queue(dev);
-	return 0;
-}
-
-EXPORT_SYMBOL(reset_airo_card);
-
-static void airo_send_event(struct net_device *dev)
-{
-	struct airo_info *ai = dev->ml_priv;
-	union iwreq_data wrqu;
-	StatusRid status_rid;
-
-	clear_bit(JOB_EVENT, &ai->jobs);
-	PC4500_readrid(ai, RID_STATUS, &status_rid, sizeof(status_rid), 0);
-	up(&ai->sem);
-	wrqu.data.length = 0;
-	wrqu.data.flags = 0;
-	memcpy(wrqu.ap_addr.sa_data, status_rid.bssid[0], ETH_ALEN);
-	wrqu.ap_addr.sa_family = ARPHRD_ETHER;
-
-	/* Send event to user space */
-	wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL);
-}
-
-static void airo_process_scan_results (struct airo_info *ai)
-{
-	union iwreq_data	wrqu;
-	BSSListRid bss;
-	int rc;
-	BSSListElement * loop_net;
-	BSSListElement * tmp_net;
-
-	/* Blow away current list of scan results */
-	list_for_each_entry_safe (loop_net, tmp_net, &ai->network_list, list) {
-		list_move_tail (&loop_net->list, &ai->network_free_list);
-		/* Don't blow away ->list, just BSS data */
-		memset (loop_net, 0, sizeof (loop_net->bss));
-	}
-
-	/* Try to read the first entry of the scan result */
-	rc = PC4500_readrid(ai, ai->bssListFirst, &bss, ai->bssListRidLen, 0);
-	if ((rc) || (bss.index == cpu_to_le16(0xffff))) {
-		/* No scan results */
-		goto out;
-	}
-
-	/* Read and parse all entries */
-	tmp_net = NULL;
-	while ((!rc) && (bss.index != cpu_to_le16(0xffff))) {
-		/* Grab a network off the free list */
-		if (!list_empty(&ai->network_free_list)) {
-			tmp_net = list_entry(ai->network_free_list.next,
-					    BSSListElement, list);
-			list_del(ai->network_free_list.next);
-		}
-
-		if (tmp_net != NULL) {
-			memcpy(tmp_net, &bss, sizeof(tmp_net->bss));
-			list_add_tail(&tmp_net->list, &ai->network_list);
-			tmp_net = NULL;
-		}
-
-		/* Read next entry */
-		rc = PC4500_readrid(ai, ai->bssListNext,
-				    &bss, ai->bssListRidLen, 0);
-	}
-
-out:
-	/* write APList back (we cleared it in airo_set_scan) */
-	disable_MAC(ai, 2);
-	writeAPListRid(ai, &ai->APList, 0);
-	enable_MAC(ai, 0);
-
-	ai->scan_timeout = 0;
-	clear_bit(JOB_SCAN_RESULTS, &ai->jobs);
-	up(&ai->sem);
-
-	/* Send an empty event to user space.
-	 * We don't send the received data on
-	 * the event because it would require
-	 * us to do complex transcoding, and
-	 * we want to minimise the work done in
-	 * the irq handler. Use a request to
-	 * extract the data - Jean II */
-	wrqu.data.length = 0;
-	wrqu.data.flags = 0;
-	wireless_send_event(ai->dev, SIOCGIWSCAN, &wrqu, NULL);
-}
-
-static int airo_thread(void *data)
-{
-	struct net_device *dev = data;
-	struct airo_info *ai = dev->ml_priv;
-	int locked;
-
-	set_freezable();
-	while (1) {
-		/* make swsusp happy with our thread */
-		try_to_freeze();
-
-		if (test_bit(JOB_DIE, &ai->jobs))
-			break;
-
-		if (ai->jobs) {
-			locked = down_interruptible(&ai->sem);
-		} else {
-			wait_queue_entry_t wait;
-
-			init_waitqueue_entry(&wait, current);
-			add_wait_queue(&ai->thr_wait, &wait);
-			for (;;) {
-				set_current_state(TASK_INTERRUPTIBLE);
-				if (ai->jobs)
-					break;
-				if (ai->expires || ai->scan_timeout) {
-					if (ai->scan_timeout &&
-							time_after_eq(jiffies, ai->scan_timeout)) {
-						set_bit(JOB_SCAN_RESULTS, &ai->jobs);
-						break;
-					} else if (ai->expires &&
-							time_after_eq(jiffies, ai->expires)) {
-						set_bit(JOB_AUTOWEP, &ai->jobs);
-						break;
-					}
-					if (!kthread_should_stop() &&
-					    !freezing(current)) {
-						unsigned long wake_at;
-						if (!ai->expires || !ai->scan_timeout) {
-							wake_at = max(ai->expires,
-								ai->scan_timeout);
-						} else {
-							wake_at = min(ai->expires,
-								ai->scan_timeout);
-						}
-						schedule_timeout(wake_at - jiffies);
-						continue;
-					}
-				} else if (!kthread_should_stop() &&
-					   !freezing(current)) {
-					schedule();
-					continue;
-				}
-				break;
-			}
-			__set_current_state(TASK_RUNNING);
-			remove_wait_queue(&ai->thr_wait, &wait);
-			locked = 1;
-		}
-
-		if (locked)
-			continue;
-
-		if (test_bit(JOB_DIE, &ai->jobs)) {
-			up(&ai->sem);
-			break;
-		}
-
-		if (ai->power.event || test_bit(FLAG_FLASHING, &ai->flags)) {
-			up(&ai->sem);
-			continue;
-		}
-
-		if (test_bit(JOB_XMIT, &ai->jobs))
-			airo_end_xmit(dev, true);
-		else if (test_bit(JOB_XMIT11, &ai->jobs))
-			airo_end_xmit11(dev, true);
-		else if (test_bit(JOB_STATS, &ai->jobs))
-			airo_read_stats(dev);
-		else if (test_bit(JOB_PROMISC, &ai->jobs))
-			airo_set_promisc(ai, true);
-		else if (test_bit(JOB_MIC, &ai->jobs))
-			micinit(ai);
-		else if (test_bit(JOB_EVENT, &ai->jobs))
-			airo_send_event(dev);
-		else if (test_bit(JOB_AUTOWEP, &ai->jobs))
-			timer_func(dev);
-		else if (test_bit(JOB_SCAN_RESULTS, &ai->jobs))
-			airo_process_scan_results(ai);
-		else  /* Shouldn't get here, but we make sure to unlock */
-			up(&ai->sem);
-	}
-
-	return 0;
-}
-
-static int header_len(__le16 ctl)
-{
-	u16 fc = le16_to_cpu(ctl);
-	switch (fc & 0xc) {
-	case 4:
-		if ((fc & 0xe0) == 0xc0)
-			return 10;	/* one-address control packet */
-		return 16;	/* two-address control packet */
-	case 8:
-		if ((fc & 0x300) == 0x300)
-			return 30;	/* WDS packet */
-	}
-	return 24;
-}
-
-static void airo_handle_cisco_mic(struct airo_info *ai)
-{
-	if (test_bit(FLAG_MIC_CAPABLE, &ai->flags)) {
-		set_bit(JOB_MIC, &ai->jobs);
-		wake_up_interruptible(&ai->thr_wait);
-	}
-}
-
-/* Airo Status codes */
-#define STAT_NOBEACON	0x8000 /* Loss of sync - missed beacons */
-#define STAT_MAXRETRIES	0x8001 /* Loss of sync - max retries */
-#define STAT_MAXARL	0x8002 /* Loss of sync - average retry level exceeded*/
-#define STAT_FORCELOSS	0x8003 /* Loss of sync - host request */
-#define STAT_TSFSYNC	0x8004 /* Loss of sync - TSF synchronization */
-#define STAT_DEAUTH	0x8100 /* low byte is 802.11 reason code */
-#define STAT_DISASSOC	0x8200 /* low byte is 802.11 reason code */
-#define STAT_ASSOC_FAIL	0x8400 /* low byte is 802.11 reason code */
-#define STAT_AUTH_FAIL	0x0300 /* low byte is 802.11 reason code */
-#define STAT_ASSOC	0x0400 /* Associated */
-#define STAT_REASSOC    0x0600 /* Reassociated?  Only on firmware >= 5.30.17 */
-
-static void airo_print_status(const char *devname, u16 status)
-{
-	u8 reason = status & 0xFF;
-
-	switch (status & 0xFF00) {
-	case STAT_NOBEACON:
-		switch (status) {
-		case STAT_NOBEACON:
-			airo_print_dbg(devname, "link lost (missed beacons)");
-			break;
-		case STAT_MAXRETRIES:
-		case STAT_MAXARL:
-			airo_print_dbg(devname, "link lost (max retries)");
-			break;
-		case STAT_FORCELOSS:
-			airo_print_dbg(devname, "link lost (local choice)");
-			break;
-		case STAT_TSFSYNC:
-			airo_print_dbg(devname, "link lost (TSF sync lost)");
-			break;
-		default:
-			airo_print_dbg(devname, "unknown status %x\n", status);
-			break;
-		}
-		break;
-	case STAT_DEAUTH:
-		airo_print_dbg(devname, "deauthenticated (reason: %d)", reason);
-		break;
-	case STAT_DISASSOC:
-		airo_print_dbg(devname, "disassociated (reason: %d)", reason);
-		break;
-	case STAT_ASSOC_FAIL:
-		airo_print_dbg(devname, "association failed (reason: %d)",
-			       reason);
-		break;
-	case STAT_AUTH_FAIL:
-		airo_print_dbg(devname, "authentication failed (reason: %d)",
-			       reason);
-		break;
-	case STAT_ASSOC:
-	case STAT_REASSOC:
-		break;
-	default:
-		airo_print_dbg(devname, "unknown status %x\n", status);
-		break;
-	}
-}
-
-static void airo_handle_link(struct airo_info *ai)
-{
-	union iwreq_data wrqu;
-	int scan_forceloss = 0;
-	u16 status;
-
-	/* Get new status and acknowledge the link change */
-	status = le16_to_cpu(IN4500(ai, LINKSTAT));
-	OUT4500(ai, EVACK, EV_LINK);
-
-	if ((status == STAT_FORCELOSS) && (ai->scan_timeout > 0))
-		scan_forceloss = 1;
-
-	airo_print_status(ai->dev->name, status);
-
-	if ((status == STAT_ASSOC) || (status == STAT_REASSOC)) {
-		if (auto_wep)
-			ai->expires = 0;
-		if (ai->list_bss_task)
-			wake_up_process(ai->list_bss_task);
-		set_bit(FLAG_UPDATE_UNI, &ai->flags);
-		set_bit(FLAG_UPDATE_MULTI, &ai->flags);
-
-		set_bit(JOB_EVENT, &ai->jobs);
-		wake_up_interruptible(&ai->thr_wait);
-
-		netif_carrier_on(ai->dev);
-	} else if (!scan_forceloss) {
-		if (auto_wep && !ai->expires) {
-			ai->expires = RUN_AT(3*HZ);
-			wake_up_interruptible(&ai->thr_wait);
-		}
-
-		/* Send event to user space */
-		eth_zero_addr(wrqu.ap_addr.sa_data);
-		wrqu.ap_addr.sa_family = ARPHRD_ETHER;
-		wireless_send_event(ai->dev, SIOCGIWAP, &wrqu, NULL);
-		netif_carrier_off(ai->dev);
-	} else {
-		netif_carrier_off(ai->dev);
-	}
-}
-
-static void airo_handle_rx(struct airo_info *ai)
-{
-	struct sk_buff *skb = NULL;
-	__le16 fc, v, *buffer, tmpbuf[4];
-	u16 len, hdrlen = 0, gap, fid;
-	struct rx_hdr hdr;
-	int success = 0;
-
-	if (test_bit(FLAG_MPI, &ai->flags)) {
-		if (test_bit(FLAG_802_11, &ai->flags))
-			mpi_receive_802_11(ai);
-		else
-			mpi_receive_802_3(ai);
-		OUT4500(ai, EVACK, EV_RX);
-		return;
-	}
-
-	fid = IN4500(ai, RXFID);
-
-	/* Get the packet length */
-	if (test_bit(FLAG_802_11, &ai->flags)) {
-		bap_setup (ai, fid, 4, BAP0);
-		bap_read (ai, (__le16*)&hdr, sizeof(hdr), BAP0);
-		/* Bad CRC. Ignore packet */
-		if (le16_to_cpu(hdr.status) & 2)
-			hdr.len = 0;
-		if (ai->wifidev == NULL)
-			hdr.len = 0;
-	} else {
-		bap_setup(ai, fid, 0x36, BAP0);
-		bap_read(ai, &hdr.len, 2, BAP0);
-	}
-	len = le16_to_cpu(hdr.len);
-
-	if (len > AIRO_DEF_MTU) {
-		airo_print_err(ai->dev->name, "Bad size %d", len);
-		goto done;
-	}
-	if (len == 0)
-		goto done;
-
-	if (test_bit(FLAG_802_11, &ai->flags)) {
-		bap_read(ai, &fc, sizeof (fc), BAP0);
-		hdrlen = header_len(fc);
-	} else
-		hdrlen = ETH_ALEN * 2;
-
-	skb = dev_alloc_skb(len + hdrlen + 2 + 2);
-	if (!skb) {
-		ai->dev->stats.rx_dropped++;
-		goto done;
-	}
-
-	skb_reserve(skb, 2); /* This way the IP header is aligned */
-	buffer = skb_put(skb, len + hdrlen);
-	if (test_bit(FLAG_802_11, &ai->flags)) {
-		buffer[0] = fc;
-		bap_read(ai, buffer + 1, hdrlen - 2, BAP0);
-		if (hdrlen == 24)
-			bap_read(ai, tmpbuf, 6, BAP0);
-
-		bap_read(ai, &v, sizeof(v), BAP0);
-		gap = le16_to_cpu(v);
-		if (gap) {
-			if (gap <= 8) {
-				bap_read(ai, tmpbuf, gap, BAP0);
-			} else {
-				airo_print_err(ai->dev->name, "gaplen too "
-					"big. Problems will follow...");
-			}
-		}
-		bap_read(ai, buffer + hdrlen/2, len, BAP0);
-	} else {
-		MICBuffer micbuf;
-
-		bap_read(ai, buffer, ETH_ALEN * 2, BAP0);
-		if (ai->micstats.enabled) {
-			bap_read(ai, (__le16 *) &micbuf, sizeof (micbuf), BAP0);
-			if (ntohs(micbuf.typelen) > 0x05DC)
-				bap_setup(ai, fid, 0x44, BAP0);
-			else {
-				if (len <= sizeof (micbuf)) {
-					dev_kfree_skb_irq(skb);
-					goto done;
-				}
-
-				len -= sizeof(micbuf);
-				skb_trim(skb, len + hdrlen);
-			}
-		}
-
-		bap_read(ai, buffer + ETH_ALEN, len, BAP0);
-		if (decapsulate(ai, &micbuf, (etherHead*) buffer, len))
-			dev_kfree_skb_irq (skb);
-		else
-			success = 1;
-	}
-
-#ifdef WIRELESS_SPY
-	if (success && (ai->spy_data.spy_number > 0)) {
-		char *sa;
-		struct iw_quality wstats;
-
-		/* Prepare spy data : addr + qual */
-		if (!test_bit(FLAG_802_11, &ai->flags)) {
-			sa = (char *) buffer + 6;
-			bap_setup(ai, fid, 8, BAP0);
-			bap_read(ai, (__le16 *) hdr.rssi, 2, BAP0);
-		} else
-			sa = (char *) buffer + 10;
-		wstats.qual = hdr.rssi[0];
-		if (ai->rssi)
-			wstats.level = 0x100 - ai->rssi[hdr.rssi[1]].rssidBm;
-		else
-			wstats.level = (hdr.rssi[1] + 321) / 2;
-		wstats.noise = ai->wstats.qual.noise;
-		wstats.updated =  IW_QUAL_LEVEL_UPDATED
-				| IW_QUAL_QUAL_UPDATED
-				| IW_QUAL_DBM;
-		/* Update spy records */
-		wireless_spy_update(ai->dev, sa, &wstats);
-	}
-#endif /* WIRELESS_SPY */
-
-done:
-	OUT4500(ai, EVACK, EV_RX);
-
-	if (success) {
-		if (test_bit(FLAG_802_11, &ai->flags)) {
-			skb_reset_mac_header(skb);
-			skb->pkt_type = PACKET_OTHERHOST;
-			skb->dev = ai->wifidev;
-			skb->protocol = htons(ETH_P_802_2);
-		} else
-			skb->protocol = eth_type_trans(skb, ai->dev);
-		skb->ip_summed = CHECKSUM_NONE;
-
-		netif_rx(skb);
-	}
-}
-
-static void airo_handle_tx(struct airo_info *ai, u16 status)
-{
-	int i, index = -1;
-	u16 fid;
-
-	if (test_bit(FLAG_MPI, &ai->flags)) {
-		unsigned long flags;
-
-		if (status & EV_TXEXC)
-			get_tx_error(ai, -1);
-
-		spin_lock_irqsave(&ai->aux_lock, flags);
-		if (!skb_queue_empty(&ai->txq)) {
-			spin_unlock_irqrestore(&ai->aux_lock, flags);
-			mpi_send_packet(ai->dev);
-		} else {
-			clear_bit(FLAG_PENDING_XMIT, &ai->flags);
-			spin_unlock_irqrestore(&ai->aux_lock, flags);
-			netif_wake_queue(ai->dev);
-		}
-		OUT4500(ai, EVACK, status & (EV_TX | EV_TXCPY | EV_TXEXC));
-		return;
-	}
-
-	fid = IN4500(ai, TXCOMPLFID);
-
-	for (i = 0; i < MAX_FIDS; i++) {
-		if ((ai->fids[i] & 0xffff) == fid)
-			index = i;
-	}
-
-	if (index != -1) {
-		if (status & EV_TXEXC)
-			get_tx_error(ai, index);
-
-		OUT4500(ai, EVACK, status & (EV_TX | EV_TXEXC));
-
-		/* Set up to be used again */
-		ai->fids[index] &= 0xffff;
-		if (index < MAX_FIDS / 2) {
-			if (!test_bit(FLAG_PENDING_XMIT, &ai->flags))
-				netif_wake_queue(ai->dev);
-		} else {
-			if (!test_bit(FLAG_PENDING_XMIT11, &ai->flags))
-				netif_wake_queue(ai->wifidev);
-		}
-	} else {
-		OUT4500(ai, EVACK, status & (EV_TX | EV_TXCPY | EV_TXEXC));
-		airo_print_err(ai->dev->name, "Unallocated FID was used to xmit");
-	}
-}
-
-static irqreturn_t airo_interrupt(int irq, void *dev_id)
-{
-	struct net_device *dev = dev_id;
-	u16 status, savedInterrupts = 0;
-	struct airo_info *ai = dev->ml_priv;
-	int handled = 0;
-
-	if (!netif_device_present(dev))
-		return IRQ_NONE;
-
-	for (;;) {
-		status = IN4500(ai, EVSTAT);
-		if (!(status & STATUS_INTS) || (status == 0xffff))
-			break;
-
-		handled = 1;
-
-		if (status & EV_AWAKE) {
-			OUT4500(ai, EVACK, EV_AWAKE);
-			OUT4500(ai, EVACK, EV_AWAKE);
-		}
-
-		if (!savedInterrupts) {
-			savedInterrupts = IN4500(ai, EVINTEN);
-			OUT4500(ai, EVINTEN, 0);
-		}
-
-		if (status & EV_MIC) {
-			OUT4500(ai, EVACK, EV_MIC);
-			airo_handle_cisco_mic(ai);
-		}
-
-		if (status & EV_LINK) {
-			/* Link status changed */
-			airo_handle_link(ai);
-		}
-
-		/* Check to see if there is something to receive */
-		if (status & EV_RX)
-			airo_handle_rx(ai);
-
-		/* Check to see if a packet has been transmitted */
-		if (status & (EV_TX | EV_TXCPY | EV_TXEXC))
-			airo_handle_tx(ai, status);
-
-		if (status & ~STATUS_INTS & ~IGNORE_INTS) {
-			airo_print_warn(ai->dev->name, "Got weird status %x",
-				status & ~STATUS_INTS & ~IGNORE_INTS);
-		}
-	}
-
-	if (savedInterrupts)
-		OUT4500(ai, EVINTEN, savedInterrupts);
-
-	return IRQ_RETVAL(handled);
-}
-
-/*
- *  Routines to talk to the card
- */
-
-/*
- *  This was originally written for the 4500, hence the name
- *  NOTE:  If use with 8bit mode and SMP bad things will happen!
- *         Why would some one do 8 bit IO in an SMP machine?!?
- */
-static void OUT4500(struct airo_info *ai, u16 reg, u16 val)
-{
-	if (test_bit(FLAG_MPI,&ai->flags))
-		reg <<= 1;
-	if (!do8bitIO)
-		outw(val, ai->dev->base_addr + reg);
-	else {
-		outb(val & 0xff, ai->dev->base_addr + reg);
-		outb(val >> 8, ai->dev->base_addr + reg + 1);
-	}
-}
-
-static u16 IN4500(struct airo_info *ai, u16 reg)
-{
-	unsigned short rc;
-
-	if (test_bit(FLAG_MPI,&ai->flags))
-		reg <<= 1;
-	if (!do8bitIO)
-		rc = inw(ai->dev->base_addr + reg);
-	else {
-		rc = inb(ai->dev->base_addr + reg);
-		rc += ((int)inb(ai->dev->base_addr + reg + 1)) << 8;
-	}
-	return rc;
-}
-
-static int enable_MAC(struct airo_info *ai, int lock)
-{
-	int rc;
-	Cmd cmd;
-	Resp rsp;
-
-	/* FLAG_RADIO_OFF : Radio disabled via /proc or Wireless Extensions
-	 * FLAG_RADIO_DOWN : Radio disabled via "ifconfig ethX down"
-	 * Note : we could try to use !netif_running(dev) in enable_MAC()
-	 * instead of this flag, but I don't trust it *within* the
-	 * open/close functions, and testing both flags together is
-	 * "cheaper" - Jean II */
-	if (ai->flags & FLAG_RADIO_MASK) return SUCCESS;
-
-	if (lock && down_interruptible(&ai->sem))
-		return -ERESTARTSYS;
-
-	if (!test_bit(FLAG_ENABLED, &ai->flags)) {
-		memset(&cmd, 0, sizeof(cmd));
-		cmd.cmd = MAC_ENABLE;
-		rc = issuecommand(ai, &cmd, &rsp, true);
-		if (rc == SUCCESS)
-			set_bit(FLAG_ENABLED, &ai->flags);
-	} else
-		rc = SUCCESS;
-
-	if (lock)
-	    up(&ai->sem);
-
-	if (rc)
-		airo_print_err(ai->dev->name, "Cannot enable MAC");
-	else if ((rsp.status & 0xFF00) != 0) {
-		airo_print_err(ai->dev->name, "Bad MAC enable reason=%x, "
-			"rid=%x, offset=%d", rsp.rsp0, rsp.rsp1, rsp.rsp2);
-		rc = ERROR;
-	}
-	return rc;
-}
-
-static void disable_MAC(struct airo_info *ai, int lock)
-{
-        Cmd cmd;
-	Resp rsp;
-
-	if (lock == 1 && down_interruptible(&ai->sem))
-		return;
-
-	if (test_bit(FLAG_ENABLED, &ai->flags)) {
-		if (lock != 2) /* lock == 2 means don't disable carrier */
-			netif_carrier_off(ai->dev);
-		memset(&cmd, 0, sizeof(cmd));
-		cmd.cmd = MAC_DISABLE; // disable in case already enabled
-		issuecommand(ai, &cmd, &rsp, true);
-		clear_bit(FLAG_ENABLED, &ai->flags);
-	}
-	if (lock == 1)
-		up(&ai->sem);
-}
-
-static void enable_interrupts(struct airo_info *ai)
-{
-	/* Enable the interrupts */
-	OUT4500(ai, EVINTEN, STATUS_INTS);
-}
-
-static void disable_interrupts(struct airo_info *ai)
-{
-	OUT4500(ai, EVINTEN, 0);
-}
-
-static void mpi_receive_802_3(struct airo_info *ai)
-{
-	RxFid rxd;
-	int len = 0;
-	struct sk_buff *skb;
-	char *buffer;
-	int off = 0;
-	MICBuffer micbuf;
-
-	memcpy_fromio(&rxd, ai->rxfids[0].card_ram_off, sizeof(rxd));
-	/* Make sure we got something */
-	if (rxd.rdy && rxd.valid == 0) {
-		len = rxd.len + 12;
-		if (len < 12 || len > 2048)
-			goto badrx;
-
-		skb = dev_alloc_skb(len);
-		if (!skb) {
-			ai->dev->stats.rx_dropped++;
-			goto badrx;
-		}
-		buffer = skb_put(skb, len);
-		memcpy(buffer, ai->rxfids[0].virtual_host_addr, ETH_ALEN * 2);
-		if (ai->micstats.enabled) {
-			memcpy(&micbuf,
-				ai->rxfids[0].virtual_host_addr + ETH_ALEN * 2,
-				sizeof(micbuf));
-			if (ntohs(micbuf.typelen) <= 0x05DC) {
-				if (len <= sizeof(micbuf) + ETH_ALEN * 2)
-					goto badmic;
-
-				off = sizeof(micbuf);
-				skb_trim (skb, len - off);
-			}
-		}
-		memcpy(buffer + ETH_ALEN * 2,
-			ai->rxfids[0].virtual_host_addr + ETH_ALEN * 2 + off,
-			len - ETH_ALEN * 2 - off);
-		if (decapsulate (ai, &micbuf, (etherHead*)buffer, len - off - ETH_ALEN * 2)) {
-badmic:
-			dev_kfree_skb_irq (skb);
-			goto badrx;
-		}
-#ifdef WIRELESS_SPY
-		if (ai->spy_data.spy_number > 0) {
-			char *sa;
-			struct iw_quality wstats;
-			/* Prepare spy data : addr + qual */
-			sa = buffer + ETH_ALEN;
-			wstats.qual = 0; /* XXX Where do I get that info from ??? */
-			wstats.level = 0;
-			wstats.updated = 0;
-			/* Update spy records */
-			wireless_spy_update(ai->dev, sa, &wstats);
-		}
-#endif /* WIRELESS_SPY */
-
-		skb->ip_summed = CHECKSUM_NONE;
-		skb->protocol = eth_type_trans(skb, ai->dev);
-		netif_rx(skb);
-	}
-badrx:
-	if (rxd.valid == 0) {
-		rxd.valid = 1;
-		rxd.rdy = 0;
-		rxd.len = PKTSIZE;
-		memcpy_toio(ai->rxfids[0].card_ram_off, &rxd, sizeof(rxd));
-	}
-}
-
-static void mpi_receive_802_11(struct airo_info *ai)
-{
-	RxFid rxd;
-	struct sk_buff *skb = NULL;
-	u16 len, hdrlen = 0;
-	__le16 fc;
-	struct rx_hdr hdr;
-	u16 gap;
-	u16 *buffer;
-	char *ptr = ai->rxfids[0].virtual_host_addr + 4;
-
-	memcpy_fromio(&rxd, ai->rxfids[0].card_ram_off, sizeof(rxd));
-	memcpy ((char *)&hdr, ptr, sizeof(hdr));
-	ptr += sizeof(hdr);
-	/* Bad CRC. Ignore packet */
-	if (le16_to_cpu(hdr.status) & 2)
-		hdr.len = 0;
-	if (ai->wifidev == NULL)
-		hdr.len = 0;
-	len = le16_to_cpu(hdr.len);
-	if (len > AIRO_DEF_MTU) {
-		airo_print_err(ai->dev->name, "Bad size %d", len);
-		goto badrx;
-	}
-	if (len == 0)
-		goto badrx;
-
-	fc = get_unaligned((__le16 *)ptr);
-	hdrlen = header_len(fc);
-
-	skb = dev_alloc_skb(len + hdrlen + 2);
-	if (!skb) {
-		ai->dev->stats.rx_dropped++;
-		goto badrx;
-	}
-	buffer = skb_put(skb, len + hdrlen);
-	memcpy ((char *)buffer, ptr, hdrlen);
-	ptr += hdrlen;
-	if (hdrlen == 24)
-		ptr += 6;
-	gap = get_unaligned_le16(ptr);
-	ptr += sizeof(__le16);
-	if (gap) {
-		if (gap <= 8)
-			ptr += gap;
-		else
-			airo_print_err(ai->dev->name,
-			    "gaplen too big. Problems will follow...");
-	}
-	memcpy ((char *)buffer + hdrlen, ptr, len);
-	ptr += len;
-#ifdef IW_WIRELESS_SPY	  /* defined in iw_handler.h */
-	if (ai->spy_data.spy_number > 0) {
-		char *sa;
-		struct iw_quality wstats;
-		/* Prepare spy data : addr + qual */
-		sa = (char*)buffer + 10;
-		wstats.qual = hdr.rssi[0];
-		if (ai->rssi)
-			wstats.level = 0x100 - ai->rssi[hdr.rssi[1]].rssidBm;
-		else
-			wstats.level = (hdr.rssi[1] + 321) / 2;
-		wstats.noise = ai->wstats.qual.noise;
-		wstats.updated = IW_QUAL_QUAL_UPDATED
-			| IW_QUAL_LEVEL_UPDATED
-			| IW_QUAL_DBM;
-		/* Update spy records */
-		wireless_spy_update(ai->dev, sa, &wstats);
-	}
-#endif /* IW_WIRELESS_SPY */
-	skb_reset_mac_header(skb);
-	skb->pkt_type = PACKET_OTHERHOST;
-	skb->dev = ai->wifidev;
-	skb->protocol = htons(ETH_P_802_2);
-	skb->ip_summed = CHECKSUM_NONE;
-	netif_rx(skb);
-
-badrx:
-	if (rxd.valid == 0) {
-		rxd.valid = 1;
-		rxd.rdy = 0;
-		rxd.len = PKTSIZE;
-		memcpy_toio(ai->rxfids[0].card_ram_off, &rxd, sizeof(rxd));
-	}
-}
-
-static inline void set_auth_type(struct airo_info *local, int auth_type)
-{
-	local->config.authType = auth_type;
-	/* Cache the last auth type used (of AUTH_OPEN and AUTH_ENCRYPT).
-	 * Used by airo_set_auth()
-	 */
-	if (auth_type == AUTH_OPEN || auth_type == AUTH_ENCRYPT)
-		local->last_auth = auth_type;
-}
-
-static int noinline_for_stack airo_readconfig(struct airo_info *ai,
-					      struct net_device *dev, int lock)
-{
-	int i, status;
-	/* large variables, so don't inline this function,
-	 * maybe change to kmalloc
-	 */
-	tdsRssiRid rssi_rid;
-	CapabilityRid cap_rid;
-
-	kfree(ai->SSID);
-	ai->SSID = NULL;
-	// general configuration (read/modify/write)
-	status = readConfigRid(ai, lock);
-	if (status != SUCCESS) return ERROR;
-
-	status = readCapabilityRid(ai, &cap_rid, lock);
-	if (status != SUCCESS) return ERROR;
-
-	status = PC4500_readrid(ai, RID_RSSI, &rssi_rid, sizeof(rssi_rid), lock);
-	if (status == SUCCESS) {
-		if (ai->rssi || (ai->rssi = kmalloc(512, GFP_KERNEL)) != NULL)
-			memcpy(ai->rssi, (u8*)&rssi_rid + 2, 512); /* Skip RID length member */
-	}
-	else {
-		kfree(ai->rssi);
-		ai->rssi = NULL;
-		if (cap_rid.softCap & cpu_to_le16(8))
-			ai->config.rmode |= RXMODE_NORMALIZED_RSSI;
-		else
-			airo_print_warn(ai->dev->name, "unknown received signal "
-					"level scale");
-	}
-	ai->config.opmode = adhoc ? MODE_STA_IBSS : MODE_STA_ESS;
-	set_auth_type(ai, AUTH_OPEN);
-	ai->config.modulation = MOD_CCK;
-
-	if (le16_to_cpu(cap_rid.len) >= sizeof(cap_rid) &&
-	    (cap_rid.extSoftCap & cpu_to_le16(1)) &&
-	    micsetup(ai) == SUCCESS) {
-		ai->config.opmode |= MODE_MIC;
-		set_bit(FLAG_MIC_CAPABLE, &ai->flags);
-	}
-
-	/* Save off the MAC */
-	eth_hw_addr_set(dev, ai->config.macAddr);
-
-	/* Check to see if there are any insmod configured
-	   rates to add */
-	if (rates[0]) {
-		memset(ai->config.rates, 0, sizeof(ai->config.rates));
-		for (i = 0; i < 8 && rates[i]; i++) {
-			ai->config.rates[i] = rates[i];
-		}
-	}
-	set_bit (FLAG_COMMIT, &ai->flags);
-
-	return SUCCESS;
-}
-
-
-static u16 setup_card(struct airo_info *ai, struct net_device *dev, int lock)
-{
-	Cmd cmd;
-	Resp rsp;
-	int status;
-	SsidRid mySsid;
-	__le16 lastindex;
-	WepKeyRid wkr;
-	int rc;
-
-	memset(&mySsid, 0, sizeof(mySsid));
-	kfree (ai->flash);
-	ai->flash = NULL;
-
-	/* The NOP is the first step in getting the card going */
-	cmd.cmd = NOP;
-	cmd.parm0 = cmd.parm1 = cmd.parm2 = 0;
-	if (lock && down_interruptible(&ai->sem))
-		return ERROR;
-	if (issuecommand(ai, &cmd, &rsp, true) != SUCCESS) {
-		if (lock)
-			up(&ai->sem);
-		return ERROR;
-	}
-	disable_MAC(ai, 0);
-
-	// Let's figure out if we need to use the AUX port
-	if (!test_bit(FLAG_MPI,&ai->flags)) {
-		cmd.cmd = CMD_ENABLEAUX;
-		if (issuecommand(ai, &cmd, &rsp, true) != SUCCESS) {
-			if (lock)
-				up(&ai->sem);
-			airo_print_err(ai->dev->name, "Error checking for AUX port");
-			return ERROR;
-		}
-		if (!aux_bap || rsp.status & 0xff00) {
-			ai->bap_read = fast_bap_read;
-			airo_print_dbg(ai->dev->name, "Doing fast bap_reads");
-		} else {
-			ai->bap_read = aux_bap_read;
-			airo_print_dbg(ai->dev->name, "Doing AUX bap_reads");
-		}
-	}
-	if (lock)
-		up(&ai->sem);
-	if (ai->config.len == 0) {
-		status = airo_readconfig(ai, dev, lock);
-		if (status != SUCCESS)
-			return ERROR;
-	}
-
-	/* Setup the SSIDs if present */
-	if (ssids[0]) {
-		int i;
-		for (i = 0; i < 3 && ssids[i]; i++) {
-			size_t len = strlen(ssids[i]);
-			if (len > 32)
-				len = 32;
-			mySsid.ssids[i].len = cpu_to_le16(len);
-			memcpy(mySsid.ssids[i].ssid, ssids[i], len);
-		}
-		mySsid.len = cpu_to_le16(sizeof(mySsid));
-	}
-
-	status = writeConfigRid(ai, lock);
-	if (status != SUCCESS) return ERROR;
-
-	/* Set up the SSID list */
-	if (ssids[0]) {
-		status = writeSsidRid(ai, &mySsid, lock);
-		if (status != SUCCESS) return ERROR;
-	}
-
-	status = enable_MAC(ai, lock);
-	if (status != SUCCESS)
-		return ERROR;
-
-	/* Grab the initial wep key, we gotta save it for auto_wep */
-	rc = readWepKeyRid(ai, &wkr, 1, lock);
-	if (rc == SUCCESS) do {
-		lastindex = wkr.kindex;
-		if (wkr.kindex == cpu_to_le16(0xffff)) {
-			ai->defindex = wkr.mac[0];
-		}
-		rc = readWepKeyRid(ai, &wkr, 0, lock);
-	} while (lastindex != wkr.kindex);
-
-	try_auto_wep(ai);
-
-	return SUCCESS;
-}
-
-static u16 issuecommand(struct airo_info *ai, Cmd *pCmd, Resp *pRsp,
-			bool may_sleep)
-{
-        // Im really paranoid about letting it run forever!
-	int max_tries = 600000;
-
-	if (IN4500(ai, EVSTAT) & EV_CMD)
-		OUT4500(ai, EVACK, EV_CMD);
-
-	OUT4500(ai, PARAM0, pCmd->parm0);
-	OUT4500(ai, PARAM1, pCmd->parm1);
-	OUT4500(ai, PARAM2, pCmd->parm2);
-	OUT4500(ai, COMMAND, pCmd->cmd);
-
-	while (max_tries-- && (IN4500(ai, EVSTAT) & EV_CMD) == 0) {
-		if ((IN4500(ai, COMMAND)) == pCmd->cmd)
-			// PC4500 didn't notice command, try again
-			OUT4500(ai, COMMAND, pCmd->cmd);
-		if (may_sleep && (max_tries & 255) == 0)
-			cond_resched();
-	}
-
-	if (max_tries == -1) {
-		airo_print_err(ai->dev->name,
-			"Max tries exceeded when issuing command");
-		if (IN4500(ai, COMMAND) & COMMAND_BUSY)
-			OUT4500(ai, EVACK, EV_CLEARCOMMANDBUSY);
-		return ERROR;
-	}
-
-	// command completed
-	pRsp->status = IN4500(ai, STATUS);
-	pRsp->rsp0 = IN4500(ai, RESP0);
-	pRsp->rsp1 = IN4500(ai, RESP1);
-	pRsp->rsp2 = IN4500(ai, RESP2);
-	if ((pRsp->status & 0xff00)!=0 && pCmd->cmd != CMD_SOFTRESET)
-		airo_print_err(ai->dev->name,
-			"cmd:%x status:%x rsp0:%x rsp1:%x rsp2:%x",
-			pCmd->cmd, pRsp->status, pRsp->rsp0, pRsp->rsp1,
-			pRsp->rsp2);
-
-	// clear stuck command busy if necessary
-	if (IN4500(ai, COMMAND) & COMMAND_BUSY) {
-		OUT4500(ai, EVACK, EV_CLEARCOMMANDBUSY);
-	}
-	// acknowledge processing the status/response
-	OUT4500(ai, EVACK, EV_CMD);
-
-	return SUCCESS;
-}
-
-/* Sets up the bap to start exchange data.  whichbap should
- * be one of the BAP0 or BAP1 defines.  Locks should be held before
- * calling! */
-static int bap_setup(struct airo_info *ai, u16 rid, u16 offset, int whichbap)
-{
-	int timeout = 50;
-	int max_tries = 3;
-
-	OUT4500(ai, SELECT0+whichbap, rid);
-	OUT4500(ai, OFFSET0+whichbap, offset);
-	while (1) {
-		int status = IN4500(ai, OFFSET0+whichbap);
-		if (status & BAP_BUSY) {
-                        /* This isn't really a timeout, but its kinda
-			   close */
-			if (timeout--) {
-				continue;
-			}
-		} else if (status & BAP_ERR) {
-			/* invalid rid or offset */
-			airo_print_err(ai->dev->name, "BAP error %x %d",
-				status, whichbap);
-			return ERROR;
-		} else if (status & BAP_DONE) { // success
-			return SUCCESS;
-		}
-		if (!(max_tries--)) {
-			airo_print_err(ai->dev->name,
-				"BAP setup error too many retries\n");
-			return ERROR;
-		}
-		// -- PC4500 missed it, try again
-		OUT4500(ai, SELECT0+whichbap, rid);
-		OUT4500(ai, OFFSET0+whichbap, offset);
-		timeout = 50;
-	}
-}
-
-/* should only be called by aux_bap_read.  This aux function and the
-   following use concepts not documented in the developers guide.  I
-   got them from a patch given to my by Aironet */
-static u16 aux_setup(struct airo_info *ai, u16 page,
-		     u16 offset, u16 *len)
-{
-	u16 next;
-
-	OUT4500(ai, AUXPAGE, page);
-	OUT4500(ai, AUXOFF, 0);
-	next = IN4500(ai, AUXDATA);
-	*len = IN4500(ai, AUXDATA)&0xff;
-	if (offset != 4) OUT4500(ai, AUXOFF, offset);
-	return next;
-}
-
-/* requires call to bap_setup() first */
-static int aux_bap_read(struct airo_info *ai, __le16 *pu16Dst,
-			int bytelen, int whichbap)
-{
-	u16 len;
-	u16 page;
-	u16 offset;
-	u16 next;
-	int words;
-	int i;
-	unsigned long flags;
-
-	spin_lock_irqsave(&ai->aux_lock, flags);
-	page = IN4500(ai, SWS0+whichbap);
-	offset = IN4500(ai, SWS2+whichbap);
-	next = aux_setup(ai, page, offset, &len);
-	words = (bytelen+1)>>1;
-
-	for (i = 0; i<words;) {
-		int count;
-		count = (len>>1) < (words-i) ? (len>>1) : (words-i);
-		if (!do8bitIO)
-			insw(ai->dev->base_addr+DATA0+whichbap,
-			      pu16Dst+i, count);
-		else
-			insb(ai->dev->base_addr+DATA0+whichbap,
-			      pu16Dst+i, count << 1);
-		i += count;
-		if (i<words) {
-			next = aux_setup(ai, next, 4, &len);
-		}
-	}
-	spin_unlock_irqrestore(&ai->aux_lock, flags);
-	return SUCCESS;
-}
-
-
-/* requires call to bap_setup() first */
-static int fast_bap_read(struct airo_info *ai, __le16 *pu16Dst,
-			 int bytelen, int whichbap)
-{
-	bytelen = (bytelen + 1) & (~1); // round up to even value
-	if (!do8bitIO)
-		insw(ai->dev->base_addr+DATA0+whichbap, pu16Dst, bytelen>>1);
-	else
-		insb(ai->dev->base_addr+DATA0+whichbap, pu16Dst, bytelen);
-	return SUCCESS;
-}
-
-/* requires call to bap_setup() first */
-static int bap_write(struct airo_info *ai, const __le16 *pu16Src,
-		     int bytelen, int whichbap)
-{
-	bytelen = (bytelen + 1) & (~1); // round up to even value
-	if (!do8bitIO)
-		outsw(ai->dev->base_addr+DATA0+whichbap,
-		       pu16Src, bytelen>>1);
-	else
-		outsb(ai->dev->base_addr+DATA0+whichbap, pu16Src, bytelen);
-	return SUCCESS;
-}
-
-static int PC4500_accessrid(struct airo_info *ai, u16 rid, u16 accmd)
-{
-	Cmd cmd; /* for issuing commands */
-	Resp rsp; /* response from commands */
-	u16 status;
-
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.cmd = accmd;
-	cmd.parm0 = rid;
-	status = issuecommand(ai, &cmd, &rsp, true);
-	if (status != 0) return status;
-	if ((rsp.status & 0x7F00) != 0) {
-		return (accmd << 8) + (rsp.rsp0 & 0xFF);
-	}
-	return 0;
-}
-
-/*  Note, that we are using BAP1 which is also used by transmit, so
- *  we must get a lock. */
-static int PC4500_readrid(struct airo_info *ai, u16 rid, void *pBuf, int len, int lock)
-{
-	u16 status;
-        int rc = SUCCESS;
-
-	if (lock) {
-		if (down_interruptible(&ai->sem))
-			return ERROR;
-	}
-	if (test_bit(FLAG_MPI,&ai->flags)) {
-		Cmd cmd;
-		Resp rsp;
-
-		memset(&cmd, 0, sizeof(cmd));
-		memset(&rsp, 0, sizeof(rsp));
-		ai->config_desc.rid_desc.valid = 1;
-		ai->config_desc.rid_desc.len = RIDSIZE;
-		ai->config_desc.rid_desc.rid = 0;
-		ai->config_desc.rid_desc.host_addr = ai->ridbus;
-
-		cmd.cmd = CMD_ACCESS;
-		cmd.parm0 = rid;
-
-		memcpy_toio(ai->config_desc.card_ram_off,
-			&ai->config_desc.rid_desc, sizeof(Rid));
-
-		rc = issuecommand(ai, &cmd, &rsp, true);
-
-		if (rsp.status & 0x7f00)
-			rc = rsp.rsp0;
-		if (!rc)
-			memcpy(pBuf, ai->config_desc.virtual_host_addr, len);
-		goto done;
-	} else {
-		if ((status = PC4500_accessrid(ai, rid, CMD_ACCESS))!=SUCCESS) {
-	                rc = status;
-	                goto done;
-	        }
-		if (bap_setup(ai, rid, 0, BAP1) != SUCCESS) {
-			rc = ERROR;
-	                goto done;
-	        }
-		// read the rid length field
-		bap_read(ai, pBuf, 2, BAP1);
-		// length for remaining part of rid
-		len = min(len, (int)le16_to_cpu(*(__le16*)pBuf)) - 2;
-
-		if (len <= 2) {
-			airo_print_err(ai->dev->name,
-				"Rid %x has a length of %d which is too short",
-				(int)rid, (int)len);
-			rc = ERROR;
-	                goto done;
-		}
-		// read remainder of the rid
-		rc = bap_read(ai, ((__le16*)pBuf)+1, len, BAP1);
-	}
-done:
-	if (lock)
-		up(&ai->sem);
-	return rc;
-}
-
-/*  Note, that we are using BAP1 which is also used by transmit, so
- *  make sure this isn't called when a transmit is happening */
-static int PC4500_writerid(struct airo_info *ai, u16 rid,
-			   const void *pBuf, int len, int lock)
-{
-	u16 status;
-	int rc = SUCCESS;
-
-	*(__le16*)pBuf = cpu_to_le16((u16)len);
-
-	if (lock) {
-		if (down_interruptible(&ai->sem))
-			return ERROR;
-	}
-	if (test_bit(FLAG_MPI,&ai->flags)) {
-		Cmd cmd;
-		Resp rsp;
-
-		if (test_bit(FLAG_ENABLED, &ai->flags) && (RID_WEP_TEMP != rid))
-			airo_print_err(ai->dev->name,
-				"%s: MAC should be disabled (rid=%04x)",
-				__func__, rid);
-		memset(&cmd, 0, sizeof(cmd));
-		memset(&rsp, 0, sizeof(rsp));
-
-		ai->config_desc.rid_desc.valid = 1;
-		ai->config_desc.rid_desc.len = *((u16 *)pBuf);
-		ai->config_desc.rid_desc.rid = 0;
-
-		cmd.cmd = CMD_WRITERID;
-		cmd.parm0 = rid;
-
-		memcpy_toio(ai->config_desc.card_ram_off,
-			&ai->config_desc.rid_desc, sizeof(Rid));
-
-		if (len < 4 || len > 2047) {
-			airo_print_err(ai->dev->name, "%s: len=%d", __func__, len);
-			rc = -1;
-		} else {
-			memcpy(ai->config_desc.virtual_host_addr,
-				pBuf, len);
-
-			rc = issuecommand(ai, &cmd, &rsp, true);
-			if ((rc & 0xff00) != 0) {
-				airo_print_err(ai->dev->name, "%s: Write rid Error %d",
-						__func__, rc);
-				airo_print_err(ai->dev->name, "%s: Cmd=%04x",
-						__func__, cmd.cmd);
-			}
-
-			if ((rsp.status & 0x7f00))
-				rc = rsp.rsp0;
-		}
-	} else {
-		// --- first access so that we can write the rid data
-		if ((status = PC4500_accessrid(ai, rid, CMD_ACCESS)) != 0) {
-	                rc = status;
-	                goto done;
-	        }
-		// --- now write the rid data
-		if (bap_setup(ai, rid, 0, BAP1) != SUCCESS) {
-	                rc = ERROR;
-	                goto done;
-	        }
-		bap_write(ai, pBuf, len, BAP1);
-		// ---now commit the rid data
-		rc = PC4500_accessrid(ai, rid, 0x100|CMD_ACCESS);
-	}
-done:
-	if (lock)
-		up(&ai->sem);
-        return rc;
-}
-
-/* Allocates a FID to be used for transmitting packets.  We only use
-   one for now. */
-static u16 transmit_allocate(struct airo_info *ai, int lenPayload, int raw)
-{
-	unsigned int loop = 3000;
-	Cmd cmd;
-	Resp rsp;
-	u16 txFid;
-	__le16 txControl;
-
-	cmd.cmd = CMD_ALLOCATETX;
-	cmd.parm0 = lenPayload;
-	if (down_interruptible(&ai->sem))
-		return ERROR;
-	if (issuecommand(ai, &cmd, &rsp, true) != SUCCESS) {
-		txFid = ERROR;
-		goto done;
-	}
-	if ((rsp.status & 0xFF00) != 0) {
-		txFid = ERROR;
-		goto done;
-	}
-	/* wait for the allocate event/indication
-	 * It makes me kind of nervous that this can just sit here and spin,
-	 * but in practice it only loops like four times. */
-	while (((IN4500(ai, EVSTAT) & EV_ALLOC) == 0) && --loop);
-	if (!loop) {
-		txFid = ERROR;
-		goto done;
-	}
-
-	// get the allocated fid and acknowledge
-	txFid = IN4500(ai, TXALLOCFID);
-	OUT4500(ai, EVACK, EV_ALLOC);
-
-	/*  The CARD is pretty cool since it converts the ethernet packet
-	 *  into 802.11.  Also note that we don't release the FID since we
-	 *  will be using the same one over and over again. */
-	/*  We only have to setup the control once since we are not
-	 *  releasing the fid. */
-	if (raw)
-		txControl = cpu_to_le16(TXCTL_TXOK | TXCTL_TXEX | TXCTL_802_11
-			| TXCTL_ETHERNET | TXCTL_NORELEASE);
-	else
-		txControl = cpu_to_le16(TXCTL_TXOK | TXCTL_TXEX | TXCTL_802_3
-			| TXCTL_ETHERNET | TXCTL_NORELEASE);
-	if (bap_setup(ai, txFid, 0x0008, BAP1) != SUCCESS)
-		txFid = ERROR;
-	else
-		bap_write(ai, &txControl, sizeof(txControl), BAP1);
-
-done:
-	up(&ai->sem);
-
-	return txFid;
-}
-
-/* In general BAP1 is dedicated to transmiting packets.  However,
-   since we need a BAP when accessing RIDs, we also use BAP1 for that.
-   Make sure the BAP1 spinlock is held when this is called. */
-static int transmit_802_3_packet(struct airo_info *ai, int len, char *pPacket,
-				 bool may_sleep)
-{
-	__le16 payloadLen;
-	Cmd cmd;
-	Resp rsp;
-	int miclen = 0;
-	u16 txFid = len;
-	MICBuffer pMic;
-
-	len >>= 16;
-
-	if (len <= ETH_ALEN * 2) {
-		airo_print_warn(ai->dev->name, "Short packet %d", len);
-		return ERROR;
-	}
-	len -= ETH_ALEN * 2;
-
-	if (test_bit(FLAG_MIC_CAPABLE, &ai->flags) && ai->micstats.enabled &&
-	    (ntohs(((__be16 *)pPacket)[6]) != 0x888E)) {
-		if (encapsulate(ai, (etherHead *)pPacket,&pMic, len) != SUCCESS)
-			return ERROR;
-		miclen = sizeof(pMic);
-	}
-	// packet is destination[6], source[6], payload[len-12]
-	// write the payload length and dst/src/payload
-	if (bap_setup(ai, txFid, 0x0036, BAP1) != SUCCESS) return ERROR;
-	/* The hardware addresses aren't counted as part of the payload, so
-	 * we have to subtract the 12 bytes for the addresses off */
-	payloadLen = cpu_to_le16(len + miclen);
-	bap_write(ai, &payloadLen, sizeof(payloadLen), BAP1);
-	bap_write(ai, (__le16*)pPacket, sizeof(etherHead), BAP1);
-	if (miclen)
-		bap_write(ai, (__le16*)&pMic, miclen, BAP1);
-	bap_write(ai, (__le16*)(pPacket + sizeof(etherHead)), len, BAP1);
-	// issue the transmit command
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.cmd = CMD_TRANSMIT;
-	cmd.parm0 = txFid;
-	if (issuecommand(ai, &cmd, &rsp, may_sleep) != SUCCESS)
-		return ERROR;
-	if ((rsp.status & 0xFF00) != 0) return ERROR;
-	return SUCCESS;
-}
-
-static int transmit_802_11_packet(struct airo_info *ai, int len, char *pPacket,
-				  bool may_sleep)
-{
-	__le16 fc, payloadLen;
-	Cmd cmd;
-	Resp rsp;
-	int hdrlen;
-	static u8 tail[(30-10) + 2 + 6] = {[30-10] = 6};
-	/* padding of header to full size + le16 gaplen (6) + gaplen bytes */
-	u16 txFid = len;
-	len >>= 16;
-
-	fc = *(__le16*)pPacket;
-	hdrlen = header_len(fc);
-
-	if (len < hdrlen) {
-		airo_print_warn(ai->dev->name, "Short packet %d", len);
-		return ERROR;
-	}
-
-	/* packet is 802.11 header +  payload
-	 * write the payload length and dst/src/payload */
-	if (bap_setup(ai, txFid, 6, BAP1) != SUCCESS) return ERROR;
-	/* The 802.11 header aren't counted as part of the payload, so
-	 * we have to subtract the header bytes off */
-	payloadLen = cpu_to_le16(len-hdrlen);
-	bap_write(ai, &payloadLen, sizeof(payloadLen), BAP1);
-	if (bap_setup(ai, txFid, 0x0014, BAP1) != SUCCESS) return ERROR;
-	bap_write(ai, (__le16 *)pPacket, hdrlen, BAP1);
-	bap_write(ai, (__le16 *)(tail + (hdrlen - 10)), 38 - hdrlen, BAP1);
-
-	bap_write(ai, (__le16 *)(pPacket + hdrlen), len - hdrlen, BAP1);
-	// issue the transmit command
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.cmd = CMD_TRANSMIT;
-	cmd.parm0 = txFid;
-	if (issuecommand(ai, &cmd, &rsp, may_sleep) != SUCCESS)
-		return ERROR;
-	if ((rsp.status & 0xFF00) != 0) return ERROR;
-	return SUCCESS;
-}
-
-/*
- *  This is the proc_fs routines.  It is a bit messier than I would
- *  like!  Feel free to clean it up!
- */
-
-static ssize_t proc_read(struct file *file,
-			  char __user *buffer,
-			  size_t len,
-			  loff_t *offset);
-
-static ssize_t proc_write(struct file *file,
-			   const char __user *buffer,
-			   size_t len,
-			   loff_t *offset);
-static int proc_close(struct inode *inode, struct file *file);
-
-static int proc_stats_open(struct inode *inode, struct file *file);
-static int proc_statsdelta_open(struct inode *inode, struct file *file);
-static int proc_status_open(struct inode *inode, struct file *file);
-static int proc_SSID_open(struct inode *inode, struct file *file);
-static int proc_APList_open(struct inode *inode, struct file *file);
-static int proc_BSSList_open(struct inode *inode, struct file *file);
-static int proc_config_open(struct inode *inode, struct file *file);
-static int proc_wepkey_open(struct inode *inode, struct file *file);
-
-static const struct proc_ops proc_statsdelta_ops = {
-	.proc_read	= proc_read,
-	.proc_open	= proc_statsdelta_open,
-	.proc_release	= proc_close,
-	.proc_lseek	= default_llseek,
-};
-
-static const struct proc_ops proc_stats_ops = {
-	.proc_read	= proc_read,
-	.proc_open	= proc_stats_open,
-	.proc_release	= proc_close,
-	.proc_lseek	= default_llseek,
-};
-
-static const struct proc_ops proc_status_ops = {
-	.proc_read	= proc_read,
-	.proc_open	= proc_status_open,
-	.proc_release	= proc_close,
-	.proc_lseek	= default_llseek,
-};
-
-static const struct proc_ops proc_SSID_ops = {
-	.proc_read	= proc_read,
-	.proc_write	= proc_write,
-	.proc_open	= proc_SSID_open,
-	.proc_release	= proc_close,
-	.proc_lseek	= default_llseek,
-};
-
-static const struct proc_ops proc_BSSList_ops = {
-	.proc_read	= proc_read,
-	.proc_write	= proc_write,
-	.proc_open	= proc_BSSList_open,
-	.proc_release	= proc_close,
-	.proc_lseek	= default_llseek,
-};
-
-static const struct proc_ops proc_APList_ops = {
-	.proc_read	= proc_read,
-	.proc_write	= proc_write,
-	.proc_open	= proc_APList_open,
-	.proc_release	= proc_close,
-	.proc_lseek	= default_llseek,
-};
-
-static const struct proc_ops proc_config_ops = {
-	.proc_read	= proc_read,
-	.proc_write	= proc_write,
-	.proc_open	= proc_config_open,
-	.proc_release	= proc_close,
-	.proc_lseek	= default_llseek,
-};
-
-static const struct proc_ops proc_wepkey_ops = {
-	.proc_read	= proc_read,
-	.proc_write	= proc_write,
-	.proc_open	= proc_wepkey_open,
-	.proc_release	= proc_close,
-	.proc_lseek	= default_llseek,
-};
-
-static struct proc_dir_entry *airo_entry;
-
-struct proc_data {
-	int release_buffer;
-	int readlen;
-	char *rbuffer;
-	int writelen;
-	int maxwritelen;
-	char *wbuffer;
-	void (*on_close) (struct inode *, struct file *);
-};
-
-static int setup_proc_entry(struct net_device *dev,
-			     struct airo_info *apriv)
-{
-	struct proc_dir_entry *entry;
-
-	/* First setup the device directory */
-	strcpy(apriv->proc_name, dev->name);
-	apriv->proc_entry = proc_mkdir_mode(apriv->proc_name, airo_perm,
-					    airo_entry);
-	if (!apriv->proc_entry)
-		return -ENOMEM;
-	proc_set_user(apriv->proc_entry, proc_kuid, proc_kgid);
-
-	/* Setup the StatsDelta */
-	entry = proc_create_data("StatsDelta", 0444 & proc_perm,
-				 apriv->proc_entry, &proc_statsdelta_ops, dev);
-	if (!entry)
-		goto fail;
-	proc_set_user(entry, proc_kuid, proc_kgid);
-
-	/* Setup the Stats */
-	entry = proc_create_data("Stats", 0444 & proc_perm,
-				 apriv->proc_entry, &proc_stats_ops, dev);
-	if (!entry)
-		goto fail;
-	proc_set_user(entry, proc_kuid, proc_kgid);
-
-	/* Setup the Status */
-	entry = proc_create_data("Status", 0444 & proc_perm,
-				 apriv->proc_entry, &proc_status_ops, dev);
-	if (!entry)
-		goto fail;
-	proc_set_user(entry, proc_kuid, proc_kgid);
-
-	/* Setup the Config */
-	entry = proc_create_data("Config", proc_perm,
-				 apriv->proc_entry, &proc_config_ops, dev);
-	if (!entry)
-		goto fail;
-	proc_set_user(entry, proc_kuid, proc_kgid);
-
-	/* Setup the SSID */
-	entry = proc_create_data("SSID", proc_perm,
-				 apriv->proc_entry, &proc_SSID_ops, dev);
-	if (!entry)
-		goto fail;
-	proc_set_user(entry, proc_kuid, proc_kgid);
-
-	/* Setup the APList */
-	entry = proc_create_data("APList", proc_perm,
-				 apriv->proc_entry, &proc_APList_ops, dev);
-	if (!entry)
-		goto fail;
-	proc_set_user(entry, proc_kuid, proc_kgid);
-
-	/* Setup the BSSList */
-	entry = proc_create_data("BSSList", proc_perm,
-				 apriv->proc_entry, &proc_BSSList_ops, dev);
-	if (!entry)
-		goto fail;
-	proc_set_user(entry, proc_kuid, proc_kgid);
-
-	/* Setup the WepKey */
-	entry = proc_create_data("WepKey", proc_perm,
-				 apriv->proc_entry, &proc_wepkey_ops, dev);
-	if (!entry)
-		goto fail;
-	proc_set_user(entry, proc_kuid, proc_kgid);
-	return 0;
-
-fail:
-	remove_proc_subtree(apriv->proc_name, airo_entry);
-	return -ENOMEM;
-}
-
-static int takedown_proc_entry(struct net_device *dev,
-				struct airo_info *apriv)
-{
-	remove_proc_subtree(apriv->proc_name, airo_entry);
-	return 0;
-}
-
-/*
- *  What we want from the proc_fs is to be able to efficiently read
- *  and write the configuration.  To do this, we want to read the
- *  configuration when the file is opened and write it when the file is
- *  closed.  So basically we allocate a read buffer at open and fill it
- *  with data, and allocate a write buffer and read it at close.
- */
-
-/*
- *  The read routine is generic, it relies on the preallocated rbuffer
- *  to supply the data.
- */
-static ssize_t proc_read(struct file *file,
-			  char __user *buffer,
-			  size_t len,
-			  loff_t *offset)
-{
-	struct proc_data *priv = file->private_data;
-
-	if (!priv->rbuffer)
-		return -EINVAL;
-
-	return simple_read_from_buffer(buffer, len, offset, priv->rbuffer,
-					priv->readlen);
-}
-
-/*
- *  The write routine is generic, it fills in a preallocated rbuffer
- *  to supply the data.
- */
-static ssize_t proc_write(struct file *file,
-			   const char __user *buffer,
-			   size_t len,
-			   loff_t *offset)
-{
-	ssize_t ret;
-	struct proc_data *priv = file->private_data;
-
-	if (!priv->wbuffer)
-		return -EINVAL;
-
-	ret = simple_write_to_buffer(priv->wbuffer, priv->maxwritelen, offset,
-					buffer, len);
-	if (ret > 0)
-		priv->writelen = max_t(int, priv->writelen, *offset);
-
-	return ret;
-}
-
-static int proc_status_open(struct inode *inode, struct file *file)
-{
-	struct proc_data *data;
-	struct net_device *dev = pde_data(inode);
-	struct airo_info *apriv = dev->ml_priv;
-	CapabilityRid cap_rid;
-	StatusRid status_rid;
-	u16 mode;
-	int i;
-
-	if ((file->private_data = kzalloc(sizeof(struct proc_data), GFP_KERNEL)) == NULL)
-		return -ENOMEM;
-	data = file->private_data;
-	if ((data->rbuffer = kmalloc(2048, GFP_KERNEL)) == NULL) {
-		kfree (file->private_data);
-		return -ENOMEM;
-	}
-
-	readStatusRid(apriv, &status_rid, 1);
-	readCapabilityRid(apriv, &cap_rid, 1);
-
-	mode = le16_to_cpu(status_rid.mode);
-
-        i = sprintf(data->rbuffer, "Status: %s%s%s%s%s%s%s%s%s\n",
-                    mode & 1 ? "CFG ": "",
-                    mode & 2 ? "ACT ": "",
-                    mode & 0x10 ? "SYN ": "",
-                    mode & 0x20 ? "LNK ": "",
-                    mode & 0x40 ? "LEAP ": "",
-                    mode & 0x80 ? "PRIV ": "",
-                    mode & 0x100 ? "KEY ": "",
-                    mode & 0x200 ? "WEP ": "",
-                    mode & 0x8000 ? "ERR ": "");
-	sprintf(data->rbuffer+i, "Mode: %x\n"
-		 "Signal Strength: %d\n"
-		 "Signal Quality: %d\n"
-		 "SSID: %-.*s\n"
-		 "AP: %-.16s\n"
-		 "Freq: %d\n"
-		 "BitRate: %dmbs\n"
-		 "Driver Version: %s\n"
-		 "Device: %s\nManufacturer: %s\nFirmware Version: %s\n"
-		 "Radio type: %x\nCountry: %x\nHardware Version: %x\n"
-		 "Software Version: %x\nSoftware Subversion: %x\n"
-		 "Boot block version: %x\n",
-		 le16_to_cpu(status_rid.mode),
-		 le16_to_cpu(status_rid.normalizedSignalStrength),
-		 le16_to_cpu(status_rid.signalQuality),
-		 le16_to_cpu(status_rid.SSIDlen),
-		 status_rid.SSID,
-		 status_rid.apName,
-		 le16_to_cpu(status_rid.channel),
-		 le16_to_cpu(status_rid.currentXmitRate) / 2,
-		 version,
-		 cap_rid.prodName,
-		 cap_rid.manName,
-		 cap_rid.prodVer,
-		 le16_to_cpu(cap_rid.radioType),
-		 le16_to_cpu(cap_rid.country),
-		 le16_to_cpu(cap_rid.hardVer),
-		 le16_to_cpu(cap_rid.softVer),
-		 le16_to_cpu(cap_rid.softSubVer),
-		 le16_to_cpu(cap_rid.bootBlockVer));
-	data->readlen = strlen(data->rbuffer);
-	return 0;
-}
-
-static int proc_stats_rid_open(struct inode*, struct file*, u16);
-static int proc_statsdelta_open(struct inode *inode,
-				 struct file *file)
-{
-	if (file->f_mode&FMODE_WRITE) {
-		return proc_stats_rid_open(inode, file, RID_STATSDELTACLEAR);
-	}
-	return proc_stats_rid_open(inode, file, RID_STATSDELTA);
-}
-
-static int proc_stats_open(struct inode *inode, struct file *file)
-{
-	return proc_stats_rid_open(inode, file, RID_STATS);
-}
-
-static int proc_stats_rid_open(struct inode *inode,
-				struct file *file,
-				u16 rid)
-{
-	struct proc_data *data;
-	struct net_device *dev = pde_data(inode);
-	struct airo_info *apriv = dev->ml_priv;
-	StatsRid stats;
-	int i, j;
-	__le32 *vals = stats.vals;
-	int len;
-
-	if ((file->private_data = kzalloc(sizeof(struct proc_data), GFP_KERNEL)) == NULL)
-		return -ENOMEM;
-	data = file->private_data;
-	if ((data->rbuffer = kmalloc(4096, GFP_KERNEL)) == NULL) {
-		kfree (file->private_data);
-		return -ENOMEM;
-	}
-
-	readStatsRid(apriv, &stats, rid, 1);
-	len = le16_to_cpu(stats.len);
-
-        j = 0;
-	for (i = 0; statsLabels[i]!=(char *)-1 && i*4<len; i++) {
-		if (!statsLabels[i]) continue;
-		if (j+strlen(statsLabels[i])+16>4096) {
-			airo_print_warn(apriv->dev->name,
-			       "Potentially disastrous buffer overflow averted!");
-			break;
-		}
-		j+=sprintf(data->rbuffer+j, "%s: %u\n", statsLabels[i],
-				le32_to_cpu(vals[i]));
-	}
-	if (i*4 >= len) {
-		airo_print_warn(apriv->dev->name, "Got a short rid");
-	}
-	data->readlen = j;
-	return 0;
-}
-
-static int get_dec_u16(char *buffer, int *start, int limit)
-{
-	u16 value;
-	int valid = 0;
-	for (value = 0; *start < limit && buffer[*start] >= '0' &&
-			buffer[*start] <= '9'; (*start)++) {
-		valid = 1;
-		value *= 10;
-		value += buffer[*start] - '0';
-	}
-	if (!valid) return -1;
-	return value;
-}
-
-static int airo_config_commit(struct net_device *dev,
-			      struct iw_request_info *info,
-			      union iwreq_data *wrqu,
-			      char *extra);
-
-static inline int sniffing_mode(struct airo_info *ai)
-{
-	return (le16_to_cpu(ai->config.rmode) & le16_to_cpu(RXMODE_MASK)) >=
-		le16_to_cpu(RXMODE_RFMON);
-}
-
-static void proc_config_on_close(struct inode *inode, struct file *file)
-{
-	struct proc_data *data = file->private_data;
-	struct net_device *dev = pde_data(inode);
-	struct airo_info *ai = dev->ml_priv;
-	char *line;
-
-	if (!data->writelen) return;
-
-	readConfigRid(ai, 1);
-	set_bit (FLAG_COMMIT, &ai->flags);
-
-	line = data->wbuffer;
-	while (line[0]) {
-/*** Mode processing */
-		if (!strncmp(line, "Mode: ", 6)) {
-			line += 6;
-			if (sniffing_mode(ai))
-				set_bit (FLAG_RESET, &ai->flags);
-			ai->config.rmode &= ~RXMODE_FULL_MASK;
-			clear_bit (FLAG_802_11, &ai->flags);
-			ai->config.opmode &= ~MODE_CFG_MASK;
-			ai->config.scanMode = SCANMODE_ACTIVE;
-			if (line[0] == 'a') {
-				ai->config.opmode |= MODE_STA_IBSS;
-			} else {
-				ai->config.opmode |= MODE_STA_ESS;
-				if (line[0] == 'r') {
-					ai->config.rmode |= RXMODE_RFMON | RXMODE_DISABLE_802_3_HEADER;
-					ai->config.scanMode = SCANMODE_PASSIVE;
-					set_bit (FLAG_802_11, &ai->flags);
-				} else if (line[0] == 'y') {
-					ai->config.rmode |= RXMODE_RFMON_ANYBSS | RXMODE_DISABLE_802_3_HEADER;
-					ai->config.scanMode = SCANMODE_PASSIVE;
-					set_bit (FLAG_802_11, &ai->flags);
-				} else if (line[0] == 'l')
-					ai->config.rmode |= RXMODE_LANMON;
-			}
-			set_bit (FLAG_COMMIT, &ai->flags);
-		}
-
-/*** Radio status */
-		else if (!strncmp(line,"Radio: ", 7)) {
-			line += 7;
-			if (!strncmp(line,"off", 3)) {
-				set_bit (FLAG_RADIO_OFF, &ai->flags);
-			} else {
-				clear_bit (FLAG_RADIO_OFF, &ai->flags);
-			}
-		}
-/*** NodeName processing */
-		else if (!strncmp(line, "NodeName: ", 10)) {
-			int j;
-
-			line += 10;
-			memset(ai->config.nodeName, 0, 16);
-/* Do the name, assume a space between the mode and node name */
-			for (j = 0; j < 16 && line[j] != '\n'; j++) {
-				ai->config.nodeName[j] = line[j];
-			}
-			set_bit (FLAG_COMMIT, &ai->flags);
-		}
-
-/*** PowerMode processing */
-		else if (!strncmp(line, "PowerMode: ", 11)) {
-			line += 11;
-			if (!strncmp(line, "PSPCAM", 6)) {
-				ai->config.powerSaveMode = POWERSAVE_PSPCAM;
-				set_bit (FLAG_COMMIT, &ai->flags);
-			} else if (!strncmp(line, "PSP", 3)) {
-				ai->config.powerSaveMode = POWERSAVE_PSP;
-				set_bit (FLAG_COMMIT, &ai->flags);
-			} else {
-				ai->config.powerSaveMode = POWERSAVE_CAM;
-				set_bit (FLAG_COMMIT, &ai->flags);
-			}
-		} else if (!strncmp(line, "DataRates: ", 11)) {
-			int v, i = 0, k = 0; /* i is index into line,
-						k is index to rates */
-
-			line += 11;
-			while ((v = get_dec_u16(line, &i, 3))!=-1) {
-				ai->config.rates[k++] = (u8)v;
-				line += i + 1;
-				i = 0;
-			}
-			set_bit (FLAG_COMMIT, &ai->flags);
-		} else if (!strncmp(line, "Channel: ", 9)) {
-			int v, i = 0;
-			line += 9;
-			v = get_dec_u16(line, &i, i+3);
-			if (v != -1) {
-				ai->config.channelSet = cpu_to_le16(v);
-				set_bit (FLAG_COMMIT, &ai->flags);
-			}
-		} else if (!strncmp(line, "XmitPower: ", 11)) {
-			int v, i = 0;
-			line += 11;
-			v = get_dec_u16(line, &i, i+3);
-			if (v != -1) {
-				ai->config.txPower = cpu_to_le16(v);
-				set_bit (FLAG_COMMIT, &ai->flags);
-			}
-		} else if (!strncmp(line, "WEP: ", 5)) {
-			line += 5;
-			switch(line[0]) {
-			case 's':
-				set_auth_type(ai, AUTH_SHAREDKEY);
-				break;
-			case 'e':
-				set_auth_type(ai, AUTH_ENCRYPT);
-				break;
-			default:
-				set_auth_type(ai, AUTH_OPEN);
-				break;
-			}
-			set_bit (FLAG_COMMIT, &ai->flags);
-		} else if (!strncmp(line, "LongRetryLimit: ", 16)) {
-			int v, i = 0;
-
-			line += 16;
-			v = get_dec_u16(line, &i, 3);
-			v = (v<0) ? 0 : ((v>255) ? 255 : v);
-			ai->config.longRetryLimit = cpu_to_le16(v);
-			set_bit (FLAG_COMMIT, &ai->flags);
-		} else if (!strncmp(line, "ShortRetryLimit: ", 17)) {
-			int v, i = 0;
-
-			line += 17;
-			v = get_dec_u16(line, &i, 3);
-			v = (v<0) ? 0 : ((v>255) ? 255 : v);
-			ai->config.shortRetryLimit = cpu_to_le16(v);
-			set_bit (FLAG_COMMIT, &ai->flags);
-		} else if (!strncmp(line, "RTSThreshold: ", 14)) {
-			int v, i = 0;
-
-			line += 14;
-			v = get_dec_u16(line, &i, 4);
-			v = (v<0) ? 0 : ((v>AIRO_DEF_MTU) ? AIRO_DEF_MTU : v);
-			ai->config.rtsThres = cpu_to_le16(v);
-			set_bit (FLAG_COMMIT, &ai->flags);
-		} else if (!strncmp(line, "TXMSDULifetime: ", 16)) {
-			int v, i = 0;
-
-			line += 16;
-			v = get_dec_u16(line, &i, 5);
-			v = (v<0) ? 0 : v;
-			ai->config.txLifetime = cpu_to_le16(v);
-			set_bit (FLAG_COMMIT, &ai->flags);
-		} else if (!strncmp(line, "RXMSDULifetime: ", 16)) {
-			int v, i = 0;
-
-			line += 16;
-			v = get_dec_u16(line, &i, 5);
-			v = (v<0) ? 0 : v;
-			ai->config.rxLifetime = cpu_to_le16(v);
-			set_bit (FLAG_COMMIT, &ai->flags);
-		} else if (!strncmp(line, "TXDiversity: ", 13)) {
-			ai->config.txDiversity =
-				(line[13]=='l') ? 1 :
-				((line[13]=='r')? 2: 3);
-			set_bit (FLAG_COMMIT, &ai->flags);
-		} else if (!strncmp(line, "RXDiversity: ", 13)) {
-			ai->config.rxDiversity =
-				(line[13]=='l') ? 1 :
-				((line[13]=='r')? 2: 3);
-			set_bit (FLAG_COMMIT, &ai->flags);
-		} else if (!strncmp(line, "FragThreshold: ", 15)) {
-			int v, i = 0;
-
-			line += 15;
-			v = get_dec_u16(line, &i, 4);
-			v = (v<256) ? 256 : ((v>AIRO_DEF_MTU) ? AIRO_DEF_MTU : v);
-			v = v & 0xfffe; /* Make sure its even */
-			ai->config.fragThresh = cpu_to_le16(v);
-			set_bit (FLAG_COMMIT, &ai->flags);
-		} else if (!strncmp(line, "Modulation: ", 12)) {
-			line += 12;
-			switch(*line) {
-			case 'd':  ai->config.modulation = MOD_DEFAULT; set_bit(FLAG_COMMIT, &ai->flags); break;
-			case 'c':  ai->config.modulation = MOD_CCK; set_bit(FLAG_COMMIT, &ai->flags); break;
-			case 'm':  ai->config.modulation = MOD_MOK; set_bit(FLAG_COMMIT, &ai->flags); break;
-			default: airo_print_warn(ai->dev->name, "Unknown modulation");
-			}
-		} else if (!strncmp(line, "Preamble: ", 10)) {
-			line += 10;
-			switch(*line) {
-			case 'a': ai->config.preamble = PREAMBLE_AUTO; set_bit(FLAG_COMMIT, &ai->flags); break;
-			case 'l': ai->config.preamble = PREAMBLE_LONG; set_bit(FLAG_COMMIT, &ai->flags); break;
-			case 's': ai->config.preamble = PREAMBLE_SHORT; set_bit(FLAG_COMMIT, &ai->flags); break;
-			default: airo_print_warn(ai->dev->name, "Unknown preamble");
-			}
-		} else {
-			airo_print_warn(ai->dev->name, "Couldn't figure out %s", line);
-		}
-		while (line[0] && line[0] != '\n') line++;
-		if (line[0]) line++;
-	}
-	airo_config_commit(dev, NULL, NULL, NULL);
-}
-
-static const char *get_rmode(__le16 mode)
-{
-        switch(mode & RXMODE_MASK) {
-        case RXMODE_RFMON:  return "rfmon";
-        case RXMODE_RFMON_ANYBSS:  return "yna (any) bss rfmon";
-        case RXMODE_LANMON:  return "lanmon";
-        }
-        return "ESS";
-}
-
-static int proc_config_open(struct inode *inode, struct file *file)
-{
-	struct proc_data *data;
-	struct net_device *dev = pde_data(inode);
-	struct airo_info *ai = dev->ml_priv;
-	int i;
-	__le16 mode;
-
-	if ((file->private_data = kzalloc(sizeof(struct proc_data), GFP_KERNEL)) == NULL)
-		return -ENOMEM;
-	data = file->private_data;
-	if ((data->rbuffer = kmalloc(2048, GFP_KERNEL)) == NULL) {
-		kfree (file->private_data);
-		return -ENOMEM;
-	}
-	if ((data->wbuffer = kzalloc(2048, GFP_KERNEL)) == NULL) {
-		kfree (data->rbuffer);
-		kfree (file->private_data);
-		return -ENOMEM;
-	}
-	data->maxwritelen = 2048;
-	data->on_close = proc_config_on_close;
-
-	readConfigRid(ai, 1);
-
-	mode = ai->config.opmode & MODE_CFG_MASK;
-	i = sprintf(data->rbuffer,
-		     "Mode: %s\n"
-		     "Radio: %s\n"
-		     "NodeName: %-16s\n"
-		     "PowerMode: %s\n"
-		     "DataRates: %d %d %d %d %d %d %d %d\n"
-		     "Channel: %d\n"
-		     "XmitPower: %d\n",
-		     mode == MODE_STA_IBSS ? "adhoc" :
-		     mode == MODE_STA_ESS ? get_rmode(ai->config.rmode):
-		     mode == MODE_AP ? "AP" :
-		     mode == MODE_AP_RPTR ? "AP RPTR" : "Error",
-		     test_bit(FLAG_RADIO_OFF, &ai->flags) ? "off" : "on",
-		     ai->config.nodeName,
-		     ai->config.powerSaveMode == POWERSAVE_CAM ? "CAM" :
-		     ai->config.powerSaveMode == POWERSAVE_PSP ? "PSP" :
-		     ai->config.powerSaveMode == POWERSAVE_PSPCAM ? "PSPCAM" :
-		     "Error",
-		     (int)ai->config.rates[0],
-		     (int)ai->config.rates[1],
-		     (int)ai->config.rates[2],
-		     (int)ai->config.rates[3],
-		     (int)ai->config.rates[4],
-		     (int)ai->config.rates[5],
-		     (int)ai->config.rates[6],
-		     (int)ai->config.rates[7],
-		     le16_to_cpu(ai->config.channelSet),
-		     le16_to_cpu(ai->config.txPower)
-		);
-	sprintf(data->rbuffer + i,
-		 "LongRetryLimit: %d\n"
-		 "ShortRetryLimit: %d\n"
-		 "RTSThreshold: %d\n"
-		 "TXMSDULifetime: %d\n"
-		 "RXMSDULifetime: %d\n"
-		 "TXDiversity: %s\n"
-		 "RXDiversity: %s\n"
-		 "FragThreshold: %d\n"
-		 "WEP: %s\n"
-		 "Modulation: %s\n"
-		 "Preamble: %s\n",
-		 le16_to_cpu(ai->config.longRetryLimit),
-		 le16_to_cpu(ai->config.shortRetryLimit),
-		 le16_to_cpu(ai->config.rtsThres),
-		 le16_to_cpu(ai->config.txLifetime),
-		 le16_to_cpu(ai->config.rxLifetime),
-		 ai->config.txDiversity == 1 ? "left" :
-		 ai->config.txDiversity == 2 ? "right" : "both",
-		 ai->config.rxDiversity == 1 ? "left" :
-		 ai->config.rxDiversity == 2 ? "right" : "both",
-		 le16_to_cpu(ai->config.fragThresh),
-		 ai->config.authType == AUTH_ENCRYPT ? "encrypt" :
-		 ai->config.authType == AUTH_SHAREDKEY ? "shared" : "open",
-		 ai->config.modulation == MOD_DEFAULT ? "default" :
-		 ai->config.modulation == MOD_CCK ? "cck" :
-		 ai->config.modulation == MOD_MOK ? "mok" : "error",
-		 ai->config.preamble == PREAMBLE_AUTO ? "auto" :
-		 ai->config.preamble == PREAMBLE_LONG ? "long" :
-		 ai->config.preamble == PREAMBLE_SHORT ? "short" : "error"
-		);
-	data->readlen = strlen(data->rbuffer);
-	return 0;
-}
-
-static void proc_SSID_on_close(struct inode *inode, struct file *file)
-{
-	struct proc_data *data = file->private_data;
-	struct net_device *dev = pde_data(inode);
-	struct airo_info *ai = dev->ml_priv;
-	SsidRid SSID_rid;
-	int i;
-	char *p = data->wbuffer;
-	char *end = p + data->writelen;
-
-	if (!data->writelen)
-		return;
-
-	*end = '\n'; /* sentinel; we have space for it */
-
-	memset(&SSID_rid, 0, sizeof(SSID_rid));
-
-	for (i = 0; i < 3 && p < end; i++) {
-		int j = 0;
-		/* copy up to 32 characters from this line */
-		while (*p != '\n' && j < 32)
-			SSID_rid.ssids[i].ssid[j++] = *p++;
-		if (j == 0)
-			break;
-		SSID_rid.ssids[i].len = cpu_to_le16(j);
-		/* skip to the beginning of the next line */
-		while (*p++ != '\n')
-			;
-	}
-	if (i)
-		SSID_rid.len = cpu_to_le16(sizeof(SSID_rid));
-	disable_MAC(ai, 1);
-	writeSsidRid(ai, &SSID_rid, 1);
-	enable_MAC(ai, 1);
-}
-
-static void proc_APList_on_close(struct inode *inode, struct file *file)
-{
-	struct proc_data *data = file->private_data;
-	struct net_device *dev = pde_data(inode);
-	struct airo_info *ai = dev->ml_priv;
-	APListRid *APList_rid = &ai->APList;
-	int i;
-
-	if (!data->writelen) return;
-
-	memset(APList_rid, 0, sizeof(*APList_rid));
-	APList_rid->len = cpu_to_le16(sizeof(*APList_rid));
-
-	for (i = 0; i < 4 && data->writelen >= (i + 1) * 6 * 3; i++)
-		mac_pton(data->wbuffer + i * 6 * 3, APList_rid->ap[i]);
-
-	disable_MAC(ai, 1);
-	writeAPListRid(ai, APList_rid, 1);
-	enable_MAC(ai, 1);
-}
-
-/* This function wraps PC4500_writerid with a MAC disable */
-static int do_writerid(struct airo_info *ai, u16 rid, const void *rid_data,
-			int len, int dummy)
-{
-	int rc;
-
-	disable_MAC(ai, 1);
-	rc = PC4500_writerid(ai, rid, rid_data, len, 1);
-	enable_MAC(ai, 1);
-	return rc;
-}
-
-/* Returns the WEP key at the specified index, or -1 if that key does
- * not exist.  The buffer is assumed to be at least 16 bytes in length.
- */
-static int get_wep_key(struct airo_info *ai, u16 index, char *buf, u16 buflen)
-{
-	WepKeyRid wkr;
-	int rc;
-	__le16 lastindex;
-
-	rc = readWepKeyRid(ai, &wkr, 1, 1);
-	if (rc != SUCCESS)
-		return -1;
-	do {
-		lastindex = wkr.kindex;
-		if (le16_to_cpu(wkr.kindex) == index) {
-			int klen = min_t(int, buflen, le16_to_cpu(wkr.klen));
-			memcpy(buf, wkr.key, klen);
-			return klen;
-		}
-		rc = readWepKeyRid(ai, &wkr, 0, 1);
-		if (rc != SUCCESS)
-			return -1;
-	} while (lastindex != wkr.kindex);
-	return -1;
-}
-
-static int get_wep_tx_idx(struct airo_info *ai)
-{
-	WepKeyRid wkr;
-	int rc;
-	__le16 lastindex;
-
-	rc = readWepKeyRid(ai, &wkr, 1, 1);
-	if (rc != SUCCESS)
-		return -1;
-	do {
-		lastindex = wkr.kindex;
-		if (wkr.kindex == cpu_to_le16(0xffff))
-			return wkr.mac[0];
-		rc = readWepKeyRid(ai, &wkr, 0, 1);
-		if (rc != SUCCESS)
-			return -1;
-	} while (lastindex != wkr.kindex);
-	return -1;
-}
-
-static int set_wep_key(struct airo_info *ai, u16 index, const u8 *key,
-		       u16 keylen, int perm, int lock)
-{
-	static const unsigned char macaddr[ETH_ALEN] = { 0x01, 0, 0, 0, 0, 0 };
-	WepKeyRid wkr;
-	int rc;
-
-	if (WARN_ON(keylen == 0))
-		return -1;
-
-	memset(&wkr, 0, sizeof(wkr));
-	wkr.len = cpu_to_le16(sizeof(wkr));
-	wkr.kindex = cpu_to_le16(index);
-	wkr.klen = cpu_to_le16(keylen);
-	memcpy(wkr.key, key, keylen);
-	memcpy(wkr.mac, macaddr, ETH_ALEN);
-
-	if (perm) disable_MAC(ai, lock);
-	rc = writeWepKeyRid(ai, &wkr, perm, lock);
-	if (perm) enable_MAC(ai, lock);
-	return rc;
-}
-
-static int set_wep_tx_idx(struct airo_info *ai, u16 index, int perm, int lock)
-{
-	WepKeyRid wkr;
-	int rc;
-
-	memset(&wkr, 0, sizeof(wkr));
-	wkr.len = cpu_to_le16(sizeof(wkr));
-	wkr.kindex = cpu_to_le16(0xffff);
-	wkr.mac[0] = (char)index;
-
-	if (perm) {
-		ai->defindex = (char)index;
-		disable_MAC(ai, lock);
-	}
-
-	rc = writeWepKeyRid(ai, &wkr, perm, lock);
-
-	if (perm)
-		enable_MAC(ai, lock);
-	return rc;
-}
-
-static void proc_wepkey_on_close(struct inode *inode, struct file *file)
-{
-	struct proc_data *data;
-	struct net_device *dev = pde_data(inode);
-	struct airo_info *ai = dev->ml_priv;
-	int i, rc;
-	u8 key[16];
-	u16 index = 0;
-	int j = 0;
-
-	memset(key, 0, sizeof(key));
-
-	data = file->private_data;
-	if (!data->writelen) return;
-
-	if (data->wbuffer[0] >= '0' && data->wbuffer[0] <= '3' &&
-	    (data->wbuffer[1] == ' ' || data->wbuffer[1] == '\n')) {
-		index = data->wbuffer[0] - '0';
-		if (data->wbuffer[1] == '\n') {
-			rc = set_wep_tx_idx(ai, index, 1, 1);
-			if (rc < 0) {
-				airo_print_err(ai->dev->name, "failed to set "
-				               "WEP transmit index to %d: %d.",
-				               index, rc);
-			}
-			return;
-		}
-		j = 2;
-	} else {
-		airo_print_err(ai->dev->name, "WepKey passed invalid key index");
-		return;
-	}
-
-	for (i = 0; i < 16*3 && data->wbuffer[i+j]; i++) {
-		int val;
-
-		if (i % 3 == 2)
-			continue;
-
-		val = hex_to_bin(data->wbuffer[i+j]);
-		if (val < 0) {
-			airo_print_err(ai->dev->name, "WebKey passed invalid key hex");
-			return;
-		}
-		switch(i%3) {
-		case 0:
-			key[i/3] = (u8)val << 4;
-			break;
-		case 1:
-			key[i/3] |= (u8)val;
-			break;
-		}
-	}
-
-	rc = set_wep_key(ai, index, key, i/3, 1, 1);
-	if (rc < 0) {
-		airo_print_err(ai->dev->name, "failed to set WEP key at index "
-		               "%d: %d.", index, rc);
-	}
-}
-
-static int proc_wepkey_open(struct inode *inode, struct file *file)
-{
-	struct proc_data *data;
-	struct net_device *dev = pde_data(inode);
-	struct airo_info *ai = dev->ml_priv;
-	char *ptr;
-	WepKeyRid wkr;
-	__le16 lastindex;
-	int j = 0;
-	int rc;
-
-	if ((file->private_data = kzalloc(sizeof(struct proc_data), GFP_KERNEL)) == NULL)
-		return -ENOMEM;
-	memset(&wkr, 0, sizeof(wkr));
-	data = file->private_data;
-	if ((data->rbuffer = kzalloc(180, GFP_KERNEL)) == NULL) {
-		kfree (file->private_data);
-		return -ENOMEM;
-	}
-	data->writelen = 0;
-	data->maxwritelen = 80;
-	if ((data->wbuffer = kzalloc(80, GFP_KERNEL)) == NULL) {
-		kfree (data->rbuffer);
-		kfree (file->private_data);
-		return -ENOMEM;
-	}
-	data->on_close = proc_wepkey_on_close;
-
-	ptr = data->rbuffer;
-	strcpy(ptr, "No wep keys\n");
-	rc = readWepKeyRid(ai, &wkr, 1, 1);
-	if (rc == SUCCESS) do {
-		lastindex = wkr.kindex;
-		if (wkr.kindex == cpu_to_le16(0xffff)) {
-			j += sprintf(ptr+j, "Tx key = %d\n",
-				     (int)wkr.mac[0]);
-		} else {
-			j += sprintf(ptr+j, "Key %d set with length = %d\n",
-				     le16_to_cpu(wkr.kindex),
-				     le16_to_cpu(wkr.klen));
-		}
-		readWepKeyRid(ai, &wkr, 0, 1);
-	} while ((lastindex != wkr.kindex) && (j < 180-30));
-
-	data->readlen = strlen(data->rbuffer);
-	return 0;
-}
-
-static int proc_SSID_open(struct inode *inode, struct file *file)
-{
-	struct proc_data *data;
-	struct net_device *dev = pde_data(inode);
-	struct airo_info *ai = dev->ml_priv;
-	int i;
-	char *ptr;
-	SsidRid SSID_rid;
-
-	if ((file->private_data = kzalloc(sizeof(struct proc_data), GFP_KERNEL)) == NULL)
-		return -ENOMEM;
-	data = file->private_data;
-	if ((data->rbuffer = kmalloc(104, GFP_KERNEL)) == NULL) {
-		kfree (file->private_data);
-		return -ENOMEM;
-	}
-	data->writelen = 0;
-	data->maxwritelen = 33*3;
-	/* allocate maxwritelen + 1; we'll want a sentinel */
-	if ((data->wbuffer = kzalloc(33*3 + 1, GFP_KERNEL)) == NULL) {
-		kfree (data->rbuffer);
-		kfree (file->private_data);
-		return -ENOMEM;
-	}
-	data->on_close = proc_SSID_on_close;
-
-	readSsidRid(ai, &SSID_rid);
-	ptr = data->rbuffer;
-	for (i = 0; i < 3; i++) {
-		int j;
-		size_t len = le16_to_cpu(SSID_rid.ssids[i].len);
-		if (!len)
-			break;
-		if (len > 32)
-			len = 32;
-		for (j = 0; j < len && SSID_rid.ssids[i].ssid[j]; j++)
-			*ptr++ = SSID_rid.ssids[i].ssid[j];
-		*ptr++ = '\n';
-	}
-	*ptr = '\0';
-	data->readlen = strlen(data->rbuffer);
-	return 0;
-}
-
-static int proc_APList_open(struct inode *inode, struct file *file)
-{
-	struct proc_data *data;
-	struct net_device *dev = pde_data(inode);
-	struct airo_info *ai = dev->ml_priv;
-	int i;
-	char *ptr;
-	APListRid *APList_rid = &ai->APList;
-
-	if ((file->private_data = kzalloc(sizeof(struct proc_data), GFP_KERNEL)) == NULL)
-		return -ENOMEM;
-	data = file->private_data;
-	if ((data->rbuffer = kmalloc(104, GFP_KERNEL)) == NULL) {
-		kfree (file->private_data);
-		return -ENOMEM;
-	}
-	data->writelen = 0;
-	data->maxwritelen = 4*6*3;
-	if ((data->wbuffer = kzalloc(data->maxwritelen, GFP_KERNEL)) == NULL) {
-		kfree (data->rbuffer);
-		kfree (file->private_data);
-		return -ENOMEM;
-	}
-	data->on_close = proc_APList_on_close;
-
-	ptr = data->rbuffer;
-	for (i = 0; i < 4; i++) {
-// We end when we find a zero MAC
-		if (!*(int*)APList_rid->ap[i] &&
-		     !*(int*)&APList_rid->ap[i][2]) break;
-		ptr += sprintf(ptr, "%pM\n", APList_rid->ap[i]);
-	}
-	if (i==0) ptr += sprintf(ptr, "Not using specific APs\n");
-
-	*ptr = '\0';
-	data->readlen = strlen(data->rbuffer);
-	return 0;
-}
-
-static int proc_BSSList_open(struct inode *inode, struct file *file)
-{
-	struct proc_data *data;
-	struct net_device *dev = pde_data(inode);
-	struct airo_info *ai = dev->ml_priv;
-	char *ptr;
-	BSSListRid BSSList_rid;
-	int rc;
-	/* If doLoseSync is not 1, we won't do a Lose Sync */
-	int doLoseSync = -1;
-
-	if ((file->private_data = kzalloc(sizeof(struct proc_data), GFP_KERNEL)) == NULL)
-		return -ENOMEM;
-	data = file->private_data;
-	if ((data->rbuffer = kmalloc(1024, GFP_KERNEL)) == NULL) {
-		kfree (file->private_data);
-		return -ENOMEM;
-	}
-	data->writelen = 0;
-	data->maxwritelen = 0;
-	data->wbuffer = NULL;
-	data->on_close = NULL;
-
-	if (file->f_mode & FMODE_WRITE) {
-		if (!(file->f_mode & FMODE_READ)) {
-			Cmd cmd;
-			Resp rsp;
-
-			if (ai->flags & FLAG_RADIO_MASK) {
-				kfree(data->rbuffer);
-				kfree(file->private_data);
-				return -ENETDOWN;
-			}
-			memset(&cmd, 0, sizeof(cmd));
-			cmd.cmd = CMD_LISTBSS;
-			if (down_interruptible(&ai->sem)) {
-				kfree(data->rbuffer);
-				kfree(file->private_data);
-				return -ERESTARTSYS;
-			}
-			issuecommand(ai, &cmd, &rsp, true);
-			up(&ai->sem);
-			data->readlen = 0;
-			return 0;
-		}
-		doLoseSync = 1;
-	}
-	ptr = data->rbuffer;
-	/* There is a race condition here if there are concurrent opens.
-           Since it is a rare condition, we'll just live with it, otherwise
-           we have to add a spin lock... */
-	rc = readBSSListRid(ai, doLoseSync, &BSSList_rid);
-	while (rc == 0 && BSSList_rid.index != cpu_to_le16(0xffff)) {
-		ptr += sprintf(ptr, "%pM %.*s rssi = %d",
-			       BSSList_rid.bssid,
-				(int)BSSList_rid.ssidLen,
-				BSSList_rid.ssid,
-				le16_to_cpu(BSSList_rid.dBm));
-		ptr += sprintf(ptr, " channel = %d %s %s %s %s\n",
-				le16_to_cpu(BSSList_rid.dsChannel),
-				BSSList_rid.cap & CAP_ESS ? "ESS" : "",
-				BSSList_rid.cap & CAP_IBSS ? "adhoc" : "",
-				BSSList_rid.cap & CAP_PRIVACY ? "wep" : "",
-				BSSList_rid.cap & CAP_SHORTHDR ? "shorthdr" : "");
-		rc = readBSSListRid(ai, 0, &BSSList_rid);
-	}
-	*ptr = '\0';
-	data->readlen = strlen(data->rbuffer);
-	return 0;
-}
-
-static int proc_close(struct inode *inode, struct file *file)
-{
-	struct proc_data *data = file->private_data;
-
-	if (data->on_close != NULL)
-		data->on_close(inode, file);
-	kfree(data->rbuffer);
-	kfree(data->wbuffer);
-	kfree(data);
-	return 0;
-}
-
-/* Since the card doesn't automatically switch to the right WEP mode,
-   we will make it do it.  If the card isn't associated, every secs we
-   will switch WEP modes to see if that will help.  If the card is
-   associated we will check every minute to see if anything has
-   changed. */
-static void timer_func(struct net_device *dev)
-{
-	struct airo_info *apriv = dev->ml_priv;
-
-/* We don't have a link so try changing the authtype */
-	readConfigRid(apriv, 0);
-	disable_MAC(apriv, 0);
-	switch(apriv->config.authType) {
-		case AUTH_ENCRYPT:
-/* So drop to OPEN */
-			apriv->config.authType = AUTH_OPEN;
-			break;
-		case AUTH_SHAREDKEY:
-			if (apriv->keyindex < auto_wep) {
-				set_wep_tx_idx(apriv, apriv->keyindex, 0, 0);
-				apriv->config.authType = AUTH_SHAREDKEY;
-				apriv->keyindex++;
-			} else {
-			        /* Drop to ENCRYPT */
-				apriv->keyindex = 0;
-				set_wep_tx_idx(apriv, apriv->defindex, 0, 0);
-				apriv->config.authType = AUTH_ENCRYPT;
-			}
-			break;
-		default:  /* We'll escalate to SHAREDKEY */
-			apriv->config.authType = AUTH_SHAREDKEY;
-	}
-	set_bit (FLAG_COMMIT, &apriv->flags);
-	writeConfigRid(apriv, 0);
-	enable_MAC(apriv, 0);
-	up(&apriv->sem);
-
-/* Schedule check to see if the change worked */
-	clear_bit(JOB_AUTOWEP, &apriv->jobs);
-	apriv->expires = RUN_AT(HZ*3);
-}
-
-#ifdef CONFIG_PCI
-static int airo_pci_probe(struct pci_dev *pdev,
-				    const struct pci_device_id *pent)
-{
-	struct net_device *dev;
-
-	if (pci_enable_device(pdev))
-		return -ENODEV;
-	pci_set_master(pdev);
-
-	if (pdev->device == 0x5000 || pdev->device == 0xa504)
-			dev = _init_airo_card(pdev->irq, pdev->resource[0].start, 0, pdev, &pdev->dev);
-	else
-			dev = _init_airo_card(pdev->irq, pdev->resource[2].start, 0, pdev, &pdev->dev);
-	if (!dev) {
-		pci_disable_device(pdev);
-		return -ENODEV;
-	}
-
-	pci_set_drvdata(pdev, dev);
-	return 0;
-}
-
-static void airo_pci_remove(struct pci_dev *pdev)
-{
-	struct net_device *dev = pci_get_drvdata(pdev);
-
-	airo_print_info(dev->name, "Unregistering...");
-	stop_airo_card(dev, 1);
-	pci_disable_device(pdev);
-}
-
-static int __maybe_unused airo_pci_suspend(struct device *dev_d)
-{
-	struct net_device *dev = dev_get_drvdata(dev_d);
-	struct airo_info *ai = dev->ml_priv;
-	Cmd cmd;
-	Resp rsp;
-
-	if (!ai->SSID)
-		ai->SSID = kmalloc(sizeof(SsidRid), GFP_KERNEL);
-	if (!ai->SSID)
-		return -ENOMEM;
-	readSsidRid(ai, ai->SSID);
-	memset(&cmd, 0, sizeof(cmd));
-	/* the lock will be released at the end of the resume callback */
-	if (down_interruptible(&ai->sem))
-		return -EAGAIN;
-	disable_MAC(ai, 0);
-	netif_device_detach(dev);
-	ai->power = PMSG_SUSPEND;
-	cmd.cmd = HOSTSLEEP;
-	issuecommand(ai, &cmd, &rsp, true);
-
-	device_wakeup_enable(dev_d);
-	return 0;
-}
-
-static int __maybe_unused airo_pci_resume(struct device *dev_d)
-{
-	struct net_device *dev = dev_get_drvdata(dev_d);
-	struct airo_info *ai = dev->ml_priv;
-	pci_power_t prev_state = to_pci_dev(dev_d)->current_state;
-
-	device_wakeup_disable(dev_d);
-
-	if (prev_state != PCI_D1) {
-		reset_card(dev, 0);
-		mpi_init_descriptors(ai);
-		setup_card(ai, dev, 0);
-		clear_bit(FLAG_RADIO_OFF, &ai->flags);
-		clear_bit(FLAG_PENDING_XMIT, &ai->flags);
-	} else {
-		OUT4500(ai, EVACK, EV_AWAKEN);
-		OUT4500(ai, EVACK, EV_AWAKEN);
-		msleep(100);
-	}
-
-	set_bit(FLAG_COMMIT, &ai->flags);
-	disable_MAC(ai, 0);
-        msleep(200);
-	if (ai->SSID) {
-		writeSsidRid(ai, ai->SSID, 0);
-		kfree(ai->SSID);
-		ai->SSID = NULL;
-	}
-	writeAPListRid(ai, &ai->APList, 0);
-	writeConfigRid(ai, 0);
-	enable_MAC(ai, 0);
-	ai->power = PMSG_ON;
-	netif_device_attach(dev);
-	netif_wake_queue(dev);
-	enable_interrupts(ai);
-	up(&ai->sem);
-	return 0;
-}
-#endif
-
-static int __init airo_init_module(void)
-{
-	int i;
-
-	proc_kuid = make_kuid(&init_user_ns, proc_uid);
-	proc_kgid = make_kgid(&init_user_ns, proc_gid);
-	if (!uid_valid(proc_kuid) || !gid_valid(proc_kgid))
-		return -EINVAL;
-
-	airo_entry = proc_mkdir_mode("driver/aironet", airo_perm, NULL);
-
-	if (airo_entry)
-		proc_set_user(airo_entry, proc_kuid, proc_kgid);
-
-	for (i = 0; i < 4 && io[i] && irq[i]; i++) {
-		airo_print_info("", "Trying to configure ISA adapter at irq=%d "
-			"io = 0x%x", irq[i], io[i]);
-		if (init_airo_card(irq[i], io[i], 0, NULL)) {
-			/* do nothing */ ;
-		}
-	}
-
-#ifdef CONFIG_PCI
-	airo_print_info("", "Probing for PCI adapters");
-	i = pci_register_driver(&airo_driver);
-	airo_print_info("", "Finished probing for PCI adapters");
-
-	if (i) {
-		remove_proc_entry("driver/aironet", NULL);
-		return i;
-	}
-#endif
-
-	/* Always exit with success, as we are a library module
-	 * as well as a driver module
-	 */
-	return 0;
-}
-
-static void __exit airo_cleanup_module(void)
-{
-	struct airo_info *ai;
-	while (!list_empty(&airo_devices)) {
-		ai = list_entry(airo_devices.next, struct airo_info, dev_list);
-		airo_print_info(ai->dev->name, "Unregistering...");
-		stop_airo_card(ai->dev, 1);
-	}
-#ifdef CONFIG_PCI
-	pci_unregister_driver(&airo_driver);
-#endif
-	remove_proc_entry("driver/aironet", NULL);
-}
-
-/*
- * Initial Wireless Extension code for Aironet driver by :
- *	Jean Tourrilhes <jt@hpl.hp.com> - HPL - 17 November 00
- * Conversion to new driver API by :
- *	Jean Tourrilhes <jt@hpl.hp.com> - HPL - 26 March 02
- * Javier also did a good amount of work here, adding some new extensions
- * and fixing my code. Let's just say that without him this code just
- * would not work at all... - Jean II
- */
-
-static u8 airo_rssi_to_dbm (tdsRssiEntry *rssi_rid, u8 rssi)
-{
-	if (!rssi_rid)
-		return 0;
-
-	return (0x100 - rssi_rid[rssi].rssidBm);
-}
-
-static u8 airo_dbm_to_pct (tdsRssiEntry *rssi_rid, u8 dbm)
-{
-	int i;
-
-	if (!rssi_rid)
-		return 0;
-
-	for (i = 0; i < 256; i++)
-		if (rssi_rid[i].rssidBm == dbm)
-			return rssi_rid[i].rssipct;
-
-	return 0;
-}
-
-
-static int airo_get_quality (StatusRid *status_rid, CapabilityRid *cap_rid)
-{
-	int quality = 0;
-	u16 sq;
-
-	if ((status_rid->mode & cpu_to_le16(0x3f)) != cpu_to_le16(0x3f))
-		return 0;
-
-	if (!(cap_rid->hardCap & cpu_to_le16(8)))
-		return 0;
-
-	sq = le16_to_cpu(status_rid->signalQuality);
-	if (memcmp(cap_rid->prodName, "350", 3))
-		if (sq > 0x20)
-			quality = 0;
-		else
-			quality = 0x20 - sq;
-	else
-		if (sq > 0xb0)
-			quality = 0;
-		else if (sq < 0x10)
-			quality = 0xa0;
-		else
-			quality = 0xb0 - sq;
-	return quality;
-}
-
-#define airo_get_max_quality(cap_rid) (memcmp((cap_rid)->prodName, "350", 3) ? 0x20 : 0xa0)
-#define airo_get_avg_quality(cap_rid) (memcmp((cap_rid)->prodName, "350", 3) ? 0x10 : 0x50)
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get protocol name
- */
-static int airo_get_name(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *cwrq,
-			 char *extra)
-{
-	strcpy(cwrq->name, "IEEE 802.11-DS");
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : set frequency
- */
-static int airo_set_freq(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *wrqu,
-			 char *extra)
-{
-	struct iw_freq *fwrq = &wrqu->freq;
-	struct airo_info *local = dev->ml_priv;
-	int rc = -EINPROGRESS;		/* Call commit handler */
-
-	/* If setting by frequency, convert to a channel */
-	if (fwrq->e == 1) {
-		int f = fwrq->m / 100000;
-
-		/* Hack to fall through... */
-		fwrq->e = 0;
-		fwrq->m = ieee80211_frequency_to_channel(f);
-	}
-	/* Setting by channel number */
-	if (fwrq->m < 0 || fwrq->m > 1000 || fwrq->e > 0)
-		rc = -EOPNOTSUPP;
-	else {
-		int channel = fwrq->m;
-		/* We should do a better check than that,
-		 * based on the card capability !!! */
-		if ((channel < 1) || (channel > 14)) {
-			airo_print_dbg(dev->name, "New channel value of %d is invalid!",
-				fwrq->m);
-			rc = -EINVAL;
-		} else {
-			readConfigRid(local, 1);
-			/* Yes ! We can set it !!! */
-			local->config.channelSet = cpu_to_le16(channel);
-			set_bit (FLAG_COMMIT, &local->flags);
-		}
-	}
-	return rc;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get frequency
- */
-static int airo_get_freq(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *wrqu,
-			 char *extra)
-{
-	struct iw_freq *fwrq = &wrqu->freq;
-	struct airo_info *local = dev->ml_priv;
-	StatusRid status_rid;		/* Card status info */
-	int ch;
-
-	readConfigRid(local, 1);
-	if ((local->config.opmode & MODE_CFG_MASK) == MODE_STA_ESS)
-		status_rid.channel = local->config.channelSet;
-	else
-		readStatusRid(local, &status_rid, 1);
-
-	ch = le16_to_cpu(status_rid.channel);
-	if ((ch > 0) && (ch < 15)) {
-		fwrq->m = 100000 *
-			ieee80211_channel_to_frequency(ch, NL80211_BAND_2GHZ);
-		fwrq->e = 1;
-	} else {
-		fwrq->m = ch;
-		fwrq->e = 0;
-	}
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : set ESSID
- */
-static int airo_set_essid(struct net_device *dev,
-			  struct iw_request_info *info,
-			  union iwreq_data *wrqu,
-			  char *extra)
-{
-	struct iw_point *dwrq = &wrqu->essid;
-	struct airo_info *local = dev->ml_priv;
-	SsidRid SSID_rid;		/* SSIDs */
-
-	/* Reload the list of current SSID */
-	readSsidRid(local, &SSID_rid);
-
-	/* Check if we asked for `any' */
-	if (dwrq->flags == 0) {
-		/* Just send an empty SSID list */
-		memset(&SSID_rid, 0, sizeof(SSID_rid));
-	} else {
-		unsigned index = (dwrq->flags & IW_ENCODE_INDEX) - 1;
-
-		/* Check the size of the string */
-		if (dwrq->length > IW_ESSID_MAX_SIZE)
-			return -E2BIG ;
-
-		/* Check if index is valid */
-		if (index >= ARRAY_SIZE(SSID_rid.ssids))
-			return -EINVAL;
-
-		/* Set the SSID */
-		memset(SSID_rid.ssids[index].ssid, 0,
-		       sizeof(SSID_rid.ssids[index].ssid));
-		memcpy(SSID_rid.ssids[index].ssid, extra, dwrq->length);
-		SSID_rid.ssids[index].len = cpu_to_le16(dwrq->length);
-	}
-	SSID_rid.len = cpu_to_le16(sizeof(SSID_rid));
-	/* Write it to the card */
-	disable_MAC(local, 1);
-	writeSsidRid(local, &SSID_rid, 1);
-	enable_MAC(local, 1);
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get ESSID
- */
-static int airo_get_essid(struct net_device *dev,
-			  struct iw_request_info *info,
-			  union iwreq_data *wrqu,
-			  char *extra)
-{
-	struct iw_point *dwrq = &wrqu->essid;
-	struct airo_info *local = dev->ml_priv;
-	StatusRid status_rid;		/* Card status info */
-
-	readStatusRid(local, &status_rid, 1);
-
-	/* Note : if dwrq->flags != 0, we should
-	 * get the relevant SSID from the SSID list... */
-
-	/* Get the current SSID */
-	memcpy(extra, status_rid.SSID, le16_to_cpu(status_rid.SSIDlen));
-	/* If none, we may want to get the one that was set */
-
-	/* Push it out ! */
-	dwrq->length = le16_to_cpu(status_rid.SSIDlen);
-	dwrq->flags = 1; /* active */
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : set AP address
- */
-static int airo_set_wap(struct net_device *dev,
-			struct iw_request_info *info,
-			union iwreq_data *wrqu,
-			char *extra)
-{
-	struct sockaddr *awrq = &wrqu->ap_addr;
-	struct airo_info *local = dev->ml_priv;
-	Cmd cmd;
-	Resp rsp;
-	APListRid *APList_rid = &local->APList;
-
-	if (awrq->sa_family != ARPHRD_ETHER)
-		return -EINVAL;
-	else if (is_broadcast_ether_addr(awrq->sa_data) ||
-		 is_zero_ether_addr(awrq->sa_data)) {
-		memset(&cmd, 0, sizeof(cmd));
-		cmd.cmd = CMD_LOSE_SYNC;
-		if (down_interruptible(&local->sem))
-			return -ERESTARTSYS;
-		issuecommand(local, &cmd, &rsp, true);
-		up(&local->sem);
-	} else {
-		memset(APList_rid, 0, sizeof(*APList_rid));
-		APList_rid->len = cpu_to_le16(sizeof(*APList_rid));
-		memcpy(APList_rid->ap[0], awrq->sa_data, ETH_ALEN);
-		disable_MAC(local, 1);
-		writeAPListRid(local, APList_rid, 1);
-		enable_MAC(local, 1);
-	}
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get AP address
- */
-static int airo_get_wap(struct net_device *dev,
-			struct iw_request_info *info,
-			union iwreq_data *wrqu,
-			char *extra)
-{
-	struct sockaddr *awrq = &wrqu->ap_addr;
-	struct airo_info *local = dev->ml_priv;
-	StatusRid status_rid;		/* Card status info */
-
-	readStatusRid(local, &status_rid, 1);
-
-	/* Tentative. This seems to work, wow, I'm lucky !!! */
-	memcpy(awrq->sa_data, status_rid.bssid[0], ETH_ALEN);
-	awrq->sa_family = ARPHRD_ETHER;
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : set Nickname
- */
-static int airo_set_nick(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *wrqu,
-			 char *extra)
-{
-	struct iw_point *dwrq = &wrqu->data;
-	struct airo_info *local = dev->ml_priv;
-
-	/* Check the size of the string */
-	if (dwrq->length > 16) {
-		return -E2BIG;
-	}
-	readConfigRid(local, 1);
-	memset(local->config.nodeName, 0, sizeof(local->config.nodeName));
-	memcpy(local->config.nodeName, extra, dwrq->length);
-	set_bit (FLAG_COMMIT, &local->flags);
-
-	return -EINPROGRESS;		/* Call commit handler */
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get Nickname
- */
-static int airo_get_nick(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *wrqu,
-			 char *extra)
-{
-	struct iw_point *dwrq = &wrqu->data;
-	struct airo_info *local = dev->ml_priv;
-
-	readConfigRid(local, 1);
-	strncpy(extra, local->config.nodeName, 16);
-	extra[16] = '\0';
-	dwrq->length = strlen(extra);
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : set Bit-Rate
- */
-static int airo_set_rate(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *wrqu,
-			 char *extra)
-{
-	struct iw_param *vwrq = &wrqu->bitrate;
-	struct airo_info *local = dev->ml_priv;
-	CapabilityRid cap_rid;		/* Card capability info */
-	u8	brate = 0;
-	int	i;
-
-	/* First : get a valid bit rate value */
-	readCapabilityRid(local, &cap_rid, 1);
-
-	/* Which type of value ? */
-	if ((vwrq->value < 8) && (vwrq->value >= 0)) {
-		/* Setting by rate index */
-		/* Find value in the magic rate table */
-		brate = cap_rid.supportedRates[vwrq->value];
-	} else {
-		/* Setting by frequency value */
-		u8	normvalue = (u8) (vwrq->value/500000);
-
-		/* Check if rate is valid */
-		for (i = 0 ; i < 8 ; i++) {
-			if (normvalue == cap_rid.supportedRates[i]) {
-				brate = normvalue;
-				break;
-			}
-		}
-	}
-	/* -1 designed the max rate (mostly auto mode) */
-	if (vwrq->value == -1) {
-		/* Get the highest available rate */
-		for (i = 0 ; i < 8 ; i++) {
-			if (cap_rid.supportedRates[i] == 0)
-				break;
-		}
-		if (i != 0)
-			brate = cap_rid.supportedRates[i - 1];
-	}
-	/* Check that it is valid */
-	if (brate == 0) {
-		return -EINVAL;
-	}
-
-	readConfigRid(local, 1);
-	/* Now, check if we want a fixed or auto value */
-	if (vwrq->fixed == 0) {
-		/* Fill all the rates up to this max rate */
-		memset(local->config.rates, 0, 8);
-		for (i = 0 ; i < 8 ; i++) {
-			local->config.rates[i] = cap_rid.supportedRates[i];
-			if (local->config.rates[i] == brate)
-				break;
-		}
-	} else {
-		/* Fixed mode */
-		/* One rate, fixed */
-		memset(local->config.rates, 0, 8);
-		local->config.rates[0] = brate;
-	}
-	set_bit (FLAG_COMMIT, &local->flags);
-
-	return -EINPROGRESS;		/* Call commit handler */
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get Bit-Rate
- */
-static int airo_get_rate(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *wrqu,
-			 char *extra)
-{
-	struct iw_param *vwrq = &wrqu->bitrate;
-	struct airo_info *local = dev->ml_priv;
-	StatusRid status_rid;		/* Card status info */
-	int ret;
-
-	ret = readStatusRid(local, &status_rid, 1);
-	if (ret)
-		return -EBUSY;
-
-	vwrq->value = le16_to_cpu(status_rid.currentXmitRate) * 500000;
-	/* If more than one rate, set auto */
-	readConfigRid(local, 1);
-	vwrq->fixed = (local->config.rates[1] == 0);
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : set RTS threshold
- */
-static int airo_set_rts(struct net_device *dev,
-			struct iw_request_info *info,
-			union iwreq_data *wrqu,
-			char *extra)
-{
-	struct iw_param *vwrq = &wrqu->rts;
-	struct airo_info *local = dev->ml_priv;
-	int rthr = vwrq->value;
-
-	if (vwrq->disabled)
-		rthr = AIRO_DEF_MTU;
-	if ((rthr < 0) || (rthr > AIRO_DEF_MTU)) {
-		return -EINVAL;
-	}
-	readConfigRid(local, 1);
-	local->config.rtsThres = cpu_to_le16(rthr);
-	set_bit (FLAG_COMMIT, &local->flags);
-
-	return -EINPROGRESS;		/* Call commit handler */
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get RTS threshold
- */
-static int airo_get_rts(struct net_device *dev,
-			struct iw_request_info *info,
-			union iwreq_data *wrqu,
-			char *extra)
-{
-	struct iw_param *vwrq = &wrqu->rts;
-	struct airo_info *local = dev->ml_priv;
-
-	readConfigRid(local, 1);
-	vwrq->value = le16_to_cpu(local->config.rtsThres);
-	vwrq->disabled = (vwrq->value >= AIRO_DEF_MTU);
-	vwrq->fixed = 1;
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : set Fragmentation threshold
- */
-static int airo_set_frag(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *vwrq = &wrqu->frag;
-	struct airo_info *local = dev->ml_priv;
-	int fthr = vwrq->value;
-
-	if (vwrq->disabled)
-		fthr = AIRO_DEF_MTU;
-	if ((fthr < 256) || (fthr > AIRO_DEF_MTU)) {
-		return -EINVAL;
-	}
-	fthr &= ~0x1;	/* Get an even value - is it really needed ??? */
-	readConfigRid(local, 1);
-	local->config.fragThresh = cpu_to_le16(fthr);
-	set_bit (FLAG_COMMIT, &local->flags);
-
-	return -EINPROGRESS;		/* Call commit handler */
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get Fragmentation threshold
- */
-static int airo_get_frag(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *wrqu,
-			 char *extra)
-{
-	struct iw_param *vwrq = &wrqu->frag;
-	struct airo_info *local = dev->ml_priv;
-
-	readConfigRid(local, 1);
-	vwrq->value = le16_to_cpu(local->config.fragThresh);
-	vwrq->disabled = (vwrq->value >= AIRO_DEF_MTU);
-	vwrq->fixed = 1;
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : set Mode of Operation
- */
-static int airo_set_mode(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *uwrq,
-			 char *extra)
-{
-	__u32 mode = uwrq->mode;
-	struct airo_info *local = dev->ml_priv;
-	int reset = 0;
-
-	readConfigRid(local, 1);
-	if (sniffing_mode(local))
-		reset = 1;
-
-	switch (mode) {
-		case IW_MODE_ADHOC:
-			local->config.opmode &= ~MODE_CFG_MASK;
-			local->config.opmode |= MODE_STA_IBSS;
-			local->config.rmode &= ~RXMODE_FULL_MASK;
-			local->config.scanMode = SCANMODE_ACTIVE;
-			clear_bit (FLAG_802_11, &local->flags);
-			break;
-		case IW_MODE_INFRA:
-			local->config.opmode &= ~MODE_CFG_MASK;
-			local->config.opmode |= MODE_STA_ESS;
-			local->config.rmode &= ~RXMODE_FULL_MASK;
-			local->config.scanMode = SCANMODE_ACTIVE;
-			clear_bit (FLAG_802_11, &local->flags);
-			break;
-		case IW_MODE_MASTER:
-			local->config.opmode &= ~MODE_CFG_MASK;
-			local->config.opmode |= MODE_AP;
-			local->config.rmode &= ~RXMODE_FULL_MASK;
-			local->config.scanMode = SCANMODE_ACTIVE;
-			clear_bit (FLAG_802_11, &local->flags);
-			break;
-		case IW_MODE_REPEAT:
-			local->config.opmode &= ~MODE_CFG_MASK;
-			local->config.opmode |= MODE_AP_RPTR;
-			local->config.rmode &= ~RXMODE_FULL_MASK;
-			local->config.scanMode = SCANMODE_ACTIVE;
-			clear_bit (FLAG_802_11, &local->flags);
-			break;
-		case IW_MODE_MONITOR:
-			local->config.opmode &= ~MODE_CFG_MASK;
-			local->config.opmode |= MODE_STA_ESS;
-			local->config.rmode &= ~RXMODE_FULL_MASK;
-			local->config.rmode |= RXMODE_RFMON | RXMODE_DISABLE_802_3_HEADER;
-			local->config.scanMode = SCANMODE_PASSIVE;
-			set_bit (FLAG_802_11, &local->flags);
-			break;
-		default:
-			return -EINVAL;
-	}
-	if (reset)
-		set_bit (FLAG_RESET, &local->flags);
-	set_bit (FLAG_COMMIT, &local->flags);
-
-	return -EINPROGRESS;		/* Call commit handler */
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get Mode of Operation
- */
-static int airo_get_mode(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *uwrq,
-			 char *extra)
-{
-	struct airo_info *local = dev->ml_priv;
-
-	readConfigRid(local, 1);
-	/* If not managed, assume it's ad-hoc */
-	switch (local->config.opmode & MODE_CFG_MASK) {
-		case MODE_STA_ESS:
-			uwrq->mode = IW_MODE_INFRA;
-			break;
-		case MODE_AP:
-			uwrq->mode = IW_MODE_MASTER;
-			break;
-		case MODE_AP_RPTR:
-			uwrq->mode = IW_MODE_REPEAT;
-			break;
-		default:
-			uwrq->mode = IW_MODE_ADHOC;
-	}
-
-	return 0;
-}
-
-static inline int valid_index(struct airo_info *ai, int index)
-{
-	return (index >= 0) && (index <= ai->max_wep_idx);
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : set Encryption Key
- */
-static int airo_set_encode(struct net_device *dev,
-			   struct iw_request_info *info,
-			   union iwreq_data *wrqu,
-			   char *extra)
-{
-	struct iw_point *dwrq = &wrqu->encoding;
-	struct airo_info *local = dev->ml_priv;
-	int perm = (dwrq->flags & IW_ENCODE_TEMP ? 0 : 1);
-	__le16 currentAuthType = local->config.authType;
-	int rc = 0;
-
-	if (!local->wep_capable)
-		return -EOPNOTSUPP;
-
-	readConfigRid(local, 1);
-
-	/* Basic checking: do we have a key to set ?
-	 * Note : with the new API, it's impossible to get a NULL pointer.
-	 * Therefore, we need to check a key size == 0 instead.
-	 * New version of iwconfig properly set the IW_ENCODE_NOKEY flag
-	 * when no key is present (only change flags), but older versions
-	 * don't do it. - Jean II */
-	if (dwrq->length > 0) {
-		wep_key_t key;
-		int index = (dwrq->flags & IW_ENCODE_INDEX) - 1;
-		int current_index;
-
-		/* Check the size of the key */
-		if (dwrq->length > MAX_KEY_SIZE) {
-			return -EINVAL;
-		}
-
-		current_index = get_wep_tx_idx(local);
-		if (current_index < 0)
-			current_index = 0;
-
-		/* Check the index (none -> use current) */
-		if (!valid_index(local, index))
-			index = current_index;
-
-		/* Set the length */
-		if (dwrq->length > MIN_KEY_SIZE)
-			key.len = MAX_KEY_SIZE;
-		else
-			key.len = MIN_KEY_SIZE;
-		/* Check if the key is not marked as invalid */
-		if (!(dwrq->flags & IW_ENCODE_NOKEY)) {
-			/* Cleanup */
-			memset(key.key, 0, MAX_KEY_SIZE);
-			/* Copy the key in the driver */
-			memcpy(key.key, extra, dwrq->length);
-			/* Send the key to the card */
-			rc = set_wep_key(local, index, key.key, key.len, perm, 1);
-			if (rc < 0) {
-				airo_print_err(local->dev->name, "failed to set"
-				               " WEP key at index %d: %d.",
-				               index, rc);
-				return rc;
-			}
-		}
-		/* WE specify that if a valid key is set, encryption
-		 * should be enabled (user may turn it off later)
-		 * This is also how "iwconfig ethX key on" works */
-		if ((index == current_index) && (key.len > 0) &&
-		   (local->config.authType == AUTH_OPEN))
-			set_auth_type(local, AUTH_ENCRYPT);
-	} else {
-		/* Do we want to just set the transmit key index ? */
-		int index = (dwrq->flags & IW_ENCODE_INDEX) - 1;
-		if (valid_index(local, index)) {
-			rc = set_wep_tx_idx(local, index, perm, 1);
-			if (rc < 0) {
-				airo_print_err(local->dev->name, "failed to set"
-				               " WEP transmit index to %d: %d.",
-				               index, rc);
-				return rc;
-			}
-		} else {
-			/* Don't complain if only change the mode */
-			if (!(dwrq->flags & IW_ENCODE_MODE))
-				return -EINVAL;
-		}
-	}
-	/* Read the flags */
-	if (dwrq->flags & IW_ENCODE_DISABLED)
-		set_auth_type(local, AUTH_OPEN);	/* disable encryption */
-	if (dwrq->flags & IW_ENCODE_RESTRICTED)
-		set_auth_type(local, AUTH_SHAREDKEY);	/* Only Both */
-	if (dwrq->flags & IW_ENCODE_OPEN)
-		set_auth_type(local, AUTH_ENCRYPT);	/* Only Wep */
-	/* Commit the changes to flags if needed */
-	if (local->config.authType != currentAuthType)
-		set_bit (FLAG_COMMIT, &local->flags);
-	return -EINPROGRESS;		/* Call commit handler */
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get Encryption Key
- */
-static int airo_get_encode(struct net_device *dev,
-			   struct iw_request_info *info,
-			   union iwreq_data *wrqu,
-			   char *extra)
-{
-	struct iw_point *dwrq = &wrqu->encoding;
-	struct airo_info *local = dev->ml_priv;
-	int index = (dwrq->flags & IW_ENCODE_INDEX) - 1;
-	int wep_key_len;
-	u8 buf[16];
-
-	if (!local->wep_capable)
-		return -EOPNOTSUPP;
-
-	readConfigRid(local, 1);
-
-	/* Check encryption mode */
-	switch(local->config.authType)	{
-		case AUTH_ENCRYPT:
-			dwrq->flags = IW_ENCODE_OPEN;
-			break;
-		case AUTH_SHAREDKEY:
-			dwrq->flags = IW_ENCODE_RESTRICTED;
-			break;
-		default:
-		case AUTH_OPEN:
-			dwrq->flags = IW_ENCODE_DISABLED;
-			break;
-	}
-	/* We can't return the key, so set the proper flag and return zero */
-	dwrq->flags |= IW_ENCODE_NOKEY;
-	memset(extra, 0, 16);
-
-	/* Which key do we want ? -1 -> tx index */
-	if (!valid_index(local, index)) {
-		index = get_wep_tx_idx(local);
-		if (index < 0)
-			index = 0;
-	}
-	dwrq->flags |= index + 1;
-
-	/* Copy the key to the user buffer */
-	wep_key_len = get_wep_key(local, index, &buf[0], sizeof(buf));
-	if (wep_key_len < 0) {
-		dwrq->length = 0;
-	} else {
-		dwrq->length = wep_key_len;
-		memcpy(extra, buf, dwrq->length);
-	}
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : set extended Encryption parameters
- */
-static int airo_set_encodeext(struct net_device *dev,
-			   struct iw_request_info *info,
-			    union iwreq_data *wrqu,
-			    char *extra)
-{
-	struct airo_info *local = dev->ml_priv;
-	struct iw_point *encoding = &wrqu->encoding;
-	struct iw_encode_ext *ext = (struct iw_encode_ext *)extra;
-	int perm = (encoding->flags & IW_ENCODE_TEMP ? 0 : 1);
-	__le16 currentAuthType = local->config.authType;
-	int idx, key_len, alg = ext->alg, set_key = 1, rc;
-	wep_key_t key;
-
-	if (!local->wep_capable)
-		return -EOPNOTSUPP;
-
-	readConfigRid(local, 1);
-
-	/* Determine and validate the key index */
-	idx = encoding->flags & IW_ENCODE_INDEX;
-	if (idx) {
-		if (!valid_index(local, idx - 1))
-			return -EINVAL;
-		idx--;
-	} else {
-		idx = get_wep_tx_idx(local);
-		if (idx < 0)
-			idx = 0;
-	}
-
-	if (encoding->flags & IW_ENCODE_DISABLED)
-		alg = IW_ENCODE_ALG_NONE;
-
-	if (ext->ext_flags & IW_ENCODE_EXT_SET_TX_KEY) {
-		/* Only set transmit key index here, actual
-		 * key is set below if needed.
-		 */
-		rc = set_wep_tx_idx(local, idx, perm, 1);
-		if (rc < 0) {
-			airo_print_err(local->dev->name, "failed to set "
-			               "WEP transmit index to %d: %d.",
-			               idx, rc);
-			return rc;
-		}
-		set_key = ext->key_len > 0 ? 1 : 0;
-	}
-
-	if (set_key) {
-		/* Set the requested key first */
-		memset(key.key, 0, MAX_KEY_SIZE);
-		switch (alg) {
-		case IW_ENCODE_ALG_NONE:
-			key.len = 0;
-			break;
-		case IW_ENCODE_ALG_WEP:
-			if (ext->key_len > MIN_KEY_SIZE) {
-				key.len = MAX_KEY_SIZE;
-			} else if (ext->key_len > 0) {
-				key.len = MIN_KEY_SIZE;
-			} else {
-				return -EINVAL;
-			}
-			key_len = min (ext->key_len, key.len);
-			memcpy(key.key, ext->key, key_len);
-			break;
-		default:
-			return -EINVAL;
-		}
-		if (key.len == 0) {
-			rc = set_wep_tx_idx(local, idx, perm, 1);
-			if (rc < 0) {
-				airo_print_err(local->dev->name,
-					       "failed to set WEP transmit index to %d: %d.",
-					       idx, rc);
-				return rc;
-			}
-		} else {
-			rc = set_wep_key(local, idx, key.key, key.len, perm, 1);
-			if (rc < 0) {
-				airo_print_err(local->dev->name,
-					       "failed to set WEP key at index %d: %d.",
-					       idx, rc);
-				return rc;
-			}
-		}
-	}
-
-	/* Read the flags */
-	if (encoding->flags & IW_ENCODE_DISABLED)
-		set_auth_type(local, AUTH_OPEN);	/* disable encryption */
-	if (encoding->flags & IW_ENCODE_RESTRICTED)
-		set_auth_type(local, AUTH_SHAREDKEY);	/* Only Both */
-	if (encoding->flags & IW_ENCODE_OPEN)
-		set_auth_type(local, AUTH_ENCRYPT);
-	/* Commit the changes to flags if needed */
-	if (local->config.authType != currentAuthType)
-		set_bit (FLAG_COMMIT, &local->flags);
-
-	return -EINPROGRESS;
-}
-
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get extended Encryption parameters
- */
-static int airo_get_encodeext(struct net_device *dev,
-			    struct iw_request_info *info,
-			    union iwreq_data *wrqu,
-			    char *extra)
-{
-	struct airo_info *local = dev->ml_priv;
-	struct iw_point *encoding = &wrqu->encoding;
-	struct iw_encode_ext *ext = (struct iw_encode_ext *)extra;
-	int idx, max_key_len, wep_key_len;
-	u8 buf[16];
-
-	if (!local->wep_capable)
-		return -EOPNOTSUPP;
-
-	readConfigRid(local, 1);
-
-	max_key_len = encoding->length - sizeof(*ext);
-	if (max_key_len < 0)
-		return -EINVAL;
-
-	idx = encoding->flags & IW_ENCODE_INDEX;
-	if (idx) {
-		if (!valid_index(local, idx - 1))
-			return -EINVAL;
-		idx--;
-	} else {
-		idx = get_wep_tx_idx(local);
-		if (idx < 0)
-			idx = 0;
-	}
-
-	encoding->flags = idx + 1;
-	memset(ext, 0, sizeof(*ext));
-
-	/* Check encryption mode */
-	switch(local->config.authType) {
-		case AUTH_ENCRYPT:
-			encoding->flags = IW_ENCODE_ALG_WEP | IW_ENCODE_ENABLED;
-			break;
-		case AUTH_SHAREDKEY:
-			encoding->flags = IW_ENCODE_ALG_WEP | IW_ENCODE_ENABLED;
-			break;
-		default:
-		case AUTH_OPEN:
-			encoding->flags = IW_ENCODE_ALG_NONE | IW_ENCODE_DISABLED;
-			break;
-	}
-	/* We can't return the key, so set the proper flag and return zero */
-	encoding->flags |= IW_ENCODE_NOKEY;
-	memset(extra, 0, 16);
-
-	/* Copy the key to the user buffer */
-	wep_key_len = get_wep_key(local, idx, &buf[0], sizeof(buf));
-	if (wep_key_len < 0) {
-		ext->key_len = 0;
-	} else {
-		ext->key_len = wep_key_len;
-		memcpy(extra, buf, ext->key_len);
-	}
-
-	return 0;
-}
-
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : set extended authentication parameters
- */
-static int airo_set_auth(struct net_device *dev,
-			       struct iw_request_info *info,
-			       union iwreq_data *wrqu, char *extra)
-{
-	struct airo_info *local = dev->ml_priv;
-	struct iw_param *param = &wrqu->param;
-	__le16 currentAuthType = local->config.authType;
-
-	switch (param->flags & IW_AUTH_INDEX) {
-	case IW_AUTH_WPA_VERSION:
-	case IW_AUTH_CIPHER_PAIRWISE:
-	case IW_AUTH_CIPHER_GROUP:
-	case IW_AUTH_KEY_MGMT:
-	case IW_AUTH_RX_UNENCRYPTED_EAPOL:
-	case IW_AUTH_PRIVACY_INVOKED:
-		/*
-		 * airo does not use these parameters
-		 */
-		break;
-
-	case IW_AUTH_DROP_UNENCRYPTED:
-		if (param->value) {
-			/* Only change auth type if unencrypted */
-			if (currentAuthType == AUTH_OPEN)
-				set_auth_type(local, AUTH_ENCRYPT);
-		} else {
-			set_auth_type(local, AUTH_OPEN);
-		}
-
-		/* Commit the changes to flags if needed */
-		if (local->config.authType != currentAuthType)
-			set_bit (FLAG_COMMIT, &local->flags);
-		break;
-
-	case IW_AUTH_80211_AUTH_ALG: {
-			if (param->value & IW_AUTH_ALG_SHARED_KEY) {
-				set_auth_type(local, AUTH_SHAREDKEY);
-			} else if (param->value & IW_AUTH_ALG_OPEN_SYSTEM) {
-				/* We don't know here if WEP open system or
-				 * unencrypted mode was requested - so use the
-				 * last mode (of these two) used last time
-				 */
-				set_auth_type(local, local->last_auth);
-			} else
-				return -EINVAL;
-
-			/* Commit the changes to flags if needed */
-			if (local->config.authType != currentAuthType)
-				set_bit (FLAG_COMMIT, &local->flags);
-			break;
-		}
-
-	case IW_AUTH_WPA_ENABLED:
-		/* Silently accept disable of WPA */
-		if (param->value > 0)
-			return -EOPNOTSUPP;
-		break;
-
-	default:
-		return -EOPNOTSUPP;
-	}
-	return -EINPROGRESS;
-}
-
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get extended authentication parameters
- */
-static int airo_get_auth(struct net_device *dev,
-			       struct iw_request_info *info,
-			       union iwreq_data *wrqu, char *extra)
-{
-	struct airo_info *local = dev->ml_priv;
-	struct iw_param *param = &wrqu->param;
-	__le16 currentAuthType = local->config.authType;
-
-	switch (param->flags & IW_AUTH_INDEX) {
-	case IW_AUTH_DROP_UNENCRYPTED:
-		switch (currentAuthType) {
-		case AUTH_SHAREDKEY:
-		case AUTH_ENCRYPT:
-			param->value = 1;
-			break;
-		default:
-			param->value = 0;
-			break;
-		}
-		break;
-
-	case IW_AUTH_80211_AUTH_ALG:
-		switch (currentAuthType) {
-		case AUTH_SHAREDKEY:
-			param->value = IW_AUTH_ALG_SHARED_KEY;
-			break;
-		case AUTH_ENCRYPT:
-		default:
-			param->value = IW_AUTH_ALG_OPEN_SYSTEM;
-			break;
-		}
-		break;
-
-	case IW_AUTH_WPA_ENABLED:
-		param->value = 0;
-		break;
-
-	default:
-		return -EOPNOTSUPP;
-	}
-	return 0;
-}
-
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : set Tx-Power
- */
-static int airo_set_txpow(struct net_device *dev,
-			  struct iw_request_info *info,
-			  union iwreq_data *wrqu,
-			  char *extra)
-{
-	struct iw_param *vwrq = &wrqu->txpower;
-	struct airo_info *local = dev->ml_priv;
-	CapabilityRid cap_rid;		/* Card capability info */
-	int i;
-	int rc = -EINVAL;
-	__le16 v = cpu_to_le16(vwrq->value);
-
-	readCapabilityRid(local, &cap_rid, 1);
-
-	if (vwrq->disabled) {
-		set_bit (FLAG_RADIO_OFF, &local->flags);
-		set_bit (FLAG_COMMIT, &local->flags);
-		return -EINPROGRESS;		/* Call commit handler */
-	}
-	if (vwrq->flags != IW_TXPOW_MWATT) {
-		return -EINVAL;
-	}
-	clear_bit (FLAG_RADIO_OFF, &local->flags);
-	for (i = 0; i < 8 && cap_rid.txPowerLevels[i]; i++)
-		if (v == cap_rid.txPowerLevels[i]) {
-			readConfigRid(local, 1);
-			local->config.txPower = v;
-			set_bit (FLAG_COMMIT, &local->flags);
-			rc = -EINPROGRESS;	/* Call commit handler */
-			break;
-		}
-	return rc;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get Tx-Power
- */
-static int airo_get_txpow(struct net_device *dev,
-			  struct iw_request_info *info,
-			  union iwreq_data *wrqu,
-			  char *extra)
-{
-	struct iw_param *vwrq = &wrqu->txpower;
-	struct airo_info *local = dev->ml_priv;
-
-	readConfigRid(local, 1);
-	vwrq->value = le16_to_cpu(local->config.txPower);
-	vwrq->fixed = 1;	/* No power control */
-	vwrq->disabled = test_bit(FLAG_RADIO_OFF, &local->flags);
-	vwrq->flags = IW_TXPOW_MWATT;
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : set Retry limits
- */
-static int airo_set_retry(struct net_device *dev,
-			  struct iw_request_info *info,
-			  union iwreq_data *wrqu,
-			  char *extra)
-{
-	struct iw_param *vwrq = &wrqu->retry;
-	struct airo_info *local = dev->ml_priv;
-	int rc = -EINVAL;
-
-	if (vwrq->disabled) {
-		return -EINVAL;
-	}
-	readConfigRid(local, 1);
-	if (vwrq->flags & IW_RETRY_LIMIT) {
-		__le16 v = cpu_to_le16(vwrq->value);
-		if (vwrq->flags & IW_RETRY_LONG)
-			local->config.longRetryLimit = v;
-		else if (vwrq->flags & IW_RETRY_SHORT)
-			local->config.shortRetryLimit = v;
-		else {
-			/* No modifier : set both */
-			local->config.longRetryLimit = v;
-			local->config.shortRetryLimit = v;
-		}
-		set_bit (FLAG_COMMIT, &local->flags);
-		rc = -EINPROGRESS;		/* Call commit handler */
-	}
-	if (vwrq->flags & IW_RETRY_LIFETIME) {
-		local->config.txLifetime = cpu_to_le16(vwrq->value / 1024);
-		set_bit (FLAG_COMMIT, &local->flags);
-		rc = -EINPROGRESS;		/* Call commit handler */
-	}
-	return rc;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get Retry limits
- */
-static int airo_get_retry(struct net_device *dev,
-			  struct iw_request_info *info,
-			  union iwreq_data *wrqu,
-			  char *extra)
-{
-	struct iw_param *vwrq = &wrqu->retry;
-	struct airo_info *local = dev->ml_priv;
-
-	vwrq->disabled = 0;      /* Can't be disabled */
-
-	readConfigRid(local, 1);
-	/* Note : by default, display the min retry number */
-	if ((vwrq->flags & IW_RETRY_TYPE) == IW_RETRY_LIFETIME) {
-		vwrq->flags = IW_RETRY_LIFETIME;
-		vwrq->value = le16_to_cpu(local->config.txLifetime) * 1024;
-	} else if ((vwrq->flags & IW_RETRY_LONG)) {
-		vwrq->flags = IW_RETRY_LIMIT | IW_RETRY_LONG;
-		vwrq->value = le16_to_cpu(local->config.longRetryLimit);
-	} else {
-		vwrq->flags = IW_RETRY_LIMIT;
-		vwrq->value = le16_to_cpu(local->config.shortRetryLimit);
-		if (local->config.shortRetryLimit != local->config.longRetryLimit)
-			vwrq->flags |= IW_RETRY_SHORT;
-	}
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get range info
- */
-static int airo_get_range(struct net_device *dev,
-			  struct iw_request_info *info,
-			  union iwreq_data *wrqu,
-			  char *extra)
-{
-	struct iw_point *dwrq = &wrqu->data;
-	struct airo_info *local = dev->ml_priv;
-	struct iw_range *range = (struct iw_range *) extra;
-	CapabilityRid cap_rid;		/* Card capability info */
-	int		i;
-	int		k;
-
-	readCapabilityRid(local, &cap_rid, 1);
-
-	dwrq->length = sizeof(struct iw_range);
-	memset(range, 0, sizeof(*range));
-	range->min_nwid = 0x0000;
-	range->max_nwid = 0x0000;
-	range->num_channels = 14;
-	/* Should be based on cap_rid.country to give only
-	 * what the current card support */
-	k = 0;
-	for (i = 0; i < 14; i++) {
-		range->freq[k].i = i + 1; /* List index */
-		range->freq[k].m = 100000 *
-		     ieee80211_channel_to_frequency(i + 1, NL80211_BAND_2GHZ);
-		range->freq[k++].e = 1;	/* Values in MHz -> * 10^5 * 10 */
-	}
-	range->num_frequency = k;
-
-	range->sensitivity = 65535;
-
-	/* Hum... Should put the right values there */
-	if (local->rssi)
-		range->max_qual.qual = 100;	/* % */
-	else
-		range->max_qual.qual = airo_get_max_quality(&cap_rid);
-	range->max_qual.level = 0x100 - 120;	/* -120 dBm */
-	range->max_qual.noise = 0x100 - 120;	/* -120 dBm */
-
-	/* Experimental measurements - boundary 11/5.5 Mb/s */
-	/* Note : with or without the (local->rssi), results
-	 * are somewhat different. - Jean II */
-	if (local->rssi) {
-		range->avg_qual.qual = 50;		/* % */
-		range->avg_qual.level = 0x100 - 70;	/* -70 dBm */
-	} else {
-		range->avg_qual.qual = airo_get_avg_quality(&cap_rid);
-		range->avg_qual.level = 0x100 - 80;	/* -80 dBm */
-	}
-	range->avg_qual.noise = 0x100 - 85;		/* -85 dBm */
-
-	for (i = 0 ; i < 8 ; i++) {
-		range->bitrate[i] = cap_rid.supportedRates[i] * 500000;
-		if (range->bitrate[i] == 0)
-			break;
-	}
-	range->num_bitrates = i;
-
-	/* Set an indication of the max TCP throughput
-	 * in bit/s that we can expect using this interface.
-	 * May be use for QoS stuff... Jean II */
-	if (i > 2)
-		range->throughput = 5000 * 1000;
-	else
-		range->throughput = 1500 * 1000;
-
-	range->min_rts = 0;
-	range->max_rts = AIRO_DEF_MTU;
-	range->min_frag = 256;
-	range->max_frag = AIRO_DEF_MTU;
-
-	if (cap_rid.softCap & cpu_to_le16(2)) {
-		// WEP: RC4 40 bits
-		range->encoding_size[0] = 5;
-		// RC4 ~128 bits
-		if (cap_rid.softCap & cpu_to_le16(0x100)) {
-			range->encoding_size[1] = 13;
-			range->num_encoding_sizes = 2;
-		} else
-			range->num_encoding_sizes = 1;
-		range->max_encoding_tokens =
-			cap_rid.softCap & cpu_to_le16(0x80) ? 4 : 1;
-	} else {
-		range->num_encoding_sizes = 0;
-		range->max_encoding_tokens = 0;
-	}
-	range->min_pmp = 0;
-	range->max_pmp = 5000000;	/* 5 secs */
-	range->min_pmt = 0;
-	range->max_pmt = 65535 * 1024;	/* ??? */
-	range->pmp_flags = IW_POWER_PERIOD;
-	range->pmt_flags = IW_POWER_TIMEOUT;
-	range->pm_capa = IW_POWER_PERIOD | IW_POWER_TIMEOUT | IW_POWER_ALL_R;
-
-	/* Transmit Power - values are in mW */
-	for (i = 0 ; i < 8 ; i++) {
-		range->txpower[i] = le16_to_cpu(cap_rid.txPowerLevels[i]);
-		if (range->txpower[i] == 0)
-			break;
-	}
-	range->num_txpower = i;
-	range->txpower_capa = IW_TXPOW_MWATT;
-	range->we_version_source = 19;
-	range->we_version_compiled = WIRELESS_EXT;
-	range->retry_capa = IW_RETRY_LIMIT | IW_RETRY_LIFETIME;
-	range->retry_flags = IW_RETRY_LIMIT;
-	range->r_time_flags = IW_RETRY_LIFETIME;
-	range->min_retry = 1;
-	range->max_retry = 65535;
-	range->min_r_time = 1024;
-	range->max_r_time = 65535 * 1024;
-
-	/* Event capability (kernel + driver) */
-	range->event_capa[0] = (IW_EVENT_CAPA_K_0 |
-				IW_EVENT_CAPA_MASK(SIOCGIWTHRSPY) |
-				IW_EVENT_CAPA_MASK(SIOCGIWAP) |
-				IW_EVENT_CAPA_MASK(SIOCGIWSCAN));
-	range->event_capa[1] = IW_EVENT_CAPA_K_1;
-	range->event_capa[4] = IW_EVENT_CAPA_MASK(IWEVTXDROP);
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : set Power Management
- */
-static int airo_set_power(struct net_device *dev,
-			  struct iw_request_info *info,
-			  union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *vwrq = &wrqu->power;
-	struct airo_info *local = dev->ml_priv;
-
-	readConfigRid(local, 1);
-	if (vwrq->disabled) {
-		if (sniffing_mode(local))
-			return -EINVAL;
-		local->config.powerSaveMode = POWERSAVE_CAM;
-		local->config.rmode &= ~RXMODE_MASK;
-		local->config.rmode |= RXMODE_BC_MC_ADDR;
-		set_bit (FLAG_COMMIT, &local->flags);
-		return -EINPROGRESS;		/* Call commit handler */
-	}
-	if ((vwrq->flags & IW_POWER_TYPE) == IW_POWER_TIMEOUT) {
-		local->config.fastListenDelay = cpu_to_le16((vwrq->value + 500) / 1024);
-		local->config.powerSaveMode = POWERSAVE_PSPCAM;
-		set_bit (FLAG_COMMIT, &local->flags);
-	} else if ((vwrq->flags & IW_POWER_TYPE) == IW_POWER_PERIOD) {
-		local->config.fastListenInterval =
-		local->config.listenInterval =
-			cpu_to_le16((vwrq->value + 500) / 1024);
-		local->config.powerSaveMode = POWERSAVE_PSPCAM;
-		set_bit (FLAG_COMMIT, &local->flags);
-	}
-	switch (vwrq->flags & IW_POWER_MODE) {
-		case IW_POWER_UNICAST_R:
-			if (sniffing_mode(local))
-				return -EINVAL;
-			local->config.rmode &= ~RXMODE_MASK;
-			local->config.rmode |= RXMODE_ADDR;
-			set_bit (FLAG_COMMIT, &local->flags);
-			break;
-		case IW_POWER_ALL_R:
-			if (sniffing_mode(local))
-				return -EINVAL;
-			local->config.rmode &= ~RXMODE_MASK;
-			local->config.rmode |= RXMODE_BC_MC_ADDR;
-			set_bit (FLAG_COMMIT, &local->flags);
-			break;
-		case IW_POWER_ON:
-			/* This is broken, fixme ;-) */
-			break;
-		default:
-			return -EINVAL;
-	}
-	// Note : we may want to factor local->need_commit here
-	// Note2 : may also want to factor RXMODE_RFMON test
-	return -EINPROGRESS;		/* Call commit handler */
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get Power Management
- */
-static int airo_get_power(struct net_device *dev,
-			  struct iw_request_info *info,
-			  union iwreq_data *wrqu,
-			  char *extra)
-{
-	struct iw_param *vwrq = &wrqu->power;
-	struct airo_info *local = dev->ml_priv;
-	__le16 mode;
-
-	readConfigRid(local, 1);
-	mode = local->config.powerSaveMode;
-	if ((vwrq->disabled = (mode == POWERSAVE_CAM)))
-		return 0;
-	if ((vwrq->flags & IW_POWER_TYPE) == IW_POWER_TIMEOUT) {
-		vwrq->value = le16_to_cpu(local->config.fastListenDelay) * 1024;
-		vwrq->flags = IW_POWER_TIMEOUT;
-	} else {
-		vwrq->value = le16_to_cpu(local->config.fastListenInterval) * 1024;
-		vwrq->flags = IW_POWER_PERIOD;
-	}
-	if ((local->config.rmode & RXMODE_MASK) == RXMODE_ADDR)
-		vwrq->flags |= IW_POWER_UNICAST_R;
-	else
-		vwrq->flags |= IW_POWER_ALL_R;
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : set Sensitivity
- */
-static int airo_set_sens(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *wrqu,
-			 char *extra)
-{
-	struct iw_param *vwrq = &wrqu->sens;
-	struct airo_info *local = dev->ml_priv;
-
-	readConfigRid(local, 1);
-	local->config.rssiThreshold =
-		cpu_to_le16(vwrq->disabled ? RSSI_DEFAULT : vwrq->value);
-	set_bit (FLAG_COMMIT, &local->flags);
-
-	return -EINPROGRESS;		/* Call commit handler */
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get Sensitivity
- */
-static int airo_get_sens(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *wrqu,
-			 char *extra)
-{
-	struct iw_param *vwrq = &wrqu->sens;
-	struct airo_info *local = dev->ml_priv;
-
-	readConfigRid(local, 1);
-	vwrq->value = le16_to_cpu(local->config.rssiThreshold);
-	vwrq->disabled = (vwrq->value == 0);
-	vwrq->fixed = 1;
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get AP List
- * Note : this is deprecated in favor of IWSCAN
- */
-static int airo_get_aplist(struct net_device *dev,
-			   struct iw_request_info *info,
-			   union iwreq_data *wrqu,
-			   char *extra)
-{
-	struct iw_point *dwrq = &wrqu->data;
-	struct airo_info *local = dev->ml_priv;
-	struct sockaddr *address = (struct sockaddr *) extra;
-	struct iw_quality *qual;
-	BSSListRid BSSList;
-	int i;
-	int loseSync = capable(CAP_NET_ADMIN) ? 1: -1;
-
-	qual = kmalloc_array(IW_MAX_AP, sizeof(*qual), GFP_KERNEL);
-	if (!qual)
-		return -ENOMEM;
-
-	for (i = 0; i < IW_MAX_AP; i++) {
-		u16 dBm;
-		if (readBSSListRid(local, loseSync, &BSSList))
-			break;
-		loseSync = 0;
-		memcpy(address[i].sa_data, BSSList.bssid, ETH_ALEN);
-		address[i].sa_family = ARPHRD_ETHER;
-		dBm = le16_to_cpu(BSSList.dBm);
-		if (local->rssi) {
-			qual[i].level = 0x100 - dBm;
-			qual[i].qual = airo_dbm_to_pct(local->rssi, dBm);
-			qual[i].updated = IW_QUAL_QUAL_UPDATED
-					| IW_QUAL_LEVEL_UPDATED
-					| IW_QUAL_DBM;
-		} else {
-			qual[i].level = (dBm + 321) / 2;
-			qual[i].qual = 0;
-			qual[i].updated = IW_QUAL_QUAL_INVALID
-					| IW_QUAL_LEVEL_UPDATED
-					| IW_QUAL_DBM;
-		}
-		qual[i].noise = local->wstats.qual.noise;
-		if (BSSList.index == cpu_to_le16(0xffff))
-			break;
-	}
-	if (!i) {
-		StatusRid status_rid;		/* Card status info */
-		readStatusRid(local, &status_rid, 1);
-		for (i = 0;
-		     i < min(IW_MAX_AP, 4) &&
-			     (status_rid.bssid[i][0]
-			      & status_rid.bssid[i][1]
-			      & status_rid.bssid[i][2]
-			      & status_rid.bssid[i][3]
-			      & status_rid.bssid[i][4]
-			      & status_rid.bssid[i][5])!=0xff &&
-			     (status_rid.bssid[i][0]
-			      | status_rid.bssid[i][1]
-			      | status_rid.bssid[i][2]
-			      | status_rid.bssid[i][3]
-			      | status_rid.bssid[i][4]
-			      | status_rid.bssid[i][5]);
-		     i++) {
-			memcpy(address[i].sa_data,
-			       status_rid.bssid[i], ETH_ALEN);
-			address[i].sa_family = ARPHRD_ETHER;
-		}
-	} else {
-		dwrq->flags = 1; /* Should be define'd */
-		memcpy(extra + sizeof(struct sockaddr) * i, qual,
-		       sizeof(struct iw_quality) * i);
-	}
-	dwrq->length = i;
-
-	kfree(qual);
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : Initiate Scan
- */
-static int airo_set_scan(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *wrqu,
-			 char *extra)
-{
-	struct airo_info *ai = dev->ml_priv;
-	Cmd cmd;
-	Resp rsp;
-	int wake = 0;
-	APListRid APList_rid_empty;
-
-	/* Note : you may have realised that, as this is a SET operation,
-	 * this is privileged and therefore a normal user can't
-	 * perform scanning.
-	 * This is not an error, while the device perform scanning,
-	 * traffic doesn't flow, so it's a perfect DoS...
-	 * Jean II */
-	if (ai->flags & FLAG_RADIO_MASK) return -ENETDOWN;
-
-	if (down_interruptible(&ai->sem))
-		return -ERESTARTSYS;
-
-	/* If there's already a scan in progress, don't
-	 * trigger another one. */
-	if (ai->scan_timeout > 0)
-		goto out;
-
-	/* Clear APList as it affects scan results */
-	memset(&APList_rid_empty, 0, sizeof(APList_rid_empty));
-	APList_rid_empty.len = cpu_to_le16(sizeof(APList_rid_empty));
-	disable_MAC(ai, 2);
-	writeAPListRid(ai, &APList_rid_empty, 0);
-	enable_MAC(ai, 0);
-
-	/* Initiate a scan command */
-	ai->scan_timeout = RUN_AT(3*HZ);
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.cmd = CMD_LISTBSS;
-	issuecommand(ai, &cmd, &rsp, true);
-	wake = 1;
-
-out:
-	up(&ai->sem);
-	if (wake)
-		wake_up_interruptible(&ai->thr_wait);
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Translate scan data returned from the card to a card independent
- * format that the Wireless Tools will understand - Jean II
- */
-static inline char *airo_translate_scan(struct net_device *dev,
-					struct iw_request_info *info,
-					char *current_ev,
-					char *end_buf,
-					BSSListRid *bss)
-{
-	struct airo_info *ai = dev->ml_priv;
-	struct iw_event		iwe;		/* Temporary buffer */
-	__le16			capabilities;
-	char *			current_val;	/* For rates */
-	int			i;
-	char *		buf;
-	u16 dBm;
-
-	/* First entry *MUST* be the AP MAC address */
-	iwe.cmd = SIOCGIWAP;
-	iwe.u.ap_addr.sa_family = ARPHRD_ETHER;
-	memcpy(iwe.u.ap_addr.sa_data, bss->bssid, ETH_ALEN);
-	current_ev = iwe_stream_add_event(info, current_ev, end_buf,
-					  &iwe, IW_EV_ADDR_LEN);
-
-	/* Other entries will be displayed in the order we give them */
-
-	/* Add the ESSID */
-	iwe.u.data.length = bss->ssidLen;
-	if (iwe.u.data.length > 32)
-		iwe.u.data.length = 32;
-	iwe.cmd = SIOCGIWESSID;
-	iwe.u.data.flags = 1;
-	current_ev = iwe_stream_add_point(info, current_ev, end_buf,
-					  &iwe, bss->ssid);
-
-	/* Add mode */
-	iwe.cmd = SIOCGIWMODE;
-	capabilities = bss->cap;
-	if (capabilities & (CAP_ESS | CAP_IBSS)) {
-		if (capabilities & CAP_ESS)
-			iwe.u.mode = IW_MODE_MASTER;
-		else
-			iwe.u.mode = IW_MODE_ADHOC;
-		current_ev = iwe_stream_add_event(info, current_ev, end_buf,
-						  &iwe, IW_EV_UINT_LEN);
-	}
-
-	/* Add frequency */
-	iwe.cmd = SIOCGIWFREQ;
-	iwe.u.freq.m = le16_to_cpu(bss->dsChannel);
-	iwe.u.freq.m = 100000 *
-	      ieee80211_channel_to_frequency(iwe.u.freq.m, NL80211_BAND_2GHZ);
-	iwe.u.freq.e = 1;
-	current_ev = iwe_stream_add_event(info, current_ev, end_buf,
-					  &iwe, IW_EV_FREQ_LEN);
-
-	dBm = le16_to_cpu(bss->dBm);
-
-	/* Add quality statistics */
-	iwe.cmd = IWEVQUAL;
-	if (ai->rssi) {
-		iwe.u.qual.level = 0x100 - dBm;
-		iwe.u.qual.qual = airo_dbm_to_pct(ai->rssi, dBm);
-		iwe.u.qual.updated = IW_QUAL_QUAL_UPDATED
-				| IW_QUAL_LEVEL_UPDATED
-				| IW_QUAL_DBM;
-	} else {
-		iwe.u.qual.level = (dBm + 321) / 2;
-		iwe.u.qual.qual = 0;
-		iwe.u.qual.updated = IW_QUAL_QUAL_INVALID
-				| IW_QUAL_LEVEL_UPDATED
-				| IW_QUAL_DBM;
-	}
-	iwe.u.qual.noise = ai->wstats.qual.noise;
-	current_ev = iwe_stream_add_event(info, current_ev, end_buf,
-					  &iwe, IW_EV_QUAL_LEN);
-
-	/* Add encryption capability */
-	iwe.cmd = SIOCGIWENCODE;
-	if (capabilities & CAP_PRIVACY)
-		iwe.u.data.flags = IW_ENCODE_ENABLED | IW_ENCODE_NOKEY;
-	else
-		iwe.u.data.flags = IW_ENCODE_DISABLED;
-	iwe.u.data.length = 0;
-	current_ev = iwe_stream_add_point(info, current_ev, end_buf,
-					  &iwe, bss->ssid);
-
-	/* Rate : stuffing multiple values in a single event require a bit
-	 * more of magic - Jean II */
-	current_val = current_ev + iwe_stream_lcp_len(info);
-
-	iwe.cmd = SIOCGIWRATE;
-	/* Those two flags are ignored... */
-	iwe.u.bitrate.fixed = iwe.u.bitrate.disabled = 0;
-	/* Max 8 values */
-	for (i = 0 ; i < 8 ; i++) {
-		/* NULL terminated */
-		if (bss->rates[i] == 0)
-			break;
-		/* Bit rate given in 500 kb/s units (+ 0x80) */
-		iwe.u.bitrate.value = ((bss->rates[i] & 0x7f) * 500000);
-		/* Add new value to event */
-		current_val = iwe_stream_add_value(info, current_ev,
-						   current_val, end_buf,
-						   &iwe, IW_EV_PARAM_LEN);
-	}
-	/* Check if we added any event */
-	if ((current_val - current_ev) > iwe_stream_lcp_len(info))
-		current_ev = current_val;
-
-	/* Beacon interval */
-	buf = kmalloc(30, GFP_KERNEL);
-	if (buf) {
-		iwe.cmd = IWEVCUSTOM;
-		sprintf(buf, "bcn_int=%d", bss->beaconInterval);
-		iwe.u.data.length = strlen(buf);
-		current_ev = iwe_stream_add_point(info, current_ev, end_buf,
-						  &iwe, buf);
-		kfree(buf);
-	}
-
-	/* Put WPA/RSN Information Elements into the event stream */
-	if (test_bit(FLAG_WPA_CAPABLE, &ai->flags)) {
-		unsigned int num_null_ies = 0;
-		u16 length = sizeof (bss->extra.iep);
-		u8 *ie = (void *)&bss->extra.iep;
-
-		while ((length >= 2) && (num_null_ies < 2)) {
-			if (2 + ie[1] > length) {
-				/* Invalid element, don't continue parsing IE */
-				break;
-			}
-
-			switch (ie[0]) {
-			case WLAN_EID_SSID:
-				/* Two zero-length SSID elements
-				 * mean we're done parsing elements */
-				if (!ie[1])
-					num_null_ies++;
-				break;
-
-			case WLAN_EID_VENDOR_SPECIFIC:
-				if (ie[1] >= 4 &&
-				    ie[2] == 0x00 &&
-				    ie[3] == 0x50 &&
-				    ie[4] == 0xf2 &&
-				    ie[5] == 0x01) {
-					iwe.cmd = IWEVGENIE;
-					/* 64 is an arbitrary cut-off */
-					iwe.u.data.length = min(ie[1] + 2,
-								64);
-					current_ev = iwe_stream_add_point(
-							info, current_ev,
-							end_buf, &iwe, ie);
-				}
-				break;
-
-			case WLAN_EID_RSN:
-				iwe.cmd = IWEVGENIE;
-				/* 64 is an arbitrary cut-off */
-				iwe.u.data.length = min(ie[1] + 2, 64);
-				current_ev = iwe_stream_add_point(
-					info, current_ev, end_buf,
-					&iwe, ie);
-				break;
-
-			default:
-				break;
-			}
-
-			length -= 2 + ie[1];
-			ie += 2 + ie[1];
-		}
-	}
-	return current_ev;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : Read Scan Results
- */
-static int airo_get_scan(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *wrqu,
-			 char *extra)
-{
-	struct iw_point *dwrq = &wrqu->data;
-	struct airo_info *ai = dev->ml_priv;
-	BSSListElement *net;
-	int err = 0;
-	char *current_ev = extra;
-
-	/* If a scan is in-progress, return -EAGAIN */
-	if (ai->scan_timeout > 0)
-		return -EAGAIN;
-
-	if (down_interruptible(&ai->sem))
-		return -EAGAIN;
-
-	list_for_each_entry (net, &ai->network_list, list) {
-		/* Translate to WE format this entry */
-		current_ev = airo_translate_scan(dev, info, current_ev,
-						 extra + dwrq->length,
-						 &net->bss);
-
-		/* Check if there is space for one more entry */
-		if ((extra + dwrq->length - current_ev) <= IW_EV_ADDR_LEN) {
-			/* Ask user space to try again with a bigger buffer */
-			err = -E2BIG;
-			goto out;
-		}
-	}
-
-	/* Length of data */
-	dwrq->length = (current_ev - extra);
-	dwrq->flags = 0;	/* todo */
-
-out:
-	up(&ai->sem);
-	return err;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Commit handler : called after a bunch of SET operations
- */
-static int airo_config_commit(struct net_device *dev,
-			      struct iw_request_info *info,	/* NULL */
-			      union iwreq_data *wrqu,		/* NULL */
-			      char *extra)			/* NULL */
-{
-	struct airo_info *local = dev->ml_priv;
-
-	if (!test_bit (FLAG_COMMIT, &local->flags))
-		return 0;
-
-	/* Some of the "SET" function may have modified some of the
-	 * parameters. It's now time to commit them in the card */
-	disable_MAC(local, 1);
-	if (test_bit (FLAG_RESET, &local->flags)) {
-		SsidRid SSID_rid;
-
-		readSsidRid(local, &SSID_rid);
-		if (test_bit(FLAG_MPI,&local->flags))
-			setup_card(local, dev, 1);
-		else
-			reset_airo_card(dev);
-		disable_MAC(local, 1);
-		writeSsidRid(local, &SSID_rid, 1);
-		writeAPListRid(local, &local->APList, 1);
-	}
-	if (down_interruptible(&local->sem))
-		return -ERESTARTSYS;
-	writeConfigRid(local, 0);
-	enable_MAC(local, 0);
-	if (test_bit (FLAG_RESET, &local->flags))
-		airo_set_promisc(local, true);
-	else
-		up(&local->sem);
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Structures to export the Wireless Handlers
- */
-
-static const struct iw_priv_args airo_private_args[] = {
-/*{ cmd,         set_args,                            get_args, name } */
-  { AIROIOCTL, IW_PRIV_TYPE_BYTE | IW_PRIV_SIZE_FIXED | sizeof (aironet_ioctl),
-    IW_PRIV_TYPE_BYTE | 2047, "airoioctl" },
-  { AIROIDIFC, IW_PRIV_TYPE_BYTE | IW_PRIV_SIZE_FIXED | sizeof (aironet_ioctl),
-    IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "airoidifc" },
-};
-
-static const iw_handler		airo_handler[] =
-{
-	IW_HANDLER(SIOCSIWCOMMIT,	airo_config_commit),
-	IW_HANDLER(SIOCGIWNAME,		airo_get_name),
-	IW_HANDLER(SIOCSIWFREQ,		airo_set_freq),
-	IW_HANDLER(SIOCGIWFREQ,		airo_get_freq),
-	IW_HANDLER(SIOCSIWMODE,		airo_set_mode),
-	IW_HANDLER(SIOCGIWMODE,		airo_get_mode),
-	IW_HANDLER(SIOCSIWSENS,		airo_set_sens),
-	IW_HANDLER(SIOCGIWSENS,		airo_get_sens),
-	IW_HANDLER(SIOCGIWRANGE,	airo_get_range),
-	IW_HANDLER(SIOCSIWSPY,		iw_handler_set_spy),
-	IW_HANDLER(SIOCGIWSPY,		iw_handler_get_spy),
-	IW_HANDLER(SIOCSIWTHRSPY,	iw_handler_set_thrspy),
-	IW_HANDLER(SIOCGIWTHRSPY,	iw_handler_get_thrspy),
-	IW_HANDLER(SIOCSIWAP,		airo_set_wap),
-	IW_HANDLER(SIOCGIWAP,		airo_get_wap),
-	IW_HANDLER(SIOCGIWAPLIST,	airo_get_aplist),
-	IW_HANDLER(SIOCSIWSCAN,		airo_set_scan),
-	IW_HANDLER(SIOCGIWSCAN,		airo_get_scan),
-	IW_HANDLER(SIOCSIWESSID,	airo_set_essid),
-	IW_HANDLER(SIOCGIWESSID,	airo_get_essid),
-	IW_HANDLER(SIOCSIWNICKN,	airo_set_nick),
-	IW_HANDLER(SIOCGIWNICKN,	airo_get_nick),
-	IW_HANDLER(SIOCSIWRATE,		airo_set_rate),
-	IW_HANDLER(SIOCGIWRATE,		airo_get_rate),
-	IW_HANDLER(SIOCSIWRTS,		airo_set_rts),
-	IW_HANDLER(SIOCGIWRTS,		airo_get_rts),
-	IW_HANDLER(SIOCSIWFRAG,		airo_set_frag),
-	IW_HANDLER(SIOCGIWFRAG,		airo_get_frag),
-	IW_HANDLER(SIOCSIWTXPOW,	airo_set_txpow),
-	IW_HANDLER(SIOCGIWTXPOW,	airo_get_txpow),
-	IW_HANDLER(SIOCSIWRETRY,	airo_set_retry),
-	IW_HANDLER(SIOCGIWRETRY,	airo_get_retry),
-	IW_HANDLER(SIOCSIWENCODE,	airo_set_encode),
-	IW_HANDLER(SIOCGIWENCODE,	airo_get_encode),
-	IW_HANDLER(SIOCSIWPOWER,	airo_set_power),
-	IW_HANDLER(SIOCGIWPOWER,	airo_get_power),
-	IW_HANDLER(SIOCSIWAUTH,		airo_set_auth),
-	IW_HANDLER(SIOCGIWAUTH,		airo_get_auth),
-	IW_HANDLER(SIOCSIWENCODEEXT,	airo_set_encodeext),
-	IW_HANDLER(SIOCGIWENCODEEXT,	airo_get_encodeext),
-};
-
-/* Note : don't describe AIROIDIFC and AIROOLDIDIFC in here.
- * We want to force the use of the ioctl code, because those can't be
- * won't work the iw_handler code (because they simultaneously read
- * and write data and iw_handler can't do that).
- * Note that it's perfectly legal to read/write on a single ioctl command,
- * you just can't use iwpriv and need to force it via the ioctl handler.
- * Jean II */
-static const iw_handler		airo_private_handler[] =
-{
-	NULL,				/* SIOCIWFIRSTPRIV */
-};
-
-static const struct iw_handler_def	airo_handler_def =
-{
-	.num_standard	= ARRAY_SIZE(airo_handler),
-	.num_private	= ARRAY_SIZE(airo_private_handler),
-	.num_private_args = ARRAY_SIZE(airo_private_args),
-	.standard	= airo_handler,
-	.private	= airo_private_handler,
-	.private_args	= airo_private_args,
-	.get_wireless_stats = airo_get_wireless_stats,
-};
-
-/*
- * This defines the configuration part of the Wireless Extensions
- * Note : irq and spinlock protection will occur in the subroutines
- *
- * TODO :
- *	o Check input value more carefully and fill correct values in range
- *	o Test and shakeout the bugs (if any)
- *
- * Jean II
- *
- * Javier Achirica did a great job of merging code from the unnamed CISCO
- * developer that added support for flashing the card.
- */
-static int airo_siocdevprivate(struct net_device *dev, struct ifreq *rq,
-			       void __user *data, int cmd)
-{
-	int rc = 0;
-	struct airo_info *ai = dev->ml_priv;
-
-	if (ai->power.event)
-		return 0;
-
-	switch (cmd) {
-#ifdef CISCO_EXT
-	case AIROIDIFC:
-#ifdef AIROOLDIDIFC
-	case AIROOLDIDIFC:
-#endif
-	{
-		int val = AIROMAGIC;
-		aironet_ioctl com;
-		if (copy_from_user(&com, data, sizeof(com)))
-			rc = -EFAULT;
-		else if (copy_to_user(com.data, (char *)&val, sizeof(val)))
-			rc = -EFAULT;
-	}
-	break;
-
-	case AIROIOCTL:
-#ifdef AIROOLDIOCTL
-	case AIROOLDIOCTL:
-#endif
-		/* Get the command struct and hand it off for evaluation by
-		 * the proper subfunction
-		 */
-	{
-		aironet_ioctl com;
-		if (copy_from_user(&com, data, sizeof(com))) {
-			rc = -EFAULT;
-			break;
-		}
-
-		/* Separate R/W functions bracket legality here
-		 */
-		if (com.command == AIRORSWVERSION) {
-			if (copy_to_user(com.data, swversion, sizeof(swversion)))
-				rc = -EFAULT;
-			else
-				rc = 0;
-		}
-		else if (com.command <= AIRORRID)
-			rc = readrids(dev,&com);
-		else if (com.command >= AIROPCAP && com.command <= (AIROPLEAPUSR+2))
-			rc = writerids(dev,&com);
-		else if (com.command >= AIROFLSHRST && com.command <= AIRORESTART)
-			rc = flashcard(dev,&com);
-		else
-			rc = -EINVAL;      /* Bad command in ioctl */
-	}
-	break;
-#endif /* CISCO_EXT */
-
-	// All other calls are currently unsupported
-	default:
-		rc = -EOPNOTSUPP;
-	}
-	return rc;
-}
-
-/*
- * Get the Wireless stats out of the driver
- * Note : irq and spinlock protection will occur in the subroutines
- *
- * TODO :
- *	o Check if work in Ad-Hoc mode (otherwise, use SPY, as in wvlan_cs)
- *
- * Jean
- */
-static void airo_read_wireless_stats(struct airo_info *local)
-{
-	StatusRid status_rid;
-	StatsRid stats_rid;
-	CapabilityRid cap_rid;
-	__le32 *vals = stats_rid.vals;
-
-	/* Get stats out of the card */
-	if (local->power.event)
-		return;
-
-	readCapabilityRid(local, &cap_rid, 0);
-	readStatusRid(local, &status_rid, 0);
-	readStatsRid(local, &stats_rid, RID_STATS, 0);
-
-	/* The status */
-	local->wstats.status = le16_to_cpu(status_rid.mode);
-
-	/* Signal quality and co */
-	if (local->rssi) {
-		local->wstats.qual.level =
-			airo_rssi_to_dbm(local->rssi,
-					 le16_to_cpu(status_rid.sigQuality));
-		/* normalizedSignalStrength appears to be a percentage */
-		local->wstats.qual.qual =
-			le16_to_cpu(status_rid.normalizedSignalStrength);
-	} else {
-		local->wstats.qual.level =
-			(le16_to_cpu(status_rid.normalizedSignalStrength) + 321) / 2;
-		local->wstats.qual.qual = airo_get_quality(&status_rid, &cap_rid);
-	}
-	if (le16_to_cpu(status_rid.len) >= 124) {
-		local->wstats.qual.noise = 0x100 - status_rid.noisedBm;
-		local->wstats.qual.updated = IW_QUAL_ALL_UPDATED | IW_QUAL_DBM;
-	} else {
-		local->wstats.qual.noise = 0;
-		local->wstats.qual.updated = IW_QUAL_QUAL_UPDATED | IW_QUAL_LEVEL_UPDATED | IW_QUAL_NOISE_INVALID | IW_QUAL_DBM;
-	}
-
-	/* Packets discarded in the wireless adapter due to wireless
-	 * specific problems */
-	local->wstats.discard.nwid = le32_to_cpu(vals[56]) +
-				     le32_to_cpu(vals[57]) +
-				     le32_to_cpu(vals[58]); /* SSID Mismatch */
-	local->wstats.discard.code = le32_to_cpu(vals[6]);/* RxWepErr */
-	local->wstats.discard.fragment = le32_to_cpu(vals[30]);
-	local->wstats.discard.retries = le32_to_cpu(vals[10]);
-	local->wstats.discard.misc = le32_to_cpu(vals[1]) +
-				     le32_to_cpu(vals[32]);
-	local->wstats.miss.beacon = le32_to_cpu(vals[34]);
-}
-
-static struct iw_statistics *airo_get_wireless_stats(struct net_device *dev)
-{
-	struct airo_info *local =  dev->ml_priv;
-
-	if (!down_interruptible(&local->sem)) {
-		airo_read_wireless_stats(local);
-		up(&local->sem);
-	}
-	return &local->wstats;
-}
-
-#ifdef CISCO_EXT
-/*
- * This just translates from driver IOCTL codes to the command codes to
- * feed to the radio's host interface. Things can be added/deleted
- * as needed.  This represents the READ side of control I/O to
- * the card
- */
-static int readrids(struct net_device *dev, aironet_ioctl *comp)
-{
-	unsigned short ridcode;
-	unsigned char *iobuf;
-	int len;
-	struct airo_info *ai = dev->ml_priv;
-
-	if (test_bit(FLAG_FLASHING, &ai->flags))
-		return -EIO;
-
-	switch(comp->command)
-	{
-	case AIROGCAP:      ridcode = RID_CAPABILITIES; break;
-	case AIROGCFG:      ridcode = RID_CONFIG;
-		if (test_bit(FLAG_COMMIT, &ai->flags)) {
-			disable_MAC (ai, 1);
-			writeConfigRid (ai, 1);
-			enable_MAC(ai, 1);
-		}
-		break;
-	case AIROGSLIST:    ridcode = RID_SSID;         break;
-	case AIROGVLIST:    ridcode = RID_APLIST;       break;
-	case AIROGDRVNAM:   ridcode = RID_DRVNAME;      break;
-	case AIROGEHTENC:   ridcode = RID_ETHERENCAP;   break;
-	case AIROGWEPKTMP:  ridcode = RID_WEP_TEMP;	break;
-	case AIROGWEPKNV:   ridcode = RID_WEP_PERM;	break;
-	case AIROGSTAT:     ridcode = RID_STATUS;       break;
-	case AIROGSTATSD32: ridcode = RID_STATSDELTA;   break;
-	case AIROGSTATSC32: ridcode = RID_STATS;        break;
-	case AIROGMICSTATS:
-		if (copy_to_user(comp->data, &ai->micstats,
-				 min((int)comp->len, (int)sizeof(ai->micstats))))
-			return -EFAULT;
-		return 0;
-	case AIRORRID:      ridcode = comp->ridnum;     break;
-	default:
-		return -EINVAL;
-	}
-
-	if (ridcode == RID_WEP_TEMP || ridcode == RID_WEP_PERM) {
-		/* Only super-user can read WEP keys */
-		if (!capable(CAP_NET_ADMIN))
-			return -EPERM;
-	}
-
-	if ((iobuf = kzalloc(RIDSIZE, GFP_KERNEL)) == NULL)
-		return -ENOMEM;
-
-	PC4500_readrid(ai, ridcode, iobuf, RIDSIZE, 1);
-	/* get the count of bytes in the rid  docs say 1st 2 bytes is it.
-	 * then return it to the user
-	 * 9/22/2000 Honor user given length
-	 */
-	len = comp->len;
-
-	if (copy_to_user(comp->data, iobuf, min(len, (int)RIDSIZE))) {
-		kfree (iobuf);
-		return -EFAULT;
-	}
-	kfree (iobuf);
-	return 0;
-}
-
-/*
- * Danger Will Robinson write the rids here
- */
-
-static int writerids(struct net_device *dev, aironet_ioctl *comp)
-{
-	struct airo_info *ai = dev->ml_priv;
-	int  ridcode;
-        int  enabled;
-	int (*writer)(struct airo_info *, u16 rid, const void *, int, int);
-	unsigned char *iobuf;
-
-	/* Only super-user can write RIDs */
-	if (!capable(CAP_NET_ADMIN))
-		return -EPERM;
-
-	if (test_bit(FLAG_FLASHING, &ai->flags))
-		return -EIO;
-
-	ridcode = 0;
-	writer = do_writerid;
-
-	switch(comp->command)
-	{
-	case AIROPSIDS:     ridcode = RID_SSID;         break;
-	case AIROPCAP:      ridcode = RID_CAPABILITIES; break;
-	case AIROPAPLIST:   ridcode = RID_APLIST;       break;
-	case AIROPCFG: ai->config.len = 0;
-			    clear_bit(FLAG_COMMIT, &ai->flags);
-			    ridcode = RID_CONFIG;       break;
-	case AIROPWEPKEYNV: ridcode = RID_WEP_PERM;     break;
-	case AIROPLEAPUSR:  ridcode = RID_LEAPUSERNAME; break;
-	case AIROPLEAPPWD:  ridcode = RID_LEAPPASSWORD; break;
-	case AIROPWEPKEY:   ridcode = RID_WEP_TEMP; writer = PC4500_writerid;
-		break;
-	case AIROPLEAPUSR+1: ridcode = 0xFF2A;          break;
-	case AIROPLEAPUSR+2: ridcode = 0xFF2B;          break;
-
-		/* this is not really a rid but a command given to the card
-		 * same with MAC off
-		 */
-	case AIROPMACON:
-		if (enable_MAC(ai, 1) != 0)
-			return -EIO;
-		return 0;
-
-		/*
-		 * Evidently this code in the airo driver does not get a symbol
-		 * as disable_MAC. it's probably so short the compiler does not gen one.
-		 */
-	case AIROPMACOFF:
-		disable_MAC(ai, 1);
-		return 0;
-
-		/* This command merely clears the counts does not actually store any data
-		 * only reads rid. But as it changes the cards state, I put it in the
-		 * writerid routines.
-		 */
-	case AIROPSTCLR:
-		if ((iobuf = kmalloc(RIDSIZE, GFP_KERNEL)) == NULL)
-			return -ENOMEM;
-
-		PC4500_readrid(ai, RID_STATSDELTACLEAR, iobuf, RIDSIZE, 1);
-
-		enabled = ai->micstats.enabled;
-		memset(&ai->micstats, 0, sizeof(ai->micstats));
-		ai->micstats.enabled = enabled;
-
-		if (copy_to_user(comp->data, iobuf,
-				 min((int)comp->len, (int)RIDSIZE))) {
-			kfree (iobuf);
-			return -EFAULT;
-		}
-		kfree (iobuf);
-		return 0;
-
-	default:
-		return -EOPNOTSUPP;	/* Blarg! */
-	}
-	if (comp->len > RIDSIZE)
-		return -EINVAL;
-
-	if ((iobuf = kmalloc(RIDSIZE, GFP_KERNEL)) == NULL)
-		return -ENOMEM;
-
-	if (copy_from_user(iobuf, comp->data, comp->len)) {
-		kfree (iobuf);
-		return -EFAULT;
-	}
-
-	if (comp->command == AIROPCFG) {
-		ConfigRid *cfg = (ConfigRid *)iobuf;
-
-		if (test_bit(FLAG_MIC_CAPABLE, &ai->flags))
-			cfg->opmode |= MODE_MIC;
-
-		if ((cfg->opmode & MODE_CFG_MASK) == MODE_STA_IBSS)
-			set_bit (FLAG_ADHOC, &ai->flags);
-		else
-			clear_bit (FLAG_ADHOC, &ai->flags);
-	}
-
-	if ((*writer)(ai, ridcode, iobuf, comp->len, 1)) {
-		kfree (iobuf);
-		return -EIO;
-	}
-	kfree (iobuf);
-	return 0;
-}
-
-/*****************************************************************************
- * Ancillary flash / mod functions much black magic lurkes here              *
- *****************************************************************************
- */
-
-/*
- * Flash command switch table
- */
-
-static int flashcard(struct net_device *dev, aironet_ioctl *comp)
-{
-	int z;
-
-	/* Only super-user can modify flash */
-	if (!capable(CAP_NET_ADMIN))
-		return -EPERM;
-
-	switch(comp->command)
-	{
-	case AIROFLSHRST:
-		return cmdreset((struct airo_info *)dev->ml_priv);
-
-	case AIROFLSHSTFL:
-		if (!AIRO_FLASH(dev) &&
-		    (AIRO_FLASH(dev) = kmalloc(FLASHSIZE, GFP_KERNEL)) == NULL)
-			return -ENOMEM;
-		return setflashmode((struct airo_info *)dev->ml_priv);
-
-	case AIROFLSHGCHR: /* Get char from aux */
-		if (comp->len != sizeof(int))
-			return -EINVAL;
-		if (copy_from_user(&z, comp->data, comp->len))
-			return -EFAULT;
-		return flashgchar((struct airo_info *)dev->ml_priv, z, 8000);
-
-	case AIROFLSHPCHR: /* Send char to card. */
-		if (comp->len != sizeof(int))
-			return -EINVAL;
-		if (copy_from_user(&z, comp->data, comp->len))
-			return -EFAULT;
-		return flashpchar((struct airo_info *)dev->ml_priv, z, 8000);
-
-	case AIROFLPUTBUF: /* Send 32k to card */
-		if (!AIRO_FLASH(dev))
-			return -ENOMEM;
-		if (comp->len > FLASHSIZE)
-			return -EINVAL;
-		if (copy_from_user(AIRO_FLASH(dev), comp->data, comp->len))
-			return -EFAULT;
-
-		flashputbuf((struct airo_info *)dev->ml_priv);
-		return 0;
-
-	case AIRORESTART:
-		if (flashrestart((struct airo_info *)dev->ml_priv, dev))
-			return -EIO;
-		return 0;
-	}
-	return -EINVAL;
-}
-
-#define FLASH_COMMAND  0x7e7e
-
-/*
- * STEP 1)
- * Disable MAC and do soft reset on
- * card.
- */
-
-static int cmdreset(struct airo_info *ai)
-{
-	disable_MAC(ai, 1);
-
-	if (!waitbusy (ai)) {
-		airo_print_info(ai->dev->name, "Waitbusy hang before RESET");
-		return -EBUSY;
-	}
-
-	OUT4500(ai, COMMAND, CMD_SOFTRESET);
-
-	ssleep(1);			/* WAS 600 12/7/00 */
-
-	if (!waitbusy (ai)) {
-		airo_print_info(ai->dev->name, "Waitbusy hang AFTER RESET");
-		return -EBUSY;
-	}
-	return 0;
-}
-
-/* STEP 2)
- * Put the card in legendary flash
- * mode
- */
-
-static int setflashmode (struct airo_info *ai)
-{
-	set_bit (FLAG_FLASHING, &ai->flags);
-
-	OUT4500(ai, SWS0, FLASH_COMMAND);
-	OUT4500(ai, SWS1, FLASH_COMMAND);
-	if (probe) {
-		OUT4500(ai, SWS0, FLASH_COMMAND);
-		OUT4500(ai, COMMAND, 0x10);
-	} else {
-		OUT4500(ai, SWS2, FLASH_COMMAND);
-		OUT4500(ai, SWS3, FLASH_COMMAND);
-		OUT4500(ai, COMMAND, 0);
-	}
-	msleep(500);		/* 500ms delay */
-
-	if (!waitbusy(ai)) {
-		clear_bit (FLAG_FLASHING, &ai->flags);
-		airo_print_info(ai->dev->name, "Waitbusy hang after setflash mode");
-		return -EIO;
-	}
-	return 0;
-}
-
-/* Put character to SWS0 wait for dwelltime
- * x 50us for  echo .
- */
-
-static int flashpchar(struct airo_info *ai, int byte, int dwelltime)
-{
-	int echo;
-	int waittime;
-
-	byte |= 0x8000;
-
-	if (dwelltime == 0)
-		dwelltime = 200;
-
-	waittime = dwelltime;
-
-	/* Wait for busy bit d15 to go false indicating buffer empty */
-	while ((IN4500 (ai, SWS0) & 0x8000) && waittime > 0) {
-		udelay (50);
-		waittime -= 50;
-	}
-
-	/* timeout for busy clear wait */
-	if (waittime <= 0) {
-		airo_print_info(ai->dev->name, "flash putchar busywait timeout!");
-		return -EBUSY;
-	}
-
-	/* Port is clear now write byte and wait for it to echo back */
-	do {
-		OUT4500(ai, SWS0, byte);
-		udelay(50);
-		dwelltime -= 50;
-		echo = IN4500(ai, SWS1);
-	} while (dwelltime >= 0 && echo != byte);
-
-	OUT4500(ai, SWS1, 0);
-
-	return (echo == byte) ? 0 : -EIO;
-}
-
-/*
- * Get a character from the card matching matchbyte
- * Step 3)
- */
-static int flashgchar(struct airo_info *ai, int matchbyte, int dwelltime)
-{
-	int           rchar;
-	unsigned char rbyte = 0;
-
-	do {
-		rchar = IN4500(ai, SWS1);
-
-		if (dwelltime && !(0x8000 & rchar)) {
-			dwelltime -= 10;
-			mdelay(10);
-			continue;
-		}
-		rbyte = 0xff & rchar;
-
-		if ((rbyte == matchbyte) && (0x8000 & rchar)) {
-			OUT4500(ai, SWS1, 0);
-			return 0;
-		}
-		if (rbyte == 0x81 || rbyte == 0x82 || rbyte == 0x83 || rbyte == 0x1a || 0xffff == rchar)
-			break;
-		OUT4500(ai, SWS1, 0);
-
-	} while (dwelltime > 0);
-	return -EIO;
-}
-
-/*
- * Transfer 32k of firmware data from user buffer to our buffer and
- * send to the card
- */
-
-static int flashputbuf(struct airo_info *ai)
-{
-	int            nwords;
-
-	/* Write stuff */
-	if (test_bit(FLAG_MPI,&ai->flags))
-		memcpy_toio(ai->pciaux + 0x8000, ai->flash, FLASHSIZE);
-	else {
-		OUT4500(ai, AUXPAGE, 0x100);
-		OUT4500(ai, AUXOFF, 0);
-
-		for (nwords = 0; nwords != FLASHSIZE / 2; nwords++) {
-			OUT4500(ai, AUXDATA, ai->flash[nwords] & 0xffff);
-		}
-	}
-	OUT4500(ai, SWS0, 0x8000);
-
-	return 0;
-}
-
-/*
- *
- */
-static int flashrestart(struct airo_info *ai, struct net_device *dev)
-{
-	int    i, status;
-
-	ssleep(1);			/* Added 12/7/00 */
-	clear_bit (FLAG_FLASHING, &ai->flags);
-	if (test_bit(FLAG_MPI, &ai->flags)) {
-		status = mpi_init_descriptors(ai);
-		if (status != SUCCESS)
-			return status;
-	}
-	status = setup_card(ai, dev, 1);
-
-	if (!test_bit(FLAG_MPI,&ai->flags))
-		for (i = 0; i < MAX_FIDS; i++) {
-			ai->fids[i] = transmit_allocate
-				(ai, AIRO_DEF_MTU, i >= MAX_FIDS / 2);
-		}
-
-	ssleep(1);			/* Added 12/7/00 */
-	return status;
-}
-#endif /* CISCO_EXT */
-
-/*
-    This program is free software; you can redistribute it and/or
-    modify it under the terms of the GNU General Public License
-    as published by the Free Software Foundation; either version 2
-    of the License, or (at your option) any later version.
-
-    This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
-
-    In addition:
-
-    Redistribution and use in source and binary forms, with or without
-    modification, are permitted provided that the following conditions
-    are met:
-
-    1. Redistributions of source code must retain the above copyright
-       notice, this list of conditions and the following disclaimer.
-    2. Redistributions in binary form must reproduce the above copyright
-       notice, this list of conditions and the following disclaimer in the
-       documentation and/or other materials provided with the distribution.
-    3. The name of the author may not be used to endorse or promote
-       products derived from this software without specific prior written
-       permission.
-
-    THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
-    IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-    WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
-    ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT,
-    INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
-    (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-    SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
-    HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
-    STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
-    IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
-    POSSIBILITY OF SUCH DAMAGE.
-*/
-
-module_init(airo_init_module);
-module_exit(airo_cleanup_module);
diff --git a/drivers/net/wireless/cisco/airo.h b/drivers/net/wireless/cisco/airo.h
deleted file mode 100644
index 8a02977a2e2b..000000000000
--- a/drivers/net/wireless/cisco/airo.h
+++ /dev/null
@@ -1,10 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _AIRO_H_
-#define _AIRO_H_
-
-struct net_device *init_airo_card(unsigned short irq, int port, int is_pcmcia,
-				  struct device *dmdev);
-int reset_airo_card(struct net_device *dev);
-void stop_airo_card(struct net_device *dev, int freeres);
-
-#endif  /*  _AIRO_H_  */
diff --git a/drivers/net/wireless/cisco/airo_cs.c b/drivers/net/wireless/cisco/airo_cs.c
deleted file mode 100644
index fcfe4c6d62f0..000000000000
--- a/drivers/net/wireless/cisco/airo_cs.c
+++ /dev/null
@@ -1,218 +0,0 @@
-/*======================================================================
-
-    Aironet driver for 4500 and 4800 series cards
-
-    This code is released under both the GPL version 2 and BSD licenses.
-    Either license may be used.  The respective licenses are found at
-    the end of this file.
-
-    This code was developed by Benjamin Reed <breed@users.sourceforge.net>
-    including portions of which come from the Aironet PC4500
-    Developer's Reference Manual and used with permission.  Copyright
-    (C) 1999 Benjamin Reed.  All Rights Reserved.  Permission to use
-    code in the Developer's manual was granted for this driver by
-    Aironet.
-
-    In addition this module was derived from dummy_cs.
-    The initial developer of dummy_cs is David A. Hinds
-    <dahinds@users.sourceforge.net>.  Portions created by David A. Hinds
-    are Copyright (C) 1999 David A. Hinds.  All Rights Reserved.
-
-======================================================================*/
-
-#ifdef __IN_PCMCIA_PACKAGE__
-#include <pcmcia/k_compat.h>
-#endif
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/ptrace.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/timer.h>
-#include <linux/netdevice.h>
-
-#include <pcmcia/cistpl.h>
-#include <pcmcia/cisreg.h>
-#include <pcmcia/ds.h>
-
-#include <linux/io.h>
-
-#include "airo.h"
-
-
-/*====================================================================*/
-
-MODULE_AUTHOR("Benjamin Reed");
-MODULE_DESCRIPTION("Support for Cisco/Aironet 802.11 wireless ethernet "
-		   "cards.  This is the module that links the PCMCIA card "
-		   "with the airo module.");
-MODULE_LICENSE("Dual BSD/GPL");
-
-/*====================================================================*/
-
-static int airo_config(struct pcmcia_device *link);
-static void airo_release(struct pcmcia_device *link);
-
-static void airo_detach(struct pcmcia_device *p_dev);
-
-struct local_info {
-	struct net_device *eth_dev;
-};
-
-static int airo_probe(struct pcmcia_device *p_dev)
-{
-	struct local_info *local;
-
-	dev_dbg(&p_dev->dev, "airo_attach()\n");
-
-	/* Allocate space for private device-specific data */
-	local = kzalloc(sizeof(*local), GFP_KERNEL);
-	if (!local)
-		return -ENOMEM;
-
-	p_dev->priv = local;
-
-	return airo_config(p_dev);
-} /* airo_attach */
-
-static void airo_detach(struct pcmcia_device *link)
-{
-	dev_dbg(&link->dev, "airo_detach\n");
-
-	airo_release(link);
-
-	if (((struct local_info *)link->priv)->eth_dev) {
-		stop_airo_card(((struct local_info *)link->priv)->eth_dev,
-			       0);
-	}
-	((struct local_info *)link->priv)->eth_dev = NULL;
-
-	kfree(link->priv);
-} /* airo_detach */
-
-static int airo_cs_config_check(struct pcmcia_device *p_dev, void *priv_data)
-{
-	if (p_dev->config_index == 0)
-		return -EINVAL;
-
-	return pcmcia_request_io(p_dev);
-}
-
-
-static int airo_config(struct pcmcia_device *link)
-{
-	int ret;
-
-	dev_dbg(&link->dev, "airo_config\n");
-
-	link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_VPP |
-		CONF_AUTO_AUDIO | CONF_AUTO_SET_IO;
-
-	ret = pcmcia_loop_config(link, airo_cs_config_check, NULL);
-	if (ret)
-		goto failed;
-
-	if (!link->irq)
-		goto failed;
-
-	ret = pcmcia_enable_device(link);
-	if (ret)
-		goto failed;
-	((struct local_info *)link->priv)->eth_dev =
-		init_airo_card(link->irq,
-			       link->resource[0]->start, 1, &link->dev);
-	if (!((struct local_info *)link->priv)->eth_dev)
-		goto failed;
-
-	return 0;
-
- failed:
-	airo_release(link);
-	return -ENODEV;
-} /* airo_config */
-
-static void airo_release(struct pcmcia_device *link)
-{
-	dev_dbg(&link->dev, "airo_release\n");
-	pcmcia_disable_device(link);
-}
-
-static int airo_suspend(struct pcmcia_device *link)
-{
-	struct local_info *local = link->priv;
-
-	netif_device_detach(local->eth_dev);
-
-	return 0;
-}
-
-static int airo_resume(struct pcmcia_device *link)
-{
-	struct local_info *local = link->priv;
-
-	if (link->open) {
-		reset_airo_card(local->eth_dev);
-		netif_device_attach(local->eth_dev);
-	}
-
-	return 0;
-}
-
-static const struct pcmcia_device_id airo_ids[] = {
-	PCMCIA_DEVICE_MANF_CARD(0x015f, 0x000a),
-	PCMCIA_DEVICE_MANF_CARD(0x015f, 0x0005),
-	PCMCIA_DEVICE_MANF_CARD(0x015f, 0x0007),
-	PCMCIA_DEVICE_MANF_CARD(0x0105, 0x0007),
-	PCMCIA_DEVICE_NULL,
-};
-MODULE_DEVICE_TABLE(pcmcia, airo_ids);
-
-static struct pcmcia_driver airo_driver = {
-	.owner		= THIS_MODULE,
-	.name		= "airo_cs",
-	.probe		= airo_probe,
-	.remove		= airo_detach,
-	.id_table       = airo_ids,
-	.suspend	= airo_suspend,
-	.resume		= airo_resume,
-};
-module_pcmcia_driver(airo_driver);
-
-/*
-    This program is free software; you can redistribute it and/or
-    modify it under the terms of the GNU General Public License
-    as published by the Free Software Foundation; either version 2
-    of the License, or (at your option) any later version.
-
-    This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
-
-    In addition:
-
-    Redistribution and use in source and binary forms, with or without
-    modification, are permitted provided that the following conditions
-    are met:
-
-    1. Redistributions of source code must retain the above copyright
-       notice, this list of conditions and the following disclaimer.
-    2. Redistributions in binary form must reproduce the above copyright
-       notice, this list of conditions and the following disclaimer in the
-       documentation and/or other materials provided with the distribution.
-    3. The name of the author may not be used to endorse or promote
-       products derived from this software without specific prior written
-       permission.
-
-    THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
-    IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-    WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
-    ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT,
-    INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
-    (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-    SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
-    HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
-    STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
-    IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
-    POSSIBILITY OF SUCH DAMAGE.
-*/
diff --git a/drivers/net/wireless/intel/iwlegacy/4965-mac.c b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
index 69276266ce6f..70e420df1643 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
@@ -4231,8 +4231,6 @@ il4965_rx_handle(struct il_priv *il)
 		fill_rx = 1;
 
 	while (i != r) {
-		int len;
-
 		rxb = rxq->queue[i];
 
 		/* If an RXB doesn't have a Rx queue slot associated with it,
@@ -4246,10 +4244,6 @@ il4965_rx_handle(struct il_priv *il)
 			       PAGE_SIZE << il->hw_params.rx_page_order,
 			       DMA_FROM_DEVICE);
 		pkt = rxb_addr(rxb);
-
-		len = le32_to_cpu(pkt->len_n_flags) & IL_RX_FRAME_SIZE_MSK;
-		len += sizeof(u32);	/* account for status word */
-
 		reclaim = il_need_reclaim(il, pkt);
 
 		/* Based on type of command response or notification,
diff --git a/drivers/net/wireless/intel/iwlegacy/common.c b/drivers/net/wireless/intel/iwlegacy/common.c
index 054fef680aba..17570d62c896 100644
--- a/drivers/net/wireless/intel/iwlegacy/common.c
+++ b/drivers/net/wireless/intel/iwlegacy/common.c
@@ -541,6 +541,9 @@ il_leds_init(struct il_priv *il)
 
 	il->led.name =
 	    kasprintf(GFP_KERNEL, "%s-led", wiphy_name(il->hw->wiphy));
+	if (!il->led.name)
+		return;
+
 	il->led.brightness_set = il_led_brightness_set;
 	il->led.blink_set = il_led_blink_set;
 	il->led.max_brightness = 1;
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
index 7b18e098b125..798731ecbefd 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
@@ -60,6 +60,12 @@ enum iwl_debug_cmds {
 	 */
 	FW_DUMP_COMPLETE_CMD = 0xB,
 	/**
+	 * @FW_CLEAR_BUFFER:
+	 * clears the firmware's internal buffer
+	 * no payload
+	 */
+	FW_CLEAR_BUFFER = 0xD,
+	/**
 	 * @MFU_ASSERT_DUMP_NTF:
 	 * &struct iwl_mfu_assert_dump_notif
 	 */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h
index dfe0bebabc81..7ec959244ffc 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h
@@ -269,6 +269,9 @@ struct iwl_nvm_access_complete_cmd {
 	__le32 reserved;
 } __packed; /* NVM_ACCESS_COMPLETE_CMD_API_S_VER_1 */
 
+#define IWL_MCC_US	0x5553
+#define IWL_MCC_CANADA	0x4341
+
 /**
  * struct iwl_mcc_update_cmd - Request the device to update geographic
  * regulatory profile according to the given MCC (Mobile Country Code).
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index 3975a53a9f20..e27774e7ed74 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -880,10 +880,10 @@ iwl_fw_error_dump_file(struct iwl_fw_runtime *fwrt,
 			cpu_to_le32(fwrt->trans->hw_rev_step);
 		memcpy(dump_info->fw_human_readable, fwrt->fw->human_readable,
 		       sizeof(dump_info->fw_human_readable));
-		strncpy(dump_info->dev_human_readable, fwrt->trans->name,
-			sizeof(dump_info->dev_human_readable) - 1);
-		strncpy(dump_info->bus_human_readable, fwrt->dev->bus->name,
-			sizeof(dump_info->bus_human_readable) - 1);
+		strscpy_pad(dump_info->dev_human_readable, fwrt->trans->name,
+			sizeof(dump_info->dev_human_readable));
+		strscpy_pad(dump_info->bus_human_readable, fwrt->dev->bus->name,
+			sizeof(dump_info->bus_human_readable));
 		dump_info->num_of_lmacs = fwrt->smem_cfg.num_lmacs;
 		dump_info->lmac_err_id[0] =
 			cpu_to_le32(fwrt->dump.lmac_err_id[0]);
@@ -3395,3 +3395,22 @@ void iwl_fw_disable_dbg_asserts(struct iwl_fw_runtime *fwrt)
 	iwl_trans_send_cmd(fwrt->trans, &hcmd);
 }
 IWL_EXPORT_SYMBOL(iwl_fw_disable_dbg_asserts);
+
+void iwl_fw_dbg_clear_monitor_buf(struct iwl_fw_runtime *fwrt)
+{
+	struct iwl_fw_dbg_params params = {0};
+
+	iwl_fw_dbg_stop_sync(fwrt);
+
+	if (fw_has_api(&fwrt->fw->ucode_capa,
+		       IWL_UCODE_TLV_API_INT_DBG_BUF_CLEAR)) {
+		struct iwl_host_cmd hcmd = {
+			.id = WIDE_ID(DEBUG_GROUP, FW_CLEAR_BUFFER),
+		};
+		iwl_trans_send_cmd(fwrt->trans, &hcmd);
+	}
+
+	iwl_dbg_tlv_init_cfg(fwrt);
+	iwl_fw_dbg_stop_restart_recording(fwrt, &params, false);
+}
+IWL_EXPORT_SYMBOL(iwl_fw_dbg_clear_monitor_buf);
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
index 66b233250c7c..eb38c686b5cb 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
@@ -330,6 +330,7 @@ void iwl_send_dbg_dump_complete_cmd(struct iwl_fw_runtime *fwrt,
 				    u32 timepoint,
 				    u32 timepoint_data);
 void iwl_fw_disable_dbg_asserts(struct iwl_fw_runtime *fwrt);
+void iwl_fw_dbg_clear_monitor_buf(struct iwl_fw_runtime *fwrt);
 
 #define IWL_FW_CHECK_FAILED(_obj, _fmt, ...)				\
 	IWL_ERR_LIMIT(_obj, _fmt, __VA_ARGS__)
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/file.h b/drivers/net/wireless/intel/iwlwifi/fw/file.h
index 03f6e520145f..bfc39bd5bbc6 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/file.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/file.h
@@ -20,7 +20,7 @@ struct iwl_ucode_header {
 			__le32 init_size;	/* bytes of init code */
 			__le32 init_data_size;	/* bytes of init data */
 			__le32 boot_size;	/* bytes of bootstrap code */
-			u8 data[0];		/* in same order as sizes */
+			u8 data[];		/* in same order as sizes */
 		} v1;
 		struct {
 			__le32 build;		/* build number */
@@ -29,7 +29,7 @@ struct iwl_ucode_header {
 			__le32 init_size;	/* bytes of init code */
 			__le32 init_data_size;	/* bytes of init data */
 			__le32 boot_size;	/* bytes of bootstrap code */
-			u8 data[0];		/* in same order as sizes */
+			u8 data[];		/* in same order as sizes */
 		} v2;
 	} u;
 };
@@ -243,6 +243,10 @@ typedef unsigned int __bitwise iwl_ucode_tlv_api_t;
  *	version tables.
  * @IWL_UCODE_TLV_API_REDUCED_SCAN_CONFIG: This ucode supports v3 of
  *  SCAN_CONFIG_DB_CMD_API_S.
+ * @IWL_UCODE_TLV_API_NO_HOST_DISABLE_TX: Firmware offloaded the station disable tx
+ *	logic.
+ * @IWL_UCODE_TLV_API_INT_DBG_BUF_CLEAR: Firmware supports clearing the debug
+ *	internal buffer
  *
  * @NUM_IWL_UCODE_TLV_API: number of bits used
  */
@@ -280,6 +284,9 @@ enum iwl_ucode_tlv_api {
 	IWL_UCODE_TLV_API_ADWELL_HB_DEF_N_AP	= (__force iwl_ucode_tlv_api_t)57,
 	IWL_UCODE_TLV_API_SCAN_EXT_CHAN_VER	= (__force iwl_ucode_tlv_api_t)58,
 	IWL_UCODE_TLV_API_BAND_IN_RX_DATA	= (__force iwl_ucode_tlv_api_t)59,
+	/* API Set 2 */
+	IWL_UCODE_TLV_API_NO_HOST_DISABLE_TX	= (__force iwl_ucode_tlv_api_t)66,
+	IWL_UCODE_TLV_API_INT_DBG_BUF_CLEAR     = (__force iwl_ucode_tlv_api_t)67,
 
 	NUM_IWL_UCODE_TLV_API
 /*
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index 02ded22295c1..ae6f1cd4d660 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -377,7 +377,6 @@ struct iwl_cfg {
 	u16 nvm_calib_ver;
 	u32 rx_with_siso_diversity:1,
 	    tx_with_siso_diversity:1,
-	    bt_shared_single_ant:1,
 	    internal_wimax_coex:1,
 	    host_interrupt_operation_mode:1,
 	    high_temp:1,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
index a4df67ff21ba..4511d7fb2279 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
@@ -354,6 +354,8 @@ enum {
 #define CSR_HW_RF_ID_TYPE_GF		(0x0010D000)
 #define CSR_HW_RF_ID_TYPE_GF4		(0x0010E000)
 #define CSR_HW_RF_ID_TYPE_MS		(0x00111000)
+#define CSR_HW_RF_ID_TYPE_FM		(0x00112000)
+#define CSR_HW_RF_ID_TYPE_WP		(0x00113000)
 
 /* HW_RF CHIP STEP  */
 #define CSR_HW_RF_STEP(_val) (((_val) >> 8) & 0xF)
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
index b658cf228fbe..3b14f6476743 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
@@ -1274,7 +1274,7 @@ iwl_dbg_tlv_tp_trigger(struct iwl_fw_runtime *fwrt, bool sync,
 	return 0;
 }
 
-static void iwl_dbg_tlv_init_cfg(struct iwl_fw_runtime *fwrt)
+void iwl_dbg_tlv_init_cfg(struct iwl_fw_runtime *fwrt)
 {
 	enum iwl_fw_ini_buffer_location *ini_dest = &fwrt->trans->dbg.ini_dest;
 	int ret, i;
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h
index 06fb7d665390..7ed6329fd8ca 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h
@@ -57,6 +57,7 @@ void _iwl_dbg_tlv_time_point(struct iwl_fw_runtime *fwrt,
 			     enum iwl_fw_ini_time_point tp_id,
 			     union iwl_dbg_tlv_tp_data *tp_data,
 			     bool sync);
+void iwl_dbg_tlv_init_cfg(struct iwl_fw_runtime *fwrt);
 
 static inline void iwl_dbg_tlv_time_point(struct iwl_fw_runtime *fwrt,
 					  enum iwl_fw_ini_time_point tp_id,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-data.h b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-data.h
index 347fd95c4e3a..2c280a2fe3df 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-data.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-data.h
@@ -3,7 +3,7 @@
  *
  * Copyright(c) 2009 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2015        Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2018 - 2019, 2023 Intel Corporation
  *****************************************************************************/
 
 #if !defined(__IWLWIFI_DEVICE_TRACE_DATA) || defined(TRACE_HEADER_MULTI_READ)
@@ -36,20 +36,17 @@ TRACE_EVENT(iwlwifi_dev_tx_tb,
 
 TRACE_EVENT(iwlwifi_dev_rx_data,
 	TP_PROTO(const struct device *dev,
-		 const struct iwl_trans *trans,
-		 void *rxbuf, size_t len),
-	TP_ARGS(dev, trans, rxbuf, len),
+		 void *rxbuf, size_t len, size_t start),
+	TP_ARGS(dev, rxbuf, len, start),
 	TP_STRUCT__entry(
 		DEV_ENTRY
-		__dynamic_array(u8, data,
-				len - iwl_rx_trace_len(trans, rxbuf, len, NULL))
+		__dynamic_array(u8, data, len - start)
 	),
 	TP_fast_assign(
-		size_t offs = iwl_rx_trace_len(trans, rxbuf, len, NULL);
 		DEV_ASSIGN;
-		if (offs < len)
+		if (start < len)
 			memcpy(__get_dynamic_array(data),
-			       ((u8 *)rxbuf) + offs, len - offs);
+			       ((u8 *)rxbuf) + start, len - start);
 	),
 	TP_printk("[%s] RX frame data", __get_str(dev))
 );
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h
index 46ed723f138a..e656bf6bc003 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h
@@ -4,7 +4,7 @@
  * Copyright(c) 2009 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018        Intel Corporation
+ * Copyright(c) 2018, 2023  Intel Corporation
  *****************************************************************************/
 
 #if !defined(__IWLWIFI_DEVICE_TRACE_IWLWIFI) || defined(TRACE_HEADER_MULTI_READ)
@@ -50,23 +50,20 @@ TRACE_EVENT(iwlwifi_dev_hcmd,
 );
 
 TRACE_EVENT(iwlwifi_dev_rx,
-	TP_PROTO(const struct device *dev, const struct iwl_trans *trans,
-		 struct iwl_rx_packet *pkt, size_t len),
-	TP_ARGS(dev, trans, pkt, len),
+	TP_PROTO(const struct device *dev,
+		 struct iwl_rx_packet *pkt, size_t len, size_t trace_len,
+		 size_t hdr_offset),
+	TP_ARGS(dev, pkt, len, trace_len, hdr_offset),
 	TP_STRUCT__entry(
 		DEV_ENTRY
 		__field(u16, cmd)
 		__field(u8, hdr_offset)
-		__dynamic_array(u8, rxbuf,
-				iwl_rx_trace_len(trans, pkt, len, NULL))
+		__dynamic_array(u8, rxbuf, trace_len)
 	),
 	TP_fast_assign(
-		size_t hdr_offset = 0;
-
 		DEV_ASSIGN;
 		__entry->cmd = WIDE_ID(pkt->hdr.group_id, pkt->hdr.cmd);
-		memcpy(__get_dynamic_array(rxbuf), pkt,
-		       iwl_rx_trace_len(trans, pkt, len, &hdr_offset));
+		memcpy(__get_dynamic_array(rxbuf), pkt, trace_len);
 		__entry->hdr_offset = hdr_offset;
 	),
 	TP_printk("[%s] RX cmd %#.2x",
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace.c b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace.c
index e46639b097f4..7e686297963d 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace.c
@@ -2,7 +2,7 @@
 /******************************************************************************
  *
  * Copyright(c) 2009 - 2014 Intel Corporation. All rights reserved.
- * Copyright (C) 2018 Intel Corporation
+ * Copyright (C) 2018, 2023 Intel Corporation
  *****************************************************************************/
 
 #include <linux/module.h>
@@ -20,4 +20,17 @@
 EXPORT_TRACEPOINT_SYMBOL(iwlwifi_dev_ucode_event);
 EXPORT_TRACEPOINT_SYMBOL(iwlwifi_dev_ucode_cont_event);
 EXPORT_TRACEPOINT_SYMBOL(iwlwifi_dev_ucode_wrap_event);
-#endif
+#else
+#include "iwl-devtrace.h"
+#endif /* __CHECKER__ */
+
+void __trace_iwlwifi_dev_rx(struct iwl_trans *trans, void *pkt, size_t len)
+{
+	size_t hdr_offset = 0, trace_len;
+
+	trace_len = iwl_rx_trace_len(trans, pkt, len, &hdr_offset);
+	trace_iwlwifi_dev_rx(trans->dev, pkt, len, trace_len, hdr_offset);
+
+	if (trace_len < len)
+		trace_iwlwifi_dev_rx_data(trans->dev, pkt, len, trace_len);
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace.h b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace.h
index 01fb7b900a6d..c3e09f4fefeb 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace.h
@@ -7,12 +7,12 @@
  *****************************************************************************/
 
 #ifndef __IWLWIFI_DEVICE_TRACE
+#define __IWLWIFI_DEVICE_TRACE
 #include <linux/skbuff.h>
 #include <linux/ieee80211.h>
 #include <net/cfg80211.h>
 #include <net/mac80211.h>
 #include "iwl-trans.h"
-#if !defined(__IWLWIFI_DEVICE_TRACE)
 static inline bool iwl_trace_data(struct sk_buff *skb)
 {
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
@@ -70,9 +70,6 @@ static inline size_t iwl_rx_trace_len(const struct iwl_trans *trans,
 	return sizeof(__le32) + sizeof(*cmd) + trans->rx_mpdu_cmd_hdr_size +
 		ieee80211_hdrlen(hdr->frame_control);
 }
-#endif
-
-#define __IWLWIFI_DEVICE_TRACE
 
 #include <linux/tracepoint.h>
 #include <linux/device.h>
@@ -98,4 +95,20 @@ static inline void trace_ ## name(proto) {}
 #include "iwl-devtrace-data.h"
 #include "iwl-devtrace-iwlwifi.h"
 
+#ifdef CONFIG_IWLWIFI_DEVICE_TRACING
+DECLARE_TRACEPOINT(iwlwifi_dev_rx);
+DECLARE_TRACEPOINT(iwlwifi_dev_rx_data);
+#endif
+
+void __trace_iwlwifi_dev_rx(struct iwl_trans *trans, void *pkt, size_t len);
+
+static inline void maybe_trace_iwlwifi_dev_rx(struct iwl_trans *trans,
+					      void *pkt, size_t len)
+{
+#ifdef CONFIG_IWLWIFI_DEVICE_TRACING
+	if (tracepoint_enabled(iwlwifi_dev_rx) ||
+	    tracepoint_enabled(iwlwifi_dev_rx_data))
+		__trace_iwlwifi_dev_rx(trans, pkt, len);
+#endif
+}
 #endif /* __IWLWIFI_DEVICE_TRACE */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 6015e1255d2a..402896988686 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -1029,7 +1029,8 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
 			  IEEE80211_EHT_PHY_CAP3_NG_16_MU_FEEDBACK |
 			  IEEE80211_EHT_PHY_CAP3_CODEBOOK_4_2_SU_FDBK |
 			  IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK |
-			  IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK);
+			  IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK |
+			  IEEE80211_EHT_PHY_CAP3_TRIG_CQI_FDBK);
 		iftype_data->eht_cap.eht_cap_elem.phy_cap_info[4] &=
 			~(IEEE80211_EHT_PHY_CAP4_PART_BW_DL_MU_MIMO |
 			  IEEE80211_EHT_PHY_CAP4_POWER_BOOST_FACT_SUPP);
@@ -1608,10 +1609,17 @@ static u32 iwl_nvm_get_regdom_bw_flags(const u16 *nvm_chan,
 	/* Set the GO concurrent flag only in case that NO_IR is set.
 	 * Otherwise it is meaningless
 	 */
-	if ((nvm_flags & NVM_CHANNEL_GO_CONCURRENT) &&
-	    (flags & NL80211_RRF_NO_IR))
-		flags |= NL80211_RRF_GO_CONCURRENT;
-
+	if ((nvm_flags & NVM_CHANNEL_GO_CONCURRENT)) {
+		if (flags & NL80211_RRF_NO_IR)
+			flags |= NL80211_RRF_GO_CONCURRENT;
+		if (flags & NL80211_RRF_DFS) {
+			flags |= NL80211_RRF_DFS_CONCURRENT;
+			/* Our device doesn't set active bit for DFS channels
+			 * however, once marked as DFS no-ir is not needed.
+			 */
+			flags &= ~NL80211_RRF_NO_IR;
+		}
+	}
 	/*
 	 * reg_capa is per regulatory domain so apply it for every channel
 	 */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h b/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h
index af5f9b210f22..3dc618a7c70f 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h
@@ -64,8 +64,6 @@ struct iwl_cfg;
  *	received on the RSS queue(s). The queue parameter indicates which of the
  *	RSS queues received this frame; it will always be non-zero.
  *	This method must not sleep.
- * @async_cb: called when an ASYNC command with CMD_WANT_ASYNC_CALLBACK set
- *	completes. Must be atomic.
  * @queue_full: notifies that a HW queue is full.
  *	Must be atomic and called with BH disabled.
  * @queue_not_full: notifies that a HW queue is not full any more.
@@ -96,8 +94,6 @@ struct iwl_op_mode_ops {
 		   struct iwl_rx_cmd_buffer *rxb);
 	void (*rx_rss)(struct iwl_op_mode *op_mode, struct napi_struct *napi,
 		       struct iwl_rx_cmd_buffer *rxb, unsigned int queue);
-	void (*async_cb)(struct iwl_op_mode *op_mode,
-			 const struct iwl_device_cmd *cmd);
 	void (*queue_full)(struct iwl_op_mode *op_mode, int queue);
 	void (*queue_not_full)(struct iwl_op_mode *op_mode, int queue);
 	bool (*hw_rf_kill)(struct iwl_op_mode *op_mode, bool state);
@@ -147,13 +143,6 @@ static inline void iwl_op_mode_rx_rss(struct iwl_op_mode *op_mode,
 	op_mode->ops->rx_rss(op_mode, napi, rxb, queue);
 }
 
-static inline void iwl_op_mode_async_cb(struct iwl_op_mode *op_mode,
-					const struct iwl_device_cmd *cmd)
-{
-	if (op_mode->ops->async_cb)
-		op_mode->ops->async_cb(op_mode, cmd);
-}
-
 static inline void iwl_op_mode_queue_full(struct iwl_op_mode *op_mode,
 					  int queue)
 {
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
index 4bd759432d44..f95098c21c7d 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
@@ -172,10 +172,6 @@ int iwl_trans_send_cmd(struct iwl_trans *trans, struct iwl_host_cmd *cmd)
 		return -EIO;
 	}
 
-	if (WARN_ON((cmd->flags & CMD_WANT_ASYNC_CALLBACK) &&
-		    !(cmd->flags & CMD_ASYNC)))
-		return -EINVAL;
-
 	if (!(cmd->flags & CMD_ASYNC))
 		lock_map_acquire_read(&trans->sync_cmd_lockdep_map);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 05e72a2125b3..5789a8735976 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -110,8 +110,7 @@ static inline u32 iwl_rx_packet_payload_len(const struct iwl_rx_packet *pkt)
  * @CMD_WANT_SKB: Not valid with CMD_ASYNC. The caller needs the buffer of
  *	the response. The caller needs to call iwl_free_resp when done.
  * @CMD_SEND_IN_RFKILL: Send the command even if the NIC is in RF-kill.
- * @CMD_WANT_ASYNC_CALLBACK: the op_mode's async callback function must be
- *	called after this command completes. Valid only with CMD_ASYNC.
+ * @CMD_BLOCK_TXQS: Block TXQs while the comment is executing.
  * @CMD_SEND_IN_D3: Allow the command to be sent in D3 mode, relevant to
  *	SUSPEND and RESUME commands. We are in D3 mode when we set
  *	trans->system_pm_mode to IWL_PLAT_PM_MODE_D3.
@@ -120,7 +119,7 @@ enum CMD_MODE {
 	CMD_ASYNC		= BIT(0),
 	CMD_WANT_SKB		= BIT(1),
 	CMD_SEND_IN_RFKILL	= BIT(2),
-	CMD_WANT_ASYNC_CALLBACK	= BIT(3),
+	CMD_BLOCK_TXQS		= BIT(3),
 	CMD_SEND_IN_D3          = BIT(4),
 };
 
@@ -534,11 +533,6 @@ struct iwl_pnvm_image {
  * @wait_txq_empty: wait until specific tx queue is empty. May sleep.
  * @freeze_txq_timer: prevents the timer of the queue from firing until the
  *	queue is set to awake. Must be atomic.
- * @block_txq_ptrs: stop updating the write pointers of the Tx queues. Note
- *	that the transport needs to refcount the calls since this function
- *	will be called several times with block = true, and then the queues
- *	need to be unblocked only after the same number of calls with
- *	block = false.
  * @write8: write a u8 to a register at offset ofs from the BAR
  * @write32: write a u32 to a register at offset ofs from the BAR
  * @read32: read a u32 register at offset ofs from the BAR
@@ -613,7 +607,6 @@ struct iwl_trans_ops {
 	int (*wait_txq_empty)(struct iwl_trans *trans, int queue);
 	void (*freeze_txq_timer)(struct iwl_trans *trans, unsigned long txqs,
 				 bool freeze);
-	void (*block_txq_ptrs)(struct iwl_trans *trans, bool block);
 
 	void (*write8)(struct iwl_trans *trans, u32 ofs, u8 val);
 	void (*write32)(struct iwl_trans *trans, u32 ofs, u32 val);
@@ -1323,7 +1316,7 @@ iwl_trans_get_rxq_dma_data(struct iwl_trans *trans, int queue,
 			   struct iwl_trans_rxq_dma_data *data)
 {
 	if (WARN_ON_ONCE(!trans->ops->rxq_dma_data))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	return trans->ops->rxq_dma_data(trans, queue, data);
 }
@@ -1345,7 +1338,7 @@ iwl_trans_txq_alloc(struct iwl_trans *trans,
 	might_sleep();
 
 	if (WARN_ON_ONCE(!trans->ops->txq_alloc))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (WARN_ON_ONCE(trans->state != IWL_TRANS_FW_ALIVE)) {
 		IWL_ERR(trans, "%s bad state = %d\n", __func__, trans->state);
@@ -1407,23 +1400,11 @@ static inline void iwl_trans_freeze_txq_timer(struct iwl_trans *trans,
 		trans->ops->freeze_txq_timer(trans, txqs, freeze);
 }
 
-static inline void iwl_trans_block_txq_ptrs(struct iwl_trans *trans,
-					    bool block)
-{
-	if (WARN_ON_ONCE(trans->state != IWL_TRANS_FW_ALIVE)) {
-		IWL_ERR(trans, "%s bad state = %d\n", __func__, trans->state);
-		return;
-	}
-
-	if (trans->ops->block_txq_ptrs)
-		trans->ops->block_txq_ptrs(trans, block);
-}
-
 static inline int iwl_trans_wait_tx_queues_empty(struct iwl_trans *trans,
 						 u32 txqs)
 {
 	if (WARN_ON_ONCE(!trans->ops->wait_tx_queues_empty))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	/* No need to wait if the firmware is not alive */
 	if (trans->state != IWL_TRANS_FW_ALIVE) {
@@ -1437,7 +1418,7 @@ static inline int iwl_trans_wait_tx_queues_empty(struct iwl_trans *trans,
 static inline int iwl_trans_wait_txq_empty(struct iwl_trans *trans, int queue)
 {
 	if (WARN_ON_ONCE(!trans->ops->wait_txq_empty))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (WARN_ON_ONCE(trans->state != IWL_TRANS_FW_ALIVE)) {
 		IWL_ERR(trans, "%s bad state = %d\n", __func__, trans->state);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/coex.c b/drivers/net/wireless/intel/iwlwifi/mvm/coex.c
index 5a5b1128e75c..9fe1761691ec 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/coex.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/coex.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2013-2014, 2018-2020, 2022 Intel Corporation
+ * Copyright (C) 2013-2014, 2018-2020, 2022-2023 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  */
 #include <linux/ieee80211.h>
@@ -116,11 +116,6 @@ iwl_get_coex_type(struct iwl_mvm *mvm, const struct ieee80211_vif *vif)
 
 	ret = BT_COEX_TX_DIS_LUT;
 
-	if (mvm->cfg->bt_shared_single_ant) {
-		rcu_read_unlock();
-		return ret;
-	}
-
 	phy_ctx_id = *((u16 *)chanctx_conf->drv_priv);
 	primary_ch_phy_id = le32_to_cpu(mvm->last_bt_ci_cmd.primary_ch_phy_id);
 	secondary_ch_phy_id =
@@ -383,13 +378,12 @@ static void iwl_mvm_bt_notif_per_link(struct iwl_mvm *mvm,
 	/*
 	 * don't reduce the Tx power if one of these is true:
 	 *  we are in LOOSE
-	 *  single share antenna product
 	 *  BT is inactive
 	 *  we are not associated
 	 */
 	if (iwl_get_coex_type(mvm, vif) == BT_COEX_LOOSE_LUT ||
-	    mvm->cfg->bt_shared_single_ant || !vif->cfg.assoc ||
-	    le32_to_cpu(mvm->last_bt_notif.bt_activity_grading) == BT_OFF) {
+	    le32_to_cpu(mvm->last_bt_notif.bt_activity_grading) == BT_OFF ||
+	    !vif->cfg.assoc) {
 		iwl_mvm_bt_coex_reduced_txp(mvm, link_info->ap_sta_id, false);
 		/* FIXME: should this be per link? */
 		iwl_mvm_bt_coex_enable_rssi_event(mvm, vif, false, 0);
@@ -570,7 +564,7 @@ void iwl_mvm_bt_rssi_event(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	 * Check if rssi is good enough for reduced Tx power, but not in loose
 	 * scheme.
 	 */
-	if (rssi_event == RSSI_EVENT_LOW || mvm->cfg->bt_shared_single_ant ||
+	if (rssi_event == RSSI_EVENT_LOW ||
 	    iwl_get_coex_type(mvm, vif) == BT_COEX_LOOSE_LUT)
 		ret = iwl_mvm_bt_coex_reduced_txp(mvm,
 						  mvmvif->deflink.ap_sta_id,
@@ -639,10 +633,6 @@ bool iwl_mvm_bt_coex_is_mimo_allowed(struct iwl_mvm *mvm,
 
 bool iwl_mvm_bt_coex_is_ant_avail(struct iwl_mvm *mvm, u8 ant)
 {
-	/* there is no other antenna, shared antenna is always available */
-	if (mvm->cfg->bt_shared_single_ant)
-		return true;
-
 	if (ant & mvm->cfg->non_shared_ant)
 		return true;
 
@@ -652,10 +642,6 @@ bool iwl_mvm_bt_coex_is_ant_avail(struct iwl_mvm *mvm, u8 ant)
 
 bool iwl_mvm_bt_coex_is_shared_ant_avail(struct iwl_mvm *mvm)
 {
-	/* there is no other antenna, shared antenna is always available */
-	if (mvm->cfg->bt_shared_single_ant)
-		return true;
-
 	return le32_to_cpu(mvm->last_bt_notif.bt_activity_grading) < BT_HIGH_TRAFFIC;
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index 92c45571bd69..4582afb149d7 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -1130,14 +1130,7 @@ iwl_mvm_wowlan_config(struct iwl_mvm *mvm,
 			return ret;
 	}
 
-	/*
-	 * This needs to be unlocked due to lock ordering
-	 * constraints. Since we're in the suspend path
-	 * that isn't really a problem though.
-	 */
-	mutex_unlock(&mvm->mutex);
 	ret = iwl_mvm_wowlan_config_key_params(mvm, vif);
-	mutex_lock(&mvm->mutex);
 	if (ret)
 		return ret;
 
@@ -2497,7 +2490,7 @@ static bool iwl_mvm_query_wakeup_reasons(struct iwl_mvm *mvm,
 					 struct iwl_wowlan_status_data *status)
 {
 	int i;
-	bool keep;
+	bool keep = false;
 	struct iwl_mvm_sta *mvm_ap_sta;
 
 	if (!status)
@@ -2525,18 +2518,12 @@ static bool iwl_mvm_query_wakeup_reasons(struct iwl_mvm *mvm,
 				     mvm_ap_sta->tid_data[i].seq_number >> 4);
 	}
 
-	/* now we have all the data we need, unlock to avoid mac80211 issues */
-	mutex_unlock(&mvm->mutex);
-
 	iwl_mvm_report_wakeup_reasons(mvm, vif, status);
 
 	keep = iwl_mvm_setup_connection_keep(mvm, vif, status);
-
-	return keep;
-
 out_unlock:
 	mutex_unlock(&mvm->mutex);
-	return false;
+	return keep;
 }
 
 #define ND_QUERY_BUF_LEN (sizeof(struct iwl_scan_offload_profile_match) * \
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index 329c545f65fd..edc8204f7c0e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -1521,7 +1521,7 @@ static ssize_t iwl_dbgfs_inject_packet_write(struct iwl_mvm *mvm,
 
 	/* supporting only MQ RX */
 	if (!mvm->trans->trans_cfg->mq_rx_supported)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	rxb._page = alloc_pages(GFP_ATOMIC, 0);
 	if (!rxb._page)
@@ -1714,6 +1714,20 @@ static ssize_t iwl_dbgfs_fw_dbg_collect_write(struct iwl_mvm *mvm,
 	return count;
 }
 
+static ssize_t iwl_dbgfs_fw_dbg_clear_write(struct iwl_mvm *mvm,
+					    char *buf, size_t count,
+					    loff_t *ppos)
+{
+	if (mvm->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_9000)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&mvm->mutex);
+	iwl_fw_dbg_clear_monitor_buf(&mvm->fwrt);
+	mutex_unlock(&mvm->mutex);
+
+	return count;
+}
+
 static ssize_t iwl_dbgfs_dbg_time_point_write(struct iwl_mvm *mvm,
 					      char *buf, size_t count,
 					      loff_t *ppos)
@@ -1815,7 +1829,7 @@ static ssize_t _iwl_dbgfs_link_sta_##name##_write(struct file *file,	\
 	char buf[buflen] = {};						\
 	size_t buf_size = min(count, sizeof(buf) -  1);			\
 									\
-	if (copy_from_user(buf, user_buf, sizeof(buf)))			\
+	if (copy_from_user(buf, user_buf, buf_size))			\
 		return -EFAULT;						\
 									\
 	return _iwl_dbgfs_link_sta_wrap_write(iwl_dbgfs_##name##_write,	\
@@ -2166,6 +2180,7 @@ MVM_DEBUGFS_WRITE_FILE_OPS(bt_force_ant, 10);
 MVM_DEBUGFS_READ_WRITE_FILE_OPS(scan_ant_rxchain, 8);
 MVM_DEBUGFS_READ_WRITE_FILE_OPS(fw_dbg_conf, 8);
 MVM_DEBUGFS_WRITE_FILE_OPS(fw_dbg_collect, 64);
+MVM_DEBUGFS_WRITE_FILE_OPS(fw_dbg_clear, 64);
 MVM_DEBUGFS_WRITE_FILE_OPS(dbg_time_point, 64);
 MVM_DEBUGFS_WRITE_FILE_OPS(indirection_tbl,
 			   (IWL_RSS_INDIRECTION_TABLE_SIZE * 2));
@@ -2372,6 +2387,7 @@ void iwl_mvm_dbgfs_register(struct iwl_mvm *mvm)
 	MVM_DEBUGFS_ADD_FILE(prph_reg, mvm->debugfs_dir, 0600);
 	MVM_DEBUGFS_ADD_FILE(fw_dbg_conf, mvm->debugfs_dir, 0600);
 	MVM_DEBUGFS_ADD_FILE(fw_dbg_collect, mvm->debugfs_dir, 0200);
+	MVM_DEBUGFS_ADD_FILE(fw_dbg_clear, mvm->debugfs_dir, 0200);
 	MVM_DEBUGFS_ADD_FILE(dbg_time_point, mvm->debugfs_dir, 0200);
 	MVM_DEBUGFS_ADD_FILE(send_echo_cmd, mvm->debugfs_dir, 0200);
 	MVM_DEBUGFS_ADD_FILE(indirection_tbl, mvm->debugfs_dir, 0200);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-responder.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-responder.c
index 10b9219b3bfd..8f10590f9cdd 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-responder.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-responder.c
@@ -39,7 +39,7 @@ static int iwl_mvm_ftm_responder_set_bw_v1(struct cfg80211_chan_def *chandef,
 		*ctrl_ch_position = iwl_mvm_get_ctrl_pos(chandef);
 		break;
 	default:
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 
 	return 0;
@@ -77,7 +77,7 @@ static int iwl_mvm_ftm_responder_set_bw_v2(struct cfg80211_chan_def *chandef,
 		}
 		fallthrough;
 	default:
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 
 	return 0;
@@ -291,7 +291,7 @@ iwl_mvm_ftm_responder_dyn_cfg_cmd(struct iwl_mvm *mvm,
 	default:
 		IWL_ERR(mvm, "Unsupported DYN_CONFIG_CMD version %u\n",
 			cmd_ver);
-		ret = -ENOTSUPP;
+		ret = -EOPNOTSUPP;
 	}
 
 	return ret;
@@ -333,7 +333,7 @@ int iwl_mvm_ftm_respoder_add_pasn_sta(struct iwl_mvm *mvm,
 
 	if (cmd_ver < 3) {
 		IWL_ERR(mvm, "Adding PASN station not supported by FW\n");
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 
 	if ((!hltk || !hltk_len) && (!tk || !tk_len)) {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 403bd17b8b7a..1252084662c6 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -27,9 +27,6 @@
 #define MVM_UCODE_ALIVE_TIMEOUT	(2 * HZ)
 #define MVM_UCODE_CALIB_TIMEOUT	(2 * HZ)
 
-#define IWL_TAS_US_MCC 0x5553
-#define IWL_TAS_CANADA_MCC 0x4341
-
 #define IWL_UATS_VLP_AP_SUPPORTED BIT(29)
 #define IWL_UATS_AFC_AP_SUPPORTED BIT(30)
 
@@ -1234,10 +1231,10 @@ static void iwl_mvm_tas_init(struct iwl_mvm *mvm)
 				dmi_get_system_info(DMI_SYS_VENDOR));
 		if ((!iwl_mvm_add_to_tas_block_list(cmd.v4.block_list_array,
 						    &cmd.v4.block_list_size,
-							IWL_TAS_US_MCC)) ||
+							IWL_MCC_US)) ||
 		    (!iwl_mvm_add_to_tas_block_list(cmd.v4.block_list_array,
 						    &cmd.v4.block_list_size,
-							IWL_TAS_CANADA_MCC))) {
+							IWL_MCC_CANADA))) {
 			IWL_DEBUG_RADIO(mvm,
 					"Unable to add US/Canada to TAS block list, disabling TAS\n");
 			return;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index a64600f0ed9f..7f13dff04b26 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -152,6 +152,16 @@ struct ieee80211_regdomain *iwl_mvm_get_regdomain(struct wiphy *wiphy,
 	mvm->lar_regdom_set = true;
 	mvm->mcc_src = src_id;
 
+	/* Some kind of regulatory mess means we need to currently disallow
+	 * puncturing in the US and Canada. Do that here, at least until we
+	 * figure out the new chanctx APIs for puncturing.
+	 */
+	if (resp->mcc == cpu_to_le16(IWL_MCC_US) ||
+	    resp->mcc == cpu_to_le16(IWL_MCC_CANADA))
+		ieee80211_hw_set(mvm->hw, DISALLOW_PUNCTURING);
+	else
+		__clear_bit(IEEE80211_HW_DISALLOW_PUNCTURING, mvm->hw->flags);
+
 	iwl_mei_set_country_code(__le16_to_cpu(resp->mcc));
 
 out:
@@ -288,7 +298,7 @@ int iwl_mvm_op_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant)
 	/* This has been tested on those devices only */
 	if (mvm->trans->trans_cfg->device_family != IWL_DEVICE_FAMILY_9000 &&
 	    mvm->trans->trans_cfg->device_family != IWL_DEVICE_FAMILY_22000)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (!mvm->nvm_data)
 		return -EBUSY;
@@ -517,6 +527,10 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 		hw->wiphy->regulatory_flags |= REGULATORY_CUSTOM_REG |
 					       REGULATORY_DISABLE_BEACON_HINTS;
 
+	if (mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
+		wiphy_ext_feature_set(hw->wiphy,
+				      NL80211_EXT_FEATURE_DFS_CONCURRENT);
+
 	hw->wiphy->flags |= WIPHY_FLAG_AP_UAPSD;
 	hw->wiphy->flags |= WIPHY_FLAG_HAS_CHANNEL_SWITCH;
 	hw->wiphy->flags |= WIPHY_FLAG_SPLIT_SCAN_6GHZ;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
index ff6cb064051b..61170173f917 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
@@ -271,17 +271,17 @@ __iwl_mvm_mld_assign_vif_chanctx(struct iwl_mvm *mvm,
 		}
 	}
 
+	mvmvif->link[link_id]->phy_ctxt = phy_ctxt;
+
 	if (iwl_mvm_is_esr_supported(mvm->fwrt.trans) && n_active > 1) {
 		mvmvif->link[link_id]->listen_lmac = true;
 		ret = iwl_mvm_esr_mode_active(mvm, vif);
 		if (ret) {
 			IWL_ERR(mvm, "failed to activate ESR mode (%d)\n", ret);
-			return ret;
+			goto out;
 		}
 	}
 
-	mvmvif->link[link_id]->phy_ctxt = phy_ctxt;
-
 	if (switching_chanctx) {
 		/* reactivate if we turned this off during channel switch */
 		if (vif->type == NL80211_IFTYPE_AP)
@@ -716,7 +716,7 @@ void iwl_mvm_mld_select_links(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 		}
 	}
 
-	if (WARN_ON(!new_active_links))
+	if (!new_active_links)
 		return;
 
 	if (vif->active_links != new_active_links)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
index ca5e4fbcf8ce..1628bf55458f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
@@ -707,8 +707,10 @@ int iwl_mvm_mld_add_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			rcu_dereference_protected(mvm_sta->link[link_id],
 						  lockdep_is_held(&mvm->mutex));
 
-		if (WARN_ON(!link_conf || !mvm_link_sta))
+		if (WARN_ON(!link_conf || !mvm_link_sta)) {
+			ret = -EINVAL;
 			goto err;
+		}
 
 		ret = iwl_mvm_mld_cfg_sta(mvm, sta, vif, link_sta, link_conf,
 					  mvm_link_sta);
@@ -872,6 +874,9 @@ void iwl_mvm_mld_sta_modify_disable_tx(struct iwl_mvm *mvm,
 	cmd.sta_id = cpu_to_le32(mvmsta->deflink.sta_id);
 	cmd.disable = cpu_to_le32(disable);
 
+	if (WARN_ON(iwl_mvm_has_no_host_disable_tx(mvm)))
+		return;
+
 	ret = iwl_mvm_send_cmd_pdu(mvm,
 				   WIDE_ID(MAC_CONF_GROUP, STA_DISABLE_TX_CMD),
 				   CMD_ASYNC, sizeof(cmd), &cmd);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index f2af3e571409..40627961b834 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -947,6 +947,7 @@ struct iwl_mvm {
 
 	/* the vif that requested the current scan */
 	struct iwl_mvm_vif *scan_vif;
+	u8 scan_link_id;
 
 	/* rx chain antennas set through debugfs for the scan command */
 	u8 scan_rx_ant;
@@ -1513,6 +1514,12 @@ static inline bool iwl_mvm_has_quota_low_latency(struct iwl_mvm *mvm)
 			  IWL_UCODE_TLV_API_QUOTA_LOW_LATENCY);
 }
 
+static inline bool iwl_mvm_has_no_host_disable_tx(struct iwl_mvm *mvm)
+{
+	return fw_has_api(&mvm->fw->ucode_capa,
+			  IWL_UCODE_TLV_API_NO_HOST_DISABLE_TX);
+}
+
 static inline bool iwl_mvm_has_tlc_offload(const struct iwl_mvm *mvm)
 {
 	return fw_has_capa(&mvm->fw->ucode_capa,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 1627b2f819db..adbbe19aeae5 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -1703,18 +1703,6 @@ void iwl_mvm_rx_mq(struct iwl_op_mode *op_mode,
 		iwl_mvm_rx_common(mvm, rxb, pkt);
 }
 
-static void iwl_mvm_async_cb(struct iwl_op_mode *op_mode,
-			     const struct iwl_device_cmd *cmd)
-{
-	struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
-
-	/*
-	 * For now, we only set the CMD_WANT_ASYNC_CALLBACK for ADD_STA
-	 * commands that need to block the Tx queues.
-	 */
-	iwl_trans_block_txq_ptrs(mvm->trans, false);
-}
-
 static int iwl_mvm_is_static_queue(struct iwl_mvm *mvm, int queue)
 {
 	return queue == mvm->aux_queue || queue == mvm->probe_queue ||
@@ -2024,7 +2012,6 @@ static void iwl_op_mode_mvm_time_point(struct iwl_op_mode *op_mode,
 
 #define IWL_MVM_COMMON_OPS					\
 	/* these could be differentiated */			\
-	.async_cb = iwl_mvm_async_cb,				\
 	.queue_full = iwl_mvm_stop_sw_queue,			\
 	.queue_not_full = iwl_mvm_wake_sw_queue,		\
 	.hw_rf_kill = iwl_mvm_set_hw_rfkill_state,		\
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c
index 4e1fccff3987..334d1f59f6e4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c
@@ -99,17 +99,6 @@ static void iwl_mvm_phy_ctxt_set_rxchain(struct iwl_mvm *mvm,
 		active_cnt = 2;
 	}
 
-	/*
-	 * If the firmware requested it, then we know that it supports
-	 * getting zero for the values to indicate "use one, but pick
-	 * which one yourself", which means it can dynamically pick one
-	 * that e.g. has better RSSI.
-	 */
-	if (mvm->fw_static_smps_request && active_cnt == 1 && idle_cnt == 1) {
-		idle_cnt = 0;
-		active_cnt = 0;
-	}
-
 	*rxchain_info = cpu_to_le32(iwl_mvm_get_valid_rx_ant(mvm) <<
 					PHY_RX_CHAIN_VALID_POS);
 	*rxchain_info |= cpu_to_le32(idle_cnt << PHY_RX_CHAIN_CNT_POS);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index 75c5c58e14a5..7b6f1cdca067 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -101,6 +101,7 @@ struct iwl_mvm_scan_params {
 	bool scan_6ghz;
 	bool enable_6ghz_passive;
 	bool respect_p2p_go, respect_p2p_go_hb;
+	s8 tsf_report_link_id;
 	u8 bssid[ETH_ALEN] __aligned(2);
 };
 
@@ -2342,20 +2343,15 @@ iwl_mvm_scan_umac_fill_general_p_v12(struct iwl_mvm *mvm,
 	if (gen_flags & IWL_UMAC_SCAN_GEN_FLAGS_V2_FRAGMENTED_LMAC2)
 		gp->num_of_fragments[SCAN_HB_LMAC_IDX] = IWL_SCAN_NUM_OF_FRAGS;
 
+	mvm->scan_link_id = 0;
+
 	if (version < 16) {
 		gp->scan_start_mac_or_link_id = scan_vif->id;
 	} else {
-		struct iwl_mvm_vif_link_info *link_info;
-		u8 link_id = 0;
+		struct iwl_mvm_vif_link_info *link_info =
+			scan_vif->link[params->tsf_report_link_id];
 
-		/* Use one of the active link (if any). In the future it would
-		 * be possible that the link ID would be part of the scan
-		 * request coming from upper layers so we would need to use it.
-		 */
-		if (vif->active_links)
-			link_id = ffs(vif->active_links) - 1;
-
-		link_info = scan_vif->link[link_id];
+		mvm->scan_link_id = params->tsf_report_link_id;
 		if (!WARN_ON(!link_info))
 			gp->scan_start_mac_or_link_id = link_info->fw_link_id;
 	}
@@ -2977,6 +2973,14 @@ int iwl_mvm_reg_scan_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	if (req->duration)
 		params.iter_notif = true;
 
+	params.tsf_report_link_id = req->tsf_report_link_id;
+	if (params.tsf_report_link_id < 0) {
+		if (vif->active_links)
+			params.tsf_report_link_id = __ffs(vif->active_links);
+		else
+			params.tsf_report_link_id = 0;
+	}
+
 	iwl_mvm_build_scan_probe(mvm, vif, ies, &params);
 
 	iwl_mvm_scan_6ghz_passive_scan(mvm, &params, vif);
@@ -3164,8 +3168,13 @@ void iwl_mvm_rx_umac_scan_complete_notif(struct iwl_mvm *mvm,
 			.aborted = aborted,
 			.scan_start_tsf = mvm->scan_start,
 		};
+		struct iwl_mvm_vif *scan_vif = mvm->scan_vif;
+		struct iwl_mvm_vif_link_info *link_info =
+			scan_vif->link[mvm->scan_link_id];
+
+		if (!WARN_ON(!link_info))
+			memcpy(info.tsf_bssid, link_info->bssid, ETH_ALEN);
 
-		memcpy(info.tsf_bssid, mvm->scan_vif->deflink.bssid, ETH_ALEN);
 		ieee80211_scan_completed(mvm->hw, &info);
 		mvm->scan_vif = NULL;
 		cancel_delayed_work(&mvm->scan_timeout_dwork);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index bba96a968890..2a3ca9785974 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -2550,7 +2550,7 @@ int iwl_mvm_add_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 
 	if (WARN_ON(vif->type != NL80211_IFTYPE_AP &&
 		    vif->type != NL80211_IFTYPE_ADHOC))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	/*
 	 * In IBSS, ieee80211_check_queues() sets the cab_queue to be
@@ -3234,7 +3234,7 @@ int iwl_mvm_sta_tx_agg_oper(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 		 * should be updated as well.
 		 */
 		if (buf_size < IWL_FRAME_LIMIT)
-			return -ENOTSUPP;
+			return -EOPNOTSUPP;
 
 		ret = iwl_mvm_sta_tx_agg(mvm, sta, tid, queue, true);
 		if (ret)
@@ -4111,10 +4111,8 @@ void iwl_mvm_sta_modify_sleep_tx_count(struct iwl_mvm *mvm,
 	}
 
 	/* block the Tx queues until the FW updated the sleep Tx count */
-	iwl_trans_block_txq_ptrs(mvm->trans, true);
-
 	ret = iwl_mvm_send_cmd_pdu(mvm, ADD_STA,
-				   CMD_ASYNC | CMD_WANT_ASYNC_CALLBACK,
+				   CMD_ASYNC | CMD_BLOCK_TXQS,
 				   iwl_mvm_add_sta_cmd_size(mvm), &cmd);
 	if (ret)
 		IWL_ERR(mvm, "Failed to send ADD_STA command (%d)\n", ret);
@@ -4152,7 +4150,8 @@ void iwl_mvm_sta_modify_disable_tx(struct iwl_mvm *mvm,
 	int ret;
 
 	if (mvm->mld_api_is_used) {
-		iwl_mvm_mld_sta_modify_disable_tx(mvm, mvmsta, disable);
+		if (!iwl_mvm_has_no_host_disable_tx(mvm))
+			iwl_mvm_mld_sta_modify_disable_tx(mvm, mvmsta, disable);
 		return;
 	}
 
@@ -4169,7 +4168,8 @@ void iwl_mvm_sta_modify_disable_tx_ap(struct iwl_mvm *mvm,
 	struct iwl_mvm_sta *mvm_sta = iwl_mvm_sta_from_mac80211(sta);
 
 	if (mvm->mld_api_is_used) {
-		iwl_mvm_mld_sta_modify_disable_tx_ap(mvm, sta, disable);
+		if (!iwl_mvm_has_no_host_disable_tx(mvm))
+			iwl_mvm_mld_sta_modify_disable_tx_ap(mvm, sta, disable);
 		return;
 	}
 
@@ -4224,7 +4224,9 @@ void iwl_mvm_modify_all_sta_disable_tx(struct iwl_mvm *mvm,
 	int i;
 
 	if (mvm->mld_api_is_used) {
-		iwl_mvm_mld_modify_all_sta_disable_tx(mvm, mvmvif, disable);
+		if (!iwl_mvm_has_no_host_disable_tx(mvm))
+			iwl_mvm_mld_modify_all_sta_disable_tx(mvm, mvmvif,
+							      disable);
 		return;
 	}
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index ae5cd13cd6dd..db986bfc4dc3 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -2256,7 +2256,7 @@ int iwl_mvm_flush_sta_tids(struct iwl_mvm *mvm, u32 sta_id, u16 tids)
 	WARN_ON(!iwl_mvm_has_new_tx_api(mvm));
 
 	if (iwl_fw_lookup_notif_ver(mvm->fw, LONG_GROUP, TXPATH_FLUSH, 0) > 0)
-		cmd.flags |= CMD_WANT_SKB;
+		cmd.flags |= CMD_WANT_SKB | CMD_SEND_IN_RFKILL;
 
 	IWL_DEBUG_TX_QUEUES(mvm, "flush for sta id %d tid mask 0x%x\n",
 			    sta_id, tids);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 26a0953603ab..2c9b98c8184b 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -1121,9 +1121,8 @@ static const struct iwl_dev_info iwl_dev_info_table[] = {
 /*
  * Read rf id and cdb info from prph register and store it
  */
-static int get_crf_id(struct iwl_trans *iwl_trans)
+static void get_crf_id(struct iwl_trans *iwl_trans)
 {
-	int ret = 0;
 	u32 sd_reg_ver_addr;
 	u32 val = 0;
 
@@ -1150,8 +1149,6 @@ static int get_crf_id(struct iwl_trans *iwl_trans)
 	IWL_INFO(iwl_trans, "Detected crf-id 0x%x, cnv-id 0x%x wfpm id 0x%x\n",
 		 iwl_trans->hw_crf_id, iwl_trans->hw_cnv_id,
 		 iwl_trans->hw_wfpm_id);
-
-	return ret;
 }
 
 /*
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index 56def20374f3..7805a42948af 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -770,7 +770,7 @@ static inline void iwl_enable_rfkill_int(struct iwl_trans *trans)
 	}
 }
 
-void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans);
+void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans, bool from_irq);
 
 static inline bool iwl_is_rfkill_set(struct iwl_trans *trans)
 {
@@ -817,7 +817,7 @@ static inline bool iwl_pcie_dbg_on(struct iwl_trans *trans)
 	return (trans->dbg.dest_tlv || iwl_trans_dbg_ini_valid(trans));
 }
 
-void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state);
+void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state, bool from_irq);
 void iwl_trans_pcie_dump_regs(struct iwl_trans *trans);
 
 #ifdef CONFIG_IWLWIFI_DEBUGFS
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index 146bc7bd14fb..9c2461ba13c5 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -1351,8 +1351,7 @@ static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans,
 		if (len < sizeof(*pkt) || offset > max_len)
 			break;
 
-		trace_iwlwifi_dev_rx(trans->dev, trans, pkt, len);
-		trace_iwlwifi_dev_rx_data(trans->dev, trans, pkt, len);
+		maybe_trace_iwlwifi_dev_rx(trans, pkt, len);
 
 		/* Reclaim a command buffer only if this packet is a response
 		 *   to a (driver-originated) command.
@@ -1385,7 +1384,7 @@ static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans,
 		 * if it is true then one of the handlers took the page.
 		 */
 
-		if (reclaim) {
+		if (reclaim && txq) {
 			u16 sequence = le16_to_cpu(pkt->hdr.sequence);
 			int index = SEQ_TO_INDEX(sequence);
 			int cmd_index = iwl_txq_get_cmd_index(txq, index);
@@ -1783,7 +1782,7 @@ static u32 iwl_pcie_int_cause_ict(struct iwl_trans *trans)
 	return inta;
 }
 
-void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans)
+void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans, bool from_irq)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct isr_statistics *isr_stats = &trans_pcie->isr_stats;
@@ -1807,7 +1806,7 @@ void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans)
 	isr_stats->rfkill++;
 
 	if (prev != report)
-		iwl_trans_pcie_rf_kill(trans, report);
+		iwl_trans_pcie_rf_kill(trans, report, from_irq);
 	mutex_unlock(&trans_pcie->mutex);
 
 	if (hw_rfkill) {
@@ -1947,7 +1946,7 @@ irqreturn_t iwl_pcie_irq_handler(int irq, void *dev_id)
 
 	/* HW RF KILL switch toggled */
 	if (inta & CSR_INT_BIT_RF_KILL) {
-		iwl_pcie_handle_rfkill_irq(trans);
+		iwl_pcie_handle_rfkill_irq(trans, true);
 		handled |= CSR_INT_BIT_RF_KILL;
 	}
 
@@ -2370,7 +2369,7 @@ irqreturn_t iwl_pcie_irq_msix_handler(int irq, void *dev_id)
 
 	/* HW RF KILL switch toggled */
 	if (inta_hw & MSIX_HW_INT_CAUSES_REG_RF_KILL)
-		iwl_pcie_handle_rfkill_irq(trans);
+		iwl_pcie_handle_rfkill_irq(trans, true);
 
 	if (inta_hw & MSIX_HW_INT_CAUSES_REG_HW_ERR) {
 		IWL_ERR(trans,
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
index c9e5bda8f0b7..a4a4772330cf 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
@@ -290,6 +290,16 @@ static void iwl_pcie_get_rf_name(struct iwl_trans *trans)
 	case CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_MS):
 		pos = scnprintf(buf, buflen, "MS");
 		break;
+	case CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_FM):
+		pos = scnprintf(buf, buflen, "FM");
+		break;
+	case CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_WP):
+		if (SILICON_Z_STEP ==
+		    CSR_HW_RFID_STEP(trans->hw_rf_id))
+			pos = scnprintf(buf, buflen, "WHTC");
+		else
+			pos = scnprintf(buf, buflen, "WH");
+		break;
 	default:
 		return;
 	}
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index a468e5efeecd..63e13577aff8 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -1082,7 +1082,7 @@ bool iwl_pcie_check_hw_rf_kill(struct iwl_trans *trans)
 	report = test_bit(STATUS_RFKILL_OPMODE, &trans->status);
 
 	if (prev != report)
-		iwl_trans_pcie_rf_kill(trans, report);
+		iwl_trans_pcie_rf_kill(trans, report, false);
 
 	return hw_rfkill;
 }
@@ -1237,7 +1237,7 @@ static void iwl_pcie_init_msix(struct iwl_trans_pcie *trans_pcie)
 	trans_pcie->hw_mask = trans_pcie->hw_init_mask;
 }
 
-static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans)
+static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool from_irq)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 
@@ -1264,7 +1264,8 @@ static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans)
 	if (test_and_clear_bit(STATUS_DEVICE_ENABLED, &trans->status)) {
 		IWL_DEBUG_INFO(trans,
 			       "DEVICE_ENABLED bit was set and is now cleared\n");
-		iwl_pcie_synchronize_irqs(trans);
+		if (!from_irq)
+			iwl_pcie_synchronize_irqs(trans);
 		iwl_pcie_rx_napi_sync(trans);
 		iwl_pcie_tx_stop(trans);
 		iwl_pcie_rx_stop(trans);
@@ -1454,7 +1455,7 @@ void iwl_trans_pcie_handle_stop_rfkill(struct iwl_trans *trans,
 		clear_bit(STATUS_RFKILL_OPMODE, &trans->status);
 	}
 	if (hw_rfkill != was_in_rfkill)
-		iwl_trans_pcie_rf_kill(trans, hw_rfkill);
+		iwl_trans_pcie_rf_kill(trans, hw_rfkill, false);
 }
 
 static void iwl_trans_pcie_stop_device(struct iwl_trans *trans)
@@ -1469,12 +1470,12 @@ static void iwl_trans_pcie_stop_device(struct iwl_trans *trans)
 	mutex_lock(&trans_pcie->mutex);
 	trans_pcie->opmode_down = true;
 	was_in_rfkill = test_bit(STATUS_RFKILL_OPMODE, &trans->status);
-	_iwl_trans_pcie_stop_device(trans);
+	_iwl_trans_pcie_stop_device(trans, false);
 	iwl_trans_pcie_handle_stop_rfkill(trans, was_in_rfkill);
 	mutex_unlock(&trans_pcie->mutex);
 }
 
-void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state)
+void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state, bool from_irq)
 {
 	struct iwl_trans_pcie __maybe_unused *trans_pcie =
 		IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -1487,7 +1488,7 @@ void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state)
 		if (trans->trans_cfg->gen2)
 			_iwl_trans_pcie_gen2_stop_device(trans);
 		else
-			_iwl_trans_pcie_stop_device(trans);
+			_iwl_trans_pcie_stop_device(trans, from_irq);
 	}
 }
 
@@ -2107,18 +2108,29 @@ static void iwl_trans_pcie_removal_wk(struct work_struct *wk)
 		container_of(wk, struct iwl_trans_pcie_removal, work);
 	struct pci_dev *pdev = removal->pdev;
 	static char *prop[] = {"EVENT=INACCESSIBLE", NULL};
-	struct pci_bus *bus = pdev->bus;
+	struct pci_bus *bus;
+
+	pci_lock_rescan_remove();
+
+	bus = pdev->bus;
+	/* in this case, something else already removed the device */
+	if (!bus)
+		goto out;
 
 	dev_err(&pdev->dev, "Device gone - attempting removal\n");
+
 	kobject_uevent_env(&pdev->dev.kobj, KOBJ_CHANGE, prop);
-	pci_lock_rescan_remove();
-	pci_dev_put(pdev);
+
 	pci_stop_and_remove_bus_device(pdev);
-	if (removal->rescan && bus) {
+	pci_dev_put(pdev);
+
+	if (removal->rescan) {
 		if (bus->parent)
 			bus = bus->parent;
 		pci_rescan_bus(bus);
 	}
+
+out:
 	pci_unlock_rescan_remove();
 
 	kfree(removal);
@@ -2133,6 +2145,7 @@ void iwl_trans_pcie_remove(struct iwl_trans *trans, bool rescan)
 		return;
 
 	IWL_ERR(trans, "Device gone - scheduling removal!\n");
+	iwl_pcie_dump_csr(trans);
 
 	/*
 	 * get a module reference to avoid doing this
@@ -2365,32 +2378,6 @@ static int iwl_trans_pcie_read_config32(struct iwl_trans *trans, u32 ofs,
 				     ofs, val);
 }
 
-static void iwl_trans_pcie_block_txq_ptrs(struct iwl_trans *trans, bool block)
-{
-	int i;
-
-	for (i = 0; i < trans->trans_cfg->base_params->num_of_queues; i++) {
-		struct iwl_txq *txq = trans->txqs.txq[i];
-
-		if (i == trans->txqs.cmd.q_id)
-			continue;
-
-		spin_lock_bh(&txq->lock);
-
-		if (!block && !(WARN_ON_ONCE(!txq->block))) {
-			txq->block--;
-			if (!txq->block) {
-				iwl_write32(trans, HBUS_TARG_WRPTR,
-					    txq->write_ptr | (i << 8));
-			}
-		} else if (block) {
-			txq->block++;
-		}
-
-		spin_unlock_bh(&txq->lock);
-	}
-}
-
 #define IWL_FLUSH_WAIT_MS	2000
 
 static int iwl_trans_pcie_rxq_dma_data(struct iwl_trans *trans, int queue,
@@ -2887,7 +2874,7 @@ static ssize_t iwl_dbgfs_rfkill_write(struct file *file,
 	IWL_WARN(trans, "changing debug rfkill %d->%d\n",
 		 trans_pcie->debug_rfkill, new_value);
 	trans_pcie->debug_rfkill = new_value;
-	iwl_pcie_handle_rfkill_irq(trans);
+	iwl_pcie_handle_rfkill_irq(trans, false);
 
 	return count;
 }
@@ -3106,7 +3093,7 @@ static u32 iwl_trans_pcie_dump_rbs(struct iwl_trans *trans,
 	struct iwl_rxq *rxq = &trans_pcie->rxq[0];
 	u32 i, r, j, rb_len = 0;
 
-	spin_lock(&rxq->lock);
+	spin_lock_bh(&rxq->lock);
 
 	r = iwl_get_closed_rb_stts(trans, rxq);
 
@@ -3130,7 +3117,7 @@ static u32 iwl_trans_pcie_dump_rbs(struct iwl_trans *trans,
 		*data = iwl_fw_error_next_data(*data);
 	}
 
-	spin_unlock(&rxq->lock);
+	spin_unlock_bh(&rxq->lock);
 
 	return rb_len;
 }
@@ -3572,7 +3559,6 @@ static const struct iwl_trans_ops trans_ops_pcie = {
 	.wait_tx_queues_empty = iwl_trans_pcie_wait_txqs_empty,
 
 	.freeze_txq_timer = iwl_trans_txq_freeze_timer,
-	.block_txq_ptrs = iwl_trans_pcie_block_txq_ptrs,
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 	.debugfs_cleanup = iwl_trans_pcie_debugfs_cleanup,
 #endif
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index c72a84d8bb4f..aabbef114bc2 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (C) 2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2020 Intel Corporation
+ * Copyright (C) 2018-2020, 2023 Intel Corporation
  */
 #include <net/tso.h>
 #include <linux/tcp.h>
@@ -42,6 +42,9 @@ int iwl_pcie_gen2_enqueue_hcmd(struct iwl_trans *trans,
 	struct iwl_tfh_tfd *tfd;
 	unsigned long flags;
 
+	if (WARN_ON(cmd->flags & CMD_BLOCK_TXQS))
+		return -EINVAL;
+
 	copy_size = sizeof(struct iwl_cmd_header_wide);
 	cmd_size = sizeof(struct iwl_cmd_header_wide);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index 2f39b639c43f..6c2b37e56c78 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -873,6 +873,33 @@ void iwl_trans_pcie_txq_disable(struct iwl_trans *trans, int txq_id,
 
 /*************** HOST COMMAND QUEUE FUNCTIONS   *****/
 
+static void iwl_trans_pcie_block_txq_ptrs(struct iwl_trans *trans, bool block)
+{
+	int i;
+
+	for (i = 0; i < trans->trans_cfg->base_params->num_of_queues; i++) {
+		struct iwl_txq *txq = trans->txqs.txq[i];
+
+		if (i == trans->txqs.cmd.q_id)
+			continue;
+
+		/* we skip the command queue (obviously) so it's OK to nest */
+		spin_lock_nested(&txq->lock, 1);
+
+		if (!block && !(WARN_ON_ONCE(!txq->block))) {
+			txq->block--;
+			if (!txq->block) {
+				iwl_write32(trans, HBUS_TARG_WRPTR,
+					    txq->write_ptr | (i << 8));
+			}
+		} else if (block) {
+			txq->block++;
+		}
+
+		spin_unlock(&txq->lock);
+	}
+}
+
 /*
  * iwl_pcie_enqueue_hcmd - enqueue a uCode command
  * @priv: device private data point
@@ -1137,6 +1164,9 @@ int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 		goto out;
 	}
 
+	if (cmd->flags & CMD_BLOCK_TXQS)
+		iwl_trans_pcie_block_txq_ptrs(trans, true);
+
 	/* Increment and update queue's write index */
 	txq->write_ptr = iwl_txq_inc_wrap(trans, txq->write_ptr);
 	iwl_pcie_txq_inc_wr_ptr(trans, txq);
@@ -1202,8 +1232,8 @@ void iwl_pcie_hcmd_complete(struct iwl_trans *trans,
 		meta->source->_rx_page_order = trans_pcie->rx_page_order;
 	}
 
-	if (meta->flags & CMD_WANT_ASYNC_CALLBACK)
-		iwl_op_mode_async_cb(trans->op_mode, cmd);
+	if (meta->flags & CMD_BLOCK_TXQS)
+		iwl_trans_pcie_block_txq_ptrs(trans, false);
 
 	iwl_pcie_cmdq_reclaim(trans, txq_id, index);
 
diff --git a/drivers/net/wireless/intersil/Kconfig b/drivers/net/wireless/intersil/Kconfig
index bd6bf70ece03..201b1534a9ca 100644
--- a/drivers/net/wireless/intersil/Kconfig
+++ b/drivers/net/wireless/intersil/Kconfig
@@ -12,8 +12,6 @@ config WLAN_VENDOR_INTERSIL
 
 if WLAN_VENDOR_INTERSIL
 
-source "drivers/net/wireless/intersil/hostap/Kconfig"
-source "drivers/net/wireless/intersil/orinoco/Kconfig"
 source "drivers/net/wireless/intersil/p54/Kconfig"
 
 endif # WLAN_VENDOR_INTERSIL
diff --git a/drivers/net/wireless/intersil/Makefile b/drivers/net/wireless/intersil/Makefile
index 65281d1b3d85..27e9b2869da1 100644
--- a/drivers/net/wireless/intersil/Makefile
+++ b/drivers/net/wireless/intersil/Makefile
@@ -1,4 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_HOSTAP)		+= hostap/
-obj-$(CONFIG_HERMES)		+= orinoco/
 obj-$(CONFIG_P54_COMMON)	+= p54/
diff --git a/drivers/net/wireless/intersil/hostap/Kconfig b/drivers/net/wireless/intersil/hostap/Kconfig
deleted file mode 100644
index 2edff8efbcbb..000000000000
--- a/drivers/net/wireless/intersil/hostap/Kconfig
+++ /dev/null
@@ -1,95 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-config HOSTAP
-	tristate "IEEE 802.11 for Host AP (Prism2/2.5/3 and WEP/TKIP/CCMP)"
-	select WIRELESS_EXT
-	select WEXT_SPY
-	select WEXT_PRIV
-	select CRYPTO
-	select CRYPTO_MICHAEL_MIC
-	select CRC32
-	select LIB80211
-	select LIB80211_CRYPT_WEP
-	select LIB80211_CRYPT_TKIP
-	select LIB80211_CRYPT_CCMP
-	help
-	Shared driver code for IEEE 802.11b wireless cards based on
-	Intersil Prism2/2.5/3 chipset. This driver supports so called
-	Host AP mode that allows the card to act as an IEEE 802.11
-	access point.
-
-	See <http://hostap.epitest.fi/> for more information about the
-	Host AP driver configuration and tools. This site includes
-	information and tools (hostapd and wpa_supplicant) for WPA/WPA2
-	support.
-
-	This option includes the base Host AP driver code that is shared by
-	different hardware models. You will also need to enable support for
-	PLX/PCI/CS version of the driver to actually use the driver.
-
-	The driver can be compiled as a module and it will be called
-	hostap.
-
-config HOSTAP_FIRMWARE
-	bool "Support downloading firmware images with Host AP driver"
-	depends on HOSTAP
-	help
-	Configure Host AP driver to include support for firmware image
-	download. This option by itself only enables downloading to the
-	volatile memory, i.e. the card RAM. This option is required to
-	support cards that don't have firmware in flash, such as D-Link
-	DWL-520 rev E and D-Link DWL-650 rev P.
-
-	Firmware image downloading needs a user space tool, prism2_srec.
-	It is available from http://hostap.epitest.fi/.
-
-config HOSTAP_FIRMWARE_NVRAM
-	bool "Support for non-volatile firmware download"
-	depends on HOSTAP_FIRMWARE
-	help
-	Allow Host AP driver to write firmware images to the non-volatile
-	card memory, i.e. flash memory that survives power cycling.
-	Enable this option if you want to be able to change card firmware
-	permanently.
-
-	Firmware image downloading needs a user space tool, prism2_srec.
-	It is available from http://hostap.epitest.fi/.
-
-config HOSTAP_PLX
-	tristate "Host AP driver for Prism2/2.5/3 in PLX9052 PCI adaptors"
-	depends on PCI && HOSTAP && HAS_IOPORT
-	help
-	Host AP driver's version for Prism2/2.5/3 PC Cards in PLX9052 based
-	PCI adaptors.
-
-	"Host AP support for Prism2/2.5/3 IEEE 802.11b" is required for this
-	driver and its help text includes more information about the Host AP
-	driver.
-
-	The driver can be compiled as a module and will be named
-	hostap_plx.
-
-config HOSTAP_PCI
-	tristate "Host AP driver for Prism2.5 PCI adaptors"
-	depends on PCI && HOSTAP
-	help
-	Host AP driver's version for Prism2.5 PCI adaptors.
-
-	"Host AP support for Prism2/2.5/3 IEEE 802.11b" is required for this
-	driver and its help text includes more information about the Host AP
-	driver.
-
-	The driver can be compiled as a module and will be named
-	hostap_pci.
-
-config HOSTAP_CS
-	tristate "Host AP driver for Prism2/2.5/3 PC Cards"
-	depends on PCMCIA && HOSTAP
-	help
-	Host AP driver's version for Prism2/2.5/3 PC Cards.
-
-	"Host AP support for Prism2/2.5/3 IEEE 802.11b" is required for this
-	driver and its help text includes more information about the Host AP
-	driver.
-
-	The driver can be compiled as a module and will be named
-	hostap_cs.
diff --git a/drivers/net/wireless/intersil/hostap/Makefile b/drivers/net/wireless/intersil/hostap/Makefile
deleted file mode 100644
index ae3bb73b2d99..000000000000
--- a/drivers/net/wireless/intersil/hostap/Makefile
+++ /dev/null
@@ -1,8 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-hostap-y := hostap_80211_rx.o hostap_80211_tx.o hostap_ap.o hostap_info.o \
-            hostap_ioctl.o hostap_main.o hostap_proc.o 
-obj-$(CONFIG_HOSTAP) += hostap.o
-
-obj-$(CONFIG_HOSTAP_CS) += hostap_cs.o
-obj-$(CONFIG_HOSTAP_PLX) += hostap_plx.o
-obj-$(CONFIG_HOSTAP_PCI) += hostap_pci.o
diff --git a/drivers/net/wireless/intersil/hostap/hostap.h b/drivers/net/wireless/intersil/hostap/hostap.h
deleted file mode 100644
index 552ae33d7875..000000000000
--- a/drivers/net/wireless/intersil/hostap/hostap.h
+++ /dev/null
@@ -1,98 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef HOSTAP_H
-#define HOSTAP_H
-
-#include <linux/ethtool.h>
-#include <linux/kernel.h>
-
-#include "hostap_wlan.h"
-#include "hostap_ap.h"
-
-static const long __maybe_unused freq_list[] = {
-	2412, 2417, 2422, 2427, 2432, 2437, 2442,
-	2447, 2452, 2457, 2462, 2467, 2472, 2484
-};
-#define FREQ_COUNT ARRAY_SIZE(freq_list)
-
-/* hostap.c */
-
-extern struct proc_dir_entry *hostap_proc;
-
-u16 hostap_tx_callback_register(local_info_t *local,
-				void (*func)(struct sk_buff *, int ok, void *),
-				void *data);
-int hostap_tx_callback_unregister(local_info_t *local, u16 idx);
-int hostap_set_word(struct net_device *dev, int rid, u16 val);
-int hostap_set_string(struct net_device *dev, int rid, const char *val);
-u16 hostap_get_porttype(local_info_t *local);
-int hostap_set_encryption(local_info_t *local);
-int hostap_set_antsel(local_info_t *local);
-int hostap_set_roaming(local_info_t *local);
-int hostap_set_auth_algs(local_info_t *local);
-void hostap_dump_rx_header(const char *name,
-			   const struct hfa384x_rx_frame *rx);
-void hostap_dump_tx_header(const char *name,
-			   const struct hfa384x_tx_frame *tx);
-extern const struct header_ops hostap_80211_ops;
-int hostap_80211_get_hdrlen(__le16 fc);
-struct net_device_stats *hostap_get_stats(struct net_device *dev);
-void hostap_setup_dev(struct net_device *dev, local_info_t *local,
-		      int type);
-void hostap_set_multicast_list_queue(struct work_struct *work);
-int hostap_set_hostapd(local_info_t *local, int val, int rtnl_locked);
-int hostap_set_hostapd_sta(local_info_t *local, int val, int rtnl_locked);
-void hostap_cleanup(local_info_t *local);
-void hostap_cleanup_handler(void *data);
-struct net_device * hostap_add_interface(struct local_info *local,
-					 int type, int rtnl_locked,
-					 const char *prefix, const char *name);
-void hostap_remove_interface(struct net_device *dev, int rtnl_locked,
-			     int remove_from_list);
-int prism2_update_comms_qual(struct net_device *dev);
-int prism2_sta_send_mgmt(local_info_t *local, u8 *dst, u16 stype,
-			 u8 *body, size_t bodylen);
-int prism2_sta_deauth(local_info_t *local, u16 reason);
-int prism2_wds_add(local_info_t *local, u8 *remote_addr,
-		   int rtnl_locked);
-int prism2_wds_del(local_info_t *local, u8 *remote_addr,
-		   int rtnl_locked, int do_not_remove);
-
-
-/* hostap_ap.c */
-
-int ap_control_add_mac(struct mac_restrictions *mac_restrictions, u8 *mac);
-int ap_control_del_mac(struct mac_restrictions *mac_restrictions, u8 *mac);
-void ap_control_flush_macs(struct mac_restrictions *mac_restrictions);
-int ap_control_kick_mac(struct ap_data *ap, struct net_device *dev, u8 *mac);
-void ap_control_kickall(struct ap_data *ap);
-void * ap_crypt_get_ptrs(struct ap_data *ap, u8 *addr, int permanent,
-			 struct lib80211_crypt_data ***crypt);
-int prism2_ap_get_sta_qual(local_info_t *local, struct sockaddr addr[],
-			   struct iw_quality qual[], int buf_size,
-			   int aplist);
-int prism2_ap_translate_scan(struct net_device *dev,
-			     struct iw_request_info *info, char *buffer);
-int prism2_hostapd(struct ap_data *ap, struct prism2_hostapd_param *param);
-
-
-/* hostap_proc.c */
-
-void hostap_init_proc(local_info_t *local);
-void hostap_remove_proc(local_info_t *local);
-
-
-/* hostap_info.c */
-
-void hostap_info_init(local_info_t *local);
-void hostap_info_process(local_info_t *local, struct sk_buff *skb);
-
-
-/* hostap_ioctl.c */
-
-extern const struct iw_handler_def hostap_iw_handler_def;
-extern const struct ethtool_ops prism2_ethtool_ops;
-
-int hostap_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
-			  void __user *data, int cmd);
-
-#endif /* HOSTAP_H */
diff --git a/drivers/net/wireless/intersil/hostap/hostap_80211.h b/drivers/net/wireless/intersil/hostap/hostap_80211.h
deleted file mode 100644
index 1452cf6ecb07..000000000000
--- a/drivers/net/wireless/intersil/hostap/hostap_80211.h
+++ /dev/null
@@ -1,97 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef HOSTAP_80211_H
-#define HOSTAP_80211_H
-
-#include <linux/types.h>
-#include <linux/skbuff.h>
-#include <linux/netdevice.h>
-
-struct hostap_ieee80211_mgmt {
-	__le16 frame_control;
-	__le16 duration;
-	u8 da[6];
-	u8 sa[6];
-	u8 bssid[6];
-	__le16 seq_ctrl;
-	union {
-		struct {
-			__le16 auth_alg;
-			__le16 auth_transaction;
-			__le16 status_code;
-			/* possibly followed by Challenge text */
-			u8 variable[0];
-		} __packed auth;
-		struct {
-			__le16 reason_code;
-		} __packed deauth;
-		struct {
-			__le16 capab_info;
-			__le16 listen_interval;
-			/* followed by SSID and Supported rates */
-			u8 variable[0];
-		} __packed assoc_req;
-		struct {
-			__le16 capab_info;
-			__le16 status_code;
-			__le16 aid;
-			/* followed by Supported rates */
-			u8 variable[0];
-		} __packed assoc_resp, reassoc_resp;
-		struct {
-			__le16 capab_info;
-			__le16 listen_interval;
-			u8 current_ap[6];
-			/* followed by SSID and Supported rates */
-			u8 variable[0];
-		} __packed reassoc_req;
-		struct {
-			__le16 reason_code;
-		} __packed disassoc;
-		struct {
-		} __packed probe_req;
-		struct {
-			u8 timestamp[8];
-			__le16 beacon_int;
-			__le16 capab_info;
-			/* followed by some of SSID, Supported rates,
-			 * FH Params, DS Params, CF Params, IBSS Params, TIM */
-			u8 variable[0];
-		} __packed beacon, probe_resp;
-	} u;
-} __packed;
-
-
-#define IEEE80211_MGMT_HDR_LEN 24
-#define IEEE80211_DATA_HDR3_LEN 24
-#define IEEE80211_DATA_HDR4_LEN 30
-
-
-struct hostap_80211_rx_status {
-	u32 mac_time;
-	u8 signal;
-	u8 noise;
-	u16 rate; /* in 100 kbps */
-};
-
-/* prism2_rx_80211 'type' argument */
-enum {
-	PRISM2_RX_MONITOR, PRISM2_RX_MGMT, PRISM2_RX_NON_ASSOC,
-	PRISM2_RX_NULLFUNC_ACK
-};
-
-int prism2_rx_80211(struct net_device *dev, struct sk_buff *skb,
-		    struct hostap_80211_rx_status *rx_stats, int type);
-void hostap_80211_rx(struct net_device *dev, struct sk_buff *skb,
-		     struct hostap_80211_rx_status *rx_stats);
-void hostap_dump_rx_80211(const char *name, struct sk_buff *skb,
-			  struct hostap_80211_rx_status *rx_stats);
-
-void hostap_dump_tx_80211(const char *name, struct sk_buff *skb);
-netdev_tx_t hostap_data_start_xmit(struct sk_buff *skb,
-				   struct net_device *dev);
-netdev_tx_t hostap_mgmt_start_xmit(struct sk_buff *skb,
-				   struct net_device *dev);
-netdev_tx_t hostap_master_start_xmit(struct sk_buff *skb,
-				     struct net_device *dev);
-
-#endif /* HOSTAP_80211_H */
diff --git a/drivers/net/wireless/intersil/hostap/hostap_80211_rx.c b/drivers/net/wireless/intersil/hostap/hostap_80211_rx.c
deleted file mode 100644
index 61be822f90b5..000000000000
--- a/drivers/net/wireless/intersil/hostap/hostap_80211_rx.c
+++ /dev/null
@@ -1,1116 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/etherdevice.h>
-#include <linux/slab.h>
-#include <linux/export.h>
-#include <net/lib80211.h>
-#include <linux/if_arp.h>
-
-#include "hostap_80211.h"
-#include "hostap.h"
-#include "hostap_ap.h"
-
-/* See IEEE 802.1H for LLC/SNAP encapsulation/decapsulation */
-/* Ethernet-II snap header (RFC1042 for most EtherTypes) */
-static unsigned char rfc1042_header[] =
-{ 0xaa, 0xaa, 0x03, 0x00, 0x00, 0x00 };
-/* Bridge-Tunnel header (for EtherTypes ETH_P_AARP and ETH_P_IPX) */
-static unsigned char bridge_tunnel_header[] =
-{ 0xaa, 0xaa, 0x03, 0x00, 0x00, 0xf8 };
-/* No encapsulation header if EtherType < 0x600 (=length) */
-
-void hostap_dump_rx_80211(const char *name, struct sk_buff *skb,
-			  struct hostap_80211_rx_status *rx_stats)
-{
-	struct ieee80211_hdr *hdr;
-	u16 fc;
-
-	hdr = (struct ieee80211_hdr *) skb->data;
-
-	printk(KERN_DEBUG "%s: RX signal=%d noise=%d rate=%d len=%d "
-	       "jiffies=%ld\n",
-	       name, rx_stats->signal, rx_stats->noise, rx_stats->rate,
-	       skb->len, jiffies);
-
-	if (skb->len < 2)
-		return;
-
-	fc = le16_to_cpu(hdr->frame_control);
-	printk(KERN_DEBUG "   FC=0x%04x (type=%d:%d)%s%s",
-	       fc, (fc & IEEE80211_FCTL_FTYPE) >> 2,
-	       (fc & IEEE80211_FCTL_STYPE) >> 4,
-	       fc & IEEE80211_FCTL_TODS ? " [ToDS]" : "",
-	       fc & IEEE80211_FCTL_FROMDS ? " [FromDS]" : "");
-
-	if (skb->len < IEEE80211_DATA_HDR3_LEN) {
-		printk("\n");
-		return;
-	}
-
-	printk(" dur=0x%04x seq=0x%04x\n", le16_to_cpu(hdr->duration_id),
-	       le16_to_cpu(hdr->seq_ctrl));
-
-	printk(KERN_DEBUG "   A1=%pM", hdr->addr1);
-	printk(" A2=%pM", hdr->addr2);
-	printk(" A3=%pM", hdr->addr3);
-	if (skb->len >= 30)
-		printk(" A4=%pM", hdr->addr4);
-	printk("\n");
-}
-
-
-/* Send RX frame to netif with 802.11 (and possible prism) header.
- * Called from hardware or software IRQ context. */
-int prism2_rx_80211(struct net_device *dev, struct sk_buff *skb,
-		    struct hostap_80211_rx_status *rx_stats, int type)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int hdrlen, phdrlen, head_need, tail_need;
-	u16 fc;
-	int prism_header, ret;
-	struct ieee80211_hdr *fhdr;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (dev->type == ARPHRD_IEEE80211_PRISM) {
-		if (local->monitor_type == PRISM2_MONITOR_PRISM) {
-			prism_header = 1;
-			phdrlen = sizeof(struct linux_wlan_ng_prism_hdr);
-		} else { /* local->monitor_type == PRISM2_MONITOR_CAPHDR */
-			prism_header = 2;
-			phdrlen = sizeof(struct linux_wlan_ng_cap_hdr);
-		}
-	} else if (dev->type == ARPHRD_IEEE80211_RADIOTAP) {
-		prism_header = 3;
-		phdrlen = sizeof(struct hostap_radiotap_rx);
-	} else {
-		prism_header = 0;
-		phdrlen = 0;
-	}
-
-	fhdr = (struct ieee80211_hdr *) skb->data;
-	fc = le16_to_cpu(fhdr->frame_control);
-
-	if (type == PRISM2_RX_MGMT && (fc & IEEE80211_FCTL_VERS)) {
-		printk(KERN_DEBUG "%s: dropped management frame with header "
-		       "version %d\n", dev->name, fc & IEEE80211_FCTL_VERS);
-		dev_kfree_skb_any(skb);
-		return 0;
-	}
-
-	hdrlen = hostap_80211_get_hdrlen(fhdr->frame_control);
-
-	/* check if there is enough room for extra data; if not, expand skb
-	 * buffer to be large enough for the changes */
-	head_need = phdrlen;
-	tail_need = 0;
-#ifdef PRISM2_ADD_BOGUS_CRC
-	tail_need += 4;
-#endif /* PRISM2_ADD_BOGUS_CRC */
-
-	head_need -= skb_headroom(skb);
-	tail_need -= skb_tailroom(skb);
-
-	if (head_need > 0 || tail_need > 0) {
-		if (pskb_expand_head(skb, head_need > 0 ? head_need : 0,
-				     tail_need > 0 ? tail_need : 0,
-				     GFP_ATOMIC)) {
-			printk(KERN_DEBUG "%s: prism2_rx_80211 failed to "
-			       "reallocate skb buffer\n", dev->name);
-			dev_kfree_skb_any(skb);
-			return 0;
-		}
-	}
-
-	/* We now have an skb with enough head and tail room, so just insert
-	 * the extra data */
-
-#ifdef PRISM2_ADD_BOGUS_CRC
-	memset(skb_put(skb, 4), 0xff, 4); /* Prism2 strips CRC */
-#endif /* PRISM2_ADD_BOGUS_CRC */
-
-	if (prism_header == 1) {
-		struct linux_wlan_ng_prism_hdr *hdr;
-		hdr = skb_push(skb, phdrlen);
-		memset(hdr, 0, phdrlen);
-		hdr->msgcode = LWNG_CAP_DID_BASE;
-		hdr->msglen = sizeof(*hdr);
-		memcpy(hdr->devname, dev->name, sizeof(hdr->devname));
-#define LWNG_SETVAL(f,i,s,l,d) \
-hdr->f.did = LWNG_CAP_DID_BASE | (i << 12); \
-hdr->f.status = s; hdr->f.len = l; hdr->f.data = d
-		LWNG_SETVAL(hosttime, 1, 0, 4, jiffies);
-		LWNG_SETVAL(mactime, 2, 0, 4, rx_stats->mac_time);
-		LWNG_SETVAL(channel, 3, 1 /* no value */, 4, 0);
-		LWNG_SETVAL(rssi, 4, 1 /* no value */, 4, 0);
-		LWNG_SETVAL(sq, 5, 1 /* no value */, 4, 0);
-		LWNG_SETVAL(signal, 6, 0, 4, rx_stats->signal);
-		LWNG_SETVAL(noise, 7, 0, 4, rx_stats->noise);
-		LWNG_SETVAL(rate, 8, 0, 4, rx_stats->rate / 5);
-		LWNG_SETVAL(istx, 9, 0, 4, 0);
-		LWNG_SETVAL(frmlen, 10, 0, 4, skb->len - phdrlen);
-#undef LWNG_SETVAL
-	} else if (prism_header == 2) {
-		struct linux_wlan_ng_cap_hdr *hdr;
-		hdr = skb_push(skb, phdrlen);
-		memset(hdr, 0, phdrlen);
-		hdr->version    = htonl(LWNG_CAPHDR_VERSION);
-		hdr->length     = htonl(phdrlen);
-		hdr->mactime    = __cpu_to_be64(rx_stats->mac_time);
-		hdr->hosttime   = __cpu_to_be64(jiffies);
-		hdr->phytype    = htonl(4); /* dss_dot11_b */
-		hdr->channel    = htonl(local->channel);
-		hdr->datarate   = htonl(rx_stats->rate);
-		hdr->antenna    = htonl(0); /* unknown */
-		hdr->priority   = htonl(0); /* unknown */
-		hdr->ssi_type   = htonl(3); /* raw */
-		hdr->ssi_signal = htonl(rx_stats->signal);
-		hdr->ssi_noise  = htonl(rx_stats->noise);
-		hdr->preamble   = htonl(0); /* unknown */
-		hdr->encoding   = htonl(1); /* cck */
-	} else if (prism_header == 3) {
-		struct hostap_radiotap_rx *hdr;
-		hdr = skb_push(skb, phdrlen);
-		memset(hdr, 0, phdrlen);
-		hdr->hdr.it_len = cpu_to_le16(phdrlen);
-		hdr->hdr.it_present =
-			cpu_to_le32((1 << IEEE80211_RADIOTAP_TSFT) |
-				    (1 << IEEE80211_RADIOTAP_CHANNEL) |
-				    (1 << IEEE80211_RADIOTAP_RATE) |
-				    (1 << IEEE80211_RADIOTAP_DBM_ANTSIGNAL) |
-				    (1 << IEEE80211_RADIOTAP_DBM_ANTNOISE));
-		hdr->tsft = cpu_to_le64(rx_stats->mac_time);
-		hdr->chan_freq = cpu_to_le16(freq_list[local->channel - 1]);
-		hdr->chan_flags = cpu_to_le16(IEEE80211_CHAN_CCK |
-						 IEEE80211_CHAN_2GHZ);
-		hdr->rate = rx_stats->rate / 5;
-		hdr->dbm_antsignal = rx_stats->signal;
-		hdr->dbm_antnoise = rx_stats->noise;
-	}
-
-	ret = skb->len - phdrlen;
-	skb->dev = dev;
-	skb_reset_mac_header(skb);
-	skb_pull(skb, hdrlen);
-	if (prism_header)
-		skb_pull(skb, phdrlen);
-	skb->pkt_type = PACKET_OTHERHOST;
-	skb->protocol = cpu_to_be16(ETH_P_802_2);
-	memset(skb->cb, 0, sizeof(skb->cb));
-	netif_rx(skb);
-
-	return ret;
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static void monitor_rx(struct net_device *dev, struct sk_buff *skb,
-		       struct hostap_80211_rx_status *rx_stats)
-{
-	int len;
-
-	len = prism2_rx_80211(dev, skb, rx_stats, PRISM2_RX_MONITOR);
-	dev->stats.rx_packets++;
-	dev->stats.rx_bytes += len;
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static struct prism2_frag_entry *
-prism2_frag_cache_find(local_info_t *local, unsigned int seq,
-		       unsigned int frag, u8 *src, u8 *dst)
-{
-	struct prism2_frag_entry *entry;
-	int i;
-
-	for (i = 0; i < PRISM2_FRAG_CACHE_LEN; i++) {
-		entry = &local->frag_cache[i];
-		if (entry->skb != NULL &&
-		    time_after(jiffies, entry->first_frag_time + 2 * HZ)) {
-			printk(KERN_DEBUG "%s: expiring fragment cache entry "
-			       "seq=%u last_frag=%u\n",
-			       local->dev->name, entry->seq, entry->last_frag);
-			dev_kfree_skb(entry->skb);
-			entry->skb = NULL;
-		}
-
-		if (entry->skb != NULL && entry->seq == seq &&
-		    (entry->last_frag + 1 == frag || frag == -1) &&
-		    memcmp(entry->src_addr, src, ETH_ALEN) == 0 &&
-		    memcmp(entry->dst_addr, dst, ETH_ALEN) == 0)
-			return entry;
-	}
-
-	return NULL;
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static struct sk_buff *
-prism2_frag_cache_get(local_info_t *local, struct ieee80211_hdr *hdr)
-{
-	struct sk_buff *skb = NULL;
-	u16 sc;
-	unsigned int frag, seq;
-	struct prism2_frag_entry *entry;
-
-	sc = le16_to_cpu(hdr->seq_ctrl);
-	frag = sc & IEEE80211_SCTL_FRAG;
-	seq = (sc & IEEE80211_SCTL_SEQ) >> 4;
-
-	if (frag == 0) {
-		/* Reserve enough space to fit maximum frame length */
-		skb = dev_alloc_skb(local->dev->mtu +
-				    sizeof(struct ieee80211_hdr) +
-				    8 /* LLC */ +
-				    2 /* alignment */ +
-				    8 /* WEP */ + ETH_ALEN /* WDS */);
-		if (skb == NULL)
-			return NULL;
-
-		entry = &local->frag_cache[local->frag_next_idx];
-		local->frag_next_idx++;
-		if (local->frag_next_idx >= PRISM2_FRAG_CACHE_LEN)
-			local->frag_next_idx = 0;
-
-		if (entry->skb != NULL)
-			dev_kfree_skb(entry->skb);
-
-		entry->first_frag_time = jiffies;
-		entry->seq = seq;
-		entry->last_frag = frag;
-		entry->skb = skb;
-		memcpy(entry->src_addr, hdr->addr2, ETH_ALEN);
-		memcpy(entry->dst_addr, hdr->addr1, ETH_ALEN);
-	} else {
-		/* received a fragment of a frame for which the head fragment
-		 * should have already been received */
-		entry = prism2_frag_cache_find(local, seq, frag, hdr->addr2,
-					       hdr->addr1);
-		if (entry != NULL) {
-			entry->last_frag = frag;
-			skb = entry->skb;
-		}
-	}
-
-	return skb;
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static int prism2_frag_cache_invalidate(local_info_t *local,
-					struct ieee80211_hdr *hdr)
-{
-	u16 sc;
-	unsigned int seq;
-	struct prism2_frag_entry *entry;
-
-	sc = le16_to_cpu(hdr->seq_ctrl);
-	seq = (sc & IEEE80211_SCTL_SEQ) >> 4;
-
-	entry = prism2_frag_cache_find(local, seq, -1, hdr->addr2, hdr->addr1);
-
-	if (entry == NULL) {
-		printk(KERN_DEBUG "%s: could not invalidate fragment cache "
-		       "entry (seq=%u)\n",
-		       local->dev->name, seq);
-		return -1;
-	}
-
-	entry->skb = NULL;
-	return 0;
-}
-
-
-static struct hostap_bss_info *__hostap_get_bss(local_info_t *local, u8 *bssid,
-						u8 *ssid, size_t ssid_len)
-{
-	struct list_head *ptr;
-	struct hostap_bss_info *bss;
-
-	list_for_each(ptr, &local->bss_list) {
-		bss = list_entry(ptr, struct hostap_bss_info, list);
-		if (memcmp(bss->bssid, bssid, ETH_ALEN) == 0 &&
-		    (ssid == NULL ||
-		     (ssid_len == bss->ssid_len &&
-		      memcmp(ssid, bss->ssid, ssid_len) == 0))) {
-			list_move(&bss->list, &local->bss_list);
-			return bss;
-		}
-	}
-
-	return NULL;
-}
-
-
-static struct hostap_bss_info *__hostap_add_bss(local_info_t *local, u8 *bssid,
-						u8 *ssid, size_t ssid_len)
-{
-	struct hostap_bss_info *bss;
-
-	if (local->num_bss_info >= HOSTAP_MAX_BSS_COUNT) {
-		bss = list_entry(local->bss_list.prev,
-				 struct hostap_bss_info, list);
-		list_del(&bss->list);
-		local->num_bss_info--;
-	} else {
-		bss = kmalloc(sizeof(*bss), GFP_ATOMIC);
-		if (bss == NULL)
-			return NULL;
-	}
-
-	memset(bss, 0, sizeof(*bss));
-	memcpy(bss->bssid, bssid, ETH_ALEN);
-	memcpy(bss->ssid, ssid, ssid_len);
-	bss->ssid_len = ssid_len;
-	local->num_bss_info++;
-	list_add(&bss->list, &local->bss_list);
-	return bss;
-}
-
-
-static void __hostap_expire_bss(local_info_t *local)
-{
-	struct hostap_bss_info *bss;
-
-	while (local->num_bss_info > 0) {
-		bss = list_entry(local->bss_list.prev,
-				 struct hostap_bss_info, list);
-		if (!time_after(jiffies, bss->last_update + 60 * HZ))
-			break;
-
-		list_del(&bss->list);
-		local->num_bss_info--;
-		kfree(bss);
-	}
-}
-
-
-/* Both IEEE 802.11 Beacon and Probe Response frames have similar structure, so
- * the same routine can be used to parse both of them. */
-static void hostap_rx_sta_beacon(local_info_t *local, struct sk_buff *skb,
-				 int stype)
-{
-	struct hostap_ieee80211_mgmt *mgmt;
-	int left, chan = 0;
-	u8 *pos;
-	u8 *ssid = NULL, *wpa = NULL, *rsn = NULL;
-	size_t ssid_len = 0, wpa_len = 0, rsn_len = 0;
-	struct hostap_bss_info *bss;
-
-	if (skb->len < IEEE80211_MGMT_HDR_LEN + sizeof(mgmt->u.beacon))
-		return;
-
-	mgmt = (struct hostap_ieee80211_mgmt *) skb->data;
-	pos = mgmt->u.beacon.variable;
-	left = skb->len - (pos - skb->data);
-
-	while (left >= 2) {
-		if (2 + pos[1] > left)
-			return; /* parse failed */
-		switch (*pos) {
-		case WLAN_EID_SSID:
-			ssid = pos + 2;
-			ssid_len = pos[1];
-			break;
-		case WLAN_EID_VENDOR_SPECIFIC:
-			if (pos[1] >= 4 &&
-			    pos[2] == 0x00 && pos[3] == 0x50 &&
-			    pos[4] == 0xf2 && pos[5] == 1) {
-				wpa = pos;
-				wpa_len = pos[1] + 2;
-			}
-			break;
-		case WLAN_EID_RSN:
-			rsn = pos;
-			rsn_len = pos[1] + 2;
-			break;
-		case WLAN_EID_DS_PARAMS:
-			if (pos[1] >= 1)
-				chan = pos[2];
-			break;
-		}
-		left -= 2 + pos[1];
-		pos += 2 + pos[1];
-	}
-
-	if (wpa_len > MAX_WPA_IE_LEN)
-		wpa_len = MAX_WPA_IE_LEN;
-	if (rsn_len > MAX_WPA_IE_LEN)
-		rsn_len = MAX_WPA_IE_LEN;
-	if (ssid_len > sizeof(bss->ssid))
-		ssid_len = sizeof(bss->ssid);
-
-	spin_lock(&local->lock);
-	bss = __hostap_get_bss(local, mgmt->bssid, ssid, ssid_len);
-	if (bss == NULL)
-		bss = __hostap_add_bss(local, mgmt->bssid, ssid, ssid_len);
-	if (bss) {
-		bss->last_update = jiffies;
-		bss->count++;
-		bss->capab_info = le16_to_cpu(mgmt->u.beacon.capab_info);
-		if (wpa) {
-			memcpy(bss->wpa_ie, wpa, wpa_len);
-			bss->wpa_ie_len = wpa_len;
-		} else
-			bss->wpa_ie_len = 0;
-		if (rsn) {
-			memcpy(bss->rsn_ie, rsn, rsn_len);
-			bss->rsn_ie_len = rsn_len;
-		} else
-			bss->rsn_ie_len = 0;
-		bss->chan = chan;
-	}
-	__hostap_expire_bss(local);
-	spin_unlock(&local->lock);
-}
-
-
-static int
-hostap_rx_frame_mgmt(local_info_t *local, struct sk_buff *skb,
-		     struct hostap_80211_rx_status *rx_stats, u16 type,
-		     u16 stype)
-{
-	if (local->iw_mode == IW_MODE_MASTER)
-		hostap_update_sta_ps(local, (struct ieee80211_hdr *) skb->data);
-
-	if (local->hostapd && type == IEEE80211_FTYPE_MGMT) {
-		if (stype == IEEE80211_STYPE_BEACON &&
-		    local->iw_mode == IW_MODE_MASTER) {
-			struct sk_buff *skb2;
-			/* Process beacon frames also in kernel driver to
-			 * update STA(AP) table statistics */
-			skb2 = skb_clone(skb, GFP_ATOMIC);
-			if (skb2)
-				hostap_rx(skb2->dev, skb2, rx_stats);
-		}
-
-		/* send management frames to the user space daemon for
-		 * processing */
-		local->apdevstats.rx_packets++;
-		local->apdevstats.rx_bytes += skb->len;
-		if (local->apdev == NULL)
-			return -1;
-		prism2_rx_80211(local->apdev, skb, rx_stats, PRISM2_RX_MGMT);
-		return 0;
-	}
-
-	if (local->iw_mode == IW_MODE_MASTER) {
-		if (type != IEEE80211_FTYPE_MGMT &&
-		    type != IEEE80211_FTYPE_CTL) {
-			printk(KERN_DEBUG "%s: unknown management frame "
-			       "(type=0x%02x, stype=0x%02x) dropped\n",
-			       skb->dev->name, type >> 2, stype >> 4);
-			return -1;
-		}
-
-		hostap_rx(skb->dev, skb, rx_stats);
-		return 0;
-	} else if (type == IEEE80211_FTYPE_MGMT &&
-		   (stype == IEEE80211_STYPE_BEACON ||
-		    stype == IEEE80211_STYPE_PROBE_RESP)) {
-		hostap_rx_sta_beacon(local, skb, stype);
-		return -1;
-	} else if (type == IEEE80211_FTYPE_MGMT &&
-		   (stype == IEEE80211_STYPE_ASSOC_RESP ||
-		    stype == IEEE80211_STYPE_REASSOC_RESP)) {
-		/* Ignore (Re)AssocResp silently since these are not currently
-		 * needed but are still received when WPA/RSN mode is enabled.
-		 */
-		return -1;
-	} else {
-		printk(KERN_DEBUG "%s: hostap_rx_frame_mgmt: dropped unhandled"
-		       " management frame in non-Host AP mode (type=%d:%d)\n",
-		       skb->dev->name, type >> 2, stype >> 4);
-		return -1;
-	}
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static struct net_device *prism2_rx_get_wds(local_info_t *local,
-						   u8 *addr)
-{
-	struct hostap_interface *iface = NULL;
-	struct list_head *ptr;
-
-	read_lock_bh(&local->iface_lock);
-	list_for_each(ptr, &local->hostap_interfaces) {
-		iface = list_entry(ptr, struct hostap_interface, list);
-		if (iface->type == HOSTAP_INTERFACE_WDS &&
-		    memcmp(iface->u.wds.remote_addr, addr, ETH_ALEN) == 0)
-			break;
-		iface = NULL;
-	}
-	read_unlock_bh(&local->iface_lock);
-
-	return iface ? iface->dev : NULL;
-}
-
-
-static int
-hostap_rx_frame_wds(local_info_t *local, struct ieee80211_hdr *hdr, u16 fc,
-		    struct net_device **wds)
-{
-	/* FIX: is this really supposed to accept WDS frames only in Master
-	 * mode? What about Repeater or Managed with WDS frames? */
-	if ((fc & (IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS)) !=
-	    (IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS) &&
-	    (local->iw_mode != IW_MODE_MASTER || !(fc & IEEE80211_FCTL_TODS)))
-		return 0; /* not a WDS frame */
-
-	/* Possible WDS frame: either IEEE 802.11 compliant (if FromDS)
-	 * or own non-standard frame with 4th address after payload */
-	if (!ether_addr_equal(hdr->addr1, local->dev->dev_addr) &&
-	    (hdr->addr1[0] != 0xff || hdr->addr1[1] != 0xff ||
-	     hdr->addr1[2] != 0xff || hdr->addr1[3] != 0xff ||
-	     hdr->addr1[4] != 0xff || hdr->addr1[5] != 0xff)) {
-		/* RA (or BSSID) is not ours - drop */
-		PDEBUG(DEBUG_EXTRA2, "%s: received WDS frame with "
-		       "not own or broadcast %s=%pM\n",
-		       local->dev->name,
-		       fc & IEEE80211_FCTL_FROMDS ? "RA" : "BSSID",
-		       hdr->addr1);
-		return -1;
-	}
-
-	/* check if the frame came from a registered WDS connection */
-	*wds = prism2_rx_get_wds(local, hdr->addr2);
-	if (*wds == NULL && fc & IEEE80211_FCTL_FROMDS &&
-	    (local->iw_mode != IW_MODE_INFRA ||
-	     !(local->wds_type & HOSTAP_WDS_AP_CLIENT) ||
-	     memcmp(hdr->addr2, local->bssid, ETH_ALEN) != 0)) {
-		/* require that WDS link has been registered with TA or the
-		 * frame is from current AP when using 'AP client mode' */
-		PDEBUG(DEBUG_EXTRA, "%s: received WDS[4 addr] frame "
-		       "from unknown TA=%pM\n",
-		       local->dev->name, hdr->addr2);
-		if (local->ap && local->ap->autom_ap_wds)
-			hostap_wds_link_oper(local, hdr->addr2, WDS_ADD);
-		return -1;
-	}
-
-	if (*wds && !(fc & IEEE80211_FCTL_FROMDS) && local->ap &&
-	    hostap_is_sta_assoc(local->ap, hdr->addr2)) {
-		/* STA is actually associated with us even though it has a
-		 * registered WDS link. Assume it is in 'AP client' mode.
-		 * Since this is a 3-addr frame, assume it is not (bogus) WDS
-		 * frame and process it like any normal ToDS frame from
-		 * associated STA. */
-		*wds = NULL;
-	}
-
-	return 0;
-}
-
-
-static int hostap_is_eapol_frame(local_info_t *local, struct sk_buff *skb)
-{
-	struct net_device *dev = local->dev;
-	u16 fc, ethertype;
-	struct ieee80211_hdr *hdr;
-	u8 *pos;
-
-	if (skb->len < 24)
-		return 0;
-
-	hdr = (struct ieee80211_hdr *) skb->data;
-	fc = le16_to_cpu(hdr->frame_control);
-
-	/* check that the frame is unicast frame to us */
-	if ((fc & (IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS)) ==
-	    IEEE80211_FCTL_TODS &&
-	    ether_addr_equal(hdr->addr1, dev->dev_addr) &&
-	    ether_addr_equal(hdr->addr3, dev->dev_addr)) {
-		/* ToDS frame with own addr BSSID and DA */
-	} else if ((fc & (IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS)) ==
-		   IEEE80211_FCTL_FROMDS &&
-		   ether_addr_equal(hdr->addr1, dev->dev_addr)) {
-		/* FromDS frame with own addr as DA */
-	} else
-		return 0;
-
-	if (skb->len < 24 + 8)
-		return 0;
-
-	/* check for port access entity Ethernet type */
-	pos = skb->data + 24;
-	ethertype = (pos[6] << 8) | pos[7];
-	if (ethertype == ETH_P_PAE)
-		return 1;
-
-	return 0;
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static int
-hostap_rx_frame_decrypt(local_info_t *local, struct sk_buff *skb,
-			struct lib80211_crypt_data *crypt)
-{
-	struct ieee80211_hdr *hdr;
-	int res, hdrlen;
-
-	if (crypt == NULL || crypt->ops->decrypt_mpdu == NULL)
-		return 0;
-
-	hdr = (struct ieee80211_hdr *) skb->data;
-	hdrlen = hostap_80211_get_hdrlen(hdr->frame_control);
-
-	if (local->tkip_countermeasures &&
-	    strcmp(crypt->ops->name, "TKIP") == 0) {
-		if (net_ratelimit()) {
-			printk(KERN_DEBUG "%s: TKIP countermeasures: dropped "
-			       "received packet from %pM\n",
-			       local->dev->name, hdr->addr2);
-		}
-		return -1;
-	}
-
-	atomic_inc(&crypt->refcnt);
-	res = crypt->ops->decrypt_mpdu(skb, hdrlen, crypt->priv);
-	atomic_dec(&crypt->refcnt);
-	if (res < 0) {
-		printk(KERN_DEBUG "%s: decryption failed (SA=%pM) res=%d\n",
-		       local->dev->name, hdr->addr2, res);
-		local->comm_tallies.rx_discards_wep_undecryptable++;
-		return -1;
-	}
-
-	return res;
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static int
-hostap_rx_frame_decrypt_msdu(local_info_t *local, struct sk_buff *skb,
-			     int keyidx, struct lib80211_crypt_data *crypt)
-{
-	struct ieee80211_hdr *hdr;
-	int res, hdrlen;
-
-	if (crypt == NULL || crypt->ops->decrypt_msdu == NULL)
-		return 0;
-
-	hdr = (struct ieee80211_hdr *) skb->data;
-	hdrlen = hostap_80211_get_hdrlen(hdr->frame_control);
-
-	atomic_inc(&crypt->refcnt);
-	res = crypt->ops->decrypt_msdu(skb, keyidx, hdrlen, crypt->priv);
-	atomic_dec(&crypt->refcnt);
-	if (res < 0) {
-		printk(KERN_DEBUG "%s: MSDU decryption/MIC verification failed"
-		       " (SA=%pM keyidx=%d)\n",
-		       local->dev->name, hdr->addr2, keyidx);
-		return -1;
-	}
-
-	return 0;
-}
-
-
-/* All received frames are sent to this function. @skb contains the frame in
- * IEEE 802.11 format, i.e., in the format it was sent over air.
- * This function is called only as a tasklet (software IRQ). */
-void hostap_80211_rx(struct net_device *dev, struct sk_buff *skb,
-		     struct hostap_80211_rx_status *rx_stats)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	struct ieee80211_hdr *hdr;
-	size_t hdrlen;
-	u16 fc, type, stype, sc;
-	struct net_device *wds = NULL;
-	unsigned int frag;
-	u8 *payload;
-	struct sk_buff *skb2 = NULL;
-	u16 ethertype;
-	int frame_authorized = 0;
-	int from_assoc_ap = 0;
-	u8 dst[ETH_ALEN];
-	u8 src[ETH_ALEN];
-	struct lib80211_crypt_data *crypt = NULL;
-	void *sta = NULL;
-	int keyidx = 0;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-	iface->stats.rx_packets++;
-	iface->stats.rx_bytes += skb->len;
-
-	/* dev is the master radio device; change this to be the default
-	 * virtual interface (this may be changed to WDS device below) */
-	dev = local->ddev;
-	iface = netdev_priv(dev);
-
-	hdr = (struct ieee80211_hdr *) skb->data;
-
-	if (skb->len < 10)
-		goto rx_dropped;
-
-	fc = le16_to_cpu(hdr->frame_control);
-	type = fc & IEEE80211_FCTL_FTYPE;
-	stype = fc & IEEE80211_FCTL_STYPE;
-	sc = le16_to_cpu(hdr->seq_ctrl);
-	frag = sc & IEEE80211_SCTL_FRAG;
-	hdrlen = hostap_80211_get_hdrlen(hdr->frame_control);
-
-	/* Put this code here so that we avoid duplicating it in all
-	 * Rx paths. - Jean II */
-#ifdef IW_WIRELESS_SPY		/* defined in iw_handler.h */
-	/* If spy monitoring on */
-	if (iface->spy_data.spy_number > 0) {
-		struct iw_quality wstats;
-		wstats.level = rx_stats->signal;
-		wstats.noise = rx_stats->noise;
-		wstats.updated = IW_QUAL_LEVEL_UPDATED | IW_QUAL_NOISE_UPDATED
-			| IW_QUAL_QUAL_INVALID | IW_QUAL_DBM;
-		/* Update spy records */
-		wireless_spy_update(dev, hdr->addr2, &wstats);
-	}
-#endif /* IW_WIRELESS_SPY */
-	hostap_update_rx_stats(local->ap, hdr, rx_stats);
-
-	if (local->iw_mode == IW_MODE_MONITOR) {
-		monitor_rx(dev, skb, rx_stats);
-		return;
-	}
-
-	if (local->host_decrypt) {
-		int idx = 0;
-		if (skb->len >= hdrlen + 3)
-			idx = skb->data[hdrlen + 3] >> 6;
-		crypt = local->crypt_info.crypt[idx];
-		sta = NULL;
-
-		/* Use station specific key to override default keys if the
-		 * receiver address is a unicast address ("individual RA"). If
-		 * bcrx_sta_key parameter is set, station specific key is used
-		 * even with broad/multicast targets (this is against IEEE
-		 * 802.11, but makes it easier to use different keys with
-		 * stations that do not support WEP key mapping). */
-
-		if (!(hdr->addr1[0] & 0x01) || local->bcrx_sta_key)
-			(void) hostap_handle_sta_crypto(local, hdr, &crypt,
-							&sta);
-
-		/* allow NULL decrypt to indicate an station specific override
-		 * for default encryption */
-		if (crypt && (crypt->ops == NULL ||
-			      crypt->ops->decrypt_mpdu == NULL))
-			crypt = NULL;
-
-		if (!crypt && (fc & IEEE80211_FCTL_PROTECTED)) {
-#if 0
-			/* This seems to be triggered by some (multicast?)
-			 * frames from other than current BSS, so just drop the
-			 * frames silently instead of filling system log with
-			 * these reports. */
-			printk(KERN_DEBUG "%s: WEP decryption failed (not set)"
-			       " (SA=%pM)\n",
-			       local->dev->name, hdr->addr2);
-#endif
-			local->comm_tallies.rx_discards_wep_undecryptable++;
-			goto rx_dropped;
-		}
-	}
-
-	if (type != IEEE80211_FTYPE_DATA) {
-		if (type == IEEE80211_FTYPE_MGMT &&
-		    stype == IEEE80211_STYPE_AUTH &&
-		    fc & IEEE80211_FCTL_PROTECTED && local->host_decrypt &&
-		    (keyidx = hostap_rx_frame_decrypt(local, skb, crypt)) < 0)
-		{
-			printk(KERN_DEBUG "%s: failed to decrypt mgmt::auth "
-			       "from %pM\n", dev->name, hdr->addr2);
-			/* TODO: could inform hostapd about this so that it
-			 * could send auth failure report */
-			goto rx_dropped;
-		}
-
-		if (hostap_rx_frame_mgmt(local, skb, rx_stats, type, stype))
-			goto rx_dropped;
-		else
-			goto rx_exit;
-	}
-
-	/* Data frame - extract src/dst addresses */
-	if (skb->len < IEEE80211_DATA_HDR3_LEN)
-		goto rx_dropped;
-
-	switch (fc & (IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS)) {
-	case IEEE80211_FCTL_FROMDS:
-		memcpy(dst, hdr->addr1, ETH_ALEN);
-		memcpy(src, hdr->addr3, ETH_ALEN);
-		break;
-	case IEEE80211_FCTL_TODS:
-		memcpy(dst, hdr->addr3, ETH_ALEN);
-		memcpy(src, hdr->addr2, ETH_ALEN);
-		break;
-	case IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS:
-		if (skb->len < IEEE80211_DATA_HDR4_LEN)
-			goto rx_dropped;
-		memcpy(dst, hdr->addr3, ETH_ALEN);
-		memcpy(src, hdr->addr4, ETH_ALEN);
-		break;
-	default:
-		memcpy(dst, hdr->addr1, ETH_ALEN);
-		memcpy(src, hdr->addr2, ETH_ALEN);
-		break;
-	}
-
-	if (hostap_rx_frame_wds(local, hdr, fc, &wds))
-		goto rx_dropped;
-	if (wds)
-		skb->dev = dev = wds;
-
-	if (local->iw_mode == IW_MODE_MASTER && !wds &&
-	    (fc & (IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS)) ==
-	    IEEE80211_FCTL_FROMDS &&
-	    local->stadev &&
-	    memcmp(hdr->addr2, local->assoc_ap_addr, ETH_ALEN) == 0) {
-		/* Frame from BSSID of the AP for which we are a client */
-		skb->dev = dev = local->stadev;
-		from_assoc_ap = 1;
-	}
-
-	if ((local->iw_mode == IW_MODE_MASTER ||
-	     local->iw_mode == IW_MODE_REPEAT) &&
-	    !from_assoc_ap) {
-		switch (hostap_handle_sta_rx(local, dev, skb, rx_stats,
-					     wds != NULL)) {
-		case AP_RX_CONTINUE_NOT_AUTHORIZED:
-			frame_authorized = 0;
-			break;
-		case AP_RX_CONTINUE:
-			frame_authorized = 1;
-			break;
-		case AP_RX_DROP:
-			goto rx_dropped;
-		case AP_RX_EXIT:
-			goto rx_exit;
-		}
-	}
-
-	/* Nullfunc frames may have PS-bit set, so they must be passed to
-	 * hostap_handle_sta_rx() before being dropped here. */
-	if (stype != IEEE80211_STYPE_DATA &&
-	    stype != IEEE80211_STYPE_DATA_CFACK &&
-	    stype != IEEE80211_STYPE_DATA_CFPOLL &&
-	    stype != IEEE80211_STYPE_DATA_CFACKPOLL) {
-		if (stype != IEEE80211_STYPE_NULLFUNC)
-			printk(KERN_DEBUG "%s: RX: dropped data frame "
-			       "with no data (type=0x%02x, subtype=0x%02x)\n",
-			       dev->name, type >> 2, stype >> 4);
-		goto rx_dropped;
-	}
-
-	/* skb: hdr + (possibly fragmented, possibly encrypted) payload */
-
-	if (local->host_decrypt && (fc & IEEE80211_FCTL_PROTECTED) &&
-	    (keyidx = hostap_rx_frame_decrypt(local, skb, crypt)) < 0)
-		goto rx_dropped;
-	hdr = (struct ieee80211_hdr *) skb->data;
-
-	/* skb: hdr + (possibly fragmented) plaintext payload */
-
-	if (local->host_decrypt && (fc & IEEE80211_FCTL_PROTECTED) &&
-	    (frag != 0 || (fc & IEEE80211_FCTL_MOREFRAGS))) {
-		int flen;
-		struct sk_buff *frag_skb =
-			prism2_frag_cache_get(local, hdr);
-		if (!frag_skb) {
-			printk(KERN_DEBUG "%s: Rx cannot get skb from "
-			       "fragment cache (morefrag=%d seq=%u frag=%u)\n",
-			       dev->name, (fc & IEEE80211_FCTL_MOREFRAGS) != 0,
-			       (sc & IEEE80211_SCTL_SEQ) >> 4, frag);
-			goto rx_dropped;
-		}
-
-		flen = skb->len;
-		if (frag != 0)
-			flen -= hdrlen;
-
-		if (frag_skb->tail + flen > frag_skb->end) {
-			printk(KERN_WARNING "%s: host decrypted and "
-			       "reassembled frame did not fit skb\n",
-			       dev->name);
-			prism2_frag_cache_invalidate(local, hdr);
-			goto rx_dropped;
-		}
-
-		if (frag == 0) {
-			/* copy first fragment (including full headers) into
-			 * beginning of the fragment cache skb */
-			skb_copy_from_linear_data(skb, skb_put(frag_skb, flen),
-						  flen);
-		} else {
-			/* append frame payload to the end of the fragment
-			 * cache skb */
-			skb_copy_from_linear_data_offset(skb, hdrlen,
-							 skb_put(frag_skb,
-								 flen), flen);
-		}
-		dev_kfree_skb(skb);
-		skb = NULL;
-
-		if (fc & IEEE80211_FCTL_MOREFRAGS) {
-			/* more fragments expected - leave the skb in fragment
-			 * cache for now; it will be delivered to upper layers
-			 * after all fragments have been received */
-			goto rx_exit;
-		}
-
-		/* this was the last fragment and the frame will be
-		 * delivered, so remove skb from fragment cache */
-		skb = frag_skb;
-		hdr = (struct ieee80211_hdr *) skb->data;
-		prism2_frag_cache_invalidate(local, hdr);
-	}
-
-	/* skb: hdr + (possible reassembled) full MSDU payload; possibly still
-	 * encrypted/authenticated */
-
-	if (local->host_decrypt && (fc & IEEE80211_FCTL_PROTECTED) &&
-	    hostap_rx_frame_decrypt_msdu(local, skb, keyidx, crypt))
-		goto rx_dropped;
-
-	hdr = (struct ieee80211_hdr *) skb->data;
-	if (crypt && !(fc & IEEE80211_FCTL_PROTECTED) && !local->open_wep) {
-		if (local->ieee_802_1x &&
-		    hostap_is_eapol_frame(local, skb)) {
-			/* pass unencrypted EAPOL frames even if encryption is
-			 * configured */
-			PDEBUG(DEBUG_EXTRA2, "%s: RX: IEEE 802.1X - passing "
-			       "unencrypted EAPOL frame\n", local->dev->name);
-		} else {
-			printk(KERN_DEBUG "%s: encryption configured, but RX "
-			       "frame not encrypted (SA=%pM)\n",
-			       local->dev->name, hdr->addr2);
-			goto rx_dropped;
-		}
-	}
-
-	if (local->drop_unencrypted && !(fc & IEEE80211_FCTL_PROTECTED) &&
-	    !hostap_is_eapol_frame(local, skb)) {
-		if (net_ratelimit()) {
-			printk(KERN_DEBUG "%s: dropped unencrypted RX data "
-			       "frame from %pM (drop_unencrypted=1)\n",
-			       dev->name, hdr->addr2);
-		}
-		goto rx_dropped;
-	}
-
-	/* skb: hdr + (possible reassembled) full plaintext payload */
-
-	payload = skb->data + hdrlen;
-	ethertype = (payload[6] << 8) | payload[7];
-
-	/* If IEEE 802.1X is used, check whether the port is authorized to send
-	 * the received frame. */
-	if (local->ieee_802_1x && local->iw_mode == IW_MODE_MASTER) {
-		if (ethertype == ETH_P_PAE) {
-			PDEBUG(DEBUG_EXTRA2, "%s: RX: IEEE 802.1X frame\n",
-			       dev->name);
-			if (local->hostapd && local->apdev) {
-				/* Send IEEE 802.1X frames to the user
-				 * space daemon for processing */
-				prism2_rx_80211(local->apdev, skb, rx_stats,
-						PRISM2_RX_MGMT);
-				local->apdevstats.rx_packets++;
-				local->apdevstats.rx_bytes += skb->len;
-				goto rx_exit;
-			}
-		} else if (!frame_authorized) {
-			printk(KERN_DEBUG "%s: dropped frame from "
-			       "unauthorized port (IEEE 802.1X): "
-			       "ethertype=0x%04x\n",
-			       dev->name, ethertype);
-			goto rx_dropped;
-		}
-	}
-
-	/* convert hdr + possible LLC headers into Ethernet header */
-	if (skb->len - hdrlen >= 8 &&
-	    ((memcmp(payload, rfc1042_header, 6) == 0 &&
-	      ethertype != ETH_P_AARP && ethertype != ETH_P_IPX) ||
-	     memcmp(payload, bridge_tunnel_header, 6) == 0)) {
-		/* remove RFC1042 or Bridge-Tunnel encapsulation and
-		 * replace EtherType */
-		skb_pull(skb, hdrlen + 6);
-		memcpy(skb_push(skb, ETH_ALEN), src, ETH_ALEN);
-		memcpy(skb_push(skb, ETH_ALEN), dst, ETH_ALEN);
-	} else {
-		__be16 len;
-		/* Leave Ethernet header part of hdr and full payload */
-		skb_pull(skb, hdrlen);
-		len = htons(skb->len);
-		memcpy(skb_push(skb, 2), &len, 2);
-		memcpy(skb_push(skb, ETH_ALEN), src, ETH_ALEN);
-		memcpy(skb_push(skb, ETH_ALEN), dst, ETH_ALEN);
-	}
-
-	if (wds && ((fc & (IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS)) ==
-		    IEEE80211_FCTL_TODS) &&
-	    skb->len >= ETH_HLEN + ETH_ALEN) {
-		/* Non-standard frame: get addr4 from its bogus location after
-		 * the payload */
-		skb_copy_from_linear_data_offset(skb, skb->len - ETH_ALEN,
-						 skb->data + ETH_ALEN,
-						 ETH_ALEN);
-		skb_trim(skb, skb->len - ETH_ALEN);
-	}
-
-	dev->stats.rx_packets++;
-	dev->stats.rx_bytes += skb->len;
-
-	if (local->iw_mode == IW_MODE_MASTER && !wds &&
-	    local->ap->bridge_packets) {
-		if (dst[0] & 0x01) {
-			/* copy multicast frame both to the higher layers and
-			 * to the wireless media */
-			local->ap->bridged_multicast++;
-			skb2 = skb_clone(skb, GFP_ATOMIC);
-			if (skb2 == NULL)
-				printk(KERN_DEBUG "%s: skb_clone failed for "
-				       "multicast frame\n", dev->name);
-		} else if (hostap_is_sta_authorized(local->ap, dst)) {
-			/* send frame directly to the associated STA using
-			 * wireless media and not passing to higher layers */
-			local->ap->bridged_unicast++;
-			skb2 = skb;
-			skb = NULL;
-		}
-	}
-
-	if (skb2 != NULL) {
-		/* send to wireless media */
-		skb2->dev = dev;
-		skb2->protocol = cpu_to_be16(ETH_P_802_3);
-		skb_reset_mac_header(skb2);
-		skb_reset_network_header(skb2);
-		/* skb2->network_header += ETH_HLEN; */
-		dev_queue_xmit(skb2);
-	}
-
-	if (skb) {
-		skb->protocol = eth_type_trans(skb, dev);
-		memset(skb->cb, 0, sizeof(skb->cb));
-		netif_rx(skb);
-	}
-
- rx_exit:
-	if (sta)
-		hostap_handle_sta_release(sta);
-	return;
-
- rx_dropped:
-	dev_kfree_skb(skb);
-
-	dev->stats.rx_dropped++;
-	goto rx_exit;
-}
-
-
-EXPORT_SYMBOL(hostap_80211_rx);
diff --git a/drivers/net/wireless/intersil/hostap/hostap_80211_tx.c b/drivers/net/wireless/intersil/hostap/hostap_80211_tx.c
deleted file mode 100644
index c47da06945c2..000000000000
--- a/drivers/net/wireless/intersil/hostap/hostap_80211_tx.c
+++ /dev/null
@@ -1,554 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/slab.h>
-#include <linux/export.h>
-#include <linux/etherdevice.h>
-
-#include "hostap_80211.h"
-#include "hostap_common.h"
-#include "hostap_wlan.h"
-#include "hostap.h"
-#include "hostap_ap.h"
-
-/* See IEEE 802.1H for LLC/SNAP encapsulation/decapsulation */
-/* Ethernet-II snap header (RFC1042 for most EtherTypes) */
-static unsigned char rfc1042_header[] =
-{ 0xaa, 0xaa, 0x03, 0x00, 0x00, 0x00 };
-/* Bridge-Tunnel header (for EtherTypes ETH_P_AARP and ETH_P_IPX) */
-static unsigned char bridge_tunnel_header[] =
-{ 0xaa, 0xaa, 0x03, 0x00, 0x00, 0xf8 };
-/* No encapsulation header if EtherType < 0x600 (=length) */
-
-void hostap_dump_tx_80211(const char *name, struct sk_buff *skb)
-{
-	struct ieee80211_hdr *hdr;
-	u16 fc;
-
-	hdr = (struct ieee80211_hdr *) skb->data;
-
-	printk(KERN_DEBUG "%s: TX len=%d jiffies=%ld\n",
-	       name, skb->len, jiffies);
-
-	if (skb->len < 2)
-		return;
-
-	fc = le16_to_cpu(hdr->frame_control);
-	printk(KERN_DEBUG "   FC=0x%04x (type=%d:%d)%s%s",
-	       fc, (fc & IEEE80211_FCTL_FTYPE) >> 2,
-	       (fc & IEEE80211_FCTL_STYPE) >> 4,
-	       fc & IEEE80211_FCTL_TODS ? " [ToDS]" : "",
-	       fc & IEEE80211_FCTL_FROMDS ? " [FromDS]" : "");
-
-	if (skb->len < IEEE80211_DATA_HDR3_LEN) {
-		printk("\n");
-		return;
-	}
-
-	printk(" dur=0x%04x seq=0x%04x\n", le16_to_cpu(hdr->duration_id),
-	       le16_to_cpu(hdr->seq_ctrl));
-
-	printk(KERN_DEBUG "   A1=%pM", hdr->addr1);
-	printk(" A2=%pM", hdr->addr2);
-	printk(" A3=%pM", hdr->addr3);
-	if (skb->len >= 30)
-		printk(" A4=%pM", hdr->addr4);
-	printk("\n");
-}
-
-
-/* hard_start_xmit function for data interfaces (wlan#, wlan#wds#, wlan#sta)
- * Convert Ethernet header into a suitable IEEE 802.11 header depending on
- * device configuration. */
-netdev_tx_t hostap_data_start_xmit(struct sk_buff *skb,
-				   struct net_device *dev)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int need_headroom, need_tailroom = 0;
-	struct ieee80211_hdr hdr;
-	u16 fc, ethertype = 0;
-	enum {
-		WDS_NO = 0, WDS_OWN_FRAME, WDS_COMPLIANT_FRAME
-	} use_wds = WDS_NO;
-	u8 *encaps_data;
-	int hdr_len, encaps_len, skip_header_bytes;
-	int to_assoc_ap = 0;
-	struct hostap_skb_tx_data *meta;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (skb->len < ETH_HLEN) {
-		printk(KERN_DEBUG "%s: hostap_data_start_xmit: short skb "
-		       "(len=%d)\n", dev->name, skb->len);
-		kfree_skb(skb);
-		return NETDEV_TX_OK;
-	}
-
-	if (local->ddev != dev) {
-		use_wds = (local->iw_mode == IW_MODE_MASTER &&
-			   !(local->wds_type & HOSTAP_WDS_STANDARD_FRAME)) ?
-			WDS_OWN_FRAME : WDS_COMPLIANT_FRAME;
-		if (dev == local->stadev) {
-			to_assoc_ap = 1;
-			use_wds = WDS_NO;
-		} else if (dev == local->apdev) {
-			printk(KERN_DEBUG "%s: prism2_tx: trying to use "
-			       "AP device with Ethernet net dev\n", dev->name);
-			kfree_skb(skb);
-			return NETDEV_TX_OK;
-		}
-	} else {
-		if (local->iw_mode == IW_MODE_REPEAT) {
-			printk(KERN_DEBUG "%s: prism2_tx: trying to use "
-			       "non-WDS link in Repeater mode\n", dev->name);
-			kfree_skb(skb);
-			return NETDEV_TX_OK;
-		} else if (local->iw_mode == IW_MODE_INFRA &&
-			   (local->wds_type & HOSTAP_WDS_AP_CLIENT) &&
-			   !ether_addr_equal(skb->data + ETH_ALEN, dev->dev_addr)) {
-			/* AP client mode: send frames with foreign src addr
-			 * using 4-addr WDS frames */
-			use_wds = WDS_COMPLIANT_FRAME;
-		}
-	}
-
-	/* Incoming skb->data: dst_addr[6], src_addr[6], proto[2], payload
-	 * ==>
-	 * Prism2 TX frame with 802.11 header:
-	 * txdesc (address order depending on used mode; includes dst_addr and
-	 * src_addr), possible encapsulation (RFC1042/Bridge-Tunnel;
-	 * proto[2], payload {, possible addr4[6]} */
-
-	ethertype = (skb->data[12] << 8) | skb->data[13];
-
-	memset(&hdr, 0, sizeof(hdr));
-
-	/* Length of data after IEEE 802.11 header */
-	encaps_data = NULL;
-	encaps_len = 0;
-	skip_header_bytes = ETH_HLEN;
-	if (ethertype == ETH_P_AARP || ethertype == ETH_P_IPX) {
-		encaps_data = bridge_tunnel_header;
-		encaps_len = sizeof(bridge_tunnel_header);
-		skip_header_bytes -= 2;
-	} else if (ethertype >= 0x600) {
-		encaps_data = rfc1042_header;
-		encaps_len = sizeof(rfc1042_header);
-		skip_header_bytes -= 2;
-	}
-
-	fc = IEEE80211_FTYPE_DATA | IEEE80211_STYPE_DATA;
-	hdr_len = IEEE80211_DATA_HDR3_LEN;
-
-	if (use_wds != WDS_NO) {
-		/* Note! Prism2 station firmware has problems with sending real
-		 * 802.11 frames with four addresses; until these problems can
-		 * be fixed or worked around, 4-addr frames needed for WDS are
-		 * using incompatible format: FromDS flag is not set and the
-		 * fourth address is added after the frame payload; it is
-		 * assumed, that the receiving station knows how to handle this
-		 * frame format */
-
-		if (use_wds == WDS_COMPLIANT_FRAME) {
-			fc |= IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS;
-			/* From&To DS: Addr1 = RA, Addr2 = TA, Addr3 = DA,
-			 * Addr4 = SA */
-			skb_copy_from_linear_data_offset(skb, ETH_ALEN,
-							 &hdr.addr4, ETH_ALEN);
-			hdr_len += ETH_ALEN;
-		} else {
-			/* bogus 4-addr format to workaround Prism2 station
-			 * f/w bug */
-			fc |= IEEE80211_FCTL_TODS;
-			/* From DS: Addr1 = DA (used as RA),
-			 * Addr2 = BSSID (used as TA), Addr3 = SA (used as DA),
-			 */
-
-			/* SA from skb->data + ETH_ALEN will be added after
-			 * frame payload; use hdr.addr4 as a temporary buffer
-			 */
-			skb_copy_from_linear_data_offset(skb, ETH_ALEN,
-							 &hdr.addr4, ETH_ALEN);
-			need_tailroom += ETH_ALEN;
-		}
-
-		/* send broadcast and multicast frames to broadcast RA, if
-		 * configured; otherwise, use unicast RA of the WDS link */
-		if ((local->wds_type & HOSTAP_WDS_BROADCAST_RA) &&
-		    is_multicast_ether_addr(skb->data))
-			eth_broadcast_addr(hdr.addr1);
-		else if (iface->type == HOSTAP_INTERFACE_WDS)
-			memcpy(&hdr.addr1, iface->u.wds.remote_addr,
-			       ETH_ALEN);
-		else
-			memcpy(&hdr.addr1, local->bssid, ETH_ALEN);
-		memcpy(&hdr.addr2, dev->dev_addr, ETH_ALEN);
-		skb_copy_from_linear_data(skb, &hdr.addr3, ETH_ALEN);
-	} else if (local->iw_mode == IW_MODE_MASTER && !to_assoc_ap) {
-		fc |= IEEE80211_FCTL_FROMDS;
-		/* From DS: Addr1 = DA, Addr2 = BSSID, Addr3 = SA */
-		skb_copy_from_linear_data(skb, &hdr.addr1, ETH_ALEN);
-		memcpy(&hdr.addr2, dev->dev_addr, ETH_ALEN);
-		skb_copy_from_linear_data_offset(skb, ETH_ALEN, &hdr.addr3,
-						 ETH_ALEN);
-	} else if (local->iw_mode == IW_MODE_INFRA || to_assoc_ap) {
-		fc |= IEEE80211_FCTL_TODS;
-		/* To DS: Addr1 = BSSID, Addr2 = SA, Addr3 = DA */
-		memcpy(&hdr.addr1, to_assoc_ap ?
-		       local->assoc_ap_addr : local->bssid, ETH_ALEN);
-		skb_copy_from_linear_data_offset(skb, ETH_ALEN, &hdr.addr2,
-						 ETH_ALEN);
-		skb_copy_from_linear_data(skb, &hdr.addr3, ETH_ALEN);
-	} else if (local->iw_mode == IW_MODE_ADHOC) {
-		/* not From/To DS: Addr1 = DA, Addr2 = SA, Addr3 = BSSID */
-		skb_copy_from_linear_data(skb, &hdr.addr1, ETH_ALEN);
-		skb_copy_from_linear_data_offset(skb, ETH_ALEN, &hdr.addr2,
-						 ETH_ALEN);
-		memcpy(&hdr.addr3, local->bssid, ETH_ALEN);
-	}
-
-	hdr.frame_control = cpu_to_le16(fc);
-
-	skb_pull(skb, skip_header_bytes);
-	need_headroom = local->func->need_tx_headroom + hdr_len + encaps_len;
-	if (skb_tailroom(skb) < need_tailroom) {
-		skb = skb_unshare(skb, GFP_ATOMIC);
-		if (skb == NULL) {
-			iface->stats.tx_dropped++;
-			return NETDEV_TX_OK;
-		}
-		if (pskb_expand_head(skb, need_headroom, need_tailroom,
-				     GFP_ATOMIC)) {
-			kfree_skb(skb);
-			iface->stats.tx_dropped++;
-			return NETDEV_TX_OK;
-		}
-	} else if (skb_headroom(skb) < need_headroom) {
-		struct sk_buff *tmp = skb;
-		skb = skb_realloc_headroom(skb, need_headroom);
-		kfree_skb(tmp);
-		if (skb == NULL) {
-			iface->stats.tx_dropped++;
-			return NETDEV_TX_OK;
-		}
-	} else {
-		skb = skb_unshare(skb, GFP_ATOMIC);
-		if (skb == NULL) {
-			iface->stats.tx_dropped++;
-			return NETDEV_TX_OK;
-		}
-	}
-
-	if (encaps_data)
-		memcpy(skb_push(skb, encaps_len), encaps_data, encaps_len);
-	memcpy(skb_push(skb, hdr_len), &hdr, hdr_len);
-	if (use_wds == WDS_OWN_FRAME) {
-		skb_put_data(skb, &hdr.addr4, ETH_ALEN);
-	}
-
-	iface->stats.tx_packets++;
-	iface->stats.tx_bytes += skb->len;
-
-	skb_reset_mac_header(skb);
-	meta = (struct hostap_skb_tx_data *) skb->cb;
-	memset(meta, 0, sizeof(*meta));
-	meta->magic = HOSTAP_SKB_TX_DATA_MAGIC;
-	if (use_wds)
-		meta->flags |= HOSTAP_TX_FLAGS_WDS;
-	meta->ethertype = ethertype;
-	meta->iface = iface;
-
-	/* Send IEEE 802.11 encapsulated frame using the master radio device */
-	skb->dev = local->dev;
-	dev_queue_xmit(skb);
-	return NETDEV_TX_OK;
-}
-
-
-/* hard_start_xmit function for hostapd wlan#ap interfaces */
-netdev_tx_t hostap_mgmt_start_xmit(struct sk_buff *skb,
-				   struct net_device *dev)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	struct hostap_skb_tx_data *meta;
-	struct ieee80211_hdr *hdr;
-	u16 fc;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (skb->len < 10) {
-		printk(KERN_DEBUG "%s: hostap_mgmt_start_xmit: short skb "
-		       "(len=%d)\n", dev->name, skb->len);
-		kfree_skb(skb);
-		return NETDEV_TX_OK;
-	}
-
-	iface->stats.tx_packets++;
-	iface->stats.tx_bytes += skb->len;
-
-	meta = (struct hostap_skb_tx_data *) skb->cb;
-	memset(meta, 0, sizeof(*meta));
-	meta->magic = HOSTAP_SKB_TX_DATA_MAGIC;
-	meta->iface = iface;
-
-	if (skb->len >= IEEE80211_DATA_HDR3_LEN + sizeof(rfc1042_header) + 2) {
-		hdr = (struct ieee80211_hdr *) skb->data;
-		fc = le16_to_cpu(hdr->frame_control);
-		if (ieee80211_is_data(hdr->frame_control) &&
-		    (fc & IEEE80211_FCTL_STYPE) == IEEE80211_STYPE_DATA) {
-			u8 *pos = &skb->data[IEEE80211_DATA_HDR3_LEN +
-					     sizeof(rfc1042_header)];
-			meta->ethertype = (pos[0] << 8) | pos[1];
-		}
-	}
-
-	/* Send IEEE 802.11 encapsulated frame using the master radio device */
-	skb->dev = local->dev;
-	dev_queue_xmit(skb);
-	return NETDEV_TX_OK;
-}
-
-
-/* Called only from software IRQ */
-static struct sk_buff * hostap_tx_encrypt(struct sk_buff *skb,
-					  struct lib80211_crypt_data *crypt)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	struct ieee80211_hdr *hdr;
-	int prefix_len, postfix_len, hdr_len, res;
-
-	iface = netdev_priv(skb->dev);
-	local = iface->local;
-
-	if (skb->len < IEEE80211_DATA_HDR3_LEN) {
-		kfree_skb(skb);
-		return NULL;
-	}
-
-	if (local->tkip_countermeasures &&
-	    strcmp(crypt->ops->name, "TKIP") == 0) {
-		hdr = (struct ieee80211_hdr *) skb->data;
-		if (net_ratelimit()) {
-			printk(KERN_DEBUG "%s: TKIP countermeasures: dropped "
-			       "TX packet to %pM\n",
-			       local->dev->name, hdr->addr1);
-		}
-		kfree_skb(skb);
-		return NULL;
-	}
-
-	skb = skb_unshare(skb, GFP_ATOMIC);
-	if (skb == NULL)
-		return NULL;
-
-	prefix_len = crypt->ops->extra_mpdu_prefix_len +
-		crypt->ops->extra_msdu_prefix_len;
-	postfix_len = crypt->ops->extra_mpdu_postfix_len +
-		crypt->ops->extra_msdu_postfix_len;
-	if ((skb_headroom(skb) < prefix_len ||
-	     skb_tailroom(skb) < postfix_len) &&
-	    pskb_expand_head(skb, prefix_len, postfix_len, GFP_ATOMIC)) {
-		kfree_skb(skb);
-		return NULL;
-	}
-
-	hdr = (struct ieee80211_hdr *) skb->data;
-	hdr_len = hostap_80211_get_hdrlen(hdr->frame_control);
-
-	/* Host-based IEEE 802.11 fragmentation for TX is not yet supported, so
-	 * call both MSDU and MPDU encryption functions from here. */
-	atomic_inc(&crypt->refcnt);
-	res = 0;
-	if (crypt->ops->encrypt_msdu)
-		res = crypt->ops->encrypt_msdu(skb, hdr_len, crypt->priv);
-	if (res == 0 && crypt->ops->encrypt_mpdu)
-		res = crypt->ops->encrypt_mpdu(skb, hdr_len, crypt->priv);
-	atomic_dec(&crypt->refcnt);
-	if (res < 0) {
-		kfree_skb(skb);
-		return NULL;
-	}
-
-	return skb;
-}
-
-
-/* hard_start_xmit function for master radio interface wifi#.
- * AP processing (TX rate control, power save buffering, etc.).
- * Use hardware TX function to send the frame. */
-netdev_tx_t hostap_master_start_xmit(struct sk_buff *skb,
-				     struct net_device *dev)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	netdev_tx_t ret = NETDEV_TX_BUSY;
-	u16 fc;
-	struct hostap_tx_data tx;
-	ap_tx_ret tx_ret;
-	struct hostap_skb_tx_data *meta;
-	int no_encrypt = 0;
-	struct ieee80211_hdr *hdr;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	tx.skb = skb;
-	tx.sta_ptr = NULL;
-
-	meta = (struct hostap_skb_tx_data *) skb->cb;
-	if (meta->magic != HOSTAP_SKB_TX_DATA_MAGIC) {
-		printk(KERN_DEBUG "%s: invalid skb->cb magic (0x%08x, "
-		       "expected 0x%08x)\n",
-		       dev->name, meta->magic, HOSTAP_SKB_TX_DATA_MAGIC);
-		ret = NETDEV_TX_OK;
-		iface->stats.tx_dropped++;
-		goto fail;
-	}
-
-	if (local->host_encrypt) {
-		/* Set crypt to default algorithm and key; will be replaced in
-		 * AP code if STA has own alg/key */
-		tx.crypt = local->crypt_info.crypt[local->crypt_info.tx_keyidx];
-		tx.host_encrypt = 1;
-	} else {
-		tx.crypt = NULL;
-		tx.host_encrypt = 0;
-	}
-
-	if (skb->len < 24) {
-		printk(KERN_DEBUG "%s: hostap_master_start_xmit: short skb "
-		       "(len=%d)\n", dev->name, skb->len);
-		ret = NETDEV_TX_OK;
-		iface->stats.tx_dropped++;
-		goto fail;
-	}
-
-	/* FIX (?):
-	 * Wi-Fi 802.11b test plan suggests that AP should ignore power save
-	 * bit in authentication and (re)association frames and assume tha
-	 * STA remains awake for the response. */
-	tx_ret = hostap_handle_sta_tx(local, &tx);
-	skb = tx.skb;
-	meta = (struct hostap_skb_tx_data *) skb->cb;
-	hdr = (struct ieee80211_hdr *) skb->data;
-	fc = le16_to_cpu(hdr->frame_control);
-	switch (tx_ret) {
-	case AP_TX_CONTINUE:
-		break;
-	case AP_TX_CONTINUE_NOT_AUTHORIZED:
-		if (local->ieee_802_1x &&
-		    ieee80211_is_data(hdr->frame_control) &&
-		    meta->ethertype != ETH_P_PAE &&
-		    !(meta->flags & HOSTAP_TX_FLAGS_WDS)) {
-			printk(KERN_DEBUG "%s: dropped frame to unauthorized "
-			       "port (IEEE 802.1X): ethertype=0x%04x\n",
-			       dev->name, meta->ethertype);
-			hostap_dump_tx_80211(dev->name, skb);
-
-			ret = NETDEV_TX_OK; /* drop packet */
-			iface->stats.tx_dropped++;
-			goto fail;
-		}
-		break;
-	case AP_TX_DROP:
-		ret = NETDEV_TX_OK; /* drop packet */
-		iface->stats.tx_dropped++;
-		goto fail;
-	case AP_TX_RETRY:
-		goto fail;
-	case AP_TX_BUFFERED:
-		/* do not free skb here, it will be freed when the
-		 * buffered frame is sent/timed out */
-		ret = NETDEV_TX_OK;
-		goto tx_exit;
-	}
-
-	/* Request TX callback if protocol version is 2 in 802.11 header;
-	 * this version 2 is a special case used between hostapd and kernel
-	 * driver */
-	if (((fc & IEEE80211_FCTL_VERS) == BIT(1)) &&
-	    local->ap && local->ap->tx_callback_idx && meta->tx_cb_idx == 0) {
-		meta->tx_cb_idx = local->ap->tx_callback_idx;
-
-		/* remove special version from the frame header */
-		fc &= ~IEEE80211_FCTL_VERS;
-		hdr->frame_control = cpu_to_le16(fc);
-	}
-
-	if (!ieee80211_is_data(hdr->frame_control)) {
-		no_encrypt = 1;
-		tx.crypt = NULL;
-	}
-
-	if (local->ieee_802_1x && meta->ethertype == ETH_P_PAE && tx.crypt &&
-	    !(fc & IEEE80211_FCTL_PROTECTED)) {
-		no_encrypt = 1;
-		PDEBUG(DEBUG_EXTRA2, "%s: TX: IEEE 802.1X - passing "
-		       "unencrypted EAPOL frame\n", dev->name);
-		tx.crypt = NULL; /* no encryption for IEEE 802.1X frames */
-	}
-
-	if (tx.crypt && (!tx.crypt->ops || !tx.crypt->ops->encrypt_mpdu))
-		tx.crypt = NULL;
-	else if ((tx.crypt ||
-		 local->crypt_info.crypt[local->crypt_info.tx_keyidx]) &&
-		 !no_encrypt) {
-		/* Add ISWEP flag both for firmware and host based encryption
-		 */
-		fc |= IEEE80211_FCTL_PROTECTED;
-		hdr->frame_control = cpu_to_le16(fc);
-	} else if (local->drop_unencrypted &&
-		   ieee80211_is_data(hdr->frame_control) &&
-		   meta->ethertype != ETH_P_PAE) {
-		if (net_ratelimit()) {
-			printk(KERN_DEBUG "%s: dropped unencrypted TX data "
-			       "frame (drop_unencrypted=1)\n", dev->name);
-		}
-		iface->stats.tx_dropped++;
-		ret = NETDEV_TX_OK;
-		goto fail;
-	}
-
-	if (tx.crypt) {
-		skb = hostap_tx_encrypt(skb, tx.crypt);
-		if (skb == NULL) {
-			printk(KERN_DEBUG "%s: TX - encryption failed\n",
-			       dev->name);
-			ret = NETDEV_TX_OK;
-			goto fail;
-		}
-		meta = (struct hostap_skb_tx_data *) skb->cb;
-		if (meta->magic != HOSTAP_SKB_TX_DATA_MAGIC) {
-			printk(KERN_DEBUG "%s: invalid skb->cb magic (0x%08x, "
-			       "expected 0x%08x) after hostap_tx_encrypt\n",
-			       dev->name, meta->magic,
-			       HOSTAP_SKB_TX_DATA_MAGIC);
-			ret = NETDEV_TX_OK;
-			iface->stats.tx_dropped++;
-			goto fail;
-		}
-	}
-
-	if (local->func->tx == NULL || local->func->tx(skb, dev)) {
-		ret = NETDEV_TX_OK;
-		iface->stats.tx_dropped++;
-	} else {
-		ret = NETDEV_TX_OK;
-		iface->stats.tx_packets++;
-		iface->stats.tx_bytes += skb->len;
-	}
-
- fail:
-	if (ret == NETDEV_TX_OK && skb)
-		dev_kfree_skb(skb);
- tx_exit:
-	if (tx.sta_ptr)
-		hostap_handle_sta_release(tx.sta_ptr);
-	return ret;
-}
-
-
-EXPORT_SYMBOL(hostap_master_start_xmit);
diff --git a/drivers/net/wireless/intersil/hostap/hostap_ap.c b/drivers/net/wireless/intersil/hostap/hostap_ap.c
deleted file mode 100644
index 9b546a71e7a2..000000000000
--- a/drivers/net/wireless/intersil/hostap/hostap_ap.c
+++ /dev/null
@@ -1,3277 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Intersil Prism2 driver with Host AP (software access point) support
- * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen
- * <j@w1.fi>
- * Copyright (c) 2002-2005, Jouni Malinen <j@w1.fi>
- *
- * This file is to be included into hostap.c when S/W AP functionality is
- * compiled.
- *
- * AP:  FIX:
- * - if unicast Class 2 (assoc,reassoc,disassoc) frame received from
- *   unauthenticated STA, send deauth. frame (8802.11: 5.5)
- * - if unicast Class 3 (data with to/from DS,deauth,pspoll) frame received
- *   from authenticated, but unassoc STA, send disassoc frame (8802.11: 5.5)
- * - if unicast Class 3 received from unauthenticated STA, send deauth. frame
- *   (8802.11: 5.5)
- */
-
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/delay.h>
-#include <linux/random.h>
-#include <linux/if_arp.h>
-#include <linux/slab.h>
-#include <linux/export.h>
-#include <linux/moduleparam.h>
-#include <linux/etherdevice.h>
-
-#include "hostap_wlan.h"
-#include "hostap.h"
-#include "hostap_ap.h"
-
-static int other_ap_policy[MAX_PARM_DEVICES] = { AP_OTHER_AP_SKIP_ALL,
-						 DEF_INTS };
-module_param_array(other_ap_policy, int, NULL, 0444);
-MODULE_PARM_DESC(other_ap_policy, "Other AP beacon monitoring policy (0-3)");
-
-static int ap_max_inactivity[MAX_PARM_DEVICES] = { AP_MAX_INACTIVITY_SEC,
-						   DEF_INTS };
-module_param_array(ap_max_inactivity, int, NULL, 0444);
-MODULE_PARM_DESC(ap_max_inactivity, "AP timeout (in seconds) for station "
-		 "inactivity");
-
-static int ap_bridge_packets[MAX_PARM_DEVICES] = { 1, DEF_INTS };
-module_param_array(ap_bridge_packets, int, NULL, 0444);
-MODULE_PARM_DESC(ap_bridge_packets, "Bridge packets directly between "
-		 "stations");
-
-static int autom_ap_wds[MAX_PARM_DEVICES] = { 0, DEF_INTS };
-module_param_array(autom_ap_wds, int, NULL, 0444);
-MODULE_PARM_DESC(autom_ap_wds, "Add WDS connections to other APs "
-		 "automatically");
-
-
-static struct sta_info* ap_get_sta(struct ap_data *ap, u8 *sta);
-static void hostap_event_expired_sta(struct net_device *dev,
-				     struct sta_info *sta);
-static void handle_add_proc_queue(struct work_struct *work);
-
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-static void handle_wds_oper_queue(struct work_struct *work);
-static void prism2_send_mgmt(struct net_device *dev,
-			     u16 type_subtype, char *body,
-			     int body_len, u8 *addr, u16 tx_cb_idx);
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-
-
-#if !defined(PRISM2_NO_PROCFS_DEBUG) && defined(CONFIG_PROC_FS)
-static int ap_debug_proc_show(struct seq_file *m, void *v)
-{
-	struct ap_data *ap = pde_data(file_inode(m->file));
-
-	seq_printf(m, "BridgedUnicastFrames=%u\n", ap->bridged_unicast);
-	seq_printf(m, "BridgedMulticastFrames=%u\n", ap->bridged_multicast);
-	seq_printf(m, "max_inactivity=%u\n", ap->max_inactivity / HZ);
-	seq_printf(m, "bridge_packets=%u\n", ap->bridge_packets);
-	seq_printf(m, "nullfunc_ack=%u\n", ap->nullfunc_ack);
-	seq_printf(m, "autom_ap_wds=%u\n", ap->autom_ap_wds);
-	seq_printf(m, "auth_algs=%u\n", ap->local->auth_algs);
-	seq_printf(m, "tx_drop_nonassoc=%u\n", ap->tx_drop_nonassoc);
-	return 0;
-}
-#endif
-
-static void ap_sta_hash_add(struct ap_data *ap, struct sta_info *sta)
-{
-	sta->hnext = ap->sta_hash[STA_HASH(sta->addr)];
-	ap->sta_hash[STA_HASH(sta->addr)] = sta;
-}
-
-static void ap_sta_hash_del(struct ap_data *ap, struct sta_info *sta)
-{
-	struct sta_info *s;
-
-	s = ap->sta_hash[STA_HASH(sta->addr)];
-	if (s == NULL) return;
-	if (ether_addr_equal(s->addr, sta->addr)) {
-		ap->sta_hash[STA_HASH(sta->addr)] = s->hnext;
-		return;
-	}
-
-	while (s->hnext != NULL && !ether_addr_equal(s->hnext->addr, sta->addr))
-		s = s->hnext;
-	if (s->hnext != NULL)
-		s->hnext = s->hnext->hnext;
-	else
-		printk("AP: could not remove STA %pM from hash table\n",
-		       sta->addr);
-}
-
-static void ap_free_sta(struct ap_data *ap, struct sta_info *sta)
-{
-	if (sta->ap && sta->local)
-		hostap_event_expired_sta(sta->local->dev, sta);
-
-	if (ap->proc != NULL) {
-		char name[20];
-		sprintf(name, "%pM", sta->addr);
-		remove_proc_entry(name, ap->proc);
-	}
-
-	if (sta->crypt) {
-		sta->crypt->ops->deinit(sta->crypt->priv);
-		kfree(sta->crypt);
-		sta->crypt = NULL;
-	}
-
-	skb_queue_purge(&sta->tx_buf);
-
-	ap->num_sta--;
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-	if (sta->aid > 0)
-		ap->sta_aid[sta->aid - 1] = NULL;
-
-	if (!sta->ap)
-		kfree(sta->u.sta.challenge);
-	timer_shutdown_sync(&sta->timer);
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-
-	kfree(sta);
-}
-
-
-static void hostap_set_tim(local_info_t *local, int aid, int set)
-{
-	if (local->func->set_tim)
-		local->func->set_tim(local->dev, aid, set);
-}
-
-
-static void hostap_event_new_sta(struct net_device *dev, struct sta_info *sta)
-{
-	union iwreq_data wrqu;
-	memset(&wrqu, 0, sizeof(wrqu));
-	memcpy(wrqu.addr.sa_data, sta->addr, ETH_ALEN);
-	wrqu.addr.sa_family = ARPHRD_ETHER;
-	wireless_send_event(dev, IWEVREGISTERED, &wrqu, NULL);
-}
-
-
-static void hostap_event_expired_sta(struct net_device *dev,
-				     struct sta_info *sta)
-{
-	union iwreq_data wrqu;
-	memset(&wrqu, 0, sizeof(wrqu));
-	memcpy(wrqu.addr.sa_data, sta->addr, ETH_ALEN);
-	wrqu.addr.sa_family = ARPHRD_ETHER;
-	wireless_send_event(dev, IWEVEXPIRED, &wrqu, NULL);
-}
-
-
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-
-static void ap_handle_timer(struct timer_list *t)
-{
-	struct sta_info *sta = from_timer(sta, t, timer);
-	local_info_t *local;
-	struct ap_data *ap;
-	unsigned long next_time = 0;
-	int was_assoc;
-
-	if (sta == NULL || sta->local == NULL || sta->local->ap == NULL) {
-		PDEBUG(DEBUG_AP, "ap_handle_timer() called with NULL data\n");
-		return;
-	}
-
-	local = sta->local;
-	ap = local->ap;
-	was_assoc = sta->flags & WLAN_STA_ASSOC;
-
-	if (atomic_read(&sta->users) != 0)
-		next_time = jiffies + HZ;
-	else if ((sta->flags & WLAN_STA_PERM) && !(sta->flags & WLAN_STA_AUTH))
-		next_time = jiffies + ap->max_inactivity;
-
-	if (time_before(jiffies, sta->last_rx + ap->max_inactivity)) {
-		/* station activity detected; reset timeout state */
-		sta->timeout_next = STA_NULLFUNC;
-		next_time = sta->last_rx + ap->max_inactivity;
-	} else if (sta->timeout_next == STA_DISASSOC &&
-		   !(sta->flags & WLAN_STA_PENDING_POLL)) {
-		/* STA ACKed data nullfunc frame poll */
-		sta->timeout_next = STA_NULLFUNC;
-		next_time = jiffies + ap->max_inactivity;
-	}
-
-	if (next_time) {
-		sta->timer.expires = next_time;
-		add_timer(&sta->timer);
-		return;
-	}
-
-	if (sta->ap)
-		sta->timeout_next = STA_DEAUTH;
-
-	if (sta->timeout_next == STA_DEAUTH && !(sta->flags & WLAN_STA_PERM)) {
-		spin_lock(&ap->sta_table_lock);
-		ap_sta_hash_del(ap, sta);
-		list_del(&sta->list);
-		spin_unlock(&ap->sta_table_lock);
-		sta->flags &= ~(WLAN_STA_AUTH | WLAN_STA_ASSOC);
-	} else if (sta->timeout_next == STA_DISASSOC)
-		sta->flags &= ~WLAN_STA_ASSOC;
-
-	if (was_assoc && !(sta->flags & WLAN_STA_ASSOC) && !sta->ap)
-		hostap_event_expired_sta(local->dev, sta);
-
-	if (sta->timeout_next == STA_DEAUTH && sta->aid > 0 &&
-	    !skb_queue_empty(&sta->tx_buf)) {
-		hostap_set_tim(local, sta->aid, 0);
-		sta->flags &= ~WLAN_STA_TIM;
-	}
-
-	if (sta->ap) {
-		if (ap->autom_ap_wds) {
-			PDEBUG(DEBUG_AP, "%s: removing automatic WDS "
-			       "connection to AP %pM\n",
-			       local->dev->name, sta->addr);
-			hostap_wds_link_oper(local, sta->addr, WDS_DEL);
-		}
-	} else if (sta->timeout_next == STA_NULLFUNC) {
-		/* send data frame to poll STA and check whether this frame
-		 * is ACKed */
-		/* FIX: IEEE80211_STYPE_NULLFUNC would be more appropriate, but
-		 * it is apparently not retried so TX Exc events are not
-		 * received for it */
-		sta->flags |= WLAN_STA_PENDING_POLL;
-		prism2_send_mgmt(local->dev, IEEE80211_FTYPE_DATA |
-				 IEEE80211_STYPE_DATA, NULL, 0,
-				 sta->addr, ap->tx_callback_poll);
-	} else {
-		int deauth = sta->timeout_next == STA_DEAUTH;
-		__le16 resp;
-		PDEBUG(DEBUG_AP, "%s: sending %s info to STA %pM"
-		       "(last=%lu, jiffies=%lu)\n",
-		       local->dev->name,
-		       deauth ? "deauthentication" : "disassociation",
-		       sta->addr, sta->last_rx, jiffies);
-
-		resp = cpu_to_le16(deauth ? WLAN_REASON_PREV_AUTH_NOT_VALID :
-				   WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY);
-		prism2_send_mgmt(local->dev, IEEE80211_FTYPE_MGMT |
-				 (deauth ? IEEE80211_STYPE_DEAUTH :
-				  IEEE80211_STYPE_DISASSOC),
-				 (char *) &resp, 2, sta->addr, 0);
-	}
-
-	if (sta->timeout_next == STA_DEAUTH) {
-		if (sta->flags & WLAN_STA_PERM) {
-			PDEBUG(DEBUG_AP, "%s: STA %pM"
-			       " would have been removed, "
-			       "but it has 'perm' flag\n",
-			       local->dev->name, sta->addr);
-		} else
-			ap_free_sta(ap, sta);
-		return;
-	}
-
-	if (sta->timeout_next == STA_NULLFUNC) {
-		sta->timeout_next = STA_DISASSOC;
-		sta->timer.expires = jiffies + AP_DISASSOC_DELAY;
-	} else {
-		sta->timeout_next = STA_DEAUTH;
-		sta->timer.expires = jiffies + AP_DEAUTH_DELAY;
-	}
-
-	add_timer(&sta->timer);
-}
-
-
-void hostap_deauth_all_stas(struct net_device *dev, struct ap_data *ap,
-			    int resend)
-{
-	u8 addr[ETH_ALEN];
-	__le16 resp;
-	int i;
-
-	PDEBUG(DEBUG_AP, "%s: Deauthenticate all stations\n", dev->name);
-	eth_broadcast_addr(addr);
-
-	resp = cpu_to_le16(WLAN_REASON_PREV_AUTH_NOT_VALID);
-
-	/* deauth message sent; try to resend it few times; the message is
-	 * broadcast, so it may be delayed until next DTIM; there is not much
-	 * else we can do at this point since the driver is going to be shut
-	 * down */
-	for (i = 0; i < 5; i++) {
-		prism2_send_mgmt(dev, IEEE80211_FTYPE_MGMT |
-				 IEEE80211_STYPE_DEAUTH,
-				 (char *) &resp, 2, addr, 0);
-
-		if (!resend || ap->num_sta <= 0)
-			return;
-
-		mdelay(50);
-	}
-}
-
-
-static int ap_control_proc_show(struct seq_file *m, void *v)
-{
-	struct ap_data *ap = pde_data(file_inode(m->file));
-	char *policy_txt;
-	struct mac_entry *entry;
-
-	if (v == SEQ_START_TOKEN) {
-		switch (ap->mac_restrictions.policy) {
-		case MAC_POLICY_OPEN:
-			policy_txt = "open";
-			break;
-		case MAC_POLICY_ALLOW:
-			policy_txt = "allow";
-			break;
-		case MAC_POLICY_DENY:
-			policy_txt = "deny";
-			break;
-		default:
-			policy_txt = "unknown";
-			break;
-		}
-		seq_printf(m, "MAC policy: %s\n", policy_txt);
-		seq_printf(m, "MAC entries: %u\n", ap->mac_restrictions.entries);
-		seq_puts(m, "MAC list:\n");
-		return 0;
-	}
-
-	entry = v;
-	seq_printf(m, "%pM\n", entry->addr);
-	return 0;
-}
-
-static void *ap_control_proc_start(struct seq_file *m, loff_t *_pos)
-{
-	struct ap_data *ap = pde_data(file_inode(m->file));
-	spin_lock_bh(&ap->mac_restrictions.lock);
-	return seq_list_start_head(&ap->mac_restrictions.mac_list, *_pos);
-}
-
-static void *ap_control_proc_next(struct seq_file *m, void *v, loff_t *_pos)
-{
-	struct ap_data *ap = pde_data(file_inode(m->file));
-	return seq_list_next(v, &ap->mac_restrictions.mac_list, _pos);
-}
-
-static void ap_control_proc_stop(struct seq_file *m, void *v)
-{
-	struct ap_data *ap = pde_data(file_inode(m->file));
-	spin_unlock_bh(&ap->mac_restrictions.lock);
-}
-
-static const struct seq_operations ap_control_proc_seqops = {
-	.start	= ap_control_proc_start,
-	.next	= ap_control_proc_next,
-	.stop	= ap_control_proc_stop,
-	.show	= ap_control_proc_show,
-};
-
-int ap_control_add_mac(struct mac_restrictions *mac_restrictions, u8 *mac)
-{
-	struct mac_entry *entry;
-
-	entry = kmalloc(sizeof(struct mac_entry), GFP_KERNEL);
-	if (entry == NULL)
-		return -ENOMEM;
-
-	memcpy(entry->addr, mac, ETH_ALEN);
-
-	spin_lock_bh(&mac_restrictions->lock);
-	list_add_tail(&entry->list, &mac_restrictions->mac_list);
-	mac_restrictions->entries++;
-	spin_unlock_bh(&mac_restrictions->lock);
-
-	return 0;
-}
-
-
-int ap_control_del_mac(struct mac_restrictions *mac_restrictions, u8 *mac)
-{
-	struct list_head *ptr;
-	struct mac_entry *entry;
-
-	spin_lock_bh(&mac_restrictions->lock);
-	for (ptr = mac_restrictions->mac_list.next;
-	     ptr != &mac_restrictions->mac_list; ptr = ptr->next) {
-		entry = list_entry(ptr, struct mac_entry, list);
-
-		if (ether_addr_equal(entry->addr, mac)) {
-			list_del(ptr);
-			kfree(entry);
-			mac_restrictions->entries--;
-			spin_unlock_bh(&mac_restrictions->lock);
-			return 0;
-		}
-	}
-	spin_unlock_bh(&mac_restrictions->lock);
-	return -1;
-}
-
-
-static int ap_control_mac_deny(struct mac_restrictions *mac_restrictions,
-			       u8 *mac)
-{
-	struct mac_entry *entry;
-	int found = 0;
-
-	if (mac_restrictions->policy == MAC_POLICY_OPEN)
-		return 0;
-
-	spin_lock_bh(&mac_restrictions->lock);
-	list_for_each_entry(entry, &mac_restrictions->mac_list, list) {
-		if (ether_addr_equal(entry->addr, mac)) {
-			found = 1;
-			break;
-		}
-	}
-	spin_unlock_bh(&mac_restrictions->lock);
-
-	if (mac_restrictions->policy == MAC_POLICY_ALLOW)
-		return !found;
-	else
-		return found;
-}
-
-
-void ap_control_flush_macs(struct mac_restrictions *mac_restrictions)
-{
-	struct list_head *ptr, *n;
-	struct mac_entry *entry;
-
-	if (mac_restrictions->entries == 0)
-		return;
-
-	spin_lock_bh(&mac_restrictions->lock);
-	for (ptr = mac_restrictions->mac_list.next, n = ptr->next;
-	     ptr != &mac_restrictions->mac_list;
-	     ptr = n, n = ptr->next) {
-		entry = list_entry(ptr, struct mac_entry, list);
-		list_del(ptr);
-		kfree(entry);
-	}
-	mac_restrictions->entries = 0;
-	spin_unlock_bh(&mac_restrictions->lock);
-}
-
-
-int ap_control_kick_mac(struct ap_data *ap, struct net_device *dev, u8 *mac)
-{
-	struct sta_info *sta;
-	__le16 resp;
-
-	spin_lock_bh(&ap->sta_table_lock);
-	sta = ap_get_sta(ap, mac);
-	if (sta) {
-		ap_sta_hash_del(ap, sta);
-		list_del(&sta->list);
-	}
-	spin_unlock_bh(&ap->sta_table_lock);
-
-	if (!sta)
-		return -EINVAL;
-
-	resp = cpu_to_le16(WLAN_REASON_PREV_AUTH_NOT_VALID);
-	prism2_send_mgmt(dev, IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_DEAUTH,
-			 (char *) &resp, 2, sta->addr, 0);
-
-	if ((sta->flags & WLAN_STA_ASSOC) && !sta->ap)
-		hostap_event_expired_sta(dev, sta);
-
-	ap_free_sta(ap, sta);
-
-	return 0;
-}
-
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-
-
-void ap_control_kickall(struct ap_data *ap)
-{
-	struct list_head *ptr, *n;
-	struct sta_info *sta;
-
-	spin_lock_bh(&ap->sta_table_lock);
-	for (ptr = ap->sta_list.next, n = ptr->next; ptr != &ap->sta_list;
-	     ptr = n, n = ptr->next) {
-		sta = list_entry(ptr, struct sta_info, list);
-		ap_sta_hash_del(ap, sta);
-		list_del(&sta->list);
-		if ((sta->flags & WLAN_STA_ASSOC) && !sta->ap && sta->local)
-			hostap_event_expired_sta(sta->local->dev, sta);
-		ap_free_sta(ap, sta);
-	}
-	spin_unlock_bh(&ap->sta_table_lock);
-}
-
-
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-
-static int prism2_ap_proc_show(struct seq_file *m, void *v)
-{
-	struct sta_info *sta = v;
-	int i;
-
-	if (v == SEQ_START_TOKEN) {
-		seq_printf(m, "# BSSID CHAN SIGNAL NOISE RATE SSID FLAGS\n");
-		return 0;
-	}
-
-	if (!sta->ap)
-		return 0;
-
-	seq_printf(m, "%pM %d %d %d %d '",
-		   sta->addr,
-		   sta->u.ap.channel, sta->last_rx_signal,
-		   sta->last_rx_silence, sta->last_rx_rate);
-
-	for (i = 0; i < sta->u.ap.ssid_len; i++) {
-		if (sta->u.ap.ssid[i] >= 32 && sta->u.ap.ssid[i] < 127)
-			seq_putc(m, sta->u.ap.ssid[i]);
-		else
-			seq_printf(m, "<%02x>", sta->u.ap.ssid[i]);
-	}
-
-	seq_putc(m, '\'');
-	if (sta->capability & WLAN_CAPABILITY_ESS)
-		seq_puts(m, " [ESS]");
-	if (sta->capability & WLAN_CAPABILITY_IBSS)
-		seq_puts(m, " [IBSS]");
-	if (sta->capability & WLAN_CAPABILITY_PRIVACY)
-		seq_puts(m, " [WEP]");
-	seq_putc(m, '\n');
-	return 0;
-}
-
-static void *prism2_ap_proc_start(struct seq_file *m, loff_t *_pos)
-{
-	struct ap_data *ap = pde_data(file_inode(m->file));
-	spin_lock_bh(&ap->sta_table_lock);
-	return seq_list_start_head(&ap->sta_list, *_pos);
-}
-
-static void *prism2_ap_proc_next(struct seq_file *m, void *v, loff_t *_pos)
-{
-	struct ap_data *ap = pde_data(file_inode(m->file));
-	return seq_list_next(v, &ap->sta_list, _pos);
-}
-
-static void prism2_ap_proc_stop(struct seq_file *m, void *v)
-{
-	struct ap_data *ap = pde_data(file_inode(m->file));
-	spin_unlock_bh(&ap->sta_table_lock);
-}
-
-static const struct seq_operations prism2_ap_proc_seqops = {
-	.start	= prism2_ap_proc_start,
-	.next	= prism2_ap_proc_next,
-	.stop	= prism2_ap_proc_stop,
-	.show	= prism2_ap_proc_show,
-};
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-
-
-void hostap_check_sta_fw_version(struct ap_data *ap, int sta_fw_ver)
-{
-	if (!ap)
-		return;
-
-	if (sta_fw_ver == PRISM2_FW_VER(0,8,0)) {
-		PDEBUG(DEBUG_AP, "Using data::nullfunc ACK workaround - "
-		       "firmware upgrade recommended\n");
-		ap->nullfunc_ack = 1;
-	} else
-		ap->nullfunc_ack = 0;
-
-	if (sta_fw_ver == PRISM2_FW_VER(1,4,2)) {
-		printk(KERN_WARNING "%s: Warning: secondary station firmware "
-		       "version 1.4.2 does not seem to work in Host AP mode\n",
-		       ap->local->dev->name);
-	}
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static void hostap_ap_tx_cb(struct sk_buff *skb, int ok, void *data)
-{
-	struct ap_data *ap = data;
-	struct ieee80211_hdr *hdr;
-
-	if (!ap->local->hostapd || !ap->local->apdev) {
-		dev_kfree_skb(skb);
-		return;
-	}
-
-	/* Pass the TX callback frame to the hostapd; use 802.11 header version
-	 * 1 to indicate failure (no ACK) and 2 success (frame ACKed) */
-
-	hdr = (struct ieee80211_hdr *) skb->data;
-	hdr->frame_control &= cpu_to_le16(~IEEE80211_FCTL_VERS);
-	hdr->frame_control |= cpu_to_le16(ok ? BIT(1) : BIT(0));
-
-	skb->dev = ap->local->apdev;
-	skb_pull(skb, hostap_80211_get_hdrlen(hdr->frame_control));
-	skb->pkt_type = PACKET_OTHERHOST;
-	skb->protocol = cpu_to_be16(ETH_P_802_2);
-	memset(skb->cb, 0, sizeof(skb->cb));
-	netif_rx(skb);
-}
-
-
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-/* Called only as a tasklet (software IRQ) */
-static void hostap_ap_tx_cb_auth(struct sk_buff *skb, int ok, void *data)
-{
-	struct ap_data *ap = data;
-	struct net_device *dev = ap->local->dev;
-	struct ieee80211_hdr *hdr;
-	u16 auth_alg, auth_transaction, status;
-	__le16 *pos;
-	struct sta_info *sta = NULL;
-	char *txt = NULL;
-
-	if (ap->local->hostapd) {
-		dev_kfree_skb(skb);
-		return;
-	}
-
-	hdr = (struct ieee80211_hdr *) skb->data;
-	if (!ieee80211_is_auth(hdr->frame_control) ||
-	    skb->len < IEEE80211_MGMT_HDR_LEN + 6) {
-		printk(KERN_DEBUG "%s: hostap_ap_tx_cb_auth received invalid "
-		       "frame\n", dev->name);
-		dev_kfree_skb(skb);
-		return;
-	}
-
-	pos = (__le16 *) (skb->data + IEEE80211_MGMT_HDR_LEN);
-	auth_alg = le16_to_cpu(*pos++);
-	auth_transaction = le16_to_cpu(*pos++);
-	status = le16_to_cpu(*pos++);
-
-	if (!ok) {
-		txt = "frame was not ACKed";
-		goto done;
-	}
-
-	spin_lock(&ap->sta_table_lock);
-	sta = ap_get_sta(ap, hdr->addr1);
-	if (sta)
-		atomic_inc(&sta->users);
-	spin_unlock(&ap->sta_table_lock);
-
-	if (!sta) {
-		txt = "STA not found";
-		goto done;
-	}
-
-	if (status == WLAN_STATUS_SUCCESS &&
-	    ((auth_alg == WLAN_AUTH_OPEN && auth_transaction == 2) ||
-	     (auth_alg == WLAN_AUTH_SHARED_KEY && auth_transaction == 4))) {
-		txt = "STA authenticated";
-		sta->flags |= WLAN_STA_AUTH;
-		sta->last_auth = jiffies;
-	} else if (status != WLAN_STATUS_SUCCESS)
-		txt = "authentication failed";
-
- done:
-	if (sta)
-		atomic_dec(&sta->users);
-	if (txt) {
-		PDEBUG(DEBUG_AP, "%s: %pM auth_cb - alg=%d "
-		       "trans#=%d status=%d - %s\n",
-		       dev->name, hdr->addr1,
-		       auth_alg, auth_transaction, status, txt);
-	}
-	dev_kfree_skb(skb);
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static void hostap_ap_tx_cb_assoc(struct sk_buff *skb, int ok, void *data)
-{
-	struct ap_data *ap = data;
-	struct net_device *dev = ap->local->dev;
-	struct ieee80211_hdr *hdr;
-	u16 status;
-	__le16 *pos;
-	struct sta_info *sta = NULL;
-	char *txt = NULL;
-
-	if (ap->local->hostapd) {
-		dev_kfree_skb(skb);
-		return;
-	}
-
-	hdr = (struct ieee80211_hdr *) skb->data;
-	if ((!ieee80211_is_assoc_resp(hdr->frame_control) &&
-	     !ieee80211_is_reassoc_resp(hdr->frame_control)) ||
-	    skb->len < IEEE80211_MGMT_HDR_LEN + 4) {
-		printk(KERN_DEBUG "%s: hostap_ap_tx_cb_assoc received invalid "
-		       "frame\n", dev->name);
-		dev_kfree_skb(skb);
-		return;
-	}
-
-	if (!ok) {
-		txt = "frame was not ACKed";
-		goto done;
-	}
-
-	spin_lock(&ap->sta_table_lock);
-	sta = ap_get_sta(ap, hdr->addr1);
-	if (sta)
-		atomic_inc(&sta->users);
-	spin_unlock(&ap->sta_table_lock);
-
-	if (!sta) {
-		txt = "STA not found";
-		goto done;
-	}
-
-	pos = (__le16 *) (skb->data + IEEE80211_MGMT_HDR_LEN);
-	pos++;
-	status = le16_to_cpu(*pos++);
-	if (status == WLAN_STATUS_SUCCESS) {
-		if (!(sta->flags & WLAN_STA_ASSOC))
-			hostap_event_new_sta(dev, sta);
-		txt = "STA associated";
-		sta->flags |= WLAN_STA_ASSOC;
-		sta->last_assoc = jiffies;
-	} else
-		txt = "association failed";
-
- done:
-	if (sta)
-		atomic_dec(&sta->users);
-	if (txt) {
-		PDEBUG(DEBUG_AP, "%s: %pM assoc_cb - %s\n",
-		       dev->name, hdr->addr1, txt);
-	}
-	dev_kfree_skb(skb);
-}
-
-/* Called only as a tasklet (software IRQ); TX callback for poll frames used
- * in verifying whether the STA is still present. */
-static void hostap_ap_tx_cb_poll(struct sk_buff *skb, int ok, void *data)
-{
-	struct ap_data *ap = data;
-	struct ieee80211_hdr *hdr;
-	struct sta_info *sta;
-
-	if (skb->len < 24)
-		goto fail;
-	hdr = (struct ieee80211_hdr *) skb->data;
-	if (ok) {
-		spin_lock(&ap->sta_table_lock);
-		sta = ap_get_sta(ap, hdr->addr1);
-		if (sta)
-			sta->flags &= ~WLAN_STA_PENDING_POLL;
-		spin_unlock(&ap->sta_table_lock);
-	} else {
-		PDEBUG(DEBUG_AP,
-		       "%s: STA %pM did not ACK activity poll frame\n",
-		       ap->local->dev->name, hdr->addr1);
-	}
-
- fail:
-	dev_kfree_skb(skb);
-}
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-
-
-void hostap_init_data(local_info_t *local)
-{
-	struct ap_data *ap = local->ap;
-
-	if (ap == NULL) {
-		printk(KERN_WARNING "hostap_init_data: ap == NULL\n");
-		return;
-	}
-	memset(ap, 0, sizeof(struct ap_data));
-	ap->local = local;
-
-	ap->ap_policy = GET_INT_PARM(other_ap_policy, local->card_idx);
-	ap->bridge_packets = GET_INT_PARM(ap_bridge_packets, local->card_idx);
-	ap->max_inactivity =
-		GET_INT_PARM(ap_max_inactivity, local->card_idx) * HZ;
-	ap->autom_ap_wds = GET_INT_PARM(autom_ap_wds, local->card_idx);
-
-	spin_lock_init(&ap->sta_table_lock);
-	INIT_LIST_HEAD(&ap->sta_list);
-
-	/* Initialize task queue structure for AP management */
-	INIT_WORK(&local->ap->add_sta_proc_queue, handle_add_proc_queue);
-
-	ap->tx_callback_idx =
-		hostap_tx_callback_register(local, hostap_ap_tx_cb, ap);
-	if (ap->tx_callback_idx == 0)
-		printk(KERN_WARNING "%s: failed to register TX callback for "
-		       "AP\n", local->dev->name);
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-	INIT_WORK(&local->ap->wds_oper_queue, handle_wds_oper_queue);
-
-	ap->tx_callback_auth =
-		hostap_tx_callback_register(local, hostap_ap_tx_cb_auth, ap);
-	ap->tx_callback_assoc =
-		hostap_tx_callback_register(local, hostap_ap_tx_cb_assoc, ap);
-	ap->tx_callback_poll =
-		hostap_tx_callback_register(local, hostap_ap_tx_cb_poll, ap);
-	if (ap->tx_callback_auth == 0 || ap->tx_callback_assoc == 0 ||
-		ap->tx_callback_poll == 0)
-		printk(KERN_WARNING "%s: failed to register TX callback for "
-		       "AP\n", local->dev->name);
-
-	spin_lock_init(&ap->mac_restrictions.lock);
-	INIT_LIST_HEAD(&ap->mac_restrictions.mac_list);
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-
-	ap->initialized = 1;
-}
-
-
-void hostap_init_ap_proc(local_info_t *local)
-{
-	struct ap_data *ap = local->ap;
-
-	ap->proc = local->proc;
-	if (ap->proc == NULL)
-		return;
-
-#ifndef PRISM2_NO_PROCFS_DEBUG
-	proc_create_single_data("ap_debug", 0, ap->proc, ap_debug_proc_show, ap);
-#endif /* PRISM2_NO_PROCFS_DEBUG */
-
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-	proc_create_seq_data("ap_control", 0, ap->proc, &ap_control_proc_seqops,
-			ap);
-	proc_create_seq_data("ap", 0, ap->proc, &prism2_ap_proc_seqops, ap);
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-
-}
-
-
-void hostap_free_data(struct ap_data *ap)
-{
-	struct sta_info *n, *sta;
-
-	if (ap == NULL || !ap->initialized) {
-		printk(KERN_DEBUG "hostap_free_data: ap has not yet been "
-		       "initialized - skip resource freeing\n");
-		return;
-	}
-
-	flush_work(&ap->add_sta_proc_queue);
-
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-	flush_work(&ap->wds_oper_queue);
-	if (ap->crypt)
-		ap->crypt->deinit(ap->crypt_priv);
-	ap->crypt = ap->crypt_priv = NULL;
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-
-	list_for_each_entry_safe(sta, n, &ap->sta_list, list) {
-		ap_sta_hash_del(ap, sta);
-		list_del(&sta->list);
-		if ((sta->flags & WLAN_STA_ASSOC) && !sta->ap && sta->local)
-			hostap_event_expired_sta(sta->local->dev, sta);
-		ap_free_sta(ap, sta);
-	}
-
-#ifndef PRISM2_NO_PROCFS_DEBUG
-	if (ap->proc != NULL) {
-		remove_proc_entry("ap_debug", ap->proc);
-	}
-#endif /* PRISM2_NO_PROCFS_DEBUG */
-
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-	if (ap->proc != NULL) {
-	  remove_proc_entry("ap", ap->proc);
-		remove_proc_entry("ap_control", ap->proc);
-	}
-	ap_control_flush_macs(&ap->mac_restrictions);
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-
-	ap->initialized = 0;
-}
-
-
-/* caller should have mutex for AP STA list handling */
-static struct sta_info* ap_get_sta(struct ap_data *ap, u8 *sta)
-{
-	struct sta_info *s;
-
-	s = ap->sta_hash[STA_HASH(sta)];
-	while (s != NULL && !ether_addr_equal(s->addr, sta))
-		s = s->hnext;
-	return s;
-}
-
-
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-
-/* Called from timer handler and from scheduled AP queue handlers */
-static void prism2_send_mgmt(struct net_device *dev,
-			     u16 type_subtype, char *body,
-			     int body_len, u8 *addr, u16 tx_cb_idx)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	struct ieee80211_hdr *hdr;
-	u16 fc;
-	struct sk_buff *skb;
-	struct hostap_skb_tx_data *meta;
-	int hdrlen;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-	dev = local->dev; /* always use master radio device */
-	iface = netdev_priv(dev);
-
-	if (!(dev->flags & IFF_UP)) {
-		PDEBUG(DEBUG_AP, "%s: prism2_send_mgmt - device is not UP - "
-		       "cannot send frame\n", dev->name);
-		return;
-	}
-
-	skb = dev_alloc_skb(sizeof(*hdr) + body_len);
-	if (skb == NULL) {
-		PDEBUG(DEBUG_AP, "%s: prism2_send_mgmt failed to allocate "
-		       "skb\n", dev->name);
-		return;
-	}
-
-	fc = type_subtype;
-	hdrlen = hostap_80211_get_hdrlen(cpu_to_le16(type_subtype));
-	hdr = skb_put_zero(skb, hdrlen);
-	if (body)
-		skb_put_data(skb, body, body_len);
-
-	/* FIX: ctrl::ack sending used special HFA384X_TX_CTRL_802_11
-	 * tx_control instead of using local->tx_control */
-
-
-	memcpy(hdr->addr1, addr, ETH_ALEN); /* DA / RA */
-	if (ieee80211_is_data(hdr->frame_control)) {
-		fc |= IEEE80211_FCTL_FROMDS;
-		memcpy(hdr->addr2, dev->dev_addr, ETH_ALEN); /* BSSID */
-		memcpy(hdr->addr3, dev->dev_addr, ETH_ALEN); /* SA */
-	} else if (ieee80211_is_ctl(hdr->frame_control)) {
-		/* control:ACK does not have addr2 or addr3 */
-		eth_zero_addr(hdr->addr2);
-		eth_zero_addr(hdr->addr3);
-	} else {
-		memcpy(hdr->addr2, dev->dev_addr, ETH_ALEN); /* SA */
-		memcpy(hdr->addr3, dev->dev_addr, ETH_ALEN); /* BSSID */
-	}
-
-	hdr->frame_control = cpu_to_le16(fc);
-
-	meta = (struct hostap_skb_tx_data *) skb->cb;
-	memset(meta, 0, sizeof(*meta));
-	meta->magic = HOSTAP_SKB_TX_DATA_MAGIC;
-	meta->iface = iface;
-	meta->tx_cb_idx = tx_cb_idx;
-
-	skb->dev = dev;
-	skb_reset_mac_header(skb);
-	skb_reset_network_header(skb);
-	dev_queue_xmit(skb);
-}
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-
-#ifdef CONFIG_PROC_FS
-static int prism2_sta_proc_show(struct seq_file *m, void *v)
-{
-	struct sta_info *sta = m->private;
-	int i;
-
-	/* FIX: possible race condition.. the STA data could have just expired,
-	 * but proc entry was still here so that the read could have started;
-	 * some locking should be done here.. */
-
-	seq_printf(m,
-		   "%s=%pM\nusers=%d\naid=%d\n"
-		   "flags=0x%04x%s%s%s%s%s%s%s\n"
-		   "capability=0x%02x\nlisten_interval=%d\nsupported_rates=",
-		   sta->ap ? "AP" : "STA",
-		   sta->addr, atomic_read(&sta->users), sta->aid,
-		   sta->flags,
-		   sta->flags & WLAN_STA_AUTH ? " AUTH" : "",
-		   sta->flags & WLAN_STA_ASSOC ? " ASSOC" : "",
-		   sta->flags & WLAN_STA_PS ? " PS" : "",
-		   sta->flags & WLAN_STA_TIM ? " TIM" : "",
-		   sta->flags & WLAN_STA_PERM ? " PERM" : "",
-		   sta->flags & WLAN_STA_AUTHORIZED ? " AUTHORIZED" : "",
-		   sta->flags & WLAN_STA_PENDING_POLL ? " POLL" : "",
-		   sta->capability, sta->listen_interval);
-	/* supported_rates: 500 kbit/s units with msb ignored */
-	for (i = 0; i < sizeof(sta->supported_rates); i++)
-		if (sta->supported_rates[i] != 0)
-			seq_printf(m, "%d%sMbps ",
-				   (sta->supported_rates[i] & 0x7f) / 2,
-				   sta->supported_rates[i] & 1 ? ".5" : "");
-	seq_printf(m,
-		   "\njiffies=%lu\nlast_auth=%lu\nlast_assoc=%lu\n"
-		   "last_rx=%lu\nlast_tx=%lu\nrx_packets=%lu\n"
-		   "tx_packets=%lu\n"
-		   "rx_bytes=%lu\ntx_bytes=%lu\nbuffer_count=%d\n"
-		   "last_rx: silence=%d dBm signal=%d dBm rate=%d%s Mbps\n"
-		   "tx_rate=%d\ntx[1M]=%d\ntx[2M]=%d\ntx[5.5M]=%d\n"
-		   "tx[11M]=%d\n"
-		   "rx[1M]=%d\nrx[2M]=%d\nrx[5.5M]=%d\nrx[11M]=%d\n",
-		   jiffies, sta->last_auth, sta->last_assoc, sta->last_rx,
-		   sta->last_tx,
-		   sta->rx_packets, sta->tx_packets, sta->rx_bytes,
-		   sta->tx_bytes, skb_queue_len(&sta->tx_buf),
-		   sta->last_rx_silence,
-		   sta->last_rx_signal, sta->last_rx_rate / 10,
-		   sta->last_rx_rate % 10 ? ".5" : "",
-		   sta->tx_rate, sta->tx_count[0], sta->tx_count[1],
-		   sta->tx_count[2], sta->tx_count[3],  sta->rx_count[0],
-		   sta->rx_count[1], sta->rx_count[2], sta->rx_count[3]);
-	if (sta->crypt && sta->crypt->ops && sta->crypt->ops->print_stats)
-		sta->crypt->ops->print_stats(m, sta->crypt->priv);
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-	if (sta->ap) {
-		if (sta->u.ap.channel >= 0)
-			seq_printf(m, "channel=%d\n", sta->u.ap.channel);
-		seq_puts(m, "ssid=");
-		for (i = 0; i < sta->u.ap.ssid_len; i++) {
-			if (sta->u.ap.ssid[i] >= 32 && sta->u.ap.ssid[i] < 127)
-				seq_putc(m, sta->u.ap.ssid[i]);
-			else
-				seq_printf(m, "<%02x>", sta->u.ap.ssid[i]);
-		}
-		seq_putc(m, '\n');
-	}
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-
-	return 0;
-}
-#endif
-
-static void handle_add_proc_queue(struct work_struct *work)
-{
-	struct ap_data *ap = container_of(work, struct ap_data,
-					  add_sta_proc_queue);
-	struct sta_info *sta;
-	char name[20];
-	struct add_sta_proc_data *entry, *prev;
-
-	entry = ap->add_sta_proc_entries;
-	ap->add_sta_proc_entries = NULL;
-
-	while (entry) {
-		spin_lock_bh(&ap->sta_table_lock);
-		sta = ap_get_sta(ap, entry->addr);
-		if (sta)
-			atomic_inc(&sta->users);
-		spin_unlock_bh(&ap->sta_table_lock);
-
-		if (sta) {
-			sprintf(name, "%pM", sta->addr);
-			sta->proc = proc_create_single_data(
-				name, 0, ap->proc,
-				prism2_sta_proc_show, sta);
-
-			atomic_dec(&sta->users);
-		}
-
-		prev = entry;
-		entry = entry->next;
-		kfree(prev);
-	}
-}
-
-
-static struct sta_info * ap_add_sta(struct ap_data *ap, u8 *addr)
-{
-	struct sta_info *sta;
-
-	sta = kzalloc(sizeof(struct sta_info), GFP_ATOMIC);
-	if (sta == NULL) {
-		PDEBUG(DEBUG_AP, "AP: kmalloc failed\n");
-		return NULL;
-	}
-
-	/* initialize STA info data */
-	sta->local = ap->local;
-	skb_queue_head_init(&sta->tx_buf);
-	memcpy(sta->addr, addr, ETH_ALEN);
-
-	atomic_inc(&sta->users);
-	spin_lock_bh(&ap->sta_table_lock);
-	list_add(&sta->list, &ap->sta_list);
-	ap->num_sta++;
-	ap_sta_hash_add(ap, sta);
-	spin_unlock_bh(&ap->sta_table_lock);
-
-	if (ap->proc) {
-		struct add_sta_proc_data *entry;
-		/* schedule a non-interrupt context process to add a procfs
-		 * entry for the STA since procfs code use GFP_KERNEL */
-		entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
-		if (entry) {
-			memcpy(entry->addr, sta->addr, ETH_ALEN);
-			entry->next = ap->add_sta_proc_entries;
-			ap->add_sta_proc_entries = entry;
-			schedule_work(&ap->add_sta_proc_queue);
-		} else
-			printk(KERN_DEBUG "Failed to add STA proc data\n");
-	}
-
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-	timer_setup(&sta->timer, ap_handle_timer, 0);
-	sta->timer.expires = jiffies + ap->max_inactivity;
-	if (!ap->local->hostapd)
-		add_timer(&sta->timer);
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-
-	return sta;
-}
-
-
-static int ap_tx_rate_ok(int rateidx, struct sta_info *sta,
-			 local_info_t *local)
-{
-	if (rateidx > sta->tx_max_rate ||
-	    !(sta->tx_supp_rates & (1 << rateidx)))
-		return 0;
-
-	if (local->tx_rate_control != 0 &&
-	    !(local->tx_rate_control & (1 << rateidx)))
-		return 0;
-
-	return 1;
-}
-
-
-static void prism2_check_tx_rates(struct sta_info *sta)
-{
-	int i;
-
-	sta->tx_supp_rates = 0;
-	for (i = 0; i < sizeof(sta->supported_rates); i++) {
-		if ((sta->supported_rates[i] & 0x7f) == 2)
-			sta->tx_supp_rates |= WLAN_RATE_1M;
-		if ((sta->supported_rates[i] & 0x7f) == 4)
-			sta->tx_supp_rates |= WLAN_RATE_2M;
-		if ((sta->supported_rates[i] & 0x7f) == 11)
-			sta->tx_supp_rates |= WLAN_RATE_5M5;
-		if ((sta->supported_rates[i] & 0x7f) == 22)
-			sta->tx_supp_rates |= WLAN_RATE_11M;
-	}
-	sta->tx_max_rate = sta->tx_rate = sta->tx_rate_idx = 0;
-	if (sta->tx_supp_rates & WLAN_RATE_1M) {
-		sta->tx_max_rate = 0;
-		if (ap_tx_rate_ok(0, sta, sta->local)) {
-			sta->tx_rate = 10;
-			sta->tx_rate_idx = 0;
-		}
-	}
-	if (sta->tx_supp_rates & WLAN_RATE_2M) {
-		sta->tx_max_rate = 1;
-		if (ap_tx_rate_ok(1, sta, sta->local)) {
-			sta->tx_rate = 20;
-			sta->tx_rate_idx = 1;
-		}
-	}
-	if (sta->tx_supp_rates & WLAN_RATE_5M5) {
-		sta->tx_max_rate = 2;
-		if (ap_tx_rate_ok(2, sta, sta->local)) {
-			sta->tx_rate = 55;
-			sta->tx_rate_idx = 2;
-		}
-	}
-	if (sta->tx_supp_rates & WLAN_RATE_11M) {
-		sta->tx_max_rate = 3;
-		if (ap_tx_rate_ok(3, sta, sta->local)) {
-			sta->tx_rate = 110;
-			sta->tx_rate_idx = 3;
-		}
-	}
-}
-
-
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-
-static void ap_crypt_init(struct ap_data *ap)
-{
-	ap->crypt = lib80211_get_crypto_ops("WEP");
-
-	if (ap->crypt) {
-		if (ap->crypt->init) {
-			ap->crypt_priv = ap->crypt->init(0);
-			if (ap->crypt_priv == NULL)
-				ap->crypt = NULL;
-			else {
-				u8 key[WEP_KEY_LEN];
-				get_random_bytes(key, WEP_KEY_LEN);
-				ap->crypt->set_key(key, WEP_KEY_LEN, NULL,
-						   ap->crypt_priv);
-			}
-		}
-	}
-
-	if (ap->crypt == NULL) {
-		printk(KERN_WARNING "AP could not initialize WEP: load module "
-		       "lib80211_crypt_wep.ko\n");
-	}
-}
-
-
-/* Generate challenge data for shared key authentication. IEEE 802.11 specifies
- * that WEP algorithm is used for generating challenge. This should be unique,
- * but otherwise there is not really need for randomness etc. Initialize WEP
- * with pseudo random key and then use increasing IV to get unique challenge
- * streams.
- *
- * Called only as a scheduled task for pending AP frames.
- */
-static char * ap_auth_make_challenge(struct ap_data *ap)
-{
-	char *tmpbuf;
-	struct sk_buff *skb;
-
-	if (ap->crypt == NULL) {
-		ap_crypt_init(ap);
-		if (ap->crypt == NULL)
-			return NULL;
-	}
-
-	tmpbuf = kmalloc(WLAN_AUTH_CHALLENGE_LEN, GFP_ATOMIC);
-	if (tmpbuf == NULL) {
-		PDEBUG(DEBUG_AP, "AP: kmalloc failed for challenge\n");
-		return NULL;
-	}
-
-	skb = dev_alloc_skb(WLAN_AUTH_CHALLENGE_LEN +
-			    ap->crypt->extra_mpdu_prefix_len +
-			    ap->crypt->extra_mpdu_postfix_len);
-	if (skb == NULL) {
-		kfree(tmpbuf);
-		return NULL;
-	}
-
-	skb_reserve(skb, ap->crypt->extra_mpdu_prefix_len);
-	skb_put_zero(skb, WLAN_AUTH_CHALLENGE_LEN);
-	if (ap->crypt->encrypt_mpdu(skb, 0, ap->crypt_priv)) {
-		dev_kfree_skb(skb);
-		kfree(tmpbuf);
-		return NULL;
-	}
-
-	skb_copy_from_linear_data_offset(skb, ap->crypt->extra_mpdu_prefix_len,
-					 tmpbuf, WLAN_AUTH_CHALLENGE_LEN);
-	dev_kfree_skb(skb);
-
-	return tmpbuf;
-}
-
-
-/* Called only as a scheduled task for pending AP frames. */
-static void handle_authen(local_info_t *local, struct sk_buff *skb,
-			  struct hostap_80211_rx_status *rx_stats)
-{
-	struct net_device *dev = local->dev;
-	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
-	size_t hdrlen;
-	struct ap_data *ap = local->ap;
-	char body[8 + WLAN_AUTH_CHALLENGE_LEN], *challenge = NULL;
-	int len, olen;
-	u16 auth_alg, auth_transaction, status_code;
-	__le16 *pos;
-	u16 resp = WLAN_STATUS_SUCCESS;
-	struct sta_info *sta = NULL;
-	struct lib80211_crypt_data *crypt;
-	char *txt = "";
-
-	len = skb->len - IEEE80211_MGMT_HDR_LEN;
-
-	hdrlen = hostap_80211_get_hdrlen(hdr->frame_control);
-
-	if (len < 6) {
-		PDEBUG(DEBUG_AP, "%s: handle_authen - too short payload "
-		       "(len=%d) from %pM\n", dev->name, len, hdr->addr2);
-		return;
-	}
-
-	spin_lock_bh(&local->ap->sta_table_lock);
-	sta = ap_get_sta(local->ap, hdr->addr2);
-	if (sta)
-		atomic_inc(&sta->users);
-	spin_unlock_bh(&local->ap->sta_table_lock);
-
-	if (sta && sta->crypt)
-		crypt = sta->crypt;
-	else {
-		int idx = 0;
-		if (skb->len >= hdrlen + 3)
-			idx = skb->data[hdrlen + 3] >> 6;
-		crypt = local->crypt_info.crypt[idx];
-	}
-
-	pos = (__le16 *) (skb->data + IEEE80211_MGMT_HDR_LEN);
-	auth_alg = __le16_to_cpu(*pos);
-	pos++;
-	auth_transaction = __le16_to_cpu(*pos);
-	pos++;
-	status_code = __le16_to_cpu(*pos);
-	pos++;
-
-	if (ether_addr_equal(dev->dev_addr, hdr->addr2) ||
-	    ap_control_mac_deny(&ap->mac_restrictions, hdr->addr2)) {
-		txt = "authentication denied";
-		resp = WLAN_STATUS_UNSPECIFIED_FAILURE;
-		goto fail;
-	}
-
-	if (((local->auth_algs & PRISM2_AUTH_OPEN) &&
-	     auth_alg == WLAN_AUTH_OPEN) ||
-	    ((local->auth_algs & PRISM2_AUTH_SHARED_KEY) &&
-	     crypt && auth_alg == WLAN_AUTH_SHARED_KEY)) {
-	} else {
-		txt = "unsupported algorithm";
-		resp = WLAN_STATUS_NOT_SUPPORTED_AUTH_ALG;
-		goto fail;
-	}
-
-	if (len >= 8) {
-		u8 *u = (u8 *) pos;
-		if (*u == WLAN_EID_CHALLENGE) {
-			if (*(u + 1) != WLAN_AUTH_CHALLENGE_LEN) {
-				txt = "invalid challenge len";
-				resp = WLAN_STATUS_CHALLENGE_FAIL;
-				goto fail;
-			}
-			if (len - 8 < WLAN_AUTH_CHALLENGE_LEN) {
-				txt = "challenge underflow";
-				resp = WLAN_STATUS_CHALLENGE_FAIL;
-				goto fail;
-			}
-			challenge = (char *) (u + 2);
-		}
-	}
-
-	if (sta && sta->ap) {
-		if (time_after(jiffies, sta->u.ap.last_beacon +
-			       (10 * sta->listen_interval * HZ) / 1024)) {
-			PDEBUG(DEBUG_AP, "%s: no beacons received for a while,"
-			       " assuming AP %pM is now STA\n",
-			       dev->name, sta->addr);
-			sta->ap = 0;
-			sta->flags = 0;
-			sta->u.sta.challenge = NULL;
-		} else {
-			txt = "AP trying to authenticate?";
-			resp = WLAN_STATUS_UNSPECIFIED_FAILURE;
-			goto fail;
-		}
-	}
-
-	if ((auth_alg == WLAN_AUTH_OPEN && auth_transaction == 1) ||
-	    (auth_alg == WLAN_AUTH_SHARED_KEY &&
-	     (auth_transaction == 1 ||
-	      (auth_transaction == 3 && sta != NULL &&
-	       sta->u.sta.challenge != NULL)))) {
-	} else {
-		txt = "unknown authentication transaction number";
-		resp = WLAN_STATUS_UNKNOWN_AUTH_TRANSACTION;
-		goto fail;
-	}
-
-	if (sta == NULL) {
-		txt = "new STA";
-
-		if (local->ap->num_sta >= MAX_STA_COUNT) {
-			/* FIX: might try to remove some old STAs first? */
-			txt = "no more room for new STAs";
-			resp = WLAN_STATUS_UNSPECIFIED_FAILURE;
-			goto fail;
-		}
-
-		sta = ap_add_sta(local->ap, hdr->addr2);
-		if (sta == NULL) {
-			txt = "ap_add_sta failed";
-			resp = WLAN_STATUS_UNSPECIFIED_FAILURE;
-			goto fail;
-		}
-	}
-
-	switch (auth_alg) {
-	case WLAN_AUTH_OPEN:
-		txt = "authOK";
-		/* IEEE 802.11 standard is not completely clear about
-		 * whether STA is considered authenticated after
-		 * authentication OK frame has been send or after it
-		 * has been ACKed. In order to reduce interoperability
-		 * issues, mark the STA authenticated before ACK. */
-		sta->flags |= WLAN_STA_AUTH;
-		break;
-
-	case WLAN_AUTH_SHARED_KEY:
-		if (auth_transaction == 1) {
-			if (sta->u.sta.challenge == NULL) {
-				sta->u.sta.challenge =
-					ap_auth_make_challenge(local->ap);
-				if (sta->u.sta.challenge == NULL) {
-					resp = WLAN_STATUS_UNSPECIFIED_FAILURE;
-					goto fail;
-				}
-			}
-		} else {
-			if (sta->u.sta.challenge == NULL ||
-			    challenge == NULL ||
-			    memcmp(sta->u.sta.challenge, challenge,
-				   WLAN_AUTH_CHALLENGE_LEN) != 0 ||
-			    !ieee80211_has_protected(hdr->frame_control)) {
-				txt = "challenge response incorrect";
-				resp = WLAN_STATUS_CHALLENGE_FAIL;
-				goto fail;
-			}
-
-			txt = "challenge OK - authOK";
-			/* IEEE 802.11 standard is not completely clear about
-			 * whether STA is considered authenticated after
-			 * authentication OK frame has been send or after it
-			 * has been ACKed. In order to reduce interoperability
-			 * issues, mark the STA authenticated before ACK. */
-			sta->flags |= WLAN_STA_AUTH;
-			kfree(sta->u.sta.challenge);
-			sta->u.sta.challenge = NULL;
-		}
-		break;
-	}
-
- fail:
-	pos = (__le16 *) body;
-	*pos = cpu_to_le16(auth_alg);
-	pos++;
-	*pos = cpu_to_le16(auth_transaction + 1);
-	pos++;
-	*pos = cpu_to_le16(resp); /* status_code */
-	pos++;
-	olen = 6;
-
-	if (resp == WLAN_STATUS_SUCCESS && sta != NULL &&
-	    sta->u.sta.challenge != NULL &&
-	    auth_alg == WLAN_AUTH_SHARED_KEY && auth_transaction == 1) {
-		u8 *tmp = (u8 *) pos;
-		*tmp++ = WLAN_EID_CHALLENGE;
-		*tmp++ = WLAN_AUTH_CHALLENGE_LEN;
-		pos++;
-		memcpy(pos, sta->u.sta.challenge, WLAN_AUTH_CHALLENGE_LEN);
-		olen += 2 + WLAN_AUTH_CHALLENGE_LEN;
-	}
-
-	prism2_send_mgmt(dev, IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_AUTH,
-			 body, olen, hdr->addr2, ap->tx_callback_auth);
-
-	if (sta) {
-		sta->last_rx = jiffies;
-		atomic_dec(&sta->users);
-	}
-
-	if (resp) {
-		PDEBUG(DEBUG_AP, "%s: %pM auth (alg=%d "
-		       "trans#=%d stat=%d len=%d fc=%04x) ==> %d (%s)\n",
-		       dev->name, hdr->addr2,
-		       auth_alg, auth_transaction, status_code, len,
-		       le16_to_cpu(hdr->frame_control), resp, txt);
-	}
-}
-
-
-/* Called only as a scheduled task for pending AP frames. */
-static void handle_assoc(local_info_t *local, struct sk_buff *skb,
-			 struct hostap_80211_rx_status *rx_stats, int reassoc)
-{
-	struct net_device *dev = local->dev;
-	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
-	char body[12], *p, *lpos;
-	int len, left;
-	__le16 *pos;
-	u16 resp = WLAN_STATUS_SUCCESS;
-	struct sta_info *sta = NULL;
-	int send_deauth = 0;
-	char __always_unused *txt = "";
-	u8 prev_ap[ETH_ALEN];
-
-	left = len = skb->len - IEEE80211_MGMT_HDR_LEN;
-
-	if (len < (reassoc ? 10 : 4)) {
-		PDEBUG(DEBUG_AP, "%s: handle_assoc - too short payload "
-		       "(len=%d, reassoc=%d) from %pM\n",
-		       dev->name, len, reassoc, hdr->addr2);
-		return;
-	}
-
-	spin_lock_bh(&local->ap->sta_table_lock);
-	sta = ap_get_sta(local->ap, hdr->addr2);
-	if (sta == NULL || (sta->flags & WLAN_STA_AUTH) == 0) {
-		spin_unlock_bh(&local->ap->sta_table_lock);
-		txt = "trying to associate before authentication";
-		send_deauth = 1;
-		resp = WLAN_STATUS_UNSPECIFIED_FAILURE;
-		sta = NULL; /* do not decrement sta->users */
-		goto fail;
-	}
-	atomic_inc(&sta->users);
-	spin_unlock_bh(&local->ap->sta_table_lock);
-
-	pos = (__le16 *) (skb->data + IEEE80211_MGMT_HDR_LEN);
-	sta->capability = __le16_to_cpu(*pos);
-	pos++; left -= 2;
-	sta->listen_interval = __le16_to_cpu(*pos);
-	pos++; left -= 2;
-
-	if (reassoc) {
-		memcpy(prev_ap, pos, ETH_ALEN);
-		pos++; pos++; pos++; left -= 6;
-	} else
-		eth_zero_addr(prev_ap);
-
-	if (left >= 2) {
-		unsigned int ileft;
-		unsigned char *u = (unsigned char *) pos;
-
-		if (*u == WLAN_EID_SSID) {
-			u++; left--;
-			ileft = *u;
-			u++; left--;
-
-			if (ileft > left || ileft > MAX_SSID_LEN) {
-				txt = "SSID overflow";
-				resp = WLAN_STATUS_UNSPECIFIED_FAILURE;
-				goto fail;
-			}
-
-			if (ileft != strlen(local->essid) ||
-			    memcmp(local->essid, u, ileft) != 0) {
-				txt = "not our SSID";
-				resp = WLAN_STATUS_ASSOC_DENIED_UNSPEC;
-				goto fail;
-			}
-
-			u += ileft;
-			left -= ileft;
-		}
-
-		if (left >= 2 && *u == WLAN_EID_SUPP_RATES) {
-			u++; left--;
-			ileft = *u;
-			u++; left--;
-
-			if (ileft > left || ileft == 0 ||
-			    ileft > WLAN_SUPP_RATES_MAX) {
-				txt = "SUPP_RATES len error";
-				resp = WLAN_STATUS_UNSPECIFIED_FAILURE;
-				goto fail;
-			}
-
-			memset(sta->supported_rates, 0,
-			       sizeof(sta->supported_rates));
-			memcpy(sta->supported_rates, u, ileft);
-			prism2_check_tx_rates(sta);
-
-			u += ileft;
-			left -= ileft;
-		}
-
-		if (left > 0) {
-			PDEBUG(DEBUG_AP, "%s: assoc from %pM"
-			       " with extra data (%d bytes) [",
-			       dev->name, hdr->addr2, left);
-			while (left > 0) {
-				PDEBUG2(DEBUG_AP, "<%02x>", *u);
-				u++; left--;
-			}
-			PDEBUG2(DEBUG_AP, "]\n");
-		}
-	} else {
-		txt = "frame underflow";
-		resp = WLAN_STATUS_UNSPECIFIED_FAILURE;
-		goto fail;
-	}
-
-	/* get a unique AID */
-	if (sta->aid > 0)
-		txt = "OK, old AID";
-	else {
-		spin_lock_bh(&local->ap->sta_table_lock);
-		for (sta->aid = 1; sta->aid <= MAX_AID_TABLE_SIZE; sta->aid++)
-			if (local->ap->sta_aid[sta->aid - 1] == NULL)
-				break;
-		if (sta->aid > MAX_AID_TABLE_SIZE) {
-			sta->aid = 0;
-			spin_unlock_bh(&local->ap->sta_table_lock);
-			resp = WLAN_STATUS_AP_UNABLE_TO_HANDLE_NEW_STA;
-			txt = "no room for more AIDs";
-		} else {
-			local->ap->sta_aid[sta->aid - 1] = sta;
-			spin_unlock_bh(&local->ap->sta_table_lock);
-			txt = "OK, new AID";
-		}
-	}
-
- fail:
-	pos = (__le16 *) body;
-
-	if (send_deauth) {
-		*pos = cpu_to_le16(WLAN_REASON_STA_REQ_ASSOC_WITHOUT_AUTH);
-		pos++;
-	} else {
-		/* FIX: CF-Pollable and CF-PollReq should be set to match the
-		 * values in beacons/probe responses */
-		/* FIX: how about privacy and WEP? */
-		/* capability */
-		*pos = cpu_to_le16(WLAN_CAPABILITY_ESS);
-		pos++;
-
-		/* status_code */
-		*pos = cpu_to_le16(resp);
-		pos++;
-
-		*pos = cpu_to_le16((sta && sta->aid > 0 ? sta->aid : 0) |
-				     BIT(14) | BIT(15)); /* AID */
-		pos++;
-
-		/* Supported rates (Information element) */
-		p = (char *) pos;
-		*p++ = WLAN_EID_SUPP_RATES;
-		lpos = p;
-		*p++ = 0; /* len */
-		if (local->tx_rate_control & WLAN_RATE_1M) {
-			*p++ = local->basic_rates & WLAN_RATE_1M ? 0x82 : 0x02;
-			(*lpos)++;
-		}
-		if (local->tx_rate_control & WLAN_RATE_2M) {
-			*p++ = local->basic_rates & WLAN_RATE_2M ? 0x84 : 0x04;
-			(*lpos)++;
-		}
-		if (local->tx_rate_control & WLAN_RATE_5M5) {
-			*p++ = local->basic_rates & WLAN_RATE_5M5 ?
-				0x8b : 0x0b;
-			(*lpos)++;
-		}
-		if (local->tx_rate_control & WLAN_RATE_11M) {
-			*p++ = local->basic_rates & WLAN_RATE_11M ?
-				0x96 : 0x16;
-			(*lpos)++;
-		}
-		pos = (__le16 *) p;
-	}
-
-	prism2_send_mgmt(dev, IEEE80211_FTYPE_MGMT |
-			 (send_deauth ? IEEE80211_STYPE_DEAUTH :
-			  (reassoc ? IEEE80211_STYPE_REASSOC_RESP :
-			   IEEE80211_STYPE_ASSOC_RESP)),
-			 body, (u8 *) pos - (u8 *) body,
-			 hdr->addr2,
-			 send_deauth ? 0 : local->ap->tx_callback_assoc);
-
-	if (sta) {
-		if (resp == WLAN_STATUS_SUCCESS) {
-			sta->last_rx = jiffies;
-			/* STA will be marked associated from TX callback, if
-			 * AssocResp is ACKed */
-		}
-		atomic_dec(&sta->users);
-	}
-
-#if 0
-	PDEBUG(DEBUG_AP, "%s: %pM %sassoc (len=%d "
-	       "prev_ap=%pM) => %d(%d) (%s)\n",
-	       dev->name,
-	       hdr->addr2,
-	       reassoc ? "re" : "", len,
-	       prev_ap,
-	       resp, send_deauth, txt);
-#endif
-}
-
-
-/* Called only as a scheduled task for pending AP frames. */
-static void handle_deauth(local_info_t *local, struct sk_buff *skb,
-			  struct hostap_80211_rx_status *rx_stats)
-{
-	struct net_device *dev = local->dev;
-	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
-	char *body = (char *) (skb->data + IEEE80211_MGMT_HDR_LEN);
-	int len;
-	u16 reason_code;
-	__le16 *pos;
-	struct sta_info *sta = NULL;
-
-	len = skb->len - IEEE80211_MGMT_HDR_LEN;
-
-	if (len < 2) {
-		printk("handle_deauth - too short payload (len=%d)\n", len);
-		return;
-	}
-
-	pos = (__le16 *) body;
-	reason_code = le16_to_cpu(*pos);
-
-	PDEBUG(DEBUG_AP, "%s: deauthentication: %pM len=%d, "
-	       "reason_code=%d\n", dev->name, hdr->addr2,
-	       len, reason_code);
-
-	spin_lock_bh(&local->ap->sta_table_lock);
-	sta = ap_get_sta(local->ap, hdr->addr2);
-	if (sta != NULL) {
-		if ((sta->flags & WLAN_STA_ASSOC) && !sta->ap)
-			hostap_event_expired_sta(local->dev, sta);
-		sta->flags &= ~(WLAN_STA_AUTH | WLAN_STA_ASSOC);
-	}
-	spin_unlock_bh(&local->ap->sta_table_lock);
-	if (sta == NULL) {
-		printk("%s: deauthentication from %pM, "
-	       "reason_code=%d, but STA not authenticated\n", dev->name,
-		       hdr->addr2, reason_code);
-	}
-}
-
-
-/* Called only as a scheduled task for pending AP frames. */
-static void handle_disassoc(local_info_t *local, struct sk_buff *skb,
-			    struct hostap_80211_rx_status *rx_stats)
-{
-	struct net_device *dev = local->dev;
-	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
-	char *body = skb->data + IEEE80211_MGMT_HDR_LEN;
-	int len;
-	u16 reason_code;
-	__le16 *pos;
-	struct sta_info *sta = NULL;
-
-	len = skb->len - IEEE80211_MGMT_HDR_LEN;
-
-	if (len < 2) {
-		printk("handle_disassoc - too short payload (len=%d)\n", len);
-		return;
-	}
-
-	pos = (__le16 *) body;
-	reason_code = le16_to_cpu(*pos);
-
-	PDEBUG(DEBUG_AP, "%s: disassociation: %pM len=%d, "
-	       "reason_code=%d\n", dev->name, hdr->addr2,
-	       len, reason_code);
-
-	spin_lock_bh(&local->ap->sta_table_lock);
-	sta = ap_get_sta(local->ap, hdr->addr2);
-	if (sta != NULL) {
-		if ((sta->flags & WLAN_STA_ASSOC) && !sta->ap)
-			hostap_event_expired_sta(local->dev, sta);
-		sta->flags &= ~WLAN_STA_ASSOC;
-	}
-	spin_unlock_bh(&local->ap->sta_table_lock);
-	if (sta == NULL) {
-		printk("%s: disassociation from %pM, "
-		       "reason_code=%d, but STA not authenticated\n",
-		       dev->name, hdr->addr2, reason_code);
-	}
-}
-
-
-/* Called only as a scheduled task for pending AP frames. */
-static void ap_handle_data_nullfunc(local_info_t *local,
-				    struct ieee80211_hdr *hdr)
-{
-	struct net_device *dev = local->dev;
-
-	/* some STA f/w's seem to require control::ACK frame for
-	 * data::nullfunc, but at least Prism2 station f/w version 0.8.0 does
-	 * not send this..
-	 * send control::ACK for the data::nullfunc */
-
-	printk(KERN_DEBUG "Sending control::ACK for data::nullfunc\n");
-	prism2_send_mgmt(dev, IEEE80211_FTYPE_CTL | IEEE80211_STYPE_ACK,
-			 NULL, 0, hdr->addr2, 0);
-}
-
-
-/* Called only as a scheduled task for pending AP frames. */
-static void ap_handle_dropped_data(local_info_t *local,
-				   struct ieee80211_hdr *hdr)
-{
-	struct net_device *dev = local->dev;
-	struct sta_info *sta;
-	__le16 reason;
-
-	spin_lock_bh(&local->ap->sta_table_lock);
-	sta = ap_get_sta(local->ap, hdr->addr2);
-	if (sta)
-		atomic_inc(&sta->users);
-	spin_unlock_bh(&local->ap->sta_table_lock);
-
-	if (sta != NULL && (sta->flags & WLAN_STA_ASSOC)) {
-		PDEBUG(DEBUG_AP, "ap_handle_dropped_data: STA is now okay?\n");
-		atomic_dec(&sta->users);
-		return;
-	}
-
-	reason = cpu_to_le16(WLAN_REASON_CLASS3_FRAME_FROM_NONASSOC_STA);
-	prism2_send_mgmt(dev, IEEE80211_FTYPE_MGMT |
-			 ((sta == NULL || !(sta->flags & WLAN_STA_ASSOC)) ?
-			  IEEE80211_STYPE_DEAUTH : IEEE80211_STYPE_DISASSOC),
-			 (char *) &reason, sizeof(reason), hdr->addr2, 0);
-
-	if (sta)
-		atomic_dec(&sta->users);
-}
-
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-
-
-/* Called only as a scheduled task for pending AP frames. */
-static void pspoll_send_buffered(local_info_t *local, struct sta_info *sta,
-				 struct sk_buff *skb)
-{
-	struct hostap_skb_tx_data *meta;
-
-	if (!(sta->flags & WLAN_STA_PS)) {
-		/* Station has moved to non-PS mode, so send all buffered
-		 * frames using normal device queue. */
-		dev_queue_xmit(skb);
-		return;
-	}
-
-	/* add a flag for hostap_handle_sta_tx() to know that this skb should
-	 * be passed through even though STA is using PS */
-	meta = (struct hostap_skb_tx_data *) skb->cb;
-	meta->flags |= HOSTAP_TX_FLAGS_BUFFERED_FRAME;
-	if (!skb_queue_empty(&sta->tx_buf)) {
-		/* indicate to STA that more frames follow */
-		meta->flags |= HOSTAP_TX_FLAGS_ADD_MOREDATA;
-	}
-	dev_queue_xmit(skb);
-}
-
-
-/* Called only as a scheduled task for pending AP frames. */
-static void handle_pspoll(local_info_t *local,
-			  struct ieee80211_hdr *hdr,
-			  struct hostap_80211_rx_status *rx_stats)
-{
-	struct net_device *dev = local->dev;
-	struct sta_info *sta;
-	u16 aid;
-	struct sk_buff *skb;
-
-	PDEBUG(DEBUG_PS2, "handle_pspoll: BSSID=%pM, TA=%pM PWRMGT=%d\n",
-	       hdr->addr1, hdr->addr2, !!ieee80211_has_pm(hdr->frame_control));
-
-	if (!ether_addr_equal(hdr->addr1, dev->dev_addr)) {
-		PDEBUG(DEBUG_AP,
-		       "handle_pspoll - addr1(BSSID)=%pM not own MAC\n",
-		       hdr->addr1);
-		return;
-	}
-
-	aid = le16_to_cpu(hdr->duration_id);
-	if ((aid & (BIT(15) | BIT(14))) != (BIT(15) | BIT(14))) {
-		PDEBUG(DEBUG_PS, "   PSPOLL and AID[15:14] not set\n");
-		return;
-	}
-	aid &= ~(BIT(15) | BIT(14));
-	if (aid == 0 || aid > MAX_AID_TABLE_SIZE) {
-		PDEBUG(DEBUG_PS, "   invalid aid=%d\n", aid);
-		return;
-	}
-	PDEBUG(DEBUG_PS2, "   aid=%d\n", aid);
-
-	spin_lock_bh(&local->ap->sta_table_lock);
-	sta = ap_get_sta(local->ap, hdr->addr2);
-	if (sta)
-		atomic_inc(&sta->users);
-	spin_unlock_bh(&local->ap->sta_table_lock);
-
-	if (sta == NULL) {
-		PDEBUG(DEBUG_PS, "   STA not found\n");
-		return;
-	}
-	if (sta->aid != aid) {
-		PDEBUG(DEBUG_PS, "   received aid=%i does not match with "
-		       "assoc.aid=%d\n", aid, sta->aid);
-		return;
-	}
-
-	/* FIX: todo:
-	 * - add timeout for buffering (clear aid in TIM vector if buffer timed
-	 *   out (expiry time must be longer than ListenInterval for
-	 *   the corresponding STA; "8802-11: 11.2.1.9 AP aging function"
-	 * - what to do, if buffered, pspolled, and sent frame is not ACKed by
-	 *   sta; store buffer for later use and leave TIM aid bit set? use
-	 *   TX event to check whether frame was ACKed?
-	 */
-
-	while ((skb = skb_dequeue(&sta->tx_buf)) != NULL) {
-		/* send buffered frame .. */
-		PDEBUG(DEBUG_PS2, "Sending buffered frame to STA after PS POLL"
-		       " (buffer_count=%d)\n", skb_queue_len(&sta->tx_buf));
-
-		pspoll_send_buffered(local, sta, skb);
-
-		if (sta->flags & WLAN_STA_PS) {
-			/* send only one buffered packet per PS Poll */
-			/* FIX: should ignore further PS Polls until the
-			 * buffered packet that was just sent is acknowledged
-			 * (Tx or TxExc event) */
-			break;
-		}
-	}
-
-	if (skb_queue_empty(&sta->tx_buf)) {
-		/* try to clear aid from TIM */
-		if (!(sta->flags & WLAN_STA_TIM))
-			PDEBUG(DEBUG_PS2,  "Re-unsetting TIM for aid %d\n",
-			       aid);
-		hostap_set_tim(local, aid, 0);
-		sta->flags &= ~WLAN_STA_TIM;
-	}
-
-	atomic_dec(&sta->users);
-}
-
-
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-
-static void handle_wds_oper_queue(struct work_struct *work)
-{
-	struct ap_data *ap = container_of(work, struct ap_data,
-					  wds_oper_queue);
-	local_info_t *local = ap->local;
-	struct wds_oper_data *entry, *prev;
-
-	spin_lock_bh(&local->lock);
-	entry = local->ap->wds_oper_entries;
-	local->ap->wds_oper_entries = NULL;
-	spin_unlock_bh(&local->lock);
-
-	while (entry) {
-		PDEBUG(DEBUG_AP, "%s: %s automatic WDS connection "
-		       "to AP %pM\n",
-		       local->dev->name,
-		       entry->type == WDS_ADD ? "adding" : "removing",
-		       entry->addr);
-		if (entry->type == WDS_ADD)
-			prism2_wds_add(local, entry->addr, 0);
-		else if (entry->type == WDS_DEL)
-			prism2_wds_del(local, entry->addr, 0, 1);
-
-		prev = entry;
-		entry = entry->next;
-		kfree(prev);
-	}
-}
-
-
-/* Called only as a scheduled task for pending AP frames. */
-static void handle_beacon(local_info_t *local, struct sk_buff *skb,
-			  struct hostap_80211_rx_status *rx_stats)
-{
-	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
-	char *body = skb->data + IEEE80211_MGMT_HDR_LEN;
-	int len, left;
-	u16 beacon_int, capability;
-	__le16 *pos;
-	char *ssid = NULL;
-	unsigned char *supp_rates = NULL;
-	int ssid_len = 0, supp_rates_len = 0;
-	struct sta_info *sta = NULL;
-	int new_sta = 0, channel = -1;
-
-	len = skb->len - IEEE80211_MGMT_HDR_LEN;
-
-	if (len < 8 + 2 + 2) {
-		printk(KERN_DEBUG "handle_beacon - too short payload "
-		       "(len=%d)\n", len);
-		return;
-	}
-
-	pos = (__le16 *) body;
-	left = len;
-
-	/* Timestamp (8 octets) */
-	pos += 4; left -= 8;
-	/* Beacon interval (2 octets) */
-	beacon_int = le16_to_cpu(*pos);
-	pos++; left -= 2;
-	/* Capability information (2 octets) */
-	capability = le16_to_cpu(*pos);
-	pos++; left -= 2;
-
-	if (local->ap->ap_policy != AP_OTHER_AP_EVEN_IBSS &&
-	    capability & WLAN_CAPABILITY_IBSS)
-		return;
-
-	if (left >= 2) {
-		unsigned int ileft;
-		unsigned char *u = (unsigned char *) pos;
-
-		if (*u == WLAN_EID_SSID) {
-			u++; left--;
-			ileft = *u;
-			u++; left--;
-
-			if (ileft > left || ileft > MAX_SSID_LEN) {
-				PDEBUG(DEBUG_AP, "SSID: overflow\n");
-				return;
-			}
-
-			if (local->ap->ap_policy == AP_OTHER_AP_SAME_SSID &&
-			    (ileft != strlen(local->essid) ||
-			     memcmp(local->essid, u, ileft) != 0)) {
-				/* not our SSID */
-				return;
-			}
-
-			ssid = u;
-			ssid_len = ileft;
-
-			u += ileft;
-			left -= ileft;
-		}
-
-		if (*u == WLAN_EID_SUPP_RATES) {
-			u++; left--;
-			ileft = *u;
-			u++; left--;
-
-			if (ileft > left || ileft == 0 || ileft > 8) {
-				PDEBUG(DEBUG_AP, " - SUPP_RATES len error\n");
-				return;
-			}
-
-			supp_rates = u;
-			supp_rates_len = ileft;
-
-			u += ileft;
-			left -= ileft;
-		}
-
-		if (*u == WLAN_EID_DS_PARAMS) {
-			u++; left--;
-			ileft = *u;
-			u++; left--;
-
-			if (ileft > left || ileft != 1) {
-				PDEBUG(DEBUG_AP, " - DS_PARAMS len error\n");
-				return;
-			}
-
-			channel = *u;
-
-			u += ileft;
-			left -= ileft;
-		}
-	}
-
-	spin_lock_bh(&local->ap->sta_table_lock);
-	sta = ap_get_sta(local->ap, hdr->addr2);
-	if (sta != NULL)
-		atomic_inc(&sta->users);
-	spin_unlock_bh(&local->ap->sta_table_lock);
-
-	if (sta == NULL) {
-		/* add new AP */
-		new_sta = 1;
-		sta = ap_add_sta(local->ap, hdr->addr2);
-		if (sta == NULL) {
-			printk(KERN_INFO "prism2: kmalloc failed for AP "
-			       "data structure\n");
-			return;
-		}
-		hostap_event_new_sta(local->dev, sta);
-
-		/* mark APs authentication and associated for pseudo ad-hoc
-		 * style communication */
-		sta->flags = WLAN_STA_AUTH | WLAN_STA_ASSOC;
-
-		if (local->ap->autom_ap_wds) {
-			hostap_wds_link_oper(local, sta->addr, WDS_ADD);
-		}
-	}
-
-	sta->ap = 1;
-	if (ssid) {
-		sta->u.ap.ssid_len = ssid_len;
-		memcpy(sta->u.ap.ssid, ssid, ssid_len);
-		sta->u.ap.ssid[ssid_len] = '\0';
-	} else {
-		sta->u.ap.ssid_len = 0;
-		sta->u.ap.ssid[0] = '\0';
-	}
-	sta->u.ap.channel = channel;
-	sta->rx_packets++;
-	sta->rx_bytes += len;
-	sta->u.ap.last_beacon = sta->last_rx = jiffies;
-	sta->capability = capability;
-	sta->listen_interval = beacon_int;
-
-	atomic_dec(&sta->users);
-
-	if (new_sta) {
-		memset(sta->supported_rates, 0, sizeof(sta->supported_rates));
-		memcpy(sta->supported_rates, supp_rates, supp_rates_len);
-		prism2_check_tx_rates(sta);
-	}
-}
-
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-
-
-/* Called only as a tasklet. */
-static void handle_ap_item(local_info_t *local, struct sk_buff *skb,
-			   struct hostap_80211_rx_status *rx_stats)
-{
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-	struct net_device *dev = local->dev;
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-	u16 fc, type, stype;
-	struct ieee80211_hdr *hdr;
-
-	/* FIX: should give skb->len to handler functions and check that the
-	 * buffer is long enough */
-	hdr = (struct ieee80211_hdr *) skb->data;
-	fc = le16_to_cpu(hdr->frame_control);
-	type = fc & IEEE80211_FCTL_FTYPE;
-	stype = fc & IEEE80211_FCTL_STYPE;
-
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-	if (!local->hostapd && type == IEEE80211_FTYPE_DATA) {
-		PDEBUG(DEBUG_AP, "handle_ap_item - data frame\n");
-
-		if (!(fc & IEEE80211_FCTL_TODS) ||
-		    (fc & IEEE80211_FCTL_FROMDS)) {
-			if (stype == IEEE80211_STYPE_NULLFUNC) {
-				/* no ToDS nullfunc seems to be used to check
-				 * AP association; so send reject message to
-				 * speed up re-association */
-				ap_handle_dropped_data(local, hdr);
-				goto done;
-			}
-			PDEBUG(DEBUG_AP, "   not ToDS frame (fc=0x%04x)\n",
-			       fc);
-			goto done;
-		}
-
-		if (!ether_addr_equal(hdr->addr1, dev->dev_addr)) {
-			PDEBUG(DEBUG_AP, "handle_ap_item - addr1(BSSID)=%pM"
-			       " not own MAC\n", hdr->addr1);
-			goto done;
-		}
-
-		if (local->ap->nullfunc_ack &&
-		    stype == IEEE80211_STYPE_NULLFUNC)
-			ap_handle_data_nullfunc(local, hdr);
-		else
-			ap_handle_dropped_data(local, hdr);
-		goto done;
-	}
-
-	if (type == IEEE80211_FTYPE_MGMT && stype == IEEE80211_STYPE_BEACON) {
-		handle_beacon(local, skb, rx_stats);
-		goto done;
-	}
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-
-	if (type == IEEE80211_FTYPE_CTL && stype == IEEE80211_STYPE_PSPOLL) {
-		handle_pspoll(local, hdr, rx_stats);
-		goto done;
-	}
-
-	if (local->hostapd) {
-		PDEBUG(DEBUG_AP, "Unknown frame in AP queue: type=0x%02x "
-		       "subtype=0x%02x\n", type, stype);
-		goto done;
-	}
-
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-	if (type != IEEE80211_FTYPE_MGMT) {
-		PDEBUG(DEBUG_AP, "handle_ap_item - not a management frame?\n");
-		goto done;
-	}
-
-	if (!ether_addr_equal(hdr->addr1, dev->dev_addr)) {
-		PDEBUG(DEBUG_AP, "handle_ap_item - addr1(DA)=%pM"
-		       " not own MAC\n", hdr->addr1);
-		goto done;
-	}
-
-	if (!ether_addr_equal(hdr->addr3, dev->dev_addr)) {
-		PDEBUG(DEBUG_AP, "handle_ap_item - addr3(BSSID)=%pM"
-		       " not own MAC\n", hdr->addr3);
-		goto done;
-	}
-
-	switch (stype) {
-	case IEEE80211_STYPE_ASSOC_REQ:
-		handle_assoc(local, skb, rx_stats, 0);
-		break;
-	case IEEE80211_STYPE_ASSOC_RESP:
-		PDEBUG(DEBUG_AP, "==> ASSOC RESP (ignored)\n");
-		break;
-	case IEEE80211_STYPE_REASSOC_REQ:
-		handle_assoc(local, skb, rx_stats, 1);
-		break;
-	case IEEE80211_STYPE_REASSOC_RESP:
-		PDEBUG(DEBUG_AP, "==> REASSOC RESP (ignored)\n");
-		break;
-	case IEEE80211_STYPE_ATIM:
-		PDEBUG(DEBUG_AP, "==> ATIM (ignored)\n");
-		break;
-	case IEEE80211_STYPE_DISASSOC:
-		handle_disassoc(local, skb, rx_stats);
-		break;
-	case IEEE80211_STYPE_AUTH:
-		handle_authen(local, skb, rx_stats);
-		break;
-	case IEEE80211_STYPE_DEAUTH:
-		handle_deauth(local, skb, rx_stats);
-		break;
-	default:
-		PDEBUG(DEBUG_AP, "Unknown mgmt frame subtype 0x%02x\n",
-		       stype >> 4);
-		break;
-	}
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-
- done:
-	dev_kfree_skb(skb);
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-void hostap_rx(struct net_device *dev, struct sk_buff *skb,
-	       struct hostap_80211_rx_status *rx_stats)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	struct ieee80211_hdr *hdr;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (skb->len < 16)
-		goto drop;
-
-	dev->stats.rx_packets++;
-
-	hdr = (struct ieee80211_hdr *) skb->data;
-
-	if (local->ap->ap_policy == AP_OTHER_AP_SKIP_ALL &&
-	    ieee80211_is_beacon(hdr->frame_control))
-		goto drop;
-
-	skb->protocol = cpu_to_be16(ETH_P_HOSTAP);
-	handle_ap_item(local, skb, rx_stats);
-	return;
-
- drop:
-	dev_kfree_skb(skb);
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static void schedule_packet_send(local_info_t *local, struct sta_info *sta)
-{
-	struct sk_buff *skb;
-	struct ieee80211_hdr *hdr;
-	struct hostap_80211_rx_status rx_stats;
-
-	if (skb_queue_empty(&sta->tx_buf))
-		return;
-
-	skb = dev_alloc_skb(16);
-	if (skb == NULL) {
-		printk(KERN_DEBUG "%s: schedule_packet_send: skb alloc "
-		       "failed\n", local->dev->name);
-		return;
-	}
-
-	hdr = skb_put(skb, 16);
-
-	/* Generate a fake pspoll frame to start packet delivery */
-	hdr->frame_control = cpu_to_le16(
-		IEEE80211_FTYPE_CTL | IEEE80211_STYPE_PSPOLL);
-	memcpy(hdr->addr1, local->dev->dev_addr, ETH_ALEN);
-	memcpy(hdr->addr2, sta->addr, ETH_ALEN);
-	hdr->duration_id = cpu_to_le16(sta->aid | BIT(15) | BIT(14));
-
-	PDEBUG(DEBUG_PS2,
-	       "%s: Scheduling buffered packet delivery for STA %pM\n",
-	       local->dev->name, sta->addr);
-
-	skb->dev = local->dev;
-
-	memset(&rx_stats, 0, sizeof(rx_stats));
-	hostap_rx(local->dev, skb, &rx_stats);
-}
-
-
-int prism2_ap_get_sta_qual(local_info_t *local, struct sockaddr addr[],
-			   struct iw_quality qual[], int buf_size,
-			   int aplist)
-{
-	struct ap_data *ap = local->ap;
-	struct list_head *ptr;
-	int count = 0;
-
-	spin_lock_bh(&ap->sta_table_lock);
-
-	for (ptr = ap->sta_list.next; ptr != NULL && ptr != &ap->sta_list;
-	     ptr = ptr->next) {
-		struct sta_info *sta = (struct sta_info *) ptr;
-
-		if (aplist && !sta->ap)
-			continue;
-		addr[count].sa_family = ARPHRD_ETHER;
-		memcpy(addr[count].sa_data, sta->addr, ETH_ALEN);
-		if (sta->last_rx_silence == 0)
-			qual[count].qual = sta->last_rx_signal < 27 ?
-				0 : (sta->last_rx_signal - 27) * 92 / 127;
-		else
-			qual[count].qual = sta->last_rx_signal -
-				sta->last_rx_silence - 35;
-		qual[count].level = HFA384X_LEVEL_TO_dBm(sta->last_rx_signal);
-		qual[count].noise = HFA384X_LEVEL_TO_dBm(sta->last_rx_silence);
-		qual[count].updated = sta->last_rx_updated;
-
-		sta->last_rx_updated = IW_QUAL_DBM;
-
-		count++;
-		if (count >= buf_size)
-			break;
-	}
-	spin_unlock_bh(&ap->sta_table_lock);
-
-	return count;
-}
-
-
-/* Translate our list of Access Points & Stations to a card independent
- * format that the Wireless Tools will understand - Jean II */
-int prism2_ap_translate_scan(struct net_device *dev,
-			     struct iw_request_info *info, char *buffer)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	struct ap_data *ap;
-	struct list_head *ptr;
-	struct iw_event iwe;
-	char *current_ev = buffer;
-	char *end_buf = buffer + IW_SCAN_MAX_DATA;
-#if !defined(PRISM2_NO_KERNEL_IEEE80211_MGMT)
-	char buf[64];
-#endif
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-	ap = local->ap;
-
-	spin_lock_bh(&ap->sta_table_lock);
-
-	for (ptr = ap->sta_list.next; ptr != NULL && ptr != &ap->sta_list;
-	     ptr = ptr->next) {
-		struct sta_info *sta = (struct sta_info *) ptr;
-
-		/* First entry *MUST* be the AP MAC address */
-		memset(&iwe, 0, sizeof(iwe));
-		iwe.cmd = SIOCGIWAP;
-		iwe.u.ap_addr.sa_family = ARPHRD_ETHER;
-		memcpy(iwe.u.ap_addr.sa_data, sta->addr, ETH_ALEN);
-		iwe.len = IW_EV_ADDR_LEN;
-		current_ev = iwe_stream_add_event(info, current_ev, end_buf,
-						  &iwe, IW_EV_ADDR_LEN);
-
-		/* Use the mode to indicate if it's a station or
-		 * an Access Point */
-		memset(&iwe, 0, sizeof(iwe));
-		iwe.cmd = SIOCGIWMODE;
-		if (sta->ap)
-			iwe.u.mode = IW_MODE_MASTER;
-		else
-			iwe.u.mode = IW_MODE_INFRA;
-		iwe.len = IW_EV_UINT_LEN;
-		current_ev = iwe_stream_add_event(info, current_ev, end_buf,
-						  &iwe, IW_EV_UINT_LEN);
-
-		/* Some quality */
-		memset(&iwe, 0, sizeof(iwe));
-		iwe.cmd = IWEVQUAL;
-		if (sta->last_rx_silence == 0)
-			iwe.u.qual.qual = sta->last_rx_signal < 27 ?
-				0 : (sta->last_rx_signal - 27) * 92 / 127;
-		else
-			iwe.u.qual.qual = sta->last_rx_signal -
-				sta->last_rx_silence - 35;
-		iwe.u.qual.level = HFA384X_LEVEL_TO_dBm(sta->last_rx_signal);
-		iwe.u.qual.noise = HFA384X_LEVEL_TO_dBm(sta->last_rx_silence);
-		iwe.u.qual.updated = sta->last_rx_updated;
-		iwe.len = IW_EV_QUAL_LEN;
-		current_ev = iwe_stream_add_event(info, current_ev, end_buf,
-						  &iwe, IW_EV_QUAL_LEN);
-
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-		if (sta->ap) {
-			memset(&iwe, 0, sizeof(iwe));
-			iwe.cmd = SIOCGIWESSID;
-			iwe.u.data.length = sta->u.ap.ssid_len;
-			iwe.u.data.flags = 1;
-			current_ev = iwe_stream_add_point(info, current_ev,
-							  end_buf, &iwe,
-							  sta->u.ap.ssid);
-
-			memset(&iwe, 0, sizeof(iwe));
-			iwe.cmd = SIOCGIWENCODE;
-			if (sta->capability & WLAN_CAPABILITY_PRIVACY)
-				iwe.u.data.flags =
-					IW_ENCODE_ENABLED | IW_ENCODE_NOKEY;
-			else
-				iwe.u.data.flags = IW_ENCODE_DISABLED;
-			current_ev = iwe_stream_add_point(info, current_ev,
-							  end_buf, &iwe,
-							  sta->u.ap.ssid);
-
-			if (sta->u.ap.channel > 0 &&
-			    sta->u.ap.channel <= FREQ_COUNT) {
-				memset(&iwe, 0, sizeof(iwe));
-				iwe.cmd = SIOCGIWFREQ;
-				iwe.u.freq.m = freq_list[sta->u.ap.channel - 1]
-					* 100000;
-				iwe.u.freq.e = 1;
-				current_ev = iwe_stream_add_event(
-					info, current_ev, end_buf, &iwe,
-					IW_EV_FREQ_LEN);
-			}
-
-			memset(&iwe, 0, sizeof(iwe));
-			iwe.cmd = IWEVCUSTOM;
-			sprintf(buf, "beacon_interval=%d",
-				sta->listen_interval);
-			iwe.u.data.length = strlen(buf);
-			current_ev = iwe_stream_add_point(info, current_ev,
-							  end_buf, &iwe, buf);
-		}
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-
-		sta->last_rx_updated = IW_QUAL_DBM;
-
-		/* To be continued, we should make good use of IWEVCUSTOM */
-	}
-
-	spin_unlock_bh(&ap->sta_table_lock);
-
-	return current_ev - buffer;
-}
-
-
-static int prism2_hostapd_add_sta(struct ap_data *ap,
-				  struct prism2_hostapd_param *param)
-{
-	struct sta_info *sta;
-
-	spin_lock_bh(&ap->sta_table_lock);
-	sta = ap_get_sta(ap, param->sta_addr);
-	if (sta)
-		atomic_inc(&sta->users);
-	spin_unlock_bh(&ap->sta_table_lock);
-
-	if (sta == NULL) {
-		sta = ap_add_sta(ap, param->sta_addr);
-		if (sta == NULL)
-			return -1;
-	}
-
-	if (!(sta->flags & WLAN_STA_ASSOC) && !sta->ap && sta->local)
-		hostap_event_new_sta(sta->local->dev, sta);
-
-	sta->flags |= WLAN_STA_AUTH | WLAN_STA_ASSOC;
-	sta->last_rx = jiffies;
-	sta->aid = param->u.add_sta.aid;
-	sta->capability = param->u.add_sta.capability;
-	sta->tx_supp_rates = param->u.add_sta.tx_supp_rates;
-	if (sta->tx_supp_rates & WLAN_RATE_1M)
-		sta->supported_rates[0] = 2;
-	if (sta->tx_supp_rates & WLAN_RATE_2M)
-		sta->supported_rates[1] = 4;
-	if (sta->tx_supp_rates & WLAN_RATE_5M5)
-		sta->supported_rates[2] = 11;
-	if (sta->tx_supp_rates & WLAN_RATE_11M)
-		sta->supported_rates[3] = 22;
-	prism2_check_tx_rates(sta);
-	atomic_dec(&sta->users);
-	return 0;
-}
-
-
-static int prism2_hostapd_remove_sta(struct ap_data *ap,
-				     struct prism2_hostapd_param *param)
-{
-	struct sta_info *sta;
-
-	spin_lock_bh(&ap->sta_table_lock);
-	sta = ap_get_sta(ap, param->sta_addr);
-	if (sta) {
-		ap_sta_hash_del(ap, sta);
-		list_del(&sta->list);
-	}
-	spin_unlock_bh(&ap->sta_table_lock);
-
-	if (!sta)
-		return -ENOENT;
-
-	if ((sta->flags & WLAN_STA_ASSOC) && !sta->ap && sta->local)
-		hostap_event_expired_sta(sta->local->dev, sta);
-	ap_free_sta(ap, sta);
-
-	return 0;
-}
-
-
-static int prism2_hostapd_get_info_sta(struct ap_data *ap,
-				       struct prism2_hostapd_param *param)
-{
-	struct sta_info *sta;
-
-	spin_lock_bh(&ap->sta_table_lock);
-	sta = ap_get_sta(ap, param->sta_addr);
-	if (sta)
-		atomic_inc(&sta->users);
-	spin_unlock_bh(&ap->sta_table_lock);
-
-	if (!sta)
-		return -ENOENT;
-
-	param->u.get_info_sta.inactive_sec = (jiffies - sta->last_rx) / HZ;
-
-	atomic_dec(&sta->users);
-
-	return 1;
-}
-
-
-static int prism2_hostapd_set_flags_sta(struct ap_data *ap,
-					struct prism2_hostapd_param *param)
-{
-	struct sta_info *sta;
-
-	spin_lock_bh(&ap->sta_table_lock);
-	sta = ap_get_sta(ap, param->sta_addr);
-	if (sta) {
-		sta->flags |= param->u.set_flags_sta.flags_or;
-		sta->flags &= param->u.set_flags_sta.flags_and;
-	}
-	spin_unlock_bh(&ap->sta_table_lock);
-
-	if (!sta)
-		return -ENOENT;
-
-	return 0;
-}
-
-
-static int prism2_hostapd_sta_clear_stats(struct ap_data *ap,
-					  struct prism2_hostapd_param *param)
-{
-	struct sta_info *sta;
-	int rate;
-
-	spin_lock_bh(&ap->sta_table_lock);
-	sta = ap_get_sta(ap, param->sta_addr);
-	if (sta) {
-		sta->rx_packets = sta->tx_packets = 0;
-		sta->rx_bytes = sta->tx_bytes = 0;
-		for (rate = 0; rate < WLAN_RATE_COUNT; rate++) {
-			sta->tx_count[rate] = 0;
-			sta->rx_count[rate] = 0;
-		}
-	}
-	spin_unlock_bh(&ap->sta_table_lock);
-
-	if (!sta)
-		return -ENOENT;
-
-	return 0;
-}
-
-
-int prism2_hostapd(struct ap_data *ap, struct prism2_hostapd_param *param)
-{
-	switch (param->cmd) {
-	case PRISM2_HOSTAPD_FLUSH:
-		ap_control_kickall(ap);
-		return 0;
-	case PRISM2_HOSTAPD_ADD_STA:
-		return prism2_hostapd_add_sta(ap, param);
-	case PRISM2_HOSTAPD_REMOVE_STA:
-		return prism2_hostapd_remove_sta(ap, param);
-	case PRISM2_HOSTAPD_GET_INFO_STA:
-		return prism2_hostapd_get_info_sta(ap, param);
-	case PRISM2_HOSTAPD_SET_FLAGS_STA:
-		return prism2_hostapd_set_flags_sta(ap, param);
-	case PRISM2_HOSTAPD_STA_CLEAR_STATS:
-		return prism2_hostapd_sta_clear_stats(ap, param);
-	default:
-		printk(KERN_WARNING "prism2_hostapd: unknown cmd=%d\n",
-		       param->cmd);
-		return -EOPNOTSUPP;
-	}
-}
-
-
-/* Update station info for host-based TX rate control and return current
- * TX rate */
-static int ap_update_sta_tx_rate(struct sta_info *sta, struct net_device *dev)
-{
-	int ret = sta->tx_rate;
-	struct hostap_interface *iface;
-	local_info_t *local;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	sta->tx_count[sta->tx_rate_idx]++;
-	sta->tx_since_last_failure++;
-	sta->tx_consecutive_exc = 0;
-	if (sta->tx_since_last_failure >= WLAN_RATE_UPDATE_COUNT &&
-	    sta->tx_rate_idx < sta->tx_max_rate) {
-		/* use next higher rate */
-		int old_rate, new_rate;
-		old_rate = new_rate = sta->tx_rate_idx;
-		while (new_rate < sta->tx_max_rate) {
-			new_rate++;
-			if (ap_tx_rate_ok(new_rate, sta, local)) {
-				sta->tx_rate_idx = new_rate;
-				break;
-			}
-		}
-		if (old_rate != sta->tx_rate_idx) {
-			switch (sta->tx_rate_idx) {
-			case 0: sta->tx_rate = 10; break;
-			case 1: sta->tx_rate = 20; break;
-			case 2: sta->tx_rate = 55; break;
-			case 3: sta->tx_rate = 110; break;
-			default: sta->tx_rate = 0; break;
-			}
-			PDEBUG(DEBUG_AP, "%s: STA %pM TX rate raised to %d\n",
-			       dev->name, sta->addr, sta->tx_rate);
-		}
-		sta->tx_since_last_failure = 0;
-	}
-
-	return ret;
-}
-
-
-/* Called only from software IRQ. Called for each TX frame prior possible
- * encryption and transmit. */
-ap_tx_ret hostap_handle_sta_tx(local_info_t *local, struct hostap_tx_data *tx)
-{
-	struct sta_info *sta = NULL;
-	struct sk_buff *skb = tx->skb;
-	int set_tim, ret;
-	struct ieee80211_hdr *hdr;
-	struct hostap_skb_tx_data *meta;
-
-	meta = (struct hostap_skb_tx_data *) skb->cb;
-	ret = AP_TX_CONTINUE;
-	if (local->ap == NULL || skb->len < 10 ||
-	    meta->iface->type == HOSTAP_INTERFACE_STA)
-		goto out;
-
-	hdr = (struct ieee80211_hdr *) skb->data;
-
-	if (hdr->addr1[0] & 0x01) {
-		/* broadcast/multicast frame - no AP related processing */
-		if (local->ap->num_sta <= 0)
-			ret = AP_TX_DROP;
-		goto out;
-	}
-
-	/* unicast packet - check whether destination STA is associated */
-	spin_lock(&local->ap->sta_table_lock);
-	sta = ap_get_sta(local->ap, hdr->addr1);
-	if (sta)
-		atomic_inc(&sta->users);
-	spin_unlock(&local->ap->sta_table_lock);
-
-	if (local->iw_mode == IW_MODE_MASTER && sta == NULL &&
-	    !(meta->flags & HOSTAP_TX_FLAGS_WDS) &&
-	    meta->iface->type != HOSTAP_INTERFACE_MASTER &&
-	    meta->iface->type != HOSTAP_INTERFACE_AP) {
-#if 0
-		/* This can happen, e.g., when wlan0 is added to a bridge and
-		 * bridging code does not know which port is the correct target
-		 * for a unicast frame. In this case, the packet is send to all
-		 * ports of the bridge. Since this is a valid scenario, do not
-		 * print out any errors here. */
-		if (net_ratelimit()) {
-			printk(KERN_DEBUG "AP: drop packet to non-associated "
-			       "STA %pM\n", hdr->addr1);
-		}
-#endif
-		local->ap->tx_drop_nonassoc++;
-		ret = AP_TX_DROP;
-		goto out;
-	}
-
-	if (sta == NULL)
-		goto out;
-
-	if (!(sta->flags & WLAN_STA_AUTHORIZED))
-		ret = AP_TX_CONTINUE_NOT_AUTHORIZED;
-
-	/* Set tx_rate if using host-based TX rate control */
-	if (!local->fw_tx_rate_control)
-		local->ap->last_tx_rate = meta->rate =
-			ap_update_sta_tx_rate(sta, local->dev);
-
-	if (local->iw_mode != IW_MODE_MASTER)
-		goto out;
-
-	if (!(sta->flags & WLAN_STA_PS))
-		goto out;
-
-	if (meta->flags & HOSTAP_TX_FLAGS_ADD_MOREDATA) {
-		/* indicate to STA that more frames follow */
-		hdr->frame_control |=
-			cpu_to_le16(IEEE80211_FCTL_MOREDATA);
-	}
-
-	if (meta->flags & HOSTAP_TX_FLAGS_BUFFERED_FRAME) {
-		/* packet was already buffered and now send due to
-		 * PS poll, so do not rebuffer it */
-		goto out;
-	}
-
-	if (skb_queue_len(&sta->tx_buf) >= STA_MAX_TX_BUFFER) {
-		PDEBUG(DEBUG_PS, "%s: No more space in STA (%pM)'s"
-		       "PS mode buffer\n",
-		       local->dev->name, sta->addr);
-		/* Make sure that TIM is set for the station (it might not be
-		 * after AP wlan hw reset). */
-		/* FIX: should fix hw reset to restore bits based on STA
-		 * buffer state.. */
-		hostap_set_tim(local, sta->aid, 1);
-		sta->flags |= WLAN_STA_TIM;
-		ret = AP_TX_DROP;
-		goto out;
-	}
-
-	/* STA in PS mode, buffer frame for later delivery */
-	set_tim = skb_queue_empty(&sta->tx_buf);
-	skb_queue_tail(&sta->tx_buf, skb);
-	/* FIX: could save RX time to skb and expire buffered frames after
-	 * some time if STA does not poll for them */
-
-	if (set_tim) {
-		if (sta->flags & WLAN_STA_TIM)
-			PDEBUG(DEBUG_PS2, "Re-setting TIM for aid %d\n",
-			       sta->aid);
-		hostap_set_tim(local, sta->aid, 1);
-		sta->flags |= WLAN_STA_TIM;
-	}
-
-	ret = AP_TX_BUFFERED;
-
- out:
-	if (sta != NULL) {
-		if (ret == AP_TX_CONTINUE ||
-		    ret == AP_TX_CONTINUE_NOT_AUTHORIZED) {
-			sta->tx_packets++;
-			sta->tx_bytes += skb->len;
-			sta->last_tx = jiffies;
-		}
-
-		if ((ret == AP_TX_CONTINUE ||
-		     ret == AP_TX_CONTINUE_NOT_AUTHORIZED) &&
-		    sta->crypt && tx->host_encrypt) {
-			tx->crypt = sta->crypt;
-			tx->sta_ptr = sta; /* hostap_handle_sta_release() will
-					    * be called to release sta info
-					    * later */
-		} else
-			atomic_dec(&sta->users);
-	}
-
-	return ret;
-}
-
-
-void hostap_handle_sta_release(void *ptr)
-{
-	struct sta_info *sta = ptr;
-	atomic_dec(&sta->users);
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-void hostap_handle_sta_tx_exc(local_info_t *local, struct sk_buff *skb)
-{
-	struct sta_info *sta;
-	struct ieee80211_hdr *hdr;
-	struct hostap_skb_tx_data *meta;
-
-	hdr = (struct ieee80211_hdr *) skb->data;
-	meta = (struct hostap_skb_tx_data *) skb->cb;
-
-	spin_lock(&local->ap->sta_table_lock);
-	sta = ap_get_sta(local->ap, hdr->addr1);
-	if (!sta) {
-		spin_unlock(&local->ap->sta_table_lock);
-		PDEBUG(DEBUG_AP, "%s: Could not find STA %pM"
-		       " for this TX error (@%lu)\n",
-		       local->dev->name, hdr->addr1, jiffies);
-		return;
-	}
-
-	sta->tx_since_last_failure = 0;
-	sta->tx_consecutive_exc++;
-
-	if (sta->tx_consecutive_exc >= WLAN_RATE_DECREASE_THRESHOLD &&
-	    sta->tx_rate_idx > 0 && meta->rate <= sta->tx_rate) {
-		/* use next lower rate */
-		int old, rate;
-		old = rate = sta->tx_rate_idx;
-		while (rate > 0) {
-			rate--;
-			if (ap_tx_rate_ok(rate, sta, local)) {
-				sta->tx_rate_idx = rate;
-				break;
-			}
-		}
-		if (old != sta->tx_rate_idx) {
-			switch (sta->tx_rate_idx) {
-			case 0: sta->tx_rate = 10; break;
-			case 1: sta->tx_rate = 20; break;
-			case 2: sta->tx_rate = 55; break;
-			case 3: sta->tx_rate = 110; break;
-			default: sta->tx_rate = 0; break;
-			}
-			PDEBUG(DEBUG_AP,
-			       "%s: STA %pM TX rate lowered to %d\n",
-			       local->dev->name, sta->addr, sta->tx_rate);
-		}
-		sta->tx_consecutive_exc = 0;
-	}
-	spin_unlock(&local->ap->sta_table_lock);
-}
-
-
-static void hostap_update_sta_ps2(local_info_t *local, struct sta_info *sta,
-				  int pwrmgt, int type, int stype)
-{
-	if (pwrmgt && !(sta->flags & WLAN_STA_PS)) {
-		sta->flags |= WLAN_STA_PS;
-		PDEBUG(DEBUG_PS2, "STA %pM changed to use PS "
-		       "mode (type=0x%02X, stype=0x%02X)\n",
-		       sta->addr, type >> 2, stype >> 4);
-	} else if (!pwrmgt && (sta->flags & WLAN_STA_PS)) {
-		sta->flags &= ~WLAN_STA_PS;
-		PDEBUG(DEBUG_PS2, "STA %pM changed to not use "
-		       "PS mode (type=0x%02X, stype=0x%02X)\n",
-		       sta->addr, type >> 2, stype >> 4);
-		if (type != IEEE80211_FTYPE_CTL ||
-		    stype != IEEE80211_STYPE_PSPOLL)
-			schedule_packet_send(local, sta);
-	}
-}
-
-
-/* Called only as a tasklet (software IRQ). Called for each RX frame to update
- * STA power saving state. pwrmgt is a flag from 802.11 frame_control field. */
-int hostap_update_sta_ps(local_info_t *local, struct ieee80211_hdr *hdr)
-{
-	struct sta_info *sta;
-	u16 fc;
-
-	spin_lock(&local->ap->sta_table_lock);
-	sta = ap_get_sta(local->ap, hdr->addr2);
-	if (sta)
-		atomic_inc(&sta->users);
-	spin_unlock(&local->ap->sta_table_lock);
-
-	if (!sta)
-		return -1;
-
-	fc = le16_to_cpu(hdr->frame_control);
-	hostap_update_sta_ps2(local, sta, fc & IEEE80211_FCTL_PM,
-			      fc & IEEE80211_FCTL_FTYPE,
-			      fc & IEEE80211_FCTL_STYPE);
-
-	atomic_dec(&sta->users);
-	return 0;
-}
-
-
-/* Called only as a tasklet (software IRQ). Called for each RX frame after
- * getting RX header and payload from hardware. */
-ap_rx_ret hostap_handle_sta_rx(local_info_t *local, struct net_device *dev,
-			       struct sk_buff *skb,
-			       struct hostap_80211_rx_status *rx_stats,
-			       int wds)
-{
-	int ret;
-	struct sta_info *sta;
-	u16 fc, type, stype;
-	struct ieee80211_hdr *hdr;
-
-	if (local->ap == NULL)
-		return AP_RX_CONTINUE;
-
-	hdr = (struct ieee80211_hdr *) skb->data;
-
-	fc = le16_to_cpu(hdr->frame_control);
-	type = fc & IEEE80211_FCTL_FTYPE;
-	stype = fc & IEEE80211_FCTL_STYPE;
-
-	spin_lock(&local->ap->sta_table_lock);
-	sta = ap_get_sta(local->ap, hdr->addr2);
-	if (sta)
-		atomic_inc(&sta->users);
-	spin_unlock(&local->ap->sta_table_lock);
-
-	if (sta && !(sta->flags & WLAN_STA_AUTHORIZED))
-		ret = AP_RX_CONTINUE_NOT_AUTHORIZED;
-	else
-		ret = AP_RX_CONTINUE;
-
-
-	if (fc & IEEE80211_FCTL_TODS) {
-		if (!wds && (sta == NULL || !(sta->flags & WLAN_STA_ASSOC))) {
-			if (local->hostapd) {
-				prism2_rx_80211(local->apdev, skb, rx_stats,
-						PRISM2_RX_NON_ASSOC);
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-			} else {
-				printk(KERN_DEBUG "%s: dropped received packet"
-				       " from non-associated STA %pM"
-				       " (type=0x%02x, subtype=0x%02x)\n",
-				       dev->name, hdr->addr2,
-				       type >> 2, stype >> 4);
-				hostap_rx(dev, skb, rx_stats);
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-			}
-			ret = AP_RX_EXIT;
-			goto out;
-		}
-	} else if (fc & IEEE80211_FCTL_FROMDS) {
-		if (!wds) {
-			/* FromDS frame - not for us; probably
-			 * broadcast/multicast in another BSS - drop */
-			if (ether_addr_equal(hdr->addr1, dev->dev_addr)) {
-				printk(KERN_DEBUG "Odd.. FromDS packet "
-				       "received with own BSSID\n");
-				hostap_dump_rx_80211(dev->name, skb, rx_stats);
-			}
-			ret = AP_RX_DROP;
-			goto out;
-		}
-	} else if (stype == IEEE80211_STYPE_NULLFUNC && sta == NULL &&
-		   ether_addr_equal(hdr->addr1, dev->dev_addr)) {
-
-		if (local->hostapd) {
-			prism2_rx_80211(local->apdev, skb, rx_stats,
-					PRISM2_RX_NON_ASSOC);
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-		} else {
-			/* At least Lucent f/w seems to send data::nullfunc
-			 * frames with no ToDS flag when the current AP returns
-			 * after being unavailable for some time. Speed up
-			 * re-association by informing the station about it not
-			 * being associated. */
-			printk(KERN_DEBUG "%s: rejected received nullfunc frame"
-			       " without ToDS from not associated STA %pM\n",
-			       dev->name, hdr->addr2);
-			hostap_rx(dev, skb, rx_stats);
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-		}
-		ret = AP_RX_EXIT;
-		goto out;
-	} else if (stype == IEEE80211_STYPE_NULLFUNC) {
-		/* At least Lucent cards seem to send periodic nullfunc
-		 * frames with ToDS. Let these through to update SQ
-		 * stats and PS state. Nullfunc frames do not contain
-		 * any data and they will be dropped below. */
-	} else {
-		/* If BSSID (Addr3) is foreign, this frame is a normal
-		 * broadcast frame from an IBSS network. Drop it silently.
-		 * If BSSID is own, report the dropping of this frame. */
-		if (ether_addr_equal(hdr->addr3, dev->dev_addr)) {
-			printk(KERN_DEBUG "%s: dropped received packet from %pM"
-			       " with no ToDS flag "
-			       "(type=0x%02x, subtype=0x%02x)\n", dev->name,
-			       hdr->addr2, type >> 2, stype >> 4);
-			hostap_dump_rx_80211(dev->name, skb, rx_stats);
-		}
-		ret = AP_RX_DROP;
-		goto out;
-	}
-
-	if (sta) {
-		hostap_update_sta_ps2(local, sta, fc & IEEE80211_FCTL_PM,
-				      type, stype);
-
-		sta->rx_packets++;
-		sta->rx_bytes += skb->len;
-		sta->last_rx = jiffies;
-	}
-
-	if (local->ap->nullfunc_ack && stype == IEEE80211_STYPE_NULLFUNC &&
-	    fc & IEEE80211_FCTL_TODS) {
-		if (local->hostapd) {
-			prism2_rx_80211(local->apdev, skb, rx_stats,
-					PRISM2_RX_NULLFUNC_ACK);
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-		} else {
-			/* some STA f/w's seem to require control::ACK frame
-			 * for data::nullfunc, but Prism2 f/w 0.8.0 (at least
-			 * from Compaq) does not send this.. Try to generate
-			 * ACK for these frames from the host driver to make
-			 * power saving work with, e.g., Lucent WaveLAN f/w */
-			hostap_rx(dev, skb, rx_stats);
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-		}
-		ret = AP_RX_EXIT;
-		goto out;
-	}
-
- out:
-	if (sta)
-		atomic_dec(&sta->users);
-
-	return ret;
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-int hostap_handle_sta_crypto(local_info_t *local,
-			     struct ieee80211_hdr *hdr,
-			     struct lib80211_crypt_data **crypt,
-			     void **sta_ptr)
-{
-	struct sta_info *sta;
-
-	spin_lock(&local->ap->sta_table_lock);
-	sta = ap_get_sta(local->ap, hdr->addr2);
-	if (sta)
-		atomic_inc(&sta->users);
-	spin_unlock(&local->ap->sta_table_lock);
-
-	if (!sta)
-		return -1;
-
-	if (sta->crypt) {
-		*crypt = sta->crypt;
-		*sta_ptr = sta;
-		/* hostap_handle_sta_release() will be called to release STA
-		 * info */
-	} else
-		atomic_dec(&sta->users);
-
-	return 0;
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-int hostap_is_sta_assoc(struct ap_data *ap, u8 *sta_addr)
-{
-	struct sta_info *sta;
-	int ret = 0;
-
-	spin_lock(&ap->sta_table_lock);
-	sta = ap_get_sta(ap, sta_addr);
-	if (sta != NULL && (sta->flags & WLAN_STA_ASSOC) && !sta->ap)
-		ret = 1;
-	spin_unlock(&ap->sta_table_lock);
-
-	return ret;
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-int hostap_is_sta_authorized(struct ap_data *ap, u8 *sta_addr)
-{
-	struct sta_info *sta;
-	int ret = 0;
-
-	spin_lock(&ap->sta_table_lock);
-	sta = ap_get_sta(ap, sta_addr);
-	if (sta != NULL && (sta->flags & WLAN_STA_ASSOC) && !sta->ap &&
-	    ((sta->flags & WLAN_STA_AUTHORIZED) ||
-	     ap->local->ieee_802_1x == 0))
-		ret = 1;
-	spin_unlock(&ap->sta_table_lock);
-
-	return ret;
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-int hostap_add_sta(struct ap_data *ap, u8 *sta_addr)
-{
-	struct sta_info *sta;
-	int ret = 1;
-
-	if (!ap)
-		return -1;
-
-	spin_lock(&ap->sta_table_lock);
-	sta = ap_get_sta(ap, sta_addr);
-	if (sta)
-		ret = 0;
-	spin_unlock(&ap->sta_table_lock);
-
-	if (ret == 1) {
-		sta = ap_add_sta(ap, sta_addr);
-		if (!sta)
-			return -1;
-		sta->flags = WLAN_STA_AUTH | WLAN_STA_ASSOC;
-		sta->ap = 1;
-		memset(sta->supported_rates, 0, sizeof(sta->supported_rates));
-		/* No way of knowing which rates are supported since we did not
-		 * get supported rates element from beacon/assoc req. Assume
-		 * that remote end supports all 802.11b rates. */
-		sta->supported_rates[0] = 0x82;
-		sta->supported_rates[1] = 0x84;
-		sta->supported_rates[2] = 0x0b;
-		sta->supported_rates[3] = 0x16;
-		sta->tx_supp_rates = WLAN_RATE_1M | WLAN_RATE_2M |
-			WLAN_RATE_5M5 | WLAN_RATE_11M;
-		sta->tx_rate = 110;
-		sta->tx_max_rate = sta->tx_rate_idx = 3;
-	}
-
-	return ret;
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-int hostap_update_rx_stats(struct ap_data *ap,
-			   struct ieee80211_hdr *hdr,
-			   struct hostap_80211_rx_status *rx_stats)
-{
-	struct sta_info *sta;
-
-	if (!ap)
-		return -1;
-
-	spin_lock(&ap->sta_table_lock);
-	sta = ap_get_sta(ap, hdr->addr2);
-	if (sta) {
-		sta->last_rx_silence = rx_stats->noise;
-		sta->last_rx_signal = rx_stats->signal;
-		sta->last_rx_rate = rx_stats->rate;
-		sta->last_rx_updated = IW_QUAL_ALL_UPDATED | IW_QUAL_DBM;
-		if (rx_stats->rate == 10)
-			sta->rx_count[0]++;
-		else if (rx_stats->rate == 20)
-			sta->rx_count[1]++;
-		else if (rx_stats->rate == 55)
-			sta->rx_count[2]++;
-		else if (rx_stats->rate == 110)
-			sta->rx_count[3]++;
-	}
-	spin_unlock(&ap->sta_table_lock);
-
-	return sta ? 0 : -1;
-}
-
-
-void hostap_update_rates(local_info_t *local)
-{
-	struct sta_info *sta;
-	struct ap_data *ap = local->ap;
-
-	if (!ap)
-		return;
-
-	spin_lock_bh(&ap->sta_table_lock);
-	list_for_each_entry(sta, &ap->sta_list, list) {
-		prism2_check_tx_rates(sta);
-	}
-	spin_unlock_bh(&ap->sta_table_lock);
-}
-
-
-void * ap_crypt_get_ptrs(struct ap_data *ap, u8 *addr, int permanent,
-			 struct lib80211_crypt_data ***crypt)
-{
-	struct sta_info *sta;
-
-	spin_lock_bh(&ap->sta_table_lock);
-	sta = ap_get_sta(ap, addr);
-	if (sta)
-		atomic_inc(&sta->users);
-	spin_unlock_bh(&ap->sta_table_lock);
-
-	if (!sta && permanent)
-		sta = ap_add_sta(ap, addr);
-
-	if (!sta)
-		return NULL;
-
-	if (permanent)
-		sta->flags |= WLAN_STA_PERM;
-
-	*crypt = &sta->crypt;
-
-	return sta;
-}
-
-
-void hostap_add_wds_links(local_info_t *local)
-{
-	struct ap_data *ap = local->ap;
-	struct sta_info *sta;
-
-	spin_lock_bh(&ap->sta_table_lock);
-	list_for_each_entry(sta, &ap->sta_list, list) {
-		if (sta->ap)
-			hostap_wds_link_oper(local, sta->addr, WDS_ADD);
-	}
-	spin_unlock_bh(&ap->sta_table_lock);
-
-	schedule_work(&local->ap->wds_oper_queue);
-}
-
-
-void hostap_wds_link_oper(local_info_t *local, u8 *addr, wds_oper_type type)
-{
-	struct wds_oper_data *entry;
-
-	entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
-	if (!entry)
-		return;
-	memcpy(entry->addr, addr, ETH_ALEN);
-	entry->type = type;
-	spin_lock_bh(&local->lock);
-	entry->next = local->ap->wds_oper_entries;
-	local->ap->wds_oper_entries = entry;
-	spin_unlock_bh(&local->lock);
-
-	schedule_work(&local->ap->wds_oper_queue);
-}
-
-
-EXPORT_SYMBOL(hostap_init_data);
-EXPORT_SYMBOL(hostap_init_ap_proc);
-EXPORT_SYMBOL(hostap_free_data);
-EXPORT_SYMBOL(hostap_check_sta_fw_version);
-EXPORT_SYMBOL(hostap_handle_sta_tx_exc);
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
diff --git a/drivers/net/wireless/intersil/hostap/hostap_ap.h b/drivers/net/wireless/intersil/hostap/hostap_ap.h
deleted file mode 100644
index b7ac9e2f1a39..000000000000
--- a/drivers/net/wireless/intersil/hostap/hostap_ap.h
+++ /dev/null
@@ -1,264 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef HOSTAP_AP_H
-#define HOSTAP_AP_H
-
-#include "hostap_80211.h"
-
-/* AP data structures for STAs */
-
-/* maximum number of frames to buffer per STA */
-#define STA_MAX_TX_BUFFER 32
-
-/* STA flags */
-#define WLAN_STA_AUTH BIT(0)
-#define WLAN_STA_ASSOC BIT(1)
-#define WLAN_STA_PS BIT(2)
-#define WLAN_STA_TIM BIT(3) /* TIM bit is on for PS stations */
-#define WLAN_STA_PERM BIT(4) /* permanent; do not remove entry on expiration */
-#define WLAN_STA_AUTHORIZED BIT(5) /* If 802.1X is used, this flag is
-				    * controlling whether STA is authorized to
-				    * send and receive non-IEEE 802.1X frames
-				    */
-#define WLAN_STA_PENDING_POLL BIT(6) /* pending activity poll not ACKed */
-
-#define WLAN_RATE_1M BIT(0)
-#define WLAN_RATE_2M BIT(1)
-#define WLAN_RATE_5M5 BIT(2)
-#define WLAN_RATE_11M BIT(3)
-#define WLAN_RATE_COUNT 4
-
-/* Maximum size of Supported Rates info element. IEEE 802.11 has a limit of 8,
- * but some pre-standard IEEE 802.11g products use longer elements. */
-#define WLAN_SUPP_RATES_MAX 32
-
-/* Try to increase TX rate after # successfully sent consecutive packets */
-#define WLAN_RATE_UPDATE_COUNT 50
-
-/* Decrease TX rate after # consecutive dropped packets */
-#define WLAN_RATE_DECREASE_THRESHOLD 2
-
-struct sta_info {
-	struct list_head list;
-	struct sta_info *hnext; /* next entry in hash table list */
-	atomic_t users; /* number of users (do not remove if > 0) */
-	struct proc_dir_entry *proc;
-
-	u8 addr[6];
-	u16 aid; /* STA's unique AID (1 .. 2007) or 0 if not yet assigned */
-	u32 flags;
-	u16 capability;
-	u16 listen_interval; /* or beacon_int for APs */
-	u8 supported_rates[WLAN_SUPP_RATES_MAX];
-
-	unsigned long last_auth;
-	unsigned long last_assoc;
-	unsigned long last_rx;
-	unsigned long last_tx;
-	unsigned long rx_packets, tx_packets;
-	unsigned long rx_bytes, tx_bytes;
-	struct sk_buff_head tx_buf;
-	/* FIX: timeout buffers with an expiry time somehow derived from
-	 * listen_interval */
-
-	s8 last_rx_silence; /* Noise in dBm */
-	s8 last_rx_signal; /* Signal strength in dBm */
-	u8 last_rx_rate; /* TX rate in 0.1 Mbps */
-	u8 last_rx_updated; /* IWSPY's struct iw_quality::updated */
-
-	u8 tx_supp_rates; /* bit field of supported TX rates */
-	u8 tx_rate; /* current TX rate (in 0.1 Mbps) */
-	u8 tx_rate_idx; /* current TX rate (WLAN_RATE_*) */
-	u8 tx_max_rate; /* max TX rate (WLAN_RATE_*) */
-	u32 tx_count[WLAN_RATE_COUNT]; /* number of frames sent (per rate) */
-	u32 rx_count[WLAN_RATE_COUNT]; /* number of frames received (per rate)
-					*/
-	u32 tx_since_last_failure;
-	u32 tx_consecutive_exc;
-
-	struct lib80211_crypt_data *crypt;
-
-	int ap; /* whether this station is an AP */
-
-	local_info_t *local;
-
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-	union {
-		struct {
-			char *challenge; /* shared key authentication
-					  * challenge */
-		} sta;
-		struct {
-			int ssid_len;
-			unsigned char ssid[MAX_SSID_LEN + 1]; /* AP's ssid */
-			int channel;
-			unsigned long last_beacon; /* last RX beacon time */
-		} ap;
-	} u;
-
-	struct timer_list timer;
-	enum { STA_NULLFUNC = 0, STA_DISASSOC, STA_DEAUTH } timeout_next;
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-};
-
-
-#define MAX_STA_COUNT 1024
-
-/* Maximum number of AIDs to use for STAs; must be 2007 or lower
- * (8802.11 limitation) */
-#define MAX_AID_TABLE_SIZE 128
-
-#define STA_HASH_SIZE 256
-#define STA_HASH(sta) (sta[5])
-
-
-/* Default value for maximum station inactivity. After AP_MAX_INACTIVITY_SEC
- * has passed since last received frame from the station, a nullfunc data
- * frame is sent to the station. If this frame is not acknowledged and no other
- * frames have been received, the station will be disassociated after
- * AP_DISASSOC_DELAY. Similarly, a the station will be deauthenticated after
- * AP_DEAUTH_DELAY. AP_TIMEOUT_RESOLUTION is the resolution that is used with
- * max inactivity timer. */
-#define AP_MAX_INACTIVITY_SEC (5 * 60)
-#define AP_DISASSOC_DELAY (HZ)
-#define AP_DEAUTH_DELAY (HZ)
-
-/* ap_policy: whether to accept frames to/from other APs/IBSS */
-typedef enum {
-	AP_OTHER_AP_SKIP_ALL = 0,
-	AP_OTHER_AP_SAME_SSID = 1,
-	AP_OTHER_AP_ALL = 2,
-	AP_OTHER_AP_EVEN_IBSS = 3
-} ap_policy_enum;
-
-#define PRISM2_AUTH_OPEN BIT(0)
-#define PRISM2_AUTH_SHARED_KEY BIT(1)
-
-
-/* MAC address-based restrictions */
-struct mac_entry {
-	struct list_head list;
-	u8 addr[6];
-};
-
-struct mac_restrictions {
-	enum { MAC_POLICY_OPEN = 0, MAC_POLICY_ALLOW, MAC_POLICY_DENY } policy;
-	unsigned int entries;
-	struct list_head mac_list;
-	spinlock_t lock;
-};
-
-
-struct add_sta_proc_data {
-	u8 addr[ETH_ALEN];
-	struct add_sta_proc_data *next;
-};
-
-
-typedef enum { WDS_ADD, WDS_DEL } wds_oper_type;
-struct wds_oper_data {
-	wds_oper_type type;
-	u8 addr[ETH_ALEN];
-	struct wds_oper_data *next;
-};
-
-
-struct ap_data {
-	int initialized; /* whether ap_data has been initialized */
-	local_info_t *local;
-	int bridge_packets; /* send packet to associated STAs directly to the
-			     * wireless media instead of higher layers in the
-			     * kernel */
-	unsigned int bridged_unicast; /* number of unicast frames bridged on
-				       * wireless media */
-	unsigned int bridged_multicast; /* number of non-unicast frames
-					 * bridged on wireless media */
-	unsigned int tx_drop_nonassoc; /* number of unicast TX packets dropped
-					* because they were to an address that
-					* was not associated */
-	int nullfunc_ack; /* use workaround for nullfunc frame ACKs */
-
-	spinlock_t sta_table_lock;
-	int num_sta; /* number of entries in sta_list */
-	struct list_head sta_list; /* STA info list head */
-	struct sta_info *sta_hash[STA_HASH_SIZE];
-
-	struct proc_dir_entry *proc;
-
-	ap_policy_enum ap_policy;
-	unsigned int max_inactivity;
-	int autom_ap_wds;
-
-	struct mac_restrictions mac_restrictions; /* MAC-based auth */
-	int last_tx_rate;
-
-	struct work_struct add_sta_proc_queue;
-	struct add_sta_proc_data *add_sta_proc_entries;
-
-	struct work_struct wds_oper_queue;
-	struct wds_oper_data *wds_oper_entries;
-
-	u16 tx_callback_idx;
-
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-	/* pointers to STA info; based on allocated AID or NULL if AID free
-	 * AID is in the range 1-2007, so sta_aid[0] corresponders to AID 1
-	 * and so on
-	 */
-	struct sta_info *sta_aid[MAX_AID_TABLE_SIZE];
-
-	u16 tx_callback_auth, tx_callback_assoc, tx_callback_poll;
-
-	/* WEP operations for generating challenges to be used with shared key
-	 * authentication */
-	struct lib80211_crypto_ops *crypt;
-	void *crypt_priv;
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-};
-
-
-void hostap_rx(struct net_device *dev, struct sk_buff *skb,
-	       struct hostap_80211_rx_status *rx_stats);
-void hostap_init_data(local_info_t *local);
-void hostap_init_ap_proc(local_info_t *local);
-void hostap_free_data(struct ap_data *ap);
-void hostap_check_sta_fw_version(struct ap_data *ap, int sta_fw_ver);
-
-typedef enum {
-	AP_TX_CONTINUE, AP_TX_DROP, AP_TX_RETRY, AP_TX_BUFFERED,
-	AP_TX_CONTINUE_NOT_AUTHORIZED
-} ap_tx_ret;
-struct hostap_tx_data {
-	struct sk_buff *skb;
-	int host_encrypt;
-	struct lib80211_crypt_data *crypt;
-	void *sta_ptr;
-};
-ap_tx_ret hostap_handle_sta_tx(local_info_t *local, struct hostap_tx_data *tx);
-void hostap_handle_sta_release(void *ptr);
-void hostap_handle_sta_tx_exc(local_info_t *local, struct sk_buff *skb);
-int hostap_update_sta_ps(local_info_t *local, struct ieee80211_hdr *hdr);
-typedef enum {
-	AP_RX_CONTINUE, AP_RX_DROP, AP_RX_EXIT, AP_RX_CONTINUE_NOT_AUTHORIZED
-} ap_rx_ret;
-ap_rx_ret hostap_handle_sta_rx(local_info_t *local, struct net_device *dev,
-			       struct sk_buff *skb,
-			       struct hostap_80211_rx_status *rx_stats,
-			       int wds);
-int hostap_handle_sta_crypto(local_info_t *local, struct ieee80211_hdr *hdr,
-			     struct lib80211_crypt_data **crypt,
-			     void **sta_ptr);
-int hostap_is_sta_assoc(struct ap_data *ap, u8 *sta_addr);
-int hostap_is_sta_authorized(struct ap_data *ap, u8 *sta_addr);
-int hostap_add_sta(struct ap_data *ap, u8 *sta_addr);
-int hostap_update_rx_stats(struct ap_data *ap, struct ieee80211_hdr *hdr,
-			   struct hostap_80211_rx_status *rx_stats);
-void hostap_update_rates(local_info_t *local);
-void hostap_add_wds_links(local_info_t *local);
-void hostap_wds_link_oper(local_info_t *local, u8 *addr, wds_oper_type type);
-
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-void hostap_deauth_all_stas(struct net_device *dev, struct ap_data *ap,
-			    int resend);
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-
-#endif /* HOSTAP_AP_H */
diff --git a/drivers/net/wireless/intersil/hostap/hostap_common.h b/drivers/net/wireless/intersil/hostap/hostap_common.h
deleted file mode 100644
index dd29a8e8d349..000000000000
--- a/drivers/net/wireless/intersil/hostap/hostap_common.h
+++ /dev/null
@@ -1,420 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef HOSTAP_COMMON_H
-#define HOSTAP_COMMON_H
-
-#include <linux/types.h>
-#include <linux/if_ether.h>
-
-/* IEEE 802.11 defines */
-
-/* HFA384X Configuration RIDs */
-#define HFA384X_RID_CNFPORTTYPE 0xFC00
-#define HFA384X_RID_CNFOWNMACADDR 0xFC01
-#define HFA384X_RID_CNFDESIREDSSID 0xFC02
-#define HFA384X_RID_CNFOWNCHANNEL 0xFC03
-#define HFA384X_RID_CNFOWNSSID 0xFC04
-#define HFA384X_RID_CNFOWNATIMWINDOW 0xFC05
-#define HFA384X_RID_CNFSYSTEMSCALE 0xFC06
-#define HFA384X_RID_CNFMAXDATALEN 0xFC07
-#define HFA384X_RID_CNFWDSADDRESS 0xFC08
-#define HFA384X_RID_CNFPMENABLED 0xFC09
-#define HFA384X_RID_CNFPMEPS 0xFC0A
-#define HFA384X_RID_CNFMULTICASTRECEIVE 0xFC0B
-#define HFA384X_RID_CNFMAXSLEEPDURATION 0xFC0C
-#define HFA384X_RID_CNFPMHOLDOVERDURATION 0xFC0D
-#define HFA384X_RID_CNFOWNNAME 0xFC0E
-#define HFA384X_RID_CNFOWNDTIMPERIOD 0xFC10
-#define HFA384X_RID_CNFWDSADDRESS1 0xFC11 /* AP f/w only */
-#define HFA384X_RID_CNFWDSADDRESS2 0xFC12 /* AP f/w only */
-#define HFA384X_RID_CNFWDSADDRESS3 0xFC13 /* AP f/w only */
-#define HFA384X_RID_CNFWDSADDRESS4 0xFC14 /* AP f/w only */
-#define HFA384X_RID_CNFWDSADDRESS5 0xFC15 /* AP f/w only */
-#define HFA384X_RID_CNFWDSADDRESS6 0xFC16 /* AP f/w only */
-#define HFA384X_RID_CNFMULTICASTPMBUFFERING 0xFC17 /* AP f/w only */
-#define HFA384X_RID_UNKNOWN1 0xFC20
-#define HFA384X_RID_UNKNOWN2 0xFC21
-#define HFA384X_RID_CNFWEPDEFAULTKEYID 0xFC23
-#define HFA384X_RID_CNFDEFAULTKEY0 0xFC24
-#define HFA384X_RID_CNFDEFAULTKEY1 0xFC25
-#define HFA384X_RID_CNFDEFAULTKEY2 0xFC26
-#define HFA384X_RID_CNFDEFAULTKEY3 0xFC27
-#define HFA384X_RID_CNFWEPFLAGS 0xFC28
-#define HFA384X_RID_CNFWEPKEYMAPPINGTABLE 0xFC29
-#define HFA384X_RID_CNFAUTHENTICATION 0xFC2A
-#define HFA384X_RID_CNFMAXASSOCSTA 0xFC2B /* AP f/w only */
-#define HFA384X_RID_CNFTXCONTROL 0xFC2C
-#define HFA384X_RID_CNFROAMINGMODE 0xFC2D
-#define HFA384X_RID_CNFHOSTAUTHENTICATION 0xFC2E /* AP f/w only */
-#define HFA384X_RID_CNFRCVCRCERROR 0xFC30
-#define HFA384X_RID_CNFMMLIFE 0xFC31
-#define HFA384X_RID_CNFALTRETRYCOUNT 0xFC32
-#define HFA384X_RID_CNFBEACONINT 0xFC33
-#define HFA384X_RID_CNFAPPCFINFO 0xFC34 /* AP f/w only */
-#define HFA384X_RID_CNFSTAPCFINFO 0xFC35
-#define HFA384X_RID_CNFPRIORITYQUSAGE 0xFC37
-#define HFA384X_RID_CNFTIMCTRL 0xFC40
-#define HFA384X_RID_UNKNOWN3 0xFC41 /* added in STA f/w 0.7.x */
-#define HFA384X_RID_CNFTHIRTY2TALLY 0xFC42 /* added in STA f/w 0.8.0 */
-#define HFA384X_RID_CNFENHSECURITY 0xFC43 /* AP f/w or STA f/w >= 1.6.3 */
-#define HFA384X_RID_CNFDBMADJUST 0xFC46 /* added in STA f/w 1.3.1 */
-#define HFA384X_RID_GENERICELEMENT 0xFC48 /* added in STA f/w 1.7.0;
-					   * write only */
-#define HFA384X_RID_PROPAGATIONDELAY 0xFC49 /* added in STA f/w 1.7.6 */
-#define HFA384X_RID_GROUPADDRESSES 0xFC80
-#define HFA384X_RID_CREATEIBSS 0xFC81
-#define HFA384X_RID_FRAGMENTATIONTHRESHOLD 0xFC82
-#define HFA384X_RID_RTSTHRESHOLD 0xFC83
-#define HFA384X_RID_TXRATECONTROL 0xFC84
-#define HFA384X_RID_PROMISCUOUSMODE 0xFC85
-#define HFA384X_RID_FRAGMENTATIONTHRESHOLD0 0xFC90 /* AP f/w only */
-#define HFA384X_RID_FRAGMENTATIONTHRESHOLD1 0xFC91 /* AP f/w only */
-#define HFA384X_RID_FRAGMENTATIONTHRESHOLD2 0xFC92 /* AP f/w only */
-#define HFA384X_RID_FRAGMENTATIONTHRESHOLD3 0xFC93 /* AP f/w only */
-#define HFA384X_RID_FRAGMENTATIONTHRESHOLD4 0xFC94 /* AP f/w only */
-#define HFA384X_RID_FRAGMENTATIONTHRESHOLD5 0xFC95 /* AP f/w only */
-#define HFA384X_RID_FRAGMENTATIONTHRESHOLD6 0xFC96 /* AP f/w only */
-#define HFA384X_RID_RTSTHRESHOLD0 0xFC97 /* AP f/w only */
-#define HFA384X_RID_RTSTHRESHOLD1 0xFC98 /* AP f/w only */
-#define HFA384X_RID_RTSTHRESHOLD2 0xFC99 /* AP f/w only */
-#define HFA384X_RID_RTSTHRESHOLD3 0xFC9A /* AP f/w only */
-#define HFA384X_RID_RTSTHRESHOLD4 0xFC9B /* AP f/w only */
-#define HFA384X_RID_RTSTHRESHOLD5 0xFC9C /* AP f/w only */
-#define HFA384X_RID_RTSTHRESHOLD6 0xFC9D /* AP f/w only */
-#define HFA384X_RID_TXRATECONTROL0 0xFC9E /* AP f/w only */
-#define HFA384X_RID_TXRATECONTROL1 0xFC9F /* AP f/w only */
-#define HFA384X_RID_TXRATECONTROL2 0xFCA0 /* AP f/w only */
-#define HFA384X_RID_TXRATECONTROL3 0xFCA1 /* AP f/w only */
-#define HFA384X_RID_TXRATECONTROL4 0xFCA2 /* AP f/w only */
-#define HFA384X_RID_TXRATECONTROL5 0xFCA3 /* AP f/w only */
-#define HFA384X_RID_TXRATECONTROL6 0xFCA4 /* AP f/w only */
-#define HFA384X_RID_CNFSHORTPREAMBLE 0xFCB0
-#define HFA384X_RID_CNFEXCLUDELONGPREAMBLE 0xFCB1
-#define HFA384X_RID_CNFAUTHENTICATIONRSPTO 0xFCB2
-#define HFA384X_RID_CNFBASICRATES 0xFCB3
-#define HFA384X_RID_CNFSUPPORTEDRATES 0xFCB4
-#define HFA384X_RID_CNFFALLBACKCTRL 0xFCB5 /* added in STA f/w 1.3.1 */
-#define HFA384X_RID_WEPKEYDISABLE 0xFCB6 /* added in STA f/w 1.3.1 */
-#define HFA384X_RID_WEPKEYMAPINDEX 0xFCB7 /* ? */
-#define HFA384X_RID_BROADCASTKEYID 0xFCB8 /* ? */
-#define HFA384X_RID_ENTSECFLAGEYID 0xFCB9 /* ? */
-#define HFA384X_RID_CNFPASSIVESCANCTRL 0xFCBA /* added in STA f/w 1.5.0 */
-#define HFA384X_RID_SSNHANDLINGMODE 0xFCBB /* added in STA f/w 1.7.0 */
-#define HFA384X_RID_MDCCONTROL 0xFCBC /* added in STA f/w 1.7.0 */
-#define HFA384X_RID_MDCCOUNTRY 0xFCBD /* added in STA f/w 1.7.0 */
-#define HFA384X_RID_TXPOWERMAX 0xFCBE /* added in STA f/w 1.7.0 */
-#define HFA384X_RID_CNFLFOENABLED 0xFCBF /* added in STA f/w 1.6.3 */
-#define HFA384X_RID_CAPINFO 0xFCC0 /* added in STA f/w 1.7.0 */
-#define HFA384X_RID_LISTENINTERVAL 0xFCC1 /* added in STA f/w 1.7.0 */
-#define HFA384X_RID_SW_ANT_DIV 0xFCC2 /* added in STA f/w 1.7.0; Prism3 */
-#define HFA384X_RID_LED_CTRL 0xFCC4 /* added in STA f/w 1.7.6 */
-#define HFA384X_RID_HFODELAY 0xFCC5 /* added in STA f/w 1.7.6 */
-#define HFA384X_RID_DISALLOWEDBSSID 0xFCC6 /* added in STA f/w 1.8.0 */
-#define HFA384X_RID_TICKTIME 0xFCE0
-#define HFA384X_RID_SCANREQUEST 0xFCE1
-#define HFA384X_RID_JOINREQUEST 0xFCE2
-#define HFA384X_RID_AUTHENTICATESTATION 0xFCE3 /* AP f/w only */
-#define HFA384X_RID_CHANNELINFOREQUEST 0xFCE4 /* AP f/w only */
-#define HFA384X_RID_HOSTSCAN 0xFCE5 /* added in STA f/w 1.3.1 */
-
-/* HFA384X Information RIDs */
-#define HFA384X_RID_MAXLOADTIME 0xFD00
-#define HFA384X_RID_DOWNLOADBUFFER 0xFD01
-#define HFA384X_RID_PRIID 0xFD02
-#define HFA384X_RID_PRISUPRANGE 0xFD03
-#define HFA384X_RID_CFIACTRANGES 0xFD04
-#define HFA384X_RID_NICSERNUM 0xFD0A
-#define HFA384X_RID_NICID 0xFD0B
-#define HFA384X_RID_MFISUPRANGE 0xFD0C
-#define HFA384X_RID_CFISUPRANGE 0xFD0D
-#define HFA384X_RID_CHANNELLIST 0xFD10
-#define HFA384X_RID_REGULATORYDOMAINS 0xFD11
-#define HFA384X_RID_TEMPTYPE 0xFD12
-#define HFA384X_RID_CIS 0xFD13
-#define HFA384X_RID_STAID 0xFD20
-#define HFA384X_RID_STASUPRANGE 0xFD21
-#define HFA384X_RID_MFIACTRANGES 0xFD22
-#define HFA384X_RID_CFIACTRANGES2 0xFD23
-#define HFA384X_RID_PRODUCTNAME 0xFD24 /* added in STA f/w 1.3.1;
-					* only Prism2.5(?) */
-#define HFA384X_RID_PORTSTATUS 0xFD40
-#define HFA384X_RID_CURRENTSSID 0xFD41
-#define HFA384X_RID_CURRENTBSSID 0xFD42
-#define HFA384X_RID_COMMSQUALITY 0xFD43
-#define HFA384X_RID_CURRENTTXRATE 0xFD44
-#define HFA384X_RID_CURRENTBEACONINTERVAL 0xFD45
-#define HFA384X_RID_CURRENTSCALETHRESHOLDS 0xFD46
-#define HFA384X_RID_PROTOCOLRSPTIME 0xFD47
-#define HFA384X_RID_SHORTRETRYLIMIT 0xFD48
-#define HFA384X_RID_LONGRETRYLIMIT 0xFD49
-#define HFA384X_RID_MAXTRANSMITLIFETIME 0xFD4A
-#define HFA384X_RID_MAXRECEIVELIFETIME 0xFD4B
-#define HFA384X_RID_CFPOLLABLE 0xFD4C
-#define HFA384X_RID_AUTHENTICATIONALGORITHMS 0xFD4D
-#define HFA384X_RID_PRIVACYOPTIONIMPLEMENTED 0xFD4F
-#define HFA384X_RID_DBMCOMMSQUALITY 0xFD51 /* added in STA f/w 1.3.1 */
-#define HFA384X_RID_CURRENTTXRATE1 0xFD80 /* AP f/w only */
-#define HFA384X_RID_CURRENTTXRATE2 0xFD81 /* AP f/w only */
-#define HFA384X_RID_CURRENTTXRATE3 0xFD82 /* AP f/w only */
-#define HFA384X_RID_CURRENTTXRATE4 0xFD83 /* AP f/w only */
-#define HFA384X_RID_CURRENTTXRATE5 0xFD84 /* AP f/w only */
-#define HFA384X_RID_CURRENTTXRATE6 0xFD85 /* AP f/w only */
-#define HFA384X_RID_OWNMACADDR 0xFD86 /* AP f/w only */
-#define HFA384X_RID_SCANRESULTSTABLE 0xFD88 /* added in STA f/w 0.8.3 */
-#define HFA384X_RID_HOSTSCANRESULTS 0xFD89 /* added in STA f/w 1.3.1 */
-#define HFA384X_RID_AUTHENTICATIONUSED 0xFD8A /* added in STA f/w 1.3.4 */
-#define HFA384X_RID_CNFFAASWITCHCTRL 0xFD8B /* added in STA f/w 1.6.3 */
-#define HFA384X_RID_ASSOCIATIONFAILURE 0xFD8D /* added in STA f/w 1.8.0 */
-#define HFA384X_RID_PHYTYPE 0xFDC0
-#define HFA384X_RID_CURRENTCHANNEL 0xFDC1
-#define HFA384X_RID_CURRENTPOWERSTATE 0xFDC2
-#define HFA384X_RID_CCAMODE 0xFDC3
-#define HFA384X_RID_SUPPORTEDDATARATES 0xFDC6
-#define HFA384X_RID_LFO_VOLT_REG_TEST_RES 0xFDC7 /* added in STA f/w 1.7.1 */
-#define HFA384X_RID_BUILDSEQ 0xFFFE
-#define HFA384X_RID_FWID 0xFFFF
-
-
-struct hfa384x_comp_ident
-{
-	__le16 id;
-	__le16 variant;
-	__le16 major;
-	__le16 minor;
-} __packed;
-
-#define HFA384X_COMP_ID_PRI 0x15
-#define HFA384X_COMP_ID_STA 0x1f
-#define HFA384X_COMP_ID_FW_AP 0x14b
-
-struct hfa384x_sup_range
-{
-	__le16 role;
-	__le16 id;
-	__le16 variant;
-	__le16 bottom;
-	__le16 top;
-} __packed;
-
-
-struct hfa384x_build_id
-{
-	__le16 pri_seq;
-	__le16 sec_seq;
-} __packed;
-
-/* FD01 - Download Buffer */
-struct hfa384x_rid_download_buffer
-{
-	__le16 page;
-	__le16 offset;
-	__le16 length;
-} __packed;
-
-/* BSS connection quality (RID FD43 range, RID FD51 dBm-normalized) */
-struct hfa384x_comms_quality {
-	__le16 comm_qual; /* 0 .. 92 */
-	__le16 signal_level; /* 27 .. 154 */
-	__le16 noise_level; /* 27 .. 154 */
-} __packed;
-
-
-/* netdevice private ioctls (used, e.g., with iwpriv from user space) */
-
-/* New wireless extensions API - SET/GET convention (even ioctl numbers are
- * root only)
- */
-#define PRISM2_IOCTL_PRISM2_PARAM (SIOCIWFIRSTPRIV + 0)
-#define PRISM2_IOCTL_GET_PRISM2_PARAM (SIOCIWFIRSTPRIV + 1)
-#define PRISM2_IOCTL_WRITEMIF (SIOCIWFIRSTPRIV + 2)
-#define PRISM2_IOCTL_READMIF (SIOCIWFIRSTPRIV + 3)
-#define PRISM2_IOCTL_MONITOR (SIOCIWFIRSTPRIV + 4)
-#define PRISM2_IOCTL_RESET (SIOCIWFIRSTPRIV + 6)
-#define PRISM2_IOCTL_INQUIRE (SIOCIWFIRSTPRIV + 8)
-#define PRISM2_IOCTL_WDS_ADD (SIOCIWFIRSTPRIV + 10)
-#define PRISM2_IOCTL_WDS_DEL (SIOCIWFIRSTPRIV + 12)
-#define PRISM2_IOCTL_SET_RID_WORD (SIOCIWFIRSTPRIV + 14)
-#define PRISM2_IOCTL_MACCMD (SIOCIWFIRSTPRIV + 16)
-#define PRISM2_IOCTL_ADDMAC (SIOCIWFIRSTPRIV + 18)
-#define PRISM2_IOCTL_DELMAC (SIOCIWFIRSTPRIV + 20)
-#define PRISM2_IOCTL_KICKMAC (SIOCIWFIRSTPRIV + 22)
-
-/* following are not in SIOCGIWPRIV list; check permission in the driver code
- */
-#define PRISM2_IOCTL_DOWNLOAD (SIOCDEVPRIVATE + 13)
-#define PRISM2_IOCTL_HOSTAPD (SIOCDEVPRIVATE + 14)
-
-
-/* PRISM2_IOCTL_PRISM2_PARAM ioctl() subtypes: */
-enum {
-	/* PRISM2_PARAM_PTYPE = 1, */ /* REMOVED 2003-10-22 */
-	PRISM2_PARAM_TXRATECTRL = 2,
-	PRISM2_PARAM_BEACON_INT = 3,
-	PRISM2_PARAM_PSEUDO_IBSS = 4,
-	PRISM2_PARAM_ALC = 5,
-	/* PRISM2_PARAM_TXPOWER = 6, */ /* REMOVED 2003-10-22 */
-	PRISM2_PARAM_DUMP = 7,
-	PRISM2_PARAM_OTHER_AP_POLICY = 8,
-	PRISM2_PARAM_AP_MAX_INACTIVITY = 9,
-	PRISM2_PARAM_AP_BRIDGE_PACKETS = 10,
-	PRISM2_PARAM_DTIM_PERIOD = 11,
-	PRISM2_PARAM_AP_NULLFUNC_ACK = 12,
-	PRISM2_PARAM_MAX_WDS = 13,
-	PRISM2_PARAM_AP_AUTOM_AP_WDS = 14,
-	PRISM2_PARAM_AP_AUTH_ALGS = 15,
-	PRISM2_PARAM_MONITOR_ALLOW_FCSERR = 16,
-	PRISM2_PARAM_HOST_ENCRYPT = 17,
-	PRISM2_PARAM_HOST_DECRYPT = 18,
-	/* PRISM2_PARAM_BUS_MASTER_THRESHOLD_RX = 19, REMOVED 2005-08-14 */
-	/* PRISM2_PARAM_BUS_MASTER_THRESHOLD_TX = 20, REMOVED 2005-08-14 */
-	PRISM2_PARAM_HOST_ROAMING = 21,
-	PRISM2_PARAM_BCRX_STA_KEY = 22,
-	PRISM2_PARAM_IEEE_802_1X = 23,
-	PRISM2_PARAM_ANTSEL_TX = 24,
-	PRISM2_PARAM_ANTSEL_RX = 25,
-	PRISM2_PARAM_MONITOR_TYPE = 26,
-	PRISM2_PARAM_WDS_TYPE = 27,
-	PRISM2_PARAM_HOSTSCAN = 28,
-	PRISM2_PARAM_AP_SCAN = 29,
-	PRISM2_PARAM_ENH_SEC = 30,
-	PRISM2_PARAM_IO_DEBUG = 31,
-	PRISM2_PARAM_BASIC_RATES = 32,
-	PRISM2_PARAM_OPER_RATES = 33,
-	PRISM2_PARAM_HOSTAPD = 34,
-	PRISM2_PARAM_HOSTAPD_STA = 35,
-	PRISM2_PARAM_WPA = 36,
-	PRISM2_PARAM_PRIVACY_INVOKED = 37,
-	PRISM2_PARAM_TKIP_COUNTERMEASURES = 38,
-	PRISM2_PARAM_DROP_UNENCRYPTED = 39,
-	PRISM2_PARAM_SCAN_CHANNEL_MASK = 40,
-};
-
-enum { HOSTAP_ANTSEL_DO_NOT_TOUCH = 0, HOSTAP_ANTSEL_DIVERSITY = 1,
-       HOSTAP_ANTSEL_LOW = 2, HOSTAP_ANTSEL_HIGH = 3 };
-
-
-/* PRISM2_IOCTL_MACCMD ioctl() subcommands: */
-enum { AP_MAC_CMD_POLICY_OPEN = 0, AP_MAC_CMD_POLICY_ALLOW = 1,
-       AP_MAC_CMD_POLICY_DENY = 2, AP_MAC_CMD_FLUSH = 3,
-       AP_MAC_CMD_KICKALL = 4 };
-
-
-/* PRISM2_IOCTL_DOWNLOAD ioctl() dl_cmd: */
-enum {
-	PRISM2_DOWNLOAD_VOLATILE = 1 /* RAM */,
-	/* Note! Old versions of prism2_srec have a fatal error in CRC-16
-	 * calculation, which will corrupt all non-volatile downloads.
-	 * PRISM2_DOWNLOAD_NON_VOLATILE used to be 2, but it is now 3 to
-	 * prevent use of old versions of prism2_srec for non-volatile
-	 * download. */
-	PRISM2_DOWNLOAD_NON_VOLATILE = 3 /* FLASH */,
-	PRISM2_DOWNLOAD_VOLATILE_GENESIS = 4 /* RAM in Genesis mode */,
-	/* Persistent versions of volatile download commands (keep firmware
-	 * data in memory and automatically re-download after hw_reset */
-	PRISM2_DOWNLOAD_VOLATILE_PERSISTENT = 5,
-	PRISM2_DOWNLOAD_VOLATILE_GENESIS_PERSISTENT = 6,
-};
-
-struct prism2_download_param {
-	u32 dl_cmd;
-	u32 start_addr;
-	u32 num_areas;
-	struct prism2_download_area {
-		u32 addr; /* wlan card address */
-		u32 len;
-		void __user *ptr; /* pointer to data in user space */
-	} data[];
-};
-
-#define PRISM2_MAX_DOWNLOAD_AREA_LEN 131072
-#define PRISM2_MAX_DOWNLOAD_LEN 262144
-
-
-/* PRISM2_IOCTL_HOSTAPD ioctl() cmd: */
-enum {
-	PRISM2_HOSTAPD_FLUSH = 1,
-	PRISM2_HOSTAPD_ADD_STA = 2,
-	PRISM2_HOSTAPD_REMOVE_STA = 3,
-	PRISM2_HOSTAPD_GET_INFO_STA = 4,
-	/* REMOVED: PRISM2_HOSTAPD_RESET_TXEXC_STA = 5, */
-	PRISM2_SET_ENCRYPTION = 6,
-	PRISM2_GET_ENCRYPTION = 7,
-	PRISM2_HOSTAPD_SET_FLAGS_STA = 8,
-	PRISM2_HOSTAPD_GET_RID = 9,
-	PRISM2_HOSTAPD_SET_RID = 10,
-	PRISM2_HOSTAPD_SET_ASSOC_AP_ADDR = 11,
-	PRISM2_HOSTAPD_SET_GENERIC_ELEMENT = 12,
-	PRISM2_HOSTAPD_MLME = 13,
-	PRISM2_HOSTAPD_SCAN_REQ = 14,
-	PRISM2_HOSTAPD_STA_CLEAR_STATS = 15,
-};
-
-#define PRISM2_HOSTAPD_MAX_BUF_SIZE 1024
-#define PRISM2_HOSTAPD_RID_HDR_LEN \
-offsetof(struct prism2_hostapd_param, u.rid.data)
-#define PRISM2_HOSTAPD_GENERIC_ELEMENT_HDR_LEN \
-offsetof(struct prism2_hostapd_param, u.generic_elem.data)
-
-/* Maximum length for algorithm names (-1 for nul termination) used in ioctl()
- */
-#define HOSTAP_CRYPT_ALG_NAME_LEN 16
-
-
-struct prism2_hostapd_param {
-	u32 cmd;
-	u8 sta_addr[ETH_ALEN];
-	union {
-		struct {
-			u16 aid;
-			u16 capability;
-			u8 tx_supp_rates;
-		} add_sta;
-		struct {
-			u32 inactive_sec;
-		} get_info_sta;
-		struct {
-			u8 alg[HOSTAP_CRYPT_ALG_NAME_LEN];
-			u32 flags;
-			u32 err;
-			u8 idx;
-			u8 seq[8]; /* sequence counter (set: RX, get: TX) */
-			u16 key_len;
-			u8 key[0];
-		} crypt;
-		struct {
-			u32 flags_and;
-			u32 flags_or;
-		} set_flags_sta;
-		struct {
-			u16 rid;
-			u16 len;
-			u8 data[0];
-		} rid;
-		struct {
-			u8 len;
-			u8 data[0];
-		} generic_elem;
-		struct {
-#define MLME_STA_DEAUTH 0
-#define MLME_STA_DISASSOC 1
-			u16 cmd;
-			u16 reason_code;
-		} mlme;
-		struct {
-			u8 ssid_len;
-			u8 ssid[32];
-		} scan_req;
-	} u;
-};
-
-#define HOSTAP_CRYPT_FLAG_SET_TX_KEY BIT(0)
-#define HOSTAP_CRYPT_FLAG_PERMANENT BIT(1)
-
-#define HOSTAP_CRYPT_ERR_UNKNOWN_ALG 2
-#define HOSTAP_CRYPT_ERR_UNKNOWN_ADDR 3
-#define HOSTAP_CRYPT_ERR_CRYPT_INIT_FAILED 4
-#define HOSTAP_CRYPT_ERR_KEY_SET_FAILED 5
-#define HOSTAP_CRYPT_ERR_TX_KEY_SET_FAILED 6
-#define HOSTAP_CRYPT_ERR_CARD_CONF_FAILED 7
-
-
-#endif /* HOSTAP_COMMON_H */
diff --git a/drivers/net/wireless/intersil/hostap/hostap_config.h b/drivers/net/wireless/intersil/hostap/hostap_config.h
deleted file mode 100644
index 3ebd55847fad..000000000000
--- a/drivers/net/wireless/intersil/hostap/hostap_config.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef HOSTAP_CONFIG_H
-#define HOSTAP_CONFIG_H
-
-/* In the previous versions of Host AP driver, support for user space version
- * of IEEE 802.11 management (hostapd) used to be disabled in the default
- * configuration. From now on, support for hostapd is always included and it is
- * possible to disable kernel driver version of IEEE 802.11 management with a
- * separate define, PRISM2_NO_KERNEL_IEEE80211_MGMT. */
-/* #define PRISM2_NO_KERNEL_IEEE80211_MGMT */
-
-/* Maximum number of events handler per one interrupt */
-#define PRISM2_MAX_INTERRUPT_EVENTS 20
-
-/* Include code for downloading firmware images into volatile RAM. */
-#define PRISM2_DOWNLOAD_SUPPORT
-
-/* Allow kernel configuration to enable download support. */
-#if !defined(PRISM2_DOWNLOAD_SUPPORT) && defined(CONFIG_HOSTAP_FIRMWARE)
-#define PRISM2_DOWNLOAD_SUPPORT
-#endif
-
-/* Allow kernel configuration to enable non-volatile download support. */
-#ifdef CONFIG_HOSTAP_FIRMWARE_NVRAM
-#define PRISM2_NON_VOLATILE_DOWNLOAD
-#endif
-
-/* Save low-level I/O for debugging. This should not be enabled in normal use.
- */
-/* #define PRISM2_IO_DEBUG */
-
-/* Following defines can be used to remove unneeded parts of the driver, e.g.,
- * to limit the size of the kernel module. Definitions can be added here in
- * hostap_config.h or they can be added to make command with ccflags-y,
- * e.g.,
- * 'make pccard ccflags-y="-DPRISM2_NO_DEBUG -DPRISM2_NO_PROCFS_DEBUG"'
- */
-
-/* Do not include debug messages into the driver */
-/* #define PRISM2_NO_DEBUG */
-
-/* Do not include /proc/net/prism2/wlan#/{registers,debug} */
-/* #define PRISM2_NO_PROCFS_DEBUG */
-
-/* Do not include station functionality (i.e., allow only Master (Host AP) mode
- */
-/* #define PRISM2_NO_STATION_MODES */
-
-#endif /* HOSTAP_CONFIG_H */
diff --git a/drivers/net/wireless/intersil/hostap/hostap_cs.c b/drivers/net/wireless/intersil/hostap/hostap_cs.c
deleted file mode 100644
index ec7db2badc40..000000000000
--- a/drivers/net/wireless/intersil/hostap/hostap_cs.c
+++ /dev/null
@@ -1,710 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-#define PRISM2_PCCARD
-
-#include <linux/module.h>
-#include <linux/if.h>
-#include <linux/slab.h>
-#include <linux/wait.h>
-#include <linux/timer.h>
-#include <linux/skbuff.h>
-#include <linux/netdevice.h>
-#include <linux/workqueue.h>
-#include <linux/wireless.h>
-#include <net/iw_handler.h>
-
-#include <pcmcia/cistpl.h>
-#include <pcmcia/cisreg.h>
-#include <pcmcia/ds.h>
-
-#include <asm/io.h>
-
-#include "hostap_wlan.h"
-
-
-static char *dev_info = "hostap_cs";
-
-MODULE_AUTHOR("Jouni Malinen");
-MODULE_DESCRIPTION("Support for Intersil Prism2-based 802.11 wireless LAN "
-		   "cards (PC Card).");
-MODULE_LICENSE("GPL");
-
-
-static int ignore_cis_vcc;
-module_param(ignore_cis_vcc, int, 0444);
-MODULE_PARM_DESC(ignore_cis_vcc, "Ignore broken CIS VCC entry");
-
-
-/* struct local_info::hw_priv */
-struct hostap_cs_priv {
-	struct pcmcia_device *link;
-	int sandisk_connectplus;
-};
-
-
-#ifdef PRISM2_IO_DEBUG
-
-static inline void hfa384x_outb_debug(struct net_device *dev, int a, u8 v)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	unsigned long flags;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-	spin_lock_irqsave(&local->lock, flags);
-	prism2_io_debug_add(dev, PRISM2_IO_DEBUG_CMD_OUTB, a, v);
-	outb(v, dev->base_addr + a);
-	spin_unlock_irqrestore(&local->lock, flags);
-}
-
-static inline u8 hfa384x_inb_debug(struct net_device *dev, int a)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	unsigned long flags;
-	u8 v;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-	spin_lock_irqsave(&local->lock, flags);
-	v = inb(dev->base_addr + a);
-	prism2_io_debug_add(dev, PRISM2_IO_DEBUG_CMD_INB, a, v);
-	spin_unlock_irqrestore(&local->lock, flags);
-	return v;
-}
-
-static inline void hfa384x_outw_debug(struct net_device *dev, int a, u16 v)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	unsigned long flags;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-	spin_lock_irqsave(&local->lock, flags);
-	prism2_io_debug_add(dev, PRISM2_IO_DEBUG_CMD_OUTW, a, v);
-	outw(v, dev->base_addr + a);
-	spin_unlock_irqrestore(&local->lock, flags);
-}
-
-static inline u16 hfa384x_inw_debug(struct net_device *dev, int a)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	unsigned long flags;
-	u16 v;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-	spin_lock_irqsave(&local->lock, flags);
-	v = inw(dev->base_addr + a);
-	prism2_io_debug_add(dev, PRISM2_IO_DEBUG_CMD_INW, a, v);
-	spin_unlock_irqrestore(&local->lock, flags);
-	return v;
-}
-
-static inline void hfa384x_outsw_debug(struct net_device *dev, int a,
-				       u8 *buf, int wc)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	unsigned long flags;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-	spin_lock_irqsave(&local->lock, flags);
-	prism2_io_debug_add(dev, PRISM2_IO_DEBUG_CMD_OUTSW, a, wc);
-	outsw(dev->base_addr + a, buf, wc);
-	spin_unlock_irqrestore(&local->lock, flags);
-}
-
-static inline void hfa384x_insw_debug(struct net_device *dev, int a,
-				      u8 *buf, int wc)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	unsigned long flags;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-	spin_lock_irqsave(&local->lock, flags);
-	prism2_io_debug_add(dev, PRISM2_IO_DEBUG_CMD_INSW, a, wc);
-	insw(dev->base_addr + a, buf, wc);
-	spin_unlock_irqrestore(&local->lock, flags);
-}
-
-#define HFA384X_OUTB(v,a) hfa384x_outb_debug(dev, (a), (v))
-#define HFA384X_INB(a) hfa384x_inb_debug(dev, (a))
-#define HFA384X_OUTW(v,a) hfa384x_outw_debug(dev, (a), (v))
-#define HFA384X_INW(a) hfa384x_inw_debug(dev, (a))
-#define HFA384X_OUTSW(a, buf, wc) hfa384x_outsw_debug(dev, (a), (buf), (wc))
-#define HFA384X_INSW(a, buf, wc) hfa384x_insw_debug(dev, (a), (buf), (wc))
-
-#else /* PRISM2_IO_DEBUG */
-
-#define HFA384X_OUTB(v,a) outb((v), dev->base_addr + (a))
-#define HFA384X_INB(a) inb(dev->base_addr + (a))
-#define HFA384X_OUTW(v,a) outw((v), dev->base_addr + (a))
-#define HFA384X_INW(a) inw(dev->base_addr + (a))
-#define HFA384X_INSW(a, buf, wc) insw(dev->base_addr + (a), buf, wc)
-#define HFA384X_OUTSW(a, buf, wc) outsw(dev->base_addr + (a), buf, wc)
-
-#endif /* PRISM2_IO_DEBUG */
-
-
-static int hfa384x_from_bap(struct net_device *dev, u16 bap, void *buf,
-			    int len)
-{
-	u16 d_off;
-	u16 *pos;
-
-	d_off = (bap == 1) ? HFA384X_DATA1_OFF : HFA384X_DATA0_OFF;
-	pos = (u16 *) buf;
-
-	if (len / 2)
-		HFA384X_INSW(d_off, buf, len / 2);
-	pos += len / 2;
-
-	if (len & 1)
-		*((char *) pos) = HFA384X_INB(d_off);
-
-	return 0;
-}
-
-
-static int hfa384x_to_bap(struct net_device *dev, u16 bap, void *buf, int len)
-{
-	u16 d_off;
-	u16 *pos;
-
-	d_off = (bap == 1) ? HFA384X_DATA1_OFF : HFA384X_DATA0_OFF;
-	pos = (u16 *) buf;
-
-	if (len / 2)
-		HFA384X_OUTSW(d_off, buf, len / 2);
-	pos += len / 2;
-
-	if (len & 1)
-		HFA384X_OUTB(*((char *) pos), d_off);
-
-	return 0;
-}
-
-
-/* FIX: This might change at some point.. */
-#include "hostap_hw.c"
-
-
-
-static void prism2_detach(struct pcmcia_device *p_dev);
-static void prism2_release(u_long arg);
-static int prism2_config(struct pcmcia_device *link);
-
-
-static int prism2_pccard_card_present(local_info_t *local)
-{
-	struct hostap_cs_priv *hw_priv = local->hw_priv;
-	if (hw_priv != NULL && hw_priv->link != NULL && pcmcia_dev_present(hw_priv->link))
-		return 1;
-	return 0;
-}
-
-
-/*
- * SanDisk CompactFlash WLAN Flashcard - Product Manual v1.0
- * Document No. 20-10-00058, January 2004
- * http://www.sandisk.com/pdf/industrial/ProdManualCFWLANv1.0.pdf
- */
-#define SANDISK_WLAN_ACTIVATION_OFF 0x40
-#define SANDISK_HCR_OFF 0x42
-
-
-static void sandisk_set_iobase(local_info_t *local)
-{
-	int res;
-	struct hostap_cs_priv *hw_priv = local->hw_priv;
-
-	res = pcmcia_write_config_byte(hw_priv->link, 0x10,
-				hw_priv->link->resource[0]->start & 0x00ff);
-	if (res != 0) {
-		printk(KERN_DEBUG "Prism3 SanDisk - failed to set I/O base 0 -"
-		       " res=%d\n", res);
-	}
-	udelay(10);
-
-	res = pcmcia_write_config_byte(hw_priv->link, 0x12,
-				(hw_priv->link->resource[0]->start >> 8) & 0x00ff);
-	if (res != 0) {
-		printk(KERN_DEBUG "Prism3 SanDisk - failed to set I/O base 1 -"
-		       " res=%d\n", res);
-	}
-}
-
-
-static void sandisk_write_hcr(local_info_t *local, int hcr)
-{
-	struct net_device *dev = local->dev;
-	int i;
-
-	HFA384X_OUTB(0x80, SANDISK_WLAN_ACTIVATION_OFF);
-	udelay(50);
-	for (i = 0; i < 10; i++) {
-		HFA384X_OUTB(hcr, SANDISK_HCR_OFF);
-	}
-	udelay(55);
-	HFA384X_OUTB(0x45, SANDISK_WLAN_ACTIVATION_OFF);
-}
-
-
-static int sandisk_enable_wireless(struct net_device *dev)
-{
-	int res, ret = 0;
-	struct hostap_interface *iface = netdev_priv(dev);
-	local_info_t *local = iface->local;
-	struct hostap_cs_priv *hw_priv = local->hw_priv;
-
-	if (resource_size(hw_priv->link->resource[0]) < 0x42) {
-		/* Not enough ports to be SanDisk multi-function card */
-		ret = -ENODEV;
-		goto done;
-	}
-
-	if (hw_priv->link->manf_id != 0xd601 || hw_priv->link->card_id != 0x0101) {
-		/* No SanDisk manfid found */
-		ret = -ENODEV;
-		goto done;
-	}
-
-	if (hw_priv->link->socket->functions < 2) {
-		/* No multi-function links found */
-		ret = -ENODEV;
-		goto done;
-	}
-
-	printk(KERN_DEBUG "%s: Multi-function SanDisk ConnectPlus detected"
-	       " - using vendor-specific initialization\n", dev->name);
-	hw_priv->sandisk_connectplus = 1;
-
-	res = pcmcia_write_config_byte(hw_priv->link, CISREG_COR,
-				COR_SOFT_RESET);
-	if (res != 0) {
-		printk(KERN_DEBUG "%s: SanDisk - COR sreset failed (%d)\n",
-		       dev->name, res);
-		goto done;
-	}
-	mdelay(5);
-
-	/*
-	 * Do not enable interrupts here to avoid some bogus events. Interrupts
-	 * will be enabled during the first cor_sreset call.
-	 */
-	res = pcmcia_write_config_byte(hw_priv->link, CISREG_COR,
-				(COR_LEVEL_REQ | 0x8 | COR_ADDR_DECODE |
-					COR_FUNC_ENA));
-	if (res != 0) {
-		printk(KERN_DEBUG "%s: SanDisk - COR sreset failed (%d)\n",
-		       dev->name, res);
-		goto done;
-	}
-	mdelay(5);
-
-	sandisk_set_iobase(local);
-
-	HFA384X_OUTB(0xc5, SANDISK_WLAN_ACTIVATION_OFF);
-	udelay(10);
-	HFA384X_OUTB(0x4b, SANDISK_WLAN_ACTIVATION_OFF);
-	udelay(10);
-
-done:
-	return ret;
-}
-
-
-static void prism2_pccard_cor_sreset(local_info_t *local)
-{
-	int res;
-	u8 val;
-	struct hostap_cs_priv *hw_priv = local->hw_priv;
-
-	if (!prism2_pccard_card_present(local))
-	       return;
-
-	res = pcmcia_read_config_byte(hw_priv->link, CISREG_COR, &val);
-	if (res != 0) {
-		printk(KERN_DEBUG "prism2_pccard_cor_sreset failed 1 (%d)\n",
-		       res);
-		return;
-	}
-	printk(KERN_DEBUG "prism2_pccard_cor_sreset: original COR %02x\n",
-		val);
-
-	val |= COR_SOFT_RESET;
-	res = pcmcia_write_config_byte(hw_priv->link, CISREG_COR, val);
-	if (res != 0) {
-		printk(KERN_DEBUG "prism2_pccard_cor_sreset failed 2 (%d)\n",
-		       res);
-		return;
-	}
-
-	mdelay(hw_priv->sandisk_connectplus ? 5 : 2);
-
-	val &= ~COR_SOFT_RESET;
-	if (hw_priv->sandisk_connectplus)
-		val |= COR_IREQ_ENA;
-	res = pcmcia_write_config_byte(hw_priv->link, CISREG_COR, val);
-	if (res != 0) {
-		printk(KERN_DEBUG "prism2_pccard_cor_sreset failed 3 (%d)\n",
-		       res);
-		return;
-	}
-
-	mdelay(hw_priv->sandisk_connectplus ? 5 : 2);
-
-	if (hw_priv->sandisk_connectplus)
-		sandisk_set_iobase(local);
-}
-
-
-static void prism2_pccard_genesis_reset(local_info_t *local, int hcr)
-{
-	int res;
-	u8 old_cor;
-	struct hostap_cs_priv *hw_priv = local->hw_priv;
-
-	if (!prism2_pccard_card_present(local))
-	       return;
-
-	if (hw_priv->sandisk_connectplus) {
-		sandisk_write_hcr(local, hcr);
-		return;
-	}
-
-	res = pcmcia_read_config_byte(hw_priv->link, CISREG_COR, &old_cor);
-	if (res != 0) {
-		printk(KERN_DEBUG "%s failed 1 (%d)\n", __func__, res);
-		return;
-	}
-	printk(KERN_DEBUG "%s: original COR %02x\n", __func__, old_cor);
-
-	res = pcmcia_write_config_byte(hw_priv->link, CISREG_COR,
-				old_cor | COR_SOFT_RESET);
-	if (res != 0) {
-		printk(KERN_DEBUG "%s failed 2 (%d)\n", __func__, res);
-		return;
-	}
-
-	mdelay(10);
-
-	/* Setup Genesis mode */
-	res = pcmcia_write_config_byte(hw_priv->link, CISREG_CCSR, hcr);
-	if (res != 0) {
-		printk(KERN_DEBUG "%s failed 3 (%d)\n", __func__, res);
-		return;
-	}
-	mdelay(10);
-
-	res = pcmcia_write_config_byte(hw_priv->link, CISREG_COR,
-				old_cor & ~COR_SOFT_RESET);
-	if (res != 0) {
-		printk(KERN_DEBUG "%s failed 4 (%d)\n", __func__, res);
-		return;
-	}
-
-	mdelay(10);
-}
-
-
-static struct prism2_helper_functions prism2_pccard_funcs =
-{
-	.card_present	= prism2_pccard_card_present,
-	.cor_sreset	= prism2_pccard_cor_sreset,
-	.genesis_reset	= prism2_pccard_genesis_reset,
-	.hw_type	= HOSTAP_HW_PCCARD,
-};
-
-
-/* allocate local data and register with CardServices
- * initialize dev_link structure, but do not configure the card yet */
-static int hostap_cs_probe(struct pcmcia_device *p_dev)
-{
-	int ret;
-
-	PDEBUG(DEBUG_HW, "%s: setting Vcc=33 (constant)\n", dev_info);
-
-	ret = prism2_config(p_dev);
-	if (ret) {
-		PDEBUG(DEBUG_EXTRA, "prism2_config() failed\n");
-	}
-
-	return ret;
-}
-
-
-static void prism2_detach(struct pcmcia_device *link)
-{
-	PDEBUG(DEBUG_FLOW, "prism2_detach\n");
-
-	prism2_release((u_long)link);
-
-	/* release net devices */
-	if (link->priv) {
-		struct hostap_cs_priv *hw_priv;
-		struct net_device *dev;
-		struct hostap_interface *iface;
-		dev = link->priv;
-		iface = netdev_priv(dev);
-		hw_priv = iface->local->hw_priv;
-		prism2_free_local_data(dev);
-		kfree(hw_priv);
-	}
-}
-
-
-static int prism2_config_check(struct pcmcia_device *p_dev, void *priv_data)
-{
-	if (p_dev->config_index == 0)
-		return -EINVAL;
-
-	return pcmcia_request_io(p_dev);
-}
-
-static int prism2_config(struct pcmcia_device *link)
-{
-	struct net_device *dev;
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int ret;
-	struct hostap_cs_priv *hw_priv;
-	unsigned long flags;
-
-	PDEBUG(DEBUG_FLOW, "prism2_config()\n");
-
-	hw_priv = kzalloc(sizeof(*hw_priv), GFP_KERNEL);
-	if (hw_priv == NULL) {
-		ret = -ENOMEM;
-		goto failed;
-	}
-
-	/* Look for an appropriate configuration table entry in the CIS */
-	link->config_flags |= CONF_AUTO_SET_VPP | CONF_AUTO_AUDIO |
-		CONF_AUTO_CHECK_VCC | CONF_AUTO_SET_IO | CONF_ENABLE_IRQ;
-	if (ignore_cis_vcc)
-		link->config_flags &= ~CONF_AUTO_CHECK_VCC;
-	ret = pcmcia_loop_config(link, prism2_config_check, NULL);
-	if (ret) {
-		if (!ignore_cis_vcc)
-			printk(KERN_ERR "GetNextTuple(): No matching "
-			       "CIS configuration.  Maybe you need the "
-			       "ignore_cis_vcc=1 parameter.\n");
-		goto failed;
-	}
-
-	/* Need to allocate net_device before requesting IRQ handler */
-	dev = prism2_init_local_data(&prism2_pccard_funcs, 0,
-				     &link->dev);
-	if (!dev) {
-		ret = -ENOMEM;
-		goto failed;
-	}
-	link->priv = dev;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-	local->hw_priv = hw_priv;
-	hw_priv->link = link;
-
-	/*
-	 * We enable IRQ here, but IRQ handler will not proceed
-	 * until dev->base_addr is set below. This protect us from
-	 * receive interrupts when driver is not initialized.
-	 */
-	ret = pcmcia_request_irq(link, prism2_interrupt);
-	if (ret)
-		goto failed;
-
-	ret = pcmcia_enable_device(link);
-	if (ret)
-		goto failed;
-
-	spin_lock_irqsave(&local->irq_init_lock, flags);
-	dev->irq = link->irq;
-	dev->base_addr = link->resource[0]->start;
-	spin_unlock_irqrestore(&local->irq_init_lock, flags);
-
-	local->shutdown = 0;
-
-	sandisk_enable_wireless(dev);
-
-	ret = prism2_hw_config(dev, 1);
-	if (!ret)
-		ret = hostap_hw_ready(dev);
-
-	return ret;
-
- failed:
-	kfree(hw_priv);
-	prism2_release((u_long)link);
-	return ret;
-}
-
-
-static void prism2_release(u_long arg)
-{
-	struct pcmcia_device *link = (struct pcmcia_device *)arg;
-
-	PDEBUG(DEBUG_FLOW, "prism2_release\n");
-
-	if (link->priv) {
-		struct net_device *dev = link->priv;
-		struct hostap_interface *iface;
-
-		iface = netdev_priv(dev);
-		prism2_hw_shutdown(dev, 0);
-		iface->local->shutdown = 1;
-	}
-
-	pcmcia_disable_device(link);
-	PDEBUG(DEBUG_FLOW, "release - done\n");
-}
-
-static int hostap_cs_suspend(struct pcmcia_device *link)
-{
-	struct net_device *dev = (struct net_device *) link->priv;
-	int dev_open = 0;
-	struct hostap_interface *iface = NULL;
-
-	if (!dev)
-		return -ENODEV;
-
-	iface = netdev_priv(dev);
-
-	PDEBUG(DEBUG_EXTRA, "%s: CS_EVENT_PM_SUSPEND\n", dev_info);
-	if (iface && iface->local)
-		dev_open = iface->local->num_dev_open > 0;
-	if (dev_open) {
-		netif_stop_queue(dev);
-		netif_device_detach(dev);
-	}
-	prism2_suspend(dev);
-
-	return 0;
-}
-
-static int hostap_cs_resume(struct pcmcia_device *link)
-{
-	struct net_device *dev = (struct net_device *) link->priv;
-	int dev_open = 0;
-	struct hostap_interface *iface = NULL;
-
-	if (!dev)
-		return -ENODEV;
-
-	iface = netdev_priv(dev);
-
-	PDEBUG(DEBUG_EXTRA, "%s: CS_EVENT_PM_RESUME\n", dev_info);
-
-	if (iface && iface->local)
-		dev_open = iface->local->num_dev_open > 0;
-
-	prism2_hw_shutdown(dev, 1);
-	prism2_hw_config(dev, dev_open ? 0 : 1);
-	if (dev_open) {
-		netif_device_attach(dev);
-		netif_start_queue(dev);
-	}
-
-	return 0;
-}
-
-static const struct pcmcia_device_id hostap_cs_ids[] = {
-	PCMCIA_DEVICE_MANF_CARD(0x000b, 0x7100),
-	PCMCIA_DEVICE_MANF_CARD(0x000b, 0x7300),
-	PCMCIA_DEVICE_MANF_CARD(0x0101, 0x0777),
-	PCMCIA_DEVICE_MANF_CARD(0x0126, 0x8000),
-	PCMCIA_DEVICE_MANF_CARD(0x0138, 0x0002),
-	PCMCIA_DEVICE_MANF_CARD(0x01bf, 0x3301),
-	PCMCIA_DEVICE_MANF_CARD(0x0250, 0x0002),
-	PCMCIA_DEVICE_MANF_CARD(0x026f, 0x030b),
-	PCMCIA_DEVICE_MANF_CARD(0x0274, 0x1612),
-	PCMCIA_DEVICE_MANF_CARD(0x0274, 0x1613),
-	PCMCIA_DEVICE_MANF_CARD(0x028a, 0x0002),
-	PCMCIA_DEVICE_MANF_CARD(0x02aa, 0x0002),
-	PCMCIA_DEVICE_MANF_CARD(0x02d2, 0x0001),
-	PCMCIA_DEVICE_MANF_CARD(0x50c2, 0x0001),
-	PCMCIA_DEVICE_MANF_CARD(0x50c2, 0x7300),
-/*	PCMCIA_DEVICE_MANF_CARD(0xc00f, 0x0000),    conflict with pcnet_cs */
-	PCMCIA_DEVICE_MANF_CARD(0xc250, 0x0002),
-	PCMCIA_DEVICE_MANF_CARD(0xd601, 0x0002),
-	PCMCIA_DEVICE_MANF_CARD(0xd601, 0x0005),
-	PCMCIA_DEVICE_MANF_CARD(0xd601, 0x0010),
-	PCMCIA_DEVICE_MANF_CARD(0x0126, 0x0002),
-	PCMCIA_DEVICE_MANF_CARD_PROD_ID1(0xd601, 0x0005, "ADLINK 345 CF",
-					 0x2d858104),
-	PCMCIA_DEVICE_MANF_CARD_PROD_ID1(0x0156, 0x0002, "INTERSIL",
-					 0x74c5e40d),
-	PCMCIA_DEVICE_MANF_CARD_PROD_ID1(0x0156, 0x0002, "Intersil",
-					 0x4b801a17),
-	PCMCIA_DEVICE_MANF_CARD_PROD_ID3(0x0156, 0x0002, "Version 01.02",
-					 0x4b74baa0),
-	PCMCIA_MFC_DEVICE_PROD_ID12(0, "SanDisk", "ConnectPlus",
-				    0x7a954bd9, 0x74be00c6),
-	PCMCIA_DEVICE_PROD_ID123(
-		"Addtron", "AWP-100 Wireless PCMCIA", "Version 01.02",
-		0xe6ec52ce, 0x08649af2, 0x4b74baa0),
-	PCMCIA_DEVICE_PROD_ID123(
-		"Canon", "Wireless LAN CF Card K30225", "Version 01.00",
-		0x96ef6fe2, 0x263fcbab, 0xa57adb8c),
-	PCMCIA_DEVICE_PROD_ID123(
-		"D", "Link DWL-650 11Mbps WLAN Card", "Version 01.02",
-		0x71b18589, 0xb6f1b0ab, 0x4b74baa0),
-	PCMCIA_DEVICE_PROD_ID123(
-		"Instant Wireless ", " Network PC CARD", "Version 01.02",
-		0x11d901af, 0x6e9bd926, 0x4b74baa0),
-	PCMCIA_DEVICE_PROD_ID123(
-		"SMC", "SMC2632W", "Version 01.02",
-		0xc4f8b18b, 0x474a1f2a, 0x4b74baa0),
-	PCMCIA_DEVICE_PROD_ID12("BUFFALO", "WLI-CF-S11G", 
-				0x2decece3, 0x82067c18),
-	PCMCIA_DEVICE_PROD_ID12("Compaq", "WL200_11Mbps_Wireless_PCI_Card",
-				0x54f7c49c, 0x15a75e5b),
-	PCMCIA_DEVICE_PROD_ID12("INTERSIL", "HFA384x/IEEE",
-				0x74c5e40d, 0xdb472a18),
-	PCMCIA_DEVICE_PROD_ID12("Linksys", "Wireless CompactFlash Card",
-				0x0733cc81, 0x0c52f395),
-	PCMCIA_DEVICE_PROD_ID12(
-		"ZoomAir 11Mbps High", "Rate wireless Networking",
-		0x273fe3db, 0x32a1eaee),
-	PCMCIA_DEVICE_PROD_ID12("NETGEAR MA401 Wireless PC", "Card",
-		0xa37434e9, 0x9762e8f1),
-	PCMCIA_DEVICE_PROD_ID123(
-		"Pretec", "CompactWLAN Card 802.11b", "2.5",
-		0x1cadd3e5, 0xe697636c, 0x7a5bfcf1),
-	PCMCIA_DEVICE_PROD_ID123(
-		"U.S. Robotics", "IEEE 802.11b PC-CARD", "Version 01.02",
-		0xc7b8df9d, 0x1700d087, 0x4b74baa0),
-	PCMCIA_DEVICE_PROD_ID123(
-		"Allied Telesyn", "AT-WCL452 Wireless PCMCIA Radio",
-		"Ver. 1.00",
-		0x5cd01705, 0x4271660f, 0x9d08ee12),
-	PCMCIA_DEVICE_PROD_ID123(
-		"Wireless LAN" , "11Mbps PC Card", "Version 01.02",
-		0x4b8870ff, 0x70e946d1, 0x4b74baa0),
-	PCMCIA_DEVICE_PROD_ID3("HFA3863", 0x355cb092),
-	PCMCIA_DEVICE_PROD_ID3("ISL37100P", 0x630d52b2),
-	PCMCIA_DEVICE_PROD_ID3("ISL37101P-10", 0xdd97a26b),
-	PCMCIA_DEVICE_PROD_ID3("ISL37300P", 0xc9049a39),
-	PCMCIA_DEVICE_NULL
-};
-MODULE_DEVICE_TABLE(pcmcia, hostap_cs_ids);
-
-
-static struct pcmcia_driver hostap_driver = {
-	.name		= "hostap_cs",
-	.probe		= hostap_cs_probe,
-	.remove		= prism2_detach,
-	.owner		= THIS_MODULE,
-	.id_table	= hostap_cs_ids,
-	.suspend	= hostap_cs_suspend,
-	.resume		= hostap_cs_resume,
-};
-module_pcmcia_driver(hostap_driver);
diff --git a/drivers/net/wireless/intersil/hostap/hostap_download.c b/drivers/net/wireless/intersil/hostap/hostap_download.c
deleted file mode 100644
index 5e5bada28b5b..000000000000
--- a/drivers/net/wireless/intersil/hostap/hostap_download.c
+++ /dev/null
@@ -1,810 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-static int prism2_enable_aux_port(struct net_device *dev, int enable)
-{
-	u16 val, reg;
-	int i, tries;
-	unsigned long flags;
-	struct hostap_interface *iface;
-	local_info_t *local;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (local->no_pri) {
-		if (enable) {
-			PDEBUG(DEBUG_EXTRA2, "%s: no PRI f/w - assuming Aux "
-			       "port is already enabled\n", dev->name);
-		}
-		return 0;
-	}
-
-	spin_lock_irqsave(&local->cmdlock, flags);
-
-	/* wait until busy bit is clear */
-	tries = HFA384X_CMD_BUSY_TIMEOUT;
-	while (HFA384X_INW(HFA384X_CMD_OFF) & HFA384X_CMD_BUSY && tries > 0) {
-		tries--;
-		udelay(1);
-	}
-	if (tries == 0) {
-		reg = HFA384X_INW(HFA384X_CMD_OFF);
-		spin_unlock_irqrestore(&local->cmdlock, flags);
-		printk("%s: prism2_enable_aux_port - timeout - reg=0x%04x\n",
-		       dev->name, reg);
-		return -ETIMEDOUT;
-	}
-
-	val = HFA384X_INW(HFA384X_CONTROL_OFF);
-
-	if (enable) {
-		HFA384X_OUTW(HFA384X_AUX_MAGIC0, HFA384X_PARAM0_OFF);
-		HFA384X_OUTW(HFA384X_AUX_MAGIC1, HFA384X_PARAM1_OFF);
-		HFA384X_OUTW(HFA384X_AUX_MAGIC2, HFA384X_PARAM2_OFF);
-
-		if ((val & HFA384X_AUX_PORT_MASK) != HFA384X_AUX_PORT_DISABLED)
-			printk("prism2_enable_aux_port: was not disabled!?\n");
-		val &= ~HFA384X_AUX_PORT_MASK;
-		val |= HFA384X_AUX_PORT_ENABLE;
-	} else {
-		HFA384X_OUTW(0, HFA384X_PARAM0_OFF);
-		HFA384X_OUTW(0, HFA384X_PARAM1_OFF);
-		HFA384X_OUTW(0, HFA384X_PARAM2_OFF);
-
-		if ((val & HFA384X_AUX_PORT_MASK) != HFA384X_AUX_PORT_ENABLED)
-			printk("prism2_enable_aux_port: was not enabled!?\n");
-		val &= ~HFA384X_AUX_PORT_MASK;
-		val |= HFA384X_AUX_PORT_DISABLE;
-	}
-	HFA384X_OUTW(val, HFA384X_CONTROL_OFF);
-
-	udelay(5);
-
-	i = 10000;
-	while (i > 0) {
-		val = HFA384X_INW(HFA384X_CONTROL_OFF);
-		val &= HFA384X_AUX_PORT_MASK;
-
-		if ((enable && val == HFA384X_AUX_PORT_ENABLED) ||
-		    (!enable && val == HFA384X_AUX_PORT_DISABLED))
-			break;
-
-		udelay(10);
-		i--;
-	}
-
-	spin_unlock_irqrestore(&local->cmdlock, flags);
-
-	if (i == 0) {
-		printk("prism2_enable_aux_port(%d) timed out\n",
-		       enable);
-		return -ETIMEDOUT;
-	}
-
-	return 0;
-}
-
-
-static int hfa384x_from_aux(struct net_device *dev, unsigned int addr, int len,
-			    void *buf)
-{
-	u16 page, offset;
-	if (addr & 1 || len & 1)
-		return -1;
-
-	page = addr >> 7;
-	offset = addr & 0x7f;
-
-	HFA384X_OUTW(page, HFA384X_AUXPAGE_OFF);
-	HFA384X_OUTW(offset, HFA384X_AUXOFFSET_OFF);
-
-	udelay(5);
-
-#ifdef PRISM2_PCI
-	{
-		__le16 *pos = (__le16 *) buf;
-		while (len > 0) {
-			*pos++ = HFA384X_INW_DATA(HFA384X_AUXDATA_OFF);
-			len -= 2;
-		}
-	}
-#else /* PRISM2_PCI */
-	HFA384X_INSW(HFA384X_AUXDATA_OFF, buf, len / 2);
-#endif /* PRISM2_PCI */
-
-	return 0;
-}
-
-
-static int hfa384x_to_aux(struct net_device *dev, unsigned int addr, int len,
-			  void *buf)
-{
-	u16 page, offset;
-	if (addr & 1 || len & 1)
-		return -1;
-
-	page = addr >> 7;
-	offset = addr & 0x7f;
-
-	HFA384X_OUTW(page, HFA384X_AUXPAGE_OFF);
-	HFA384X_OUTW(offset, HFA384X_AUXOFFSET_OFF);
-
-	udelay(5);
-
-#ifdef PRISM2_PCI
-	{
-		__le16 *pos = (__le16 *) buf;
-		while (len > 0) {
-			HFA384X_OUTW_DATA(*pos++, HFA384X_AUXDATA_OFF);
-			len -= 2;
-		}
-	}
-#else /* PRISM2_PCI */
-	HFA384X_OUTSW(HFA384X_AUXDATA_OFF, buf, len / 2);
-#endif /* PRISM2_PCI */
-
-	return 0;
-}
-
-
-static int prism2_pda_ok(u8 *buf)
-{
-	__le16 *pda = (__le16 *) buf;
-	int pos;
-	u16 len, pdr;
-
-	if (buf[0] == 0xff && buf[1] == 0x00 && buf[2] == 0xff &&
-	    buf[3] == 0x00)
-		return 0;
-
-	pos = 0;
-	while (pos + 1 < PRISM2_PDA_SIZE / 2) {
-		len = le16_to_cpu(pda[pos]);
-		pdr = le16_to_cpu(pda[pos + 1]);
-		if (len == 0 || pos + len > PRISM2_PDA_SIZE / 2)
-			return 0;
-
-		if (pdr == 0x0000 && len == 2) {
-			/* PDA end found */
-			return 1;
-		}
-
-		pos += len + 1;
-	}
-
-	return 0;
-}
-
-
-#define prism2_download_aux_dump_npages 65536
-
-struct prism2_download_aux_dump {
-	local_info_t *local;
-	u16 page[0x80];
-};
-
-static int prism2_download_aux_dump_proc_show(struct seq_file *m, void *v)
-{
-	struct prism2_download_aux_dump *ctx = m->private;
-
-	hfa384x_from_aux(ctx->local->dev, (unsigned long)v - 1, 0x80, ctx->page);
-	seq_write(m, ctx->page, 0x80);
-	return 0;
-}
-
-static void *prism2_download_aux_dump_proc_start(struct seq_file *m, loff_t *_pos)
-{
-	struct prism2_download_aux_dump *ctx = m->private;
-	prism2_enable_aux_port(ctx->local->dev, 1);
-	if (*_pos >= prism2_download_aux_dump_npages)
-		return NULL;
-	return (void *)((unsigned long)*_pos + 1);
-}
-
-static void *prism2_download_aux_dump_proc_next(struct seq_file *m, void *v, loff_t *_pos)
-{
-	++*_pos;
-	if (*_pos >= prism2_download_aux_dump_npages)
-		return NULL;
-	return (void *)((unsigned long)*_pos + 1);
-}
-
-static void prism2_download_aux_dump_proc_stop(struct seq_file *m, void *v)
-{
-	struct prism2_download_aux_dump *ctx = m->private;
-	prism2_enable_aux_port(ctx->local->dev, 0);
-}
-
-static const struct seq_operations prism2_download_aux_dump_proc_seqops = {
-	.start	= prism2_download_aux_dump_proc_start,
-	.next	= prism2_download_aux_dump_proc_next,
-	.stop	= prism2_download_aux_dump_proc_stop,
-	.show	= prism2_download_aux_dump_proc_show,
-};
-
-static int prism2_download_aux_dump_proc_open(struct inode *inode, struct file *file)
-{
-	int ret = seq_open_private(file, &prism2_download_aux_dump_proc_seqops,
-				   sizeof(struct prism2_download_aux_dump));
-	if (ret == 0) {
-		struct seq_file *m = file->private_data;
-		m->private = pde_data(inode);
-	}
-	return ret;
-}
-
-static const struct proc_ops prism2_download_aux_dump_proc_ops = {
-	.proc_open		= prism2_download_aux_dump_proc_open,
-	.proc_read		= seq_read,
-	.proc_lseek		= seq_lseek,
-	.proc_release		= seq_release_private,
-};
-
-
-static u8 * prism2_read_pda(struct net_device *dev)
-{
-	u8 *buf;
-	int res, i, found = 0;
-#define NUM_PDA_ADDRS 4
-	unsigned int pda_addr[NUM_PDA_ADDRS] = {
-		0x7f0000 /* others than HFA3841 */,
-		0x3f0000 /* HFA3841 */,
-		0x390000 /* apparently used in older cards */,
-		0x7f0002 /* Intel PRO/Wireless 2011B (PCI) */,
-	};
-
-	buf = kmalloc(PRISM2_PDA_SIZE, GFP_KERNEL);
-	if (buf == NULL)
-		return NULL;
-
-	/* Note: wlan card should be in initial state (just after init cmd)
-	 * and no other operations should be performed concurrently. */
-
-	prism2_enable_aux_port(dev, 1);
-
-	for (i = 0; i < NUM_PDA_ADDRS; i++) {
-		PDEBUG(DEBUG_EXTRA2, "%s: trying to read PDA from 0x%08x",
-		       dev->name, pda_addr[i]);
-		res = hfa384x_from_aux(dev, pda_addr[i], PRISM2_PDA_SIZE, buf);
-		if (res)
-			continue;
-		if (res == 0 && prism2_pda_ok(buf)) {
-			PDEBUG2(DEBUG_EXTRA2, ": OK\n");
-			found = 1;
-			break;
-		} else {
-			PDEBUG2(DEBUG_EXTRA2, ": failed\n");
-		}
-	}
-
-	prism2_enable_aux_port(dev, 0);
-
-	if (!found) {
-		printk(KERN_DEBUG "%s: valid PDA not found\n", dev->name);
-		kfree(buf);
-		buf = NULL;
-	}
-
-	return buf;
-}
-
-
-static int prism2_download_volatile(local_info_t *local,
-				    struct prism2_download_data *param)
-{
-	struct net_device *dev = local->dev;
-	int ret = 0, i;
-	u16 param0, param1;
-
-	if (local->hw_downloading) {
-		printk(KERN_WARNING "%s: Already downloading - aborting new "
-		       "request\n", dev->name);
-		return -1;
-	}
-
-	local->hw_downloading = 1;
-	if (local->pri_only) {
-		hfa384x_disable_interrupts(dev);
-	} else {
-		prism2_hw_shutdown(dev, 0);
-
-		if (prism2_hw_init(dev, 0)) {
-			printk(KERN_WARNING "%s: Could not initialize card for"
-			       " download\n", dev->name);
-			ret = -1;
-			goto out;
-		}
-	}
-
-	if (prism2_enable_aux_port(dev, 1)) {
-		printk(KERN_WARNING "%s: Could not enable AUX port\n",
-		       dev->name);
-		ret = -1;
-		goto out;
-	}
-
-	param0 = param->start_addr & 0xffff;
-	param1 = param->start_addr >> 16;
-
-	HFA384X_OUTW(0, HFA384X_PARAM2_OFF);
-	HFA384X_OUTW(param1, HFA384X_PARAM1_OFF);
-	if (hfa384x_cmd_wait(dev, HFA384X_CMDCODE_DOWNLOAD |
-			     (HFA384X_PROGMODE_ENABLE_VOLATILE << 8),
-			     param0)) {
-		printk(KERN_WARNING "%s: Download command execution failed\n",
-		       dev->name);
-		ret = -1;
-		goto out;
-	}
-
-	for (i = 0; i < param->num_areas; i++) {
-		PDEBUG(DEBUG_EXTRA2, "%s: Writing %d bytes at 0x%08x\n",
-		       dev->name, param->data[i].len, param->data[i].addr);
-		if (hfa384x_to_aux(dev, param->data[i].addr,
-				   param->data[i].len, param->data[i].data)) {
-			printk(KERN_WARNING "%s: RAM download at 0x%08x "
-			       "(len=%d) failed\n", dev->name,
-			       param->data[i].addr, param->data[i].len);
-			ret = -1;
-			goto out;
-		}
-	}
-
-	HFA384X_OUTW(param1, HFA384X_PARAM1_OFF);
-	HFA384X_OUTW(0, HFA384X_PARAM2_OFF);
-	if (hfa384x_cmd_no_wait(dev, HFA384X_CMDCODE_DOWNLOAD |
-				(HFA384X_PROGMODE_DISABLE << 8), param0)) {
-		printk(KERN_WARNING "%s: Download command execution failed\n",
-		       dev->name);
-		ret = -1;
-		goto out;
-	}
-	/* ProgMode disable causes the hardware to restart itself from the
-	 * given starting address. Give hw some time and ACK command just in
-	 * case restart did not happen. */
-	mdelay(5);
-	HFA384X_OUTW(HFA384X_EV_CMD, HFA384X_EVACK_OFF);
-
-	if (prism2_enable_aux_port(dev, 0)) {
-		printk(KERN_DEBUG "%s: Disabling AUX port failed\n",
-		       dev->name);
-		/* continue anyway.. restart should have taken care of this */
-	}
-
-	mdelay(5);
-	local->hw_downloading = 0;
-	if (prism2_hw_config(dev, 2)) {
-		printk(KERN_WARNING "%s: Card configuration after RAM "
-		       "download failed\n", dev->name);
-		ret = -1;
-		goto out;
-	}
-
- out:
-	local->hw_downloading = 0;
-	return ret;
-}
-
-
-static int prism2_enable_genesis(local_info_t *local, int hcr)
-{
-	struct net_device *dev = local->dev;
-	u8 initseq[4] = { 0x00, 0xe1, 0xa1, 0xff };
-	u8 readbuf[4];
-
-	printk(KERN_DEBUG "%s: test Genesis mode with HCR 0x%02x\n",
-	       dev->name, hcr);
-	local->func->cor_sreset(local);
-	hfa384x_to_aux(dev, 0x7e0038, sizeof(initseq), initseq);
-	local->func->genesis_reset(local, hcr);
-
-	/* Readback test */
-	hfa384x_from_aux(dev, 0x7e0038, sizeof(readbuf), readbuf);
-	hfa384x_to_aux(dev, 0x7e0038, sizeof(initseq), initseq);
-	hfa384x_from_aux(dev, 0x7e0038, sizeof(readbuf), readbuf);
-
-	if (memcmp(initseq, readbuf, sizeof(initseq)) == 0) {
-		printk(KERN_DEBUG "Readback test succeeded, HCR 0x%02x\n",
-		       hcr);
-		return 0;
-	} else {
-		printk(KERN_DEBUG "Readback test failed, HCR 0x%02x write %4ph read %4ph\n",
-		       hcr, initseq, readbuf);
-		return 1;
-	}
-}
-
-
-static int prism2_get_ram_size(local_info_t *local)
-{
-	int ret;
-
-	/* Try to enable genesis mode; 0x1F for x8 SRAM or 0x0F for x16 SRAM */
-	if (prism2_enable_genesis(local, 0x1f) == 0)
-		ret = 8;
-	else if (prism2_enable_genesis(local, 0x0f) == 0)
-		ret = 16;
-	else
-		ret = -1;
-
-	/* Disable genesis mode */
-	local->func->genesis_reset(local, ret == 16 ? 0x07 : 0x17);
-
-	return ret;
-}
-
-
-static int prism2_download_genesis(local_info_t *local,
-				   struct prism2_download_data *param)
-{
-	struct net_device *dev = local->dev;
-	int ram16 = 0, i;
-	int ret = 0;
-
-	if (local->hw_downloading) {
-		printk(KERN_WARNING "%s: Already downloading - aborting new "
-		       "request\n", dev->name);
-		return -EBUSY;
-	}
-
-	if (!local->func->genesis_reset || !local->func->cor_sreset) {
-		printk(KERN_INFO "%s: Genesis mode downloading not supported "
-		       "with this hwmodel\n", dev->name);
-		return -EOPNOTSUPP;
-	}
-
-	local->hw_downloading = 1;
-
-	if (prism2_enable_aux_port(dev, 1)) {
-		printk(KERN_DEBUG "%s: failed to enable AUX port\n",
-		       dev->name);
-		ret = -EIO;
-		goto out;
-	}
-
-	if (local->sram_type == -1) {
-		/* 0x1F for x8 SRAM or 0x0F for x16 SRAM */
-		if (prism2_enable_genesis(local, 0x1f) == 0) {
-			ram16 = 0;
-			PDEBUG(DEBUG_EXTRA2, "%s: Genesis mode OK using x8 "
-			       "SRAM\n", dev->name);
-		} else if (prism2_enable_genesis(local, 0x0f) == 0) {
-			ram16 = 1;
-			PDEBUG(DEBUG_EXTRA2, "%s: Genesis mode OK using x16 "
-			       "SRAM\n", dev->name);
-		} else {
-			printk(KERN_DEBUG "%s: Could not initiate genesis "
-			       "mode\n", dev->name);
-			ret = -EIO;
-			goto out;
-		}
-	} else {
-		if (prism2_enable_genesis(local, local->sram_type == 8 ?
-					  0x1f : 0x0f)) {
-			printk(KERN_DEBUG "%s: Failed to set Genesis "
-			       "mode (sram_type=%d)\n", dev->name,
-			       local->sram_type);
-			ret = -EIO;
-			goto out;
-		}
-		ram16 = local->sram_type != 8;
-	}
-
-	for (i = 0; i < param->num_areas; i++) {
-		PDEBUG(DEBUG_EXTRA2, "%s: Writing %d bytes at 0x%08x\n",
-		       dev->name, param->data[i].len, param->data[i].addr);
-		if (hfa384x_to_aux(dev, param->data[i].addr,
-				   param->data[i].len, param->data[i].data)) {
-			printk(KERN_WARNING "%s: RAM download at 0x%08x "
-			       "(len=%d) failed\n", dev->name,
-			       param->data[i].addr, param->data[i].len);
-			ret = -EIO;
-			goto out;
-		}
-	}
-
-	PDEBUG(DEBUG_EXTRA2, "Disable genesis mode\n");
-	local->func->genesis_reset(local, ram16 ? 0x07 : 0x17);
-	if (prism2_enable_aux_port(dev, 0)) {
-		printk(KERN_DEBUG "%s: Failed to disable AUX port\n",
-		       dev->name);
-	}
-
-	mdelay(5);
-	local->hw_downloading = 0;
-
-	PDEBUG(DEBUG_EXTRA2, "Trying to initialize card\n");
-	/*
-	 * Make sure the INIT command does not generate a command completion
-	 * event by disabling interrupts.
-	 */
-	hfa384x_disable_interrupts(dev);
-	if (prism2_hw_init(dev, 1)) {
-		printk(KERN_DEBUG "%s: Initialization after genesis mode "
-		       "download failed\n", dev->name);
-		ret = -EIO;
-		goto out;
-	}
-
-	PDEBUG(DEBUG_EXTRA2, "Card initialized - running PRI only\n");
-	if (prism2_hw_init2(dev, 1)) {
-		printk(KERN_DEBUG "%s: Initialization(2) after genesis mode "
-		       "download failed\n", dev->name);
-		ret = -EIO;
-		goto out;
-	}
-
- out:
-	local->hw_downloading = 0;
-	return ret;
-}
-
-
-#ifdef PRISM2_NON_VOLATILE_DOWNLOAD
-/* Note! Non-volatile downloading functionality has not yet been tested
- * thoroughly and it may corrupt flash image and effectively kill the card that
- * is being updated. You have been warned. */
-
-static inline int prism2_download_block(struct net_device *dev,
-					u32 addr, u8 *data,
-					u32 bufaddr, int rest_len)
-{
-	u16 param0, param1;
-	int block_len;
-
-	block_len = rest_len < 4096 ? rest_len : 4096;
-
-	param0 = addr & 0xffff;
-	param1 = addr >> 16;
-
-	HFA384X_OUTW(block_len, HFA384X_PARAM2_OFF);
-	HFA384X_OUTW(param1, HFA384X_PARAM1_OFF);
-
-	if (hfa384x_cmd_wait(dev, HFA384X_CMDCODE_DOWNLOAD |
-			     (HFA384X_PROGMODE_ENABLE_NON_VOLATILE << 8),
-			     param0)) {
-		printk(KERN_WARNING "%s: Flash download command execution "
-		       "failed\n", dev->name);
-		return -1;
-	}
-
-	if (hfa384x_to_aux(dev, bufaddr, block_len, data)) {
-		printk(KERN_WARNING "%s: flash download at 0x%08x "
-		       "(len=%d) failed\n", dev->name, addr, block_len);
-		return -1;
-	}
-
-	HFA384X_OUTW(0, HFA384X_PARAM2_OFF);
-	HFA384X_OUTW(0, HFA384X_PARAM1_OFF);
-	if (hfa384x_cmd_wait(dev, HFA384X_CMDCODE_DOWNLOAD |
-			     (HFA384X_PROGMODE_PROGRAM_NON_VOLATILE << 8),
-			     0)) {
-		printk(KERN_WARNING "%s: Flash write command execution "
-		       "failed\n", dev->name);
-		return -1;
-	}
-
-	return block_len;
-}
-
-
-static int prism2_download_nonvolatile(local_info_t *local,
-				       struct prism2_download_data *dl)
-{
-	struct net_device *dev = local->dev;
-	int ret = 0, i;
-	struct {
-		__le16 page;
-		__le16 offset;
-		__le16 len;
-	} dlbuffer;
-	u32 bufaddr;
-
-	if (local->hw_downloading) {
-		printk(KERN_WARNING "%s: Already downloading - aborting new "
-		       "request\n", dev->name);
-		return -1;
-	}
-
-	ret = local->func->get_rid(dev, HFA384X_RID_DOWNLOADBUFFER,
-				   &dlbuffer, 6, 0);
-
-	if (ret < 0) {
-		printk(KERN_WARNING "%s: Could not read download buffer "
-		       "parameters\n", dev->name);
-		goto out;
-	}
-
-	printk(KERN_DEBUG "Download buffer: %d bytes at 0x%04x:0x%04x\n",
-	       le16_to_cpu(dlbuffer.len),
-	       le16_to_cpu(dlbuffer.page),
-	       le16_to_cpu(dlbuffer.offset));
-
-	bufaddr = (le16_to_cpu(dlbuffer.page) << 7) + le16_to_cpu(dlbuffer.offset);
-
-	local->hw_downloading = 1;
-
-	if (!local->pri_only) {
-		prism2_hw_shutdown(dev, 0);
-
-		if (prism2_hw_init(dev, 0)) {
-			printk(KERN_WARNING "%s: Could not initialize card for"
-			       " download\n", dev->name);
-			ret = -1;
-			goto out;
-		}
-	}
-
-	hfa384x_disable_interrupts(dev);
-
-	if (prism2_enable_aux_port(dev, 1)) {
-		printk(KERN_WARNING "%s: Could not enable AUX port\n",
-		       dev->name);
-		ret = -1;
-		goto out;
-	}
-
-	printk(KERN_DEBUG "%s: starting flash download\n", dev->name);
-	for (i = 0; i < dl->num_areas; i++) {
-		int rest_len = dl->data[i].len;
-		int data_off = 0;
-
-		while (rest_len > 0) {
-			int block_len;
-
-			block_len = prism2_download_block(
-				dev, dl->data[i].addr + data_off,
-				dl->data[i].data + data_off, bufaddr,
-				rest_len);
-
-			if (block_len < 0) {
-				ret = -1;
-				goto out;
-			}
-
-			rest_len -= block_len;
-			data_off += block_len;
-		}
-	}
-
-	HFA384X_OUTW(0, HFA384X_PARAM1_OFF);
-	HFA384X_OUTW(0, HFA384X_PARAM2_OFF);
-	if (hfa384x_cmd_wait(dev, HFA384X_CMDCODE_DOWNLOAD |
-				(HFA384X_PROGMODE_DISABLE << 8), 0)) {
-		printk(KERN_WARNING "%s: Download command execution failed\n",
-		       dev->name);
-		ret = -1;
-		goto out;
-	}
-
-	if (prism2_enable_aux_port(dev, 0)) {
-		printk(KERN_DEBUG "%s: Disabling AUX port failed\n",
-		       dev->name);
-		/* continue anyway.. restart should have taken care of this */
-	}
-
-	mdelay(5);
-
-	local->func->hw_reset(dev);
-	local->hw_downloading = 0;
-	if (prism2_hw_config(dev, 2)) {
-		printk(KERN_WARNING "%s: Card configuration after flash "
-		       "download failed\n", dev->name);
-		ret = -1;
-	} else {
-		printk(KERN_INFO "%s: Card initialized successfully after "
-		       "flash download\n", dev->name);
-	}
-
- out:
-	local->hw_downloading = 0;
-	return ret;
-}
-#endif /* PRISM2_NON_VOLATILE_DOWNLOAD */
-
-
-static void prism2_download_free_data(struct prism2_download_data *dl)
-{
-	int i;
-
-	if (dl == NULL)
-		return;
-
-	for (i = 0; i < dl->num_areas; i++)
-		kfree(dl->data[i].data);
-	kfree(dl);
-}
-
-
-static int prism2_download(local_info_t *local,
-			   struct prism2_download_param *param)
-{
-	int ret = 0;
-	int i;
-	u32 total_len = 0;
-	struct prism2_download_data *dl = NULL;
-
-	printk(KERN_DEBUG "prism2_download: dl_cmd=%d start_addr=0x%08x "
-	       "num_areas=%d\n",
-	       param->dl_cmd, param->start_addr, param->num_areas);
-
-	if (param->num_areas > 100) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	dl = kzalloc(struct_size(dl, data, param->num_areas), GFP_KERNEL);
-	if (dl == NULL) {
-		ret = -ENOMEM;
-		goto out;
-	}
-	dl->dl_cmd = param->dl_cmd;
-	dl->start_addr = param->start_addr;
-	dl->num_areas = param->num_areas;
-	for (i = 0; i < param->num_areas; i++) {
-		PDEBUG(DEBUG_EXTRA2,
-		       "  area %d: addr=0x%08x len=%d ptr=0x%p\n",
-		       i, param->data[i].addr, param->data[i].len,
-		       param->data[i].ptr);
-
-		dl->data[i].addr = param->data[i].addr;
-		dl->data[i].len = param->data[i].len;
-
-		total_len += param->data[i].len;
-		if (param->data[i].len > PRISM2_MAX_DOWNLOAD_AREA_LEN ||
-		    total_len > PRISM2_MAX_DOWNLOAD_LEN) {
-			ret = -E2BIG;
-			goto out;
-		}
-
-		dl->data[i].data = kmalloc(dl->data[i].len, GFP_KERNEL);
-		if (dl->data[i].data == NULL) {
-			ret = -ENOMEM;
-			goto out;
-		}
-
-		if (copy_from_user(dl->data[i].data, param->data[i].ptr,
-				   param->data[i].len)) {
-			ret = -EFAULT;
-			goto out;
-		}
-	}
-
-	switch (param->dl_cmd) {
-	case PRISM2_DOWNLOAD_VOLATILE:
-	case PRISM2_DOWNLOAD_VOLATILE_PERSISTENT:
-		ret = prism2_download_volatile(local, dl);
-		break;
-	case PRISM2_DOWNLOAD_VOLATILE_GENESIS:
-	case PRISM2_DOWNLOAD_VOLATILE_GENESIS_PERSISTENT:
-		ret = prism2_download_genesis(local, dl);
-		break;
-	case PRISM2_DOWNLOAD_NON_VOLATILE:
-#ifdef PRISM2_NON_VOLATILE_DOWNLOAD
-		ret = prism2_download_nonvolatile(local, dl);
-#else /* PRISM2_NON_VOLATILE_DOWNLOAD */
-		printk(KERN_INFO "%s: non-volatile downloading not enabled\n",
-		       local->dev->name);
-		ret = -EOPNOTSUPP;
-#endif /* PRISM2_NON_VOLATILE_DOWNLOAD */
-		break;
-	default:
-		printk(KERN_DEBUG "%s: unsupported download command %d\n",
-		       local->dev->name, param->dl_cmd);
-		ret = -EINVAL;
-		break;
-	}
-
- out:
-	if (ret == 0 && dl &&
-	    param->dl_cmd == PRISM2_DOWNLOAD_VOLATILE_GENESIS_PERSISTENT) {
-		prism2_download_free_data(local->dl_pri);
-		local->dl_pri = dl;
-	} else if (ret == 0 && dl &&
-		   param->dl_cmd == PRISM2_DOWNLOAD_VOLATILE_PERSISTENT) {
-		prism2_download_free_data(local->dl_sec);
-		local->dl_sec = dl;
-	} else
-		prism2_download_free_data(dl);
-
-	return ret;
-}
diff --git a/drivers/net/wireless/intersil/hostap/hostap_hw.c b/drivers/net/wireless/intersil/hostap/hostap_hw.c
deleted file mode 100644
index b74f4cb5d6d3..000000000000
--- a/drivers/net/wireless/intersil/hostap/hostap_hw.c
+++ /dev/null
@@ -1,3387 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Host AP (software wireless LAN access point) driver for
- * Intersil Prism2/2.5/3.
- *
- * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen
- * <j@w1.fi>
- * Copyright (c) 2002-2005, Jouni Malinen <j@w1.fi>
- *
- * FIX:
- * - there is currently no way of associating TX packets to correct wds device
- *   when TX Exc/OK event occurs, so all tx_packets and some
- *   tx_errors/tx_dropped are added to the main netdevice; using sw_support
- *   field in txdesc might be used to fix this (using Alloc event to increment
- *   tx_packets would need some further info in txfid table)
- *
- * Buffer Access Path (BAP) usage:
- *   Prism2 cards have two separate BAPs for accessing the card memory. These
- *   should allow concurrent access to two different frames and the driver
- *   previously used BAP0 for sending data and BAP1 for receiving data.
- *   However, there seems to be number of issues with concurrent access and at
- *   least one know hardware bug in using BAP0 and BAP1 concurrently with PCI
- *   Prism2.5. Therefore, the driver now only uses BAP0 for moving data between
- *   host and card memories. BAP0 accesses are protected with local->baplock
- *   (spin_lock_bh) to prevent concurrent use.
- */
-
-
-
-#include <asm/delay.h>
-#include <linux/uaccess.h>
-
-#include <linux/slab.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/if_arp.h>
-#include <linux/delay.h>
-#include <linux/random.h>
-#include <linux/wait.h>
-#include <linux/sched/signal.h>
-#include <linux/rtnetlink.h>
-#include <linux/wireless.h>
-#include <net/iw_handler.h>
-#include <net/lib80211.h>
-#include <asm/irq.h>
-
-#include "hostap_80211.h"
-#include "hostap.h"
-#include "hostap_ap.h"
-
-
-/* #define final_version */
-
-static int mtu = 1500;
-module_param(mtu, int, 0444);
-MODULE_PARM_DESC(mtu, "Maximum transfer unit");
-
-static int channel[MAX_PARM_DEVICES] = { 3, DEF_INTS };
-module_param_array(channel, int, NULL, 0444);
-MODULE_PARM_DESC(channel, "Initial channel");
-
-static char essid[33] = "test";
-module_param_string(essid, essid, sizeof(essid), 0444);
-MODULE_PARM_DESC(essid, "Host AP's ESSID");
-
-static int iw_mode[MAX_PARM_DEVICES] = { IW_MODE_MASTER, DEF_INTS };
-module_param_array(iw_mode, int, NULL, 0444);
-MODULE_PARM_DESC(iw_mode, "Initial operation mode");
-
-static int beacon_int[MAX_PARM_DEVICES] = { 100, DEF_INTS };
-module_param_array(beacon_int, int, NULL, 0444);
-MODULE_PARM_DESC(beacon_int, "Beacon interval (1 = 1024 usec)");
-
-static int dtim_period[MAX_PARM_DEVICES] = { 1, DEF_INTS };
-module_param_array(dtim_period, int, NULL, 0444);
-MODULE_PARM_DESC(dtim_period, "DTIM period");
-
-static char dev_template[16] = "wlan%d";
-module_param_string(dev_template, dev_template, sizeof(dev_template), 0444);
-MODULE_PARM_DESC(dev_template, "Prefix for network device name (default: "
-		 "wlan%d)");
-
-#ifdef final_version
-#define EXTRA_EVENTS_WTERR 0
-#else
-/* check WTERR events (Wait Time-out) in development versions */
-#define EXTRA_EVENTS_WTERR HFA384X_EV_WTERR
-#endif
-
-/* Events that will be using BAP0 */
-#define HFA384X_BAP0_EVENTS \
-	(HFA384X_EV_TXEXC | HFA384X_EV_RX | HFA384X_EV_INFO | HFA384X_EV_TX)
-
-/* event mask, i.e., events that will result in an interrupt */
-#define HFA384X_EVENT_MASK \
-	(HFA384X_BAP0_EVENTS | HFA384X_EV_ALLOC | HFA384X_EV_INFDROP | \
-	HFA384X_EV_CMD | HFA384X_EV_TICK | \
-	EXTRA_EVENTS_WTERR)
-
-/* Default TX control flags: use 802.11 headers and request interrupt for
- * failed transmits. Frames that request ACK callback, will add
- * _TX_OK flag and _ALT_RTRY flag may be used to select different retry policy.
- */
-#define HFA384X_TX_CTRL_FLAGS \
-	(HFA384X_TX_CTRL_802_11 | HFA384X_TX_CTRL_TX_EX)
-
-
-/* ca. 1 usec */
-#define HFA384X_CMD_BUSY_TIMEOUT 5000
-#define HFA384X_BAP_BUSY_TIMEOUT 50000
-
-/* ca. 10 usec */
-#define HFA384X_CMD_COMPL_TIMEOUT 20000
-#define HFA384X_DL_COMPL_TIMEOUT 1000000
-
-/* Wait times for initialization; yield to other processes to avoid busy
- * waiting for long time. */
-#define HFA384X_INIT_TIMEOUT (HZ / 2) /* 500 ms */
-#define HFA384X_ALLOC_COMPL_TIMEOUT (HZ / 20) /* 50 ms */
-
-
-static void prism2_hw_reset(struct net_device *dev);
-static void prism2_check_sta_fw_version(local_info_t *local);
-
-#ifdef PRISM2_DOWNLOAD_SUPPORT
-/* hostap_download.c */
-static const struct proc_ops prism2_download_aux_dump_proc_ops;
-static u8 * prism2_read_pda(struct net_device *dev);
-static int prism2_download(local_info_t *local,
-			   struct prism2_download_param *param);
-static void prism2_download_free_data(struct prism2_download_data *dl);
-static int prism2_download_volatile(local_info_t *local,
-				    struct prism2_download_data *param);
-static int prism2_download_genesis(local_info_t *local,
-				   struct prism2_download_data *param);
-static int prism2_get_ram_size(local_info_t *local);
-#endif /* PRISM2_DOWNLOAD_SUPPORT */
-
-
-
-
-#ifndef final_version
-/* magic value written to SWSUPPORT0 reg. for detecting whether card is still
- * present */
-#define HFA384X_MAGIC 0x8A32
-#endif
-
-static void hfa384x_read_regs(struct net_device *dev,
-			      struct hfa384x_regs *regs)
-{
-	regs->cmd = HFA384X_INW(HFA384X_CMD_OFF);
-	regs->evstat = HFA384X_INW(HFA384X_EVSTAT_OFF);
-	regs->offset0 = HFA384X_INW(HFA384X_OFFSET0_OFF);
-	regs->offset1 = HFA384X_INW(HFA384X_OFFSET1_OFF);
-	regs->swsupport0 = HFA384X_INW(HFA384X_SWSUPPORT0_OFF);
-}
-
-
-/**
- * __hostap_cmd_queue_free - Free Prism2 command queue entry (private)
- * @local: pointer to private Host AP driver data
- * @entry: Prism2 command queue entry to be freed
- * @del_req: request the entry to be removed
- *
- * Internal helper function for freeing Prism2 command queue entries.
- * Caller must have acquired local->cmdlock before calling this function.
- */
-static inline void __hostap_cmd_queue_free(local_info_t *local,
-					   struct hostap_cmd_queue *entry,
-					   int del_req)
-{
-	if (del_req) {
-		entry->del_req = 1;
-		if (!list_empty(&entry->list)) {
-			list_del_init(&entry->list);
-			local->cmd_queue_len--;
-		}
-	}
-
-	if (refcount_dec_and_test(&entry->usecnt) && entry->del_req)
-		kfree(entry);
-}
-
-
-/**
- * hostap_cmd_queue_free - Free Prism2 command queue entry
- * @local: pointer to private Host AP driver data
- * @entry: Prism2 command queue entry to be freed
- * @del_req: request the entry to be removed
- *
- * Free a Prism2 command queue entry.
- */
-static inline void hostap_cmd_queue_free(local_info_t *local,
-					 struct hostap_cmd_queue *entry,
-					 int del_req)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&local->cmdlock, flags);
-	__hostap_cmd_queue_free(local, entry, del_req);
-	spin_unlock_irqrestore(&local->cmdlock, flags);
-}
-
-
-/**
- * prism2_clear_cmd_queue - Free all pending Prism2 command queue entries
- * @local: pointer to private Host AP driver data
- */
-static void prism2_clear_cmd_queue(local_info_t *local)
-{
-	struct list_head *ptr, *n;
-	unsigned long flags;
-	struct hostap_cmd_queue *entry;
-
-	spin_lock_irqsave(&local->cmdlock, flags);
-	list_for_each_safe(ptr, n, &local->cmd_queue) {
-		entry = list_entry(ptr, struct hostap_cmd_queue, list);
-		refcount_inc(&entry->usecnt);
-		printk(KERN_DEBUG "%s: removed pending cmd_queue entry "
-		       "(type=%d, cmd=0x%04x, param0=0x%04x)\n",
-		       local->dev->name, entry->type, entry->cmd,
-		       entry->param0);
-		__hostap_cmd_queue_free(local, entry, 1);
-	}
-	if (local->cmd_queue_len) {
-		/* This should not happen; print debug message and clear
-		 * queue length. */
-		printk(KERN_DEBUG "%s: cmd_queue_len (%d) not zero after "
-		       "flush\n", local->dev->name, local->cmd_queue_len);
-		local->cmd_queue_len = 0;
-	}
-	spin_unlock_irqrestore(&local->cmdlock, flags);
-}
-
-
-/**
- * hfa384x_cmd_issue - Issue a Prism2 command to the hardware
- * @dev: pointer to net_device
- * @entry: Prism2 command queue entry to be issued
- */
-static int hfa384x_cmd_issue(struct net_device *dev,
-				    struct hostap_cmd_queue *entry)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int tries;
-	u16 reg;
-	unsigned long flags;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (local->func->card_present && !local->func->card_present(local))
-		return -ENODEV;
-
-	if (entry->issued) {
-		printk(KERN_DEBUG "%s: driver bug - re-issuing command @%p\n",
-		       dev->name, entry);
-	}
-
-	/* wait until busy bit is clear; this should always be clear since the
-	 * commands are serialized */
-	tries = HFA384X_CMD_BUSY_TIMEOUT;
-	while (HFA384X_INW(HFA384X_CMD_OFF) & HFA384X_CMD_BUSY && tries > 0) {
-		tries--;
-		udelay(1);
-	}
-#ifndef final_version
-	if (tries != HFA384X_CMD_BUSY_TIMEOUT) {
-		prism2_io_debug_error(dev, 1);
-		printk(KERN_DEBUG "%s: hfa384x_cmd_issue: cmd reg was busy "
-		       "for %d usec\n", dev->name,
-		       HFA384X_CMD_BUSY_TIMEOUT - tries);
-	}
-#endif
-	if (tries == 0) {
-		reg = HFA384X_INW(HFA384X_CMD_OFF);
-		prism2_io_debug_error(dev, 2);
-		printk(KERN_DEBUG "%s: hfa384x_cmd_issue - timeout - "
-		       "reg=0x%04x\n", dev->name, reg);
-		return -ETIMEDOUT;
-	}
-
-	/* write command */
-	spin_lock_irqsave(&local->cmdlock, flags);
-	HFA384X_OUTW(entry->param0, HFA384X_PARAM0_OFF);
-	HFA384X_OUTW(entry->param1, HFA384X_PARAM1_OFF);
-	HFA384X_OUTW(entry->cmd, HFA384X_CMD_OFF);
-	entry->issued = 1;
-	spin_unlock_irqrestore(&local->cmdlock, flags);
-
-	return 0;
-}
-
-
-/**
- * hfa384x_cmd - Issue a Prism2 command and wait (sleep) for completion
- * @dev: pointer to net_device
- * @cmd: Prism2 command code (HFA384X_CMD_CODE_*)
- * @param0: value for Param0 register
- * @param1: value for Param1 register (pointer; %NULL if not used)
- * @resp0: pointer for Resp0 data or %NULL if Resp0 is not needed
- *
- * Issue given command (possibly after waiting in command queue) and sleep
- * until the command is completed (or timed out or interrupted). This can be
- * called only from user process context.
- */
-static int hfa384x_cmd(struct net_device *dev, u16 cmd, u16 param0,
-		       u16 *param1, u16 *resp0)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int err, res, issue, issued = 0;
-	unsigned long flags;
-	struct hostap_cmd_queue *entry;
-	DECLARE_WAITQUEUE(wait, current);
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (local->cmd_queue_len >= HOSTAP_CMD_QUEUE_MAX_LEN) {
-		printk(KERN_DEBUG "%s: hfa384x_cmd: cmd_queue full\n",
-		       dev->name);
-		return -1;
-	}
-
-	if (signal_pending(current))
-		return -EINTR;
-
-	entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
-	if (entry == NULL)
-		return -ENOMEM;
-
-	refcount_set(&entry->usecnt, 1);
-	entry->type = CMD_SLEEP;
-	entry->cmd = cmd;
-	entry->param0 = param0;
-	if (param1)
-		entry->param1 = *param1;
-	init_waitqueue_head(&entry->compl);
-
-	/* prepare to wait for command completion event, but do not sleep yet
-	 */
-	add_wait_queue(&entry->compl, &wait);
-	set_current_state(TASK_INTERRUPTIBLE);
-
-	spin_lock_irqsave(&local->cmdlock, flags);
-	issue = list_empty(&local->cmd_queue);
-	if (issue)
-		entry->issuing = 1;
-	list_add_tail(&entry->list, &local->cmd_queue);
-	local->cmd_queue_len++;
-	spin_unlock_irqrestore(&local->cmdlock, flags);
-
-	err = 0;
-	if (!issue)
-		goto wait_completion;
-
-	if (signal_pending(current))
-		err = -EINTR;
-
-	if (!err) {
-		if (hfa384x_cmd_issue(dev, entry))
-			err = -ETIMEDOUT;
-		else
-			issued = 1;
-	}
-
- wait_completion:
-	if (!err && entry->type != CMD_COMPLETED) {
-		/* sleep until command is completed or timed out */
-		res = schedule_timeout(2 * HZ);
-	} else
-		res = -1;
-
-	if (!err && signal_pending(current))
-		err = -EINTR;
-
-	if (err && issued) {
-		/* the command was issued, so a CmdCompl event should occur
-		 * soon; however, there's a pending signal and
-		 * schedule_timeout() would be interrupted; wait a short period
-		 * of time to avoid removing entry from the list before
-		 * CmdCompl event */
-		udelay(300);
-	}
-
-	set_current_state(TASK_RUNNING);
-	remove_wait_queue(&entry->compl, &wait);
-
-	/* If entry->list is still in the list, it must be removed
-	 * first and in this case prism2_cmd_ev() does not yet have
-	 * local reference to it, and the data can be kfree()'d
-	 * here. If the command completion event is still generated,
-	 * it will be assigned to next (possibly) pending command, but
-	 * the driver will reset the card anyway due to timeout
-	 *
-	 * If the entry is not in the list prism2_cmd_ev() has a local
-	 * reference to it, but keeps cmdlock as long as the data is
-	 * needed, so the data can be kfree()'d here. */
-
-	/* FIX: if the entry->list is in the list, it has not been completed
-	 * yet, so removing it here is somewhat wrong.. this could cause
-	 * references to freed memory and next list_del() causing NULL pointer
-	 * dereference.. it would probably be better to leave the entry in the
-	 * list and the list should be emptied during hw reset */
-
-	spin_lock_irqsave(&local->cmdlock, flags);
-	if (!list_empty(&entry->list)) {
-		printk(KERN_DEBUG "%s: hfa384x_cmd: entry still in list? "
-		       "(entry=%p, type=%d, res=%d)\n", dev->name, entry,
-		       entry->type, res);
-		list_del_init(&entry->list);
-		local->cmd_queue_len--;
-	}
-	spin_unlock_irqrestore(&local->cmdlock, flags);
-
-	if (err) {
-		printk(KERN_DEBUG "%s: hfa384x_cmd: interrupted; err=%d\n",
-		       dev->name, err);
-		res = err;
-		goto done;
-	}
-
-	if (entry->type != CMD_COMPLETED) {
-		u16 reg = HFA384X_INW(HFA384X_EVSTAT_OFF);
-		printk(KERN_DEBUG "%s: hfa384x_cmd: command was not "
-		       "completed (res=%d, entry=%p, type=%d, cmd=0x%04x, "
-		       "param0=0x%04x, EVSTAT=%04x INTEN=%04x)\n", dev->name,
-		       res, entry, entry->type, entry->cmd, entry->param0, reg,
-		       HFA384X_INW(HFA384X_INTEN_OFF));
-		if (reg & HFA384X_EV_CMD) {
-			/* Command completion event is pending, but the
-			 * interrupt was not delivered - probably an issue
-			 * with pcmcia-cs configuration. */
-			printk(KERN_WARNING "%s: interrupt delivery does not "
-			       "seem to work\n", dev->name);
-		}
-		prism2_io_debug_error(dev, 3);
-		res = -ETIMEDOUT;
-		goto done;
-	}
-
-	if (resp0 != NULL)
-		*resp0 = entry->resp0;
-#ifndef final_version
-	if (entry->res) {
-		printk(KERN_DEBUG "%s: CMD=0x%04x => res=0x%02x, "
-		       "resp0=0x%04x\n",
-		       dev->name, cmd, entry->res, entry->resp0);
-	}
-#endif /* final_version */
-
-	res = entry->res;
- done:
-	hostap_cmd_queue_free(local, entry, 1);
-	return res;
-}
-
-
-/**
- * hfa384x_cmd_callback - Issue a Prism2 command; callback when completed
- * @dev: pointer to net_device
- * @cmd: Prism2 command code (HFA384X_CMD_CODE_*)
- * @param0: value for Param0 register
- * @callback: command completion callback function (%NULL = no callback)
- * @context: context data to be given to the callback function
- *
- * Issue given command (possibly after waiting in command queue) and use
- * callback function to indicate command completion. This can be called both
- * from user and interrupt context. The callback function will be called in
- * hardware IRQ context. It can be %NULL, when no function is called when
- * command is completed.
- */
-static int hfa384x_cmd_callback(struct net_device *dev, u16 cmd, u16 param0,
-				void (*callback)(struct net_device *dev,
-						 long context, u16 resp0,
-						 u16 status),
-				long context)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int issue, ret;
-	unsigned long flags;
-	struct hostap_cmd_queue *entry;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (local->cmd_queue_len >= HOSTAP_CMD_QUEUE_MAX_LEN + 2) {
-		printk(KERN_DEBUG "%s: hfa384x_cmd: cmd_queue full\n",
-		       dev->name);
-		return -1;
-	}
-
-	entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
-	if (entry == NULL)
-		return -ENOMEM;
-
-	refcount_set(&entry->usecnt, 1);
-	entry->type = CMD_CALLBACK;
-	entry->cmd = cmd;
-	entry->param0 = param0;
-	entry->callback = callback;
-	entry->context = context;
-
-	spin_lock_irqsave(&local->cmdlock, flags);
-	issue = list_empty(&local->cmd_queue);
-	if (issue)
-		entry->issuing = 1;
-	list_add_tail(&entry->list, &local->cmd_queue);
-	local->cmd_queue_len++;
-	spin_unlock_irqrestore(&local->cmdlock, flags);
-
-	if (issue && hfa384x_cmd_issue(dev, entry))
-		ret = -ETIMEDOUT;
-	else
-		ret = 0;
-
-	hostap_cmd_queue_free(local, entry, ret);
-
-	return ret;
-}
-
-
-/**
- * __hfa384x_cmd_no_wait - Issue a Prism2 command (private)
- * @dev: pointer to net_device
- * @cmd: Prism2 command code (HFA384X_CMD_CODE_*)
- * @param0: value for Param0 register
- * @io_debug_num: I/O debug error number
- *
- * Shared helper function for hfa384x_cmd_wait() and hfa384x_cmd_no_wait().
- */
-static int __hfa384x_cmd_no_wait(struct net_device *dev, u16 cmd, u16 param0,
-				 int io_debug_num)
-{
-	int tries;
-	u16 reg;
-
-	/* wait until busy bit is clear; this should always be clear since the
-	 * commands are serialized */
-	tries = HFA384X_CMD_BUSY_TIMEOUT;
-	while (HFA384X_INW(HFA384X_CMD_OFF) & HFA384X_CMD_BUSY && tries > 0) {
-		tries--;
-		udelay(1);
-	}
-	if (tries == 0) {
-		reg = HFA384X_INW(HFA384X_CMD_OFF);
-		prism2_io_debug_error(dev, io_debug_num);
-		printk(KERN_DEBUG "%s: __hfa384x_cmd_no_wait(%d) - timeout - "
-		       "reg=0x%04x\n", dev->name, io_debug_num, reg);
-		return -ETIMEDOUT;
-	}
-
-	/* write command */
-	HFA384X_OUTW(param0, HFA384X_PARAM0_OFF);
-	HFA384X_OUTW(cmd, HFA384X_CMD_OFF);
-
-	return 0;
-}
-
-
-/**
- * hfa384x_cmd_wait - Issue a Prism2 command and busy wait for completion
- * @dev: pointer to net_device
- * @cmd: Prism2 command code (HFA384X_CMD_CODE_*)
- * @param0: value for Param0 register
- */
-static int hfa384x_cmd_wait(struct net_device *dev, u16 cmd, u16 param0)
-{
-	int res, tries;
-	u16 reg;
-
-	res = __hfa384x_cmd_no_wait(dev, cmd, param0, 4);
-	if (res)
-		return res;
-
-        /* wait for command completion */
-	if ((cmd & HFA384X_CMDCODE_MASK) == HFA384X_CMDCODE_DOWNLOAD)
-		tries = HFA384X_DL_COMPL_TIMEOUT;
-	else
-		tries = HFA384X_CMD_COMPL_TIMEOUT;
-
-        while (!(HFA384X_INW(HFA384X_EVSTAT_OFF) & HFA384X_EV_CMD) &&
-               tries > 0) {
-                tries--;
-                udelay(10);
-        }
-        if (tries == 0) {
-                reg = HFA384X_INW(HFA384X_EVSTAT_OFF);
-		prism2_io_debug_error(dev, 5);
-                printk(KERN_DEBUG "%s: hfa384x_cmd_wait - timeout2 - "
-		       "reg=0x%04x\n", dev->name, reg);
-                return -ETIMEDOUT;
-        }
-
-        res = (HFA384X_INW(HFA384X_STATUS_OFF) &
-               (BIT(14) | BIT(13) | BIT(12) | BIT(11) | BIT(10) | BIT(9) |
-                BIT(8))) >> 8;
-#ifndef final_version
-	if (res) {
-		printk(KERN_DEBUG "%s: CMD=0x%04x => res=0x%02x\n",
-		       dev->name, cmd, res);
-	}
-#endif
-
-	HFA384X_OUTW(HFA384X_EV_CMD, HFA384X_EVACK_OFF);
-
-	return res;
-}
-
-
-/**
- * hfa384x_cmd_no_wait - Issue a Prism2 command; do not wait for completion
- * @dev: pointer to net_device
- * @cmd: Prism2 command code (HFA384X_CMD_CODE_*)
- * @param0: value for Param0 register
- */
-static inline int hfa384x_cmd_no_wait(struct net_device *dev, u16 cmd,
-				      u16 param0)
-{
-	return __hfa384x_cmd_no_wait(dev, cmd, param0, 6);
-}
-
-
-/**
- * prism2_cmd_ev - Prism2 command completion event handler
- * @dev: pointer to net_device
- *
- * Interrupt handler for command completion events. Called by the main
- * interrupt handler in hardware IRQ context. Read Resp0 and status registers
- * from the hardware and ACK the event. Depending on the issued command type
- * either wake up the sleeping process that is waiting for command completion
- * or call the callback function. Issue the next command, if one is pending.
- */
-static void prism2_cmd_ev(struct net_device *dev)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	struct hostap_cmd_queue *entry = NULL;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	spin_lock(&local->cmdlock);
-	if (!list_empty(&local->cmd_queue)) {
-		entry = list_entry(local->cmd_queue.next,
-				   struct hostap_cmd_queue, list);
-		refcount_inc(&entry->usecnt);
-		list_del_init(&entry->list);
-		local->cmd_queue_len--;
-
-		if (!entry->issued) {
-			printk(KERN_DEBUG "%s: Command completion event, but "
-			       "cmd not issued\n", dev->name);
-			__hostap_cmd_queue_free(local, entry, 1);
-			entry = NULL;
-		}
-	}
-	spin_unlock(&local->cmdlock);
-
-	if (!entry) {
-		HFA384X_OUTW(HFA384X_EV_CMD, HFA384X_EVACK_OFF);
-		printk(KERN_DEBUG "%s: Command completion event, but no "
-		       "pending commands\n", dev->name);
-		return;
-	}
-
-	entry->resp0 = HFA384X_INW(HFA384X_RESP0_OFF);
-	entry->res = (HFA384X_INW(HFA384X_STATUS_OFF) &
-		      (BIT(14) | BIT(13) | BIT(12) | BIT(11) | BIT(10) |
-		       BIT(9) | BIT(8))) >> 8;
-	HFA384X_OUTW(HFA384X_EV_CMD, HFA384X_EVACK_OFF);
-
-	/* TODO: rest of the CmdEv handling could be moved to tasklet */
-	if (entry->type == CMD_SLEEP) {
-		entry->type = CMD_COMPLETED;
-		wake_up_interruptible(&entry->compl);
-	} else if (entry->type == CMD_CALLBACK) {
-		if (entry->callback)
-			entry->callback(dev, entry->context, entry->resp0,
-					entry->res);
-	} else {
-		printk(KERN_DEBUG "%s: Invalid command completion type %d\n",
-		       dev->name, entry->type);
-	}
-	hostap_cmd_queue_free(local, entry, 1);
-
-	/* issue next command, if pending */
-	entry = NULL;
-	spin_lock(&local->cmdlock);
-	if (!list_empty(&local->cmd_queue)) {
-		entry = list_entry(local->cmd_queue.next,
-				   struct hostap_cmd_queue, list);
-		if (entry->issuing) {
-			/* hfa384x_cmd() has already started issuing this
-			 * command, so do not start here */
-			entry = NULL;
-		}
-		if (entry)
-			refcount_inc(&entry->usecnt);
-	}
-	spin_unlock(&local->cmdlock);
-
-	if (entry) {
-		/* issue next command; if command issuing fails, remove the
-		 * entry from cmd_queue */
-		int res = hfa384x_cmd_issue(dev, entry);
-		spin_lock(&local->cmdlock);
-		__hostap_cmd_queue_free(local, entry, res);
-		spin_unlock(&local->cmdlock);
-	}
-}
-
-
-static int hfa384x_wait_offset(struct net_device *dev, u16 o_off)
-{
-	int tries = HFA384X_BAP_BUSY_TIMEOUT;
-	int res = HFA384X_INW(o_off) & HFA384X_OFFSET_BUSY;
-
-	while (res && tries > 0) {
-		tries--;
-		udelay(1);
-		res = HFA384X_INW(o_off) & HFA384X_OFFSET_BUSY;
-	}
-	return res;
-}
-
-
-/* Offset must be even */
-static int hfa384x_setup_bap(struct net_device *dev, u16 bap, u16 id,
-			     int offset)
-{
-	u16 o_off, s_off;
-	int ret = 0;
-
-	if (offset % 2 || bap > 1)
-		return -EINVAL;
-
-	if (bap == BAP1) {
-		o_off = HFA384X_OFFSET1_OFF;
-		s_off = HFA384X_SELECT1_OFF;
-	} else {
-		o_off = HFA384X_OFFSET0_OFF;
-		s_off = HFA384X_SELECT0_OFF;
-	}
-
-	if (hfa384x_wait_offset(dev, o_off)) {
-		prism2_io_debug_error(dev, 7);
-		printk(KERN_DEBUG "%s: hfa384x_setup_bap - timeout before\n",
-		       dev->name);
-		ret = -ETIMEDOUT;
-		goto out;
-	}
-
-	HFA384X_OUTW(id, s_off);
-	HFA384X_OUTW(offset, o_off);
-
-	if (hfa384x_wait_offset(dev, o_off)) {
-		prism2_io_debug_error(dev, 8);
-		printk(KERN_DEBUG "%s: hfa384x_setup_bap - timeout after\n",
-		       dev->name);
-		ret = -ETIMEDOUT;
-		goto out;
-	}
-#ifndef final_version
-	if (HFA384X_INW(o_off) & HFA384X_OFFSET_ERR) {
-		prism2_io_debug_error(dev, 9);
-		printk(KERN_DEBUG "%s: hfa384x_setup_bap - offset error "
-		       "(%d,0x04%x,%d); reg=0x%04x\n",
-		       dev->name, bap, id, offset, HFA384X_INW(o_off));
-		ret = -EINVAL;
-	}
-#endif
-
- out:
-	return ret;
-}
-
-
-static int hfa384x_get_rid(struct net_device *dev, u16 rid, void *buf, int len,
-			   int exact_len)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int res, rlen = 0;
-	struct hfa384x_rid_hdr rec;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (local->no_pri) {
-		printk(KERN_DEBUG "%s: cannot get RID %04x (len=%d) - no PRI "
-		       "f/w\n", dev->name, rid, len);
-		return -ENOTTY; /* Well.. not really correct, but return
-				 * something unique enough.. */
-	}
-
-	if ((local->func->card_present && !local->func->card_present(local)) ||
-	    local->hw_downloading)
-		return -ENODEV;
-
-	res = mutex_lock_interruptible(&local->rid_bap_mtx);
-	if (res)
-		return res;
-
-	res = hfa384x_cmd(dev, HFA384X_CMDCODE_ACCESS, rid, NULL, NULL);
-	if (res) {
-		printk(KERN_DEBUG "%s: hfa384x_get_rid: CMDCODE_ACCESS failed "
-		       "(res=%d, rid=%04x, len=%d)\n",
-		       dev->name, res, rid, len);
-		mutex_unlock(&local->rid_bap_mtx);
-		return res;
-	}
-
-	spin_lock_bh(&local->baplock);
-
-	res = hfa384x_setup_bap(dev, BAP0, rid, 0);
-	if (res)
-		goto unlock;
-
-	res = hfa384x_from_bap(dev, BAP0, &rec, sizeof(rec));
-	if (res)
-		goto unlock;
-
-	if (le16_to_cpu(rec.len) == 0) {
-		/* RID not available */
-		res = -ENODATA;
-		goto unlock;
-	}
-
-	rlen = (le16_to_cpu(rec.len) - 1) * 2;
-	if (exact_len && rlen != len) {
-		printk(KERN_DEBUG "%s: hfa384x_get_rid - RID len mismatch: "
-		       "rid=0x%04x, len=%d (expected %d)\n",
-		       dev->name, rid, rlen, len);
-		res = -ENODATA;
-	}
-
-	res = hfa384x_from_bap(dev, BAP0, buf, len);
-
-unlock:
-	spin_unlock_bh(&local->baplock);
-	mutex_unlock(&local->rid_bap_mtx);
-
-	if (res) {
-		if (res != -ENODATA)
-			printk(KERN_DEBUG "%s: hfa384x_get_rid (rid=%04x, "
-			       "len=%d) - failed - res=%d\n", dev->name, rid,
-			       len, res);
-		if (res == -ETIMEDOUT)
-			prism2_hw_reset(dev);
-		return res;
-	}
-
-	return rlen;
-}
-
-
-static int hfa384x_set_rid(struct net_device *dev, u16 rid, void *buf, int len)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	struct hfa384x_rid_hdr rec;
-	int res;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (local->no_pri) {
-		printk(KERN_DEBUG "%s: cannot set RID %04x (len=%d) - no PRI "
-		       "f/w\n", dev->name, rid, len);
-		return -ENOTTY; /* Well.. not really correct, but return
-				 * something unique enough.. */
-	}
-
-	if ((local->func->card_present && !local->func->card_present(local)) ||
-	    local->hw_downloading)
-		return -ENODEV;
-
-	rec.rid = cpu_to_le16(rid);
-	/* RID len in words and +1 for rec.rid */
-	rec.len = cpu_to_le16(len / 2 + len % 2 + 1);
-
-	res = mutex_lock_interruptible(&local->rid_bap_mtx);
-	if (res)
-		return res;
-
-	spin_lock_bh(&local->baplock);
-	res = hfa384x_setup_bap(dev, BAP0, rid, 0);
-	if (!res)
-		res = hfa384x_to_bap(dev, BAP0, &rec, sizeof(rec));
-	if (!res)
-		res = hfa384x_to_bap(dev, BAP0, buf, len);
-	spin_unlock_bh(&local->baplock);
-
-	if (res) {
-		printk(KERN_DEBUG "%s: hfa384x_set_rid (rid=%04x, len=%d) - "
-		       "failed - res=%d\n", dev->name, rid, len, res);
-		mutex_unlock(&local->rid_bap_mtx);
-		return res;
-	}
-
-	res = hfa384x_cmd(dev, HFA384X_CMDCODE_ACCESS_WRITE, rid, NULL, NULL);
-	mutex_unlock(&local->rid_bap_mtx);
-
-	if (res) {
-		printk(KERN_DEBUG "%s: hfa384x_set_rid: CMDCODE_ACCESS_WRITE "
-		       "failed (res=%d, rid=%04x, len=%d)\n",
-		       dev->name, res, rid, len);
-
-		if (res == -ETIMEDOUT)
-			prism2_hw_reset(dev);
-	}
-
-	return res;
-}
-
-
-static void hfa384x_disable_interrupts(struct net_device *dev)
-{
-	/* disable interrupts and clear event status */
-	HFA384X_OUTW(0, HFA384X_INTEN_OFF);
-	HFA384X_OUTW(0xffff, HFA384X_EVACK_OFF);
-}
-
-
-static void hfa384x_enable_interrupts(struct net_device *dev)
-{
-	/* ack pending events and enable interrupts from selected events */
-	HFA384X_OUTW(0xffff, HFA384X_EVACK_OFF);
-	HFA384X_OUTW(HFA384X_EVENT_MASK, HFA384X_INTEN_OFF);
-}
-
-
-static void hfa384x_events_no_bap0(struct net_device *dev)
-{
-	HFA384X_OUTW(HFA384X_EVENT_MASK & ~HFA384X_BAP0_EVENTS,
-		     HFA384X_INTEN_OFF);
-}
-
-
-static void hfa384x_events_all(struct net_device *dev)
-{
-	HFA384X_OUTW(HFA384X_EVENT_MASK, HFA384X_INTEN_OFF);
-}
-
-
-static void hfa384x_events_only_cmd(struct net_device *dev)
-{
-	HFA384X_OUTW(HFA384X_EV_CMD, HFA384X_INTEN_OFF);
-}
-
-
-static u16 hfa384x_allocate_fid(struct net_device *dev, int len)
-{
-	u16 fid;
-	unsigned long delay;
-
-	/* FIX: this could be replace with hfa384x_cmd() if the Alloc event
-	 * below would be handled like CmdCompl event (sleep here, wake up from
-	 * interrupt handler */
-	if (hfa384x_cmd_wait(dev, HFA384X_CMDCODE_ALLOC, len)) {
-		printk(KERN_DEBUG "%s: cannot allocate fid, len=%d\n",
-		       dev->name, len);
-		return 0xffff;
-	}
-
-	delay = jiffies + HFA384X_ALLOC_COMPL_TIMEOUT;
-	while (!(HFA384X_INW(HFA384X_EVSTAT_OFF) & HFA384X_EV_ALLOC) &&
-	       time_before(jiffies, delay))
-		yield();
-	if (!(HFA384X_INW(HFA384X_EVSTAT_OFF) & HFA384X_EV_ALLOC)) {
-		printk("%s: fid allocate, len=%d - timeout\n", dev->name, len);
-		return 0xffff;
-	}
-
-	fid = HFA384X_INW(HFA384X_ALLOCFID_OFF);
-	HFA384X_OUTW(HFA384X_EV_ALLOC, HFA384X_EVACK_OFF);
-
-	return fid;
-}
-
-
-static int prism2_reset_port(struct net_device *dev)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int res;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (!local->dev_enabled)
-		return 0;
-
-	res = hfa384x_cmd(dev, HFA384X_CMDCODE_DISABLE, 0,
-			  NULL, NULL);
-	if (res)
-		printk(KERN_DEBUG "%s: reset port failed to disable port\n",
-		       dev->name);
-	else {
-		res = hfa384x_cmd(dev, HFA384X_CMDCODE_ENABLE, 0,
-				  NULL, NULL);
-		if (res)
-			printk(KERN_DEBUG "%s: reset port failed to enable "
-			       "port\n", dev->name);
-	}
-
-	/* It looks like at least some STA firmware versions reset
-	 * fragmentation threshold back to 2346 after enable command. Restore
-	 * the configured value, if it differs from this default. */
-	if (local->fragm_threshold != 2346 &&
-	    hostap_set_word(dev, HFA384X_RID_FRAGMENTATIONTHRESHOLD,
-			    local->fragm_threshold)) {
-		printk(KERN_DEBUG "%s: failed to restore fragmentation "
-		       "threshold (%d) after Port0 enable\n",
-		       dev->name, local->fragm_threshold);
-	}
-
-	/* Some firmwares lose antenna selection settings on reset */
-	(void) hostap_set_antsel(local);
-
-	return res;
-}
-
-
-static int prism2_get_version_info(struct net_device *dev, u16 rid,
-				   const char *txt)
-{
-	struct hfa384x_comp_ident comp;
-	struct hostap_interface *iface;
-	local_info_t *local;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (local->no_pri) {
-		/* PRI f/w not yet available - cannot read RIDs */
-		return -1;
-	}
-	if (hfa384x_get_rid(dev, rid, &comp, sizeof(comp), 1) < 0) {
-		printk(KERN_DEBUG "Could not get RID for component %s\n", txt);
-		return -1;
-	}
-
-	printk(KERN_INFO "%s: %s: id=0x%02x v%d.%d.%d\n", dev->name, txt,
-	       __le16_to_cpu(comp.id), __le16_to_cpu(comp.major),
-	       __le16_to_cpu(comp.minor), __le16_to_cpu(comp.variant));
-	return 0;
-}
-
-
-static int prism2_setup_rids(struct net_device *dev)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	__le16 tmp;
-	int ret = 0;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	hostap_set_word(dev, HFA384X_RID_TICKTIME, 2000);
-
-	if (!local->fw_ap) {
-		u16 tmp1 = hostap_get_porttype(local);
-		ret = hostap_set_word(dev, HFA384X_RID_CNFPORTTYPE, tmp1);
-		if (ret) {
-			printk("%s: Port type setting to %d failed\n",
-			       dev->name, tmp1);
-			goto fail;
-		}
-	}
-
-	/* Setting SSID to empty string seems to kill the card in Host AP mode
-	 */
-	if (local->iw_mode != IW_MODE_MASTER || local->essid[0] != '\0') {
-		ret = hostap_set_string(dev, HFA384X_RID_CNFOWNSSID,
-					local->essid);
-		if (ret) {
-			printk("%s: AP own SSID setting failed\n", dev->name);
-			goto fail;
-		}
-	}
-
-	ret = hostap_set_word(dev, HFA384X_RID_CNFMAXDATALEN,
-			      PRISM2_DATA_MAXLEN);
-	if (ret) {
-		printk("%s: MAC data length setting to %d failed\n",
-		       dev->name, PRISM2_DATA_MAXLEN);
-		goto fail;
-	}
-
-	if (hfa384x_get_rid(dev, HFA384X_RID_CHANNELLIST, &tmp, 2, 1) < 0) {
-		printk("%s: Channel list read failed\n", dev->name);
-		ret = -EINVAL;
-		goto fail;
-	}
-	local->channel_mask = le16_to_cpu(tmp);
-
-	if (local->channel < 1 || local->channel > 14 ||
-	    !(local->channel_mask & (1 << (local->channel - 1)))) {
-		printk(KERN_WARNING "%s: Channel setting out of range "
-		       "(%d)!\n", dev->name, local->channel);
-		ret = -EBUSY;
-		goto fail;
-	}
-
-	ret = hostap_set_word(dev, HFA384X_RID_CNFOWNCHANNEL, local->channel);
-	if (ret) {
-		printk("%s: Channel setting to %d failed\n",
-		       dev->name, local->channel);
-		goto fail;
-	}
-
-	ret = hostap_set_word(dev, HFA384X_RID_CNFBEACONINT,
-			      local->beacon_int);
-	if (ret) {
-		printk("%s: Beacon interval setting to %d failed\n",
-		       dev->name, local->beacon_int);
-		/* this may fail with Symbol/Lucent firmware */
-		if (ret == -ETIMEDOUT)
-			goto fail;
-	}
-
-	ret = hostap_set_word(dev, HFA384X_RID_CNFOWNDTIMPERIOD,
-			      local->dtim_period);
-	if (ret) {
-		printk("%s: DTIM period setting to %d failed\n",
-		       dev->name, local->dtim_period);
-		/* this may fail with Symbol/Lucent firmware */
-		if (ret == -ETIMEDOUT)
-			goto fail;
-	}
-
-	ret = hostap_set_word(dev, HFA384X_RID_PROMISCUOUSMODE,
-			      local->is_promisc);
-	if (ret)
-		printk(KERN_INFO "%s: Setting promiscuous mode (%d) failed\n",
-		       dev->name, local->is_promisc);
-
-	if (!local->fw_ap) {
-		ret = hostap_set_string(dev, HFA384X_RID_CNFDESIREDSSID,
-					local->essid);
-		if (ret) {
-			printk("%s: Desired SSID setting failed\n", dev->name);
-			goto fail;
-		}
-	}
-
-	/* Setup TXRateControl, defaults to allow use of 1, 2, 5.5, and
-	 * 11 Mbps in automatic TX rate fallback and 1 and 2 Mbps as basic
-	 * rates */
-	if (local->tx_rate_control == 0) {
-		local->tx_rate_control =
-			HFA384X_RATES_1MBPS |
-			HFA384X_RATES_2MBPS |
-			HFA384X_RATES_5MBPS |
-			HFA384X_RATES_11MBPS;
-	}
-	if (local->basic_rates == 0)
-		local->basic_rates = HFA384X_RATES_1MBPS | HFA384X_RATES_2MBPS;
-
-	if (!local->fw_ap) {
-		ret = hostap_set_word(dev, HFA384X_RID_TXRATECONTROL,
-				      local->tx_rate_control);
-		if (ret) {
-			printk("%s: TXRateControl setting to %d failed\n",
-			       dev->name, local->tx_rate_control);
-			goto fail;
-		}
-
-		ret = hostap_set_word(dev, HFA384X_RID_CNFSUPPORTEDRATES,
-				      local->tx_rate_control);
-		if (ret) {
-			printk("%s: cnfSupportedRates setting to %d failed\n",
-			       dev->name, local->tx_rate_control);
-		}
-
-		ret = hostap_set_word(dev, HFA384X_RID_CNFBASICRATES,
-				      local->basic_rates);
-		if (ret) {
-			printk("%s: cnfBasicRates setting to %d failed\n",
-			       dev->name, local->basic_rates);
-		}
-
-		ret = hostap_set_word(dev, HFA384X_RID_CREATEIBSS, 1);
-		if (ret) {
-			printk("%s: Create IBSS setting to 1 failed\n",
-			       dev->name);
-		}
-	}
-
-	if (local->name_set)
-		(void) hostap_set_string(dev, HFA384X_RID_CNFOWNNAME,
-					 local->name);
-
-	if (hostap_set_encryption(local)) {
-		printk(KERN_INFO "%s: could not configure encryption\n",
-		       dev->name);
-	}
-
-	(void) hostap_set_antsel(local);
-
-	if (hostap_set_roaming(local)) {
-		printk(KERN_INFO "%s: could not set host roaming\n",
-		       dev->name);
-	}
-
-	if (local->sta_fw_ver >= PRISM2_FW_VER(1,6,3) &&
-	    hostap_set_word(dev, HFA384X_RID_CNFENHSECURITY, local->enh_sec))
-		printk(KERN_INFO "%s: cnfEnhSecurity setting to 0x%x failed\n",
-		       dev->name, local->enh_sec);
-
-	/* 32-bit tallies were added in STA f/w 0.8.0, but they were apparently
-	 * not working correctly (last seven counters report bogus values).
-	 * This has been fixed in 0.8.2, so enable 32-bit tallies only
-	 * beginning with that firmware version. Another bug fix for 32-bit
-	 * tallies in 1.4.0; should 16-bit tallies be used for some other
-	 * versions, too? */
-	if (local->sta_fw_ver >= PRISM2_FW_VER(0,8,2)) {
-		if (hostap_set_word(dev, HFA384X_RID_CNFTHIRTY2TALLY, 1)) {
-			printk(KERN_INFO "%s: cnfThirty2Tally setting "
-			       "failed\n", dev->name);
-			local->tallies32 = 0;
-		} else
-			local->tallies32 = 1;
-	} else
-		local->tallies32 = 0;
-
-	hostap_set_auth_algs(local);
-
-	if (hostap_set_word(dev, HFA384X_RID_FRAGMENTATIONTHRESHOLD,
-			    local->fragm_threshold)) {
-		printk(KERN_INFO "%s: setting FragmentationThreshold to %d "
-		       "failed\n", dev->name, local->fragm_threshold);
-	}
-
-	if (hostap_set_word(dev, HFA384X_RID_RTSTHRESHOLD,
-			    local->rts_threshold)) {
-		printk(KERN_INFO "%s: setting RTSThreshold to %d failed\n",
-		       dev->name, local->rts_threshold);
-	}
-
-	if (local->manual_retry_count >= 0 &&
-	    hostap_set_word(dev, HFA384X_RID_CNFALTRETRYCOUNT,
-			    local->manual_retry_count)) {
-		printk(KERN_INFO "%s: setting cnfAltRetryCount to %d failed\n",
-		       dev->name, local->manual_retry_count);
-	}
-
-	if (local->sta_fw_ver >= PRISM2_FW_VER(1,3,1) &&
-	    hfa384x_get_rid(dev, HFA384X_RID_CNFDBMADJUST, &tmp, 2, 1) == 2) {
-		local->rssi_to_dBm = le16_to_cpu(tmp);
-	}
-
-	if (local->sta_fw_ver >= PRISM2_FW_VER(1,7,0) && local->wpa &&
-	    hostap_set_word(dev, HFA384X_RID_SSNHANDLINGMODE, 1)) {
-		printk(KERN_INFO "%s: setting ssnHandlingMode to 1 failed\n",
-		       dev->name);
-	}
-
-	if (local->sta_fw_ver >= PRISM2_FW_VER(1,7,0) && local->generic_elem &&
-	    hfa384x_set_rid(dev, HFA384X_RID_GENERICELEMENT,
-			    local->generic_elem, local->generic_elem_len)) {
-		printk(KERN_INFO "%s: setting genericElement failed\n",
-		       dev->name);
-	}
-
- fail:
-	return ret;
-}
-
-
-static int prism2_hw_init(struct net_device *dev, int initial)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int ret, first = 1;
-	unsigned long start, delay;
-
-	PDEBUG(DEBUG_FLOW, "prism2_hw_init()\n");
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	clear_bit(HOSTAP_BITS_TRANSMIT, &local->bits);
-
- init:
-	/* initialize HFA 384x */
-	ret = hfa384x_cmd_no_wait(dev, HFA384X_CMDCODE_INIT, 0);
-	if (ret) {
-		printk(KERN_INFO "%s: first command failed - assuming card "
-		       "does not have primary firmware\n", dev_info);
-	}
-
-	if (first && (HFA384X_INW(HFA384X_EVSTAT_OFF) & HFA384X_EV_CMD)) {
-		/* EvStat has Cmd bit set in some cases, so retry once if no
-		 * wait was needed */
-		HFA384X_OUTW(HFA384X_EV_CMD, HFA384X_EVACK_OFF);
-		printk(KERN_DEBUG "%s: init command completed too quickly - "
-		       "retrying\n", dev->name);
-		first = 0;
-		goto init;
-	}
-
-	start = jiffies;
-	delay = jiffies + HFA384X_INIT_TIMEOUT;
-	while (!(HFA384X_INW(HFA384X_EVSTAT_OFF) & HFA384X_EV_CMD) &&
-	       time_before(jiffies, delay))
-		yield();
-	if (!(HFA384X_INW(HFA384X_EVSTAT_OFF) & HFA384X_EV_CMD)) {
-		printk(KERN_DEBUG "%s: assuming no Primary image in "
-		       "flash - card initialization not completed\n",
-		       dev_info);
-		local->no_pri = 1;
-#ifdef PRISM2_DOWNLOAD_SUPPORT
-			if (local->sram_type == -1)
-				local->sram_type = prism2_get_ram_size(local);
-#endif /* PRISM2_DOWNLOAD_SUPPORT */
-		return 1;
-	}
-	local->no_pri = 0;
-	printk(KERN_DEBUG "prism2_hw_init: initialized in %lu ms\n",
-	       (jiffies - start) * 1000 / HZ);
-	HFA384X_OUTW(HFA384X_EV_CMD, HFA384X_EVACK_OFF);
-	return 0;
-}
-
-
-static int prism2_hw_init2(struct net_device *dev, int initial)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int i;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-#ifdef PRISM2_DOWNLOAD_SUPPORT
-	kfree(local->pda);
-	if (local->no_pri)
-		local->pda = NULL;
-	else
-		local->pda = prism2_read_pda(dev);
-#endif /* PRISM2_DOWNLOAD_SUPPORT */
-
-	hfa384x_disable_interrupts(dev);
-
-#ifndef final_version
-	HFA384X_OUTW(HFA384X_MAGIC, HFA384X_SWSUPPORT0_OFF);
-	if (HFA384X_INW(HFA384X_SWSUPPORT0_OFF) != HFA384X_MAGIC) {
-		printk("SWSUPPORT0 write/read failed: %04X != %04X\n",
-		       HFA384X_INW(HFA384X_SWSUPPORT0_OFF), HFA384X_MAGIC);
-		goto failed;
-	}
-#endif
-
-	if (initial || local->pri_only) {
-		hfa384x_events_only_cmd(dev);
-		/* get card version information */
-		if (prism2_get_version_info(dev, HFA384X_RID_NICID, "NIC") ||
-		    prism2_get_version_info(dev, HFA384X_RID_PRIID, "PRI")) {
-			hfa384x_disable_interrupts(dev);
-			goto failed;
-		}
-
-		if (prism2_get_version_info(dev, HFA384X_RID_STAID, "STA")) {
-			printk(KERN_DEBUG "%s: Failed to read STA f/w version "
-			       "- only Primary f/w present\n", dev->name);
-			local->pri_only = 1;
-			return 0;
-		}
-		local->pri_only = 0;
-		hfa384x_disable_interrupts(dev);
-	}
-
-	/* FIX: could convert allocate_fid to use sleeping CmdCompl wait and
-	 * enable interrupts before this. This would also require some sort of
-	 * sleeping AllocEv waiting */
-
-	/* allocate TX FIDs */
-	local->txfid_len = PRISM2_TXFID_LEN;
-	for (i = 0; i < PRISM2_TXFID_COUNT; i++) {
-		local->txfid[i] = hfa384x_allocate_fid(dev, local->txfid_len);
-		if (local->txfid[i] == 0xffff && local->txfid_len > 1600) {
-			local->txfid[i] = hfa384x_allocate_fid(dev, 1600);
-			if (local->txfid[i] != 0xffff) {
-				printk(KERN_DEBUG "%s: Using shorter TX FID "
-				       "(1600 bytes)\n", dev->name);
-				local->txfid_len = 1600;
-			}
-		}
-		if (local->txfid[i] == 0xffff)
-			goto failed;
-		local->intransmitfid[i] = PRISM2_TXFID_EMPTY;
-	}
-
-	hfa384x_events_only_cmd(dev);
-
-	if (initial) {
-		u8 addr[ETH_ALEN] = {};
-		struct list_head *ptr;
-
-		prism2_check_sta_fw_version(local);
-
-		if (hfa384x_get_rid(dev, HFA384X_RID_CNFOWNMACADDR,
-				    addr, ETH_ALEN, 1) < 0) {
-			printk("%s: could not get own MAC address\n",
-			       dev->name);
-		}
-		eth_hw_addr_set(dev, addr);
-		list_for_each(ptr, &local->hostap_interfaces) {
-			iface = list_entry(ptr, struct hostap_interface, list);
-			eth_hw_addr_inherit(iface->dev, dev);
-		}
-	} else if (local->fw_ap)
-		prism2_check_sta_fw_version(local);
-
-	prism2_setup_rids(dev);
-
-	/* MAC is now configured, but port 0 is not yet enabled */
-	return 0;
-
- failed:
-	if (!local->no_pri)
-		printk(KERN_WARNING "%s: Initialization failed\n", dev_info);
-	return 1;
-}
-
-
-static int prism2_hw_enable(struct net_device *dev, int initial)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int was_resetting;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-	was_resetting = local->hw_resetting;
-
-	if (hfa384x_cmd(dev, HFA384X_CMDCODE_ENABLE, 0, NULL, NULL)) {
-		printk("%s: MAC port 0 enabling failed\n", dev->name);
-		return 1;
-	}
-
-	local->hw_ready = 1;
-	local->hw_reset_tries = 0;
-	local->hw_resetting = 0;
-	hfa384x_enable_interrupts(dev);
-
-	/* at least D-Link DWL-650 seems to require additional port reset
-	 * before it starts acting as an AP, so reset port automatically
-	 * here just in case */
-	if (initial && prism2_reset_port(dev)) {
-		printk("%s: MAC port 0 resetting failed\n", dev->name);
-		return 1;
-	}
-
-	if (was_resetting && netif_queue_stopped(dev)) {
-		/* If hw_reset() was called during pending transmit, netif
-		 * queue was stopped. Wake it up now since the wlan card has
-		 * been resetted. */
-		netif_wake_queue(dev);
-	}
-
-	return 0;
-}
-
-
-static int prism2_hw_config(struct net_device *dev, int initial)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (local->hw_downloading)
-		return 1;
-
-	if (prism2_hw_init(dev, initial)) {
-		return local->no_pri ? 0 : 1;
-	}
-
-	if (prism2_hw_init2(dev, initial))
-		return 1;
-
-	/* Enable firmware if secondary image is loaded and at least one of the
-	 * netdevices is up. */
-	if (!local->pri_only &&
-	    (initial == 0 || (initial == 2 && local->num_dev_open > 0))) {
-		if (!local->dev_enabled)
-			prism2_callback(local, PRISM2_CALLBACK_ENABLE);
-		local->dev_enabled = 1;
-		return prism2_hw_enable(dev, initial);
-	}
-
-	return 0;
-}
-
-
-static void prism2_hw_shutdown(struct net_device *dev, int no_disable)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	/* Allow only command completion events during disable */
-	hfa384x_events_only_cmd(dev);
-
-	local->hw_ready = 0;
-	if (local->dev_enabled)
-		prism2_callback(local, PRISM2_CALLBACK_DISABLE);
-	local->dev_enabled = 0;
-
-	if (local->func->card_present && !local->func->card_present(local)) {
-		printk(KERN_DEBUG "%s: card already removed or not configured "
-		       "during shutdown\n", dev->name);
-		return;
-	}
-
-	if ((no_disable & HOSTAP_HW_NO_DISABLE) == 0 &&
-	    hfa384x_cmd(dev, HFA384X_CMDCODE_DISABLE, 0, NULL, NULL))
-		printk(KERN_WARNING "%s: Shutdown failed\n", dev_info);
-
-	hfa384x_disable_interrupts(dev);
-
-	if (no_disable & HOSTAP_HW_ENABLE_CMDCOMPL)
-		hfa384x_events_only_cmd(dev);
-	else
-		prism2_clear_cmd_queue(local);
-}
-
-
-static void prism2_hw_reset(struct net_device *dev)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-
-#if 0
-	static long last_reset = 0;
-
-	/* do not reset card more than once per second to avoid ending up in a
-	 * busy loop resetting the card */
-	if (time_before_eq(jiffies, last_reset + HZ))
-		return;
-	last_reset = jiffies;
-#endif
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (local->hw_downloading)
-		return;
-
-	if (local->hw_resetting) {
-		printk(KERN_WARNING "%s: %s: already resetting card - "
-		       "ignoring reset request\n", dev_info, dev->name);
-		return;
-	}
-
-	local->hw_reset_tries++;
-	if (local->hw_reset_tries > 10) {
-		printk(KERN_WARNING "%s: too many reset tries, skipping\n",
-		       dev->name);
-		return;
-	}
-
-	printk(KERN_WARNING "%s: %s: resetting card\n", dev_info, dev->name);
-	hfa384x_disable_interrupts(dev);
-	local->hw_resetting = 1;
-	if (local->func->cor_sreset) {
-		/* Host system seems to hang in some cases with high traffic
-		 * load or shared interrupts during COR sreset. Disable shared
-		 * interrupts during reset to avoid these crashes. COS sreset
-		 * takes quite a long time, so it is unfortunate that this
-		 * seems to be needed. Anyway, I do not know of any better way
-		 * of avoiding the crash. */
-		disable_irq(dev->irq);
-		local->func->cor_sreset(local);
-		enable_irq(dev->irq);
-	}
-	prism2_hw_shutdown(dev, 1);
-	prism2_hw_config(dev, 0);
-	local->hw_resetting = 0;
-
-#ifdef PRISM2_DOWNLOAD_SUPPORT
-	if (local->dl_pri) {
-		printk(KERN_DEBUG "%s: persistent download of primary "
-		       "firmware\n", dev->name);
-		if (prism2_download_genesis(local, local->dl_pri) < 0)
-			printk(KERN_WARNING "%s: download (PRI) failed\n",
-			       dev->name);
-	}
-
-	if (local->dl_sec) {
-		printk(KERN_DEBUG "%s: persistent download of secondary "
-		       "firmware\n", dev->name);
-		if (prism2_download_volatile(local, local->dl_sec) < 0)
-			printk(KERN_WARNING "%s: download (SEC) failed\n",
-			       dev->name);
-	}
-#endif /* PRISM2_DOWNLOAD_SUPPORT */
-
-	/* TODO: restore beacon TIM bits for STAs that have buffered frames */
-}
-
-
-static void prism2_schedule_reset(local_info_t *local)
-{
-	schedule_work(&local->reset_queue);
-}
-
-
-/* Called only as scheduled task after noticing card timeout in interrupt
- * context */
-static void handle_reset_queue(struct work_struct *work)
-{
-	local_info_t *local = container_of(work, local_info_t, reset_queue);
-
-	printk(KERN_DEBUG "%s: scheduled card reset\n", local->dev->name);
-	prism2_hw_reset(local->dev);
-
-	if (netif_queue_stopped(local->dev)) {
-		int i;
-
-		for (i = 0; i < PRISM2_TXFID_COUNT; i++)
-			if (local->intransmitfid[i] == PRISM2_TXFID_EMPTY) {
-				PDEBUG(DEBUG_EXTRA, "prism2_tx_timeout: "
-				       "wake up queue\n");
-				netif_wake_queue(local->dev);
-				break;
-			}
-	}
-}
-
-
-static int prism2_get_txfid_idx(local_info_t *local)
-{
-	int idx, end;
-	unsigned long flags;
-
-	spin_lock_irqsave(&local->txfidlock, flags);
-	end = idx = local->next_txfid;
-	do {
-		if (local->intransmitfid[idx] == PRISM2_TXFID_EMPTY) {
-			local->intransmitfid[idx] = PRISM2_TXFID_RESERVED;
-			spin_unlock_irqrestore(&local->txfidlock, flags);
-			return idx;
-		}
-		idx++;
-		if (idx >= PRISM2_TXFID_COUNT)
-			idx = 0;
-	} while (idx != end);
-	spin_unlock_irqrestore(&local->txfidlock, flags);
-
-	PDEBUG(DEBUG_EXTRA2, "prism2_get_txfid_idx: no room in txfid buf: "
-	       "packet dropped\n");
-	local->dev->stats.tx_dropped++;
-
-	return -1;
-}
-
-
-/* Called only from hardware IRQ */
-static void prism2_transmit_cb(struct net_device *dev, long context,
-			       u16 resp0, u16 res)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int idx = (int) context;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (res) {
-		printk(KERN_DEBUG "%s: prism2_transmit_cb - res=0x%02x\n",
-		       dev->name, res);
-		return;
-	}
-
-	if (idx < 0 || idx >= PRISM2_TXFID_COUNT) {
-		printk(KERN_DEBUG "%s: prism2_transmit_cb called with invalid "
-		       "idx=%d\n", dev->name, idx);
-		return;
-	}
-
-	if (!test_and_clear_bit(HOSTAP_BITS_TRANSMIT, &local->bits)) {
-		printk(KERN_DEBUG "%s: driver bug: prism2_transmit_cb called "
-		       "with no pending transmit\n", dev->name);
-	}
-
-	if (netif_queue_stopped(dev)) {
-		/* ready for next TX, so wake up queue that was stopped in
-		 * prism2_transmit() */
-		netif_wake_queue(dev);
-	}
-
-	spin_lock(&local->txfidlock);
-
-	/* With reclaim, Resp0 contains new txfid for transmit; the old txfid
-	 * will be automatically allocated for the next TX frame */
-	local->intransmitfid[idx] = resp0;
-
-	PDEBUG(DEBUG_FID, "%s: prism2_transmit_cb: txfid[%d]=0x%04x, "
-	       "resp0=0x%04x, transmit_txfid=0x%04x\n",
-	       dev->name, idx, local->txfid[idx],
-	       resp0, local->intransmitfid[local->next_txfid]);
-
-	idx++;
-	if (idx >= PRISM2_TXFID_COUNT)
-		idx = 0;
-	local->next_txfid = idx;
-
-	/* check if all TX buffers are occupied */
-	do {
-		if (local->intransmitfid[idx] == PRISM2_TXFID_EMPTY) {
-			spin_unlock(&local->txfidlock);
-			return;
-		}
-		idx++;
-		if (idx >= PRISM2_TXFID_COUNT)
-			idx = 0;
-	} while (idx != local->next_txfid);
-	spin_unlock(&local->txfidlock);
-
-	/* no empty TX buffers, stop queue */
-	netif_stop_queue(dev);
-}
-
-
-/* Called only from software IRQ if PCI bus master is not used (with bus master
- * this can be called both from software and hardware IRQ) */
-static int prism2_transmit(struct net_device *dev, int idx)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int res;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	/* The driver tries to stop netif queue so that there would not be
-	 * more than one attempt to transmit frames going on; check that this
-	 * is really the case */
-
-	if (test_and_set_bit(HOSTAP_BITS_TRANSMIT, &local->bits)) {
-		printk(KERN_DEBUG "%s: driver bug - prism2_transmit() called "
-		       "when previous TX was pending\n", dev->name);
-		return -1;
-	}
-
-	/* stop the queue for the time that transmit is pending */
-	netif_stop_queue(dev);
-
-	/* transmit packet */
-	res = hfa384x_cmd_callback(
-		dev,
-		HFA384X_CMDCODE_TRANSMIT | HFA384X_CMD_TX_RECLAIM,
-		local->txfid[idx],
-		prism2_transmit_cb, (long) idx);
-
-	if (res) {
-		printk(KERN_DEBUG "%s: prism2_transmit: CMDCODE_TRANSMIT "
-		       "failed (res=%d)\n", dev->name, res);
-		dev->stats.tx_dropped++;
-		netif_wake_queue(dev);
-		return -1;
-	}
-	netif_trans_update(dev);
-
-	/* Since we did not wait for command completion, the card continues
-	 * to process on the background and we will finish handling when
-	 * command completion event is handled (prism2_cmd_ev() function) */
-
-	return 0;
-}
-
-
-/* Send IEEE 802.11 frame (convert the header into Prism2 TX descriptor and
- * send the payload with this descriptor) */
-/* Called only from software IRQ */
-static int prism2_tx_80211(struct sk_buff *skb, struct net_device *dev)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	struct hfa384x_tx_frame txdesc;
-	struct hostap_skb_tx_data *meta;
-	int hdr_len, data_len, idx, res, ret = -1;
-	u16 tx_control;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	meta = (struct hostap_skb_tx_data *) skb->cb;
-
-	prism2_callback(local, PRISM2_CALLBACK_TX_START);
-
-	if ((local->func->card_present && !local->func->card_present(local)) ||
-	    !local->hw_ready || local->hw_downloading || local->pri_only) {
-		if (net_ratelimit()) {
-			printk(KERN_DEBUG "%s: prism2_tx_80211: hw not ready -"
-			       " skipping\n", dev->name);
-		}
-		goto fail;
-	}
-
-	memset(&txdesc, 0, sizeof(txdesc));
-
-	/* skb->data starts with txdesc->frame_control */
-	hdr_len = sizeof(txdesc.header);
-	BUILD_BUG_ON(hdr_len != 24);
-	skb_copy_from_linear_data(skb, &txdesc.header, hdr_len);
-	if (ieee80211_is_data(txdesc.frame_control) &&
-	    ieee80211_has_a4(txdesc.frame_control) &&
-	    skb->len >= 30) {
-		/* Addr4 */
-		skb_copy_from_linear_data_offset(skb, hdr_len, txdesc.addr4,
-						 ETH_ALEN);
-		hdr_len += ETH_ALEN;
-	}
-
-	tx_control = local->tx_control;
-	if (meta->tx_cb_idx) {
-		tx_control |= HFA384X_TX_CTRL_TX_OK;
-		txdesc.sw_support = cpu_to_le32(meta->tx_cb_idx);
-	}
-	txdesc.tx_control = cpu_to_le16(tx_control);
-	txdesc.tx_rate = meta->rate;
-
-	data_len = skb->len - hdr_len;
-	txdesc.data_len = cpu_to_le16(data_len);
-	txdesc.len = cpu_to_be16(data_len);
-
-	idx = prism2_get_txfid_idx(local);
-	if (idx < 0)
-		goto fail;
-
-	if (local->frame_dump & PRISM2_DUMP_TX_HDR)
-		hostap_dump_tx_header(dev->name, &txdesc);
-
-	spin_lock(&local->baplock);
-	res = hfa384x_setup_bap(dev, BAP0, local->txfid[idx], 0);
-
-	if (!res)
-		res = hfa384x_to_bap(dev, BAP0, &txdesc, sizeof(txdesc));
-	if (!res)
-		res = hfa384x_to_bap(dev, BAP0, skb->data + hdr_len,
-				     skb->len - hdr_len);
-	spin_unlock(&local->baplock);
-
-	if (!res)
-		res = prism2_transmit(dev, idx);
-	if (res) {
-		printk(KERN_DEBUG "%s: prism2_tx_80211 - to BAP0 failed\n",
-		       dev->name);
-		local->intransmitfid[idx] = PRISM2_TXFID_EMPTY;
-		schedule_work(&local->reset_queue);
-		goto fail;
-	}
-
-	ret = 0;
-
-fail:
-	prism2_callback(local, PRISM2_CALLBACK_TX_END);
-	return ret;
-}
-
-
-/* Some SMP systems have reported number of odd errors with hostap_pci. fid
- * register has changed values between consecutive reads for an unknown reason.
- * This should really not happen, so more debugging is needed. This test
- * version is a bit slower, but it will detect most of such register changes
- * and will try to get the correct fid eventually. */
-#define EXTRA_FID_READ_TESTS
-
-static u16 prism2_read_fid_reg(struct net_device *dev, u16 reg)
-{
-#ifdef EXTRA_FID_READ_TESTS
-	u16 val, val2, val3;
-	int i;
-
-	for (i = 0; i < 10; i++) {
-		val = HFA384X_INW(reg);
-		val2 = HFA384X_INW(reg);
-		val3 = HFA384X_INW(reg);
-
-		if (val == val2 && val == val3)
-			return val;
-
-		printk(KERN_DEBUG "%s: detected fid change (try=%d, reg=%04x):"
-		       " %04x %04x %04x\n",
-		       dev->name, i, reg, val, val2, val3);
-		if ((val == val2 || val == val3) && val != 0)
-			return val;
-		if (val2 == val3 && val2 != 0)
-			return val2;
-	}
-	printk(KERN_WARNING "%s: Uhhuh.. could not read good fid from reg "
-	       "%04x (%04x %04x %04x)\n", dev->name, reg, val, val2, val3);
-	return val;
-#else /* EXTRA_FID_READ_TESTS */
-	return HFA384X_INW(reg);
-#endif /* EXTRA_FID_READ_TESTS */
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static void prism2_rx(local_info_t *local)
-{
-	struct net_device *dev = local->dev;
-	int res, rx_pending = 0;
-	u16 len, hdr_len, rxfid, status, macport;
-	struct hfa384x_rx_frame rxdesc;
-	struct sk_buff *skb = NULL;
-
-	prism2_callback(local, PRISM2_CALLBACK_RX_START);
-
-	rxfid = prism2_read_fid_reg(dev, HFA384X_RXFID_OFF);
-#ifndef final_version
-	if (rxfid == 0) {
-		rxfid = HFA384X_INW(HFA384X_RXFID_OFF);
-		printk(KERN_DEBUG "prism2_rx: rxfid=0 (next 0x%04x)\n",
-		       rxfid);
-		if (rxfid == 0) {
-			schedule_work(&local->reset_queue);
-			goto rx_dropped;
-		}
-		/* try to continue with the new rxfid value */
-	}
-#endif
-
-	spin_lock(&local->baplock);
-	res = hfa384x_setup_bap(dev, BAP0, rxfid, 0);
-	if (!res)
-		res = hfa384x_from_bap(dev, BAP0, &rxdesc, sizeof(rxdesc));
-
-	if (res) {
-		spin_unlock(&local->baplock);
-		printk(KERN_DEBUG "%s: copy from BAP0 failed %d\n", dev->name,
-		       res);
-		if (res == -ETIMEDOUT) {
-			schedule_work(&local->reset_queue);
-		}
-		goto rx_dropped;
-	}
-
-	len = le16_to_cpu(rxdesc.data_len);
-	hdr_len = sizeof(rxdesc);
-	status = le16_to_cpu(rxdesc.status);
-	macport = (status >> 8) & 0x07;
-
-	/* Drop frames with too large reported payload length. Monitor mode
-	 * seems to sometimes pass frames (e.g., ctrl::ack) with signed and
-	 * negative value, so allow also values 65522 .. 65534 (-14 .. -2) for
-	 * macport 7 */
-	if (len > PRISM2_DATA_MAXLEN + 8 /* WEP */) {
-		if (macport == 7 && local->iw_mode == IW_MODE_MONITOR) {
-			if (len >= (u16) -14) {
-				hdr_len -= 65535 - len;
-				hdr_len--;
-			}
-			len = 0;
-		} else {
-			spin_unlock(&local->baplock);
-			printk(KERN_DEBUG "%s: Received frame with invalid "
-			       "length 0x%04x\n", dev->name, len);
-			hostap_dump_rx_header(dev->name, &rxdesc);
-			goto rx_dropped;
-		}
-	}
-
-	skb = dev_alloc_skb(len + hdr_len);
-	if (!skb) {
-		spin_unlock(&local->baplock);
-		printk(KERN_DEBUG "%s: RX failed to allocate skb\n",
-		       dev->name);
-		goto rx_dropped;
-	}
-	skb->dev = dev;
-	skb_put_data(skb, &rxdesc, hdr_len);
-
-	if (len > 0)
-		res = hfa384x_from_bap(dev, BAP0, skb_put(skb, len), len);
-	spin_unlock(&local->baplock);
-	if (res) {
-		printk(KERN_DEBUG "%s: RX failed to read "
-		       "frame data\n", dev->name);
-		goto rx_dropped;
-	}
-
-	skb_queue_tail(&local->rx_list, skb);
-	tasklet_schedule(&local->rx_tasklet);
-
- rx_exit:
-	prism2_callback(local, PRISM2_CALLBACK_RX_END);
-	if (!rx_pending) {
-		HFA384X_OUTW(HFA384X_EV_RX, HFA384X_EVACK_OFF);
-	}
-
-	return;
-
- rx_dropped:
-	dev->stats.rx_dropped++;
-	if (skb)
-		dev_kfree_skb(skb);
-	goto rx_exit;
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static void hostap_rx_skb(local_info_t *local, struct sk_buff *skb)
-{
-	struct hfa384x_rx_frame *rxdesc;
-	struct net_device *dev = skb->dev;
-	struct hostap_80211_rx_status stats;
-	int hdrlen, rx_hdrlen;
-
-	rx_hdrlen = sizeof(*rxdesc);
-	if (skb->len < sizeof(*rxdesc)) {
-		/* Allow monitor mode to receive shorter frames */
-		if (local->iw_mode == IW_MODE_MONITOR &&
-		    skb->len >= sizeof(*rxdesc) - 30) {
-			rx_hdrlen = skb->len;
-		} else {
-			dev_kfree_skb(skb);
-			return;
-		}
-	}
-
-	rxdesc = (struct hfa384x_rx_frame *) skb->data;
-
-	if (local->frame_dump & PRISM2_DUMP_RX_HDR &&
-	    skb->len >= sizeof(*rxdesc))
-		hostap_dump_rx_header(dev->name, rxdesc);
-
-	if (le16_to_cpu(rxdesc->status) & HFA384X_RX_STATUS_FCSERR &&
-	    (!local->monitor_allow_fcserr ||
-	     local->iw_mode != IW_MODE_MONITOR))
-		goto drop;
-
-	if (skb->len > PRISM2_DATA_MAXLEN) {
-		printk(KERN_DEBUG "%s: RX: len(%d) > MAX(%d)\n",
-		       dev->name, skb->len, PRISM2_DATA_MAXLEN);
-		goto drop;
-	}
-
-	stats.mac_time = le32_to_cpu(rxdesc->time);
-	stats.signal = rxdesc->signal - local->rssi_to_dBm;
-	stats.noise = rxdesc->silence - local->rssi_to_dBm;
-	stats.rate = rxdesc->rate;
-
-	/* Convert Prism2 RX structure into IEEE 802.11 header */
-	hdrlen = hostap_80211_get_hdrlen(rxdesc->frame_control);
-	if (hdrlen > rx_hdrlen)
-		hdrlen = rx_hdrlen;
-
-	memmove(skb_pull(skb, rx_hdrlen - hdrlen),
-		&rxdesc->frame_control, hdrlen);
-
-	hostap_80211_rx(dev, skb, &stats);
-	return;
-
- drop:
-	dev_kfree_skb(skb);
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static void hostap_rx_tasklet(struct tasklet_struct *t)
-{
-	local_info_t *local = from_tasklet(local, t, rx_tasklet);
-	struct sk_buff *skb;
-
-	while ((skb = skb_dequeue(&local->rx_list)) != NULL)
-		hostap_rx_skb(local, skb);
-}
-
-
-/* Called only from hardware IRQ */
-static void prism2_alloc_ev(struct net_device *dev)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int idx;
-	u16 fid;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	fid = prism2_read_fid_reg(dev, HFA384X_ALLOCFID_OFF);
-
-	PDEBUG(DEBUG_FID, "FID: interrupt: ALLOC - fid=0x%04x\n", fid);
-
-	spin_lock(&local->txfidlock);
-	idx = local->next_alloc;
-
-	do {
-		if (local->txfid[idx] == fid) {
-			PDEBUG(DEBUG_FID, "FID: found matching txfid[%d]\n",
-			       idx);
-
-#ifndef final_version
-			if (local->intransmitfid[idx] == PRISM2_TXFID_EMPTY)
-				printk("Already released txfid found at idx "
-				       "%d\n", idx);
-			if (local->intransmitfid[idx] == PRISM2_TXFID_RESERVED)
-				printk("Already reserved txfid found at idx "
-				       "%d\n", idx);
-#endif
-			local->intransmitfid[idx] = PRISM2_TXFID_EMPTY;
-			idx++;
-			local->next_alloc = idx >= PRISM2_TXFID_COUNT ? 0 :
-				idx;
-
-			if (!test_bit(HOSTAP_BITS_TRANSMIT, &local->bits) &&
-			    netif_queue_stopped(dev))
-				netif_wake_queue(dev);
-
-			spin_unlock(&local->txfidlock);
-			return;
-		}
-
-		idx++;
-		if (idx >= PRISM2_TXFID_COUNT)
-			idx = 0;
-	} while (idx != local->next_alloc);
-
-	printk(KERN_WARNING "%s: could not find matching txfid (0x%04x, new "
-	       "read 0x%04x) for alloc event\n", dev->name, fid,
-	       HFA384X_INW(HFA384X_ALLOCFID_OFF));
-	printk(KERN_DEBUG "TXFIDs:");
-	for (idx = 0; idx < PRISM2_TXFID_COUNT; idx++)
-		printk(" %04x[%04x]", local->txfid[idx],
-		       local->intransmitfid[idx]);
-	printk("\n");
-	spin_unlock(&local->txfidlock);
-
-	/* FIX: should probably schedule reset; reference to one txfid was lost
-	 * completely.. Bad things will happen if we run out of txfids
-	 * Actually, this will cause netdev watchdog to notice TX timeout and
-	 * then card reset after all txfids have been leaked. */
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static void hostap_tx_callback(local_info_t *local,
-			       struct hfa384x_tx_frame *txdesc, int ok,
-			       char *payload)
-{
-	u16 sw_support, hdrlen, len;
-	struct sk_buff *skb;
-	struct hostap_tx_callback_info *cb;
-
-	/* Make sure that frame was from us. */
-	if (!ether_addr_equal(txdesc->addr2, local->dev->dev_addr)) {
-		printk(KERN_DEBUG "%s: TX callback - foreign frame\n",
-		       local->dev->name);
-		return;
-	}
-
-	sw_support = le32_to_cpu(txdesc->sw_support);
-
-	spin_lock(&local->lock);
-	cb = local->tx_callback;
-	while (cb != NULL && cb->idx != sw_support)
-		cb = cb->next;
-	spin_unlock(&local->lock);
-
-	if (cb == NULL) {
-		printk(KERN_DEBUG "%s: could not find TX callback (idx %d)\n",
-		       local->dev->name, sw_support);
-		return;
-	}
-
-	hdrlen = hostap_80211_get_hdrlen(txdesc->frame_control);
-	len = le16_to_cpu(txdesc->data_len);
-	skb = dev_alloc_skb(hdrlen + len);
-	if (skb == NULL) {
-		printk(KERN_DEBUG "%s: hostap_tx_callback failed to allocate "
-		       "skb\n", local->dev->name);
-		return;
-	}
-
-	skb_put_data(skb, (void *)&txdesc->frame_control, hdrlen);
-	if (payload)
-		skb_put_data(skb, payload, len);
-
-	skb->dev = local->dev;
-	skb_reset_mac_header(skb);
-
-	cb->func(skb, ok, cb->data);
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static int hostap_tx_compl_read(local_info_t *local, int error,
-				struct hfa384x_tx_frame *txdesc,
-				char **payload)
-{
-	u16 fid, len;
-	int res, ret = 0;
-	struct net_device *dev = local->dev;
-
-	fid = prism2_read_fid_reg(dev, HFA384X_TXCOMPLFID_OFF);
-
-	PDEBUG(DEBUG_FID, "interrupt: TX (err=%d) - fid=0x%04x\n", fid, error);
-
-	spin_lock(&local->baplock);
-	res = hfa384x_setup_bap(dev, BAP0, fid, 0);
-	if (!res)
-		res = hfa384x_from_bap(dev, BAP0, txdesc, sizeof(*txdesc));
-	if (res) {
-		PDEBUG(DEBUG_EXTRA, "%s: TX (err=%d) - fid=0x%04x - could not "
-		       "read txdesc\n", dev->name, error, fid);
-		if (res == -ETIMEDOUT) {
-			schedule_work(&local->reset_queue);
-		}
-		ret = -1;
-		goto fail;
-	}
-	if (txdesc->sw_support) {
-		len = le16_to_cpu(txdesc->data_len);
-		if (len < PRISM2_DATA_MAXLEN) {
-			*payload = kmalloc(len, GFP_ATOMIC);
-			if (*payload == NULL ||
-			    hfa384x_from_bap(dev, BAP0, *payload, len)) {
-				PDEBUG(DEBUG_EXTRA, "%s: could not read TX "
-				       "frame payload\n", dev->name);
-				kfree(*payload);
-				*payload = NULL;
-				ret = -1;
-				goto fail;
-			}
-		}
-	}
-
- fail:
-	spin_unlock(&local->baplock);
-
-	return ret;
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static void prism2_tx_ev(local_info_t *local)
-{
-	struct net_device *dev = local->dev;
-	char *payload = NULL;
-	struct hfa384x_tx_frame txdesc;
-
-	if (hostap_tx_compl_read(local, 0, &txdesc, &payload))
-		goto fail;
-
-	if (local->frame_dump & PRISM2_DUMP_TX_HDR) {
-		PDEBUG(DEBUG_EXTRA, "%s: TX - status=0x%04x "
-		       "retry_count=%d tx_rate=%d seq_ctrl=%d "
-		       "duration_id=%d\n",
-		       dev->name, le16_to_cpu(txdesc.status),
-		       txdesc.retry_count, txdesc.tx_rate,
-		       le16_to_cpu(txdesc.seq_ctrl),
-		       le16_to_cpu(txdesc.duration_id));
-	}
-
-	if (txdesc.sw_support)
-		hostap_tx_callback(local, &txdesc, 1, payload);
-	kfree(payload);
-
- fail:
-	HFA384X_OUTW(HFA384X_EV_TX, HFA384X_EVACK_OFF);
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static void hostap_sta_tx_exc_tasklet(struct tasklet_struct *t)
-{
-	local_info_t *local = from_tasklet(local, t, sta_tx_exc_tasklet);
-	struct sk_buff *skb;
-
-	while ((skb = skb_dequeue(&local->sta_tx_exc_list)) != NULL) {
-		struct hfa384x_tx_frame *txdesc =
-			(struct hfa384x_tx_frame *) skb->data;
-
-		if (skb->len >= sizeof(*txdesc)) {
-			/* Convert Prism2 RX structure into IEEE 802.11 header
-			 */
-			int hdrlen = hostap_80211_get_hdrlen(txdesc->frame_control);
-			memmove(skb_pull(skb, sizeof(*txdesc) - hdrlen),
-				&txdesc->frame_control, hdrlen);
-
-			hostap_handle_sta_tx_exc(local, skb);
-		}
-		dev_kfree_skb(skb);
-	}
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static void prism2_txexc(local_info_t *local)
-{
-	struct net_device *dev = local->dev;
-	u16 status, fc;
-	int show_dump, res;
-	char *payload = NULL;
-	struct hfa384x_tx_frame txdesc;
-
-	show_dump = local->frame_dump & PRISM2_DUMP_TXEXC_HDR;
-	dev->stats.tx_errors++;
-
-	res = hostap_tx_compl_read(local, 1, &txdesc, &payload);
-	HFA384X_OUTW(HFA384X_EV_TXEXC, HFA384X_EVACK_OFF);
-	if (res)
-		return;
-
-	status = le16_to_cpu(txdesc.status);
-
-	/* We produce a TXDROP event only for retry or lifetime
-	 * exceeded, because that's the only status that really mean
-	 * that this particular node went away.
-	 * Other errors means that *we* screwed up. - Jean II */
-	if (status & (HFA384X_TX_STATUS_RETRYERR | HFA384X_TX_STATUS_AGEDERR))
-	{
-		union iwreq_data wrqu;
-
-		/* Copy 802.11 dest address. */
-		memcpy(wrqu.addr.sa_data, txdesc.addr1, ETH_ALEN);
-		wrqu.addr.sa_family = ARPHRD_ETHER;
-		wireless_send_event(dev, IWEVTXDROP, &wrqu, NULL);
-	} else
-		show_dump = 1;
-
-	if (local->iw_mode == IW_MODE_MASTER ||
-	    local->iw_mode == IW_MODE_REPEAT ||
-	    local->wds_type & HOSTAP_WDS_AP_CLIENT) {
-		struct sk_buff *skb;
-		skb = dev_alloc_skb(sizeof(txdesc));
-		if (skb) {
-			skb_put_data(skb, &txdesc, sizeof(txdesc));
-			skb_queue_tail(&local->sta_tx_exc_list, skb);
-			tasklet_schedule(&local->sta_tx_exc_tasklet);
-		}
-	}
-
-	if (txdesc.sw_support)
-		hostap_tx_callback(local, &txdesc, 0, payload);
-	kfree(payload);
-
-	if (!show_dump)
-		return;
-
-	PDEBUG(DEBUG_EXTRA, "%s: TXEXC - status=0x%04x (%s%s%s%s)"
-	       " tx_control=%04x\n",
-	       dev->name, status,
-	       status & HFA384X_TX_STATUS_RETRYERR ? "[RetryErr]" : "",
-	       status & HFA384X_TX_STATUS_AGEDERR ? "[AgedErr]" : "",
-	       status & HFA384X_TX_STATUS_DISCON ? "[Discon]" : "",
-	       status & HFA384X_TX_STATUS_FORMERR ? "[FormErr]" : "",
-	       le16_to_cpu(txdesc.tx_control));
-
-	fc = le16_to_cpu(txdesc.frame_control);
-	PDEBUG(DEBUG_EXTRA, "   retry_count=%d tx_rate=%d fc=0x%04x "
-	       "(%s%s%s::%d%s%s)\n",
-	       txdesc.retry_count, txdesc.tx_rate, fc,
-	       ieee80211_is_mgmt(txdesc.frame_control) ? "Mgmt" : "",
-	       ieee80211_is_ctl(txdesc.frame_control) ? "Ctrl" : "",
-	       ieee80211_is_data(txdesc.frame_control) ? "Data" : "",
-	       (fc & IEEE80211_FCTL_STYPE) >> 4,
-	       ieee80211_has_tods(txdesc.frame_control) ? " ToDS" : "",
-	       ieee80211_has_fromds(txdesc.frame_control) ? " FromDS" : "");
-	PDEBUG(DEBUG_EXTRA, "   A1=%pM A2=%pM A3=%pM A4=%pM\n",
-	       txdesc.addr1, txdesc.addr2,
-	       txdesc.addr3, txdesc.addr4);
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static void hostap_info_tasklet(struct tasklet_struct *t)
-{
-	local_info_t *local = from_tasklet(local, t, info_tasklet);
-	struct sk_buff *skb;
-
-	while ((skb = skb_dequeue(&local->info_list)) != NULL) {
-		hostap_info_process(local, skb);
-		dev_kfree_skb(skb);
-	}
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static void prism2_info(local_info_t *local)
-{
-	struct net_device *dev = local->dev;
-	u16 fid;
-	int res, left;
-	struct hfa384x_info_frame info;
-	struct sk_buff *skb;
-
-	fid = HFA384X_INW(HFA384X_INFOFID_OFF);
-
-	spin_lock(&local->baplock);
-	res = hfa384x_setup_bap(dev, BAP0, fid, 0);
-	if (!res)
-		res = hfa384x_from_bap(dev, BAP0, &info, sizeof(info));
-	if (res) {
-		spin_unlock(&local->baplock);
-		printk(KERN_DEBUG "Could not get info frame (fid=0x%04x)\n",
-		       fid);
-		if (res == -ETIMEDOUT) {
-			schedule_work(&local->reset_queue);
-		}
-		goto out;
-	}
-
-	left = (le16_to_cpu(info.len) - 1) * 2;
-
-	if (info.len & cpu_to_le16(0x8000) || info.len == 0 || left > 2060) {
-		/* data register seems to give 0x8000 in some error cases even
-		 * though busy bit is not set in offset register;
-		 * in addition, length must be at least 1 due to type field */
-		spin_unlock(&local->baplock);
-		printk(KERN_DEBUG "%s: Received info frame with invalid "
-		       "length 0x%04x (type 0x%04x)\n", dev->name,
-		       le16_to_cpu(info.len), le16_to_cpu(info.type));
-		goto out;
-	}
-
-	skb = dev_alloc_skb(sizeof(info) + left);
-	if (skb == NULL) {
-		spin_unlock(&local->baplock);
-		printk(KERN_DEBUG "%s: Could not allocate skb for info "
-		       "frame\n", dev->name);
-		goto out;
-	}
-
-	skb_put_data(skb, &info, sizeof(info));
-	if (left > 0 && hfa384x_from_bap(dev, BAP0, skb_put(skb, left), left))
-	{
-		spin_unlock(&local->baplock);
-		printk(KERN_WARNING "%s: Info frame read failed (fid=0x%04x, "
-		       "len=0x%04x, type=0x%04x\n", dev->name, fid,
-		       le16_to_cpu(info.len), le16_to_cpu(info.type));
-		dev_kfree_skb(skb);
-		goto out;
-	}
-	spin_unlock(&local->baplock);
-
-	skb_queue_tail(&local->info_list, skb);
-	tasklet_schedule(&local->info_tasklet);
-
- out:
-	HFA384X_OUTW(HFA384X_EV_INFO, HFA384X_EVACK_OFF);
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static void hostap_bap_tasklet(struct tasklet_struct *t)
-{
-	local_info_t *local = from_tasklet(local, t, bap_tasklet);
-	struct net_device *dev = local->dev;
-	u16 ev;
-	int frames = 30;
-
-	if (local->func->card_present && !local->func->card_present(local))
-		return;
-
-	set_bit(HOSTAP_BITS_BAP_TASKLET, &local->bits);
-
-	/* Process all pending BAP events without generating new interrupts
-	 * for them */
-	while (frames-- > 0) {
-		ev = HFA384X_INW(HFA384X_EVSTAT_OFF);
-		if (ev == 0xffff || !(ev & HFA384X_BAP0_EVENTS))
-			break;
-		if (ev & HFA384X_EV_RX)
-			prism2_rx(local);
-		if (ev & HFA384X_EV_INFO)
-			prism2_info(local);
-		if (ev & HFA384X_EV_TX)
-			prism2_tx_ev(local);
-		if (ev & HFA384X_EV_TXEXC)
-			prism2_txexc(local);
-	}
-
-	set_bit(HOSTAP_BITS_BAP_TASKLET2, &local->bits);
-	clear_bit(HOSTAP_BITS_BAP_TASKLET, &local->bits);
-
-	/* Enable interrupts for new BAP events */
-	hfa384x_events_all(dev);
-	clear_bit(HOSTAP_BITS_BAP_TASKLET2, &local->bits);
-}
-
-
-/* Called only from hardware IRQ */
-static void prism2_infdrop(struct net_device *dev)
-{
-	static unsigned long last_inquire = 0;
-
-	PDEBUG(DEBUG_EXTRA, "%s: INFDROP event\n", dev->name);
-
-	/* some firmware versions seem to get stuck with
-	 * full CommTallies in high traffic load cases; every
-	 * packet will then cause INFDROP event and CommTallies
-	 * info frame will not be sent automatically. Try to
-	 * get out of this state by inquiring CommTallies. */
-	if (!last_inquire || time_after(jiffies, last_inquire + HZ)) {
-		hfa384x_cmd_callback(dev, HFA384X_CMDCODE_INQUIRE,
-				     HFA384X_INFO_COMMTALLIES, NULL, 0);
-		last_inquire = jiffies;
-	}
-}
-
-
-/* Called only from hardware IRQ */
-static void prism2_ev_tick(struct net_device *dev)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	u16 evstat, inten;
-	static int prev_stuck = 0;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (time_after(jiffies, local->last_tick_timer + 5 * HZ) &&
-	    local->last_tick_timer) {
-		evstat = HFA384X_INW(HFA384X_EVSTAT_OFF);
-		inten = HFA384X_INW(HFA384X_INTEN_OFF);
-		if (!prev_stuck) {
-			printk(KERN_INFO "%s: SW TICK stuck? "
-			       "bits=0x%lx EvStat=%04x IntEn=%04x\n",
-			       dev->name, local->bits, evstat, inten);
-		}
-		local->sw_tick_stuck++;
-		if ((evstat & HFA384X_BAP0_EVENTS) &&
-		    (inten & HFA384X_BAP0_EVENTS)) {
-			printk(KERN_INFO "%s: trying to recover from IRQ "
-			       "hang\n", dev->name);
-			hfa384x_events_no_bap0(dev);
-		}
-		prev_stuck = 1;
-	} else
-		prev_stuck = 0;
-}
-
-
-/* Called only from hardware IRQ */
-static void prism2_check_magic(local_info_t *local)
-{
-	/* at least PCI Prism2.5 with bus mastering seems to sometimes
-	 * return 0x0000 in SWSUPPORT0 for unknown reason, but re-reading the
-	 * register once or twice seems to get the correct value.. PCI cards
-	 * cannot anyway be removed during normal operation, so there is not
-	 * really any need for this verification with them. */
-
-#ifndef PRISM2_PCI
-#ifndef final_version
-	static unsigned long last_magic_err = 0;
-	struct net_device *dev = local->dev;
-
-	if (HFA384X_INW(HFA384X_SWSUPPORT0_OFF) != HFA384X_MAGIC) {
-		if (!local->hw_ready)
-			return;
-		HFA384X_OUTW(0xffff, HFA384X_EVACK_OFF);
-		if (time_after(jiffies, last_magic_err + 10 * HZ)) {
-			printk("%s: Interrupt, but SWSUPPORT0 does not match: "
-			       "%04X != %04X - card removed?\n", dev->name,
-			       HFA384X_INW(HFA384X_SWSUPPORT0_OFF),
-			       HFA384X_MAGIC);
-			last_magic_err = jiffies;
-		} else if (net_ratelimit()) {
-			printk(KERN_DEBUG "%s: interrupt - SWSUPPORT0=%04x "
-			       "MAGIC=%04x\n", dev->name,
-			       HFA384X_INW(HFA384X_SWSUPPORT0_OFF),
-			       HFA384X_MAGIC);
-		}
-		if (HFA384X_INW(HFA384X_SWSUPPORT0_OFF) != 0xffff)
-			schedule_work(&local->reset_queue);
-		return;
-	}
-#endif /* final_version */
-#endif /* !PRISM2_PCI */
-}
-
-
-/* Called only from hardware IRQ */
-static irqreturn_t prism2_interrupt(int irq, void *dev_id)
-{
-	struct net_device *dev = dev_id;
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int events = 0;
-	u16 ev;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	/* Detect early interrupt before driver is fully configured */
-	spin_lock(&local->irq_init_lock);
-	if (!dev->base_addr) {
-		if (net_ratelimit()) {
-			printk(KERN_DEBUG "%s: Interrupt, but dev not configured\n",
-			       dev->name);
-		}
-		spin_unlock(&local->irq_init_lock);
-		return IRQ_HANDLED;
-	}
-	spin_unlock(&local->irq_init_lock);
-
-	prism2_io_debug_add(dev, PRISM2_IO_DEBUG_CMD_INTERRUPT, 0, 0);
-
-	if (local->func->card_present && !local->func->card_present(local)) {
-		if (net_ratelimit()) {
-			printk(KERN_DEBUG "%s: Interrupt, but dev not OK\n",
-			       dev->name);
-		}
-		return IRQ_HANDLED;
-	}
-
-	prism2_check_magic(local);
-
-	for (;;) {
-		ev = HFA384X_INW(HFA384X_EVSTAT_OFF);
-		if (ev == 0xffff) {
-			if (local->shutdown)
-				return IRQ_HANDLED;
-			HFA384X_OUTW(0xffff, HFA384X_EVACK_OFF);
-			printk(KERN_DEBUG "%s: prism2_interrupt: ev=0xffff\n",
-			       dev->name);
-			return IRQ_HANDLED;
-		}
-
-		ev &= HFA384X_INW(HFA384X_INTEN_OFF);
-		if (ev == 0)
-			break;
-
-		if (ev & HFA384X_EV_CMD) {
-			prism2_cmd_ev(dev);
-		}
-
-		/* Above events are needed even before hw is ready, but other
-		 * events should be skipped during initialization. This may
-		 * change for AllocEv if allocate_fid is implemented without
-		 * busy waiting. */
-		if (!local->hw_ready || local->hw_resetting ||
-		    !local->dev_enabled) {
-			ev = HFA384X_INW(HFA384X_EVSTAT_OFF);
-			if (ev & HFA384X_EV_CMD)
-				goto next_event;
-			if ((ev & HFA384X_EVENT_MASK) == 0)
-				return IRQ_HANDLED;
-			if (local->dev_enabled && (ev & ~HFA384X_EV_TICK) &&
-			    net_ratelimit()) {
-				printk(KERN_DEBUG "%s: prism2_interrupt: hw "
-				       "not ready; skipping events 0x%04x "
-				       "(IntEn=0x%04x)%s%s%s\n",
-				       dev->name, ev,
-				       HFA384X_INW(HFA384X_INTEN_OFF),
-				       !local->hw_ready ? " (!hw_ready)" : "",
-				       local->hw_resetting ?
-				       " (hw_resetting)" : "",
-				       !local->dev_enabled ?
-				       " (!dev_enabled)" : "");
-			}
-			HFA384X_OUTW(ev, HFA384X_EVACK_OFF);
-			return IRQ_HANDLED;
-		}
-
-		if (ev & HFA384X_EV_TICK) {
-			prism2_ev_tick(dev);
-			HFA384X_OUTW(HFA384X_EV_TICK, HFA384X_EVACK_OFF);
-		}
-
-		if (ev & HFA384X_EV_ALLOC) {
-			prism2_alloc_ev(dev);
-			HFA384X_OUTW(HFA384X_EV_ALLOC, HFA384X_EVACK_OFF);
-		}
-
-		/* Reading data from the card is quite time consuming, so do it
-		 * in tasklets. TX, TXEXC, RX, and INFO events will be ACKed
-		 * and unmasked after needed data has been read completely. */
-		if (ev & HFA384X_BAP0_EVENTS) {
-			hfa384x_events_no_bap0(dev);
-			tasklet_schedule(&local->bap_tasklet);
-		}
-
-#ifndef final_version
-		if (ev & HFA384X_EV_WTERR) {
-			PDEBUG(DEBUG_EXTRA, "%s: WTERR event\n", dev->name);
-			HFA384X_OUTW(HFA384X_EV_WTERR, HFA384X_EVACK_OFF);
-		}
-#endif /* final_version */
-
-		if (ev & HFA384X_EV_INFDROP) {
-			prism2_infdrop(dev);
-			HFA384X_OUTW(HFA384X_EV_INFDROP, HFA384X_EVACK_OFF);
-		}
-
-	next_event:
-		events++;
-		if (events >= PRISM2_MAX_INTERRUPT_EVENTS) {
-			PDEBUG(DEBUG_EXTRA, "prism2_interrupt: >%d events "
-			       "(EvStat=0x%04x)\n",
-			       PRISM2_MAX_INTERRUPT_EVENTS,
-			       HFA384X_INW(HFA384X_EVSTAT_OFF));
-			break;
-		}
-	}
-	prism2_io_debug_add(dev, PRISM2_IO_DEBUG_CMD_INTERRUPT, 0, 1);
-	return IRQ_RETVAL(events);
-}
-
-
-static void prism2_check_sta_fw_version(local_info_t *local)
-{
-	struct hfa384x_comp_ident comp;
-	int id, variant, major, minor;
-
-	if (hfa384x_get_rid(local->dev, HFA384X_RID_STAID,
-			    &comp, sizeof(comp), 1) < 0)
-		return;
-
-	local->fw_ap = 0;
-	id = le16_to_cpu(comp.id);
-	if (id != HFA384X_COMP_ID_STA) {
-		if (id == HFA384X_COMP_ID_FW_AP)
-			local->fw_ap = 1;
-		return;
-	}
-
-	major = __le16_to_cpu(comp.major);
-	minor = __le16_to_cpu(comp.minor);
-	variant = __le16_to_cpu(comp.variant);
-	local->sta_fw_ver = PRISM2_FW_VER(major, minor, variant);
-
-	/* Station firmware versions before 1.4.x seem to have a bug in
-	 * firmware-based WEP encryption when using Host AP mode, so use
-	 * host_encrypt as a default for them. Firmware version 1.4.9 is the
-	 * first one that has been seen to produce correct encryption, but the
-	 * bug might be fixed before that (although, at least 1.4.2 is broken).
-	 */
-	local->fw_encrypt_ok = local->sta_fw_ver >= PRISM2_FW_VER(1,4,9);
-
-	if (local->iw_mode == IW_MODE_MASTER && !local->host_encrypt &&
-	    !local->fw_encrypt_ok) {
-		printk(KERN_DEBUG "%s: defaulting to host-based encryption as "
-		       "a workaround for firmware bug in Host AP mode WEP\n",
-		       local->dev->name);
-		local->host_encrypt = 1;
-	}
-
-	/* IEEE 802.11 standard compliant WDS frames (4 addresses) were broken
-	 * in station firmware versions before 1.5.x. With these versions, the
-	 * driver uses a workaround with bogus frame format (4th address after
-	 * the payload). This is not compatible with other AP devices. Since
-	 * the firmware bug is fixed in the latest station firmware versions,
-	 * automatically enable standard compliant mode for cards using station
-	 * firmware version 1.5.0 or newer. */
-	if (local->sta_fw_ver >= PRISM2_FW_VER(1,5,0))
-		local->wds_type |= HOSTAP_WDS_STANDARD_FRAME;
-	else {
-		printk(KERN_DEBUG "%s: defaulting to bogus WDS frame as a "
-		       "workaround for firmware bug in Host AP mode WDS\n",
-		       local->dev->name);
-	}
-
-	hostap_check_sta_fw_version(local->ap, local->sta_fw_ver);
-}
-
-
-static void hostap_passive_scan(struct timer_list *t)
-{
-	local_info_t *local = from_timer(local, t, passive_scan_timer);
-	struct net_device *dev = local->dev;
-	u16 chan;
-
-	if (local->passive_scan_interval <= 0)
-		return;
-
-	if (local->passive_scan_state == PASSIVE_SCAN_LISTEN) {
-		int max_tries = 16;
-
-		/* Even though host system does not really know when the WLAN
-		 * MAC is sending frames, try to avoid changing channels for
-		 * passive scanning when a host-generated frame is being
-		 * transmitted */
-		if (test_bit(HOSTAP_BITS_TRANSMIT, &local->bits)) {
-			printk(KERN_DEBUG "%s: passive scan detected pending "
-			       "TX - delaying\n", dev->name);
-			local->passive_scan_timer.expires = jiffies + HZ / 10;
-			add_timer(&local->passive_scan_timer);
-			return;
-		}
-
-		do {
-			local->passive_scan_channel++;
-			if (local->passive_scan_channel > 14)
-				local->passive_scan_channel = 1;
-			max_tries--;
-		} while (!(local->channel_mask &
-			   (1 << (local->passive_scan_channel - 1))) &&
-			 max_tries > 0);
-
-		if (max_tries == 0) {
-			printk(KERN_INFO "%s: no allowed passive scan channels"
-			       " found\n", dev->name);
-			return;
-		}
-
-		printk(KERN_DEBUG "%s: passive scan channel %d\n",
-		       dev->name, local->passive_scan_channel);
-		chan = local->passive_scan_channel;
-		local->passive_scan_state = PASSIVE_SCAN_WAIT;
-		local->passive_scan_timer.expires = jiffies + HZ / 10;
-	} else {
-		chan = local->channel;
-		local->passive_scan_state = PASSIVE_SCAN_LISTEN;
-		local->passive_scan_timer.expires = jiffies +
-			local->passive_scan_interval * HZ;
-	}
-
-	if (hfa384x_cmd_callback(dev, HFA384X_CMDCODE_TEST |
-				 (HFA384X_TEST_CHANGE_CHANNEL << 8),
-				 chan, NULL, 0))
-		printk(KERN_ERR "%s: passive scan channel set %d "
-		       "failed\n", dev->name, chan);
-
-	add_timer(&local->passive_scan_timer);
-}
-
-
-/* Called only as a scheduled task when communications quality values should
- * be updated. */
-static void handle_comms_qual_update(struct work_struct *work)
-{
-	local_info_t *local =
-		container_of(work, local_info_t, comms_qual_update);
-	prism2_update_comms_qual(local->dev);
-}
-
-
-/* Software watchdog - called as a timer. Hardware interrupt (Tick event) is
- * used to monitor that local->last_tick_timer is being updated. If not,
- * interrupt busy-loop is assumed and driver tries to recover by masking out
- * some events. */
-static void hostap_tick_timer(struct timer_list *t)
-{
-	static unsigned long last_inquire = 0;
-	local_info_t *local = from_timer(local, t, tick_timer);
-	local->last_tick_timer = jiffies;
-
-	/* Inquire CommTallies every 10 seconds to keep the statistics updated
-	 * more often during low load and when using 32-bit tallies. */
-	if ((!last_inquire || time_after(jiffies, last_inquire + 10 * HZ)) &&
-	    !local->hw_downloading && local->hw_ready &&
-	    !local->hw_resetting && local->dev_enabled) {
-		hfa384x_cmd_callback(local->dev, HFA384X_CMDCODE_INQUIRE,
-				     HFA384X_INFO_COMMTALLIES, NULL, 0);
-		last_inquire = jiffies;
-	}
-
-	if ((local->last_comms_qual_update == 0 ||
-	     time_after(jiffies, local->last_comms_qual_update + 10 * HZ)) &&
-	    (local->iw_mode == IW_MODE_INFRA ||
-	     local->iw_mode == IW_MODE_ADHOC)) {
-		schedule_work(&local->comms_qual_update);
-	}
-
-	local->tick_timer.expires = jiffies + 2 * HZ;
-	add_timer(&local->tick_timer);
-}
-
-
-#if !defined(PRISM2_NO_PROCFS_DEBUG) && defined(CONFIG_PROC_FS)
-static u16 hfa384x_read_reg(struct net_device *dev, u16 reg)
-{
-	return HFA384X_INW(reg);
-}
-
-static int prism2_registers_proc_show(struct seq_file *m, void *v)
-{
-	local_info_t *local = m->private;
-
-#define SHOW_REG(n) \
-  seq_printf(m, #n "=%04x\n", hfa384x_read_reg(local->dev, HFA384X_##n##_OFF))
-
-	SHOW_REG(CMD);
-	SHOW_REG(PARAM0);
-	SHOW_REG(PARAM1);
-	SHOW_REG(PARAM2);
-	SHOW_REG(STATUS);
-	SHOW_REG(RESP0);
-	SHOW_REG(RESP1);
-	SHOW_REG(RESP2);
-	SHOW_REG(INFOFID);
-	SHOW_REG(CONTROL);
-	SHOW_REG(SELECT0);
-	SHOW_REG(SELECT1);
-	SHOW_REG(OFFSET0);
-	SHOW_REG(OFFSET1);
-	SHOW_REG(RXFID);
-	SHOW_REG(ALLOCFID);
-	SHOW_REG(TXCOMPLFID);
-	SHOW_REG(SWSUPPORT0);
-	SHOW_REG(SWSUPPORT1);
-	SHOW_REG(SWSUPPORT2);
-	SHOW_REG(EVSTAT);
-	SHOW_REG(INTEN);
-	SHOW_REG(EVACK);
-	/* Do not read data registers, because they change the state of the
-	 * MAC (offset += 2) */
-	/* SHOW_REG(DATA0); */
-	/* SHOW_REG(DATA1); */
-	SHOW_REG(AUXPAGE);
-	SHOW_REG(AUXOFFSET);
-	/* SHOW_REG(AUXDATA); */
-#ifdef PRISM2_PCI
-	SHOW_REG(PCICOR);
-	SHOW_REG(PCIHCR);
-	SHOW_REG(PCI_M0_ADDRH);
-	SHOW_REG(PCI_M0_ADDRL);
-	SHOW_REG(PCI_M0_LEN);
-	SHOW_REG(PCI_M0_CTL);
-	SHOW_REG(PCI_STATUS);
-	SHOW_REG(PCI_M1_ADDRH);
-	SHOW_REG(PCI_M1_ADDRL);
-	SHOW_REG(PCI_M1_LEN);
-	SHOW_REG(PCI_M1_CTL);
-#endif /* PRISM2_PCI */
-
-	return 0;
-}
-#endif
-
-struct set_tim_data {
-	struct list_head list;
-	int aid;
-	int set;
-};
-
-static int prism2_set_tim(struct net_device *dev, int aid, int set)
-{
-	struct list_head *ptr;
-	struct set_tim_data *new_entry;
-	struct hostap_interface *iface;
-	local_info_t *local;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	new_entry = kzalloc(sizeof(*new_entry), GFP_ATOMIC);
-	if (new_entry == NULL)
-		return -ENOMEM;
-
-	new_entry->aid = aid;
-	new_entry->set = set;
-
-	spin_lock_bh(&local->set_tim_lock);
-	list_for_each(ptr, &local->set_tim_list) {
-		struct set_tim_data *entry =
-			list_entry(ptr, struct set_tim_data, list);
-		if (entry->aid == aid) {
-			PDEBUG(DEBUG_PS2, "%s: prism2_set_tim: aid=%d "
-			       "set=%d ==> %d\n",
-			       local->dev->name, aid, entry->set, set);
-			entry->set = set;
-			kfree(new_entry);
-			new_entry = NULL;
-			break;
-		}
-	}
-	if (new_entry)
-		list_add_tail(&new_entry->list, &local->set_tim_list);
-	spin_unlock_bh(&local->set_tim_lock);
-
-	schedule_work(&local->set_tim_queue);
-
-	return 0;
-}
-
-
-static void handle_set_tim_queue(struct work_struct *work)
-{
-	local_info_t *local = container_of(work, local_info_t, set_tim_queue);
-	struct set_tim_data *entry;
-	u16 val;
-
-	for (;;) {
-		entry = NULL;
-		spin_lock_bh(&local->set_tim_lock);
-		if (!list_empty(&local->set_tim_list)) {
-			entry = list_entry(local->set_tim_list.next,
-					   struct set_tim_data, list);
-			list_del(&entry->list);
-		}
-		spin_unlock_bh(&local->set_tim_lock);
-		if (!entry)
-			break;
-
-		PDEBUG(DEBUG_PS2, "%s: handle_set_tim_queue: aid=%d set=%d\n",
-		       local->dev->name, entry->aid, entry->set);
-
-		val = entry->aid;
-		if (entry->set)
-			val |= 0x8000;
-		if (hostap_set_word(local->dev, HFA384X_RID_CNFTIMCTRL, val)) {
-			printk(KERN_DEBUG "%s: set_tim failed (aid=%d "
-			       "set=%d)\n",
-			       local->dev->name, entry->aid, entry->set);
-		}
-
-		kfree(entry);
-	}
-}
-
-
-static void prism2_clear_set_tim_queue(local_info_t *local)
-{
-	struct list_head *ptr, *n;
-
-	list_for_each_safe(ptr, n, &local->set_tim_list) {
-		struct set_tim_data *entry;
-		entry = list_entry(ptr, struct set_tim_data, list);
-		list_del(&entry->list);
-		kfree(entry);
-	}
-}
-
-
-/*
- * HostAP uses two layers of net devices, where the inner
- * layer gets called all the time from the outer layer.
- * This is a natural nesting, which needs a split lock type.
- */
-static struct lock_class_key hostap_netdev_xmit_lock_key;
-static struct lock_class_key hostap_netdev_addr_lock_key;
-
-static void prism2_set_lockdep_class_one(struct net_device *dev,
-					 struct netdev_queue *txq,
-					 void *_unused)
-{
-	lockdep_set_class(&txq->_xmit_lock,
-			  &hostap_netdev_xmit_lock_key);
-}
-
-static void prism2_set_lockdep_class(struct net_device *dev)
-{
-	lockdep_set_class(&dev->addr_list_lock,
-			  &hostap_netdev_addr_lock_key);
-	netdev_for_each_tx_queue(dev, prism2_set_lockdep_class_one, NULL);
-}
-
-static struct net_device *
-prism2_init_local_data(struct prism2_helper_functions *funcs, int card_idx,
-		       struct device *sdev)
-{
-	struct net_device *dev;
-	struct hostap_interface *iface;
-	struct local_info *local;
-	int len, i, ret;
-
-	if (funcs == NULL)
-		return NULL;
-
-	len = strlen(dev_template);
-	if (len >= IFNAMSIZ || strstr(dev_template, "%d") == NULL) {
-		printk(KERN_WARNING "hostap: Invalid dev_template='%s'\n",
-		       dev_template);
-		return NULL;
-	}
-
-	len = sizeof(struct hostap_interface) +
-		3 + sizeof(struct local_info) +
-		3 + sizeof(struct ap_data);
-
-	dev = alloc_etherdev(len);
-	if (dev == NULL)
-		return NULL;
-
-	iface = netdev_priv(dev);
-	local = (struct local_info *) ((((long) (iface + 1)) + 3) & ~3);
-	local->ap = (struct ap_data *) ((((long) (local + 1)) + 3) & ~3);
-	local->dev = iface->dev = dev;
-	iface->local = local;
-	iface->type = HOSTAP_INTERFACE_MASTER;
-	INIT_LIST_HEAD(&local->hostap_interfaces);
-
-	local->hw_module = THIS_MODULE;
-
-#ifdef PRISM2_IO_DEBUG
-	local->io_debug_enabled = 1;
-#endif /* PRISM2_IO_DEBUG */
-
-	local->func = funcs;
-	local->func->cmd = hfa384x_cmd;
-	local->func->read_regs = hfa384x_read_regs;
-	local->func->get_rid = hfa384x_get_rid;
-	local->func->set_rid = hfa384x_set_rid;
-	local->func->hw_enable = prism2_hw_enable;
-	local->func->hw_config = prism2_hw_config;
-	local->func->hw_reset = prism2_hw_reset;
-	local->func->hw_shutdown = prism2_hw_shutdown;
-	local->func->reset_port = prism2_reset_port;
-	local->func->schedule_reset = prism2_schedule_reset;
-#ifdef PRISM2_DOWNLOAD_SUPPORT
-	local->func->read_aux_proc_ops = &prism2_download_aux_dump_proc_ops;
-	local->func->download = prism2_download;
-#endif /* PRISM2_DOWNLOAD_SUPPORT */
-	local->func->tx = prism2_tx_80211;
-	local->func->set_tim = prism2_set_tim;
-	local->func->need_tx_headroom = 0; /* no need to add txdesc in
-					    * skb->data (FIX: maybe for DMA bus
-					    * mastering? */
-
-	local->mtu = mtu;
-
-	rwlock_init(&local->iface_lock);
-	spin_lock_init(&local->txfidlock);
-	spin_lock_init(&local->cmdlock);
-	spin_lock_init(&local->baplock);
-	spin_lock_init(&local->lock);
-	spin_lock_init(&local->irq_init_lock);
-	mutex_init(&local->rid_bap_mtx);
-
-	if (card_idx < 0 || card_idx >= MAX_PARM_DEVICES)
-		card_idx = 0;
-	local->card_idx = card_idx;
-
-	len = strlen(essid);
-	memcpy(local->essid, essid,
-	       len > MAX_SSID_LEN ? MAX_SSID_LEN : len);
-	local->essid[MAX_SSID_LEN] = '\0';
-	i = GET_INT_PARM(iw_mode, card_idx);
-	if ((i >= IW_MODE_ADHOC && i <= IW_MODE_REPEAT) ||
-	    i == IW_MODE_MONITOR) {
-		local->iw_mode = i;
-	} else {
-		printk(KERN_WARNING "prism2: Unknown iw_mode %d; using "
-		       "IW_MODE_MASTER\n", i);
-		local->iw_mode = IW_MODE_MASTER;
-	}
-	local->channel = GET_INT_PARM(channel, card_idx);
-	local->beacon_int = GET_INT_PARM(beacon_int, card_idx);
-	local->dtim_period = GET_INT_PARM(dtim_period, card_idx);
-	local->wds_max_connections = 16;
-	local->tx_control = HFA384X_TX_CTRL_FLAGS;
-	local->manual_retry_count = -1;
-	local->rts_threshold = 2347;
-	local->fragm_threshold = 2346;
-	local->rssi_to_dBm = 100; /* default; to be overriden by
-				   * cnfDbmAdjust, if available */
-	local->auth_algs = PRISM2_AUTH_OPEN | PRISM2_AUTH_SHARED_KEY;
-	local->sram_type = -1;
-	local->scan_channel_mask = 0xffff;
-	local->monitor_type = PRISM2_MONITOR_RADIOTAP;
-
-	/* Initialize task queue structures */
-	INIT_WORK(&local->reset_queue, handle_reset_queue);
-	INIT_WORK(&local->set_multicast_list_queue,
-		  hostap_set_multicast_list_queue);
-
-	INIT_WORK(&local->set_tim_queue, handle_set_tim_queue);
-	INIT_LIST_HEAD(&local->set_tim_list);
-	spin_lock_init(&local->set_tim_lock);
-
-	INIT_WORK(&local->comms_qual_update, handle_comms_qual_update);
-
-	/* Initialize tasklets for handling hardware IRQ related operations
-	 * outside hw IRQ handler */
-	tasklet_setup(&local->bap_tasklet, hostap_bap_tasklet);
-	tasklet_setup(&local->info_tasklet, hostap_info_tasklet);
-	hostap_info_init(local);
-
-	tasklet_setup(&local->rx_tasklet, hostap_rx_tasklet);
-	skb_queue_head_init(&local->rx_list);
-
-	tasklet_setup(&local->sta_tx_exc_tasklet,
-			    hostap_sta_tx_exc_tasklet);
-	skb_queue_head_init(&local->sta_tx_exc_list);
-
-	INIT_LIST_HEAD(&local->cmd_queue);
-	init_waitqueue_head(&local->hostscan_wq);
-
-	lib80211_crypt_info_init(&local->crypt_info, dev->name, &local->lock);
-
-	timer_setup(&local->passive_scan_timer, hostap_passive_scan, 0);
-	timer_setup(&local->tick_timer, hostap_tick_timer, 0);
-	local->tick_timer.expires = jiffies + 2 * HZ;
-	add_timer(&local->tick_timer);
-
-	INIT_LIST_HEAD(&local->bss_list);
-
-	hostap_setup_dev(dev, local, HOSTAP_INTERFACE_MASTER);
-
-	dev->type = ARPHRD_IEEE80211;
-	dev->header_ops = &hostap_80211_ops;
-
-	rtnl_lock();
-	ret = dev_alloc_name(dev, "wifi%d");
-	SET_NETDEV_DEV(dev, sdev);
-	if (ret >= 0)
-		ret = register_netdevice(dev);
-
-	prism2_set_lockdep_class(dev);
-	rtnl_unlock();
-	if (ret < 0) {
-		printk(KERN_WARNING "%s: register netdevice failed!\n",
-		       dev_info);
-		goto fail;
-	}
-	printk(KERN_INFO "%s: Registered netdevice %s\n", dev_info, dev->name);
-
-	hostap_init_data(local);
-	return dev;
-
- fail:
-	free_netdev(dev);
-	return NULL;
-}
-
-
-static int hostap_hw_ready(struct net_device *dev)
-{
-	struct hostap_interface *iface;
-	struct local_info *local;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-	local->ddev = hostap_add_interface(local, HOSTAP_INTERFACE_MAIN, 0,
-					   "", dev_template);
-
-	if (local->ddev) {
-		if (local->iw_mode == IW_MODE_INFRA ||
-		    local->iw_mode == IW_MODE_ADHOC) {
-			netif_carrier_off(local->dev);
-			netif_carrier_off(local->ddev);
-		}
-		hostap_init_proc(local);
-#ifndef PRISM2_NO_PROCFS_DEBUG
-		proc_create_single_data("registers", 0, local->proc,
-				 prism2_registers_proc_show, local);
-#endif /* PRISM2_NO_PROCFS_DEBUG */
-		hostap_init_ap_proc(local);
-		return 0;
-	}
-
-	return -1;
-}
-
-
-static void prism2_free_local_data(struct net_device *dev)
-{
-	struct hostap_tx_callback_info *tx_cb, *tx_cb_prev;
-	int i;
-	struct hostap_interface *iface;
-	struct local_info *local;
-	struct list_head *ptr, *n;
-
-	if (dev == NULL)
-		return;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	/* Unregister all netdevs before freeing local data. */
-	list_for_each_safe(ptr, n, &local->hostap_interfaces) {
-		iface = list_entry(ptr, struct hostap_interface, list);
-		if (iface->type == HOSTAP_INTERFACE_MASTER) {
-			/* special handling for this interface below */
-			continue;
-		}
-		hostap_remove_interface(iface->dev, 0, 1);
-	}
-
-	unregister_netdev(local->dev);
-
-	flush_work(&local->reset_queue);
-	flush_work(&local->set_multicast_list_queue);
-	flush_work(&local->set_tim_queue);
-#ifndef PRISM2_NO_STATION_MODES
-	flush_work(&local->info_queue);
-#endif
-	flush_work(&local->comms_qual_update);
-
-	lib80211_crypt_info_free(&local->crypt_info);
-
-	if (timer_pending(&local->passive_scan_timer))
-		del_timer(&local->passive_scan_timer);
-
-	if (timer_pending(&local->tick_timer))
-		del_timer(&local->tick_timer);
-
-	prism2_clear_cmd_queue(local);
-
-	skb_queue_purge(&local->info_list);
-	skb_queue_purge(&local->rx_list);
-	skb_queue_purge(&local->sta_tx_exc_list);
-
-	if (local->dev_enabled)
-		prism2_callback(local, PRISM2_CALLBACK_DISABLE);
-
-	if (local->ap != NULL)
-		hostap_free_data(local->ap);
-
-#ifndef PRISM2_NO_PROCFS_DEBUG
-	if (local->proc != NULL)
-		remove_proc_entry("registers", local->proc);
-#endif /* PRISM2_NO_PROCFS_DEBUG */
-	hostap_remove_proc(local);
-
-	tx_cb = local->tx_callback;
-	while (tx_cb != NULL) {
-		tx_cb_prev = tx_cb;
-		tx_cb = tx_cb->next;
-		kfree(tx_cb_prev);
-	}
-
-	hostap_set_hostapd(local, 0, 0);
-	hostap_set_hostapd_sta(local, 0, 0);
-
-	for (i = 0; i < PRISM2_FRAG_CACHE_LEN; i++) {
-		if (local->frag_cache[i].skb != NULL)
-			dev_kfree_skb(local->frag_cache[i].skb);
-	}
-
-#ifdef PRISM2_DOWNLOAD_SUPPORT
-	prism2_download_free_data(local->dl_pri);
-	prism2_download_free_data(local->dl_sec);
-#endif /* PRISM2_DOWNLOAD_SUPPORT */
-
-	prism2_clear_set_tim_queue(local);
-
-	list_for_each_safe(ptr, n, &local->bss_list) {
-		struct hostap_bss_info *bss =
-			list_entry(ptr, struct hostap_bss_info, list);
-		kfree(bss);
-	}
-
-	kfree(local->pda);
-	kfree(local->last_scan_results);
-	kfree(local->generic_elem);
-
-	free_netdev(local->dev);
-}
-
-
-#if defined(PRISM2_PCI) || defined(PRISM2_PCCARD)
-static void __maybe_unused prism2_suspend(struct net_device *dev)
-{
-	struct hostap_interface *iface;
-	struct local_info *local;
-	union iwreq_data wrqu;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	/* Send disconnect event, e.g., to trigger reassociation after resume
-	 * if wpa_supplicant is used. */
-	memset(&wrqu, 0, sizeof(wrqu));
-	wrqu.ap_addr.sa_family = ARPHRD_ETHER;
-	wireless_send_event(local->dev, SIOCGIWAP, &wrqu, NULL);
-
-	/* Disable hardware and firmware */
-	prism2_hw_shutdown(dev, 0);
-}
-#endif /* PRISM2_PCI || PRISM2_PCCARD */
-
-
-/* These might at some point be compiled separately and used as separate
- * kernel modules or linked into one */
-#ifdef PRISM2_DOWNLOAD_SUPPORT
-#include "hostap_download.c"
-#endif /* PRISM2_DOWNLOAD_SUPPORT */
-
-#ifdef PRISM2_CALLBACK
-/* External hostap_callback.c file can be used to, e.g., blink activity led.
- * This can use platform specific code and must define prism2_callback()
- * function (if PRISM2_CALLBACK is not defined, these function calls are not
- * used. */
-#include "hostap_callback.c"
-#endif /* PRISM2_CALLBACK */
diff --git a/drivers/net/wireless/intersil/hostap/hostap_info.c b/drivers/net/wireless/intersil/hostap/hostap_info.c
deleted file mode 100644
index da8c30f10d92..000000000000
--- a/drivers/net/wireless/intersil/hostap/hostap_info.c
+++ /dev/null
@@ -1,509 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Host AP driver Info Frame processing (part of hostap.o module) */
-
-#include <linux/if_arp.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/export.h>
-#include <linux/etherdevice.h>
-#include "hostap_wlan.h"
-#include "hostap.h"
-#include "hostap_ap.h"
-
-/* Called only as a tasklet (software IRQ) */
-static void prism2_info_commtallies16(local_info_t *local, unsigned char *buf,
-				      int left)
-{
-	struct hfa384x_comm_tallies *tallies;
-
-	if (left < sizeof(struct hfa384x_comm_tallies)) {
-		printk(KERN_DEBUG "%s: too short (len=%d) commtallies "
-		       "info frame\n", local->dev->name, left);
-		return;
-	}
-
-	tallies = (struct hfa384x_comm_tallies *) buf;
-#define ADD_COMM_TALLIES(name) \
-local->comm_tallies.name += le16_to_cpu(tallies->name)
-	ADD_COMM_TALLIES(tx_unicast_frames);
-	ADD_COMM_TALLIES(tx_multicast_frames);
-	ADD_COMM_TALLIES(tx_fragments);
-	ADD_COMM_TALLIES(tx_unicast_octets);
-	ADD_COMM_TALLIES(tx_multicast_octets);
-	ADD_COMM_TALLIES(tx_deferred_transmissions);
-	ADD_COMM_TALLIES(tx_single_retry_frames);
-	ADD_COMM_TALLIES(tx_multiple_retry_frames);
-	ADD_COMM_TALLIES(tx_retry_limit_exceeded);
-	ADD_COMM_TALLIES(tx_discards);
-	ADD_COMM_TALLIES(rx_unicast_frames);
-	ADD_COMM_TALLIES(rx_multicast_frames);
-	ADD_COMM_TALLIES(rx_fragments);
-	ADD_COMM_TALLIES(rx_unicast_octets);
-	ADD_COMM_TALLIES(rx_multicast_octets);
-	ADD_COMM_TALLIES(rx_fcs_errors);
-	ADD_COMM_TALLIES(rx_discards_no_buffer);
-	ADD_COMM_TALLIES(tx_discards_wrong_sa);
-	ADD_COMM_TALLIES(rx_discards_wep_undecryptable);
-	ADD_COMM_TALLIES(rx_message_in_msg_fragments);
-	ADD_COMM_TALLIES(rx_message_in_bad_msg_fragments);
-#undef ADD_COMM_TALLIES
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static void prism2_info_commtallies32(local_info_t *local, unsigned char *buf,
-				      int left)
-{
-	struct hfa384x_comm_tallies32 *tallies;
-
-	if (left < sizeof(struct hfa384x_comm_tallies32)) {
-		printk(KERN_DEBUG "%s: too short (len=%d) commtallies32 "
-		       "info frame\n", local->dev->name, left);
-		return;
-	}
-
-	tallies = (struct hfa384x_comm_tallies32 *) buf;
-#define ADD_COMM_TALLIES(name) \
-local->comm_tallies.name += le32_to_cpu(tallies->name)
-	ADD_COMM_TALLIES(tx_unicast_frames);
-	ADD_COMM_TALLIES(tx_multicast_frames);
-	ADD_COMM_TALLIES(tx_fragments);
-	ADD_COMM_TALLIES(tx_unicast_octets);
-	ADD_COMM_TALLIES(tx_multicast_octets);
-	ADD_COMM_TALLIES(tx_deferred_transmissions);
-	ADD_COMM_TALLIES(tx_single_retry_frames);
-	ADD_COMM_TALLIES(tx_multiple_retry_frames);
-	ADD_COMM_TALLIES(tx_retry_limit_exceeded);
-	ADD_COMM_TALLIES(tx_discards);
-	ADD_COMM_TALLIES(rx_unicast_frames);
-	ADD_COMM_TALLIES(rx_multicast_frames);
-	ADD_COMM_TALLIES(rx_fragments);
-	ADD_COMM_TALLIES(rx_unicast_octets);
-	ADD_COMM_TALLIES(rx_multicast_octets);
-	ADD_COMM_TALLIES(rx_fcs_errors);
-	ADD_COMM_TALLIES(rx_discards_no_buffer);
-	ADD_COMM_TALLIES(tx_discards_wrong_sa);
-	ADD_COMM_TALLIES(rx_discards_wep_undecryptable);
-	ADD_COMM_TALLIES(rx_message_in_msg_fragments);
-	ADD_COMM_TALLIES(rx_message_in_bad_msg_fragments);
-#undef ADD_COMM_TALLIES
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static void prism2_info_commtallies(local_info_t *local, unsigned char *buf,
-				    int left)
-{
-	if (local->tallies32)
-		prism2_info_commtallies32(local, buf, left);
-	else
-		prism2_info_commtallies16(local, buf, left);
-}
-
-
-#ifndef PRISM2_NO_STATION_MODES
-#ifndef PRISM2_NO_DEBUG
-static const char* hfa384x_linkstatus_str(u16 linkstatus)
-{
-	switch (linkstatus) {
-	case HFA384X_LINKSTATUS_CONNECTED:
-		return "Connected";
-	case HFA384X_LINKSTATUS_DISCONNECTED:
-		return "Disconnected";
-	case HFA384X_LINKSTATUS_AP_CHANGE:
-		return "Access point change";
-	case HFA384X_LINKSTATUS_AP_OUT_OF_RANGE:
-		return "Access point out of range";
-	case HFA384X_LINKSTATUS_AP_IN_RANGE:
-		return "Access point in range";
-	case HFA384X_LINKSTATUS_ASSOC_FAILED:
-		return "Association failed";
-	default:
-		return "Unknown";
-	}
-}
-#endif /* PRISM2_NO_DEBUG */
-
-
-/* Called only as a tasklet (software IRQ) */
-static void prism2_info_linkstatus(local_info_t *local, unsigned char *buf,
-				    int left)
-{
-	u16 val;
-	int non_sta_mode;
-
-	/* Alloc new JoinRequests to occur since LinkStatus for the previous
-	 * has been received */
-	local->last_join_time = 0;
-
-	if (left != 2) {
-		printk(KERN_DEBUG "%s: invalid linkstatus info frame "
-		       "length %d\n", local->dev->name, left);
-		return;
-	}
-
-	non_sta_mode = local->iw_mode == IW_MODE_MASTER ||
-		local->iw_mode == IW_MODE_REPEAT ||
-		local->iw_mode == IW_MODE_MONITOR;
-
-	val = buf[0] | (buf[1] << 8);
-	if (!non_sta_mode || val != HFA384X_LINKSTATUS_DISCONNECTED) {
-		PDEBUG(DEBUG_EXTRA, "%s: LinkStatus=%d (%s)\n",
-		       local->dev->name, val, hfa384x_linkstatus_str(val));
-	}
-
-	if (non_sta_mode) {
-		netif_carrier_on(local->dev);
-		netif_carrier_on(local->ddev);
-		return;
-	}
-
-	/* Get current BSSID later in scheduled task */
-	set_bit(PRISM2_INFO_PENDING_LINKSTATUS, &local->pending_info);
-	local->prev_link_status = val;
-	schedule_work(&local->info_queue);
-}
-
-
-static void prism2_host_roaming(local_info_t *local)
-{
-	struct hfa384x_join_request req;
-	struct net_device *dev = local->dev;
-	struct hfa384x_hostscan_result *selected, *entry;
-	int i;
-	unsigned long flags;
-
-	if (local->last_join_time &&
-	    time_before(jiffies, local->last_join_time + 10 * HZ)) {
-		PDEBUG(DEBUG_EXTRA, "%s: last join request has not yet been "
-		       "completed - waiting for it before issuing new one\n",
-		       dev->name);
-		return;
-	}
-
-	/* ScanResults are sorted: first ESS results in decreasing signal
-	 * quality then IBSS results in similar order.
-	 * Trivial roaming policy: just select the first entry.
-	 * This could probably be improved by adding hysteresis to limit
-	 * number of handoffs, etc.
-	 *
-	 * Could do periodic RID_SCANREQUEST or Inquire F101 to get new
-	 * ScanResults */
-	spin_lock_irqsave(&local->lock, flags);
-	if (local->last_scan_results == NULL ||
-	    local->last_scan_results_count == 0) {
-		spin_unlock_irqrestore(&local->lock, flags);
-		PDEBUG(DEBUG_EXTRA, "%s: no scan results for host roaming\n",
-		       dev->name);
-		return;
-	}
-
-	selected = &local->last_scan_results[0];
-
-	if (local->preferred_ap[0] || local->preferred_ap[1] ||
-	    local->preferred_ap[2] || local->preferred_ap[3] ||
-	    local->preferred_ap[4] || local->preferred_ap[5]) {
-		/* Try to find preferred AP */
-		PDEBUG(DEBUG_EXTRA, "%s: Preferred AP BSSID %pM\n",
-		       dev->name, local->preferred_ap);
-		for (i = 0; i < local->last_scan_results_count; i++) {
-			entry = &local->last_scan_results[i];
-			if (memcmp(local->preferred_ap, entry->bssid, 6) == 0)
-			{
-				PDEBUG(DEBUG_EXTRA, "%s: using preferred AP "
-				       "selection\n", dev->name);
-				selected = entry;
-				break;
-			}
-		}
-	}
-
-	memcpy(req.bssid, selected->bssid, ETH_ALEN);
-	req.channel = selected->chid;
-	spin_unlock_irqrestore(&local->lock, flags);
-
-	PDEBUG(DEBUG_EXTRA, "%s: JoinRequest: BSSID=%pM"
-	       " channel=%d\n",
-	       dev->name, req.bssid, le16_to_cpu(req.channel));
-	if (local->func->set_rid(dev, HFA384X_RID_JOINREQUEST, &req,
-				 sizeof(req))) {
-		printk(KERN_DEBUG "%s: JoinRequest failed\n", dev->name);
-	}
-	local->last_join_time = jiffies;
-}
-
-
-static void hostap_report_scan_complete(local_info_t *local)
-{
-	union iwreq_data wrqu;
-
-	/* Inform user space about new scan results (just empty event,
-	 * SIOCGIWSCAN can be used to fetch data */
-	wrqu.data.length = 0;
-	wrqu.data.flags = 0;
-	wireless_send_event(local->dev, SIOCGIWSCAN, &wrqu, NULL);
-
-	/* Allow SIOCGIWSCAN handling to occur since we have received
-	 * scanning result */
-	local->scan_timestamp = 0;
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static void prism2_info_scanresults(local_info_t *local, unsigned char *buf,
-				    int left)
-{
-	u16 *pos;
-	int new_count, i;
-	unsigned long flags;
-	struct hfa384x_scan_result *res;
-	struct hfa384x_hostscan_result *results, *prev;
-
-	if (left < 4) {
-		printk(KERN_DEBUG "%s: invalid scanresult info frame "
-		       "length %d\n", local->dev->name, left);
-		return;
-	}
-
-	pos = (u16 *) buf;
-	pos++;
-	pos++;
-	left -= 4;
-
-	new_count = left / sizeof(struct hfa384x_scan_result);
-	results = kmalloc_array(new_count,
-				sizeof(struct hfa384x_hostscan_result),
-				GFP_ATOMIC);
-	if (results == NULL)
-		return;
-
-	/* Convert to hostscan result format. */
-	res = (struct hfa384x_scan_result *) pos;
-	for (i = 0; i < new_count; i++) {
-		memcpy(&results[i], &res[i],
-		       sizeof(struct hfa384x_scan_result));
-		results[i].atim = 0;
-	}
-
-	spin_lock_irqsave(&local->lock, flags);
-	local->last_scan_type = PRISM2_SCAN;
-	prev = local->last_scan_results;
-	local->last_scan_results = results;
-	local->last_scan_results_count = new_count;
-	spin_unlock_irqrestore(&local->lock, flags);
-	kfree(prev);
-
-	hostap_report_scan_complete(local);
-
-	/* Perform rest of ScanResults handling later in scheduled task */
-	set_bit(PRISM2_INFO_PENDING_SCANRESULTS, &local->pending_info);
-	schedule_work(&local->info_queue);
-}
-
-
-/* Called only as a tasklet (software IRQ) */
-static void prism2_info_hostscanresults(local_info_t *local,
-					unsigned char *buf, int left)
-{
-	int i, result_size, copy_len, new_count;
-	struct hfa384x_hostscan_result *results, *prev;
-	unsigned long flags;
-	__le16 *pos;
-	u8 *ptr;
-
-	wake_up_interruptible(&local->hostscan_wq);
-
-	if (left < 4) {
-		printk(KERN_DEBUG "%s: invalid hostscanresult info frame "
-		       "length %d\n", local->dev->name, left);
-		return;
-	}
-
-	pos = (__le16 *) buf;
-	copy_len = result_size = le16_to_cpu(*pos);
-	if (result_size == 0) {
-		printk(KERN_DEBUG "%s: invalid result_size (0) in "
-		       "hostscanresults\n", local->dev->name);
-		return;
-	}
-	if (copy_len > sizeof(struct hfa384x_hostscan_result))
-		copy_len = sizeof(struct hfa384x_hostscan_result);
-
-	pos++;
-	pos++;
-	left -= 4;
-	ptr = (u8 *) pos;
-
-	new_count = left / result_size;
-	results = kcalloc(new_count, sizeof(struct hfa384x_hostscan_result),
-			  GFP_ATOMIC);
-	if (results == NULL)
-		return;
-
-	for (i = 0; i < new_count; i++) {
-		memcpy(&results[i], ptr, copy_len);
-		ptr += result_size;
-		left -= result_size;
-	}
-
-	if (left) {
-		printk(KERN_DEBUG "%s: short HostScan result entry (%d/%d)\n",
-		       local->dev->name, left, result_size);
-	}
-
-	spin_lock_irqsave(&local->lock, flags);
-	local->last_scan_type = PRISM2_HOSTSCAN;
-	prev = local->last_scan_results;
-	local->last_scan_results = results;
-	local->last_scan_results_count = new_count;
-	spin_unlock_irqrestore(&local->lock, flags);
-	kfree(prev);
-
-	hostap_report_scan_complete(local);
-}
-#endif /* PRISM2_NO_STATION_MODES */
-
-
-/* Called only as a tasklet (software IRQ) */
-void hostap_info_process(local_info_t *local, struct sk_buff *skb)
-{
-	struct hfa384x_info_frame *info;
-	unsigned char *buf;
-	int left;
-#ifndef PRISM2_NO_DEBUG
-	int i;
-#endif /* PRISM2_NO_DEBUG */
-
-	info = (struct hfa384x_info_frame *) skb->data;
-	buf = skb->data + sizeof(*info);
-	left = skb->len - sizeof(*info);
-
-	switch (le16_to_cpu(info->type)) {
-	case HFA384X_INFO_COMMTALLIES:
-		prism2_info_commtallies(local, buf, left);
-		break;
-
-#ifndef PRISM2_NO_STATION_MODES
-	case HFA384X_INFO_LINKSTATUS:
-		prism2_info_linkstatus(local, buf, left);
-		break;
-
-	case HFA384X_INFO_SCANRESULTS:
-		prism2_info_scanresults(local, buf, left);
-		break;
-
-	case HFA384X_INFO_HOSTSCANRESULTS:
-		prism2_info_hostscanresults(local, buf, left);
-		break;
-#endif /* PRISM2_NO_STATION_MODES */
-
-#ifndef PRISM2_NO_DEBUG
-	default:
-		PDEBUG(DEBUG_EXTRA, "%s: INFO - len=%d type=0x%04x\n",
-		       local->dev->name, le16_to_cpu(info->len),
-		       le16_to_cpu(info->type));
-		PDEBUG(DEBUG_EXTRA, "Unknown info frame:");
-		for (i = 0; i < (left < 100 ? left : 100); i++)
-			PDEBUG2(DEBUG_EXTRA, " %02x", buf[i]);
-		PDEBUG2(DEBUG_EXTRA, "\n");
-		break;
-#endif /* PRISM2_NO_DEBUG */
-	}
-}
-
-
-#ifndef PRISM2_NO_STATION_MODES
-static void handle_info_queue_linkstatus(local_info_t *local)
-{
-	int val = local->prev_link_status;
-	int connected;
-	union iwreq_data wrqu;
-
-	connected =
-		val == HFA384X_LINKSTATUS_CONNECTED ||
-		val == HFA384X_LINKSTATUS_AP_CHANGE ||
-		val == HFA384X_LINKSTATUS_AP_IN_RANGE;
-
-	if (local->func->get_rid(local->dev, HFA384X_RID_CURRENTBSSID,
-				 local->bssid, ETH_ALEN, 1) < 0) {
-		printk(KERN_DEBUG "%s: could not read CURRENTBSSID after "
-		       "LinkStatus event\n", local->dev->name);
-	} else {
-		PDEBUG(DEBUG_EXTRA, "%s: LinkStatus: BSSID=%pM\n",
-		       local->dev->name,
-		       (unsigned char *) local->bssid);
-		if (local->wds_type & HOSTAP_WDS_AP_CLIENT)
-			hostap_add_sta(local->ap, local->bssid);
-	}
-
-	/* Get BSSID if we have a valid AP address */
-	if (connected) {
-		netif_carrier_on(local->dev);
-		netif_carrier_on(local->ddev);
-		memcpy(wrqu.ap_addr.sa_data, local->bssid, ETH_ALEN);
-	} else {
-		netif_carrier_off(local->dev);
-		netif_carrier_off(local->ddev);
-		eth_zero_addr(wrqu.ap_addr.sa_data);
-	}
-	wrqu.ap_addr.sa_family = ARPHRD_ETHER;
-
-	/*
-	 * Filter out sequential disconnect events in order not to cause a
-	 * flood of SIOCGIWAP events that have a race condition with EAPOL
-	 * frames and can confuse wpa_supplicant about the current association
-	 * status.
-	 */
-	if (connected || local->prev_linkstatus_connected)
-		wireless_send_event(local->dev, SIOCGIWAP, &wrqu, NULL);
-	local->prev_linkstatus_connected = connected;
-}
-
-
-static void handle_info_queue_scanresults(local_info_t *local)
-{
-	if (local->host_roaming == 1 && local->iw_mode == IW_MODE_INFRA)
-		prism2_host_roaming(local);
-
-	if (local->host_roaming == 2 && local->iw_mode == IW_MODE_INFRA &&
-	    !is_zero_ether_addr(local->preferred_ap)) {
-		/*
-		 * Firmware seems to be getting into odd state in host_roaming
-		 * mode 2 when hostscan is used without join command, so try
-		 * to fix this by re-joining the current AP. This does not
-		 * actually trigger a new association if the current AP is
-		 * still in the scan results.
-		 */
-		prism2_host_roaming(local);
-	}
-}
-
-
-/* Called only as scheduled task after receiving info frames (used to avoid
- * pending too much time in HW IRQ handler). */
-static void handle_info_queue(struct work_struct *work)
-{
-	local_info_t *local = container_of(work, local_info_t, info_queue);
-
-	if (test_and_clear_bit(PRISM2_INFO_PENDING_LINKSTATUS,
-			       &local->pending_info))
-		handle_info_queue_linkstatus(local);
-
-	if (test_and_clear_bit(PRISM2_INFO_PENDING_SCANRESULTS,
-			       &local->pending_info))
-		handle_info_queue_scanresults(local);
-}
-#endif /* PRISM2_NO_STATION_MODES */
-
-
-void hostap_info_init(local_info_t *local)
-{
-	skb_queue_head_init(&local->info_list);
-#ifndef PRISM2_NO_STATION_MODES
-	INIT_WORK(&local->info_queue, handle_info_queue);
-#endif /* PRISM2_NO_STATION_MODES */
-}
-
-
-EXPORT_SYMBOL(hostap_info_init);
-EXPORT_SYMBOL(hostap_info_process);
diff --git a/drivers/net/wireless/intersil/hostap/hostap_ioctl.c b/drivers/net/wireless/intersil/hostap/hostap_ioctl.c
deleted file mode 100644
index 26162f92e3c3..000000000000
--- a/drivers/net/wireless/intersil/hostap/hostap_ioctl.c
+++ /dev/null
@@ -1,3847 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* ioctl() (mostly Linux Wireless Extensions) routines for Host AP driver */
-
-#include <linux/slab.h>
-#include <linux/types.h>
-#include <linux/sched/signal.h>
-#include <linux/ethtool.h>
-#include <linux/if_arp.h>
-#include <linux/module.h>
-#include <linux/etherdevice.h>
-#include <net/lib80211.h>
-
-#include "hostap_wlan.h"
-#include "hostap.h"
-#include "hostap_ap.h"
-
-static struct iw_statistics *hostap_get_wireless_stats(struct net_device *dev)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	struct iw_statistics *wstats;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	/* Why are we doing that ? Jean II */
-	if (iface->type != HOSTAP_INTERFACE_MAIN)
-		return NULL;
-
-	wstats = &local->wstats;
-
-	wstats->status = 0;
-	wstats->discard.code =
-		local->comm_tallies.rx_discards_wep_undecryptable;
-	wstats->discard.misc =
-		local->comm_tallies.rx_fcs_errors +
-		local->comm_tallies.rx_discards_no_buffer +
-		local->comm_tallies.tx_discards_wrong_sa;
-
-	wstats->discard.retries =
-		local->comm_tallies.tx_retry_limit_exceeded;
-	wstats->discard.fragment =
-		local->comm_tallies.rx_message_in_bad_msg_fragments;
-
-	if (local->iw_mode != IW_MODE_MASTER &&
-	    local->iw_mode != IW_MODE_REPEAT) {
-
-		if (prism2_update_comms_qual(dev) == 0)
-			wstats->qual.updated = IW_QUAL_ALL_UPDATED |
-				IW_QUAL_DBM;
-
-		wstats->qual.qual = local->comms_qual;
-		wstats->qual.level = local->avg_signal;
-		wstats->qual.noise = local->avg_noise;
-	} else {
-		wstats->qual.qual = 0;
-		wstats->qual.level = 0;
-		wstats->qual.noise = 0;
-		wstats->qual.updated = IW_QUAL_ALL_INVALID;
-	}
-
-	return wstats;
-}
-
-
-static int prism2_get_datarates(struct net_device *dev, u8 *rates)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	u8 buf[12];
-	int len;
-	u16 val;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	len = local->func->get_rid(dev, HFA384X_RID_SUPPORTEDDATARATES, buf,
-				   sizeof(buf), 0);
-	if (len < 2)
-		return 0;
-
-	val = le16_to_cpu(*(__le16 *) buf); /* string length */
-
-	if (len - 2 < val || val > 10)
-		return 0;
-
-	memcpy(rates, buf + 2, val);
-	return val;
-}
-
-
-static int prism2_get_name(struct net_device *dev,
-			   struct iw_request_info *info,
-			   union iwreq_data *wrqu, char *extra)
-{
-	u8 rates[10];
-	int len, i, over2 = 0;
-
-	len = prism2_get_datarates(dev, rates);
-
-	for (i = 0; i < len; i++) {
-		if (rates[i] == 0x0b || rates[i] == 0x16) {
-			over2 = 1;
-			break;
-		}
-	}
-
-	strcpy(wrqu->name, over2 ? "IEEE 802.11b" : "IEEE 802.11-DS");
-
-	return 0;
-}
-
-
-static int prism2_ioctl_siwencode(struct net_device *dev,
-				  struct iw_request_info *info,
-				  union iwreq_data *wrqu, char *keybuf)
-{
-	struct iw_point *erq = &wrqu->encoding;
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int i;
-	struct lib80211_crypt_data **crypt;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	i = erq->flags & IW_ENCODE_INDEX;
-	if (i < 1 || i > 4)
-		i = local->crypt_info.tx_keyidx;
-	else
-		i--;
-	if (i < 0 || i >= WEP_KEYS)
-		return -EINVAL;
-
-	crypt = &local->crypt_info.crypt[i];
-
-	if (erq->flags & IW_ENCODE_DISABLED) {
-		if (*crypt)
-			lib80211_crypt_delayed_deinit(&local->crypt_info, crypt);
-		goto done;
-	}
-
-	if (*crypt != NULL && (*crypt)->ops != NULL &&
-	    strcmp((*crypt)->ops->name, "WEP") != 0) {
-		/* changing to use WEP; deinit previously used algorithm */
-		lib80211_crypt_delayed_deinit(&local->crypt_info, crypt);
-	}
-
-	if (*crypt == NULL) {
-		struct lib80211_crypt_data *new_crypt;
-
-		/* take WEP into use */
-		new_crypt = kzalloc(sizeof(struct lib80211_crypt_data),
-				GFP_KERNEL);
-		if (new_crypt == NULL)
-			return -ENOMEM;
-		new_crypt->ops = lib80211_get_crypto_ops("WEP");
-		if (!new_crypt->ops) {
-			request_module("lib80211_crypt_wep");
-			new_crypt->ops = lib80211_get_crypto_ops("WEP");
-		}
-		if (new_crypt->ops && try_module_get(new_crypt->ops->owner))
-			new_crypt->priv = new_crypt->ops->init(i);
-		if (!new_crypt->ops || !new_crypt->priv) {
-			kfree(new_crypt);
-			new_crypt = NULL;
-
-			printk(KERN_WARNING "%s: could not initialize WEP: "
-			       "load module hostap_crypt_wep.o\n",
-			       dev->name);
-			return -EOPNOTSUPP;
-		}
-		*crypt = new_crypt;
-	}
-
-	if (erq->length > 0) {
-		int len = erq->length <= 5 ? 5 : 13;
-		int first = 1, j;
-		if (len > erq->length)
-			memset(keybuf + erq->length, 0, len - erq->length);
-		(*crypt)->ops->set_key(keybuf, len, NULL, (*crypt)->priv);
-		for (j = 0; j < WEP_KEYS; j++) {
-			if (j != i && local->crypt_info.crypt[j]) {
-				first = 0;
-				break;
-			}
-		}
-		if (first)
-			local->crypt_info.tx_keyidx = i;
-	} else {
-		/* No key data - just set the default TX key index */
-		local->crypt_info.tx_keyidx = i;
-	}
-
- done:
-	local->open_wep = erq->flags & IW_ENCODE_OPEN;
-
-	if (hostap_set_encryption(local)) {
-		printk(KERN_DEBUG "%s: set_encryption failed\n", dev->name);
-		return -EINVAL;
-	}
-
-	/* Do not reset port0 if card is in Managed mode since resetting will
-	 * generate new IEEE 802.11 authentication which may end up in looping
-	 * with IEEE 802.1X. Prism2 documentation seem to require port reset
-	 * after WEP configuration. However, keys are apparently changed at
-	 * least in Managed mode. */
-	if (local->iw_mode != IW_MODE_INFRA && local->func->reset_port(dev)) {
-		printk(KERN_DEBUG "%s: reset_port failed\n", dev->name);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-
-static int prism2_ioctl_giwencode(struct net_device *dev,
-				  struct iw_request_info *info,
-				  union iwreq_data *wrqu, char *key)
-{
-	struct iw_point *erq = &wrqu->encoding;
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int i, len;
-	u16 val;
-	struct lib80211_crypt_data *crypt;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	i = erq->flags & IW_ENCODE_INDEX;
-	if (i < 1 || i > 4)
-		i = local->crypt_info.tx_keyidx;
-	else
-		i--;
-	if (i < 0 || i >= WEP_KEYS)
-		return -EINVAL;
-
-	crypt = local->crypt_info.crypt[i];
-	erq->flags = i + 1;
-
-	if (crypt == NULL || crypt->ops == NULL) {
-		erq->length = 0;
-		erq->flags |= IW_ENCODE_DISABLED;
-		return 0;
-	}
-
-	if (strcmp(crypt->ops->name, "WEP") != 0) {
-		/* only WEP is supported with wireless extensions, so just
-		 * report that encryption is used */
-		erq->length = 0;
-		erq->flags |= IW_ENCODE_ENABLED;
-		return 0;
-	}
-
-	/* Reads from HFA384X_RID_CNFDEFAULTKEY* return bogus values, so show
-	 * the keys from driver buffer */
-	len = crypt->ops->get_key(key, WEP_KEY_LEN, NULL, crypt->priv);
-	erq->length = (len >= 0 ? len : 0);
-
-	if (local->func->get_rid(dev, HFA384X_RID_CNFWEPFLAGS, &val, 2, 1) < 0)
-	{
-		printk("CNFWEPFLAGS reading failed\n");
-		return -EOPNOTSUPP;
-	}
-	le16_to_cpus(&val);
-	if (val & HFA384X_WEPFLAGS_PRIVACYINVOKED)
-		erq->flags |= IW_ENCODE_ENABLED;
-	else
-		erq->flags |= IW_ENCODE_DISABLED;
-	if (val & HFA384X_WEPFLAGS_EXCLUDEUNENCRYPTED)
-		erq->flags |= IW_ENCODE_RESTRICTED;
-	else
-		erq->flags |= IW_ENCODE_OPEN;
-
-	return 0;
-}
-
-
-static int hostap_set_rate(struct net_device *dev)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int ret, basic_rates;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	basic_rates = local->basic_rates & local->tx_rate_control;
-	if (!basic_rates || basic_rates != local->basic_rates) {
-		printk(KERN_INFO "%s: updating basic rate set automatically "
-		       "to match with the new supported rate set\n",
-		       dev->name);
-		if (!basic_rates)
-			basic_rates = local->tx_rate_control;
-
-		local->basic_rates = basic_rates;
-		if (hostap_set_word(dev, HFA384X_RID_CNFBASICRATES,
-				    basic_rates))
-			printk(KERN_WARNING "%s: failed to set "
-			       "cnfBasicRates\n", dev->name);
-	}
-
-	ret = (hostap_set_word(dev, HFA384X_RID_TXRATECONTROL,
-			       local->tx_rate_control) ||
-	       hostap_set_word(dev, HFA384X_RID_CNFSUPPORTEDRATES,
-			       local->tx_rate_control) ||
-	       local->func->reset_port(dev));
-
-	if (ret) {
-		printk(KERN_WARNING "%s: TXRateControl/cnfSupportedRates "
-		       "setting to 0x%x failed\n",
-		       dev->name, local->tx_rate_control);
-	}
-
-	/* Update TX rate configuration for all STAs based on new operational
-	 * rate set. */
-	hostap_update_rates(local);
-
-	return ret;
-}
-
-
-static int prism2_ioctl_siwrate(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *rrq = &wrqu->bitrate;
-	struct hostap_interface *iface;
-	local_info_t *local;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (rrq->fixed) {
-		switch (rrq->value) {
-		case 11000000:
-			local->tx_rate_control = HFA384X_RATES_11MBPS;
-			break;
-		case 5500000:
-			local->tx_rate_control = HFA384X_RATES_5MBPS;
-			break;
-		case 2000000:
-			local->tx_rate_control = HFA384X_RATES_2MBPS;
-			break;
-		case 1000000:
-			local->tx_rate_control = HFA384X_RATES_1MBPS;
-			break;
-		default:
-			local->tx_rate_control = HFA384X_RATES_1MBPS |
-				HFA384X_RATES_2MBPS | HFA384X_RATES_5MBPS |
-				HFA384X_RATES_11MBPS;
-			break;
-		}
-	} else {
-		switch (rrq->value) {
-		case 11000000:
-			local->tx_rate_control = HFA384X_RATES_1MBPS |
-				HFA384X_RATES_2MBPS | HFA384X_RATES_5MBPS |
-				HFA384X_RATES_11MBPS;
-			break;
-		case 5500000:
-			local->tx_rate_control = HFA384X_RATES_1MBPS |
-				HFA384X_RATES_2MBPS | HFA384X_RATES_5MBPS;
-			break;
-		case 2000000:
-			local->tx_rate_control = HFA384X_RATES_1MBPS |
-				HFA384X_RATES_2MBPS;
-			break;
-		case 1000000:
-			local->tx_rate_control = HFA384X_RATES_1MBPS;
-			break;
-		default:
-			local->tx_rate_control = HFA384X_RATES_1MBPS |
-				HFA384X_RATES_2MBPS | HFA384X_RATES_5MBPS |
-				HFA384X_RATES_11MBPS;
-			break;
-		}
-	}
-
-	return hostap_set_rate(dev);
-}
-
-
-static int prism2_ioctl_giwrate(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *rrq = &wrqu->bitrate;
-	u16 val;
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int ret = 0;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (local->func->get_rid(dev, HFA384X_RID_TXRATECONTROL, &val, 2, 1) <
-	    0)
-		return -EINVAL;
-
-	if ((val & 0x1) && (val > 1))
-		rrq->fixed = 0;
-	else
-		rrq->fixed = 1;
-
-	if (local->iw_mode == IW_MODE_MASTER && local->ap != NULL &&
-	    !local->fw_tx_rate_control) {
-		/* HFA384X_RID_CURRENTTXRATE seems to always be 2 Mbps in
-		 * Host AP mode, so use the recorded TX rate of the last sent
-		 * frame */
-		rrq->value = local->ap->last_tx_rate > 0 ?
-			local->ap->last_tx_rate * 100000 : 11000000;
-		return 0;
-	}
-
-	if (local->func->get_rid(dev, HFA384X_RID_CURRENTTXRATE, &val, 2, 1) <
-	    0)
-		return -EINVAL;
-
-	switch (val) {
-	case HFA384X_RATES_1MBPS:
-		rrq->value = 1000000;
-		break;
-	case HFA384X_RATES_2MBPS:
-		rrq->value = 2000000;
-		break;
-	case HFA384X_RATES_5MBPS:
-		rrq->value = 5500000;
-		break;
-	case HFA384X_RATES_11MBPS:
-		rrq->value = 11000000;
-		break;
-	default:
-		/* should not happen */
-		rrq->value = 11000000;
-		ret = -EINVAL;
-		break;
-	}
-
-	return ret;
-}
-
-
-static int prism2_ioctl_siwsens(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *sens = &wrqu->sens;
-	struct hostap_interface *iface;
-	local_info_t *local;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	/* Set the desired AP density */
-	if (sens->value < 1 || sens->value > 3)
-		return -EINVAL;
-
-	if (hostap_set_word(dev, HFA384X_RID_CNFSYSTEMSCALE, sens->value) ||
-	    local->func->reset_port(dev))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int prism2_ioctl_giwsens(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *sens = &wrqu->sens;
-	struct hostap_interface *iface;
-	local_info_t *local;
-	__le16 val;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	/* Get the current AP density */
-	if (local->func->get_rid(dev, HFA384X_RID_CNFSYSTEMSCALE, &val, 2, 1) <
-	    0)
-		return -EINVAL;
-
-	sens->value = le16_to_cpu(val);
-	sens->fixed = 1;
-
-	return 0;
-}
-
-
-/* Deprecated in new wireless extension API */
-static int prism2_ioctl_giwaplist(struct net_device *dev,
-				  struct iw_request_info *info,
-				  union iwreq_data *wrqu, char *extra)
-{
-	struct iw_point *data = &wrqu->data;
-	struct hostap_interface *iface;
-	local_info_t *local;
-	struct sockaddr *addr;
-	struct iw_quality *qual;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (local->iw_mode != IW_MODE_MASTER) {
-		printk(KERN_DEBUG "SIOCGIWAPLIST is currently only supported "
-		       "in Host AP mode\n");
-		data->length = 0;
-		return -EOPNOTSUPP;
-	}
-
-	addr = kmalloc_array(IW_MAX_AP, sizeof(struct sockaddr), GFP_KERNEL);
-	qual = kmalloc_array(IW_MAX_AP, sizeof(struct iw_quality), GFP_KERNEL);
-	if (addr == NULL || qual == NULL) {
-		kfree(addr);
-		kfree(qual);
-		data->length = 0;
-		return -ENOMEM;
-	}
-
-	data->length = prism2_ap_get_sta_qual(local, addr, qual, IW_MAX_AP, 1);
-
-	memcpy(extra, addr, sizeof(struct sockaddr) * data->length);
-	data->flags = 1; /* has quality information */
-	memcpy(extra + sizeof(struct sockaddr) * data->length, qual,
-	       sizeof(struct iw_quality) * data->length);
-
-	kfree(addr);
-	kfree(qual);
-	return 0;
-}
-
-
-static int prism2_ioctl_siwrts(struct net_device *dev,
-			       struct iw_request_info *info,
-			       union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *rts = &wrqu->rts;
-	struct hostap_interface *iface;
-	local_info_t *local;
-	__le16 val;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (rts->disabled)
-		val = cpu_to_le16(2347);
-	else if (rts->value < 0 || rts->value > 2347)
-		return -EINVAL;
-	else
-		val = cpu_to_le16(rts->value);
-
-	if (local->func->set_rid(dev, HFA384X_RID_RTSTHRESHOLD, &val, 2) ||
-	    local->func->reset_port(dev))
-		return -EINVAL;
-
-	local->rts_threshold = rts->value;
-
-	return 0;
-}
-
-static int prism2_ioctl_giwrts(struct net_device *dev,
-			       struct iw_request_info *info,
-			       union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *rts = &wrqu->rts;
-	struct hostap_interface *iface;
-	local_info_t *local;
-	__le16 val;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (local->func->get_rid(dev, HFA384X_RID_RTSTHRESHOLD, &val, 2, 1) <
-	    0)
-		return -EINVAL;
-
-	rts->value = le16_to_cpu(val);
-	rts->disabled = (rts->value == 2347);
-	rts->fixed = 1;
-
-	return 0;
-}
-
-
-static int prism2_ioctl_siwfrag(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *rts = &wrqu->rts;
-	struct hostap_interface *iface;
-	local_info_t *local;
-	__le16 val;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (rts->disabled)
-		val = cpu_to_le16(2346);
-	else if (rts->value < 256 || rts->value > 2346)
-		return -EINVAL;
-	else
-		val = cpu_to_le16(rts->value & ~0x1); /* even numbers only */
-
-	local->fragm_threshold = rts->value & ~0x1;
-	if (local->func->set_rid(dev, HFA384X_RID_FRAGMENTATIONTHRESHOLD, &val,
-				 2)
-	    || local->func->reset_port(dev))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int prism2_ioctl_giwfrag(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *rts = &wrqu->rts;
-	struct hostap_interface *iface;
-	local_info_t *local;
-	__le16 val;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (local->func->get_rid(dev, HFA384X_RID_FRAGMENTATIONTHRESHOLD,
-				 &val, 2, 1) < 0)
-		return -EINVAL;
-
-	rts->value = le16_to_cpu(val);
-	rts->disabled = (rts->value == 2346);
-	rts->fixed = 1;
-
-	return 0;
-}
-
-
-#ifndef PRISM2_NO_STATION_MODES
-static int hostap_join_ap(struct net_device *dev)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	struct hfa384x_join_request req;
-	unsigned long flags;
-	int i;
-	struct hfa384x_hostscan_result *entry;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	memcpy(req.bssid, local->preferred_ap, ETH_ALEN);
-	req.channel = 0;
-
-	spin_lock_irqsave(&local->lock, flags);
-	for (i = 0; i < local->last_scan_results_count; i++) {
-		if (!local->last_scan_results)
-			break;
-		entry = &local->last_scan_results[i];
-		if (ether_addr_equal(local->preferred_ap, entry->bssid)) {
-			req.channel = entry->chid;
-			break;
-		}
-	}
-	spin_unlock_irqrestore(&local->lock, flags);
-
-	if (local->func->set_rid(dev, HFA384X_RID_JOINREQUEST, &req,
-				 sizeof(req))) {
-		printk(KERN_DEBUG "%s: JoinRequest %pM failed\n",
-		       dev->name, local->preferred_ap);
-		return -1;
-	}
-
-	printk(KERN_DEBUG "%s: Trying to join BSSID %pM\n",
-	       dev->name, local->preferred_ap);
-
-	return 0;
-}
-#endif /* PRISM2_NO_STATION_MODES */
-
-
-static int prism2_ioctl_siwap(struct net_device *dev,
-			      struct iw_request_info *info,
-			      union iwreq_data *wrqu, char *extra)
-{
-	struct sockaddr *ap_addr = &wrqu->ap_addr;
-#ifdef PRISM2_NO_STATION_MODES
-	return -EOPNOTSUPP;
-#else /* PRISM2_NO_STATION_MODES */
-	struct hostap_interface *iface;
-	local_info_t *local;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	memcpy(local->preferred_ap, &ap_addr->sa_data, ETH_ALEN);
-
-	if (local->host_roaming == 1 && local->iw_mode == IW_MODE_INFRA) {
-		struct hfa384x_scan_request scan_req;
-		memset(&scan_req, 0, sizeof(scan_req));
-		scan_req.channel_list = cpu_to_le16(0x3fff);
-		scan_req.txrate = cpu_to_le16(HFA384X_RATES_1MBPS);
-		if (local->func->set_rid(dev, HFA384X_RID_SCANREQUEST,
-					 &scan_req, sizeof(scan_req))) {
-			printk(KERN_DEBUG "%s: ScanResults request failed - "
-			       "preferred AP delayed to next unsolicited "
-			       "scan\n", dev->name);
-		}
-	} else if (local->host_roaming == 2 &&
-		   local->iw_mode == IW_MODE_INFRA) {
-		if (hostap_join_ap(dev))
-			return -EINVAL;
-	} else {
-		printk(KERN_DEBUG "%s: Preferred AP (SIOCSIWAP) is used only "
-		       "in Managed mode when host_roaming is enabled\n",
-		       dev->name);
-	}
-
-	return 0;
-#endif /* PRISM2_NO_STATION_MODES */
-}
-
-static int prism2_ioctl_giwap(struct net_device *dev,
-			      struct iw_request_info *info,
-			      union iwreq_data *wrqu, char *extra)
-{
-	struct sockaddr *ap_addr = &wrqu->ap_addr;
-	struct hostap_interface *iface;
-	local_info_t *local;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	ap_addr->sa_family = ARPHRD_ETHER;
-	switch (iface->type) {
-	case HOSTAP_INTERFACE_AP:
-		memcpy(&ap_addr->sa_data, dev->dev_addr, ETH_ALEN);
-		break;
-	case HOSTAP_INTERFACE_STA:
-		memcpy(&ap_addr->sa_data, local->assoc_ap_addr, ETH_ALEN);
-		break;
-	case HOSTAP_INTERFACE_WDS:
-		memcpy(&ap_addr->sa_data, iface->u.wds.remote_addr, ETH_ALEN);
-		break;
-	default:
-		if (local->func->get_rid(dev, HFA384X_RID_CURRENTBSSID,
-					 &ap_addr->sa_data, ETH_ALEN, 1) < 0)
-			return -EOPNOTSUPP;
-
-		/* local->bssid is also updated in LinkStatus handler when in
-		 * station mode */
-		memcpy(local->bssid, &ap_addr->sa_data, ETH_ALEN);
-		break;
-	}
-
-	return 0;
-}
-
-
-static int prism2_ioctl_siwnickn(struct net_device *dev,
-				 struct iw_request_info *info,
-				 union iwreq_data *wrqu, char *nickname)
-{
-	struct iw_point *data = &wrqu->data;
-	struct hostap_interface *iface;
-	local_info_t *local;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	memset(local->name, 0, sizeof(local->name));
-	memcpy(local->name, nickname, data->length);
-	local->name_set = 1;
-
-	if (hostap_set_string(dev, HFA384X_RID_CNFOWNNAME, local->name) ||
-	    local->func->reset_port(dev))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int prism2_ioctl_giwnickn(struct net_device *dev,
-				 struct iw_request_info *info,
-				 union iwreq_data *wrqu, char *nickname)
-{
-	struct iw_point *data = &wrqu->data;
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int len;
-	char name[MAX_NAME_LEN + 3];
-	u16 val;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	len = local->func->get_rid(dev, HFA384X_RID_CNFOWNNAME,
-				   &name, MAX_NAME_LEN + 2, 0);
-	val = le16_to_cpu(*(__le16 *) name);
-	if (len > MAX_NAME_LEN + 2 || len < 0 || val > MAX_NAME_LEN)
-		return -EOPNOTSUPP;
-
-	name[val + 2] = '\0';
-	data->length = val + 1;
-	memcpy(nickname, name + 2, val + 1);
-
-	return 0;
-}
-
-
-static int prism2_ioctl_siwfreq(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
-{
-	struct iw_freq *freq = &wrqu->freq;
-	struct hostap_interface *iface;
-	local_info_t *local;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	/* freq => chan. */
-	if (freq->e == 1 &&
-	    freq->m / 100000 >= freq_list[0] &&
-	    freq->m / 100000 <= freq_list[FREQ_COUNT - 1]) {
-		int ch;
-		int fr = freq->m / 100000;
-		for (ch = 0; ch < FREQ_COUNT; ch++) {
-			if (fr == freq_list[ch]) {
-				freq->e = 0;
-				freq->m = ch + 1;
-				break;
-			}
-		}
-	}
-
-	if (freq->e != 0 || freq->m < 1 || freq->m > FREQ_COUNT ||
-	    !(local->channel_mask & (1 << (freq->m - 1))))
-		return -EINVAL;
-
-	local->channel = freq->m; /* channel is used in prism2_setup_rids() */
-	if (hostap_set_word(dev, HFA384X_RID_CNFOWNCHANNEL, local->channel) ||
-	    local->func->reset_port(dev))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int prism2_ioctl_giwfreq(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
-{
-	struct iw_freq *freq = &wrqu->freq;
-	struct hostap_interface *iface;
-	local_info_t *local;
-	u16 val;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (local->func->get_rid(dev, HFA384X_RID_CURRENTCHANNEL, &val, 2, 1) <
-	    0)
-		return -EINVAL;
-
-	le16_to_cpus(&val);
-	if (val < 1 || val > FREQ_COUNT)
-		return -EINVAL;
-
-	freq->m = freq_list[val - 1] * 100000;
-	freq->e = 1;
-
-	return 0;
-}
-
-
-static void hostap_monitor_set_type(local_info_t *local)
-{
-	struct net_device *dev = local->ddev;
-
-	if (dev == NULL)
-		return;
-
-	if (local->monitor_type == PRISM2_MONITOR_PRISM ||
-	    local->monitor_type == PRISM2_MONITOR_CAPHDR) {
-		dev->type = ARPHRD_IEEE80211_PRISM;
-	} else if (local->monitor_type == PRISM2_MONITOR_RADIOTAP) {
-		dev->type = ARPHRD_IEEE80211_RADIOTAP;
-	} else {
-		dev->type = ARPHRD_IEEE80211;
-	}
-}
-
-
-static int prism2_ioctl_siwessid(struct net_device *dev,
-				 struct iw_request_info *info,
-				 union iwreq_data *wrqu, char *ssid)
-{
-	struct iw_point *data = &wrqu->data;
-	struct hostap_interface *iface;
-	local_info_t *local;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (iface->type == HOSTAP_INTERFACE_WDS)
-		return -EOPNOTSUPP;
-
-	if (data->flags == 0)
-		ssid[0] = '\0'; /* ANY */
-
-	if (local->iw_mode == IW_MODE_MASTER && ssid[0] == '\0') {
-		/* Setting SSID to empty string seems to kill the card in
-		 * Host AP mode */
-		printk(KERN_DEBUG "%s: Host AP mode does not support "
-		       "'Any' essid\n", dev->name);
-		return -EINVAL;
-	}
-
-	memcpy(local->essid, ssid, data->length);
-	local->essid[data->length] = '\0';
-
-	if ((!local->fw_ap &&
-	     hostap_set_string(dev, HFA384X_RID_CNFDESIREDSSID, local->essid))
-	    || hostap_set_string(dev, HFA384X_RID_CNFOWNSSID, local->essid) ||
-	    local->func->reset_port(dev))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int prism2_ioctl_giwessid(struct net_device *dev,
-				 struct iw_request_info *info,
-				 union iwreq_data *wrqu, char *essid)
-{
-	struct iw_point *data = &wrqu->data;
-	struct hostap_interface *iface;
-	local_info_t *local;
-	u16 val;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (iface->type == HOSTAP_INTERFACE_WDS)
-		return -EOPNOTSUPP;
-
-	data->flags = 1; /* active */
-	if (local->iw_mode == IW_MODE_MASTER) {
-		data->length = strlen(local->essid);
-		memcpy(essid, local->essid, IW_ESSID_MAX_SIZE);
-	} else {
-		int len;
-		char ssid[MAX_SSID_LEN + 2];
-		memset(ssid, 0, sizeof(ssid));
-		len = local->func->get_rid(dev, HFA384X_RID_CURRENTSSID,
-					   &ssid, MAX_SSID_LEN + 2, 0);
-		val = le16_to_cpu(*(__le16 *) ssid);
-		if (len > MAX_SSID_LEN + 2 || len < 0 || val > MAX_SSID_LEN) {
-			return -EOPNOTSUPP;
-		}
-		data->length = val;
-		memcpy(essid, ssid + 2, IW_ESSID_MAX_SIZE);
-	}
-
-	return 0;
-}
-
-
-static int prism2_ioctl_giwrange(struct net_device *dev,
-				 struct iw_request_info *info,
-				 union iwreq_data *wrqu, char *extra)
-{
-	struct iw_point *data = &wrqu->data;
-	struct hostap_interface *iface;
-	local_info_t *local;
-	struct iw_range *range = (struct iw_range *) extra;
-	u8 rates[10];
-	u16 val;
-	int i, len, over2;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	data->length = sizeof(struct iw_range);
-	memset(range, 0, sizeof(struct iw_range));
-
-	/* TODO: could fill num_txpower and txpower array with
-	 * something; however, there are 128 different values.. */
-
-	range->txpower_capa = IW_TXPOW_DBM;
-
-	if (local->iw_mode == IW_MODE_INFRA || local->iw_mode == IW_MODE_ADHOC)
-	{
-		range->min_pmp = 1 * 1024;
-		range->max_pmp = 65535 * 1024;
-		range->min_pmt = 1 * 1024;
-		range->max_pmt = 1000 * 1024;
-		range->pmp_flags = IW_POWER_PERIOD;
-		range->pmt_flags = IW_POWER_TIMEOUT;
-		range->pm_capa = IW_POWER_PERIOD | IW_POWER_TIMEOUT |
-			IW_POWER_UNICAST_R | IW_POWER_ALL_R;
-	}
-
-	range->we_version_compiled = WIRELESS_EXT;
-	range->we_version_source = 18;
-
-	range->retry_capa = IW_RETRY_LIMIT;
-	range->retry_flags = IW_RETRY_LIMIT;
-	range->min_retry = 0;
-	range->max_retry = 255;
-
-	range->num_channels = FREQ_COUNT;
-
-	val = 0;
-	for (i = 0; i < FREQ_COUNT; i++) {
-		if (local->channel_mask & (1 << i)) {
-			range->freq[val].i = i + 1;
-			range->freq[val].m = freq_list[i] * 100000;
-			range->freq[val].e = 1;
-			val++;
-		}
-		if (val == IW_MAX_FREQUENCIES)
-			break;
-	}
-	range->num_frequency = val;
-
-	if (local->sta_fw_ver >= PRISM2_FW_VER(1,3,1)) {
-		range->max_qual.qual = 70; /* what is correct max? This was not
-					    * documented exactly. At least
-					    * 69 has been observed. */
-		range->max_qual.level = 0; /* dB */
-		range->max_qual.noise = 0; /* dB */
-
-		/* What would be suitable values for "average/typical" qual? */
-		range->avg_qual.qual = 20;
-		range->avg_qual.level = -60;
-		range->avg_qual.noise = -95;
-	} else {
-		range->max_qual.qual = 92; /* 0 .. 92 */
-		range->max_qual.level = 154; /* 27 .. 154 */
-		range->max_qual.noise = 154; /* 27 .. 154 */
-	}
-	range->sensitivity = 3;
-
-	range->max_encoding_tokens = WEP_KEYS;
-	range->num_encoding_sizes = 2;
-	range->encoding_size[0] = 5;
-	range->encoding_size[1] = 13;
-
-	over2 = 0;
-	len = prism2_get_datarates(dev, rates);
-	range->num_bitrates = 0;
-	for (i = 0; i < len; i++) {
-		if (range->num_bitrates < IW_MAX_BITRATES) {
-			range->bitrate[range->num_bitrates] =
-				rates[i] * 500000;
-			range->num_bitrates++;
-		}
-		if (rates[i] == 0x0b || rates[i] == 0x16)
-			over2 = 1;
-	}
-	/* estimated maximum TCP throughput values (bps) */
-	range->throughput = over2 ? 5500000 : 1500000;
-
-	range->min_rts = 0;
-	range->max_rts = 2347;
-	range->min_frag = 256;
-	range->max_frag = 2346;
-
-	/* Event capability (kernel + driver) */
-	range->event_capa[0] = (IW_EVENT_CAPA_K_0 |
-				IW_EVENT_CAPA_MASK(SIOCGIWTHRSPY) |
-				IW_EVENT_CAPA_MASK(SIOCGIWAP) |
-				IW_EVENT_CAPA_MASK(SIOCGIWSCAN));
-	range->event_capa[1] = IW_EVENT_CAPA_K_1;
-	range->event_capa[4] = (IW_EVENT_CAPA_MASK(IWEVTXDROP) |
-				IW_EVENT_CAPA_MASK(IWEVCUSTOM) |
-				IW_EVENT_CAPA_MASK(IWEVREGISTERED) |
-				IW_EVENT_CAPA_MASK(IWEVEXPIRED));
-
-	range->enc_capa = IW_ENC_CAPA_WPA | IW_ENC_CAPA_WPA2 |
-		IW_ENC_CAPA_CIPHER_TKIP | IW_ENC_CAPA_CIPHER_CCMP;
-
-	if (local->sta_fw_ver >= PRISM2_FW_VER(1,3,1))
-		range->scan_capa = IW_SCAN_CAPA_ESSID;
-
-	return 0;
-}
-
-
-static int hostap_monitor_mode_enable(local_info_t *local)
-{
-	struct net_device *dev = local->dev;
-
-	printk(KERN_DEBUG "Enabling monitor mode\n");
-	hostap_monitor_set_type(local);
-
-	if (hostap_set_word(dev, HFA384X_RID_CNFPORTTYPE,
-			    HFA384X_PORTTYPE_PSEUDO_IBSS)) {
-		printk(KERN_DEBUG "Port type setting for monitor mode "
-		       "failed\n");
-		return -EOPNOTSUPP;
-	}
-
-	/* Host decrypt is needed to get the IV and ICV fields;
-	 * however, monitor mode seems to remove WEP flag from frame
-	 * control field */
-	if (hostap_set_word(dev, HFA384X_RID_CNFWEPFLAGS,
-			    HFA384X_WEPFLAGS_HOSTENCRYPT |
-			    HFA384X_WEPFLAGS_HOSTDECRYPT)) {
-		printk(KERN_DEBUG "WEP flags setting failed\n");
-		return -EOPNOTSUPP;
-	}
-
-	if (local->func->reset_port(dev) ||
-	    local->func->cmd(dev, HFA384X_CMDCODE_TEST |
-			     (HFA384X_TEST_MONITOR << 8),
-			     0, NULL, NULL)) {
-		printk(KERN_DEBUG "Setting monitor mode failed\n");
-		return -EOPNOTSUPP;
-	}
-
-	return 0;
-}
-
-
-static int hostap_monitor_mode_disable(local_info_t *local)
-{
-	struct net_device *dev = local->ddev;
-
-	if (dev == NULL)
-		return -1;
-
-	printk(KERN_DEBUG "%s: Disabling monitor mode\n", dev->name);
-	dev->type = ARPHRD_ETHER;
-
-	if (local->func->cmd(dev, HFA384X_CMDCODE_TEST |
-			     (HFA384X_TEST_STOP << 8),
-			     0, NULL, NULL))
-		return -1;
-	return hostap_set_encryption(local);
-}
-
-
-static int prism2_ioctl_siwmode(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
-{
-	__u32 *mode = &wrqu->mode;
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int double_reset = 0;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (*mode != IW_MODE_ADHOC && *mode != IW_MODE_INFRA &&
-	    *mode != IW_MODE_MASTER && *mode != IW_MODE_REPEAT &&
-	    *mode != IW_MODE_MONITOR)
-		return -EOPNOTSUPP;
-
-#ifdef PRISM2_NO_STATION_MODES
-	if (*mode == IW_MODE_ADHOC || *mode == IW_MODE_INFRA)
-		return -EOPNOTSUPP;
-#endif /* PRISM2_NO_STATION_MODES */
-
-	if (*mode == local->iw_mode)
-		return 0;
-
-	if (*mode == IW_MODE_MASTER && local->essid[0] == '\0') {
-		printk(KERN_WARNING "%s: empty SSID not allowed in Master "
-		       "mode\n", dev->name);
-		return -EINVAL;
-	}
-
-	if (local->iw_mode == IW_MODE_MONITOR)
-		hostap_monitor_mode_disable(local);
-
-	if ((local->iw_mode == IW_MODE_ADHOC ||
-	     local->iw_mode == IW_MODE_MONITOR) && *mode == IW_MODE_MASTER) {
-		/* There seems to be a firmware bug in at least STA f/w v1.5.6
-		 * that leaves beacon frames to use IBSS type when moving from
-		 * IBSS to Host AP mode. Doing double Port0 reset seems to be
-		 * enough to workaround this. */
-		double_reset = 1;
-	}
-
-	printk(KERN_DEBUG "prism2: %s: operating mode changed "
-	       "%d -> %d\n", dev->name, local->iw_mode, *mode);
-	local->iw_mode = *mode;
-
-	if (local->iw_mode == IW_MODE_MONITOR)
-		hostap_monitor_mode_enable(local);
-	else if (local->iw_mode == IW_MODE_MASTER && !local->host_encrypt &&
-		 !local->fw_encrypt_ok) {
-		printk(KERN_DEBUG "%s: defaulting to host-based encryption as "
-		       "a workaround for firmware bug in Host AP mode WEP\n",
-		       dev->name);
-		local->host_encrypt = 1;
-	}
-
-	if (hostap_set_word(dev, HFA384X_RID_CNFPORTTYPE,
-			    hostap_get_porttype(local)))
-		return -EOPNOTSUPP;
-
-	if (local->func->reset_port(dev))
-		return -EINVAL;
-	if (double_reset && local->func->reset_port(dev))
-		return -EINVAL;
-
-	if (local->iw_mode != IW_MODE_INFRA && local->iw_mode != IW_MODE_ADHOC)
-	{
-		/* netif_carrier is used only in client modes for now, so make
-		 * sure carrier is on when moving to non-client modes. */
-		netif_carrier_on(local->dev);
-		netif_carrier_on(local->ddev);
-	}
-	return 0;
-}
-
-
-static int prism2_ioctl_giwmode(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
-{
-	__u32 *mode = &wrqu->mode;
-	struct hostap_interface *iface;
-	local_info_t *local;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	switch (iface->type) {
-	case HOSTAP_INTERFACE_STA:
-		*mode = IW_MODE_INFRA;
-		break;
-	case HOSTAP_INTERFACE_WDS:
-		*mode = IW_MODE_REPEAT;
-		break;
-	default:
-		*mode = local->iw_mode;
-		break;
-	}
-	return 0;
-}
-
-
-static int prism2_ioctl_siwpower(struct net_device *dev,
-				 struct iw_request_info *info,
-				 union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *wrq = &wrqu->power;
-#ifdef PRISM2_NO_STATION_MODES
-	return -EOPNOTSUPP;
-#else /* PRISM2_NO_STATION_MODES */
-	int ret = 0;
-
-	if (wrq->disabled)
-		return hostap_set_word(dev, HFA384X_RID_CNFPMENABLED, 0);
-
-	switch (wrq->flags & IW_POWER_MODE) {
-	case IW_POWER_UNICAST_R:
-		ret = hostap_set_word(dev, HFA384X_RID_CNFMULTICASTRECEIVE, 0);
-		if (ret)
-			return ret;
-		ret = hostap_set_word(dev, HFA384X_RID_CNFPMENABLED, 1);
-		if (ret)
-			return ret;
-		break;
-	case IW_POWER_ALL_R:
-		ret = hostap_set_word(dev, HFA384X_RID_CNFMULTICASTRECEIVE, 1);
-		if (ret)
-			return ret;
-		ret = hostap_set_word(dev, HFA384X_RID_CNFPMENABLED, 1);
-		if (ret)
-			return ret;
-		break;
-	case IW_POWER_ON:
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if (wrq->flags & IW_POWER_TIMEOUT) {
-		ret = hostap_set_word(dev, HFA384X_RID_CNFPMENABLED, 1);
-		if (ret)
-			return ret;
-		ret = hostap_set_word(dev, HFA384X_RID_CNFPMHOLDOVERDURATION,
-				      wrq->value / 1024);
-		if (ret)
-			return ret;
-	}
-	if (wrq->flags & IW_POWER_PERIOD) {
-		ret = hostap_set_word(dev, HFA384X_RID_CNFPMENABLED, 1);
-		if (ret)
-			return ret;
-		ret = hostap_set_word(dev, HFA384X_RID_CNFMAXSLEEPDURATION,
-				      wrq->value / 1024);
-		if (ret)
-			return ret;
-	}
-
-	return ret;
-#endif /* PRISM2_NO_STATION_MODES */
-}
-
-
-static int prism2_ioctl_giwpower(struct net_device *dev,
-				 struct iw_request_info *info,
-				 union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *rrq = &wrqu->power;
-#ifdef PRISM2_NO_STATION_MODES
-	return -EOPNOTSUPP;
-#else /* PRISM2_NO_STATION_MODES */
-	struct hostap_interface *iface;
-	local_info_t *local;
-	__le16 enable, mcast;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (local->func->get_rid(dev, HFA384X_RID_CNFPMENABLED, &enable, 2, 1)
-	    < 0)
-		return -EINVAL;
-
-	if (!le16_to_cpu(enable)) {
-		rrq->disabled = 1;
-		return 0;
-	}
-
-	rrq->disabled = 0;
-
-	if ((rrq->flags & IW_POWER_TYPE) == IW_POWER_TIMEOUT) {
-		__le16 timeout;
-		if (local->func->get_rid(dev,
-					 HFA384X_RID_CNFPMHOLDOVERDURATION,
-					 &timeout, 2, 1) < 0)
-			return -EINVAL;
-
-		rrq->flags = IW_POWER_TIMEOUT;
-		rrq->value = le16_to_cpu(timeout) * 1024;
-	} else {
-		__le16 period;
-		if (local->func->get_rid(dev, HFA384X_RID_CNFMAXSLEEPDURATION,
-					 &period, 2, 1) < 0)
-			return -EINVAL;
-
-		rrq->flags = IW_POWER_PERIOD;
-		rrq->value = le16_to_cpu(period) * 1024;
-	}
-
-	if (local->func->get_rid(dev, HFA384X_RID_CNFMULTICASTRECEIVE, &mcast,
-				 2, 1) < 0)
-		return -EINVAL;
-
-	if (le16_to_cpu(mcast))
-		rrq->flags |= IW_POWER_ALL_R;
-	else
-		rrq->flags |= IW_POWER_UNICAST_R;
-
-	return 0;
-#endif /* PRISM2_NO_STATION_MODES */
-}
-
-
-static int prism2_ioctl_siwretry(struct net_device *dev,
-				 struct iw_request_info *info,
-				 union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *rrq = &wrqu->retry;
-	struct hostap_interface *iface;
-	local_info_t *local;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (rrq->disabled)
-		return -EINVAL;
-
-	/* setting retry limits is not supported with the current station
-	 * firmware code; simulate this with alternative retry count for now */
-	if (rrq->flags == IW_RETRY_LIMIT) {
-		if (rrq->value < 0) {
-			/* disable manual retry count setting and use firmware
-			 * defaults */
-			local->manual_retry_count = -1;
-			local->tx_control &= ~HFA384X_TX_CTRL_ALT_RTRY;
-		} else {
-			if (hostap_set_word(dev, HFA384X_RID_CNFALTRETRYCOUNT,
-					    rrq->value)) {
-				printk(KERN_DEBUG "%s: Alternate retry count "
-				       "setting to %d failed\n",
-				       dev->name, rrq->value);
-				return -EOPNOTSUPP;
-			}
-
-			local->manual_retry_count = rrq->value;
-			local->tx_control |= HFA384X_TX_CTRL_ALT_RTRY;
-		}
-		return 0;
-	}
-
-	return -EOPNOTSUPP;
-
-#if 0
-	/* what could be done, if firmware would support this.. */
-
-	if (rrq->flags & IW_RETRY_LIMIT) {
-		if (rrq->flags & IW_RETRY_LONG)
-			HFA384X_RID_LONGRETRYLIMIT = rrq->value;
-		else if (rrq->flags & IW_RETRY_SHORT)
-			HFA384X_RID_SHORTRETRYLIMIT = rrq->value;
-		else {
-			HFA384X_RID_LONGRETRYLIMIT = rrq->value;
-			HFA384X_RID_SHORTRETRYLIMIT = rrq->value;
-		}
-
-	}
-
-	if (rrq->flags & IW_RETRY_LIFETIME) {
-		HFA384X_RID_MAXTRANSMITLIFETIME = rrq->value / 1024;
-	}
-
-	return 0;
-#endif /* 0 */
-}
-
-static int prism2_ioctl_giwretry(struct net_device *dev,
-				 struct iw_request_info *info,
-				 union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *rrq = &wrqu->retry;
-	struct hostap_interface *iface;
-	local_info_t *local;
-	__le16 shortretry, longretry, lifetime, altretry;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (local->func->get_rid(dev, HFA384X_RID_SHORTRETRYLIMIT, &shortretry,
-				 2, 1) < 0 ||
-	    local->func->get_rid(dev, HFA384X_RID_LONGRETRYLIMIT, &longretry,
-				 2, 1) < 0 ||
-	    local->func->get_rid(dev, HFA384X_RID_MAXTRANSMITLIFETIME,
-				 &lifetime, 2, 1) < 0)
-		return -EINVAL;
-
-	rrq->disabled = 0;
-
-	if ((rrq->flags & IW_RETRY_TYPE) == IW_RETRY_LIFETIME) {
-		rrq->flags = IW_RETRY_LIFETIME;
-		rrq->value = le16_to_cpu(lifetime) * 1024;
-	} else {
-		if (local->manual_retry_count >= 0) {
-			rrq->flags = IW_RETRY_LIMIT;
-			if (local->func->get_rid(dev,
-						 HFA384X_RID_CNFALTRETRYCOUNT,
-						 &altretry, 2, 1) >= 0)
-				rrq->value = le16_to_cpu(altretry);
-			else
-				rrq->value = local->manual_retry_count;
-		} else if ((rrq->flags & IW_RETRY_LONG)) {
-			rrq->flags = IW_RETRY_LIMIT | IW_RETRY_LONG;
-			rrq->value = le16_to_cpu(longretry);
-		} else {
-			rrq->flags = IW_RETRY_LIMIT;
-			rrq->value = le16_to_cpu(shortretry);
-			if (shortretry != longretry)
-				rrq->flags |= IW_RETRY_SHORT;
-		}
-	}
-	return 0;
-}
-
-
-/* Note! This TX power controlling is experimental and should not be used in
- * production use. It just sets raw power register and does not use any kind of
- * feedback information from the measured TX power (CR58). This is now
- * commented out to make sure that it is not used by accident. TX power
- * configuration will be enabled again after proper algorithm using feedback
- * has been implemented. */
-
-#ifdef RAW_TXPOWER_SETTING
-/* Map HFA386x's CR31 to and from dBm with some sort of ad hoc mapping..
- * This version assumes following mapping:
- * CR31 is 7-bit value with -64 to +63 range.
- * -64 is mapped into +20dBm and +63 into -43dBm.
- * This is certainly not an exact mapping for every card, but at least
- * increasing dBm value should correspond to increasing TX power.
- */
-
-static int prism2_txpower_hfa386x_to_dBm(u16 val)
-{
-	signed char tmp;
-
-	if (val > 255)
-		val = 255;
-
-	tmp = val;
-	tmp >>= 2;
-
-	return -12 - tmp;
-}
-
-static u16 prism2_txpower_dBm_to_hfa386x(int val)
-{
-	signed char tmp;
-
-	if (val > 20)
-		return 128;
-	else if (val < -43)
-		return 127;
-
-	tmp = val;
-	tmp = -12 - tmp;
-	tmp <<= 2;
-
-	return (unsigned char) tmp;
-}
-#endif /* RAW_TXPOWER_SETTING */
-
-
-static int prism2_ioctl_siwtxpow(struct net_device *dev,
-				 struct iw_request_info *info,
-				 union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *rrq = &wrqu->txpower;
-	struct hostap_interface *iface;
-	local_info_t *local;
-#ifdef RAW_TXPOWER_SETTING
-	char *tmp;
-#endif
-	u16 val;
-	int ret = 0;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (rrq->disabled) {
-		if (local->txpower_type != PRISM2_TXPOWER_OFF) {
-			val = 0xff; /* use all standby and sleep modes */
-			ret = local->func->cmd(dev, HFA384X_CMDCODE_WRITEMIF,
-					       HFA386X_CR_A_D_TEST_MODES2,
-					       &val, NULL);
-			printk(KERN_DEBUG "%s: Turning radio off: %s\n",
-			       dev->name, ret ? "failed" : "OK");
-			local->txpower_type = PRISM2_TXPOWER_OFF;
-		}
-		return (ret ? -EOPNOTSUPP : 0);
-	}
-
-	if (local->txpower_type == PRISM2_TXPOWER_OFF) {
-		val = 0; /* disable all standby and sleep modes */
-		ret = local->func->cmd(dev, HFA384X_CMDCODE_WRITEMIF,
-				       HFA386X_CR_A_D_TEST_MODES2, &val, NULL);
-		printk(KERN_DEBUG "%s: Turning radio on: %s\n",
-		       dev->name, ret ? "failed" : "OK");
-		local->txpower_type = PRISM2_TXPOWER_UNKNOWN;
-	}
-
-#ifdef RAW_TXPOWER_SETTING
-	if (!rrq->fixed && local->txpower_type != PRISM2_TXPOWER_AUTO) {
-		printk(KERN_DEBUG "Setting ALC on\n");
-		val = HFA384X_TEST_CFG_BIT_ALC;
-		local->func->cmd(dev, HFA384X_CMDCODE_TEST |
-				 (HFA384X_TEST_CFG_BITS << 8), 1, &val, NULL);
-		local->txpower_type = PRISM2_TXPOWER_AUTO;
-		return 0;
-	}
-
-	if (local->txpower_type != PRISM2_TXPOWER_FIXED) {
-		printk(KERN_DEBUG "Setting ALC off\n");
-		val = HFA384X_TEST_CFG_BIT_ALC;
-		local->func->cmd(dev, HFA384X_CMDCODE_TEST |
-				 (HFA384X_TEST_CFG_BITS << 8), 0, &val, NULL);
-			local->txpower_type = PRISM2_TXPOWER_FIXED;
-	}
-
-	if (rrq->flags == IW_TXPOW_DBM)
-		tmp = "dBm";
-	else if (rrq->flags == IW_TXPOW_MWATT)
-		tmp = "mW";
-	else
-		tmp = "UNKNOWN";
-	printk(KERN_DEBUG "Setting TX power to %d %s\n", rrq->value, tmp);
-
-	if (rrq->flags != IW_TXPOW_DBM) {
-		printk("SIOCSIWTXPOW with mW is not supported; use dBm\n");
-		return -EOPNOTSUPP;
-	}
-
-	local->txpower = rrq->value;
-	val = prism2_txpower_dBm_to_hfa386x(local->txpower);
-	if (local->func->cmd(dev, HFA384X_CMDCODE_WRITEMIF,
-			     HFA386X_CR_MANUAL_TX_POWER, &val, NULL))
-		ret = -EOPNOTSUPP;
-#else /* RAW_TXPOWER_SETTING */
-	if (rrq->fixed)
-		ret = -EOPNOTSUPP;
-#endif /* RAW_TXPOWER_SETTING */
-
-	return ret;
-}
-
-static int prism2_ioctl_giwtxpow(struct net_device *dev,
-				 struct iw_request_info *info,
-				 union iwreq_data *wrqu, char *extra)
-{
-#ifdef RAW_TXPOWER_SETTING
-	struct iw_param *rrq = &wrqu->txpower;
-	struct hostap_interface *iface;
-	local_info_t *local;
-	u16 resp0;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	rrq->flags = IW_TXPOW_DBM;
-	rrq->disabled = 0;
-	rrq->fixed = 0;
-
-	if (local->txpower_type == PRISM2_TXPOWER_AUTO) {
-		if (local->func->cmd(dev, HFA384X_CMDCODE_READMIF,
-				     HFA386X_CR_MANUAL_TX_POWER,
-				     NULL, &resp0) == 0) {
-			rrq->value = prism2_txpower_hfa386x_to_dBm(resp0);
-		} else {
-			/* Could not get real txpower; guess 15 dBm */
-			rrq->value = 15;
-		}
-	} else if (local->txpower_type == PRISM2_TXPOWER_OFF) {
-		rrq->value = 0;
-		rrq->disabled = 1;
-	} else if (local->txpower_type == PRISM2_TXPOWER_FIXED) {
-		rrq->value = local->txpower;
-		rrq->fixed = 1;
-	} else {
-		printk("SIOCGIWTXPOW - unknown txpower_type=%d\n",
-		       local->txpower_type);
-	}
-	return 0;
-#else /* RAW_TXPOWER_SETTING */
-	return -EOPNOTSUPP;
-#endif /* RAW_TXPOWER_SETTING */
-}
-
-
-#ifndef PRISM2_NO_STATION_MODES
-
-/* HostScan request works with and without host_roaming mode. In addition, it
- * does not break current association. However, it requires newer station
- * firmware version (>= 1.3.1) than scan request. */
-static int prism2_request_hostscan(struct net_device *dev,
-				   u8 *ssid, u8 ssid_len)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	struct hfa384x_hostscan_request scan_req;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	memset(&scan_req, 0, sizeof(scan_req));
-	scan_req.channel_list = cpu_to_le16(local->channel_mask &
-					    local->scan_channel_mask);
-	scan_req.txrate = cpu_to_le16(HFA384X_RATES_1MBPS);
-	if (ssid) {
-		if (ssid_len > 32)
-			return -EINVAL;
-		scan_req.target_ssid_len = cpu_to_le16(ssid_len);
-		memcpy(scan_req.target_ssid, ssid, ssid_len);
-	}
-
-	if (local->func->set_rid(dev, HFA384X_RID_HOSTSCAN, &scan_req,
-				 sizeof(scan_req))) {
-		printk(KERN_DEBUG "%s: HOSTSCAN failed\n", dev->name);
-		return -EINVAL;
-	}
-	return 0;
-}
-
-
-static int prism2_request_scan(struct net_device *dev)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	struct hfa384x_scan_request scan_req;
-	int ret = 0;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	memset(&scan_req, 0, sizeof(scan_req));
-	scan_req.channel_list = cpu_to_le16(local->channel_mask &
-					    local->scan_channel_mask);
-	scan_req.txrate = cpu_to_le16(HFA384X_RATES_1MBPS);
-
-	/* FIX:
-	 * It seems to be enough to set roaming mode for a short moment to
-	 * host-based and then setup scanrequest data and return the mode to
-	 * firmware-based.
-	 *
-	 * Master mode would need to drop to Managed mode for a short while
-	 * to make scanning work.. Or sweep through the different channels and
-	 * use passive scan based on beacons. */
-
-	if (!local->host_roaming)
-		hostap_set_word(dev, HFA384X_RID_CNFROAMINGMODE,
-				HFA384X_ROAMING_HOST);
-
-	if (local->func->set_rid(dev, HFA384X_RID_SCANREQUEST, &scan_req,
-				 sizeof(scan_req))) {
-		printk(KERN_DEBUG "SCANREQUEST failed\n");
-		ret = -EINVAL;
-	}
-
-	if (!local->host_roaming)
-		hostap_set_word(dev, HFA384X_RID_CNFROAMINGMODE,
-				HFA384X_ROAMING_FIRMWARE);
-
-	return ret;
-}
-
-#else /* !PRISM2_NO_STATION_MODES */
-
-static inline int prism2_request_hostscan(struct net_device *dev,
-					  u8 *ssid, u8 ssid_len)
-{
-	return -EOPNOTSUPP;
-}
-
-
-static inline int prism2_request_scan(struct net_device *dev)
-{
-	return -EOPNOTSUPP;
-}
-
-#endif /* !PRISM2_NO_STATION_MODES */
-
-
-static int prism2_ioctl_siwscan(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
-{
-	struct iw_point *data = &wrqu->data;
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int ret;
-	u8 *ssid = NULL, ssid_len = 0;
-	struct iw_scan_req *req = (struct iw_scan_req *) extra;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (data->length < sizeof(struct iw_scan_req))
-		req = NULL;
-
-	if (local->iw_mode == IW_MODE_MASTER) {
-		/* In master mode, we just return the results of our local
-		 * tables, so we don't need to start anything...
-		 * Jean II */
-		data->length = 0;
-		return 0;
-	}
-
-	if (!local->dev_enabled)
-		return -ENETDOWN;
-
-	if (req && data->flags & IW_SCAN_THIS_ESSID) {
-		ssid = req->essid;
-		ssid_len = req->essid_len;
-
-		if (ssid_len &&
-		    ((local->iw_mode != IW_MODE_INFRA &&
-		      local->iw_mode != IW_MODE_ADHOC) ||
-		     (local->sta_fw_ver < PRISM2_FW_VER(1,3,1))))
-			return -EOPNOTSUPP;
-	}
-
-	if (local->sta_fw_ver >= PRISM2_FW_VER(1,3,1))
-		ret = prism2_request_hostscan(dev, ssid, ssid_len);
-	else
-		ret = prism2_request_scan(dev);
-
-	if (ret == 0)
-		local->scan_timestamp = jiffies;
-
-	/* Could inquire F101, F103 or wait for SIOCGIWSCAN and read RID */
-
-	return ret;
-}
-
-
-#ifndef PRISM2_NO_STATION_MODES
-static char * __prism2_translate_scan(local_info_t *local,
-				      struct iw_request_info *info,
-				      struct hfa384x_hostscan_result *scan,
-				      struct hostap_bss_info *bss,
-				      char *current_ev, char *end_buf)
-{
-	int i, chan;
-	struct iw_event iwe;
-	char *current_val;
-	u16 capabilities;
-	u8 *pos;
-	u8 *ssid, *bssid;
-	size_t ssid_len;
-	char *buf;
-
-	if (bss) {
-		ssid = bss->ssid;
-		ssid_len = bss->ssid_len;
-		bssid = bss->bssid;
-	} else {
-		ssid = scan->ssid;
-		ssid_len = le16_to_cpu(scan->ssid_len);
-		bssid = scan->bssid;
-	}
-	if (ssid_len > 32)
-		ssid_len = 32;
-
-	/* First entry *MUST* be the AP MAC address */
-	memset(&iwe, 0, sizeof(iwe));
-	iwe.cmd = SIOCGIWAP;
-	iwe.u.ap_addr.sa_family = ARPHRD_ETHER;
-	memcpy(iwe.u.ap_addr.sa_data, bssid, ETH_ALEN);
-	current_ev = iwe_stream_add_event(info, current_ev, end_buf, &iwe,
-					  IW_EV_ADDR_LEN);
-
-	/* Other entries will be displayed in the order we give them */
-
-	memset(&iwe, 0, sizeof(iwe));
-	iwe.cmd = SIOCGIWESSID;
-	iwe.u.data.length = ssid_len;
-	iwe.u.data.flags = 1;
-	current_ev = iwe_stream_add_point(info, current_ev, end_buf,
-					  &iwe, ssid);
-
-	memset(&iwe, 0, sizeof(iwe));
-	iwe.cmd = SIOCGIWMODE;
-	if (bss) {
-		capabilities = bss->capab_info;
-	} else {
-		capabilities = le16_to_cpu(scan->capability);
-	}
-	if (capabilities & (WLAN_CAPABILITY_ESS |
-			    WLAN_CAPABILITY_IBSS)) {
-		if (capabilities & WLAN_CAPABILITY_ESS)
-			iwe.u.mode = IW_MODE_MASTER;
-		else
-			iwe.u.mode = IW_MODE_ADHOC;
-		current_ev = iwe_stream_add_event(info, current_ev, end_buf,
-						  &iwe, IW_EV_UINT_LEN);
-	}
-
-	memset(&iwe, 0, sizeof(iwe));
-	iwe.cmd = SIOCGIWFREQ;
-	if (scan) {
-		chan = le16_to_cpu(scan->chid);
-	} else if (bss) {
-		chan = bss->chan;
-	} else {
-		chan = 0;
-	}
-
-	if (chan > 0) {
-		iwe.u.freq.m = freq_list[chan - 1] * 100000;
-		iwe.u.freq.e = 1;
-		current_ev = iwe_stream_add_event(info, current_ev, end_buf,
-						  &iwe, IW_EV_FREQ_LEN);
-	}
-
-	if (scan) {
-		memset(&iwe, 0, sizeof(iwe));
-		iwe.cmd = IWEVQUAL;
-		if (local->last_scan_type == PRISM2_HOSTSCAN) {
-			iwe.u.qual.level = le16_to_cpu(scan->sl);
-			iwe.u.qual.noise = le16_to_cpu(scan->anl);
-		} else {
-			iwe.u.qual.level =
-				HFA384X_LEVEL_TO_dBm(le16_to_cpu(scan->sl));
-			iwe.u.qual.noise =
-				HFA384X_LEVEL_TO_dBm(le16_to_cpu(scan->anl));
-		}
-		iwe.u.qual.updated = IW_QUAL_LEVEL_UPDATED
-			| IW_QUAL_NOISE_UPDATED
-			| IW_QUAL_QUAL_INVALID
-			| IW_QUAL_DBM;
-		current_ev = iwe_stream_add_event(info, current_ev, end_buf,
-						  &iwe, IW_EV_QUAL_LEN);
-	}
-
-	memset(&iwe, 0, sizeof(iwe));
-	iwe.cmd = SIOCGIWENCODE;
-	if (capabilities & WLAN_CAPABILITY_PRIVACY)
-		iwe.u.data.flags = IW_ENCODE_ENABLED | IW_ENCODE_NOKEY;
-	else
-		iwe.u.data.flags = IW_ENCODE_DISABLED;
-	iwe.u.data.length = 0;
-	current_ev = iwe_stream_add_point(info, current_ev, end_buf, &iwe, "");
-
-	/* TODO: add SuppRates into BSS table */
-	if (scan) {
-		memset(&iwe, 0, sizeof(iwe));
-		iwe.cmd = SIOCGIWRATE;
-		current_val = current_ev + iwe_stream_lcp_len(info);
-		pos = scan->sup_rates;
-		for (i = 0; i < sizeof(scan->sup_rates); i++) {
-			if (pos[i] == 0)
-				break;
-			/* Bit rate given in 500 kb/s units (+ 0x80) */
-			iwe.u.bitrate.value = ((pos[i] & 0x7f) * 500000);
-			current_val = iwe_stream_add_value(
-				info, current_ev, current_val, end_buf, &iwe,
-				IW_EV_PARAM_LEN);
-		}
-		/* Check if we added any event */
-		if ((current_val - current_ev) > iwe_stream_lcp_len(info))
-			current_ev = current_val;
-	}
-
-	/* TODO: add BeaconInt,resp_rate,atim into BSS table */
-	buf = kmalloc(MAX_WPA_IE_LEN * 2 + 30, GFP_ATOMIC);
-	if (buf && scan) {
-		memset(&iwe, 0, sizeof(iwe));
-		iwe.cmd = IWEVCUSTOM;
-		sprintf(buf, "bcn_int=%d", le16_to_cpu(scan->beacon_interval));
-		iwe.u.data.length = strlen(buf);
-		current_ev = iwe_stream_add_point(info, current_ev, end_buf,
-						  &iwe, buf);
-
-		memset(&iwe, 0, sizeof(iwe));
-		iwe.cmd = IWEVCUSTOM;
-		sprintf(buf, "resp_rate=%d", le16_to_cpu(scan->rate));
-		iwe.u.data.length = strlen(buf);
-		current_ev = iwe_stream_add_point(info, current_ev, end_buf,
-						  &iwe, buf);
-
-		if (local->last_scan_type == PRISM2_HOSTSCAN &&
-		    (capabilities & WLAN_CAPABILITY_IBSS)) {
-			memset(&iwe, 0, sizeof(iwe));
-			iwe.cmd = IWEVCUSTOM;
-			sprintf(buf, "atim=%d", le16_to_cpu(scan->atim));
-			iwe.u.data.length = strlen(buf);
-			current_ev = iwe_stream_add_point(info, current_ev,
-							  end_buf, &iwe, buf);
-		}
-	}
-	kfree(buf);
-
-	if (bss && bss->wpa_ie_len > 0 && bss->wpa_ie_len <= MAX_WPA_IE_LEN) {
-		memset(&iwe, 0, sizeof(iwe));
-		iwe.cmd = IWEVGENIE;
-		iwe.u.data.length = bss->wpa_ie_len;
-		current_ev = iwe_stream_add_point(info, current_ev, end_buf,
-						  &iwe, bss->wpa_ie);
-	}
-
-	if (bss && bss->rsn_ie_len > 0 && bss->rsn_ie_len <= MAX_WPA_IE_LEN) {
-		memset(&iwe, 0, sizeof(iwe));
-		iwe.cmd = IWEVGENIE;
-		iwe.u.data.length = bss->rsn_ie_len;
-		current_ev = iwe_stream_add_point(info, current_ev, end_buf,
-						  &iwe, bss->rsn_ie);
-	}
-
-	return current_ev;
-}
-
-
-/* Translate scan data returned from the card to a card independent
- * format that the Wireless Tools will understand - Jean II */
-static inline int prism2_translate_scan(local_info_t *local,
-					struct iw_request_info *info,
-					char *buffer, int buflen)
-{
-	struct hfa384x_hostscan_result *scan;
-	int entry;
-	char *current_ev = buffer;
-	char *end_buf = buffer + buflen;
-	struct list_head *ptr;
-
-	spin_lock_bh(&local->lock);
-
-	list_for_each(ptr, &local->bss_list) {
-		struct hostap_bss_info *bss;
-		bss = list_entry(ptr, struct hostap_bss_info, list);
-		bss->included = 0;
-	}
-
-	for (entry = 0; entry < local->last_scan_results_count; entry++) {
-		int found = 0;
-		scan = &local->last_scan_results[entry];
-
-		/* Report every SSID if the AP is using multiple SSIDs. If no
-		 * BSS record is found (e.g., when WPA mode is disabled),
-		 * report the AP once. */
-		list_for_each(ptr, &local->bss_list) {
-			struct hostap_bss_info *bss;
-			bss = list_entry(ptr, struct hostap_bss_info, list);
-			if (ether_addr_equal(bss->bssid, scan->bssid)) {
-				bss->included = 1;
-				current_ev = __prism2_translate_scan(
-					local, info, scan, bss, current_ev,
-					end_buf);
-				found++;
-			}
-		}
-		if (!found) {
-			current_ev = __prism2_translate_scan(
-				local, info, scan, NULL, current_ev, end_buf);
-		}
-		/* Check if there is space for one more entry */
-		if ((end_buf - current_ev) <= IW_EV_ADDR_LEN) {
-			/* Ask user space to try again with a bigger buffer */
-			spin_unlock_bh(&local->lock);
-			return -E2BIG;
-		}
-	}
-
-	/* Prism2 firmware has limits (32 at least in some versions) for number
-	 * of BSSes in scan results. Extend this limit by using local BSS list.
-	 */
-	list_for_each(ptr, &local->bss_list) {
-		struct hostap_bss_info *bss;
-		bss = list_entry(ptr, struct hostap_bss_info, list);
-		if (bss->included)
-			continue;
-		current_ev = __prism2_translate_scan(local, info, NULL, bss,
-						     current_ev, end_buf);
-		/* Check if there is space for one more entry */
-		if ((end_buf - current_ev) <= IW_EV_ADDR_LEN) {
-			/* Ask user space to try again with a bigger buffer */
-			spin_unlock_bh(&local->lock);
-			return -E2BIG;
-		}
-	}
-
-	spin_unlock_bh(&local->lock);
-
-	return current_ev - buffer;
-}
-#endif /* PRISM2_NO_STATION_MODES */
-
-
-static inline int prism2_ioctl_giwscan_sta(struct net_device *dev,
-					   struct iw_request_info *info,
-					   struct iw_point *data, char *extra)
-{
-#ifdef PRISM2_NO_STATION_MODES
-	return -EOPNOTSUPP;
-#else /* PRISM2_NO_STATION_MODES */
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int res;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	/* Wait until the scan is finished. We can probably do better
-	 * than that - Jean II */
-	if (local->scan_timestamp &&
-	    time_before(jiffies, local->scan_timestamp + 3 * HZ)) {
-		/* Important note : we don't want to block the caller
-		 * until results are ready for various reasons.
-		 * First, managing wait queues is complex and racy
-		 * (there may be multiple simultaneous callers).
-		 * Second, we grab some rtnetlink lock before coming
-		 * here (in dev_ioctl()).
-		 * Third, the caller can wait on the Wireless Event
-		 * - Jean II */
-		return -EAGAIN;
-	}
-	local->scan_timestamp = 0;
-
-	res = prism2_translate_scan(local, info, extra, data->length);
-
-	if (res >= 0) {
-		data->length = res;
-		return 0;
-	} else {
-		data->length = 0;
-		return res;
-	}
-#endif /* PRISM2_NO_STATION_MODES */
-}
-
-
-static int prism2_ioctl_giwscan(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
-{
-	struct iw_point *data = &wrqu->data;
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int res;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (local->iw_mode == IW_MODE_MASTER) {
-		/* In MASTER mode, it doesn't make sense to go around
-		 * scanning the frequencies and make the stations we serve
-		 * wait when what the user is really interested about is the
-		 * list of stations and access points we are talking to.
-		 * So, just extract results from our cache...
-		 * Jean II */
-
-		/* Translate to WE format */
-		res = prism2_ap_translate_scan(dev, info, extra);
-		if (res >= 0) {
-			printk(KERN_DEBUG "Scan result translation succeeded "
-			       "(length=%d)\n", res);
-			data->length = res;
-			return 0;
-		} else {
-			printk(KERN_DEBUG
-			       "Scan result translation failed (res=%d)\n",
-			       res);
-			data->length = 0;
-			return res;
-		}
-	} else {
-		/* Station mode */
-		return prism2_ioctl_giwscan_sta(dev, info, data, extra);
-	}
-}
-
-
-static const struct iw_priv_args prism2_priv[] = {
-	{ PRISM2_IOCTL_MONITOR,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "monitor" },
-	{ PRISM2_IOCTL_READMIF,
-	  IW_PRIV_TYPE_BYTE | IW_PRIV_SIZE_FIXED | 1,
-	  IW_PRIV_TYPE_BYTE | IW_PRIV_SIZE_FIXED | 1, "readmif" },
-	{ PRISM2_IOCTL_WRITEMIF,
-	  IW_PRIV_TYPE_BYTE | IW_PRIV_SIZE_FIXED | 2, 0, "writemif" },
-	{ PRISM2_IOCTL_RESET,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "reset" },
-	{ PRISM2_IOCTL_INQUIRE,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "inquire" },
-	{ PRISM2_IOCTL_SET_RID_WORD,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 2, 0, "set_rid_word" },
-	{ PRISM2_IOCTL_MACCMD,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "maccmd" },
-	{ PRISM2_IOCTL_WDS_ADD,
-	  IW_PRIV_TYPE_ADDR | IW_PRIV_SIZE_FIXED | 1, 0, "wds_add" },
-	{ PRISM2_IOCTL_WDS_DEL,
-	  IW_PRIV_TYPE_ADDR | IW_PRIV_SIZE_FIXED | 1, 0, "wds_del" },
-	{ PRISM2_IOCTL_ADDMAC,
-	  IW_PRIV_TYPE_ADDR | IW_PRIV_SIZE_FIXED | 1, 0, "addmac" },
-	{ PRISM2_IOCTL_DELMAC,
-	  IW_PRIV_TYPE_ADDR | IW_PRIV_SIZE_FIXED | 1, 0, "delmac" },
-	{ PRISM2_IOCTL_KICKMAC,
-	  IW_PRIV_TYPE_ADDR | IW_PRIV_SIZE_FIXED | 1, 0, "kickmac" },
-	/* --- raw access to sub-ioctls --- */
-	{ PRISM2_IOCTL_PRISM2_PARAM,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 2, 0, "prism2_param" },
-	{ PRISM2_IOCTL_GET_PRISM2_PARAM,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getprism2_param" },
-	/* --- sub-ioctls handlers --- */
-	{ PRISM2_IOCTL_PRISM2_PARAM,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "" },
-	{ PRISM2_IOCTL_GET_PRISM2_PARAM,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "" },
-	/* --- sub-ioctls definitions --- */
-	{ PRISM2_PARAM_TXRATECTRL,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "txratectrl" },
-	{ PRISM2_PARAM_TXRATECTRL,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "gettxratectrl" },
-	{ PRISM2_PARAM_BEACON_INT,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "beacon_int" },
-	{ PRISM2_PARAM_BEACON_INT,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getbeacon_int" },
-#ifndef PRISM2_NO_STATION_MODES
-	{ PRISM2_PARAM_PSEUDO_IBSS,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "pseudo_ibss" },
-	{ PRISM2_PARAM_PSEUDO_IBSS,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getpseudo_ibss" },
-#endif /* PRISM2_NO_STATION_MODES */
-	{ PRISM2_PARAM_ALC,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "alc" },
-	{ PRISM2_PARAM_ALC,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getalc" },
-	{ PRISM2_PARAM_DUMP,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "dump" },
-	{ PRISM2_PARAM_DUMP,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getdump" },
-	{ PRISM2_PARAM_OTHER_AP_POLICY,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "other_ap_policy" },
-	{ PRISM2_PARAM_OTHER_AP_POLICY,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getother_ap_pol" },
-	{ PRISM2_PARAM_AP_MAX_INACTIVITY,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "max_inactivity" },
-	{ PRISM2_PARAM_AP_MAX_INACTIVITY,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getmax_inactivi" },
-	{ PRISM2_PARAM_AP_BRIDGE_PACKETS,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "bridge_packets" },
-	{ PRISM2_PARAM_AP_BRIDGE_PACKETS,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getbridge_packe" },
-	{ PRISM2_PARAM_DTIM_PERIOD,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "dtim_period" },
-	{ PRISM2_PARAM_DTIM_PERIOD,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getdtim_period" },
-	{ PRISM2_PARAM_AP_NULLFUNC_ACK,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "nullfunc_ack" },
-	{ PRISM2_PARAM_AP_NULLFUNC_ACK,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getnullfunc_ack" },
-	{ PRISM2_PARAM_MAX_WDS,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "max_wds" },
-	{ PRISM2_PARAM_MAX_WDS,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getmax_wds" },
-	{ PRISM2_PARAM_AP_AUTOM_AP_WDS,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "autom_ap_wds" },
-	{ PRISM2_PARAM_AP_AUTOM_AP_WDS,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getautom_ap_wds" },
-	{ PRISM2_PARAM_AP_AUTH_ALGS,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "ap_auth_algs" },
-	{ PRISM2_PARAM_AP_AUTH_ALGS,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getap_auth_algs" },
-	{ PRISM2_PARAM_MONITOR_ALLOW_FCSERR,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "allow_fcserr" },
-	{ PRISM2_PARAM_MONITOR_ALLOW_FCSERR,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getallow_fcserr" },
-	{ PRISM2_PARAM_HOST_ENCRYPT,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "host_encrypt" },
-	{ PRISM2_PARAM_HOST_ENCRYPT,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "gethost_encrypt" },
-	{ PRISM2_PARAM_HOST_DECRYPT,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "host_decrypt" },
-	{ PRISM2_PARAM_HOST_DECRYPT,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "gethost_decrypt" },
-#ifndef PRISM2_NO_STATION_MODES
-	{ PRISM2_PARAM_HOST_ROAMING,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "host_roaming" },
-	{ PRISM2_PARAM_HOST_ROAMING,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "gethost_roaming" },
-#endif /* PRISM2_NO_STATION_MODES */
-	{ PRISM2_PARAM_BCRX_STA_KEY,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "bcrx_sta_key" },
-	{ PRISM2_PARAM_BCRX_STA_KEY,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getbcrx_sta_key" },
-	{ PRISM2_PARAM_IEEE_802_1X,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "ieee_802_1x" },
-	{ PRISM2_PARAM_IEEE_802_1X,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getieee_802_1x" },
-	{ PRISM2_PARAM_ANTSEL_TX,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "antsel_tx" },
-	{ PRISM2_PARAM_ANTSEL_TX,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getantsel_tx" },
-	{ PRISM2_PARAM_ANTSEL_RX,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "antsel_rx" },
-	{ PRISM2_PARAM_ANTSEL_RX,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getantsel_rx" },
-	{ PRISM2_PARAM_MONITOR_TYPE,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "monitor_type" },
-	{ PRISM2_PARAM_MONITOR_TYPE,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getmonitor_type" },
-	{ PRISM2_PARAM_WDS_TYPE,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "wds_type" },
-	{ PRISM2_PARAM_WDS_TYPE,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getwds_type" },
-	{ PRISM2_PARAM_HOSTSCAN,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "hostscan" },
-	{ PRISM2_PARAM_HOSTSCAN,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "gethostscan" },
-	{ PRISM2_PARAM_AP_SCAN,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "ap_scan" },
-	{ PRISM2_PARAM_AP_SCAN,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getap_scan" },
-	{ PRISM2_PARAM_ENH_SEC,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "enh_sec" },
-	{ PRISM2_PARAM_ENH_SEC,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getenh_sec" },
-#ifdef PRISM2_IO_DEBUG
-	{ PRISM2_PARAM_IO_DEBUG,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "io_debug" },
-	{ PRISM2_PARAM_IO_DEBUG,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getio_debug" },
-#endif /* PRISM2_IO_DEBUG */
-	{ PRISM2_PARAM_BASIC_RATES,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "basic_rates" },
-	{ PRISM2_PARAM_BASIC_RATES,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getbasic_rates" },
-	{ PRISM2_PARAM_OPER_RATES,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "oper_rates" },
-	{ PRISM2_PARAM_OPER_RATES,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getoper_rates" },
-	{ PRISM2_PARAM_HOSTAPD,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "hostapd" },
-	{ PRISM2_PARAM_HOSTAPD,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "gethostapd" },
-	{ PRISM2_PARAM_HOSTAPD_STA,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "hostapd_sta" },
-	{ PRISM2_PARAM_HOSTAPD_STA,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "gethostapd_sta" },
-	{ PRISM2_PARAM_WPA,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "wpa" },
-	{ PRISM2_PARAM_WPA,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getwpa" },
-	{ PRISM2_PARAM_PRIVACY_INVOKED,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "privacy_invoked" },
-	{ PRISM2_PARAM_PRIVACY_INVOKED,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getprivacy_invo" },
-	{ PRISM2_PARAM_TKIP_COUNTERMEASURES,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "tkip_countermea" },
-	{ PRISM2_PARAM_TKIP_COUNTERMEASURES,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "gettkip_counter" },
-	{ PRISM2_PARAM_DROP_UNENCRYPTED,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "drop_unencrypte" },
-	{ PRISM2_PARAM_DROP_UNENCRYPTED,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getdrop_unencry" },
-	{ PRISM2_PARAM_SCAN_CHANNEL_MASK,
-	  IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "scan_channels" },
-	{ PRISM2_PARAM_SCAN_CHANNEL_MASK,
-	  0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getscan_channel" },
-};
-
-
-static int prism2_ioctl_priv_prism2_param(struct net_device *dev,
-					  struct iw_request_info *info,
-					  union iwreq_data *uwrq, char *extra)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int *i = (int *) extra;
-	int param = *i;
-	int value = *(i + 1);
-	int ret = 0;
-	u16 val;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	switch (param) {
-	case PRISM2_PARAM_TXRATECTRL:
-		local->fw_tx_rate_control = value;
-		break;
-
-	case PRISM2_PARAM_BEACON_INT:
-		if (hostap_set_word(dev, HFA384X_RID_CNFBEACONINT, value) ||
-		    local->func->reset_port(dev))
-			ret = -EINVAL;
-		else
-			local->beacon_int = value;
-		break;
-
-#ifndef PRISM2_NO_STATION_MODES
-	case PRISM2_PARAM_PSEUDO_IBSS:
-		if (value == local->pseudo_adhoc)
-			break;
-
-		if (value != 0 && value != 1) {
-			ret = -EINVAL;
-			break;
-		}
-
-		printk(KERN_DEBUG "prism2: %s: pseudo IBSS change %d -> %d\n",
-		       dev->name, local->pseudo_adhoc, value);
-		local->pseudo_adhoc = value;
-		if (local->iw_mode != IW_MODE_ADHOC)
-			break;
-
-		if (hostap_set_word(dev, HFA384X_RID_CNFPORTTYPE,
-				    hostap_get_porttype(local))) {
-			ret = -EOPNOTSUPP;
-			break;
-		}
-
-		if (local->func->reset_port(dev))
-			ret = -EINVAL;
-		break;
-#endif /* PRISM2_NO_STATION_MODES */
-
-	case PRISM2_PARAM_ALC:
-		printk(KERN_DEBUG "%s: %s ALC\n", dev->name,
-		       value == 0 ? "Disabling" : "Enabling");
-		val = HFA384X_TEST_CFG_BIT_ALC;
-		local->func->cmd(dev, HFA384X_CMDCODE_TEST |
-				 (HFA384X_TEST_CFG_BITS << 8),
-				 value == 0 ? 0 : 1, &val, NULL);
-		break;
-
-	case PRISM2_PARAM_DUMP:
-		local->frame_dump = value;
-		break;
-
-	case PRISM2_PARAM_OTHER_AP_POLICY:
-		if (value < 0 || value > 3) {
-			ret = -EINVAL;
-			break;
-		}
-		if (local->ap != NULL)
-			local->ap->ap_policy = value;
-		break;
-
-	case PRISM2_PARAM_AP_MAX_INACTIVITY:
-		if (value < 0 || value > 7 * 24 * 60 * 60) {
-			ret = -EINVAL;
-			break;
-		}
-		if (local->ap != NULL)
-			local->ap->max_inactivity = value * HZ;
-		break;
-
-	case PRISM2_PARAM_AP_BRIDGE_PACKETS:
-		if (local->ap != NULL)
-			local->ap->bridge_packets = value;
-		break;
-
-	case PRISM2_PARAM_DTIM_PERIOD:
-		if (value < 0 || value > 65535) {
-			ret = -EINVAL;
-			break;
-		}
-		if (hostap_set_word(dev, HFA384X_RID_CNFOWNDTIMPERIOD, value)
-		    || local->func->reset_port(dev))
-			ret = -EINVAL;
-		else
-			local->dtim_period = value;
-		break;
-
-	case PRISM2_PARAM_AP_NULLFUNC_ACK:
-		if (local->ap != NULL)
-			local->ap->nullfunc_ack = value;
-		break;
-
-	case PRISM2_PARAM_MAX_WDS:
-		local->wds_max_connections = value;
-		break;
-
-	case PRISM2_PARAM_AP_AUTOM_AP_WDS:
-		if (local->ap != NULL) {
-			if (!local->ap->autom_ap_wds && value) {
-				/* add WDS link to all APs in STA table */
-				hostap_add_wds_links(local);
-			}
-			local->ap->autom_ap_wds = value;
-		}
-		break;
-
-	case PRISM2_PARAM_AP_AUTH_ALGS:
-		local->auth_algs = value;
-		if (hostap_set_auth_algs(local))
-			ret = -EINVAL;
-		break;
-
-	case PRISM2_PARAM_MONITOR_ALLOW_FCSERR:
-		local->monitor_allow_fcserr = value;
-		break;
-
-	case PRISM2_PARAM_HOST_ENCRYPT:
-		local->host_encrypt = value;
-		if (hostap_set_encryption(local) ||
-		    local->func->reset_port(dev))
-			ret = -EINVAL;
-		break;
-
-	case PRISM2_PARAM_HOST_DECRYPT:
-		local->host_decrypt = value;
-		if (hostap_set_encryption(local) ||
-		    local->func->reset_port(dev))
-			ret = -EINVAL;
-		break;
-
-#ifndef PRISM2_NO_STATION_MODES
-	case PRISM2_PARAM_HOST_ROAMING:
-		if (value < 0 || value > 2) {
-			ret = -EINVAL;
-			break;
-		}
-		local->host_roaming = value;
-		if (hostap_set_roaming(local) || local->func->reset_port(dev))
-			ret = -EINVAL;
-		break;
-#endif /* PRISM2_NO_STATION_MODES */
-
-	case PRISM2_PARAM_BCRX_STA_KEY:
-		local->bcrx_sta_key = value;
-		break;
-
-	case PRISM2_PARAM_IEEE_802_1X:
-		local->ieee_802_1x = value;
-		break;
-
-	case PRISM2_PARAM_ANTSEL_TX:
-		if (value < 0 || value > HOSTAP_ANTSEL_HIGH) {
-			ret = -EINVAL;
-			break;
-		}
-		local->antsel_tx = value;
-		hostap_set_antsel(local);
-		break;
-
-	case PRISM2_PARAM_ANTSEL_RX:
-		if (value < 0 || value > HOSTAP_ANTSEL_HIGH) {
-			ret = -EINVAL;
-			break;
-		}
-		local->antsel_rx = value;
-		hostap_set_antsel(local);
-		break;
-
-	case PRISM2_PARAM_MONITOR_TYPE:
-		if (value != PRISM2_MONITOR_80211 &&
-		    value != PRISM2_MONITOR_CAPHDR &&
-		    value != PRISM2_MONITOR_PRISM &&
-		    value != PRISM2_MONITOR_RADIOTAP) {
-			ret = -EINVAL;
-			break;
-		}
-		local->monitor_type = value;
-		if (local->iw_mode == IW_MODE_MONITOR)
-			hostap_monitor_set_type(local);
-		break;
-
-	case PRISM2_PARAM_WDS_TYPE:
-		local->wds_type = value;
-		break;
-
-	case PRISM2_PARAM_HOSTSCAN:
-	{
-		struct hfa384x_hostscan_request scan_req;
-		u16 rate;
-
-		memset(&scan_req, 0, sizeof(scan_req));
-		scan_req.channel_list = cpu_to_le16(0x3fff);
-		switch (value) {
-		case 1: rate = HFA384X_RATES_1MBPS; break;
-		case 2: rate = HFA384X_RATES_2MBPS; break;
-		case 3: rate = HFA384X_RATES_5MBPS; break;
-		case 4: rate = HFA384X_RATES_11MBPS; break;
-		default: rate = HFA384X_RATES_1MBPS; break;
-		}
-		scan_req.txrate = cpu_to_le16(rate);
-		/* leave SSID empty to accept all SSIDs */
-
-		if (local->iw_mode == IW_MODE_MASTER) {
-			if (hostap_set_word(dev, HFA384X_RID_CNFPORTTYPE,
-					    HFA384X_PORTTYPE_BSS) ||
-			    local->func->reset_port(dev))
-				printk(KERN_DEBUG "Leaving Host AP mode "
-				       "for HostScan failed\n");
-		}
-
-		if (local->func->set_rid(dev, HFA384X_RID_HOSTSCAN, &scan_req,
-					 sizeof(scan_req))) {
-			printk(KERN_DEBUG "HOSTSCAN failed\n");
-			ret = -EINVAL;
-		}
-		if (local->iw_mode == IW_MODE_MASTER) {
-			wait_queue_entry_t __wait;
-			init_waitqueue_entry(&__wait, current);
-			add_wait_queue(&local->hostscan_wq, &__wait);
-			set_current_state(TASK_INTERRUPTIBLE);
-			schedule_timeout(HZ);
-			if (signal_pending(current))
-				ret = -EINTR;
-			set_current_state(TASK_RUNNING);
-			remove_wait_queue(&local->hostscan_wq, &__wait);
-
-			if (hostap_set_word(dev, HFA384X_RID_CNFPORTTYPE,
-					    HFA384X_PORTTYPE_HOSTAP) ||
-			    local->func->reset_port(dev))
-				printk(KERN_DEBUG "Returning to Host AP mode "
-				       "after HostScan failed\n");
-		}
-		break;
-	}
-
-	case PRISM2_PARAM_AP_SCAN:
-		local->passive_scan_interval = value;
-		if (timer_pending(&local->passive_scan_timer))
-			del_timer(&local->passive_scan_timer);
-		if (value > 0 && value < INT_MAX / HZ) {
-			local->passive_scan_timer.expires = jiffies +
-				local->passive_scan_interval * HZ;
-			add_timer(&local->passive_scan_timer);
-		}
-		break;
-
-	case PRISM2_PARAM_ENH_SEC:
-		if (value < 0 || value > 3) {
-			ret = -EINVAL;
-			break;
-		}
-		local->enh_sec = value;
-		if (hostap_set_word(dev, HFA384X_RID_CNFENHSECURITY,
-				    local->enh_sec) ||
-		    local->func->reset_port(dev)) {
-			printk(KERN_INFO "%s: cnfEnhSecurity requires STA f/w "
-			       "1.6.3 or newer\n", dev->name);
-			ret = -EOPNOTSUPP;
-		}
-		break;
-
-#ifdef PRISM2_IO_DEBUG
-	case PRISM2_PARAM_IO_DEBUG:
-		local->io_debug_enabled = value;
-		break;
-#endif /* PRISM2_IO_DEBUG */
-
-	case PRISM2_PARAM_BASIC_RATES:
-		if ((value & local->tx_rate_control) != value || value == 0) {
-			printk(KERN_INFO "%s: invalid basic rate set - basic "
-			       "rates must be in supported rate set\n",
-			       dev->name);
-			ret = -EINVAL;
-			break;
-		}
-		local->basic_rates = value;
-		if (hostap_set_word(dev, HFA384X_RID_CNFBASICRATES,
-				    local->basic_rates) ||
-		    local->func->reset_port(dev))
-			ret = -EINVAL;
-		break;
-
-	case PRISM2_PARAM_OPER_RATES:
-		local->tx_rate_control = value;
-		if (hostap_set_rate(dev))
-			ret = -EINVAL;
-		break;
-
-	case PRISM2_PARAM_HOSTAPD:
-		ret = hostap_set_hostapd(local, value, 1);
-		break;
-
-	case PRISM2_PARAM_HOSTAPD_STA:
-		ret = hostap_set_hostapd_sta(local, value, 1);
-		break;
-
-	case PRISM2_PARAM_WPA:
-		local->wpa = value;
-		if (local->sta_fw_ver < PRISM2_FW_VER(1,7,0))
-			ret = -EOPNOTSUPP;
-		else if (hostap_set_word(dev, HFA384X_RID_SSNHANDLINGMODE,
-					 value ? 1 : 0))
-			ret = -EINVAL;
-		break;
-
-	case PRISM2_PARAM_PRIVACY_INVOKED:
-		local->privacy_invoked = value;
-		if (hostap_set_encryption(local) ||
-		    local->func->reset_port(dev))
-			ret = -EINVAL;
-		break;
-
-	case PRISM2_PARAM_TKIP_COUNTERMEASURES:
-		local->tkip_countermeasures = value;
-		break;
-
-	case PRISM2_PARAM_DROP_UNENCRYPTED:
-		local->drop_unencrypted = value;
-		break;
-
-	case PRISM2_PARAM_SCAN_CHANNEL_MASK:
-		local->scan_channel_mask = value;
-		break;
-
-	default:
-		printk(KERN_DEBUG "%s: prism2_param: unknown param %d\n",
-		       dev->name, param);
-		ret = -EOPNOTSUPP;
-		break;
-	}
-
-	return ret;
-}
-
-
-static int prism2_ioctl_priv_get_prism2_param(struct net_device *dev,
-					      struct iw_request_info *info,
-					      union iwreq_data *wrqu, char *extra)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int *param = (int *) extra;
-	int ret = 0;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	switch (*param) {
-	case PRISM2_PARAM_TXRATECTRL:
-		*param = local->fw_tx_rate_control;
-		break;
-
-	case PRISM2_PARAM_BEACON_INT:
-		*param = local->beacon_int;
-		break;
-
-	case PRISM2_PARAM_PSEUDO_IBSS:
-		*param = local->pseudo_adhoc;
-		break;
-
-	case PRISM2_PARAM_ALC:
-		ret = -EOPNOTSUPP; /* FIX */
-		break;
-
-	case PRISM2_PARAM_DUMP:
-		*param = local->frame_dump;
-		break;
-
-	case PRISM2_PARAM_OTHER_AP_POLICY:
-		if (local->ap != NULL)
-			*param = local->ap->ap_policy;
-		else
-			ret = -EOPNOTSUPP;
-		break;
-
-	case PRISM2_PARAM_AP_MAX_INACTIVITY:
-		if (local->ap != NULL)
-			*param = local->ap->max_inactivity / HZ;
-		else
-			ret = -EOPNOTSUPP;
-		break;
-
-	case PRISM2_PARAM_AP_BRIDGE_PACKETS:
-		if (local->ap != NULL)
-			*param = local->ap->bridge_packets;
-		else
-			ret = -EOPNOTSUPP;
-		break;
-
-	case PRISM2_PARAM_DTIM_PERIOD:
-		*param = local->dtim_period;
-		break;
-
-	case PRISM2_PARAM_AP_NULLFUNC_ACK:
-		if (local->ap != NULL)
-			*param = local->ap->nullfunc_ack;
-		else
-			ret = -EOPNOTSUPP;
-		break;
-
-	case PRISM2_PARAM_MAX_WDS:
-		*param = local->wds_max_connections;
-		break;
-
-	case PRISM2_PARAM_AP_AUTOM_AP_WDS:
-		if (local->ap != NULL)
-			*param = local->ap->autom_ap_wds;
-		else
-			ret = -EOPNOTSUPP;
-		break;
-
-	case PRISM2_PARAM_AP_AUTH_ALGS:
-		*param = local->auth_algs;
-		break;
-
-	case PRISM2_PARAM_MONITOR_ALLOW_FCSERR:
-		*param = local->monitor_allow_fcserr;
-		break;
-
-	case PRISM2_PARAM_HOST_ENCRYPT:
-		*param = local->host_encrypt;
-		break;
-
-	case PRISM2_PARAM_HOST_DECRYPT:
-		*param = local->host_decrypt;
-		break;
-
-	case PRISM2_PARAM_HOST_ROAMING:
-		*param = local->host_roaming;
-		break;
-
-	case PRISM2_PARAM_BCRX_STA_KEY:
-		*param = local->bcrx_sta_key;
-		break;
-
-	case PRISM2_PARAM_IEEE_802_1X:
-		*param = local->ieee_802_1x;
-		break;
-
-	case PRISM2_PARAM_ANTSEL_TX:
-		*param = local->antsel_tx;
-		break;
-
-	case PRISM2_PARAM_ANTSEL_RX:
-		*param = local->antsel_rx;
-		break;
-
-	case PRISM2_PARAM_MONITOR_TYPE:
-		*param = local->monitor_type;
-		break;
-
-	case PRISM2_PARAM_WDS_TYPE:
-		*param = local->wds_type;
-		break;
-
-	case PRISM2_PARAM_HOSTSCAN:
-		ret = -EOPNOTSUPP;
-		break;
-
-	case PRISM2_PARAM_AP_SCAN:
-		*param = local->passive_scan_interval;
-		break;
-
-	case PRISM2_PARAM_ENH_SEC:
-		*param = local->enh_sec;
-		break;
-
-#ifdef PRISM2_IO_DEBUG
-	case PRISM2_PARAM_IO_DEBUG:
-		*param = local->io_debug_enabled;
-		break;
-#endif /* PRISM2_IO_DEBUG */
-
-	case PRISM2_PARAM_BASIC_RATES:
-		*param = local->basic_rates;
-		break;
-
-	case PRISM2_PARAM_OPER_RATES:
-		*param = local->tx_rate_control;
-		break;
-
-	case PRISM2_PARAM_HOSTAPD:
-		*param = local->hostapd;
-		break;
-
-	case PRISM2_PARAM_HOSTAPD_STA:
-		*param = local->hostapd_sta;
-		break;
-
-	case PRISM2_PARAM_WPA:
-		if (local->sta_fw_ver < PRISM2_FW_VER(1,7,0))
-			ret = -EOPNOTSUPP;
-		*param = local->wpa;
-		break;
-
-	case PRISM2_PARAM_PRIVACY_INVOKED:
-		*param = local->privacy_invoked;
-		break;
-
-	case PRISM2_PARAM_TKIP_COUNTERMEASURES:
-		*param = local->tkip_countermeasures;
-		break;
-
-	case PRISM2_PARAM_DROP_UNENCRYPTED:
-		*param = local->drop_unencrypted;
-		break;
-
-	case PRISM2_PARAM_SCAN_CHANNEL_MASK:
-		*param = local->scan_channel_mask;
-		break;
-
-	default:
-		printk(KERN_DEBUG "%s: get_prism2_param: unknown param %d\n",
-		       dev->name, *param);
-		ret = -EOPNOTSUPP;
-		break;
-	}
-
-	return ret;
-}
-
-
-static int prism2_ioctl_priv_readmif(struct net_device *dev,
-				     struct iw_request_info *info,
-				     union iwreq_data *wrqu, char *extra)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	u16 resp0;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (local->func->cmd(dev, HFA384X_CMDCODE_READMIF, *extra, NULL,
-			     &resp0))
-		return -EOPNOTSUPP;
-	else
-		*extra = resp0;
-
-	return 0;
-}
-
-
-static int prism2_ioctl_priv_writemif(struct net_device *dev,
-				      struct iw_request_info *info,
-				      union iwreq_data *wrqu, char *extra)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	u16 cr, val;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	cr = *extra;
-	val = *(extra + 1);
-	if (local->func->cmd(dev, HFA384X_CMDCODE_WRITEMIF, cr, &val, NULL))
-		return -EOPNOTSUPP;
-
-	return 0;
-}
-
-
-#ifdef PRISM2_DOWNLOAD_SUPPORT
-static int prism2_ioctl_priv_download(local_info_t *local, struct iw_point *p)
-{
-	struct prism2_download_param *param;
-	int ret = 0;
-
-	if (p->length < sizeof(struct prism2_download_param) ||
-	    p->length > 1024 || !p->pointer)
-		return -EINVAL;
-
-	param = memdup_user(p->pointer, p->length);
-	if (IS_ERR(param)) {
-		return PTR_ERR(param);
-	}
-
-	if (p->length < sizeof(struct prism2_download_param) +
-	    param->num_areas * sizeof(struct prism2_download_area)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	ret = local->func->download(local, param);
-
- out:
-	kfree(param);
-	return ret;
-}
-#endif /* PRISM2_DOWNLOAD_SUPPORT */
-
-
-static int prism2_set_genericelement(struct net_device *dev, u8 *elem,
-				     size_t len)
-{
-	struct hostap_interface *iface = netdev_priv(dev);
-	local_info_t *local = iface->local;
-	u8 *buf;
-
-	/*
-	 * Add 16-bit length in the beginning of the buffer because Prism2 RID
-	 * includes it.
-	 */
-	buf = kmalloc(len + 2, GFP_KERNEL);
-	if (buf == NULL)
-		return -ENOMEM;
-
-	*((__le16 *) buf) = cpu_to_le16(len);
-	memcpy(buf + 2, elem, len);
-
-	kfree(local->generic_elem);
-	local->generic_elem = buf;
-	local->generic_elem_len = len + 2;
-
-	return local->func->set_rid(local->dev, HFA384X_RID_GENERICELEMENT,
-				    buf, len + 2);
-}
-
-
-static int prism2_ioctl_siwauth(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *data = &wrqu->param;
-	struct hostap_interface *iface = netdev_priv(dev);
-	local_info_t *local = iface->local;
-
-	switch (data->flags & IW_AUTH_INDEX) {
-	case IW_AUTH_WPA_VERSION:
-	case IW_AUTH_CIPHER_PAIRWISE:
-	case IW_AUTH_CIPHER_GROUP:
-	case IW_AUTH_KEY_MGMT:
-		/*
-		 * Host AP driver does not use these parameters and allows
-		 * wpa_supplicant to control them internally.
-		 */
-		break;
-	case IW_AUTH_TKIP_COUNTERMEASURES:
-		local->tkip_countermeasures = data->value;
-		break;
-	case IW_AUTH_DROP_UNENCRYPTED:
-		local->drop_unencrypted = data->value;
-		break;
-	case IW_AUTH_80211_AUTH_ALG:
-		local->auth_algs = data->value;
-		break;
-	case IW_AUTH_WPA_ENABLED:
-		if (data->value == 0) {
-			local->wpa = 0;
-			if (local->sta_fw_ver < PRISM2_FW_VER(1,7,0))
-				break;
-			prism2_set_genericelement(dev, "", 0);
-			local->host_roaming = 0;
-			local->privacy_invoked = 0;
-			if (hostap_set_word(dev, HFA384X_RID_SSNHANDLINGMODE,
-					    0) ||
-			    hostap_set_roaming(local) ||
-			    hostap_set_encryption(local) ||
-			    local->func->reset_port(dev))
-				return -EINVAL;
-			break;
-		}
-		if (local->sta_fw_ver < PRISM2_FW_VER(1,7,0))
-			return -EOPNOTSUPP;
-		local->host_roaming = 2;
-		local->privacy_invoked = 1;
-		local->wpa = 1;
-		if (hostap_set_word(dev, HFA384X_RID_SSNHANDLINGMODE, 1) ||
-		    hostap_set_roaming(local) ||
-		    hostap_set_encryption(local) ||
-		    local->func->reset_port(dev))
-			return -EINVAL;
-		break;
-	case IW_AUTH_RX_UNENCRYPTED_EAPOL:
-		local->ieee_802_1x = data->value;
-		break;
-	case IW_AUTH_PRIVACY_INVOKED:
-		local->privacy_invoked = data->value;
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-	return 0;
-}
-
-
-static int prism2_ioctl_giwauth(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *data = &wrqu->param;
-	struct hostap_interface *iface = netdev_priv(dev);
-	local_info_t *local = iface->local;
-
-	switch (data->flags & IW_AUTH_INDEX) {
-	case IW_AUTH_WPA_VERSION:
-	case IW_AUTH_CIPHER_PAIRWISE:
-	case IW_AUTH_CIPHER_GROUP:
-	case IW_AUTH_KEY_MGMT:
-		/*
-		 * Host AP driver does not use these parameters and allows
-		 * wpa_supplicant to control them internally.
-		 */
-		return -EOPNOTSUPP;
-	case IW_AUTH_TKIP_COUNTERMEASURES:
-		data->value = local->tkip_countermeasures;
-		break;
-	case IW_AUTH_DROP_UNENCRYPTED:
-		data->value = local->drop_unencrypted;
-		break;
-	case IW_AUTH_80211_AUTH_ALG:
-		data->value = local->auth_algs;
-		break;
-	case IW_AUTH_WPA_ENABLED:
-		data->value = local->wpa;
-		break;
-	case IW_AUTH_RX_UNENCRYPTED_EAPOL:
-		data->value = local->ieee_802_1x;
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-	return 0;
-}
-
-
-static int prism2_ioctl_siwencodeext(struct net_device *dev,
-				     struct iw_request_info *info,
-				     union iwreq_data *wrqu, char *extra)
-{
-	struct iw_point *erq = &wrqu->encoding;
-	struct hostap_interface *iface = netdev_priv(dev);
-	local_info_t *local = iface->local;
-	struct iw_encode_ext *ext = (struct iw_encode_ext *) extra;
-	int i, ret = 0;
-	struct lib80211_crypto_ops *ops;
-	struct lib80211_crypt_data **crypt;
-	void *sta_ptr;
-	u8 *addr;
-	const char *alg, *module;
-
-	i = erq->flags & IW_ENCODE_INDEX;
-	if (i > WEP_KEYS)
-		return -EINVAL;
-	if (i < 1 || i > WEP_KEYS)
-		i = local->crypt_info.tx_keyidx;
-	else
-		i--;
-	if (i < 0 || i >= WEP_KEYS)
-		return -EINVAL;
-
-	addr = ext->addr.sa_data;
-	if (is_broadcast_ether_addr(addr)) {
-		sta_ptr = NULL;
-		crypt = &local->crypt_info.crypt[i];
-	} else {
-		if (i != 0)
-			return -EINVAL;
-		sta_ptr = ap_crypt_get_ptrs(local->ap, addr, 0, &crypt);
-		if (sta_ptr == NULL) {
-			if (local->iw_mode == IW_MODE_INFRA) {
-				/*
-				 * TODO: add STA entry for the current AP so
-				 * that unicast key can be used. For now, this
-				 * is emulated by using default key idx 0.
-				 */
-				i = 0;
-				crypt = &local->crypt_info.crypt[i];
-			} else
-				return -EINVAL;
-		}
-	}
-
-	if ((erq->flags & IW_ENCODE_DISABLED) ||
-	    ext->alg == IW_ENCODE_ALG_NONE) {
-		if (*crypt)
-			lib80211_crypt_delayed_deinit(&local->crypt_info, crypt);
-		goto done;
-	}
-
-	switch (ext->alg) {
-	case IW_ENCODE_ALG_WEP:
-		alg = "WEP";
-		module = "lib80211_crypt_wep";
-		break;
-	case IW_ENCODE_ALG_TKIP:
-		alg = "TKIP";
-		module = "lib80211_crypt_tkip";
-		break;
-	case IW_ENCODE_ALG_CCMP:
-		alg = "CCMP";
-		module = "lib80211_crypt_ccmp";
-		break;
-	default:
-		printk(KERN_DEBUG "%s: unsupported algorithm %d\n",
-		       local->dev->name, ext->alg);
-		ret = -EOPNOTSUPP;
-		goto done;
-	}
-
-	ops = lib80211_get_crypto_ops(alg);
-	if (ops == NULL) {
-		request_module(module);
-		ops = lib80211_get_crypto_ops(alg);
-	}
-	if (ops == NULL) {
-		printk(KERN_DEBUG "%s: unknown crypto alg '%s'\n",
-		       local->dev->name, alg);
-		ret = -EOPNOTSUPP;
-		goto done;
-	}
-
-	if (sta_ptr || ext->alg != IW_ENCODE_ALG_WEP) {
-		/*
-		 * Per station encryption and other than WEP algorithms
-		 * require host-based encryption, so force them on
-		 * automatically.
-		 */
-		local->host_decrypt = local->host_encrypt = 1;
-	}
-
-	if (*crypt == NULL || (*crypt)->ops != ops) {
-		struct lib80211_crypt_data *new_crypt;
-
-		lib80211_crypt_delayed_deinit(&local->crypt_info, crypt);
-
-		new_crypt = kzalloc(sizeof(struct lib80211_crypt_data),
-				GFP_KERNEL);
-		if (new_crypt == NULL) {
-			ret = -ENOMEM;
-			goto done;
-		}
-		new_crypt->ops = ops;
-		if (new_crypt->ops && try_module_get(new_crypt->ops->owner))
-			new_crypt->priv = new_crypt->ops->init(i);
-		if (new_crypt->priv == NULL) {
-			kfree(new_crypt);
-			ret = -EINVAL;
-			goto done;
-		}
-
-		*crypt = new_crypt;
-	}
-
-	/*
-	 * TODO: if ext_flags does not have IW_ENCODE_EXT_RX_SEQ_VALID, the
-	 * existing seq# should not be changed.
-	 * TODO: if ext_flags has IW_ENCODE_EXT_TX_SEQ_VALID, next TX seq#
-	 * should be changed to something else than zero.
-	 */
-	if ((!(ext->ext_flags & IW_ENCODE_EXT_SET_TX_KEY) || ext->key_len > 0)
-	    && (*crypt)->ops->set_key &&
-	    (*crypt)->ops->set_key(ext->key, ext->key_len, ext->rx_seq,
-				   (*crypt)->priv) < 0) {
-		printk(KERN_DEBUG "%s: key setting failed\n",
-		       local->dev->name);
-		ret = -EINVAL;
-		goto done;
-	}
-
-	if (ext->ext_flags & IW_ENCODE_EXT_SET_TX_KEY) {
-		if (!sta_ptr)
-			local->crypt_info.tx_keyidx = i;
-	}
-
-
-	if (sta_ptr == NULL && ext->key_len > 0) {
-		int first = 1, j;
-		for (j = 0; j < WEP_KEYS; j++) {
-			if (j != i && local->crypt_info.crypt[j]) {
-				first = 0;
-				break;
-			}
-		}
-		if (first)
-			local->crypt_info.tx_keyidx = i;
-	}
-
- done:
-	if (sta_ptr)
-		hostap_handle_sta_release(sta_ptr);
-
-	local->open_wep = erq->flags & IW_ENCODE_OPEN;
-
-	/*
-	 * Do not reset port0 if card is in Managed mode since resetting will
-	 * generate new IEEE 802.11 authentication which may end up in looping
-	 * with IEEE 802.1X. Prism2 documentation seem to require port reset
-	 * after WEP configuration. However, keys are apparently changed at
-	 * least in Managed mode.
-	 */
-	if (ret == 0 &&
-	    (hostap_set_encryption(local) ||
-	     (local->iw_mode != IW_MODE_INFRA &&
-	      local->func->reset_port(local->dev))))
-		ret = -EINVAL;
-
-	return ret;
-}
-
-
-static int prism2_ioctl_giwencodeext(struct net_device *dev,
-				     struct iw_request_info *info,
-				     union iwreq_data *wrqu, char *extra)
-{
-	struct iw_point *erq = &wrqu->encoding;
-	struct hostap_interface *iface = netdev_priv(dev);
-	local_info_t *local = iface->local;
-	struct lib80211_crypt_data **crypt;
-	void *sta_ptr;
-	int max_key_len, i;
-	struct iw_encode_ext *ext = (struct iw_encode_ext *) extra;
-	u8 *addr;
-
-	max_key_len = erq->length - sizeof(*ext);
-	if (max_key_len < 0)
-		return -EINVAL;
-
-	i = erq->flags & IW_ENCODE_INDEX;
-	if (i < 1 || i > WEP_KEYS)
-		i = local->crypt_info.tx_keyidx;
-	else
-		i--;
-
-	addr = ext->addr.sa_data;
-	if (is_broadcast_ether_addr(addr)) {
-		sta_ptr = NULL;
-		crypt = &local->crypt_info.crypt[i];
-	} else {
-		i = 0;
-		sta_ptr = ap_crypt_get_ptrs(local->ap, addr, 0, &crypt);
-		if (sta_ptr == NULL)
-			return -EINVAL;
-	}
-	erq->flags = i + 1;
-	memset(ext, 0, sizeof(*ext));
-
-	if (*crypt == NULL || (*crypt)->ops == NULL) {
-		ext->alg = IW_ENCODE_ALG_NONE;
-		ext->key_len = 0;
-		erq->flags |= IW_ENCODE_DISABLED;
-	} else {
-		if (strcmp((*crypt)->ops->name, "WEP") == 0)
-			ext->alg = IW_ENCODE_ALG_WEP;
-		else if (strcmp((*crypt)->ops->name, "TKIP") == 0)
-			ext->alg = IW_ENCODE_ALG_TKIP;
-		else if (strcmp((*crypt)->ops->name, "CCMP") == 0)
-			ext->alg = IW_ENCODE_ALG_CCMP;
-		else
-			return -EINVAL;
-
-		if ((*crypt)->ops->get_key) {
-			ext->key_len =
-				(*crypt)->ops->get_key(ext->key,
-						       max_key_len,
-						       ext->tx_seq,
-						       (*crypt)->priv);
-			if (ext->key_len &&
-			    (ext->alg == IW_ENCODE_ALG_TKIP ||
-			     ext->alg == IW_ENCODE_ALG_CCMP))
-				ext->ext_flags |= IW_ENCODE_EXT_TX_SEQ_VALID;
-		}
-	}
-
-	if (sta_ptr)
-		hostap_handle_sta_release(sta_ptr);
-
-	return 0;
-}
-
-
-static int prism2_ioctl_set_encryption(local_info_t *local,
-				       struct prism2_hostapd_param *param,
-				       int param_len)
-{
-	int ret = 0;
-	struct lib80211_crypto_ops *ops;
-	struct lib80211_crypt_data **crypt;
-	void *sta_ptr;
-
-	param->u.crypt.err = 0;
-	param->u.crypt.alg[HOSTAP_CRYPT_ALG_NAME_LEN - 1] = '\0';
-
-	if (param_len !=
-	    (int) ((char *) param->u.crypt.key - (char *) param) +
-	    param->u.crypt.key_len)
-		return -EINVAL;
-
-	if (is_broadcast_ether_addr(param->sta_addr)) {
-		if (param->u.crypt.idx >= WEP_KEYS)
-			return -EINVAL;
-		sta_ptr = NULL;
-		crypt = &local->crypt_info.crypt[param->u.crypt.idx];
-	} else {
-		if (param->u.crypt.idx)
-			return -EINVAL;
-		sta_ptr = ap_crypt_get_ptrs(
-			local->ap, param->sta_addr,
-			(param->u.crypt.flags & HOSTAP_CRYPT_FLAG_PERMANENT),
-			&crypt);
-
-		if (sta_ptr == NULL) {
-			param->u.crypt.err = HOSTAP_CRYPT_ERR_UNKNOWN_ADDR;
-			return -EINVAL;
-		}
-	}
-
-	if (strcmp(param->u.crypt.alg, "none") == 0) {
-		if (crypt)
-			lib80211_crypt_delayed_deinit(&local->crypt_info, crypt);
-		goto done;
-	}
-
-	ops = lib80211_get_crypto_ops(param->u.crypt.alg);
-	if (ops == NULL && strcmp(param->u.crypt.alg, "WEP") == 0) {
-		request_module("lib80211_crypt_wep");
-		ops = lib80211_get_crypto_ops(param->u.crypt.alg);
-	} else if (ops == NULL && strcmp(param->u.crypt.alg, "TKIP") == 0) {
-		request_module("lib80211_crypt_tkip");
-		ops = lib80211_get_crypto_ops(param->u.crypt.alg);
-	} else if (ops == NULL && strcmp(param->u.crypt.alg, "CCMP") == 0) {
-		request_module("lib80211_crypt_ccmp");
-		ops = lib80211_get_crypto_ops(param->u.crypt.alg);
-	}
-	if (ops == NULL) {
-		printk(KERN_DEBUG "%s: unknown crypto alg '%s'\n",
-		       local->dev->name, param->u.crypt.alg);
-		param->u.crypt.err = HOSTAP_CRYPT_ERR_UNKNOWN_ALG;
-		ret = -EINVAL;
-		goto done;
-	}
-
-	/* station based encryption and other than WEP algorithms require
-	 * host-based encryption, so force them on automatically */
-	local->host_decrypt = local->host_encrypt = 1;
-
-	if (*crypt == NULL || (*crypt)->ops != ops) {
-		struct lib80211_crypt_data *new_crypt;
-
-		lib80211_crypt_delayed_deinit(&local->crypt_info, crypt);
-
-		new_crypt = kzalloc(sizeof(struct lib80211_crypt_data),
-				GFP_KERNEL);
-		if (new_crypt == NULL) {
-			ret = -ENOMEM;
-			goto done;
-		}
-		new_crypt->ops = ops;
-		new_crypt->priv = new_crypt->ops->init(param->u.crypt.idx);
-		if (new_crypt->priv == NULL) {
-			kfree(new_crypt);
-			param->u.crypt.err =
-				HOSTAP_CRYPT_ERR_CRYPT_INIT_FAILED;
-			ret = -EINVAL;
-			goto done;
-		}
-
-		*crypt = new_crypt;
-	}
-
-	if ((!(param->u.crypt.flags & HOSTAP_CRYPT_FLAG_SET_TX_KEY) ||
-	     param->u.crypt.key_len > 0) && (*crypt)->ops->set_key &&
-	    (*crypt)->ops->set_key(param->u.crypt.key,
-				   param->u.crypt.key_len, param->u.crypt.seq,
-				   (*crypt)->priv) < 0) {
-		printk(KERN_DEBUG "%s: key setting failed\n",
-		       local->dev->name);
-		param->u.crypt.err = HOSTAP_CRYPT_ERR_KEY_SET_FAILED;
-		ret = -EINVAL;
-		goto done;
-	}
-
-	if (param->u.crypt.flags & HOSTAP_CRYPT_FLAG_SET_TX_KEY) {
-		if (!sta_ptr)
-			local->crypt_info.tx_keyidx = param->u.crypt.idx;
-		else if (param->u.crypt.idx) {
-			printk(KERN_DEBUG "%s: TX key idx setting failed\n",
-			       local->dev->name);
-			param->u.crypt.err =
-				HOSTAP_CRYPT_ERR_TX_KEY_SET_FAILED;
-			ret = -EINVAL;
-			goto done;
-		}
-	}
-
- done:
-	if (sta_ptr)
-		hostap_handle_sta_release(sta_ptr);
-
-	/* Do not reset port0 if card is in Managed mode since resetting will
-	 * generate new IEEE 802.11 authentication which may end up in looping
-	 * with IEEE 802.1X. Prism2 documentation seem to require port reset
-	 * after WEP configuration. However, keys are apparently changed at
-	 * least in Managed mode. */
-	if (ret == 0 &&
-	    (hostap_set_encryption(local) ||
-	     (local->iw_mode != IW_MODE_INFRA &&
-	      local->func->reset_port(local->dev)))) {
-		param->u.crypt.err = HOSTAP_CRYPT_ERR_CARD_CONF_FAILED;
-		return -EINVAL;
-	}
-
-	return ret;
-}
-
-
-static int prism2_ioctl_get_encryption(local_info_t *local,
-				       struct prism2_hostapd_param *param,
-				       int param_len)
-{
-	struct lib80211_crypt_data **crypt;
-	void *sta_ptr;
-	int max_key_len;
-
-	param->u.crypt.err = 0;
-
-	max_key_len = param_len -
-		(int) ((char *) param->u.crypt.key - (char *) param);
-	if (max_key_len < 0)
-		return -EINVAL;
-
-	if (is_broadcast_ether_addr(param->sta_addr)) {
-		sta_ptr = NULL;
-		if (param->u.crypt.idx >= WEP_KEYS)
-			param->u.crypt.idx = local->crypt_info.tx_keyidx;
-		crypt = &local->crypt_info.crypt[param->u.crypt.idx];
-	} else {
-		param->u.crypt.idx = 0;
-		sta_ptr = ap_crypt_get_ptrs(local->ap, param->sta_addr, 0,
-					    &crypt);
-
-		if (sta_ptr == NULL) {
-			param->u.crypt.err = HOSTAP_CRYPT_ERR_UNKNOWN_ADDR;
-			return -EINVAL;
-		}
-	}
-
-	if (*crypt == NULL || (*crypt)->ops == NULL) {
-		memcpy(param->u.crypt.alg, "none", 5);
-		param->u.crypt.key_len = 0;
-		param->u.crypt.idx = 0xff;
-	} else {
-		strscpy(param->u.crypt.alg, (*crypt)->ops->name,
-			HOSTAP_CRYPT_ALG_NAME_LEN);
-		param->u.crypt.key_len = 0;
-
-		memset(param->u.crypt.seq, 0, 8);
-		if ((*crypt)->ops->get_key) {
-			param->u.crypt.key_len =
-				(*crypt)->ops->get_key(param->u.crypt.key,
-						       max_key_len,
-						       param->u.crypt.seq,
-						       (*crypt)->priv);
-		}
-	}
-
-	if (sta_ptr)
-		hostap_handle_sta_release(sta_ptr);
-
-	return 0;
-}
-
-
-static int prism2_ioctl_get_rid(local_info_t *local,
-				struct prism2_hostapd_param *param,
-				int param_len)
-{
-	int max_len, res;
-
-	max_len = param_len - PRISM2_HOSTAPD_RID_HDR_LEN;
-	if (max_len < 0)
-		return -EINVAL;
-
-	res = local->func->get_rid(local->dev, param->u.rid.rid,
-				   param->u.rid.data, param->u.rid.len, 0);
-	if (res >= 0) {
-		param->u.rid.len = res;
-		return 0;
-	}
-
-	return res;
-}
-
-
-static int prism2_ioctl_set_rid(local_info_t *local,
-				struct prism2_hostapd_param *param,
-				int param_len)
-{
-	int max_len;
-
-	max_len = param_len - PRISM2_HOSTAPD_RID_HDR_LEN;
-	if (max_len < 0 || max_len < param->u.rid.len)
-		return -EINVAL;
-
-	return local->func->set_rid(local->dev, param->u.rid.rid,
-				    param->u.rid.data, param->u.rid.len);
-}
-
-
-static int prism2_ioctl_set_assoc_ap_addr(local_info_t *local,
-					  struct prism2_hostapd_param *param,
-					  int param_len)
-{
-	printk(KERN_DEBUG "%ssta: associated as client with AP %pM\n",
-	       local->dev->name, param->sta_addr);
-	memcpy(local->assoc_ap_addr, param->sta_addr, ETH_ALEN);
-	return 0;
-}
-
-
-static int prism2_ioctl_siwgenie(struct net_device *dev,
-				 struct iw_request_info *info,
-				 union iwreq_data *wrqu, char *extra)
-{
-	struct iw_point *data = &wrqu->data;
-	return prism2_set_genericelement(dev, extra, data->length);
-}
-
-
-static int prism2_ioctl_giwgenie(struct net_device *dev,
-				 struct iw_request_info *info,
-				 union iwreq_data *wrqu, char *extra)
-{
-	struct iw_point *data = &wrqu->data;
-	struct hostap_interface *iface = netdev_priv(dev);
-	local_info_t *local = iface->local;
-	int len = local->generic_elem_len - 2;
-
-	if (len <= 0 || local->generic_elem == NULL) {
-		data->length = 0;
-		return 0;
-	}
-
-	if (data->length < len)
-		return -E2BIG;
-
-	data->length = len;
-	memcpy(extra, local->generic_elem + 2, len);
-
-	return 0;
-}
-
-
-static int prism2_ioctl_set_generic_element(local_info_t *local,
-					    struct prism2_hostapd_param *param,
-					    int param_len)
-{
-	int max_len, len;
-
-	len = param->u.generic_elem.len;
-	max_len = param_len - PRISM2_HOSTAPD_GENERIC_ELEMENT_HDR_LEN;
-	if (max_len < 0 || max_len < len)
-		return -EINVAL;
-
-	return prism2_set_genericelement(local->dev,
-					 param->u.generic_elem.data, len);
-}
-
-
-static int prism2_ioctl_siwmlme(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
-{
-	struct hostap_interface *iface = netdev_priv(dev);
-	local_info_t *local = iface->local;
-	struct iw_mlme *mlme = (struct iw_mlme *) extra;
-	__le16 reason;
-
-	reason = cpu_to_le16(mlme->reason_code);
-
-	switch (mlme->cmd) {
-	case IW_MLME_DEAUTH:
-		return prism2_sta_send_mgmt(local, mlme->addr.sa_data,
-					    IEEE80211_STYPE_DEAUTH,
-					    (u8 *) &reason, 2);
-	case IW_MLME_DISASSOC:
-		return prism2_sta_send_mgmt(local, mlme->addr.sa_data,
-					    IEEE80211_STYPE_DISASSOC,
-					    (u8 *) &reason, 2);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-
-static int prism2_ioctl_mlme(local_info_t *local,
-			     struct prism2_hostapd_param *param)
-{
-	__le16 reason;
-
-	reason = cpu_to_le16(param->u.mlme.reason_code);
-	switch (param->u.mlme.cmd) {
-	case MLME_STA_DEAUTH:
-		return prism2_sta_send_mgmt(local, param->sta_addr,
-					    IEEE80211_STYPE_DEAUTH,
-					    (u8 *) &reason, 2);
-	case MLME_STA_DISASSOC:
-		return prism2_sta_send_mgmt(local, param->sta_addr,
-					    IEEE80211_STYPE_DISASSOC,
-					    (u8 *) &reason, 2);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-
-static int prism2_ioctl_scan_req(local_info_t *local,
-				 struct prism2_hostapd_param *param)
-{
-#ifndef PRISM2_NO_STATION_MODES
-	if ((local->iw_mode != IW_MODE_INFRA &&
-	     local->iw_mode != IW_MODE_ADHOC) ||
-	    (local->sta_fw_ver < PRISM2_FW_VER(1,3,1)))
-		return -EOPNOTSUPP;
-
-	if (!local->dev_enabled)
-		return -ENETDOWN;
-
-	return prism2_request_hostscan(local->dev, param->u.scan_req.ssid,
-				       param->u.scan_req.ssid_len);
-#else /* PRISM2_NO_STATION_MODES */
-	return -EOPNOTSUPP;
-#endif /* PRISM2_NO_STATION_MODES */
-}
-
-
-static int prism2_ioctl_priv_hostapd(local_info_t *local, struct iw_point *p)
-{
-	struct prism2_hostapd_param *param;
-	int ret = 0;
-	int ap_ioctl = 0;
-
-	if (p->length < sizeof(struct prism2_hostapd_param) ||
-	    p->length > PRISM2_HOSTAPD_MAX_BUF_SIZE || !p->pointer)
-		return -EINVAL;
-
-	param = memdup_user(p->pointer, p->length);
-	if (IS_ERR(param)) {
-		return PTR_ERR(param);
-	}
-
-	switch (param->cmd) {
-	case PRISM2_SET_ENCRYPTION:
-		ret = prism2_ioctl_set_encryption(local, param, p->length);
-		break;
-	case PRISM2_GET_ENCRYPTION:
-		ret = prism2_ioctl_get_encryption(local, param, p->length);
-		break;
-	case PRISM2_HOSTAPD_GET_RID:
-		ret = prism2_ioctl_get_rid(local, param, p->length);
-		break;
-	case PRISM2_HOSTAPD_SET_RID:
-		ret = prism2_ioctl_set_rid(local, param, p->length);
-		break;
-	case PRISM2_HOSTAPD_SET_ASSOC_AP_ADDR:
-		ret = prism2_ioctl_set_assoc_ap_addr(local, param, p->length);
-		break;
-	case PRISM2_HOSTAPD_SET_GENERIC_ELEMENT:
-		ret = prism2_ioctl_set_generic_element(local, param,
-						       p->length);
-		break;
-	case PRISM2_HOSTAPD_MLME:
-		ret = prism2_ioctl_mlme(local, param);
-		break;
-	case PRISM2_HOSTAPD_SCAN_REQ:
-		ret = prism2_ioctl_scan_req(local, param);
-		break;
-	default:
-		ret = prism2_hostapd(local->ap, param);
-		ap_ioctl = 1;
-		break;
-	}
-
-	if (ret == 1 || !ap_ioctl) {
-		if (copy_to_user(p->pointer, param, p->length)) {
-			ret = -EFAULT;
-			goto out;
-		} else if (ap_ioctl)
-			ret = 0;
-	}
-
- out:
-	kfree(param);
-	return ret;
-}
-
-
-static void prism2_get_drvinfo(struct net_device *dev,
-			       struct ethtool_drvinfo *info)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	strscpy(info->driver, "hostap", sizeof(info->driver));
-	snprintf(info->fw_version, sizeof(info->fw_version),
-		 "%d.%d.%d", (local->sta_fw_ver >> 16) & 0xff,
-		 (local->sta_fw_ver >> 8) & 0xff,
-		 local->sta_fw_ver & 0xff);
-}
-
-const struct ethtool_ops prism2_ethtool_ops = {
-	.get_drvinfo = prism2_get_drvinfo
-};
-
-
-/* Structures to export the Wireless Handlers */
-
-static const iw_handler prism2_handler[] =
-{
-	IW_HANDLER(SIOCGIWNAME,		prism2_get_name),
-	IW_HANDLER(SIOCSIWFREQ,		prism2_ioctl_siwfreq),
-	IW_HANDLER(SIOCGIWFREQ,		prism2_ioctl_giwfreq),
-	IW_HANDLER(SIOCSIWMODE,		prism2_ioctl_siwmode),
-	IW_HANDLER(SIOCGIWMODE,		prism2_ioctl_giwmode),
-	IW_HANDLER(SIOCSIWSENS,		prism2_ioctl_siwsens),
-	IW_HANDLER(SIOCGIWSENS,		prism2_ioctl_giwsens),
-	IW_HANDLER(SIOCGIWRANGE,	prism2_ioctl_giwrange),
-	IW_HANDLER(SIOCSIWSPY,		iw_handler_set_spy),
-	IW_HANDLER(SIOCGIWSPY,		iw_handler_get_spy),
-	IW_HANDLER(SIOCSIWTHRSPY,	iw_handler_set_thrspy),
-	IW_HANDLER(SIOCGIWTHRSPY,	iw_handler_get_thrspy),
-	IW_HANDLER(SIOCSIWAP,		prism2_ioctl_siwap),
-	IW_HANDLER(SIOCGIWAP,		prism2_ioctl_giwap),
-	IW_HANDLER(SIOCSIWMLME,		prism2_ioctl_siwmlme),
-	IW_HANDLER(SIOCGIWAPLIST,       prism2_ioctl_giwaplist),
-	IW_HANDLER(SIOCSIWSCAN,		prism2_ioctl_siwscan),
-	IW_HANDLER(SIOCGIWSCAN,		prism2_ioctl_giwscan),
-	IW_HANDLER(SIOCSIWESSID,        prism2_ioctl_siwessid),
-	IW_HANDLER(SIOCGIWESSID,        prism2_ioctl_giwessid),
-	IW_HANDLER(SIOCSIWNICKN,        prism2_ioctl_siwnickn),
-	IW_HANDLER(SIOCGIWNICKN,        prism2_ioctl_giwnickn),
-	IW_HANDLER(SIOCSIWRATE,		prism2_ioctl_siwrate),
-	IW_HANDLER(SIOCGIWRATE,		prism2_ioctl_giwrate),
-	IW_HANDLER(SIOCSIWRTS,		prism2_ioctl_siwrts),
-	IW_HANDLER(SIOCGIWRTS,		prism2_ioctl_giwrts),
-	IW_HANDLER(SIOCSIWFRAG,		prism2_ioctl_siwfrag),
-	IW_HANDLER(SIOCGIWFRAG,		prism2_ioctl_giwfrag),
-	IW_HANDLER(SIOCSIWTXPOW,        prism2_ioctl_siwtxpow),
-	IW_HANDLER(SIOCGIWTXPOW,        prism2_ioctl_giwtxpow),
-	IW_HANDLER(SIOCSIWRETRY,        prism2_ioctl_siwretry),
-	IW_HANDLER(SIOCGIWRETRY,        prism2_ioctl_giwretry),
-	IW_HANDLER(SIOCSIWENCODE,       prism2_ioctl_siwencode),
-	IW_HANDLER(SIOCGIWENCODE,       prism2_ioctl_giwencode),
-	IW_HANDLER(SIOCSIWPOWER,        prism2_ioctl_siwpower),
-	IW_HANDLER(SIOCGIWPOWER,        prism2_ioctl_giwpower),
-	IW_HANDLER(SIOCSIWGENIE,        prism2_ioctl_siwgenie),
-	IW_HANDLER(SIOCGIWGENIE,        prism2_ioctl_giwgenie),
-	IW_HANDLER(SIOCSIWAUTH,		prism2_ioctl_siwauth),
-	IW_HANDLER(SIOCGIWAUTH,		prism2_ioctl_giwauth),
-	IW_HANDLER(SIOCSIWENCODEEXT,    prism2_ioctl_siwencodeext),
-	IW_HANDLER(SIOCGIWENCODEEXT,    prism2_ioctl_giwencodeext),
-};
-
-static const iw_handler prism2_private_handler[] =
-{						/* SIOCIWFIRSTPRIV + */
-	prism2_ioctl_priv_prism2_param,		/* 0 */
-	prism2_ioctl_priv_get_prism2_param,	/* 1 */
-	prism2_ioctl_priv_writemif,		/* 2 */
-	prism2_ioctl_priv_readmif,		/* 3 */
-};
-
-const struct iw_handler_def hostap_iw_handler_def =
-{
-	.num_standard	= ARRAY_SIZE(prism2_handler),
-	.num_private	= ARRAY_SIZE(prism2_private_handler),
-	.num_private_args = ARRAY_SIZE(prism2_priv),
-	.standard	= prism2_handler,
-	.private	= prism2_private_handler,
-	.private_args	= (struct iw_priv_args *) prism2_priv,
-	.get_wireless_stats = hostap_get_wireless_stats,
-};
-
-
-/* Private ioctls that are not used with iwpriv;
- * in SIOCDEVPRIVATE range */
-int hostap_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
-			  void __user *data, int cmd)
-{
-	struct iwreq *wrq = (struct iwreq *)ifr;
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int ret = 0;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (in_compat_syscall()) /* not implemented yet */
-		return -EOPNOTSUPP;
-
-	switch (cmd) {
-#ifdef PRISM2_DOWNLOAD_SUPPORT
-	case PRISM2_IOCTL_DOWNLOAD:
-		if (!capable(CAP_NET_ADMIN)) ret = -EPERM;
-		else ret = prism2_ioctl_priv_download(local, &wrq->u.data);
-		break;
-#endif /* PRISM2_DOWNLOAD_SUPPORT */
-
-	case PRISM2_IOCTL_HOSTAPD:
-		if (!capable(CAP_NET_ADMIN)) ret = -EPERM;
-		else ret = prism2_ioctl_priv_hostapd(local, &wrq->u.data);
-		break;
-
-	default:
-		ret = -EOPNOTSUPP;
-		break;
-	}
-
-	return ret;
-}
diff --git a/drivers/net/wireless/intersil/hostap/hostap_main.c b/drivers/net/wireless/intersil/hostap/hostap_main.c
deleted file mode 100644
index bf86ac26c2ac..000000000000
--- a/drivers/net/wireless/intersil/hostap/hostap_main.c
+++ /dev/null
@@ -1,1123 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Host AP (software wireless LAN access point) driver for
- * Intersil Prism2/2.5/3 - hostap.o module, common routines
- *
- * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen
- * <j@w1.fi>
- * Copyright (c) 2002-2005, Jouni Malinen <j@w1.fi>
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/proc_fs.h>
-#include <linux/if_arp.h>
-#include <linux/delay.h>
-#include <linux/random.h>
-#include <linux/workqueue.h>
-#include <linux/kmod.h>
-#include <linux/rtnetlink.h>
-#include <linux/wireless.h>
-#include <linux/etherdevice.h>
-#include <net/net_namespace.h>
-#include <net/iw_handler.h>
-#include <net/lib80211.h>
-#include <linux/uaccess.h>
-
-#include "hostap_wlan.h"
-#include "hostap_80211.h"
-#include "hostap_ap.h"
-#include "hostap.h"
-
-MODULE_AUTHOR("Jouni Malinen");
-MODULE_DESCRIPTION("Host AP common routines");
-MODULE_LICENSE("GPL");
-
-#define TX_TIMEOUT (2 * HZ)
-
-#define PRISM2_MAX_FRAME_SIZE 2304
-#define PRISM2_MIN_MTU 256
-/* FIX: */
-#define PRISM2_MAX_MTU (PRISM2_MAX_FRAME_SIZE - (6 /* LLC */ + 8 /* WEP */))
-
-
-struct net_device * hostap_add_interface(struct local_info *local,
-					 int type, int rtnl_locked,
-					 const char *prefix,
-					 const char *name)
-{
-	struct net_device *dev, *mdev;
-	struct hostap_interface *iface;
-	int ret;
-
-	dev = alloc_etherdev(sizeof(struct hostap_interface));
-	if (dev == NULL)
-		return NULL;
-
-	iface = netdev_priv(dev);
-	iface->dev = dev;
-	iface->local = local;
-	iface->type = type;
-	list_add(&iface->list, &local->hostap_interfaces);
-
-	mdev = local->dev;
-	eth_hw_addr_inherit(dev, mdev);
-	dev->base_addr = mdev->base_addr;
-	dev->irq = mdev->irq;
-	dev->mem_start = mdev->mem_start;
-	dev->mem_end = mdev->mem_end;
-
-	hostap_setup_dev(dev, local, type);
-	dev->needs_free_netdev = true;
-
-	sprintf(dev->name, "%s%s", prefix, name);
-	if (!rtnl_locked)
-		rtnl_lock();
-
-	SET_NETDEV_DEV(dev, mdev->dev.parent);
-	ret = register_netdevice(dev);
-
-	if (!rtnl_locked)
-		rtnl_unlock();
-
-	if (ret < 0) {
-		printk(KERN_WARNING "%s: failed to add new netdevice!\n",
-		       dev->name);
-		free_netdev(dev);
-		return NULL;
-	}
-
-	printk(KERN_DEBUG "%s: registered netdevice %s\n",
-	       mdev->name, dev->name);
-
-	return dev;
-}
-
-
-void hostap_remove_interface(struct net_device *dev, int rtnl_locked,
-			     int remove_from_list)
-{
-	struct hostap_interface *iface;
-
-	if (!dev)
-		return;
-
-	iface = netdev_priv(dev);
-
-	if (remove_from_list) {
-		list_del(&iface->list);
-	}
-
-	if (dev == iface->local->ddev)
-		iface->local->ddev = NULL;
-	else if (dev == iface->local->apdev)
-		iface->local->apdev = NULL;
-	else if (dev == iface->local->stadev)
-		iface->local->stadev = NULL;
-
-	if (rtnl_locked)
-		unregister_netdevice(dev);
-	else
-		unregister_netdev(dev);
-
-	/* 'dev->needs_free_netdev = true' implies device data, including
-	 * private data, will be freed when the device is removed */
-}
-
-
-static inline int prism2_wds_special_addr(u8 *addr)
-{
-	if (addr[0] || addr[1] || addr[2] || addr[3] || addr[4] || addr[5])
-		return 0;
-
-	return 1;
-}
-
-
-int prism2_wds_add(local_info_t *local, u8 *remote_addr,
-		   int rtnl_locked)
-{
-	struct net_device *dev;
-	struct list_head *ptr;
-	struct hostap_interface *iface, *empty, *match;
-
-	empty = match = NULL;
-	read_lock_bh(&local->iface_lock);
-	list_for_each(ptr, &local->hostap_interfaces) {
-		iface = list_entry(ptr, struct hostap_interface, list);
-		if (iface->type != HOSTAP_INTERFACE_WDS)
-			continue;
-
-		if (prism2_wds_special_addr(iface->u.wds.remote_addr))
-			empty = iface;
-		else if (ether_addr_equal(iface->u.wds.remote_addr, remote_addr)) {
-			match = iface;
-			break;
-		}
-	}
-	if (!match && empty && !prism2_wds_special_addr(remote_addr)) {
-		/* take pre-allocated entry into use */
-		memcpy(empty->u.wds.remote_addr, remote_addr, ETH_ALEN);
-		read_unlock_bh(&local->iface_lock);
-		printk(KERN_DEBUG "%s: using pre-allocated WDS netdevice %s\n",
-		       local->dev->name, empty->dev->name);
-		return 0;
-	}
-	read_unlock_bh(&local->iface_lock);
-
-	if (!prism2_wds_special_addr(remote_addr)) {
-		if (match)
-			return -EEXIST;
-		hostap_add_sta(local->ap, remote_addr);
-	}
-
-	if (local->wds_connections >= local->wds_max_connections)
-		return -ENOBUFS;
-
-	/* verify that there is room for wds# postfix in the interface name */
-	if (strlen(local->dev->name) >= IFNAMSIZ - 5) {
-		printk(KERN_DEBUG "'%s' too long base device name\n",
-		       local->dev->name);
-		return -EINVAL;
-	}
-
-	dev = hostap_add_interface(local, HOSTAP_INTERFACE_WDS, rtnl_locked,
-				   local->ddev->name, "wds%d");
-	if (dev == NULL)
-		return -ENOMEM;
-
-	iface = netdev_priv(dev);
-	memcpy(iface->u.wds.remote_addr, remote_addr, ETH_ALEN);
-
-	local->wds_connections++;
-
-	return 0;
-}
-
-
-int prism2_wds_del(local_info_t *local, u8 *remote_addr,
-		   int rtnl_locked, int do_not_remove)
-{
-	unsigned long flags;
-	struct list_head *ptr;
-	struct hostap_interface *iface, *selected = NULL;
-
-	write_lock_irqsave(&local->iface_lock, flags);
-	list_for_each(ptr, &local->hostap_interfaces) {
-		iface = list_entry(ptr, struct hostap_interface, list);
-		if (iface->type != HOSTAP_INTERFACE_WDS)
-			continue;
-
-		if (ether_addr_equal(iface->u.wds.remote_addr, remote_addr)) {
-			selected = iface;
-			break;
-		}
-	}
-	if (selected && !do_not_remove)
-		list_del(&selected->list);
-	write_unlock_irqrestore(&local->iface_lock, flags);
-
-	if (selected) {
-		if (do_not_remove)
-			eth_zero_addr(selected->u.wds.remote_addr);
-		else {
-			hostap_remove_interface(selected->dev, rtnl_locked, 0);
-			local->wds_connections--;
-		}
-	}
-
-	return selected ? 0 : -ENODEV;
-}
-
-
-u16 hostap_tx_callback_register(local_info_t *local,
-				void (*func)(struct sk_buff *, int ok, void *),
-				void *data)
-{
-	unsigned long flags;
-	struct hostap_tx_callback_info *entry;
-
-	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
-	if (entry == NULL)
-		return 0;
-
-	entry->func = func;
-	entry->data = data;
-
-	spin_lock_irqsave(&local->lock, flags);
-	entry->idx = local->tx_callback ? local->tx_callback->idx + 1 : 1;
-	entry->next = local->tx_callback;
-	local->tx_callback = entry;
-	spin_unlock_irqrestore(&local->lock, flags);
-
-	return entry->idx;
-}
-
-
-int hostap_tx_callback_unregister(local_info_t *local, u16 idx)
-{
-	unsigned long flags;
-	struct hostap_tx_callback_info *cb, *prev = NULL;
-
-	spin_lock_irqsave(&local->lock, flags);
-	cb = local->tx_callback;
-	while (cb != NULL && cb->idx != idx) {
-		prev = cb;
-		cb = cb->next;
-	}
-	if (cb) {
-		if (prev == NULL)
-			local->tx_callback = cb->next;
-		else
-			prev->next = cb->next;
-		kfree(cb);
-	}
-	spin_unlock_irqrestore(&local->lock, flags);
-
-	return cb ? 0 : -1;
-}
-
-
-/* val is in host byte order */
-int hostap_set_word(struct net_device *dev, int rid, u16 val)
-{
-	struct hostap_interface *iface;
-	__le16 tmp = cpu_to_le16(val);
-	iface = netdev_priv(dev);
-	return iface->local->func->set_rid(dev, rid, &tmp, 2);
-}
-
-
-int hostap_set_string(struct net_device *dev, int rid, const char *val)
-{
-	struct hostap_interface *iface;
-	char buf[MAX_SSID_LEN + 2];
-	int len;
-
-	iface = netdev_priv(dev);
-	len = strlen(val);
-	if (len > MAX_SSID_LEN)
-		return -1;
-	memset(buf, 0, sizeof(buf));
-	buf[0] = len; /* little endian 16 bit word */
-	memcpy(buf + 2, val, len);
-
-	return iface->local->func->set_rid(dev, rid, &buf, MAX_SSID_LEN + 2);
-}
-
-
-u16 hostap_get_porttype(local_info_t *local)
-{
-	if (local->iw_mode == IW_MODE_ADHOC && local->pseudo_adhoc)
-		return HFA384X_PORTTYPE_PSEUDO_IBSS;
-	if (local->iw_mode == IW_MODE_ADHOC)
-		return HFA384X_PORTTYPE_IBSS;
-	if (local->iw_mode == IW_MODE_INFRA)
-		return HFA384X_PORTTYPE_BSS;
-	if (local->iw_mode == IW_MODE_REPEAT)
-		return HFA384X_PORTTYPE_WDS;
-	if (local->iw_mode == IW_MODE_MONITOR)
-		return HFA384X_PORTTYPE_PSEUDO_IBSS;
-	return HFA384X_PORTTYPE_HOSTAP;
-}
-
-
-int hostap_set_encryption(local_info_t *local)
-{
-	u16 val, old_val;
-	int i, keylen, len, idx;
-	char keybuf[WEP_KEY_LEN + 1];
-	enum { NONE, WEP, OTHER } encrypt_type;
-
-	idx = local->crypt_info.tx_keyidx;
-	if (local->crypt_info.crypt[idx] == NULL ||
-	    local->crypt_info.crypt[idx]->ops == NULL)
-		encrypt_type = NONE;
-	else if (strcmp(local->crypt_info.crypt[idx]->ops->name, "WEP") == 0)
-		encrypt_type = WEP;
-	else
-		encrypt_type = OTHER;
-
-	if (local->func->get_rid(local->dev, HFA384X_RID_CNFWEPFLAGS, &val, 2,
-				 1) < 0) {
-		printk(KERN_DEBUG "Could not read current WEP flags.\n");
-		goto fail;
-	}
-	le16_to_cpus(&val);
-	old_val = val;
-
-	if (encrypt_type != NONE || local->privacy_invoked)
-		val |= HFA384X_WEPFLAGS_PRIVACYINVOKED;
-	else
-		val &= ~HFA384X_WEPFLAGS_PRIVACYINVOKED;
-
-	if (local->open_wep || encrypt_type == NONE ||
-	    ((local->ieee_802_1x || local->wpa) && local->host_decrypt))
-		val &= ~HFA384X_WEPFLAGS_EXCLUDEUNENCRYPTED;
-	else
-		val |= HFA384X_WEPFLAGS_EXCLUDEUNENCRYPTED;
-
-	if ((encrypt_type != NONE || local->privacy_invoked) &&
-	    (encrypt_type == OTHER || local->host_encrypt))
-		val |= HFA384X_WEPFLAGS_HOSTENCRYPT;
-	else
-		val &= ~HFA384X_WEPFLAGS_HOSTENCRYPT;
-	if ((encrypt_type != NONE || local->privacy_invoked) &&
-	    (encrypt_type == OTHER || local->host_decrypt))
-		val |= HFA384X_WEPFLAGS_HOSTDECRYPT;
-	else
-		val &= ~HFA384X_WEPFLAGS_HOSTDECRYPT;
-
-	if (val != old_val &&
-	    hostap_set_word(local->dev, HFA384X_RID_CNFWEPFLAGS, val)) {
-		printk(KERN_DEBUG "Could not write new WEP flags (0x%x)\n",
-		       val);
-		goto fail;
-	}
-
-	if (encrypt_type != WEP)
-		return 0;
-
-	/* 104-bit support seems to require that all the keys are set to the
-	 * same keylen */
-	keylen = 6; /* first 5 octets */
-	len = local->crypt_info.crypt[idx]->ops->get_key(keybuf, sizeof(keybuf), NULL,
-							   local->crypt_info.crypt[idx]->priv);
-	if (idx >= 0 && idx < WEP_KEYS && len > 5)
-		keylen = WEP_KEY_LEN + 1; /* first 13 octets */
-
-	for (i = 0; i < WEP_KEYS; i++) {
-		memset(keybuf, 0, sizeof(keybuf));
-		if (local->crypt_info.crypt[i]) {
-			(void) local->crypt_info.crypt[i]->ops->get_key(
-				keybuf, sizeof(keybuf),
-				NULL, local->crypt_info.crypt[i]->priv);
-		}
-		if (local->func->set_rid(local->dev,
-					 HFA384X_RID_CNFDEFAULTKEY0 + i,
-					 keybuf, keylen)) {
-			printk(KERN_DEBUG "Could not set key %d (len=%d)\n",
-			       i, keylen);
-			goto fail;
-		}
-	}
-	if (hostap_set_word(local->dev, HFA384X_RID_CNFWEPDEFAULTKEYID, idx)) {
-		printk(KERN_DEBUG "Could not set default keyid %d\n", idx);
-		goto fail;
-	}
-
-	return 0;
-
- fail:
-	printk(KERN_DEBUG "%s: encryption setup failed\n", local->dev->name);
-	return -1;
-}
-
-
-int hostap_set_antsel(local_info_t *local)
-{
-	u16 val;
-	int ret = 0;
-
-	if (local->antsel_tx != HOSTAP_ANTSEL_DO_NOT_TOUCH &&
-	    local->func->cmd(local->dev, HFA384X_CMDCODE_READMIF,
-			     HFA386X_CR_TX_CONFIGURE,
-			     NULL, &val) == 0) {
-		val &= ~(BIT(2) | BIT(1));
-		switch (local->antsel_tx) {
-		case HOSTAP_ANTSEL_DIVERSITY:
-			val |= BIT(1);
-			break;
-		case HOSTAP_ANTSEL_LOW:
-			break;
-		case HOSTAP_ANTSEL_HIGH:
-			val |= BIT(2);
-			break;
-		}
-
-		if (local->func->cmd(local->dev, HFA384X_CMDCODE_WRITEMIF,
-				     HFA386X_CR_TX_CONFIGURE, &val, NULL)) {
-			printk(KERN_INFO "%s: setting TX AntSel failed\n",
-			       local->dev->name);
-			ret = -1;
-		}
-	}
-
-	if (local->antsel_rx != HOSTAP_ANTSEL_DO_NOT_TOUCH &&
-	    local->func->cmd(local->dev, HFA384X_CMDCODE_READMIF,
-			     HFA386X_CR_RX_CONFIGURE,
-			     NULL, &val) == 0) {
-		val &= ~(BIT(1) | BIT(0));
-		switch (local->antsel_rx) {
-		case HOSTAP_ANTSEL_DIVERSITY:
-			break;
-		case HOSTAP_ANTSEL_LOW:
-			val |= BIT(0);
-			break;
-		case HOSTAP_ANTSEL_HIGH:
-			val |= BIT(0) | BIT(1);
-			break;
-		}
-
-		if (local->func->cmd(local->dev, HFA384X_CMDCODE_WRITEMIF,
-				     HFA386X_CR_RX_CONFIGURE, &val, NULL)) {
-			printk(KERN_INFO "%s: setting RX AntSel failed\n",
-			       local->dev->name);
-			ret = -1;
-		}
-	}
-
-	return ret;
-}
-
-
-int hostap_set_roaming(local_info_t *local)
-{
-	u16 val;
-
-	switch (local->host_roaming) {
-	case 1:
-		val = HFA384X_ROAMING_HOST;
-		break;
-	case 2:
-		val = HFA384X_ROAMING_DISABLED;
-		break;
-	case 0:
-	default:
-		val = HFA384X_ROAMING_FIRMWARE;
-		break;
-	}
-
-	return hostap_set_word(local->dev, HFA384X_RID_CNFROAMINGMODE, val);
-}
-
-
-int hostap_set_auth_algs(local_info_t *local)
-{
-	int val = local->auth_algs;
-	/* At least STA f/w v0.6.2 seems to have issues with cnfAuthentication
-	 * set to include both Open and Shared Key flags. It tries to use
-	 * Shared Key authentication in that case even if WEP keys are not
-	 * configured.. STA f/w v0.7.6 is able to handle such configuration,
-	 * but it is unknown when this was fixed between 0.6.2 .. 0.7.6. */
-	if (local->sta_fw_ver < PRISM2_FW_VER(0,7,0) &&
-	    val != PRISM2_AUTH_OPEN && val != PRISM2_AUTH_SHARED_KEY)
-		val = PRISM2_AUTH_OPEN;
-
-	if (hostap_set_word(local->dev, HFA384X_RID_CNFAUTHENTICATION, val)) {
-		printk(KERN_INFO "%s: cnfAuthentication setting to 0x%x "
-		       "failed\n", local->dev->name, local->auth_algs);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-
-void hostap_dump_rx_header(const char *name, const struct hfa384x_rx_frame *rx)
-{
-	u16 status, fc;
-
-	status = __le16_to_cpu(rx->status);
-
-	printk(KERN_DEBUG "%s: RX status=0x%04x (port=%d, type=%d, "
-	       "fcserr=%d) silence=%d signal=%d rate=%d rxflow=%d; "
-	       "jiffies=%ld\n",
-	       name, status, (status >> 8) & 0x07, status >> 13, status & 1,
-	       rx->silence, rx->signal, rx->rate, rx->rxflow, jiffies);
-
-	fc = __le16_to_cpu(rx->frame_control);
-	printk(KERN_DEBUG "   FC=0x%04x (type=%d:%d) dur=0x%04x seq=0x%04x "
-	       "data_len=%d%s%s\n",
-	       fc, (fc & IEEE80211_FCTL_FTYPE) >> 2,
-	       (fc & IEEE80211_FCTL_STYPE) >> 4,
-	       __le16_to_cpu(rx->duration_id), __le16_to_cpu(rx->seq_ctrl),
-	       __le16_to_cpu(rx->data_len),
-	       fc & IEEE80211_FCTL_TODS ? " [ToDS]" : "",
-	       fc & IEEE80211_FCTL_FROMDS ? " [FromDS]" : "");
-
-	printk(KERN_DEBUG "   A1=%pM A2=%pM A3=%pM A4=%pM\n",
-	       rx->addr1, rx->addr2, rx->addr3, rx->addr4);
-
-	printk(KERN_DEBUG "   dst=%pM src=%pM len=%d\n",
-	       rx->dst_addr, rx->src_addr,
-	       __be16_to_cpu(rx->len));
-}
-
-
-void hostap_dump_tx_header(const char *name, const struct hfa384x_tx_frame *tx)
-{
-	u16 fc;
-
-	printk(KERN_DEBUG "%s: TX status=0x%04x retry_count=%d tx_rate=%d "
-	       "tx_control=0x%04x; jiffies=%ld\n",
-	       name, __le16_to_cpu(tx->status), tx->retry_count, tx->tx_rate,
-	       __le16_to_cpu(tx->tx_control), jiffies);
-
-	fc = __le16_to_cpu(tx->frame_control);
-	printk(KERN_DEBUG "   FC=0x%04x (type=%d:%d) dur=0x%04x seq=0x%04x "
-	       "data_len=%d%s%s\n",
-	       fc, (fc & IEEE80211_FCTL_FTYPE) >> 2,
-	       (fc & IEEE80211_FCTL_STYPE) >> 4,
-	       __le16_to_cpu(tx->duration_id), __le16_to_cpu(tx->seq_ctrl),
-	       __le16_to_cpu(tx->data_len),
-	       fc & IEEE80211_FCTL_TODS ? " [ToDS]" : "",
-	       fc & IEEE80211_FCTL_FROMDS ? " [FromDS]" : "");
-
-	printk(KERN_DEBUG "   A1=%pM A2=%pM A3=%pM A4=%pM\n",
-	       tx->addr1, tx->addr2, tx->addr3, tx->addr4);
-
-	printk(KERN_DEBUG "   dst=%pM src=%pM len=%d\n",
-	       tx->dst_addr, tx->src_addr,
-	       __be16_to_cpu(tx->len));
-}
-
-
-static int hostap_80211_header_parse(const struct sk_buff *skb,
-				     unsigned char *haddr)
-{
-	memcpy(haddr, skb_mac_header(skb) + 10, ETH_ALEN); /* addr2 */
-	return ETH_ALEN;
-}
-
-
-int hostap_80211_get_hdrlen(__le16 fc)
-{
-	if (ieee80211_is_data(fc) && ieee80211_has_a4 (fc))
-		return 30; /* Addr4 */
-	else if (ieee80211_is_cts(fc) || ieee80211_is_ack(fc))
-		return 10;
-	else if (ieee80211_is_ctl(fc))
-		return 16;
-
-	return 24;
-}
-
-
-static int prism2_close(struct net_device *dev)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-
-	PDEBUG(DEBUG_FLOW, "%s: prism2_close\n", dev->name);
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (dev == local->ddev) {
-		prism2_sta_deauth(local, WLAN_REASON_DEAUTH_LEAVING);
-	}
-#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-	if (!local->hostapd && dev == local->dev &&
-	    (!local->func->card_present || local->func->card_present(local)) &&
-	    local->hw_ready && local->ap && local->iw_mode == IW_MODE_MASTER)
-		hostap_deauth_all_stas(dev, local->ap, 1);
-#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
-
-	if (dev == local->dev) {
-		local->func->hw_shutdown(dev, HOSTAP_HW_ENABLE_CMDCOMPL);
-	}
-
-	if (netif_running(dev)) {
-		netif_stop_queue(dev);
-		netif_device_detach(dev);
-	}
-
-	cancel_work_sync(&local->reset_queue);
-	cancel_work_sync(&local->set_multicast_list_queue);
-	cancel_work_sync(&local->set_tim_queue);
-#ifndef PRISM2_NO_STATION_MODES
-	cancel_work_sync(&local->info_queue);
-#endif
-	cancel_work_sync(&local->comms_qual_update);
-
-	module_put(local->hw_module);
-
-	local->num_dev_open--;
-
-	if (dev != local->dev && local->dev->flags & IFF_UP &&
-	    local->master_dev_auto_open && local->num_dev_open == 1) {
-		/* Close master radio interface automatically if it was also
-		 * opened automatically and we are now closing the last
-		 * remaining non-master device. */
-		dev_close(local->dev);
-	}
-
-	return 0;
-}
-
-
-static int prism2_open(struct net_device *dev)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-
-	PDEBUG(DEBUG_FLOW, "%s: prism2_open\n", dev->name);
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (local->no_pri) {
-		printk(KERN_DEBUG "%s: could not set interface UP - no PRI "
-		       "f/w\n", dev->name);
-		return -ENODEV;
-	}
-
-	if ((local->func->card_present && !local->func->card_present(local)) ||
-	    local->hw_downloading)
-		return -ENODEV;
-
-	if (!try_module_get(local->hw_module))
-		return -ENODEV;
-	local->num_dev_open++;
-
-	if (!local->dev_enabled && local->func->hw_enable(dev, 1)) {
-		printk(KERN_WARNING "%s: could not enable MAC port\n",
-		       dev->name);
-		prism2_close(dev);
-		return -ENODEV;
-	}
-	if (!local->dev_enabled)
-		prism2_callback(local, PRISM2_CALLBACK_ENABLE);
-	local->dev_enabled = 1;
-
-	if (dev != local->dev && !(local->dev->flags & IFF_UP)) {
-		/* Master radio interface is needed for all operation, so open
-		 * it automatically when any virtual net_device is opened. */
-		local->master_dev_auto_open = 1;
-		dev_open(local->dev, NULL);
-	}
-
-	netif_device_attach(dev);
-	netif_start_queue(dev);
-
-	return 0;
-}
-
-
-static int prism2_set_mac_address(struct net_device *dev, void *p)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	struct list_head *ptr;
-	struct sockaddr *addr = p;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	if (local->func->set_rid(dev, HFA384X_RID_CNFOWNMACADDR, addr->sa_data,
-				 ETH_ALEN) < 0 || local->func->reset_port(dev))
-		return -EINVAL;
-
-	read_lock_bh(&local->iface_lock);
-	list_for_each(ptr, &local->hostap_interfaces) {
-		iface = list_entry(ptr, struct hostap_interface, list);
-		eth_hw_addr_set(iface->dev, addr->sa_data);
-	}
-	eth_hw_addr_set(local->dev, addr->sa_data);
-	read_unlock_bh(&local->iface_lock);
-
-	return 0;
-}
-
-
-/* TODO: to be further implemented as soon as Prism2 fully supports
- *       GroupAddresses and correct documentation is available */
-void hostap_set_multicast_list_queue(struct work_struct *work)
-{
-	local_info_t *local =
-		container_of(work, local_info_t, set_multicast_list_queue);
-	struct net_device *dev = local->dev;
-
-	if (hostap_set_word(dev, HFA384X_RID_PROMISCUOUSMODE,
-			    local->is_promisc)) {
-		printk(KERN_INFO "%s: %sabling promiscuous mode failed\n",
-		       dev->name, local->is_promisc ? "en" : "dis");
-	}
-}
-
-
-static void hostap_set_multicast_list(struct net_device *dev)
-{
-#if 0
-	/* FIX: promiscuous mode seems to be causing a lot of problems with
-	 * some station firmware versions (FCSErr frames, invalid MACPort, etc.
-	 * corrupted incoming frames). This code is now commented out while the
-	 * problems are investigated. */
-	struct hostap_interface *iface;
-	local_info_t *local;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-	if ((dev->flags & IFF_ALLMULTI) || (dev->flags & IFF_PROMISC)) {
-		local->is_promisc = 1;
-	} else {
-		local->is_promisc = 0;
-	}
-
-	schedule_work(&local->set_multicast_list_queue);
-#endif
-}
-
-
-static void prism2_tx_timeout(struct net_device *dev, unsigned int txqueue)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	struct hfa384x_regs regs;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	printk(KERN_WARNING "%s Tx timed out! Resetting card\n", dev->name);
-	netif_stop_queue(local->dev);
-
-	local->func->read_regs(dev, &regs);
-	printk(KERN_DEBUG "%s: CMD=%04x EVSTAT=%04x "
-	       "OFFSET0=%04x OFFSET1=%04x SWSUPPORT0=%04x\n",
-	       dev->name, regs.cmd, regs.evstat, regs.offset0, regs.offset1,
-	       regs.swsupport0);
-
-	local->func->schedule_reset(local);
-}
-
-const struct header_ops hostap_80211_ops = {
-	.create		= eth_header,
-	.cache		= eth_header_cache,
-	.cache_update	= eth_header_cache_update,
-	.parse		= hostap_80211_header_parse,
-};
-EXPORT_SYMBOL(hostap_80211_ops);
-
-
-static const struct net_device_ops hostap_netdev_ops = {
-	.ndo_start_xmit		= hostap_data_start_xmit,
-
-	.ndo_open		= prism2_open,
-	.ndo_stop		= prism2_close,
-	.ndo_siocdevprivate	= hostap_siocdevprivate,
-	.ndo_set_mac_address	= prism2_set_mac_address,
-	.ndo_set_rx_mode	= hostap_set_multicast_list,
-	.ndo_tx_timeout 	= prism2_tx_timeout,
-	.ndo_validate_addr	= eth_validate_addr,
-};
-
-static const struct net_device_ops hostap_mgmt_netdev_ops = {
-	.ndo_start_xmit		= hostap_mgmt_start_xmit,
-
-	.ndo_open		= prism2_open,
-	.ndo_stop		= prism2_close,
-	.ndo_siocdevprivate	= hostap_siocdevprivate,
-	.ndo_set_mac_address	= prism2_set_mac_address,
-	.ndo_set_rx_mode	= hostap_set_multicast_list,
-	.ndo_tx_timeout 	= prism2_tx_timeout,
-	.ndo_validate_addr	= eth_validate_addr,
-};
-
-static const struct net_device_ops hostap_master_ops = {
-	.ndo_start_xmit 	= hostap_master_start_xmit,
-
-	.ndo_open		= prism2_open,
-	.ndo_stop		= prism2_close,
-	.ndo_siocdevprivate	= hostap_siocdevprivate,
-	.ndo_set_mac_address	= prism2_set_mac_address,
-	.ndo_set_rx_mode	= hostap_set_multicast_list,
-	.ndo_tx_timeout 	= prism2_tx_timeout,
-	.ndo_validate_addr	= eth_validate_addr,
-};
-
-void hostap_setup_dev(struct net_device *dev, local_info_t *local,
-		      int type)
-{
-	struct hostap_interface *iface;
-
-	iface = netdev_priv(dev);
-	ether_setup(dev);
-	dev->min_mtu = PRISM2_MIN_MTU;
-	dev->max_mtu = PRISM2_MAX_MTU;
-	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
-
-	/* kernel callbacks */
-	if (iface) {
-		/* Currently, we point to the proper spy_data only on
-		 * the main_dev. This could be fixed. Jean II */
-		iface->wireless_data.spy_data = &iface->spy_data;
-		dev->wireless_data = &iface->wireless_data;
-	}
-	dev->wireless_handlers = &hostap_iw_handler_def;
-	dev->watchdog_timeo = TX_TIMEOUT;
-
-	switch(type) {
-	case HOSTAP_INTERFACE_AP:
-		dev->priv_flags |= IFF_NO_QUEUE;	/* use main radio device queue */
-		dev->netdev_ops = &hostap_mgmt_netdev_ops;
-		dev->type = ARPHRD_IEEE80211;
-		dev->header_ops = &hostap_80211_ops;
-		break;
-	case HOSTAP_INTERFACE_MASTER:
-		dev->netdev_ops = &hostap_master_ops;
-		break;
-	default:
-		dev->priv_flags |= IFF_NO_QUEUE;	/* use main radio device queue */
-		dev->netdev_ops = &hostap_netdev_ops;
-	}
-
-	dev->mtu = local->mtu;
-
-
-	dev->ethtool_ops = &prism2_ethtool_ops;
-
-}
-
-static int hostap_enable_hostapd(local_info_t *local, int rtnl_locked)
-{
-	struct net_device *dev = local->dev;
-
-	if (local->apdev)
-		return -EEXIST;
-
-	printk(KERN_DEBUG "%s: enabling hostapd mode\n", dev->name);
-
-	local->apdev = hostap_add_interface(local, HOSTAP_INTERFACE_AP,
-					    rtnl_locked, local->ddev->name,
-					    "ap");
-	if (local->apdev == NULL)
-		return -ENOMEM;
-
-	return 0;
-}
-
-
-static int hostap_disable_hostapd(local_info_t *local, int rtnl_locked)
-{
-	struct net_device *dev = local->dev;
-
-	printk(KERN_DEBUG "%s: disabling hostapd mode\n", dev->name);
-
-	hostap_remove_interface(local->apdev, rtnl_locked, 1);
-	local->apdev = NULL;
-
-	return 0;
-}
-
-
-static int hostap_enable_hostapd_sta(local_info_t *local, int rtnl_locked)
-{
-	struct net_device *dev = local->dev;
-
-	if (local->stadev)
-		return -EEXIST;
-
-	printk(KERN_DEBUG "%s: enabling hostapd STA mode\n", dev->name);
-
-	local->stadev = hostap_add_interface(local, HOSTAP_INTERFACE_STA,
-					     rtnl_locked, local->ddev->name,
-					     "sta");
-	if (local->stadev == NULL)
-		return -ENOMEM;
-
-	return 0;
-}
-
-
-static int hostap_disable_hostapd_sta(local_info_t *local, int rtnl_locked)
-{
-	struct net_device *dev = local->dev;
-
-	printk(KERN_DEBUG "%s: disabling hostapd mode\n", dev->name);
-
-	hostap_remove_interface(local->stadev, rtnl_locked, 1);
-	local->stadev = NULL;
-
-	return 0;
-}
-
-
-int hostap_set_hostapd(local_info_t *local, int val, int rtnl_locked)
-{
-	int ret;
-
-	if (val < 0 || val > 1)
-		return -EINVAL;
-
-	if (local->hostapd == val)
-		return 0;
-
-	if (val) {
-		ret = hostap_enable_hostapd(local, rtnl_locked);
-		if (ret == 0)
-			local->hostapd = 1;
-	} else {
-		local->hostapd = 0;
-		ret = hostap_disable_hostapd(local, rtnl_locked);
-		if (ret != 0)
-			local->hostapd = 1;
-	}
-
-	return ret;
-}
-
-
-int hostap_set_hostapd_sta(local_info_t *local, int val, int rtnl_locked)
-{
-	int ret;
-
-	if (val < 0 || val > 1)
-		return -EINVAL;
-
-	if (local->hostapd_sta == val)
-		return 0;
-
-	if (val) {
-		ret = hostap_enable_hostapd_sta(local, rtnl_locked);
-		if (ret == 0)
-			local->hostapd_sta = 1;
-	} else {
-		local->hostapd_sta = 0;
-		ret = hostap_disable_hostapd_sta(local, rtnl_locked);
-		if (ret != 0)
-			local->hostapd_sta = 1;
-	}
-
-
-	return ret;
-}
-
-
-int prism2_update_comms_qual(struct net_device *dev)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	int ret = 0;
-	struct hfa384x_comms_quality sq;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-	if (!local->sta_fw_ver)
-		ret = -1;
-	else if (local->sta_fw_ver >= PRISM2_FW_VER(1,3,1)) {
-		if (local->func->get_rid(local->dev,
-					 HFA384X_RID_DBMCOMMSQUALITY,
-					 &sq, sizeof(sq), 1) >= 0) {
-			local->comms_qual = (s16) le16_to_cpu(sq.comm_qual);
-			local->avg_signal = (s16) le16_to_cpu(sq.signal_level);
-			local->avg_noise = (s16) le16_to_cpu(sq.noise_level);
-			local->last_comms_qual_update = jiffies;
-		} else
-			ret = -1;
-	} else {
-		if (local->func->get_rid(local->dev, HFA384X_RID_COMMSQUALITY,
-					 &sq, sizeof(sq), 1) >= 0) {
-			local->comms_qual = le16_to_cpu(sq.comm_qual);
-			local->avg_signal = HFA384X_LEVEL_TO_dBm(
-				le16_to_cpu(sq.signal_level));
-			local->avg_noise = HFA384X_LEVEL_TO_dBm(
-				le16_to_cpu(sq.noise_level));
-			local->last_comms_qual_update = jiffies;
-		} else
-			ret = -1;
-	}
-
-	return ret;
-}
-
-
-int prism2_sta_send_mgmt(local_info_t *local, u8 *dst, u16 stype,
-			 u8 *body, size_t bodylen)
-{
-	struct sk_buff *skb;
-	struct hostap_ieee80211_mgmt *mgmt;
-	struct hostap_skb_tx_data *meta;
-	struct net_device *dev = local->dev;
-
-	skb = dev_alloc_skb(IEEE80211_MGMT_HDR_LEN + bodylen);
-	if (skb == NULL)
-		return -ENOMEM;
-
-	mgmt = skb_put_zero(skb, IEEE80211_MGMT_HDR_LEN);
-	mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | stype);
-	memcpy(mgmt->da, dst, ETH_ALEN);
-	memcpy(mgmt->sa, dev->dev_addr, ETH_ALEN);
-	memcpy(mgmt->bssid, dst, ETH_ALEN);
-	if (body)
-		skb_put_data(skb, body, bodylen);
-
-	meta = (struct hostap_skb_tx_data *) skb->cb;
-	memset(meta, 0, sizeof(*meta));
-	meta->magic = HOSTAP_SKB_TX_DATA_MAGIC;
-	meta->iface = netdev_priv(dev);
-
-	skb->dev = dev;
-	skb_reset_mac_header(skb);
-	skb_reset_network_header(skb);
-	dev_queue_xmit(skb);
-
-	return 0;
-}
-
-
-int prism2_sta_deauth(local_info_t *local, u16 reason)
-{
-	union iwreq_data wrqu;
-	int ret;
-	__le16 val = cpu_to_le16(reason);
-
-	if (local->iw_mode != IW_MODE_INFRA ||
-	    is_zero_ether_addr(local->bssid) ||
-	    ether_addr_equal(local->bssid, "\x44\x44\x44\x44\x44\x44"))
-		return 0;
-
-	ret = prism2_sta_send_mgmt(local, local->bssid, IEEE80211_STYPE_DEAUTH,
-				   (u8 *) &val, 2);
-	eth_zero_addr(wrqu.ap_addr.sa_data);
-	wireless_send_event(local->dev, SIOCGIWAP, &wrqu, NULL);
-	return ret;
-}
-
-
-struct proc_dir_entry *hostap_proc;
-
-static int __init hostap_init(void)
-{
-	if (init_net.proc_net != NULL) {
-		hostap_proc = proc_mkdir("hostap", init_net.proc_net);
-		if (!hostap_proc)
-			printk(KERN_WARNING "Failed to mkdir "
-			       "/proc/net/hostap\n");
-	} else
-		hostap_proc = NULL;
-
-	return 0;
-}
-
-
-static void __exit hostap_exit(void)
-{
-	if (hostap_proc != NULL) {
-		hostap_proc = NULL;
-		remove_proc_entry("hostap", init_net.proc_net);
-	}
-}
-
-
-EXPORT_SYMBOL(hostap_set_word);
-EXPORT_SYMBOL(hostap_set_string);
-EXPORT_SYMBOL(hostap_get_porttype);
-EXPORT_SYMBOL(hostap_set_encryption);
-EXPORT_SYMBOL(hostap_set_antsel);
-EXPORT_SYMBOL(hostap_set_roaming);
-EXPORT_SYMBOL(hostap_set_auth_algs);
-EXPORT_SYMBOL(hostap_dump_rx_header);
-EXPORT_SYMBOL(hostap_dump_tx_header);
-EXPORT_SYMBOL(hostap_80211_get_hdrlen);
-EXPORT_SYMBOL(hostap_setup_dev);
-EXPORT_SYMBOL(hostap_set_multicast_list_queue);
-EXPORT_SYMBOL(hostap_set_hostapd);
-EXPORT_SYMBOL(hostap_set_hostapd_sta);
-EXPORT_SYMBOL(hostap_add_interface);
-EXPORT_SYMBOL(hostap_remove_interface);
-EXPORT_SYMBOL(prism2_update_comms_qual);
-
-module_init(hostap_init);
-module_exit(hostap_exit);
diff --git a/drivers/net/wireless/intersil/hostap/hostap_pci.c b/drivers/net/wireless/intersil/hostap/hostap_pci.c
deleted file mode 100644
index 52d77506effd..000000000000
--- a/drivers/net/wireless/intersil/hostap/hostap_pci.c
+++ /dev/null
@@ -1,445 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-#define PRISM2_PCI
-
-/* Host AP driver's support for Intersil Prism2.5 PCI cards is based on
- * driver patches from Reyk Floeter <reyk@vantronix.net> and
- * Andy Warner <andyw@pobox.com> */
-
-#include <linux/module.h>
-#include <linux/if.h>
-#include <linux/skbuff.h>
-#include <linux/netdevice.h>
-#include <linux/slab.h>
-#include <linux/workqueue.h>
-#include <linux/wireless.h>
-#include <net/iw_handler.h>
-
-#include <linux/ioport.h>
-#include <linux/pci.h>
-#include <asm/io.h>
-
-#include "hostap_wlan.h"
-
-
-static char *dev_info = "hostap_pci";
-
-
-MODULE_AUTHOR("Jouni Malinen");
-MODULE_DESCRIPTION("Support for Intersil Prism2.5-based 802.11 wireless LAN "
-		   "PCI cards.");
-MODULE_LICENSE("GPL");
-
-
-/* struct local_info::hw_priv */
-struct hostap_pci_priv {
-	void __iomem *mem_start;
-};
-
-
-/* FIX: do we need mb/wmb/rmb with memory operations? */
-
-
-static const struct pci_device_id prism2_pci_id_table[] = {
-	/* Intersil Prism3 ISL3872 11Mb/s WLAN Controller */
-	{ 0x1260, 0x3872, PCI_ANY_ID, PCI_ANY_ID },
-	/* Intersil Prism2.5 ISL3874 11Mb/s WLAN Controller */
-	{ 0x1260, 0x3873, PCI_ANY_ID, PCI_ANY_ID },
-	/* Samsung MagicLAN SWL-2210P */
-	{ 0x167d, 0xa000, PCI_ANY_ID, PCI_ANY_ID },
-	{ 0 }
-};
-
-
-#ifdef PRISM2_IO_DEBUG
-
-static inline void hfa384x_outb_debug(struct net_device *dev, int a, u8 v)
-{
-	struct hostap_interface *iface;
-	struct hostap_pci_priv *hw_priv;
-	local_info_t *local;
-	unsigned long flags;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-	hw_priv = local->hw_priv;
-
-	spin_lock_irqsave(&local->lock, flags);
-	prism2_io_debug_add(dev, PRISM2_IO_DEBUG_CMD_OUTB, a, v);
-	writeb(v, hw_priv->mem_start + a);
-	spin_unlock_irqrestore(&local->lock, flags);
-}
-
-static inline u8 hfa384x_inb_debug(struct net_device *dev, int a)
-{
-	struct hostap_interface *iface;
-	struct hostap_pci_priv *hw_priv;
-	local_info_t *local;
-	unsigned long flags;
-	u8 v;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-	hw_priv = local->hw_priv;
-
-	spin_lock_irqsave(&local->lock, flags);
-	v = readb(hw_priv->mem_start + a);
-	prism2_io_debug_add(dev, PRISM2_IO_DEBUG_CMD_INB, a, v);
-	spin_unlock_irqrestore(&local->lock, flags);
-	return v;
-}
-
-static inline void hfa384x_outw_debug(struct net_device *dev, int a, u16 v)
-{
-	struct hostap_interface *iface;
-	struct hostap_pci_priv *hw_priv;
-	local_info_t *local;
-	unsigned long flags;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-	hw_priv = local->hw_priv;
-
-	spin_lock_irqsave(&local->lock, flags);
-	prism2_io_debug_add(dev, PRISM2_IO_DEBUG_CMD_OUTW, a, v);
-	writew(v, hw_priv->mem_start + a);
-	spin_unlock_irqrestore(&local->lock, flags);
-}
-
-static inline u16 hfa384x_inw_debug(struct net_device *dev, int a)
-{
-	struct hostap_interface *iface;
-	struct hostap_pci_priv *hw_priv;
-	local_info_t *local;
-	unsigned long flags;
-	u16 v;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-	hw_priv = local->hw_priv;
-
-	spin_lock_irqsave(&local->lock, flags);
-	v = readw(hw_priv->mem_start + a);
-	prism2_io_debug_add(dev, PRISM2_IO_DEBUG_CMD_INW, a, v);
-	spin_unlock_irqrestore(&local->lock, flags);
-	return v;
-}
-
-#define HFA384X_OUTB(v,a) hfa384x_outb_debug(dev, (a), (v))
-#define HFA384X_INB(a) hfa384x_inb_debug(dev, (a))
-#define HFA384X_OUTW(v,a) hfa384x_outw_debug(dev, (a), (v))
-#define HFA384X_INW(a) hfa384x_inw_debug(dev, (a))
-#define HFA384X_OUTW_DATA(v,a) hfa384x_outw_debug(dev, (a), le16_to_cpu((v)))
-#define HFA384X_INW_DATA(a) cpu_to_le16(hfa384x_inw_debug(dev, (a)))
-
-#else /* PRISM2_IO_DEBUG */
-
-static inline void hfa384x_outb(struct net_device *dev, int a, u8 v)
-{
-	struct hostap_interface *iface;
-	struct hostap_pci_priv *hw_priv;
-	iface = netdev_priv(dev);
-	hw_priv = iface->local->hw_priv;
-	writeb(v, hw_priv->mem_start + a);
-}
-
-static inline u8 hfa384x_inb(struct net_device *dev, int a)
-{
-	struct hostap_interface *iface;
-	struct hostap_pci_priv *hw_priv;
-	iface = netdev_priv(dev);
-	hw_priv = iface->local->hw_priv;
-	return readb(hw_priv->mem_start + a);
-}
-
-static inline void hfa384x_outw(struct net_device *dev, int a, u16 v)
-{
-	struct hostap_interface *iface;
-	struct hostap_pci_priv *hw_priv;
-	iface = netdev_priv(dev);
-	hw_priv = iface->local->hw_priv;
-	writew(v, hw_priv->mem_start + a);
-}
-
-static inline u16 hfa384x_inw(struct net_device *dev, int a)
-{
-	struct hostap_interface *iface;
-	struct hostap_pci_priv *hw_priv;
-	iface = netdev_priv(dev);
-	hw_priv = iface->local->hw_priv;
-	return readw(hw_priv->mem_start + a);
-}
-
-#define HFA384X_OUTB(v,a) hfa384x_outb(dev, (a), (v))
-#define HFA384X_INB(a) hfa384x_inb(dev, (a))
-#define HFA384X_OUTW(v,a) hfa384x_outw(dev, (a), (v))
-#define HFA384X_INW(a) hfa384x_inw(dev, (a))
-#define HFA384X_OUTW_DATA(v,a) hfa384x_outw(dev, (a), le16_to_cpu((v)))
-#define HFA384X_INW_DATA(a) cpu_to_le16(hfa384x_inw(dev, (a)))
-
-#endif /* PRISM2_IO_DEBUG */
-
-
-static int hfa384x_from_bap(struct net_device *dev, u16 bap, void *buf,
-			    int len)
-{
-	u16 d_off;
-	__le16 *pos;
-
-	d_off = (bap == 1) ? HFA384X_DATA1_OFF : HFA384X_DATA0_OFF;
-	pos = (__le16 *) buf;
-
-	for ( ; len > 1; len -= 2)
-		*pos++ = HFA384X_INW_DATA(d_off);
-
-	if (len & 1)
-		*((char *) pos) = HFA384X_INB(d_off);
-
-	return 0;
-}
-
-
-static int hfa384x_to_bap(struct net_device *dev, u16 bap, void *buf, int len)
-{
-	u16 d_off;
-	__le16 *pos;
-
-	d_off = (bap == 1) ? HFA384X_DATA1_OFF : HFA384X_DATA0_OFF;
-	pos = (__le16 *) buf;
-
-	for ( ; len > 1; len -= 2)
-		HFA384X_OUTW_DATA(*pos++, d_off);
-
-	if (len & 1)
-		HFA384X_OUTB(*((char *) pos), d_off);
-
-	return 0;
-}
-
-
-/* FIX: This might change at some point.. */
-#include "hostap_hw.c"
-
-static void prism2_pci_cor_sreset(local_info_t *local)
-{
-	struct net_device *dev = local->dev;
-	u16 reg;
-
-	reg = HFA384X_INB(HFA384X_PCICOR_OFF);
-	printk(KERN_DEBUG "%s: Original COR value: 0x%0x\n", dev->name, reg);
-
-	/* linux-wlan-ng uses extremely long hold and settle times for
-	 * COR sreset. A comment in the driver code mentions that the long
-	 * delays appear to be necessary. However, at least IBM 22P6901 seems
-	 * to work fine with shorter delays.
-	 *
-	 * Longer delays can be configured by uncommenting following line: */
-/* #define PRISM2_PCI_USE_LONG_DELAYS */
-
-#ifdef PRISM2_PCI_USE_LONG_DELAYS
-	int i;
-
-	HFA384X_OUTW(reg | 0x0080, HFA384X_PCICOR_OFF);
-	mdelay(250);
-
-	HFA384X_OUTW(reg & ~0x0080, HFA384X_PCICOR_OFF);
-	mdelay(500);
-
-	/* Wait for f/w to complete initialization (CMD:BUSY == 0) */
-	i = 2000000 / 10;
-	while ((HFA384X_INW(HFA384X_CMD_OFF) & HFA384X_CMD_BUSY) && --i)
-		udelay(10);
-
-#else /* PRISM2_PCI_USE_LONG_DELAYS */
-
-	HFA384X_OUTW(reg | 0x0080, HFA384X_PCICOR_OFF);
-	mdelay(2);
-	HFA384X_OUTW(reg & ~0x0080, HFA384X_PCICOR_OFF);
-	mdelay(2);
-
-#endif /* PRISM2_PCI_USE_LONG_DELAYS */
-
-	if (HFA384X_INW(HFA384X_CMD_OFF) & HFA384X_CMD_BUSY) {
-		printk(KERN_DEBUG "%s: COR sreset timeout\n", dev->name);
-	}
-}
-
-
-static void prism2_pci_genesis_reset(local_info_t *local, int hcr)
-{
-	struct net_device *dev = local->dev;
-
-	HFA384X_OUTW(0x00C5, HFA384X_PCICOR_OFF);
-	mdelay(10);
-	HFA384X_OUTW(hcr, HFA384X_PCIHCR_OFF);
-	mdelay(10);
-	HFA384X_OUTW(0x0045, HFA384X_PCICOR_OFF);
-	mdelay(10);
-}
-
-
-static struct prism2_helper_functions prism2_pci_funcs =
-{
-	.card_present	= NULL,
-	.cor_sreset	= prism2_pci_cor_sreset,
-	.genesis_reset	= prism2_pci_genesis_reset,
-	.hw_type	= HOSTAP_HW_PCI,
-};
-
-
-static int prism2_pci_probe(struct pci_dev *pdev,
-			    const struct pci_device_id *id)
-{
-	unsigned long phymem;
-	void __iomem *mem = NULL;
-	local_info_t *local = NULL;
-	struct net_device *dev = NULL;
-	static int cards_found /* = 0 */;
-	int irq_registered = 0;
-	struct hostap_interface *iface;
-	struct hostap_pci_priv *hw_priv;
-
-	hw_priv = kzalloc(sizeof(*hw_priv), GFP_KERNEL);
-	if (hw_priv == NULL)
-		return -ENOMEM;
-
-	if (pci_enable_device(pdev))
-		goto err_out_free;
-
-	phymem = pci_resource_start(pdev, 0);
-
-	if (!request_mem_region(phymem, pci_resource_len(pdev, 0), "Prism2")) {
-		printk(KERN_ERR "prism2: Cannot reserve PCI memory region\n");
-		goto err_out_disable;
-	}
-
-	mem = pci_ioremap_bar(pdev, 0);
-	if (mem == NULL) {
-		printk(KERN_ERR "prism2: Cannot remap PCI memory region\n") ;
-		goto fail;
-	}
-
-	dev = prism2_init_local_data(&prism2_pci_funcs, cards_found,
-				     &pdev->dev);
-	if (dev == NULL)
-		goto fail;
-	iface = netdev_priv(dev);
-	local = iface->local;
-	local->hw_priv = hw_priv;
-	cards_found++;
-
-        dev->irq = pdev->irq;
-        hw_priv->mem_start = mem;
-	dev->base_addr = (unsigned long) mem;
-
-	prism2_pci_cor_sreset(local);
-
-	pci_set_drvdata(pdev, dev);
-
-	if (request_irq(dev->irq, prism2_interrupt, IRQF_SHARED, dev->name,
-			dev)) {
-		printk(KERN_WARNING "%s: request_irq failed\n", dev->name);
-		goto fail;
-	} else
-		irq_registered = 1;
-
-	if (!local->pri_only && prism2_hw_config(dev, 1)) {
-		printk(KERN_DEBUG "%s: hardware initialization failed\n",
-		       dev_info);
-		goto fail;
-	}
-
-	printk(KERN_INFO "%s: Intersil Prism2.5 PCI: "
-	       "mem=0x%lx, irq=%d\n", dev->name, phymem, dev->irq);
-
-	return hostap_hw_ready(dev);
-
- fail:
-	if (irq_registered && dev)
-		free_irq(dev->irq, dev);
-
-	if (mem)
-		iounmap(mem);
-
-	release_mem_region(phymem, pci_resource_len(pdev, 0));
-
- err_out_disable:
-	pci_disable_device(pdev);
-	prism2_free_local_data(dev);
-
- err_out_free:
-	kfree(hw_priv);
-
-	return -ENODEV;
-}
-
-
-static void prism2_pci_remove(struct pci_dev *pdev)
-{
-	struct net_device *dev;
-	struct hostap_interface *iface;
-	void __iomem *mem_start;
-	struct hostap_pci_priv *hw_priv;
-
-	dev = pci_get_drvdata(pdev);
-	iface = netdev_priv(dev);
-	hw_priv = iface->local->hw_priv;
-
-	/* Reset the hardware, and ensure interrupts are disabled. */
-	prism2_pci_cor_sreset(iface->local);
-	hfa384x_disable_interrupts(dev);
-
-	if (dev->irq)
-		free_irq(dev->irq, dev);
-
-	mem_start = hw_priv->mem_start;
-	prism2_free_local_data(dev);
-	kfree(hw_priv);
-
-	iounmap(mem_start);
-
-	release_mem_region(pci_resource_start(pdev, 0),
-			   pci_resource_len(pdev, 0));
-	pci_disable_device(pdev);
-}
-
-static int __maybe_unused prism2_pci_suspend(struct device *dev_d)
-{
-	struct net_device *dev = dev_get_drvdata(dev_d);
-
-	if (netif_running(dev)) {
-		netif_stop_queue(dev);
-		netif_device_detach(dev);
-	}
-	prism2_suspend(dev);
-
-	return 0;
-}
-
-static int __maybe_unused prism2_pci_resume(struct device *dev_d)
-{
-	struct net_device *dev = dev_get_drvdata(dev_d);
-
-	prism2_hw_config(dev, 0);
-	if (netif_running(dev)) {
-		netif_device_attach(dev);
-		netif_start_queue(dev);
-	}
-
-	return 0;
-}
-
-MODULE_DEVICE_TABLE(pci, prism2_pci_id_table);
-
-static SIMPLE_DEV_PM_OPS(prism2_pci_pm_ops,
-			 prism2_pci_suspend,
-			 prism2_pci_resume);
-
-static struct pci_driver prism2_pci_driver = {
-	.name		= "hostap_pci",
-	.id_table	= prism2_pci_id_table,
-	.probe		= prism2_pci_probe,
-	.remove		= prism2_pci_remove,
-	.driver.pm	= &prism2_pci_pm_ops,
-};
-
-module_pci_driver(prism2_pci_driver);
diff --git a/drivers/net/wireless/intersil/hostap/hostap_plx.c b/drivers/net/wireless/intersil/hostap/hostap_plx.c
deleted file mode 100644
index 58247290fcbc..000000000000
--- a/drivers/net/wireless/intersil/hostap/hostap_plx.c
+++ /dev/null
@@ -1,617 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-#define PRISM2_PLX
-
-/* Host AP driver's support for PC Cards on PCI adapters using PLX9052 is
- * based on:
- * - Host AP driver patch from james@madingley.org
- * - linux-wlan-ng driver, Copyright (C) AbsoluteValue Systems, Inc.
- */
-
-
-#include <linux/module.h>
-#include <linux/if.h>
-#include <linux/skbuff.h>
-#include <linux/netdevice.h>
-#include <linux/slab.h>
-#include <linux/workqueue.h>
-#include <linux/wireless.h>
-#include <net/iw_handler.h>
-
-#include <linux/ioport.h>
-#include <linux/pci.h>
-#include <asm/io.h>
-
-#include "hostap_wlan.h"
-
-
-static char *dev_info = "hostap_plx";
-
-
-MODULE_AUTHOR("Jouni Malinen");
-MODULE_DESCRIPTION("Support for Intersil Prism2-based 802.11 wireless LAN "
-		   "cards (PLX).");
-MODULE_LICENSE("GPL");
-
-
-static int ignore_cis;
-module_param(ignore_cis, int, 0444);
-MODULE_PARM_DESC(ignore_cis, "Do not verify manfid information in CIS");
-
-
-/* struct local_info::hw_priv */
-struct hostap_plx_priv {
-	void __iomem *attr_mem;
-	unsigned int cor_offset;
-};
-
-
-#define PLX_MIN_ATTR_LEN 512	/* at least 2 x 256 is needed for CIS */
-#define COR_SRESET       0x80
-#define COR_LEVLREQ      0x40
-#define COR_ENABLE_FUNC  0x01
-/* PCI Configuration Registers */
-#define PLX_PCIIPR       0x3d   /* PCI Interrupt Pin */
-/* Local Configuration Registers */
-#define PLX_INTCSR       0x4c   /* Interrupt Control/Status Register */
-#define PLX_INTCSR_PCI_INTEN BIT(6) /* PCI Interrupt Enable */
-#define PLX_CNTRL        0x50
-#define PLX_CNTRL_SERIAL_EEPROM_PRESENT BIT(28)
-
-
-#define PLXDEV(vendor,dev,str) { vendor, dev, PCI_ANY_ID, PCI_ANY_ID }
-
-static const struct pci_device_id prism2_plx_id_table[] = {
-	PLXDEV(0x10b7, 0x7770, "3Com AirConnect PCI 777A"),
-	PLXDEV(0x111a, 0x1023, "Siemens SpeedStream SS1023"),
-	PLXDEV(0x126c, 0x8030, "Nortel emobility"),
-	PLXDEV(0x1562, 0x0001, "Symbol LA-4123"),
-	PLXDEV(0x1385, 0x4100, "Netgear MA301"),
-	PLXDEV(0x15e8, 0x0130, "National Datacomm NCP130 (PLX9052)"),
-	PLXDEV(0x15e8, 0x0131, "National Datacomm NCP130 (TMD7160)"),
-	PLXDEV(0x1638, 0x1100, "Eumitcom WL11000"),
-	PLXDEV(0x16ab, 0x1100, "Global Sun Tech GL24110P"),
-	PLXDEV(0x16ab, 0x1101, "Global Sun Tech GL24110P (?)"),
-	PLXDEV(0x16ab, 0x1102, "Linksys WPC11 with WDT11"),
-	PLXDEV(0x16ab, 0x1103, "Longshine 8031"),
-	PLXDEV(0x16ec, 0x3685, "US Robotics USR2415"),
-	PLXDEV(0xec80, 0xec00, "Belkin F5D6000"),
-	{ 0 }
-};
-
-
-/* Array of known Prism2/2.5 PC Card manufactured ids. If your card's manfid
- * is not listed here, you will need to add it here to get the driver
- * initialized. */
-static struct prism2_plx_manfid {
-	u16 manfid1, manfid2;
-} prism2_plx_known_manfids[] = {
-	{ 0x000b, 0x7110 } /* D-Link DWL-650 Rev. P1 */,
-	{ 0x000b, 0x7300 } /* Philips 802.11b WLAN PCMCIA */,
-	{ 0x0101, 0x0777 } /* 3Com AirConnect PCI 777A */,
-	{ 0x0126, 0x8000 } /* Proxim RangeLAN */,
-	{ 0x0138, 0x0002 } /* Compaq WL100 */,
-	{ 0x0156, 0x0002 } /* Intersil Prism II Ref. Design (and others) */,
-	{ 0x026f, 0x030b } /* Buffalo WLI-CF-S11G */,
-	{ 0x0274, 0x1612 } /* Linksys WPC11 Ver 2.5 */,
-	{ 0x0274, 0x1613 } /* Linksys WPC11 Ver 3 */,
-	{ 0x028a, 0x0002 } /* D-Link DRC-650 */,
-	{ 0x0250, 0x0002 } /* Samsung SWL2000-N */,
-	{ 0xc250, 0x0002 } /* EMTAC A2424i */,
-	{ 0xd601, 0x0002 } /* Z-Com XI300 */,
-	{ 0xd601, 0x0005 } /* Zcomax XI-325H 200mW */,
-	{ 0, 0}
-};
-
-
-#ifdef PRISM2_IO_DEBUG
-
-static inline void hfa384x_outb_debug(struct net_device *dev, int a, u8 v)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	unsigned long flags;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	spin_lock_irqsave(&local->lock, flags);
-	prism2_io_debug_add(dev, PRISM2_IO_DEBUG_CMD_OUTB, a, v);
-	outb(v, dev->base_addr + a);
-	spin_unlock_irqrestore(&local->lock, flags);
-}
-
-static inline u8 hfa384x_inb_debug(struct net_device *dev, int a)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	unsigned long flags;
-	u8 v;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	spin_lock_irqsave(&local->lock, flags);
-	v = inb(dev->base_addr + a);
-	prism2_io_debug_add(dev, PRISM2_IO_DEBUG_CMD_INB, a, v);
-	spin_unlock_irqrestore(&local->lock, flags);
-	return v;
-}
-
-static inline void hfa384x_outw_debug(struct net_device *dev, int a, u16 v)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	unsigned long flags;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	spin_lock_irqsave(&local->lock, flags);
-	prism2_io_debug_add(dev, PRISM2_IO_DEBUG_CMD_OUTW, a, v);
-	outw(v, dev->base_addr + a);
-	spin_unlock_irqrestore(&local->lock, flags);
-}
-
-static inline u16 hfa384x_inw_debug(struct net_device *dev, int a)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	unsigned long flags;
-	u16 v;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	spin_lock_irqsave(&local->lock, flags);
-	v = inw(dev->base_addr + a);
-	prism2_io_debug_add(dev, PRISM2_IO_DEBUG_CMD_INW, a, v);
-	spin_unlock_irqrestore(&local->lock, flags);
-	return v;
-}
-
-static inline void hfa384x_outsw_debug(struct net_device *dev, int a,
-				       u8 *buf, int wc)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	unsigned long flags;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	spin_lock_irqsave(&local->lock, flags);
-	prism2_io_debug_add(dev, PRISM2_IO_DEBUG_CMD_OUTSW, a, wc);
-	outsw(dev->base_addr + a, buf, wc);
-	spin_unlock_irqrestore(&local->lock, flags);
-}
-
-static inline void hfa384x_insw_debug(struct net_device *dev, int a,
-				      u8 *buf, int wc)
-{
-	struct hostap_interface *iface;
-	local_info_t *local;
-	unsigned long flags;
-
-	iface = netdev_priv(dev);
-	local = iface->local;
-
-	spin_lock_irqsave(&local->lock, flags);
-	prism2_io_debug_add(dev, PRISM2_IO_DEBUG_CMD_INSW, a, wc);
-	insw(dev->base_addr + a, buf, wc);
-	spin_unlock_irqrestore(&local->lock, flags);
-}
-
-#define HFA384X_OUTB(v,a) hfa384x_outb_debug(dev, (a), (v))
-#define HFA384X_INB(a) hfa384x_inb_debug(dev, (a))
-#define HFA384X_OUTW(v,a) hfa384x_outw_debug(dev, (a), (v))
-#define HFA384X_INW(a) hfa384x_inw_debug(dev, (a))
-#define HFA384X_OUTSW(a, buf, wc) hfa384x_outsw_debug(dev, (a), (buf), (wc))
-#define HFA384X_INSW(a, buf, wc) hfa384x_insw_debug(dev, (a), (buf), (wc))
-
-#else /* PRISM2_IO_DEBUG */
-
-#define HFA384X_OUTB(v,a) outb((v), dev->base_addr + (a))
-#define HFA384X_INB(a) inb(dev->base_addr + (a))
-#define HFA384X_OUTW(v,a) outw((v), dev->base_addr + (a))
-#define HFA384X_INW(a) inw(dev->base_addr + (a))
-#define HFA384X_INSW(a, buf, wc) insw(dev->base_addr + (a), buf, wc)
-#define HFA384X_OUTSW(a, buf, wc) outsw(dev->base_addr + (a), buf, wc)
-
-#endif /* PRISM2_IO_DEBUG */
-
-
-static int hfa384x_from_bap(struct net_device *dev, u16 bap, void *buf,
-			    int len)
-{
-	u16 d_off;
-	u16 *pos;
-
-	d_off = (bap == 1) ? HFA384X_DATA1_OFF : HFA384X_DATA0_OFF;
-	pos = (u16 *) buf;
-
-	if (len / 2)
-		HFA384X_INSW(d_off, buf, len / 2);
-	pos += len / 2;
-
-	if (len & 1)
-		*((char *) pos) = HFA384X_INB(d_off);
-
-	return 0;
-}
-
-
-static int hfa384x_to_bap(struct net_device *dev, u16 bap, void *buf, int len)
-{
-	u16 d_off;
-	u16 *pos;
-
-	d_off = (bap == 1) ? HFA384X_DATA1_OFF : HFA384X_DATA0_OFF;
-	pos = (u16 *) buf;
-
-	if (len / 2)
-		HFA384X_OUTSW(d_off, buf, len / 2);
-	pos += len / 2;
-
-	if (len & 1)
-		HFA384X_OUTB(*((char *) pos), d_off);
-
-	return 0;
-}
-
-
-/* FIX: This might change at some point.. */
-#include "hostap_hw.c"
-
-
-static void prism2_plx_cor_sreset(local_info_t *local)
-{
-	unsigned char corsave;
-	struct hostap_plx_priv *hw_priv = local->hw_priv;
-
-	printk(KERN_DEBUG "%s: Doing reset via direct COR access.\n",
-	       dev_info);
-
-	/* Set sreset bit of COR and clear it after hold time */
-
-	if (hw_priv->attr_mem == NULL) {
-		/* TMD7160 - COR at card's first I/O addr */
-		corsave = inb(hw_priv->cor_offset);
-		outb(corsave | COR_SRESET, hw_priv->cor_offset);
-		mdelay(2);
-		outb(corsave & ~COR_SRESET, hw_priv->cor_offset);
-		mdelay(2);
-	} else {
-		/* PLX9052 */
-		corsave = readb(hw_priv->attr_mem + hw_priv->cor_offset);
-		writeb(corsave | COR_SRESET,
-		       hw_priv->attr_mem + hw_priv->cor_offset);
-		mdelay(2);
-		writeb(corsave & ~COR_SRESET,
-		       hw_priv->attr_mem + hw_priv->cor_offset);
-		mdelay(2);
-	}
-}
-
-
-static void prism2_plx_genesis_reset(local_info_t *local, int hcr)
-{
-	unsigned char corsave;
-	struct hostap_plx_priv *hw_priv = local->hw_priv;
-
-	if (hw_priv->attr_mem == NULL) {
-		/* TMD7160 - COR at card's first I/O addr */
-		corsave = inb(hw_priv->cor_offset);
-		outb(corsave | COR_SRESET, hw_priv->cor_offset);
-		mdelay(10);
-		outb(hcr, hw_priv->cor_offset + 2);
-		mdelay(10);
-		outb(corsave & ~COR_SRESET, hw_priv->cor_offset);
-		mdelay(10);
-	} else {
-		/* PLX9052 */
-		corsave = readb(hw_priv->attr_mem + hw_priv->cor_offset);
-		writeb(corsave | COR_SRESET,
-		       hw_priv->attr_mem + hw_priv->cor_offset);
-		mdelay(10);
-		writeb(hcr, hw_priv->attr_mem + hw_priv->cor_offset + 2);
-		mdelay(10);
-		writeb(corsave & ~COR_SRESET,
-		       hw_priv->attr_mem + hw_priv->cor_offset);
-		mdelay(10);
-	}
-}
-
-
-static struct prism2_helper_functions prism2_plx_funcs =
-{
-	.card_present	= NULL,
-	.cor_sreset	= prism2_plx_cor_sreset,
-	.genesis_reset	= prism2_plx_genesis_reset,
-	.hw_type	= HOSTAP_HW_PLX,
-};
-
-
-static int prism2_plx_check_cis(void __iomem *attr_mem, int attr_len,
-				unsigned int *cor_offset,
-				unsigned int *cor_index)
-{
-#define CISTPL_CONFIG 0x1A
-#define CISTPL_MANFID 0x20
-#define CISTPL_END 0xFF
-#define CIS_MAX_LEN 256
-	u8 *cis;
-	int i, pos;
-	unsigned int rmsz, rasz, manfid1, manfid2;
-	struct prism2_plx_manfid *manfid;
-
-	cis = kmalloc(CIS_MAX_LEN, GFP_KERNEL);
-	if (cis == NULL)
-		return -ENOMEM;
-
-	/* read CIS; it is in even offsets in the beginning of attr_mem */
-	for (i = 0; i < CIS_MAX_LEN; i++)
-		cis[i] = readb(attr_mem + 2 * i);
-	printk(KERN_DEBUG "%s: CIS: %6ph ...\n", dev_info, cis);
-
-	/* set reasonable defaults for Prism2 cards just in case CIS parsing
-	 * fails */
-	*cor_offset = 0x3e0;
-	*cor_index = 0x01;
-	manfid1 = manfid2 = 0;
-
-	pos = 0;
-	while (pos < CIS_MAX_LEN - 1 && cis[pos] != CISTPL_END) {
-		if (pos + 2 + cis[pos + 1] > CIS_MAX_LEN)
-			goto cis_error;
-
-		switch (cis[pos]) {
-		case CISTPL_CONFIG:
-			if (cis[pos + 1] < 2)
-				goto cis_error;
-			rmsz = (cis[pos + 2] & 0x3c) >> 2;
-			rasz = cis[pos + 2] & 0x03;
-			if (4 + rasz + rmsz > cis[pos + 1])
-				goto cis_error;
-			*cor_index = cis[pos + 3] & 0x3F;
-			*cor_offset = 0;
-			for (i = 0; i <= rasz; i++)
-				*cor_offset += cis[pos + 4 + i] << (8 * i);
-			printk(KERN_DEBUG "%s: cor_index=0x%x "
-			       "cor_offset=0x%x\n", dev_info,
-			       *cor_index, *cor_offset);
-			if (*cor_offset > attr_len) {
-				printk(KERN_ERR "%s: COR offset not within "
-				       "attr_mem\n", dev_info);
-				kfree(cis);
-				return -1;
-			}
-			break;
-
-		case CISTPL_MANFID:
-			if (cis[pos + 1] < 4)
-				goto cis_error;
-			manfid1 = cis[pos + 2] + (cis[pos + 3] << 8);
-			manfid2 = cis[pos + 4] + (cis[pos + 5] << 8);
-			printk(KERN_DEBUG "%s: manfid=0x%04x, 0x%04x\n",
-			       dev_info, manfid1, manfid2);
-			break;
-		}
-
-		pos += cis[pos + 1] + 2;
-	}
-
-	if (pos >= CIS_MAX_LEN || cis[pos] != CISTPL_END)
-		goto cis_error;
-
-	for (manfid = prism2_plx_known_manfids; manfid->manfid1 != 0; manfid++)
-		if (manfid1 == manfid->manfid1 && manfid2 == manfid->manfid2) {
-			kfree(cis);
-			return 0;
-		}
-
-	printk(KERN_INFO "%s: unknown manfid 0x%04x, 0x%04x - assuming this is"
-	       " not supported card\n", dev_info, manfid1, manfid2);
-	goto fail;
-
- cis_error:
-	printk(KERN_WARNING "%s: invalid CIS data\n", dev_info);
-
- fail:
-	kfree(cis);
-	if (ignore_cis) {
-		printk(KERN_INFO "%s: ignore_cis parameter set - ignoring "
-		       "errors during CIS verification\n", dev_info);
-		return 0;
-	}
-	return -1;
-}
-
-
-static int prism2_plx_probe(struct pci_dev *pdev,
-			    const struct pci_device_id *id)
-{
-	unsigned int pccard_ioaddr, plx_ioaddr;
-	unsigned long pccard_attr_mem;
-	unsigned int pccard_attr_len;
-	void __iomem *attr_mem = NULL;
-	unsigned int cor_offset = 0, cor_index = 0;
-	u32 reg;
-	local_info_t *local = NULL;
-	struct net_device *dev = NULL;
-	struct hostap_interface *iface;
-	static int cards_found /* = 0 */;
-	int irq_registered = 0;
-	int tmd7160;
-	struct hostap_plx_priv *hw_priv;
-
-	hw_priv = kzalloc(sizeof(*hw_priv), GFP_KERNEL);
-	if (hw_priv == NULL)
-		return -ENOMEM;
-
-	if (pci_enable_device(pdev))
-		goto err_out_free;
-
-	/* National Datacomm NCP130 based on TMD7160, not PLX9052. */
-	tmd7160 = (pdev->vendor == 0x15e8) && (pdev->device == 0x0131);
-
-	plx_ioaddr = pci_resource_start(pdev, 1);
-	pccard_ioaddr = pci_resource_start(pdev, tmd7160 ? 2 : 3);
-
-	if (tmd7160) {
-		/* TMD7160 */
-		attr_mem = NULL; /* no access to PC Card attribute memory */
-
-		printk(KERN_INFO "TMD7160 PCI/PCMCIA adapter: io=0x%x, "
-		       "irq=%d, pccard_io=0x%x\n",
-		       plx_ioaddr, pdev->irq, pccard_ioaddr);
-
-		cor_offset = plx_ioaddr;
-		cor_index = 0x04;
-
-		outb(cor_index | COR_LEVLREQ | COR_ENABLE_FUNC, plx_ioaddr);
-		mdelay(1);
-		reg = inb(plx_ioaddr);
-		if (reg != (cor_index | COR_LEVLREQ | COR_ENABLE_FUNC)) {
-			printk(KERN_ERR "%s: Error setting COR (expected="
-			       "0x%02x, was=0x%02x)\n", dev_info,
-			       cor_index | COR_LEVLREQ | COR_ENABLE_FUNC, reg);
-			goto fail;
-		}
-	} else {
-		/* PLX9052 */
-		pccard_attr_mem = pci_resource_start(pdev, 2);
-		pccard_attr_len = pci_resource_len(pdev, 2);
-		if (pccard_attr_len < PLX_MIN_ATTR_LEN)
-			goto fail;
-
-
-		attr_mem = ioremap(pccard_attr_mem, pccard_attr_len);
-		if (attr_mem == NULL) {
-			printk(KERN_ERR "%s: cannot remap attr_mem\n",
-			       dev_info);
-			goto fail;
-		}
-
-		printk(KERN_INFO "PLX9052 PCI/PCMCIA adapter: "
-		       "mem=0x%lx, plx_io=0x%x, irq=%d, pccard_io=0x%x\n",
-		       pccard_attr_mem, plx_ioaddr, pdev->irq, pccard_ioaddr);
-
-		if (prism2_plx_check_cis(attr_mem, pccard_attr_len,
-					 &cor_offset, &cor_index)) {
-			printk(KERN_INFO "Unknown PC Card CIS - not a "
-			       "Prism2/2.5 card?\n");
-			goto fail;
-		}
-
-		printk(KERN_DEBUG "Prism2/2.5 PC Card detected in PLX9052 "
-		       "adapter\n");
-
-		/* Write COR to enable PC Card */
-		writeb(cor_index | COR_LEVLREQ | COR_ENABLE_FUNC,
-		       attr_mem + cor_offset);
-
-		/* Enable PCI interrupts if they are not already enabled */
-		reg = inl(plx_ioaddr + PLX_INTCSR);
-		printk(KERN_DEBUG "PLX_INTCSR=0x%x\n", reg);
-		if (!(reg & PLX_INTCSR_PCI_INTEN)) {
-			outl(reg | PLX_INTCSR_PCI_INTEN,
-			     plx_ioaddr + PLX_INTCSR);
-			if (!(inl(plx_ioaddr + PLX_INTCSR) &
-			      PLX_INTCSR_PCI_INTEN)) {
-				printk(KERN_WARNING "%s: Could not enable "
-				       "Local Interrupts\n", dev_info);
-				goto fail;
-			}
-		}
-
-		reg = inl(plx_ioaddr + PLX_CNTRL);
-		printk(KERN_DEBUG "PLX_CNTRL=0x%x (Serial EEPROM "
-		       "present=%d)\n",
-		       reg, (reg & PLX_CNTRL_SERIAL_EEPROM_PRESENT) != 0);
-		/* should set PLX_PCIIPR to 0x01 (INTA#) if Serial EEPROM is
-		 * not present; but are there really such cards in use(?) */
-	}
-
-	dev = prism2_init_local_data(&prism2_plx_funcs, cards_found,
-				     &pdev->dev);
-	if (dev == NULL)
-		goto fail;
-	iface = netdev_priv(dev);
-	local = iface->local;
-	local->hw_priv = hw_priv;
-	cards_found++;
-
-	dev->irq = pdev->irq;
-	dev->base_addr = pccard_ioaddr;
-	hw_priv->attr_mem = attr_mem;
-	hw_priv->cor_offset = cor_offset;
-
-	pci_set_drvdata(pdev, dev);
-
-	if (request_irq(dev->irq, prism2_interrupt, IRQF_SHARED, dev->name,
-			dev)) {
-		printk(KERN_WARNING "%s: request_irq failed\n", dev->name);
-		goto fail;
-	} else
-		irq_registered = 1;
-
-	if (prism2_hw_config(dev, 1)) {
-		printk(KERN_DEBUG "%s: hardware initialization failed\n",
-		       dev_info);
-		goto fail;
-	}
-
-	return hostap_hw_ready(dev);
-
- fail:
-	if (irq_registered && dev)
-		free_irq(dev->irq, dev);
-
-	if (attr_mem)
-		iounmap(attr_mem);
-
-	pci_disable_device(pdev);
-	prism2_free_local_data(dev);
-
- err_out_free:
-	kfree(hw_priv);
-
-	return -ENODEV;
-}
-
-
-static void prism2_plx_remove(struct pci_dev *pdev)
-{
-	struct net_device *dev;
-	struct hostap_interface *iface;
-	struct hostap_plx_priv *hw_priv;
-
-	dev = pci_get_drvdata(pdev);
-	iface = netdev_priv(dev);
-	hw_priv = iface->local->hw_priv;
-
-	/* Reset the hardware, and ensure interrupts are disabled. */
-	prism2_plx_cor_sreset(iface->local);
-	hfa384x_disable_interrupts(dev);
-
-	if (hw_priv->attr_mem)
-		iounmap(hw_priv->attr_mem);
-	if (dev->irq)
-		free_irq(dev->irq, dev);
-
-	prism2_free_local_data(dev);
-	kfree(hw_priv);
-	pci_disable_device(pdev);
-}
-
-
-MODULE_DEVICE_TABLE(pci, prism2_plx_id_table);
-
-static struct pci_driver prism2_plx_driver = {
-	.name		= "hostap_plx",
-	.id_table	= prism2_plx_id_table,
-	.probe		= prism2_plx_probe,
-	.remove		= prism2_plx_remove,
-};
-
-module_pci_driver(prism2_plx_driver);
diff --git a/drivers/net/wireless/intersil/hostap/hostap_proc.c b/drivers/net/wireless/intersil/hostap/hostap_proc.c
deleted file mode 100644
index 61f68786056f..000000000000
--- a/drivers/net/wireless/intersil/hostap/hostap_proc.c
+++ /dev/null
@@ -1,411 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* /proc routines for Host AP driver */
-
-#include <linux/types.h>
-#include <linux/proc_fs.h>
-#include <linux/export.h>
-#include <net/lib80211.h>
-
-#include "hostap_wlan.h"
-#include "hostap.h"
-
-#define PROC_LIMIT (PAGE_SIZE - 80)
-
-#if !defined(PRISM2_NO_PROCFS_DEBUG) && defined(CONFIG_PROC_FS)
-static int prism2_debug_proc_show(struct seq_file *m, void *v)
-{
-	local_info_t *local = m->private;
-	int i;
-
-	seq_printf(m, "next_txfid=%d next_alloc=%d\n",
-		   local->next_txfid, local->next_alloc);
-	for (i = 0; i < PRISM2_TXFID_COUNT; i++)
-		seq_printf(m, "FID: tx=%04X intransmit=%04X\n",
-			   local->txfid[i], local->intransmitfid[i]);
-	seq_printf(m, "FW TX rate control: %d\n", local->fw_tx_rate_control);
-	seq_printf(m, "beacon_int=%d\n", local->beacon_int);
-	seq_printf(m, "dtim_period=%d\n", local->dtim_period);
-	seq_printf(m, "wds_max_connections=%d\n", local->wds_max_connections);
-	seq_printf(m, "dev_enabled=%d\n", local->dev_enabled);
-	seq_printf(m, "sw_tick_stuck=%d\n", local->sw_tick_stuck);
-	for (i = 0; i < WEP_KEYS; i++) {
-		if (local->crypt_info.crypt[i] &&
-		    local->crypt_info.crypt[i]->ops) {
-			seq_printf(m, "crypt[%d]=%s\n", i,
-				   local->crypt_info.crypt[i]->ops->name);
-		}
-	}
-	seq_printf(m, "pri_only=%d\n", local->pri_only);
-	seq_printf(m, "pci=%d\n", local->func->hw_type == HOSTAP_HW_PCI);
-	seq_printf(m, "sram_type=%d\n", local->sram_type);
-	seq_printf(m, "no_pri=%d\n", local->no_pri);
-
-	return 0;
-}
-#endif
-
-#ifdef CONFIG_PROC_FS
-static int prism2_stats_proc_show(struct seq_file *m, void *v)
-{
-	local_info_t *local = m->private;
-	struct comm_tallies_sums *sums = &local->comm_tallies;
-
-	seq_printf(m, "TxUnicastFrames=%u\n", sums->tx_unicast_frames);
-	seq_printf(m, "TxMulticastframes=%u\n", sums->tx_multicast_frames);
-	seq_printf(m, "TxFragments=%u\n", sums->tx_fragments);
-	seq_printf(m, "TxUnicastOctets=%u\n", sums->tx_unicast_octets);
-	seq_printf(m, "TxMulticastOctets=%u\n", sums->tx_multicast_octets);
-	seq_printf(m, "TxDeferredTransmissions=%u\n",
-		   sums->tx_deferred_transmissions);
-	seq_printf(m, "TxSingleRetryFrames=%u\n", sums->tx_single_retry_frames);
-	seq_printf(m, "TxMultipleRetryFrames=%u\n",
-		   sums->tx_multiple_retry_frames);
-	seq_printf(m, "TxRetryLimitExceeded=%u\n",
-		   sums->tx_retry_limit_exceeded);
-	seq_printf(m, "TxDiscards=%u\n", sums->tx_discards);
-	seq_printf(m, "RxUnicastFrames=%u\n", sums->rx_unicast_frames);
-	seq_printf(m, "RxMulticastFrames=%u\n", sums->rx_multicast_frames);
-	seq_printf(m, "RxFragments=%u\n", sums->rx_fragments);
-	seq_printf(m, "RxUnicastOctets=%u\n", sums->rx_unicast_octets);
-	seq_printf(m, "RxMulticastOctets=%u\n", sums->rx_multicast_octets);
-	seq_printf(m, "RxFCSErrors=%u\n", sums->rx_fcs_errors);
-	seq_printf(m, "RxDiscardsNoBuffer=%u\n", sums->rx_discards_no_buffer);
-	seq_printf(m, "TxDiscardsWrongSA=%u\n", sums->tx_discards_wrong_sa);
-	seq_printf(m, "RxDiscardsWEPUndecryptable=%u\n",
-		   sums->rx_discards_wep_undecryptable);
-	seq_printf(m, "RxMessageInMsgFragments=%u\n",
-		   sums->rx_message_in_msg_fragments);
-	seq_printf(m, "RxMessageInBadMsgFragments=%u\n",
-		   sums->rx_message_in_bad_msg_fragments);
-	/* FIX: this may grow too long for one page(?) */
-
-	return 0;
-}
-#endif
-
-static int prism2_wds_proc_show(struct seq_file *m, void *v)
-{
-	struct list_head *ptr = v;
-	struct hostap_interface *iface;
-
-	iface = list_entry(ptr, struct hostap_interface, list);
-	if (iface->type == HOSTAP_INTERFACE_WDS)
-		seq_printf(m, "%s\t%pM\n",
-			   iface->dev->name, iface->u.wds.remote_addr);
-	return 0;
-}
-
-static void *prism2_wds_proc_start(struct seq_file *m, loff_t *_pos)
-{
-	local_info_t *local = pde_data(file_inode(m->file));
-	read_lock_bh(&local->iface_lock);
-	return seq_list_start(&local->hostap_interfaces, *_pos);
-}
-
-static void *prism2_wds_proc_next(struct seq_file *m, void *v, loff_t *_pos)
-{
-	local_info_t *local = pde_data(file_inode(m->file));
-	return seq_list_next(v, &local->hostap_interfaces, _pos);
-}
-
-static void prism2_wds_proc_stop(struct seq_file *m, void *v)
-{
-	local_info_t *local = pde_data(file_inode(m->file));
-	read_unlock_bh(&local->iface_lock);
-}
-
-static const struct seq_operations prism2_wds_proc_seqops = {
-	.start	= prism2_wds_proc_start,
-	.next	= prism2_wds_proc_next,
-	.stop	= prism2_wds_proc_stop,
-	.show	= prism2_wds_proc_show,
-};
-
-static int prism2_bss_list_proc_show(struct seq_file *m, void *v)
-{
-	local_info_t *local = pde_data(file_inode(m->file));
-	struct list_head *ptr = v;
-	struct hostap_bss_info *bss;
-
-	if (ptr == &local->bss_list) {
-		seq_printf(m, "#BSSID\tlast_update\tcount\tcapab_info\tSSID(txt)\t"
-			   "SSID(hex)\tWPA IE\n");
-		return 0;
-	}
-
-	bss = list_entry(ptr, struct hostap_bss_info, list);
-	seq_printf(m, "%pM\t%lu\t%u\t0x%x\t",
-		   bss->bssid, bss->last_update,
-		   bss->count, bss->capab_info);
-
-	seq_printf(m, "%*pE", (int)bss->ssid_len, bss->ssid);
-
-	seq_putc(m, '\t');
-	seq_printf(m, "%*phN", (int)bss->ssid_len, bss->ssid);
-	seq_putc(m, '\t');
-	seq_printf(m, "%*phN", (int)bss->wpa_ie_len, bss->wpa_ie);
-	seq_putc(m, '\n');
-	return 0;
-}
-
-static void *prism2_bss_list_proc_start(struct seq_file *m, loff_t *_pos)
-	__acquires(&local->lock)
-{
-	local_info_t *local = pde_data(file_inode(m->file));
-	spin_lock_bh(&local->lock);
-	return seq_list_start_head(&local->bss_list, *_pos);
-}
-
-static void *prism2_bss_list_proc_next(struct seq_file *m, void *v, loff_t *_pos)
-{
-	local_info_t *local = pde_data(file_inode(m->file));
-	return seq_list_next(v, &local->bss_list, _pos);
-}
-
-static void prism2_bss_list_proc_stop(struct seq_file *m, void *v)
-	__releases(&local->lock)
-{
-	local_info_t *local = pde_data(file_inode(m->file));
-	spin_unlock_bh(&local->lock);
-}
-
-static const struct seq_operations prism2_bss_list_proc_seqops = {
-	.start	= prism2_bss_list_proc_start,
-	.next	= prism2_bss_list_proc_next,
-	.stop	= prism2_bss_list_proc_stop,
-	.show	= prism2_bss_list_proc_show,
-};
-
-#ifdef CONFIG_PROC_FS
-static int prism2_crypt_proc_show(struct seq_file *m, void *v)
-{
-	local_info_t *local = m->private;
-	int i;
-
-	seq_printf(m, "tx_keyidx=%d\n", local->crypt_info.tx_keyidx);
-	for (i = 0; i < WEP_KEYS; i++) {
-		if (local->crypt_info.crypt[i] &&
-		    local->crypt_info.crypt[i]->ops &&
-		    local->crypt_info.crypt[i]->ops->print_stats) {
-			local->crypt_info.crypt[i]->ops->print_stats(
-				m, local->crypt_info.crypt[i]->priv);
-		}
-	}
-	return 0;
-}
-#endif
-
-static ssize_t prism2_pda_proc_read(struct file *file, char __user *buf,
-				    size_t count, loff_t *_pos)
-{
-	local_info_t *local = pde_data(file_inode(file));
-	size_t off;
-
-	if (local->pda == NULL || *_pos >= PRISM2_PDA_SIZE)
-		return 0;
-
-	off = *_pos;
-	if (count > PRISM2_PDA_SIZE - off)
-		count = PRISM2_PDA_SIZE - off;
-	if (copy_to_user(buf, local->pda + off, count) != 0)
-		return -EFAULT;
-	*_pos += count;
-	return count;
-}
-
-static const struct proc_ops prism2_pda_proc_ops = {
-	.proc_read	= prism2_pda_proc_read,
-	.proc_lseek	= generic_file_llseek,
-};
-
-
-static ssize_t prism2_aux_dump_proc_no_read(struct file *file, char __user *buf,
-					    size_t bufsize, loff_t *_pos)
-{
-	return 0;
-}
-
-static const struct proc_ops prism2_aux_dump_proc_ops = {
-	.proc_read	= prism2_aux_dump_proc_no_read,
-	.proc_lseek	= default_llseek,
-};
-
-
-#ifdef PRISM2_IO_DEBUG
-static int prism2_io_debug_proc_read(char *page, char **start, off_t off,
-				     int count, int *eof, void *data)
-{
-	local_info_t *local = (local_info_t *) data;
-	int head = local->io_debug_head;
-	int start_bytes, left, copy;
-
-	if (off + count > PRISM2_IO_DEBUG_SIZE * 4) {
-		*eof = 1;
-		if (off >= PRISM2_IO_DEBUG_SIZE * 4)
-			return 0;
-		count = PRISM2_IO_DEBUG_SIZE * 4 - off;
-	}
-
-	start_bytes = (PRISM2_IO_DEBUG_SIZE - head) * 4;
-	left = count;
-
-	if (off < start_bytes) {
-		copy = start_bytes - off;
-		if (copy > count)
-			copy = count;
-		memcpy(page, ((u8 *) &local->io_debug[head]) + off, copy);
-		left -= copy;
-		if (left > 0)
-			memcpy(&page[copy], local->io_debug, left);
-	} else {
-		memcpy(page, ((u8 *) local->io_debug) + (off - start_bytes),
-		       left);
-	}
-
-	*start = page;
-
-	return count;
-}
-#endif /* PRISM2_IO_DEBUG */
-
-
-#ifndef PRISM2_NO_STATION_MODES
-static int prism2_scan_results_proc_show(struct seq_file *m, void *v)
-{
-	local_info_t *local = pde_data(file_inode(m->file));
-	unsigned long entry;
-	int i, len;
-	struct hfa384x_hostscan_result *scanres;
-	u8 *p;
-
-	if (v == SEQ_START_TOKEN) {
-		seq_printf(m,
-			   "CHID ANL SL BcnInt Capab Rate BSSID ATIM SupRates SSID\n");
-		return 0;
-	}
-
-	entry = (unsigned long)v - 2;
-	scanres = &local->last_scan_results[entry];
-
-	seq_printf(m, "%d %d %d %d 0x%02x %d %pM %d ",
-		   le16_to_cpu(scanres->chid),
-		   (s16) le16_to_cpu(scanres->anl),
-		   (s16) le16_to_cpu(scanres->sl),
-		   le16_to_cpu(scanres->beacon_interval),
-		   le16_to_cpu(scanres->capability),
-		   le16_to_cpu(scanres->rate),
-		   scanres->bssid,
-		   le16_to_cpu(scanres->atim));
-
-	p = scanres->sup_rates;
-	for (i = 0; i < sizeof(scanres->sup_rates); i++) {
-		if (p[i] == 0)
-			break;
-		seq_printf(m, "<%02x>", p[i]);
-	}
-	seq_putc(m, ' ');
-
-	p = scanres->ssid;
-	len = le16_to_cpu(scanres->ssid_len);
-	if (len > 32)
-		len = 32;
-	for (i = 0; i < len; i++) {
-		unsigned char c = p[i];
-		if (c >= 32 && c < 127)
-			seq_putc(m, c);
-		else
-			seq_printf(m, "<%02x>", c);
-	}
-	seq_putc(m, '\n');
-	return 0;
-}
-
-static void *prism2_scan_results_proc_start(struct seq_file *m, loff_t *_pos)
-{
-	local_info_t *local = pde_data(file_inode(m->file));
-	spin_lock_bh(&local->lock);
-
-	/* We have a header (pos 0) + N results to show (pos 1...N) */
-	if (*_pos > local->last_scan_results_count)
-		return NULL;
-	return (void *)(unsigned long)(*_pos + 1); /* 0 would be EOF */
-}
-
-static void *prism2_scan_results_proc_next(struct seq_file *m, void *v, loff_t *_pos)
-{
-	local_info_t *local = pde_data(file_inode(m->file));
-
-	++*_pos;
-	if (*_pos > local->last_scan_results_count)
-		return NULL;
-	return (void *)(unsigned long)(*_pos + 1); /* 0 would be EOF */
-}
-
-static void prism2_scan_results_proc_stop(struct seq_file *m, void *v)
-{
-	local_info_t *local = pde_data(file_inode(m->file));
-	spin_unlock_bh(&local->lock);
-}
-
-static const struct seq_operations prism2_scan_results_proc_seqops = {
-	.start	= prism2_scan_results_proc_start,
-	.next	= prism2_scan_results_proc_next,
-	.stop	= prism2_scan_results_proc_stop,
-	.show	= prism2_scan_results_proc_show,
-};
-#endif /* PRISM2_NO_STATION_MODES */
-
-
-void hostap_init_proc(local_info_t *local)
-{
-	local->proc = NULL;
-
-	if (hostap_proc == NULL) {
-		printk(KERN_WARNING "%s: hostap proc directory not created\n",
-		       local->dev->name);
-		return;
-	}
-
-	local->proc = proc_mkdir(local->ddev->name, hostap_proc);
-	if (local->proc == NULL) {
-		printk(KERN_INFO "/proc/net/hostap/%s creation failed\n",
-		       local->ddev->name);
-		return;
-	}
-
-#ifndef PRISM2_NO_PROCFS_DEBUG
-	proc_create_single_data("debug", 0, local->proc,
-			prism2_debug_proc_show, local);
-#endif /* PRISM2_NO_PROCFS_DEBUG */
-	proc_create_single_data("stats", 0, local->proc, prism2_stats_proc_show,
-			local);
-	proc_create_seq_data("wds", 0, local->proc,
-			&prism2_wds_proc_seqops, local);
-	proc_create_data("pda", 0, local->proc,
-			 &prism2_pda_proc_ops, local);
-	proc_create_data("aux_dump", 0, local->proc,
-			 local->func->read_aux_proc_ops ?: &prism2_aux_dump_proc_ops,
-			 local);
-	proc_create_seq_data("bss_list", 0, local->proc,
-			&prism2_bss_list_proc_seqops, local);
-	proc_create_single_data("crypt", 0, local->proc, prism2_crypt_proc_show,
-		local);
-#ifdef PRISM2_IO_DEBUG
-	proc_create_single_data("io_debug", 0, local->proc,
-			prism2_debug_proc_show, local);
-#endif /* PRISM2_IO_DEBUG */
-#ifndef PRISM2_NO_STATION_MODES
-	proc_create_seq_data("scan_results", 0, local->proc,
-			&prism2_scan_results_proc_seqops, local);
-#endif /* PRISM2_NO_STATION_MODES */
-}
-
-
-void hostap_remove_proc(local_info_t *local)
-{
-	proc_remove(local->proc);
-}
-
-
-EXPORT_SYMBOL(hostap_init_proc);
-EXPORT_SYMBOL(hostap_remove_proc);
diff --git a/drivers/net/wireless/intersil/hostap/hostap_wlan.h b/drivers/net/wireless/intersil/hostap/hostap_wlan.h
deleted file mode 100644
index f71c0545c0be..000000000000
--- a/drivers/net/wireless/intersil/hostap/hostap_wlan.h
+++ /dev/null
@@ -1,1051 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef HOSTAP_WLAN_H
-#define HOSTAP_WLAN_H
-
-#include <linux/interrupt.h>
-#include <linux/wireless.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/mutex.h>
-#include <linux/refcount.h>
-#include <net/iw_handler.h>
-#include <net/ieee80211_radiotap.h>
-#include <net/lib80211.h>
-
-#include "hostap_config.h"
-#include "hostap_common.h"
-
-#define MAX_PARM_DEVICES 8
-#define PARM_MIN_MAX "1-" __MODULE_STRING(MAX_PARM_DEVICES)
-#define DEF_INTS -1, -1, -1, -1, -1, -1, -1
-#define GET_INT_PARM(var,idx) var[var[idx] < 0 ? 0 : idx]
-
-
-/* Specific skb->protocol value that indicates that the packet already contains
- * txdesc header.
- * FIX: This might need own value that would be allocated especially for Prism2
- * txdesc; ETH_P_CONTROL is commented as "Card specific control frames".
- * However, these skb's should have only minimal path in the kernel side since
- * prism2_send_mgmt() sends these with dev_queue_xmit() to prism2_tx(). */
-#define ETH_P_HOSTAP ETH_P_CONTROL
-
-/* ARPHRD_IEEE80211_PRISM uses a bloated version of Prism2 RX frame header
- * (from linux-wlan-ng) */
-struct linux_wlan_ng_val {
-	u32 did;
-	u16 status, len;
-	u32 data;
-} __packed;
-
-struct linux_wlan_ng_prism_hdr {
-	u32 msgcode, msglen;
-	char devname[16];
-	struct linux_wlan_ng_val hosttime, mactime, channel, rssi, sq, signal,
-		noise, rate, istx, frmlen;
-} __packed;
-
-struct linux_wlan_ng_cap_hdr {
-	__be32 version;
-	__be32 length;
-	__be64 mactime;
-	__be64 hosttime;
-	__be32 phytype;
-	__be32 channel;
-	__be32 datarate;
-	__be32 antenna;
-	__be32 priority;
-	__be32 ssi_type;
-	__be32 ssi_signal;
-	__be32 ssi_noise;
-	__be32 preamble;
-	__be32 encoding;
-} __packed;
-
-struct hostap_radiotap_rx {
-	struct ieee80211_radiotap_header hdr;
-	__le64 tsft;
-	u8 rate;
-	u8 padding;
-	__le16 chan_freq;
-	__le16 chan_flags;
-	s8 dbm_antsignal;
-	s8 dbm_antnoise;
-} __packed;
-
-#define LWNG_CAP_DID_BASE   (4 | (1 << 6)) /* section 4, group 1 */
-#define LWNG_CAPHDR_VERSION 0x80211001
-
-struct hfa384x_rx_frame {
-	/* HFA384X RX frame descriptor */
-	__le16 status; /* HFA384X_RX_STATUS_ flags */
-	__le32 time; /* timestamp, 1 microsecond resolution */
-	u8 silence; /* 27 .. 154; seems to be 0 */
-	u8 signal; /* 27 .. 154 */
-	u8 rate; /* 10, 20, 55, or 110 */
-	u8 rxflow;
-	__le32 reserved;
-
-	/* 802.11 */
-	__le16 frame_control;
-	__le16 duration_id;
-	u8 addr1[ETH_ALEN];
-	u8 addr2[ETH_ALEN];
-	u8 addr3[ETH_ALEN];
-	__le16 seq_ctrl;
-	u8 addr4[ETH_ALEN];
-	__le16 data_len;
-
-	/* 802.3 */
-	u8 dst_addr[ETH_ALEN];
-	u8 src_addr[ETH_ALEN];
-	__be16 len;
-
-	/* followed by frame data; max 2304 bytes */
-} __packed;
-
-
-struct hfa384x_tx_frame {
-	/* HFA384X TX frame descriptor */
-	__le16 status; /* HFA384X_TX_STATUS_ flags */
-	__le16 reserved1;
-	__le16 reserved2;
-	__le32 sw_support;
-	u8 retry_count; /* not yet implemented */
-	u8 tx_rate; /* Host AP only; 0 = firmware, or 10, 20, 55, 110 */
-	__le16 tx_control; /* HFA384X_TX_CTRL_ flags */
-
-	/* 802.11 */
-	struct_group(header,
-		__le16 frame_control; /* parts not used */
-		__le16 duration_id;
-		u8 addr1[ETH_ALEN];
-		u8 addr2[ETH_ALEN]; /* filled by firmware */
-		u8 addr3[ETH_ALEN];
-		__le16 seq_ctrl; /* filled by firmware */
-	);
-	u8 addr4[ETH_ALEN];
-	__le16 data_len;
-
-	/* 802.3 */
-	u8 dst_addr[ETH_ALEN];
-	u8 src_addr[ETH_ALEN];
-	__be16 len;
-
-	/* followed by frame data; max 2304 bytes */
-} __packed;
-
-
-struct hfa384x_rid_hdr
-{
-	__le16 len;
-	__le16 rid;
-} __packed;
-
-
-/* Macro for converting signal levels (range 27 .. 154) to wireless ext
- * dBm value with some accuracy */
-#define HFA384X_LEVEL_TO_dBm(v) 0x100 + (v) * 100 / 255 - 100
-
-#define HFA384X_LEVEL_TO_dBm_sign(v) (v) * 100 / 255 - 100
-
-struct hfa384x_scan_request {
-	__le16 channel_list;
-	__le16 txrate; /* HFA384X_RATES_* */
-} __packed;
-
-struct hfa384x_hostscan_request {
-	__le16 channel_list;
-	__le16 txrate;
-	__le16 target_ssid_len;
-	u8 target_ssid[32];
-} __packed;
-
-struct hfa384x_join_request {
-	u8 bssid[ETH_ALEN];
-	__le16 channel;
-} __packed;
-
-struct hfa384x_info_frame {
-	__le16 len;
-	__le16 type;
-} __packed;
-
-struct hfa384x_comm_tallies {
-	__le16 tx_unicast_frames;
-	__le16 tx_multicast_frames;
-	__le16 tx_fragments;
-	__le16 tx_unicast_octets;
-	__le16 tx_multicast_octets;
-	__le16 tx_deferred_transmissions;
-	__le16 tx_single_retry_frames;
-	__le16 tx_multiple_retry_frames;
-	__le16 tx_retry_limit_exceeded;
-	__le16 tx_discards;
-	__le16 rx_unicast_frames;
-	__le16 rx_multicast_frames;
-	__le16 rx_fragments;
-	__le16 rx_unicast_octets;
-	__le16 rx_multicast_octets;
-	__le16 rx_fcs_errors;
-	__le16 rx_discards_no_buffer;
-	__le16 tx_discards_wrong_sa;
-	__le16 rx_discards_wep_undecryptable;
-	__le16 rx_message_in_msg_fragments;
-	__le16 rx_message_in_bad_msg_fragments;
-} __packed;
-
-struct hfa384x_comm_tallies32 {
-	__le32 tx_unicast_frames;
-	__le32 tx_multicast_frames;
-	__le32 tx_fragments;
-	__le32 tx_unicast_octets;
-	__le32 tx_multicast_octets;
-	__le32 tx_deferred_transmissions;
-	__le32 tx_single_retry_frames;
-	__le32 tx_multiple_retry_frames;
-	__le32 tx_retry_limit_exceeded;
-	__le32 tx_discards;
-	__le32 rx_unicast_frames;
-	__le32 rx_multicast_frames;
-	__le32 rx_fragments;
-	__le32 rx_unicast_octets;
-	__le32 rx_multicast_octets;
-	__le32 rx_fcs_errors;
-	__le32 rx_discards_no_buffer;
-	__le32 tx_discards_wrong_sa;
-	__le32 rx_discards_wep_undecryptable;
-	__le32 rx_message_in_msg_fragments;
-	__le32 rx_message_in_bad_msg_fragments;
-} __packed;
-
-struct hfa384x_scan_result_hdr {
-	__le16 reserved;
-	__le16 scan_reason;
-#define HFA384X_SCAN_IN_PROGRESS 0 /* no results available yet */
-#define HFA384X_SCAN_HOST_INITIATED 1
-#define HFA384X_SCAN_FIRMWARE_INITIATED 2
-#define HFA384X_SCAN_INQUIRY_FROM_HOST 3
-} __packed;
-
-#define HFA384X_SCAN_MAX_RESULTS 32
-
-struct hfa384x_scan_result {
-	__le16 chid;
-	__le16 anl;
-	__le16 sl;
-	u8 bssid[ETH_ALEN];
-	__le16 beacon_interval;
-	__le16 capability;
-	__le16 ssid_len;
-	u8 ssid[32];
-	u8 sup_rates[10];
-	__le16 rate;
-} __packed;
-
-struct hfa384x_hostscan_result {
-	__le16 chid;
-	__le16 anl;
-	__le16 sl;
-	u8 bssid[ETH_ALEN];
-	__le16 beacon_interval;
-	__le16 capability;
-	__le16 ssid_len;
-	u8 ssid[32];
-	u8 sup_rates[10];
-	__le16 rate;
-	__le16 atim;
-} __packed;
-
-struct comm_tallies_sums {
-	unsigned int tx_unicast_frames;
-	unsigned int tx_multicast_frames;
-	unsigned int tx_fragments;
-	unsigned int tx_unicast_octets;
-	unsigned int tx_multicast_octets;
-	unsigned int tx_deferred_transmissions;
-	unsigned int tx_single_retry_frames;
-	unsigned int tx_multiple_retry_frames;
-	unsigned int tx_retry_limit_exceeded;
-	unsigned int tx_discards;
-	unsigned int rx_unicast_frames;
-	unsigned int rx_multicast_frames;
-	unsigned int rx_fragments;
-	unsigned int rx_unicast_octets;
-	unsigned int rx_multicast_octets;
-	unsigned int rx_fcs_errors;
-	unsigned int rx_discards_no_buffer;
-	unsigned int tx_discards_wrong_sa;
-	unsigned int rx_discards_wep_undecryptable;
-	unsigned int rx_message_in_msg_fragments;
-	unsigned int rx_message_in_bad_msg_fragments;
-};
-
-
-struct hfa384x_regs {
-	u16 cmd;
-	u16 evstat;
-	u16 offset0;
-	u16 offset1;
-	u16 swsupport0;
-};
-
-
-#if defined(PRISM2_PCCARD) || defined(PRISM2_PLX)
-/* I/O ports for HFA384X Controller access */
-#define HFA384X_CMD_OFF 0x00
-#define HFA384X_PARAM0_OFF 0x02
-#define HFA384X_PARAM1_OFF 0x04
-#define HFA384X_PARAM2_OFF 0x06
-#define HFA384X_STATUS_OFF 0x08
-#define HFA384X_RESP0_OFF 0x0A
-#define HFA384X_RESP1_OFF 0x0C
-#define HFA384X_RESP2_OFF 0x0E
-#define HFA384X_INFOFID_OFF 0x10
-#define HFA384X_CONTROL_OFF 0x14
-#define HFA384X_SELECT0_OFF 0x18
-#define HFA384X_SELECT1_OFF 0x1A
-#define HFA384X_OFFSET0_OFF 0x1C
-#define HFA384X_OFFSET1_OFF 0x1E
-#define HFA384X_RXFID_OFF 0x20
-#define HFA384X_ALLOCFID_OFF 0x22
-#define HFA384X_TXCOMPLFID_OFF 0x24
-#define HFA384X_SWSUPPORT0_OFF 0x28
-#define HFA384X_SWSUPPORT1_OFF 0x2A
-#define HFA384X_SWSUPPORT2_OFF 0x2C
-#define HFA384X_EVSTAT_OFF 0x30
-#define HFA384X_INTEN_OFF 0x32
-#define HFA384X_EVACK_OFF 0x34
-#define HFA384X_DATA0_OFF 0x36
-#define HFA384X_DATA1_OFF 0x38
-#define HFA384X_AUXPAGE_OFF 0x3A
-#define HFA384X_AUXOFFSET_OFF 0x3C
-#define HFA384X_AUXDATA_OFF 0x3E
-#endif /* PRISM2_PCCARD || PRISM2_PLX */
-
-#ifdef PRISM2_PCI
-/* Memory addresses for ISL3874 controller access */
-#define HFA384X_CMD_OFF 0x00
-#define HFA384X_PARAM0_OFF 0x04
-#define HFA384X_PARAM1_OFF 0x08
-#define HFA384X_PARAM2_OFF 0x0C
-#define HFA384X_STATUS_OFF 0x10
-#define HFA384X_RESP0_OFF 0x14
-#define HFA384X_RESP1_OFF 0x18
-#define HFA384X_RESP2_OFF 0x1C
-#define HFA384X_INFOFID_OFF 0x20
-#define HFA384X_CONTROL_OFF 0x28
-#define HFA384X_SELECT0_OFF 0x30
-#define HFA384X_SELECT1_OFF 0x34
-#define HFA384X_OFFSET0_OFF 0x38
-#define HFA384X_OFFSET1_OFF 0x3C
-#define HFA384X_RXFID_OFF 0x40
-#define HFA384X_ALLOCFID_OFF 0x44
-#define HFA384X_TXCOMPLFID_OFF 0x48
-#define HFA384X_PCICOR_OFF 0x4C
-#define HFA384X_SWSUPPORT0_OFF 0x50
-#define HFA384X_SWSUPPORT1_OFF 0x54
-#define HFA384X_SWSUPPORT2_OFF 0x58
-#define HFA384X_PCIHCR_OFF 0x5C
-#define HFA384X_EVSTAT_OFF 0x60
-#define HFA384X_INTEN_OFF 0x64
-#define HFA384X_EVACK_OFF 0x68
-#define HFA384X_DATA0_OFF 0x6C
-#define HFA384X_DATA1_OFF 0x70
-#define HFA384X_AUXPAGE_OFF 0x74
-#define HFA384X_AUXOFFSET_OFF 0x78
-#define HFA384X_AUXDATA_OFF 0x7C
-#define HFA384X_PCI_M0_ADDRH_OFF 0x80
-#define HFA384X_PCI_M0_ADDRL_OFF 0x84
-#define HFA384X_PCI_M0_LEN_OFF 0x88
-#define HFA384X_PCI_M0_CTL_OFF 0x8C
-#define HFA384X_PCI_STATUS_OFF 0x98
-#define HFA384X_PCI_M1_ADDRH_OFF 0xA0
-#define HFA384X_PCI_M1_ADDRL_OFF 0xA4
-#define HFA384X_PCI_M1_LEN_OFF 0xA8
-#define HFA384X_PCI_M1_CTL_OFF 0xAC
-
-/* PCI bus master control bits (these are undocumented; based on guessing and
- * experimenting..) */
-#define HFA384X_PCI_CTL_FROM_BAP (BIT(5) | BIT(1) | BIT(0))
-#define HFA384X_PCI_CTL_TO_BAP (BIT(5) | BIT(0))
-
-#endif /* PRISM2_PCI */
-
-
-/* Command codes for CMD reg. */
-#define HFA384X_CMDCODE_INIT 0x00
-#define HFA384X_CMDCODE_ENABLE 0x01
-#define HFA384X_CMDCODE_DISABLE 0x02
-#define HFA384X_CMDCODE_ALLOC 0x0A
-#define HFA384X_CMDCODE_TRANSMIT 0x0B
-#define HFA384X_CMDCODE_INQUIRE 0x11
-#define HFA384X_CMDCODE_ACCESS 0x21
-#define HFA384X_CMDCODE_ACCESS_WRITE (0x21 | BIT(8))
-#define HFA384X_CMDCODE_DOWNLOAD 0x22
-#define HFA384X_CMDCODE_READMIF 0x30
-#define HFA384X_CMDCODE_WRITEMIF 0x31
-#define HFA384X_CMDCODE_TEST 0x38
-
-#define HFA384X_CMDCODE_MASK 0x3F
-
-/* Test mode operations */
-#define HFA384X_TEST_CHANGE_CHANNEL 0x08
-#define HFA384X_TEST_MONITOR 0x0B
-#define HFA384X_TEST_STOP 0x0F
-#define HFA384X_TEST_CFG_BITS 0x15
-#define HFA384X_TEST_CFG_BIT_ALC BIT(3)
-
-#define HFA384X_CMD_BUSY BIT(15)
-
-#define HFA384X_CMD_TX_RECLAIM BIT(8)
-
-#define HFA384X_OFFSET_ERR BIT(14)
-#define HFA384X_OFFSET_BUSY BIT(15)
-
-
-/* ProgMode for download command */
-#define HFA384X_PROGMODE_DISABLE 0
-#define HFA384X_PROGMODE_ENABLE_VOLATILE 1
-#define HFA384X_PROGMODE_ENABLE_NON_VOLATILE 2
-#define HFA384X_PROGMODE_PROGRAM_NON_VOLATILE 3
-
-#define HFA384X_AUX_MAGIC0 0xfe01
-#define HFA384X_AUX_MAGIC1 0xdc23
-#define HFA384X_AUX_MAGIC2 0xba45
-
-#define HFA384X_AUX_PORT_DISABLED 0
-#define HFA384X_AUX_PORT_DISABLE BIT(14)
-#define HFA384X_AUX_PORT_ENABLE BIT(15)
-#define HFA384X_AUX_PORT_ENABLED (BIT(14) | BIT(15))
-#define HFA384X_AUX_PORT_MASK (BIT(14) | BIT(15))
-
-#define PRISM2_PDA_SIZE 1024
-
-
-/* Events; EvStat, Interrupt mask (IntEn), and acknowledge bits (EvAck) */
-#define HFA384X_EV_TICK BIT(15)
-#define HFA384X_EV_WTERR BIT(14)
-#define HFA384X_EV_INFDROP BIT(13)
-#ifdef PRISM2_PCI
-#define HFA384X_EV_PCI_M1 BIT(9)
-#define HFA384X_EV_PCI_M0 BIT(8)
-#endif /* PRISM2_PCI */
-#define HFA384X_EV_INFO BIT(7)
-#define HFA384X_EV_DTIM BIT(5)
-#define HFA384X_EV_CMD BIT(4)
-#define HFA384X_EV_ALLOC BIT(3)
-#define HFA384X_EV_TXEXC BIT(2)
-#define HFA384X_EV_TX BIT(1)
-#define HFA384X_EV_RX BIT(0)
-
-
-/* HFA384X Information frames */
-#define HFA384X_INFO_HANDOVERADDR 0xF000 /* AP f/w ? */
-#define HFA384X_INFO_HANDOVERDEAUTHADDR 0xF001 /* AP f/w 1.3.7 */
-#define HFA384X_INFO_COMMTALLIES 0xF100
-#define HFA384X_INFO_SCANRESULTS 0xF101
-#define HFA384X_INFO_CHANNELINFORESULTS 0xF102 /* AP f/w only */
-#define HFA384X_INFO_HOSTSCANRESULTS 0xF103
-#define HFA384X_INFO_LINKSTATUS 0xF200
-#define HFA384X_INFO_ASSOCSTATUS 0xF201 /* ? */
-#define HFA384X_INFO_AUTHREQ 0xF202 /* ? */
-#define HFA384X_INFO_PSUSERCNT 0xF203 /* ? */
-#define HFA384X_INFO_KEYIDCHANGED 0xF204 /* ? */
-
-enum { HFA384X_LINKSTATUS_CONNECTED = 1,
-       HFA384X_LINKSTATUS_DISCONNECTED = 2,
-       HFA384X_LINKSTATUS_AP_CHANGE = 3,
-       HFA384X_LINKSTATUS_AP_OUT_OF_RANGE = 4,
-       HFA384X_LINKSTATUS_AP_IN_RANGE = 5,
-       HFA384X_LINKSTATUS_ASSOC_FAILED = 6 };
-
-enum { HFA384X_PORTTYPE_BSS = 1, HFA384X_PORTTYPE_WDS = 2,
-       HFA384X_PORTTYPE_PSEUDO_IBSS = 3, HFA384X_PORTTYPE_IBSS = 0,
-       HFA384X_PORTTYPE_HOSTAP = 6 };
-
-#define HFA384X_RATES_1MBPS BIT(0)
-#define HFA384X_RATES_2MBPS BIT(1)
-#define HFA384X_RATES_5MBPS BIT(2)
-#define HFA384X_RATES_11MBPS BIT(3)
-
-#define HFA384X_ROAMING_FIRMWARE 1
-#define HFA384X_ROAMING_HOST 2
-#define HFA384X_ROAMING_DISABLED 3
-
-#define HFA384X_WEPFLAGS_PRIVACYINVOKED BIT(0)
-#define HFA384X_WEPFLAGS_EXCLUDEUNENCRYPTED BIT(1)
-#define HFA384X_WEPFLAGS_HOSTENCRYPT BIT(4)
-#define HFA384X_WEPFLAGS_HOSTDECRYPT BIT(7)
-
-#define HFA384X_RX_STATUS_MSGTYPE (BIT(15) | BIT(14) | BIT(13))
-#define HFA384X_RX_STATUS_PCF BIT(12)
-#define HFA384X_RX_STATUS_MACPORT (BIT(10) | BIT(9) | BIT(8))
-#define HFA384X_RX_STATUS_UNDECR BIT(1)
-#define HFA384X_RX_STATUS_FCSERR BIT(0)
-
-#define HFA384X_RX_STATUS_GET_MSGTYPE(s) \
-(((s) & HFA384X_RX_STATUS_MSGTYPE) >> 13)
-#define HFA384X_RX_STATUS_GET_MACPORT(s) \
-(((s) & HFA384X_RX_STATUS_MACPORT) >> 8)
-
-enum { HFA384X_RX_MSGTYPE_NORMAL = 0, HFA384X_RX_MSGTYPE_RFC1042 = 1,
-       HFA384X_RX_MSGTYPE_BRIDGETUNNEL = 2, HFA384X_RX_MSGTYPE_MGMT = 4 };
-
-
-#define HFA384X_TX_CTRL_ALT_RTRY BIT(5)
-#define HFA384X_TX_CTRL_802_11 BIT(3)
-#define HFA384X_TX_CTRL_802_3 0
-#define HFA384X_TX_CTRL_TX_EX BIT(2)
-#define HFA384X_TX_CTRL_TX_OK BIT(1)
-
-#define HFA384X_TX_STATUS_RETRYERR BIT(0)
-#define HFA384X_TX_STATUS_AGEDERR BIT(1)
-#define HFA384X_TX_STATUS_DISCON BIT(2)
-#define HFA384X_TX_STATUS_FORMERR BIT(3)
-
-/* HFA3861/3863 (BBP) Control Registers */
-#define HFA386X_CR_TX_CONFIGURE 0x12 /* CR9 */
-#define HFA386X_CR_RX_CONFIGURE 0x14 /* CR10 */
-#define HFA386X_CR_A_D_TEST_MODES2 0x1A /* CR13 */
-#define HFA386X_CR_MANUAL_TX_POWER 0x3E /* CR31 */
-#define HFA386X_CR_MEASURED_TX_POWER 0x74 /* CR58 */
-
-
-#ifdef __KERNEL__
-
-#define PRISM2_TXFID_COUNT 8
-#define PRISM2_DATA_MAXLEN 2304
-#define PRISM2_TXFID_LEN (PRISM2_DATA_MAXLEN + sizeof(struct hfa384x_tx_frame))
-#define PRISM2_TXFID_EMPTY 0xffff
-#define PRISM2_TXFID_RESERVED 0xfffe
-#define PRISM2_DUMMY_FID 0xffff
-#define MAX_SSID_LEN 32
-#define MAX_NAME_LEN 32 /* this is assumed to be equal to MAX_SSID_LEN */
-
-#define PRISM2_DUMP_RX_HDR BIT(0)
-#define PRISM2_DUMP_TX_HDR BIT(1)
-#define PRISM2_DUMP_TXEXC_HDR BIT(2)
-
-struct hostap_tx_callback_info {
-	u16 idx;
-	void (*func)(struct sk_buff *, int ok, void *);
-	void *data;
-	struct hostap_tx_callback_info *next;
-};
-
-
-/* IEEE 802.11 requires that STA supports concurrent reception of at least
- * three fragmented frames. This define can be increased to support more
- * concurrent frames, but it should be noted that each entry can consume about
- * 2 kB of RAM and increasing cache size will slow down frame reassembly. */
-#define PRISM2_FRAG_CACHE_LEN 4
-
-struct prism2_frag_entry {
-	unsigned long first_frag_time;
-	unsigned int seq;
-	unsigned int last_frag;
-	struct sk_buff *skb;
-	u8 src_addr[ETH_ALEN];
-	u8 dst_addr[ETH_ALEN];
-};
-
-
-struct hostap_cmd_queue {
-	struct list_head list;
-	wait_queue_head_t compl;
-	volatile enum { CMD_SLEEP, CMD_CALLBACK, CMD_COMPLETED } type;
-	void (*callback)(struct net_device *dev, long context, u16 resp0,
-			 u16 res);
-	long context;
-	u16 cmd, param0, param1;
-	u16 resp0, res;
-	volatile int issued, issuing;
-
-	refcount_t usecnt;
-	int del_req;
-};
-
-/* options for hw_shutdown */
-#define HOSTAP_HW_NO_DISABLE BIT(0)
-#define HOSTAP_HW_ENABLE_CMDCOMPL BIT(1)
-
-typedef struct local_info local_info_t;
-
-struct prism2_helper_functions {
-	/* these functions are defined in hardware model specific files
-	 * (hostap_{cs,plx,pci}.c */
-	int (*card_present)(local_info_t *local);
-	void (*cor_sreset)(local_info_t *local);
-	void (*genesis_reset)(local_info_t *local, int hcr);
-
-	/* the following functions are from hostap_hw.c, but they may have some
-	 * hardware model specific code */
-
-	/* FIX: low-level commands like cmd might disappear at some point to
-	 * make it easier to change them if needed (e.g., cmd would be replaced
-	 * with write_mif/read_mif/testcmd/inquire); at least get_rid and
-	 * set_rid might move to hostap_{cs,plx,pci}.c */
-	int (*cmd)(struct net_device *dev, u16 cmd, u16 param0, u16 *param1,
-		   u16 *resp0);
-	void (*read_regs)(struct net_device *dev, struct hfa384x_regs *regs);
-	int (*get_rid)(struct net_device *dev, u16 rid, void *buf, int len,
-		       int exact_len);
-	int (*set_rid)(struct net_device *dev, u16 rid, void *buf, int len);
-	int (*hw_enable)(struct net_device *dev, int initial);
-	int (*hw_config)(struct net_device *dev, int initial);
-	void (*hw_reset)(struct net_device *dev);
-	void (*hw_shutdown)(struct net_device *dev, int no_disable);
-	int (*reset_port)(struct net_device *dev);
-	void (*schedule_reset)(local_info_t *local);
-	int (*download)(local_info_t *local,
-			struct prism2_download_param *param);
-	int (*tx)(struct sk_buff *skb, struct net_device *dev);
-	int (*set_tim)(struct net_device *dev, int aid, int set);
-	const struct proc_ops *read_aux_proc_ops;
-
-	int need_tx_headroom; /* number of bytes of headroom needed before
-			       * IEEE 802.11 header */
-	enum { HOSTAP_HW_PCCARD, HOSTAP_HW_PLX, HOSTAP_HW_PCI } hw_type;
-};
-
-
-struct prism2_download_data {
-	u32 dl_cmd;
-	u32 start_addr;
-	u32 num_areas;
-	struct prism2_download_data_area {
-		u32 addr; /* wlan card address */
-		u32 len;
-		u8 *data; /* allocated data */
-	} data[] __counted_by(num_areas);
-};
-
-
-#define HOSTAP_MAX_BSS_COUNT 64
-#define MAX_WPA_IE_LEN 64
-
-struct hostap_bss_info {
-	struct list_head list;
-	unsigned long last_update;
-	unsigned int count;
-	u8 bssid[ETH_ALEN];
-	u16 capab_info;
-	u8 ssid[32];
-	size_t ssid_len;
-	u8 wpa_ie[MAX_WPA_IE_LEN];
-	size_t wpa_ie_len;
-	u8 rsn_ie[MAX_WPA_IE_LEN];
-	size_t rsn_ie_len;
-	int chan;
-	int included;
-};
-
-
-/* Per radio private Host AP data - shared by all net devices interfaces used
- * by each radio (wlan#, wlan#ap, wlan#sta, WDS).
- * ((struct hostap_interface *) netdev_priv(dev))->local points to this
- * structure. */
-struct local_info {
-	struct module *hw_module;
-	int card_idx;
-	int dev_enabled;
-	int master_dev_auto_open; /* was master device opened automatically */
-	int num_dev_open; /* number of open devices */
-	struct net_device *dev; /* master radio device */
-	struct net_device *ddev; /* main data device */
-	struct list_head hostap_interfaces; /* Host AP interface list (contains
-					     * struct hostap_interface entries)
-					     */
-	rwlock_t iface_lock; /* hostap_interfaces read lock; use write lock
-			      * when removing entries from the list.
-			      * TX and RX paths can use read lock. */
-	spinlock_t cmdlock, baplock, lock, irq_init_lock;
-	struct mutex rid_bap_mtx;
-	u16 infofid; /* MAC buffer id for info frame */
-	/* txfid, intransmitfid, next_txtid, and next_alloc are protected by
-	 * txfidlock */
-	spinlock_t txfidlock;
-	int txfid_len; /* length of allocated TX buffers */
-	u16 txfid[PRISM2_TXFID_COUNT]; /* buffer IDs for TX frames */
-	/* buffer IDs for intransmit frames or PRISM2_TXFID_EMPTY if
-	 * corresponding txfid is free for next TX frame */
-	u16 intransmitfid[PRISM2_TXFID_COUNT];
-	int next_txfid; /* index to the next txfid to be checked for
-			 * availability */
-	int next_alloc; /* index to the next intransmitfid to be checked for
-			 * allocation events */
-
-	/* bitfield for atomic bitops */
-#define HOSTAP_BITS_TRANSMIT 0
-#define HOSTAP_BITS_BAP_TASKLET 1
-#define HOSTAP_BITS_BAP_TASKLET2 2
-	unsigned long bits;
-
-	struct ap_data *ap;
-
-	char essid[MAX_SSID_LEN + 1];
-	char name[MAX_NAME_LEN + 1];
-	int name_set;
-	u16 channel_mask; /* mask of allowed channels */
-	u16 scan_channel_mask; /* mask of channels to be scanned */
-	struct comm_tallies_sums comm_tallies;
-	struct proc_dir_entry *proc;
-	int iw_mode; /* operating mode (IW_MODE_*) */
-	int pseudo_adhoc; /* 0: IW_MODE_ADHOC is real 802.11 compliant IBSS
-			   * 1: IW_MODE_ADHOC is "pseudo IBSS" */
-	char bssid[ETH_ALEN];
-	int channel;
-	int beacon_int;
-	int dtim_period;
-	int mtu;
-	int frame_dump; /* dump RX/TX frame headers, PRISM2_DUMP_ flags */
-	int fw_tx_rate_control;
-	u16 tx_rate_control;
-	u16 basic_rates;
-	int hw_resetting;
-	int hw_ready;
-	int hw_reset_tries; /* how many times reset has been tried */
-	int hw_downloading;
-	int shutdown;
-	int pri_only;
-	int no_pri; /* no PRI f/w present */
-	int sram_type; /* 8 = x8 SRAM, 16 = x16 SRAM, -1 = unknown */
-
-	enum {
-		PRISM2_TXPOWER_AUTO = 0, PRISM2_TXPOWER_OFF,
-		PRISM2_TXPOWER_FIXED, PRISM2_TXPOWER_UNKNOWN
-	} txpower_type;
-	int txpower; /* if txpower_type == PRISM2_TXPOWER_FIXED */
-
-	/* command queue for hfa384x_cmd(); protected with cmdlock */
-	struct list_head cmd_queue;
-	/* max_len for cmd_queue; in addition, cmd_callback can use two
-	 * additional entries to prevent sleeping commands from stopping
-	 * transmits */
-#define HOSTAP_CMD_QUEUE_MAX_LEN 16
-	int cmd_queue_len; /* number of entries in cmd_queue */
-
-	/* if card timeout is detected in interrupt context, reset_queue is
-	 * used to schedule card reseting to be done in user context */
-	struct work_struct reset_queue;
-
-	/* For scheduling a change of the promiscuous mode RID */
-	int is_promisc;
-	struct work_struct set_multicast_list_queue;
-
-	struct work_struct set_tim_queue;
-	struct list_head set_tim_list;
-	spinlock_t set_tim_lock;
-
-	int wds_max_connections;
-	int wds_connections;
-#define HOSTAP_WDS_BROADCAST_RA BIT(0)
-#define HOSTAP_WDS_AP_CLIENT BIT(1)
-#define HOSTAP_WDS_STANDARD_FRAME BIT(2)
-	u32 wds_type;
-	u16 tx_control; /* flags to be used in TX description */
-	int manual_retry_count; /* -1 = use f/w default; otherwise retry count
-				 * to be used with all frames */
-
-	struct iw_statistics wstats;
-	unsigned long scan_timestamp; /* Time started to scan */
-	enum {
-		PRISM2_MONITOR_80211 = 0, PRISM2_MONITOR_PRISM = 1,
-		PRISM2_MONITOR_CAPHDR = 2, PRISM2_MONITOR_RADIOTAP = 3
-	} monitor_type;
-	int monitor_allow_fcserr;
-
-	int hostapd; /* whether user space daemon, hostapd, is used for AP
-		      * management */
-	int hostapd_sta; /* whether hostapd is used with an extra STA interface
-			  */
-	struct net_device *apdev;
-	struct net_device_stats apdevstats;
-
-	char assoc_ap_addr[ETH_ALEN];
-	struct net_device *stadev;
-	struct net_device_stats stadevstats;
-
-#define WEP_KEYS 4
-#define WEP_KEY_LEN 13
-	struct lib80211_crypt_info crypt_info;
-
-	int open_wep; /* allow unencrypted frames */
-	int host_encrypt;
-	int host_decrypt;
-	int privacy_invoked; /* force privacy invoked flag even if no keys are
-			      * configured */
-	int fw_encrypt_ok; /* whether firmware-based WEP encrypt is working
-			    * in Host AP mode (STA f/w 1.4.9 or newer) */
-	int bcrx_sta_key; /* use individual keys to override default keys even
-			   * with RX of broad/multicast frames */
-
-	struct prism2_frag_entry frag_cache[PRISM2_FRAG_CACHE_LEN];
-	unsigned int frag_next_idx;
-
-	int ieee_802_1x; /* is IEEE 802.1X used */
-
-	int antsel_tx, antsel_rx;
-	int rts_threshold; /* dot11RTSThreshold */
-	int fragm_threshold; /* dot11FragmentationThreshold */
-	int auth_algs; /* PRISM2_AUTH_ flags */
-
-	int enh_sec; /* cnfEnhSecurity options (broadcast SSID hide/ignore) */
-	int tallies32; /* 32-bit tallies in use */
-
-	struct prism2_helper_functions *func;
-
-	u8 *pda;
-	int fw_ap;
-#define PRISM2_FW_VER(major, minor, variant) \
-(((major) << 16) | ((minor) << 8) | variant)
-	u32 sta_fw_ver;
-
-	/* Tasklets for handling hardware IRQ related operations outside hw IRQ
-	 * handler */
-	struct tasklet_struct bap_tasklet;
-
-	struct tasklet_struct info_tasklet;
-	struct sk_buff_head info_list; /* info frames as skb's for
-					* info_tasklet */
-
-	struct hostap_tx_callback_info *tx_callback; /* registered TX callbacks
-						      */
-
-	struct tasklet_struct rx_tasklet;
-	struct sk_buff_head rx_list;
-
-	struct tasklet_struct sta_tx_exc_tasklet;
-	struct sk_buff_head sta_tx_exc_list;
-
-	int host_roaming;
-	unsigned long last_join_time; /* time of last JoinRequest */
-	struct hfa384x_hostscan_result *last_scan_results;
-	int last_scan_results_count;
-	enum { PRISM2_SCAN, PRISM2_HOSTSCAN } last_scan_type;
-	struct work_struct info_queue;
-	unsigned long pending_info; /* bit field of pending info_queue items */
-#define PRISM2_INFO_PENDING_LINKSTATUS 0
-#define PRISM2_INFO_PENDING_SCANRESULTS 1
-	int prev_link_status; /* previous received LinkStatus info */
-	int prev_linkstatus_connected;
-	u8 preferred_ap[ETH_ALEN]; /* use this AP if possible */
-
-#ifdef PRISM2_CALLBACK
-	void *callback_data; /* Can be used in callbacks; e.g., allocate
-			      * on enable event and free on disable event.
-			      * Host AP driver code does not touch this. */
-#endif /* PRISM2_CALLBACK */
-
-	wait_queue_head_t hostscan_wq;
-
-	/* Passive scan in Host AP mode */
-	struct timer_list passive_scan_timer;
-	int passive_scan_interval; /* in seconds, 0 = disabled */
-	int passive_scan_channel;
-	enum { PASSIVE_SCAN_WAIT, PASSIVE_SCAN_LISTEN } passive_scan_state;
-
-	struct timer_list tick_timer;
-	unsigned long last_tick_timer;
-	unsigned int sw_tick_stuck;
-
-	/* commsQuality / dBmCommsQuality data from periodic polling; only
-	 * valid for Managed and Ad-hoc modes */
-	unsigned long last_comms_qual_update;
-	int comms_qual; /* in some odd unit.. */
-	int avg_signal; /* in dB (note: negative) */
-	int avg_noise; /* in dB (note: negative) */
-	struct work_struct comms_qual_update;
-
-	/* RSSI to dBm adjustment (for RX descriptor fields) */
-	int rssi_to_dBm; /* subtract from RSSI to get approximate dBm value */
-
-	/* BSS list / protected by local->lock */
-	struct list_head bss_list;
-	int num_bss_info;
-	int wpa; /* WPA support enabled */
-	int tkip_countermeasures;
-	int drop_unencrypted;
-	/* Generic IEEE 802.11 info element to be added to
-	 * ProbeResp/Beacon/(Re)AssocReq */
-	u8 *generic_elem;
-	size_t generic_elem_len;
-
-#ifdef PRISM2_DOWNLOAD_SUPPORT
-	/* Persistent volatile download data */
-	struct prism2_download_data *dl_pri;
-	struct prism2_download_data *dl_sec;
-#endif /* PRISM2_DOWNLOAD_SUPPORT */
-
-#ifdef PRISM2_IO_DEBUG
-#define PRISM2_IO_DEBUG_SIZE 10000
-	u32 io_debug[PRISM2_IO_DEBUG_SIZE];
-	int io_debug_head;
-	int io_debug_enabled;
-#endif /* PRISM2_IO_DEBUG */
-
-	/* Pointer to hardware model specific (cs,pci,plx) private data. */
-	void *hw_priv;
-};
-
-
-/* Per interface private Host AP data
- * Allocated for each net device that Host AP uses (wlan#, wlan#ap, wlan#sta,
- * WDS) and netdev_priv(dev) points to this structure. */
-struct hostap_interface {
-	struct list_head list; /* list entry in Host AP interface list */
-	struct net_device *dev; /* pointer to this device */
-	struct local_info *local; /* pointer to shared private data */
-	struct net_device_stats stats;
-	struct iw_spy_data spy_data; /* iwspy support */
-	struct iw_public_data wireless_data;
-
-	enum {
-		HOSTAP_INTERFACE_MASTER,
-		HOSTAP_INTERFACE_MAIN,
-		HOSTAP_INTERFACE_AP,
-		HOSTAP_INTERFACE_STA,
-		HOSTAP_INTERFACE_WDS,
-	} type;
-
-	union {
-		struct hostap_interface_wds {
-			u8 remote_addr[ETH_ALEN];
-		} wds;
-	} u;
-};
-
-
-#define HOSTAP_SKB_TX_DATA_MAGIC 0xf08a36a2
-
-/*
- * TX meta data - stored in skb->cb buffer, so this must not be increased over
- * the 48-byte limit.
- * THE PADDING THIS STARTS WITH IS A HORRIBLE HACK THAT SHOULD NOT LIVE
- * TO SEE THE DAY.
- */
-struct hostap_skb_tx_data {
-	unsigned int __padding_for_default_qdiscs;
-	u32 magic; /* HOSTAP_SKB_TX_DATA_MAGIC */
-	u8 rate; /* transmit rate */
-#define HOSTAP_TX_FLAGS_WDS BIT(0)
-#define HOSTAP_TX_FLAGS_BUFFERED_FRAME BIT(1)
-#define HOSTAP_TX_FLAGS_ADD_MOREDATA BIT(2)
-	u8 flags; /* HOSTAP_TX_FLAGS_* */
-	u16 tx_cb_idx;
-	struct hostap_interface *iface;
-	unsigned long jiffies; /* queueing timestamp */
-	unsigned short ethertype;
-};
-
-
-#ifndef PRISM2_NO_DEBUG
-
-#define DEBUG_FID BIT(0)
-#define DEBUG_PS BIT(1)
-#define DEBUG_FLOW BIT(2)
-#define DEBUG_AP BIT(3)
-#define DEBUG_HW BIT(4)
-#define DEBUG_EXTRA BIT(5)
-#define DEBUG_EXTRA2 BIT(6)
-#define DEBUG_PS2 BIT(7)
-#define DEBUG_MASK (DEBUG_PS | DEBUG_AP | DEBUG_HW | DEBUG_EXTRA)
-#define PDEBUG(n, args...) \
-do { if ((n) & DEBUG_MASK) printk(KERN_DEBUG args); } while (0)
-#define PDEBUG2(n, args...) \
-do { if ((n) & DEBUG_MASK) printk(args); } while (0)
-
-#else /* PRISM2_NO_DEBUG */
-
-#define PDEBUG(n, args...)
-#define PDEBUG2(n, args...)
-
-#endif /* PRISM2_NO_DEBUG */
-
-enum { BAP0 = 0, BAP1 = 1 };
-
-#define PRISM2_IO_DEBUG_CMD_INB 0
-#define PRISM2_IO_DEBUG_CMD_INW 1
-#define PRISM2_IO_DEBUG_CMD_INSW 2
-#define PRISM2_IO_DEBUG_CMD_OUTB 3
-#define PRISM2_IO_DEBUG_CMD_OUTW 4
-#define PRISM2_IO_DEBUG_CMD_OUTSW 5
-#define PRISM2_IO_DEBUG_CMD_ERROR 6
-#define PRISM2_IO_DEBUG_CMD_INTERRUPT 7
-
-#ifdef PRISM2_IO_DEBUG
-
-#define PRISM2_IO_DEBUG_ENTRY(cmd, reg, value) \
-(((cmd) << 24) | ((reg) << 16) | value)
-
-static inline void prism2_io_debug_add(struct net_device *dev, int cmd,
-				       int reg, int value)
-{
-	struct hostap_interface *iface = netdev_priv(dev);
-	local_info_t *local = iface->local;
-
-	if (!local->io_debug_enabled)
-		return;
-
-	local->io_debug[local->io_debug_head] =	jiffies & 0xffffffff;
-	if (++local->io_debug_head >= PRISM2_IO_DEBUG_SIZE)
-		local->io_debug_head = 0;
-	local->io_debug[local->io_debug_head] =
-		PRISM2_IO_DEBUG_ENTRY(cmd, reg, value);
-	if (++local->io_debug_head >= PRISM2_IO_DEBUG_SIZE)
-		local->io_debug_head = 0;
-}
-
-
-static inline void prism2_io_debug_error(struct net_device *dev, int err)
-{
-	struct hostap_interface *iface = netdev_priv(dev);
-	local_info_t *local = iface->local;
-	unsigned long flags;
-
-	if (!local->io_debug_enabled)
-		return;
-
-	spin_lock_irqsave(&local->lock, flags);
-	prism2_io_debug_add(dev, PRISM2_IO_DEBUG_CMD_ERROR, 0, err);
-	if (local->io_debug_enabled == 1) {
-		local->io_debug_enabled = 0;
-		printk(KERN_DEBUG "%s: I/O debug stopped\n", dev->name);
-	}
-	spin_unlock_irqrestore(&local->lock, flags);
-}
-
-#else /* PRISM2_IO_DEBUG */
-
-static inline void prism2_io_debug_add(struct net_device *dev, int cmd,
-				       int reg, int value)
-{
-}
-
-static inline void prism2_io_debug_error(struct net_device *dev, int err)
-{
-}
-
-#endif /* PRISM2_IO_DEBUG */
-
-
-#ifdef PRISM2_CALLBACK
-enum {
-	/* Called when card is enabled */
-	PRISM2_CALLBACK_ENABLE,
-
-	/* Called when card is disabled */
-	PRISM2_CALLBACK_DISABLE,
-
-	/* Called when RX/TX starts/ends */
-	PRISM2_CALLBACK_RX_START, PRISM2_CALLBACK_RX_END,
-	PRISM2_CALLBACK_TX_START, PRISM2_CALLBACK_TX_END
-};
-void prism2_callback(local_info_t *local, int event);
-#else /* PRISM2_CALLBACK */
-#define prism2_callback(d, e) do { } while (0)
-#endif /* PRISM2_CALLBACK */
-
-#endif /* __KERNEL__ */
-
-#endif /* HOSTAP_WLAN_H */
diff --git a/drivers/net/wireless/intersil/orinoco/Kconfig b/drivers/net/wireless/intersil/orinoco/Kconfig
deleted file mode 100644
index f62730aa7be3..000000000000
--- a/drivers/net/wireless/intersil/orinoco/Kconfig
+++ /dev/null
@@ -1,143 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-config HERMES
-	tristate "Hermes chipset 802.11b support (Orinoco/Prism2/Symbol)"
-	depends on (PPC_PMAC || PCI || PCMCIA)
-	depends on CFG80211
-	select CFG80211_WEXT_EXPORT
-	select WIRELESS_EXT
-	select WEXT_SPY
-	select WEXT_PRIV
-	select FW_LOADER
-	select CRYPTO
-	select CRYPTO_MICHAEL_MIC
-	help
-	  A driver for 802.11b wireless cards based on the "Hermes" or
-	  Intersil HFA384x (Prism 2) MAC controller.  This includes the vast
-	  majority of the PCMCIA 802.11b cards (which are nearly all rebadges)
-	  - except for the Cisco/Aironet cards.  Cards supported include the
-	  Apple Airport (not a PCMCIA card), WavelanIEEE/Orinoco,
-	  Cabletron/EnteraSys Roamabout, ELSA AirLancer, MELCO Buffalo, Avaya,
-	  IBM High Rate Wireless, Farralon Syyline, Samsung MagicLAN, Netgear
-	  MA401, LinkSys WPC-11, D-Link DWL-650, 3Com AirConnect, Intel
-	  IPW2011, and Symbol Spectrum24 High Rate amongst others.
-
-	  This option includes the guts of the driver, but in order to
-	  actually use a card you will also need to enable support for PCMCIA
-	  Hermes cards, PLX9052 based PCI adaptors or the Apple Airport below.
-
-	  You will also very likely also need the Wireless Tools in order to
-	  configure your card and that /etc/pcmcia/wireless.opts works :
-	  <https://www.hpl.hp.com/personal/Jean_Tourrilhes/Linux/Tools.html>
-
-config HERMES_PRISM
-	bool "Support Prism 2/2.5 chipset"
-	depends on HERMES
-	help
-
-	  Say Y to enable support for Prism 2 and 2.5 chipsets.  These
-	  chipsets are better handled by the hostap driver.  This driver
-	  would not support WPA or firmware download for Prism chipset.
-
-	  If you are not sure, say N.
-
-config HERMES_CACHE_FW_ON_INIT
-	bool "Cache Hermes firmware on driver initialisation"
-	depends on HERMES
-	default y
-	help
-	  Say Y to cache any firmware required by the Hermes drivers
-	  on startup.  The firmware will remain cached until the
-	  driver is unloaded.  The cache uses 64K of RAM.
-
-	  Otherwise load the firmware from userspace as required.  In
-	  this case the driver should be unloaded and restarted
-	  whenever the firmware is changed.
-
-	  If you are not sure, say Y.
-
-config APPLE_AIRPORT
-	tristate "Apple Airport support (built-in)"
-	depends on PPC_PMAC && HERMES
-	help
-	  Say Y here to support the Airport 802.11b wireless Ethernet hardware
-	  built into the Macintosh iBook and other recent PowerPC-based
-	  Macintosh machines. This is essentially a Lucent Orinoco card with
-	  a non-standard interface.
-
-	  This driver does not support the Airport Extreme (802.11b/g). Use
-	  the BCM43xx driver for Airport Extreme cards.
-
-config PLX_HERMES
-	tristate "Hermes in PLX9052 based PCI adaptor support (Netgear MA301 etc.)"
-	depends on PCI && HERMES
-	help
-	  Enable support for PCMCIA cards supported by the "Hermes" (aka
-	  orinoco) driver when used in PLX9052 based PCI adaptors.  These
-	  adaptors are not a full PCMCIA controller but act as a more limited
-	  PCI <-> PCMCIA bridge.  Several vendors sell such adaptors so that
-	  802.11b PCMCIA cards can be used in desktop machines.  The Netgear
-	  MA301 is such an adaptor.
-
-config TMD_HERMES
-	tristate "Hermes in TMD7160 based PCI adaptor support"
-	depends on PCI && HERMES
-	help
-	  Enable support for PCMCIA cards supported by the "Hermes" (aka
-	  orinoco) driver when used in TMD7160 based PCI adaptors.  These
-	  adaptors are not a full PCMCIA controller but act as a more limited
-	  PCI <-> PCMCIA bridge.  Several vendors sell such adaptors so that
-	  802.11b PCMCIA cards can be used in desktop machines.
-
-config NORTEL_HERMES
-	tristate "Nortel emobility PCI adaptor support"
-	depends on PCI && HERMES
-	help
-	  Enable support for PCMCIA cards supported by the "Hermes" (aka
-	  orinoco) driver when used in Nortel emobility PCI adaptors.  These
-	  adaptors are not full PCMCIA controllers, but act as a more limited
-	  PCI <-> PCMCIA bridge.
-
-config PCI_HERMES
-	tristate "Prism 2.5 PCI 802.11b adaptor support"
-	depends on PCI && HERMES && HERMES_PRISM
-	help
-	  Enable support for PCI and mini-PCI 802.11b wireless NICs based on
-	  the Prism 2.5 chipset.  These are true PCI cards, not the 802.11b
-	  PCMCIA cards bundled with PCI<->PCMCIA adaptors which are also
-	  common.  Some of the built-in wireless adaptors in laptops are of
-	  this variety.
-
-config PCMCIA_HERMES
-	tristate "Hermes PCMCIA card support"
-	depends on PCMCIA && HERMES && HAS_IOPORT_MAP
-	help
-	  A driver for "Hermes" chipset based PCMCIA wireless adaptors, such
-	  as the Lucent WavelanIEEE/Orinoco cards and their OEM (Cabletron/
-	  EnteraSys RoamAbout 802.11, ELSA Airlancer, Melco Buffalo and
-	  others).  It should also be usable on various Prism II based cards
-	  such as the Linksys, D-Link and Farallon Skyline.  It should also
-	  work on Symbol cards such as the 3Com AirConnect and Ericsson WLAN.
-
-	  You will very likely need the Wireless Tools in order to
-	  configure your card and that /etc/pcmcia/wireless.opts works:
-	  <https://www.hpl.hp.com/personal/Jean_Tourrilhes/Linux/Tools.html>.
-
-config PCMCIA_SPECTRUM
-	tristate "Symbol Spectrum24 Trilogy PCMCIA card support"
-	depends on PCMCIA && HERMES && HAS_IOPORT_MAP
-	help
-
-	  This is a driver for 802.11b cards using RAM-loadable Symbol
-	  firmware, such as Symbol Wireless Networker LA4100, CompactFlash
-	  cards by Socket Communications and Intel PRO/Wireless 2011B.
-
-	  This driver requires firmware download on startup.  Utilities
-	  for downloading Symbol firmware are available at
-	  <http://sourceforge.net/projects/orinoco/>
-
-config ORINOCO_USB
-	tristate "Agere Orinoco USB support"
-	depends on USB && HERMES
-	select FW_LOADER
-	help
-	  This driver is for USB versions of the Agere Orinoco card.
diff --git a/drivers/net/wireless/intersil/orinoco/Makefile b/drivers/net/wireless/intersil/orinoco/Makefile
deleted file mode 100644
index 0c29c56c88d6..000000000000
--- a/drivers/net/wireless/intersil/orinoco/Makefile
+++ /dev/null
@@ -1,15 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile for the orinoco wireless device drivers.
-#
-orinoco-objs := main.o fw.o hw.o mic.o scan.o wext.o hermes_dld.o hermes.o cfg.o
-
-obj-$(CONFIG_HERMES)		+= orinoco.o
-obj-$(CONFIG_PCMCIA_HERMES)	+= orinoco_cs.o
-obj-$(CONFIG_APPLE_AIRPORT)	+= airport.o
-obj-$(CONFIG_PLX_HERMES)	+= orinoco_plx.o
-obj-$(CONFIG_PCI_HERMES)	+= orinoco_pci.o
-obj-$(CONFIG_TMD_HERMES)	+= orinoco_tmd.o
-obj-$(CONFIG_NORTEL_HERMES)	+= orinoco_nortel.o
-obj-$(CONFIG_PCMCIA_SPECTRUM)	+= spectrum_cs.o
-obj-$(CONFIG_ORINOCO_USB)	+= orinoco_usb.o
diff --git a/drivers/net/wireless/intersil/orinoco/airport.c b/drivers/net/wireless/intersil/orinoco/airport.c
deleted file mode 100644
index 45ac00fdafa5..000000000000
--- a/drivers/net/wireless/intersil/orinoco/airport.c
+++ /dev/null
@@ -1,268 +0,0 @@
-/* airport.c
- *
- * A driver for "Hermes" chipset based Apple Airport wireless
- * card.
- *
- * Copyright notice & release notes in file main.c
- *
- * Note specific to airport stub:
- *
- *  0.05 : first version of the new split driver
- *  0.06 : fix possible hang on powerup, add sleep support
- */
-
-#define DRIVER_NAME "airport"
-#define PFX DRIVER_NAME ": "
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/mod_devicetable.h>
-#include <asm/pmac_feature.h>
-
-#include "orinoco.h"
-
-#define AIRPORT_IO_LEN	(0x1000)	/* one page */
-
-struct airport {
-	struct macio_dev *mdev;
-	void __iomem *vaddr;
-	unsigned int irq;
-	int irq_requested;
-	int ndev_registered;
-};
-
-static int
-airport_suspend(struct macio_dev *mdev, pm_message_t state)
-{
-	struct orinoco_private *priv = dev_get_drvdata(&mdev->ofdev.dev);
-	struct net_device *dev = priv->ndev;
-	struct airport *card = priv->card;
-	unsigned long flags;
-	int err;
-
-	printk(KERN_DEBUG "%s: Airport entering sleep mode\n", dev->name);
-
-	err = orinoco_lock(priv, &flags);
-	if (err) {
-		printk(KERN_ERR "%s: hw_unavailable on PBOOK_SLEEP_NOW\n",
-		       dev->name);
-		return 0;
-	}
-
-	orinoco_down(priv);
-	orinoco_unlock(priv, &flags);
-
-	disable_irq(card->irq);
-	pmac_call_feature(PMAC_FTR_AIRPORT_ENABLE,
-			  macio_get_of_node(mdev), 0, 0);
-
-	return 0;
-}
-
-static int
-airport_resume(struct macio_dev *mdev)
-{
-	struct orinoco_private *priv = dev_get_drvdata(&mdev->ofdev.dev);
-	struct net_device *dev = priv->ndev;
-	struct airport *card = priv->card;
-	unsigned long flags;
-	int err;
-
-	printk(KERN_DEBUG "%s: Airport waking up\n", dev->name);
-
-	pmac_call_feature(PMAC_FTR_AIRPORT_ENABLE,
-			  macio_get_of_node(mdev), 0, 1);
-	msleep(200);
-
-	enable_irq(card->irq);
-
-	priv->hw.ops->lock_irqsave(&priv->lock, &flags);
-	err = orinoco_up(priv);
-	priv->hw.ops->unlock_irqrestore(&priv->lock, &flags);
-
-	return err;
-}
-
-static int
-airport_detach(struct macio_dev *mdev)
-{
-	struct orinoco_private *priv = dev_get_drvdata(&mdev->ofdev.dev);
-	struct airport *card = priv->card;
-
-	if (card->ndev_registered)
-		orinoco_if_del(priv);
-	card->ndev_registered = 0;
-
-	if (card->irq_requested)
-		free_irq(card->irq, priv);
-	card->irq_requested = 0;
-
-	if (card->vaddr)
-		iounmap(card->vaddr);
-	card->vaddr = NULL;
-
-	macio_release_resource(mdev, 0);
-
-	pmac_call_feature(PMAC_FTR_AIRPORT_ENABLE,
-			  macio_get_of_node(mdev), 0, 0);
-	ssleep(1);
-
-	macio_set_drvdata(mdev, NULL);
-	free_orinocodev(priv);
-
-	return 0;
-}
-
-static int airport_hard_reset(struct orinoco_private *priv)
-{
-	/* It would be nice to power cycle the Airport for a real hard
-	 * reset, but for some reason although it appears to
-	 * re-initialize properly, it falls in a screaming heap
-	 * shortly afterwards. */
-#if 0
-	struct airport *card = priv->card;
-
-	/* Vitally important.  If we don't do this it seems we get an
-	 * interrupt somewhere during the power cycle, since
-	 * hw_unavailable is already set it doesn't get ACKed, we get
-	 * into an interrupt loop and the PMU decides to turn us
-	 * off. */
-	disable_irq(card->irq);
-
-	pmac_call_feature(PMAC_FTR_AIRPORT_ENABLE,
-			  macio_get_of_node(card->mdev), 0, 0);
-	ssleep(1);
-	pmac_call_feature(PMAC_FTR_AIRPORT_ENABLE,
-			  macio_get_of_node(card->mdev), 0, 1);
-	ssleep(1);
-
-	enable_irq(card->irq);
-	ssleep(1);
-#endif
-
-	return 0;
-}
-
-static int
-airport_attach(struct macio_dev *mdev, const struct of_device_id *match)
-{
-	struct orinoco_private *priv;
-	struct airport *card;
-	unsigned long phys_addr;
-	struct hermes *hw;
-
-	if (macio_resource_count(mdev) < 1 || macio_irq_count(mdev) < 1) {
-		printk(KERN_ERR PFX "Wrong interrupt/addresses in OF tree\n");
-		return -ENODEV;
-	}
-
-	/* Allocate space for private device-specific data */
-	priv = alloc_orinocodev(sizeof(*card), &mdev->ofdev.dev,
-				airport_hard_reset, NULL);
-	if (!priv) {
-		printk(KERN_ERR PFX "Cannot allocate network device\n");
-		return -ENODEV;
-	}
-	card = priv->card;
-
-	hw = &priv->hw;
-	card->mdev = mdev;
-
-	if (macio_request_resource(mdev, 0, DRIVER_NAME)) {
-		printk(KERN_ERR PFX "can't request IO resource !\n");
-		free_orinocodev(priv);
-		return -EBUSY;
-	}
-
-	macio_set_drvdata(mdev, priv);
-
-	/* Setup interrupts & base address */
-	card->irq = macio_irq(mdev, 0);
-	phys_addr = macio_resource_start(mdev, 0);  /* Physical address */
-	printk(KERN_DEBUG PFX "Physical address %lx\n", phys_addr);
-	card->vaddr = ioremap(phys_addr, AIRPORT_IO_LEN);
-	if (!card->vaddr) {
-		printk(KERN_ERR PFX "ioremap() failed\n");
-		goto failed;
-	}
-
-	hermes_struct_init(hw, card->vaddr, HERMES_16BIT_REGSPACING);
-
-	/* Power up card */
-	pmac_call_feature(PMAC_FTR_AIRPORT_ENABLE,
-			  macio_get_of_node(mdev), 0, 1);
-	ssleep(1);
-
-	/* Reset it before we get the interrupt */
-	hw->ops->init(hw);
-
-	if (request_irq(card->irq, orinoco_interrupt, 0, DRIVER_NAME, priv)) {
-		printk(KERN_ERR PFX "Couldn't get IRQ %d\n", card->irq);
-		goto failed;
-	}
-	card->irq_requested = 1;
-
-	/* Initialise the main driver */
-	if (orinoco_init(priv) != 0) {
-		printk(KERN_ERR PFX "orinoco_init() failed\n");
-		goto failed;
-	}
-
-	/* Register an interface with the stack */
-	if (orinoco_if_add(priv, phys_addr, card->irq, NULL) != 0) {
-		printk(KERN_ERR PFX "orinoco_if_add() failed\n");
-		goto failed;
-	}
-	card->ndev_registered = 1;
-	return 0;
- failed:
-	airport_detach(mdev);
-	return -ENODEV;
-}				/* airport_attach */
-
-
-static char version[] __initdata = DRIVER_NAME " " DRIVER_VERSION
-	" (Benjamin Herrenschmidt <benh@kernel.crashing.org>)";
-MODULE_AUTHOR("Benjamin Herrenschmidt <benh@kernel.crashing.org>");
-MODULE_DESCRIPTION("Driver for the Apple Airport wireless card.");
-MODULE_LICENSE("Dual MPL/GPL");
-
-static const struct of_device_id airport_match[] = {
-	{
-	.name		= "radio",
-	},
-	{},
-};
-
-MODULE_DEVICE_TABLE(of, airport_match);
-
-static struct macio_driver airport_driver = {
-	.driver = {
-		.name		= DRIVER_NAME,
-		.owner		= THIS_MODULE,
-		.of_match_table	= airport_match,
-	},
-	.probe		= airport_attach,
-	.remove		= airport_detach,
-	.suspend	= airport_suspend,
-	.resume		= airport_resume,
-};
-
-static int __init
-init_airport(void)
-{
-	printk(KERN_DEBUG "%s\n", version);
-
-	return macio_register_driver(&airport_driver);
-}
-
-static void __exit
-exit_airport(void)
-{
-	macio_unregister_driver(&airport_driver);
-}
-
-module_init(init_airport);
-module_exit(exit_airport);
diff --git a/drivers/net/wireless/intersil/orinoco/cfg.c b/drivers/net/wireless/intersil/orinoco/cfg.c
deleted file mode 100644
index b2d5ec8634b5..000000000000
--- a/drivers/net/wireless/intersil/orinoco/cfg.c
+++ /dev/null
@@ -1,291 +0,0 @@
-/* cfg80211 support
- *
- * See copyright notice in main.c
- */
-#include <linux/ieee80211.h>
-#include <net/cfg80211.h>
-#include "hw.h"
-#include "main.h"
-#include "orinoco.h"
-
-#include "cfg.h"
-
-/* Supported bitrates. Must agree with hw.c */
-static struct ieee80211_rate orinoco_rates[] = {
-	{ .bitrate = 10 },
-	{ .bitrate = 20 },
-	{ .bitrate = 55 },
-	{ .bitrate = 110 },
-};
-
-static const void * const orinoco_wiphy_privid = &orinoco_wiphy_privid;
-
-/* Called after orinoco_private is allocated. */
-void orinoco_wiphy_init(struct wiphy *wiphy)
-{
-	struct orinoco_private *priv = wiphy_priv(wiphy);
-
-	wiphy->privid = orinoco_wiphy_privid;
-
-	set_wiphy_dev(wiphy, priv->dev);
-}
-
-/* Called after firmware is initialised */
-int orinoco_wiphy_register(struct wiphy *wiphy)
-{
-	struct orinoco_private *priv = wiphy_priv(wiphy);
-	int i, channels = 0;
-
-	if (priv->firmware_type == FIRMWARE_TYPE_AGERE)
-		wiphy->max_scan_ssids = 1;
-	else
-		wiphy->max_scan_ssids = 0;
-
-	wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION);
-
-	/* TODO: should we set if we only have demo ad-hoc?
-	 *       (priv->has_port3)
-	 */
-	if (priv->has_ibss)
-		wiphy->interface_modes |= BIT(NL80211_IFTYPE_ADHOC);
-
-	if (!priv->broken_monitor || force_monitor)
-		wiphy->interface_modes |= BIT(NL80211_IFTYPE_MONITOR);
-
-	priv->band.bitrates = orinoco_rates;
-	priv->band.n_bitrates = ARRAY_SIZE(orinoco_rates);
-
-	/* Only support channels allowed by the card EEPROM */
-	for (i = 0; i < NUM_CHANNELS; i++) {
-		if (priv->channel_mask & (1 << i)) {
-			priv->channels[i].center_freq =
-				ieee80211_channel_to_frequency(i + 1,
-							   NL80211_BAND_2GHZ);
-			channels++;
-		}
-	}
-	priv->band.channels = priv->channels;
-	priv->band.n_channels = channels;
-
-	wiphy->bands[NL80211_BAND_2GHZ] = &priv->band;
-	wiphy->signal_type = CFG80211_SIGNAL_TYPE_MBM;
-
-	i = 0;
-	if (priv->has_wep) {
-		priv->cipher_suites[i] = WLAN_CIPHER_SUITE_WEP40;
-		i++;
-
-		if (priv->has_big_wep) {
-			priv->cipher_suites[i] = WLAN_CIPHER_SUITE_WEP104;
-			i++;
-		}
-	}
-	if (priv->has_wpa) {
-		priv->cipher_suites[i] = WLAN_CIPHER_SUITE_TKIP;
-		i++;
-	}
-	wiphy->cipher_suites = priv->cipher_suites;
-	wiphy->n_cipher_suites = i;
-
-	wiphy->rts_threshold = priv->rts_thresh;
-	if (!priv->has_mwo)
-		wiphy->frag_threshold = priv->frag_thresh + 1;
-	wiphy->retry_short = priv->short_retry_limit;
-	wiphy->retry_long = priv->long_retry_limit;
-
-	return wiphy_register(wiphy);
-}
-
-static int orinoco_change_vif(struct wiphy *wiphy, struct net_device *dev,
-			      enum nl80211_iftype type,
-			      struct vif_params *params)
-{
-	struct orinoco_private *priv = wiphy_priv(wiphy);
-	int err = 0;
-	unsigned long lock;
-
-	if (orinoco_lock(priv, &lock) != 0)
-		return -EBUSY;
-
-	switch (type) {
-	case NL80211_IFTYPE_ADHOC:
-		if (!priv->has_ibss && !priv->has_port3)
-			err = -EINVAL;
-		break;
-
-	case NL80211_IFTYPE_STATION:
-		break;
-
-	case NL80211_IFTYPE_MONITOR:
-		if (priv->broken_monitor && !force_monitor) {
-			wiphy_warn(wiphy,
-				   "Monitor mode support is buggy in this firmware, not enabling\n");
-			err = -EINVAL;
-		}
-		break;
-
-	default:
-		err = -EINVAL;
-	}
-
-	if (!err) {
-		priv->iw_mode = type;
-		set_port_type(priv);
-		err = orinoco_commit(priv);
-	}
-
-	orinoco_unlock(priv, &lock);
-
-	return err;
-}
-
-static int orinoco_scan(struct wiphy *wiphy,
-			struct cfg80211_scan_request *request)
-{
-	struct orinoco_private *priv = wiphy_priv(wiphy);
-	int err;
-
-	if (!request)
-		return -EINVAL;
-
-	if (priv->scan_request && priv->scan_request != request)
-		return -EBUSY;
-
-	priv->scan_request = request;
-
-	err = orinoco_hw_trigger_scan(priv, request->ssids);
-	/* On error the we aren't processing the request */
-	if (err)
-		priv->scan_request = NULL;
-
-	return err;
-}
-
-static int orinoco_set_monitor_channel(struct wiphy *wiphy,
-				       struct cfg80211_chan_def *chandef)
-{
-	struct orinoco_private *priv = wiphy_priv(wiphy);
-	int err = 0;
-	unsigned long flags;
-	int channel;
-
-	if (!chandef->chan)
-		return -EINVAL;
-
-	if (cfg80211_get_chandef_type(chandef) != NL80211_CHAN_NO_HT)
-		return -EINVAL;
-
-	if (chandef->chan->band != NL80211_BAND_2GHZ)
-		return -EINVAL;
-
-	channel = ieee80211_frequency_to_channel(chandef->chan->center_freq);
-
-	if ((channel < 1) || (channel > NUM_CHANNELS) ||
-	     !(priv->channel_mask & (1 << (channel - 1))))
-		return -EINVAL;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	priv->channel = channel;
-	if (priv->iw_mode == NL80211_IFTYPE_MONITOR) {
-		/* Fast channel change - no commit if successful */
-		struct hermes *hw = &priv->hw;
-		err = hw->ops->cmd_wait(hw, HERMES_CMD_TEST |
-					    HERMES_TEST_SET_CHANNEL,
-					channel, NULL);
-	}
-	orinoco_unlock(priv, &flags);
-
-	return err;
-}
-
-static int orinoco_set_wiphy_params(struct wiphy *wiphy, u32 changed)
-{
-	struct orinoco_private *priv = wiphy_priv(wiphy);
-	int frag_value = -1;
-	int rts_value = -1;
-	int err = 0;
-
-	if (changed & WIPHY_PARAM_RETRY_SHORT) {
-		/* Setting short retry not supported */
-		err = -EINVAL;
-	}
-
-	if (changed & WIPHY_PARAM_RETRY_LONG) {
-		/* Setting long retry not supported */
-		err = -EINVAL;
-	}
-
-	if (changed & WIPHY_PARAM_FRAG_THRESHOLD) {
-		/* Set fragmentation */
-		if (priv->has_mwo) {
-			if (wiphy->frag_threshold == -1)
-				frag_value = 0;
-			else {
-				printk(KERN_WARNING "%s: Fixed fragmentation "
-				       "is not supported on this firmware. "
-				       "Using MWO robust instead.\n",
-				       priv->ndev->name);
-				frag_value = 1;
-			}
-		} else {
-			if (wiphy->frag_threshold == -1)
-				frag_value = 2346;
-			else if ((wiphy->frag_threshold < 257) ||
-				 (wiphy->frag_threshold > 2347))
-				err = -EINVAL;
-			else
-				/* cfg80211 value is 257-2347 (odd only)
-				 * orinoco rid has range 256-2346 (even only) */
-				frag_value = wiphy->frag_threshold & ~0x1;
-		}
-	}
-
-	if (changed & WIPHY_PARAM_RTS_THRESHOLD) {
-		/* Set RTS.
-		 *
-		 * Prism documentation suggests default of 2432,
-		 * and a range of 0-3000.
-		 *
-		 * Current implementation uses 2347 as the default and
-		 * the upper limit.
-		 */
-
-		if (wiphy->rts_threshold == -1)
-			rts_value = 2347;
-		else if (wiphy->rts_threshold > 2347)
-			err = -EINVAL;
-		else
-			rts_value = wiphy->rts_threshold;
-	}
-
-	if (!err) {
-		unsigned long flags;
-
-		if (orinoco_lock(priv, &flags) != 0)
-			return -EBUSY;
-
-		if (frag_value >= 0) {
-			if (priv->has_mwo)
-				priv->mwo_robust = frag_value;
-			else
-				priv->frag_thresh = frag_value;
-		}
-		if (rts_value >= 0)
-			priv->rts_thresh = rts_value;
-
-		err = orinoco_commit(priv);
-
-		orinoco_unlock(priv, &flags);
-	}
-
-	return err;
-}
-
-const struct cfg80211_ops orinoco_cfg_ops = {
-	.change_virtual_intf = orinoco_change_vif,
-	.set_monitor_channel = orinoco_set_monitor_channel,
-	.scan = orinoco_scan,
-	.set_wiphy_params = orinoco_set_wiphy_params,
-};
diff --git a/drivers/net/wireless/intersil/orinoco/cfg.h b/drivers/net/wireless/intersil/orinoco/cfg.h
deleted file mode 100644
index 3ddc96a06cd7..000000000000
--- a/drivers/net/wireless/intersil/orinoco/cfg.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* cfg80211 support.
- *
- * See copyright notice in main.c
- */
-#ifndef ORINOCO_CFG_H
-#define ORINOCO_CFG_H
-
-#include <net/cfg80211.h>
-
-extern const struct cfg80211_ops orinoco_cfg_ops;
-
-void orinoco_wiphy_init(struct wiphy *wiphy);
-int orinoco_wiphy_register(struct wiphy *wiphy);
-
-#endif /* ORINOCO_CFG_H */
diff --git a/drivers/net/wireless/intersil/orinoco/fw.c b/drivers/net/wireless/intersil/orinoco/fw.c
deleted file mode 100644
index 015af782881b..000000000000
--- a/drivers/net/wireless/intersil/orinoco/fw.c
+++ /dev/null
@@ -1,387 +0,0 @@
-/* Firmware file reading and download helpers
- *
- * See copyright notice in main.c
- */
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/firmware.h>
-#include <linux/device.h>
-#include <linux/module.h>
-
-#include "hermes.h"
-#include "hermes_dld.h"
-#include "orinoco.h"
-
-#include "fw.h"
-
-/* End markers (for Symbol firmware only) */
-#define TEXT_END	0x1A		/* End of text header */
-
-struct fw_info {
-	char *pri_fw;
-	char *sta_fw;
-	char *ap_fw;
-	u32 pda_addr;
-	u16 pda_size;
-};
-
-static const struct fw_info orinoco_fw[] = {
-	{ NULL, "agere_sta_fw.bin", "agere_ap_fw.bin", 0x00390000, 1000 },
-	{ NULL, "prism_sta_fw.bin", "prism_ap_fw.bin", 0, 1024 },
-	{ "symbol_sp24t_prim_fw", "symbol_sp24t_sec_fw", NULL, 0x00003100, 512 }
-};
-MODULE_FIRMWARE("agere_sta_fw.bin");
-MODULE_FIRMWARE("agere_ap_fw.bin");
-MODULE_FIRMWARE("prism_sta_fw.bin");
-MODULE_FIRMWARE("prism_ap_fw.bin");
-MODULE_FIRMWARE("symbol_sp24t_prim_fw");
-MODULE_FIRMWARE("symbol_sp24t_sec_fw");
-
-/* Structure used to access fields in FW
- * Make sure LE decoding macros are used
- */
-struct orinoco_fw_header {
-	char hdr_vers[6];       /* ASCII string for header version */
-	__le16 headersize;      /* Total length of header */
-	__le32 entry_point;     /* NIC entry point */
-	__le32 blocks;          /* Number of blocks to program */
-	__le32 block_offset;    /* Offset of block data from eof header */
-	__le32 pdr_offset;      /* Offset to PDR data from eof header */
-	__le32 pri_offset;      /* Offset to primary plug data */
-	__le32 compat_offset;   /* Offset to compatibility data*/
-	char signature[];      /* FW signature length headersize-20 */
-} __packed;
-
-/* Check the range of various header entries. Return a pointer to a
- * description of the problem, or NULL if everything checks out. */
-static const char *validate_fw(const struct orinoco_fw_header *hdr, size_t len)
-{
-	u16 hdrsize;
-
-	if (len < sizeof(*hdr))
-		return "image too small";
-	if (memcmp(hdr->hdr_vers, "HFW", 3) != 0)
-		return "format not recognised";
-
-	hdrsize = le16_to_cpu(hdr->headersize);
-	if (hdrsize > len)
-		return "bad headersize";
-	if ((hdrsize + le32_to_cpu(hdr->block_offset)) > len)
-		return "bad block offset";
-	if ((hdrsize + le32_to_cpu(hdr->pdr_offset)) > len)
-		return "bad PDR offset";
-	if ((hdrsize + le32_to_cpu(hdr->pri_offset)) > len)
-		return "bad PRI offset";
-	if ((hdrsize + le32_to_cpu(hdr->compat_offset)) > len)
-		return "bad compat offset";
-
-	/* TODO: consider adding a checksum or CRC to the firmware format */
-	return NULL;
-}
-
-#if defined(CONFIG_HERMES_CACHE_FW_ON_INIT) || defined(CONFIG_PM_SLEEP)
-static inline const struct firmware *
-orinoco_cached_fw_get(struct orinoco_private *priv, bool primary)
-{
-	if (primary)
-		return priv->cached_pri_fw;
-	else
-		return priv->cached_fw;
-}
-#else
-#define orinoco_cached_fw_get(priv, primary) (NULL)
-#endif
-
-/* Download either STA or AP firmware into the card. */
-static int
-orinoco_dl_firmware(struct orinoco_private *priv,
-		    const struct fw_info *fw,
-		    int ap)
-{
-	/* Plug Data Area (PDA) */
-	__le16 *pda;
-
-	struct hermes *hw = &priv->hw;
-	const struct firmware *fw_entry;
-	const struct orinoco_fw_header *hdr;
-	const unsigned char *first_block;
-	const void *end;
-	const char *firmware;
-	const char *fw_err;
-	struct device *dev = priv->dev;
-	int err = 0;
-
-	pda = kzalloc(fw->pda_size, GFP_KERNEL);
-	if (!pda)
-		return -ENOMEM;
-
-	if (ap)
-		firmware = fw->ap_fw;
-	else
-		firmware = fw->sta_fw;
-
-	dev_dbg(dev, "Attempting to download firmware %s\n", firmware);
-
-	/* Read current plug data */
-	err = hw->ops->read_pda(hw, pda, fw->pda_addr, fw->pda_size);
-	dev_dbg(dev, "Read PDA returned %d\n", err);
-	if (err)
-		goto free;
-
-	if (!orinoco_cached_fw_get(priv, false)) {
-		err = request_firmware(&fw_entry, firmware, priv->dev);
-
-		if (err) {
-			dev_err(dev, "Cannot find firmware %s\n", firmware);
-			err = -ENOENT;
-			goto free;
-		}
-	} else
-		fw_entry = orinoco_cached_fw_get(priv, false);
-
-	hdr = (const struct orinoco_fw_header *) fw_entry->data;
-
-	fw_err = validate_fw(hdr, fw_entry->size);
-	if (fw_err) {
-		dev_warn(dev, "Invalid firmware image detected (%s). "
-			 "Aborting download\n", fw_err);
-		err = -EINVAL;
-		goto abort;
-	}
-
-	/* Enable aux port to allow programming */
-	err = hw->ops->program_init(hw, le32_to_cpu(hdr->entry_point));
-	dev_dbg(dev, "Program init returned %d\n", err);
-	if (err != 0)
-		goto abort;
-
-	/* Program data */
-	first_block = (fw_entry->data +
-		       le16_to_cpu(hdr->headersize) +
-		       le32_to_cpu(hdr->block_offset));
-	end = fw_entry->data + fw_entry->size;
-
-	err = hermes_program(hw, first_block, end);
-	dev_dbg(dev, "Program returned %d\n", err);
-	if (err != 0)
-		goto abort;
-
-	/* Update production data */
-	first_block = (fw_entry->data +
-		       le16_to_cpu(hdr->headersize) +
-		       le32_to_cpu(hdr->pdr_offset));
-
-	err = hermes_apply_pda_with_defaults(hw, first_block, end, pda,
-					     &pda[fw->pda_size / sizeof(*pda)]);
-	dev_dbg(dev, "Apply PDA returned %d\n", err);
-	if (err)
-		goto abort;
-
-	/* Tell card we've finished */
-	err = hw->ops->program_end(hw);
-	dev_dbg(dev, "Program end returned %d\n", err);
-	if (err != 0)
-		goto abort;
-
-	/* Check if we're running */
-	dev_dbg(dev, "hermes_present returned %d\n", hermes_present(hw));
-
-abort:
-	/* If we requested the firmware, release it. */
-	if (!orinoco_cached_fw_get(priv, false))
-		release_firmware(fw_entry);
-
-free:
-	kfree(pda);
-	return err;
-}
-
-/*
- * Process a firmware image - stop the card, load the firmware, reset
- * the card and make sure it responds.  For the secondary firmware take
- * care of the PDA - read it and then write it on top of the firmware.
- */
-static int
-symbol_dl_image(struct orinoco_private *priv, const struct fw_info *fw,
-		const unsigned char *image, const void *end,
-		int secondary)
-{
-	struct hermes *hw = &priv->hw;
-	int ret = 0;
-	const unsigned char *ptr;
-	const unsigned char *first_block;
-
-	/* Plug Data Area (PDA) */
-	__le16 *pda = NULL;
-
-	/* Binary block begins after the 0x1A marker */
-	ptr = image;
-	while (*ptr++ != TEXT_END);
-	first_block = ptr;
-
-	/* Read the PDA from EEPROM */
-	if (secondary) {
-		pda = kzalloc(fw->pda_size, GFP_KERNEL);
-		if (!pda)
-			return -ENOMEM;
-
-		ret = hw->ops->read_pda(hw, pda, fw->pda_addr, fw->pda_size);
-		if (ret)
-			goto free;
-	}
-
-	/* Stop the firmware, so that it can be safely rewritten */
-	if (priv->stop_fw) {
-		ret = priv->stop_fw(priv, 1);
-		if (ret)
-			goto free;
-	}
-
-	/* Program the adapter with new firmware */
-	ret = hermes_program(hw, first_block, end);
-	if (ret)
-		goto free;
-
-	/* Write the PDA to the adapter */
-	if (secondary) {
-		size_t len = hermes_blocks_length(first_block, end);
-		ptr = first_block + len;
-		ret = hermes_apply_pda(hw, ptr, end, pda,
-				       &pda[fw->pda_size / sizeof(*pda)]);
-		kfree(pda);
-		if (ret)
-			return ret;
-	}
-
-	/* Run the firmware */
-	if (priv->stop_fw) {
-		ret = priv->stop_fw(priv, 0);
-		if (ret)
-			return ret;
-	}
-
-	/* Reset hermes chip and make sure it responds */
-	ret = hw->ops->init(hw);
-
-	/* hermes_reset() should return 0 with the secondary firmware */
-	if (secondary && ret != 0)
-		return -ENODEV;
-
-	/* And this should work with any firmware */
-	if (!hermes_present(hw))
-		return -ENODEV;
-
-	return 0;
-
-free:
-	kfree(pda);
-	return ret;
-}
-
-
-/*
- * Download the firmware into the card, this also does a PCMCIA soft
- * reset on the card, to make sure it's in a sane state.
- */
-static int
-symbol_dl_firmware(struct orinoco_private *priv,
-		   const struct fw_info *fw)
-{
-	struct device *dev = priv->dev;
-	int ret;
-	const struct firmware *fw_entry;
-
-	if (!orinoco_cached_fw_get(priv, true)) {
-		if (request_firmware(&fw_entry, fw->pri_fw, priv->dev) != 0) {
-			dev_err(dev, "Cannot find firmware: %s\n", fw->pri_fw);
-			return -ENOENT;
-		}
-	} else
-		fw_entry = orinoco_cached_fw_get(priv, true);
-
-	/* Load primary firmware */
-	ret = symbol_dl_image(priv, fw, fw_entry->data,
-			      fw_entry->data + fw_entry->size, 0);
-
-	if (!orinoco_cached_fw_get(priv, true))
-		release_firmware(fw_entry);
-	if (ret) {
-		dev_err(dev, "Primary firmware download failed\n");
-		return ret;
-	}
-
-	if (!orinoco_cached_fw_get(priv, false)) {
-		if (request_firmware(&fw_entry, fw->sta_fw, priv->dev) != 0) {
-			dev_err(dev, "Cannot find firmware: %s\n", fw->sta_fw);
-			return -ENOENT;
-		}
-	} else
-		fw_entry = orinoco_cached_fw_get(priv, false);
-
-	/* Load secondary firmware */
-	ret = symbol_dl_image(priv, fw, fw_entry->data,
-			      fw_entry->data + fw_entry->size, 1);
-	if (!orinoco_cached_fw_get(priv, false))
-		release_firmware(fw_entry);
-	if (ret)
-		dev_err(dev, "Secondary firmware download failed\n");
-
-	return ret;
-}
-
-int orinoco_download(struct orinoco_private *priv)
-{
-	int err = 0;
-	/* Reload firmware */
-	switch (priv->firmware_type) {
-	case FIRMWARE_TYPE_AGERE:
-		/* case FIRMWARE_TYPE_INTERSIL: */
-		err = orinoco_dl_firmware(priv,
-					  &orinoco_fw[priv->firmware_type], 0);
-		break;
-
-	case FIRMWARE_TYPE_SYMBOL:
-		err = symbol_dl_firmware(priv,
-					 &orinoco_fw[priv->firmware_type]);
-		break;
-	case FIRMWARE_TYPE_INTERSIL:
-		break;
-	}
-	/* TODO: if we fail we probably need to reinitialise
-	 * the driver */
-
-	return err;
-}
-
-#if defined(CONFIG_HERMES_CACHE_FW_ON_INIT) || defined(CONFIG_PM_SLEEP)
-void orinoco_cache_fw(struct orinoco_private *priv, int ap)
-{
-	const struct firmware *fw_entry = NULL;
-	const char *pri_fw;
-	const char *fw;
-
-	pri_fw = orinoco_fw[priv->firmware_type].pri_fw;
-	if (ap)
-		fw = orinoco_fw[priv->firmware_type].ap_fw;
-	else
-		fw = orinoco_fw[priv->firmware_type].sta_fw;
-
-	if (pri_fw) {
-		if (request_firmware(&fw_entry, pri_fw, priv->dev) == 0)
-			priv->cached_pri_fw = fw_entry;
-	}
-
-	if (fw) {
-		if (request_firmware(&fw_entry, fw, priv->dev) == 0)
-			priv->cached_fw = fw_entry;
-	}
-}
-
-void orinoco_uncache_fw(struct orinoco_private *priv)
-{
-	release_firmware(priv->cached_pri_fw);
-	release_firmware(priv->cached_fw);
-	priv->cached_pri_fw = NULL;
-	priv->cached_fw = NULL;
-}
-#endif
diff --git a/drivers/net/wireless/intersil/orinoco/fw.h b/drivers/net/wireless/intersil/orinoco/fw.h
deleted file mode 100644
index aca63e3c4b5b..000000000000
--- a/drivers/net/wireless/intersil/orinoco/fw.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* Firmware file reading and download helpers
- *
- * See copyright notice in main.c
- */
-#ifndef _ORINOCO_FW_H_
-#define _ORINOCO_FW_H_
-
-/* Forward declations */
-struct orinoco_private;
-
-int orinoco_download(struct orinoco_private *priv);
-
-#if defined(CONFIG_HERMES_CACHE_FW_ON_INIT) || defined(CONFIG_PM_SLEEP)
-void orinoco_cache_fw(struct orinoco_private *priv, int ap);
-void orinoco_uncache_fw(struct orinoco_private *priv);
-#else
-#define orinoco_cache_fw(priv, ap) do { } while (0)
-#define orinoco_uncache_fw(priv) do { } while (0)
-#endif
-
-#endif /* _ORINOCO_FW_H_ */
diff --git a/drivers/net/wireless/intersil/orinoco/hermes.c b/drivers/net/wireless/intersil/orinoco/hermes.c
deleted file mode 100644
index 4888286727ff..000000000000
--- a/drivers/net/wireless/intersil/orinoco/hermes.c
+++ /dev/null
@@ -1,778 +0,0 @@
-/* hermes.c
- *
- * Driver core for the "Hermes" wireless MAC controller, as used in
- * the Lucent Orinoco and Cabletron RoamAbout cards. It should also
- * work on the hfa3841 and hfa3842 MAC controller chips used in the
- * Prism II chipsets.
- *
- * This is not a complete driver, just low-level access routines for
- * the MAC controller itself.
- *
- * Based on the prism2 driver from Absolute Value Systems' linux-wlan
- * project, the Linux wvlan_cs driver, Lucent's HCF-Light
- * (wvlan_hcf.c) library, and the NetBSD wireless driver (in no
- * particular order).
- *
- * Copyright (C) 2000, David Gibson, Linuxcare Australia.
- * (C) Copyright David Gibson, IBM Corp. 2001-2003.
- *
- * The contents of this file are subject to the Mozilla Public License
- * Version 1.1 (the "License"); you may not use this file except in
- * compliance with the License. You may obtain a copy of the License
- * at http://www.mozilla.org/MPL/
- *
- * Software distributed under the License is distributed on an "AS IS"
- * basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See
- * the License for the specific language governing rights and
- * limitations under the License.
- *
- * Alternatively, the contents of this file may be used under the
- * terms of the GNU General Public License version 2 (the "GPL"), in
- * which case the provisions of the GPL are applicable instead of the
- * above.  If you wish to allow the use of your version of this file
- * only under the terms of the GPL and not to allow others to use your
- * version of this file under the MPL, indicate your decision by
- * deleting the provisions above and replace them with the notice and
- * other provisions required by the GPL.  If you do not delete the
- * provisions above, a recipient may use your version of this file
- * under either the MPL or the GPL.
- */
-
-#include <linux/net.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/delay.h>
-
-#include "hermes.h"
-
-/* These are maximum timeouts. Most often, card wil react much faster */
-#define CMD_BUSY_TIMEOUT (100) /* In iterations of ~1us */
-#define CMD_INIT_TIMEOUT (50000) /* in iterations of ~10us */
-#define CMD_COMPL_TIMEOUT (20000) /* in iterations of ~10us */
-#define ALLOC_COMPL_TIMEOUT (1000) /* in iterations of ~10us */
-
-/*
- * AUX port access.  To unlock the AUX port write the access keys to the
- * PARAM0-2 registers, then write HERMES_AUX_ENABLE to the HERMES_CONTROL
- * register.  Then read it and make sure it's HERMES_AUX_ENABLED.
- */
-#define HERMES_AUX_ENABLE	0x8000	/* Enable auxiliary port access */
-#define HERMES_AUX_DISABLE	0x4000	/* Disable to auxiliary port access */
-#define HERMES_AUX_ENABLED	0xC000	/* Auxiliary port is open */
-#define HERMES_AUX_DISABLED	0x0000	/* Auxiliary port is closed */
-
-#define HERMES_AUX_PW0	0xFE01
-#define HERMES_AUX_PW1	0xDC23
-#define HERMES_AUX_PW2	0xBA45
-
-/* HERMES_CMD_DOWNLD */
-#define HERMES_PROGRAM_DISABLE             (0x0000 | HERMES_CMD_DOWNLD)
-#define HERMES_PROGRAM_ENABLE_VOLATILE     (0x0100 | HERMES_CMD_DOWNLD)
-#define HERMES_PROGRAM_ENABLE_NON_VOLATILE (0x0200 | HERMES_CMD_DOWNLD)
-#define HERMES_PROGRAM_NON_VOLATILE        (0x0300 | HERMES_CMD_DOWNLD)
-
-/*
- * Debugging helpers
- */
-
-#define DMSG(stuff...) do {printk(KERN_DEBUG "hermes @ %p: " , hw->iobase); \
-			printk(stuff); } while (0)
-
-#undef HERMES_DEBUG
-#ifdef HERMES_DEBUG
-
-#define DEBUG(lvl, stuff...) if ((lvl) <= HERMES_DEBUG) DMSG(stuff)
-
-#else /* ! HERMES_DEBUG */
-
-#define DEBUG(lvl, stuff...) do { } while (0)
-
-#endif /* ! HERMES_DEBUG */
-
-static const struct hermes_ops hermes_ops_local;
-
-/*
- * Internal functions
- */
-
-/* Issue a command to the chip. Waiting for it to complete is the caller's
-   problem.
-
-   Returns -EBUSY if the command register is busy, 0 on success.
-
-   Callable from any context.
-*/
-static int hermes_issue_cmd(struct hermes *hw, u16 cmd, u16 param0,
-			    u16 param1, u16 param2)
-{
-	int k = CMD_BUSY_TIMEOUT;
-	u16 reg;
-
-	/* First wait for the command register to unbusy */
-	reg = hermes_read_regn(hw, CMD);
-	while ((reg & HERMES_CMD_BUSY) && k) {
-		k--;
-		udelay(1);
-		reg = hermes_read_regn(hw, CMD);
-	}
-	if (reg & HERMES_CMD_BUSY)
-		return -EBUSY;
-
-	hermes_write_regn(hw, PARAM2, param2);
-	hermes_write_regn(hw, PARAM1, param1);
-	hermes_write_regn(hw, PARAM0, param0);
-	hermes_write_regn(hw, CMD, cmd);
-
-	return 0;
-}
-
-/*
- * Function definitions
- */
-
-/* For doing cmds that wipe the magic constant in SWSUPPORT0 */
-static int hermes_doicmd_wait(struct hermes *hw, u16 cmd,
-			      u16 parm0, u16 parm1, u16 parm2,
-			      struct hermes_response *resp)
-{
-	int err = 0;
-	int k;
-	u16 status, reg;
-
-	err = hermes_issue_cmd(hw, cmd, parm0, parm1, parm2);
-	if (err)
-		return err;
-
-	reg = hermes_read_regn(hw, EVSTAT);
-	k = CMD_INIT_TIMEOUT;
-	while ((!(reg & HERMES_EV_CMD)) && k) {
-		k--;
-		udelay(10);
-		reg = hermes_read_regn(hw, EVSTAT);
-	}
-
-	hermes_write_regn(hw, SWSUPPORT0, HERMES_MAGIC);
-
-	if (!hermes_present(hw)) {
-		DEBUG(0, "hermes @ 0x%x: Card removed during reset.\n",
-		       hw->iobase);
-		err = -ENODEV;
-		goto out;
-	}
-
-	if (!(reg & HERMES_EV_CMD)) {
-		printk(KERN_ERR "hermes @ %p: "
-		       "Timeout waiting for card to reset (reg=0x%04x)!\n",
-		       hw->iobase, reg);
-		err = -ETIMEDOUT;
-		goto out;
-	}
-
-	status = hermes_read_regn(hw, STATUS);
-	if (resp) {
-		resp->status = status;
-		resp->resp0 = hermes_read_regn(hw, RESP0);
-		resp->resp1 = hermes_read_regn(hw, RESP1);
-		resp->resp2 = hermes_read_regn(hw, RESP2);
-	}
-
-	hermes_write_regn(hw, EVACK, HERMES_EV_CMD);
-
-	if (status & HERMES_STATUS_RESULT)
-		err = -EIO;
-out:
-	return err;
-}
-
-void hermes_struct_init(struct hermes *hw, void __iomem *address,
-			int reg_spacing)
-{
-	hw->iobase = address;
-	hw->reg_spacing = reg_spacing;
-	hw->inten = 0x0;
-	hw->eeprom_pda = false;
-	hw->ops = &hermes_ops_local;
-}
-EXPORT_SYMBOL(hermes_struct_init);
-
-static int hermes_init(struct hermes *hw)
-{
-	u16 reg;
-	int err = 0;
-	int k;
-
-	/* We don't want to be interrupted while resetting the chipset */
-	hw->inten = 0x0;
-	hermes_write_regn(hw, INTEN, 0);
-	hermes_write_regn(hw, EVACK, 0xffff);
-
-	/* Normally it's a "can't happen" for the command register to
-	   be busy when we go to issue a command because we are
-	   serializing all commands.  However we want to have some
-	   chance of resetting the card even if it gets into a stupid
-	   state, so we actually wait to see if the command register
-	   will unbusy itself here. */
-	k = CMD_BUSY_TIMEOUT;
-	reg = hermes_read_regn(hw, CMD);
-	while (k && (reg & HERMES_CMD_BUSY)) {
-		if (reg == 0xffff) /* Special case - the card has probably been
-				      removed, so don't wait for the timeout */
-			return -ENODEV;
-
-		k--;
-		udelay(1);
-		reg = hermes_read_regn(hw, CMD);
-	}
-
-	/* No need to explicitly handle the timeout - if we've timed
-	   out hermes_issue_cmd() will probably return -EBUSY below */
-
-	/* According to the documentation, EVSTAT may contain
-	   obsolete event occurrence information.  We have to acknowledge
-	   it by writing EVACK. */
-	reg = hermes_read_regn(hw, EVSTAT);
-	hermes_write_regn(hw, EVACK, reg);
-
-	/* We don't use hermes_docmd_wait here, because the reset wipes
-	   the magic constant in SWSUPPORT0 away, and it gets confused */
-	err = hermes_doicmd_wait(hw, HERMES_CMD_INIT, 0, 0, 0, NULL);
-
-	return err;
-}
-
-/* Issue a command to the chip, and (busy!) wait for it to
- * complete.
- *
- * Returns:
- *     < 0 on internal error
- *       0 on success
- *     > 0 on error returned by the firmware
- *
- * Callable from any context, but locking is your problem. */
-static int hermes_docmd_wait(struct hermes *hw, u16 cmd, u16 parm0,
-			     struct hermes_response *resp)
-{
-	int err;
-	int k;
-	u16 reg;
-	u16 status;
-
-	err = hermes_issue_cmd(hw, cmd, parm0, 0, 0);
-	if (err) {
-		if (!hermes_present(hw)) {
-			if (net_ratelimit())
-				printk(KERN_WARNING "hermes @ %p: "
-				       "Card removed while issuing command "
-				       "0x%04x.\n", hw->iobase, cmd);
-			err = -ENODEV;
-		} else
-			if (net_ratelimit())
-				printk(KERN_ERR "hermes @ %p: "
-				       "Error %d issuing command 0x%04x.\n",
-				       hw->iobase, err, cmd);
-		goto out;
-	}
-
-	reg = hermes_read_regn(hw, EVSTAT);
-	k = CMD_COMPL_TIMEOUT;
-	while ((!(reg & HERMES_EV_CMD)) && k) {
-		k--;
-		udelay(10);
-		reg = hermes_read_regn(hw, EVSTAT);
-	}
-
-	if (!hermes_present(hw)) {
-		printk(KERN_WARNING "hermes @ %p: Card removed "
-		       "while waiting for command 0x%04x completion.\n",
-		       hw->iobase, cmd);
-		err = -ENODEV;
-		goto out;
-	}
-
-	if (!(reg & HERMES_EV_CMD)) {
-		printk(KERN_ERR "hermes @ %p: Timeout waiting for "
-		       "command 0x%04x completion.\n", hw->iobase, cmd);
-		err = -ETIMEDOUT;
-		goto out;
-	}
-
-	status = hermes_read_regn(hw, STATUS);
-	if (resp) {
-		resp->status = status;
-		resp->resp0 = hermes_read_regn(hw, RESP0);
-		resp->resp1 = hermes_read_regn(hw, RESP1);
-		resp->resp2 = hermes_read_regn(hw, RESP2);
-	}
-
-	hermes_write_regn(hw, EVACK, HERMES_EV_CMD);
-
-	if (status & HERMES_STATUS_RESULT)
-		err = -EIO;
-
- out:
-	return err;
-}
-
-static int hermes_allocate(struct hermes *hw, u16 size, u16 *fid)
-{
-	int err = 0;
-	int k;
-	u16 reg;
-
-	if ((size < HERMES_ALLOC_LEN_MIN) || (size > HERMES_ALLOC_LEN_MAX))
-		return -EINVAL;
-
-	err = hermes_docmd_wait(hw, HERMES_CMD_ALLOC, size, NULL);
-	if (err)
-		return err;
-
-	reg = hermes_read_regn(hw, EVSTAT);
-	k = ALLOC_COMPL_TIMEOUT;
-	while ((!(reg & HERMES_EV_ALLOC)) && k) {
-		k--;
-		udelay(10);
-		reg = hermes_read_regn(hw, EVSTAT);
-	}
-
-	if (!hermes_present(hw)) {
-		printk(KERN_WARNING "hermes @ %p: "
-		       "Card removed waiting for frame allocation.\n",
-		       hw->iobase);
-		return -ENODEV;
-	}
-
-	if (!(reg & HERMES_EV_ALLOC)) {
-		printk(KERN_ERR "hermes @ %p: "
-		       "Timeout waiting for frame allocation\n",
-		       hw->iobase);
-		return -ETIMEDOUT;
-	}
-
-	*fid = hermes_read_regn(hw, ALLOCFID);
-	hermes_write_regn(hw, EVACK, HERMES_EV_ALLOC);
-
-	return 0;
-}
-
-/* Set up a BAP to read a particular chunk of data from card's internal buffer.
- *
- * Returns:
- *     < 0 on internal failure (errno)
- *       0 on success
- *     > 0 on error
- * from firmware
- *
- * Callable from any context */
-static int hermes_bap_seek(struct hermes *hw, int bap, u16 id, u16 offset)
-{
-	int sreg = bap ? HERMES_SELECT1 : HERMES_SELECT0;
-	int oreg = bap ? HERMES_OFFSET1 : HERMES_OFFSET0;
-	int k;
-	u16 reg;
-
-	/* Paranoia.. */
-	if ((offset > HERMES_BAP_OFFSET_MAX) || (offset % 2))
-		return -EINVAL;
-
-	k = HERMES_BAP_BUSY_TIMEOUT;
-	reg = hermes_read_reg(hw, oreg);
-	while ((reg & HERMES_OFFSET_BUSY) && k) {
-		k--;
-		udelay(1);
-		reg = hermes_read_reg(hw, oreg);
-	}
-
-	if (reg & HERMES_OFFSET_BUSY)
-		return -ETIMEDOUT;
-
-	/* Now we actually set up the transfer */
-	hermes_write_reg(hw, sreg, id);
-	hermes_write_reg(hw, oreg, offset);
-
-	/* Wait for the BAP to be ready */
-	k = HERMES_BAP_BUSY_TIMEOUT;
-	reg = hermes_read_reg(hw, oreg);
-	while ((reg & (HERMES_OFFSET_BUSY | HERMES_OFFSET_ERR)) && k) {
-		k--;
-		udelay(1);
-		reg = hermes_read_reg(hw, oreg);
-	}
-
-	if (reg != offset) {
-		printk(KERN_ERR "hermes @ %p: BAP%d offset %s: "
-		       "reg=0x%x id=0x%x offset=0x%x\n", hw->iobase, bap,
-		       (reg & HERMES_OFFSET_BUSY) ? "timeout" : "error",
-		       reg, id, offset);
-
-		if (reg & HERMES_OFFSET_BUSY)
-			return -ETIMEDOUT;
-
-		return -EIO;		/* error or wrong offset */
-	}
-
-	return 0;
-}
-
-/* Read a block of data from the chip's buffer, via the
- * BAP. Synchronization/serialization is the caller's problem.  len
- * must be even.
- *
- * Returns:
- *     < 0 on internal failure (errno)
- *       0 on success
- *     > 0 on error from firmware
- */
-static int hermes_bap_pread(struct hermes *hw, int bap, void *buf, int len,
-			    u16 id, u16 offset)
-{
-	int dreg = bap ? HERMES_DATA1 : HERMES_DATA0;
-	int err = 0;
-
-	if ((len < 0) || (len % 2))
-		return -EINVAL;
-
-	err = hermes_bap_seek(hw, bap, id, offset);
-	if (err)
-		goto out;
-
-	/* Actually do the transfer */
-	hermes_read_words(hw, dreg, buf, len / 2);
-
- out:
-	return err;
-}
-
-/* Write a block of data to the chip's buffer, via the
- * BAP. Synchronization/serialization is the caller's problem.
- *
- * Returns:
- *     < 0 on internal failure (errno)
- *       0 on success
- *     > 0 on error from firmware
- */
-static int hermes_bap_pwrite(struct hermes *hw, int bap, const void *buf,
-			     int len, u16 id, u16 offset)
-{
-	int dreg = bap ? HERMES_DATA1 : HERMES_DATA0;
-	int err = 0;
-
-	if (len < 0)
-		return -EINVAL;
-
-	err = hermes_bap_seek(hw, bap, id, offset);
-	if (err)
-		goto out;
-
-	/* Actually do the transfer */
-	hermes_write_bytes(hw, dreg, buf, len);
-
- out:
-	return err;
-}
-
-/* Read a Length-Type-Value record from the card.
- *
- * If length is NULL, we ignore the length read from the card, and
- * read the entire buffer regardless. This is useful because some of
- * the configuration records appear to have incorrect lengths in
- * practice.
- *
- * Callable from user or bh context.  */
-static int hermes_read_ltv(struct hermes *hw, int bap, u16 rid,
-			   unsigned bufsize, u16 *length, void *buf)
-{
-	int err = 0;
-	int dreg = bap ? HERMES_DATA1 : HERMES_DATA0;
-	u16 rlength, rtype;
-	unsigned nwords;
-
-	if (bufsize % 2)
-		return -EINVAL;
-
-	err = hermes_docmd_wait(hw, HERMES_CMD_ACCESS, rid, NULL);
-	if (err)
-		return err;
-
-	err = hermes_bap_seek(hw, bap, rid, 0);
-	if (err)
-		return err;
-
-	rlength = hermes_read_reg(hw, dreg);
-
-	if (!rlength)
-		return -ENODATA;
-
-	rtype = hermes_read_reg(hw, dreg);
-
-	if (length)
-		*length = rlength;
-
-	if (rtype != rid)
-		printk(KERN_WARNING "hermes @ %p: %s(): "
-		       "rid (0x%04x) does not match type (0x%04x)\n",
-		       hw->iobase, __func__, rid, rtype);
-	if (HERMES_RECLEN_TO_BYTES(rlength) > bufsize)
-		printk(KERN_WARNING "hermes @ %p: "
-		       "Truncating LTV record from %d to %d bytes. "
-		       "(rid=0x%04x, len=0x%04x)\n", hw->iobase,
-		       HERMES_RECLEN_TO_BYTES(rlength), bufsize, rid, rlength);
-
-	nwords = min((unsigned)rlength - 1, bufsize / 2);
-	hermes_read_words(hw, dreg, buf, nwords);
-
-	return 0;
-}
-
-static int hermes_write_ltv(struct hermes *hw, int bap, u16 rid,
-			    u16 length, const void *value)
-{
-	int dreg = bap ? HERMES_DATA1 : HERMES_DATA0;
-	int err = 0;
-	unsigned count;
-
-	if (length == 0)
-		return -EINVAL;
-
-	err = hermes_bap_seek(hw, bap, rid, 0);
-	if (err)
-		return err;
-
-	hermes_write_reg(hw, dreg, length);
-	hermes_write_reg(hw, dreg, rid);
-
-	count = length - 1;
-
-	hermes_write_bytes(hw, dreg, value, count << 1);
-
-	err = hermes_docmd_wait(hw, HERMES_CMD_ACCESS | HERMES_CMD_WRITE,
-				rid, NULL);
-
-	return err;
-}
-
-/*** Hermes AUX control ***/
-
-static inline void
-hermes_aux_setaddr(struct hermes *hw, u32 addr)
-{
-	hermes_write_reg(hw, HERMES_AUXPAGE, (u16) (addr >> 7));
-	hermes_write_reg(hw, HERMES_AUXOFFSET, (u16) (addr & 0x7F));
-}
-
-static inline int
-hermes_aux_control(struct hermes *hw, int enabled)
-{
-	int desired_state = enabled ? HERMES_AUX_ENABLED : HERMES_AUX_DISABLED;
-	int action = enabled ? HERMES_AUX_ENABLE : HERMES_AUX_DISABLE;
-	int i;
-
-	/* Already open? */
-	if (hermes_read_reg(hw, HERMES_CONTROL) == desired_state)
-		return 0;
-
-	hermes_write_reg(hw, HERMES_PARAM0, HERMES_AUX_PW0);
-	hermes_write_reg(hw, HERMES_PARAM1, HERMES_AUX_PW1);
-	hermes_write_reg(hw, HERMES_PARAM2, HERMES_AUX_PW2);
-	hermes_write_reg(hw, HERMES_CONTROL, action);
-
-	for (i = 0; i < 20; i++) {
-		udelay(10);
-		if (hermes_read_reg(hw, HERMES_CONTROL) ==
-		    desired_state)
-			return 0;
-	}
-
-	return -EBUSY;
-}
-
-/*** Hermes programming ***/
-
-/* About to start programming data (Hermes I)
- * offset is the entry point
- *
- * Spectrum_cs' Symbol fw does not require this
- * wl_lkm Agere fw does
- * Don't know about intersil
- */
-static int hermesi_program_init(struct hermes *hw, u32 offset)
-{
-	int err;
-
-	/* Disable interrupts?*/
-	/*hw->inten = 0x0;*/
-	/*hermes_write_regn(hw, INTEN, 0);*/
-	/*hermes_set_irqmask(hw, 0);*/
-
-	/* Acknowledge any outstanding command */
-	hermes_write_regn(hw, EVACK, 0xFFFF);
-
-	/* Using init_cmd_wait rather than cmd_wait */
-	err = hw->ops->init_cmd_wait(hw,
-				     0x0100 | HERMES_CMD_INIT,
-				     0, 0, 0, NULL);
-	if (err)
-		return err;
-
-	err = hw->ops->init_cmd_wait(hw,
-				     0x0000 | HERMES_CMD_INIT,
-				     0, 0, 0, NULL);
-	if (err)
-		return err;
-
-	err = hermes_aux_control(hw, 1);
-	pr_debug("AUX enable returned %d\n", err);
-
-	if (err)
-		return err;
-
-	pr_debug("Enabling volatile, EP 0x%08x\n", offset);
-	err = hw->ops->init_cmd_wait(hw,
-				     HERMES_PROGRAM_ENABLE_VOLATILE,
-				     offset & 0xFFFFu,
-				     offset >> 16,
-				     0,
-				     NULL);
-	pr_debug("PROGRAM_ENABLE returned %d\n", err);
-
-	return err;
-}
-
-/* Done programming data (Hermes I)
- *
- * Spectrum_cs' Symbol fw does not require this
- * wl_lkm Agere fw does
- * Don't know about intersil
- */
-static int hermesi_program_end(struct hermes *hw)
-{
-	struct hermes_response resp;
-	int rc = 0;
-	int err;
-
-	rc = hw->ops->cmd_wait(hw, HERMES_PROGRAM_DISABLE, 0, &resp);
-
-	pr_debug("PROGRAM_DISABLE returned %d, "
-		 "r0 0x%04x, r1 0x%04x, r2 0x%04x\n",
-		 rc, resp.resp0, resp.resp1, resp.resp2);
-
-	if ((rc == 0) &&
-	    ((resp.status & HERMES_STATUS_CMDCODE) != HERMES_CMD_DOWNLD))
-		rc = -EIO;
-
-	err = hermes_aux_control(hw, 0);
-	pr_debug("AUX disable returned %d\n", err);
-
-	/* Acknowledge any outstanding command */
-	hermes_write_regn(hw, EVACK, 0xFFFF);
-
-	/* Reinitialise, ignoring return */
-	(void) hw->ops->init_cmd_wait(hw, 0x0000 | HERMES_CMD_INIT,
-				      0, 0, 0, NULL);
-
-	return rc ? rc : err;
-}
-
-static int hermes_program_bytes(struct hermes *hw, const char *data,
-				u32 addr, u32 len)
-{
-	/* wl lkm splits the programming into chunks of 2000 bytes.
-	 * This restriction appears to come from USB. The PCMCIA
-	 * adapters can program the whole lot in one go */
-	hermes_aux_setaddr(hw, addr);
-	hermes_write_bytes(hw, HERMES_AUXDATA, data, len);
-	return 0;
-}
-
-/* Read PDA from the adapter */
-static int hermes_read_pda(struct hermes *hw, __le16 *pda, u32 pda_addr,
-			   u16 pda_len)
-{
-	int ret;
-	u16 pda_size;
-	u16 data_len = pda_len;
-	__le16 *data = pda;
-
-	if (hw->eeprom_pda) {
-		/* PDA of spectrum symbol is in eeprom */
-
-		/* Issue command to read EEPROM */
-		ret = hw->ops->cmd_wait(hw, HERMES_CMD_READMIF, 0, NULL);
-		if (ret)
-			return ret;
-	} else {
-		/* wl_lkm does not include PDA size in the PDA area.
-		 * We will pad the information into pda, so other routines
-		 * don't have to be modified */
-		pda[0] = cpu_to_le16(pda_len - 2);
-			/* Includes CFG_PROD_DATA but not itself */
-		pda[1] = cpu_to_le16(0x0800); /* CFG_PROD_DATA */
-		data_len = pda_len - 4;
-		data = pda + 2;
-	}
-
-	/* Open auxiliary port */
-	ret = hermes_aux_control(hw, 1);
-	pr_debug("AUX enable returned %d\n", ret);
-	if (ret)
-		return ret;
-
-	/* Read PDA */
-	hermes_aux_setaddr(hw, pda_addr);
-	hermes_read_words(hw, HERMES_AUXDATA, data, data_len / 2);
-
-	/* Close aux port */
-	ret = hermes_aux_control(hw, 0);
-	pr_debug("AUX disable returned %d\n", ret);
-
-	/* Check PDA length */
-	pda_size = le16_to_cpu(pda[0]);
-	pr_debug("Actual PDA length %d, Max allowed %d\n",
-		 pda_size, pda_len);
-	if (pda_size > pda_len)
-		return -EINVAL;
-
-	return 0;
-}
-
-static void hermes_lock_irqsave(spinlock_t *lock,
-				unsigned long *flags) __acquires(lock)
-{
-	spin_lock_irqsave(lock, *flags);
-}
-
-static void hermes_unlock_irqrestore(spinlock_t *lock,
-				     unsigned long *flags) __releases(lock)
-{
-	spin_unlock_irqrestore(lock, *flags);
-}
-
-static void hermes_lock_irq(spinlock_t *lock) __acquires(lock)
-{
-	spin_lock_irq(lock);
-}
-
-static void hermes_unlock_irq(spinlock_t *lock) __releases(lock)
-{
-	spin_unlock_irq(lock);
-}
-
-/* Hermes operations for local buses */
-static const struct hermes_ops hermes_ops_local = {
-	.init = hermes_init,
-	.cmd_wait = hermes_docmd_wait,
-	.init_cmd_wait = hermes_doicmd_wait,
-	.allocate = hermes_allocate,
-	.read_ltv = hermes_read_ltv,
-	.read_ltv_pr = hermes_read_ltv,
-	.write_ltv = hermes_write_ltv,
-	.bap_pread = hermes_bap_pread,
-	.bap_pwrite = hermes_bap_pwrite,
-	.read_pda = hermes_read_pda,
-	.program_init = hermesi_program_init,
-	.program_end = hermesi_program_end,
-	.program = hermes_program_bytes,
-	.lock_irqsave = hermes_lock_irqsave,
-	.unlock_irqrestore = hermes_unlock_irqrestore,
-	.lock_irq = hermes_lock_irq,
-	.unlock_irq = hermes_unlock_irq,
-};
diff --git a/drivers/net/wireless/intersil/orinoco/hermes.h b/drivers/net/wireless/intersil/orinoco/hermes.h
deleted file mode 100644
index 3dc561a5cb7a..000000000000
--- a/drivers/net/wireless/intersil/orinoco/hermes.h
+++ /dev/null
@@ -1,534 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/* hermes.h
- *
- * Driver core for the "Hermes" wireless MAC controller, as used in
- * the Lucent Orinoco and Cabletron RoamAbout cards. It should also
- * work on the hfa3841 and hfa3842 MAC controller chips used in the
- * Prism I & II chipsets.
- *
- * This is not a complete driver, just low-level access routines for
- * the MAC controller itself.
- *
- * Based on the prism2 driver from Absolute Value Systems' linux-wlan
- * project, the Linux wvlan_cs driver, Lucent's HCF-Light
- * (wvlan_hcf.c) library, and the NetBSD wireless driver.
- *
- * Copyright (C) 2000, David Gibson, Linuxcare Australia.
- * (C) Copyright David Gibson, IBM Corp. 2001-2003.
- *
- * Portions taken from hfa384x.h.
- * Copyright (C) 1999 AbsoluteValue Systems, Inc. All Rights Reserved.
- */
-
-#ifndef _HERMES_H
-#define _HERMES_H
-
-/* Notes on locking:
- *
- * As a module of low level hardware access routines, there is no
- * locking. Users of this module should ensure that they serialize
- * access to the hermes structure, and to the hardware
-*/
-
-#include <linux/if_ether.h>
-#include <linux/io.h>
-
-/*
- * Limits and constants
- */
-#define		HERMES_ALLOC_LEN_MIN		(4)
-#define		HERMES_ALLOC_LEN_MAX		(2400)
-#define		HERMES_LTV_LEN_MAX		(34)
-#define		HERMES_BAP_DATALEN_MAX		(4096)
-#define		HERMES_BAP_OFFSET_MAX		(4096)
-#define		HERMES_PORTID_MAX		(7)
-#define		HERMES_NUMPORTS_MAX		(HERMES_PORTID_MAX + 1)
-#define		HERMES_PDR_LEN_MAX		(260)	/* in bytes, from EK */
-#define		HERMES_PDA_RECS_MAX		(200)	/* a guess */
-#define		HERMES_PDA_LEN_MAX		(1024)	/* in bytes, from EK */
-#define		HERMES_SCANRESULT_MAX		(35)
-#define		HERMES_CHINFORESULT_MAX		(8)
-#define		HERMES_MAX_MULTICAST		(16)
-#define		HERMES_MAGIC			(0x7d1f)
-
-/*
- * Hermes register offsets
- */
-#define		HERMES_CMD			(0x00)
-#define		HERMES_PARAM0			(0x02)
-#define		HERMES_PARAM1			(0x04)
-#define		HERMES_PARAM2			(0x06)
-#define		HERMES_STATUS			(0x08)
-#define		HERMES_RESP0			(0x0A)
-#define		HERMES_RESP1			(0x0C)
-#define		HERMES_RESP2			(0x0E)
-#define		HERMES_INFOFID			(0x10)
-#define		HERMES_RXFID			(0x20)
-#define		HERMES_ALLOCFID			(0x22)
-#define		HERMES_TXCOMPLFID		(0x24)
-#define		HERMES_SELECT0			(0x18)
-#define		HERMES_OFFSET0			(0x1C)
-#define		HERMES_DATA0			(0x36)
-#define		HERMES_SELECT1			(0x1A)
-#define		HERMES_OFFSET1			(0x1E)
-#define		HERMES_DATA1			(0x38)
-#define		HERMES_EVSTAT			(0x30)
-#define		HERMES_INTEN			(0x32)
-#define		HERMES_EVACK			(0x34)
-#define		HERMES_CONTROL			(0x14)
-#define		HERMES_SWSUPPORT0		(0x28)
-#define		HERMES_SWSUPPORT1		(0x2A)
-#define		HERMES_SWSUPPORT2		(0x2C)
-#define		HERMES_AUXPAGE			(0x3A)
-#define		HERMES_AUXOFFSET		(0x3C)
-#define		HERMES_AUXDATA			(0x3E)
-
-/*
- * CMD register bitmasks
- */
-#define		HERMES_CMD_BUSY			(0x8000)
-#define		HERMES_CMD_AINFO		(0x7f00)
-#define		HERMES_CMD_MACPORT		(0x0700)
-#define		HERMES_CMD_RECL			(0x0100)
-#define		HERMES_CMD_WRITE		(0x0100)
-#define		HERMES_CMD_PROGMODE		(0x0300)
-#define		HERMES_CMD_CMDCODE		(0x003f)
-
-/*
- * STATUS register bitmasks
- */
-#define		HERMES_STATUS_RESULT		(0x7f00)
-#define		HERMES_STATUS_CMDCODE		(0x003f)
-
-/*
- * OFFSET register bitmasks
- */
-#define		HERMES_OFFSET_BUSY		(0x8000)
-#define		HERMES_OFFSET_ERR		(0x4000)
-#define		HERMES_OFFSET_DATAOFF		(0x0ffe)
-
-/*
- * Event register bitmasks (INTEN, EVSTAT, EVACK)
- */
-#define		HERMES_EV_TICK			(0x8000)
-#define		HERMES_EV_WTERR			(0x4000)
-#define		HERMES_EV_INFDROP		(0x2000)
-#define		HERMES_EV_INFO			(0x0080)
-#define		HERMES_EV_DTIM			(0x0020)
-#define		HERMES_EV_CMD			(0x0010)
-#define		HERMES_EV_ALLOC			(0x0008)
-#define		HERMES_EV_TXEXC			(0x0004)
-#define		HERMES_EV_TX			(0x0002)
-#define		HERMES_EV_RX			(0x0001)
-
-/*
- * Command codes
- */
-/*--- Controller Commands ----------------------------*/
-#define		HERMES_CMD_INIT			(0x0000)
-#define		HERMES_CMD_ENABLE		(0x0001)
-#define		HERMES_CMD_DISABLE		(0x0002)
-#define		HERMES_CMD_DIAG			(0x0003)
-
-/*--- Buffer Mgmt Commands ---------------------------*/
-#define		HERMES_CMD_ALLOC		(0x000A)
-#define		HERMES_CMD_TX			(0x000B)
-
-/*--- Regulate Commands ------------------------------*/
-#define		HERMES_CMD_NOTIFY		(0x0010)
-#define		HERMES_CMD_INQUIRE		(0x0011)
-
-/*--- Configure Commands -----------------------------*/
-#define		HERMES_CMD_ACCESS		(0x0021)
-#define		HERMES_CMD_DOWNLD		(0x0022)
-
-/*--- Serial I/O Commands ----------------------------*/
-#define		HERMES_CMD_READMIF		(0x0030)
-#define		HERMES_CMD_WRITEMIF		(0x0031)
-
-/*--- Debugging Commands -----------------------------*/
-#define		HERMES_CMD_TEST			(0x0038)
-
-
-/* Test command arguments */
-#define		HERMES_TEST_SET_CHANNEL		0x0800
-#define		HERMES_TEST_MONITOR		0x0b00
-#define		HERMES_TEST_STOP		0x0f00
-
-/* Authentication algorithms */
-#define		HERMES_AUTH_OPEN		1
-#define		HERMES_AUTH_SHARED_KEY		2
-
-/* WEP settings */
-#define		HERMES_WEP_PRIVACY_INVOKED	0x0001
-#define		HERMES_WEP_EXCL_UNENCRYPTED	0x0002
-#define		HERMES_WEP_HOST_ENCRYPT		0x0010
-#define		HERMES_WEP_HOST_DECRYPT		0x0080
-
-/* Symbol hostscan options */
-#define		HERMES_HOSTSCAN_SYMBOL_5SEC	0x0001
-#define		HERMES_HOSTSCAN_SYMBOL_ONCE	0x0002
-#define		HERMES_HOSTSCAN_SYMBOL_PASSIVE	0x0040
-#define		HERMES_HOSTSCAN_SYMBOL_BCAST	0x0080
-
-/*
- * Frame structures and constants
- */
-
-#define HERMES_DESCRIPTOR_OFFSET	0
-#define HERMES_802_11_OFFSET		(14)
-#define HERMES_802_3_OFFSET		(14 + 32)
-#define HERMES_802_2_OFFSET		(14 + 32 + 14)
-#define HERMES_TXCNTL2_OFFSET		(HERMES_802_3_OFFSET - 2)
-
-#define HERMES_RXSTAT_ERR		(0x0003)
-#define	HERMES_RXSTAT_BADCRC		(0x0001)
-#define	HERMES_RXSTAT_UNDECRYPTABLE	(0x0002)
-#define	HERMES_RXSTAT_MIC		(0x0010)	/* Frame contains MIC */
-#define	HERMES_RXSTAT_MACPORT		(0x0700)
-#define HERMES_RXSTAT_PCF		(0x1000)	/* Frame was received in CF period */
-#define	HERMES_RXSTAT_MIC_KEY_ID	(0x1800)	/* MIC key used */
-#define	HERMES_RXSTAT_MSGTYPE		(0xE000)
-#define	HERMES_RXSTAT_1042		(0x2000)	/* RFC-1042 frame */
-#define	HERMES_RXSTAT_TUNNEL		(0x4000)	/* bridge-tunnel encoded frame */
-#define	HERMES_RXSTAT_WMP		(0x6000)	/* Wavelan-II Management Protocol frame */
-
-/* Shift amount for key ID in RXSTAT and TXCTRL */
-#define	HERMES_MIC_KEY_ID_SHIFT		11
-
-struct hermes_tx_descriptor {
-	__le16 status;
-	__le16 reserved1;
-	__le16 reserved2;
-	__le32 sw_support;
-	u8 retry_count;
-	u8 tx_rate;
-	__le16 tx_control;
-} __packed;
-
-#define HERMES_TXSTAT_RETRYERR		(0x0001)
-#define HERMES_TXSTAT_AGEDERR		(0x0002)
-#define HERMES_TXSTAT_DISCON		(0x0004)
-#define HERMES_TXSTAT_FORMERR		(0x0008)
-
-#define HERMES_TXCTRL_TX_OK		(0x0002)	/* ?? interrupt on Tx complete */
-#define HERMES_TXCTRL_TX_EX		(0x0004)	/* ?? interrupt on Tx exception */
-#define HERMES_TXCTRL_802_11		(0x0008)	/* We supply 802.11 header */
-#define HERMES_TXCTRL_MIC		(0x0010)	/* 802.3 + TKIP */
-#define HERMES_TXCTRL_MIC_KEY_ID	(0x1800)	/* MIC Key ID mask */
-#define HERMES_TXCTRL_ALT_RTRY		(0x0020)
-
-/* Inquiry constants and data types */
-
-#define HERMES_INQ_TALLIES		(0xF100)
-#define HERMES_INQ_SCAN			(0xF101)
-#define HERMES_INQ_CHANNELINFO		(0xF102)
-#define HERMES_INQ_HOSTSCAN		(0xF103)
-#define HERMES_INQ_HOSTSCAN_SYMBOL	(0xF104)
-#define HERMES_INQ_LINKSTATUS		(0xF200)
-#define HERMES_INQ_SEC_STAT_AGERE	(0xF202)
-
-struct hermes_tallies_frame {
-	__le16 TxUnicastFrames;
-	__le16 TxMulticastFrames;
-	__le16 TxFragments;
-	__le16 TxUnicastOctets;
-	__le16 TxMulticastOctets;
-	__le16 TxDeferredTransmissions;
-	__le16 TxSingleRetryFrames;
-	__le16 TxMultipleRetryFrames;
-	__le16 TxRetryLimitExceeded;
-	__le16 TxDiscards;
-	__le16 RxUnicastFrames;
-	__le16 RxMulticastFrames;
-	__le16 RxFragments;
-	__le16 RxUnicastOctets;
-	__le16 RxMulticastOctets;
-	__le16 RxFCSErrors;
-	__le16 RxDiscards_NoBuffer;
-	__le16 TxDiscardsWrongSA;
-	__le16 RxWEPUndecryptable;
-	__le16 RxMsgInMsgFragments;
-	__le16 RxMsgInBadMsgFragments;
-	/* Those last are probably not available in very old firmwares */
-	__le16 RxDiscards_WEPICVError;
-	__le16 RxDiscards_WEPExcluded;
-} __packed;
-
-/* Grabbed from wlan-ng - Thanks Mark... - Jean II
- * This is the result of a scan inquiry command */
-/* Structure describing info about an Access Point */
-struct prism2_scan_apinfo {
-	__le16 channel;		/* Channel where the AP sits */
-	__le16 noise;		/* Noise level */
-	__le16 level;		/* Signal level */
-	u8 bssid[ETH_ALEN];	/* MAC address of the Access Point */
-	__le16 beacon_interv;	/* Beacon interval */
-	__le16 capabilities;	/* Capabilities */
-	__le16 essid_len;	/* ESSID length */
-	u8 essid[32];		/* ESSID of the network */
-	u8 rates[10];		/* Bit rate supported */
-	__le16 proberesp_rate;	/* Data rate of the response frame */
-	__le16 atim;		/* ATIM window time, Kus (hostscan only) */
-} __packed;
-
-/* Same stuff for the Lucent/Agere card.
- * Thanks to h1kari <h1kari AT dachb0den.com> - Jean II */
-struct agere_scan_apinfo {
-	__le16 channel;		/* Channel where the AP sits */
-	__le16 noise;		/* Noise level */
-	__le16 level;		/* Signal level */
-	u8 bssid[ETH_ALEN];	/* MAC address of the Access Point */
-	__le16 beacon_interv;	/* Beacon interval */
-	__le16 capabilities;	/* Capabilities */
-	/* bits: 0-ess, 1-ibss, 4-privacy [wep] */
-	__le16 essid_len;	/* ESSID length */
-	u8 essid[32];		/* ESSID of the network */
-} __packed;
-
-/* Moustafa: Scan structure for Symbol cards */
-struct symbol_scan_apinfo {
-	u8 channel;		/* Channel where the AP sits */
-	u8 unknown1;		/* 8 in 2.9x and 3.9x f/w, 0 otherwise */
-	__le16 noise;		/* Noise level */
-	__le16 level;		/* Signal level */
-	u8 bssid[ETH_ALEN];	/* MAC address of the Access Point */
-	__le16 beacon_interv;	/* Beacon interval */
-	__le16 capabilities;	/* Capabilities */
-	/* bits: 0-ess, 1-ibss, 4-privacy [wep] */
-	__le16 essid_len;	/* ESSID length */
-	u8 essid[32];		/* ESSID of the network */
-	__le16 rates[5];	/* Bit rate supported */
-	__le16 basic_rates;	/* Basic rates bitmask */
-	u8 unknown2[6];		/* Always FF:FF:FF:FF:00:00 */
-	u8 unknown3[8];		/* Always 0, appeared in f/w 3.91-68 */
-} __packed;
-
-union hermes_scan_info {
-	struct agere_scan_apinfo	a;
-	struct prism2_scan_apinfo	p;
-	struct symbol_scan_apinfo	s;
-};
-
-/* Extended scan struct for HERMES_INQ_CHANNELINFO.
- * wl_lkm calls this an ACS scan (Automatic Channel Select).
- * Keep out of union hermes_scan_info because it is much bigger than
- * the older scan structures. */
-struct agere_ext_scan_info {
-	__le16	reserved0;
-
-	u8	noise;
-	u8	level;
-	u8	rx_flow;
-	u8	rate;
-	__le16	reserved1[2];
-
-	__le16	frame_control;
-	__le16	dur_id;
-	u8	addr1[ETH_ALEN];
-	u8	addr2[ETH_ALEN];
-	u8	bssid[ETH_ALEN];
-	__le16	sequence;
-	u8	addr4[ETH_ALEN];
-
-	__le16	data_length;
-
-	/* Next 3 fields do not get filled in. */
-	u8	daddr[ETH_ALEN];
-	u8	saddr[ETH_ALEN];
-	__le16	len_type;
-
-	__le64	timestamp;
-	__le16	beacon_interval;
-	__le16	capabilities;
-	u8	data[];
-} __packed;
-
-#define HERMES_LINKSTATUS_NOT_CONNECTED   (0x0000)
-#define HERMES_LINKSTATUS_CONNECTED       (0x0001)
-#define HERMES_LINKSTATUS_DISCONNECTED    (0x0002)
-#define HERMES_LINKSTATUS_AP_CHANGE       (0x0003)
-#define HERMES_LINKSTATUS_AP_OUT_OF_RANGE (0x0004)
-#define HERMES_LINKSTATUS_AP_IN_RANGE     (0x0005)
-#define HERMES_LINKSTATUS_ASSOC_FAILED    (0x0006)
-
-struct hermes_linkstatus {
-	__le16 linkstatus;         /* Link status */
-} __packed;
-
-struct hermes_response {
-	u16 status, resp0, resp1, resp2;
-};
-
-/* "ID" structure - used for ESSID and station nickname */
-struct hermes_idstring {
-	__le16 len;
-	__le16 val[16];
-} __packed;
-
-struct hermes_multicast {
-	u8 addr[HERMES_MAX_MULTICAST][ETH_ALEN];
-} __packed;
-
-/* Timeouts */
-#define HERMES_BAP_BUSY_TIMEOUT (10000) /* In iterations of ~1us */
-
-struct hermes;
-
-/* Functions to access hardware */
-struct hermes_ops {
-	int (*init)(struct hermes *hw);
-	int (*cmd_wait)(struct hermes *hw, u16 cmd, u16 parm0,
-			struct hermes_response *resp);
-	int (*init_cmd_wait)(struct hermes *hw, u16 cmd,
-			     u16 parm0, u16 parm1, u16 parm2,
-			     struct hermes_response *resp);
-	int (*allocate)(struct hermes *hw, u16 size, u16 *fid);
-	int (*read_ltv)(struct hermes *hw, int bap, u16 rid, unsigned buflen,
-			u16 *length, void *buf);
-	int (*read_ltv_pr)(struct hermes *hw, int bap, u16 rid,
-			      unsigned buflen, u16 *length, void *buf);
-	int (*write_ltv)(struct hermes *hw, int bap, u16 rid,
-			 u16 length, const void *value);
-	int (*bap_pread)(struct hermes *hw, int bap, void *buf, int len,
-			 u16 id, u16 offset);
-	int (*bap_pwrite)(struct hermes *hw, int bap, const void *buf,
-			  int len, u16 id, u16 offset);
-	int (*read_pda)(struct hermes *hw, __le16 *pda,
-			u32 pda_addr, u16 pda_len);
-	int (*program_init)(struct hermes *hw, u32 entry_point);
-	int (*program_end)(struct hermes *hw);
-	int (*program)(struct hermes *hw, const char *buf,
-		       u32 addr, u32 len);
-	void (*lock_irqsave)(spinlock_t *lock, unsigned long *flags);
-	void (*unlock_irqrestore)(spinlock_t *lock, unsigned long *flags);
-	void (*lock_irq)(spinlock_t *lock);
-	void (*unlock_irq)(spinlock_t *lock);
-};
-
-/* Basic control structure */
-struct hermes {
-	void __iomem *iobase;
-	int reg_spacing;
-#define HERMES_16BIT_REGSPACING	0
-#define HERMES_32BIT_REGSPACING	1
-	u16 inten; /* Which interrupts should be enabled? */
-	bool eeprom_pda;
-	const struct hermes_ops *ops;
-	void *priv;
-};
-
-/* Register access convenience macros */
-#define hermes_read_reg(hw, off) \
-	(ioread16((hw)->iobase + ((off) << (hw)->reg_spacing)))
-#define hermes_write_reg(hw, off, val) \
-	(iowrite16((val), (hw)->iobase + ((off) << (hw)->reg_spacing)))
-#define hermes_read_regn(hw, name) hermes_read_reg((hw), HERMES_##name)
-#define hermes_write_regn(hw, name, val) \
-	hermes_write_reg((hw), HERMES_##name, (val))
-
-/* Function prototypes */
-void hermes_struct_init(struct hermes *hw, void __iomem *address,
-			int reg_spacing);
-
-/* Inline functions */
-
-static inline int hermes_present(struct hermes *hw)
-{
-	return hermes_read_regn(hw, SWSUPPORT0) == HERMES_MAGIC;
-}
-
-static inline void hermes_set_irqmask(struct hermes *hw, u16 events)
-{
-	hw->inten = events;
-	hermes_write_regn(hw, INTEN, events);
-}
-
-static inline int hermes_enable_port(struct hermes *hw, int port)
-{
-	return hw->ops->cmd_wait(hw, HERMES_CMD_ENABLE | (port << 8),
-				 0, NULL);
-}
-
-static inline int hermes_disable_port(struct hermes *hw, int port)
-{
-	return hw->ops->cmd_wait(hw, HERMES_CMD_DISABLE | (port << 8),
-				 0, NULL);
-}
-
-/* Initiate an INQUIRE command (tallies or scan).  The result will come as an
- * information frame in __orinoco_ev_info() */
-static inline int hermes_inquire(struct hermes *hw, u16 rid)
-{
-	return hw->ops->cmd_wait(hw, HERMES_CMD_INQUIRE, rid, NULL);
-}
-
-#define HERMES_BYTES_TO_RECLEN(n) ((((n) + 1) / 2) + 1)
-#define HERMES_RECLEN_TO_BYTES(n) (((n) - 1) * 2)
-
-/* Note that for the next two, the count is in 16-bit words, not bytes */
-static inline void hermes_read_words(struct hermes *hw, int off,
-				     void *buf, unsigned count)
-{
-	off = off << hw->reg_spacing;
-	ioread16_rep(hw->iobase + off, buf, count);
-}
-
-static inline void hermes_write_bytes(struct hermes *hw, int off,
-				      const char *buf, unsigned count)
-{
-	off = off << hw->reg_spacing;
-	iowrite16_rep(hw->iobase + off, buf, count >> 1);
-	if (unlikely(count & 1))
-		iowrite8(buf[count - 1], hw->iobase + off);
-}
-
-static inline void hermes_clear_words(struct hermes *hw, int off,
-				      unsigned count)
-{
-	unsigned i;
-
-	off = off << hw->reg_spacing;
-
-	for (i = 0; i < count; i++)
-		iowrite16(0, hw->iobase + off);
-}
-
-#define HERMES_READ_RECORD(hw, bap, rid, buf) \
-	(hw->ops->read_ltv((hw), (bap), (rid), sizeof(*buf), NULL, (buf)))
-#define HERMES_READ_RECORD_PR(hw, bap, rid, buf) \
-	(hw->ops->read_ltv_pr((hw), (bap), (rid), sizeof(*buf), NULL, (buf)))
-#define HERMES_WRITE_RECORD(hw, bap, rid, buf) \
-	(hw->ops->write_ltv((hw), (bap), (rid), \
-			    HERMES_BYTES_TO_RECLEN(sizeof(*buf)), (buf)))
-
-static inline int hermes_read_wordrec(struct hermes *hw, int bap, u16 rid,
-				      u16 *word)
-{
-	__le16 rec;
-	int err;
-
-	err = HERMES_READ_RECORD(hw, bap, rid, &rec);
-	*word = le16_to_cpu(rec);
-	return err;
-}
-
-static inline int hermes_read_wordrec_pr(struct hermes *hw, int bap, u16 rid,
-					 u16 *word)
-{
-	__le16 rec;
-	int err;
-
-	err = HERMES_READ_RECORD_PR(hw, bap, rid, &rec);
-	*word = le16_to_cpu(rec);
-	return err;
-}
-
-static inline int hermes_write_wordrec(struct hermes *hw, int bap, u16 rid,
-				       u16 word)
-{
-	__le16 rec = cpu_to_le16(word);
-	return HERMES_WRITE_RECORD(hw, bap, rid, &rec);
-}
-
-#endif  /* _HERMES_H */
diff --git a/drivers/net/wireless/intersil/orinoco/hermes_dld.c b/drivers/net/wireless/intersil/orinoco/hermes_dld.c
deleted file mode 100644
index dbeadfcfefe2..000000000000
--- a/drivers/net/wireless/intersil/orinoco/hermes_dld.c
+++ /dev/null
@@ -1,477 +0,0 @@
-/*
- * Hermes download helper.
- *
- * This helper:
- *  - is capable of writing to the volatile area of the hermes device
- *  - is currently not capable of writing to non-volatile areas
- *  - provide helpers to identify and update plugin data
- *  - is not capable of interpreting a fw image directly. That is up to
- *    the main card driver.
- *  - deals with Hermes I devices. It can probably be modified to deal
- *    with Hermes II devices
- *
- * Copyright (C) 2007, David Kilroy
- *
- * Plug data code slightly modified from spectrum_cs driver
- *    Copyright (C) 2002-2005 Pavel Roskin <proski@gnu.org>
- * Portions based on information in wl_lkm_718 Agere driver
- *    COPYRIGHT (C) 2001-2004 by Agere Systems Inc. All Rights Reserved
- *
- * The contents of this file are subject to the Mozilla Public License
- * Version 1.1 (the "License"); you may not use this file except in
- * compliance with the License. You may obtain a copy of the License
- * at http://www.mozilla.org/MPL/
- *
- * Software distributed under the License is distributed on an "AS IS"
- * basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See
- * the License for the specific language governing rights and
- * limitations under the License.
- *
- * Alternatively, the contents of this file may be used under the
- * terms of the GNU General Public License version 2 (the "GPL"), in
- * which case the provisions of the GPL are applicable instead of the
- * above.  If you wish to allow the use of your version of this file
- * only under the terms of the GPL and not to allow others to use your
- * version of this file under the MPL, indicate your decision by
- * deleting the provisions above and replace them with the notice and
- * other provisions required by the GPL.  If you do not delete the
- * provisions above, a recipient may use your version of this file
- * under either the MPL or the GPL.
- */
-
-#include <linux/module.h>
-#include <linux/delay.h>
-#include "hermes.h"
-#include "hermes_dld.h"
-
-#define PFX "hermes_dld: "
-
-/* End markers used in dblocks */
-#define PDI_END		0x00000000	/* End of PDA */
-#define BLOCK_END	0xFFFFFFFF	/* Last image block */
-#define TEXT_END	0x1A		/* End of text header */
-
-/*
- * The following structures have little-endian fields denoted by
- * the leading underscore.  Don't access them directly - use inline
- * functions defined below.
- */
-
-/*
- * The binary image to be downloaded consists of series of data blocks.
- * Each block has the following structure.
- */
-struct dblock {
-	__le32 addr;		/* adapter address where to write the block */
-	__le16 len;		/* length of the data only, in bytes */
-	char data[];		/* data to be written */
-} __packed;
-
-/*
- * Plug Data References are located in the image after the last data
- * block.  They refer to areas in the adapter memory where the plug data
- * items with matching ID should be written.
- */
-struct pdr {
-	__le32 id;		/* record ID */
-	__le32 addr;		/* adapter address where to write the data */
-	__le32 len;		/* expected length of the data, in bytes */
-	char next[];		/* next PDR starts here */
-} __packed;
-
-/*
- * Plug Data Items are located in the EEPROM read from the adapter by
- * primary firmware.  They refer to the device-specific data that should
- * be plugged into the secondary firmware.
- */
-struct pdi {
-	__le16 len;		/* length of ID and data, in words */
-	__le16 id;		/* record ID */
-	char data[];		/* plug data */
-} __packed;
-
-/*** FW data block access functions ***/
-
-static inline u32
-dblock_addr(const struct dblock *blk)
-{
-	return le32_to_cpu(blk->addr);
-}
-
-static inline u32
-dblock_len(const struct dblock *blk)
-{
-	return le16_to_cpu(blk->len);
-}
-
-/*** PDR Access functions ***/
-
-static inline u32
-pdr_id(const struct pdr *pdr)
-{
-	return le32_to_cpu(pdr->id);
-}
-
-static inline u32
-pdr_addr(const struct pdr *pdr)
-{
-	return le32_to_cpu(pdr->addr);
-}
-
-static inline u32
-pdr_len(const struct pdr *pdr)
-{
-	return le32_to_cpu(pdr->len);
-}
-
-/*** PDI Access functions ***/
-
-static inline u32
-pdi_id(const struct pdi *pdi)
-{
-	return le16_to_cpu(pdi->id);
-}
-
-/* Return length of the data only, in bytes */
-static inline u32
-pdi_len(const struct pdi *pdi)
-{
-	return 2 * (le16_to_cpu(pdi->len) - 1);
-}
-
-/*** Plug Data Functions ***/
-
-/*
- * Scan PDR for the record with the specified RECORD_ID.
- * If it's not found, return NULL.
- */
-static const struct pdr *
-hermes_find_pdr(const struct pdr *first_pdr, u32 record_id, const void *end)
-{
-	const struct pdr *pdr = first_pdr;
-
-	end -= sizeof(struct pdr);
-
-	while (((void *) pdr <= end) &&
-	       (pdr_id(pdr) != PDI_END)) {
-		/*
-		 * PDR area is currently not terminated by PDI_END.
-		 * It's followed by CRC records, which have the type
-		 * field where PDR has length.  The type can be 0 or 1.
-		 */
-		if (pdr_len(pdr) < 2)
-			return NULL;
-
-		/* If the record ID matches, we are done */
-		if (pdr_id(pdr) == record_id)
-			return pdr;
-
-		pdr = (struct pdr *) pdr->next;
-	}
-	return NULL;
-}
-
-/* Scan production data items for a particular entry */
-static const struct pdi *
-hermes_find_pdi(const struct pdi *first_pdi, u32 record_id, const void *end)
-{
-	const struct pdi *pdi = first_pdi;
-
-	end -= sizeof(struct pdi);
-
-	while (((void *) pdi <= end) &&
-	       (pdi_id(pdi) != PDI_END)) {
-
-		/* If the record ID matches, we are done */
-		if (pdi_id(pdi) == record_id)
-			return pdi;
-
-		pdi = (struct pdi *) &pdi->data[pdi_len(pdi)];
-	}
-	return NULL;
-}
-
-/* Process one Plug Data Item - find corresponding PDR and plug it */
-static int
-hermes_plug_pdi(struct hermes *hw, const struct pdr *first_pdr,
-		const struct pdi *pdi, const void *pdr_end)
-{
-	const struct pdr *pdr;
-
-	/* Find the PDR corresponding to this PDI */
-	pdr = hermes_find_pdr(first_pdr, pdi_id(pdi), pdr_end);
-
-	/* No match is found, safe to ignore */
-	if (!pdr)
-		return 0;
-
-	/* Lengths of the data in PDI and PDR must match */
-	if (pdi_len(pdi) != pdr_len(pdr))
-		return -EINVAL;
-
-	/* do the actual plugging */
-	hw->ops->program(hw, pdi->data, pdr_addr(pdr), pdi_len(pdi));
-
-	return 0;
-}
-
-/* Parse PDA and write the records into the adapter
- *
- * Attempt to write every records that is in the specified pda
- * which also has a valid production data record for the firmware.
- */
-int hermes_apply_pda(struct hermes *hw,
-		     const char *first_pdr,
-		     const void *pdr_end,
-		     const __le16 *pda,
-		     const void *pda_end)
-{
-	int ret;
-	const struct pdi *pdi;
-	const struct pdr *pdr;
-
-	pdr = (const struct pdr *) first_pdr;
-	pda_end -= sizeof(struct pdi);
-
-	/* Go through every PDI and plug them into the adapter */
-	pdi = (const struct pdi *) (pda + 2);
-	while (((void *) pdi <= pda_end) &&
-	       (pdi_id(pdi) != PDI_END)) {
-		ret = hermes_plug_pdi(hw, pdr, pdi, pdr_end);
-		if (ret)
-			return ret;
-
-		/* Increment to the next PDI */
-		pdi = (const struct pdi *) &pdi->data[pdi_len(pdi)];
-	}
-	return 0;
-}
-
-/* Identify the total number of bytes in all blocks
- * including the header data.
- */
-size_t
-hermes_blocks_length(const char *first_block, const void *end)
-{
-	const struct dblock *blk = (const struct dblock *) first_block;
-	int total_len = 0;
-	int len;
-
-	end -= sizeof(*blk);
-
-	/* Skip all blocks to locate Plug Data References
-	 * (Spectrum CS) */
-	while (((void *) blk <= end) &&
-	       (dblock_addr(blk) != BLOCK_END)) {
-		len = dblock_len(blk);
-		total_len += sizeof(*blk) + len;
-		blk = (struct dblock *) &blk->data[len];
-	}
-
-	return total_len;
-}
-
-/*** Hermes programming ***/
-
-/* Program the data blocks */
-int hermes_program(struct hermes *hw, const char *first_block, const void *end)
-{
-	const struct dblock *blk;
-	u32 blkaddr;
-	u32 blklen;
-	int err = 0;
-
-	blk = (const struct dblock *) first_block;
-
-	if ((void *) blk > (end - sizeof(*blk)))
-		return -EIO;
-
-	blkaddr = dblock_addr(blk);
-	blklen = dblock_len(blk);
-
-	while ((blkaddr != BLOCK_END) &&
-	       (((void *) blk + blklen) <= end)) {
-		pr_debug(PFX "Programming block of length %d "
-			 "to address 0x%08x\n", blklen, blkaddr);
-
-		err = hw->ops->program(hw, blk->data, blkaddr, blklen);
-		if (err)
-			break;
-
-		blk = (const struct dblock *) &blk->data[blklen];
-
-		if ((void *) blk > (end - sizeof(*blk)))
-			return -EIO;
-
-		blkaddr = dblock_addr(blk);
-		blklen = dblock_len(blk);
-	}
-	return err;
-}
-
-/*** Default plugging data for Hermes I ***/
-/* Values from wl_lkm_718/hcf/dhf.c */
-
-#define DEFINE_DEFAULT_PDR(pid, length, data)				\
-static const struct {							\
-	__le16 len;							\
-	__le16 id;							\
-	u8 val[length];							\
-} __packed default_pdr_data_##pid = {			\
-	cpu_to_le16((sizeof(default_pdr_data_##pid)/			\
-				sizeof(__le16)) - 1),			\
-	cpu_to_le16(pid),						\
-	data								\
-}
-
-#define DEFAULT_PDR(pid) default_pdr_data_##pid
-
-/*  HWIF Compatibility */
-DEFINE_DEFAULT_PDR(0x0005, 10, "\x00\x00\x06\x00\x01\x00\x01\x00\x01\x00");
-
-/* PPPPSign */
-DEFINE_DEFAULT_PDR(0x0108, 4, "\x00\x00\x00\x00");
-
-/* PPPPProf */
-DEFINE_DEFAULT_PDR(0x0109, 10, "\x00\x00\x00\x00\x03\x00\x00\x00\x00\x00");
-
-/* Antenna diversity */
-DEFINE_DEFAULT_PDR(0x0150, 2, "\x00\x3F");
-
-/* Modem VCO band Set-up */
-DEFINE_DEFAULT_PDR(0x0160, 28,
-		   "\x00\x00\x00\x00\x00\x00\x00\x00"
-		   "\x00\x00\x00\x00\x00\x00\x00\x00"
-		   "\x00\x00\x00\x00\x00\x00\x00\x00"
-		   "\x00\x00\x00\x00");
-
-/* Modem Rx Gain Table Values */
-DEFINE_DEFAULT_PDR(0x0161, 256,
-		   "\x3F\x01\x3F\01\x3F\x01\x3F\x01"
-		   "\x3F\x01\x3F\01\x3F\x01\x3F\x01"
-		   "\x3F\x01\x3F\01\x3F\x01\x3F\x01"
-		   "\x3F\x01\x3F\01\x3F\x01\x3F\x01"
-		   "\x3F\x01\x3E\01\x3E\x01\x3D\x01"
-		   "\x3D\x01\x3C\01\x3C\x01\x3B\x01"
-		   "\x3B\x01\x3A\01\x3A\x01\x39\x01"
-		   "\x39\x01\x38\01\x38\x01\x37\x01"
-		   "\x37\x01\x36\01\x36\x01\x35\x01"
-		   "\x35\x01\x34\01\x34\x01\x33\x01"
-		   "\x33\x01\x32\x01\x32\x01\x31\x01"
-		   "\x31\x01\x30\x01\x30\x01\x7B\x01"
-		   "\x7B\x01\x7A\x01\x7A\x01\x79\x01"
-		   "\x79\x01\x78\x01\x78\x01\x77\x01"
-		   "\x77\x01\x76\x01\x76\x01\x75\x01"
-		   "\x75\x01\x74\x01\x74\x01\x73\x01"
-		   "\x73\x01\x72\x01\x72\x01\x71\x01"
-		   "\x71\x01\x70\x01\x70\x01\x68\x01"
-		   "\x68\x01\x67\x01\x67\x01\x66\x01"
-		   "\x66\x01\x65\x01\x65\x01\x57\x01"
-		   "\x57\x01\x56\x01\x56\x01\x55\x01"
-		   "\x55\x01\x54\x01\x54\x01\x53\x01"
-		   "\x53\x01\x52\x01\x52\x01\x51\x01"
-		   "\x51\x01\x50\x01\x50\x01\x48\x01"
-		   "\x48\x01\x47\x01\x47\x01\x46\x01"
-		   "\x46\x01\x45\x01\x45\x01\x44\x01"
-		   "\x44\x01\x43\x01\x43\x01\x42\x01"
-		   "\x42\x01\x41\x01\x41\x01\x40\x01"
-		   "\x40\x01\x40\x01\x40\x01\x40\x01"
-		   "\x40\x01\x40\x01\x40\x01\x40\x01"
-		   "\x40\x01\x40\x01\x40\x01\x40\x01"
-		   "\x40\x01\x40\x01\x40\x01\x40\x01");
-
-/* Write PDA according to certain rules.
- *
- * For every production data record, look for a previous setting in
- * the pda, and use that.
- *
- * For certain records, use defaults if they are not found in pda.
- */
-int hermes_apply_pda_with_defaults(struct hermes *hw,
-				   const char *first_pdr,
-				   const void *pdr_end,
-				   const __le16 *pda,
-				   const void *pda_end)
-{
-	const struct pdr *pdr = (const struct pdr *) first_pdr;
-	const struct pdi *first_pdi = (const struct pdi *) &pda[2];
-	const struct pdi *pdi;
-	const struct pdi *default_pdi = NULL;
-	const struct pdi *outdoor_pdi;
-	int record_id;
-
-	pdr_end -= sizeof(struct pdr);
-
-	while (((void *) pdr <= pdr_end) &&
-	       (pdr_id(pdr) != PDI_END)) {
-		/*
-		 * For spectrum_cs firmwares,
-		 * PDR area is currently not terminated by PDI_END.
-		 * It's followed by CRC records, which have the type
-		 * field where PDR has length.  The type can be 0 or 1.
-		 */
-		if (pdr_len(pdr) < 2)
-			break;
-		record_id = pdr_id(pdr);
-
-		pdi = hermes_find_pdi(first_pdi, record_id, pda_end);
-		if (pdi)
-			pr_debug(PFX "Found record 0x%04x at %p\n",
-				 record_id, pdi);
-
-		switch (record_id) {
-		case 0x110: /* Modem REFDAC values */
-		case 0x120: /* Modem VGDAC values */
-			outdoor_pdi = hermes_find_pdi(first_pdi, record_id + 1,
-						      pda_end);
-			default_pdi = NULL;
-			if (outdoor_pdi) {
-				pdi = outdoor_pdi;
-				pr_debug(PFX
-					 "Using outdoor record 0x%04x at %p\n",
-					 record_id + 1, pdi);
-			}
-			break;
-		case 0x5: /*  HWIF Compatibility */
-			default_pdi = (struct pdi *) &DEFAULT_PDR(0x0005);
-			break;
-		case 0x108: /* PPPPSign */
-			default_pdi = (struct pdi *) &DEFAULT_PDR(0x0108);
-			break;
-		case 0x109: /* PPPPProf */
-			default_pdi = (struct pdi *) &DEFAULT_PDR(0x0109);
-			break;
-		case 0x150: /* Antenna diversity */
-			default_pdi = (struct pdi *) &DEFAULT_PDR(0x0150);
-			break;
-		case 0x160: /* Modem VCO band Set-up */
-			default_pdi = (struct pdi *) &DEFAULT_PDR(0x0160);
-			break;
-		case 0x161: /* Modem Rx Gain Table Values */
-			default_pdi = (struct pdi *) &DEFAULT_PDR(0x0161);
-			break;
-		default:
-			default_pdi = NULL;
-			break;
-		}
-		if (!pdi && default_pdi) {
-			/* Use default */
-			pdi = default_pdi;
-			pr_debug(PFX "Using default record 0x%04x at %p\n",
-				 record_id, pdi);
-		}
-
-		if (pdi) {
-			/* Lengths of the data in PDI and PDR must match */
-			if ((pdi_len(pdi) == pdr_len(pdr)) &&
-			    ((void *) pdi->data + pdi_len(pdi) < pda_end)) {
-				/* do the actual plugging */
-				hw->ops->program(hw, pdi->data, pdr_addr(pdr),
-						 pdi_len(pdi));
-			}
-		}
-
-		pdr++;
-	}
-	return 0;
-}
diff --git a/drivers/net/wireless/intersil/orinoco/hermes_dld.h b/drivers/net/wireless/intersil/orinoco/hermes_dld.h
deleted file mode 100644
index b5377e232c63..000000000000
--- a/drivers/net/wireless/intersil/orinoco/hermes_dld.h
+++ /dev/null
@@ -1,52 +0,0 @@
-/*
- * Copyright (C) 2007, David Kilroy
- *
- * The contents of this file are subject to the Mozilla Public License
- * Version 1.1 (the "License"); you may not use this file except in
- * compliance with the License. You may obtain a copy of the License
- * at http://www.mozilla.org/MPL/
- *
- * Software distributed under the License is distributed on an "AS IS"
- * basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See
- * the License for the specific language governing rights and
- * limitations under the License.
- *
- * Alternatively, the contents of this file may be used under the
- * terms of the GNU General Public License version 2 (the "GPL"), in
- * which case the provisions of the GPL are applicable instead of the
- * above.  If you wish to allow the use of your version of this file
- * only under the terms of the GPL and not to allow others to use your
- * version of this file under the MPL, indicate your decision by
- * deleting the provisions above and replace them with the notice and
- * other provisions required by the GPL.  If you do not delete the
- * provisions above, a recipient may use your version of this file
- * under either the MPL or the GPL.
- */
-#ifndef _HERMES_DLD_H
-#define _HERMES_DLD_H
-
-#include "hermes.h"
-
-int hermesi_program_init(struct hermes *hw, u32 offset);
-int hermesi_program_end(struct hermes *hw);
-int hermes_program(struct hermes *hw, const char *first_block, const void *end);
-
-int hermes_read_pda(struct hermes *hw,
-		    __le16 *pda,
-		    u32 pda_addr,
-		    u16 pda_len,
-		    int use_eeprom);
-int hermes_apply_pda(struct hermes *hw,
-		     const char *first_pdr,
-		     const void *pdr_end,
-		     const __le16 *pda,
-		     const void *pda_end);
-int hermes_apply_pda_with_defaults(struct hermes *hw,
-				   const char *first_pdr,
-				   const void *pdr_end,
-				   const __le16 *pda,
-				   const void *pda_end);
-
-size_t hermes_blocks_length(const char *first_block, const void *end);
-
-#endif /* _HERMES_DLD_H */
diff --git a/drivers/net/wireless/intersil/orinoco/hermes_rid.h b/drivers/net/wireless/intersil/orinoco/hermes_rid.h
deleted file mode 100644
index 42eb67dea1df..000000000000
--- a/drivers/net/wireless/intersil/orinoco/hermes_rid.h
+++ /dev/null
@@ -1,165 +0,0 @@
-#ifndef _HERMES_RID_H
-#define _HERMES_RID_H
-
-/*
- * Configuration RIDs
- */
-#define HERMES_RID_CNFPORTTYPE			0xFC00
-#define HERMES_RID_CNFOWNMACADDR		0xFC01
-#define HERMES_RID_CNFDESIREDSSID		0xFC02
-#define HERMES_RID_CNFOWNCHANNEL		0xFC03
-#define HERMES_RID_CNFOWNSSID			0xFC04
-#define HERMES_RID_CNFOWNATIMWINDOW		0xFC05
-#define HERMES_RID_CNFSYSTEMSCALE		0xFC06
-#define HERMES_RID_CNFMAXDATALEN		0xFC07
-#define HERMES_RID_CNFWDSADDRESS		0xFC08
-#define HERMES_RID_CNFPMENABLED			0xFC09
-#define HERMES_RID_CNFPMEPS			0xFC0A
-#define HERMES_RID_CNFMULTICASTRECEIVE		0xFC0B
-#define HERMES_RID_CNFMAXSLEEPDURATION		0xFC0C
-#define HERMES_RID_CNFPMHOLDOVERDURATION	0xFC0D
-#define HERMES_RID_CNFOWNNAME			0xFC0E
-#define HERMES_RID_CNFOWNDTIMPERIOD		0xFC10
-#define HERMES_RID_CNFWDSADDRESS1		0xFC11
-#define HERMES_RID_CNFWDSADDRESS2		0xFC12
-#define HERMES_RID_CNFWDSADDRESS3		0xFC13
-#define HERMES_RID_CNFWDSADDRESS4		0xFC14
-#define HERMES_RID_CNFWDSADDRESS5		0xFC15
-#define HERMES_RID_CNFWDSADDRESS6		0xFC16
-#define HERMES_RID_CNFMULTICASTPMBUFFERING	0xFC17
-#define HERMES_RID_CNFWEPENABLED_AGERE		0xFC20
-#define HERMES_RID_CNFAUTHENTICATION_AGERE	0xFC21
-#define HERMES_RID_CNFMANDATORYBSSID_SYMBOL	0xFC21
-#define HERMES_RID_CNFDROPUNENCRYPTED		0xFC22
-#define HERMES_RID_CNFWEPDEFAULTKEYID		0xFC23
-#define HERMES_RID_CNFDEFAULTKEY0		0xFC24
-#define HERMES_RID_CNFDEFAULTKEY1		0xFC25
-#define HERMES_RID_CNFMWOROBUST_AGERE		0xFC25
-#define HERMES_RID_CNFDEFAULTKEY2		0xFC26
-#define HERMES_RID_CNFDEFAULTKEY3		0xFC27
-#define HERMES_RID_CNFWEPFLAGS_INTERSIL		0xFC28
-#define HERMES_RID_CNFWEPKEYMAPPINGTABLE	0xFC29
-#define HERMES_RID_CNFAUTHENTICATION		0xFC2A
-#define HERMES_RID_CNFMAXASSOCSTA		0xFC2B
-#define	HERMES_RID_CNFKEYLENGTH_SYMBOL		0xFC2B
-#define HERMES_RID_CNFTXCONTROL			0xFC2C
-#define HERMES_RID_CNFROAMINGMODE		0xFC2D
-#define HERMES_RID_CNFHOSTAUTHENTICATION	0xFC2E
-#define HERMES_RID_CNFRCVCRCERROR		0xFC30
-#define HERMES_RID_CNFMMLIFE			0xFC31
-#define HERMES_RID_CNFALTRETRYCOUNT		0xFC32
-#define HERMES_RID_CNFBEACONINT			0xFC33
-#define HERMES_RID_CNFAPPCFINFO			0xFC34
-#define HERMES_RID_CNFSTAPCFINFO		0xFC35
-#define HERMES_RID_CNFPRIORITYQUSAGE		0xFC37
-#define HERMES_RID_CNFTIMCTRL			0xFC40
-#define HERMES_RID_CNFTHIRTY2TALLY		0xFC42
-#define HERMES_RID_CNFENHSECURITY		0xFC43
-#define HERMES_RID_CNFGROUPADDRESSES		0xFC80
-#define HERMES_RID_CNFCREATEIBSS		0xFC81
-#define HERMES_RID_CNFFRAGMENTATIONTHRESHOLD	0xFC82
-#define HERMES_RID_CNFRTSTHRESHOLD		0xFC83
-#define HERMES_RID_CNFTXRATECONTROL		0xFC84
-#define HERMES_RID_CNFPROMISCUOUSMODE		0xFC85
-#define HERMES_RID_CNFBASICRATES_SYMBOL		0xFC8A
-#define HERMES_RID_CNFPREAMBLE_SYMBOL		0xFC8C
-#define HERMES_RID_CNFFRAGMENTATIONTHRESHOLD0	0xFC90
-#define HERMES_RID_CNFFRAGMENTATIONTHRESHOLD1	0xFC91
-#define HERMES_RID_CNFFRAGMENTATIONTHRESHOLD2	0xFC92
-#define HERMES_RID_CNFFRAGMENTATIONTHRESHOLD3	0xFC93
-#define HERMES_RID_CNFFRAGMENTATIONTHRESHOLD4	0xFC94
-#define HERMES_RID_CNFFRAGMENTATIONTHRESHOLD5	0xFC95
-#define HERMES_RID_CNFFRAGMENTATIONTHRESHOLD6	0xFC96
-#define HERMES_RID_CNFRTSTHRESHOLD0		0xFC97
-#define HERMES_RID_CNFRTSTHRESHOLD1		0xFC98
-#define HERMES_RID_CNFRTSTHRESHOLD2		0xFC99
-#define HERMES_RID_CNFRTSTHRESHOLD3		0xFC9A
-#define HERMES_RID_CNFRTSTHRESHOLD4		0xFC9B
-#define HERMES_RID_CNFRTSTHRESHOLD5		0xFC9C
-#define HERMES_RID_CNFRTSTHRESHOLD6		0xFC9D
-#define HERMES_RID_CNFHOSTSCAN_SYMBOL		0xFCAB
-#define HERMES_RID_CNFSHORTPREAMBLE		0xFCB0
-#define HERMES_RID_CNFWEPKEYS_AGERE		0xFCB0
-#define HERMES_RID_CNFEXCLUDELONGPREAMBLE	0xFCB1
-#define HERMES_RID_CNFTXKEY_AGERE		0xFCB1
-#define HERMES_RID_CNFAUTHENTICATIONRSPTO	0xFCB2
-#define HERMES_RID_CNFSCANSSID_AGERE		0xFCB2
-#define HERMES_RID_CNFBASICRATES		0xFCB3
-#define HERMES_RID_CNFSUPPORTEDRATES		0xFCB4
-#define HERMES_RID_CNFADDDEFAULTTKIPKEY_AGERE	0xFCB4
-#define HERMES_RID_CNFSETWPAAUTHMGMTSUITE_AGERE	0xFCB5
-#define HERMES_RID_CNFREMDEFAULTTKIPKEY_AGERE	0xFCB6
-#define HERMES_RID_CNFADDMAPPEDTKIPKEY_AGERE	0xFCB7
-#define HERMES_RID_CNFREMMAPPEDTKIPKEY_AGERE	0xFCB8
-#define HERMES_RID_CNFSETWPACAPABILITIES_AGERE	0xFCB9
-#define HERMES_RID_CNFCACHEDPMKADDRESS		0xFCBA
-#define HERMES_RID_CNFREMOVEPMKADDRESS		0xFCBB
-#define HERMES_RID_CNFSCANCHANNELS2GHZ		0xFCC2
-#define HERMES_RID_CNFDISASSOCIATE		0xFCC8
-#define HERMES_RID_CNFTICKTIME			0xFCE0
-#define HERMES_RID_CNFSCANREQUEST		0xFCE1
-#define HERMES_RID_CNFJOINREQUEST		0xFCE2
-#define HERMES_RID_CNFAUTHENTICATESTATION	0xFCE3
-#define HERMES_RID_CNFCHANNELINFOREQUEST	0xFCE4
-#define HERMES_RID_CNFHOSTSCAN			0xFCE5
-
-/*
- * Information RIDs
- */
-#define HERMES_RID_MAXLOADTIME			0xFD00
-#define HERMES_RID_DOWNLOADBUFFER		0xFD01
-#define HERMES_RID_PRIID			0xFD02
-#define HERMES_RID_PRISUPRANGE			0xFD03
-#define HERMES_RID_CFIACTRANGES			0xFD04
-#define HERMES_RID_NICSERNUM			0xFD0A
-#define HERMES_RID_NICID			0xFD0B
-#define HERMES_RID_MFISUPRANGE			0xFD0C
-#define HERMES_RID_CFISUPRANGE			0xFD0D
-#define HERMES_RID_CHANNELLIST			0xFD10
-#define HERMES_RID_REGULATORYDOMAINS		0xFD11
-#define HERMES_RID_TEMPTYPE			0xFD12
-#define HERMES_RID_CIS				0xFD13
-#define HERMES_RID_STAID			0xFD20
-#define HERMES_RID_STASUPRANGE			0xFD21
-#define HERMES_RID_MFIACTRANGES			0xFD22
-#define HERMES_RID_CFIACTRANGES2		0xFD23
-#define HERMES_RID_SECONDARYVERSION_SYMBOL	0xFD24
-#define HERMES_RID_PORTSTATUS			0xFD40
-#define HERMES_RID_CURRENTSSID			0xFD41
-#define HERMES_RID_CURRENTBSSID			0xFD42
-#define HERMES_RID_COMMSQUALITY			0xFD43
-#define HERMES_RID_CURRENTTXRATE		0xFD44
-#define HERMES_RID_CURRENTBEACONINTERVAL	0xFD45
-#define HERMES_RID_CURRENTSCALETHRESHOLDS	0xFD46
-#define HERMES_RID_PROTOCOLRSPTIME		0xFD47
-#define HERMES_RID_SHORTRETRYLIMIT		0xFD48
-#define HERMES_RID_LONGRETRYLIMIT		0xFD49
-#define HERMES_RID_MAXTRANSMITLIFETIME		0xFD4A
-#define HERMES_RID_MAXRECEIVELIFETIME		0xFD4B
-#define HERMES_RID_CFPOLLABLE			0xFD4C
-#define HERMES_RID_AUTHENTICATIONALGORITHMS	0xFD4D
-#define HERMES_RID_PRIVACYOPTIONIMPLEMENTED	0xFD4F
-#define HERMES_RID_DBMCOMMSQUALITY_INTERSIL	0xFD51
-#define HERMES_RID_CURRENTTXRATE1		0xFD80
-#define HERMES_RID_CURRENTTXRATE2		0xFD81
-#define HERMES_RID_CURRENTTXRATE3		0xFD82
-#define HERMES_RID_CURRENTTXRATE4		0xFD83
-#define HERMES_RID_CURRENTTXRATE5		0xFD84
-#define HERMES_RID_CURRENTTXRATE6		0xFD85
-#define HERMES_RID_OWNMACADDR			0xFD86
-#define HERMES_RID_SCANRESULTSTABLE		0xFD88
-#define HERMES_RID_CURRENT_COUNTRY_INFO		0xFD89
-#define HERMES_RID_CURRENT_WPA_IE		0xFD8A
-#define HERMES_RID_CURRENT_TKIP_IV		0xFD8B
-#define HERMES_RID_CURRENT_ASSOC_REQ_INFO	0xFD8C
-#define HERMES_RID_CURRENT_ASSOC_RESP_INFO	0xFD8D
-#define HERMES_RID_TXQUEUEEMPTY			0xFD91
-#define HERMES_RID_PHYTYPE			0xFDC0
-#define HERMES_RID_CURRENTCHANNEL		0xFDC1
-#define HERMES_RID_CURRENTPOWERSTATE		0xFDC2
-#define HERMES_RID_CCAMODE			0xFDC3
-#define HERMES_RID_SUPPORTEDDATARATES		0xFDC6
-#define HERMES_RID_BUILDSEQ			0xFFFE
-#define HERMES_RID_FWID				0xFFFF
-
-#endif
diff --git a/drivers/net/wireless/intersil/orinoco/hw.c b/drivers/net/wireless/intersil/orinoco/hw.c
deleted file mode 100644
index 4fcca08e50de..000000000000
--- a/drivers/net/wireless/intersil/orinoco/hw.c
+++ /dev/null
@@ -1,1362 +0,0 @@
-/* Encapsulate basic setting changes and retrieval on Hermes hardware
- *
- * See copyright notice in main.c
- */
-#include <linux/kernel.h>
-#include <linux/device.h>
-#include <linux/if_arp.h>
-#include <linux/ieee80211.h>
-#include <linux/wireless.h>
-#include <net/cfg80211.h>
-#include "hermes.h"
-#include "hermes_rid.h"
-#include "orinoco.h"
-
-#include "hw.h"
-
-#define SYMBOL_MAX_VER_LEN	(14)
-
-/* Symbol firmware has a bug allocating buffers larger than this */
-#define TX_NICBUF_SIZE_BUG	1585
-
-/********************************************************************/
-/* Data tables                                                      */
-/********************************************************************/
-
-/* This tables gives the actual meanings of the bitrate IDs returned
- * by the firmware. */
-static const struct {
-	int bitrate; /* in 100s of kilobits */
-	int automatic;
-	u16 agere_txratectrl;
-	u16 intersil_txratectrl;
-} bitrate_table[] = {
-	{110, 1,  3, 15}, /* Entry 0 is the default */
-	{10,  0,  1,  1},
-	{10,  1,  1,  1},
-	{20,  0,  2,  2},
-	{20,  1,  6,  3},
-	{55,  0,  4,  4},
-	{55,  1,  7,  7},
-	{110, 0,  5,  8},
-};
-#define BITRATE_TABLE_SIZE ARRAY_SIZE(bitrate_table)
-
-/* Firmware version encoding */
-struct comp_id {
-	u16 id, variant, major, minor;
-} __packed;
-
-static inline enum fwtype determine_firmware_type(struct comp_id *nic_id)
-{
-	if (nic_id->id < 0x8000)
-		return FIRMWARE_TYPE_AGERE;
-	else if (nic_id->id == 0x8000 && nic_id->major == 0)
-		return FIRMWARE_TYPE_SYMBOL;
-	else
-		return FIRMWARE_TYPE_INTERSIL;
-}
-
-/* Set priv->firmware type, determine firmware properties
- * This function can be called before we have registerred with netdev,
- * so all errors go out with dev_* rather than printk
- *
- * If non-NULL stores a firmware description in fw_name.
- * If non-NULL stores a HW version in hw_ver
- *
- * These are output via generic cfg80211 ethtool support.
- */
-int determine_fw_capabilities(struct orinoco_private *priv,
-			      char *fw_name, size_t fw_name_len,
-			      u32 *hw_ver)
-{
-	struct device *dev = priv->dev;
-	struct hermes *hw = &priv->hw;
-	int err;
-	struct comp_id nic_id, sta_id;
-	unsigned int firmver;
-	char tmp[SYMBOL_MAX_VER_LEN + 1] __attribute__((aligned(2)));
-
-	/* Get the hardware version */
-	err = HERMES_READ_RECORD_PR(hw, USER_BAP, HERMES_RID_NICID, &nic_id);
-	if (err) {
-		dev_err(dev, "Cannot read hardware identity: error %d\n",
-			err);
-		return err;
-	}
-
-	le16_to_cpus(&nic_id.id);
-	le16_to_cpus(&nic_id.variant);
-	le16_to_cpus(&nic_id.major);
-	le16_to_cpus(&nic_id.minor);
-	dev_info(dev, "Hardware identity %04x:%04x:%04x:%04x\n",
-		 nic_id.id, nic_id.variant, nic_id.major, nic_id.minor);
-
-	if (hw_ver)
-		*hw_ver = (((nic_id.id & 0xff) << 24) |
-			   ((nic_id.variant & 0xff) << 16) |
-			   ((nic_id.major & 0xff) << 8) |
-			   (nic_id.minor & 0xff));
-
-	priv->firmware_type = determine_firmware_type(&nic_id);
-
-	/* Get the firmware version */
-	err = HERMES_READ_RECORD_PR(hw, USER_BAP, HERMES_RID_STAID, &sta_id);
-	if (err) {
-		dev_err(dev, "Cannot read station identity: error %d\n",
-			err);
-		return err;
-	}
-
-	le16_to_cpus(&sta_id.id);
-	le16_to_cpus(&sta_id.variant);
-	le16_to_cpus(&sta_id.major);
-	le16_to_cpus(&sta_id.minor);
-	dev_info(dev, "Station identity  %04x:%04x:%04x:%04x\n",
-		 sta_id.id, sta_id.variant, sta_id.major, sta_id.minor);
-
-	switch (sta_id.id) {
-	case 0x15:
-		dev_err(dev, "Primary firmware is active\n");
-		return -ENODEV;
-	case 0x14b:
-		dev_err(dev, "Tertiary firmware is active\n");
-		return -ENODEV;
-	case 0x1f:	/* Intersil, Agere, Symbol Spectrum24 */
-	case 0x21:	/* Symbol Spectrum24 Trilogy */
-		break;
-	default:
-		dev_notice(dev, "Unknown station ID, please report\n");
-		break;
-	}
-
-	/* Default capabilities */
-	priv->has_sensitivity = 1;
-	priv->has_mwo = 0;
-	priv->has_preamble = 0;
-	priv->has_port3 = 1;
-	priv->has_ibss = 1;
-	priv->has_wep = 0;
-	priv->has_big_wep = 0;
-	priv->has_alt_txcntl = 0;
-	priv->has_ext_scan = 0;
-	priv->has_wpa = 0;
-	priv->do_fw_download = 0;
-
-	/* Determine capabilities from the firmware version */
-	switch (priv->firmware_type) {
-	case FIRMWARE_TYPE_AGERE:
-		/* Lucent Wavelan IEEE, Lucent Orinoco, Cabletron RoamAbout,
-		   ELSA, Melco, HP, IBM, Dell 1150, Compaq 110/210 */
-		if (fw_name)
-			snprintf(fw_name, fw_name_len, "Lucent/Agere %d.%02d",
-				 sta_id.major, sta_id.minor);
-
-		firmver = ((unsigned long)sta_id.major << 16) | sta_id.minor;
-
-		priv->has_ibss = (firmver >= 0x60006);
-		priv->has_wep = (firmver >= 0x40020);
-		priv->has_big_wep = 1; /* FIXME: this is wrong - how do we tell
-					  Gold cards from the others? */
-		priv->has_mwo = (firmver >= 0x60000);
-		priv->has_pm = (firmver >= 0x40020); /* Don't work in 7.52 ? */
-		priv->ibss_port = 1;
-		priv->has_hostscan = (firmver >= 0x8000a);
-		priv->do_fw_download = 1;
-		priv->broken_monitor = (firmver >= 0x80000);
-		priv->has_alt_txcntl = (firmver >= 0x90000); /* All 9.x ? */
-		priv->has_ext_scan = (firmver >= 0x90000); /* All 9.x ? */
-		priv->has_wpa = (firmver >= 0x9002a);
-		/* Tested with Agere firmware :
-		 *	1.16 ; 4.08 ; 4.52 ; 6.04 ; 6.16 ; 7.28 => Jean II
-		 * Tested CableTron firmware : 4.32 => Anton */
-		break;
-	case FIRMWARE_TYPE_SYMBOL:
-		/* Symbol , 3Com AirConnect, Intel, Ericsson WLAN */
-		/* Intel MAC : 00:02:B3:* */
-		/* 3Com MAC : 00:50:DA:* */
-		memset(tmp, 0, sizeof(tmp));
-		/* Get the Symbol firmware version */
-		err = hw->ops->read_ltv_pr(hw, USER_BAP,
-					HERMES_RID_SECONDARYVERSION_SYMBOL,
-					SYMBOL_MAX_VER_LEN, NULL, &tmp);
-		if (err) {
-			dev_warn(dev, "Error %d reading Symbol firmware info. "
-				 "Wildly guessing capabilities...\n", err);
-			firmver = 0;
-			tmp[0] = '\0';
-		} else {
-			/* The firmware revision is a string, the format is
-			 * something like : "V2.20-01".
-			 * Quick and dirty parsing... - Jean II
-			 */
-			firmver = ((tmp[1] - '0') << 16)
-				| ((tmp[3] - '0') << 12)
-				| ((tmp[4] - '0') << 8)
-				| ((tmp[6] - '0') << 4)
-				| (tmp[7] - '0');
-
-			tmp[SYMBOL_MAX_VER_LEN] = '\0';
-		}
-
-		if (fw_name)
-			snprintf(fw_name, fw_name_len, "Symbol %s", tmp);
-
-		priv->has_ibss = (firmver >= 0x20000);
-		priv->has_wep = (firmver >= 0x15012);
-		priv->has_big_wep = (firmver >= 0x20000);
-		priv->has_pm = (firmver >= 0x20000 && firmver < 0x22000) ||
-			       (firmver >= 0x29000 && firmver < 0x30000) ||
-			       firmver >= 0x31000;
-		priv->has_preamble = (firmver >= 0x20000);
-		priv->ibss_port = 4;
-
-		/* Symbol firmware is found on various cards, but
-		 * there has been no attempt to check firmware
-		 * download on non-spectrum_cs based cards.
-		 *
-		 * Given that the Agere firmware download works
-		 * differently, we should avoid doing a firmware
-		 * download with the Symbol algorithm on non-spectrum
-		 * cards.
-		 *
-		 * For now we can identify a spectrum_cs based card
-		 * because it has a firmware reset function.
-		 */
-		priv->do_fw_download = (priv->stop_fw != NULL);
-
-		priv->broken_disableport = (firmver == 0x25013) ||
-				(firmver >= 0x30000 && firmver <= 0x31000);
-		priv->has_hostscan = (firmver >= 0x31001) ||
-				     (firmver >= 0x29057 && firmver < 0x30000);
-		/* Tested with Intel firmware : 0x20015 => Jean II */
-		/* Tested with 3Com firmware : 0x15012 & 0x22001 => Jean II */
-		break;
-	case FIRMWARE_TYPE_INTERSIL:
-		/* D-Link, Linksys, Adtron, ZoomAir, and many others...
-		 * Samsung, Compaq 100/200 and Proxim are slightly
-		 * different and less well tested */
-		/* D-Link MAC : 00:40:05:* */
-		/* Addtron MAC : 00:90:D1:* */
-		if (fw_name)
-			snprintf(fw_name, fw_name_len, "Intersil %d.%d.%d",
-				 sta_id.major, sta_id.minor, sta_id.variant);
-
-		firmver = ((unsigned long)sta_id.major << 16) |
-			((unsigned long)sta_id.minor << 8) | sta_id.variant;
-
-		priv->has_ibss = (firmver >= 0x000700); /* FIXME */
-		priv->has_big_wep = priv->has_wep = (firmver >= 0x000800);
-		priv->has_pm = (firmver >= 0x000700);
-		priv->has_hostscan = (firmver >= 0x010301);
-
-		if (firmver >= 0x000800)
-			priv->ibss_port = 0;
-		else {
-			dev_notice(dev, "Intersil firmware earlier than v0.8.x"
-				   " - several features not supported\n");
-			priv->ibss_port = 1;
-		}
-		break;
-	}
-	if (fw_name)
-		dev_info(dev, "Firmware determined as %s\n", fw_name);
-
-#ifndef CONFIG_HERMES_PRISM
-	if (priv->firmware_type == FIRMWARE_TYPE_INTERSIL) {
-		dev_err(dev, "Support for Prism chipset is not enabled\n");
-		return -ENODEV;
-	}
-#endif
-
-	return 0;
-}
-
-/* Read settings from EEPROM into our private structure.
- * MAC address gets dropped into callers buffer
- * Can be called before netdev registration.
- */
-int orinoco_hw_read_card_settings(struct orinoco_private *priv, u8 *dev_addr)
-{
-	struct device *dev = priv->dev;
-	struct hermes_idstring nickbuf;
-	struct hermes *hw = &priv->hw;
-	int len;
-	int err;
-	u16 reclen;
-
-	/* Get the MAC address */
-	err = hw->ops->read_ltv_pr(hw, USER_BAP, HERMES_RID_CNFOWNMACADDR,
-				ETH_ALEN, NULL, dev_addr);
-	if (err) {
-		dev_warn(dev, "Failed to read MAC address!\n");
-		goto out;
-	}
-
-	dev_dbg(dev, "MAC address %pM\n", dev_addr);
-
-	/* Get the station name */
-	err = hw->ops->read_ltv_pr(hw, USER_BAP, HERMES_RID_CNFOWNNAME,
-				sizeof(nickbuf), &reclen, &nickbuf);
-	if (err) {
-		dev_err(dev, "failed to read station name\n");
-		goto out;
-	}
-	if (nickbuf.len)
-		len = min(IW_ESSID_MAX_SIZE, (int)le16_to_cpu(nickbuf.len));
-	else
-		len = min(IW_ESSID_MAX_SIZE, 2 * reclen);
-	memcpy(priv->nick, &nickbuf.val, len);
-	priv->nick[len] = '\0';
-
-	dev_dbg(dev, "Station name \"%s\"\n", priv->nick);
-
-	/* Get allowed channels */
-	err = hermes_read_wordrec_pr(hw, USER_BAP, HERMES_RID_CHANNELLIST,
-				  &priv->channel_mask);
-	if (err) {
-		dev_err(dev, "Failed to read channel list!\n");
-		goto out;
-	}
-
-	/* Get initial AP density */
-	err = hermes_read_wordrec_pr(hw, USER_BAP, HERMES_RID_CNFSYSTEMSCALE,
-				  &priv->ap_density);
-	if (err || priv->ap_density < 1 || priv->ap_density > 3)
-		priv->has_sensitivity = 0;
-
-	/* Get initial RTS threshold */
-	err = hermes_read_wordrec_pr(hw, USER_BAP, HERMES_RID_CNFRTSTHRESHOLD,
-				  &priv->rts_thresh);
-	if (err) {
-		dev_err(dev, "Failed to read RTS threshold!\n");
-		goto out;
-	}
-
-	/* Get initial fragmentation settings */
-	if (priv->has_mwo)
-		err = hermes_read_wordrec_pr(hw, USER_BAP,
-					  HERMES_RID_CNFMWOROBUST_AGERE,
-					  &priv->mwo_robust);
-	else
-		err = hermes_read_wordrec_pr(hw, USER_BAP,
-					  HERMES_RID_CNFFRAGMENTATIONTHRESHOLD,
-					  &priv->frag_thresh);
-	if (err) {
-		dev_err(dev, "Failed to read fragmentation settings!\n");
-		goto out;
-	}
-
-	/* Power management setup */
-	if (priv->has_pm) {
-		priv->pm_on = 0;
-		priv->pm_mcast = 1;
-		err = hermes_read_wordrec_pr(hw, USER_BAP,
-					  HERMES_RID_CNFMAXSLEEPDURATION,
-					  &priv->pm_period);
-		if (err) {
-			dev_err(dev, "Failed to read power management "
-				"period!\n");
-			goto out;
-		}
-		err = hermes_read_wordrec_pr(hw, USER_BAP,
-					  HERMES_RID_CNFPMHOLDOVERDURATION,
-					  &priv->pm_timeout);
-		if (err) {
-			dev_err(dev, "Failed to read power management "
-				"timeout!\n");
-			goto out;
-		}
-	}
-
-	/* Preamble setup */
-	if (priv->has_preamble) {
-		err = hermes_read_wordrec_pr(hw, USER_BAP,
-					  HERMES_RID_CNFPREAMBLE_SYMBOL,
-					  &priv->preamble);
-		if (err) {
-			dev_err(dev, "Failed to read preamble setup\n");
-			goto out;
-		}
-	}
-
-	/* Retry settings */
-	err = hermes_read_wordrec_pr(hw, USER_BAP, HERMES_RID_SHORTRETRYLIMIT,
-				  &priv->short_retry_limit);
-	if (err) {
-		dev_err(dev, "Failed to read short retry limit\n");
-		goto out;
-	}
-
-	err = hermes_read_wordrec_pr(hw, USER_BAP, HERMES_RID_LONGRETRYLIMIT,
-				  &priv->long_retry_limit);
-	if (err) {
-		dev_err(dev, "Failed to read long retry limit\n");
-		goto out;
-	}
-
-	err = hermes_read_wordrec_pr(hw, USER_BAP, HERMES_RID_MAXTRANSMITLIFETIME,
-				  &priv->retry_lifetime);
-	if (err) {
-		dev_err(dev, "Failed to read max retry lifetime\n");
-		goto out;
-	}
-
-out:
-	return err;
-}
-
-/* Can be called before netdev registration */
-int orinoco_hw_allocate_fid(struct orinoco_private *priv)
-{
-	struct device *dev = priv->dev;
-	struct hermes *hw = &priv->hw;
-	int err;
-
-	err = hw->ops->allocate(hw, priv->nicbuf_size, &priv->txfid);
-	if (err == -EIO && priv->nicbuf_size > TX_NICBUF_SIZE_BUG) {
-		/* Try workaround for old Symbol firmware bug */
-		priv->nicbuf_size = TX_NICBUF_SIZE_BUG;
-		err = hw->ops->allocate(hw, priv->nicbuf_size, &priv->txfid);
-
-		dev_warn(dev, "Firmware ALLOC bug detected "
-			 "(old Symbol firmware?). Work around %s\n",
-			 err ? "failed!" : "ok.");
-	}
-
-	return err;
-}
-
-int orinoco_get_bitratemode(int bitrate, int automatic)
-{
-	int ratemode = -1;
-	int i;
-
-	if ((bitrate != 10) && (bitrate != 20) &&
-	    (bitrate != 55) && (bitrate != 110))
-		return ratemode;
-
-	for (i = 0; i < BITRATE_TABLE_SIZE; i++) {
-		if ((bitrate_table[i].bitrate == bitrate) &&
-		    (bitrate_table[i].automatic == automatic)) {
-			ratemode = i;
-			break;
-		}
-	}
-	return ratemode;
-}
-
-void orinoco_get_ratemode_cfg(int ratemode, int *bitrate, int *automatic)
-{
-	BUG_ON((ratemode < 0) || (ratemode >= BITRATE_TABLE_SIZE));
-
-	*bitrate = bitrate_table[ratemode].bitrate * 100000;
-	*automatic = bitrate_table[ratemode].automatic;
-}
-
-int orinoco_hw_program_rids(struct orinoco_private *priv)
-{
-	struct net_device *dev = priv->ndev;
-	struct wireless_dev *wdev = netdev_priv(dev);
-	struct hermes *hw = &priv->hw;
-	int err;
-	struct hermes_idstring idbuf;
-
-	/* Set the MAC address */
-	err = hw->ops->write_ltv(hw, USER_BAP, HERMES_RID_CNFOWNMACADDR,
-				 HERMES_BYTES_TO_RECLEN(ETH_ALEN),
-				 dev->dev_addr);
-	if (err) {
-		printk(KERN_ERR "%s: Error %d setting MAC address\n",
-		       dev->name, err);
-		return err;
-	}
-
-	/* Set up the link mode */
-	err = hermes_write_wordrec(hw, USER_BAP, HERMES_RID_CNFPORTTYPE,
-				   priv->port_type);
-	if (err) {
-		printk(KERN_ERR "%s: Error %d setting port type\n",
-		       dev->name, err);
-		return err;
-	}
-	/* Set the channel/frequency */
-	if (priv->channel != 0 && priv->iw_mode != NL80211_IFTYPE_STATION) {
-		err = hermes_write_wordrec(hw, USER_BAP,
-					   HERMES_RID_CNFOWNCHANNEL,
-					   priv->channel);
-		if (err) {
-			printk(KERN_ERR "%s: Error %d setting channel %d\n",
-			       dev->name, err, priv->channel);
-			return err;
-		}
-	}
-
-	if (priv->has_ibss) {
-		u16 createibss;
-
-		if ((strlen(priv->desired_essid) == 0) && (priv->createibss)) {
-			printk(KERN_WARNING "%s: This firmware requires an "
-			       "ESSID in IBSS-Ad-Hoc mode.\n", dev->name);
-			/* With wvlan_cs, in this case, we would crash.
-			 * hopefully, this driver will behave better...
-			 * Jean II */
-			createibss = 0;
-		} else {
-			createibss = priv->createibss;
-		}
-
-		err = hermes_write_wordrec(hw, USER_BAP,
-					   HERMES_RID_CNFCREATEIBSS,
-					   createibss);
-		if (err) {
-			printk(KERN_ERR "%s: Error %d setting CREATEIBSS\n",
-			       dev->name, err);
-			return err;
-		}
-	}
-
-	/* Set the desired BSSID */
-	err = __orinoco_hw_set_wap(priv);
-	if (err) {
-		printk(KERN_ERR "%s: Error %d setting AP address\n",
-		       dev->name, err);
-		return err;
-	}
-
-	/* Set the desired ESSID */
-	idbuf.len = cpu_to_le16(strlen(priv->desired_essid));
-	memcpy(&idbuf.val, priv->desired_essid, sizeof(idbuf.val));
-	/* WinXP wants partner to configure OWNSSID even in IBSS mode. (jimc) */
-	err = hw->ops->write_ltv(hw, USER_BAP, HERMES_RID_CNFOWNSSID,
-			HERMES_BYTES_TO_RECLEN(strlen(priv->desired_essid) + 2),
-			&idbuf);
-	if (err) {
-		printk(KERN_ERR "%s: Error %d setting OWNSSID\n",
-		       dev->name, err);
-		return err;
-	}
-	err = hw->ops->write_ltv(hw, USER_BAP, HERMES_RID_CNFDESIREDSSID,
-			HERMES_BYTES_TO_RECLEN(strlen(priv->desired_essid) + 2),
-			&idbuf);
-	if (err) {
-		printk(KERN_ERR "%s: Error %d setting DESIREDSSID\n",
-		       dev->name, err);
-		return err;
-	}
-
-	/* Set the station name */
-	idbuf.len = cpu_to_le16(strlen(priv->nick));
-	memcpy(&idbuf.val, priv->nick, sizeof(idbuf.val));
-	err = hw->ops->write_ltv(hw, USER_BAP, HERMES_RID_CNFOWNNAME,
-				 HERMES_BYTES_TO_RECLEN(strlen(priv->nick) + 2),
-				 &idbuf);
-	if (err) {
-		printk(KERN_ERR "%s: Error %d setting nickname\n",
-		       dev->name, err);
-		return err;
-	}
-
-	/* Set AP density */
-	if (priv->has_sensitivity) {
-		err = hermes_write_wordrec(hw, USER_BAP,
-					   HERMES_RID_CNFSYSTEMSCALE,
-					   priv->ap_density);
-		if (err) {
-			printk(KERN_WARNING "%s: Error %d setting SYSTEMSCALE. "
-			       "Disabling sensitivity control\n",
-			       dev->name, err);
-
-			priv->has_sensitivity = 0;
-		}
-	}
-
-	/* Set RTS threshold */
-	err = hermes_write_wordrec(hw, USER_BAP, HERMES_RID_CNFRTSTHRESHOLD,
-				   priv->rts_thresh);
-	if (err) {
-		printk(KERN_ERR "%s: Error %d setting RTS threshold\n",
-		       dev->name, err);
-		return err;
-	}
-
-	/* Set fragmentation threshold or MWO robustness */
-	if (priv->has_mwo)
-		err = hermes_write_wordrec(hw, USER_BAP,
-					   HERMES_RID_CNFMWOROBUST_AGERE,
-					   priv->mwo_robust);
-	else
-		err = hermes_write_wordrec(hw, USER_BAP,
-					   HERMES_RID_CNFFRAGMENTATIONTHRESHOLD,
-					   priv->frag_thresh);
-	if (err) {
-		printk(KERN_ERR "%s: Error %d setting fragmentation\n",
-		       dev->name, err);
-		return err;
-	}
-
-	/* Set bitrate */
-	err = __orinoco_hw_set_bitrate(priv);
-	if (err) {
-		printk(KERN_ERR "%s: Error %d setting bitrate\n",
-		       dev->name, err);
-		return err;
-	}
-
-	/* Set power management */
-	if (priv->has_pm) {
-		err = hermes_write_wordrec(hw, USER_BAP,
-					   HERMES_RID_CNFPMENABLED,
-					   priv->pm_on);
-		if (err) {
-			printk(KERN_ERR "%s: Error %d setting up PM\n",
-			       dev->name, err);
-			return err;
-		}
-
-		err = hermes_write_wordrec(hw, USER_BAP,
-					   HERMES_RID_CNFMULTICASTRECEIVE,
-					   priv->pm_mcast);
-		if (err) {
-			printk(KERN_ERR "%s: Error %d setting up PM\n",
-			       dev->name, err);
-			return err;
-		}
-		err = hermes_write_wordrec(hw, USER_BAP,
-					   HERMES_RID_CNFMAXSLEEPDURATION,
-					   priv->pm_period);
-		if (err) {
-			printk(KERN_ERR "%s: Error %d setting up PM\n",
-			       dev->name, err);
-			return err;
-		}
-		err = hermes_write_wordrec(hw, USER_BAP,
-					   HERMES_RID_CNFPMHOLDOVERDURATION,
-					   priv->pm_timeout);
-		if (err) {
-			printk(KERN_ERR "%s: Error %d setting up PM\n",
-			       dev->name, err);
-			return err;
-		}
-	}
-
-	/* Set preamble - only for Symbol so far... */
-	if (priv->has_preamble) {
-		err = hermes_write_wordrec(hw, USER_BAP,
-					   HERMES_RID_CNFPREAMBLE_SYMBOL,
-					   priv->preamble);
-		if (err) {
-			printk(KERN_ERR "%s: Error %d setting preamble\n",
-			       dev->name, err);
-			return err;
-		}
-	}
-
-	/* Set up encryption */
-	if (priv->has_wep || priv->has_wpa) {
-		err = __orinoco_hw_setup_enc(priv);
-		if (err) {
-			printk(KERN_ERR "%s: Error %d activating encryption\n",
-			       dev->name, err);
-			return err;
-		}
-	}
-
-	if (priv->iw_mode == NL80211_IFTYPE_MONITOR) {
-		/* Enable monitor mode */
-		dev->type = ARPHRD_IEEE80211;
-		err = hw->ops->cmd_wait(hw, HERMES_CMD_TEST |
-					    HERMES_TEST_MONITOR, 0, NULL);
-	} else {
-		/* Disable monitor mode */
-		dev->type = ARPHRD_ETHER;
-		err = hw->ops->cmd_wait(hw, HERMES_CMD_TEST |
-					    HERMES_TEST_STOP, 0, NULL);
-	}
-	if (err)
-		return err;
-
-	/* Reset promiscuity / multicast*/
-	priv->promiscuous = 0;
-	priv->mc_count = 0;
-
-	/* Record mode change */
-	wdev->iftype = priv->iw_mode;
-
-	return 0;
-}
-
-/* Get tsc from the firmware */
-int orinoco_hw_get_tkip_iv(struct orinoco_private *priv, int key, u8 *tsc)
-{
-	struct hermes *hw = &priv->hw;
-	int err = 0;
-	u8 tsc_arr[4][ORINOCO_SEQ_LEN];
-
-	if ((key < 0) || (key >= 4))
-		return -EINVAL;
-
-	err = hw->ops->read_ltv(hw, USER_BAP, HERMES_RID_CURRENT_TKIP_IV,
-				sizeof(tsc_arr), NULL, &tsc_arr);
-	if (!err)
-		memcpy(tsc, &tsc_arr[key][0], sizeof(tsc_arr[0]));
-
-	return err;
-}
-
-int __orinoco_hw_set_bitrate(struct orinoco_private *priv)
-{
-	struct hermes *hw = &priv->hw;
-	int ratemode = priv->bitratemode;
-	int err = 0;
-
-	if (ratemode >= BITRATE_TABLE_SIZE) {
-		printk(KERN_ERR "%s: BUG: Invalid bitrate mode %d\n",
-		       priv->ndev->name, ratemode);
-		return -EINVAL;
-	}
-
-	switch (priv->firmware_type) {
-	case FIRMWARE_TYPE_AGERE:
-		err = hermes_write_wordrec(hw, USER_BAP,
-				HERMES_RID_CNFTXRATECONTROL,
-				bitrate_table[ratemode].agere_txratectrl);
-		break;
-	case FIRMWARE_TYPE_INTERSIL:
-	case FIRMWARE_TYPE_SYMBOL:
-		err = hermes_write_wordrec(hw, USER_BAP,
-				HERMES_RID_CNFTXRATECONTROL,
-				bitrate_table[ratemode].intersil_txratectrl);
-		break;
-	default:
-		BUG();
-	}
-
-	return err;
-}
-
-int orinoco_hw_get_act_bitrate(struct orinoco_private *priv, int *bitrate)
-{
-	struct hermes *hw = &priv->hw;
-	int i;
-	int err = 0;
-	u16 val;
-
-	err = hermes_read_wordrec(hw, USER_BAP,
-				  HERMES_RID_CURRENTTXRATE, &val);
-	if (err)
-		return err;
-
-	switch (priv->firmware_type) {
-	case FIRMWARE_TYPE_AGERE: /* Lucent style rate */
-		/* Note : in Lucent firmware, the return value of
-		 * HERMES_RID_CURRENTTXRATE is the bitrate in Mb/s,
-		 * and therefore is totally different from the
-		 * encoding of HERMES_RID_CNFTXRATECONTROL.
-		 * Don't forget that 6Mb/s is really 5.5Mb/s */
-		if (val == 6)
-			*bitrate = 5500000;
-		else
-			*bitrate = val * 1000000;
-		break;
-	case FIRMWARE_TYPE_INTERSIL: /* Intersil style rate */
-	case FIRMWARE_TYPE_SYMBOL: /* Symbol style rate */
-		for (i = 0; i < BITRATE_TABLE_SIZE; i++)
-			if (bitrate_table[i].intersil_txratectrl == val) {
-				*bitrate = bitrate_table[i].bitrate * 100000;
-				break;
-			}
-
-		if (i >= BITRATE_TABLE_SIZE) {
-			printk(KERN_INFO "%s: Unable to determine current bitrate (0x%04hx)\n",
-			       priv->ndev->name, val);
-			err = -EIO;
-		}
-
-		break;
-	default:
-		BUG();
-	}
-
-	return err;
-}
-
-/* Set fixed AP address */
-int __orinoco_hw_set_wap(struct orinoco_private *priv)
-{
-	int roaming_flag;
-	int err = 0;
-	struct hermes *hw = &priv->hw;
-
-	switch (priv->firmware_type) {
-	case FIRMWARE_TYPE_AGERE:
-		/* not supported */
-		break;
-	case FIRMWARE_TYPE_INTERSIL:
-		if (priv->bssid_fixed)
-			roaming_flag = 2;
-		else
-			roaming_flag = 1;
-
-		err = hermes_write_wordrec(hw, USER_BAP,
-					   HERMES_RID_CNFROAMINGMODE,
-					   roaming_flag);
-		break;
-	case FIRMWARE_TYPE_SYMBOL:
-		err = HERMES_WRITE_RECORD(hw, USER_BAP,
-					  HERMES_RID_CNFMANDATORYBSSID_SYMBOL,
-					  &priv->desired_bssid);
-		break;
-	}
-	return err;
-}
-
-/* Change the WEP keys and/or the current keys.  Can be called
- * either from __orinoco_hw_setup_enc() or directly from
- * orinoco_ioctl_setiwencode().  In the later case the association
- * with the AP is not broken (if the firmware can handle it),
- * which is needed for 802.1x implementations. */
-int __orinoco_hw_setup_wepkeys(struct orinoco_private *priv)
-{
-	struct hermes *hw = &priv->hw;
-	int err = 0;
-	int i;
-
-	switch (priv->firmware_type) {
-	case FIRMWARE_TYPE_AGERE:
-	{
-		struct orinoco_key keys[ORINOCO_MAX_KEYS];
-
-		memset(&keys, 0, sizeof(keys));
-		for (i = 0; i < ORINOCO_MAX_KEYS; i++) {
-			int len = min(priv->keys[i].key_len,
-				      ORINOCO_MAX_KEY_SIZE);
-			memcpy(&keys[i].data, priv->keys[i].key, len);
-			if (len > SMALL_KEY_SIZE)
-				keys[i].len = cpu_to_le16(LARGE_KEY_SIZE);
-			else if (len > 0)
-				keys[i].len = cpu_to_le16(SMALL_KEY_SIZE);
-			else
-				keys[i].len = cpu_to_le16(0);
-		}
-
-		err = HERMES_WRITE_RECORD(hw, USER_BAP,
-					  HERMES_RID_CNFWEPKEYS_AGERE,
-					  &keys);
-		if (err)
-			return err;
-		err = hermes_write_wordrec(hw, USER_BAP,
-					   HERMES_RID_CNFTXKEY_AGERE,
-					   priv->tx_key);
-		if (err)
-			return err;
-		break;
-	}
-	case FIRMWARE_TYPE_INTERSIL:
-	case FIRMWARE_TYPE_SYMBOL:
-		{
-			int keylen;
-
-			/* Force uniform key length to work around
-			 * firmware bugs */
-			keylen = priv->keys[priv->tx_key].key_len;
-
-			if (keylen > LARGE_KEY_SIZE) {
-				printk(KERN_ERR "%s: BUG: Key %d has oversize length %d.\n",
-				       priv->ndev->name, priv->tx_key, keylen);
-				return -E2BIG;
-			} else if (keylen > SMALL_KEY_SIZE)
-				keylen = LARGE_KEY_SIZE;
-			else if (keylen > 0)
-				keylen = SMALL_KEY_SIZE;
-			else
-				keylen = 0;
-
-			/* Write all 4 keys */
-			for (i = 0; i < ORINOCO_MAX_KEYS; i++) {
-				u8 key[LARGE_KEY_SIZE] = { 0 };
-
-				memcpy(key, priv->keys[i].key,
-				       priv->keys[i].key_len);
-
-				err = hw->ops->write_ltv(hw, USER_BAP,
-						HERMES_RID_CNFDEFAULTKEY0 + i,
-						HERMES_BYTES_TO_RECLEN(keylen),
-						key);
-				if (err)
-					return err;
-			}
-
-			/* Write the index of the key used in transmission */
-			err = hermes_write_wordrec(hw, USER_BAP,
-						HERMES_RID_CNFWEPDEFAULTKEYID,
-						priv->tx_key);
-			if (err)
-				return err;
-		}
-		break;
-	}
-
-	return 0;
-}
-
-int __orinoco_hw_setup_enc(struct orinoco_private *priv)
-{
-	struct hermes *hw = &priv->hw;
-	int err = 0;
-	int master_wep_flag;
-	int auth_flag;
-	int enc_flag;
-
-	/* Setup WEP keys */
-	if (priv->encode_alg == ORINOCO_ALG_WEP)
-		__orinoco_hw_setup_wepkeys(priv);
-
-	if (priv->wep_restrict)
-		auth_flag = HERMES_AUTH_SHARED_KEY;
-	else
-		auth_flag = HERMES_AUTH_OPEN;
-
-	if (priv->wpa_enabled)
-		enc_flag = 2;
-	else if (priv->encode_alg == ORINOCO_ALG_WEP)
-		enc_flag = 1;
-	else
-		enc_flag = 0;
-
-	switch (priv->firmware_type) {
-	case FIRMWARE_TYPE_AGERE: /* Agere style WEP */
-		if (priv->encode_alg == ORINOCO_ALG_WEP) {
-			/* Enable the shared-key authentication. */
-			err = hermes_write_wordrec(hw, USER_BAP,
-					HERMES_RID_CNFAUTHENTICATION_AGERE,
-					auth_flag);
-			if (err)
-				return err;
-		}
-		err = hermes_write_wordrec(hw, USER_BAP,
-					   HERMES_RID_CNFWEPENABLED_AGERE,
-					   enc_flag);
-		if (err)
-			return err;
-
-		if (priv->has_wpa) {
-			/* Set WPA key management */
-			err = hermes_write_wordrec(hw, USER_BAP,
-				  HERMES_RID_CNFSETWPAAUTHMGMTSUITE_AGERE,
-				  priv->key_mgmt);
-			if (err)
-				return err;
-		}
-
-		break;
-
-	case FIRMWARE_TYPE_INTERSIL: /* Intersil style WEP */
-	case FIRMWARE_TYPE_SYMBOL: /* Symbol style WEP */
-		if (priv->encode_alg == ORINOCO_ALG_WEP) {
-			if (priv->wep_restrict ||
-			    (priv->firmware_type == FIRMWARE_TYPE_SYMBOL))
-				master_wep_flag = HERMES_WEP_PRIVACY_INVOKED |
-						  HERMES_WEP_EXCL_UNENCRYPTED;
-			else
-				master_wep_flag = HERMES_WEP_PRIVACY_INVOKED;
-
-			err = hermes_write_wordrec(hw, USER_BAP,
-						   HERMES_RID_CNFAUTHENTICATION,
-						   auth_flag);
-			if (err)
-				return err;
-		} else
-			master_wep_flag = 0;
-
-		if (priv->iw_mode == NL80211_IFTYPE_MONITOR)
-			master_wep_flag |= HERMES_WEP_HOST_DECRYPT;
-
-		/* Master WEP setting : on/off */
-		err = hermes_write_wordrec(hw, USER_BAP,
-					   HERMES_RID_CNFWEPFLAGS_INTERSIL,
-					   master_wep_flag);
-		if (err)
-			return err;
-
-		break;
-	}
-
-	return 0;
-}
-
-/* key must be 32 bytes, including the tx and rx MIC keys.
- * rsc must be NULL or up to 8 bytes
- * tsc must be NULL or up to 8 bytes
- */
-int __orinoco_hw_set_tkip_key(struct orinoco_private *priv, int key_idx,
-			      int set_tx, const u8 *key, size_t key_len,
-			      const u8 *rsc, size_t rsc_len,
-			      const u8 *tsc, size_t tsc_len)
-{
-	struct {
-		__le16 idx;
-		u8 rsc[ORINOCO_SEQ_LEN];
-		struct {
-			u8 key[TKIP_KEYLEN];
-			u8 tx_mic[MIC_KEYLEN];
-			u8 rx_mic[MIC_KEYLEN];
-		} tkip;
-		u8 tsc[ORINOCO_SEQ_LEN];
-	} __packed buf;
-	struct hermes *hw = &priv->hw;
-	int ret;
-	int err;
-	int k;
-	u16 xmitting;
-
-	key_idx &= 0x3;
-
-	if (set_tx)
-		key_idx |= 0x8000;
-
-	buf.idx = cpu_to_le16(key_idx);
-	if (key_len != sizeof(buf.tkip))
-		return -EINVAL;
-	memcpy(&buf.tkip, key, sizeof(buf.tkip));
-
-	if (rsc_len > sizeof(buf.rsc))
-		rsc_len = sizeof(buf.rsc);
-
-	if (tsc_len > sizeof(buf.tsc))
-		tsc_len = sizeof(buf.tsc);
-
-	memset(buf.rsc, 0, sizeof(buf.rsc));
-	memset(buf.tsc, 0, sizeof(buf.tsc));
-
-	if (rsc != NULL)
-		memcpy(buf.rsc, rsc, rsc_len);
-
-	if (tsc != NULL)
-		memcpy(buf.tsc, tsc, tsc_len);
-	else
-		buf.tsc[4] = 0x10;
-
-	/* Wait up to 100ms for tx queue to empty */
-	for (k = 100; k > 0; k--) {
-		udelay(1000);
-		ret = hermes_read_wordrec(hw, USER_BAP, HERMES_RID_TXQUEUEEMPTY,
-					  &xmitting);
-		if (ret || !xmitting)
-			break;
-	}
-
-	if (k == 0)
-		ret = -ETIMEDOUT;
-
-	err = HERMES_WRITE_RECORD(hw, USER_BAP,
-				  HERMES_RID_CNFADDDEFAULTTKIPKEY_AGERE,
-				  &buf);
-
-	return ret ? ret : err;
-}
-
-int orinoco_clear_tkip_key(struct orinoco_private *priv, int key_idx)
-{
-	struct hermes *hw = &priv->hw;
-	int err;
-
-	err = hermes_write_wordrec(hw, USER_BAP,
-				   HERMES_RID_CNFREMDEFAULTTKIPKEY_AGERE,
-				   key_idx);
-	if (err)
-		printk(KERN_WARNING "%s: Error %d clearing TKIP key %d\n",
-		       priv->ndev->name, err, key_idx);
-	return err;
-}
-
-int __orinoco_hw_set_multicast_list(struct orinoco_private *priv,
-				    struct net_device *dev,
-				    int mc_count, int promisc)
-{
-	struct hermes *hw = &priv->hw;
-	int err = 0;
-
-	if (promisc != priv->promiscuous) {
-		err = hermes_write_wordrec(hw, USER_BAP,
-					   HERMES_RID_CNFPROMISCUOUSMODE,
-					   promisc);
-		if (err) {
-			printk(KERN_ERR "%s: Error %d setting PROMISCUOUSMODE to 1.\n",
-			       priv->ndev->name, err);
-		} else
-			priv->promiscuous = promisc;
-	}
-
-	/* If we're not in promiscuous mode, then we need to set the
-	 * group address if either we want to multicast, or if we were
-	 * multicasting and want to stop */
-	if (!promisc && (mc_count || priv->mc_count)) {
-		struct netdev_hw_addr *ha;
-		struct hermes_multicast mclist;
-		int i = 0;
-
-		netdev_for_each_mc_addr(ha, dev) {
-			if (i == mc_count)
-				break;
-			memcpy(mclist.addr[i++], ha->addr, ETH_ALEN);
-		}
-
-		err = hw->ops->write_ltv(hw, USER_BAP,
-				   HERMES_RID_CNFGROUPADDRESSES,
-				   HERMES_BYTES_TO_RECLEN(mc_count * ETH_ALEN),
-				   &mclist);
-		if (err)
-			printk(KERN_ERR "%s: Error %d setting multicast list.\n",
-			       priv->ndev->name, err);
-		else
-			priv->mc_count = mc_count;
-	}
-	return err;
-}
-
-/* Return : < 0 -> error code ; >= 0 -> length */
-int orinoco_hw_get_essid(struct orinoco_private *priv, int *active,
-			 char buf[IW_ESSID_MAX_SIZE + 1])
-{
-	struct hermes *hw = &priv->hw;
-	int err = 0;
-	struct hermes_idstring essidbuf;
-	char *p = (char *)(&essidbuf.val);
-	int len;
-	unsigned long flags;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	if (strlen(priv->desired_essid) > 0) {
-		/* We read the desired SSID from the hardware rather
-		   than from priv->desired_essid, just in case the
-		   firmware is allowed to change it on us. I'm not
-		   sure about this */
-		/* My guess is that the OWNSSID should always be whatever
-		 * we set to the card, whereas CURRENT_SSID is the one that
-		 * may change... - Jean II */
-		u16 rid;
-
-		*active = 1;
-
-		rid = (priv->port_type == 3) ? HERMES_RID_CNFOWNSSID :
-			HERMES_RID_CNFDESIREDSSID;
-
-		err = hw->ops->read_ltv(hw, USER_BAP, rid, sizeof(essidbuf),
-					NULL, &essidbuf);
-		if (err)
-			goto fail_unlock;
-	} else {
-		*active = 0;
-
-		err = hw->ops->read_ltv(hw, USER_BAP, HERMES_RID_CURRENTSSID,
-					sizeof(essidbuf), NULL, &essidbuf);
-		if (err)
-			goto fail_unlock;
-	}
-
-	len = le16_to_cpu(essidbuf.len);
-	BUG_ON(len > IW_ESSID_MAX_SIZE);
-
-	memset(buf, 0, IW_ESSID_MAX_SIZE);
-	memcpy(buf, p, len);
-	err = len;
-
- fail_unlock:
-	orinoco_unlock(priv, &flags);
-
-	return err;
-}
-
-int orinoco_hw_get_freq(struct orinoco_private *priv)
-{
-	struct hermes *hw = &priv->hw;
-	int err = 0;
-	u16 channel;
-	int freq = 0;
-	unsigned long flags;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	err = hermes_read_wordrec(hw, USER_BAP, HERMES_RID_CURRENTCHANNEL,
-				  &channel);
-	if (err)
-		goto out;
-
-	/* Intersil firmware 1.3.5 returns 0 when the interface is down */
-	if (channel == 0) {
-		err = -EBUSY;
-		goto out;
-	}
-
-	if ((channel < 1) || (channel > NUM_CHANNELS)) {
-		printk(KERN_WARNING "%s: Channel out of range (%d)!\n",
-		       priv->ndev->name, channel);
-		err = -EBUSY;
-		goto out;
-
-	}
-	freq = ieee80211_channel_to_frequency(channel, NL80211_BAND_2GHZ);
-
- out:
-	orinoco_unlock(priv, &flags);
-
-	if (err > 0)
-		err = -EBUSY;
-	return err ? err : freq;
-}
-
-int orinoco_hw_get_bitratelist(struct orinoco_private *priv,
-			       int *numrates, s32 *rates, int max)
-{
-	struct hermes *hw = &priv->hw;
-	struct hermes_idstring list;
-	unsigned char *p = (unsigned char *)&list.val;
-	int err = 0;
-	int num;
-	int i;
-	unsigned long flags;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	err = hw->ops->read_ltv(hw, USER_BAP, HERMES_RID_SUPPORTEDDATARATES,
-				sizeof(list), NULL, &list);
-	orinoco_unlock(priv, &flags);
-
-	if (err)
-		return err;
-
-	num = le16_to_cpu(list.len);
-	*numrates = num;
-	num = min(num, max);
-
-	for (i = 0; i < num; i++)
-		rates[i] = (p[i] & 0x7f) * 500000; /* convert to bps */
-
-	return 0;
-}
-
-int orinoco_hw_trigger_scan(struct orinoco_private *priv,
-			    const struct cfg80211_ssid *ssid)
-{
-	struct net_device *dev = priv->ndev;
-	struct hermes *hw = &priv->hw;
-	unsigned long flags;
-	int err = 0;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	/* Scanning with port 0 disabled would fail */
-	if (!netif_running(dev)) {
-		err = -ENETDOWN;
-		goto out;
-	}
-
-	/* In monitor mode, the scan results are always empty.
-	 * Probe responses are passed to the driver as received
-	 * frames and could be processed in software. */
-	if (priv->iw_mode == NL80211_IFTYPE_MONITOR) {
-		err = -EOPNOTSUPP;
-		goto out;
-	}
-
-	if (priv->has_hostscan) {
-		switch (priv->firmware_type) {
-		case FIRMWARE_TYPE_SYMBOL:
-			err = hermes_write_wordrec(hw, USER_BAP,
-						HERMES_RID_CNFHOSTSCAN_SYMBOL,
-						HERMES_HOSTSCAN_SYMBOL_ONCE |
-						HERMES_HOSTSCAN_SYMBOL_BCAST);
-			break;
-		case FIRMWARE_TYPE_INTERSIL: {
-			__le16 req[3];
-
-			req[0] = cpu_to_le16(0x3fff);	/* All channels */
-			req[1] = cpu_to_le16(0x0001);	/* rate 1 Mbps */
-			req[2] = 0;			/* Any ESSID */
-			err = HERMES_WRITE_RECORD(hw, USER_BAP,
-						  HERMES_RID_CNFHOSTSCAN, &req);
-			break;
-		}
-		case FIRMWARE_TYPE_AGERE:
-			if (ssid->ssid_len > 0) {
-				struct hermes_idstring idbuf;
-				size_t len = ssid->ssid_len;
-
-				idbuf.len = cpu_to_le16(len);
-				memcpy(idbuf.val, ssid->ssid, len);
-
-				err = hw->ops->write_ltv(hw, USER_BAP,
-					       HERMES_RID_CNFSCANSSID_AGERE,
-					       HERMES_BYTES_TO_RECLEN(len + 2),
-					       &idbuf);
-			} else
-				err = hermes_write_wordrec(hw, USER_BAP,
-						   HERMES_RID_CNFSCANSSID_AGERE,
-						   0);	/* Any ESSID */
-			if (err)
-				break;
-
-			if (priv->has_ext_scan) {
-				err = hermes_write_wordrec(hw, USER_BAP,
-						HERMES_RID_CNFSCANCHANNELS2GHZ,
-						0x7FFF);
-				if (err)
-					goto out;
-
-				err = hermes_inquire(hw,
-						     HERMES_INQ_CHANNELINFO);
-			} else
-				err = hermes_inquire(hw, HERMES_INQ_SCAN);
-
-			break;
-		}
-	} else
-		err = hermes_inquire(hw, HERMES_INQ_SCAN);
-
- out:
-	orinoco_unlock(priv, &flags);
-
-	return err;
-}
-
-/* Disassociate from node with BSSID addr */
-int orinoco_hw_disassociate(struct orinoco_private *priv,
-			    u8 *addr, u16 reason_code)
-{
-	struct hermes *hw = &priv->hw;
-	int err;
-
-	struct {
-		u8 addr[ETH_ALEN];
-		__le16 reason_code;
-	} __packed buf;
-
-	/* Currently only supported by WPA enabled Agere fw */
-	if (!priv->has_wpa)
-		return -EOPNOTSUPP;
-
-	memcpy(buf.addr, addr, ETH_ALEN);
-	buf.reason_code = cpu_to_le16(reason_code);
-	err = HERMES_WRITE_RECORD(hw, USER_BAP,
-				  HERMES_RID_CNFDISASSOCIATE,
-				  &buf);
-	return err;
-}
-
-int orinoco_hw_get_current_bssid(struct orinoco_private *priv,
-				 u8 *addr)
-{
-	struct hermes *hw = &priv->hw;
-	int err;
-
-	err = hw->ops->read_ltv(hw, USER_BAP, HERMES_RID_CURRENTBSSID,
-				ETH_ALEN, NULL, addr);
-
-	return err;
-}
diff --git a/drivers/net/wireless/intersil/orinoco/hw.h b/drivers/net/wireless/intersil/orinoco/hw.h
deleted file mode 100644
index da5804dbdf34..000000000000
--- a/drivers/net/wireless/intersil/orinoco/hw.h
+++ /dev/null
@@ -1,60 +0,0 @@
-/* Encapsulate basic setting changes on Hermes hardware
- *
- * See copyright notice in main.c
- */
-#ifndef _ORINOCO_HW_H_
-#define _ORINOCO_HW_H_
-
-#include <linux/types.h>
-#include <linux/wireless.h>
-#include <net/cfg80211.h>
-
-/* Hardware BAPs */
-#define USER_BAP 0
-#define IRQ_BAP  1
-
-/* WEP key sizes */
-#define SMALL_KEY_SIZE 5
-#define LARGE_KEY_SIZE 13
-
-/* Number of supported channels */
-#define NUM_CHANNELS 14
-
-/* Forward declarations */
-struct orinoco_private;
-
-int determine_fw_capabilities(struct orinoco_private *priv, char *fw_name,
-			      size_t fw_name_len, u32 *hw_ver);
-int orinoco_hw_read_card_settings(struct orinoco_private *priv, u8 *dev_addr);
-int orinoco_hw_allocate_fid(struct orinoco_private *priv);
-int orinoco_get_bitratemode(int bitrate, int automatic);
-void orinoco_get_ratemode_cfg(int ratemode, int *bitrate, int *automatic);
-
-int orinoco_hw_program_rids(struct orinoco_private *priv);
-int orinoco_hw_get_tkip_iv(struct orinoco_private *priv, int key, u8 *tsc);
-int __orinoco_hw_set_bitrate(struct orinoco_private *priv);
-int orinoco_hw_get_act_bitrate(struct orinoco_private *priv, int *bitrate);
-int __orinoco_hw_set_wap(struct orinoco_private *priv);
-int __orinoco_hw_setup_wepkeys(struct orinoco_private *priv);
-int __orinoco_hw_setup_enc(struct orinoco_private *priv);
-int __orinoco_hw_set_tkip_key(struct orinoco_private *priv, int key_idx,
-			      int set_tx, const u8 *key, size_t key_len,
-			      const u8 *rsc, size_t rsc_len,
-			      const u8 *tsc, size_t tsc_len);
-int orinoco_clear_tkip_key(struct orinoco_private *priv, int key_idx);
-int __orinoco_hw_set_multicast_list(struct orinoco_private *priv,
-				    struct net_device *dev,
-				    int mc_count, int promisc);
-int orinoco_hw_get_essid(struct orinoco_private *priv, int *active,
-			 char buf[IW_ESSID_MAX_SIZE + 1]);
-int orinoco_hw_get_freq(struct orinoco_private *priv);
-int orinoco_hw_get_bitratelist(struct orinoco_private *priv,
-			       int *numrates, s32 *rates, int max);
-int orinoco_hw_trigger_scan(struct orinoco_private *priv,
-			    const struct cfg80211_ssid *ssid);
-int orinoco_hw_disassociate(struct orinoco_private *priv,
-			    u8 *addr, u16 reason_code);
-int orinoco_hw_get_current_bssid(struct orinoco_private *priv,
-				 u8 *addr);
-
-#endif /* _ORINOCO_HW_H_ */
diff --git a/drivers/net/wireless/intersil/orinoco/main.c b/drivers/net/wireless/intersil/orinoco/main.c
deleted file mode 100644
index 7df88d20ff3d..000000000000
--- a/drivers/net/wireless/intersil/orinoco/main.c
+++ /dev/null
@@ -1,2414 +0,0 @@
-/* main.c - (formerly known as dldwd_cs.c, orinoco_cs.c and orinoco.c)
- *
- * A driver for Hermes or Prism 2 chipset based PCMCIA wireless
- * adaptors, with Lucent/Agere, Intersil or Symbol firmware.
- *
- * Current maintainers (as of 29 September 2003) are:
- *	Pavel Roskin <proski AT gnu.org>
- * and	David Gibson <hermes AT gibson.dropbear.id.au>
- *
- * (C) Copyright David Gibson, IBM Corporation 2001-2003.
- * Copyright (C) 2000 David Gibson, Linuxcare Australia.
- *	With some help from :
- * Copyright (C) 2001 Jean Tourrilhes, HP Labs
- * Copyright (C) 2001 Benjamin Herrenschmidt
- *
- * Based on dummy_cs.c 1.27 2000/06/12 21:27:25
- *
- * Portions based on wvlan_cs.c 1.0.6, Copyright Andreas Neuhaus <andy
- * AT fasta.fh-dortmund.de>
- *      http://www.stud.fh-dortmund.de/~andy/wvlan/
- *
- * The contents of this file are subject to the Mozilla Public License
- * Version 1.1 (the "License"); you may not use this file except in
- * compliance with the License. You may obtain a copy of the License
- * at http://www.mozilla.org/MPL/
- *
- * Software distributed under the License is distributed on an "AS IS"
- * basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See
- * the License for the specific language governing rights and
- * limitations under the License.
- *
- * The initial developer of the original code is David A. Hinds
- * <dahinds AT users.sourceforge.net>.  Portions created by David
- * A. Hinds are Copyright (C) 1999 David A. Hinds.  All Rights
- * Reserved.
- *
- * Alternatively, the contents of this file may be used under the
- * terms of the GNU General Public License version 2 (the "GPL"), in
- * which case the provisions of the GPL are applicable instead of the
- * above.  If you wish to allow the use of your version of this file
- * only under the terms of the GPL and not to allow others to use your
- * version of this file under the MPL, indicate your decision by
- * deleting the provisions above and replace them with the notice and
- * other provisions required by the GPL.  If you do not delete the
- * provisions above, a recipient may use your version of this file
- * under either the MPL or the GPL.  */
-
-/*
- * TODO
- *	o Handle de-encapsulation within network layer, provide 802.11
- *	  headers (patch from Thomas 'Dent' Mirlacher)
- *	o Fix possible races in SPY handling.
- *	o Disconnect wireless extensions from fundamental configuration.
- *	o (maybe) Software WEP support (patch from Stano Meduna).
- *	o (maybe) Use multiple Tx buffers - driver handling queue
- *	  rather than firmware.
- */
-
-/* Locking and synchronization:
- *
- * The basic principle is that everything is serialized through a
- * single spinlock, priv->lock.  The lock is used in user, bh and irq
- * context, so when taken outside hardirq context it should always be
- * taken with interrupts disabled.  The lock protects both the
- * hardware and the struct orinoco_private.
- *
- * Another flag, priv->hw_unavailable indicates that the hardware is
- * unavailable for an extended period of time (e.g. suspended, or in
- * the middle of a hard reset).  This flag is protected by the
- * spinlock.  All code which touches the hardware should check the
- * flag after taking the lock, and if it is set, give up on whatever
- * they are doing and drop the lock again.  The orinoco_lock()
- * function handles this (it unlocks and returns -EBUSY if
- * hw_unavailable is non-zero).
- */
-
-#define DRIVER_NAME "orinoco"
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/device.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/suspend.h>
-#include <linux/if_arp.h>
-#include <linux/wireless.h>
-#include <linux/ieee80211.h>
-#include <net/iw_handler.h>
-#include <net/cfg80211.h>
-
-#include "hermes_rid.h"
-#include "hermes_dld.h"
-#include "hw.h"
-#include "scan.h"
-#include "mic.h"
-#include "fw.h"
-#include "wext.h"
-#include "cfg.h"
-#include "main.h"
-
-#include "orinoco.h"
-
-/********************************************************************/
-/* Module information                                               */
-/********************************************************************/
-
-MODULE_AUTHOR("Pavel Roskin <proski@gnu.org> & "
-	      "David Gibson <hermes@gibson.dropbear.id.au>");
-MODULE_DESCRIPTION("Driver for Lucent Orinoco, Prism II based "
-		   "and similar wireless cards");
-MODULE_LICENSE("Dual MPL/GPL");
-
-/* Level of debugging. Used in the macros in orinoco.h */
-#ifdef ORINOCO_DEBUG
-int orinoco_debug = ORINOCO_DEBUG;
-EXPORT_SYMBOL(orinoco_debug);
-module_param(orinoco_debug, int, 0644);
-MODULE_PARM_DESC(orinoco_debug, "Debug level");
-#endif
-
-static bool suppress_linkstatus; /* = 0 */
-module_param(suppress_linkstatus, bool, 0644);
-MODULE_PARM_DESC(suppress_linkstatus, "Don't log link status changes");
-
-static int ignore_disconnect; /* = 0 */
-module_param(ignore_disconnect, int, 0644);
-MODULE_PARM_DESC(ignore_disconnect,
-		 "Don't report lost link to the network layer");
-
-int force_monitor; /* = 0 */
-module_param(force_monitor, int, 0644);
-MODULE_PARM_DESC(force_monitor, "Allow monitor mode for all firmware versions");
-
-/********************************************************************/
-/* Internal constants                                               */
-/********************************************************************/
-
-/* 802.2 LLC/SNAP header used for Ethernet encapsulation over 802.11 */
-static const u8 encaps_hdr[] = {0xaa, 0xaa, 0x03, 0x00, 0x00, 0x00};
-#define ENCAPS_OVERHEAD		(sizeof(encaps_hdr) + 2)
-
-#define ORINOCO_MIN_MTU		256
-#define ORINOCO_MAX_MTU		(IEEE80211_MAX_DATA_LEN - ENCAPS_OVERHEAD)
-
-#define MAX_IRQLOOPS_PER_IRQ	10
-#define MAX_IRQLOOPS_PER_JIFFY	(20000 / HZ)	/* Based on a guestimate of
-						 * how many events the
-						 * device could
-						 * legitimately generate */
-
-#define DUMMY_FID		0xFFFF
-
-/*#define MAX_MULTICAST(priv)	(priv->firmware_type == FIRMWARE_TYPE_AGERE ? \
-  HERMES_MAX_MULTICAST : 0)*/
-#define MAX_MULTICAST(priv)	(HERMES_MAX_MULTICAST)
-
-#define ORINOCO_INTEN		(HERMES_EV_RX | HERMES_EV_ALLOC \
-				 | HERMES_EV_TX | HERMES_EV_TXEXC \
-				 | HERMES_EV_WTERR | HERMES_EV_INFO \
-				 | HERMES_EV_INFDROP)
-
-/********************************************************************/
-/* Data types                                                       */
-/********************************************************************/
-
-/* Beginning of the Tx descriptor, used in TxExc handling */
-struct hermes_txexc_data {
-	struct hermes_tx_descriptor desc;
-	__le16 frame_ctl;
-	__le16 duration_id;
-	u8 addr1[ETH_ALEN];
-} __packed;
-
-/* Rx frame header except compatibility 802.3 header */
-struct hermes_rx_descriptor {
-	/* Control */
-	__le16 status;
-	__le32 time;
-	u8 silence;
-	u8 signal;
-	u8 rate;
-	u8 rxflow;
-	__le32 reserved;
-
-	/* 802.11 header */
-	__le16 frame_ctl;
-	__le16 duration_id;
-	u8 addr1[ETH_ALEN];
-	u8 addr2[ETH_ALEN];
-	u8 addr3[ETH_ALEN];
-	__le16 seq_ctl;
-	u8 addr4[ETH_ALEN];
-
-	/* Data length */
-	__le16 data_len;
-} __packed;
-
-struct orinoco_rx_data {
-	struct hermes_rx_descriptor *desc;
-	struct sk_buff *skb;
-	struct list_head list;
-};
-
-struct orinoco_scan_data {
-	void *buf;
-	size_t len;
-	int type;
-	struct list_head list;
-};
-
-/********************************************************************/
-/* Function prototypes                                              */
-/********************************************************************/
-
-static int __orinoco_set_multicast_list(struct net_device *dev);
-static int __orinoco_up(struct orinoco_private *priv);
-static int __orinoco_down(struct orinoco_private *priv);
-static int __orinoco_commit(struct orinoco_private *priv);
-
-/********************************************************************/
-/* Internal helper functions                                        */
-/********************************************************************/
-
-void set_port_type(struct orinoco_private *priv)
-{
-	switch (priv->iw_mode) {
-	case NL80211_IFTYPE_STATION:
-		priv->port_type = 1;
-		priv->createibss = 0;
-		break;
-	case NL80211_IFTYPE_ADHOC:
-		if (priv->prefer_port3) {
-			priv->port_type = 3;
-			priv->createibss = 0;
-		} else {
-			priv->port_type = priv->ibss_port;
-			priv->createibss = 1;
-		}
-		break;
-	case NL80211_IFTYPE_MONITOR:
-		priv->port_type = 3;
-		priv->createibss = 0;
-		break;
-	default:
-		printk(KERN_ERR "%s: Invalid priv->iw_mode in set_port_type()\n",
-		       priv->ndev->name);
-	}
-}
-
-/********************************************************************/
-/* Device methods                                                   */
-/********************************************************************/
-
-int orinoco_open(struct net_device *dev)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	unsigned long flags;
-	int err;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	err = __orinoco_up(priv);
-
-	if (!err)
-		priv->open = 1;
-
-	orinoco_unlock(priv, &flags);
-
-	return err;
-}
-EXPORT_SYMBOL(orinoco_open);
-
-int orinoco_stop(struct net_device *dev)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	int err = 0;
-
-	/* We mustn't use orinoco_lock() here, because we need to be
-	   able to close the interface even if hw_unavailable is set
-	   (e.g. as we're released after a PC Card removal) */
-	orinoco_lock_irq(priv);
-
-	priv->open = 0;
-
-	err = __orinoco_down(priv);
-
-	orinoco_unlock_irq(priv);
-
-	return err;
-}
-EXPORT_SYMBOL(orinoco_stop);
-
-void orinoco_set_multicast_list(struct net_device *dev)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	unsigned long flags;
-
-	if (orinoco_lock(priv, &flags) != 0) {
-		printk(KERN_DEBUG "%s: orinoco_set_multicast_list() "
-		       "called when hw_unavailable\n", dev->name);
-		return;
-	}
-
-	__orinoco_set_multicast_list(dev);
-	orinoco_unlock(priv, &flags);
-}
-EXPORT_SYMBOL(orinoco_set_multicast_list);
-
-int orinoco_change_mtu(struct net_device *dev, int new_mtu)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-
-	/* MTU + encapsulation + header length */
-	if ((new_mtu + ENCAPS_OVERHEAD + sizeof(struct ieee80211_hdr)) >
-	     (priv->nicbuf_size - ETH_HLEN))
-		return -EINVAL;
-
-	dev->mtu = new_mtu;
-
-	return 0;
-}
-EXPORT_SYMBOL(orinoco_change_mtu);
-
-/********************************************************************/
-/* Tx path                                                          */
-/********************************************************************/
-
-/* Add encapsulation and MIC to the existing SKB.
- * The main xmit routine will then send the whole lot to the card.
- * Need 8 bytes headroom
- * Need 8 bytes tailroom
- *
- *                          With encapsulated ethernet II frame
- *                          --------
- *                          803.3 header (14 bytes)
- *                           dst[6]
- * --------                  src[6]
- * 803.3 header (14 bytes)   len[2]
- *  dst[6]                  803.2 header (8 bytes)
- *  src[6]                   encaps[6]
- *  len[2] <- leave alone -> len[2]
- * --------                 -------- <-- 0
- * Payload                  Payload
- * ...                      ...
- *
- * --------                 --------
- *                          MIC (8 bytes)
- *                          --------
- *
- * returns 0 on success, -ENOMEM on error.
- */
-int orinoco_process_xmit_skb(struct sk_buff *skb,
-			     struct net_device *dev,
-			     struct orinoco_private *priv,
-			     int *tx_control,
-			     u8 *mic_buf)
-{
-	struct orinoco_tkip_key *key;
-	struct ethhdr *eh;
-	int do_mic;
-
-	key = (struct orinoco_tkip_key *) priv->keys[priv->tx_key].key;
-
-	do_mic = ((priv->encode_alg == ORINOCO_ALG_TKIP) &&
-		  (key != NULL));
-
-	if (do_mic)
-		*tx_control |= (priv->tx_key << HERMES_MIC_KEY_ID_SHIFT) |
-			HERMES_TXCTRL_MIC;
-
-	eh = (struct ethhdr *)skb->data;
-
-	/* Encapsulate Ethernet-II frames */
-	if (ntohs(eh->h_proto) > ETH_DATA_LEN) { /* Ethernet-II frame */
-		struct header_struct {
-			struct ethhdr eth;	/* 802.3 header */
-			u8 encap[6];		/* 802.2 header */
-		} __packed hdr;
-		int len = skb->len + sizeof(encaps_hdr) - (2 * ETH_ALEN);
-
-		if (skb_headroom(skb) < ENCAPS_OVERHEAD) {
-			if (net_ratelimit())
-				printk(KERN_ERR
-				       "%s: Not enough headroom for 802.2 headers %d\n",
-				       dev->name, skb_headroom(skb));
-			return -ENOMEM;
-		}
-
-		/* Fill in new header */
-		memcpy(&hdr.eth, eh, 2 * ETH_ALEN);
-		hdr.eth.h_proto = htons(len);
-		memcpy(hdr.encap, encaps_hdr, sizeof(encaps_hdr));
-
-		/* Make room for the new header, and copy it in */
-		eh = skb_push(skb, ENCAPS_OVERHEAD);
-		memcpy(eh, &hdr, sizeof(hdr));
-	}
-
-	/* Calculate Michael MIC */
-	if (do_mic) {
-		size_t len = skb->len - ETH_HLEN;
-		u8 *mic = &mic_buf[0];
-
-		/* Have to write to an even address, so copy the spare
-		 * byte across */
-		if (skb->len % 2) {
-			*mic = skb->data[skb->len - 1];
-			mic++;
-		}
-
-		orinoco_mic(priv->tx_tfm_mic, key->tx_mic,
-			    eh->h_dest, eh->h_source, 0 /* priority */,
-			    skb->data + ETH_HLEN,
-			    len, mic);
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(orinoco_process_xmit_skb);
-
-static netdev_tx_t orinoco_xmit(struct sk_buff *skb, struct net_device *dev)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	struct net_device_stats *stats = &dev->stats;
-	struct hermes *hw = &priv->hw;
-	int err = 0;
-	u16 txfid = priv->txfid;
-	int tx_control;
-	unsigned long flags;
-	u8 mic_buf[MICHAEL_MIC_LEN + 1];
-
-	if (!netif_running(dev)) {
-		printk(KERN_ERR "%s: Tx on stopped device!\n",
-		       dev->name);
-		return NETDEV_TX_BUSY;
-	}
-
-	if (netif_queue_stopped(dev)) {
-		printk(KERN_DEBUG "%s: Tx while transmitter busy!\n",
-		       dev->name);
-		return NETDEV_TX_BUSY;
-	}
-
-	if (orinoco_lock(priv, &flags) != 0) {
-		printk(KERN_ERR "%s: orinoco_xmit() called while hw_unavailable\n",
-		       dev->name);
-		return NETDEV_TX_BUSY;
-	}
-
-	if (!netif_carrier_ok(dev) ||
-	    (priv->iw_mode == NL80211_IFTYPE_MONITOR)) {
-		/* Oops, the firmware hasn't established a connection,
-		   silently drop the packet (this seems to be the
-		   safest approach). */
-		goto drop;
-	}
-
-	/* Check packet length */
-	if (skb->len < ETH_HLEN)
-		goto drop;
-
-	tx_control = HERMES_TXCTRL_TX_OK | HERMES_TXCTRL_TX_EX;
-
-	err = orinoco_process_xmit_skb(skb, dev, priv, &tx_control,
-				       &mic_buf[0]);
-	if (err)
-		goto drop;
-
-	if (priv->has_alt_txcntl) {
-		/* WPA enabled firmwares have tx_cntl at the end of
-		 * the 802.11 header.  So write zeroed descriptor and
-		 * 802.11 header at the same time
-		 */
-		char desc[HERMES_802_3_OFFSET];
-		__le16 *txcntl = (__le16 *) &desc[HERMES_TXCNTL2_OFFSET];
-
-		memset(&desc, 0, sizeof(desc));
-
-		*txcntl = cpu_to_le16(tx_control);
-		err = hw->ops->bap_pwrite(hw, USER_BAP, &desc, sizeof(desc),
-					  txfid, 0);
-		if (err) {
-			if (net_ratelimit())
-				printk(KERN_ERR "%s: Error %d writing Tx "
-				       "descriptor to BAP\n", dev->name, err);
-			goto busy;
-		}
-	} else {
-		struct hermes_tx_descriptor desc;
-
-		memset(&desc, 0, sizeof(desc));
-
-		desc.tx_control = cpu_to_le16(tx_control);
-		err = hw->ops->bap_pwrite(hw, USER_BAP, &desc, sizeof(desc),
-					  txfid, 0);
-		if (err) {
-			if (net_ratelimit())
-				printk(KERN_ERR "%s: Error %d writing Tx "
-				       "descriptor to BAP\n", dev->name, err);
-			goto busy;
-		}
-
-		/* Clear the 802.11 header and data length fields - some
-		 * firmwares (e.g. Lucent/Agere 8.xx) appear to get confused
-		 * if this isn't done. */
-		hermes_clear_words(hw, HERMES_DATA0,
-				   HERMES_802_3_OFFSET - HERMES_802_11_OFFSET);
-	}
-
-	err = hw->ops->bap_pwrite(hw, USER_BAP, skb->data, skb->len,
-				  txfid, HERMES_802_3_OFFSET);
-	if (err) {
-		printk(KERN_ERR "%s: Error %d writing packet to BAP\n",
-		       dev->name, err);
-		goto busy;
-	}
-
-	if (tx_control & HERMES_TXCTRL_MIC) {
-		size_t offset = HERMES_802_3_OFFSET + skb->len;
-		size_t len = MICHAEL_MIC_LEN;
-
-		if (offset % 2) {
-			offset--;
-			len++;
-		}
-		err = hw->ops->bap_pwrite(hw, USER_BAP, &mic_buf[0], len,
-					  txfid, offset);
-		if (err) {
-			printk(KERN_ERR "%s: Error %d writing MIC to BAP\n",
-			       dev->name, err);
-			goto busy;
-		}
-	}
-
-	/* Finally, we actually initiate the send */
-	netif_stop_queue(dev);
-
-	err = hw->ops->cmd_wait(hw, HERMES_CMD_TX | HERMES_CMD_RECL,
-				txfid, NULL);
-	if (err) {
-		netif_start_queue(dev);
-		if (net_ratelimit())
-			printk(KERN_ERR "%s: Error %d transmitting packet\n",
-				dev->name, err);
-		goto busy;
-	}
-
-	stats->tx_bytes += HERMES_802_3_OFFSET + skb->len;
-	goto ok;
-
- drop:
-	stats->tx_errors++;
-	stats->tx_dropped++;
-
- ok:
-	orinoco_unlock(priv, &flags);
-	dev_kfree_skb(skb);
-	return NETDEV_TX_OK;
-
- busy:
-	if (err == -EIO)
-		schedule_work(&priv->reset_work);
-	orinoco_unlock(priv, &flags);
-	return NETDEV_TX_BUSY;
-}
-
-static void __orinoco_ev_alloc(struct net_device *dev, struct hermes *hw)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	u16 fid = hermes_read_regn(hw, ALLOCFID);
-
-	if (fid != priv->txfid) {
-		if (fid != DUMMY_FID)
-			printk(KERN_WARNING "%s: Allocate event on unexpected fid (%04X)\n",
-			       dev->name, fid);
-		return;
-	}
-
-	hermes_write_regn(hw, ALLOCFID, DUMMY_FID);
-}
-
-static void __orinoco_ev_tx(struct net_device *dev, struct hermes *hw)
-{
-	dev->stats.tx_packets++;
-
-	netif_wake_queue(dev);
-
-	hermes_write_regn(hw, TXCOMPLFID, DUMMY_FID);
-}
-
-static void __orinoco_ev_txexc(struct net_device *dev, struct hermes *hw)
-{
-	struct net_device_stats *stats = &dev->stats;
-	u16 fid = hermes_read_regn(hw, TXCOMPLFID);
-	u16 status;
-	struct hermes_txexc_data hdr;
-	int err = 0;
-
-	if (fid == DUMMY_FID)
-		return; /* Nothing's really happened */
-
-	/* Read part of the frame header - we need status and addr1 */
-	err = hw->ops->bap_pread(hw, IRQ_BAP, &hdr,
-				 sizeof(struct hermes_txexc_data),
-				 fid, 0);
-
-	hermes_write_regn(hw, TXCOMPLFID, DUMMY_FID);
-	stats->tx_errors++;
-
-	if (err) {
-		printk(KERN_WARNING "%s: Unable to read descriptor on Tx error "
-		       "(FID=%04X error %d)\n",
-		       dev->name, fid, err);
-		return;
-	}
-
-	DEBUG(1, "%s: Tx error, err %d (FID=%04X)\n", dev->name,
-	      err, fid);
-
-	/* We produce a TXDROP event only for retry or lifetime
-	 * exceeded, because that's the only status that really mean
-	 * that this particular node went away.
-	 * Other errors means that *we* screwed up. - Jean II */
-	status = le16_to_cpu(hdr.desc.status);
-	if (status & (HERMES_TXSTAT_RETRYERR | HERMES_TXSTAT_AGEDERR)) {
-		union iwreq_data	wrqu;
-
-		/* Copy 802.11 dest address.
-		 * We use the 802.11 header because the frame may
-		 * not be 802.3 or may be mangled...
-		 * In Ad-Hoc mode, it will be the node address.
-		 * In managed mode, it will be most likely the AP addr
-		 * User space will figure out how to convert it to
-		 * whatever it needs (IP address or else).
-		 * - Jean II */
-		memcpy(wrqu.addr.sa_data, hdr.addr1, ETH_ALEN);
-		wrqu.addr.sa_family = ARPHRD_ETHER;
-
-		/* Send event to user space */
-		wireless_send_event(dev, IWEVTXDROP, &wrqu, NULL);
-	}
-
-	netif_wake_queue(dev);
-}
-
-void orinoco_tx_timeout(struct net_device *dev, unsigned int txqueue)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	struct net_device_stats *stats = &dev->stats;
-	struct hermes *hw = &priv->hw;
-
-	printk(KERN_WARNING "%s: Tx timeout! "
-	       "ALLOCFID=%04x, TXCOMPLFID=%04x, EVSTAT=%04x\n",
-	       dev->name, hermes_read_regn(hw, ALLOCFID),
-	       hermes_read_regn(hw, TXCOMPLFID), hermes_read_regn(hw, EVSTAT));
-
-	stats->tx_errors++;
-
-	schedule_work(&priv->reset_work);
-}
-EXPORT_SYMBOL(orinoco_tx_timeout);
-
-/********************************************************************/
-/* Rx path (data frames)                                            */
-/********************************************************************/
-
-/* Does the frame have a SNAP header indicating it should be
- * de-encapsulated to Ethernet-II? */
-static inline int is_ethersnap(void *_hdr)
-{
-	u8 *hdr = _hdr;
-
-	/* We de-encapsulate all packets which, a) have SNAP headers
-	 * (i.e. SSAP=DSAP=0xaa and CTRL=0x3 in the 802.2 LLC header
-	 * and where b) the OUI of the SNAP header is 00:00:00 or
-	 * 00:00:f8 - we need both because different APs appear to use
-	 * different OUIs for some reason */
-	return (memcmp(hdr, &encaps_hdr, 5) == 0)
-		&& ((hdr[5] == 0x00) || (hdr[5] == 0xf8));
-}
-
-static inline void orinoco_spy_gather(struct net_device *dev, u_char *mac,
-				      int level, int noise)
-{
-	struct iw_quality wstats;
-	wstats.level = level - 0x95;
-	wstats.noise = noise - 0x95;
-	wstats.qual = (level > noise) ? (level - noise) : 0;
-	wstats.updated = IW_QUAL_ALL_UPDATED | IW_QUAL_DBM;
-	/* Update spy records */
-	wireless_spy_update(dev, mac, &wstats);
-}
-
-static void orinoco_stat_gather(struct net_device *dev,
-				struct sk_buff *skb,
-				struct hermes_rx_descriptor *desc)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-
-	/* Using spy support with lots of Rx packets, like in an
-	 * infrastructure (AP), will really slow down everything, because
-	 * the MAC address must be compared to each entry of the spy list.
-	 * If the user really asks for it (set some address in the
-	 * spy list), we do it, but he will pay the price.
-	 * Note that to get here, you need both WIRELESS_SPY
-	 * compiled in AND some addresses in the list !!!
-	 */
-	/* Note : gcc will optimise the whole section away if
-	 * WIRELESS_SPY is not defined... - Jean II */
-	if (SPY_NUMBER(priv)) {
-		orinoco_spy_gather(dev, skb_mac_header(skb) + ETH_ALEN,
-				   desc->signal, desc->silence);
-	}
-}
-
-/*
- * orinoco_rx_monitor - handle received monitor frames.
- *
- * Arguments:
- *	dev		network device
- *	rxfid		received FID
- *	desc		rx descriptor of the frame
- *
- * Call context: interrupt
- */
-static void orinoco_rx_monitor(struct net_device *dev, u16 rxfid,
-			       struct hermes_rx_descriptor *desc)
-{
-	u32 hdrlen = 30;	/* return full header by default */
-	u32 datalen = 0;
-	u16 fc;
-	int err;
-	int len;
-	struct sk_buff *skb;
-	struct orinoco_private *priv = ndev_priv(dev);
-	struct net_device_stats *stats = &dev->stats;
-	struct hermes *hw = &priv->hw;
-
-	len = le16_to_cpu(desc->data_len);
-
-	/* Determine the size of the header and the data */
-	fc = le16_to_cpu(desc->frame_ctl);
-	switch (fc & IEEE80211_FCTL_FTYPE) {
-	case IEEE80211_FTYPE_DATA:
-		if ((fc & IEEE80211_FCTL_TODS)
-		    && (fc & IEEE80211_FCTL_FROMDS))
-			hdrlen = 30;
-		else
-			hdrlen = 24;
-		datalen = len;
-		break;
-	case IEEE80211_FTYPE_MGMT:
-		hdrlen = 24;
-		datalen = len;
-		break;
-	case IEEE80211_FTYPE_CTL:
-		switch (fc & IEEE80211_FCTL_STYPE) {
-		case IEEE80211_STYPE_PSPOLL:
-		case IEEE80211_STYPE_RTS:
-		case IEEE80211_STYPE_CFEND:
-		case IEEE80211_STYPE_CFENDACK:
-			hdrlen = 16;
-			break;
-		case IEEE80211_STYPE_CTS:
-		case IEEE80211_STYPE_ACK:
-			hdrlen = 10;
-			break;
-		}
-		break;
-	default:
-		/* Unknown frame type */
-		break;
-	}
-
-	/* sanity check the length */
-	if (datalen > IEEE80211_MAX_DATA_LEN + 12) {
-		printk(KERN_DEBUG "%s: oversized monitor frame, "
-		       "data length = %d\n", dev->name, datalen);
-		stats->rx_length_errors++;
-		goto update_stats;
-	}
-
-	skb = dev_alloc_skb(hdrlen + datalen);
-	if (!skb) {
-		printk(KERN_WARNING "%s: Cannot allocate skb for monitor frame\n",
-		       dev->name);
-		goto update_stats;
-	}
-
-	/* Copy the 802.11 header to the skb */
-	skb_put_data(skb, &(desc->frame_ctl), hdrlen);
-	skb_reset_mac_header(skb);
-
-	/* If any, copy the data from the card to the skb */
-	if (datalen > 0) {
-		err = hw->ops->bap_pread(hw, IRQ_BAP, skb_put(skb, datalen),
-					 ALIGN(datalen, 2), rxfid,
-					 HERMES_802_2_OFFSET);
-		if (err) {
-			printk(KERN_ERR "%s: error %d reading monitor frame\n",
-			       dev->name, err);
-			goto drop;
-		}
-	}
-
-	skb->dev = dev;
-	skb->ip_summed = CHECKSUM_NONE;
-	skb->pkt_type = PACKET_OTHERHOST;
-	skb->protocol = cpu_to_be16(ETH_P_802_2);
-
-	stats->rx_packets++;
-	stats->rx_bytes += skb->len;
-
-	netif_rx(skb);
-	return;
-
- drop:
-	dev_kfree_skb_irq(skb);
- update_stats:
-	stats->rx_errors++;
-	stats->rx_dropped++;
-}
-
-void __orinoco_ev_rx(struct net_device *dev, struct hermes *hw)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	struct net_device_stats *stats = &dev->stats;
-	struct iw_statistics *wstats = &priv->wstats;
-	struct sk_buff *skb = NULL;
-	u16 rxfid, status;
-	int length;
-	struct hermes_rx_descriptor *desc;
-	struct orinoco_rx_data *rx_data;
-	int err;
-
-	desc = kmalloc(sizeof(*desc), GFP_ATOMIC);
-	if (!desc)
-		goto update_stats;
-
-	rxfid = hermes_read_regn(hw, RXFID);
-
-	err = hw->ops->bap_pread(hw, IRQ_BAP, desc, sizeof(*desc),
-				 rxfid, 0);
-	if (err) {
-		printk(KERN_ERR "%s: error %d reading Rx descriptor. "
-		       "Frame dropped.\n", dev->name, err);
-		goto update_stats;
-	}
-
-	status = le16_to_cpu(desc->status);
-
-	if (status & HERMES_RXSTAT_BADCRC) {
-		DEBUG(1, "%s: Bad CRC on Rx. Frame dropped.\n",
-		      dev->name);
-		stats->rx_crc_errors++;
-		goto update_stats;
-	}
-
-	/* Handle frames in monitor mode */
-	if (priv->iw_mode == NL80211_IFTYPE_MONITOR) {
-		orinoco_rx_monitor(dev, rxfid, desc);
-		goto out;
-	}
-
-	if (status & HERMES_RXSTAT_UNDECRYPTABLE) {
-		DEBUG(1, "%s: Undecryptable frame on Rx. Frame dropped.\n",
-		      dev->name);
-		wstats->discard.code++;
-		goto update_stats;
-	}
-
-	length = le16_to_cpu(desc->data_len);
-
-	/* Sanity checks */
-	if (length < 3) { /* No for even an 802.2 LLC header */
-		/* At least on Symbol firmware with PCF we get quite a
-		   lot of these legitimately - Poll frames with no
-		   data. */
-		goto out;
-	}
-	if (length > IEEE80211_MAX_DATA_LEN) {
-		printk(KERN_WARNING "%s: Oversized frame received (%d bytes)\n",
-		       dev->name, length);
-		stats->rx_length_errors++;
-		goto update_stats;
-	}
-
-	/* Payload size does not include Michael MIC. Increase payload
-	 * size to read it together with the data. */
-	if (status & HERMES_RXSTAT_MIC)
-		length += MICHAEL_MIC_LEN;
-
-	/* We need space for the packet data itself, plus an ethernet
-	   header, plus 2 bytes so we can align the IP header on a
-	   32bit boundary, plus 1 byte so we can read in odd length
-	   packets from the card, which has an IO granularity of 16
-	   bits */
-	skb = dev_alloc_skb(length + ETH_HLEN + 2 + 1);
-	if (!skb) {
-		printk(KERN_WARNING "%s: Can't allocate skb for Rx\n",
-		       dev->name);
-		goto update_stats;
-	}
-
-	/* We'll prepend the header, so reserve space for it.  The worst
-	   case is no decapsulation, when 802.3 header is prepended and
-	   nothing is removed.  2 is for aligning the IP header.  */
-	skb_reserve(skb, ETH_HLEN + 2);
-
-	err = hw->ops->bap_pread(hw, IRQ_BAP, skb_put(skb, length),
-				 ALIGN(length, 2), rxfid,
-				 HERMES_802_2_OFFSET);
-	if (err) {
-		printk(KERN_ERR "%s: error %d reading frame. "
-		       "Frame dropped.\n", dev->name, err);
-		goto drop;
-	}
-
-	/* Add desc and skb to rx queue */
-	rx_data = kzalloc(sizeof(*rx_data), GFP_ATOMIC);
-	if (!rx_data)
-		goto drop;
-
-	rx_data->desc = desc;
-	rx_data->skb = skb;
-	list_add_tail(&rx_data->list, &priv->rx_list);
-	tasklet_schedule(&priv->rx_tasklet);
-
-	return;
-
-drop:
-	dev_kfree_skb_irq(skb);
-update_stats:
-	stats->rx_errors++;
-	stats->rx_dropped++;
-out:
-	kfree(desc);
-}
-EXPORT_SYMBOL(__orinoco_ev_rx);
-
-static void orinoco_rx(struct net_device *dev,
-		       struct hermes_rx_descriptor *desc,
-		       struct sk_buff *skb)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	struct net_device_stats *stats = &dev->stats;
-	u16 status, fc;
-	int length;
-	struct ethhdr *hdr;
-
-	status = le16_to_cpu(desc->status);
-	length = le16_to_cpu(desc->data_len);
-	fc = le16_to_cpu(desc->frame_ctl);
-
-	/* Calculate and check MIC */
-	if (status & HERMES_RXSTAT_MIC) {
-		struct orinoco_tkip_key *key;
-		int key_id = ((status & HERMES_RXSTAT_MIC_KEY_ID) >>
-			      HERMES_MIC_KEY_ID_SHIFT);
-		u8 mic[MICHAEL_MIC_LEN];
-		u8 *rxmic;
-		u8 *src = (fc & IEEE80211_FCTL_FROMDS) ?
-			desc->addr3 : desc->addr2;
-
-		/* Extract Michael MIC from payload */
-		rxmic = skb->data + skb->len - MICHAEL_MIC_LEN;
-
-		skb_trim(skb, skb->len - MICHAEL_MIC_LEN);
-		length -= MICHAEL_MIC_LEN;
-
-		key = (struct orinoco_tkip_key *) priv->keys[key_id].key;
-
-		if (!key) {
-			printk(KERN_WARNING "%s: Received encrypted frame from "
-			       "%pM using key %i, but key is not installed\n",
-			       dev->name, src, key_id);
-			goto drop;
-		}
-
-		orinoco_mic(priv->rx_tfm_mic, key->rx_mic, desc->addr1, src,
-			    0, /* priority or QoS? */
-			    skb->data, skb->len, &mic[0]);
-
-		if (memcmp(mic, rxmic,
-			   MICHAEL_MIC_LEN)) {
-			union iwreq_data wrqu;
-			struct iw_michaelmicfailure wxmic;
-
-			printk(KERN_WARNING "%s: "
-			       "Invalid Michael MIC in data frame from %pM, "
-			       "using key %i\n",
-			       dev->name, src, key_id);
-
-			/* TODO: update stats */
-
-			/* Notify userspace */
-			memset(&wxmic, 0, sizeof(wxmic));
-			wxmic.flags = key_id & IW_MICFAILURE_KEY_ID;
-			wxmic.flags |= (desc->addr1[0] & 1) ?
-				IW_MICFAILURE_GROUP : IW_MICFAILURE_PAIRWISE;
-			wxmic.src_addr.sa_family = ARPHRD_ETHER;
-			memcpy(wxmic.src_addr.sa_data, src, ETH_ALEN);
-
-			(void) orinoco_hw_get_tkip_iv(priv, key_id,
-						      &wxmic.tsc[0]);
-
-			memset(&wrqu, 0, sizeof(wrqu));
-			wrqu.data.length = sizeof(wxmic);
-			wireless_send_event(dev, IWEVMICHAELMICFAILURE, &wrqu,
-					    (char *) &wxmic);
-
-			goto drop;
-		}
-	}
-
-	/* Handle decapsulation
-	 * In most cases, the firmware tell us about SNAP frames.
-	 * For some reason, the SNAP frames sent by LinkSys APs
-	 * are not properly recognised by most firmwares.
-	 * So, check ourselves */
-	if (length >= ENCAPS_OVERHEAD &&
-	    (((status & HERMES_RXSTAT_MSGTYPE) == HERMES_RXSTAT_1042) ||
-	     ((status & HERMES_RXSTAT_MSGTYPE) == HERMES_RXSTAT_TUNNEL) ||
-	     is_ethersnap(skb->data))) {
-		/* These indicate a SNAP within 802.2 LLC within
-		   802.11 frame which we'll need to de-encapsulate to
-		   the original EthernetII frame. */
-		hdr = skb_push(skb, ETH_HLEN - ENCAPS_OVERHEAD);
-	} else {
-		/* 802.3 frame - prepend 802.3 header as is */
-		hdr = skb_push(skb, ETH_HLEN);
-		hdr->h_proto = htons(length);
-	}
-	memcpy(hdr->h_dest, desc->addr1, ETH_ALEN);
-	if (fc & IEEE80211_FCTL_FROMDS)
-		memcpy(hdr->h_source, desc->addr3, ETH_ALEN);
-	else
-		memcpy(hdr->h_source, desc->addr2, ETH_ALEN);
-
-	skb->protocol = eth_type_trans(skb, dev);
-	skb->ip_summed = CHECKSUM_NONE;
-	if (fc & IEEE80211_FCTL_TODS)
-		skb->pkt_type = PACKET_OTHERHOST;
-
-	/* Process the wireless stats if needed */
-	orinoco_stat_gather(dev, skb, desc);
-
-	/* Pass the packet to the networking stack */
-	netif_rx(skb);
-	stats->rx_packets++;
-	stats->rx_bytes += length;
-
-	return;
-
- drop:
-	dev_kfree_skb(skb);
-	stats->rx_errors++;
-	stats->rx_dropped++;
-}
-
-static void orinoco_rx_isr_tasklet(struct tasklet_struct *t)
-{
-	struct orinoco_private *priv = from_tasklet(priv, t, rx_tasklet);
-	struct net_device *dev = priv->ndev;
-	struct orinoco_rx_data *rx_data, *temp;
-	struct hermes_rx_descriptor *desc;
-	struct sk_buff *skb;
-	unsigned long flags;
-
-	/* orinoco_rx requires the driver lock, and we also need to
-	 * protect priv->rx_list, so just hold the lock over the
-	 * lot.
-	 *
-	 * If orinoco_lock fails, we've unplugged the card. In this
-	 * case just abort. */
-	if (orinoco_lock(priv, &flags) != 0)
-		return;
-
-	/* extract desc and skb from queue */
-	list_for_each_entry_safe(rx_data, temp, &priv->rx_list, list) {
-		desc = rx_data->desc;
-		skb = rx_data->skb;
-		list_del(&rx_data->list);
-		kfree(rx_data);
-
-		orinoco_rx(dev, desc, skb);
-
-		kfree(desc);
-	}
-
-	orinoco_unlock(priv, &flags);
-}
-
-/********************************************************************/
-/* Rx path (info frames)                                            */
-/********************************************************************/
-
-static void print_linkstatus(struct net_device *dev, u16 status)
-{
-	char *s;
-
-	if (suppress_linkstatus)
-		return;
-
-	switch (status) {
-	case HERMES_LINKSTATUS_NOT_CONNECTED:
-		s = "Not Connected";
-		break;
-	case HERMES_LINKSTATUS_CONNECTED:
-		s = "Connected";
-		break;
-	case HERMES_LINKSTATUS_DISCONNECTED:
-		s = "Disconnected";
-		break;
-	case HERMES_LINKSTATUS_AP_CHANGE:
-		s = "AP Changed";
-		break;
-	case HERMES_LINKSTATUS_AP_OUT_OF_RANGE:
-		s = "AP Out of Range";
-		break;
-	case HERMES_LINKSTATUS_AP_IN_RANGE:
-		s = "AP In Range";
-		break;
-	case HERMES_LINKSTATUS_ASSOC_FAILED:
-		s = "Association Failed";
-		break;
-	default:
-		s = "UNKNOWN";
-	}
-
-	printk(KERN_DEBUG "%s: New link status: %s (%04x)\n",
-	       dev->name, s, status);
-}
-
-/* Search scan results for requested BSSID, join it if found */
-static void orinoco_join_ap(struct work_struct *work)
-{
-	struct orinoco_private *priv =
-		container_of(work, struct orinoco_private, join_work);
-	struct net_device *dev = priv->ndev;
-	struct hermes *hw = &priv->hw;
-	int err;
-	unsigned long flags;
-	struct join_req {
-		u8 bssid[ETH_ALEN];
-		__le16 channel;
-	} __packed req;
-	const int atom_len = offsetof(struct prism2_scan_apinfo, atim);
-	struct prism2_scan_apinfo *atom = NULL;
-	int offset = 4;
-	int found = 0;
-	u8 *buf;
-	u16 len;
-
-	/* Allocate buffer for scan results */
-	buf = kmalloc(MAX_SCAN_LEN, GFP_KERNEL);
-	if (!buf)
-		return;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		goto fail_lock;
-
-	/* Sanity checks in case user changed something in the meantime */
-	if (!priv->bssid_fixed)
-		goto out;
-
-	if (strlen(priv->desired_essid) == 0)
-		goto out;
-
-	/* Read scan results from the firmware */
-	err = hw->ops->read_ltv(hw, USER_BAP,
-				HERMES_RID_SCANRESULTSTABLE,
-				MAX_SCAN_LEN, &len, buf);
-	if (err) {
-		printk(KERN_ERR "%s: Cannot read scan results\n",
-		       dev->name);
-		goto out;
-	}
-
-	len = HERMES_RECLEN_TO_BYTES(len);
-
-	/* Go through the scan results looking for the channel of the AP
-	 * we were requested to join */
-	for (; offset + atom_len <= len; offset += atom_len) {
-		atom = (struct prism2_scan_apinfo *) (buf + offset);
-		if (memcmp(&atom->bssid, priv->desired_bssid, ETH_ALEN) == 0) {
-			found = 1;
-			break;
-		}
-	}
-
-	if (!found) {
-		DEBUG(1, "%s: Requested AP not found in scan results\n",
-		      dev->name);
-		goto out;
-	}
-
-	memcpy(req.bssid, priv->desired_bssid, ETH_ALEN);
-	req.channel = atom->channel;	/* both are little-endian */
-	err = HERMES_WRITE_RECORD(hw, USER_BAP, HERMES_RID_CNFJOINREQUEST,
-				  &req);
-	if (err)
-		printk(KERN_ERR "%s: Error issuing join request\n", dev->name);
-
- out:
-	orinoco_unlock(priv, &flags);
-
- fail_lock:
-	kfree(buf);
-}
-
-/* Send new BSSID to userspace */
-static void orinoco_send_bssid_wevent(struct orinoco_private *priv)
-{
-	struct net_device *dev = priv->ndev;
-	struct hermes *hw = &priv->hw;
-	union iwreq_data wrqu;
-	int err;
-
-	err = hw->ops->read_ltv(hw, USER_BAP, HERMES_RID_CURRENTBSSID,
-				ETH_ALEN, NULL, wrqu.ap_addr.sa_data);
-	if (err != 0)
-		return;
-
-	wrqu.ap_addr.sa_family = ARPHRD_ETHER;
-
-	/* Send event to user space */
-	wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL);
-}
-
-static void orinoco_send_assocreqie_wevent(struct orinoco_private *priv)
-{
-	struct net_device *dev = priv->ndev;
-	struct hermes *hw = &priv->hw;
-	union iwreq_data wrqu;
-	int err;
-	u8 buf[88];
-	u8 *ie;
-
-	if (!priv->has_wpa)
-		return;
-
-	err = hw->ops->read_ltv(hw, USER_BAP, HERMES_RID_CURRENT_ASSOC_REQ_INFO,
-				sizeof(buf), NULL, &buf);
-	if (err != 0)
-		return;
-
-	ie = orinoco_get_wpa_ie(buf, sizeof(buf));
-	if (ie) {
-		int rem = sizeof(buf) - (ie - &buf[0]);
-		wrqu.data.length = ie[1] + 2;
-		if (wrqu.data.length > rem)
-			wrqu.data.length = rem;
-
-		if (wrqu.data.length)
-			/* Send event to user space */
-			wireless_send_event(dev, IWEVASSOCREQIE, &wrqu, ie);
-	}
-}
-
-static void orinoco_send_assocrespie_wevent(struct orinoco_private *priv)
-{
-	struct net_device *dev = priv->ndev;
-	struct hermes *hw = &priv->hw;
-	union iwreq_data wrqu;
-	int err;
-	u8 buf[88]; /* TODO: verify max size or IW_GENERIC_IE_MAX */
-	u8 *ie;
-
-	if (!priv->has_wpa)
-		return;
-
-	err = hw->ops->read_ltv(hw, USER_BAP,
-				HERMES_RID_CURRENT_ASSOC_RESP_INFO,
-				sizeof(buf), NULL, &buf);
-	if (err != 0)
-		return;
-
-	ie = orinoco_get_wpa_ie(buf, sizeof(buf));
-	if (ie) {
-		int rem = sizeof(buf) - (ie - &buf[0]);
-		wrqu.data.length = ie[1] + 2;
-		if (wrqu.data.length > rem)
-			wrqu.data.length = rem;
-
-		if (wrqu.data.length)
-			/* Send event to user space */
-			wireless_send_event(dev, IWEVASSOCRESPIE, &wrqu, ie);
-	}
-}
-
-static void orinoco_send_wevents(struct work_struct *work)
-{
-	struct orinoco_private *priv =
-		container_of(work, struct orinoco_private, wevent_work);
-	unsigned long flags;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return;
-
-	orinoco_send_assocreqie_wevent(priv);
-	orinoco_send_assocrespie_wevent(priv);
-	orinoco_send_bssid_wevent(priv);
-
-	orinoco_unlock(priv, &flags);
-}
-
-static void qbuf_scan(struct orinoco_private *priv, void *buf,
-		      int len, int type)
-{
-	struct orinoco_scan_data *sd;
-	unsigned long flags;
-
-	sd = kmalloc(sizeof(*sd), GFP_ATOMIC);
-	if (!sd)
-		return;
-
-	sd->buf = buf;
-	sd->len = len;
-	sd->type = type;
-
-	spin_lock_irqsave(&priv->scan_lock, flags);
-	list_add_tail(&sd->list, &priv->scan_list);
-	spin_unlock_irqrestore(&priv->scan_lock, flags);
-
-	schedule_work(&priv->process_scan);
-}
-
-static void qabort_scan(struct orinoco_private *priv)
-{
-	struct orinoco_scan_data *sd;
-	unsigned long flags;
-
-	sd = kmalloc(sizeof(*sd), GFP_ATOMIC);
-	if (!sd)
-		return;
-
-	sd->len = -1; /* Abort */
-
-	spin_lock_irqsave(&priv->scan_lock, flags);
-	list_add_tail(&sd->list, &priv->scan_list);
-	spin_unlock_irqrestore(&priv->scan_lock, flags);
-
-	schedule_work(&priv->process_scan);
-}
-
-static void orinoco_process_scan_results(struct work_struct *work)
-{
-	struct orinoco_private *priv =
-		container_of(work, struct orinoco_private, process_scan);
-	struct orinoco_scan_data *sd, *temp;
-	unsigned long flags;
-	void *buf;
-	int len;
-	int type;
-
-	spin_lock_irqsave(&priv->scan_lock, flags);
-	list_for_each_entry_safe(sd, temp, &priv->scan_list, list) {
-
-		buf = sd->buf;
-		len = sd->len;
-		type = sd->type;
-
-		list_del(&sd->list);
-		spin_unlock_irqrestore(&priv->scan_lock, flags);
-		kfree(sd);
-
-		if (len > 0) {
-			if (type == HERMES_INQ_CHANNELINFO)
-				orinoco_add_extscan_result(priv, buf, len);
-			else
-				orinoco_add_hostscan_results(priv, buf, len);
-
-			kfree(buf);
-		} else {
-			/* Either abort or complete the scan */
-			orinoco_scan_done(priv, (len < 0));
-		}
-
-		spin_lock_irqsave(&priv->scan_lock, flags);
-	}
-	spin_unlock_irqrestore(&priv->scan_lock, flags);
-}
-
-void __orinoco_ev_info(struct net_device *dev, struct hermes *hw)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	u16 infofid;
-	struct {
-		__le16 len;
-		__le16 type;
-	} __packed info;
-	int len, type;
-	int err;
-
-	/* This is an answer to an INQUIRE command that we did earlier,
-	 * or an information "event" generated by the card
-	 * The controller return to us a pseudo frame containing
-	 * the information in question - Jean II */
-	infofid = hermes_read_regn(hw, INFOFID);
-
-	/* Read the info frame header - don't try too hard */
-	err = hw->ops->bap_pread(hw, IRQ_BAP, &info, sizeof(info),
-				 infofid, 0);
-	if (err) {
-		printk(KERN_ERR "%s: error %d reading info frame. "
-		       "Frame dropped.\n", dev->name, err);
-		return;
-	}
-
-	len = HERMES_RECLEN_TO_BYTES(le16_to_cpu(info.len));
-	type = le16_to_cpu(info.type);
-
-	switch (type) {
-	case HERMES_INQ_TALLIES: {
-		struct hermes_tallies_frame tallies;
-		struct iw_statistics *wstats = &priv->wstats;
-
-		if (len > sizeof(tallies)) {
-			printk(KERN_WARNING "%s: Tallies frame too long (%d bytes)\n",
-			       dev->name, len);
-			len = sizeof(tallies);
-		}
-
-		err = hw->ops->bap_pread(hw, IRQ_BAP, &tallies, len,
-					 infofid, sizeof(info));
-		if (err)
-			break;
-
-		/* Increment our various counters */
-		/* wstats->discard.nwid - no wrong BSSID stuff */
-		wstats->discard.code +=
-			le16_to_cpu(tallies.RxWEPUndecryptable);
-		if (len == sizeof(tallies))
-			wstats->discard.code +=
-				le16_to_cpu(tallies.RxDiscards_WEPICVError) +
-				le16_to_cpu(tallies.RxDiscards_WEPExcluded);
-		wstats->discard.misc +=
-			le16_to_cpu(tallies.TxDiscardsWrongSA);
-		wstats->discard.fragment +=
-			le16_to_cpu(tallies.RxMsgInBadMsgFragments);
-		wstats->discard.retries +=
-			le16_to_cpu(tallies.TxRetryLimitExceeded);
-		/* wstats->miss.beacon - no match */
-	}
-	break;
-	case HERMES_INQ_LINKSTATUS: {
-		struct hermes_linkstatus linkstatus;
-		u16 newstatus;
-		int connected;
-
-		if (priv->iw_mode == NL80211_IFTYPE_MONITOR)
-			break;
-
-		if (len != sizeof(linkstatus)) {
-			printk(KERN_WARNING "%s: Unexpected size for linkstatus frame (%d bytes)\n",
-			       dev->name, len);
-			break;
-		}
-
-		err = hw->ops->bap_pread(hw, IRQ_BAP, &linkstatus, len,
-					 infofid, sizeof(info));
-		if (err)
-			break;
-		newstatus = le16_to_cpu(linkstatus.linkstatus);
-
-		/* Symbol firmware uses "out of range" to signal that
-		 * the hostscan frame can be requested.  */
-		if (newstatus == HERMES_LINKSTATUS_AP_OUT_OF_RANGE &&
-		    priv->firmware_type == FIRMWARE_TYPE_SYMBOL &&
-		    priv->has_hostscan && priv->scan_request) {
-			hermes_inquire(hw, HERMES_INQ_HOSTSCAN_SYMBOL);
-			break;
-		}
-
-		connected = (newstatus == HERMES_LINKSTATUS_CONNECTED)
-			|| (newstatus == HERMES_LINKSTATUS_AP_CHANGE)
-			|| (newstatus == HERMES_LINKSTATUS_AP_IN_RANGE);
-
-		if (connected)
-			netif_carrier_on(dev);
-		else if (!ignore_disconnect)
-			netif_carrier_off(dev);
-
-		if (newstatus != priv->last_linkstatus) {
-			priv->last_linkstatus = newstatus;
-			print_linkstatus(dev, newstatus);
-			/* The info frame contains only one word which is the
-			 * status (see hermes.h). The status is pretty boring
-			 * in itself, that's why we export the new BSSID...
-			 * Jean II */
-			schedule_work(&priv->wevent_work);
-		}
-	}
-	break;
-	case HERMES_INQ_SCAN:
-		if (!priv->scan_request && priv->bssid_fixed &&
-		    priv->firmware_type == FIRMWARE_TYPE_INTERSIL) {
-			schedule_work(&priv->join_work);
-			break;
-		}
-		fallthrough;
-	case HERMES_INQ_HOSTSCAN:
-	case HERMES_INQ_HOSTSCAN_SYMBOL: {
-		/* Result of a scanning. Contains information about
-		 * cells in the vicinity - Jean II */
-		unsigned char *buf;
-
-		/* Sanity check */
-		if (len > 4096) {
-			printk(KERN_WARNING "%s: Scan results too large (%d bytes)\n",
-			       dev->name, len);
-			qabort_scan(priv);
-			break;
-		}
-
-		/* Allocate buffer for results */
-		buf = kmalloc(len, GFP_ATOMIC);
-		if (buf == NULL) {
-			/* No memory, so can't printk()... */
-			qabort_scan(priv);
-			break;
-		}
-
-		/* Read scan data */
-		err = hw->ops->bap_pread(hw, IRQ_BAP, (void *) buf, len,
-					 infofid, sizeof(info));
-		if (err) {
-			kfree(buf);
-			qabort_scan(priv);
-			break;
-		}
-
-#ifdef ORINOCO_DEBUG
-		{
-			int	i;
-			printk(KERN_DEBUG "Scan result [%02X", buf[0]);
-			for (i = 1; i < (len * 2); i++)
-				printk(":%02X", buf[i]);
-			printk("]\n");
-		}
-#endif	/* ORINOCO_DEBUG */
-
-		qbuf_scan(priv, buf, len, type);
-	}
-	break;
-	case HERMES_INQ_CHANNELINFO:
-	{
-		struct agere_ext_scan_info *bss;
-
-		if (!priv->scan_request) {
-			printk(KERN_DEBUG "%s: Got chaninfo without scan, "
-			       "len=%d\n", dev->name, len);
-			break;
-		}
-
-		/* An empty result indicates that the scan is complete */
-		if (len == 0) {
-			qbuf_scan(priv, NULL, len, type);
-			break;
-		}
-
-		/* Sanity check */
-		else if (len < (offsetof(struct agere_ext_scan_info,
-					   data) + 2)) {
-			/* Drop this result now so we don't have to
-			 * keep checking later */
-			printk(KERN_WARNING
-			       "%s: Ext scan results too short (%d bytes)\n",
-			       dev->name, len);
-			break;
-		}
-
-		bss = kmalloc(len, GFP_ATOMIC);
-		if (bss == NULL)
-			break;
-
-		/* Read scan data */
-		err = hw->ops->bap_pread(hw, IRQ_BAP, (void *) bss, len,
-					 infofid, sizeof(info));
-		if (err)
-			kfree(bss);
-		else
-			qbuf_scan(priv, bss, len, type);
-
-		break;
-	}
-	case HERMES_INQ_SEC_STAT_AGERE:
-		/* Security status (Agere specific) */
-		/* Ignore this frame for now */
-		if (priv->firmware_type == FIRMWARE_TYPE_AGERE)
-			break;
-		fallthrough;
-	default:
-		printk(KERN_DEBUG "%s: Unknown information frame received: "
-		       "type 0x%04x, length %d\n", dev->name, type, len);
-		/* We don't actually do anything about it */
-		break;
-	}
-}
-EXPORT_SYMBOL(__orinoco_ev_info);
-
-static void __orinoco_ev_infdrop(struct net_device *dev, struct hermes *hw)
-{
-	if (net_ratelimit())
-		printk(KERN_DEBUG "%s: Information frame lost.\n", dev->name);
-}
-
-/********************************************************************/
-/* Internal hardware control routines                               */
-/********************************************************************/
-
-static int __orinoco_up(struct orinoco_private *priv)
-{
-	struct net_device *dev = priv->ndev;
-	struct hermes *hw = &priv->hw;
-	int err;
-
-	netif_carrier_off(dev); /* just to make sure */
-
-	err = __orinoco_commit(priv);
-	if (err) {
-		printk(KERN_ERR "%s: Error %d configuring card\n",
-		       dev->name, err);
-		return err;
-	}
-
-	/* Fire things up again */
-	hermes_set_irqmask(hw, ORINOCO_INTEN);
-	err = hermes_enable_port(hw, 0);
-	if (err) {
-		printk(KERN_ERR "%s: Error %d enabling MAC port\n",
-		       dev->name, err);
-		return err;
-	}
-
-	netif_start_queue(dev);
-
-	return 0;
-}
-
-static int __orinoco_down(struct orinoco_private *priv)
-{
-	struct net_device *dev = priv->ndev;
-	struct hermes *hw = &priv->hw;
-	int err;
-
-	netif_stop_queue(dev);
-
-	if (!priv->hw_unavailable) {
-		if (!priv->broken_disableport) {
-			err = hermes_disable_port(hw, 0);
-			if (err) {
-				/* Some firmwares (e.g. Intersil 1.3.x) seem
-				 * to have problems disabling the port, oh
-				 * well, too bad. */
-				printk(KERN_WARNING "%s: Error %d disabling MAC port\n",
-				       dev->name, err);
-				priv->broken_disableport = 1;
-			}
-		}
-		hermes_set_irqmask(hw, 0);
-		hermes_write_regn(hw, EVACK, 0xffff);
-	}
-
-	orinoco_scan_done(priv, true);
-
-	/* firmware will have to reassociate */
-	netif_carrier_off(dev);
-	priv->last_linkstatus = 0xffff;
-
-	return 0;
-}
-
-static int orinoco_reinit_firmware(struct orinoco_private *priv)
-{
-	struct hermes *hw = &priv->hw;
-	int err;
-
-	err = hw->ops->init(hw);
-	if (priv->do_fw_download && !err) {
-		err = orinoco_download(priv);
-		if (err)
-			priv->do_fw_download = 0;
-	}
-	if (!err)
-		err = orinoco_hw_allocate_fid(priv);
-
-	return err;
-}
-
-static int
-__orinoco_set_multicast_list(struct net_device *dev)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	int err = 0;
-	int promisc, mc_count;
-
-	/* The Hermes doesn't seem to have an allmulti mode, so we go
-	 * into promiscuous mode and let the upper levels deal. */
-	if ((dev->flags & IFF_PROMISC) || (dev->flags & IFF_ALLMULTI) ||
-	    (netdev_mc_count(dev) > MAX_MULTICAST(priv))) {
-		promisc = 1;
-		mc_count = 0;
-	} else {
-		promisc = 0;
-		mc_count = netdev_mc_count(dev);
-	}
-
-	err = __orinoco_hw_set_multicast_list(priv, dev, mc_count, promisc);
-
-	return err;
-}
-
-/* This must be called from user context, without locks held - use
- * schedule_work() */
-void orinoco_reset(struct work_struct *work)
-{
-	struct orinoco_private *priv =
-		container_of(work, struct orinoco_private, reset_work);
-	struct net_device *dev = priv->ndev;
-	struct hermes *hw = &priv->hw;
-	int err;
-	unsigned long flags;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		/* When the hardware becomes available again, whatever
-		 * detects that is responsible for re-initializing
-		 * it. So no need for anything further */
-		return;
-
-	netif_stop_queue(dev);
-
-	/* Shut off interrupts.  Depending on what state the hardware
-	 * is in, this might not work, but we'll try anyway */
-	hermes_set_irqmask(hw, 0);
-	hermes_write_regn(hw, EVACK, 0xffff);
-
-	priv->hw_unavailable++;
-	priv->last_linkstatus = 0xffff; /* firmware will have to reassociate */
-	netif_carrier_off(dev);
-
-	orinoco_unlock(priv, &flags);
-
-	/* Scanning support: Notify scan cancellation */
-	orinoco_scan_done(priv, true);
-
-	if (priv->hard_reset) {
-		err = (*priv->hard_reset)(priv);
-		if (err) {
-			printk(KERN_ERR "%s: orinoco_reset: Error %d "
-			       "performing hard reset\n", dev->name, err);
-			goto disable;
-		}
-	}
-
-	err = orinoco_reinit_firmware(priv);
-	if (err) {
-		printk(KERN_ERR "%s: orinoco_reset: Error %d re-initializing firmware\n",
-		       dev->name, err);
-		goto disable;
-	}
-
-	/* This has to be called from user context */
-	orinoco_lock_irq(priv);
-
-	priv->hw_unavailable--;
-
-	/* priv->open or priv->hw_unavailable might have changed while
-	 * we dropped the lock */
-	if (priv->open && (!priv->hw_unavailable)) {
-		err = __orinoco_up(priv);
-		if (err) {
-			printk(KERN_ERR "%s: orinoco_reset: Error %d reenabling card\n",
-			       dev->name, err);
-		} else
-			netif_trans_update(dev);
-	}
-
-	orinoco_unlock_irq(priv);
-
-	return;
- disable:
-	hermes_set_irqmask(hw, 0);
-	netif_device_detach(dev);
-	printk(KERN_ERR "%s: Device has been disabled!\n", dev->name);
-}
-
-static int __orinoco_commit(struct orinoco_private *priv)
-{
-	struct net_device *dev = priv->ndev;
-	int err = 0;
-
-	/* If we've called commit, we are reconfiguring or bringing the
-	 * interface up. Maintaining countermeasures across this would
-	 * be confusing, so note that we've disabled them. The port will
-	 * be enabled later in orinoco_commit or __orinoco_up. */
-	priv->tkip_cm_active = 0;
-
-	err = orinoco_hw_program_rids(priv);
-
-	/* FIXME: what about netif_tx_lock */
-	(void) __orinoco_set_multicast_list(dev);
-
-	return err;
-}
-
-/* Ensures configuration changes are applied. May result in a reset.
- * The caller should hold priv->lock
- */
-int orinoco_commit(struct orinoco_private *priv)
-{
-	struct net_device *dev = priv->ndev;
-	struct hermes *hw = &priv->hw;
-	int err;
-
-	if (priv->broken_disableport) {
-		schedule_work(&priv->reset_work);
-		return 0;
-	}
-
-	err = hermes_disable_port(hw, 0);
-	if (err) {
-		printk(KERN_WARNING "%s: Unable to disable port "
-		       "while reconfiguring card\n", dev->name);
-		priv->broken_disableport = 1;
-		goto out;
-	}
-
-	err = __orinoco_commit(priv);
-	if (err) {
-		printk(KERN_WARNING "%s: Unable to reconfigure card\n",
-		       dev->name);
-		goto out;
-	}
-
-	err = hermes_enable_port(hw, 0);
-	if (err) {
-		printk(KERN_WARNING "%s: Unable to enable port while reconfiguring card\n",
-		       dev->name);
-		goto out;
-	}
-
- out:
-	if (err) {
-		printk(KERN_WARNING "%s: Resetting instead...\n", dev->name);
-		schedule_work(&priv->reset_work);
-		err = 0;
-	}
-	return err;
-}
-
-/********************************************************************/
-/* Interrupt handler                                                */
-/********************************************************************/
-
-static void __orinoco_ev_tick(struct net_device *dev, struct hermes *hw)
-{
-	printk(KERN_DEBUG "%s: TICK\n", dev->name);
-}
-
-static void __orinoco_ev_wterr(struct net_device *dev, struct hermes *hw)
-{
-	/* This seems to happen a fair bit under load, but ignoring it
-	   seems to work fine...*/
-	printk(KERN_DEBUG "%s: MAC controller error (WTERR). Ignoring.\n",
-	       dev->name);
-}
-
-irqreturn_t orinoco_interrupt(int irq, void *dev_id)
-{
-	struct orinoco_private *priv = dev_id;
-	struct net_device *dev = priv->ndev;
-	struct hermes *hw = &priv->hw;
-	int count = MAX_IRQLOOPS_PER_IRQ;
-	u16 evstat, events;
-	/* These are used to detect a runaway interrupt situation.
-	 *
-	 * If we get more than MAX_IRQLOOPS_PER_JIFFY iterations in a jiffy,
-	 * we panic and shut down the hardware
-	 */
-	/* jiffies value the last time we were called */
-	static int last_irq_jiffy; /* = 0 */
-	static int loops_this_jiffy; /* = 0 */
-	unsigned long flags;
-
-	if (orinoco_lock(priv, &flags) != 0) {
-		/* If hw is unavailable - we don't know if the irq was
-		 * for us or not */
-		return IRQ_HANDLED;
-	}
-
-	evstat = hermes_read_regn(hw, EVSTAT);
-	events = evstat & hw->inten;
-	if (!events) {
-		orinoco_unlock(priv, &flags);
-		return IRQ_NONE;
-	}
-
-	if (jiffies != last_irq_jiffy)
-		loops_this_jiffy = 0;
-	last_irq_jiffy = jiffies;
-
-	while (events && count--) {
-		if (++loops_this_jiffy > MAX_IRQLOOPS_PER_JIFFY) {
-			printk(KERN_WARNING "%s: IRQ handler is looping too "
-			       "much! Resetting.\n", dev->name);
-			/* Disable interrupts for now */
-			hermes_set_irqmask(hw, 0);
-			schedule_work(&priv->reset_work);
-			break;
-		}
-
-		/* Check the card hasn't been removed */
-		if (!hermes_present(hw)) {
-			DEBUG(0, "orinoco_interrupt(): card removed\n");
-			break;
-		}
-
-		if (events & HERMES_EV_TICK)
-			__orinoco_ev_tick(dev, hw);
-		if (events & HERMES_EV_WTERR)
-			__orinoco_ev_wterr(dev, hw);
-		if (events & HERMES_EV_INFDROP)
-			__orinoco_ev_infdrop(dev, hw);
-		if (events & HERMES_EV_INFO)
-			__orinoco_ev_info(dev, hw);
-		if (events & HERMES_EV_RX)
-			__orinoco_ev_rx(dev, hw);
-		if (events & HERMES_EV_TXEXC)
-			__orinoco_ev_txexc(dev, hw);
-		if (events & HERMES_EV_TX)
-			__orinoco_ev_tx(dev, hw);
-		if (events & HERMES_EV_ALLOC)
-			__orinoco_ev_alloc(dev, hw);
-
-		hermes_write_regn(hw, EVACK, evstat);
-
-		evstat = hermes_read_regn(hw, EVSTAT);
-		events = evstat & hw->inten;
-	}
-
-	orinoco_unlock(priv, &flags);
-	return IRQ_HANDLED;
-}
-EXPORT_SYMBOL(orinoco_interrupt);
-
-/********************************************************************/
-/* Power management                                                 */
-/********************************************************************/
-#if defined(CONFIG_PM_SLEEP) && !defined(CONFIG_HERMES_CACHE_FW_ON_INIT)
-static int orinoco_pm_notifier(struct notifier_block *notifier,
-			       unsigned long pm_event,
-			       void *unused)
-{
-	struct orinoco_private *priv = container_of(notifier,
-						    struct orinoco_private,
-						    pm_notifier);
-
-	/* All we need to do is cache the firmware before suspend, and
-	 * release it when we come out.
-	 *
-	 * Only need to do this if we're downloading firmware. */
-	if (!priv->do_fw_download)
-		return NOTIFY_DONE;
-
-	switch (pm_event) {
-	case PM_HIBERNATION_PREPARE:
-	case PM_SUSPEND_PREPARE:
-		orinoco_cache_fw(priv, 0);
-		break;
-
-	case PM_POST_RESTORE:
-		/* Restore from hibernation failed. We need to clean
-		 * up in exactly the same way, so fall through. */
-	case PM_POST_HIBERNATION:
-	case PM_POST_SUSPEND:
-		orinoco_uncache_fw(priv);
-		break;
-
-	case PM_RESTORE_PREPARE:
-	default:
-		break;
-	}
-
-	return NOTIFY_DONE;
-}
-
-static void orinoco_register_pm_notifier(struct orinoco_private *priv)
-{
-	priv->pm_notifier.notifier_call = orinoco_pm_notifier;
-	register_pm_notifier(&priv->pm_notifier);
-}
-
-static void orinoco_unregister_pm_notifier(struct orinoco_private *priv)
-{
-	unregister_pm_notifier(&priv->pm_notifier);
-}
-#else /* !PM_SLEEP || HERMES_CACHE_FW_ON_INIT */
-#define orinoco_register_pm_notifier(priv) do { } while (0)
-#define orinoco_unregister_pm_notifier(priv) do { } while (0)
-#endif
-
-/********************************************************************/
-/* Initialization                                                   */
-/********************************************************************/
-
-int orinoco_init(struct orinoco_private *priv)
-{
-	struct device *dev = priv->dev;
-	struct wiphy *wiphy = priv_to_wiphy(priv);
-	struct hermes *hw = &priv->hw;
-	int err = 0;
-
-	/* No need to lock, the hw_unavailable flag is already set in
-	 * alloc_orinocodev() */
-	priv->nicbuf_size = IEEE80211_MAX_FRAME_LEN + ETH_HLEN;
-
-	/* Initialize the firmware */
-	err = hw->ops->init(hw);
-	if (err != 0) {
-		dev_err(dev, "Failed to initialize firmware (err = %d)\n",
-			err);
-		goto out;
-	}
-
-	err = determine_fw_capabilities(priv, wiphy->fw_version,
-					sizeof(wiphy->fw_version),
-					&wiphy->hw_version);
-	if (err != 0) {
-		dev_err(dev, "Incompatible firmware, aborting\n");
-		goto out;
-	}
-
-	if (priv->do_fw_download) {
-#ifdef CONFIG_HERMES_CACHE_FW_ON_INIT
-		orinoco_cache_fw(priv, 0);
-#endif
-
-		err = orinoco_download(priv);
-		if (err)
-			priv->do_fw_download = 0;
-
-		/* Check firmware version again */
-		err = determine_fw_capabilities(priv, wiphy->fw_version,
-						sizeof(wiphy->fw_version),
-						&wiphy->hw_version);
-		if (err != 0) {
-			dev_err(dev, "Incompatible firmware, aborting\n");
-			goto out;
-		}
-	}
-
-	if (priv->has_port3)
-		dev_info(dev, "Ad-hoc demo mode supported\n");
-	if (priv->has_ibss)
-		dev_info(dev, "IEEE standard IBSS ad-hoc mode supported\n");
-	if (priv->has_wep)
-		dev_info(dev, "WEP supported, %s-bit key\n",
-			 priv->has_big_wep ? "104" : "40");
-	if (priv->has_wpa) {
-		dev_info(dev, "WPA-PSK supported\n");
-		if (orinoco_mic_init(priv)) {
-			dev_err(dev, "Failed to setup MIC crypto algorithm. "
-				"Disabling WPA support\n");
-			priv->has_wpa = 0;
-		}
-	}
-
-	err = orinoco_hw_read_card_settings(priv, wiphy->perm_addr);
-	if (err)
-		goto out;
-
-	err = orinoco_hw_allocate_fid(priv);
-	if (err) {
-		dev_err(dev, "Failed to allocate NIC buffer!\n");
-		goto out;
-	}
-
-	/* Set up the default configuration */
-	priv->iw_mode = NL80211_IFTYPE_STATION;
-	/* By default use IEEE/IBSS ad-hoc mode if we have it */
-	priv->prefer_port3 = priv->has_port3 && (!priv->has_ibss);
-	set_port_type(priv);
-	priv->channel = 0; /* use firmware default */
-
-	priv->promiscuous = 0;
-	priv->encode_alg = ORINOCO_ALG_NONE;
-	priv->tx_key = 0;
-	priv->wpa_enabled = 0;
-	priv->tkip_cm_active = 0;
-	priv->key_mgmt = 0;
-	priv->wpa_ie_len = 0;
-	priv->wpa_ie = NULL;
-
-	if (orinoco_wiphy_register(wiphy)) {
-		err = -ENODEV;
-		goto out;
-	}
-
-	/* Make the hardware available, as long as it hasn't been
-	 * removed elsewhere (e.g. by PCMCIA hot unplug) */
-	orinoco_lock_irq(priv);
-	priv->hw_unavailable--;
-	orinoco_unlock_irq(priv);
-
-	dev_dbg(dev, "Ready\n");
-
- out:
-	return err;
-}
-EXPORT_SYMBOL(orinoco_init);
-
-static const struct net_device_ops orinoco_netdev_ops = {
-	.ndo_open		= orinoco_open,
-	.ndo_stop		= orinoco_stop,
-	.ndo_start_xmit		= orinoco_xmit,
-	.ndo_set_rx_mode	= orinoco_set_multicast_list,
-	.ndo_change_mtu		= orinoco_change_mtu,
-	.ndo_set_mac_address	= eth_mac_addr,
-	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_tx_timeout		= orinoco_tx_timeout,
-};
-
-/* Allocate private data.
- *
- * This driver has a number of structures associated with it
- *  netdev - Net device structure for each network interface
- *  wiphy - structure associated with wireless phy
- *  wireless_dev (wdev) - structure for each wireless interface
- *  hw - structure for hermes chip info
- *  card - card specific structure for use by the card driver
- *         (airport, orinoco_cs)
- *  priv - orinoco private data
- *  device - generic linux device structure
- *
- *  +---------+    +---------+
- *  |  wiphy  |    | netdev  |
- *  | +-------+    | +-------+
- *  | | priv  |    | | wdev  |
- *  | | +-----+    +-+-------+
- *  | | | hw  |
- *  | +-+-----+
- *  | | card  |
- *  +-+-------+
- *
- * priv has a link to netdev and device
- * wdev has a link to wiphy
- */
-struct orinoco_private
-*alloc_orinocodev(int sizeof_card,
-		  struct device *device,
-		  int (*hard_reset)(struct orinoco_private *),
-		  int (*stop_fw)(struct orinoco_private *, int))
-{
-	struct orinoco_private *priv;
-	struct wiphy *wiphy;
-
-	/* allocate wiphy
-	 * NOTE: We only support a single virtual interface
-	 *       but this may change when monitor mode is added
-	 */
-	wiphy = wiphy_new(&orinoco_cfg_ops,
-			  sizeof(struct orinoco_private) + sizeof_card);
-	if (!wiphy)
-		return NULL;
-
-	priv = wiphy_priv(wiphy);
-	priv->dev = device;
-
-	if (sizeof_card)
-		priv->card = (void *)((unsigned long)priv
-				      + sizeof(struct orinoco_private));
-	else
-		priv->card = NULL;
-
-	orinoco_wiphy_init(wiphy);
-
-#ifdef WIRELESS_SPY
-	priv->wireless_data.spy_data = &priv->spy_data;
-#endif
-
-	/* Set up default callbacks */
-	priv->hard_reset = hard_reset;
-	priv->stop_fw = stop_fw;
-
-	spin_lock_init(&priv->lock);
-	priv->open = 0;
-	priv->hw_unavailable = 1; /* orinoco_init() must clear this
-				   * before anything else touches the
-				   * hardware */
-	INIT_WORK(&priv->reset_work, orinoco_reset);
-	INIT_WORK(&priv->join_work, orinoco_join_ap);
-	INIT_WORK(&priv->wevent_work, orinoco_send_wevents);
-
-	INIT_LIST_HEAD(&priv->rx_list);
-	tasklet_setup(&priv->rx_tasklet, orinoco_rx_isr_tasklet);
-
-	spin_lock_init(&priv->scan_lock);
-	INIT_LIST_HEAD(&priv->scan_list);
-	INIT_WORK(&priv->process_scan, orinoco_process_scan_results);
-
-	priv->last_linkstatus = 0xffff;
-
-#if defined(CONFIG_HERMES_CACHE_FW_ON_INIT) || defined(CONFIG_PM_SLEEP)
-	priv->cached_pri_fw = NULL;
-	priv->cached_fw = NULL;
-#endif
-
-	/* Register PM notifiers */
-	orinoco_register_pm_notifier(priv);
-
-	return priv;
-}
-EXPORT_SYMBOL(alloc_orinocodev);
-
-/* We can only support a single interface. We provide a separate
- * function to set it up to distinguish between hardware
- * initialisation and interface setup.
- *
- * The base_addr and irq parameters are passed on to netdev for use
- * with SIOCGIFMAP.
- */
-int orinoco_if_add(struct orinoco_private *priv,
-		   unsigned long base_addr,
-		   unsigned int irq,
-		   const struct net_device_ops *ops)
-{
-	struct wiphy *wiphy = priv_to_wiphy(priv);
-	struct wireless_dev *wdev;
-	struct net_device *dev;
-	int ret;
-
-	dev = alloc_etherdev(sizeof(struct wireless_dev));
-
-	if (!dev)
-		return -ENOMEM;
-
-	/* Initialise wireless_dev */
-	wdev = netdev_priv(dev);
-	wdev->wiphy = wiphy;
-	wdev->iftype = NL80211_IFTYPE_STATION;
-
-	/* Setup / override net_device fields */
-	dev->ieee80211_ptr = wdev;
-	dev->watchdog_timeo = HZ; /* 1 second timeout */
-	dev->wireless_handlers = &orinoco_handler_def;
-#ifdef WIRELESS_SPY
-	dev->wireless_data = &priv->wireless_data;
-#endif
-	/* Default to standard ops if not set */
-	if (ops)
-		dev->netdev_ops = ops;
-	else
-		dev->netdev_ops = &orinoco_netdev_ops;
-
-	/* we use the default eth_mac_addr for setting the MAC addr */
-
-	/* Reserve space in skb for the SNAP header */
-	dev->needed_headroom = ENCAPS_OVERHEAD;
-
-	netif_carrier_off(dev);
-
-	eth_hw_addr_set(dev, wiphy->perm_addr);
-
-	dev->base_addr = base_addr;
-	dev->irq = irq;
-
-	dev->min_mtu = ORINOCO_MIN_MTU;
-	dev->max_mtu = ORINOCO_MAX_MTU;
-
-	SET_NETDEV_DEV(dev, priv->dev);
-	ret = register_netdev(dev);
-	if (ret)
-		goto fail;
-
-	priv->ndev = dev;
-
-	/* Report what we've done */
-	dev_dbg(priv->dev, "Registered interface %s.\n", dev->name);
-
-	return 0;
-
- fail:
-	free_netdev(dev);
-	return ret;
-}
-EXPORT_SYMBOL(orinoco_if_add);
-
-void orinoco_if_del(struct orinoco_private *priv)
-{
-	struct net_device *dev = priv->ndev;
-
-	unregister_netdev(dev);
-	free_netdev(dev);
-}
-EXPORT_SYMBOL(orinoco_if_del);
-
-void free_orinocodev(struct orinoco_private *priv)
-{
-	struct wiphy *wiphy = priv_to_wiphy(priv);
-	struct orinoco_rx_data *rx_data, *temp;
-	struct orinoco_scan_data *sd, *sdtemp;
-
-	/* If the tasklet is scheduled when we call tasklet_kill it
-	 * will run one final time. However the tasklet will only
-	 * drain priv->rx_list if the hw is still available. */
-	tasklet_kill(&priv->rx_tasklet);
-
-	/* Explicitly drain priv->rx_list */
-	list_for_each_entry_safe(rx_data, temp, &priv->rx_list, list) {
-		list_del(&rx_data->list);
-
-		dev_kfree_skb(rx_data->skb);
-		kfree(rx_data->desc);
-		kfree(rx_data);
-	}
-
-	cancel_work_sync(&priv->process_scan);
-	/* Explicitly drain priv->scan_list */
-	list_for_each_entry_safe(sd, sdtemp, &priv->scan_list, list) {
-		list_del(&sd->list);
-
-		if (sd->len > 0)
-			kfree(sd->buf);
-		kfree(sd);
-	}
-
-	orinoco_unregister_pm_notifier(priv);
-	orinoco_uncache_fw(priv);
-
-	priv->wpa_ie_len = 0;
-	kfree(priv->wpa_ie);
-	orinoco_mic_free(priv);
-	wiphy_free(wiphy);
-}
-EXPORT_SYMBOL(free_orinocodev);
-
-int orinoco_up(struct orinoco_private *priv)
-{
-	struct net_device *dev = priv->ndev;
-	unsigned long flags;
-	int err;
-
-	priv->hw.ops->lock_irqsave(&priv->lock, &flags);
-
-	err = orinoco_reinit_firmware(priv);
-	if (err) {
-		printk(KERN_ERR "%s: Error %d re-initializing firmware\n",
-		       dev->name, err);
-		goto exit;
-	}
-
-	netif_device_attach(dev);
-	priv->hw_unavailable--;
-
-	if (priv->open && !priv->hw_unavailable) {
-		err = __orinoco_up(priv);
-		if (err)
-			printk(KERN_ERR "%s: Error %d restarting card\n",
-			       dev->name, err);
-	}
-
-exit:
-	priv->hw.ops->unlock_irqrestore(&priv->lock, &flags);
-
-	return 0;
-}
-EXPORT_SYMBOL(orinoco_up);
-
-void orinoco_down(struct orinoco_private *priv)
-{
-	struct net_device *dev = priv->ndev;
-	unsigned long flags;
-	int err;
-
-	priv->hw.ops->lock_irqsave(&priv->lock, &flags);
-	err = __orinoco_down(priv);
-	if (err)
-		printk(KERN_WARNING "%s: Error %d downing interface\n",
-		       dev->name, err);
-
-	netif_device_detach(dev);
-	priv->hw_unavailable++;
-	priv->hw.ops->unlock_irqrestore(&priv->lock, &flags);
-}
-EXPORT_SYMBOL(orinoco_down);
-
-/********************************************************************/
-/* Module initialization                                            */
-/********************************************************************/
-
-/* Can't be declared "const" or the whole __initdata section will
- * become const */
-static char version[] __initdata = DRIVER_NAME " " DRIVER_VERSION
-	" (David Gibson <hermes@gibson.dropbear.id.au>, "
-	"Pavel Roskin <proski@gnu.org>, et al)";
-
-static int __init init_orinoco(void)
-{
-	printk(KERN_DEBUG "%s\n", version);
-	return 0;
-}
-
-static void __exit exit_orinoco(void)
-{
-}
-
-module_init(init_orinoco);
-module_exit(exit_orinoco);
diff --git a/drivers/net/wireless/intersil/orinoco/main.h b/drivers/net/wireless/intersil/orinoco/main.h
deleted file mode 100644
index 5a8fec26136e..000000000000
--- a/drivers/net/wireless/intersil/orinoco/main.h
+++ /dev/null
@@ -1,50 +0,0 @@
-/* Exports from main to helper modules
- *
- * See copyright notice in main.c
- */
-#ifndef _ORINOCO_MAIN_H_
-#define _ORINOCO_MAIN_H_
-
-#include <linux/ieee80211.h>
-#include "orinoco.h"
-
-/********************************************************************/
-/* Compile time configuration and compatibility stuff               */
-/********************************************************************/
-
-/* We do this this way to avoid ifdefs in the actual code */
-#ifdef WIRELESS_SPY
-#define SPY_NUMBER(priv)	(priv->spy_data.spy_number)
-#else
-#define SPY_NUMBER(priv)	0
-#endif /* WIRELESS_SPY */
-
-/********************************************************************/
-
-/* Export module parameter */
-extern int force_monitor;
-
-/* Forward declarations */
-struct net_device;
-struct work_struct;
-
-void set_port_type(struct orinoco_private *priv);
-int orinoco_commit(struct orinoco_private *priv);
-void orinoco_reset(struct work_struct *work);
-
-/* Information element helpers - find a home for these... */
-#define WPA_OUI_TYPE	"\x00\x50\xF2\x01"
-#define WPA_SELECTOR_LEN 4
-static inline u8 *orinoco_get_wpa_ie(u8 *data, size_t len)
-{
-	u8 *p = data;
-	while ((p + 2 + WPA_SELECTOR_LEN) < (data + len)) {
-		if ((p[0] == WLAN_EID_VENDOR_SPECIFIC) &&
-		    (memcmp(&p[2], WPA_OUI_TYPE, WPA_SELECTOR_LEN) == 0))
-			return p;
-		p += p[1] + 2;
-	}
-	return NULL;
-}
-
-#endif /* _ORINOCO_MAIN_H_ */
diff --git a/drivers/net/wireless/intersil/orinoco/mic.c b/drivers/net/wireless/intersil/orinoco/mic.c
deleted file mode 100644
index a324bc4b7938..000000000000
--- a/drivers/net/wireless/intersil/orinoco/mic.c
+++ /dev/null
@@ -1,89 +0,0 @@
-/* Orinoco MIC helpers
- *
- * See copyright notice in main.c
- */
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/if_ether.h>
-#include <linux/scatterlist.h>
-#include <crypto/hash.h>
-
-#include "orinoco.h"
-#include "mic.h"
-
-/********************************************************************/
-/* Michael MIC crypto setup                                         */
-/********************************************************************/
-int orinoco_mic_init(struct orinoco_private *priv)
-{
-	priv->tx_tfm_mic = crypto_alloc_shash("michael_mic", 0, 0);
-	if (IS_ERR(priv->tx_tfm_mic)) {
-		printk(KERN_DEBUG "%s: could not allocate "
-		       "crypto API michael_mic\n", __func__);
-		priv->tx_tfm_mic = NULL;
-		return -ENOMEM;
-	}
-
-	priv->rx_tfm_mic = crypto_alloc_shash("michael_mic", 0, 0);
-	if (IS_ERR(priv->rx_tfm_mic)) {
-		printk(KERN_DEBUG "%s: could not allocate "
-		       "crypto API michael_mic\n", __func__);
-		priv->rx_tfm_mic = NULL;
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-void orinoco_mic_free(struct orinoco_private *priv)
-{
-	if (priv->tx_tfm_mic)
-		crypto_free_shash(priv->tx_tfm_mic);
-	if (priv->rx_tfm_mic)
-		crypto_free_shash(priv->rx_tfm_mic);
-}
-
-int orinoco_mic(struct crypto_shash *tfm_michael, u8 *key,
-		u8 *da, u8 *sa, u8 priority,
-		u8 *data, size_t data_len, u8 *mic)
-{
-	SHASH_DESC_ON_STACK(desc, tfm_michael);
-	u8 hdr[ETH_HLEN + 2]; /* size of header + padding */
-	int err;
-
-	if (tfm_michael == NULL) {
-		printk(KERN_WARNING "%s: tfm_michael == NULL\n", __func__);
-		return -1;
-	}
-
-	/* Copy header into buffer. We need the padding on the end zeroed */
-	memcpy(&hdr[0], da, ETH_ALEN);
-	memcpy(&hdr[ETH_ALEN], sa, ETH_ALEN);
-	hdr[ETH_ALEN * 2] = priority;
-	hdr[ETH_ALEN * 2 + 1] = 0;
-	hdr[ETH_ALEN * 2 + 2] = 0;
-	hdr[ETH_ALEN * 2 + 3] = 0;
-
-	desc->tfm = tfm_michael;
-
-	err = crypto_shash_setkey(tfm_michael, key, MIC_KEYLEN);
-	if (err)
-		return err;
-
-	err = crypto_shash_init(desc);
-	if (err)
-		return err;
-
-	err = crypto_shash_update(desc, hdr, sizeof(hdr));
-	if (err)
-		return err;
-
-	err = crypto_shash_update(desc, data, data_len);
-	if (err)
-		return err;
-
-	err = crypto_shash_final(desc, mic);
-	shash_desc_zero(desc);
-
-	return err;
-}
diff --git a/drivers/net/wireless/intersil/orinoco/mic.h b/drivers/net/wireless/intersil/orinoco/mic.h
deleted file mode 100644
index e8724e889219..000000000000
--- a/drivers/net/wireless/intersil/orinoco/mic.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/* Orinoco MIC helpers
- *
- * See copyright notice in main.c
- */
-#ifndef _ORINOCO_MIC_H_
-#define _ORINOCO_MIC_H_
-
-#include <linux/types.h>
-#include <crypto/hash.h>
-
-#define MICHAEL_MIC_LEN 8
-
-/* Forward declarations */
-struct orinoco_private;
-struct crypto_ahash;
-
-int orinoco_mic_init(struct orinoco_private *priv);
-void orinoco_mic_free(struct orinoco_private *priv);
-int orinoco_mic(struct crypto_shash *tfm_michael, u8 *key,
-		u8 *da, u8 *sa, u8 priority,
-		u8 *data, size_t data_len, u8 *mic);
-
-#endif /* ORINOCO_MIC_H */
diff --git a/drivers/net/wireless/intersil/orinoco/orinoco.h b/drivers/net/wireless/intersil/orinoco/orinoco.h
deleted file mode 100644
index cdd026af100b..000000000000
--- a/drivers/net/wireless/intersil/orinoco/orinoco.h
+++ /dev/null
@@ -1,251 +0,0 @@
-/* orinoco.h
- *
- * Common definitions to all pieces of the various orinoco
- * drivers
- */
-
-#ifndef _ORINOCO_H
-#define _ORINOCO_H
-
-#define DRIVER_VERSION "0.15"
-
-#include <linux/interrupt.h>
-#include <linux/suspend.h>
-#include <linux/netdevice.h>
-#include <linux/wireless.h>
-#include <net/iw_handler.h>
-#include <net/cfg80211.h>
-
-#include "hermes.h"
-
-/* To enable debug messages */
-/*#define ORINOCO_DEBUG		3*/
-
-#define WIRELESS_SPY		/* enable iwspy support */
-
-#define MAX_SCAN_LEN		4096
-
-#define ORINOCO_SEQ_LEN		8
-#define ORINOCO_MAX_KEY_SIZE	14
-#define ORINOCO_MAX_KEYS	4
-
-struct orinoco_key {
-	__le16 len;	/* always stored as little-endian */
-	char data[ORINOCO_MAX_KEY_SIZE];
-} __packed;
-
-#define TKIP_KEYLEN	16
-#define MIC_KEYLEN	8
-
-struct orinoco_tkip_key {
-	u8 tkip[TKIP_KEYLEN];
-	u8 tx_mic[MIC_KEYLEN];
-	u8 rx_mic[MIC_KEYLEN];
-};
-
-enum orinoco_alg {
-	ORINOCO_ALG_NONE,
-	ORINOCO_ALG_WEP,
-	ORINOCO_ALG_TKIP
-};
-
-enum fwtype {
-	FIRMWARE_TYPE_AGERE,
-	FIRMWARE_TYPE_INTERSIL,
-	FIRMWARE_TYPE_SYMBOL
-};
-
-struct firmware;
-
-struct orinoco_private {
-	void *card;	/* Pointer to card dependent structure */
-	struct device *dev;
-	int (*hard_reset)(struct orinoco_private *);
-	int (*stop_fw)(struct orinoco_private *, int);
-
-	struct ieee80211_supported_band band;
-	struct ieee80211_channel channels[14];
-	u32 cipher_suites[3];
-
-	/* Synchronisation stuff */
-	spinlock_t lock;
-	int hw_unavailable;
-	struct work_struct reset_work;
-
-	/* Interrupt tasklets */
-	struct tasklet_struct rx_tasklet;
-	struct list_head rx_list;
-
-	/* driver state */
-	int open;
-	u16 last_linkstatus;
-	struct work_struct join_work;
-	struct work_struct wevent_work;
-
-	/* Net device stuff */
-	struct net_device *ndev;
-	struct iw_statistics wstats;
-
-	/* Hardware control variables */
-	struct hermes hw;
-	u16 txfid;
-
-	/* Capabilities of the hardware/firmware */
-	enum fwtype firmware_type;
-	int ibss_port;
-	int nicbuf_size;
-	u16 channel_mask;
-
-	/* Boolean capabilities */
-	unsigned int has_ibss:1;
-	unsigned int has_port3:1;
-	unsigned int has_wep:1;
-	unsigned int has_big_wep:1;
-	unsigned int has_mwo:1;
-	unsigned int has_pm:1;
-	unsigned int has_preamble:1;
-	unsigned int has_sensitivity:1;
-	unsigned int has_hostscan:1;
-	unsigned int has_alt_txcntl:1;
-	unsigned int has_ext_scan:1;
-	unsigned int has_wpa:1;
-	unsigned int do_fw_download:1;
-	unsigned int broken_disableport:1;
-	unsigned int broken_monitor:1;
-	unsigned int prefer_port3:1;
-
-	/* Configuration paramaters */
-	enum nl80211_iftype iw_mode;
-	enum orinoco_alg encode_alg;
-	u16 wep_restrict, tx_key;
-	struct key_params keys[ORINOCO_MAX_KEYS];
-
-	int bitratemode;
-	char nick[IW_ESSID_MAX_SIZE + 1];
-	char desired_essid[IW_ESSID_MAX_SIZE + 1];
-	char desired_bssid[ETH_ALEN];
-	int bssid_fixed;
-	u16 frag_thresh, mwo_robust;
-	u16 channel;
-	u16 ap_density, rts_thresh;
-	u16 pm_on, pm_mcast, pm_period, pm_timeout;
-	u16 preamble;
-	u16 short_retry_limit, long_retry_limit;
-	u16 retry_lifetime;
-#ifdef WIRELESS_SPY
-	struct iw_spy_data spy_data; /* iwspy support */
-	struct iw_public_data	wireless_data;
-#endif
-
-	/* Configuration dependent variables */
-	int port_type, createibss;
-	int promiscuous, mc_count;
-
-	/* Scanning support */
-	struct cfg80211_scan_request *scan_request;
-	struct work_struct process_scan;
-	struct list_head scan_list;
-	spinlock_t scan_lock; /* protects the scan list */
-
-	/* WPA support */
-	u8 *wpa_ie;
-	int wpa_ie_len;
-
-	struct crypto_shash *rx_tfm_mic;
-	struct crypto_shash *tx_tfm_mic;
-
-	unsigned int wpa_enabled:1;
-	unsigned int tkip_cm_active:1;
-	unsigned int key_mgmt:3;
-
-#if defined(CONFIG_HERMES_CACHE_FW_ON_INIT) || defined(CONFIG_PM_SLEEP)
-	/* Cached in memory firmware to use during ->resume. */
-	const struct firmware *cached_pri_fw;
-	const struct firmware *cached_fw;
-#endif
-
-	struct notifier_block pm_notifier;
-};
-
-#ifdef ORINOCO_DEBUG
-extern int orinoco_debug;
-#define DEBUG(n, args...) do { \
-	if (orinoco_debug > (n)) \
-		printk(KERN_DEBUG args); \
-} while (0)
-#else
-#define DEBUG(n, args...) do { } while (0)
-#endif	/* ORINOCO_DEBUG */
-
-/********************************************************************/
-/* Exported prototypes                                              */
-/********************************************************************/
-
-struct orinoco_private *alloc_orinocodev(int sizeof_card, struct device *device,
-					 int (*hard_reset)(struct orinoco_private *),
-					 int (*stop_fw)(struct orinoco_private *, int));
-void free_orinocodev(struct orinoco_private *priv);
-int orinoco_init(struct orinoco_private *priv);
-int orinoco_if_add(struct orinoco_private *priv, unsigned long base_addr,
-		   unsigned int irq, const struct net_device_ops *ops);
-void orinoco_if_del(struct orinoco_private *priv);
-int orinoco_up(struct orinoco_private *priv);
-void orinoco_down(struct orinoco_private *priv);
-irqreturn_t orinoco_interrupt(int irq, void *dev_id);
-
-void __orinoco_ev_info(struct net_device *dev, struct hermes *hw);
-void __orinoco_ev_rx(struct net_device *dev, struct hermes *hw);
-
-int orinoco_process_xmit_skb(struct sk_buff *skb,
-			     struct net_device *dev,
-			     struct orinoco_private *priv,
-			     int *tx_control,
-			     u8 *mic);
-
-/* Common ndo functions exported for reuse by orinoco_usb */
-int orinoco_open(struct net_device *dev);
-int orinoco_stop(struct net_device *dev);
-void orinoco_set_multicast_list(struct net_device *dev);
-int orinoco_change_mtu(struct net_device *dev, int new_mtu);
-void orinoco_tx_timeout(struct net_device *dev, unsigned int txqueue);
-
-/********************************************************************/
-/* Locking and synchronization functions                            */
-/********************************************************************/
-
-static inline int orinoco_lock(struct orinoco_private *priv,
-			       unsigned long *flags)
-{
-	priv->hw.ops->lock_irqsave(&priv->lock, flags);
-	if (priv->hw_unavailable) {
-		DEBUG(1, "orinoco_lock() called with hw_unavailable (dev=%p)\n",
-		       priv->ndev);
-		priv->hw.ops->unlock_irqrestore(&priv->lock, flags);
-		return -EBUSY;
-	}
-	return 0;
-}
-
-static inline void orinoco_unlock(struct orinoco_private *priv,
-				  unsigned long *flags)
-{
-	priv->hw.ops->unlock_irqrestore(&priv->lock, flags);
-}
-
-static inline void orinoco_lock_irq(struct orinoco_private *priv)
-{
-	priv->hw.ops->lock_irq(&priv->lock);
-}
-
-static inline void orinoco_unlock_irq(struct orinoco_private *priv)
-{
-	priv->hw.ops->unlock_irq(&priv->lock);
-}
-
-/*** Navigate from net_device to orinoco_private ***/
-static inline struct orinoco_private *ndev_priv(struct net_device *dev)
-{
-	struct wireless_dev *wdev = netdev_priv(dev);
-	return wdev_priv(wdev);
-}
-#endif /* _ORINOCO_H */
diff --git a/drivers/net/wireless/intersil/orinoco/orinoco_cs.c b/drivers/net/wireless/intersil/orinoco/orinoco_cs.c
deleted file mode 100644
index 03bfd2482656..000000000000
--- a/drivers/net/wireless/intersil/orinoco/orinoco_cs.c
+++ /dev/null
@@ -1,350 +0,0 @@
-/* orinoco_cs.c (formerly known as dldwd_cs.c)
- *
- * A driver for "Hermes" chipset based PCMCIA wireless adaptors, such
- * as the Lucent WavelanIEEE/Orinoco cards and their OEM (Cabletron/
- * EnteraSys RoamAbout 802.11, ELSA Airlancer, Melco Buffalo and others).
- * It should also be usable on various Prism II based cards such as the
- * Linksys, D-Link and Farallon Skyline. It should also work on Symbol
- * cards such as the 3Com AirConnect and Ericsson WLAN.
- *
- * Copyright notice & release notes in file main.c
- */
-
-#define DRIVER_NAME "orinoco_cs"
-#define PFX DRIVER_NAME ": "
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/delay.h>
-#include <pcmcia/cistpl.h>
-#include <pcmcia/cisreg.h>
-#include <pcmcia/ds.h>
-
-#include "orinoco.h"
-
-/********************************************************************/
-/* Module stuff							    */
-/********************************************************************/
-
-MODULE_AUTHOR("David Gibson <hermes@gibson.dropbear.id.au>");
-MODULE_DESCRIPTION("Driver for PCMCIA Lucent Orinoco,"
-		   " Prism II based and similar wireless cards");
-MODULE_LICENSE("Dual MPL/GPL");
-
-/* Module parameters */
-
-/* Some D-Link cards have buggy CIS. They do work at 5v properly, but
- * don't have any CIS entry for it. This workaround it... */
-static int ignore_cis_vcc; /* = 0 */
-module_param(ignore_cis_vcc, int, 0);
-MODULE_PARM_DESC(ignore_cis_vcc, "Allow voltage mismatch between card and socket");
-
-/********************************************************************/
-/* Data structures						    */
-/********************************************************************/
-
-/* PCMCIA specific device information (goes in the card field of
- * struct orinoco_private */
-struct orinoco_pccard {
-	struct pcmcia_device	*p_dev;
-
-	/* Used to handle hard reset */
-	/* yuck, we need this hack to work around the insanity of the
-	 * PCMCIA layer */
-	unsigned long hard_reset_in_progress;
-};
-
-
-/********************************************************************/
-/* Function prototypes						    */
-/********************************************************************/
-
-static int orinoco_cs_config(struct pcmcia_device *link);
-static void orinoco_cs_release(struct pcmcia_device *link);
-static void orinoco_cs_detach(struct pcmcia_device *p_dev);
-
-/********************************************************************/
-/* Device methods						    */
-/********************************************************************/
-
-static int
-orinoco_cs_hard_reset(struct orinoco_private *priv)
-{
-	struct orinoco_pccard *card = priv->card;
-	struct pcmcia_device *link = card->p_dev;
-	int err;
-
-	/* We need atomic ops here, because we're not holding the lock */
-	set_bit(0, &card->hard_reset_in_progress);
-
-	err = pcmcia_reset_card(link->socket);
-	if (err)
-		return err;
-
-	msleep(100);
-	clear_bit(0, &card->hard_reset_in_progress);
-
-	return 0;
-}
-
-/********************************************************************/
-/* PCMCIA stuff							    */
-/********************************************************************/
-
-static int
-orinoco_cs_probe(struct pcmcia_device *link)
-{
-	struct orinoco_private *priv;
-	struct orinoco_pccard *card;
-	int ret;
-
-	priv = alloc_orinocodev(sizeof(*card), &link->dev,
-				orinoco_cs_hard_reset, NULL);
-	if (!priv)
-		return -ENOMEM;
-	card = priv->card;
-
-	/* Link both structures together */
-	card->p_dev = link;
-	link->priv = priv;
-
-	ret = orinoco_cs_config(link);
-	if (ret)
-		goto err_free_orinocodev;
-
-	return 0;
-
-err_free_orinocodev:
-	free_orinocodev(priv);
-	return ret;
-}
-
-static void orinoco_cs_detach(struct pcmcia_device *link)
-{
-	struct orinoco_private *priv = link->priv;
-
-	orinoco_if_del(priv);
-
-	orinoco_cs_release(link);
-
-	wiphy_unregister(priv_to_wiphy(priv));
-	free_orinocodev(priv);
-}				/* orinoco_cs_detach */
-
-static int orinoco_cs_config_check(struct pcmcia_device *p_dev, void *priv_data)
-{
-	if (p_dev->config_index == 0)
-		return -EINVAL;
-
-	return pcmcia_request_io(p_dev);
-};
-
-static int
-orinoco_cs_config(struct pcmcia_device *link)
-{
-	struct orinoco_private *priv = link->priv;
-	struct hermes *hw = &priv->hw;
-	int ret;
-	void __iomem *mem;
-
-	link->config_flags |= CONF_AUTO_SET_VPP | CONF_AUTO_CHECK_VCC |
-		CONF_AUTO_SET_IO | CONF_ENABLE_IRQ;
-	if (ignore_cis_vcc)
-		link->config_flags &= ~CONF_AUTO_CHECK_VCC;
-	ret = pcmcia_loop_config(link, orinoco_cs_config_check, NULL);
-	if (ret) {
-		if (!ignore_cis_vcc)
-			printk(KERN_ERR PFX "GetNextTuple(): No matching "
-			       "CIS configuration.  Maybe you need the "
-			       "ignore_cis_vcc=1 parameter.\n");
-		goto failed;
-	}
-
-	mem = ioport_map(link->resource[0]->start,
-			resource_size(link->resource[0]));
-	if (!mem)
-		goto failed;
-
-	/* We initialize the hermes structure before completing PCMCIA
-	 * configuration just in case the interrupt handler gets
-	 * called. */
-	hermes_struct_init(hw, mem, HERMES_16BIT_REGSPACING);
-
-	ret = pcmcia_request_irq(link, orinoco_interrupt);
-	if (ret)
-		goto failed;
-
-	ret = pcmcia_enable_device(link);
-	if (ret)
-		goto failed;
-
-	/* Initialise the main driver */
-	if (orinoco_init(priv) != 0) {
-		printk(KERN_ERR PFX "orinoco_init() failed\n");
-		goto failed;
-	}
-
-	/* Register an interface with the stack */
-	if (orinoco_if_add(priv, link->resource[0]->start,
-			   link->irq, NULL) != 0) {
-		printk(KERN_ERR PFX "orinoco_if_add() failed\n");
-		goto failed;
-	}
-
-	return 0;
-
- failed:
-	orinoco_cs_release(link);
-	return -ENODEV;
-}				/* orinoco_cs_config */
-
-static void
-orinoco_cs_release(struct pcmcia_device *link)
-{
-	struct orinoco_private *priv = link->priv;
-	unsigned long flags;
-
-	/* We're committed to taking the device away now, so mark the
-	 * hardware as unavailable */
-	priv->hw.ops->lock_irqsave(&priv->lock, &flags);
-	priv->hw_unavailable++;
-	priv->hw.ops->unlock_irqrestore(&priv->lock, &flags);
-
-	pcmcia_disable_device(link);
-	if (priv->hw.iobase)
-		ioport_unmap(priv->hw.iobase);
-}				/* orinoco_cs_release */
-
-static int orinoco_cs_suspend(struct pcmcia_device *link)
-{
-	struct orinoco_private *priv = link->priv;
-	struct orinoco_pccard *card = priv->card;
-
-	/* This is probably racy, but I can't think of
-	   a better way, short of rewriting the PCMCIA
-	   layer to not suck :-( */
-	if (!test_bit(0, &card->hard_reset_in_progress))
-		orinoco_down(priv);
-
-	return 0;
-}
-
-static int orinoco_cs_resume(struct pcmcia_device *link)
-{
-	struct orinoco_private *priv = link->priv;
-	struct orinoco_pccard *card = priv->card;
-	int err = 0;
-
-	if (!test_bit(0, &card->hard_reset_in_progress))
-		err = orinoco_up(priv);
-
-	return err;
-}
-
-
-/********************************************************************/
-/* Module initialization					    */
-/********************************************************************/
-
-static const struct pcmcia_device_id orinoco_cs_ids[] = {
-	PCMCIA_DEVICE_MANF_CARD(0x0101, 0x0777), /* 3Com AirConnect PCI 777A */
-	PCMCIA_DEVICE_MANF_CARD(0x016b, 0x0001), /* Ericsson WLAN Card C11 */
-	PCMCIA_DEVICE_MANF_CARD(0x01eb, 0x080a), /* Nortel Networks eMobility 802.11 Wireless Adapter */
-	PCMCIA_DEVICE_MANF_CARD(0x0261, 0x0002), /* AirWay 802.11 Adapter (PCMCIA) */
-	PCMCIA_DEVICE_MANF_CARD(0x0268, 0x0001), /* ARtem Onair */
-	PCMCIA_DEVICE_MANF_CARD(0x0268, 0x0003), /* ARtem Onair Comcard 11 */
-	PCMCIA_DEVICE_MANF_CARD(0x026f, 0x0305), /* Buffalo WLI-PCM-S11 */
-	PCMCIA_DEVICE_MANF_CARD(0x02aa, 0x0002), /* ASUS SpaceLink WL-100 */
-	PCMCIA_DEVICE_MANF_CARD(0x02ac, 0x0002), /* SpeedStream SS1021 Wireless Adapter */
-	PCMCIA_DEVICE_MANF_CARD(0x02ac, 0x3021), /* SpeedStream Wireless Adapter */
-	PCMCIA_DEVICE_MANF_CARD(0x14ea, 0xb001), /* PLANEX RoadLannerWave GW-NS11H */
-	PCMCIA_DEVICE_PROD_ID12("3Com", "3CRWE737A AirConnect Wireless LAN PC Card", 0x41240e5b, 0x56010af3),
-	PCMCIA_DEVICE_PROD_ID12("Allied Telesyn", "AT-WCL452 Wireless PCMCIA Radio", 0x5cd01705, 0x4271660f),
-	PCMCIA_DEVICE_PROD_ID12("ASUS", "802_11B_CF_CARD_25", 0x78fc06ee, 0x45a50c1e),
-	PCMCIA_DEVICE_PROD_ID12("ASUS", "802_11b_PC_CARD_25", 0x78fc06ee, 0xdb9aa842),
-	PCMCIA_DEVICE_PROD_ID12("Avaya Communication", "Avaya Wireless PC Card", 0xd8a43b78, 0x0d341169),
-	PCMCIA_DEVICE_PROD_ID12("BENQ", "AWL100 PCMCIA ADAPTER", 0x35dadc74, 0x01f7fedb),
-	PCMCIA_DEVICE_PROD_ID12("Cabletron", "RoamAbout 802.11 DS", 0x32d445f5, 0xedeffd90),
-	PCMCIA_DEVICE_PROD_ID12("D-Link Corporation", "D-Link DWL-650H 11Mbps WLAN Adapter", 0xef544d24, 0xcd8ea916),
-	PCMCIA_DEVICE_PROD_ID12("ELSA", "AirLancer MC-11", 0x4507a33a, 0xef54f0e3),
-	PCMCIA_DEVICE_PROD_ID12("HyperLink", "Wireless PC Card 11Mbps", 0x56cc3f1a, 0x0bcf220c),
-	PCMCIA_DEVICE_PROD_ID12("Intel", "PRO/Wireless 2011 LAN PC Card", 0x816cc815, 0x07f58077),
-	PCMCIA_DEVICE_PROD_ID12("LeArtery", "SYNCBYAIR 11Mbps Wireless LAN PC Card", 0x7e3b326a, 0x49893e92),
-	PCMCIA_DEVICE_PROD_ID12("Lucent Technologies", "WaveLAN/IEEE", 0x23eb9949, 0xc562e72a),
-	PCMCIA_DEVICE_PROD_ID12("MELCO", "WLI-PCM-L11", 0x481e0094, 0x7360e410),
-	PCMCIA_DEVICE_PROD_ID12("MELCO", "WLI-PCM-L11G", 0x481e0094, 0xf57ca4b3),
-	PCMCIA_DEVICE_PROD_ID12("NCR", "WaveLAN/IEEE", 0x24358cd4, 0xc562e72a),
-	PCMCIA_DEVICE_PROD_ID12("Nortel Networks", "emobility 802.11 Wireless LAN PC Card", 0x2d617ea0, 0x88cd5767),
-	PCMCIA_DEVICE_PROD_ID12("OTC", "Wireless AirEZY 2411-PCC WLAN Card", 0x4ac44287, 0x235a6bed),
-	PCMCIA_DEVICE_PROD_ID12("PROXIM", "LAN PC CARD HARMONY 80211B", 0xc6536a5e, 0x090c3cd9),
-	PCMCIA_DEVICE_PROD_ID12("PROXIM", "LAN PCI CARD HARMONY 80211B", 0xc6536a5e, 0x9f494e26),
-	PCMCIA_DEVICE_PROD_ID12("SAMSUNG", "11Mbps WLAN Card", 0x43d74cb4, 0x579bd91b),
-	PCMCIA_DEVICE_PROD_ID12("Symbol Technologies", "LA4111 Spectrum24 Wireless LAN PC Card", 0x3f02b4d6, 0x3663cb0e),
-	PCMCIA_DEVICE_MANF_CARD_PROD_ID3(0x0156, 0x0002, "Version 01.01", 0xd27deb1a), /* Lucent Orinoco */
-#ifdef CONFIG_HERMES_PRISM
-	/* Only entries that certainly identify Prism chipset */
-	PCMCIA_DEVICE_MANF_CARD(0x000b, 0x7100), /* SonicWALL Long Range Wireless Card */
-	PCMCIA_DEVICE_MANF_CARD(0x000b, 0x7300), /* Sohoware NCP110, Philips 802.11b */
-	PCMCIA_DEVICE_MANF_CARD(0x0089, 0x0002), /* AnyPoint(TM) Wireless II PC Card */
-	PCMCIA_DEVICE_MANF_CARD(0x0126, 0x8000), /* PROXIM RangeLAN-DS/LAN PC CARD */
-	PCMCIA_DEVICE_MANF_CARD(0x0138, 0x0002), /* Compaq WL100 11 Mbps Wireless Adapter */
-	PCMCIA_DEVICE_MANF_CARD(0x01ff, 0x0008), /* Intermec MobileLAN 11Mbps 802.11b WLAN Card */
-	PCMCIA_DEVICE_MANF_CARD(0x0250, 0x0002), /* Samsung SWL2000-N 11Mb/s WLAN Card */
-	PCMCIA_DEVICE_MANF_CARD(0x0274, 0x1612), /* Linksys WPC11 Version 2.5 */
-	PCMCIA_DEVICE_MANF_CARD(0x0274, 0x1613), /* Linksys WPC11 Version 3 */
-	PCMCIA_DEVICE_MANF_CARD(0x028a, 0x0002), /* Compaq HNW-100 11 Mbps Wireless Adapter */
-	PCMCIA_DEVICE_MANF_CARD(0x028a, 0x0673), /* Linksys WCF12 Wireless CompactFlash Card */
-	PCMCIA_DEVICE_MANF_CARD(0x50c2, 0x7300), /* Airvast WN-100 */
-	PCMCIA_DEVICE_MANF_CARD(0x9005, 0x0021), /* Adaptec Ultra Wireless ANW-8030 */
-	PCMCIA_DEVICE_MANF_CARD(0xc001, 0x0008), /* CONTEC FLEXSCAN/FX-DDS110-PCC */
-	PCMCIA_DEVICE_MANF_CARD(0xc250, 0x0002), /* Conceptronic CON11Cpro, EMTAC A2424i */
-	PCMCIA_DEVICE_MANF_CARD(0xd601, 0x0002), /* Safeway 802.11b, ZCOMAX AirRunner/XI-300 */
-	PCMCIA_DEVICE_MANF_CARD(0xd601, 0x0005), /* D-Link DCF660, Sandisk Connect SDWCFB-000 */
-	PCMCIA_DEVICE_PROD_ID123("Instant Wireless ", " Network PC CARD", "Version 01.02", 0x11d901af, 0x6e9bd926, 0x4b74baa0),
-	PCMCIA_DEVICE_PROD_ID12("ACTIONTEC", "PRISM Wireless LAN PC Card", 0x393089da, 0xa71e69d5),
-	PCMCIA_DEVICE_PROD_ID12("Addtron", "AWP-100 Wireless PCMCIA", 0xe6ec52ce, 0x08649af2),
-	PCMCIA_DEVICE_PROD_ID12("BUFFALO", "WLI-CF-S11G", 0x2decece3, 0x82067c18),
-	PCMCIA_DEVICE_PROD_ID12("BUFFALO", "WLI-PCM-L11G", 0x2decece3, 0xf57ca4b3),
-	PCMCIA_DEVICE_PROD_ID12("Compaq", "WL200_11Mbps_Wireless_PCI_Card", 0x54f7c49c, 0x15a75e5b),
-	PCMCIA_DEVICE_PROD_ID12("corega K.K.", "Wireless LAN PCC-11", 0x5261440f, 0xa6405584),
-	PCMCIA_DEVICE_PROD_ID12("corega K.K.", "Wireless LAN PCCA-11", 0x5261440f, 0xdf6115f9),
-	PCMCIA_DEVICE_PROD_ID12("corega_K.K.", "Wireless_LAN_PCCB-11", 0x29e33311, 0xee7a27ae),
-	PCMCIA_DEVICE_PROD_ID12("Digital Data Communications", "WPC-0100", 0xfdd73470, 0xe0b6f146),
-	PCMCIA_DEVICE_PROD_ID12("D", "Link DRC-650 11Mbps WLAN Card", 0x71b18589, 0xf144e3ac),
-	PCMCIA_DEVICE_PROD_ID12("D", "Link DWL-650 11Mbps WLAN Card", 0x71b18589, 0xb6f1b0ab),
-	PCMCIA_DEVICE_PROD_ID12(" ", "IEEE 802.11 Wireless LAN/PC Card", 0x3b6e20c8, 0xefccafe9),
-	PCMCIA_DEVICE_PROD_ID12("INTERSIL", "HFA384x/IEEE", 0x74c5e40d, 0xdb472a18),
-	PCMCIA_DEVICE_PROD_ID12("INTERSIL", "I-GATE 11M PC Card / PC Card plus", 0x74c5e40d, 0x8304ff77),
-	PCMCIA_DEVICE_PROD_ID12("Intersil", "PRISM 2_5 PCMCIA ADAPTER", 0x4b801a17, 0x6345a0bf),
-	PCMCIA_DEVICE_PROD_ID12("Linksys", "Wireless CompactFlash Card", 0x0733cc81, 0x0c52f395),
-	PCMCIA_DEVICE_PROD_ID12("Microsoft", "Wireless Notebook Adapter MN-520", 0x5961bf85, 0x6eec8c01),
-	PCMCIA_DEVICE_PROD_ID12("NETGEAR MA401RA Wireless PC", "Card", 0x0306467f, 0x9762e8f1),
-	PCMCIA_DEVICE_PROD_ID12("NETGEAR MA401 Wireless PC", "Card", 0xa37434e9, 0x9762e8f1),
-	PCMCIA_DEVICE_PROD_ID12("OEM", "PRISM2 IEEE 802.11 PC-Card", 0xfea54c90, 0x48f2bdd6),
-	PCMCIA_DEVICE_PROD_ID12("PLANEX", "GeoWave/GW-CF110", 0x209f40ab, 0xd9715264),
-	PCMCIA_DEVICE_PROD_ID12("PLANEX", "GeoWave/GW-NS110", 0x209f40ab, 0x46263178),
-	PCMCIA_DEVICE_PROD_ID12("SMC", "SMC2532W-B EliteConnect Wireless Adapter", 0xc4f8b18b, 0x196bd757),
-	PCMCIA_DEVICE_PROD_ID12("SMC", "SMC2632W", 0xc4f8b18b, 0x474a1f2a),
-	PCMCIA_DEVICE_PROD_ID12("ZoomAir 11Mbps High", "Rate wireless Networking", 0x273fe3db, 0x32a1eaee),
-	PCMCIA_DEVICE_PROD_ID3("HFA3863", 0x355cb092),
-	PCMCIA_DEVICE_PROD_ID3("ISL37100P", 0x630d52b2),
-	PCMCIA_DEVICE_PROD_ID3("ISL37101P-10", 0xdd97a26b),
-	PCMCIA_DEVICE_PROD_ID3("ISL37300P", 0xc9049a39),
-
-	/* This may be Agere or Intersil Firmware */
-	PCMCIA_DEVICE_MANF_CARD(0x0156, 0x0002),
-#endif
-	PCMCIA_DEVICE_NULL,
-};
-MODULE_DEVICE_TABLE(pcmcia, orinoco_cs_ids);
-
-static struct pcmcia_driver orinoco_driver = {
-	.owner		= THIS_MODULE,
-	.name		= DRIVER_NAME,
-	.probe		= orinoco_cs_probe,
-	.remove		= orinoco_cs_detach,
-	.id_table       = orinoco_cs_ids,
-	.suspend	= orinoco_cs_suspend,
-	.resume		= orinoco_cs_resume,
-};
-module_pcmcia_driver(orinoco_driver);
diff --git a/drivers/net/wireless/intersil/orinoco/orinoco_nortel.c b/drivers/net/wireless/intersil/orinoco/orinoco_nortel.c
deleted file mode 100644
index 18bd0d9876c2..000000000000
--- a/drivers/net/wireless/intersil/orinoco/orinoco_nortel.c
+++ /dev/null
@@ -1,314 +0,0 @@
-/* orinoco_nortel.c
- *
- * Driver for Prism II devices which would usually be driven by orinoco_cs,
- * but are connected to the PCI bus by a PCI-to-PCMCIA adapter used in
- * Nortel emobility, Symbol LA-4113 and Symbol LA-4123.
- *
- * Copyright (C) 2002 Tobias Hoffmann
- *           (C) 2003 Christoph Jungegger <disdos@traum404.de>
- *
- * Some of this code is borrowed from orinoco_plx.c
- *	Copyright (C) 2001 Daniel Barlow
- * Some of this code is borrowed from orinoco_pci.c
- *  Copyright (C) 2001 Jean Tourrilhes
- * Some of this code is "inspired" by linux-wlan-ng-0.1.10, but nothing
- * has been copied from it. linux-wlan-ng-0.1.10 is originally :
- *	Copyright (C) 1999 AbsoluteValue Systems, Inc.  All Rights Reserved.
- *
- * The contents of this file are subject to the Mozilla Public License
- * Version 1.1 (the "License"); you may not use this file except in
- * compliance with the License. You may obtain a copy of the License
- * at http://www.mozilla.org/MPL/
- *
- * Software distributed under the License is distributed on an "AS IS"
- * basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See
- * the License for the specific language governing rights and
- * limitations under the License.
- *
- * Alternatively, the contents of this file may be used under the
- * terms of the GNU General Public License version 2 (the "GPL"), in
- * which case the provisions of the GPL are applicable instead of the
- * above.  If you wish to allow the use of your version of this file
- * only under the terms of the GPL and not to allow others to use your
- * version of this file under the MPL, indicate your decision by
- * deleting the provisions above and replace them with the notice and
- * other provisions required by the GPL.  If you do not delete the
- * provisions above, a recipient may use your version of this file
- * under either the MPL or the GPL.
- */
-
-#define DRIVER_NAME "orinoco_nortel"
-#define PFX DRIVER_NAME ": "
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/pci.h>
-#include <pcmcia/cisreg.h>
-
-#include "orinoco.h"
-#include "orinoco_pci.h"
-
-#define COR_OFFSET    (0xe0)	/* COR attribute offset of Prism2 PC card */
-#define COR_VALUE     (COR_LEVEL_REQ | COR_FUNC_ENA)	/* Enable PC card with interrupt in level trigger */
-
-
-/*
- * Do a soft reset of the card using the Configuration Option Register
- * We need this to get going...
- * This is the part of the code that is strongly inspired from wlan-ng
- *
- * Note bis : Don't try to access HERMES_CMD during the reset phase.
- * It just won't work !
- */
-static int orinoco_nortel_cor_reset(struct orinoco_private *priv)
-{
-	struct orinoco_pci_card *card = priv->card;
-
-	/* Assert the reset until the card notices */
-	iowrite16(8, card->bridge_io + 2);
-	ioread16(card->attr_io + COR_OFFSET);
-	iowrite16(0x80, card->attr_io + COR_OFFSET);
-	mdelay(1);
-
-	/* Give time for the card to recover from this hard effort */
-	iowrite16(0, card->attr_io + COR_OFFSET);
-	iowrite16(0, card->attr_io + COR_OFFSET);
-	mdelay(1);
-
-	/* Set COR as usual */
-	iowrite16(COR_VALUE, card->attr_io + COR_OFFSET);
-	iowrite16(COR_VALUE, card->attr_io + COR_OFFSET);
-	mdelay(1);
-
-	iowrite16(0x228, card->bridge_io + 2);
-
-	return 0;
-}
-
-static int orinoco_nortel_hw_init(struct orinoco_pci_card *card)
-{
-	int i;
-	u32 reg;
-
-	/* Setup bridge */
-	if (ioread16(card->bridge_io) & 1) {
-		printk(KERN_ERR PFX "brg1 answer1 wrong\n");
-		return -EBUSY;
-	}
-	iowrite16(0x118, card->bridge_io + 2);
-	iowrite16(0x108, card->bridge_io + 2);
-	mdelay(30);
-	iowrite16(0x8, card->bridge_io + 2);
-	for (i = 0; i < 30; i++) {
-		mdelay(30);
-		if (ioread16(card->bridge_io) & 0x10)
-			break;
-	}
-	if (i == 30) {
-		printk(KERN_ERR PFX "brg1 timed out\n");
-		return -EBUSY;
-	}
-	if (ioread16(card->attr_io + COR_OFFSET) & 1) {
-		printk(KERN_ERR PFX "brg2 answer1 wrong\n");
-		return -EBUSY;
-	}
-	if (ioread16(card->attr_io + COR_OFFSET + 2) & 1) {
-		printk(KERN_ERR PFX "brg2 answer2 wrong\n");
-		return -EBUSY;
-	}
-	if (ioread16(card->attr_io + COR_OFFSET + 4) & 1) {
-		printk(KERN_ERR PFX "brg2 answer3 wrong\n");
-		return -EBUSY;
-	}
-
-	/* Set the PCMCIA COR register */
-	iowrite16(COR_VALUE, card->attr_io + COR_OFFSET);
-	mdelay(1);
-	reg = ioread16(card->attr_io + COR_OFFSET);
-	if (reg != COR_VALUE) {
-		printk(KERN_ERR PFX "Error setting COR value (reg=%x)\n",
-		       reg);
-		return -EBUSY;
-	}
-
-	/* Set LEDs */
-	iowrite16(1, card->bridge_io + 10);
-	return 0;
-}
-
-static int orinoco_nortel_init_one(struct pci_dev *pdev,
-				   const struct pci_device_id *ent)
-{
-	int err;
-	struct orinoco_private *priv;
-	struct orinoco_pci_card *card;
-	void __iomem *hermes_io, *bridge_io, *attr_io;
-
-	err = pci_enable_device(pdev);
-	if (err) {
-		printk(KERN_ERR PFX "Cannot enable PCI device\n");
-		return err;
-	}
-
-	err = pci_request_regions(pdev, DRIVER_NAME);
-	if (err) {
-		printk(KERN_ERR PFX "Cannot obtain PCI resources\n");
-		goto fail_resources;
-	}
-
-	bridge_io = pci_iomap(pdev, 0, 0);
-	if (!bridge_io) {
-		printk(KERN_ERR PFX "Cannot map bridge registers\n");
-		err = -EIO;
-		goto fail_map_bridge;
-	}
-
-	attr_io = pci_iomap(pdev, 1, 0);
-	if (!attr_io) {
-		printk(KERN_ERR PFX "Cannot map PCMCIA attributes\n");
-		err = -EIO;
-		goto fail_map_attr;
-	}
-
-	hermes_io = pci_iomap(pdev, 2, 0);
-	if (!hermes_io) {
-		printk(KERN_ERR PFX "Cannot map chipset registers\n");
-		err = -EIO;
-		goto fail_map_hermes;
-	}
-
-	/* Allocate network device */
-	priv = alloc_orinocodev(sizeof(*card), &pdev->dev,
-				orinoco_nortel_cor_reset, NULL);
-	if (!priv) {
-		printk(KERN_ERR PFX "Cannot allocate network device\n");
-		err = -ENOMEM;
-		goto fail_alloc;
-	}
-
-	card = priv->card;
-	card->bridge_io = bridge_io;
-	card->attr_io = attr_io;
-
-	hermes_struct_init(&priv->hw, hermes_io, HERMES_16BIT_REGSPACING);
-
-	err = request_irq(pdev->irq, orinoco_interrupt, IRQF_SHARED,
-			  DRIVER_NAME, priv);
-	if (err) {
-		printk(KERN_ERR PFX "Cannot allocate IRQ %d\n", pdev->irq);
-		err = -EBUSY;
-		goto fail_irq;
-	}
-
-	err = orinoco_nortel_hw_init(card);
-	if (err) {
-		printk(KERN_ERR PFX "Hardware initialization failed\n");
-		goto fail;
-	}
-
-	err = orinoco_nortel_cor_reset(priv);
-	if (err) {
-		printk(KERN_ERR PFX "Initial reset failed\n");
-		goto fail;
-	}
-
-	err = orinoco_init(priv);
-	if (err) {
-		printk(KERN_ERR PFX "orinoco_init() failed\n");
-		goto fail;
-	}
-
-	err = orinoco_if_add(priv, 0, 0, NULL);
-	if (err) {
-		printk(KERN_ERR PFX "orinoco_if_add() failed\n");
-		goto fail_wiphy;
-	}
-
-	pci_set_drvdata(pdev, priv);
-
-	return 0;
-
- fail_wiphy:
-	wiphy_unregister(priv_to_wiphy(priv));
- fail:
-	free_irq(pdev->irq, priv);
-
- fail_irq:
-	free_orinocodev(priv);
-
- fail_alloc:
-	pci_iounmap(pdev, hermes_io);
-
- fail_map_hermes:
-	pci_iounmap(pdev, attr_io);
-
- fail_map_attr:
-	pci_iounmap(pdev, bridge_io);
-
- fail_map_bridge:
-	pci_release_regions(pdev);
-
- fail_resources:
-	pci_disable_device(pdev);
-
-	return err;
-}
-
-static void orinoco_nortel_remove_one(struct pci_dev *pdev)
-{
-	struct orinoco_private *priv = pci_get_drvdata(pdev);
-	struct orinoco_pci_card *card = priv->card;
-
-	/* Clear LEDs */
-	iowrite16(0, card->bridge_io + 10);
-
-	orinoco_if_del(priv);
-	wiphy_unregister(priv_to_wiphy(priv));
-	free_irq(pdev->irq, priv);
-	free_orinocodev(priv);
-	pci_iounmap(pdev, priv->hw.iobase);
-	pci_iounmap(pdev, card->attr_io);
-	pci_iounmap(pdev, card->bridge_io);
-	pci_release_regions(pdev);
-	pci_disable_device(pdev);
-}
-
-static const struct pci_device_id orinoco_nortel_id_table[] = {
-	/* Nortel emobility PCI */
-	{0x126c, 0x8030, PCI_ANY_ID, PCI_ANY_ID,},
-	/* Symbol LA-4123 PCI */
-	{0x1562, 0x0001, PCI_ANY_ID, PCI_ANY_ID,},
-	{0,},
-};
-
-MODULE_DEVICE_TABLE(pci, orinoco_nortel_id_table);
-
-static struct pci_driver orinoco_nortel_driver = {
-	.name		= DRIVER_NAME,
-	.id_table	= orinoco_nortel_id_table,
-	.probe		= orinoco_nortel_init_one,
-	.remove		= orinoco_nortel_remove_one,
-	.driver.pm	= &orinoco_pci_pm_ops,
-};
-
-static char version[] __initdata = DRIVER_NAME " " DRIVER_VERSION
-	" (Tobias Hoffmann & Christoph Jungegger <disdos@traum404.de>)";
-MODULE_AUTHOR("Christoph Jungegger <disdos@traum404.de>");
-MODULE_DESCRIPTION("Driver for wireless LAN cards using the Nortel PCI bridge");
-MODULE_LICENSE("Dual MPL/GPL");
-
-static int __init orinoco_nortel_init(void)
-{
-	printk(KERN_DEBUG "%s\n", version);
-	return pci_register_driver(&orinoco_nortel_driver);
-}
-
-static void __exit orinoco_nortel_exit(void)
-{
-	pci_unregister_driver(&orinoco_nortel_driver);
-}
-
-module_init(orinoco_nortel_init);
-module_exit(orinoco_nortel_exit);
diff --git a/drivers/net/wireless/intersil/orinoco/orinoco_pci.c b/drivers/net/wireless/intersil/orinoco/orinoco_pci.c
deleted file mode 100644
index 7e3a6dd60c15..000000000000
--- a/drivers/net/wireless/intersil/orinoco/orinoco_pci.c
+++ /dev/null
@@ -1,257 +0,0 @@
-/* orinoco_pci.c
- *
- * Driver for Prism 2.5/3 devices that have a direct PCI interface
- * (i.e. these are not PCMCIA cards in a PCMCIA-to-PCI bridge).
- * The card contains only one PCI region, which contains all the usual
- * hermes registers, as well as the COR register.
- *
- * Current maintainers are:
- *	Pavel Roskin <proski AT gnu.org>
- * and	David Gibson <hermes AT gibson.dropbear.id.au>
- *
- * Some of this code is borrowed from orinoco_plx.c
- *	Copyright (C) 2001 Daniel Barlow <dan AT telent.net>
- * Some of this code is "inspired" by linux-wlan-ng-0.1.10, but nothing
- * has been copied from it. linux-wlan-ng-0.1.10 is originally :
- *	Copyright (C) 1999 AbsoluteValue Systems, Inc.  All Rights Reserved.
- * This file originally written by:
- *	Copyright (C) 2001 Jean Tourrilhes <jt AT hpl.hp.com>
- * And is now maintained by:
- *	(C) Copyright David Gibson, IBM Corp. 2002-2003.
- *
- * The contents of this file are subject to the Mozilla Public License
- * Version 1.1 (the "License"); you may not use this file except in
- * compliance with the License. You may obtain a copy of the License
- * at http://www.mozilla.org/MPL/
- *
- * Software distributed under the License is distributed on an "AS IS"
- * basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See
- * the License for the specific language governing rights and
- * limitations under the License.
- *
- * Alternatively, the contents of this file may be used under the
- * terms of the GNU General Public License version 2 (the "GPL"), in
- * which case the provisions of the GPL are applicable instead of the
- * above.  If you wish to allow the use of your version of this file
- * only under the terms of the GPL and not to allow others to use your
- * version of this file under the MPL, indicate your decision by
- * deleting the provisions above and replace them with the notice and
- * other provisions required by the GPL.  If you do not delete the
- * provisions above, a recipient may use your version of this file
- * under either the MPL or the GPL.
- */
-
-#define DRIVER_NAME "orinoco_pci"
-#define PFX DRIVER_NAME ": "
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/pci.h>
-
-#include "orinoco.h"
-#include "orinoco_pci.h"
-
-/* Offset of the COR register of the PCI card */
-#define HERMES_PCI_COR		(0x26)
-
-/* Bitmask to reset the card */
-#define HERMES_PCI_COR_MASK	(0x0080)
-
-/* Magic timeouts for doing the reset.
- * Those times are straight from wlan-ng, and it is claimed that they
- * are necessary. Alan will kill me. Take your time and grab a coffee. */
-#define HERMES_PCI_COR_ONT	(250)		/* ms */
-#define HERMES_PCI_COR_OFFT	(500)		/* ms */
-#define HERMES_PCI_COR_BUSYT	(500)		/* ms */
-
-/*
- * Do a soft reset of the card using the Configuration Option Register
- * We need this to get going...
- * This is the part of the code that is strongly inspired from wlan-ng
- *
- * Note : This code is done with irq enabled. This mean that many
- * interrupts will occur while we are there. This is why we use the
- * jiffies to regulate time instead of a straight mdelay(). Usually we
- * need only around 245 iteration of the loop to do 250 ms delay.
- *
- * Note bis : Don't try to access HERMES_CMD during the reset phase.
- * It just won't work !
- */
-static int orinoco_pci_cor_reset(struct orinoco_private *priv)
-{
-	struct hermes *hw = &priv->hw;
-	unsigned long timeout;
-	u16 reg;
-
-	/* Assert the reset until the card notices */
-	hermes_write_regn(hw, PCI_COR, HERMES_PCI_COR_MASK);
-	mdelay(HERMES_PCI_COR_ONT);
-
-	/* Give time for the card to recover from this hard effort */
-	hermes_write_regn(hw, PCI_COR, 0x0000);
-	mdelay(HERMES_PCI_COR_OFFT);
-
-	/* The card is ready when it's no longer busy */
-	timeout = jiffies + msecs_to_jiffies(HERMES_PCI_COR_BUSYT);
-	reg = hermes_read_regn(hw, CMD);
-	while (time_before(jiffies, timeout) && (reg & HERMES_CMD_BUSY)) {
-		mdelay(1);
-		reg = hermes_read_regn(hw, CMD);
-	}
-
-	/* Still busy? */
-	if (reg & HERMES_CMD_BUSY) {
-		printk(KERN_ERR PFX "Busy timeout\n");
-		return -ETIMEDOUT;
-	}
-
-	return 0;
-}
-
-static int orinoco_pci_init_one(struct pci_dev *pdev,
-				const struct pci_device_id *ent)
-{
-	int err;
-	struct orinoco_private *priv;
-	struct orinoco_pci_card *card;
-	void __iomem *hermes_io;
-
-	err = pci_enable_device(pdev);
-	if (err) {
-		printk(KERN_ERR PFX "Cannot enable PCI device\n");
-		return err;
-	}
-
-	err = pci_request_regions(pdev, DRIVER_NAME);
-	if (err) {
-		printk(KERN_ERR PFX "Cannot obtain PCI resources\n");
-		goto fail_resources;
-	}
-
-	hermes_io = pci_iomap(pdev, 0, 0);
-	if (!hermes_io) {
-		printk(KERN_ERR PFX "Cannot remap chipset registers\n");
-		err = -EIO;
-		goto fail_map_hermes;
-	}
-
-	/* Allocate network device */
-	priv = alloc_orinocodev(sizeof(*card), &pdev->dev,
-				orinoco_pci_cor_reset, NULL);
-	if (!priv) {
-		printk(KERN_ERR PFX "Cannot allocate network device\n");
-		err = -ENOMEM;
-		goto fail_alloc;
-	}
-
-	card = priv->card;
-
-	hermes_struct_init(&priv->hw, hermes_io, HERMES_32BIT_REGSPACING);
-
-	err = request_irq(pdev->irq, orinoco_interrupt, IRQF_SHARED,
-			  DRIVER_NAME, priv);
-	if (err) {
-		printk(KERN_ERR PFX "Cannot allocate IRQ %d\n", pdev->irq);
-		err = -EBUSY;
-		goto fail_irq;
-	}
-
-	err = orinoco_pci_cor_reset(priv);
-	if (err) {
-		printk(KERN_ERR PFX "Initial reset failed\n");
-		goto fail;
-	}
-
-	err = orinoco_init(priv);
-	if (err) {
-		printk(KERN_ERR PFX "orinoco_init() failed\n");
-		goto fail;
-	}
-
-	err = orinoco_if_add(priv, 0, 0, NULL);
-	if (err) {
-		printk(KERN_ERR PFX "orinoco_if_add() failed\n");
-		goto fail_wiphy;
-	}
-
-	pci_set_drvdata(pdev, priv);
-
-	return 0;
-
- fail_wiphy:
-	wiphy_unregister(priv_to_wiphy(priv));
- fail:
-	free_irq(pdev->irq, priv);
-
- fail_irq:
-	free_orinocodev(priv);
-
- fail_alloc:
-	pci_iounmap(pdev, hermes_io);
-
- fail_map_hermes:
-	pci_release_regions(pdev);
-
- fail_resources:
-	pci_disable_device(pdev);
-
-	return err;
-}
-
-static void orinoco_pci_remove_one(struct pci_dev *pdev)
-{
-	struct orinoco_private *priv = pci_get_drvdata(pdev);
-
-	orinoco_if_del(priv);
-	wiphy_unregister(priv_to_wiphy(priv));
-	free_irq(pdev->irq, priv);
-	free_orinocodev(priv);
-	pci_iounmap(pdev, priv->hw.iobase);
-	pci_release_regions(pdev);
-	pci_disable_device(pdev);
-}
-
-static const struct pci_device_id orinoco_pci_id_table[] = {
-	/* Intersil Prism 3 */
-	{0x1260, 0x3872, PCI_ANY_ID, PCI_ANY_ID,},
-	/* Intersil Prism 2.5 */
-	{0x1260, 0x3873, PCI_ANY_ID, PCI_ANY_ID,},
-	/* Samsung MagicLAN SWL-2210P */
-	{0x167d, 0xa000, PCI_ANY_ID, PCI_ANY_ID,},
-	{0,},
-};
-
-MODULE_DEVICE_TABLE(pci, orinoco_pci_id_table);
-
-static struct pci_driver orinoco_pci_driver = {
-	.name		= DRIVER_NAME,
-	.id_table	= orinoco_pci_id_table,
-	.probe		= orinoco_pci_init_one,
-	.remove		= orinoco_pci_remove_one,
-	.driver.pm	= &orinoco_pci_pm_ops,
-};
-
-static char version[] __initdata = DRIVER_NAME " " DRIVER_VERSION
-	" (Pavel Roskin <proski@gnu.org>,"
-	" David Gibson <hermes@gibson.dropbear.id.au> &"
-	" Jean Tourrilhes <jt@hpl.hp.com>)";
-MODULE_AUTHOR("Pavel Roskin <proski@gnu.org> &"
-	      " David Gibson <hermes@gibson.dropbear.id.au>");
-MODULE_DESCRIPTION("Driver for wireless LAN cards using direct PCI interface");
-MODULE_LICENSE("Dual MPL/GPL");
-
-static int __init orinoco_pci_init(void)
-{
-	printk(KERN_DEBUG "%s\n", version);
-	return pci_register_driver(&orinoco_pci_driver);
-}
-
-static void __exit orinoco_pci_exit(void)
-{
-	pci_unregister_driver(&orinoco_pci_driver);
-}
-
-module_init(orinoco_pci_init);
-module_exit(orinoco_pci_exit);
diff --git a/drivers/net/wireless/intersil/orinoco/orinoco_pci.h b/drivers/net/wireless/intersil/orinoco/orinoco_pci.h
deleted file mode 100644
index d49d940864b4..000000000000
--- a/drivers/net/wireless/intersil/orinoco/orinoco_pci.h
+++ /dev/null
@@ -1,54 +0,0 @@
-/* orinoco_pci.h
- *
- * Common code for all Orinoco drivers for PCI devices, including
- * both native PCI and PCMCIA-to-PCI bridges.
- *
- * Copyright (C) 2005, Pavel Roskin.
- * See main.c for license.
- */
-
-#ifndef _ORINOCO_PCI_H
-#define _ORINOCO_PCI_H
-
-#include <linux/netdevice.h>
-
-/* Driver specific data */
-struct orinoco_pci_card {
-	void __iomem *bridge_io;
-	void __iomem *attr_io;
-};
-
-static int __maybe_unused orinoco_pci_suspend(struct device *dev_d)
-{
-	struct pci_dev *pdev = to_pci_dev(dev_d);
-	struct orinoco_private *priv = pci_get_drvdata(pdev);
-
-	orinoco_down(priv);
-	free_irq(pdev->irq, priv);
-
-	return 0;
-}
-
-static int __maybe_unused orinoco_pci_resume(struct device *dev_d)
-{
-	struct pci_dev *pdev = to_pci_dev(dev_d);
-	struct orinoco_private *priv = pci_get_drvdata(pdev);
-	struct net_device *dev = priv->ndev;
-	int err;
-
-	err = request_irq(pdev->irq, orinoco_interrupt, IRQF_SHARED,
-			  dev->name, priv);
-	if (err) {
-		printk(KERN_ERR "%s: cannot re-allocate IRQ on resume\n",
-		       dev->name);
-		return -EBUSY;
-	}
-
-	return orinoco_up(priv);
-}
-
-static SIMPLE_DEV_PM_OPS(orinoco_pci_pm_ops,
-			 orinoco_pci_suspend,
-			 orinoco_pci_resume);
-
-#endif /* _ORINOCO_PCI_H */
diff --git a/drivers/net/wireless/intersil/orinoco/orinoco_plx.c b/drivers/net/wireless/intersil/orinoco/orinoco_plx.c
deleted file mode 100644
index 73e6ae124013..000000000000
--- a/drivers/net/wireless/intersil/orinoco/orinoco_plx.c
+++ /dev/null
@@ -1,362 +0,0 @@
-/* orinoco_plx.c
- *
- * Driver for Prism II devices which would usually be driven by orinoco_cs,
- * but are connected to the PCI bus by a PLX9052.
- *
- * Current maintainers are:
- *	Pavel Roskin <proski AT gnu.org>
- * and	David Gibson <hermes AT gibson.dropbear.id.au>
- *
- * (C) Copyright David Gibson, IBM Corp. 2001-2003.
- * Copyright (C) 2001 Daniel Barlow
- *
- * The contents of this file are subject to the Mozilla Public License
- * Version 1.1 (the "License"); you may not use this file except in
- * compliance with the License. You may obtain a copy of the License
- * at http://www.mozilla.org/MPL/
- *
- * Software distributed under the License is distributed on an "AS IS"
- * basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See
- * the License for the specific language governing rights and
- * limitations under the License.
- *
- * Alternatively, the contents of this file may be used under the
- * terms of the GNU General Public License version 2 (the "GPL"), in
- * which case the provisions of the GPL are applicable instead of the
- * above.  If you wish to allow the use of your version of this file
- * only under the terms of the GPL and not to allow others to use your
- * version of this file under the MPL, indicate your decision by
- * deleting the provisions above and replace them with the notice and
- * other provisions required by the GPL.  If you do not delete the
- * provisions above, a recipient may use your version of this file
- * under either the MPL or the GPL.
- *
- * Here's the general details on how the PLX9052 adapter works:
- *
- * - Two PCI I/O address spaces, one 0x80 long which contains the
- * PLX9052 registers, and one that's 0x40 long mapped to the PCMCIA
- * slot I/O address space.
- *
- * - One PCI memory address space, mapped to the PCMCIA attribute space
- * (containing the CIS).
- *
- * Using the later, you can read through the CIS data to make sure the
- * card is compatible with the driver. Keep in mind that the PCMCIA
- * spec specifies the CIS as the lower 8 bits of each word read from
- * the CIS, so to read the bytes of the CIS, read every other byte
- * (0,2,4,...). Passing that test, you need to enable the I/O address
- * space on the PCMCIA card via the PCMCIA COR register. This is the
- * first byte following the CIS. In my case (which may not have any
- * relation to what's on the PRISM2 cards), COR was at offset 0x800
- * within the PCI memory space. Write 0x41 to the COR register to
- * enable I/O mode and to select level triggered interrupts. To
- * confirm you actually succeeded, read the COR register back and make
- * sure it actually got set to 0x41, in case you have an unexpected
- * card inserted.
- *
- * Following that, you can treat the second PCI I/O address space (the
- * one that's not 0x80 in length) as the PCMCIA I/O space.
- *
- * Note that in the Eumitcom's source for their drivers, they register
- * the interrupt as edge triggered when registering it with the
- * Windows kernel. I don't recall how to register edge triggered on
- * Linux (if it can be done at all). But in some experimentation, I
- * don't see much operational difference between using either
- * interrupt mode. Don't mess with the interrupt mode in the COR
- * register though, as the PLX9052 wants level triggers with the way
- * the serial EEPROM configures it on the WL11000.
- *
- * There's some other little quirks related to timing that I bumped
- * into, but I don't recall right now. Also, there's two variants of
- * the WL11000 I've seen, revision A1 and T2. These seem to differ
- * slightly in the timings configured in the wait-state generator in
- * the PLX9052. There have also been some comments from Eumitcom that
- * cards shouldn't be hot swapped, apparently due to risk of cooking
- * the PLX9052. I'm unsure why they believe this, as I can't see
- * anything in the design that would really cause a problem, except
- * for crashing drivers not written to expect it. And having developed
- * drivers for the WL11000, I'd say it's quite tricky to write code
- * that will successfully deal with a hot unplug. Very odd things
- * happen on the I/O side of things. But anyway, be warned. Despite
- * that, I've hot-swapped a number of times during debugging and
- * driver development for various reasons (stuck WAIT# line after the
- * radio card's firmware locks up).
- */
-
-#define DRIVER_NAME "orinoco_plx"
-#define PFX DRIVER_NAME ": "
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/pci.h>
-#include <pcmcia/cisreg.h>
-
-#include "orinoco.h"
-#include "orinoco_pci.h"
-
-#define COR_OFFSET	(0x3e0)	/* COR attribute offset of Prism2 PC card */
-#define COR_VALUE	(COR_LEVEL_REQ | COR_FUNC_ENA) /* Enable PC card with interrupt in level trigger */
-#define COR_RESET     (0x80)	/* reset bit in the COR register */
-#define PLX_RESET_TIME	(500)	/* milliseconds */
-
-#define PLX_INTCSR		0x4c /* Interrupt Control & Status Register */
-#define PLX_INTCSR_INTEN	(1 << 6) /* Interrupt Enable bit */
-
-/*
- * Do a soft reset of the card using the Configuration Option Register
- */
-static int orinoco_plx_cor_reset(struct orinoco_private *priv)
-{
-	struct hermes *hw = &priv->hw;
-	struct orinoco_pci_card *card = priv->card;
-	unsigned long timeout;
-	u16 reg;
-
-	iowrite8(COR_VALUE | COR_RESET, card->attr_io + COR_OFFSET);
-	mdelay(1);
-
-	iowrite8(COR_VALUE, card->attr_io + COR_OFFSET);
-	mdelay(1);
-
-	/* Just in case, wait more until the card is no longer busy */
-	timeout = jiffies + msecs_to_jiffies(PLX_RESET_TIME);
-	reg = hermes_read_regn(hw, CMD);
-	while (time_before(jiffies, timeout) && (reg & HERMES_CMD_BUSY)) {
-		mdelay(1);
-		reg = hermes_read_regn(hw, CMD);
-	}
-
-	/* Still busy? */
-	if (reg & HERMES_CMD_BUSY) {
-		printk(KERN_ERR PFX "Busy timeout\n");
-		return -ETIMEDOUT;
-	}
-
-	return 0;
-}
-
-static int orinoco_plx_hw_init(struct orinoco_pci_card *card)
-{
-	int i;
-	u32 csr_reg;
-	static const u8 cis_magic[] = {
-		0x01, 0x03, 0x00, 0x00, 0xff, 0x17, 0x04, 0x67
-	};
-
-	printk(KERN_DEBUG PFX "CIS: ");
-	for (i = 0; i < 16; i++)
-		printk("%02X:", ioread8(card->attr_io + (i << 1)));
-	printk("\n");
-
-	/* Verify whether a supported PC card is present */
-	/* FIXME: we probably need to be smarted about this */
-	for (i = 0; i < sizeof(cis_magic); i++) {
-		if (cis_magic[i] != ioread8(card->attr_io + (i << 1))) {
-			printk(KERN_ERR PFX "The CIS value of Prism2 PC "
-			       "card is unexpected\n");
-			return -ENODEV;
-		}
-	}
-
-	/* bjoern: We need to tell the card to enable interrupts, in
-	   case the serial eprom didn't do this already.  See the
-	   PLX9052 data book, p8-1 and 8-24 for reference. */
-	csr_reg = ioread32(card->bridge_io + PLX_INTCSR);
-	if (!(csr_reg & PLX_INTCSR_INTEN)) {
-		csr_reg |= PLX_INTCSR_INTEN;
-		iowrite32(csr_reg, card->bridge_io + PLX_INTCSR);
-		csr_reg = ioread32(card->bridge_io + PLX_INTCSR);
-		if (!(csr_reg & PLX_INTCSR_INTEN)) {
-			printk(KERN_ERR PFX "Cannot enable interrupts\n");
-			return -EIO;
-		}
-	}
-
-	return 0;
-}
-
-static int orinoco_plx_init_one(struct pci_dev *pdev,
-				const struct pci_device_id *ent)
-{
-	int err;
-	struct orinoco_private *priv;
-	struct orinoco_pci_card *card;
-	void __iomem *hermes_io, *attr_io, *bridge_io;
-
-	err = pci_enable_device(pdev);
-	if (err) {
-		printk(KERN_ERR PFX "Cannot enable PCI device\n");
-		return err;
-	}
-
-	err = pci_request_regions(pdev, DRIVER_NAME);
-	if (err) {
-		printk(KERN_ERR PFX "Cannot obtain PCI resources\n");
-		goto fail_resources;
-	}
-
-	bridge_io = pci_iomap(pdev, 1, 0);
-	if (!bridge_io) {
-		printk(KERN_ERR PFX "Cannot map bridge registers\n");
-		err = -EIO;
-		goto fail_map_bridge;
-	}
-
-	attr_io = pci_iomap(pdev, 2, 0);
-	if (!attr_io) {
-		printk(KERN_ERR PFX "Cannot map PCMCIA attributes\n");
-		err = -EIO;
-		goto fail_map_attr;
-	}
-
-	hermes_io = pci_iomap(pdev, 3, 0);
-	if (!hermes_io) {
-		printk(KERN_ERR PFX "Cannot map chipset registers\n");
-		err = -EIO;
-		goto fail_map_hermes;
-	}
-
-	/* Allocate network device */
-	priv = alloc_orinocodev(sizeof(*card), &pdev->dev,
-				orinoco_plx_cor_reset, NULL);
-	if (!priv) {
-		printk(KERN_ERR PFX "Cannot allocate network device\n");
-		err = -ENOMEM;
-		goto fail_alloc;
-	}
-
-	card = priv->card;
-	card->bridge_io = bridge_io;
-	card->attr_io = attr_io;
-
-	hermes_struct_init(&priv->hw, hermes_io, HERMES_16BIT_REGSPACING);
-
-	err = request_irq(pdev->irq, orinoco_interrupt, IRQF_SHARED,
-			  DRIVER_NAME, priv);
-	if (err) {
-		printk(KERN_ERR PFX "Cannot allocate IRQ %d\n", pdev->irq);
-		err = -EBUSY;
-		goto fail_irq;
-	}
-
-	err = orinoco_plx_hw_init(card);
-	if (err) {
-		printk(KERN_ERR PFX "Hardware initialization failed\n");
-		goto fail;
-	}
-
-	err = orinoco_plx_cor_reset(priv);
-	if (err) {
-		printk(KERN_ERR PFX "Initial reset failed\n");
-		goto fail;
-	}
-
-	err = orinoco_init(priv);
-	if (err) {
-		printk(KERN_ERR PFX "orinoco_init() failed\n");
-		goto fail;
-	}
-
-	err = orinoco_if_add(priv, 0, 0, NULL);
-	if (err) {
-		printk(KERN_ERR PFX "orinoco_if_add() failed\n");
-		goto fail_wiphy;
-	}
-
-	pci_set_drvdata(pdev, priv);
-
-	return 0;
-
- fail_wiphy:
-	wiphy_unregister(priv_to_wiphy(priv));
- fail:
-	free_irq(pdev->irq, priv);
-
- fail_irq:
-	free_orinocodev(priv);
-
- fail_alloc:
-	pci_iounmap(pdev, hermes_io);
-
- fail_map_hermes:
-	pci_iounmap(pdev, attr_io);
-
- fail_map_attr:
-	pci_iounmap(pdev, bridge_io);
-
- fail_map_bridge:
-	pci_release_regions(pdev);
-
- fail_resources:
-	pci_disable_device(pdev);
-
-	return err;
-}
-
-static void orinoco_plx_remove_one(struct pci_dev *pdev)
-{
-	struct orinoco_private *priv = pci_get_drvdata(pdev);
-	struct orinoco_pci_card *card = priv->card;
-
-	orinoco_if_del(priv);
-	wiphy_unregister(priv_to_wiphy(priv));
-	free_irq(pdev->irq, priv);
-	free_orinocodev(priv);
-	pci_iounmap(pdev, priv->hw.iobase);
-	pci_iounmap(pdev, card->attr_io);
-	pci_iounmap(pdev, card->bridge_io);
-	pci_release_regions(pdev);
-	pci_disable_device(pdev);
-}
-
-static const struct pci_device_id orinoco_plx_id_table[] = {
-	{0x111a, 0x1023, PCI_ANY_ID, PCI_ANY_ID,},	/* Siemens SpeedStream SS1023 */
-	{0x1385, 0x4100, PCI_ANY_ID, PCI_ANY_ID,},	/* Netgear MA301 */
-	{0x15e8, 0x0130, PCI_ANY_ID, PCI_ANY_ID,},	/* Correga  - does this work? */
-	{0x1638, 0x1100, PCI_ANY_ID, PCI_ANY_ID,},	/* SMC EZConnect SMC2602W,
-							   Eumitcom PCI WL11000,
-							   Addtron AWA-100 */
-	{0x16ab, 0x1100, PCI_ANY_ID, PCI_ANY_ID,},	/* Global Sun Tech GL24110P */
-	{0x16ab, 0x1101, PCI_ANY_ID, PCI_ANY_ID,},	/* Reported working, but unknown */
-	{0x16ab, 0x1102, PCI_ANY_ID, PCI_ANY_ID,},	/* Linksys WDT11 */
-	{0x16ec, 0x3685, PCI_ANY_ID, PCI_ANY_ID,},	/* USR 2415 */
-	{0xec80, 0xec00, PCI_ANY_ID, PCI_ANY_ID,},	/* Belkin F5D6000 tested by
-							   Brendan W. McAdams <rit AT jacked-in.org> */
-	{0x10b7, 0x7770, PCI_ANY_ID, PCI_ANY_ID,},	/* 3Com AirConnect PCI tested by
-							   Damien Persohn <damien AT persohn.net> */
-	{0,},
-};
-
-MODULE_DEVICE_TABLE(pci, orinoco_plx_id_table);
-
-static struct pci_driver orinoco_plx_driver = {
-	.name		= DRIVER_NAME,
-	.id_table	= orinoco_plx_id_table,
-	.probe		= orinoco_plx_init_one,
-	.remove		= orinoco_plx_remove_one,
-	.driver.pm	= &orinoco_pci_pm_ops,
-};
-
-static char version[] __initdata = DRIVER_NAME " " DRIVER_VERSION
-	" (Pavel Roskin <proski@gnu.org>,"
-	" David Gibson <hermes@gibson.dropbear.id.au>,"
-	" Daniel Barlow <dan@telent.net>)";
-MODULE_AUTHOR("Daniel Barlow <dan@telent.net>");
-MODULE_DESCRIPTION("Driver for wireless LAN cards using the PLX9052 PCI bridge");
-MODULE_LICENSE("Dual MPL/GPL");
-
-static int __init orinoco_plx_init(void)
-{
-	printk(KERN_DEBUG "%s\n", version);
-	return pci_register_driver(&orinoco_plx_driver);
-}
-
-static void __exit orinoco_plx_exit(void)
-{
-	pci_unregister_driver(&orinoco_plx_driver);
-}
-
-module_init(orinoco_plx_init);
-module_exit(orinoco_plx_exit);
diff --git a/drivers/net/wireless/intersil/orinoco/orinoco_tmd.c b/drivers/net/wireless/intersil/orinoco/orinoco_tmd.c
deleted file mode 100644
index 939d5a1dce97..000000000000
--- a/drivers/net/wireless/intersil/orinoco/orinoco_tmd.c
+++ /dev/null
@@ -1,237 +0,0 @@
-/* orinoco_tmd.c
- *
- * Driver for Prism II devices which would usually be driven by orinoco_cs,
- * but are connected to the PCI bus by a TMD7160.
- *
- * Copyright (C) 2003 Joerg Dorchain <joerg AT dorchain.net>
- * based heavily upon orinoco_plx.c Copyright (C) 2001 Daniel Barlow
- *
- * The contents of this file are subject to the Mozilla Public License
- * Version 1.1 (the "License"); you may not use this file except in
- * compliance with the License. You may obtain a copy of the License
- * at http://www.mozilla.org/MPL/
- *
- * Software distributed under the License is distributed on an "AS IS"
- * basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See
- * the License for the specific language governing rights and
- * limitations under the License.
- *
- * Alternatively, the contents of this file may be used under the
- * terms of the GNU General Public License version 2 (the "GPL"), in
- * which case the provisions of the GPL are applicable instead of the
- * above.  If you wish to allow the use of your version of this file
- * only under the terms of the GPL and not to allow others to use your
- * version of this file under the MPL, indicate your decision by
- * deleting the provisions above and replace them with the notice and
- * other provisions required by the GPL.  If you do not delete the
- * provisions above, a recipient may use your version of this file
- * under either the MPL or the GPL.
- *
- * The actual driving is done by main.c, this is just resource
- * allocation stuff.
- *
- * This driver is modeled after the orinoco_plx driver. The main
- * difference is that the TMD chip has only IO port ranges and doesn't
- * provide access to the PCMCIA attribute space.
- *
- * Pheecom sells cards with the TMD chip as "ASIC version"
- */
-
-#define DRIVER_NAME "orinoco_tmd"
-#define PFX DRIVER_NAME ": "
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/pci.h>
-#include <pcmcia/cisreg.h>
-
-#include "orinoco.h"
-#include "orinoco_pci.h"
-
-#define COR_VALUE	(COR_LEVEL_REQ | COR_FUNC_ENA) /* Enable PC card with interrupt in level trigger */
-#define COR_RESET     (0x80)	/* reset bit in the COR register */
-#define TMD_RESET_TIME	(500)	/* milliseconds */
-
-/*
- * Do a soft reset of the card using the Configuration Option Register
- */
-static int orinoco_tmd_cor_reset(struct orinoco_private *priv)
-{
-	struct hermes *hw = &priv->hw;
-	struct orinoco_pci_card *card = priv->card;
-	unsigned long timeout;
-	u16 reg;
-
-	iowrite8(COR_VALUE | COR_RESET, card->bridge_io);
-	mdelay(1);
-
-	iowrite8(COR_VALUE, card->bridge_io);
-	mdelay(1);
-
-	/* Just in case, wait more until the card is no longer busy */
-	timeout = jiffies + msecs_to_jiffies(TMD_RESET_TIME);
-	reg = hermes_read_regn(hw, CMD);
-	while (time_before(jiffies, timeout) && (reg & HERMES_CMD_BUSY)) {
-		mdelay(1);
-		reg = hermes_read_regn(hw, CMD);
-	}
-
-	/* Still busy? */
-	if (reg & HERMES_CMD_BUSY) {
-		printk(KERN_ERR PFX "Busy timeout\n");
-		return -ETIMEDOUT;
-	}
-
-	return 0;
-}
-
-
-static int orinoco_tmd_init_one(struct pci_dev *pdev,
-				const struct pci_device_id *ent)
-{
-	int err;
-	struct orinoco_private *priv;
-	struct orinoco_pci_card *card;
-	void __iomem *hermes_io, *bridge_io;
-
-	err = pci_enable_device(pdev);
-	if (err) {
-		printk(KERN_ERR PFX "Cannot enable PCI device\n");
-		return err;
-	}
-
-	err = pci_request_regions(pdev, DRIVER_NAME);
-	if (err) {
-		printk(KERN_ERR PFX "Cannot obtain PCI resources\n");
-		goto fail_resources;
-	}
-
-	bridge_io = pci_iomap(pdev, 1, 0);
-	if (!bridge_io) {
-		printk(KERN_ERR PFX "Cannot map bridge registers\n");
-		err = -EIO;
-		goto fail_map_bridge;
-	}
-
-	hermes_io = pci_iomap(pdev, 2, 0);
-	if (!hermes_io) {
-		printk(KERN_ERR PFX "Cannot map chipset registers\n");
-		err = -EIO;
-		goto fail_map_hermes;
-	}
-
-	/* Allocate network device */
-	priv = alloc_orinocodev(sizeof(*card), &pdev->dev,
-				orinoco_tmd_cor_reset, NULL);
-	if (!priv) {
-		printk(KERN_ERR PFX "Cannot allocate network device\n");
-		err = -ENOMEM;
-		goto fail_alloc;
-	}
-
-	card = priv->card;
-	card->bridge_io = bridge_io;
-
-	hermes_struct_init(&priv->hw, hermes_io, HERMES_16BIT_REGSPACING);
-
-	err = request_irq(pdev->irq, orinoco_interrupt, IRQF_SHARED,
-			  DRIVER_NAME, priv);
-	if (err) {
-		printk(KERN_ERR PFX "Cannot allocate IRQ %d\n", pdev->irq);
-		err = -EBUSY;
-		goto fail_irq;
-	}
-
-	err = orinoco_tmd_cor_reset(priv);
-	if (err) {
-		printk(KERN_ERR PFX "Initial reset failed\n");
-		goto fail;
-	}
-
-	err = orinoco_init(priv);
-	if (err) {
-		printk(KERN_ERR PFX "orinoco_init() failed\n");
-		goto fail;
-	}
-
-	err = orinoco_if_add(priv, 0, 0, NULL);
-	if (err) {
-		printk(KERN_ERR PFX "orinoco_if_add() failed\n");
-		goto fail;
-	}
-
-	pci_set_drvdata(pdev, priv);
-
-	return 0;
-
- fail:
-	free_irq(pdev->irq, priv);
-
- fail_irq:
-	free_orinocodev(priv);
-
- fail_alloc:
-	pci_iounmap(pdev, hermes_io);
-
- fail_map_hermes:
-	pci_iounmap(pdev, bridge_io);
-
- fail_map_bridge:
-	pci_release_regions(pdev);
-
- fail_resources:
-	pci_disable_device(pdev);
-
-	return err;
-}
-
-static void orinoco_tmd_remove_one(struct pci_dev *pdev)
-{
-	struct orinoco_private *priv = pci_get_drvdata(pdev);
-	struct orinoco_pci_card *card = priv->card;
-
-	orinoco_if_del(priv);
-	free_irq(pdev->irq, priv);
-	free_orinocodev(priv);
-	pci_iounmap(pdev, priv->hw.iobase);
-	pci_iounmap(pdev, card->bridge_io);
-	pci_release_regions(pdev);
-	pci_disable_device(pdev);
-}
-
-static const struct pci_device_id orinoco_tmd_id_table[] = {
-	{0x15e8, 0x0131, PCI_ANY_ID, PCI_ANY_ID,},      /* NDC and OEMs, e.g. pheecom */
-	{0,},
-};
-
-MODULE_DEVICE_TABLE(pci, orinoco_tmd_id_table);
-
-static struct pci_driver orinoco_tmd_driver = {
-	.name		= DRIVER_NAME,
-	.id_table	= orinoco_tmd_id_table,
-	.probe		= orinoco_tmd_init_one,
-	.remove		= orinoco_tmd_remove_one,
-	.driver.pm	= &orinoco_pci_pm_ops,
-};
-
-static char version[] __initdata = DRIVER_NAME " " DRIVER_VERSION
-	" (Joerg Dorchain <joerg@dorchain.net>)";
-MODULE_AUTHOR("Joerg Dorchain <joerg@dorchain.net>");
-MODULE_DESCRIPTION("Driver for wireless LAN cards using the TMD7160 PCI bridge");
-MODULE_LICENSE("Dual MPL/GPL");
-
-static int __init orinoco_tmd_init(void)
-{
-	printk(KERN_DEBUG "%s\n", version);
-	return pci_register_driver(&orinoco_tmd_driver);
-}
-
-static void __exit orinoco_tmd_exit(void)
-{
-	pci_unregister_driver(&orinoco_tmd_driver);
-}
-
-module_init(orinoco_tmd_init);
-module_exit(orinoco_tmd_exit);
diff --git a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
deleted file mode 100644
index 866e0230df25..000000000000
--- a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
+++ /dev/null
@@ -1,1787 +0,0 @@
-/*
- * USB Orinoco driver
- *
- * Copyright (c) 2003 Manuel Estrada Sainz
- *
- * The contents of this file are subject to the Mozilla Public License
- * Version 1.1 (the "License"); you may not use this file except in
- * compliance with the License. You may obtain a copy of the License
- * at http://www.mozilla.org/MPL/
- *
- * Software distributed under the License is distributed on an "AS IS"
- * basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See
- * the License for the specific language governing rights and
- * limitations under the License.
- *
- * Alternatively, the contents of this file may be used under the
- * terms of the GNU General Public License version 2 (the "GPL"), in
- * which case the provisions of the GPL are applicable instead of the
- * above.  If you wish to allow the use of your version of this file
- * only under the terms of the GPL and not to allow others to use your
- * version of this file under the MPL, indicate your decision by
- * deleting the provisions above and replace them with the notice and
- * other provisions required by the GPL.  If you do not delete the
- * provisions above, a recipient may use your version of this file
- * under either the MPL or the GPL.
- *
- * Queueing code based on linux-wlan-ng 0.2.1-pre5
- *
- * Copyright (C) 1999 AbsoluteValue Systems, Inc.  All Rights Reserved.
- *
- *	The license is the same as above.
- *
- * Initialy based on USB Skeleton driver - 0.7
- *
- * Copyright (c) 2001 Greg Kroah-Hartman (greg@kroah.com)
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License as
- *	published by the Free Software Foundation; either version 2 of
- *	the License, or (at your option) any later version.
- *
- * NOTE: The original USB Skeleton driver is GPL, but all that code is
- * gone so MPL/GPL applies.
- */
-
-#define DRIVER_NAME "orinoco_usb"
-#define PFX DRIVER_NAME ": "
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/signal.h>
-#include <linux/errno.h>
-#include <linux/poll.h>
-#include <linux/slab.h>
-#include <linux/fcntl.h>
-#include <linux/spinlock.h>
-#include <linux/list.h>
-#include <linux/usb.h>
-#include <linux/timer.h>
-
-#include <linux/netdevice.h>
-#include <linux/if_arp.h>
-#include <linux/etherdevice.h>
-#include <linux/wireless.h>
-#include <linux/firmware.h>
-#include <linux/refcount.h>
-
-#include "mic.h"
-#include "orinoco.h"
-
-#ifndef URB_ASYNC_UNLINK
-#define URB_ASYNC_UNLINK 0
-#endif
-
-struct header_struct {
-	/* 802.3 */
-	u8 dest[ETH_ALEN];
-	u8 src[ETH_ALEN];
-	__be16 len;
-	/* 802.2 */
-	u8 dsap;
-	u8 ssap;
-	u8 ctrl;
-	/* SNAP */
-	u8 oui[3];
-	__be16 ethertype;
-} __packed;
-
-struct ez_usb_fw {
-	u16 size;
-	const u8 *code;
-};
-
-static struct ez_usb_fw firmware = {
-	.size = 0,
-	.code = NULL,
-};
-
-/* Debugging macros */
-#undef err
-#define err(format, arg...) \
-	do { printk(KERN_ERR PFX format "\n", ## arg); } while (0)
-
-MODULE_FIRMWARE("orinoco_ezusb_fw");
-
-/*
- * Under some conditions, the card gets stuck and stops paying attention
- * to the world (i.e. data communication stalls) until we do something to
- * it.  Sending an INQ_TALLIES command seems to be enough and should be
- * harmless otherwise.  This behaviour has been observed when using the
- * driver on a systemimager client during installation.  In the past a
- * timer was used to send INQ_TALLIES commands when there was no other
- * activity, but it was troublesome and was removed.
- */
-
-#define USB_COMPAQ_VENDOR_ID     0x049f /* Compaq Computer Corp. */
-#define USB_COMPAQ_WL215_ID      0x001f /* Compaq WL215 USB Adapter */
-#define USB_COMPAQ_W200_ID       0x0076 /* Compaq W200 USB Adapter */
-#define USB_HP_WL215_ID          0x0082 /* Compaq WL215 USB Adapter */
-
-#define USB_MELCO_VENDOR_ID      0x0411
-#define USB_BUFFALO_L11_ID       0x0006 /* BUFFALO WLI-USB-L11 */
-#define USB_BUFFALO_L11G_WR_ID   0x000B /* BUFFALO WLI-USB-L11G-WR */
-#define USB_BUFFALO_L11G_ID      0x000D /* BUFFALO WLI-USB-L11G */
-
-#define USB_LUCENT_VENDOR_ID     0x047E /* Lucent Technologies */
-#define USB_LUCENT_ORINOCO_ID    0x0300 /* Lucent/Agere Orinoco USB Client */
-
-#define USB_AVAYA8_VENDOR_ID     0x0D98
-#define USB_AVAYAE_VENDOR_ID     0x0D9E
-#define USB_AVAYA_WIRELESS_ID    0x0300 /* Avaya USB Wireless Card */
-
-#define USB_AGERE_VENDOR_ID      0x0D4E /* Agere Systems */
-#define USB_AGERE_MODEL0801_ID   0x1000 /* USB Wireless Card Model 0801 */
-#define USB_AGERE_MODEL0802_ID   0x1001 /* USB Wireless Card Model 0802 */
-#define USB_AGERE_REBRANDED_ID   0x047A /* USB WLAN Card */
-
-#define USB_ELSA_VENDOR_ID       0x05CC
-#define USB_ELSA_AIRLANCER_ID    0x3100 /* ELSA AirLancer USB-11 */
-
-#define USB_LEGEND_VENDOR_ID     0x0E7C
-#define USB_LEGEND_JOYNET_ID     0x0300 /* Joynet USB WLAN Card */
-
-#define USB_SAMSUNG_VENDOR_ID    0x04E8
-#define USB_SAMSUNG_SEW2001U1_ID 0x5002 /* Samsung SEW-2001u Card */
-#define USB_SAMSUNG_SEW2001U2_ID 0x5B11 /* Samsung SEW-2001u Card */
-#define USB_SAMSUNG_SEW2003U_ID  0x7011 /* Samsung SEW-2003U Card */
-
-#define USB_IGATE_VENDOR_ID      0x0681
-#define USB_IGATE_IGATE_11M_ID   0x0012 /* I-GATE 11M USB Card */
-
-#define USB_FUJITSU_VENDOR_ID    0x0BF8
-#define USB_FUJITSU_E1100_ID     0x1002 /* connect2AIR WLAN E-1100 USB */
-
-#define USB_2WIRE_VENDOR_ID      0x1630
-#define USB_2WIRE_WIRELESS_ID    0xff81 /* 2Wire USB Wireless adapter */
-
-
-#define EZUSB_REQUEST_FW_TRANS		0xA0
-#define EZUSB_REQUEST_TRIGGER		0xAA
-#define EZUSB_REQUEST_TRIG_AC		0xAC
-#define EZUSB_CPUCS_REG			0x7F92
-
-#define EZUSB_RID_TX			0x0700
-#define EZUSB_RID_RX			0x0701
-#define EZUSB_RID_INIT1			0x0702
-#define EZUSB_RID_ACK			0x0710
-#define EZUSB_RID_READ_PDA		0x0800
-#define EZUSB_RID_PROG_INIT		0x0852
-#define EZUSB_RID_PROG_SET_ADDR		0x0853
-#define EZUSB_RID_PROG_BYTES		0x0854
-#define EZUSB_RID_PROG_END		0x0855
-#define EZUSB_RID_DOCMD			0x0860
-
-/* Recognize info frames */
-#define EZUSB_IS_INFO(id)		((id >= 0xF000) && (id <= 0xF2FF))
-
-#define EZUSB_MAGIC			0x0210
-
-#define EZUSB_FRAME_DATA		1
-#define EZUSB_FRAME_CONTROL		2
-
-#define DEF_TIMEOUT			(3 * HZ)
-
-#define BULK_BUF_SIZE			2048
-
-#define MAX_DL_SIZE (BULK_BUF_SIZE - sizeof(struct ezusb_packet))
-
-#define FW_BUF_SIZE			64
-#define FW_VAR_OFFSET_PTR		0x359
-#define FW_VAR_VALUE			0
-#define FW_HOLE_START			0x100
-#define FW_HOLE_END			0x300
-
-struct ezusb_packet {
-	__le16 magic;		/* 0x0210 */
-	u8 req_reply_count;
-	u8 ans_reply_count;
-	__le16 frame_type;	/* 0x01 for data frames, 0x02 otherwise */
-	__le16 size;		/* transport size */
-	__le16 crc;		/* CRC up to here */
-	__le16 hermes_len;
-	__le16 hermes_rid;
-	u8 data[];
-} __packed;
-
-/* Table of devices that work or may work with this driver */
-static const struct usb_device_id ezusb_table[] = {
-	{USB_DEVICE(USB_COMPAQ_VENDOR_ID, USB_COMPAQ_WL215_ID)},
-	{USB_DEVICE(USB_COMPAQ_VENDOR_ID, USB_HP_WL215_ID)},
-	{USB_DEVICE(USB_COMPAQ_VENDOR_ID, USB_COMPAQ_W200_ID)},
-	{USB_DEVICE(USB_MELCO_VENDOR_ID, USB_BUFFALO_L11_ID)},
-	{USB_DEVICE(USB_MELCO_VENDOR_ID, USB_BUFFALO_L11G_WR_ID)},
-	{USB_DEVICE(USB_MELCO_VENDOR_ID, USB_BUFFALO_L11G_ID)},
-	{USB_DEVICE(USB_LUCENT_VENDOR_ID, USB_LUCENT_ORINOCO_ID)},
-	{USB_DEVICE(USB_AVAYA8_VENDOR_ID, USB_AVAYA_WIRELESS_ID)},
-	{USB_DEVICE(USB_AVAYAE_VENDOR_ID, USB_AVAYA_WIRELESS_ID)},
-	{USB_DEVICE(USB_AGERE_VENDOR_ID, USB_AGERE_MODEL0801_ID)},
-	{USB_DEVICE(USB_AGERE_VENDOR_ID, USB_AGERE_MODEL0802_ID)},
-	{USB_DEVICE(USB_ELSA_VENDOR_ID, USB_ELSA_AIRLANCER_ID)},
-	{USB_DEVICE(USB_LEGEND_VENDOR_ID, USB_LEGEND_JOYNET_ID)},
-	{USB_DEVICE_VER(USB_SAMSUNG_VENDOR_ID, USB_SAMSUNG_SEW2001U1_ID,
-			0, 0)},
-	{USB_DEVICE(USB_SAMSUNG_VENDOR_ID, USB_SAMSUNG_SEW2001U2_ID)},
-	{USB_DEVICE(USB_SAMSUNG_VENDOR_ID, USB_SAMSUNG_SEW2003U_ID)},
-	{USB_DEVICE(USB_IGATE_VENDOR_ID, USB_IGATE_IGATE_11M_ID)},
-	{USB_DEVICE(USB_FUJITSU_VENDOR_ID, USB_FUJITSU_E1100_ID)},
-	{USB_DEVICE(USB_2WIRE_VENDOR_ID, USB_2WIRE_WIRELESS_ID)},
-	{USB_DEVICE(USB_AGERE_VENDOR_ID, USB_AGERE_REBRANDED_ID)},
-	{}			/* Terminating entry */
-};
-
-MODULE_DEVICE_TABLE(usb, ezusb_table);
-
-/* Structure to hold all of our device specific stuff */
-struct ezusb_priv {
-	struct usb_device *udev;
-	struct net_device *dev;
-	struct mutex mtx;
-	spinlock_t req_lock;
-	struct list_head req_pending;
-	struct list_head req_active;
-	spinlock_t reply_count_lock;
-	u16 hermes_reg_fake[0x40];
-	u8 *bap_buf;
-	struct urb *read_urb;
-	int read_pipe;
-	int write_pipe;
-	u8 reply_count;
-};
-
-enum ezusb_state {
-	EZUSB_CTX_START,
-	EZUSB_CTX_QUEUED,
-	EZUSB_CTX_REQ_SUBMITTED,
-	EZUSB_CTX_REQ_COMPLETE,
-	EZUSB_CTX_RESP_RECEIVED,
-	EZUSB_CTX_REQ_TIMEOUT,
-	EZUSB_CTX_REQ_FAILED,
-	EZUSB_CTX_RESP_TIMEOUT,
-	EZUSB_CTX_REQSUBMIT_FAIL,
-	EZUSB_CTX_COMPLETE,
-};
-
-struct request_context {
-	struct list_head list;
-	refcount_t refcount;
-	struct completion done;	/* Signals that CTX is dead */
-	int killed;
-	struct urb *outurb;	/* OUT for req pkt */
-	struct ezusb_priv *upriv;
-	struct ezusb_packet *buf;
-	int buf_length;
-	struct timer_list timer;	/* Timeout handling */
-	enum ezusb_state state;	/* Current state */
-	/* the RID that we will wait for */
-	u16 out_rid;
-	u16 in_rid;
-};
-
-
-/* Forward declarations */
-static void ezusb_ctx_complete(struct request_context *ctx);
-static void ezusb_req_queue_run(struct ezusb_priv *upriv);
-static void ezusb_bulk_in_callback(struct urb *urb);
-
-static inline u8 ezusb_reply_inc(u8 count)
-{
-	if (count < 0x7F)
-		return count + 1;
-	else
-		return 1;
-}
-
-static void ezusb_request_context_put(struct request_context *ctx)
-{
-	if (!refcount_dec_and_test(&ctx->refcount))
-		return;
-
-	WARN_ON(!ctx->done.done);
-	BUG_ON(ctx->outurb->status == -EINPROGRESS);
-	BUG_ON(timer_pending(&ctx->timer));
-	usb_free_urb(ctx->outurb);
-	kfree(ctx->buf);
-	kfree(ctx);
-}
-
-static inline void ezusb_mod_timer(struct ezusb_priv *upriv,
-				   struct timer_list *timer,
-				   unsigned long expire)
-{
-	if (!upriv->udev)
-		return;
-	mod_timer(timer, expire);
-}
-
-static void ezusb_request_timerfn(struct timer_list *t)
-{
-	struct request_context *ctx = from_timer(ctx, t, timer);
-
-	ctx->outurb->transfer_flags |= URB_ASYNC_UNLINK;
-	if (usb_unlink_urb(ctx->outurb) == -EINPROGRESS) {
-		ctx->state = EZUSB_CTX_REQ_TIMEOUT;
-	} else {
-		ctx->state = EZUSB_CTX_RESP_TIMEOUT;
-		dev_dbg(&ctx->outurb->dev->dev, "couldn't unlink\n");
-		refcount_inc(&ctx->refcount);
-		ctx->killed = 1;
-		ezusb_ctx_complete(ctx);
-		ezusb_request_context_put(ctx);
-	}
-};
-
-static struct request_context *ezusb_alloc_ctx(struct ezusb_priv *upriv,
-					       u16 out_rid, u16 in_rid)
-{
-	struct request_context *ctx;
-
-	ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC);
-	if (!ctx)
-		return NULL;
-
-	ctx->buf = kmalloc(BULK_BUF_SIZE, GFP_ATOMIC);
-	if (!ctx->buf) {
-		kfree(ctx);
-		return NULL;
-	}
-	ctx->outurb = usb_alloc_urb(0, GFP_ATOMIC);
-	if (!ctx->outurb) {
-		kfree(ctx->buf);
-		kfree(ctx);
-		return NULL;
-	}
-
-	ctx->upriv = upriv;
-	ctx->state = EZUSB_CTX_START;
-	ctx->out_rid = out_rid;
-	ctx->in_rid = in_rid;
-
-	refcount_set(&ctx->refcount, 1);
-	init_completion(&ctx->done);
-
-	timer_setup(&ctx->timer, ezusb_request_timerfn, 0);
-	return ctx;
-}
-
-static void ezusb_ctx_complete(struct request_context *ctx)
-{
-	struct ezusb_priv *upriv = ctx->upriv;
-	unsigned long flags;
-
-	spin_lock_irqsave(&upriv->req_lock, flags);
-
-	list_del_init(&ctx->list);
-	if (upriv->udev) {
-		spin_unlock_irqrestore(&upriv->req_lock, flags);
-		ezusb_req_queue_run(upriv);
-		spin_lock_irqsave(&upriv->req_lock, flags);
-	}
-
-	switch (ctx->state) {
-	case EZUSB_CTX_COMPLETE:
-	case EZUSB_CTX_REQSUBMIT_FAIL:
-	case EZUSB_CTX_REQ_FAILED:
-	case EZUSB_CTX_REQ_TIMEOUT:
-	case EZUSB_CTX_RESP_TIMEOUT:
-		spin_unlock_irqrestore(&upriv->req_lock, flags);
-
-		if ((ctx->out_rid == EZUSB_RID_TX) && upriv->dev) {
-			struct net_device *dev = upriv->dev;
-			struct net_device_stats *stats = &dev->stats;
-
-			if (ctx->state != EZUSB_CTX_COMPLETE)
-				stats->tx_errors++;
-			else
-				stats->tx_packets++;
-
-			netif_wake_queue(dev);
-		}
-		complete_all(&ctx->done);
-		ezusb_request_context_put(ctx);
-		break;
-
-	default:
-		spin_unlock_irqrestore(&upriv->req_lock, flags);
-		if (!upriv->udev) {
-			/* This is normal, as all request contexts get flushed
-			 * when the device is disconnected */
-			err("Called, CTX not terminating, but device gone");
-			complete_all(&ctx->done);
-			ezusb_request_context_put(ctx);
-			break;
-		}
-
-		err("Called, CTX not in terminating state.");
-		/* Things are really bad if this happens. Just leak
-		 * the CTX because it may still be linked to the
-		 * queue or the OUT urb may still be active.
-		 * Just leaking at least prevents an Oops or Panic.
-		 */
-		break;
-	}
-}
-
-/*
- * ezusb_req_queue_run:
- * Description:
- *	Note: Only one active CTX at any one time, because there's no
- *	other (reliable) way to match the response URB to the correct
- *	CTX.
- */
-static void ezusb_req_queue_run(struct ezusb_priv *upriv)
-{
-	unsigned long flags;
-	struct request_context *ctx;
-	int result;
-
-	spin_lock_irqsave(&upriv->req_lock, flags);
-
-	if (!list_empty(&upriv->req_active))
-		goto unlock;
-
-	if (list_empty(&upriv->req_pending))
-		goto unlock;
-
-	ctx =
-	    list_entry(upriv->req_pending.next, struct request_context,
-		       list);
-
-	if (!ctx->upriv->udev)
-		goto unlock;
-
-	/* We need to split this off to avoid a race condition */
-	list_move_tail(&ctx->list, &upriv->req_active);
-
-	if (ctx->state == EZUSB_CTX_QUEUED) {
-		refcount_inc(&ctx->refcount);
-		result = usb_submit_urb(ctx->outurb, GFP_ATOMIC);
-		if (result) {
-			ctx->state = EZUSB_CTX_REQSUBMIT_FAIL;
-
-			spin_unlock_irqrestore(&upriv->req_lock, flags);
-
-			err("Fatal, failed to submit command urb."
-			    " error=%d\n", result);
-
-			ezusb_ctx_complete(ctx);
-			ezusb_request_context_put(ctx);
-			goto done;
-		}
-
-		ctx->state = EZUSB_CTX_REQ_SUBMITTED;
-		ezusb_mod_timer(ctx->upriv, &ctx->timer,
-				jiffies + DEF_TIMEOUT);
-	}
-
- unlock:
-	spin_unlock_irqrestore(&upriv->req_lock, flags);
-
- done:
-	return;
-}
-
-static void ezusb_req_enqueue_run(struct ezusb_priv *upriv,
-				  struct request_context *ctx)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&upriv->req_lock, flags);
-
-	if (!ctx->upriv->udev) {
-		spin_unlock_irqrestore(&upriv->req_lock, flags);
-		goto done;
-	}
-	refcount_inc(&ctx->refcount);
-	list_add_tail(&ctx->list, &upriv->req_pending);
-	spin_unlock_irqrestore(&upriv->req_lock, flags);
-
-	ctx->state = EZUSB_CTX_QUEUED;
-	ezusb_req_queue_run(upriv);
-
- done:
-	return;
-}
-
-static void ezusb_request_out_callback(struct urb *urb)
-{
-	unsigned long flags;
-	enum ezusb_state state;
-	struct request_context *ctx = urb->context;
-	struct ezusb_priv *upriv = ctx->upriv;
-
-	spin_lock_irqsave(&upriv->req_lock, flags);
-
-	del_timer(&ctx->timer);
-
-	if (ctx->killed) {
-		spin_unlock_irqrestore(&upriv->req_lock, flags);
-		pr_warn("interrupt called with dead ctx\n");
-		goto out;
-	}
-
-	state = ctx->state;
-
-	if (urb->status == 0) {
-		switch (state) {
-		case EZUSB_CTX_REQ_SUBMITTED:
-			if (ctx->in_rid) {
-				ctx->state = EZUSB_CTX_REQ_COMPLETE;
-				/* reply URB still pending */
-				ezusb_mod_timer(upriv, &ctx->timer,
-						jiffies + DEF_TIMEOUT);
-				spin_unlock_irqrestore(&upriv->req_lock,
-						       flags);
-				break;
-			}
-			fallthrough;
-		case EZUSB_CTX_RESP_RECEIVED:
-			/* IN already received before this OUT-ACK */
-			ctx->state = EZUSB_CTX_COMPLETE;
-			spin_unlock_irqrestore(&upriv->req_lock, flags);
-			ezusb_ctx_complete(ctx);
-			break;
-
-		default:
-			spin_unlock_irqrestore(&upriv->req_lock, flags);
-			err("Unexpected state(0x%x, %d) in OUT URB",
-			    state, urb->status);
-			break;
-		}
-	} else {
-		/* If someone cancels the OUT URB then its status
-		 * should be either -ECONNRESET or -ENOENT.
-		 */
-		switch (state) {
-		case EZUSB_CTX_REQ_SUBMITTED:
-		case EZUSB_CTX_RESP_RECEIVED:
-			ctx->state = EZUSB_CTX_REQ_FAILED;
-			fallthrough;
-
-		case EZUSB_CTX_REQ_FAILED:
-		case EZUSB_CTX_REQ_TIMEOUT:
-			spin_unlock_irqrestore(&upriv->req_lock, flags);
-
-			ezusb_ctx_complete(ctx);
-			break;
-
-		default:
-			spin_unlock_irqrestore(&upriv->req_lock, flags);
-
-			err("Unexpected state(0x%x, %d) in OUT URB",
-			    state, urb->status);
-			break;
-		}
-	}
- out:
-	ezusb_request_context_put(ctx);
-}
-
-static void ezusb_request_in_callback(struct ezusb_priv *upriv,
-				      struct urb *urb)
-{
-	struct ezusb_packet *ans = urb->transfer_buffer;
-	struct request_context *ctx = NULL;
-	enum ezusb_state state;
-	unsigned long flags;
-
-	/* Find the CTX on the active queue that requested this URB */
-	spin_lock_irqsave(&upriv->req_lock, flags);
-	if (upriv->udev) {
-		struct list_head *item;
-
-		list_for_each(item, &upriv->req_active) {
-			struct request_context *c;
-			int reply_count;
-
-			c = list_entry(item, struct request_context, list);
-			reply_count =
-			    ezusb_reply_inc(c->buf->req_reply_count);
-			if ((ans->ans_reply_count == reply_count)
-			    && (le16_to_cpu(ans->hermes_rid) == c->in_rid)) {
-				ctx = c;
-				break;
-			}
-			netdev_dbg(upriv->dev, "Skipped (0x%x/0x%x) (%d/%d)\n",
-				   le16_to_cpu(ans->hermes_rid), c->in_rid,
-				   ans->ans_reply_count, reply_count);
-		}
-	}
-
-	if (ctx == NULL) {
-		spin_unlock_irqrestore(&upriv->req_lock, flags);
-		err("%s: got unexpected RID: 0x%04X", __func__,
-		    le16_to_cpu(ans->hermes_rid));
-		ezusb_req_queue_run(upriv);
-		return;
-	}
-
-	/* The data we want is in the in buffer, exchange */
-	urb->transfer_buffer = ctx->buf;
-	ctx->buf = (void *) ans;
-	ctx->buf_length = urb->actual_length;
-
-	state = ctx->state;
-	switch (state) {
-	case EZUSB_CTX_REQ_SUBMITTED:
-		/* We have received our response URB before
-		 * our request has been acknowledged. Do NOT
-		 * destroy our CTX yet, because our OUT URB
-		 * is still alive ...
-		 */
-		ctx->state = EZUSB_CTX_RESP_RECEIVED;
-		spin_unlock_irqrestore(&upriv->req_lock, flags);
-
-		/* Let the machine continue running. */
-		break;
-
-	case EZUSB_CTX_REQ_COMPLETE:
-		/* This is the usual path: our request
-		 * has already been acknowledged, and
-		 * we have now received the reply.
-		 */
-		ctx->state = EZUSB_CTX_COMPLETE;
-
-		/* Stop the intimer */
-		del_timer(&ctx->timer);
-		spin_unlock_irqrestore(&upriv->req_lock, flags);
-
-		/* Call the completion handler */
-		ezusb_ctx_complete(ctx);
-		break;
-
-	default:
-		spin_unlock_irqrestore(&upriv->req_lock, flags);
-
-		pr_warn("Matched IN URB, unexpected context state(0x%x)\n",
-			state);
-		/* Throw this CTX away and try submitting another */
-		del_timer(&ctx->timer);
-		ctx->outurb->transfer_flags |= URB_ASYNC_UNLINK;
-		usb_unlink_urb(ctx->outurb);
-		ezusb_req_queue_run(upriv);
-		break;
-	}			/* switch */
-}
-
-typedef void (*ezusb_ctx_wait)(struct ezusb_priv *, struct request_context *);
-
-static void ezusb_req_ctx_wait_compl(struct ezusb_priv *upriv,
-				     struct request_context *ctx)
-{
-	switch (ctx->state) {
-	case EZUSB_CTX_QUEUED:
-	case EZUSB_CTX_REQ_SUBMITTED:
-	case EZUSB_CTX_REQ_COMPLETE:
-	case EZUSB_CTX_RESP_RECEIVED:
-		wait_for_completion(&ctx->done);
-		break;
-	default:
-		/* Done or failed - nothing to wait for */
-		break;
-	}
-}
-
-static void ezusb_req_ctx_wait_poll(struct ezusb_priv *upriv,
-				    struct request_context *ctx)
-{
-	int msecs;
-
-	switch (ctx->state) {
-	case EZUSB_CTX_QUEUED:
-	case EZUSB_CTX_REQ_SUBMITTED:
-	case EZUSB_CTX_REQ_COMPLETE:
-	case EZUSB_CTX_RESP_RECEIVED:
-		/* If we get called from a timer or with our lock acquired, then
-		 * we can't wait for the completion and have to poll. This won't
-		 * happen if the USB controller completes the URB requests in
-		 * BH.
-		 */
-		msecs = DEF_TIMEOUT * (1000 / HZ);
-
-		while (!try_wait_for_completion(&ctx->done) && msecs--)
-			udelay(1000);
-		break;
-	default:
-		/* Done or failed - nothing to wait for */
-		break;
-	}
-}
-
-static void ezusb_req_ctx_wait_skip(struct ezusb_priv *upriv,
-				    struct request_context *ctx)
-{
-	WARN(1, "Shouldn't be invoked for in_rid\n");
-}
-
-static inline u16 build_crc(struct ezusb_packet *data)
-{
-	u16 crc = 0;
-	u8 *bytes = (u8 *)data;
-	int i;
-
-	for (i = 0; i < 8; i++)
-		crc = (crc << 1) + bytes[i];
-
-	return crc;
-}
-
-/*
- * ezusb_fill_req:
- *
- * if data == NULL and length > 0 the data is assumed to be already in
- * the target buffer and only the header is filled.
- *
- */
-static int ezusb_fill_req(struct ezusb_packet *req, u16 length, u16 rid,
-			  const void *data, u16 frame_type, u8 reply_count)
-{
-	int total_size = sizeof(*req) + length;
-
-	BUG_ON(total_size > BULK_BUF_SIZE);
-
-	req->magic = cpu_to_le16(EZUSB_MAGIC);
-	req->req_reply_count = reply_count;
-	req->ans_reply_count = 0;
-	req->frame_type = cpu_to_le16(frame_type);
-	req->size = cpu_to_le16(length + 4);
-	req->crc = cpu_to_le16(build_crc(req));
-	req->hermes_len = cpu_to_le16(HERMES_BYTES_TO_RECLEN(length));
-	req->hermes_rid = cpu_to_le16(rid);
-	if (data)
-		memcpy(req->data, data, length);
-	return total_size;
-}
-
-static int ezusb_submit_in_urb(struct ezusb_priv *upriv)
-{
-	int retval = 0;
-	void *cur_buf = upriv->read_urb->transfer_buffer;
-
-	if (upriv->read_urb->status == -EINPROGRESS) {
-		netdev_dbg(upriv->dev, "urb busy, not resubmiting\n");
-		retval = -EBUSY;
-		goto exit;
-	}
-	usb_fill_bulk_urb(upriv->read_urb, upriv->udev, upriv->read_pipe,
-			  cur_buf, BULK_BUF_SIZE,
-			  ezusb_bulk_in_callback, upriv);
-	upriv->read_urb->transfer_flags = 0;
-	retval = usb_submit_urb(upriv->read_urb, GFP_ATOMIC);
-	if (retval)
-		err("%s submit failed %d", __func__, retval);
-
- exit:
-	return retval;
-}
-
-static inline int ezusb_8051_cpucs(struct ezusb_priv *upriv, int reset)
-{
-	int ret;
-	u8 *res_val = NULL;
-
-	if (!upriv->udev) {
-		err("%s: !upriv->udev", __func__);
-		return -EFAULT;
-	}
-
-	res_val = kmalloc(sizeof(*res_val), GFP_KERNEL);
-
-	if (!res_val)
-		return -ENOMEM;
-
-	*res_val = reset;	/* avoid argument promotion */
-
-	ret =  usb_control_msg(upriv->udev,
-			       usb_sndctrlpipe(upriv->udev, 0),
-			       EZUSB_REQUEST_FW_TRANS,
-			       USB_TYPE_VENDOR | USB_RECIP_DEVICE |
-			       USB_DIR_OUT, EZUSB_CPUCS_REG, 0, res_val,
-			       sizeof(*res_val), DEF_TIMEOUT);
-
-	kfree(res_val);
-
-	return ret;
-}
-
-static int ezusb_firmware_download(struct ezusb_priv *upriv,
-				   struct ez_usb_fw *fw)
-{
-	u8 *fw_buffer;
-	int retval, addr;
-	int variant_offset;
-
-	fw_buffer = kmalloc(FW_BUF_SIZE, GFP_KERNEL);
-	if (!fw_buffer) {
-		printk(KERN_ERR PFX "Out of memory for firmware buffer.\n");
-		return -ENOMEM;
-	}
-	/*
-	 * This byte is 1 and should be replaced with 0.  The offset is
-	 * 0x10AD in version 0.0.6.  The byte in question should follow
-	 * the end of the code pointed to by the jump in the beginning
-	 * of the firmware.  Also, it is read by code located at 0x358.
-	 */
-	variant_offset = be16_to_cpup((__be16 *) &fw->code[FW_VAR_OFFSET_PTR]);
-	if (variant_offset >= fw->size) {
-		printk(KERN_ERR PFX "Invalid firmware variant offset: "
-		       "0x%04x\n", variant_offset);
-		retval = -EINVAL;
-		goto fail;
-	}
-
-	retval = ezusb_8051_cpucs(upriv, 1);
-	if (retval < 0)
-		goto fail;
-	for (addr = 0; addr < fw->size; addr += FW_BUF_SIZE) {
-		/* 0x100-0x300 should be left alone, it contains card
-		 * specific data, like USB enumeration information */
-		if ((addr >= FW_HOLE_START) && (addr < FW_HOLE_END))
-			continue;
-
-		memcpy(fw_buffer, &fw->code[addr], FW_BUF_SIZE);
-		if (variant_offset >= addr &&
-		    variant_offset < addr + FW_BUF_SIZE) {
-			netdev_dbg(upriv->dev,
-				   "Patching card_variant byte at 0x%04X\n",
-				   variant_offset);
-			fw_buffer[variant_offset - addr] = FW_VAR_VALUE;
-		}
-		retval = usb_control_msg(upriv->udev,
-					 usb_sndctrlpipe(upriv->udev, 0),
-					 EZUSB_REQUEST_FW_TRANS,
-					 USB_TYPE_VENDOR | USB_RECIP_DEVICE
-					 | USB_DIR_OUT,
-					 addr, 0x0,
-					 fw_buffer, FW_BUF_SIZE,
-					 DEF_TIMEOUT);
-
-		if (retval < 0)
-			goto fail;
-	}
-	retval = ezusb_8051_cpucs(upriv, 0);
-	if (retval < 0)
-		goto fail;
-
-	goto exit;
- fail:
-	printk(KERN_ERR PFX "Firmware download failed, error %d\n",
-	       retval);
- exit:
-	kfree(fw_buffer);
-	return retval;
-}
-
-static int ezusb_access_ltv(struct ezusb_priv *upriv,
-			    struct request_context *ctx,
-			    u16 length, const void *data, u16 frame_type,
-			    void *ans_buff, unsigned ans_size, u16 *ans_length,
-			    ezusb_ctx_wait ezusb_ctx_wait_func)
-{
-	int req_size;
-	int retval = 0;
-	enum ezusb_state state;
-
-	if (!upriv->udev) {
-		retval = -ENODEV;
-		goto exit;
-	}
-
-	if (upriv->read_urb->status != -EINPROGRESS)
-		err("%s: in urb not pending", __func__);
-
-	/* protect upriv->reply_count, guarantee sequential numbers */
-	spin_lock_bh(&upriv->reply_count_lock);
-	req_size = ezusb_fill_req(ctx->buf, length, ctx->out_rid, data,
-				  frame_type, upriv->reply_count);
-	usb_fill_bulk_urb(ctx->outurb, upriv->udev, upriv->write_pipe,
-			  ctx->buf, req_size,
-			  ezusb_request_out_callback, ctx);
-
-	if (ctx->in_rid)
-		upriv->reply_count = ezusb_reply_inc(upriv->reply_count);
-
-	ezusb_req_enqueue_run(upriv, ctx);
-
-	spin_unlock_bh(&upriv->reply_count_lock);
-
-	if (ctx->in_rid)
-		ezusb_ctx_wait_func(upriv, ctx);
-
-	state = ctx->state;
-	switch (state) {
-	case EZUSB_CTX_COMPLETE:
-		retval = ctx->outurb->status;
-		break;
-
-	case EZUSB_CTX_QUEUED:
-	case EZUSB_CTX_REQ_SUBMITTED:
-		if (!ctx->in_rid)
-			break;
-		fallthrough;
-	default:
-		err("%s: Unexpected context state %d", __func__,
-		    state);
-		fallthrough;
-	case EZUSB_CTX_REQ_TIMEOUT:
-	case EZUSB_CTX_REQ_FAILED:
-	case EZUSB_CTX_RESP_TIMEOUT:
-	case EZUSB_CTX_REQSUBMIT_FAIL:
-		printk(KERN_ERR PFX "Access failed, resetting (state %d,"
-		       " reply_count %d)\n", state, upriv->reply_count);
-		upriv->reply_count = 0;
-		if (state == EZUSB_CTX_REQ_TIMEOUT
-		    || state == EZUSB_CTX_RESP_TIMEOUT) {
-			printk(KERN_ERR PFX "ctx timed out\n");
-			retval = -ETIMEDOUT;
-		} else {
-			printk(KERN_ERR PFX "ctx failed\n");
-			retval = -EFAULT;
-		}
-		goto exit;
-	}
-	if (ctx->in_rid) {
-		struct ezusb_packet *ans = ctx->buf;
-		unsigned exp_len;
-
-		if (ans->hermes_len != 0)
-			exp_len = le16_to_cpu(ans->hermes_len) * 2 + 12;
-		else
-			exp_len = 14;
-
-		if (exp_len != ctx->buf_length) {
-			err("%s: length mismatch for RID 0x%04x: "
-			    "expected %d, got %d", __func__,
-			    ctx->in_rid, exp_len, ctx->buf_length);
-			retval = -EIO;
-			goto exit;
-		}
-
-		if (ans_buff)
-			memcpy(ans_buff, ans->data, min(exp_len, ans_size));
-		if (ans_length)
-			*ans_length = le16_to_cpu(ans->hermes_len);
-	}
- exit:
-	ezusb_request_context_put(ctx);
-	return retval;
-}
-
-static int __ezusb_write_ltv(struct hermes *hw, int bap, u16 rid,
-			   u16 length, const void *data,
-			   ezusb_ctx_wait ezusb_ctx_wait_func)
-{
-	struct ezusb_priv *upriv = hw->priv;
-	u16 frame_type;
-	struct request_context *ctx;
-
-	if (length == 0)
-		return -EINVAL;
-
-	length = HERMES_RECLEN_TO_BYTES(length);
-
-	/* On memory mapped devices HERMES_RID_CNFGROUPADDRESSES can be
-	 * set to be empty, but the USB bridge doesn't like it */
-	if (length == 0)
-		return 0;
-
-	ctx = ezusb_alloc_ctx(upriv, rid, EZUSB_RID_ACK);
-	if (!ctx)
-		return -ENOMEM;
-
-	if (rid == EZUSB_RID_TX)
-		frame_type = EZUSB_FRAME_DATA;
-	else
-		frame_type = EZUSB_FRAME_CONTROL;
-
-	return ezusb_access_ltv(upriv, ctx, length, data, frame_type,
-				NULL, 0, NULL, ezusb_ctx_wait_func);
-}
-
-static int ezusb_write_ltv(struct hermes *hw, int bap, u16 rid,
-			   u16 length, const void *data)
-{
-	return __ezusb_write_ltv(hw, bap, rid, length, data,
-				 ezusb_req_ctx_wait_poll);
-}
-
-static int __ezusb_read_ltv(struct hermes *hw, int bap, u16 rid,
-			    unsigned bufsize, u16 *length, void *buf,
-			    ezusb_ctx_wait ezusb_ctx_wait_func)
-
-{
-	struct ezusb_priv *upriv = hw->priv;
-	struct request_context *ctx;
-
-	if (bufsize % 2)
-		return -EINVAL;
-
-	ctx = ezusb_alloc_ctx(upriv, rid, rid);
-	if (!ctx)
-		return -ENOMEM;
-
-	return ezusb_access_ltv(upriv, ctx, 0, NULL, EZUSB_FRAME_CONTROL,
-				buf, bufsize, length, ezusb_req_ctx_wait_poll);
-}
-
-static int ezusb_read_ltv(struct hermes *hw, int bap, u16 rid,
-			    unsigned bufsize, u16 *length, void *buf)
-{
-	return __ezusb_read_ltv(hw, bap, rid, bufsize, length, buf,
-				ezusb_req_ctx_wait_poll);
-}
-
-static int ezusb_read_ltv_preempt(struct hermes *hw, int bap, u16 rid,
-				  unsigned bufsize, u16 *length, void *buf)
-{
-	return __ezusb_read_ltv(hw, bap, rid, bufsize, length, buf,
-				ezusb_req_ctx_wait_compl);
-}
-
-static int ezusb_doicmd_wait(struct hermes *hw, u16 cmd, u16 parm0, u16 parm1,
-			     u16 parm2, struct hermes_response *resp)
-{
-	WARN_ON_ONCE(1);
-	return -EINVAL;
-}
-
-static int __ezusb_docmd_wait(struct hermes *hw, u16 cmd, u16 parm0,
-			    struct hermes_response *resp,
-			    ezusb_ctx_wait ezusb_ctx_wait_func)
-{
-	struct ezusb_priv *upriv = hw->priv;
-	struct request_context *ctx;
-
-	__le16 data[4] = {
-		cpu_to_le16(cmd),
-		cpu_to_le16(parm0),
-		0,
-		0,
-	};
-	netdev_dbg(upriv->dev, "0x%04X, parm0 0x%04X\n", cmd, parm0);
-	ctx = ezusb_alloc_ctx(upriv, EZUSB_RID_DOCMD, EZUSB_RID_ACK);
-	if (!ctx)
-		return -ENOMEM;
-
-	return ezusb_access_ltv(upriv, ctx, sizeof(data), &data,
-				EZUSB_FRAME_CONTROL, NULL, 0, NULL,
-				ezusb_ctx_wait_func);
-}
-
-static int ezusb_docmd_wait(struct hermes *hw, u16 cmd, u16 parm0,
-			    struct hermes_response *resp)
-{
-	return __ezusb_docmd_wait(hw, cmd, parm0, resp, ezusb_req_ctx_wait_poll);
-}
-
-static int ezusb_bap_pread(struct hermes *hw, int bap,
-			   void *buf, int len, u16 id, u16 offset)
-{
-	struct ezusb_priv *upriv = hw->priv;
-	struct ezusb_packet *ans = (void *) upriv->read_urb->transfer_buffer;
-	int actual_length = upriv->read_urb->actual_length;
-
-	if (id == EZUSB_RID_RX) {
-		if ((sizeof(*ans) + offset + len) > actual_length) {
-			printk(KERN_ERR PFX "BAP read beyond buffer end "
-			       "in rx frame\n");
-			return -EINVAL;
-		}
-		memcpy(buf, ans->data + offset, len);
-		return 0;
-	}
-
-	if (EZUSB_IS_INFO(id)) {
-		/* Include 4 bytes for length/type */
-		if ((sizeof(*ans) + offset + len - 4) > actual_length) {
-			printk(KERN_ERR PFX "BAP read beyond buffer end "
-			       "in info frame\n");
-			return -EFAULT;
-		}
-		memcpy(buf, ans->data + offset - 4, len);
-	} else {
-		printk(KERN_ERR PFX "Unexpected fid 0x%04x\n", id);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int ezusb_read_pda(struct hermes *hw, __le16 *pda,
-			  u32 pda_addr, u16 pda_len)
-{
-	struct ezusb_priv *upriv = hw->priv;
-	struct request_context *ctx;
-	__le16 data[] = {
-		cpu_to_le16(pda_addr & 0xffff),
-		cpu_to_le16(pda_len - 4)
-	};
-	ctx = ezusb_alloc_ctx(upriv, EZUSB_RID_READ_PDA, EZUSB_RID_READ_PDA);
-	if (!ctx)
-		return -ENOMEM;
-
-	/* wl_lkm does not include PDA size in the PDA area.
-	 * We will pad the information into pda, so other routines
-	 * don't have to be modified */
-	pda[0] = cpu_to_le16(pda_len - 2);
-	/* Includes CFG_PROD_DATA but not itself */
-	pda[1] = cpu_to_le16(0x0800); /* CFG_PROD_DATA */
-
-	return ezusb_access_ltv(upriv, ctx, sizeof(data), &data,
-				EZUSB_FRAME_CONTROL, &pda[2], pda_len - 4,
-				NULL, ezusb_req_ctx_wait_compl);
-}
-
-static int ezusb_program_init(struct hermes *hw, u32 entry_point)
-{
-	struct ezusb_priv *upriv = hw->priv;
-	struct request_context *ctx;
-	__le32 data = cpu_to_le32(entry_point);
-
-	ctx = ezusb_alloc_ctx(upriv, EZUSB_RID_PROG_INIT, EZUSB_RID_ACK);
-	if (!ctx)
-		return -ENOMEM;
-
-	return ezusb_access_ltv(upriv, ctx, sizeof(data), &data,
-				EZUSB_FRAME_CONTROL, NULL, 0, NULL,
-				ezusb_req_ctx_wait_compl);
-}
-
-static int ezusb_program_end(struct hermes *hw)
-{
-	struct ezusb_priv *upriv = hw->priv;
-	struct request_context *ctx;
-
-	ctx = ezusb_alloc_ctx(upriv, EZUSB_RID_PROG_END, EZUSB_RID_ACK);
-	if (!ctx)
-		return -ENOMEM;
-
-	return ezusb_access_ltv(upriv, ctx, 0, NULL,
-				EZUSB_FRAME_CONTROL, NULL, 0, NULL,
-				ezusb_req_ctx_wait_compl);
-}
-
-static int ezusb_program_bytes(struct hermes *hw, const char *buf,
-			       u32 addr, u32 len)
-{
-	struct ezusb_priv *upriv = hw->priv;
-	struct request_context *ctx;
-	__le32 data = cpu_to_le32(addr);
-	int err;
-
-	ctx = ezusb_alloc_ctx(upriv, EZUSB_RID_PROG_SET_ADDR, EZUSB_RID_ACK);
-	if (!ctx)
-		return -ENOMEM;
-
-	err = ezusb_access_ltv(upriv, ctx, sizeof(data), &data,
-			       EZUSB_FRAME_CONTROL, NULL, 0, NULL,
-			       ezusb_req_ctx_wait_compl);
-	if (err)
-		return err;
-
-	ctx = ezusb_alloc_ctx(upriv, EZUSB_RID_PROG_BYTES, EZUSB_RID_ACK);
-	if (!ctx)
-		return -ENOMEM;
-
-	return ezusb_access_ltv(upriv, ctx, len, buf,
-				EZUSB_FRAME_CONTROL, NULL, 0, NULL,
-				ezusb_req_ctx_wait_compl);
-}
-
-static int ezusb_program(struct hermes *hw, const char *buf,
-			 u32 addr, u32 len)
-{
-	u32 ch_addr;
-	u32 ch_len;
-	int err = 0;
-
-	/* We can only send 2048 bytes out of the bulk xmit at a time,
-	 * so we have to split any programming into chunks of <2048
-	 * bytes. */
-
-	ch_len = (len < MAX_DL_SIZE) ? len : MAX_DL_SIZE;
-	ch_addr = addr;
-
-	while (ch_addr < (addr + len)) {
-		pr_debug("Programming subblock of length %d "
-			 "to address 0x%08x. Data @ %p\n",
-			 ch_len, ch_addr, &buf[ch_addr - addr]);
-
-		err = ezusb_program_bytes(hw, &buf[ch_addr - addr],
-					  ch_addr, ch_len);
-		if (err)
-			break;
-
-		ch_addr += ch_len;
-		ch_len = ((addr + len - ch_addr) < MAX_DL_SIZE) ?
-			(addr + len - ch_addr) : MAX_DL_SIZE;
-	}
-
-	return err;
-}
-
-static netdev_tx_t ezusb_xmit(struct sk_buff *skb, struct net_device *dev)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	struct net_device_stats *stats = &dev->stats;
-	struct ezusb_priv *upriv = priv->card;
-	u8 mic[MICHAEL_MIC_LEN + 1];
-	int err = 0;
-	int tx_control;
-	unsigned long flags;
-	struct request_context *ctx;
-	u8 *buf;
-	int tx_size;
-
-	if (!netif_running(dev)) {
-		printk(KERN_ERR "%s: Tx on stopped device!\n",
-		       dev->name);
-		return NETDEV_TX_BUSY;
-	}
-
-	if (netif_queue_stopped(dev)) {
-		printk(KERN_DEBUG "%s: Tx while transmitter busy!\n",
-		       dev->name);
-		return NETDEV_TX_BUSY;
-	}
-
-	if (orinoco_lock(priv, &flags) != 0) {
-		printk(KERN_ERR
-		       "%s: ezusb_xmit() called while hw_unavailable\n",
-		       dev->name);
-		return NETDEV_TX_BUSY;
-	}
-
-	if (!netif_carrier_ok(dev) ||
-	    (priv->iw_mode == NL80211_IFTYPE_MONITOR)) {
-		/* Oops, the firmware hasn't established a connection,
-		   silently drop the packet (this seems to be the
-		   safest approach). */
-		goto drop;
-	}
-
-	/* Check packet length */
-	if (skb->len < ETH_HLEN)
-		goto drop;
-
-	tx_control = 0;
-
-	err = orinoco_process_xmit_skb(skb, dev, priv, &tx_control,
-				       &mic[0]);
-	if (err)
-		goto drop;
-
-	ctx = ezusb_alloc_ctx(upriv, EZUSB_RID_TX, 0);
-	if (!ctx)
-		goto drop;
-
-	memset(ctx->buf, 0, BULK_BUF_SIZE);
-	buf = ctx->buf->data;
-
-	{
-		__le16 *tx_cntl = (__le16 *)buf;
-		*tx_cntl = cpu_to_le16(tx_control);
-		buf += sizeof(*tx_cntl);
-	}
-
-	memcpy(buf, skb->data, skb->len);
-	buf += skb->len;
-
-	if (tx_control & HERMES_TXCTRL_MIC) {
-		u8 *m = mic;
-		/* Mic has been offset so it can be copied to an even
-		 * address. We're copying eveything anyway, so we
-		 * don't need to copy that first byte. */
-		if (skb->len % 2)
-			m++;
-		memcpy(buf, m, MICHAEL_MIC_LEN);
-		buf += MICHAEL_MIC_LEN;
-	}
-
-	/* Finally, we actually initiate the send */
-	netif_stop_queue(dev);
-
-	/* The card may behave better if we send evenly sized usb transfers */
-	tx_size = ALIGN(buf - ctx->buf->data, 2);
-
-	err = ezusb_access_ltv(upriv, ctx, tx_size, NULL,
-			       EZUSB_FRAME_DATA, NULL, 0, NULL,
-			       ezusb_req_ctx_wait_skip);
-
-	if (err) {
-		netif_start_queue(dev);
-		if (net_ratelimit())
-			printk(KERN_ERR "%s: Error %d transmitting packet\n",
-				dev->name, err);
-		goto busy;
-	}
-
-	netif_trans_update(dev);
-	stats->tx_bytes += skb->len;
-	goto ok;
-
- drop:
-	stats->tx_errors++;
-	stats->tx_dropped++;
-
- ok:
-	orinoco_unlock(priv, &flags);
-	dev_kfree_skb(skb);
-	return NETDEV_TX_OK;
-
- busy:
-	orinoco_unlock(priv, &flags);
-	return NETDEV_TX_BUSY;
-}
-
-static int ezusb_allocate(struct hermes *hw, u16 size, u16 *fid)
-{
-	*fid = EZUSB_RID_TX;
-	return 0;
-}
-
-
-static int ezusb_hard_reset(struct orinoco_private *priv)
-{
-	struct ezusb_priv *upriv = priv->card;
-	int retval = ezusb_8051_cpucs(upriv, 1);
-
-	if (retval < 0) {
-		err("Failed to reset");
-		return retval;
-	}
-
-	retval = ezusb_8051_cpucs(upriv, 0);
-	if (retval < 0) {
-		err("Failed to unreset");
-		return retval;
-	}
-
-	netdev_dbg(upriv->dev, "sending control message\n");
-	retval = usb_control_msg(upriv->udev,
-				 usb_sndctrlpipe(upriv->udev, 0),
-				 EZUSB_REQUEST_TRIGGER,
-				 USB_TYPE_VENDOR | USB_RECIP_DEVICE |
-				 USB_DIR_OUT, 0x0, 0x0, NULL, 0,
-				 DEF_TIMEOUT);
-	if (retval < 0) {
-		err("EZUSB_REQUEST_TRIGGER failed retval %d", retval);
-		return retval;
-	}
-#if 0
-	dbg("Sending EZUSB_REQUEST_TRIG_AC");
-	retval = usb_control_msg(upriv->udev,
-				 usb_sndctrlpipe(upriv->udev, 0),
-				 EZUSB_REQUEST_TRIG_AC,
-				 USB_TYPE_VENDOR | USB_RECIP_DEVICE |
-				 USB_DIR_OUT, 0x00FA, 0x0, NULL, 0,
-				 DEF_TIMEOUT);
-	if (retval < 0) {
-		err("EZUSB_REQUEST_TRIG_AC failed retval %d", retval);
-		return retval;
-	}
-#endif
-
-	return 0;
-}
-
-
-static int ezusb_init(struct hermes *hw)
-{
-	struct ezusb_priv *upriv = hw->priv;
-	int retval;
-
-	if (!upriv)
-		return -EINVAL;
-
-	upriv->reply_count = 0;
-	/* Write the MAGIC number on the simulated registers to keep
-	 * orinoco.c happy */
-	hermes_write_regn(hw, SWSUPPORT0, HERMES_MAGIC);
-	hermes_write_regn(hw, RXFID, EZUSB_RID_RX);
-
-	usb_kill_urb(upriv->read_urb);
-	ezusb_submit_in_urb(upriv);
-
-	retval = __ezusb_write_ltv(hw, 0, EZUSB_RID_INIT1,
-				 HERMES_BYTES_TO_RECLEN(2), "\x10\x00",
-				 ezusb_req_ctx_wait_compl);
-	if (retval < 0) {
-		printk(KERN_ERR PFX "EZUSB_RID_INIT1 error %d\n", retval);
-		return retval;
-	}
-
-	retval = __ezusb_docmd_wait(hw, HERMES_CMD_INIT, 0, NULL,
-				    ezusb_req_ctx_wait_compl);
-	if (retval < 0) {
-		printk(KERN_ERR PFX "HERMES_CMD_INIT error %d\n", retval);
-		return retval;
-	}
-
-	return 0;
-}
-
-static void ezusb_bulk_in_callback(struct urb *urb)
-{
-	struct ezusb_priv *upriv = (struct ezusb_priv *) urb->context;
-	struct ezusb_packet *ans = urb->transfer_buffer;
-	u16 crc;
-	u16 hermes_rid;
-
-	if (upriv->udev == NULL)
-		return;
-
-	if (urb->status == -ETIMEDOUT) {
-		/* When a device gets unplugged we get this every time
-		 * we resubmit, flooding the logs.  Since we don't use
-		 * USB timeouts, it shouldn't happen any other time*/
-		pr_warn("%s: urb timed out, not resubmitting\n", __func__);
-		return;
-	}
-	if (urb->status == -ECONNABORTED) {
-		pr_warn("%s: connection abort, resubmitting urb\n",
-			__func__);
-		goto resubmit;
-	}
-	if ((urb->status == -EILSEQ)
-	    || (urb->status == -ENOENT)
-	    || (urb->status == -ECONNRESET)) {
-		netdev_dbg(upriv->dev, "status %d, not resubmiting\n",
-			   urb->status);
-		return;
-	}
-	if (urb->status)
-		netdev_dbg(upriv->dev, "status: %d length: %d\n",
-			   urb->status, urb->actual_length);
-	if (urb->actual_length < sizeof(*ans)) {
-		err("%s: short read, ignoring", __func__);
-		goto resubmit;
-	}
-	crc = build_crc(ans);
-	if (le16_to_cpu(ans->crc) != crc) {
-		err("CRC error, ignoring packet");
-		goto resubmit;
-	}
-
-	hermes_rid = le16_to_cpu(ans->hermes_rid);
-	if ((hermes_rid != EZUSB_RID_RX) && !EZUSB_IS_INFO(hermes_rid)) {
-		ezusb_request_in_callback(upriv, urb);
-	} else if (upriv->dev) {
-		struct net_device *dev = upriv->dev;
-		struct orinoco_private *priv = ndev_priv(dev);
-		struct hermes *hw = &priv->hw;
-
-		if (hermes_rid == EZUSB_RID_RX) {
-			__orinoco_ev_rx(dev, hw);
-		} else {
-			hermes_write_regn(hw, INFOFID,
-					  le16_to_cpu(ans->hermes_rid));
-			__orinoco_ev_info(dev, hw);
-		}
-	}
-
- resubmit:
-	if (upriv->udev)
-		ezusb_submit_in_urb(upriv);
-}
-
-static inline void ezusb_delete(struct ezusb_priv *upriv)
-{
-	struct list_head *item;
-	struct list_head *tmp_item;
-	unsigned long flags;
-
-	BUG_ON(!upriv);
-
-	mutex_lock(&upriv->mtx);
-
-	upriv->udev = NULL;	/* No timer will be rearmed from here */
-
-	usb_kill_urb(upriv->read_urb);
-
-	spin_lock_irqsave(&upriv->req_lock, flags);
-	list_for_each_safe(item, tmp_item, &upriv->req_active) {
-		struct request_context *ctx;
-		int err;
-
-		ctx = list_entry(item, struct request_context, list);
-		refcount_inc(&ctx->refcount);
-
-		ctx->outurb->transfer_flags |= URB_ASYNC_UNLINK;
-		err = usb_unlink_urb(ctx->outurb);
-
-		spin_unlock_irqrestore(&upriv->req_lock, flags);
-		if (err == -EINPROGRESS)
-			wait_for_completion(&ctx->done);
-
-		del_timer_sync(&ctx->timer);
-		/* FIXME: there is an slight chance for the irq handler to
-		 * be running */
-		if (!list_empty(&ctx->list))
-			ezusb_ctx_complete(ctx);
-
-		ezusb_request_context_put(ctx);
-		spin_lock_irqsave(&upriv->req_lock, flags);
-	}
-	spin_unlock_irqrestore(&upriv->req_lock, flags);
-
-	list_for_each_safe(item, tmp_item, &upriv->req_pending)
-	    ezusb_ctx_complete(list_entry(item,
-					  struct request_context, list));
-
-	if (upriv->read_urb && upriv->read_urb->status == -EINPROGRESS)
-		printk(KERN_ERR PFX "Some URB in progress\n");
-
-	mutex_unlock(&upriv->mtx);
-
-	if (upriv->read_urb) {
-		kfree(upriv->read_urb->transfer_buffer);
-		usb_free_urb(upriv->read_urb);
-	}
-	kfree(upriv->bap_buf);
-	if (upriv->dev) {
-		struct orinoco_private *priv = ndev_priv(upriv->dev);
-		orinoco_if_del(priv);
-		wiphy_unregister(priv_to_wiphy(upriv));
-		free_orinocodev(priv);
-	}
-}
-
-static void ezusb_lock_irqsave(spinlock_t *lock,
-			       unsigned long *flags) __acquires(lock)
-{
-	spin_lock_bh(lock);
-}
-
-static void ezusb_unlock_irqrestore(spinlock_t *lock,
-				    unsigned long *flags) __releases(lock)
-{
-	spin_unlock_bh(lock);
-}
-
-static void ezusb_lock_irq(spinlock_t *lock) __acquires(lock)
-{
-	spin_lock_bh(lock);
-}
-
-static void ezusb_unlock_irq(spinlock_t *lock) __releases(lock)
-{
-	spin_unlock_bh(lock);
-}
-
-static const struct hermes_ops ezusb_ops = {
-	.init = ezusb_init,
-	.cmd_wait = ezusb_docmd_wait,
-	.init_cmd_wait = ezusb_doicmd_wait,
-	.allocate = ezusb_allocate,
-	.read_ltv = ezusb_read_ltv,
-	.read_ltv_pr = ezusb_read_ltv_preempt,
-	.write_ltv = ezusb_write_ltv,
-	.bap_pread = ezusb_bap_pread,
-	.read_pda = ezusb_read_pda,
-	.program_init = ezusb_program_init,
-	.program_end = ezusb_program_end,
-	.program = ezusb_program,
-	.lock_irqsave = ezusb_lock_irqsave,
-	.unlock_irqrestore = ezusb_unlock_irqrestore,
-	.lock_irq = ezusb_lock_irq,
-	.unlock_irq = ezusb_unlock_irq,
-};
-
-static const struct net_device_ops ezusb_netdev_ops = {
-	.ndo_open		= orinoco_open,
-	.ndo_stop		= orinoco_stop,
-	.ndo_start_xmit		= ezusb_xmit,
-	.ndo_set_rx_mode	= orinoco_set_multicast_list,
-	.ndo_change_mtu		= orinoco_change_mtu,
-	.ndo_set_mac_address	= eth_mac_addr,
-	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_tx_timeout		= orinoco_tx_timeout,
-};
-
-static int ezusb_probe(struct usb_interface *interface,
-		       const struct usb_device_id *id)
-{
-	struct usb_device *udev = interface_to_usbdev(interface);
-	struct orinoco_private *priv;
-	struct hermes *hw;
-	struct ezusb_priv *upriv = NULL;
-	struct usb_interface_descriptor *iface_desc;
-	struct usb_endpoint_descriptor *ep;
-	const struct firmware *fw_entry = NULL;
-	int retval = 0;
-	int i;
-
-	priv = alloc_orinocodev(sizeof(*upriv), &udev->dev,
-				ezusb_hard_reset, NULL);
-	if (!priv) {
-		err("Couldn't allocate orinocodev");
-		retval = -ENOMEM;
-		goto exit;
-	}
-
-	hw = &priv->hw;
-
-	upriv = priv->card;
-
-	mutex_init(&upriv->mtx);
-	spin_lock_init(&upriv->reply_count_lock);
-
-	spin_lock_init(&upriv->req_lock);
-	INIT_LIST_HEAD(&upriv->req_pending);
-	INIT_LIST_HEAD(&upriv->req_active);
-
-	upriv->udev = udev;
-
-	hw->iobase = (void __force __iomem *) &upriv->hermes_reg_fake;
-	hw->reg_spacing = HERMES_16BIT_REGSPACING;
-	hw->priv = upriv;
-	hw->ops = &ezusb_ops;
-
-	/* set up the endpoint information */
-	/* check out the endpoints */
-
-	iface_desc = &interface->cur_altsetting->desc;
-	for (i = 0; i < iface_desc->bNumEndpoints; ++i) {
-		ep = &interface->cur_altsetting->endpoint[i].desc;
-
-		if (usb_endpoint_is_bulk_in(ep)) {
-			/* we found a bulk in endpoint */
-			if (upriv->read_urb != NULL) {
-				pr_warn("Found a second bulk in ep, ignored\n");
-				continue;
-			}
-
-			upriv->read_urb = usb_alloc_urb(0, GFP_KERNEL);
-			if (!upriv->read_urb)
-				goto error;
-			if (le16_to_cpu(ep->wMaxPacketSize) != 64)
-				pr_warn("bulk in: wMaxPacketSize!= 64\n");
-			if (ep->bEndpointAddress != (2 | USB_DIR_IN))
-				pr_warn("bulk in: bEndpointAddress: %d\n",
-					ep->bEndpointAddress);
-			upriv->read_pipe = usb_rcvbulkpipe(udev,
-							 ep->
-							 bEndpointAddress);
-			upriv->read_urb->transfer_buffer =
-			    kmalloc(BULK_BUF_SIZE, GFP_KERNEL);
-			if (!upriv->read_urb->transfer_buffer) {
-				err("Couldn't allocate IN buffer");
-				goto error;
-			}
-		}
-
-		if (usb_endpoint_is_bulk_out(ep)) {
-			/* we found a bulk out endpoint */
-			if (upriv->bap_buf != NULL) {
-				pr_warn("Found a second bulk out ep, ignored\n");
-				continue;
-			}
-
-			if (le16_to_cpu(ep->wMaxPacketSize) != 64)
-				pr_warn("bulk out: wMaxPacketSize != 64\n");
-			if (ep->bEndpointAddress != 2)
-				pr_warn("bulk out: bEndpointAddress: %d\n",
-					ep->bEndpointAddress);
-			upriv->write_pipe = usb_sndbulkpipe(udev,
-							  ep->
-							  bEndpointAddress);
-			upriv->bap_buf = kmalloc(BULK_BUF_SIZE, GFP_KERNEL);
-			if (!upriv->bap_buf) {
-				err("Couldn't allocate bulk_out_buffer");
-				goto error;
-			}
-		}
-	}
-	if (!upriv->bap_buf || !upriv->read_urb) {
-		err("Didn't find the required bulk endpoints");
-		goto error;
-	}
-
-	if (request_firmware(&fw_entry, "orinoco_ezusb_fw",
-			     &interface->dev) == 0) {
-		firmware.size = fw_entry->size;
-		firmware.code = fw_entry->data;
-	}
-	if (firmware.size && firmware.code) {
-		if (ezusb_firmware_download(upriv, &firmware) < 0)
-			goto error;
-	} else {
-		err("No firmware to download");
-		goto error;
-	}
-
-	if (ezusb_hard_reset(priv) < 0) {
-		err("Cannot reset the device");
-		goto error;
-	}
-
-	/* If the firmware is already downloaded orinoco.c will call
-	 * ezusb_init but if the firmware is not already there, that will make
-	 * the kernel very unstable, so we try initializing here and quit in
-	 * case of error */
-	if (ezusb_init(hw) < 0) {
-		err("Couldn't initialize the device");
-		err("Firmware may not be downloaded or may be wrong.");
-		goto error;
-	}
-
-	/* Initialise the main driver */
-	if (orinoco_init(priv) != 0) {
-		err("orinoco_init() failed\n");
-		goto error;
-	}
-
-	if (orinoco_if_add(priv, 0, 0, &ezusb_netdev_ops) != 0) {
-		upriv->dev = NULL;
-		err("%s: orinoco_if_add() failed", __func__);
-		wiphy_unregister(priv_to_wiphy(priv));
-		goto error;
-	}
-	upriv->dev = priv->ndev;
-
-	goto exit;
-
- error:
-	ezusb_delete(upriv);
-	if (upriv->dev) {
-		/* upriv->dev was 0, so ezusb_delete() didn't free it */
-		free_orinocodev(priv);
-	}
-	upriv = NULL;
-	retval = -EFAULT;
- exit:
-	if (fw_entry) {
-		firmware.code = NULL;
-		firmware.size = 0;
-		release_firmware(fw_entry);
-	}
-	usb_set_intfdata(interface, upriv);
-	return retval;
-}
-
-
-static void ezusb_disconnect(struct usb_interface *intf)
-{
-	struct ezusb_priv *upriv = usb_get_intfdata(intf);
-	usb_set_intfdata(intf, NULL);
-	ezusb_delete(upriv);
-	printk(KERN_INFO PFX "Disconnected\n");
-}
-
-
-/* usb specific object needed to register this driver with the usb subsystem */
-static struct usb_driver orinoco_driver = {
-	.name = DRIVER_NAME,
-	.probe = ezusb_probe,
-	.disconnect = ezusb_disconnect,
-	.id_table = ezusb_table,
-	.disable_hub_initiated_lpm = 1,
-};
-
-module_usb_driver(orinoco_driver);
-
-MODULE_AUTHOR("Manuel Estrada Sainz");
-MODULE_DESCRIPTION("Driver for Orinoco wireless LAN cards using EZUSB bridge");
-MODULE_LICENSE("Dual MPL/GPL");
diff --git a/drivers/net/wireless/intersil/orinoco/scan.c b/drivers/net/wireless/intersil/orinoco/scan.c
deleted file mode 100644
index 6d1d084854fb..000000000000
--- a/drivers/net/wireless/intersil/orinoco/scan.c
+++ /dev/null
@@ -1,259 +0,0 @@
-/* Helpers for managing scan queues
- *
- * See copyright notice in main.c
- */
-
-#include <linux/gfp.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/ieee80211.h>
-#include <net/cfg80211.h>
-
-#include "hermes.h"
-#include "orinoco.h"
-#include "main.h"
-
-#include "scan.h"
-
-#define ZERO_DBM_OFFSET 0x95
-#define MAX_SIGNAL_LEVEL 0x8A
-#define MIN_SIGNAL_LEVEL 0x2F
-
-#define SIGNAL_TO_DBM(x)					\
-	(clamp_t(s32, (x), MIN_SIGNAL_LEVEL, MAX_SIGNAL_LEVEL)	\
-	 - ZERO_DBM_OFFSET)
-#define SIGNAL_TO_MBM(x) (SIGNAL_TO_DBM(x) * 100)
-
-static int symbol_build_supp_rates(u8 *buf, const __le16 *rates)
-{
-	int i;
-	u8 rate;
-
-	buf[0] = WLAN_EID_SUPP_RATES;
-	for (i = 0; i < 5; i++) {
-		rate = le16_to_cpu(rates[i]);
-		/* NULL terminated */
-		if (rate == 0x0)
-			break;
-		buf[i + 2] = rate;
-	}
-	buf[1] = i;
-
-	return i + 2;
-}
-
-static int prism_build_supp_rates(u8 *buf, const u8 *rates)
-{
-	int i;
-
-	buf[0] = WLAN_EID_SUPP_RATES;
-	for (i = 0; i < 8; i++) {
-		/* NULL terminated */
-		if (rates[i] == 0x0)
-			break;
-		buf[i + 2] = rates[i];
-	}
-	buf[1] = i;
-
-	/* We might still have another 2 rates, which need to go in
-	 * extended supported rates */
-	if (i == 8 && rates[i] > 0) {
-		buf[10] = WLAN_EID_EXT_SUPP_RATES;
-		for (; i < 10; i++) {
-			/* NULL terminated */
-			if (rates[i] == 0x0)
-				break;
-			buf[i + 2] = rates[i];
-		}
-		buf[11] = i - 8;
-	}
-
-	return (i < 8) ? i + 2 : i + 4;
-}
-
-static void orinoco_add_hostscan_result(struct orinoco_private *priv,
-					const union hermes_scan_info *bss)
-{
-	struct wiphy *wiphy = priv_to_wiphy(priv);
-	struct ieee80211_channel *channel;
-	struct cfg80211_bss *cbss;
-	u8 *ie;
-	u8 ie_buf[46];
-	u64 timestamp;
-	s32 signal;
-	u16 capability;
-	u16 beacon_interval;
-	int ie_len;
-	int freq;
-	int len;
-
-	len = le16_to_cpu(bss->a.essid_len);
-
-	/* Reconstruct SSID and bitrate IEs to pass up */
-	ie_buf[0] = WLAN_EID_SSID;
-	ie_buf[1] = len;
-	memcpy(&ie_buf[2], bss->a.essid, len);
-
-	ie = ie_buf + len + 2;
-	ie_len = ie_buf[1] + 2;
-	switch (priv->firmware_type) {
-	case FIRMWARE_TYPE_SYMBOL:
-		ie_len += symbol_build_supp_rates(ie, bss->s.rates);
-		break;
-
-	case FIRMWARE_TYPE_INTERSIL:
-		ie_len += prism_build_supp_rates(ie, bss->p.rates);
-		break;
-
-	case FIRMWARE_TYPE_AGERE:
-	default:
-		break;
-	}
-
-	freq = ieee80211_channel_to_frequency(
-		le16_to_cpu(bss->a.channel), NL80211_BAND_2GHZ);
-	channel = ieee80211_get_channel(wiphy, freq);
-	if (!channel) {
-		printk(KERN_DEBUG "Invalid channel designation %04X(%04X)",
-			bss->a.channel, freq);
-		return;	/* Then ignore it for now */
-	}
-	timestamp = 0;
-	capability = le16_to_cpu(bss->a.capabilities);
-	beacon_interval = le16_to_cpu(bss->a.beacon_interv);
-	signal = SIGNAL_TO_MBM(le16_to_cpu(bss->a.level));
-
-	cbss = cfg80211_inform_bss(wiphy, channel, CFG80211_BSS_FTYPE_UNKNOWN,
-				   bss->a.bssid, timestamp, capability,
-				   beacon_interval, ie_buf, ie_len, signal,
-				   GFP_KERNEL);
-	cfg80211_put_bss(wiphy, cbss);
-}
-
-void orinoco_add_extscan_result(struct orinoco_private *priv,
-				struct agere_ext_scan_info *bss,
-				size_t len)
-{
-	struct wiphy *wiphy = priv_to_wiphy(priv);
-	struct ieee80211_channel *channel;
-	struct cfg80211_bss *cbss;
-	const u8 *ie;
-	u64 timestamp;
-	s32 signal;
-	u16 capability;
-	u16 beacon_interval;
-	size_t ie_len;
-	int chan, freq;
-
-	ie_len = len - sizeof(*bss);
-	ie = cfg80211_find_ie(WLAN_EID_DS_PARAMS, bss->data, ie_len);
-	chan = ie ? ie[2] : 0;
-	freq = ieee80211_channel_to_frequency(chan, NL80211_BAND_2GHZ);
-	channel = ieee80211_get_channel(wiphy, freq);
-
-	timestamp = le64_to_cpu(bss->timestamp);
-	capability = le16_to_cpu(bss->capabilities);
-	beacon_interval = le16_to_cpu(bss->beacon_interval);
-	ie = bss->data;
-	signal = SIGNAL_TO_MBM(bss->level);
-
-	cbss = cfg80211_inform_bss(wiphy, channel, CFG80211_BSS_FTYPE_UNKNOWN,
-				   bss->bssid, timestamp, capability,
-				   beacon_interval, ie, ie_len, signal,
-				   GFP_KERNEL);
-	cfg80211_put_bss(wiphy, cbss);
-}
-
-void orinoco_add_hostscan_results(struct orinoco_private *priv,
-				  unsigned char *buf,
-				  size_t len)
-{
-	int offset;		/* In the scan data */
-	size_t atom_len;
-	bool abort = false;
-
-	switch (priv->firmware_type) {
-	case FIRMWARE_TYPE_AGERE:
-		atom_len = sizeof(struct agere_scan_apinfo);
-		offset = 0;
-		break;
-
-	case FIRMWARE_TYPE_SYMBOL:
-		/* Lack of documentation necessitates this hack.
-		 * Different firmwares have 68 or 76 byte long atoms.
-		 * We try modulo first.  If the length divides by both,
-		 * we check what would be the channel in the second
-		 * frame for a 68-byte atom.  76-byte atoms have 0 there.
-		 * Valid channel cannot be 0.  */
-		if (len % 76)
-			atom_len = 68;
-		else if (len % 68)
-			atom_len = 76;
-		else if (len >= 1292 && buf[68] == 0)
-			atom_len = 76;
-		else
-			atom_len = 68;
-		offset = 0;
-		break;
-
-	case FIRMWARE_TYPE_INTERSIL:
-		offset = 4;
-		if (priv->has_hostscan) {
-			atom_len = le16_to_cpup((__le16 *)buf);
-			/* Sanity check for atom_len */
-			if (atom_len < sizeof(struct prism2_scan_apinfo)) {
-				printk(KERN_ERR "%s: Invalid atom_len in scan "
-				       "data: %zu\n", priv->ndev->name,
-				       atom_len);
-				abort = true;
-				goto scan_abort;
-			}
-		} else
-			atom_len = offsetof(struct prism2_scan_apinfo, atim);
-		break;
-
-	default:
-		abort = true;
-		goto scan_abort;
-	}
-
-	/* Check that we got an whole number of atoms */
-	if ((len - offset) % atom_len) {
-		printk(KERN_ERR "%s: Unexpected scan data length %zu, "
-		       "atom_len %zu, offset %d\n", priv->ndev->name, len,
-		       atom_len, offset);
-		abort = true;
-		goto scan_abort;
-	}
-
-	/* Process the entries one by one */
-	for (; offset + atom_len <= len; offset += atom_len) {
-		union hermes_scan_info *atom;
-
-		atom = (union hermes_scan_info *) (buf + offset);
-
-		orinoco_add_hostscan_result(priv, atom);
-	}
-
- scan_abort:
-	if (priv->scan_request) {
-		struct cfg80211_scan_info info = {
-			.aborted = abort,
-		};
-
-		cfg80211_scan_done(priv->scan_request, &info);
-		priv->scan_request = NULL;
-	}
-}
-
-void orinoco_scan_done(struct orinoco_private *priv, bool abort)
-{
-	if (priv->scan_request) {
-		struct cfg80211_scan_info info = {
-			.aborted = abort,
-		};
-
-		cfg80211_scan_done(priv->scan_request, &info);
-		priv->scan_request = NULL;
-	}
-}
diff --git a/drivers/net/wireless/intersil/orinoco/scan.h b/drivers/net/wireless/intersil/orinoco/scan.h
deleted file mode 100644
index 27281fb0a6dc..000000000000
--- a/drivers/net/wireless/intersil/orinoco/scan.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* Helpers for managing scan queues
- *
- * See copyright notice in main.c
- */
-#ifndef _ORINOCO_SCAN_H_
-#define _ORINOCO_SCAN_H_
-
-/* Forward declarations */
-struct orinoco_private;
-struct agere_ext_scan_info;
-
-/* Add scan results */
-void orinoco_add_extscan_result(struct orinoco_private *priv,
-				struct agere_ext_scan_info *atom,
-				size_t len);
-void orinoco_add_hostscan_results(struct orinoco_private *dev,
-				  unsigned char *buf,
-				  size_t len);
-void orinoco_scan_done(struct orinoco_private *priv, bool abort);
-
-#endif /* _ORINOCO_SCAN_H_ */
diff --git a/drivers/net/wireless/intersil/orinoco/spectrum_cs.c b/drivers/net/wireless/intersil/orinoco/spectrum_cs.c
deleted file mode 100644
index 841d623c621a..000000000000
--- a/drivers/net/wireless/intersil/orinoco/spectrum_cs.c
+++ /dev/null
@@ -1,328 +0,0 @@
-/*
- * Driver for 802.11b cards using RAM-loadable Symbol firmware, such as
- * Symbol Wireless Networker LA4137, CompactFlash cards by Socket
- * Communications and Intel PRO/Wireless 2011B.
- *
- * The driver implements Symbol firmware download.  The rest is handled
- * in hermes.c and main.c.
- *
- * Utilities for downloading the Symbol firmware are available at
- * http://sourceforge.net/projects/orinoco/
- *
- * Copyright (C) 2002-2005 Pavel Roskin <proski@gnu.org>
- * Portions based on orinoco_cs.c:
- *	Copyright (C) David Gibson, Linuxcare Australia
- * Portions based on Spectrum24tDnld.c from original spectrum24 driver:
- *	Copyright (C) Symbol Technologies.
- *
- * See copyright notice in file main.c.
- */
-
-#define DRIVER_NAME "spectrum_cs"
-#define PFX DRIVER_NAME ": "
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/delay.h>
-#include <pcmcia/cistpl.h>
-#include <pcmcia/cisreg.h>
-#include <pcmcia/ds.h>
-
-#include "orinoco.h"
-
-/********************************************************************/
-/* Module stuff							    */
-/********************************************************************/
-
-MODULE_AUTHOR("Pavel Roskin <proski@gnu.org>");
-MODULE_DESCRIPTION("Driver for Symbol Spectrum24 Trilogy cards with firmware downloader");
-MODULE_LICENSE("Dual MPL/GPL");
-
-/* Module parameters */
-
-/* Some D-Link cards have buggy CIS. They do work at 5v properly, but
- * don't have any CIS entry for it. This workaround it... */
-static int ignore_cis_vcc; /* = 0 */
-module_param(ignore_cis_vcc, int, 0);
-MODULE_PARM_DESC(ignore_cis_vcc, "Allow voltage mismatch between card and socket");
-
-/********************************************************************/
-/* Data structures						    */
-/********************************************************************/
-
-/* PCMCIA specific device information (goes in the card field of
- * struct orinoco_private */
-struct orinoco_pccard {
-	struct pcmcia_device	*p_dev;
-};
-
-/********************************************************************/
-/* Function prototypes						    */
-/********************************************************************/
-
-static int spectrum_cs_config(struct pcmcia_device *link);
-static void spectrum_cs_release(struct pcmcia_device *link);
-
-/* Constants for the CISREG_CCSR register */
-#define HCR_RUN		0x07	/* run firmware after reset */
-#define HCR_IDLE	0x0E	/* don't run firmware after reset */
-#define HCR_MEM16	0x10	/* memory width bit, should be preserved */
-
-
-/*
- * Reset the card using configuration registers COR and CCSR.
- * If IDLE is 1, stop the firmware, so that it can be safely rewritten.
- */
-static int
-spectrum_reset(struct pcmcia_device *link, int idle)
-{
-	int ret;
-	u8 save_cor;
-	u8 ccsr;
-
-	/* Doing it if hardware is gone is guaranteed crash */
-	if (!pcmcia_dev_present(link))
-		return -ENODEV;
-
-	/* Save original COR value */
-	ret = pcmcia_read_config_byte(link, CISREG_COR, &save_cor);
-	if (ret)
-		goto failed;
-
-	/* Soft-Reset card */
-	ret = pcmcia_write_config_byte(link, CISREG_COR,
-				(save_cor | COR_SOFT_RESET));
-	if (ret)
-		goto failed;
-	udelay(1000);
-
-	/* Read CCSR */
-	ret = pcmcia_read_config_byte(link, CISREG_CCSR, &ccsr);
-	if (ret)
-		goto failed;
-
-	/*
-	 * Start or stop the firmware.  Memory width bit should be
-	 * preserved from the value we've just read.
-	 */
-	ccsr = (idle ? HCR_IDLE : HCR_RUN) | (ccsr & HCR_MEM16);
-	ret = pcmcia_write_config_byte(link, CISREG_CCSR, ccsr);
-	if (ret)
-		goto failed;
-	udelay(1000);
-
-	/* Restore original COR configuration index */
-	ret = pcmcia_write_config_byte(link, CISREG_COR,
-				(save_cor & ~COR_SOFT_RESET));
-	if (ret)
-		goto failed;
-	udelay(1000);
-	return 0;
-
-failed:
-	return -ENODEV;
-}
-
-/********************************************************************/
-/* Device methods						    */
-/********************************************************************/
-
-static int
-spectrum_cs_hard_reset(struct orinoco_private *priv)
-{
-	struct orinoco_pccard *card = priv->card;
-	struct pcmcia_device *link = card->p_dev;
-
-	/* Soft reset using COR and HCR */
-	spectrum_reset(link, 0);
-
-	return 0;
-}
-
-static int
-spectrum_cs_stop_firmware(struct orinoco_private *priv, int idle)
-{
-	struct orinoco_pccard *card = priv->card;
-	struct pcmcia_device *link = card->p_dev;
-
-	return spectrum_reset(link, idle);
-}
-
-/********************************************************************/
-/* PCMCIA stuff							    */
-/********************************************************************/
-
-static int
-spectrum_cs_probe(struct pcmcia_device *link)
-{
-	struct orinoco_private *priv;
-	struct orinoco_pccard *card;
-	int ret;
-
-	priv = alloc_orinocodev(sizeof(*card), &link->dev,
-				spectrum_cs_hard_reset,
-				spectrum_cs_stop_firmware);
-	if (!priv)
-		return -ENOMEM;
-	card = priv->card;
-
-	/* Link both structures together */
-	card->p_dev = link;
-	link->priv = priv;
-
-	ret = spectrum_cs_config(link);
-	if (ret)
-		goto err_free_orinocodev;
-
-	return 0;
-
-err_free_orinocodev:
-	free_orinocodev(priv);
-	return ret;
-}
-
-static void spectrum_cs_detach(struct pcmcia_device *link)
-{
-	struct orinoco_private *priv = link->priv;
-
-	orinoco_if_del(priv);
-
-	spectrum_cs_release(link);
-
-	free_orinocodev(priv);
-}				/* spectrum_cs_detach */
-
-static int spectrum_cs_config_check(struct pcmcia_device *p_dev,
-				    void *priv_data)
-{
-	if (p_dev->config_index == 0)
-		return -EINVAL;
-
-	return pcmcia_request_io(p_dev);
-};
-
-static int
-spectrum_cs_config(struct pcmcia_device *link)
-{
-	struct orinoco_private *priv = link->priv;
-	struct hermes *hw = &priv->hw;
-	int ret;
-	void __iomem *mem;
-
-	link->config_flags |= CONF_AUTO_SET_VPP | CONF_AUTO_CHECK_VCC |
-		CONF_AUTO_SET_IO | CONF_ENABLE_IRQ;
-	if (ignore_cis_vcc)
-		link->config_flags &= ~CONF_AUTO_CHECK_VCC;
-	ret = pcmcia_loop_config(link, spectrum_cs_config_check, NULL);
-	if (ret) {
-		if (!ignore_cis_vcc)
-			printk(KERN_ERR PFX "GetNextTuple(): No matching "
-			       "CIS configuration.  Maybe you need the "
-			       "ignore_cis_vcc=1 parameter.\n");
-		goto failed;
-	}
-
-	mem = ioport_map(link->resource[0]->start,
-			resource_size(link->resource[0]));
-	if (!mem)
-		goto failed;
-
-	/* We initialize the hermes structure before completing PCMCIA
-	 * configuration just in case the interrupt handler gets
-	 * called. */
-	hermes_struct_init(hw, mem, HERMES_16BIT_REGSPACING);
-	hw->eeprom_pda = true;
-
-	ret = pcmcia_request_irq(link, orinoco_interrupt);
-	if (ret)
-		goto failed;
-
-	ret = pcmcia_enable_device(link);
-	if (ret)
-		goto failed;
-
-	/* Reset card */
-	if (spectrum_cs_hard_reset(priv) != 0)
-		goto failed;
-
-	/* Initialise the main driver */
-	if (orinoco_init(priv) != 0) {
-		printk(KERN_ERR PFX "orinoco_init() failed\n");
-		goto failed;
-	}
-
-	/* Register an interface with the stack */
-	if (orinoco_if_add(priv, link->resource[0]->start,
-			   link->irq, NULL) != 0) {
-		printk(KERN_ERR PFX "orinoco_if_add() failed\n");
-		goto failed;
-	}
-
-	return 0;
-
- failed:
-	spectrum_cs_release(link);
-	return -ENODEV;
-}				/* spectrum_cs_config */
-
-static void
-spectrum_cs_release(struct pcmcia_device *link)
-{
-	struct orinoco_private *priv = link->priv;
-	unsigned long flags;
-
-	/* We're committed to taking the device away now, so mark the
-	 * hardware as unavailable */
-	priv->hw.ops->lock_irqsave(&priv->lock, &flags);
-	priv->hw_unavailable++;
-	priv->hw.ops->unlock_irqrestore(&priv->lock, &flags);
-
-	pcmcia_disable_device(link);
-	if (priv->hw.iobase)
-		ioport_unmap(priv->hw.iobase);
-}				/* spectrum_cs_release */
-
-
-static int
-spectrum_cs_suspend(struct pcmcia_device *link)
-{
-	struct orinoco_private *priv = link->priv;
-
-	/* Mark the device as stopped, to block IO until later */
-	orinoco_down(priv);
-
-	return 0;
-}
-
-static int
-spectrum_cs_resume(struct pcmcia_device *link)
-{
-	struct orinoco_private *priv = link->priv;
-	int err = orinoco_up(priv);
-
-	return err;
-}
-
-
-/********************************************************************/
-/* Module initialization					    */
-/********************************************************************/
-
-static const struct pcmcia_device_id spectrum_cs_ids[] = {
-	PCMCIA_DEVICE_MANF_CARD(0x026c, 0x0001), /* Symbol Spectrum24 LA4137 */
-	PCMCIA_DEVICE_MANF_CARD(0x0104, 0x0001), /* Socket Communications CF */
-	PCMCIA_DEVICE_PROD_ID12("Intel", "PRO/Wireless LAN PC Card", 0x816cc815, 0x6fbf459a), /* 2011B, not 2011 */
-	PCMCIA_DEVICE_NULL,
-};
-MODULE_DEVICE_TABLE(pcmcia, spectrum_cs_ids);
-
-static struct pcmcia_driver orinoco_driver = {
-	.owner		= THIS_MODULE,
-	.name		= DRIVER_NAME,
-	.probe		= spectrum_cs_probe,
-	.remove		= spectrum_cs_detach,
-	.suspend	= spectrum_cs_suspend,
-	.resume		= spectrum_cs_resume,
-	.id_table       = spectrum_cs_ids,
-};
-module_pcmcia_driver(orinoco_driver);
diff --git a/drivers/net/wireless/intersil/orinoco/wext.c b/drivers/net/wireless/intersil/orinoco/wext.c
deleted file mode 100644
index dea1ff044342..000000000000
--- a/drivers/net/wireless/intersil/orinoco/wext.c
+++ /dev/null
@@ -1,1428 +0,0 @@
-/* Wireless extensions support.
- *
- * See copyright notice in main.c
- */
-#include <linux/slab.h>
-#include <linux/kernel.h>
-#include <linux/if_arp.h>
-#include <linux/wireless.h>
-#include <linux/ieee80211.h>
-#include <linux/etherdevice.h>
-#include <net/iw_handler.h>
-#include <net/cfg80211.h>
-#include <net/cfg80211-wext.h>
-
-#include "hermes.h"
-#include "hermes_rid.h"
-#include "orinoco.h"
-
-#include "hw.h"
-#include "mic.h"
-#include "scan.h"
-#include "main.h"
-
-#include "wext.h"
-
-#define MAX_RID_LEN 1024
-
-/* Helper routine to record keys
- * It is called under orinoco_lock so it may not sleep */
-static int orinoco_set_key(struct orinoco_private *priv, int index,
-			   enum orinoco_alg alg, const u8 *key, int key_len,
-			   const u8 *seq, int seq_len)
-{
-	kfree_sensitive(priv->keys[index].key);
-	kfree_sensitive(priv->keys[index].seq);
-
-	if (key_len) {
-		priv->keys[index].key = kzalloc(key_len, GFP_ATOMIC);
-		if (!priv->keys[index].key)
-			goto nomem;
-	} else
-		priv->keys[index].key = NULL;
-
-	if (seq_len) {
-		priv->keys[index].seq = kzalloc(seq_len, GFP_ATOMIC);
-		if (!priv->keys[index].seq)
-			goto free_key;
-	} else
-		priv->keys[index].seq = NULL;
-
-	priv->keys[index].key_len = key_len;
-	priv->keys[index].seq_len = seq_len;
-
-	if (key_len)
-		memcpy((void *)priv->keys[index].key, key, key_len);
-	if (seq_len)
-		memcpy((void *)priv->keys[index].seq, seq, seq_len);
-
-	switch (alg) {
-	case ORINOCO_ALG_TKIP:
-		priv->keys[index].cipher = WLAN_CIPHER_SUITE_TKIP;
-		break;
-
-	case ORINOCO_ALG_WEP:
-		priv->keys[index].cipher = (key_len > SMALL_KEY_SIZE) ?
-			WLAN_CIPHER_SUITE_WEP104 : WLAN_CIPHER_SUITE_WEP40;
-		break;
-
-	case ORINOCO_ALG_NONE:
-	default:
-		priv->keys[index].cipher = 0;
-		break;
-	}
-
-	return 0;
-
-free_key:
-	kfree(priv->keys[index].key);
-	priv->keys[index].key = NULL;
-
-nomem:
-	priv->keys[index].key_len = 0;
-	priv->keys[index].seq_len = 0;
-	priv->keys[index].cipher = 0;
-
-	return -ENOMEM;
-}
-
-static struct iw_statistics *orinoco_get_wireless_stats(struct net_device *dev)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	struct hermes *hw = &priv->hw;
-	struct iw_statistics *wstats = &priv->wstats;
-	int err;
-	unsigned long flags;
-
-	if (!netif_device_present(dev)) {
-		printk(KERN_WARNING "%s: get_wireless_stats() called while device not present\n",
-		       dev->name);
-		return NULL; /* FIXME: Can we do better than this? */
-	}
-
-	/* If busy, return the old stats.  Returning NULL may cause
-	 * the interface to disappear from /proc/net/wireless */
-	if (orinoco_lock(priv, &flags) != 0)
-		return wstats;
-
-	/* We can't really wait for the tallies inquiry command to
-	 * complete, so we just use the previous results and trigger
-	 * a new tallies inquiry command for next time - Jean II */
-	/* FIXME: Really we should wait for the inquiry to come back -
-	 * as it is the stats we give don't make a whole lot of sense.
-	 * Unfortunately, it's not clear how to do that within the
-	 * wireless extensions framework: I think we're in user
-	 * context, but a lock seems to be held by the time we get in
-	 * here so we're not safe to sleep here. */
-	hermes_inquire(hw, HERMES_INQ_TALLIES);
-
-	if (priv->iw_mode == NL80211_IFTYPE_ADHOC) {
-		memset(&wstats->qual, 0, sizeof(wstats->qual));
-		/* If a spy address is defined, we report stats of the
-		 * first spy address - Jean II */
-		if (SPY_NUMBER(priv)) {
-			wstats->qual.qual = priv->spy_data.spy_stat[0].qual;
-			wstats->qual.level = priv->spy_data.spy_stat[0].level;
-			wstats->qual.noise = priv->spy_data.spy_stat[0].noise;
-			wstats->qual.updated =
-				priv->spy_data.spy_stat[0].updated;
-		}
-	} else {
-		struct {
-			__le16 qual, signal, noise, unused;
-		} __packed cq;
-
-		err = HERMES_READ_RECORD(hw, USER_BAP,
-					 HERMES_RID_COMMSQUALITY, &cq);
-
-		if (!err) {
-			wstats->qual.qual = (int)le16_to_cpu(cq.qual);
-			wstats->qual.level = (int)le16_to_cpu(cq.signal) - 0x95;
-			wstats->qual.noise = (int)le16_to_cpu(cq.noise) - 0x95;
-			wstats->qual.updated =
-				IW_QUAL_ALL_UPDATED | IW_QUAL_DBM;
-		}
-	}
-
-	orinoco_unlock(priv, &flags);
-	return wstats;
-}
-
-/********************************************************************/
-/* Wireless extensions                                              */
-/********************************************************************/
-
-static int orinoco_ioctl_setwap(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu,
-				char *extra)
-{
-	struct sockaddr *ap_addr = &wrqu->ap_addr;
-	struct orinoco_private *priv = ndev_priv(dev);
-	int err = -EINPROGRESS;		/* Call commit handler */
-	unsigned long flags;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	/* Enable automatic roaming - no sanity checks are needed */
-	if (is_zero_ether_addr(ap_addr->sa_data) ||
-	    is_broadcast_ether_addr(ap_addr->sa_data)) {
-		priv->bssid_fixed = 0;
-		eth_zero_addr(priv->desired_bssid);
-
-		/* "off" means keep existing connection */
-		if (ap_addr->sa_data[0] == 0) {
-			__orinoco_hw_set_wap(priv);
-			err = 0;
-		}
-		goto out;
-	}
-
-	if (priv->firmware_type == FIRMWARE_TYPE_AGERE) {
-		printk(KERN_WARNING "%s: Lucent/Agere firmware doesn't "
-		       "support manual roaming\n",
-		       dev->name);
-		err = -EOPNOTSUPP;
-		goto out;
-	}
-
-	if (priv->iw_mode != NL80211_IFTYPE_STATION) {
-		printk(KERN_WARNING "%s: Manual roaming supported only in "
-		       "managed mode\n", dev->name);
-		err = -EOPNOTSUPP;
-		goto out;
-	}
-
-	/* Intersil firmware hangs without Desired ESSID */
-	if (priv->firmware_type == FIRMWARE_TYPE_INTERSIL &&
-	    strlen(priv->desired_essid) == 0) {
-		printk(KERN_WARNING "%s: Desired ESSID must be set for "
-		       "manual roaming\n", dev->name);
-		err = -EOPNOTSUPP;
-		goto out;
-	}
-
-	/* Finally, enable manual roaming */
-	priv->bssid_fixed = 1;
-	memcpy(priv->desired_bssid, &ap_addr->sa_data, ETH_ALEN);
-
- out:
-	orinoco_unlock(priv, &flags);
-	return err;
-}
-
-static int orinoco_ioctl_getwap(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu,
-				char *extra)
-{
-	struct sockaddr *ap_addr = &wrqu->ap_addr;
-	struct orinoco_private *priv = ndev_priv(dev);
-
-	int err = 0;
-	unsigned long flags;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	ap_addr->sa_family = ARPHRD_ETHER;
-	err = orinoco_hw_get_current_bssid(priv, ap_addr->sa_data);
-
-	orinoco_unlock(priv, &flags);
-
-	return err;
-}
-
-static int orinoco_ioctl_setiwencode(struct net_device *dev,
-				     struct iw_request_info *info,
-				     union iwreq_data *wrqu,
-				     char *keybuf)
-{
-	struct iw_point *erq = &wrqu->encoding;
-	struct orinoco_private *priv = ndev_priv(dev);
-	int index = (erq->flags & IW_ENCODE_INDEX) - 1;
-	int setindex = priv->tx_key;
-	enum orinoco_alg encode_alg = priv->encode_alg;
-	int restricted = priv->wep_restrict;
-	int err = -EINPROGRESS;		/* Call commit handler */
-	unsigned long flags;
-
-	if (!priv->has_wep)
-		return -EOPNOTSUPP;
-
-	if (erq->pointer) {
-		/* We actually have a key to set - check its length */
-		if (erq->length > LARGE_KEY_SIZE)
-			return -E2BIG;
-
-		if ((erq->length > SMALL_KEY_SIZE) && !priv->has_big_wep)
-			return -E2BIG;
-	}
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	/* Clear any TKIP key we have */
-	if ((priv->has_wpa) && (priv->encode_alg == ORINOCO_ALG_TKIP))
-		(void) orinoco_clear_tkip_key(priv, setindex);
-
-	if (erq->length > 0) {
-		if ((index < 0) || (index >= ORINOCO_MAX_KEYS))
-			index = priv->tx_key;
-
-		/* Switch on WEP if off */
-		if (encode_alg != ORINOCO_ALG_WEP) {
-			setindex = index;
-			encode_alg = ORINOCO_ALG_WEP;
-		}
-	} else {
-		/* Important note : if the user do "iwconfig eth0 enc off",
-		 * we will arrive there with an index of -1. This is valid
-		 * but need to be taken care off... Jean II */
-		if ((index < 0) || (index >= ORINOCO_MAX_KEYS)) {
-			if ((index != -1) || (erq->flags == 0)) {
-				err = -EINVAL;
-				goto out;
-			}
-		} else {
-			/* Set the index : Check that the key is valid */
-			if (priv->keys[index].key_len == 0) {
-				err = -EINVAL;
-				goto out;
-			}
-			setindex = index;
-		}
-	}
-
-	if (erq->flags & IW_ENCODE_DISABLED)
-		encode_alg = ORINOCO_ALG_NONE;
-	if (erq->flags & IW_ENCODE_OPEN)
-		restricted = 0;
-	if (erq->flags & IW_ENCODE_RESTRICTED)
-		restricted = 1;
-
-	if (erq->pointer && erq->length > 0) {
-		err = orinoco_set_key(priv, index, ORINOCO_ALG_WEP, keybuf,
-				      erq->length, NULL, 0);
-	}
-	priv->tx_key = setindex;
-
-	/* Try fast key change if connected and only keys are changed */
-	if ((priv->encode_alg == encode_alg) &&
-	    (priv->wep_restrict == restricted) &&
-	    netif_carrier_ok(dev)) {
-		err = __orinoco_hw_setup_wepkeys(priv);
-		/* No need to commit if successful */
-		goto out;
-	}
-
-	priv->encode_alg = encode_alg;
-	priv->wep_restrict = restricted;
-
- out:
-	orinoco_unlock(priv, &flags);
-
-	return err;
-}
-
-static int orinoco_ioctl_getiwencode(struct net_device *dev,
-				     struct iw_request_info *info,
-				     union iwreq_data *wrqu,
-				     char *keybuf)
-{
-	struct iw_point *erq = &wrqu->encoding;
-	struct orinoco_private *priv = ndev_priv(dev);
-	int index = (erq->flags & IW_ENCODE_INDEX) - 1;
-	unsigned long flags;
-
-	if (!priv->has_wep)
-		return -EOPNOTSUPP;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	if ((index < 0) || (index >= ORINOCO_MAX_KEYS))
-		index = priv->tx_key;
-
-	erq->flags = 0;
-	if (!priv->encode_alg)
-		erq->flags |= IW_ENCODE_DISABLED;
-	erq->flags |= index + 1;
-
-	if (priv->wep_restrict)
-		erq->flags |= IW_ENCODE_RESTRICTED;
-	else
-		erq->flags |= IW_ENCODE_OPEN;
-
-	erq->length = priv->keys[index].key_len;
-
-	memcpy(keybuf, priv->keys[index].key, erq->length);
-
-	orinoco_unlock(priv, &flags);
-	return 0;
-}
-
-static int orinoco_ioctl_setessid(struct net_device *dev,
-				  struct iw_request_info *info,
-				  union iwreq_data *wrqu,
-				  char *essidbuf)
-{
-	struct iw_point *erq = &wrqu->essid;
-	struct orinoco_private *priv = ndev_priv(dev);
-	unsigned long flags;
-
-	/* Note : ESSID is ignored in Ad-Hoc demo mode, but we can set it
-	 * anyway... - Jean II */
-
-	/* Hum... Should not use Wireless Extension constant (may change),
-	 * should use our own... - Jean II */
-	if (erq->length > IW_ESSID_MAX_SIZE)
-		return -E2BIG;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	/* NULL the string (for NULL termination & ESSID = ANY) - Jean II */
-	memset(priv->desired_essid, 0, sizeof(priv->desired_essid));
-
-	/* If not ANY, get the new ESSID */
-	if (erq->flags)
-		memcpy(priv->desired_essid, essidbuf, erq->length);
-
-	orinoco_unlock(priv, &flags);
-
-	return -EINPROGRESS;		/* Call commit handler */
-}
-
-static int orinoco_ioctl_getessid(struct net_device *dev,
-				  struct iw_request_info *info,
-				  union iwreq_data *wrqu,
-				  char *essidbuf)
-{
-	struct iw_point *erq = &wrqu->essid;
-	struct orinoco_private *priv = ndev_priv(dev);
-	int active;
-	int err = 0;
-	unsigned long flags;
-
-	if (netif_running(dev)) {
-		err = orinoco_hw_get_essid(priv, &active, essidbuf);
-		if (err < 0)
-			return err;
-		erq->length = err;
-	} else {
-		if (orinoco_lock(priv, &flags) != 0)
-			return -EBUSY;
-		memcpy(essidbuf, priv->desired_essid, IW_ESSID_MAX_SIZE);
-		erq->length = strlen(priv->desired_essid);
-		orinoco_unlock(priv, &flags);
-	}
-
-	erq->flags = 1;
-
-	return 0;
-}
-
-static int orinoco_ioctl_setfreq(struct net_device *dev,
-				 struct iw_request_info *info,
-				 union iwreq_data *wrqu,
-				 char *extra)
-{
-	struct iw_freq *frq = &wrqu->freq;
-	struct orinoco_private *priv = ndev_priv(dev);
-	int chan = -1;
-	unsigned long flags;
-	int err = -EINPROGRESS;		/* Call commit handler */
-
-	/* In infrastructure mode the AP sets the channel */
-	if (priv->iw_mode == NL80211_IFTYPE_STATION)
-		return -EBUSY;
-
-	if ((frq->e == 0) && (frq->m <= 1000)) {
-		/* Setting by channel number */
-		chan = frq->m;
-	} else {
-		/* Setting by frequency */
-		int denom = 1;
-		int i;
-
-		/* Calculate denominator to rescale to MHz */
-		for (i = 0; i < (6 - frq->e); i++)
-			denom *= 10;
-
-		chan = ieee80211_frequency_to_channel(frq->m / denom);
-	}
-
-	if ((chan < 1) || (chan > NUM_CHANNELS) ||
-	     !(priv->channel_mask & (1 << (chan - 1))))
-		return -EINVAL;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	priv->channel = chan;
-	if (priv->iw_mode == NL80211_IFTYPE_MONITOR) {
-		/* Fast channel change - no commit if successful */
-		struct hermes *hw = &priv->hw;
-		err = hw->ops->cmd_wait(hw, HERMES_CMD_TEST |
-					    HERMES_TEST_SET_CHANNEL,
-					chan, NULL);
-	}
-	orinoco_unlock(priv, &flags);
-
-	return err;
-}
-
-static int orinoco_ioctl_getfreq(struct net_device *dev,
-				 struct iw_request_info *info,
-				 union iwreq_data *wrqu,
-				 char *extra)
-{
-	struct iw_freq *frq = &wrqu->freq;
-	struct orinoco_private *priv = ndev_priv(dev);
-	int tmp;
-
-	/* Locking done in there */
-	tmp = orinoco_hw_get_freq(priv);
-	if (tmp < 0)
-		return tmp;
-
-	frq->m = tmp * 100000;
-	frq->e = 1;
-
-	return 0;
-}
-
-static int orinoco_ioctl_getsens(struct net_device *dev,
-				 struct iw_request_info *info,
-				 union iwreq_data *wrqu,
-				 char *extra)
-{
-	struct iw_param *srq = &wrqu->sens;
-	struct orinoco_private *priv = ndev_priv(dev);
-	struct hermes *hw = &priv->hw;
-	u16 val;
-	int err;
-	unsigned long flags;
-
-	if (!priv->has_sensitivity)
-		return -EOPNOTSUPP;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-	err = hermes_read_wordrec(hw, USER_BAP,
-				  HERMES_RID_CNFSYSTEMSCALE, &val);
-	orinoco_unlock(priv, &flags);
-
-	if (err)
-		return err;
-
-	srq->value = val;
-	srq->fixed = 0; /* auto */
-
-	return 0;
-}
-
-static int orinoco_ioctl_setsens(struct net_device *dev,
-				 struct iw_request_info *info,
-				 union iwreq_data *wrqu,
-				 char *extra)
-{
-	struct iw_param *srq = &wrqu->sens;
-	struct orinoco_private *priv = ndev_priv(dev);
-	int val = srq->value;
-	unsigned long flags;
-
-	if (!priv->has_sensitivity)
-		return -EOPNOTSUPP;
-
-	if ((val < 1) || (val > 3))
-		return -EINVAL;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-	priv->ap_density = val;
-	orinoco_unlock(priv, &flags);
-
-	return -EINPROGRESS;		/* Call commit handler */
-}
-
-static int orinoco_ioctl_setrate(struct net_device *dev,
-				 struct iw_request_info *info,
-				 union iwreq_data *wrqu,
-				 char *extra)
-{
-	struct iw_param *rrq = &wrqu->bitrate;
-	struct orinoco_private *priv = ndev_priv(dev);
-	int ratemode;
-	int bitrate; /* 100s of kilobits */
-	unsigned long flags;
-
-	/* As the user space doesn't know our highest rate, it uses -1
-	 * to ask us to set the highest rate.  Test it using "iwconfig
-	 * ethX rate auto" - Jean II */
-	if (rrq->value == -1)
-		bitrate = 110;
-	else {
-		if (rrq->value % 100000)
-			return -EINVAL;
-		bitrate = rrq->value / 100000;
-	}
-
-	ratemode = orinoco_get_bitratemode(bitrate, !rrq->fixed);
-
-	if (ratemode == -1)
-		return -EINVAL;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-	priv->bitratemode = ratemode;
-	orinoco_unlock(priv, &flags);
-
-	return -EINPROGRESS;
-}
-
-static int orinoco_ioctl_getrate(struct net_device *dev,
-				 struct iw_request_info *info,
-				 union iwreq_data *wrqu,
-				 char *extra)
-{
-	struct iw_param *rrq = &wrqu->bitrate;
-	struct orinoco_private *priv = ndev_priv(dev);
-	int err = 0;
-	int bitrate, automatic;
-	unsigned long flags;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	orinoco_get_ratemode_cfg(priv->bitratemode, &bitrate, &automatic);
-
-	/* If the interface is running we try to find more about the
-	   current mode */
-	if (netif_running(dev)) {
-		int act_bitrate;
-		int lerr;
-
-		/* Ignore errors if we can't get the actual bitrate */
-		lerr = orinoco_hw_get_act_bitrate(priv, &act_bitrate);
-		if (!lerr)
-			bitrate = act_bitrate;
-	}
-
-	orinoco_unlock(priv, &flags);
-
-	rrq->value = bitrate;
-	rrq->fixed = !automatic;
-	rrq->disabled = 0;
-
-	return err;
-}
-
-static int orinoco_ioctl_setpower(struct net_device *dev,
-				  struct iw_request_info *info,
-				  union iwreq_data *wrqu,
-				  char *extra)
-{
-	struct iw_param *prq = &wrqu->power;
-	struct orinoco_private *priv = ndev_priv(dev);
-	int err = -EINPROGRESS;		/* Call commit handler */
-	unsigned long flags;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	if (prq->disabled) {
-		priv->pm_on = 0;
-	} else {
-		switch (prq->flags & IW_POWER_MODE) {
-		case IW_POWER_UNICAST_R:
-			priv->pm_mcast = 0;
-			priv->pm_on = 1;
-			break;
-		case IW_POWER_ALL_R:
-			priv->pm_mcast = 1;
-			priv->pm_on = 1;
-			break;
-		case IW_POWER_ON:
-			/* No flags : but we may have a value - Jean II */
-			break;
-		default:
-			err = -EINVAL;
-			goto out;
-		}
-
-		if (prq->flags & IW_POWER_TIMEOUT) {
-			priv->pm_on = 1;
-			priv->pm_timeout = prq->value / 1000;
-		}
-		if (prq->flags & IW_POWER_PERIOD) {
-			priv->pm_on = 1;
-			priv->pm_period = prq->value / 1000;
-		}
-		/* It's valid to not have a value if we are just toggling
-		 * the flags... Jean II */
-		if (!priv->pm_on) {
-			err = -EINVAL;
-			goto out;
-		}
-	}
-
- out:
-	orinoco_unlock(priv, &flags);
-
-	return err;
-}
-
-static int orinoco_ioctl_getpower(struct net_device *dev,
-				  struct iw_request_info *info,
-				  union iwreq_data *wrqu,
-				  char *extra)
-{
-	struct iw_param *prq = &wrqu->power;
-	struct orinoco_private *priv = ndev_priv(dev);
-	struct hermes *hw = &priv->hw;
-	int err = 0;
-	u16 enable, period, timeout, mcast;
-	unsigned long flags;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	err = hermes_read_wordrec(hw, USER_BAP,
-				  HERMES_RID_CNFPMENABLED, &enable);
-	if (err)
-		goto out;
-
-	err = hermes_read_wordrec(hw, USER_BAP,
-				  HERMES_RID_CNFMAXSLEEPDURATION, &period);
-	if (err)
-		goto out;
-
-	err = hermes_read_wordrec(hw, USER_BAP,
-				  HERMES_RID_CNFPMHOLDOVERDURATION, &timeout);
-	if (err)
-		goto out;
-
-	err = hermes_read_wordrec(hw, USER_BAP,
-				  HERMES_RID_CNFMULTICASTRECEIVE, &mcast);
-	if (err)
-		goto out;
-
-	prq->disabled = !enable;
-	/* Note : by default, display the period */
-	if ((prq->flags & IW_POWER_TYPE) == IW_POWER_TIMEOUT) {
-		prq->flags = IW_POWER_TIMEOUT;
-		prq->value = timeout * 1000;
-	} else {
-		prq->flags = IW_POWER_PERIOD;
-		prq->value = period * 1000;
-	}
-	if (mcast)
-		prq->flags |= IW_POWER_ALL_R;
-	else
-		prq->flags |= IW_POWER_UNICAST_R;
-
- out:
-	orinoco_unlock(priv, &flags);
-
-	return err;
-}
-
-static int orinoco_ioctl_set_encodeext(struct net_device *dev,
-				       struct iw_request_info *info,
-				       union iwreq_data *wrqu,
-				       char *extra)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	struct iw_point *encoding = &wrqu->encoding;
-	struct iw_encode_ext *ext = (struct iw_encode_ext *)extra;
-	int idx, alg = ext->alg, set_key = 1;
-	unsigned long flags;
-	int err = -EINVAL;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	/* Determine and validate the key index */
-	idx = encoding->flags & IW_ENCODE_INDEX;
-	if (idx) {
-		if ((idx < 1) || (idx > 4))
-			goto out;
-		idx--;
-	} else
-		idx = priv->tx_key;
-
-	if (encoding->flags & IW_ENCODE_DISABLED)
-		alg = IW_ENCODE_ALG_NONE;
-
-	if (priv->has_wpa && (alg != IW_ENCODE_ALG_TKIP)) {
-		/* Clear any TKIP TX key we had */
-		(void) orinoco_clear_tkip_key(priv, priv->tx_key);
-	}
-
-	if (ext->ext_flags & IW_ENCODE_EXT_SET_TX_KEY) {
-		priv->tx_key = idx;
-		set_key = ((alg == IW_ENCODE_ALG_TKIP) ||
-			   (ext->key_len > 0)) ? 1 : 0;
-	}
-
-	if (set_key) {
-		/* Set the requested key first */
-		switch (alg) {
-		case IW_ENCODE_ALG_NONE:
-			priv->encode_alg = ORINOCO_ALG_NONE;
-			err = orinoco_set_key(priv, idx, ORINOCO_ALG_NONE,
-					      NULL, 0, NULL, 0);
-			break;
-
-		case IW_ENCODE_ALG_WEP:
-			if (ext->key_len <= 0)
-				goto out;
-
-			priv->encode_alg = ORINOCO_ALG_WEP;
-			err = orinoco_set_key(priv, idx, ORINOCO_ALG_WEP,
-					      ext->key, ext->key_len, NULL, 0);
-			break;
-
-		case IW_ENCODE_ALG_TKIP:
-		{
-			u8 *tkip_iv = NULL;
-
-			if (!priv->has_wpa ||
-			    (ext->key_len > sizeof(struct orinoco_tkip_key)))
-				goto out;
-
-			priv->encode_alg = ORINOCO_ALG_TKIP;
-
-			if (ext->ext_flags & IW_ENCODE_EXT_RX_SEQ_VALID)
-				tkip_iv = &ext->rx_seq[0];
-
-			err = orinoco_set_key(priv, idx, ORINOCO_ALG_TKIP,
-					      ext->key, ext->key_len, tkip_iv,
-					      ORINOCO_SEQ_LEN);
-
-			err = __orinoco_hw_set_tkip_key(priv, idx,
-				 ext->ext_flags & IW_ENCODE_EXT_SET_TX_KEY,
-				 priv->keys[idx].key, priv->keys[idx].key_len,
-				 tkip_iv, ORINOCO_SEQ_LEN, NULL, 0);
-			if (err)
-				printk(KERN_ERR "%s: Error %d setting TKIP key"
-				       "\n", dev->name, err);
-
-			goto out;
-		}
-		default:
-			goto out;
-		}
-	}
-	err = -EINPROGRESS;
- out:
-	orinoco_unlock(priv, &flags);
-
-	return err;
-}
-
-static int orinoco_ioctl_get_encodeext(struct net_device *dev,
-				       struct iw_request_info *info,
-				       union iwreq_data *wrqu,
-				       char *extra)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	struct iw_point *encoding = &wrqu->encoding;
-	struct iw_encode_ext *ext = (struct iw_encode_ext *)extra;
-	int idx, max_key_len;
-	unsigned long flags;
-	int err;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	err = -EINVAL;
-	max_key_len = encoding->length - sizeof(*ext);
-	if (max_key_len < 0)
-		goto out;
-
-	idx = encoding->flags & IW_ENCODE_INDEX;
-	if (idx) {
-		if ((idx < 1) || (idx > 4))
-			goto out;
-		idx--;
-	} else
-		idx = priv->tx_key;
-
-	encoding->flags = idx + 1;
-	memset(ext, 0, sizeof(*ext));
-
-	switch (priv->encode_alg) {
-	case ORINOCO_ALG_NONE:
-		ext->alg = IW_ENCODE_ALG_NONE;
-		ext->key_len = 0;
-		encoding->flags |= IW_ENCODE_DISABLED;
-		break;
-	case ORINOCO_ALG_WEP:
-		ext->alg = IW_ENCODE_ALG_WEP;
-		ext->key_len = min(priv->keys[idx].key_len, max_key_len);
-		memcpy(ext->key, priv->keys[idx].key, ext->key_len);
-		encoding->flags |= IW_ENCODE_ENABLED;
-		break;
-	case ORINOCO_ALG_TKIP:
-		ext->alg = IW_ENCODE_ALG_TKIP;
-		ext->key_len = min(priv->keys[idx].key_len, max_key_len);
-		memcpy(ext->key, priv->keys[idx].key, ext->key_len);
-		encoding->flags |= IW_ENCODE_ENABLED;
-		break;
-	}
-
-	err = 0;
- out:
-	orinoco_unlock(priv, &flags);
-
-	return err;
-}
-
-static int orinoco_ioctl_set_auth(struct net_device *dev,
-				  struct iw_request_info *info,
-				  union iwreq_data *wrqu, char *extra)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	struct hermes *hw = &priv->hw;
-	struct iw_param *param = &wrqu->param;
-	unsigned long flags;
-	int ret = -EINPROGRESS;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	switch (param->flags & IW_AUTH_INDEX) {
-	case IW_AUTH_WPA_VERSION:
-	case IW_AUTH_CIPHER_PAIRWISE:
-	case IW_AUTH_CIPHER_GROUP:
-	case IW_AUTH_RX_UNENCRYPTED_EAPOL:
-	case IW_AUTH_PRIVACY_INVOKED:
-	case IW_AUTH_DROP_UNENCRYPTED:
-		/*
-		 * orinoco does not use these parameters
-		 */
-		break;
-
-	case IW_AUTH_MFP:
-		/* Management Frame Protection not supported.
-		 * Only fail if set to required.
-		 */
-		if (param->value == IW_AUTH_MFP_REQUIRED)
-			ret = -EINVAL;
-		break;
-
-	case IW_AUTH_KEY_MGMT:
-		/* wl_lkm implies value 2 == PSK for Hermes I
-		 * which ties in with WEXT
-		 * no other hints tho :(
-		 */
-		priv->key_mgmt = param->value;
-		break;
-
-	case IW_AUTH_TKIP_COUNTERMEASURES:
-		/* When countermeasures are enabled, shut down the
-		 * card; when disabled, re-enable the card. This must
-		 * take effect immediately.
-		 *
-		 * TODO: Make sure that the EAPOL message is getting
-		 *       out before card disabled
-		 */
-		if (param->value) {
-			priv->tkip_cm_active = 1;
-			ret = hermes_disable_port(hw, 0);
-		} else {
-			priv->tkip_cm_active = 0;
-			ret = hermes_enable_port(hw, 0);
-		}
-		break;
-
-	case IW_AUTH_80211_AUTH_ALG:
-		if (param->value & IW_AUTH_ALG_SHARED_KEY)
-			priv->wep_restrict = 1;
-		else if (param->value & IW_AUTH_ALG_OPEN_SYSTEM)
-			priv->wep_restrict = 0;
-		else
-			ret = -EINVAL;
-		break;
-
-	case IW_AUTH_WPA_ENABLED:
-		if (priv->has_wpa) {
-			priv->wpa_enabled = param->value ? 1 : 0;
-		} else {
-			if (param->value)
-				ret = -EOPNOTSUPP;
-			/* else silently accept disable of WPA */
-			priv->wpa_enabled = 0;
-		}
-		break;
-
-	default:
-		ret = -EOPNOTSUPP;
-	}
-
-	orinoco_unlock(priv, &flags);
-	return ret;
-}
-
-static int orinoco_ioctl_get_auth(struct net_device *dev,
-				  struct iw_request_info *info,
-				  union iwreq_data *wrqu, char *extra)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	struct iw_param *param = &wrqu->param;
-	unsigned long flags;
-	int ret = 0;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	switch (param->flags & IW_AUTH_INDEX) {
-	case IW_AUTH_KEY_MGMT:
-		param->value = priv->key_mgmt;
-		break;
-
-	case IW_AUTH_TKIP_COUNTERMEASURES:
-		param->value = priv->tkip_cm_active;
-		break;
-
-	case IW_AUTH_80211_AUTH_ALG:
-		if (priv->wep_restrict)
-			param->value = IW_AUTH_ALG_SHARED_KEY;
-		else
-			param->value = IW_AUTH_ALG_OPEN_SYSTEM;
-		break;
-
-	case IW_AUTH_WPA_ENABLED:
-		param->value = priv->wpa_enabled;
-		break;
-
-	default:
-		ret = -EOPNOTSUPP;
-	}
-
-	orinoco_unlock(priv, &flags);
-	return ret;
-}
-
-static int orinoco_ioctl_set_genie(struct net_device *dev,
-				   struct iw_request_info *info,
-				   union iwreq_data *wrqu, char *extra)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	u8 *buf;
-	unsigned long flags;
-
-	/* cut off at IEEE80211_MAX_DATA_LEN */
-	if ((wrqu->data.length > IEEE80211_MAX_DATA_LEN) ||
-	    (wrqu->data.length && (extra == NULL)))
-		return -EINVAL;
-
-	if (wrqu->data.length) {
-		buf = kmemdup(extra, wrqu->data.length, GFP_KERNEL);
-		if (buf == NULL)
-			return -ENOMEM;
-	} else
-		buf = NULL;
-
-	if (orinoco_lock(priv, &flags) != 0) {
-		kfree(buf);
-		return -EBUSY;
-	}
-
-	kfree(priv->wpa_ie);
-	priv->wpa_ie = buf;
-	priv->wpa_ie_len = wrqu->data.length;
-
-	if (priv->wpa_ie) {
-		/* Looks like wl_lkm wants to check the auth alg, and
-		 * somehow pass it to the firmware.
-		 * Instead it just calls the key mgmt rid
-		 *   - we do this in set auth.
-		 */
-	}
-
-	orinoco_unlock(priv, &flags);
-	return 0;
-}
-
-static int orinoco_ioctl_get_genie(struct net_device *dev,
-				   struct iw_request_info *info,
-				   union iwreq_data *wrqu, char *extra)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	unsigned long flags;
-	int err = 0;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	if ((priv->wpa_ie_len == 0) || (priv->wpa_ie == NULL)) {
-		wrqu->data.length = 0;
-		goto out;
-	}
-
-	if (wrqu->data.length < priv->wpa_ie_len) {
-		err = -E2BIG;
-		goto out;
-	}
-
-	wrqu->data.length = priv->wpa_ie_len;
-	memcpy(extra, priv->wpa_ie, priv->wpa_ie_len);
-
-out:
-	orinoco_unlock(priv, &flags);
-	return err;
-}
-
-static int orinoco_ioctl_set_mlme(struct net_device *dev,
-				  struct iw_request_info *info,
-				  union iwreq_data *wrqu, char *extra)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	struct iw_mlme *mlme = (struct iw_mlme *)extra;
-	unsigned long flags;
-	int ret = 0;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	switch (mlme->cmd) {
-	case IW_MLME_DEAUTH:
-		/* silently ignore */
-		break;
-
-	case IW_MLME_DISASSOC:
-
-		ret = orinoco_hw_disassociate(priv, mlme->addr.sa_data,
-					      mlme->reason_code);
-		break;
-
-	default:
-		ret = -EOPNOTSUPP;
-	}
-
-	orinoco_unlock(priv, &flags);
-	return ret;
-}
-
-static int orinoco_ioctl_reset(struct net_device *dev,
-			       struct iw_request_info *info,
-			       union iwreq_data *wrqu,
-			       char *extra)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-
-	if (!capable(CAP_NET_ADMIN))
-		return -EPERM;
-
-	if (info->cmd == (SIOCIWFIRSTPRIV + 0x1)) {
-		printk(KERN_DEBUG "%s: Forcing reset!\n", dev->name);
-
-		/* Firmware reset */
-		orinoco_reset(&priv->reset_work);
-	} else {
-		printk(KERN_DEBUG "%s: Force scheduling reset!\n", dev->name);
-
-		schedule_work(&priv->reset_work);
-	}
-
-	return 0;
-}
-
-static int orinoco_ioctl_setibssport(struct net_device *dev,
-				     struct iw_request_info *info,
-				     union iwreq_data *wrqu,
-				     char *extra)
-
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	int val = *((int *) extra);
-	unsigned long flags;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	priv->ibss_port = val;
-
-	/* Actually update the mode we are using */
-	set_port_type(priv);
-
-	orinoco_unlock(priv, &flags);
-	return -EINPROGRESS;		/* Call commit handler */
-}
-
-static int orinoco_ioctl_getibssport(struct net_device *dev,
-				     struct iw_request_info *info,
-				     union iwreq_data *wrqu,
-				     char *extra)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	int *val = (int *) extra;
-
-	*val = priv->ibss_port;
-	return 0;
-}
-
-static int orinoco_ioctl_setport3(struct net_device *dev,
-				  struct iw_request_info *info,
-				  union iwreq_data *wrqu,
-				  char *extra)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	int val = *((int *) extra);
-	int err = 0;
-	unsigned long flags;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	switch (val) {
-	case 0: /* Try to do IEEE ad-hoc mode */
-		if (!priv->has_ibss) {
-			err = -EINVAL;
-			break;
-		}
-		priv->prefer_port3 = 0;
-
-		break;
-
-	case 1: /* Try to do Lucent proprietary ad-hoc mode */
-		if (!priv->has_port3) {
-			err = -EINVAL;
-			break;
-		}
-		priv->prefer_port3 = 1;
-		break;
-
-	default:
-		err = -EINVAL;
-	}
-
-	if (!err) {
-		/* Actually update the mode we are using */
-		set_port_type(priv);
-		err = -EINPROGRESS;
-	}
-
-	orinoco_unlock(priv, &flags);
-
-	return err;
-}
-
-static int orinoco_ioctl_getport3(struct net_device *dev,
-				  struct iw_request_info *info,
-				  union iwreq_data *wrqu,
-				  char *extra)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	int *val = (int *) extra;
-
-	*val = priv->prefer_port3;
-	return 0;
-}
-
-static int orinoco_ioctl_setpreamble(struct net_device *dev,
-				     struct iw_request_info *info,
-				     union iwreq_data *wrqu,
-				     char *extra)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	unsigned long flags;
-	int val;
-
-	if (!priv->has_preamble)
-		return -EOPNOTSUPP;
-
-	/* 802.11b has recently defined some short preamble.
-	 * Basically, the Phy header has been reduced in size.
-	 * This increase performance, especially at high rates
-	 * (the preamble is transmitted at 1Mb/s), unfortunately
-	 * this give compatibility troubles... - Jean II */
-	val = *((int *) extra);
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	if (val)
-		priv->preamble = 1;
-	else
-		priv->preamble = 0;
-
-	orinoco_unlock(priv, &flags);
-
-	return -EINPROGRESS;		/* Call commit handler */
-}
-
-static int orinoco_ioctl_getpreamble(struct net_device *dev,
-				     struct iw_request_info *info,
-				     union iwreq_data *wrqu,
-				     char *extra)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	int *val = (int *) extra;
-
-	if (!priv->has_preamble)
-		return -EOPNOTSUPP;
-
-	*val = priv->preamble;
-	return 0;
-}
-
-/* ioctl interface to hermes_read_ltv()
- * To use with iwpriv, pass the RID as the token argument, e.g.
- * iwpriv get_rid [0xfc00]
- * At least Wireless Tools 25 is required to use iwpriv.
- * For Wireless Tools 25 and 26 append "dummy" are the end. */
-static int orinoco_ioctl_getrid(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu,
-				char *extra)
-{
-	struct iw_point *data = &wrqu->data;
-	struct orinoco_private *priv = ndev_priv(dev);
-	struct hermes *hw = &priv->hw;
-	int rid = data->flags;
-	u16 length;
-	int err;
-	unsigned long flags;
-
-	/* It's a "get" function, but we don't want users to access the
-	 * WEP key and other raw firmware data */
-	if (!capable(CAP_NET_ADMIN))
-		return -EPERM;
-
-	if (rid < 0xfc00 || rid > 0xffff)
-		return -EINVAL;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return -EBUSY;
-
-	err = hw->ops->read_ltv(hw, USER_BAP, rid, MAX_RID_LEN, &length,
-				extra);
-	if (err)
-		goto out;
-
-	data->length = min_t(u16, HERMES_RECLEN_TO_BYTES(length),
-			     MAX_RID_LEN);
-
- out:
-	orinoco_unlock(priv, &flags);
-	return err;
-}
-
-
-/* Commit handler, called after set operations */
-static int orinoco_ioctl_commit(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu,
-				char *extra)
-{
-	struct orinoco_private *priv = ndev_priv(dev);
-	unsigned long flags;
-	int err = 0;
-
-	if (!priv->open)
-		return 0;
-
-	if (orinoco_lock(priv, &flags) != 0)
-		return err;
-
-	err = orinoco_commit(priv);
-
-	orinoco_unlock(priv, &flags);
-	return err;
-}
-
-static const struct iw_priv_args orinoco_privtab[] = {
-	{ SIOCIWFIRSTPRIV + 0x0, 0, 0, "force_reset" },
-	{ SIOCIWFIRSTPRIV + 0x1, 0, 0, "card_reset" },
-	{ SIOCIWFIRSTPRIV + 0x2, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1,
-	  0, "set_port3" },
-	{ SIOCIWFIRSTPRIV + 0x3, 0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1,
-	  "get_port3" },
-	{ SIOCIWFIRSTPRIV + 0x4, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1,
-	  0, "set_preamble" },
-	{ SIOCIWFIRSTPRIV + 0x5, 0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1,
-	  "get_preamble" },
-	{ SIOCIWFIRSTPRIV + 0x6, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1,
-	  0, "set_ibssport" },
-	{ SIOCIWFIRSTPRIV + 0x7, 0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1,
-	  "get_ibssport" },
-	{ SIOCIWFIRSTPRIV + 0x9, 0, IW_PRIV_TYPE_BYTE | MAX_RID_LEN,
-	  "get_rid" },
-};
-
-
-/*
- * Structures to export the Wireless Handlers
- */
-
-static const iw_handler	orinoco_handler[] = {
-	IW_HANDLER(SIOCSIWCOMMIT,	orinoco_ioctl_commit),
-	IW_HANDLER(SIOCGIWNAME,		cfg80211_wext_giwname),
-	IW_HANDLER(SIOCSIWFREQ,		orinoco_ioctl_setfreq),
-	IW_HANDLER(SIOCGIWFREQ,		orinoco_ioctl_getfreq),
-	IW_HANDLER(SIOCSIWMODE,		cfg80211_wext_siwmode),
-	IW_HANDLER(SIOCGIWMODE,		cfg80211_wext_giwmode),
-	IW_HANDLER(SIOCSIWSENS,		orinoco_ioctl_setsens),
-	IW_HANDLER(SIOCGIWSENS,		orinoco_ioctl_getsens),
-	IW_HANDLER(SIOCGIWRANGE,	cfg80211_wext_giwrange),
-	IW_HANDLER(SIOCSIWSPY,		iw_handler_set_spy),
-	IW_HANDLER(SIOCGIWSPY,		iw_handler_get_spy),
-	IW_HANDLER(SIOCSIWTHRSPY,	iw_handler_set_thrspy),
-	IW_HANDLER(SIOCGIWTHRSPY,	iw_handler_get_thrspy),
-	IW_HANDLER(SIOCSIWAP,		orinoco_ioctl_setwap),
-	IW_HANDLER(SIOCGIWAP,		orinoco_ioctl_getwap),
-	IW_HANDLER(SIOCSIWSCAN,		cfg80211_wext_siwscan),
-	IW_HANDLER(SIOCGIWSCAN,		cfg80211_wext_giwscan),
-	IW_HANDLER(SIOCSIWESSID,	orinoco_ioctl_setessid),
-	IW_HANDLER(SIOCGIWESSID,	orinoco_ioctl_getessid),
-	IW_HANDLER(SIOCSIWRATE,		orinoco_ioctl_setrate),
-	IW_HANDLER(SIOCGIWRATE,		orinoco_ioctl_getrate),
-	IW_HANDLER(SIOCSIWRTS,		cfg80211_wext_siwrts),
-	IW_HANDLER(SIOCGIWRTS,		cfg80211_wext_giwrts),
-	IW_HANDLER(SIOCSIWFRAG,		cfg80211_wext_siwfrag),
-	IW_HANDLER(SIOCGIWFRAG,		cfg80211_wext_giwfrag),
-	IW_HANDLER(SIOCGIWRETRY,	cfg80211_wext_giwretry),
-	IW_HANDLER(SIOCSIWENCODE,	orinoco_ioctl_setiwencode),
-	IW_HANDLER(SIOCGIWENCODE,	orinoco_ioctl_getiwencode),
-	IW_HANDLER(SIOCSIWPOWER,	orinoco_ioctl_setpower),
-	IW_HANDLER(SIOCGIWPOWER,	orinoco_ioctl_getpower),
-	IW_HANDLER(SIOCSIWGENIE,	orinoco_ioctl_set_genie),
-	IW_HANDLER(SIOCGIWGENIE,	orinoco_ioctl_get_genie),
-	IW_HANDLER(SIOCSIWMLME,		orinoco_ioctl_set_mlme),
-	IW_HANDLER(SIOCSIWAUTH,		orinoco_ioctl_set_auth),
-	IW_HANDLER(SIOCGIWAUTH,		orinoco_ioctl_get_auth),
-	IW_HANDLER(SIOCSIWENCODEEXT,	orinoco_ioctl_set_encodeext),
-	IW_HANDLER(SIOCGIWENCODEEXT,	orinoco_ioctl_get_encodeext),
-};
-
-
-/*
-  Added typecasting since we no longer use iwreq_data -- Moustafa
- */
-static const iw_handler	orinoco_private_handler[] = {
-	[0] = orinoco_ioctl_reset,
-	[1] = orinoco_ioctl_reset,
-	[2] = orinoco_ioctl_setport3,
-	[3] = orinoco_ioctl_getport3,
-	[4] = orinoco_ioctl_setpreamble,
-	[5] = orinoco_ioctl_getpreamble,
-	[6] = orinoco_ioctl_setibssport,
-	[7] = orinoco_ioctl_getibssport,
-	[9] = orinoco_ioctl_getrid,
-};
-
-const struct iw_handler_def orinoco_handler_def = {
-	.num_standard = ARRAY_SIZE(orinoco_handler),
-	.num_private = ARRAY_SIZE(orinoco_private_handler),
-	.num_private_args = ARRAY_SIZE(orinoco_privtab),
-	.standard = orinoco_handler,
-	.private = orinoco_private_handler,
-	.private_args = orinoco_privtab,
-	.get_wireless_stats = orinoco_get_wireless_stats,
-};
diff --git a/drivers/net/wireless/intersil/orinoco/wext.h b/drivers/net/wireless/intersil/orinoco/wext.h
deleted file mode 100644
index 1479f4e26dde..000000000000
--- a/drivers/net/wireless/intersil/orinoco/wext.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* Wireless extensions support.
- *
- * See copyright notice in main.c
- */
-#ifndef _ORINOCO_WEXT_H_
-#define _ORINOCO_WEXT_H_
-
-#include <net/iw_handler.h>
-
-/* Structure defining all our WEXT handlers */
-extern const struct iw_handler_def orinoco_handler_def;
-
-#endif /* _ORINOCO_WEXT_H_ */
diff --git a/drivers/net/wireless/legacy/Kconfig b/drivers/net/wireless/legacy/Kconfig
deleted file mode 100644
index 3a5275941212..000000000000
--- a/drivers/net/wireless/legacy/Kconfig
+++ /dev/null
@@ -1,55 +0,0 @@
-config PCMCIA_RAYCS
-	tristate "Aviator/Raytheon 2.4GHz wireless support"
-	depends on PCMCIA
-	select WIRELESS_EXT
-	select WEXT_SPY
-	select WEXT_PRIV
-	help
-	  Say Y here if you intend to attach an Aviator/Raytheon PCMCIA
-	  (PC-card) wireless Ethernet networking card to your computer.
-	  Please read the file
-	  <file:Documentation/networking/device_drivers/wifi/ray_cs.rst> for
-	  details.
-
-	  To compile this driver as a module, choose M here: the module will be
-	  called ray_cs.  If unsure, say N.
-
-config PCMCIA_WL3501
-	tristate "Planet WL3501 PCMCIA cards"
-	depends on CFG80211 && PCMCIA
-	select WIRELESS_EXT
-	select WEXT_SPY
-	help
-	  A driver for WL3501 PCMCIA 802.11 wireless cards made by Planet.
-	  It has basic support for Linux wireless extensions and initial
-	  micro support for ethtool.
-
-config USB_NET_RNDIS_WLAN
-	tristate "Wireless RNDIS USB support"
-	depends on USB
-	depends on CFG80211
-	select USB_NET_DRIVERS
-	select USB_USBNET
-	select USB_NET_CDCETHER
-	select USB_NET_RNDIS_HOST
-	help
-	  This is a driver for wireless RNDIS devices.
-	  These are USB based adapters found in devices such as:
-
-	  Buffalo WLI-U2-KG125S
-	  U.S. Robotics USR5421
-	  Belkin F5D7051
-	  Linksys WUSB54GSv2
-	  Linksys WUSB54GSC
-	  Asus WL169gE
-	  Eminent EM4045
-	  BT Voyager 1055
-	  Linksys WUSB54GSv1
-	  U.S. Robotics USR5420
-	  BUFFALO WLI-USB-G54
-
-	  All of these devices are based on Broadcom 4320 chip which is the
-	  only wireless RNDIS chip known to date.
-
-	  If you choose to build a module, it'll be called rndis_wlan.
-
diff --git a/drivers/net/wireless/legacy/Makefile b/drivers/net/wireless/legacy/Makefile
deleted file mode 100644
index 36878f080bfc..000000000000
--- a/drivers/net/wireless/legacy/Makefile
+++ /dev/null
@@ -1,6 +0,0 @@
-# 16-bit wireless PCMCIA client drivers
-obj-$(CONFIG_PCMCIA_RAYCS)	+= ray_cs.o
-obj-$(CONFIG_PCMCIA_WL3501)	+= wl3501_cs.o
-
-obj-$(CONFIG_USB_NET_RNDIS_WLAN)	+= rndis_wlan.o
-
diff --git a/drivers/net/wireless/legacy/ray_cs.c b/drivers/net/wireless/legacy/ray_cs.c
deleted file mode 100644
index c95a79e01cd0..000000000000
--- a/drivers/net/wireless/legacy/ray_cs.c
+++ /dev/null
@@ -1,2824 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*=============================================================================
- *
- * A  PCMCIA client driver for the Raylink wireless LAN card.
- * The starting point for this module was the skeleton.c in the
- * PCMCIA 2.9.12 package written by David Hinds, dahinds@users.sourceforge.net
- *
- * Copyright (c) 1998  Corey Thomas (corey@world.std.com)
- *
- * Changes:
- * Arnaldo Carvalho de Melo <acme@conectiva.com.br> - 08/08/2000
- * - reorganize kmallocs in ray_attach, checking all for failure
- *   and releasing the previous allocations if one fails
- *
- * Daniele Bellucci <bellucda@tiscali.it> - 07/10/2003
- * - Audit copy_to_user in ioctl(SIOCGIWESSID)
- *
-=============================================================================*/
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/proc_fs.h>
-#include <linux/ptrace.h>
-#include <linux/seq_file.h>
-#include <linux/string.h>
-#include <linux/timer.h>
-#include <linux/init.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/if_arp.h>
-#include <linux/ioport.h>
-#include <linux/skbuff.h>
-#include <linux/ieee80211.h>
-
-#include <pcmcia/cistpl.h>
-#include <pcmcia/cisreg.h>
-#include <pcmcia/ds.h>
-
-#include <linux/wireless.h>
-#include <net/iw_handler.h>
-
-#include <asm/io.h>
-#include <asm/byteorder.h>
-#include <linux/uaccess.h>
-
-/* Warning : these stuff will slow down the driver... */
-#define WIRELESS_SPY		/* Enable spying addresses */
-/* Definitions we need for spy */
-typedef struct iw_statistics iw_stats;
-typedef u_char mac_addr[ETH_ALEN];	/* Hardware address */
-
-#include "rayctl.h"
-#include "ray_cs.h"
-
-
-/** Prototypes based on PCMCIA skeleton driver *******************************/
-static int ray_config(struct pcmcia_device *link);
-static void ray_release(struct pcmcia_device *link);
-static void ray_detach(struct pcmcia_device *p_dev);
-
-/***** Prototypes indicated by device structure ******************************/
-static int ray_dev_close(struct net_device *dev);
-static int ray_dev_config(struct net_device *dev, struct ifmap *map);
-static struct net_device_stats *ray_get_stats(struct net_device *dev);
-static int ray_dev_init(struct net_device *dev);
-
-static int ray_open(struct net_device *dev);
-static netdev_tx_t ray_dev_start_xmit(struct sk_buff *skb,
-					    struct net_device *dev);
-static void set_multicast_list(struct net_device *dev);
-static void ray_update_multi_list(struct net_device *dev, int all);
-static int translate_frame(ray_dev_t *local, struct tx_msg __iomem *ptx,
-			   unsigned char *data, int len);
-static void ray_build_header(ray_dev_t *local, struct tx_msg __iomem *ptx,
-			     UCHAR msg_type, unsigned char *data);
-static void untranslate(ray_dev_t *local, struct sk_buff *skb, int len);
-static iw_stats *ray_get_wireless_stats(struct net_device *dev);
-static const struct iw_handler_def ray_handler_def;
-
-/***** Prototypes for raylink functions **************************************/
-static void authenticate(ray_dev_t *local);
-static int build_auth_frame(ray_dev_t *local, UCHAR *dest, int auth_type);
-static void authenticate_timeout(struct timer_list *t);
-static int get_free_ccs(ray_dev_t *local);
-static int get_free_tx_ccs(ray_dev_t *local);
-static void init_startup_params(ray_dev_t *local);
-static int parse_addr(char *in_str, UCHAR *out);
-static int ray_hw_xmit(unsigned char *data, int len, struct net_device *dev, UCHAR type);
-static int ray_init(struct net_device *dev);
-static int interrupt_ecf(ray_dev_t *local, int ccs);
-static void ray_reset(struct net_device *dev);
-static void ray_update_parm(struct net_device *dev, UCHAR objid, UCHAR *value, int len);
-static void verify_dl_startup(struct timer_list *t);
-
-/* Prototypes for interrpt time functions **********************************/
-static irqreturn_t ray_interrupt(int reg, void *dev_id);
-static void clear_interrupt(ray_dev_t *local);
-static void rx_deauthenticate(ray_dev_t *local, struct rcs __iomem *prcs,
-			      unsigned int pkt_addr, int rx_len);
-static int copy_from_rx_buff(ray_dev_t *local, UCHAR *dest, int pkt_addr, int len);
-static void ray_rx(struct net_device *dev, ray_dev_t *local, struct rcs __iomem *prcs);
-static void release_frag_chain(ray_dev_t *local, struct rcs __iomem *prcs);
-static void rx_authenticate(ray_dev_t *local, struct rcs __iomem *prcs,
-			    unsigned int pkt_addr, int rx_len);
-static void rx_data(struct net_device *dev, struct rcs __iomem *prcs,
-		    unsigned int pkt_addr, int rx_len);
-static void associate(ray_dev_t *local);
-
-/* Card command functions */
-static int dl_startup_params(struct net_device *dev);
-static void join_net(struct timer_list *t);
-static void start_net(struct timer_list *t);
-
-/*===========================================================================*/
-/* Parameters that can be set with 'insmod' */
-
-/* ADHOC=0, Infrastructure=1 */
-static int net_type = ADHOC;
-
-/* Hop dwell time in Kus (1024 us units defined by 802.11) */
-static int hop_dwell = 128;
-
-/* Beacon period in Kus */
-static int beacon_period = 256;
-
-/* power save mode (0 = off, 1 = save power) */
-static int psm;
-
-/* String for network's Extended Service Set ID. 32 Characters max */
-static char *essid;
-
-/* Default to encapsulation unless translation requested */
-static bool translate = true;
-
-static int country = USA;
-
-static int sniffer;
-
-static int bc;
-
-/* 48 bit physical card address if overriding card's real physical
- * address is required.  Since IEEE 802.11 addresses are 48 bits
- * like ethernet, an int can't be used, so a string is used. To
- * allow use of addresses starting with a decimal digit, the first
- * character must be a letter and will be ignored. This letter is
- * followed by up to 12 hex digits which are the address.  If less
- * than 12 digits are used, the address will be left filled with 0's.
- * Note that bit 0 of the first byte is the broadcast bit, and evil
- * things will happen if it is not 0 in a card address.
- */
-static char *phy_addr = NULL;
-
-static unsigned int ray_mem_speed = 500;
-
-/* WARNING: THIS DRIVER IS NOT CAPABLE OF HANDLING MULTIPLE DEVICES! */
-static struct pcmcia_device *this_device = NULL;
-
-MODULE_AUTHOR("Corey Thomas <corey@world.std.com>");
-MODULE_DESCRIPTION("Raylink/WebGear wireless LAN driver");
-MODULE_LICENSE("GPL");
-
-module_param(net_type, int, 0);
-module_param(hop_dwell, int, 0);
-module_param(beacon_period, int, 0);
-module_param(psm, int, 0);
-module_param(essid, charp, 0);
-module_param(translate, bool, 0);
-module_param(country, int, 0);
-module_param(sniffer, int, 0);
-module_param(bc, int, 0);
-module_param(phy_addr, charp, 0);
-module_param(ray_mem_speed, int, 0);
-
-static const UCHAR b5_default_startup_parms[] = {
-	0, 0,			/* Adhoc station */
-	'L', 'I', 'N', 'U', 'X', 0, 0, 0,	/* 32 char ESSID */
-	0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0,
-	1, 0,			/* Active scan, CA Mode */
-	0, 0, 0, 0, 0, 0,	/* No default MAC addr  */
-	0x7f, 0xff,		/* Frag threshold */
-	0x00, 0x80,		/* Hop time 128 Kus */
-	0x01, 0x00,		/* Beacon period 256 Kus */
-	0x01, 0x07, 0xa3,	/* DTIM, retries, ack timeout */
-	0x1d, 0x82, 0x4e,	/* SIFS, DIFS, PIFS */
-	0x7f, 0xff,		/* RTS threshold */
-	0x04, 0xe2, 0x38, 0xA4,	/* scan_dwell, max_scan_dwell */
-	0x05,			/* assoc resp timeout thresh */
-	0x08, 0x02, 0x08,	/* adhoc, infra, super cycle max */
-	0,			/* Promiscuous mode */
-	0x0c, 0x0bd,		/* Unique word */
-	0x32,			/* Slot time */
-	0xff, 0xff,		/* roam-low snr, low snr count */
-	0x05, 0xff,		/* Infra, adhoc missed bcn thresh */
-	0x01, 0x0b, 0x4f,	/* USA, hop pattern, hop pat length */
-/* b4 - b5 differences start here */
-	0x00, 0x3f,		/* CW max */
-	0x00, 0x0f,		/* CW min */
-	0x04, 0x08,		/* Noise gain, limit offset */
-	0x28, 0x28,		/* det rssi, med busy offsets */
-	7,			/* det sync thresh */
-	0, 2, 2,		/* test mode, min, max */
-	0,			/* allow broadcast SSID probe resp */
-	0, 0,			/* privacy must start, can join */
-	2, 0, 0, 0, 0, 0, 0, 0	/* basic rate set */
-};
-
-static const UCHAR b4_default_startup_parms[] = {
-	0, 0,			/* Adhoc station */
-	'L', 'I', 'N', 'U', 'X', 0, 0, 0,	/* 32 char ESSID */
-	0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0,
-	1, 0,			/* Active scan, CA Mode */
-	0, 0, 0, 0, 0, 0,	/* No default MAC addr  */
-	0x7f, 0xff,		/* Frag threshold */
-	0x02, 0x00,		/* Hop time */
-	0x00, 0x01,		/* Beacon period */
-	0x01, 0x07, 0xa3,	/* DTIM, retries, ack timeout */
-	0x1d, 0x82, 0xce,	/* SIFS, DIFS, PIFS */
-	0x7f, 0xff,		/* RTS threshold */
-	0xfb, 0x1e, 0xc7, 0x5c,	/* scan_dwell, max_scan_dwell */
-	0x05,			/* assoc resp timeout thresh */
-	0x04, 0x02, 0x4,	/* adhoc, infra, super cycle max */
-	0,			/* Promiscuous mode */
-	0x0c, 0x0bd,		/* Unique word */
-	0x4e,			/* Slot time (TBD seems wrong) */
-	0xff, 0xff,		/* roam-low snr, low snr count */
-	0x05, 0xff,		/* Infra, adhoc missed bcn thresh */
-	0x01, 0x0b, 0x4e,	/* USA, hop pattern, hop pat length */
-/* b4 - b5 differences start here */
-	0x3f, 0x0f,		/* CW max, min */
-	0x04, 0x08,		/* Noise gain, limit offset */
-	0x28, 0x28,		/* det rssi, med busy offsets */
-	7,			/* det sync thresh */
-	0, 2, 2,		/* test mode, min, max */
-	0,			/* rx/tx delay */
-	0, 0, 0, 0, 0, 0,	/* current BSS id */
-	0			/* hop set */
-};
-
-/*===========================================================================*/
-static const u8 eth2_llc[] = { 0xaa, 0xaa, 3, 0, 0, 0 };
-
-static const char hop_pattern_length[] = { 1,
-	USA_HOP_MOD, EUROPE_HOP_MOD,
-	JAPAN_HOP_MOD, KOREA_HOP_MOD,
-	SPAIN_HOP_MOD, FRANCE_HOP_MOD,
-	ISRAEL_HOP_MOD, AUSTRALIA_HOP_MOD,
-	JAPAN_TEST_HOP_MOD
-};
-
-static const char rcsid[] =
-    "Raylink/WebGear wireless LAN - Corey <Thomas corey@world.std.com>";
-
-static const struct net_device_ops ray_netdev_ops = {
-	.ndo_init 		= ray_dev_init,
-	.ndo_open 		= ray_open,
-	.ndo_stop 		= ray_dev_close,
-	.ndo_start_xmit		= ray_dev_start_xmit,
-	.ndo_set_config		= ray_dev_config,
-	.ndo_get_stats		= ray_get_stats,
-	.ndo_set_rx_mode	= set_multicast_list,
-	.ndo_set_mac_address 	= eth_mac_addr,
-	.ndo_validate_addr	= eth_validate_addr,
-};
-
-static int ray_probe(struct pcmcia_device *p_dev)
-{
-	ray_dev_t *local;
-	struct net_device *dev;
-	int ret;
-
-	dev_dbg(&p_dev->dev, "ray_attach()\n");
-
-	/* Allocate space for private device-specific data */
-	dev = alloc_etherdev(sizeof(ray_dev_t));
-	if (!dev)
-		return -ENOMEM;
-
-	local = netdev_priv(dev);
-	local->finder = p_dev;
-
-	/* The io structure describes IO port mapping. None used here */
-	p_dev->resource[0]->end = 0;
-	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
-
-	/* General socket configuration */
-	p_dev->config_flags |= CONF_ENABLE_IRQ;
-	p_dev->config_index = 1;
-
-	p_dev->priv = dev;
-
-	local->finder = p_dev;
-	local->card_status = CARD_INSERTED;
-	local->authentication_state = UNAUTHENTICATED;
-	local->num_multi = 0;
-	dev_dbg(&p_dev->dev, "ray_attach p_dev = %p,  dev = %p,  local = %p, intr = %p\n",
-	      p_dev, dev, local, &ray_interrupt);
-
-	/* Raylink entries in the device structure */
-	dev->netdev_ops = &ray_netdev_ops;
-	dev->wireless_handlers = &ray_handler_def;
-#ifdef WIRELESS_SPY
-	local->wireless_data.spy_data = &local->spy_data;
-	dev->wireless_data = &local->wireless_data;
-#endif /* WIRELESS_SPY */
-
-
-	dev_dbg(&p_dev->dev, "ray_cs ray_attach calling ether_setup.)\n");
-	netif_stop_queue(dev);
-
-	timer_setup(&local->timer, NULL, 0);
-
-	this_device = p_dev;
-	ret = ray_config(p_dev);
-	if (ret)
-		goto err_free_dev;
-
-	return 0;
-
-err_free_dev:
-	free_netdev(dev);
-	return ret;
-}
-
-static void ray_detach(struct pcmcia_device *link)
-{
-	struct net_device *dev;
-
-	dev_dbg(&link->dev, "ray_detach\n");
-
-	this_device = NULL;
-	dev = link->priv;
-
-	ray_release(link);
-
-	if (link->priv) {
-		unregister_netdev(dev);
-		free_netdev(dev);
-	}
-	dev_dbg(&link->dev, "ray_cs ray_detach ending\n");
-} /* ray_detach */
-
-#define MAX_TUPLE_SIZE 128
-static int ray_config(struct pcmcia_device *link)
-{
-	int ret = 0;
-	int i;
-	struct net_device *dev = link->priv;
-	ray_dev_t *local = netdev_priv(dev);
-
-	dev_dbg(&link->dev, "ray_config\n");
-
-	/* Determine card type and firmware version */
-	printk(KERN_INFO "ray_cs Detected: %s%s%s%s\n",
-	       link->prod_id[0] ? link->prod_id[0] : " ",
-	       link->prod_id[1] ? link->prod_id[1] : " ",
-	       link->prod_id[2] ? link->prod_id[2] : " ",
-	       link->prod_id[3] ? link->prod_id[3] : " ");
-
-	/* Now allocate an interrupt line.  Note that this does not
-	   actually assign a handler to the interrupt.
-	 */
-	ret = pcmcia_request_irq(link, ray_interrupt);
-	if (ret)
-		goto failed;
-	dev->irq = link->irq;
-
-	ret = pcmcia_enable_device(link);
-	if (ret)
-		goto failed;
-
-/*** Set up 32k window for shared memory (transmit and control) ************/
-	link->resource[2]->flags |= WIN_DATA_WIDTH_8 | WIN_MEMORY_TYPE_CM | WIN_ENABLE | WIN_USE_WAIT;
-	link->resource[2]->start = 0;
-	link->resource[2]->end = 0x8000;
-	ret = pcmcia_request_window(link, link->resource[2], ray_mem_speed);
-	if (ret)
-		goto failed;
-	ret = pcmcia_map_mem_page(link, link->resource[2], 0);
-	if (ret)
-		goto failed;
-	local->sram = ioremap(link->resource[2]->start,
-			resource_size(link->resource[2]));
-	if (!local->sram)
-		goto failed;
-
-/*** Set up 16k window for shared memory (receive buffer) ***************/
-	link->resource[3]->flags |=
-	    WIN_DATA_WIDTH_8 | WIN_MEMORY_TYPE_CM | WIN_ENABLE | WIN_USE_WAIT;
-	link->resource[3]->start = 0;
-	link->resource[3]->end = 0x4000;
-	ret = pcmcia_request_window(link, link->resource[3], ray_mem_speed);
-	if (ret)
-		goto failed;
-	ret = pcmcia_map_mem_page(link, link->resource[3], 0x8000);
-	if (ret)
-		goto failed;
-	local->rmem = ioremap(link->resource[3]->start,
-			resource_size(link->resource[3]));
-	if (!local->rmem)
-		goto failed;
-
-/*** Set up window for attribute memory ***********************************/
-	link->resource[4]->flags |=
-	    WIN_DATA_WIDTH_8 | WIN_MEMORY_TYPE_AM | WIN_ENABLE | WIN_USE_WAIT;
-	link->resource[4]->start = 0;
-	link->resource[4]->end = 0x1000;
-	ret = pcmcia_request_window(link, link->resource[4], ray_mem_speed);
-	if (ret)
-		goto failed;
-	ret = pcmcia_map_mem_page(link, link->resource[4], 0);
-	if (ret)
-		goto failed;
-	local->amem = ioremap(link->resource[4]->start,
-			resource_size(link->resource[4]));
-	if (!local->amem)
-		goto failed;
-
-	dev_dbg(&link->dev, "ray_config sram=%p\n", local->sram);
-	dev_dbg(&link->dev, "ray_config rmem=%p\n", local->rmem);
-	dev_dbg(&link->dev, "ray_config amem=%p\n", local->amem);
-	if (ray_init(dev) < 0) {
-		ray_release(link);
-		return -ENODEV;
-	}
-
-	SET_NETDEV_DEV(dev, &link->dev);
-	i = register_netdev(dev);
-	if (i != 0) {
-		printk("ray_config register_netdev() failed\n");
-		ray_release(link);
-		return i;
-	}
-
-	printk(KERN_INFO "%s: RayLink, irq %d, hw_addr %pM\n",
-	       dev->name, dev->irq, dev->dev_addr);
-
-	return 0;
-
-failed:
-	ray_release(link);
-	return -ENODEV;
-} /* ray_config */
-
-static inline struct ccs __iomem *ccs_base(ray_dev_t *dev)
-{
-	return dev->sram + CCS_BASE;
-}
-
-static inline struct rcs __iomem *rcs_base(ray_dev_t *dev)
-{
-	/*
-	 * This looks nonsensical, since there is a separate
-	 * RCS_BASE. But the difference between a "struct rcs"
-	 * and a "struct ccs" ends up being in the _index_ off
-	 * the base, so the base pointer is the same for both
-	 * ccs/rcs.
-	 */
-	return dev->sram + CCS_BASE;
-}
-
-/*===========================================================================*/
-static int ray_init(struct net_device *dev)
-{
-	int i;
-	struct ccs __iomem *pccs;
-	ray_dev_t *local = netdev_priv(dev);
-	struct pcmcia_device *link = local->finder;
-	dev_dbg(&link->dev, "ray_init(0x%p)\n", dev);
-	if (!(pcmcia_dev_present(link))) {
-		dev_dbg(&link->dev, "ray_init - device not present\n");
-		return -1;
-	}
-
-	local->net_type = net_type;
-	local->sta_type = TYPE_STA;
-
-	/* Copy the startup results to local memory */
-	memcpy_fromio(&local->startup_res, local->sram + ECF_TO_HOST_BASE,
-		      sizeof(struct startup_res_6));
-
-	/* Check Power up test status and get mac address from card */
-	if (local->startup_res.startup_word != 0x80) {
-		printk(KERN_INFO "ray_init ERROR card status = %2x\n",
-		       local->startup_res.startup_word);
-		local->card_status = CARD_INIT_ERROR;
-		return -1;
-	}
-
-	local->fw_ver = local->startup_res.firmware_version[0];
-	local->fw_bld = local->startup_res.firmware_version[1];
-	local->fw_var = local->startup_res.firmware_version[2];
-	dev_dbg(&link->dev, "ray_init firmware version %d.%d\n", local->fw_ver,
-	      local->fw_bld);
-
-	local->tib_length = 0x20;
-	if ((local->fw_ver == 5) && (local->fw_bld >= 30))
-		local->tib_length = local->startup_res.tib_length;
-	dev_dbg(&link->dev, "ray_init tib_length = 0x%02x\n", local->tib_length);
-	/* Initialize CCS's to buffer free state */
-	pccs = ccs_base(local);
-	for (i = 0; i < NUMBER_OF_CCS; i++) {
-		writeb(CCS_BUFFER_FREE, &(pccs++)->buffer_status);
-	}
-	init_startup_params(local);
-
-	/* copy mac address to startup parameters */
-	if (!parse_addr(phy_addr, local->sparm.b4.a_mac_addr)) {
-		memcpy(&local->sparm.b4.a_mac_addr,
-		       &local->startup_res.station_addr, ADDRLEN);
-	}
-
-	clear_interrupt(local);	/* Clear any interrupt from the card */
-	local->card_status = CARD_AWAITING_PARAM;
-	dev_dbg(&link->dev, "ray_init ending\n");
-	return 0;
-} /* ray_init */
-
-/*===========================================================================*/
-/* Download startup parameters to the card and command it to read them       */
-static int dl_startup_params(struct net_device *dev)
-{
-	int ccsindex;
-	ray_dev_t *local = netdev_priv(dev);
-	struct ccs __iomem *pccs;
-	struct pcmcia_device *link = local->finder;
-
-	dev_dbg(&link->dev, "dl_startup_params entered\n");
-	if (!(pcmcia_dev_present(link))) {
-		dev_dbg(&link->dev, "ray_cs dl_startup_params - device not present\n");
-		return -1;
-	}
-
-	/* Copy parameters to host to ECF area */
-	if (local->fw_ver == 0x55)
-		memcpy_toio(local->sram + HOST_TO_ECF_BASE, &local->sparm.b4,
-			    sizeof(struct b4_startup_params));
-	else
-		memcpy_toio(local->sram + HOST_TO_ECF_BASE, &local->sparm.b5,
-			    sizeof(struct b5_startup_params));
-
-	/* Fill in the CCS fields for the ECF */
-	if ((ccsindex = get_free_ccs(local)) < 0)
-		return -1;
-	local->dl_param_ccs = ccsindex;
-	pccs = ccs_base(local) + ccsindex;
-	writeb(CCS_DOWNLOAD_STARTUP_PARAMS, &pccs->cmd);
-	dev_dbg(&link->dev, "dl_startup_params start ccsindex = %d\n",
-	      local->dl_param_ccs);
-	/* Interrupt the firmware to process the command */
-	if (interrupt_ecf(local, ccsindex)) {
-		printk(KERN_INFO "ray dl_startup_params failed - "
-		       "ECF not ready for intr\n");
-		local->card_status = CARD_DL_PARAM_ERROR;
-		writeb(CCS_BUFFER_FREE, &(pccs++)->buffer_status);
-		return -2;
-	}
-	local->card_status = CARD_DL_PARAM;
-	/* Start kernel timer to wait for dl startup to complete. */
-	local->timer.expires = jiffies + HZ / 2;
-	local->timer.function = verify_dl_startup;
-	add_timer(&local->timer);
-	dev_dbg(&link->dev,
-	      "ray_cs dl_startup_params started timer for verify_dl_startup\n");
-	return 0;
-} /* dl_startup_params */
-
-/*===========================================================================*/
-static void init_startup_params(ray_dev_t *local)
-{
-	int i;
-
-	if (country > JAPAN_TEST)
-		country = USA;
-	else if (country < USA)
-		country = USA;
-	/* structure for hop time and beacon period is defined here using
-	 * New 802.11D6.1 format.  Card firmware is still using old format
-	 * until version 6.
-	 *    Before                    After
-	 *    a_hop_time ms byte        a_hop_time ms byte
-	 *    a_hop_time 2s byte        a_hop_time ls byte
-	 *    a_hop_time ls byte        a_beacon_period ms byte
-	 *    a_beacon_period           a_beacon_period ls byte
-	 *
-	 *    a_hop_time = uS           a_hop_time = KuS
-	 *    a_beacon_period = hops    a_beacon_period = KuS
-	 *//* 64ms = 010000 */
-	if (local->fw_ver == 0x55) {
-		memcpy(&local->sparm.b4, b4_default_startup_parms,
-		       sizeof(struct b4_startup_params));
-		/* Translate sane kus input values to old build 4/5 format */
-		/* i = hop time in uS truncated to 3 bytes */
-		i = (hop_dwell * 1024) & 0xffffff;
-		local->sparm.b4.a_hop_time[0] = (i >> 16) & 0xff;
-		local->sparm.b4.a_hop_time[1] = (i >> 8) & 0xff;
-		local->sparm.b4.a_beacon_period[0] = 0;
-		local->sparm.b4.a_beacon_period[1] =
-		    ((beacon_period / hop_dwell) - 1) & 0xff;
-		local->sparm.b4.a_curr_country_code = country;
-		local->sparm.b4.a_hop_pattern_length =
-		    hop_pattern_length[(int)country] - 1;
-		if (bc) {
-			local->sparm.b4.a_ack_timeout = 0x50;
-			local->sparm.b4.a_sifs = 0x3f;
-		}
-	} else { /* Version 5 uses real kus values */
-		memcpy((UCHAR *) &local->sparm.b5, b5_default_startup_parms,
-		       sizeof(struct b5_startup_params));
-
-		local->sparm.b5.a_hop_time[0] = (hop_dwell >> 8) & 0xff;
-		local->sparm.b5.a_hop_time[1] = hop_dwell & 0xff;
-		local->sparm.b5.a_beacon_period[0] =
-		    (beacon_period >> 8) & 0xff;
-		local->sparm.b5.a_beacon_period[1] = beacon_period & 0xff;
-		if (psm)
-			local->sparm.b5.a_power_mgt_state = 1;
-		local->sparm.b5.a_curr_country_code = country;
-		local->sparm.b5.a_hop_pattern_length =
-		    hop_pattern_length[(int)country];
-	}
-
-	local->sparm.b4.a_network_type = net_type & 0x01;
-	local->sparm.b4.a_acting_as_ap_status = TYPE_STA;
-
-	if (essid != NULL)
-		strscpy(local->sparm.b4.a_current_ess_id, essid, ESSID_SIZE);
-} /* init_startup_params */
-
-/*===========================================================================*/
-static void verify_dl_startup(struct timer_list *t)
-{
-	ray_dev_t *local = from_timer(local, t, timer);
-	struct ccs __iomem *pccs = ccs_base(local) + local->dl_param_ccs;
-	UCHAR status;
-	struct pcmcia_device *link = local->finder;
-
-	if (!(pcmcia_dev_present(link))) {
-		dev_dbg(&link->dev, "ray_cs verify_dl_startup - device not present\n");
-		return;
-	}
-#if 0
-	{
-		int i;
-		printk(KERN_DEBUG
-		       "verify_dl_startup parameters sent via ccs %d:\n",
-		       local->dl_param_ccs);
-		for (i = 0; i < sizeof(struct b5_startup_params); i++) {
-			printk(" %2x",
-			       (unsigned int)readb(local->sram +
-						   HOST_TO_ECF_BASE + i));
-		}
-		printk("\n");
-	}
-#endif
-
-	status = readb(&pccs->buffer_status);
-	if (status != CCS_BUFFER_FREE) {
-		printk(KERN_INFO
-		       "Download startup params failed.  Status = %d\n",
-		       status);
-		local->card_status = CARD_DL_PARAM_ERROR;
-		return;
-	}
-	if (local->sparm.b4.a_network_type == ADHOC)
-		start_net(&local->timer);
-	else
-		join_net(&local->timer);
-} /* end verify_dl_startup */
-
-/*===========================================================================*/
-/* Command card to start a network */
-static void start_net(struct timer_list *t)
-{
-	ray_dev_t *local = from_timer(local, t, timer);
-	struct ccs __iomem *pccs;
-	int ccsindex;
-	struct pcmcia_device *link = local->finder;
-	if (!(pcmcia_dev_present(link))) {
-		dev_dbg(&link->dev, "ray_cs start_net - device not present\n");
-		return;
-	}
-	/* Fill in the CCS fields for the ECF */
-	if ((ccsindex = get_free_ccs(local)) < 0)
-		return;
-	pccs = ccs_base(local) + ccsindex;
-	writeb(CCS_START_NETWORK, &pccs->cmd);
-	writeb(0, &pccs->var.start_network.update_param);
-	/* Interrupt the firmware to process the command */
-	if (interrupt_ecf(local, ccsindex)) {
-		dev_dbg(&link->dev, "ray start net failed - card not ready for intr\n");
-		writeb(CCS_BUFFER_FREE, &(pccs++)->buffer_status);
-		return;
-	}
-	local->card_status = CARD_DOING_ACQ;
-} /* end start_net */
-
-/*===========================================================================*/
-/* Command card to join a network */
-static void join_net(struct timer_list *t)
-{
-	ray_dev_t *local = from_timer(local, t, timer);
-
-	struct ccs __iomem *pccs;
-	int ccsindex;
-	struct pcmcia_device *link = local->finder;
-
-	if (!(pcmcia_dev_present(link))) {
-		dev_dbg(&link->dev, "ray_cs join_net - device not present\n");
-		return;
-	}
-	/* Fill in the CCS fields for the ECF */
-	if ((ccsindex = get_free_ccs(local)) < 0)
-		return;
-	pccs = ccs_base(local) + ccsindex;
-	writeb(CCS_JOIN_NETWORK, &pccs->cmd);
-	writeb(0, &pccs->var.join_network.update_param);
-	writeb(0, &pccs->var.join_network.net_initiated);
-	/* Interrupt the firmware to process the command */
-	if (interrupt_ecf(local, ccsindex)) {
-		dev_dbg(&link->dev, "ray join net failed - card not ready for intr\n");
-		writeb(CCS_BUFFER_FREE, &(pccs++)->buffer_status);
-		return;
-	}
-	local->card_status = CARD_DOING_ACQ;
-}
-
-
-static void ray_release(struct pcmcia_device *link)
-{
-	struct net_device *dev = link->priv;
-	ray_dev_t *local = netdev_priv(dev);
-
-	dev_dbg(&link->dev, "ray_release\n");
-
-	del_timer_sync(&local->timer);
-
-	if (local->sram)
-		iounmap(local->sram);
-	if (local->rmem)
-		iounmap(local->rmem);
-	if (local->amem)
-		iounmap(local->amem);
-	pcmcia_disable_device(link);
-
-	dev_dbg(&link->dev, "ray_release ending\n");
-}
-
-static int ray_suspend(struct pcmcia_device *link)
-{
-	struct net_device *dev = link->priv;
-
-	if (link->open)
-		netif_device_detach(dev);
-
-	return 0;
-}
-
-static int ray_resume(struct pcmcia_device *link)
-{
-	struct net_device *dev = link->priv;
-
-	if (link->open) {
-		ray_reset(dev);
-		netif_device_attach(dev);
-	}
-
-	return 0;
-}
-
-/*===========================================================================*/
-static int ray_dev_init(struct net_device *dev)
-{
-#ifdef RAY_IMMEDIATE_INIT
-	int i;
-#endif /* RAY_IMMEDIATE_INIT */
-	ray_dev_t *local = netdev_priv(dev);
-	struct pcmcia_device *link = local->finder;
-
-	dev_dbg(&link->dev, "ray_dev_init(dev=%p)\n", dev);
-	if (!(pcmcia_dev_present(link))) {
-		dev_dbg(&link->dev, "ray_dev_init - device not present\n");
-		return -1;
-	}
-#ifdef RAY_IMMEDIATE_INIT
-	/* Download startup parameters */
-	if ((i = dl_startup_params(dev)) < 0) {
-		printk(KERN_INFO "ray_dev_init dl_startup_params failed - "
-		       "returns 0x%x\n", i);
-		return -1;
-	}
-#else /* RAY_IMMEDIATE_INIT */
-	/* Postpone the card init so that we can still configure the card,
-	 * for example using the Wireless Extensions. The init will happen
-	 * in ray_open() - Jean II */
-	dev_dbg(&link->dev,
-	      "ray_dev_init: postponing card init to ray_open() ; Status = %d\n",
-	      local->card_status);
-#endif /* RAY_IMMEDIATE_INIT */
-
-	/* copy mac and broadcast addresses to linux device */
-	eth_hw_addr_set(dev, local->sparm.b4.a_mac_addr);
-	eth_broadcast_addr(dev->broadcast);
-
-	dev_dbg(&link->dev, "ray_dev_init ending\n");
-	return 0;
-}
-
-/*===========================================================================*/
-static int ray_dev_config(struct net_device *dev, struct ifmap *map)
-{
-	ray_dev_t *local = netdev_priv(dev);
-	struct pcmcia_device *link = local->finder;
-	/* Dummy routine to satisfy device structure */
-	dev_dbg(&link->dev, "ray_dev_config(dev=%p,ifmap=%p)\n", dev, map);
-	if (!(pcmcia_dev_present(link))) {
-		dev_dbg(&link->dev, "ray_dev_config - device not present\n");
-		return -1;
-	}
-
-	return 0;
-}
-
-/*===========================================================================*/
-static netdev_tx_t ray_dev_start_xmit(struct sk_buff *skb,
-					    struct net_device *dev)
-{
-	ray_dev_t *local = netdev_priv(dev);
-	struct pcmcia_device *link = local->finder;
-	short length = skb->len;
-
-	if (!pcmcia_dev_present(link)) {
-		dev_dbg(&link->dev, "ray_dev_start_xmit - device not present\n");
-		dev_kfree_skb(skb);
-		return NETDEV_TX_OK;
-	}
-
-	dev_dbg(&link->dev, "ray_dev_start_xmit(skb=%p, dev=%p)\n", skb, dev);
-	if (local->authentication_state == NEED_TO_AUTH) {
-		dev_dbg(&link->dev, "ray_cs Sending authentication request.\n");
-		if (!build_auth_frame(local, local->auth_id, OPEN_AUTH_REQUEST)) {
-			local->authentication_state = AUTHENTICATED;
-			netif_stop_queue(dev);
-			return NETDEV_TX_BUSY;
-		}
-	}
-
-	if (length < ETH_ZLEN) {
-		if (skb_padto(skb, ETH_ZLEN))
-			return NETDEV_TX_OK;
-		length = ETH_ZLEN;
-	}
-	switch (ray_hw_xmit(skb->data, length, dev, DATA_TYPE)) {
-	case XMIT_NO_CCS:
-	case XMIT_NEED_AUTH:
-		netif_stop_queue(dev);
-		return NETDEV_TX_BUSY;
-	case XMIT_NO_INTR:
-	case XMIT_MSG_BAD:
-	case XMIT_OK:
-	default:
-		dev_kfree_skb(skb);
-	}
-
-	return NETDEV_TX_OK;
-} /* ray_dev_start_xmit */
-
-/*===========================================================================*/
-static int ray_hw_xmit(unsigned char *data, int len, struct net_device *dev,
-		       UCHAR msg_type)
-{
-	ray_dev_t *local = netdev_priv(dev);
-	struct ccs __iomem *pccs;
-	int ccsindex;
-	int offset;
-	struct tx_msg __iomem *ptx;	/* Address of xmit buffer in PC space */
-	short int addr;		/* Address of xmit buffer in card space */
-
-	pr_debug("ray_hw_xmit(data=%p, len=%d, dev=%p)\n", data, len, dev);
-	if (len + TX_HEADER_LENGTH > TX_BUF_SIZE) {
-		printk(KERN_INFO "ray_hw_xmit packet too large: %d bytes\n",
-		       len);
-		return XMIT_MSG_BAD;
-	}
-	switch (ccsindex = get_free_tx_ccs(local)) {
-	case ECCSBUSY:
-		pr_debug("ray_hw_xmit tx_ccs table busy\n");
-		fallthrough;
-	case ECCSFULL:
-		pr_debug("ray_hw_xmit No free tx ccs\n");
-		fallthrough;
-	case ECARDGONE:
-		netif_stop_queue(dev);
-		return XMIT_NO_CCS;
-	default:
-		break;
-	}
-	addr = TX_BUF_BASE + (ccsindex << 11);
-
-	if (msg_type == DATA_TYPE) {
-		local->stats.tx_bytes += len;
-		local->stats.tx_packets++;
-	}
-
-	ptx = local->sram + addr;
-
-	ray_build_header(local, ptx, msg_type, data);
-	if (translate) {
-		offset = translate_frame(local, ptx, data, len);
-	} else { /* Encapsulate frame */
-		/* TBD TIB length will move address of ptx->var */
-		memcpy_toio(&ptx->var, data, len);
-		offset = 0;
-	}
-
-	/* fill in the CCS */
-	pccs = ccs_base(local) + ccsindex;
-	len += TX_HEADER_LENGTH + offset;
-	writeb(CCS_TX_REQUEST, &pccs->cmd);
-	writeb(addr >> 8, &pccs->var.tx_request.tx_data_ptr[0]);
-	writeb(local->tib_length, &pccs->var.tx_request.tx_data_ptr[1]);
-	writeb(len >> 8, &pccs->var.tx_request.tx_data_length[0]);
-	writeb(len & 0xff, &pccs->var.tx_request.tx_data_length[1]);
-/* TBD still need psm_cam? */
-	writeb(PSM_CAM, &pccs->var.tx_request.pow_sav_mode);
-	writeb(local->net_default_tx_rate, &pccs->var.tx_request.tx_rate);
-	writeb(0, &pccs->var.tx_request.antenna);
-	pr_debug("ray_hw_xmit default_tx_rate = 0x%x\n",
-	      local->net_default_tx_rate);
-
-	/* Interrupt the firmware to process the command */
-	if (interrupt_ecf(local, ccsindex)) {
-		pr_debug("ray_hw_xmit failed - ECF not ready for intr\n");
-/* TBD very inefficient to copy packet to buffer, and then not
-   send it, but the alternative is to queue the messages and that
-   won't be done for a while.  Maybe set tbusy until a CCS is free?
-*/
-		writeb(CCS_BUFFER_FREE, &pccs->buffer_status);
-		return XMIT_NO_INTR;
-	}
-	return XMIT_OK;
-} /* end ray_hw_xmit */
-
-/*===========================================================================*/
-static int translate_frame(ray_dev_t *local, struct tx_msg __iomem *ptx,
-			   unsigned char *data, int len)
-{
-	__be16 proto = ((struct ethhdr *)data)->h_proto;
-	if (ntohs(proto) >= ETH_P_802_3_MIN) { /* DIX II ethernet frame */
-		pr_debug("ray_cs translate_frame DIX II\n");
-		/* Copy LLC header to card buffer */
-		memcpy_toio(&ptx->var, eth2_llc, sizeof(eth2_llc));
-		memcpy_toio(((void __iomem *)&ptx->var) + sizeof(eth2_llc),
-			    (UCHAR *) &proto, 2);
-		if (proto == htons(ETH_P_AARP) || proto == htons(ETH_P_IPX)) {
-			/* This is the selective translation table, only 2 entries */
-			writeb(0xf8,
-			       &((struct snaphdr_t __iomem *)ptx->var)->org[2]);
-		}
-		/* Copy body of ethernet packet without ethernet header */
-		memcpy_toio((void __iomem *)&ptx->var +
-			    sizeof(struct snaphdr_t), data + ETH_HLEN,
-			    len - ETH_HLEN);
-		return (int)sizeof(struct snaphdr_t) - ETH_HLEN;
-	} else { /* already  802 type, and proto is length */
-		pr_debug("ray_cs translate_frame 802\n");
-		if (proto == htons(0xffff)) { /* evil netware IPX 802.3 without LLC */
-			pr_debug("ray_cs translate_frame evil IPX\n");
-			memcpy_toio(&ptx->var, data + ETH_HLEN, len - ETH_HLEN);
-			return 0 - ETH_HLEN;
-		}
-		memcpy_toio(&ptx->var, data + ETH_HLEN, len - ETH_HLEN);
-		return 0 - ETH_HLEN;
-	}
-	/* TBD do other frame types */
-} /* end translate_frame */
-
-/*===========================================================================*/
-static void ray_build_header(ray_dev_t *local, struct tx_msg __iomem *ptx,
-			     UCHAR msg_type, unsigned char *data)
-{
-	writeb(PROTOCOL_VER | msg_type, &ptx->mac.frame_ctl_1);
-/*** IEEE 802.11 Address field assignments *************
-		TODS	FROMDS	addr_1		addr_2		addr_3	addr_4
-Adhoc		0	0	dest		src (terminal)	BSSID	N/A
-AP to Terminal	0	1	dest		AP(BSSID)	source	N/A
-Terminal to AP	1	0	AP(BSSID)	src (terminal)	dest	N/A
-AP to AP	1	1	dest AP		src AP		dest	source
-*******************************************************/
-	if (local->net_type == ADHOC) {
-		writeb(0, &ptx->mac.frame_ctl_2);
-		memcpy_toio(ptx->mac.addr_1, ((struct ethhdr *)data)->h_dest,
-			    ADDRLEN);
-		memcpy_toio(ptx->mac.addr_2, ((struct ethhdr *)data)->h_source,
-			    ADDRLEN);
-		memcpy_toio(ptx->mac.addr_3, local->bss_id, ADDRLEN);
-	} else { /* infrastructure */
-
-		if (local->sparm.b4.a_acting_as_ap_status) {
-			writeb(FC2_FROM_DS, &ptx->mac.frame_ctl_2);
-			memcpy_toio(ptx->mac.addr_1,
-				    ((struct ethhdr *)data)->h_dest, ADDRLEN);
-			memcpy_toio(ptx->mac.addr_2, local->bss_id, 6);
-			memcpy_toio(ptx->mac.addr_3,
-				    ((struct ethhdr *)data)->h_source, ADDRLEN);
-		} else { /* Terminal */
-
-			writeb(FC2_TO_DS, &ptx->mac.frame_ctl_2);
-			memcpy_toio(ptx->mac.addr_1, local->bss_id, ADDRLEN);
-			memcpy_toio(ptx->mac.addr_2,
-				    ((struct ethhdr *)data)->h_source, ADDRLEN);
-			memcpy_toio(ptx->mac.addr_3,
-				    ((struct ethhdr *)data)->h_dest, ADDRLEN);
-		}
-	}
-} /* end encapsulate_frame */
-
-/*====================================================================*/
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get protocol name
- */
-static int ray_get_name(struct net_device *dev, struct iw_request_info *info,
-			union iwreq_data *wrqu, char *extra)
-{
-	strcpy(wrqu->name, "IEEE 802.11-FH");
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : set frequency
- */
-static int ray_set_freq(struct net_device *dev, struct iw_request_info *info,
-			union iwreq_data *wrqu, char *extra)
-{
-	ray_dev_t *local = netdev_priv(dev);
-	int err = -EINPROGRESS;	/* Call commit handler */
-
-	/* Reject if card is already initialised */
-	if (local->card_status != CARD_AWAITING_PARAM)
-		return -EBUSY;
-
-	/* Setting by channel number */
-	if ((wrqu->freq.m > USA_HOP_MOD) || (wrqu->freq.e > 0))
-		err = -EOPNOTSUPP;
-	else
-		local->sparm.b5.a_hop_pattern = wrqu->freq.m;
-
-	return err;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get frequency
- */
-static int ray_get_freq(struct net_device *dev, struct iw_request_info *info,
-			union iwreq_data *wrqu, char *extra)
-{
-	ray_dev_t *local = netdev_priv(dev);
-
-	wrqu->freq.m = local->sparm.b5.a_hop_pattern;
-	wrqu->freq.e = 0;
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : set ESSID
- */
-static int ray_set_essid(struct net_device *dev, struct iw_request_info *info,
-			 union iwreq_data *wrqu, char *extra)
-{
-	ray_dev_t *local = netdev_priv(dev);
-
-	/* Reject if card is already initialised */
-	if (local->card_status != CARD_AWAITING_PARAM)
-		return -EBUSY;
-
-	/* Check if we asked for `any' */
-	if (wrqu->essid.flags == 0)
-		/* Corey : can you do that ? */
-		return -EOPNOTSUPP;
-
-	/* Check the size of the string */
-	if (wrqu->essid.length > IW_ESSID_MAX_SIZE)
-		return -E2BIG;
-
-	/* Set the ESSID in the card */
-	memset(local->sparm.b5.a_current_ess_id, 0, IW_ESSID_MAX_SIZE);
-	memcpy(local->sparm.b5.a_current_ess_id, extra, wrqu->essid.length);
-
-	return -EINPROGRESS;	/* Call commit handler */
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get ESSID
- */
-static int ray_get_essid(struct net_device *dev, struct iw_request_info *info,
-			 union iwreq_data *wrqu, char *extra)
-{
-	ray_dev_t *local = netdev_priv(dev);
-	UCHAR tmp[IW_ESSID_MAX_SIZE + 1];
-
-	/* Get the essid that was set */
-	memcpy(extra, local->sparm.b5.a_current_ess_id, IW_ESSID_MAX_SIZE);
-	memcpy(tmp, local->sparm.b5.a_current_ess_id, IW_ESSID_MAX_SIZE);
-	tmp[IW_ESSID_MAX_SIZE] = '\0';
-
-	/* Push it out ! */
-	wrqu->essid.length = strlen(tmp);
-	wrqu->essid.flags = 1;	/* active */
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get AP address
- */
-static int ray_get_wap(struct net_device *dev, struct iw_request_info *info,
-		       union iwreq_data *wrqu, char *extra)
-{
-	ray_dev_t *local = netdev_priv(dev);
-
-	memcpy(wrqu->ap_addr.sa_data, local->bss_id, ETH_ALEN);
-	wrqu->ap_addr.sa_family = ARPHRD_ETHER;
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : set Bit-Rate
- */
-static int ray_set_rate(struct net_device *dev, struct iw_request_info *info,
-			union iwreq_data *wrqu, char *extra)
-{
-	ray_dev_t *local = netdev_priv(dev);
-
-	/* Reject if card is already initialised */
-	if (local->card_status != CARD_AWAITING_PARAM)
-		return -EBUSY;
-
-	/* Check if rate is in range */
-	if ((wrqu->bitrate.value != 1000000) && (wrqu->bitrate.value != 2000000))
-		return -EINVAL;
-
-	/* Hack for 1.5 Mb/s instead of 2 Mb/s */
-	if ((local->fw_ver == 0x55) &&	/* Please check */
-	    (wrqu->bitrate.value == 2000000))
-		local->net_default_tx_rate = 3;
-	else
-		local->net_default_tx_rate = wrqu->bitrate.value / 500000;
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get Bit-Rate
- */
-static int ray_get_rate(struct net_device *dev, struct iw_request_info *info,
-			union iwreq_data *wrqu, char *extra)
-{
-	ray_dev_t *local = netdev_priv(dev);
-
-	if (local->net_default_tx_rate == 3)
-		wrqu->bitrate.value = 2000000;	/* Hum... */
-	else
-		wrqu->bitrate.value = local->net_default_tx_rate * 500000;
-	wrqu->bitrate.fixed = 0;	/* We are in auto mode */
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : set RTS threshold
- */
-static int ray_set_rts(struct net_device *dev, struct iw_request_info *info,
-		       union iwreq_data *wrqu, char *extra)
-{
-	ray_dev_t *local = netdev_priv(dev);
-	int rthr = wrqu->rts.value;
-
-	/* Reject if card is already initialised */
-	if (local->card_status != CARD_AWAITING_PARAM)
-		return -EBUSY;
-
-	/* if(wrq->u.rts.fixed == 0) we should complain */
-	if (wrqu->rts.disabled)
-		rthr = 32767;
-	else {
-		if ((rthr < 0) || (rthr > 2347))   /* What's the max packet size ??? */
-			return -EINVAL;
-	}
-	local->sparm.b5.a_rts_threshold[0] = (rthr >> 8) & 0xFF;
-	local->sparm.b5.a_rts_threshold[1] = rthr & 0xFF;
-
-	return -EINPROGRESS;	/* Call commit handler */
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get RTS threshold
- */
-static int ray_get_rts(struct net_device *dev, struct iw_request_info *info,
-		       union iwreq_data *wrqu, char *extra)
-{
-	ray_dev_t *local = netdev_priv(dev);
-
-	wrqu->rts.value = (local->sparm.b5.a_rts_threshold[0] << 8)
-	    + local->sparm.b5.a_rts_threshold[1];
-	wrqu->rts.disabled = (wrqu->rts.value == 32767);
-	wrqu->rts.fixed = 1;
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : set Fragmentation threshold
- */
-static int ray_set_frag(struct net_device *dev, struct iw_request_info *info,
-			union iwreq_data *wrqu, char *extra)
-{
-	ray_dev_t *local = netdev_priv(dev);
-	int fthr = wrqu->frag.value;
-
-	/* Reject if card is already initialised */
-	if (local->card_status != CARD_AWAITING_PARAM)
-		return -EBUSY;
-
-	/* if(wrq->u.frag.fixed == 0) should complain */
-	if (wrqu->frag.disabled)
-		fthr = 32767;
-	else {
-		if ((fthr < 256) || (fthr > 2347))	/* To check out ! */
-			return -EINVAL;
-	}
-	local->sparm.b5.a_frag_threshold[0] = (fthr >> 8) & 0xFF;
-	local->sparm.b5.a_frag_threshold[1] = fthr & 0xFF;
-
-	return -EINPROGRESS;	/* Call commit handler */
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get Fragmentation threshold
- */
-static int ray_get_frag(struct net_device *dev, struct iw_request_info *info,
-			union iwreq_data *wrqu, char *extra)
-{
-	ray_dev_t *local = netdev_priv(dev);
-
-	wrqu->frag.value = (local->sparm.b5.a_frag_threshold[0] << 8)
-	    + local->sparm.b5.a_frag_threshold[1];
-	wrqu->frag.disabled = (wrqu->frag.value == 32767);
-	wrqu->frag.fixed = 1;
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : set Mode of Operation
- */
-static int ray_set_mode(struct net_device *dev, struct iw_request_info *info,
-			union iwreq_data *wrqu, char *extra)
-{
-	ray_dev_t *local = netdev_priv(dev);
-	int err = -EINPROGRESS;	/* Call commit handler */
-	char card_mode = 1;
-
-	/* Reject if card is already initialised */
-	if (local->card_status != CARD_AWAITING_PARAM)
-		return -EBUSY;
-
-	switch (wrqu->mode) {
-	case IW_MODE_ADHOC:
-		card_mode = 0;
-		fallthrough;
-	case IW_MODE_INFRA:
-		local->sparm.b5.a_network_type = card_mode;
-		break;
-	default:
-		err = -EINVAL;
-	}
-
-	return err;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get Mode of Operation
- */
-static int ray_get_mode(struct net_device *dev, struct iw_request_info *info,
-			union iwreq_data *wrqu, char *extra)
-{
-	ray_dev_t *local = netdev_priv(dev);
-
-	if (local->sparm.b5.a_network_type)
-		wrqu->mode = IW_MODE_INFRA;
-	else
-		wrqu->mode = IW_MODE_ADHOC;
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Handler : get range info
- */
-static int ray_get_range(struct net_device *dev, struct iw_request_info *info,
-			 union iwreq_data *wrqu, char *extra)
-{
-	struct iw_range *range = (struct iw_range *)extra;
-
-	memset(range, 0, sizeof(struct iw_range));
-
-	/* Set the length (very important for backward compatibility) */
-	wrqu->data.length = sizeof(struct iw_range);
-
-	/* Set the Wireless Extension versions */
-	range->we_version_compiled = WIRELESS_EXT;
-	range->we_version_source = 9;
-
-	/* Set information in the range struct */
-	range->throughput = 1.1 * 1000 * 1000;	/* Put the right number here */
-	range->num_channels = hop_pattern_length[(int)country];
-	range->num_frequency = 0;
-	range->max_qual.qual = 0;
-	range->max_qual.level = 255;	/* What's the correct value ? */
-	range->max_qual.noise = 255;	/* Idem */
-	range->num_bitrates = 2;
-	range->bitrate[0] = 1000000;	/* 1 Mb/s */
-	range->bitrate[1] = 2000000;	/* 2 Mb/s */
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Private Handler : set framing mode
- */
-static int ray_set_framing(struct net_device *dev, struct iw_request_info *info,
-			   union iwreq_data *wrqu, char *extra)
-{
-	translate = !!*(extra);	/* Set framing mode */
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Private Handler : get framing mode
- */
-static int ray_get_framing(struct net_device *dev, struct iw_request_info *info,
-			   union iwreq_data *wrqu, char *extra)
-{
-	*(extra) = translate;
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Wireless Private Handler : get country
- */
-static int ray_get_country(struct net_device *dev, struct iw_request_info *info,
-			   union iwreq_data *wrqu, char *extra)
-{
-	*(extra) = country;
-
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Commit handler : called after a bunch of SET operations
- */
-static int ray_commit(struct net_device *dev, struct iw_request_info *info,
-		      union iwreq_data *wrqu, char *extra)
-{
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/*
- * Stats handler : return Wireless Stats
- */
-static iw_stats *ray_get_wireless_stats(struct net_device *dev)
-{
-	ray_dev_t *local = netdev_priv(dev);
-	struct pcmcia_device *link = local->finder;
-	struct status __iomem *p = local->sram + STATUS_BASE;
-
-	local->wstats.status = local->card_status;
-#ifdef WIRELESS_SPY
-	if ((local->spy_data.spy_number > 0)
-	    && (local->sparm.b5.a_network_type == 0)) {
-		/* Get it from the first node in spy list */
-		local->wstats.qual.qual = local->spy_data.spy_stat[0].qual;
-		local->wstats.qual.level = local->spy_data.spy_stat[0].level;
-		local->wstats.qual.noise = local->spy_data.spy_stat[0].noise;
-		local->wstats.qual.updated =
-		    local->spy_data.spy_stat[0].updated;
-	}
-#endif /* WIRELESS_SPY */
-
-	if (pcmcia_dev_present(link)) {
-		local->wstats.qual.noise = readb(&p->rxnoise);
-		local->wstats.qual.updated |= 4;
-	}
-
-	return &local->wstats;
-} /* end ray_get_wireless_stats */
-
-/*------------------------------------------------------------------*/
-/*
- * Structures to export the Wireless Handlers
- */
-
-static const iw_handler ray_handler[] = {
-	IW_HANDLER(SIOCSIWCOMMIT, ray_commit),
-	IW_HANDLER(SIOCGIWNAME, ray_get_name),
-	IW_HANDLER(SIOCSIWFREQ, ray_set_freq),
-	IW_HANDLER(SIOCGIWFREQ, ray_get_freq),
-	IW_HANDLER(SIOCSIWMODE, ray_set_mode),
-	IW_HANDLER(SIOCGIWMODE, ray_get_mode),
-	IW_HANDLER(SIOCGIWRANGE, ray_get_range),
-#ifdef WIRELESS_SPY
-	IW_HANDLER(SIOCSIWSPY, iw_handler_set_spy),
-	IW_HANDLER(SIOCGIWSPY, iw_handler_get_spy),
-	IW_HANDLER(SIOCSIWTHRSPY, iw_handler_set_thrspy),
-	IW_HANDLER(SIOCGIWTHRSPY, iw_handler_get_thrspy),
-#endif /* WIRELESS_SPY */
-	IW_HANDLER(SIOCGIWAP, ray_get_wap),
-	IW_HANDLER(SIOCSIWESSID, ray_set_essid),
-	IW_HANDLER(SIOCGIWESSID, ray_get_essid),
-	IW_HANDLER(SIOCSIWRATE, ray_set_rate),
-	IW_HANDLER(SIOCGIWRATE, ray_get_rate),
-	IW_HANDLER(SIOCSIWRTS, ray_set_rts),
-	IW_HANDLER(SIOCGIWRTS, ray_get_rts),
-	IW_HANDLER(SIOCSIWFRAG, ray_set_frag),
-	IW_HANDLER(SIOCGIWFRAG, ray_get_frag),
-};
-
-#define SIOCSIPFRAMING	SIOCIWFIRSTPRIV	/* Set framing mode */
-#define SIOCGIPFRAMING	SIOCIWFIRSTPRIV + 1	/* Get framing mode */
-#define SIOCGIPCOUNTRY	SIOCIWFIRSTPRIV + 3	/* Get country code */
-
-static const iw_handler ray_private_handler[] = {
-	[0] = ray_set_framing,
-	[1] = ray_get_framing,
-	[3] = ray_get_country,
-};
-
-static const struct iw_priv_args ray_private_args[] = {
-/* cmd,		set_args,	get_args,	name */
-	{SIOCSIPFRAMING, IW_PRIV_TYPE_BYTE | IW_PRIV_SIZE_FIXED | 1, 0,
-	 "set_framing"},
-	{SIOCGIPFRAMING, 0, IW_PRIV_TYPE_BYTE | IW_PRIV_SIZE_FIXED | 1,
-	 "get_framing"},
-	{SIOCGIPCOUNTRY, 0, IW_PRIV_TYPE_BYTE | IW_PRIV_SIZE_FIXED | 1,
-	 "get_country"},
-};
-
-static const struct iw_handler_def ray_handler_def = {
-	.num_standard = ARRAY_SIZE(ray_handler),
-	.num_private = ARRAY_SIZE(ray_private_handler),
-	.num_private_args = ARRAY_SIZE(ray_private_args),
-	.standard = ray_handler,
-	.private = ray_private_handler,
-	.private_args = ray_private_args,
-	.get_wireless_stats = ray_get_wireless_stats,
-};
-
-/*===========================================================================*/
-static int ray_open(struct net_device *dev)
-{
-	ray_dev_t *local = netdev_priv(dev);
-	struct pcmcia_device *link;
-	link = local->finder;
-
-	dev_dbg(&link->dev, "ray_open('%s')\n", dev->name);
-
-	if (link->open == 0)
-		local->num_multi = 0;
-	link->open++;
-
-	/* If the card is not started, time to start it ! - Jean II */
-	if (local->card_status == CARD_AWAITING_PARAM) {
-		int i;
-
-		dev_dbg(&link->dev, "ray_open: doing init now !\n");
-
-		/* Download startup parameters */
-		if ((i = dl_startup_params(dev)) < 0) {
-			printk(KERN_INFO
-			       "ray_dev_init dl_startup_params failed - "
-			       "returns 0x%x\n", i);
-			return -1;
-		}
-	}
-
-	if (sniffer)
-		netif_stop_queue(dev);
-	else
-		netif_start_queue(dev);
-
-	dev_dbg(&link->dev, "ray_open ending\n");
-	return 0;
-} /* end ray_open */
-
-/*===========================================================================*/
-static int ray_dev_close(struct net_device *dev)
-{
-	ray_dev_t *local = netdev_priv(dev);
-	struct pcmcia_device *link;
-	link = local->finder;
-
-	dev_dbg(&link->dev, "ray_dev_close('%s')\n", dev->name);
-
-	link->open--;
-	netif_stop_queue(dev);
-
-	/* In here, we should stop the hardware (stop card from beeing active)
-	 * and set local->card_status to CARD_AWAITING_PARAM, so that while the
-	 * card is closed we can chage its configuration.
-	 * Probably also need a COR reset to get sane state - Jean II */
-
-	return 0;
-} /* end ray_dev_close */
-
-/*===========================================================================*/
-static void ray_reset(struct net_device *dev)
-{
-	pr_debug("ray_reset entered\n");
-}
-
-/*===========================================================================*/
-/* Cause a firmware interrupt if it is ready for one                         */
-/* Return nonzero if not ready                                               */
-static int interrupt_ecf(ray_dev_t *local, int ccs)
-{
-	int i = 50;
-	struct pcmcia_device *link = local->finder;
-
-	if (!(pcmcia_dev_present(link))) {
-		dev_dbg(&link->dev, "ray_cs interrupt_ecf - device not present\n");
-		return -1;
-	}
-	dev_dbg(&link->dev, "interrupt_ecf(local=%p, ccs = 0x%x\n", local, ccs);
-
-	while (i &&
-	       (readb(local->amem + CIS_OFFSET + ECF_INTR_OFFSET) &
-		ECF_INTR_SET))
-		i--;
-	if (i == 0) {
-		dev_dbg(&link->dev, "ray_cs interrupt_ecf card not ready for interrupt\n");
-		return -1;
-	}
-	/* Fill the mailbox, then kick the card */
-	writeb(ccs, local->sram + SCB_BASE);
-	writeb(ECF_INTR_SET, local->amem + CIS_OFFSET + ECF_INTR_OFFSET);
-	return 0;
-} /* interrupt_ecf */
-
-/*===========================================================================*/
-/* Get next free transmit CCS                                                */
-/* Return - index of current tx ccs                                          */
-static int get_free_tx_ccs(ray_dev_t *local)
-{
-	int i;
-	struct ccs __iomem *pccs = ccs_base(local);
-	struct pcmcia_device *link = local->finder;
-
-	if (!(pcmcia_dev_present(link))) {
-		dev_dbg(&link->dev, "ray_cs get_free_tx_ccs - device not present\n");
-		return ECARDGONE;
-	}
-
-	if (test_and_set_bit(0, &local->tx_ccs_lock)) {
-		dev_dbg(&link->dev, "ray_cs tx_ccs_lock busy\n");
-		return ECCSBUSY;
-	}
-
-	for (i = 0; i < NUMBER_OF_TX_CCS; i++) {
-		if (readb(&(pccs + i)->buffer_status) == CCS_BUFFER_FREE) {
-			writeb(CCS_BUFFER_BUSY, &(pccs + i)->buffer_status);
-			writeb(CCS_END_LIST, &(pccs + i)->link);
-			local->tx_ccs_lock = 0;
-			return i;
-		}
-	}
-	local->tx_ccs_lock = 0;
-	dev_dbg(&link->dev, "ray_cs ERROR no free tx CCS for raylink card\n");
-	return ECCSFULL;
-} /* get_free_tx_ccs */
-
-/*===========================================================================*/
-/* Get next free CCS                                                         */
-/* Return - index of current ccs                                             */
-static int get_free_ccs(ray_dev_t *local)
-{
-	int i;
-	struct ccs __iomem *pccs = ccs_base(local);
-	struct pcmcia_device *link = local->finder;
-
-	if (!(pcmcia_dev_present(link))) {
-		dev_dbg(&link->dev, "ray_cs get_free_ccs - device not present\n");
-		return ECARDGONE;
-	}
-	if (test_and_set_bit(0, &local->ccs_lock)) {
-		dev_dbg(&link->dev, "ray_cs ccs_lock busy\n");
-		return ECCSBUSY;
-	}
-
-	for (i = NUMBER_OF_TX_CCS; i < NUMBER_OF_CCS; i++) {
-		if (readb(&(pccs + i)->buffer_status) == CCS_BUFFER_FREE) {
-			writeb(CCS_BUFFER_BUSY, &(pccs + i)->buffer_status);
-			writeb(CCS_END_LIST, &(pccs + i)->link);
-			local->ccs_lock = 0;
-			return i;
-		}
-	}
-	local->ccs_lock = 0;
-	dev_dbg(&link->dev, "ray_cs ERROR no free CCS for raylink card\n");
-	return ECCSFULL;
-} /* get_free_ccs */
-
-/*===========================================================================*/
-static void authenticate_timeout(struct timer_list *t)
-{
-	ray_dev_t *local = from_timer(local, t, timer);
-	del_timer(&local->timer);
-	printk(KERN_INFO "ray_cs Authentication with access point failed"
-	       " - timeout\n");
-	join_net(&local->timer);
-}
-
-/*===========================================================================*/
-static int parse_addr(char *in_str, UCHAR *out)
-{
-	int i, k;
-	int len;
-
-	if (in_str == NULL)
-		return 0;
-	len = strnlen(in_str, ADDRLEN * 2 + 1) - 1;
-	if (len < 1)
-		return 0;
-	memset(out, 0, ADDRLEN);
-
-	i = 5;
-
-	while (len > 0) {
-		if ((k = hex_to_bin(in_str[len--])) != -1)
-			out[i] = k;
-		else
-			return 0;
-
-		if (len == 0)
-			break;
-		if ((k = hex_to_bin(in_str[len--])) != -1)
-			out[i] += k << 4;
-		else
-			return 0;
-		if (!i--)
-			break;
-	}
-	return 1;
-}
-
-/*===========================================================================*/
-static struct net_device_stats *ray_get_stats(struct net_device *dev)
-{
-	ray_dev_t *local = netdev_priv(dev);
-	struct pcmcia_device *link = local->finder;
-	struct status __iomem *p = local->sram + STATUS_BASE;
-	if (!(pcmcia_dev_present(link))) {
-		dev_dbg(&link->dev, "ray_cs net_device_stats - device not present\n");
-		return &local->stats;
-	}
-	if (readb(&p->mrx_overflow_for_host)) {
-		local->stats.rx_over_errors += swab16(readw(&p->mrx_overflow));
-		writeb(0, &p->mrx_overflow);
-		writeb(0, &p->mrx_overflow_for_host);
-	}
-	if (readb(&p->mrx_checksum_error_for_host)) {
-		local->stats.rx_crc_errors +=
-		    swab16(readw(&p->mrx_checksum_error));
-		writeb(0, &p->mrx_checksum_error);
-		writeb(0, &p->mrx_checksum_error_for_host);
-	}
-	if (readb(&p->rx_hec_error_for_host)) {
-		local->stats.rx_frame_errors += swab16(readw(&p->rx_hec_error));
-		writeb(0, &p->rx_hec_error);
-		writeb(0, &p->rx_hec_error_for_host);
-	}
-	return &local->stats;
-}
-
-/*===========================================================================*/
-static void ray_update_parm(struct net_device *dev, UCHAR objid, UCHAR *value,
-			    int len)
-{
-	ray_dev_t *local = netdev_priv(dev);
-	struct pcmcia_device *link = local->finder;
-	int ccsindex;
-	int i;
-	struct ccs __iomem *pccs;
-
-	if (!(pcmcia_dev_present(link))) {
-		dev_dbg(&link->dev, "ray_update_parm - device not present\n");
-		return;
-	}
-
-	if ((ccsindex = get_free_ccs(local)) < 0) {
-		dev_dbg(&link->dev, "ray_update_parm - No free ccs\n");
-		return;
-	}
-	pccs = ccs_base(local) + ccsindex;
-	writeb(CCS_UPDATE_PARAMS, &pccs->cmd);
-	writeb(objid, &pccs->var.update_param.object_id);
-	writeb(1, &pccs->var.update_param.number_objects);
-	writeb(0, &pccs->var.update_param.failure_cause);
-	for (i = 0; i < len; i++) {
-		writeb(value[i], local->sram + HOST_TO_ECF_BASE);
-	}
-	/* Interrupt the firmware to process the command */
-	if (interrupt_ecf(local, ccsindex)) {
-		dev_dbg(&link->dev, "ray_cs associate failed - ECF not ready for intr\n");
-		writeb(CCS_BUFFER_FREE, &(pccs++)->buffer_status);
-	}
-}
-
-/*===========================================================================*/
-static void ray_update_multi_list(struct net_device *dev, int all)
-{
-	int ccsindex;
-	struct ccs __iomem *pccs;
-	ray_dev_t *local = netdev_priv(dev);
-	struct pcmcia_device *link = local->finder;
-	void __iomem *p = local->sram + HOST_TO_ECF_BASE;
-
-	if (!(pcmcia_dev_present(link))) {
-		dev_dbg(&link->dev, "ray_update_multi_list - device not present\n");
-		return;
-	} else
-		dev_dbg(&link->dev, "ray_update_multi_list(%p)\n", dev);
-	if ((ccsindex = get_free_ccs(local)) < 0) {
-		dev_dbg(&link->dev, "ray_update_multi - No free ccs\n");
-		return;
-	}
-	pccs = ccs_base(local) + ccsindex;
-	writeb(CCS_UPDATE_MULTICAST_LIST, &pccs->cmd);
-
-	if (all) {
-		writeb(0xff, &pccs->var);
-		local->num_multi = 0xff;
-	} else {
-		struct netdev_hw_addr *ha;
-		int i = 0;
-
-		/* Copy the kernel's list of MC addresses to card */
-		netdev_for_each_mc_addr(ha, dev) {
-			memcpy_toio(p, ha->addr, ETH_ALEN);
-			dev_dbg(&link->dev, "ray_update_multi add addr %pm\n",
-				ha->addr);
-			p += ETH_ALEN;
-			i++;
-		}
-		if (i > 256 / ADDRLEN)
-			i = 256 / ADDRLEN;
-		writeb((UCHAR) i, &pccs->var);
-		dev_dbg(&link->dev, "ray_cs update_multi %d addresses in list\n", i);
-		/* Interrupt the firmware to process the command */
-		local->num_multi = i;
-	}
-	if (interrupt_ecf(local, ccsindex)) {
-		dev_dbg(&link->dev,
-		      "ray_cs update_multi failed - ECF not ready for intr\n");
-		writeb(CCS_BUFFER_FREE, &(pccs++)->buffer_status);
-	}
-} /* end ray_update_multi_list */
-
-/*===========================================================================*/
-static void set_multicast_list(struct net_device *dev)
-{
-	ray_dev_t *local = netdev_priv(dev);
-	UCHAR promisc;
-
-	pr_debug("ray_cs set_multicast_list(%p)\n", dev);
-
-	if (dev->flags & IFF_PROMISC) {
-		if (local->sparm.b5.a_promiscuous_mode == 0) {
-			pr_debug("ray_cs set_multicast_list promisc on\n");
-			local->sparm.b5.a_promiscuous_mode = 1;
-			promisc = 1;
-			ray_update_parm(dev, OBJID_promiscuous_mode,
-					&promisc, sizeof(promisc));
-		}
-	} else {
-		if (local->sparm.b5.a_promiscuous_mode == 1) {
-			pr_debug("ray_cs set_multicast_list promisc off\n");
-			local->sparm.b5.a_promiscuous_mode = 0;
-			promisc = 0;
-			ray_update_parm(dev, OBJID_promiscuous_mode,
-					&promisc, sizeof(promisc));
-		}
-	}
-
-	if (dev->flags & IFF_ALLMULTI)
-		ray_update_multi_list(dev, 1);
-	else {
-		if (local->num_multi != netdev_mc_count(dev))
-			ray_update_multi_list(dev, 0);
-	}
-} /* end set_multicast_list */
-
-/*=============================================================================
- * All routines below here are run at interrupt time.
-=============================================================================*/
-static irqreturn_t ray_interrupt(int irq, void *dev_id)
-{
-	struct net_device *dev = dev_id;
-	struct pcmcia_device *link;
-	ray_dev_t *local;
-	struct ccs __iomem *pccs;
-	struct rcs __iomem *prcs;
-	UCHAR rcsindex;
-	UCHAR tmp;
-	UCHAR cmd;
-	UCHAR status;
-	UCHAR memtmp[ESSID_SIZE + 1];
-
-
-	if (dev == NULL)	/* Note that we want interrupts with dev->start == 0 */
-		return IRQ_NONE;
-
-	pr_debug("ray_cs: interrupt for *dev=%p\n", dev);
-
-	local = netdev_priv(dev);
-	link = local->finder;
-	if (!pcmcia_dev_present(link)) {
-		pr_debug(
-			"ray_cs interrupt from device not present or suspended.\n");
-		return IRQ_NONE;
-	}
-	rcsindex = readb(&((struct scb __iomem *)(local->sram))->rcs_index);
-
-	if (rcsindex >= (NUMBER_OF_CCS + NUMBER_OF_RCS)) {
-		dev_dbg(&link->dev, "ray_cs interrupt bad rcsindex = 0x%x\n", rcsindex);
-		clear_interrupt(local);
-		return IRQ_HANDLED;
-	}
-	if (rcsindex < NUMBER_OF_CCS) { /* If it's a returned CCS */
-		pccs = ccs_base(local) + rcsindex;
-		cmd = readb(&pccs->cmd);
-		status = readb(&pccs->buffer_status);
-		switch (cmd) {
-		case CCS_DOWNLOAD_STARTUP_PARAMS:	/* Happens in firmware someday */
-			del_timer(&local->timer);
-			if (status == CCS_COMMAND_COMPLETE) {
-				dev_dbg(&link->dev,
-				      "ray_cs interrupt download_startup_parameters OK\n");
-			} else {
-				dev_dbg(&link->dev,
-				      "ray_cs interrupt download_startup_parameters fail\n");
-			}
-			break;
-		case CCS_UPDATE_PARAMS:
-			dev_dbg(&link->dev, "ray_cs interrupt update params done\n");
-			if (status != CCS_COMMAND_COMPLETE) {
-				tmp =
-				    readb(&pccs->var.update_param.
-					  failure_cause);
-				dev_dbg(&link->dev,
-				      "ray_cs interrupt update params failed - reason %d\n",
-				      tmp);
-			}
-			break;
-		case CCS_REPORT_PARAMS:
-			dev_dbg(&link->dev, "ray_cs interrupt report params done\n");
-			break;
-		case CCS_UPDATE_MULTICAST_LIST:	/* Note that this CCS isn't returned */
-			dev_dbg(&link->dev,
-			      "ray_cs interrupt CCS Update Multicast List done\n");
-			break;
-		case CCS_UPDATE_POWER_SAVINGS_MODE:
-			dev_dbg(&link->dev,
-			      "ray_cs interrupt update power save mode done\n");
-			break;
-		case CCS_START_NETWORK:
-		case CCS_JOIN_NETWORK:
-			memcpy(memtmp, local->sparm.b4.a_current_ess_id,
-								ESSID_SIZE);
-			memtmp[ESSID_SIZE] = '\0';
-
-			if (status == CCS_COMMAND_COMPLETE) {
-				if (readb
-				    (&pccs->var.start_network.net_initiated) ==
-				    1) {
-					dev_dbg(&link->dev,
-					      "ray_cs interrupt network \"%s\" started\n",
-					      memtmp);
-				} else {
-					dev_dbg(&link->dev,
-					      "ray_cs interrupt network \"%s\" joined\n",
-					      memtmp);
-				}
-				memcpy_fromio(&local->bss_id,
-					      pccs->var.start_network.bssid,
-					      ADDRLEN);
-
-				if (local->fw_ver == 0x55)
-					local->net_default_tx_rate = 3;
-				else
-					local->net_default_tx_rate =
-					    readb(&pccs->var.start_network.
-						  net_default_tx_rate);
-				local->encryption =
-				    readb(&pccs->var.start_network.encryption);
-				if (!sniffer && (local->net_type == INFRA)
-				    && !(local->sparm.b4.a_acting_as_ap_status)) {
-					authenticate(local);
-				}
-				local->card_status = CARD_ACQ_COMPLETE;
-			} else {
-				local->card_status = CARD_ACQ_FAILED;
-
-				del_timer(&local->timer);
-				local->timer.expires = jiffies + HZ * 5;
-				if (status == CCS_START_NETWORK) {
-					dev_dbg(&link->dev,
-					      "ray_cs interrupt network \"%s\" start failed\n",
-					      memtmp);
-					local->timer.function = start_net;
-				} else {
-					dev_dbg(&link->dev,
-					      "ray_cs interrupt network \"%s\" join failed\n",
-					      memtmp);
-					local->timer.function = join_net;
-				}
-				add_timer(&local->timer);
-			}
-			break;
-		case CCS_START_ASSOCIATION:
-			if (status == CCS_COMMAND_COMPLETE) {
-				local->card_status = CARD_ASSOC_COMPLETE;
-				dev_dbg(&link->dev, "ray_cs association successful\n");
-			} else {
-				dev_dbg(&link->dev, "ray_cs association failed,\n");
-				local->card_status = CARD_ASSOC_FAILED;
-				join_net(&local->timer);
-			}
-			break;
-		case CCS_TX_REQUEST:
-			if (status == CCS_COMMAND_COMPLETE) {
-				dev_dbg(&link->dev,
-				      "ray_cs interrupt tx request complete\n");
-			} else {
-				dev_dbg(&link->dev,
-				      "ray_cs interrupt tx request failed\n");
-			}
-			if (!sniffer)
-				netif_start_queue(dev);
-			netif_wake_queue(dev);
-			break;
-		case CCS_TEST_MEMORY:
-			dev_dbg(&link->dev, "ray_cs interrupt mem test done\n");
-			break;
-		case CCS_SHUTDOWN:
-			dev_dbg(&link->dev,
-			      "ray_cs interrupt Unexpected CCS returned - Shutdown\n");
-			break;
-		case CCS_DUMP_MEMORY:
-			dev_dbg(&link->dev, "ray_cs interrupt dump memory done\n");
-			break;
-		case CCS_START_TIMER:
-			dev_dbg(&link->dev,
-			      "ray_cs interrupt DING - raylink timer expired\n");
-			break;
-		default:
-			dev_dbg(&link->dev,
-			      "ray_cs interrupt Unexpected CCS 0x%x returned 0x%x\n",
-			      rcsindex, cmd);
-		}
-		writeb(CCS_BUFFER_FREE, &pccs->buffer_status);
-	} else { /* It's an RCS */
-
-		prcs = rcs_base(local) + rcsindex;
-
-		switch (readb(&prcs->interrupt_id)) {
-		case PROCESS_RX_PACKET:
-			ray_rx(dev, local, prcs);
-			break;
-		case REJOIN_NET_COMPLETE:
-			dev_dbg(&link->dev, "ray_cs interrupt rejoin net complete\n");
-			local->card_status = CARD_ACQ_COMPLETE;
-			/* do we need to clear tx buffers CCS's? */
-			if (local->sparm.b4.a_network_type == ADHOC) {
-				if (!sniffer)
-					netif_start_queue(dev);
-			} else {
-				memcpy_fromio(&local->bss_id,
-					      prcs->var.rejoin_net_complete.
-					      bssid, ADDRLEN);
-				dev_dbg(&link->dev, "ray_cs new BSSID = %pm\n",
-					local->bss_id);
-				if (!sniffer)
-					authenticate(local);
-			}
-			break;
-		case ROAMING_INITIATED:
-			dev_dbg(&link->dev, "ray_cs interrupt roaming initiated\n");
-			netif_stop_queue(dev);
-			local->card_status = CARD_DOING_ACQ;
-			break;
-		case JAPAN_CALL_SIGN_RXD:
-			dev_dbg(&link->dev, "ray_cs interrupt japan call sign rx\n");
-			break;
-		default:
-			dev_dbg(&link->dev,
-			      "ray_cs Unexpected interrupt for RCS 0x%x cmd = 0x%x\n",
-			      rcsindex,
-			      (unsigned int)readb(&prcs->interrupt_id));
-			break;
-		}
-		writeb(CCS_BUFFER_FREE, &prcs->buffer_status);
-	}
-	clear_interrupt(local);
-	return IRQ_HANDLED;
-} /* ray_interrupt */
-
-/*===========================================================================*/
-static void ray_rx(struct net_device *dev, ray_dev_t *local,
-		   struct rcs __iomem *prcs)
-{
-	int rx_len;
-	unsigned int pkt_addr;
-	void __iomem *pmsg;
-	pr_debug("ray_rx process rx packet\n");
-
-	/* Calculate address of packet within Rx buffer */
-	pkt_addr = ((readb(&prcs->var.rx_packet.rx_data_ptr[0]) << 8)
-		    + readb(&prcs->var.rx_packet.rx_data_ptr[1])) & RX_BUFF_END;
-	/* Length of first packet fragment */
-	rx_len = (readb(&prcs->var.rx_packet.rx_data_length[0]) << 8)
-	    + readb(&prcs->var.rx_packet.rx_data_length[1]);
-
-	local->last_rsl = readb(&prcs->var.rx_packet.rx_sig_lev);
-	pmsg = local->rmem + pkt_addr;
-	switch (readb(pmsg)) {
-	case DATA_TYPE:
-		pr_debug("ray_rx data type\n");
-		rx_data(dev, prcs, pkt_addr, rx_len);
-		break;
-	case AUTHENTIC_TYPE:
-		pr_debug("ray_rx authentic type\n");
-		if (sniffer)
-			rx_data(dev, prcs, pkt_addr, rx_len);
-		else
-			rx_authenticate(local, prcs, pkt_addr, rx_len);
-		break;
-	case DEAUTHENTIC_TYPE:
-		pr_debug("ray_rx deauth type\n");
-		if (sniffer)
-			rx_data(dev, prcs, pkt_addr, rx_len);
-		else
-			rx_deauthenticate(local, prcs, pkt_addr, rx_len);
-		break;
-	case NULL_MSG_TYPE:
-		pr_debug("ray_cs rx NULL msg\n");
-		break;
-	case BEACON_TYPE:
-		pr_debug("ray_rx beacon type\n");
-		if (sniffer)
-			rx_data(dev, prcs, pkt_addr, rx_len);
-
-		copy_from_rx_buff(local, (UCHAR *) &local->last_bcn, pkt_addr,
-				  rx_len < sizeof(struct beacon_rx) ?
-				  rx_len : sizeof(struct beacon_rx));
-
-		local->beacon_rxed = 1;
-		/* Get the statistics so the card counters never overflow */
-		ray_get_stats(dev);
-		break;
-	default:
-		pr_debug("ray_cs unknown pkt type %2x\n",
-		      (unsigned int)readb(pmsg));
-		break;
-	}
-
-} /* end ray_rx */
-
-/*===========================================================================*/
-static void rx_data(struct net_device *dev, struct rcs __iomem *prcs,
-		    unsigned int pkt_addr, int rx_len)
-{
-	struct sk_buff *skb = NULL;
-	struct rcs __iomem *prcslink = prcs;
-	ray_dev_t *local = netdev_priv(dev);
-	UCHAR *rx_ptr;
-	int total_len;
-	int tmp;
-#ifdef WIRELESS_SPY
-	int siglev = local->last_rsl;
-	u_char linksrcaddr[ETH_ALEN];	/* Other end of the wireless link */
-#endif
-
-	if (!sniffer) {
-		if (translate) {
-/* TBD length needs fixing for translated header */
-			if (rx_len < (ETH_HLEN + RX_MAC_HEADER_LENGTH) ||
-			    rx_len >
-			    (dev->mtu + RX_MAC_HEADER_LENGTH + ETH_HLEN +
-			     FCS_LEN)) {
-				pr_debug(
-				      "ray_cs invalid packet length %d received\n",
-				      rx_len);
-				return;
-			}
-		} else { /* encapsulated ethernet */
-
-			if (rx_len < (ETH_HLEN + RX_MAC_HEADER_LENGTH) ||
-			    rx_len >
-			    (dev->mtu + RX_MAC_HEADER_LENGTH + ETH_HLEN +
-			     FCS_LEN)) {
-				pr_debug(
-				      "ray_cs invalid packet length %d received\n",
-				      rx_len);
-				return;
-			}
-		}
-	}
-	pr_debug("ray_cs rx_data packet\n");
-	/* If fragmented packet, verify sizes of fragments add up */
-	if (readb(&prcs->var.rx_packet.next_frag_rcs_index) != 0xFF) {
-		pr_debug("ray_cs rx'ed fragment\n");
-		tmp = (readb(&prcs->var.rx_packet.totalpacketlength[0]) << 8)
-		    + readb(&prcs->var.rx_packet.totalpacketlength[1]);
-		total_len = tmp;
-		prcslink = prcs;
-		do {
-			tmp -=
-			    (readb(&prcslink->var.rx_packet.rx_data_length[0])
-			     << 8)
-			    + readb(&prcslink->var.rx_packet.rx_data_length[1]);
-			if (readb(&prcslink->var.rx_packet.next_frag_rcs_index)
-			    == 0xFF || tmp < 0)
-				break;
-			prcslink = rcs_base(local)
-			    + readb(&prcslink->link_field);
-		} while (1);
-
-		if (tmp < 0) {
-			pr_debug(
-			      "ray_cs rx_data fragment lengths don't add up\n");
-			local->stats.rx_dropped++;
-			release_frag_chain(local, prcs);
-			return;
-		}
-	} else { /* Single unfragmented packet */
-		total_len = rx_len;
-	}
-
-	skb = dev_alloc_skb(total_len + 5);
-	if (skb == NULL) {
-		pr_debug("ray_cs rx_data could not allocate skb\n");
-		local->stats.rx_dropped++;
-		if (readb(&prcs->var.rx_packet.next_frag_rcs_index) != 0xFF)
-			release_frag_chain(local, prcs);
-		return;
-	}
-	skb_reserve(skb, 2);	/* Align IP on 16 byte (TBD check this) */
-
-	pr_debug("ray_cs rx_data total_len = %x, rx_len = %x\n", total_len,
-	      rx_len);
-
-/************************/
-	/* Reserve enough room for the whole damn packet. */
-	rx_ptr = skb_put(skb, total_len);
-	/* Copy the whole packet to sk_buff */
-	rx_ptr +=
-	    copy_from_rx_buff(local, rx_ptr, pkt_addr & RX_BUFF_END, rx_len);
-	/* Get source address */
-#ifdef WIRELESS_SPY
-	skb_copy_from_linear_data_offset(skb,
-					 offsetof(struct mac_header, addr_2),
-					 linksrcaddr, ETH_ALEN);
-#endif
-	/* Now, deal with encapsulation/translation/sniffer */
-	if (!sniffer) {
-		if (!translate) {
-			/* Encapsulated ethernet, so just lop off 802.11 MAC header */
-/* TBD reserve            skb_reserve( skb, RX_MAC_HEADER_LENGTH); */
-			skb_pull(skb, RX_MAC_HEADER_LENGTH);
-		} else {
-			/* Do translation */
-			untranslate(local, skb, total_len);
-		}
-	} else { /* sniffer mode, so just pass whole packet */
-	}
-
-/************************/
-	/* Now pick up the rest of the fragments if any */
-	tmp = 17;
-	if (readb(&prcs->var.rx_packet.next_frag_rcs_index) != 0xFF) {
-		prcslink = prcs;
-		pr_debug("ray_cs rx_data in fragment loop\n");
-		do {
-			prcslink = rcs_base(local)
-			    +
-			    readb(&prcslink->var.rx_packet.next_frag_rcs_index);
-			rx_len =
-			    ((readb(&prcslink->var.rx_packet.rx_data_length[0])
-			      << 8)
-			     +
-			     readb(&prcslink->var.rx_packet.rx_data_length[1]))
-			    & RX_BUFF_END;
-			pkt_addr =
-			    ((readb(&prcslink->var.rx_packet.rx_data_ptr[0]) <<
-			      8)
-			     + readb(&prcslink->var.rx_packet.rx_data_ptr[1]))
-			    & RX_BUFF_END;
-
-			rx_ptr +=
-			    copy_from_rx_buff(local, rx_ptr, pkt_addr, rx_len);
-
-		} while (tmp-- &&
-			 readb(&prcslink->var.rx_packet.next_frag_rcs_index) !=
-			 0xFF);
-		release_frag_chain(local, prcs);
-	}
-
-	skb->protocol = eth_type_trans(skb, dev);
-	netif_rx(skb);
-	local->stats.rx_packets++;
-	local->stats.rx_bytes += total_len;
-
-	/* Gather signal strength per address */
-#ifdef WIRELESS_SPY
-	/* For the Access Point or the node having started the ad-hoc net
-	 * note : ad-hoc work only in some specific configurations, but we
-	 * kludge in ray_get_wireless_stats... */
-	if (!memcmp(linksrcaddr, local->bss_id, ETH_ALEN)) {
-		/* Update statistics */
-		/*local->wstats.qual.qual = none ? */
-		local->wstats.qual.level = siglev;
-		/*local->wstats.qual.noise = none ? */
-		local->wstats.qual.updated = 0x2;
-	}
-	/* Now, update the spy stuff */
-	{
-		struct iw_quality wstats;
-		wstats.level = siglev;
-		/* wstats.noise = none ? */
-		/* wstats.qual = none ? */
-		wstats.updated = 0x2;
-		/* Update spy records */
-		wireless_spy_update(dev, linksrcaddr, &wstats);
-	}
-#endif /* WIRELESS_SPY */
-} /* end rx_data */
-
-/*===========================================================================*/
-static void untranslate(ray_dev_t *local, struct sk_buff *skb, int len)
-{
-	snaphdr_t *psnap = (snaphdr_t *) (skb->data + RX_MAC_HEADER_LENGTH);
-	struct ieee80211_hdr *pmac = (struct ieee80211_hdr *)skb->data;
-	__be16 type = *(__be16 *) psnap->ethertype;
-	int delta;
-	struct ethhdr *peth;
-	UCHAR srcaddr[ADDRLEN];
-	UCHAR destaddr[ADDRLEN];
-	static const UCHAR org_bridge[3] = { 0, 0, 0xf8 };
-	static const UCHAR org_1042[3] = { 0, 0, 0 };
-
-	memcpy(destaddr, ieee80211_get_DA(pmac), ADDRLEN);
-	memcpy(srcaddr, ieee80211_get_SA(pmac), ADDRLEN);
-
-#if 0
-	if {
-		print_hex_dump(KERN_DEBUG, "skb->data before untranslate: ",
-			       DUMP_PREFIX_NONE, 16, 1,
-			       skb->data, 64, true);
-		printk(KERN_DEBUG
-		       "type = %08x, xsap = %02x%02x%02x, org = %02x02x02x\n",
-		       ntohs(type), psnap->dsap, psnap->ssap, psnap->ctrl,
-		       psnap->org[0], psnap->org[1], psnap->org[2]);
-		printk(KERN_DEBUG "untranslate skb->data = %p\n", skb->data);
-	}
-#endif
-
-	if (psnap->dsap != 0xaa || psnap->ssap != 0xaa || psnap->ctrl != 3) {
-		/* not a snap type so leave it alone */
-		pr_debug("ray_cs untranslate NOT SNAP %02x %02x %02x\n",
-		      psnap->dsap, psnap->ssap, psnap->ctrl);
-
-		delta = RX_MAC_HEADER_LENGTH - ETH_HLEN;
-		peth = (struct ethhdr *)(skb->data + delta);
-		peth->h_proto = htons(len - RX_MAC_HEADER_LENGTH);
-	} else { /* Its a SNAP */
-		if (memcmp(psnap->org, org_bridge, 3) == 0) {
-		/* EtherII and nuke the LLC */
-			pr_debug("ray_cs untranslate Bridge encap\n");
-			delta = RX_MAC_HEADER_LENGTH
-			    + sizeof(struct snaphdr_t) - ETH_HLEN;
-			peth = (struct ethhdr *)(skb->data + delta);
-			peth->h_proto = type;
-		} else if (memcmp(psnap->org, org_1042, 3) == 0) {
-			switch (ntohs(type)) {
-			case ETH_P_IPX:
-			case ETH_P_AARP:
-				pr_debug("ray_cs untranslate RFC IPX/AARP\n");
-				delta = RX_MAC_HEADER_LENGTH - ETH_HLEN;
-				peth = (struct ethhdr *)(skb->data + delta);
-				peth->h_proto =
-				    htons(len - RX_MAC_HEADER_LENGTH);
-				break;
-			default:
-				pr_debug("ray_cs untranslate RFC default\n");
-				delta = RX_MAC_HEADER_LENGTH +
-				    sizeof(struct snaphdr_t) - ETH_HLEN;
-				peth = (struct ethhdr *)(skb->data + delta);
-				peth->h_proto = type;
-				break;
-			}
-		} else {
-			printk("ray_cs untranslate very confused by packet\n");
-			delta = RX_MAC_HEADER_LENGTH - ETH_HLEN;
-			peth = (struct ethhdr *)(skb->data + delta);
-			peth->h_proto = type;
-		}
-	}
-/* TBD reserve  skb_reserve(skb, delta); */
-	skb_pull(skb, delta);
-	pr_debug("untranslate after skb_pull(%d), skb->data = %p\n", delta,
-	      skb->data);
-	memcpy(peth->h_dest, destaddr, ADDRLEN);
-	memcpy(peth->h_source, srcaddr, ADDRLEN);
-#if 0
-	{
-		int i;
-		printk(KERN_DEBUG "skb->data after untranslate:");
-		for (i = 0; i < 64; i++)
-			printk("%02x ", skb->data[i]);
-		printk("\n");
-	}
-#endif
-} /* end untranslate */
-
-/*===========================================================================*/
-/* Copy data from circular receive buffer to PC memory.
- * dest     = destination address in PC memory
- * pkt_addr = source address in receive buffer
- * len      = length of packet to copy
- */
-static int copy_from_rx_buff(ray_dev_t *local, UCHAR *dest, int pkt_addr,
-			     int length)
-{
-	int wrap_bytes = (pkt_addr + length) - (RX_BUFF_END + 1);
-	if (wrap_bytes <= 0) {
-		memcpy_fromio(dest, local->rmem + pkt_addr, length);
-	} else { /* Packet wrapped in circular buffer */
-
-		memcpy_fromio(dest, local->rmem + pkt_addr,
-			      length - wrap_bytes);
-		memcpy_fromio(dest + length - wrap_bytes, local->rmem,
-			      wrap_bytes);
-	}
-	return length;
-}
-
-/*===========================================================================*/
-static void release_frag_chain(ray_dev_t *local, struct rcs __iomem *prcs)
-{
-	struct rcs __iomem *prcslink = prcs;
-	int tmp = 17;
-	unsigned rcsindex = readb(&prcs->var.rx_packet.next_frag_rcs_index);
-
-	while (tmp--) {
-		writeb(CCS_BUFFER_FREE, &prcslink->buffer_status);
-		if (rcsindex >= (NUMBER_OF_CCS + NUMBER_OF_RCS)) {
-			pr_debug("ray_cs interrupt bad rcsindex = 0x%x\n",
-			      rcsindex);
-			break;
-		}
-		prcslink = rcs_base(local) + rcsindex;
-		rcsindex = readb(&prcslink->var.rx_packet.next_frag_rcs_index);
-	}
-	writeb(CCS_BUFFER_FREE, &prcslink->buffer_status);
-}
-
-/*===========================================================================*/
-static void authenticate(ray_dev_t *local)
-{
-	struct pcmcia_device *link = local->finder;
-	dev_dbg(&link->dev, "ray_cs Starting authentication.\n");
-	if (!(pcmcia_dev_present(link))) {
-		dev_dbg(&link->dev, "ray_cs authenticate - device not present\n");
-		return;
-	}
-
-	del_timer(&local->timer);
-	if (build_auth_frame(local, local->bss_id, OPEN_AUTH_REQUEST)) {
-		local->timer.function = join_net;
-	} else {
-		local->timer.function = authenticate_timeout;
-	}
-	local->timer.expires = jiffies + HZ * 2;
-	add_timer(&local->timer);
-	local->authentication_state = AWAITING_RESPONSE;
-} /* end authenticate */
-
-/*===========================================================================*/
-static void rx_authenticate(ray_dev_t *local, struct rcs __iomem *prcs,
-			    unsigned int pkt_addr, int rx_len)
-{
-	UCHAR buff[256];
-	struct ray_rx_msg *msg = (struct ray_rx_msg *) buff;
-
-	del_timer(&local->timer);
-
-	copy_from_rx_buff(local, buff, pkt_addr, rx_len & 0xff);
-	/* if we are trying to get authenticated */
-	if (local->sparm.b4.a_network_type == ADHOC) {
-		pr_debug("ray_cs rx_auth var= %6ph\n", msg->var);
-		if (msg->var[2] == 1) {
-			pr_debug("ray_cs Sending authentication response.\n");
-			if (!build_auth_frame
-			    (local, msg->mac.addr_2, OPEN_AUTH_RESPONSE)) {
-				local->authentication_state = NEED_TO_AUTH;
-				memcpy(local->auth_id, msg->mac.addr_2,
-				       ADDRLEN);
-			}
-		}
-	} else { /* Infrastructure network */
-
-		if (local->authentication_state == AWAITING_RESPONSE) {
-			/* Verify authentication sequence #2 and success */
-			if (msg->var[2] == 2) {
-				if ((msg->var[3] | msg->var[4]) == 0) {
-					pr_debug("Authentication successful\n");
-					local->card_status = CARD_AUTH_COMPLETE;
-					associate(local);
-					local->authentication_state =
-					    AUTHENTICATED;
-				} else {
-					pr_debug("Authentication refused\n");
-					local->card_status = CARD_AUTH_REFUSED;
-					join_net(&local->timer);
-					local->authentication_state =
-					    UNAUTHENTICATED;
-				}
-			}
-		}
-	}
-
-} /* end rx_authenticate */
-
-/*===========================================================================*/
-static void associate(ray_dev_t *local)
-{
-	struct ccs __iomem *pccs;
-	struct pcmcia_device *link = local->finder;
-	struct net_device *dev = link->priv;
-	int ccsindex;
-	if (!(pcmcia_dev_present(link))) {
-		dev_dbg(&link->dev, "ray_cs associate - device not present\n");
-		return;
-	}
-	/* If no tx buffers available, return */
-	if ((ccsindex = get_free_ccs(local)) < 0) {
-/* TBD should never be here but... what if we are? */
-		dev_dbg(&link->dev, "ray_cs associate - No free ccs\n");
-		return;
-	}
-	dev_dbg(&link->dev, "ray_cs Starting association with access point\n");
-	pccs = ccs_base(local) + ccsindex;
-	/* fill in the CCS */
-	writeb(CCS_START_ASSOCIATION, &pccs->cmd);
-	/* Interrupt the firmware to process the command */
-	if (interrupt_ecf(local, ccsindex)) {
-		dev_dbg(&link->dev, "ray_cs associate failed - ECF not ready for intr\n");
-		writeb(CCS_BUFFER_FREE, &(pccs++)->buffer_status);
-
-		del_timer(&local->timer);
-		local->timer.expires = jiffies + HZ * 2;
-		local->timer.function = join_net;
-		add_timer(&local->timer);
-		local->card_status = CARD_ASSOC_FAILED;
-		return;
-	}
-	if (!sniffer)
-		netif_start_queue(dev);
-
-} /* end associate */
-
-/*===========================================================================*/
-static void rx_deauthenticate(ray_dev_t *local, struct rcs __iomem *prcs,
-			      unsigned int pkt_addr, int rx_len)
-{
-/*  UCHAR buff[256];
-    struct ray_rx_msg *msg = (struct ray_rx_msg *) buff;
-*/
-	pr_debug("Deauthentication frame received\n");
-	local->authentication_state = UNAUTHENTICATED;
-	/* Need to reauthenticate or rejoin depending on reason code */
-/*  copy_from_rx_buff(local, buff, pkt_addr, rx_len & 0xff);
- */
-}
-
-/*===========================================================================*/
-static void clear_interrupt(ray_dev_t *local)
-{
-	writeb(0, local->amem + CIS_OFFSET + HCS_INTR_OFFSET);
-}
-
-/*===========================================================================*/
-#ifdef CONFIG_PROC_FS
-#define MAXDATA (PAGE_SIZE - 80)
-
-static const char *card_status[] = {
-	"Card inserted - uninitialized",	/* 0 */
-	"Card not downloaded",			/* 1 */
-	"Waiting for download parameters",	/* 2 */
-	"Card doing acquisition",		/* 3 */
-	"Acquisition complete",			/* 4 */
-	"Authentication complete",		/* 5 */
-	"Association complete",			/* 6 */
-	"???", "???", "???", "???",		/* 7 8 9 10 undefined */
-	"Card init error",			/* 11 */
-	"Download parameters error",		/* 12 */
-	"???",					/* 13 */
-	"Acquisition failed",			/* 14 */
-	"Authentication refused",		/* 15 */
-	"Association failed"			/* 16 */
-};
-
-static const char *nettype[] = { "Adhoc", "Infra " };
-static const char *framing[] = { "Encapsulation", "Translation" }
-
-;
-/*===========================================================================*/
-static int ray_cs_proc_show(struct seq_file *m, void *v)
-{
-/* Print current values which are not available via other means
- * eg ifconfig
- */
-	int i;
-	struct pcmcia_device *link;
-	struct net_device *dev;
-	ray_dev_t *local;
-	UCHAR *p;
-	struct freq_hop_element *pfh;
-	UCHAR c[33];
-
-	link = this_device;
-	if (!link)
-		return 0;
-	dev = link->priv;
-	if (!dev)
-		return 0;
-	local = netdev_priv(dev);
-	if (!local)
-		return 0;
-
-	seq_puts(m, "Raylink Wireless LAN driver status\n");
-	seq_printf(m, "%s\n", rcsid);
-	/* build 4 does not report version, and field is 0x55 after memtest */
-	seq_puts(m, "Firmware version     = ");
-	if (local->fw_ver == 0x55)
-		seq_puts(m, "4 - Use dump_cis for more details\n");
-	else
-		seq_printf(m, "%2d.%02d.%02d\n",
-			   local->fw_ver, local->fw_bld, local->fw_var);
-
-	for (i = 0; i < 32; i++)
-		c[i] = local->sparm.b5.a_current_ess_id[i];
-	c[32] = 0;
-	seq_printf(m, "%s network ESSID = \"%s\"\n",
-		   nettype[local->sparm.b5.a_network_type], c);
-
-	p = local->bss_id;
-	seq_printf(m, "BSSID                = %pM\n", p);
-
-	seq_printf(m, "Country code         = %d\n",
-		   local->sparm.b5.a_curr_country_code);
-
-	i = local->card_status;
-	if (i < 0)
-		i = 10;
-	if (i > 16)
-		i = 10;
-	seq_printf(m, "Card status          = %s\n", card_status[i]);
-
-	seq_printf(m, "Framing mode         = %s\n", framing[translate]);
-
-	seq_printf(m, "Last pkt signal lvl  = %d\n", local->last_rsl);
-
-	if (local->beacon_rxed) {
-		/* Pull some fields out of last beacon received */
-		seq_printf(m, "Beacon Interval      = %d Kus\n",
-			   local->last_bcn.beacon_intvl[0]
-			   + 256 * local->last_bcn.beacon_intvl[1]);
-
-		p = local->last_bcn.elements;
-		if (p[0] == C_ESSID_ELEMENT_ID)
-			p += p[1] + 2;
-		else {
-			seq_printf(m,
-				   "Parse beacon failed at essid element id = %d\n",
-				   p[0]);
-			return 0;
-		}
-
-		if (p[0] == C_SUPPORTED_RATES_ELEMENT_ID) {
-			seq_puts(m, "Supported rate codes = ");
-			for (i = 2; i < p[1] + 2; i++)
-				seq_printf(m, "0x%02x ", p[i]);
-			seq_putc(m, '\n');
-			p += p[1] + 2;
-		} else {
-			seq_puts(m, "Parse beacon failed at rates element\n");
-			return 0;
-		}
-
-		if (p[0] == C_FH_PARAM_SET_ELEMENT_ID) {
-			pfh = (struct freq_hop_element *)p;
-			seq_printf(m, "Hop dwell            = %d Kus\n",
-				   pfh->dwell_time[0] +
-				   256 * pfh->dwell_time[1]);
-			seq_printf(m, "Hop set              = %d\n",
-				   pfh->hop_set);
-			seq_printf(m, "Hop pattern          = %d\n",
-				   pfh->hop_pattern);
-			seq_printf(m, "Hop index            = %d\n",
-				   pfh->hop_index);
-			p += p[1] + 2;
-		} else {
-			seq_puts(m,
-				 "Parse beacon failed at FH param element\n");
-			return 0;
-		}
-	} else {
-		seq_puts(m, "No beacons received\n");
-	}
-	return 0;
-}
-#endif
-/*===========================================================================*/
-static int build_auth_frame(ray_dev_t *local, UCHAR *dest, int auth_type)
-{
-	int addr;
-	struct ccs __iomem *pccs;
-	struct tx_msg __iomem *ptx;
-	int ccsindex;
-
-	/* If no tx buffers available, return */
-	if ((ccsindex = get_free_tx_ccs(local)) < 0) {
-		pr_debug("ray_cs send authenticate - No free tx ccs\n");
-		return -1;
-	}
-
-	pccs = ccs_base(local) + ccsindex;
-
-	/* Address in card space */
-	addr = TX_BUF_BASE + (ccsindex << 11);
-	/* fill in the CCS */
-	writeb(CCS_TX_REQUEST, &pccs->cmd);
-	writeb(addr >> 8, pccs->var.tx_request.tx_data_ptr);
-	writeb(0x20, pccs->var.tx_request.tx_data_ptr + 1);
-	writeb(TX_AUTHENTICATE_LENGTH_MSB, pccs->var.tx_request.tx_data_length);
-	writeb(TX_AUTHENTICATE_LENGTH_LSB,
-	       pccs->var.tx_request.tx_data_length + 1);
-	writeb(0, &pccs->var.tx_request.pow_sav_mode);
-
-	ptx = local->sram + addr;
-	/* fill in the mac header */
-	writeb(PROTOCOL_VER | AUTHENTIC_TYPE, &ptx->mac.frame_ctl_1);
-	writeb(0, &ptx->mac.frame_ctl_2);
-
-	memcpy_toio(ptx->mac.addr_1, dest, ADDRLEN);
-	memcpy_toio(ptx->mac.addr_2, local->sparm.b4.a_mac_addr, ADDRLEN);
-	memcpy_toio(ptx->mac.addr_3, local->bss_id, ADDRLEN);
-
-	/* Fill in msg body with protocol 00 00, sequence 01 00 ,status 00 00 */
-	memset_io(ptx->var, 0, 6);
-	writeb(auth_type & 0xff, ptx->var + 2);
-
-	/* Interrupt the firmware to process the command */
-	if (interrupt_ecf(local, ccsindex)) {
-		pr_debug(
-		      "ray_cs send authentication request failed - ECF not ready for intr\n");
-		writeb(CCS_BUFFER_FREE, &(pccs++)->buffer_status);
-		return -1;
-	}
-	return 0;
-} /* End build_auth_frame */
-
-/*===========================================================================*/
-#ifdef CONFIG_PROC_FS
-static ssize_t ray_cs_essid_proc_write(struct file *file,
-		const char __user *buffer, size_t count, loff_t *pos)
-{
-	static char proc_essid[33];
-	unsigned int len = count;
-
-	if (len > 32)
-		len = 32;
-	memset(proc_essid, 0, 33);
-	if (copy_from_user(proc_essid, buffer, len))
-		return -EFAULT;
-	essid = proc_essid;
-	return count;
-}
-
-static const struct proc_ops ray_cs_essid_proc_ops = {
-	.proc_write	= ray_cs_essid_proc_write,
-	.proc_lseek	= noop_llseek,
-};
-
-static ssize_t int_proc_write(struct file *file, const char __user *buffer,
-			      size_t count, loff_t *pos)
-{
-	static char proc_number[10];
-	char *p;
-	int nr, len;
-
-	if (!count)
-		return 0;
-
-	if (count > 9)
-		return -EINVAL;
-	if (copy_from_user(proc_number, buffer, count))
-		return -EFAULT;
-	p = proc_number;
-	nr = 0;
-	len = count;
-	do {
-		unsigned int c = *p - '0';
-		if (c > 9)
-			return -EINVAL;
-		nr = nr * 10 + c;
-		p++;
-	} while (--len);
-	*(int *)pde_data(file_inode(file)) = nr;
-	return count;
-}
-
-static const struct proc_ops int_proc_ops = {
-	.proc_write	= int_proc_write,
-	.proc_lseek	= noop_llseek,
-};
-#endif
-
-static const struct pcmcia_device_id ray_ids[] = {
-	PCMCIA_DEVICE_MANF_CARD(0x01a6, 0x0000),
-	PCMCIA_DEVICE_NULL,
-};
-
-MODULE_DEVICE_TABLE(pcmcia, ray_ids);
-
-static struct pcmcia_driver ray_driver = {
-	.owner = THIS_MODULE,
-	.name = "ray_cs",
-	.probe = ray_probe,
-	.remove = ray_detach,
-	.id_table = ray_ids,
-	.suspend = ray_suspend,
-	.resume = ray_resume,
-};
-
-static int __init init_ray_cs(void)
-{
-	int rc;
-
-	pr_debug("%s\n", rcsid);
-	rc = pcmcia_register_driver(&ray_driver);
-	pr_debug("raylink init_module register_pcmcia_driver returns 0x%x\n",
-	      rc);
-	if (rc)
-		return rc;
-
-#ifdef CONFIG_PROC_FS
-	proc_mkdir("driver/ray_cs", NULL);
-
-	proc_create_single("driver/ray_cs/ray_cs", 0, NULL, ray_cs_proc_show);
-	proc_create("driver/ray_cs/essid", 0200, NULL, &ray_cs_essid_proc_ops);
-	proc_create_data("driver/ray_cs/net_type", 0200, NULL, &int_proc_ops,
-			 &net_type);
-	proc_create_data("driver/ray_cs/translate", 0200, NULL, &int_proc_ops,
-			 &translate);
-#endif
-	translate = !!translate;
-	return 0;
-} /* init_ray_cs */
-
-/*===========================================================================*/
-
-static void __exit exit_ray_cs(void)
-{
-	pr_debug("ray_cs: cleanup_module\n");
-
-#ifdef CONFIG_PROC_FS
-	remove_proc_subtree("driver/ray_cs", NULL);
-#endif
-
-	pcmcia_unregister_driver(&ray_driver);
-} /* exit_ray_cs */
-
-module_init(init_ray_cs);
-module_exit(exit_ray_cs);
-
-/*===========================================================================*/
diff --git a/drivers/net/wireless/legacy/ray_cs.h b/drivers/net/wireless/legacy/ray_cs.h
deleted file mode 100644
index 0609d8625019..000000000000
--- a/drivers/net/wireless/legacy/ray_cs.h
+++ /dev/null
@@ -1,74 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Raytheon wireless LAN PCMCIA card driver for Linux 
-   A  PCMCIA client driver for the Raylink wireless network card
-   Written by Corey Thomas
-*/
-
-#ifndef _RAY_CS_H_
-#define _RAY_CS_H_
-
-struct beacon_rx {
-    struct mac_header mac;
-    UCHAR timestamp[8];
-    UCHAR beacon_intvl[2];
-    UCHAR capability[2];
-    UCHAR elements[sizeof(struct essid_element) 
-                  + sizeof(struct rates_element)
-                  + sizeof(struct freq_hop_element) 
-                  + sizeof(struct japan_call_sign_element)
-                  + sizeof(struct tim_element)];
-};
-
-/* Return values for get_free{,_tx}_ccs */
-#define ECCSFULL  (-1)
-#define ECCSBUSY  (-2)
-#define ECARDGONE (-3)
-
-typedef struct ray_dev_t {
-    int card_status;
-    int authentication_state;
-    void __iomem *sram;            /* pointer to beginning of shared RAM     */
-    void __iomem *amem;            /* pointer to attribute mem window        */
-    void __iomem *rmem;            /* pointer to receive buffer window       */
-    struct pcmcia_device *finder;            /* pointer back to struct pcmcia_device for card    */
-    struct timer_list timer;
-    unsigned long tx_ccs_lock;
-    unsigned long ccs_lock;
-    int   dl_param_ccs;
-    union {
-        struct b4_startup_params b4;
-        struct b5_startup_params b5;
-    } sparm;
-    int timeout_flag;
-    UCHAR supported_rates[8];
-    UCHAR japan_call_sign[12];
-    struct startup_res_6 startup_res;
-    int num_multi;
-    /* Network parameters from start/join */
-    UCHAR bss_id[6];
-    UCHAR auth_id[6];
-    UCHAR net_default_tx_rate;
-    UCHAR encryption;
-    struct net_device_stats stats;
-
-    UCHAR net_type;
-    UCHAR sta_type;
-    UCHAR fw_ver;
-    UCHAR fw_bld;
-    UCHAR fw_var;
-    UCHAR ASIC_version;
-    UCHAR assoc_id[2];
-    UCHAR tib_length;
-    UCHAR last_rsl;
-    int beacon_rxed;
-    struct beacon_rx last_bcn;
-    iw_stats	wstats;		/* Wireless specific stats */
-#ifdef WIRELESS_SPY
-    struct iw_spy_data		spy_data;
-    struct iw_public_data	wireless_data;
-#endif	/* WIRELESS_SPY */
-
-} ray_dev_t;
-/*****************************************************************************/
-
-#endif /* _RAY_CS_H_ */
diff --git a/drivers/net/wireless/legacy/rayctl.h b/drivers/net/wireless/legacy/rayctl.h
deleted file mode 100644
index 1f3bde8ac73d..000000000000
--- a/drivers/net/wireless/legacy/rayctl.h
+++ /dev/null
@@ -1,734 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _RAYCTL_H_
-#define _RAYCTL_H_
-
-typedef unsigned char UCHAR;
-
-/****** IEEE 802.11 constants ************************************************/
-#define ADDRLEN           6
-/* Frame control 1 bit fields */
-#define PROTOCOL_VER      0x00
-#define DATA_TYPE         0x08
-#define ASSOC_REQ_TYPE    0x00
-#define ASSOC_RESP_TYPE   0x10
-#define REASSOC_REQ_TYPE  0x20
-#define REASSOC_RESP_TYPE 0x30
-#define NULL_MSG_TYPE     0x48
-#define BEACON_TYPE       0x80
-#define DISASSOC_TYPE     0xA0
-#define PSPOLL_TYPE       0xA4
-#define AUTHENTIC_TYPE    0xB0
-#define DEAUTHENTIC_TYPE  0xC0
-/* Frame control 2 bit fields */
-#define FC2_TO_DS         0x01
-#define FC2_FROM_DS       0x02
-#define FC2_MORE_FRAG     0x04
-#define FC2_RETRY         0x08
-#define FC2_PSM           0x10
-#define FC2_MORE_DATA     0x20
-#define FC2_WEP           0x40
-#define FC2_ORDER         0x80
-/*****************************************************************************/
-/* 802.11 element ID's and lengths */
-#define C_BP_CAPABILITY_ESS             0x01
-#define C_BP_CAPABILITY_IBSS            0x02
-#define C_BP_CAPABILITY_CF_POLLABLE     0x04
-#define C_BP_CAPABILITY_CF_POLL_REQUEST 0x08
-#define C_BP_CAPABILITY_PRIVACY         0x10
-
-#define C_ESSID_ELEMENT_ID               0
-#define C_ESSID_ELEMENT_MAX_LENGTH       32
-
-#define C_SUPPORTED_RATES_ELEMENT_ID     1
-#define C_SUPPORTED_RATES_ELEMENT_LENGTH 2
-
-#define C_FH_PARAM_SET_ELEMENT_ID        2
-#define C_FH_PARAM_SET_ELEMENT_LNGTH     5
-
-#define C_CF_PARAM_SET_ELEMENT_ID        4
-#define C_CF_PARAM_SET_ELEMENT_LNGTH     6
-
-#define C_TIM_ELEMENT_ID                 5
-#define C_TIM_BITMAP_LENGTH            251
-#define C_TIM_BMCAST_BIT              0x01
-
-#define C_IBSS_ELEMENT_ID                6
-#define C_IBSS_ELEMENT_LENGTH            2
-
-#define C_JAPAN_CALL_SIGN_ELEMENT_ID    51
-#define C_JAPAN_CALL_SIGN_ELEMENT_LNGTH 12
-
-#define C_DISASSOC_REASON_CODE_LEN       2
-#define C_DISASSOC_REASON_CODE_DEFAULT   8
-
-#define C_CRC_LEN                        4
-#define C_NUM_SUPPORTED_RATES            8 
-/****** IEEE 802.11 mac header for type data packets *************************/
-struct mac_header {
-  UCHAR frame_ctl_1;                          
-  UCHAR frame_ctl_2;
-  UCHAR duration_lsb;
-  UCHAR duration_msb;
-  UCHAR addr_1[ADDRLEN];
-  UCHAR addr_2[ADDRLEN];
-  UCHAR addr_3[ADDRLEN];
-  UCHAR seq_frag_num[2];
-/*  UCHAR addr_4[ADDRLEN]; *//* only present for AP to AP (TO DS and FROM DS */
-};
-/****** IEEE 802.11 frame element structures *********************************/
-struct essid_element
-{
-  UCHAR id;
-  UCHAR length;
-  UCHAR text[C_ESSID_ELEMENT_MAX_LENGTH];
-};
-struct rates_element
-{
-  UCHAR id;
-  UCHAR length;
-  UCHAR value[8];
-};
-struct freq_hop_element
-{
-  UCHAR id;
-  UCHAR length;
-  UCHAR dwell_time[2];
-  UCHAR hop_set;
-  UCHAR hop_pattern;
-  UCHAR hop_index;
-};
-struct tim_element
-{
-  UCHAR id;
-  UCHAR length;
-  UCHAR dtim_count;
-  UCHAR dtim_period;    
-  UCHAR bitmap_control;
-  UCHAR tim[C_TIM_BITMAP_LENGTH];
-};
-struct ibss_element
-{
-  UCHAR id;
-  UCHAR length;
-  UCHAR atim_window[2];
-};
-struct japan_call_sign_element
-{
-  UCHAR id;
-  UCHAR length;
-  UCHAR call_sign[12];
-};
-/****** Beacon message structures ********************************************/
-/* .elements is a large lump of max size because elements are variable size  */
-struct infra_beacon
-{
-    UCHAR timestamp[8];
-    UCHAR beacon_intvl[2];
-    UCHAR capability[2];
-    UCHAR elements[sizeof(struct essid_element) 
-                  + sizeof(struct rates_element)
-                  + sizeof(struct freq_hop_element) 
-                  + sizeof(struct japan_call_sign_element)
-                  + sizeof(struct tim_element)];
-};
-struct adhoc_beacon
-{
-    UCHAR timestamp[8];
-    UCHAR beacon_intvl[2];
-    UCHAR capability[2];
-    UCHAR elements[sizeof(struct essid_element) 
-                  + sizeof(struct rates_element)
-                  + sizeof(struct freq_hop_element) 
-                  + sizeof(struct japan_call_sign_element)
-                  + sizeof(struct ibss_element)];
-};
-/*****************************************************************************/
-/*****************************************************************************/
-/* #define C_MAC_HDR_2_WEP 0x40 */
-/* TX/RX CCS constants */
-#define TX_HEADER_LENGTH 0x1C
-#define RX_MAC_HEADER_LENGTH 0x18
-#define TX_AUTHENTICATE_LENGTH (TX_HEADER_LENGTH + 6)
-#define TX_AUTHENTICATE_LENGTH_MSB (TX_AUTHENTICATE_LENGTH >> 8)
-#define TX_AUTHENTICATE_LENGTH_LSB (TX_AUTHENTICATE_LENGTH & 0xff)
-#define TX_DEAUTHENTICATE_LENGTH (TX_HEADER_LENGTH + 2)
-#define TX_DEAUTHENTICATE_LENGTH_MSB (TX_AUTHENTICATE_LENGTH >> 8)
-#define TX_DEAUTHENTICATE_LENGTH_LSB (TX_AUTHENTICATE_LENGTH & 0xff)
-#define FCS_LEN           4
-
-#define ADHOC                 0
-#define INFRA                 1
-
-#define TYPE_STA              0
-#define TYPE_AP               1
-
-#define PASSIVE_SCAN          1
-#define ACTIVE_SCAN           1
-
-#define PSM_CAM               0
-
-/* Country codes */
-#define USA                   1
-#define EUROPE                2
-#define JAPAN                 3
-#define KOREA                 4
-#define SPAIN                 5
-#define FRANCE                6
-#define ISRAEL                7
-#define AUSTRALIA             8
-#define JAPAN_TEST            9
-
-/* Hop pattern lengths */
-#define USA_HOP_MOD          79 
-#define EUROPE_HOP_MOD       79 
-#define JAPAN_HOP_MOD        23
-#define KOREA_HOP_MOD        23
-#define SPAIN_HOP_MOD        27
-#define FRANCE_HOP_MOD       35
-#define ISRAEL_HOP_MOD       35
-#define AUSTRALIA_HOP_MOD    47
-#define JAPAN_TEST_HOP_MOD   23
-
-#define ESSID_SIZE           32
-/**********************************************************************/
-/* CIS Register Constants */
-#define CIS_OFFSET             0x0f00
-/* Configuration Option Register (0x0F00) */
-#define COR_OFFSET             0x00
-#define COR_SOFT_RESET         0x80
-#define COR_LEVEL_IRQ          0x40
-#define COR_CONFIG_NUM         0x01
-#define COR_DEFAULT            (COR_LEVEL_IRQ | COR_CONFIG_NUM)
-
-/* Card Configuration and Status Register (0x0F01) */
-#define CCSR_OFFSET            0x01
-#define CCSR_HOST_INTR_PENDING 0x01
-#define CCSR_POWER_DOWN        0x04
-
-/* HCS Interrupt Register (0x0F05) */
-#define HCS_INTR_OFFSET        0x05
-/* #define HCS_INTR_OFFSET        0x0A */
-#define HCS_INTR_CLEAR         0x00
-
-/* ECF Interrupt Register (0x0F06) */
-#define ECF_INTR_OFFSET        0x06
-/* #define ECF_INTR_OFFSET        0x0C */
-#define ECF_INTR_SET           0x01
-
-/* Authorization Register 0 (0x0F08) */
-#define AUTH_0_ON              0x57
-
-/* Authorization Register 1 (0x0F09) */
-#define AUTH_1_ON              0x82
-
-/* Program Mode Register (0x0F0A) */
-#define PC2PM                  0x02
-#define PC2CAL                 0x10
-#define PC2MLSE                0x20
-
-/* PC Test Mode Register (0x0F0B) */
-#define PC_TEST_MODE           0x08
-
-/* Frequency Control Word (0x0F10) */
-/* Range 0x02 - 0xA6 */
-
-/* Test Mode Control 1-4 (0x0F14 - 0x0F17) */
-
-/**********************************************************************/
-
-/* Shared RAM Area */
-#define SCB_BASE               0x0000
-#define STATUS_BASE            0x0100
-#define HOST_TO_ECF_BASE       0x0200
-#define ECF_TO_HOST_BASE       0x0300
-#define CCS_BASE               0x0400
-#define RCS_BASE               0x0800
-#define INFRA_TIM_BASE         0x0C00
-#define SSID_LIST_BASE         0x0D00
-#define TX_BUF_BASE            0x1000
-#define RX_BUF_BASE            0x8000
-
-#define NUMBER_OF_CCS    64
-#define NUMBER_OF_RCS    64
-/*#define NUMBER_OF_TX_CCS 14 */
-#define NUMBER_OF_TX_CCS 14
-
-#define TX_BUF_SIZE      (2048 - sizeof(struct tx_msg))
-#define RX_BUFF_END      0x3FFF
-/* Values for buffer_status */
-#define CCS_BUFFER_FREE       0
-#define CCS_BUFFER_BUSY       1
-#define CCS_COMMAND_COMPLETE  2
-#define CCS_COMMAND_FAILED    3
-
-/* Values for cmd */
-#define CCS_DOWNLOAD_STARTUP_PARAMS    1
-#define CCS_UPDATE_PARAMS              2
-#define CCS_REPORT_PARAMS              3
-#define CCS_UPDATE_MULTICAST_LIST      4
-#define CCS_UPDATE_POWER_SAVINGS_MODE  5
-#define CCS_START_NETWORK              6
-#define CCS_JOIN_NETWORK               7
-#define CCS_START_ASSOCIATION          8
-#define CCS_TX_REQUEST                 9
-#define CCS_TEST_MEMORY              0xa
-#define CCS_SHUTDOWN                 0xb
-#define CCS_DUMP_MEMORY              0xc
-#define CCS_START_TIMER              0xe
-#define CCS_LAST_CMD                 CCS_START_TIMER
-
-/* Values for link field */
-#define CCS_END_LIST                 0xff
-
-/* values for buffer_status field */
-#define RCS_BUFFER_FREE       0
-#define RCS_BUFFER_BUSY       1
-#define RCS_COMPLETE          2
-#define RCS_FAILED            3
-#define RCS_BUFFER_RELEASE    0xFF
-
-/* values for interrupt_id field */
-#define PROCESS_RX_PACKET           0x80 /* */
-#define REJOIN_NET_COMPLETE         0x81 /* RCS ID: Rejoin Net Complete */
-#define ROAMING_INITIATED           0x82 /* RCS ID: Roaming Initiated   */
-#define JAPAN_CALL_SIGN_RXD         0x83 /* RCS ID: New Japan Call Sign */
-
-/*****************************************************************************/
-/* Memory types for dump memory command */
-#define C_MEM_PROG  0
-#define C_MEM_XDATA 1
-#define C_MEM_SFR   2
-#define C_MEM_IDATA 3
-
-/*** Return values for hw_xmit **********/
-#define XMIT_OK        (0)
-#define XMIT_MSG_BAD   (-1)
-#define XMIT_NO_CCS    (-2)
-#define XMIT_NO_INTR   (-3)
-#define XMIT_NEED_AUTH (-4)
-
-/*** Values for card status */
-#define CARD_INSERTED       (0)
-
-#define CARD_AWAITING_PARAM (1)
-#define CARD_INIT_ERROR     (11)
-
-#define CARD_DL_PARAM       (2)
-#define CARD_DL_PARAM_ERROR (12)
-
-#define CARD_DOING_ACQ      (3)
-
-#define CARD_ACQ_COMPLETE   (4)
-#define CARD_ACQ_FAILED     (14)
-
-#define CARD_AUTH_COMPLETE  (5)
-#define CARD_AUTH_REFUSED   (15)
-
-#define CARD_ASSOC_COMPLETE (6)
-#define CARD_ASSOC_FAILED   (16)
-
-/*** Values for authentication_state ***********************************/
-#define UNAUTHENTICATED     (0)
-#define AWAITING_RESPONSE   (1)
-#define AUTHENTICATED       (2)
-#define NEED_TO_AUTH        (3)
-
-/*** Values for authentication type ************************************/
-#define OPEN_AUTH_REQUEST   (1)
-#define OPEN_AUTH_RESPONSE  (2)
-#define BROADCAST_DEAUTH    (0xc0)
-/*** Values for timer functions ****************************************/
-#define TODO_NOTHING              (0)
-#define TODO_VERIFY_DL_START      (-1)
-#define TODO_START_NET            (-2)
-#define TODO_JOIN_NET             (-3)
-#define TODO_AUTHENTICATE_TIMEOUT (-4)
-#define TODO_SEND_CCS             (-5)
-/***********************************************************************/
-/* Parameter passing structure for update/report parameter CCS's */
-struct object_id {
-    void          *object_addr;
-    unsigned char object_length;
-};
-
-#define OBJID_network_type            0
-#define OBJID_acting_as_ap_status     1
-#define OBJID_current_ess_id          2
-#define OBJID_scanning_mode           3
-#define OBJID_power_mgt_state         4
-#define OBJID_mac_address             5
-#define OBJID_frag_threshold          6
-#define OBJID_hop_time                7
-#define OBJID_beacon_period           8
-#define OBJID_dtim_period             9
-#define OBJID_retry_max              10
-#define OBJID_ack_timeout            11
-#define OBJID_sifs                   12
-#define OBJID_difs                   13
-#define OBJID_pifs                   14
-#define OBJID_rts_threshold          15
-#define OBJID_scan_dwell_time        16
-#define OBJID_max_scan_dwell_time    17
-#define OBJID_assoc_resp_timeout     18
-#define OBJID_adhoc_scan_cycle_max   19
-#define OBJID_infra_scan_cycle_max   20
-#define OBJID_infra_super_cycle_max  21
-#define OBJID_promiscuous_mode       22
-#define OBJID_unique_word            23
-#define OBJID_slot_time              24
-#define OBJID_roaming_low_snr        25
-#define OBJID_low_snr_count_thresh   26
-#define OBJID_infra_missed_bcn       27
-#define OBJID_adhoc_missed_bcn       28
-#define OBJID_curr_country_code      29
-#define OBJID_hop_pattern            30
-#define OBJID_reserved               31
-#define OBJID_cw_max_msb             32
-#define OBJID_cw_min_msb             33
-#define OBJID_noise_filter_gain      34
-#define OBJID_noise_limit_offset     35
-#define OBJID_det_rssi_thresh_offset 36
-#define OBJID_med_busy_thresh_offset 37
-#define OBJID_det_sync_thresh        38
-#define OBJID_test_mode              39
-#define OBJID_test_min_chan_num      40
-#define OBJID_test_max_chan_num      41
-#define OBJID_allow_bcast_ID_prbrsp  42
-#define OBJID_privacy_must_start     43
-#define OBJID_privacy_can_join       44
-#define OBJID_basic_rate_set         45
-
-/**** Configuration/Status/Control Area ***************************/
-/*    System Control Block (SCB) Area
- *    Located at Shared RAM offset 0
- */
-struct scb {
-    UCHAR ccs_index;
-    UCHAR rcs_index;
-};
-
-/****** Status area at Shared RAM offset 0x0100 ******************************/
-struct status {
-    UCHAR mrx_overflow_for_host;         /* 0=ECF may write, 1=host may write*/
-    UCHAR mrx_checksum_error_for_host;   /* 0=ECF may write, 1=host may write*/
-    UCHAR rx_hec_error_for_host;         /* 0=ECF may write, 1=host may write*/
-    UCHAR reserved1;
-    short mrx_overflow;                  /* ECF increments on rx overflow    */
-    short mrx_checksum_error;            /* ECF increments on rx CRC error   */
-    short rx_hec_error;                  /* ECF incs on mac header CRC error */
-    UCHAR rxnoise;                       /* Average RSL measurement          */
-};
-
-/****** Host-to-ECF Data Area at Shared RAM offset 0x200 *********************/
-struct host_to_ecf_area {
-    
-};
-
-/****** ECF-to-Host Data Area at Shared RAM offset 0x0300 ********************/
-struct startup_res_518 {
-    UCHAR startup_word;
-    UCHAR station_addr[ADDRLEN];
-    UCHAR calc_prog_chksum;
-    UCHAR calc_cis_chksum;
-    UCHAR ecf_spare[7];
-    UCHAR japan_call_sign[12];
-};
-
-struct startup_res_6 {
-    UCHAR startup_word;
-    UCHAR station_addr[ADDRLEN];
-    UCHAR reserved;
-    UCHAR supp_rates[8];
-    UCHAR japan_call_sign[12];
-    UCHAR calc_prog_chksum;
-    UCHAR calc_cis_chksum;
-    UCHAR firmware_version[3];
-    UCHAR asic_version;
-    UCHAR tib_length;
-};
-
-struct start_join_net_params {
-    UCHAR net_type;
-    UCHAR ssid[ESSID_SIZE];
-    UCHAR reserved;
-    UCHAR privacy_can_join;
-};
-
-/****** Command Control Structure area at Shared ram offset 0x0400 ***********/
-/* Structures for command specific parameters (ccs.var) */
-struct update_param_cmd {
-    UCHAR object_id;
-    UCHAR number_objects;
-    UCHAR failure_cause;
-};
-struct report_param_cmd {
-    UCHAR object_id;
-    UCHAR number_objects;
-    UCHAR failure_cause;
-    UCHAR length;
-};
-struct start_network_cmd {
-    UCHAR update_param;
-    UCHAR bssid[ADDRLEN];
-    UCHAR net_initiated;
-    UCHAR net_default_tx_rate;
-    UCHAR encryption;
-};
-struct join_network_cmd {
-    UCHAR update_param;
-    UCHAR bssid[ADDRLEN];
-    UCHAR net_initiated;
-    UCHAR net_default_tx_rate;
-    UCHAR encryption;
-};
-struct tx_requested_cmd {
- 
-    UCHAR tx_data_ptr[2];
-    UCHAR tx_data_length[2];
-    UCHAR host_reserved[2];
-    UCHAR reserved[3];
-    UCHAR tx_rate;
-    UCHAR pow_sav_mode;
-    UCHAR retries;
-    UCHAR antenna;
-};
-struct tx_requested_cmd_4 {
- 
-    UCHAR tx_data_ptr[2];
-    UCHAR tx_data_length[2];
-    UCHAR dest_addr[ADDRLEN];
-    UCHAR pow_sav_mode;
-    UCHAR retries;
-    UCHAR station_id;
-};
-struct memory_dump_cmd {
-    UCHAR memory_type;
-    UCHAR memory_ptr[2];
-    UCHAR length;
-};
-struct update_association_cmd {
-    UCHAR status;
-    UCHAR aid[2];
-};
-struct start_timer_cmd {
-    UCHAR duration[2];
-};
-
-struct ccs {
-    UCHAR buffer_status;                 /* 0 = buffer free, 1 = buffer busy */
-                                         /* 2 = command complete, 3 = failed */
-    UCHAR cmd;                           /* command to ECF                   */
-    UCHAR link;                          /* link to next CCS, FF=end of list */
-    /* command specific parameters      */
-    union {
-        char reserved[13];
-        struct update_param_cmd update_param;
-        struct report_param_cmd report_param;
-        UCHAR nummulticast;
-        UCHAR mode;
-        struct start_network_cmd start_network;
-        struct join_network_cmd join_network;
-        struct tx_requested_cmd tx_request;
-        struct memory_dump_cmd memory_dump;
-        struct update_association_cmd update_assoc;
-        struct start_timer_cmd start_timer;
-    } var;
-};
-
-/*****************************************************************************/
-/* Transmit buffer structures */
-struct tib_structure {
-    UCHAR ccs_index;
-    UCHAR psm;
-    UCHAR pass_fail;
-    UCHAR retry_count;
-    UCHAR max_retries;
-    UCHAR frags_remaining;
-    UCHAR no_rb;
-    UCHAR rts_reqd;
-    UCHAR csma_tx_cntrl_2;
-    UCHAR sifs_tx_cntrl_2;
-    UCHAR tx_dma_addr_1[2];
-    UCHAR tx_dma_addr_2[2];
-    UCHAR var_dur_2mhz[2];
-    UCHAR var_dur_1mhz[2];
-    UCHAR max_dur_2mhz[2];
-    UCHAR max_dur_1mhz[2];
-    UCHAR hdr_len;
-    UCHAR max_frag_len[2];
-    UCHAR var_len[2];
-    UCHAR phy_hdr_4;
-    UCHAR mac_hdr_1;
-    UCHAR mac_hdr_2;
-    UCHAR sid[2];
-};
-
-struct phy_header {
-    UCHAR sfd[2];
-    UCHAR hdr_3;
-    UCHAR hdr_4;
-};
-struct ray_rx_msg {
-    struct mac_header mac;
-	UCHAR	var[];
-};
-
-struct tx_msg {
-    struct tib_structure tib;
-    struct phy_header phy;
-    struct mac_header mac;
-    UCHAR  var[];
-};
-
-/****** ECF Receive Control Structure (RCS) Area at Shared RAM offset 0x0800  */
-/* Structures for command specific parameters (rcs.var) */
-struct rx_packet_cmd {
-    UCHAR rx_data_ptr[2];
-    UCHAR rx_data_length[2];
-    UCHAR rx_sig_lev;
-    UCHAR next_frag_rcs_index;
-    UCHAR totalpacketlength[2];
-};
-struct rejoin_net_cmplt_cmd {
-    UCHAR reserved;
-    UCHAR bssid[ADDRLEN];
-};
-struct japan_call_sign_rxd {
-    UCHAR rxd_call_sign[8];
-    UCHAR reserved[5];
-};
-
-struct rcs {
-    UCHAR buffer_status;
-    UCHAR interrupt_id;
-    UCHAR link_field;
-    /* command specific parameters      */
-    union {
-        UCHAR reserved[13]; 
-        struct rx_packet_cmd rx_packet;
-        struct rejoin_net_cmplt_cmd rejoin_net_complete;
-        struct japan_call_sign_rxd japan_call_sign;
-    } var;
-};
-
-/****** Startup parameter structures for both versions of firmware ***********/
-struct b4_startup_params {
-    UCHAR a_network_type;                /* C_ADHOC, C_INFRA                 */
-    UCHAR a_acting_as_ap_status;         /* C_TYPE_STA, C_TYPE_AP            */
-    UCHAR a_current_ess_id[ESSID_SIZE];  /* Null terminated unless 32 long   */
-    UCHAR a_scanning_mode;               /* passive 0, active 1              */
-    UCHAR a_power_mgt_state;             /* CAM 0,                           */
-    UCHAR a_mac_addr[ADDRLEN];           /*                                  */
-    UCHAR a_frag_threshold[2];           /* 512                              */
-    UCHAR a_hop_time[2];                 /* 16k * 2**n, n=0-4 in Kus         */
-    UCHAR a_beacon_period[2];            /* n * a_hop_time  in Kus           */
-    UCHAR a_dtim_period;                 /* in beacons                       */
-    UCHAR a_retry_max;                   /*                                  */
-    UCHAR a_ack_timeout;                 /*                                  */
-    UCHAR a_sifs;                        /*                                  */
-    UCHAR a_difs;                        /*                                  */
-    UCHAR a_pifs;                        /*                                  */
-    UCHAR a_rts_threshold[2];            /*                                  */
-    UCHAR a_scan_dwell_time[2];          /*                                  */
-    UCHAR a_max_scan_dwell_time[2];      /*                                  */
-    UCHAR a_assoc_resp_timeout_thresh;   /*                                  */
-    UCHAR a_adhoc_scan_cycle_max;        /*                                  */
-    UCHAR a_infra_scan_cycle_max;        /*                                  */
-    UCHAR a_infra_super_scan_cycle_max;  /*                                  */
-    UCHAR a_promiscuous_mode;            /*                                  */
-    UCHAR a_unique_word[2];              /*                                  */
-    UCHAR a_slot_time;                   /*                                  */
-    UCHAR a_roaming_low_snr_thresh;      /*                                  */
-    UCHAR a_low_snr_count_thresh;        /*                                  */
-    UCHAR a_infra_missed_bcn_thresh;     /*                                  */
-    UCHAR a_adhoc_missed_bcn_thresh;     /*                                  */
-    UCHAR a_curr_country_code;           /* C_USA                            */
-    UCHAR a_hop_pattern;                 /*                                  */
-    UCHAR a_hop_pattern_length;          /*                                  */
-/* b4 - b5 differences start here */
-    UCHAR a_cw_max;                      /*                                  */
-    UCHAR a_cw_min;                      /*                                  */
-    UCHAR a_noise_filter_gain;           /*                                  */
-    UCHAR a_noise_limit_offset;          /*                                  */
-    UCHAR a_det_rssi_thresh_offset;      /*                                  */
-    UCHAR a_med_busy_thresh_offset;      /*                                  */
-    UCHAR a_det_sync_thresh;             /*                                  */
-    UCHAR a_test_mode;                   /*                                  */
-    UCHAR a_test_min_chan_num;           /*                                  */
-    UCHAR a_test_max_chan_num;           /*                                  */
-    UCHAR a_rx_tx_delay;                 /*                                  */
-    UCHAR a_current_bss_id[ADDRLEN];     /*                                  */
-    UCHAR a_hop_set;                     /*                                  */
-};
-struct b5_startup_params {
-    UCHAR a_network_type;                /* C_ADHOC, C_INFRA                 */
-    UCHAR a_acting_as_ap_status;         /* C_TYPE_STA, C_TYPE_AP            */
-    UCHAR a_current_ess_id[ESSID_SIZE];  /* Null terminated unless 32 long   */
-    UCHAR a_scanning_mode;               /* passive 0, active 1              */
-    UCHAR a_power_mgt_state;             /* CAM 0,                           */
-    UCHAR a_mac_addr[ADDRLEN];           /*                                  */
-    UCHAR a_frag_threshold[2];           /* 512                              */
-    UCHAR a_hop_time[2];                 /* 16k * 2**n, n=0-4 in Kus         */
-    UCHAR a_beacon_period[2];            /* n * a_hop_time  in Kus           */
-    UCHAR a_dtim_period;                 /* in beacons                       */
-    UCHAR a_retry_max;                   /* 4                                */
-    UCHAR a_ack_timeout;                 /*                                  */
-    UCHAR a_sifs;                        /*                                  */
-    UCHAR a_difs;                        /*                                  */
-    UCHAR a_pifs;                        /*                                  */
-    UCHAR a_rts_threshold[2];            /*                                  */
-    UCHAR a_scan_dwell_time[2];          /*                                  */
-    UCHAR a_max_scan_dwell_time[2];      /*                                  */
-    UCHAR a_assoc_resp_timeout_thresh;   /*                                  */
-    UCHAR a_adhoc_scan_cycle_max;        /*                                  */
-    UCHAR a_infra_scan_cycle_max;        /*                                  */
-    UCHAR a_infra_super_scan_cycle_max;  /*                                  */
-    UCHAR a_promiscuous_mode;            /*                                  */
-    UCHAR a_unique_word[2];              /*                                  */
-    UCHAR a_slot_time;                   /*                                  */
-    UCHAR a_roaming_low_snr_thresh;      /*                                  */
-    UCHAR a_low_snr_count_thresh;        /*                                  */
-    UCHAR a_infra_missed_bcn_thresh;     /*                                  */
-    UCHAR a_adhoc_missed_bcn_thresh;     /*                                  */
-    UCHAR a_curr_country_code;           /* C_USA                            */
-    UCHAR a_hop_pattern;                 /*                                  */
-    UCHAR a_hop_pattern_length;          /*                                  */
-/* b4 - b5 differences start here */
-    UCHAR a_cw_max[2];                   /*                                  */
-    UCHAR a_cw_min[2];                   /*                                  */
-    UCHAR a_noise_filter_gain;           /*                                  */
-    UCHAR a_noise_limit_offset;          /*                                  */
-    UCHAR a_det_rssi_thresh_offset;      /*                                  */
-    UCHAR a_med_busy_thresh_offset;      /*                                  */
-    UCHAR a_det_sync_thresh;             /*                                  */
-    UCHAR a_test_mode;                   /*                                  */
-    UCHAR a_test_min_chan_num;           /*                                  */
-    UCHAR a_test_max_chan_num;           /*                                  */
-    UCHAR a_allow_bcast_SSID_probe_rsp;
-    UCHAR a_privacy_must_start;
-    UCHAR a_privacy_can_join;
-    UCHAR a_basic_rate_set[8];
-};
-
-/*****************************************************************************/
-#define RAY_IOCG_PARMS (SIOCDEVPRIVATE)
-#define RAY_IOCS_PARMS (SIOCDEVPRIVATE + 1)
-#define RAY_DO_CMD     (SIOCDEVPRIVATE + 2)
-
-/****** ethernet <-> 802.11 translation **************************************/
-typedef struct snaphdr_t
-{
-  UCHAR   dsap;
-  UCHAR   ssap;
-  UCHAR   ctrl;
-  UCHAR   org[3];
-  UCHAR   ethertype[2];
-} snaphdr_t;
-
-#define BRIDGE_ENCAP  0xf80000
-#define RFC1042_ENCAP 0
-#define SNAP_ID       0x0003aaaa
-#define RAY_IPX_TYPE  0x8137
-#define APPLEARP_TYPE 0x80f3
-/*****************************************************************************/
-#endif /* _RAYCTL_H_ */
diff --git a/drivers/net/wireless/legacy/rndis_wlan.c b/drivers/net/wireless/legacy/rndis_wlan.c
deleted file mode 100644
index e7fea7ded6d5..000000000000
--- a/drivers/net/wireless/legacy/rndis_wlan.c
+++ /dev/null
@@ -1,3760 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Driver for RNDIS based USB wireless devices.
- *
- * Copyright (C) 2007 by Bjorge Dijkstra <bjd@jooz.net>
- * Copyright (C) 2008-2009 by Jussi Kivilinna <jussi.kivilinna@iki.fi>
- *
- *  Portions of this file are based on NDISwrapper project,
- *  Copyright (C) 2003-2005 Pontus Fuchs, Giridhar Pemmasani
- *  http://ndiswrapper.sourceforge.net/
- */
-
-// #define	DEBUG			// error path messages, extra info
-// #define	VERBOSE			// more; success messages
-
-#include <linux/module.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/ethtool.h>
-#include <linux/workqueue.h>
-#include <linux/mutex.h>
-#include <linux/mii.h>
-#include <linux/usb.h>
-#include <linux/usb/cdc.h>
-#include <linux/ieee80211.h>
-#include <linux/if_arp.h>
-#include <linux/ctype.h>
-#include <linux/spinlock.h>
-#include <linux/slab.h>
-#include <net/cfg80211.h>
-#include <linux/usb/usbnet.h>
-#include <linux/usb/rndis_host.h>
-
-
-/* NOTE: All these are settings for Broadcom chipset */
-static char modparam_country[4] = "EU";
-module_param_string(country, modparam_country, 4, 0444);
-MODULE_PARM_DESC(country, "Country code (ISO 3166-1 alpha-2), default: EU");
-
-static int modparam_frameburst = 1;
-module_param_named(frameburst, modparam_frameburst, int, 0444);
-MODULE_PARM_DESC(frameburst, "enable frame bursting (default: on)");
-
-static int modparam_afterburner = 0;
-module_param_named(afterburner, modparam_afterburner, int, 0444);
-MODULE_PARM_DESC(afterburner,
-	"enable afterburner aka '125 High Speed Mode' (default: off)");
-
-static int modparam_power_save = 0;
-module_param_named(power_save, modparam_power_save, int, 0444);
-MODULE_PARM_DESC(power_save,
-	"set power save mode: 0=off, 1=on, 2=fast (default: off)");
-
-static int modparam_power_output = 3;
-module_param_named(power_output, modparam_power_output, int, 0444);
-MODULE_PARM_DESC(power_output,
-	"set power output: 0=25%, 1=50%, 2=75%, 3=100% (default: 100%)");
-
-static int modparam_roamtrigger = -70;
-module_param_named(roamtrigger, modparam_roamtrigger, int, 0444);
-MODULE_PARM_DESC(roamtrigger,
-	"set roaming dBm trigger: -80=optimize for distance, "
-				"-60=bandwidth (default: -70)");
-
-static int modparam_roamdelta = 1;
-module_param_named(roamdelta, modparam_roamdelta, int, 0444);
-MODULE_PARM_DESC(roamdelta,
-	"set roaming tendency: 0=aggressive, 1=moderate, "
-				"2=conservative (default: moderate)");
-
-static int modparam_workaround_interval;
-module_param_named(workaround_interval, modparam_workaround_interval,
-							int, 0444);
-MODULE_PARM_DESC(workaround_interval,
-	"set stall workaround interval in msecs (0=disabled) (default: 0)");
-
-/* Typical noise/maximum signal level values taken from ndiswrapper iw_ndis.h */
-#define	WL_NOISE	-96	/* typical noise level in dBm */
-#define	WL_SIGMAX	-32	/* typical maximum signal level in dBm */
-
-
-/* Assume that Broadcom 4320 (only chipset at time of writing known to be
- * based on wireless rndis) has default txpower of 13dBm.
- * This value is from Linksys WUSB54GSC User Guide, Appendix F: Specifications.
- *  100% : 20 mW ~ 13dBm
- *   75% : 15 mW ~ 12dBm
- *   50% : 10 mW ~ 10dBm
- *   25% :  5 mW ~  7dBm
- */
-#define BCM4320_DEFAULT_TXPOWER_DBM_100 13
-#define BCM4320_DEFAULT_TXPOWER_DBM_75  12
-#define BCM4320_DEFAULT_TXPOWER_DBM_50  10
-#define BCM4320_DEFAULT_TXPOWER_DBM_25  7
-
-/* Known device types */
-#define RNDIS_UNKNOWN	0
-#define RNDIS_BCM4320A	1
-#define RNDIS_BCM4320B	2
-
-
-/* NDIS data structures. Taken from wpa_supplicant driver_ndis.c
- * slightly modified for datatype endianess, etc
- */
-#define NDIS_802_11_LENGTH_SSID 32
-#define NDIS_802_11_LENGTH_RATES 8
-#define NDIS_802_11_LENGTH_RATES_EX 16
-
-enum ndis_80211_net_type {
-	NDIS_80211_TYPE_FREQ_HOP,
-	NDIS_80211_TYPE_DIRECT_SEQ,
-	NDIS_80211_TYPE_OFDM_A,
-	NDIS_80211_TYPE_OFDM_G
-};
-
-enum ndis_80211_net_infra {
-	NDIS_80211_INFRA_ADHOC,
-	NDIS_80211_INFRA_INFRA,
-	NDIS_80211_INFRA_AUTO_UNKNOWN
-};
-
-enum ndis_80211_auth_mode {
-	NDIS_80211_AUTH_OPEN,
-	NDIS_80211_AUTH_SHARED,
-	NDIS_80211_AUTH_AUTO_SWITCH,
-	NDIS_80211_AUTH_WPA,
-	NDIS_80211_AUTH_WPA_PSK,
-	NDIS_80211_AUTH_WPA_NONE,
-	NDIS_80211_AUTH_WPA2,
-	NDIS_80211_AUTH_WPA2_PSK
-};
-
-enum ndis_80211_encr_status {
-	NDIS_80211_ENCR_WEP_ENABLED,
-	NDIS_80211_ENCR_DISABLED,
-	NDIS_80211_ENCR_WEP_KEY_ABSENT,
-	NDIS_80211_ENCR_NOT_SUPPORTED,
-	NDIS_80211_ENCR_TKIP_ENABLED,
-	NDIS_80211_ENCR_TKIP_KEY_ABSENT,
-	NDIS_80211_ENCR_CCMP_ENABLED,
-	NDIS_80211_ENCR_CCMP_KEY_ABSENT
-};
-
-enum ndis_80211_priv_filter {
-	NDIS_80211_PRIV_ACCEPT_ALL,
-	NDIS_80211_PRIV_8021X_WEP
-};
-
-enum ndis_80211_status_type {
-	NDIS_80211_STATUSTYPE_AUTHENTICATION,
-	NDIS_80211_STATUSTYPE_MEDIASTREAMMODE,
-	NDIS_80211_STATUSTYPE_PMKID_CANDIDATELIST,
-	NDIS_80211_STATUSTYPE_RADIOSTATE,
-};
-
-enum ndis_80211_media_stream_mode {
-	NDIS_80211_MEDIA_STREAM_OFF,
-	NDIS_80211_MEDIA_STREAM_ON
-};
-
-enum ndis_80211_radio_status {
-	NDIS_80211_RADIO_STATUS_ON,
-	NDIS_80211_RADIO_STATUS_HARDWARE_OFF,
-	NDIS_80211_RADIO_STATUS_SOFTWARE_OFF,
-};
-
-enum ndis_80211_addkey_bits {
-	NDIS_80211_ADDKEY_8021X_AUTH = cpu_to_le32(1 << 28),
-	NDIS_80211_ADDKEY_SET_INIT_RECV_SEQ = cpu_to_le32(1 << 29),
-	NDIS_80211_ADDKEY_PAIRWISE_KEY = cpu_to_le32(1 << 30),
-	NDIS_80211_ADDKEY_TRANSMIT_KEY = cpu_to_le32(1 << 31)
-};
-
-enum ndis_80211_addwep_bits {
-	NDIS_80211_ADDWEP_PERCLIENT_KEY = cpu_to_le32(1 << 30),
-	NDIS_80211_ADDWEP_TRANSMIT_KEY = cpu_to_le32(1 << 31)
-};
-
-enum ndis_80211_power_mode {
-	NDIS_80211_POWER_MODE_CAM,
-	NDIS_80211_POWER_MODE_MAX_PSP,
-	NDIS_80211_POWER_MODE_FAST_PSP,
-};
-
-enum ndis_80211_pmkid_cand_list_flag_bits {
-	NDIS_80211_PMKID_CAND_PREAUTH = cpu_to_le32(1 << 0)
-};
-
-struct ndis_80211_auth_request {
-	__le32 length;
-	u8 bssid[ETH_ALEN];
-	u8 padding[2];
-	__le32 flags;
-} __packed;
-
-struct ndis_80211_pmkid_candidate {
-	u8 bssid[ETH_ALEN];
-	u8 padding[2];
-	__le32 flags;
-} __packed;
-
-struct ndis_80211_pmkid_cand_list {
-	__le32 version;
-	__le32 num_candidates;
-	struct ndis_80211_pmkid_candidate candidate_list[];
-} __packed;
-
-struct ndis_80211_status_indication {
-	__le32 status_type;
-	union {
-		__le32					media_stream_mode;
-		__le32					radio_status;
-		DECLARE_FLEX_ARRAY(struct ndis_80211_auth_request, auth_request);
-		struct ndis_80211_pmkid_cand_list	cand_list;
-	} u;
-} __packed;
-
-struct ndis_80211_ssid {
-	__le32 length;
-	u8 essid[NDIS_802_11_LENGTH_SSID];
-} __packed;
-
-struct ndis_80211_conf_freq_hop {
-	__le32 length;
-	__le32 hop_pattern;
-	__le32 hop_set;
-	__le32 dwell_time;
-} __packed;
-
-struct ndis_80211_conf {
-	__le32 length;
-	__le32 beacon_period;
-	__le32 atim_window;
-	__le32 ds_config;
-	struct ndis_80211_conf_freq_hop fh_config;
-} __packed;
-
-struct ndis_80211_bssid_ex {
-	__le32 length;
-	u8 mac[ETH_ALEN];
-	u8 padding[2];
-	struct ndis_80211_ssid ssid;
-	__le32 privacy;
-	__le32 rssi;
-	__le32 net_type;
-	struct ndis_80211_conf config;
-	__le32 net_infra;
-	u8 rates[NDIS_802_11_LENGTH_RATES_EX];
-	__le32 ie_length;
-	u8 ies[];
-} __packed;
-
-struct ndis_80211_bssid_list_ex {
-	__le32 num_items;
-	u8 bssid_data[];
-} __packed;
-
-struct ndis_80211_fixed_ies {
-	u8 timestamp[8];
-	__le16 beacon_interval;
-	__le16 capabilities;
-} __packed;
-
-struct ndis_80211_wep_key {
-	__le32 size;
-	__le32 index;
-	__le32 length;
-	u8 material[32];
-} __packed;
-
-struct ndis_80211_key {
-	__le32 size;
-	__le32 index;
-	__le32 length;
-	u8 bssid[ETH_ALEN];
-	u8 padding[6];
-	u8 rsc[8];
-	u8 material[32];
-} __packed;
-
-struct ndis_80211_remove_key {
-	__le32 size;
-	__le32 index;
-	u8 bssid[ETH_ALEN];
-	u8 padding[2];
-} __packed;
-
-struct ndis_config_param {
-	__le32 name_offs;
-	__le32 name_length;
-	__le32 type;
-	__le32 value_offs;
-	__le32 value_length;
-} __packed;
-
-struct ndis_80211_assoc_info {
-	__le32 length;
-	__le16 req_ies;
-	struct req_ie {
-		__le16 capa;
-		__le16 listen_interval;
-		u8 cur_ap_address[ETH_ALEN];
-	} req_ie;
-	__le32 req_ie_length;
-	__le32 offset_req_ies;
-	__le16 resp_ies;
-	struct resp_ie {
-		__le16 capa;
-		__le16 status_code;
-		__le16 assoc_id;
-	} resp_ie;
-	__le32 resp_ie_length;
-	__le32 offset_resp_ies;
-} __packed;
-
-struct ndis_80211_capability {
-	__le32 length;
-	__le32 version;
-	__le32 num_pmkids;
-	__le32 num_auth_encr_pair;
-} __packed;
-
-struct ndis_80211_bssid_info {
-	u8 bssid[ETH_ALEN];
-	u8 pmkid[16];
-} __packed;
-
-struct ndis_80211_pmkid {
-	__le32 length;
-	__le32 bssid_info_count;
-	struct ndis_80211_bssid_info bssid_info[];
-} __packed;
-
-/*
- *  private data
- */
-#define CAP_MODE_80211A		1
-#define CAP_MODE_80211B		2
-#define CAP_MODE_80211G		4
-#define CAP_MODE_MASK		7
-
-#define WORK_LINK_UP		0
-#define WORK_LINK_DOWN		1
-#define WORK_SET_MULTICAST_LIST	2
-
-#define RNDIS_WLAN_ALG_NONE	0
-#define RNDIS_WLAN_ALG_WEP	(1<<0)
-#define RNDIS_WLAN_ALG_TKIP	(1<<1)
-#define RNDIS_WLAN_ALG_CCMP	(1<<2)
-
-#define RNDIS_WLAN_NUM_KEYS		4
-#define RNDIS_WLAN_KEY_MGMT_NONE	0
-#define RNDIS_WLAN_KEY_MGMT_802_1X	(1<<0)
-#define RNDIS_WLAN_KEY_MGMT_PSK		(1<<1)
-
-#define COMMAND_BUFFER_SIZE	(CONTROL_BUFFER_SIZE + sizeof(struct rndis_set))
-
-static const struct ieee80211_channel rndis_channels[] = {
-	{ .center_freq = 2412 },
-	{ .center_freq = 2417 },
-	{ .center_freq = 2422 },
-	{ .center_freq = 2427 },
-	{ .center_freq = 2432 },
-	{ .center_freq = 2437 },
-	{ .center_freq = 2442 },
-	{ .center_freq = 2447 },
-	{ .center_freq = 2452 },
-	{ .center_freq = 2457 },
-	{ .center_freq = 2462 },
-	{ .center_freq = 2467 },
-	{ .center_freq = 2472 },
-	{ .center_freq = 2484 },
-};
-
-static const struct ieee80211_rate rndis_rates[] = {
-	{ .bitrate = 10 },
-	{ .bitrate = 20, .flags = IEEE80211_RATE_SHORT_PREAMBLE },
-	{ .bitrate = 55, .flags = IEEE80211_RATE_SHORT_PREAMBLE },
-	{ .bitrate = 110, .flags = IEEE80211_RATE_SHORT_PREAMBLE },
-	{ .bitrate = 60 },
-	{ .bitrate = 90 },
-	{ .bitrate = 120 },
-	{ .bitrate = 180 },
-	{ .bitrate = 240 },
-	{ .bitrate = 360 },
-	{ .bitrate = 480 },
-	{ .bitrate = 540 }
-};
-
-static const u32 rndis_cipher_suites[] = {
-	WLAN_CIPHER_SUITE_WEP40,
-	WLAN_CIPHER_SUITE_WEP104,
-	WLAN_CIPHER_SUITE_TKIP,
-	WLAN_CIPHER_SUITE_CCMP,
-};
-
-struct rndis_wlan_encr_key {
-	int len;
-	u32 cipher;
-	u8 material[32];
-	u8 bssid[ETH_ALEN];
-	bool pairwise;
-	bool tx_key;
-};
-
-/* RNDIS device private data */
-struct rndis_wlan_private {
-	struct usbnet *usbdev;
-
-	struct wireless_dev wdev;
-
-	struct cfg80211_scan_request *scan_request;
-
-	struct workqueue_struct *workqueue;
-	struct delayed_work dev_poller_work;
-	struct delayed_work scan_work;
-	struct work_struct work;
-	struct mutex command_lock;
-	unsigned long work_pending;
-	int last_qual;
-	s32 cqm_rssi_thold;
-	u32 cqm_rssi_hyst;
-	int last_cqm_event_rssi;
-
-	struct ieee80211_supported_band band;
-	struct ieee80211_channel channels[ARRAY_SIZE(rndis_channels)];
-	struct ieee80211_rate rates[ARRAY_SIZE(rndis_rates)];
-	u32 cipher_suites[ARRAY_SIZE(rndis_cipher_suites)];
-
-	int device_type;
-	int caps;
-	int multicast_size;
-
-	/* module parameters */
-	char param_country[4];
-	int  param_frameburst;
-	int  param_afterburner;
-	int  param_power_save;
-	int  param_power_output;
-	int  param_roamtrigger;
-	int  param_roamdelta;
-	u32  param_workaround_interval;
-
-	/* hardware state */
-	bool radio_on;
-	int power_mode;
-	int infra_mode;
-	bool connected;
-	u8 bssid[ETH_ALEN];
-	u32 current_command_oid;
-
-	/* encryption stuff */
-	u8 encr_tx_key_index;
-	struct rndis_wlan_encr_key encr_keys[RNDIS_WLAN_NUM_KEYS];
-	int  wpa_version;
-
-	u8 command_buffer[COMMAND_BUFFER_SIZE];
-};
-
-/*
- * cfg80211 ops
- */
-static int rndis_change_virtual_intf(struct wiphy *wiphy,
-					struct net_device *dev,
-					enum nl80211_iftype type,
-					struct vif_params *params);
-
-static int rndis_scan(struct wiphy *wiphy,
-			struct cfg80211_scan_request *request);
-
-static int rndis_set_wiphy_params(struct wiphy *wiphy, u32 changed);
-
-static int rndis_set_tx_power(struct wiphy *wiphy,
-			      struct wireless_dev *wdev,
-			      enum nl80211_tx_power_setting type,
-			      int mbm);
-static int rndis_get_tx_power(struct wiphy *wiphy,
-			      struct wireless_dev *wdev,
-			      int *dbm);
-
-static int rndis_connect(struct wiphy *wiphy, struct net_device *dev,
-				struct cfg80211_connect_params *sme);
-
-static int rndis_disconnect(struct wiphy *wiphy, struct net_device *dev,
-				u16 reason_code);
-
-static int rndis_join_ibss(struct wiphy *wiphy, struct net_device *dev,
-					struct cfg80211_ibss_params *params);
-
-static int rndis_leave_ibss(struct wiphy *wiphy, struct net_device *dev);
-
-static int rndis_add_key(struct wiphy *wiphy, struct net_device *netdev,
-			 int link_id,  u8 key_index, bool pairwise,
-			 const u8 *mac_addr, struct key_params *params);
-
-static int rndis_del_key(struct wiphy *wiphy, struct net_device *netdev,
-			 int link_id, u8 key_index, bool pairwise,
-			 const u8 *mac_addr);
-
-static int rndis_set_default_key(struct wiphy *wiphy, struct net_device *netdev,
-				 int link_id, u8 key_index, bool unicast,
-				 bool multicast);
-
-static int rndis_get_station(struct wiphy *wiphy, struct net_device *dev,
-			     const u8 *mac, struct station_info *sinfo);
-
-static int rndis_dump_station(struct wiphy *wiphy, struct net_device *dev,
-			       int idx, u8 *mac, struct station_info *sinfo);
-
-static int rndis_set_pmksa(struct wiphy *wiphy, struct net_device *netdev,
-				struct cfg80211_pmksa *pmksa);
-
-static int rndis_del_pmksa(struct wiphy *wiphy, struct net_device *netdev,
-				struct cfg80211_pmksa *pmksa);
-
-static int rndis_flush_pmksa(struct wiphy *wiphy, struct net_device *netdev);
-
-static int rndis_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev,
-				bool enabled, int timeout);
-
-static int rndis_set_cqm_rssi_config(struct wiphy *wiphy,
-					struct net_device *dev,
-					s32 rssi_thold, u32 rssi_hyst);
-
-static const struct cfg80211_ops rndis_config_ops = {
-	.change_virtual_intf = rndis_change_virtual_intf,
-	.scan = rndis_scan,
-	.set_wiphy_params = rndis_set_wiphy_params,
-	.set_tx_power = rndis_set_tx_power,
-	.get_tx_power = rndis_get_tx_power,
-	.connect = rndis_connect,
-	.disconnect = rndis_disconnect,
-	.join_ibss = rndis_join_ibss,
-	.leave_ibss = rndis_leave_ibss,
-	.add_key = rndis_add_key,
-	.del_key = rndis_del_key,
-	.set_default_key = rndis_set_default_key,
-	.get_station = rndis_get_station,
-	.dump_station = rndis_dump_station,
-	.set_pmksa = rndis_set_pmksa,
-	.del_pmksa = rndis_del_pmksa,
-	.flush_pmksa = rndis_flush_pmksa,
-	.set_power_mgmt = rndis_set_power_mgmt,
-	.set_cqm_rssi_config = rndis_set_cqm_rssi_config,
-};
-
-static void *rndis_wiphy_privid = &rndis_wiphy_privid;
-
-
-static struct rndis_wlan_private *get_rndis_wlan_priv(struct usbnet *dev)
-{
-	return (struct rndis_wlan_private *)dev->driver_priv;
-}
-
-static u32 get_bcm4320_power_dbm(struct rndis_wlan_private *priv)
-{
-	switch (priv->param_power_output) {
-	default:
-	case 3:
-		return BCM4320_DEFAULT_TXPOWER_DBM_100;
-	case 2:
-		return BCM4320_DEFAULT_TXPOWER_DBM_75;
-	case 1:
-		return BCM4320_DEFAULT_TXPOWER_DBM_50;
-	case 0:
-		return BCM4320_DEFAULT_TXPOWER_DBM_25;
-	}
-}
-
-static bool is_wpa_key(struct rndis_wlan_private *priv, u8 idx)
-{
-	int cipher = priv->encr_keys[idx].cipher;
-
-	return (cipher == WLAN_CIPHER_SUITE_CCMP ||
-		cipher == WLAN_CIPHER_SUITE_TKIP);
-}
-
-static int rndis_cipher_to_alg(u32 cipher)
-{
-	switch (cipher) {
-	default:
-		return RNDIS_WLAN_ALG_NONE;
-	case WLAN_CIPHER_SUITE_WEP40:
-	case WLAN_CIPHER_SUITE_WEP104:
-		return RNDIS_WLAN_ALG_WEP;
-	case WLAN_CIPHER_SUITE_TKIP:
-		return RNDIS_WLAN_ALG_TKIP;
-	case WLAN_CIPHER_SUITE_CCMP:
-		return RNDIS_WLAN_ALG_CCMP;
-	}
-}
-
-static int rndis_akm_suite_to_key_mgmt(u32 akm_suite)
-{
-	switch (akm_suite) {
-	default:
-		return RNDIS_WLAN_KEY_MGMT_NONE;
-	case WLAN_AKM_SUITE_8021X:
-		return RNDIS_WLAN_KEY_MGMT_802_1X;
-	case WLAN_AKM_SUITE_PSK:
-		return RNDIS_WLAN_KEY_MGMT_PSK;
-	}
-}
-
-#ifdef DEBUG
-static const char *oid_to_string(u32 oid)
-{
-	switch (oid) {
-#define OID_STR(oid) case oid: return(#oid)
-		/* from rndis_host.h */
-		OID_STR(RNDIS_OID_802_3_PERMANENT_ADDRESS);
-		OID_STR(RNDIS_OID_GEN_MAXIMUM_FRAME_SIZE);
-		OID_STR(RNDIS_OID_GEN_CURRENT_PACKET_FILTER);
-		OID_STR(RNDIS_OID_GEN_PHYSICAL_MEDIUM);
-
-		/* from rndis_wlan.c */
-		OID_STR(RNDIS_OID_GEN_LINK_SPEED);
-		OID_STR(RNDIS_OID_GEN_RNDIS_CONFIG_PARAMETER);
-
-		OID_STR(RNDIS_OID_GEN_XMIT_OK);
-		OID_STR(RNDIS_OID_GEN_RCV_OK);
-		OID_STR(RNDIS_OID_GEN_XMIT_ERROR);
-		OID_STR(RNDIS_OID_GEN_RCV_ERROR);
-		OID_STR(RNDIS_OID_GEN_RCV_NO_BUFFER);
-
-		OID_STR(RNDIS_OID_802_3_CURRENT_ADDRESS);
-		OID_STR(RNDIS_OID_802_3_MULTICAST_LIST);
-		OID_STR(RNDIS_OID_802_3_MAXIMUM_LIST_SIZE);
-
-		OID_STR(RNDIS_OID_802_11_BSSID);
-		OID_STR(RNDIS_OID_802_11_SSID);
-		OID_STR(RNDIS_OID_802_11_INFRASTRUCTURE_MODE);
-		OID_STR(RNDIS_OID_802_11_ADD_WEP);
-		OID_STR(RNDIS_OID_802_11_REMOVE_WEP);
-		OID_STR(RNDIS_OID_802_11_DISASSOCIATE);
-		OID_STR(RNDIS_OID_802_11_AUTHENTICATION_MODE);
-		OID_STR(RNDIS_OID_802_11_PRIVACY_FILTER);
-		OID_STR(RNDIS_OID_802_11_BSSID_LIST_SCAN);
-		OID_STR(RNDIS_OID_802_11_ENCRYPTION_STATUS);
-		OID_STR(RNDIS_OID_802_11_ADD_KEY);
-		OID_STR(RNDIS_OID_802_11_REMOVE_KEY);
-		OID_STR(RNDIS_OID_802_11_ASSOCIATION_INFORMATION);
-		OID_STR(RNDIS_OID_802_11_CAPABILITY);
-		OID_STR(RNDIS_OID_802_11_PMKID);
-		OID_STR(RNDIS_OID_802_11_NETWORK_TYPES_SUPPORTED);
-		OID_STR(RNDIS_OID_802_11_NETWORK_TYPE_IN_USE);
-		OID_STR(RNDIS_OID_802_11_TX_POWER_LEVEL);
-		OID_STR(RNDIS_OID_802_11_RSSI);
-		OID_STR(RNDIS_OID_802_11_RSSI_TRIGGER);
-		OID_STR(RNDIS_OID_802_11_FRAGMENTATION_THRESHOLD);
-		OID_STR(RNDIS_OID_802_11_RTS_THRESHOLD);
-		OID_STR(RNDIS_OID_802_11_SUPPORTED_RATES);
-		OID_STR(RNDIS_OID_802_11_CONFIGURATION);
-		OID_STR(RNDIS_OID_802_11_POWER_MODE);
-		OID_STR(RNDIS_OID_802_11_BSSID_LIST);
-#undef OID_STR
-	}
-
-	return "?";
-}
-#else
-static const char *oid_to_string(u32 oid)
-{
-	return "?";
-}
-#endif
-
-/* translate error code */
-static int rndis_error_status(__le32 rndis_status)
-{
-	int ret = -EINVAL;
-	switch (le32_to_cpu(rndis_status)) {
-	case RNDIS_STATUS_SUCCESS:
-		ret = 0;
-		break;
-	case RNDIS_STATUS_FAILURE:
-	case RNDIS_STATUS_INVALID_DATA:
-		ret = -EINVAL;
-		break;
-	case RNDIS_STATUS_NOT_SUPPORTED:
-		ret = -EOPNOTSUPP;
-		break;
-	case RNDIS_STATUS_ADAPTER_NOT_READY:
-	case RNDIS_STATUS_ADAPTER_NOT_OPEN:
-		ret = -EBUSY;
-		break;
-	}
-	return ret;
-}
-
-static int rndis_query_oid(struct usbnet *dev, u32 oid, void *data, int *len)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(dev);
-	union {
-		void			*buf;
-		struct rndis_msg_hdr	*header;
-		struct rndis_query	*get;
-		struct rndis_query_c	*get_c;
-	} u;
-	int ret;
-	size_t buflen, resplen, respoffs, copylen;
-
-	buflen = *len + sizeof(*u.get);
-	if (buflen < CONTROL_BUFFER_SIZE)
-		buflen = CONTROL_BUFFER_SIZE;
-
-	if (buflen > COMMAND_BUFFER_SIZE) {
-		u.buf = kmalloc(buflen, GFP_KERNEL);
-		if (!u.buf)
-			return -ENOMEM;
-	} else {
-		u.buf = priv->command_buffer;
-	}
-
-	mutex_lock(&priv->command_lock);
-
-	memset(u.get, 0, sizeof *u.get);
-	u.get->msg_type = cpu_to_le32(RNDIS_MSG_QUERY);
-	u.get->msg_len = cpu_to_le32(sizeof *u.get);
-	u.get->oid = cpu_to_le32(oid);
-
-	priv->current_command_oid = oid;
-	ret = rndis_command(dev, u.header, buflen);
-	priv->current_command_oid = 0;
-	if (ret < 0)
-		netdev_dbg(dev->net, "%s(%s): rndis_command() failed, %d (%08x)\n",
-			   __func__, oid_to_string(oid), ret,
-			   le32_to_cpu(u.get_c->status));
-
-	if (ret == 0) {
-		resplen = le32_to_cpu(u.get_c->len);
-		respoffs = le32_to_cpu(u.get_c->offset) + 8;
-
-		if (respoffs > buflen) {
-			/* Device returned data offset outside buffer, error. */
-			netdev_dbg(dev->net,
-				   "%s(%s): received invalid data offset: %zu > %zu\n",
-				   __func__, oid_to_string(oid), respoffs, buflen);
-
-			ret = -EINVAL;
-			goto exit_unlock;
-		}
-
-		copylen = min(resplen, buflen - respoffs);
-
-		if (copylen > *len)
-			copylen = *len;
-
-		memcpy(data, u.buf + respoffs, copylen);
-
-		*len = resplen;
-
-		ret = rndis_error_status(u.get_c->status);
-		if (ret < 0)
-			netdev_dbg(dev->net, "%s(%s): device returned error,  0x%08x (%d)\n",
-				   __func__, oid_to_string(oid),
-				   le32_to_cpu(u.get_c->status), ret);
-	}
-
-exit_unlock:
-	mutex_unlock(&priv->command_lock);
-
-	if (u.buf != priv->command_buffer)
-		kfree(u.buf);
-	return ret;
-}
-
-static int rndis_set_oid(struct usbnet *dev, u32 oid, const void *data,
-			 int len)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(dev);
-	union {
-		void			*buf;
-		struct rndis_msg_hdr	*header;
-		struct rndis_set	*set;
-		struct rndis_set_c	*set_c;
-	} u;
-	int ret, buflen;
-
-	buflen = len + sizeof(*u.set);
-	if (buflen < CONTROL_BUFFER_SIZE)
-		buflen = CONTROL_BUFFER_SIZE;
-
-	if (buflen > COMMAND_BUFFER_SIZE) {
-		u.buf = kmalloc(buflen, GFP_KERNEL);
-		if (!u.buf)
-			return -ENOMEM;
-	} else {
-		u.buf = priv->command_buffer;
-	}
-
-	mutex_lock(&priv->command_lock);
-
-	memset(u.set, 0, sizeof *u.set);
-	u.set->msg_type = cpu_to_le32(RNDIS_MSG_SET);
-	u.set->msg_len = cpu_to_le32(sizeof(*u.set) + len);
-	u.set->oid = cpu_to_le32(oid);
-	u.set->len = cpu_to_le32(len);
-	u.set->offset = cpu_to_le32(sizeof(*u.set) - 8);
-	u.set->handle = cpu_to_le32(0);
-	memcpy(u.buf + sizeof(*u.set), data, len);
-
-	priv->current_command_oid = oid;
-	ret = rndis_command(dev, u.header, buflen);
-	priv->current_command_oid = 0;
-	if (ret < 0)
-		netdev_dbg(dev->net, "%s(%s): rndis_command() failed, %d (%08x)\n",
-			   __func__, oid_to_string(oid), ret,
-			   le32_to_cpu(u.set_c->status));
-
-	if (ret == 0) {
-		ret = rndis_error_status(u.set_c->status);
-
-		if (ret < 0)
-			netdev_dbg(dev->net, "%s(%s): device returned error, 0x%08x (%d)\n",
-				   __func__, oid_to_string(oid),
-				   le32_to_cpu(u.set_c->status), ret);
-	}
-
-	mutex_unlock(&priv->command_lock);
-
-	if (u.buf != priv->command_buffer)
-		kfree(u.buf);
-	return ret;
-}
-
-static int rndis_reset(struct usbnet *usbdev)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	struct rndis_reset *reset;
-	int ret;
-
-	mutex_lock(&priv->command_lock);
-
-	reset = (void *)priv->command_buffer;
-	memset(reset, 0, sizeof(*reset));
-	reset->msg_type = cpu_to_le32(RNDIS_MSG_RESET);
-	reset->msg_len = cpu_to_le32(sizeof(*reset));
-	priv->current_command_oid = 0;
-	ret = rndis_command(usbdev, (void *)reset, CONTROL_BUFFER_SIZE);
-
-	mutex_unlock(&priv->command_lock);
-
-	if (ret < 0)
-		return ret;
-	return 0;
-}
-
-/*
- * Specs say that we can only set config parameters only soon after device
- * initialization.
- *   value_type: 0 = u32, 2 = unicode string
- */
-static int rndis_set_config_parameter(struct usbnet *dev, char *param,
-						int value_type, void *value)
-{
-	struct ndis_config_param *infobuf;
-	int value_len, info_len, param_len, ret, i;
-	__le16 *unibuf;
-	__le32 *dst_value;
-
-	if (value_type == 0)
-		value_len = sizeof(__le32);
-	else if (value_type == 2)
-		value_len = strlen(value) * sizeof(__le16);
-	else
-		return -EINVAL;
-
-	param_len = strlen(param) * sizeof(__le16);
-	info_len = sizeof(*infobuf) + param_len + value_len;
-
-#ifdef DEBUG
-	info_len += 12;
-#endif
-	infobuf = kmalloc(info_len, GFP_KERNEL);
-	if (!infobuf)
-		return -ENOMEM;
-
-#ifdef DEBUG
-	info_len -= 12;
-	/* extra 12 bytes are for padding (debug output) */
-	memset(infobuf, 0xCC, info_len + 12);
-#endif
-
-	if (value_type == 2)
-		netdev_dbg(dev->net, "setting config parameter: %s, value: %s\n",
-			   param, (u8 *)value);
-	else
-		netdev_dbg(dev->net, "setting config parameter: %s, value: %d\n",
-			   param, *(u32 *)value);
-
-	infobuf->name_offs = cpu_to_le32(sizeof(*infobuf));
-	infobuf->name_length = cpu_to_le32(param_len);
-	infobuf->type = cpu_to_le32(value_type);
-	infobuf->value_offs = cpu_to_le32(sizeof(*infobuf) + param_len);
-	infobuf->value_length = cpu_to_le32(value_len);
-
-	/* simple string to unicode string conversion */
-	unibuf = (void *)infobuf + sizeof(*infobuf);
-	for (i = 0; i < param_len / sizeof(__le16); i++)
-		unibuf[i] = cpu_to_le16(param[i]);
-
-	if (value_type == 2) {
-		unibuf = (void *)infobuf + sizeof(*infobuf) + param_len;
-		for (i = 0; i < value_len / sizeof(__le16); i++)
-			unibuf[i] = cpu_to_le16(((u8 *)value)[i]);
-	} else {
-		dst_value = (void *)infobuf + sizeof(*infobuf) + param_len;
-		*dst_value = cpu_to_le32(*(u32 *)value);
-	}
-
-#ifdef DEBUG
-	netdev_dbg(dev->net, "info buffer (len: %d)\n", info_len);
-	for (i = 0; i < info_len; i += 12) {
-		u32 *tmp = (u32 *)((u8 *)infobuf + i);
-		netdev_dbg(dev->net, "%08X:%08X:%08X\n",
-			   cpu_to_be32(tmp[0]),
-			   cpu_to_be32(tmp[1]),
-			   cpu_to_be32(tmp[2]));
-	}
-#endif
-
-	ret = rndis_set_oid(dev, RNDIS_OID_GEN_RNDIS_CONFIG_PARAMETER,
-							infobuf, info_len);
-	if (ret != 0)
-		netdev_dbg(dev->net, "setting rndis config parameter failed, %d\n",
-			   ret);
-
-	kfree(infobuf);
-	return ret;
-}
-
-static int rndis_set_config_parameter_str(struct usbnet *dev,
-						char *param, char *value)
-{
-	return rndis_set_config_parameter(dev, param, 2, value);
-}
-
-/*
- * data conversion functions
- */
-static int level_to_qual(int level)
-{
-	int qual = 100 * (level - WL_NOISE) / (WL_SIGMAX - WL_NOISE);
-	return qual >= 0 ? (qual <= 100 ? qual : 100) : 0;
-}
-
-/*
- * common functions
- */
-static int set_infra_mode(struct usbnet *usbdev, int mode);
-static void restore_keys(struct usbnet *usbdev);
-static int rndis_check_bssid_list(struct usbnet *usbdev, u8 *match_bssid,
-					bool *matched);
-
-static int rndis_start_bssid_list_scan(struct usbnet *usbdev)
-{
-	__le32 tmp;
-
-	/* Note: RNDIS_OID_802_11_BSSID_LIST_SCAN clears internal BSS list. */
-	tmp = cpu_to_le32(1);
-	return rndis_set_oid(usbdev, RNDIS_OID_802_11_BSSID_LIST_SCAN, &tmp,
-							sizeof(tmp));
-}
-
-static int set_essid(struct usbnet *usbdev, struct ndis_80211_ssid *ssid)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	int ret;
-
-	ret = rndis_set_oid(usbdev, RNDIS_OID_802_11_SSID,
-			    ssid, sizeof(*ssid));
-	if (ret < 0) {
-		netdev_warn(usbdev->net, "setting SSID failed (%08X)\n", ret);
-		return ret;
-	}
-	if (ret == 0) {
-		priv->radio_on = true;
-		netdev_dbg(usbdev->net, "%s(): radio_on = true\n", __func__);
-	}
-
-	return ret;
-}
-
-static int set_bssid(struct usbnet *usbdev, const u8 *bssid)
-{
-	int ret;
-
-	ret = rndis_set_oid(usbdev, RNDIS_OID_802_11_BSSID,
-			    bssid, ETH_ALEN);
-	if (ret < 0) {
-		netdev_warn(usbdev->net, "setting BSSID[%pM] failed (%08X)\n",
-			    bssid, ret);
-		return ret;
-	}
-
-	return ret;
-}
-
-static int clear_bssid(struct usbnet *usbdev)
-{
-	static const u8 broadcast_mac[ETH_ALEN] = {
-		0xff, 0xff, 0xff, 0xff, 0xff, 0xff
-	};
-
-	return set_bssid(usbdev, broadcast_mac);
-}
-
-static int get_bssid(struct usbnet *usbdev, u8 bssid[ETH_ALEN])
-{
-	int ret, len;
-
-	len = ETH_ALEN;
-	ret = rndis_query_oid(usbdev, RNDIS_OID_802_11_BSSID,
-			      bssid, &len);
-
-	if (ret != 0)
-		eth_zero_addr(bssid);
-
-	return ret;
-}
-
-static int get_association_info(struct usbnet *usbdev,
-			struct ndis_80211_assoc_info *info, int len)
-{
-	return rndis_query_oid(usbdev,
-			RNDIS_OID_802_11_ASSOCIATION_INFORMATION,
-			info, &len);
-}
-
-static bool is_associated(struct usbnet *usbdev)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	u8 bssid[ETH_ALEN];
-
-	if (!priv->radio_on)
-		return false;
-
-	return (get_bssid(usbdev, bssid) == 0 && !is_zero_ether_addr(bssid));
-}
-
-static int disassociate(struct usbnet *usbdev, bool reset_ssid)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	struct ndis_80211_ssid ssid;
-	int i, ret = 0;
-
-	if (priv->radio_on) {
-		ret = rndis_set_oid(usbdev,
-				RNDIS_OID_802_11_DISASSOCIATE,
-				NULL, 0);
-		if (ret == 0) {
-			priv->radio_on = false;
-			netdev_dbg(usbdev->net, "%s(): radio_on = false\n",
-				   __func__);
-
-			if (reset_ssid)
-				msleep(100);
-		}
-	}
-
-	/* disassociate causes radio to be turned off; if reset_ssid
-	 * is given, set random ssid to enable radio */
-	if (reset_ssid) {
-		/* Set device to infrastructure mode so we don't get ad-hoc
-		 * 'media connect' indications with the random ssid.
-		 */
-		set_infra_mode(usbdev, NDIS_80211_INFRA_INFRA);
-
-		ssid.length = cpu_to_le32(sizeof(ssid.essid));
-		get_random_bytes(&ssid.essid[2], sizeof(ssid.essid)-2);
-		ssid.essid[0] = 0x1;
-		ssid.essid[1] = 0xff;
-		for (i = 2; i < sizeof(ssid.essid); i++)
-			ssid.essid[i] = 0x1 + (ssid.essid[i] * 0xfe / 0xff);
-		ret = set_essid(usbdev, &ssid);
-	}
-	return ret;
-}
-
-static int set_auth_mode(struct usbnet *usbdev, u32 wpa_version,
-				enum nl80211_auth_type auth_type, int keymgmt)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	__le32 tmp;
-	int auth_mode, ret;
-
-	netdev_dbg(usbdev->net, "%s(): wpa_version=0x%x authalg=0x%x keymgmt=0x%x\n",
-		   __func__, wpa_version, auth_type, keymgmt);
-
-	if (wpa_version & NL80211_WPA_VERSION_2) {
-		if (keymgmt & RNDIS_WLAN_KEY_MGMT_802_1X)
-			auth_mode = NDIS_80211_AUTH_WPA2;
-		else
-			auth_mode = NDIS_80211_AUTH_WPA2_PSK;
-	} else if (wpa_version & NL80211_WPA_VERSION_1) {
-		if (keymgmt & RNDIS_WLAN_KEY_MGMT_802_1X)
-			auth_mode = NDIS_80211_AUTH_WPA;
-		else if (keymgmt & RNDIS_WLAN_KEY_MGMT_PSK)
-			auth_mode = NDIS_80211_AUTH_WPA_PSK;
-		else
-			auth_mode = NDIS_80211_AUTH_WPA_NONE;
-	} else if (auth_type == NL80211_AUTHTYPE_SHARED_KEY)
-		auth_mode = NDIS_80211_AUTH_SHARED;
-	else if (auth_type == NL80211_AUTHTYPE_OPEN_SYSTEM)
-		auth_mode = NDIS_80211_AUTH_OPEN;
-	else if (auth_type == NL80211_AUTHTYPE_AUTOMATIC)
-		auth_mode = NDIS_80211_AUTH_AUTO_SWITCH;
-	else
-		return -ENOTSUPP;
-
-	tmp = cpu_to_le32(auth_mode);
-	ret = rndis_set_oid(usbdev,
-			    RNDIS_OID_802_11_AUTHENTICATION_MODE,
-			    &tmp, sizeof(tmp));
-	if (ret != 0) {
-		netdev_warn(usbdev->net, "setting auth mode failed (%08X)\n",
-			    ret);
-		return ret;
-	}
-
-	priv->wpa_version = wpa_version;
-
-	return 0;
-}
-
-static int set_priv_filter(struct usbnet *usbdev)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	__le32 tmp;
-
-	netdev_dbg(usbdev->net, "%s(): wpa_version=0x%x\n",
-		   __func__, priv->wpa_version);
-
-	if (priv->wpa_version & NL80211_WPA_VERSION_2 ||
-	    priv->wpa_version & NL80211_WPA_VERSION_1)
-		tmp = cpu_to_le32(NDIS_80211_PRIV_8021X_WEP);
-	else
-		tmp = cpu_to_le32(NDIS_80211_PRIV_ACCEPT_ALL);
-
-	return rndis_set_oid(usbdev,
-			     RNDIS_OID_802_11_PRIVACY_FILTER, &tmp,
-			     sizeof(tmp));
-}
-
-static int set_encr_mode(struct usbnet *usbdev, int pairwise, int groupwise)
-{
-	__le32 tmp;
-	int encr_mode, ret;
-
-	netdev_dbg(usbdev->net, "%s(): cipher_pair=0x%x cipher_group=0x%x\n",
-		   __func__, pairwise, groupwise);
-
-	if (pairwise & RNDIS_WLAN_ALG_CCMP)
-		encr_mode = NDIS_80211_ENCR_CCMP_ENABLED;
-	else if (pairwise & RNDIS_WLAN_ALG_TKIP)
-		encr_mode = NDIS_80211_ENCR_TKIP_ENABLED;
-	else if (pairwise & RNDIS_WLAN_ALG_WEP)
-		encr_mode = NDIS_80211_ENCR_WEP_ENABLED;
-	else if (groupwise & RNDIS_WLAN_ALG_CCMP)
-		encr_mode = NDIS_80211_ENCR_CCMP_ENABLED;
-	else if (groupwise & RNDIS_WLAN_ALG_TKIP)
-		encr_mode = NDIS_80211_ENCR_TKIP_ENABLED;
-	else
-		encr_mode = NDIS_80211_ENCR_DISABLED;
-
-	tmp = cpu_to_le32(encr_mode);
-	ret = rndis_set_oid(usbdev,
-			RNDIS_OID_802_11_ENCRYPTION_STATUS, &tmp,
-			sizeof(tmp));
-	if (ret != 0) {
-		netdev_warn(usbdev->net, "setting encr mode failed (%08X)\n",
-			    ret);
-		return ret;
-	}
-
-	return 0;
-}
-
-static int set_infra_mode(struct usbnet *usbdev, int mode)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	__le32 tmp;
-	int ret;
-
-	netdev_dbg(usbdev->net, "%s(): infra_mode=0x%x\n",
-		   __func__, priv->infra_mode);
-
-	tmp = cpu_to_le32(mode);
-	ret = rndis_set_oid(usbdev,
-			    RNDIS_OID_802_11_INFRASTRUCTURE_MODE,
-			    &tmp, sizeof(tmp));
-	if (ret != 0) {
-		netdev_warn(usbdev->net, "setting infra mode failed (%08X)\n",
-			    ret);
-		return ret;
-	}
-
-	/* NDIS drivers clear keys when infrastructure mode is
-	 * changed. But Linux tools assume otherwise. So set the
-	 * keys */
-	restore_keys(usbdev);
-
-	priv->infra_mode = mode;
-	return 0;
-}
-
-static int set_rts_threshold(struct usbnet *usbdev, u32 rts_threshold)
-{
-	__le32 tmp;
-
-	netdev_dbg(usbdev->net, "%s(): %i\n", __func__, rts_threshold);
-
-	if (rts_threshold == -1 || rts_threshold > 2347)
-		rts_threshold = 2347;
-
-	tmp = cpu_to_le32(rts_threshold);
-	return rndis_set_oid(usbdev,
-			     RNDIS_OID_802_11_RTS_THRESHOLD,
-			     &tmp, sizeof(tmp));
-}
-
-static int set_frag_threshold(struct usbnet *usbdev, u32 frag_threshold)
-{
-	__le32 tmp;
-
-	netdev_dbg(usbdev->net, "%s(): %i\n", __func__, frag_threshold);
-
-	if (frag_threshold < 256 || frag_threshold > 2346)
-		frag_threshold = 2346;
-
-	tmp = cpu_to_le32(frag_threshold);
-	return rndis_set_oid(usbdev,
-			RNDIS_OID_802_11_FRAGMENTATION_THRESHOLD,
-			&tmp, sizeof(tmp));
-}
-
-static void set_default_iw_params(struct usbnet *usbdev)
-{
-	set_infra_mode(usbdev, NDIS_80211_INFRA_INFRA);
-	set_auth_mode(usbdev, 0, NL80211_AUTHTYPE_OPEN_SYSTEM,
-						RNDIS_WLAN_KEY_MGMT_NONE);
-	set_priv_filter(usbdev);
-	set_encr_mode(usbdev, RNDIS_WLAN_ALG_NONE, RNDIS_WLAN_ALG_NONE);
-}
-
-static int deauthenticate(struct usbnet *usbdev)
-{
-	int ret;
-
-	ret = disassociate(usbdev, true);
-	set_default_iw_params(usbdev);
-	return ret;
-}
-
-static int set_channel(struct usbnet *usbdev, int channel)
-{
-	struct ndis_80211_conf config;
-	unsigned int dsconfig;
-	int len, ret;
-
-	netdev_dbg(usbdev->net, "%s(%d)\n", __func__, channel);
-
-	/* this OID is valid only when not associated */
-	if (is_associated(usbdev))
-		return 0;
-
-	dsconfig = 1000 *
-		ieee80211_channel_to_frequency(channel, NL80211_BAND_2GHZ);
-
-	len = sizeof(config);
-	ret = rndis_query_oid(usbdev,
-			RNDIS_OID_802_11_CONFIGURATION,
-			&config, &len);
-	if (ret < 0) {
-		netdev_dbg(usbdev->net, "%s(): querying configuration failed\n",
-			   __func__);
-		return ret;
-	}
-
-	config.ds_config = cpu_to_le32(dsconfig);
-	ret = rndis_set_oid(usbdev,
-			RNDIS_OID_802_11_CONFIGURATION,
-			&config, sizeof(config));
-
-	netdev_dbg(usbdev->net, "%s(): %d -> %d\n", __func__, channel, ret);
-
-	return ret;
-}
-
-static struct ieee80211_channel *get_current_channel(struct usbnet *usbdev,
-						     u32 *beacon_period)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	struct ieee80211_channel *channel;
-	struct ndis_80211_conf config;
-	int len, ret;
-
-	/* Get channel and beacon interval */
-	len = sizeof(config);
-	ret = rndis_query_oid(usbdev,
-			RNDIS_OID_802_11_CONFIGURATION,
-			&config, &len);
-	netdev_dbg(usbdev->net, "%s(): RNDIS_OID_802_11_CONFIGURATION -> %d\n",
-				__func__, ret);
-	if (ret < 0)
-		return NULL;
-
-	channel = ieee80211_get_channel(priv->wdev.wiphy,
-				KHZ_TO_MHZ(le32_to_cpu(config.ds_config)));
-	if (!channel)
-		return NULL;
-
-	if (beacon_period)
-		*beacon_period = le32_to_cpu(config.beacon_period);
-	return channel;
-}
-
-/* index must be 0 - N, as per NDIS  */
-static int add_wep_key(struct usbnet *usbdev, const u8 *key, int key_len,
-								u8 index)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	struct ndis_80211_wep_key ndis_key;
-	u32 cipher;
-	int ret;
-
-	netdev_dbg(usbdev->net, "%s(idx: %d, len: %d)\n",
-		   __func__, index, key_len);
-
-	if (index >= RNDIS_WLAN_NUM_KEYS)
-		return -EINVAL;
-
-	if (key_len == 5)
-		cipher = WLAN_CIPHER_SUITE_WEP40;
-	else if (key_len == 13)
-		cipher = WLAN_CIPHER_SUITE_WEP104;
-	else
-		return -EINVAL;
-
-	memset(&ndis_key, 0, sizeof(ndis_key));
-
-	ndis_key.size = cpu_to_le32(sizeof(ndis_key));
-	ndis_key.length = cpu_to_le32(key_len);
-	ndis_key.index = cpu_to_le32(index);
-	memcpy(&ndis_key.material, key, key_len);
-
-	if (index == priv->encr_tx_key_index) {
-		ndis_key.index |= NDIS_80211_ADDWEP_TRANSMIT_KEY;
-		ret = set_encr_mode(usbdev, RNDIS_WLAN_ALG_WEP,
-							RNDIS_WLAN_ALG_NONE);
-		if (ret)
-			netdev_warn(usbdev->net, "encryption couldn't be enabled (%08X)\n",
-				    ret);
-	}
-
-	ret = rndis_set_oid(usbdev,
-			RNDIS_OID_802_11_ADD_WEP, &ndis_key,
-			sizeof(ndis_key));
-	if (ret != 0) {
-		netdev_warn(usbdev->net, "adding encryption key %d failed (%08X)\n",
-			    index + 1, ret);
-		return ret;
-	}
-
-	priv->encr_keys[index].len = key_len;
-	priv->encr_keys[index].cipher = cipher;
-	memcpy(&priv->encr_keys[index].material, key, key_len);
-	eth_broadcast_addr(priv->encr_keys[index].bssid);
-
-	return 0;
-}
-
-static int add_wpa_key(struct usbnet *usbdev, const u8 *key, int key_len,
-			u8 index, const u8 *addr, const u8 *rx_seq,
-			int seq_len, u32 cipher, __le32 flags)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	struct ndis_80211_key ndis_key;
-	bool is_addr_ok;
-	int ret;
-
-	if (index >= RNDIS_WLAN_NUM_KEYS) {
-		netdev_dbg(usbdev->net, "%s(): index out of range (%i)\n",
-			   __func__, index);
-		return -EINVAL;
-	}
-	if (key_len > sizeof(ndis_key.material) || key_len < 0) {
-		netdev_dbg(usbdev->net, "%s(): key length out of range (%i)\n",
-			   __func__, key_len);
-		return -EINVAL;
-	}
-	if (flags & NDIS_80211_ADDKEY_SET_INIT_RECV_SEQ) {
-		if (!rx_seq || seq_len <= 0) {
-			netdev_dbg(usbdev->net, "%s(): recv seq flag without buffer\n",
-				   __func__);
-			return -EINVAL;
-		}
-		if (rx_seq && seq_len > sizeof(ndis_key.rsc)) {
-			netdev_dbg(usbdev->net, "%s(): too big recv seq buffer\n", __func__);
-			return -EINVAL;
-		}
-	}
-
-	is_addr_ok = addr && !is_zero_ether_addr(addr) &&
-					!is_broadcast_ether_addr(addr);
-	if ((flags & NDIS_80211_ADDKEY_PAIRWISE_KEY) && !is_addr_ok) {
-		netdev_dbg(usbdev->net, "%s(): pairwise but bssid invalid (%pM)\n",
-			   __func__, addr);
-		return -EINVAL;
-	}
-
-	netdev_dbg(usbdev->net, "%s(%i): flags:%i%i%i\n",
-		   __func__, index,
-		   !!(flags & NDIS_80211_ADDKEY_TRANSMIT_KEY),
-		   !!(flags & NDIS_80211_ADDKEY_PAIRWISE_KEY),
-		   !!(flags & NDIS_80211_ADDKEY_SET_INIT_RECV_SEQ));
-
-	memset(&ndis_key, 0, sizeof(ndis_key));
-
-	ndis_key.size = cpu_to_le32(sizeof(ndis_key) -
-				sizeof(ndis_key.material) + key_len);
-	ndis_key.length = cpu_to_le32(key_len);
-	ndis_key.index = cpu_to_le32(index) | flags;
-
-	if (cipher == WLAN_CIPHER_SUITE_TKIP && key_len == 32) {
-		/* wpa_supplicant gives us the Michael MIC RX/TX keys in
-		 * different order than NDIS spec, so swap the order here. */
-		memcpy(ndis_key.material, key, 16);
-		memcpy(ndis_key.material + 16, key + 24, 8);
-		memcpy(ndis_key.material + 24, key + 16, 8);
-	} else
-		memcpy(ndis_key.material, key, key_len);
-
-	if (flags & NDIS_80211_ADDKEY_SET_INIT_RECV_SEQ)
-		memcpy(ndis_key.rsc, rx_seq, seq_len);
-
-	if (flags & NDIS_80211_ADDKEY_PAIRWISE_KEY) {
-		/* pairwise key */
-		memcpy(ndis_key.bssid, addr, ETH_ALEN);
-	} else {
-		/* group key */
-		if (priv->infra_mode == NDIS_80211_INFRA_ADHOC)
-			eth_broadcast_addr(ndis_key.bssid);
-		else
-			get_bssid(usbdev, ndis_key.bssid);
-	}
-
-	ret = rndis_set_oid(usbdev,
-			RNDIS_OID_802_11_ADD_KEY, &ndis_key,
-			le32_to_cpu(ndis_key.size));
-	netdev_dbg(usbdev->net, "%s(): RNDIS_OID_802_11_ADD_KEY -> %08X\n",
-		   __func__, ret);
-	if (ret != 0)
-		return ret;
-
-	memset(&priv->encr_keys[index], 0, sizeof(priv->encr_keys[index]));
-	priv->encr_keys[index].len = key_len;
-	priv->encr_keys[index].cipher = cipher;
-	memcpy(&priv->encr_keys[index].material, key, key_len);
-	if (flags & NDIS_80211_ADDKEY_PAIRWISE_KEY)
-		memcpy(&priv->encr_keys[index].bssid, ndis_key.bssid, ETH_ALEN);
-	else
-		eth_broadcast_addr(priv->encr_keys[index].bssid);
-
-	if (flags & NDIS_80211_ADDKEY_TRANSMIT_KEY)
-		priv->encr_tx_key_index = index;
-
-	return 0;
-}
-
-static int restore_key(struct usbnet *usbdev, u8 key_idx)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	struct rndis_wlan_encr_key key;
-
-	if (is_wpa_key(priv, key_idx))
-		return 0;
-
-	key = priv->encr_keys[key_idx];
-
-	netdev_dbg(usbdev->net, "%s(): %i:%i\n", __func__, key_idx, key.len);
-
-	if (key.len == 0)
-		return 0;
-
-	return add_wep_key(usbdev, key.material, key.len, key_idx);
-}
-
-static void restore_keys(struct usbnet *usbdev)
-{
-	int i;
-
-	for (i = 0; i < 4; i++)
-		restore_key(usbdev, i);
-}
-
-static void clear_key(struct rndis_wlan_private *priv, u8 idx)
-{
-	memset(&priv->encr_keys[idx], 0, sizeof(priv->encr_keys[idx]));
-}
-
-/* remove_key is for both wep and wpa */
-static int remove_key(struct usbnet *usbdev, u8 index, const u8 *bssid)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	struct ndis_80211_remove_key remove_key;
-	__le32 keyindex;
-	bool is_wpa;
-	int ret;
-
-	if (index >= RNDIS_WLAN_NUM_KEYS)
-		return -ENOENT;
-
-	if (priv->encr_keys[index].len == 0)
-		return 0;
-
-	is_wpa = is_wpa_key(priv, index);
-
-	netdev_dbg(usbdev->net, "%s(): %i:%s:%i\n",
-		   __func__, index, is_wpa ? "wpa" : "wep",
-		   priv->encr_keys[index].len);
-
-	clear_key(priv, index);
-
-	if (is_wpa) {
-		remove_key.size = cpu_to_le32(sizeof(remove_key));
-		remove_key.index = cpu_to_le32(index);
-		if (bssid) {
-			/* pairwise key */
-			if (!is_broadcast_ether_addr(bssid))
-				remove_key.index |=
-					NDIS_80211_ADDKEY_PAIRWISE_KEY;
-			memcpy(remove_key.bssid, bssid,
-					sizeof(remove_key.bssid));
-		} else
-			memset(remove_key.bssid, 0xff,
-						sizeof(remove_key.bssid));
-
-		ret = rndis_set_oid(usbdev,
-				RNDIS_OID_802_11_REMOVE_KEY,
-				&remove_key, sizeof(remove_key));
-		if (ret != 0)
-			return ret;
-	} else {
-		keyindex = cpu_to_le32(index);
-		ret = rndis_set_oid(usbdev,
-				RNDIS_OID_802_11_REMOVE_WEP,
-				&keyindex, sizeof(keyindex));
-		if (ret != 0) {
-			netdev_warn(usbdev->net,
-				    "removing encryption key %d failed (%08X)\n",
-				    index, ret);
-			return ret;
-		}
-	}
-
-	/* if it is transmit key, disable encryption */
-	if (index == priv->encr_tx_key_index)
-		set_encr_mode(usbdev, RNDIS_WLAN_ALG_NONE, RNDIS_WLAN_ALG_NONE);
-
-	return 0;
-}
-
-static void set_multicast_list(struct usbnet *usbdev)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	struct netdev_hw_addr *ha;
-	__le32 filter, basefilter;
-	int ret;
-	char *mc_addrs = NULL;
-	int mc_count;
-
-	basefilter = filter = cpu_to_le32(RNDIS_PACKET_TYPE_DIRECTED |
-					  RNDIS_PACKET_TYPE_BROADCAST);
-
-	if (usbdev->net->flags & IFF_PROMISC) {
-		filter |= cpu_to_le32(RNDIS_PACKET_TYPE_PROMISCUOUS |
-				      RNDIS_PACKET_TYPE_ALL_LOCAL);
-	} else if (usbdev->net->flags & IFF_ALLMULTI) {
-		filter |= cpu_to_le32(RNDIS_PACKET_TYPE_ALL_MULTICAST);
-	}
-
-	if (filter != basefilter)
-		goto set_filter;
-
-	/*
-	 * mc_list should be accessed holding the lock, so copy addresses to
-	 * local buffer first.
-	 */
-	netif_addr_lock_bh(usbdev->net);
-	mc_count = netdev_mc_count(usbdev->net);
-	if (mc_count > priv->multicast_size) {
-		filter |= cpu_to_le32(RNDIS_PACKET_TYPE_ALL_MULTICAST);
-	} else if (mc_count) {
-		int i = 0;
-
-		mc_addrs = kmalloc_array(mc_count, ETH_ALEN, GFP_ATOMIC);
-		if (!mc_addrs) {
-			netif_addr_unlock_bh(usbdev->net);
-			return;
-		}
-
-		netdev_for_each_mc_addr(ha, usbdev->net)
-			memcpy(mc_addrs + i++ * ETH_ALEN,
-			       ha->addr, ETH_ALEN);
-	}
-	netif_addr_unlock_bh(usbdev->net);
-
-	if (filter != basefilter)
-		goto set_filter;
-
-	if (mc_count) {
-		ret = rndis_set_oid(usbdev,
-				RNDIS_OID_802_3_MULTICAST_LIST,
-				mc_addrs, mc_count * ETH_ALEN);
-		kfree(mc_addrs);
-		if (ret == 0)
-			filter |= cpu_to_le32(RNDIS_PACKET_TYPE_MULTICAST);
-		else
-			filter |= cpu_to_le32(RNDIS_PACKET_TYPE_ALL_MULTICAST);
-
-		netdev_dbg(usbdev->net, "RNDIS_OID_802_3_MULTICAST_LIST(%d, max: %d) -> %d\n",
-			   mc_count, priv->multicast_size, ret);
-	}
-
-set_filter:
-	ret = rndis_set_oid(usbdev, RNDIS_OID_GEN_CURRENT_PACKET_FILTER, &filter,
-							sizeof(filter));
-	if (ret < 0) {
-		netdev_warn(usbdev->net, "couldn't set packet filter: %08x\n",
-			    le32_to_cpu(filter));
-	}
-
-	netdev_dbg(usbdev->net, "RNDIS_OID_GEN_CURRENT_PACKET_FILTER(%08x) -> %d\n",
-		   le32_to_cpu(filter), ret);
-}
-
-#ifdef DEBUG
-static void debug_print_pmkids(struct usbnet *usbdev,
-				struct ndis_80211_pmkid *pmkids,
-				const char *func_str)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	int i, len, count, max_pmkids, entry_len;
-
-	max_pmkids = priv->wdev.wiphy->max_num_pmkids;
-	len = le32_to_cpu(pmkids->length);
-	count = le32_to_cpu(pmkids->bssid_info_count);
-
-	entry_len = (count > 0) ? (len - sizeof(*pmkids)) / count : -1;
-
-	netdev_dbg(usbdev->net, "%s(): %d PMKIDs (data len: %d, entry len: "
-				"%d)\n", func_str, count, len, entry_len);
-
-	if (count > max_pmkids)
-		count = max_pmkids;
-
-	for (i = 0; i < count; i++) {
-		u32 *tmp = (u32 *)pmkids->bssid_info[i].pmkid;
-
-		netdev_dbg(usbdev->net, "%s():  bssid: %pM, "
-				"pmkid: %08X:%08X:%08X:%08X\n",
-				func_str, pmkids->bssid_info[i].bssid,
-				cpu_to_be32(tmp[0]), cpu_to_be32(tmp[1]),
-				cpu_to_be32(tmp[2]), cpu_to_be32(tmp[3]));
-	}
-}
-#else
-static void debug_print_pmkids(struct usbnet *usbdev,
-				struct ndis_80211_pmkid *pmkids,
-				const char *func_str)
-{
-	return;
-}
-#endif
-
-static struct ndis_80211_pmkid *get_device_pmkids(struct usbnet *usbdev)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	struct ndis_80211_pmkid *pmkids;
-	int len, ret, max_pmkids;
-
-	max_pmkids = priv->wdev.wiphy->max_num_pmkids;
-	len = struct_size(pmkids, bssid_info, max_pmkids);
-
-	pmkids = kzalloc(len, GFP_KERNEL);
-	if (!pmkids)
-		return ERR_PTR(-ENOMEM);
-
-	pmkids->length = cpu_to_le32(len);
-	pmkids->bssid_info_count = cpu_to_le32(max_pmkids);
-
-	ret = rndis_query_oid(usbdev, RNDIS_OID_802_11_PMKID,
-			pmkids, &len);
-	if (ret < 0) {
-		netdev_dbg(usbdev->net, "%s(): RNDIS_OID_802_11_PMKID(%d, %d)"
-				" -> %d\n", __func__, len, max_pmkids, ret);
-
-		kfree(pmkids);
-		return ERR_PTR(ret);
-	}
-
-	if (le32_to_cpu(pmkids->bssid_info_count) > max_pmkids)
-		pmkids->bssid_info_count = cpu_to_le32(max_pmkids);
-
-	debug_print_pmkids(usbdev, pmkids, __func__);
-
-	return pmkids;
-}
-
-static int set_device_pmkids(struct usbnet *usbdev,
-				struct ndis_80211_pmkid *pmkids)
-{
-	int ret, len, num_pmkids;
-
-	num_pmkids = le32_to_cpu(pmkids->bssid_info_count);
-	len = struct_size(pmkids, bssid_info, num_pmkids);
-	pmkids->length = cpu_to_le32(len);
-
-	debug_print_pmkids(usbdev, pmkids, __func__);
-
-	ret = rndis_set_oid(usbdev, RNDIS_OID_802_11_PMKID, pmkids,
-			    le32_to_cpu(pmkids->length));
-	if (ret < 0) {
-		netdev_dbg(usbdev->net, "%s(): RNDIS_OID_802_11_PMKID(%d, %d) -> %d"
-				"\n", __func__, len, num_pmkids, ret);
-	}
-
-	kfree(pmkids);
-	return ret;
-}
-
-static struct ndis_80211_pmkid *remove_pmkid(struct usbnet *usbdev,
-						struct ndis_80211_pmkid *pmkids,
-						struct cfg80211_pmksa *pmksa,
-						int max_pmkids)
-{
-	int i, err;
-	unsigned int count;
-
-	count = le32_to_cpu(pmkids->bssid_info_count);
-
-	if (count > max_pmkids)
-		count = max_pmkids;
-
-	for (i = 0; i < count; i++)
-		if (ether_addr_equal(pmkids->bssid_info[i].bssid,
-				     pmksa->bssid))
-			break;
-
-	/* pmkid not found */
-	if (i == count) {
-		netdev_dbg(usbdev->net, "%s(): bssid not found (%pM)\n",
-					__func__, pmksa->bssid);
-		err = -ENOENT;
-		goto error;
-	}
-
-	for (; i + 1 < count; i++)
-		pmkids->bssid_info[i] = pmkids->bssid_info[i + 1];
-
-	count--;
-	pmkids->length = cpu_to_le32(struct_size(pmkids, bssid_info, count));
-	pmkids->bssid_info_count = cpu_to_le32(count);
-
-	return pmkids;
-error:
-	kfree(pmkids);
-	return ERR_PTR(err);
-}
-
-static struct ndis_80211_pmkid *update_pmkid(struct usbnet *usbdev,
-						struct ndis_80211_pmkid *pmkids,
-						struct cfg80211_pmksa *pmksa,
-						int max_pmkids)
-{
-	struct ndis_80211_pmkid *new_pmkids;
-	int i, err, newlen;
-	unsigned int count;
-
-	count = le32_to_cpu(pmkids->bssid_info_count);
-
-	if (count > max_pmkids)
-		count = max_pmkids;
-
-	/* update with new pmkid */
-	for (i = 0; i < count; i++) {
-		if (!ether_addr_equal(pmkids->bssid_info[i].bssid,
-				      pmksa->bssid))
-			continue;
-
-		memcpy(pmkids->bssid_info[i].pmkid, pmksa->pmkid,
-								WLAN_PMKID_LEN);
-
-		return pmkids;
-	}
-
-	/* out of space, return error */
-	if (i == max_pmkids) {
-		netdev_dbg(usbdev->net, "%s(): out of space\n", __func__);
-		err = -ENOSPC;
-		goto error;
-	}
-
-	/* add new pmkid */
-	newlen = struct_size(pmkids, bssid_info, count + 1);
-
-	new_pmkids = krealloc(pmkids, newlen, GFP_KERNEL);
-	if (!new_pmkids) {
-		err = -ENOMEM;
-		goto error;
-	}
-	pmkids = new_pmkids;
-
-	pmkids->length = cpu_to_le32(newlen);
-	pmkids->bssid_info_count = cpu_to_le32(count + 1);
-
-	memcpy(pmkids->bssid_info[count].bssid, pmksa->bssid, ETH_ALEN);
-	memcpy(pmkids->bssid_info[count].pmkid, pmksa->pmkid, WLAN_PMKID_LEN);
-
-	return pmkids;
-error:
-	kfree(pmkids);
-	return ERR_PTR(err);
-}
-
-/*
- * cfg80211 ops
- */
-static int rndis_change_virtual_intf(struct wiphy *wiphy,
-					struct net_device *dev,
-					enum nl80211_iftype type,
-					struct vif_params *params)
-{
-	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
-	struct usbnet *usbdev = priv->usbdev;
-	int mode;
-
-	switch (type) {
-	case NL80211_IFTYPE_ADHOC:
-		mode = NDIS_80211_INFRA_ADHOC;
-		break;
-	case NL80211_IFTYPE_STATION:
-		mode = NDIS_80211_INFRA_INFRA;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	priv->wdev.iftype = type;
-
-	return set_infra_mode(usbdev, mode);
-}
-
-static int rndis_set_wiphy_params(struct wiphy *wiphy, u32 changed)
-{
-	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
-	struct usbnet *usbdev = priv->usbdev;
-	int err;
-
-	if (changed & WIPHY_PARAM_FRAG_THRESHOLD) {
-		err = set_frag_threshold(usbdev, wiphy->frag_threshold);
-		if (err < 0)
-			return err;
-	}
-
-	if (changed & WIPHY_PARAM_RTS_THRESHOLD) {
-		err = set_rts_threshold(usbdev, wiphy->rts_threshold);
-		if (err < 0)
-			return err;
-	}
-
-	return 0;
-}
-
-static int rndis_set_tx_power(struct wiphy *wiphy,
-			      struct wireless_dev *wdev,
-			      enum nl80211_tx_power_setting type,
-			      int mbm)
-{
-	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
-	struct usbnet *usbdev = priv->usbdev;
-
-	netdev_dbg(usbdev->net, "%s(): type:0x%x mbm:%i\n",
-		   __func__, type, mbm);
-
-	if (mbm < 0 || (mbm % 100))
-		return -ENOTSUPP;
-
-	/* Device doesn't support changing txpower after initialization, only
-	 * turn off/on radio. Support 'auto' mode and setting same dBm that is
-	 * currently used.
-	 */
-	if (type == NL80211_TX_POWER_AUTOMATIC ||
-	    MBM_TO_DBM(mbm) == get_bcm4320_power_dbm(priv)) {
-		if (!priv->radio_on)
-			disassociate(usbdev, true); /* turn on radio */
-
-		return 0;
-	}
-
-	return -ENOTSUPP;
-}
-
-static int rndis_get_tx_power(struct wiphy *wiphy,
-			      struct wireless_dev *wdev,
-			      int *dbm)
-{
-	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
-	struct usbnet *usbdev = priv->usbdev;
-
-	*dbm = get_bcm4320_power_dbm(priv);
-
-	netdev_dbg(usbdev->net, "%s(): dbm:%i\n", __func__, *dbm);
-
-	return 0;
-}
-
-#define SCAN_DELAY_JIFFIES (6 * HZ)
-static int rndis_scan(struct wiphy *wiphy,
-			struct cfg80211_scan_request *request)
-{
-	struct net_device *dev = request->wdev->netdev;
-	struct usbnet *usbdev = netdev_priv(dev);
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	int ret;
-	int delay = SCAN_DELAY_JIFFIES;
-
-	netdev_dbg(usbdev->net, "cfg80211.scan\n");
-
-	/* Get current bssid list from device before new scan, as new scan
-	 * clears internal bssid list.
-	 */
-	rndis_check_bssid_list(usbdev, NULL, NULL);
-
-	if (priv->scan_request && priv->scan_request != request)
-		return -EBUSY;
-
-	priv->scan_request = request;
-
-	ret = rndis_start_bssid_list_scan(usbdev);
-	if (ret == 0) {
-		if (priv->device_type == RNDIS_BCM4320A)
-			delay = HZ;
-
-		/* Wait before retrieving scan results from device */
-		queue_delayed_work(priv->workqueue, &priv->scan_work, delay);
-	}
-
-	return ret;
-}
-
-static bool rndis_bss_info_update(struct usbnet *usbdev,
-				  struct ndis_80211_bssid_ex *bssid)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	struct ieee80211_channel *channel;
-	struct cfg80211_bss *bss;
-	s32 signal;
-	u64 timestamp;
-	u16 capability;
-	u16 beacon_interval;
-	struct ndis_80211_fixed_ies *fixed;
-	int ie_len, bssid_len;
-	u8 *ie;
-
-	netdev_dbg(usbdev->net, " found bssid: '%.32s' [%pM], len: %d\n",
-		   bssid->ssid.essid, bssid->mac, le32_to_cpu(bssid->length));
-
-	/* parse bssid structure */
-	bssid_len = le32_to_cpu(bssid->length);
-
-	if (bssid_len < sizeof(struct ndis_80211_bssid_ex) +
-			sizeof(struct ndis_80211_fixed_ies))
-		return false;
-
-	fixed = (struct ndis_80211_fixed_ies *)bssid->ies;
-
-	ie = (void *)(bssid->ies + sizeof(struct ndis_80211_fixed_ies));
-	ie_len = min(bssid_len - (int)sizeof(*bssid),
-					(int)le32_to_cpu(bssid->ie_length));
-	ie_len -= sizeof(struct ndis_80211_fixed_ies);
-	if (ie_len < 0)
-		return false;
-
-	/* extract data for cfg80211_inform_bss */
-	channel = ieee80211_get_channel(priv->wdev.wiphy,
-			KHZ_TO_MHZ(le32_to_cpu(bssid->config.ds_config)));
-	if (!channel)
-		return false;
-
-	signal = level_to_qual(le32_to_cpu(bssid->rssi));
-	timestamp = le64_to_cpu(*(__le64 *)fixed->timestamp);
-	capability = le16_to_cpu(fixed->capabilities);
-	beacon_interval = le16_to_cpu(fixed->beacon_interval);
-
-	bss = cfg80211_inform_bss(priv->wdev.wiphy, channel,
-				  CFG80211_BSS_FTYPE_UNKNOWN, bssid->mac,
-				  timestamp, capability, beacon_interval,
-				  ie, ie_len, signal, GFP_KERNEL);
-	cfg80211_put_bss(priv->wdev.wiphy, bss);
-
-	return (bss != NULL);
-}
-
-static struct ndis_80211_bssid_ex *next_bssid_list_item(
-					struct ndis_80211_bssid_ex *bssid,
-					int *bssid_len, void *buf, int len)
-{
-	void *buf_end, *bssid_end;
-
-	buf_end = (char *)buf + len;
-	bssid_end = (char *)bssid + *bssid_len;
-
-	if ((int)(buf_end - bssid_end) < sizeof(bssid->length)) {
-		*bssid_len = 0;
-		return NULL;
-	} else {
-		bssid = (void *)((char *)bssid + *bssid_len);
-		*bssid_len = le32_to_cpu(bssid->length);
-		return bssid;
-	}
-}
-
-static bool check_bssid_list_item(struct ndis_80211_bssid_ex *bssid,
-				  int bssid_len, void *buf, int len)
-{
-	void *buf_end, *bssid_end;
-
-	if (!bssid || bssid_len <= 0 || bssid_len > len)
-		return false;
-
-	buf_end = (char *)buf + len;
-	bssid_end = (char *)bssid + bssid_len;
-
-	return (int)(buf_end - bssid_end) >= 0 && (int)(bssid_end - buf) >= 0;
-}
-
-static int rndis_check_bssid_list(struct usbnet *usbdev, u8 *match_bssid,
-					bool *matched)
-{
-	void *buf = NULL;
-	struct ndis_80211_bssid_list_ex *bssid_list;
-	struct ndis_80211_bssid_ex *bssid;
-	int ret = -EINVAL, len, count, bssid_len, real_count, new_len;
-
-	netdev_dbg(usbdev->net, "%s()\n", __func__);
-
-	len = CONTROL_BUFFER_SIZE;
-resize_buf:
-	buf = kzalloc(len, GFP_KERNEL);
-	if (!buf) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	/* BSSID-list might have got bigger last time we checked, keep
-	 * resizing until it won't get any bigger.
-	 */
-	new_len = len;
-	ret = rndis_query_oid(usbdev, RNDIS_OID_802_11_BSSID_LIST,
-			      buf, &new_len);
-	if (ret != 0 || new_len < sizeof(struct ndis_80211_bssid_list_ex))
-		goto out;
-
-	if (new_len > len) {
-		len = new_len;
-		kfree(buf);
-		goto resize_buf;
-	}
-
-	len = new_len;
-
-	bssid_list = buf;
-	count = le32_to_cpu(bssid_list->num_items);
-	real_count = 0;
-	netdev_dbg(usbdev->net, "%s(): buflen: %d\n", __func__, len);
-
-	bssid_len = 0;
-	bssid = next_bssid_list_item((void *)bssid_list->bssid_data,
-				     &bssid_len, buf, len);
-
-	/* Device returns incorrect 'num_items'. Workaround by ignoring the
-	 * received 'num_items' and walking through full bssid buffer instead.
-	 */
-	while (check_bssid_list_item(bssid, bssid_len, buf, len)) {
-		if (rndis_bss_info_update(usbdev, bssid) && match_bssid &&
-		    matched) {
-			if (ether_addr_equal(bssid->mac, match_bssid))
-				*matched = true;
-		}
-
-		real_count++;
-		bssid = next_bssid_list_item(bssid, &bssid_len, buf, len);
-	}
-
-	netdev_dbg(usbdev->net, "%s(): num_items from device: %d, really found:"
-				" %d\n", __func__, count, real_count);
-
-out:
-	kfree(buf);
-	return ret;
-}
-
-static void rndis_get_scan_results(struct work_struct *work)
-{
-	struct rndis_wlan_private *priv =
-		container_of(work, struct rndis_wlan_private, scan_work.work);
-	struct usbnet *usbdev = priv->usbdev;
-	struct cfg80211_scan_info info = {};
-	int ret;
-
-	netdev_dbg(usbdev->net, "get_scan_results\n");
-
-	if (!priv->scan_request)
-		return;
-
-	ret = rndis_check_bssid_list(usbdev, NULL, NULL);
-
-	info.aborted = ret < 0;
-	cfg80211_scan_done(priv->scan_request, &info);
-
-	priv->scan_request = NULL;
-}
-
-static int rndis_connect(struct wiphy *wiphy, struct net_device *dev,
-					struct cfg80211_connect_params *sme)
-{
-	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
-	struct usbnet *usbdev = priv->usbdev;
-	struct ieee80211_channel *channel = sme->channel;
-	struct ndis_80211_ssid ssid;
-	int pairwise = RNDIS_WLAN_ALG_NONE;
-	int groupwise = RNDIS_WLAN_ALG_NONE;
-	int keymgmt = RNDIS_WLAN_KEY_MGMT_NONE;
-	int length, i, ret, chan = -1;
-
-	if (channel)
-		chan = ieee80211_frequency_to_channel(channel->center_freq);
-
-	groupwise = rndis_cipher_to_alg(sme->crypto.cipher_group);
-	for (i = 0; i < sme->crypto.n_ciphers_pairwise; i++)
-		pairwise |=
-			rndis_cipher_to_alg(sme->crypto.ciphers_pairwise[i]);
-
-	if (sme->crypto.n_ciphers_pairwise > 0 &&
-			pairwise == RNDIS_WLAN_ALG_NONE) {
-		netdev_err(usbdev->net, "Unsupported pairwise cipher\n");
-		return -ENOTSUPP;
-	}
-
-	for (i = 0; i < sme->crypto.n_akm_suites; i++)
-		keymgmt |=
-			rndis_akm_suite_to_key_mgmt(sme->crypto.akm_suites[i]);
-
-	if (sme->crypto.n_akm_suites > 0 &&
-			keymgmt == RNDIS_WLAN_KEY_MGMT_NONE) {
-		netdev_err(usbdev->net, "Invalid keymgmt\n");
-		return -ENOTSUPP;
-	}
-
-	netdev_dbg(usbdev->net, "cfg80211.connect('%.32s':[%pM]:%d:[%d,0x%x:0x%x]:[0x%x:0x%x]:0x%x)\n",
-		   sme->ssid, sme->bssid, chan,
-		   sme->privacy, sme->crypto.wpa_versions, sme->auth_type,
-		   groupwise, pairwise, keymgmt);
-
-	if (is_associated(usbdev))
-		disassociate(usbdev, false);
-
-	ret = set_infra_mode(usbdev, NDIS_80211_INFRA_INFRA);
-	if (ret < 0) {
-		netdev_dbg(usbdev->net, "connect: set_infra_mode failed, %d\n",
-			   ret);
-		goto err_turn_radio_on;
-	}
-
-	ret = set_auth_mode(usbdev, sme->crypto.wpa_versions, sme->auth_type,
-								keymgmt);
-	if (ret < 0) {
-		netdev_dbg(usbdev->net, "connect: set_auth_mode failed, %d\n",
-			   ret);
-		goto err_turn_radio_on;
-	}
-
-	set_priv_filter(usbdev);
-
-	ret = set_encr_mode(usbdev, pairwise, groupwise);
-	if (ret < 0) {
-		netdev_dbg(usbdev->net, "connect: set_encr_mode failed, %d\n",
-			   ret);
-		goto err_turn_radio_on;
-	}
-
-	if (channel) {
-		ret = set_channel(usbdev, chan);
-		if (ret < 0) {
-			netdev_dbg(usbdev->net, "connect: set_channel failed, %d\n",
-				   ret);
-			goto err_turn_radio_on;
-		}
-	}
-
-	if (sme->key && ((groupwise | pairwise) & RNDIS_WLAN_ALG_WEP)) {
-		priv->encr_tx_key_index = sme->key_idx;
-		ret = add_wep_key(usbdev, sme->key, sme->key_len, sme->key_idx);
-		if (ret < 0) {
-			netdev_dbg(usbdev->net, "connect: add_wep_key failed, %d (%d, %d)\n",
-				   ret, sme->key_len, sme->key_idx);
-			goto err_turn_radio_on;
-		}
-	}
-
-	if (sme->bssid && !is_zero_ether_addr(sme->bssid) &&
-				!is_broadcast_ether_addr(sme->bssid)) {
-		ret = set_bssid(usbdev, sme->bssid);
-		if (ret < 0) {
-			netdev_dbg(usbdev->net, "connect: set_bssid failed, %d\n",
-				   ret);
-			goto err_turn_radio_on;
-		}
-	} else
-		clear_bssid(usbdev);
-
-	length = sme->ssid_len;
-	if (length > NDIS_802_11_LENGTH_SSID)
-		length = NDIS_802_11_LENGTH_SSID;
-
-	memset(&ssid, 0, sizeof(ssid));
-	ssid.length = cpu_to_le32(length);
-	memcpy(ssid.essid, sme->ssid, length);
-
-	/* Pause and purge rx queue, so we don't pass packets before
-	 * 'media connect'-indication.
-	 */
-	usbnet_pause_rx(usbdev);
-	usbnet_purge_paused_rxq(usbdev);
-
-	ret = set_essid(usbdev, &ssid);
-	if (ret < 0)
-		netdev_dbg(usbdev->net, "connect: set_essid failed, %d\n", ret);
-	return ret;
-
-err_turn_radio_on:
-	disassociate(usbdev, true);
-
-	return ret;
-}
-
-static int rndis_disconnect(struct wiphy *wiphy, struct net_device *dev,
-								u16 reason_code)
-{
-	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
-	struct usbnet *usbdev = priv->usbdev;
-
-	netdev_dbg(usbdev->net, "cfg80211.disconnect(%d)\n", reason_code);
-
-	priv->connected = false;
-	eth_zero_addr(priv->bssid);
-
-	return deauthenticate(usbdev);
-}
-
-static int rndis_join_ibss(struct wiphy *wiphy, struct net_device *dev,
-					struct cfg80211_ibss_params *params)
-{
-	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
-	struct usbnet *usbdev = priv->usbdev;
-	struct ieee80211_channel *channel = params->chandef.chan;
-	struct ndis_80211_ssid ssid;
-	enum nl80211_auth_type auth_type;
-	int ret, alg, length, chan = -1;
-
-	if (channel)
-		chan = ieee80211_frequency_to_channel(channel->center_freq);
-
-	/* TODO: How to handle ad-hoc encryption?
-	 * connect() has *key, join_ibss() doesn't. RNDIS requires key to be
-	 * pre-shared for encryption (open/shared/wpa), is key set before
-	 * join_ibss? Which auth_type to use (not in params)? What about WPA?
-	 */
-	if (params->privacy) {
-		auth_type = NL80211_AUTHTYPE_SHARED_KEY;
-		alg = RNDIS_WLAN_ALG_WEP;
-	} else {
-		auth_type = NL80211_AUTHTYPE_OPEN_SYSTEM;
-		alg = RNDIS_WLAN_ALG_NONE;
-	}
-
-	netdev_dbg(usbdev->net, "cfg80211.join_ibss('%.32s':[%pM]:%d:%d)\n",
-		   params->ssid, params->bssid, chan, params->privacy);
-
-	if (is_associated(usbdev))
-		disassociate(usbdev, false);
-
-	ret = set_infra_mode(usbdev, NDIS_80211_INFRA_ADHOC);
-	if (ret < 0) {
-		netdev_dbg(usbdev->net, "join_ibss: set_infra_mode failed, %d\n",
-			   ret);
-		goto err_turn_radio_on;
-	}
-
-	ret = set_auth_mode(usbdev, 0, auth_type, RNDIS_WLAN_KEY_MGMT_NONE);
-	if (ret < 0) {
-		netdev_dbg(usbdev->net, "join_ibss: set_auth_mode failed, %d\n",
-			   ret);
-		goto err_turn_radio_on;
-	}
-
-	set_priv_filter(usbdev);
-
-	ret = set_encr_mode(usbdev, alg, RNDIS_WLAN_ALG_NONE);
-	if (ret < 0) {
-		netdev_dbg(usbdev->net, "join_ibss: set_encr_mode failed, %d\n",
-			   ret);
-		goto err_turn_radio_on;
-	}
-
-	if (channel) {
-		ret = set_channel(usbdev, chan);
-		if (ret < 0) {
-			netdev_dbg(usbdev->net, "join_ibss: set_channel failed, %d\n",
-				   ret);
-			goto err_turn_radio_on;
-		}
-	}
-
-	if (params->bssid && !is_zero_ether_addr(params->bssid) &&
-				!is_broadcast_ether_addr(params->bssid)) {
-		ret = set_bssid(usbdev, params->bssid);
-		if (ret < 0) {
-			netdev_dbg(usbdev->net, "join_ibss: set_bssid failed, %d\n",
-				   ret);
-			goto err_turn_radio_on;
-		}
-	} else
-		clear_bssid(usbdev);
-
-	length = params->ssid_len;
-	if (length > NDIS_802_11_LENGTH_SSID)
-		length = NDIS_802_11_LENGTH_SSID;
-
-	memset(&ssid, 0, sizeof(ssid));
-	ssid.length = cpu_to_le32(length);
-	memcpy(ssid.essid, params->ssid, length);
-
-	/* Don't need to pause rx queue for ad-hoc. */
-	usbnet_purge_paused_rxq(usbdev);
-	usbnet_resume_rx(usbdev);
-
-	ret = set_essid(usbdev, &ssid);
-	if (ret < 0)
-		netdev_dbg(usbdev->net, "join_ibss: set_essid failed, %d\n",
-			   ret);
-	return ret;
-
-err_turn_radio_on:
-	disassociate(usbdev, true);
-
-	return ret;
-}
-
-static int rndis_leave_ibss(struct wiphy *wiphy, struct net_device *dev)
-{
-	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
-	struct usbnet *usbdev = priv->usbdev;
-
-	netdev_dbg(usbdev->net, "cfg80211.leave_ibss()\n");
-
-	priv->connected = false;
-	eth_zero_addr(priv->bssid);
-
-	return deauthenticate(usbdev);
-}
-
-static int rndis_add_key(struct wiphy *wiphy, struct net_device *netdev,
-			 int link_id,  u8 key_index, bool pairwise,
-			 const u8 *mac_addr, struct key_params *params)
-{
-	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
-	struct usbnet *usbdev = priv->usbdev;
-	__le32 flags;
-
-	netdev_dbg(usbdev->net, "%s(%i, %pM, %08x)\n",
-		   __func__, key_index, mac_addr, params->cipher);
-
-	switch (params->cipher) {
-	case WLAN_CIPHER_SUITE_WEP40:
-	case WLAN_CIPHER_SUITE_WEP104:
-		return add_wep_key(usbdev, params->key, params->key_len,
-								key_index);
-	case WLAN_CIPHER_SUITE_TKIP:
-	case WLAN_CIPHER_SUITE_CCMP:
-		flags = 0;
-
-		if (params->seq && params->seq_len > 0)
-			flags |= NDIS_80211_ADDKEY_SET_INIT_RECV_SEQ;
-		if (mac_addr)
-			flags |= NDIS_80211_ADDKEY_PAIRWISE_KEY |
-					NDIS_80211_ADDKEY_TRANSMIT_KEY;
-
-		return add_wpa_key(usbdev, params->key, params->key_len,
-				key_index, mac_addr, params->seq,
-				params->seq_len, params->cipher, flags);
-	default:
-		netdev_dbg(usbdev->net, "%s(): unsupported cipher %08x\n",
-			   __func__, params->cipher);
-		return -ENOTSUPP;
-	}
-}
-
-static int rndis_del_key(struct wiphy *wiphy, struct net_device *netdev,
-			 int link_id, u8 key_index, bool pairwise,
-			 const u8 *mac_addr)
-{
-	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
-	struct usbnet *usbdev = priv->usbdev;
-
-	netdev_dbg(usbdev->net, "%s(%i, %pM)\n", __func__, key_index, mac_addr);
-
-	return remove_key(usbdev, key_index, mac_addr);
-}
-
-static int rndis_set_default_key(struct wiphy *wiphy, struct net_device *netdev,
-				 int link_id, u8 key_index, bool unicast,
-				 bool multicast)
-{
-	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
-	struct usbnet *usbdev = priv->usbdev;
-	struct rndis_wlan_encr_key key;
-
-	netdev_dbg(usbdev->net, "%s(%i)\n", __func__, key_index);
-
-	if (key_index >= RNDIS_WLAN_NUM_KEYS)
-		return -ENOENT;
-
-	priv->encr_tx_key_index = key_index;
-
-	if (is_wpa_key(priv, key_index))
-		return 0;
-
-	key = priv->encr_keys[key_index];
-
-	return add_wep_key(usbdev, key.material, key.len, key_index);
-}
-
-static void rndis_fill_station_info(struct usbnet *usbdev,
-						struct station_info *sinfo)
-{
-	__le32 linkspeed, rssi;
-	int ret, len;
-
-	memset(sinfo, 0, sizeof(*sinfo));
-
-	len = sizeof(linkspeed);
-	ret = rndis_query_oid(usbdev, RNDIS_OID_GEN_LINK_SPEED, &linkspeed, &len);
-	if (ret == 0) {
-		sinfo->txrate.legacy = le32_to_cpu(linkspeed) / 1000;
-		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
-	}
-
-	len = sizeof(rssi);
-	ret = rndis_query_oid(usbdev, RNDIS_OID_802_11_RSSI,
-			      &rssi, &len);
-	if (ret == 0) {
-		sinfo->signal = level_to_qual(le32_to_cpu(rssi));
-		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
-	}
-}
-
-static int rndis_get_station(struct wiphy *wiphy, struct net_device *dev,
-			     const u8 *mac, struct station_info *sinfo)
-{
-	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
-	struct usbnet *usbdev = priv->usbdev;
-
-	if (!ether_addr_equal(priv->bssid, mac))
-		return -ENOENT;
-
-	rndis_fill_station_info(usbdev, sinfo);
-
-	return 0;
-}
-
-static int rndis_dump_station(struct wiphy *wiphy, struct net_device *dev,
-			       int idx, u8 *mac, struct station_info *sinfo)
-{
-	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
-	struct usbnet *usbdev = priv->usbdev;
-
-	if (idx != 0)
-		return -ENOENT;
-
-	memcpy(mac, priv->bssid, ETH_ALEN);
-
-	rndis_fill_station_info(usbdev, sinfo);
-
-	return 0;
-}
-
-static int rndis_set_pmksa(struct wiphy *wiphy, struct net_device *netdev,
-				struct cfg80211_pmksa *pmksa)
-{
-	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
-	struct usbnet *usbdev = priv->usbdev;
-	struct ndis_80211_pmkid *pmkids;
-	u32 *tmp = (u32 *)pmksa->pmkid;
-
-	netdev_dbg(usbdev->net, "%s(%pM, %08X:%08X:%08X:%08X)\n", __func__,
-			pmksa->bssid,
-			cpu_to_be32(tmp[0]), cpu_to_be32(tmp[1]),
-			cpu_to_be32(tmp[2]), cpu_to_be32(tmp[3]));
-
-	pmkids = get_device_pmkids(usbdev);
-	if (IS_ERR(pmkids)) {
-		/* couldn't read PMKID cache from device */
-		return PTR_ERR(pmkids);
-	}
-
-	pmkids = update_pmkid(usbdev, pmkids, pmksa, wiphy->max_num_pmkids);
-	if (IS_ERR(pmkids)) {
-		/* not found, list full, etc */
-		return PTR_ERR(pmkids);
-	}
-
-	return set_device_pmkids(usbdev, pmkids);
-}
-
-static int rndis_del_pmksa(struct wiphy *wiphy, struct net_device *netdev,
-				struct cfg80211_pmksa *pmksa)
-{
-	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
-	struct usbnet *usbdev = priv->usbdev;
-	struct ndis_80211_pmkid *pmkids;
-	u32 *tmp = (u32 *)pmksa->pmkid;
-
-	netdev_dbg(usbdev->net, "%s(%pM, %08X:%08X:%08X:%08X)\n", __func__,
-			pmksa->bssid,
-			cpu_to_be32(tmp[0]), cpu_to_be32(tmp[1]),
-			cpu_to_be32(tmp[2]), cpu_to_be32(tmp[3]));
-
-	pmkids = get_device_pmkids(usbdev);
-	if (IS_ERR(pmkids)) {
-		/* Couldn't read PMKID cache from device */
-		return PTR_ERR(pmkids);
-	}
-
-	pmkids = remove_pmkid(usbdev, pmkids, pmksa, wiphy->max_num_pmkids);
-	if (IS_ERR(pmkids)) {
-		/* not found, etc */
-		return PTR_ERR(pmkids);
-	}
-
-	return set_device_pmkids(usbdev, pmkids);
-}
-
-static int rndis_flush_pmksa(struct wiphy *wiphy, struct net_device *netdev)
-{
-	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
-	struct usbnet *usbdev = priv->usbdev;
-	struct ndis_80211_pmkid pmkid;
-
-	netdev_dbg(usbdev->net, "%s()\n", __func__);
-
-	memset(&pmkid, 0, sizeof(pmkid));
-
-	pmkid.length = cpu_to_le32(sizeof(pmkid));
-	pmkid.bssid_info_count = cpu_to_le32(0);
-
-	return rndis_set_oid(usbdev, RNDIS_OID_802_11_PMKID,
-			     &pmkid, sizeof(pmkid));
-}
-
-static int rndis_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev,
-				bool enabled, int timeout)
-{
-	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
-	struct usbnet *usbdev = priv->usbdev;
-	int power_mode;
-	__le32 mode;
-	int ret;
-
-	if (priv->device_type != RNDIS_BCM4320B)
-		return -ENOTSUPP;
-
-	netdev_dbg(usbdev->net, "%s(): %s, %d\n", __func__,
-				enabled ? "enabled" : "disabled",
-				timeout);
-
-	if (enabled)
-		power_mode = NDIS_80211_POWER_MODE_FAST_PSP;
-	else
-		power_mode = NDIS_80211_POWER_MODE_CAM;
-
-	if (power_mode == priv->power_mode)
-		return 0;
-
-	priv->power_mode = power_mode;
-
-	mode = cpu_to_le32(power_mode);
-	ret = rndis_set_oid(usbdev, RNDIS_OID_802_11_POWER_MODE,
-			    &mode, sizeof(mode));
-
-	netdev_dbg(usbdev->net, "%s(): RNDIS_OID_802_11_POWER_MODE -> %d\n",
-				__func__, ret);
-
-	return ret;
-}
-
-static int rndis_set_cqm_rssi_config(struct wiphy *wiphy,
-					struct net_device *dev,
-					s32 rssi_thold, u32 rssi_hyst)
-{
-	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
-
-	priv->cqm_rssi_thold = rssi_thold;
-	priv->cqm_rssi_hyst = rssi_hyst;
-	priv->last_cqm_event_rssi = 0;
-
-	return 0;
-}
-
-static void rndis_wlan_craft_connected_bss(struct usbnet *usbdev, u8 *bssid,
-					   struct ndis_80211_assoc_info *info)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	struct ieee80211_channel *channel;
-	struct ndis_80211_ssid ssid;
-	struct cfg80211_bss *bss;
-	s32 signal;
-	u64 timestamp;
-	u16 capability;
-	u32 beacon_period = 0;
-	__le32 rssi;
-	u8 ie_buf[34];
-	int len, ret, ie_len;
-
-	/* Get signal quality, in case of error use rssi=0 and ignore error. */
-	len = sizeof(rssi);
-	rssi = 0;
-	ret = rndis_query_oid(usbdev, RNDIS_OID_802_11_RSSI,
-			      &rssi, &len);
-	signal = level_to_qual(le32_to_cpu(rssi));
-
-	netdev_dbg(usbdev->net, "%s(): RNDIS_OID_802_11_RSSI -> %d, "
-		   "rssi:%d, qual: %d\n", __func__, ret, le32_to_cpu(rssi),
-		   level_to_qual(le32_to_cpu(rssi)));
-
-	/* Get AP capabilities */
-	if (info) {
-		capability = le16_to_cpu(info->resp_ie.capa);
-	} else {
-		/* Set atleast ESS/IBSS capability */
-		capability = (priv->infra_mode == NDIS_80211_INFRA_INFRA) ?
-				WLAN_CAPABILITY_ESS : WLAN_CAPABILITY_IBSS;
-	}
-
-	/* Get channel and beacon interval */
-	channel = get_current_channel(usbdev, &beacon_period);
-	if (!channel) {
-		netdev_warn(usbdev->net, "%s(): could not get channel.\n",
-					__func__);
-		return;
-	}
-
-	/* Get SSID, in case of error, use zero length SSID and ignore error. */
-	len = sizeof(ssid);
-	memset(&ssid, 0, sizeof(ssid));
-	ret = rndis_query_oid(usbdev, RNDIS_OID_802_11_SSID,
-			      &ssid, &len);
-	netdev_dbg(usbdev->net, "%s(): RNDIS_OID_802_11_SSID -> %d, len: %d, ssid: "
-				"'%.32s'\n", __func__, ret,
-				le32_to_cpu(ssid.length), ssid.essid);
-
-	if (le32_to_cpu(ssid.length) > 32)
-		ssid.length = cpu_to_le32(32);
-
-	ie_buf[0] = WLAN_EID_SSID;
-	ie_buf[1] = le32_to_cpu(ssid.length);
-	memcpy(&ie_buf[2], ssid.essid, le32_to_cpu(ssid.length));
-
-	ie_len = le32_to_cpu(ssid.length) + 2;
-
-	/* no tsf */
-	timestamp = 0;
-
-	netdev_dbg(usbdev->net, "%s(): channel:%d(freq), bssid:[%pM], tsf:%d, "
-		"capa:%x, beacon int:%d, resp_ie(len:%d, essid:'%.32s'), "
-		"signal:%d\n", __func__, (channel ? channel->center_freq : -1),
-		bssid, (u32)timestamp, capability, beacon_period, ie_len,
-		ssid.essid, signal);
-
-	bss = cfg80211_inform_bss(priv->wdev.wiphy, channel,
-				  CFG80211_BSS_FTYPE_UNKNOWN, bssid,
-				  timestamp, capability, beacon_period,
-				  ie_buf, ie_len, signal, GFP_KERNEL);
-	cfg80211_put_bss(priv->wdev.wiphy, bss);
-}
-
-/*
- * workers, indication handlers, device poller
- */
-static void rndis_wlan_do_link_up_work(struct usbnet *usbdev)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	struct ndis_80211_assoc_info *info = NULL;
-	u8 bssid[ETH_ALEN];
-	unsigned int resp_ie_len, req_ie_len;
-	unsigned int offset;
-	u8 *req_ie, *resp_ie;
-	int ret;
-	bool roamed = false;
-	bool match_bss;
-
-	if (priv->infra_mode == NDIS_80211_INFRA_INFRA && priv->connected) {
-		/* received media connect indication while connected, either
-		 * device reassociated with same AP or roamed to new. */
-		roamed = true;
-	}
-
-	req_ie_len = 0;
-	resp_ie_len = 0;
-	req_ie = NULL;
-	resp_ie = NULL;
-
-	if (priv->infra_mode == NDIS_80211_INFRA_INFRA) {
-		info = kzalloc(CONTROL_BUFFER_SIZE, GFP_KERNEL);
-		if (!info) {
-			/* No memory? Try resume work later */
-			set_bit(WORK_LINK_UP, &priv->work_pending);
-			queue_work(priv->workqueue, &priv->work);
-			return;
-		}
-
-		/* Get association info IEs from device. */
-		ret = get_association_info(usbdev, info, CONTROL_BUFFER_SIZE);
-		if (!ret) {
-			req_ie_len = le32_to_cpu(info->req_ie_length);
-			if (req_ie_len > CONTROL_BUFFER_SIZE)
-				req_ie_len = CONTROL_BUFFER_SIZE;
-			if (req_ie_len != 0) {
-				offset = le32_to_cpu(info->offset_req_ies);
-
-				if (offset > CONTROL_BUFFER_SIZE)
-					offset = CONTROL_BUFFER_SIZE;
-
-				req_ie = (u8 *)info + offset;
-
-				if (offset + req_ie_len > CONTROL_BUFFER_SIZE)
-					req_ie_len =
-						CONTROL_BUFFER_SIZE - offset;
-			}
-
-			resp_ie_len = le32_to_cpu(info->resp_ie_length);
-			if (resp_ie_len > CONTROL_BUFFER_SIZE)
-				resp_ie_len = CONTROL_BUFFER_SIZE;
-			if (resp_ie_len != 0) {
-				offset = le32_to_cpu(info->offset_resp_ies);
-
-				if (offset > CONTROL_BUFFER_SIZE)
-					offset = CONTROL_BUFFER_SIZE;
-
-				resp_ie = (u8 *)info + offset;
-
-				if (offset + resp_ie_len > CONTROL_BUFFER_SIZE)
-					resp_ie_len =
-						CONTROL_BUFFER_SIZE - offset;
-			}
-		} else {
-			/* Since rndis_wlan_craft_connected_bss() might use info
-			 * later and expects info to contain valid data if
-			 * non-null, free info and set NULL here.
-			 */
-			kfree(info);
-			info = NULL;
-		}
-	} else if (WARN_ON(priv->infra_mode != NDIS_80211_INFRA_ADHOC))
-		return;
-
-	ret = get_bssid(usbdev, bssid);
-	if (ret < 0)
-		memset(bssid, 0, sizeof(bssid));
-
-	netdev_dbg(usbdev->net, "link up work: [%pM]%s\n",
-		   bssid, roamed ? " roamed" : "");
-
-	/* Internal bss list in device should contain at least the currently
-	 * connected bss and we can get it to cfg80211 with
-	 * rndis_check_bssid_list().
-	 *
-	 * NDIS spec says: "If the device is associated, but the associated
-	 *  BSSID is not in its BSSID scan list, then the driver must add an
-	 *  entry for the BSSID at the end of the data that it returns in
-	 *  response to query of RNDIS_OID_802_11_BSSID_LIST."
-	 *
-	 * NOTE: Seems to be true for BCM4320b variant, but not BCM4320a.
-	 */
-	match_bss = false;
-	rndis_check_bssid_list(usbdev, bssid, &match_bss);
-
-	if (!is_zero_ether_addr(bssid) && !match_bss) {
-		/* Couldn't get bss from device, we need to manually craft bss
-		 * for cfg80211.
-		 */
-		rndis_wlan_craft_connected_bss(usbdev, bssid, info);
-	}
-
-	if (priv->infra_mode == NDIS_80211_INFRA_INFRA) {
-		if (!roamed) {
-			cfg80211_connect_result(usbdev->net, bssid, req_ie,
-						req_ie_len, resp_ie,
-						resp_ie_len, 0, GFP_KERNEL);
-		} else {
-			struct cfg80211_roam_info roam_info = {
-				.links[0].channel =
-					get_current_channel(usbdev, NULL),
-				.links[0].bssid = bssid,
-				.req_ie = req_ie,
-				.req_ie_len = req_ie_len,
-				.resp_ie = resp_ie,
-				.resp_ie_len = resp_ie_len,
-			};
-
-			cfg80211_roamed(usbdev->net, &roam_info, GFP_KERNEL);
-		}
-	} else if (priv->infra_mode == NDIS_80211_INFRA_ADHOC)
-		cfg80211_ibss_joined(usbdev->net, bssid,
-				     get_current_channel(usbdev, NULL),
-				     GFP_KERNEL);
-
-	kfree(info);
-
-	priv->connected = true;
-	memcpy(priv->bssid, bssid, ETH_ALEN);
-
-	usbnet_resume_rx(usbdev);
-	netif_carrier_on(usbdev->net);
-}
-
-static void rndis_wlan_do_link_down_work(struct usbnet *usbdev)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-
-	if (priv->connected) {
-		priv->connected = false;
-		eth_zero_addr(priv->bssid);
-
-		deauthenticate(usbdev);
-
-		cfg80211_disconnected(usbdev->net, 0, NULL, 0, true, GFP_KERNEL);
-	}
-
-	netif_carrier_off(usbdev->net);
-}
-
-static void rndis_wlan_worker(struct work_struct *work)
-{
-	struct rndis_wlan_private *priv =
-		container_of(work, struct rndis_wlan_private, work);
-	struct usbnet *usbdev = priv->usbdev;
-
-	if (test_and_clear_bit(WORK_LINK_UP, &priv->work_pending))
-		rndis_wlan_do_link_up_work(usbdev);
-
-	if (test_and_clear_bit(WORK_LINK_DOWN, &priv->work_pending))
-		rndis_wlan_do_link_down_work(usbdev);
-
-	if (test_and_clear_bit(WORK_SET_MULTICAST_LIST, &priv->work_pending))
-		set_multicast_list(usbdev);
-}
-
-static void rndis_wlan_set_multicast_list(struct net_device *dev)
-{
-	struct usbnet *usbdev = netdev_priv(dev);
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-
-	if (test_bit(WORK_SET_MULTICAST_LIST, &priv->work_pending))
-		return;
-
-	set_bit(WORK_SET_MULTICAST_LIST, &priv->work_pending);
-	queue_work(priv->workqueue, &priv->work);
-}
-
-static void rndis_wlan_auth_indication(struct usbnet *usbdev,
-				struct ndis_80211_status_indication *indication,
-				int len)
-{
-	u8 *buf;
-	const char *type;
-	int flags, buflen, key_id;
-	bool pairwise_error, group_error;
-	struct ndis_80211_auth_request *auth_req;
-	enum nl80211_key_type key_type;
-
-	/* must have at least one array entry */
-	if (len < offsetof(struct ndis_80211_status_indication, u) +
-				sizeof(struct ndis_80211_auth_request)) {
-		netdev_info(usbdev->net, "authentication indication: too short message (%i)\n",
-			    len);
-		return;
-	}
-
-	buf = (void *)&indication->u.auth_request[0];
-	buflen = len - offsetof(struct ndis_80211_status_indication, u);
-
-	while (buflen >= sizeof(*auth_req)) {
-		auth_req = (void *)buf;
-		if (buflen < le32_to_cpu(auth_req->length))
-			return;
-		type = "unknown";
-		flags = le32_to_cpu(auth_req->flags);
-		pairwise_error = false;
-		group_error = false;
-
-		if (flags & 0x1)
-			type = "reauth request";
-		if (flags & 0x2)
-			type = "key update request";
-		if (flags & 0x6) {
-			pairwise_error = true;
-			type = "pairwise_error";
-		}
-		if (flags & 0xe) {
-			group_error = true;
-			type = "group_error";
-		}
-
-		netdev_info(usbdev->net, "authentication indication: %s (0x%08x)\n",
-			    type, le32_to_cpu(auth_req->flags));
-
-		if (pairwise_error) {
-			key_type = NL80211_KEYTYPE_PAIRWISE;
-			key_id = -1;
-
-			cfg80211_michael_mic_failure(usbdev->net,
-							auth_req->bssid,
-							key_type, key_id, NULL,
-							GFP_KERNEL);
-		}
-
-		if (group_error) {
-			key_type = NL80211_KEYTYPE_GROUP;
-			key_id = -1;
-
-			cfg80211_michael_mic_failure(usbdev->net,
-							auth_req->bssid,
-							key_type, key_id, NULL,
-							GFP_KERNEL);
-		}
-
-		buflen -= le32_to_cpu(auth_req->length);
-		buf += le32_to_cpu(auth_req->length);
-	}
-}
-
-static void rndis_wlan_pmkid_cand_list_indication(struct usbnet *usbdev,
-				struct ndis_80211_status_indication *indication,
-				int len)
-{
-	struct ndis_80211_pmkid_cand_list *cand_list;
-	int list_len, expected_len, i;
-
-	if (len < offsetof(struct ndis_80211_status_indication, u) +
-				sizeof(struct ndis_80211_pmkid_cand_list)) {
-		netdev_info(usbdev->net, "pmkid candidate list indication: too short message (%i)\n",
-			    len);
-		return;
-	}
-
-	list_len = le32_to_cpu(indication->u.cand_list.num_candidates) *
-			sizeof(struct ndis_80211_pmkid_candidate);
-	expected_len = sizeof(struct ndis_80211_pmkid_cand_list) + list_len +
-			offsetof(struct ndis_80211_status_indication, u);
-
-	if (len < expected_len) {
-		netdev_info(usbdev->net, "pmkid candidate list indication: list larger than buffer (%i < %i)\n",
-			    len, expected_len);
-		return;
-	}
-
-	cand_list = &indication->u.cand_list;
-
-	netdev_info(usbdev->net, "pmkid candidate list indication: version %i, candidates %i\n",
-		    le32_to_cpu(cand_list->version),
-		    le32_to_cpu(cand_list->num_candidates));
-
-	if (le32_to_cpu(cand_list->version) != 1)
-		return;
-
-	for (i = 0; i < le32_to_cpu(cand_list->num_candidates); i++) {
-		struct ndis_80211_pmkid_candidate *cand =
-						&cand_list->candidate_list[i];
-		bool preauth = !!(cand->flags & NDIS_80211_PMKID_CAND_PREAUTH);
-
-		netdev_dbg(usbdev->net, "cand[%i]: flags: 0x%08x, preauth: %d, bssid: %pM\n",
-			   i, le32_to_cpu(cand->flags), preauth, cand->bssid);
-
-		cfg80211_pmksa_candidate_notify(usbdev->net, i, cand->bssid,
-						preauth, GFP_ATOMIC);
-	}
-}
-
-static void rndis_wlan_media_specific_indication(struct usbnet *usbdev,
-			struct rndis_indicate *msg, int buflen)
-{
-	struct ndis_80211_status_indication *indication;
-	unsigned int len, offset;
-
-	offset = offsetof(struct rndis_indicate, status) +
-			le32_to_cpu(msg->offset);
-	len = le32_to_cpu(msg->length);
-
-	if (len < 8) {
-		netdev_info(usbdev->net, "media specific indication, ignore too short message (%i < 8)\n",
-			    len);
-		return;
-	}
-
-	if (len > buflen || offset > buflen || offset + len > buflen) {
-		netdev_info(usbdev->net, "media specific indication, too large to fit to buffer (%i > %i)\n",
-			    offset + len, buflen);
-		return;
-	}
-
-	indication = (void *)((u8 *)msg + offset);
-
-	switch (le32_to_cpu(indication->status_type)) {
-	case NDIS_80211_STATUSTYPE_RADIOSTATE:
-		netdev_info(usbdev->net, "radio state indication: %i\n",
-			    le32_to_cpu(indication->u.radio_status));
-		return;
-
-	case NDIS_80211_STATUSTYPE_MEDIASTREAMMODE:
-		netdev_info(usbdev->net, "media stream mode indication: %i\n",
-			    le32_to_cpu(indication->u.media_stream_mode));
-		return;
-
-	case NDIS_80211_STATUSTYPE_AUTHENTICATION:
-		rndis_wlan_auth_indication(usbdev, indication, len);
-		return;
-
-	case NDIS_80211_STATUSTYPE_PMKID_CANDIDATELIST:
-		rndis_wlan_pmkid_cand_list_indication(usbdev, indication, len);
-		return;
-
-	default:
-		netdev_info(usbdev->net, "media specific indication: unknown status type 0x%08x\n",
-			    le32_to_cpu(indication->status_type));
-	}
-}
-
-static void rndis_wlan_indication(struct usbnet *usbdev, void *ind, int buflen)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	struct rndis_indicate *msg = ind;
-
-	switch (le32_to_cpu(msg->status)) {
-	case RNDIS_STATUS_MEDIA_CONNECT:
-		if (priv->current_command_oid == RNDIS_OID_802_11_ADD_KEY) {
-			/* RNDIS_OID_802_11_ADD_KEY causes sometimes extra
-			 * "media connect" indications which confuses driver
-			 * and userspace to think that device is
-			 * roaming/reassociating when it isn't.
-			 */
-			netdev_dbg(usbdev->net, "ignored RNDIS_OID_802_11_ADD_KEY triggered 'media connect'\n");
-			return;
-		}
-
-		usbnet_pause_rx(usbdev);
-
-		netdev_info(usbdev->net, "media connect\n");
-
-		/* queue work to avoid recursive calls into rndis_command */
-		set_bit(WORK_LINK_UP, &priv->work_pending);
-		queue_work(priv->workqueue, &priv->work);
-		break;
-
-	case RNDIS_STATUS_MEDIA_DISCONNECT:
-		netdev_info(usbdev->net, "media disconnect\n");
-
-		/* queue work to avoid recursive calls into rndis_command */
-		set_bit(WORK_LINK_DOWN, &priv->work_pending);
-		queue_work(priv->workqueue, &priv->work);
-		break;
-
-	case RNDIS_STATUS_MEDIA_SPECIFIC_INDICATION:
-		rndis_wlan_media_specific_indication(usbdev, msg, buflen);
-		break;
-
-	default:
-		netdev_info(usbdev->net, "indication: 0x%08x\n",
-			    le32_to_cpu(msg->status));
-		break;
-	}
-}
-
-static int rndis_wlan_get_caps(struct usbnet *usbdev, struct wiphy *wiphy)
-{
-	struct {
-		__le32	num_items;
-		__le32	items[8];
-	} networks_supported;
-	struct ndis_80211_capability caps;
-	int len, retval, i, n;
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-
-	/* determine supported modes */
-	len = sizeof(networks_supported);
-	retval = rndis_query_oid(usbdev,
-				 RNDIS_OID_802_11_NETWORK_TYPES_SUPPORTED,
-				 &networks_supported, &len);
-	if (!retval) {
-		n = le32_to_cpu(networks_supported.num_items);
-		if (n > 8)
-			n = 8;
-		for (i = 0; i < n; i++) {
-			switch (le32_to_cpu(networks_supported.items[i])) {
-			case NDIS_80211_TYPE_FREQ_HOP:
-			case NDIS_80211_TYPE_DIRECT_SEQ:
-				priv->caps |= CAP_MODE_80211B;
-				break;
-			case NDIS_80211_TYPE_OFDM_A:
-				priv->caps |= CAP_MODE_80211A;
-				break;
-			case NDIS_80211_TYPE_OFDM_G:
-				priv->caps |= CAP_MODE_80211G;
-				break;
-			}
-		}
-	}
-
-	/* get device 802.11 capabilities, number of PMKIDs */
-	len = sizeof(caps);
-	retval = rndis_query_oid(usbdev,
-				 RNDIS_OID_802_11_CAPABILITY,
-				 &caps, &len);
-	if (!retval) {
-		netdev_dbg(usbdev->net, "RNDIS_OID_802_11_CAPABILITY -> len %d, "
-				"ver %d, pmkids %d, auth-encr-pairs %d\n",
-				le32_to_cpu(caps.length),
-				le32_to_cpu(caps.version),
-				le32_to_cpu(caps.num_pmkids),
-				le32_to_cpu(caps.num_auth_encr_pair));
-		wiphy->max_num_pmkids = le32_to_cpu(caps.num_pmkids);
-	} else
-		wiphy->max_num_pmkids = 0;
-
-	return retval;
-}
-
-static void rndis_do_cqm(struct usbnet *usbdev, s32 rssi)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	enum nl80211_cqm_rssi_threshold_event event;
-	int thold, hyst, last_event;
-
-	if (priv->cqm_rssi_thold >= 0 || rssi >= 0)
-		return;
-	if (priv->infra_mode != NDIS_80211_INFRA_INFRA)
-		return;
-
-	last_event = priv->last_cqm_event_rssi;
-	thold = priv->cqm_rssi_thold;
-	hyst = priv->cqm_rssi_hyst;
-
-	if (rssi < thold && (last_event == 0 || rssi < last_event - hyst))
-		event = NL80211_CQM_RSSI_THRESHOLD_EVENT_LOW;
-	else if (rssi > thold && (last_event == 0 || rssi > last_event + hyst))
-		event = NL80211_CQM_RSSI_THRESHOLD_EVENT_HIGH;
-	else
-		return;
-
-	priv->last_cqm_event_rssi = rssi;
-	cfg80211_cqm_rssi_notify(usbdev->net, event, rssi, GFP_KERNEL);
-}
-
-#define DEVICE_POLLER_JIFFIES (HZ)
-static void rndis_device_poller(struct work_struct *work)
-{
-	struct rndis_wlan_private *priv =
-		container_of(work, struct rndis_wlan_private,
-							dev_poller_work.work);
-	struct usbnet *usbdev = priv->usbdev;
-	__le32 rssi, tmp;
-	int len, ret, j;
-	int update_jiffies = DEVICE_POLLER_JIFFIES;
-	void *buf;
-
-	/* Only check/do workaround when connected. Calling is_associated()
-	 * also polls device with rndis_command() and catches for media link
-	 * indications.
-	 */
-	if (!is_associated(usbdev)) {
-		/* Workaround bad scanning in BCM4320a devices with active
-		 * background scanning when not associated.
-		 */
-		if (priv->device_type == RNDIS_BCM4320A && priv->radio_on &&
-		    !priv->scan_request) {
-			/* Get previous scan results */
-			rndis_check_bssid_list(usbdev, NULL, NULL);
-
-			/* Initiate new scan */
-			rndis_start_bssid_list_scan(usbdev);
-		}
-
-		goto end;
-	}
-
-	len = sizeof(rssi);
-	ret = rndis_query_oid(usbdev, RNDIS_OID_802_11_RSSI,
-			      &rssi, &len);
-	if (ret == 0) {
-		priv->last_qual = level_to_qual(le32_to_cpu(rssi));
-		rndis_do_cqm(usbdev, le32_to_cpu(rssi));
-	}
-
-	netdev_dbg(usbdev->net, "dev-poller: RNDIS_OID_802_11_RSSI -> %d, rssi:%d, qual: %d\n",
-		   ret, le32_to_cpu(rssi), level_to_qual(le32_to_cpu(rssi)));
-
-	/* Workaround transfer stalls on poor quality links.
-	 * TODO: find right way to fix these stalls (as stalls do not happen
-	 * with ndiswrapper/windows driver). */
-	if (priv->param_workaround_interval > 0 && priv->last_qual <= 25) {
-		/* Decrease stats worker interval to catch stalls.
-		 * faster. Faster than 400-500ms causes packet loss,
-		 * Slower doesn't catch stalls fast enough.
-		 */
-		j = msecs_to_jiffies(priv->param_workaround_interval);
-		if (j > DEVICE_POLLER_JIFFIES)
-			j = DEVICE_POLLER_JIFFIES;
-		else if (j <= 0)
-			j = 1;
-		update_jiffies = j;
-
-		/* Send scan OID. Use of both OIDs is required to get device
-		 * working.
-		 */
-		tmp = cpu_to_le32(1);
-		rndis_set_oid(usbdev,
-			      RNDIS_OID_802_11_BSSID_LIST_SCAN,
-			      &tmp, sizeof(tmp));
-
-		len = CONTROL_BUFFER_SIZE;
-		buf = kmalloc(len, GFP_KERNEL);
-		if (!buf)
-			goto end;
-
-		rndis_query_oid(usbdev,
-				RNDIS_OID_802_11_BSSID_LIST,
-				buf, &len);
-		kfree(buf);
-	}
-
-end:
-	if (update_jiffies >= HZ)
-		update_jiffies = round_jiffies_relative(update_jiffies);
-	else {
-		j = round_jiffies_relative(update_jiffies);
-		if (abs(j - update_jiffies) <= 10)
-			update_jiffies = j;
-	}
-
-	queue_delayed_work(priv->workqueue, &priv->dev_poller_work,
-								update_jiffies);
-}
-
-/*
- * driver/device initialization
- */
-static void rndis_copy_module_params(struct usbnet *usbdev, int device_type)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-
-	priv->device_type = device_type;
-
-	priv->param_country[0] = modparam_country[0];
-	priv->param_country[1] = modparam_country[1];
-	priv->param_country[2] = 0;
-	priv->param_frameburst   = modparam_frameburst;
-	priv->param_afterburner  = modparam_afterburner;
-	priv->param_power_save   = modparam_power_save;
-	priv->param_power_output = modparam_power_output;
-	priv->param_roamtrigger  = modparam_roamtrigger;
-	priv->param_roamdelta    = modparam_roamdelta;
-
-	priv->param_country[0] = toupper(priv->param_country[0]);
-	priv->param_country[1] = toupper(priv->param_country[1]);
-	/* doesn't support EU as country code, use FI instead */
-	if (!strcmp(priv->param_country, "EU"))
-		strcpy(priv->param_country, "FI");
-
-	if (priv->param_power_save < 0)
-		priv->param_power_save = 0;
-	else if (priv->param_power_save > 2)
-		priv->param_power_save = 2;
-
-	if (priv->param_power_output < 0)
-		priv->param_power_output = 0;
-	else if (priv->param_power_output > 3)
-		priv->param_power_output = 3;
-
-	if (priv->param_roamtrigger < -80)
-		priv->param_roamtrigger = -80;
-	else if (priv->param_roamtrigger > -60)
-		priv->param_roamtrigger = -60;
-
-	if (priv->param_roamdelta < 0)
-		priv->param_roamdelta = 0;
-	else if (priv->param_roamdelta > 2)
-		priv->param_roamdelta = 2;
-
-	if (modparam_workaround_interval < 0)
-		priv->param_workaround_interval = 500;
-	else
-		priv->param_workaround_interval = modparam_workaround_interval;
-}
-
-static int unknown_early_init(struct usbnet *usbdev)
-{
-	/* copy module parameters for unknown so that iwconfig reports txpower
-	 * and workaround parameter is copied to private structure correctly.
-	 */
-	rndis_copy_module_params(usbdev, RNDIS_UNKNOWN);
-
-	/* This is unknown device, so do not try set configuration parameters.
-	 */
-
-	return 0;
-}
-
-static int bcm4320a_early_init(struct usbnet *usbdev)
-{
-	/* copy module parameters for bcm4320a so that iwconfig reports txpower
-	 * and workaround parameter is copied to private structure correctly.
-	 */
-	rndis_copy_module_params(usbdev, RNDIS_BCM4320A);
-
-	/* bcm4320a doesn't handle configuration parameters well. Try
-	 * set any and you get partially zeroed mac and broken device.
-	 */
-
-	return 0;
-}
-
-static int bcm4320b_early_init(struct usbnet *usbdev)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	char buf[8];
-
-	rndis_copy_module_params(usbdev, RNDIS_BCM4320B);
-
-	/* Early initialization settings, setting these won't have effect
-	 * if called after generic_rndis_bind().
-	 */
-
-	rndis_set_config_parameter_str(usbdev, "Country", priv->param_country);
-	rndis_set_config_parameter_str(usbdev, "FrameBursting",
-					priv->param_frameburst ? "1" : "0");
-	rndis_set_config_parameter_str(usbdev, "Afterburner",
-					priv->param_afterburner ? "1" : "0");
-	sprintf(buf, "%d", priv->param_power_save);
-	rndis_set_config_parameter_str(usbdev, "PowerSaveMode", buf);
-	sprintf(buf, "%d", priv->param_power_output);
-	rndis_set_config_parameter_str(usbdev, "PwrOut", buf);
-	sprintf(buf, "%d", priv->param_roamtrigger);
-	rndis_set_config_parameter_str(usbdev, "RoamTrigger", buf);
-	sprintf(buf, "%d", priv->param_roamdelta);
-	rndis_set_config_parameter_str(usbdev, "RoamDelta", buf);
-
-	return 0;
-}
-
-/* same as rndis_netdev_ops but with local multicast handler */
-static const struct net_device_ops rndis_wlan_netdev_ops = {
-	.ndo_open		= usbnet_open,
-	.ndo_stop		= usbnet_stop,
-	.ndo_start_xmit		= usbnet_start_xmit,
-	.ndo_tx_timeout		= usbnet_tx_timeout,
-	.ndo_get_stats64	= dev_get_tstats64,
-	.ndo_set_mac_address 	= eth_mac_addr,
-	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_set_rx_mode	= rndis_wlan_set_multicast_list,
-};
-
-static int rndis_wlan_bind(struct usbnet *usbdev, struct usb_interface *intf)
-{
-	struct wiphy *wiphy;
-	struct rndis_wlan_private *priv;
-	int retval, len;
-	__le32 tmp;
-
-	/* allocate wiphy and rndis private data
-	 * NOTE: We only support a single virtual interface, so wiphy
-	 * and wireless_dev are somewhat synonymous for this device.
-	 */
-	wiphy = wiphy_new(&rndis_config_ops, sizeof(struct rndis_wlan_private));
-	if (!wiphy)
-		return -ENOMEM;
-
-	priv = wiphy_priv(wiphy);
-	usbdev->net->ieee80211_ptr = &priv->wdev;
-	priv->wdev.wiphy = wiphy;
-	priv->wdev.iftype = NL80211_IFTYPE_STATION;
-
-	/* These have to be initialized before calling generic_rndis_bind().
-	 * Otherwise we'll be in big trouble in rndis_wlan_early_init().
-	 */
-	usbdev->driver_priv = priv;
-	priv->usbdev = usbdev;
-
-	mutex_init(&priv->command_lock);
-
-	/* because rndis_command() sleeps we need to use workqueue */
-	priv->workqueue = create_singlethread_workqueue("rndis_wlan");
-	if (!priv->workqueue) {
-		wiphy_free(wiphy);
-		return -ENOMEM;
-	}
-	INIT_WORK(&priv->work, rndis_wlan_worker);
-	INIT_DELAYED_WORK(&priv->dev_poller_work, rndis_device_poller);
-	INIT_DELAYED_WORK(&priv->scan_work, rndis_get_scan_results);
-
-	/* try bind rndis_host */
-	retval = generic_rndis_bind(usbdev, intf, FLAG_RNDIS_PHYM_WIRELESS);
-	if (retval < 0)
-		goto fail;
-
-	/* generic_rndis_bind set packet filter to multicast_all+
-	 * promisc mode which doesn't work well for our devices (device
-	 * picks up rssi to closest station instead of to access point).
-	 *
-	 * rndis_host wants to avoid all OID as much as possible
-	 * so do promisc/multicast handling in rndis_wlan.
-	 */
-	usbdev->net->netdev_ops = &rndis_wlan_netdev_ops;
-
-	tmp = cpu_to_le32(RNDIS_PACKET_TYPE_DIRECTED | RNDIS_PACKET_TYPE_BROADCAST);
-	retval = rndis_set_oid(usbdev,
-			       RNDIS_OID_GEN_CURRENT_PACKET_FILTER,
-			       &tmp, sizeof(tmp));
-
-	len = sizeof(tmp);
-	retval = rndis_query_oid(usbdev,
-				 RNDIS_OID_802_3_MAXIMUM_LIST_SIZE,
-				 &tmp, &len);
-	priv->multicast_size = le32_to_cpu(tmp);
-	if (retval < 0 || priv->multicast_size < 0)
-		priv->multicast_size = 0;
-	if (priv->multicast_size > 0)
-		usbdev->net->flags |= IFF_MULTICAST;
-	else
-		usbdev->net->flags &= ~IFF_MULTICAST;
-
-	/* fill-out wiphy structure and register w/ cfg80211 */
-	memcpy(wiphy->perm_addr, usbdev->net->dev_addr, ETH_ALEN);
-	wiphy->privid = rndis_wiphy_privid;
-	wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION)
-					| BIT(NL80211_IFTYPE_ADHOC);
-	wiphy->max_scan_ssids = 1;
-
-	/* TODO: fill-out band/encr information based on priv->caps */
-	rndis_wlan_get_caps(usbdev, wiphy);
-
-	memcpy(priv->channels, rndis_channels, sizeof(rndis_channels));
-	memcpy(priv->rates, rndis_rates, sizeof(rndis_rates));
-	priv->band.channels = priv->channels;
-	priv->band.n_channels = ARRAY_SIZE(rndis_channels);
-	priv->band.bitrates = priv->rates;
-	priv->band.n_bitrates = ARRAY_SIZE(rndis_rates);
-	wiphy->bands[NL80211_BAND_2GHZ] = &priv->band;
-	wiphy->signal_type = CFG80211_SIGNAL_TYPE_UNSPEC;
-
-	memcpy(priv->cipher_suites, rndis_cipher_suites,
-						sizeof(rndis_cipher_suites));
-	wiphy->cipher_suites = priv->cipher_suites;
-	wiphy->n_cipher_suites = ARRAY_SIZE(rndis_cipher_suites);
-
-	set_wiphy_dev(wiphy, &usbdev->udev->dev);
-
-	if (wiphy_register(wiphy)) {
-		retval = -ENODEV;
-		goto fail;
-	}
-
-	set_default_iw_params(usbdev);
-
-	priv->power_mode = -1;
-
-	/* set default rts/frag */
-	rndis_set_wiphy_params(wiphy,
-			WIPHY_PARAM_FRAG_THRESHOLD | WIPHY_PARAM_RTS_THRESHOLD);
-
-	/* turn radio off on init */
-	priv->radio_on = false;
-	disassociate(usbdev, false);
-	netif_carrier_off(usbdev->net);
-
-	return 0;
-
-fail:
-	cancel_delayed_work_sync(&priv->dev_poller_work);
-	cancel_delayed_work_sync(&priv->scan_work);
-	cancel_work_sync(&priv->work);
-	destroy_workqueue(priv->workqueue);
-
-	wiphy_free(wiphy);
-	return retval;
-}
-
-static void rndis_wlan_unbind(struct usbnet *usbdev, struct usb_interface *intf)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-
-	/* turn radio off */
-	disassociate(usbdev, false);
-
-	cancel_delayed_work_sync(&priv->dev_poller_work);
-	cancel_delayed_work_sync(&priv->scan_work);
-	cancel_work_sync(&priv->work);
-	destroy_workqueue(priv->workqueue);
-
-	rndis_unbind(usbdev, intf);
-
-	wiphy_unregister(priv->wdev.wiphy);
-	wiphy_free(priv->wdev.wiphy);
-}
-
-static int rndis_wlan_reset(struct usbnet *usbdev)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	int retval;
-
-	netdev_dbg(usbdev->net, "%s()\n", __func__);
-
-	retval = rndis_reset(usbdev);
-	if (retval)
-		netdev_warn(usbdev->net, "rndis_reset failed: %d\n", retval);
-
-	/* rndis_reset cleared multicast list, so restore here.
-	   (set_multicast_list() also turns on current packet filter) */
-	set_multicast_list(usbdev);
-
-	queue_delayed_work(priv->workqueue, &priv->dev_poller_work,
-		round_jiffies_relative(DEVICE_POLLER_JIFFIES));
-
-	return deauthenticate(usbdev);
-}
-
-static int rndis_wlan_stop(struct usbnet *usbdev)
-{
-	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
-	int retval;
-	__le32 filter;
-
-	netdev_dbg(usbdev->net, "%s()\n", __func__);
-
-	retval = disassociate(usbdev, false);
-
-	priv->work_pending = 0;
-	cancel_delayed_work_sync(&priv->dev_poller_work);
-	cancel_delayed_work_sync(&priv->scan_work);
-	cancel_work_sync(&priv->work);
-	flush_workqueue(priv->workqueue);
-
-	if (priv->scan_request) {
-		struct cfg80211_scan_info info = {
-			.aborted = true,
-		};
-
-		cfg80211_scan_done(priv->scan_request, &info);
-		priv->scan_request = NULL;
-	}
-
-	/* Set current packet filter zero to block receiving data packets from
-	   device. */
-	filter = 0;
-	rndis_set_oid(usbdev, RNDIS_OID_GEN_CURRENT_PACKET_FILTER, &filter,
-								sizeof(filter));
-
-	return retval;
-}
-
-static const struct driver_info	bcm4320b_info = {
-	.description =	"Wireless RNDIS device, BCM4320b based",
-	.flags =	FLAG_WLAN | FLAG_FRAMING_RN | FLAG_NO_SETINT |
-				FLAG_AVOID_UNLINK_URBS,
-	.bind =		rndis_wlan_bind,
-	.unbind =	rndis_wlan_unbind,
-	.status =	rndis_status,
-	.rx_fixup =	rndis_rx_fixup,
-	.tx_fixup =	rndis_tx_fixup,
-	.reset =	rndis_wlan_reset,
-	.stop =		rndis_wlan_stop,
-	.early_init =	bcm4320b_early_init,
-	.indication =	rndis_wlan_indication,
-};
-
-static const struct driver_info	bcm4320a_info = {
-	.description =	"Wireless RNDIS device, BCM4320a based",
-	.flags =	FLAG_WLAN | FLAG_FRAMING_RN | FLAG_NO_SETINT |
-				FLAG_AVOID_UNLINK_URBS,
-	.bind =		rndis_wlan_bind,
-	.unbind =	rndis_wlan_unbind,
-	.status =	rndis_status,
-	.rx_fixup =	rndis_rx_fixup,
-	.tx_fixup =	rndis_tx_fixup,
-	.reset =	rndis_wlan_reset,
-	.stop =		rndis_wlan_stop,
-	.early_init =	bcm4320a_early_init,
-	.indication =	rndis_wlan_indication,
-};
-
-static const struct driver_info rndis_wlan_info = {
-	.description =	"Wireless RNDIS device",
-	.flags =	FLAG_WLAN | FLAG_FRAMING_RN | FLAG_NO_SETINT |
-				FLAG_AVOID_UNLINK_URBS,
-	.bind =		rndis_wlan_bind,
-	.unbind =	rndis_wlan_unbind,
-	.status =	rndis_status,
-	.rx_fixup =	rndis_rx_fixup,
-	.tx_fixup =	rndis_tx_fixup,
-	.reset =	rndis_wlan_reset,
-	.stop =		rndis_wlan_stop,
-	.early_init =	unknown_early_init,
-	.indication =	rndis_wlan_indication,
-};
-
-/*-------------------------------------------------------------------------*/
-
-static const struct usb_device_id products [] = {
-#define	RNDIS_MASTER_INTERFACE \
-	.bInterfaceClass	= USB_CLASS_COMM, \
-	.bInterfaceSubClass	= 2 /* ACM */, \
-	.bInterfaceProtocol	= 0x0ff
-
-/* INF driver for these devices have DriverVer >= 4.xx.xx.xx and many custom
- * parameters available. Chipset marked as 'BCM4320SKFBG' in NDISwrapper-wiki.
- */
-{
-	.match_flags	=   USB_DEVICE_ID_MATCH_INT_INFO
-			  | USB_DEVICE_ID_MATCH_DEVICE,
-	.idVendor		= 0x0411,
-	.idProduct		= 0x00bc,	/* Buffalo WLI-U2-KG125S */
-	RNDIS_MASTER_INTERFACE,
-	.driver_info		= (unsigned long) &bcm4320b_info,
-}, {
-	.match_flags	=   USB_DEVICE_ID_MATCH_INT_INFO
-			  | USB_DEVICE_ID_MATCH_DEVICE,
-	.idVendor		= 0x0baf,
-	.idProduct		= 0x011b,	/* U.S. Robotics USR5421 */
-	RNDIS_MASTER_INTERFACE,
-	.driver_info		= (unsigned long) &bcm4320b_info,
-}, {
-	.match_flags	=   USB_DEVICE_ID_MATCH_INT_INFO
-			  | USB_DEVICE_ID_MATCH_DEVICE,
-	.idVendor		= 0x050d,
-	.idProduct		= 0x011b,	/* Belkin F5D7051 */
-	RNDIS_MASTER_INTERFACE,
-	.driver_info		= (unsigned long) &bcm4320b_info,
-}, {
-	.match_flags	=   USB_DEVICE_ID_MATCH_INT_INFO
-			  | USB_DEVICE_ID_MATCH_DEVICE,
-	.idVendor		= 0x1799,	/* Belkin has two vendor ids */
-	.idProduct		= 0x011b,	/* Belkin F5D7051 */
-	RNDIS_MASTER_INTERFACE,
-	.driver_info		= (unsigned long) &bcm4320b_info,
-}, {
-	.match_flags	=   USB_DEVICE_ID_MATCH_INT_INFO
-			  | USB_DEVICE_ID_MATCH_DEVICE,
-	.idVendor		= 0x13b1,
-	.idProduct		= 0x0014,	/* Linksys WUSB54GSv2 */
-	RNDIS_MASTER_INTERFACE,
-	.driver_info		= (unsigned long) &bcm4320b_info,
-}, {
-	.match_flags	=   USB_DEVICE_ID_MATCH_INT_INFO
-			  | USB_DEVICE_ID_MATCH_DEVICE,
-	.idVendor		= 0x13b1,
-	.idProduct		= 0x0026,	/* Linksys WUSB54GSC */
-	RNDIS_MASTER_INTERFACE,
-	.driver_info		= (unsigned long) &bcm4320b_info,
-}, {
-	.match_flags	=   USB_DEVICE_ID_MATCH_INT_INFO
-			  | USB_DEVICE_ID_MATCH_DEVICE,
-	.idVendor		= 0x0b05,
-	.idProduct		= 0x1717,	/* Asus WL169gE */
-	RNDIS_MASTER_INTERFACE,
-	.driver_info		= (unsigned long) &bcm4320b_info,
-}, {
-	.match_flags	=   USB_DEVICE_ID_MATCH_INT_INFO
-			  | USB_DEVICE_ID_MATCH_DEVICE,
-	.idVendor		= 0x0a5c,
-	.idProduct		= 0xd11b,	/* Eminent EM4045 */
-	RNDIS_MASTER_INTERFACE,
-	.driver_info		= (unsigned long) &bcm4320b_info,
-}, {
-	.match_flags	=   USB_DEVICE_ID_MATCH_INT_INFO
-			  | USB_DEVICE_ID_MATCH_DEVICE,
-	.idVendor		= 0x1690,
-	.idProduct		= 0x0715,	/* BT Voyager 1055 */
-	RNDIS_MASTER_INTERFACE,
-	.driver_info		= (unsigned long) &bcm4320b_info,
-},
-/* These devices have DriverVer < 4.xx.xx.xx and do not have any custom
- * parameters available, hardware probably contain older firmware version with
- * no way of updating. Chipset marked as 'BCM4320????' in NDISwrapper-wiki.
- */
-{
-	.match_flags	=   USB_DEVICE_ID_MATCH_INT_INFO
-			  | USB_DEVICE_ID_MATCH_DEVICE,
-	.idVendor		= 0x13b1,
-	.idProduct		= 0x000e,	/* Linksys WUSB54GSv1 */
-	RNDIS_MASTER_INTERFACE,
-	.driver_info		= (unsigned long) &bcm4320a_info,
-}, {
-	.match_flags	=   USB_DEVICE_ID_MATCH_INT_INFO
-			  | USB_DEVICE_ID_MATCH_DEVICE,
-	.idVendor		= 0x0baf,
-	.idProduct		= 0x0111,	/* U.S. Robotics USR5420 */
-	RNDIS_MASTER_INTERFACE,
-	.driver_info		= (unsigned long) &bcm4320a_info,
-}, {
-	.match_flags	=   USB_DEVICE_ID_MATCH_INT_INFO
-			  | USB_DEVICE_ID_MATCH_DEVICE,
-	.idVendor		= 0x0411,
-	.idProduct		= 0x004b,	/* BUFFALO WLI-USB-G54 */
-	RNDIS_MASTER_INTERFACE,
-	.driver_info		= (unsigned long) &bcm4320a_info,
-},
-/* Generic Wireless RNDIS devices that we don't have exact
- * idVendor/idProduct/chip yet.
- */
-{
-	/* RNDIS is MSFT's un-official variant of CDC ACM */
-	USB_INTERFACE_INFO(USB_CLASS_COMM, 2 /* ACM */, 0x0ff),
-	.driver_info = (unsigned long) &rndis_wlan_info,
-}, {
-	/* "ActiveSync" is an undocumented variant of RNDIS, used in WM5 */
-	USB_INTERFACE_INFO(USB_CLASS_MISC, 1, 1),
-	.driver_info = (unsigned long) &rndis_wlan_info,
-},
-	{ },		// END
-};
-MODULE_DEVICE_TABLE(usb, products);
-
-static struct usb_driver rndis_wlan_driver = {
-	.name =		"rndis_wlan",
-	.id_table =	products,
-	.probe =	usbnet_probe,
-	.disconnect =	usbnet_disconnect,
-	.suspend =	usbnet_suspend,
-	.resume =	usbnet_resume,
-	.disable_hub_initiated_lpm = 1,
-};
-
-module_usb_driver(rndis_wlan_driver);
-
-MODULE_AUTHOR("Bjorge Dijkstra");
-MODULE_AUTHOR("Jussi Kivilinna");
-MODULE_DESCRIPTION("Driver for RNDIS based USB Wireless adapters");
-MODULE_LICENSE("GPL");
-
diff --git a/drivers/net/wireless/legacy/wl3501.h b/drivers/net/wireless/legacy/wl3501.h
deleted file mode 100644
index 91f276dd22a1..000000000000
--- a/drivers/net/wireless/legacy/wl3501.h
+++ /dev/null
@@ -1,615 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __WL3501_H__
-#define __WL3501_H__
-
-#include <linux/spinlock.h>
-#include <linux/ieee80211.h>
-
-/* define for WLA 2.0 */
-#define WL3501_BLKSZ 256
-/*
- * ID for input Signals of DRIVER block
- * bit[7-5] is block ID: 000
- * bit[4-0] is signal ID
-*/
-enum wl3501_signals {
-	WL3501_SIG_ALARM,
-	WL3501_SIG_MD_CONFIRM,
-	WL3501_SIG_MD_IND,
-	WL3501_SIG_ASSOC_CONFIRM,
-	WL3501_SIG_ASSOC_IND,
-	WL3501_SIG_AUTH_CONFIRM,
-	WL3501_SIG_AUTH_IND,
-	WL3501_SIG_DEAUTH_CONFIRM,
-	WL3501_SIG_DEAUTH_IND,
-	WL3501_SIG_DISASSOC_CONFIRM,
-	WL3501_SIG_DISASSOC_IND,
-	WL3501_SIG_GET_CONFIRM,
-	WL3501_SIG_JOIN_CONFIRM,
-	WL3501_SIG_PWR_MGMT_CONFIRM,
-	WL3501_SIG_REASSOC_CONFIRM,
-	WL3501_SIG_REASSOC_IND,
-	WL3501_SIG_SCAN_CONFIRM,
-	WL3501_SIG_SET_CONFIRM,
-	WL3501_SIG_START_CONFIRM,
-	WL3501_SIG_RESYNC_CONFIRM,
-	WL3501_SIG_SITE_CONFIRM,
-	WL3501_SIG_SAVE_CONFIRM,
-	WL3501_SIG_RFTEST_CONFIRM,
-/*
- * ID for input Signals of MLME block
- * bit[7-5] is block ID: 010
- * bit[4-0] is signal ID
- */
-	WL3501_SIG_ASSOC_REQ = 0x20,
-	WL3501_SIG_AUTH_REQ,
-	WL3501_SIG_DEAUTH_REQ,
-	WL3501_SIG_DISASSOC_REQ,
-	WL3501_SIG_GET_REQ,
-	WL3501_SIG_JOIN_REQ,
-	WL3501_SIG_PWR_MGMT_REQ,
-	WL3501_SIG_REASSOC_REQ,
-	WL3501_SIG_SCAN_REQ,
-	WL3501_SIG_SET_REQ,
-	WL3501_SIG_START_REQ,
-	WL3501_SIG_MD_REQ,
-	WL3501_SIG_RESYNC_REQ,
-	WL3501_SIG_SITE_REQ,
-	WL3501_SIG_SAVE_REQ,
-	WL3501_SIG_RF_TEST_REQ,
-	WL3501_SIG_MM_CONFIRM = 0x60,
-	WL3501_SIG_MM_IND,
-};
-
-enum wl3501_mib_attribs {
-	WL3501_MIB_ATTR_STATION_ID,
-	WL3501_MIB_ATTR_AUTH_ALGORITHMS,
-	WL3501_MIB_ATTR_AUTH_TYPE,
-	WL3501_MIB_ATTR_MEDIUM_OCCUPANCY_LIMIT,
-	WL3501_MIB_ATTR_CF_POLLABLE,
-	WL3501_MIB_ATTR_CFP_PERIOD,
-	WL3501_MIB_ATTR_CFPMAX_DURATION,
-	WL3501_MIB_ATTR_AUTH_RESP_TMOUT,
-	WL3501_MIB_ATTR_RX_DTIMS,
-	WL3501_MIB_ATTR_PRIV_OPT_IMPLEMENTED,
-	WL3501_MIB_ATTR_PRIV_INVOKED,
-	WL3501_MIB_ATTR_WEP_DEFAULT_KEYS,
-	WL3501_MIB_ATTR_WEP_DEFAULT_KEY_ID,
-	WL3501_MIB_ATTR_WEP_KEY_MAPPINGS,
-	WL3501_MIB_ATTR_WEP_KEY_MAPPINGS_LEN,
-	WL3501_MIB_ATTR_EXCLUDE_UNENCRYPTED,
-	WL3501_MIB_ATTR_WEP_ICV_ERROR_COUNT,
-	WL3501_MIB_ATTR_WEP_UNDECRYPTABLE_COUNT,
-	WL3501_MIB_ATTR_WEP_EXCLUDED_COUNT,
-	WL3501_MIB_ATTR_MAC_ADDR,
-	WL3501_MIB_ATTR_GROUP_ADDRS,
-	WL3501_MIB_ATTR_RTS_THRESHOLD,
-	WL3501_MIB_ATTR_SHORT_RETRY_LIMIT,
-	WL3501_MIB_ATTR_LONG_RETRY_LIMIT,
-	WL3501_MIB_ATTR_FRAG_THRESHOLD,
-	WL3501_MIB_ATTR_MAX_TX_MSDU_LIFETIME,
-	WL3501_MIB_ATTR_MAX_RX_LIFETIME,
-	WL3501_MIB_ATTR_MANUFACTURER_ID,
-	WL3501_MIB_ATTR_PRODUCT_ID,
-	WL3501_MIB_ATTR_TX_FRAG_COUNT,
-	WL3501_MIB_ATTR_MULTICAST_TX_FRAME_COUNT,
-	WL3501_MIB_ATTR_FAILED_COUNT,
-	WL3501_MIB_ATTR_RX_FRAG_COUNT,
-	WL3501_MIB_ATTR_MULTICAST_RX_COUNT,
-	WL3501_MIB_ATTR_FCS_ERROR_COUNT,
-	WL3501_MIB_ATTR_RETRY_COUNT,
-	WL3501_MIB_ATTR_MULTIPLE_RETRY_COUNT,
-	WL3501_MIB_ATTR_RTS_SUCCESS_COUNT,
-	WL3501_MIB_ATTR_RTS_FAILURE_COUNT,
-	WL3501_MIB_ATTR_ACK_FAILURE_COUNT,
-	WL3501_MIB_ATTR_FRAME_DUPLICATE_COUNT,
-	WL3501_MIB_ATTR_PHY_TYPE,
-	WL3501_MIB_ATTR_REG_DOMAINS_SUPPORT,
-	WL3501_MIB_ATTR_CURRENT_REG_DOMAIN,
-	WL3501_MIB_ATTR_SLOT_TIME,
-	WL3501_MIB_ATTR_CCA_TIME,
-	WL3501_MIB_ATTR_RX_TX_TURNAROUND_TIME,
-	WL3501_MIB_ATTR_TX_PLCP_DELAY,
-	WL3501_MIB_ATTR_RX_TX_SWITCH_TIME,
-	WL3501_MIB_ATTR_TX_RAMP_ON_TIME,
-	WL3501_MIB_ATTR_TX_RF_DELAY,
-	WL3501_MIB_ATTR_SIFS_TIME,
-	WL3501_MIB_ATTR_RX_RF_DELAY,
-	WL3501_MIB_ATTR_RX_PLCP_DELAY,
-	WL3501_MIB_ATTR_MAC_PROCESSING_DELAY,
-	WL3501_MIB_ATTR_TX_RAMP_OFF_TIME,
-	WL3501_MIB_ATTR_PREAMBLE_LEN,
-	WL3501_MIB_ATTR_PLCP_HEADER_LEN,
-	WL3501_MIB_ATTR_MPDU_DURATION_FACTOR,
-	WL3501_MIB_ATTR_AIR_PROPAGATION_TIME,
-	WL3501_MIB_ATTR_TEMP_TYPE,
-	WL3501_MIB_ATTR_CW_MIN,
-	WL3501_MIB_ATTR_CW_MAX,
-	WL3501_MIB_ATTR_SUPPORT_DATA_RATES_TX,
-	WL3501_MIB_ATTR_SUPPORT_DATA_RATES_RX,
-	WL3501_MIB_ATTR_MPDU_MAX_LEN,
-	WL3501_MIB_ATTR_SUPPORT_TX_ANTENNAS,
-	WL3501_MIB_ATTR_CURRENT_TX_ANTENNA,
-	WL3501_MIB_ATTR_SUPPORT_RX_ANTENNAS,
-	WL3501_MIB_ATTR_DIVERSITY_SUPPORT,
-	WL3501_MIB_ATTR_DIVERSITY_SELECTION_RS,
-	WL3501_MIB_ATTR_NR_SUPPORTED_PWR_LEVELS,
-	WL3501_MIB_ATTR_TX_PWR_LEVEL1,
-	WL3501_MIB_ATTR_TX_PWR_LEVEL2,
-	WL3501_MIB_ATTR_TX_PWR_LEVEL3,
-	WL3501_MIB_ATTR_TX_PWR_LEVEL4,
-	WL3501_MIB_ATTR_TX_PWR_LEVEL5,
-	WL3501_MIB_ATTR_TX_PWR_LEVEL6,
-	WL3501_MIB_ATTR_TX_PWR_LEVEL7,
-	WL3501_MIB_ATTR_TX_PWR_LEVEL8,
-	WL3501_MIB_ATTR_CURRENT_TX_PWR_LEVEL,
-	WL3501_MIB_ATTR_CURRENT_CHAN,
-	WL3501_MIB_ATTR_CCA_MODE_SUPPORTED,
-	WL3501_MIB_ATTR_CURRENT_CCA_MODE,
-	WL3501_MIB_ATTR_ED_THRESHOLD,
-	WL3501_MIB_ATTR_SINTHESIZER_LOCKED,
-	WL3501_MIB_ATTR_CURRENT_PWR_STATE,
-	WL3501_MIB_ATTR_DOZE_TURNON_TIME,
-	WL3501_MIB_ATTR_RCR33,
-	WL3501_MIB_ATTR_DEFAULT_CHAN,
-	WL3501_MIB_ATTR_SSID,
-	WL3501_MIB_ATTR_PWR_MGMT_ENABLE,
-	WL3501_MIB_ATTR_NET_CAPABILITY,
-	WL3501_MIB_ATTR_ROUTING,
-};
-
-enum wl3501_net_type {
-	WL3501_NET_TYPE_INFRA,
-	WL3501_NET_TYPE_ADHOC,
-	WL3501_NET_TYPE_ANY_BSS,
-};
-
-enum wl3501_scan_type {
-	WL3501_SCAN_TYPE_ACTIVE,
-	WL3501_SCAN_TYPE_PASSIVE,
-};
-
-enum wl3501_tx_result {
-	WL3501_TX_RESULT_SUCCESS,
-	WL3501_TX_RESULT_NO_BSS,
-	WL3501_TX_RESULT_RETRY_LIMIT,
-};
-
-enum wl3501_sys_type {
-	WL3501_SYS_TYPE_OPEN,
-	WL3501_SYS_TYPE_SHARE_KEY,
-};
-
-enum wl3501_status {
-	WL3501_STATUS_SUCCESS,
-	WL3501_STATUS_INVALID,
-	WL3501_STATUS_TIMEOUT,
-	WL3501_STATUS_REFUSED,
-	WL3501_STATUS_MANY_REQ,
-	WL3501_STATUS_ALREADY_BSS,
-};
-
-#define WL3501_MGMT_CAPABILITY_ESS		0x0001  /* see 802.11 p.58 */
-#define WL3501_MGMT_CAPABILITY_IBSS		0x0002  /*      - " -	   */
-#define WL3501_MGMT_CAPABILITY_CF_POLLABLE	0x0004  /*      - " -	   */
-#define WL3501_MGMT_CAPABILITY_CF_POLL_REQUEST	0x0008  /*      - " -	   */
-#define WL3501_MGMT_CAPABILITY_PRIVACY		0x0010  /*      - " -	   */
-
-#define IW_REG_DOMAIN_FCC	0x10	/* Channel 1 to 11	USA    */
-#define IW_REG_DOMAIN_DOC	0x20	/* Channel 1 to 11	Canada */
-#define IW_REG_DOMAIN_ETSI	0x30	/* Channel 1 to 13	Europe */
-#define IW_REG_DOMAIN_SPAIN	0x31	/* Channel 10 to 11	Spain  */
-#define IW_REG_DOMAIN_FRANCE	0x32	/* Channel 10 to 13	France */
-#define IW_REG_DOMAIN_MKK	0x40	/* Channel 14		Japan  */
-#define IW_REG_DOMAIN_MKK1	0x41	/* Channel 1-14		Japan  */
-#define IW_REG_DOMAIN_ISRAEL	0x50	/* Channel 3 - 9	Israel */
-
-#define IW_MGMT_RATE_LABEL_MANDATORY 128 /* MSB */
-
-enum iw_mgmt_rate_labels {
-	IW_MGMT_RATE_LABEL_1MBIT   = 2,
-	IW_MGMT_RATE_LABEL_2MBIT   = 4,
-	IW_MGMT_RATE_LABEL_5_5MBIT = 11,
-	IW_MGMT_RATE_LABEL_11MBIT  = 22,
-};
-
-enum iw_mgmt_info_element_ids {
-	IW_MGMT_INFO_ELEMENT_SSID,		  /* Service Set Identity */
-	IW_MGMT_INFO_ELEMENT_SUPPORTED_RATES,
-	IW_MGMT_INFO_ELEMENT_FH_PARAMETER_SET,
-	IW_MGMT_INFO_ELEMENT_DS_PARAMETER_SET,
-	IW_MGMT_INFO_ELEMENT_CS_PARAMETER_SET,
-	IW_MGMT_INFO_ELEMENT_CS_TIM,		  /* Traffic Information Map */
-	IW_MGMT_INFO_ELEMENT_IBSS_PARAMETER_SET,
-	/* 7-15: Reserved, unused */
-	IW_MGMT_INFO_ELEMENT_CHALLENGE_TEXT = 16,
-	/* 17-31 Reserved for challenge text extension */
-	/* 32-255 Reserved, unused */
-};
-
-struct iw_mgmt_info_element {
-	u8 id; /* one of enum iw_mgmt_info_element_ids,
-		  but sizeof(enum) > sizeof(u8) :-( */
-	u8 len;
-	u8 data[];
-} __packed;
-
-struct iw_mgmt_essid_pset {
-	struct iw_mgmt_info_element el;
-	u8 			    essid[IW_ESSID_MAX_SIZE];
-} __packed;
-
-/*
- * According to 802.11 Wireless Networks, the definitive guide - O'Reilly
- * Pg 75
- */ 
-#define IW_DATA_RATE_MAX_LABELS 8
-
-struct iw_mgmt_data_rset {
-	struct iw_mgmt_info_element el;
-	u8 			    data_rate_labels[IW_DATA_RATE_MAX_LABELS];
-} __packed;
-
-struct iw_mgmt_ds_pset {
-	struct iw_mgmt_info_element el;
-	u8 			    chan;
-} __packed;
-
-struct iw_mgmt_cf_pset {
-	struct iw_mgmt_info_element el;
-	u8 			    cfp_count;
-	u8 			    cfp_period;
-	u16 			    cfp_max_duration;
-	u16 			    cfp_dur_remaining;
-} __packed;
-
-struct iw_mgmt_ibss_pset {
-	struct iw_mgmt_info_element el;
-	u16 			    atim_window;
-} __packed;
-
-struct wl3501_tx_hdr {
-	u16	tx_cnt;
-	u8	sync[16];
-	u16	sfd;
-	u8	signal;
-	u8	service;
-	u16	len;
-	u16	crc16;
-	u16	frame_ctrl;
-	u16	duration_id;
-	u8	addr1[ETH_ALEN];
-	u8	addr2[ETH_ALEN];
-	u8	addr3[ETH_ALEN];
-	u16	seq_ctrl;
-	u8	addr4[ETH_ALEN];
-};
-
-struct wl3501_rx_hdr {
-	u16	rx_next_blk;
-	u16	rc_next_frame_blk;
-	u8	rx_blk_ctrl;
-	u8	rx_next_frame;
-	u8	rx_next_frame1;
-	u8	rssi;
-	char	time[8];
-	u8	signal;
-	u8	service;
-	u16	len;
-	u16	crc16;
-	u16	frame_ctrl;
-	u16	duration;
-	u8	addr1[ETH_ALEN];
-	u8	addr2[ETH_ALEN];
-	u8	addr3[ETH_ALEN];
-	u16	seq;
-	u8	addr4[ETH_ALEN];
-};
-
-struct wl3501_start_req {
-	u16			    next_blk;
-	u8			    sig_id;
-	u8			    bss_type;
-	u16			    beacon_period;
-	u16			    dtim_period;
-	u16			    probe_delay;
-	u16			    cap_info;
-	struct iw_mgmt_essid_pset   ssid;
-	struct iw_mgmt_data_rset    bss_basic_rset;
-	struct iw_mgmt_data_rset    operational_rset;
-	struct iw_mgmt_cf_pset	    cf_pset;
-	struct iw_mgmt_ds_pset	    ds_pset;
-	struct iw_mgmt_ibss_pset    ibss_pset;
-};
-
-struct wl3501_assoc_req {
-	u16	next_blk;
-	u8	sig_id;
-	u8	reserved;
-	u16	timeout;
-	u16	cap_info;
-	u16	listen_interval;
-	u8	mac_addr[ETH_ALEN];
-};
-
-struct wl3501_assoc_confirm {
-	u16	next_blk;
-	u8	sig_id;
-	u8	reserved;
-	u16	status;
-};
-
-struct wl3501_assoc_ind {
-	u16	next_blk;
-	u8	sig_id;
-	u8	mac_addr[ETH_ALEN];
-};
-
-struct wl3501_auth_req {
-	u16	next_blk;
-	u8	sig_id;
-	u8	reserved;
-	u16	type;
-	u16	timeout;
-	u8	mac_addr[ETH_ALEN];
-};
-
-struct wl3501_auth_confirm {
-	u16	next_blk;
-	u8	sig_id;
-	u8	reserved;
-	u16	type;
-	u16	status;
-	u8	mac_addr[ETH_ALEN];
-};
-
-struct wl3501_get_req {
-	u16	next_blk;
-	u8	sig_id;
-	u8	reserved;
-	u16	mib_attrib;
-};
-
-struct wl3501_get_confirm {
-	u16	next_blk;
-	u8	sig_id;
-	u8	reserved;
-	u16	mib_status;
-	u16	mib_attrib;
-	u8	mib_value[100];
-};
-
-struct wl3501_req {
-	u16			    beacon_period;
-	u16			    dtim_period;
-	u16			    cap_info;
-	u8			    bss_type;
-	u8			    bssid[ETH_ALEN];
-	struct iw_mgmt_essid_pset   ssid;
-	struct iw_mgmt_ds_pset	    ds_pset;
-	struct iw_mgmt_cf_pset	    cf_pset;
-	struct iw_mgmt_ibss_pset    ibss_pset;
-	struct iw_mgmt_data_rset    bss_basic_rset;
-};
-
-struct wl3501_join_req {
-	u16			    next_blk;
-	u8			    sig_id;
-	u8			    reserved;
-	struct iw_mgmt_data_rset    operational_rset;
-	u16			    reserved2;
-	u16			    timeout;
-	u16			    probe_delay;
-	u8			    timestamp[8];
-	u8			    local_time[8];
-	struct wl3501_req	    req;
-};
-
-struct wl3501_join_confirm {
-	u16	next_blk;
-	u8	sig_id;
-	u8	reserved;
-	u16	status;
-};
-
-struct wl3501_pwr_mgmt_req {
-	u16	next_blk;
-	u8	sig_id;
-	u8	pwr_save;
-	u8	wake_up;
-	u8	receive_dtims;
-};
-
-struct wl3501_pwr_mgmt_confirm {
-	u16	next_blk;
-	u8	sig_id;
-	u8	reserved;
-	u16	status;
-};
-
-struct wl3501_scan_req {
-	u16			    next_blk;
-	u8			    sig_id;
-	u8			    bss_type;
-	u16			    probe_delay;
-	u16			    min_chan_time;
-	u16			    max_chan_time;
-	u8			    chan_list[14];
-	u8			    bssid[ETH_ALEN];
-	struct iw_mgmt_essid_pset   ssid;
-	enum wl3501_scan_type	    scan_type;
-};
-
-struct wl3501_scan_confirm {
-	u16			    next_blk;
-	u8			    sig_id;
-	u8			    reserved;
-	u16			    status;
-	char			    timestamp[8];
-	char			    localtime[8];
-	struct wl3501_req	    req;
-	u8			    rssi;
-};
-
-struct wl3501_start_confirm {
-	u16	next_blk;
-	u8	sig_id;
-	u8	reserved;
-	u16	status;
-};
-
-struct wl3501_md_req {
-	u16	next_blk;
-	u8	sig_id;
-	u8	routing;
-	u16	data;
-	u16	size;
-	u8	pri;
-	u8	service_class;
-	struct {
-		u8	daddr[ETH_ALEN];
-		u8	saddr[ETH_ALEN];
-	} addr;
-};
-
-struct wl3501_md_ind {
-	u16	next_blk;
-	u8	sig_id;
-	u8	routing;
-	u16	data;
-	u16	size;
-	u8	reception;
-	u8	pri;
-	u8	service_class;
-	struct {
-		u8	daddr[ETH_ALEN];
-		u8	saddr[ETH_ALEN];
-	} addr;
-};
-
-struct wl3501_md_confirm {
-	u16	next_blk;
-	u8	sig_id;
-	u8	reserved;
-	u16	data;
-	u8	status;
-	u8	pri;
-	u8	service_class;
-};
-
-struct wl3501_resync_req {
-	u16	next_blk;
-	u8	sig_id;
-};
-
-/* Definitions for supporting clone adapters. */
-/* System Interface Registers (SIR space) */
-#define WL3501_NIC_GCR ((u8)0x00)	/* SIR0 - General Conf Register */
-#define WL3501_NIC_BSS ((u8)0x01)	/* SIR1 - Bank Switching Select Reg */
-#define WL3501_NIC_LMAL ((u8)0x02)	/* SIR2 - Local Mem addr Reg [7:0] */
-#define WL3501_NIC_LMAH ((u8)0x03)	/* SIR3 - Local Mem addr Reg [14:8] */
-#define WL3501_NIC_IODPA ((u8)0x04)	/* SIR4 - I/O Data Port A */
-#define WL3501_NIC_IODPB ((u8)0x05)	/* SIR5 - I/O Data Port B */
-#define WL3501_NIC_IODPC ((u8)0x06)	/* SIR6 - I/O Data Port C */
-#define WL3501_NIC_IODPD ((u8)0x07)	/* SIR7 - I/O Data Port D */
-
-/* Bits in GCR */
-#define WL3501_GCR_SWRESET ((u8)0x80)
-#define WL3501_GCR_CORESET ((u8)0x40)
-#define WL3501_GCR_DISPWDN ((u8)0x20)
-#define WL3501_GCR_ECWAIT  ((u8)0x10)
-#define WL3501_GCR_ECINT   ((u8)0x08)
-#define WL3501_GCR_INT2EC  ((u8)0x04)
-#define WL3501_GCR_ENECINT ((u8)0x02)
-#define WL3501_GCR_DAM     ((u8)0x01)
-
-/* Bits in BSS (Bank Switching Select Register) */
-#define WL3501_BSS_FPAGE0 ((u8)0x20)	/* Flash memory page0 */
-#define WL3501_BSS_FPAGE1 ((u8)0x28)
-#define WL3501_BSS_FPAGE2 ((u8)0x30)
-#define WL3501_BSS_FPAGE3 ((u8)0x38)
-#define WL3501_BSS_SPAGE0 ((u8)0x00)	/* SRAM page0 */
-#define WL3501_BSS_SPAGE1 ((u8)0x08)
-#define WL3501_BSS_SPAGE2 ((u8)0x10)
-#define WL3501_BSS_SPAGE3 ((u8)0x18)
-
-/* Define Driver Interface */
-/* Refer IEEE 802.11 */
-/* Tx packet header, include PLCP and MPDU */
-/* Tx PLCP Header */
-struct wl3501_80211_tx_plcp_hdr {
-	u8	sync[16];
-	u16	sfd;
-	u8	signal;
-	u8	service;
-	u16	len;
-	u16	crc16;
-} __packed;
-
-struct wl3501_80211_tx_hdr {
-	struct wl3501_80211_tx_plcp_hdr	pclp_hdr;
-	struct ieee80211_hdr		mac_hdr;
-} __packed __aligned(2);
-
-/*
-   Reserve the beginning Tx space for descriptor use.
-
-   TxBlockOffset -->	*----*----*----*----* \
-	(TxFreeDesc)	|  0 |  1 |  2 |  3 |  \
-			|  4 |  5 |  6 |  7 |   |
-			|  8 |  9 | 10 | 11 |   TX_DESC * 20
-			| 12 | 13 | 14 | 15 |   |
-			| 16 | 17 | 18 | 19 |  /
-   TxBufferBegin -->	*----*----*----*----* /
-   (TxBufferHead)	| 		    |
-   (TxBufferTail)	| 		    |
-			|    Send Buffer    |
-			| 		    |
-			|		    |
-			*-------------------*
-   TxBufferEnd    -------------------------/
-
-*/
-
-struct wl3501_card {
-	int				base_addr;
-	u8				mac_addr[ETH_ALEN];
-	spinlock_t			lock;
-	wait_queue_head_t		wait;
-	struct wl3501_get_confirm	sig_get_confirm;
-	struct wl3501_pwr_mgmt_confirm	sig_pwr_mgmt_confirm;
-	u16				tx_buffer_size;
-	u16				tx_buffer_head;
-	u16				tx_buffer_tail;
-	u16				tx_buffer_cnt;
-	u16				esbq_req_start;
-	u16				esbq_req_end;
-	u16				esbq_req_head;
-	u16				esbq_req_tail;
-	u16				esbq_confirm_start;
-	u16				esbq_confirm_end;
-	u16				esbq_confirm;
-	struct iw_mgmt_essid_pset  	essid;
-	struct iw_mgmt_essid_pset  	keep_essid;
-	u8				bssid[ETH_ALEN];
-	int				net_type;
-	char				nick[32];
-	char				card_name[32];
-	char				firmware_date[32];
-	u8				chan;
-	u8				cap_info;
-	u16				start_seg;
-	u16				bss_cnt;
-	u16				join_sta_bss;
-	u8				rssi;
-	u8				adhoc_times;
-	u8				reg_domain;
-	u8				version[2];
-	struct wl3501_scan_confirm	bss_set[20];
-
-	struct iw_statistics		wstats;
-	struct iw_spy_data		spy_data;
-	struct iw_public_data		wireless_data;
-	struct pcmcia_device		*p_dev;
-};
-#endif
diff --git a/drivers/net/wireless/legacy/wl3501_cs.c b/drivers/net/wireless/legacy/wl3501_cs.c
deleted file mode 100644
index c45c4b7cbbaf..000000000000
--- a/drivers/net/wireless/legacy/wl3501_cs.c
+++ /dev/null
@@ -1,2036 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * WL3501 Wireless LAN PCMCIA Card Driver for Linux
- * Written originally for Linux 2.0.30 by Fox Chen, mhchen@golf.ccl.itri.org.tw
- * Ported to 2.2, 2.4 & 2.5 by Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- * Wireless extensions in 2.4 by Gustavo Niemeyer <niemeyer@conectiva.com>
- *
- * References used by Fox Chen while writing the original driver for 2.0.30:
- *
- *   1. WL24xx packet drivers (tooasm.asm)
- *   2. Access Point Firmware Interface Specification for IEEE 802.11 SUTRO
- *   3. IEEE 802.11
- *   4. Linux network driver (/usr/src/linux/drivers/net)
- *   5. ISA card driver - wl24.c
- *   6. Linux PCMCIA skeleton driver - skeleton.c
- *   7. Linux PCMCIA 3c589 network driver - 3c589_cs.c
- *
- * Tested with WL2400 firmware 1.2, Linux 2.0.30, and pcmcia-cs-2.9.12
- *   1. Performance: about 165 Kbytes/sec in TCP/IP with Ad-Hoc mode.
- *      rsh 192.168.1.3 "dd if=/dev/zero bs=1k count=1000" > /dev/null
- *      (Specification 2M bits/sec. is about 250 Kbytes/sec., but we must deduct
- *       ETHER/IP/UDP/TCP header, and acknowledgement overhead)
- *
- * Tested with Planet AP in 2.4.17, 184 Kbytes/s in UDP in Infrastructure mode,
- * 173 Kbytes/s in TCP.
- *
- * Tested with Planet AP in 2.5.73-bk, 216 Kbytes/s in Infrastructure mode
- * with a SMP machine (dual pentium 100), using pktgen, 432 pps (pkt_size = 60)
- */
-
-#include <linux/delay.h>
-#include <linux/types.h>
-#include <linux/interrupt.h>
-#include <linux/in.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/fcntl.h>
-#include <linux/if_arp.h>
-#include <linux/ioport.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/skbuff.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/wireless.h>
-#include <net/cfg80211.h>
-
-#include <net/iw_handler.h>
-
-#include <pcmcia/cistpl.h>
-#include <pcmcia/cisreg.h>
-#include <pcmcia/ds.h>
-
-#include <asm/io.h>
-#include <linux/uaccess.h>
-
-#include "wl3501.h"
-
-#ifndef __i386__
-#define slow_down_io()
-#endif
-
-/* For rough constant delay */
-#define WL3501_NOPLOOP(n) { int x = 0; while (x++ < n) slow_down_io(); }
-
-
-
-#define wl3501_outb(a, b) { outb(a, b); slow_down_io(); }
-#define wl3501_outb_p(a, b) { outb_p(a, b); slow_down_io(); }
-#define wl3501_outsb(a, b, c) { outsb(a, b, c); slow_down_io(); }
-
-#define WL3501_RELEASE_TIMEOUT (25 * HZ)
-#define WL3501_MAX_ADHOC_TRIES 16
-
-#define WL3501_RESUME	0
-#define WL3501_SUSPEND	1
-
-static int wl3501_config(struct pcmcia_device *link);
-static void wl3501_release(struct pcmcia_device *link);
-
-static const struct {
-	int reg_domain;
-	int min, max, deflt;
-} iw_channel_table[] = {
-	{
-		.reg_domain = IW_REG_DOMAIN_FCC,
-		.min	    = 1,
-		.max	    = 11,
-		.deflt	    = 1,
-	},
-	{
-		.reg_domain = IW_REG_DOMAIN_DOC,
-		.min	    = 1,
-		.max	    = 11,
-		.deflt	    = 1,
-	},
-	{
-		.reg_domain = IW_REG_DOMAIN_ETSI,
-		.min	    = 1,
-		.max	    = 13,
-		.deflt	    = 1,
-	},
-	{
-		.reg_domain = IW_REG_DOMAIN_SPAIN,
-		.min	    = 10,
-		.max	    = 11,
-		.deflt	    = 10,
-	},
-	{
-		.reg_domain = IW_REG_DOMAIN_FRANCE,
-		.min	    = 10,
-		.max	    = 13,
-		.deflt	    = 10,
-	},
-	{
-		.reg_domain = IW_REG_DOMAIN_MKK,
-		.min	    = 14,
-		.max	    = 14,
-		.deflt	    = 14,
-	},
-	{
-		.reg_domain = IW_REG_DOMAIN_MKK1,
-		.min	    = 1,
-		.max	    = 14,
-		.deflt	    = 1,
-	},
-	{
-		.reg_domain = IW_REG_DOMAIN_ISRAEL,
-		.min	    = 3,
-		.max	    = 9,
-		.deflt	    = 9,
-	},
-};
-
-/**
- * iw_valid_channel - validate channel in regulatory domain
- * @reg_domain: regulatory domain
- * @channel: channel to validate
- *
- * Returns 0 if invalid in the specified regulatory domain, non-zero if valid.
- */
-static int iw_valid_channel(int reg_domain, int channel)
-{
-	int i, rc = 0;
-
-	for (i = 0; i < ARRAY_SIZE(iw_channel_table); i++)
-		if (reg_domain == iw_channel_table[i].reg_domain) {
-			rc = channel >= iw_channel_table[i].min &&
-			     channel <= iw_channel_table[i].max;
-			break;
-		}
-	return rc;
-}
-
-/**
- * iw_default_channel - get default channel for a regulatory domain
- * @reg_domain: regulatory domain
- *
- * Returns the default channel for a regulatory domain
- */
-static int iw_default_channel(int reg_domain)
-{
-	int i, rc = 1;
-
-	for (i = 0; i < ARRAY_SIZE(iw_channel_table); i++)
-		if (reg_domain == iw_channel_table[i].reg_domain) {
-			rc = iw_channel_table[i].deflt;
-			break;
-		}
-	return rc;
-}
-
-static void iw_set_mgmt_info_element(enum iw_mgmt_info_element_ids id,
-				     struct iw_mgmt_info_element *el,
-				     void *value, int len)
-{
-	el->id  = id;
-	el->len = len;
-	memcpy(el->data, value, len);
-}
-
-static void iw_copy_mgmt_info_element(struct iw_mgmt_info_element *to,
-				      struct iw_mgmt_info_element *from)
-{
-	iw_set_mgmt_info_element(from->id, to, from->data, from->len);
-}
-
-static inline void wl3501_switch_page(struct wl3501_card *this, u8 page)
-{
-	wl3501_outb(page, this->base_addr + WL3501_NIC_BSS);
-}
-
-/*
- * Get Ethernet MAC address.
- *
- * WARNING: We switch to FPAGE0 and switc back again.
- *          Making sure there is no other WL function beening called by ISR.
- */
-static int wl3501_get_flash_mac_addr(struct wl3501_card *this)
-{
-	int base_addr = this->base_addr;
-
-	/* get MAC addr */
-	wl3501_outb(WL3501_BSS_FPAGE3, base_addr + WL3501_NIC_BSS); /* BSS */
-	wl3501_outb(0x00, base_addr + WL3501_NIC_LMAL);	/* LMAL */
-	wl3501_outb(0x40, base_addr + WL3501_NIC_LMAH);	/* LMAH */
-
-	/* wait for reading EEPROM */
-	WL3501_NOPLOOP(100);
-	this->mac_addr[0] = inb(base_addr + WL3501_NIC_IODPA);
-	WL3501_NOPLOOP(100);
-	this->mac_addr[1] = inb(base_addr + WL3501_NIC_IODPA);
-	WL3501_NOPLOOP(100);
-	this->mac_addr[2] = inb(base_addr + WL3501_NIC_IODPA);
-	WL3501_NOPLOOP(100);
-	this->mac_addr[3] = inb(base_addr + WL3501_NIC_IODPA);
-	WL3501_NOPLOOP(100);
-	this->mac_addr[4] = inb(base_addr + WL3501_NIC_IODPA);
-	WL3501_NOPLOOP(100);
-	this->mac_addr[5] = inb(base_addr + WL3501_NIC_IODPA);
-	WL3501_NOPLOOP(100);
-	this->reg_domain = inb(base_addr + WL3501_NIC_IODPA);
-	WL3501_NOPLOOP(100);
-	wl3501_outb(WL3501_BSS_FPAGE0, base_addr + WL3501_NIC_BSS);
-	wl3501_outb(0x04, base_addr + WL3501_NIC_LMAL);
-	wl3501_outb(0x40, base_addr + WL3501_NIC_LMAH);
-	WL3501_NOPLOOP(100);
-	this->version[0] = inb(base_addr + WL3501_NIC_IODPA);
-	WL3501_NOPLOOP(100);
-	this->version[1] = inb(base_addr + WL3501_NIC_IODPA);
-	/* switch to SRAM Page 0 (for safety) */
-	wl3501_switch_page(this, WL3501_BSS_SPAGE0);
-
-	/* The MAC addr should be 00:60:... */
-	return this->mac_addr[0] == 0x00 && this->mac_addr[1] == 0x60;
-}
-
-/**
- * wl3501_set_to_wla - Move 'size' bytes from PC to card
- * @this: Card
- * @dest: Card addressing space
- * @src: PC addressing space
- * @size: Bytes to move
- *
- * Move 'size' bytes from PC to card. (Shouldn't be interrupted)
- */
-static void wl3501_set_to_wla(struct wl3501_card *this, u16 dest, void *src,
-			      int size)
-{
-	/* switch to SRAM Page 0 */
-	wl3501_switch_page(this, (dest & 0x8000) ? WL3501_BSS_SPAGE1 :
-						   WL3501_BSS_SPAGE0);
-	/* set LMAL and LMAH */
-	wl3501_outb(dest & 0xff, this->base_addr + WL3501_NIC_LMAL);
-	wl3501_outb(((dest >> 8) & 0x7f), this->base_addr + WL3501_NIC_LMAH);
-
-	/* rep out to Port A */
-	wl3501_outsb(this->base_addr + WL3501_NIC_IODPA, src, size);
-}
-
-/**
- * wl3501_get_from_wla - Move 'size' bytes from card to PC
- * @this: Card
- * @src: Card addressing space
- * @dest: PC addressing space
- * @size: Bytes to move
- *
- * Move 'size' bytes from card to PC. (Shouldn't be interrupted)
- */
-static void wl3501_get_from_wla(struct wl3501_card *this, u16 src, void *dest,
-				int size)
-{
-	/* switch to SRAM Page 0 */
-	wl3501_switch_page(this, (src & 0x8000) ? WL3501_BSS_SPAGE1 :
-						  WL3501_BSS_SPAGE0);
-	/* set LMAL and LMAH */
-	wl3501_outb(src & 0xff, this->base_addr + WL3501_NIC_LMAL);
-	wl3501_outb((src >> 8) & 0x7f, this->base_addr + WL3501_NIC_LMAH);
-
-	/* rep get from Port A */
-	insb(this->base_addr + WL3501_NIC_IODPA, dest, size);
-}
-
-/*
- * Get/Allocate a free Tx Data Buffer
- *
- *  *--------------*-----------------*----------------------------------*
- *  |    PLCP      |    MAC Header   |  DST  SRC         Data ...       |
- *  |  (24 bytes)  |    (30 bytes)   |  (6)  (6)  (Ethernet Row Data)   |
- *  *--------------*-----------------*----------------------------------*
- *  \               \- IEEE 802.11 -/ \-------------- len --------------/
- *   \-struct wl3501_80211_tx_hdr--/   \-------- Ethernet Frame -------/
- *
- * Return = Position in Card
- */
-static u16 wl3501_get_tx_buffer(struct wl3501_card *this, u16 len)
-{
-	u16 next, blk_cnt = 0, zero = 0;
-	u16 full_len = sizeof(struct wl3501_80211_tx_hdr) + len;
-	u16 ret = 0;
-
-	if (full_len > this->tx_buffer_cnt * 254)
-		goto out;
-	ret = this->tx_buffer_head;
-	while (full_len) {
-		if (full_len < 254)
-			full_len = 0;
-		else
-			full_len -= 254;
-		wl3501_get_from_wla(this, this->tx_buffer_head, &next,
-				    sizeof(next));
-		if (!full_len)
-			wl3501_set_to_wla(this, this->tx_buffer_head, &zero,
-					  sizeof(zero));
-		this->tx_buffer_head = next;
-		blk_cnt++;
-		/* if buffer is not enough */
-		if (!next && full_len) {
-			this->tx_buffer_head = ret;
-			ret = 0;
-			goto out;
-		}
-	}
-	this->tx_buffer_cnt -= blk_cnt;
-out:
-	return ret;
-}
-
-/*
- * Free an allocated Tx Buffer. ptr must be correct position.
- */
-static void wl3501_free_tx_buffer(struct wl3501_card *this, u16 ptr)
-{
-	/* check if all space is not free */
-	if (!this->tx_buffer_head)
-		this->tx_buffer_head = ptr;
-	else
-		wl3501_set_to_wla(this, this->tx_buffer_tail,
-				  &ptr, sizeof(ptr));
-	while (ptr) {
-		u16 next;
-
-		this->tx_buffer_cnt++;
-		wl3501_get_from_wla(this, ptr, &next, sizeof(next));
-		this->tx_buffer_tail = ptr;
-		ptr = next;
-	}
-}
-
-static int wl3501_esbq_req_test(struct wl3501_card *this)
-{
-	u8 tmp = 0;
-
-	wl3501_get_from_wla(this, this->esbq_req_head + 3, &tmp, sizeof(tmp));
-	return tmp & 0x80;
-}
-
-static void wl3501_esbq_req(struct wl3501_card *this, u16 *ptr)
-{
-	u16 tmp = 0;
-
-	wl3501_set_to_wla(this, this->esbq_req_head, ptr, 2);
-	wl3501_set_to_wla(this, this->esbq_req_head + 2, &tmp, sizeof(tmp));
-	this->esbq_req_head += 4;
-	if (this->esbq_req_head >= this->esbq_req_end)
-		this->esbq_req_head = this->esbq_req_start;
-}
-
-static int wl3501_esbq_exec(struct wl3501_card *this, void *sig, int sig_size)
-{
-	int rc = -EIO;
-
-	if (wl3501_esbq_req_test(this)) {
-		u16 ptr = wl3501_get_tx_buffer(this, sig_size);
-		if (ptr) {
-			wl3501_set_to_wla(this, ptr, sig, sig_size);
-			wl3501_esbq_req(this, &ptr);
-			rc = 0;
-		}
-	}
-	return rc;
-}
-
-static int wl3501_request_mib(struct wl3501_card *this, u8 index, void *bf)
-{
-	struct wl3501_get_req sig = {
-		.sig_id	    = WL3501_SIG_GET_REQ,
-		.mib_attrib = index,
-	};
-	unsigned long flags;
-	int rc = -EIO;
-
-	spin_lock_irqsave(&this->lock, flags);
-	if (wl3501_esbq_req_test(this)) {
-		u16 ptr = wl3501_get_tx_buffer(this, sizeof(sig));
-		if (ptr) {
-			wl3501_set_to_wla(this, ptr, &sig, sizeof(sig));
-			wl3501_esbq_req(this, &ptr);
-			this->sig_get_confirm.mib_status = 255;
-			rc = 0;
-		}
-	}
-	spin_unlock_irqrestore(&this->lock, flags);
-
-	return rc;
-}
-
-static int wl3501_get_mib_value(struct wl3501_card *this, u8 index,
-				void *bf, int size)
-{
-	int rc;
-
-	rc = wl3501_request_mib(this, index, bf);
-	if (rc)
-		return rc;
-
-	rc = wait_event_interruptible(this->wait,
-		this->sig_get_confirm.mib_status != 255);
-	if (rc)
-		return rc;
-
-	memcpy(bf, this->sig_get_confirm.mib_value, size);
-	return 0;
-}
-
-static int wl3501_pwr_mgmt(struct wl3501_card *this, int suspend)
-{
-	struct wl3501_pwr_mgmt_req sig = {
-		.sig_id		= WL3501_SIG_PWR_MGMT_REQ,
-		.pwr_save	= suspend,
-		.wake_up	= !suspend,
-		.receive_dtims	= 10,
-	};
-	unsigned long flags;
-	int rc = -EIO;
-
-	spin_lock_irqsave(&this->lock, flags);
-	if (wl3501_esbq_req_test(this)) {
-		u16 ptr = wl3501_get_tx_buffer(this, sizeof(sig));
-		if (ptr) {
-			wl3501_set_to_wla(this, ptr, &sig, sizeof(sig));
-			wl3501_esbq_req(this, &ptr);
-			this->sig_pwr_mgmt_confirm.status = 255;
-			spin_unlock_irqrestore(&this->lock, flags);
-			rc = wait_event_interruptible(this->wait,
-				this->sig_pwr_mgmt_confirm.status != 255);
-			printk(KERN_INFO "%s: %s status=%d\n", __func__,
-			       suspend ? "suspend" : "resume",
-			       this->sig_pwr_mgmt_confirm.status);
-			goto out;
-		}
-	}
-	spin_unlock_irqrestore(&this->lock, flags);
-out:
-	return rc;
-}
-
-/**
- * wl3501_send_pkt - Send a packet.
- * @this: Card
- * @data: Ethernet raw frame.  (e.g. data[0] - data[5] is Dest MAC Addr,
- *                                   data[6] - data[11] is Src MAC Addr)
- * @len: Packet length
- * Ref: IEEE 802.11
- */
-static int wl3501_send_pkt(struct wl3501_card *this, u8 *data, u16 len)
-{
-	u16 bf, sig_bf, next, tmplen, pktlen;
-	struct wl3501_md_req sig = {
-		.sig_id = WL3501_SIG_MD_REQ,
-	};
-	size_t sig_addr_len = sizeof(sig.addr);
-	u8 *pdata = (char *)data;
-	int rc = -EIO;
-
-	if (wl3501_esbq_req_test(this)) {
-		sig_bf = wl3501_get_tx_buffer(this, sizeof(sig));
-		rc = -ENOMEM;
-		if (!sig_bf)	/* No free buffer available */
-			goto out;
-		bf = wl3501_get_tx_buffer(this, len + 26 + 24);
-		if (!bf) {
-			/* No free buffer available */
-			wl3501_free_tx_buffer(this, sig_bf);
-			goto out;
-		}
-		rc = 0;
-		memcpy(&sig.addr, pdata, sig_addr_len);
-		pktlen = len - sig_addr_len;
-		pdata += sig_addr_len;
-		sig.data = bf;
-		if (((*pdata) * 256 + (*(pdata + 1))) > 1500) {
-			u8 addr4[ETH_ALEN] = {
-				[0] = 0xAA, [1] = 0xAA, [2] = 0x03, [4] = 0x00,
-			};
-
-			wl3501_set_to_wla(this, bf + 2 +
-					  offsetof(struct wl3501_tx_hdr, addr4),
-					  addr4, sizeof(addr4));
-			sig.size = pktlen + 24 + 4 + 6;
-			if (pktlen > (254 - sizeof(struct wl3501_tx_hdr))) {
-				tmplen = 254 - sizeof(struct wl3501_tx_hdr);
-				pktlen -= tmplen;
-			} else {
-				tmplen = pktlen;
-				pktlen = 0;
-			}
-			wl3501_set_to_wla(this,
-					  bf + 2 + sizeof(struct wl3501_tx_hdr),
-					  pdata, tmplen);
-			pdata += tmplen;
-			wl3501_get_from_wla(this, bf, &next, sizeof(next));
-			bf = next;
-		} else {
-			sig.size = pktlen + 24 + 4 - 2;
-			pdata += 2;
-			pktlen -= 2;
-			if (pktlen > (254 - sizeof(struct wl3501_tx_hdr) + 6)) {
-				tmplen = 254 - sizeof(struct wl3501_tx_hdr) + 6;
-				pktlen -= tmplen;
-			} else {
-				tmplen = pktlen;
-				pktlen = 0;
-			}
-			wl3501_set_to_wla(this, bf + 2 +
-					  offsetof(struct wl3501_tx_hdr, addr4),
-					  pdata, tmplen);
-			pdata += tmplen;
-			wl3501_get_from_wla(this, bf, &next, sizeof(next));
-			bf = next;
-		}
-		while (pktlen > 0) {
-			if (pktlen > 254) {
-				tmplen = 254;
-				pktlen -= 254;
-			} else {
-				tmplen = pktlen;
-				pktlen = 0;
-			}
-			wl3501_set_to_wla(this, bf + 2, pdata, tmplen);
-			pdata += tmplen;
-			wl3501_get_from_wla(this, bf, &next, sizeof(next));
-			bf = next;
-		}
-		wl3501_set_to_wla(this, sig_bf, &sig, sizeof(sig));
-		wl3501_esbq_req(this, &sig_bf);
-	}
-out:
-	return rc;
-}
-
-static int wl3501_mgmt_resync(struct wl3501_card *this)
-{
-	struct wl3501_resync_req sig = {
-		.sig_id = WL3501_SIG_RESYNC_REQ,
-	};
-
-	return wl3501_esbq_exec(this, &sig, sizeof(sig));
-}
-
-static inline int wl3501_fw_bss_type(struct wl3501_card *this)
-{
-	return this->net_type == IW_MODE_INFRA ? WL3501_NET_TYPE_INFRA :
-						 WL3501_NET_TYPE_ADHOC;
-}
-
-static inline int wl3501_fw_cap_info(struct wl3501_card *this)
-{
-	return this->net_type == IW_MODE_INFRA ? WL3501_MGMT_CAPABILITY_ESS :
-						 WL3501_MGMT_CAPABILITY_IBSS;
-}
-
-static int wl3501_mgmt_scan(struct wl3501_card *this, u16 chan_time)
-{
-	struct wl3501_scan_req sig = {
-		.sig_id		= WL3501_SIG_SCAN_REQ,
-		.scan_type	= WL3501_SCAN_TYPE_ACTIVE,
-		.probe_delay	= 0x10,
-		.min_chan_time	= chan_time,
-		.max_chan_time	= chan_time,
-		.bss_type	= wl3501_fw_bss_type(this),
-	};
-
-	this->bss_cnt = this->join_sta_bss = 0;
-	return wl3501_esbq_exec(this, &sig, sizeof(sig));
-}
-
-static int wl3501_mgmt_join(struct wl3501_card *this, u16 stas)
-{
-	struct wl3501_join_req sig = {
-		.sig_id		  = WL3501_SIG_JOIN_REQ,
-		.timeout	  = 10,
-		.req.ds_pset = {
-			.el = {
-				.id  = IW_MGMT_INFO_ELEMENT_DS_PARAMETER_SET,
-				.len = 1,
-			},
-			.chan	= this->chan,
-		},
-	};
-
-	memcpy(&sig.req, &this->bss_set[stas].req, sizeof(sig.req));
-	return wl3501_esbq_exec(this, &sig, sizeof(sig));
-}
-
-static int wl3501_mgmt_start(struct wl3501_card *this)
-{
-	struct wl3501_start_req sig = {
-		.sig_id			= WL3501_SIG_START_REQ,
-		.beacon_period		= 400,
-		.dtim_period		= 1,
-		.ds_pset = {
-			.el = {
-				.id  = IW_MGMT_INFO_ELEMENT_DS_PARAMETER_SET,
-				.len = 1,
-			},
-			.chan	= this->chan,
-		},
-		.bss_basic_rset	= {
-			.el = {
-				.id	= IW_MGMT_INFO_ELEMENT_SUPPORTED_RATES,
-				.len = 2,
-			},
-			.data_rate_labels = {
-				[0] = IW_MGMT_RATE_LABEL_MANDATORY |
-				      IW_MGMT_RATE_LABEL_1MBIT,
-				[1] = IW_MGMT_RATE_LABEL_MANDATORY |
-				      IW_MGMT_RATE_LABEL_2MBIT,
-			},
-		},
-		.operational_rset	= {
-			.el = {
-				.id	= IW_MGMT_INFO_ELEMENT_SUPPORTED_RATES,
-				.len = 2,
-			},
-			.data_rate_labels = {
-				[0] = IW_MGMT_RATE_LABEL_MANDATORY |
-				      IW_MGMT_RATE_LABEL_1MBIT,
-				[1] = IW_MGMT_RATE_LABEL_MANDATORY |
-				      IW_MGMT_RATE_LABEL_2MBIT,
-			},
-		},
-		.ibss_pset		= {
-			.el = {
-				.id	 = IW_MGMT_INFO_ELEMENT_IBSS_PARAMETER_SET,
-				.len     = 2,
-			},
-			.atim_window = 10,
-		},
-		.bss_type		= wl3501_fw_bss_type(this),
-		.cap_info		= wl3501_fw_cap_info(this),
-	};
-
-	iw_copy_mgmt_info_element(&sig.ssid.el, &this->essid.el);
-	iw_copy_mgmt_info_element(&this->keep_essid.el, &this->essid.el);
-	return wl3501_esbq_exec(this, &sig, sizeof(sig));
-}
-
-static void wl3501_mgmt_scan_confirm(struct wl3501_card *this, u16 addr)
-{
-	u16 i = 0;
-	int matchflag = 0;
-	struct wl3501_scan_confirm sig;
-
-	pr_debug("entry");
-	wl3501_get_from_wla(this, addr, &sig, sizeof(sig));
-	if (sig.status == WL3501_STATUS_SUCCESS) {
-		pr_debug("success");
-		if ((this->net_type == IW_MODE_INFRA &&
-		     (sig.req.cap_info & WL3501_MGMT_CAPABILITY_ESS)) ||
-		    (this->net_type == IW_MODE_ADHOC &&
-		     (sig.req.cap_info & WL3501_MGMT_CAPABILITY_IBSS)) ||
-		    this->net_type == IW_MODE_AUTO) {
-			if (!this->essid.el.len)
-				matchflag = 1;
-			else if (this->essid.el.len == 3 &&
-				 !memcmp(this->essid.essid, "ANY", 3))
-				matchflag = 1;
-			else if (this->essid.el.len != sig.req.ssid.el.len)
-				matchflag = 0;
-			else if (memcmp(this->essid.essid, sig.req.ssid.essid,
-					this->essid.el.len))
-				matchflag = 0;
-			else
-				matchflag = 1;
-			if (matchflag) {
-				for (i = 0; i < this->bss_cnt; i++) {
-					if (ether_addr_equal_unaligned(this->bss_set[i].req.bssid,
-								       sig.req.bssid)) {
-						matchflag = 0;
-						break;
-					}
-				}
-			}
-			if (matchflag && (i < 20)) {
-				memcpy(&this->bss_set[i].req,
-				       &sig.req, sizeof(sig.req));
-				this->bss_cnt++;
-				this->rssi = sig.rssi;
-				this->bss_set[i].rssi = sig.rssi;
-			}
-		}
-	} else if (sig.status == WL3501_STATUS_TIMEOUT) {
-		pr_debug("timeout");
-		this->join_sta_bss = 0;
-		for (i = this->join_sta_bss; i < this->bss_cnt; i++)
-			if (!wl3501_mgmt_join(this, i))
-				break;
-		this->join_sta_bss = i;
-		if (this->join_sta_bss == this->bss_cnt) {
-			if (this->net_type == IW_MODE_INFRA)
-				wl3501_mgmt_scan(this, 100);
-			else {
-				this->adhoc_times++;
-				if (this->adhoc_times > WL3501_MAX_ADHOC_TRIES)
-					wl3501_mgmt_start(this);
-				else
-					wl3501_mgmt_scan(this, 100);
-			}
-		}
-	}
-}
-
-/**
- * wl3501_block_interrupt - Mask interrupt from SUTRO
- * @this: Card
- *
- * Mask interrupt from SUTRO. (i.e. SUTRO cannot interrupt the HOST)
- * Return: 1 if interrupt is originally enabled
- */
-static int wl3501_block_interrupt(struct wl3501_card *this)
-{
-	u8 old = inb(this->base_addr + WL3501_NIC_GCR);
-	u8 new = old & (~(WL3501_GCR_ECINT | WL3501_GCR_INT2EC |
-			WL3501_GCR_ENECINT));
-
-	wl3501_outb(new, this->base_addr + WL3501_NIC_GCR);
-	return old & WL3501_GCR_ENECINT;
-}
-
-/**
- * wl3501_unblock_interrupt - Enable interrupt from SUTRO
- * @this: Card
- *
- * Enable interrupt from SUTRO. (i.e. SUTRO can interrupt the HOST)
- * Return: 1 if interrupt is originally enabled
- */
-static int wl3501_unblock_interrupt(struct wl3501_card *this)
-{
-	u8 old = inb(this->base_addr + WL3501_NIC_GCR);
-	u8 new = (old & ~(WL3501_GCR_ECINT | WL3501_GCR_INT2EC)) |
-		  WL3501_GCR_ENECINT;
-
-	wl3501_outb(new, this->base_addr + WL3501_NIC_GCR);
-	return old & WL3501_GCR_ENECINT;
-}
-
-/**
- * wl3501_receive - Receive data from Receive Queue.
- *
- * Receive data from Receive Queue.
- *
- * @this: card
- * @bf: address of host
- * @size: size of buffer.
- */
-static u16 wl3501_receive(struct wl3501_card *this, u8 *bf, u16 size)
-{
-	u16 next_addr, next_addr1;
-	u8 *data = bf + 12;
-
-	size -= 12;
-	wl3501_get_from_wla(this, this->start_seg + 2,
-			    &next_addr, sizeof(next_addr));
-	if (size > WL3501_BLKSZ - sizeof(struct wl3501_rx_hdr)) {
-		wl3501_get_from_wla(this,
-				    this->start_seg +
-					sizeof(struct wl3501_rx_hdr), data,
-				    WL3501_BLKSZ -
-					sizeof(struct wl3501_rx_hdr));
-		size -= WL3501_BLKSZ - sizeof(struct wl3501_rx_hdr);
-		data += WL3501_BLKSZ - sizeof(struct wl3501_rx_hdr);
-	} else {
-		wl3501_get_from_wla(this,
-				    this->start_seg +
-					sizeof(struct wl3501_rx_hdr),
-				    data, size);
-		size = 0;
-	}
-	while (size > 0) {
-		if (size > WL3501_BLKSZ - 5) {
-			wl3501_get_from_wla(this, next_addr + 5, data,
-					    WL3501_BLKSZ - 5);
-			size -= WL3501_BLKSZ - 5;
-			data += WL3501_BLKSZ - 5;
-			wl3501_get_from_wla(this, next_addr + 2, &next_addr1,
-					    sizeof(next_addr1));
-			next_addr = next_addr1;
-		} else {
-			wl3501_get_from_wla(this, next_addr + 5, data, size);
-			size = 0;
-		}
-	}
-	return 0;
-}
-
-static void wl3501_esbq_req_free(struct wl3501_card *this)
-{
-	u8 tmp;
-	u16 addr;
-
-	if (this->esbq_req_head == this->esbq_req_tail)
-		goto out;
-	wl3501_get_from_wla(this, this->esbq_req_tail + 3, &tmp, sizeof(tmp));
-	if (!(tmp & 0x80))
-		goto out;
-	wl3501_get_from_wla(this, this->esbq_req_tail, &addr, sizeof(addr));
-	wl3501_free_tx_buffer(this, addr);
-	this->esbq_req_tail += 4;
-	if (this->esbq_req_tail >= this->esbq_req_end)
-		this->esbq_req_tail = this->esbq_req_start;
-out:
-	return;
-}
-
-static int wl3501_esbq_confirm(struct wl3501_card *this)
-{
-	u8 tmp;
-
-	wl3501_get_from_wla(this, this->esbq_confirm + 3, &tmp, sizeof(tmp));
-	return tmp & 0x80;
-}
-
-static void wl3501_online(struct net_device *dev)
-{
-	struct wl3501_card *this = netdev_priv(dev);
-
-	printk(KERN_INFO "%s: Wireless LAN online. BSSID: %pM\n",
-	       dev->name, this->bssid);
-	netif_wake_queue(dev);
-}
-
-static void wl3501_esbq_confirm_done(struct wl3501_card *this)
-{
-	u8 tmp = 0;
-
-	wl3501_set_to_wla(this, this->esbq_confirm + 3, &tmp, sizeof(tmp));
-	this->esbq_confirm += 4;
-	if (this->esbq_confirm >= this->esbq_confirm_end)
-		this->esbq_confirm = this->esbq_confirm_start;
-}
-
-static int wl3501_mgmt_auth(struct wl3501_card *this)
-{
-	struct wl3501_auth_req sig = {
-		.sig_id	 = WL3501_SIG_AUTH_REQ,
-		.type	 = WL3501_SYS_TYPE_OPEN,
-		.timeout = 1000,
-	};
-
-	pr_debug("entry");
-	memcpy(sig.mac_addr, this->bssid, ETH_ALEN);
-	return wl3501_esbq_exec(this, &sig, sizeof(sig));
-}
-
-static int wl3501_mgmt_association(struct wl3501_card *this)
-{
-	struct wl3501_assoc_req sig = {
-		.sig_id		 = WL3501_SIG_ASSOC_REQ,
-		.timeout	 = 1000,
-		.listen_interval = 5,
-		.cap_info	 = this->cap_info,
-	};
-
-	pr_debug("entry");
-	memcpy(sig.mac_addr, this->bssid, ETH_ALEN);
-	return wl3501_esbq_exec(this, &sig, sizeof(sig));
-}
-
-static void wl3501_mgmt_join_confirm(struct net_device *dev, u16 addr)
-{
-	struct wl3501_card *this = netdev_priv(dev);
-	struct wl3501_join_confirm sig;
-
-	pr_debug("entry");
-	wl3501_get_from_wla(this, addr, &sig, sizeof(sig));
-	if (sig.status == WL3501_STATUS_SUCCESS) {
-		if (this->net_type == IW_MODE_INFRA) {
-			if (this->join_sta_bss < this->bss_cnt) {
-				const int i = this->join_sta_bss;
-				memcpy(this->bssid,
-				       this->bss_set[i].req.bssid, ETH_ALEN);
-				this->chan = this->bss_set[i].req.ds_pset.chan;
-				iw_copy_mgmt_info_element(&this->keep_essid.el,
-						     &this->bss_set[i].req.ssid.el);
-				wl3501_mgmt_auth(this);
-			}
-		} else {
-			const int i = this->join_sta_bss;
-
-			memcpy(&this->bssid, &this->bss_set[i].req.bssid, ETH_ALEN);
-			this->chan = this->bss_set[i].req.ds_pset.chan;
-			iw_copy_mgmt_info_element(&this->keep_essid.el,
-						  &this->bss_set[i].req.ssid.el);
-			wl3501_online(dev);
-		}
-	} else {
-		int i;
-		this->join_sta_bss++;
-		for (i = this->join_sta_bss; i < this->bss_cnt; i++)
-			if (!wl3501_mgmt_join(this, i))
-				break;
-		this->join_sta_bss = i;
-		if (this->join_sta_bss == this->bss_cnt) {
-			if (this->net_type == IW_MODE_INFRA)
-				wl3501_mgmt_scan(this, 100);
-			else {
-				this->adhoc_times++;
-				if (this->adhoc_times > WL3501_MAX_ADHOC_TRIES)
-					wl3501_mgmt_start(this);
-				else
-					wl3501_mgmt_scan(this, 100);
-			}
-		}
-	}
-}
-
-static inline void wl3501_alarm_interrupt(struct net_device *dev,
-					  struct wl3501_card *this)
-{
-	if (this->net_type == IW_MODE_INFRA) {
-		printk(KERN_INFO "Wireless LAN offline\n");
-		netif_stop_queue(dev);
-		wl3501_mgmt_resync(this);
-	}
-}
-
-static inline void wl3501_md_confirm_interrupt(struct net_device *dev,
-					       struct wl3501_card *this,
-					       u16 addr)
-{
-	struct wl3501_md_confirm sig;
-
-	pr_debug("entry");
-	wl3501_get_from_wla(this, addr, &sig, sizeof(sig));
-	wl3501_free_tx_buffer(this, sig.data);
-	if (netif_queue_stopped(dev))
-		netif_wake_queue(dev);
-}
-
-static inline void wl3501_md_ind_interrupt(struct net_device *dev,
-					   struct wl3501_card *this, u16 addr)
-{
-	struct wl3501_md_ind sig;
-	struct sk_buff *skb;
-	u8 rssi, addr4[ETH_ALEN];
-	u16 pkt_len;
-
-	wl3501_get_from_wla(this, addr, &sig, sizeof(sig));
-	this->start_seg = sig.data;
-	wl3501_get_from_wla(this,
-			    sig.data + offsetof(struct wl3501_rx_hdr, rssi),
-			    &rssi, sizeof(rssi));
-	this->rssi = rssi <= 63 ? (rssi * 100) / 64 : 255;
-
-	wl3501_get_from_wla(this,
-			    sig.data +
-				offsetof(struct wl3501_rx_hdr, addr4),
-			    &addr4, sizeof(addr4));
-	if (!(addr4[0] == 0xAA && addr4[1] == 0xAA &&
-	      addr4[2] == 0x03 && addr4[4] == 0x00)) {
-		printk(KERN_INFO "Unsupported packet type!\n");
-		return;
-	}
-	pkt_len = sig.size + 12 - 24 - 4 - 6;
-
-	skb = dev_alloc_skb(pkt_len + 5);
-
-	if (!skb) {
-		printk(KERN_WARNING "%s: Can't alloc a sk_buff of size %d.\n",
-		       dev->name, pkt_len);
-		dev->stats.rx_dropped++;
-	} else {
-		skb->dev = dev;
-		skb_reserve(skb, 2); /* IP headers on 16 bytes boundaries */
-		skb_copy_to_linear_data(skb, (unsigned char *)&sig.addr,
-					sizeof(sig.addr));
-		wl3501_receive(this, skb->data, pkt_len);
-		skb_put(skb, pkt_len);
-		skb->protocol	= eth_type_trans(skb, dev);
-		dev->stats.rx_packets++;
-		dev->stats.rx_bytes += skb->len;
-		netif_rx(skb);
-	}
-}
-
-static inline void wl3501_get_confirm_interrupt(struct wl3501_card *this,
-						u16 addr, void *sig, int size)
-{
-	pr_debug("entry");
-	wl3501_get_from_wla(this, addr, &this->sig_get_confirm,
-			    sizeof(this->sig_get_confirm));
-	wake_up(&this->wait);
-}
-
-static inline void wl3501_start_confirm_interrupt(struct net_device *dev,
-						  struct wl3501_card *this,
-						  u16 addr)
-{
-	struct wl3501_start_confirm sig;
-
-	pr_debug("entry");
-	wl3501_get_from_wla(this, addr, &sig, sizeof(sig));
-	if (sig.status == WL3501_STATUS_SUCCESS)
-		netif_wake_queue(dev);
-}
-
-static inline void wl3501_assoc_confirm_interrupt(struct net_device *dev,
-						  u16 addr)
-{
-	struct wl3501_card *this = netdev_priv(dev);
-	struct wl3501_assoc_confirm sig;
-
-	pr_debug("entry");
-	wl3501_get_from_wla(this, addr, &sig, sizeof(sig));
-
-	if (sig.status == WL3501_STATUS_SUCCESS)
-		wl3501_online(dev);
-}
-
-static inline void wl3501_auth_confirm_interrupt(struct wl3501_card *this,
-						 u16 addr)
-{
-	struct wl3501_auth_confirm sig;
-
-	pr_debug("entry");
-	wl3501_get_from_wla(this, addr, &sig, sizeof(sig));
-
-	if (sig.status == WL3501_STATUS_SUCCESS)
-		wl3501_mgmt_association(this);
-	else
-		wl3501_mgmt_resync(this);
-}
-
-static inline void wl3501_rx_interrupt(struct net_device *dev)
-{
-	int morepkts;
-	u16 addr;
-	u8 sig_id;
-	struct wl3501_card *this = netdev_priv(dev);
-
-	pr_debug("entry");
-loop:
-	morepkts = 0;
-	if (!wl3501_esbq_confirm(this))
-		goto free;
-	wl3501_get_from_wla(this, this->esbq_confirm, &addr, sizeof(addr));
-	wl3501_get_from_wla(this, addr + 2, &sig_id, sizeof(sig_id));
-
-	switch (sig_id) {
-	case WL3501_SIG_DEAUTH_IND:
-	case WL3501_SIG_DISASSOC_IND:
-	case WL3501_SIG_ALARM:
-		wl3501_alarm_interrupt(dev, this);
-		break;
-	case WL3501_SIG_MD_CONFIRM:
-		wl3501_md_confirm_interrupt(dev, this, addr);
-		break;
-	case WL3501_SIG_MD_IND:
-		wl3501_md_ind_interrupt(dev, this, addr);
-		break;
-	case WL3501_SIG_GET_CONFIRM:
-		wl3501_get_confirm_interrupt(this, addr,
-					     &this->sig_get_confirm,
-					     sizeof(this->sig_get_confirm));
-		break;
-	case WL3501_SIG_PWR_MGMT_CONFIRM:
-		wl3501_get_confirm_interrupt(this, addr,
-					     &this->sig_pwr_mgmt_confirm,
-					    sizeof(this->sig_pwr_mgmt_confirm));
-		break;
-	case WL3501_SIG_START_CONFIRM:
-		wl3501_start_confirm_interrupt(dev, this, addr);
-		break;
-	case WL3501_SIG_SCAN_CONFIRM:
-		wl3501_mgmt_scan_confirm(this, addr);
-		break;
-	case WL3501_SIG_JOIN_CONFIRM:
-		wl3501_mgmt_join_confirm(dev, addr);
-		break;
-	case WL3501_SIG_ASSOC_CONFIRM:
-		wl3501_assoc_confirm_interrupt(dev, addr);
-		break;
-	case WL3501_SIG_AUTH_CONFIRM:
-		wl3501_auth_confirm_interrupt(this, addr);
-		break;
-	case WL3501_SIG_RESYNC_CONFIRM:
-		wl3501_mgmt_resync(this); /* FIXME: should be resync_confirm */
-		break;
-	}
-	wl3501_esbq_confirm_done(this);
-	morepkts = 1;
-	/* free request if necessary */
-free:
-	wl3501_esbq_req_free(this);
-	if (morepkts)
-		goto loop;
-}
-
-static inline void wl3501_ack_interrupt(struct wl3501_card *this)
-{
-	wl3501_outb(WL3501_GCR_ECINT, this->base_addr + WL3501_NIC_GCR);
-}
-
-/**
- * wl3501_interrupt - Hardware interrupt from card.
- * @irq: Interrupt number
- * @dev_id: net_device
- *
- * We must acknowledge the interrupt as soon as possible, and block the
- * interrupt from the same card immediately to prevent re-entry.
- *
- * Before accessing the Control_Status_Block, we must lock SUTRO first.
- * On the other hand, to prevent SUTRO from malfunctioning, we must
- * unlock the SUTRO as soon as possible.
- */
-static irqreturn_t wl3501_interrupt(int irq, void *dev_id)
-{
-	struct net_device *dev = dev_id;
-	struct wl3501_card *this;
-
-	this = netdev_priv(dev);
-	spin_lock(&this->lock);
-	wl3501_ack_interrupt(this);
-	wl3501_block_interrupt(this);
-	wl3501_rx_interrupt(dev);
-	wl3501_unblock_interrupt(this);
-	spin_unlock(&this->lock);
-
-	return IRQ_HANDLED;
-}
-
-static int wl3501_reset_board(struct wl3501_card *this)
-{
-	u8 tmp = 0;
-	int i, rc = 0;
-
-	/* Coreset */
-	wl3501_outb_p(WL3501_GCR_CORESET, this->base_addr + WL3501_NIC_GCR);
-	wl3501_outb_p(0, this->base_addr + WL3501_NIC_GCR);
-	wl3501_outb_p(WL3501_GCR_CORESET, this->base_addr + WL3501_NIC_GCR);
-
-	/* Reset SRAM 0x480 to zero */
-	wl3501_set_to_wla(this, 0x480, &tmp, sizeof(tmp));
-
-	/* Start up */
-	wl3501_outb_p(0, this->base_addr + WL3501_NIC_GCR);
-
-	WL3501_NOPLOOP(1024 * 50);
-
-	wl3501_unblock_interrupt(this);	/* acme: was commented */
-
-	/* Polling Self_Test_Status */
-	for (i = 0; i < 10000; i++) {
-		wl3501_get_from_wla(this, 0x480, &tmp, sizeof(tmp));
-
-		if (tmp == 'W') {
-			/* firmware complete all test successfully */
-			tmp = 'A';
-			wl3501_set_to_wla(this, 0x480, &tmp, sizeof(tmp));
-			goto out;
-		}
-		WL3501_NOPLOOP(10);
-	}
-	printk(KERN_WARNING "%s: failed to reset the board!\n", __func__);
-	rc = -ENODEV;
-out:
-	return rc;
-}
-
-static int wl3501_init_firmware(struct wl3501_card *this)
-{
-	u16 ptr, next;
-	int rc = wl3501_reset_board(this);
-
-	if (rc)
-		goto fail;
-	this->card_name[0] = '\0';
-	wl3501_get_from_wla(this, 0x1a00,
-			    this->card_name, sizeof(this->card_name));
-	this->card_name[sizeof(this->card_name) - 1] = '\0';
-	this->firmware_date[0] = '\0';
-	wl3501_get_from_wla(this, 0x1a40,
-			    this->firmware_date, sizeof(this->firmware_date));
-	this->firmware_date[sizeof(this->firmware_date) - 1] = '\0';
-	/* Switch to SRAM Page 0 */
-	wl3501_switch_page(this, WL3501_BSS_SPAGE0);
-	/* Read parameter from card */
-	wl3501_get_from_wla(this, 0x482, &this->esbq_req_start, 2);
-	wl3501_get_from_wla(this, 0x486, &this->esbq_req_end, 2);
-	wl3501_get_from_wla(this, 0x488, &this->esbq_confirm_start, 2);
-	wl3501_get_from_wla(this, 0x48c, &this->esbq_confirm_end, 2);
-	wl3501_get_from_wla(this, 0x48e, &this->tx_buffer_head, 2);
-	wl3501_get_from_wla(this, 0x492, &this->tx_buffer_size, 2);
-	this->esbq_req_tail	= this->esbq_req_head = this->esbq_req_start;
-	this->esbq_req_end     += this->esbq_req_start;
-	this->esbq_confirm	= this->esbq_confirm_start;
-	this->esbq_confirm_end += this->esbq_confirm_start;
-	/* Initial Tx Buffer */
-	this->tx_buffer_cnt = 1;
-	ptr = this->tx_buffer_head;
-	next = ptr + WL3501_BLKSZ;
-	while ((next - this->tx_buffer_head) < this->tx_buffer_size) {
-		this->tx_buffer_cnt++;
-		wl3501_set_to_wla(this, ptr, &next, sizeof(next));
-		ptr = next;
-		next = ptr + WL3501_BLKSZ;
-	}
-	rc = 0;
-	next = 0;
-	wl3501_set_to_wla(this, ptr, &next, sizeof(next));
-	this->tx_buffer_tail = ptr;
-out:
-	return rc;
-fail:
-	printk(KERN_WARNING "%s: failed!\n", __func__);
-	goto out;
-}
-
-static int wl3501_close(struct net_device *dev)
-{
-	struct wl3501_card *this = netdev_priv(dev);
-	unsigned long flags;
-	struct pcmcia_device *link;
-	link = this->p_dev;
-
-	spin_lock_irqsave(&this->lock, flags);
-	link->open--;
-
-	/* Stop wl3501_hard_start_xmit() from now on */
-	netif_stop_queue(dev);
-	wl3501_ack_interrupt(this);
-
-	/* Mask interrupts from the SUTRO */
-	wl3501_block_interrupt(this);
-
-	printk(KERN_INFO "%s: WL3501 closed\n", dev->name);
-	spin_unlock_irqrestore(&this->lock, flags);
-	return 0;
-}
-
-/**
- * wl3501_reset - Reset the SUTRO.
- * @dev: network device
- *
- * It is almost the same as wl3501_open(). In fact, we may just wl3501_close()
- * and wl3501_open() again, but I wouldn't like to free_irq() when the driver
- * is running. It seems to be dangerous.
- */
-static int wl3501_reset(struct net_device *dev)
-{
-	struct wl3501_card *this = netdev_priv(dev);
-	int rc = -ENODEV;
-	unsigned long flags;
-
-	spin_lock_irqsave(&this->lock, flags);
-	wl3501_block_interrupt(this);
-
-	if (wl3501_init_firmware(this)) {
-		printk(KERN_WARNING "%s: Can't initialize Firmware!\n",
-		       dev->name);
-		/* Free IRQ, and mark IRQ as unused */
-		free_irq(dev->irq, dev);
-		goto out;
-	}
-
-	/*
-	 * Queue has to be started only when the Card is Started
-	 */
-	netif_stop_queue(dev);
-	this->adhoc_times = 0;
-	wl3501_ack_interrupt(this);
-	wl3501_unblock_interrupt(this);
-	wl3501_mgmt_scan(this, 100);
-	pr_debug("%s: device reset", dev->name);
-	rc = 0;
-out:
-	spin_unlock_irqrestore(&this->lock, flags);
-	return rc;
-}
-
-static void wl3501_tx_timeout(struct net_device *dev, unsigned int txqueue)
-{
-	struct net_device_stats *stats = &dev->stats;
-	int rc;
-
-	stats->tx_errors++;
-	rc = wl3501_reset(dev);
-	if (rc)
-		printk(KERN_ERR "%s: Error %d resetting card on Tx timeout!\n",
-		       dev->name, rc);
-	else {
-		netif_trans_update(dev); /* prevent tx timeout */
-		netif_wake_queue(dev);
-	}
-}
-
-/*
- * Return : 0 - OK
- *	    1 - Could not transmit (dev_queue_xmit will queue it)
- *		and try to sent it later
- */
-static netdev_tx_t wl3501_hard_start_xmit(struct sk_buff *skb,
-						struct net_device *dev)
-{
-	int enabled, rc;
-	struct wl3501_card *this = netdev_priv(dev);
-	unsigned long flags;
-
-	spin_lock_irqsave(&this->lock, flags);
-	enabled = wl3501_block_interrupt(this);
-	rc = wl3501_send_pkt(this, skb->data, skb->len);
-	if (enabled)
-		wl3501_unblock_interrupt(this);
-	if (rc) {
-		++dev->stats.tx_dropped;
-		netif_stop_queue(dev);
-	} else {
-		++dev->stats.tx_packets;
-		dev->stats.tx_bytes += skb->len;
-		dev_kfree_skb_irq(skb);
-
-		if (this->tx_buffer_cnt < 2)
-			netif_stop_queue(dev);
-	}
-	spin_unlock_irqrestore(&this->lock, flags);
-	return NETDEV_TX_OK;
-}
-
-static int wl3501_open(struct net_device *dev)
-{
-	int rc = -ENODEV;
-	struct wl3501_card *this = netdev_priv(dev);
-	unsigned long flags;
-	struct pcmcia_device *link;
-	link = this->p_dev;
-
-	spin_lock_irqsave(&this->lock, flags);
-	if (!pcmcia_dev_present(link))
-		goto out;
-	netif_device_attach(dev);
-	link->open++;
-
-	/* Initial WL3501 firmware */
-	pr_debug("%s: Initialize WL3501 firmware...", dev->name);
-	if (wl3501_init_firmware(this))
-		goto fail;
-	/* Initial device variables */
-	this->adhoc_times = 0;
-	/* Acknowledge Interrupt, for cleaning last state */
-	wl3501_ack_interrupt(this);
-
-	/* Enable interrupt from card after all */
-	wl3501_unblock_interrupt(this);
-	wl3501_mgmt_scan(this, 100);
-	rc = 0;
-	pr_debug("%s: WL3501 opened", dev->name);
-	printk(KERN_INFO "%s: Card Name: %s\n"
-			 "%s: Firmware Date: %s\n",
-			 dev->name, this->card_name,
-			 dev->name, this->firmware_date);
-out:
-	spin_unlock_irqrestore(&this->lock, flags);
-	return rc;
-fail:
-	printk(KERN_WARNING "%s: Can't initialize firmware!\n", dev->name);
-	goto out;
-}
-
-static struct iw_statistics *wl3501_get_wireless_stats(struct net_device *dev)
-{
-	struct wl3501_card *this = netdev_priv(dev);
-	struct iw_statistics *wstats = &this->wstats;
-	u32 value; /* size checked: it is u32 */
-
-	memset(wstats, 0, sizeof(*wstats));
-	wstats->status = netif_running(dev);
-	if (!wl3501_get_mib_value(this, WL3501_MIB_ATTR_WEP_ICV_ERROR_COUNT,
-				  &value, sizeof(value)))
-		wstats->discard.code += value;
-	if (!wl3501_get_mib_value(this, WL3501_MIB_ATTR_WEP_UNDECRYPTABLE_COUNT,
-				  &value, sizeof(value)))
-		wstats->discard.code += value;
-	if (!wl3501_get_mib_value(this, WL3501_MIB_ATTR_WEP_EXCLUDED_COUNT,
-				  &value, sizeof(value)))
-		wstats->discard.code += value;
-	if (!wl3501_get_mib_value(this, WL3501_MIB_ATTR_RETRY_COUNT,
-				  &value, sizeof(value)))
-		wstats->discard.retries	= value;
-	if (!wl3501_get_mib_value(this, WL3501_MIB_ATTR_FAILED_COUNT,
-				  &value, sizeof(value)))
-		wstats->discard.misc += value;
-	if (!wl3501_get_mib_value(this, WL3501_MIB_ATTR_RTS_FAILURE_COUNT,
-				  &value, sizeof(value)))
-		wstats->discard.misc += value;
-	if (!wl3501_get_mib_value(this, WL3501_MIB_ATTR_ACK_FAILURE_COUNT,
-				  &value, sizeof(value)))
-		wstats->discard.misc += value;
-	if (!wl3501_get_mib_value(this, WL3501_MIB_ATTR_FRAME_DUPLICATE_COUNT,
-				  &value, sizeof(value)))
-		wstats->discard.misc += value;
-	return wstats;
-}
-
-/**
- * wl3501_detach - deletes a driver "instance"
- * @link: FILL_IN
- *
- * This deletes a driver "instance". The device is de-registered with Card
- * Services. If it has been released, all local data structures are freed.
- * Otherwise, the structures will be freed when the device is released.
- */
-static void wl3501_detach(struct pcmcia_device *link)
-{
-	struct net_device *dev = link->priv;
-
-	/* If the device is currently configured and active, we won't actually
-	 * delete it yet.  Instead, it is marked so that when the release()
-	 * function is called, that will trigger a proper detach(). */
-
-	while (link->open > 0)
-		wl3501_close(dev);
-
-	netif_device_detach(dev);
-	wl3501_release(link);
-
-	unregister_netdev(dev);
-	free_netdev(dev);
-}
-
-static int wl3501_get_name(struct net_device *dev, struct iw_request_info *info,
-			   union iwreq_data *wrqu, char *extra)
-{
-	strscpy(wrqu->name, "IEEE 802.11-DS", sizeof(wrqu->name));
-	return 0;
-}
-
-static int wl3501_set_freq(struct net_device *dev, struct iw_request_info *info,
-			   union iwreq_data *wrqu, char *extra)
-{
-	struct wl3501_card *this = netdev_priv(dev);
-	int channel = wrqu->freq.m;
-	int rc = -EINVAL;
-
-	if (iw_valid_channel(this->reg_domain, channel)) {
-		this->chan = channel;
-		rc = wl3501_reset(dev);
-	}
-	return rc;
-}
-
-static int wl3501_get_freq(struct net_device *dev, struct iw_request_info *info,
-			   union iwreq_data *wrqu, char *extra)
-{
-	struct wl3501_card *this = netdev_priv(dev);
-
-	wrqu->freq.m = 100000 *
-		ieee80211_channel_to_frequency(this->chan, NL80211_BAND_2GHZ);
-	wrqu->freq.e = 1;
-	return 0;
-}
-
-static int wl3501_set_mode(struct net_device *dev, struct iw_request_info *info,
-			   union iwreq_data *wrqu, char *extra)
-{
-	int rc = -EINVAL;
-
-	if (wrqu->mode == IW_MODE_INFRA ||
-	    wrqu->mode == IW_MODE_ADHOC ||
-	    wrqu->mode == IW_MODE_AUTO) {
-		struct wl3501_card *this = netdev_priv(dev);
-
-		this->net_type = wrqu->mode;
-		rc = wl3501_reset(dev);
-	}
-	return rc;
-}
-
-static int wl3501_get_mode(struct net_device *dev, struct iw_request_info *info,
-			   union iwreq_data *wrqu, char *extra)
-{
-	struct wl3501_card *this = netdev_priv(dev);
-
-	wrqu->mode = this->net_type;
-	return 0;
-}
-
-static int wl3501_get_sens(struct net_device *dev, struct iw_request_info *info,
-			   union iwreq_data *wrqu, char *extra)
-{
-	struct wl3501_card *this = netdev_priv(dev);
-
-	wrqu->sens.value = this->rssi;
-	wrqu->sens.disabled = !wrqu->sens.value;
-	wrqu->sens.fixed = 1;
-	return 0;
-}
-
-static int wl3501_get_range(struct net_device *dev,
-			    struct iw_request_info *info,
-			    union iwreq_data *wrqu, char *extra)
-{
-	struct iw_range *range = (struct iw_range *)extra;
-
-	/* Set the length (very important for backward compatibility) */
-	wrqu->data.length = sizeof(*range);
-
-	/* Set all the info we don't care or don't know about to zero */
-	memset(range, 0, sizeof(*range));
-
-	/* Set the Wireless Extension versions */
-	range->we_version_compiled	= WIRELESS_EXT;
-	range->we_version_source	= 1;
-	range->throughput		= 2 * 1000 * 1000;     /* ~2 Mb/s */
-	/* FIXME: study the code to fill in more fields... */
-	return 0;
-}
-
-static int wl3501_set_wap(struct net_device *dev, struct iw_request_info *info,
-			  union iwreq_data *wrqu, char *extra)
-{
-	struct wl3501_card *this = netdev_priv(dev);
-	int rc = -EINVAL;
-
-	/* FIXME: we support other ARPHRDs...*/
-	if (wrqu->ap_addr.sa_family != ARPHRD_ETHER)
-		goto out;
-	if (is_broadcast_ether_addr(wrqu->ap_addr.sa_data)) {
-		/* FIXME: rescan? */
-	} else
-		memcpy(this->bssid, wrqu->ap_addr.sa_data, ETH_ALEN);
-		/* FIXME: rescan? deassoc & scan? */
-	rc = 0;
-out:
-	return rc;
-}
-
-static int wl3501_get_wap(struct net_device *dev, struct iw_request_info *info,
-			  union iwreq_data *wrqu, char *extra)
-{
-	struct wl3501_card *this = netdev_priv(dev);
-
-	wrqu->ap_addr.sa_family = ARPHRD_ETHER;
-	memcpy(wrqu->ap_addr.sa_data, this->bssid, ETH_ALEN);
-	return 0;
-}
-
-static int wl3501_set_scan(struct net_device *dev, struct iw_request_info *info,
-			   union iwreq_data *wrqu, char *extra)
-{
-	/*
-	 * FIXME: trigger scanning with a reset, yes, I'm lazy
-	 */
-	return wl3501_reset(dev);
-}
-
-static int wl3501_get_scan(struct net_device *dev, struct iw_request_info *info,
-			   union iwreq_data *wrqu, char *extra)
-{
-	struct wl3501_card *this = netdev_priv(dev);
-	int i;
-	char *current_ev = extra;
-	struct iw_event iwe;
-
-	for (i = 0; i < this->bss_cnt; ++i) {
-		iwe.cmd			= SIOCGIWAP;
-		iwe.u.ap_addr.sa_family = ARPHRD_ETHER;
-		memcpy(iwe.u.ap_addr.sa_data, this->bss_set[i].req.bssid, ETH_ALEN);
-		current_ev = iwe_stream_add_event(info, current_ev,
-						  extra + IW_SCAN_MAX_DATA,
-						  &iwe, IW_EV_ADDR_LEN);
-		iwe.cmd		  = SIOCGIWESSID;
-		iwe.u.data.flags  = 1;
-		iwe.u.data.length = this->bss_set[i].req.ssid.el.len;
-		current_ev = iwe_stream_add_point(info, current_ev,
-						  extra + IW_SCAN_MAX_DATA,
-						  &iwe,
-						  this->bss_set[i].req.ssid.essid);
-		iwe.cmd	   = SIOCGIWMODE;
-		iwe.u.mode = this->bss_set[i].req.bss_type;
-		current_ev = iwe_stream_add_event(info, current_ev,
-						  extra + IW_SCAN_MAX_DATA,
-						  &iwe, IW_EV_UINT_LEN);
-		iwe.cmd = SIOCGIWFREQ;
-		iwe.u.freq.m = this->bss_set[i].req.ds_pset.chan;
-		iwe.u.freq.e = 0;
-		current_ev = iwe_stream_add_event(info, current_ev,
-						  extra + IW_SCAN_MAX_DATA,
-						  &iwe, IW_EV_FREQ_LEN);
-		iwe.cmd = SIOCGIWENCODE;
-		if (this->bss_set[i].req.cap_info & WL3501_MGMT_CAPABILITY_PRIVACY)
-			iwe.u.data.flags = IW_ENCODE_ENABLED | IW_ENCODE_NOKEY;
-		else
-			iwe.u.data.flags = IW_ENCODE_DISABLED;
-		iwe.u.data.length = 0;
-		current_ev = iwe_stream_add_point(info, current_ev,
-						  extra + IW_SCAN_MAX_DATA,
-						  &iwe, NULL);
-	}
-	/* Length of data */
-	wrqu->data.length = (current_ev - extra);
-	wrqu->data.flags = 0; /* FIXME: set properly these flags */
-	return 0;
-}
-
-static int wl3501_set_essid(struct net_device *dev,
-			    struct iw_request_info *info,
-			    union iwreq_data *wrqu, char *extra)
-{
-	struct wl3501_card *this = netdev_priv(dev);
-
-	if (wrqu->data.flags) {
-		iw_set_mgmt_info_element(IW_MGMT_INFO_ELEMENT_SSID,
-					 &this->essid.el,
-					 extra, wrqu->data.length);
-	} else { /* We accept any ESSID */
-		iw_set_mgmt_info_element(IW_MGMT_INFO_ELEMENT_SSID,
-					 &this->essid.el, "ANY", 3);
-	}
-	return wl3501_reset(dev);
-}
-
-static int wl3501_get_essid(struct net_device *dev,
-			    struct iw_request_info *info,
-			    union iwreq_data *wrqu, char *extra)
-{
-	struct wl3501_card *this = netdev_priv(dev);
-	unsigned long flags;
-
-	spin_lock_irqsave(&this->lock, flags);
-	wrqu->essid.flags  = 1;
-	wrqu->essid.length = this->essid.el.len;
-	memcpy(extra, this->essid.essid, this->essid.el.len);
-	spin_unlock_irqrestore(&this->lock, flags);
-	return 0;
-}
-
-static int wl3501_set_nick(struct net_device *dev, struct iw_request_info *info,
-			   union iwreq_data *wrqu, char *extra)
-{
-	struct wl3501_card *this = netdev_priv(dev);
-
-	if (wrqu->data.length > sizeof(this->nick))
-		return -E2BIG;
-	strscpy(this->nick, extra, wrqu->data.length);
-	return 0;
-}
-
-static int wl3501_get_nick(struct net_device *dev, struct iw_request_info *info,
-			   union iwreq_data *wrqu, char *extra)
-{
-	struct wl3501_card *this = netdev_priv(dev);
-
-	strscpy(extra, this->nick, 32);
-	wrqu->data.length = strlen(extra);
-	return 0;
-}
-
-static int wl3501_get_rate(struct net_device *dev, struct iw_request_info *info,
-			   union iwreq_data *wrqu, char *extra)
-{
-	/*
-	 * FIXME: have to see from where to get this info, perhaps this card
-	 * works at 1 Mbit/s too... for now leave at 2 Mbit/s that is the most
-	 * common with the Planet Access Points. -acme
-	 */
-	wrqu->bitrate.value = 2000000;
-	wrqu->bitrate.fixed = 1;
-	return 0;
-}
-
-static int wl3501_get_rts_threshold(struct net_device *dev,
-				    struct iw_request_info *info,
-				    union iwreq_data *wrqu, char *extra)
-{
-	u16 threshold; /* size checked: it is u16 */
-	struct wl3501_card *this = netdev_priv(dev);
-	int rc = wl3501_get_mib_value(this, WL3501_MIB_ATTR_RTS_THRESHOLD,
-				      &threshold, sizeof(threshold));
-	if (!rc) {
-		wrqu->rts.value = threshold;
-		wrqu->rts.disabled = threshold >= 2347;
-		wrqu->rts.fixed = 1;
-	}
-	return rc;
-}
-
-static int wl3501_get_frag_threshold(struct net_device *dev,
-				     struct iw_request_info *info,
-				     union iwreq_data *wrqu, char *extra)
-{
-	u16 threshold; /* size checked: it is u16 */
-	struct wl3501_card *this = netdev_priv(dev);
-	int rc = wl3501_get_mib_value(this, WL3501_MIB_ATTR_FRAG_THRESHOLD,
-				      &threshold, sizeof(threshold));
-	if (!rc) {
-		wrqu->frag.value = threshold;
-		wrqu->frag.disabled = threshold >= 2346;
-		wrqu->frag.fixed = 1;
-	}
-	return rc;
-}
-
-static int wl3501_get_txpow(struct net_device *dev,
-			    struct iw_request_info *info,
-			    union iwreq_data *wrqu, char *extra)
-{
-	u16 txpow;
-	struct wl3501_card *this = netdev_priv(dev);
-	int rc = wl3501_get_mib_value(this,
-				      WL3501_MIB_ATTR_CURRENT_TX_PWR_LEVEL,
-				      &txpow, sizeof(txpow));
-	if (!rc) {
-		wrqu->txpower.value = txpow;
-		wrqu->txpower.disabled = 0;
-		/*
-		 * From the MIB values I think this can be configurable,
-		 * as it lists several tx power levels -acme
-		 */
-		wrqu->txpower.fixed = 0;
-		wrqu->txpower.flags = IW_TXPOW_MWATT;
-	}
-	return rc;
-}
-
-static int wl3501_get_retry(struct net_device *dev,
-			    struct iw_request_info *info,
-			    union iwreq_data *wrqu, char *extra)
-{
-	u8 retry; /* size checked: it is u8 */
-	struct wl3501_card *this = netdev_priv(dev);
-	int rc = wl3501_get_mib_value(this,
-				      WL3501_MIB_ATTR_LONG_RETRY_LIMIT,
-				      &retry, sizeof(retry));
-	if (rc)
-		goto out;
-	if (wrqu->retry.flags & IW_RETRY_LONG) {
-		wrqu->retry.flags = IW_RETRY_LIMIT | IW_RETRY_LONG;
-		goto set_value;
-	}
-	rc = wl3501_get_mib_value(this, WL3501_MIB_ATTR_SHORT_RETRY_LIMIT,
-				  &retry, sizeof(retry));
-	if (rc)
-		goto out;
-	wrqu->retry.flags = IW_RETRY_LIMIT | IW_RETRY_SHORT;
-set_value:
-	wrqu->retry.value = retry;
-	wrqu->retry.disabled = 0;
-out:
-	return rc;
-}
-
-static int wl3501_get_encode(struct net_device *dev,
-			     struct iw_request_info *info,
-			     union iwreq_data *wrqu, char *extra)
-{
-	u8 implemented, restricted, keys[100], len_keys, tocopy;
-	struct wl3501_card *this = netdev_priv(dev);
-	int rc = wl3501_get_mib_value(this,
-				      WL3501_MIB_ATTR_PRIV_OPT_IMPLEMENTED,
-				      &implemented, sizeof(implemented));
-	if (rc)
-		goto out;
-	if (!implemented) {
-		wrqu->encoding.flags = IW_ENCODE_DISABLED;
-		goto out;
-	}
-	rc = wl3501_get_mib_value(this, WL3501_MIB_ATTR_EXCLUDE_UNENCRYPTED,
-				  &restricted, sizeof(restricted));
-	if (rc)
-		goto out;
-	wrqu->encoding.flags = restricted ? IW_ENCODE_RESTRICTED :
-					    IW_ENCODE_OPEN;
-	rc = wl3501_get_mib_value(this, WL3501_MIB_ATTR_WEP_KEY_MAPPINGS_LEN,
-				  &len_keys, sizeof(len_keys));
-	if (rc)
-		goto out;
-	rc = wl3501_get_mib_value(this, WL3501_MIB_ATTR_WEP_KEY_MAPPINGS,
-				  keys, len_keys);
-	if (rc)
-		goto out;
-	tocopy = min_t(u16, len_keys, wrqu->encoding.length);
-	tocopy = min_t(u8, tocopy, 100);
-	wrqu->encoding.length = tocopy;
-	memcpy(extra, keys, tocopy);
-out:
-	return rc;
-}
-
-static int wl3501_get_power(struct net_device *dev,
-			    struct iw_request_info *info,
-			    union iwreq_data *wrqu, char *extra)
-{
-	u8 pwr_state;
-	struct wl3501_card *this = netdev_priv(dev);
-	int rc = wl3501_get_mib_value(this,
-				      WL3501_MIB_ATTR_CURRENT_PWR_STATE,
-				      &pwr_state, sizeof(pwr_state));
-	if (rc)
-		goto out;
-	wrqu->power.disabled = !pwr_state;
-	wrqu->power.flags = IW_POWER_ON;
-out:
-	return rc;
-}
-
-static const iw_handler	wl3501_handler[] = {
-	IW_HANDLER(SIOCGIWNAME, wl3501_get_name),
-	IW_HANDLER(SIOCSIWFREQ, wl3501_set_freq),
-	IW_HANDLER(SIOCGIWFREQ, wl3501_get_freq),
-	IW_HANDLER(SIOCSIWMODE, wl3501_set_mode),
-	IW_HANDLER(SIOCGIWMODE, wl3501_get_mode),
-	IW_HANDLER(SIOCGIWSENS, wl3501_get_sens),
-	IW_HANDLER(SIOCGIWRANGE, wl3501_get_range),
-	IW_HANDLER(SIOCSIWSPY, iw_handler_set_spy),
-	IW_HANDLER(SIOCGIWSPY, iw_handler_get_spy),
-	IW_HANDLER(SIOCSIWTHRSPY, iw_handler_set_thrspy),
-	IW_HANDLER(SIOCGIWTHRSPY, iw_handler_get_thrspy),
-	IW_HANDLER(SIOCSIWAP, wl3501_set_wap),
-	IW_HANDLER(SIOCGIWAP, wl3501_get_wap),
-	IW_HANDLER(SIOCSIWSCAN, wl3501_set_scan),
-	IW_HANDLER(SIOCGIWSCAN, wl3501_get_scan),
-	IW_HANDLER(SIOCSIWESSID, wl3501_set_essid),
-	IW_HANDLER(SIOCGIWESSID, wl3501_get_essid),
-	IW_HANDLER(SIOCSIWNICKN, wl3501_set_nick),
-	IW_HANDLER(SIOCGIWNICKN, wl3501_get_nick),
-	IW_HANDLER(SIOCGIWRATE, wl3501_get_rate),
-	IW_HANDLER(SIOCGIWRTS, wl3501_get_rts_threshold),
-	IW_HANDLER(SIOCGIWFRAG, wl3501_get_frag_threshold),
-	IW_HANDLER(SIOCGIWTXPOW, wl3501_get_txpow),
-	IW_HANDLER(SIOCGIWRETRY, wl3501_get_retry),
-	IW_HANDLER(SIOCGIWENCODE, wl3501_get_encode),
-	IW_HANDLER(SIOCGIWPOWER, wl3501_get_power),
-};
-
-static const struct iw_handler_def wl3501_handler_def = {
-	.num_standard	= ARRAY_SIZE(wl3501_handler),
-	.standard	= (iw_handler *)wl3501_handler,
-	.get_wireless_stats = wl3501_get_wireless_stats,
-};
-
-static const struct net_device_ops wl3501_netdev_ops = {
-	.ndo_open		= wl3501_open,
-	.ndo_stop		= wl3501_close,
-	.ndo_start_xmit		= wl3501_hard_start_xmit,
-	.ndo_tx_timeout		= wl3501_tx_timeout,
-	.ndo_set_mac_address 	= eth_mac_addr,
-	.ndo_validate_addr	= eth_validate_addr,
-};
-
-static int wl3501_probe(struct pcmcia_device *p_dev)
-{
-	struct net_device *dev;
-	struct wl3501_card *this;
-	int ret;
-
-	/* The io structure describes IO port mapping */
-	p_dev->resource[0]->end	= 16;
-	p_dev->resource[0]->flags	= IO_DATA_PATH_WIDTH_8;
-
-	/* General socket configuration */
-	p_dev->config_flags	= CONF_ENABLE_IRQ;
-	p_dev->config_index	= 1;
-
-	dev = alloc_etherdev(sizeof(struct wl3501_card));
-	if (!dev)
-		return -ENOMEM;
-
-	dev->netdev_ops		= &wl3501_netdev_ops;
-	dev->watchdog_timeo	= 5 * HZ;
-
-	this = netdev_priv(dev);
-	this->wireless_data.spy_data = &this->spy_data;
-	this->p_dev = p_dev;
-	dev->wireless_data	= &this->wireless_data;
-	dev->wireless_handlers	= &wl3501_handler_def;
-	netif_stop_queue(dev);
-	p_dev->priv = dev;
-
-	ret = wl3501_config(p_dev);
-	if (ret)
-		goto out_free_etherdev;
-
-	return 0;
-
-out_free_etherdev:
-	free_netdev(dev);
-	return ret;
-}
-
-static int wl3501_config(struct pcmcia_device *link)
-{
-	struct net_device *dev = link->priv;
-	int i = 0, j, ret;
-	struct wl3501_card *this;
-
-	/* Try allocating IO ports.  This tries a few fixed addresses.  If you
-	 * want, you can also read the card's config table to pick addresses --
-	 * see the serial driver for an example. */
-	link->io_lines = 5;
-
-	for (j = 0x280; j < 0x400; j += 0x20) {
-		/* The '^0x300' is so that we probe 0x300-0x3ff first, then
-		 * 0x200-0x2ff, and so on, because this seems safer */
-		link->resource[0]->start = j;
-		link->resource[1]->start = link->resource[0]->start + 0x10;
-		i = pcmcia_request_io(link);
-		if (i == 0)
-			break;
-	}
-	if (i != 0)
-		goto failed;
-
-	/* Now allocate an interrupt line. Note that this does not actually
-	 * assign a handler to the interrupt. */
-
-	ret = pcmcia_request_irq(link, wl3501_interrupt);
-	if (ret)
-		goto failed;
-
-	ret = pcmcia_enable_device(link);
-	if (ret)
-		goto failed;
-
-	dev->irq = link->irq;
-	dev->base_addr = link->resource[0]->start;
-	SET_NETDEV_DEV(dev, &link->dev);
-	if (register_netdev(dev)) {
-		printk(KERN_NOTICE "wl3501_cs: register_netdev() failed\n");
-		goto failed;
-	}
-
-	this = netdev_priv(dev);
-
-	this->base_addr = dev->base_addr;
-
-	if (!wl3501_get_flash_mac_addr(this)) {
-		printk(KERN_WARNING "%s: Can't read MAC addr in flash ROM?\n",
-		       dev->name);
-		unregister_netdev(dev);
-		goto failed;
-	}
-
-	eth_hw_addr_set(dev, this->mac_addr);
-
-	/* print probe information */
-	printk(KERN_INFO "%s: wl3501 @ 0x%3.3x, IRQ %d, "
-	       "MAC addr in flash ROM:%pM\n",
-	       dev->name, this->base_addr, (int)dev->irq,
-	       dev->dev_addr);
-	/*
-	 * Initialize card parameters - added by jss
-	 */
-	this->net_type		= IW_MODE_INFRA;
-	this->bss_cnt		= 0;
-	this->join_sta_bss	= 0;
-	this->adhoc_times	= 0;
-	iw_set_mgmt_info_element(IW_MGMT_INFO_ELEMENT_SSID, &this->essid.el,
-				 "ANY", 3);
-	this->card_name[0]	= '\0';
-	this->firmware_date[0]	= '\0';
-	this->rssi		= 255;
-	this->chan		= iw_default_channel(this->reg_domain);
-	strscpy(this->nick, "Planet WL3501", sizeof(this->nick));
-	spin_lock_init(&this->lock);
-	init_waitqueue_head(&this->wait);
-	netif_start_queue(dev);
-	return 0;
-
-failed:
-	wl3501_release(link);
-	return -ENODEV;
-}
-
-static void wl3501_release(struct pcmcia_device *link)
-{
-	pcmcia_disable_device(link);
-}
-
-static int wl3501_suspend(struct pcmcia_device *link)
-{
-	struct net_device *dev = link->priv;
-
-	wl3501_pwr_mgmt(netdev_priv(dev), WL3501_SUSPEND);
-	if (link->open)
-		netif_device_detach(dev);
-
-	return 0;
-}
-
-static int wl3501_resume(struct pcmcia_device *link)
-{
-	struct net_device *dev = link->priv;
-
-	wl3501_pwr_mgmt(netdev_priv(dev), WL3501_RESUME);
-	if (link->open) {
-		wl3501_reset(dev);
-		netif_device_attach(dev);
-	}
-
-	return 0;
-}
-
-
-static const struct pcmcia_device_id wl3501_ids[] = {
-	PCMCIA_DEVICE_MANF_CARD(0xd601, 0x0001),
-	PCMCIA_DEVICE_NULL
-};
-MODULE_DEVICE_TABLE(pcmcia, wl3501_ids);
-
-static struct pcmcia_driver wl3501_driver = {
-	.owner		= THIS_MODULE,
-	.name		= "wl3501_cs",
-	.probe		= wl3501_probe,
-	.remove		= wl3501_detach,
-	.id_table	= wl3501_ids,
-	.suspend	= wl3501_suspend,
-	.resume		= wl3501_resume,
-};
-module_pcmcia_driver(wl3501_driver);
-
-MODULE_AUTHOR("Fox Chen <mhchen@golf.ccl.itri.org.tw>, "
-	      "Arnaldo Carvalho de Melo <acme@conectiva.com.br>,"
-	      "Gustavo Niemeyer <niemeyer@conectiva.com>");
-MODULE_DESCRIPTION("Planet wl3501 wireless driver");
-MODULE_LICENSE("GPL");
diff --git a/drivers/net/wireless/marvell/libertas/Kconfig b/drivers/net/wireless/marvell/libertas/Kconfig
index 6d62ab49aa8d..36b234bc5be8 100644
--- a/drivers/net/wireless/marvell/libertas/Kconfig
+++ b/drivers/net/wireless/marvell/libertas/Kconfig
@@ -1,9 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config LIBERTAS
 	tristate "Marvell 8xxx Libertas WLAN driver support"
+	depends on USB || MMC || SPI
 	depends on CFG80211
-	select WIRELESS_EXT
-	select WEXT_SPY
 	select LIB80211
 	select FW_LOADER
 	help
@@ -15,12 +14,6 @@ config LIBERTAS_USB
 	help
 	  A driver for Marvell Libertas 8388 USB devices.
 
-config LIBERTAS_CS
-	tristate "Marvell Libertas 8385 CompactFlash 802.11b/g cards"
-	depends on LIBERTAS && PCMCIA && HAS_IOPORT_MAP
-	help
-	  A driver for Marvell Libertas 8385 CompactFlash devices.
-
 config LIBERTAS_SDIO
 	tristate "Marvell Libertas 8385/8686/8688 SDIO 802.11b/g cards"
 	depends on LIBERTAS && MMC
diff --git a/drivers/net/wireless/marvell/libertas/Makefile b/drivers/net/wireless/marvell/libertas/Makefile
index 41b9b440a542..2ac04f4d61a5 100644
--- a/drivers/net/wireless/marvell/libertas/Makefile
+++ b/drivers/net/wireless/marvell/libertas/Makefile
@@ -17,6 +17,5 @@ libertas_spi-objs += if_spi.o
 
 obj-$(CONFIG_LIBERTAS)     += libertas.o
 obj-$(CONFIG_LIBERTAS_USB) += usb8xxx.o
-obj-$(CONFIG_LIBERTAS_CS)  += libertas_cs.o
 obj-$(CONFIG_LIBERTAS_SDIO) += libertas_sdio.o
 obj-$(CONFIG_LIBERTAS_SPI) += libertas_spi.o
diff --git a/drivers/net/wireless/marvell/libertas/if_cs.c b/drivers/net/wireless/marvell/libertas/if_cs.c
deleted file mode 100644
index 4103f15bca6b..000000000000
--- a/drivers/net/wireless/marvell/libertas/if_cs.c
+++ /dev/null
@@ -1,957 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
-
-  Driver for the Marvell 8385 based compact flash WLAN cards.
-
-  (C) 2007 by Holger Schurig <hs4233@mail.mn-solutions.de>
-
-
-*/
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/delay.h>
-#include <linux/moduleparam.h>
-#include <linux/firmware.h>
-#include <linux/netdevice.h>
-
-#include <pcmcia/cistpl.h>
-#include <pcmcia/ds.h>
-
-#include <linux/io.h>
-
-#define DRV_NAME "libertas_cs"
-
-#include "decl.h"
-#include "defs.h"
-#include "dev.h"
-
-
-/********************************************************************/
-/* Module stuff                                                     */
-/********************************************************************/
-
-MODULE_AUTHOR("Holger Schurig <hs4233@mail.mn-solutions.de>");
-MODULE_DESCRIPTION("Driver for Marvell 83xx compact flash WLAN cards");
-MODULE_LICENSE("GPL");
-
-
-
-/********************************************************************/
-/* Data structures                                                  */
-/********************************************************************/
-
-struct if_cs_card {
-	struct pcmcia_device *p_dev;
-	struct lbs_private *priv;
-	void __iomem *iobase;
-	bool align_regs;
-	u32 model;
-};
-
-
-enum {
-	MODEL_UNKNOWN = 0x00,
-	MODEL_8305 = 0x01,
-	MODEL_8381 = 0x02,
-	MODEL_8385 = 0x03
-};
-
-static const struct lbs_fw_table fw_table[] = {
-	{ MODEL_8305, "libertas/cf8305.bin", NULL },
-	{ MODEL_8305, "libertas_cs_helper.fw", NULL },
-	{ MODEL_8381, "libertas/cf8381_helper.bin", "libertas/cf8381.bin" },
-	{ MODEL_8381, "libertas_cs_helper.fw", "libertas_cs.fw" },
-	{ MODEL_8385, "libertas/cf8385_helper.bin", "libertas/cf8385.bin" },
-	{ MODEL_8385, "libertas_cs_helper.fw", "libertas_cs.fw" },
-	{ 0, NULL, NULL }
-};
-MODULE_FIRMWARE("libertas/cf8305.bin");
-MODULE_FIRMWARE("libertas/cf8381_helper.bin");
-MODULE_FIRMWARE("libertas/cf8381.bin");
-MODULE_FIRMWARE("libertas/cf8385_helper.bin");
-MODULE_FIRMWARE("libertas/cf8385.bin");
-MODULE_FIRMWARE("libertas_cs_helper.fw");
-MODULE_FIRMWARE("libertas_cs.fw");
-
-
-/********************************************************************/
-/* Hardware access                                                  */
-/********************************************************************/
-
-/* This define enables wrapper functions which allow you
-   to dump all register accesses. You normally won't this,
-   except for development */
-/* #define DEBUG_IO */
-
-#ifdef DEBUG_IO
-static int debug_output = 0;
-#else
-/* This way the compiler optimizes the printk's away */
-#define debug_output 0
-#endif
-
-static inline unsigned int if_cs_read8(struct if_cs_card *card, uint reg)
-{
-	unsigned int val = ioread8(card->iobase + reg);
-	if (debug_output)
-		printk(KERN_INFO "inb %08x<%02x\n", reg, val);
-	return val;
-}
-static inline unsigned int if_cs_read16(struct if_cs_card *card, uint reg)
-{
-	unsigned int val = ioread16(card->iobase + reg);
-	if (debug_output)
-		printk(KERN_INFO "inw %08x<%04x\n", reg, val);
-	return val;
-}
-static inline void if_cs_read16_rep(
-	struct if_cs_card *card,
-	uint reg,
-	void *buf,
-	unsigned long count)
-{
-	if (debug_output)
-		printk(KERN_INFO "insw %08x<(0x%lx words)\n",
-			reg, count);
-	ioread16_rep(card->iobase + reg, buf, count);
-}
-
-static inline void if_cs_write8(struct if_cs_card *card, uint reg, u8 val)
-{
-	if (debug_output)
-		printk(KERN_INFO "outb %08x>%02x\n", reg, val);
-	iowrite8(val, card->iobase + reg);
-}
-
-static inline void if_cs_write16(struct if_cs_card *card, uint reg, u16 val)
-{
-	if (debug_output)
-		printk(KERN_INFO "outw %08x>%04x\n", reg, val);
-	iowrite16(val, card->iobase + reg);
-}
-
-static inline void if_cs_write16_rep(
-	struct if_cs_card *card,
-	uint reg,
-	const void *buf,
-	unsigned long count)
-{
-	if (debug_output)
-		printk(KERN_INFO "outsw %08x>(0x%lx words)\n",
-			reg, count);
-	iowrite16_rep(card->iobase + reg, buf, count);
-}
-
-
-/*
- * I know that polling/delaying is frowned upon. However, this procedure
- * with polling is needed while downloading the firmware. At this stage,
- * the hardware does unfortunately not create any interrupts.
- *
- * Fortunately, this function is never used once the firmware is in
- * the card. :-)
- *
- * As a reference, see the "Firmware Specification v5.1", page 18
- * and 19. I did not follow their suggested timing to the word,
- * but this works nice & fast anyway.
- */
-static int if_cs_poll_while_fw_download(struct if_cs_card *card, uint addr, u8 reg)
-{
-	int i;
-
-	for (i = 0; i < 100000; i++) {
-		u8 val = if_cs_read8(card, addr);
-		if (val == reg)
-			return 0;
-		udelay(5);
-	}
-	return -ETIME;
-}
-
-
-
-/*
- * First the bitmasks for the host/card interrupt/status registers:
- */
-#define IF_CS_BIT_TX			0x0001
-#define IF_CS_BIT_RX			0x0002
-#define IF_CS_BIT_COMMAND		0x0004
-#define IF_CS_BIT_RESP			0x0008
-#define IF_CS_BIT_EVENT			0x0010
-#define	IF_CS_BIT_MASK			0x001f
-
-
-
-/*
- * It's not really clear to me what the host status register is for. It
- * needs to be set almost in union with "host int cause". The following
- * bits from above are used:
- *
- *   IF_CS_BIT_TX         driver downloaded a data packet
- *   IF_CS_BIT_RX         driver got a data packet
- *   IF_CS_BIT_COMMAND    driver downloaded a command
- *   IF_CS_BIT_RESP       not used (has some meaning with powerdown)
- *   IF_CS_BIT_EVENT      driver read a host event
- */
-#define IF_CS_HOST_STATUS		0x00000000
-
-/*
- * With the host int cause register can the host (that is, Linux) cause
- * an interrupt in the firmware, to tell the firmware about those events:
- *
- *   IF_CS_BIT_TX         a data packet has been downloaded
- *   IF_CS_BIT_RX         a received data packet has retrieved
- *   IF_CS_BIT_COMMAND    a firmware block or a command has been downloaded
- *   IF_CS_BIT_RESP       not used (has some meaning with powerdown)
- *   IF_CS_BIT_EVENT      a host event (link lost etc) has been retrieved
- */
-#define IF_CS_HOST_INT_CAUSE		0x00000002
-
-/*
- * The host int mask register is used to enable/disable interrupt.  However,
- * I have the suspicion that disabled interrupts are lost.
- */
-#define IF_CS_HOST_INT_MASK		0x00000004
-
-/*
- * Used to send or receive data packets:
- */
-#define IF_CS_WRITE			0x00000016
-#define IF_CS_WRITE_LEN			0x00000014
-#define IF_CS_READ			0x00000010
-#define IF_CS_READ_LEN			0x00000024
-
-/*
- * Used to send commands (and to send firmware block) and to
- * receive command responses:
- */
-#define IF_CS_CMD			0x0000001A
-#define IF_CS_CMD_LEN			0x00000018
-#define IF_CS_RESP			0x00000012
-#define IF_CS_RESP_LEN			0x00000030
-
-/*
- * The card status registers shows what the card/firmware actually
- * accepts:
- *
- *   IF_CS_BIT_TX        you may send a data packet
- *   IF_CS_BIT_RX        you may retrieve a data packet
- *   IF_CS_BIT_COMMAND   you may send a command
- *   IF_CS_BIT_RESP      you may retrieve a command response
- *   IF_CS_BIT_EVENT     the card has a event for use (link lost, snr low etc)
- *
- * When reading this register several times, you will get back the same
- * results --- with one exception: the IF_CS_BIT_EVENT clear itself
- * automatically.
- *
- * Not that we don't rely on BIT_RX,_BIT_RESP or BIT_EVENT because
- * we handle this via the card int cause register.
- */
-#define IF_CS_CARD_STATUS		0x00000020
-#define IF_CS_CARD_STATUS_MASK		0x7f00
-
-/*
- * The card int cause register is used by the card/firmware to notify us
- * about the following events:
- *
- *   IF_CS_BIT_TX        a data packet has successfully been sentx
- *   IF_CS_BIT_RX        a data packet has been received and can be retrieved
- *   IF_CS_BIT_COMMAND   not used
- *   IF_CS_BIT_RESP      the firmware has a command response for us
- *   IF_CS_BIT_EVENT     the card has a event for use (link lost, snr low etc)
- */
-#define IF_CS_CARD_INT_CAUSE		0x00000022
-
-/*
- * This is used to for handshaking with the card's bootloader/helper image
- * to synchronize downloading of firmware blocks.
- */
-#define IF_CS_SQ_READ_LOW		0x00000028
-#define IF_CS_SQ_HELPER_OK		0x10
-
-/*
- * The scratch register tells us ...
- *
- * IF_CS_SCRATCH_BOOT_OK     the bootloader runs
- * IF_CS_SCRATCH_HELPER_OK   the helper firmware already runs
- */
-#define IF_CS_SCRATCH			0x0000003F
-#define IF_CS_SCRATCH_BOOT_OK		0x00
-#define IF_CS_SCRATCH_HELPER_OK		0x5a
-
-/*
- * Used to detect ancient chips:
- */
-#define IF_CS_PRODUCT_ID		0x0000001C
-#define IF_CS_CF8385_B1_REV		0x12
-#define IF_CS_CF8381_B3_REV		0x04
-#define IF_CS_CF8305_B1_REV		0x03
-
-/*
- * Used to detect other cards than CF8385 since their revisions of silicon
- * doesn't match those from CF8385, eg. CF8381 B3 works with this driver.
- */
-#define CF8305_MANFID		0x02db
-#define CF8305_CARDID		0x8103
-#define CF8381_MANFID		0x02db
-#define CF8381_CARDID		0x6064
-#define CF8385_MANFID		0x02df
-#define CF8385_CARDID		0x8103
-
-/*
- * FIXME: just use the 'driver_info' field of 'struct pcmcia_device_id' when
- * that gets fixed.  Currently there's no way to access it from the probe hook.
- */
-static inline u32 get_model(u16 manf_id, u16 card_id)
-{
-	/* NOTE: keep in sync with if_cs_ids */
-	if (manf_id == CF8305_MANFID && card_id == CF8305_CARDID)
-		return MODEL_8305;
-	else if (manf_id == CF8381_MANFID && card_id == CF8381_CARDID)
-		return MODEL_8381;
-	else if (manf_id == CF8385_MANFID && card_id == CF8385_CARDID)
-		return MODEL_8385;
-	return MODEL_UNKNOWN;
-}
-
-/********************************************************************/
-/* I/O and interrupt handling                                       */
-/********************************************************************/
-
-static inline void if_cs_enable_ints(struct if_cs_card *card)
-{
-	if_cs_write16(card, IF_CS_HOST_INT_MASK, 0);
-}
-
-static inline void if_cs_disable_ints(struct if_cs_card *card)
-{
-	if_cs_write16(card, IF_CS_HOST_INT_MASK, IF_CS_BIT_MASK);
-}
-
-/*
- * Called from if_cs_host_to_card to send a command to the hardware
- */
-static int if_cs_send_cmd(struct lbs_private *priv, u8 *buf, u16 nb)
-{
-	struct if_cs_card *card = (struct if_cs_card *)priv->card;
-	int ret = -1;
-	int loops = 0;
-
-	if_cs_disable_ints(card);
-
-	/* Is hardware ready? */
-	while (1) {
-		u16 status = if_cs_read16(card, IF_CS_CARD_STATUS);
-		if (status & IF_CS_BIT_COMMAND)
-			break;
-		if (++loops > 100) {
-			netdev_err(priv->dev, "card not ready for commands\n");
-			goto done;
-		}
-		mdelay(1);
-	}
-
-	if_cs_write16(card, IF_CS_CMD_LEN, nb);
-
-	if_cs_write16_rep(card, IF_CS_CMD, buf, nb / 2);
-	/* Are we supposed to transfer an odd amount of bytes? */
-	if (nb & 1)
-		if_cs_write8(card, IF_CS_CMD, buf[nb-1]);
-
-	/* "Assert the download over interrupt command in the Host
-	 * status register" */
-	if_cs_write16(card, IF_CS_HOST_STATUS, IF_CS_BIT_COMMAND);
-
-	/* "Assert the download over interrupt command in the Card
-	 * interrupt case register" */
-	if_cs_write16(card, IF_CS_HOST_INT_CAUSE, IF_CS_BIT_COMMAND);
-	ret = 0;
-
-done:
-	if_cs_enable_ints(card);
-	return ret;
-}
-
-/*
- * Called from if_cs_host_to_card to send a data to the hardware
- */
-static void if_cs_send_data(struct lbs_private *priv, u8 *buf, u16 nb)
-{
-	struct if_cs_card *card = (struct if_cs_card *)priv->card;
-	u16 status;
-
-	if_cs_disable_ints(card);
-
-	status = if_cs_read16(card, IF_CS_CARD_STATUS);
-	BUG_ON((status & IF_CS_BIT_TX) == 0);
-
-	if_cs_write16(card, IF_CS_WRITE_LEN, nb);
-
-	/* write even number of bytes, then odd byte if necessary */
-	if_cs_write16_rep(card, IF_CS_WRITE, buf, nb / 2);
-	if (nb & 1)
-		if_cs_write8(card, IF_CS_WRITE, buf[nb-1]);
-
-	if_cs_write16(card, IF_CS_HOST_STATUS, IF_CS_BIT_TX);
-	if_cs_write16(card, IF_CS_HOST_INT_CAUSE, IF_CS_BIT_TX);
-	if_cs_enable_ints(card);
-}
-
-/*
- * Get the command result out of the card.
- */
-static int if_cs_receive_cmdres(struct lbs_private *priv, u8 *data, u32 *len)
-{
-	unsigned long flags;
-	int ret = -1;
-	u16 status;
-
-	/* is hardware ready? */
-	status = if_cs_read16(priv->card, IF_CS_CARD_STATUS);
-	if ((status & IF_CS_BIT_RESP) == 0) {
-		netdev_err(priv->dev, "no cmd response in card\n");
-		*len = 0;
-		goto out;
-	}
-
-	*len = if_cs_read16(priv->card, IF_CS_RESP_LEN);
-	if ((*len == 0) || (*len > LBS_CMD_BUFFER_SIZE)) {
-		netdev_err(priv->dev,
-			   "card cmd buffer has invalid # of bytes (%d)\n",
-			   *len);
-		goto out;
-	}
-
-	/* read even number of bytes, then odd byte if necessary */
-	if_cs_read16_rep(priv->card, IF_CS_RESP, data, *len/sizeof(u16));
-	if (*len & 1)
-		data[*len-1] = if_cs_read8(priv->card, IF_CS_RESP);
-
-	/* This is a workaround for a firmware that reports too much
-	 * bytes */
-	*len -= 8;
-	ret = 0;
-
-	/* Clear this flag again */
-	spin_lock_irqsave(&priv->driver_lock, flags);
-	priv->dnld_sent = DNLD_RES_RECEIVED;
-	spin_unlock_irqrestore(&priv->driver_lock, flags);
-
-out:
-	return ret;
-}
-
-static struct sk_buff *if_cs_receive_data(struct lbs_private *priv)
-{
-	struct sk_buff *skb = NULL;
-	u16 len;
-	u8 *data;
-
-	len = if_cs_read16(priv->card, IF_CS_READ_LEN);
-	if (len == 0 || len > MRVDRV_ETH_RX_PACKET_BUFFER_SIZE) {
-		netdev_err(priv->dev,
-			   "card data buffer has invalid # of bytes (%d)\n",
-			   len);
-		priv->dev->stats.rx_dropped++;
-		goto dat_err;
-	}
-
-	skb = dev_alloc_skb(MRVDRV_ETH_RX_PACKET_BUFFER_SIZE + 2);
-	if (!skb)
-		goto out;
-	skb_put(skb, len);
-	skb_reserve(skb, 2);/* 16 byte align */
-	data = skb->data;
-
-	/* read even number of bytes, then odd byte if necessary */
-	if_cs_read16_rep(priv->card, IF_CS_READ, data, len/sizeof(u16));
-	if (len & 1)
-		data[len-1] = if_cs_read8(priv->card, IF_CS_READ);
-
-dat_err:
-	if_cs_write16(priv->card, IF_CS_HOST_STATUS, IF_CS_BIT_RX);
-	if_cs_write16(priv->card, IF_CS_HOST_INT_CAUSE, IF_CS_BIT_RX);
-
-out:
-	return skb;
-}
-
-static irqreturn_t if_cs_interrupt(int irq, void *data)
-{
-	struct if_cs_card *card = data;
-	struct lbs_private *priv = card->priv;
-	u16 cause;
-
-	/* Ask card interrupt cause register if there is something for us */
-	cause = if_cs_read16(card, IF_CS_CARD_INT_CAUSE);
-	lbs_deb_cs("cause 0x%04x\n", cause);
-
-	if (cause == 0) {
-		/* Not for us */
-		return IRQ_NONE;
-	}
-
-	if (cause == 0xffff) {
-		/* Read in junk, the card has probably been removed */
-		card->priv->surpriseremoved = 1;
-		return IRQ_HANDLED;
-	}
-
-	if (cause & IF_CS_BIT_RX) {
-		struct sk_buff *skb;
-		lbs_deb_cs("rx packet\n");
-		skb = if_cs_receive_data(priv);
-		if (skb)
-			lbs_process_rxed_packet(priv, skb);
-	}
-
-	if (cause & IF_CS_BIT_TX) {
-		lbs_deb_cs("tx done\n");
-		lbs_host_to_card_done(priv);
-	}
-
-	if (cause & IF_CS_BIT_RESP) {
-		unsigned long flags;
-		u8 i;
-
-		lbs_deb_cs("cmd resp\n");
-		spin_lock_irqsave(&priv->driver_lock, flags);
-		i = (priv->resp_idx == 0) ? 1 : 0;
-		spin_unlock_irqrestore(&priv->driver_lock, flags);
-
-		BUG_ON(priv->resp_len[i]);
-		if_cs_receive_cmdres(priv, priv->resp_buf[i],
-			&priv->resp_len[i]);
-
-		spin_lock_irqsave(&priv->driver_lock, flags);
-		lbs_notify_command_response(priv, i);
-		spin_unlock_irqrestore(&priv->driver_lock, flags);
-	}
-
-	if (cause & IF_CS_BIT_EVENT) {
-		u16 status = if_cs_read16(priv->card, IF_CS_CARD_STATUS);
-		if_cs_write16(priv->card, IF_CS_HOST_INT_CAUSE,
-			IF_CS_BIT_EVENT);
-		lbs_queue_event(priv, (status & IF_CS_CARD_STATUS_MASK) >> 8);
-	}
-
-	/* Clear interrupt cause */
-	if_cs_write16(card, IF_CS_CARD_INT_CAUSE, cause & IF_CS_BIT_MASK);
-
-	return IRQ_HANDLED;
-}
-
-
-
-
-/********************************************************************/
-/* Firmware                                                         */
-/********************************************************************/
-
-/*
- * Tries to program the helper firmware.
- *
- * Return 0 on success
- */
-static int if_cs_prog_helper(struct if_cs_card *card, const struct firmware *fw)
-{
-	int ret = 0;
-	int sent = 0;
-	u8  scratch;
-
-	/*
-	 * This is the only place where an unaligned register access happens on
-	 * the CF8305 card, therefore for the sake of speed of the driver, we do
-	 * the alignment correction here.
-	 */
-	if (card->align_regs)
-		scratch = if_cs_read16(card, IF_CS_SCRATCH) >> 8;
-	else
-		scratch = if_cs_read8(card, IF_CS_SCRATCH);
-
-	/* "If the value is 0x5a, the firmware is already
-	 * downloaded successfully"
-	 */
-	if (scratch == IF_CS_SCRATCH_HELPER_OK)
-		goto done;
-
-	/* "If the value is != 00, it is invalid value of register */
-	if (scratch != IF_CS_SCRATCH_BOOT_OK) {
-		ret = -ENODEV;
-		goto done;
-	}
-
-	lbs_deb_cs("helper size %td\n", fw->size);
-
-	/* "Set the 5 bytes of the helper image to 0" */
-	/* Not needed, this contains an ARM branch instruction */
-
-	for (;;) {
-		/* "the number of bytes to send is 256" */
-		int count = 256;
-		int remain = fw->size - sent;
-
-		if (remain < count)
-			count = remain;
-
-		/*
-		 * "write the number of bytes to be sent to the I/O Command
-		 * write length register"
-		 */
-		if_cs_write16(card, IF_CS_CMD_LEN, count);
-
-		/* "write this to I/O Command port register as 16 bit writes */
-		if (count)
-			if_cs_write16_rep(card, IF_CS_CMD,
-				&fw->data[sent],
-				count >> 1);
-
-		/*
-		 * "Assert the download over interrupt command in the Host
-		 * status register"
-		 */
-		if_cs_write8(card, IF_CS_HOST_STATUS, IF_CS_BIT_COMMAND);
-
-		/*
-		 * "Assert the download over interrupt command in the Card
-		 * interrupt case register"
-		 */
-		if_cs_write16(card, IF_CS_HOST_INT_CAUSE, IF_CS_BIT_COMMAND);
-
-		/*
-		 * "The host polls the Card Status register ... for 50 ms before
-		 * declaring a failure"
-		 */
-		ret = if_cs_poll_while_fw_download(card, IF_CS_CARD_STATUS,
-			IF_CS_BIT_COMMAND);
-		if (ret < 0) {
-			pr_err("can't download helper at 0x%x, ret %d\n",
-			       sent, ret);
-			goto done;
-		}
-
-		if (count == 0)
-			break;
-
-		sent += count;
-	}
-
-done:
-	return ret;
-}
-
-
-static int if_cs_prog_real(struct if_cs_card *card, const struct firmware *fw)
-{
-	int ret = 0;
-	int retry = 0;
-	int len = 0;
-	int sent;
-
-	lbs_deb_cs("fw size %td\n", fw->size);
-
-	ret = if_cs_poll_while_fw_download(card, IF_CS_SQ_READ_LOW,
-		IF_CS_SQ_HELPER_OK);
-	if (ret < 0) {
-		pr_err("helper firmware doesn't answer\n");
-		goto done;
-	}
-
-	for (sent = 0; sent < fw->size; sent += len) {
-		len = if_cs_read16(card, IF_CS_SQ_READ_LOW);
-		if (len & 1) {
-			retry++;
-			pr_info("odd, need to retry this firmware block\n");
-		} else {
-			retry = 0;
-		}
-
-		if (retry > 20) {
-			pr_err("could not download firmware\n");
-			ret = -ENODEV;
-			goto done;
-		}
-		if (retry) {
-			sent -= len;
-		}
-
-
-		if_cs_write16(card, IF_CS_CMD_LEN, len);
-
-		if_cs_write16_rep(card, IF_CS_CMD,
-			&fw->data[sent],
-			(len+1) >> 1);
-		if_cs_write8(card, IF_CS_HOST_STATUS, IF_CS_BIT_COMMAND);
-		if_cs_write16(card, IF_CS_HOST_INT_CAUSE, IF_CS_BIT_COMMAND);
-
-		ret = if_cs_poll_while_fw_download(card, IF_CS_CARD_STATUS,
-			IF_CS_BIT_COMMAND);
-		if (ret < 0) {
-			pr_err("can't download firmware at 0x%x\n", sent);
-			goto done;
-		}
-	}
-
-	ret = if_cs_poll_while_fw_download(card, IF_CS_SCRATCH, 0x5a);
-	if (ret < 0)
-		pr_err("firmware download failed\n");
-
-done:
-	return ret;
-}
-
-static void if_cs_prog_firmware(struct lbs_private *priv, int ret,
-				 const struct firmware *helper,
-				 const struct firmware *mainfw)
-{
-	struct if_cs_card *card = priv->card;
-
-	if (ret) {
-		pr_err("failed to find firmware (%d)\n", ret);
-		return;
-	}
-
-	/* Load the firmware */
-	ret = if_cs_prog_helper(card, helper);
-	if (ret == 0 && (card->model != MODEL_8305))
-		ret = if_cs_prog_real(card, mainfw);
-	if (ret)
-		return;
-
-	/* Now actually get the IRQ */
-	ret = request_irq(card->p_dev->irq, if_cs_interrupt,
-		IRQF_SHARED, DRV_NAME, card);
-	if (ret) {
-		pr_err("error in request_irq\n");
-		return;
-	}
-
-	/*
-	 * Clear any interrupt cause that happened while sending
-	 * firmware/initializing card
-	 */
-	if_cs_write16(card, IF_CS_CARD_INT_CAUSE, IF_CS_BIT_MASK);
-	if_cs_enable_ints(card);
-
-	/* And finally bring the card up */
-	priv->fw_ready = 1;
-	if (lbs_start_card(priv) != 0) {
-		pr_err("could not activate card\n");
-		free_irq(card->p_dev->irq, card);
-	}
-}
-
-
-/********************************************************************/
-/* Callback functions for libertas.ko                               */
-/********************************************************************/
-
-/* Send commands or data packets to the card */
-static int if_cs_host_to_card(struct lbs_private *priv,
-	u8 type,
-	u8 *buf,
-	u16 nb)
-{
-	int ret = -1;
-
-	switch (type) {
-	case MVMS_DAT:
-		priv->dnld_sent = DNLD_DATA_SENT;
-		if_cs_send_data(priv, buf, nb);
-		ret = 0;
-		break;
-	case MVMS_CMD:
-		priv->dnld_sent = DNLD_CMD_SENT;
-		ret = if_cs_send_cmd(priv, buf, nb);
-		break;
-	default:
-		netdev_err(priv->dev, "%s: unsupported type %d\n",
-			   __func__, type);
-	}
-
-	return ret;
-}
-
-
-static void if_cs_release(struct pcmcia_device *p_dev)
-{
-	struct if_cs_card *card = p_dev->priv;
-
-	free_irq(p_dev->irq, card);
-	pcmcia_disable_device(p_dev);
-	if (card->iobase)
-		ioport_unmap(card->iobase);
-}
-
-
-static int if_cs_ioprobe(struct pcmcia_device *p_dev, void *priv_data)
-{
-	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
-	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
-
-	if (p_dev->resource[1]->end) {
-		pr_err("wrong CIS (check number of IO windows)\n");
-		return -ENODEV;
-	}
-
-	/* This reserves IO space but doesn't actually enable it */
-	return pcmcia_request_io(p_dev);
-}
-
-static int if_cs_probe(struct pcmcia_device *p_dev)
-{
-	int ret = -ENOMEM;
-	unsigned int prod_id;
-	struct lbs_private *priv;
-	struct if_cs_card *card;
-
-	card = kzalloc(sizeof(struct if_cs_card), GFP_KERNEL);
-	if (!card)
-		goto out;
-
-	card->p_dev = p_dev;
-	p_dev->priv = card;
-
-	p_dev->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO;
-
-	if (pcmcia_loop_config(p_dev, if_cs_ioprobe, NULL)) {
-		pr_err("error in pcmcia_loop_config\n");
-		goto out1;
-	}
-
-	/*
-	 * Allocate an interrupt line.  Note that this does not assign
-	 * a handler to the interrupt, unless the 'Handler' member of
-	 * the irq structure is initialized.
-	 */
-	if (!p_dev->irq)
-		goto out1;
-
-	/* Initialize io access */
-	card->iobase = ioport_map(p_dev->resource[0]->start,
-				resource_size(p_dev->resource[0]));
-	if (!card->iobase) {
-		pr_err("error in ioport_map\n");
-		ret = -EIO;
-		goto out1;
-	}
-
-	ret = pcmcia_enable_device(p_dev);
-	if (ret) {
-		pr_err("error in pcmcia_enable_device\n");
-		goto out2;
-	}
-
-	/* Finally, report what we've done */
-	lbs_deb_cs("irq %d, io %pR", p_dev->irq, p_dev->resource[0]);
-
-	/*
-	 * Most of the libertas cards can do unaligned register access, but some
-	 * weird ones cannot. That's especially true for the CF8305 card.
-	 */
-	card->align_regs = false;
-
-	card->model = get_model(p_dev->manf_id, p_dev->card_id);
-	if (card->model == MODEL_UNKNOWN) {
-		pr_err("unsupported manf_id 0x%04x / card_id 0x%04x\n",
-		       p_dev->manf_id, p_dev->card_id);
-		ret = -ENODEV;
-		goto out2;
-	}
-
-	/* Check if we have a current silicon */
-	prod_id = if_cs_read8(card, IF_CS_PRODUCT_ID);
-	if (card->model == MODEL_8305) {
-		card->align_regs = true;
-		if (prod_id < IF_CS_CF8305_B1_REV) {
-			pr_err("8305 rev B0 and older are not supported\n");
-			ret = -ENODEV;
-			goto out2;
-		}
-	}
-
-	if ((card->model == MODEL_8381) && prod_id < IF_CS_CF8381_B3_REV) {
-		pr_err("8381 rev B2 and older are not supported\n");
-		ret = -ENODEV;
-		goto out2;
-	}
-
-	if ((card->model == MODEL_8385) && prod_id < IF_CS_CF8385_B1_REV) {
-		pr_err("8385 rev B0 and older are not supported\n");
-		ret = -ENODEV;
-		goto out2;
-	}
-
-	/* Make this card known to the libertas driver */
-	priv = lbs_add_card(card, &p_dev->dev);
-	if (IS_ERR(priv)) {
-		ret = PTR_ERR(priv);
-		goto out2;
-	}
-
-	/* Set up fields in lbs_private */
-	card->priv = priv;
-	priv->card = card;
-	priv->hw_host_to_card = if_cs_host_to_card;
-	priv->enter_deep_sleep = NULL;
-	priv->exit_deep_sleep = NULL;
-	priv->reset_deep_sleep_wakeup = NULL;
-
-	/* Get firmware */
-	ret = lbs_get_firmware_async(priv, &p_dev->dev, card->model, fw_table,
-				     if_cs_prog_firmware);
-	if (ret) {
-		pr_err("failed to find firmware (%d)\n", ret);
-		goto out3;
-	}
-
-	goto out;
-
-out3:
-	lbs_remove_card(priv);
-out2:
-	ioport_unmap(card->iobase);
-out1:
-	pcmcia_disable_device(p_dev);
-out:
-	return ret;
-}
-
-
-static void if_cs_detach(struct pcmcia_device *p_dev)
-{
-	struct if_cs_card *card = p_dev->priv;
-
-	lbs_stop_card(card->priv);
-	lbs_remove_card(card->priv);
-	if_cs_disable_ints(card);
-	if_cs_release(p_dev);
-	kfree(card);
-}
-
-
-
-/********************************************************************/
-/* Module initialization                                            */
-/********************************************************************/
-
-static const struct pcmcia_device_id if_cs_ids[] = {
-	PCMCIA_DEVICE_MANF_CARD(CF8305_MANFID, CF8305_CARDID),
-	PCMCIA_DEVICE_MANF_CARD(CF8381_MANFID, CF8381_CARDID),
-	PCMCIA_DEVICE_MANF_CARD(CF8385_MANFID, CF8385_CARDID),
-	/* NOTE: keep in sync with get_model() */
-	PCMCIA_DEVICE_NULL,
-};
-MODULE_DEVICE_TABLE(pcmcia, if_cs_ids);
-
-static struct pcmcia_driver lbs_driver = {
-	.owner		= THIS_MODULE,
-	.name		= DRV_NAME,
-	.probe		= if_cs_probe,
-	.remove		= if_cs_detach,
-	.id_table       = if_cs_ids,
-};
-module_pcmcia_driver(lbs_driver);
diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index 7a15ea8072e6..3604abcbcff9 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -2047,6 +2047,8 @@ static int mwifiex_cfg80211_start_ap(struct wiphy *wiphy,
 
 	mwifiex_set_sys_config_invalid_data(bss_cfg);
 
+	memcpy(bss_cfg->mac_addr, priv->curr_addr, ETH_ALEN);
+
 	if (params->beacon_interval)
 		bss_cfg->beacon_period = params->beacon_interval;
 	if (params->dtim_period)
diff --git a/drivers/net/wireless/marvell/mwifiex/cmdevt.c b/drivers/net/wireless/marvell/mwifiex/cmdevt.c
index 3756aa247e77..9eff29a25544 100644
--- a/drivers/net/wireless/marvell/mwifiex/cmdevt.c
+++ b/drivers/net/wireless/marvell/mwifiex/cmdevt.c
@@ -1244,8 +1244,6 @@ mwifiex_process_sleep_confirm_resp(struct mwifiex_adapter *adapter,
 				   u8 *pbuf, u32 upld_len)
 {
 	struct host_cmd_ds_command *cmd = (struct host_cmd_ds_command *) pbuf;
-	struct mwifiex_private *priv =
-		mwifiex_get_priv(adapter, MWIFIEX_BSS_ROLE_ANY);
 	uint16_t result = le16_to_cpu(cmd->result);
 	uint16_t command = le16_to_cpu(cmd->command);
 	uint16_t seq_num = le16_to_cpu(cmd->seq_num);
@@ -1260,12 +1258,6 @@ mwifiex_process_sleep_confirm_resp(struct mwifiex_adapter *adapter,
 		    "cmd: CMD_RESP: 0x%x, result %d, len %d, seqno 0x%x\n",
 		    command, result, le16_to_cpu(cmd->size), seq_num);
 
-	/* Get BSS number and corresponding priv */
-	priv = mwifiex_get_priv_by_id(adapter, HostCmd_GET_BSS_NO(seq_num),
-				      HostCmd_GET_BSS_TYPE(seq_num));
-	if (!priv)
-		priv = mwifiex_get_priv(adapter, MWIFIEX_BSS_ROLE_ANY);
-
 	/* Update sequence number */
 	seq_num = HostCmd_GET_SEQ_NO(seq_num);
 	/* Clear RET_BIT from HostCmd */
diff --git a/drivers/net/wireless/marvell/mwifiex/fw.h b/drivers/net/wireless/marvell/mwifiex/fw.h
index 8e6db904e5b2..62f3c9a52a1d 100644
--- a/drivers/net/wireless/marvell/mwifiex/fw.h
+++ b/drivers/net/wireless/marvell/mwifiex/fw.h
@@ -165,6 +165,7 @@ enum MWIFIEX_802_11_PRIVACY_FILTER {
 #define TLV_TYPE_STA_MAC_ADDR       (PROPRIETARY_TLV_BASE_ID + 32)
 #define TLV_TYPE_BSSID              (PROPRIETARY_TLV_BASE_ID + 35)
 #define TLV_TYPE_CHANNELBANDLIST    (PROPRIETARY_TLV_BASE_ID + 42)
+#define TLV_TYPE_UAP_MAC_ADDRESS    (PROPRIETARY_TLV_BASE_ID + 43)
 #define TLV_TYPE_UAP_BEACON_PERIOD  (PROPRIETARY_TLV_BASE_ID + 44)
 #define TLV_TYPE_UAP_DTIM_PERIOD    (PROPRIETARY_TLV_BASE_ID + 45)
 #define TLV_TYPE_UAP_BCAST_SSID     (PROPRIETARY_TLV_BASE_ID + 48)
diff --git a/drivers/net/wireless/marvell/mwifiex/ioctl.h b/drivers/net/wireless/marvell/mwifiex/ioctl.h
index 091e7ca79376..e8825f302de8 100644
--- a/drivers/net/wireless/marvell/mwifiex/ioctl.h
+++ b/drivers/net/wireless/marvell/mwifiex/ioctl.h
@@ -107,6 +107,7 @@ struct mwifiex_uap_bss_param {
 	u8 qos_info;
 	u8 power_constraint;
 	struct mwifiex_types_wmm_info wmm_info;
+	u8 mac_addr[ETH_ALEN];
 };
 
 enum {
diff --git a/drivers/net/wireless/marvell/mwifiex/join.c b/drivers/net/wireless/marvell/mwifiex/join.c
index a6e254a1185c..9d98a1908dd6 100644
--- a/drivers/net/wireless/marvell/mwifiex/join.c
+++ b/drivers/net/wireless/marvell/mwifiex/join.c
@@ -1427,8 +1427,8 @@ int mwifiex_adhoc_join(struct mwifiex_private *priv,
 
 	/* Check if the requested SSID is already joined */
 	if (priv->curr_bss_params.bss_descriptor.ssid.ssid_len &&
-	    !mwifiex_ssid_cmp(&bss_desc->ssid,
-			      &priv->curr_bss_params.bss_descriptor.ssid) &&
+	    cfg80211_ssid_eq(&bss_desc->ssid,
+			     &priv->curr_bss_params.bss_descriptor.ssid) &&
 	    (priv->curr_bss_params.bss_descriptor.bss_mode ==
 							NL80211_IFTYPE_ADHOC)) {
 		mwifiex_dbg(priv->adapter, INFO,
diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h
index d263eae6078c..318b42b1896f 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.h
+++ b/drivers/net/wireless/marvell/mwifiex/main.h
@@ -1152,7 +1152,6 @@ void mwifiex_queue_scan_cmd(struct mwifiex_private *priv,
 			    struct cmd_ctrl_node *cmd_node);
 int mwifiex_ret_802_11_scan(struct mwifiex_private *priv,
 			    struct host_cmd_ds_command *resp);
-s32 mwifiex_ssid_cmp(struct cfg80211_ssid *ssid1, struct cfg80211_ssid *ssid2);
 int mwifiex_associate(struct mwifiex_private *priv,
 		      struct mwifiex_bssdescriptor *bss_desc);
 int mwifiex_cmd_802_11_associate(struct mwifiex_private *priv,
diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c
index 72904c275461..a2ddac363b10 100644
--- a/drivers/net/wireless/marvell/mwifiex/scan.c
+++ b/drivers/net/wireless/marvell/mwifiex/scan.c
@@ -180,17 +180,6 @@ mwifiex_is_wpa_oui_present(struct mwifiex_bssdescriptor *bss_desc, u32 cipher)
 }
 
 /*
- * This function compares two SSIDs and checks if they match.
- */
-s32
-mwifiex_ssid_cmp(struct cfg80211_ssid *ssid1, struct cfg80211_ssid *ssid2)
-{
-	if (!ssid1 || !ssid2 || (ssid1->ssid_len != ssid2->ssid_len))
-		return -1;
-	return memcmp(ssid1->ssid, ssid2->ssid, ssid1->ssid_len);
-}
-
-/*
  * This function checks if wapi is enabled in driver and scanned network is
  * compatible with it.
  */
diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c
index 6462a0ffe698..75f53c2f1e1f 100644
--- a/drivers/net/wireless/marvell/mwifiex/sdio.c
+++ b/drivers/net/wireless/marvell/mwifiex/sdio.c
@@ -331,6 +331,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8786 = {
 	.can_dump_fw = false,
 	.can_auto_tdls = false,
 	.can_ext_scan = false,
+	.fw_ready_extra_delay = false,
 };
 
 static const struct mwifiex_sdio_device mwifiex_sdio_sd8787 = {
@@ -346,6 +347,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8787 = {
 	.can_dump_fw = false,
 	.can_auto_tdls = false,
 	.can_ext_scan = true,
+	.fw_ready_extra_delay = false,
 };
 
 static const struct mwifiex_sdio_device mwifiex_sdio_sd8797 = {
@@ -361,6 +363,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8797 = {
 	.can_dump_fw = false,
 	.can_auto_tdls = false,
 	.can_ext_scan = true,
+	.fw_ready_extra_delay = false,
 };
 
 static const struct mwifiex_sdio_device mwifiex_sdio_sd8897 = {
@@ -376,6 +379,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8897 = {
 	.can_dump_fw = true,
 	.can_auto_tdls = false,
 	.can_ext_scan = true,
+	.fw_ready_extra_delay = false,
 };
 
 static const struct mwifiex_sdio_device mwifiex_sdio_sd8977 = {
@@ -392,6 +396,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8977 = {
 	.fw_dump_enh = true,
 	.can_auto_tdls = false,
 	.can_ext_scan = true,
+	.fw_ready_extra_delay = false,
 };
 
 static const struct mwifiex_sdio_device mwifiex_sdio_sd8978 = {
@@ -408,6 +413,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8978 = {
 	.fw_dump_enh = true,
 	.can_auto_tdls = false,
 	.can_ext_scan = true,
+	.fw_ready_extra_delay = true,
 };
 
 static const struct mwifiex_sdio_device mwifiex_sdio_sd8997 = {
@@ -425,6 +431,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8997 = {
 	.fw_dump_enh = true,
 	.can_auto_tdls = false,
 	.can_ext_scan = true,
+	.fw_ready_extra_delay = false,
 };
 
 static const struct mwifiex_sdio_device mwifiex_sdio_sd8887 = {
@@ -440,6 +447,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8887 = {
 	.can_dump_fw = false,
 	.can_auto_tdls = true,
 	.can_ext_scan = true,
+	.fw_ready_extra_delay = false,
 };
 
 static const struct mwifiex_sdio_device mwifiex_sdio_sd8987 = {
@@ -456,6 +464,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8987 = {
 	.fw_dump_enh = true,
 	.can_auto_tdls = true,
 	.can_ext_scan = true,
+	.fw_ready_extra_delay = false,
 };
 
 static const struct mwifiex_sdio_device mwifiex_sdio_sd8801 = {
@@ -471,6 +480,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8801 = {
 	.can_dump_fw = false,
 	.can_auto_tdls = false,
 	.can_ext_scan = true,
+	.fw_ready_extra_delay = false,
 };
 
 static struct memory_type_mapping generic_mem_type_map[] = {
@@ -563,6 +573,7 @@ mwifiex_sdio_probe(struct sdio_func *func, const struct sdio_device_id *id)
 		card->fw_dump_enh = data->fw_dump_enh;
 		card->can_auto_tdls = data->can_auto_tdls;
 		card->can_ext_scan = data->can_ext_scan;
+		card->fw_ready_extra_delay = data->fw_ready_extra_delay;
 		INIT_WORK(&card->work, mwifiex_sdio_work);
 	}
 
@@ -766,8 +777,9 @@ mwifiex_sdio_read_fw_status(struct mwifiex_adapter *adapter, u16 *dat)
 static int mwifiex_check_fw_status(struct mwifiex_adapter *adapter,
 				   u32 poll_num)
 {
+	struct sdio_mmc_card *card = adapter->card;
 	int ret = 0;
-	u16 firmware_stat;
+	u16 firmware_stat = 0;
 	u32 tries;
 
 	for (tries = 0; tries < poll_num; tries++) {
@@ -783,6 +795,13 @@ static int mwifiex_check_fw_status(struct mwifiex_adapter *adapter,
 		ret = -1;
 	}
 
+	if (card->fw_ready_extra_delay &&
+	    firmware_stat == FIRMWARE_READY_SDIO)
+		/* firmware might pretend to be ready, when it's not.
+		 * Wait a little bit more as a workaround.
+		 */
+		msleep(100);
+
 	return ret;
 }
 
diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.h b/drivers/net/wireless/marvell/mwifiex/sdio.h
index b86a9263a6a8..cb63ad55d675 100644
--- a/drivers/net/wireless/marvell/mwifiex/sdio.h
+++ b/drivers/net/wireless/marvell/mwifiex/sdio.h
@@ -255,6 +255,7 @@ struct sdio_mmc_card {
 	bool fw_dump_enh;
 	bool can_auto_tdls;
 	bool can_ext_scan;
+	bool fw_ready_extra_delay;
 
 	struct mwifiex_sdio_mpa_tx mpa_tx;
 	struct mwifiex_sdio_mpa_rx mpa_rx;
@@ -278,6 +279,7 @@ struct mwifiex_sdio_device {
 	bool fw_dump_enh;
 	bool can_auto_tdls;
 	bool can_ext_scan;
+	bool fw_ready_extra_delay;
 };
 
 /*
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
index a2ad2b53f016..32a27fad7b79 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
@@ -345,8 +345,8 @@ int mwifiex_bss_start(struct mwifiex_private *priv, struct cfg80211_bss *bss,
 		/* Adhoc mode */
 		/* If the requested SSID matches current SSID, return */
 		if (bss_desc && bss_desc->ssid.ssid_len &&
-		    (!mwifiex_ssid_cmp(&priv->curr_bss_params.bss_descriptor.
-				       ssid, &bss_desc->ssid))) {
+		    cfg80211_ssid_eq(&priv->curr_bss_params.bss_descriptor.ssid,
+				     &bss_desc->ssid)) {
 			ret = 0;
 			goto done;
 		}
diff --git a/drivers/net/wireless/marvell/mwifiex/uap_cmd.c b/drivers/net/wireless/marvell/mwifiex/uap_cmd.c
index e78a201cd150..491e36611909 100644
--- a/drivers/net/wireless/marvell/mwifiex/uap_cmd.c
+++ b/drivers/net/wireless/marvell/mwifiex/uap_cmd.c
@@ -468,6 +468,7 @@ void mwifiex_config_uap_11d(struct mwifiex_private *priv,
 static int
 mwifiex_uap_bss_param_prepare(u8 *tlv, void *cmd_buf, u16 *param_size)
 {
+	struct host_cmd_tlv_mac_addr *mac_tlv;
 	struct host_cmd_tlv_dtim_period *dtim_period;
 	struct host_cmd_tlv_beacon_period *beacon_period;
 	struct host_cmd_tlv_ssid *ssid;
@@ -487,6 +488,13 @@ mwifiex_uap_bss_param_prepare(u8 *tlv, void *cmd_buf, u16 *param_size)
 	int i;
 	u16 cmd_size = *param_size;
 
+	mac_tlv = (struct host_cmd_tlv_mac_addr *)tlv;
+	mac_tlv->header.type = cpu_to_le16(TLV_TYPE_UAP_MAC_ADDRESS);
+	mac_tlv->header.len = cpu_to_le16(ETH_ALEN);
+	memcpy(mac_tlv->mac_addr, bss_cfg->mac_addr, ETH_ALEN);
+	cmd_size += sizeof(struct host_cmd_tlv_mac_addr);
+	tlv += sizeof(struct host_cmd_tlv_mac_addr);
+
 	if (bss_cfg->ssid.ssid_len) {
 		ssid = (struct host_cmd_tlv_ssid *)tlv;
 		ssid->header.type = cpu_to_le16(TLV_TYPE_UAP_SSID);
diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index 511fe7e6e744..00230f106294 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -9,11 +9,11 @@
 
 #if IS_ENABLED(CONFIG_NET_MEDIATEK_SOC_WED)
 
-#define Q_READ(_dev, _q, _field) ({					\
+#define Q_READ(_q, _field) ({						\
 	u32 _offset = offsetof(struct mt76_queue_regs, _field);		\
 	u32 _val;							\
 	if ((_q)->flags & MT_QFLAG_WED)					\
-		_val = mtk_wed_device_reg_read(&(_dev)->mmio.wed,	\
+		_val = mtk_wed_device_reg_read((_q)->wed,		\
 					       ((_q)->wed_regs +	\
 					        _offset));		\
 	else								\
@@ -21,10 +21,10 @@
 	_val;								\
 })
 
-#define Q_WRITE(_dev, _q, _field, _val)	do {				\
+#define Q_WRITE(_q, _field, _val)	do {				\
 	u32 _offset = offsetof(struct mt76_queue_regs, _field);		\
 	if ((_q)->flags & MT_QFLAG_WED)					\
-		mtk_wed_device_reg_write(&(_dev)->mmio.wed,		\
+		mtk_wed_device_reg_write((_q)->wed,			\
 					 ((_q)->wed_regs + _offset),	\
 					 _val);				\
 	else								\
@@ -33,8 +33,8 @@
 
 #else
 
-#define Q_READ(_dev, _q, _field)	readl(&(_q)->regs->_field)
-#define Q_WRITE(_dev, _q, _field, _val)	writel(_val, &(_q)->regs->_field)
+#define Q_READ(_q, _field)		readl(&(_q)->regs->_field)
+#define Q_WRITE(_q, _field, _val)	writel(_val, &(_q)->regs->_field)
 
 #endif
 
@@ -188,41 +188,67 @@ EXPORT_SYMBOL_GPL(mt76_free_pending_rxwi);
 static void
 mt76_dma_sync_idx(struct mt76_dev *dev, struct mt76_queue *q)
 {
-	Q_WRITE(dev, q, desc_base, q->desc_dma);
-	Q_WRITE(dev, q, ring_size, q->ndesc);
-	q->head = Q_READ(dev, q, dma_idx);
+	Q_WRITE(q, desc_base, q->desc_dma);
+	if (q->flags & MT_QFLAG_WED_RRO_EN)
+		Q_WRITE(q, ring_size, MT_DMA_RRO_EN | q->ndesc);
+	else
+		Q_WRITE(q, ring_size, q->ndesc);
+	q->head = Q_READ(q, dma_idx);
 	q->tail = q->head;
 }
 
 static void
-mt76_dma_queue_reset(struct mt76_dev *dev, struct mt76_queue *q)
+__mt76_dma_queue_reset(struct mt76_dev *dev, struct mt76_queue *q,
+		       bool reset_idx)
 {
-	int i;
-
 	if (!q || !q->ndesc)
 		return;
 
-	/* clear descriptors */
-	for (i = 0; i < q->ndesc; i++)
-		q->desc[i].ctrl = cpu_to_le32(MT_DMA_CTL_DMA_DONE);
+	if (!mt76_queue_is_wed_rro_ind(q)) {
+		int i;
+
+		/* clear descriptors */
+		for (i = 0; i < q->ndesc; i++)
+			q->desc[i].ctrl = cpu_to_le32(MT_DMA_CTL_DMA_DONE);
+	}
 
-	Q_WRITE(dev, q, cpu_idx, 0);
-	Q_WRITE(dev, q, dma_idx, 0);
+	if (reset_idx) {
+		Q_WRITE(q, cpu_idx, 0);
+		Q_WRITE(q, dma_idx, 0);
+	}
 	mt76_dma_sync_idx(dev, q);
 }
 
+static void
+mt76_dma_queue_reset(struct mt76_dev *dev, struct mt76_queue *q)
+{
+	__mt76_dma_queue_reset(dev, q, true);
+}
+
 static int
 mt76_dma_add_rx_buf(struct mt76_dev *dev, struct mt76_queue *q,
 		    struct mt76_queue_buf *buf, void *data)
 {
-	struct mt76_desc *desc = &q->desc[q->head];
 	struct mt76_queue_entry *entry = &q->entry[q->head];
 	struct mt76_txwi_cache *txwi = NULL;
-	u32 buf1 = 0, ctrl;
+	struct mt76_desc *desc;
 	int idx = q->head;
+	u32 buf1 = 0, ctrl;
 	int rx_token;
 
+	if (mt76_queue_is_wed_rro_ind(q)) {
+		struct mt76_wed_rro_desc *rro_desc;
+
+		rro_desc = (struct mt76_wed_rro_desc *)q->desc;
+		data = &rro_desc[q->head];
+		goto done;
+	}
+
+	desc = &q->desc[q->head];
 	ctrl = FIELD_PREP(MT_DMA_CTL_SD_LEN0, buf[0].len);
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+	buf1 = FIELD_PREP(MT_DMA_CTL_SDP0_H, buf->addr >> 32);
+#endif
 
 	if (mt76_queue_is_wed_rx(q)) {
 		txwi = mt76_get_rxwi(dev);
@@ -244,6 +270,7 @@ mt76_dma_add_rx_buf(struct mt76_dev *dev, struct mt76_queue *q,
 	WRITE_ONCE(desc->ctrl, cpu_to_le32(ctrl));
 	WRITE_ONCE(desc->info, 0);
 
+done:
 	entry->dma_addr[0] = buf->addr;
 	entry->dma_len[0] = buf->len;
 	entry->txwi = txwi;
@@ -288,11 +315,18 @@ mt76_dma_add_buf(struct mt76_dev *dev, struct mt76_queue *q,
 		entry->dma_len[0] = buf[0].len;
 
 		ctrl = FIELD_PREP(MT_DMA_CTL_SD_LEN0, buf[0].len);
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+		info |= FIELD_PREP(MT_DMA_CTL_SDP0_H, buf[0].addr >> 32);
+#endif
 		if (i < nbufs - 1) {
 			entry->dma_addr[1] = buf[1].addr;
 			entry->dma_len[1] = buf[1].len;
 			buf1 = buf[1].addr;
 			ctrl |= FIELD_PREP(MT_DMA_CTL_SD_LEN1, buf[1].len);
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+			info |= FIELD_PREP(MT_DMA_CTL_SDP1_H,
+					   buf[1].addr >> 32);
+#endif
 			if (buf[1].skip_unmap)
 				entry->skip_buf1 = true;
 		}
@@ -343,7 +377,7 @@ static void
 mt76_dma_kick_queue(struct mt76_dev *dev, struct mt76_queue *q)
 {
 	wmb();
-	Q_WRITE(dev, q, cpu_idx, q->head);
+	Q_WRITE(q, cpu_idx, q->head);
 }
 
 static void
@@ -359,7 +393,7 @@ mt76_dma_tx_cleanup(struct mt76_dev *dev, struct mt76_queue *q, bool flush)
 	if (flush)
 		last = -1;
 	else
-		last = Q_READ(dev, q, dma_idx);
+		last = Q_READ(q, dma_idx);
 
 	while (q->queued > 0 && q->tail != last) {
 		mt76_dma_tx_cleanup_idx(dev, q, q->tail, &entry);
@@ -371,7 +405,7 @@ mt76_dma_tx_cleanup(struct mt76_dev *dev, struct mt76_queue *q, bool flush)
 		}
 
 		if (!flush && q->tail == last)
-			last = Q_READ(dev, q, dma_idx);
+			last = Q_READ(q, dma_idx);
 	}
 	spin_unlock_bh(&q->cleanup_lock);
 
@@ -392,19 +426,26 @@ mt76_dma_get_buf(struct mt76_dev *dev, struct mt76_queue *q, int idx,
 {
 	struct mt76_queue_entry *e = &q->entry[idx];
 	struct mt76_desc *desc = &q->desc[idx];
-	void *buf;
+	u32 ctrl, desc_info, buf1;
+	void *buf = e->buf;
+
+	if (mt76_queue_is_wed_rro_ind(q))
+		goto done;
 
+	ctrl = le32_to_cpu(READ_ONCE(desc->ctrl));
 	if (len) {
-		u32 ctrl = le32_to_cpu(READ_ONCE(desc->ctrl));
 		*len = FIELD_GET(MT_DMA_CTL_SD_LEN0, ctrl);
 		*more = !(ctrl & MT_DMA_CTL_LAST_SEC0);
 	}
 
+	desc_info = le32_to_cpu(desc->info);
 	if (info)
-		*info = le32_to_cpu(desc->info);
+		*info = desc_info;
+
+	buf1 = le32_to_cpu(desc->buf1);
+	mt76_dma_should_drop_buf(drop, ctrl, buf1, desc_info);
 
 	if (mt76_queue_is_wed_rx(q)) {
-		u32 buf1 = le32_to_cpu(desc->buf1);
 		u32 token = FIELD_GET(MT_DMA_CTL_TOKEN, buf1);
 		struct mt76_txwi_cache *t = mt76_rx_token_release(dev, token);
 
@@ -420,23 +461,16 @@ mt76_dma_get_buf(struct mt76_dev *dev, struct mt76_queue *q, int idx,
 		t->ptr = NULL;
 
 		mt76_put_rxwi(dev, t);
-
-		if (drop) {
-			u32 ctrl = le32_to_cpu(READ_ONCE(desc->ctrl));
-
-			*drop = !!(ctrl & (MT_DMA_CTL_TO_HOST_A |
-					   MT_DMA_CTL_DROP));
-
+		if (drop)
 			*drop |= !!(buf1 & MT_DMA_CTL_WO_DROP);
-		}
 	} else {
-		buf = e->buf;
-		e->buf = NULL;
 		dma_sync_single_for_cpu(dev->dma_dev, e->dma_addr[0],
 				SKB_WITH_OVERHEAD(q->buf_size),
 				page_pool_get_dma_dir(q->page_pool));
 	}
 
+done:
+	e->buf = NULL;
 	return buf;
 }
 
@@ -450,11 +484,16 @@ mt76_dma_dequeue(struct mt76_dev *dev, struct mt76_queue *q, bool flush,
 	if (!q->queued)
 		return NULL;
 
-	if (flush)
-		q->desc[idx].ctrl |= cpu_to_le32(MT_DMA_CTL_DMA_DONE);
-	else if (!(q->desc[idx].ctrl & cpu_to_le32(MT_DMA_CTL_DMA_DONE)))
+	if (mt76_queue_is_wed_rro_data(q))
 		return NULL;
 
+	if (!mt76_queue_is_wed_rro_ind(q)) {
+		if (flush)
+			q->desc[idx].ctrl |= cpu_to_le32(MT_DMA_CTL_DMA_DONE);
+		else if (!(q->desc[idx].ctrl & cpu_to_le32(MT_DMA_CTL_DMA_DONE)))
+			return NULL;
+	}
+
 	q->tail = (q->tail + 1) % q->ndesc;
 	q->queued--;
 
@@ -606,11 +645,14 @@ mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q,
 	spin_lock_bh(&q->lock);
 
 	while (q->queued < q->ndesc - 1) {
+		struct mt76_queue_buf qbuf = {};
 		enum dma_data_direction dir;
-		struct mt76_queue_buf qbuf;
 		dma_addr_t addr;
 		int offset;
-		void *buf;
+		void *buf = NULL;
+
+		if (mt76_queue_is_wed_rro_ind(q))
+			goto done;
 
 		buf = mt76_get_page_pool_buf(q, &offset, q->buf_size);
 		if (!buf)
@@ -621,6 +663,7 @@ mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q,
 		dma_sync_single_for_device(dev->dma_dev, addr, len, dir);
 
 		qbuf.addr = addr + q->buf_offset;
+done:
 		qbuf.len = len - q->buf_offset;
 		qbuf.skip_unmap = false;
 		if (mt76_dma_add_rx_buf(dev, q, &qbuf, buf) < 0) {
@@ -630,7 +673,7 @@ mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q,
 		frames++;
 	}
 
-	if (frames)
+	if (frames || mt76_queue_is_wed_rx(q))
 		mt76_dma_kick_queue(dev, q);
 
 	spin_unlock_bh(&q->lock);
@@ -641,15 +684,14 @@ mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q,
 int mt76_dma_wed_setup(struct mt76_dev *dev, struct mt76_queue *q, bool reset)
 {
 #ifdef CONFIG_NET_MEDIATEK_SOC_WED
-	struct mtk_wed_device *wed = &dev->mmio.wed;
-	int ret, type, ring;
-	u8 flags;
+	int ret = 0, type, ring;
+	u16 flags;
 
 	if (!q || !q->ndesc)
 		return -EINVAL;
 
 	flags = q->flags;
-	if (!mtk_wed_device_active(wed))
+	if (!q->wed || !mtk_wed_device_active(q->wed))
 		q->flags &= ~MT_QFLAG_WED;
 
 	if (!(q->flags & MT_QFLAG_WED))
@@ -660,29 +702,52 @@ int mt76_dma_wed_setup(struct mt76_dev *dev, struct mt76_queue *q, bool reset)
 
 	switch (type) {
 	case MT76_WED_Q_TX:
-		ret = mtk_wed_device_tx_ring_setup(wed, ring, q->regs, reset);
+		ret = mtk_wed_device_tx_ring_setup(q->wed, ring, q->regs,
+						   reset);
 		if (!ret)
-			q->wed_regs = wed->tx_ring[ring].reg_base;
+			q->wed_regs = q->wed->tx_ring[ring].reg_base;
 		break;
 	case MT76_WED_Q_TXFREE:
 		/* WED txfree queue needs ring to be initialized before setup */
 		q->flags = 0;
 		mt76_dma_queue_reset(dev, q);
 		mt76_dma_rx_fill(dev, q, false);
-		q->flags = flags;
 
-		ret = mtk_wed_device_txfree_ring_setup(wed, q->regs);
+		ret = mtk_wed_device_txfree_ring_setup(q->wed, q->regs);
 		if (!ret)
-			q->wed_regs = wed->txfree_ring.reg_base;
+			q->wed_regs = q->wed->txfree_ring.reg_base;
 		break;
 	case MT76_WED_Q_RX:
-		ret = mtk_wed_device_rx_ring_setup(wed, ring, q->regs, reset);
+		ret = mtk_wed_device_rx_ring_setup(q->wed, ring, q->regs,
+						   reset);
 		if (!ret)
-			q->wed_regs = wed->rx_ring[ring].reg_base;
+			q->wed_regs = q->wed->rx_ring[ring].reg_base;
+		break;
+	case MT76_WED_RRO_Q_DATA:
+		q->flags &= ~MT_QFLAG_WED;
+		__mt76_dma_queue_reset(dev, q, false);
+		mtk_wed_device_rro_rx_ring_setup(q->wed, ring, q->regs);
+		q->head = q->ndesc - 1;
+		q->queued = q->head;
+		break;
+	case MT76_WED_RRO_Q_MSDU_PG:
+		q->flags &= ~MT_QFLAG_WED;
+		__mt76_dma_queue_reset(dev, q, false);
+		mtk_wed_device_msdu_pg_rx_ring_setup(q->wed, ring, q->regs);
+		q->head = q->ndesc - 1;
+		q->queued = q->head;
+		break;
+	case MT76_WED_RRO_Q_IND:
+		q->flags &= ~MT_QFLAG_WED;
+		mt76_dma_queue_reset(dev, q);
+		mt76_dma_rx_fill(dev, q, false);
+		mtk_wed_device_ind_rx_ring_setup(q->wed, q->regs);
 		break;
 	default:
 		ret = -EINVAL;
+		break;
 	}
+	q->flags = flags;
 
 	return ret;
 #else
@@ -706,11 +771,26 @@ mt76_dma_alloc_queue(struct mt76_dev *dev, struct mt76_queue *q,
 	q->buf_size = bufsize;
 	q->hw_idx = idx;
 
-	size = q->ndesc * sizeof(struct mt76_desc);
-	q->desc = dmam_alloc_coherent(dev->dma_dev, size, &q->desc_dma, GFP_KERNEL);
+	size = mt76_queue_is_wed_rro_ind(q) ? sizeof(struct mt76_wed_rro_desc)
+					    : sizeof(struct mt76_desc);
+	q->desc = dmam_alloc_coherent(dev->dma_dev, q->ndesc * size,
+				      &q->desc_dma, GFP_KERNEL);
 	if (!q->desc)
 		return -ENOMEM;
 
+	if (mt76_queue_is_wed_rro_ind(q)) {
+		struct mt76_wed_rro_desc *rro_desc;
+		int i;
+
+		rro_desc = (struct mt76_wed_rro_desc *)q->desc;
+		for (i = 0; i < q->ndesc; i++) {
+			struct mt76_wed_rro_ind *cmd;
+
+			cmd = (struct mt76_wed_rro_ind *)&rro_desc[i];
+			cmd->magic_cnt = MT_DMA_WED_IND_CMD_CNT - 1;
+		}
+	}
+
 	size = q->ndesc * sizeof(*q->entry);
 	q->entry = devm_kzalloc(dev->dev, size, GFP_KERNEL);
 	if (!q->entry)
@@ -724,8 +804,13 @@ mt76_dma_alloc_queue(struct mt76_dev *dev, struct mt76_queue *q,
 	if (ret)
 		return ret;
 
-	if (q->flags != MT_WED_Q_TXFREE)
-		mt76_dma_queue_reset(dev, q);
+	if (mtk_wed_device_active(&dev->mmio.wed)) {
+		if ((mtk_wed_get_rx_capa(&dev->mmio.wed) && mt76_queue_is_wed_rro(q)) ||
+		    mt76_queue_is_wed_tx_free(q))
+			return 0;
+	}
+
+	mt76_dma_queue_reset(dev, q);
 
 	return 0;
 }
@@ -747,7 +832,8 @@ mt76_dma_rx_cleanup(struct mt76_dev *dev, struct mt76_queue *q)
 		if (!buf)
 			break;
 
-		mt76_put_page_pool_buf(buf, false);
+		if (!mt76_queue_is_wed_rro(q))
+			mt76_put_page_pool_buf(buf, false);
 	} while (1);
 
 	spin_lock_bh(&q->lock);
@@ -763,27 +849,36 @@ static void
 mt76_dma_rx_reset(struct mt76_dev *dev, enum mt76_rxq_id qid)
 {
 	struct mt76_queue *q = &dev->q_rx[qid];
-	int i;
 
 	if (!q->ndesc)
 		return;
 
-	for (i = 0; i < q->ndesc; i++)
-		q->desc[i].ctrl = cpu_to_le32(MT_DMA_CTL_DMA_DONE);
+	if (!mt76_queue_is_wed_rro_ind(q)) {
+		int i;
+
+		for (i = 0; i < q->ndesc; i++)
+			q->desc[i].ctrl = cpu_to_le32(MT_DMA_CTL_DMA_DONE);
+	}
 
 	mt76_dma_rx_cleanup(dev, q);
 
 	/* reset WED rx queues */
 	mt76_dma_wed_setup(dev, q, true);
-	if (q->flags != MT_WED_Q_TXFREE) {
-		mt76_dma_sync_idx(dev, q);
-		mt76_dma_rx_fill(dev, q, false);
-	}
+
+	if (mt76_queue_is_wed_tx_free(q))
+		return;
+
+	if (mtk_wed_device_active(&dev->mmio.wed) &&
+	    mt76_queue_is_wed_rro(q))
+		return;
+
+	mt76_dma_sync_idx(dev, q);
+	mt76_dma_rx_fill(dev, q, false);
 }
 
 static void
 mt76_add_fragment(struct mt76_dev *dev, struct mt76_queue *q, void *data,
-		  int len, bool more, u32 info)
+		  int len, bool more, u32 info, bool allow_direct)
 {
 	struct sk_buff *skb = q->rx_head;
 	struct skb_shared_info *shinfo = skb_shinfo(skb);
@@ -795,7 +890,7 @@ mt76_add_fragment(struct mt76_dev *dev, struct mt76_queue *q, void *data,
 
 		skb_add_rx_frag(skb, nr_frags, page, offset, len, q->buf_size);
 	} else {
-		mt76_put_page_pool_buf(data, true);
+		mt76_put_page_pool_buf(data, allow_direct);
 	}
 
 	if (more)
@@ -815,11 +910,12 @@ mt76_dma_rx_process(struct mt76_dev *dev, struct mt76_queue *q, int budget)
 	struct sk_buff *skb;
 	unsigned char *data;
 	bool check_ddone = false;
+	bool allow_direct = !mt76_queue_is_wed_rx(q);
 	bool more;
 
 	if (IS_ENABLED(CONFIG_NET_MEDIATEK_SOC_WED) &&
-	    q->flags == MT_WED_Q_TXFREE) {
-		dma_idx = Q_READ(dev, q, dma_idx);
+	    mt76_queue_is_wed_tx_free(q)) {
+		dma_idx = Q_READ(q, dma_idx);
 		check_ddone = true;
 	}
 
@@ -829,7 +925,7 @@ mt76_dma_rx_process(struct mt76_dev *dev, struct mt76_queue *q, int budget)
 
 		if (check_ddone) {
 			if (q->tail == dma_idx)
-				dma_idx = Q_READ(dev, q, dma_idx);
+				dma_idx = Q_READ(q, dma_idx);
 
 			if (q->tail == dma_idx)
 				break;
@@ -855,7 +951,8 @@ mt76_dma_rx_process(struct mt76_dev *dev, struct mt76_queue *q, int budget)
 		}
 
 		if (q->rx_head) {
-			mt76_add_fragment(dev, q, data, len, more, info);
+			mt76_add_fragment(dev, q, data, len, more, info,
+					  allow_direct);
 			continue;
 		}
 
@@ -884,7 +981,7 @@ mt76_dma_rx_process(struct mt76_dev *dev, struct mt76_queue *q, int budget)
 		continue;
 
 free_frag:
-		mt76_put_page_pool_buf(data, true);
+		mt76_put_page_pool_buf(data, allow_direct);
 	}
 
 	mt76_dma_rx_fill(dev, q, true);
@@ -957,6 +1054,20 @@ void mt76_dma_attach(struct mt76_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt76_dma_attach);
 
+void mt76_dma_wed_reset(struct mt76_dev *dev)
+{
+	struct mt76_mmio *mmio = &dev->mmio;
+
+	if (!test_bit(MT76_STATE_WED_RESET, &dev->phy.state))
+		return;
+
+	complete(&mmio->wed_reset);
+
+	if (!wait_for_completion_timeout(&mmio->wed_reset_complete, 3 * HZ))
+		dev_err(dev->dev, "wed reset complete timeout\n");
+}
+EXPORT_SYMBOL_GPL(mt76_dma_wed_reset);
+
 void mt76_dma_cleanup(struct mt76_dev *dev)
 {
 	int i;
@@ -981,16 +1092,23 @@ void mt76_dma_cleanup(struct mt76_dev *dev)
 	mt76_for_each_q_rx(dev, i) {
 		struct mt76_queue *q = &dev->q_rx[i];
 
+		if (mtk_wed_device_active(&dev->mmio.wed) &&
+		    mt76_queue_is_wed_rro(q))
+			continue;
+
 		netif_napi_del(&dev->napi[i]);
 		mt76_dma_rx_cleanup(dev, q);
 
 		page_pool_destroy(q->page_pool);
 	}
 
-	mt76_free_pending_txwi(dev);
-	mt76_free_pending_rxwi(dev);
-
 	if (mtk_wed_device_active(&dev->mmio.wed))
 		mtk_wed_device_detach(&dev->mmio.wed);
+
+	if (mtk_wed_device_active(&dev->mmio.wed_hif2))
+		mtk_wed_device_detach(&dev->mmio.wed_hif2);
+
+	mt76_free_pending_txwi(dev);
+	mt76_free_pending_rxwi(dev);
 }
 EXPORT_SYMBOL_GPL(mt76_dma_cleanup);
diff --git a/drivers/net/wireless/mediatek/mt76/dma.h b/drivers/net/wireless/mediatek/mt76/dma.h
index 1b090d78cd05..c479cc6388ef 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.h
+++ b/drivers/net/wireless/mediatek/mt76/dma.h
@@ -19,12 +19,23 @@
 #define MT_DMA_CTL_TO_HOST_A		BIT(12)
 #define MT_DMA_CTL_DROP			BIT(14)
 #define MT_DMA_CTL_TOKEN		GENMASK(31, 16)
+#define MT_DMA_CTL_SDP1_H		GENMASK(19, 16)
+#define MT_DMA_CTL_SDP0_H		GENMASK(3, 0)
 #define MT_DMA_CTL_WO_DROP		BIT(8)
 
 #define MT_DMA_PPE_CPU_REASON		GENMASK(15, 11)
 #define MT_DMA_PPE_ENTRY		GENMASK(30, 16)
+#define MT_DMA_INFO_DMA_FRAG		BIT(9)
 #define MT_DMA_INFO_PPE_VLD		BIT(31)
 
+#define MT_DMA_CTL_PN_CHK_FAIL		BIT(13)
+#define MT_DMA_CTL_VER_MASK		BIT(7)
+
+#define MT_DMA_RRO_EN		BIT(13)
+
+#define MT_DMA_WED_IND_CMD_CNT		8
+#define MT_DMA_WED_IND_REASON		GENMASK(15, 12)
+
 #define MT_DMA_HDR_LEN			4
 #define MT_RX_INFO_LEN			4
 #define MT_FCE_INFO_LEN			4
@@ -37,6 +48,11 @@ struct mt76_desc {
 	__le32 info;
 } __packed __aligned(4);
 
+struct mt76_wed_rro_desc {
+	__le32 buf0;
+	__le32 buf1;
+} __packed __aligned(4);
+
 enum mt76_qsel {
 	MT_QSEL_MGMT,
 	MT_QSEL_HCCA,
@@ -54,9 +70,47 @@ enum mt76_mcu_evt_type {
 	EVT_EVENT_DFS_DETECT_RSP,
 };
 
+enum mt76_dma_wed_ind_reason {
+	MT_DMA_WED_IND_REASON_NORMAL,
+	MT_DMA_WED_IND_REASON_REPEAT,
+	MT_DMA_WED_IND_REASON_OLDPKT,
+};
+
 int mt76_dma_rx_poll(struct napi_struct *napi, int budget);
 void mt76_dma_attach(struct mt76_dev *dev);
 void mt76_dma_cleanup(struct mt76_dev *dev);
 int mt76_dma_wed_setup(struct mt76_dev *dev, struct mt76_queue *q, bool reset);
+void mt76_dma_wed_reset(struct mt76_dev *dev);
+
+static inline void
+mt76_dma_reset_tx_queue(struct mt76_dev *dev, struct mt76_queue *q)
+{
+	dev->queue_ops->reset_q(dev, q);
+	if (mtk_wed_device_active(&dev->mmio.wed))
+		mt76_dma_wed_setup(dev, q, true);
+}
+
+static inline void
+mt76_dma_should_drop_buf(bool *drop, u32 ctrl, u32 buf1, u32 info)
+{
+	if (!drop)
+		return;
+
+	*drop = !!(ctrl & (MT_DMA_CTL_TO_HOST_A | MT_DMA_CTL_DROP));
+	if (!(ctrl & MT_DMA_CTL_VER_MASK))
+		return;
+
+	switch (FIELD_GET(MT_DMA_WED_IND_REASON, buf1)) {
+	case MT_DMA_WED_IND_REASON_REPEAT:
+		*drop = true;
+		break;
+	case MT_DMA_WED_IND_REASON_OLDPKT:
+		*drop = !(info & MT_DMA_INFO_DMA_FRAG);
+		break;
+	default:
+		*drop = !!(ctrl & MT_DMA_CTL_PN_CHK_FAIL);
+		break;
+	}
+}
 
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/eeprom.c b/drivers/net/wireless/mediatek/mt76/eeprom.c
index 7725dd6763ef..0bc66cc19acd 100644
--- a/drivers/net/wireless/mediatek/mt76/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/eeprom.c
@@ -28,7 +28,7 @@ static int mt76_get_of_eeprom_data(struct mt76_dev *dev, void *eep, int len)
 	return 0;
 }
 
-static int mt76_get_of_epprom_from_mtd(struct mt76_dev *dev, void *eep, int offset, int len)
+int mt76_get_of_data_from_mtd(struct mt76_dev *dev, void *eep, int offset, int len)
 {
 #ifdef CONFIG_MTD
 	struct device_node *np = dev->dev->of_node;
@@ -67,7 +67,7 @@ static int mt76_get_of_epprom_from_mtd(struct mt76_dev *dev, void *eep, int offs
 		goto out_put_node;
 	}
 
-	offset = be32_to_cpup(list);
+	offset += be32_to_cpup(list);
 	ret = mtd_read(mtd, offset, len, &retlen, eep);
 	put_mtd_device(mtd);
 	if (mtd_is_bitflip(ret))
@@ -105,8 +105,10 @@ out_put_node:
 	return -ENOENT;
 #endif
 }
+EXPORT_SYMBOL_GPL(mt76_get_of_data_from_mtd);
 
-static int mt76_get_of_epprom_from_nvmem(struct mt76_dev *dev, void *eep, int len)
+int mt76_get_of_data_from_nvmem(struct mt76_dev *dev, void *eep,
+				const char *cell_name, int len)
 {
 	struct device_node *np = dev->dev->of_node;
 	struct nvmem_cell *cell;
@@ -114,7 +116,7 @@ static int mt76_get_of_epprom_from_nvmem(struct mt76_dev *dev, void *eep, int le
 	size_t retlen;
 	int ret = 0;
 
-	cell = of_nvmem_cell_get(np, "eeprom");
+	cell = of_nvmem_cell_get(np, cell_name);
 	if (IS_ERR(cell))
 		return PTR_ERR(cell);
 
@@ -136,8 +138,9 @@ exit:
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(mt76_get_of_data_from_nvmem);
 
-int mt76_get_of_eeprom(struct mt76_dev *dev, void *eep, int offset, int len)
+static int mt76_get_of_eeprom(struct mt76_dev *dev, void *eep, int len)
 {
 	struct device_node *np = dev->dev->of_node;
 	int ret;
@@ -149,13 +152,12 @@ int mt76_get_of_eeprom(struct mt76_dev *dev, void *eep, int offset, int len)
 	if (!ret)
 		return 0;
 
-	ret = mt76_get_of_epprom_from_mtd(dev, eep, offset, len);
+	ret = mt76_get_of_data_from_mtd(dev, eep, 0, len);
 	if (!ret)
 		return 0;
 
-	return mt76_get_of_epprom_from_nvmem(dev, eep, len);
+	return mt76_get_of_data_from_nvmem(dev, eep, "eeprom", len);
 }
-EXPORT_SYMBOL_GPL(mt76_get_of_eeprom);
 
 void
 mt76_eeprom_override(struct mt76_phy *phy)
@@ -379,7 +381,7 @@ s8 mt76_get_rate_power_limits(struct mt76_phy *phy,
 	if (!np)
 		return target_power;
 
-	txs_delta = mt76_get_txs_delta(np, hweight8(phy->antenna_mask));
+	txs_delta = mt76_get_txs_delta(np, hweight16(phy->chainmask));
 
 	val = mt76_get_of_array(np, "rates-cck", &len, ARRAY_SIZE(dest->cck));
 	mt76_apply_array_limit(dest->cck, ARRAY_SIZE(dest->cck), val,
@@ -412,6 +414,6 @@ mt76_eeprom_init(struct mt76_dev *dev, int len)
 	if (!dev->eeprom.data)
 		return -ENOMEM;
 
-	return !mt76_get_of_eeprom(dev, dev->eeprom.data, 0, len);
+	return !mt76_get_of_eeprom(dev, dev->eeprom.data, len);
 }
 EXPORT_SYMBOL_GPL(mt76_eeprom_init);
diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index 51a767121b0d..8a3a90d1bfac 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -197,10 +197,33 @@ static int mt76_led_init(struct mt76_phy *phy)
 {
 	struct mt76_dev *dev = phy->dev;
 	struct ieee80211_hw *hw = phy->hw;
+	struct device_node *np = dev->dev->of_node;
 
 	if (!phy->leds.cdev.brightness_set && !phy->leds.cdev.blink_set)
 		return 0;
 
+	np = of_get_child_by_name(np, "led");
+	if (np) {
+		if (!of_device_is_available(np)) {
+			of_node_put(np);
+			dev_info(dev->dev,
+				"led registration was explicitly disabled by dts\n");
+			return 0;
+		}
+
+		if (phy == &dev->phy) {
+			int led_pin;
+
+			if (!of_property_read_u32(np, "led-sources", &led_pin))
+				phy->leds.pin = led_pin;
+
+			phy->leds.al =
+				of_property_read_bool(np, "led-active-low");
+		}
+
+		of_node_put(np);
+	}
+
 	snprintf(phy->leds.name, sizeof(phy->leds.name), "mt76-%s",
 		 wiphy_name(hw->wiphy));
 
@@ -211,20 +234,8 @@ static int mt76_led_init(struct mt76_phy *phy)
 					mt76_tpt_blink,
 					ARRAY_SIZE(mt76_tpt_blink));
 
-	if (phy == &dev->phy) {
-		struct device_node *np = dev->dev->of_node;
-
-		np = of_get_child_by_name(np, "led");
-		if (np) {
-			int led_pin;
-
-			if (!of_property_read_u32(np, "led-sources", &led_pin))
-				phy->leds.pin = led_pin;
-			phy->leds.al = of_property_read_bool(np,
-							     "led-active-low");
-			of_node_put(np);
-		}
-	}
+	dev_info(dev->dev,
+		"registering led '%s'\n", phy->leds.name);
 
 	return led_classdev_register(dev->dev, &phy->leds.cdev);
 }
@@ -1537,7 +1548,7 @@ int mt76_get_txpower(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		     int *dbm)
 {
 	struct mt76_phy *phy = hw->priv;
-	int n_chains = hweight8(phy->antenna_mask);
+	int n_chains = hweight16(phy->chainmask);
 	int delta = mt76_tx_power_nss_delta(n_chains);
 
 	*dbm = DIV_ROUND_UP(phy->txpower_cur + delta, 2);
@@ -1725,7 +1736,7 @@ EXPORT_SYMBOL_GPL(mt76_get_antenna);
 
 struct mt76_queue *
 mt76_init_queue(struct mt76_dev *dev, int qid, int idx, int n_desc,
-		int ring_base, u32 flags)
+		int ring_base, void *wed, u32 flags)
 {
 	struct mt76_queue *hwq;
 	int err;
@@ -1735,6 +1746,7 @@ mt76_init_queue(struct mt76_dev *dev, int qid, int idx, int n_desc,
 		return ERR_PTR(-ENOMEM);
 
 	hwq->flags = flags;
+	hwq->wed = wed;
 
 	err = dev->queue_ops->alloc(dev, hwq, idx, n_desc, 0, ring_base);
 	if (err < 0)
@@ -1842,3 +1854,19 @@ enum mt76_dfs_state mt76_phy_dfs_state(struct mt76_phy *phy)
 	return MT_DFS_STATE_ACTIVE;
 }
 EXPORT_SYMBOL_GPL(mt76_phy_dfs_state);
+
+#ifdef CONFIG_NET_MEDIATEK_SOC_WED
+int mt76_net_setup_tc(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		      struct net_device *netdev, enum tc_setup_type type,
+		      void *type_data)
+{
+	struct mt76_phy *phy = hw->priv;
+	struct mtk_wed_device *wed = &phy->dev->mmio.wed;
+
+	if (!mtk_wed_device_active(wed))
+		return -EOPNOTSUPP;
+
+	return mtk_wed_device_setup_tc(wed, netdev, type, type_data);
+}
+EXPORT_SYMBOL_GPL(mt76_net_setup_tc);
+#endif /* CONFIG_NET_MEDIATEK_SOC_WED */
diff --git a/drivers/net/wireless/mediatek/mt76/mmio.c b/drivers/net/wireless/mediatek/mt76/mmio.c
index 86e3d2ac4d0d..c3e0e23e0161 100644
--- a/drivers/net/wireless/mediatek/mt76/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mmio.c
@@ -4,6 +4,7 @@
  */
 
 #include "mt76.h"
+#include "dma.h"
 #include "trace.h"
 
 static u32 mt76_mmio_rr(struct mt76_dev *dev, u32 offset)
@@ -84,6 +85,113 @@ void mt76_set_irq_mask(struct mt76_dev *dev, u32 addr,
 }
 EXPORT_SYMBOL_GPL(mt76_set_irq_mask);
 
+#ifdef CONFIG_NET_MEDIATEK_SOC_WED
+void mt76_mmio_wed_release_rx_buf(struct mtk_wed_device *wed)
+{
+	struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed);
+	int i;
+
+	for (i = 0; i < dev->rx_token_size; i++) {
+		struct mt76_txwi_cache *t;
+
+		t = mt76_rx_token_release(dev, i);
+		if (!t || !t->ptr)
+			continue;
+
+		mt76_put_page_pool_buf(t->ptr, false);
+		t->ptr = NULL;
+
+		mt76_put_rxwi(dev, t);
+	}
+
+	mt76_free_pending_rxwi(dev);
+}
+EXPORT_SYMBOL_GPL(mt76_mmio_wed_release_rx_buf);
+
+u32 mt76_mmio_wed_init_rx_buf(struct mtk_wed_device *wed, int size)
+{
+	struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed);
+	struct mtk_wed_bm_desc *desc = wed->rx_buf_ring.desc;
+	struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN];
+	int i, len = SKB_WITH_OVERHEAD(q->buf_size);
+	struct mt76_txwi_cache *t = NULL;
+
+	for (i = 0; i < size; i++) {
+		enum dma_data_direction dir;
+		dma_addr_t addr;
+		u32 offset;
+		int token;
+		void *buf;
+
+		t = mt76_get_rxwi(dev);
+		if (!t)
+			goto unmap;
+
+		buf = mt76_get_page_pool_buf(q, &offset, q->buf_size);
+		if (!buf)
+			goto unmap;
+
+		addr = page_pool_get_dma_addr(virt_to_head_page(buf)) + offset;
+		dir = page_pool_get_dma_dir(q->page_pool);
+		dma_sync_single_for_device(dev->dma_dev, addr, len, dir);
+
+		desc->buf0 = cpu_to_le32(addr);
+		token = mt76_rx_token_consume(dev, buf, t, addr);
+		if (token < 0) {
+			mt76_put_page_pool_buf(buf, false);
+			goto unmap;
+		}
+
+		token = FIELD_PREP(MT_DMA_CTL_TOKEN, token);
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+		token |= FIELD_PREP(MT_DMA_CTL_SDP0_H, addr >> 32);
+#endif
+		desc->token |= cpu_to_le32(token);
+		desc++;
+	}
+
+	return 0;
+
+unmap:
+	if (t)
+		mt76_put_rxwi(dev, t);
+	mt76_mmio_wed_release_rx_buf(wed);
+
+	return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(mt76_mmio_wed_init_rx_buf);
+
+int mt76_mmio_wed_offload_enable(struct mtk_wed_device *wed)
+{
+	struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed);
+
+	spin_lock_bh(&dev->token_lock);
+	dev->token_size = wed->wlan.token_start;
+	spin_unlock_bh(&dev->token_lock);
+
+	return !wait_event_timeout(dev->tx_wait, !dev->wed_token_count, HZ);
+}
+EXPORT_SYMBOL_GPL(mt76_mmio_wed_offload_enable);
+
+void mt76_mmio_wed_offload_disable(struct mtk_wed_device *wed)
+{
+	struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed);
+
+	spin_lock_bh(&dev->token_lock);
+	dev->token_size = dev->drv->token_size;
+	spin_unlock_bh(&dev->token_lock);
+}
+EXPORT_SYMBOL_GPL(mt76_mmio_wed_offload_disable);
+
+void mt76_mmio_wed_reset_complete(struct mtk_wed_device *wed)
+{
+	struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed);
+
+	complete(&dev->mmio.wed_reset_complete);
+}
+EXPORT_SYMBOL_GPL(mt76_mmio_wed_reset_complete);
+#endif /*CONFIG_NET_MEDIATEK_SOC_WED */
+
 void mt76_mmio_init(struct mt76_dev *dev, void __iomem *regs)
 {
 	static const struct mt76_bus_ops mt76_mmio_ops = {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index ea828ba0b83a..b20c34d5a0f7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -29,15 +29,22 @@
 #define MT76_TOKEN_FREE_THR	64
 
 #define MT_QFLAG_WED_RING	GENMASK(1, 0)
-#define MT_QFLAG_WED_TYPE	GENMASK(3, 2)
-#define MT_QFLAG_WED		BIT(4)
+#define MT_QFLAG_WED_TYPE	GENMASK(4, 2)
+#define MT_QFLAG_WED		BIT(5)
+#define MT_QFLAG_WED_RRO	BIT(6)
+#define MT_QFLAG_WED_RRO_EN	BIT(7)
 
 #define __MT_WED_Q(_type, _n)	(MT_QFLAG_WED | \
 				 FIELD_PREP(MT_QFLAG_WED_TYPE, _type) | \
 				 FIELD_PREP(MT_QFLAG_WED_RING, _n))
+#define __MT_WED_RRO_Q(_type, _n)	(MT_QFLAG_WED_RRO | __MT_WED_Q(_type, _n))
+
 #define MT_WED_Q_TX(_n)		__MT_WED_Q(MT76_WED_Q_TX, _n)
 #define MT_WED_Q_RX(_n)		__MT_WED_Q(MT76_WED_Q_RX, _n)
 #define MT_WED_Q_TXFREE		__MT_WED_Q(MT76_WED_Q_TXFREE, 0)
+#define MT_WED_RRO_Q_DATA(_n)	__MT_WED_RRO_Q(MT76_WED_RRO_Q_DATA, _n)
+#define MT_WED_RRO_Q_MSDU_PG(_n)	__MT_WED_RRO_Q(MT76_WED_RRO_Q_MSDU_PG, _n)
+#define MT_WED_RRO_Q_IND	__MT_WED_RRO_Q(MT76_WED_RRO_Q_IND, 0)
 
 struct mt76_dev;
 struct mt76_phy;
@@ -59,6 +66,9 @@ enum mt76_wed_type {
 	MT76_WED_Q_TX,
 	MT76_WED_Q_TXFREE,
 	MT76_WED_Q_RX,
+	MT76_WED_RRO_Q_DATA,
+	MT76_WED_RRO_Q_MSDU_PG,
+	MT76_WED_RRO_Q_IND,
 };
 
 struct mt76_bus_ops {
@@ -107,6 +117,16 @@ enum mt76_rxq_id {
 	MT_RXQ_MAIN_WA,
 	MT_RXQ_BAND2,
 	MT_RXQ_BAND2_WA,
+	MT_RXQ_RRO_BAND0,
+	MT_RXQ_RRO_BAND1,
+	MT_RXQ_RRO_BAND2,
+	MT_RXQ_MSDU_PAGE_BAND0,
+	MT_RXQ_MSDU_PAGE_BAND1,
+	MT_RXQ_MSDU_PAGE_BAND2,
+	MT_RXQ_TXFREE_BAND0,
+	MT_RXQ_TXFREE_BAND1,
+	MT_RXQ_TXFREE_BAND2,
+	MT_RXQ_RRO_IND,
 	__MT_RXQ_MAX
 };
 
@@ -163,7 +183,7 @@ struct mt76_queue_entry {
 		struct urb *urb;
 		int buf_sz;
 	};
-	u32 dma_addr[2];
+	dma_addr_t dma_addr[2];
 	u16 dma_len[2];
 	u16 wcid;
 	bool skip_buf0:1;
@@ -184,6 +204,7 @@ struct mt76_queue {
 	spinlock_t lock;
 	spinlock_t cleanup_lock;
 	struct mt76_queue_entry *entry;
+	struct mt76_rro_desc *rro_desc;
 	struct mt76_desc *desc;
 
 	u16 first;
@@ -197,8 +218,9 @@ struct mt76_queue {
 
 	u8 buf_offset;
 	u8 hw_idx;
-	u8 flags;
+	u16 flags;
 
+	struct mtk_wed_device *wed;
 	u32 wed_regs;
 
 	dma_addr_t desc_dma;
@@ -353,6 +375,17 @@ struct mt76_txq {
 	bool aggr;
 };
 
+struct mt76_wed_rro_ind {
+	u32 se_id	: 12;
+	u32 rsv		: 4;
+	u32 start_sn	: 12;
+	u32 ind_reason	: 4;
+	u32 ind_cnt	: 13;
+	u32 win_sz	: 3;
+	u32 rsv2	: 13;
+	u32 magic_cnt	: 3;
+};
+
 struct mt76_txwi_cache {
 	struct list_head list;
 	dma_addr_t dma_addr;
@@ -371,6 +404,7 @@ struct mt76_rx_tid {
 	spinlock_t lock;
 	struct delayed_work reorder_work;
 
+	u16 id;
 	u16 head;
 	u16 size;
 	u16 nframes;
@@ -575,8 +609,7 @@ struct mt76_sdio {
 	struct mt76_worker txrx_worker;
 	struct mt76_worker status_worker;
 	struct mt76_worker net_worker;
-
-	struct work_struct stat_work;
+	struct mt76_worker stat_worker;
 
 	u8 *xmit_buf;
 	u32 xmit_buf_sz;
@@ -603,6 +636,7 @@ struct mt76_mmio {
 	u32 irqmask;
 
 	struct mtk_wed_device wed;
+	struct mtk_wed_device wed_hif2;
 	struct completion wed_reset;
 	struct completion wed_reset_complete;
 };
@@ -1047,6 +1081,12 @@ bool ____mt76_poll_msec(struct mt76_dev *dev, u32 offset, u32 mask, u32 val,
 void mt76_mmio_init(struct mt76_dev *dev, void __iomem *regs);
 void mt76_pci_disable_aspm(struct pci_dev *pdev);
 
+#ifdef CONFIG_NET_MEDIATEK_SOC_WED
+int mt76_net_setup_tc(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		      struct net_device *netdev, enum tc_setup_type type,
+		      void *type_data);
+#endif /*CONFIG_NET_MEDIATEK_SOC_WED */
+
 static inline u16 mt76_chip(struct mt76_dev *dev)
 {
 	return dev->rev >> 16;
@@ -1057,6 +1097,14 @@ static inline u16 mt76_rev(struct mt76_dev *dev)
 	return dev->rev & 0xffff;
 }
 
+#ifdef CONFIG_NET_MEDIATEK_SOC_WED
+u32 mt76_mmio_wed_init_rx_buf(struct mtk_wed_device *wed, int size);
+void mt76_mmio_wed_release_rx_buf(struct mtk_wed_device *wed);
+int mt76_mmio_wed_offload_enable(struct mtk_wed_device *wed);
+void mt76_mmio_wed_offload_disable(struct mtk_wed_device *wed);
+void mt76_mmio_wed_reset_complete(struct mtk_wed_device *wed);
+#endif /*CONFIG_NET_MEDIATEK_SOC_WED */
+
 #define mt76xx_chip(dev) mt76_chip(&((dev)->mt76))
 #define mt76xx_rev(dev) mt76_rev(&((dev)->mt76))
 
@@ -1102,19 +1150,22 @@ void mt76_seq_puts_array(struct seq_file *file, const char *str,
 
 int mt76_eeprom_init(struct mt76_dev *dev, int len);
 void mt76_eeprom_override(struct mt76_phy *phy);
-int mt76_get_of_eeprom(struct mt76_dev *dev, void *data, int offset, int len);
+int mt76_get_of_data_from_mtd(struct mt76_dev *dev, void *eep, int offset, int len);
+int mt76_get_of_data_from_nvmem(struct mt76_dev *dev, void *eep,
+				const char *cell_name, int len);
 
 struct mt76_queue *
 mt76_init_queue(struct mt76_dev *dev, int qid, int idx, int n_desc,
-		int ring_base, u32 flags);
+		int ring_base, void *wed, u32 flags);
 u16 mt76_calculate_default_rate(struct mt76_phy *phy,
 				struct ieee80211_vif *vif, int rateidx);
 static inline int mt76_init_tx_queue(struct mt76_phy *phy, int qid, int idx,
-				     int n_desc, int ring_base, u32 flags)
+				     int n_desc, int ring_base, void *wed,
+				     u32 flags)
 {
 	struct mt76_queue *q;
 
-	q = mt76_init_queue(phy->dev, qid, idx, n_desc, ring_base, flags);
+	q = mt76_init_queue(phy->dev, qid, idx, n_desc, ring_base, wed, flags);
 	if (IS_ERR(q))
 		return PTR_ERR(q);
 
@@ -1128,7 +1179,7 @@ static inline int mt76_init_mcu_queue(struct mt76_dev *dev, int qid, int idx,
 {
 	struct mt76_queue *q;
 
-	q = mt76_init_queue(dev, qid, idx, n_desc, ring_base, 0);
+	q = mt76_init_queue(dev, qid, idx, n_desc, ring_base, NULL, 0);
 	if (IS_ERR(q))
 		return PTR_ERR(q);
 
@@ -1547,10 +1598,38 @@ s8 mt76_get_rate_power_limits(struct mt76_phy *phy,
 			      struct mt76_power_limits *dest,
 			      s8 target_power);
 
-static inline bool mt76_queue_is_wed_rx(struct mt76_queue *q)
+static inline bool mt76_queue_is_wed_tx_free(struct mt76_queue *q)
 {
 	return (q->flags & MT_QFLAG_WED) &&
-	       FIELD_GET(MT_QFLAG_WED_TYPE, q->flags) == MT76_WED_Q_RX;
+	       FIELD_GET(MT_QFLAG_WED_TYPE, q->flags) == MT76_WED_Q_TXFREE;
+}
+
+static inline bool mt76_queue_is_wed_rro(struct mt76_queue *q)
+{
+	return q->flags & MT_QFLAG_WED_RRO;
+}
+
+static inline bool mt76_queue_is_wed_rro_ind(struct mt76_queue *q)
+{
+	return mt76_queue_is_wed_rro(q) &&
+	       FIELD_GET(MT_QFLAG_WED_TYPE, q->flags) == MT76_WED_RRO_Q_IND;
+}
+
+static inline bool mt76_queue_is_wed_rro_data(struct mt76_queue *q)
+{
+	return mt76_queue_is_wed_rro(q) &&
+	       (FIELD_GET(MT_QFLAG_WED_TYPE, q->flags) == MT76_WED_RRO_Q_DATA ||
+		FIELD_GET(MT_QFLAG_WED_TYPE, q->flags) == MT76_WED_RRO_Q_MSDU_PG);
+}
+
+static inline bool mt76_queue_is_wed_rx(struct mt76_queue *q)
+{
+	if (!(q->flags & MT_QFLAG_WED))
+		return false;
+
+	return FIELD_GET(MT_QFLAG_WED_TYPE, q->flags) == MT76_WED_Q_RX ||
+	       mt76_queue_is_wed_rro_ind(q) || mt76_queue_is_wed_rro_data(q);
+
 }
 
 struct mt76_txwi_cache *
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c
index 03ba11a61c90..7a2f5d38562b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c
@@ -173,13 +173,14 @@ int mt7603_dma_init(struct mt7603_dev *dev)
 
 	for (i = 0; i < ARRAY_SIZE(wmm_queue_map); i++) {
 		ret = mt76_init_tx_queue(&dev->mphy, i, wmm_queue_map[i],
-					 MT7603_TX_RING_SIZE, MT_TX_RING_BASE, 0);
+					 MT7603_TX_RING_SIZE, MT_TX_RING_BASE,
+					 NULL, 0);
 		if (ret)
 			return ret;
 	}
 
 	ret = mt76_init_tx_queue(&dev->mphy, MT_TXQ_PSD, MT_TX_HW_QUEUE_MGMT,
-				 MT7603_PSD_RING_SIZE, MT_TX_RING_BASE, 0);
+				 MT7603_PSD_RING_SIZE, MT_TX_RING_BASE, NULL, 0);
 	if (ret)
 		return ret;
 
@@ -189,12 +190,12 @@ int mt7603_dma_init(struct mt7603_dev *dev)
 		return ret;
 
 	ret = mt76_init_tx_queue(&dev->mphy, MT_TXQ_BEACON, MT_TX_HW_QUEUE_BCN,
-				 MT_MCU_RING_SIZE, MT_TX_RING_BASE, 0);
+				 MT_MCU_RING_SIZE, MT_TX_RING_BASE, NULL, 0);
 	if (ret)
 		return ret;
 
 	ret = mt76_init_tx_queue(&dev->mphy, MT_TXQ_CAB, MT_TX_HW_QUEUE_BMC,
-				 MT_MCU_RING_SIZE, MT_TX_RING_BASE, 0);
+				 MT_MCU_RING_SIZE, MT_TX_RING_BASE, NULL, 0);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/soc.c b/drivers/net/wireless/mediatek/mt76/mt7603/soc.c
index ba927033bbe8..ec02148a7f1f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/soc.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/soc.c
@@ -52,15 +52,12 @@ error:
 	return ret;
 }
 
-static int
-mt76_wmac_remove(struct platform_device *pdev)
+static void mt76_wmac_remove(struct platform_device *pdev)
 {
 	struct mt76_dev *mdev = platform_get_drvdata(pdev);
 	struct mt7603_dev *dev = container_of(mdev, struct mt7603_dev, mt76);
 
 	mt7603_unregister_device(dev);
-
-	return 0;
 }
 
 static const struct of_device_id of_wmac_match[] = {
@@ -74,7 +71,7 @@ MODULE_FIRMWARE(MT7628_FIRMWARE_E2);
 
 struct platform_driver mt76_wmac_driver = {
 	.probe		= mt76_wmac_probe,
-	.remove		= mt76_wmac_remove,
+	.remove_new	= mt76_wmac_remove,
 	.driver = {
 		.name = "mt76_wmac",
 		.of_match_table = of_wmac_match,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/dma.c b/drivers/net/wireless/mediatek/mt76/mt7615/dma.c
index 0ce01ccc5dce..e7135b2f1742 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/dma.c
@@ -26,14 +26,14 @@ mt7622_init_tx_queues_multi(struct mt7615_dev *dev)
 	for (i = 0; i < ARRAY_SIZE(wmm_queue_map); i++) {
 		ret = mt76_init_tx_queue(&dev->mphy, i, wmm_queue_map[i],
 					 MT7615_TX_RING_SIZE / 2,
-					 MT_TX_RING_BASE, 0);
+					 MT_TX_RING_BASE, NULL, 0);
 		if (ret)
 			return ret;
 	}
 
 	ret = mt76_init_tx_queue(&dev->mphy, MT_TXQ_PSD, MT7622_TXQ_MGMT,
 				 MT7615_TX_MGMT_RING_SIZE,
-				 MT_TX_RING_BASE, 0);
+				 MT_TX_RING_BASE, NULL, 0);
 	if (ret)
 		return ret;
 
@@ -55,7 +55,7 @@ mt7615_init_tx_queues(struct mt7615_dev *dev)
 		return mt7622_init_tx_queues_multi(dev);
 
 	ret = mt76_connac_init_tx_queues(&dev->mphy, 0, MT7615_TX_RING_SIZE,
-					 MT_TX_RING_BASE, 0);
+					 MT_TX_RING_BASE, NULL, 0);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
index 955974a82180..ae34d019e588 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
@@ -453,7 +453,7 @@ mt7615_mcu_scan_event(struct mt7615_dev *dev, struct sk_buff *skb)
 	else
 		mphy = &dev->mt76.phy;
 
-	phy = (struct mt7615_phy *)mphy->priv;
+	phy = mphy->priv;
 
 	spin_lock_bh(&dev->mt76.lock);
 	__skb_queue_tail(&phy->scan_event_list, skb);
@@ -481,7 +481,7 @@ mt7615_mcu_roc_event(struct mt7615_dev *dev, struct sk_buff *skb)
 
 	ieee80211_ready_on_channel(mphy->hw);
 
-	phy = (struct mt7615_phy *)mphy->priv;
+	phy = mphy->priv;
 	phy->roc_grant = true;
 	wake_up(&phy->roc_wait);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c
index fc547a0031ea..67cedd2555f9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c
@@ -204,8 +204,8 @@ static int mt7663s_suspend(struct device *dev)
 	mt76_worker_disable(&mdev->mt76.sdio.txrx_worker);
 	mt76_worker_disable(&mdev->mt76.sdio.status_worker);
 	mt76_worker_disable(&mdev->mt76.sdio.net_worker);
+	mt76_worker_disable(&mdev->mt76.sdio.stat_worker);
 
-	cancel_work_sync(&mdev->mt76.sdio.stat_work);
 	clear_bit(MT76_READING_STATS, &mdev->mphy.state);
 
 	mt76_tx_status_check(&mdev->mt76, true);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/soc.c b/drivers/net/wireless/mediatek/mt76/mt7615/soc.c
index f13d1b418742..12e3e4a91d27 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/soc.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/soc.c
@@ -45,13 +45,11 @@ static int mt7622_wmac_probe(struct platform_device *pdev)
 	return mt7615_mmio_probe(&pdev->dev, mem_base, irq, mt7615e_reg_map);
 }
 
-static int mt7622_wmac_remove(struct platform_device *pdev)
+static void mt7622_wmac_remove(struct platform_device *pdev)
 {
 	struct mt7615_dev *dev = platform_get_drvdata(pdev);
 
 	mt7615_unregister_device(dev);
-
-	return 0;
 }
 
 static const struct of_device_id mt7622_wmac_of_match[] = {
@@ -65,7 +63,7 @@ struct platform_driver mt7622_wmac_driver = {
 		.of_match_table = mt7622_wmac_of_match,
 	},
 	.probe = mt7622_wmac_probe,
-	.remove = mt7622_wmac_remove,
+	.remove_new = mt7622_wmac_remove,
 };
 
 MODULE_FIRMWARE(MT7622_FIRMWARE_N9);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac.h
index 1f29d8cd900c..fdde3d70b300 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac.h
@@ -222,6 +222,11 @@ static inline bool is_mt7996(struct mt76_dev *dev)
 	return mt76_chip(dev) == 0x7990;
 }
 
+static inline bool is_mt7992(struct mt76_dev *dev)
+{
+	return mt76_chip(dev) == 0x7992;
+}
+
 static inline bool is_mt7622(struct mt76_dev *dev)
 {
 	if (!IS_ENABLED(CONFIG_MT7622_WMAC))
@@ -391,7 +396,8 @@ mt76_connac_mutex_release(struct mt76_dev *dev, struct mt76_connac_pm *pm)
 
 void mt76_connac_gen_ppe_thresh(u8 *he_ppet, int nss);
 int mt76_connac_init_tx_queues(struct mt76_phy *phy, int idx, int n_desc,
-			       int ring_base, u32 flags);
+			       int ring_base, void *wed, u32 flags);
+
 void mt76_connac_write_hw_txp(struct mt76_dev *dev,
 			      struct mt76_tx_info *tx_info,
 			      void *txp_ptr, u32 id);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
index 2250252b2047..83dcd964bfd0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
@@ -239,11 +239,13 @@ enum tx_mgnt_type {
 
 #define MT_TXD6_TX_SRC			GENMASK(31, 30)
 #define MT_TXD6_VTA			BIT(28)
-#define MT_TXD6_BW			GENMASK(25, 22)
+#define MT_TXD6_FIXED_BW		BIT(25)
+#define MT_TXD6_BW			GENMASK(24, 22)
 #define MT_TXD6_TX_RATE			GENMASK(21, 16)
 #define MT_TXD6_TIMESTAMP_OFS_EN	BIT(15)
 #define MT_TXD6_TIMESTAMP_OFS_IDX	GENMASK(14, 10)
 #define MT_TXD6_MSDU_CNT		GENMASK(9, 4)
+#define MT_TXD6_MSDU_CNT_V2		GENMASK(15, 10)
 #define MT_TXD6_DIS_MAT			BIT(3)
 #define MT_TXD6_DAS			BIT(2)
 #define MT_TXD6_AMSDU_CAP		BIT(1)
@@ -259,6 +261,9 @@ enum tx_mgnt_type {
 
 #define MT_TXD9_WLAN_IDX		GENMASK(23, 8)
 
+#define MT_TXP_BUF_LEN			GENMASK(11, 0)
+#define MT_TXP_DMA_ADDR_H		GENMASK(15, 12)
+
 #define MT_TX_RATE_STBC			BIT(14)
 #define MT_TX_RATE_NSS			GENMASK(13, 10)
 #define MT_TX_RATE_MODE			GENMASK(9, 6)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
index 93402d2c2538..c7914643e9c0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
@@ -256,11 +256,12 @@ void mt76_connac_txp_skb_unmap(struct mt76_dev *dev,
 EXPORT_SYMBOL_GPL(mt76_connac_txp_skb_unmap);
 
 int mt76_connac_init_tx_queues(struct mt76_phy *phy, int idx, int n_desc,
-			       int ring_base, u32 flags)
+			       int ring_base, void *wed, u32 flags)
 {
 	int i, err;
 
-	err = mt76_init_tx_queue(phy, 0, idx, n_desc, ring_base, flags);
+	err = mt76_init_tx_queue(phy, 0, idx, n_desc, ring_base,
+				 wed, flags);
 	if (err < 0)
 		return err;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
index ae6bf3c968df..96494ba2fdf7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
@@ -67,7 +67,8 @@ int mt76_connac_mcu_init_download(struct mt76_dev *dev, u32 addr, u32 len,
 	if ((!is_connac_v1(dev) && addr == MCU_PATCH_ADDRESS) ||
 	    (is_mt7921(dev) && addr == 0x900000) ||
 	    (is_mt7925(dev) && addr == 0x900000) ||
-	    (is_mt7996(dev) && addr == 0x900000))
+	    (is_mt7996(dev) && addr == 0x900000) ||
+	    (is_mt7992(dev) && addr == 0x900000))
 		cmd = MCU_CMD(PATCH_START_REQ);
 	else
 		cmd = MCU_CMD(TARGET_ADDRESS_LEN_REQ);
@@ -1359,7 +1360,7 @@ u8 mt76_connac_get_phy_mode_ext(struct mt76_phy *phy, struct ieee80211_vif *vif,
 	sband = phy->hw->wiphy->bands[band];
 	eht_cap = ieee80211_get_eht_iftype_cap(sband, vif->type);
 
-	if (!eht_cap || !eht_cap->has_eht)
+	if (!eht_cap || !eht_cap->has_eht || !vif->bss_conf.eht_support)
 		return mode;
 
 	switch (band) {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
index 0563b1b22f48..ae6d0179727d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
@@ -416,6 +416,14 @@ struct sta_rec_he_6g_capa {
 	u8 rsv[2];
 } __packed;
 
+struct sta_rec_pn_info {
+	__le16 tag;
+	__le16 len;
+	u8 pn[6];
+	u8 tsc_type;
+	u8 rsv;
+} __packed;
+
 struct sec_key {
 	u8 cipher_id;
 	u8 cipher_len;
@@ -768,6 +776,7 @@ struct wtbl_raw {
 					 sizeof(struct sta_rec_sec) +	\
 					 sizeof(struct sta_rec_ra_fixed) + \
 					 sizeof(struct sta_rec_he_6g_capa) + \
+					 sizeof(struct sta_rec_pn_info) + \
 					 sizeof(struct tlv) +		\
 					 MT76_CONNAC_WTBL_UPDATE_MAX_SIZE)
 
@@ -798,6 +807,7 @@ enum {
 	STA_REC_HE_V2 = 0x19,
 	STA_REC_MLD = 0x20,
 	STA_REC_EHT = 0x22,
+	STA_REC_PN_INFO = 0x26,
 	STA_REC_HDRT = 0x28,
 	STA_REC_HDR_TRANS = 0x2B,
 	STA_REC_MAX_NUM
@@ -1021,7 +1031,9 @@ enum {
 	MCU_UNI_EVENT_RDD_REPORT = 0x11,
 	MCU_UNI_EVENT_ROC = 0x27,
 	MCU_UNI_EVENT_TX_DONE = 0x2d,
+	MCU_UNI_EVENT_THERMAL = 0x35,
 	MCU_UNI_EVENT_NIC_CAPAB = 0x43,
+	MCU_UNI_EVENT_WED_RRO = 0x57,
 	MCU_UNI_EVENT_PER_STA_INFO = 0x6d,
 	MCU_UNI_EVENT_ALL_STA_INFO = 0x6e,
 };
@@ -1088,6 +1100,13 @@ enum mcu_cipher_type {
 	MCU_CIPHER_GCMP_256,
 	MCU_CIPHER_WAPI,
 	MCU_CIPHER_BIP_CMAC_128,
+	MCU_CIPHER_BIP_CMAC_256,
+	MCU_CIPHER_BCN_PROT_CMAC_128,
+	MCU_CIPHER_BCN_PROT_CMAC_256,
+	MCU_CIPHER_BCN_PROT_GMAC_128,
+	MCU_CIPHER_BCN_PROT_GMAC_256,
+	MCU_CIPHER_BIP_GMAC_128,
+	MCU_CIPHER_BIP_GMAC_256,
 };
 
 enum {
@@ -1240,6 +1259,7 @@ enum {
 	MCU_UNI_CMD_CHANNEL_SWITCH = 0x34,
 	MCU_UNI_CMD_THERMAL = 0x35,
 	MCU_UNI_CMD_VOW = 0x37,
+	MCU_UNI_CMD_FIXED_RATE_TABLE = 0x40,
 	MCU_UNI_CMD_RRO = 0x57,
 	MCU_UNI_CMD_OFFCH_SCAN_CTRL = 0x58,
 	MCU_UNI_CMD_PER_STA_INFO = 0x6d,
@@ -1307,6 +1327,7 @@ enum {
 	UNI_BSS_INFO_RATE = 11,
 	UNI_BSS_INFO_QBSS = 15,
 	UNI_BSS_INFO_SEC = 16,
+	UNI_BSS_INFO_BCN_PROT = 17,
 	UNI_BSS_INFO_TXCMD = 18,
 	UNI_BSS_INFO_UAPSD = 19,
 	UNI_BSS_INFO_PS = 21,
@@ -1325,7 +1346,7 @@ enum {
 };
 
 enum UNI_ALL_STA_INFO_TAG {
-	UNI_ALL_STA_TX_RATE,
+	UNI_ALL_STA_TXRX_RATE,
 	UNI_ALL_STA_TX_STAT,
 	UNI_ALL_STA_TXRX_ADM_STAT,
 	UNI_ALL_STA_TXRX_AIR_TIME,
@@ -1768,6 +1789,12 @@ mt76_connac_mcu_get_cipher(int cipher)
 		return MCU_CIPHER_GCMP;
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		return MCU_CIPHER_GCMP_256;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+		return MCU_CIPHER_BIP_GMAC_128;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		return MCU_CIPHER_BIP_GMAC_256;
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+		return MCU_CIPHER_BIP_CMAC_256;
 	case WLAN_CIPHER_SUITE_SMS4:
 		return MCU_CIPHER_WAPI;
 	default:
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
index 9b5e3fb7b0df..e5ad635d3c56 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
@@ -199,13 +199,14 @@ int mt76x02_dma_init(struct mt76x02_dev *dev)
 	for (i = 0; i < IEEE80211_NUM_ACS; i++) {
 		ret = mt76_init_tx_queue(&dev->mphy, i, mt76_ac_to_hwq(i),
 					 MT76x02_TX_RING_SIZE,
-					 MT_TX_RING_BASE, 0);
+					 MT_TX_RING_BASE, NULL, 0);
 		if (ret)
 			return ret;
 	}
 
 	ret = mt76_init_tx_queue(&dev->mphy, MT_TXQ_PSD, MT_TX_HW_QUEUE_MGMT,
-				 MT76x02_PSD_RING_SIZE, MT_TX_RING_BASE, 0);
+				 MT76x02_PSD_RING_SIZE, MT_TX_RING_BASE,
+				 NULL, 0);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/dma.c b/drivers/net/wireless/mediatek/mt76/mt7915/dma.c
index 59a44d79aaed..c91a1c54027f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/dma.c
@@ -9,18 +9,20 @@ static int
 mt7915_init_tx_queues(struct mt7915_phy *phy, int idx, int n_desc, int ring_base)
 {
 	struct mt7915_dev *dev = phy->dev;
+	struct mtk_wed_device *wed = NULL;
 
-	if (mtk_wed_device_active(&phy->dev->mt76.mmio.wed)) {
+	if (mtk_wed_device_active(&dev->mt76.mmio.wed)) {
 		if (is_mt798x(&dev->mt76))
 			ring_base += MT_TXQ_ID(0) * MT_RING_SIZE;
 		else
 			ring_base = MT_WED_TX_RING_BASE;
 
 		idx -= MT_TXQ_ID(0);
+		wed = &dev->mt76.mmio.wed;
 	}
 
 	return mt76_connac_init_tx_queues(phy->mt76, idx, n_desc, ring_base,
-					  MT_WED_Q_TX(idx));
+					  wed, MT_WED_Q_TX(idx));
 }
 
 static int mt7915_poll_tx(struct napi_struct *napi, int budget)
@@ -492,7 +494,8 @@ int mt7915_dma_init(struct mt7915_dev *dev, struct mt7915_phy *phy2)
 	if (mtk_wed_device_active(&mdev->mmio.wed) && is_mt7915(mdev)) {
 		wa_rx_base = MT_WED_RX_RING_BASE;
 		wa_rx_idx = MT7915_RXQ_MCU_WA;
-		dev->mt76.q_rx[MT_RXQ_MCU_WA].flags = MT_WED_Q_TXFREE;
+		mdev->q_rx[MT_RXQ_MCU_WA].flags = MT_WED_Q_TXFREE;
+		mdev->q_rx[MT_RXQ_MCU_WA].wed = &mdev->mmio.wed;
 	} else {
 		wa_rx_base = MT_RXQ_RING_BASE(MT_RXQ_MCU_WA);
 		wa_rx_idx = MT_RXQ_ID(MT_RXQ_MCU_WA);
@@ -507,9 +510,10 @@ int mt7915_dma_init(struct mt7915_dev *dev, struct mt7915_phy *phy2)
 	if (!dev->phy.mt76->band_idx) {
 		if (mtk_wed_device_active(&mdev->mmio.wed) &&
 		    mtk_wed_get_rx_capa(&mdev->mmio.wed)) {
-			dev->mt76.q_rx[MT_RXQ_MAIN].flags =
+			mdev->q_rx[MT_RXQ_MAIN].flags =
 				MT_WED_Q_RX(MT7915_RXQ_BAND0);
 			dev->mt76.rx_token_size += MT7915_RX_RING_SIZE;
+			mdev->q_rx[MT_RXQ_MAIN].wed = &mdev->mmio.wed;
 		}
 
 		ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MAIN],
@@ -528,6 +532,7 @@ int mt7915_dma_init(struct mt7915_dev *dev, struct mt7915_phy *phy2)
 
 		if (mtk_wed_device_active(&mdev->mmio.wed)) {
 			mdev->q_rx[MT_RXQ_MAIN_WA].flags = MT_WED_Q_TXFREE;
+			mdev->q_rx[MT_RXQ_MAIN_WA].wed = &mdev->mmio.wed;
 			if (is_mt7916(mdev)) {
 				wa_rx_base =  MT_WED_RX_RING_BASE;
 				wa_rx_idx = MT7915_RXQ_MCU_WA;
@@ -544,9 +549,10 @@ int mt7915_dma_init(struct mt7915_dev *dev, struct mt7915_phy *phy2)
 	if (dev->dbdc_support || dev->phy.mt76->band_idx) {
 		if (mtk_wed_device_active(&mdev->mmio.wed) &&
 		    mtk_wed_get_rx_capa(&mdev->mmio.wed)) {
-			dev->mt76.q_rx[MT_RXQ_BAND1].flags =
+			mdev->q_rx[MT_RXQ_BAND1].flags =
 				MT_WED_Q_RX(MT7915_RXQ_BAND1);
 			dev->mt76.rx_token_size += MT7915_RX_RING_SIZE;
+			mdev->q_rx[MT_RXQ_BAND1].wed = &mdev->mmio.wed;
 		}
 
 		/* rx data queue for band1 */
@@ -581,28 +587,6 @@ int mt7915_dma_init(struct mt7915_dev *dev, struct mt7915_phy *phy2)
 	return 0;
 }
 
-static void mt7915_dma_wed_reset(struct mt7915_dev *dev)
-{
-	struct mt76_dev *mdev = &dev->mt76;
-
-	if (!test_bit(MT76_STATE_WED_RESET, &dev->mphy.state))
-		return;
-
-	complete(&mdev->mmio.wed_reset);
-
-	if (!wait_for_completion_timeout(&dev->mt76.mmio.wed_reset_complete,
-					 3 * HZ))
-		dev_err(dev->mt76.dev, "wed reset complete timeout\n");
-}
-
-static void
-mt7915_dma_reset_tx_queue(struct mt7915_dev *dev, struct mt76_queue *q)
-{
-	mt76_queue_reset(dev, q);
-	if (mtk_wed_device_active(&dev->mt76.mmio.wed))
-		mt76_dma_wed_setup(&dev->mt76, q, true);
-}
-
 int mt7915_dma_reset(struct mt7915_dev *dev, bool force)
 {
 	struct mt76_phy *mphy_ext = dev->mt76.phys[MT_BAND1];
@@ -630,20 +614,20 @@ int mt7915_dma_reset(struct mt7915_dev *dev, bool force)
 		mtk_wed_device_dma_reset(wed);
 
 	mt7915_dma_disable(dev, force);
-	mt7915_dma_wed_reset(dev);
+	mt76_dma_wed_reset(&dev->mt76);
 
 	/* reset hw queues */
 	for (i = 0; i < __MT_TXQ_MAX; i++) {
-		mt7915_dma_reset_tx_queue(dev, dev->mphy.q_tx[i]);
+		mt76_dma_reset_tx_queue(&dev->mt76, dev->mphy.q_tx[i]);
 		if (mphy_ext)
-			mt7915_dma_reset_tx_queue(dev, mphy_ext->q_tx[i]);
+			mt76_dma_reset_tx_queue(&dev->mt76, mphy_ext->q_tx[i]);
 	}
 
 	for (i = 0; i < __MT_MCUQ_MAX; i++)
 		mt76_queue_reset(dev, dev->mt76.q_mcu[i]);
 
 	mt76_for_each_q_rx(&dev->mt76, i) {
-		if (dev->mt76.q_rx[i].flags == MT_WED_Q_TXFREE)
+		if (mt76_queue_is_wed_tx_free(&dev->mt76.q_rx[i]))
 			continue;
 
 		mt76_queue_reset(dev, &dev->mt76.q_rx[i]);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c
index 76be7308460b..3bb2643d1b26 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c
@@ -11,6 +11,7 @@ static int mt7915_eeprom_load_precal(struct mt7915_dev *dev)
 	u8 *eeprom = mdev->eeprom.data;
 	u32 val = eeprom[MT_EE_DO_PRE_CAL];
 	u32 offs;
+	int ret;
 
 	if (!dev->flash_mode)
 		return 0;
@@ -25,7 +26,11 @@ static int mt7915_eeprom_load_precal(struct mt7915_dev *dev)
 
 	offs = is_mt7915(&dev->mt76) ? MT_EE_PRECAL : MT_EE_PRECAL_V2;
 
-	return mt76_get_of_eeprom(mdev, dev->cal, offs, val);
+	ret = mt76_get_of_data_from_mtd(mdev, dev->cal, offs, val);
+	if (!ret)
+		return ret;
+
+	return mt76_get_of_data_from_nvmem(mdev, dev->cal, "precal", val);
 }
 
 static int mt7915_check_eeprom(struct mt7915_dev *dev)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.h b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.h
index f3e56817d36e..adc26a222823 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.h
@@ -144,7 +144,8 @@ static inline bool
 mt7915_tssi_enabled(struct mt7915_dev *dev, enum nl80211_band band)
 {
 	u8 *eep = dev->mt76.eeprom.data;
-	u8 val = eep[MT_EE_WIFI_CONF + 7];
+	u8 offs = is_mt7981(&dev->mt76) ? 8 : 7;
+	u8 val = eep[MT_EE_WIFI_CONF + offs];
 
 	if (band == NL80211_BAND_2GHZ)
 		return val & MT_EE_WIFI_CONF7_TSSI0_2G;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
index 81478289f17e..cea2f6d9050a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
@@ -275,10 +275,11 @@ static void mt7915_led_set_brightness(struct led_classdev *led_cdev,
 		mt7915_led_set_config(led_cdev, 0xff, 0);
 }
 
-void mt7915_init_txpower(struct mt7915_dev *dev,
-			 struct ieee80211_supported_band *sband)
+static void __mt7915_init_txpower(struct mt7915_phy *phy,
+				  struct ieee80211_supported_band *sband)
 {
-	int i, n_chains = hweight8(dev->mphy.antenna_mask);
+	struct mt7915_dev *dev = phy->dev;
+	int i, n_chains = hweight16(phy->mt76->chainmask);
 	int nss_delta = mt76_tx_power_nss_delta(n_chains);
 	int pwr_delta = mt7915_eeprom_get_power_delta(dev, sband->band);
 	struct mt76_power_limits limits;
@@ -296,7 +297,7 @@ void mt7915_init_txpower(struct mt7915_dev *dev,
 		}
 
 		target_power += pwr_delta;
-		target_power = mt76_get_rate_power_limits(&dev->mphy, chan,
+		target_power = mt76_get_rate_power_limits(phy->mt76, chan,
 							  &limits,
 							  target_power);
 		target_power += nss_delta;
@@ -307,6 +308,19 @@ void mt7915_init_txpower(struct mt7915_dev *dev,
 	}
 }
 
+void mt7915_init_txpower(struct mt7915_phy *phy)
+{
+	if (!phy)
+		return;
+
+	if (phy->mt76->cap.has_2ghz)
+		__mt7915_init_txpower(phy, &phy->mt76->sband_2g.sband);
+	if (phy->mt76->cap.has_5ghz)
+		__mt7915_init_txpower(phy, &phy->mt76->sband_5g.sband);
+	if (phy->mt76->cap.has_6ghz)
+		__mt7915_init_txpower(phy, &phy->mt76->sband_6g.sband);
+}
+
 static void
 mt7915_regd_notifier(struct wiphy *wiphy,
 		     struct regulatory_request *request)
@@ -322,9 +336,7 @@ mt7915_regd_notifier(struct wiphy *wiphy,
 	if (dev->mt76.region == NL80211_DFS_UNSET)
 		mt7915_mcu_rdd_background_enable(phy, NULL);
 
-	mt7915_init_txpower(dev, &mphy->sband_2g.sband);
-	mt7915_init_txpower(dev, &mphy->sband_5g.sband);
-	mt7915_init_txpower(dev, &mphy->sband_6g.sband);
+	mt7915_init_txpower(phy);
 
 	mphy->dfs_state = MT_DFS_STATE_UNKNOWN;
 	mt7915_dfs_init_radar_detector(phy);
@@ -442,6 +454,7 @@ mt7915_init_wiphy(struct mt7915_phy *phy)
 	mt76_set_stream_caps(phy->mt76, true);
 	mt7915_set_stream_vht_txbf_caps(phy);
 	mt7915_set_stream_he_caps(phy);
+	mt7915_init_txpower(phy);
 
 	wiphy->available_antennas_rx = phy->mt76->antenna_mask;
 	wiphy->available_antennas_tx = phy->mt76->antenna_mask;
@@ -703,9 +716,6 @@ static void mt7915_init_work(struct work_struct *work)
 
 	mt7915_mcu_set_eeprom(dev);
 	mt7915_mac_init(dev);
-	mt7915_init_txpower(dev, &dev->mphy.sband_2g.sband);
-	mt7915_init_txpower(dev, &dev->mphy.sband_5g.sband);
-	mt7915_init_txpower(dev, &dev->mphy.sband_6g.sband);
 	mt7915_txbf_init(dev);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index 2222fb9aa103..b01edbed969c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -1247,7 +1247,7 @@ mt7915_phy_get_nf(struct mt7915_phy *phy, int idx)
 
 void mt7915_update_channel(struct mt76_phy *mphy)
 {
-	struct mt7915_phy *phy = (struct mt7915_phy *)mphy->priv;
+	struct mt7915_phy *phy = mphy->priv;
 	struct mt76_channel_state *state = mphy->chan_state;
 	int nf;
 
@@ -1401,8 +1401,8 @@ mt7915_mac_restart(struct mt7915_dev *dev)
 		goto out;
 
 	mt7915_mac_init(dev);
-	mt7915_init_txpower(dev, &dev->mphy.sband_2g.sband);
-	mt7915_init_txpower(dev, &dev->mphy.sband_5g.sband);
+	mt7915_init_txpower(&dev->phy);
+	mt7915_init_txpower(phy2);
 	ret = mt7915_txbf_init(dev);
 
 	if (test_bit(MT76_STATE_RUNNING, &dev->mphy.state)) {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index a3fd54cc1911..df2d4279790d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -1059,8 +1059,9 @@ mt7915_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant)
 
 	phy->mt76->antenna_mask = tx_ant;
 
-	/* handle a variant of mt7916 which has 3T3R but nss2 on 5 GHz band */
-	if (is_mt7916(&dev->mt76) && band && hweight8(tx_ant) == max_nss)
+	/* handle a variant of mt7916/mt7981 which has 3T3R but nss2 on 5 GHz band */
+	if ((is_mt7916(&dev->mt76) || is_mt7981(&dev->mt76)) &&
+	    band && hweight8(tx_ant) == max_nss)
 		phy->mt76->chainmask = (dev->chainmask >> chainshift) << chainshift;
 	else
 		phy->mt76->chainmask = tx_ant << (chainshift * band);
@@ -1653,20 +1654,6 @@ mt7915_net_fill_forward_path(struct ieee80211_hw *hw,
 
 	return 0;
 }
-
-static int
-mt7915_net_setup_tc(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-		    struct net_device *netdev, enum tc_setup_type type,
-		    void *type_data)
-{
-	struct mt7915_dev *dev = mt7915_hw_dev(hw);
-	struct mtk_wed_device *wed = &dev->mt76.mmio.wed;
-
-	if (!mtk_wed_device_active(wed))
-		return -EOPNOTSUPP;
-
-	return mtk_wed_device_setup_tc(wed, netdev, type, type_data);
-}
 #endif
 
 const struct ieee80211_ops mt7915_ops = {
@@ -1721,6 +1708,6 @@ const struct ieee80211_ops mt7915_ops = {
 	.set_radar_background = mt7915_set_radar_background,
 #ifdef CONFIG_NET_MEDIATEK_SOC_WED
 	.net_fill_forward_path = mt7915_net_fill_forward_path,
-	.net_setup_tc = mt7915_net_setup_tc,
+	.net_setup_tc = mt76_net_setup_tc,
 #endif
 };
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index b22f06d4411a..c67c4f6ca2aa 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -269,7 +269,7 @@ mt7915_mcu_rx_thermal_notify(struct mt7915_dev *dev, struct sk_buff *skb)
 	    dev->mt76.phys[MT_BAND1])
 		mphy = dev->mt76.phys[MT_BAND1];
 
-	phy = (struct mt7915_phy *)mphy->priv;
+	phy = mphy->priv;
 	phy->throttle_state = t->ctrl.duty.duty_cycle;
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h
index 1592b5d6751a..b41ac4aaced7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h
@@ -519,7 +519,7 @@ static inline s8
 mt7915_get_power_bound(struct mt7915_phy *phy, s8 txpower)
 {
 	struct mt76_phy *mphy = phy->mt76;
-	int n_chains = hweight8(mphy->antenna_mask);
+	int n_chains = hweight16(mphy->chainmask);
 
 	txpower = mt76_get_sar_power(mphy, mphy->chandef.chan, txpower * 2);
 	txpower -= mt76_tx_power_nss_delta(n_chains);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
index e7d8e03f826f..aff4f21e843d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
@@ -542,105 +542,6 @@ static u32 mt7915_rmw(struct mt76_dev *mdev, u32 offset, u32 mask, u32 val)
 }
 
 #ifdef CONFIG_NET_MEDIATEK_SOC_WED
-static int mt7915_mmio_wed_offload_enable(struct mtk_wed_device *wed)
-{
-	struct mt7915_dev *dev;
-
-	dev = container_of(wed, struct mt7915_dev, mt76.mmio.wed);
-
-	spin_lock_bh(&dev->mt76.token_lock);
-	dev->mt76.token_size = wed->wlan.token_start;
-	spin_unlock_bh(&dev->mt76.token_lock);
-
-	return !wait_event_timeout(dev->mt76.tx_wait,
-				   !dev->mt76.wed_token_count, HZ);
-}
-
-static void mt7915_mmio_wed_offload_disable(struct mtk_wed_device *wed)
-{
-	struct mt7915_dev *dev;
-
-	dev = container_of(wed, struct mt7915_dev, mt76.mmio.wed);
-
-	spin_lock_bh(&dev->mt76.token_lock);
-	dev->mt76.token_size = MT7915_TOKEN_SIZE;
-	spin_unlock_bh(&dev->mt76.token_lock);
-}
-
-static void mt7915_mmio_wed_release_rx_buf(struct mtk_wed_device *wed)
-{
-	struct mt7915_dev *dev;
-	int i;
-
-	dev = container_of(wed, struct mt7915_dev, mt76.mmio.wed);
-	for (i = 0; i < dev->mt76.rx_token_size; i++) {
-		struct mt76_txwi_cache *t;
-
-		t = mt76_rx_token_release(&dev->mt76, i);
-		if (!t || !t->ptr)
-			continue;
-
-		mt76_put_page_pool_buf(t->ptr, false);
-		t->ptr = NULL;
-
-		mt76_put_rxwi(&dev->mt76, t);
-	}
-
-	mt76_free_pending_rxwi(&dev->mt76);
-}
-
-static u32 mt7915_mmio_wed_init_rx_buf(struct mtk_wed_device *wed, int size)
-{
-	struct mtk_wed_bm_desc *desc = wed->rx_buf_ring.desc;
-	struct mt76_txwi_cache *t = NULL;
-	struct mt7915_dev *dev;
-	struct mt76_queue *q;
-	int i, len;
-
-	dev = container_of(wed, struct mt7915_dev, mt76.mmio.wed);
-	q = &dev->mt76.q_rx[MT_RXQ_MAIN];
-	len = SKB_WITH_OVERHEAD(q->buf_size);
-
-	for (i = 0; i < size; i++) {
-		enum dma_data_direction dir;
-		dma_addr_t addr;
-		u32 offset;
-		int token;
-		void *buf;
-
-		t = mt76_get_rxwi(&dev->mt76);
-		if (!t)
-			goto unmap;
-
-		buf = mt76_get_page_pool_buf(q, &offset, q->buf_size);
-		if (!buf)
-			goto unmap;
-
-		addr = page_pool_get_dma_addr(virt_to_head_page(buf)) + offset;
-		dir = page_pool_get_dma_dir(q->page_pool);
-		dma_sync_single_for_device(dev->mt76.dma_dev, addr, len, dir);
-
-		desc->buf0 = cpu_to_le32(addr);
-		token = mt76_rx_token_consume(&dev->mt76, buf, t, addr);
-		if (token < 0) {
-			mt76_put_page_pool_buf(buf, false);
-			goto unmap;
-		}
-
-		desc->token |= cpu_to_le32(FIELD_PREP(MT_DMA_CTL_TOKEN,
-						      token));
-		desc++;
-	}
-
-	return 0;
-
-unmap:
-	if (t)
-		mt76_put_rxwi(&dev->mt76, t);
-	mt7915_mmio_wed_release_rx_buf(wed);
-	return -ENOMEM;
-}
-
 static void mt7915_mmio_wed_update_rx_stats(struct mtk_wed_device *wed,
 					    struct mtk_wed_wo_rx_stats *stats)
 {
@@ -694,13 +595,6 @@ out:
 
 	return ret;
 }
-
-static void mt7915_mmio_wed_reset_complete(struct mtk_wed_device *wed)
-{
-	struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed);
-
-	complete(&dev->mmio.wed_reset_complete);
-}
 #endif
 
 int mt7915_mmio_wed_init(struct mt7915_dev *dev, void *pdev_ptr,
@@ -742,7 +636,7 @@ int mt7915_mmio_wed_init(struct mt7915_dev *dev, void *pdev_ptr,
 
 		res = platform_get_resource(plat_dev, IORESOURCE_MEM, 0);
 		if (!res)
-			return -ENOMEM;
+			return 0;
 
 		wed->wlan.platform_dev = plat_dev;
 		wed->wlan.bus_type = MTK_WED_BUS_AXI;
@@ -778,13 +672,13 @@ int mt7915_mmio_wed_init(struct mt7915_dev *dev, void *pdev_ptr,
 	}
 
 	wed->wlan.init_buf = mt7915_wed_init_buf;
-	wed->wlan.offload_enable = mt7915_mmio_wed_offload_enable;
-	wed->wlan.offload_disable = mt7915_mmio_wed_offload_disable;
-	wed->wlan.init_rx_buf = mt7915_mmio_wed_init_rx_buf;
-	wed->wlan.release_rx_buf = mt7915_mmio_wed_release_rx_buf;
+	wed->wlan.offload_enable = mt76_mmio_wed_offload_enable;
+	wed->wlan.offload_disable = mt76_mmio_wed_offload_disable;
+	wed->wlan.init_rx_buf = mt76_mmio_wed_init_rx_buf;
+	wed->wlan.release_rx_buf = mt76_mmio_wed_release_rx_buf;
 	wed->wlan.update_wo_rx_stats = mt7915_mmio_wed_update_rx_stats;
 	wed->wlan.reset = mt7915_mmio_wed_reset;
-	wed->wlan.reset_complete = mt7915_mmio_wed_reset_complete;
+	wed->wlan.reset_complete = mt76_mmio_wed_reset_complete;
 
 	dev->mt76.rx_token_size = wed->wlan.rx_npkt;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
index d317c523b23f..4727d9c7b11d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
@@ -425,8 +425,7 @@ void mt7915_dma_cleanup(struct mt7915_dev *dev);
 int mt7915_dma_reset(struct mt7915_dev *dev, bool force);
 int mt7915_dma_start(struct mt7915_dev *dev, bool reset, bool wed_reset);
 int mt7915_txbf_init(struct mt7915_dev *dev);
-void mt7915_init_txpower(struct mt7915_dev *dev,
-			 struct ieee80211_supported_band *sband);
+void mt7915_init_txpower(struct mt7915_phy *phy);
 void mt7915_reset(struct mt7915_dev *dev);
 int mt7915_run(struct ieee80211_hw *hw);
 int mt7915_mcu_init(struct mt7915_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/soc.c b/drivers/net/wireless/mediatek/mt76/mt7915/soc.c
index 06e3d9db996c..8b4809703efc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/soc.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/soc.c
@@ -1282,13 +1282,11 @@ free_device:
 	return ret;
 }
 
-static int mt798x_wmac_remove(struct platform_device *pdev)
+static void mt798x_wmac_remove(struct platform_device *pdev)
 {
 	struct mt7915_dev *dev = platform_get_drvdata(pdev);
 
 	mt7915_unregister_device(dev);
-
-	return 0;
 }
 
 static const struct of_device_id mt798x_wmac_of_match[] = {
@@ -1305,7 +1303,7 @@ struct platform_driver mt798x_wmac_driver = {
 		.of_match_table = mt798x_wmac_of_match,
 	},
 	.probe = mt798x_wmac_probe,
-	.remove = mt798x_wmac_remove,
+	.remove_new = mt798x_wmac_remove,
 };
 
 MODULE_FIRMWARE(MT7986_FIRMWARE_WA);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index 7d6a9d746011..48433c6d5e7d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -110,24 +110,37 @@ mt7921_regd_channel_update(struct wiphy *wiphy, struct mt792x_dev *dev)
 	}
 }
 
+void mt7921_regd_update(struct mt792x_dev *dev)
+{
+	struct mt76_dev *mdev = &dev->mt76;
+	struct ieee80211_hw *hw = mdev->hw;
+	struct wiphy *wiphy = hw->wiphy;
+
+	mt7921_mcu_set_clc(dev, mdev->alpha2, dev->country_ie_env);
+	mt7921_regd_channel_update(wiphy, dev);
+	mt76_connac_mcu_set_channel_domain(hw->priv);
+	mt7921_set_tx_sar_pwr(hw, NULL);
+}
+EXPORT_SYMBOL_GPL(mt7921_regd_update);
+
 static void
 mt7921_regd_notifier(struct wiphy *wiphy,
 		     struct regulatory_request *request)
 {
 	struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy);
 	struct mt792x_dev *dev = mt792x_hw_dev(hw);
+	struct mt76_connac_pm *pm = &dev->pm;
 
 	memcpy(dev->mt76.alpha2, request->alpha2, sizeof(dev->mt76.alpha2));
 	dev->mt76.region = request->dfs_region;
 	dev->country_ie_env = request->country_ie_env;
 
+	if (pm->suspended)
+		return;
+
 	mt792x_mutex_acquire(dev);
-	mt7921_mcu_set_clc(dev, request->alpha2, request->country_ie_env);
-	mt76_connac_mcu_set_channel_domain(hw->priv);
-	mt7921_set_tx_sar_pwr(hw, NULL);
+	mt7921_regd_update(dev);
 	mt792x_mutex_release(dev);
-
-	mt7921_regd_channel_update(wiphy, dev);
 }
 
 int mt7921_mac_init(struct mt792x_dev *dev)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 510a575a973b..0645417e0582 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -683,17 +683,45 @@ static void mt7921_bss_info_changed(struct ieee80211_hw *hw,
 }
 
 static void
-mt7921_regd_set_6ghz_power_type(struct ieee80211_vif *vif)
+mt7921_calc_vif_num(void *priv, u8 *mac, struct ieee80211_vif *vif)
+{
+	u32 *num = priv;
+
+	if (!priv)
+		return;
+
+	switch (vif->type) {
+	case NL80211_IFTYPE_STATION:
+	case NL80211_IFTYPE_P2P_CLIENT:
+	case NL80211_IFTYPE_AP:
+	case NL80211_IFTYPE_P2P_GO:
+		*num += 1;
+		break;
+	default:
+		break;
+	}
+}
+
+static void
+mt7921_regd_set_6ghz_power_type(struct ieee80211_vif *vif, bool is_add)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt792x_phy *phy = mvif->phy;
 	struct mt792x_dev *dev = phy->dev;
+	u32 valid_vif_num = 0;
+
+	ieee80211_iterate_active_interfaces(mt76_hw(dev),
+					    IEEE80211_IFACE_ITER_RESUME_ALL,
+					    mt7921_calc_vif_num, &valid_vif_num);
 
-	if (hweight64(dev->mt76.vif_mask) > 1) {
+	if (valid_vif_num > 1) {
 		phy->power_type = MT_AP_DEFAULT;
 		goto out;
 	}
 
+	if (!is_add)
+		vif->bss_conf.power_type = IEEE80211_REG_UNSET_AP;
+
 	switch (vif->bss_conf.power_type) {
 	case IEEE80211_REG_SP_AP:
 		phy->power_type = MT_AP_SP;
@@ -705,6 +733,8 @@ mt7921_regd_set_6ghz_power_type(struct ieee80211_vif *vif)
 		phy->power_type = MT_AP_LPI;
 		break;
 	case IEEE80211_REG_UNSET_AP:
+		phy->power_type = MT_AP_UNSET;
+		break;
 	default:
 		phy->power_type = MT_AP_DEFAULT;
 		break;
@@ -749,7 +779,7 @@ int mt7921_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	if (ret)
 		return ret;
 
-	mt7921_regd_set_6ghz_power_type(vif);
+	mt7921_regd_set_6ghz_power_type(vif, true);
 
 	mt76_connac_power_save_sched(&dev->mphy, &dev->pm);
 
@@ -811,6 +841,8 @@ void mt7921_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 		list_del_init(&msta->wcid.poll_list);
 	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
+	mt7921_regd_set_6ghz_power_type(vif, false);
+
 	mt76_connac_power_save_sched(&dev->mphy, &dev->pm);
 }
 EXPORT_SYMBOL_GPL(mt7921_mac_sta_remove);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
index 63f3d4a5c9aa..f5582477c7e4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
@@ -160,7 +160,7 @@ static void
 mt7921_mcu_scan_event(struct mt792x_dev *dev, struct sk_buff *skb)
 {
 	struct mt76_phy *mphy = &dev->mt76.phy;
-	struct mt792x_phy *phy = (struct mt792x_phy *)mphy->priv;
+	struct mt792x_phy *phy = mphy->priv;
 
 	spin_lock_bh(&dev->mt76.lock);
 	__skb_queue_tail(&phy->scan_event_list, skb);
@@ -375,6 +375,7 @@ static int mt7921_load_clc(struct mt792x_dev *dev, const char *fw_name)
 	int ret, i, len, offset = 0;
 	u8 *clc_base = NULL, hw_encap = 0;
 
+	dev->phy.clc_chan_conf = 0xff;
 	if (mt7921_disable_clc ||
 	    mt76_is_usb(&dev->mt76))
 		return 0;
@@ -1260,15 +1261,19 @@ int __mt7921_mcu_set_clc(struct mt792x_dev *dev, u8 *alpha2,
 		u8 alpha2[2];
 		u8 type[2];
 		u8 env_6g;
-		u8 rsvd[63];
+		u8 mtcl_conf;
+		u8 rsvd[62];
 	} __packed req = {
+		.ver = 1,
 		.idx = idx,
 		.env = env_cap,
 		.env_6g = dev->phy.power_type,
 		.acpi_conf = mt792x_acpi_get_flags(&dev->phy),
+		.mtcl_conf = mt792x_acpi_get_mtcl_conf(&dev->phy, alpha2),
 	};
 	int ret, valid_cnt = 0;
-	u8 i, *pos;
+	u16 buf_len = 0;
+	u8 *pos;
 
 	if (!clc)
 		return 0;
@@ -1278,12 +1283,15 @@ int __mt7921_mcu_set_clc(struct mt792x_dev *dev, u8 *alpha2,
 	if (mt76_find_power_limits_node(&dev->mt76))
 		req.cap |= CLC_CAP_DTS_EN;
 
+	buf_len = le16_to_cpu(clc->len) - sizeof(*clc);
 	pos = clc->data;
-	for (i = 0; i < clc->nr_country; i++) {
+	while (buf_len > 16) {
 		struct mt7921_clc_rule *rule = (struct mt7921_clc_rule *)pos;
 		u16 len = le16_to_cpu(rule->len);
+		u16 offset = len + sizeof(*rule);
 
-		pos += len + sizeof(*rule);
+		pos += offset;
+		buf_len -= offset;
 		if (rule->alpha2[0] != alpha2[0] ||
 		    rule->alpha2[1] != alpha2[1])
 			continue;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index f28621121927..1cb21133992b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -12,7 +12,8 @@
 #define MT7921_TX_FWDL_RING_SIZE	128
 
 #define MT7921_RX_RING_SIZE		1536
-#define MT7921_RX_MCU_RING_SIZE		512
+#define MT7921_RX_MCU_RING_SIZE		8
+#define MT7921_RX_MCU_WA_RING_SIZE	512
 
 #define MT7921_EEPROM_SIZE		3584
 #define MT7921_TOKEN_SIZE		8192
@@ -233,6 +234,7 @@ mt7921_l1_rmw(struct mt792x_dev *dev, u32 addr, u32 mask, u32 val)
 #define mt7921_l1_set(dev, addr, val)	mt7921_l1_rmw(dev, addr, 0, val)
 #define mt7921_l1_clear(dev, addr, val)	mt7921_l1_rmw(dev, addr, val, 0)
 
+void mt7921_regd_update(struct mt792x_dev *dev);
 int mt7921_mac_init(struct mt792x_dev *dev);
 bool mt7921_mac_wtbl_update(struct mt792x_dev *dev, int idx, u32 mask);
 int mt7921_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index f04e7095e181..57903c6e4f11 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -171,7 +171,7 @@ static int mt7921_dma_init(struct mt792x_dev *dev)
 	/* init tx queue */
 	ret = mt76_connac_init_tx_queues(dev->phy.mt76, MT7921_TXQ_BAND0,
 					 MT7921_TX_RING_SIZE,
-					 MT_TX_RING_BASE, 0);
+					 MT_TX_RING_BASE, NULL, 0);
 	if (ret)
 		return ret;
 
@@ -200,7 +200,7 @@ static int mt7921_dma_init(struct mt792x_dev *dev)
 	/* Change mcu queue after firmware download */
 	ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MCU_WA],
 			       MT7921_RXQ_MCU_WM,
-			       MT7921_RX_MCU_RING_SIZE,
+			       MT7921_RX_MCU_WA_RING_SIZE,
 			       MT_RX_BUF_SIZE, MT_WFDMA0(0x540));
 	if (ret)
 		return ret;
@@ -507,6 +507,9 @@ static int mt7921_pci_resume(struct device *device)
 		mt76_connac_mcu_set_deep_sleep(&dev->mt76, false);
 
 	err = mt76_connac_mcu_set_hif_suspend(mdev, false);
+
+	mt7921_regd_update(dev);
+
 failed:
 	pm->suspended = false;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
index dc1beb76df3e..7591e54d2897 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
@@ -228,7 +228,7 @@ static int mt7921s_suspend(struct device *__dev)
 	mt76_txq_schedule_all(&dev->mphy);
 	mt76_worker_disable(&mdev->tx_worker);
 	mt76_worker_disable(&mdev->sdio.status_worker);
-	cancel_work_sync(&mdev->sdio.stat_work);
+	mt76_worker_disable(&mdev->sdio.stat_worker);
 	clear_bit(MT76_READING_STATS, &dev->mphy.state);
 	mt76_tx_status_check(mdev, true);
 
@@ -260,6 +260,7 @@ restore_txrx_worker:
 restore_worker:
 	mt76_worker_enable(&mdev->tx_worker);
 	mt76_worker_enable(&mdev->sdio.status_worker);
+	mt76_worker_enable(&mdev->sdio.stat_worker);
 
 	if (!pm->ds_enable)
 		mt76_connac_mcu_set_deep_sleep(mdev, false);
@@ -292,6 +293,7 @@ static int mt7921s_resume(struct device *__dev)
 	mt76_worker_enable(&mdev->sdio.txrx_worker);
 	mt76_worker_enable(&mdev->sdio.status_worker);
 	mt76_worker_enable(&mdev->sdio.net_worker);
+	mt76_worker_enable(&mdev->sdio.stat_worker);
 
 	/* restore previous ds setting */
 	if (!pm->ds_enable)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c
index 8edd0291c128..389eb0903807 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c
@@ -107,7 +107,7 @@ int mt7921s_mac_reset(struct mt792x_dev *dev)
 	mt76_worker_disable(&dev->mt76.sdio.txrx_worker);
 	mt76_worker_disable(&dev->mt76.sdio.status_worker);
 	mt76_worker_disable(&dev->mt76.sdio.net_worker);
-	cancel_work_sync(&dev->mt76.sdio.stat_work);
+	mt76_worker_disable(&dev->mt76.sdio.stat_worker);
 
 	mt7921s_disable_irq(&dev->mt76);
 	mt7921s_wfsys_reset(dev);
@@ -115,6 +115,7 @@ int mt7921s_mac_reset(struct mt792x_dev *dev)
 	mt76_worker_enable(&dev->mt76.sdio.txrx_worker);
 	mt76_worker_enable(&dev->mt76.sdio.status_worker);
 	mt76_worker_enable(&dev->mt76.sdio.net_worker);
+	mt76_worker_enable(&dev->mt76.sdio.stat_worker);
 
 	dev->fw_assert = false;
 	clear_bit(MT76_MCU_RESET, &dev->mphy.state);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
index 15c2fb0bcb1b..8f1075da4903 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
@@ -14,7 +14,7 @@
 static void
 mt7925_init_he_caps(struct mt792x_phy *phy, enum nl80211_band band,
 		    struct ieee80211_sband_iftype_data *data,
-			enum nl80211_iftype iftype)
+		    enum nl80211_iftype iftype)
 {
 	struct ieee80211_sta_he_cap *he_cap = &data->he_cap;
 	struct ieee80211_he_cap_elem *he_cap_elem = &he_cap->he_cap_elem;
@@ -53,7 +53,7 @@ mt7925_init_he_caps(struct mt792x_phy *phy, enum nl80211_band band,
 		IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO |
 		IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO;
 
-	switch (i) {
+	switch (iftype) {
 	case NL80211_IFTYPE_AP:
 		he_cap_elem->mac_cap_info[2] |=
 			IEEE80211_HE_MAC_CAP2_BSR;
@@ -154,8 +154,7 @@ mt7925_init_he_caps(struct mt792x_phy *phy, enum nl80211_band band,
 
 static void
 mt7925_init_eht_caps(struct mt792x_phy *phy, enum nl80211_band band,
-		     struct ieee80211_sband_iftype_data *data,
-		     enum nl80211_iftype iftype)
+		     struct ieee80211_sband_iftype_data *data)
 {
 	struct ieee80211_sta_eht_cap *eht_cap = &data->eht_cap;
 	struct ieee80211_eht_cap_elem_fixed *eht_cap_elem = &eht_cap->eht_cap_elem;
@@ -256,7 +255,7 @@ __mt7925_set_stream_he_eht_caps(struct mt792x_phy *phy,
 
 		data[n].types_mask = BIT(i);
 		mt7925_init_he_caps(phy, band, &data[n], i);
-		mt7925_init_eht_caps(phy, band, &data[n], i);
+		mt7925_init_eht_caps(phy, band, &data[n]);
 
 		n++;
 	}
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index 9c0e397537ac..c5fd7116929b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -345,7 +345,7 @@ static void
 mt7925_mcu_scan_event(struct mt792x_dev *dev, struct sk_buff *skb)
 {
 	struct mt76_phy *mphy = &dev->mt76.phy;
-	struct mt792x_phy *phy = (struct mt792x_phy *)mphy->priv;
+	struct mt792x_phy *phy = mphy->priv;
 
 	spin_lock_bh(&dev->mt76.lock);
 	__skb_queue_tail(&phy->scan_event_list, skb);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
index 08ef75e24e1c..734f31ee40d3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
@@ -218,7 +218,7 @@ static int mt7925_dma_init(struct mt792x_dev *dev)
 	/* init tx queue */
 	ret = mt76_connac_init_tx_queues(dev->phy.mt76, MT7925_TXQ_BAND0,
 					 MT7925_TX_RING_SIZE,
-					 MT_TX_RING_BASE, 0);
+					 MT_TX_RING_BASE, NULL, 0);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index 36fae736dd19..3c897b34aaa7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -382,6 +382,7 @@ int mt792xe_mcu_fw_pmctrl(struct mt792x_dev *dev);
 int mt792x_init_acpi_sar(struct mt792x_dev *dev);
 int mt792x_init_acpi_sar_power(struct mt792x_phy *phy, bool set_default);
 u8 mt792x_acpi_get_flags(struct mt792x_phy *phy);
+u8 mt792x_acpi_get_mtcl_conf(struct mt792x_phy *phy, char *alpha2);
 #else
 static inline int mt792x_init_acpi_sar(struct mt792x_dev *dev)
 {
@@ -398,6 +399,11 @@ static inline u8 mt792x_acpi_get_flags(struct mt792x_phy *phy)
 {
 	return 0;
 }
+
+static inline u8 mt792x_acpi_get_mtcl_conf(struct mt792x_phy *phy, char *alpha2)
+{
+	return 0xf;
+}
 #endif
 
 #endif /* __MT7925_H */
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c b/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c
index 303c0f5c9c66..e7afea87e82e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c
@@ -348,3 +348,56 @@ u8 mt792x_acpi_get_flags(struct mt792x_phy *phy)
 	return flags;
 }
 EXPORT_SYMBOL_GPL(mt792x_acpi_get_flags);
+
+static u8
+mt792x_acpi_get_mtcl_map(int row, int column, struct mt792x_asar_cl *cl)
+{
+	u8 config = 0;
+
+	if (cl->cl6g[row] & BIT(column))
+		config |= (cl->mode_6g & 0x3) << 2;
+	if (cl->version > 1 && cl->cl5g9[row] & BIT(column))
+		config |= (cl->mode_5g9 & 0x3);
+
+	return config;
+}
+
+u8 mt792x_acpi_get_mtcl_conf(struct mt792x_phy *phy, char *alpha2)
+{
+	static const char * const cc_list_all[] = {
+		"00", "EU", "AR", "AU", "AZ", "BY", "BO", "BR",
+		"CA", "CL", "CN", "ID", "JP", "MY", "MX", "ME",
+		"MA", "NZ", "NG", "PH", "RU", "RS", "SG", "KR",
+		"TW", "TH", "UA", "GB", "US", "VN", "KH", "PY",
+	};
+	static const char * const cc_list_eu[] = {
+		"AT", "BE", "BG", "CY", "CZ", "HR", "DK", "EE",
+		"FI", "FR", "DE", "GR", "HU", "IS", "IE", "IT",
+		"LV", "LI", "LT", "LU", "MT", "NL", "NO", "PL",
+		"PT", "RO", "MT", "SK", "SI", "ES", "CH",
+	};
+	struct mt792x_acpi_sar *sar = phy->acpisar;
+	struct mt792x_asar_cl *cl;
+	int col, row, i;
+
+	if (!sar)
+		return 0xf;
+
+	cl = sar->countrylist;
+	if (!cl)
+		return 0xc;
+
+	for (i = 0; i < ARRAY_SIZE(cc_list_all); i++) {
+		col = 7 - i % 8;
+		row = i / 8;
+		if (!memcmp(cc_list_all[i], alpha2, 2))
+			return mt792x_acpi_get_mtcl_map(row, col, cl);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(cc_list_eu); i++)
+		if (!memcmp(cc_list_eu[i], alpha2, 2))
+			return mt792x_acpi_get_mtcl_map(0, 6, cl);
+
+	return mt792x_acpi_get_mtcl_map(0, 7, cl);
+}
+EXPORT_SYMBOL_GPL(mt792x_acpi_get_mtcl_conf);
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.h b/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.h
index d6d332e863ba..2298983b6342 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.h
@@ -77,6 +77,8 @@ struct mt792x_asar_cl {
 	u8 version;
 	u8 mode_6g;
 	u8 cl6g[6];
+	u8 mode_5g9;
+	u8 cl5g9[6];
 } __packed;
 
 struct mt792x_asar_fg {
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_mac.c b/drivers/net/wireless/mediatek/mt76/mt792x_mac.c
index 5d1f8229fdc1..eb29434abee1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_mac.c
@@ -223,7 +223,7 @@ static void
 mt792x_phy_update_channel(struct mt76_phy *mphy, int idx)
 {
 	struct mt792x_dev *dev = container_of(mphy->dev, struct mt792x_dev, mt76);
-	struct mt792x_phy *phy = (struct mt792x_phy *)mphy->priv;
+	struct mt792x_phy *phy = mphy->priv;
 	struct mt76_channel_state *state;
 	u64 busy_time, tx_time, rx_time, obss_time;
 	int nf;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c
index 4d40ec7ff57f..9bd953586b04 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c
@@ -476,7 +476,7 @@ mt7996_txbf_stat_read_phy(struct mt7996_phy *phy, struct seq_file *s)
 {
 	struct mt76_mib_stats *mib = &phy->mib;
 	static const char * const bw[] = {
-		"BW20", "BW40", "BW80", "BW160"
+		"BW20", "BW40", "BW80", "BW160", "BW320"
 	};
 
 	/* Tx Beamformer monitor */
@@ -489,8 +489,9 @@ mt7996_txbf_stat_read_phy(struct mt7996_phy *phy, struct seq_file *s)
 	/* Tx Beamformer Rx feedback monitor */
 	seq_puts(s, "Tx Beamformer Rx feedback statistics: ");
 
-	seq_printf(s, "All: %d, HE: %d, VHT: %d, HT: %d, ",
+	seq_printf(s, "All: %d, EHT: %d, HE: %d, VHT: %d, HT: %d, ",
 		   mib->tx_bf_rx_fb_all_cnt,
+		   mib->tx_bf_rx_fb_eht_cnt,
 		   mib->tx_bf_rx_fb_he_cnt,
 		   mib->tx_bf_rx_fb_vht_cnt,
 		   mib->tx_bf_rx_fb_ht_cnt);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/dma.c b/drivers/net/wireless/mediatek/mt76/mt7996/dma.c
index 586e247a1e06..483ad81b6eec 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/dma.c
@@ -7,6 +7,26 @@
 #include "../dma.h"
 #include "mac.h"
 
+int mt7996_init_tx_queues(struct mt7996_phy *phy, int idx, int n_desc,
+			  int ring_base, struct mtk_wed_device *wed)
+{
+	struct mt7996_dev *dev = phy->dev;
+	u32 flags = 0;
+
+	if (mtk_wed_device_active(wed)) {
+		ring_base += MT_TXQ_ID(0) * MT_RING_SIZE;
+		idx -= MT_TXQ_ID(0);
+
+		if (phy->mt76->band_idx == MT_BAND2)
+			flags = MT_WED_Q_TX(0);
+		else
+			flags = MT_WED_Q_TX(idx);
+	}
+
+	return mt76_connac_init_tx_queues(phy->mt76, idx, n_desc,
+					  ring_base, wed, flags);
+}
+
 static int mt7996_poll_tx(struct napi_struct *napi, int budget)
 {
 	struct mt7996_dev *dev;
@@ -37,18 +57,51 @@ static void mt7996_dma_config(struct mt7996_dev *dev)
 	RXQ_CONFIG(MT_RXQ_MCU, WFDMA0, MT_INT_RX_DONE_WM, MT7996_RXQ_MCU_WM);
 	RXQ_CONFIG(MT_RXQ_MCU_WA, WFDMA0, MT_INT_RX_DONE_WA, MT7996_RXQ_MCU_WA);
 
-	/* band0/band1 */
+	/* mt7996: band0 and band1, mt7992: band0 */
 	RXQ_CONFIG(MT_RXQ_MAIN, WFDMA0, MT_INT_RX_DONE_BAND0, MT7996_RXQ_BAND0);
 	RXQ_CONFIG(MT_RXQ_MAIN_WA, WFDMA0, MT_INT_RX_DONE_WA_MAIN, MT7996_RXQ_MCU_WA_MAIN);
 
-	/* band2 */
-	RXQ_CONFIG(MT_RXQ_BAND2, WFDMA0, MT_INT_RX_DONE_BAND2, MT7996_RXQ_BAND2);
-	RXQ_CONFIG(MT_RXQ_BAND2_WA, WFDMA0, MT_INT_RX_DONE_WA_TRI, MT7996_RXQ_MCU_WA_TRI);
+	if (is_mt7996(&dev->mt76)) {
+		/* mt7996 band2 */
+		RXQ_CONFIG(MT_RXQ_BAND2, WFDMA0, MT_INT_RX_DONE_BAND2, MT7996_RXQ_BAND2);
+		RXQ_CONFIG(MT_RXQ_BAND2_WA, WFDMA0, MT_INT_RX_DONE_WA_TRI, MT7996_RXQ_MCU_WA_TRI);
+	} else {
+		/* mt7992 band1 */
+		RXQ_CONFIG(MT_RXQ_BAND1, WFDMA0, MT_INT_RX_DONE_BAND1, MT7996_RXQ_BAND1);
+		RXQ_CONFIG(MT_RXQ_BAND1_WA, WFDMA0, MT_INT_RX_DONE_WA_EXT, MT7996_RXQ_MCU_WA_EXT);
+	}
+
+	if (dev->has_rro) {
+		/* band0 */
+		RXQ_CONFIG(MT_RXQ_RRO_BAND0, WFDMA0, MT_INT_RX_DONE_RRO_BAND0,
+			   MT7996_RXQ_RRO_BAND0);
+		RXQ_CONFIG(MT_RXQ_MSDU_PAGE_BAND0, WFDMA0, MT_INT_RX_DONE_MSDU_PG_BAND0,
+			   MT7996_RXQ_MSDU_PG_BAND0);
+		RXQ_CONFIG(MT_RXQ_TXFREE_BAND0, WFDMA0, MT_INT_RX_TXFREE_MAIN,
+			   MT7996_RXQ_TXFREE0);
+		/* band1 */
+		RXQ_CONFIG(MT_RXQ_MSDU_PAGE_BAND1, WFDMA0, MT_INT_RX_DONE_MSDU_PG_BAND1,
+			   MT7996_RXQ_MSDU_PG_BAND1);
+		/* band2 */
+		RXQ_CONFIG(MT_RXQ_RRO_BAND2, WFDMA0, MT_INT_RX_DONE_RRO_BAND2,
+			   MT7996_RXQ_RRO_BAND2);
+		RXQ_CONFIG(MT_RXQ_MSDU_PAGE_BAND2, WFDMA0, MT_INT_RX_DONE_MSDU_PG_BAND2,
+			   MT7996_RXQ_MSDU_PG_BAND2);
+		RXQ_CONFIG(MT_RXQ_TXFREE_BAND2, WFDMA0, MT_INT_RX_TXFREE_TRI,
+			   MT7996_RXQ_TXFREE2);
+
+		RXQ_CONFIG(MT_RXQ_RRO_IND, WFDMA0, MT_INT_RX_DONE_RRO_IND,
+			   MT7996_RXQ_RRO_IND);
+	}
 
 	/* data tx queue */
 	TXQ_CONFIG(0, WFDMA0, MT_INT_TX_DONE_BAND0, MT7996_TXQ_BAND0);
-	TXQ_CONFIG(1, WFDMA0, MT_INT_TX_DONE_BAND1, MT7996_TXQ_BAND1);
-	TXQ_CONFIG(2, WFDMA0, MT_INT_TX_DONE_BAND2, MT7996_TXQ_BAND2);
+	if (is_mt7996(&dev->mt76)) {
+		TXQ_CONFIG(1, WFDMA0, MT_INT_TX_DONE_BAND1, MT7996_TXQ_BAND1);
+		TXQ_CONFIG(2, WFDMA0, MT_INT_TX_DONE_BAND2, MT7996_TXQ_BAND2);
+	} else {
+		TXQ_CONFIG(1, WFDMA0, MT_INT_TX_DONE_BAND1, MT7996_TXQ_BAND1);
+	}
 
 	/* mcu tx queue */
 	MCUQ_CONFIG(MT_MCUQ_WM, WFDMA0, MT_INT_TX_DONE_MCU_WM, MT7996_TXQ_MCU_WM);
@@ -56,22 +109,57 @@ static void mt7996_dma_config(struct mt7996_dev *dev)
 	MCUQ_CONFIG(MT_MCUQ_FWDL, WFDMA0, MT_INT_TX_DONE_FWDL, MT7996_TXQ_FWDL);
 }
 
+static u32 __mt7996_dma_prefetch_base(u16 *base, u8 depth)
+{
+	u32 ret = *base << 16 | depth;
+
+	*base = *base + (depth << 4);
+
+	return ret;
+}
+
 static void __mt7996_dma_prefetch(struct mt7996_dev *dev, u32 ofs)
 {
-#define PREFETCH(_base, _depth)	((_base) << 16 | (_depth))
+	u16 base = 0;
+	u8 queue;
+
+#define PREFETCH(_depth)	(__mt7996_dma_prefetch_base(&base, (_depth)))
 	/* prefetch SRAM wrapping boundary for tx/rx ring. */
-	mt76_wr(dev, MT_MCUQ_EXT_CTRL(MT_MCUQ_FWDL) + ofs, PREFETCH(0x0, 0x2));
-	mt76_wr(dev, MT_MCUQ_EXT_CTRL(MT_MCUQ_WM) + ofs, PREFETCH(0x20, 0x2));
-	mt76_wr(dev, MT_TXQ_EXT_CTRL(0) + ofs, PREFETCH(0x40, 0x4));
-	mt76_wr(dev, MT_TXQ_EXT_CTRL(1) + ofs, PREFETCH(0x80, 0x4));
-	mt76_wr(dev, MT_MCUQ_EXT_CTRL(MT_MCUQ_WA) + ofs, PREFETCH(0xc0, 0x2));
-	mt76_wr(dev, MT_TXQ_EXT_CTRL(2) + ofs, PREFETCH(0xe0, 0x4));
-	mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_MCU) + ofs, PREFETCH(0x120, 0x2));
-	mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_MCU_WA) + ofs, PREFETCH(0x140, 0x2));
-	mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_MAIN_WA) + ofs, PREFETCH(0x160, 0x2));
-	mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_BAND2_WA) + ofs, PREFETCH(0x180, 0x2));
-	mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_MAIN) + ofs, PREFETCH(0x1a0, 0x10));
-	mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_BAND2) + ofs, PREFETCH(0x2a0, 0x10));
+	mt76_wr(dev, MT_MCUQ_EXT_CTRL(MT_MCUQ_FWDL) + ofs, PREFETCH(0x2));
+	mt76_wr(dev, MT_MCUQ_EXT_CTRL(MT_MCUQ_WM) + ofs, PREFETCH(0x2));
+	mt76_wr(dev, MT_TXQ_EXT_CTRL(0) + ofs, PREFETCH(0x8));
+	mt76_wr(dev, MT_TXQ_EXT_CTRL(1) + ofs, PREFETCH(0x8));
+	mt76_wr(dev, MT_MCUQ_EXT_CTRL(MT_MCUQ_WA) + ofs, PREFETCH(0x2));
+	mt76_wr(dev, MT_TXQ_EXT_CTRL(2) + ofs, PREFETCH(0x8));
+	mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_MCU) + ofs, PREFETCH(0x2));
+	mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_MCU_WA) + ofs, PREFETCH(0x2));
+	mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_MAIN_WA) + ofs, PREFETCH(0x2));
+
+	queue = is_mt7996(&dev->mt76) ? MT_RXQ_BAND2_WA : MT_RXQ_BAND1_WA;
+	mt76_wr(dev, MT_RXQ_BAND1_CTRL(queue) + ofs, PREFETCH(0x2));
+
+	mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_MAIN) + ofs, PREFETCH(0x10));
+
+	queue = is_mt7996(&dev->mt76) ? MT_RXQ_BAND2 : MT_RXQ_BAND1;
+	mt76_wr(dev, MT_RXQ_BAND1_CTRL(queue) + ofs, PREFETCH(0x10));
+
+	if (dev->has_rro) {
+		mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_RRO_BAND0) + ofs,
+			PREFETCH(0x10));
+		mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_RRO_BAND2) + ofs,
+			PREFETCH(0x10));
+		mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_MSDU_PAGE_BAND0) + ofs,
+			PREFETCH(0x4));
+		mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_MSDU_PAGE_BAND1) + ofs,
+			PREFETCH(0x4));
+		mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_MSDU_PAGE_BAND2) + ofs,
+			PREFETCH(0x4));
+		mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_TXFREE_BAND0) + ofs,
+			PREFETCH(0x4));
+		mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_TXFREE_BAND2) + ofs,
+			PREFETCH(0x4));
+	}
+#undef PREFETCH
 
 	mt76_set(dev, WF_WFDMA0_GLO_CFG_EXT1 + ofs, WF_WFDMA0_GLO_CFG_EXT1_CALC_MODE);
 }
@@ -128,8 +216,9 @@ static void mt7996_dma_disable(struct mt7996_dev *dev, bool reset)
 	}
 }
 
-void mt7996_dma_start(struct mt7996_dev *dev, bool reset)
+void mt7996_dma_start(struct mt7996_dev *dev, bool reset, bool wed_reset)
 {
+	struct mtk_wed_device *wed = &dev->mt76.mmio.wed;
 	u32 hif1_ofs = 0;
 	u32 irq_mask;
 
@@ -138,37 +227,49 @@ void mt7996_dma_start(struct mt7996_dev *dev, bool reset)
 
 	/* enable WFDMA Tx/Rx */
 	if (!reset) {
-		mt76_set(dev, MT_WFDMA0_GLO_CFG,
-			 MT_WFDMA0_GLO_CFG_TX_DMA_EN |
-			 MT_WFDMA0_GLO_CFG_RX_DMA_EN |
-			 MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
-			 MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2);
+		if (mtk_wed_device_active(wed) && mtk_wed_get_rx_capa(wed))
+			mt76_set(dev, MT_WFDMA0_GLO_CFG,
+				 MT_WFDMA0_GLO_CFG_TX_DMA_EN |
+				 MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
+				 MT_WFDMA0_GLO_CFG_EXT_EN);
+		else
+			mt76_set(dev, MT_WFDMA0_GLO_CFG,
+				 MT_WFDMA0_GLO_CFG_TX_DMA_EN |
+				 MT_WFDMA0_GLO_CFG_RX_DMA_EN |
+				 MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
+				 MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2);
 
 		if (dev->hif2)
 			mt76_set(dev, MT_WFDMA0_GLO_CFG + hif1_ofs,
 				 MT_WFDMA0_GLO_CFG_TX_DMA_EN |
 				 MT_WFDMA0_GLO_CFG_RX_DMA_EN |
 				 MT_WFDMA0_GLO_CFG_OMIT_TX_INFO |
-				 MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2);
+				 MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2 |
+				 MT_WFDMA0_GLO_CFG_EXT_EN);
 	}
 
 	/* enable interrupts for TX/RX rings */
-	irq_mask = MT_INT_MCU_CMD;
-	if (reset)
-		goto done;
+	irq_mask = MT_INT_MCU_CMD | MT_INT_RX_DONE_MCU | MT_INT_TX_DONE_MCU;
 
-	irq_mask = MT_INT_RX_DONE_MCU | MT_INT_TX_DONE_MCU;
-
-	if (!dev->mphy.band_idx)
+	if (mt7996_band_valid(dev, MT_BAND0))
 		irq_mask |= MT_INT_BAND0_RX_DONE;
 
-	if (dev->dbdc_support)
+	if (mt7996_band_valid(dev, MT_BAND1))
 		irq_mask |= MT_INT_BAND1_RX_DONE;
 
-	if (dev->tbtc_support)
+	if (mt7996_band_valid(dev, MT_BAND2))
 		irq_mask |= MT_INT_BAND2_RX_DONE;
 
-done:
+	if (mtk_wed_device_active(wed) && wed_reset) {
+		u32 wed_irq_mask = irq_mask;
+
+		wed_irq_mask |= MT_INT_TX_DONE_BAND0 | MT_INT_TX_DONE_BAND1;
+		mt76_wr(dev, MT_INT_MASK_CSR, wed_irq_mask);
+		mtk_wed_device_start(wed, wed_irq_mask);
+	}
+
+	irq_mask = reset ? MT_INT_MCU_CMD : irq_mask;
+
 	mt7996_irq_enable(dev, irq_mask);
 	mt7996_irq_disable(dev, 0);
 }
@@ -223,6 +324,12 @@ static void mt7996_dma_enable(struct mt7996_dev *dev, bool reset)
 	mt76_set(dev, WF_WFDMA0_GLO_CFG_EXT1,
 		 WF_WFDMA0_GLO_CFG_EXT1_TX_FCTRL_MODE);
 
+	/* WFDMA rx threshold */
+	mt76_wr(dev, MT_WFDMA0_PAUSE_RX_Q_45_TH, 0xc000c);
+	mt76_wr(dev, MT_WFDMA0_PAUSE_RX_Q_67_TH, 0x10008);
+	mt76_wr(dev, MT_WFDMA0_PAUSE_RX_Q_89_TH, 0x10008);
+	mt76_wr(dev, MT_WFDMA0_PAUSE_RX_Q_RRO_TH, 0x20);
+
 	if (dev->hif2) {
 		/* GLO_CFG_EXT0 */
 		mt76_set(dev, WF_WFDMA0_GLO_CFG_EXT0 + hif1_ofs,
@@ -234,24 +341,108 @@ static void mt7996_dma_enable(struct mt7996_dev *dev, bool reset)
 			 WF_WFDMA0_GLO_CFG_EXT1_TX_FCTRL_MODE);
 
 		mt76_set(dev, MT_WFDMA_HOST_CONFIG,
-			 MT_WFDMA_HOST_CONFIG_PDMA_BAND);
+			 MT_WFDMA_HOST_CONFIG_PDMA_BAND |
+			 MT_WFDMA_HOST_CONFIG_BAND2_PCIE1);
+
+		/* AXI read outstanding number */
+		mt76_rmw(dev, MT_WFDMA_AXI_R2A_CTRL,
+			 MT_WFDMA_AXI_R2A_CTRL_OUTSTAND_MASK, 0x14);
+
+		/* WFDMA rx threshold */
+		mt76_wr(dev, MT_WFDMA0_PAUSE_RX_Q_45_TH + hif1_ofs, 0xc000c);
+		mt76_wr(dev, MT_WFDMA0_PAUSE_RX_Q_67_TH + hif1_ofs, 0x10008);
+		mt76_wr(dev, MT_WFDMA0_PAUSE_RX_Q_89_TH + hif1_ofs, 0x10008);
+		mt76_wr(dev, MT_WFDMA0_PAUSE_RX_Q_RRO_TH + hif1_ofs, 0x20);
 	}
 
 	if (dev->hif2) {
 		/* fix hardware limitation, pcie1's rx ring3 is not available
 		 * so, redirect pcie0 rx ring3 interrupt to pcie1
 		 */
-		mt76_set(dev, MT_WFDMA0_RX_INT_PCIE_SEL,
-			 MT_WFDMA0_RX_INT_SEL_RING3);
+		if (mtk_wed_device_active(&dev->mt76.mmio.wed) &&
+		    dev->has_rro)
+			mt76_set(dev, MT_WFDMA0_RX_INT_PCIE_SEL + hif1_ofs,
+				 MT_WFDMA0_RX_INT_SEL_RING6);
+		else
+			mt76_set(dev, MT_WFDMA0_RX_INT_PCIE_SEL,
+				 MT_WFDMA0_RX_INT_SEL_RING3);
+	}
+
+	mt7996_dma_start(dev, reset, true);
+}
+
+#ifdef CONFIG_NET_MEDIATEK_SOC_WED
+int mt7996_dma_rro_init(struct mt7996_dev *dev)
+{
+	struct mt76_dev *mdev = &dev->mt76;
+	u32 irq_mask;
+	int ret;
 
-		/* TODO: redirect rx ring6 interrupt to pcie0 for wed function */
+	/* ind cmd */
+	mdev->q_rx[MT_RXQ_RRO_IND].flags = MT_WED_RRO_Q_IND;
+	mdev->q_rx[MT_RXQ_RRO_IND].wed = &mdev->mmio.wed;
+	ret = mt76_queue_alloc(dev, &mdev->q_rx[MT_RXQ_RRO_IND],
+			       MT_RXQ_ID(MT_RXQ_RRO_IND),
+			       MT7996_RX_RING_SIZE,
+			       0, MT_RXQ_RRO_IND_RING_BASE);
+	if (ret)
+		return ret;
+
+	/* rx msdu page queue for band0 */
+	mdev->q_rx[MT_RXQ_MSDU_PAGE_BAND0].flags =
+		MT_WED_RRO_Q_MSDU_PG(0) | MT_QFLAG_WED_RRO_EN;
+	mdev->q_rx[MT_RXQ_MSDU_PAGE_BAND0].wed = &mdev->mmio.wed;
+	ret = mt76_queue_alloc(dev, &mdev->q_rx[MT_RXQ_MSDU_PAGE_BAND0],
+			       MT_RXQ_ID(MT_RXQ_MSDU_PAGE_BAND0),
+			       MT7996_RX_RING_SIZE,
+			       MT7996_RX_MSDU_PAGE_SIZE,
+			       MT_RXQ_RING_BASE(MT_RXQ_MSDU_PAGE_BAND0));
+	if (ret)
+		return ret;
+
+	if (mt7996_band_valid(dev, MT_BAND1)) {
+		/* rx msdu page queue for band1 */
+		mdev->q_rx[MT_RXQ_MSDU_PAGE_BAND1].flags =
+			MT_WED_RRO_Q_MSDU_PG(1) | MT_QFLAG_WED_RRO_EN;
+		mdev->q_rx[MT_RXQ_MSDU_PAGE_BAND1].wed = &mdev->mmio.wed;
+		ret = mt76_queue_alloc(dev, &mdev->q_rx[MT_RXQ_MSDU_PAGE_BAND1],
+				       MT_RXQ_ID(MT_RXQ_MSDU_PAGE_BAND1),
+				       MT7996_RX_RING_SIZE,
+				       MT7996_RX_MSDU_PAGE_SIZE,
+				       MT_RXQ_RING_BASE(MT_RXQ_MSDU_PAGE_BAND1));
+		if (ret)
+			return ret;
 	}
 
-	mt7996_dma_start(dev, reset);
+	if (mt7996_band_valid(dev, MT_BAND2)) {
+		/* rx msdu page queue for band2 */
+		mdev->q_rx[MT_RXQ_MSDU_PAGE_BAND2].flags =
+			MT_WED_RRO_Q_MSDU_PG(2) | MT_QFLAG_WED_RRO_EN;
+		mdev->q_rx[MT_RXQ_MSDU_PAGE_BAND2].wed = &mdev->mmio.wed;
+		ret = mt76_queue_alloc(dev, &mdev->q_rx[MT_RXQ_MSDU_PAGE_BAND2],
+				       MT_RXQ_ID(MT_RXQ_MSDU_PAGE_BAND2),
+				       MT7996_RX_RING_SIZE,
+				       MT7996_RX_MSDU_PAGE_SIZE,
+				       MT_RXQ_RING_BASE(MT_RXQ_MSDU_PAGE_BAND2));
+		if (ret)
+			return ret;
+	}
+
+	irq_mask = mdev->mmio.irqmask | MT_INT_RRO_RX_DONE |
+		   MT_INT_TX_DONE_BAND2;
+	mt76_wr(dev, MT_INT_MASK_CSR, irq_mask);
+	mtk_wed_device_start_hw_rro(&mdev->mmio.wed, irq_mask, false);
+	mt7996_irq_enable(dev, irq_mask);
+
+	return 0;
 }
+#endif /* CONFIG_NET_MEDIATEK_SOC_WED */
 
 int mt7996_dma_init(struct mt7996_dev *dev)
 {
+	struct mtk_wed_device *wed = &dev->mt76.mmio.wed;
+	struct mtk_wed_device *wed_hif2 = &dev->mt76.mmio.wed_hif2;
+	u32 rx_base;
 	u32 hif1_ofs = 0;
 	int ret;
 
@@ -265,10 +456,11 @@ int mt7996_dma_init(struct mt7996_dev *dev)
 	mt7996_dma_disable(dev, true);
 
 	/* init tx queue */
-	ret = mt76_connac_init_tx_queues(dev->phy.mt76,
-					 MT_TXQ_ID(dev->mphy.band_idx),
-					 MT7996_TX_RING_SIZE,
-					 MT_TXQ_RING_BASE(0), 0);
+	ret = mt7996_init_tx_queues(&dev->phy,
+				    MT_TXQ_ID(dev->mphy.band_idx),
+				    MT7996_TX_RING_SIZE,
+				    MT_TXQ_RING_BASE(0),
+				    wed);
 	if (ret)
 		return ret;
 
@@ -314,7 +506,12 @@ int mt7996_dma_init(struct mt7996_dev *dev)
 	if (ret)
 		return ret;
 
-	/* rx data queue for band0 and band1 */
+	/* rx data queue for band0 and mt7996 band1 */
+	if (mtk_wed_device_active(wed) && mtk_wed_get_rx_capa(wed)) {
+		dev->mt76.q_rx[MT_RXQ_MAIN].flags = MT_WED_Q_RX(0);
+		dev->mt76.q_rx[MT_RXQ_MAIN].wed = wed;
+	}
+
 	ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MAIN],
 			       MT_RXQ_ID(MT_RXQ_MAIN),
 			       MT7996_RX_RING_SIZE,
@@ -324,6 +521,11 @@ int mt7996_dma_init(struct mt7996_dev *dev)
 		return ret;
 
 	/* tx free notify event from WA for band0 */
+	if (mtk_wed_device_active(wed) && !dev->has_rro) {
+		dev->mt76.q_rx[MT_RXQ_MAIN_WA].flags = MT_WED_Q_TXFREE;
+		dev->mt76.q_rx[MT_RXQ_MAIN_WA].wed = wed;
+	}
+
 	ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MAIN_WA],
 			       MT_RXQ_ID(MT_RXQ_MAIN_WA),
 			       MT7996_RX_MCU_RING_SIZE,
@@ -332,19 +534,25 @@ int mt7996_dma_init(struct mt7996_dev *dev)
 	if (ret)
 		return ret;
 
-	if (dev->tbtc_support || dev->mphy.band_idx == MT_BAND2) {
-		/* rx data queue for band2 */
+	if (mt7996_band_valid(dev, MT_BAND2)) {
+		/* rx data queue for mt7996 band2 */
+		rx_base = MT_RXQ_RING_BASE(MT_RXQ_BAND2) + hif1_ofs;
 		ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_BAND2],
 				       MT_RXQ_ID(MT_RXQ_BAND2),
 				       MT7996_RX_RING_SIZE,
 				       MT_RX_BUF_SIZE,
-				       MT_RXQ_RING_BASE(MT_RXQ_BAND2) + hif1_ofs);
+				       rx_base);
 		if (ret)
 			return ret;
 
-		/* tx free notify event from WA for band2
+		/* tx free notify event from WA for mt7996 band2
 		 * use pcie0's rx ring3, but, redirect pcie0 rx ring3 interrupt to pcie1
 		 */
+		if (mtk_wed_device_active(wed_hif2) && !dev->has_rro) {
+			dev->mt76.q_rx[MT_RXQ_BAND2_WA].flags = MT_WED_Q_TXFREE;
+			dev->mt76.q_rx[MT_RXQ_BAND2_WA].wed = wed_hif2;
+		}
+
 		ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_BAND2_WA],
 				       MT_RXQ_ID(MT_RXQ_BAND2_WA),
 				       MT7996_RX_MCU_RING_SIZE,
@@ -352,6 +560,80 @@ int mt7996_dma_init(struct mt7996_dev *dev)
 				       MT_RXQ_RING_BASE(MT_RXQ_BAND2_WA));
 		if (ret)
 			return ret;
+	} else if (mt7996_band_valid(dev, MT_BAND1)) {
+		/* rx data queue for mt7992 band1 */
+		rx_base = MT_RXQ_RING_BASE(MT_RXQ_BAND1) + hif1_ofs;
+		ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_BAND1],
+				       MT_RXQ_ID(MT_RXQ_BAND1),
+				       MT7996_RX_RING_SIZE,
+				       MT_RX_BUF_SIZE,
+				       rx_base);
+		if (ret)
+			return ret;
+
+		/* tx free notify event from WA for mt7992 band1 */
+		rx_base = MT_RXQ_RING_BASE(MT_RXQ_BAND1_WA) + hif1_ofs;
+		ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_BAND1_WA],
+				       MT_RXQ_ID(MT_RXQ_BAND1_WA),
+				       MT7996_RX_MCU_RING_SIZE,
+				       MT_RX_BUF_SIZE,
+				       rx_base);
+		if (ret)
+			return ret;
+	}
+
+	if (mtk_wed_device_active(wed) && mtk_wed_get_rx_capa(wed) &&
+	    dev->has_rro) {
+		/* rx rro data queue for band0 */
+		dev->mt76.q_rx[MT_RXQ_RRO_BAND0].flags =
+			MT_WED_RRO_Q_DATA(0) | MT_QFLAG_WED_RRO_EN;
+		dev->mt76.q_rx[MT_RXQ_RRO_BAND0].wed = wed;
+		ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_RRO_BAND0],
+				       MT_RXQ_ID(MT_RXQ_RRO_BAND0),
+				       MT7996_RX_RING_SIZE,
+				       MT7996_RX_BUF_SIZE,
+				       MT_RXQ_RING_BASE(MT_RXQ_RRO_BAND0));
+		if (ret)
+			return ret;
+
+		/* tx free notify event from WA for band0 */
+		dev->mt76.q_rx[MT_RXQ_TXFREE_BAND0].flags = MT_WED_Q_TXFREE;
+		dev->mt76.q_rx[MT_RXQ_TXFREE_BAND0].wed = wed;
+
+		ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_TXFREE_BAND0],
+				       MT_RXQ_ID(MT_RXQ_TXFREE_BAND0),
+				       MT7996_RX_MCU_RING_SIZE,
+				       MT7996_RX_BUF_SIZE,
+				       MT_RXQ_RING_BASE(MT_RXQ_TXFREE_BAND0));
+		if (ret)
+			return ret;
+
+		if (mt7996_band_valid(dev, MT_BAND2)) {
+			/* rx rro data queue for band2 */
+			dev->mt76.q_rx[MT_RXQ_RRO_BAND2].flags =
+				MT_WED_RRO_Q_DATA(1) | MT_QFLAG_WED_RRO_EN;
+			dev->mt76.q_rx[MT_RXQ_RRO_BAND2].wed = wed;
+			ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_RRO_BAND2],
+					       MT_RXQ_ID(MT_RXQ_RRO_BAND2),
+					       MT7996_RX_RING_SIZE,
+					       MT7996_RX_BUF_SIZE,
+					       MT_RXQ_RING_BASE(MT_RXQ_RRO_BAND2) + hif1_ofs);
+			if (ret)
+				return ret;
+
+			/* tx free notify event from MAC for band2 */
+			if (mtk_wed_device_active(wed_hif2)) {
+				dev->mt76.q_rx[MT_RXQ_TXFREE_BAND2].flags = MT_WED_Q_TXFREE;
+				dev->mt76.q_rx[MT_RXQ_TXFREE_BAND2].wed = wed_hif2;
+			}
+			ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_TXFREE_BAND2],
+					       MT_RXQ_ID(MT_RXQ_TXFREE_BAND2),
+					       MT7996_RX_MCU_RING_SIZE,
+					       MT7996_RX_BUF_SIZE,
+					       MT_RXQ_RING_BASE(MT_RXQ_TXFREE_BAND2) + hif1_ofs);
+			if (ret)
+				return ret;
+		}
 	}
 
 	ret = mt76_init_queues(dev, mt76_dma_rx_poll);
@@ -405,21 +687,33 @@ void mt7996_dma_reset(struct mt7996_dev *dev, bool force)
 	if (force)
 		mt7996_wfsys_reset(dev);
 
+	if (dev->hif2 && mtk_wed_device_active(&dev->mt76.mmio.wed_hif2))
+		mtk_wed_device_dma_reset(&dev->mt76.mmio.wed_hif2);
+
+	if (mtk_wed_device_active(&dev->mt76.mmio.wed))
+		mtk_wed_device_dma_reset(&dev->mt76.mmio.wed);
+
 	mt7996_dma_disable(dev, force);
+	mt76_dma_wed_reset(&dev->mt76);
 
 	/* reset hw queues */
 	for (i = 0; i < __MT_TXQ_MAX; i++) {
-		mt76_queue_reset(dev, dev->mphy.q_tx[i]);
+		mt76_dma_reset_tx_queue(&dev->mt76, dev->mphy.q_tx[i]);
 		if (phy2)
-			mt76_queue_reset(dev, phy2->q_tx[i]);
+			mt76_dma_reset_tx_queue(&dev->mt76, phy2->q_tx[i]);
 		if (phy3)
-			mt76_queue_reset(dev, phy3->q_tx[i]);
+			mt76_dma_reset_tx_queue(&dev->mt76, phy3->q_tx[i]);
 	}
 
 	for (i = 0; i < __MT_MCUQ_MAX; i++)
 		mt76_queue_reset(dev, dev->mt76.q_mcu[i]);
 
 	mt76_for_each_q_rx(&dev->mt76, i) {
+		if (mtk_wed_device_active(&dev->mt76.mmio.wed))
+			if (mt76_queue_is_wed_rro(&dev->mt76.q_rx[i]) ||
+			    mt76_queue_is_wed_tx_free(&dev->mt76.q_rx[i]))
+				continue;
+
 		mt76_queue_reset(dev, &dev->mt76.q_rx[i]);
 	}
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.c
index 544b6c6f1ea3..4a8237118287 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.c
@@ -14,7 +14,9 @@ static int mt7996_check_eeprom(struct mt7996_dev *dev)
 
 	switch (val) {
 	case 0x7990:
-		return 0;
+		return is_mt7996(&dev->mt76) ? 0 : -EINVAL;
+	case 0x7992:
+		return is_mt7992(&dev->mt76) ? 0 : -EINVAL;
 	default:
 		return -EINVAL;
 	}
@@ -22,8 +24,14 @@ static int mt7996_check_eeprom(struct mt7996_dev *dev)
 
 static char *mt7996_eeprom_name(struct mt7996_dev *dev)
 {
-	/* reserve for future variants */
-	return MT7996_EEPROM_DEFAULT;
+	switch (mt76_chip(&dev->mt76)) {
+	case 0x7990:
+		return MT7996_EEPROM_DEFAULT;
+	case 0x7992:
+		return MT7992_EEPROM_DEFAULT;
+	default:
+		return MT7996_EEPROM_DEFAULT;
+	}
 }
 
 static int
@@ -103,7 +111,8 @@ static int mt7996_eeprom_parse_efuse_hw_cap(struct mt7996_dev *dev)
 		dev->wtbl_size_group = u32_get_bits(cap, WTBL_SIZE_GROUP);
 	}
 
-	if (dev->wtbl_size_group < 2 || dev->wtbl_size_group > 4)
+	if (dev->wtbl_size_group < 2 || dev->wtbl_size_group > 4 ||
+	    is_mt7992(&dev->mt76))
 		dev->wtbl_size_group = 2; /* set default */
 
 	return 0;
@@ -148,36 +157,49 @@ static int mt7996_eeprom_parse_band_config(struct mt7996_phy *phy)
 
 int mt7996_eeprom_parse_hw_cap(struct mt7996_dev *dev, struct mt7996_phy *phy)
 {
-	u8 path, nss, band_idx = phy->mt76->band_idx;
+	u8 path, rx_path, nss, band_idx = phy->mt76->band_idx;
 	u8 *eeprom = dev->mt76.eeprom.data;
 	struct mt76_phy *mphy = phy->mt76;
+	int max_path = 5, max_nss = 4;
 	int ret;
 
 	switch (band_idx) {
 	case MT_BAND1:
 		path = FIELD_GET(MT_EE_WIFI_CONF2_TX_PATH_BAND1,
 				 eeprom[MT_EE_WIFI_CONF + 2]);
+		rx_path = FIELD_GET(MT_EE_WIFI_CONF3_RX_PATH_BAND1,
+				    eeprom[MT_EE_WIFI_CONF + 3]);
 		nss = FIELD_GET(MT_EE_WIFI_CONF5_STREAM_NUM_BAND1,
 				eeprom[MT_EE_WIFI_CONF + 5]);
 		break;
 	case MT_BAND2:
 		path = FIELD_GET(MT_EE_WIFI_CONF2_TX_PATH_BAND2,
 				 eeprom[MT_EE_WIFI_CONF + 2]);
+		rx_path = FIELD_GET(MT_EE_WIFI_CONF4_RX_PATH_BAND2,
+				    eeprom[MT_EE_WIFI_CONF + 4]);
 		nss = FIELD_GET(MT_EE_WIFI_CONF5_STREAM_NUM_BAND2,
 				eeprom[MT_EE_WIFI_CONF + 5]);
 		break;
 	default:
 		path = FIELD_GET(MT_EE_WIFI_CONF1_TX_PATH_BAND0,
 				 eeprom[MT_EE_WIFI_CONF + 1]);
+		rx_path = FIELD_GET(MT_EE_WIFI_CONF3_RX_PATH_BAND0,
+				    eeprom[MT_EE_WIFI_CONF + 3]);
 		nss = FIELD_GET(MT_EE_WIFI_CONF4_STREAM_NUM_BAND0,
 				eeprom[MT_EE_WIFI_CONF + 4]);
 		break;
 	}
 
-	if (!path || path > 4)
-		path = 4;
+	if (!path || path > max_path)
+		path = max_path;
+
+	if (!nss || nss > max_nss)
+		nss = max_nss;
+
+	nss = min_t(u8, nss, path);
 
-	nss = min_t(u8, min_t(u8, 4, nss), path);
+	if (path != rx_path)
+		phy->has_aux_rx = true;
 
 	mphy->antenna_mask = BIT(nss) - 1;
 	mphy->chainmask = (BIT(path) - 1) << dev->chainshift[band_idx];
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.h b/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.h
index 0c749774f6b1..412d6e2f8014 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.h
@@ -33,6 +33,9 @@ enum mt7996_eeprom_field {
 #define MT_EE_WIFI_CONF1_TX_PATH_BAND0		GENMASK(5, 3)
 #define MT_EE_WIFI_CONF2_TX_PATH_BAND1		GENMASK(2, 0)
 #define MT_EE_WIFI_CONF2_TX_PATH_BAND2		GENMASK(5, 3)
+#define MT_EE_WIFI_CONF3_RX_PATH_BAND0		GENMASK(2, 0)
+#define MT_EE_WIFI_CONF3_RX_PATH_BAND1		GENMASK(5, 3)
+#define MT_EE_WIFI_CONF4_RX_PATH_BAND2		GENMASK(2, 0)
 #define MT_EE_WIFI_CONF4_STREAM_NUM_BAND0	GENMASK(5, 3)
 #define MT_EE_WIFI_CONF5_STREAM_NUM_BAND1	GENMASK(2, 0)
 #define MT_EE_WIFI_CONF5_STREAM_NUM_BAND2	GENMASK(5, 3)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/init.c b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
index 55cb1770fa34..0cf0d1fe420a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
@@ -5,6 +5,8 @@
 
 #include <linux/etherdevice.h>
 #include <linux/of.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
 #include <linux/thermal.h>
 #include "mt7996.h"
 #include "mac.h"
@@ -43,6 +45,183 @@ static const struct ieee80211_iface_combination if_comb[] = {
 	}
 };
 
+static ssize_t mt7996_thermal_temp_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	struct mt7996_phy *phy = dev_get_drvdata(dev);
+	int i = to_sensor_dev_attr(attr)->index;
+	int temperature;
+
+	switch (i) {
+	case 0:
+		temperature = mt7996_mcu_get_temperature(phy);
+		if (temperature < 0)
+			return temperature;
+		/* display in millidegree celcius */
+		return sprintf(buf, "%u\n", temperature * 1000);
+	case 1:
+	case 2:
+		return sprintf(buf, "%u\n",
+			       phy->throttle_temp[i - 1] * 1000);
+	case 3:
+		return sprintf(buf, "%hhu\n", phy->throttle_state);
+	default:
+		return -EINVAL;
+	}
+}
+
+static ssize_t mt7996_thermal_temp_store(struct device *dev,
+					 struct device_attribute *attr,
+					 const char *buf, size_t count)
+{
+	struct mt7996_phy *phy = dev_get_drvdata(dev);
+	int ret, i = to_sensor_dev_attr(attr)->index;
+	long val;
+
+	ret = kstrtol(buf, 10, &val);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&phy->dev->mt76.mutex);
+	val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), 40, 130);
+
+	/* add a safety margin ~10 */
+	if ((i - 1 == MT7996_CRIT_TEMP_IDX &&
+	     val > phy->throttle_temp[MT7996_MAX_TEMP_IDX] - 10) ||
+	    (i - 1 == MT7996_MAX_TEMP_IDX &&
+	     val - 10 < phy->throttle_temp[MT7996_CRIT_TEMP_IDX])) {
+		dev_err(phy->dev->mt76.dev,
+			"temp1_max shall be 10 degrees higher than temp1_crit.");
+		mutex_unlock(&phy->dev->mt76.mutex);
+		return -EINVAL;
+	}
+
+	phy->throttle_temp[i - 1] = val;
+	mutex_unlock(&phy->dev->mt76.mutex);
+
+	ret = mt7996_mcu_set_thermal_protect(phy, true);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+static SENSOR_DEVICE_ATTR_RO(temp1_input, mt7996_thermal_temp, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_crit, mt7996_thermal_temp, 1);
+static SENSOR_DEVICE_ATTR_RW(temp1_max, mt7996_thermal_temp, 2);
+static SENSOR_DEVICE_ATTR_RO(throttle1, mt7996_thermal_temp, 3);
+
+static struct attribute *mt7996_hwmon_attrs[] = {
+	&sensor_dev_attr_temp1_input.dev_attr.attr,
+	&sensor_dev_attr_temp1_crit.dev_attr.attr,
+	&sensor_dev_attr_temp1_max.dev_attr.attr,
+	&sensor_dev_attr_throttle1.dev_attr.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(mt7996_hwmon);
+
+static int
+mt7996_thermal_get_max_throttle_state(struct thermal_cooling_device *cdev,
+				      unsigned long *state)
+{
+	*state = MT7996_CDEV_THROTTLE_MAX;
+
+	return 0;
+}
+
+static int
+mt7996_thermal_get_cur_throttle_state(struct thermal_cooling_device *cdev,
+				      unsigned long *state)
+{
+	struct mt7996_phy *phy = cdev->devdata;
+
+	*state = phy->cdev_state;
+
+	return 0;
+}
+
+static int
+mt7996_thermal_set_cur_throttle_state(struct thermal_cooling_device *cdev,
+				      unsigned long state)
+{
+	struct mt7996_phy *phy = cdev->devdata;
+	u8 throttling = MT7996_THERMAL_THROTTLE_MAX - state;
+	int ret;
+
+	if (state > MT7996_CDEV_THROTTLE_MAX) {
+		dev_err(phy->dev->mt76.dev,
+			"please specify a valid throttling state\n");
+		return -EINVAL;
+	}
+
+	if (state == phy->cdev_state)
+		return 0;
+
+	/* cooling_device convention: 0 = no cooling, more = more cooling
+	 * mcu convention: 1 = max cooling, more = less cooling
+	 */
+	ret = mt7996_mcu_set_thermal_throttling(phy, throttling);
+	if (ret)
+		return ret;
+
+	phy->cdev_state = state;
+
+	return 0;
+}
+
+static const struct thermal_cooling_device_ops mt7996_thermal_ops = {
+	.get_max_state = mt7996_thermal_get_max_throttle_state,
+	.get_cur_state = mt7996_thermal_get_cur_throttle_state,
+	.set_cur_state = mt7996_thermal_set_cur_throttle_state,
+};
+
+static void mt7996_unregister_thermal(struct mt7996_phy *phy)
+{
+	struct wiphy *wiphy = phy->mt76->hw->wiphy;
+
+	if (!phy->cdev)
+		return;
+
+	sysfs_remove_link(&wiphy->dev.kobj, "cooling_device");
+	thermal_cooling_device_unregister(phy->cdev);
+}
+
+static int mt7996_thermal_init(struct mt7996_phy *phy)
+{
+	struct wiphy *wiphy = phy->mt76->hw->wiphy;
+	struct thermal_cooling_device *cdev;
+	struct device *hwmon;
+	const char *name;
+
+	name = devm_kasprintf(&wiphy->dev, GFP_KERNEL, "mt7996_%s",
+			      wiphy_name(wiphy));
+
+	cdev = thermal_cooling_device_register(name, phy, &mt7996_thermal_ops);
+	if (!IS_ERR(cdev)) {
+		if (sysfs_create_link(&wiphy->dev.kobj, &cdev->device.kobj,
+				      "cooling_device") < 0)
+			thermal_cooling_device_unregister(cdev);
+		else
+			phy->cdev = cdev;
+	}
+
+	/* initialize critical/maximum high temperature */
+	phy->throttle_temp[MT7996_CRIT_TEMP_IDX] = MT7996_CRIT_TEMP;
+	phy->throttle_temp[MT7996_MAX_TEMP_IDX] = MT7996_MAX_TEMP;
+
+	if (!IS_REACHABLE(CONFIG_HWMON))
+		return 0;
+
+	hwmon = devm_hwmon_device_register_with_groups(&wiphy->dev, name, phy,
+						       mt7996_hwmon_groups);
+
+	if (IS_ERR(hwmon))
+		return PTR_ERR(hwmon);
+
+	return 0;
+}
+
 static void mt7996_led_set_config(struct led_classdev *led_cdev,
 				  u8 delay_on, u8 delay_off)
 {
@@ -109,10 +288,11 @@ static void mt7996_led_set_brightness(struct led_classdev *led_cdev,
 		mt7996_led_set_config(led_cdev, 0xff, 0);
 }
 
-void mt7996_init_txpower(struct mt7996_dev *dev,
-			 struct ieee80211_supported_band *sband)
+static void __mt7996_init_txpower(struct mt7996_phy *phy,
+				  struct ieee80211_supported_band *sband)
 {
-	int i, nss = hweight8(dev->mphy.antenna_mask);
+	struct mt7996_dev *dev = phy->dev;
+	int i, nss = hweight16(phy->mt76->chainmask);
 	int nss_delta = mt76_tx_power_nss_delta(nss);
 	int pwr_delta = mt7996_eeprom_get_power_delta(dev, sband->band);
 	struct mt76_power_limits limits;
@@ -122,7 +302,7 @@ void mt7996_init_txpower(struct mt7996_dev *dev,
 		int target_power = mt7996_eeprom_get_target_power(dev, chan);
 
 		target_power += pwr_delta;
-		target_power = mt76_get_rate_power_limits(&dev->mphy, chan,
+		target_power = mt76_get_rate_power_limits(phy->mt76, chan,
 							  &limits,
 							  target_power);
 		target_power += nss_delta;
@@ -133,6 +313,19 @@ void mt7996_init_txpower(struct mt7996_dev *dev,
 	}
 }
 
+void mt7996_init_txpower(struct mt7996_phy *phy)
+{
+	if (!phy)
+		return;
+
+	if (phy->mt76->cap.has_2ghz)
+		__mt7996_init_txpower(phy, &phy->mt76->sband_2g.sband);
+	if (phy->mt76->cap.has_5ghz)
+		__mt7996_init_txpower(phy, &phy->mt76->sband_5g.sband);
+	if (phy->mt76->cap.has_6ghz)
+		__mt7996_init_txpower(phy, &phy->mt76->sband_6g.sband);
+}
+
 static void
 mt7996_regd_notifier(struct wiphy *wiphy,
 		     struct regulatory_request *request)
@@ -147,16 +340,14 @@ mt7996_regd_notifier(struct wiphy *wiphy,
 	if (dev->mt76.region == NL80211_DFS_UNSET)
 		mt7996_mcu_rdd_background_enable(phy, NULL);
 
-	mt7996_init_txpower(dev, &phy->mt76->sband_2g.sband);
-	mt7996_init_txpower(dev, &phy->mt76->sband_5g.sband);
-	mt7996_init_txpower(dev, &phy->mt76->sband_6g.sband);
+	mt7996_init_txpower(phy);
 
 	phy->mt76->dfs_state = MT_DFS_STATE_UNKNOWN;
 	mt7996_dfs_init_radar_detector(phy);
 }
 
 static void
-mt7996_init_wiphy(struct ieee80211_hw *hw)
+mt7996_init_wiphy(struct ieee80211_hw *hw, struct mtk_wed_device *wed)
 {
 	struct mt7996_phy *phy = mt7996_hw_phy(hw);
 	struct mt76_dev *mdev = &phy->dev->mt76;
@@ -168,11 +359,14 @@ mt7996_init_wiphy(struct ieee80211_hw *hw)
 	hw->max_rx_aggregation_subframes = max_subframes;
 	hw->max_tx_aggregation_subframes = max_subframes;
 	hw->netdev_features = NETIF_F_RXCSUM;
+	if (mtk_wed_device_active(wed))
+		hw->netdev_features |= NETIF_F_HW_TC;
 
 	hw->radiotap_timestamp.units_pos =
 		IEEE80211_RADIOTAP_TIMESTAMP_UNIT_US;
 
 	phy->slottime = 9;
+	phy->beacon_rate = -1;
 
 	hw->sta_data_size = sizeof(struct mt7996_sta);
 	hw->vif_data_size = sizeof(struct mt7996_vif);
@@ -242,6 +436,7 @@ mt7996_init_wiphy(struct ieee80211_hw *hw)
 	mt76_set_stream_caps(phy->mt76, true);
 	mt7996_set_stream_vht_txbf_caps(phy);
 	mt7996_set_stream_he_eht_caps(phy);
+	mt7996_init_txpower(phy);
 
 	wiphy->available_antennas_rx = phy->mt76->antenna_mask;
 	wiphy->available_antennas_tx = phy->mt76->antenna_mask;
@@ -287,11 +482,12 @@ static void mt7996_mac_init_basic_rates(struct mt7996_dev *dev)
 
 	for (i = 0; i < ARRAY_SIZE(mt76_rates); i++) {
 		u16 rate = mt76_rates[i].hw_value;
-		u16 idx = MT7996_BASIC_RATES_TBL + i;
+		/* odd index for driver, even index for firmware */
+		u16 idx = MT7996_BASIC_RATES_TBL + 2 * i;
 
 		rate = FIELD_PREP(MT_TX_RATE_MODE, rate >> 8) |
 		       FIELD_PREP(MT_TX_RATE_IDX, rate & GENMASK(7, 0));
-		mt7996_mac_set_fixed_rate_table(dev, idx, rate);
+		mt7996_mcu_set_fixed_rate_table(&dev->phy, idx, rate, false);
 	}
 }
 
@@ -317,9 +513,23 @@ void mt7996_mac_init(struct mt7996_dev *dev)
 	mt76_rmw_field(dev, MT_DMA_TCRF1(2), MT_DMA_TCRF1_QIDX, 0);
 
 	/* rro module init */
-	mt7996_mcu_set_rro(dev, UNI_RRO_SET_PLATFORM_TYPE, 2);
-	mt7996_mcu_set_rro(dev, UNI_RRO_SET_BYPASS_MODE, 3);
-	mt7996_mcu_set_rro(dev, UNI_RRO_SET_TXFREE_PATH, 1);
+	if (is_mt7996(&dev->mt76))
+		mt7996_mcu_set_rro(dev, UNI_RRO_SET_PLATFORM_TYPE, 2);
+	else
+		mt7996_mcu_set_rro(dev, UNI_RRO_SET_PLATFORM_TYPE,
+				   dev->hif2 ? 7 : 0);
+
+	if (dev->has_rro) {
+		u16 timeout;
+
+		timeout = mt76_rr(dev, MT_HW_REV) == MT_HW_REV1 ? 512 : 128;
+		mt7996_mcu_set_rro(dev, UNI_RRO_SET_FLUSH_TIMEOUT, timeout);
+		mt7996_mcu_set_rro(dev, UNI_RRO_SET_BYPASS_MODE, 1);
+		mt7996_mcu_set_rro(dev, UNI_RRO_SET_TXFREE_PATH, 0);
+	} else {
+		mt7996_mcu_set_rro(dev, UNI_RRO_SET_BYPASS_MODE, 3);
+		mt7996_mcu_set_rro(dev, UNI_RRO_SET_TXFREE_PATH, 1);
+	}
 
 	mt7996_mcu_wa_cmd(dev, MCU_WA_PARAM_CMD(SET),
 			  MCU_WA_PARAM_HW_PATH_HIF_VER,
@@ -335,7 +545,8 @@ int mt7996_txbf_init(struct mt7996_dev *dev)
 {
 	int ret;
 
-	if (dev->dbdc_support) {
+	if (mt7996_band_valid(dev, MT_BAND1) ||
+	    mt7996_band_valid(dev, MT_BAND2)) {
 		ret = mt7996_mcu_set_txbf(dev, BF_MOD_EN_CTRL);
 		if (ret)
 			return ret;
@@ -356,19 +567,18 @@ static int mt7996_register_phy(struct mt7996_dev *dev, struct mt7996_phy *phy,
 	struct mt76_phy *mphy;
 	u32 mac_ofs, hif1_ofs = 0;
 	int ret;
+	struct mtk_wed_device *wed = &dev->mt76.mmio.wed;
 
-	if (band != MT_BAND1 && band != MT_BAND2)
-		return 0;
-
-	if ((band == MT_BAND1 && !dev->dbdc_support) ||
-	    (band == MT_BAND2 && !dev->tbtc_support))
+	if (!mt7996_band_valid(dev, band) || band == MT_BAND0)
 		return 0;
 
 	if (phy)
 		return 0;
 
-	if (band == MT_BAND2 && dev->hif2)
+	if (is_mt7996(&dev->mt76) && band == MT_BAND2 && dev->hif2) {
 		hif1_ofs = MT_WFDMA0_PCIE1(0) - MT_WFDMA0(0);
+		wed = &dev->mt76.mmio.wed_hif2;
+	}
 
 	mphy = mt76_alloc_phy(&dev->mt76, sizeof(*phy), &mt7996_ops, band);
 	if (!mphy)
@@ -401,11 +611,12 @@ static int mt7996_register_phy(struct mt7996_dev *dev, struct mt7996_phy *phy,
 	mt76_eeprom_override(mphy);
 
 	/* init wiphy according to mphy and phy */
-	mt7996_init_wiphy(mphy->hw);
-	ret = mt76_connac_init_tx_queues(phy->mt76,
-					 MT_TXQ_ID(band),
-					 MT7996_TX_RING_SIZE,
-					 MT_TXQ_RING_BASE(band) + hif1_ofs, 0);
+	mt7996_init_wiphy(mphy->hw, wed);
+	ret = mt7996_init_tx_queues(mphy->priv,
+				    MT_TXQ_ID(band),
+				    MT7996_TX_RING_SIZE,
+				    MT_TXQ_RING_BASE(band) + hif1_ofs,
+				    wed);
 	if (ret)
 		goto error;
 
@@ -414,10 +625,21 @@ static int mt7996_register_phy(struct mt7996_dev *dev, struct mt7996_phy *phy,
 	if (ret)
 		goto error;
 
+	ret = mt7996_thermal_init(phy);
+	if (ret)
+		goto error;
+
 	ret = mt7996_init_debugfs(phy);
 	if (ret)
 		goto error;
 
+	if (wed == &dev->mt76.mmio.wed_hif2 && mtk_wed_device_active(wed)) {
+		u32 irq_mask = dev->mt76.mmio.irqmask | MT_INT_TX_DONE_BAND2;
+
+		mt76_wr(dev, MT_INT1_MASK_CSR, irq_mask);
+		mtk_wed_device_start(&dev->mt76.mmio.wed_hif2, irq_mask);
+	}
+
 	return 0;
 
 error:
@@ -434,6 +656,8 @@ mt7996_unregister_phy(struct mt7996_phy *phy, enum mt76_band_id band)
 	if (!phy)
 		return;
 
+	mt7996_unregister_thermal(phy);
+
 	mphy = phy->dev->mt76.phys[band];
 	mt76_unregister_phy(mphy);
 	ieee80211_free_hw(mphy->hw);
@@ -447,9 +671,6 @@ static void mt7996_init_work(struct work_struct *work)
 
 	mt7996_mcu_set_eeprom(dev);
 	mt7996_mac_init(dev);
-	mt7996_init_txpower(dev, &dev->mphy.sband_2g.sband);
-	mt7996_init_txpower(dev, &dev->mphy.sband_5g.sband);
-	mt7996_init_txpower(dev, &dev->mphy.sband_6g.sband);
 	mt7996_txbf_init(dev);
 }
 
@@ -462,16 +683,225 @@ void mt7996_wfsys_reset(struct mt7996_dev *dev)
 	msleep(20);
 }
 
+static int mt7996_wed_rro_init(struct mt7996_dev *dev)
+{
+#ifdef CONFIG_NET_MEDIATEK_SOC_WED
+	struct mtk_wed_device *wed = &dev->mt76.mmio.wed;
+	u32 reg = MT_RRO_ADDR_ELEM_SEG_ADDR0;
+	struct mt7996_wed_rro_addr *addr;
+	void *ptr;
+	int i;
+
+	if (!dev->has_rro)
+		return 0;
+
+	if (!mtk_wed_device_active(wed))
+		return 0;
+
+	for (i = 0; i < ARRAY_SIZE(dev->wed_rro.ba_bitmap); i++) {
+		ptr = dmam_alloc_coherent(dev->mt76.dma_dev,
+					  MT7996_RRO_BA_BITMAP_CR_SIZE,
+					  &dev->wed_rro.ba_bitmap[i].phy_addr,
+					  GFP_KERNEL);
+		if (!ptr)
+			return -ENOMEM;
+
+		dev->wed_rro.ba_bitmap[i].ptr = ptr;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(dev->wed_rro.addr_elem); i++) {
+		int j;
+
+		ptr = dmam_alloc_coherent(dev->mt76.dma_dev,
+				MT7996_RRO_WINDOW_MAX_SIZE * sizeof(*addr),
+				&dev->wed_rro.addr_elem[i].phy_addr,
+				GFP_KERNEL);
+		if (!ptr)
+			return -ENOMEM;
+
+		dev->wed_rro.addr_elem[i].ptr = ptr;
+		memset(dev->wed_rro.addr_elem[i].ptr, 0,
+		       MT7996_RRO_WINDOW_MAX_SIZE * sizeof(*addr));
+
+		addr = dev->wed_rro.addr_elem[i].ptr;
+		for (j = 0; j < MT7996_RRO_WINDOW_MAX_SIZE; j++) {
+			addr->signature = 0xff;
+			addr++;
+		}
+
+		wed->wlan.ind_cmd.addr_elem_phys[i] =
+			dev->wed_rro.addr_elem[i].phy_addr;
+	}
+
+	ptr = dmam_alloc_coherent(dev->mt76.dma_dev,
+				  MT7996_RRO_WINDOW_MAX_LEN * sizeof(*addr),
+				  &dev->wed_rro.session.phy_addr,
+				  GFP_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
+	dev->wed_rro.session.ptr = ptr;
+	addr = dev->wed_rro.session.ptr;
+	for (i = 0; i < MT7996_RRO_WINDOW_MAX_LEN; i++) {
+		addr->signature = 0xff;
+		addr++;
+	}
+
+	/* rro hw init */
+	/* TODO: remove line after WM has set */
+	mt76_clear(dev, WF_RRO_AXI_MST_CFG, WF_RRO_AXI_MST_CFG_DIDX_OK);
+
+	/* setup BA bitmap cache address */
+	mt76_wr(dev, MT_RRO_BA_BITMAP_BASE0,
+		dev->wed_rro.ba_bitmap[0].phy_addr);
+	mt76_wr(dev, MT_RRO_BA_BITMAP_BASE1, 0);
+	mt76_wr(dev, MT_RRO_BA_BITMAP_BASE_EXT0,
+		dev->wed_rro.ba_bitmap[1].phy_addr);
+	mt76_wr(dev, MT_RRO_BA_BITMAP_BASE_EXT1, 0);
+
+	/* setup Address element address */
+	for (i = 0; i < ARRAY_SIZE(dev->wed_rro.addr_elem); i++) {
+		mt76_wr(dev, reg, dev->wed_rro.addr_elem[i].phy_addr >> 4);
+		reg += 4;
+	}
+
+	/* setup Address element address - separate address segment mode */
+	mt76_wr(dev, MT_RRO_ADDR_ARRAY_BASE1,
+		MT_RRO_ADDR_ARRAY_ELEM_ADDR_SEG_MODE);
+
+	wed->wlan.ind_cmd.win_size = ffs(MT7996_RRO_WINDOW_MAX_LEN) - 6;
+	wed->wlan.ind_cmd.particular_sid = MT7996_RRO_MAX_SESSION;
+	wed->wlan.ind_cmd.particular_se_phys = dev->wed_rro.session.phy_addr;
+	wed->wlan.ind_cmd.se_group_nums = MT7996_RRO_ADDR_ELEM_LEN;
+	wed->wlan.ind_cmd.ack_sn_addr = MT_RRO_ACK_SN_CTRL;
+
+	mt76_wr(dev, MT_RRO_IND_CMD_SIGNATURE_BASE0, 0x15010e00);
+	mt76_set(dev, MT_RRO_IND_CMD_SIGNATURE_BASE1,
+		 MT_RRO_IND_CMD_SIGNATURE_BASE1_EN);
+
+	/* particular session configure */
+	/* use max session idx + 1 as particular session id */
+	mt76_wr(dev, MT_RRO_PARTICULAR_CFG0, dev->wed_rro.session.phy_addr);
+	mt76_wr(dev, MT_RRO_PARTICULAR_CFG1,
+		MT_RRO_PARTICULAR_CONFG_EN |
+		FIELD_PREP(MT_RRO_PARTICULAR_SID, MT7996_RRO_MAX_SESSION));
+
+	/* interrupt enable */
+	mt76_wr(dev, MT_RRO_HOST_INT_ENA,
+		MT_RRO_HOST_INT_ENA_HOST_RRO_DONE_ENA);
+
+	/* rro ind cmd queue init */
+	return mt7996_dma_rro_init(dev);
+#else
+	return 0;
+#endif
+}
+
+static void mt7996_wed_rro_free(struct mt7996_dev *dev)
+{
+#ifdef CONFIG_NET_MEDIATEK_SOC_WED
+	int i;
+
+	if (!dev->has_rro)
+		return;
+
+	if (!mtk_wed_device_active(&dev->mt76.mmio.wed))
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(dev->wed_rro.ba_bitmap); i++) {
+		if (!dev->wed_rro.ba_bitmap[i].ptr)
+			continue;
+
+		dmam_free_coherent(dev->mt76.dma_dev,
+				   MT7996_RRO_BA_BITMAP_CR_SIZE,
+				   dev->wed_rro.ba_bitmap[i].ptr,
+				   dev->wed_rro.ba_bitmap[i].phy_addr);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(dev->wed_rro.addr_elem); i++) {
+		if (!dev->wed_rro.addr_elem[i].ptr)
+			continue;
+
+		dmam_free_coherent(dev->mt76.dma_dev,
+				   MT7996_RRO_WINDOW_MAX_SIZE *
+				   sizeof(struct mt7996_wed_rro_addr),
+				   dev->wed_rro.addr_elem[i].ptr,
+				   dev->wed_rro.addr_elem[i].phy_addr);
+	}
+
+	if (!dev->wed_rro.session.ptr)
+		return;
+
+	dmam_free_coherent(dev->mt76.dma_dev,
+			   MT7996_RRO_WINDOW_MAX_LEN *
+			   sizeof(struct mt7996_wed_rro_addr),
+			   dev->wed_rro.session.ptr,
+			   dev->wed_rro.session.phy_addr);
+#endif
+}
+
+static void mt7996_wed_rro_work(struct work_struct *work)
+{
+#ifdef CONFIG_NET_MEDIATEK_SOC_WED
+	struct mt7996_dev *dev;
+	LIST_HEAD(list);
+
+	dev = (struct mt7996_dev *)container_of(work, struct mt7996_dev,
+						wed_rro.work);
+
+	spin_lock_bh(&dev->wed_rro.lock);
+	list_splice_init(&dev->wed_rro.poll_list, &list);
+	spin_unlock_bh(&dev->wed_rro.lock);
+
+	while (!list_empty(&list)) {
+		struct mt7996_wed_rro_session_id *e;
+		int i;
+
+		e = list_first_entry(&list, struct mt7996_wed_rro_session_id,
+				     list);
+		list_del_init(&e->list);
+
+		for (i = 0; i < MT7996_RRO_WINDOW_MAX_LEN; i++) {
+			void *ptr = dev->wed_rro.session.ptr;
+			struct mt7996_wed_rro_addr *elem;
+			u32 idx, elem_id = i;
+
+			if (e->id == MT7996_RRO_MAX_SESSION)
+				goto reset;
+
+			idx = e->id / MT7996_RRO_BA_BITMAP_SESSION_SIZE;
+			if (idx >= ARRAY_SIZE(dev->wed_rro.addr_elem))
+				goto out;
+
+			ptr = dev->wed_rro.addr_elem[idx].ptr;
+			elem_id +=
+				(e->id % MT7996_RRO_BA_BITMAP_SESSION_SIZE) *
+				MT7996_RRO_WINDOW_MAX_LEN;
+reset:
+			elem = ptr + elem_id * sizeof(*elem);
+			elem->signature = 0xff;
+		}
+		mt7996_mcu_wed_rro_reset_sessions(dev, e->id);
+out:
+		kfree(e);
+	}
+#endif
+}
+
 static int mt7996_init_hardware(struct mt7996_dev *dev)
 {
 	int ret, idx;
 
 	mt76_wr(dev, MT_INT_SOURCE_CSR, ~0);
+	if (is_mt7992(&dev->mt76)) {
+		mt76_rmw(dev, MT_AFE_CTL_BAND_PLL_03(MT_BAND0), MT_AFE_CTL_BAND_PLL_03_MSB_EN, 0);
+		mt76_rmw(dev, MT_AFE_CTL_BAND_PLL_03(MT_BAND1), MT_AFE_CTL_BAND_PLL_03_MSB_EN, 0);
+	}
 
 	INIT_WORK(&dev->init_work, mt7996_init_work);
-
-	dev->dbdc_support = true;
-	dev->tbtc_support = true;
+	INIT_WORK(&dev->wed_rro.work, mt7996_wed_rro_work);
+	INIT_LIST_HEAD(&dev->wed_rro.poll_list);
+	spin_lock_init(&dev->wed_rro.lock);
 
 	ret = mt7996_dma_init(dev);
 	if (ret)
@@ -483,6 +913,10 @@ static int mt7996_init_hardware(struct mt7996_dev *dev)
 	if (ret)
 		return ret;
 
+	ret = mt7996_wed_rro_init(dev);
+	if (ret)
+		return ret;
+
 	ret = mt7996_eeprom_init(dev);
 	if (ret < 0)
 		return ret;
@@ -889,14 +1323,16 @@ int mt7996_register_device(struct mt7996_dev *dev)
 	if (ret)
 		return ret;
 
-	mt7996_init_wiphy(hw);
+	mt7996_init_wiphy(hw, &dev->mt76.mmio.wed);
 
 	ret = mt76_register_device(&dev->mt76, true, mt76_rates,
 				   ARRAY_SIZE(mt76_rates));
 	if (ret)
 		return ret;
 
-	ieee80211_queue_work(mt76_hw(dev), &dev->init_work);
+	ret = mt7996_thermal_init(&dev->phy);
+	if (ret)
+		return ret;
 
 	ret = mt7996_register_phy(dev, mt7996_phy2(dev), MT_BAND1);
 	if (ret)
@@ -906,21 +1342,35 @@ int mt7996_register_device(struct mt7996_dev *dev)
 	if (ret)
 		return ret;
 
+	ieee80211_queue_work(mt76_hw(dev), &dev->init_work);
+
 	dev->recovery.hw_init_done = true;
 
 	ret = mt7996_init_debugfs(&dev->phy);
 	if (ret)
-		return ret;
+		goto error;
+
+	ret = mt7996_coredump_register(dev);
+	if (ret)
+		goto error;
 
-	return mt7996_coredump_register(dev);
+	return 0;
+
+error:
+	cancel_work_sync(&dev->init_work);
+
+	return ret;
 }
 
 void mt7996_unregister_device(struct mt7996_dev *dev)
 {
+	cancel_work_sync(&dev->wed_rro.work);
 	mt7996_unregister_phy(mt7996_phy3(dev), MT_BAND2);
 	mt7996_unregister_phy(mt7996_phy2(dev), MT_BAND1);
+	mt7996_unregister_thermal(&dev->phy);
 	mt7996_coredump_unregister(dev);
 	mt76_unregister_device(&dev->mt76);
+	mt7996_wed_rro_free(dev);
 	mt7996_mcu_exit(dev);
 	mt7996_tx_token_put(dev);
 	mt7996_dma_cleanup(dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 04540833485f..53258488d49f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -102,7 +102,6 @@ static void mt7996_mac_sta_poll(struct mt7996_dev *dev)
 	};
 	struct ieee80211_sta *sta;
 	struct mt7996_sta *msta;
-	struct rate_info *rate;
 	u32 tx_time[IEEE80211_NUM_ACS], rx_time[IEEE80211_NUM_ACS];
 	LIST_HEAD(sta_poll_list);
 	int i;
@@ -118,7 +117,6 @@ static void mt7996_mac_sta_poll(struct mt7996_dev *dev)
 		u32 addr, val;
 		u16 idx;
 		s8 rssi[4];
-		u8 bw;
 
 		spin_lock_bh(&dev->mt76.sta_poll_lock);
 		if (list_empty(&sta_poll_list)) {
@@ -174,49 +172,6 @@ static void mt7996_mac_sta_poll(struct mt7996_dev *dev)
 			ieee80211_sta_register_airtime(sta, tid, tx_cur, rx_cur);
 		}
 
-		/* We don't support reading GI info from txs packets.
-		 * For accurate tx status reporting and AQL improvement,
-		 * we need to make sure that flags match so polling GI
-		 * from per-sta counters directly.
-		 */
-		rate = &msta->wcid.rate;
-
-		switch (rate->bw) {
-		case RATE_INFO_BW_320:
-			bw = IEEE80211_STA_RX_BW_320;
-			break;
-		case RATE_INFO_BW_160:
-			bw = IEEE80211_STA_RX_BW_160;
-			break;
-		case RATE_INFO_BW_80:
-			bw = IEEE80211_STA_RX_BW_80;
-			break;
-		case RATE_INFO_BW_40:
-			bw = IEEE80211_STA_RX_BW_40;
-			break;
-		default:
-			bw = IEEE80211_STA_RX_BW_20;
-			break;
-		}
-
-		addr = mt7996_mac_wtbl_lmac_addr(dev, idx, 6);
-		val = mt76_rr(dev, addr);
-		if (rate->flags & RATE_INFO_FLAGS_EHT_MCS) {
-			addr = mt7996_mac_wtbl_lmac_addr(dev, idx, 5);
-			val = mt76_rr(dev, addr);
-			rate->eht_gi = FIELD_GET(GENMASK(25, 24), val);
-		} else if (rate->flags & RATE_INFO_FLAGS_HE_MCS) {
-			u8 offs = 24 + 2 * bw;
-
-			rate->he_gi = (val & (0x3 << offs)) >> offs;
-		} else if (rate->flags &
-			   (RATE_INFO_FLAGS_VHT_MCS | RATE_INFO_FLAGS_MCS)) {
-			if (val & BIT(12 + bw))
-				rate->flags |= RATE_INFO_FLAGS_SHORT_GI;
-			else
-				rate->flags &= ~RATE_INFO_FLAGS_SHORT_GI;
-		}
-
 		/* get signal strength of resp frames (CTS/BA/ACK) */
 		addr = mt7996_mac_wtbl_lmac_addr(dev, idx, 34);
 		val = mt76_rr(dev, addr);
@@ -248,17 +203,6 @@ void mt7996_mac_enable_rtscts(struct mt7996_dev *dev,
 		mt76_clear(dev, addr, BIT(5));
 }
 
-void mt7996_mac_set_fixed_rate_table(struct mt7996_dev *dev,
-				     u8 tbl_idx, u16 rate_idx)
-{
-	u32 ctrl = MT_WTBL_ITCR_WR | MT_WTBL_ITCR_EXEC | tbl_idx;
-
-	mt76_wr(dev, MT_WTBL_ITDR0, rate_idx);
-	/* use wtbl spe idx */
-	mt76_wr(dev, MT_WTBL_ITDR1, MT_WTBL_SPE_IDX_SEL);
-	mt76_wr(dev, MT_WTBL_ITCR, ctrl);
-}
-
 /* The HW does not translate the mac header to 802.3 for mesh point */
 static int mt7996_reverse_frag0_hdr_trans(struct sk_buff *skb, u16 hdr_gap)
 {
@@ -449,8 +393,36 @@ mt7996_mac_fill_rx_rate(struct mt7996_dev *dev,
 	return 0;
 }
 
+static void
+mt7996_wed_check_ppe(struct mt7996_dev *dev, struct mt76_queue *q,
+		     struct mt7996_sta *msta, struct sk_buff *skb,
+		     u32 info)
+{
+	struct ieee80211_vif *vif;
+	struct wireless_dev *wdev;
+
+	if (!msta || !msta->vif)
+		return;
+
+	if (!mt76_queue_is_wed_rx(q))
+		return;
+
+	if (!(info & MT_DMA_INFO_PPE_VLD))
+		return;
+
+	vif = container_of((void *)msta->vif, struct ieee80211_vif,
+			   drv_priv);
+	wdev = ieee80211_vif_to_wdev(vif);
+	skb->dev = wdev->netdev;
+
+	mtk_wed_device_ppe_check(&dev->mt76.mmio.wed, skb,
+				 FIELD_GET(MT_DMA_PPE_CPU_REASON, info),
+				 FIELD_GET(MT_DMA_PPE_ENTRY, info));
+}
+
 static int
-mt7996_mac_fill_rx(struct mt7996_dev *dev, struct sk_buff *skb)
+mt7996_mac_fill_rx(struct mt7996_dev *dev, enum mt76_rxq_id q,
+		   struct sk_buff *skb, u32 *info)
 {
 	struct mt76_rx_status *status = (struct mt76_rx_status *)skb->cb;
 	struct mt76_phy *mphy = &dev->mt76.phy;
@@ -475,7 +447,10 @@ mt7996_mac_fill_rx(struct mt7996_dev *dev, struct sk_buff *skb)
 	u16 seq_ctrl = 0;
 	__le16 fc = 0;
 	int idx;
+	u8 hw_aggr = false;
+	struct mt7996_sta *msta = NULL;
 
+	hw_aggr = status->aggr;
 	memset(status, 0, sizeof(*status));
 
 	band_idx = FIELD_GET(MT_RXD1_NORMAL_BAND_IDX, rxd1);
@@ -502,8 +477,6 @@ mt7996_mac_fill_rx(struct mt7996_dev *dev, struct sk_buff *skb)
 	status->wcid = mt7996_rx_get_wcid(dev, idx, unicast);
 
 	if (status->wcid) {
-		struct mt7996_sta *msta;
-
 		msta = container_of(status->wcid, struct mt7996_sta, wcid);
 		spin_lock_bh(&dev->mt76.sta_poll_lock);
 		if (list_empty(&msta->wcid.poll_list))
@@ -708,12 +681,14 @@ mt7996_mac_fill_rx(struct mt7996_dev *dev, struct sk_buff *skb)
 		}
 	} else {
 		status->flag |= RX_FLAG_8023;
+		mt7996_wed_check_ppe(dev, &dev->mt76.q_rx[q], msta, skb,
+				     *info);
 	}
 
 	if (rxv && mode >= MT_PHY_TYPE_HE_SU && !(status->flag & RX_FLAG_8023))
 		mt76_connac3_mac_decode_he_radiotap(skb, rxv, mode);
 
-	if (!status->wcid || !ieee80211_is_data_qos(fc))
+	if (!status->wcid || !ieee80211_is_data_qos(fc) || hw_aggr)
 		return 0;
 
 	status->aggr = unicast &&
@@ -840,10 +815,10 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 	struct mt76_vif *mvif;
 	u16 tx_count = 15;
 	u32 val;
-	bool beacon = !!(changed & (BSS_CHANGED_BEACON |
-				    BSS_CHANGED_BEACON_ENABLED));
 	bool inband_disc = !!(changed & (BSS_CHANGED_UNSOL_BCAST_PROBE_RESP |
 					 BSS_CHANGED_FILS_DISCOVERY));
+	bool beacon = !!(changed & (BSS_CHANGED_BEACON |
+				    BSS_CHANGED_BEACON_ENABLED)) && (!inband_disc);
 
 	mvif = vif ? (struct mt76_vif *)vif->drv_priv : NULL;
 	if (mvif) {
@@ -898,8 +873,11 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 		val |= MT_TXD5_TX_STATUS_HOST;
 	txwi[5] = cpu_to_le32(val);
 
-	val = MT_TXD6_DIS_MAT | MT_TXD6_DAS |
-	      FIELD_PREP(MT_TXD6_MSDU_CNT, 1);
+	val = MT_TXD6_DIS_MAT | MT_TXD6_DAS;
+	if (is_mt7996(&dev->mt76))
+		val |= FIELD_PREP(MT_TXD6_MSDU_CNT, 1);
+	else
+		val |= FIELD_PREP(MT_TXD6_MSDU_CNT_V2, 1);
 	txwi[6] = cpu_to_le32(val);
 	txwi[7] = 0;
 
@@ -923,7 +901,8 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 				idx = mvif->basic_rates_idx;
 		}
 
-		txwi[6] |= cpu_to_le32(FIELD_PREP(MT_TXD6_TX_RATE, idx));
+		val = FIELD_PREP(MT_TXD6_TX_RATE, idx) | MT_TXD6_FIXED_BW;
+		txwi[6] |= cpu_to_le32(val);
 		txwi[3] |= cpu_to_le32(MT_TXD3_BA_DISABLE);
 	}
 }
@@ -963,8 +942,16 @@ int mt7996_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 
 	txp = (struct mt76_connac_txp_common *)(txwi + MT_TXD_SIZE);
 	for (i = 0; i < nbuf; i++) {
+		u16 len;
+
+		len = FIELD_PREP(MT_TXP_BUF_LEN, tx_info->buf[i + 1].len);
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+		len |= FIELD_PREP(MT_TXP_DMA_ADDR_H,
+				  tx_info->buf[i + 1].addr >> 32);
+#endif
+
 		txp->fw.buf[i] = cpu_to_le32(tx_info->buf[i + 1].addr);
-		txp->fw.len[i] = cpu_to_le16(tx_info->buf[i + 1].len);
+		txp->fw.len[i] = cpu_to_le16(len);
 	}
 	txp->fw.nbuf = nbuf;
 
@@ -996,6 +983,29 @@ int mt7996_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 	return 0;
 }
 
+u32 mt7996_wed_init_buf(void *ptr, dma_addr_t phys, int token_id)
+{
+	struct mt76_connac_fw_txp *txp = ptr + MT_TXD_SIZE;
+	__le32 *txwi = ptr;
+	u32 val;
+
+	memset(ptr, 0, MT_TXD_SIZE + sizeof(*txp));
+
+	val = FIELD_PREP(MT_TXD0_TX_BYTES, MT_TXD_SIZE) |
+	      FIELD_PREP(MT_TXD0_PKT_FMT, MT_TX_TYPE_CT);
+	txwi[0] = cpu_to_le32(val);
+
+	val = BIT(31) |
+	      FIELD_PREP(MT_TXD1_HDR_FORMAT, MT_HDR_FORMAT_802_3);
+	txwi[1] = cpu_to_le32(val);
+
+	txp->token = cpu_to_le16(token_id);
+	txp->nbuf = 1;
+	txp->buf[0] = cpu_to_le32(phys + MT_TXD_SIZE + sizeof(*txp));
+
+	return MT_TXD_SIZE + sizeof(*txp);
+}
+
 static void
 mt7996_tx_check_aggr(struct ieee80211_sta *sta, struct sk_buff *skb)
 {
@@ -1074,7 +1084,7 @@ mt7996_mac_tx_free(struct mt7996_dev *dev, void *data, int len)
 	struct mt76_phy *phy3 = mdev->phys[MT_BAND2];
 	struct mt76_txwi_cache *txwi;
 	struct ieee80211_sta *sta = NULL;
-	struct mt76_wcid *wcid;
+	struct mt76_wcid *wcid = NULL;
 	LIST_HEAD(free_list);
 	struct sk_buff *skb, *tmp;
 	void *end = data + len;
@@ -1254,6 +1264,8 @@ mt7996_mac_add_txs_skb(struct mt7996_dev *dev, struct mt76_wcid *wcid,
 			goto out;
 
 		rate.flags = RATE_INFO_FLAGS_VHT_MCS;
+		if (wcid->rate.flags & RATE_INFO_FLAGS_SHORT_GI)
+			rate.flags |= RATE_INFO_FLAGS_SHORT_GI;
 		break;
 	case MT_PHY_TYPE_HE_SU:
 	case MT_PHY_TYPE_HE_EXT_SU:
@@ -1403,6 +1415,12 @@ void mt7996_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
 
 	switch (type) {
 	case PKT_TYPE_TXRX_NOTIFY:
+		if (mtk_wed_device_active(&dev->mt76.mmio.wed_hif2) &&
+		    q == MT_RXQ_TXFREE_BAND2) {
+			dev_kfree_skb(skb);
+			break;
+		}
+
 		mt7996_mac_tx_free(dev, skb->data, skb->len);
 		napi_consume_skb(skb, 1);
 		break;
@@ -1419,7 +1437,7 @@ void mt7996_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
 		dev_kfree_skb(skb);
 		break;
 	case PKT_TYPE_NORMAL:
-		if (!mt7996_mac_fill_rx(dev, skb)) {
+		if (!mt7996_mac_fill_rx(dev, q, skb, info)) {
 			mt76_rx(&dev->mt76, q, skb);
 			return;
 		}
@@ -1525,7 +1543,7 @@ mt7996_phy_get_nf(struct mt7996_phy *phy, u8 band_idx)
 
 void mt7996_update_channel(struct mt76_phy *mphy)
 {
-	struct mt7996_phy *phy = (struct mt7996_phy *)mphy->priv;
+	struct mt7996_phy *phy = mphy->priv;
 	struct mt76_channel_state *state = mphy->chan_state;
 	int nf;
 
@@ -1652,6 +1670,10 @@ mt7996_mac_restart(struct mt7996_dev *dev)
 	/* disable all tx/rx napi */
 	mt76_worker_disable(&dev->mt76.tx_worker);
 	mt76_for_each_q_rx(mdev, i) {
+		if (mtk_wed_device_active(&dev->mt76.mmio.wed) &&
+		    mt76_queue_is_wed_rro(&mdev->q_rx[i]))
+			continue;
+
 		if (mdev->q_rx[i].ndesc)
 			napi_disable(&dev->mt76.napi[i]);
 	}
@@ -1665,6 +1687,10 @@ mt7996_mac_restart(struct mt7996_dev *dev)
 
 	local_bh_disable();
 	mt76_for_each_q_rx(mdev, i) {
+		if (mtk_wed_device_active(&dev->mt76.mmio.wed) &&
+		    mt76_queue_is_wed_rro(&mdev->q_rx[i]))
+			continue;
+
 		if (mdev->q_rx[i].ndesc) {
 			napi_enable(&dev->mt76.napi[i]);
 			napi_schedule(&dev->mt76.napi[i]);
@@ -1697,9 +1723,9 @@ mt7996_mac_restart(struct mt7996_dev *dev)
 		goto out;
 
 	mt7996_mac_init(dev);
-	mt7996_init_txpower(dev, &dev->mphy.sband_2g.sband);
-	mt7996_init_txpower(dev, &dev->mphy.sband_5g.sband);
-	mt7996_init_txpower(dev, &dev->mphy.sband_6g.sband);
+	mt7996_init_txpower(&dev->phy);
+	mt7996_init_txpower(phy2);
+	mt7996_init_txpower(phy3);
 	ret = mt7996_txbf_init(dev);
 
 	if (test_bit(MT76_STATE_RUNNING, &dev->mphy.state)) {
@@ -1754,6 +1780,7 @@ mt7996_mac_full_reset(struct mt7996_dev *dev)
 	if (phy3)
 		ieee80211_stop_queues(phy3->mt76->hw);
 
+	cancel_work_sync(&dev->wed_rro.work);
 	cancel_delayed_work_sync(&dev->mphy.mac_work);
 	if (phy2)
 		cancel_delayed_work_sync(&phy2->mt76->mac_work);
@@ -1836,6 +1863,13 @@ void mt7996_mac_reset_work(struct work_struct *work)
 
 	dev_info(dev->mt76.dev,"\n%s L1 SER recovery start.",
 		 wiphy_name(dev->mt76.hw->wiphy));
+
+	if (mtk_wed_device_active(&dev->mt76.mmio.wed_hif2))
+		mtk_wed_device_stop(&dev->mt76.mmio.wed_hif2);
+
+	if (mtk_wed_device_active(&dev->mt76.mmio.wed))
+		mtk_wed_device_stop(&dev->mt76.mmio.wed);
+
 	ieee80211_stop_queues(mt76_hw(dev));
 	if (phy2)
 		ieee80211_stop_queues(phy2->mt76->hw);
@@ -1845,6 +1879,8 @@ void mt7996_mac_reset_work(struct work_struct *work)
 	set_bit(MT76_RESET, &dev->mphy.state);
 	set_bit(MT76_MCU_RESET, &dev->mphy.state);
 	wake_up(&dev->mt76.mcu.wait);
+
+	cancel_work_sync(&dev->wed_rro.work);
 	cancel_delayed_work_sync(&dev->mphy.mac_work);
 	if (phy2) {
 		set_bit(MT76_RESET, &phy2->mt76->state);
@@ -1855,8 +1891,13 @@ void mt7996_mac_reset_work(struct work_struct *work)
 		cancel_delayed_work_sync(&phy3->mt76->mac_work);
 	}
 	mt76_worker_disable(&dev->mt76.tx_worker);
-	mt76_for_each_q_rx(&dev->mt76, i)
+	mt76_for_each_q_rx(&dev->mt76, i) {
+		if (mtk_wed_device_active(&dev->mt76.mmio.wed) &&
+		    mt76_queue_is_wed_rro(&dev->mt76.q_rx[i]))
+			continue;
+
 		napi_disable(&dev->mt76.napi[i]);
+	}
 	napi_disable(&dev->mt76.tx_napi);
 
 	mutex_lock(&dev->mt76.mutex);
@@ -1877,7 +1918,28 @@ void mt7996_mac_reset_work(struct work_struct *work)
 	mt7996_wait_reset_state(dev, MT_MCU_CMD_NORMAL_STATE);
 
 	/* enable DMA Tx/Tx and interrupt */
-	mt7996_dma_start(dev, false);
+	mt7996_dma_start(dev, false, false);
+
+	if (mtk_wed_device_active(&dev->mt76.mmio.wed)) {
+		u32 wed_irq_mask = MT_INT_RRO_RX_DONE | MT_INT_TX_DONE_BAND2 |
+				   dev->mt76.mmio.irqmask;
+
+		if (mtk_wed_get_rx_capa(&dev->mt76.mmio.wed))
+			wed_irq_mask &= ~MT_INT_RX_DONE_RRO_IND;
+
+		mt76_wr(dev, MT_INT_MASK_CSR, wed_irq_mask);
+
+		mtk_wed_device_start_hw_rro(&dev->mt76.mmio.wed, wed_irq_mask,
+					    true);
+		mt7996_irq_enable(dev, wed_irq_mask);
+		mt7996_irq_disable(dev, 0);
+	}
+
+	if (mtk_wed_device_active(&dev->mt76.mmio.wed_hif2)) {
+		mt76_wr(dev, MT_INT_PCIE1_MASK_CSR, MT_INT_TX_RX_DONE_EXT);
+		mtk_wed_device_start(&dev->mt76.mmio.wed_hif2,
+				     MT_INT_TX_RX_DONE_EXT);
+	}
 
 	clear_bit(MT76_MCU_RESET, &dev->mphy.state);
 	clear_bit(MT76_RESET, &dev->mphy.state);
@@ -1888,6 +1950,10 @@ void mt7996_mac_reset_work(struct work_struct *work)
 
 	local_bh_disable();
 	mt76_for_each_q_rx(&dev->mt76, i) {
+		if (mtk_wed_device_active(&dev->mt76.mmio.wed) &&
+		    mt76_queue_is_wed_rro(&dev->mt76.q_rx[i]))
+			continue;
+
 		napi_enable(&dev->mt76.napi[i]);
 		napi_schedule(&dev->mt76.napi[i]);
 	}
@@ -2187,7 +2253,9 @@ void mt7996_mac_sta_rc_work(struct work_struct *work)
 			       IEEE80211_RC_BW_CHANGED))
 			mt7996_mcu_add_rate_ctrl(dev, vif, sta, true);
 
-		/* TODO: smps change */
+		if (changed & IEEE80211_RC_SMPS_CHANGED)
+			mt7996_mcu_set_fixed_field(dev, vif, sta, NULL,
+						   RATE_PARAM_MMPS_UPDATE);
 
 		spin_lock_bh(&dev->mt76.sta_poll_lock);
 	}
@@ -2212,6 +2280,7 @@ void mt7996_mac_work(struct work_struct *work)
 
 		mt7996_mac_update_stats(phy);
 
+		mt7996_mcu_get_all_sta_info(phy, UNI_ALL_STA_TXRX_RATE);
 		if (mtk_wed_device_active(&phy->dev->mt76.mmio.wed)) {
 			mt7996_mcu_get_all_sta_info(phy, UNI_ALL_STA_TXRX_ADM_STAT);
 			mt7996_mcu_get_all_sta_info(phy, UNI_ALL_STA_TXRX_MSDU_COUNT);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 09c7a28a3d51..51deea84b642 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -51,6 +51,14 @@ int mt7996_run(struct ieee80211_hw *hw)
 	if (ret)
 		goto out;
 
+	ret = mt7996_mcu_set_thermal_throttling(phy, MT7996_THERMAL_THROTTLE_MAX);
+	if (ret)
+		goto out;
+
+	ret = mt7996_mcu_set_thermal_protect(phy, true);
+	if (ret)
+		goto out;
+
 	set_bit(MT76_STATE_RUNNING, &phy->mt76->state);
 
 	ieee80211_queue_delayed_work(hw, &phy->mt76->mac_work,
@@ -342,6 +350,8 @@ static int mt7996_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 	case WLAN_CIPHER_SUITE_SMS4:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
 		break;
 	case WLAN_CIPHER_SUITE_WEP40:
 	case WLAN_CIPHER_SUITE_WEP104:
@@ -365,9 +375,13 @@ static int mt7996_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 	}
 
 	mt76_wcid_key_setup(&dev->mt76, wcid, key);
-	err = mt7996_mcu_add_key(&dev->mt76, vif, &msta->bip,
-				 key, MCU_WMWA_UNI_CMD(STA_REC_UPDATE),
-				 &msta->wcid, cmd);
+
+	if (key->keyidx == 6 || key->keyidx == 7)
+		err = mt7996_mcu_bcn_prot_enable(dev, vif, key);
+	else
+		err = mt7996_mcu_add_key(&dev->mt76, vif, key,
+					 MCU_WMWA_UNI_CMD(STA_REC_UPDATE),
+					 &msta->wcid, cmd);
 out:
 	mutex_unlock(&dev->mt76.mutex);
 
@@ -388,6 +402,13 @@ static int mt7996_config(struct ieee80211_hw *hw, u32 changed)
 		ieee80211_wake_queues(hw);
 	}
 
+	if (changed & (IEEE80211_CONF_CHANGE_POWER |
+		       IEEE80211_CONF_CHANGE_CHANNEL)) {
+		ret = mt7996_mcu_set_txpower_sku(phy);
+		if (ret)
+			return ret;
+	}
+
 	mutex_lock(&dev->mt76.mutex);
 
 	if (changed & IEEE80211_CONF_CHANGE_MONITOR) {
@@ -514,24 +535,25 @@ mt7996_get_rates_table(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv;
 	struct mt76_phy *mphy = hw->priv;
 	u16 rate;
-	u8 i, idx, ht;
+	u8 i, idx;
 
 	rate = mt76_connac2_mac_tx_rate_val(mphy, vif, beacon, mcast);
-	ht = FIELD_GET(MT_TX_RATE_MODE, rate) > MT_PHY_TYPE_OFDM;
 
-	if (beacon && ht) {
-		struct mt7996_dev *dev = mt7996_hw_dev(hw);
+	if (beacon) {
+		struct mt7996_phy *phy = mphy->priv;
+
+		/* odd index for driver, even index for firmware */
+		idx = MT7996_BEACON_RATES_TBL + 2 * phy->mt76->band_idx;
+		if (phy->beacon_rate != rate)
+			mt7996_mcu_set_fixed_rate_table(phy, idx, rate, beacon);
 
-		/* must odd index */
-		idx = MT7996_BEACON_RATES_TBL + 2 * (mvif->idx % 20);
-		mt7996_mac_set_fixed_rate_table(dev, idx, rate);
 		return idx;
 	}
 
 	idx = FIELD_GET(MT_TX_RATE_IDX, rate);
 	for (i = 0; i < ARRAY_SIZE(mt76_rates); i++)
 		if ((mt76_rates[i].hw_value & GENMASK(7, 0)) == idx)
-			return MT7996_BASIC_RATES_TBL + i;
+			return MT7996_BASIC_RATES_TBL + 2 * i;
 
 	return mvif->basic_rates_idx;
 }
@@ -956,8 +978,8 @@ mt7996_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant)
 	mt76_set_stream_caps(phy->mt76, true);
 	mt7996_set_stream_vht_txbf_caps(phy);
 	mt7996_set_stream_he_eht_caps(phy);
+	mt7996_mcu_set_txpower_sku(phy);
 
-	/* TODO: update bmc_wtbl spe_idx when antenna changes */
 	mutex_unlock(&dev->mt76.mutex);
 
 	return 0;
@@ -982,6 +1004,7 @@ static void mt7996_sta_statistics(struct ieee80211_hw *hw,
 			sinfo->txrate.he_gi = txrate->he_gi;
 			sinfo->txrate.he_dcm = txrate->he_dcm;
 			sinfo->txrate.he_ru_alloc = txrate->he_ru_alloc;
+			sinfo->txrate.eht_gi = txrate->eht_gi;
 		}
 		sinfo->txrate.flags = txrate->flags;
 		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
@@ -1388,6 +1411,44 @@ out:
 	return ret;
 }
 
+#ifdef CONFIG_NET_MEDIATEK_SOC_WED
+static int
+mt7996_net_fill_forward_path(struct ieee80211_hw *hw,
+			     struct ieee80211_vif *vif,
+			     struct ieee80211_sta *sta,
+			     struct net_device_path_ctx *ctx,
+			     struct net_device_path *path)
+{
+	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
+	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+	struct mt7996_dev *dev = mt7996_hw_dev(hw);
+	struct mt7996_phy *phy = mt7996_hw_phy(hw);
+	struct mtk_wed_device *wed = &dev->mt76.mmio.wed;
+
+	if (phy != &dev->phy && phy->mt76->band_idx == MT_BAND2)
+		wed = &dev->mt76.mmio.wed_hif2;
+
+	if (!mtk_wed_device_active(wed))
+		return -ENODEV;
+
+	if (msta->wcid.idx > MT7996_WTBL_STA)
+		return -EIO;
+
+	path->type = DEV_PATH_MTK_WDMA;
+	path->dev = ctx->dev;
+	path->mtk_wdma.wdma_idx = wed->wdma_idx;
+	path->mtk_wdma.bss = mvif->mt76.idx;
+	path->mtk_wdma.queue = 0;
+	path->mtk_wdma.wcid = msta->wcid.idx;
+
+	path->mtk_wdma.amsdu = mtk_wed_is_amsdu_supported(wed);
+	ctx->dev = NULL;
+
+	return 0;
+}
+
+#endif
+
 const struct ieee80211_ops mt7996_ops = {
 	.tx = mt7996_tx,
 	.start = mt7996_start,
@@ -1432,4 +1493,8 @@ const struct ieee80211_ops mt7996_ops = {
 	.sta_add_debugfs = mt7996_sta_add_debugfs,
 #endif
 	.set_radar_background = mt7996_set_radar_background,
+#ifdef CONFIG_NET_MEDIATEK_SOC_WED
+	.net_fill_forward_path = mt7996_net_fill_forward_path,
+	.net_setup_tc = mt76_net_setup_tc,
+#endif
 };
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index bf917beb9439..3c729b563edc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -10,6 +10,20 @@
 #include "mac.h"
 #include "eeprom.h"
 
+#define fw_name(_dev, name, ...)	({			\
+	char *_fw;						\
+	switch (mt76_chip(&(_dev)->mt76)) {			\
+	case 0x7992:						\
+		_fw = MT7992_##name;				\
+		break;						\
+	case 0x7990:						\
+	default:						\
+		_fw = MT7996_##name;				\
+		break;						\
+	}							\
+	_fw;							\
+})
+
 struct mt7996_patch_hdr {
 	char build_date[16];
 	char platform[4];
@@ -449,6 +463,43 @@ mt7996_mcu_ie_countdown(struct mt7996_dev *dev, struct sk_buff *skb)
 	}
 }
 
+static int
+mt7996_mcu_update_tx_gi(struct rate_info *rate, struct all_sta_trx_rate *mcu_rate)
+{
+	switch (mcu_rate->tx_mode) {
+	case MT_PHY_TYPE_CCK:
+	case MT_PHY_TYPE_OFDM:
+		break;
+	case MT_PHY_TYPE_HT:
+	case MT_PHY_TYPE_HT_GF:
+	case MT_PHY_TYPE_VHT:
+		if (mcu_rate->tx_gi)
+			rate->flags |= RATE_INFO_FLAGS_SHORT_GI;
+		else
+			rate->flags &= ~RATE_INFO_FLAGS_SHORT_GI;
+		break;
+	case MT_PHY_TYPE_HE_SU:
+	case MT_PHY_TYPE_HE_EXT_SU:
+	case MT_PHY_TYPE_HE_TB:
+	case MT_PHY_TYPE_HE_MU:
+		if (mcu_rate->tx_gi > NL80211_RATE_INFO_HE_GI_3_2)
+			return -EINVAL;
+		rate->he_gi = mcu_rate->tx_gi;
+		break;
+	case MT_PHY_TYPE_EHT_SU:
+	case MT_PHY_TYPE_EHT_TRIG:
+	case MT_PHY_TYPE_EHT_MU:
+		if (mcu_rate->tx_gi > NL80211_RATE_INFO_EHT_GI_3_2)
+			return -EINVAL;
+		rate->eht_gi = mcu_rate->tx_gi;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static void
 mt7996_mcu_rx_all_sta_info_event(struct mt7996_dev *dev, struct sk_buff *skb)
 {
@@ -465,6 +516,16 @@ mt7996_mcu_rx_all_sta_info_event(struct mt7996_dev *dev, struct sk_buff *skb)
 		struct mt76_wcid *wcid;
 
 		switch (le16_to_cpu(res->tag)) {
+		case UNI_ALL_STA_TXRX_RATE:
+			wlan_idx = le16_to_cpu(res->rate[i].wlan_idx);
+			wcid = rcu_dereference(dev->mt76.wcid[wlan_idx]);
+
+			if (!wcid)
+				break;
+
+			if (mt7996_mcu_update_tx_gi(&wcid->rate, &res->rate[i]))
+				dev_err(dev->mt76.dev, "Failed to update TX GI\n");
+			break;
 		case UNI_ALL_STA_TXRX_ADM_STAT:
 			wlan_idx = le16_to_cpu(res->adm_stat[i].wlan_idx);
 			wcid = rcu_dereference(dev->mt76.wcid[wlan_idx]);
@@ -498,6 +559,34 @@ mt7996_mcu_rx_all_sta_info_event(struct mt7996_dev *dev, struct sk_buff *skb)
 }
 
 static void
+mt7996_mcu_rx_thermal_notify(struct mt7996_dev *dev, struct sk_buff *skb)
+{
+#define THERMAL_NOTIFY_TAG 0x4
+#define THERMAL_NOTIFY 0x2
+	struct mt76_phy *mphy = &dev->mt76.phy;
+	struct mt7996_mcu_thermal_notify *n;
+	struct mt7996_phy *phy;
+
+	n = (struct mt7996_mcu_thermal_notify *)skb->data;
+
+	if (le16_to_cpu(n->tag) != THERMAL_NOTIFY_TAG)
+		return;
+
+	if (n->event_id != THERMAL_NOTIFY)
+		return;
+
+	if (n->band_idx > MT_BAND2)
+		return;
+
+	mphy = dev->mt76.phys[n->band_idx];
+	if (!mphy)
+		return;
+
+	phy = (struct mt7996_phy *)mphy->priv;
+	phy->throttle_state = n->duty_percent;
+}
+
+static void
 mt7996_mcu_rx_ext_event(struct mt7996_dev *dev, struct sk_buff *skb)
 {
 	struct mt7996_mcu_rxd *rxd = (struct mt7996_mcu_rxd *)skb->data;
@@ -520,6 +609,9 @@ mt7996_mcu_rx_unsolicited_event(struct mt7996_dev *dev, struct sk_buff *skb)
 	case MCU_EVENT_EXT:
 		mt7996_mcu_rx_ext_event(dev, skb);
 		break;
+	case MCU_UNI_EVENT_THERMAL:
+		mt7996_mcu_rx_thermal_notify(dev, skb);
+		break;
 	default:
 		break;
 	}
@@ -527,6 +619,73 @@ mt7996_mcu_rx_unsolicited_event(struct mt7996_dev *dev, struct sk_buff *skb)
 }
 
 static void
+mt7996_mcu_wed_rro_event(struct mt7996_dev *dev, struct sk_buff *skb)
+{
+	struct mt7996_mcu_wed_rro_event *event = (void *)skb->data;
+
+	if (!dev->has_rro)
+		return;
+
+	skb_pull(skb, sizeof(struct mt7996_mcu_rxd) + 4);
+
+	switch (le16_to_cpu(event->tag)) {
+	case UNI_WED_RRO_BA_SESSION_STATUS: {
+		struct mt7996_mcu_wed_rro_ba_event *e;
+
+		while (skb->len >= sizeof(*e)) {
+			struct mt76_rx_tid *tid;
+			struct mt76_wcid *wcid;
+			u16 idx;
+
+			e = (void *)skb->data;
+			idx = le16_to_cpu(e->wlan_id);
+			if (idx >= ARRAY_SIZE(dev->mt76.wcid))
+				break;
+
+			wcid = rcu_dereference(dev->mt76.wcid[idx]);
+			if (!wcid || !wcid->sta)
+				break;
+
+			if (e->tid >= ARRAY_SIZE(wcid->aggr))
+				break;
+
+			tid = rcu_dereference(wcid->aggr[e->tid]);
+			if (!tid)
+				break;
+
+			tid->id = le16_to_cpu(e->id);
+			skb_pull(skb, sizeof(*e));
+		}
+		break;
+	}
+	case UNI_WED_RRO_BA_SESSION_DELETE: {
+		struct mt7996_mcu_wed_rro_ba_delete_event *e;
+
+		while (skb->len >= sizeof(*e)) {
+			struct mt7996_wed_rro_session_id *session;
+
+			e = (void *)skb->data;
+			session = kzalloc(sizeof(*session), GFP_ATOMIC);
+			if (!session)
+				break;
+
+			session->id = le16_to_cpu(e->session_id);
+
+			spin_lock_bh(&dev->wed_rro.lock);
+			list_add_tail(&session->list, &dev->wed_rro.poll_list);
+			spin_unlock_bh(&dev->wed_rro.lock);
+
+			ieee80211_queue_work(mt76_hw(dev), &dev->wed_rro.work);
+			skb_pull(skb, sizeof(*e));
+		}
+		break;
+	}
+	default:
+		break;
+	}
+}
+
+static void
 mt7996_mcu_uni_rx_unsolicited_event(struct mt7996_dev *dev, struct sk_buff *skb)
 {
 	struct mt7996_mcu_rxd *rxd = (struct mt7996_mcu_rxd *)skb->data;
@@ -544,6 +703,9 @@ mt7996_mcu_uni_rx_unsolicited_event(struct mt7996_dev *dev, struct sk_buff *skb)
 	case MCU_UNI_EVENT_ALL_STA_INFO:
 		mt7996_mcu_rx_all_sta_info_event(dev, skb);
 		break;
+	case MCU_UNI_EVENT_WED_RRO:
+		mt7996_mcu_wed_rro_event(dev, skb);
+		break;
 	default:
 		break;
 	}
@@ -963,7 +1125,7 @@ int mt7996_mcu_set_timing(struct mt7996_phy *phy, struct ieee80211_vif *vif)
 }
 
 static int
-mt7996_mcu_sta_ba(struct mt76_dev *dev, struct mt76_vif *mvif,
+mt7996_mcu_sta_ba(struct mt7996_dev *dev, struct mt76_vif *mvif,
 		  struct ieee80211_ampdu_params *params,
 		  bool enable, bool tx)
 {
@@ -972,7 +1134,7 @@ mt7996_mcu_sta_ba(struct mt76_dev *dev, struct mt76_vif *mvif,
 	struct sk_buff *skb;
 	struct tlv *tlv;
 
-	skb = __mt76_connac_mcu_alloc_sta_req(dev, mvif, wcid,
+	skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, mvif, wcid,
 					      MT7996_STA_UPDATE_MAX_SIZE);
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
@@ -986,8 +1148,9 @@ mt7996_mcu_sta_ba(struct mt76_dev *dev, struct mt76_vif *mvif,
 	ba->ba_en = enable << params->tid;
 	ba->amsdu = params->amsdu;
 	ba->tid = params->tid;
+	ba->ba_rdd_rro = !tx && enable && dev->has_rro;
 
-	return mt76_mcu_skb_send_msg(dev, skb,
+	return mt76_mcu_skb_send_msg(&dev->mt76, skb,
 				     MCU_WMWA_UNI_CMD(STA_REC_UPDATE), true);
 }
 
@@ -1002,8 +1165,7 @@ int mt7996_mcu_add_tx_ba(struct mt7996_dev *dev,
 	if (enable && !params->amsdu)
 		msta->wcid.amsdu = false;
 
-	return mt7996_mcu_sta_ba(&dev->mt76, &mvif->mt76, params,
-				 enable, true);
+	return mt7996_mcu_sta_ba(dev, &mvif->mt76, params, enable, true);
 }
 
 int mt7996_mcu_add_rx_ba(struct mt7996_dev *dev,
@@ -1013,8 +1175,7 @@ int mt7996_mcu_add_rx_ba(struct mt7996_dev *dev,
 	struct mt7996_sta *msta = (struct mt7996_sta *)params->sta->drv_priv;
 	struct mt7996_vif *mvif = msta->vif;
 
-	return mt7996_mcu_sta_ba(&dev->mt76, &mvif->mt76, params,
-				 enable, false);
+	return mt7996_mcu_sta_ba(dev, &mvif->mt76, params, enable, false);
 }
 
 static void
@@ -1108,7 +1269,7 @@ mt7996_mcu_sta_eht_tlv(struct sk_buff *skb, struct ieee80211_sta *sta)
 static void
 mt7996_mcu_sta_ht_tlv(struct sk_buff *skb, struct ieee80211_sta *sta)
 {
-	struct sta_rec_ht *ht;
+	struct sta_rec_ht_uni *ht;
 	struct tlv *tlv;
 
 	if (!sta->deflink.ht_cap.ht_supported)
@@ -1116,8 +1277,12 @@ mt7996_mcu_sta_ht_tlv(struct sk_buff *skb, struct ieee80211_sta *sta)
 
 	tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_HT, sizeof(*ht));
 
-	ht = (struct sta_rec_ht *)tlv;
+	ht = (struct sta_rec_ht_uni *)tlv;
 	ht->ht_cap = cpu_to_le16(sta->deflink.ht_cap.cap);
+	ht->ampdu_param = u8_encode_bits(sta->deflink.ht_cap.ampdu_factor,
+					 IEEE80211_HT_AMPDU_PARM_FACTOR) |
+			  u8_encode_bits(sta->deflink.ht_cap.ampdu_density,
+					 IEEE80211_HT_AMPDU_PARM_DENSITY);
 }
 
 static void
@@ -1575,44 +1740,6 @@ mt7996_mcu_sta_bfee_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
 }
 
 static void
-mt7996_mcu_sta_phy_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
-		       struct ieee80211_vif *vif, struct ieee80211_sta *sta)
-{
-	struct sta_rec_phy *phy;
-	struct tlv *tlv;
-	u8 af = 0, mm = 0;
-
-	if (!sta->deflink.ht_cap.ht_supported && !sta->deflink.he_6ghz_capa.capa)
-		return;
-
-	tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_PHY, sizeof(*phy));
-
-	phy = (struct sta_rec_phy *)tlv;
-	if (sta->deflink.ht_cap.ht_supported) {
-		af = sta->deflink.ht_cap.ampdu_factor;
-		mm = sta->deflink.ht_cap.ampdu_density;
-	}
-
-	if (sta->deflink.vht_cap.vht_supported) {
-		u8 vht_af = FIELD_GET(IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK,
-				      sta->deflink.vht_cap.cap);
-
-		af = max_t(u8, af, vht_af);
-	}
-
-	if (sta->deflink.he_6ghz_capa.capa) {
-		af = le16_get_bits(sta->deflink.he_6ghz_capa.capa,
-				   IEEE80211_HE_6GHZ_CAP_MAX_AMPDU_LEN_EXP);
-		mm = le16_get_bits(sta->deflink.he_6ghz_capa.capa,
-				   IEEE80211_HE_6GHZ_CAP_MIN_MPDU_START);
-	}
-
-	phy->ampdu = FIELD_PREP(IEEE80211_HT_AMPDU_PARM_FACTOR, af) |
-		     FIELD_PREP(IEEE80211_HT_AMPDU_PARM_DENSITY, mm);
-	phy->max_ampdu_len = af;
-}
-
-static void
 mt7996_mcu_sta_hdrt_tlv(struct mt7996_dev *dev, struct sk_buff *skb)
 {
 	struct sta_rec_hdrt *hdrt;
@@ -1700,14 +1827,13 @@ int mt7996_mcu_set_fixed_rate_ctrl(struct mt7996_dev *dev,
 				     MCU_WM_UNI_CMD(RA), true);
 }
 
-static int
-mt7996_mcu_set_fixed_field(struct mt7996_dev *dev, struct ieee80211_vif *vif,
-			   struct ieee80211_sta *sta, void *data, u32 field)
+int mt7996_mcu_set_fixed_field(struct mt7996_dev *dev, struct ieee80211_vif *vif,
+			       struct ieee80211_sta *sta, void *data, u32 field)
 {
 	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
-	struct sta_phy *phy = data;
-	struct sta_rec_ra_fixed *ra;
+	struct sta_phy_uni *phy = data;
+	struct sta_rec_ra_fixed_uni *ra;
 	struct sk_buff *skb;
 	struct tlv *tlv;
 
@@ -1718,7 +1844,7 @@ mt7996_mcu_set_fixed_field(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 		return PTR_ERR(skb);
 
 	tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_RA_UPDATE, sizeof(*ra));
-	ra = (struct sta_rec_ra_fixed *)tlv;
+	ra = (struct sta_rec_ra_fixed_uni *)tlv;
 
 	switch (field) {
 	case RATE_PARAM_AUTO:
@@ -1730,6 +1856,9 @@ mt7996_mcu_set_fixed_field(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 		if (phy)
 			ra->phy = *phy;
 		break;
+	case RATE_PARAM_MMPS_UPDATE:
+		ra->mmps_mode = mt7996_mcu_get_mmps_mode(sta->deflink.smps_mode);
+		break;
 	default:
 		break;
 	}
@@ -1747,7 +1876,7 @@ mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev, struct ieee80211_vif *vif
 	struct cfg80211_chan_def *chandef = &mvif->phy->mt76->chandef;
 	struct cfg80211_bitrate_mask *mask = &mvif->bitrate_mask;
 	enum nl80211_band band = chandef->chan->band;
-	struct sta_phy phy = {};
+	struct sta_phy_uni phy = {};
 	int ret, nrates = 0;
 
 #define __sta_phy_bitrate_mask_check(_mcs, _gi, _ht, _he)			\
@@ -1835,13 +1964,13 @@ mt7996_mcu_sta_rate_ctrl_tlv(struct sk_buff *skb, struct mt7996_dev *dev,
 	struct cfg80211_chan_def *chandef = &mphy->chandef;
 	struct cfg80211_bitrate_mask *mask = &mvif->bitrate_mask;
 	enum nl80211_band band = chandef->chan->band;
-	struct sta_rec_ra *ra;
+	struct sta_rec_ra_uni *ra;
 	struct tlv *tlv;
 	u32 supp_rate = sta->deflink.supp_rates[band];
 	u32 cap = sta->wme ? STA_CAP_WMM : 0;
 
 	tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_RA, sizeof(*ra));
-	ra = (struct sta_rec_ra *)tlv;
+	ra = (struct sta_rec_ra_uni *)tlv;
 
 	ra->valid = true;
 	ra->auto_rate = true;
@@ -2018,8 +2147,6 @@ int mt7996_mcu_add_sta(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 
 	/* tag order is in accordance with firmware dependency. */
 	if (sta) {
-		/* starec phy */
-		mt7996_mcu_sta_phy_tlv(dev, skb, vif, sta);
 		/* starec hdrt mode */
 		mt7996_mcu_sta_hdrt_tlv(dev, skb);
 		/* starec bfer */
@@ -2058,7 +2185,6 @@ out:
 
 static int
 mt7996_mcu_sta_key_tlv(struct mt76_wcid *wcid,
-		       struct mt76_connac_sta_key_conf *sta_key_conf,
 		       struct sk_buff *skb,
 		       struct ieee80211_key_conf *key,
 		       enum set_key_cmd cmd)
@@ -2079,43 +2205,22 @@ mt7996_mcu_sta_key_tlv(struct mt76_wcid *wcid,
 			return -EOPNOTSUPP;
 
 		sec_key = &sec->key[0];
+		sec_key->wlan_idx = cpu_to_le16(wcid->idx);
+		sec_key->mgmt_prot = 0;
+		sec_key->cipher_id = cipher;
 		sec_key->cipher_len = sizeof(*sec_key);
-
-		if (cipher == MCU_CIPHER_BIP_CMAC_128) {
-			sec_key->wlan_idx = cpu_to_le16(wcid->idx);
-			sec_key->cipher_id = MCU_CIPHER_AES_CCMP;
-			sec_key->key_id = sta_key_conf->keyidx;
-			sec_key->key_len = 16;
-			memcpy(sec_key->key, sta_key_conf->key, 16);
-
-			sec_key = &sec->key[1];
-			sec_key->wlan_idx = cpu_to_le16(wcid->idx);
-			sec_key->cipher_id = MCU_CIPHER_BIP_CMAC_128;
-			sec_key->cipher_len = sizeof(*sec_key);
-			sec_key->key_len = 16;
-			memcpy(sec_key->key, key->key, 16);
-			sec->n_cipher = 2;
-		} else {
-			sec_key->wlan_idx = cpu_to_le16(wcid->idx);
-			sec_key->cipher_id = cipher;
-			sec_key->key_id = key->keyidx;
-			sec_key->key_len = key->keylen;
-			memcpy(sec_key->key, key->key, key->keylen);
-
-			if (cipher == MCU_CIPHER_TKIP) {
-				/* Rx/Tx MIC keys are swapped */
-				memcpy(sec_key->key + 16, key->key + 24, 8);
-				memcpy(sec_key->key + 24, key->key + 16, 8);
-			}
-
-			/* store key_conf for BIP batch update */
-			if (cipher == MCU_CIPHER_AES_CCMP) {
-				memcpy(sta_key_conf->key, key->key, key->keylen);
-				sta_key_conf->keyidx = key->keyidx;
-			}
-
-			sec->n_cipher = 1;
+		sec_key->key_id = key->keyidx;
+		sec_key->key_len = key->keylen;
+		sec_key->need_resp = 0;
+		memcpy(sec_key->key, key->key, key->keylen);
+
+		if (cipher == MCU_CIPHER_TKIP) {
+			/* Rx/Tx MIC keys are swapped */
+			memcpy(sec_key->key + 16, key->key + 24, 8);
+			memcpy(sec_key->key + 24, key->key + 16, 8);
 		}
+
+		sec->n_cipher = 1;
 	} else {
 		sec->n_cipher = 0;
 	}
@@ -2124,7 +2229,6 @@ mt7996_mcu_sta_key_tlv(struct mt76_wcid *wcid,
 }
 
 int mt7996_mcu_add_key(struct mt76_dev *dev, struct ieee80211_vif *vif,
-		       struct mt76_connac_sta_key_conf *sta_key_conf,
 		       struct ieee80211_key_conf *key, int mcu_cmd,
 		       struct mt76_wcid *wcid, enum set_key_cmd cmd)
 {
@@ -2137,13 +2241,99 @@ int mt7996_mcu_add_key(struct mt76_dev *dev, struct ieee80211_vif *vif,
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
 
-	ret = mt7996_mcu_sta_key_tlv(wcid, sta_key_conf, skb, key, cmd);
+	ret = mt7996_mcu_sta_key_tlv(wcid, skb, key, cmd);
 	if (ret)
 		return ret;
 
 	return mt76_mcu_skb_send_msg(dev, skb, mcu_cmd, true);
 }
 
+static int mt7996_mcu_get_pn(struct mt7996_dev *dev, struct ieee80211_vif *vif,
+			     u8 *pn)
+{
+#define TSC_TYPE_BIGTK_PN 2
+	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
+	struct sta_rec_pn_info *pn_info;
+	struct sk_buff *skb, *rskb;
+	struct tlv *tlv;
+	int ret;
+
+	skb = mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->mt76, &mvif->sta.wcid);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_PN_INFO, sizeof(*pn_info));
+	pn_info = (struct sta_rec_pn_info *)tlv;
+
+	pn_info->tsc_type = TSC_TYPE_BIGTK_PN;
+	ret = mt76_mcu_skb_send_and_get_msg(&dev->mt76, skb,
+					    MCU_WM_UNI_CMD_QUERY(STA_REC_UPDATE),
+					    true, &rskb);
+	if (ret)
+		return ret;
+
+	skb_pull(rskb, 4);
+
+	pn_info = (struct sta_rec_pn_info *)rskb->data;
+	if (le16_to_cpu(pn_info->tag) == STA_REC_PN_INFO)
+		memcpy(pn, pn_info->pn, 6);
+
+	dev_kfree_skb(rskb);
+	return 0;
+}
+
+int mt7996_mcu_bcn_prot_enable(struct mt7996_dev *dev, struct ieee80211_vif *vif,
+			       struct ieee80211_key_conf *key)
+{
+	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
+	struct mt7996_mcu_bcn_prot_tlv *bcn_prot;
+	struct sk_buff *skb;
+	struct tlv *tlv;
+	u8 pn[6] = {};
+	int len = sizeof(struct bss_req_hdr) +
+		  sizeof(struct mt7996_mcu_bcn_prot_tlv);
+	int ret;
+
+	skb = __mt7996_mcu_alloc_bss_req(&dev->mt76, &mvif->mt76, len);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	tlv = mt76_connac_mcu_add_tlv(skb, UNI_BSS_INFO_BCN_PROT, sizeof(*bcn_prot));
+
+	bcn_prot = (struct mt7996_mcu_bcn_prot_tlv *)tlv;
+
+	ret = mt7996_mcu_get_pn(dev, vif, pn);
+	if (ret) {
+		dev_kfree_skb(skb);
+		return ret;
+	}
+
+	switch (key->cipher) {
+	case WLAN_CIPHER_SUITE_AES_CMAC:
+		bcn_prot->cipher_id = MCU_CIPHER_BCN_PROT_CMAC_128;
+		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+		bcn_prot->cipher_id = MCU_CIPHER_BCN_PROT_GMAC_128;
+		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		bcn_prot->cipher_id = MCU_CIPHER_BCN_PROT_GMAC_256;
+		break;
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+	default:
+		dev_err(dev->mt76.dev, "Not supported Bigtk Cipher\n");
+		dev_kfree_skb(skb);
+		return -EOPNOTSUPP;
+	}
+
+	pn[0]++;
+	memcpy(bcn_prot->pn, pn, 6);
+	bcn_prot->enable = BP_SW_MODE;
+	memcpy(bcn_prot->key, key->key, WLAN_MAX_KEY_LEN);
+	bcn_prot->key_id = key->keyidx;
+
+	return mt76_mcu_skb_send_msg(&dev->mt76, skb,
+				     MCU_WMWA_UNI_CMD(BSS_INFO_UPDATE), true);
+}
 int mt7996_mcu_add_dev_info(struct mt7996_phy *phy,
 			    struct ieee80211_vif *vif, bool enable)
 {
@@ -2463,7 +2653,7 @@ static int mt7996_load_patch(struct mt7996_dev *dev)
 		return -EAGAIN;
 	}
 
-	ret = request_firmware(&fw, MT7996_ROM_PATCH, dev->mt76.dev);
+	ret = request_firmware(&fw, fw_name(dev, ROM_PATCH), dev->mt76.dev);
 	if (ret)
 		goto out;
 
@@ -2626,17 +2816,17 @@ static int mt7996_load_ram(struct mt7996_dev *dev)
 {
 	int ret;
 
-	ret = __mt7996_load_ram(dev, "WM", MT7996_FIRMWARE_WM,
+	ret = __mt7996_load_ram(dev, "WM", fw_name(dev, FIRMWARE_WM),
 				MT7996_RAM_TYPE_WM);
 	if (ret)
 		return ret;
 
-	ret = __mt7996_load_ram(dev, "DSP", MT7996_FIRMWARE_DSP,
+	ret = __mt7996_load_ram(dev, "DSP", fw_name(dev, FIRMWARE_DSP),
 				MT7996_RAM_TYPE_DSP);
 	if (ret)
 		return ret;
 
-	return __mt7996_load_ram(dev, "WA", MT7996_FIRMWARE_WA,
+	return __mt7996_load_ram(dev, "WA", fw_name(dev, FIRMWARE_WA),
 				 MT7996_RAM_TYPE_WA);
 }
 
@@ -2788,9 +2978,10 @@ mt7996_mcu_init_rx_airtime(struct mt7996_dev *dev)
 {
 	struct uni_header hdr = {};
 	struct sk_buff *skb;
-	int len, num;
+	int len, num, i;
 
-	num = 2 + 2 * (dev->dbdc_support + dev->tbtc_support);
+	num = 2 + 2 * (mt7996_band_valid(dev, MT_BAND1) +
+		       mt7996_band_valid(dev, MT_BAND2));
 	len = sizeof(hdr) + num * sizeof(struct vow_rx_airtime);
 	skb = mt76_mcu_msg_alloc(&dev->mt76, NULL, len);
 	if (!skb)
@@ -2798,13 +2989,10 @@ mt7996_mcu_init_rx_airtime(struct mt7996_dev *dev)
 
 	skb_put_data(skb, &hdr, sizeof(hdr));
 
-	mt7996_add_rx_airtime_tlv(skb, dev->mt76.phy.band_idx);
-
-	if (dev->dbdc_support)
-		mt7996_add_rx_airtime_tlv(skb, MT_BAND1);
-
-	if (dev->tbtc_support)
-		mt7996_add_rx_airtime_tlv(skb, MT_BAND2);
+	for (i = 0; i < __MT_MAX_BAND; i++) {
+		if (mt7996_band_valid(dev, i))
+			mt7996_add_rx_airtime_tlv(skb, i);
+	}
 
 	return mt76_mcu_skb_send_msg(&dev->mt76, skb,
 				     MCU_WM_UNI_CMD(VOW), true);
@@ -3230,7 +3418,7 @@ int mt7996_mcu_set_chan_info(struct mt7996_phy *phy, u16 tag)
 		.center_ch = ieee80211_frequency_to_channel(freq1),
 		.bw = mt76_connac_chan_bw(chandef),
 		.tx_path_num = hweight16(phy->mt76->chainmask),
-		.rx_path = phy->mt76->chainmask >> dev->chainshift[band_idx],
+		.rx_path = mt7996_rx_chainmask(phy) >> dev->chainshift[band_idx],
 		.band_idx = band_idx,
 		.channel_band = ch_band[chandef->chan->band],
 	};
@@ -3502,6 +3690,121 @@ out:
 	return 0;
 }
 
+int mt7996_mcu_get_temperature(struct mt7996_phy *phy)
+{
+#define TEMPERATURE_QUERY 0
+#define GET_TEMPERATURE 0
+	struct {
+		u8 _rsv[4];
+
+		__le16 tag;
+		__le16 len;
+
+		u8 rsv1;
+		u8 action;
+		u8 band_idx;
+		u8 rsv2;
+	} req = {
+		.tag = cpu_to_le16(TEMPERATURE_QUERY),
+		.len = cpu_to_le16(sizeof(req) - 4),
+		.action = GET_TEMPERATURE,
+		.band_idx = phy->mt76->band_idx,
+	};
+	struct mt7996_mcu_thermal {
+		u8 _rsv[4];
+
+		__le16 tag;
+		__le16 len;
+
+		__le32 rsv;
+		__le32 temperature;
+	} __packed * res;
+	struct sk_buff *skb;
+	int ret;
+
+	ret = mt76_mcu_send_and_get_msg(&phy->dev->mt76, MCU_WM_UNI_CMD(THERMAL),
+					&req, sizeof(req), true, &skb);
+	if (ret)
+		return ret;
+
+	res = (void *)skb->data;
+
+	return le32_to_cpu(res->temperature);
+}
+
+int mt7996_mcu_set_thermal_throttling(struct mt7996_phy *phy, u8 state)
+{
+	struct {
+		u8 _rsv[4];
+
+		__le16 tag;
+		__le16 len;
+
+		struct mt7996_mcu_thermal_ctrl ctrl;
+	} __packed req = {
+		.tag = cpu_to_le16(UNI_CMD_THERMAL_PROTECT_DUTY_CONFIG),
+		.len = cpu_to_le16(sizeof(req) - 4),
+		.ctrl = {
+			.band_idx = phy->mt76->band_idx,
+		},
+	};
+	int level, ret;
+
+	/* set duty cycle and level */
+	for (level = 0; level < 4; level++) {
+		req.ctrl.duty.duty_level = level;
+		req.ctrl.duty.duty_cycle = state;
+		state /= 2;
+
+		ret = mt76_mcu_send_msg(&phy->dev->mt76, MCU_WM_UNI_CMD(THERMAL),
+					&req, sizeof(req), false);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+int mt7996_mcu_set_thermal_protect(struct mt7996_phy *phy, bool enable)
+{
+#define SUSTAIN_PERIOD		10
+	struct {
+		u8 _rsv[4];
+
+		__le16 tag;
+		__le16 len;
+
+		struct mt7996_mcu_thermal_ctrl ctrl;
+		struct mt7996_mcu_thermal_enable enable;
+	} __packed req = {
+		.len = cpu_to_le16(sizeof(req) - 4 - sizeof(req.enable)),
+		.ctrl = {
+			.band_idx = phy->mt76->band_idx,
+			.type.protect_type = 1,
+			.type.trigger_type = 1,
+		},
+	};
+	int ret;
+
+	req.tag = cpu_to_le16(UNI_CMD_THERMAL_PROTECT_DISABLE);
+
+	ret = mt76_mcu_send_msg(&phy->dev->mt76, MCU_WM_UNI_CMD(THERMAL),
+				&req, sizeof(req) - sizeof(req.enable), false);
+	if (ret || !enable)
+		return ret;
+
+	/* set high-temperature trigger threshold */
+	req.tag = cpu_to_le16(UNI_CMD_THERMAL_PROTECT_ENABLE);
+	req.enable.restore_temp = cpu_to_le32(phy->throttle_temp[0]);
+	req.enable.trigger_temp = cpu_to_le32(phy->throttle_temp[1]);
+	req.enable.sustain_time = cpu_to_le16(SUSTAIN_PERIOD);
+
+	req.len = cpu_to_le16(sizeof(req) - 4);
+
+	return mt76_mcu_send_msg(&phy->dev->mt76, MCU_WM_UNI_CMD(THERMAL),
+				 &req, sizeof(req), false);
+}
+
 int mt7996_mcu_set_ser(struct mt7996_dev *dev, u8 action, u8 val, u8 band)
 {
 	struct {
@@ -3964,6 +4267,35 @@ int mt7996_mcu_wtbl_update_hdr_trans(struct mt7996_dev *dev,
 				     MCU_WMWA_UNI_CMD(STA_REC_UPDATE), true);
 }
 
+int mt7996_mcu_set_fixed_rate_table(struct mt7996_phy *phy, u8 table_idx,
+				    u16 rate_idx, bool beacon)
+{
+#define UNI_FIXED_RATE_TABLE_SET	0
+#define SPE_IXD_SELECT_TXD		0
+#define SPE_IXD_SELECT_BMC_WTBL		1
+	struct mt7996_dev *dev = phy->dev;
+	struct fixed_rate_table_ctrl req = {
+		.tag = cpu_to_le16(UNI_FIXED_RATE_TABLE_SET),
+		.len = cpu_to_le16(sizeof(req) - 4),
+		.table_idx = table_idx,
+		.rate_idx = cpu_to_le16(rate_idx),
+		.gi = 1,
+		.he_ltf = 1,
+	};
+	u8 band_idx = phy->mt76->band_idx;
+
+	if (beacon) {
+		req.spe_idx_sel = SPE_IXD_SELECT_TXD;
+		req.spe_idx = 24 + band_idx;
+		phy->beacon_rate = rate_idx;
+	} else {
+		req.spe_idx_sel = SPE_IXD_SELECT_BMC_WTBL;
+	}
+
+	return mt76_mcu_send_msg(&dev->mt76, MCU_WM_UNI_CMD(FIXED_RATE_TABLE),
+				 &req, sizeof(req), false);
+}
+
 int mt7996_mcu_rf_regval(struct mt7996_dev *dev, u32 regidx, u32 *val, bool set)
 {
 	struct {
@@ -4019,14 +4351,12 @@ int mt7996_mcu_trigger_assert(struct mt7996_dev *dev)
 				 &req, sizeof(req), false);
 }
 
-int mt7996_mcu_set_rro(struct mt7996_dev *dev, u16 tag, u8 val)
+int mt7996_mcu_set_rro(struct mt7996_dev *dev, u16 tag, u16 val)
 {
 	struct {
 		u8 __rsv1[4];
-
 		__le16 tag;
 		__le16 len;
-
 		union {
 			struct {
 				u8 type;
@@ -4041,6 +4371,11 @@ int mt7996_mcu_set_rro(struct mt7996_dev *dev, u16 tag, u8 val)
 				u8 path;
 				u8 __rsv2[3];
 			} __packed txfree_path;
+			struct {
+				__le16 flush_one;
+				__le16 flush_all;
+				u8 __rsv2[4];
+			} __packed timeout;
 		};
 	} __packed req = {
 		.tag = cpu_to_le16(tag),
@@ -4057,6 +4392,10 @@ int mt7996_mcu_set_rro(struct mt7996_dev *dev, u16 tag, u8 val)
 	case UNI_RRO_SET_TXFREE_PATH:
 		req.txfree_path.path = val;
 		break;
+	case UNI_RRO_SET_FLUSH_TIMEOUT:
+		req.timeout.flush_one = cpu_to_le16(val);
+		req.timeout.flush_all = cpu_to_le16(2 * val);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -4081,3 +4420,80 @@ int mt7996_mcu_get_all_sta_info(struct mt7996_phy *phy, u16 tag)
 	return mt76_mcu_send_msg(&dev->mt76, MCU_WM_UNI_CMD(ALL_STA_INFO),
 				 &req, sizeof(req), false);
 }
+
+int mt7996_mcu_wed_rro_reset_sessions(struct mt7996_dev *dev, u16 id)
+{
+	struct {
+		u8 __rsv[4];
+
+		__le16 tag;
+		__le16 len;
+		__le16 session_id;
+		u8 pad[4];
+	} __packed req = {
+		.tag = cpu_to_le16(UNI_RRO_DEL_BA_SESSION),
+		.len = cpu_to_le16(sizeof(req) - 4),
+		.session_id = cpu_to_le16(id),
+	};
+
+	return mt76_mcu_send_msg(&dev->mt76, MCU_WM_UNI_CMD(RRO), &req,
+				 sizeof(req), true);
+}
+
+int mt7996_mcu_set_txpower_sku(struct mt7996_phy *phy)
+{
+#define TX_POWER_LIMIT_TABLE_RATE	0
+	struct mt7996_dev *dev = phy->dev;
+	struct mt76_phy *mphy = phy->mt76;
+	struct ieee80211_hw *hw = mphy->hw;
+	struct tx_power_limit_table_ctrl {
+		u8 __rsv1[4];
+
+		__le16 tag;
+		__le16 len;
+		u8 power_ctrl_id;
+		u8 power_limit_type;
+		u8 band_idx;
+	} __packed req = {
+		.tag = cpu_to_le16(UNI_TXPOWER_POWER_LIMIT_TABLE_CTRL),
+		.len = cpu_to_le16(sizeof(req) + MT7996_SKU_RATE_NUM - 4),
+		.power_ctrl_id = UNI_TXPOWER_POWER_LIMIT_TABLE_CTRL,
+		.power_limit_type = TX_POWER_LIMIT_TABLE_RATE,
+		.band_idx = phy->mt76->band_idx,
+	};
+	struct mt76_power_limits la = {};
+	struct sk_buff *skb;
+	int i, tx_power;
+
+	tx_power = mt7996_get_power_bound(phy, hw->conf.power_level);
+	tx_power = mt76_get_rate_power_limits(mphy, mphy->chandef.chan,
+					      &la, tx_power);
+	mphy->txpower_cur = tx_power;
+
+	skb = mt76_mcu_msg_alloc(&dev->mt76, NULL,
+				 sizeof(req) + MT7996_SKU_RATE_NUM);
+	if (!skb)
+		return -ENOMEM;
+
+	skb_put_data(skb, &req, sizeof(req));
+	/* cck and ofdm */
+	skb_put_data(skb, &la.cck, sizeof(la.cck) + sizeof(la.ofdm));
+	/* ht20 */
+	skb_put_data(skb, &la.mcs[0], 8);
+	/* ht40 */
+	skb_put_data(skb, &la.mcs[1], 9);
+
+	/* vht */
+	for (i = 0; i < 4; i++) {
+		skb_put_data(skb, &la.mcs[i], sizeof(la.mcs[i]));
+		skb_put_zero(skb, 2);  /* padding */
+	}
+
+	/* he */
+	skb_put_data(skb, &la.ru[0], sizeof(la.ru));
+	/* eht */
+	skb_put_data(skb, &la.eht[0], sizeof(la.eht));
+
+	return mt76_mcu_skb_send_msg(&dev->mt76, skb,
+				     MCU_WM_UNI_CMD(TXPOWER), true);
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h
index a88f6af323da..36cacc495c75 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h
@@ -30,6 +30,28 @@ struct mt7996_mcu_uni_event {
 	__le32 status; /* 0: success, others: fail */
 } __packed;
 
+struct mt7996_mcu_thermal_ctrl {
+	u8 ctrl_id;
+	u8 band_idx;
+	union {
+		struct {
+			u8 protect_type; /* 1: duty admit, 2: radio off */
+			u8 trigger_type; /* 0: low, 1: high */
+		} __packed type;
+		struct {
+			u8 duty_level;	/* level 0~3 */
+			u8 duty_cycle;
+		} __packed duty;
+	};
+} __packed;
+
+struct mt7996_mcu_thermal_enable {
+	__le32 trigger_temp;
+	__le32 restore_temp;
+	__le16 sustain_time;
+	u8 rsv[2];
+} __packed;
+
 struct mt7996_mcu_csa_notify {
 	struct mt7996_mcu_rxd rxd;
 
@@ -153,6 +175,27 @@ struct mt7996_mcu_mib {
 	__le64 data;
 } __packed;
 
+struct all_sta_trx_rate {
+	__le16 wlan_idx;
+	u8 __rsv1[2];
+	u8 tx_mode;
+	u8 flags;
+	u8 tx_stbc;
+	u8 tx_gi;
+	u8 tx_bw;
+	u8 tx_ldpc;
+	u8 tx_mcs;
+	u8 tx_nss;
+	u8 rx_rate;
+	u8 rx_mode;
+	u8 rx_nsts;
+	u8 rx_gi;
+	u8 rx_coding;
+	u8 rx_stbc;
+	u8 rx_bw;
+	u8 __rsv2;
+} __packed;
+
 struct mt7996_mcu_all_sta_info_event {
 	u8 rsv[4];
 	__le16 tag;
@@ -160,23 +203,75 @@ struct mt7996_mcu_all_sta_info_event {
 	u8 more;
 	u8 rsv2;
 	__le16 sta_num;
-	u8 rsv3[2];
+	u8 rsv3[4];
 
 	union {
-		struct {
+		DECLARE_FLEX_ARRAY(struct all_sta_trx_rate, rate);
+		DECLARE_FLEX_ARRAY(struct {
 			__le16 wlan_idx;
 			u8 rsv[2];
 			__le32 tx_bytes[IEEE80211_NUM_ACS];
 			__le32 rx_bytes[IEEE80211_NUM_ACS];
-		} adm_stat[0];
+		} __packed, adm_stat);
 
-		struct {
+		DECLARE_FLEX_ARRAY(struct {
 			__le16 wlan_idx;
 			u8 rsv[2];
 			__le32 tx_msdu_cnt;
 			__le32 rx_msdu_cnt;
-		} msdu_cnt[0];
-	};
+		} __packed, msdu_cnt);
+	} __packed;
+} __packed;
+
+struct mt7996_mcu_wed_rro_event {
+	struct mt7996_mcu_rxd rxd;
+
+	u8 __rsv1[4];
+
+	__le16 tag;
+	__le16 len;
+} __packed;
+
+struct mt7996_mcu_wed_rro_ba_event {
+	__le16 tag;
+	__le16 len;
+
+	__le16 wlan_id;
+	u8 tid;
+	u8 __rsv1;
+	__le32 status;
+	__le16 id;
+	u8 __rsv2[2];
+} __packed;
+
+struct mt7996_mcu_wed_rro_ba_delete_event {
+	__le16 tag;
+	__le16 len;
+
+	__le16 session_id;
+	u8 __rsv2[2];
+} __packed;
+
+enum  {
+	UNI_WED_RRO_BA_SESSION_STATUS,
+	UNI_WED_RRO_BA_SESSION_TBL,
+	UNI_WED_RRO_BA_SESSION_DELETE,
+};
+
+struct mt7996_mcu_thermal_notify {
+	struct mt7996_mcu_rxd rxd;
+
+	u8 __rsv1[4];
+
+	__le16 tag;
+	__le16 len;
+
+	u8 event_id;
+	u8 band_idx;
+	u8 level_idx;
+	u8 duty_percent;
+	__le32 restore_temp;
+	u8 __rsv2[4];
 } __packed;
 
 enum mt7996_chan_mib_offs {
@@ -247,7 +342,24 @@ struct bss_rate_tlv {
 	u8 short_preamble;
 	u8 bc_fixed_rate;
 	u8 mc_fixed_rate;
-	u8 __rsv2[1];
+	u8 __rsv2[9];
+} __packed;
+
+enum {
+	BP_DISABLE,
+	BP_SW_MODE,
+	BP_HW_MODE,
+};
+
+struct mt7996_mcu_bcn_prot_tlv {
+	__le16 tag;
+	__le16 len;
+	u8 pn[6];
+	u8 enable;
+	u8 cipher_id;
+	u8 key[WLAN_MAX_KEY_LEN];
+	u8 key_id;
+	u8 __rsv[3];
 } __packed;
 
 struct bss_ra_tlv {
@@ -372,6 +484,15 @@ struct bss_mld_tlv {
 	u8 __rsv[3];
 } __packed;
 
+struct sta_rec_ht_uni {
+	__le16 tag;
+	__le16 len;
+	__le16 ht_cap;
+	__le16 ht_cap_ext;
+	u8 ampdu_param;
+	u8 _rsv[3];
+} __packed;
+
 struct sta_rec_ba_uni {
 	__le16 tag;
 	__le16 len;
@@ -421,6 +542,73 @@ struct sta_rec_sec_uni {
 	struct sec_key_uni key[2];
 } __packed;
 
+struct sta_phy_uni {
+	u8 type;
+	u8 flag;
+	u8 stbc;
+	u8 sgi;
+	u8 bw;
+	u8 ldpc;
+	u8 mcs;
+	u8 nss;
+	u8 he_ltf;
+	u8 rsv[3];
+};
+
+struct sta_rec_ra_uni {
+	__le16 tag;
+	__le16 len;
+
+	u8 valid;
+	u8 auto_rate;
+	u8 phy_mode;
+	u8 channel;
+	u8 bw;
+	u8 disable_cck;
+	u8 ht_mcs32;
+	u8 ht_gf;
+	u8 ht_mcs[4];
+	u8 mmps_mode;
+	u8 gband_256;
+	u8 af;
+	u8 auth_wapi_mode;
+	u8 rate_len;
+
+	u8 supp_mode;
+	u8 supp_cck_rate;
+	u8 supp_ofdm_rate;
+	__le32 supp_ht_mcs;
+	__le16 supp_vht_mcs[4];
+
+	u8 op_mode;
+	u8 op_vht_chan_width;
+	u8 op_vht_rx_nss;
+	u8 op_vht_rx_nss_type;
+
+	__le32 sta_cap;
+
+	struct sta_phy_uni phy;
+	u8 rx_rcpi[4];
+} __packed;
+
+struct sta_rec_ra_fixed_uni {
+	__le16 tag;
+	__le16 len;
+
+	__le32 field;
+	u8 op_mode;
+	u8 op_vht_chan_width;
+	u8 op_vht_rx_nss;
+	u8 op_vht_rx_nss_type;
+
+	struct sta_phy_uni phy;
+
+	u8 spe_idx;
+	u8 short_preamble;
+	u8 is_5g;
+	u8 mmps_mode;
+} __packed;
+
 struct sta_rec_hdrt {
 	__le16 tag;
 	__le16 len;
@@ -596,17 +784,16 @@ enum {
 #define MT7996_STA_UPDATE_MAX_SIZE	(sizeof(struct sta_req_hdr) +		\
 					 sizeof(struct sta_rec_basic) +		\
 					 sizeof(struct sta_rec_bf) +		\
-					 sizeof(struct sta_rec_ht) +		\
+					 sizeof(struct sta_rec_ht_uni) +	\
 					 sizeof(struct sta_rec_he_v2) +		\
 					 sizeof(struct sta_rec_ba_uni) +	\
 					 sizeof(struct sta_rec_vht) +		\
 					 sizeof(struct sta_rec_uapsd) + 	\
 					 sizeof(struct sta_rec_amsdu) +		\
 					 sizeof(struct sta_rec_bfee) +		\
-					 sizeof(struct sta_rec_phy) +		\
-					 sizeof(struct sta_rec_ra) +		\
+					 sizeof(struct sta_rec_ra_uni) +	\
 					 sizeof(struct sta_rec_sec) +		\
-					 sizeof(struct sta_rec_ra_fixed) +	\
+					 sizeof(struct sta_rec_ra_fixed_uni) +	\
 					 sizeof(struct sta_rec_he_6g_capa) +	\
 					 sizeof(struct sta_rec_eht) +		\
 					 sizeof(struct sta_rec_hdrt) +		\
@@ -622,6 +809,18 @@ enum {
 #define MT7996_MAX_BSS_OFFLOAD_SIZE	(MT7996_MAX_BEACON_SIZE +		\
 					 MT7996_BEACON_UPDATE_SIZE)
 
+static inline s8
+mt7996_get_power_bound(struct mt7996_phy *phy, s8 txpower)
+{
+	struct mt76_phy *mphy = phy->mt76;
+	int n_chains = hweight16(mphy->chainmask);
+
+	txpower = mt76_get_sar_power(mphy, mphy->chandef.chan, txpower * 2);
+	txpower -= mt76_tx_power_nss_delta(n_chains);
+
+	return txpower;
+}
+
 enum {
 	UNI_BAND_CONFIG_RADIO_ENABLE,
 	UNI_BAND_CONFIG_RTS_THRESHOLD = 0x08,
@@ -669,6 +868,8 @@ enum {
 	UNI_RRO_GET_BA_SESSION_TABLE,
 	UNI_RRO_SET_BYPASS_MODE,
 	UNI_RRO_SET_TXFREE_PATH,
+	UNI_RRO_DEL_BA_SESSION,
+	UNI_RRO_SET_FLUSH_TIMEOUT
 };
 
 enum{
@@ -683,6 +884,16 @@ enum{
 };
 
 enum {
+	UNI_CMD_THERMAL_PROTECT_ENABLE = 0x6,
+	UNI_CMD_THERMAL_PROTECT_DISABLE,
+	UNI_CMD_THERMAL_PROTECT_DUTY_CONFIG,
+};
+
+enum {
+	UNI_TXPOWER_POWER_LIMIT_TABLE_CTRL = 4,
+};
+
+enum {
 	UNI_CMD_ACCESS_REG_BASIC = 0x0,
 	UNI_CMD_ACCESS_RF_REG_BASIC,
 };
@@ -720,4 +931,24 @@ enum {
 #define MT7996_SEC_KEY_IDX		GENMASK(2, 1)
 #define MT7996_SEC_IV			BIT(3)
 
+struct fixed_rate_table_ctrl {
+	u8 _rsv[4];
+
+	__le16 tag;
+	__le16 len;
+
+	u8 table_idx;
+	u8 antenna_idx;
+	__le16 rate_idx;
+	u8 spe_idx_sel;
+	u8 spe_idx;
+	u8 gi;
+	u8 he_ltf;
+	bool ldpc;
+	bool txbf;
+	bool dynamic_bw;
+
+	u8 _rsv2;
+} __packed;
+
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
index 3a591a7b47ae..c50d89a445e9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
@@ -6,10 +6,16 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/rtnetlink.h>
 
 #include "mt7996.h"
 #include "mac.h"
+#include "mcu.h"
 #include "../trace.h"
+#include "../dma.h"
+
+static bool wed_enable;
+module_param(wed_enable, bool, 0644);
 
 static const struct __base mt7996_reg_base[] = {
 	[WF_AGG_BASE]		= { { 0x820e2000, 0x820f2000, 0x830e2000 } },
@@ -24,6 +30,58 @@ static const struct __base mt7996_reg_base[] = {
 	[WF_RATE_BASE]		= { { 0x820ee000, 0x820fe000, 0x830ee000 } },
 };
 
+static const u32 mt7996_offs[] = {
+	[MIB_RVSR0]		= 0x720,
+	[MIB_RVSR1]		= 0x724,
+	[MIB_BTSCR5]		= 0x788,
+	[MIB_BTSCR6]		= 0x798,
+	[MIB_RSCR1]		= 0x7ac,
+	[MIB_RSCR27]		= 0x954,
+	[MIB_RSCR28]		= 0x958,
+	[MIB_RSCR29]		= 0x95c,
+	[MIB_RSCR30]		= 0x960,
+	[MIB_RSCR31]		= 0x964,
+	[MIB_RSCR33]		= 0x96c,
+	[MIB_RSCR35]		= 0x974,
+	[MIB_RSCR36]		= 0x978,
+	[MIB_BSCR0]		= 0x9cc,
+	[MIB_BSCR1]		= 0x9d0,
+	[MIB_BSCR2]		= 0x9d4,
+	[MIB_BSCR3]		= 0x9d8,
+	[MIB_BSCR4]		= 0x9dc,
+	[MIB_BSCR5]		= 0x9e0,
+	[MIB_BSCR6]		= 0x9e4,
+	[MIB_BSCR7]		= 0x9e8,
+	[MIB_BSCR17]		= 0xa10,
+	[MIB_TRDR1]		= 0xa28,
+};
+
+static const u32 mt7992_offs[] = {
+	[MIB_RVSR0]		= 0x760,
+	[MIB_RVSR1]		= 0x764,
+	[MIB_BTSCR5]		= 0x7c8,
+	[MIB_BTSCR6]		= 0x7d8,
+	[MIB_RSCR1]		= 0x7f0,
+	[MIB_RSCR27]		= 0x998,
+	[MIB_RSCR28]		= 0x99c,
+	[MIB_RSCR29]		= 0x9a0,
+	[MIB_RSCR30]		= 0x9a4,
+	[MIB_RSCR31]		= 0x9a8,
+	[MIB_RSCR33]		= 0x9b0,
+	[MIB_RSCR35]		= 0x9b8,
+	[MIB_RSCR36]		= 0x9bc,
+	[MIB_BSCR0]		= 0xac8,
+	[MIB_BSCR1]		= 0xacc,
+	[MIB_BSCR2]		= 0xad0,
+	[MIB_BSCR3]		= 0xad4,
+	[MIB_BSCR4]		= 0xad8,
+	[MIB_BSCR5]		= 0xadc,
+	[MIB_BSCR6]		= 0xae0,
+	[MIB_BSCR7]		= 0xae4,
+	[MIB_BSCR17]		= 0xb0c,
+	[MIB_TRDR1]		= 0xb24,
+};
+
 static const struct __map mt7996_reg_map[] = {
 	{ 0x54000000, 0x02000, 0x1000 }, /* WFDMA_0 (PCIE0 MCU DMA0) */
 	{ 0x55000000, 0x03000, 0x1000 }, /* WFDMA_1 (PCIE0 MCU DMA1) */
@@ -191,6 +249,169 @@ static u32 mt7996_rmw(struct mt76_dev *mdev, u32 offset, u32 mask, u32 val)
 	return dev->bus_ops->rmw(mdev, __mt7996_reg_addr(dev, offset), mask, val);
 }
 
+#ifdef CONFIG_NET_MEDIATEK_SOC_WED
+static int mt7996_mmio_wed_reset(struct mtk_wed_device *wed)
+{
+	struct mt76_dev *mdev = container_of(wed, struct mt76_dev, mmio.wed);
+	struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76);
+	struct mt76_phy *mphy = &dev->mphy;
+	int ret;
+
+	ASSERT_RTNL();
+
+	if (test_and_set_bit(MT76_STATE_WED_RESET, &mphy->state))
+		return -EBUSY;
+
+	ret = mt7996_mcu_set_ser(dev, UNI_CMD_SER_TRIGGER, UNI_CMD_SER_SET_RECOVER_L1,
+				 mphy->band_idx);
+	if (ret)
+		goto out;
+
+	rtnl_unlock();
+	if (!wait_for_completion_timeout(&mdev->mmio.wed_reset, 20 * HZ)) {
+		dev_err(mdev->dev, "wed reset timeout\n");
+		ret = -ETIMEDOUT;
+	}
+	rtnl_lock();
+out:
+	clear_bit(MT76_STATE_WED_RESET, &mphy->state);
+
+	return ret;
+}
+#endif
+
+int mt7996_mmio_wed_init(struct mt7996_dev *dev, void *pdev_ptr,
+			 bool hif2, int *irq)
+{
+#ifdef CONFIG_NET_MEDIATEK_SOC_WED
+	struct mtk_wed_device *wed = &dev->mt76.mmio.wed;
+	struct pci_dev *pci_dev = pdev_ptr;
+	u32 hif1_ofs = 0;
+
+	if (!wed_enable)
+		return 0;
+
+	dev->has_rro = true;
+
+	hif1_ofs = MT_WFDMA0_PCIE1(0) - MT_WFDMA0(0);
+
+	if (hif2)
+		wed = &dev->mt76.mmio.wed_hif2;
+
+	wed->wlan.pci_dev = pci_dev;
+	wed->wlan.bus_type = MTK_WED_BUS_PCIE;
+
+	wed->wlan.base = devm_ioremap(dev->mt76.dev,
+				      pci_resource_start(pci_dev, 0),
+				      pci_resource_len(pci_dev, 0));
+	wed->wlan.phy_base = pci_resource_start(pci_dev, 0);
+
+	if (hif2) {
+		wed->wlan.wpdma_int = wed->wlan.phy_base +
+				      MT_INT_PCIE1_SOURCE_CSR_EXT;
+		wed->wlan.wpdma_mask = wed->wlan.phy_base +
+				       MT_INT_PCIE1_MASK_CSR;
+		wed->wlan.wpdma_tx = wed->wlan.phy_base + hif1_ofs +
+					     MT_TXQ_RING_BASE(0) +
+					     MT7996_TXQ_BAND2 * MT_RING_SIZE;
+		if (dev->has_rro) {
+			wed->wlan.wpdma_txfree = wed->wlan.phy_base + hif1_ofs +
+						 MT_RXQ_RING_BASE(0) +
+						 MT7996_RXQ_TXFREE2 * MT_RING_SIZE;
+			wed->wlan.txfree_tbit = ffs(MT_INT_RX_TXFREE_EXT) - 1;
+		} else {
+			wed->wlan.wpdma_txfree = wed->wlan.phy_base + hif1_ofs +
+						 MT_RXQ_RING_BASE(0) +
+						 MT7996_RXQ_MCU_WA_TRI * MT_RING_SIZE;
+			wed->wlan.txfree_tbit = ffs(MT_INT_RX_DONE_WA_TRI) - 1;
+		}
+
+		wed->wlan.wpdma_rx_glo = wed->wlan.phy_base + hif1_ofs + MT_WFDMA0_GLO_CFG;
+		wed->wlan.wpdma_rx = wed->wlan.phy_base + hif1_ofs +
+				     MT_RXQ_RING_BASE(MT7996_RXQ_BAND0) +
+				     MT7996_RXQ_BAND0 * MT_RING_SIZE;
+
+		wed->wlan.id = 0x7991;
+		wed->wlan.tx_tbit[0] = ffs(MT_INT_TX_DONE_BAND2) - 1;
+	} else {
+		wed->wlan.hw_rro = dev->has_rro; /* default on */
+		wed->wlan.wpdma_int = wed->wlan.phy_base + MT_INT_SOURCE_CSR;
+		wed->wlan.wpdma_mask = wed->wlan.phy_base + MT_INT_MASK_CSR;
+		wed->wlan.wpdma_tx = wed->wlan.phy_base + MT_TXQ_RING_BASE(0) +
+				     MT7996_TXQ_BAND0 * MT_RING_SIZE;
+
+		wed->wlan.wpdma_rx_glo = wed->wlan.phy_base + MT_WFDMA0_GLO_CFG;
+
+		wed->wlan.wpdma_rx = wed->wlan.phy_base +
+				     MT_RXQ_RING_BASE(MT7996_RXQ_BAND0) +
+				     MT7996_RXQ_BAND0 * MT_RING_SIZE;
+
+		wed->wlan.wpdma_rx_rro[0] = wed->wlan.phy_base +
+					    MT_RXQ_RING_BASE(MT7996_RXQ_RRO_BAND0) +
+					    MT7996_RXQ_RRO_BAND0 * MT_RING_SIZE;
+		wed->wlan.wpdma_rx_rro[1] = wed->wlan.phy_base + hif1_ofs +
+					    MT_RXQ_RING_BASE(MT7996_RXQ_RRO_BAND2) +
+					    MT7996_RXQ_RRO_BAND2 * MT_RING_SIZE;
+		wed->wlan.wpdma_rx_pg = wed->wlan.phy_base +
+					MT_RXQ_RING_BASE(MT7996_RXQ_MSDU_PG_BAND0) +
+					MT7996_RXQ_MSDU_PG_BAND0 * MT_RING_SIZE;
+
+		wed->wlan.rx_nbuf = 65536;
+		wed->wlan.rx_npkt = dev->hif2 ? 32768 : 24576;
+		wed->wlan.rx_size = SKB_WITH_OVERHEAD(MT_RX_BUF_SIZE);
+
+		wed->wlan.rx_tbit[0] = ffs(MT_INT_RX_DONE_BAND0) - 1;
+		wed->wlan.rx_tbit[1] = ffs(MT_INT_RX_DONE_BAND2) - 1;
+
+		wed->wlan.rro_rx_tbit[0] = ffs(MT_INT_RX_DONE_RRO_BAND0) - 1;
+		wed->wlan.rro_rx_tbit[1] = ffs(MT_INT_RX_DONE_RRO_BAND2) - 1;
+
+		wed->wlan.rx_pg_tbit[0] = ffs(MT_INT_RX_DONE_MSDU_PG_BAND0) - 1;
+		wed->wlan.rx_pg_tbit[1] = ffs(MT_INT_RX_DONE_MSDU_PG_BAND1) - 1;
+		wed->wlan.rx_pg_tbit[2] = ffs(MT_INT_RX_DONE_MSDU_PG_BAND2) - 1;
+
+		wed->wlan.tx_tbit[0] = ffs(MT_INT_TX_DONE_BAND0) - 1;
+		wed->wlan.tx_tbit[1] = ffs(MT_INT_TX_DONE_BAND1) - 1;
+		if (dev->has_rro) {
+			wed->wlan.wpdma_txfree = wed->wlan.phy_base + MT_RXQ_RING_BASE(0) +
+						 MT7996_RXQ_TXFREE0 * MT_RING_SIZE;
+			wed->wlan.txfree_tbit = ffs(MT_INT_RX_TXFREE_MAIN) - 1;
+		} else {
+			wed->wlan.txfree_tbit = ffs(MT_INT_RX_DONE_WA_MAIN) - 1;
+			wed->wlan.wpdma_txfree = wed->wlan.phy_base + MT_RXQ_RING_BASE(0) +
+						  MT7996_RXQ_MCU_WA_MAIN * MT_RING_SIZE;
+		}
+		dev->mt76.rx_token_size = MT7996_TOKEN_SIZE + wed->wlan.rx_npkt;
+	}
+
+	wed->wlan.nbuf = MT7996_HW_TOKEN_SIZE;
+	wed->wlan.token_start = MT7996_TOKEN_SIZE - wed->wlan.nbuf;
+
+	wed->wlan.amsdu_max_subframes = 8;
+	wed->wlan.amsdu_max_len = 1536;
+
+	wed->wlan.init_buf = mt7996_wed_init_buf;
+	wed->wlan.init_rx_buf = mt76_mmio_wed_init_rx_buf;
+	wed->wlan.release_rx_buf = mt76_mmio_wed_release_rx_buf;
+	wed->wlan.offload_enable = mt76_mmio_wed_offload_enable;
+	wed->wlan.offload_disable = mt76_mmio_wed_offload_disable;
+	if (!hif2) {
+		wed->wlan.reset = mt7996_mmio_wed_reset;
+		wed->wlan.reset_complete = mt76_mmio_wed_reset_complete;
+	}
+
+	if (mtk_wed_device_attach(wed))
+		return 0;
+
+	*irq = wed->irq;
+	dev->mt76.dma_dev = wed->dev;
+
+	return 1;
+#else
+	return 0;
+#endif
+}
+
 static int mt7996_mmio_init(struct mt76_dev *mdev,
 			    void __iomem *mem_base,
 			    u32 device_id)
@@ -204,6 +425,13 @@ static int mt7996_mmio_init(struct mt76_dev *mdev,
 	switch (device_id) {
 	case 0x7990:
 		dev->reg.base = mt7996_reg_base;
+		dev->reg.offs_rev = mt7996_offs;
+		dev->reg.map = mt7996_reg_map;
+		dev->reg.map_size = ARRAY_SIZE(mt7996_reg_map);
+		break;
+	case 0x7992:
+		dev->reg.base = mt7996_reg_base;
+		dev->reg.offs_rev = mt7992_offs;
 		dev->reg.map = mt7996_reg_map;
 		dev->reg.map_size = ARRAY_SIZE(mt7996_reg_map);
 		break;
@@ -241,8 +469,17 @@ void mt7996_dual_hif_set_irq_mask(struct mt7996_dev *dev, bool write_reg,
 	mdev->mmio.irqmask |= set;
 
 	if (write_reg) {
-		mt76_wr(dev, MT_INT_MASK_CSR, mdev->mmio.irqmask);
-		mt76_wr(dev, MT_INT1_MASK_CSR, mdev->mmio.irqmask);
+		if (mtk_wed_device_active(&mdev->mmio.wed)) {
+			mtk_wed_device_irq_set_mask(&mdev->mmio.wed,
+						    mdev->mmio.irqmask);
+			if (mtk_wed_device_active(&mdev->mmio.wed_hif2)) {
+				mtk_wed_device_irq_set_mask(&mdev->mmio.wed_hif2,
+							    mdev->mmio.irqmask);
+			}
+		} else {
+			mt76_wr(dev, MT_INT_MASK_CSR, mdev->mmio.irqmask);
+			mt76_wr(dev, MT_INT1_MASK_CSR, mdev->mmio.irqmask);
+		}
 	}
 
 	spin_unlock_irqrestore(&mdev->mmio.irq_lock, flags);
@@ -260,22 +497,36 @@ static void mt7996_rx_poll_complete(struct mt76_dev *mdev,
 static void mt7996_irq_tasklet(struct tasklet_struct *t)
 {
 	struct mt7996_dev *dev = from_tasklet(dev, t, mt76.irq_tasklet);
+	struct mtk_wed_device *wed = &dev->mt76.mmio.wed;
+	struct mtk_wed_device *wed_hif2 = &dev->mt76.mmio.wed_hif2;
 	u32 i, intr, mask, intr1;
 
-	mt76_wr(dev, MT_INT_MASK_CSR, 0);
-	if (dev->hif2)
-		mt76_wr(dev, MT_INT1_MASK_CSR, 0);
-
-	intr = mt76_rr(dev, MT_INT_SOURCE_CSR);
-	intr &= dev->mt76.mmio.irqmask;
-	mt76_wr(dev, MT_INT_SOURCE_CSR, intr);
-
-	if (dev->hif2) {
-		intr1 = mt76_rr(dev, MT_INT1_SOURCE_CSR);
-		intr1 &= dev->mt76.mmio.irqmask;
-		mt76_wr(dev, MT_INT1_SOURCE_CSR, intr1);
+	if (dev->hif2 && mtk_wed_device_active(wed_hif2)) {
+		mtk_wed_device_irq_set_mask(wed_hif2, 0);
+		intr1 = mtk_wed_device_irq_get(wed_hif2,
+					       dev->mt76.mmio.irqmask);
+		if (intr1 & MT_INT_RX_TXFREE_EXT)
+			napi_schedule(&dev->mt76.napi[MT_RXQ_TXFREE_BAND2]);
+	}
 
-		intr |= intr1;
+	if (mtk_wed_device_active(wed)) {
+		mtk_wed_device_irq_set_mask(wed, 0);
+		intr = mtk_wed_device_irq_get(wed, dev->mt76.mmio.irqmask);
+		intr |= (intr1 & ~MT_INT_RX_TXFREE_EXT);
+	} else {
+		mt76_wr(dev, MT_INT_MASK_CSR, 0);
+		if (dev->hif2)
+			mt76_wr(dev, MT_INT1_MASK_CSR, 0);
+
+		intr = mt76_rr(dev, MT_INT_SOURCE_CSR);
+		intr &= dev->mt76.mmio.irqmask;
+		mt76_wr(dev, MT_INT_SOURCE_CSR, intr);
+		if (dev->hif2) {
+			intr1 = mt76_rr(dev, MT_INT1_SOURCE_CSR);
+			intr1 &= dev->mt76.mmio.irqmask;
+			mt76_wr(dev, MT_INT1_SOURCE_CSR, intr1);
+			intr |= intr1;
+		}
 	}
 
 	trace_dev_irq(&dev->mt76, intr, dev->mt76.mmio.irqmask);
@@ -308,9 +559,17 @@ irqreturn_t mt7996_irq_handler(int irq, void *dev_instance)
 {
 	struct mt7996_dev *dev = dev_instance;
 
-	mt76_wr(dev, MT_INT_MASK_CSR, 0);
-	if (dev->hif2)
-		mt76_wr(dev, MT_INT1_MASK_CSR, 0);
+	if (mtk_wed_device_active(&dev->mt76.mmio.wed))
+		mtk_wed_device_irq_set_mask(&dev->mt76.mmio.wed, 0);
+	else
+		mt76_wr(dev, MT_INT_MASK_CSR, 0);
+
+	if (dev->hif2) {
+		if (mtk_wed_device_active(&dev->mt76.mmio.wed_hif2))
+			mtk_wed_device_irq_set_mask(&dev->mt76.mmio.wed_hif2, 0);
+		else
+			mt76_wr(dev, MT_INT1_MASK_CSR, 0);
+	}
 
 	if (!test_bit(MT76_STATE_INITIALIZED, &dev->mphy.state))
 		return IRQ_NONE;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index e53cf6a3704c..bc73bcb47bf0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -13,6 +13,7 @@
 
 #define MT7996_MAX_INTERFACES		19	/* per-band */
 #define MT7996_MAX_WMM_SETS		4
+#define MT7996_WTBL_BMC_SIZE		(is_mt7992(&dev->mt76) ? 32 : 64)
 #define MT7996_WTBL_RESERVED		(mt7996_wtbl_size(dev) - 1)
 #define MT7996_WTBL_STA			(MT7996_WTBL_RESERVED - \
 					 mt7996_max_interface_num(dev))
@@ -33,22 +34,54 @@
 #define MT7996_FIRMWARE_DSP		"mediatek/mt7996/mt7996_dsp.bin"
 #define MT7996_ROM_PATCH		"mediatek/mt7996/mt7996_rom_patch.bin"
 
+#define MT7992_FIRMWARE_WA		"mediatek/mt7996/mt7992_wa.bin"
+#define MT7992_FIRMWARE_WM		"mediatek/mt7996/mt7992_wm.bin"
+#define MT7992_FIRMWARE_DSP		"mediatek/mt7996/mt7992_dsp.bin"
+#define MT7992_ROM_PATCH		"mediatek/mt7996/mt7992_rom_patch.bin"
+
 #define MT7996_EEPROM_DEFAULT		"mediatek/mt7996/mt7996_eeprom.bin"
+#define MT7992_EEPROM_DEFAULT		"mediatek/mt7996/mt7992_eeprom.bin"
 #define MT7996_EEPROM_SIZE		7680
 #define MT7996_EEPROM_BLOCK_SIZE	16
 #define MT7996_TOKEN_SIZE		16384
+#define MT7996_HW_TOKEN_SIZE		8192
 
 #define MT7996_CFEND_RATE_DEFAULT	0x49	/* OFDM 24M */
 #define MT7996_CFEND_RATE_11B		0x03	/* 11B LP, 11M */
 
+#define MT7996_SKU_RATE_NUM		417
+
 #define MT7996_MAX_TWT_AGRT		16
 #define MT7996_MAX_STA_TWT_AGRT		8
 #define MT7996_MAX_QUEUE		(__MT_RXQ_MAX +	__MT_MCUQ_MAX + 3)
 
 /* NOTE: used to map mt76_rates. idx may change if firmware expands table */
-#define MT7996_BASIC_RATES_TBL		11
+#define MT7996_BASIC_RATES_TBL		31
 #define MT7996_BEACON_RATES_TBL		25
 
+#define MT7996_THERMAL_THROTTLE_MAX	100
+#define MT7996_CDEV_THROTTLE_MAX	99
+#define MT7996_CRIT_TEMP_IDX		0
+#define MT7996_MAX_TEMP_IDX		1
+#define MT7996_CRIT_TEMP		110
+#define MT7996_MAX_TEMP			120
+
+#define MT7996_RRO_MAX_SESSION		1024
+#define MT7996_RRO_WINDOW_MAX_LEN	1024
+#define MT7996_RRO_ADDR_ELEM_LEN	128
+#define MT7996_RRO_BA_BITMAP_LEN	2
+#define MT7996_RRO_BA_BITMAP_CR_SIZE	((MT7996_RRO_MAX_SESSION * 128) /	\
+					 MT7996_RRO_BA_BITMAP_LEN)
+#define MT7996_RRO_BA_BITMAP_SESSION_SIZE	(MT7996_RRO_MAX_SESSION /	\
+						 MT7996_RRO_ADDR_ELEM_LEN)
+#define MT7996_RRO_WINDOW_MAX_SIZE	(MT7996_RRO_WINDOW_MAX_LEN *		\
+					 MT7996_RRO_BA_BITMAP_SESSION_SIZE)
+
+#define MT7996_RX_BUF_SIZE		(1800 + \
+					 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+#define MT7996_RX_MSDU_PAGE_SIZE	(128 + \
+					 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+
 struct mt7996_vif;
 struct mt7996_sta;
 struct mt7996_dfs_pulse;
@@ -73,11 +106,21 @@ enum mt7996_rxq_id {
 	MT7996_RXQ_MCU_WM = 0,
 	MT7996_RXQ_MCU_WA,
 	MT7996_RXQ_MCU_WA_MAIN = 2,
-	MT7996_RXQ_MCU_WA_EXT = 2,/* unused */
+	MT7996_RXQ_MCU_WA_EXT = 3, /* for mt7992 */
 	MT7996_RXQ_MCU_WA_TRI = 3,
 	MT7996_RXQ_BAND0 = 4,
-	MT7996_RXQ_BAND1 = 4,/* unused */
+	MT7996_RXQ_BAND1 = 5, /* for mt7992 */
 	MT7996_RXQ_BAND2 = 5,
+	MT7996_RXQ_RRO_BAND0 = 8,
+	MT7996_RXQ_RRO_BAND1 = 8,/* unused */
+	MT7996_RXQ_RRO_BAND2 = 6,
+	MT7996_RXQ_MSDU_PG_BAND0 = 10,
+	MT7996_RXQ_MSDU_PG_BAND1 = 11,
+	MT7996_RXQ_MSDU_PG_BAND2 = 12,
+	MT7996_RXQ_TXFREE0 = 9,
+	MT7996_RXQ_TXFREE1 = 9,
+	MT7996_RXQ_TXFREE2 = 7,
+	MT7996_RXQ_RRO_IND = 0,
 };
 
 struct mt7996_twt_flow {
@@ -146,6 +189,20 @@ struct mt7996_hif {
 	int irq;
 };
 
+struct mt7996_wed_rro_addr {
+	u32 head_low;
+	u32 head_high : 4;
+	u32 count: 11;
+	u32 oor: 1;
+	u32 rsv : 8;
+	u32 signature : 8;
+};
+
+struct mt7996_wed_rro_session_id {
+	struct list_head list;
+	u16 id;
+};
+
 struct mt7996_phy {
 	struct mt76_phy *mt76;
 	struct mt7996_dev *dev;
@@ -154,6 +211,11 @@ struct mt7996_phy {
 
 	struct ieee80211_vif *monitor_vif;
 
+	struct thermal_cooling_device *cdev;
+	u8 cdev_state;
+	u8 throttle_state;
+	u32 throttle_temp[2]; /* 0: critical high, 1: maximum */
+
 	u32 rxfilter;
 	u64 omac_mask;
 
@@ -164,11 +226,15 @@ struct mt7996_phy {
 
 	u8 rdd_state;
 
+	u16 beacon_rate;
+
 	u32 rx_ampdu_ts;
 	u32 ampdu_ref;
 
 	struct mt76_mib_stats mib;
 	struct mt76_channel_state state_ts;
+
+	bool has_aux_rx;
 };
 
 struct mt7996_dev {
@@ -221,10 +287,28 @@ struct mt7996_dev {
 
 	u32 hw_pattern;
 
-	bool dbdc_support:1;
-	bool tbtc_support:1;
 	bool flash_mode:1;
 	bool has_eht:1;
+	bool has_rro:1;
+
+	struct {
+		struct {
+			void *ptr;
+			dma_addr_t phy_addr;
+		} ba_bitmap[MT7996_RRO_BA_BITMAP_LEN];
+		struct {
+			void *ptr;
+			dma_addr_t phy_addr;
+		} addr_elem[MT7996_RRO_ADDR_ELEM_LEN];
+		struct {
+			void *ptr;
+			dma_addr_t phy_addr;
+		} session;
+
+		struct work_struct work;
+		struct list_head poll_list;
+		spinlock_t lock;
+	} wed_rro;
 
 	bool ibf;
 	u8 fw_debug_wm;
@@ -314,6 +398,20 @@ mt7996_phy3(struct mt7996_dev *dev)
 	return __mt7996_phy(dev, MT_BAND2);
 }
 
+static inline bool
+mt7996_band_valid(struct mt7996_dev *dev, u8 band)
+{
+	if (is_mt7992(&dev->mt76))
+		return band <= MT_BAND1;
+
+	/* tri-band support */
+	if (band <= MT_BAND2 &&
+	    mt76_get_field(dev, MT_PAD_GPIO, MT_PAD_GPIO_ADIE_COMB) <= 1)
+		return true;
+
+	return band == MT_BAND0 || band == MT_BAND2;
+}
+
 extern const struct ieee80211_ops mt7996_ops;
 extern struct pci_driver mt7996_pci_driver;
 extern struct pci_driver mt7996_hif_driver;
@@ -334,9 +432,10 @@ int mt7996_dma_init(struct mt7996_dev *dev);
 void mt7996_dma_reset(struct mt7996_dev *dev, bool force);
 void mt7996_dma_prefetch(struct mt7996_dev *dev);
 void mt7996_dma_cleanup(struct mt7996_dev *dev);
-void mt7996_dma_start(struct mt7996_dev *dev, bool reset);
-void mt7996_init_txpower(struct mt7996_dev *dev,
-			 struct ieee80211_supported_band *sband);
+void mt7996_dma_start(struct mt7996_dev *dev, bool reset, bool wed_reset);
+int mt7996_init_tx_queues(struct mt7996_phy *phy, int idx,
+			  int n_desc, int ring_base, struct mtk_wed_device *wed);
+void mt7996_init_txpower(struct mt7996_phy *phy);
 int mt7996_txbf_init(struct mt7996_dev *dev);
 void mt7996_reset(struct mt7996_dev *dev);
 int mt7996_run(struct ieee80211_hw *hw);
@@ -373,6 +472,8 @@ int mt7996_mcu_set_chan_info(struct mt7996_phy *phy, u16 tag);
 int mt7996_mcu_set_tx(struct mt7996_dev *dev, struct ieee80211_vif *vif);
 int mt7996_mcu_set_fixed_rate_ctrl(struct mt7996_dev *dev,
 				   void *data, u16 version);
+int mt7996_mcu_set_fixed_field(struct mt7996_dev *dev, struct ieee80211_vif *vif,
+			       struct ieee80211_sta *sta, void *data, u32 field);
 int mt7996_mcu_set_eeprom(struct mt7996_dev *dev);
 int mt7996_mcu_get_eeprom(struct mt7996_dev *dev, u32 offset);
 int mt7996_mcu_get_eeprom_free_block(struct mt7996_dev *dev, u8 *block_num);
@@ -388,13 +489,19 @@ int mt7996_mcu_set_radio_en(struct mt7996_phy *phy, bool enable);
 int mt7996_mcu_set_rts_thresh(struct mt7996_phy *phy, u32 val);
 int mt7996_mcu_set_timing(struct mt7996_phy *phy, struct ieee80211_vif *vif);
 int mt7996_mcu_get_chan_mib_info(struct mt7996_phy *phy, bool chan_switch);
+int mt7996_mcu_get_temperature(struct mt7996_phy *phy);
+int mt7996_mcu_set_thermal_throttling(struct mt7996_phy *phy, u8 state);
+int mt7996_mcu_set_thermal_protect(struct mt7996_phy *phy, bool enable);
+int mt7996_mcu_set_txpower_sku(struct mt7996_phy *phy);
 int mt7996_mcu_rdd_cmd(struct mt7996_dev *dev, int cmd, u8 index,
 		       u8 rx_sel, u8 val);
 int mt7996_mcu_rdd_background_enable(struct mt7996_phy *phy,
 				     struct cfg80211_chan_def *chandef);
+int mt7996_mcu_set_fixed_rate_table(struct mt7996_phy *phy, u8 table_idx,
+				    u16 rate_idx, bool beacon);
 int mt7996_mcu_rf_regval(struct mt7996_dev *dev, u32 regidx, u32 *val, bool set);
 int mt7996_mcu_set_hdr_trans(struct mt7996_dev *dev, bool hdr_trans);
-int mt7996_mcu_set_rro(struct mt7996_dev *dev, u16 tag, u8 val);
+int mt7996_mcu_set_rro(struct mt7996_dev *dev, u16 tag, u16 val);
 int mt7996_mcu_wa_cmd(struct mt7996_dev *dev, int cmd, u32 a1, u32 a2, u32 a3);
 int mt7996_mcu_fw_log_2_host(struct mt7996_dev *dev, u8 type, u8 ctrl);
 int mt7996_mcu_fw_dbg_ctrl(struct mt7996_dev *dev, u32 module, u8 level);
@@ -402,15 +509,18 @@ int mt7996_mcu_trigger_assert(struct mt7996_dev *dev);
 void mt7996_mcu_rx_event(struct mt7996_dev *dev, struct sk_buff *skb);
 void mt7996_mcu_exit(struct mt7996_dev *dev);
 int mt7996_mcu_get_all_sta_info(struct mt7996_phy *phy, u16 tag);
+int mt7996_mcu_wed_rro_reset_sessions(struct mt7996_dev *dev, u16 id);
 
 static inline u8 mt7996_max_interface_num(struct mt7996_dev *dev)
 {
-	return MT7996_MAX_INTERFACES * (1 + dev->dbdc_support + dev->tbtc_support);
+	return min(MT7996_MAX_INTERFACES * (1 + mt7996_band_valid(dev, MT_BAND1) +
+					    mt7996_band_valid(dev, MT_BAND2)),
+		   MT7996_WTBL_BMC_SIZE);
 }
 
 static inline u16 mt7996_wtbl_size(struct mt7996_dev *dev)
 {
-	return (dev->wtbl_size_group << 8) + 64;
+	return (dev->wtbl_size_group << 8) + MT7996_WTBL_BMC_SIZE;
 }
 
 void mt7996_dual_hif_set_irq_mask(struct mt7996_dev *dev, bool write_reg,
@@ -437,6 +547,18 @@ static inline void mt7996_irq_disable(struct mt7996_dev *dev, u32 mask)
 void mt7996_memcpy_fromio(struct mt7996_dev *dev, void *buf, u32 offset,
 			  size_t len);
 
+static inline u16 mt7996_rx_chainmask(struct mt7996_phy *phy)
+{
+	int max_nss = hweight8(phy->mt76->hw->wiphy->available_antennas_tx);
+	int cur_nss = hweight8(phy->mt76->antenna_mask);
+	u16 tx_chainmask = phy->mt76->chainmask;
+
+	if (cur_nss != max_nss)
+		return tx_chainmask;
+
+	return tx_chainmask | (BIT(fls(tx_chainmask)) * phy->has_aux_rx);
+}
+
 void mt7996_mac_init(struct mt7996_dev *dev);
 u32 mt7996_mac_wtbl_lmac_addr(struct mt7996_dev *dev, u16 wcid, u8 dw);
 bool mt7996_mac_wtbl_update(struct mt7996_dev *dev, int idx, u32 mask);
@@ -445,8 +567,6 @@ void mt7996_mac_cca_stats_reset(struct mt7996_phy *phy);
 void mt7996_mac_enable_nf(struct mt7996_dev *dev, u8 band);
 void mt7996_mac_enable_rtscts(struct mt7996_dev *dev,
 			      struct ieee80211_vif *vif, bool enable);
-void mt7996_mac_set_fixed_rate_table(struct mt7996_dev *dev,
-				     u8 tbl_idx, u16 rate_idx);
 void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 			   struct sk_buff *skb, struct mt76_wcid *wcid,
 			   struct ieee80211_key_conf *key, int pid,
@@ -485,9 +605,10 @@ int mt7996_init_debugfs(struct mt7996_phy *phy);
 void mt7996_debugfs_rx_fw_monitor(struct mt7996_dev *dev, const void *data, int len);
 bool mt7996_debugfs_rx_log(struct mt7996_dev *dev, const void *data, int len);
 int mt7996_mcu_add_key(struct mt76_dev *dev, struct ieee80211_vif *vif,
-		       struct mt76_connac_sta_key_conf *sta_key_conf,
 		       struct ieee80211_key_conf *key, int mcu_cmd,
 		       struct mt76_wcid *wcid, enum set_key_cmd cmd);
+int mt7996_mcu_bcn_prot_enable(struct mt7996_dev *dev, struct ieee80211_vif *vif,
+			       struct ieee80211_key_conf *key);
 int mt7996_mcu_wtbl_update_hdr_trans(struct mt7996_dev *dev,
 				     struct ieee80211_vif *vif,
 				     struct ieee80211_sta *sta);
@@ -495,5 +616,16 @@ int mt7996_mcu_wtbl_update_hdr_trans(struct mt7996_dev *dev,
 void mt7996_sta_add_debugfs(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			    struct ieee80211_sta *sta, struct dentry *dir);
 #endif
+int mt7996_mmio_wed_init(struct mt7996_dev *dev, void *pdev_ptr,
+			 bool hif2, int *irq);
+u32 mt7996_wed_init_buf(void *ptr, dma_addr_t phys, int token_id);
+
+#ifdef CONFIG_MTK_DEBUG
+int mt7996_mtk_init_debugfs(struct mt7996_phy *phy, struct dentry *dir);
+#endif
+
+#ifdef CONFIG_NET_MEDIATEK_SOC_WED
+int mt7996_dma_rro_init(struct mt7996_dev *dev);
+#endif /* CONFIG_NET_MEDIATEK_SOC_WED */
 
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/pci.c b/drivers/net/wireless/mediatek/mt76/mt7996/pci.c
index c5301050ff8b..04056181368a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/pci.c
@@ -17,11 +17,13 @@ static u32 hif_idx;
 
 static const struct pci_device_id mt7996_pci_device_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x7990) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x7992) },
 	{ },
 };
 
 static const struct pci_device_id mt7996_hif_device_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x7991) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x799a) },
 	{ },
 };
 
@@ -60,7 +62,9 @@ static void mt7996_put_hif2(struct mt7996_hif *hif)
 static struct mt7996_hif *mt7996_pci_init_hif2(struct pci_dev *pdev)
 {
 	hif_idx++;
-	if (!pci_get_device(PCI_VENDOR_ID_MEDIATEK, 0x7991, NULL))
+
+	if (!pci_get_device(PCI_VENDOR_ID_MEDIATEK, 0x7991, NULL) &&
+	    !pci_get_device(PCI_VENDOR_ID_MEDIATEK, 0x799a, NULL))
 		return NULL;
 
 	writel(hif_idx | MT_PCIE_RECOG_ID_SEM,
@@ -92,10 +96,10 @@ static int mt7996_pci_probe(struct pci_dev *pdev,
 			    const struct pci_device_id *id)
 {
 	struct pci_dev *hif2_dev;
+	struct mt7996_hif *hif2;
 	struct mt7996_dev *dev;
+	int irq, hif2_irq, ret;
 	struct mt76_dev *mdev;
-	struct mt7996_hif *hif2;
-	int irq, ret;
 
 	ret = pcim_enable_device(pdev);
 	if (ret)
@@ -107,13 +111,17 @@ static int mt7996_pci_probe(struct pci_dev *pdev,
 
 	pci_set_master(pdev);
 
-	ret = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
+	ret = dma_set_mask(&pdev->dev, DMA_BIT_MASK(36));
+	if (ret)
+		return ret;
+
+	ret = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
 	if (ret)
 		return ret;
 
 	mt76_pci_disable_aspm(pdev);
 
-	if (id->device == 0x7991)
+	if (id->device == 0x7991 || id->device == 0x799a)
 		return mt7996_pci_hif2_probe(pdev);
 
 	dev = mt7996_mmio_probe(&pdev->dev, pcim_iomap_table(pdev)[0],
@@ -125,15 +133,22 @@ static int mt7996_pci_probe(struct pci_dev *pdev,
 	mt7996_wfsys_reset(dev);
 	hif2 = mt7996_pci_init_hif2(pdev);
 
-	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
+	ret = mt7996_mmio_wed_init(dev, pdev, false, &irq);
 	if (ret < 0)
-		goto free_device;
+		goto free_wed_or_irq_vector;
+
+	if (!ret) {
+		ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
+		if (ret < 0)
+			goto free_device;
+
+		irq = pdev->irq;
+	}
 
-	irq = pdev->irq;
 	ret = devm_request_irq(mdev->dev, irq, mt7996_irq_handler,
 			       IRQF_SHARED, KBUILD_MODNAME, dev);
 	if (ret)
-		goto free_irq_vector;
+		goto free_wed_or_irq_vector;
 
 	mt76_wr(dev, MT_INT_MASK_CSR, 0);
 	/* master switch of PCIe tnterrupt enable */
@@ -143,16 +158,25 @@ static int mt7996_pci_probe(struct pci_dev *pdev,
 		hif2_dev = container_of(hif2->dev, struct pci_dev, dev);
 		dev->hif2 = hif2;
 
-		ret = pci_alloc_irq_vectors(hif2_dev, 1, 1, PCI_IRQ_ALL_TYPES);
+		ret = mt7996_mmio_wed_init(dev, hif2_dev, true, &hif2_irq);
 		if (ret < 0)
-			goto free_hif2;
+			goto free_hif2_wed_irq_vector;
+
+		if (!ret) {
+			ret = pci_alloc_irq_vectors(hif2_dev, 1, 1,
+						    PCI_IRQ_ALL_TYPES);
+			if (ret < 0)
+				goto free_hif2;
 
-		dev->hif2->irq = hif2_dev->irq;
-		ret = devm_request_irq(mdev->dev, dev->hif2->irq,
-				       mt7996_irq_handler, IRQF_SHARED,
-				       KBUILD_MODNAME "-hif", dev);
+			dev->hif2->irq = hif2_dev->irq;
+			hif2_irq = dev->hif2->irq;
+		}
+
+		ret = devm_request_irq(mdev->dev, hif2_irq, mt7996_irq_handler,
+				       IRQF_SHARED, KBUILD_MODNAME "-hif",
+				       dev);
 		if (ret)
-			goto free_hif2_irq_vector;
+			goto free_hif2_wed_irq_vector;
 
 		mt76_wr(dev, MT_INT1_MASK_CSR, 0);
 		/* master switch of PCIe tnterrupt enable */
@@ -167,16 +191,23 @@ static int mt7996_pci_probe(struct pci_dev *pdev,
 
 free_hif2_irq:
 	if (dev->hif2)
-		devm_free_irq(mdev->dev, dev->hif2->irq, dev);
-free_hif2_irq_vector:
-	if (dev->hif2)
-		pci_free_irq_vectors(hif2_dev);
+		devm_free_irq(mdev->dev, hif2_irq, dev);
+free_hif2_wed_irq_vector:
+	if (dev->hif2) {
+		if (mtk_wed_device_active(&dev->mt76.mmio.wed_hif2))
+			mtk_wed_device_detach(&dev->mt76.mmio.wed_hif2);
+		else
+			pci_free_irq_vectors(hif2_dev);
+	}
 free_hif2:
 	if (dev->hif2)
 		put_device(dev->hif2->dev);
 	devm_free_irq(mdev->dev, irq, dev);
-free_irq_vector:
-	pci_free_irq_vectors(pdev);
+free_wed_or_irq_vector:
+	if (mtk_wed_device_active(&dev->mt76.mmio.wed))
+		mtk_wed_device_detach(&dev->mt76.mmio.wed);
+	else
+		pci_free_irq_vectors(pdev);
 free_device:
 	mt76_free_device(&dev->mt76);
 
@@ -221,3 +252,7 @@ MODULE_FIRMWARE(MT7996_FIRMWARE_WA);
 MODULE_FIRMWARE(MT7996_FIRMWARE_WM);
 MODULE_FIRMWARE(MT7996_FIRMWARE_DSP);
 MODULE_FIRMWARE(MT7996_ROM_PATCH);
+MODULE_FIRMWARE(MT7992_FIRMWARE_WA);
+MODULE_FIRMWARE(MT7992_FIRMWARE_WM);
+MODULE_FIRMWARE(MT7992_FIRMWARE_DSP);
+MODULE_FIRMWARE(MT7992_ROM_PATCH);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/regs.h b/drivers/net/wireless/mediatek/mt76/mt7996/regs.h
index 0086a7866657..47b429d8bfbe 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/regs.h
@@ -19,6 +19,7 @@ struct __base {
 /* used to differentiate between generations */
 struct mt7996_reg_desc {
 	const struct __base *base;
+	const u32 *offs_rev;
 	const struct __map *map;
 	u32 map_size;
 };
@@ -39,6 +40,73 @@ enum base_rev {
 
 #define __BASE(_id, _band)			(dev->reg.base[(_id)].band_base[(_band)])
 
+enum offs_rev {
+	MIB_RVSR0,
+	MIB_RVSR1,
+	MIB_BTSCR5,
+	MIB_BTSCR6,
+	MIB_RSCR1,
+	MIB_RSCR27,
+	MIB_RSCR28,
+	MIB_RSCR29,
+	MIB_RSCR30,
+	MIB_RSCR31,
+	MIB_RSCR33,
+	MIB_RSCR35,
+	MIB_RSCR36,
+	MIB_BSCR0,
+	MIB_BSCR1,
+	MIB_BSCR2,
+	MIB_BSCR3,
+	MIB_BSCR4,
+	MIB_BSCR5,
+	MIB_BSCR6,
+	MIB_BSCR7,
+	MIB_BSCR17,
+	MIB_TRDR1,
+	__MT_OFFS_MAX,
+};
+
+#define __OFFS(id)			(dev->reg.offs_rev[(id)])
+
+/* RRO TOP */
+#define MT_RRO_TOP_BASE				0xA000
+#define MT_RRO_TOP(ofs)				(MT_RRO_TOP_BASE + (ofs))
+
+#define MT_RRO_BA_BITMAP_BASE0			MT_RRO_TOP(0x8)
+#define MT_RRO_BA_BITMAP_BASE1			MT_RRO_TOP(0xC)
+#define WF_RRO_AXI_MST_CFG			MT_RRO_TOP(0xB8)
+#define WF_RRO_AXI_MST_CFG_DIDX_OK		BIT(12)
+#define MT_RRO_ADDR_ARRAY_BASE1			MT_RRO_TOP(0x34)
+#define MT_RRO_ADDR_ARRAY_ELEM_ADDR_SEG_MODE	BIT(31)
+
+#define MT_RRO_IND_CMD_SIGNATURE_BASE0		MT_RRO_TOP(0x38)
+#define MT_RRO_IND_CMD_SIGNATURE_BASE1		MT_RRO_TOP(0x3C)
+#define MT_RRO_IND_CMD_0_CTRL0			MT_RRO_TOP(0x40)
+#define MT_RRO_IND_CMD_SIGNATURE_BASE1_EN	BIT(31)
+
+#define MT_RRO_PARTICULAR_CFG0			MT_RRO_TOP(0x5C)
+#define MT_RRO_PARTICULAR_CFG1			MT_RRO_TOP(0x60)
+#define MT_RRO_PARTICULAR_CONFG_EN		BIT(31)
+#define MT_RRO_PARTICULAR_SID			GENMASK(30, 16)
+
+#define MT_RRO_BA_BITMAP_BASE_EXT0		MT_RRO_TOP(0x70)
+#define MT_RRO_BA_BITMAP_BASE_EXT1		MT_RRO_TOP(0x74)
+#define MT_RRO_HOST_INT_ENA			MT_RRO_TOP(0x204)
+#define MT_RRO_HOST_INT_ENA_HOST_RRO_DONE_ENA   BIT(0)
+
+#define MT_RRO_ADDR_ELEM_SEG_ADDR0		MT_RRO_TOP(0x400)
+
+#define MT_RRO_ACK_SN_CTRL			MT_RRO_TOP(0x50)
+#define MT_RRO_ACK_SN_CTRL_SN_MASK		GENMASK(27, 16)
+#define MT_RRO_ACK_SN_CTRL_SESSION_MASK		GENMASK(11, 0)
+
+#define MT_RRO_DBG_RD_CTRL			MT_RRO_TOP(0xe0)
+#define MT_RRO_DBG_RD_ADDR			GENMASK(15, 0)
+#define MT_RRO_DBG_RD_EXEC			BIT(31)
+
+#define MT_RRO_DBG_RDAT_DW(_n)			MT_RRO_TOP(0xf0 + (_n) * 0x4)
+
 #define MT_MCU_INT_EVENT			0x2108
 #define MT_MCU_INT_EVENT_DMA_STOPPED		BIT(0)
 #define MT_MCU_INT_EVENT_DMA_INIT		BIT(1)
@@ -140,32 +208,32 @@ enum base_rev {
 #define MT_WF_MIB_BASE(_band)			__BASE(WF_MIB_BASE, (_band))
 #define MT_WF_MIB(_band, ofs)			(MT_WF_MIB_BASE(_band) + (ofs))
 
-#define MT_MIB_BSCR0(_band)			MT_WF_MIB(_band, 0x9cc)
-#define MT_MIB_BSCR1(_band)			MT_WF_MIB(_band, 0x9d0)
-#define MT_MIB_BSCR2(_band)			MT_WF_MIB(_band, 0x9d4)
-#define MT_MIB_BSCR3(_band)			MT_WF_MIB(_band, 0x9d8)
-#define MT_MIB_BSCR4(_band)			MT_WF_MIB(_band, 0x9dc)
-#define MT_MIB_BSCR5(_band)			MT_WF_MIB(_band, 0x9e0)
-#define MT_MIB_BSCR6(_band)			MT_WF_MIB(_band, 0x9e4)
-#define MT_MIB_BSCR7(_band)			MT_WF_MIB(_band, 0x9e8)
-#define MT_MIB_BSCR17(_band)			MT_WF_MIB(_band, 0xa10)
+#define MT_MIB_BSCR0(_band)			MT_WF_MIB(_band, __OFFS(MIB_BSCR0))
+#define MT_MIB_BSCR1(_band)			MT_WF_MIB(_band, __OFFS(MIB_BSCR1))
+#define MT_MIB_BSCR2(_band)			MT_WF_MIB(_band, __OFFS(MIB_BSCR2))
+#define MT_MIB_BSCR3(_band)			MT_WF_MIB(_band, __OFFS(MIB_BSCR3))
+#define MT_MIB_BSCR4(_band)			MT_WF_MIB(_band, __OFFS(MIB_BSCR4))
+#define MT_MIB_BSCR5(_band)			MT_WF_MIB(_band, __OFFS(MIB_BSCR5))
+#define MT_MIB_BSCR6(_band)			MT_WF_MIB(_band, __OFFS(MIB_BSCR6))
+#define MT_MIB_BSCR7(_band)			MT_WF_MIB(_band, __OFFS(MIB_BSCR7))
+#define MT_MIB_BSCR17(_band)			MT_WF_MIB(_band, __OFFS(MIB_BSCR17))
 
 #define MT_MIB_TSCR5(_band)			MT_WF_MIB(_band, 0x6c4)
 #define MT_MIB_TSCR6(_band)			MT_WF_MIB(_band, 0x6c8)
 #define MT_MIB_TSCR7(_band)			MT_WF_MIB(_band, 0x6d0)
 
-#define MT_MIB_RSCR1(_band)			MT_WF_MIB(_band, 0x7ac)
+#define MT_MIB_RSCR1(_band)			MT_WF_MIB(_band, __OFFS(MIB_RSCR1))
 /* rx mpdu counter, full 32 bits */
-#define MT_MIB_RSCR31(_band)			MT_WF_MIB(_band, 0x964)
-#define MT_MIB_RSCR33(_band)			MT_WF_MIB(_band, 0x96c)
+#define MT_MIB_RSCR31(_band)			MT_WF_MIB(_band, __OFFS(MIB_RSCR31))
+#define MT_MIB_RSCR33(_band)			MT_WF_MIB(_band, __OFFS(MIB_RSCR33))
 
 #define MT_MIB_SDR6(_band)			MT_WF_MIB(_band, 0x020)
 #define MT_MIB_SDR6_CHANNEL_IDL_CNT_MASK	GENMASK(15, 0)
 
-#define MT_MIB_RVSR0(_band)			MT_WF_MIB(_band, 0x720)
+#define MT_MIB_RVSR0(_band)			MT_WF_MIB(_band, __OFFS(MIB_RVSR0))
 
-#define MT_MIB_RSCR35(_band)			MT_WF_MIB(_band, 0x974)
-#define MT_MIB_RSCR36(_band)			MT_WF_MIB(_band, 0x978)
+#define MT_MIB_RSCR35(_band)			MT_WF_MIB(_band, __OFFS(MIB_RSCR35))
+#define MT_MIB_RSCR36(_band)			MT_WF_MIB(_band, __OFFS(MIB_RSCR36))
 
 /* tx ampdu cnt, full 32 bits */
 #define MT_MIB_TSCR0(_band)			MT_WF_MIB(_band, 0x6b0)
@@ -178,16 +246,16 @@ enum base_rev {
 #define MT_MIB_TSCR4(_band)			MT_WF_MIB(_band, 0x6c0)
 
 /* rx ampdu count, 32-bit */
-#define MT_MIB_RSCR27(_band)			MT_WF_MIB(_band, 0x954)
+#define MT_MIB_RSCR27(_band)			MT_WF_MIB(_band, __OFFS(MIB_RSCR27))
 
 /* rx ampdu bytes count, 32-bit */
-#define MT_MIB_RSCR28(_band)			MT_WF_MIB(_band, 0x958)
+#define MT_MIB_RSCR28(_band)			MT_WF_MIB(_band, __OFFS(MIB_RSCR28))
 
 /* rx ampdu valid subframe count */
-#define MT_MIB_RSCR29(_band)			MT_WF_MIB(_band, 0x95c)
+#define MT_MIB_RSCR29(_band)			MT_WF_MIB(_band, __OFFS(MIB_RSCR29))
 
 /* rx ampdu valid subframe bytes count, 32bits */
-#define MT_MIB_RSCR30(_band)			MT_WF_MIB(_band, 0x960)
+#define MT_MIB_RSCR30(_band)			MT_WF_MIB(_band, __OFFS(MIB_RSCR30))
 
 /* remaining windows protected stats */
 #define MT_MIB_SDR27(_band)			MT_WF_MIB(_band, 0x080)
@@ -196,18 +264,18 @@ enum base_rev {
 #define MT_MIB_SDR28(_band)			MT_WF_MIB(_band, 0x084)
 #define MT_MIB_SDR28_TX_RWP_NEED_CNT		GENMASK(15, 0)
 
-#define MT_MIB_RVSR1(_band)			MT_WF_MIB(_band, 0x724)
+#define MT_MIB_RVSR1(_band)			MT_WF_MIB(_band, __OFFS(MIB_RVSR1))
 
 /* rx blockack count, 32 bits */
 #define MT_MIB_TSCR1(_band)			MT_WF_MIB(_band, 0x6b4)
 
 #define MT_MIB_BTSCR0(_band)			MT_WF_MIB(_band, 0x5e0)
-#define MT_MIB_BTSCR5(_band)			MT_WF_MIB(_band, 0x788)
-#define MT_MIB_BTSCR6(_band)			MT_WF_MIB(_band, 0x798)
+#define MT_MIB_BTSCR5(_band)			MT_WF_MIB(_band, __OFFS(MIB_BTSCR5))
+#define MT_MIB_BTSCR6(_band)			MT_WF_MIB(_band, __OFFS(MIB_BTSCR6))
 
 #define MT_MIB_BFTFCR(_band)			MT_WF_MIB(_band, 0x5d0)
 
-#define MT_TX_AGG_CNT(_band, n)			MT_WF_MIB(_band, 0xa28 + ((n) << 2))
+#define MT_TX_AGG_CNT(_band, n)			MT_WF_MIB(_band, __OFFS(MIB_TRDR1) + ((n) << 2))
 #define MT_MIB_ARNG(_band, n)			MT_WF_MIB(_band, 0x0b0 + ((n) << 2))
 #define MT_MIB_ARNCR_RANGE(val, n)		(((val) >> ((n) << 4)) & GENMASK(9, 0))
 
@@ -330,15 +398,22 @@ enum base_rev {
 
 #define MT_WFDMA0_RX_INT_PCIE_SEL		MT_WFDMA0(0x154)
 #define MT_WFDMA0_RX_INT_SEL_RING3		BIT(3)
+#define MT_WFDMA0_RX_INT_SEL_RING6		BIT(6)
 
 #define MT_WFDMA0_MCU_HOST_INT_ENA		MT_WFDMA0(0x1f4)
 
 #define MT_WFDMA0_GLO_CFG			MT_WFDMA0(0x208)
 #define MT_WFDMA0_GLO_CFG_TX_DMA_EN		BIT(0)
 #define MT_WFDMA0_GLO_CFG_RX_DMA_EN		BIT(2)
-#define MT_WFDMA0_GLO_CFG_OMIT_TX_INFO		BIT(28)
-#define MT_WFDMA0_GLO_CFG_OMIT_RX_INFO		BIT(27)
 #define MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2	BIT(21)
+#define MT_WFDMA0_GLO_CFG_EXT_EN		BIT(26)
+#define MT_WFDMA0_GLO_CFG_OMIT_RX_INFO		BIT(27)
+#define MT_WFDMA0_GLO_CFG_OMIT_TX_INFO		BIT(28)
+
+#define MT_WFDMA0_PAUSE_RX_Q_45_TH		MT_WFDMA0(0x268)
+#define MT_WFDMA0_PAUSE_RX_Q_67_TH		MT_WFDMA0(0x26c)
+#define MT_WFDMA0_PAUSE_RX_Q_89_TH		MT_WFDMA0(0x270)
+#define MT_WFDMA0_PAUSE_RX_Q_RRO_TH		MT_WFDMA0(0x27c)
 
 #define WF_WFDMA0_GLO_CFG_EXT0			MT_WFDMA0(0x2b0)
 #define WF_WFDMA0_GLO_CFG_EXT0_RX_WB_RXD	BIT(18)
@@ -362,10 +437,14 @@ enum base_rev {
 
 #define MT_WFDMA_HOST_CONFIG			MT_WFDMA_EXT_CSR(0x30)
 #define MT_WFDMA_HOST_CONFIG_PDMA_BAND		BIT(0)
+#define MT_WFDMA_HOST_CONFIG_BAND2_PCIE1	BIT(22)
 
 #define MT_WFDMA_EXT_CSR_HIF_MISC		MT_WFDMA_EXT_CSR(0x44)
 #define MT_WFDMA_EXT_CSR_HIF_MISC_BUSY		BIT(0)
 
+#define MT_WFDMA_AXI_R2A_CTRL			MT_WFDMA_EXT_CSR(0x500)
+#define MT_WFDMA_AXI_R2A_CTRL_OUTSTAND_MASK	GENMASK(4, 0)
+
 #define MT_PCIE_RECOG_ID			0xd7090
 #define MT_PCIE_RECOG_ID_MASK			GENMASK(30, 0)
 #define MT_PCIE_RECOG_ID_SEM			BIT(31)
@@ -374,6 +453,9 @@ enum base_rev {
 #define MT_WFDMA0_PCIE1_BASE			0xd8000
 #define MT_WFDMA0_PCIE1(ofs)			(MT_WFDMA0_PCIE1_BASE + (ofs))
 
+#define MT_INT_PCIE1_SOURCE_CSR_EXT		MT_WFDMA0_PCIE1(0x118)
+#define MT_INT_PCIE1_MASK_CSR			MT_WFDMA0_PCIE1(0x11c)
+
 #define MT_WFDMA0_PCIE1_BUSY_ENA		MT_WFDMA0_PCIE1(0x13c)
 #define MT_WFDMA0_PCIE1_BUSY_ENA_TX_FIFO0	BIT(0)
 #define MT_WFDMA0_PCIE1_BUSY_ENA_TX_FIFO1	BIT(1)
@@ -394,6 +476,7 @@ enum base_rev {
 #define MT_MCUQ_RING_BASE(q)			(MT_Q_BASE(q) + 0x300)
 #define MT_TXQ_RING_BASE(q)			(MT_Q_BASE(__TXQ(q)) + 0x300)
 #define MT_RXQ_RING_BASE(q)			(MT_Q_BASE(__RXQ(q)) + 0x500)
+#define MT_RXQ_RRO_IND_RING_BASE		MT_RRO_TOP(0x40)
 
 #define MT_MCUQ_EXT_CTRL(q)			(MT_Q_BASE(q) +	0x600 +	\
 						 MT_MCUQ_ID(q) * 0x4)
@@ -409,17 +492,27 @@ enum base_rev {
 #define MT_INT1_MASK_CSR			MT_WFDMA0_PCIE1(0x204)
 
 #define MT_INT_RX_DONE_BAND0			BIT(12)
-#define MT_INT_RX_DONE_BAND1			BIT(12)
+#define MT_INT_RX_DONE_BAND1			BIT(13) /* for mt7992 */
 #define MT_INT_RX_DONE_BAND2			BIT(13)
 #define MT_INT_RX_DONE_WM			BIT(0)
 #define MT_INT_RX_DONE_WA			BIT(1)
 #define MT_INT_RX_DONE_WA_MAIN			BIT(2)
-#define MT_INT_RX_DONE_WA_EXT			BIT(2)
+#define MT_INT_RX_DONE_WA_EXT			BIT(3) /* for mt7992 */
 #define MT_INT_RX_DONE_WA_TRI			BIT(3)
 #define MT_INT_RX_TXFREE_MAIN			BIT(17)
 #define MT_INT_RX_TXFREE_TRI			BIT(15)
+#define MT_INT_RX_DONE_BAND2_EXT		BIT(23)
+#define MT_INT_RX_TXFREE_EXT			BIT(26)
 #define MT_INT_MCU_CMD				BIT(29)
 
+#define MT_INT_RX_DONE_RRO_BAND0		BIT(16)
+#define MT_INT_RX_DONE_RRO_BAND1		BIT(16)
+#define MT_INT_RX_DONE_RRO_BAND2		BIT(14)
+#define MT_INT_RX_DONE_RRO_IND			BIT(11)
+#define MT_INT_RX_DONE_MSDU_PG_BAND0		BIT(18)
+#define MT_INT_RX_DONE_MSDU_PG_BAND1		BIT(19)
+#define MT_INT_RX_DONE_MSDU_PG_BAND2		BIT(23)
+
 #define MT_INT_RX(q)				(dev->q_int_mask[__RXQ(q)])
 #define MT_INT_TX_MCU(q)			(dev->q_int_mask[(q)])
 
@@ -427,20 +520,31 @@ enum base_rev {
 						 MT_INT_RX(MT_RXQ_MCU_WA))
 
 #define MT_INT_BAND0_RX_DONE			(MT_INT_RX(MT_RXQ_MAIN) |	\
-						 MT_INT_RX(MT_RXQ_MAIN_WA))
+						 MT_INT_RX(MT_RXQ_MAIN_WA) |	\
+						 MT_INT_RX(MT_RXQ_TXFREE_BAND0))
 
 #define MT_INT_BAND1_RX_DONE			(MT_INT_RX(MT_RXQ_BAND1) |	\
 						 MT_INT_RX(MT_RXQ_BAND1_WA) |	\
-						 MT_INT_RX(MT_RXQ_MAIN_WA))
+						 MT_INT_RX(MT_RXQ_MAIN_WA) |	\
+						 MT_INT_RX(MT_RXQ_TXFREE_BAND0))
 
 #define MT_INT_BAND2_RX_DONE			(MT_INT_RX(MT_RXQ_BAND2) |	\
 						 MT_INT_RX(MT_RXQ_BAND2_WA) |	\
-						 MT_INT_RX(MT_RXQ_MAIN_WA))
+						 MT_INT_RX(MT_RXQ_MAIN_WA) |	\
+						 MT_INT_RX(MT_RXQ_TXFREE_BAND0))
+
+#define MT_INT_RRO_RX_DONE			(MT_INT_RX(MT_RXQ_RRO_BAND0) |		\
+						 MT_INT_RX(MT_RXQ_RRO_BAND1) |		\
+						 MT_INT_RX(MT_RXQ_RRO_BAND2) |		\
+						 MT_INT_RX(MT_RXQ_MSDU_PAGE_BAND0) |	\
+						 MT_INT_RX(MT_RXQ_MSDU_PAGE_BAND1) |	\
+						 MT_INT_RX(MT_RXQ_MSDU_PAGE_BAND2))
 
 #define MT_INT_RX_DONE_ALL			(MT_INT_RX_DONE_MCU |		\
 						 MT_INT_BAND0_RX_DONE |		\
 						 MT_INT_BAND1_RX_DONE |		\
-						 MT_INT_BAND2_RX_DONE)
+						 MT_INT_BAND2_RX_DONE |		\
+						 MT_INT_RRO_RX_DONE)
 
 #define MT_INT_TX_DONE_FWDL			BIT(26)
 #define MT_INT_TX_DONE_MCU_WM			BIT(27)
@@ -449,6 +553,10 @@ enum base_rev {
 #define MT_INT_TX_DONE_BAND1			BIT(31)
 #define MT_INT_TX_DONE_BAND2			BIT(15)
 
+#define MT_INT_TX_RX_DONE_EXT			(MT_INT_TX_DONE_BAND2 |		\
+						 MT_INT_RX_DONE_BAND2_EXT |	\
+						 MT_INT_RX_TXFREE_EXT)
+
 #define MT_INT_TX_DONE_MCU			(MT_INT_TX_MCU(MT_MCUQ_WA) |	\
 						 MT_INT_TX_MCU(MT_MCUQ_WM) |	\
 						 MT_INT_TX_MCU(MT_MCUQ_FWDL))
@@ -552,7 +660,12 @@ enum base_rev {
 #define MT_TOP_MISC				MT_TOP(0xf0)
 #define MT_TOP_MISC_FW_STATE			GENMASK(2, 0)
 
+#define MT_PAD_GPIO				0x700056f0
+#define MT_PAD_GPIO_ADIE_COMB			GENMASK(16, 15)
+
 #define MT_HW_REV				0x70010204
+#define MT_HW_REV1				0x8a00
+
 #define MT_WF_SUBSYS_RST			0x70028600
 
 /* PCIE MAC */
@@ -601,4 +714,11 @@ enum base_rev {
 #define MT_MCU_WM_EXCP_LR_CTRL			MT_MCU_WM_EXCP(0x200)
 #define MT_MCU_WM_EXCP_LR_LOG			MT_MCU_WM_EXCP(0x204)
 
+/* CONN AFE CTL CON */
+#define MT_AFE_CTL_BASE				0x18043000
+#define MT_AFE_CTL_BAND(_band, ofs)		(MT_AFE_CTL_BASE + \
+						 ((_band) * 0x1000) + (ofs))
+#define MT_AFE_CTL_BAND_PLL_03(_band)		MT_AFE_CTL_BAND(_band, 0x2c)
+#define MT_AFE_CTL_BAND_PLL_03_MSB_EN		BIT(1)
+
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/sdio.c b/drivers/net/wireless/mediatek/mt76/sdio.c
index 419723118ded..c52d550f0c32 100644
--- a/drivers/net/wireless/mediatek/mt76/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/sdio.c
@@ -481,21 +481,21 @@ static void mt76s_status_worker(struct mt76_worker *w)
 		if (dev->drv->tx_status_data && ndata_frames > 0 &&
 		    !test_and_set_bit(MT76_READING_STATS, &dev->phy.state) &&
 		    !test_bit(MT76_STATE_SUSPEND, &dev->phy.state))
-			ieee80211_queue_work(dev->hw, &dev->sdio.stat_work);
+			mt76_worker_schedule(&sdio->stat_worker);
 	} while (nframes > 0);
 
 	if (resched)
 		mt76_worker_schedule(&dev->tx_worker);
 }
 
-static void mt76s_tx_status_data(struct work_struct *work)
+static void mt76s_tx_status_data(struct mt76_worker *worker)
 {
 	struct mt76_sdio *sdio;
 	struct mt76_dev *dev;
 	u8 update = 1;
 	u16 count = 0;
 
-	sdio = container_of(work, struct mt76_sdio, stat_work);
+	sdio = container_of(worker, struct mt76_sdio, stat_worker);
 	dev = container_of(sdio, struct mt76_dev, sdio);
 
 	while (true) {
@@ -508,7 +508,7 @@ static void mt76s_tx_status_data(struct work_struct *work)
 	}
 
 	if (count && test_bit(MT76_STATE_RUNNING, &dev->phy.state))
-		ieee80211_queue_work(dev->hw, &sdio->stat_work);
+		mt76_worker_schedule(&sdio->status_worker);
 	else
 		clear_bit(MT76_READING_STATS, &dev->phy.state);
 }
@@ -600,8 +600,8 @@ void mt76s_deinit(struct mt76_dev *dev)
 	mt76_worker_teardown(&sdio->txrx_worker);
 	mt76_worker_teardown(&sdio->status_worker);
 	mt76_worker_teardown(&sdio->net_worker);
+	mt76_worker_teardown(&sdio->stat_worker);
 
-	cancel_work_sync(&sdio->stat_work);
 	clear_bit(MT76_READING_STATS, &dev->phy.state);
 
 	mt76_tx_status_check(dev, true);
@@ -644,10 +644,14 @@ int mt76s_init(struct mt76_dev *dev, struct sdio_func *func,
 	if (err)
 		return err;
 
+	err = mt76_worker_setup(dev->hw, &sdio->stat_worker, mt76s_tx_status_data,
+				"sdio-sta");
+	if (err)
+		return err;
+
 	sched_set_fifo_low(sdio->status_worker.task);
 	sched_set_fifo_low(sdio->net_worker.task);
-
-	INIT_WORK(&sdio->stat_work, mt76s_tx_status_data);
+	sched_set_fifo_low(sdio->stat_worker.task);
 
 	dev->queue_ops = &sdio_queue_ops;
 	dev->bus = bus_ops;
diff --git a/drivers/net/wireless/microchip/wilc1000/cfg80211.c b/drivers/net/wireless/microchip/wilc1000/cfg80211.c
index da52f91693b5..ad2509d8c99a 100644
--- a/drivers/net/wireless/microchip/wilc1000/cfg80211.c
+++ b/drivers/net/wireless/microchip/wilc1000/cfg80211.c
@@ -105,10 +105,9 @@ struct wilc_ch_list_elem {
 } __packed;
 
 static void cfg_scan_result(enum scan_event scan_event,
-			    struct wilc_rcvd_net_info *info, void *user_void)
+			    struct wilc_rcvd_net_info *info,
+			    struct wilc_priv *priv)
 {
-	struct wilc_priv *priv = user_void;
-
 	if (!priv->cfg_scanning)
 		return;
 
@@ -162,9 +161,8 @@ static void cfg_scan_result(enum scan_event scan_event,
 }
 
 static void cfg_connect_result(enum conn_event conn_disconn_evt, u8 mac_status,
-			       void *priv_data)
+			       struct wilc_priv *priv)
 {
-	struct wilc_priv *priv = priv_data;
 	struct net_device *dev = priv->dev;
 	struct wilc_vif *vif = netdev_priv(dev);
 	struct wilc *wl = vif->wilc;
@@ -286,9 +284,8 @@ static int scan(struct wiphy *wiphy, struct cfg80211_scan_request *request)
 	else
 		scan_type = WILC_FW_PASSIVE_SCAN;
 
-	ret = wilc_scan(vif, WILC_FW_USER_SCAN, scan_type, scan_ch_list,
-			request->n_channels, cfg_scan_result, (void *)priv,
-			request);
+	ret = wilc_scan(vif, WILC_FW_USER_SCAN, scan_type,
+			scan_ch_list, cfg_scan_result, request);
 
 	if (ret) {
 		priv->scan_req = NULL;
@@ -412,9 +409,8 @@ static int connect(struct wiphy *wiphy, struct net_device *dev,
 
 	wfi_drv->conn_info.security = security;
 	wfi_drv->conn_info.auth_type = auth_type;
-	wfi_drv->conn_info.ch = ch;
 	wfi_drv->conn_info.conn_result = cfg_connect_result;
-	wfi_drv->conn_info.arg = priv;
+	wfi_drv->conn_info.priv = priv;
 	wfi_drv->conn_info.param = join_params;
 
 	if (sme->mfp == NL80211_MFP_OPTIONAL)
@@ -1094,9 +1090,8 @@ static void wilc_wfi_mgmt_tx_complete(void *priv, int status)
 	kfree(pv_data);
 }
 
-static void wilc_wfi_remain_on_channel_expired(void *data, u64 cookie)
+static void wilc_wfi_remain_on_channel_expired(struct wilc_vif *vif, u64 cookie)
 {
-	struct wilc_vif *vif = data;
 	struct wilc_priv *priv = &vif->priv;
 	struct wilc_wfi_p2p_listen_params *params = &priv->remain_on_ch_params;
 
@@ -1128,9 +1123,8 @@ static int remain_on_channel(struct wiphy *wiphy,
 	if (id == 0)
 		id = ++priv->inc_roc_cookie;
 
-	ret = wilc_remain_on_channel(vif, id, duration, chan->hw_value,
-				     wilc_wfi_remain_on_channel_expired,
-				     (void *)vif);
+	ret = wilc_remain_on_channel(vif, id, chan->hw_value,
+				     wilc_wfi_remain_on_channel_expired);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/wireless/microchip/wilc1000/hif.c b/drivers/net/wireless/microchip/wilc1000/hif.c
index a28da5938481..839f142663e8 100644
--- a/drivers/net/wireless/microchip/wilc1000/hif.c
+++ b/drivers/net/wireless/microchip/wilc1000/hif.c
@@ -144,18 +144,19 @@ static int handle_scan_done(struct wilc_vif *vif, enum scan_event evt)
 
 	scan_req = &hif_drv->usr_scan_req;
 	if (scan_req->scan_result) {
-		scan_req->scan_result(evt, NULL, scan_req->arg);
+		scan_req->scan_result(evt, NULL, scan_req->priv);
 		scan_req->scan_result = NULL;
 	}
 
 	return result;
 }
 
-int wilc_scan(struct wilc_vif *vif, u8 scan_source, u8 scan_type,
-	      u8 *ch_freq_list, u8 ch_list_len,
+int wilc_scan(struct wilc_vif *vif, u8 scan_source,
+	      u8 scan_type, u8 *ch_freq_list,
 	      void (*scan_result_fn)(enum scan_event,
-				     struct wilc_rcvd_net_info *, void *),
-	      void *user_arg, struct cfg80211_scan_request *request)
+				     struct wilc_rcvd_net_info *,
+				     struct wilc_priv *),
+	      struct cfg80211_scan_request *request)
 {
 	int result = 0;
 	struct wid wid_list[WILC_SCAN_WID_LIST_SIZE];
@@ -164,6 +165,7 @@ int wilc_scan(struct wilc_vif *vif, u8 scan_source, u8 scan_type,
 	u8 *buffer;
 	u8 valuesize = 0;
 	u8 *search_ssid_vals = NULL;
+	const u8 ch_list_len = request->n_channels;
 	struct host_if_drv *hif_drv = vif->hif_drv;
 
 	if (hif_drv->hif_state >= HOST_IF_SCANNING &&
@@ -249,7 +251,7 @@ int wilc_scan(struct wilc_vif *vif, u8 scan_source, u8 scan_type,
 	index++;
 
 	hif_drv->usr_scan_req.scan_result = scan_result_fn;
-	hif_drv->usr_scan_req.arg = user_arg;
+	hif_drv->usr_scan_req.priv = &vif->priv;
 
 	result = wilc_send_config_pkt(vif, WILC_SET_CFG, wid_list, index);
 	if (result) {
@@ -348,7 +350,7 @@ static void handle_connect_timeout(struct work_struct *work)
 	if (hif_drv->conn_info.conn_result) {
 		hif_drv->conn_info.conn_result(CONN_DISCONN_EVENT_CONN_RESP,
 					       WILC_MAC_STATUS_DISCONNECTED,
-					       hif_drv->conn_info.arg);
+					       hif_drv->conn_info.priv);
 
 	} else {
 		netdev_err(vif->ndev, "%s: conn_result is NULL\n", __func__);
@@ -371,8 +373,9 @@ out:
 	kfree(msg);
 }
 
-void *wilc_parse_join_bss_param(struct cfg80211_bss *bss,
-				struct cfg80211_crypto_settings *crypto)
+struct wilc_join_bss_param *
+wilc_parse_join_bss_param(struct cfg80211_bss *bss,
+			  struct cfg80211_crypto_settings *crypto)
 {
 	struct wilc_join_bss_param *param;
 	struct ieee80211_p2p_noa_attr noa_attr;
@@ -545,7 +548,7 @@ static void handle_rcvd_ntwrk_info(struct work_struct *work)
 
 	if (scan_req->scan_result)
 		scan_req->scan_result(SCAN_EVENT_NETWORK_FOUND, rcvd_info,
-				      scan_req->arg);
+				      scan_req->priv);
 
 done:
 	kfree(rcvd_info->mgmt);
@@ -627,7 +630,7 @@ static inline void host_int_parse_assoc_resp_info(struct wilc_vif *vif,
 
 	del_timer(&hif_drv->connect_timer);
 	conn_info->conn_result(CONN_DISCONN_EVENT_CONN_RESP, mac_status,
-			       hif_drv->conn_info.arg);
+			       hif_drv->conn_info.priv);
 
 	if (mac_status == WILC_MAC_STATUS_CONNECTED &&
 	    conn_info->status == WLAN_STATUS_SUCCESS) {
@@ -657,7 +660,7 @@ void wilc_handle_disconnect(struct wilc_vif *vif)
 
 	if (hif_drv->conn_info.conn_result)
 		hif_drv->conn_info.conn_result(CONN_DISCONN_EVENT_DISCONN_NOTIF,
-					       0, hif_drv->conn_info.arg);
+					       0, hif_drv->conn_info.priv);
 
 	eth_zero_addr(hif_drv->assoc_bssid);
 
@@ -729,7 +732,7 @@ int wilc_disconnect(struct wilc_vif *vif)
 
 	if (scan_req->scan_result) {
 		del_timer(&hif_drv->scan_timer);
-		scan_req->scan_result(SCAN_EVENT_ABORTED, NULL, scan_req->arg);
+		scan_req->scan_result(SCAN_EVENT_ABORTED, NULL, scan_req->priv);
 		scan_req->scan_result = NULL;
 	}
 
@@ -739,7 +742,7 @@ int wilc_disconnect(struct wilc_vif *vif)
 			del_timer(&hif_drv->connect_timer);
 
 		conn_info->conn_result(CONN_DISCONN_EVENT_DISCONN_NOTIF, 0,
-				       conn_info->arg);
+				       conn_info->priv);
 	} else {
 		netdev_err(vif->ndev, "%s: conn_result is NULL\n", __func__);
 	}
@@ -878,7 +881,7 @@ static int handle_remain_on_chan(struct wilc_vif *vif,
 	if (result)
 		return -EBUSY;
 
-	hif_drv->remain_on_ch.arg = hif_remain_ch->arg;
+	hif_drv->remain_on_ch.vif = hif_remain_ch->vif;
 	hif_drv->remain_on_ch.expired = hif_remain_ch->expired;
 	hif_drv->remain_on_ch.ch = hif_remain_ch->ch;
 	hif_drv->remain_on_ch.cookie = hif_remain_ch->cookie;
@@ -915,7 +918,7 @@ static int wilc_handle_roc_expired(struct wilc_vif *vif, u64 cookie)
 		}
 
 		if (hif_drv->remain_on_ch.expired) {
-			hif_drv->remain_on_ch.expired(hif_drv->remain_on_ch.arg,
+			hif_drv->remain_on_ch.expired(hif_drv->remain_on_ch.vif,
 						      cookie);
 		}
 	} else {
@@ -1538,7 +1541,7 @@ int wilc_deinit(struct wilc_vif *vif)
 
 	if (hif_drv->usr_scan_req.scan_result) {
 		hif_drv->usr_scan_req.scan_result(SCAN_EVENT_ABORTED, NULL,
-						  hif_drv->usr_scan_req.arg);
+						  hif_drv->usr_scan_req.priv);
 		hif_drv->usr_scan_req.scan_result = NULL;
 	}
 
@@ -1669,18 +1672,15 @@ void wilc_scan_complete_received(struct wilc *wilc, u8 *buffer, u32 length)
 	}
 }
 
-int wilc_remain_on_channel(struct wilc_vif *vif, u64 cookie,
-			   u32 duration, u16 chan,
-			   void (*expired)(void *, u64),
-			   void *user_arg)
+int wilc_remain_on_channel(struct wilc_vif *vif, u64 cookie, u16 chan,
+			   void (*expired)(struct wilc_vif *, u64))
 {
 	struct wilc_remain_ch roc;
 	int result;
 
 	roc.ch = chan;
 	roc.expired = expired;
-	roc.arg = user_arg;
-	roc.duration = duration;
+	roc.vif = vif;
 	roc.cookie = cookie;
 	result = handle_remain_on_chan(vif, &roc);
 	if (result)
diff --git a/drivers/net/wireless/microchip/wilc1000/hif.h b/drivers/net/wireless/microchip/wilc1000/hif.h
index 8e386db72e45..0d380586b1d9 100644
--- a/drivers/net/wireless/microchip/wilc1000/hif.h
+++ b/drivers/net/wireless/microchip/wilc1000/hif.h
@@ -95,34 +95,37 @@ struct wilc_rcvd_net_info {
 	struct ieee80211_mgmt *mgmt;
 };
 
+struct wilc_priv;
 struct wilc_user_scan_req {
 	void (*scan_result)(enum scan_event evt,
-			    struct wilc_rcvd_net_info *info, void *priv);
-	void *arg;
+			    struct wilc_rcvd_net_info *info,
+			    struct wilc_priv *priv);
+	struct wilc_priv *priv;
 	u32 ch_cnt;
 };
 
+struct wilc_join_bss_param;
 struct wilc_conn_info {
 	u8 bssid[ETH_ALEN];
 	u8 security;
 	enum authtype auth_type;
 	enum mfptype mfp_type;
-	u8 ch;
 	u8 *req_ies;
 	size_t req_ies_len;
 	u8 *resp_ies;
 	u16 resp_ies_len;
 	u16 status;
-	void (*conn_result)(enum conn_event evt, u8 status, void *priv_data);
-	void *arg;
-	void *param;
+	void (*conn_result)(enum conn_event evt, u8 status,
+			    struct wilc_priv *priv);
+	struct wilc_priv *priv;
+	struct wilc_join_bss_param *param;
 };
 
+struct wilc_vif;
 struct wilc_remain_ch {
 	u16 ch;
-	u32 duration;
-	void (*expired)(void *priv, u64 cookie);
-	void *arg;
+	void (*expired)(struct wilc_vif *vif, u64 cookie);
+	struct wilc_vif *vif;
 	u64 cookie;
 };
 
@@ -150,7 +153,6 @@ struct host_if_drv {
 	u8 assoc_resp[WILC_MAX_ASSOC_RESP_FRAME_SIZE];
 };
 
-struct wilc_vif;
 int wilc_add_ptk(struct wilc_vif *vif, const u8 *ptk, u8 ptk_key_len,
 		 const u8 *mac_addr, const u8 *rx_mic, const u8 *tx_mic,
 		 u8 mode, u8 cipher_mode, u8 index);
@@ -171,11 +173,12 @@ int wilc_set_join_req(struct wilc_vif *vif, u8 *bssid, const u8 *ies,
 int wilc_disconnect(struct wilc_vif *vif);
 int wilc_set_mac_chnl_num(struct wilc_vif *vif, u8 channel);
 int wilc_get_rssi(struct wilc_vif *vif, s8 *rssi_level);
-int wilc_scan(struct wilc_vif *vif, u8 scan_source, u8 scan_type,
-	      u8 *ch_freq_list, u8 ch_list_len,
+int wilc_scan(struct wilc_vif *vif, u8 scan_source,
+	      u8 scan_type, u8 *ch_freq_list,
 	      void (*scan_result_fn)(enum scan_event,
-				     struct wilc_rcvd_net_info *, void *),
-	      void *user_arg, struct cfg80211_scan_request *request);
+				     struct wilc_rcvd_net_info *,
+				     struct wilc_priv *),
+	      struct cfg80211_scan_request *request);
 int wilc_hif_set_cfg(struct wilc_vif *vif,
 		     struct cfg_param_attr *cfg_param);
 int wilc_init(struct net_device *dev, struct host_if_drv **hif_drv_handler);
@@ -192,10 +195,8 @@ int wilc_edit_station(struct wilc_vif *vif, const u8 *mac,
 int wilc_set_power_mgmt(struct wilc_vif *vif, bool enabled, u32 timeout);
 int wilc_setup_multicast_filter(struct wilc_vif *vif, u32 enabled, u32 count,
 				u8 *mc_list);
-int wilc_remain_on_channel(struct wilc_vif *vif, u64 cookie,
-			   u32 duration, u16 chan,
-			   void (*expired)(void *, u64),
-			   void *user_arg);
+int wilc_remain_on_channel(struct wilc_vif *vif, u64 cookie, u16 chan,
+			   void (*expired)(struct wilc_vif *, u64));
 int wilc_listen_state_expired(struct wilc_vif *vif, u64 cookie);
 void wilc_frame_register(struct wilc_vif *vif, u16 frame_type, bool reg);
 int wilc_set_operation_mode(struct wilc_vif *vif, int index, u8 mode,
@@ -210,8 +211,9 @@ int wilc_set_external_auth_param(struct wilc_vif *vif,
 void wilc_scan_complete_received(struct wilc *wilc, u8 *buffer, u32 length);
 void wilc_network_info_received(struct wilc *wilc, u8 *buffer, u32 length);
 void wilc_gnrl_async_info_received(struct wilc *wilc, u8 *buffer, u32 length);
-void *wilc_parse_join_bss_param(struct cfg80211_bss *bss,
-				struct cfg80211_crypto_settings *crypto);
+struct wilc_join_bss_param *
+wilc_parse_join_bss_param(struct cfg80211_bss *bss,
+			  struct cfg80211_crypto_settings *crypto);
 int wilc_set_default_mgmt_key_index(struct wilc_vif *vif, u8 index);
 void wilc_handle_disconnect(struct wilc_vif *vif);
 
diff --git a/drivers/net/wireless/microchip/wilc1000/sdio.c b/drivers/net/wireless/microchip/wilc1000/sdio.c
index 87948ba69a22..0d13e3e46e98 100644
--- a/drivers/net/wireless/microchip/wilc1000/sdio.c
+++ b/drivers/net/wireless/microchip/wilc1000/sdio.c
@@ -106,9 +106,10 @@ static int wilc_sdio_cmd53(struct wilc *wilc, struct sdio_cmd53 *cmd)
 		size = cmd->count;
 
 	if (cmd->use_global_buf) {
-		if (size > sizeof(u32))
-			return -EINVAL;
-
+		if (size > sizeof(u32)) {
+			ret = -EINVAL;
+			goto out;
+		}
 		buf = sdio_priv->cmd53_buf;
 	}
 
@@ -123,7 +124,7 @@ static int wilc_sdio_cmd53(struct wilc *wilc, struct sdio_cmd53 *cmd)
 		if (cmd->use_global_buf)
 			memcpy(cmd->buffer, buf, size);
 	}
-
+out:
 	sdio_release_host(func);
 
 	if (ret)
diff --git a/drivers/net/wireless/purelifi/plfxlc/usb.c b/drivers/net/wireless/purelifi/plfxlc/usb.c
index 76d0a778636a..311676c1ece0 100644
--- a/drivers/net/wireless/purelifi/plfxlc/usb.c
+++ b/drivers/net/wireless/purelifi/plfxlc/usb.c
@@ -493,9 +493,12 @@ int plfxlc_usb_wreq_async(struct plfxlc_usb *usb, const u8 *buffer,
 			  void *context)
 {
 	struct usb_device *udev = interface_to_usbdev(usb->ez_usb);
-	struct urb *urb = usb_alloc_urb(0, GFP_ATOMIC);
+	struct urb *urb;
 	int r;
 
+	urb = usb_alloc_urb(0, GFP_ATOMIC);
+	if (!urb)
+		return -ENOMEM;
 	usb_fill_bulk_urb(urb, udev, usb_sndbulkpipe(udev, EP_DATA_OUT),
 			  (void *)buffer, buffer_len, complete_fn, context);
 
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800.h b/drivers/net/wireless/ralink/rt2x00/rt2800.h
index 48521e45577d..8930589b4967 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2800.h
+++ b/drivers/net/wireless/ralink/rt2x00/rt2800.h
@@ -3194,4 +3194,8 @@ enum rt2800_eeprom_word {
  */
 #define BCN_TBTT_OFFSET 64
 
+/* Watchdog type mask */
+#define RT2800_WATCHDOG_HANG		BIT(0)
+#define RT2800_WATCHDOG_DMA_BUSY	BIT(1)
+
 #endif /* RT2800_H */
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
index ee880f749b3c..aaf31857ae1e 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
@@ -30,9 +30,10 @@
 #include "rt2800lib.h"
 #include "rt2800.h"
 
-static bool modparam_watchdog;
-module_param_named(watchdog, modparam_watchdog, bool, S_IRUGO);
-MODULE_PARM_DESC(watchdog, "Enable watchdog to detect tx/rx hangs and reset hardware if detected");
+static unsigned int modparam_watchdog = RT2800_WATCHDOG_DMA_BUSY;
+module_param_named(watchdog, modparam_watchdog, uint, 0444);
+MODULE_PARM_DESC(watchdog, "Enable watchdog to recover tx/rx hangs.\n"
+		 "\t\t(0=disabled, 1=hang watchdog, 2=DMA watchdog(default), 3=both)");
 
 /*
  * Register access.
@@ -1261,15 +1262,12 @@ static void rt2800_update_survey(struct rt2x00_dev *rt2x00dev)
 	chan_survey->time_ext_busy += rt2800_register_read(rt2x00dev, CH_BUSY_STA_SEC);
 }
 
-void rt2800_watchdog(struct rt2x00_dev *rt2x00dev)
+static bool rt2800_watchdog_hung(struct rt2x00_dev *rt2x00dev)
 {
 	struct data_queue *queue;
 	bool hung_tx = false;
 	bool hung_rx = false;
 
-	if (test_bit(DEVICE_STATE_SCANNING, &rt2x00dev->flags))
-		return;
-
 	rt2800_update_survey(rt2x00dev);
 
 	queue_for_each(rt2x00dev, queue) {
@@ -1297,18 +1295,72 @@ void rt2800_watchdog(struct rt2x00_dev *rt2x00dev)
 		}
 	}
 
+	if (!hung_tx && !hung_rx)
+		return false;
+
 	if (hung_tx)
 		rt2x00_warn(rt2x00dev, "Watchdog TX hung detected\n");
 
 	if (hung_rx)
 		rt2x00_warn(rt2x00dev, "Watchdog RX hung detected\n");
 
-	if (hung_tx || hung_rx) {
-		queue_for_each(rt2x00dev, queue)
-			queue->wd_count = 0;
+	queue_for_each(rt2x00dev, queue)
+		queue->wd_count = 0;
+
+	return true;
+}
+
+static bool rt2800_watchdog_dma_busy(struct rt2x00_dev *rt2x00dev)
+{
+	bool busy_rx, busy_tx;
+	u32 reg_cfg = rt2800_register_read(rt2x00dev, WPDMA_GLO_CFG);
+	u32 reg_int = rt2800_register_read(rt2x00dev, INT_SOURCE_CSR);
+
+	if (rt2x00_get_field32(reg_cfg, WPDMA_GLO_CFG_RX_DMA_BUSY) &&
+	    rt2x00_get_field32(reg_int, INT_SOURCE_CSR_RX_COHERENT))
+		rt2x00dev->rxdma_busy++;
+	else
+		rt2x00dev->rxdma_busy = 0;
+
+	if (rt2x00_get_field32(reg_cfg, WPDMA_GLO_CFG_TX_DMA_BUSY) &&
+	    rt2x00_get_field32(reg_int, INT_SOURCE_CSR_TX_COHERENT))
+		rt2x00dev->txdma_busy++;
+	else
+		rt2x00dev->txdma_busy = 0;
+
+	busy_rx = rt2x00dev->rxdma_busy > 30;
+	busy_tx = rt2x00dev->txdma_busy > 30;
+
+	if (!busy_rx && !busy_tx)
+		return false;
 
+	if (busy_rx)
+		rt2x00_warn(rt2x00dev, "Watchdog RX DMA busy detected\n");
+
+	if (busy_tx)
+		rt2x00_warn(rt2x00dev, "Watchdog TX DMA busy detected\n");
+
+	rt2x00dev->rxdma_busy = 0;
+	rt2x00dev->txdma_busy = 0;
+
+	return true;
+}
+
+void rt2800_watchdog(struct rt2x00_dev *rt2x00dev)
+{
+	bool reset = false;
+
+	if (test_bit(DEVICE_STATE_SCANNING, &rt2x00dev->flags))
+		return;
+
+	if (rt2x00dev->link.watchdog & RT2800_WATCHDOG_DMA_BUSY)
+		reset = rt2800_watchdog_dma_busy(rt2x00dev);
+
+	if (rt2x00dev->link.watchdog & RT2800_WATCHDOG_HANG)
+		reset = rt2800_watchdog_hung(rt2x00dev) || reset;
+
+	if (reset)
 		ieee80211_restart_hw(rt2x00dev->hw);
-	}
 }
 EXPORT_SYMBOL_GPL(rt2800_watchdog);
 
@@ -6048,7 +6100,7 @@ static int rt2800_init_registers(struct rt2x00_dev *rt2x00dev)
 	rt2x00_set_field32(&reg, CCK_PROT_CFG_TX_OP_ALLOW_MM40, 0);
 	rt2x00_set_field32(&reg, CCK_PROT_CFG_TX_OP_ALLOW_GF20, 1);
 	rt2x00_set_field32(&reg, CCK_PROT_CFG_TX_OP_ALLOW_GF40, 0);
-	rt2x00_set_field32(&reg, CCK_PROT_CFG_RTS_TH_EN, 1);
+	rt2x00_set_field32(&reg, CCK_PROT_CFG_RTS_TH_EN, 0);
 	rt2800_register_write(rt2x00dev, CCK_PROT_CFG, reg);
 
 	reg = rt2800_register_read(rt2x00dev, OFDM_PROT_CFG);
@@ -6061,7 +6113,7 @@ static int rt2800_init_registers(struct rt2x00_dev *rt2x00dev)
 	rt2x00_set_field32(&reg, OFDM_PROT_CFG_TX_OP_ALLOW_MM40, 0);
 	rt2x00_set_field32(&reg, OFDM_PROT_CFG_TX_OP_ALLOW_GF20, 1);
 	rt2x00_set_field32(&reg, OFDM_PROT_CFG_TX_OP_ALLOW_GF40, 0);
-	rt2x00_set_field32(&reg, OFDM_PROT_CFG_RTS_TH_EN, 1);
+	rt2x00_set_field32(&reg, OFDM_PROT_CFG_RTS_TH_EN, 0);
 	rt2800_register_write(rt2x00dev, OFDM_PROT_CFG, reg);
 
 	reg = rt2800_register_read(rt2x00dev, MM20_PROT_CFG);
@@ -8659,7 +8711,7 @@ static void rt2800_rxdcoc_calibration(struct rt2x00_dev *rt2x00dev)
 	rt2800_rfcsr_write_bank(rt2x00dev, 5, 4, saverfb5r4);
 	rt2800_rfcsr_write_bank(rt2x00dev, 7, 4, saverfb7r4);
 
-	rt2800_bbp_write(rt2x00dev, 158, 141);
+	rt2800_bbp_write(rt2x00dev, 158, 140);
 	bbpreg = rt2800_bbp_read(rt2x00dev, 159);
 	bbpreg = bbpreg & (~0x40);
 	rt2800_bbp_write(rt2x00dev, 159, bbpreg);
@@ -12013,11 +12065,13 @@ int rt2800_probe_hw(struct rt2x00_dev *rt2x00dev)
 		__set_bit(REQUIRE_TASKLET_CONTEXT, &rt2x00dev->cap_flags);
 	}
 
-	if (modparam_watchdog) {
+	rt2x00dev->link.watchdog = modparam_watchdog;
+	/* USB NICs don't support DMA watchdog as INT_SOURCE_CSR is invalid */
+	if (rt2x00_is_usb(rt2x00dev))
+		rt2x00dev->link.watchdog &= ~RT2800_WATCHDOG_DMA_BUSY;
+	if (rt2x00dev->link.watchdog) {
 		__set_bit(CAPABILITY_RESTART_HW, &rt2x00dev->cap_flags);
 		rt2x00dev->link.watchdog_interval = msecs_to_jiffies(100);
-	} else {
-		rt2x00dev->link.watchdog_disabled = true;
 	}
 
 	/*
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00.h b/drivers/net/wireless/ralink/rt2x00/rt2x00.h
index aaaf99331967..82af01448a0a 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00.h
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00.h
@@ -334,7 +334,7 @@ struct link {
 	 */
 	struct delayed_work watchdog_work;
 	unsigned int watchdog_interval;
-	bool watchdog_disabled;
+	unsigned int watchdog;
 
 	/*
 	 * Work structure for scheduling periodic AGC adjustments.
@@ -926,6 +926,9 @@ struct rt2x00_dev {
 	 */
 	u16 beacon_int;
 
+	/* Rx/Tx DMA busy watchdog counter */
+	u16 rxdma_busy, txdma_busy;
+
 	/**
 	 * Timestamp of last received beacon
 	 */
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c b/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c
index c88ce446e117..9e7d9dbe954c 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c
@@ -101,6 +101,7 @@ void rt2x00lib_disable_radio(struct rt2x00_dev *rt2x00dev)
 	rt2x00link_stop_tuner(rt2x00dev);
 	rt2x00queue_stop_queues(rt2x00dev);
 	rt2x00queue_flush_queues(rt2x00dev, true);
+	rt2x00queue_stop_queue(rt2x00dev->bcn);
 
 	/*
 	 * Disable radio.
@@ -1286,6 +1287,7 @@ int rt2x00lib_start(struct rt2x00_dev *rt2x00dev)
 	rt2x00dev->intf_ap_count = 0;
 	rt2x00dev->intf_sta_count = 0;
 	rt2x00dev->intf_associated = 0;
+	rt2x00dev->intf_beaconing = 0;
 
 	/* Enable the radio */
 	retval = rt2x00lib_enable_radio(rt2x00dev);
@@ -1312,6 +1314,7 @@ void rt2x00lib_stop(struct rt2x00_dev *rt2x00dev)
 	rt2x00dev->intf_ap_count = 0;
 	rt2x00dev->intf_sta_count = 0;
 	rt2x00dev->intf_associated = 0;
+	rt2x00dev->intf_beaconing = 0;
 }
 
 static inline void rt2x00lib_set_if_combinations(struct rt2x00_dev *rt2x00dev)
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00link.c b/drivers/net/wireless/ralink/rt2x00/rt2x00link.c
index 6cf7e7c997c2..fb23d409fba8 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00link.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00link.c
@@ -384,7 +384,7 @@ void rt2x00link_start_watchdog(struct rt2x00_dev *rt2x00dev)
 	struct link *link = &rt2x00dev->link;
 
 	if (test_bit(DEVICE_STATE_PRESENT, &rt2x00dev->flags) &&
-	    rt2x00dev->ops->lib->watchdog && !link->watchdog_disabled)
+	    rt2x00dev->ops->lib->watchdog && link->watchdog)
 		ieee80211_queue_delayed_work(rt2x00dev->hw,
 					     &link->watchdog_work,
 					     link->watchdog_interval);
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c
index 4202c6517783..75fda72c14ca 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c
@@ -598,6 +598,17 @@ void rt2x00mac_bss_info_changed(struct ieee80211_hw *hw,
 	 */
 	if (changes & BSS_CHANGED_BEACON_ENABLED) {
 		mutex_lock(&intf->beacon_skb_mutex);
+
+		/*
+		 * Clear the 'enable_beacon' flag and clear beacon because
+		 * the beacon queue has been stopped after hardware reset.
+		 */
+		if (test_bit(DEVICE_STATE_RESET, &rt2x00dev->flags) &&
+		    intf->enable_beacon) {
+			intf->enable_beacon = false;
+			rt2x00queue_clear_beacon(rt2x00dev, vif);
+		}
+
 		if (!bss_conf->enable_beacon && intf->enable_beacon) {
 			rt2x00dev->intf_beaconing--;
 			intf->enable_beacon = false;
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c
index 98df0aef8168..013003777fee 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c
@@ -416,9 +416,6 @@ static void rt2x00queue_create_tx_descriptor(struct rt2x00_dev *rt2x00dev,
 			__set_bit(ENTRY_TXD_RTS_FRAME, &txdesc->flags);
 		else
 			__set_bit(ENTRY_TXD_CTS_FRAME, &txdesc->flags);
-		if (tx_info->control.rts_cts_rate_idx >= 0)
-			rate =
-			    ieee80211_get_rts_cts_rate(rt2x00dev->hw, tx_info);
 	}
 
 	/*
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
index 43ee7592bc6e..180907319e8c 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
@@ -7961,6 +7961,18 @@ static const struct usb_device_id dev_table[] = {
 	.driver_info = (unsigned long)&rtl8192eu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(USB_VENDOR_ID_REALTEK, 0x818c, 0xff, 0xff, 0xff),
 	.driver_info = (unsigned long)&rtl8192eu_fops},
+/* D-Link DWA-131 rev C1 */
+{USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x3312, 0xff, 0xff, 0xff),
+	.driver_info = (unsigned long)&rtl8192eu_fops},
+/* TP-Link TL-WN8200ND V2 */
+{USB_DEVICE_AND_INTERFACE_INFO(0x2357, 0x0126, 0xff, 0xff, 0xff),
+	.driver_info = (unsigned long)&rtl8192eu_fops},
+/* Mercusys MW300UM */
+{USB_DEVICE_AND_INTERFACE_INFO(0x2c4e, 0x0100, 0xff, 0xff, 0xff),
+	.driver_info = (unsigned long)&rtl8192eu_fops},
+/* Mercusys MW300UH */
+{USB_DEVICE_AND_INTERFACE_INFO(0x2c4e, 0x0104, 0xff, 0xff, 0xff),
+	.driver_info = (unsigned long)&rtl8192eu_fops},
 #endif
 { }
 };
diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c
index 7ce37fb4fdbf..1a8d715b7c07 100644
--- a/drivers/net/wireless/realtek/rtlwifi/base.c
+++ b/drivers/net/wireless/realtek/rtlwifi/base.c
@@ -1402,10 +1402,6 @@ bool rtl_action_proc(struct ieee80211_hw *hw, struct sk_buff *skb, u8 is_tx)
 
 				sta_entry =
 					(struct rtl_sta_info *)sta->drv_priv;
-				if (!sta_entry) {
-					rcu_read_unlock();
-					return true;
-				}
 				capab =
 				  le16_to_cpu(mgmt->u.action.u.addba_req.capab);
 				tid = (capab &
@@ -1760,8 +1756,6 @@ int rtl_tx_agg_start(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		return -EINVAL;
 
 	sta_entry = (struct rtl_sta_info *)sta->drv_priv;
-	if (!sta_entry)
-		return -ENXIO;
 	tid_data = &sta_entry->tids[tid];
 
 	rtl_dbg(rtlpriv, COMP_SEND, DBG_DMESG,
@@ -1818,8 +1812,6 @@ int rtl_rx_agg_start(struct ieee80211_hw *hw,
 	}
 
 	sta_entry = (struct rtl_sta_info *)sta->drv_priv;
-	if (!sta_entry)
-		return -ENXIO;
 	tid_data = &sta_entry->tids[tid];
 
 	rtl_dbg(rtlpriv, COMP_RECV, DBG_DMESG,
diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c
index 9886e719739b..96ce05bcf0b3 100644
--- a/drivers/net/wireless/realtek/rtlwifi/pci.c
+++ b/drivers/net/wireless/realtek/rtlwifi/pci.c
@@ -64,13 +64,12 @@ static void _rtl_pci_update_default_setting(struct ieee80211_hw *hw)
 	struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw));
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	u8 pcibridge_vendor = pcipriv->ndis_adapter.pcibridge_vendor;
-	u8 init_aspm;
+	u16 init_aspm;
 
 	ppsc->reg_rfps_level = 0;
 	ppsc->support_aspm = false;
 
 	/*Update PCI ASPM setting */
-	ppsc->const_amdpci_aspm = rtlpci->const_amdpci_aspm;
 	switch (rtlpci->const_pci_aspm) {
 	case 0:
 		/*No ASPM */
@@ -151,9 +150,10 @@ static void _rtl_pci_update_default_setting(struct ieee80211_hw *hw)
 	/* toshiba aspm issue, toshiba will set aspm selfly
 	 * so we should not set aspm in driver
 	 */
-	pci_read_config_byte(rtlpci->pdev, 0x80, &init_aspm);
+	pcie_capability_read_word(rtlpci->pdev, PCI_EXP_LNKCTL, &init_aspm);
 	if (rtlpriv->rtlhal.hw_type == HARDWARE_TYPE_RTL8192SE &&
-	    init_aspm == 0x43)
+	    ((u8)init_aspm) == (PCI_EXP_LNKCTL_ASPM_L0S |
+				PCI_EXP_LNKCTL_ASPM_L1 | PCI_EXP_LNKCTL_CCC))
 		ppsc->support_aspm = false;
 }
 
@@ -164,21 +164,29 @@ static bool _rtl_pci_platform_switch_device_pci_aspm(
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
 
+	value &= PCI_EXP_LNKCTL_ASPMC;
+
 	if (rtlhal->hw_type != HARDWARE_TYPE_RTL8192SE)
-		value |= 0x40;
+		value |= PCI_EXP_LNKCTL_CCC;
 
-	pci_write_config_byte(rtlpci->pdev, 0x80, value);
+	pcie_capability_clear_and_set_word(rtlpci->pdev, PCI_EXP_LNKCTL,
+					   PCI_EXP_LNKCTL_ASPMC | value,
+					   value);
 
 	return false;
 }
 
-/*When we set 0x01 to enable clk request. Set 0x0 to disable clk req.*/
-static void _rtl_pci_switch_clk_req(struct ieee80211_hw *hw, u8 value)
+/* @value is PCI_EXP_LNKCTL_CLKREQ_EN or 0 to enable/disable clk request. */
+static void _rtl_pci_switch_clk_req(struct ieee80211_hw *hw, u16 value)
 {
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
 
-	pci_write_config_byte(rtlpci->pdev, 0x81, value);
+	value &= PCI_EXP_LNKCTL_CLKREQ_EN;
+
+	pcie_capability_clear_and_set_word(rtlpci->pdev, PCI_EXP_LNKCTL,
+					   PCI_EXP_LNKCTL_CLKREQ_EN,
+					   value);
 
 	if (rtlhal->hw_type == HARDWARE_TYPE_RTL8192SE)
 		udelay(100);
@@ -192,13 +200,10 @@ static void rtl_pci_disable_aspm(struct ieee80211_hw *hw)
 	struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw));
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	u8 pcibridge_vendor = pcipriv->ndis_adapter.pcibridge_vendor;
-	u8 num4bytes = pcipriv->ndis_adapter.num4bytes;
 	/*Retrieve original configuration settings. */
 	u8 linkctrl_reg = pcipriv->ndis_adapter.linkctrl_reg;
-	u16 pcibridge_linkctrlreg = pcipriv->ndis_adapter.
-				pcibridge_linkctrlreg;
 	u16 aspmlevel = 0;
-	u8 tmp_u1b = 0;
+	u16 tmp_u1b = 0;
 
 	if (!ppsc->support_aspm)
 		return;
@@ -216,21 +221,13 @@ static void rtl_pci_disable_aspm(struct ieee80211_hw *hw)
 	}
 
 	/*for promising device will in L0 state after an I/O. */
-	pci_read_config_byte(rtlpci->pdev, 0x80, &tmp_u1b);
+	pcie_capability_read_word(rtlpci->pdev, PCI_EXP_LNKCTL, &tmp_u1b);
 
 	/*Set corresponding value. */
-	aspmlevel |= BIT(0) | BIT(1);
+	aspmlevel |= PCI_EXP_LNKCTL_ASPM_L0S | PCI_EXP_LNKCTL_ASPM_L1;
 	linkctrl_reg &= ~aspmlevel;
-	pcibridge_linkctrlreg &= ~(BIT(0) | BIT(1));
 
 	_rtl_pci_platform_switch_device_pci_aspm(hw, linkctrl_reg);
-	udelay(50);
-
-	/*4 Disable Pci Bridge ASPM */
-	pci_write_config_byte(rtlpci->pdev, (num4bytes << 2),
-			      pcibridge_linkctrlreg);
-
-	udelay(50);
 }
 
 /*Enable RTL8192SE ASPM & Enable Pci Bridge ASPM for
@@ -245,9 +242,7 @@ static void rtl_pci_enable_aspm(struct ieee80211_hw *hw)
 	struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw));
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	u8 pcibridge_vendor = pcipriv->ndis_adapter.pcibridge_vendor;
-	u8 num4bytes = pcipriv->ndis_adapter.num4bytes;
 	u16 aspmlevel;
-	u8 u_pcibridge_aspmsetting;
 	u8 u_device_aspmsetting;
 
 	if (!ppsc->support_aspm)
@@ -259,25 +254,6 @@ static void rtl_pci_enable_aspm(struct ieee80211_hw *hw)
 		return;
 	}
 
-	/*4 Enable Pci Bridge ASPM */
-
-	u_pcibridge_aspmsetting =
-	    pcipriv->ndis_adapter.pcibridge_linkctrlreg |
-	    rtlpci->const_hostpci_aspm_setting;
-
-	if (pcibridge_vendor == PCI_BRIDGE_VENDOR_INTEL)
-		u_pcibridge_aspmsetting &= ~BIT(0);
-
-	pci_write_config_byte(rtlpci->pdev, (num4bytes << 2),
-			      u_pcibridge_aspmsetting);
-
-	rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
-		"PlatformEnableASPM(): Write reg[%x] = %x\n",
-		(pcipriv->ndis_adapter.pcibridge_pciehdr_offset + 0x10),
-		u_pcibridge_aspmsetting);
-
-	udelay(50);
-
 	/*Get ASPM level (with/without Clock Req) */
 	aspmlevel = rtlpci->const_devicepci_aspm_setting;
 	u_device_aspmsetting = pcipriv->ndis_adapter.linkctrl_reg;
@@ -291,7 +267,8 @@ static void rtl_pci_enable_aspm(struct ieee80211_hw *hw)
 
 	if (ppsc->reg_rfps_level & RT_RF_OFF_LEVL_CLK_REQ) {
 		_rtl_pci_switch_clk_req(hw, (ppsc->reg_rfps_level &
-					     RT_RF_OFF_LEVL_CLK_REQ) ? 1 : 0);
+					     RT_RF_OFF_LEVL_CLK_REQ) ?
+					     PCI_EXP_LNKCTL_CLKREQ_EN : 0);
 		RT_SET_PS_LEVEL(ppsc, RT_RF_OFF_LEVL_CLK_REQ);
 	}
 	udelay(100);
@@ -358,22 +335,6 @@ static bool rtl_pci_check_buddy_priv(struct ieee80211_hw *hw,
 	return tpriv != NULL;
 }
 
-static void rtl_pci_get_linkcontrol_field(struct ieee80211_hw *hw)
-{
-	struct rtl_pci_priv *pcipriv = rtl_pcipriv(hw);
-	struct rtl_pci *rtlpci = rtl_pcidev(pcipriv);
-	u8 capabilityoffset = pcipriv->ndis_adapter.pcibridge_pciehdr_offset;
-	u8 linkctrl_reg;
-	u8 num4bbytes;
-
-	num4bbytes = (capabilityoffset + 0x10) / 4;
-
-	/*Read  Link Control Register */
-	pci_read_config_byte(rtlpci->pdev, (num4bbytes << 2), &linkctrl_reg);
-
-	pcipriv->ndis_adapter.pcibridge_linkctrlreg = linkctrl_reg;
-}
-
 static void rtl_pci_parse_configuration(struct pci_dev *pdev,
 					struct ieee80211_hw *hw)
 {
@@ -390,9 +351,8 @@ static void rtl_pci_parse_configuration(struct pci_dev *pdev,
 	rtl_dbg(rtlpriv, COMP_INIT, DBG_TRACE, "Link Control Register =%x\n",
 		pcipriv->ndis_adapter.linkctrl_reg);
 
-	pci_read_config_byte(pdev, 0x98, &tmp);
-	tmp |= BIT(4);
-	pci_write_config_byte(pdev, 0x98, tmp);
+	pcie_capability_set_word(pdev, PCI_EXP_DEVCTL2,
+				 PCI_EXP_DEVCTL2_COMP_TMOUT_DIS);
 
 	tmp = 0x17;
 	pci_write_config_byte(pdev, 0x70f, tmp);
@@ -2008,7 +1968,6 @@ static bool _rtl_pci_find_adapter(struct pci_dev *pdev,
 	 */
 	if (bridge_pdev) {
 		/*find bridge info if available */
-		pcipriv->ndis_adapter.pcibridge_vendorid = bridge_pdev->vendor;
 		for (tmp = 0; tmp < PCI_BRIDGE_VENDOR_MAX; tmp++) {
 			if (bridge_pdev->vendor == pcibridge_vendors[tmp]) {
 				pcipriv->ndis_adapter.pcibridge_vendor = tmp;
@@ -2028,12 +1987,6 @@ static bool _rtl_pci_find_adapter(struct pci_dev *pdev,
 		    PCI_SLOT(bridge_pdev->devfn);
 		pcipriv->ndis_adapter.pcibridge_funcnum =
 		    PCI_FUNC(bridge_pdev->devfn);
-		pcipriv->ndis_adapter.pcibridge_pciehdr_offset =
-		    pci_pcie_cap(bridge_pdev);
-		pcipriv->ndis_adapter.num4bytes =
-		    (pcipriv->ndis_adapter.pcibridge_pciehdr_offset + 0x10) / 4;
-
-		rtl_pci_get_linkcontrol_field(hw);
 
 		if (pcipriv->ndis_adapter.pcibridge_vendor ==
 		    PCI_BRIDGE_VENDOR_AMD) {
@@ -2050,13 +2003,11 @@ static bool _rtl_pci_find_adapter(struct pci_dev *pdev,
 		pdev->vendor, pcipriv->ndis_adapter.linkctrl_reg);
 
 	rtl_dbg(rtlpriv, COMP_INIT, DBG_DMESG,
-		"pci_bridge busnumber:devnumber:funcnumber:vendor:pcie_cap:link_ctl_reg:amd %d:%d:%d:%x:%x:%x:%x\n",
+		"pci_bridge busnumber:devnumber:funcnumber:vendor:amd %d:%d:%d:%x:%x\n",
 		pcipriv->ndis_adapter.pcibridge_busnum,
 		pcipriv->ndis_adapter.pcibridge_devnum,
 		pcipriv->ndis_adapter.pcibridge_funcnum,
 		pcibridge_vendors[pcipriv->ndis_adapter.pcibridge_vendor],
-		pcipriv->ndis_adapter.pcibridge_pciehdr_offset,
-		pcipriv->ndis_adapter.pcibridge_linkctrlreg,
 		pcipriv->ndis_adapter.amd_l1_patch);
 
 	rtl_pci_parse_configuration(pdev, hw);
diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.h b/drivers/net/wireless/realtek/rtlwifi/pci.h
index 866861626a0a..e8fa022df8b4 100644
--- a/drivers/net/wireless/realtek/rtlwifi/pci.h
+++ b/drivers/net/wireless/realtek/rtlwifi/pci.h
@@ -44,18 +44,6 @@
 #define ATI_DEVICE_ID				0x7914
 #define AMD_VENDOR_ID				0x1022
 
-#define PCI_MAX_BRIDGE_NUMBER			255
-#define PCI_MAX_DEVICES				32
-#define PCI_MAX_FUNCTION			8
-
-#define PCI_CONF_ADDRESS	0x0CF8	/*PCI Configuration Space Address */
-#define PCI_CONF_DATA		0x0CFC	/*PCI Configuration Space Data */
-
-#define PCI_CLASS_BRIDGE_DEV		0x06
-#define PCI_SUBCLASS_BR_PCI_TO_PCI	0x04
-#define PCI_CAPABILITY_ID_PCI_EXPRESS	0x10
-#define PCI_CAP_ID_EXP			0x10
-
 #define U1DONTCARE			0xFF
 #define U2DONTCARE			0xFFFF
 #define U4DONTCARE			0xFFFFFFFF
@@ -113,11 +101,6 @@ enum pci_bridge_vendor {
 	PCI_BRIDGE_VENDOR_MAX,
 };
 
-struct rtl_pci_capabilities_header {
-	u8 capability_id;
-	u8 next;
-};
-
 /* In new TRX flow, Buffer_desc is new concept
  * But TX wifi info == TX descriptor in old flow
  * RX wifi info == RX descriptor in old flow
@@ -195,7 +178,6 @@ struct rtl_pci {
 	u32 reg_bcn_ctrl_val;
 
 	 /*ASPM*/ u8 const_pci_aspm;
-	u8 const_amdpci_aspm;
 	u8 const_hwsw_rfoff_d3;
 	u8 const_support_pciaspm;
 	/*pci-e bridge */
@@ -233,13 +215,6 @@ struct mp_adapter {
 	u8 pcibridge_funcnum;
 
 	u8 pcibridge_vendor;
-	u16 pcibridge_vendorid;
-	u16 pcibridge_deviceid;
-
-	u8 num4bytes;
-
-	u8 pcibridge_pciehdr_offset;
-	u8 pcibridge_linkctrlreg;
 
 	bool amd_l1_patch;
 };
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/phy.c
index 12d0b3a87af7..0fab3a0c7d49 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/phy.c
@@ -16,12 +16,6 @@ static u32 _rtl88e_phy_rf_serial_read(struct ieee80211_hw *hw,
 static void _rtl88e_phy_rf_serial_write(struct ieee80211_hw *hw,
 					enum radio_path rfpath, u32 offset,
 					u32 data);
-static u32 _rtl88e_phy_calculate_bit_shift(u32 bitmask)
-{
-	u32 i = ffs(bitmask);
-
-	return i ? i - 1 : 32;
-}
 static bool _rtl88e_phy_bb8188e_config_parafile(struct ieee80211_hw *hw);
 static bool _rtl88e_phy_config_mac_with_headerfile(struct ieee80211_hw *hw);
 static bool phy_config_bb_with_headerfile(struct ieee80211_hw *hw,
@@ -51,7 +45,7 @@ u32 rtl88e_phy_query_bb_reg(struct ieee80211_hw *hw, u32 regaddr, u32 bitmask)
 	rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE,
 		"regaddr(%#x), bitmask(%#x)\n", regaddr, bitmask);
 	originalvalue = rtl_read_dword(rtlpriv, regaddr);
-	bitshift = _rtl88e_phy_calculate_bit_shift(bitmask);
+	bitshift = calculate_bit_shift(bitmask);
 	returnvalue = (originalvalue & bitmask) >> bitshift;
 
 	rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE,
@@ -74,7 +68,7 @@ void rtl88e_phy_set_bb_reg(struct ieee80211_hw *hw,
 
 	if (bitmask != MASKDWORD) {
 		originalvalue = rtl_read_dword(rtlpriv, regaddr);
-		bitshift = _rtl88e_phy_calculate_bit_shift(bitmask);
+		bitshift = calculate_bit_shift(bitmask);
 		data = ((originalvalue & (~bitmask)) | (data << bitshift));
 	}
 
@@ -99,7 +93,7 @@ u32 rtl88e_phy_query_rf_reg(struct ieee80211_hw *hw,
 
 
 	original_value = _rtl88e_phy_rf_serial_read(hw, rfpath, regaddr);
-	bitshift = _rtl88e_phy_calculate_bit_shift(bitmask);
+	bitshift = calculate_bit_shift(bitmask);
 	readback_value = (original_value & bitmask) >> bitshift;
 
 	spin_unlock(&rtlpriv->locks.rf_lock);
@@ -127,7 +121,7 @@ void rtl88e_phy_set_rf_reg(struct ieee80211_hw *hw,
 			original_value = _rtl88e_phy_rf_serial_read(hw,
 								    rfpath,
 								    regaddr);
-			bitshift = _rtl88e_phy_calculate_bit_shift(bitmask);
+			bitshift = calculate_bit_shift(bitmask);
 			data =
 			    ((original_value & (~bitmask)) |
 			     (data << bitshift));
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c
index b77937fe2448..37bb59fa8bfa 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c
@@ -21,9 +21,6 @@ static void rtl88e_init_aspm_vars(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
-	/*close ASPM for AMD defaultly */
-	rtlpci->const_amdpci_aspm = 0;
-
 	/* ASPM PS mode.
 	 * 0 - Disable ASPM,
 	 * 1 - Enable ASPM without Clock Req,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192c/phy_common.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192c/phy_common.c
index 3d29c8dbb255..3730613a3962 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192c/phy_common.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192c/phy_common.c
@@ -17,7 +17,7 @@ u32 rtl92c_phy_query_bb_reg(struct ieee80211_hw *hw, u32 regaddr, u32 bitmask)
 	rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE, "regaddr(%#x), bitmask(%#x)\n",
 		regaddr, bitmask);
 	originalvalue = rtl_read_dword(rtlpriv, regaddr);
-	bitshift = _rtl92c_phy_calculate_bit_shift(bitmask);
+	bitshift = calculate_bit_shift(bitmask);
 	returnvalue = (originalvalue & bitmask) >> bitshift;
 
 	rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE,
@@ -40,7 +40,7 @@ void rtl92c_phy_set_bb_reg(struct ieee80211_hw *hw,
 
 	if (bitmask != MASKDWORD) {
 		originalvalue = rtl_read_dword(rtlpriv, regaddr);
-		bitshift = _rtl92c_phy_calculate_bit_shift(bitmask);
+		bitshift = calculate_bit_shift(bitmask);
 		data = ((originalvalue & (~bitmask)) | (data << bitshift));
 	}
 
@@ -143,14 +143,6 @@ void _rtl92c_phy_rf_serial_write(struct ieee80211_hw *hw,
 }
 EXPORT_SYMBOL(_rtl92c_phy_rf_serial_write);
 
-u32 _rtl92c_phy_calculate_bit_shift(u32 bitmask)
-{
-	u32 i = ffs(bitmask);
-
-	return i ? i - 1 : 32;
-}
-EXPORT_SYMBOL(_rtl92c_phy_calculate_bit_shift);
-
 static void _rtl92c_phy_bb_config_1t(struct ieee80211_hw *hw)
 {
 	rtl_set_bbreg(hw, RFPGA0_TXINFO, 0x3, 0x2);
@@ -1487,12 +1479,8 @@ EXPORT_SYMBOL(rtl92c_phy_lc_calibrate);
 
 void rtl92c_phy_ap_calibrate(struct ieee80211_hw *hw, s8 delta)
 {
-	struct rtl_priv *rtlpriv = rtl_priv(hw);
-	struct rtl_phy *rtlphy = &(rtlpriv->phy);
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
 
-	if (rtlphy->apk_done)
-		return;
 	if (IS_92C_SERIAL(rtlhal->version))
 		_rtl92c_phy_ap_calibrate(hw, delta, true);
 	else
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192c/phy_common.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192c/phy_common.h
index 75afa6253ad0..e64d377dfe9e 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192c/phy_common.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192c/phy_common.h
@@ -196,7 +196,6 @@ bool rtl92c_phy_set_rf_power_state(struct ieee80211_hw *hw,
 void rtl92ce_phy_set_rf_on(struct ieee80211_hw *hw);
 void rtl92c_phy_set_io(struct ieee80211_hw *hw);
 void rtl92c_bb_block_on(struct ieee80211_hw *hw);
-u32 _rtl92c_phy_calculate_bit_shift(u32 bitmask);
 long _rtl92c_phy_txpwr_idx_to_dbm(struct ieee80211_hw *hw,
 				  enum wireless_mode wirelessmode,
 				  u8 txpwridx);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/phy.c
index da54e51badd3..fa70a7d5539f 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/phy.c
@@ -39,7 +39,7 @@ u32 rtl92c_phy_query_rf_reg(struct ieee80211_hw *hw,
 							       rfpath, regaddr);
 	}
 
-	bitshift = _rtl92c_phy_calculate_bit_shift(bitmask);
+	bitshift = calculate_bit_shift(bitmask);
 	readback_value = (original_value & bitmask) >> bitshift;
 
 	spin_unlock(&rtlpriv->locks.rf_lock);
@@ -110,7 +110,7 @@ void rtl92ce_phy_set_rf_reg(struct ieee80211_hw *hw,
 			original_value = _rtl92c_phy_rf_serial_read(hw,
 								    rfpath,
 								    regaddr);
-			bitshift = _rtl92c_phy_calculate_bit_shift(bitmask);
+			bitshift = calculate_bit_shift(bitmask);
 			data =
 			    ((original_value & (~bitmask)) |
 			     (data << bitshift));
@@ -122,7 +122,7 @@ void rtl92ce_phy_set_rf_reg(struct ieee80211_hw *hw,
 			original_value = _rtl92c_phy_fw_rf_serial_read(hw,
 								       rfpath,
 								       regaddr);
-			bitshift = _rtl92c_phy_calculate_bit_shift(bitmask);
+			bitshift = calculate_bit_shift(bitmask);
 			data =
 			    ((original_value & (~bitmask)) |
 			     (data << bitshift));
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/phy.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/phy.h
index 7582a162bd11..c7a0d4c776f0 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/phy.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/phy.h
@@ -94,7 +94,6 @@ u32 _rtl92c_phy_rf_serial_read(struct ieee80211_hw *hw, enum radio_path rfpath,
 			       u32 offset);
 u32 _rtl92c_phy_fw_rf_serial_read(struct ieee80211_hw *hw,
 				  enum radio_path rfpath, u32 offset);
-u32 _rtl92c_phy_calculate_bit_shift(u32 bitmask);
 void _rtl92c_phy_rf_serial_write(struct ieee80211_hw *hw,
 				 enum radio_path rfpath, u32 offset, u32 data);
 void _rtl92c_phy_fw_rf_serial_write(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c
index e452275d8789..e20f2bec45c4 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c
@@ -24,9 +24,6 @@ static void rtl92c_init_aspm_vars(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
-	/*close ASPM for AMD defaultly */
-	rtlpci->const_amdpci_aspm = 0;
-
 	/*
 	 * ASPM PS mode.
 	 * 0 - Disable ASPM,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/phy.c
index a8d9fe269f31..0b8cb7e61fd8 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/phy.c
@@ -32,7 +32,7 @@ u32 rtl92cu_phy_query_rf_reg(struct ieee80211_hw *hw,
 		original_value = _rtl92c_phy_fw_rf_serial_read(hw,
 							       rfpath, regaddr);
 	}
-	bitshift = _rtl92c_phy_calculate_bit_shift(bitmask);
+	bitshift = calculate_bit_shift(bitmask);
 	readback_value = (original_value & bitmask) >> bitshift;
 	rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE,
 		"regaddr(%#x), rfpath(%#x), bitmask(%#x), original_value(%#x)\n",
@@ -56,7 +56,7 @@ void rtl92cu_phy_set_rf_reg(struct ieee80211_hw *hw,
 			original_value = _rtl92c_phy_rf_serial_read(hw,
 								    rfpath,
 								    regaddr);
-			bitshift = _rtl92c_phy_calculate_bit_shift(bitmask);
+			bitshift = calculate_bit_shift(bitmask);
 			data =
 			    ((original_value & (~bitmask)) |
 			     (data << bitshift));
@@ -67,7 +67,7 @@ void rtl92cu_phy_set_rf_reg(struct ieee80211_hw *hw,
 			original_value = _rtl92c_phy_fw_rf_serial_read(hw,
 								       rfpath,
 								       regaddr);
-			bitshift = _rtl92c_phy_calculate_bit_shift(bitmask);
+			bitshift = calculate_bit_shift(bitmask);
 			data =
 			    ((original_value & (~bitmask)) |
 			     (data << bitshift));
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c
index d18c092b6142..d835a27429f0 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c
@@ -169,13 +169,6 @@ static const u8 channel_all[59] = {
 	157, 159, 161, 163, 165
 };
 
-static u32 _rtl92d_phy_calculate_bit_shift(u32 bitmask)
-{
-	u32 i = ffs(bitmask);
-
-	return i ? i - 1 : 32;
-}
-
 u32 rtl92d_phy_query_bb_reg(struct ieee80211_hw *hw, u32 regaddr, u32 bitmask)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
@@ -198,7 +191,7 @@ u32 rtl92d_phy_query_bb_reg(struct ieee80211_hw *hw, u32 regaddr, u32 bitmask)
 	} else {
 		originalvalue = rtl_read_dword(rtlpriv, regaddr);
 	}
-	bitshift = _rtl92d_phy_calculate_bit_shift(bitmask);
+	bitshift = calculate_bit_shift(bitmask);
 	returnvalue = (originalvalue & bitmask) >> bitshift;
 	rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE,
 		"BBR MASK=0x%x Addr[0x%x]=0x%x\n",
@@ -230,7 +223,7 @@ void rtl92d_phy_set_bb_reg(struct ieee80211_hw *hw,
 					dbi_direct);
 		else
 			originalvalue = rtl_read_dword(rtlpriv, regaddr);
-		bitshift = _rtl92d_phy_calculate_bit_shift(bitmask);
+		bitshift = calculate_bit_shift(bitmask);
 		data = ((originalvalue & (~bitmask)) | (data << bitshift));
 	}
 	if (rtlhal->during_mac1init_radioa || rtlhal->during_mac0init_radiob)
@@ -317,7 +310,7 @@ u32 rtl92d_phy_query_rf_reg(struct ieee80211_hw *hw,
 		regaddr, rfpath, bitmask);
 	spin_lock(&rtlpriv->locks.rf_lock);
 	original_value = _rtl92d_phy_rf_serial_read(hw, rfpath, regaddr);
-	bitshift = _rtl92d_phy_calculate_bit_shift(bitmask);
+	bitshift = calculate_bit_shift(bitmask);
 	readback_value = (original_value & bitmask) >> bitshift;
 	spin_unlock(&rtlpriv->locks.rf_lock);
 	rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE,
@@ -343,7 +336,7 @@ void rtl92d_phy_set_rf_reg(struct ieee80211_hw *hw, enum radio_path rfpath,
 		if (bitmask != RFREG_OFFSET_MASK) {
 			original_value = _rtl92d_phy_rf_serial_read(hw,
 				rfpath, regaddr);
-			bitshift = _rtl92d_phy_calculate_bit_shift(bitmask);
+			bitshift = calculate_bit_shift(bitmask);
 			data = ((original_value & (~bitmask)) |
 				(data << bitshift));
 		}
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c
index 11f319c97124..afd685ed460a 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c
@@ -21,9 +21,6 @@ static void rtl92d_init_aspm_vars(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
-	/*close ASPM for AMD defaultly */
-	rtlpci->const_amdpci_aspm = 0;
-
 	/*
 	 * ASPM PS mode.
 	 * 0 - Disable ASPM,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/dm.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/dm.c
index 5a828a934fe9..17486e3f322c 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/dm.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/dm.c
@@ -432,10 +432,8 @@ static void rtl92ee_dm_check_rssi_monitor(struct ieee80211_hw *hw)
 static void rtl92ee_dm_init_primary_cca_check(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
-	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
 	struct dynamic_primary_cca *primarycca = &rtlpriv->primarycca;
 
-	rtlhal->rts_en = 0;
 	primarycca->dup_rts_flag = 0;
 	primarycca->intf_flag = 0;
 	primarycca->intf_type = 0;
@@ -562,7 +560,7 @@ static void rtl92ee_dm_write_dynamic_cca(struct ieee80211_hw *hw,
 	primarycca->mf_state = cur_mf_state;
 }
 
-static void rtl92ee_dm_dynamic_primary_cca_ckeck(struct ieee80211_hw *hw)
+static void rtl92ee_dm_dynamic_primary_cca_check(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct false_alarm_statistics *falsealm_cnt = &rtlpriv->falsealm_cnt;
@@ -615,13 +613,11 @@ static void rtl92ee_dm_dynamic_primary_cca_ckeck(struct ieee80211_hw *hw)
 				rtl92ee_dm_write_dynamic_cca(hw, cur_mf_state);
 				primarycca->pricca_flag = 1;
 				primarycca->dup_rts_flag = 1;
-				rtlpriv->rtlhal.rts_en = 1;
 			} else {
 				primarycca->intf_type = 0;
 				primarycca->intf_flag = 0;
 				cur_mf_state = MF_USC_LSC;
 				rtl92ee_dm_write_dynamic_cca(hw, cur_mf_state);
-				rtlpriv->rtlhal.rts_en = 0;
 				primarycca->dup_rts_flag = 0;
 			}
 		} else if (sec_ch_offset == 1) {
@@ -642,13 +638,11 @@ static void rtl92ee_dm_dynamic_primary_cca_ckeck(struct ieee80211_hw *hw)
 				rtl92ee_dm_write_dynamic_cca(hw, cur_mf_state);
 				primarycca->pricca_flag = 1;
 				primarycca->dup_rts_flag = 1;
-				rtlpriv->rtlhal.rts_en = 1;
 			} else {
 				primarycca->intf_type = 0;
 				primarycca->intf_flag = 0;
 				cur_mf_state = MF_USC_LSC;
 				rtl92ee_dm_write_dynamic_cca(hw, cur_mf_state);
-				rtlpriv->rtlhal.rts_en = 0;
 				primarycca->dup_rts_flag = 0;
 			}
 		}
@@ -660,7 +654,6 @@ static void rtl92ee_dm_dynamic_primary_cca_ckeck(struct ieee80211_hw *hw)
 			cur_mf_state = MF_USC_LSC;
 			/* default */
 			rtl92ee_dm_write_dynamic_cca(hw, cur_mf_state);
-			rtlpriv->rtlhal.rts_en = 0;
 			primarycca->dup_rts_flag = 0;
 			primarycca->intf_type = 0;
 			primarycca->intf_flag = 0;
@@ -1090,7 +1083,7 @@ void rtl92ee_dm_watchdog(struct ieee80211_hw *hw)
 		rtl92ee_dm_refresh_rate_adaptive_mask(hw);
 		rtl92ee_dm_check_edca_turbo(hw);
 		rtl92ee_dm_dynamic_atc_switch(hw);
-		rtl92ee_dm_dynamic_primary_cca_ckeck(hw);
+		rtl92ee_dm_dynamic_primary_cca_check(hw);
 	}
 	spin_unlock(&rtlpriv->locks.rf_ps_lock);
 }
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c
index ebb7abd0c9ad..d4da5cdc8414 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c
@@ -1320,7 +1320,6 @@ int rtl92ee_hw_init(struct ieee80211_hw *hw)
 		err = 1;
 		return err;
 	}
-	rtlhal->rx_tag = 0;
 	rtl_write_word(rtlpriv, REG_PCIE_CTRL_REG, 0x8000);
 	err = rtl92ee_download_fw(hw, false);
 	if (err) {
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.c
index cc0bcaf13e96..73ef602bfb01 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.c
@@ -16,7 +16,6 @@ static u32 _rtl92ee_phy_rf_serial_read(struct ieee80211_hw *hw,
 static void _rtl92ee_phy_rf_serial_write(struct ieee80211_hw *hw,
 					 enum radio_path rfpath, u32 offset,
 					 u32 data);
-static u32 _rtl92ee_phy_calculate_bit_shift(u32 bitmask);
 static bool _rtl92ee_phy_bb8192ee_config_parafile(struct ieee80211_hw *hw);
 static bool _rtl92ee_phy_config_mac_with_headerfile(struct ieee80211_hw *hw);
 static bool phy_config_bb_with_hdr_file(struct ieee80211_hw *hw,
@@ -46,7 +45,7 @@ u32 rtl92ee_phy_query_bb_reg(struct ieee80211_hw *hw, u32 regaddr, u32 bitmask)
 	rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE,
 		"regaddr(%#x), bitmask(%#x)\n", regaddr, bitmask);
 	originalvalue = rtl_read_dword(rtlpriv, regaddr);
-	bitshift = _rtl92ee_phy_calculate_bit_shift(bitmask);
+	bitshift = calculate_bit_shift(bitmask);
 	returnvalue = (originalvalue & bitmask) >> bitshift;
 
 	rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE,
@@ -68,7 +67,7 @@ void rtl92ee_phy_set_bb_reg(struct ieee80211_hw *hw, u32 regaddr,
 
 	if (bitmask != MASKDWORD) {
 		originalvalue = rtl_read_dword(rtlpriv, regaddr);
-		bitshift = _rtl92ee_phy_calculate_bit_shift(bitmask);
+		bitshift = calculate_bit_shift(bitmask);
 		data = ((originalvalue & (~bitmask)) | (data << bitshift));
 	}
 
@@ -92,7 +91,7 @@ u32 rtl92ee_phy_query_rf_reg(struct ieee80211_hw *hw,
 	spin_lock(&rtlpriv->locks.rf_lock);
 
 	original_value = _rtl92ee_phy_rf_serial_read(hw , rfpath, regaddr);
-	bitshift = _rtl92ee_phy_calculate_bit_shift(bitmask);
+	bitshift = calculate_bit_shift(bitmask);
 	readback_value = (original_value & bitmask) >> bitshift;
 
 	spin_unlock(&rtlpriv->locks.rf_lock);
@@ -119,7 +118,7 @@ void rtl92ee_phy_set_rf_reg(struct ieee80211_hw *hw,
 
 	if (bitmask != RFREG_OFFSET_MASK) {
 		original_value = _rtl92ee_phy_rf_serial_read(hw, rfpath, addr);
-		bitshift = _rtl92ee_phy_calculate_bit_shift(bitmask);
+		bitshift = calculate_bit_shift(bitmask);
 		data = (original_value & (~bitmask)) | (data << bitshift);
 	}
 
@@ -201,13 +200,6 @@ static void _rtl92ee_phy_rf_serial_write(struct ieee80211_hw *hw,
 		pphyreg->rf3wire_offset, data_and_addr);
 }
 
-static u32 _rtl92ee_phy_calculate_bit_shift(u32 bitmask)
-{
-	u32 i = ffs(bitmask);
-
-	return i ? i - 1 : 32;
-}
-
 bool rtl92ee_phy_mac_config(struct ieee80211_hw *hw)
 {
 	return _rtl92ee_phy_config_mac_with_headerfile(hw);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c
index 011ce82efeff..7bde20fdbeab 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c
@@ -24,9 +24,6 @@ static void rtl92ee_init_aspm_vars(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
-	/*close ASPM for AMD defaultly */
-	rtlpci->const_amdpci_aspm = 0;
-
 	/**
 	 * ASPM PS mode.
 	 * 0 - Disable ASPM,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/phy.c
index 09591a0b5a81..d9ef7e1da1db 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/phy.c
@@ -14,13 +14,6 @@
 #include "hw.h"
 #include "table.h"
 
-static u32 _rtl92s_phy_calculate_bit_shift(u32 bitmask)
-{
-	u32 i = ffs(bitmask);
-
-	return i ? i - 1 : 32;
-}
-
 u32 rtl92s_phy_query_bb_reg(struct ieee80211_hw *hw, u32 regaddr, u32 bitmask)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
@@ -30,7 +23,7 @@ u32 rtl92s_phy_query_bb_reg(struct ieee80211_hw *hw, u32 regaddr, u32 bitmask)
 		regaddr, bitmask);
 
 	originalvalue = rtl_read_dword(rtlpriv, regaddr);
-	bitshift = _rtl92s_phy_calculate_bit_shift(bitmask);
+	bitshift = calculate_bit_shift(bitmask);
 	returnvalue = (originalvalue & bitmask) >> bitshift;
 
 	rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE, "BBR MASK=0x%x Addr[0x%x]=0x%x\n",
@@ -52,7 +45,7 @@ void rtl92s_phy_set_bb_reg(struct ieee80211_hw *hw, u32 regaddr, u32 bitmask,
 
 	if (bitmask != MASKDWORD) {
 		originalvalue = rtl_read_dword(rtlpriv, regaddr);
-		bitshift = _rtl92s_phy_calculate_bit_shift(bitmask);
+		bitshift = calculate_bit_shift(bitmask);
 		data = ((originalvalue & (~bitmask)) | (data << bitshift));
 	}
 
@@ -157,7 +150,7 @@ u32 rtl92s_phy_query_rf_reg(struct ieee80211_hw *hw, enum radio_path rfpath,
 
 	original_value = _rtl92s_phy_rf_serial_read(hw, rfpath, regaddr);
 
-	bitshift = _rtl92s_phy_calculate_bit_shift(bitmask);
+	bitshift = calculate_bit_shift(bitmask);
 	readback_value = (original_value & bitmask) >> bitshift;
 
 	spin_unlock(&rtlpriv->locks.rf_lock);
@@ -188,7 +181,7 @@ void rtl92s_phy_set_rf_reg(struct ieee80211_hw *hw, enum radio_path rfpath,
 	if (bitmask != RFREG_OFFSET_MASK) {
 		original_value = _rtl92s_phy_rf_serial_read(hw, rfpath,
 							    regaddr);
-		bitshift = _rtl92s_phy_calculate_bit_shift(bitmask);
+		bitshift = calculate_bit_shift(bitmask);
 		data = ((original_value & (~bitmask)) | (data << bitshift));
 	}
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c
index 30bce381c3bb..675bdd32feb1 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c
@@ -21,9 +21,6 @@ static void rtl92s_init_aspm_vars(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
-	/*close ASPM for AMD defaultly */
-	rtlpci->const_amdpci_aspm = 0;
-
 	/* ASPM PS mode.
 	 * 0 - Disable ASPM,
 	 * 1 - Enable ASPM without Clock Req,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/phy.c
index fe9b407dc2af..71e29b103da5 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/phy.c
@@ -49,7 +49,7 @@ u32 rtl8723e_phy_query_rf_reg(struct ieee80211_hw *hw,
 							    rfpath, regaddr);
 	}
 
-	bitshift = rtl8723_phy_calculate_bit_shift(bitmask);
+	bitshift = calculate_bit_shift(bitmask);
 	readback_value = (original_value & bitmask) >> bitshift;
 
 	spin_unlock(&rtlpriv->locks.rf_lock);
@@ -80,7 +80,7 @@ void rtl8723e_phy_set_rf_reg(struct ieee80211_hw *hw,
 			original_value = rtl8723_phy_rf_serial_read(hw,
 								    rfpath,
 								    regaddr);
-			bitshift = rtl8723_phy_calculate_bit_shift(bitmask);
+			bitshift = calculate_bit_shift(bitmask);
 			data =
 			    ((original_value & (~bitmask)) |
 			     (data << bitshift));
@@ -89,7 +89,7 @@ void rtl8723e_phy_set_rf_reg(struct ieee80211_hw *hw,
 		rtl8723_phy_rf_serial_write(hw, rfpath, regaddr, data);
 	} else {
 		if (bitmask != RFREG_OFFSET_MASK) {
-			bitshift = rtl8723_phy_calculate_bit_shift(bitmask);
+			bitshift = calculate_bit_shift(bitmask);
 			data =
 			    ((original_value & (~bitmask)) |
 			     (data << bitshift));
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c
index c821436a1991..dd7505e2f22c 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c
@@ -26,9 +26,6 @@ static void rtl8723e_init_aspm_vars(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
-	/*close ASPM for AMD defaultly */
-	rtlpci->const_amdpci_aspm = 0;
-
 	/**
 	 * ASPM PS mode.
 	 * 0 - Disable ASPM,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/phy.c
index 2b9313cb93db..094cb36153f5 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/phy.c
@@ -41,7 +41,7 @@ u32 rtl8723be_phy_query_rf_reg(struct ieee80211_hw *hw, enum radio_path rfpath,
 	spin_lock(&rtlpriv->locks.rf_lock);
 
 	original_value = rtl8723_phy_rf_serial_read(hw, rfpath, regaddr);
-	bitshift = rtl8723_phy_calculate_bit_shift(bitmask);
+	bitshift = calculate_bit_shift(bitmask);
 	readback_value = (original_value & bitmask) >> bitshift;
 
 	spin_unlock(&rtlpriv->locks.rf_lock);
@@ -68,7 +68,7 @@ void rtl8723be_phy_set_rf_reg(struct ieee80211_hw *hw, enum radio_path path,
 	if (bitmask != RFREG_OFFSET_MASK) {
 			original_value = rtl8723_phy_rf_serial_read(hw, path,
 								    regaddr);
-			bitshift = rtl8723_phy_calculate_bit_shift(bitmask);
+			bitshift = calculate_bit_shift(bitmask);
 			data = ((original_value & (~bitmask)) |
 				(data << bitshift));
 		}
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c
index 43b611d5288d..162c34f0e9b7 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c
@@ -26,9 +26,6 @@ static void rtl8723be_init_aspm_vars(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
-	/*close ASPM for AMD defaultly */
-	rtlpci->const_amdpci_aspm = 0;
-
 	/* ASPM PS mode.
 	 * 0 - Disable ASPM,
 	 * 1 - Enable ASPM without Clock Req,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723com/phy_common.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723com/phy_common.c
index 47b6c1aa36b0..d97c88ebce75 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723com/phy_common.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723com/phy_common.c
@@ -17,7 +17,7 @@ u32 rtl8723_phy_query_bb_reg(struct ieee80211_hw *hw,
 	rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE,
 		"regaddr(%#x), bitmask(%#x)\n", regaddr, bitmask);
 	originalvalue = rtl_read_dword(rtlpriv, regaddr);
-	bitshift = rtl8723_phy_calculate_bit_shift(bitmask);
+	bitshift = calculate_bit_shift(bitmask);
 	returnvalue = (originalvalue & bitmask) >> bitshift;
 
 	rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE,
@@ -39,7 +39,7 @@ void rtl8723_phy_set_bb_reg(struct ieee80211_hw *hw, u32 regaddr,
 
 	if (bitmask != MASKDWORD) {
 		originalvalue = rtl_read_dword(rtlpriv, regaddr);
-		bitshift = rtl8723_phy_calculate_bit_shift(bitmask);
+		bitshift = calculate_bit_shift(bitmask);
 		data = ((originalvalue & (~bitmask)) | (data << bitshift));
 	}
 
@@ -51,14 +51,6 @@ void rtl8723_phy_set_bb_reg(struct ieee80211_hw *hw, u32 regaddr,
 }
 EXPORT_SYMBOL_GPL(rtl8723_phy_set_bb_reg);
 
-u32 rtl8723_phy_calculate_bit_shift(u32 bitmask)
-{
-	u32 i = ffs(bitmask);
-
-	return i ? i - 1 : 32;
-}
-EXPORT_SYMBOL_GPL(rtl8723_phy_calculate_bit_shift);
-
 u32 rtl8723_phy_rf_serial_read(struct ieee80211_hw *hw,
 			       enum radio_path rfpath, u32 offset)
 {
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723com/phy_common.h b/drivers/net/wireless/realtek/rtlwifi/rtl8723com/phy_common.h
index edf1c52f0ee2..af85c3287507 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723com/phy_common.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723com/phy_common.h
@@ -27,7 +27,6 @@ u32 rtl8723_phy_query_bb_reg(struct ieee80211_hw *hw,
 			     u32 regaddr, u32 bitmask);
 void rtl8723_phy_set_bb_reg(struct ieee80211_hw *hw, u32 regaddr,
 			      u32 bitmask, u32 data);
-u32 rtl8723_phy_calculate_bit_shift(u32 bitmask);
 u32 rtl8723_phy_rf_serial_read(struct ieee80211_hw *hw,
 			       enum radio_path rfpath, u32 offset);
 void rtl8723_phy_rf_serial_write(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
index 1633328bc3d1..f4b232f038a9 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
@@ -2270,67 +2270,27 @@ static void _rtl8821ae_clear_pci_pme_status(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
-	u16 cap_hdr;
-	u8 cap_pointer;
-	u8 cap_id = 0xff;
-	u8 pmcs_reg;
-	u8 cnt = 0;
+	struct pci_dev *pdev = rtlpci->pdev;
+	u16 pmcs_reg;
+	u8 pm_cap;
 
-	/* Get the Capability pointer first,
-	 * the Capability Pointer is located at
-	 * offset 0x34 from the Function Header */
-
-	pci_read_config_byte(rtlpci->pdev, 0x34, &cap_pointer);
-	rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
-		"PCI configuration 0x34 = 0x%2x\n", cap_pointer);
-
-	do {
-		pci_read_config_word(rtlpci->pdev, cap_pointer, &cap_hdr);
-		cap_id = cap_hdr & 0xFF;
-
-		rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
-			"in pci configuration, cap_pointer%x = %x\n",
-			cap_pointer, cap_id);
-
-		if (cap_id == 0x01) {
-			break;
-		} else {
-			/* point to next Capability */
-			cap_pointer = (cap_hdr >> 8) & 0xFF;
-			/* 0: end of pci capability, 0xff: invalid value */
-			if (cap_pointer == 0x00 || cap_pointer == 0xff) {
-				cap_id = 0xff;
-				break;
-			}
-		}
-	} while (cnt++ < 200);
-
-	if (cap_id == 0x01) {
-		/* Get the PM CSR (Control/Status Register),
-		 * The PME_Status is located at PM Capatibility offset 5, bit 7
-		 */
-		pci_read_config_byte(rtlpci->pdev, cap_pointer + 5, &pmcs_reg);
-
-		if (pmcs_reg & BIT(7)) {
-			/* PME event occured, clear the PM_Status by write 1 */
-			pmcs_reg = pmcs_reg | BIT(7);
-
-			pci_write_config_byte(rtlpci->pdev, cap_pointer + 5,
-					      pmcs_reg);
-			/* Read it back to check */
-			pci_read_config_byte(rtlpci->pdev, cap_pointer + 5,
-					     &pmcs_reg);
-			rtl_dbg(rtlpriv, COMP_INIT, DBG_DMESG,
-				"Clear PME status 0x%2x to 0x%2x\n",
-				cap_pointer + 5, pmcs_reg);
-		} else {
-			rtl_dbg(rtlpriv, COMP_INIT, DBG_DMESG,
-				"PME status(0x%2x) = 0x%2x\n",
-				cap_pointer + 5, pmcs_reg);
-		}
-	} else {
+	pm_cap = pci_find_capability(pdev, PCI_CAP_ID_PM);
+	if (!pm_cap) {
 		rtl_dbg(rtlpriv, COMP_INIT, DBG_WARNING,
 			"Cannot find PME Capability\n");
+		return;
+	}
+
+	pci_read_config_word(pdev, pm_cap + PCI_PM_CTRL, &pmcs_reg);
+	if (pmcs_reg & PCI_PM_CTRL_PME_STATUS) {
+		/* Clear PME_Status with write */
+		pci_write_config_word(pdev, pm_cap + PCI_PM_CTRL, pmcs_reg);
+		pci_read_config_word(pdev, pm_cap + PCI_PM_CTRL, &pmcs_reg);
+		rtl_dbg(rtlpriv, COMP_INIT, DBG_DMESG,
+			"Cleared PME status, PMCS reg = 0x%4x\n", pmcs_reg);
+	} else {
+		rtl_dbg(rtlpriv, COMP_INIT, DBG_DMESG,
+			"PMCS reg = 0x%4x\n", pmcs_reg);
 	}
 }
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c
index 5323ead30db0..1be51ea3f3c8 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c
@@ -27,12 +27,6 @@ static u32 _rtl8821ae_phy_rf_serial_read(struct ieee80211_hw *hw,
 static void _rtl8821ae_phy_rf_serial_write(struct ieee80211_hw *hw,
 					   enum radio_path rfpath, u32 offset,
 					   u32 data);
-static u32 _rtl8821ae_phy_calculate_bit_shift(u32 bitmask)
-{
-	u32 i = ffs(bitmask);
-
-	return i ? i - 1 : 32;
-}
 static bool _rtl8821ae_phy_bb8821a_config_parafile(struct ieee80211_hw *hw);
 /*static bool _rtl8812ae_phy_config_mac_with_headerfile(struct ieee80211_hw *hw);*/
 static bool _rtl8821ae_phy_config_mac_with_headerfile(struct ieee80211_hw *hw);
@@ -105,7 +99,7 @@ u32 rtl8821ae_phy_query_bb_reg(struct ieee80211_hw *hw, u32 regaddr,
 		"regaddr(%#x), bitmask(%#x)\n",
 		regaddr, bitmask);
 	originalvalue = rtl_read_dword(rtlpriv, regaddr);
-	bitshift = _rtl8821ae_phy_calculate_bit_shift(bitmask);
+	bitshift = calculate_bit_shift(bitmask);
 	returnvalue = (originalvalue & bitmask) >> bitshift;
 
 	rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE,
@@ -126,7 +120,7 @@ void rtl8821ae_phy_set_bb_reg(struct ieee80211_hw *hw,
 
 	if (bitmask != MASKDWORD) {
 		originalvalue = rtl_read_dword(rtlpriv, regaddr);
-		bitshift = _rtl8821ae_phy_calculate_bit_shift(bitmask);
+		bitshift = calculate_bit_shift(bitmask);
 		data = ((originalvalue & (~bitmask)) |
 			((data << bitshift) & bitmask));
 	}
@@ -152,7 +146,7 @@ u32 rtl8821ae_phy_query_rf_reg(struct ieee80211_hw *hw,
 	spin_lock(&rtlpriv->locks.rf_lock);
 
 	original_value = _rtl8821ae_phy_rf_serial_read(hw, rfpath, regaddr);
-	bitshift = _rtl8821ae_phy_calculate_bit_shift(bitmask);
+	bitshift = calculate_bit_shift(bitmask);
 	readback_value = (original_value & bitmask) >> bitshift;
 
 	spin_unlock(&rtlpriv->locks.rf_lock);
@@ -180,7 +174,7 @@ void rtl8821ae_phy_set_rf_reg(struct ieee80211_hw *hw,
 	if (bitmask != RFREG_OFFSET_MASK) {
 		original_value =
 		   _rtl8821ae_phy_rf_serial_read(hw, rfpath, regaddr);
-		bitshift = _rtl8821ae_phy_calculate_bit_shift(bitmask);
+		bitshift = calculate_bit_shift(bitmask);
 		data = ((original_value & (~bitmask)) | (data << bitshift));
 	}
 
@@ -2038,15 +2032,9 @@ static bool _rtl8821ae_phy_config_bb_with_pgheaderfile(struct ieee80211_hw *hw,
 			 /*don't need the hw_body*/
 			if (!_rtl8821ae_check_condition(hw, v1)) {
 				i += 2; /* skip the pair of expression*/
-				v1 = array[i];
 				v2 = array[i+1];
-				v3 = array[i+2];
-				while (v2 != 0xDEAD) {
+				while (v2 != 0xDEAD)
 					i += 3;
-					v1 = array[i];
-					v2 = array[i+1];
-					v3 = array[i+2];
-				}
 			}
 		}
 	}
@@ -3543,7 +3531,6 @@ u8 rtl8821ae_phy_sw_chnl(struct ieee80211_hw *hw)
 	struct rtl_phy *rtlphy = &rtlpriv->phy;
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
 	u32 timeout = 1000, timecount = 0;
-	u8 channel = rtlphy->current_channel;
 
 	if (rtlphy->sw_chnl_inprogress)
 		return 0;
@@ -3566,8 +3553,6 @@ u8 rtl8821ae_phy_sw_chnl(struct ieee80211_hw *hw)
 		rtl8821ae_phy_switch_wirelessband(hw, BAND_ON_2_4G);
 
 	rtlphy->sw_chnl_inprogress = true;
-	if (channel == 0)
-		channel = 1;
 
 	rtl_dbg(rtlpriv, COMP_SCAN, DBG_TRACE,
 		"switch to channel%d, band type is %d\n",
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c
index 0bca542e103f..7b911695db33 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c
@@ -23,9 +23,6 @@ static void rtl8821ae_init_aspm_vars(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
-	/*close ASPM for AMD defaultly */
-	rtlpci->const_amdpci_aspm = 0;
-
 	/**
 	 * ASPM PS mode.
 	 * 0 - Disable ASPM,
diff --git a/drivers/net/wireless/realtek/rtlwifi/wifi.h b/drivers/net/wireless/realtek/rtlwifi/wifi.h
index 31a481f43a07..d87cd2252eac 100644
--- a/drivers/net/wireless/realtek/rtlwifi/wifi.h
+++ b/drivers/net/wireless/realtek/rtlwifi/wifi.h
@@ -1316,7 +1316,6 @@ struct rtl_phy {
 	u8 sw_chnl_stage;
 	u8 sw_chnl_step;
 	u8 current_channel;
-	u8 h2c_box_num;
 	u8 set_io_inprogress;
 	u8 lck_inprogress;
 
@@ -1329,9 +1328,6 @@ struct rtl_phy {
 	s32 reg_ebc;
 	s32 reg_ec4;
 	s32 reg_ecc;
-	u8 rfpienable;
-	u8 reserve_0;
-	u16 reserve_1;
 	u32 reg_c04, reg_c08, reg_874;
 	u32 adda_backup[16];
 	u32 iqk_mac_backup[IQK_MAC_REG_NUM];
@@ -1345,7 +1341,6 @@ struct rtl_phy {
 	struct iqk_matrix_regs iqk_matrix[IQK_MATRIX_SETTINGS_NUM];
 
 	bool rfpi_enable;
-	bool iqk_in_progress;
 
 	u8 pwrgroup_cnt;
 	u8 cck_high_power;
@@ -1383,7 +1378,6 @@ struct rtl_phy {
 			 [MAX_RF_PATH_NUM];
 
 	u32 rfreg_chnlval[2];
-	bool apk_done;
 	u32 reg_rf3c[2];	/* pathA / pathB  */
 
 	u32 backup_rf_0x1a;/*92ee*/
@@ -1395,7 +1389,6 @@ struct rtl_phy {
 	struct phy_parameters hwparam_tables[MAX_TAB];
 	u16 rf_pathmap;
 
-	u8 hw_rof_enable; /*Enable GPIO[9] as WL RF HW PDn source*/
 	enum rt_polarity_ctl polarity_ctl;
 };
 
@@ -1610,7 +1603,6 @@ struct rtl_hal {
 	bool up_first_time;
 	bool first_init;
 	bool being_init_adapter;
-	bool bbrf_ready;
 	bool mac_func_enable;
 	bool pre_edcca_enable;
 	struct bt_coexist_8723 hal_coex_8723;
@@ -1623,9 +1615,7 @@ struct rtl_hal {
 	u8 state;		/*stop 0, start 1 */
 	u8 board_type;
 	u8 package_type;
-	u8 external_pa;
 
-	u8 pa_mode;
 	u8 pa_type_2g;
 	u8 pa_type_5g;
 	u8 lna_type_2g;
@@ -1691,14 +1681,9 @@ struct rtl_hal {
 	bool master_of_dmsp;
 	bool slave_of_dmsp;
 
-	u16 rx_tag;/*for 92ee*/
-	u8 rts_en;
-
 	/*for wowlan*/
-	bool wow_enable;
 	bool enter_pnp_sleep;
 	bool wake_from_pnp_sleep;
-	bool wow_enabled;
 	time64_t last_suspend_sec;
 	u32 wowlan_fwsize;
 	u8 *wowlan_firmware;
@@ -2023,8 +2008,6 @@ struct rtl_ps_ctl {
 	u32 cur_ps_level;
 	u32 reg_rfps_level;
 
-	/*just for PCIE ASPM */
-	u8 const_amdpci_aspm;
 	bool pwrdown_mode;
 
 	enum rf_pwrstate inactive_pwrstate;
@@ -3069,4 +3052,11 @@ static inline struct ieee80211_sta *rtl_find_sta(struct ieee80211_hw *hw,
 	return ieee80211_find_sta(mac->vif, mac_addr);
 }
 
+static inline u32 calculate_bit_shift(u32 bitmask)
+{
+	if (WARN_ON_ONCE(!bitmask))
+		return 0;
+
+	return __ffs(bitmask);
+}
 #endif
diff --git a/drivers/net/wireless/realtek/rtw88/debug.c b/drivers/net/wireless/realtek/rtw88/debug.c
index 35bc37a3c469..1b2ad81838be 100644
--- a/drivers/net/wireless/realtek/rtw88/debug.c
+++ b/drivers/net/wireless/realtek/rtw88/debug.c
@@ -1314,8 +1314,8 @@ void rtw_debugfs_init(struct rtw_dev *rtwdev)
 
 #ifdef CONFIG_RTW88_DEBUG
 
-void __rtw_dbg(struct rtw_dev *rtwdev, enum rtw_debug_mask mask,
-	       const char *fmt, ...)
+void rtw_dbg(struct rtw_dev *rtwdev, enum rtw_debug_mask mask,
+	     const char *fmt, ...)
 {
 	struct va_format vaf = {
 		.fmt = fmt,
@@ -1330,6 +1330,6 @@ void __rtw_dbg(struct rtw_dev *rtwdev, enum rtw_debug_mask mask,
 
 	va_end(args);
 }
-EXPORT_SYMBOL(__rtw_dbg);
+EXPORT_SYMBOL(rtw_dbg);
 
 #endif /* CONFIG_RTW88_DEBUG */
diff --git a/drivers/net/wireless/realtek/rtw88/debug.h b/drivers/net/wireless/realtek/rtw88/debug.h
index a03ced11bbe0..f20c0471c82a 100644
--- a/drivers/net/wireless/realtek/rtw88/debug.h
+++ b/drivers/net/wireless/realtek/rtw88/debug.h
@@ -43,10 +43,8 @@ static inline void rtw_debugfs_init(struct rtw_dev *rtwdev) {}
 #ifdef CONFIG_RTW88_DEBUG
 
 __printf(3, 4)
-void __rtw_dbg(struct rtw_dev *rtwdev, enum rtw_debug_mask mask,
-	       const char *fmt, ...);
-
-#define rtw_dbg(rtwdev, a...) __rtw_dbg(rtwdev, ##a)
+void rtw_dbg(struct rtw_dev *rtwdev, enum rtw_debug_mask mask,
+	     const char *fmt, ...);
 
 static inline bool rtw_dbg_is_enabled(struct rtw_dev *rtwdev,
 				      enum rtw_debug_mask mask)
diff --git a/drivers/net/wireless/realtek/rtw88/fw.c b/drivers/net/wireless/realtek/rtw88/fw.c
index acd78311c8c4..3f037ddcecf1 100644
--- a/drivers/net/wireless/realtek/rtw88/fw.c
+++ b/drivers/net/wireless/realtek/rtw88/fw.c
@@ -998,7 +998,7 @@ static u8 rtw_get_rsvd_page_probe_req_location(struct rtw_dev *rtwdev,
 		if (rsvd_pkt->type != RSVD_PROBE_REQ)
 			continue;
 		if ((!ssid && !rsvd_pkt->ssid) ||
-		    rtw_ssid_equal(rsvd_pkt->ssid, ssid))
+		    cfg80211_ssid_eq(rsvd_pkt->ssid, ssid))
 			location = rsvd_pkt->page;
 	}
 
@@ -1015,7 +1015,7 @@ static u16 rtw_get_rsvd_page_probe_req_size(struct rtw_dev *rtwdev,
 		if (rsvd_pkt->type != RSVD_PROBE_REQ)
 			continue;
 		if ((!ssid && !rsvd_pkt->ssid) ||
-		    rtw_ssid_equal(rsvd_pkt->ssid, ssid))
+		    cfg80211_ssid_eq(rsvd_pkt->ssid, ssid))
 			size = rsvd_pkt->probe_req_size;
 	}
 
diff --git a/drivers/net/wireless/realtek/rtw88/mac80211.c b/drivers/net/wireless/realtek/rtw88/mac80211.c
index a99b53d44267..d8d68f16014e 100644
--- a/drivers/net/wireless/realtek/rtw88/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw88/mac80211.c
@@ -280,9 +280,9 @@ static void rtw_ops_configure_filter(struct ieee80211_hw *hw,
 
 	if (changed_flags & FIF_ALLMULTI) {
 		if (*new_flags & FIF_ALLMULTI)
-			rtwdev->hal.rcr |= BIT_AM | BIT_AB;
+			rtwdev->hal.rcr |= BIT_AM;
 		else
-			rtwdev->hal.rcr &= ~(BIT_AM | BIT_AB);
+			rtwdev->hal.rcr &= ~(BIT_AM);
 	}
 	if (changed_flags & FIF_FCSFAIL) {
 		if (*new_flags & FIF_FCSFAIL)
diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
index 4a33d2e47f33..6d22628129d0 100644
--- a/drivers/net/wireless/realtek/rtw88/main.c
+++ b/drivers/net/wireless/realtek/rtw88/main.c
@@ -2008,6 +2008,11 @@ static int rtw_chip_efuse_info_setup(struct rtw_dev *rtwdev)
 	efuse->ext_pa_5g = efuse->pa_type_5g & BIT(0) ? 1 : 0;
 	efuse->ext_lna_2g = efuse->lna_type_5g & BIT(3) ? 1 : 0;
 
+	if (!is_valid_ether_addr(efuse->addr)) {
+		eth_random_addr(efuse->addr);
+		dev_warn(rtwdev->dev, "efuse MAC invalid, using random\n");
+	}
+
 out_disable:
 	rtw_chip_efuse_disable(rtwdev);
 
diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h
index b6bfd4c02e2d..e14d1da43940 100644
--- a/drivers/net/wireless/realtek/rtw88/main.h
+++ b/drivers/net/wireless/realtek/rtw88/main.h
@@ -2090,18 +2090,6 @@ static inline struct ieee80211_vif *rtwvif_to_vif(struct rtw_vif *rtwvif)
 	return container_of(p, struct ieee80211_vif, drv_priv);
 }
 
-static inline bool rtw_ssid_equal(struct cfg80211_ssid *a,
-				  struct cfg80211_ssid *b)
-{
-	if (!a || !b || a->ssid_len != b->ssid_len)
-		return false;
-
-	if (memcmp(a->ssid, b->ssid, a->ssid_len))
-		return false;
-
-	return true;
-}
-
 static inline void rtw_chip_efuse_grant_on(struct rtw_dev *rtwdev)
 {
 	if (rtwdev->chip->ops->efuse_grant)
diff --git a/drivers/net/wireless/realtek/rtw88/sdio.c b/drivers/net/wireless/realtek/rtw88/sdio.c
index 2c1fb2dabd40..0cae5746f540 100644
--- a/drivers/net/wireless/realtek/rtw88/sdio.c
+++ b/drivers/net/wireless/realtek/rtw88/sdio.c
@@ -500,19 +500,40 @@ static u32 rtw_sdio_get_tx_addr(struct rtw_dev *rtwdev, size_t size,
 static int rtw_sdio_read_port(struct rtw_dev *rtwdev, u8 *buf, size_t count)
 {
 	struct rtw_sdio *rtwsdio = (struct rtw_sdio *)rtwdev->priv;
+	struct mmc_host *host = rtwsdio->sdio_func->card->host;
 	bool bus_claim = rtw_sdio_bus_claim_needed(rtwsdio);
 	u32 rxaddr = rtwsdio->rx_addr++;
-	int ret;
+	int ret = 0, err;
+	size_t bytes;
 
 	if (bus_claim)
 		sdio_claim_host(rtwsdio->sdio_func);
 
-	ret = sdio_memcpy_fromio(rtwsdio->sdio_func, buf,
-				 RTW_SDIO_ADDR_RX_RX0FF_GEN(rxaddr), count);
-	if (ret)
-		rtw_warn(rtwdev,
-			 "Failed to read %zu byte(s) from SDIO port 0x%08x",
-			 count, rxaddr);
+	while (count > 0) {
+		bytes = min_t(size_t, host->max_req_size, count);
+
+		err = sdio_memcpy_fromio(rtwsdio->sdio_func, buf,
+					 RTW_SDIO_ADDR_RX_RX0FF_GEN(rxaddr),
+					 bytes);
+		if (err) {
+			rtw_warn(rtwdev,
+				 "Failed to read %zu byte(s) from SDIO port 0x%08x: %d",
+				 bytes, rxaddr, err);
+
+			 /* Signal to the caller that reading did not work and
+			  * that the data in the buffer is short/corrupted.
+			  */
+			ret = err;
+
+			/* Don't stop here - instead drain the remaining data
+			 * from the card's buffer, else the card will return
+			 * corrupt data for the next rtw_sdio_read_port() call.
+			 */
+		}
+
+		count -= bytes;
+		buf += bytes;
+	}
 
 	if (bus_claim)
 		sdio_release_host(rtwsdio->sdio_func);
diff --git a/drivers/net/wireless/realtek/rtw88/tx.c b/drivers/net/wireless/realtek/rtw88/tx.c
index f63900b6621d..c02ac673be32 100644
--- a/drivers/net/wireless/realtek/rtw88/tx.c
+++ b/drivers/net/wireless/realtek/rtw88/tx.c
@@ -656,9 +656,8 @@ void __rtw_tx_work(struct rtw_dev *rtwdev)
 	list_for_each_entry_safe(rtwtxq, tmp, &rtwdev->txqs, list) {
 		struct ieee80211_txq *txq = rtwtxq_to_txq(rtwtxq);
 		unsigned long frame_cnt;
-		unsigned long byte_cnt;
 
-		ieee80211_txq_get_depth(txq, &frame_cnt, &byte_cnt);
+		ieee80211_txq_get_depth(txq, &frame_cnt, NULL);
 		rtw_txq_push(rtwdev, rtwtxq, frame_cnt);
 
 		list_del_init(&rtwtxq->list);
diff --git a/drivers/net/wireless/realtek/rtw89/acpi.c b/drivers/net/wireless/realtek/rtw89/acpi.c
index 8aaf83a2a6b4..2e7326a8e3e4 100644
--- a/drivers/net/wireless/realtek/rtw89/acpi.c
+++ b/drivers/net/wireless/realtek/rtw89/acpi.c
@@ -12,27 +12,74 @@ static const guid_t rtw89_guid = GUID_INIT(0xD2A8C3E8, 0x4B69, 0x4F00,
 					   0x82, 0xBD, 0xFE, 0x86,
 					   0x07, 0x80, 0x3A, 0xA7);
 
-static int rtw89_acpi_dsm_get(struct rtw89_dev *rtwdev, union acpi_object *obj,
-			      u8 *value)
+static
+int rtw89_acpi_dsm_get_value(struct rtw89_dev *rtwdev, union acpi_object *obj,
+			     u8 *value)
 {
-	switch (obj->type) {
-	case ACPI_TYPE_INTEGER:
-		*value = (u8)obj->integer.value;
-		break;
-	case ACPI_TYPE_BUFFER:
-		*value = obj->buffer.pointer[0];
-		break;
-	default:
-		rtw89_debug(rtwdev, RTW89_DBG_UNEXP,
-			    "acpi dsm return unhandled type: %d\n", obj->type);
+	if (obj->type != ACPI_TYPE_INTEGER) {
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI,
+			    "acpi: expect integer but type: %d\n", obj->type);
 		return -EINVAL;
 	}
 
+	*value = (u8)obj->integer.value;
+	return 0;
+}
+
+static bool chk_acpi_policy_6ghz_sig(const struct rtw89_acpi_policy_6ghz *p)
+{
+	return p->signature[0] == 0x00 &&
+	       p->signature[1] == 0xE0 &&
+	       p->signature[2] == 0x4C;
+}
+
+static
+int rtw89_acpi_dsm_get_policy_6ghz(struct rtw89_dev *rtwdev,
+				   union acpi_object *obj,
+				   struct rtw89_acpi_policy_6ghz **policy_6ghz)
+{
+	const struct rtw89_acpi_policy_6ghz *ptr;
+	u32 expect_len;
+	u32 len;
+
+	if (obj->type != ACPI_TYPE_BUFFER) {
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI,
+			    "acpi: expect buffer but type: %d\n", obj->type);
+		return -EINVAL;
+	}
+
+	len = obj->buffer.length;
+	if (len < sizeof(*ptr)) {
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI, "%s: invalid buffer length: %u\n",
+			    __func__, len);
+		return -EINVAL;
+	}
+
+	ptr = (typeof(ptr))obj->buffer.pointer;
+	if (!chk_acpi_policy_6ghz_sig(ptr)) {
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI, "%s: bad signature\n", __func__);
+		return -EINVAL;
+	}
+
+	expect_len = struct_size(ptr, country_list, ptr->country_count);
+	if (len < expect_len) {
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI, "%s: expect %u but length: %u\n",
+			    __func__, expect_len, len);
+		return -EINVAL;
+	}
+
+	*policy_6ghz = kmemdup(ptr, expect_len, GFP_KERNEL);
+	if (!*policy_6ghz)
+		return -ENOMEM;
+
+	rtw89_hex_dump(rtwdev, RTW89_DBG_ACPI, "policy_6ghz: ", *policy_6ghz,
+		       expect_len);
 	return 0;
 }
 
 int rtw89_acpi_evaluate_dsm(struct rtw89_dev *rtwdev,
-			    enum rtw89_acpi_dsm_func func, u8 *value)
+			    enum rtw89_acpi_dsm_func func,
+			    struct rtw89_acpi_dsm_result *res)
 {
 	union acpi_object *obj;
 	int ret;
@@ -40,12 +87,16 @@ int rtw89_acpi_evaluate_dsm(struct rtw89_dev *rtwdev,
 	obj = acpi_evaluate_dsm(ACPI_HANDLE(rtwdev->dev), &rtw89_guid,
 				0, func, NULL);
 	if (!obj) {
-		rtw89_debug(rtwdev, RTW89_DBG_UNEXP,
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI,
 			    "acpi dsm fail to evaluate func: %d\n", func);
 		return -ENOENT;
 	}
 
-	ret = rtw89_acpi_dsm_get(rtwdev, obj, value);
+	if (func == RTW89_ACPI_DSM_FUNC_6G_BP)
+		ret = rtw89_acpi_dsm_get_policy_6ghz(rtwdev, obj,
+						     &res->u.policy_6ghz);
+	else
+		ret = rtw89_acpi_dsm_get_value(rtwdev, obj, &res->u.value);
 
 	ACPI_FREE(obj);
 	return ret;
diff --git a/drivers/net/wireless/realtek/rtw89/acpi.h b/drivers/net/wireless/realtek/rtw89/acpi.h
index ed74d8ceb733..fe85b40cf076 100644
--- a/drivers/net/wireless/realtek/rtw89/acpi.h
+++ b/drivers/net/wireless/realtek/rtw89/acpi.h
@@ -15,7 +15,37 @@ enum rtw89_acpi_dsm_func {
 	RTW89_ACPI_DSM_FUNC_59G_EN = 6,
 };
 
+enum rtw89_acpi_policy_mode {
+	RTW89_ACPI_POLICY_BLOCK = 0,
+	RTW89_ACPI_POLICY_ALLOW = 1,
+};
+
+struct rtw89_acpi_country_code {
+	/* below are allowed:
+	 * * ISO alpha2 country code
+	 * * EU for countries in Europe
+	 */
+	char alpha2[2];
+} __packed;
+
+struct rtw89_acpi_policy_6ghz {
+	u8 signature[3];
+	u8 rsvd;
+	u8 policy_mode;
+	u8 country_count;
+	struct rtw89_acpi_country_code country_list[] __counted_by(country_count);
+} __packed;
+
+struct rtw89_acpi_dsm_result {
+	union {
+		u8 value;
+		/* caller needs to free it after using */
+		struct rtw89_acpi_policy_6ghz *policy_6ghz;
+	} u;
+};
+
 int rtw89_acpi_evaluate_dsm(struct rtw89_dev *rtwdev,
-			    enum rtw89_acpi_dsm_func func, u8 *value);
+			    enum rtw89_acpi_dsm_func func,
+			    struct rtw89_acpi_dsm_result *res);
 
 #endif
diff --git a/drivers/net/wireless/realtek/rtw89/cam.c b/drivers/net/wireless/realtek/rtw89/cam.c
index f5301c2bbf13..914c94988b2f 100644
--- a/drivers/net/wireless/realtek/rtw89/cam.c
+++ b/drivers/net/wireless/realtek/rtw89/cam.c
@@ -488,6 +488,20 @@ static int rtw89_cam_get_avail_addr_cam(struct rtw89_dev *rtwdev,
 	return 0;
 }
 
+static u8 rtw89_get_addr_cam_entry_size(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+
+	switch (chip->chip_id) {
+	case RTL8852A:
+	case RTL8852B:
+	case RTL8851B:
+		return ADDR_CAM_ENT_SIZE;
+	default:
+		return ADDR_CAM_ENT_SHORT_SIZE;
+	}
+}
+
 int rtw89_cam_init_addr_cam(struct rtw89_dev *rtwdev,
 			    struct rtw89_addr_cam_entry *addr_cam,
 			    const struct rtw89_bssid_cam_entry *bssid_cam)
@@ -509,7 +523,7 @@ int rtw89_cam_init_addr_cam(struct rtw89_dev *rtwdev,
 	}
 
 	addr_cam->addr_cam_idx = addr_cam_idx;
-	addr_cam->len = ADDR_CAM_ENT_SIZE;
+	addr_cam->len = rtw89_get_addr_cam_entry_size(rtwdev);
 	addr_cam->offset = 0;
 	addr_cam->valid = true;
 	addr_cam->addr_mask = 0;
diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index bdcc172639e4..f37afb4cbb63 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -6,6 +6,7 @@
 #include "debug.h"
 #include "fw.h"
 #include "mac.h"
+#include "phy.h"
 #include "ps.h"
 #include "reg.h"
 
@@ -122,7 +123,8 @@ static const u32 cxtbl[] = {
 	0xea55556a, /* 21 */
 	0xaafafafa, /* 22 */
 	0xfafaaafa, /* 23 */
-	0xfafffaff  /* 24 */
+	0xfafffaff, /* 24 */
+	0xea6a5a5a, /* 25 */
 };
 
 static const struct rtw89_btc_ver rtw89_btc_ver_defs[] = {
@@ -131,7 +133,7 @@ static const struct rtw89_btc_ver rtw89_btc_ver_defs[] = {
 	 .fcxbtcrpt = 105, .fcxtdma = 3,    .fcxslots = 1, .fcxcysta = 5,
 	 .fcxstep = 3,   .fcxnullsta = 2, .fcxmreg = 2,  .fcxgpiodbg = 1,
 	 .fcxbtver = 1,  .fcxbtscan = 2,  .fcxbtafh = 2, .fcxbtdevinfo = 1,
-	 .fwlrole = 1,   .frptmap = 3,    .fcxctrl = 1,
+	 .fwlrole = 2,   .frptmap = 3,    .fcxctrl = 1,
 	 .info_buf = 1800, .max_role_num = 6,
 	},
 	{RTL8852C, RTW89_FW_VER_CODE(0, 27, 57, 0),
@@ -159,7 +161,7 @@ static const struct rtw89_btc_ver rtw89_btc_ver_defs[] = {
 	 .fcxbtcrpt = 105, .fcxtdma = 3,  .fcxslots = 1, .fcxcysta = 5,
 	 .fcxstep = 3,   .fcxnullsta = 2, .fcxmreg = 2,  .fcxgpiodbg = 1,
 	 .fcxbtver = 1,  .fcxbtscan = 2,  .fcxbtafh = 2, .fcxbtdevinfo = 1,
-	 .fwlrole = 1,   .frptmap = 3,    .fcxctrl = 1,
+	 .fwlrole = 2,   .frptmap = 3,    .fcxctrl = 1,
 	 .info_buf = 1800, .max_role_num = 6,
 	},
 	{RTL8852B, RTW89_FW_VER_CODE(0, 29, 14, 0),
@@ -246,6 +248,11 @@ struct rtw89_btc_btf_set_mon_reg {
 	struct rtw89_btc_fbtc_mreg regs[] __counted_by(reg_num);
 } __packed;
 
+struct _wl_rinfo_now {
+	u8 link_mode;
+	u32 dbcc_2g_phy: 2;
+};
+
 enum btc_btf_set_cx_policy {
 	CXPOLICY_TDMA = 0x0,
 	CXPOLICY_SLOT = 0x1,
@@ -262,6 +269,8 @@ enum btc_b2w_scoreboard {
 	BTC_BSCB_RFK_RUN = BIT(5),
 	BTC_BSCB_RFK_REQ = BIT(6),
 	BTC_BSCB_LPS = BIT(7),
+	BTC_BSCB_BT_LNAB0 = BIT(8),
+	BTC_BSCB_BT_LNAB1 = BIT(10),
 	BTC_BSCB_WLRFK = BIT(11),
 	BTC_BSCB_BT_HILNA = BIT(13),
 	BTC_BSCB_BT_CONNECT = BIT(16),
@@ -405,11 +414,14 @@ enum btc_cx_poicy_type {
 	/* TDMA Fix slot-8: W1:B1 = user-define */
 	BTC_CXP_FIX_TDW1B1 = (BTC_CXP_FIX << 8) | 8,
 
-	/* TDMA Fix slot-9: W1:B1 = 40:20 */
-	BTC_CXP_FIX_TD4020 = (BTC_CXP_FIX << 8) | 9,
-
 	/* TDMA Fix slot-9: W1:B1 = 40:10 */
-	BTC_CXP_FIX_TD4010ISO = (BTC_CXP_FIX << 8) | 10,
+	BTC_CXP_FIX_TD4010ISO = (BTC_CXP_FIX << 8) | 9,
+
+	/* TDMA Fix slot-10: W1:B1 = 40:10 */
+	BTC_CXP_FIX_TD4010ISO_DL = (BTC_CXP_FIX << 8) | 10,
+
+	/* TDMA Fix slot-11: W1:B1 = 40:10 */
+	BTC_CXP_FIX_TD4010ISO_UL = (BTC_CXP_FIX << 8) | 11,
 
 	/* PS-TDMA Fix slot-0: W1:B1 = 30:30 */
 	BTC_CXP_PFIX_TD3030 = (BTC_CXP_PFIX << 8) | 0,
@@ -710,7 +722,8 @@ static void _reset_btc_var(struct rtw89_dev *rtwdev, u8 type)
 
 	if (type & BTC_RESET_CX)
 		memset(cx, 0, sizeof(*cx));
-	else if (type & BTC_RESET_BTINFO) /* only for BT enable */
+
+	if (type & BTC_RESET_BTINFO) /* only for BT enable */
 		memset(bt, 0, sizeof(*bt));
 
 	if (type & BTC_RESET_CTRL) {
@@ -739,12 +752,115 @@ static void _reset_btc_var(struct rtw89_dev *rtwdev, u8 type)
 		btc->dm.coex_info_map = BTC_COEX_INFO_ALL;
 		btc->dm.wl_tx_limit.tx_time = BTC_MAX_TX_TIME_DEF;
 		btc->dm.wl_tx_limit.tx_retry = BTC_MAX_TX_RETRY_DEF;
+		btc->dm.wl_pre_agc_rb = BTC_PREAGC_NOTFOUND;
+		btc->dm.wl_btg_rx_rb = BTC_BTGCTRL_BB_GNT_NOTFOUND;
 	}
 
 	if (type & BTC_RESET_MDINFO)
 		memset(&btc->mdinfo, 0, sizeof(btc->mdinfo));
 }
 
+static u8 _search_reg_index(struct rtw89_dev *rtwdev, u8 mreg_num, u16 reg_type, u32 target)
+{
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	u8 i;
+
+	for (i = 0; i < mreg_num; i++)
+		if (le16_to_cpu(chip->mon_reg[i].type) == reg_type &&
+		    le32_to_cpu(chip->mon_reg[i].offset) == target) {
+			return i;
+	}
+	return BTC_REG_NOTFOUND;
+}
+
+static void _get_reg_status(struct rtw89_dev *rtwdev, u8 type, u8 *val)
+{
+	struct rtw89_btc *btc = &rtwdev->btc;
+	const struct rtw89_btc_ver *ver = btc->ver;
+	struct rtw89_btc_module *md = &btc->mdinfo;
+	union rtw89_btc_fbtc_mreg_val *pmreg;
+	u32 pre_agc_addr = R_BTC_BB_PRE_AGC_S1;
+	u32 reg_val;
+	u8 idx;
+
+	if (md->ant.btg_pos == RF_PATH_A)
+		pre_agc_addr = R_BTC_BB_PRE_AGC_S0;
+
+	switch (type) {
+	case BTC_CSTATUS_TXDIV_POS:
+		if (md->switch_type == BTC_SWITCH_INTERNAL)
+			*val = BTC_ANT_DIV_MAIN;
+		break;
+	case BTC_CSTATUS_RXDIV_POS:
+		if (md->switch_type == BTC_SWITCH_INTERNAL)
+			*val = BTC_ANT_DIV_MAIN;
+		break;
+	case BTC_CSTATUS_BB_GNT_MUX:
+		reg_val = rtw89_phy_read32(rtwdev, R_BTC_BB_BTG_RX);
+		*val = !(reg_val & B_BTC_BB_GNT_MUX);
+		break;
+	case BTC_CSTATUS_BB_GNT_MUX_MON:
+		if (!btc->fwinfo.rpt_fbtc_mregval.cinfo.valid)
+			return;
+
+		pmreg = &btc->fwinfo.rpt_fbtc_mregval.finfo;
+		if (ver->fcxmreg == 1) {
+			idx = _search_reg_index(rtwdev, pmreg->v1.reg_num,
+						REG_BB, R_BTC_BB_BTG_RX);
+			if (idx == BTC_REG_NOTFOUND) {
+				*val = BTC_BTGCTRL_BB_GNT_NOTFOUND;
+			} else {
+				reg_val = le32_to_cpu(pmreg->v1.mreg_val[idx]);
+				*val = !(reg_val & B_BTC_BB_GNT_MUX);
+			}
+		} else if (ver->fcxmreg == 2) {
+			idx = _search_reg_index(rtwdev, pmreg->v2.reg_num,
+						REG_BB, R_BTC_BB_BTG_RX);
+			if (idx == BTC_REG_NOTFOUND) {
+				*val = BTC_BTGCTRL_BB_GNT_NOTFOUND;
+			} else {
+				reg_val = le32_to_cpu(pmreg->v2.mreg_val[idx]);
+				*val = !(reg_val & B_BTC_BB_GNT_MUX);
+			}
+		}
+		break;
+	case BTC_CSTATUS_BB_PRE_AGC:
+		reg_val = rtw89_phy_read32(rtwdev, pre_agc_addr);
+		reg_val &= B_BTC_BB_PRE_AGC_MASK;
+		*val = (reg_val == B_BTC_BB_PRE_AGC_VAL);
+		break;
+	case BTC_CSTATUS_BB_PRE_AGC_MON:
+		if (!btc->fwinfo.rpt_fbtc_mregval.cinfo.valid)
+			return;
+
+		pmreg = &btc->fwinfo.rpt_fbtc_mregval.finfo;
+		if (ver->fcxmreg == 1) {
+			idx = _search_reg_index(rtwdev, pmreg->v1.reg_num,
+						REG_BB, pre_agc_addr);
+			if (idx == BTC_REG_NOTFOUND) {
+				*val = BTC_PREAGC_NOTFOUND;
+			} else {
+				reg_val = le32_to_cpu(pmreg->v1.mreg_val[idx]) &
+					  B_BTC_BB_PRE_AGC_MASK;
+				*val = (reg_val == B_BTC_BB_PRE_AGC_VAL);
+			}
+		} else if (ver->fcxmreg == 2) {
+			idx = _search_reg_index(rtwdev, pmreg->v2.reg_num,
+						REG_BB, pre_agc_addr);
+			if (idx == BTC_REG_NOTFOUND) {
+				*val = BTC_PREAGC_NOTFOUND;
+			} else {
+				reg_val = le32_to_cpu(pmreg->v2.mreg_val[idx]) &
+					  B_BTC_BB_PRE_AGC_MASK;
+				*val = (reg_val == B_BTC_BB_PRE_AGC_VAL);
+			}
+		}
+		break;
+	default:
+		break;
+	}
+}
+
 #define BTC_RPT_HDR_SIZE 3
 #define BTC_CHK_WLSLOT_DRIFT_MAX 15
 #define BTC_CHK_BTSLOT_DRIFT_MAX 15
@@ -1003,7 +1119,7 @@ static u32 _chk_btc_report(struct rtw89_dev *rtwdev,
 	u16 wl_slot_set = 0, wl_slot_real = 0;
 	u32 trace_step = btc->ctrl.trace_step, rpt_len = 0, diff_t = 0;
 	u32 cnt_leak_slot, bt_slot_real, bt_slot_set, cnt_rx_imr;
-	u8 i;
+	u8 i, val = 0;
 
 	rtw89_debug(rtwdev, RTW89_DBG_BTC,
 		    "[BTC], %s(): index:%d\n",
@@ -1508,6 +1624,19 @@ static u32 _chk_btc_report(struct rtw89_dev *rtwdev,
 			goto err;
 		}
 		break;
+	case BTC_RPT_TYPE_MREG:
+		_get_reg_status(rtwdev, BTC_CSTATUS_BB_GNT_MUX_MON, &val);
+		if (dm->wl_btg_rx == BTC_BTGCTRL_BB_GNT_FWCTRL)
+			dm->wl_btg_rx_rb = BTC_BTGCTRL_BB_GNT_FWCTRL;
+		else
+			dm->wl_btg_rx_rb = val;
+
+		_get_reg_status(rtwdev, BTC_CSTATUS_BB_PRE_AGC_MON, &val);
+		if (dm->wl_pre_agc == BTC_PREAGC_BB_FWCTRL)
+			dm->wl_pre_agc_rb = BTC_PREAGC_BB_FWCTRL;
+		else
+			dm->wl_pre_agc_rb = val;
+		break;
 	case BTC_RPT_TYPE_BT_VER:
 	case BTC_RPT_TYPE_BT_SCAN:
 	case BTC_RPT_TYPE_BT_AFH:
@@ -1576,13 +1705,13 @@ static void _append_tdma(struct rtw89_dev *rtwdev)
 	if (ver->fcxtdma == 1) {
 		v = (struct rtw89_btc_fbtc_tdma *)&tlv->val[0];
 		tlv->len = sizeof(*v);
-		memcpy(v, &dm->tdma, sizeof(*v));
+		*v = dm->tdma;
 		btc->policy_len += BTC_TLV_HDR_LEN + sizeof(*v);
 	} else {
 		tlv->len = sizeof(*v3);
 		v3 = (struct rtw89_btc_fbtc_tdma_v3 *)&tlv->val[0];
 		v3->fver = ver->fcxtdma;
-		memcpy(&v3->tdma, &dm->tdma, sizeof(v3->tdma));
+		v3->tdma = dm->tdma;
 		btc->policy_len += BTC_TLV_HDR_LEN + sizeof(*v3);
 	}
 
@@ -2155,8 +2284,9 @@ static void _set_bt_rx_gain(struct rtw89_dev *rtwdev, u8 level)
 	struct rtw89_btc *btc = &rtwdev->btc;
 	struct rtw89_btc_bt_info *bt = &btc->cx.bt;
 
-	if (bt->rf_para.rx_gain_freerun == level ||
-	    level > BTC_BT_RX_NORMAL_LVL)
+	if ((bt->rf_para.rx_gain_freerun == level ||
+	     level > BTC_BT_RX_NORMAL_LVL) &&
+	    (!rtwdev->chip->scbd || bt->lna_constrain == level))
 		return;
 
 	bt->rf_para.rx_gain_freerun = level;
@@ -2171,32 +2301,59 @@ static void _set_bt_rx_gain(struct rtw89_dev *rtwdev, u8 level)
 	else
 		_write_scbd(rtwdev, BTC_WSCB_RXGAIN, true);
 
-	_send_fw_cmd(rtwdev, BTFC_SET, SET_BT_LNA_CONSTRAIN, &level, 1);
+	_send_fw_cmd(rtwdev, BTFC_SET, SET_BT_LNA_CONSTRAIN, &level, sizeof(level));
 }
 
 static void _set_rf_trx_para(struct rtw89_dev *rtwdev)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	struct rtw89_btc *btc = &rtwdev->btc;
+	const struct rtw89_btc_ver *ver = btc->ver;
 	struct rtw89_btc_dm *dm = &btc->dm;
 	struct rtw89_btc_wl_info *wl = &btc->cx.wl;
 	struct rtw89_btc_bt_info *bt = &btc->cx.bt;
 	struct rtw89_btc_bt_link_info *b = &bt->link_info;
+	struct rtw89_btc_wl_smap *wl_smap = &wl->status.map;
 	struct rtw89_btc_rf_trx_para para;
 	u32 wl_stb_chg = 0;
-	u8 level_id = 0;
+	u8 level_id = 0, link_mode = 0, i, dbcc_2g_phy = 0;
 
-	if (!dm->freerun) {
-		/* fix LNA2 = level-5 for BT ACI issue at BTG */
+	if (ver->fwlrole == 0) {
+		link_mode = wl->role_info.link_mode;
+		for (i = 0; i < RTW89_PHY_MAX; i++) {
+			if (wl->dbcc_info.real_band[i] == RTW89_BAND_2G)
+				dbcc_2g_phy = i;
+		}
+	} else if (ver->fwlrole == 1) {
+		link_mode = wl->role_info_v1.link_mode;
+		dbcc_2g_phy = wl->role_info_v1.dbcc_2g_phy;
+	} else if (ver->fwlrole == 2) {
+		link_mode = wl->role_info_v2.link_mode;
+		dbcc_2g_phy = wl->role_info_v2.dbcc_2g_phy;
+	}
+
+	/* decide trx_para_level */
+	if (btc->mdinfo.ant.type == BTC_ANT_SHARED) {
+		/* fix LNA2 + TIA gain not change by GNT_BT */
 		if ((btc->dm.wl_btg_rx && b->profile_cnt.now != 0) ||
 		    dm->bt_only == 1)
-			dm->trx_para_level = 1;
+			dm->trx_para_level = 1; /* for better BT ACI issue */
 		else
 			dm->trx_para_level = 0;
+	} else { /* non-shared antenna  */
+		dm->trx_para_level = 5;
+		/* modify trx_para if WK 2.4G-STA-DL + bt link */
+		if (b->profile_cnt.now != 0 &&
+		    link_mode == BTC_WLINK_2G_STA &&
+		    wl->status.map.traffic_dir & BIT(RTW89_TFC_UL)) { /* uplink */
+			if (wl->rssi_level == 4 && bt->rssi_level > 2)
+				dm->trx_para_level = 6;
+			else if (wl->rssi_level == 3 && bt->rssi_level > 3)
+				dm->trx_para_level = 7;
+		}
 	}
 
-	level_id = (u8)dm->trx_para_level;
-
+	level_id = dm->trx_para_level;
 	if (level_id >= chip->rf_para_dlink_num ||
 	    level_id >= chip->rf_para_ulink_num) {
 		rtw89_debug(rtwdev, RTW89_DBG_BTC,
@@ -2210,25 +2367,26 @@ static void _set_rf_trx_para(struct rtw89_dev *rtwdev)
 	else
 		para = chip->rf_para_dlink[level_id];
 
-	if (para.wl_tx_power != RTW89_BTC_WL_DEF_TX_PWR)
-		rtw89_debug(rtwdev, RTW89_DBG_BTC,
-			    "[BTC], %s(): wl_tx_power=%d\n",
-			    __func__, para.wl_tx_power);
-	_set_wl_tx_power(rtwdev, para.wl_tx_power);
-	_set_wl_rx_gain(rtwdev, para.wl_rx_gain);
-	_set_bt_tx_power(rtwdev, para.bt_tx_power);
-	_set_bt_rx_gain(rtwdev, para.bt_rx_gain);
-
-	if (bt->enable.now == 0 || wl->status.map.rf_off == 1 ||
-	    wl->status.map.lps == BTC_LPS_RF_OFF)
+	if (dm->fddt_train) {
+		_set_wl_rx_gain(rtwdev, 1);
+		_write_scbd(rtwdev, BTC_WSCB_RXGAIN, true);
+	} else {
+		_set_wl_tx_power(rtwdev, para.wl_tx_power);
+		_set_wl_rx_gain(rtwdev, para.wl_rx_gain);
+		_set_bt_tx_power(rtwdev, para.bt_tx_power);
+		_set_bt_rx_gain(rtwdev, para.bt_rx_gain);
+	}
+
+	if (!bt->enable.now || dm->wl_only || wl_smap->rf_off ||
+	    wl_smap->lps == BTC_LPS_RF_OFF ||
+	    link_mode == BTC_WLINK_5G ||
+	    link_mode == BTC_WLINK_NOLINK ||
+	    (rtwdev->dbcc_en && dbcc_2g_phy != RTW89_PHY_1))
 		wl_stb_chg = 0;
 	else
 		wl_stb_chg = 1;
 
 	if (wl_stb_chg != dm->wl_stb_chg) {
-		rtw89_debug(rtwdev, RTW89_DBG_BTC,
-			    "[BTC], %s(): wl_stb_chg=%d\n",
-			    __func__, wl_stb_chg);
 		dm->wl_stb_chg = wl_stb_chg;
 		chip->ops->btc_wl_s1_standby(rtwdev, dm->wl_stb_chg);
 	}
@@ -2661,9 +2819,17 @@ void rtw89_btc_set_policy(struct rtw89_dev *rtwdev, u16 policy_type)
 			_slot_set(btc, CXST_W1, 40, tbl_w1, SLOT_ISO);
 			_slot_set(btc, CXST_B1, 10, tbl_b1, SLOT_MIX);
 			break;
-		case BTC_CXP_FIX_TD4020:
-			_slot_set(btc, CXST_W1, 40, cxtbl[1], SLOT_MIX);
-			_slot_set(btc, CXST_B1, 20, tbl_b1, SLOT_MIX);
+		case BTC_CXP_FIX_TD4010ISO:
+			_slot_set(btc, CXST_W1, 40, cxtbl[1], SLOT_ISO);
+			_slot_set(btc, CXST_B1, 10, tbl_b1, SLOT_MIX);
+			break;
+		case BTC_CXP_FIX_TD4010ISO_DL:
+			_slot_set(btc, CXST_W1, 40, cxtbl[25], SLOT_ISO);
+			_slot_set(btc, CXST_B1, 10, cxtbl[25], SLOT_ISO);
+			break;
+		case BTC_CXP_FIX_TD4010ISO_UL:
+			_slot_set(btc, CXST_W1, 40, cxtbl[20], SLOT_ISO);
+			_slot_set(btc, CXST_B1, 10, cxtbl[25], SLOT_MIX);
 			break;
 		case BTC_CXP_FIX_TD7010:
 			_slot_set(btc, CXST_W1, 70, tbl_w1, SLOT_ISO);
@@ -3002,9 +3168,13 @@ void rtw89_btc_set_policy_v1(struct rtw89_dev *rtwdev, u16 policy_type)
 			_slot_set(btc, CXST_W1, 40, cxtbl[1], SLOT_ISO);
 			_slot_set(btc, CXST_B1, 10, tbl_b1, SLOT_MIX);
 			break;
-		case BTC_CXP_FIX_TD4020:
-			_slot_set(btc, CXST_W1, 40, cxtbl[1], SLOT_MIX);
-			_slot_set(btc, CXST_B1, 20, tbl_b1, SLOT_MIX);
+		case BTC_CXP_FIX_TD4010ISO_DL:
+			_slot_set(btc, CXST_W1, 40, cxtbl[25], SLOT_ISO);
+			_slot_set(btc, CXST_B1, 10, cxtbl[25], SLOT_ISO);
+			break;
+		case BTC_CXP_FIX_TD4010ISO_UL:
+			_slot_set(btc, CXST_W1, 40, cxtbl[20], SLOT_ISO);
+			_slot_set(btc, CXST_B1, 10, cxtbl[25], SLOT_MIX);
 			break;
 		case BTC_CXP_FIX_TD7010:
 			_slot_set(btc, CXST_W1, 70, tbl_w1, SLOT_ISO);
@@ -3381,17 +3551,32 @@ static void _action_wl_init(struct rtw89_dev *rtwdev)
 	_set_policy(rtwdev, BTC_CXP_OFF_BT, BTC_ACT_WL_INIT);
 }
 
-static void _action_wl_off(struct rtw89_dev *rtwdev)
+static void _action_wl_off(struct rtw89_dev *rtwdev, u8 mode)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	struct rtw89_btc_wl_info *wl = &btc->cx.wl;
 
 	rtw89_debug(rtwdev, RTW89_DBG_BTC, "[BTC], %s(): !!\n", __func__);
 
-	if (wl->status.map.rf_off || btc->dm.bt_only)
+	if (wl->status.map.rf_off || btc->dm.bt_only) {
 		_set_ant(rtwdev, NM_EXEC, BTC_PHY_ALL, BTC_ANT_WOFF);
+	} else if (wl->status.map.lps == BTC_LPS_RF_ON) {
+		if (wl->role_info.link_mode == BTC_WLINK_5G)
+			_set_ant(rtwdev, FC_EXEC, BTC_PHY_ALL, BTC_ANT_W5G);
+		else
+			_set_ant(rtwdev, FC_EXEC, BTC_PHY_ALL, BTC_ANT_W2G);
+	}
 
-	_set_policy(rtwdev, BTC_CXP_OFF_BT, BTC_ACT_WL_OFF);
+	if (mode == BTC_WLINK_5G) {
+		_set_policy(rtwdev, BTC_CXP_OFF_EQ0, BTC_ACT_WL_OFF);
+	} else if (wl->status.map.lps == BTC_LPS_RF_ON) {
+		if (btc->cx.bt.link_info.a2dp_desc.active)
+			_set_policy(rtwdev, BTC_CXP_OFF_BT, BTC_ACT_WL_OFF);
+		else
+			_set_policy(rtwdev, BTC_CXP_OFF_BWB1, BTC_ACT_WL_OFF);
+	} else {
+		_set_policy(rtwdev, BTC_CXP_OFF_BT, BTC_ACT_WL_OFF);
+	}
 }
 
 static void _action_freerun(struct rtw89_dev *rtwdev)
@@ -3426,31 +3611,25 @@ static void _action_bt_idle(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	struct rtw89_btc_bt_link_info *b = &btc->cx.bt.link_info;
+	struct rtw89_btc_wl_info *wl = &btc->cx.wl;
 
 	_set_ant(rtwdev, NM_EXEC, BTC_PHY_ALL, BTC_ANT_W2G);
 
 	if (btc->mdinfo.ant.type == BTC_ANT_SHARED) { /* shared-antenna */
 		switch (btc->cx.state_map) {
 		case BTC_WBUSY_BNOSCAN: /*wl-busy + bt idle*/
-			if (b->profile_cnt.now > 0)
-				_set_policy(rtwdev, BTC_CXP_FIX_TD4010,
-					    BTC_ACT_BT_IDLE);
+		case BTC_WSCAN_BNOSCAN: /* wl-scan + bt-idle */
+			if (b->status.map.connect)
+				_set_policy(rtwdev, BTC_CXP_FIX_TD4010, BTC_ACT_BT_IDLE);
+			else if (wl->status.map.traffic_dir & BIT(RTW89_TFC_DL))
+				_set_policy(rtwdev, BTC_CXP_FIX_TD4010ISO_DL, BTC_ACT_BT_IDLE);
 			else
-				_set_policy(rtwdev, BTC_CXP_FIX_TD4020,
-					    BTC_ACT_BT_IDLE);
+				_set_policy(rtwdev, BTC_CXP_FIX_TD4010ISO_UL, BTC_ACT_BT_IDLE);
 			break;
 		case BTC_WBUSY_BSCAN: /*wl-busy + bt-inq */
 			_set_policy(rtwdev, BTC_CXP_PFIX_TD5050,
 				    BTC_ACT_BT_IDLE);
 			break;
-		case BTC_WSCAN_BNOSCAN: /* wl-scan + bt-idle */
-			if (b->profile_cnt.now > 0)
-				_set_policy(rtwdev, BTC_CXP_FIX_TD4010,
-					    BTC_ACT_BT_IDLE);
-			else
-				_set_policy(rtwdev, BTC_CXP_FIX_TD4020,
-					    BTC_ACT_BT_IDLE);
-			break;
 		case BTC_WSCAN_BSCAN: /* wl-scan + bt-inq */
 			_set_policy(rtwdev, BTC_CXP_FIX_TD5050,
 				    BTC_ACT_BT_IDLE);
@@ -3617,7 +3796,7 @@ static void _action_bt_pan(struct rtw89_dev *rtwdev)
 		_set_policy(rtwdev, BTC_CXP_FIX_TD3060, BTC_ACT_BT_PAN);
 		break;
 	case BTC_WLINKING: /* wl-connecting + bt-PAN */
-		_set_policy(rtwdev, BTC_CXP_FIX_TD4020, BTC_ACT_BT_PAN);
+		_set_policy(rtwdev, BTC_CXP_FIX_TD4010ISO, BTC_ACT_BT_PAN);
 		break;
 	case BTC_WIDLE: /* wl-idle + bt-pan */
 		_set_policy(rtwdev, BTC_CXP_PFIX_TD2080, BTC_ACT_BT_PAN);
@@ -3798,46 +3977,134 @@ static void _action_wl_rfk(struct rtw89_dev *rtwdev)
 static void _set_btg_ctrl(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
-	const struct rtw89_btc_ver *ver = btc->ver;
 	struct rtw89_btc_wl_info *wl = &btc->cx.wl;
-	struct rtw89_btc_wl_role_info *wl_rinfo = &wl->role_info;
 	struct rtw89_btc_wl_role_info_v1 *wl_rinfo_v1 = &wl->role_info_v1;
 	struct rtw89_btc_wl_role_info_v2 *wl_rinfo_v2 = &wl->role_info_v2;
+	struct rtw89_btc_wl_role_info *wl_rinfo_v0 = &wl->role_info;
 	struct rtw89_btc_wl_dbcc_info *wl_dinfo = &wl->dbcc_info;
-	bool is_btg;
-	u8 mode;
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	const struct rtw89_btc_ver *ver = btc->ver;
+	struct rtw89_btc_bt_info *bt = &btc->cx.bt;
+	struct rtw89_btc_dm *dm = &btc->dm;
+	struct _wl_rinfo_now wl_rinfo;
+	u32 run_reason = btc->dm.run_reason;
+	u32 is_btg;
+	u8 i, val;
 
 	if (btc->ctrl.manual)
 		return;
 
 	if (ver->fwlrole == 0)
-		mode = wl_rinfo->link_mode;
+		wl_rinfo.link_mode = wl_rinfo_v0->link_mode;
 	else if (ver->fwlrole == 1)
-		mode = wl_rinfo_v1->link_mode;
+		wl_rinfo.link_mode = wl_rinfo_v1->link_mode;
 	else if (ver->fwlrole == 2)
-		mode = wl_rinfo_v2->link_mode;
+		wl_rinfo.link_mode = wl_rinfo_v2->link_mode;
 	else
 		return;
 
-	/* notify halbb ignore GNT_BT or not for WL BB Rx-AGC control */
-	if (mode == BTC_WLINK_5G) /* always 0 if 5G */
-		is_btg = false;
-	else if (mode == BTC_WLINK_25G_DBCC &&
-		 wl_dinfo->real_band[RTW89_PHY_1] != RTW89_BAND_2G)
-		is_btg = false;
+	if (rtwdev->dbcc_en) {
+		if (ver->fwlrole == 0) {
+			for (i = 0; i < RTW89_PHY_MAX; i++) {
+				if (wl_dinfo->real_band[i] == RTW89_BAND_2G)
+					wl_rinfo.dbcc_2g_phy = i;
+			}
+		} else if (ver->fwlrole == 1) {
+			wl_rinfo.dbcc_2g_phy = wl_rinfo_v1->dbcc_2g_phy;
+		} else if (ver->fwlrole == 2) {
+			wl_rinfo.dbcc_2g_phy = wl_rinfo_v2->dbcc_2g_phy;
+		} else {
+			return;
+		}
+	}
+
+	if (wl_rinfo.link_mode == BTC_WLINK_25G_MCC)
+		is_btg = BTC_BTGCTRL_BB_GNT_FWCTRL;
+	else if (!(bt->run_patch_code && bt->enable.now))
+		is_btg = BTC_BTGCTRL_DISABLE;
+	else if (wl_rinfo.link_mode == BTC_WLINK_5G)
+		is_btg = BTC_BTGCTRL_DISABLE;
+	else if (dm->freerun)
+		is_btg = BTC_BTGCTRL_DISABLE;
+	else if (rtwdev->dbcc_en && wl_rinfo.dbcc_2g_phy != RTW89_PHY_1)
+		is_btg = BTC_BTGCTRL_DISABLE;
 	else
-		is_btg = true;
+		is_btg = BTC_BTGCTRL_ENABLE;
 
-	if (btc->dm.run_reason != BTC_RSN_NTFY_INIT &&
-	    is_btg == btc->dm.wl_btg_rx)
-		return;
+	if (dm->wl_btg_rx_rb != dm->wl_btg_rx &&
+	    dm->wl_btg_rx_rb != BTC_BTGCTRL_BB_GNT_NOTFOUND) {
+		_get_reg_status(rtwdev, BTC_CSTATUS_BB_GNT_MUX, &val);
+		dm->wl_btg_rx_rb = val;
+	}
 
-	btc->dm.wl_btg_rx = is_btg;
+	if (run_reason == BTC_RSN_NTFY_INIT ||
+	    run_reason == BTC_RSN_NTFY_SWBAND ||
+	    dm->wl_btg_rx_rb != dm->wl_btg_rx ||
+	    is_btg != dm->wl_btg_rx) {
+
+		dm->wl_btg_rx = is_btg;
+
+		if (is_btg > BTC_BTGCTRL_ENABLE)
+			return;
 
-	if (mode == BTC_WLINK_25G_MCC)
+		chip->ops->ctrl_btg_bt_rx(rtwdev, is_btg, RTW89_PHY_0);
+	}
+}
+
+static void _set_wl_preagc_ctrl(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_btc *btc = &rtwdev->btc;
+	struct rtw89_btc_bt_link_info *bt_linfo = &btc->cx.bt.link_info;
+	struct rtw89_btc_wl_info *wl = &btc->cx.wl;
+	struct rtw89_btc_wl_role_info_v2 *wl_rinfo = &wl->role_info_v2;
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	const struct rtw89_btc_ver *ver = btc->ver;
+	struct rtw89_btc_bt_info *bt = &btc->cx.bt;
+	struct rtw89_btc_dm *dm = &btc->dm;
+	u8 is_preagc, val;
+
+	if (btc->ctrl.manual)
 		return;
 
-	rtw89_ctrl_btg_bt_rx(rtwdev, is_btg, RTW89_PHY_0);
+	if (wl_rinfo->link_mode == BTC_WLINK_25G_MCC)
+		is_preagc = BTC_PREAGC_BB_FWCTRL;
+	else if (!(bt->run_patch_code && bt->enable.now))
+		is_preagc = BTC_PREAGC_DISABLE;
+	else if (wl_rinfo->link_mode == BTC_WLINK_5G)
+		is_preagc = BTC_PREAGC_DISABLE;
+	else if (wl_rinfo->link_mode == BTC_WLINK_NOLINK ||
+		 btc->cx.bt.link_info.profile_cnt.now == 0)
+		is_preagc = BTC_PREAGC_DISABLE;
+	else if (dm->tdma_now.type != CXTDMA_OFF &&
+		 !bt_linfo->hfp_desc.exist &&
+		 !bt_linfo->hid_desc.exist &&
+		 dm->fddt_train == BTC_FDDT_DISABLE)
+		is_preagc = BTC_PREAGC_DISABLE;
+	else if (ver->fwlrole == 2 && wl_rinfo->dbcc_en &&
+		 wl_rinfo->dbcc_2g_phy != RTW89_PHY_1)
+		is_preagc = BTC_PREAGC_DISABLE;
+	else if (btc->mdinfo.ant.type == BTC_ANT_SHARED)
+		is_preagc = BTC_PREAGC_DISABLE;
+	else
+		is_preagc = BTC_PREAGC_ENABLE;
+
+	if (dm->wl_pre_agc_rb != dm->wl_pre_agc &&
+	    dm->wl_pre_agc_rb != BTC_PREAGC_NOTFOUND) {
+		_get_reg_status(rtwdev, BTC_CSTATUS_BB_PRE_AGC, &val);
+		dm->wl_pre_agc_rb = val;
+	}
+
+	if ((wl->coex_mode == BTC_MODE_NORMAL &&
+	     (dm->run_reason == BTC_RSN_NTFY_INIT ||
+	      dm->run_reason == BTC_RSN_NTFY_SWBAND ||
+	      dm->wl_pre_agc_rb != dm->wl_pre_agc)) ||
+	    is_preagc != dm->wl_pre_agc) {
+		dm->wl_pre_agc = is_preagc;
+
+		if (is_preagc > BTC_PREAGC_ENABLE)
+			return;
+		chip->ops->ctrl_nbtg_bt_tx(rtwdev, dm->wl_pre_agc, RTW89_PHY_0);
+	}
 }
 
 struct rtw89_txtime_data {
@@ -4024,6 +4291,7 @@ static void _action_common(struct rtw89_dev *rtwdev)
 	struct rtw89_btc_wl_info *wl = &btc->cx.wl;
 
 	_set_btg_ctrl(rtwdev);
+	_set_wl_preagc_ctrl(rtwdev);
 	_set_wl_tx_limit(rtwdev);
 	_set_bt_afh_info(rtwdev);
 	_set_bt_rx_agc(rtwdev);
@@ -5008,8 +5276,7 @@ static void _update_bt_scbd(struct rtw89_dev *rtwdev, bool only_update)
 		return;
 	}
 
-	if (!(val & BTC_BSCB_ON) ||
-	    btc->dm.cnt_dm[BTC_DCNT_BTCNT_HANG] >= BTC_CHK_HANG_MAX)
+	if (!(val & BTC_BSCB_ON))
 		bt->enable.now = 0;
 	else
 		bt->enable.now = 1;
@@ -5035,6 +5302,9 @@ static void _update_bt_scbd(struct rtw89_dev *rtwdev, bool only_update)
 	bt->btg_type = val & BTC_BSCB_BT_S1 ? BTC_BT_BTG : BTC_BT_ALONE;
 	bt->link_info.a2dp_desc.exist = !!(val & BTC_BSCB_A2DP_ACT);
 
+	bt->lna_constrain = !!(val & BTC_BSCB_BT_LNAB0) +
+			    !!(val & BTC_BSCB_BT_LNAB1) * 2 + 4;
+
 	/* if rfk run 1->0 */
 	if (bt->rfk_info.map.run && !(val & BTC_BSCB_RFK_RUN))
 		status_change = true;
@@ -5128,17 +5398,28 @@ void _run_coex(struct rtw89_dev *rtwdev, enum btc_reason_and_action reason)
 	}
 
 	if (wl->status.map.rf_off_pre == wl->status.map.rf_off &&
-	    wl->status.map.lps_pre == wl->status.map.lps &&
-	    (reason == BTC_RSN_NTFY_POWEROFF ||
-	    reason == BTC_RSN_NTFY_RADIO_STATE)) {
-		rtw89_debug(rtwdev, RTW89_DBG_BTC,
-			    "[BTC], %s(): return for WL rf off state no change!!\n",
-			    __func__);
-		return;
+	    wl->status.map.lps_pre == wl->status.map.lps) {
+		if (reason == BTC_RSN_NTFY_POWEROFF ||
+		    reason == BTC_RSN_NTFY_RADIO_STATE) {
+			rtw89_debug(rtwdev, RTW89_DBG_BTC,
+				    "[BTC], %s(): return for WL rf off state no change!!\n",
+				    __func__);
+			return;
+		}
+		if (wl->status.map.rf_off == 1 ||
+		    wl->status.map.lps == BTC_LPS_RF_OFF) {
+			rtw89_debug(rtwdev, RTW89_DBG_BTC,
+				    "[BTC], %s(): return for WL rf off state!!\n",
+				    __func__);
+			return;
+		}
 	}
 
+	dm->freerun = false;
 	dm->cnt_dm[BTC_DCNT_RUN]++;
 	dm->fddt_train = BTC_FDDT_DISABLE;
+	btc->ctrl.igno_bt = false;
+	bt->scan_rx_low_pri = false;
 
 	if (btc->ctrl.always_freerun) {
 		_action_freerun(rtwdev);
@@ -5153,15 +5434,11 @@ void _run_coex(struct rtw89_dev *rtwdev, enum btc_reason_and_action reason)
 	}
 
 	if (wl->status.map.rf_off || wl->status.map.lps || dm->bt_only) {
-		_action_wl_off(rtwdev);
+		_action_wl_off(rtwdev, mode);
 		btc->ctrl.igno_bt = true;
 		goto exit;
 	}
 
-	btc->ctrl.igno_bt = false;
-	dm->freerun = false;
-	bt->scan_rx_low_pri = false;
-
 	if (reason == BTC_RSN_NTFY_INIT) {
 		_action_wl_init(rtwdev);
 		goto exit;
@@ -5186,12 +5463,14 @@ void _run_coex(struct rtw89_dev *rtwdev, enum btc_reason_and_action reason)
 		if (mode == BTC_WLINK_NOLINK || mode == BTC_WLINK_2G_STA ||
 		    mode == BTC_WLINK_5G) {
 			_action_wl_scan(rtwdev);
+			bt->scan_rx_low_pri = false;
 			goto exit;
 		}
 	}
 
 	if (wl->status.map.scan) {
 		_action_wl_scan(rtwdev);
+		bt->scan_rx_low_pri = false;
 		goto exit;
 	}
 
@@ -5308,6 +5587,7 @@ void rtw89_btc_ntfy_init(struct rtw89_dev *rtwdev, u8 mode)
 	rtw89_debug(rtwdev, RTW89_DBG_BTC,
 		    "[BTC], %s(): mode=%d\n", __func__, mode);
 
+	wl->coex_mode = mode;
 	dm->cnt_notify[BTC_NCNT_INIT_COEX]++;
 	dm->wl_only = mode == BTC_MODE_WL ? 1 : 0;
 	dm->bt_only = mode == BTC_MODE_BT ? 1 : 0;
@@ -5352,6 +5632,10 @@ void rtw89_btc_ntfy_scan_start(struct rtw89_dev *rtwdev, u8 phy_idx, u8 band)
 	rtw89_debug(rtwdev, RTW89_DBG_BTC,
 		    "[BTC], %s(): phy_idx=%d, band=%d\n",
 		    __func__, phy_idx, band);
+
+	if (phy_idx >= RTW89_PHY_MAX)
+		return;
+
 	btc->dm.cnt_notify[BTC_NCNT_SCAN_START]++;
 	wl->status.map.scan = true;
 	wl->scan_info.band[phy_idx] = band;
@@ -5396,6 +5680,10 @@ void rtw89_btc_ntfy_switch_band(struct rtw89_dev *rtwdev, u8 phy_idx, u8 band)
 	rtw89_debug(rtwdev, RTW89_DBG_BTC,
 		    "[BTC], %s(): phy_idx=%d, band=%d\n",
 		    __func__, phy_idx, band);
+
+	if (phy_idx >= RTW89_PHY_MAX)
+		return;
+
 	btc->dm.cnt_notify[BTC_NCNT_SWITCH_BAND]++;
 
 	wl->scan_info.band[phy_idx] = band;
@@ -5517,6 +5805,37 @@ void rtw89_btc_ntfy_icmp_packet_work(struct work_struct *work)
 	mutex_unlock(&rtwdev->mutex);
 }
 
+static u8 _update_bt_rssi_level(struct rtw89_dev *rtwdev, u8 rssi)
+{
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	struct rtw89_btc *btc = &rtwdev->btc;
+	struct rtw89_btc_bt_info *bt = &btc->cx.bt;
+	u8 *rssi_st, rssi_th, rssi_level = 0;
+	u8 i;
+
+	/* for rssi locate in which {40, 36, 31, 28}
+	 * if rssi >= 40% (-60dBm) --> rssi_level = 4
+	 * if 36% <= rssi < 40%    --> rssi_level = 3
+	 * if 31% <= rssi < 36%    --> rssi_level = 2
+	 * if 28% <= rssi < 31%    --> rssi_level = 1
+	 * if rssi < 28%           --> rssi_level = 0
+	 */
+
+	/* check if rssi across bt_rssi_thres boundary */
+	for (i = 0; i < BTC_BT_RSSI_THMAX; i++) {
+		rssi_th = chip->bt_rssi_thres[i];
+		rssi_st = &bt->link_info.rssi_state[i];
+
+		*rssi_st = _update_rssi_state(rtwdev, *rssi_st, rssi, rssi_th);
+
+		if (BTC_RSSI_HIGH(*rssi_st)) {
+			rssi_level = BTC_BT_RSSI_THMAX - i;
+			break;
+		}
+	}
+	return rssi_level;
+}
+
 #define BT_PROFILE_PROTOCOL_MASK GENMASK(7, 4)
 
 static void _update_bt_info(struct rtw89_dev *rtwdev, u8 *buf, u32 len)
@@ -5592,7 +5911,8 @@ static void _update_bt_info(struct rtw89_dev *rtwdev, u8 *buf, u32 len)
 	btinfo.val = bt->raw_info[BTC_BTINFO_H0];
 	/* raw val is dBm unit, translate from -100~ 0dBm to 0~100%*/
 	b->rssi = chip->ops->btc_get_bt_rssi(rtwdev, btinfo.hb0.rssi);
-	btc->dm.trx_info.bt_rssi = b->rssi;
+	bt->rssi_level = _update_bt_rssi_level(rtwdev, b->rssi);
+	btc->dm.trx_info.bt_rssi = bt->rssi_level;
 
 	/* parse raw info high-Byte1 */
 	btinfo.val = bt->raw_info[BTC_BTINFO_H1];
@@ -5796,22 +6116,22 @@ void rtw89_btc_ntfy_radio_state(struct rtw89_dev *rtwdev, enum btc_rfctrl rf_sta
 		chip->ops->btc_init_cfg(rtwdev);
 	} else {
 		rtw89_btc_fw_en_rpt(rtwdev, RPT_EN_ALL, false);
-		if (rf_state == BTC_RFCTRL_WL_OFF)
+		if (rf_state == BTC_RFCTRL_FW_CTRL)
+			_write_scbd(rtwdev, BTC_WSCB_ACTIVE, false);
+		else if (rf_state == BTC_RFCTRL_WL_OFF)
 			_write_scbd(rtwdev, BTC_WSCB_ALL, false);
-		else if (rf_state == BTC_RFCTRL_LPS_WL_ON &&
-			 wl->status.map.lps_pre != BTC_LPS_OFF)
+		else
+			_write_scbd(rtwdev, BTC_WSCB_ACTIVE, false);
+
+		if (rf_state == BTC_RFCTRL_LPS_WL_ON &&
+		    wl->status.map.lps_pre != BTC_LPS_OFF)
 			_update_bt_scbd(rtwdev, true);
 	}
 
 	btc->dm.cnt_dm[BTC_DCNT_BTCNT_HANG] = 0;
-	if (wl->status.map.lps_pre == BTC_LPS_OFF &&
-	    wl->status.map.lps_pre != wl->status.map.lps)
-		btc->dm.tdma_instant_excute = 1;
-	else
-		btc->dm.tdma_instant_excute = 0;
+	btc->dm.tdma_instant_excute = 1;
 
 	_run_coex(rtwdev, BTC_RSN_NTFY_RADIO_STATE);
-	btc->dm.tdma_instant_excute = 0;
 	wl->status.map.rf_off_pre = wl->status.map.rf_off;
 	wl->status.map.lps_pre = wl->status.map.lps;
 }
@@ -6050,6 +6370,13 @@ static void rtw89_btc_ntfy_wl_sta_iter(void *data, struct ieee80211_sta *sta)
 	dm->trx_info.tx_tp = link_info_t->tx_throughput;
 	dm->trx_info.rx_tp = link_info_t->rx_throughput;
 
+	/* Trigger coex-run if 0x10980 reg-value is diff with coex setup */
+	if ((dm->wl_btg_rx_rb != dm->wl_btg_rx &&
+	     dm->wl_btg_rx_rb != BTC_BTGCTRL_BB_GNT_NOTFOUND) ||
+	     (dm->wl_pre_agc_rb != dm->wl_pre_agc &&
+	      dm->wl_pre_agc_rb != BTC_PREAGC_NOTFOUND))
+		iter_data->is_sta_change = true;
+
 	if (is_sta_change)
 		iter_data->is_sta_change = true;
 
@@ -6435,8 +6762,9 @@ static void _show_bt_info(struct rtw89_dev *rtwdev, struct seq_file *m)
 		   bt_linfo->pan_desc.active ? "Y" : "N");
 
 	seq_printf(m,
-		   " %-15s : rssi:%ddBm, tx_rate:%dM, %s%s%s",
+		   " %-15s : rssi:%ddBm(lvl:%d), tx_rate:%dM, %s%s%s",
 		   "[link]", bt_linfo->rssi - 100,
+		   bt->rssi_level,
 		   bt_linfo->tx_3m ? 3 : 2,
 		   bt_linfo->status.map.inq_pag ? " inq-page!!" : "",
 		   bt_linfo->status.map.acl_busy ? " acl_busy!!" : "",
@@ -6545,6 +6873,8 @@ static void _show_bt_info(struct rtw89_dev *rtwdev, struct seq_file *m)
 	case BTC_CXP_ ## e | BTC_POLICY_EXT_BIT: return #e
 #define CASE_BTC_SLOT_STR(e) case CXST_ ## e: return #e
 #define CASE_BTC_EVT_STR(e) case CXEVNT_## e: return #e
+#define CASE_BTC_INIT(e) case BTC_MODE_## e: return #e
+#define CASE_BTC_ANTPATH_STR(e) case BTC_ANT_##e: return #e
 
 static const char *steps_to_str(u16 step)
 {
@@ -6625,8 +6955,9 @@ static const char *steps_to_str(u16 step)
 	CASE_BTC_POLICY_STR(FIX_TD3060);
 	CASE_BTC_POLICY_STR(FIX_TD2080);
 	CASE_BTC_POLICY_STR(FIX_TDW1B1);
-	CASE_BTC_POLICY_STR(FIX_TD4020);
 	CASE_BTC_POLICY_STR(FIX_TD4010ISO);
+	CASE_BTC_POLICY_STR(FIX_TD4010ISO_DL);
+	CASE_BTC_POLICY_STR(FIX_TD4010ISO_UL);
 	CASE_BTC_POLICY_STR(PFIX_TD3030);
 	CASE_BTC_POLICY_STR(PFIX_TD5050);
 	CASE_BTC_POLICY_STR(PFIX_TD2030);
@@ -6719,6 +7050,37 @@ static const char *id_to_evt(u32 id)
 	}
 }
 
+static const char *id_to_mode(u8 id)
+{
+	switch (id) {
+	CASE_BTC_INIT(NORMAL);
+	CASE_BTC_INIT(WL);
+	CASE_BTC_INIT(BT);
+	CASE_BTC_INIT(WLOFF);
+	default:
+		return "unknown";
+	}
+}
+
+static const char *id_to_ant(u32 id)
+{
+	switch (id) {
+	CASE_BTC_ANTPATH_STR(WPOWERON);
+	CASE_BTC_ANTPATH_STR(WINIT);
+	CASE_BTC_ANTPATH_STR(WONLY);
+	CASE_BTC_ANTPATH_STR(WOFF);
+	CASE_BTC_ANTPATH_STR(W2G);
+	CASE_BTC_ANTPATH_STR(W5G);
+	CASE_BTC_ANTPATH_STR(W25G);
+	CASE_BTC_ANTPATH_STR(FREERUN);
+	CASE_BTC_ANTPATH_STR(WRFK);
+	CASE_BTC_ANTPATH_STR(BRFK);
+	CASE_BTC_ANTPATH_STR(MAX);
+	default:
+		return "unknown";
+	}
+}
+
 static
 void seq_print_segment(struct seq_file *m, const char *prefix, u16 *data,
 		       u8 len, u8 seg_len, u8 start_idx, u8 ring_len)
@@ -6773,12 +7135,13 @@ static void _show_dm_info(struct rtw89_dev *rtwdev, struct seq_file *m)
 		   (btc->ctrl.manual ? "(Manual)" : "(Auto)"));
 
 	seq_printf(m,
-		   " %-15s : type:%s, reason:%s(), action:%s(), ant_path:%ld, run_cnt:%d\n",
+		   " %-15s : type:%s, reason:%s(), action:%s(), ant_path:%s, init_mode:%s, run_cnt:%d\n",
 		   "[status]",
 		   module->ant.type == BTC_ANT_SHARED ? "shared" : "dedicated",
 		   steps_to_str(dm->run_reason),
 		   steps_to_str(dm->run_action | BTC_ACT_EXT_BIT),
-		   FIELD_GET(GENMASK(7, 0), dm->set_ant_path),
+		   id_to_ant(FIELD_GET(GENMASK(7, 0), dm->set_ant_path)),
+		   id_to_mode(wl->coex_mode),
 		   dm->cnt_dm[BTC_DCNT_RUN]);
 
 	_show_dm_step(rtwdev, m);
@@ -7681,7 +8044,8 @@ static void _get_gnt(struct rtw89_dev *rtwdev, struct rtw89_mac_ax_coex_gnt *gnt
 	struct rtw89_mac_ax_gnt *gnt;
 	u32 val, status;
 
-	if (chip->chip_id == RTL8852A || chip->chip_id == RTL8852B) {
+	if (chip->chip_id == RTL8852A || chip->chip_id == RTL8852B ||
+	    chip->chip_id == RTL8851B) {
 		rtw89_mac_read_lte(rtwdev, R_AX_LTE_SW_CFG_1, &val);
 		rtw89_mac_read_lte(rtwdev, R_AX_GNT_VAL, &status);
 
@@ -7743,27 +8107,25 @@ static void _show_mreg_v1(struct rtw89_dev *rtwdev, struct seq_file *m)
 		   bt->scbd, cx->cnt_bt[BTC_BCNT_SCBDREAD],
 		   cx->cnt_bt[BTC_BCNT_SCBDUPDATE]);
 
-	/* To avoid I/O if WL LPS or power-off  */
-	if (!wl->status.map.lps && !wl->status.map.rf_off) {
-		btc->dm.pta_owner = rtw89_mac_get_ctrl_path(rtwdev);
+	btc->dm.pta_owner = rtw89_mac_get_ctrl_path(rtwdev);
+	_get_gnt(rtwdev, &gnt_cfg);
+
+	gnt = gnt_cfg.band[0];
+	seq_printf(m,
+		   " %-15s : pta_owner:%s, phy-0[gnt_wl:%s-%d/gnt_bt:%s-%d], ",
+		   "[gnt_status]",
+		   chip->chip_id == RTL8852C ? "HW" :
+		   btc->dm.pta_owner == BTC_CTRL_BY_WL ? "WL" : "BT",
+		   gnt.gnt_wl_sw_en ? "SW" : "HW", gnt.gnt_wl,
+		   gnt.gnt_bt_sw_en ? "SW" : "HW", gnt.gnt_bt);
+
+	gnt = gnt_cfg.band[1];
+	seq_printf(m, "phy-1[gnt_wl:%s-%d/gnt_bt:%s-%d]\n",
+		   gnt.gnt_wl_sw_en ? "SW" : "HW",
+		   gnt.gnt_wl,
+		   gnt.gnt_bt_sw_en ? "SW" : "HW",
+		   gnt.gnt_bt);
 
-		_get_gnt(rtwdev, &gnt_cfg);
-		gnt = gnt_cfg.band[0];
-		seq_printf(m,
-			   " %-15s : pta_owner:%s, phy-0[gnt_wl:%s-%d/gnt_bt:%s-%d], ",
-			   "[gnt_status]",
-			   chip->chip_id == RTL8852C ? "HW" :
-			   btc->dm.pta_owner == BTC_CTRL_BY_WL ? "WL" : "BT",
-			   gnt.gnt_wl_sw_en ? "SW" : "HW", gnt.gnt_wl,
-			   gnt.gnt_bt_sw_en ? "SW" : "HW", gnt.gnt_bt);
-
-		gnt = gnt_cfg.band[1];
-		seq_printf(m, "phy-1[gnt_wl:%s-%d/gnt_bt:%s-%d]\n",
-			   gnt.gnt_wl_sw_en ? "SW" : "HW",
-			   gnt.gnt_wl,
-			   gnt.gnt_bt_sw_en ? "SW" : "HW",
-			   gnt.gnt_bt);
-	}
 	pcinfo = &pfwinfo->rpt_fbtc_mregval.cinfo;
 	if (!pcinfo->valid) {
 		rtw89_debug(rtwdev, RTW89_DBG_BTC,
@@ -7847,27 +8209,25 @@ static void _show_mreg_v2(struct rtw89_dev *rtwdev, struct seq_file *m)
 		   bt->scbd, cx->cnt_bt[BTC_BCNT_SCBDREAD],
 		   cx->cnt_bt[BTC_BCNT_SCBDUPDATE]);
 
-	/* To avoid I/O if WL LPS or power-off  */
-	if (!wl->status.map.lps && !wl->status.map.rf_off) {
-		btc->dm.pta_owner = rtw89_mac_get_ctrl_path(rtwdev);
+	btc->dm.pta_owner = rtw89_mac_get_ctrl_path(rtwdev);
+	_get_gnt(rtwdev, &gnt_cfg);
+
+	gnt = gnt_cfg.band[0];
+	seq_printf(m,
+		   " %-15s : pta_owner:%s, phy-0[gnt_wl:%s-%d/gnt_bt:%s-%d], ",
+		   "[gnt_status]",
+		   chip->chip_id == RTL8852C ? "HW" :
+		   btc->dm.pta_owner == BTC_CTRL_BY_WL ? "WL" : "BT",
+		   gnt.gnt_wl_sw_en ? "SW" : "HW", gnt.gnt_wl,
+		   gnt.gnt_bt_sw_en ? "SW" : "HW", gnt.gnt_bt);
+
+	gnt = gnt_cfg.band[1];
+	seq_printf(m, "phy-1[gnt_wl:%s-%d/gnt_bt:%s-%d]\n",
+		   gnt.gnt_wl_sw_en ? "SW" : "HW",
+		   gnt.gnt_wl,
+		   gnt.gnt_bt_sw_en ? "SW" : "HW",
+		   gnt.gnt_bt);
 
-		_get_gnt(rtwdev, &gnt_cfg);
-		gnt = gnt_cfg.band[0];
-		seq_printf(m,
-			   " %-15s : pta_owner:%s, phy-0[gnt_wl:%s-%d/gnt_bt:%s-%d], ",
-			   "[gnt_status]",
-			   chip->chip_id == RTL8852C ? "HW" :
-			   btc->dm.pta_owner == BTC_CTRL_BY_WL ? "WL" : "BT",
-			   gnt.gnt_wl_sw_en ? "SW" : "HW", gnt.gnt_wl,
-			   gnt.gnt_bt_sw_en ? "SW" : "HW", gnt.gnt_bt);
-
-		gnt = gnt_cfg.band[1];
-		seq_printf(m, "phy-1[gnt_wl:%s-%d/gnt_bt:%s-%d]\n",
-			   gnt.gnt_wl_sw_en ? "SW" : "HW",
-			   gnt.gnt_wl,
-			   gnt.gnt_bt_sw_en ? "SW" : "HW",
-			   gnt.gnt_bt);
-	}
 	pcinfo = &pfwinfo->rpt_fbtc_mregval.cinfo;
 	if (!pcinfo->valid) {
 		rtw89_debug(rtwdev, RTW89_DBG_BTC,
diff --git a/drivers/net/wireless/realtek/rtw89/coex.h b/drivers/net/wireless/realtek/rtw89/coex.h
index e76153709793..46e25c6f88a6 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.h
+++ b/drivers/net/wireless/realtek/rtw89/coex.h
@@ -142,6 +142,44 @@ enum btc_lps_state {
 	BTC_LPS_RF_ON = 2
 };
 
+#define R_BTC_BB_BTG_RX 0x980
+#define R_BTC_BB_PRE_AGC_S1 0x476C
+#define R_BTC_BB_PRE_AGC_S0 0x4688
+
+#define B_BTC_BB_GNT_MUX GENMASK(20, 17)
+#define B_BTC_BB_PRE_AGC_MASK GENMASK(31, 24)
+#define B_BTC_BB_PRE_AGC_VAL BIT(31)
+
+#define BTC_REG_NOTFOUND 0xff
+
+enum btc_ant_div_pos {
+	BTC_ANT_DIV_MAIN = 0,
+	BTC_ANT_DIV_AUX = 1,
+};
+
+enum btc_get_reg_status {
+	BTC_CSTATUS_TXDIV_POS = 0,
+	BTC_CSTATUS_RXDIV_POS = 1,
+	BTC_CSTATUS_BB_GNT_MUX = 2,
+	BTC_CSTATUS_BB_GNT_MUX_MON = 3,
+	BTC_CSTATUS_BB_PRE_AGC = 4,
+	BTC_CSTATUS_BB_PRE_AGC_MON = 5,
+};
+
+enum btc_preagc_type {
+	BTC_PREAGC_DISABLE,
+	BTC_PREAGC_ENABLE,
+	BTC_PREAGC_BB_FWCTRL,
+	BTC_PREAGC_NOTFOUND,
+};
+
+enum btc_btgctrl_type {
+	BTC_BTGCTRL_DISABLE,
+	BTC_BTGCTRL_ENABLE,
+	BTC_BTGCTRL_BB_GNT_FWCTRL,
+	BTC_BTGCTRL_BB_GNT_NOTFOUND,
+};
+
 void rtw89_btc_ntfy_poweron(struct rtw89_dev *rtwdev);
 void rtw89_btc_ntfy_poweroff(struct rtw89_dev *rtwdev);
 void rtw89_btc_ntfy_init(struct rtw89_dev *rtwdev, u8 mode);
diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 3d75165e48be..fd527a249996 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -1407,29 +1407,65 @@ static int rtw89_core_rx_process_mac_ppdu(struct rtw89_dev *rtwdev,
 					  struct sk_buff *skb,
 					  struct rtw89_rx_phy_ppdu *phy_ppdu)
 {
+	const struct rtw89_chip_info *chip = rtwdev->chip;
 	const struct rtw89_rxinfo *rxinfo = (const struct rtw89_rxinfo *)skb->data;
+	const struct rtw89_rxinfo_user *user;
+	enum rtw89_chip_gen chip_gen = rtwdev->chip->chip_gen;
+	int rx_cnt_size = RTW89_PPDU_MAC_RX_CNT_SIZE;
 	bool rx_cnt_valid = false;
+	bool invalid = false;
 	u8 plcp_size = 0;
-	u8 usr_num = 0;
 	u8 *phy_sts;
+	u8 usr_num;
+	int i;
+
+	if (chip_gen == RTW89_CHIP_BE) {
+		invalid = le32_get_bits(rxinfo->w0, RTW89_RXINFO_W0_INVALID_V1);
+		rx_cnt_size = RTW89_PPDU_MAC_RX_CNT_SIZE_V1;
+	}
+
+	if (invalid)
+		return -EINVAL;
 
 	rx_cnt_valid = le32_get_bits(rxinfo->w0, RTW89_RXINFO_W0_RX_CNT_VLD);
-	plcp_size = le32_get_bits(rxinfo->w1, RTW89_RXINFO_W1_PLCP_LEN) << 3;
-	usr_num = le32_get_bits(rxinfo->w0, RTW89_RXINFO_W0_USR_NUM);
-	if (usr_num > RTW89_PPDU_MAX_USR) {
-		rtw89_warn(rtwdev, "Invalid user number in mac info\n");
+	if (chip_gen == RTW89_CHIP_BE) {
+		plcp_size = le32_get_bits(rxinfo->w0, RTW89_RXINFO_W0_PLCP_LEN_V1) << 3;
+		usr_num = le32_get_bits(rxinfo->w0, RTW89_RXINFO_W0_USR_NUM_V1);
+	} else {
+		plcp_size = le32_get_bits(rxinfo->w1, RTW89_RXINFO_W1_PLCP_LEN) << 3;
+		usr_num = le32_get_bits(rxinfo->w0, RTW89_RXINFO_W0_USR_NUM);
+	}
+	if (usr_num > chip->ppdu_max_usr) {
+		rtw89_warn(rtwdev, "Invalid user number (%d) in mac info\n",
+			   usr_num);
 		return -EINVAL;
 	}
 
+	/* For WiFi 7 chips, RXWD.mac_id of PPDU status is not set by hardware,
+	 * so update mac_id by rxinfo_user[].mac_id.
+	 */
+	for (i = 0; i < usr_num && chip_gen == RTW89_CHIP_BE; i++) {
+		user = &rxinfo->user[i];
+		if (!le32_get_bits(user->w0, RTW89_RXINFO_USER_MAC_ID_VALID))
+			continue;
+
+		phy_ppdu->mac_id =
+			le32_get_bits(user->w0, RTW89_RXINFO_USER_MACID);
+		break;
+	}
+
 	phy_sts = skb->data + RTW89_PPDU_MAC_INFO_SIZE;
 	phy_sts += usr_num * RTW89_PPDU_MAC_INFO_USR_SIZE;
 	/* 8-byte alignment */
 	if (usr_num & BIT(0))
 		phy_sts += RTW89_PPDU_MAC_INFO_USR_SIZE;
 	if (rx_cnt_valid)
-		phy_sts += RTW89_PPDU_MAC_RX_CNT_SIZE;
+		phy_sts += rx_cnt_size;
 	phy_sts += plcp_size;
 
+	if (phy_sts > skb->data + skb->len)
+		return -EINVAL;
+
 	phy_ppdu->buf = phy_sts;
 	phy_ppdu->len = skb->data + skb->len - phy_sts;
 
@@ -1477,14 +1513,24 @@ static void rtw89_core_rx_process_phy_ppdu_iter(void *data,
 static u16 rtw89_core_get_phy_status_ie_len(struct rtw89_dev *rtwdev,
 					    const struct rtw89_phy_sts_iehdr *iehdr)
 {
-	static const u8 physts_ie_len_tab[32] = {
-		16, 32, 24, 24, 8, 8, 8, 8, VAR_LEN, 8, VAR_LEN, 176, VAR_LEN,
-		VAR_LEN, VAR_LEN, VAR_LEN, VAR_LEN, VAR_LEN, 16, 24, VAR_LEN,
-		VAR_LEN, VAR_LEN, 0, 24, 24, 24, 24, 32, 32, 32, 32
+	static const u8 physts_ie_len_tabs[RTW89_CHIP_GEN_NUM][32] = {
+		[RTW89_CHIP_AX] = {
+			16, 32, 24, 24, 8, 8, 8, 8, VAR_LEN, 8, VAR_LEN, 176, VAR_LEN,
+			VAR_LEN, VAR_LEN, VAR_LEN, VAR_LEN, VAR_LEN, 16, 24, VAR_LEN,
+			VAR_LEN, VAR_LEN, 0, 24, 24, 24, 24, 32, 32, 32, 32
+		},
+		[RTW89_CHIP_BE] = {
+			32, 40, 24, 24, 8, 8, 8, 8, VAR_LEN, 8, VAR_LEN, 176, VAR_LEN,
+			VAR_LEN, VAR_LEN, VAR_LEN, VAR_LEN, VAR_LEN, 16, 24, VAR_LEN,
+			VAR_LEN, VAR_LEN, 0, 24, 24, 24, 24, 32, 32, 32, 32
+		},
 	};
+	const u8 *physts_ie_len_tab;
 	u16 ie_len;
 	u8 ie;
 
+	physts_ie_len_tab = physts_ie_len_tabs[rtwdev->chip->chip_gen];
+
 	ie = le32_get_bits(iehdr->w0, RTW89_PHY_STS_IEHDR_TYPE);
 	if (physts_ie_len_tab[ie] != VAR_LEN)
 		ie_len = physts_ie_len_tab[ie];
@@ -1563,9 +1609,17 @@ static int rtw89_core_rx_process_phy_ppdu(struct rtw89_dev *rtwdev,
 {
 	const struct rtw89_phy_sts_hdr *hdr = phy_ppdu->buf;
 	u32 len_from_header;
+	bool physts_valid;
+
+	physts_valid = le32_get_bits(hdr->w0, RTW89_PHY_STS_HDR_W0_VALID);
+	if (!physts_valid)
+		return -EINVAL;
 
 	len_from_header = le32_get_bits(hdr->w0, RTW89_PHY_STS_HDR_W0_LEN) << 3;
 
+	if (rtwdev->chip->chip_gen == RTW89_CHIP_BE)
+		len_from_header += PHY_STS_HDR_LEN;
+
 	if (len_from_header != phy_ppdu->len) {
 		rtw89_debug(rtwdev, RTW89_DBG_UNEXP, "phy ppdu len mismatch\n");
 		return -EINVAL;
@@ -2052,13 +2106,19 @@ static void rtw89_core_rx_process_ppdu_sts(struct rtw89_dev *rtwdev,
 					     .mac_id = desc_info->mac_id};
 	int ret;
 
-	if (desc_info->mac_info_valid)
-		rtw89_core_rx_process_mac_ppdu(rtwdev, skb, &phy_ppdu);
+	if (desc_info->mac_info_valid) {
+		ret = rtw89_core_rx_process_mac_ppdu(rtwdev, skb, &phy_ppdu);
+		if (ret)
+			goto out;
+	}
+
 	ret = rtw89_core_rx_process_phy_ppdu(rtwdev, &phy_ppdu);
 	if (ret)
-		rtw89_debug(rtwdev, RTW89_DBG_TXRX, "process ppdu failed\n");
+		goto out;
 
 	rtw89_core_rx_process_phy_sts(rtwdev, &phy_ppdu);
+
+out:
 	rtw89_core_rx_pending_skb(rtwdev, &phy_ppdu, desc_info, skb);
 	dev_kfree_skb_any(skb);
 }
@@ -2823,9 +2883,6 @@ void rtw89_roc_start(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 
 	lockdep_assert_held(&rtwdev->mutex);
 
-	ieee80211_queue_delayed_work(hw, &rtwvif->roc.roc_work,
-				     msecs_to_jiffies(rtwvif->roc.duration));
-
 	rtw89_leave_ips_by_hwflags(rtwdev);
 	rtw89_leave_lps(rtwdev);
 	rtw89_chanctx_pause(rtwdev, RTW89_CHANCTX_PAUSE_REASON_ROC);
@@ -2847,6 +2904,9 @@ void rtw89_roc_start(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 			  B_AX_A_UC_CAM_MATCH | B_AX_A_BC_CAM_MATCH);
 
 	ieee80211_ready_on_channel(hw);
+	cancel_delayed_work(&rtwvif->roc.roc_work);
+	ieee80211_queue_delayed_work(hw, &rtwvif->roc.roc_work,
+				     msecs_to_jiffies(rtwvif->roc.duration));
 }
 
 void rtw89_roc_end(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
@@ -2886,7 +2946,7 @@ void rtw89_roc_end(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 
 	if (hw->conf.flags & IEEE80211_CONF_IDLE)
 		ieee80211_queue_delayed_work(hw, &roc->roc_work,
-					     RTW89_ROC_IDLE_TIMEOUT);
+					     msecs_to_jiffies(RTW89_ROC_IDLE_TIMEOUT));
 }
 
 void rtw89_roc_work(struct work_struct *work)
@@ -3069,6 +3129,7 @@ static void rtw89_track_work(struct work_struct *work)
 	rtw89_phy_tx_path_div_track(rtwdev);
 	rtw89_phy_antdiv_track(rtwdev);
 	rtw89_phy_ul_tb_ctrl_track(rtwdev);
+	rtw89_phy_edcca_track(rtwdev);
 	rtw89_tas_track(rtwdev);
 	rtw89_chanctx_track(rtwdev);
 
@@ -3895,10 +3956,7 @@ int rtw89_core_start(struct rtw89_dev *rtwdev)
 	/* efuse process */
 
 	/* pre-config BB/RF, BB reset/RFC reset */
-	ret = rtw89_chip_disable_bb_rf(rtwdev);
-	if (ret)
-		return ret;
-	ret = rtw89_chip_enable_bb_rf(rtwdev);
+	ret = rtw89_chip_reset_bb_rf(rtwdev);
 	if (ret)
 		return ret;
 
@@ -4156,17 +4214,18 @@ out:
 
 static int rtw89_chip_efuse_info_setup(struct rtw89_dev *rtwdev)
 {
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	int ret;
 
 	ret = rtw89_mac_partial_init(rtwdev, false);
 	if (ret)
 		return ret;
 
-	ret = rtw89_parse_efuse_map(rtwdev);
+	ret = mac->parse_efuse_map(rtwdev);
 	if (ret)
 		return ret;
 
-	ret = rtw89_parse_phycap_map(rtwdev);
+	ret = mac->parse_phycap_map(rtwdev);
 	if (ret)
 		return ret;
 
@@ -4176,6 +4235,8 @@ static int rtw89_chip_efuse_info_setup(struct rtw89_dev *rtwdev)
 
 	rtw89_core_setup_phycap(rtwdev);
 
+	rtw89_hci_mac_pre_deinit(rtwdev);
+
 	rtw89_mac_pwr_off(rtwdev);
 
 	return 0;
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 91e4d4e79eea..ea6df859ba15 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -16,6 +16,9 @@ struct rtw89_dev;
 struct rtw89_pci_info;
 struct rtw89_mac_gen_def;
 struct rtw89_phy_gen_def;
+struct rtw89_efuse_block_cfg;
+struct rtw89_fw_txpwr_track_cfg;
+struct rtw89_phy_rfk_log_fmt;
 
 extern const struct ieee80211_ops rtw89_ops;
 
@@ -37,6 +40,8 @@ extern const struct ieee80211_ops rtw89_ops;
 #define RSSI_FACTOR 1
 #define RTW89_RSSI_RAW_TO_DBM(rssi) ((s8)((rssi) >> RSSI_FACTOR) - MAX_RSSI)
 #define RTW89_TX_DIV_RSSI_RAW_TH (2 << RSSI_FACTOR)
+#define DELTA_SWINGIDX_SIZE 30
+
 #define RTW89_RADIOTAP_ROOM_HE sizeof(struct ieee80211_radiotap_he)
 #define RTW89_RADIOTAP_ROOM_EHT \
 	(sizeof(struct ieee80211_radiotap_tlv) + \
@@ -103,6 +108,14 @@ enum rtw89_gain_offset {
 	RTW89_GAIN_OFFSET_5G_LOW,
 	RTW89_GAIN_OFFSET_5G_MID,
 	RTW89_GAIN_OFFSET_5G_HIGH,
+	RTW89_GAIN_OFFSET_6G_L0,
+	RTW89_GAIN_OFFSET_6G_L1,
+	RTW89_GAIN_OFFSET_6G_M0,
+	RTW89_GAIN_OFFSET_6G_M1,
+	RTW89_GAIN_OFFSET_6G_H0,
+	RTW89_GAIN_OFFSET_6G_H1,
+	RTW89_GAIN_OFFSET_6G_UH0,
+	RTW89_GAIN_OFFSET_6G_UH1,
 
 	RTW89_GAIN_OFFSET_NR,
 };
@@ -1693,6 +1706,7 @@ struct rtw89_btc_wl_info {
 	u8 port_id[RTW89_WIFI_ROLE_MLME_MAX];
 	u8 rssi_level;
 	u8 cn_report;
+	u8 coex_mode;
 
 	bool scbd_change;
 	u32 scbd;
@@ -1800,6 +1814,7 @@ struct rtw89_btc_bt_info {
 	union rtw89_btc_bt_rfk_info_map rfk_info;
 
 	u8 raw_info[BTC_BTINFO_MAX]; /* raw bt info from mailbox */
+	u8 rssi_level;
 
 	u32 scbd;
 	u32 feature;
@@ -1816,7 +1831,8 @@ struct rtw89_btc_bt_info {
 	u32 hi_lna_rx: 1;
 	u32 scan_rx_low_pri: 1;
 	u32 scan_info_update: 1;
-	u32 rsvd: 20;
+	u32 lna_constrain: 3;
+	u32 rsvd: 17;
 };
 
 struct rtw89_btc_cx {
@@ -2294,12 +2310,6 @@ struct rtw89_btc_fbtc_fddt_cell_status {
 	u8 state_phase; /* [0:3] train state, [4:7] train phase */
 } __packed;
 
-struct rtw89_btc_fbtc_fddt_cell_status_v5 {
-	s8 wl_tx_pwr;
-	s8 bt_tx_pwr;
-	s8 bt_rx_gain;
-} __packed;
-
 struct rtw89_btc_fbtc_cysta_v3 { /* statistics for cycles */
 	u8 fver;
 	u8 rsvd;
@@ -2363,9 +2373,9 @@ struct rtw89_btc_fbtc_cysta_v5 { /* statistics for cycles */
 	struct rtw89_btc_fbtc_cycle_a2dp_empty_info a2dp_ept;
 	struct rtw89_btc_fbtc_a2dp_trx_stat_v4 a2dp_trx[BTC_CYCLE_SLOT_MAX];
 	struct rtw89_btc_fbtc_cycle_fddt_info_v5 fddt_trx[BTC_CYCLE_SLOT_MAX];
-	struct rtw89_btc_fbtc_fddt_cell_status_v5 fddt_cells[FDD_TRAIN_WL_DIRECTION]
-							    [FDD_TRAIN_WL_RSSI_LEVEL]
-							    [FDD_TRAIN_BT_RSSI_LEVEL];
+	struct rtw89_btc_fbtc_fddt_cell_status fddt_cells[FDD_TRAIN_WL_DIRECTION]
+							 [FDD_TRAIN_WL_RSSI_LEVEL]
+							 [FDD_TRAIN_BT_RSSI_LEVEL];
 	__le32 except_map;
 } __packed;
 
@@ -2498,18 +2508,22 @@ struct rtw89_btc_dm {
 	u32 noisy_level: 3;
 	u32 coex_info_map: 8;
 	u32 bt_only: 1;
-	u32 wl_btg_rx: 1;
+	u32 wl_btg_rx: 2;
 	u32 trx_para_level: 8;
 	u32 wl_stb_chg: 1;
 	u32 pta_owner: 1;
+
 	u32 tdma_instant_excute: 1;
+	u32 wl_btg_rx_rb: 2;
 
 	u16 slot_dur[CXST_MAX];
 
 	u8 run_reason;
 	u8 run_action;
 
+	u8 wl_pre_agc: 2;
 	u8 wl_lna2: 1;
+	u8 wl_pre_agc_rb: 2;
 };
 
 struct rtw89_btc_ctrl {
@@ -2777,6 +2791,20 @@ enum rtw89_rx_frame_type {
 	RTW89_RX_TYPE_RSVD = 3,
 };
 
+enum rtw89_efuse_block {
+	RTW89_EFUSE_BLOCK_SYS = 0,
+	RTW89_EFUSE_BLOCK_RF = 1,
+	RTW89_EFUSE_BLOCK_HCI_DIG_PCIE_SDIO = 2,
+	RTW89_EFUSE_BLOCK_HCI_DIG_USB = 3,
+	RTW89_EFUSE_BLOCK_HCI_PHY_PCIE = 4,
+	RTW89_EFUSE_BLOCK_HCI_PHY_USB3 = 5,
+	RTW89_EFUSE_BLOCK_HCI_PHY_USB2 = 6,
+	RTW89_EFUSE_BLOCK_ADIE = 7,
+
+	RTW89_EFUSE_BLOCK_NUM,
+	RTW89_EFUSE_BLOCK_IGNORE,
+};
+
 struct rtw89_ra_info {
 	u8 is_dis_ra:1;
 	/* Bit0 : CCK
@@ -2815,10 +2843,10 @@ struct rtw89_ra_info {
 	u8 csi_bw:3;
 };
 
-#define RTW89_PPDU_MAX_USR 4
 #define RTW89_PPDU_MAC_INFO_USR_SIZE 4
 #define RTW89_PPDU_MAC_INFO_SIZE 8
 #define RTW89_PPDU_MAC_RX_CNT_SIZE 96
+#define RTW89_PPDU_MAC_RX_CNT_SIZE_V1 128
 
 #define RTW89_MAX_RX_AGG_NUM 64
 #define RTW89_MAX_TX_AGG_NUM 128
@@ -3064,6 +3092,7 @@ struct rtw89_hci_ops {
 	void (*write32)(struct rtw89_dev *rtwdev, u32 addr, u32 data);
 
 	int (*mac_pre_init)(struct rtw89_dev *rtwdev);
+	int (*mac_pre_deinit)(struct rtw89_dev *rtwdev);
 	int (*mac_post_init)(struct rtw89_dev *rtwdev);
 	int (*deinit)(struct rtw89_dev *rtwdev);
 
@@ -3118,7 +3147,8 @@ struct rtw89_chip_ops {
 				 const struct rtw89_chan *chan,
 				 enum rtw89_mac_idx mac_idx,
 				 enum rtw89_phy_idx phy_idx);
-	int (*read_efuse)(struct rtw89_dev *rtwdev, u8 *log_map);
+	int (*read_efuse)(struct rtw89_dev *rtwdev, u8 *log_map,
+			  enum rtw89_efuse_block block);
 	int (*read_phycap)(struct rtw89_dev *rtwdev, u8 *phycap_map);
 	void (*fem_setup)(struct rtw89_dev *rtwdev);
 	void (*rfe_gpio)(struct rtw89_dev *rtwdev);
@@ -3267,6 +3297,8 @@ struct rtw89_dle_size {
 	u16 pge_size;
 	u16 lnk_pge_num;
 	u16 unlnk_pge_num;
+	/* for WiFi 7 chips below */
+	u32 srt_ofst;
 };
 
 struct rtw89_wde_quota {
@@ -3289,6 +3321,26 @@ struct rtw89_ple_quota {
 	u16 wd_rel;
 	u16 cpu_io;
 	u16 tx_rpt;
+	/* for WiFi 7 chips below */
+	u16 h2d;
+};
+
+struct rtw89_rsvd_quota {
+	u16 mpdu_info_tbl;
+	u16 b0_csi;
+	u16 b1_csi;
+	u16 b0_lmr;
+	u16 b1_lmr;
+	u16 b0_ftm;
+	u16 b1_ftm;
+	u16 b0_smr;
+	u16 b1_smr;
+	u16 others;
+};
+
+struct rtw89_dle_rsvd_size {
+	u32 srt_ofst;
+	u32 size;
 };
 
 struct rtw89_dle_mem {
@@ -3299,6 +3351,10 @@ struct rtw89_dle_mem {
 	const struct rtw89_wde_quota *wde_max_qt;
 	const struct rtw89_ple_quota *ple_min_qt;
 	const struct rtw89_ple_quota *ple_max_qt;
+	/* for WiFi 7 chips below */
+	const struct rtw89_rsvd_quota *rsvd_qt;
+	const struct rtw89_dle_rsvd_size *rsvd0_size;
+	const struct rtw89_dle_rsvd_size *rsvd1_size;
 };
 
 struct rtw89_reg_def {
@@ -3325,6 +3381,12 @@ struct rtw89_reg5_def {
 	u32 data;
 };
 
+struct rtw89_reg_imr {
+	u32 addr;
+	u32 clr;
+	u32 set;
+};
+
 struct rtw89_phy_table {
 	const struct rtw89_reg2_def *regs;
 	u32 n_regs;
@@ -3534,6 +3596,11 @@ struct rtw89_imr_info {
 	u32 tmac_imr_set;
 };
 
+struct rtw89_imr_table {
+	const struct rtw89_reg_imr *regs;
+	u32 n_regs;
+};
+
 struct rtw89_xtal_info {
 	u32 xcap_reg;
 	u32 sc_xo_mask;
@@ -3565,6 +3632,22 @@ struct rtw89_dig_regs {
 	struct rtw89_reg_def p1_s20_pagcugc_en;
 };
 
+struct rtw89_edcca_regs {
+	u32 edcca_level;
+	u32 edcca_mask;
+	u32 edcca_p_mask;
+	u32 ppdu_level;
+	u32 ppdu_mask;
+	u32 rpt_a;
+	u32 rpt_b;
+	u32 rpt_sel;
+	u32 rpt_sel_mask;
+	u32 rpt_sel_be;
+	u32 rpt_sel_be_mask;
+	u32 tx_collision_t2r_st;
+	u32 tx_collision_t2r_st_mask;
+};
+
 struct rtw89_phy_ul_tb_info {
 	bool dyn_tb_tri_en;
 	u8 def_if_bandedge;
@@ -3625,8 +3708,8 @@ struct rtw89_chip_info {
 	u32 rsvd_ple_ofst;
 	const struct rtw89_hfc_param_ini *hfc_param_ini;
 	const struct rtw89_dle_mem *dle_mem;
-	u8 wde_qempty_acq_num;
-	u8 wde_qempty_mgq_sel;
+	u8 wde_qempty_acq_grpnum;
+	u8 wde_qempty_mgq_grpsel;
 	u32 rf_base_addr[2];
 	u8 support_chanctx_num;
 	u8 support_bands;
@@ -3644,6 +3727,7 @@ struct rtw89_chip_info {
 	u8 bacam_num;
 	u8 bacam_dynamic_num;
 	enum rtw89_bacam_ver bacam_ver;
+	u8 ppdu_max_usr;
 
 	u8 sec_ctrl_efuse_size;
 	u32 physical_efuse_size;
@@ -3653,6 +3737,7 @@ struct rtw89_chip_info {
 	u32 dav_log_efuse_size;
 	u32 phycap_addr;
 	u32 phycap_size;
+	const struct rtw89_efuse_block_cfg *efuse_blocks;
 
 	const struct rtw89_pwr_cfg * const *pwr_on_seq;
 	const struct rtw89_pwr_cfg * const *pwr_off_seq;
@@ -3710,11 +3795,13 @@ struct rtw89_chip_info {
 	const struct rtw89_reg_def *dcfo_comp;
 	u8 dcfo_comp_sft;
 	const struct rtw89_imr_info *imr_info;
+	const struct rtw89_imr_table *imr_dmac_table;
+	const struct rtw89_imr_table *imr_cmac_table;
 	const struct rtw89_rrsr_cfgs *rrsr_cfgs;
 	struct rtw89_reg_def bss_clr_vld;
 	u32 bss_clr_map_reg;
 	u32 dma_ch_mask;
-	u32 edcca_lvl_reg;
+	const struct rtw89_edcca_regs *edcca_regs;
 	const struct wiphy_wowlan_support *wowlan_stub;
 	const struct rtw89_xtal_info *xtal_info;
 };
@@ -3738,8 +3825,10 @@ enum rtw89_hcifc_mode {
 };
 
 struct rtw89_dle_info {
+	const struct rtw89_rsvd_quota *rsvd_qt;
 	enum rtw89_qta_mode qta_mode;
 	u16 ple_pg_size;
+	u16 ple_free_pg;
 	u16 c0_rx_qta;
 	u16 c1_rx_qta;
 };
@@ -3864,6 +3953,8 @@ struct rtw89_fw_elm_info {
 	struct rtw89_phy_table *bb_gain;
 	struct rtw89_phy_table *rf_radio[RF_PATH_MAX];
 	struct rtw89_phy_table *rf_nctl;
+	struct rtw89_fw_txpwr_track_cfg *txpwr_trk;
+	struct rtw89_phy_rfk_log_fmt *rfk_log_fmt;
 };
 
 struct rtw89_fw_info {
@@ -3983,6 +4074,17 @@ struct rtw89_sub_entity {
 	struct rtw89_chanctx_cfg *cfg;
 };
 
+struct rtw89_edcca_bak {
+	u8 a;
+	u8 p;
+	u8 ppdu;
+	u8 th_old;
+};
+
+enum rtw89_dm_type {
+	RTW89_DM_DYNAMIC_EDCCA,
+};
+
 struct rtw89_hal {
 	u32 rx_fltr;
 	u8 cv;
@@ -4007,7 +4109,8 @@ struct rtw89_hal {
 	bool entity_pause;
 	enum rtw89_entity_mode entity_mode;
 
-	u32 edcca_bak;
+	struct rtw89_edcca_bak edcca_bak;
+	u32 disabled_dm_bitmap; /* bitmap of enum rtw89_dm_type */
 };
 
 #define RTW89_MAX_MAC_ID_NUM 128
@@ -4015,6 +4118,9 @@ struct rtw89_hal {
 
 enum rtw89_flags {
 	RTW89_FLAG_POWERON,
+	RTW89_FLAG_DMAC_FUNC,
+	RTW89_FLAG_CMAC0_FUNC,
+	RTW89_FLAG_CMAC1_FUNC,
 	RTW89_FLAG_FW_RDY,
 	RTW89_FLAG_RUNNING,
 	RTW89_FLAG_BFEE_MON,
@@ -4318,6 +4424,7 @@ struct rtw89_power_trim_info {
 	bool pg_pa_bias_trim;
 	u8 thermal_trim[RF_PATH_MAX];
 	u8 pa_bias_trim[RF_PATH_MAX];
+	u8 pad_bias_trim[RF_PATH_MAX];
 };
 
 struct rtw89_regd {
@@ -4325,9 +4432,12 @@ struct rtw89_regd {
 	u8 txpwr_regd[RTW89_BAND_NUM];
 };
 
+#define RTW89_REGD_MAX_COUNTRY_NUM U8_MAX
+
 struct rtw89_regulatory_info {
 	const struct rtw89_regd *regd;
 	enum rtw89_reg_6ghz_power reg_6ghz_power;
+	DECLARE_BITMAP(block_6ghz, RTW89_REGD_MAX_COUNTRY_NUM);
 };
 
 enum rtw89_ifs_clm_application {
@@ -4802,6 +4912,11 @@ static inline void rtw89_hci_tx_kick_off(struct rtw89_dev *rtwdev, u8 txch)
 	return rtwdev->hci.ops->tx_kick_off(rtwdev, txch);
 }
 
+static inline int rtw89_hci_mac_pre_deinit(struct rtw89_dev *rtwdev)
+{
+	return rtwdev->hci.ops->mac_pre_deinit(rtwdev);
+}
+
 static inline void rtw89_hci_flush_queues(struct rtw89_dev *rtwdev, u32 queues,
 					  bool drop)
 {
diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c
index a3f795d240ea..44829a148185 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.c
+++ b/drivers/net/wireless/realtek/rtw89/debug.c
@@ -3330,13 +3330,14 @@ out:
 
 static int rtw89_dbg_trigger_ctrl_error(struct rtw89_dev *rtwdev)
 {
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	struct rtw89_cpuio_ctrl ctrl_para = {0};
 	u16 pkt_id;
 	int ret;
 
 	rtw89_leave_ps_mode(rtwdev);
 
-	ret = rtw89_mac_dle_buf_req(rtwdev, 0x20, true, &pkt_id);
+	ret = mac->dle_buf_req(rtwdev, 0x20, true, &pkt_id);
 	if (ret)
 		return ret;
 
@@ -3348,7 +3349,7 @@ static int rtw89_dbg_trigger_ctrl_error(struct rtw89_dev *rtwdev)
 	ctrl_para.dst_pid = WDE_DLE_PORT_ID_WDRLS;
 	ctrl_para.dst_qid = WDE_DLE_QUEID_NO_REPORT;
 
-	if (rtw89_mac_set_cpuio(rtwdev, &ctrl_para, true))
+	if (mac->set_cpuio(rtwdev, &ctrl_para, true))
 		return -EFAULT;
 
 	return 0;
@@ -3770,6 +3771,58 @@ static int rtw89_debug_priv_stations_get(struct seq_file *m, void *v)
 	return 0;
 }
 
+#define DM_INFO(type) {RTW89_DM_ ## type, #type}
+
+static const struct rtw89_disabled_dm_info {
+	enum rtw89_dm_type type;
+	const char *name;
+} rtw89_disabled_dm_infos[] = {
+	DM_INFO(DYNAMIC_EDCCA),
+};
+
+static int
+rtw89_debug_priv_disable_dm_get(struct seq_file *m, void *v)
+{
+	struct rtw89_debugfs_priv *debugfs_priv = m->private;
+	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
+	const struct rtw89_disabled_dm_info *info;
+	struct rtw89_hal *hal = &rtwdev->hal;
+	u32 disabled;
+	int i;
+
+	seq_printf(m, "Disabled DM: 0x%x\n", hal->disabled_dm_bitmap);
+
+	for (i = 0; i < ARRAY_SIZE(rtw89_disabled_dm_infos); i++) {
+		info = &rtw89_disabled_dm_infos[i];
+		disabled = BIT(info->type) & hal->disabled_dm_bitmap;
+
+		seq_printf(m, "[%d] %s: %c\n", info->type, info->name,
+			   disabled ? 'X' : 'O');
+	}
+
+	return 0;
+}
+
+static ssize_t
+rtw89_debug_priv_disable_dm_set(struct file *filp, const char __user *user_buf,
+				size_t count, loff_t *loff)
+{
+	struct seq_file *m = (struct seq_file *)filp->private_data;
+	struct rtw89_debugfs_priv *debugfs_priv = m->private;
+	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
+	struct rtw89_hal *hal = &rtwdev->hal;
+	u32 conf;
+	int ret;
+
+	ret = kstrtou32_from_user(user_buf, count, 0, &conf);
+	if (ret)
+		return -EINVAL;
+
+	hal->disabled_dm_bitmap = conf;
+
+	return count;
+}
+
 static struct rtw89_debugfs_priv rtw89_debug_priv_read_reg = {
 	.cb_read = rtw89_debug_priv_read_reg_get,
 	.cb_write = rtw89_debug_priv_read_reg_select,
@@ -3845,6 +3898,11 @@ static struct rtw89_debugfs_priv rtw89_debug_priv_stations = {
 	.cb_read = rtw89_debug_priv_stations_get,
 };
 
+static struct rtw89_debugfs_priv rtw89_debug_priv_disable_dm = {
+	.cb_read = rtw89_debug_priv_disable_dm_get,
+	.cb_write = rtw89_debug_priv_disable_dm_set,
+};
+
 #define rtw89_debugfs_add(name, mode, fopname, parent)				\
 	do {									\
 		rtw89_debug_priv_ ##name.rtwdev = rtwdev;			\
@@ -3885,13 +3943,13 @@ void rtw89_debugfs_init(struct rtw89_dev *rtwdev)
 	rtw89_debugfs_add_w(fw_log_manual);
 	rtw89_debugfs_add_r(phy_info);
 	rtw89_debugfs_add_r(stations);
+	rtw89_debugfs_add_rw(disable_dm);
 }
 #endif
 
 #ifdef CONFIG_RTW89_DEBUGMSG
-void __rtw89_debug(struct rtw89_dev *rtwdev,
-		   enum rtw89_debug_mask mask,
-		   const char *fmt, ...)
+void rtw89_debug(struct rtw89_dev *rtwdev, enum rtw89_debug_mask mask,
+		 const char *fmt, ...)
 {
 	struct va_format vaf = {
 	.fmt = fmt,
@@ -3907,5 +3965,5 @@ void __rtw89_debug(struct rtw89_dev *rtwdev,
 
 	va_end(args);
 }
-EXPORT_SYMBOL(__rtw89_debug);
+EXPORT_SYMBOL(rtw89_debug);
 #endif
diff --git a/drivers/net/wireless/realtek/rtw89/debug.h b/drivers/net/wireless/realtek/rtw89/debug.h
index 079269bb5251..800ea59873a1 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.h
+++ b/drivers/net/wireless/realtek/rtw89/debug.h
@@ -29,6 +29,8 @@ enum rtw89_debug_mask {
 	RTW89_DBG_WOW = BIT(18),
 	RTW89_DBG_UL_TB = BIT(19),
 	RTW89_DBG_CHAN = BIT(20),
+	RTW89_DBG_ACPI = BIT(21),
+	RTW89_DBG_EDCCA = BIT(22),
 
 	RTW89_DBG_UNEXP = BIT(31),
 };
@@ -57,12 +59,10 @@ static inline void rtw89_debugfs_init(struct rtw89_dev *rtwdev) {}
 
 #ifdef CONFIG_RTW89_DEBUGMSG
 extern unsigned int rtw89_debug_mask;
-#define rtw89_debug(rtwdev, a...) __rtw89_debug(rtwdev, ##a)
 
 __printf(3, 4)
-void __rtw89_debug(struct rtw89_dev *rtwdev,
-		   enum rtw89_debug_mask mask,
-		   const char *fmt, ...);
+void rtw89_debug(struct rtw89_dev *rtwdev, enum rtw89_debug_mask mask,
+		 const char *fmt, ...);
 static inline void rtw89_hex_dump(struct rtw89_dev *rtwdev,
 				  enum rtw89_debug_mask mask,
 				  const char *prefix_str,
@@ -73,6 +73,12 @@ static inline void rtw89_hex_dump(struct rtw89_dev *rtwdev,
 
 	print_hex_dump_bytes(prefix_str, DUMP_PREFIX_OFFSET, buf, len);
 }
+
+static inline bool rtw89_debug_is_enabled(struct rtw89_dev *rtwdev,
+					  enum rtw89_debug_mask mask)
+{
+	return !!(rtw89_debug_mask & mask);
+}
 #else
 static inline void rtw89_debug(struct rtw89_dev *rtwdev,
 			       enum rtw89_debug_mask mask,
@@ -81,6 +87,11 @@ static inline void rtw89_hex_dump(struct rtw89_dev *rtwdev,
 				  enum rtw89_debug_mask mask,
 				  const char *prefix_str,
 				  const void *buf, size_t len) {}
+static inline bool rtw89_debug_is_enabled(struct rtw89_dev *rtwdev,
+					  enum rtw89_debug_mask mask)
+{
+	return false;
+}
 #endif
 
 #endif
diff --git a/drivers/net/wireless/realtek/rtw89/efuse.c b/drivers/net/wireless/realtek/rtw89/efuse.c
index 2aaf4d013e46..e1236079a84a 100644
--- a/drivers/net/wireless/realtek/rtw89/efuse.c
+++ b/drivers/net/wireless/realtek/rtw89/efuse.c
@@ -114,6 +114,11 @@ static int rtw89_dump_physical_efuse_map_ddv(struct rtw89_dev *rtwdev, u8 *map,
 	return 0;
 }
 
+int rtw89_cnv_efuse_state_ax(struct rtw89_dev *rtwdev, bool idle)
+{
+	return 0;
+}
+
 static int rtw89_dump_physical_efuse_map_dav(struct rtw89_dev *rtwdev, u8 *map,
 					     u32 dump_addr, u32 dump_size)
 {
@@ -231,7 +236,7 @@ static int rtw89_dump_logical_efuse_map(struct rtw89_dev *rtwdev, u8 *phy_map,
 	return 0;
 }
 
-int rtw89_parse_efuse_map(struct rtw89_dev *rtwdev)
+int rtw89_parse_efuse_map_ax(struct rtw89_dev *rtwdev)
 {
 	u32 phy_size = rtwdev->chip->physical_efuse_size;
 	u32 log_size = rtwdev->chip->logical_efuse_size;
@@ -286,7 +291,7 @@ int rtw89_parse_efuse_map(struct rtw89_dev *rtwdev)
 
 	rtw89_hex_dump(rtwdev, RTW89_DBG_FW, "log_map: ", log_map, full_log_size);
 
-	ret = rtwdev->chip->ops->read_efuse(rtwdev, log_map);
+	ret = rtwdev->chip->ops->read_efuse(rtwdev, log_map, RTW89_EFUSE_BLOCK_IGNORE);
 	if (ret) {
 		rtw89_warn(rtwdev, "failed to read efuse map\n");
 		goto out_free;
@@ -300,7 +305,7 @@ out_free:
 	return ret;
 }
 
-int rtw89_parse_phycap_map(struct rtw89_dev *rtwdev)
+int rtw89_parse_phycap_map_ax(struct rtw89_dev *rtwdev)
 {
 	u32 phycap_addr = rtwdev->chip->phycap_addr;
 	u32 phycap_size = rtwdev->chip->phycap_size;
diff --git a/drivers/net/wireless/realtek/rtw89/efuse.h b/drivers/net/wireless/realtek/rtw89/efuse.h
index 79071aff28de..5c6787179bad 100644
--- a/drivers/net/wireless/realtek/rtw89/efuse.h
+++ b/drivers/net/wireless/realtek/rtw89/efuse.h
@@ -7,8 +7,21 @@
 
 #include "core.h"
 
-int rtw89_parse_efuse_map(struct rtw89_dev *rtwdev);
-int rtw89_parse_phycap_map(struct rtw89_dev *rtwdev);
+#define RTW89_EFUSE_BLOCK_ID_MASK GENMASK(31, 16)
+#define RTW89_EFUSE_BLOCK_SIZE_MASK GENMASK(15, 0)
+#define RTW89_EFUSE_MAX_BLOCK_SIZE 0x10000
+
+struct rtw89_efuse_block_cfg {
+	u32 offset;
+	u32 size;
+};
+
+int rtw89_parse_efuse_map_ax(struct rtw89_dev *rtwdev);
+int rtw89_parse_phycap_map_ax(struct rtw89_dev *rtwdev);
+int rtw89_cnv_efuse_state_ax(struct rtw89_dev *rtwdev, bool idle);
+int rtw89_parse_efuse_map_be(struct rtw89_dev *rtwdev);
+int rtw89_parse_phycap_map_be(struct rtw89_dev *rtwdev);
+int rtw89_cnv_efuse_state_be(struct rtw89_dev *rtwdev, bool idle);
 int rtw89_read_efuse_ver(struct rtw89_dev *rtwdev, u8 *efv);
 
 #endif
diff --git a/drivers/net/wireless/realtek/rtw89/efuse_be.c b/drivers/net/wireless/realtek/rtw89/efuse_be.c
new file mode 100644
index 000000000000..8e8b7cd315f7
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtw89/efuse_be.c
@@ -0,0 +1,420 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/* Copyright(c) 2023  Realtek Corporation
+ */
+
+#include "debug.h"
+#include "efuse.h"
+#include "mac.h"
+#include "reg.h"
+
+static void rtw89_enable_efuse_pwr_cut_ddv_be(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	struct rtw89_hal *hal = &rtwdev->hal;
+	bool aphy_patch = true;
+
+	if (chip->chip_id == RTL8922A && hal->cv == CHIP_CAV)
+		aphy_patch = false;
+
+	rtw89_write8_set(rtwdev, R_BE_PMC_DBG_CTRL2, B_BE_SYSON_DIS_PMCR_BE_WRMSK);
+
+	if (aphy_patch) {
+		rtw89_write16_set(rtwdev, R_BE_SYS_ISO_CTRL, B_BE_PWC_EV2EF_S);
+		mdelay(1);
+		rtw89_write16_set(rtwdev, R_BE_SYS_ISO_CTRL, B_BE_PWC_EV2EF_B);
+		rtw89_write16_clr(rtwdev, R_BE_SYS_ISO_CTRL, B_BE_ISO_EB2CORE);
+	}
+
+	rtw89_write32_set(rtwdev, R_BE_EFUSE_CTRL_2_V1, B_BE_EF_BURST);
+}
+
+static void rtw89_disable_efuse_pwr_cut_ddv_be(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	struct rtw89_hal *hal = &rtwdev->hal;
+	bool aphy_patch = true;
+
+	if (chip->chip_id == RTL8922A && hal->cv == CHIP_CAV)
+		aphy_patch = false;
+
+	if (aphy_patch) {
+		rtw89_write16_set(rtwdev, R_BE_SYS_ISO_CTRL, B_BE_ISO_EB2CORE);
+		rtw89_write16_clr(rtwdev, R_BE_SYS_ISO_CTRL, B_BE_PWC_EV2EF_B);
+		mdelay(1);
+		rtw89_write16_clr(rtwdev, R_BE_SYS_ISO_CTRL, B_BE_PWC_EV2EF_S);
+	}
+
+	rtw89_write8_clr(rtwdev, R_BE_PMC_DBG_CTRL2, B_BE_SYSON_DIS_PMCR_BE_WRMSK);
+	rtw89_write32_clr(rtwdev, R_BE_EFUSE_CTRL_2_V1, B_BE_EF_BURST);
+}
+
+static int rtw89_dump_physical_efuse_map_ddv_be(struct rtw89_dev *rtwdev, u8 *map,
+						u32 dump_addr, u32 dump_size)
+{
+	u32 efuse_ctl;
+	u32 addr;
+	u32 data;
+	int ret;
+
+	if (!IS_ALIGNED(dump_addr, 4) || !IS_ALIGNED(dump_size, 4)) {
+		rtw89_err(rtwdev, "Efuse addr 0x%x or size 0x%x not aligned\n",
+			  dump_addr, dump_size);
+		return -EINVAL;
+	}
+
+	rtw89_enable_efuse_pwr_cut_ddv_be(rtwdev);
+
+	for (addr = dump_addr; addr < dump_addr + dump_size; addr += 4, map += 4) {
+		efuse_ctl = u32_encode_bits(addr, B_BE_EF_ADDR_MASK);
+		rtw89_write32(rtwdev, R_BE_EFUSE_CTRL, efuse_ctl & ~B_BE_EF_RDY);
+
+		ret = read_poll_timeout_atomic(rtw89_read32, efuse_ctl,
+					       efuse_ctl & B_BE_EF_RDY, 1, 1000000,
+					       true, rtwdev, R_BE_EFUSE_CTRL);
+		if (ret)
+			return -EBUSY;
+
+		data = rtw89_read32(rtwdev, R_BE_EFUSE_CTRL_1_V1);
+		*((__le32 *)map) = cpu_to_le32(data);
+	}
+
+	rtw89_disable_efuse_pwr_cut_ddv_be(rtwdev);
+
+	return 0;
+}
+
+static int rtw89_dump_physical_efuse_map_dav_be(struct rtw89_dev *rtwdev, u8 *map,
+						u32 dump_addr, u32 dump_size)
+{
+	u32 addr;
+	u8 val8;
+	int err;
+	int ret;
+
+	for (addr = dump_addr; addr < dump_addr + dump_size; addr++) {
+		ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_CTRL, 0x40,
+					      FULL_BIT_MASK);
+		if (ret)
+			return ret;
+		ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_LOW_ADDR, addr & 0xff,
+					      XTAL_SI_LOW_ADDR_MASK);
+		if (ret)
+			return ret;
+		ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_CTRL, addr >> 8,
+					      XTAL_SI_HIGH_ADDR_MASK);
+		if (ret)
+			return ret;
+		ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_CTRL, 0,
+					      XTAL_SI_MODE_SEL_MASK);
+		if (ret)
+			return ret;
+
+		ret = read_poll_timeout_atomic(rtw89_mac_read_xtal_si, err,
+					       !err && (val8 & XTAL_SI_RDY),
+					       1, 10000, false,
+					       rtwdev, XTAL_SI_CTRL, &val8);
+		if (ret) {
+			rtw89_warn(rtwdev, "failed to read dav efuse\n");
+			return ret;
+		}
+
+		ret = rtw89_mac_read_xtal_si(rtwdev, XTAL_SI_READ_VAL, &val8);
+		if (ret)
+			return ret;
+		*map++ = val8;
+	}
+
+	return 0;
+}
+
+int rtw89_cnv_efuse_state_be(struct rtw89_dev *rtwdev, bool idle)
+{
+	u32 val;
+	int ret = 0;
+
+	if (idle) {
+		rtw89_write32_set(rtwdev, R_BE_WL_BT_PWR_CTRL, B_BE_BT_DISN_EN);
+	} else {
+		rtw89_write32_clr(rtwdev, R_BE_WL_BT_PWR_CTRL, B_BE_BT_DISN_EN);
+
+		ret = read_poll_timeout(rtw89_read32_mask, val,
+					val == MAC_AX_SYS_ACT, 50, 5000,
+					false, rtwdev, R_BE_IC_PWR_STATE,
+					B_BE_WHOLE_SYS_PWR_STE_MASK);
+		if (ret)
+			rtw89_warn(rtwdev, "failed to convert efuse state\n");
+	}
+
+	return ret;
+}
+
+static int rtw89_dump_physical_efuse_map_be(struct rtw89_dev *rtwdev, u8 *map,
+					    u32 dump_addr, u32 dump_size, bool dav)
+{
+	int ret;
+
+	if (!map || dump_size == 0)
+		return 0;
+
+	rtw89_cnv_efuse_state_be(rtwdev, false);
+
+	if (dav) {
+		ret = rtw89_dump_physical_efuse_map_dav_be(rtwdev, map,
+							   dump_addr, dump_size);
+		if (ret)
+			return ret;
+
+		rtw89_hex_dump(rtwdev, RTW89_DBG_FW, "phy_map dav: ", map, dump_size);
+	} else {
+		ret = rtw89_dump_physical_efuse_map_ddv_be(rtwdev, map,
+							   dump_addr, dump_size);
+		if (ret)
+			return ret;
+
+		rtw89_hex_dump(rtwdev, RTW89_DBG_FW, "phy_map ddv: ", map, dump_size);
+	}
+
+	rtw89_cnv_efuse_state_be(rtwdev, true);
+
+	return 0;
+}
+
+#define EFUSE_HDR_CONST_MASK GENMASK(23, 20)
+#define EFUSE_HDR_PAGE_MASK GENMASK(19, 17)
+#define EFUSE_HDR_OFFSET_MASK GENMASK(16, 4)
+#define EFUSE_HDR_OFFSET_DAV_MASK GENMASK(11, 4)
+#define EFUSE_HDR_WORD_EN_MASK GENMASK(3, 0)
+
+#define invalid_efuse_header_be(hdr1, hdr2, hdr3) \
+	((hdr1) == 0xff || (hdr2) == 0xff || (hdr3) == 0xff)
+#define invalid_efuse_content_be(word_en, i) \
+	(((word_en) & BIT(i)) != 0x0)
+#define get_efuse_blk_idx_be(hdr1, hdr2, hdr3) \
+	(((hdr1) << 16) | ((hdr2) << 8) | (hdr3))
+#define block_idx_to_logical_idx_be(blk_idx, i) \
+	(((blk_idx) << 3) + ((i) << 1))
+
+#define invalid_efuse_header_dav_be(hdr1, hdr2) \
+	((hdr1) == 0xff || (hdr2) == 0xff)
+#define get_efuse_blk_idx_dav_be(hdr1, hdr2) \
+	(((hdr1) << 8) | (hdr2))
+
+static int rtw89_eeprom_parser_be(struct rtw89_dev *rtwdev,
+				  const u8 *phy_map, u32 phy_size, u8 *log_map,
+				  const struct rtw89_efuse_block_cfg *efuse_block)
+{
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	enum rtw89_efuse_block blk_page, page;
+	u32 size = efuse_block->size;
+	u32 phy_idx, log_idx;
+	u32 hdr, page_offset;
+	u8 hdr1, hdr2, hdr3;
+	u8 i, val0, val1;
+	u32 min, max;
+	u16 blk_idx;
+	u8 word_en;
+
+	page = u32_get_bits(efuse_block->offset, RTW89_EFUSE_BLOCK_ID_MASK);
+	page_offset = u32_get_bits(efuse_block->offset, RTW89_EFUSE_BLOCK_SIZE_MASK);
+
+	min = ALIGN_DOWN(page_offset, 2);
+	max = ALIGN(page_offset + size, 2);
+
+	memset(log_map, 0xff, size);
+
+	phy_idx = chip->sec_ctrl_efuse_size;
+
+	do {
+		if (page == RTW89_EFUSE_BLOCK_ADIE) {
+			hdr1 = phy_map[phy_idx];
+			hdr2 = phy_map[phy_idx + 1];
+			if (invalid_efuse_header_dav_be(hdr1, hdr2))
+				break;
+
+			phy_idx += 2;
+
+			hdr = get_efuse_blk_idx_dav_be(hdr1, hdr2);
+
+			blk_page = RTW89_EFUSE_BLOCK_ADIE;
+			blk_idx = u32_get_bits(hdr, EFUSE_HDR_OFFSET_DAV_MASK);
+			word_en = u32_get_bits(hdr, EFUSE_HDR_WORD_EN_MASK);
+		} else {
+			hdr1 = phy_map[phy_idx];
+			hdr2 = phy_map[phy_idx + 1];
+			hdr3 = phy_map[phy_idx + 2];
+			if (invalid_efuse_header_be(hdr1, hdr2, hdr3))
+				break;
+
+			phy_idx += 3;
+
+			hdr = get_efuse_blk_idx_be(hdr1, hdr2, hdr3);
+
+			blk_page = u32_get_bits(hdr, EFUSE_HDR_PAGE_MASK);
+			blk_idx = u32_get_bits(hdr, EFUSE_HDR_OFFSET_MASK);
+			word_en = u32_get_bits(hdr, EFUSE_HDR_WORD_EN_MASK);
+		}
+
+		if (blk_idx >= RTW89_EFUSE_MAX_BLOCK_SIZE >> 3) {
+			rtw89_err(rtwdev, "[ERR]efuse idx:0x%X\n", phy_idx - 3);
+			rtw89_err(rtwdev, "[ERR]read hdr:0x%X\n", hdr);
+			return -EINVAL;
+		}
+
+		for (i = 0; i < 4; i++) {
+			if (invalid_efuse_content_be(word_en, i))
+				continue;
+
+			if (phy_idx >= phy_size - 1)
+				return -EINVAL;
+
+			log_idx = block_idx_to_logical_idx_be(blk_idx, i);
+
+			if (blk_page == page && log_idx >= min && log_idx < max) {
+				val0 = phy_map[phy_idx];
+				val1 = phy_map[phy_idx + 1];
+
+				if (log_idx == min && page_offset > min) {
+					log_map[log_idx - page_offset + 1] = val1;
+				} else if (log_idx + 2 == max &&
+					   page_offset + size < max) {
+					log_map[log_idx - page_offset] = val0;
+				} else {
+					log_map[log_idx - page_offset] = val0;
+					log_map[log_idx - page_offset + 1] = val1;
+				}
+			}
+			phy_idx += 2;
+		}
+	} while (phy_idx < phy_size);
+
+	return 0;
+}
+
+static int rtw89_parse_logical_efuse_block_be(struct rtw89_dev *rtwdev,
+					      const u8 *phy_map, u32 phy_size,
+					      enum rtw89_efuse_block block)
+{
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	const struct rtw89_efuse_block_cfg *efuse_block;
+	u8 *log_map;
+	int ret;
+
+	efuse_block = &chip->efuse_blocks[block];
+
+	log_map = kmalloc(efuse_block->size, GFP_KERNEL);
+	if (!log_map)
+		return -ENOMEM;
+
+	ret = rtw89_eeprom_parser_be(rtwdev, phy_map, phy_size, log_map, efuse_block);
+	if (ret) {
+		rtw89_warn(rtwdev, "failed to dump efuse logical block %d\n", block);
+		goto out_free;
+	}
+
+	rtw89_hex_dump(rtwdev, RTW89_DBG_FW, "log_map: ", log_map, efuse_block->size);
+
+	ret = rtwdev->chip->ops->read_efuse(rtwdev, log_map, block);
+	if (ret) {
+		rtw89_warn(rtwdev, "failed to read efuse map\n");
+		goto out_free;
+	}
+
+out_free:
+	kfree(log_map);
+
+	return ret;
+}
+
+int rtw89_parse_efuse_map_be(struct rtw89_dev *rtwdev)
+{
+	u32 phy_size = rtwdev->chip->physical_efuse_size;
+	u32 dav_phy_size = rtwdev->chip->dav_phy_efuse_size;
+	enum rtw89_efuse_block block;
+	u8 *phy_map = NULL;
+	u8 *dav_phy_map = NULL;
+	int ret;
+
+	if (rtw89_read16(rtwdev, R_BE_SYS_WL_EFUSE_CTRL) & B_BE_AUTOLOAD_SUS)
+		rtwdev->efuse.valid = true;
+	else
+		rtw89_warn(rtwdev, "failed to check efuse autoload\n");
+
+	phy_map = kmalloc(phy_size, GFP_KERNEL);
+	if (dav_phy_size)
+		dav_phy_map = kmalloc(dav_phy_size, GFP_KERNEL);
+
+	if (!phy_map || (dav_phy_size && !dav_phy_map)) {
+		ret = -ENOMEM;
+		goto out_free;
+	}
+
+	ret = rtw89_dump_physical_efuse_map_be(rtwdev, phy_map, 0, phy_size, false);
+	if (ret) {
+		rtw89_warn(rtwdev, "failed to dump efuse physical map\n");
+		goto out_free;
+	}
+	ret = rtw89_dump_physical_efuse_map_be(rtwdev, dav_phy_map, 0, dav_phy_size, true);
+	if (ret) {
+		rtw89_warn(rtwdev, "failed to dump efuse dav physical map\n");
+		goto out_free;
+	}
+
+	if (rtwdev->hci.type == RTW89_HCI_TYPE_USB)
+		block = RTW89_EFUSE_BLOCK_HCI_DIG_USB;
+	else
+		block = RTW89_EFUSE_BLOCK_HCI_DIG_PCIE_SDIO;
+
+	ret = rtw89_parse_logical_efuse_block_be(rtwdev, phy_map, phy_size, block);
+	if (ret) {
+		rtw89_warn(rtwdev, "failed to parse efuse logic block %d\n",
+			   RTW89_EFUSE_BLOCK_HCI_DIG_PCIE_SDIO);
+		goto out_free;
+	}
+
+	ret = rtw89_parse_logical_efuse_block_be(rtwdev, phy_map, phy_size,
+						 RTW89_EFUSE_BLOCK_RF);
+	if (ret) {
+		rtw89_warn(rtwdev, "failed to parse efuse logic block %d\n",
+			   RTW89_EFUSE_BLOCK_RF);
+		goto out_free;
+	}
+
+out_free:
+	kfree(dav_phy_map);
+	kfree(phy_map);
+
+	return ret;
+}
+
+int rtw89_parse_phycap_map_be(struct rtw89_dev *rtwdev)
+{
+	u32 phycap_addr = rtwdev->chip->phycap_addr;
+	u32 phycap_size = rtwdev->chip->phycap_size;
+	u8 *phycap_map = NULL;
+	int ret = 0;
+
+	if (!phycap_size)
+		return 0;
+
+	phycap_map = kmalloc(phycap_size, GFP_KERNEL);
+	if (!phycap_map)
+		return -ENOMEM;
+
+	ret = rtw89_dump_physical_efuse_map_be(rtwdev, phycap_map,
+					       phycap_addr, phycap_size, false);
+	if (ret) {
+		rtw89_warn(rtwdev, "failed to dump phycap map\n");
+		goto out_free;
+	}
+
+	ret = rtwdev->chip->ops->read_phycap(rtwdev, phycap_map);
+	if (ret) {
+		rtw89_warn(rtwdev, "failed to read phycap map\n");
+		goto out_free;
+	}
+
+out_free:
+	kfree(phycap_map);
+
+	return ret;
+}
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index a732c22a2d54..09684cea9731 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -401,10 +401,14 @@ int __rtw89_fw_recognize_from_elm(struct rtw89_dev *rtwdev,
 				  const union rtw89_fw_element_arg arg)
 {
 	enum rtw89_fw_type type = arg.fw_type;
+	struct rtw89_hal *hal = &rtwdev->hal;
 	struct rtw89_fw_suit *fw_suit;
 
+	if (hal->cv != elm->u.bbmcu.cv)
+		return 1; /* ignore this element */
+
 	fw_suit = rtw89_fw_suit_get(rtwdev, type);
-	fw_suit->data = elm->u.common.contents;
+	fw_suit->data = elm->u.bbmcu.contents;
 	fw_suit->size = le32_to_cpu(elm->size);
 
 	return rtw89_fw_update_ver(rtwdev, type, fw_suit);
@@ -453,6 +457,7 @@ static const struct __fw_feat_cfg fw_feat_tbl[] = {
 	__CFG_FW_FEAT(RTL8852C, ge, 0, 27, 36, 0, SCAN_OFFLOAD),
 	__CFG_FW_FEAT(RTL8852C, ge, 0, 27, 40, 0, CRASH_TRIGGER),
 	__CFG_FW_FEAT(RTL8852C, ge, 0, 27, 56, 10, BEACON_FILTER),
+	__CFG_FW_FEAT(RTL8922A, ge, 0, 34, 30, 0, CRASH_TRIGGER),
 };
 
 static void rtw89_fw_iterate_feature_cfg(struct rtw89_fw_info *fw,
@@ -658,6 +663,97 @@ setup:
 	return 0;
 }
 
+static
+int rtw89_build_txpwr_trk_tbl_from_elm(struct rtw89_dev *rtwdev,
+				       const struct rtw89_fw_element_hdr *elm,
+				       const union rtw89_fw_element_arg arg)
+{
+	struct rtw89_fw_elm_info *elm_info = &rtwdev->fw.elm_info;
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	u32 needed_bitmap = 0;
+	u32 offset = 0;
+	int subband;
+	u32 bitmap;
+	int type;
+
+	if (chip->support_bands & BIT(NL80211_BAND_6GHZ))
+		needed_bitmap |= RTW89_DEFAULT_NEEDED_FW_TXPWR_TRK_6GHZ;
+	if (chip->support_bands & BIT(NL80211_BAND_5GHZ))
+		needed_bitmap |= RTW89_DEFAULT_NEEDED_FW_TXPWR_TRK_5GHZ;
+	if (chip->support_bands & BIT(NL80211_BAND_2GHZ))
+		needed_bitmap |= RTW89_DEFAULT_NEEDED_FW_TXPWR_TRK_2GHZ;
+
+	bitmap = le32_to_cpu(elm->u.txpwr_trk.bitmap);
+
+	if ((bitmap & needed_bitmap) != needed_bitmap) {
+		rtw89_warn(rtwdev, "needed txpwr trk bitmap %08x but %0x8x\n",
+			   needed_bitmap, bitmap);
+		return -ENOENT;
+	}
+
+	elm_info->txpwr_trk = kzalloc(sizeof(*elm_info->txpwr_trk), GFP_KERNEL);
+	if (!elm_info->txpwr_trk)
+		return -ENOMEM;
+
+	for (type = 0; bitmap; type++, bitmap >>= 1) {
+		if (!(bitmap & BIT(0)))
+			continue;
+
+		if (type >= __RTW89_FW_TXPWR_TRK_TYPE_6GHZ_START &&
+		    type <= __RTW89_FW_TXPWR_TRK_TYPE_6GHZ_MAX)
+			subband = 4;
+		else if (type >= __RTW89_FW_TXPWR_TRK_TYPE_5GHZ_START &&
+			 type <= __RTW89_FW_TXPWR_TRK_TYPE_5GHZ_MAX)
+			subband = 3;
+		else if (type >= __RTW89_FW_TXPWR_TRK_TYPE_2GHZ_START &&
+			 type <= __RTW89_FW_TXPWR_TRK_TYPE_2GHZ_MAX)
+			subband = 1;
+		else
+			break;
+
+		elm_info->txpwr_trk->delta[type] = &elm->u.txpwr_trk.contents[offset];
+
+		offset += subband;
+		if (offset * DELTA_SWINGIDX_SIZE > le32_to_cpu(elm->size))
+			goto err;
+	}
+
+	return 0;
+
+err:
+	rtw89_warn(rtwdev, "unexpected txpwr trk offset %d over size %d\n",
+		   offset, le32_to_cpu(elm->size));
+	kfree(elm_info->txpwr_trk);
+	elm_info->txpwr_trk = NULL;
+
+	return -EFAULT;
+}
+
+static
+int rtw89_build_rfk_log_fmt_from_elm(struct rtw89_dev *rtwdev,
+				     const struct rtw89_fw_element_hdr *elm,
+				     const union rtw89_fw_element_arg arg)
+{
+	struct rtw89_fw_elm_info *elm_info = &rtwdev->fw.elm_info;
+	u8 rfk_id;
+
+	if (elm_info->rfk_log_fmt)
+		goto allocated;
+
+	elm_info->rfk_log_fmt = kzalloc(sizeof(*elm_info->rfk_log_fmt), GFP_KERNEL);
+	if (!elm_info->rfk_log_fmt)
+		return 1; /* this is an optional element, so just ignore this */
+
+allocated:
+	rfk_id = elm->u.rfk_log_fmt.rfk_id;
+	if (rfk_id >= RTW89_PHY_C2H_RFK_LOG_FUNC_NUM)
+		return 1;
+
+	elm_info->rfk_log_fmt->elm[rfk_id] = elm;
+
+	return 0;
+}
+
 static const struct rtw89_fw_element_handler __fw_element_handlers[] = {
 	[RTW89_FW_ELEMENT_ID_BBMCU0] = {__rtw89_fw_recognize_from_elm,
 					{ .fw_type = RTW89_FW_BBMCU0 }, NULL},
@@ -710,6 +806,12 @@ static const struct rtw89_fw_element_handler __fw_element_handlers[] = {
 		rtw89_fw_recognize_txpwr_from_elm,
 		{ .offset = offsetof(struct rtw89_rfe_data, tx_shape_lmt_ru.conf) }, NULL,
 	},
+	[RTW89_FW_ELEMENT_ID_TXPWR_TRK] = {
+		rtw89_build_txpwr_trk_tbl_from_elm, {}, "PWR_TRK",
+	},
+	[RTW89_FW_ELEMENT_ID_RFKLOG_FMT] = {
+		rtw89_build_rfk_log_fmt_from_elm, {}, NULL,
+	},
 };
 
 int rtw89_fw_recognize_elements(struct rtw89_dev *rtwdev)
@@ -750,6 +852,8 @@ int rtw89_fw_recognize_elements(struct rtw89_dev *rtwdev)
 			goto next;
 
 		ret = handler->fn(rtwdev, hdr, handler->arg);
+		if (ret == 1) /* ignore this element */
+			goto next;
 		if (ret)
 			return ret;
 
@@ -956,16 +1060,24 @@ static int rtw89_fw_download_main(struct rtw89_dev *rtwdev,
 
 static void rtw89_fw_prog_cnt_dump(struct rtw89_dev *rtwdev)
 {
+	enum rtw89_chip_gen chip_gen = rtwdev->chip->chip_gen;
+	u32 addr = R_AX_DBG_PORT_SEL;
 	u32 val32;
 	u16 index;
 
+	if (chip_gen == RTW89_CHIP_BE) {
+		addr = R_BE_WLCPU_PORT_PC;
+		goto dump;
+	}
+
 	rtw89_write32(rtwdev, R_AX_DBG_CTRL,
 		      FIELD_PREP(B_AX_DBG_SEL0, FW_PROG_CNTR_DBG_SEL) |
 		      FIELD_PREP(B_AX_DBG_SEL1, FW_PROG_CNTR_DBG_SEL));
 	rtw89_write32_mask(rtwdev, R_AX_SYS_STATUS1, B_AX_SEL_0XC0_MASK, MAC_DBG_SEL);
 
+dump:
 	for (index = 0; index < 15; index++) {
-		val32 = rtw89_read32(rtwdev, R_AX_DBG_PORT_SEL);
+		val32 = rtw89_read32(rtwdev, addr);
 		rtw89_err(rtwdev, "[ERR]fw PC = 0x%x\n", val32);
 		fsleep(10);
 	}
@@ -1135,6 +1247,9 @@ static void rtw89_unload_firmware_elements(struct rtw89_dev *rtwdev)
 	for (i = 0; i < ARRAY_SIZE(elm_info->rf_radio); i++)
 		rtw89_free_phy_tbl_from_elm(elm_info->rf_radio[i]);
 	rtw89_free_phy_tbl_from_elm(elm_info->rf_nctl);
+
+	kfree(elm_info->txpwr_trk);
+	kfree(elm_info->rfk_log_fmt);
 }
 
 void rtw89_unload_firmware(struct rtw89_dev *rtwdev)
@@ -2215,6 +2330,41 @@ fail:
 	return ret;
 }
 
+int rtw89_fw_h2c_notify_dbcc(struct rtw89_dev *rtwdev, bool en)
+{
+	struct rtw89_h2c_notify_dbcc *h2c;
+	u32 len = sizeof(*h2c);
+	struct sk_buff *skb;
+	int ret;
+
+	skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, len);
+	if (!skb) {
+		rtw89_err(rtwdev, "failed to alloc skb for h2c notify dbcc\n");
+		return -ENOMEM;
+	}
+	skb_put(skb, len);
+	h2c = (struct rtw89_h2c_notify_dbcc *)skb->data;
+
+	h2c->w0 = le32_encode_bits(en, RTW89_H2C_NOTIFY_DBCC_EN);
+
+	rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C,
+			      H2C_CAT_MAC, H2C_CL_MAC_MEDIA_RPT,
+			      H2C_FUNC_NOTIFY_DBCC, 0, 1,
+			      len);
+
+	ret = rtw89_h2c_tx(rtwdev, skb, false);
+	if (ret) {
+		rtw89_err(rtwdev, "failed to send h2c\n");
+		goto fail;
+	}
+
+	return 0;
+fail:
+	dev_kfree_skb_any(skb);
+
+	return ret;
+}
+
 int rtw89_fw_h2c_macid_pause(struct rtw89_dev *rtwdev, u8 sh, u8 grp,
 			     bool pause)
 {
@@ -3451,6 +3601,8 @@ static bool rtw89_fw_c2h_chk_atomic(struct rtw89_dev *rtwdev,
 		return false;
 	case RTW89_C2H_CAT_MAC:
 		return rtw89_mac_c2h_chk_atomic(rtwdev, class, func);
+	case RTW89_C2H_CAT_OUTSRC:
+		return rtw89_phy_c2h_chk_atomic(rtwdev, class, func);
 	}
 }
 
@@ -3867,6 +4019,8 @@ static void rtw89_hw_scan_add_chan(struct rtw89_dev *rtwdev, int chan_type,
 			if (info->channel_6ghz &&
 			    ch_info->pri_ch != info->channel_6ghz)
 				continue;
+			else if (info->channel_6ghz && probe_count != 0)
+				ch_info->period += RTW89_CHANNEL_TIME_6G;
 			ch_info->pkt_id[probe_count++] = info->id;
 			if (probe_count >= RTW89_SCANOFLD_MAX_SSID)
 				break;
@@ -4043,6 +4197,7 @@ void rtw89_hw_scan_complete(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif,
 	rtw89_core_scan_complete(rtwdev, vif, true);
 	ieee80211_scan_completed(rtwdev->hw, &info);
 	ieee80211_wake_queues(rtwdev->hw);
+	rtw89_mac_enable_beacon_for_ap_vifs(rtwdev, true);
 
 	rtw89_release_pkt_list(rtwdev);
 	rtwvif = (struct rtw89_vif *)vif->drv_priv;
@@ -4060,6 +4215,19 @@ void rtw89_hw_scan_abort(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif)
 	rtw89_hw_scan_complete(rtwdev, vif, true);
 }
 
+static bool rtw89_is_any_vif_connected_or_connecting(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_vif *rtwvif;
+
+	rtw89_for_each_rtwvif(rtwdev, rtwvif) {
+		/* This variable implies connected or during attempt to connect */
+		if (!is_zero_ether_addr(rtwvif->bssid))
+			return true;
+	}
+
+	return false;
+}
+
 int rtw89_hw_scan_offload(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif,
 			  bool enable)
 {
@@ -4072,8 +4240,7 @@ int rtw89_hw_scan_offload(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif,
 	if (!rtwvif)
 		return -EINVAL;
 
-	/* This variable implies connected or during attempt to connect */
-	connected = !is_zero_ether_addr(rtwvif->bssid);
+	connected = rtw89_is_any_vif_connected_or_connecting(rtwdev);
 	opt.enable = enable;
 	opt.target_ch_mode = connected;
 	if (enable) {
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index d4db9ab0b5e8..01016588b1fc 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -1685,6 +1685,12 @@ static inline void SET_JOININFO_SELF_ROLE(void *h2c, u32 val)
 	le32p_replace_bits((__le32 *)h2c, val, GENMASK(31, 30));
 }
 
+struct rtw89_h2c_notify_dbcc {
+	__le32 w0;
+} __packed;
+
+#define RTW89_H2C_NOTIFY_DBCC_EN BIT(0)
+
 static inline void SET_GENERAL_PKT_MACID(void *h2c, u32 val)
 {
 	le32p_replace_bits((__le32 *)h2c, val, GENMASK(7, 0));
@@ -3426,6 +3432,8 @@ enum rtw89_fw_element_id {
 	RTW89_FW_ELEMENT_ID_TXPWR_LMT_RU_6GHZ = 15,
 	RTW89_FW_ELEMENT_ID_TX_SHAPE_LMT = 16,
 	RTW89_FW_ELEMENT_ID_TX_SHAPE_LMT_RU = 17,
+	RTW89_FW_ELEMENT_ID_TXPWR_TRK = 18,
+	RTW89_FW_ELEMENT_ID_RFKLOG_FMT = 19,
 
 	RTW89_FW_ELEMENT_ID_NUM,
 };
@@ -3446,6 +3454,7 @@ enum rtw89_fw_element_id {
 					     BIT(RTW89_FW_ELEMENT_ID_RADIO_A) | \
 					     BIT(RTW89_FW_ELEMENT_ID_RADIO_B) | \
 					     BIT(RTW89_FW_ELEMENT_ID_RF_NCTL) | \
+					     BIT(RTW89_FW_ELEMENT_ID_TXPWR_TRK) | \
 					     BITS_OF_RTW89_TXPWR_FW_ELEMENTS)
 
 struct __rtw89_fw_txpwr_element {
@@ -3457,6 +3466,59 @@ struct __rtw89_fw_txpwr_element {
 	u8 content[];
 } __packed;
 
+enum rtw89_fw_txpwr_trk_type {
+	__RTW89_FW_TXPWR_TRK_TYPE_6GHZ_START = 0,
+	RTW89_FW_TXPWR_TRK_TYPE_6GB_N = 0,
+	RTW89_FW_TXPWR_TRK_TYPE_6GB_P = 1,
+	RTW89_FW_TXPWR_TRK_TYPE_6GA_N = 2,
+	RTW89_FW_TXPWR_TRK_TYPE_6GA_P = 3,
+	__RTW89_FW_TXPWR_TRK_TYPE_6GHZ_MAX = 3,
+
+	__RTW89_FW_TXPWR_TRK_TYPE_5GHZ_START = 4,
+	RTW89_FW_TXPWR_TRK_TYPE_5GB_N = 4,
+	RTW89_FW_TXPWR_TRK_TYPE_5GB_P = 5,
+	RTW89_FW_TXPWR_TRK_TYPE_5GA_N = 6,
+	RTW89_FW_TXPWR_TRK_TYPE_5GA_P = 7,
+	__RTW89_FW_TXPWR_TRK_TYPE_5GHZ_MAX = 7,
+
+	__RTW89_FW_TXPWR_TRK_TYPE_2GHZ_START = 8,
+	RTW89_FW_TXPWR_TRK_TYPE_2GB_N = 8,
+	RTW89_FW_TXPWR_TRK_TYPE_2GB_P = 9,
+	RTW89_FW_TXPWR_TRK_TYPE_2GA_N = 10,
+	RTW89_FW_TXPWR_TRK_TYPE_2GA_P = 11,
+	RTW89_FW_TXPWR_TRK_TYPE_2G_CCK_B_N = 12,
+	RTW89_FW_TXPWR_TRK_TYPE_2G_CCK_B_P = 13,
+	RTW89_FW_TXPWR_TRK_TYPE_2G_CCK_A_N = 14,
+	RTW89_FW_TXPWR_TRK_TYPE_2G_CCK_A_P = 15,
+	__RTW89_FW_TXPWR_TRK_TYPE_2GHZ_MAX = 15,
+
+	RTW89_FW_TXPWR_TRK_TYPE_NR,
+};
+
+struct rtw89_fw_txpwr_track_cfg {
+	const s8 (*delta[RTW89_FW_TXPWR_TRK_TYPE_NR])[DELTA_SWINGIDX_SIZE];
+};
+
+#define RTW89_DEFAULT_NEEDED_FW_TXPWR_TRK_6GHZ \
+	(BIT(RTW89_FW_TXPWR_TRK_TYPE_6GB_N) | \
+	 BIT(RTW89_FW_TXPWR_TRK_TYPE_6GB_P) | \
+	 BIT(RTW89_FW_TXPWR_TRK_TYPE_6GA_N) | \
+	 BIT(RTW89_FW_TXPWR_TRK_TYPE_6GA_P))
+#define RTW89_DEFAULT_NEEDED_FW_TXPWR_TRK_5GHZ \
+	(BIT(RTW89_FW_TXPWR_TRK_TYPE_5GB_N) | \
+	 BIT(RTW89_FW_TXPWR_TRK_TYPE_5GB_P) | \
+	 BIT(RTW89_FW_TXPWR_TRK_TYPE_5GA_N) | \
+	 BIT(RTW89_FW_TXPWR_TRK_TYPE_5GA_P))
+#define RTW89_DEFAULT_NEEDED_FW_TXPWR_TRK_2GHZ \
+	(BIT(RTW89_FW_TXPWR_TRK_TYPE_2GB_N) | \
+	 BIT(RTW89_FW_TXPWR_TRK_TYPE_2GB_P) | \
+	 BIT(RTW89_FW_TXPWR_TRK_TYPE_2GA_N) | \
+	 BIT(RTW89_FW_TXPWR_TRK_TYPE_2GA_P) | \
+	 BIT(RTW89_FW_TXPWR_TRK_TYPE_2G_CCK_B_N) | \
+	 BIT(RTW89_FW_TXPWR_TRK_TYPE_2G_CCK_B_P) | \
+	 BIT(RTW89_FW_TXPWR_TRK_TYPE_2G_CCK_A_N) | \
+	 BIT(RTW89_FW_TXPWR_TRK_TYPE_2G_CCK_A_P))
+
 struct rtw89_fw_element_hdr {
 	__le32 id; /* enum rtw89_fw_element_id */
 	__le32 size; /* exclude header size */
@@ -3477,6 +3539,23 @@ struct rtw89_fw_element_hdr {
 				__le32 data;
 			} __packed regs[];
 		} __packed reg2;
+		struct {
+			u8 cv;
+			u8 priv[7];
+			u8 contents[];
+		} __packed bbmcu;
+		struct {
+			__le32 bitmap; /* bitmap of enum rtw89_fw_txpwr_trk_type */
+			__le32 rsvd;
+			s8 contents[][DELTA_SWINGIDX_SIZE];
+		} __packed txpwr_trk;
+		struct {
+			u8 nr;
+			u8 rsvd[3];
+			u8 rfk_id; /* enum rtw89_phy_c2h_rfk_log_func */
+			u8 rsvd1[3];
+			__le16 offset[];
+		} __packed rfk_log_fmt;
 		struct __rtw89_fw_txpwr_element txpwr;
 	} __packed u;
 } __packed;
@@ -3577,6 +3656,7 @@ struct rtw89_fw_h2c_rf_reg_info {
 #define H2C_CL_MAC_MEDIA_RPT		0x8
 #define H2C_FUNC_MAC_JOININFO		0x0
 #define H2C_FUNC_MAC_FWROLE_MAINTAIN	0x4
+#define H2C_FUNC_NOTIFY_DBCC		0x5
 
 /* CLASS 9 - FW offload */
 #define H2C_CL_MAC_FW_OFLD		0x9
@@ -3649,9 +3729,78 @@ struct rtw89_fw_h2c_rf_get_mccch {
 	__le32 current_band_type;
 } __packed;
 
-#define RTW89_FW_RSVD_PLE_SIZE 0x800
+enum rtw89_rf_log_type {
+	RTW89_RF_RUN_LOG = 0,
+	RTW89_RF_RPT_LOG = 1,
+};
 
-#define RTW89_WCPU_BASE_MASK GENMASK(27, 0)
+struct rtw89_c2h_rf_log_hdr {
+	u8 type; /* enum rtw89_rf_log_type */
+	__le16 len;
+	u8 content[];
+} __packed;
+
+struct rtw89_c2h_rf_run_log {
+	__le32 fmt_idx;
+	__le32 arg[4];
+} __packed;
+
+struct rtw89_c2h_rf_dpk_rpt_log {
+	u8 ver;
+	u8 idx[2];
+	u8 band[2];
+	u8 bw[2];
+	u8 ch[2];
+	u8 path_ok[2];
+	u8 txagc[2];
+	u8 ther[2];
+	u8 gs[2];
+	u8 dc_i[4];
+	u8 dc_q[4];
+	u8 corr_val[2];
+	u8 corr_idx[2];
+	u8 is_timeout[2];
+	u8 rxbb_ov[2];
+	u8 rsvd;
+} __packed;
+
+struct rtw89_c2h_rf_dack_rpt_log {
+	u8 fwdack_ver;
+	u8 fwdack_rpt_ver;
+	u8 msbk_d[2][2][16];
+	u8 dadck_d[2][2];
+	u8 cdack_d[2][2][2];
+	__le16 addck2_d[2][2][2];
+	u8 adgaink_d[2][2];
+	__le16 biask_d[2][2];
+	u8 addck_timeout;
+	u8 cdack_timeout;
+	u8 dadck_timeout;
+	u8 msbk_timeout;
+	u8 adgaink_timeout;
+	u8 dack_fail;
+} __packed;
+
+struct rtw89_c2h_rf_rxdck_rpt_log {
+	u8 ver;
+	u8 band[2];
+	u8 bw[2];
+	u8 ch[2];
+	u8 timeout[2];
+} __packed;
+
+struct rtw89_c2h_rf_txgapk_rpt_log {
+	__le32 r0x8010[2];
+	__le32 chk_cnt;
+	u8 track_d[2][17];
+	u8 power_d[2][17];
+	u8 is_txgapk_ok;
+	u8 chk_id;
+	u8 ver;
+	u8 rsv1;
+} __packed;
+
+#define RTW89_FW_RSVD_PLE_SIZE 0x800
 
 #define RTW89_FW_BACKTRACE_INFO_SIZE 8
 #define RTW89_VALID_FW_BACKTRACE_SIZE(_size) \
@@ -3704,6 +3853,7 @@ int rtw89_fw_h2c_role_maintain(struct rtw89_dev *rtwdev,
 			       enum rtw89_upd_mode upd_mode);
 int rtw89_fw_h2c_join_info(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 			   struct rtw89_sta *rtwsta, bool dis_conn);
+int rtw89_fw_h2c_notify_dbcc(struct rtw89_dev *rtwdev, bool en);
 int rtw89_fw_h2c_macid_pause(struct rtw89_dev *rtwdev, u8 sh, u8 grp,
 			     bool pause);
 int rtw89_fw_h2c_set_edca(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index 0c5768f41d55..c485ef2cc3d3 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -5,6 +5,7 @@
 #include "cam.h"
 #include "chan.h"
 #include "debug.h"
+#include "efuse.h"
 #include "fw.h"
 #include "mac.h"
 #include "pci.h"
@@ -56,8 +57,8 @@ static u32 rtw89_mac_mem_read(struct rtw89_dev *rtwdev, u32 offset,
 	return rtw89_read32(rtwdev, mac->indir_access_addr);
 }
 
-int rtw89_mac_check_mac_en(struct rtw89_dev *rtwdev, u8 mac_idx,
-			   enum rtw89_mac_hwmod_sel sel)
+static int rtw89_mac_check_mac_en_ax(struct rtw89_dev *rtwdev, u8 mac_idx,
+				     enum rtw89_mac_hwmod_sel sel)
 {
 	u32 val, r_val;
 
@@ -112,8 +113,7 @@ int rtw89_mac_read_lte(struct rtw89_dev *rtwdev, const u32 offset, u32 *val)
 	return ret;
 }
 
-static
-int dle_dfi_ctrl(struct rtw89_dev *rtwdev, struct rtw89_mac_dle_dfi_ctrl *ctrl)
+int rtw89_mac_dle_dfi_cfg(struct rtw89_dev *rtwdev, struct rtw89_mac_dle_dfi_ctrl *ctrl)
 {
 	u32 ctrl_reg, data_reg, ctrl_data;
 	u32 val;
@@ -153,8 +153,8 @@ int dle_dfi_ctrl(struct rtw89_dev *rtwdev, struct rtw89_mac_dle_dfi_ctrl *ctrl)
 	return 0;
 }
 
-static int dle_dfi_quota(struct rtw89_dev *rtwdev,
-			 struct rtw89_mac_dle_dfi_quota *quota)
+int rtw89_mac_dle_dfi_quota_cfg(struct rtw89_dev *rtwdev,
+				struct rtw89_mac_dle_dfi_quota *quota)
 {
 	struct rtw89_mac_dle_dfi_ctrl ctrl;
 	int ret;
@@ -162,9 +162,9 @@ static int dle_dfi_quota(struct rtw89_dev *rtwdev,
 	ctrl.type = quota->dle_type;
 	ctrl.target = DLE_DFI_TYPE_QUOTA;
 	ctrl.addr = quota->qtaid;
-	ret = dle_dfi_ctrl(rtwdev, &ctrl);
+	ret = rtw89_mac_dle_dfi_cfg(rtwdev, &ctrl);
 	if (ret) {
-		rtw89_warn(rtwdev, "[ERR]dle_dfi_ctrl %d\n", ret);
+		rtw89_warn(rtwdev, "[ERR] dle dfi quota %d\n", ret);
 		return ret;
 	}
 
@@ -173,8 +173,8 @@ static int dle_dfi_quota(struct rtw89_dev *rtwdev,
 	return 0;
 }
 
-static int dle_dfi_qempty(struct rtw89_dev *rtwdev,
-			  struct rtw89_mac_dle_dfi_qempty *qempty)
+int rtw89_mac_dle_dfi_qempty_cfg(struct rtw89_dev *rtwdev,
+				 struct rtw89_mac_dle_dfi_qempty *qempty)
 {
 	struct rtw89_mac_dle_dfi_ctrl ctrl;
 	u32 ret;
@@ -182,9 +182,9 @@ static int dle_dfi_qempty(struct rtw89_dev *rtwdev,
 	ctrl.type = qempty->dle_type;
 	ctrl.target = DLE_DFI_TYPE_QEMPTY;
 	ctrl.addr = qempty->grpsel;
-	ret = dle_dfi_ctrl(rtwdev, &ctrl);
+	ret = rtw89_mac_dle_dfi_cfg(rtwdev, &ctrl);
 	if (ret) {
-		rtw89_warn(rtwdev, "[ERR]dle_dfi_ctrl %d\n", ret);
+		rtw89_warn(rtwdev, "[ERR] dle dfi qempty %d\n", ret);
 		return ret;
 	}
 
@@ -192,7 +192,7 @@ static int dle_dfi_qempty(struct rtw89_dev *rtwdev,
 	return 0;
 }
 
-static void dump_err_status_dispatcher(struct rtw89_dev *rtwdev)
+static void dump_err_status_dispatcher_ax(struct rtw89_dev *rtwdev)
 {
 	rtw89_info(rtwdev, "R_AX_HOST_DISPATCHER_ALWAYS_IMR=0x%08x ",
 		   rtw89_read32(rtwdev, R_AX_HOST_DISPATCHER_ERR_IMR));
@@ -208,7 +208,7 @@ static void dump_err_status_dispatcher(struct rtw89_dev *rtwdev)
 		   rtw89_read32(rtwdev, R_AX_OTHER_DISPATCHER_ERR_ISR));
 }
 
-static void rtw89_mac_dump_qta_lost(struct rtw89_dev *rtwdev)
+static void rtw89_mac_dump_qta_lost_ax(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_mac_dle_dfi_qempty qempty;
 	struct rtw89_mac_dle_dfi_quota quota;
@@ -219,7 +219,7 @@ static void rtw89_mac_dump_qta_lost(struct rtw89_dev *rtwdev)
 	qempty.dle_type = DLE_CTRL_TYPE_PLE;
 	qempty.grpsel = 0;
 	qempty.qempty = ~(u32)0;
-	ret = dle_dfi_qempty(rtwdev, &qempty);
+	ret = rtw89_mac_dle_dfi_qempty_cfg(rtwdev, &qempty);
 	if (ret)
 		rtw89_warn(rtwdev, "%s: query DLE fail\n", __func__);
 	else
@@ -231,19 +231,19 @@ static void rtw89_mac_dump_qta_lost(struct rtw89_dev *rtwdev)
 		ctrl.type = DLE_CTRL_TYPE_PLE;
 		ctrl.target = DLE_DFI_TYPE_QLNKTBL;
 		ctrl.addr = (QLNKTBL_ADDR_INFO_SEL_0 ? QLNKTBL_ADDR_INFO_SEL : 0) |
-			    FIELD_PREP(QLNKTBL_ADDR_TBL_IDX_MASK, i);
-		ret = dle_dfi_ctrl(rtwdev, &ctrl);
+			    u32_encode_bits(i, QLNKTBL_ADDR_TBL_IDX_MASK);
+		ret = rtw89_mac_dle_dfi_cfg(rtwdev, &ctrl);
 		if (ret)
 			rtw89_warn(rtwdev, "%s: query DLE fail\n", __func__);
 		else
-			rtw89_info(rtwdev, "qidx%d pktcnt = %ld\n", i,
-				   FIELD_GET(QLNKTBL_DATA_SEL1_PKT_CNT_MASK,
-					     ctrl.out_data));
+			rtw89_info(rtwdev, "qidx%d pktcnt = %d\n", i,
+				   u32_get_bits(ctrl.out_data,
+						QLNKTBL_DATA_SEL1_PKT_CNT_MASK));
 	}
 
 	quota.dle_type = DLE_CTRL_TYPE_PLE;
 	quota.qtaid = 6;
-	ret = dle_dfi_quota(rtwdev, &quota);
+	ret = rtw89_mac_dle_dfi_quota_cfg(rtwdev, &quota);
 	if (ret)
 		rtw89_warn(rtwdev, "%s: query DLE fail\n", __func__);
 	else
@@ -251,33 +251,74 @@ static void rtw89_mac_dump_qta_lost(struct rtw89_dev *rtwdev)
 			   quota.rsv_pgnum, quota.use_pgnum);
 
 	val = rtw89_read32(rtwdev, R_AX_PLE_QTA6_CFG);
-	rtw89_info(rtwdev, "[PLE][CMAC0_RX]min_pgnum=0x%lx\n",
-		   FIELD_GET(B_AX_PLE_Q6_MIN_SIZE_MASK, val));
-	rtw89_info(rtwdev, "[PLE][CMAC0_RX]max_pgnum=0x%lx\n",
-		   FIELD_GET(B_AX_PLE_Q6_MAX_SIZE_MASK, val));
+	rtw89_info(rtwdev, "[PLE][CMAC0_RX]min_pgnum=0x%x\n",
+		   u32_get_bits(val, B_AX_PLE_Q6_MIN_SIZE_MASK));
+	rtw89_info(rtwdev, "[PLE][CMAC0_RX]max_pgnum=0x%x\n",
+		   u32_get_bits(val, B_AX_PLE_Q6_MAX_SIZE_MASK));
+	val = rtw89_read32(rtwdev, R_AX_RX_FLTR_OPT);
+	rtw89_info(rtwdev, "[PLE][CMAC0_RX]B_AX_RX_MPDU_MAX_LEN=0x%x\n",
+		   u32_get_bits(val, B_AX_RX_MPDU_MAX_LEN_MASK));
+	rtw89_info(rtwdev, "R_AX_RSP_CHK_SIG=0x%08x\n",
+		   rtw89_read32(rtwdev, R_AX_RSP_CHK_SIG));
+	rtw89_info(rtwdev, "R_AX_TRXPTCL_RESP_0=0x%08x\n",
+		   rtw89_read32(rtwdev, R_AX_TRXPTCL_RESP_0));
+	rtw89_info(rtwdev, "R_AX_CCA_CONTROL=0x%08x\n",
+		   rtw89_read32(rtwdev, R_AX_CCA_CONTROL));
+
+	if (!rtw89_mac_check_mac_en(rtwdev, RTW89_MAC_1, RTW89_CMAC_SEL)) {
+		quota.dle_type = DLE_CTRL_TYPE_PLE;
+		quota.qtaid = 7;
+		ret = rtw89_mac_dle_dfi_quota_cfg(rtwdev, &quota);
+		if (ret)
+			rtw89_warn(rtwdev, "%s: query DLE fail\n", __func__);
+		else
+			rtw89_info(rtwdev, "quota7 rsv/use: 0x%x/0x%x\n",
+				   quota.rsv_pgnum, quota.use_pgnum);
+
+		val = rtw89_read32(rtwdev, R_AX_PLE_QTA7_CFG);
+		rtw89_info(rtwdev, "[PLE][CMAC1_RX]min_pgnum=0x%x\n",
+			   u32_get_bits(val, B_AX_PLE_Q7_MIN_SIZE_MASK));
+		rtw89_info(rtwdev, "[PLE][CMAC1_RX]max_pgnum=0x%x\n",
+			   u32_get_bits(val, B_AX_PLE_Q7_MAX_SIZE_MASK));
+		val = rtw89_read32(rtwdev, R_AX_RX_FLTR_OPT_C1);
+		rtw89_info(rtwdev, "[PLE][CMAC1_RX]B_AX_RX_MPDU_MAX_LEN=0x%x\n",
+			   u32_get_bits(val, B_AX_RX_MPDU_MAX_LEN_MASK));
+		rtw89_info(rtwdev, "R_AX_RSP_CHK_SIG_C1=0x%08x\n",
+			   rtw89_read32(rtwdev, R_AX_RSP_CHK_SIG_C1));
+		rtw89_info(rtwdev, "R_AX_TRXPTCL_RESP_0_C1=0x%08x\n",
+			   rtw89_read32(rtwdev, R_AX_TRXPTCL_RESP_0_C1));
+		rtw89_info(rtwdev, "R_AX_CCA_CONTROL_C1=0x%08x\n",
+			   rtw89_read32(rtwdev, R_AX_CCA_CONTROL_C1));
+	}
+
+	rtw89_info(rtwdev, "R_AX_DLE_EMPTY0=0x%08x\n",
+		   rtw89_read32(rtwdev, R_AX_DLE_EMPTY0));
+	rtw89_info(rtwdev, "R_AX_DLE_EMPTY1=0x%08x\n",
+		   rtw89_read32(rtwdev, R_AX_DLE_EMPTY1));
 
-	dump_err_status_dispatcher(rtwdev);
+	dump_err_status_dispatcher_ax(rtwdev);
 }
 
-static void rtw89_mac_dump_l0_to_l1(struct rtw89_dev *rtwdev,
-				    enum mac_ax_err_info err)
+void rtw89_mac_dump_l0_to_l1(struct rtw89_dev *rtwdev,
+			     enum mac_ax_err_info err)
 {
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	u32 dbg, event;
 
 	dbg = rtw89_read32(rtwdev, R_AX_SER_DBG_INFO);
-	event = FIELD_GET(B_AX_L0_TO_L1_EVENT_MASK, dbg);
+	event = u32_get_bits(dbg, B_AX_L0_TO_L1_EVENT_MASK);
 
 	switch (event) {
 	case MAC_AX_L0_TO_L1_RX_QTA_LOST:
 		rtw89_info(rtwdev, "quota lost!\n");
-		rtw89_mac_dump_qta_lost(rtwdev);
+		mac->dump_qta_lost(rtwdev);
 		break;
 	default:
 		break;
 	}
 }
 
-static void rtw89_mac_dump_dmac_err_status(struct rtw89_dev *rtwdev)
+void rtw89_mac_dump_dmac_err_status(struct rtw89_dev *rtwdev)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	u32 dmac_err;
@@ -357,6 +398,21 @@ static void rtw89_mac_dump_dmac_err_status(struct rtw89_dev *rtwdev)
 				rtw89_info(rtwdev, "sel=%x,R_AX_SEC_DEBUG2=0x%08x\n",
 					   i, rtw89_read32(rtwdev, R_AX_SEC_DEBUG2));
 			}
+		} else if (chip->chip_id == RTL8922A) {
+			rtw89_info(rtwdev, "R_BE_SEC_ERROR_FLAG=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_SEC_ERROR_FLAG));
+			rtw89_info(rtwdev, "R_BE_SEC_ERROR_IMR=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_SEC_ERROR_IMR));
+			rtw89_info(rtwdev, "R_BE_SEC_ENG_CTRL=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_SEC_ENG_CTRL));
+			rtw89_info(rtwdev, "R_BE_SEC_MPDU_PROC=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_SEC_MPDU_PROC));
+			rtw89_info(rtwdev, "R_BE_SEC_CAM_ACCESS=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_SEC_CAM_ACCESS));
+			rtw89_info(rtwdev, "R_BE_SEC_CAM_RDATA=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_SEC_CAM_RDATA));
+			rtw89_info(rtwdev, "R_BE_SEC_DEBUG2=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_SEC_DEBUG2));
 		} else {
 			rtw89_info(rtwdev, "R_AX_SEC_ERR_IMR_ISR=0x%08x\n",
 				   rtw89_read32(rtwdev, R_AX_SEC_DEBUG));
@@ -393,10 +449,17 @@ static void rtw89_mac_dump_dmac_err_status(struct rtw89_dev *rtwdev)
 	}
 
 	if (dmac_err & B_AX_STA_SCHEDULER_ERR_FLAG) {
-		rtw89_info(rtwdev, "R_AX_STA_SCHEDULER_ERR_IMR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_STA_SCHEDULER_ERR_IMR));
-		rtw89_info(rtwdev, "R_AX_STA_SCHEDULER_ERR_ISR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_STA_SCHEDULER_ERR_ISR));
+		if (chip->chip_id == RTL8922A) {
+			rtw89_info(rtwdev, "R_BE_INTERRUPT_MASK_REG=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_INTERRUPT_MASK_REG));
+			rtw89_info(rtwdev, "R_BE_INTERRUPT_STS_REG=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_INTERRUPT_STS_REG));
+		} else {
+			rtw89_info(rtwdev, "R_AX_STA_SCHEDULER_ERR_IMR=0x%08x\n",
+				   rtw89_read32(rtwdev, R_AX_STA_SCHEDULER_ERR_IMR));
+			rtw89_info(rtwdev, "R_AX_STA_SCHEDULER_ERR_ISR=0x%08x\n",
+				   rtw89_read32(rtwdev, R_AX_STA_SCHEDULER_ERR_ISR));
+		}
 	}
 
 	if (dmac_err & B_AX_WDE_DLE_ERR_FLAG) {
@@ -411,7 +474,7 @@ static void rtw89_mac_dump_dmac_err_status(struct rtw89_dev *rtwdev)
 	}
 
 	if (dmac_err & B_AX_TXPKTCTRL_ERR_FLAG) {
-		if (chip->chip_id == RTL8852C) {
+		if (chip->chip_id == RTL8852C || chip->chip_id == RTL8922A) {
 			rtw89_info(rtwdev, "R_AX_TXPKTCTL_B0_ERRFLAG_IMR=0x%08x\n",
 				   rtw89_read32(rtwdev, R_AX_TXPKTCTL_B0_ERRFLAG_IMR));
 			rtw89_info(rtwdev, "R_AX_TXPKTCTL_B0_ERRFLAG_ISR=0x%08x\n",
@@ -443,30 +506,41 @@ static void rtw89_mac_dump_dmac_err_status(struct rtw89_dev *rtwdev)
 			   rtw89_read32(rtwdev, R_AX_WD_CPUQ_OP_1));
 		rtw89_info(rtwdev, "R_AX_WD_CPUQ_OP_2=0x%08x\n",
 			   rtw89_read32(rtwdev, R_AX_WD_CPUQ_OP_2));
-		rtw89_info(rtwdev, "R_AX_WD_CPUQ_OP_STATUS=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_WD_CPUQ_OP_STATUS));
 		rtw89_info(rtwdev, "R_AX_PL_CPUQ_OP_0=0x%08x\n",
 			   rtw89_read32(rtwdev, R_AX_PL_CPUQ_OP_0));
 		rtw89_info(rtwdev, "R_AX_PL_CPUQ_OP_1=0x%08x\n",
 			   rtw89_read32(rtwdev, R_AX_PL_CPUQ_OP_1));
 		rtw89_info(rtwdev, "R_AX_PL_CPUQ_OP_2=0x%08x\n",
 			   rtw89_read32(rtwdev, R_AX_PL_CPUQ_OP_2));
-		rtw89_info(rtwdev, "R_AX_PL_CPUQ_OP_STATUS=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_PL_CPUQ_OP_STATUS));
-		if (chip->chip_id == RTL8852C) {
-			rtw89_info(rtwdev, "R_AX_RX_CTRL0=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_RX_CTRL0));
-			rtw89_info(rtwdev, "R_AX_RX_CTRL1=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_RX_CTRL1));
-			rtw89_info(rtwdev, "R_AX_RX_CTRL2=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_RX_CTRL2));
+		if (chip->chip_id == RTL8922A) {
+			rtw89_info(rtwdev, "R_BE_WD_CPUQ_OP_3=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_WD_CPUQ_OP_3));
+			rtw89_info(rtwdev, "R_BE_WD_CPUQ_OP_STATUS=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_WD_CPUQ_OP_STATUS));
+			rtw89_info(rtwdev, "R_BE_PLE_CPUQ_OP_3=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_PL_CPUQ_OP_3));
+			rtw89_info(rtwdev, "R_BE_PL_CPUQ_OP_STATUS=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_PL_CPUQ_OP_STATUS));
 		} else {
-			rtw89_info(rtwdev, "R_AX_RXDMA_PKT_INFO_0=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_RXDMA_PKT_INFO_0));
-			rtw89_info(rtwdev, "R_AX_RXDMA_PKT_INFO_1=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_RXDMA_PKT_INFO_1));
-			rtw89_info(rtwdev, "R_AX_RXDMA_PKT_INFO_2=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_RXDMA_PKT_INFO_2));
+			rtw89_info(rtwdev, "R_AX_WD_CPUQ_OP_STATUS=0x%08x\n",
+				   rtw89_read32(rtwdev, R_AX_WD_CPUQ_OP_STATUS));
+			rtw89_info(rtwdev, "R_AX_PL_CPUQ_OP_STATUS=0x%08x\n",
+				   rtw89_read32(rtwdev, R_AX_PL_CPUQ_OP_STATUS));
+			if (chip->chip_id == RTL8852C) {
+				rtw89_info(rtwdev, "R_AX_RX_CTRL0=0x%08x\n",
+					   rtw89_read32(rtwdev, R_AX_RX_CTRL0));
+				rtw89_info(rtwdev, "R_AX_RX_CTRL1=0x%08x\n",
+					   rtw89_read32(rtwdev, R_AX_RX_CTRL1));
+				rtw89_info(rtwdev, "R_AX_RX_CTRL2=0x%08x\n",
+					   rtw89_read32(rtwdev, R_AX_RX_CTRL2));
+			} else {
+				rtw89_info(rtwdev, "R_AX_RXDMA_PKT_INFO_0=0x%08x\n",
+					   rtw89_read32(rtwdev, R_AX_RXDMA_PKT_INFO_0));
+				rtw89_info(rtwdev, "R_AX_RXDMA_PKT_INFO_1=0x%08x\n",
+					   rtw89_read32(rtwdev, R_AX_RXDMA_PKT_INFO_1));
+				rtw89_info(rtwdev, "R_AX_RXDMA_PKT_INFO_2=0x%08x\n",
+					   rtw89_read32(rtwdev, R_AX_RXDMA_PKT_INFO_2));
+			}
 		}
 	}
 
@@ -478,22 +552,37 @@ static void rtw89_mac_dump_dmac_err_status(struct rtw89_dev *rtwdev)
 	}
 
 	if (dmac_err & B_AX_DISPATCH_ERR_FLAG) {
-		rtw89_info(rtwdev, "R_AX_HOST_DISPATCHER_ERR_IMR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_HOST_DISPATCHER_ERR_IMR));
-		rtw89_info(rtwdev, "R_AX_HOST_DISPATCHER_ERR_ISR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_HOST_DISPATCHER_ERR_ISR));
-		rtw89_info(rtwdev, "R_AX_CPU_DISPATCHER_ERR_IMR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_CPU_DISPATCHER_ERR_IMR));
-		rtw89_info(rtwdev, "R_AX_CPU_DISPATCHER_ERR_ISR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_CPU_DISPATCHER_ERR_ISR));
-		rtw89_info(rtwdev, "R_AX_OTHER_DISPATCHER_ERR_IMR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_OTHER_DISPATCHER_ERR_IMR));
-		rtw89_info(rtwdev, "R_AX_OTHER_DISPATCHER_ERR_ISR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_OTHER_DISPATCHER_ERR_ISR));
+		if (chip->chip_id == RTL8922A) {
+			rtw89_info(rtwdev, "R_BE_DISP_HOST_IMR=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_DISP_HOST_IMR));
+			rtw89_info(rtwdev, "R_BE_DISP_ERROR_ISR1=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_DISP_ERROR_ISR1));
+			rtw89_info(rtwdev, "R_BE_DISP_CPU_IMR=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_DISP_CPU_IMR));
+			rtw89_info(rtwdev, "R_BE_DISP_ERROR_ISR2=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_DISP_ERROR_ISR2));
+			rtw89_info(rtwdev, "R_BE_DISP_OTHER_IMR=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_DISP_OTHER_IMR));
+			rtw89_info(rtwdev, "R_BE_DISP_ERROR_ISR0=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_DISP_ERROR_ISR0));
+		} else {
+			rtw89_info(rtwdev, "R_AX_HOST_DISPATCHER_ERR_IMR=0x%08x\n",
+				   rtw89_read32(rtwdev, R_AX_HOST_DISPATCHER_ERR_IMR));
+			rtw89_info(rtwdev, "R_AX_HOST_DISPATCHER_ERR_ISR=0x%08x\n",
+				   rtw89_read32(rtwdev, R_AX_HOST_DISPATCHER_ERR_ISR));
+			rtw89_info(rtwdev, "R_AX_CPU_DISPATCHER_ERR_IMR=0x%08x\n",
+				   rtw89_read32(rtwdev, R_AX_CPU_DISPATCHER_ERR_IMR));
+			rtw89_info(rtwdev, "R_AX_CPU_DISPATCHER_ERR_ISR=0x%08x\n",
+				   rtw89_read32(rtwdev, R_AX_CPU_DISPATCHER_ERR_ISR));
+			rtw89_info(rtwdev, "R_AX_OTHER_DISPATCHER_ERR_IMR=0x%08x\n",
+				   rtw89_read32(rtwdev, R_AX_OTHER_DISPATCHER_ERR_IMR));
+			rtw89_info(rtwdev, "R_AX_OTHER_DISPATCHER_ERR_ISR=0x%08x\n",
+				   rtw89_read32(rtwdev, R_AX_OTHER_DISPATCHER_ERR_ISR));
+		}
 	}
 
 	if (dmac_err & B_AX_BBRPT_ERR_FLAG) {
-		if (chip->chip_id == RTL8852C) {
+		if (chip->chip_id == RTL8852C || chip->chip_id == RTL8922A) {
 			rtw89_info(rtwdev, "R_AX_BBRPT_COM_ERR_IMR=0x%08x\n",
 				   rtw89_read32(rtwdev, R_AX_BBRPT_COM_ERR_IMR));
 			rtw89_info(rtwdev, "R_AX_BBRPT_COM_ERR_ISR=0x%08x\n",
@@ -518,18 +607,54 @@ static void rtw89_mac_dump_dmac_err_status(struct rtw89_dev *rtwdev)
 			rtw89_info(rtwdev, "R_AX_BBRPT_DFS_ERR_ISR=0x%08x\n",
 				   rtw89_read32(rtwdev, R_AX_BBRPT_DFS_ERR_ISR));
 		}
+		if (chip->chip_id == RTL8922A) {
+			rtw89_info(rtwdev, "R_BE_LA_ERRFLAG_IMR=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_LA_ERRFLAG_IMR));
+			rtw89_info(rtwdev, "R_BE_LA_ERRFLAG_ISR=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_LA_ERRFLAG_ISR));
+		}
+	}
+
+	if (dmac_err & B_AX_HAXIDMA_ERR_FLAG) {
+		if (chip->chip_id == RTL8922A) {
+			rtw89_info(rtwdev, "R_BE_HAXI_IDCT_MSK=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_HAXI_IDCT_MSK));
+			rtw89_info(rtwdev, "R_BE_HAXI_IDCT=0x%08x\n",
+				   rtw89_read32(rtwdev, R_BE_HAXI_IDCT));
+		} else if (chip->chip_id == RTL8852C) {
+			rtw89_info(rtwdev, "R_AX_HAXIDMA_ERR_IMR=0x%08x\n",
+				   rtw89_read32(rtwdev, R_AX_HAXI_IDCT_MSK));
+			rtw89_info(rtwdev, "R_AX_HAXIDMA_ERR_ISR=0x%08x\n",
+				   rtw89_read32(rtwdev, R_AX_HAXI_IDCT));
+		}
 	}
 
-	if (dmac_err & B_AX_HAXIDMA_ERR_FLAG && chip->chip_id == RTL8852C) {
-		rtw89_info(rtwdev, "R_AX_HAXIDMA_ERR_IMR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_HAXI_IDCT_MSK));
-		rtw89_info(rtwdev, "R_AX_HAXIDMA_ERR_ISR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_HAXI_IDCT));
+	if (dmac_err & B_BE_P_AXIDMA_ERR_INT) {
+		rtw89_info(rtwdev, "R_BE_PL_AXIDMA_IDCT_MSK=0x%08x\n",
+			   rtw89_mac_mem_read(rtwdev, R_BE_PL_AXIDMA_IDCT_MSK,
+					      RTW89_MAC_MEM_AXIDMA));
+		rtw89_info(rtwdev, "R_BE_PL_AXIDMA_IDCT=0x%08x\n",
+			   rtw89_mac_mem_read(rtwdev, R_BE_PL_AXIDMA_IDCT,
+					      RTW89_MAC_MEM_AXIDMA));
+	}
+
+	if (dmac_err & B_BE_MLO_ERR_INT) {
+		rtw89_info(rtwdev, "R_BE_MLO_ERR_IDCT_IMR=0x%08x\n",
+			   rtw89_read32(rtwdev, R_BE_MLO_ERR_IDCT_IMR));
+		rtw89_info(rtwdev, "R_BE_PKTIN_ERR_ISR=0x%08x\n",
+			   rtw89_read32(rtwdev, R_BE_MLO_ERR_IDCT_ISR));
+	}
+
+	if (dmac_err & B_BE_PLRLS_ERR_INT) {
+		rtw89_info(rtwdev, "R_BE_PLRLS_ERR_IMR=0x%08x\n",
+			   rtw89_read32(rtwdev, R_BE_PLRLS_ERR_IMR));
+		rtw89_info(rtwdev, "R_BE_PLRLS_ERR_ISR=0x%08x\n",
+			   rtw89_read32(rtwdev, R_BE_PLRLS_ERR_ISR));
 	}
 }
 
-static void rtw89_mac_dump_cmac_err_status(struct rtw89_dev *rtwdev,
-					   u8 band)
+static void rtw89_mac_dump_cmac_err_status_ax(struct rtw89_dev *rtwdev,
+					      u8 band)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	u32 offset = 0;
@@ -619,8 +744,8 @@ static void rtw89_mac_dump_cmac_err_status(struct rtw89_dev *rtwdev,
 		   rtw89_read32(rtwdev, R_AX_CMAC_ERR_IMR + offset));
 }
 
-static void rtw89_mac_dump_err_status(struct rtw89_dev *rtwdev,
-				      enum mac_ax_err_info err)
+static void rtw89_mac_dump_err_status_ax(struct rtw89_dev *rtwdev,
+					 enum mac_ax_err_info err)
 {
 	if (err != MAC_AX_ERR_L1_ERR_DMAC &&
 	    err != MAC_AX_ERR_L0_PROMOTE_TO_L1 &&
@@ -632,11 +757,16 @@ static void rtw89_mac_dump_err_status(struct rtw89_dev *rtwdev,
 	rtw89_info(rtwdev, "--->\nerr=0x%x\n", err);
 	rtw89_info(rtwdev, "R_AX_SER_DBG_INFO =0x%08x\n",
 		   rtw89_read32(rtwdev, R_AX_SER_DBG_INFO));
+	rtw89_info(rtwdev, "R_AX_SER_DBG_INFO =0x%08x\n",
+		   rtw89_read32(rtwdev, R_AX_SER_DBG_INFO));
+	rtw89_info(rtwdev, "DBG Counter 1 (R_AX_DRV_FW_HSK_4)=0x%08x\n",
+		   rtw89_read32(rtwdev, R_AX_DRV_FW_HSK_4));
+	rtw89_info(rtwdev, "DBG Counter 2 (R_AX_DRV_FW_HSK_5)=0x%08x\n",
+		   rtw89_read32(rtwdev, R_AX_DRV_FW_HSK_5));
 
 	rtw89_mac_dump_dmac_err_status(rtwdev);
-	rtw89_mac_dump_cmac_err_status(rtwdev, RTW89_MAC_0);
-	if (rtwdev->dbcc_en)
-		rtw89_mac_dump_cmac_err_status(rtwdev, RTW89_MAC_1);
+	rtw89_mac_dump_cmac_err_status_ax(rtwdev, RTW89_MAC_0);
+	rtw89_mac_dump_cmac_err_status_ax(rtwdev, RTW89_MAC_1);
 
 	rtwdev->hci.ops->dump_err_status(rtwdev);
 
@@ -681,6 +811,7 @@ static bool rtw89_mac_suppress_log(struct rtw89_dev *rtwdev, u32 err)
 
 u32 rtw89_mac_get_err_status(struct rtw89_dev *rtwdev)
 {
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	u32 err, err_scnr;
 	int ret;
 
@@ -706,7 +837,7 @@ u32 rtw89_mac_get_err_status(struct rtw89_dev *rtwdev)
 		return err;
 
 	rtw89_fw_st_dbg_dump(rtwdev);
-	rtw89_mac_dump_err_status(rtwdev, err);
+	mac->dump_err_status(rtwdev, err);
 
 	return err;
 }
@@ -900,7 +1031,7 @@ static int hfc_pub_ctrl(struct rtw89_dev *rtwdev)
 	return 0;
 }
 
-static int hfc_upd_mix_info(struct rtw89_dev *rtwdev)
+static void hfc_get_mix_info_ax(struct rtw89_dev *rtwdev)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	const struct rtw89_page_regs *regs = chip->page_regs;
@@ -909,11 +1040,6 @@ static int hfc_upd_mix_info(struct rtw89_dev *rtwdev)
 	struct rtw89_hfc_prec_cfg *prec_cfg = &param->prec_cfg;
 	struct rtw89_hfc_pub_info *info = &param->pub_info;
 	u32 val;
-	int ret;
-
-	ret = rtw89_mac_check_mac_en(rtwdev, RTW89_MAC_0, RTW89_DMAC_SEL);
-	if (ret)
-		return ret;
 
 	val = rtw89_read32(rtwdev, regs->pub_page_info1);
 	info->g0_used = u32_get_bits(val, B_AX_G0_USE_PG_MASK);
@@ -958,6 +1084,19 @@ static int hfc_upd_mix_info(struct rtw89_dev *rtwdev)
 	val = rtw89_read32(rtwdev, regs->pub_page_ctrl1);
 	pub_cfg->grp0 = u32_get_bits(val, B_AX_PUBPG_G0_MASK);
 	pub_cfg->grp1 = u32_get_bits(val, B_AX_PUBPG_G1_MASK);
+}
+
+static int hfc_upd_mix_info(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
+	struct rtw89_hfc_param *param = &rtwdev->mac.hfc_param;
+	int ret;
+
+	ret = rtw89_mac_check_mac_en(rtwdev, RTW89_MAC_0, RTW89_DMAC_SEL);
+	if (ret)
+		return ret;
+
+	mac->hfc_get_mix_info(rtwdev);
 
 	ret = hfc_pub_info_chk(rtwdev);
 	if (param->en && ret)
@@ -966,7 +1105,7 @@ static int hfc_upd_mix_info(struct rtw89_dev *rtwdev)
 	return 0;
 }
 
-static void hfc_h2c_cfg(struct rtw89_dev *rtwdev)
+static void hfc_h2c_cfg_ax(struct rtw89_dev *rtwdev)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	const struct rtw89_page_regs *regs = chip->page_regs;
@@ -982,7 +1121,7 @@ static void hfc_h2c_cfg(struct rtw89_dev *rtwdev)
 			   prec_cfg->h2c_full_cond);
 }
 
-static void hfc_mix_cfg(struct rtw89_dev *rtwdev)
+static void hfc_mix_cfg_ax(struct rtw89_dev *rtwdev)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	const struct rtw89_page_regs *regs = chip->page_regs;
@@ -1017,7 +1156,7 @@ static void hfc_mix_cfg(struct rtw89_dev *rtwdev)
 	rtw89_write32(rtwdev, regs->hci_fc_ctrl, val);
 }
 
-static void hfc_func_en(struct rtw89_dev *rtwdev, bool en, bool h2c_en)
+static void hfc_func_en_ax(struct rtw89_dev *rtwdev, bool en, bool h2c_en)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	const struct rtw89_page_regs *regs = chip->page_regs;
@@ -1033,8 +1172,9 @@ static void hfc_func_en(struct rtw89_dev *rtwdev, bool en, bool h2c_en)
 	rtw89_write32(rtwdev, regs->hci_fc_ctrl, val);
 }
 
-static int hfc_init(struct rtw89_dev *rtwdev, bool reset, bool en, bool h2c_en)
+int rtw89_mac_hfc_init(struct rtw89_dev *rtwdev, bool reset, bool en, bool h2c_en)
 {
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	u32 dma_ch_mask = chip->dma_ch_mask;
 	u8 ch;
@@ -1049,11 +1189,11 @@ static int hfc_init(struct rtw89_dev *rtwdev, bool reset, bool en, bool h2c_en)
 	if (ret)
 		return ret;
 
-	hfc_func_en(rtwdev, false, false);
+	mac->hfc_func_en(rtwdev, false, false);
 
 	if (!en && h2c_en) {
-		hfc_h2c_cfg(rtwdev);
-		hfc_func_en(rtwdev, en, h2c_en);
+		mac->hfc_h2c_cfg(rtwdev);
+		mac->hfc_func_en(rtwdev, en, h2c_en);
 		return ret;
 	}
 
@@ -1069,9 +1209,9 @@ static int hfc_init(struct rtw89_dev *rtwdev, bool reset, bool en, bool h2c_en)
 	if (ret)
 		return ret;
 
-	hfc_mix_cfg(rtwdev);
+	mac->hfc_mix_cfg(rtwdev);
 	if (en || h2c_en) {
-		hfc_func_en(rtwdev, en, h2c_en);
+		mac->hfc_func_en(rtwdev, en, h2c_en);
 		udelay(10);
 	}
 	for (ch = RTW89_DMA_ACH0; ch < RTW89_DMA_H2C; ch++) {
@@ -1333,9 +1473,14 @@ static int rtw89_mac_power_switch(struct rtw89_dev *rtwdev, bool on)
 
 	if (on) {
 		set_bit(RTW89_FLAG_POWERON, rtwdev->flags);
+		set_bit(RTW89_FLAG_DMAC_FUNC, rtwdev->flags);
+		set_bit(RTW89_FLAG_CMAC0_FUNC, rtwdev->flags);
 		rtw89_write8(rtwdev, R_AX_SCOREBOARD + 3, MAC_AX_NOTIFY_TP_MAJOR);
 	} else {
 		clear_bit(RTW89_FLAG_POWERON, rtwdev->flags);
+		clear_bit(RTW89_FLAG_DMAC_FUNC, rtwdev->flags);
+		clear_bit(RTW89_FLAG_CMAC0_FUNC, rtwdev->flags);
+		clear_bit(RTW89_FLAG_CMAC1_FUNC, rtwdev->flags);
 		clear_bit(RTW89_FLAG_FW_RDY, rtwdev->flags);
 		rtw89_write8(rtwdev, R_AX_SCOREBOARD + 3, MAC_AX_NOTIFY_PWR_MAJOR);
 		rtw89_set_entity_state(rtwdev, false);
@@ -1350,7 +1495,7 @@ void rtw89_mac_pwr_off(struct rtw89_dev *rtwdev)
 	rtw89_mac_power_switch(rtwdev, false);
 }
 
-static int cmac_func_en(struct rtw89_dev *rtwdev, u8 mac_idx, bool en)
+static int cmac_func_en_ax(struct rtw89_dev *rtwdev, u8 mac_idx, bool en)
 {
 	u32 func_en = 0;
 	u32 ck_en = 0;
@@ -1396,7 +1541,7 @@ static int cmac_func_en(struct rtw89_dev *rtwdev, u8 mac_idx, bool en)
 	return 0;
 }
 
-static int dmac_func_en(struct rtw89_dev *rtwdev)
+static int dmac_func_en_ax(struct rtw89_dev *rtwdev)
 {
 	enum rtw89_core_chip_id chip_id = rtwdev->chip->chip_id;
 	u32 val32;
@@ -1428,7 +1573,7 @@ static int dmac_func_en(struct rtw89_dev *rtwdev)
 	return 0;
 }
 
-static int chip_func_en(struct rtw89_dev *rtwdev)
+static int chip_func_en_ax(struct rtw89_dev *rtwdev)
 {
 	enum rtw89_core_chip_id chip_id = rtwdev->chip->chip_id;
 
@@ -1439,19 +1584,19 @@ static int chip_func_en(struct rtw89_dev *rtwdev)
 	return 0;
 }
 
-static int rtw89_mac_sys_init(struct rtw89_dev *rtwdev)
+static int sys_init_ax(struct rtw89_dev *rtwdev)
 {
 	int ret;
 
-	ret = dmac_func_en(rtwdev);
+	ret = dmac_func_en_ax(rtwdev);
 	if (ret)
 		return ret;
 
-	ret = cmac_func_en(rtwdev, 0, true);
+	ret = cmac_func_en_ax(rtwdev, 0, true);
 	if (ret)
 		return ret;
 
-	ret = chip_func_en(rtwdev);
+	ret = chip_func_en_ax(rtwdev);
 	if (ret)
 		return ret;
 
@@ -1460,10 +1605,14 @@ static int rtw89_mac_sys_init(struct rtw89_dev *rtwdev)
 
 const struct rtw89_mac_size_set rtw89_mac_size = {
 	.hfc_preccfg_pcie = {2, 40, 0, 0, 1, 0, 0, 0},
+	.hfc_prec_cfg_c0 = {2, 32, 0, 0, 0, 0, 0, 0},
+	.hfc_prec_cfg_c2 = {0, 256, 0, 0, 0, 0, 0, 0},
 	/* PCIE 64 */
 	.wde_size0 = {RTW89_WDE_PG_64, 4095, 1,},
+	.wde_size0_v1 = {RTW89_WDE_PG_64, 3328, 0, 0,},
 	/* DLFW */
 	.wde_size4 = {RTW89_WDE_PG_64, 0, 4096,},
+	.wde_size4_v1 = {RTW89_WDE_PG_64, 0, 3328, 0,},
 	/* PCIE 64 */
 	.wde_size6 = {RTW89_WDE_PG_64, 512, 0,},
 	/* 8852B PCIE SCC */
@@ -1476,6 +1625,8 @@ const struct rtw89_mac_size_set rtw89_mac_size = {
 	.wde_size19 = {RTW89_WDE_PG_64, 3328, 0,},
 	/* PCIE */
 	.ple_size0 = {RTW89_PLE_PG_128, 1520, 16,},
+	.ple_size0_v1 = {RTW89_PLE_PG_128, 2672, 256, 212992,},
+	.ple_size3_v1 = {RTW89_PLE_PG_128, 2928, 0, 212992,},
 	/* DLFW */
 	.ple_size4 = {RTW89_PLE_PG_128, 64, 1472,},
 	/* PCIE 64 */
@@ -1488,6 +1639,7 @@ const struct rtw89_mac_size_set rtw89_mac_size = {
 	.ple_size19 = {RTW89_PLE_PG_128, 1904, 16,},
 	/* PCIE 64 */
 	.wde_qt0 = {3792, 196, 0, 107,},
+	.wde_qt0_v1 = {3302, 6, 0, 20,},
 	/* DLFW */
 	.wde_qt4 = {0, 0, 0, 0,},
 	/* PCIE 64 */
@@ -1498,10 +1650,13 @@ const struct rtw89_mac_size_set rtw89_mac_size = {
 	.wde_qt17 = {0, 0, 0,  0,},
 	/* 8852C PCIE SCC */
 	.wde_qt18 = {3228, 60, 0, 40,},
+	.ple_qt0 = {320, 0, 32, 16, 13, 13, 292, 0, 32, 18, 1, 4, 0,},
+	.ple_qt1 = {320, 0, 32, 16, 1944, 1944, 2223, 0, 1963, 1949, 1, 1935, 0,},
 	/* PCIE SCC */
 	.ple_qt4 = {264, 0, 16, 20, 26, 13, 356, 0, 32, 40, 8,},
 	/* PCIE SCC */
 	.ple_qt5 = {264, 0, 32, 20, 64, 13, 1101, 0, 64, 128, 120,},
+	.ple_qt9 = {0, 0, 32, 256, 0, 0, 0, 0, 0, 0, 1, 0, 0,},
 	/* DLFW */
 	.ple_qt13 = {0, 0, 16, 48, 0, 0, 0, 0, 0, 0, 0,},
 	/* PCIE 64 */
@@ -1522,6 +1677,10 @@ const struct rtw89_mac_size_set rtw89_mac_size = {
 	.ple_qt_52b_wow = {147, 0, 16, 20, 157, 13, 133, 0, 172, 14, 24, 0,},
 	/* 8851B PCIE WOW */
 	.ple_qt_51b_wow = {147, 0, 16, 20, 157, 13, 133, 0, 172, 14, 24, 0,},
+	.ple_rsvd_qt0 = {2, 112, 56, 6, 6, 6, 6, 0, 0, 62,},
+	.ple_rsvd_qt1 = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0,},
+	.rsvd0_size0 = {212992, 0,},
+	.rsvd1_size0 = {587776, 2048,},
 };
 EXPORT_SYMBOL(rtw89_mac_size);
 
@@ -1540,7 +1699,9 @@ static const struct rtw89_dle_mem *get_dle_mem_cfg(struct rtw89_dev *rtwdev,
 		return NULL;
 	}
 
+	mac->dle_info.rsvd_qt = cfg->rsvd_qt;
 	mac->dle_info.ple_pg_size = cfg->ple_size->pge_size;
+	mac->dle_info.ple_free_pg = cfg->ple_size->lnk_pge_num;
 	mac->dle_info.qta_mode = mode;
 	mac->dle_info.c0_rx_qta = cfg->ple_min_qt->cma0_dma;
 	mac->dle_info.c1_rx_qta = cfg->ple_min_qt->cma1_dma;
@@ -1548,33 +1709,86 @@ static const struct rtw89_dle_mem *get_dle_mem_cfg(struct rtw89_dev *rtwdev,
 	return cfg;
 }
 
-static bool mac_is_txq_empty(struct rtw89_dev *rtwdev)
+int rtw89_mac_get_dle_rsvd_qt_cfg(struct rtw89_dev *rtwdev,
+				  enum rtw89_mac_dle_rsvd_qt_type type,
+				  struct rtw89_mac_dle_rsvd_qt_cfg *cfg)
+{
+	struct rtw89_dle_info *dle_info = &rtwdev->mac.dle_info;
+	const struct rtw89_rsvd_quota *rsvd_qt = dle_info->rsvd_qt;
+
+	switch (type) {
+	case DLE_RSVD_QT_MPDU_INFO:
+		cfg->pktid = dle_info->ple_free_pg;
+		cfg->pg_num = rsvd_qt->mpdu_info_tbl;
+		break;
+	case DLE_RSVD_QT_B0_CSI:
+		cfg->pktid = dle_info->ple_free_pg + rsvd_qt->mpdu_info_tbl;
+		cfg->pg_num = rsvd_qt->b0_csi;
+		break;
+	case DLE_RSVD_QT_B1_CSI:
+		cfg->pktid = dle_info->ple_free_pg +
+			     rsvd_qt->mpdu_info_tbl + rsvd_qt->b0_csi;
+		cfg->pg_num = rsvd_qt->b1_csi;
+		break;
+	case DLE_RSVD_QT_B0_LMR:
+		cfg->pktid = dle_info->ple_free_pg +
+			     rsvd_qt->mpdu_info_tbl + rsvd_qt->b0_csi + rsvd_qt->b1_csi;
+		cfg->pg_num = rsvd_qt->b0_lmr;
+		break;
+	case DLE_RSVD_QT_B1_LMR:
+		cfg->pktid = dle_info->ple_free_pg +
+			     rsvd_qt->mpdu_info_tbl + rsvd_qt->b0_csi + rsvd_qt->b1_csi +
+			     rsvd_qt->b0_lmr;
+		cfg->pg_num = rsvd_qt->b1_lmr;
+		break;
+	case DLE_RSVD_QT_B0_FTM:
+		cfg->pktid = dle_info->ple_free_pg +
+			     rsvd_qt->mpdu_info_tbl + rsvd_qt->b0_csi + rsvd_qt->b1_csi +
+			     rsvd_qt->b0_lmr + rsvd_qt->b1_lmr;
+		cfg->pg_num = rsvd_qt->b0_ftm;
+		break;
+	case DLE_RSVD_QT_B1_FTM:
+		cfg->pktid = dle_info->ple_free_pg +
+			     rsvd_qt->mpdu_info_tbl + rsvd_qt->b0_csi + rsvd_qt->b1_csi +
+			     rsvd_qt->b0_lmr + rsvd_qt->b1_lmr + rsvd_qt->b0_ftm;
+		cfg->pg_num = rsvd_qt->b1_ftm;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	cfg->size = (u32)cfg->pg_num * dle_info->ple_pg_size;
+
+	return 0;
+}
+
+static bool mac_is_txq_empty_ax(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_mac_dle_dfi_qempty qempty;
-	u32 qnum, qtmp, val32, msk32;
+	u32 grpnum, qtmp, val32, msk32;
 	int i, j, ret;
 
-	qnum = rtwdev->chip->wde_qempty_acq_num;
+	grpnum = rtwdev->chip->wde_qempty_acq_grpnum;
 	qempty.dle_type = DLE_CTRL_TYPE_WDE;
 
-	for (i = 0; i < qnum; i++) {
+	for (i = 0; i < grpnum; i++) {
 		qempty.grpsel = i;
-		ret = dle_dfi_qempty(rtwdev, &qempty);
+		ret = rtw89_mac_dle_dfi_qempty_cfg(rtwdev, &qempty);
 		if (ret) {
 			rtw89_warn(rtwdev, "dle dfi acq empty %d\n", ret);
 			return false;
 		}
 		qtmp = qempty.qempty;
 		for (j = 0 ; j < QEMP_ACQ_GRP_MACID_NUM; j++) {
-			val32 = FIELD_GET(QEMP_ACQ_GRP_QSEL_MASK, qtmp);
+			val32 = u32_get_bits(qtmp, QEMP_ACQ_GRP_QSEL_MASK);
 			if (val32 != QEMP_ACQ_GRP_QSEL_MASK)
 				return false;
 			qtmp >>= QEMP_ACQ_GRP_QSEL_SH;
 		}
 	}
 
-	qempty.grpsel = rtwdev->chip->wde_qempty_mgq_sel;
-	ret = dle_dfi_qempty(rtwdev, &qempty);
+	qempty.grpsel = rtwdev->chip->wde_qempty_mgq_grpsel;
+	ret = rtw89_mac_dle_dfi_qempty_cfg(rtwdev, &qempty);
 	if (ret) {
 		rtw89_warn(rtwdev, "dle dfi mgq empty %d\n", ret);
 		return false;
@@ -1602,11 +1816,21 @@ static bool mac_is_txq_empty(struct rtw89_dev *rtwdev)
 	return (val32 & msk32) == msk32;
 }
 
-static inline u32 dle_used_size(const struct rtw89_dle_size *wde,
-				const struct rtw89_dle_size *ple)
+static inline u32 dle_used_size(const struct rtw89_dle_mem *cfg)
 {
-	return wde->pge_size * (wde->lnk_pge_num + wde->unlnk_pge_num) +
+	const struct rtw89_dle_size *wde = cfg->wde_size;
+	const struct rtw89_dle_size *ple = cfg->ple_size;
+	u32 used;
+
+	used = wde->pge_size * (wde->lnk_pge_num + wde->unlnk_pge_num) +
 	       ple->pge_size * (ple->lnk_pge_num + ple->unlnk_pge_num);
+
+	if (cfg->rsvd0_size && cfg->rsvd1_size) {
+		used += cfg->rsvd0_size->size;
+		used += cfg->rsvd1_size->size;
+	}
+
+	return used;
 }
 
 static u32 dle_expected_used_size(struct rtw89_dev *rtwdev,
@@ -1620,7 +1844,7 @@ static u32 dle_expected_used_size(struct rtw89_dev *rtwdev,
 	return size;
 }
 
-static void dle_func_en(struct rtw89_dev *rtwdev, bool enable)
+static void dle_func_en_ax(struct rtw89_dev *rtwdev, bool enable)
 {
 	if (enable)
 		rtw89_write32_set(rtwdev, R_AX_DMAC_FUNC_EN,
@@ -1630,7 +1854,7 @@ static void dle_func_en(struct rtw89_dev *rtwdev, bool enable)
 				  B_AX_DLE_WDE_EN | B_AX_DLE_PLE_EN);
 }
 
-static void dle_clk_en(struct rtw89_dev *rtwdev, bool enable)
+static void dle_clk_en_ax(struct rtw89_dev *rtwdev, bool enable)
 {
 	u32 val = B_AX_DLE_WDE_CLK_EN | B_AX_DLE_PLE_CLK_EN;
 
@@ -1643,7 +1867,7 @@ static void dle_clk_en(struct rtw89_dev *rtwdev, bool enable)
 	}
 }
 
-static int dle_mix_cfg(struct rtw89_dev *rtwdev, const struct rtw89_dle_mem *cfg)
+static int dle_mix_cfg_ax(struct rtw89_dev *rtwdev, const struct rtw89_dle_mem *cfg)
 {
 	const struct rtw89_dle_size *size_cfg;
 	u32 val;
@@ -1700,6 +1924,23 @@ static int dle_mix_cfg(struct rtw89_dev *rtwdev, const struct rtw89_dle_mem *cfg
 	return 0;
 }
 
+static int chk_dle_rdy_ax(struct rtw89_dev *rtwdev, bool wde_or_ple)
+{
+	u32 reg, mask;
+	u32 ini;
+
+	if (wde_or_ple) {
+		reg = R_AX_WDE_INI_STATUS;
+		mask = WDE_MGN_INI_RDY;
+	} else {
+		reg = R_AX_PLE_INI_STATUS;
+		mask = PLE_MGN_INI_RDY;
+	}
+
+	return read_poll_timeout(rtw89_read32, ini, (ini & mask) == mask, 1,
+				2000, false, rtwdev, reg);
+}
+
 #define INVALID_QT_WCPU U16_MAX
 #define SET_QUOTA_VAL(_min_x, _max_x, _module, _idx)			\
 	do {								\
@@ -1712,10 +1953,10 @@ static int dle_mix_cfg(struct rtw89_dev *rtwdev, const struct rtw89_dle_mem *cfg
 #define SET_QUOTA(_x, _module, _idx)					\
 	SET_QUOTA_VAL(min_cfg->_x, max_cfg->_x, _module, _idx)
 
-static void wde_quota_cfg(struct rtw89_dev *rtwdev,
-			  const struct rtw89_wde_quota *min_cfg,
-			  const struct rtw89_wde_quota *max_cfg,
-			  u16 ext_wde_min_qt_wcpu)
+static void wde_quota_cfg_ax(struct rtw89_dev *rtwdev,
+			     const struct rtw89_wde_quota *min_cfg,
+			     const struct rtw89_wde_quota *max_cfg,
+			     u16 ext_wde_min_qt_wcpu)
 {
 	u16 min_qt_wcpu = ext_wde_min_qt_wcpu != INVALID_QT_WCPU ?
 			  ext_wde_min_qt_wcpu : min_cfg->wcpu;
@@ -1727,9 +1968,9 @@ static void wde_quota_cfg(struct rtw89_dev *rtwdev,
 	SET_QUOTA(cpu_io, WDE, 4);
 }
 
-static void ple_quota_cfg(struct rtw89_dev *rtwdev,
-			  const struct rtw89_ple_quota *min_cfg,
-			  const struct rtw89_ple_quota *max_cfg)
+static void ple_quota_cfg_ax(struct rtw89_dev *rtwdev,
+			     const struct rtw89_ple_quota *min_cfg,
+			     const struct rtw89_ple_quota *max_cfg)
 {
 	u32 val;
 
@@ -1794,17 +2035,19 @@ static void dle_quota_cfg(struct rtw89_dev *rtwdev,
 			  const struct rtw89_dle_mem *cfg,
 			  u16 ext_wde_min_qt_wcpu)
 {
-	wde_quota_cfg(rtwdev, cfg->wde_min_qt, cfg->wde_max_qt, ext_wde_min_qt_wcpu);
-	ple_quota_cfg(rtwdev, cfg->ple_min_qt, cfg->ple_max_qt);
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
+
+	mac->wde_quota_cfg(rtwdev, cfg->wde_min_qt, cfg->wde_max_qt, ext_wde_min_qt_wcpu);
+	mac->ple_quota_cfg(rtwdev, cfg->ple_min_qt, cfg->ple_max_qt);
 }
 
-static int dle_init(struct rtw89_dev *rtwdev, enum rtw89_qta_mode mode,
-		    enum rtw89_qta_mode ext_mode)
+int rtw89_mac_dle_init(struct rtw89_dev *rtwdev, enum rtw89_qta_mode mode,
+		       enum rtw89_qta_mode ext_mode)
 {
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	const struct rtw89_dle_mem *cfg, *ext_cfg;
 	u16 ext_wde_min_qt_wcpu = INVALID_QT_WCPU;
-	int ret = 0;
-	u32 ini;
+	int ret;
 
 	ret = rtw89_mac_check_mac_en(rtwdev, RTW89_MAC_0, RTW89_DMAC_SEL);
 	if (ret)
@@ -1828,36 +2071,31 @@ static int dle_init(struct rtw89_dev *rtwdev, enum rtw89_qta_mode mode,
 		ext_wde_min_qt_wcpu = ext_cfg->wde_min_qt->wcpu;
 	}
 
-	if (dle_used_size(cfg->wde_size, cfg->ple_size) !=
-	    dle_expected_used_size(rtwdev, mode)) {
+	if (dle_used_size(cfg) != dle_expected_used_size(rtwdev, mode)) {
 		rtw89_err(rtwdev, "[ERR]wd/dle mem cfg\n");
 		ret = -EINVAL;
 		goto error;
 	}
 
-	dle_func_en(rtwdev, false);
-	dle_clk_en(rtwdev, true);
+	mac->dle_func_en(rtwdev, false);
+	mac->dle_clk_en(rtwdev, true);
 
-	ret = dle_mix_cfg(rtwdev, cfg);
+	ret = mac->dle_mix_cfg(rtwdev, cfg);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR] dle mix cfg\n");
 		goto error;
 	}
 	dle_quota_cfg(rtwdev, cfg, ext_wde_min_qt_wcpu);
 
-	dle_func_en(rtwdev, true);
+	mac->dle_func_en(rtwdev, true);
 
-	ret = read_poll_timeout(rtw89_read32, ini,
-				(ini & WDE_MGN_INI_RDY) == WDE_MGN_INI_RDY, 1,
-				2000, false, rtwdev, R_AX_WDE_INI_STATUS);
+	ret = mac->chk_dle_rdy(rtwdev, true);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]WDE cfg ready\n");
 		return ret;
 	}
 
-	ret = read_poll_timeout(rtw89_read32, ini,
-				(ini & WDE_MGN_INI_RDY) == WDE_MGN_INI_RDY, 1,
-				2000, false, rtwdev, R_AX_PLE_INI_STATUS);
+	ret = mac->chk_dle_rdy(rtwdev, false);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]PLE cfg ready\n");
 		return ret;
@@ -1865,7 +2103,7 @@ static int dle_init(struct rtw89_dev *rtwdev, enum rtw89_qta_mode mode,
 
 	return 0;
 error:
-	dle_func_en(rtwdev, false);
+	mac->dle_func_en(rtwdev, false);
 	rtw89_err(rtwdev, "[ERR]trxcfg wde 0x8900 = %x\n",
 		  rtw89_read32(rtwdev, R_AX_WDE_INI_STATUS));
 	rtw89_err(rtwdev, "[ERR]trxcfg ple 0x8D00 = %x\n",
@@ -1900,8 +2138,8 @@ static bool is_qta_poh(struct rtw89_dev *rtwdev)
 	return rtwdev->hci.type == RTW89_HCI_TYPE_PCIE;
 }
 
-static int preload_init(struct rtw89_dev *rtwdev, enum rtw89_mac_idx mac_idx,
-			enum rtw89_qta_mode mode)
+int rtw89_mac_preload_init(struct rtw89_dev *rtwdev, enum rtw89_mac_idx mac_idx,
+			   enum rtw89_qta_mode mode)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 
@@ -1950,7 +2188,7 @@ static void _patch_ss2f_path(struct rtw89_dev *rtwdev)
 			   SS2F_PATH_WLCPU);
 }
 
-static int sta_sch_init(struct rtw89_dev *rtwdev)
+static int sta_sch_init_ax(struct rtw89_dev *rtwdev)
 {
 	u32 p_val;
 	u8 val;
@@ -1979,7 +2217,7 @@ static int sta_sch_init(struct rtw89_dev *rtwdev)
 	return 0;
 }
 
-static int mpdu_proc_init(struct rtw89_dev *rtwdev)
+static int mpdu_proc_init_ax(struct rtw89_dev *rtwdev)
 {
 	int ret;
 
@@ -1996,7 +2234,7 @@ static int mpdu_proc_init(struct rtw89_dev *rtwdev)
 	return 0;
 }
 
-static int sec_eng_init(struct rtw89_dev *rtwdev)
+static int sec_eng_init_ax(struct rtw89_dev *rtwdev)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	u32 val = 0;
@@ -2031,41 +2269,41 @@ static int sec_eng_init(struct rtw89_dev *rtwdev)
 	return 0;
 }
 
-static int dmac_init(struct rtw89_dev *rtwdev, u8 mac_idx)
+static int dmac_init_ax(struct rtw89_dev *rtwdev, u8 mac_idx)
 {
 	int ret;
 
-	ret = dle_init(rtwdev, rtwdev->mac.qta_mode, RTW89_QTA_INVALID);
+	ret = rtw89_mac_dle_init(rtwdev, rtwdev->mac.qta_mode, RTW89_QTA_INVALID);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]DLE init %d\n", ret);
 		return ret;
 	}
 
-	ret = preload_init(rtwdev, RTW89_MAC_0, rtwdev->mac.qta_mode);
+	ret = rtw89_mac_preload_init(rtwdev, RTW89_MAC_0, rtwdev->mac.qta_mode);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]preload init %d\n", ret);
 		return ret;
 	}
 
-	ret = hfc_init(rtwdev, true, true, true);
+	ret = rtw89_mac_hfc_init(rtwdev, true, true, true);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]HCI FC init %d\n", ret);
 		return ret;
 	}
 
-	ret = sta_sch_init(rtwdev);
+	ret = sta_sch_init_ax(rtwdev);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]STA SCH init %d\n", ret);
 		return ret;
 	}
 
-	ret = mpdu_proc_init(rtwdev);
+	ret = mpdu_proc_init_ax(rtwdev);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]MPDU Proc init %d\n", ret);
 		return ret;
 	}
 
-	ret = sec_eng_init(rtwdev);
+	ret = sec_eng_init_ax(rtwdev);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]Security Engine init %d\n", ret);
 		return ret;
@@ -2074,7 +2312,7 @@ static int dmac_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	return ret;
 }
 
-static int addr_cam_init(struct rtw89_dev *rtwdev, u8 mac_idx)
+static int addr_cam_init_ax(struct rtw89_dev *rtwdev, u8 mac_idx)
 {
 	u32 val, reg;
 	u16 p_val;
@@ -2101,7 +2339,7 @@ static int addr_cam_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	return 0;
 }
 
-static int scheduler_init(struct rtw89_dev *rtwdev, u8 mac_idx)
+static int scheduler_init_ax(struct rtw89_dev *rtwdev, u8 mac_idx)
 {
 	u32 ret;
 	u32 reg;
@@ -2142,10 +2380,10 @@ static int scheduler_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	return 0;
 }
 
-int rtw89_mac_typ_fltr_opt(struct rtw89_dev *rtwdev,
-			   enum rtw89_machdr_frame_type type,
-			   enum rtw89_mac_fwd_target fwd_target,
-			   u8 mac_idx)
+static int rtw89_mac_typ_fltr_opt_ax(struct rtw89_dev *rtwdev,
+				     enum rtw89_machdr_frame_type type,
+				     enum rtw89_mac_fwd_target fwd_target,
+				     u8 mac_idx)
 {
 	u32 reg;
 	u32 val;
@@ -2184,7 +2422,7 @@ int rtw89_mac_typ_fltr_opt(struct rtw89_dev *rtwdev,
 	return 0;
 }
 
-static int rx_fltr_init(struct rtw89_dev *rtwdev, u8 mac_idx)
+static int rx_fltr_init_ax(struct rtw89_dev *rtwdev, u8 mac_idx)
 {
 	int ret, i;
 	u32 mac_ftlr, plcp_ftlr;
@@ -2194,8 +2432,8 @@ static int rx_fltr_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 		return ret;
 
 	for (i = RTW89_MGNT; i <= RTW89_DATA; i++) {
-		ret = rtw89_mac_typ_fltr_opt(rtwdev, i, RTW89_FWD_TO_HOST,
-					     mac_idx);
+		ret = rtw89_mac_typ_fltr_opt_ax(rtwdev, i, RTW89_FWD_TO_HOST,
+						mac_idx);
 		if (ret)
 			return ret;
 	}
@@ -2246,7 +2484,7 @@ static void _patch_dis_resp_chk(struct rtw89_dev *rtwdev, u8 mac_idx)
 	}
 }
 
-static int cca_ctrl_init(struct rtw89_dev *rtwdev, u8 mac_idx)
+static int cca_ctrl_init_ax(struct rtw89_dev *rtwdev, u8 mac_idx)
 {
 	u32 val, reg;
 	int ret;
@@ -2278,7 +2516,7 @@ static int cca_ctrl_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	return 0;
 }
 
-static int nav_ctrl_init(struct rtw89_dev *rtwdev)
+static int nav_ctrl_init_ax(struct rtw89_dev *rtwdev)
 {
 	rtw89_write32_set(rtwdev, R_AX_WMAC_NAV_CTL, B_AX_WMAC_PLCP_UP_NAV_EN |
 						     B_AX_WMAC_TF_UP_NAV_EN |
@@ -2288,7 +2526,7 @@ static int nav_ctrl_init(struct rtw89_dev *rtwdev)
 	return 0;
 }
 
-static int spatial_reuse_init(struct rtw89_dev *rtwdev, u8 mac_idx)
+static int spatial_reuse_init_ax(struct rtw89_dev *rtwdev, u8 mac_idx)
 {
 	u32 reg;
 	int ret;
@@ -2302,7 +2540,7 @@ static int spatial_reuse_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	return 0;
 }
 
-static int tmac_init(struct rtw89_dev *rtwdev, u8 mac_idx)
+static int tmac_init_ax(struct rtw89_dev *rtwdev, u8 mac_idx)
 {
 	u32 reg;
 	int ret;
@@ -2324,7 +2562,7 @@ static int tmac_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	return 0;
 }
 
-static int trxptcl_init(struct rtw89_dev *rtwdev, u8 mac_idx)
+static int trxptcl_init_ax(struct rtw89_dev *rtwdev, u8 mac_idx)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	const struct rtw89_rrsr_cfgs *rrsr = chip->rrsr_cfgs;
@@ -2381,7 +2619,7 @@ static void rst_bacam(struct rtw89_dev *rtwdev)
 		rtw89_warn(rtwdev, "failed to reset BA CAM\n");
 }
 
-static int rmac_init(struct rtw89_dev *rtwdev, u8 mac_idx)
+static int rmac_init_ax(struct rtw89_dev *rtwdev, u8 mac_idx)
 {
 #define TRXCFG_RMAC_CCA_TO	32
 #define TRXCFG_RMAC_DATA_TO	15
@@ -2439,7 +2677,7 @@ static int rmac_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	return ret;
 }
 
-static int cmac_com_init(struct rtw89_dev *rtwdev, u8 mac_idx)
+static int cmac_com_init_ax(struct rtw89_dev *rtwdev, u8 mac_idx)
 {
 	enum rtw89_core_chip_id chip_id = rtwdev->chip->chip_id;
 	u32 val, reg;
@@ -2464,7 +2702,7 @@ static int cmac_com_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	return 0;
 }
 
-static bool is_qta_dbcc(struct rtw89_dev *rtwdev, enum rtw89_qta_mode mode)
+bool rtw89_mac_is_qta_dbcc(struct rtw89_dev *rtwdev, enum rtw89_qta_mode mode)
 {
 	const struct rtw89_dle_mem *cfg;
 
@@ -2477,7 +2715,7 @@ static bool is_qta_dbcc(struct rtw89_dev *rtwdev, enum rtw89_qta_mode mode)
 	return (cfg->ple_min_qt->cma1_dma && cfg->ple_max_qt->cma1_dma);
 }
 
-static int ptcl_init(struct rtw89_dev *rtwdev, u8 mac_idx)
+static int ptcl_init_ax(struct rtw89_dev *rtwdev, u8 mac_idx)
 {
 	u32 val, reg;
 	int ret;
@@ -2520,7 +2758,7 @@ static int ptcl_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	return 0;
 }
 
-static int cmac_dma_init(struct rtw89_dev *rtwdev, u8 mac_idx)
+static int cmac_dma_init_ax(struct rtw89_dev *rtwdev, u8 mac_idx)
 {
 	enum rtw89_core_chip_id chip_id = rtwdev->chip->chip_id;
 	u32 reg;
@@ -2539,82 +2777,82 @@ static int cmac_dma_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 	return 0;
 }
 
-static int cmac_init(struct rtw89_dev *rtwdev, u8 mac_idx)
+static int cmac_init_ax(struct rtw89_dev *rtwdev, u8 mac_idx)
 {
 	int ret;
 
-	ret = scheduler_init(rtwdev, mac_idx);
+	ret = scheduler_init_ax(rtwdev, mac_idx);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]CMAC%d SCH init %d\n", mac_idx, ret);
 		return ret;
 	}
 
-	ret = addr_cam_init(rtwdev, mac_idx);
+	ret = addr_cam_init_ax(rtwdev, mac_idx);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]CMAC%d ADDR_CAM reset %d\n", mac_idx,
 			  ret);
 		return ret;
 	}
 
-	ret = rx_fltr_init(rtwdev, mac_idx);
+	ret = rx_fltr_init_ax(rtwdev, mac_idx);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]CMAC%d RX filter init %d\n", mac_idx,
 			  ret);
 		return ret;
 	}
 
-	ret = cca_ctrl_init(rtwdev, mac_idx);
+	ret = cca_ctrl_init_ax(rtwdev, mac_idx);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]CMAC%d CCA CTRL init %d\n", mac_idx,
 			  ret);
 		return ret;
 	}
 
-	ret = nav_ctrl_init(rtwdev);
+	ret = nav_ctrl_init_ax(rtwdev);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]CMAC%d NAV CTRL init %d\n", mac_idx,
 			  ret);
 		return ret;
 	}
 
-	ret = spatial_reuse_init(rtwdev, mac_idx);
+	ret = spatial_reuse_init_ax(rtwdev, mac_idx);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]CMAC%d Spatial Reuse init %d\n",
 			  mac_idx, ret);
 		return ret;
 	}
 
-	ret = tmac_init(rtwdev, mac_idx);
+	ret = tmac_init_ax(rtwdev, mac_idx);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]CMAC%d TMAC init %d\n", mac_idx, ret);
 		return ret;
 	}
 
-	ret = trxptcl_init(rtwdev, mac_idx);
+	ret = trxptcl_init_ax(rtwdev, mac_idx);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]CMAC%d TRXPTCL init %d\n", mac_idx, ret);
 		return ret;
 	}
 
-	ret = rmac_init(rtwdev, mac_idx);
+	ret = rmac_init_ax(rtwdev, mac_idx);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]CMAC%d RMAC init %d\n", mac_idx, ret);
 		return ret;
 	}
 
-	ret = cmac_com_init(rtwdev, mac_idx);
+	ret = cmac_com_init_ax(rtwdev, mac_idx);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]CMAC%d Com init %d\n", mac_idx, ret);
 		return ret;
 	}
 
-	ret = ptcl_init(rtwdev, mac_idx);
+	ret = ptcl_init_ax(rtwdev, mac_idx);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]CMAC%d PTCL init %d\n", mac_idx, ret);
 		return ret;
 	}
 
-	ret = cmac_dma_init(rtwdev, mac_idx);
+	ret = cmac_dma_init_ax(rtwdev, mac_idx);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]CMAC%d DMA init %d\n", mac_idx, ret);
 		return ret;
@@ -2626,20 +2864,26 @@ static int cmac_init(struct rtw89_dev *rtwdev, u8 mac_idx)
 static int rtw89_mac_read_phycap(struct rtw89_dev *rtwdev,
 				 struct rtw89_mac_c2h_info *c2h_info)
 {
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	struct rtw89_mac_h2c_info h2c_info = {0};
 	u32 ret;
 
+	mac->cnv_efuse_state(rtwdev, false);
+
 	h2c_info.id = RTW89_FWCMD_H2CREG_FUNC_GET_FEATURE;
 	h2c_info.content_len = 0;
 
 	ret = rtw89_fw_msg_reg(rtwdev, &h2c_info, c2h_info);
 	if (ret)
-		return ret;
+		goto out;
 
 	if (c2h_info->id != RTW89_FWCMD_C2HREG_FUNC_PHY_CAP)
-		return -EINVAL;
+		ret = -EINVAL;
 
-	return 0;
+out:
+	mac->cnv_efuse_state(rtwdev, true);
+
+	return ret;
 }
 
 int rtw89_mac_setup_phycap(struct rtw89_dev *rtwdev)
@@ -2871,7 +3115,7 @@ int rtw89_mac_resume_sch_tx_v1(struct rtw89_dev *rtwdev, u8 mac_idx, u32 tx_en)
 }
 EXPORT_SYMBOL(rtw89_mac_resume_sch_tx_v1);
 
-int rtw89_mac_dle_buf_req(struct rtw89_dev *rtwdev, u16 buf_len, bool wd, u16 *pkt_id)
+static int dle_buf_req_ax(struct rtw89_dev *rtwdev, u16 buf_len, bool wd, u16 *pkt_id)
 {
 	u32 val, reg;
 	int ret;
@@ -2895,7 +3139,7 @@ int rtw89_mac_dle_buf_req(struct rtw89_dev *rtwdev, u16 buf_len, bool wd, u16 *p
 	return 0;
 }
 
-int rtw89_mac_set_cpuio(struct rtw89_dev *rtwdev,
+static int set_cpuio_ax(struct rtw89_dev *rtwdev,
 			struct rtw89_cpuio_ctrl *ctrl_para, bool wd)
 {
 	u32 val, cmd_type, reg;
@@ -2948,8 +3192,9 @@ int rtw89_mac_set_cpuio(struct rtw89_dev *rtwdev,
 	return 0;
 }
 
-static int dle_quota_change(struct rtw89_dev *rtwdev, enum rtw89_qta_mode mode)
+int rtw89_mac_dle_quota_change(struct rtw89_dev *rtwdev, enum rtw89_qta_mode mode)
 {
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	const struct rtw89_dle_mem *cfg;
 	struct rtw89_cpuio_ctrl ctrl_para = {0};
 	u16 pkt_id;
@@ -2961,15 +3206,14 @@ static int dle_quota_change(struct rtw89_dev *rtwdev, enum rtw89_qta_mode mode)
 		return -EINVAL;
 	}
 
-	if (dle_used_size(cfg->wde_size, cfg->ple_size) !=
-	    dle_expected_used_size(rtwdev, mode)) {
+	if (dle_used_size(cfg) != dle_expected_used_size(rtwdev, mode)) {
 		rtw89_err(rtwdev, "[ERR]wd/dle mem cfg\n");
 		return -EINVAL;
 	}
 
 	dle_quota_cfg(rtwdev, cfg, INVALID_QT_WCPU);
 
-	ret = rtw89_mac_dle_buf_req(rtwdev, 0x20, true, &pkt_id);
+	ret = mac->dle_buf_req(rtwdev, 0x20, true, &pkt_id);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]WDE DLE buf req\n");
 		return ret;
@@ -2981,13 +3225,13 @@ static int dle_quota_change(struct rtw89_dev *rtwdev, enum rtw89_qta_mode mode)
 	ctrl_para.pkt_num = 0;
 	ctrl_para.dst_pid = WDE_DLE_PORT_ID_WDRLS;
 	ctrl_para.dst_qid = WDE_DLE_QUEID_NO_REPORT;
-	ret = rtw89_mac_set_cpuio(rtwdev, &ctrl_para, true);
+	ret = mac->set_cpuio(rtwdev, &ctrl_para, true);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]WDE DLE enqueue to head\n");
 		return -EFAULT;
 	}
 
-	ret = rtw89_mac_dle_buf_req(rtwdev, 0x20, false, &pkt_id);
+	ret = mac->dle_buf_req(rtwdev, 0x20, false, &pkt_id);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]PLE DLE buf req\n");
 		return ret;
@@ -2999,7 +3243,7 @@ static int dle_quota_change(struct rtw89_dev *rtwdev, enum rtw89_qta_mode mode)
 	ctrl_para.pkt_num = 0;
 	ctrl_para.dst_pid = PLE_DLE_PORT_ID_PLRLS;
 	ctrl_para.dst_qid = PLE_DLE_QUEID_NO_REPORT;
-	ret = rtw89_mac_set_cpuio(rtwdev, &ctrl_para, false);
+	ret = mac->set_cpuio(rtwdev, &ctrl_para, false);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]PLE DLE enqueue to head\n");
 		return -EFAULT;
@@ -3031,7 +3275,7 @@ static int band_idle_ck_b(struct rtw89_dev *rtwdev, u8 mac_idx)
 	return 0;
 }
 
-static int band1_enable(struct rtw89_dev *rtwdev)
+static int band1_enable_ax(struct rtw89_dev *rtwdev)
 {
 	int ret, i;
 	u32 sleep_bak[4] = {0};
@@ -3057,7 +3301,7 @@ static int band1_enable(struct rtw89_dev *rtwdev)
 		return ret;
 	}
 
-	ret = dle_quota_change(rtwdev, rtwdev->mac.qta_mode);
+	ret = rtw89_mac_dle_quota_change(rtwdev, rtwdev->mac.qta_mode);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]DLE quota change %d\n", ret);
 		return ret;
@@ -3074,13 +3318,13 @@ static int band1_enable(struct rtw89_dev *rtwdev)
 		return ret;
 	}
 
-	ret = cmac_func_en(rtwdev, 1, true);
+	ret = cmac_func_en_ax(rtwdev, 1, true);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]CMAC1 func en %d\n", ret);
 		return ret;
 	}
 
-	ret = cmac_init(rtwdev, 1);
+	ret = cmac_init_ax(rtwdev, 1);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]CMAC1 init %d\n", ret);
 		return ret;
@@ -3289,8 +3533,8 @@ static void rtw89_tmac_imr_enable(struct rtw89_dev *rtwdev, u8 mac_idx)
 	rtw89_write32_set(rtwdev, reg, imr->tmac_imr_set);
 }
 
-static int rtw89_mac_enable_imr(struct rtw89_dev *rtwdev, u8 mac_idx,
-				enum rtw89_mac_hwmod_sel sel)
+static int enable_imr_ax(struct rtw89_dev *rtwdev, u8 mac_idx,
+			 enum rtw89_mac_hwmod_sel sel)
 {
 	int ret;
 
@@ -3327,7 +3571,7 @@ static int rtw89_mac_enable_imr(struct rtw89_dev *rtwdev, u8 mac_idx,
 	return 0;
 }
 
-static void rtw89_mac_err_imr_ctrl(struct rtw89_dev *rtwdev, bool en)
+static void err_imr_ctrl_ax(struct rtw89_dev *rtwdev, bool en)
 {
 	enum rtw89_core_chip_id chip_id = rtwdev->chip->chip_id;
 
@@ -3340,18 +3584,18 @@ static void rtw89_mac_err_imr_ctrl(struct rtw89_dev *rtwdev, bool en)
 			      en ? CMAC1_ERR_IMR_EN : CMAC1_ERR_IMR_DIS);
 }
 
-static int rtw89_mac_dbcc_enable(struct rtw89_dev *rtwdev, bool enable)
+static int dbcc_enable_ax(struct rtw89_dev *rtwdev, bool enable)
 {
 	int ret = 0;
 
 	if (enable) {
-		ret = band1_enable(rtwdev);
+		ret = band1_enable_ax(rtwdev);
 		if (ret) {
 			rtw89_err(rtwdev, "[ERR] band1_enable %d\n", ret);
 			return ret;
 		}
 
-		ret = rtw89_mac_enable_imr(rtwdev, RTW89_MAC_1, RTW89_CMAC_SEL);
+		ret = enable_imr_ax(rtwdev, RTW89_MAC_1, RTW89_CMAC_SEL);
 		if (ret) {
 			rtw89_err(rtwdev, "[ERR] enable CMAC1 IMR %d\n", ret);
 			return ret;
@@ -3364,7 +3608,7 @@ static int rtw89_mac_dbcc_enable(struct rtw89_dev *rtwdev, bool enable)
 	return 0;
 }
 
-static int set_host_rpr(struct rtw89_dev *rtwdev)
+static int set_host_rpr_ax(struct rtw89_dev *rtwdev)
 {
 	if (rtwdev->hci.type == RTW89_HCI_TYPE_PCIE) {
 		rtw89_write32_mask(rtwdev, R_AX_WDRLS_CFG,
@@ -3384,46 +3628,46 @@ static int set_host_rpr(struct rtw89_dev *rtwdev)
 	return 0;
 }
 
-static int rtw89_mac_trx_init(struct rtw89_dev *rtwdev)
+static int trx_init_ax(struct rtw89_dev *rtwdev)
 {
 	enum rtw89_qta_mode qta_mode = rtwdev->mac.qta_mode;
 	int ret;
 
-	ret = dmac_init(rtwdev, 0);
+	ret = dmac_init_ax(rtwdev, 0);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]DMAC init %d\n", ret);
 		return ret;
 	}
 
-	ret = cmac_init(rtwdev, 0);
+	ret = cmac_init_ax(rtwdev, 0);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]CMAC%d init %d\n", 0, ret);
 		return ret;
 	}
 
-	if (is_qta_dbcc(rtwdev, qta_mode)) {
-		ret = rtw89_mac_dbcc_enable(rtwdev, true);
+	if (rtw89_mac_is_qta_dbcc(rtwdev, qta_mode)) {
+		ret = dbcc_enable_ax(rtwdev, true);
 		if (ret) {
 			rtw89_err(rtwdev, "[ERR]dbcc_enable init %d\n", ret);
 			return ret;
 		}
 	}
 
-	ret = rtw89_mac_enable_imr(rtwdev, RTW89_MAC_0, RTW89_DMAC_SEL);
+	ret = enable_imr_ax(rtwdev, RTW89_MAC_0, RTW89_DMAC_SEL);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR] enable DMAC IMR %d\n", ret);
 		return ret;
 	}
 
-	ret = rtw89_mac_enable_imr(rtwdev, RTW89_MAC_0, RTW89_CMAC_SEL);
+	ret = enable_imr_ax(rtwdev, RTW89_MAC_0, RTW89_CMAC_SEL);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR] to enable CMAC0 IMR %d\n", ret);
 		return ret;
 	}
 
-	rtw89_mac_err_imr_ctrl(rtwdev, true);
+	err_imr_ctrl_ax(rtwdev, true);
 
-	ret = set_host_rpr(rtwdev);
+	ret = set_host_rpr_ax(rtwdev);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR] set host rpr %d\n", ret);
 		return ret;
@@ -3514,11 +3758,10 @@ static int rtw89_mac_enable_cpu_ax(struct rtw89_dev *rtwdev, u8 boot_reason,
 	return 0;
 }
 
-static int rtw89_mac_dmac_pre_init(struct rtw89_dev *rtwdev)
+static void rtw89_mac_hci_func_en_ax(struct rtw89_dev *rtwdev)
 {
 	enum rtw89_core_chip_id chip_id = rtwdev->chip->chip_id;
 	u32 val;
-	int ret;
 
 	if (chip_id == RTL8852C)
 		val = B_AX_MAC_FUNC_EN | B_AX_DMAC_FUNC_EN | B_AX_DISPATCHER_EN |
@@ -3527,6 +3770,12 @@ static int rtw89_mac_dmac_pre_init(struct rtw89_dev *rtwdev)
 		val = B_AX_MAC_FUNC_EN | B_AX_DMAC_FUNC_EN | B_AX_DISPATCHER_EN |
 		      B_AX_PKT_BUF_EN;
 	rtw89_write32(rtwdev, R_AX_DMAC_FUNC_EN, val);
+}
+
+static void rtw89_mac_dmac_func_pre_en_ax(struct rtw89_dev *rtwdev)
+{
+	enum rtw89_core_chip_id chip_id = rtwdev->chip->chip_id;
+	u32 val;
 
 	if (chip_id == RTL8851B)
 		val = B_AX_DISPATCHER_CLK_EN | B_AX_AXIDMA_CLK_EN;
@@ -3535,7 +3784,7 @@ static int rtw89_mac_dmac_pre_init(struct rtw89_dev *rtwdev)
 	rtw89_write32(rtwdev, R_AX_DMAC_CLK_EN, val);
 
 	if (chip_id != RTL8852C)
-		goto dle;
+		return;
 
 	val = rtw89_read32(rtwdev, R_AX_HAXI_INIT_CFG1);
 	val &= ~(B_AX_DMA_MODE_MASK | B_AX_STOP_AXI_MST);
@@ -3550,15 +3799,23 @@ static int rtw89_mac_dmac_pre_init(struct rtw89_dev *rtwdev)
 			  B_AX_STOP_CH12 | B_AX_STOP_ACH2);
 	rtw89_write32_clr(rtwdev, R_AX_HAXI_DMA_STOP2, B_AX_STOP_CH10 | B_AX_STOP_CH11);
 	rtw89_write32_set(rtwdev, R_AX_PLATFORM_ENABLE, B_AX_AXIDMA_EN);
+}
+
+static int rtw89_mac_dmac_pre_init(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
+	int ret;
+
+	mac->hci_func_en(rtwdev);
+	mac->dmac_func_pre_en(rtwdev);
 
-dle:
-	ret = dle_init(rtwdev, RTW89_QTA_DLFW, rtwdev->mac.qta_mode);
+	ret = rtw89_mac_dle_init(rtwdev, RTW89_QTA_DLFW, rtwdev->mac.qta_mode);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]DLE pre init %d\n", ret);
 		return ret;
 	}
 
-	ret = hfc_init(rtwdev, true, false, true);
+	ret = rtw89_mac_hfc_init(rtwdev, true, false, true);
 	if (ret) {
 		rtw89_err(rtwdev, "[ERR]HCI FC pre init %d\n", ret);
 		return ret;
@@ -3632,6 +3889,7 @@ int rtw89_mac_partial_init(struct rtw89_dev *rtwdev, bool include_bb)
 
 int rtw89_mac_init(struct rtw89_dev *rtwdev)
 {
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	bool include_bb = !!chip->bbmcu_nr;
 	int ret;
@@ -3644,11 +3902,11 @@ int rtw89_mac_init(struct rtw89_dev *rtwdev)
 	if (ret)
 		goto fail;
 
-	ret = rtw89_mac_sys_init(rtwdev);
+	ret = mac->sys_init(rtwdev);
 	if (ret)
 		goto fail;
 
-	ret = rtw89_mac_trx_init(rtwdev);
+	ret = mac->trx_init(rtwdev);
 	if (ret)
 		goto fail;
 
@@ -3747,6 +4005,50 @@ static const struct rtw89_port_reg rtw89_port_base_ax = {
 		    R_AX_PORT_HGQ_WINDOW_CFG + 3},
 };
 
+static void rtw89_mac_check_packet_ctrl(struct rtw89_dev *rtwdev,
+					struct rtw89_vif *rtwvif, u8 type)
+{
+	u8 mask = B_AX_PTCL_DBG_INFO_MASK_BY_PORT(rtwvif->port);
+	u32 reg_info, reg_ctrl;
+	u32 val;
+	int ret;
+
+	reg_info = rtw89_mac_reg_by_idx(rtwdev, R_AX_PTCL_DBG_INFO, rtwvif->mac_idx);
+	reg_ctrl = rtw89_mac_reg_by_idx(rtwdev, R_AX_PTCL_DBG, rtwvif->mac_idx);
+
+	rtw89_write32_mask(rtwdev, reg_ctrl, B_AX_PTCL_DBG_SEL_MASK, type);
+	rtw89_write32_set(rtwdev, reg_ctrl, B_AX_PTCL_DBG_EN);
+	fsleep(100);
+
+	ret = read_poll_timeout(rtw89_read32_mask, val, val == 0, 1000, 100000,
+				true, rtwdev, reg_info, mask);
+	if (ret)
+		rtw89_warn(rtwdev, "Polling beacon packet empty fail\n");
+}
+
+static void rtw89_mac_bcn_drop(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
+{
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
+	const struct rtw89_port_reg *p = mac->port_base;
+
+	rtw89_write32_set(rtwdev, R_AX_BCN_DROP_ALL0, BIT(rtwvif->port));
+	rtw89_write32_port_mask(rtwdev, rtwvif, p->tbtt_prohib, B_AX_TBTT_SETUP_MASK, 1);
+	rtw89_write32_port_mask(rtwdev, rtwvif, p->bcn_area, B_AX_BCN_MSK_AREA_MASK, 0);
+	rtw89_write32_port_mask(rtwdev, rtwvif, p->tbtt_prohib, B_AX_TBTT_HOLD_MASK, 0);
+	rtw89_write32_port_mask(rtwdev, rtwvif, p->bcn_early, B_AX_BCNERLY_MASK, 2);
+	rtw89_write16_port_mask(rtwdev, rtwvif, p->tbtt_early, B_AX_TBTTERLY_MASK, 1);
+	rtw89_write32_port_mask(rtwdev, rtwvif, p->bcn_space, B_AX_BCN_SPACE_MASK, 1);
+	rtw89_write32_port_set(rtwdev, rtwvif, p->port_cfg, B_AX_BCNTX_EN);
+
+	rtw89_mac_check_packet_ctrl(rtwdev, rtwvif, AX_PTCL_DBG_BCNQ_NUM0);
+	if (rtwvif->port == RTW89_PORT_0)
+		rtw89_mac_check_packet_ctrl(rtwdev, rtwvif, AX_PTCL_DBG_BCNQ_NUM1);
+
+	rtw89_write32_clr(rtwdev, R_AX_BCN_DROP_ALL0, BIT(rtwvif->port));
+	rtw89_write32_port_clr(rtwdev, rtwvif, p->port_cfg, B_AX_TBTT_PROHIB_EN);
+	fsleep(2);
+}
+
 #define BCN_INTERVAL 100
 #define BCN_ERLY_DEF 160
 #define BCN_SETUP_DEF 2
@@ -3762,21 +4064,36 @@ static void rtw89_mac_port_cfg_func_sw(struct rtw89_dev *rtwdev,
 	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	const struct rtw89_port_reg *p = mac->port_base;
 	struct ieee80211_vif *vif = rtwvif_to_vif(rtwvif);
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	bool need_backup = false;
+	u32 backup_val;
 
 	if (!rtw89_read32_port_mask(rtwdev, rtwvif, p->port_cfg, B_AX_PORT_FUNC_EN))
 		return;
 
-	rtw89_write32_port_clr(rtwdev, rtwvif, p->tbtt_prohib, B_AX_TBTT_SETUP_MASK);
-	rtw89_write32_port_mask(rtwdev, rtwvif, p->tbtt_prohib, B_AX_TBTT_HOLD_MASK, 1);
-	rtw89_write16_port_clr(rtwdev, rtwvif, p->tbtt_early, B_AX_TBTTERLY_MASK);
-	rtw89_write16_port_clr(rtwdev, rtwvif, p->bcn_early, B_AX_BCNERLY_MASK);
+	if (chip->chip_id == RTL8852A && rtwvif->port != RTW89_PORT_0) {
+		need_backup = true;
+		backup_val = rtw89_read32_port(rtwdev, rtwvif, p->tbtt_prohib);
+	}
 
-	msleep(vif->bss_conf.beacon_int + 1);
+	if (rtwvif->net_type == RTW89_NET_TYPE_AP_MODE)
+		rtw89_mac_bcn_drop(rtwdev, rtwvif);
+
+	if (chip->chip_id == RTL8852A) {
+		rtw89_write32_port_clr(rtwdev, rtwvif, p->tbtt_prohib, B_AX_TBTT_SETUP_MASK);
+		rtw89_write32_port_mask(rtwdev, rtwvif, p->tbtt_prohib, B_AX_TBTT_HOLD_MASK, 1);
+		rtw89_write16_port_clr(rtwdev, rtwvif, p->tbtt_early, B_AX_TBTTERLY_MASK);
+		rtw89_write16_port_clr(rtwdev, rtwvif, p->bcn_early, B_AX_BCNERLY_MASK);
+	}
 
+	msleep(vif->bss_conf.beacon_int + 1);
 	rtw89_write32_port_clr(rtwdev, rtwvif, p->port_cfg, B_AX_PORT_FUNC_EN |
 							    B_AX_BRK_SETUP);
 	rtw89_write32_port_set(rtwdev, rtwvif, p->port_cfg, B_AX_TSFTR_RST);
 	rtw89_write32_port(rtwdev, rtwvif, p->bcn_cnt_tmr, 0);
+
+	if (need_backup)
+		rtw89_write32_port(rtwdev, rtwvif, p->tbtt_prohib, backup_val);
 }
 
 static void rtw89_mac_port_cfg_tx_rpt(struct rtw89_dev *rtwdev,
@@ -3857,12 +4174,10 @@ static void rtw89_mac_port_cfg_rx_sync(struct rtw89_dev *rtwdev,
 }
 
 static void rtw89_mac_port_cfg_tx_sw(struct rtw89_dev *rtwdev,
-				     struct rtw89_vif *rtwvif)
+				     struct rtw89_vif *rtwvif, bool en)
 {
 	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	const struct rtw89_port_reg *p = mac->port_base;
-	bool en = rtwvif->net_type == RTW89_NET_TYPE_AP_MODE ||
-		  rtwvif->net_type == RTW89_NET_TYPE_AD_HOC;
 
 	if (en)
 		rtw89_write32_port_set(rtwdev, rtwvif, p->port_cfg, B_AX_BCNTX_EN);
@@ -3870,6 +4185,24 @@ static void rtw89_mac_port_cfg_tx_sw(struct rtw89_dev *rtwdev,
 		rtw89_write32_port_clr(rtwdev, rtwvif, p->port_cfg, B_AX_BCNTX_EN);
 }
 
+static void rtw89_mac_port_cfg_tx_sw_by_nettype(struct rtw89_dev *rtwdev,
+						struct rtw89_vif *rtwvif)
+{
+	bool en = rtwvif->net_type == RTW89_NET_TYPE_AP_MODE ||
+		  rtwvif->net_type == RTW89_NET_TYPE_AD_HOC;
+
+	rtw89_mac_port_cfg_tx_sw(rtwdev, rtwvif, en);
+}
+
+void rtw89_mac_enable_beacon_for_ap_vifs(struct rtw89_dev *rtwdev, bool en)
+{
+	struct rtw89_vif *rtwvif;
+
+	rtw89_for_each_rtwvif(rtwdev, rtwvif)
+		if (rtwvif->net_type == RTW89_NET_TYPE_AP_MODE)
+			rtw89_mac_port_cfg_tx_sw(rtwdev, rtwvif, en);
+}
+
 static void rtw89_mac_port_cfg_bcn_intv(struct rtw89_dev *rtwdev,
 					struct rtw89_vif *rtwvif)
 {
@@ -4176,7 +4509,7 @@ int rtw89_mac_port_update(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 	rtw89_mac_port_cfg_bcn_prct(rtwdev, rtwvif);
 	rtw89_mac_port_cfg_rx_sw(rtwdev, rtwvif);
 	rtw89_mac_port_cfg_rx_sync(rtwdev, rtwvif);
-	rtw89_mac_port_cfg_tx_sw(rtwdev, rtwvif);
+	rtw89_mac_port_cfg_tx_sw_by_nettype(rtwdev, rtwvif);
 	rtw89_mac_port_cfg_bcn_intv(rtwdev, rtwvif);
 	rtw89_mac_port_cfg_hiq_win(rtwdev, rtwvif);
 	rtw89_mac_port_cfg_hiq_dtim(rtwdev, rtwvif);
@@ -4261,7 +4594,7 @@ void rtw89_mac_set_he_obss_narrow_bw_ru(struct rtw89_dev *rtwdev,
 
 void rtw89_mac_stop_ap(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
-	rtw89_mac_port_cfg_func_en(rtwdev, rtwvif, false);
+	rtw89_mac_port_cfg_func_sw(rtwdev, rtwvif);
 }
 
 int rtw89_mac_add_vif(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
@@ -4338,8 +4671,10 @@ rtw89_mac_c2h_scanofld_rsp(struct rtw89_dev *rtwdev, struct sk_buff *c2h,
 
 	switch (reason) {
 	case RTW89_SCAN_LEAVE_CH_NOTIFY:
-		if (rtw89_is_op_chan(rtwdev, band, chan))
+		if (rtw89_is_op_chan(rtwdev, band, chan)) {
+			rtw89_mac_enable_beacon_for_ap_vifs(rtwdev, false);
 			ieee80211_stop_queues(rtwdev->hw);
+		}
 		return;
 	case RTW89_SCAN_END_SCAN_NOTIFY:
 		if (rtwvif && rtwvif->scan_req &&
@@ -4357,6 +4692,7 @@ rtw89_mac_c2h_scanofld_rsp(struct rtw89_dev *rtwdev, struct sk_buff *c2h,
 		if (rtw89_is_op_chan(rtwdev, band, chan)) {
 			rtw89_assign_entity_chan(rtwdev, rtwvif->sub_entity_idx,
 						 &rtwdev->scan_info.op_chan);
+			rtw89_mac_enable_beacon_for_ap_vifs(rtwdev, true);
 			ieee80211_wake_queues(rtwdev->hw);
 		} else {
 			rtw89_chan_create(&new, chan, chan, band,
@@ -5171,7 +5507,8 @@ bool rtw89_mac_get_ctrl_path(struct rtw89_dev *rtwdev)
 
 	if (chip->chip_id == RTL8852C)
 		return false;
-	else if (chip->chip_id == RTL8852A || chip->chip_id == RTL8852B)
+	else if (chip->chip_id == RTL8852A || chip->chip_id == RTL8852B ||
+		 chip->chip_id == RTL8851B)
 		val = rtw89_read8_mask(rtwdev, R_AX_SYS_SDIO_CTRL + 3,
 				       B_AX_LTE_MUX_CTRL_PATH >> 24);
 
@@ -5616,7 +5953,8 @@ int rtw89_mac_set_hw_muedca_ctrl(struct rtw89_dev *rtwdev,
 	return 0;
 }
 
-int rtw89_mac_write_xtal_si(struct rtw89_dev *rtwdev, u8 offset, u8 val, u8 mask)
+static
+int rtw89_mac_write_xtal_si_ax(struct rtw89_dev *rtwdev, u8 offset, u8 val, u8 mask)
 {
 	u32 val32;
 	int ret;
@@ -5638,9 +5976,9 @@ int rtw89_mac_write_xtal_si(struct rtw89_dev *rtwdev, u8 offset, u8 val, u8 mask
 
 	return 0;
 }
-EXPORT_SYMBOL(rtw89_mac_write_xtal_si);
 
-int rtw89_mac_read_xtal_si(struct rtw89_dev *rtwdev, u8 offset, u8 *val)
+static
+int rtw89_mac_read_xtal_si_ax(struct rtw89_dev *rtwdev, u8 offset, u8 *val)
 {
 	u32 val32;
 	int ret;
@@ -5663,7 +6001,6 @@ int rtw89_mac_read_xtal_si(struct rtw89_dev *rtwdev, u8 offset, u8 *val)
 
 	return 0;
 }
-EXPORT_SYMBOL(rtw89_mac_read_xtal_si);
 
 static
 void rtw89_mac_pkt_drop_sta(struct rtw89_dev *rtwdev, struct rtw89_sta *rtwsta)
@@ -5713,6 +6050,7 @@ void rtw89_mac_pkt_drop_vif(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 int rtw89_mac_ptk_drop_by_band_and_wait(struct rtw89_dev *rtwdev,
 					enum rtw89_mac_idx band)
 {
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	struct rtw89_pkt_drop_params params = {0};
 	bool empty;
 	int i, ret = 0, try_cnt = 3;
@@ -5721,7 +6059,7 @@ int rtw89_mac_ptk_drop_by_band_and_wait(struct rtw89_dev *rtwdev,
 	params.sel = RTW89_PKT_DROP_SEL_BAND_ONCE;
 
 	for (i = 0; i < try_cnt; i++) {
-		ret = read_poll_timeout(mac_is_txq_empty, empty, empty, 50,
+		ret = read_poll_timeout(mac->is_txq_empty, empty, empty, 50,
 					50000, false, rtwdev);
 		if (ret && !RTW89_CHK_FW_FEATURE(NO_PACKET_DROP, &rtwdev->fw))
 			rtw89_fw_h2c_pkt_drop(rtwdev, &params);
@@ -5769,13 +6107,44 @@ const struct rtw89_mac_gen_def rtw89_mac_gen_ax = {
 			B_AX_BFMEE_HE_NDPA_EN,
 	},
 
+	.check_mac_en = rtw89_mac_check_mac_en_ax,
+	.sys_init = sys_init_ax,
+	.trx_init = trx_init_ax,
+	.hci_func_en = rtw89_mac_hci_func_en_ax,
+	.dmac_func_pre_en = rtw89_mac_dmac_func_pre_en_ax,
+	.dle_func_en = dle_func_en_ax,
+	.dle_clk_en = dle_clk_en_ax,
 	.bf_assoc = rtw89_mac_bf_assoc_ax,
 
+	.typ_fltr_opt = rtw89_mac_typ_fltr_opt_ax,
+
+	.dle_mix_cfg = dle_mix_cfg_ax,
+	.chk_dle_rdy = chk_dle_rdy_ax,
+	.dle_buf_req = dle_buf_req_ax,
+	.hfc_func_en = hfc_func_en_ax,
+	.hfc_h2c_cfg = hfc_h2c_cfg_ax,
+	.hfc_mix_cfg = hfc_mix_cfg_ax,
+	.hfc_get_mix_info = hfc_get_mix_info_ax,
+	.wde_quota_cfg = wde_quota_cfg_ax,
+	.ple_quota_cfg = ple_quota_cfg_ax,
+	.set_cpuio = set_cpuio_ax,
+
 	.disable_cpu = rtw89_mac_disable_cpu_ax,
 	.fwdl_enable_wcpu = rtw89_mac_enable_cpu_ax,
 	.fwdl_get_status = rtw89_fw_get_rdy_ax,
 	.fwdl_check_path_ready = rtw89_fwdl_check_path_ready_ax,
+	.parse_efuse_map = rtw89_parse_efuse_map_ax,
+	.parse_phycap_map = rtw89_parse_phycap_map_ax,
+	.cnv_efuse_state = rtw89_cnv_efuse_state_ax,
 
 	.get_txpwr_cr = rtw89_mac_get_txpwr_cr_ax,
+
+	.write_xtal_si = rtw89_mac_write_xtal_si_ax,
+	.read_xtal_si = rtw89_mac_read_xtal_si_ax,
+
+	.dump_qta_lost = rtw89_mac_dump_qta_lost_ax,
+	.dump_err_status = rtw89_mac_dump_err_status_ax,
+
+	.is_txq_empty = mac_is_txq_empty_ax,
 };
 EXPORT_SYMBOL(rtw89_mac_gen_ax);
diff --git a/drivers/net/wireless/realtek/rtw89/mac.h b/drivers/net/wireless/realtek/rtw89/mac.h
index c11c904f87fe..ed98b49809a4 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.h
+++ b/drivers/net/wireless/realtek/rtw89/mac.h
@@ -10,6 +10,7 @@
 
 #define MAC_MEM_DUMP_PAGE_SIZE 0x40000
 #define ADDR_CAM_ENT_SIZE  0x40
+#define ADDR_CAM_ENT_SHORT_SIZE 0x20
 #define BSSID_CAM_ENT_SIZE 0x08
 #define HFC_PAGE_UNIT 64
 #define RPWM_TRY_CNT 3
@@ -536,6 +537,9 @@ enum rtw89_mac_bf_rrsc_rate {
 #define B_CMAC1_MGQ_NO_PWRSAV	BIT(11)
 #define B_CMAC1_CPUMGQ		BIT(12)
 
+#define B_CMAC0_MGQ_NORMAL_BE	BIT(2)
+#define B_CMAC1_MGQ_NORMAL_BE	BIT(30)
+
 #define QEMP_ACQ_GRP_MACID_NUM	8
 #define QEMP_ACQ_GRP_QSEL_SH	4
 #define QEMP_ACQ_GRP_QSEL_MASK	0xF
@@ -649,6 +653,22 @@ struct rtw89_mac_dle_dfi_qempty {
 	u32 qempty;
 };
 
+enum rtw89_mac_dle_rsvd_qt_type {
+	DLE_RSVD_QT_MPDU_INFO,
+	DLE_RSVD_QT_B0_CSI,
+	DLE_RSVD_QT_B1_CSI,
+	DLE_RSVD_QT_B0_LMR,
+	DLE_RSVD_QT_B1_LMR,
+	DLE_RSVD_QT_B0_FTM,
+	DLE_RSVD_QT_B1_FTM,
+};
+
+struct rtw89_mac_dle_rsvd_qt_cfg {
+	u16 pktid;
+	u16 pg_num;
+	u32 size;
+};
+
 enum rtw89_mac_error_scenario {
 	RTW89_RXI300_ERROR		= 1,
 	RTW89_WCPU_CPU_EXCEPTION	= 2,
@@ -817,27 +837,37 @@ enum mac_ax_err_info {
 
 struct rtw89_mac_size_set {
 	const struct rtw89_hfc_prec_cfg hfc_preccfg_pcie;
+	const struct rtw89_hfc_prec_cfg hfc_prec_cfg_c0;
+	const struct rtw89_hfc_prec_cfg hfc_prec_cfg_c2;
 	const struct rtw89_dle_size wde_size0;
+	const struct rtw89_dle_size wde_size0_v1;
 	const struct rtw89_dle_size wde_size4;
+	const struct rtw89_dle_size wde_size4_v1;
 	const struct rtw89_dle_size wde_size6;
 	const struct rtw89_dle_size wde_size7;
 	const struct rtw89_dle_size wde_size9;
 	const struct rtw89_dle_size wde_size18;
 	const struct rtw89_dle_size wde_size19;
 	const struct rtw89_dle_size ple_size0;
+	const struct rtw89_dle_size ple_size0_v1;
+	const struct rtw89_dle_size ple_size3_v1;
 	const struct rtw89_dle_size ple_size4;
 	const struct rtw89_dle_size ple_size6;
 	const struct rtw89_dle_size ple_size8;
 	const struct rtw89_dle_size ple_size18;
 	const struct rtw89_dle_size ple_size19;
 	const struct rtw89_wde_quota wde_qt0;
+	const struct rtw89_wde_quota wde_qt0_v1;
 	const struct rtw89_wde_quota wde_qt4;
 	const struct rtw89_wde_quota wde_qt6;
 	const struct rtw89_wde_quota wde_qt7;
 	const struct rtw89_wde_quota wde_qt17;
 	const struct rtw89_wde_quota wde_qt18;
+	const struct rtw89_ple_quota ple_qt0;
+	const struct rtw89_ple_quota ple_qt1;
 	const struct rtw89_ple_quota ple_qt4;
 	const struct rtw89_ple_quota ple_qt5;
+	const struct rtw89_ple_quota ple_qt9;
 	const struct rtw89_ple_quota ple_qt13;
 	const struct rtw89_ple_quota ple_qt18;
 	const struct rtw89_ple_quota ple_qt44;
@@ -848,6 +878,10 @@ struct rtw89_mac_size_set {
 	const struct rtw89_ple_quota ple_qt_52a_wow;
 	const struct rtw89_ple_quota ple_qt_52b_wow;
 	const struct rtw89_ple_quota ple_qt_51b_wow;
+	const struct rtw89_rsvd_quota ple_rsvd_qt0;
+	const struct rtw89_rsvd_quota ple_rsvd_qt1;
+	const struct rtw89_dle_rsvd_size rsvd0_size0;
+	const struct rtw89_dle_rsvd_size rsvd1_size0;
 };
 
 extern const struct rtw89_mac_size_set rtw89_mac_size;
@@ -864,18 +898,60 @@ struct rtw89_mac_gen_def {
 	struct rtw89_reg_def muedca_ctrl;
 	struct rtw89_reg_def bfee_ctrl;
 
+	int (*check_mac_en)(struct rtw89_dev *rtwdev, u8 band,
+			    enum rtw89_mac_hwmod_sel sel);
+	int (*sys_init)(struct rtw89_dev *rtwdev);
+	int (*trx_init)(struct rtw89_dev *rtwdev);
+	void (*hci_func_en)(struct rtw89_dev *rtwdev);
+	void (*dmac_func_pre_en)(struct rtw89_dev *rtwdev);
+	void (*dle_func_en)(struct rtw89_dev *rtwdev, bool enable);
+	void (*dle_clk_en)(struct rtw89_dev *rtwdev, bool enable);
 	void (*bf_assoc)(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif,
 			 struct ieee80211_sta *sta);
 
+	int (*typ_fltr_opt)(struct rtw89_dev *rtwdev,
+			    enum rtw89_machdr_frame_type type,
+			    enum rtw89_mac_fwd_target fwd_target,
+			    u8 mac_idx);
+
+	int (*dle_mix_cfg)(struct rtw89_dev *rtwdev, const struct rtw89_dle_mem *cfg);
+	int (*chk_dle_rdy)(struct rtw89_dev *rtwdev, bool wde_or_ple);
+	int (*dle_buf_req)(struct rtw89_dev *rtwdev, u16 buf_len, bool wd, u16 *pkt_id);
+	void (*hfc_func_en)(struct rtw89_dev *rtwdev, bool en, bool h2c_en);
+	void (*hfc_h2c_cfg)(struct rtw89_dev *rtwdev);
+	void (*hfc_mix_cfg)(struct rtw89_dev *rtwdev);
+	void (*hfc_get_mix_info)(struct rtw89_dev *rtwdev);
+	void (*wde_quota_cfg)(struct rtw89_dev *rtwdev,
+			      const struct rtw89_wde_quota *min_cfg,
+			      const struct rtw89_wde_quota *max_cfg,
+			      u16 ext_wde_min_qt_wcpu);
+	void (*ple_quota_cfg)(struct rtw89_dev *rtwdev,
+			      const struct rtw89_ple_quota *min_cfg,
+			      const struct rtw89_ple_quota *max_cfg);
+	int (*set_cpuio)(struct rtw89_dev *rtwdev,
+			 struct rtw89_cpuio_ctrl *ctrl_para, bool wd);
+
 	void (*disable_cpu)(struct rtw89_dev *rtwdev);
 	int (*fwdl_enable_wcpu)(struct rtw89_dev *rtwdev, u8 boot_reason,
 				bool dlfw, bool include_bb);
 	u8 (*fwdl_get_status)(struct rtw89_dev *rtwdev, enum rtw89_fwdl_check_type type);
 	int (*fwdl_check_path_ready)(struct rtw89_dev *rtwdev, bool h2c_or_fwdl);
+	int (*parse_efuse_map)(struct rtw89_dev *rtwdev);
+	int (*parse_phycap_map)(struct rtw89_dev *rtwdev);
+	int (*cnv_efuse_state)(struct rtw89_dev *rtwdev, bool idle);
 
 	bool (*get_txpwr_cr)(struct rtw89_dev *rtwdev,
 			     enum rtw89_phy_idx phy_idx,
 			     u32 reg_base, u32 *cr);
+
+	int (*write_xtal_si)(struct rtw89_dev *rtwdev, u8 offset, u8 val, u8 mask);
+	int (*read_xtal_si)(struct rtw89_dev *rtwdev, u8 offset, u8 *val);
+
+	void (*dump_qta_lost)(struct rtw89_dev *rtwdev);
+	void (*dump_err_status)(struct rtw89_dev *rtwdev,
+				enum mac_ax_err_info err);
+
+	bool (*is_txq_empty)(struct rtw89_dev *rtwdev);
 };
 
 extern const struct rtw89_mac_gen_def rtw89_mac_gen_ax;
@@ -977,10 +1053,31 @@ rtw89_write32_port_set(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 void rtw89_mac_pwr_off(struct rtw89_dev *rtwdev);
 int rtw89_mac_partial_init(struct rtw89_dev *rtwdev, bool include_bb);
 int rtw89_mac_init(struct rtw89_dev *rtwdev);
+int rtw89_mac_dle_init(struct rtw89_dev *rtwdev, enum rtw89_qta_mode mode,
+		       enum rtw89_qta_mode ext_mode);
+int rtw89_mac_hfc_init(struct rtw89_dev *rtwdev, bool reset, bool en, bool h2c_en);
+int rtw89_mac_preload_init(struct rtw89_dev *rtwdev, enum rtw89_mac_idx mac_idx,
+			   enum rtw89_qta_mode mode);
+bool rtw89_mac_is_qta_dbcc(struct rtw89_dev *rtwdev, enum rtw89_qta_mode mode);
+static inline
 int rtw89_mac_check_mac_en(struct rtw89_dev *rtwdev, u8 band,
-			   enum rtw89_mac_hwmod_sel sel);
+			   enum rtw89_mac_hwmod_sel sel)
+{
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
+
+	return mac->check_mac_en(rtwdev, band, sel);
+}
+
 int rtw89_mac_write_lte(struct rtw89_dev *rtwdev, const u32 offset, u32 val);
 int rtw89_mac_read_lte(struct rtw89_dev *rtwdev, const u32 offset, u32 *val);
+int rtw89_mac_dle_dfi_cfg(struct rtw89_dev *rtwdev, struct rtw89_mac_dle_dfi_ctrl *ctrl);
+int rtw89_mac_dle_dfi_quota_cfg(struct rtw89_dev *rtwdev,
+				struct rtw89_mac_dle_dfi_quota *quota);
+void rtw89_mac_dump_dmac_err_status(struct rtw89_dev *rtwdev);
+int rtw89_mac_dle_dfi_qempty_cfg(struct rtw89_dev *rtwdev,
+				 struct rtw89_mac_dle_dfi_qempty *qempty);
+void rtw89_mac_dump_l0_to_l1(struct rtw89_dev *rtwdev,
+			     enum mac_ax_err_info err);
 int rtw89_mac_add_vif(struct rtw89_dev *rtwdev, struct rtw89_vif *vif);
 int rtw89_mac_port_update(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif);
 void rtw89_mac_port_tsf_sync(struct rtw89_dev *rtwdev,
@@ -992,6 +1089,7 @@ int rtw89_mac_port_get_tsf(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 void rtw89_mac_set_he_obss_narrow_bw_ru(struct rtw89_dev *rtwdev,
 					struct ieee80211_vif *vif);
 void rtw89_mac_stop_ap(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif);
+void rtw89_mac_enable_beacon_for_ap_vifs(struct rtw89_dev *rtwdev, bool en);
 int rtw89_mac_remove_vif(struct rtw89_dev *rtwdev, struct rtw89_vif *vif);
 int rtw89_mac_enable_bb_rf(struct rtw89_dev *rtwdev);
 int rtw89_mac_disable_bb_rf(struct rtw89_dev *rtwdev);
@@ -1010,6 +1108,23 @@ static inline int rtw89_chip_disable_bb_rf(struct rtw89_dev *rtwdev)
 	return chip->ops->disable_bb_rf(rtwdev);
 }
 
+static inline int rtw89_chip_reset_bb_rf(struct rtw89_dev *rtwdev)
+{
+	int ret;
+
+	if (rtwdev->chip->chip_gen != RTW89_CHIP_AX)
+		return 0;
+
+	ret = rtw89_chip_disable_bb_rf(rtwdev);
+	if (ret)
+		return ret;
+	ret = rtw89_chip_enable_bb_rf(rtwdev);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
 u32 rtw89_mac_get_err_status(struct rtw89_dev *rtwdev);
 int rtw89_mac_set_err_status(struct rtw89_dev *rtwdev, u32 err);
 bool rtw89_mac_c2h_chk_atomic(struct rtw89_dev *rtwdev, u8 class, u8 func);
@@ -1185,6 +1300,7 @@ enum rtw89_mac_xtal_si_offset {
 #define XTAL_SC_XI_MASK		GENMASK(7, 0)
 	XTAL_SI_XTAL_SC_XO = 0x05,
 #define XTAL_SC_XO_MASK		GENMASK(7, 0)
+	XTAL_SI_XREF_MODE = 0x0B,
 	XTAL_SI_PWR_CUT = 0x10,
 #define XTAL_SI_SMALL_PWR_CUT	BIT(0)
 #define XTAL_SI_BIG_PWR_CUT	BIT(1)
@@ -1194,6 +1310,8 @@ enum rtw89_mac_xtal_si_offset {
 #define XTAL_SI_LDO_LPS		GENMASK(6, 4)
 	XTAL_SI_XTAL_XMD_4 = 0x26,
 #define XTAL_SI_LPS_CAP		GENMASK(3, 0)
+	XTAL_SI_XREF_RF1 = 0x2D,
+	XTAL_SI_XREF_RF2 = 0x2E,
 	XTAL_SI_CV = 0x41,
 #define XTAL_SI_ACV_MASK	GENMASK(3, 0)
 	XTAL_SI_LOW_ADDR = 0x62,
@@ -1221,20 +1339,34 @@ enum rtw89_mac_xtal_si_offset {
 	XTAL_SI_SRAM_CTRL = 0xA1,
 #define XTAL_SI_SRAM_DIS	BIT(1)
 #define FULL_BIT_MASK		GENMASK(7, 0)
+	XTAL_SI_PLL = 0xE0,
+	XTAL_SI_PLL_1 = 0xE1,
 };
 
-int rtw89_mac_write_xtal_si(struct rtw89_dev *rtwdev, u8 offset, u8 val, u8 mask);
-int rtw89_mac_read_xtal_si(struct rtw89_dev *rtwdev, u8 offset, u8 *val);
+static inline
+int rtw89_mac_write_xtal_si(struct rtw89_dev *rtwdev, u8 offset, u8 val, u8 mask)
+{
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
+
+	return mac->write_xtal_si(rtwdev, offset, val, mask);
+}
+
+static inline
+int rtw89_mac_read_xtal_si(struct rtw89_dev *rtwdev, u8 offset, u8 *val)
+{
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
+
+	return mac->read_xtal_si(rtwdev, offset, val);
+}
+
 void rtw89_mac_pkt_drop_vif(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif);
-int rtw89_mac_dle_buf_req(struct rtw89_dev *rtwdev, u16 buf_len, bool wd, u16 *pkt_id);
-int rtw89_mac_set_cpuio(struct rtw89_dev *rtwdev,
-			struct rtw89_cpuio_ctrl *ctrl_para, bool wd);
-int rtw89_mac_typ_fltr_opt(struct rtw89_dev *rtwdev,
-			   enum rtw89_machdr_frame_type type,
-			   enum rtw89_mac_fwd_target fwd_target, u8 mac_idx);
 int rtw89_mac_resize_ple_rx_quota(struct rtw89_dev *rtwdev, bool wow);
 int rtw89_mac_ptk_drop_by_band_and_wait(struct rtw89_dev *rtwdev,
 					enum rtw89_mac_idx band);
 void rtw89_mac_hw_mgnt_sec(struct rtw89_dev *rtwdev, bool wow);
+int rtw89_mac_dle_quota_change(struct rtw89_dev *rtwdev, enum rtw89_qta_mode mode);
+int rtw89_mac_get_dle_rsvd_qt_cfg(struct rtw89_dev *rtwdev,
+				  enum rtw89_mac_dle_rsvd_qt_type type,
+				  struct rtw89_mac_dle_rsvd_qt_cfg *cfg);
 
 #endif
diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c
index 31d1f7891675..93889d2fface 100644
--- a/drivers/net/wireless/realtek/rtw89/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw89/mac80211.c
@@ -226,6 +226,7 @@ static void rtw89_ops_configure_filter(struct ieee80211_hw *hw,
 {
 	struct rtw89_dev *rtwdev = hw->priv;
 	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
+	u32 rx_fltr;
 
 	mutex_lock(&rtwdev->mutex);
 	rtw89_leave_ps_mode(rtwdev);
@@ -272,16 +273,29 @@ static void rtw89_ops_configure_filter(struct ieee80211_hw *hw,
 		}
 	}
 
+	rx_fltr = rtwdev->hal.rx_fltr;
+
+	/* mac80211 doesn't configure filter when HW scan, driver need to
+	 * set by itself. However, during P2P scan might have configure
+	 * filter to overwrite filter that HW scan needed, so we need to
+	 * check scan and append related filter
+	 */
+	if (rtwdev->scanning) {
+		rx_fltr &= ~B_AX_A_BCN_CHK_EN;
+		rx_fltr &= ~B_AX_A_BC;
+		rx_fltr &= ~B_AX_A_A1_MATCH;
+	}
+
 	rtw89_write32_mask(rtwdev,
 			   rtw89_mac_reg_by_idx(rtwdev, mac->rx_fltr, RTW89_MAC_0),
 			   B_AX_RX_FLTR_CFG_MASK,
-			   rtwdev->hal.rx_fltr);
+			   rx_fltr);
 	if (!rtwdev->dbcc_en)
 		goto out;
 	rtw89_write32_mask(rtwdev,
 			   rtw89_mac_reg_by_idx(rtwdev, mac->rx_fltr, RTW89_MAC_1),
 			   B_AX_RX_FLTR_CFG_MASK,
-			   rtwdev->hal.rx_fltr);
+			   rx_fltr);
 
 out:
 	mutex_unlock(&rtwdev->mutex);
@@ -477,6 +491,9 @@ static int rtw89_ops_start_ap(struct ieee80211_hw *hw,
 		return -EOPNOTSUPP;
 	}
 
+	if (rtwdev->scanning)
+		rtw89_hw_scan_abort(rtwdev, rtwdev->scan_info.scanning_vif);
+
 	ether_addr_copy(rtwvif->bssid, vif->bss_conf.bssid);
 	rtw89_cam_bssid_changed(rtwdev, rtwvif);
 	rtw89_mac_port_update(rtwdev, rtwvif);
diff --git a/drivers/net/wireless/realtek/rtw89/mac_be.c b/drivers/net/wireless/realtek/rtw89/mac_be.c
index 3278f241db6e..be30c9346293 100644
--- a/drivers/net/wireless/realtek/rtw89/mac_be.c
+++ b/drivers/net/wireless/realtek/rtw89/mac_be.c
@@ -3,6 +3,7 @@
  */
 
 #include "debug.h"
+#include "efuse.h"
 #include "fw.h"
 #include "mac.h"
 #include "reg.h"
@@ -56,6 +57,369 @@ static const struct rtw89_port_reg rtw89_port_base_be = {
 		    R_BE_PORT_HGQ_WINDOW_CFG + 3},
 };
 
+static int rtw89_mac_check_mac_en_be(struct rtw89_dev *rtwdev, u8 mac_idx,
+				     enum rtw89_mac_hwmod_sel sel)
+{
+	if (sel == RTW89_DMAC_SEL &&
+	    test_bit(RTW89_FLAG_DMAC_FUNC, rtwdev->flags))
+		return 0;
+	if (sel == RTW89_CMAC_SEL && mac_idx == RTW89_MAC_0 &&
+	    test_bit(RTW89_FLAG_CMAC0_FUNC, rtwdev->flags))
+		return 0;
+	if (sel == RTW89_CMAC_SEL && mac_idx == RTW89_MAC_1 &&
+	    test_bit(RTW89_FLAG_CMAC1_FUNC, rtwdev->flags))
+		return 0;
+
+	return -EFAULT;
+}
+
+static bool is_qta_poh(struct rtw89_dev *rtwdev)
+{
+	return rtwdev->hci.type == RTW89_HCI_TYPE_PCIE;
+}
+
+static void hfc_get_mix_info_be(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_hfc_param *param = &rtwdev->mac.hfc_param;
+	struct rtw89_hfc_prec_cfg *prec_cfg = &param->prec_cfg;
+	struct rtw89_hfc_pub_cfg *pub_cfg = &param->pub_cfg;
+	struct rtw89_hfc_pub_info *info = &param->pub_info;
+	u32 val;
+
+	val = rtw89_read32(rtwdev, R_BE_PUB_PAGE_INFO1);
+	info->g0_used = u32_get_bits(val, B_BE_G0_USE_PG_MASK);
+	info->g1_used = u32_get_bits(val, B_BE_G1_USE_PG_MASK);
+
+	val = rtw89_read32(rtwdev, R_BE_PUB_PAGE_INFO3);
+	info->g0_aval = u32_get_bits(val, B_BE_G0_AVAL_PG_MASK);
+	info->g1_aval = u32_get_bits(val, B_BE_G1_AVAL_PG_MASK);
+	info->pub_aval = u32_get_bits(rtw89_read32(rtwdev, R_BE_PUB_PAGE_INFO2),
+				      B_BE_PUB_AVAL_PG_MASK);
+	info->wp_aval = u32_get_bits(rtw89_read32(rtwdev, R_BE_WP_PAGE_INFO1),
+				     B_BE_WP_AVAL_PG_MASK);
+
+	val = rtw89_read32(rtwdev, R_BE_HCI_FC_CTRL);
+	param->en = !!(val & B_BE_HCI_FC_EN);
+	param->h2c_en = !!(val & B_BE_HCI_FC_CH12_EN);
+	param->mode = u32_get_bits(val, B_BE_HCI_FC_MODE_MASK);
+	prec_cfg->ch011_full_cond = u32_get_bits(val, B_BE_HCI_FC_WD_FULL_COND_MASK);
+	prec_cfg->h2c_full_cond = u32_get_bits(val, B_BE_HCI_FC_CH12_FULL_COND_MASK);
+	prec_cfg->wp_ch07_full_cond =
+		u32_get_bits(val, B_BE_HCI_FC_WP_CH07_FULL_COND_MASK);
+	prec_cfg->wp_ch811_full_cond =
+		u32_get_bits(val, B_BE_HCI_FC_WP_CH811_FULL_COND_MASK);
+
+	val = rtw89_read32(rtwdev, R_BE_CH_PAGE_CTRL);
+	prec_cfg->ch011_prec = u32_get_bits(val, B_BE_PREC_PAGE_CH011_V1_MASK);
+	prec_cfg->h2c_prec = u32_get_bits(val, B_BE_PREC_PAGE_CH12_V1_MASK);
+
+	val = rtw89_read32(rtwdev, R_BE_PUB_PAGE_CTRL2);
+	pub_cfg->pub_max = u32_get_bits(val, B_BE_PUBPG_ALL_MASK);
+
+	val = rtw89_read32(rtwdev, R_BE_WP_PAGE_CTRL1);
+	prec_cfg->wp_ch07_prec = u32_get_bits(val, B_BE_PREC_PAGE_WP_CH07_MASK);
+	prec_cfg->wp_ch811_prec = u32_get_bits(val, B_BE_PREC_PAGE_WP_CH811_MASK);
+
+	val = rtw89_read32(rtwdev, R_BE_WP_PAGE_CTRL2);
+	pub_cfg->wp_thrd = u32_get_bits(val, B_BE_WP_THRD_MASK);
+
+	val = rtw89_read32(rtwdev, R_BE_PUB_PAGE_CTRL1);
+	pub_cfg->grp0 = u32_get_bits(val, B_BE_PUBPG_G0_MASK);
+	pub_cfg->grp1 = u32_get_bits(val, B_BE_PUBPG_G1_MASK);
+}
+
+static void hfc_h2c_cfg_be(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_hfc_param *param = &rtwdev->mac.hfc_param;
+	const struct rtw89_hfc_prec_cfg *prec_cfg = &param->prec_cfg;
+	u32 val;
+
+	val = u32_encode_bits(prec_cfg->h2c_prec, B_BE_PREC_PAGE_CH12_V1_MASK);
+	rtw89_write32(rtwdev, R_BE_CH_PAGE_CTRL, val);
+}
+
+static void hfc_mix_cfg_be(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_hfc_param *param = &rtwdev->mac.hfc_param;
+	const struct rtw89_hfc_prec_cfg *prec_cfg = &param->prec_cfg;
+	const struct rtw89_hfc_pub_cfg *pub_cfg = &param->pub_cfg;
+	u32 val;
+
+	val = u32_encode_bits(prec_cfg->ch011_prec, B_BE_PREC_PAGE_CH011_V1_MASK) |
+	      u32_encode_bits(prec_cfg->h2c_prec, B_BE_PREC_PAGE_CH12_V1_MASK);
+	rtw89_write32(rtwdev, R_BE_CH_PAGE_CTRL, val);
+
+	val = u32_encode_bits(pub_cfg->pub_max, B_BE_PUBPG_ALL_MASK);
+	rtw89_write32(rtwdev, R_BE_PUB_PAGE_CTRL2, val);
+
+	val = u32_encode_bits(prec_cfg->wp_ch07_prec, B_BE_PREC_PAGE_WP_CH07_MASK) |
+	      u32_encode_bits(prec_cfg->wp_ch811_prec, B_BE_PREC_PAGE_WP_CH811_MASK);
+	rtw89_write32(rtwdev, R_BE_WP_PAGE_CTRL1, val);
+
+	val = u32_replace_bits(rtw89_read32(rtwdev, R_BE_HCI_FC_CTRL),
+			       param->mode, B_BE_HCI_FC_MODE_MASK);
+	val = u32_replace_bits(val, prec_cfg->ch011_full_cond,
+			       B_BE_HCI_FC_WD_FULL_COND_MASK);
+	val = u32_replace_bits(val, prec_cfg->h2c_full_cond,
+			       B_BE_HCI_FC_CH12_FULL_COND_MASK);
+	val = u32_replace_bits(val, prec_cfg->wp_ch07_full_cond,
+			       B_BE_HCI_FC_WP_CH07_FULL_COND_MASK);
+	val = u32_replace_bits(val, prec_cfg->wp_ch811_full_cond,
+			       B_BE_HCI_FC_WP_CH811_FULL_COND_MASK);
+	rtw89_write32(rtwdev, R_BE_HCI_FC_CTRL, val);
+}
+
+static void hfc_func_en_be(struct rtw89_dev *rtwdev, bool en, bool h2c_en)
+{
+	struct rtw89_hfc_param *param = &rtwdev->mac.hfc_param;
+	u32 val;
+
+	val = rtw89_read32(rtwdev, R_BE_HCI_FC_CTRL);
+	param->en = en;
+	param->h2c_en = h2c_en;
+	val = en ? (val | B_BE_HCI_FC_EN) : (val & ~B_BE_HCI_FC_EN);
+	val = h2c_en ? (val | B_BE_HCI_FC_CH12_EN) :
+		       (val & ~B_BE_HCI_FC_CH12_EN);
+	rtw89_write32(rtwdev, R_BE_HCI_FC_CTRL, val);
+}
+
+static void dle_func_en_be(struct rtw89_dev *rtwdev, bool enable)
+{
+	if (enable)
+		rtw89_write32_set(rtwdev, R_BE_DMAC_FUNC_EN,
+				  B_BE_DLE_WDE_EN | B_BE_DLE_PLE_EN);
+	else
+		rtw89_write32_clr(rtwdev, R_BE_DMAC_FUNC_EN,
+				  B_BE_DLE_WDE_EN | B_BE_DLE_PLE_EN);
+}
+
+static void dle_clk_en_be(struct rtw89_dev *rtwdev, bool enable)
+{
+	if (enable)
+		rtw89_write32_set(rtwdev, R_BE_DMAC_CLK_EN,
+				  B_BE_DLE_WDE_CLK_EN | B_BE_DLE_PLE_CLK_EN);
+	else
+		rtw89_write32_clr(rtwdev, R_BE_DMAC_CLK_EN,
+				  B_BE_DLE_WDE_CLK_EN | B_BE_DLE_PLE_CLK_EN);
+}
+
+static int dle_mix_cfg_be(struct rtw89_dev *rtwdev, const struct rtw89_dle_mem *cfg)
+{
+	const struct rtw89_dle_size *wde_size_cfg, *ple_size_cfg;
+	u32 bound;
+	u32 val;
+
+	wde_size_cfg = cfg->wde_size;
+	ple_size_cfg = cfg->ple_size;
+
+	val = rtw89_read32(rtwdev, R_BE_WDE_PKTBUF_CFG);
+
+	switch (wde_size_cfg->pge_size) {
+	default:
+	case RTW89_WDE_PG_64:
+		val = u32_replace_bits(val, S_AX_WDE_PAGE_SEL_64,
+				       B_BE_WDE_PAGE_SEL_MASK);
+		break;
+	case RTW89_WDE_PG_128:
+		val = u32_replace_bits(val, S_AX_WDE_PAGE_SEL_128,
+				       B_BE_WDE_PAGE_SEL_MASK);
+		break;
+	case RTW89_WDE_PG_256:
+		rtw89_err(rtwdev, "[ERR]WDE DLE doesn't support 256 byte!\n");
+		return -EINVAL;
+	}
+
+	bound = wde_size_cfg->srt_ofst / DLE_BOUND_UNIT;
+	val = u32_replace_bits(val, bound, B_BE_WDE_START_BOUND_MASK);
+	val = u32_replace_bits(val, wde_size_cfg->lnk_pge_num,
+			       B_BE_WDE_FREE_PAGE_NUM_MASK);
+	rtw89_write32(rtwdev, R_BE_WDE_PKTBUF_CFG, val);
+
+	val = rtw89_read32(rtwdev, R_BE_PLE_PKTBUF_CFG);
+
+	switch (ple_size_cfg->pge_size) {
+	default:
+	case RTW89_PLE_PG_64:
+		rtw89_err(rtwdev, "[ERR]PLE DLE doesn't support 64 byte!\n");
+		return -EINVAL;
+	case RTW89_PLE_PG_128:
+		val = u32_replace_bits(val, S_AX_PLE_PAGE_SEL_128,
+				       B_BE_PLE_PAGE_SEL_MASK);
+		break;
+	case RTW89_PLE_PG_256:
+		val = u32_replace_bits(val, S_AX_PLE_PAGE_SEL_256,
+				       B_BE_PLE_PAGE_SEL_MASK);
+		break;
+	}
+
+	bound = ple_size_cfg->srt_ofst / DLE_BOUND_UNIT;
+	val = u32_replace_bits(val, bound, B_BE_PLE_START_BOUND_MASK);
+	val = u32_replace_bits(val, ple_size_cfg->lnk_pge_num,
+			       B_BE_PLE_FREE_PAGE_NUM_MASK);
+	rtw89_write32(rtwdev, R_BE_PLE_PKTBUF_CFG, val);
+
+	return 0;
+}
+
+static int chk_dle_rdy_be(struct rtw89_dev *rtwdev, bool wde_or_ple)
+{
+	u32 reg, mask;
+	u32 ini;
+
+	if (wde_or_ple) {
+		reg = R_AX_WDE_INI_STATUS;
+		mask = WDE_MGN_INI_RDY;
+	} else {
+		reg = R_AX_PLE_INI_STATUS;
+		mask = PLE_MGN_INI_RDY;
+	}
+
+	return read_poll_timeout(rtw89_read32, ini, (ini & mask) == mask, 1,
+				2000, false, rtwdev, reg);
+}
+
+#define INVALID_QT_WCPU U16_MAX
+#define SET_QUOTA_VAL(_min_x, _max_x, _module, _idx)			\
+	do {								\
+		val = u32_encode_bits(_min_x, B_BE_ ## _module ## _Q ## _idx ## _MIN_SIZE_MASK) | \
+		      u32_encode_bits(_max_x, B_BE_ ## _module ## _Q ## _idx ## _MAX_SIZE_MASK);  \
+		rtw89_write32(rtwdev,					\
+			      R_BE_ ## _module ## _QTA ## _idx ## _CFG,	\
+			      val);					\
+	} while (0)
+#define SET_QUOTA(_x, _module, _idx)					\
+	SET_QUOTA_VAL(min_cfg->_x, max_cfg->_x, _module, _idx)
+
+static void wde_quota_cfg_be(struct rtw89_dev *rtwdev,
+			     const struct rtw89_wde_quota *min_cfg,
+			     const struct rtw89_wde_quota *max_cfg,
+			     u16 ext_wde_min_qt_wcpu)
+{
+	u16 min_qt_wcpu = ext_wde_min_qt_wcpu != INVALID_QT_WCPU ?
+			  ext_wde_min_qt_wcpu : min_cfg->wcpu;
+	u16 max_qt_wcpu = max(max_cfg->wcpu, min_qt_wcpu);
+	u32 val;
+
+	SET_QUOTA(hif, WDE, 0);
+	SET_QUOTA_VAL(min_qt_wcpu, max_qt_wcpu, WDE, 1);
+	SET_QUOTA_VAL(0, 0, WDE, 2);
+	SET_QUOTA(pkt_in, WDE, 3);
+	SET_QUOTA(cpu_io, WDE, 4);
+}
+
+static void ple_quota_cfg_be(struct rtw89_dev *rtwdev,
+			     const struct rtw89_ple_quota *min_cfg,
+			     const struct rtw89_ple_quota *max_cfg)
+{
+	u32 val;
+
+	SET_QUOTA(cma0_tx, PLE, 0);
+	SET_QUOTA(cma1_tx, PLE, 1);
+	SET_QUOTA(c2h, PLE, 2);
+	SET_QUOTA(h2c, PLE, 3);
+	SET_QUOTA(wcpu, PLE, 4);
+	SET_QUOTA(mpdu_proc, PLE, 5);
+	SET_QUOTA(cma0_dma, PLE, 6);
+	SET_QUOTA(cma1_dma, PLE, 7);
+	SET_QUOTA(bb_rpt, PLE, 8);
+	SET_QUOTA(wd_rel, PLE, 9);
+	SET_QUOTA(cpu_io, PLE, 10);
+	SET_QUOTA(tx_rpt, PLE, 11);
+	SET_QUOTA(h2d, PLE, 12);
+}
+
+static void rtw89_mac_hci_func_en_be(struct rtw89_dev *rtwdev)
+{
+	rtw89_write32_set(rtwdev, R_BE_HCI_FUNC_EN, B_BE_HCI_TXDMA_EN |
+						    B_BE_HCI_RXDMA_EN);
+}
+
+static void rtw89_mac_dmac_func_pre_en_be(struct rtw89_dev *rtwdev)
+{
+	u32 val;
+
+	val = rtw89_read32(rtwdev, R_BE_HAXI_INIT_CFG1);
+
+	switch (rtwdev->hci.type) {
+	case RTW89_HCI_TYPE_PCIE:
+		val = u32_replace_bits(val, S_BE_DMA_MOD_PCIE_NO_DATA_CPU,
+				       B_BE_DMA_MODE_MASK);
+		break;
+	case RTW89_HCI_TYPE_USB:
+		val = u32_replace_bits(val, S_BE_DMA_MOD_USB, B_BE_DMA_MODE_MASK);
+		val = (val & ~B_BE_STOP_AXI_MST) | B_BE_TXDMA_EN | B_BE_RXDMA_EN;
+		break;
+	case RTW89_HCI_TYPE_SDIO:
+		val = u32_replace_bits(val, S_BE_DMA_MOD_SDIO, B_BE_DMA_MODE_MASK);
+		val = (val & ~B_BE_STOP_AXI_MST) | B_BE_TXDMA_EN | B_BE_RXDMA_EN;
+		break;
+	default:
+		return;
+	}
+
+	rtw89_write32(rtwdev, R_BE_HAXI_INIT_CFG1, val);
+
+	rtw89_write32_clr(rtwdev, R_BE_HAXI_DMA_STOP1,
+			  B_BE_STOP_CH0 | B_BE_STOP_CH1 | B_BE_STOP_CH2 |
+			  B_BE_STOP_CH3 | B_BE_STOP_CH4 | B_BE_STOP_CH5 |
+			  B_BE_STOP_CH6 | B_BE_STOP_CH7 | B_BE_STOP_CH8 |
+			  B_BE_STOP_CH9 | B_BE_STOP_CH10 | B_BE_STOP_CH11 |
+			  B_BE_STOP_CH12 | B_BE_STOP_CH13 | B_BE_STOP_CH14);
+
+	rtw89_write32_set(rtwdev, R_BE_DMAC_TABLE_CTRL, B_BE_DMAC_ADDR_MODE);
+}
+
+static
+int rtw89_mac_write_xtal_si_be(struct rtw89_dev *rtwdev, u8 offset, u8 val, u8 mask)
+{
+	u32 val32;
+	int ret;
+
+	val32 = u32_encode_bits(offset, B_BE_WL_XTAL_SI_ADDR_MASK) |
+		u32_encode_bits(val, B_BE_WL_XTAL_SI_DATA_MASK) |
+		u32_encode_bits(mask, B_BE_WL_XTAL_SI_BITMASK_MASK) |
+		u32_encode_bits(XTAL_SI_NORMAL_WRITE, B_BE_WL_XTAL_SI_MODE_MASK) |
+		u32_encode_bits(0, B_BE_WL_XTAL_SI_CHIPID_MASK) |
+		B_BE_WL_XTAL_SI_CMD_POLL;
+	rtw89_write32(rtwdev, R_BE_WLAN_XTAL_SI_CTRL, val32);
+
+	ret = read_poll_timeout(rtw89_read32, val32, !(val32 & B_BE_WL_XTAL_SI_CMD_POLL),
+				50, 50000, false, rtwdev, R_BE_WLAN_XTAL_SI_CTRL);
+	if (ret) {
+		rtw89_warn(rtwdev, "xtal si not ready(W): offset=%x val=%x mask=%x\n",
+			   offset, val, mask);
+		return ret;
+	}
+
+	return 0;
+}
+
+static
+int rtw89_mac_read_xtal_si_be(struct rtw89_dev *rtwdev, u8 offset, u8 *val)
+{
+	u32 val32;
+	int ret;
+
+	val32 = u32_encode_bits(offset, B_BE_WL_XTAL_SI_ADDR_MASK) |
+		u32_encode_bits(0x0, B_BE_WL_XTAL_SI_DATA_MASK) |
+		u32_encode_bits(0x0, B_BE_WL_XTAL_SI_BITMASK_MASK) |
+		u32_encode_bits(XTAL_SI_NORMAL_READ, B_BE_WL_XTAL_SI_MODE_MASK) |
+		u32_encode_bits(0, B_BE_WL_XTAL_SI_CHIPID_MASK) |
+		B_BE_WL_XTAL_SI_CMD_POLL;
+	rtw89_write32(rtwdev, R_BE_WLAN_XTAL_SI_CTRL, val32);
+
+	ret = read_poll_timeout(rtw89_read32, val32, !(val32 & B_BE_WL_XTAL_SI_CMD_POLL),
+				50, 50000, false, rtwdev, R_BE_WLAN_XTAL_SI_CTRL);
+	if (ret) {
+		rtw89_warn(rtwdev, "xtal si not ready(R): offset=%x\n", offset);
+		return ret;
+	}
+
+	*val = rtw89_read8(rtwdev, R_BE_WLAN_XTAL_SI_CTRL + 1);
+
+	return 0;
+}
+
 static void rtw89_mac_disable_cpu_be(struct rtw89_dev *rtwdev)
 {
 	u32 val32;
@@ -92,8 +456,6 @@ static int wcpu_on(struct rtw89_dev *rtwdev, u8 boot_reason, bool dlfw)
 	u32 val32;
 	int ret;
 
-	rtw89_write32_set(rtwdev, R_BE_UDM0, B_BE_UDM0_DBG_MODE_CTRL);
-
 	val32 = rtw89_read32(rtwdev, R_BE_HALT_C2H);
 	if (val32) {
 		rtw89_warn(rtwdev, "[SER] AON L2 Debug register not empty before Boot.\n");
@@ -117,6 +479,10 @@ static int wcpu_on(struct rtw89_dev *rtwdev, u8 boot_reason, bool dlfw)
 	rtw89_write32(rtwdev, R_BE_HALT_H2C_CTRL, 0);
 	rtw89_write32(rtwdev, R_BE_HALT_C2H_CTRL, 0);
 
+	val32 = rtw89_read32(rtwdev, R_BE_HISR0);
+	rtw89_write32(rtwdev, R_BE_HISR0, B_BE_HALT_C2H_INT);
+	rtw89_debug(rtwdev, RTW89_DBG_SER, "HISR0=0x%x\n", val32);
+
 	rtw89_write32_set(rtwdev, R_BE_SYS_CLK_CTRL, B_BE_CPU_CLK_EN);
 	rtw89_write32_clr(rtwdev, R_BE_SYS_CFG5,
 			  B_BE_WDT_WAKE_PCIE_EN | B_BE_WDT_WAKE_USB_EN);
@@ -205,6 +571,1153 @@ static int rtw89_fwdl_check_path_ready_be(struct rtw89_dev *rtwdev,
 					rtwdev, R_BE_WCPU_FW_CTRL);
 }
 
+static int dmac_func_en_be(struct rtw89_dev *rtwdev)
+{
+	return 0;
+}
+
+static int cmac_func_en_be(struct rtw89_dev *rtwdev, u8 mac_idx, bool en)
+{
+	u32 reg;
+
+	if (mac_idx > RTW89_MAC_1)
+		return -EINVAL;
+
+	if (mac_idx == RTW89_MAC_0)
+		return 0;
+
+	if (en) {
+		rtw89_write32_set(rtwdev, R_BE_AFE_CTRL1, B_BE_AFE_CTRL1_SET);
+		rtw89_write32_clr(rtwdev, R_BE_SYS_ISO_CTRL_EXTEND, B_BE_R_SYM_ISO_CMAC12PP);
+		rtw89_write32_set(rtwdev, R_BE_FEN_RST_ENABLE, B_BE_CMAC1_FEN);
+
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_CK_EN, mac_idx);
+		rtw89_write32_set(rtwdev, reg, B_BE_CK_EN_SET);
+
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_CMAC_FUNC_EN, mac_idx);
+		rtw89_write32_set(rtwdev, reg, B_BE_CMAC_FUNC_EN_SET);
+
+		set_bit(RTW89_FLAG_CMAC1_FUNC, rtwdev->flags);
+	} else {
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_CMAC_FUNC_EN, mac_idx);
+		rtw89_write32_clr(rtwdev, reg, B_BE_CMAC_FUNC_EN_SET);
+
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_CK_EN, mac_idx);
+		rtw89_write32_clr(rtwdev, reg, B_BE_CK_EN_SET);
+
+		rtw89_write32_clr(rtwdev, R_BE_FEN_RST_ENABLE, B_BE_CMAC1_FEN);
+		rtw89_write32_set(rtwdev, R_BE_SYS_ISO_CTRL_EXTEND, B_BE_R_SYM_ISO_CMAC12PP);
+		rtw89_write32_clr(rtwdev, R_BE_AFE_CTRL1, B_BE_AFE_CTRL1_SET);
+
+		clear_bit(RTW89_FLAG_CMAC1_FUNC, rtwdev->flags);
+	}
+
+	return 0;
+}
+
+static int chip_func_en_be(struct rtw89_dev *rtwdev)
+{
+	return 0;
+}
+
+static int sys_init_be(struct rtw89_dev *rtwdev)
+{
+	int ret;
+
+	ret = dmac_func_en_be(rtwdev);
+	if (ret)
+		return ret;
+
+	ret = cmac_func_en_be(rtwdev, RTW89_MAC_0, true);
+	if (ret)
+		return ret;
+
+	ret = chip_func_en_be(rtwdev);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+
+static int sta_sch_init_be(struct rtw89_dev *rtwdev)
+{
+	u32 p_val;
+	int ret;
+
+	ret = rtw89_mac_check_mac_en(rtwdev, RTW89_MAC_0, RTW89_DMAC_SEL);
+	if (ret)
+		return ret;
+
+	rtw89_write8_set(rtwdev, R_BE_SS_CTRL, B_BE_SS_EN);
+
+	ret = read_poll_timeout(rtw89_read32, p_val, p_val & B_BE_SS_INIT_DONE,
+				1, TRXCFG_WAIT_CNT, false, rtwdev, R_BE_SS_CTRL);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]STA scheduler init\n");
+		return ret;
+	}
+
+	rtw89_write32_set(rtwdev, R_BE_SS_CTRL, B_BE_WARM_INIT);
+	rtw89_write32_clr(rtwdev, R_BE_SS_CTRL, B_BE_BAND_TRIG_EN | B_BE_BAND1_TRIG_EN);
+
+	return 0;
+}
+
+static int mpdu_proc_init_be(struct rtw89_dev *rtwdev)
+{
+	u32 val32;
+	int ret;
+
+	ret = rtw89_mac_check_mac_en(rtwdev, RTW89_MAC_0, RTW89_DMAC_SEL);
+	if (ret)
+		return ret;
+
+	rtw89_write32_set(rtwdev, R_BE_MPDU_PROC, B_BE_APPEND_FCS);
+	rtw89_write32(rtwdev, R_BE_CUT_AMSDU_CTRL, TRXCFG_MPDU_PROC_CUT_CTRL);
+
+	val32 = rtw89_read32(rtwdev, R_BE_HDR_SHCUT_SETTING);
+	val32 |= (B_BE_TX_HW_SEQ_EN | B_BE_TX_HW_ACK_POLICY_EN | B_BE_TX_MAC_MPDU_PROC_EN);
+	val32 &= ~B_BE_TX_ADDR_MLD_TO_LIK;
+	rtw89_write32_set(rtwdev, R_BE_HDR_SHCUT_SETTING, val32);
+
+	rtw89_write32(rtwdev, R_BE_RX_HDRTRNS, TRXCFG_MPDU_PROC_RX_HDR_CONV);
+
+	val32 = rtw89_read32(rtwdev, R_BE_DISP_FWD_WLAN_0);
+	val32 = u32_replace_bits(val32, 1, B_BE_FWD_WLAN_CPU_TYPE_0_DATA_MASK);
+	val32 = u32_replace_bits(val32, 1, B_BE_FWD_WLAN_CPU_TYPE_0_MNG_MASK);
+	val32 = u32_replace_bits(val32, 1, B_BE_FWD_WLAN_CPU_TYPE_0_CTL_MASK);
+	val32 = u32_replace_bits(val32, 1, B_BE_FWD_WLAN_CPU_TYPE_1_MASK);
+	rtw89_write32(rtwdev, R_BE_DISP_FWD_WLAN_0, val32);
+
+	return 0;
+}
+
+static int sec_eng_init_be(struct rtw89_dev *rtwdev)
+{
+	u32 val32;
+	int ret;
+
+	ret = rtw89_mac_check_mac_en(rtwdev, RTW89_MAC_0, RTW89_DMAC_SEL);
+	if (ret)
+		return ret;
+
+	val32 = rtw89_read32(rtwdev, R_BE_SEC_ENG_CTRL);
+	val32 |= B_BE_CLK_EN_CGCMP | B_BE_CLK_EN_WAPI | B_BE_CLK_EN_WEP_TKIP |
+		 B_BE_SEC_TX_ENC | B_BE_SEC_RX_DEC |
+		 B_BE_MC_DEC | B_BE_BC_DEC |
+		 B_BE_BMC_MGNT_DEC | B_BE_UC_MGNT_DEC;
+	val32 &= ~B_BE_SEC_PRE_ENQUE_TX;
+	rtw89_write32(rtwdev, R_BE_SEC_ENG_CTRL, val32);
+
+	rtw89_write32_set(rtwdev, R_BE_SEC_MPDU_PROC, B_BE_APPEND_ICV | B_BE_APPEND_MIC);
+
+	return 0;
+}
+
+static int txpktctrl_init_be(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_mac_dle_rsvd_qt_cfg qt_cfg;
+	u32 val32;
+	int ret;
+
+	ret = rtw89_mac_get_dle_rsvd_qt_cfg(rtwdev, DLE_RSVD_QT_MPDU_INFO, &qt_cfg);
+	if (ret) {
+		rtw89_err(rtwdev, "get dle rsvd qt %d cfg fail %d\n",
+			  DLE_RSVD_QT_MPDU_INFO, ret);
+		return ret;
+	}
+
+	val32 = rtw89_read32(rtwdev, R_BE_TXPKTCTL_MPDUINFO_CFG);
+	val32 = u32_replace_bits(val32, qt_cfg.pktid, B_BE_MPDUINFO_PKTID_MASK);
+	val32 = u32_replace_bits(val32, MPDU_INFO_B1_OFST, B_BE_MPDUINFO_B1_BADDR_MASK);
+	val32 |= B_BE_MPDUINFO_FEN;
+	rtw89_write32(rtwdev, R_BE_TXPKTCTL_MPDUINFO_CFG, val32);
+
+	return 0;
+}
+
+static int mlo_init_be(struct rtw89_dev *rtwdev)
+{
+	u32 val32;
+	int ret;
+
+	val32 = rtw89_read32(rtwdev, R_BE_MLO_INIT_CTL);
+
+	val32 |= B_BE_MLO_TABLE_REINIT;
+	rtw89_write32(rtwdev, R_BE_MLO_INIT_CTL, val32);
+	val32 &= ~B_BE_MLO_TABLE_REINIT;
+	rtw89_write32(rtwdev, R_BE_MLO_INIT_CTL, val32);
+
+	ret = read_poll_timeout_atomic(rtw89_read32, val32,
+				       val32 & B_BE_MLO_TABLE_INIT_DONE,
+				       1, 1000, false, rtwdev, R_BE_MLO_INIT_CTL);
+	if (ret)
+		rtw89_err(rtwdev, "[MLO]%s: MLO init polling timeout\n", __func__);
+
+	rtw89_write32_set(rtwdev, R_BE_SS_CTRL, B_BE_MLO_HW_CHGLINK_EN);
+	rtw89_write32_set(rtwdev, R_BE_CMAC_SHARE_ACQCHK_CFG_0, B_BE_R_MACID_ACQ_CHK_EN);
+
+	return ret;
+}
+
+static int dmac_init_be(struct rtw89_dev *rtwdev, u8 mac_idx)
+{
+	int ret;
+
+	ret = rtw89_mac_dle_init(rtwdev, rtwdev->mac.qta_mode, RTW89_QTA_INVALID);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]DLE init %d\n", ret);
+		return ret;
+	}
+
+	ret = rtw89_mac_preload_init(rtwdev, RTW89_MAC_0, rtwdev->mac.qta_mode);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]preload init %d\n", ret);
+		return ret;
+	}
+
+	ret = rtw89_mac_hfc_init(rtwdev, true, true, true);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]HCI FC init %d\n", ret);
+		return ret;
+	}
+
+	ret = sta_sch_init_be(rtwdev);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]STA SCH init %d\n", ret);
+		return ret;
+	}
+
+	ret = mpdu_proc_init_be(rtwdev);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]MPDU Proc init %d\n", ret);
+		return ret;
+	}
+
+	ret = sec_eng_init_be(rtwdev);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]Security Engine init %d\n", ret);
+		return ret;
+	}
+
+	ret = txpktctrl_init_be(rtwdev);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]TX pkt ctrl init %d\n", ret);
+		return ret;
+	}
+
+	ret = mlo_init_be(rtwdev);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]MLO init %d\n", ret);
+		return ret;
+	}
+
+	return ret;
+}
+
+static int scheduler_init_be(struct rtw89_dev *rtwdev, u8 mac_idx)
+{
+	u32 val32;
+	u32 reg;
+	int ret;
+
+	ret = rtw89_mac_check_mac_en(rtwdev, mac_idx, RTW89_CMAC_SEL);
+	if (ret)
+		return ret;
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_HE_CTN_CHK_CCA_NAV, mac_idx);
+	val32 = B_BE_HE_CTN_CHK_CCA_P20 | B_BE_HE_CTN_CHK_EDCCA_P20 |
+		B_BE_HE_CTN_CHK_CCA_BITMAP | B_BE_HE_CTN_CHK_EDCCA_BITMAP |
+		B_BE_HE_CTN_CHK_NO_GNT_WL | B_BE_HE_CTN_CHK_BASIC_NAV |
+		B_BE_HE_CTN_CHK_INTRA_NAV | B_BE_HE_CTN_CHK_TX_NAV;
+	rtw89_write32(rtwdev, reg, val32);
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_HE_SIFS_CHK_CCA_NAV, mac_idx);
+	val32 = B_BE_HE_SIFS_CHK_EDCCA_P20 | B_BE_HE_SIFS_CHK_EDCCA_BITMAP |
+		B_BE_HE_SIFS_CHK_NO_GNT_WL;
+	rtw89_write32(rtwdev, reg, val32);
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_TB_CHK_CCA_NAV, mac_idx);
+	val32 = B_BE_TB_CHK_EDCCA_BITMAP | B_BE_TB_CHK_NO_GNT_WL | B_BE_TB_CHK_BASIC_NAV;
+	rtw89_write32(rtwdev, reg, val32);
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_CCA_CFG_0, mac_idx);
+	rtw89_write32_clr(rtwdev, reg, B_BE_NO_GNT_WL_EN);
+
+	if (is_qta_poh(rtwdev)) {
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_PREBKF_CFG_0, mac_idx);
+		rtw89_write32_mask(rtwdev, reg, B_BE_PREBKF_TIME_MASK,
+				   SCH_PREBKF_24US);
+
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_CTN_CFG_0, mac_idx);
+		rtw89_write32_mask(rtwdev, reg, B_BE_PREBKF_TIME_NONAC_MASK,
+				   SCH_PREBKF_24US);
+	}
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_EDCA_BCNQ_PARAM, mac_idx);
+	rtw89_write32_mask(rtwdev, reg, B_BE_BCNQ_CW_MASK, 0x32);
+	rtw89_write32_mask(rtwdev, reg, B_BE_BCNQ_AIFS_MASK, BCN_IFS_25US);
+
+	return 0;
+}
+
+static int addr_cam_init_be(struct rtw89_dev *rtwdev, u8 mac_idx)
+{
+	u32 val32;
+	u16 val16;
+	u32 reg;
+	int ret;
+
+	ret = rtw89_mac_check_mac_en(rtwdev, mac_idx, RTW89_CMAC_SEL);
+	if (ret)
+		return ret;
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_ADDR_CAM_CTRL, mac_idx);
+	val32 = rtw89_read32(rtwdev, reg);
+	val32 = u32_replace_bits(val32, ADDR_CAM_SERCH_RANGE, B_BE_ADDR_CAM_RANGE_MASK);
+	val32 |= B_BE_ADDR_CAM_EN;
+	if (mac_idx == RTW89_MAC_0)
+		val32 |= B_BE_ADDR_CAM_CLR;
+	rtw89_write32(rtwdev, reg, val32);
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_ADDR_CAM_CTRL, mac_idx);
+	ret = read_poll_timeout_atomic(rtw89_read16, val16, !(val16 & B_BE_ADDR_CAM_CLR),
+				       1, TRXCFG_WAIT_CNT, false, rtwdev, reg);
+	if (ret)
+		rtw89_err(rtwdev, "[ERR]ADDR_CAM reset\n");
+
+	return ret;
+}
+
+static int rtw89_mac_typ_fltr_opt_be(struct rtw89_dev *rtwdev,
+				     enum rtw89_machdr_frame_type type,
+				     enum rtw89_mac_fwd_target fwd_target,
+				     u8 mac_idx)
+{
+	u32 reg;
+	u32 val;
+
+	switch (fwd_target) {
+	case RTW89_FWD_DONT_CARE:
+		val = RX_FLTR_FRAME_DROP_BE;
+		break;
+	case RTW89_FWD_TO_HOST:
+	case RTW89_FWD_TO_WLAN_CPU:
+		val = RX_FLTR_FRAME_ACCEPT_BE;
+		break;
+	default:
+		rtw89_err(rtwdev, "[ERR]set rx filter fwd target err\n");
+		return -EINVAL;
+	}
+
+	switch (type) {
+	case RTW89_MGNT:
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_MGNT_FLTR, mac_idx);
+		break;
+	case RTW89_CTRL:
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_CTRL_FLTR, mac_idx);
+		break;
+	case RTW89_DATA:
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_DATA_FLTR, mac_idx);
+		break;
+	default:
+		rtw89_err(rtwdev, "[ERR]set rx filter type err\n");
+		return -EINVAL;
+	}
+	rtw89_write32(rtwdev, reg, val);
+
+	return 0;
+}
+
+static int rx_fltr_init_be(struct rtw89_dev *rtwdev, u8 mac_idx)
+{
+	u32 reg;
+	u32 val;
+
+	rtw89_mac_typ_fltr_opt_be(rtwdev, RTW89_MGNT, RTW89_FWD_TO_HOST, mac_idx);
+	rtw89_mac_typ_fltr_opt_be(rtwdev, RTW89_CTRL, RTW89_FWD_TO_HOST, mac_idx);
+	rtw89_mac_typ_fltr_opt_be(rtwdev, RTW89_DATA, RTW89_FWD_TO_HOST, mac_idx);
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_RX_FLTR_OPT, mac_idx);
+	val = B_BE_A_BC_CAM_MATCH | B_BE_A_UC_CAM_MATCH | B_BE_A_MC |
+	      B_BE_A_BC | B_BE_A_A1_MATCH | B_BE_SNIFFER_MODE |
+	      u32_encode_bits(15, B_BE_UID_FILTER_MASK);
+	rtw89_write32(rtwdev, reg, val);
+	u32p_replace_bits(&rtwdev->hal.rx_fltr, 15, B_BE_UID_FILTER_MASK);
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_PLCP_HDR_FLTR, mac_idx);
+	val = B_BE_HE_SIGB_CRC_CHK | B_BE_VHT_MU_SIGB_CRC_CHK |
+	      B_BE_VHT_SU_SIGB_CRC_CHK | B_BE_SIGA_CRC_CHK |
+	      B_BE_LSIG_PARITY_CHK_EN | B_BE_CCK_SIG_CHK | B_BE_CCK_CRC_CHK;
+	rtw89_write16(rtwdev, reg, val);
+
+	return 0;
+}
+
+static int cca_ctrl_init_be(struct rtw89_dev *rtwdev, u8 mac_idx)
+{
+	return 0;
+}
+
+static int nav_ctrl_init_be(struct rtw89_dev *rtwdev, u8 mac_idx)
+{
+	u32 val32;
+	u32 reg;
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_WMAC_NAV_CTL, mac_idx);
+
+	val32 = rtw89_read32(rtwdev, reg);
+	val32 &= ~B_BE_WMAC_PLCP_UP_NAV_EN;
+	val32 |= B_BE_WMAC_TF_UP_NAV_EN | B_BE_WMAC_NAV_UPPER_EN;
+	val32 = u32_replace_bits(val32, NAV_25MS, B_BE_WMAC_NAV_UPPER_MASK);
+
+	rtw89_write32(rtwdev, reg, val32);
+
+	return 0;
+}
+
+static int spatial_reuse_init_be(struct rtw89_dev *rtwdev, u8 mac_idx)
+{
+	u32 reg;
+	int ret;
+
+	ret = rtw89_mac_check_mac_en(rtwdev, mac_idx, RTW89_CMAC_SEL);
+	if (ret)
+		return ret;
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_RX_SR_CTRL, mac_idx);
+	rtw89_write8_clr(rtwdev, reg, B_BE_SR_EN | B_BE_SR_CTRL_PLCP_EN);
+
+	return 0;
+}
+
+static int tmac_init_be(struct rtw89_dev *rtwdev, u8 mac_idx)
+{
+	u32 reg;
+
+	rtw89_write32_clr(rtwdev, R_BE_TB_PPDU_CTRL, B_BE_QOSNULL_UPD_MUEDCA_EN);
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_WMTX_TCR_BE_4, mac_idx);
+	rtw89_write32_mask(rtwdev, reg, B_BE_EHT_HE_PPDU_4XLTF_ZLD_USTIMER_MASK, 0x12);
+	rtw89_write32_mask(rtwdev, reg, B_BE_EHT_HE_PPDU_2XLTF_ZLD_USTIMER_MASK, 0xe);
+
+	return 0;
+}
+
+static int trxptcl_init_be(struct rtw89_dev *rtwdev, u8 mac_idx)
+{
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	const struct rtw89_rrsr_cfgs *rrsr = chip->rrsr_cfgs;
+	struct rtw89_hal *hal = &rtwdev->hal;
+	u32 val32;
+	u32 reg;
+	int ret;
+
+	ret = rtw89_mac_check_mac_en(rtwdev, mac_idx, RTW89_CMAC_SEL);
+	if (ret)
+		return ret;
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_MAC_LOOPBACK, mac_idx);
+	val32 = rtw89_read32(rtwdev, reg);
+	val32 = u32_replace_bits(val32, S_BE_MACLBK_PLCP_DLY_DEF,
+				 B_BE_MACLBK_PLCP_DLY_MASK);
+	val32 &= ~B_BE_MACLBK_EN;
+	rtw89_write32(rtwdev, reg, val32);
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_TRXPTCL_RESP_0, mac_idx);
+	val32 = rtw89_read32(rtwdev, reg);
+	val32 = u32_replace_bits(val32, WMAC_SPEC_SIFS_CCK,
+				 B_BE_WMAC_SPEC_SIFS_CCK_MASK);
+	val32 = u32_replace_bits(val32, WMAC_SPEC_SIFS_OFDM_1115E,
+				 B_BE_WMAC_SPEC_SIFS_OFDM_MASK);
+	rtw89_write32(rtwdev, reg, val32);
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_WMAC_ACK_BA_RESP_LEGACY, mac_idx);
+	rtw89_write32_clr(rtwdev, reg, B_BE_ACK_BA_RESP_LEGACY_CHK_EDCCA);
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_WMAC_ACK_BA_RESP_HE, mac_idx);
+	rtw89_write32_clr(rtwdev, reg, B_BE_ACK_BA_RESP_HE_CHK_EDCCA);
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_WMAC_ACK_BA_RESP_EHT_LEG_PUNC, mac_idx);
+	rtw89_write32_clr(rtwdev, reg, B_BE_ACK_BA_EHT_LEG_PUNC_CHK_EDCCA);
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_RXTRIG_TEST_USER_2, mac_idx);
+	rtw89_write32_set(rtwdev, reg, B_BE_RXTRIG_FCSCHK_EN);
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_TRXPTCL_RESP_1, mac_idx);
+	val32 = rtw89_read32(rtwdev, reg);
+	val32 &= B_BE_FTM_RRSR_RATE_EN_MASK | B_BE_WMAC_RESP_DOPPLEB_BE_EN |
+		 B_BE_WMAC_RESP_DCM_EN | B_BE_WMAC_RESP_REF_RATE_MASK;
+	rtw89_write32(rtwdev, reg, val32);
+	rtw89_write32_mask(rtwdev, reg, rrsr->ref_rate.mask, rrsr->ref_rate.data);
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_PTCL_RRSR1, mac_idx);
+	val32 = rtw89_read32(rtwdev, reg);
+	val32 &= B_BE_RRSR_RATE_EN_MASK | B_BE_RRSR_CCK_MASK | B_BE_RSC_MASK;
+	rtw89_write32(rtwdev, reg, val32);
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_PTCL_RRSR0, mac_idx);
+	val32 = rtw89_read32(rtwdev, reg);
+	val32 &= B_BE_RRSR_OFDM_MASK | B_BE_RRSR_HT_MASK | B_BE_RRSR_VHT_MASK |
+		 B_BE_RRSR_HE_MASK;
+	rtw89_write32(rtwdev, reg, val32);
+
+	if (chip->chip_id == RTL8922A && hal->cv == CHIP_CAV) {
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_PTCL_RRSR1, mac_idx);
+		rtw89_write32_mask(rtwdev, reg, B_BE_RSC_MASK, 1);
+	}
+
+	return 0;
+}
+
+static int rst_bacam_be(struct rtw89_dev *rtwdev)
+{
+	u32 val;
+	int ret;
+
+	rtw89_write32_mask(rtwdev, R_BE_RESPBA_CAM_CTRL, B_BE_BACAM_RST_MASK,
+			   S_BE_BACAM_RST_ALL);
+
+	ret = read_poll_timeout_atomic(rtw89_read32_mask, val, val == S_BE_BACAM_RST_DONE,
+				       1, 1000, false,
+				       rtwdev, R_BE_RESPBA_CAM_CTRL, B_BE_BACAM_RST_MASK);
+	if (ret)
+		rtw89_err(rtwdev, "[ERR]bacam rst timeout\n");
+
+	return ret;
+}
+
+#define PLD_RLS_MAX_PG 127
+#define RX_MAX_LEN_UNIT 512
+#define RX_SPEC_MAX_LEN (11454 + RX_MAX_LEN_UNIT)
+
+static int rmac_init_be(struct rtw89_dev *rtwdev, u8 mac_idx)
+{
+	u32 rx_min_qta, rx_max_len, rx_max_pg;
+	u16 val16;
+	u32 reg;
+	int ret;
+
+	ret = rtw89_mac_check_mac_en(rtwdev, mac_idx, RTW89_CMAC_SEL);
+	if (ret)
+		return ret;
+
+	if (mac_idx == RTW89_MAC_0) {
+		ret = rst_bacam_be(rtwdev);
+		if (ret)
+			return ret;
+	}
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_DLK_PROTECT_CTL, mac_idx);
+	val16 = rtw89_read16(rtwdev, reg);
+	val16 = u16_replace_bits(val16, TRXCFG_RMAC_DATA_TO, B_BE_RX_DLK_DATA_TIME_MASK);
+	val16 = u16_replace_bits(val16, TRXCFG_RMAC_CCA_TO, B_BE_RX_DLK_CCA_TIME_MASK);
+	val16 |= B_BE_RX_DLK_RST_EN;
+	rtw89_write16(rtwdev, reg, val16);
+
+	if (mac_idx == RTW89_MAC_0)
+		rx_min_qta = rtwdev->mac.dle_info.c0_rx_qta;
+	else
+		rx_min_qta = rtwdev->mac.dle_info.c1_rx_qta;
+	rx_max_pg = min_t(u32, rx_min_qta, PLD_RLS_MAX_PG);
+	rx_max_len = rx_max_pg * rtwdev->mac.dle_info.ple_pg_size;
+	rx_max_len = min_t(u32, rx_max_len, RX_SPEC_MAX_LEN);
+	rx_max_len /= RX_MAX_LEN_UNIT;
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_RX_FLTR_OPT, mac_idx);
+	rtw89_write32_mask(rtwdev, reg, B_BE_RX_MPDU_MAX_LEN_MASK, rx_max_len);
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_PLCP_HDR_FLTR, mac_idx);
+	rtw89_write8_clr(rtwdev, reg, B_BE_VHT_SU_SIGB_CRC_CHK);
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_RCR, mac_idx);
+	rtw89_write16_set(rtwdev, reg, B_BE_BUSY_CHKSN);
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_RX_PLCP_EXT_OPTION_1, mac_idx);
+	rtw89_write16_set(rtwdev, reg, B_BE_PLCP_SU_PSDU_LEN_SRC);
+
+	return 0;
+}
+
+static int resp_pktctl_init_be(struct rtw89_dev *rtwdev, u8 mac_idx)
+{
+	struct rtw89_mac_dle_rsvd_qt_cfg qt_cfg;
+	enum rtw89_mac_dle_rsvd_qt_type type;
+	u32 reg;
+	int ret;
+
+	if (mac_idx == RTW89_MAC_1)
+		type = DLE_RSVD_QT_B1_CSI;
+	else
+		type = DLE_RSVD_QT_B0_CSI;
+
+	ret = rtw89_mac_get_dle_rsvd_qt_cfg(rtwdev, type, &qt_cfg);
+	if (ret) {
+		rtw89_err(rtwdev, "get dle rsvd qt %d cfg fail %d\n", type, ret);
+		return ret;
+	}
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_RESP_CSI_RESERVED_PAGE, mac_idx);
+	rtw89_write32_mask(rtwdev, reg, B_BE_CSI_RESERVED_START_PAGE_MASK, qt_cfg.pktid);
+	rtw89_write32_mask(rtwdev, reg, B_BE_CSI_RESERVED_PAGE_NUM_MASK, qt_cfg.pg_num);
+
+	return 0;
+}
+
+static int cmac_com_init_be(struct rtw89_dev *rtwdev, u8 mac_idx)
+{
+	u32 val32;
+	int ret;
+
+	ret = rtw89_mac_check_mac_en(rtwdev, mac_idx, RTW89_CMAC_SEL);
+	if (ret)
+		return ret;
+
+	if (mac_idx == RTW89_MAC_0) {
+		val32 = rtw89_read32(rtwdev, R_BE_TX_SUB_BAND_VALUE);
+		val32 = u32_replace_bits(val32, S_BE_TXSB_20M_8, B_BE_TXSB_20M_MASK);
+		val32 = u32_replace_bits(val32, S_BE_TXSB_40M_4, B_BE_TXSB_40M_MASK);
+		val32 = u32_replace_bits(val32, S_BE_TXSB_80M_2, B_BE_TXSB_80M_MASK);
+		val32 = u32_replace_bits(val32, S_BE_TXSB_160M_1, B_BE_TXSB_160M_MASK);
+		rtw89_write32(rtwdev, R_BE_TX_SUB_BAND_VALUE, val32);
+	} else {
+		val32 = rtw89_read32(rtwdev, R_BE_TX_SUB_BAND_VALUE_C1);
+		val32 = u32_replace_bits(val32, S_BE_TXSB_20M_2, B_BE_TXSB_20M_MASK);
+		val32 = u32_replace_bits(val32, S_BE_TXSB_40M_1, B_BE_TXSB_40M_MASK);
+		val32 = u32_replace_bits(val32, S_BE_TXSB_80M_0, B_BE_TXSB_80M_MASK);
+		val32 = u32_replace_bits(val32, S_BE_TXSB_160M_0, B_BE_TXSB_160M_MASK);
+		rtw89_write32(rtwdev, R_BE_TX_SUB_BAND_VALUE_C1, val32);
+	}
+
+	return 0;
+}
+
+static int ptcl_init_be(struct rtw89_dev *rtwdev, u8 mac_idx)
+{
+	u32 val32;
+	u8 val8;
+	u32 reg;
+	int ret;
+
+	ret = rtw89_mac_check_mac_en(rtwdev, mac_idx, RTW89_CMAC_SEL);
+	if (ret)
+		return ret;
+
+	if (is_qta_poh(rtwdev)) {
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_SIFS_SETTING, mac_idx);
+		val32 = rtw89_read32(rtwdev, reg);
+		val32 = u32_replace_bits(val32, S_AX_CTS2S_TH_1K,
+					 B_BE_HW_CTS2SELF_PKT_LEN_TH_MASK);
+		val32 = u32_replace_bits(val32, S_AX_CTS2S_TH_SEC_256B,
+					 B_BE_HW_CTS2SELF_PKT_LEN_TH_TWW_MASK);
+		val32 |= B_BE_HW_CTS2SELF_EN;
+		rtw89_write32(rtwdev, reg, val32);
+
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_PTCL_FSM_MON, mac_idx);
+		val32 = rtw89_read32(rtwdev, reg);
+		val32 = u32_replace_bits(val32, S_AX_PTCL_TO_2MS,
+					 B_BE_PTCL_TX_ARB_TO_THR_MASK);
+		val32 &= ~B_BE_PTCL_TX_ARB_TO_MODE;
+		rtw89_write32(rtwdev, reg, val32);
+	}
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_PTCL_COMMON_SETTING_0, mac_idx);
+	val8 = rtw89_read8(rtwdev, reg);
+	val8 |= B_BE_CMAC_TX_MODE_0 | B_BE_CMAC_TX_MODE_1;
+	val8 &= ~(B_BE_PTCL_TRIGGER_SS_EN_0 |
+		  B_BE_PTCL_TRIGGER_SS_EN_1 |
+		  B_BE_PTCL_TRIGGER_SS_EN_UL);
+	rtw89_write8(rtwdev, reg, val8);
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_AMPDU_AGG_LIMIT, mac_idx);
+	rtw89_write32_mask(rtwdev, reg, B_BE_AMPDU_MAX_TIME_MASK, AMPDU_MAX_TIME);
+
+	return 0;
+}
+
+static int cmac_dma_init_be(struct rtw89_dev *rtwdev, u8 mac_idx)
+{
+	u32 val32;
+	u32 reg;
+	int ret;
+
+	ret = rtw89_mac_check_mac_en(rtwdev, mac_idx, RTW89_CMAC_SEL);
+	if (ret)
+		return ret;
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_RX_CTRL_1, mac_idx);
+
+	val32 = rtw89_read32(rtwdev, reg);
+	val32 = u32_replace_bits(val32, WLCPU_RXCH2_QID,
+				 B_BE_RXDMA_TXRPT_QUEUE_ID_SW_MASK);
+	val32 = u32_replace_bits(val32, WLCPU_RXCH2_QID,
+				 B_BE_RXDMA_F2PCMDRPT_QUEUE_ID_SW_MASK);
+	rtw89_write32(rtwdev, reg, val32);
+
+	return 0;
+}
+
+static int cmac_init_be(struct rtw89_dev *rtwdev, u8 mac_idx)
+{
+	int ret;
+
+	ret = scheduler_init_be(rtwdev, mac_idx);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]CMAC%d SCH init %d\n", mac_idx, ret);
+		return ret;
+	}
+
+	ret = addr_cam_init_be(rtwdev, mac_idx);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]CMAC%d ADDR_CAM reset %d\n", mac_idx,
+			  ret);
+		return ret;
+	}
+
+	ret = rx_fltr_init_be(rtwdev, mac_idx);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]CMAC%d RX filter init %d\n", mac_idx,
+			  ret);
+		return ret;
+	}
+
+	ret = cca_ctrl_init_be(rtwdev, mac_idx);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]CMAC%d CCA CTRL init %d\n", mac_idx,
+			  ret);
+		return ret;
+	}
+
+	ret = nav_ctrl_init_be(rtwdev, mac_idx);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]CMAC%d NAV CTRL init %d\n", mac_idx,
+			  ret);
+		return ret;
+	}
+
+	ret = spatial_reuse_init_be(rtwdev, mac_idx);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]CMAC%d Spatial Reuse init %d\n",
+			  mac_idx, ret);
+		return ret;
+	}
+
+	ret = tmac_init_be(rtwdev, mac_idx);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]CMAC%d TMAC init %d\n", mac_idx, ret);
+		return ret;
+	}
+
+	ret = trxptcl_init_be(rtwdev, mac_idx);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]CMAC%d TRXPTCL init %d\n", mac_idx, ret);
+		return ret;
+	}
+
+	ret = rmac_init_be(rtwdev, mac_idx);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]CMAC%d RMAC init %d\n", mac_idx, ret);
+		return ret;
+	}
+
+	ret = resp_pktctl_init_be(rtwdev, mac_idx);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]CMAC%d resp pktctl init %d\n", mac_idx, ret);
+		return ret;
+	}
+
+	ret = cmac_com_init_be(rtwdev, mac_idx);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]CMAC%d Com init %d\n", mac_idx, ret);
+		return ret;
+	}
+
+	ret = ptcl_init_be(rtwdev, mac_idx);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]CMAC%d PTCL init %d\n", mac_idx, ret);
+		return ret;
+	}
+
+	ret = cmac_dma_init_be(rtwdev, mac_idx);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]CMAC%d DMA init %d\n", mac_idx, ret);
+		return ret;
+	}
+
+	return ret;
+}
+
+static int tx_idle_poll_band_be(struct rtw89_dev *rtwdev, u8 mac_idx)
+{
+	u32 reg;
+	u8 val8;
+	int ret;
+
+	ret = rtw89_mac_check_mac_en(rtwdev, mac_idx, RTW89_CMAC_SEL);
+	if (ret)
+		return ret;
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_PTCL_TX_CTN_SEL, mac_idx);
+
+	ret = read_poll_timeout_atomic(rtw89_read8, val8, !(val8 & B_BE_PTCL_BUSY),
+				       30, 66000, false, rtwdev, reg);
+
+	return ret;
+}
+
+static int dle_buf_req_be(struct rtw89_dev *rtwdev, u16 buf_len, bool wd, u16 *pkt_id)
+{
+	u32 val, reg;
+	int ret;
+
+	reg = wd ? R_BE_WD_BUF_REQ : R_BE_PL_BUF_REQ;
+	val = buf_len;
+	val |= B_BE_WD_BUF_REQ_EXEC;
+	rtw89_write32(rtwdev, reg, val);
+
+	reg = wd ? R_BE_WD_BUF_STATUS : R_BE_PL_BUF_STATUS;
+
+	ret = read_poll_timeout(rtw89_read32, val, val & B_BE_WD_BUF_STAT_DONE,
+				1, 2000, false, rtwdev, reg);
+	if (ret)
+		return ret;
+
+	*pkt_id = u32_get_bits(val, B_BE_WD_BUF_STAT_PKTID_MASK);
+	if (*pkt_id == S_WD_BUF_STAT_PKTID_INVALID)
+		return -ENOENT;
+
+	return 0;
+}
+
+static int set_cpuio_be(struct rtw89_dev *rtwdev,
+			struct rtw89_cpuio_ctrl *ctrl_para, bool wd)
+{
+	u32 val_op0, val_op1, val_op2, val_op3;
+	u32 val, cmd_type, reg;
+	int ret;
+
+	cmd_type = ctrl_para->cmd_type;
+
+	reg = wd ? R_BE_WD_CPUQ_OP_3 : R_BE_PL_CPUQ_OP_3;
+	val_op3 = u32_replace_bits(0, ctrl_para->start_pktid,
+				   B_BE_WD_CPUQ_OP_STRT_PKTID_MASK);
+	val_op3 = u32_replace_bits(val_op3, ctrl_para->end_pktid,
+				   B_BE_WD_CPUQ_OP_END_PKTID_MASK);
+	rtw89_write32(rtwdev, reg, val_op3);
+
+	reg = wd ? R_BE_WD_CPUQ_OP_1 : R_BE_PL_CPUQ_OP_1;
+	val_op1 = u32_replace_bits(0, ctrl_para->src_pid,
+				   B_BE_WD_CPUQ_OP_SRC_PID_MASK);
+	val_op1 = u32_replace_bits(val_op1, ctrl_para->src_qid,
+				   B_BE_WD_CPUQ_OP_SRC_QID_MASK);
+	val_op1 = u32_replace_bits(val_op1, ctrl_para->macid,
+				   B_BE_WD_CPUQ_OP_SRC_MACID_MASK);
+	rtw89_write32(rtwdev, reg, val_op1);
+
+	reg = wd ? R_BE_WD_CPUQ_OP_2 : R_BE_PL_CPUQ_OP_2;
+	val_op2 = u32_replace_bits(0, ctrl_para->dst_pid,
+				   B_BE_WD_CPUQ_OP_DST_PID_MASK);
+	val_op2 = u32_replace_bits(val_op2, ctrl_para->dst_qid,
+				   B_BE_WD_CPUQ_OP_DST_QID_MASK);
+	val_op2 = u32_replace_bits(val_op2, ctrl_para->macid,
+				   B_BE_WD_CPUQ_OP_DST_MACID_MASK);
+	rtw89_write32(rtwdev, reg, val_op2);
+
+	reg = wd ? R_BE_WD_CPUQ_OP_0 : R_BE_PL_CPUQ_OP_0;
+	val_op0 = u32_replace_bits(0, cmd_type,
+				   B_BE_WD_CPUQ_OP_CMD_TYPE_MASK);
+	val_op0 = u32_replace_bits(val_op0, ctrl_para->pkt_num,
+				   B_BE_WD_CPUQ_OP_PKTNUM_MASK);
+	val_op0 |= B_BE_WD_CPUQ_OP_EXEC;
+	rtw89_write32(rtwdev, reg, val_op0);
+
+	reg = wd ? R_BE_WD_CPUQ_OP_STATUS : R_BE_PL_CPUQ_OP_STATUS;
+
+	ret = read_poll_timeout(rtw89_read32, val, val & B_BE_WD_CPUQ_OP_STAT_DONE,
+				1, 2000, false, rtwdev, reg);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]set cpuio wd timeout\n");
+		rtw89_err(rtwdev, "[ERR]op_0=0x%X, op_1=0x%X, op_2=0x%X\n",
+			  val_op0, val_op1, val_op2);
+		return ret;
+	}
+
+	if (cmd_type == CPUIO_OP_CMD_GET_NEXT_PID ||
+	    cmd_type == CPUIO_OP_CMD_GET_1ST_PID)
+		ctrl_para->pktid = u32_get_bits(val, B_BE_WD_CPUQ_OP_PKTID_MASK);
+
+	return 0;
+}
+
+static int preload_init_be(struct rtw89_dev *rtwdev, u8 mac_idx,
+			   enum rtw89_qta_mode mode)
+{
+	u32 max_preld_size, min_rsvd_size;
+	u32 val32;
+	u32 reg;
+
+	max_preld_size = mac_idx == RTW89_MAC_0 ?
+			 PRELD_B0_ENT_NUM : PRELD_B1_ENT_NUM;
+	max_preld_size *= PRELD_AMSDU_SIZE;
+
+	reg = mac_idx == RTW89_MAC_0 ? R_BE_TXPKTCTL_B0_PRELD_CFG0 :
+				       R_BE_TXPKTCTL_B1_PRELD_CFG0;
+	val32 = rtw89_read32(rtwdev, reg);
+	val32 = u32_replace_bits(val32, max_preld_size, B_BE_B0_PRELD_USEMAXSZ_MASK);
+	val32 |= B_BE_B0_PRELD_FEN;
+	rtw89_write32(rtwdev, reg, val32);
+
+	min_rsvd_size = PRELD_AMSDU_SIZE;
+	reg = mac_idx == RTW89_MAC_0 ? R_BE_TXPKTCTL_B0_PRELD_CFG1 :
+				       R_BE_TXPKTCTL_B1_PRELD_CFG1;
+	val32 = rtw89_read32(rtwdev, reg);
+	val32 = u32_replace_bits(val32, PRELD_NEXT_WND, B_BE_B0_PRELD_NXT_TXENDWIN_MASK);
+	val32 = u32_replace_bits(val32, min_rsvd_size, B_BE_B0_PRELD_NXT_RSVMINSZ_MASK);
+	rtw89_write32(rtwdev, reg, val32);
+
+	return 0;
+}
+
+static int dbcc_bb_ctrl_be(struct rtw89_dev *rtwdev, bool bb1_en)
+{
+	return 0;
+}
+
+static int enable_imr_be(struct rtw89_dev *rtwdev, u8 mac_idx,
+			 enum rtw89_mac_hwmod_sel sel)
+{
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	const struct rtw89_imr_table *table;
+	const struct rtw89_reg_imr *reg;
+	u32 addr;
+	u32 val;
+	int i;
+
+	if (sel == RTW89_DMAC_SEL)
+		table = chip->imr_dmac_table;
+	else if (sel == RTW89_CMAC_SEL)
+		table = chip->imr_cmac_table;
+	else
+		return -EINVAL;
+
+	for (i = 0; i < table->n_regs; i++) {
+		reg = &table->regs[i];
+		addr = rtw89_mac_reg_by_idx(rtwdev, reg->addr, mac_idx);
+
+		val = rtw89_read32(rtwdev, addr);
+		val &= ~reg->clr;
+		val |= reg->set;
+		rtw89_write32(rtwdev, addr, val);
+	}
+
+	return 0;
+}
+
+static void err_imr_ctrl_be(struct rtw89_dev *rtwdev, bool en)
+{
+	u32 v32_dmac = en ? DMAC_ERR_IMR_EN : DMAC_ERR_IMR_DIS;
+	u32 v32_cmac0 = en ? CMAC0_ERR_IMR_EN : CMAC0_ERR_IMR_DIS;
+	u32 v32_cmac1 = en ? CMAC1_ERR_IMR_EN : CMAC1_ERR_IMR_DIS;
+
+	v32_dmac &= ~B_BE_DMAC_NOTX_ERR_INT_EN;
+
+	rtw89_write32(rtwdev, R_BE_DMAC_ERR_IMR, v32_dmac);
+	rtw89_write32(rtwdev, R_BE_CMAC_ERR_IMR, v32_cmac0);
+
+	if (rtwdev->dbcc_en)
+		rtw89_write32(rtwdev, R_BE_CMAC_ERR_IMR_C1, v32_cmac1);
+}
+
+static int band1_enable_be(struct rtw89_dev *rtwdev)
+{
+	int ret;
+
+	ret = tx_idle_poll_band_be(rtwdev, RTW89_MAC_0);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]tx idle poll %d\n", ret);
+		return ret;
+	}
+
+	ret = rtw89_mac_dle_quota_change(rtwdev, rtwdev->mac.qta_mode);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]DLE quota change %d\n", ret);
+		return ret;
+	}
+
+	ret = preload_init_be(rtwdev, RTW89_MAC_1, rtwdev->mac.qta_mode);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]preload init B1 %d\n", ret);
+		return ret;
+	}
+
+	ret = cmac_func_en_be(rtwdev, RTW89_MAC_1, true);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]CMAC%d func en %d\n", RTW89_MAC_1, ret);
+		return ret;
+	}
+
+	ret = cmac_init_be(rtwdev, RTW89_MAC_1);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]CMAC%d init %d\n", RTW89_MAC_1, ret);
+		return ret;
+	}
+
+	ret = dbcc_bb_ctrl_be(rtwdev, true);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]enable bb 1 %d\n", ret);
+		return ret;
+	}
+
+	ret = enable_imr_be(rtwdev, RTW89_MAC_1, RTW89_CMAC_SEL);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR] enable CMAC1 IMR %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int band1_disable_be(struct rtw89_dev *rtwdev)
+{
+	int ret;
+
+	ret = dbcc_bb_ctrl_be(rtwdev, false);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]disable bb 1 %d\n", ret);
+		return ret;
+	}
+
+	ret = cmac_func_en_be(rtwdev, RTW89_MAC_1, false);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]CMAC%d func dis %d\n", RTW89_MAC_1, ret);
+		return ret;
+	}
+
+	ret = rtw89_mac_dle_quota_change(rtwdev, rtwdev->mac.qta_mode);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]DLE quota change %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int dbcc_enable_be(struct rtw89_dev *rtwdev, bool enable)
+{
+	int ret;
+
+	if (enable) {
+		ret = band1_enable_be(rtwdev);
+		if (ret) {
+			rtw89_err(rtwdev, "[ERR] band1_enable %d\n", ret);
+			return ret;
+		}
+
+		if (test_bit(RTW89_FLAG_FW_RDY, rtwdev->flags)) {
+			ret = rtw89_fw_h2c_notify_dbcc(rtwdev, true);
+			if (ret) {
+				rtw89_err(rtwdev, "%s:[ERR]notfify dbcc1 fail %d\n",
+					  __func__, ret);
+				return ret;
+			}
+		}
+	} else {
+		if (test_bit(RTW89_FLAG_FW_RDY, rtwdev->flags)) {
+			ret = rtw89_fw_h2c_notify_dbcc(rtwdev, false);
+			if (ret) {
+				rtw89_err(rtwdev, "%s:[ERR]notfify dbcc1 fail %d\n",
+					  __func__, ret);
+				return ret;
+			}
+		}
+
+		ret = band1_disable_be(rtwdev);
+		if (ret) {
+			rtw89_err(rtwdev, "[ERR] band1_disable %d\n", ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int set_host_rpr_be(struct rtw89_dev *rtwdev)
+{
+	u32 val32;
+	u32 mode;
+	u32 fltr;
+	bool poh;
+
+	poh = is_qta_poh(rtwdev);
+
+	if (poh) {
+		mode = RTW89_RPR_MODE_POH;
+		fltr = S_BE_WDRLS_FLTR_TXOK | S_BE_WDRLS_FLTR_RTYLMT |
+		       S_BE_WDRLS_FLTR_LIFTIM | S_BE_WDRLS_FLTR_MACID;
+	} else {
+		mode = RTW89_RPR_MODE_STF;
+		fltr = 0;
+	}
+
+	rtw89_write32_mask(rtwdev, R_BE_WDRLS_CFG, B_BE_WDRLS_MODE_MASK, mode);
+
+	val32 = rtw89_read32(rtwdev, R_BE_RLSRPT0_CFG1);
+	val32 = u32_replace_bits(val32, fltr, B_BE_RLSRPT0_FLTR_MAP_MASK);
+	val32 = u32_replace_bits(val32, 30, B_BE_RLSRPT0_AGGNUM_MASK);
+	val32 = u32_replace_bits(val32, 255, B_BE_RLSRPT0_TO_MASK);
+	rtw89_write32(rtwdev, R_BE_RLSRPT0_CFG1, val32);
+
+	return 0;
+}
+
+static int trx_init_be(struct rtw89_dev *rtwdev)
+{
+	enum rtw89_qta_mode qta_mode = rtwdev->mac.qta_mode;
+	int ret;
+
+	ret = dmac_init_be(rtwdev, 0);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]DMAC init %d\n", ret);
+		return ret;
+	}
+
+	ret = cmac_init_be(rtwdev, 0);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]CMAC%d init %d\n", 0, ret);
+		return ret;
+	}
+
+	if (rtw89_mac_is_qta_dbcc(rtwdev, qta_mode)) {
+		ret = dbcc_enable_be(rtwdev, true);
+		if (ret) {
+			rtw89_err(rtwdev, "[ERR]dbcc_enable init %d\n", ret);
+			return ret;
+		}
+	}
+
+	ret = enable_imr_be(rtwdev, RTW89_MAC_0, RTW89_DMAC_SEL);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR] enable DMAC IMR %d\n", ret);
+		return ret;
+	}
+
+	ret = enable_imr_be(rtwdev, RTW89_MAC_0, RTW89_CMAC_SEL);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR] to enable CMAC0 IMR %d\n", ret);
+		return ret;
+	}
+
+	err_imr_ctrl_be(rtwdev, true);
+
+	ret = set_host_rpr_be(rtwdev);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR] set host rpr %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
 static bool rtw89_mac_get_txpwr_cr_be(struct rtw89_dev *rtwdev,
 				      enum rtw89_phy_idx phy_idx,
 				      u32 reg_base, u32 *cr)
@@ -404,6 +1917,299 @@ static void rtw89_mac_bf_assoc_be(struct rtw89_dev *rtwdev,
 	}
 }
 
+static void dump_err_status_dispatcher_be(struct rtw89_dev *rtwdev)
+{
+	rtw89_info(rtwdev, "R_BE_DISP_HOST_IMR=0x%08x ",
+		   rtw89_read32(rtwdev, R_BE_DISP_HOST_IMR));
+	rtw89_info(rtwdev, "R_BE_DISP_ERROR_ISR1=0x%08x\n",
+		   rtw89_read32(rtwdev, R_BE_DISP_ERROR_ISR1));
+	rtw89_info(rtwdev, "R_BE_DISP_CPU_IMR=0x%08x ",
+		   rtw89_read32(rtwdev, R_BE_DISP_CPU_IMR));
+	rtw89_info(rtwdev, "R_BE_DISP_ERROR_ISR2=0x%08x\n",
+		   rtw89_read32(rtwdev, R_BE_DISP_ERROR_ISR2));
+	rtw89_info(rtwdev, "R_BE_DISP_OTHER_IMR=0x%08x ",
+		   rtw89_read32(rtwdev, R_BE_DISP_OTHER_IMR));
+	rtw89_info(rtwdev, "R_BE_DISP_ERROR_ISR0=0x%08x\n",
+		   rtw89_read32(rtwdev, R_BE_DISP_ERROR_ISR0));
+}
+
+static void rtw89_mac_dump_qta_lost_be(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_mac_dle_dfi_qempty qempty;
+	struct rtw89_mac_dle_dfi_quota quota;
+	struct rtw89_mac_dle_dfi_ctrl ctrl;
+	u32 val, not_empty, i;
+	int ret;
+
+	qempty.dle_type = DLE_CTRL_TYPE_PLE;
+	qempty.grpsel = 0;
+	qempty.qempty = ~(u32)0;
+	ret = rtw89_mac_dle_dfi_qempty_cfg(rtwdev, &qempty);
+	if (ret)
+		rtw89_warn(rtwdev, "%s: query DLE fail\n", __func__);
+	else
+		rtw89_info(rtwdev, "DLE group0 empty: 0x%x\n", qempty.qempty);
+
+	for (not_empty = ~qempty.qempty, i = 0; not_empty != 0; not_empty >>= 1, i++) {
+		if (!(not_empty & BIT(0)))
+			continue;
+		ctrl.type = DLE_CTRL_TYPE_PLE;
+		ctrl.target = DLE_DFI_TYPE_QLNKTBL;
+		ctrl.addr = (QLNKTBL_ADDR_INFO_SEL_0 ? QLNKTBL_ADDR_INFO_SEL : 0) |
+			    u32_encode_bits(i, QLNKTBL_ADDR_TBL_IDX_MASK);
+		ret = rtw89_mac_dle_dfi_cfg(rtwdev, &ctrl);
+		if (ret)
+			rtw89_warn(rtwdev, "%s: query DLE fail\n", __func__);
+		else
+			rtw89_info(rtwdev, "qidx%d pktcnt = %d\n", i,
+				   u32_get_bits(ctrl.out_data,
+						QLNKTBL_DATA_SEL1_PKT_CNT_MASK));
+	}
+
+	quota.dle_type = DLE_CTRL_TYPE_PLE;
+	quota.qtaid = 6;
+	ret = rtw89_mac_dle_dfi_quota_cfg(rtwdev, &quota);
+	if (ret)
+		rtw89_warn(rtwdev, "%s: query DLE fail\n", __func__);
+	else
+		rtw89_info(rtwdev, "quota6 rsv/use: 0x%x/0x%x\n",
+			   quota.rsv_pgnum, quota.use_pgnum);
+
+	val = rtw89_read32(rtwdev, R_BE_PLE_QTA6_CFG);
+	rtw89_info(rtwdev, "[PLE][CMAC0_RX]min_pgnum=0x%x\n",
+		   u32_get_bits(val, B_BE_PLE_Q6_MIN_SIZE_MASK));
+	rtw89_info(rtwdev, "[PLE][CMAC0_RX]max_pgnum=0x%x\n",
+		   u32_get_bits(val, B_BE_PLE_Q6_MAX_SIZE_MASK));
+	val = rtw89_read32(rtwdev, R_BE_RX_FLTR_OPT);
+	rtw89_info(rtwdev, "[PLE][CMAC0_RX]B_BE_RX_MPDU_MAX_LEN=0x%x\n",
+		   u32_get_bits(val, B_BE_RX_MPDU_MAX_LEN_MASK));
+	rtw89_info(rtwdev, "R_BE_RSP_CHK_SIG=0x%08x\n",
+		   rtw89_read32(rtwdev, R_BE_RSP_CHK_SIG));
+	rtw89_info(rtwdev, "R_BE_TRXPTCL_RESP_0=0x%08x\n",
+		   rtw89_read32(rtwdev, R_BE_TRXPTCL_RESP_0));
+
+	if (!rtw89_mac_check_mac_en(rtwdev, RTW89_MAC_1, RTW89_CMAC_SEL)) {
+		quota.dle_type = DLE_CTRL_TYPE_PLE;
+		quota.qtaid = 7;
+		ret = rtw89_mac_dle_dfi_quota_cfg(rtwdev, &quota);
+		if (ret)
+			rtw89_warn(rtwdev, "%s: query DLE fail\n", __func__);
+		else
+			rtw89_info(rtwdev, "quota7 rsv/use: 0x%x/0x%x\n",
+				   quota.rsv_pgnum, quota.use_pgnum);
+
+		val = rtw89_read32(rtwdev, R_BE_PLE_QTA7_CFG);
+		rtw89_info(rtwdev, "[PLE][CMAC1_RX]min_pgnum=0x%x\n",
+			   u32_get_bits(val, B_BE_PLE_Q7_MIN_SIZE_MASK));
+		rtw89_info(rtwdev, "[PLE][CMAC1_RX]max_pgnum=0x%x\n",
+			   u32_get_bits(val, B_BE_PLE_Q7_MAX_SIZE_MASK));
+		val = rtw89_read32(rtwdev, R_BE_RX_FLTR_OPT_C1);
+		rtw89_info(rtwdev, "[PLE][CMAC1_RX]B_BE_RX_MPDU_MAX_LEN=0x%x\n",
+			   u32_get_bits(val, B_BE_RX_MPDU_MAX_LEN_MASK));
+		rtw89_info(rtwdev, "R_BE_RSP_CHK_SIG_C1=0x%08x\n",
+			   rtw89_read32(rtwdev, R_BE_RSP_CHK_SIG_C1));
+		rtw89_info(rtwdev, "R_BE_TRXPTCL_RESP_0_C1=0x%08x\n",
+			   rtw89_read32(rtwdev, R_BE_TRXPTCL_RESP_0_C1));
+	}
+
+	rtw89_info(rtwdev, "R_BE_DLE_EMPTY0=0x%08x\n",
+		   rtw89_read32(rtwdev, R_BE_DLE_EMPTY0));
+	rtw89_info(rtwdev, "R_BE_DLE_EMPTY1=0x%08x\n",
+		   rtw89_read32(rtwdev, R_BE_DLE_EMPTY1));
+
+	dump_err_status_dispatcher_be(rtwdev);
+}
+
+static void rtw89_mac_dump_cmac_err_status_be(struct rtw89_dev *rtwdev,
+					      u8 band)
+{
+	u32 offset = 0;
+	u32 cmac_err;
+	int ret;
+
+	ret = rtw89_mac_check_mac_en(rtwdev, band, RTW89_CMAC_SEL);
+	if (ret) {
+		rtw89_info(rtwdev, "[CMAC] : CMAC%d not enabled\n", band);
+		return;
+	}
+
+	if (band)
+		offset = RTW89_MAC_BE_BAND_REG_OFFSET;
+
+	cmac_err = rtw89_read32(rtwdev, R_BE_CMAC_ERR_ISR + offset);
+	rtw89_info(rtwdev, "R_BE_CMAC_ERR_ISR [%d]=0x%08x\n", band,
+		   rtw89_read32(rtwdev, R_BE_CMAC_ERR_ISR + offset));
+	rtw89_info(rtwdev, "R_BE_CMAC_FUNC_EN [%d]=0x%08x\n", band,
+		   rtw89_read32(rtwdev, R_BE_CMAC_FUNC_EN + offset));
+	rtw89_info(rtwdev, "R_BE_CK_EN [%d]=0x%08x\n", band,
+		   rtw89_read32(rtwdev, R_BE_CK_EN + offset));
+
+	if (cmac_err & B_BE_SCHEDULE_TOP_ERR_IND) {
+		rtw89_info(rtwdev, "R_BE_SCHEDULE_ERR_IMR [%d]=0x%08x\n", band,
+			   rtw89_read32(rtwdev, R_BE_SCHEDULE_ERR_IMR + offset));
+		rtw89_info(rtwdev, "R_BE_SCHEDULE_ERR_ISR [%d]=0x%08x\n", band,
+			   rtw89_read32(rtwdev, R_BE_SCHEDULE_ERR_ISR + offset));
+	}
+
+	if (cmac_err & B_BE_PTCL_TOP_ERR_IND) {
+		rtw89_info(rtwdev, "R_BE_PTCL_IMR0 [%d]=0x%08x\n", band,
+			   rtw89_read32(rtwdev, R_BE_PTCL_IMR0 + offset));
+		rtw89_info(rtwdev, "R_BE_PTCL_ISR0 [%d]=0x%08x\n", band,
+			   rtw89_read32(rtwdev, R_BE_PTCL_ISR0 + offset));
+		rtw89_info(rtwdev, "R_BE_PTCL_IMR1 [%d]=0x%08x\n", band,
+			   rtw89_read32(rtwdev, R_BE_PTCL_IMR1 + offset));
+		rtw89_info(rtwdev, "R_BE_PTCL_ISR1 [%d]=0x%08x\n", band,
+			   rtw89_read32(rtwdev, R_BE_PTCL_ISR1 + offset));
+	}
+
+	if (cmac_err & B_BE_DMA_TOP_ERR_IND) {
+		rtw89_info(rtwdev, "R_BE_RX_ERROR_FLAG_IMR [%d]=0x%08x\n", band,
+			   rtw89_read32(rtwdev, R_BE_RX_ERROR_FLAG_IMR + offset));
+		rtw89_info(rtwdev, "R_BE_RX_ERROR_FLAG [%d]=0x%08x\n", band,
+			   rtw89_read32(rtwdev, R_BE_RX_ERROR_FLAG + offset));
+		rtw89_info(rtwdev, "R_BE_TX_ERROR_FLAG_IMR [%d]=0x%08x\n", band,
+			   rtw89_read32(rtwdev, R_BE_TX_ERROR_FLAG_IMR + offset));
+		rtw89_info(rtwdev, "R_BE_TX_ERROR_FLAG [%d]=0x%08x\n", band,
+			   rtw89_read32(rtwdev, R_BE_TX_ERROR_FLAG + offset));
+		rtw89_info(rtwdev, "R_BE_RX_ERROR_FLAG_IMR_1 [%d]=0x%08x\n", band,
+			   rtw89_read32(rtwdev, R_BE_RX_ERROR_FLAG_IMR_1 + offset));
+		rtw89_info(rtwdev, "R_BE_RX_ERROR_FLAG_1 [%d]=0x%08x\n", band,
+			   rtw89_read32(rtwdev, R_BE_RX_ERROR_FLAG_1 + offset));
+	}
+
+	if (cmac_err & B_BE_PHYINTF_ERR_IND) {
+		rtw89_info(rtwdev, "R_BE_PHYINFO_ERR_IMR [%d]=0x%08x\n", band,
+			   rtw89_read32(rtwdev, R_BE_PHYINFO_ERR_IMR_V1 + offset));
+		rtw89_info(rtwdev, "R_BE_PHYINFO_ERR_ISR [%d]=0x%08x\n", band,
+			   rtw89_read32(rtwdev, R_BE_PHYINFO_ERR_ISR + offset));
+	}
+
+	if (cmac_err & B_AX_TXPWR_CTRL_ERR_IND) {
+		rtw89_info(rtwdev, "R_BE_TXPWR_ERR_FLAG [%d]=0x%08x\n", band,
+			   rtw89_read32(rtwdev, R_BE_TXPWR_ERR_FLAG + offset));
+		rtw89_info(rtwdev, "R_BE_TXPWR_ERR_IMR [%d]=0x%08x\n", band,
+			   rtw89_read32(rtwdev, R_BE_TXPWR_ERR_IMR + offset));
+	}
+
+	if (cmac_err & (B_BE_WMAC_RX_ERR_IND | B_BE_WMAC_TX_ERR_IND |
+			B_BE_WMAC_RX_IDLETO_IDCT | B_BE_PTCL_TX_IDLETO_IDCT)) {
+		rtw89_info(rtwdev, "R_BE_DBGSEL_TRXPTCL [%d]=0x%08x\n", band,
+			   rtw89_read32(rtwdev, R_BE_DBGSEL_TRXPTCL + offset));
+		rtw89_info(rtwdev, "R_BE_TRXPTCL_ERROR_INDICA_MASK [%d]=0x%08x\n", band,
+			   rtw89_read32(rtwdev, R_BE_TRXPTCL_ERROR_INDICA_MASK + offset));
+		rtw89_info(rtwdev, "R_BE_TRXPTCL_ERROR_INDICA [%d]=0x%08x\n", band,
+			   rtw89_read32(rtwdev, R_BE_TRXPTCL_ERROR_INDICA + offset));
+		rtw89_info(rtwdev, "R_BE_RX_ERR_IMR [%d]=0x%08x\n", band,
+			   rtw89_read32(rtwdev, R_BE_RX_ERR_IMR + offset));
+		rtw89_info(rtwdev, "R_BE_RX_ERR_ISR [%d]=0x%08x\n", band,
+			   rtw89_read32(rtwdev, R_BE_RX_ERR_ISR + offset));
+	}
+
+	rtw89_info(rtwdev, "R_BE_CMAC_ERR_IMR [%d]=0x%08x\n", band,
+		   rtw89_read32(rtwdev, R_BE_CMAC_ERR_IMR + offset));
+}
+
+static void rtw89_mac_dump_err_status_be(struct rtw89_dev *rtwdev,
+					 enum mac_ax_err_info err)
+{
+	if (err != MAC_AX_ERR_L1_ERR_DMAC &&
+	    err != MAC_AX_ERR_L0_PROMOTE_TO_L1 &&
+	    err != MAC_AX_ERR_L0_ERR_CMAC0 &&
+	    err != MAC_AX_ERR_L0_ERR_CMAC1 &&
+	    err != MAC_AX_ERR_RXI300)
+		return;
+
+	rtw89_info(rtwdev, "--->\nerr=0x%x\n", err);
+	rtw89_info(rtwdev, "R_BE_SER_DBG_INFO=0x%08x\n",
+		   rtw89_read32(rtwdev, R_BE_SER_DBG_INFO));
+	rtw89_info(rtwdev, "R_BE_SER_L0_DBG_CNT=0x%08x\n",
+		   rtw89_read32(rtwdev, R_BE_SER_L0_DBG_CNT));
+	rtw89_info(rtwdev, "R_BE_SER_L0_DBG_CNT1=0x%08x\n",
+		   rtw89_read32(rtwdev, R_BE_SER_L0_DBG_CNT1));
+	rtw89_info(rtwdev, "R_BE_SER_L0_DBG_CNT2=0x%08x\n",
+		   rtw89_read32(rtwdev, R_BE_SER_L0_DBG_CNT2));
+	rtw89_info(rtwdev, "R_BE_SER_L0_DBG_CNT3=0x%08x\n",
+		   rtw89_read32(rtwdev, R_BE_SER_L0_DBG_CNT3));
+	if (!rtw89_mac_check_mac_en(rtwdev, RTW89_MAC_1, RTW89_CMAC_SEL)) {
+		rtw89_info(rtwdev, "R_BE_SER_L0_DBG_CNT_C1=0x%08x\n",
+			   rtw89_read32(rtwdev, R_BE_SER_L0_DBG_CNT_C1));
+		rtw89_info(rtwdev, "R_BE_SER_L0_DBG_CNT1_C1=0x%08x\n",
+			   rtw89_read32(rtwdev, R_BE_SER_L0_DBG_CNT1_C1));
+	}
+	rtw89_info(rtwdev, "R_BE_SER_L1_DBG_CNT_0=0x%08x\n",
+		   rtw89_read32(rtwdev, R_BE_SER_L1_DBG_CNT_0));
+	rtw89_info(rtwdev, "R_BE_SER_L1_DBG_CNT_1=0x%08x\n",
+		   rtw89_read32(rtwdev, R_BE_SER_L1_DBG_CNT_1));
+	rtw89_info(rtwdev, "R_BE_SER_L1_DBG_CNT_2=0x%08x\n",
+		   rtw89_read32(rtwdev, R_BE_SER_L1_DBG_CNT_2));
+	rtw89_info(rtwdev, "R_BE_SER_L1_DBG_CNT_3=0x%08x\n",
+		   rtw89_read32(rtwdev, R_BE_SER_L1_DBG_CNT_3));
+	rtw89_info(rtwdev, "R_BE_SER_L1_DBG_CNT_4=0x%08x\n",
+		   rtw89_read32(rtwdev, R_BE_SER_L1_DBG_CNT_4));
+	rtw89_info(rtwdev, "R_BE_SER_L1_DBG_CNT_5=0x%08x\n",
+		   rtw89_read32(rtwdev, R_BE_SER_L1_DBG_CNT_5));
+	rtw89_info(rtwdev, "R_BE_SER_L1_DBG_CNT_6=0x%08x\n",
+		   rtw89_read32(rtwdev, R_BE_SER_L1_DBG_CNT_6));
+	rtw89_info(rtwdev, "R_BE_SER_L1_DBG_CNT_7=0x%08x\n",
+		   rtw89_read32(rtwdev, R_BE_SER_L1_DBG_CNT_7));
+
+	rtw89_mac_dump_dmac_err_status(rtwdev);
+	rtw89_mac_dump_cmac_err_status_be(rtwdev, RTW89_MAC_0);
+	rtw89_mac_dump_cmac_err_status_be(rtwdev, RTW89_MAC_1);
+
+	rtwdev->hci.ops->dump_err_status(rtwdev);
+
+	if (err == MAC_AX_ERR_L0_PROMOTE_TO_L1)
+		rtw89_mac_dump_l0_to_l1(rtwdev, err);
+
+	rtw89_info(rtwdev, "<---\n");
+}
+
+static bool mac_is_txq_empty_be(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_mac_dle_dfi_qempty qempty;
+	u32 val32, msk32;
+	u32 grpnum;
+	int ret;
+	int i;
+
+	grpnum = rtwdev->chip->wde_qempty_acq_grpnum;
+	qempty.dle_type = DLE_CTRL_TYPE_WDE;
+
+	for (i = 0; i < grpnum; i++) {
+		qempty.grpsel = i;
+		ret = rtw89_mac_dle_dfi_qempty_cfg(rtwdev, &qempty);
+		if (ret) {
+			rtw89_warn(rtwdev,
+				   "%s: failed to dle dfi acq empty: %d\n",
+				   __func__, ret);
+			return false;
+		}
+
+		/* Each acq group contains 32 queues (8 macid * 4 acq),
+		 * but here, we can simply check if all bits are set.
+		 */
+		if (qempty.qempty != MASKDWORD)
+			return false;
+	}
+
+	qempty.grpsel = rtwdev->chip->wde_qempty_mgq_grpsel;
+	ret = rtw89_mac_dle_dfi_qempty_cfg(rtwdev, &qempty);
+	if (ret) {
+		rtw89_warn(rtwdev, "%s: failed to dle dfi mgq empty: %d\n",
+			   __func__, ret);
+		return false;
+	}
+
+	msk32 = B_CMAC0_MGQ_NORMAL_BE | B_CMAC1_MGQ_NORMAL_BE;
+	if ((qempty.qempty & msk32) != msk32)
+		return false;
+
+	msk32 = B_BE_WDE_EMPTY_QUE_OTHERS;
+	val32 = rtw89_read32(rtwdev, R_BE_DLE_EMPTY0);
+	return (val32 & msk32) == msk32;
+}
+
 const struct rtw89_mac_gen_def rtw89_mac_gen_be = {
 	.band1_offset = RTW89_MAC_BE_BAND_REG_OFFSET,
 	.filter_model_addr = R_BE_FILTER_MODEL_ADDR,
@@ -423,13 +2229,44 @@ const struct rtw89_mac_gen_def rtw89_mac_gen_be = {
 			B_BE_BFMEE_HE_NDPA_EN | B_BE_BFMEE_EHT_NDPA_EN,
 	},
 
+	.check_mac_en = rtw89_mac_check_mac_en_be,
+	.sys_init = sys_init_be,
+	.trx_init = trx_init_be,
+	.hci_func_en = rtw89_mac_hci_func_en_be,
+	.dmac_func_pre_en = rtw89_mac_dmac_func_pre_en_be,
+	.dle_func_en = dle_func_en_be,
+	.dle_clk_en = dle_clk_en_be,
 	.bf_assoc = rtw89_mac_bf_assoc_be,
 
+	.typ_fltr_opt = rtw89_mac_typ_fltr_opt_be,
+
+	.dle_mix_cfg = dle_mix_cfg_be,
+	.chk_dle_rdy = chk_dle_rdy_be,
+	.dle_buf_req = dle_buf_req_be,
+	.hfc_func_en = hfc_func_en_be,
+	.hfc_h2c_cfg = hfc_h2c_cfg_be,
+	.hfc_mix_cfg = hfc_mix_cfg_be,
+	.hfc_get_mix_info = hfc_get_mix_info_be,
+	.wde_quota_cfg = wde_quota_cfg_be,
+	.ple_quota_cfg = ple_quota_cfg_be,
+	.set_cpuio = set_cpuio_be,
+
 	.disable_cpu = rtw89_mac_disable_cpu_be,
 	.fwdl_enable_wcpu = rtw89_mac_fwdl_enable_wcpu_be,
 	.fwdl_get_status = fwdl_get_status_be,
 	.fwdl_check_path_ready = rtw89_fwdl_check_path_ready_be,
+	.parse_efuse_map = rtw89_parse_efuse_map_be,
+	.parse_phycap_map = rtw89_parse_phycap_map_be,
+	.cnv_efuse_state = rtw89_cnv_efuse_state_be,
 
 	.get_txpwr_cr = rtw89_mac_get_txpwr_cr_be,
+
+	.write_xtal_si = rtw89_mac_write_xtal_si_be,
+	.read_xtal_si = rtw89_mac_read_xtal_si_be,
+
+	.dump_qta_lost = rtw89_mac_dump_qta_lost_be,
+	.dump_err_status = rtw89_mac_dump_err_status_be,
+
+	.is_txq_empty = mac_is_txq_empty_be,
 };
 EXPORT_SYMBOL(rtw89_mac_gen_be);
diff --git a/drivers/net/wireless/realtek/rtw89/pci.c b/drivers/net/wireless/realtek/rtw89/pci.c
index 14ddb0d39e63..769f1ce62ebc 100644
--- a/drivers/net/wireless/realtek/rtw89/pci.c
+++ b/drivers/net/wireless/realtek/rtw89/pci.c
@@ -19,28 +19,25 @@ MODULE_PARM_DESC(disable_clkreq, "Set Y to disable PCI clkreq support");
 MODULE_PARM_DESC(disable_aspm_l1, "Set Y to disable PCI ASPM L1 support");
 MODULE_PARM_DESC(disable_aspm_l1ss, "Set Y to disable PCI L1SS support");
 
-static int rtw89_pci_rst_bdram_pcie(struct rtw89_dev *rtwdev)
+static int rtw89_pci_rst_bdram_ax(struct rtw89_dev *rtwdev)
 {
 	u32 val;
 	int ret;
 
-	rtw89_write32(rtwdev, R_AX_PCIE_INIT_CFG1,
-		      rtw89_read32(rtwdev, R_AX_PCIE_INIT_CFG1) | B_AX_RST_BDRAM);
+	rtw89_write32_set(rtwdev, R_AX_PCIE_INIT_CFG1, B_AX_RST_BDRAM);
 
 	ret = read_poll_timeout_atomic(rtw89_read32, val, !(val & B_AX_RST_BDRAM),
 				       1, RTW89_PCI_POLL_BDRAM_RST_CNT, false,
 				       rtwdev, R_AX_PCIE_INIT_CFG1);
 
-	if (ret)
-		return -EBUSY;
-
-	return 0;
+	return ret;
 }
 
 static u32 rtw89_pci_dma_recalc(struct rtw89_dev *rtwdev,
 				struct rtw89_pci_dma_ring *bd_ring,
 				u32 cur_idx, bool tx)
 {
+	const struct rtw89_pci_info *info = rtwdev->pci_info;
 	u32 cnt, cur_rp, wp, rp, len;
 
 	rp = bd_ring->rp;
@@ -48,10 +45,14 @@ static u32 rtw89_pci_dma_recalc(struct rtw89_dev *rtwdev,
 	len = bd_ring->len;
 
 	cur_rp = FIELD_GET(TXBD_HW_IDX_MASK, cur_idx);
-	if (tx)
+	if (tx) {
 		cnt = cur_rp >= rp ? cur_rp - rp : len - (rp - cur_rp);
-	else
+	} else {
+		if (info->rx_ring_eq_is_full)
+			wp += 1;
+
 		cnt = cur_rp >= wp ? cur_rp - wp : len - (wp - cur_rp);
+	}
 
 	bd_ring->rp = cur_rp;
 
@@ -226,6 +227,21 @@ rtw89_skb_put_rx_data(struct rtw89_dev *rtwdev, bool fs, bool ls,
 	return true;
 }
 
+static u32 rtw89_pci_get_rx_skb_idx(struct rtw89_dev *rtwdev,
+				    struct rtw89_pci_dma_ring *bd_ring)
+{
+	const struct rtw89_pci_info *info = rtwdev->pci_info;
+	u32 wp = bd_ring->wp;
+
+	if (!info->rx_ring_eq_is_full)
+		return wp;
+
+	if (++wp >= bd_ring->len)
+		wp = 0;
+
+	return wp;
+}
+
 static u32 rtw89_pci_rxbd_deliver_skbs(struct rtw89_dev *rtwdev,
 				       struct rtw89_pci_rx_ring *rx_ring)
 {
@@ -235,12 +251,14 @@ static u32 rtw89_pci_rxbd_deliver_skbs(struct rtw89_dev *rtwdev,
 	struct sk_buff *new = rx_ring->diliver_skb;
 	struct sk_buff *skb;
 	u32 rxinfo_size = sizeof(struct rtw89_pci_rxbd_info);
+	u32 skb_idx;
 	u32 offset;
 	u32 cnt = 1;
 	bool fs, ls;
 	int ret;
 
-	skb = rx_ring->buf[bd_ring->wp];
+	skb_idx = rtw89_pci_get_rx_skb_idx(rtwdev, bd_ring);
+	skb = rx_ring->buf[skb_idx];
 	rtw89_pci_sync_skb_for_cpu(rtwdev, skb);
 
 	ret = rtw89_pci_rxbd_info_update(rtwdev, skb);
@@ -525,10 +543,12 @@ static u32 rtw89_pci_release_tx_skbs(struct rtw89_dev *rtwdev,
 	u32 cnt = 0;
 	u32 rpp_size = sizeof(struct rtw89_pci_rpp_fmt);
 	u32 rxinfo_size = sizeof(struct rtw89_pci_rxbd_info);
+	u32 skb_idx;
 	u32 offset;
 	int ret;
 
-	skb = rx_ring->buf[bd_ring->wp];
+	skb_idx = rtw89_pci_get_rx_skb_idx(rtwdev, bd_ring);
+	skb = rx_ring->buf[skb_idx];
 	rtw89_pci_sync_skb_for_cpu(rtwdev, skb);
 
 	ret = rtw89_pci_rxbd_info_update(rtwdev, skb);
@@ -676,11 +696,26 @@ void rtw89_pci_recognize_intrs_v1(struct rtw89_dev *rtwdev,
 }
 EXPORT_SYMBOL(rtw89_pci_recognize_intrs_v1);
 
-static void rtw89_pci_clear_isr0(struct rtw89_dev *rtwdev, u32 isr00)
+void rtw89_pci_recognize_intrs_v2(struct rtw89_dev *rtwdev,
+				  struct rtw89_pci *rtwpci,
+				  struct rtw89_pci_isrs *isrs)
 {
-	/* write 1 clear */
-	rtw89_write32(rtwdev, R_AX_PCIE_HISR00, isr00);
+	isrs->ind_isrs = rtw89_read32(rtwdev, R_BE_PCIE_HISR) & rtwpci->ind_intrs;
+	isrs->halt_c2h_isrs = isrs->ind_isrs & B_BE_HS0ISR_IND_INT ?
+			      rtw89_read32(rtwdev, R_BE_HISR0) & rtwpci->halt_c2h_intrs : 0;
+	isrs->isrs[0] = isrs->ind_isrs & B_BE_HCI_AXIDMA_INT ?
+			rtw89_read32(rtwdev, R_BE_HAXI_HISR00) & rtwpci->intrs[0] : 0;
+	isrs->isrs[1] = rtw89_read32(rtwdev, R_BE_PCIE_DMA_ISR);
+
+	if (isrs->halt_c2h_isrs)
+		rtw89_write32(rtwdev, R_BE_HISR0, isrs->halt_c2h_isrs);
+	if (isrs->isrs[0])
+		rtw89_write32(rtwdev, R_BE_HAXI_HISR00, isrs->isrs[0]);
+	if (isrs->isrs[1])
+		rtw89_write32(rtwdev, R_BE_PCIE_DMA_ISR, isrs->isrs[1]);
+	rtw89_write32(rtwdev, R_BE_PCIE_HISR, isrs->ind_isrs);
 }
+EXPORT_SYMBOL(rtw89_pci_recognize_intrs_v2);
 
 void rtw89_pci_enable_intr(struct rtw89_dev *rtwdev, struct rtw89_pci *rtwpci)
 {
@@ -713,6 +748,22 @@ void rtw89_pci_disable_intr_v1(struct rtw89_dev *rtwdev, struct rtw89_pci *rtwpc
 }
 EXPORT_SYMBOL(rtw89_pci_disable_intr_v1);
 
+void rtw89_pci_enable_intr_v2(struct rtw89_dev *rtwdev, struct rtw89_pci *rtwpci)
+{
+	rtw89_write32(rtwdev, R_BE_HIMR0, rtwpci->halt_c2h_intrs);
+	rtw89_write32(rtwdev, R_BE_HAXI_HIMR00, rtwpci->intrs[0]);
+	rtw89_write32(rtwdev, R_BE_PCIE_DMA_IMR_0_V1, rtwpci->intrs[1]);
+	rtw89_write32(rtwdev, R_BE_PCIE_HIMR0, rtwpci->ind_intrs);
+}
+EXPORT_SYMBOL(rtw89_pci_enable_intr_v2);
+
+void rtw89_pci_disable_intr_v2(struct rtw89_dev *rtwdev, struct rtw89_pci *rtwpci)
+{
+	rtw89_write32(rtwdev, R_BE_PCIE_HIMR0, 0);
+	rtw89_write32(rtwdev, R_BE_PCIE_DMA_IMR_0_V1, 0);
+}
+EXPORT_SYMBOL(rtw89_pci_disable_intr_v2);
+
 static void rtw89_pci_ops_recovery_start(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_pci *rtwpci = (struct rtw89_pci *)rtwdev->priv;
@@ -753,6 +804,8 @@ static irqreturn_t rtw89_pci_interrupt_threadfn(int irq, void *dev)
 {
 	struct rtw89_dev *rtwdev = dev;
 	struct rtw89_pci *rtwpci = (struct rtw89_pci *)rtwdev->priv;
+	const struct rtw89_pci_info *info = rtwdev->pci_info;
+	const struct rtw89_pci_gen_def *gen_def = info->gen_def;
 	struct rtw89_pci_isrs isrs;
 	unsigned long flags;
 
@@ -760,13 +813,13 @@ static irqreturn_t rtw89_pci_interrupt_threadfn(int irq, void *dev)
 	rtw89_chip_recognize_intrs(rtwdev, rtwpci, &isrs);
 	spin_unlock_irqrestore(&rtwpci->irq_lock, flags);
 
-	if (unlikely(isrs.isrs[0] & B_AX_RDU_INT))
+	if (unlikely(isrs.isrs[0] & gen_def->isr_rdu))
 		rtw89_pci_isr_rxd_unavail(rtwdev, rtwpci);
 
-	if (unlikely(isrs.halt_c2h_isrs & B_AX_HALT_C2H_INT_EN))
+	if (unlikely(isrs.halt_c2h_isrs & gen_def->isr_halt_c2h))
 		rtw89_ser_notify(rtwdev, rtw89_mac_get_err_status(rtwdev));
 
-	if (unlikely(isrs.halt_c2h_isrs & B_AX_WDT_TIMEOUT_INT_EN))
+	if (unlikely(isrs.halt_c2h_isrs & gen_def->isr_wdt_timeout))
 		rtw89_ser_notify(rtwdev, MAC_AX_ERR_L2_ERR_WDT_TIMEOUT_INT);
 
 	if (unlikely(rtwpci->under_recovery))
@@ -817,6 +870,15 @@ exit:
 	return irqret;
 }
 
+#define DEF_TXCHADDRS_TYPE2(gen, ch_idx, txch, v...) \
+	[RTW89_TXCH_##ch_idx] = { \
+		.num = R_##gen##_##txch##_TXBD_NUM ##v, \
+		.idx = R_##gen##_##txch##_TXBD_IDX ##v, \
+		.bdram = 0, \
+		.desa_l = R_##gen##_##txch##_TXBD_DESA_L ##v, \
+		.desa_h = R_##gen##_##txch##_TXBD_DESA_H ##v, \
+	}
+
 #define DEF_TXCHADDRS_TYPE1(info, txch, v...) \
 	[RTW89_TXCH_##txch] = { \
 		.num = R_AX_##txch##_TXBD_NUM ##v, \
@@ -835,12 +897,12 @@ exit:
 		.desa_h = R_AX_##txch##_TXBD_DESA_H ##v, \
 	}
 
-#define DEF_RXCHADDRS(info, rxch, v...) \
-	[RTW89_RXCH_##rxch] = { \
-		.num = R_AX_##rxch##_RXBD_NUM ##v, \
-		.idx = R_AX_##rxch##_RXBD_IDX ##v, \
-		.desa_l = R_AX_##rxch##_RXBD_DESA_L ##v, \
-		.desa_h = R_AX_##rxch##_RXBD_DESA_H ##v, \
+#define DEF_RXCHADDRS(gen, ch_idx, rxch, v...) \
+	[RTW89_RXCH_##ch_idx] = { \
+		.num = R_##gen##_##rxch##_RXBD_NUM ##v, \
+		.idx = R_##gen##_##rxch##_RXBD_IDX ##v, \
+		.desa_l = R_##gen##_##rxch##_RXBD_DESA_L ##v, \
+		.desa_h = R_##gen##_##rxch##_RXBD_DESA_H ##v, \
 	}
 
 const struct rtw89_pci_ch_dma_addr_set rtw89_pci_ch_dma_addr_set = {
@@ -860,8 +922,8 @@ const struct rtw89_pci_ch_dma_addr_set rtw89_pci_ch_dma_addr_set = {
 		DEF_TXCHADDRS(info, CH12),
 	},
 	.rx = {
-		DEF_RXCHADDRS(info, RXQ),
-		DEF_RXCHADDRS(info, RPQ),
+		DEF_RXCHADDRS(AX, RXQ, RXQ),
+		DEF_RXCHADDRS(AX, RPQ, RPQ),
 	},
 };
 EXPORT_SYMBOL(rtw89_pci_ch_dma_addr_set);
@@ -883,12 +945,35 @@ const struct rtw89_pci_ch_dma_addr_set rtw89_pci_ch_dma_addr_set_v1 = {
 		DEF_TXCHADDRS(info, CH12, _V1),
 	},
 	.rx = {
-		DEF_RXCHADDRS(info, RXQ, _V1),
-		DEF_RXCHADDRS(info, RPQ, _V1),
+		DEF_RXCHADDRS(AX, RXQ, RXQ, _V1),
+		DEF_RXCHADDRS(AX, RPQ, RPQ, _V1),
 	},
 };
 EXPORT_SYMBOL(rtw89_pci_ch_dma_addr_set_v1);
 
+const struct rtw89_pci_ch_dma_addr_set rtw89_pci_ch_dma_addr_set_be = {
+	.tx = {
+		DEF_TXCHADDRS_TYPE2(BE, ACH0, CH0, _V1),
+		DEF_TXCHADDRS_TYPE2(BE, ACH1, CH1, _V1),
+		DEF_TXCHADDRS_TYPE2(BE, ACH2, CH2, _V1),
+		DEF_TXCHADDRS_TYPE2(BE, ACH3, CH3, _V1),
+		DEF_TXCHADDRS_TYPE2(BE, ACH4, CH4, _V1),
+		DEF_TXCHADDRS_TYPE2(BE, ACH5, CH5, _V1),
+		DEF_TXCHADDRS_TYPE2(BE, ACH6, CH6, _V1),
+		DEF_TXCHADDRS_TYPE2(BE, ACH7, CH7, _V1),
+		DEF_TXCHADDRS_TYPE2(BE, CH8, CH8, _V1),
+		DEF_TXCHADDRS_TYPE2(BE, CH9, CH9, _V1),
+		DEF_TXCHADDRS_TYPE2(BE, CH10, CH10, _V1),
+		DEF_TXCHADDRS_TYPE2(BE, CH11, CH11, _V1),
+		DEF_TXCHADDRS_TYPE2(BE, CH12, CH12, _V1),
+	},
+	.rx = {
+		DEF_RXCHADDRS(BE, RXQ, RXQ0, _V1),
+		DEF_RXCHADDRS(BE, RPQ, RPQ0, _V1),
+	},
+};
+EXPORT_SYMBOL(rtw89_pci_ch_dma_addr_set_be);
+
 #undef DEF_TXCHADDRS_TYPE1
 #undef DEF_TXCHADDRS
 #undef DEF_RXCHADDRS
@@ -1422,6 +1507,7 @@ static void rtw89_pci_reset_trx_rings(struct rtw89_dev *rtwdev)
 	struct rtw89_pci_dma_ring *bd_ring;
 	const struct rtw89_pci_bd_ram *bd_ram;
 	u32 addr_num;
+	u32 addr_idx;
 	u32 addr_bdram;
 	u32 addr_desa_l;
 	u32 val32;
@@ -1433,19 +1519,21 @@ static void rtw89_pci_reset_trx_rings(struct rtw89_dev *rtwdev)
 
 		tx_ring = &rtwpci->tx_rings[i];
 		bd_ring = &tx_ring->bd_ring;
-		bd_ram = &bd_ram_table[i];
+		bd_ram = bd_ram_table ? &bd_ram_table[i] : NULL;
 		addr_num = bd_ring->addr.num;
 		addr_bdram = bd_ring->addr.bdram;
 		addr_desa_l = bd_ring->addr.desa_l;
 		bd_ring->wp = 0;
 		bd_ring->rp = 0;
 
-		val32 = FIELD_PREP(BDRAM_SIDX_MASK, bd_ram->start_idx) |
-			FIELD_PREP(BDRAM_MAX_MASK, bd_ram->max_num) |
-			FIELD_PREP(BDRAM_MIN_MASK, bd_ram->min_num);
-
 		rtw89_write16(rtwdev, addr_num, bd_ring->len);
-		rtw89_write32(rtwdev, addr_bdram, val32);
+		if (addr_bdram && bd_ram) {
+			val32 = FIELD_PREP(BDRAM_SIDX_MASK, bd_ram->start_idx) |
+				FIELD_PREP(BDRAM_MAX_MASK, bd_ram->max_num) |
+				FIELD_PREP(BDRAM_MIN_MASK, bd_ram->min_num);
+
+			rtw89_write32(rtwdev, addr_bdram, val32);
+		}
 		rtw89_write32(rtwdev, addr_desa_l, bd_ring->dma);
 	}
 
@@ -1453,14 +1541,21 @@ static void rtw89_pci_reset_trx_rings(struct rtw89_dev *rtwdev)
 		rx_ring = &rtwpci->rx_rings[i];
 		bd_ring = &rx_ring->bd_ring;
 		addr_num = bd_ring->addr.num;
+		addr_idx = bd_ring->addr.idx;
 		addr_desa_l = bd_ring->addr.desa_l;
-		bd_ring->wp = 0;
+		if (info->rx_ring_eq_is_full)
+			bd_ring->wp = bd_ring->len - 1;
+		else
+			bd_ring->wp = 0;
 		bd_ring->rp = 0;
 		rx_ring->diliver_skb = NULL;
 		rx_ring->diliver_desc.ready = false;
 
 		rtw89_write16(rtwdev, addr_num, bd_ring->len);
 		rtw89_write32(rtwdev, addr_desa_l, bd_ring->dma);
+
+		if (info->rx_ring_eq_is_full)
+			rtw89_write16(rtwdev, addr_idx, bd_ring->wp);
 	}
 }
 
@@ -1471,7 +1566,7 @@ static void rtw89_pci_release_tx_ring(struct rtw89_dev *rtwdev,
 	rtw89_pci_release_pending_txwd_skb(rtwdev, tx_ring);
 }
 
-static void rtw89_pci_ops_reset(struct rtw89_dev *rtwdev)
+void rtw89_pci_ops_reset(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_pci *rtwpci = (struct rtw89_pci *)rtwdev->priv;
 	const struct rtw89_pci_info *info = rtwdev->pci_info;
@@ -1684,24 +1779,16 @@ static void rtw89_pci_ctrl_dma_trx(struct rtw89_dev *rtwdev, bool enable)
 
 static void rtw89_pci_ctrl_dma_io(struct rtw89_dev *rtwdev, bool enable)
 {
-	enum rtw89_core_chip_id chip_id = rtwdev->chip->chip_id;
-	u32 reg, mask;
-
-	if (chip_id == RTL8852C) {
-		reg = R_AX_HAXI_INIT_CFG1;
-		mask = B_AX_STOP_AXI_MST;
-	} else {
-		reg = R_AX_PCIE_DMA_STOP1;
-		mask = B_AX_STOP_PCIEIO;
-	}
+	const struct rtw89_pci_info *info = rtwdev->pci_info;
+	const struct rtw89_reg_def *reg = &info->dma_io_stop;
 
 	if (enable)
-		rtw89_write32_clr(rtwdev, reg, mask);
+		rtw89_write32_clr(rtwdev, reg->addr, reg->mask);
 	else
-		rtw89_write32_set(rtwdev, reg, mask);
+		rtw89_write32_set(rtwdev, reg->addr, reg->mask);
 }
 
-static void rtw89_pci_ctrl_dma_all(struct rtw89_dev *rtwdev, bool enable)
+void rtw89_pci_ctrl_dma_all(struct rtw89_dev *rtwdev, bool enable)
 {
 	rtw89_pci_ctrl_dma_io(rtwdev, enable);
 	rtw89_pci_ctrl_dma_trx(rtwdev, enable);
@@ -2303,7 +2390,7 @@ static void rtw89_pci_set_keep_reg(struct rtw89_dev *rtwdev)
 			  B_AX_PCIE_TXRST_KEEP_REG | B_AX_PCIE_RXRST_KEEP_REG);
 }
 
-static void rtw89_pci_clr_idx_all(struct rtw89_dev *rtwdev)
+static void rtw89_pci_clr_idx_all_ax(struct rtw89_dev *rtwdev)
 {
 	const struct rtw89_pci_info *info = rtwdev->pci_info;
 	enum rtw89_core_chip_id chip_id = rtwdev->chip->chip_id;
@@ -2491,7 +2578,7 @@ static int rtw89_pci_ops_deinit(struct rtw89_dev *rtwdev)
 	return 0;
 }
 
-static int rtw89_pci_ops_mac_pre_init(struct rtw89_dev *rtwdev)
+static int rtw89_pci_ops_mac_pre_init_ax(struct rtw89_dev *rtwdev)
 {
 	const struct rtw89_pci_info *info = rtwdev->pci_info;
 	int ret;
@@ -2550,7 +2637,7 @@ static int rtw89_pci_ops_mac_pre_init(struct rtw89_dev *rtwdev)
 	/* fill TRX BD indexes */
 	rtw89_pci_ops_reset(rtwdev);
 
-	ret = rtw89_pci_rst_bdram_pcie(rtwdev);
+	ret = rtw89_pci_rst_bdram_ax(rtwdev);
 	if (ret) {
 		rtw89_warn(rtwdev, "reset bdram busy\n");
 		return ret;
@@ -2648,7 +2735,7 @@ int rtw89_pci_ltr_set_v1(struct rtw89_dev *rtwdev, bool en)
 }
 EXPORT_SYMBOL(rtw89_pci_ltr_set_v1);
 
-static int rtw89_pci_ops_mac_post_init(struct rtw89_dev *rtwdev)
+static int rtw89_pci_ops_mac_post_init_ax(struct rtw89_dev *rtwdev)
 {
 	const struct rtw89_pci_info *info = rtwdev->pci_info;
 	enum rtw89_core_chip_id chip_id = rtwdev->chip->chip_id;
@@ -3026,6 +3113,7 @@ static int rtw89_pci_alloc_rx_ring(struct rtw89_dev *rtwdev,
 				   struct rtw89_pci_rx_ring *rx_ring,
 				   u32 desc_size, u32 len, u32 rxch)
 {
+	const struct rtw89_pci_info *info = rtwdev->pci_info;
 	const struct rtw89_pci_ch_dma_addr *rxch_addr;
 	struct sk_buff *skb;
 	u8 *head;
@@ -3052,7 +3140,10 @@ static int rtw89_pci_alloc_rx_ring(struct rtw89_dev *rtwdev,
 	rx_ring->bd_ring.len = len;
 	rx_ring->bd_ring.desc_size = desc_size;
 	rx_ring->bd_ring.addr = *rxch_addr;
-	rx_ring->bd_ring.wp = 0;
+	if (info->rx_ring_eq_is_full)
+		rx_ring->bd_ring.wp = len - 1;
+	else
+		rx_ring->bd_ring.wp = 0;
 	rx_ring->bd_ring.rp = 0;
 	rx_ring->buf_sz = buf_sz;
 	rx_ring->diliver_skb = NULL;
@@ -3289,6 +3380,55 @@ void rtw89_pci_config_intr_mask_v1(struct rtw89_dev *rtwdev)
 }
 EXPORT_SYMBOL(rtw89_pci_config_intr_mask_v1);
 
+static void rtw89_pci_recovery_intr_mask_v2(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_pci *rtwpci = (struct rtw89_pci *)rtwdev->priv;
+
+	rtwpci->ind_intrs = B_BE_HS0_IND_INT_EN0;
+	rtwpci->halt_c2h_intrs = B_BE_HALT_C2H_INT_EN | B_BE_WDT_TIMEOUT_INT_EN;
+	rtwpci->intrs[0] = 0;
+	rtwpci->intrs[1] = B_BE_PCIE_RX_RX0P2_IMR0_V1 |
+			   B_BE_PCIE_RX_RPQ0_IMR0_V1;
+}
+
+static void rtw89_pci_default_intr_mask_v2(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_pci *rtwpci = (struct rtw89_pci *)rtwdev->priv;
+
+	rtwpci->ind_intrs = B_BE_HCI_AXIDMA_INT_EN0 |
+			    B_BE_HS0_IND_INT_EN0;
+	rtwpci->halt_c2h_intrs = B_BE_HALT_C2H_INT_EN | B_BE_WDT_TIMEOUT_INT_EN;
+	rtwpci->intrs[0] = B_BE_RDU_CH1_INT_IMR_V1 |
+			   B_BE_RDU_CH0_INT_IMR_V1;
+	rtwpci->intrs[1] = B_BE_PCIE_RX_RX0P2_IMR0_V1 |
+			   B_BE_PCIE_RX_RPQ0_IMR0_V1;
+}
+
+static void rtw89_pci_low_power_intr_mask_v2(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_pci *rtwpci = (struct rtw89_pci *)rtwdev->priv;
+
+	rtwpci->ind_intrs = B_BE_HS0_IND_INT_EN0 |
+			    B_BE_HS1_IND_INT_EN0;
+	rtwpci->halt_c2h_intrs = B_BE_HALT_C2H_INT_EN | B_BE_WDT_TIMEOUT_INT_EN;
+	rtwpci->intrs[0] = 0;
+	rtwpci->intrs[1] = B_BE_PCIE_RX_RX0P2_IMR0_V1 |
+			   B_BE_PCIE_RX_RPQ0_IMR0_V1;
+}
+
+void rtw89_pci_config_intr_mask_v2(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_pci *rtwpci = (struct rtw89_pci *)rtwdev->priv;
+
+	if (rtwpci->under_recovery)
+		rtw89_pci_recovery_intr_mask_v2(rtwdev);
+	else if (rtwpci->low_power)
+		rtw89_pci_low_power_intr_mask_v2(rtwdev);
+	else
+		rtw89_pci_default_intr_mask_v2(rtwdev);
+}
+EXPORT_SYMBOL(rtw89_pci_config_intr_mask_v2);
+
 static int rtw89_pci_request_irq(struct rtw89_dev *rtwdev,
 				 struct pci_dev *pdev)
 {
@@ -3480,19 +3620,27 @@ static void rtw89_pci_aspm_set(struct rtw89_dev *rtwdev, bool enable)
 
 static void rtw89_pci_recalc_int_mit(struct rtw89_dev *rtwdev)
 {
+	enum rtw89_chip_gen chip_gen = rtwdev->chip->chip_gen;
+	const struct rtw89_pci_info *info = rtwdev->pci_info;
 	struct rtw89_traffic_stats *stats = &rtwdev->stats;
 	enum rtw89_tfc_lv tx_tfc_lv = stats->tx_tfc_lv;
 	enum rtw89_tfc_lv rx_tfc_lv = stats->rx_tfc_lv;
 	u32 val = 0;
 
-	if (!rtwdev->scanning &&
-	    (tx_tfc_lv >= RTW89_TFC_HIGH || rx_tfc_lv >= RTW89_TFC_HIGH))
+	if (rtwdev->scanning ||
+	    (tx_tfc_lv < RTW89_TFC_HIGH && rx_tfc_lv < RTW89_TFC_HIGH))
+		goto out;
+
+	if (chip_gen == RTW89_CHIP_BE)
+		val = B_BE_PCIE_MIT_RX0P2_EN | B_BE_PCIE_MIT_RX0P1_EN;
+	else
 		val = B_AX_RXMIT_RXP2_SEL | B_AX_RXMIT_RXP1_SEL |
 		      FIELD_PREP(B_AX_RXCOUNTER_MATCH_MASK, RTW89_PCI_RXBD_NUM_MAX / 2) |
 		      FIELD_PREP(B_AX_RXTIMER_UNIT_MASK, AX_RXTIMER_UNIT_64US) |
 		      FIELD_PREP(B_AX_RXTIMER_MATCH_MASK, 2048 / 64);
 
-	rtw89_write32(rtwdev, R_AX_INT_MIT_RX, val);
+out:
+	rtw89_write32(rtwdev, info->mit_addr, val);
 }
 
 static void rtw89_pci_link_cfg(struct rtw89_dev *rtwdev)
@@ -3582,7 +3730,7 @@ static void rtw89_pci_l1ss_cfg(struct rtw89_dev *rtwdev)
 		rtw89_pci_l1ss_set(rtwdev, true);
 }
 
-static int rtw89_pci_poll_io_idle(struct rtw89_dev *rtwdev)
+static int rtw89_pci_poll_io_idle_ax(struct rtw89_dev *rtwdev)
 {
 	int ret = 0;
 	u32 sts;
@@ -3599,7 +3747,7 @@ static int rtw89_pci_poll_io_idle(struct rtw89_dev *rtwdev)
 	return ret;
 }
 
-static int rtw89_pci_lv1rst_stop_dma(struct rtw89_dev *rtwdev)
+static int rtw89_pci_lv1rst_stop_dma_ax(struct rtw89_dev *rtwdev)
 {
 	u32 val;
 	int ret;
@@ -3608,7 +3756,7 @@ static int rtw89_pci_lv1rst_stop_dma(struct rtw89_dev *rtwdev)
 		return 0;
 
 	rtw89_pci_ctrl_dma_all(rtwdev, false);
-	ret = rtw89_pci_poll_io_idle(rtwdev);
+	ret = rtw89_pci_poll_io_idle_ax(rtwdev);
 	if (ret) {
 		val = rtw89_read32(rtwdev, R_AX_DBG_ERR_FLAG);
 		rtw89_debug(rtwdev, RTW89_DBG_HCI,
@@ -3619,7 +3767,7 @@ static int rtw89_pci_lv1rst_stop_dma(struct rtw89_dev *rtwdev)
 		if (val & B_AX_RX_STUCK)
 			rtw89_mac_ctrl_hci_dma_rx(rtwdev, false);
 		rtw89_mac_ctrl_hci_dma_trx(rtwdev, true);
-		ret = rtw89_pci_poll_io_idle(rtwdev);
+		ret = rtw89_pci_poll_io_idle_ax(rtwdev);
 		val = rtw89_read32(rtwdev, R_AX_DBG_ERR_FLAG);
 		rtw89_debug(rtwdev, RTW89_DBG_HCI,
 			    "[PCIe] poll_io_idle fail, after 0x%08x: 0x%08x\n",
@@ -3629,23 +3777,7 @@ static int rtw89_pci_lv1rst_stop_dma(struct rtw89_dev *rtwdev)
 	return ret;
 }
 
-
-
-static int rtw89_pci_rst_bdram(struct rtw89_dev *rtwdev)
-{
-	int ret = 0;
-	u32 val32, sts;
-
-	val32 = B_AX_RST_BDRAM;
-	rtw89_write32_set(rtwdev, R_AX_PCIE_INIT_CFG1, val32);
-
-	ret = read_poll_timeout_atomic(rtw89_read32, sts,
-				       (sts & B_AX_RST_BDRAM) == 0x0, 1, 100,
-				       true, rtwdev, R_AX_PCIE_INIT_CFG1);
-	return ret;
-}
-
-static int rtw89_pci_lv1rst_start_dma(struct rtw89_dev *rtwdev)
+static int rtw89_pci_lv1rst_start_dma_ax(struct rtw89_dev *rtwdev)
 {
 	u32 ret;
 
@@ -3656,7 +3788,7 @@ static int rtw89_pci_lv1rst_start_dma(struct rtw89_dev *rtwdev)
 	rtw89_mac_ctrl_hci_dma_trx(rtwdev, true);
 	rtw89_pci_clr_idx_all(rtwdev);
 
-	ret = rtw89_pci_rst_bdram(rtwdev);
+	ret = rtw89_pci_rst_bdram_ax(rtwdev);
 	if (ret)
 		return ret;
 
@@ -3667,18 +3799,20 @@ static int rtw89_pci_lv1rst_start_dma(struct rtw89_dev *rtwdev)
 static int rtw89_pci_ops_mac_lv1_recovery(struct rtw89_dev *rtwdev,
 					  enum rtw89_lv1_rcvy_step step)
 {
+	const struct rtw89_pci_info *info = rtwdev->pci_info;
+	const struct rtw89_pci_gen_def *gen_def = info->gen_def;
 	int ret;
 
 	switch (step) {
 	case RTW89_LV1_RCVY_STEP_1:
-		ret = rtw89_pci_lv1rst_stop_dma(rtwdev);
+		ret = gen_def->lv1rst_stop_dma(rtwdev);
 		if (ret)
 			rtw89_err(rtwdev, "lv1 rcvy pci stop dma fail\n");
 
 		break;
 
 	case RTW89_LV1_RCVY_STEP_2:
-		ret = rtw89_pci_lv1rst_start_dma(rtwdev);
+		ret = gen_def->lv1rst_start_dma(rtwdev);
 		if (ret)
 			rtw89_err(rtwdev, "lv1 rcvy pci start dma fail\n");
 		break;
@@ -3692,29 +3826,41 @@ static int rtw89_pci_ops_mac_lv1_recovery(struct rtw89_dev *rtwdev,
 
 static void rtw89_pci_ops_dump_err_status(struct rtw89_dev *rtwdev)
 {
-	rtw89_info(rtwdev, "R_AX_RPQ_RXBD_IDX =0x%08x\n",
-		   rtw89_read32(rtwdev, R_AX_RPQ_RXBD_IDX));
-	rtw89_info(rtwdev, "R_AX_DBG_ERR_FLAG=0x%08x\n",
-		   rtw89_read32(rtwdev, R_AX_DBG_ERR_FLAG));
-	rtw89_info(rtwdev, "R_AX_LBC_WATCHDOG=0x%08x\n",
-		   rtw89_read32(rtwdev, R_AX_LBC_WATCHDOG));
+	if (rtwdev->chip->chip_gen == RTW89_CHIP_BE)
+		return;
+
+	if (rtwdev->chip->chip_id == RTL8852C) {
+		rtw89_info(rtwdev, "R_AX_DBG_ERR_FLAG=0x%08x\n",
+			   rtw89_read32(rtwdev, R_AX_DBG_ERR_FLAG_V1));
+		rtw89_info(rtwdev, "R_AX_LBC_WATCHDOG=0x%08x\n",
+			   rtw89_read32(rtwdev, R_AX_LBC_WATCHDOG_V1));
+	} else {
+		rtw89_info(rtwdev, "R_AX_RPQ_RXBD_IDX =0x%08x\n",
+			   rtw89_read32(rtwdev, R_AX_RPQ_RXBD_IDX));
+		rtw89_info(rtwdev, "R_AX_DBG_ERR_FLAG=0x%08x\n",
+			   rtw89_read32(rtwdev, R_AX_DBG_ERR_FLAG));
+		rtw89_info(rtwdev, "R_AX_LBC_WATCHDOG=0x%08x\n",
+			   rtw89_read32(rtwdev, R_AX_LBC_WATCHDOG));
+	}
 }
 
 static int rtw89_pci_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct rtw89_dev *rtwdev = container_of(napi, struct rtw89_dev, napi);
 	struct rtw89_pci *rtwpci = (struct rtw89_pci *)rtwdev->priv;
+	const struct rtw89_pci_info *info = rtwdev->pci_info;
+	const struct rtw89_pci_gen_def *gen_def = info->gen_def;
 	unsigned long flags;
 	int work_done;
 
 	rtwdev->napi_budget_countdown = budget;
 
-	rtw89_pci_clear_isr0(rtwdev, B_AX_RPQDMA_INT | B_AX_RPQBD_FULL_INT);
+	rtw89_write32(rtwdev, gen_def->isr_clear_rpq.addr, gen_def->isr_clear_rpq.data);
 	work_done = rtw89_pci_poll_rpq_dma(rtwdev, rtwpci, rtwdev->napi_budget_countdown);
 	if (work_done == budget)
 		return budget;
 
-	rtw89_pci_clear_isr0(rtwdev, B_AX_RXP1DMA_INT | B_AX_RXDMA_INT | B_AX_RDU_INT);
+	rtw89_write32(rtwdev, gen_def->isr_clear_rxq.addr, gen_def->isr_clear_rxq.data);
 	work_done += rtw89_pci_poll_rxq_dma(rtwdev, rtwpci, rtwdev->napi_budget_countdown);
 	if (work_done < budget && napi_complete_done(napi, work_done)) {
 		spin_lock_irqsave(&rtwpci->irq_lock, flags);
@@ -3791,6 +3937,26 @@ static int __maybe_unused rtw89_pci_resume(struct device *dev)
 SIMPLE_DEV_PM_OPS(rtw89_pm_ops, rtw89_pci_suspend, rtw89_pci_resume);
 EXPORT_SYMBOL(rtw89_pm_ops);
 
+const struct rtw89_pci_gen_def rtw89_pci_gen_ax = {
+	.isr_rdu = B_AX_RDU_INT,
+	.isr_halt_c2h = B_AX_HALT_C2H_INT_EN,
+	.isr_wdt_timeout = B_AX_WDT_TIMEOUT_INT_EN,
+	.isr_clear_rpq = {R_AX_PCIE_HISR00, B_AX_RPQDMA_INT | B_AX_RPQBD_FULL_INT},
+	.isr_clear_rxq = {R_AX_PCIE_HISR00, B_AX_RXP1DMA_INT | B_AX_RXDMA_INT |
+					    B_AX_RDU_INT},
+
+	.mac_pre_init = rtw89_pci_ops_mac_pre_init_ax,
+	.mac_pre_deinit = NULL,
+	.mac_post_init = rtw89_pci_ops_mac_post_init_ax,
+
+	.clr_idx_all = rtw89_pci_clr_idx_all_ax,
+	.rst_bdram = rtw89_pci_rst_bdram_ax,
+
+	.lv1rst_stop_dma = rtw89_pci_lv1rst_stop_dma_ax,
+	.lv1rst_start_dma = rtw89_pci_lv1rst_start_dma_ax,
+};
+EXPORT_SYMBOL(rtw89_pci_gen_ax);
+
 static const struct rtw89_hci_ops rtw89_pci_ops = {
 	.tx_write	= rtw89_pci_ops_tx_write,
 	.tx_kick_off	= rtw89_pci_ops_tx_kick_off,
@@ -3810,6 +3976,7 @@ static const struct rtw89_hci_ops rtw89_pci_ops = {
 	.write32	= rtw89_pci_ops_write32,
 
 	.mac_pre_init	= rtw89_pci_ops_mac_pre_init,
+	.mac_pre_deinit	= rtw89_pci_ops_mac_pre_deinit,
 	.mac_post_init	= rtw89_pci_ops_mac_post_init,
 	.deinit		= rtw89_pci_ops_deinit,
 
@@ -3829,7 +3996,7 @@ static const struct rtw89_hci_ops rtw89_pci_ops = {
 	.clear		= rtw89_pci_clear_resource,
 	.disable_intr	= rtw89_pci_disable_intr_lock,
 	.enable_intr	= rtw89_pci_enable_intr_lock,
-	.rst_bdram	= rtw89_pci_rst_bdram_pcie,
+	.rst_bdram	= rtw89_pci_reset_bdram,
 };
 
 int rtw89_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
diff --git a/drivers/net/wireless/realtek/rtw89/pci.h b/drivers/net/wireless/realtek/rtw89/pci.h
index 2f3d1ad3b0f7..ca5de77fee90 100644
--- a/drivers/net/wireless/realtek/rtw89/pci.h
+++ b/drivers/net/wireless/realtek/rtw89/pci.h
@@ -245,6 +245,203 @@
 #define B_AX_HS1ISR_IND_INT BIT(25)
 #define B_AX_PCIE_DBG_STE_INT BIT(13)
 
+#define R_BE_PCIE_FRZ_CLK 0x3004
+#define B_BE_PCIE_FRZ_MAC_HW_RST BIT(31)
+#define B_BE_PCIE_FRZ_CFG_SPC_RST BIT(30)
+#define B_BE_PCIE_FRZ_ELBI_RST BIT(29)
+#define B_BE_PCIE_MAC_IS_ACTIVE BIT(28)
+#define B_BE_PCIE_FRZ_RTK_HW_RST BIT(27)
+#define B_BE_PCIE_FRZ_REG_RST BIT(26)
+#define B_BE_PCIE_FRZ_ANA_RST BIT(25)
+#define B_BE_PCIE_FRZ_WLAN_RST BIT(24)
+#define B_BE_PCIE_FRZ_FLR_RST BIT(23)
+#define B_BE_PCIE_FRZ_RET_NON_STKY_RST BIT(22)
+#define B_BE_PCIE_FRZ_RET_STKY_RST BIT(21)
+#define B_BE_PCIE_FRZ_NON_STKY_RST BIT(20)
+#define B_BE_PCIE_FRZ_STKY_RST BIT(19)
+#define B_BE_PCIE_FRZ_RET_CORE_RST BIT(18)
+#define B_BE_PCIE_FRZ_PWR_RST BIT(17)
+#define B_BE_PCIE_FRZ_PERST_RST BIT(16)
+#define B_BE_PCIE_FRZ_PHY_ALOAD BIT(15)
+#define B_BE_PCIE_FRZ_PHY_HW_RST BIT(14)
+#define B_BE_PCIE_DBG_CLK BIT(4)
+#define B_BE_PCIE_EN_CLK BIT(3)
+#define B_BE_PCIE_DBI_ACLK_ACT BIT(2)
+#define B_BE_PCIE_S1_ACLK_ACT BIT(1)
+#define B_BE_PCIE_EN_AUX_CLK BIT(0)
+
+#define R_BE_PCIE_PS_CTRL 0x3008
+#define B_BE_RSM_L0S_EN BIT(8)
+#define B_BE_CMAC_EXIT_L1_EN BIT(7)
+#define B_BE_DMAC0_EXIT_L1_EN BIT(6)
+#define B_BE_FORCE_L0 BIT(5)
+#define B_BE_DBI_RO_WR_DISABLE BIT(4)
+#define B_BE_SEL_XFER_PENDING BIT(3)
+#define B_BE_SEL_REQ_ENTR_L1 BIT(2)
+#define B_BE_PCIE_EN_SWENT_L23 BIT(1)
+#define B_BE_SEL_REQ_EXIT_L1 BIT(0)
+
+#define R_BE_PCIE_LAT_CTRL 0x3044
+#define B_BE_ELBI_PHY_REMAP_MASK GENMASK(29, 24)
+#define B_BE_SYS_SUS_L12_EN BIT(17)
+#define B_BE_MDIO_S_EN BIT(16)
+#define B_BE_SYM_AUX_CLK_SEL BIT(15)
+#define B_BE_RTK_LDO_POWER_LATENCY_MASK GENMASK(11, 10)
+#define B_BE_RTK_LDO_BIAS_LATENCY_MASK GENMASK(9, 8)
+#define B_BE_CLK_REQ_LAT_MASK GENMASK(7, 4)
+
+#define R_BE_PCIE_HIMR0 0x30B0
+#define B_BE_PCIE_HB1_IND_INTA_IMR BIT(31)
+#define B_BE_PCIE_HB0_IND_INTA_IMR BIT(30)
+#define B_BE_HCI_AXIDMA_INTA_IMR BIT(29)
+#define B_BE_HC0_IND_INTA_IMR BIT(28)
+#define B_BE_HD1_IND_INTA_IMR BIT(27)
+#define B_BE_HD0_IND_INTA_IMR BIT(26)
+#define B_BE_HS1_IND_INTA_IMR BIT(25)
+#define B_BE_HS0_IND_INTA_IMR BIT(24)
+#define B_BE_PCIE_HOTRST_INT_EN BIT(16)
+#define B_BE_PCIE_FLR_INT_EN BIT(15)
+#define B_BE_PCIE_PERST_INT_EN BIT(14)
+#define B_BE_PCIE_DBG_STE_INT_EN BIT(13)
+#define B_BE_HB1_IND_INT_EN0 BIT(9)
+#define B_BE_HB0_IND_INT_EN0 BIT(8)
+#define B_BE_HC1_IND_INT_EN0 BIT(7)
+#define B_BE_HCI_AXIDMA_INT_EN0 BIT(5)
+#define B_BE_HC0_IND_INT_EN0 BIT(4)
+#define B_BE_HD1_IND_INT_EN0 BIT(3)
+#define B_BE_HD0_IND_INT_EN0 BIT(2)
+#define B_BE_HS1_IND_INT_EN0 BIT(1)
+#define B_BE_HS0_IND_INT_EN0 BIT(0)
+
+#define R_BE_PCIE_HISR 0x30B4
+#define B_BE_PCIE_HOTRST_INT BIT(16)
+#define B_BE_PCIE_FLR_INT BIT(15)
+#define B_BE_PCIE_PERST_INT BIT(14)
+#define B_BE_PCIE_DBG_STE_INT BIT(13)
+#define B_BE_HB1IMR_IND BIT(9)
+#define B_BE_HB0IMR_IND BIT(8)
+#define B_BE_HC1ISR_IND_INT BIT(7)
+#define B_BE_HCI_AXIDMA_INT BIT(5)
+#define B_BE_HC0ISR_IND_INT BIT(4)
+#define B_BE_HD1ISR_IND_INT BIT(3)
+#define B_BE_HD0ISR_IND_INT BIT(2)
+#define B_BE_HS1ISR_IND_INT BIT(1)
+#define B_BE_HS0ISR_IND_INT BIT(0)
+
+#define R_BE_PCIE_DMA_IMR_0_V1 0x30B8
+#define B_BE_PCIE_RX_RX1P1_IMR0_V1 BIT(23)
+#define B_BE_PCIE_RX_RX0P1_IMR0_V1 BIT(22)
+#define B_BE_PCIE_RX_ROQ1_IMR0_V1 BIT(21)
+#define B_BE_PCIE_RX_RPQ1_IMR0_V1 BIT(20)
+#define B_BE_PCIE_RX_RX1P2_IMR0_V1 BIT(19)
+#define B_BE_PCIE_RX_ROQ0_IMR0_V1 BIT(18)
+#define B_BE_PCIE_RX_RPQ0_IMR0_V1 BIT(17)
+#define B_BE_PCIE_RX_RX0P2_IMR0_V1 BIT(16)
+#define B_BE_PCIE_TX_CH14_IMR0 BIT(14)
+#define B_BE_PCIE_TX_CH13_IMR0 BIT(13)
+#define B_BE_PCIE_TX_CH12_IMR0 BIT(12)
+#define B_BE_PCIE_TX_CH11_IMR0 BIT(11)
+#define B_BE_PCIE_TX_CH10_IMR0 BIT(10)
+#define B_BE_PCIE_TX_CH9_IMR0 BIT(9)
+#define B_BE_PCIE_TX_CH8_IMR0 BIT(8)
+#define B_BE_PCIE_TX_CH7_IMR0 BIT(7)
+#define B_BE_PCIE_TX_CH6_IMR0 BIT(6)
+#define B_BE_PCIE_TX_CH5_IMR0 BIT(5)
+#define B_BE_PCIE_TX_CH4_IMR0 BIT(4)
+#define B_BE_PCIE_TX_CH3_IMR0 BIT(3)
+#define B_BE_PCIE_TX_CH2_IMR0 BIT(2)
+#define B_BE_PCIE_TX_CH1_IMR0 BIT(1)
+#define B_BE_PCIE_TX_CH0_IMR0 BIT(0)
+
+#define R_BE_PCIE_DMA_ISR 0x30BC
+#define B_BE_PCIE_RX_RX1P1_ISR_V1 BIT(23)
+#define B_BE_PCIE_RX_RX0P1_ISR_V1 BIT(22)
+#define B_BE_PCIE_RX_ROQ1_ISR_V1 BIT(21)
+#define B_BE_PCIE_RX_RPQ1_ISR_V1 BIT(20)
+#define B_BE_PCIE_RX_RX1P2_ISR_V1 BIT(19)
+#define B_BE_PCIE_RX_ROQ0_ISR_V1 BIT(18)
+#define B_BE_PCIE_RX_RPQ0_ISR_V1 BIT(17)
+#define B_BE_PCIE_RX_RX0P2_ISR_V1 BIT(16)
+#define B_BE_PCIE_TX_CH14_ISR BIT(14)
+#define B_BE_PCIE_TX_CH13_ISR BIT(13)
+#define B_BE_PCIE_TX_CH12_ISR BIT(12)
+#define B_BE_PCIE_TX_CH11_ISR BIT(11)
+#define B_BE_PCIE_TX_CH10_ISR BIT(10)
+#define B_BE_PCIE_TX_CH9_ISR BIT(9)
+#define B_BE_PCIE_TX_CH8_ISR BIT(8)
+#define B_BE_PCIE_TX_CH7_ISR BIT(7)
+#define B_BE_PCIE_TX_CH6_ISR BIT(6)
+#define B_BE_PCIE_TX_CH5_ISR BIT(5)
+#define B_BE_PCIE_TX_CH4_ISR BIT(4)
+#define B_BE_PCIE_TX_CH3_ISR BIT(3)
+#define B_BE_PCIE_TX_CH2_ISR BIT(2)
+#define B_BE_PCIE_TX_CH1_ISR BIT(1)
+#define B_BE_PCIE_TX_CH0_ISR BIT(0)
+
+#define R_BE_HAXI_HIMR00 0xB0B0
+#define B_BE_RDU_CH5_INT_IMR_V1 BIT(30)
+#define B_BE_RDU_CH4_INT_IMR_V1 BIT(29)
+#define B_BE_RDU_CH3_INT_IMR_V1 BIT(28)
+#define B_BE_RDU_CH2_INT_IMR_V1 BIT(27)
+#define B_BE_RDU_CH1_INT_IMR_V1 BIT(26)
+#define B_BE_RDU_CH0_INT_IMR_V1 BIT(25)
+#define B_BE_RXDMA_STUCK_INT_EN_V1 BIT(24)
+#define B_BE_TXDMA_STUCK_INT_EN_V1 BIT(23)
+#define B_BE_TXDMA_CH14_INT_EN_V1 BIT(22)
+#define B_BE_TXDMA_CH13_INT_EN_V1 BIT(21)
+#define B_BE_TXDMA_CH12_INT_EN_V1 BIT(20)
+#define B_BE_TXDMA_CH11_INT_EN_V1 BIT(19)
+#define B_BE_TXDMA_CH10_INT_EN_V1 BIT(18)
+#define B_BE_TXDMA_CH9_INT_EN_V1 BIT(17)
+#define B_BE_TXDMA_CH8_INT_EN_V1 BIT(16)
+#define B_BE_TXDMA_CH7_INT_EN_V1 BIT(15)
+#define B_BE_TXDMA_CH6_INT_EN_V1 BIT(14)
+#define B_BE_TXDMA_CH5_INT_EN_V1 BIT(13)
+#define B_BE_TXDMA_CH4_INT_EN_V1 BIT(12)
+#define B_BE_TXDMA_CH3_INT_EN_V1 BIT(11)
+#define B_BE_TXDMA_CH2_INT_EN_V1 BIT(10)
+#define B_BE_TXDMA_CH1_INT_EN_V1 BIT(9)
+#define B_BE_TXDMA_CH0_INT_EN_V1 BIT(8)
+#define B_BE_RX1P1DMA_INT_EN_V1 BIT(7)
+#define B_BE_RX0P1DMA_INT_EN_V1 BIT(6)
+#define B_BE_RO1DMA_INT_EN BIT(5)
+#define B_BE_RP1DMA_INT_EN BIT(4)
+#define B_BE_RX1DMA_INT_EN BIT(3)
+#define B_BE_RO0DMA_INT_EN BIT(2)
+#define B_BE_RP0DMA_INT_EN BIT(1)
+#define B_BE_RX0DMA_INT_EN BIT(0)
+
+#define R_BE_HAXI_HISR00 0xB0B4
+#define B_BE_RDU_CH6_INT BIT(28)
+#define B_BE_RDU_CH5_INT BIT(27)
+#define B_BE_RDU_CH4_INT BIT(26)
+#define B_BE_RDU_CH2_INT BIT(25)
+#define B_BE_RDU_CH1_INT BIT(24)
+#define B_BE_RDU_CH0_INT BIT(23)
+#define B_BE_RXDMA_STUCK_INT BIT(22)
+#define B_BE_TXDMA_STUCK_INT BIT(21)
+#define B_BE_TXDMA_CH14_INT BIT(20)
+#define B_BE_TXDMA_CH13_INT BIT(19)
+#define B_BE_TXDMA_CH12_INT BIT(18)
+#define B_BE_TXDMA_CH11_INT BIT(17)
+#define B_BE_TXDMA_CH10_INT BIT(16)
+#define B_BE_TXDMA_CH9_INT BIT(15)
+#define B_BE_TXDMA_CH8_INT BIT(14)
+#define B_BE_TXDMA_CH7_INT BIT(13)
+#define B_BE_TXDMA_CH6_INT BIT(12)
+#define B_BE_TXDMA_CH5_INT BIT(11)
+#define B_BE_TXDMA_CH4_INT BIT(10)
+#define B_BE_TXDMA_CH3_INT BIT(9)
+#define B_BE_TXDMA_CH2_INT BIT(8)
+#define B_BE_TXDMA_CH1_INT BIT(7)
+#define B_BE_TXDMA_CH0_INT BIT(6)
+#define B_BE_RPQ1DMA_INT BIT(5)
+#define B_BE_RX1P1DMA_INT BIT(4)
+#define B_BE_RX1DMA_INT BIT(3)
+#define B_BE_RPQ0DMA_INT BIT(2)
+#define B_BE_RX0P1DMA_INT BIT(1)
+#define B_BE_RX0DMA_INT BIT(0)
+
 /* TX/RX */
 #define R_AX_DRV_FW_HSK_0	0x01B0
 #define R_AX_DRV_FW_HSK_1	0x01B4
@@ -496,6 +693,105 @@
 #define B_AX_CH11_BUSY			BIT(1)
 #define B_AX_CH10_BUSY			BIT(0)
 
+#define R_BE_HAXI_DMA_STOP1 0xB010
+#define B_BE_STOP_WPDMA BIT(31)
+#define B_BE_STOP_CH14 BIT(14)
+#define B_BE_STOP_CH13 BIT(13)
+#define B_BE_STOP_CH12 BIT(12)
+#define B_BE_STOP_CH11 BIT(11)
+#define B_BE_STOP_CH10 BIT(10)
+#define B_BE_STOP_CH9 BIT(9)
+#define B_BE_STOP_CH8 BIT(8)
+#define B_BE_STOP_CH7 BIT(7)
+#define B_BE_STOP_CH6 BIT(6)
+#define B_BE_STOP_CH5 BIT(5)
+#define B_BE_STOP_CH4 BIT(4)
+#define B_BE_STOP_CH3 BIT(3)
+#define B_BE_STOP_CH2 BIT(2)
+#define B_BE_STOP_CH1 BIT(1)
+#define B_BE_STOP_CH0 BIT(0)
+#define B_BE_TX_STOP1_MASK (B_BE_STOP_CH0 | B_BE_STOP_CH1 | \
+			    B_BE_STOP_CH2 | B_BE_STOP_CH3 | \
+			    B_BE_STOP_CH4 | B_BE_STOP_CH5 | \
+			    B_BE_STOP_CH6 | B_BE_STOP_CH7 | \
+			    B_BE_STOP_CH8 | B_BE_STOP_CH9 | \
+			    B_BE_STOP_CH10 | B_BE_STOP_CH11 | \
+			    B_BE_STOP_CH12)
+
+#define R_BE_CH0_TXBD_NUM_V1 0xB030
+#define R_BE_CH1_TXBD_NUM_V1 0xB032
+#define R_BE_CH2_TXBD_NUM_V1 0xB034
+#define R_BE_CH3_TXBD_NUM_V1 0xB036
+#define R_BE_CH4_TXBD_NUM_V1 0xB038
+#define R_BE_CH5_TXBD_NUM_V1 0xB03A
+#define R_BE_CH6_TXBD_NUM_V1 0xB03C
+#define R_BE_CH7_TXBD_NUM_V1 0xB03E
+#define R_BE_CH8_TXBD_NUM_V1 0xB040
+#define R_BE_CH9_TXBD_NUM_V1 0xB042
+#define R_BE_CH10_TXBD_NUM_V1 0xB044
+#define R_BE_CH11_TXBD_NUM_V1 0xB046
+#define R_BE_CH12_TXBD_NUM_V1 0xB048
+#define R_BE_CH13_TXBD_NUM_V1 0xB04C
+#define R_BE_CH14_TXBD_NUM_V1 0xB04E
+
+#define R_BE_RXQ0_RXBD_NUM_V1 0xB050
+#define R_BE_RPQ0_RXBD_NUM_V1 0xB052
+
+#define R_BE_CH0_TXBD_IDX_V1 0xB100
+#define R_BE_CH1_TXBD_IDX_V1 0xB104
+#define R_BE_CH2_TXBD_IDX_V1 0xB108
+#define R_BE_CH3_TXBD_IDX_V1 0xB10C
+#define R_BE_CH4_TXBD_IDX_V1 0xB110
+#define R_BE_CH5_TXBD_IDX_V1 0xB114
+#define R_BE_CH6_TXBD_IDX_V1 0xB118
+#define R_BE_CH7_TXBD_IDX_V1 0xB11C
+#define R_BE_CH8_TXBD_IDX_V1 0xB120
+#define R_BE_CH9_TXBD_IDX_V1 0xB124
+#define R_BE_CH10_TXBD_IDX_V1 0xB128
+#define R_BE_CH11_TXBD_IDX_V1 0xB12C
+#define R_BE_CH12_TXBD_IDX_V1 0xB130
+#define R_BE_CH13_TXBD_IDX_V1 0xB134
+#define R_BE_CH14_TXBD_IDX_V1 0xB138
+
+#define R_BE_RXQ0_RXBD_IDX_V1 0xB160
+#define R_BE_RPQ0_RXBD_IDX_V1 0xB164
+
+#define R_BE_CH0_TXBD_DESA_L_V1 0xB200
+#define R_BE_CH0_TXBD_DESA_H_V1 0xB204
+#define R_BE_CH1_TXBD_DESA_L_V1 0xB208
+#define R_BE_CH1_TXBD_DESA_H_V1 0xB20C
+#define R_BE_CH2_TXBD_DESA_L_V1 0xB210
+#define R_BE_CH2_TXBD_DESA_H_V1 0xB214
+#define R_BE_CH3_TXBD_DESA_L_V1 0xB218
+#define R_BE_CH3_TXBD_DESA_H_V1 0xB21C
+#define R_BE_CH4_TXBD_DESA_L_V1 0xB220
+#define R_BE_CH4_TXBD_DESA_H_V1 0xB224
+#define R_BE_CH5_TXBD_DESA_L_V1 0xB228
+#define R_BE_CH5_TXBD_DESA_H_V1 0xB22C
+#define R_BE_CH6_TXBD_DESA_L_V1 0xB230
+#define R_BE_CH6_TXBD_DESA_H_V1 0xB234
+#define R_BE_CH7_TXBD_DESA_L_V1 0xB238
+#define R_BE_CH7_TXBD_DESA_H_V1 0xB23C
+#define R_BE_CH8_TXBD_DESA_L_V1 0xB240
+#define R_BE_CH8_TXBD_DESA_H_V1 0xB244
+#define R_BE_CH9_TXBD_DESA_L_V1 0xB248
+#define R_BE_CH9_TXBD_DESA_H_V1 0xB24C
+#define R_BE_CH10_TXBD_DESA_L_V1 0xB250
+#define R_BE_CH10_TXBD_DESA_H_V1 0xB254
+#define R_BE_CH11_TXBD_DESA_L_V1 0xB258
+#define R_BE_CH11_TXBD_DESA_H_V1 0xB25C
+#define R_BE_CH12_TXBD_DESA_L_V1 0xB260
+#define R_BE_CH12_TXBD_DESA_H_V1 0xB264
+#define R_BE_CH13_TXBD_DESA_L_V1 0xB268
+#define R_BE_CH13_TXBD_DESA_H_V1 0xB26C
+#define R_BE_CH14_TXBD_DESA_L_V1 0xB270
+#define R_BE_CH14_TXBD_DESA_H_V1 0xB274
+
+#define R_BE_RXQ0_RXBD_DESA_L_V1 0xB300
+#define R_BE_RXQ0_RXBD_DESA_H_V1 0xB304
+#define R_BE_RPQ0_RXBD_DESA_L_V1 0xB308
+#define R_BE_RPQ0_RXBD_DESA_H_V1 0xB30C
+
 /* Configure */
 #define R_AX_PCIE_INIT_CFG2		0x1004
 #define B_AX_WD_ITVL_IDLE		GENMASK(27, 24)
@@ -516,6 +812,15 @@
 #define B_AX_RXCOUNTER_MATCH_MASK	GENMASK(15, 8)
 #define B_AX_RXTIMER_MATCH_MASK		GENMASK(7, 0)
 
+#define R_AX_DBG_ERR_FLAG_V1 0x1104
+
+#define R_AX_INT_MIT_RX_V1 0x1184
+#define B_AX_RXMIT_RXP2_SEL_V1 BIT(19)
+#define B_AX_RXMIT_RXP1_SEL_V1 BIT(18)
+#define B_AX_MIT_RXTIMER_UNIT_MASK GENMASK(17, 16)
+#define B_AX_MIT_RXCOUNTER_MATCH_MASK GENMASK(15, 8)
+#define B_AX_MIT_RXTIMER_MATCH_MASK GENMASK(7, 0)
+
 #define R_AX_DBG_ERR_FLAG		0x11C4
 #define B_AX_PCIE_RPQ_FULL		BIT(29)
 #define B_AX_PCIE_RXQ_FULL		BIT(28)
@@ -554,6 +859,138 @@
 #define R_AX_PCIE_HRPWM_V1		0x30C0
 #define R_AX_PCIE_CRPWM			0x30C4
 
+#define R_AX_LBC_WATCHDOG_V1 0x30D8
+
+#define R_BE_PCIE_HRPWM 0x30C0
+#define R_BE_PCIE_CRPWM 0x30C4
+
+#define R_BE_L1_2_CTRL_HCILDO 0x3110
+#define B_BE_PCIE_DIS_L1_2_CTRL_HCILDO BIT(0)
+
+#define R_BE_PL1_DBG_INFO 0x3120
+#define B_BE_END_PL1_CNT_MASK GENMASK(23, 16)
+#define B_BE_START_PL1_CNT_MASK GENMASK(7, 0)
+
+#define R_BE_PCIE_MIT0_TMR 0x3330
+#define B_BE_PCIE_MIT0_RX_TMR_MASK GENMASK(5, 4)
+#define BE_MIT0_TMR_UNIT_1MS 0
+#define BE_MIT0_TMR_UNIT_2MS 1
+#define BE_MIT0_TMR_UNIT_4MS 2
+#define BE_MIT0_TMR_UNIT_8MS 3
+#define B_BE_PCIE_MIT0_TX_TMR_MASK GENMASK(1, 0)
+
+#define R_BE_PCIE_MIT0_CNT 0x3334
+#define B_BE_PCIE_RX_MIT0_CNT_MASK GENMASK(31, 24)
+#define B_BE_PCIE_TX_MIT0_CNT_MASK GENMASK(23, 16)
+#define B_BE_PCIE_RX_MIT0_TMR_CNT_MASK GENMASK(15, 8)
+#define B_BE_PCIE_TX_MIT0_TMR_CNT_MASK GENMASK(7, 0)
+
+#define R_BE_PCIE_MIT_CH_EN 0x3338
+#define B_BE_PCIE_MIT_RX1P1_EN BIT(23)
+#define B_BE_PCIE_MIT_RX0P1_EN BIT(22)
+#define B_BE_PCIE_MIT_ROQ1_EN BIT(21)
+#define B_BE_PCIE_MIT_RPQ1_EN BIT(20)
+#define B_BE_PCIE_MIT_RX1P2_EN BIT(19)
+#define B_BE_PCIE_MIT_ROQ0_EN BIT(18)
+#define B_BE_PCIE_MIT_RPQ0_EN BIT(17)
+#define B_BE_PCIE_MIT_RX0P2_EN BIT(16)
+#define B_BE_PCIE_MIT_TXCH14_EN BIT(14)
+#define B_BE_PCIE_MIT_TXCH13_EN BIT(13)
+#define B_BE_PCIE_MIT_TXCH12_EN BIT(12)
+#define B_BE_PCIE_MIT_TXCH11_EN BIT(11)
+#define B_BE_PCIE_MIT_TXCH10_EN BIT(10)
+#define B_BE_PCIE_MIT_TXCH9_EN BIT(9)
+#define B_BE_PCIE_MIT_TXCH8_EN BIT(8)
+#define B_BE_PCIE_MIT_TXCH7_EN BIT(7)
+#define B_BE_PCIE_MIT_TXCH6_EN BIT(6)
+#define B_BE_PCIE_MIT_TXCH5_EN BIT(5)
+#define B_BE_PCIE_MIT_TXCH4_EN BIT(4)
+#define B_BE_PCIE_MIT_TXCH3_EN BIT(3)
+#define B_BE_PCIE_MIT_TXCH2_EN BIT(2)
+#define B_BE_PCIE_MIT_TXCH1_EN BIT(1)
+#define B_BE_PCIE_MIT_TXCH0_EN BIT(0)
+
+#define R_BE_SER_PL1_CTRL 0x34A8
+#define B_BE_PL1_SER_PL1_EN BIT(31)
+#define B_BE_PL1_IGNORE_HOT_RST BIT(30)
+#define B_BE_PL1_TIMER_UNIT_MASK GENMASK(19, 17)
+#define B_BE_PL1_TIMER_CLEAR BIT(0)
+
+#define R_BE_REG_PL1_MASK 0x34B0
+#define B_BE_SER_PCLKREQ_ACK_MASK BIT(5)
+#define B_BE_SER_PM_CLK_MASK BIT(4)
+#define B_BE_SER_LTSSM_IMR BIT(3)
+#define B_BE_SER_PM_MASTER_IMR BIT(2)
+#define B_BE_SER_L1SUB_IMR BIT(1)
+#define B_BE_SER_PMU_IMR BIT(0)
+
+#define R_BE_RX_APPEND_MODE 0x8920
+#define B_BE_APPEND_OFFSET_MASK GENMASK(23, 16)
+#define B_BE_APPEND_LEN_MASK GENMASK(15, 0)
+
+#define R_BE_TXBD_RWPTR_CLR1 0xB014
+#define B_BE_CLR_CH14_IDX BIT(14)
+#define B_BE_CLR_CH13_IDX BIT(13)
+#define B_BE_CLR_CH12_IDX BIT(12)
+#define B_BE_CLR_CH11_IDX BIT(11)
+#define B_BE_CLR_CH10_IDX BIT(10)
+#define B_BE_CLR_CH9_IDX BIT(9)
+#define B_BE_CLR_CH8_IDX BIT(8)
+#define B_BE_CLR_CH7_IDX BIT(7)
+#define B_BE_CLR_CH6_IDX BIT(6)
+#define B_BE_CLR_CH5_IDX BIT(5)
+#define B_BE_CLR_CH4_IDX BIT(4)
+#define B_BE_CLR_CH3_IDX BIT(3)
+#define B_BE_CLR_CH2_IDX BIT(2)
+#define B_BE_CLR_CH1_IDX BIT(1)
+#define B_BE_CLR_CH0_IDX BIT(0)
+
+#define R_BE_RXBD_RWPTR_CLR1_V1 0xB018
+#define B_BE_CLR_ROQ1_IDX_V1 BIT(5)
+#define B_BE_CLR_RPQ1_IDX_V1 BIT(4)
+#define B_BE_CLR_RXQ1_IDX_V1 BIT(3)
+#define B_BE_CLR_ROQ0_IDX BIT(2)
+#define B_BE_CLR_RPQ0_IDX BIT(1)
+#define B_BE_CLR_RXQ0_IDX BIT(0)
+
+#define R_BE_HAXI_DMA_BUSY1 0xB01C
+#define B_BE_HAXI_MST_BUSY BIT(31)
+#define B_BE_HAXI_RX_IDLE BIT(25)
+#define B_BE_HAXI_TX_IDLE BIT(24)
+#define B_BE_ROQ1_BUSY_V1 BIT(21)
+#define B_BE_RPQ1_BUSY_V1 BIT(20)
+#define B_BE_RXQ1_BUSY_V1 BIT(19)
+#define B_BE_ROQ0_BUSY_V1 BIT(18)
+#define B_BE_RPQ0_BUSY_V1 BIT(17)
+#define B_BE_RXQ0_BUSY_V1 BIT(16)
+#define B_BE_WPDMA_BUSY BIT(15)
+#define B_BE_CH14_BUSY BIT(14)
+#define B_BE_CH13_BUSY BIT(13)
+#define B_BE_CH12_BUSY BIT(12)
+#define B_BE_CH11_BUSY BIT(11)
+#define B_BE_CH10_BUSY BIT(10)
+#define B_BE_CH9_BUSY BIT(9)
+#define B_BE_CH8_BUSY BIT(8)
+#define B_BE_CH7_BUSY BIT(7)
+#define B_BE_CH6_BUSY BIT(6)
+#define B_BE_CH5_BUSY BIT(5)
+#define B_BE_CH4_BUSY BIT(4)
+#define B_BE_CH3_BUSY BIT(3)
+#define B_BE_CH2_BUSY BIT(2)
+#define B_BE_CH1_BUSY BIT(1)
+#define B_BE_CH0_BUSY BIT(0)
+#define DMA_BUSY1_CHECK_BE (B_BE_CH0_BUSY | B_BE_CH1_BUSY | B_BE_CH2_BUSY | \
+			    B_BE_CH3_BUSY | B_BE_CH4_BUSY | B_BE_CH5_BUSY | \
+			    B_BE_CH6_BUSY | B_BE_CH7_BUSY | B_BE_CH8_BUSY | \
+			    B_BE_CH9_BUSY | B_BE_CH10_BUSY | B_BE_CH11_BUSY | \
+			    B_BE_CH12_BUSY | B_BE_CH13_BUSY | B_BE_CH14_BUSY)
+
+#define R_BE_HAXI_EXP_CTRL_V1 0xB020
+#define B_BE_R_NO_SEC_ACCESS BIT(31)
+#define B_BE_FORCE_EN_DMA_RX_GCLK BIT(5)
+#define B_BE_FORCE_EN_DMA_TX_GCLK BIT(4)
+#define B_BE_MAX_TAG_NUM_MASK GENMASK(3, 0)
+
 #define RTW89_PCI_TXBD_NUM_MAX		256
 #define RTW89_PCI_RXBD_NUM_MAX		256
 #define RTW89_PCI_TXWD_NUM_MAX		512
@@ -565,12 +1002,15 @@
 #define RTW89_PCI_MULTITAG		8
 
 /* PCIE CFG register */
+#define RTW89_PCIE_CAPABILITY_SPEED	0x7C
+#define RTW89_PCIE_SUPPORT_GEN_MASK	GENMASK(3, 0)
 #define RTW89_PCIE_L1_STS_V1		0x80
 #define RTW89_BCFG_LINK_SPEED_MASK	GENMASK(19, 16)
 #define RTW89_PCIE_GEN1_SPEED		0x01
 #define RTW89_PCIE_GEN2_SPEED		0x02
 #define RTW89_PCIE_PHY_RATE		0x82
 #define RTW89_PCIE_PHY_RATE_MASK	GENMASK(1, 0)
+#define RTW89_PCIE_LINK_CHANGE_SPEED	0xA0
 #define RTW89_PCIE_L1SS_STS_V1		0x0168
 #define RTW89_PCIE_BIT_ASPM_L11		BIT(3)
 #define RTW89_PCIE_BIT_ASPM_L12		BIT(2)
@@ -585,6 +1025,8 @@
 #define RTW89_PCIE_BIT_CLK		BIT(4)
 #define RTW89_PCIE_BIT_L1		BIT(3)
 #define RTW89_PCIE_CLK_CTRL		0x0725
+#define RTW89_PCIE_FTS			0x080C
+#define RTW89_PCIE_POLLING_BIT		BIT(17)
 #define RTW89_PCIE_RST_MSTATE		0x0B48
 #define RTW89_PCIE_BIT_CFG_RST_MSTATE	BIT(0)
 
@@ -757,7 +1199,26 @@ struct rtw89_pci_bd_ram {
 	u8 min_num;
 };
 
+struct rtw89_pci_gen_def {
+	u32 isr_rdu;
+	u32 isr_halt_c2h;
+	u32 isr_wdt_timeout;
+	struct rtw89_reg2_def isr_clear_rpq;
+	struct rtw89_reg2_def isr_clear_rxq;
+
+	int (*mac_pre_init)(struct rtw89_dev *rtwdev);
+	int (*mac_pre_deinit)(struct rtw89_dev *rtwdev);
+	int (*mac_post_init)(struct rtw89_dev *rtwdev);
+
+	void (*clr_idx_all)(struct rtw89_dev *rtwdev);
+	int (*rst_bdram)(struct rtw89_dev *rtwdev);
+
+	int (*lv1rst_stop_dma)(struct rtw89_dev *rtwdev);
+	int (*lv1rst_start_dma)(struct rtw89_dev *rtwdev);
+};
+
 struct rtw89_pci_info {
+	const struct rtw89_pci_gen_def *gen_def;
 	enum mac_ax_bd_trunc_mode txbd_trunc_mode;
 	enum mac_ax_bd_trunc_mode rxbd_trunc_mode;
 	enum mac_ax_rxbd_mode rxbd_mode;
@@ -772,6 +1233,7 @@ struct rtw89_pci_info {
 	enum mac_ax_pcie_func_ctrl autok_en;
 	enum mac_ax_pcie_func_ctrl io_rcy_en;
 	enum mac_ax_io_rcy_tmr io_rcy_tmr;
+	bool rx_ring_eq_is_full;
 
 	u32 init_cfg_reg;
 	u32 txhci_en_bit;
@@ -781,6 +1243,7 @@ struct rtw89_pci_info {
 	u32 max_tag_num_mask;
 	u32 rxbd_rwptr_clr_reg;
 	u32 txbd_rwptr_clr2_reg;
+	struct rtw89_reg_def dma_io_stop;
 	struct rtw89_reg_def dma_stop1;
 	struct rtw89_reg_def dma_stop2;
 	struct rtw89_reg_def dma_busy1;
@@ -789,6 +1252,7 @@ struct rtw89_pci_info {
 
 	u32 rpwm_addr;
 	u32 cpwm_addr;
+	u32 mit_addr;
 	u32 tx_dma_ch_mask;
 	const struct rtw89_pci_bd_idx_addr *bd_idx_addr_low_power;
 	const struct rtw89_pci_ch_dma_addr_set *dma_addr_set;
@@ -1059,33 +1523,45 @@ static inline bool rtw89_pci_ltr_is_err_reg_val(u32 val)
 extern const struct dev_pm_ops rtw89_pm_ops;
 extern const struct rtw89_pci_ch_dma_addr_set rtw89_pci_ch_dma_addr_set;
 extern const struct rtw89_pci_ch_dma_addr_set rtw89_pci_ch_dma_addr_set_v1;
+extern const struct rtw89_pci_ch_dma_addr_set rtw89_pci_ch_dma_addr_set_be;
 extern const struct rtw89_pci_bd_ram rtw89_bd_ram_table_dual[RTW89_TXCH_NUM];
 extern const struct rtw89_pci_bd_ram rtw89_bd_ram_table_single[RTW89_TXCH_NUM];
+extern const struct rtw89_pci_gen_def rtw89_pci_gen_ax;
+extern const struct rtw89_pci_gen_def rtw89_pci_gen_be;
 
 struct pci_device_id;
 
 int rtw89_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id);
 void rtw89_pci_remove(struct pci_dev *pdev);
+void rtw89_pci_ops_reset(struct rtw89_dev *rtwdev);
 int rtw89_pci_ltr_set(struct rtw89_dev *rtwdev, bool en);
 int rtw89_pci_ltr_set_v1(struct rtw89_dev *rtwdev, bool en);
+int rtw89_pci_ltr_set_v2(struct rtw89_dev *rtwdev, bool en);
 u32 rtw89_pci_fill_txaddr_info(struct rtw89_dev *rtwdev,
 			       void *txaddr_info_addr, u32 total_len,
 			       dma_addr_t dma, u8 *add_info_nr);
 u32 rtw89_pci_fill_txaddr_info_v1(struct rtw89_dev *rtwdev,
 				  void *txaddr_info_addr, u32 total_len,
 				  dma_addr_t dma, u8 *add_info_nr);
+void rtw89_pci_ctrl_dma_all(struct rtw89_dev *rtwdev, bool enable);
 void rtw89_pci_config_intr_mask(struct rtw89_dev *rtwdev);
 void rtw89_pci_config_intr_mask_v1(struct rtw89_dev *rtwdev);
+void rtw89_pci_config_intr_mask_v2(struct rtw89_dev *rtwdev);
 void rtw89_pci_enable_intr(struct rtw89_dev *rtwdev, struct rtw89_pci *rtwpci);
 void rtw89_pci_disable_intr(struct rtw89_dev *rtwdev, struct rtw89_pci *rtwpci);
 void rtw89_pci_enable_intr_v1(struct rtw89_dev *rtwdev, struct rtw89_pci *rtwpci);
 void rtw89_pci_disable_intr_v1(struct rtw89_dev *rtwdev, struct rtw89_pci *rtwpci);
+void rtw89_pci_enable_intr_v2(struct rtw89_dev *rtwdev, struct rtw89_pci *rtwpci);
+void rtw89_pci_disable_intr_v2(struct rtw89_dev *rtwdev, struct rtw89_pci *rtwpci);
 void rtw89_pci_recognize_intrs(struct rtw89_dev *rtwdev,
 			       struct rtw89_pci *rtwpci,
 			       struct rtw89_pci_isrs *isrs);
 void rtw89_pci_recognize_intrs_v1(struct rtw89_dev *rtwdev,
 				  struct rtw89_pci *rtwpci,
 				  struct rtw89_pci_isrs *isrs);
+void rtw89_pci_recognize_intrs_v2(struct rtw89_dev *rtwdev,
+				  struct rtw89_pci *rtwpci,
+				  struct rtw89_pci_isrs *isrs);
 
 static inline
 u32 rtw89_chip_fill_txaddr_info(struct rtw89_dev *rtwdev,
@@ -1157,4 +1633,47 @@ void rtw89_chip_recognize_intrs(struct rtw89_dev *rtwdev,
 	info->recognize_intrs(rtwdev, rtwpci, isrs);
 }
 
+static inline int rtw89_pci_ops_mac_pre_init(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_pci_info *info = rtwdev->pci_info;
+	const struct rtw89_pci_gen_def *gen_def = info->gen_def;
+
+	return gen_def->mac_pre_init(rtwdev);
+}
+
+static inline int rtw89_pci_ops_mac_pre_deinit(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_pci_info *info = rtwdev->pci_info;
+	const struct rtw89_pci_gen_def *gen_def = info->gen_def;
+
+	if (!gen_def->mac_pre_deinit)
+		return 0;
+
+	return gen_def->mac_pre_deinit(rtwdev);
+}
+
+static inline int rtw89_pci_ops_mac_post_init(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_pci_info *info = rtwdev->pci_info;
+	const struct rtw89_pci_gen_def *gen_def = info->gen_def;
+
+	return gen_def->mac_post_init(rtwdev);
+}
+
+static inline void rtw89_pci_clr_idx_all(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_pci_info *info = rtwdev->pci_info;
+	const struct rtw89_pci_gen_def *gen_def = info->gen_def;
+
+	gen_def->clr_idx_all(rtwdev);
+}
+
+static inline int rtw89_pci_reset_bdram(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_pci_info *info = rtwdev->pci_info;
+	const struct rtw89_pci_gen_def *gen_def = info->gen_def;
+
+	return gen_def->rst_bdram(rtwdev);
+}
+
 #endif
diff --git a/drivers/net/wireless/realtek/rtw89/pci_be.c b/drivers/net/wireless/realtek/rtw89/pci_be.c
new file mode 100644
index 000000000000..629ffa4bee91
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtw89/pci_be.c
@@ -0,0 +1,509 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/* Copyright(c) 2023  Realtek Corporation
+ */
+
+#include <linux/pci.h>
+
+#include "mac.h"
+#include "pci.h"
+#include "reg.h"
+
+enum pcie_rxbd_mode {
+	PCIE_RXBD_NORM = 0,
+	PCIE_RXBD_SEP,
+	PCIE_RXBD_EXT,
+};
+
+#define PL0_TMR_SCALE_ASIC 1
+#define PL0_TMR_ANA_172US 0x800
+#define PL0_TMR_MAC_1MS 0x27100
+#define PL0_TMR_AUX_1MS 0x1E848
+
+static void _patch_pcie_power_wake_be(struct rtw89_dev *rtwdev, bool power_up)
+{
+	if (power_up)
+		rtw89_write32_set(rtwdev, R_BE_HCI_OPT_CTRL, BIT_WAKE_CTRL_V1);
+	else
+		rtw89_write32_clr(rtwdev, R_BE_HCI_OPT_CTRL, BIT_WAKE_CTRL_V1);
+}
+
+static void rtw89_pci_set_io_rcy_be(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_pci_info *info = rtwdev->pci_info;
+	u32 scale = PL0_TMR_SCALE_ASIC;
+	u32 val32;
+
+	if (info->io_rcy_en == MAC_AX_PCIE_ENABLE) {
+		val32 = info->io_rcy_tmr == MAC_AX_IO_RCY_ANA_TMR_DEF ?
+			PL0_TMR_ANA_172US : info->io_rcy_tmr;
+		val32 /= scale;
+
+		rtw89_write32(rtwdev, R_BE_AON_WDT_TMR, val32);
+		rtw89_write32(rtwdev, R_BE_MDIO_WDT_TMR, val32);
+		rtw89_write32(rtwdev, R_BE_LA_MODE_WDT_TMR, val32);
+		rtw89_write32(rtwdev, R_BE_WDT_AR_TMR, val32);
+		rtw89_write32(rtwdev, R_BE_WDT_AW_TMR, val32);
+		rtw89_write32(rtwdev, R_BE_WDT_W_TMR, val32);
+		rtw89_write32(rtwdev, R_BE_WDT_B_TMR, val32);
+		rtw89_write32(rtwdev, R_BE_WDT_R_TMR, val32);
+
+		val32 = info->io_rcy_tmr == MAC_AX_IO_RCY_ANA_TMR_DEF ?
+			PL0_TMR_MAC_1MS : info->io_rcy_tmr;
+		val32 /= scale;
+		rtw89_write32(rtwdev, R_BE_WLAN_WDT_TMR, val32);
+		rtw89_write32(rtwdev, R_BE_AXIDMA_WDT_TMR, val32);
+
+		val32 = info->io_rcy_tmr == MAC_AX_IO_RCY_ANA_TMR_DEF ?
+			PL0_TMR_AUX_1MS : info->io_rcy_tmr;
+		val32 /= scale;
+		rtw89_write32(rtwdev, R_BE_LOCAL_WDT_TMR, val32);
+	} else {
+		rtw89_write32_clr(rtwdev, R_BE_WLAN_WDT, B_BE_WLAN_WDT_ENABLE);
+		rtw89_write32_clr(rtwdev, R_BE_AXIDMA_WDT, B_BE_AXIDMA_WDT_ENABLE);
+		rtw89_write32_clr(rtwdev, R_BE_AON_WDT, B_BE_AON_WDT_ENABLE);
+		rtw89_write32_clr(rtwdev, R_BE_LOCAL_WDT, B_BE_LOCAL_WDT_ENABLE);
+		rtw89_write32_clr(rtwdev, R_BE_MDIO_WDT, B_BE_MDIO_WDT_ENABLE);
+		rtw89_write32_clr(rtwdev, R_BE_LA_MODE_WDT, B_BE_LA_MODE_WDT_ENABLE);
+		rtw89_write32_clr(rtwdev, R_BE_WDT_AR, B_BE_WDT_AR_ENABLE);
+		rtw89_write32_clr(rtwdev, R_BE_WDT_AW, B_BE_WDT_AW_ENABLE);
+		rtw89_write32_clr(rtwdev, R_BE_WDT_W, B_BE_WDT_W_ENABLE);
+		rtw89_write32_clr(rtwdev, R_BE_WDT_B, B_BE_WDT_B_ENABLE);
+		rtw89_write32_clr(rtwdev, R_BE_WDT_R, B_BE_WDT_R_ENABLE);
+	}
+}
+
+static void rtw89_pci_ctrl_wpdma_pcie_be(struct rtw89_dev *rtwdev, bool en)
+{
+	if (en)
+		rtw89_write32_clr(rtwdev, R_BE_HAXI_DMA_STOP1, B_BE_STOP_WPDMA);
+	else
+		rtw89_write32_set(rtwdev, R_BE_HAXI_DMA_STOP1, B_BE_STOP_WPDMA);
+}
+
+static void rtw89_pci_ctrl_trxdma_pcie_be(struct rtw89_dev *rtwdev,
+					  enum mac_ax_pcie_func_ctrl tx_en,
+					  enum mac_ax_pcie_func_ctrl rx_en,
+					  enum mac_ax_pcie_func_ctrl io_en)
+{
+	u32 val;
+
+	val = rtw89_read32(rtwdev, R_BE_HAXI_INIT_CFG1);
+
+	if (tx_en == MAC_AX_PCIE_ENABLE)
+		val |= B_BE_TXDMA_EN;
+	else if (tx_en == MAC_AX_PCIE_DISABLE)
+		val &= ~B_BE_TXDMA_EN;
+
+	if (rx_en == MAC_AX_PCIE_ENABLE)
+		val |= B_BE_RXDMA_EN;
+	else if (rx_en == MAC_AX_PCIE_DISABLE)
+		val &= ~B_BE_RXDMA_EN;
+
+	if (io_en == MAC_AX_PCIE_ENABLE)
+		val &= ~B_BE_STOP_AXI_MST;
+	else if (io_en == MAC_AX_PCIE_DISABLE)
+		val |= B_BE_STOP_AXI_MST;
+
+	rtw89_write32(rtwdev, R_BE_HAXI_INIT_CFG1, val);
+}
+
+static void rtw89_pci_clr_idx_all_be(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_pci *rtwpci = (struct rtw89_pci *)rtwdev->priv;
+	struct rtw89_pci_rx_ring *rx_ring;
+	u32 val;
+
+	val = B_BE_CLR_CH0_IDX | B_BE_CLR_CH1_IDX | B_BE_CLR_CH2_IDX |
+	      B_BE_CLR_CH3_IDX | B_BE_CLR_CH4_IDX | B_BE_CLR_CH5_IDX |
+	      B_BE_CLR_CH6_IDX | B_BE_CLR_CH7_IDX | B_BE_CLR_CH8_IDX |
+	      B_BE_CLR_CH9_IDX | B_BE_CLR_CH10_IDX | B_BE_CLR_CH11_IDX |
+	      B_BE_CLR_CH12_IDX | B_BE_CLR_CH13_IDX | B_BE_CLR_CH14_IDX;
+	rtw89_write32(rtwdev, R_BE_TXBD_RWPTR_CLR1, val);
+
+	rtw89_write32(rtwdev, R_BE_RXBD_RWPTR_CLR1_V1,
+		      B_BE_CLR_RXQ0_IDX | B_BE_CLR_RPQ0_IDX);
+
+	rx_ring = &rtwpci->rx_rings[RTW89_RXCH_RXQ];
+	rtw89_write16(rtwdev, R_BE_RXQ0_RXBD_IDX_V1, rx_ring->bd_ring.len - 1);
+
+	rx_ring = &rtwpci->rx_rings[RTW89_RXCH_RPQ];
+	rtw89_write16(rtwdev, R_BE_RPQ0_RXBD_IDX_V1, rx_ring->bd_ring.len - 1);
+}
+
+static int rtw89_pci_poll_txdma_ch_idle_be(struct rtw89_dev *rtwdev)
+{
+	u32 val;
+
+	return read_poll_timeout(rtw89_read32, val, (val & DMA_BUSY1_CHECK_BE) == 0,
+				 10, 1000, false, rtwdev, R_BE_HAXI_DMA_BUSY1);
+}
+
+static int rtw89_pci_poll_rxdma_ch_idle_be(struct rtw89_dev *rtwdev)
+{
+	u32 check;
+	u32 val;
+
+	check = B_BE_RXQ0_BUSY_V1 | B_BE_RPQ0_BUSY_V1;
+
+	return read_poll_timeout(rtw89_read32, val, (val & check) == 0,
+				 10, 1000, false, rtwdev, R_BE_HAXI_DMA_BUSY1);
+}
+
+static int rtw89_pci_poll_dma_all_idle_be(struct rtw89_dev *rtwdev)
+{
+	int ret;
+
+	ret = rtw89_pci_poll_txdma_ch_idle_be(rtwdev);
+	if (ret) {
+		rtw89_err(rtwdev, "txdma ch busy\n");
+		return ret;
+	}
+
+	ret = rtw89_pci_poll_rxdma_ch_idle_be(rtwdev);
+	if (ret) {
+		rtw89_err(rtwdev, "rxdma ch busy\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static void rtw89_pci_mode_op_be(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_pci_info *info = rtwdev->pci_info;
+	u32 val32_init1, val32_rxapp, val32_exp;
+
+	val32_init1 = rtw89_read32(rtwdev, R_BE_HAXI_INIT_CFG1);
+	val32_rxapp = rtw89_read32(rtwdev, R_BE_RX_APPEND_MODE);
+	val32_exp = rtw89_read32(rtwdev, R_BE_HAXI_EXP_CTRL_V1);
+
+	if (info->rxbd_mode == MAC_AX_RXBD_PKT) {
+		val32_init1 = u32_replace_bits(val32_init1, PCIE_RXBD_NORM,
+					       B_BE_RXQ_RXBD_MODE_MASK);
+	} else if (info->rxbd_mode == MAC_AX_RXBD_SEP) {
+		val32_init1 = u32_replace_bits(val32_init1, PCIE_RXBD_SEP,
+					       B_BE_RXQ_RXBD_MODE_MASK);
+		val32_rxapp = u32_replace_bits(val32_rxapp, 0,
+					       B_BE_APPEND_LEN_MASK);
+	}
+
+	val32_init1 = u32_replace_bits(val32_init1, info->tx_burst,
+				       B_BE_MAX_TXDMA_MASK);
+	val32_init1 = u32_replace_bits(val32_init1, info->rx_burst,
+				       B_BE_MAX_RXDMA_MASK);
+	val32_exp = u32_replace_bits(val32_exp, info->multi_tag_num,
+				     B_BE_MAX_TAG_NUM_MASK);
+	val32_init1 = u32_replace_bits(val32_init1, info->wd_dma_idle_intvl,
+				       B_BE_CFG_WD_PERIOD_IDLE_MASK);
+	val32_init1 = u32_replace_bits(val32_init1, info->wd_dma_act_intvl,
+				       B_BE_CFG_WD_PERIOD_ACTIVE_MASK);
+
+	rtw89_write32(rtwdev, R_BE_HAXI_INIT_CFG1, val32_init1);
+	rtw89_write32(rtwdev, R_BE_RX_APPEND_MODE, val32_rxapp);
+	rtw89_write32(rtwdev, R_BE_HAXI_EXP_CTRL_V1, val32_exp);
+}
+
+static int rtw89_pci_rst_bdram_be(struct rtw89_dev *rtwdev)
+{
+	u32 val;
+
+	rtw89_write32_set(rtwdev, R_BE_HAXI_INIT_CFG1, B_BE_SET_BDRAM_BOUND);
+
+	return read_poll_timeout(rtw89_read32, val, !(val & B_BE_SET_BDRAM_BOUND),
+				 50, 500000, false, rtwdev, R_BE_HAXI_INIT_CFG1);
+}
+
+static void rtw89_pci_debounce_be(struct rtw89_dev *rtwdev)
+{
+	u32 val32;
+
+	val32 = rtw89_read32(rtwdev, R_BE_SYS_PAGE_CLK_GATED);
+	val32 = u32_replace_bits(val32, 0, B_BE_PCIE_PRST_DEBUNC_PERIOD_MASK);
+	val32 |= B_BE_SYM_PRST_DEBUNC_SEL;
+	rtw89_write32(rtwdev, R_BE_SYS_PAGE_CLK_GATED, val32);
+}
+
+static void rtw89_pci_ldo_low_pwr_be(struct rtw89_dev *rtwdev)
+{
+	rtw89_write32_set(rtwdev, R_BE_SYS_PW_CTRL, B_BE_PSUS_OFF_CAPC_EN);
+	rtw89_write32_set(rtwdev, R_BE_SYS_PAGE_CLK_GATED,
+			  B_BE_SOP_OFFPOOBS_PC | B_BE_CPHY_AUXCLK_OP |
+			  B_BE_CPHY_POWER_READY_CHK);
+	rtw89_write32_clr(rtwdev, R_BE_SYS_SDIO_CTRL, B_BE_PCIE_FORCE_IBX_EN |
+						      B_BE_PCIE_DIS_L2_RTK_PERST |
+						      B_BE_PCIE_DIS_L2__CTRL_LDO_HCI);
+	rtw89_write32_clr(rtwdev, R_BE_L1_2_CTRL_HCILDO, B_BE_PCIE_DIS_L1_2_CTRL_HCILDO);
+}
+
+static void rtw89_pci_pcie_setting_be(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	struct rtw89_hal *hal = &rtwdev->hal;
+
+	rtw89_write32_set(rtwdev, R_BE_PCIE_FRZ_CLK, B_BE_PCIE_EN_AUX_CLK);
+	rtw89_write32_clr(rtwdev, R_BE_PCIE_PS_CTRL, B_BE_CMAC_EXIT_L1_EN);
+
+	if (chip->chip_id == RTL8922A && hal->cv == CHIP_CAV)
+		return;
+
+	rtw89_write32_set(rtwdev, R_BE_EFUSE_CTRL_2_V1, B_BE_R_SYM_AUTOLOAD_WITH_PMC_SEL);
+	rtw89_write32_set(rtwdev, R_BE_PCIE_LAT_CTRL, B_BE_SYM_AUX_CLK_SEL);
+}
+
+static void rtw89_pci_ser_setting_be(struct rtw89_dev *rtwdev)
+{
+	u32 val32;
+
+	rtw89_write32(rtwdev, R_BE_PL1_DBG_INFO, 0x0);
+	rtw89_write32_set(rtwdev, R_BE_FWS1IMR, B_BE_PCIE_SER_TIMEOUT_INDIC_EN);
+	rtw89_write32_set(rtwdev, R_BE_SER_PL1_CTRL, B_BE_PL1_SER_PL1_EN);
+
+	val32 = rtw89_read32(rtwdev, R_BE_REG_PL1_MASK);
+	val32 |= B_BE_SER_PMU_IMR | B_BE_SER_L1SUB_IMR | B_BE_SER_PM_MASTER_IMR |
+		 B_BE_SER_LTSSM_IMR | B_BE_SER_PM_CLK_MASK | B_BE_SER_PCLKREQ_ACK_MASK;
+	rtw89_write32(rtwdev, R_BE_REG_PL1_MASK, val32);
+}
+
+static void rtw89_pci_ctrl_txdma_ch_be(struct rtw89_dev *rtwdev, bool all_en,
+				       bool h2c_en)
+{
+	u32 mask_all;
+	u32 val;
+
+	mask_all = B_BE_STOP_CH0 | B_BE_STOP_CH1 | B_BE_STOP_CH2 |
+		   B_BE_STOP_CH3 | B_BE_STOP_CH4 | B_BE_STOP_CH5 |
+		   B_BE_STOP_CH6 | B_BE_STOP_CH7 | B_BE_STOP_CH8 |
+		   B_BE_STOP_CH9 | B_BE_STOP_CH10 | B_BE_STOP_CH11;
+
+	val = rtw89_read32(rtwdev, R_BE_HAXI_DMA_STOP1);
+	val |= B_BE_STOP_CH13 | B_BE_STOP_CH14;
+
+	if (all_en)
+		val &= ~mask_all;
+	else
+		val |= mask_all;
+
+	if (h2c_en)
+		val &= ~B_BE_STOP_CH12;
+	else
+		val |= B_BE_STOP_CH12;
+
+	rtw89_write32(rtwdev, R_BE_HAXI_DMA_STOP1, val);
+}
+
+static int rtw89_pci_ops_mac_pre_init_be(struct rtw89_dev *rtwdev)
+{
+	int ret;
+
+	rtw89_pci_set_io_rcy_be(rtwdev);
+	_patch_pcie_power_wake_be(rtwdev, true);
+	rtw89_pci_ctrl_wpdma_pcie_be(rtwdev, false);
+	rtw89_pci_ctrl_trxdma_pcie_be(rtwdev, MAC_AX_PCIE_DISABLE,
+				      MAC_AX_PCIE_DISABLE, MAC_AX_PCIE_DISABLE);
+	rtw89_pci_clr_idx_all_be(rtwdev);
+
+	ret = rtw89_pci_poll_dma_all_idle_be(rtwdev);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR] poll pcie dma all idle\n");
+		return ret;
+	}
+
+	rtw89_pci_mode_op_be(rtwdev);
+	rtw89_pci_ops_reset(rtwdev);
+
+	ret = rtw89_pci_rst_bdram_be(rtwdev);
+	if (ret) {
+		rtw89_err(rtwdev, "[ERR]pcie rst bdram\n");
+		return ret;
+	}
+
+	rtw89_pci_debounce_be(rtwdev);
+	rtw89_pci_ldo_low_pwr_be(rtwdev);
+	rtw89_pci_pcie_setting_be(rtwdev);
+	rtw89_pci_ser_setting_be(rtwdev);
+
+	rtw89_pci_ctrl_txdma_ch_be(rtwdev, false, true);
+	rtw89_pci_ctrl_trxdma_pcie_be(rtwdev, MAC_AX_PCIE_ENABLE,
+				      MAC_AX_PCIE_ENABLE, MAC_AX_PCIE_ENABLE);
+
+	return 0;
+}
+
+static int rtw89_pci_ops_mac_pre_deinit_be(struct rtw89_dev *rtwdev)
+{
+	u32 val;
+
+	_patch_pcie_power_wake_be(rtwdev, false);
+
+	val = rtw89_read32_mask(rtwdev, R_BE_IC_PWR_STATE, B_BE_WLMAC_PWR_STE_MASK);
+	if (val == 0)
+		return 0;
+
+	rtw89_pci_ctrl_trxdma_pcie_be(rtwdev, MAC_AX_PCIE_DISABLE,
+				      MAC_AX_PCIE_DISABLE, MAC_AX_PCIE_DISABLE);
+	rtw89_pci_clr_idx_all_be(rtwdev);
+
+	return 0;
+}
+
+int rtw89_pci_ltr_set_v2(struct rtw89_dev *rtwdev, bool en)
+{
+	u32 ctrl0, cfg0, cfg1, dec_ctrl, idle_ltcy, act_ltcy, dis_ltcy;
+
+	ctrl0 = rtw89_read32(rtwdev, R_BE_LTR_CTRL_0);
+	if (rtw89_pci_ltr_is_err_reg_val(ctrl0))
+		return -EINVAL;
+	cfg0 = rtw89_read32(rtwdev, R_BE_LTR_CFG_0);
+	if (rtw89_pci_ltr_is_err_reg_val(cfg0))
+		return -EINVAL;
+	cfg1 = rtw89_read32(rtwdev, R_BE_LTR_CFG_1);
+	if (rtw89_pci_ltr_is_err_reg_val(cfg1))
+		return -EINVAL;
+	dec_ctrl = rtw89_read32(rtwdev, R_BE_LTR_DECISION_CTRL_V1);
+	if (rtw89_pci_ltr_is_err_reg_val(dec_ctrl))
+		return -EINVAL;
+	idle_ltcy = rtw89_read32(rtwdev, R_BE_LTR_LATENCY_IDX3_V1);
+	if (rtw89_pci_ltr_is_err_reg_val(idle_ltcy))
+		return -EINVAL;
+	act_ltcy = rtw89_read32(rtwdev, R_BE_LTR_LATENCY_IDX1_V1);
+	if (rtw89_pci_ltr_is_err_reg_val(act_ltcy))
+		return -EINVAL;
+	dis_ltcy = rtw89_read32(rtwdev, R_BE_LTR_LATENCY_IDX0_V1);
+	if (rtw89_pci_ltr_is_err_reg_val(dis_ltcy))
+		return -EINVAL;
+
+	if (en) {
+		dec_ctrl |= B_BE_ENABLE_LTR_CTL_DECISION | B_BE_LTR_HW_DEC_EN_V1;
+		ctrl0 |= B_BE_LTR_HW_EN;
+	} else {
+		dec_ctrl &= ~(B_BE_ENABLE_LTR_CTL_DECISION | B_BE_LTR_HW_DEC_EN_V1 |
+			      B_BE_LTR_EN_PORT_V1_MASK);
+		ctrl0 &= ~B_BE_LTR_HW_EN;
+	}
+
+	dec_ctrl = u32_replace_bits(dec_ctrl, PCI_LTR_SPC_500US,
+				    B_BE_LTR_SPACE_IDX_MASK);
+	cfg0 = u32_replace_bits(cfg0, PCI_LTR_IDLE_TIMER_3_2MS,
+				B_BE_LTR_IDLE_TIMER_IDX_MASK);
+	cfg1 = u32_replace_bits(cfg1, 0xC0, B_BE_LTR_CMAC0_RX_USE_PG_TH_MASK);
+	cfg1 = u32_replace_bits(cfg1, 0xC0, B_BE_LTR_CMAC1_RX_USE_PG_TH_MASK);
+	cfg0 = u32_replace_bits(cfg0, 1, B_BE_LTR_IDX_ACTIVE_MASK);
+	cfg0 = u32_replace_bits(cfg0, 3, B_BE_LTR_IDX_IDLE_MASK);
+	dec_ctrl = u32_replace_bits(dec_ctrl, 0, B_BE_LTR_IDX_DISABLE_V1_MASK);
+
+	rtw89_write32(rtwdev, R_BE_LTR_LATENCY_IDX3_V1, 0x90039003);
+	rtw89_write32(rtwdev, R_BE_LTR_LATENCY_IDX1_V1, 0x880b880b);
+	rtw89_write32(rtwdev, R_BE_LTR_LATENCY_IDX0_V1, 0);
+	rtw89_write32(rtwdev, R_BE_LTR_DECISION_CTRL_V1, dec_ctrl);
+	rtw89_write32(rtwdev, R_BE_LTR_CFG_0, cfg0);
+	rtw89_write32(rtwdev, R_BE_LTR_CFG_1, cfg1);
+	rtw89_write32(rtwdev, R_BE_LTR_CTRL_0, ctrl0);
+
+	return 0;
+}
+EXPORT_SYMBOL(rtw89_pci_ltr_set_v2);
+
+static void rtw89_pci_configure_mit_be(struct rtw89_dev *rtwdev)
+{
+	u32 cnt;
+	u32 val;
+
+	rtw89_write32_mask(rtwdev, R_BE_PCIE_MIT0_TMR,
+			   B_BE_PCIE_MIT0_RX_TMR_MASK, BE_MIT0_TMR_UNIT_1MS);
+
+	val = rtw89_read32(rtwdev, R_BE_PCIE_MIT0_CNT);
+	cnt = min_t(u32, U8_MAX, RTW89_PCI_RXBD_NUM_MAX / 2);
+	val = u32_replace_bits(val, cnt, B_BE_PCIE_RX_MIT0_CNT_MASK);
+	val = u32_replace_bits(val, 2, B_BE_PCIE_RX_MIT0_TMR_CNT_MASK);
+	rtw89_write32(rtwdev, R_BE_PCIE_MIT0_CNT, val);
+}
+
+static int rtw89_pci_ops_mac_post_init_be(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_pci_info *info = rtwdev->pci_info;
+	int ret;
+
+	ret = info->ltr_set(rtwdev, true);
+	if (ret) {
+		rtw89_err(rtwdev, "pci ltr set fail\n");
+		return ret;
+	}
+
+	rtw89_pci_ctrl_trxdma_pcie_be(rtwdev, MAC_AX_PCIE_IGNORE,
+				      MAC_AX_PCIE_IGNORE, MAC_AX_PCIE_ENABLE);
+	rtw89_pci_ctrl_wpdma_pcie_be(rtwdev, true);
+	rtw89_pci_ctrl_txdma_ch_be(rtwdev, true, true);
+	rtw89_pci_configure_mit_be(rtwdev);
+
+	return 0;
+}
+
+static int rtw89_pci_poll_io_idle_be(struct rtw89_dev *rtwdev)
+{
+	u32 sts;
+	int ret;
+
+	ret = read_poll_timeout_atomic(rtw89_read32, sts,
+				       !(sts & B_BE_HAXI_MST_BUSY),
+				       10, 1000, false, rtwdev,
+				       R_BE_HAXI_DMA_BUSY1);
+	if (ret) {
+		rtw89_err(rtwdev, "pci dmach busy1 0x%X\n", sts);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int rtw89_pci_lv1rst_stop_dma_be(struct rtw89_dev *rtwdev)
+{
+	int ret;
+
+	rtw89_pci_ctrl_dma_all(rtwdev, false);
+	ret = rtw89_pci_poll_io_idle_be(rtwdev);
+	if (!ret)
+		return 0;
+
+	rtw89_debug(rtwdev, RTW89_DBG_HCI,
+		    "[PCIe] poll_io_idle fail; reset hci dma trx\n");
+
+	rtw89_mac_ctrl_hci_dma_trx(rtwdev, false);
+	rtw89_mac_ctrl_hci_dma_trx(rtwdev, true);
+
+	return rtw89_pci_poll_io_idle_be(rtwdev);
+}
+
+static int rtw89_pci_lv1rst_start_dma_be(struct rtw89_dev *rtwdev)
+{
+	int ret;
+
+	rtw89_mac_ctrl_hci_dma_trx(rtwdev, false);
+	rtw89_mac_ctrl_hci_dma_trx(rtwdev, true);
+	rtw89_pci_clr_idx_all(rtwdev);
+
+	ret = rtw89_pci_rst_bdram_be(rtwdev);
+	if (ret)
+		return ret;
+
+	rtw89_pci_ctrl_dma_all(rtwdev, true);
+	return 0;
+}
+
+const struct rtw89_pci_gen_def rtw89_pci_gen_be = {
+	.isr_rdu = B_BE_RDU_CH1_INT | B_BE_RDU_CH0_INT,
+	.isr_halt_c2h = B_BE_HALT_C2H_INT,
+	.isr_wdt_timeout = B_BE_WDT_TIMEOUT_INT,
+	.isr_clear_rpq = {R_BE_PCIE_DMA_ISR, B_BE_PCIE_RX_RPQ0_ISR_V1},
+	.isr_clear_rxq = {R_BE_PCIE_DMA_ISR, B_BE_PCIE_RX_RX0P2_ISR_V1},
+
+	.mac_pre_init = rtw89_pci_ops_mac_pre_init_be,
+	.mac_pre_deinit = rtw89_pci_ops_mac_pre_deinit_be,
+	.mac_post_init = rtw89_pci_ops_mac_post_init_be,
+
+	.clr_idx_all = rtw89_pci_clr_idx_all_be,
+	.rst_bdram = rtw89_pci_rst_bdram_be,
+
+	.lv1rst_stop_dma = rtw89_pci_lv1rst_stop_dma_be,
+	.lv1rst_start_dma = rtw89_pci_lv1rst_start_dma_be,
+};
+EXPORT_SYMBOL(rtw89_pci_gen_be);
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index 17ccc9efed28..bafc7b1cc104 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -2445,6 +2445,298 @@ void (* const rtw89_phy_c2h_ra_handler[])(struct rtw89_dev *rtwdev,
 	[RTW89_PHY_C2H_FUNC_TXSTS] = NULL,
 };
 
+static void rtw89_phy_c2h_rfk_rpt_log(struct rtw89_dev *rtwdev,
+				      enum rtw89_phy_c2h_rfk_log_func func,
+				      void *content, u16 len)
+{
+	struct rtw89_c2h_rf_txgapk_rpt_log *txgapk;
+	struct rtw89_c2h_rf_rxdck_rpt_log *rxdck;
+	struct rtw89_c2h_rf_dack_rpt_log *dack;
+	struct rtw89_c2h_rf_dpk_rpt_log *dpk;
+
+	switch (func) {
+	case RTW89_PHY_C2H_RFK_LOG_FUNC_DPK:
+		if (len != sizeof(*dpk))
+			goto out;
+
+		dpk = content;
+		rtw89_debug(rtwdev, RTW89_DBG_RFK,
+			    "DPK ver:%d idx:%2ph band:%2ph bw:%2ph ch:%2ph path:%2ph\n",
+			    dpk->ver, dpk->idx, dpk->band, dpk->bw, dpk->ch, dpk->path_ok);
+		rtw89_debug(rtwdev, RTW89_DBG_RFK,
+			    "DPK txagc:%2ph ther:%2ph gs:%2ph dc_i:%4ph dc_q:%4ph\n",
+			    dpk->txagc, dpk->ther, dpk->gs, dpk->dc_i, dpk->dc_q);
+		rtw89_debug(rtwdev, RTW89_DBG_RFK,
+			    "DPK corr_v:%2ph corr_i:%2ph to:%2ph ov:%2ph\n",
+			    dpk->corr_val, dpk->corr_idx, dpk->is_timeout, dpk->rxbb_ov);
+		return;
+	case RTW89_PHY_C2H_RFK_LOG_FUNC_DACK:
+		if (len != sizeof(*dack))
+			goto out;
+
+		dack = content;
+
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]ver=0x%x 0x%x\n",
+			    dack->fwdack_ver, dack->fwdack_rpt_ver);
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]S0 CDACK ic = [0x%x, 0x%x]\n",
+			    dack->cdack_d[0][0][0], dack->cdack_d[0][0][1]);
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]S0 CDACK qc = [0x%x, 0x%x]\n",
+			    dack->cdack_d[0][1][0], dack->cdack_d[0][1][1]);
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]S1 CDACK ic = [0x%x, 0x%x]\n",
+			    dack->cdack_d[1][0][0], dack->cdack_d[1][0][1]);
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]S1 CDACK qc = [0x%x, 0x%x]\n",
+			    dack->cdack_d[1][1][0], dack->cdack_d[1][1][1]);
+
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]S0 ADC_DCK ic = [0x%x, 0x%x]\n",
+			    dack->addck2_d[0][0][0], dack->addck2_d[0][0][1]);
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]S0 ADC_DCK qc = [0x%x, 0x%x]\n",
+			    dack->addck2_d[0][1][0], dack->addck2_d[0][1][1]);
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]S1 ADC_DCK ic = [0x%x, 0x%x]\n",
+			    dack->addck2_d[1][0][0], dack->addck2_d[1][0][1]);
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]S1 ADC_DCK qc = [0x%x, 0x%x]\n",
+			    dack->addck2_d[1][1][0], dack->addck2_d[1][1][1]);
+
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]S0 ADC_GAINK ic = 0x%x, qc = 0x%x\n",
+			    dack->adgaink_d[0][0], dack->adgaink_d[0][1]);
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]S1 ADC_GAINK ic = 0x%x, qc = 0x%x\n",
+			    dack->adgaink_d[1][0], dack->adgaink_d[1][1]);
+
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]S0 DAC_DCK ic = 0x%x, qc = 0x%x\n",
+			    dack->dadck_d[0][0], dack->dadck_d[0][1]);
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]S1 DAC_DCK ic = 0x%x, qc = 0x%x\n",
+			    dack->dadck_d[1][0], dack->dadck_d[1][1]);
+
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]S0 biask iqc = 0x%x\n",
+			    dack->biask_d[0][0]);
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]S1 biask iqc = 0x%x\n",
+			    dack->biask_d[1][0]);
+
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]S0 MSBK ic: %*ph\n",
+			    (int)sizeof(dack->msbk_d[0][0]), dack->msbk_d[0][0]);
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]S0 MSBK qc: %*ph\n",
+			    (int)sizeof(dack->msbk_d[0][1]), dack->msbk_d[0][1]);
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]S1 MSBK ic: %*ph\n",
+			    (int)sizeof(dack->msbk_d[1][0]), dack->msbk_d[1][0]);
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]S1 MSBK qc: %*ph\n",
+			    (int)sizeof(dack->msbk_d[1][1]), dack->msbk_d[1][1]);
+		return;
+	case RTW89_PHY_C2H_RFK_LOG_FUNC_RXDCK:
+		if (len != sizeof(*rxdck))
+			goto out;
+
+		rxdck = content;
+		rtw89_debug(rtwdev, RTW89_DBG_RFK,
+			    "RXDCK ver:%d band:%2ph bw:%2ph ch:%2ph to:%2ph\n",
+			    rxdck->ver, rxdck->band, rxdck->bw, rxdck->ch,
+			    rxdck->timeout);
+		return;
+	case RTW89_PHY_C2H_RFK_LOG_FUNC_TXGAPK:
+		if (len != sizeof(*txgapk))
+			goto out;
+
+		txgapk = content;
+		rtw89_debug(rtwdev, RTW89_DBG_RFK,
+			    "[TXGAPK]rpt r0x8010[0]=0x%x, r0x8010[1]=0x%x\n",
+			    le32_to_cpu(txgapk->r0x8010[0]),
+			    le32_to_cpu(txgapk->r0x8010[1]));
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[TXGAPK]rpt chk_id = %d\n",
+			    txgapk->chk_id);
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[TXGAPK]rpt chk_cnt = %d\n",
+			    le32_to_cpu(txgapk->chk_cnt));
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[TXGAPK]rpt ver = 0x%x\n",
+			    txgapk->ver);
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[TXGAPK]rpt rsv1 = %d\n",
+			    txgapk->rsv1);
+
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[TXGAPK]rpt track_d[0] = %*ph\n",
+			    (int)sizeof(txgapk->track_d[0]), txgapk->track_d[0]);
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[TXGAPK]rpt power_d[0] = %*ph\n",
+			    (int)sizeof(txgapk->power_d[0]), txgapk->power_d[0]);
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[TXGAPK]rpt track_d[1] = %*ph\n",
+			    (int)sizeof(txgapk->track_d[1]), txgapk->track_d[1]);
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[TXGAPK]rpt power_d[1] = %*ph\n",
+			    (int)sizeof(txgapk->power_d[1]), txgapk->power_d[1]);
+		return;
+	default:
+		break;
+	}
+
+out:
+	rtw89_debug(rtwdev, RTW89_DBG_RFK,
+		    "unexpected RFK func %d report log with length %d\n", func, len);
+}
+
+static bool rtw89_phy_c2h_rfk_run_log(struct rtw89_dev *rtwdev,
+				      enum rtw89_phy_c2h_rfk_log_func func,
+				      void *content, u16 len)
+{
+	struct rtw89_fw_elm_info *elm_info = &rtwdev->fw.elm_info;
+	const struct rtw89_c2h_rf_run_log *log = content;
+	const struct rtw89_fw_element_hdr *elm;
+	u32 fmt_idx;
+	u16 offset;
+
+	if (sizeof(*log) != len)
+		return false;
+
+	if (!elm_info->rfk_log_fmt)
+		return false;
+
+	elm = elm_info->rfk_log_fmt->elm[func];
+	fmt_idx = le32_to_cpu(log->fmt_idx);
+	if (!elm || fmt_idx >= elm->u.rfk_log_fmt.nr)
+		return false;
+
+	offset = le16_to_cpu(elm->u.rfk_log_fmt.offset[fmt_idx]);
+	if (offset == 0)
+		return false;
+
+	rtw89_debug(rtwdev, RTW89_DBG_RFK, &elm->u.common.contents[offset],
+		    le32_to_cpu(log->arg[0]), le32_to_cpu(log->arg[1]),
+		    le32_to_cpu(log->arg[2]), le32_to_cpu(log->arg[3]));
+
+	return true;
+}
+
+static void rtw89_phy_c2h_rfk_log(struct rtw89_dev *rtwdev, struct sk_buff *c2h,
+				  u32 len, enum rtw89_phy_c2h_rfk_log_func func,
+				  const char *rfk_name)
+{
+	struct rtw89_c2h_hdr *c2h_hdr = (struct rtw89_c2h_hdr *)c2h->data;
+	struct rtw89_c2h_rf_log_hdr *log_hdr;
+	void *log_ptr = c2h_hdr;
+	u16 content_len;
+	u16 chunk_len;
+	bool handled;
+
+	if (!rtw89_debug_is_enabled(rtwdev, RTW89_DBG_RFK))
+		return;
+
+	log_ptr += sizeof(*c2h_hdr);
+	len -= sizeof(*c2h_hdr);
+
+	while (len > sizeof(*log_hdr)) {
+		log_hdr = log_ptr;
+		content_len = le16_to_cpu(log_hdr->len);
+		chunk_len = content_len + sizeof(*log_hdr);
+
+		if (chunk_len > len)
+			break;
+
+		switch (log_hdr->type) {
+		case RTW89_RF_RUN_LOG:
+			handled = rtw89_phy_c2h_rfk_run_log(rtwdev, func,
+							    log_hdr->content, content_len);
+			if (handled)
+				break;
+
+			rtw89_debug(rtwdev, RTW89_DBG_RFK, "%s run: %*ph\n",
+				    rfk_name, content_len, log_hdr->content);
+			break;
+		case RTW89_RF_RPT_LOG:
+			rtw89_phy_c2h_rfk_rpt_log(rtwdev, func,
+						  log_hdr->content, content_len);
+			break;
+		default:
+			return;
+		}
+
+		log_ptr += chunk_len;
+		len -= chunk_len;
+	}
+}
+
+static void
+rtw89_phy_c2h_rfk_log_iqk(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u32 len)
+{
+	rtw89_phy_c2h_rfk_log(rtwdev, c2h, len,
+			      RTW89_PHY_C2H_RFK_LOG_FUNC_IQK, "IQK");
+}
+
+static void
+rtw89_phy_c2h_rfk_log_dpk(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u32 len)
+{
+	rtw89_phy_c2h_rfk_log(rtwdev, c2h, len,
+			      RTW89_PHY_C2H_RFK_LOG_FUNC_DPK, "DPK");
+}
+
+static void
+rtw89_phy_c2h_rfk_log_dack(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u32 len)
+{
+	rtw89_phy_c2h_rfk_log(rtwdev, c2h, len,
+			      RTW89_PHY_C2H_RFK_LOG_FUNC_DACK, "DACK");
+}
+
+static void
+rtw89_phy_c2h_rfk_log_rxdck(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u32 len)
+{
+	rtw89_phy_c2h_rfk_log(rtwdev, c2h, len,
+			      RTW89_PHY_C2H_RFK_LOG_FUNC_RXDCK, "RX_DCK");
+}
+
+static void
+rtw89_phy_c2h_rfk_log_tssi(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u32 len)
+{
+	rtw89_phy_c2h_rfk_log(rtwdev, c2h, len,
+			      RTW89_PHY_C2H_RFK_LOG_FUNC_TSSI, "TSSI");
+}
+
+static void
+rtw89_phy_c2h_rfk_log_txgapk(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u32 len)
+{
+	rtw89_phy_c2h_rfk_log(rtwdev, c2h, len,
+			      RTW89_PHY_C2H_RFK_LOG_FUNC_TXGAPK, "TXGAPK");
+}
+
+static
+void (* const rtw89_phy_c2h_rfk_log_handler[])(struct rtw89_dev *rtwdev,
+					       struct sk_buff *c2h, u32 len) = {
+	[RTW89_PHY_C2H_RFK_LOG_FUNC_IQK] = rtw89_phy_c2h_rfk_log_iqk,
+	[RTW89_PHY_C2H_RFK_LOG_FUNC_DPK] = rtw89_phy_c2h_rfk_log_dpk,
+	[RTW89_PHY_C2H_RFK_LOG_FUNC_DACK] = rtw89_phy_c2h_rfk_log_dack,
+	[RTW89_PHY_C2H_RFK_LOG_FUNC_RXDCK] = rtw89_phy_c2h_rfk_log_rxdck,
+	[RTW89_PHY_C2H_RFK_LOG_FUNC_TSSI] = rtw89_phy_c2h_rfk_log_tssi,
+	[RTW89_PHY_C2H_RFK_LOG_FUNC_TXGAPK] = rtw89_phy_c2h_rfk_log_txgapk,
+};
+
+static void
+rtw89_phy_c2h_rfk_report_state(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u32 len)
+{
+}
+
+static
+void (* const rtw89_phy_c2h_rfk_report_handler[])(struct rtw89_dev *rtwdev,
+						  struct sk_buff *c2h, u32 len) = {
+	[RTW89_PHY_C2H_RFK_REPORT_FUNC_STATE] = rtw89_phy_c2h_rfk_report_state,
+};
+
+bool rtw89_phy_c2h_chk_atomic(struct rtw89_dev *rtwdev, u8 class, u8 func)
+{
+	switch (class) {
+	case RTW89_PHY_C2H_RFK_LOG:
+		switch (func) {
+		case RTW89_PHY_C2H_RFK_LOG_FUNC_IQK:
+		case RTW89_PHY_C2H_RFK_LOG_FUNC_DPK:
+		case RTW89_PHY_C2H_RFK_LOG_FUNC_DACK:
+		case RTW89_PHY_C2H_RFK_LOG_FUNC_RXDCK:
+		case RTW89_PHY_C2H_RFK_LOG_FUNC_TSSI:
+		case RTW89_PHY_C2H_RFK_LOG_FUNC_TXGAPK:
+			return true;
+		default:
+			return false;
+		}
+	case RTW89_PHY_C2H_RFK_REPORT:
+		switch (func) {
+		case RTW89_PHY_C2H_RFK_REPORT_FUNC_STATE:
+			return true;
+		default:
+			return false;
+		}
+	default:
+		return false;
+	}
+}
+
 void rtw89_phy_c2h_handle(struct rtw89_dev *rtwdev, struct sk_buff *skb,
 			  u32 len, u8 class, u8 func)
 {
@@ -2456,6 +2748,14 @@ void rtw89_phy_c2h_handle(struct rtw89_dev *rtwdev, struct sk_buff *skb,
 		if (func < RTW89_PHY_C2H_FUNC_RA_MAX)
 			handler = rtw89_phy_c2h_ra_handler[func];
 		break;
+	case RTW89_PHY_C2H_RFK_LOG:
+		if (func < ARRAY_SIZE(rtw89_phy_c2h_rfk_log_handler))
+			handler = rtw89_phy_c2h_rfk_log_handler[func];
+		break;
+	case RTW89_PHY_C2H_RFK_REPORT:
+		if (func < ARRAY_SIZE(rtw89_phy_c2h_rfk_report_handler))
+			handler = rtw89_phy_c2h_rfk_report_handler[func];
+		break;
 	case RTW89_PHY_C2H_CLASS_DM:
 		if (func == RTW89_PHY_C2H_DM_FUNC_LOWRT_RTY)
 			return;
@@ -4620,6 +4920,29 @@ static void rtw89_phy_env_monitor_init(struct rtw89_dev *rtwdev)
 	rtw89_phy_ifs_clm_setting_init(rtwdev);
 }
 
+static void rtw89_phy_edcca_init(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_edcca_regs *edcca_regs = rtwdev->chip->edcca_regs;
+	struct rtw89_edcca_bak *edcca_bak = &rtwdev->hal.edcca_bak;
+
+	memset(edcca_bak, 0, sizeof(*edcca_bak));
+
+	if (rtwdev->chip->chip_id == RTL8922A && rtwdev->hal.cv == CHIP_CAV) {
+		rtw89_phy_set_phy_regs(rtwdev, R_TXGATING, B_TXGATING_EN, 0);
+		rtw89_phy_set_phy_regs(rtwdev, R_CTLTOP, B_CTLTOP_VAL, 2);
+		rtw89_phy_set_phy_regs(rtwdev, R_CTLTOP, B_CTLTOP_ON, 1);
+		rtw89_phy_set_phy_regs(rtwdev, R_SPOOF_CG, B_SPOOF_CG_EN, 0);
+		rtw89_phy_set_phy_regs(rtwdev, R_DFS_FFT_CG, B_DFS_CG_EN, 0);
+		rtw89_phy_set_phy_regs(rtwdev, R_DFS_FFT_CG, B_DFS_FFT_EN, 0);
+		rtw89_phy_set_phy_regs(rtwdev, R_SEGSND, B_SEGSND_EN, 0);
+		rtw89_phy_set_phy_regs(rtwdev, R_SEGSND, B_SEGSND_EN, 1);
+		rtw89_phy_set_phy_regs(rtwdev, R_DFS_FFT_CG, B_DFS_FFT_EN, 1);
+	}
+
+	rtw89_phy_write32_mask(rtwdev, edcca_regs->tx_collision_t2r_st,
+			       edcca_regs->tx_collision_t2r_st_mask, 0x29);
+}
+
 void rtw89_phy_dm_init(struct rtw89_dev *rtwdev)
 {
 	rtw89_phy_stat_init(rtwdev);
@@ -4630,6 +4953,7 @@ void rtw89_phy_dm_init(struct rtw89_dev *rtwdev)
 	rtw89_physts_parsing_init(rtwdev);
 	rtw89_phy_dig_init(rtwdev);
 	rtw89_phy_cfo_init(rtwdev);
+	rtw89_phy_edcca_init(rtwdev);
 	rtw89_phy_ul_tb_info_init(rtwdev);
 	rtw89_phy_antdiv_init(rtwdev);
 	rtw89_chip_rfe_gpio(rtwdev);
@@ -4892,23 +5216,188 @@ void rtw89_decode_chan_idx(struct rtw89_dev *rtwdev, u8 chan_idx,
 }
 EXPORT_SYMBOL(rtw89_decode_chan_idx);
 
-#define EDCCA_DEFAULT 249
 void rtw89_phy_config_edcca(struct rtw89_dev *rtwdev, bool scan)
 {
-	u32 reg = rtwdev->chip->edcca_lvl_reg;
-	struct rtw89_hal *hal = &rtwdev->hal;
-	u32 val;
+	const struct rtw89_edcca_regs *edcca_regs = rtwdev->chip->edcca_regs;
+	struct rtw89_edcca_bak *edcca_bak = &rtwdev->hal.edcca_bak;
 
 	if (scan) {
-		hal->edcca_bak = rtw89_phy_read32(rtwdev, reg);
-		val = hal->edcca_bak;
-		u32p_replace_bits(&val, EDCCA_DEFAULT, B_SEG0R_EDCCA_LVL_A_MSK);
-		u32p_replace_bits(&val, EDCCA_DEFAULT, B_SEG0R_EDCCA_LVL_P_MSK);
-		u32p_replace_bits(&val, EDCCA_DEFAULT, B_SEG0R_PPDU_LVL_MSK);
-		rtw89_phy_write32(rtwdev, reg, val);
+		edcca_bak->a =
+			rtw89_phy_read32_mask(rtwdev, edcca_regs->edcca_level,
+					      edcca_regs->edcca_mask);
+		edcca_bak->p =
+			rtw89_phy_read32_mask(rtwdev, edcca_regs->edcca_level,
+					      edcca_regs->edcca_p_mask);
+		edcca_bak->ppdu =
+			rtw89_phy_read32_mask(rtwdev, edcca_regs->ppdu_level,
+					      edcca_regs->ppdu_mask);
+
+		rtw89_phy_write32_mask(rtwdev, edcca_regs->edcca_level,
+				       edcca_regs->edcca_mask, EDCCA_MAX);
+		rtw89_phy_write32_mask(rtwdev, edcca_regs->edcca_level,
+				       edcca_regs->edcca_p_mask, EDCCA_MAX);
+		rtw89_phy_write32_mask(rtwdev, edcca_regs->ppdu_level,
+				       edcca_regs->ppdu_mask, EDCCA_MAX);
+	} else {
+		rtw89_phy_write32_mask(rtwdev, edcca_regs->edcca_level,
+				       edcca_regs->edcca_mask,
+				       edcca_bak->a);
+		rtw89_phy_write32_mask(rtwdev, edcca_regs->edcca_level,
+				       edcca_regs->edcca_p_mask,
+				       edcca_bak->p);
+		rtw89_phy_write32_mask(rtwdev, edcca_regs->ppdu_level,
+				       edcca_regs->ppdu_mask,
+				       edcca_bak->ppdu);
+	}
+}
+
+static void rtw89_phy_edcca_log(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_edcca_regs *edcca_regs = rtwdev->chip->edcca_regs;
+	bool flag_fb, flag_p20, flag_s20, flag_s40, flag_s80;
+	s8 pwdb_fb, pwdb_p20, pwdb_s20, pwdb_s40, pwdb_s80;
+	u8 path, per20_bitmap;
+	u8 pwdb[8];
+	u32 tmp;
+
+	if (!rtw89_debug_is_enabled(rtwdev, RTW89_DBG_EDCCA))
+		return;
+
+	if (rtwdev->chip->chip_id == RTL8922A)
+		rtw89_phy_write32_mask(rtwdev, edcca_regs->rpt_sel_be,
+				       edcca_regs->rpt_sel_be_mask, 0);
+
+	rtw89_phy_write32_mask(rtwdev, edcca_regs->rpt_sel,
+			       edcca_regs->rpt_sel_mask, 0);
+	tmp = rtw89_phy_read32(rtwdev, edcca_regs->rpt_b);
+	path = u32_get_bits(tmp, B_EDCCA_RPT_B_PATH_MASK);
+	flag_s80 = u32_get_bits(tmp, B_EDCCA_RPT_B_S80);
+	flag_s40 = u32_get_bits(tmp, B_EDCCA_RPT_B_S40);
+	flag_s20 = u32_get_bits(tmp, B_EDCCA_RPT_B_S20);
+	flag_p20 = u32_get_bits(tmp, B_EDCCA_RPT_B_P20);
+	flag_fb = u32_get_bits(tmp, B_EDCCA_RPT_B_FB);
+	pwdb_s20 = u32_get_bits(tmp, MASKBYTE1);
+	pwdb_p20 = u32_get_bits(tmp, MASKBYTE2);
+	pwdb_fb = u32_get_bits(tmp, MASKBYTE3);
+
+	rtw89_phy_write32_mask(rtwdev, edcca_regs->rpt_sel,
+			       edcca_regs->rpt_sel_mask, 4);
+	tmp = rtw89_phy_read32(rtwdev, edcca_regs->rpt_b);
+	pwdb_s80 = u32_get_bits(tmp, MASKBYTE1);
+	pwdb_s40 = u32_get_bits(tmp, MASKBYTE2);
+
+	per20_bitmap = rtw89_phy_read32_mask(rtwdev, edcca_regs->rpt_a,
+					     MASKBYTE0);
+
+	if (rtwdev->chip->chip_id == RTL8922A) {
+		rtw89_phy_write32_mask(rtwdev, edcca_regs->rpt_sel_be,
+				       edcca_regs->rpt_sel_be_mask, 4);
+		tmp = rtw89_phy_read32(rtwdev, edcca_regs->rpt_b);
+		pwdb[0] = u32_get_bits(tmp, MASKBYTE3);
+		pwdb[1] = u32_get_bits(tmp, MASKBYTE2);
+		pwdb[2] = u32_get_bits(tmp, MASKBYTE1);
+		pwdb[3] = u32_get_bits(tmp, MASKBYTE0);
+
+		rtw89_phy_write32_mask(rtwdev, edcca_regs->rpt_sel_be,
+				       edcca_regs->rpt_sel_be_mask, 5);
+		tmp = rtw89_phy_read32(rtwdev, edcca_regs->rpt_b);
+		pwdb[4] = u32_get_bits(tmp, MASKBYTE3);
+		pwdb[5] = u32_get_bits(tmp, MASKBYTE2);
+		pwdb[6] = u32_get_bits(tmp, MASKBYTE1);
+		pwdb[7] = u32_get_bits(tmp, MASKBYTE0);
 	} else {
-		rtw89_phy_write32(rtwdev, reg, hal->edcca_bak);
+		rtw89_phy_write32_mask(rtwdev, edcca_regs->rpt_sel,
+				       edcca_regs->rpt_sel_mask, 0);
+		tmp = rtw89_phy_read32(rtwdev, edcca_regs->rpt_a);
+		pwdb[0] = u32_get_bits(tmp, MASKBYTE3);
+		pwdb[1] = u32_get_bits(tmp, MASKBYTE2);
+
+		rtw89_phy_write32_mask(rtwdev, edcca_regs->rpt_sel,
+				       edcca_regs->rpt_sel_mask, 1);
+		tmp = rtw89_phy_read32(rtwdev, edcca_regs->rpt_a);
+		pwdb[2] = u32_get_bits(tmp, MASKBYTE3);
+		pwdb[3] = u32_get_bits(tmp, MASKBYTE2);
+
+		rtw89_phy_write32_mask(rtwdev, edcca_regs->rpt_sel,
+				       edcca_regs->rpt_sel_mask, 2);
+		tmp = rtw89_phy_read32(rtwdev, edcca_regs->rpt_a);
+		pwdb[4] = u32_get_bits(tmp, MASKBYTE3);
+		pwdb[5] = u32_get_bits(tmp, MASKBYTE2);
+
+		rtw89_phy_write32_mask(rtwdev, edcca_regs->rpt_sel,
+				       edcca_regs->rpt_sel_mask, 3);
+		tmp = rtw89_phy_read32(rtwdev, edcca_regs->rpt_a);
+		pwdb[6] = u32_get_bits(tmp, MASKBYTE3);
+		pwdb[7] = u32_get_bits(tmp, MASKBYTE2);
 	}
+
+	rtw89_debug(rtwdev, RTW89_DBG_EDCCA,
+		    "[EDCCA]: edcca_bitmap = %04x\n", per20_bitmap);
+
+	rtw89_debug(rtwdev, RTW89_DBG_EDCCA,
+		    "[EDCCA]: pwdb per20{0,1,2,3,4,5,6,7} = {%d,%d,%d,%d,%d,%d,%d,%d}(dBm)\n",
+		    pwdb[0], pwdb[1], pwdb[2], pwdb[3], pwdb[4], pwdb[5],
+		    pwdb[6], pwdb[7]);
+
+	rtw89_debug(rtwdev, RTW89_DBG_EDCCA,
+		    "[EDCCA]: path=%d, flag {FB,p20,s20,s40,s80} = {%d,%d,%d,%d,%d}\n",
+		    path, flag_fb, flag_p20, flag_s20, flag_s40, flag_s80);
+
+	rtw89_debug(rtwdev, RTW89_DBG_EDCCA,
+		    "[EDCCA]: pwdb {FB,p20,s20,s40,s80} = {%d,%d,%d,%d,%d}(dBm)\n",
+		    pwdb_fb, pwdb_p20, pwdb_s20, pwdb_s40, pwdb_s80);
+}
+
+static u8 rtw89_phy_edcca_get_thre_by_rssi(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_phy_ch_info *ch_info = &rtwdev->ch_info;
+	bool is_linked = rtwdev->total_sta_assoc > 0;
+	u8 rssi_min = ch_info->rssi_min >> 1;
+	u8 edcca_thre;
+
+	if (!is_linked) {
+		edcca_thre = EDCCA_MAX;
+	} else {
+		edcca_thre = rssi_min - RSSI_UNIT_CONVER + EDCCA_UNIT_CONVER -
+			     EDCCA_TH_REF;
+		edcca_thre = max_t(u8, edcca_thre, EDCCA_TH_L2H_LB);
+	}
+
+	return edcca_thre;
+}
+
+void rtw89_phy_edcca_thre_calc(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_edcca_regs *edcca_regs = rtwdev->chip->edcca_regs;
+	struct rtw89_edcca_bak *edcca_bak = &rtwdev->hal.edcca_bak;
+	u8 th;
+
+	th = rtw89_phy_edcca_get_thre_by_rssi(rtwdev);
+	if (th == edcca_bak->th_old)
+		return;
+
+	edcca_bak->th_old = th;
+
+	rtw89_debug(rtwdev, RTW89_DBG_EDCCA,
+		    "[EDCCA]: Normal Mode, EDCCA_th = %d\n", th);
+
+	rtw89_phy_write32_mask(rtwdev, edcca_regs->edcca_level,
+			       edcca_regs->edcca_mask, th);
+	rtw89_phy_write32_mask(rtwdev, edcca_regs->edcca_level,
+			       edcca_regs->edcca_p_mask, th);
+	rtw89_phy_write32_mask(rtwdev, edcca_regs->ppdu_level,
+			       edcca_regs->ppdu_mask, th);
+}
+
+void rtw89_phy_edcca_track(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_hal *hal = &rtwdev->hal;
+
+	if (hal->disabled_dm_bitmap & BIT(RTW89_DM_DYNAMIC_EDCCA))
+		return;
+
+	rtw89_phy_edcca_thre_calc(rtwdev);
+	rtw89_phy_edcca_log(rtwdev);
 }
 
 static const struct rtw89_ccx_regs rtw89_ccx_regs_ax = {
diff --git a/drivers/net/wireless/realtek/rtw89/phy.h b/drivers/net/wireless/realtek/rtw89/phy.h
index 5c85122e7bb5..3e379077c6ca 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.h
+++ b/drivers/net/wireless/realtek/rtw89/phy.h
@@ -122,6 +122,13 @@
 #define PHYSTS_RSVD BIT(RTW89_RX_TYPE_RSVD)
 #define PPDU_FILTER_BITMAP (PHYSTS_MGNT | PHYSTS_DATA)
 
+#define EDCCA_MAX 249
+#define EDCCA_TH_L2H_LB 66
+#define EDCCA_TH_REF 3
+#define EDCCA_HL_DIFF_NORMAL 8
+#define RSSI_UNIT_CONVER 110
+#define EDCCA_UNIT_CONVER 128
+
 enum rtw89_phy_c2h_ra_func {
 	RTW89_PHY_C2H_FUNC_STS_RPT,
 	RTW89_PHY_C2H_FUNC_MU_GPTBL_RPT,
@@ -129,6 +136,21 @@ enum rtw89_phy_c2h_ra_func {
 	RTW89_PHY_C2H_FUNC_RA_MAX,
 };
 
+enum rtw89_phy_c2h_rfk_log_func {
+	RTW89_PHY_C2H_RFK_LOG_FUNC_IQK = 0,
+	RTW89_PHY_C2H_RFK_LOG_FUNC_DPK = 1,
+	RTW89_PHY_C2H_RFK_LOG_FUNC_DACK = 2,
+	RTW89_PHY_C2H_RFK_LOG_FUNC_RXDCK = 3,
+	RTW89_PHY_C2H_RFK_LOG_FUNC_TSSI = 4,
+	RTW89_PHY_C2H_RFK_LOG_FUNC_TXGAPK = 5,
+
+	RTW89_PHY_C2H_RFK_LOG_FUNC_NUM,
+};
+
+enum rtw89_phy_c2h_rfk_report_func {
+	RTW89_PHY_C2H_RFK_REPORT_FUNC_STATE = 0,
+};
+
 enum rtw89_phy_c2h_dm_func {
 	RTW89_PHY_C2H_DM_FUNC_FW_TEST,
 	RTW89_PHY_C2H_DM_FUNC_FW_TRIG_TX_RPT,
@@ -142,6 +164,8 @@ enum rtw89_phy_c2h_class {
 	RTW89_PHY_C2H_CLASS_RUA,
 	RTW89_PHY_C2H_CLASS_RA,
 	RTW89_PHY_C2H_CLASS_DM,
+	RTW89_PHY_C2H_RFK_LOG = 0x8,
+	RTW89_PHY_C2H_RFK_REPORT = 0x9,
 	RTW89_PHY_C2H_CLASS_BTC_MIN = 0x10,
 	RTW89_PHY_C2H_CLASS_BTC_MAX = 0x17,
 	RTW89_PHY_C2H_CLASS_MAX,
@@ -284,8 +308,6 @@ struct rtw89_txpwr_byrate_cfg {
 	u32 data;
 };
 
-#define DELTA_SWINGIDX_SIZE 30
-
 struct rtw89_txpwr_track_cfg {
 	const s8 (*delta_swingidx_6gb_n)[DELTA_SWINGIDX_SIZE];
 	const s8 (*delta_swingidx_6gb_p)[DELTA_SWINGIDX_SIZE];
@@ -478,6 +500,10 @@ struct rtw89_txpwr_limit_ru_be {
 	s8 ru106_26[RTW89_RU_SEC_NUM_BE];
 };
 
+struct rtw89_phy_rfk_log_fmt {
+	const struct rtw89_fw_element_hdr *elm[RTW89_PHY_C2H_RFK_LOG_FUNC_NUM];
+};
+
 struct rtw89_phy_gen_def {
 	u32 cr_base;
 	const struct rtw89_ccx_regs *ccx;
@@ -591,6 +617,22 @@ enum rtw89_gain_offset rtw89_subband_to_gain_offset_band_of_ofdm(enum rtw89_subb
 		return RTW89_GAIN_OFFSET_5G_MID;
 	case RTW89_CH_5G_BAND_4:
 		return RTW89_GAIN_OFFSET_5G_HIGH;
+	case RTW89_CH_6G_BAND_IDX0:
+		return RTW89_GAIN_OFFSET_6G_L0;
+	case RTW89_CH_6G_BAND_IDX1:
+		return RTW89_GAIN_OFFSET_6G_L1;
+	case RTW89_CH_6G_BAND_IDX2:
+		return RTW89_GAIN_OFFSET_6G_M0;
+	case RTW89_CH_6G_BAND_IDX3:
+		return RTW89_GAIN_OFFSET_6G_M1;
+	case RTW89_CH_6G_BAND_IDX4:
+		return RTW89_GAIN_OFFSET_6G_H0;
+	case RTW89_CH_6G_BAND_IDX5:
+		return RTW89_GAIN_OFFSET_6G_H1;
+	case RTW89_CH_6G_BAND_IDX6:
+		return RTW89_GAIN_OFFSET_6G_UH0;
+	case RTW89_CH_6G_BAND_IDX7:
+		return RTW89_GAIN_OFFSET_6G_UH1;
 	}
 }
 
@@ -764,6 +806,7 @@ void rtw89_phy_ra_updata_sta(struct rtw89_dev *rtwdev, struct ieee80211_sta *sta
 void rtw89_phy_rate_pattern_vif(struct rtw89_dev *rtwdev,
 				struct ieee80211_vif *vif,
 				const struct cfg80211_bitrate_mask *mask);
+bool rtw89_phy_c2h_chk_atomic(struct rtw89_dev *rtwdev, u8 class, u8 func);
 void rtw89_phy_c2h_handle(struct rtw89_dev *rtwdev, struct sk_buff *skb,
 			  u32 len, u8 class, u8 func);
 void rtw89_phy_cfo_track(struct rtw89_dev *rtwdev);
@@ -791,5 +834,7 @@ u8 rtw89_encode_chan_idx(struct rtw89_dev *rtwdev, u8 central_ch, u8 band);
 void rtw89_decode_chan_idx(struct rtw89_dev *rtwdev, u8 chan_idx,
 			   u8 *ch, enum nl80211_band *band);
 void rtw89_phy_config_edcca(struct rtw89_dev *rtwdev, bool scan);
+void rtw89_phy_edcca_track(struct rtw89_dev *rtwdev);
+void rtw89_phy_edcca_thre_calc(struct rtw89_dev *rtwdev);
 
 #endif
diff --git a/drivers/net/wireless/realtek/rtw89/ps.h b/drivers/net/wireless/realtek/rtw89/ps.h
index aff0fba71cb0..54486e4550b6 100644
--- a/drivers/net/wireless/realtek/rtw89/ps.h
+++ b/drivers/net/wireless/realtek/rtw89/ps.h
@@ -33,6 +33,10 @@ static inline void rtw89_enter_ips_by_hwflags(struct rtw89_dev *rtwdev)
 {
 	struct ieee80211_hw *hw = rtwdev->hw;
 
+	/* prevent entering IPS after ROC, but it is scanning */
+	if (rtwdev->scanning)
+		return;
+
 	if (hw->conf.flags & IEEE80211_CONF_IDLE)
 		rtw89_enter_ips(rtwdev);
 }
diff --git a/drivers/net/wireless/realtek/rtw89/reg.h b/drivers/net/wireless/realtek/rtw89/reg.h
index ccd5481e8a3d..8456e2b0c14f 100644
--- a/drivers/net/wireless/realtek/rtw89/reg.h
+++ b/drivers/net/wireless/realtek/rtw89/reg.h
@@ -116,6 +116,7 @@
 #define B_AX_LTE_MUX_CTRL_PATH BIT(26)
 
 #define R_AX_HCI_OPT_CTRL 0x0074
+#define BIT_WAKE_CTRL_V1 BIT(23)
 #define BIT_WAKE_CTRL BIT(5)
 
 #define R_AX_HCI_BG_CTRL 0x0078
@@ -1456,6 +1457,8 @@
 #define B_AX_PLE_Q6_MAX_SIZE_MASK GENMASK(27, 16)
 #define B_AX_PLE_Q6_MIN_SIZE_MASK GENMASK(11, 0)
 #define R_AX_PLE_QTA7_CFG 0x905C
+#define B_AX_PLE_Q7_MAX_SIZE_MASK GENMASK(27, 16)
+#define B_AX_PLE_Q7_MIN_SIZE_MASK GENMASK(11, 0)
 #define R_AX_PLE_QTA8_CFG 0x9060
 #define R_AX_PLE_QTA9_CFG 0x9064
 #define R_AX_PLE_QTA10_CFG 0x9068
@@ -2375,6 +2378,14 @@
 #define R_AX_TSFTR_HIGH_P4 0xC53C
 #define B_AX_TSFTR_HIGH_MASK GENMASK(31, 0)
 
+#define R_AX_BCN_DROP_ALL0 0xC560
+#define R_AX_BCN_DROP_ALL0_C1 0xE560
+#define B_AX_BCN_DROP_ALL_P4 BIT(4)
+#define B_AX_BCN_DROP_ALL_P3 BIT(3)
+#define B_AX_BCN_DROP_ALL_P2 BIT(2)
+#define B_AX_BCN_DROP_ALL_P1 BIT(1)
+#define B_AX_BCN_DROP_ALL_P0 BIT(0)
+
 #define R_AX_MBSSID_CTRL 0xC568
 #define R_AX_MBSSID_CTRL_C1 0xE568
 #define B_AX_P0MB_ALL_MASK GENMASK(23, 1)
@@ -2554,11 +2565,20 @@
 
 #define R_AX_PTCL_DBG_INFO 0xC6F0
 #define R_AX_PTCL_DBG_INFO_C1 0xE6F0
+#define B_AX_PTCL_DBG_INFO_MASK_BY_PORT(port) \
+({\
+	typeof(port) _port = (port); \
+	GENMASK((_port) * 2 + 1, (_port) * 2); \
+})
+
 #define B_AX_PTCL_DBG_INFO_MASK GENMASK(31, 0)
 #define R_AX_PTCL_DBG 0xC6F4
 #define R_AX_PTCL_DBG_C1 0xE6F4
 #define B_AX_PTCL_DBG_EN BIT(8)
 #define B_AX_PTCL_DBG_SEL_MASK GENMASK(7, 0)
+#define AX_PTCL_DBG_BCNQ_NUM0 8
+#define AX_PTCL_DBG_BCNQ_NUM1 9
+
 
 #define R_AX_DLE_CTRL 0xC800
 #define R_AX_DLE_CTRL_C1 0xE800
@@ -3629,6 +3649,50 @@
 #define B_AX_GNT_BT_TX_SW_VAL BIT(1)
 #define B_AX_GNT_BT_TX_SW_CTRL BIT(0)
 
+#define R_BE_SYS_ISO_CTRL 0x0000
+#define B_BE_PWC_EV2EF_B BIT(15)
+#define B_BE_PWC_EV2EF_S BIT(14)
+#define B_BE_PA33V_EN BIT(13)
+#define B_BE_PA12V_EN BIT(12)
+#define B_BE_PAOOBS33V_EN BIT(11)
+#define B_BE_PAOOBS12V_EN BIT(10)
+#define B_BE_ISO_RFDIO BIT(9)
+#define B_BE_ISO_EB2CORE BIT(8)
+#define B_BE_ISO_DIOE BIT(7)
+#define B_BE_ISO_WLPON2PP BIT(6)
+#define B_BE_ISO_IP2MAC_WA02PP BIT(5)
+#define B_BE_ISO_PD2CORE BIT(4)
+#define B_BE_ISO_PA2PCIE BIT(3)
+#define B_BE_ISO_PAOOBS2PCIE BIT(1)
+#define B_BE_ISO_WD2PP BIT(0)
+
+#define R_BE_SYS_PW_CTRL 0x0004
+#define B_BE_SOP_ASWRM BIT(31)
+#define B_BE_SOP_EASWR BIT(30)
+#define B_BE_SOP_PWMM_DSWR BIT(29)
+#define B_BE_SOP_EDSWR BIT(28)
+#define B_BE_SOP_ACKF BIT(27)
+#define B_BE_SOP_ERCK BIT(26)
+#define B_BE_SOP_ANA_CLK_DIVISION_2 BIT(25)
+#define B_BE_SOP_EXTL BIT(24)
+#define B_BE_SOP_OFF_CAPC_EN BIT(23)
+#define B_BE_XTAL_OFF_A_DIE BIT(22)
+#define B_BE_ROP_SWPR BIT(21)
+#define B_BE_DIS_HW_LPLDM BIT(20)
+#define B_BE_DIS_HW_LPURLDO BIT(19)
+#define B_BE_DIS_WLBT_PDNSUSEN_SOPC BIT(18)
+#define B_BE_RDY_SYSPWR BIT(17)
+#define B_BE_EN_WLON BIT(16)
+#define B_BE_APDM_HPDN BIT(15)
+#define B_BE_PSUS_OFF_CAPC_EN BIT(14)
+#define B_BE_AFSM_PCIE_SUS_EN BIT(12)
+#define B_BE_AFSM_WLSUS_EN BIT(11)
+#define B_BE_APFM_SWLPS BIT(10)
+#define B_BE_APFM_OFFMAC BIT(9)
+#define B_BE_APFN_ONMAC BIT(8)
+#define B_BE_CHIP_PDN_EN BIT(7)
+#define B_BE_RDY_MACDIS BIT(6)
+
 #define R_BE_SYS_CLK_CTRL 0x0008
 #define B_BE_CPU_CLK_EN BIT(14)
 #define B_BE_SYMR_BE_CLK_EN BIT(13)
@@ -3639,6 +3703,249 @@
 #define B_BE_ANA_CLK_DIVISION_2 BIT(1)
 #define B_BE_CNTD16V_EN BIT(0)
 
+#define R_BE_SYS_WL_EFUSE_CTRL 0x000A
+#define B_BE_OTP_B_PWC_RPT BIT(15)
+#define B_BE_OTP_S_PWC_RPT BIT(14)
+#define B_BE_OTP_ISO_RPT BIT(13)
+#define B_BE_OTP_BURST_RPT BIT(12)
+#define B_BE_OTP_AUTOLOAD_RPT BIT(11)
+#define B_BE_AUTOLOAD_DIS_A_DIE BIT(6)
+#define B_BE_AUTOLOAD_SUS BIT(5)
+#define B_BE_AUTOLOAD_DIS BIT(4)
+
+#define R_BE_SYS_PAGE_CLK_GATED 0x000C
+#define B_BE_USB_APHY_PC_DLP_OP BIT(27)
+#define B_BE_PCIE_APHY_PC_DLP_OP BIT(26)
+#define B_BE_UPHY_POWER_READY_CHK BIT(25)
+#define B_BE_CPHY_POWER_READY_CHK BIT(24)
+#define B_BE_PCIE_PRST_DEBUNC_PERIOD_MASK GENMASK(23, 22)
+#define B_BE_SYM_PRST_DEBUNC_SEL BIT(21)
+#define B_BE_CPHY_AUXCLK_OP BIT(20)
+#define B_BE_SOP_OFFUA_PC BIT(19)
+#define B_BE_SOP_OFFPOOBS_PC BIT(18)
+#define B_BE_PCIE_LAN1_MASK BIT(17)
+#define B_BE_PCIE_LAN0_MASK BIT(16)
+#define B_BE_DIS_CLK_REGF_GATE BIT(15)
+#define B_BE_DIS_CLK_REGE_GATE BIT(14)
+#define B_BE_DIS_CLK_REGD_GATE BIT(13)
+#define B_BE_DIS_CLK_REGC_GATE BIT(12)
+#define B_BE_DIS_CLK_REGB_GATE BIT(11)
+#define B_BE_DIS_CLK_REGA_GATE BIT(10)
+#define B_BE_DIS_CLK_REG9_GATE BIT(9)
+#define B_BE_DIS_CLK_REG8_GATE BIT(8)
+#define B_BE_DIS_CLK_REG7_GATE BIT(7)
+#define B_BE_DIS_CLK_REG6_GATE BIT(6)
+#define B_BE_DIS_CLK_REG5_GATE BIT(5)
+#define B_BE_DIS_CLK_REG4_GATE BIT(4)
+#define B_BE_DIS_CLK_REG3_GATE BIT(3)
+#define B_BE_DIS_CLK_REG2_GATE BIT(2)
+#define B_BE_DIS_CLK_REG1_GATE BIT(1)
+#define B_BE_DIS_CLK_REG0_GATE BIT(0)
+
+#define R_BE_ANAPAR_POW_MAC 0x0016
+#define B_BE_POW_PC_LDO_PORT1 BIT(3)
+#define B_BE_POW_PC_LDO_PORT0 BIT(2)
+#define B_BE_POW_PLL_V1 BIT(1)
+#define B_BE_POW_POWER_CUT_POW_LDO BIT(0)
+
+#define R_BE_SYS_ADIE_PAD_PWR_CTRL 0x0018
+#define B_BE_SYM_PADPDN_WL_RFC1_1P3 BIT(6)
+#define B_BE_SYM_PADPDN_WL_RFC0_1P3 BIT(5)
+
+#define R_BE_AFE_LDO_CTRL 0x0020
+#define B_BE_FORCE_MACBBBT_PWR_ON BIT(31)
+#define B_BE_R_SYM_WLPOFF_P4_PC_EN BIT(28)
+#define B_BE_R_SYM_WLPOFF_P3_PC_EN BIT(27)
+#define B_BE_R_SYM_WLPOFF_P2_PC_EN BIT(26)
+#define B_BE_R_SYM_WLPOFF_P1_PC_EN BIT(25)
+#define B_BE_R_SYM_WLPOFF_PC_EN BIT(24)
+#define B_BE_AON_OFF_PC_EN BIT(23)
+#define B_BE_R_SYM_WLPON_P3_PC_EN BIT(21)
+#define B_BE_R_SYM_WLPON_P2_PC_EN BIT(20)
+#define B_BE_R_SYM_WLPON_P1_PC_EN BIT(19)
+#define B_BE_R_SYM_WLPON_PC_EN BIT(18)
+#define B_BE_R_SYM_WLBBPON1_P1_PC_EN BIT(15)
+#define B_BE_R_SYM_WLBBPON1_PC_EN BIT(14)
+#define B_BE_R_SYM_WLBBPON_P1_PC_EN BIT(13)
+#define B_BE_R_SYM_WLBBPON_PC_EN BIT(12)
+#define B_BE_R_SYM_DIS_WPHYBBOFF_PC BIT(10)
+#define B_BE_R_SYM_WLBBOFF1_P4_PC_EN BIT(9)
+#define B_BE_R_SYM_WLBBOFF1_P3_PC_EN BIT(8)
+#define B_BE_R_SYM_WLBBOFF1_P2_PC_EN BIT(7)
+#define B_BE_R_SYM_WLBBOFF1_P1_PC_EN BIT(6)
+#define B_BE_R_SYM_WLBBOFF1_PC_EN BIT(5)
+#define B_BE_R_SYM_WLBBOFF_P4_PC_EN BIT(4)
+#define B_BE_R_SYM_WLBBOFF_P3_PC_EN BIT(3)
+#define B_BE_R_SYM_WLBBOFF_P2_PC_EN BIT(2)
+#define B_BE_R_SYM_WLBBOFF_P1_PC_EN BIT(1)
+#define B_BE_R_SYM_WLBBOFF_PC_EN BIT(0)
+
+#define R_BE_AFE_CTRL1 0x0024
+#define B_BE_R_SYM_WLCMAC0_P4_PC_EN BIT(28)
+#define B_BE_R_SYM_WLCMAC0_P3_PC_EN BIT(27)
+#define B_BE_R_SYM_WLCMAC0_P2_PC_EN BIT(26)
+#define B_BE_R_SYM_WLCMAC0_P1_PC_EN BIT(25)
+#define B_BE_R_SYM_WLCMAC0_PC_EN BIT(24)
+#define B_BE_DATAMEM_PC3_EN BIT(23)
+#define B_BE_DATAMEM_PC2_EN BIT(22)
+#define B_BE_DATAMEM_PC1_EN BIT(21)
+#define B_BE_DATAMEM_PC_EN BIT(20)
+#define B_BE_DMEM7_PC_EN BIT(19)
+#define B_BE_DMEM6_PC_EN BIT(18)
+#define B_BE_DMEM5_PC_EN BIT(17)
+#define B_BE_DMEM4_PC_EN BIT(16)
+#define B_BE_DMEM3_PC_EN BIT(15)
+#define B_BE_DMEM2_PC_EN BIT(14)
+#define B_BE_DMEM1_PC_EN BIT(13)
+#define B_BE_IMEM4_PC_EN BIT(12)
+#define B_BE_IMEM3_PC_EN BIT(11)
+#define B_BE_IMEM2_PC_EN BIT(10)
+#define B_BE_IMEM1_PC_EN BIT(9)
+#define B_BE_IMEM0_PC_EN BIT(8)
+#define B_BE_R_SYM_WLCMAC1_P4_PC_EN BIT(4)
+#define B_BE_R_SYM_WLCMAC1_P3_PC_EN BIT(3)
+#define B_BE_R_SYM_WLCMAC1_P2_PC_EN BIT(2)
+#define B_BE_R_SYM_WLCMAC1_P1_PC_EN BIT(1)
+#define B_BE_R_SYM_WLCMAC1_PC_EN BIT(0)
+#define B_BE_AFE_CTRL1_SET (B_BE_R_SYM_WLCMAC1_PC_EN | \
+			    B_BE_R_SYM_WLCMAC1_P1_PC_EN | \
+			    B_BE_R_SYM_WLCMAC1_P2_PC_EN | \
+			    B_BE_R_SYM_WLCMAC1_P3_PC_EN | \
+			    B_BE_R_SYM_WLCMAC1_P4_PC_EN)
+
+#define R_BE_EFUSE_CTRL 0x0030
+#define B_BE_EF_MODE_SEL_MASK GENMASK(31, 30)
+#define B_BE_EF_RDY BIT(29)
+#define B_BE_EF_COMP_RESULT BIT(28)
+#define B_BE_EF_ADDR_MASK GENMASK(15, 0)
+
+#define R_BE_EFUSE_CTRL_1_V1 0x0034
+#define B_BE_EF_DATA_MASK GENMASK(31, 0)
+
+#define R_BE_WL_BT_PWR_CTRL 0x0068
+#define B_BE_ISO_BD2PP BIT(31)
+#define B_BE_LDOV12B_EN BIT(30)
+#define B_BE_CKEN_BT BIT(29)
+#define B_BE_FEN_BT BIT(28)
+#define B_BE_BTCPU_BOOTSEL BIT(27)
+#define B_BE_SPI_SPEEDUP BIT(26)
+#define B_BE_BT_LDO_MODE BIT(25)
+#define B_BE_ISO_BTPON2PP BIT(22)
+#define B_BE_BT_FUNC_EN BIT(18)
+#define B_BE_BT_HWPDN_SL BIT(17)
+#define B_BE_BT_DISN_EN BIT(16)
+#define B_BE_SDM_SRC_SEL BIT(12)
+#define B_BE_ISO_BA2PP BIT(11)
+#define B_BE_BT_AFE_LDO_EN BIT(10)
+#define B_BE_BT_AFE_PLL_EN BIT(9)
+#define B_BE_WLAN_32K_SEL BIT(6)
+#define B_BE_WL_DRV_EXIST_IDX BIT(5)
+#define B_BE_DOP_EHPAD BIT(4)
+#define B_BE_WL_FUNC_EN BIT(2)
+#define B_BE_WL_HWPDN_SL BIT(1)
+#define B_BE_WL_HWPDN_EN BIT(0)
+
+#define R_BE_SYS_SDIO_CTRL 0x0070
+#define B_BE_MCM_FLASH_EN BIT(28)
+#define B_BE_PCIE_SEC_LOAD BIT(26)
+#define B_BE_PCIE_SER_RSTB BIT(25)
+#define B_BE_PCIE_SEC_LOAD_CLR BIT(24)
+#define B_BE_SDIO_CMD_SW_RST BIT(20)
+#define B_BE_SDIO_INT_POLARITY BIT(19)
+#define B_BE_SDIO_OFF_EN BIT(17)
+#define B_BE_SDIO_ON_EN BIT(16)
+#define B_BE_PCIE_DIS_L2__CTRL_LDO_HCI BIT(15)
+#define B_BE_PCIE_DIS_L2_RTK_PERST BIT(14)
+#define B_BE_PCIE_FORCE_PWR_NGAT BIT(13)
+#define B_BE_PCIE_FORCE_IBX_EN BIT(12)
+#define B_BE_PCIE_AUXCLK_GATE BIT(11)
+#define B_BE_PCIE_WAIT_TIMEOUT_EVENT BIT(10)
+#define B_BE_PCIE_WAIT_TIME BIT(9)
+#define B_BE_L1OFF_TO_L0_RESUME_EVT BIT(8)
+#define B_BE_USBA_FORCE_PWR_NGAT BIT(7)
+#define B_BE_USBD_FORCE_PWR_NGAT BIT(6)
+#define B_BE_BT_CTRL_USB_PWR BIT(5)
+#define B_BE_USB_D_STATE_HOLD BIT(4)
+#define B_BE_R_BE_FORCE_DP BIT(3)
+#define B_BE_R_BE_DP_MODE BIT(2)
+#define B_BE_RES_USB_MASS_STORAGE_DESC BIT(1)
+#define B_BE_USB_WAIT_TIME BIT(0)
+
+#define R_BE_HCI_OPT_CTRL 0x0074
+#define B_BE_HCI_WLAN_IO_ST BIT(31)
+#define B_BE_HCI_WLAN_IO_EN BIT(28)
+#define B_BE_HAXIDMA_IO_ST BIT(27)
+#define B_BE_HAXIDMA_BACKUP_RESTORE_ST BIT(26)
+#define B_BE_HAXIDMA_IO_EN BIT(24)
+#define B_BE_EN_PCIE_WAKE BIT(23)
+#define B_BE_SDIO_PAD_H3L1 BIT(22)
+#define B_BE_USBMAC_ANACLK_SW BIT(21)
+#define B_BE_PCIE_CPHY_CCK_XTAL_SEL BIT(20)
+#define B_BE_SDIO_DATA_PAD_SMT BIT(19)
+#define B_BE_SDIO_PAD_E5 BIT(18)
+#define B_BE_FORCE_PCIE_AUXCLK BIT(17)
+#define B_BE_HCI_LA_ADDR_MAP BIT(16)
+#define B_BE_HCI_LA_GLO_RST BIT(15)
+#define B_BE_USB3_SUS_DIS BIT(14)
+#define B_BE_NOPWR_CTRL_SEL BIT(13)
+#define B_BE_USB_HOST_PWR_OFF_EN BIT(12)
+#define B_BE_SYM_LPS_BLOCK_EN BIT(11)
+#define B_BE_USB_LPM_ACT_EN BIT(10)
+#define B_BE_USB_LPM_NY BIT(9)
+#define B_BE_USB2_SUS_DIS BIT(8)
+#define B_BE_SDIO_PAD_E_MASK GENMASK(7, 5)
+#define B_BE_USB_LPPLL_EN BIT(4)
+#define B_BE_USB1_1_USB2_0_DECISION BIT(3)
+#define B_BE_ROP_SW15 BIT(2)
+#define B_BE_PCI_CKRDY_OPT BIT(1)
+#define B_BE_PCI_VAUX_EN BIT(0)
+
+#define R_BE_SYS_ISO_CTRL_EXTEND 0x0080
+#define B_BE_R_SYM_ISO_DMEM62PP BIT(29)
+#define B_BE_R_SYM_ISO_DMEM52PP BIT(28)
+#define B_BE_R_SYM_ISO_DMEM42PP BIT(27)
+#define B_BE_R_SYM_ISO_DMEM32PP BIT(26)
+#define B_BE_R_SYM_ISO_DMEM22PP BIT(25)
+#define B_BE_R_SYM_ISO_DMEM12PP BIT(24)
+#define B_BE_R_SYM_ISO_IMEM42PP BIT(22)
+#define B_BE_R_SYM_ISO_IMEM32PP BIT(21)
+#define B_BE_R_SYM_ISO_IMEM22PP BIT(20)
+#define B_BE_R_SYM_ISO_IMEM12PP BIT(19)
+#define B_BE_R_SYM_ISO_IMEM02PP BIT(18)
+#define B_BE_R_SYM_ISO_AON_OFF2PP BIT(15)
+#define B_BE_R_SYM_PWC_HCILA BIT(13)
+#define B_BE_R_SYM_PWC_PD12V BIT(12)
+#define B_BE_R_SYM_PWC_UD12V BIT(11)
+#define B_BE_R_SYM_PWC_BTBRG BIT(10)
+#define B_BE_R_SYM_LDOBTSDIO_EN BIT(9)
+#define B_BE_R_SYM_LDOSPDIO_EN BIT(8)
+#define B_BE_R_SYM_ISO_HCILA BIT(4)
+#define B_BE_R_SYM_ISO_BTBRG2PP BIT(2)
+#define B_BE_R_SYM_ISO_BTSDIO2PP BIT(1)
+#define B_BE_R_SYM_ISO_SPDIO2PP BIT(0)
+
+#define R_BE_FEN_RST_ENABLE 0x0084
+#define B_BE_R_SYM_FEN_WLMACOFF BIT(31)
+#define B_BE_R_SYM_ISO_WA12PP BIT(28)
+#define B_BE_R_SYM_ISO_CMAC12PP BIT(25)
+#define B_BE_R_SYM_ISO_CMAC02PP BIT(24)
+#define B_BE_R_SYM_ISO_ADDA_P32PP BIT(23)
+#define B_BE_R_SYM_ISO_ADDA_P22PP BIT(22)
+#define B_BE_R_SYM_ISO_ADDA_P12PP BIT(21)
+#define B_BE_R_SYM_ISO_ADDA_P02PP BIT(20)
+#define B_BE_CMAC1_FEN BIT(17)
+#define B_BE_CMAC0_FEN BIT(16)
+#define B_BE_SYM_ISO_BBPON12PP BIT(13)
+#define B_BE_SYM_ISO_BB12PP BIT(12)
+#define B_BE_BOOT_RDY1 BIT(10)
+#define B_BE_FEN_BB1_IP_RSTN BIT(9)
+#define B_BE_FEN_BB1PLAT_RSTB BIT(8)
+#define B_BE_SYM_ISO_BBPON02PP BIT(5)
+#define B_BE_SYM_ISO_BB02PP BIT(4)
+#define B_BE_BOOT_RDY0 BIT(2)
+#define B_BE_FEN_BB_IP_RSTN BIT(1)
+#define B_BE_FEN_BBPLAT_RSTB BIT(0)
+
 #define R_BE_PLATFORM_ENABLE 0x0088
 #define B_BE_HOLD_AFTER_RESET BIT(11)
 #define B_BE_SYM_WLPLT_MEM_MUX_EN BIT(10)
@@ -3652,6 +3959,92 @@
 #define B_BE_WCPU_EN BIT(1)
 #define B_BE_PLATFORM_EN BIT(0)
 
+#define R_BE_WLLPS_CTRL 0x0090
+#define B_BE_LPSOP_BBMEMDS BIT(30)
+#define B_BE_LPSOP_BBOFF BIT(29)
+#define B_BE_LPSOP_MACOFF BIT(28)
+#define B_BE_LPSOP_OFF_CAPC_EN BIT(27)
+#define B_BE_LPSOP_MEM_DS BIT(26)
+#define B_BE_LPSOP_XTALM_LPS BIT(23)
+#define B_BE_LPSOP_XTAL BIT(22)
+#define B_BE_LPSOP_ACLK_DIV_2 BIT(21)
+#define B_BE_LPSOP_ACLK_SEL BIT(20)
+#define B_BE_LPSOP_ASWRM BIT(17)
+#define B_BE_LPSOP_ASWR BIT(16)
+#define B_BE_LPSOP_DSWR_ADJ_MASK GENMASK(15, 12)
+#define B_BE_LPSOP_DSWRSD BIT(10)
+#define B_BE_LPSOP_DSWRM BIT(9)
+#define B_BE_LPSOP_DSWR BIT(8)
+#define B_BE_LPSOP_OLD_ADJ_MASK GENMASK(7, 4)
+#define B_BE_FORCE_LEAVE_LPS BIT(3)
+#define B_BE_LPSOP_OLDSD BIT(2)
+#define B_BE_DIS_WLBT_LPSEN_LOPC BIT(1)
+#define B_BE_WL_LPS_EN BIT(0)
+
+#define R_BE_WLRESUME_CTRL 0x0094
+#define B_BE_LPSROP_DMEM5_RSU_EN BIT(31)
+#define B_BE_LPSROP_DMEM4_RSU_EN BIT(30)
+#define B_BE_LPSROP_DMEM3_RSU_EN BIT(29)
+#define B_BE_LPSROP_DMEM2_RSU_EN BIT(28)
+#define B_BE_LPSROP_DMEM1_RSU_EN BIT(27)
+#define B_BE_LPSROP_DMEM0_RSU_EN BIT(26)
+#define B_BE_LPSROP_IMEM5_RSU_EN BIT(25)
+#define B_BE_LPSROP_IMEM4_RSU_EN BIT(24)
+#define B_BE_LPSROP_IMEM3_RSU_EN BIT(23)
+#define B_BE_LPSROP_IMEM2_RSU_EN BIT(22)
+#define B_BE_LPSROP_IMEM1_RSU_EN BIT(21)
+#define B_BE_LPSROP_IMEM0_RSU_EN BIT(20)
+#define B_BE_LPSROP_BB1_W_BB0 BIT(14)
+#define B_BE_LPSROP_CMAC1 BIT(13)
+#define B_BE_LPSROP_CMAC0 BIT(12)
+#define B_BE_LPSROP_XTALM BIT(11)
+#define B_BE_LPSROP_PLLM BIT(10)
+#define B_BE_LPSROP_HIOE BIT(9)
+#define B_BE_LPSROP_CPU BIT(8)
+#define B_BE_LPSROP_LOWPWRPLL BIT(7)
+#define B_BE_LPSROP_DSWRSD_SEL_MASK GENMASK(5, 4)
+
+#define R_BE_EFUSE_CTRL_2_V1 0x00A4
+#define B_BE_EF_ENT BIT(31)
+#define B_BE_EF_TCOLUMN_EN BIT(29)
+#define B_BE_BT_OTP_PWC_DIS BIT(28)
+#define B_BE_EF_RDT BIT(27)
+#define B_BE_R_SYM_AUTOLOAD_WITH_PMC_SEL BIT(24)
+#define B_BE_EF_PGTS_MASK GENMASK(23, 20)
+#define B_BE_EF_BURST BIT(19)
+#define B_BE_EF_TEST_SEL_MASK GENMASK(18, 16)
+#define B_BE_EF_TROW_EN BIT(15)
+#define B_BE_EF_ERR_FLAG BIT(14)
+#define B_BE_EF_FBURST_DIS BIT(13)
+#define B_BE_EF_HT_SEL BIT(12)
+#define B_BE_EF_DSB_EN BIT(11)
+#define B_BE_EF_DLY_SEL_MASK GENMASK(3, 0)
+
+#define R_BE_PMC_DBG_CTRL2 0x00CC
+#define B_BE_EFUSE_BURN_GNT_MASK GENMASK(31, 24)
+#define B_BE_DIS_IOWRAP_TIMEOUT BIT(16)
+#define B_BE_STOP_WL_PMC BIT(9)
+#define B_BE_STOP_SYM_PMC BIT(8)
+#define B_BE_SYM_REG_PCIE_WRMSK BIT(7)
+#define B_BE_BT_ACCESS_WL_PAGE0 BIT(6)
+#define B_BE_R_BE_RST_WLPMC BIT(5)
+#define B_BE_R_BE_RST_PD12N BIT(4)
+#define B_BE_SYSON_DIS_WLR_BE_WRMSK BIT(3)
+#define B_BE_SYSON_DIS_PMCR_BE_WRMSK BIT(2)
+#define B_BE_SYSON_R_BE_ARB_MASK GENMASK(1, 0)
+
+#define R_BE_PCIE_MIO_INTF 0x00E4
+#define B_BE_AON_MIO_EPHY_1K_SEL_MASK GENMASK(29, 24)
+#define B_BE_PCIE_MIO_ADDR_PAGE_V1_MASK GENMASK(20, 16)
+#define B_BE_PCIE_MIO_ASIF BIT(15)
+#define B_BE_PCIE_MIO_BYIOREG BIT(13)
+#define B_BE_PCIE_MIO_RE BIT(12)
+#define B_BE_PCIE_MIO_WE_MASK GENMASK(11, 8)
+#define B_BE_PCIE_MIO_ADDR_MASK GENMASK(7, 0)
+
+#define R_BE_PCIE_MIO_INTD 0x00E8
+#define B_BE_PCIE_MIO_DATA_MASK GENMASK(31, 0)
+
 #define R_BE_HALT_H2C_CTRL 0x0160
 #define B_BE_HALT_H2C_TRIGGER BIT(0)
 
@@ -3676,6 +4069,82 @@
 
 #define R_BE_SECURE_BOOT_MALLOC_INFO 0x0184
 
+#define R_BE_FWS1IMR 0x0198
+#define B_BE_FS_RPWM_INT_EN_V1 BIT(24)
+#define B_BE_PCIE_HOTRST_EN BIT(22)
+#define B_BE_PCIE_SER_TIMEOUT_INDIC_EN BIT(21)
+#define B_BE_PCIE_RXI300_SLVTOUT_INDIC_EN BIT(20)
+#define B_BE_AON_PCIE_FLR_INT_EN BIT(19)
+#define B_BE_PCIE_ERR_INDIC_INT_EN BIT(18)
+#define B_BE_SDIO_ERR_INDIC_INT_EN BIT(17)
+#define B_BE_USB_ERR_INDIC_INT_EN BIT(16)
+#define B_BE_FS_GPIO27_INT_EN BIT(11)
+#define B_BE_FS_GPIO26_INT_EN BIT(10)
+#define B_BE_FS_GPIO25_INT_EN BIT(9)
+#define B_BE_FS_GPIO24_INT_EN BIT(8)
+#define B_BE_FS_GPIO23_INT_EN BIT(7)
+#define B_BE_FS_GPIO22_INT_EN BIT(6)
+#define B_BE_FS_GPIO21_INT_EN BIT(5)
+#define B_BE_FS_GPIO20_INT_EN BIT(4)
+#define B_BE_FS_GPIO19_INT_EN BIT(3)
+#define B_BE_FS_GPIO18_INT_EN BIT(2)
+#define B_BE_FS_GPIO17_INT_EN BIT(1)
+#define B_BE_FS_GPIO16_INT_EN BIT(0)
+
+#define R_BE_HIMR0 0x01A0
+#define B_BE_WDT_DATACPU_TIMEOUT_INT_EN BIT(25)
+#define B_BE_HALT_D2H_INT_EN BIT(24)
+#define B_BE_WDT_TIMEOUT_INT_EN BIT(22)
+#define B_BE_HALT_C2H_INT_EN BIT(21)
+#define B_BE_RON_INT_EN BIT(20)
+#define B_BE_PDNINT_EN BIT(19)
+#define B_BE_SPSANA_OCP_INT_EN BIT(18)
+#define B_BE_SPS_OCP_INT_EN BIT(17)
+#define B_BE_BTON_STS_UPDATE_INT_EN BIT(16)
+#define B_BE_GPIOF_INT_EN BIT(15)
+#define B_BE_GPIOE_INT_EN BIT(14)
+#define B_BE_GPIOD_INT_EN BIT(13)
+#define B_BE_GPIOC_INT_EN BIT(12)
+#define B_BE_GPIOB_INT_EN BIT(11)
+#define B_BE_GPIOA_INT_EN BIT(10)
+#define B_BE_GPIO9_INT_EN BIT(9)
+#define B_BE_GPIO8_INT_EN BIT(8)
+#define B_BE_GPIO7_INT_EN BIT(7)
+#define B_BE_GPIO6_INT_EN BIT(6)
+#define B_BE_GPIO5_INT_EN BIT(5)
+#define B_BE_GPIO4_INT_EN BIT(4)
+#define B_BE_GPIO3_INT_EN BIT(3)
+#define B_BE_GPIO2_INT_EN BIT(2)
+#define B_BE_GPIO1_INT_EN BIT(1)
+#define B_BE_GPIO0_INT_EN BIT(0)
+
+#define R_BE_HISR0 0x01A4
+#define B_BE_WDT_DATACPU_TIMEOUT_INT BIT(25)
+#define B_BE_HALT_D2H_INT BIT(24)
+#define B_BE_WDT_TIMEOUT_INT BIT(22)
+#define B_BE_HALT_C2H_INT BIT(21)
+#define B_BE_RON_INT BIT(20)
+#define B_BE_PDNINT BIT(19)
+#define B_BE_SPSANA_OCP_INT BIT(18)
+#define B_BE_SPS_OCP_INT BIT(17)
+#define B_BE_BTON_STS_UPDATE_INT BIT(16)
+#define B_BE_GPIOF_INT BIT(15)
+#define B_BE_GPIOE_INT BIT(14)
+#define B_BE_GPIOD_INT BIT(13)
+#define B_BE_GPIOC_INT BIT(12)
+#define B_BE_GPIOB_INT BIT(11)
+#define B_BE_GPIOA_INT BIT(10)
+#define B_BE_GPIO9_INT BIT(9)
+#define B_BE_GPIO8_INT BIT(8)
+#define B_BE_GPIO7_INT BIT(7)
+#define B_BE_GPIO6_INT BIT(6)
+#define B_BE_GPIO5_INT BIT(5)
+#define B_BE_GPIO4_INT BIT(4)
+#define B_BE_GPIO3_INT BIT(3)
+#define B_BE_GPIO2_INT BIT(2)
+#define B_BE_GPIO1_INT BIT(1)
+#define B_BE_GPIO0_INT BIT(0)
+
 #define R_BE_WCPU_FW_CTRL 0x01E0
 #define B_BE_RUN_ENV_MASK GENMASK(31, 30)
 #define B_BE_WCPU_FWDL_STATUS_MASK GENMASK(29, 26)
@@ -3721,6 +4190,78 @@
 #define R_BE_UDM2 0x01F8
 #define B_BE_UDM2_EPC_RA_MASK GENMASK(31, 0)
 
+#define R_BE_AFE_ON_CTRL0 0x0240
+#define B_BE_REG_LPF_R3_3_0_MASK GENMASK(31, 29)
+#define B_BE_REG_LPF_R2_MASK GENMASK(28, 24)
+#define B_BE_REG_LPF_C3_MASK GENMASK(23, 21)
+#define B_BE_REG_LPF_C2_MASK GENMASK(20, 18)
+#define B_BE_REG_LPF_C1_MASK GENMASK(17, 15)
+#define B_BE_REG_CP_ICPX2 BIT(14)
+#define B_BE_REG_CP_ICP_SEL_FAST_MASK GENMASK(13, 10)
+#define B_BE_REG_CP_ICP_SEL_MASK GENMASK(9, 6)
+#define B_BE_REG_IB_PI_MASK GENMASK(5, 4)
+#define B_BE_REG_CK_DEBUG_BT BIT(3)
+#define B_BE_EN_PC_LDO BIT(2)
+#define B_BE_LDO_VSEL_MASK GENMASK(1, 0)
+
+#define R_BE_AFE_ON_CTRL1 0x0244
+#define B_BE_REG_CK_MON_SEL_MASK GENMASK(31, 29)
+#define B_BE_REG_CK_MON_CK960M_EN BIT(28)
+#define B_BE_REG_XTAL_FREQ_SEL BIT(27)
+#define B_BE_REG_XTAL_EDGE_SEL BIT(26)
+#define B_BE_REG_VCO_KVCO BIT(25)
+#define B_BE_REG_SDM_EDGE_SEL BIT(24)
+#define B_BE_REG_SDM_CK_SEL BIT(23)
+#define B_BE_REG_SDM_CK_GATED BIT(22)
+#define B_BE_REG_PFD_RESET_GATED BIT(21)
+#define B_BE_REG_LPF_R3_FAST_MASK GENMASK(20, 16)
+#define B_BE_REG_LPF_R2_FAST_MASK GENMASK(15, 11)
+#define B_BE_REG_LPF_C3_FAST_MASK GENMASK(10, 8)
+#define B_BE_REG_LPF_C2_FAST_MASK GENMASK(7, 5)
+#define B_BE_REG_LPF_C1_FAST_MASK GENMASK(4, 2)
+#define B_BE_REG_LPF_R3_4_MASK GENMASK(1, 0)
+
+#define R_BE_AFE_ON_CTRL3 0x024C
+#define B_BE_LDO_VSEL_DA_1_MASK GENMASK(31, 30)
+#define B_BE_LDO_VSEL_DA_0_MASK GENMASK(29, 28)
+#define B_BE_LDO_VSEL_D2S_1_MASK GENMASK(27, 26)
+#define B_BE_LDO_VSEL_D2S_0_MASK GENMASK(25, 24)
+#define B_BE_LDO_VSEL_BUF_MASK GENMASK(23, 22)
+#define B_BE_REG_R2_L_MASK GENMASK(21, 19)
+#define B_BE_REG_R1_L_MASK GENMASK(18, 16)
+#define B_BE_REG_CK_DEBUG_BT_MON BIT(15)
+#define B_BE_REG_BT_CLK_BUF_POWER BIT(14)
+#define B_BE_REG_BG_OUT_BTADC_V1 BIT(13)
+#define B_BE_REG_SEL_V18 BIT(11)
+#define B_BE_REG_FRAC_EN BIT(10)
+#define B_BE_REG_CK1920M_EN BIT(9)
+#define B_BE_REG_CK1280M_EN BIT(8)
+#define B_BE_REG_12LDO_SEL_MASK GENMASK(7, 6)
+#define B_BE_REG_09LDO_SEL_MASK GENMASK(5, 4)
+#define B_BE_REG_VC_TH BIT(3)
+#define B_BE_REG_VC_TL BIT(2)
+#define B_BE_REG_CK40M_EN BIT(1)
+#define B_BE_REG_CK640M_EN BIT(0)
+
+#define R_BE_WLAN_XTAL_SI_CTRL 0x0270
+#define B_BE_WL_XTAL_SI_CMD_POLL BIT(31)
+#define B_BE_WL_XTAL_SI_CHIPID_MASK GENMASK(30, 28)
+#define B_BE_WL_XTAL_SI_MODE_MASK GENMASK(25, 24)
+#define B_BE_WL_XTAL_SI_BITMASK_MASK GENMASK(23, 16)
+#define B_BE_WL_XTAL_SI_DATA_MASK GENMASK(15, 8)
+#define B_BE_WL_XTAL_SI_ADDR_MASK GENMASK(7, 0)
+
+#define R_BE_IC_PWR_STATE 0x03F0
+#define B_BE_WHOLE_SYS_PWR_STE_MASK GENMASK(25, 16)
+#define MAC_AX_SYS_ACT 0x220
+#define B_BE_WLMAC_PWR_STE_MASK GENMASK(9, 8)
+#define B_BE_UART_HCISYS_PWR_STE_MASK GENMASK(7, 6)
+#define B_BE_SDIO_HCISYS_PWR_STE_MASK GENMASK(5, 4)
+#define B_BE_USB_HCISYS_PWR_STE_MASK GENMASK(3, 2)
+#define B_BE_PCIE_HCISYS_PWR_STE_MASK GENMASK(1, 0)
+
+#define R_BE_WLCPU_PORT_PC 0x03FC
+
 #define R_BE_DCPU_PLATFORM_ENABLE 0x0888
 #define B_BE_DCPU_SYM_DPLT_MEM_MUX_EN BIT(10)
 #define B_BE_DCPU_WARM_EN BIT(9)
@@ -3730,8 +4271,947 @@
 #define B_BE_DCPU_EN BIT(1)
 #define B_BE_DCPU_PLATFORM_EN BIT(0)
 
+#define R_BE_PL_AXIDMA_IDCT_MSK 0x0910
+#define B_BE_PL_AXIDMA_RRESP_ERR_MASK BIT(6)
+#define B_BE_PL_AXIDMA_BRESP_ERR_MASK BIT(5)
+#define B_BE_PL_AXIDMA_FC_ERR_MASK BIT(4)
+#define B_BE_PL_AXIDMA_TXBD_LEN0_MASK BIT(3)
+#define B_BE_PL_AXIDMA_TXBD_4KBOUD_LENERR_MASK BIT(2)
+#define B_BE_PL_AXIDMA_TXBD_RX_STUCK_MASK BIT(1)
+#define B_BE_PL_AXIDMA_TXBD_TX_STUCK_MASK BIT(0)
+#define B_BE_PL_AXIDMA_IDCT_MSK_CLR (B_BE_PL_AXIDMA_TXBD_TX_STUCK_MASK | \
+				     B_BE_PL_AXIDMA_TXBD_RX_STUCK_MASK | \
+				     B_BE_PL_AXIDMA_TXBD_LEN0_MASK | \
+				     B_BE_PL_AXIDMA_FC_ERR_MASK | \
+				     B_BE_PL_AXIDMA_BRESP_ERR_MASK | \
+				     B_BE_PL_AXIDMA_RRESP_ERR_MASK)
+#define B_BE_PL_AXIDMA_IDCT_MSK_SET (B_BE_PL_AXIDMA_TXBD_TX_STUCK_MASK | \
+				     B_BE_PL_AXIDMA_TXBD_RX_STUCK_MASK | \
+				     B_BE_PL_AXIDMA_TXBD_LEN0_MASK | \
+				     B_BE_PL_AXIDMA_FC_ERR_MASK)
+
+#define R_BE_PL_AXIDMA_IDCT 0x0914
+#define B_BE_PL_AXIDMA_RRESP_ERR BIT(6)
+#define B_BE_PL_AXIDMA_BRESP_ERR BIT(5)
+#define B_BE_PL_AXIDMA_FC_ERR BIT(4)
+#define B_BE_PL_AXIDMA_TXBD_LEN0 BIT(3)
+#define B_BE_PL_AXIDMA_TXBD_4KBOUD_LENERR BIT(2)
+#define B_BE_PL_AXIDMA_TXBD_RX_STUCK BIT(1)
+#define B_BE_PL_AXIDMA_TXBD_TX_STUCK BIT(0)
+
 #define R_BE_FILTER_MODEL_ADDR 0x0C04
 
+#define R_BE_WLAN_WDT 0x3050
+#define B_BE_WLAN_WDT_TIMEOUT BIT(31)
+#define B_BE_WLAN_WDT_TIMER_CLEAR BIT(4)
+#define B_BE_WLAN_WDT_BYPASS BIT(1)
+#define B_BE_WLAN_WDT_ENABLE BIT(0)
+
+#define R_BE_AXIDMA_WDT 0x305C
+#define B_BE_AXIDMA_WDT_TIMEOUT BIT(31)
+#define B_BE_AXIDMA_WDT_TIMER_CLEAR BIT(4)
+#define B_BE_AXIDMA_WDT_BYPASS BIT(1)
+#define B_BE_AXIDMA_WDT_ENABLE BIT(0)
+
+#define R_BE_AON_WDT 0x3068
+#define B_BE_AON_WDT_TIMEOUT BIT(31)
+#define B_BE_AON_WDT_TIMER_CLEAR BIT(4)
+#define B_BE_AON_WDT_BYPASS BIT(1)
+#define B_BE_AON_WDT_ENABLE BIT(0)
+
+#define R_BE_AON_WDT_TMR 0x306C
+#define R_BE_MDIO_WDT_TMR 0x3090
+#define R_BE_LA_MODE_WDT_TMR 0x309C
+#define R_BE_WDT_AR_TMR 0x3144
+#define R_BE_WDT_AW_TMR 0x3150
+#define R_BE_WLAN_WDT_TMR 0x3054
+#define R_BE_WDT_W_TMR 0x315C
+#define R_BE_AXIDMA_WDT_TMR 0x3060
+#define R_BE_WDT_B_TMR 0x3164
+#define R_BE_WDT_R_TMR 0x316C
+#define R_BE_LOCAL_WDT_TMR 0x3084
+
+#define R_BE_LOCAL_WDT 0x3080
+#define B_BE_LOCAL_WDT_TIMEOUT BIT(31)
+#define B_BE_LOCAL_WDT_TIMER_CLEAR BIT(4)
+#define B_BE_LOCAL_WDT_BYPASS BIT(1)
+#define B_BE_LOCAL_WDT_ENABLE BIT(0)
+
+#define R_BE_MDIO_WDT 0x308C
+#define B_BE_MDIO_WDT_TIMEOUT BIT(31)
+#define B_BE_MDIO_WDT_TIMER_CLEAR BIT(4)
+#define B_BE_MDIO_WDT_BYPASS BIT(1)
+#define B_BE_MDIO_WDT_ENABLE BIT(0)
+
+#define R_BE_LA_MODE_WDT 0x3098
+#define B_BE_LA_MODE_WDT_TIMEOUT BIT(31)
+#define B_BE_LA_MODE_WDT_TIMER_CLEAR BIT(4)
+#define B_BE_LA_MODE_WDT_BYPASS BIT(1)
+#define B_BE_LA_MODE_WDT_ENABLE BIT(0)
+
+#define R_BE_WDT_AR 0x3140
+#define B_BE_WDT_AR_TIMEOUT BIT(31)
+#define B_BE_WDT_AR_TIMER_CLEAR BIT(4)
+#define B_BE_WDT_AR_BYPASS BIT(1)
+#define B_BE_WDT_AR_ENABLE BIT(0)
+
+#define R_BE_WDT_AW 0x314C
+#define B_BE_WDT_AW_TIMEOUT BIT(31)
+#define B_BE_WDT_AW_TIMER_CLEAR BIT(4)
+#define B_BE_WDT_AW_BYPASS BIT(1)
+#define B_BE_WDT_AW_ENABLE BIT(0)
+
+#define R_BE_WDT_W 0x3158
+#define B_BE_WDT_W_TIMEOUT BIT(31)
+#define B_BE_WDT_W_TIMER_CLEAR BIT(4)
+#define B_BE_WDT_W_BYPASS BIT(1)
+#define B_BE_WDT_W_ENABLE BIT(0)
+
+#define R_BE_WDT_B 0x3160
+#define B_BE_WDT_B_TIMEOUT BIT(31)
+#define B_BE_WDT_B_TIMER_CLEAR BIT(4)
+#define B_BE_WDT_B_BYPASS BIT(1)
+#define B_BE_WDT_B_ENABLE BIT(0)
+
+#define R_BE_WDT_R 0x3168
+#define B_BE_WDT_R_TIMEOUT BIT(31)
+#define B_BE_WDT_R_TIMER_CLEAR BIT(4)
+#define B_BE_WDT_R_BYPASS BIT(1)
+#define B_BE_WDT_R_ENABLE BIT(0)
+
+#define R_BE_LTR_DECISION_CTRL_V1 0x3610
+#define B_BE_ENABLE_LTR_CTL_DECISION BIT(31)
+#define B_BE_LAT_LTR_IDX_DRV_VLD_V1 BIT(24)
+#define B_BE_LAT_LTR_IDX_DRV_V1_MASK GENMASK(23, 22)
+#define B_BE_LAT_LTR_IDX_FW_VLD_V1 BIT(21)
+#define B_BE_LAT_LTR_IDX_FW_V1_MASK GENMASK(20, 19)
+#define B_BE_LAT_LTR_IDX_HW_VLD_V1 BIT(18)
+#define B_BE_LAT_LTR_IDX_HW_V1_MASK GENMASK(17, 16)
+#define B_BE_LTR_IDX_DRV_V1_MASK GENMASK(15, 14)
+#define B_BE_LTR_REQ_DRV_V1 BIT(13)
+#define B_BE_LTR_IDX_DISABLE_V1_MASK GENMASK(9, 8)
+#define B_BE_LTR_EN_PORT_V1_MASK GENMASK(6, 4)
+#define B_BE_LTR_DRV_DEC_EN_V1 BIT(6)
+#define B_BE_LTR_FW_DEC_EN_V1 BIT(5)
+#define B_BE_LTR_HW_DEC_EN_V1 BIT(4)
+#define B_BE_LTR_SPACE_IDX_MASK GENMASK(1, 0)
+
+#define R_BE_LTR_LATENCY_IDX0_V1 0x3614
+#define R_BE_LTR_LATENCY_IDX1_V1 0x3618
+#define R_BE_LTR_LATENCY_IDX2_V1 0x361C
+#define R_BE_LTR_LATENCY_IDX3_V1 0x3620
+
+#define R_BE_HCI_FUNC_EN 0x7880
+#define B_BE_HCI_CR_PROTECT BIT(31)
+#define B_BE_HCI_TRXBUF_EN BIT(2)
+#define B_BE_HCI_RXDMA_EN BIT(1)
+#define B_BE_HCI_TXDMA_EN BIT(0)
+
+#define R_BE_DMAC_FUNC_EN 0x8400
+#define B_BE_DMAC_CRPRT BIT(31)
+#define B_BE_MAC_FUNC_EN BIT(30)
+#define B_BE_DMAC_FUNC_EN BIT(29)
+#define B_BE_MPDU_PROC_EN BIT(28)
+#define B_BE_WD_RLS_EN BIT(27)
+#define B_BE_DLE_WDE_EN BIT(26)
+#define B_BE_TXPKT_CTRL_EN BIT(25)
+#define B_BE_STA_SCH_EN BIT(24)
+#define B_BE_DLE_PLE_EN BIT(23)
+#define B_BE_PKT_BUF_EN BIT(22)
+#define B_BE_DMAC_TBL_EN BIT(21)
+#define B_BE_PKT_IN_EN BIT(20)
+#define B_BE_DLE_CPUIO_EN BIT(19)
+#define B_BE_DISPATCHER_EN BIT(18)
+#define B_BE_BBRPT_EN BIT(17)
+#define B_BE_MAC_SEC_EN BIT(16)
+#define B_BE_DMACREG_GCKEN BIT(15)
+#define B_BE_H_AXIDMA_EN BIT(14)
+#define B_BE_DMAC_MLO_EN BIT(11)
+#define B_BE_PLRLS_EN BIT(10)
+#define B_BE_P_AXIDMA_EN BIT(9)
+#define B_BE_DLE_DATACPUIO_EN BIT(8)
+#define B_BE_LTR_CTL_EN BIT(7)
+
+#define R_BE_DMAC_CLK_EN 0x8404
+#define B_BE_MAC_CKEN BIT(30)
+#define B_BE_DMAC_CKEN BIT(29)
+#define B_BE_MPDU_CKEN BIT(28)
+#define B_BE_WD_RLS_CLK_EN BIT(27)
+#define B_BE_DLE_WDE_CLK_EN BIT(26)
+#define B_BE_TXPKT_CTRL_CLK_EN BIT(25)
+#define B_BE_STA_SCH_CLK_EN BIT(24)
+#define B_BE_DLE_PLE_CLK_EN BIT(23)
+#define B_BE_PKTBUF_CKEN BIT(22)
+#define B_BE_DMAC_TABLE_CLK_EN BIT(21)
+#define B_BE_PKT_IN_CLK_EN BIT(20)
+#define B_BE_DLE_CPUIO_CLK_EN BIT(19)
+#define B_BE_DISPATCHER_CLK_EN BIT(18)
+#define B_BE_BBRPT_CLK_EN BIT(17)
+#define B_BE_MAC_SEC_CLK_EN BIT(16)
+#define B_BE_H_AXIDMA_CKEN BIT(14)
+#define B_BE_DMAC_MLO_CKEN BIT(11)
+#define B_BE_PLRLS_CKEN BIT(10)
+#define B_BE_P_AXIDMA_CKEN BIT(9)
+#define B_BE_DLE_DATACPUIO_CKEN BIT(8)
+
+#define R_BE_LTR_CTRL_0 0x8410
+#define B_BE_LTR_REQ_FW BIT(18)
+#define B_BE_LTR_IDX_FW_MASK GENMASK(17, 16)
+#define B_BE_LTR_IDLE_TIMER_IDX_MASK GENMASK(10, 8)
+#define B_BE_LTR_WD_NOEMP_CHK BIT(1)
+#define B_BE_LTR_HW_EN BIT(0)
+
+#define R_BE_LTR_CFG_0 0x8414
+#define B_BE_LTR_IDX_DISABLE_MASK GENMASK(17, 16)
+#define B_BE_LTR_IDX_IDLE_MASK GENMASK(15, 14)
+#define B_BE_LTR_IDX_ACTIVE_MASK GENMASK(13, 12)
+#define B_BE_LTR_IDLE_TIMER_IDX_MASK GENMASK(10, 8)
+#define B_BE_EN_LTR_CMAC_RX_USE_PG_CHK BIT(3)
+#define B_BE_EN_LTR_WD_NON_EMPTY_CHK BIT(2)
+#define B_BE_EN_LTR_HAXIDMA_TX_IDLE_CHK BIT(1)
+#define B_BE_EN_LTR_HAXIDMA_RX_IDLE_CHK BIT(0)
+
+#define R_BE_LTR_CFG_1 0x8418
+#define B_BE_LTR_CMAC1_RX_USE_PG_TH_MASK GENMASK(27, 16)
+#define B_BE_LTR_CMAC0_RX_USE_PG_TH_MASK GENMASK(11, 0)
+
+#define R_BE_DMAC_TABLE_CTRL 0x8420
+#define B_BE_HWAMSDU_PADDING_MODE BIT(31)
+#define B_BE_MACID_MPDU_PROCESSOR_OFFSET_MASK GENMASK(26, 16)
+#define B_BE_DMAC_ADDR_MODE BIT(12)
+#define B_BE_DMAC_CTRL_INFO_SER_IO BIT(11)
+#define B_BE_DMAC_CTRL_INFO_OFFSET_MASK GENMASK(10, 0)
+
+#define R_BE_SER_DBG_INFO 0x8424
+#define B_BE_SER_L0_PROMOTE_L1_EVENT_MASK GENMASK(31, 28)
+#define B_BE_SER_L1_COUNTER_MASK GENMASK(27, 24)
+#define B_BE_RMAC_PPDU_HANG_CNT_MASK GENMASK(23, 16)
+#define B_BE_SER_L0_COUNTER_MASK GENMASK(8, 0)
+
+#define R_BE_DLE_EMPTY0 0x8430
+#define B_BE_PLE_EMPTY_QTA_DMAC_H2D BIT(27)
+#define B_BE_PLE_EMPTY_QTA_DMAC_CPUIO BIT(26)
+#define B_BE_PLE_EMPTY_QTA_DMAC_MPDU_TX BIT(25)
+#define B_BE_PLE_EMPTY_QTA_DMAC_WLAN_CPU BIT(24)
+#define B_BE_PLE_EMPTY_QTA_DMAC_H2C BIT(23)
+#define B_BE_PLE_EMPTY_QTA_DMAC_B1_TXPL BIT(22)
+#define B_BE_PLE_EMPTY_QTA_DMAC_B0_TXPL BIT(21)
+#define B_BE_WDE_EMPTY_QTA_DMAC_CPUIO BIT(20)
+#define B_BE_WDE_EMPTY_QTA_DMAC_PKTIN BIT(19)
+#define B_BE_WDE_EMPTY_QTA_DMAC_DATA_CPU BIT(18)
+#define B_BE_WDE_EMPTY_QTA_DMAC_WLAN_CPU BIT(17)
+#define B_BE_WDE_EMPTY_QTA_DMAC_HIF BIT(16)
+#define B_BE_WDE_EMPTY_QUE_CMAC_B1_HIQ BIT(15)
+#define B_BE_WDE_EMPTY_QUE_CMAC_B1_MBH BIT(14)
+#define B_BE_WDE_EMPTY_QUE_CMAC_B0_OTHERS BIT(13)
+#define B_BE_WDE_EMPTY_QUE_DMAC_MLO_ACQ BIT(12)
+#define B_BE_WDE_EMPTY_QUE_DMAC_MLO_MISC BIT(11)
+#define B_BE_WDE_EMPTY_QUE_DMAC_PKTIN BIT(10)
+#define B_BE_PLE_EMPTY_QUE_DMAC_SEC_TX BIT(9)
+#define B_BE_PLE_EMPTY_QUE_DMAC_MPDU_TX BIT(8)
+#define B_BE_WDE_EMPTY_QUE_OTHERS BIT(7)
+#define B_BE_WDE_EMPTY_QUE_CMAC_WMM3 BIT(6)
+#define B_BE_WDE_EMPTY_QUE_CMAC_WMM2 BIT(5)
+#define B_BE_WDE_EMPTY_QUE_CMAC0_WMM1 BIT(4)
+#define B_BE_WDE_EMPTY_QUE_CMAC0_WMM0 BIT(3)
+#define B_BE_WDE_EMPTY_QUE_CMAC1_MBH BIT(2)
+#define B_BE_WDE_EMPTY_QUE_CMAC0_MBH BIT(1)
+#define B_BE_WDE_EMPTY_QUE_CMAC0_ALL_AC BIT(0)
+
+#define R_BE_DLE_EMPTY1 0x8434
+#define B_BE_PLE_EMPTY_QTA_CMAC_DMA_TXRPT BIT(21)
+#define B_BE_PLE_EMPTY_QTA_DMAC_WDRLS BIT(20)
+#define B_BE_PLE_EMPTY_QTA_CMAC1_DMA_BBRPT BIT(19)
+#define B_BE_PLE_EMPTY_QTA_CMAC1_DMA_RX BIT(18)
+#define B_BE_PLE_EMPTY_QTA_CMAC0_DMA_RX BIT(17)
+#define B_BE_PLE_EMPTY_QTA_DMAC_C2H BIT(16)
+#define B_BE_PLE_EMPTY_QUE_DMAC_PLRLS BIT(5)
+#define B_BE_PLE_EMPTY_QUE_DMAC_CPUIO BIT(4)
+#define B_BE_PLE_EMPTY_QUE_DMAC_SEC_RX BIT(3)
+#define B_BE_PLE_EMPTY_QUE_DMAC_MPDU_RX BIT(2)
+#define B_BE_PLE_EMPTY_QUE_DMAC_HDP BIT(1)
+#define B_BE_WDE_EMPTY_QUE_DMAC_WDRLS BIT(0)
+
+#define R_BE_SER_L1_DBG_CNT_0 0x8440
+#define B_BE_SER_L1_WDRLS_CNT_MASK GENMASK(31, 24)
+#define B_BE_SER_L1_SEC_CNT_MASK GENMASK(23, 16)
+#define B_BE_SER_L1_MPDU_CNT_MASK GENMASK(15, 8)
+#define B_BE_SER_L1_STA_SCH_CNT_MASK GENMASK(7, 0)
+
+#define R_BE_SER_L1_DBG_CNT_1 0x8444
+#define B_BE_SER_L1_WDE_CNT_MASK GENMASK(31, 24)
+#define B_BE_SER_L1_TXPKTCTRL_CNT_MASK GENMASK(23, 16)
+#define B_BE_SER_L1_PLE_CNT_MASK GENMASK(15, 8)
+#define B_BE_SER_L1_PKTIN_CNT_MASK GENMASK(7, 0)
+
+#define R_BE_SER_L1_DBG_CNT_2 0x8448
+#define B_BE_SER_L1_DISP_CNT_MASK GENMASK(31, 24)
+#define B_BE_SER_L1_APB_BRIDGE_CNT_MASK GENMASK(23, 16)
+#define B_BE_SER_L1_DLE_W_CPUIO_CNT_MASK GENMASK(15, 8)
+#define B_BE_SER_L1_BBRPT_CNT_MASK GENMASK(7, 0)
+
+#define R_BE_SER_L1_DBG_CNT_3 0x844C
+#define B_BE_SER_L1_HCI_BUF_CNT_MASK GENMASK(31, 24)
+#define B_BE_SER_L1_P_AXIDMA_CNT_MASK GENMASK(23, 16)
+#define B_BE_SER_L1_H_AXIDMA_CNT_MASK GENMASK(15, 8)
+#define B_BE_SER_L1_MLO_ERR_CNT_MASK GENMASK(7, 0)
+
+#define R_BE_SER_L1_DBG_CNT_4 0x8450
+#define B_BE_SER_L1_PLDRLS_ERR_CNT_MASK GENMASK(31, 24)
+#define B_BE_SER_L1_DLE_D_CPUIO_CNT_MASK GENMASK(23, 16)
+
+#define R_BE_SER_L1_DBG_CNT_5 0x8454
+#define B_BE_SER_L1_DBG_0_MASK GENMASK(31, 0)
+
+#define R_BE_SER_L1_DBG_CNT_6 0x8458
+#define B_BE_SER_L1_DBG_1_MASK GENMASK(31, 0)
+
+#define R_BE_SER_L1_DBG_CNT_7 0x845C
+#define B_BE_SER_L1_DBG_2_MASK GENMASK(31, 0)
+
+#define R_BE_DMAC_ERR_IMR 0x8520
+#define B_BE_DMAC_NOTX_ERR_INT_EN BIT(21)
+#define B_BE_DMAC_NORX_ERR_INT_EN BIT(20)
+#define B_BE_DLE_DATACPUIO_ERR_INT_EN BIT(19)
+#define B_BE_PLRSL_ERR_INT_EN BIT(18)
+#define B_BE_MLO_ERR_INT_EN BIT(17)
+#define B_BE_DMAC_FW_ERR_INT_EN BIT(16)
+#define B_BE_H_AXIDMA_ERR_INT_EN BIT(14)
+#define B_BE_P_AXIDMA_ERR_INT_EN BIT(13)
+#define B_BE_HCI_BUF_ERR_INT_EN BIT(12)
+#define B_BE_BBRPT_ERR_INT_EN BIT(11)
+#define B_BE_DLE_CPUIO_ERR_INT_EN BIT(10)
+#define B_BE_APB_BRIDGE_ERR_INT_EN BIT(9)
+#define B_BE_DISPATCH_ERR_INT_EN BIT(8)
+#define B_BE_PKTIN_ERR_INT_EN BIT(7)
+#define B_BE_PLE_DLE_ERR_INT_EN BIT(6)
+#define B_BE_TXPKTCTRL_ERR_INT_EN BIT(5)
+#define B_BE_WDE_DLE_ERR_INT_EN BIT(4)
+#define B_BE_STA_SCHEDULER_ERR_INT_EN BIT(3)
+#define B_BE_MPDU_ERR_INT_EN BIT(2)
+#define B_BE_WSEC_ERR_INT_EN BIT(1)
+#define B_BE_WDRLS_ERR_INT_EN BIT(0)
+
+#define R_BE_DMAC_ERR_ISR 0x8524
+#define B_BE_DLE_DATACPUIO_ERR_INT BIT(19)
+#define B_BE_PLRLS_ERR_INT BIT(18)
+#define B_BE_MLO_ERR_INT BIT(17)
+#define B_BE_DMAC_FW_ERR_IDCT BIT(16)
+#define B_BE_H_AXIDMA_ERR_INT BIT(14)
+#define B_BE_P_AXIDMA_ERR_INT BIT(13)
+#define B_BE_HCI_BUF_ERR_FLAG BIT(12)
+#define B_BE_BBRPT_ERR_FLAG BIT(11)
+#define B_BE_DLE_CPUIO_ERR_FLAG BIT(10)
+#define B_BE_APB_BRIDGE_ERR_FLAG BIT(9)
+#define B_BE_DISPATCH_ERR_FLAG BIT(8)
+#define B_BE_PKTIN_ERR_FLAG BIT(7)
+#define B_BE_PLE_DLE_ERR_FLAG BIT(6)
+#define B_BE_TXPKTCTRL_ERR_FLAG BIT(5)
+#define B_BE_WDE_DLE_ERR_FLAG BIT(4)
+#define B_BE_STA_SCHEDULER_ERR_FLAG BIT(3)
+#define B_BE_MPDU_ERR_FLAG BIT(2)
+#define B_BE_WSEC_ERR_FLAG BIT(1)
+#define B_BE_WDRLS_ERR_FLAG BIT(0)
+
+#define R_BE_DISP_ERROR_ISR0 0x8804
+#define B_BE_REUSE_SIZE_ERR BIT(31)
+#define B_BE_REUSE_EN_ERR BIT(30)
+#define B_BE_STF_OQT_UNDERFLOW_ERR BIT(29)
+#define B_BE_STF_OQT_OVERFLOW_ERR BIT(28)
+#define B_BE_STF_WRFF_UNDERFLOW_ERR BIT(27)
+#define B_BE_STF_WRFF_OVERFLOW_ERR BIT(26)
+#define B_BE_STF_CMD_UNDERFLOW_ERR BIT(25)
+#define B_BE_STF_CMD_OVERFLOW_ERR BIT(24)
+#define B_BE_REUSE_SIZE_ZERO_ERR BIT(23)
+#define B_BE_REUSE_PKT_CNT_ERR BIT(22)
+#define B_BE_CDT_PTR_TIMEOUT_ERR BIT(21)
+#define B_BE_CDT_HCI_TIMEOUT_ERR BIT(20)
+#define B_BE_HDT_PTR_TIMEOUT_ERR BIT(19)
+#define B_BE_HDT_HCI_TIMEOUT_ERR BIT(18)
+#define B_BE_CDT_ADDR_INFO_LEN_ERR BIT(17)
+#define B_BE_HDT_ADDR_INFO_LEN_ERR BIT(16)
+#define B_BE_CDR_DMA_TIMEOUT_ERR BIT(15)
+#define B_BE_CDR_RX_TIMEOUT_ERR BIT(14)
+#define B_BE_PLE_OUTPUT_ERR BIT(12)
+#define B_BE_PLE_RESPOSE_ERR BIT(11)
+#define B_BE_PLE_BURST_NUM_ERR BIT(10)
+#define B_BE_PLE_NULL_PKT_ERR BIT(9)
+#define B_BE_PLE_FLOW_CTRL_ERR BIT(8)
+#define B_BE_HDR_DMA_TIMEOUT_ERR BIT(7)
+#define B_BE_HDR_RX_TIMEOUT_ERR BIT(6)
+#define B_BE_WDE_OUTPUT_ERR BIT(4)
+#define B_BE_WDE_RESPONSE_ERR BIT(3)
+#define B_BE_WDE_BURST_NUM_ERR BIT(2)
+#define B_BE_WDE_NULL_PKT_ERR BIT(1)
+#define B_BE_WDE_FLOW_CTRL_ERR BIT(0)
+
+#define R_BE_DISP_ERROR_ISR1 0x8808
+#define B_BE_HR_WRFF_UNDERFLOW_ERR BIT(31)
+#define B_BE_HR_WRFF_OVERFLOW_ERR BIT(30)
+#define B_BE_HR_CHKSUM_FSM_ERR BIT(29)
+#define B_BE_HR_SHIFT_DMA_CFG_ERR BIT(28)
+#define B_BE_HR_DMA_PROCESS_ERR BIT(27)
+#define B_BE_HR_TOTAL_LEN_UNDER_ERR BIT(26)
+#define B_BE_HR_SHIFT_EN_ERR BIT(25)
+#define B_BE_HR_AGG_CFG_ERR BIT(24)
+#define B_BE_HR_PLD_LEN_ZERO_ERR BIT(22)
+#define B_BE_HT_ILL_CH_ERR BIT(20)
+#define B_BE_HT_ADDR_INFO_LEN_ERR BIT(18)
+#define B_BE_HT_WD_LEN_OVER_ERR BIT(17)
+#define B_BE_HT_PLD_CMD_UNDERFLOW_ERR BIT(16)
+#define B_BE_HT_PLD_CMD_OVERFLOW_ERR BIT(15)
+#define B_BE_HT_WRFF_UNDERFLOW_ERR BIT(14)
+#define B_BE_HT_WRFF_OVERFLOW_ERR BIT(13)
+#define B_BE_HT_CHKSUM_FSM_ERR BIT(12)
+#define B_BE_HT_NON_IDLE_PKT_STR_ERR BIT(11)
+#define B_BE_HT_PRE_SUB_BE_ERR BIT(10)
+#define B_BE_HT_WD_CHKSUM_ERR BIT(9)
+#define B_BE_HT_CHANNEL_DMA_ERR BIT(8)
+#define B_BE_HT_OFFSET_UNMATCH_ERR BIT(7)
+#define B_BE_HT_PAYLOAD_UNDER_ERR BIT(6)
+#define B_BE_HT_PAYLOAD_OVER_ERR BIT(5)
+#define B_BE_HT_PERMU_FF_UNDERFLOW_ERR BIT(4)
+#define B_BE_HT_PERMU_FF_OVERFLOW_ERR BIT(3)
+#define B_BE_HT_PKT_FAIL_ERR BIT(2)
+#define B_BE_HT_CH_ID_ERR BIT(1)
+#define B_BE_HT_EP_CH_DIFF_ERR BIT(0)
+
+#define R_BE_DISP_ERROR_ISR2 0x880C
+#define B_BE_CR_PLD_LEN_ERR BIT(30)
+#define B_BE_CR_WRFF_UNDERFLOW_ERR BIT(29)
+#define B_BE_CR_WRFF_OVERFLOW_ERR BIT(28)
+#define B_BE_CR_SHIFT_DMA_CFG_ERR BIT(27)
+#define B_BE_CR_DMA_PROCESS_ERR BIT(26)
+#define B_BE_CR_SHIFT_EN_ERR BIT(24)
+#define B_BE_REUSE_FIFO_B_UNDER_ERR BIT(22)
+#define B_BE_REUSE_FIFO_B_OVER_ERR BIT(21)
+#define B_BE_REUSE_FIFO_A_UNDER_ERR BIT(20)
+#define B_BE_REUSE_FIFO_A_OVER_ERR BIT(19)
+#define B_BE_CT_ADDR_INFO_LEN_MISS_ERR BIT(17)
+#define B_BE_CT_WD_LEN_OVER_ERR BIT(16)
+#define B_BE_CT_F2P_SEQ_ERR BIT(15)
+#define B_BE_CT_F2P_QSEL_ERR BIT(14)
+#define B_BE_CT_PLD_CMD_UNDERFLOW_ERR BIT(13)
+#define B_BE_CT_PLD_CMD_OVERFLOW_ERR BIT(12)
+#define B_BE_CT_PRE_SUB_ERR BIT(11)
+#define B_BE_CT_WD_CHKSUM_ERR BIT(10)
+#define B_BE_CT_CHANNEL_DMA_ERR BIT(9)
+#define B_BE_CT_OFFSET_UNMATCH_ERR BIT(8)
+#define B_BE_F2P_TOTAL_NUM_ERR BIT(7)
+#define B_BE_CT_PAYLOAD_UNDER_ERR BIT(6)
+#define B_BE_CT_PAYLOAD_OVER_ERR BIT(5)
+#define B_BE_CT_PERMU_FF_UNDERFLOW_ERR BIT(4)
+#define B_BE_CT_PERMU_FF_OVERFLOW_ERR BIT(3)
+#define B_BE_CT_CH_ID_ERR BIT(2)
+#define B_BE_CT_EP_CH_DIFF_ERR BIT(0)
+
+#define R_BE_DISP_OTHER_IMR 0x8870
+#define B_BE_REUSE_SIZE_ERR_INT_EN BIT(31)
+#define B_BE_REUSE_EN_ERR_INT_EN BIT(30)
+#define B_BE_STF_OQT_UNDERFLOW_ERR_INT_EN BIT(29)
+#define B_BE_STF_OQT_OVERFLOW_ERR_INT_EN BIT(28)
+#define B_BE_STF_WRFF_UNDERFLOW_ERR_INT_EN BIT(27)
+#define B_BE_STF_WRFF_OVERFLOW_ERR_INT_EN BIT(26)
+#define B_BE_STF_CMD_UNDERFLOW_ERR_INT_EN BIT(25)
+#define B_BE_STF_CMD_OVERFLOW_ERR_INT_EN BIT(24)
+#define B_BE_REUSE_SIZE_ZERO_ERR_INT_EN BIT(23)
+#define B_BE_REUSE_PKT_CNT_ERR_INT_EN BIT(22)
+#define B_BE_CDT_PTR_TIMEOUT_ERR_INT_EN BIT(21)
+#define B_BE_CDT_HCI_TIMEOUT_ERR_INT_EN BIT(20)
+#define B_BE_HDT_PTR_TIMEOUT_ERR_INT_EN BIT(19)
+#define B_BE_HDT_HCI_TIMEOUT_ERR_INT_EN BIT(18)
+#define B_BE_CDT_ADDR_INFO_LEN_ERR_INT_EN BIT(17)
+#define B_BE_HDT_ADDR_INFO_LEN_ERR_INT_EN BIT(16)
+#define B_BE_CDR_DMA_TIMEOUT_ERR_INT_EN BIT(15)
+#define B_BE_CDR_RX_TIMEOUT_ERR_INT_EN BIT(14)
+#define B_BE_PLE_OUTPUT_ERR_INT_EN BIT(12)
+#define B_BE_PLE_RESPOSE_ERR_INT_EN BIT(11)
+#define B_BE_PLE_BURST_NUM_ERR_INT_EN BIT(10)
+#define B_BE_PLE_NULL_PKT_ERR_INT_EN BIT(9)
+#define B_BE_PLE_FLOW_CTRL_ERR_INT_EN BIT(8)
+#define B_BE_HDR_DMA_TIMEOUT_ERR_INT_EN BIT(7)
+#define B_BE_HDR_RX_TIMEOUT_ERR_INT_EN BIT(6)
+#define B_BE_WDE_OUTPUT_ERR_INT_EN BIT(4)
+#define B_BE_WDE_RESPONSE_ERR_INT_EN BIT(3)
+#define B_BE_WDE_BURST_NUM_ERR_INT_EN BIT(2)
+#define B_BE_WDE_NULL_PKT_ERR_INT_EN BIT(1)
+#define B_BE_WDE_FLOW_CTRL_ERR_INT_EN BIT(0)
+#define B_BE_DISP_OTHER_IMR_CLR (B_BE_WDE_FLOW_CTRL_ERR_INT_EN | \
+				 B_BE_WDE_NULL_PKT_ERR_INT_EN | \
+				 B_BE_WDE_BURST_NUM_ERR_INT_EN | \
+				 B_BE_WDE_RESPONSE_ERR_INT_EN | \
+				 B_BE_WDE_OUTPUT_ERR_INT_EN | \
+				 B_BE_HDR_RX_TIMEOUT_ERR_INT_EN | \
+				 B_BE_HDR_DMA_TIMEOUT_ERR_INT_EN | \
+				 B_BE_PLE_FLOW_CTRL_ERR_INT_EN | \
+				 B_BE_PLE_NULL_PKT_ERR_INT_EN | \
+				 B_BE_PLE_BURST_NUM_ERR_INT_EN | \
+				 B_BE_PLE_RESPOSE_ERR_INT_EN | \
+				 B_BE_PLE_OUTPUT_ERR_INT_EN | \
+				 B_BE_CDR_RX_TIMEOUT_ERR_INT_EN | \
+				 B_BE_CDR_DMA_TIMEOUT_ERR_INT_EN | \
+				 B_BE_HDT_ADDR_INFO_LEN_ERR_INT_EN | \
+				 B_BE_CDT_ADDR_INFO_LEN_ERR_INT_EN | \
+				 B_BE_HDT_HCI_TIMEOUT_ERR_INT_EN | \
+				 B_BE_HDT_PTR_TIMEOUT_ERR_INT_EN | \
+				 B_BE_CDT_HCI_TIMEOUT_ERR_INT_EN | \
+				 B_BE_CDT_PTR_TIMEOUT_ERR_INT_EN | \
+				 B_BE_REUSE_PKT_CNT_ERR_INT_EN | \
+				 B_BE_REUSE_SIZE_ZERO_ERR_INT_EN | \
+				 B_BE_STF_CMD_OVERFLOW_ERR_INT_EN | \
+				 B_BE_STF_CMD_UNDERFLOW_ERR_INT_EN | \
+				 B_BE_STF_WRFF_OVERFLOW_ERR_INT_EN | \
+				 B_BE_STF_WRFF_UNDERFLOW_ERR_INT_EN | \
+				 B_BE_STF_OQT_OVERFLOW_ERR_INT_EN | \
+				 B_BE_STF_OQT_UNDERFLOW_ERR_INT_EN | \
+				 B_BE_REUSE_EN_ERR_INT_EN | \
+				 B_BE_REUSE_SIZE_ERR_INT_EN)
+#define B_BE_DISP_OTHER_IMR_SET (B_BE_STF_CMD_OVERFLOW_ERR_INT_EN | \
+				 B_BE_STF_CMD_UNDERFLOW_ERR_INT_EN | \
+				 B_BE_STF_WRFF_OVERFLOW_ERR_INT_EN | \
+				 B_BE_STF_WRFF_UNDERFLOW_ERR_INT_EN | \
+				 B_BE_STF_OQT_OVERFLOW_ERR_INT_EN | \
+				 B_BE_STF_OQT_UNDERFLOW_ERR_INT_EN)
+
+#define R_BE_DISP_HOST_IMR 0x8874
+#define B_BE_HR_WRFF_UNDERFLOW_ERR_INT_EN BIT(31)
+#define B_BE_HR_WRFF_OVERFLOW_ERR_INT_EN BIT(30)
+#define B_BE_HR_CHKSUM_FSM_ERR_INT_EN BIT(29)
+#define B_BE_HR_SHIFT_DMA_CFG_ERR_INT_EN BIT(28)
+#define B_BE_HR_DMA_PROCESS_ERR_INT_EN BIT(27)
+#define B_BE_HR_TOTAL_LEN_UNDER_ERR_INT_EN BIT(26)
+#define B_BE_HR_SHIFT_EN_ERR_INT_EN BIT(25)
+#define B_BE_HR_AGG_CFG_ERR_INT_EN BIT(24)
+#define B_BE_HR_PLD_LEN_ZERO_ERR_INT_EN BIT(22)
+#define B_BE_HT_ILL_CH_ERR_INT_EN BIT(20)
+#define B_BE_HT_ADDR_INFO_LEN_ERR_INT_EN BIT(18)
+#define B_BE_HT_WD_LEN_OVER_ERR_INT_EN BIT(17)
+#define B_BE_HT_PLD_CMD_UNDERFLOW_ERR_INT_EN BIT(16)
+#define B_BE_HT_PLD_CMD_OVERFLOW_ERR_INT_EN BIT(15)
+#define B_BE_HT_WRFF_UNDERFLOW_ERR_INT_EN BIT(14)
+#define B_BE_HT_WRFF_OVERFLOW_ERR_INT_EN BIT(13)
+#define B_BE_HT_CHKSUM_FSM_ERR_INT_EN BIT(12)
+#define B_BE_HT_NON_IDLE_PKT_STR_ERR_EN BIT(11)
+#define B_BE_HT_PRE_SUB_ERR_INT_EN BIT(10)
+#define B_BE_HT_WD_CHKSUM_ERR_INT_EN BIT(9)
+#define B_BE_HT_CHANNEL_DMA_ERR_INT_EN BIT(8)
+#define B_BE_HT_OFFSET_UNMATCH_ERR_INT_EN BIT(7)
+#define B_BE_HT_PAYLOAD_UNDER_ERR_INT_EN BIT(6)
+#define B_BE_HT_PAYLOAD_OVER_ERR_INT_EN BIT(5)
+#define B_BE_HT_PERMU_FF_UNDERFLOW_ERR_INT_EN BIT(4)
+#define B_BE_HT_PERMU_FF_OVERFLOW_ERR_INT_EN BIT(3)
+#define B_BE_HT_PKT_FAIL_ERR_INT_EN BIT(2)
+#define B_BE_HT_CH_ID_ERR_INT_EN BIT(1)
+#define B_BE_HT_EP_CH_DIFF_ERR_INT_EN BIT(0)
+#define B_BE_DISP_HOST_IMR_CLR (B_BE_HT_EP_CH_DIFF_ERR_INT_EN | \
+				B_BE_HT_CH_ID_ERR_INT_EN | \
+				B_BE_HT_PKT_FAIL_ERR_INT_EN | \
+				B_BE_HT_PERMU_FF_OVERFLOW_ERR_INT_EN | \
+				B_BE_HT_PERMU_FF_UNDERFLOW_ERR_INT_EN | \
+				B_BE_HT_PAYLOAD_OVER_ERR_INT_EN | \
+				B_BE_HT_PAYLOAD_UNDER_ERR_INT_EN | \
+				B_BE_HT_OFFSET_UNMATCH_ERR_INT_EN | \
+				B_BE_HT_CHANNEL_DMA_ERR_INT_EN | \
+				B_BE_HT_WD_CHKSUM_ERR_INT_EN | \
+				B_BE_HT_PRE_SUB_ERR_INT_EN | \
+				B_BE_HT_NON_IDLE_PKT_STR_ERR_EN | \
+				B_BE_HT_CHKSUM_FSM_ERR_INT_EN | \
+				B_BE_HT_WRFF_OVERFLOW_ERR_INT_EN | \
+				B_BE_HT_WRFF_UNDERFLOW_ERR_INT_EN | \
+				B_BE_HT_PLD_CMD_OVERFLOW_ERR_INT_EN | \
+				B_BE_HT_PLD_CMD_UNDERFLOW_ERR_INT_EN | \
+				B_BE_HT_WD_LEN_OVER_ERR_INT_EN | \
+				B_BE_HT_ADDR_INFO_LEN_ERR_INT_EN | \
+				B_BE_HT_ILL_CH_ERR_INT_EN | \
+				B_BE_HR_PLD_LEN_ZERO_ERR_INT_EN | \
+				B_BE_HR_AGG_CFG_ERR_INT_EN | \
+				B_BE_HR_SHIFT_EN_ERR_INT_EN | \
+				B_BE_HR_TOTAL_LEN_UNDER_ERR_INT_EN | \
+				B_BE_HR_DMA_PROCESS_ERR_INT_EN | \
+				B_BE_HR_SHIFT_DMA_CFG_ERR_INT_EN | \
+				B_BE_HR_CHKSUM_FSM_ERR_INT_EN | \
+				B_BE_HR_WRFF_OVERFLOW_ERR_INT_EN | \
+				B_BE_HR_WRFF_UNDERFLOW_ERR_INT_EN)
+#define B_BE_DISP_HOST_IMR_SET (B_BE_HT_EP_CH_DIFF_ERR_INT_EN | \
+				B_BE_HT_PERMU_FF_OVERFLOW_ERR_INT_EN | \
+				B_BE_HT_PERMU_FF_UNDERFLOW_ERR_INT_EN | \
+				B_BE_HT_PAYLOAD_OVER_ERR_INT_EN | \
+				B_BE_HT_PAYLOAD_UNDER_ERR_INT_EN | \
+				B_BE_HT_CHANNEL_DMA_ERR_INT_EN | \
+				B_BE_HT_PRE_SUB_ERR_INT_EN | \
+				B_BE_HT_WRFF_OVERFLOW_ERR_INT_EN | \
+				B_BE_HT_WRFF_UNDERFLOW_ERR_INT_EN | \
+				B_BE_HT_PLD_CMD_OVERFLOW_ERR_INT_EN | \
+				B_BE_HT_PLD_CMD_UNDERFLOW_ERR_INT_EN | \
+				B_BE_HT_WD_LEN_OVER_ERR_INT_EN | \
+				B_BE_HT_ILL_CH_ERR_INT_EN | \
+				B_BE_HR_TOTAL_LEN_UNDER_ERR_INT_EN | \
+				B_BE_HR_DMA_PROCESS_ERR_INT_EN | \
+				B_BE_HR_WRFF_OVERFLOW_ERR_INT_EN | \
+				B_BE_HR_WRFF_UNDERFLOW_ERR_INT_EN)
+
+#define R_BE_DISP_CPU_IMR 0x8878
+#define B_BE_CR_PLD_LEN_ERR_INT_EN BIT(30)
+#define B_BE_CR_WRFF_UNDERFLOW_ERR_INT_EN BIT(29)
+#define B_BE_CR_WRFF_OVERFLOW_ERR_INT_EN BIT(28)
+#define B_BE_CR_SHIFT_DMA_CFG_ERR_INT_EN BIT(27)
+#define B_BE_CR_DMA_PROCESS_ERR_INT_EN BIT(26)
+#define B_BE_CR_TOTAL_LEN_UNDER_ERR_INT_EN BIT(25)
+#define B_BE_CR_SHIFT_EN_ERR_INT_EN BIT(24)
+#define B_BE_REUSE_FIFO_B_UNDER_ERR_INT_EN BIT(22)
+#define B_BE_REUSE_FIFO_B_OVER_ERR_INT_EN BIT(21)
+#define B_BE_REUSE_FIFO_A_UNDER_ERR_INT_EN BIT(20)
+#define B_BE_REUSE_FIFO_A_OVER_ERR_INT_EN BIT(19)
+#define B_BE_CT_ADDR_INFO_LEN_MISS_ERR_INT_EN BIT(17)
+#define B_BE_CT_WD_LEN_OVER_ERR_INT_EN BIT(16)
+#define B_BE_CT_F2P_SEQ_ERR_INT_EN BIT(15)
+#define B_BE_CT_F2P_QSEL_ERR_INT_EN BIT(14)
+#define B_BE_CT_PLD_CMD_UNDERFLOW_ERR_INT_EN BIT(13)
+#define B_BE_CT_PLD_CMD_OVERFLOW_ERR_INT_EN BIT(12)
+#define B_BE_CT_PRE_SUB_ERR_INT_EN BIT(11)
+#define B_BE_CT_WD_CHKSUM_ERR_INT_EN BIT(10)
+#define B_BE_CT_CHANNEL_DMA_ERR_INT_EN BIT(9)
+#define B_BE_CT_OFFSET_UNMATCH_ERR_INT_EN BIT(8)
+#define B_BE_CT_PAYLOAD_CHKSUM_ERR_INT_EN BIT(7)
+#define B_BE_CT_PAYLOAD_UNDER_ERR_INT_EN BIT(6)
+#define B_BE_CT_PAYLOAD_OVER_ERR_INT_EN BIT(5)
+#define B_BE_CT_PERMU_FF_UNDERFLOW_ERR_INT_EN BIT(4)
+#define B_BE_CT_PERMU_FF_OVERFLOW_ERR_INT_EN BIT(3)
+#define B_BE_CT_CH_ID_ERR_INT_EN BIT(2)
+#define B_BE_CT_PKT_FAIL_ERR_INT_EN BIT(1)
+#define B_BE_CT_EP_CH_DIFF_ERR_INT_EN BIT(0)
+#define B_BE_DISP_CPU_IMR_CLR (B_BE_CT_EP_CH_DIFF_ERR_INT_EN | \
+			       B_BE_CT_CH_ID_ERR_INT_EN | \
+			       B_BE_CT_PERMU_FF_OVERFLOW_ERR_INT_EN | \
+			       B_BE_CT_PERMU_FF_UNDERFLOW_ERR_INT_EN | \
+			       B_BE_CT_PAYLOAD_OVER_ERR_INT_EN | \
+			       B_BE_CT_PAYLOAD_UNDER_ERR_INT_EN | \
+			       B_BE_CT_OFFSET_UNMATCH_ERR_INT_EN | \
+			       B_BE_CT_CHANNEL_DMA_ERR_INT_EN | \
+			       B_BE_CT_WD_CHKSUM_ERR_INT_EN | \
+			       B_BE_CT_PRE_SUB_ERR_INT_EN | \
+			       B_BE_CT_PLD_CMD_OVERFLOW_ERR_INT_EN | \
+			       B_BE_CT_PLD_CMD_UNDERFLOW_ERR_INT_EN | \
+			       B_BE_CT_F2P_QSEL_ERR_INT_EN | \
+			       B_BE_CT_F2P_SEQ_ERR_INT_EN | \
+			       B_BE_CT_WD_LEN_OVER_ERR_INT_EN | \
+			       B_BE_CT_ADDR_INFO_LEN_MISS_ERR_INT_EN | \
+			       B_BE_REUSE_FIFO_A_OVER_ERR_INT_EN | \
+			       B_BE_REUSE_FIFO_A_UNDER_ERR_INT_EN | \
+			       B_BE_REUSE_FIFO_B_OVER_ERR_INT_EN | \
+			       B_BE_REUSE_FIFO_B_UNDER_ERR_INT_EN | \
+			       B_BE_CR_SHIFT_EN_ERR_INT_EN | \
+			       B_BE_CR_DMA_PROCESS_ERR_INT_EN | \
+			       B_BE_CR_SHIFT_DMA_CFG_ERR_INT_EN | \
+			       B_BE_CR_WRFF_OVERFLOW_ERR_INT_EN | \
+			       B_BE_CR_WRFF_UNDERFLOW_ERR_INT_EN | \
+			       B_BE_CR_PLD_LEN_ERR_INT_EN)
+#define B_BE_DISP_CPU_IMR_SET (B_BE_CT_EP_CH_DIFF_ERR_INT_EN | \
+			       B_BE_CT_CH_ID_ERR_INT_EN | \
+			       B_BE_CT_PERMU_FF_OVERFLOW_ERR_INT_EN | \
+			       B_BE_CT_PERMU_FF_UNDERFLOW_ERR_INT_EN | \
+			       B_BE_CT_PAYLOAD_OVER_ERR_INT_EN | \
+			       B_BE_CT_PAYLOAD_UNDER_ERR_INT_EN | \
+			       B_BE_CT_PRE_SUB_ERR_INT_EN | \
+			       B_BE_CT_PLD_CMD_OVERFLOW_ERR_INT_EN | \
+			       B_BE_CT_PLD_CMD_UNDERFLOW_ERR_INT_EN | \
+			       B_BE_CT_WD_LEN_OVER_ERR_INT_EN | \
+			       B_BE_REUSE_FIFO_A_OVER_ERR_INT_EN | \
+			       B_BE_REUSE_FIFO_A_UNDER_ERR_INT_EN | \
+			       B_BE_REUSE_FIFO_B_OVER_ERR_INT_EN | \
+			       B_BE_REUSE_FIFO_B_UNDER_ERR_INT_EN | \
+			       B_BE_CR_DMA_PROCESS_ERR_INT_EN | \
+			       B_BE_CR_WRFF_OVERFLOW_ERR_INT_EN | \
+			       B_BE_CR_WRFF_UNDERFLOW_ERR_INT_EN)
+
+#define R_BE_DISP_FWD_WLAN_0 0x8938
+#define B_BE_FWD_WLAN_CPU_TYPE_13_MASK GENMASK(31, 30)
+#define B_BE_FWD_WLAN_CPU_TYPE_12_MASK GENMASK(29, 28)
+#define B_BE_FWD_WLAN_CPU_TYPE_11_MASK GENMASK(27, 26)
+#define B_BE_FWD_WLAN_CPU_TYPE_10_MASK GENMASK(25, 24)
+#define B_BE_FWD_WLAN_CPU_TYPE_9_MASK GENMASK(23, 22)
+#define B_BE_FWD_WLAN_CPU_TYPE_8_MASK GENMASK(21, 20)
+#define B_BE_FWD_WLAN_CPU_TYPE_7_MASK GENMASK(19, 18)
+#define B_BE_FWD_WLAN_CPU_TYPE_6_MASK GENMASK(17, 16)
+#define B_BE_FWD_WLAN_CPU_TYPE_5_MASK GENMASK(15, 14)
+#define B_BE_FWD_WLAN_CPU_TYPE_4_MASK GENMASK(13, 12)
+#define B_BE_FWD_WLAN_CPU_TYPE_3_MASK GENMASK(11, 10)
+#define B_BE_FWD_WLAN_CPU_TYPE_2_MASK GENMASK(9, 8)
+#define B_BE_FWD_WLAN_CPU_TYPE_1_MASK GENMASK(7, 6)
+#define B_BE_FWD_WLAN_CPU_TYPE_0_CTL_MASK GENMASK(5, 4)
+#define B_BE_FWD_WLAN_CPU_TYPE_0_MNG_MASK GENMASK(3, 2)
+#define B_BE_FWD_WLAN_CPU_TYPE_0_DATA_MASK GENMASK(1, 0)
+
+#define R_BE_WDE_PKTBUF_CFG 0x8C08
+#define B_BE_WDE_FREE_PAGE_NUM_MASK GENMASK(28, 16)
+#define B_BE_WDE_START_BOUND_MASK GENMASK(14, 8)
+#define B_BE_WDE_PAGE_SEL_MASK GENMASK(1, 0)
+
+#define R_BE_WDE_ERR_IMR 0x8C38
+#define B_BE_WDE_DATCHN_CAMREQ_ERR_INT_EN BIT(29)
+#define B_BE_WDE_DATCHN_ADRERR_ERR_INT_EN BIT(28)
+#define B_BE_WDE_DATCHN_RRDY_ERR_INT_EN BIT(27)
+#define B_BE_WDE_DATCHN_FRZTO_ERR_INT_EN BIT(26)
+#define B_BE_WDE_DATCHN_NULLPG_ERR_INT_EN BIT(25)
+#define B_BE_WDE_DATCHN_ARBT_ERR_INT_EN BIT(24)
+#define B_BE_WDE_QUEMGN_FRZTO_ERR_INT_EN BIT(23)
+#define B_BE_WDE_NXTPKTLL_AD_ERR_INT_EN BIT(22)
+#define B_BE_WDE_PREPKTLLT_AD_ERR_INT_EN BIT(21)
+#define B_BE_WDE_ENQ_PKTCNT_NVAL_ERR_INT_EN BIT(20)
+#define B_BE_WDE_ENQ_PKTCNT_OVRF_ERR_INT_EN BIT(19)
+#define B_BE_WDE_QUE_SRCQUEID_ERR_INT_EN BIT(18)
+#define B_BE_WDE_QUE_DSTQUEID_ERR_INT_EN BIT(17)
+#define B_BE_WDE_QUE_CMDTYPE_ERR_INT_EN BIT(16)
+#define B_BE_WDE_BUFMGN_MRG_SZLMT_ERR_INT_EN BIT(13)
+#define B_BE_WDE_BUFMGN_MRG_QTAID_ERR_INT_EN BIT(12)
+#define B_BE_WDE_BUFMGN_MRG_ENDPKTID_ERR_INT_EN BIT(11)
+#define B_BE_WDE_ERR_BUFMGN_MRG_STRPKTID_ERR_INT_EN BIT(10)
+#define B_BE_WDE_BUFMGN_FRZTO_ERR_INT_EN BIT(9)
+#define B_BE_WDE_GETNPG_PGOFST_ERR_INT_EN BIT(8)
+#define B_BE_WDE_GETNPG_STRPG_ERR_INT_EN BIT(7)
+#define B_BE_WDE_BUFREQ_SRCHTAILPG_ERR_INT_EN BIT(6)
+#define B_BE_WDE_BUFRTN_SIZE_ERR_INT_EN BIT(5)
+#define B_BE_WDE_BUFRTN_INVLD_PKTID_ERR_INT_EN BIT(4)
+#define B_BE_WDE_BUFREQ_UNAVAL_ERR_INT_EN BIT(3)
+#define B_BE_WDE_BUFREQ_SIZELMT_INT_EN BIT(2)
+#define B_BE_WDE_BUFREQ_SIZE0_INT_EN BIT(1)
+#define B_BE_WDE_BUFREQ_QTAID_ERR_INT_EN BIT(0)
+#define B_BE_WDE_ERR_IMR_CLR (B_BE_WDE_BUFREQ_QTAID_ERR_INT_EN | \
+			      B_BE_WDE_BUFREQ_SIZE0_INT_EN | \
+			      B_BE_WDE_BUFREQ_SIZELMT_INT_EN | \
+			      B_BE_WDE_BUFREQ_UNAVAL_ERR_INT_EN | \
+			      B_BE_WDE_BUFRTN_INVLD_PKTID_ERR_INT_EN | \
+			      B_BE_WDE_BUFRTN_SIZE_ERR_INT_EN | \
+			      B_BE_WDE_BUFREQ_SRCHTAILPG_ERR_INT_EN | \
+			      B_BE_WDE_GETNPG_STRPG_ERR_INT_EN | \
+			      B_BE_WDE_GETNPG_PGOFST_ERR_INT_EN | \
+			      B_BE_WDE_BUFMGN_FRZTO_ERR_INT_EN | \
+			      B_BE_WDE_ERR_BUFMGN_MRG_STRPKTID_ERR_INT_EN | \
+			      B_BE_WDE_BUFMGN_MRG_ENDPKTID_ERR_INT_EN | \
+			      B_BE_WDE_BUFMGN_MRG_QTAID_ERR_INT_EN | \
+			      B_BE_WDE_BUFMGN_MRG_SZLMT_ERR_INT_EN | \
+			      B_BE_WDE_QUE_CMDTYPE_ERR_INT_EN | \
+			      B_BE_WDE_QUE_DSTQUEID_ERR_INT_EN | \
+			      B_BE_WDE_QUE_SRCQUEID_ERR_INT_EN | \
+			      B_BE_WDE_ENQ_PKTCNT_OVRF_ERR_INT_EN | \
+			      B_BE_WDE_ENQ_PKTCNT_NVAL_ERR_INT_EN | \
+			      B_BE_WDE_PREPKTLLT_AD_ERR_INT_EN | \
+			      B_BE_WDE_NXTPKTLL_AD_ERR_INT_EN | \
+			      B_BE_WDE_QUEMGN_FRZTO_ERR_INT_EN | \
+			      B_BE_WDE_DATCHN_ARBT_ERR_INT_EN | \
+			      B_BE_WDE_DATCHN_NULLPG_ERR_INT_EN | \
+			      B_BE_WDE_DATCHN_FRZTO_ERR_INT_EN | \
+			      B_BE_WDE_DATCHN_RRDY_ERR_INT_EN | \
+			      B_BE_WDE_DATCHN_ADRERR_ERR_INT_EN | \
+			      B_BE_WDE_DATCHN_CAMREQ_ERR_INT_EN)
+#define B_BE_WDE_ERR_IMR_SET (B_BE_WDE_BUFREQ_QTAID_ERR_INT_EN | \
+			      B_BE_WDE_BUFREQ_SIZE0_INT_EN | \
+			      B_BE_WDE_BUFREQ_SIZELMT_INT_EN | \
+			      B_BE_WDE_BUFREQ_UNAVAL_ERR_INT_EN | \
+			      B_BE_WDE_BUFRTN_INVLD_PKTID_ERR_INT_EN | \
+			      B_BE_WDE_BUFRTN_SIZE_ERR_INT_EN | \
+			      B_BE_WDE_BUFREQ_SRCHTAILPG_ERR_INT_EN | \
+			      B_BE_WDE_GETNPG_STRPG_ERR_INT_EN | \
+			      B_BE_WDE_GETNPG_PGOFST_ERR_INT_EN | \
+			      B_BE_WDE_BUFMGN_FRZTO_ERR_INT_EN | \
+			      B_BE_WDE_ERR_BUFMGN_MRG_STRPKTID_ERR_INT_EN | \
+			      B_BE_WDE_BUFMGN_MRG_ENDPKTID_ERR_INT_EN | \
+			      B_BE_WDE_BUFMGN_MRG_QTAID_ERR_INT_EN | \
+			      B_BE_WDE_BUFMGN_MRG_SZLMT_ERR_INT_EN | \
+			      B_BE_WDE_QUE_CMDTYPE_ERR_INT_EN | \
+			      B_BE_WDE_QUE_DSTQUEID_ERR_INT_EN | \
+			      B_BE_WDE_QUE_SRCQUEID_ERR_INT_EN | \
+			      B_BE_WDE_ENQ_PKTCNT_OVRF_ERR_INT_EN | \
+			      B_BE_WDE_ENQ_PKTCNT_NVAL_ERR_INT_EN | \
+			      B_BE_WDE_PREPKTLLT_AD_ERR_INT_EN | \
+			      B_BE_WDE_NXTPKTLL_AD_ERR_INT_EN | \
+			      B_BE_WDE_QUEMGN_FRZTO_ERR_INT_EN | \
+			      B_BE_WDE_DATCHN_ARBT_ERR_INT_EN | \
+			      B_BE_WDE_DATCHN_NULLPG_ERR_INT_EN | \
+			      B_BE_WDE_DATCHN_FRZTO_ERR_INT_EN | \
+			      B_BE_WDE_DATCHN_RRDY_ERR_INT_EN | \
+			      B_BE_WDE_DATCHN_ADRERR_ERR_INT_EN | \
+			      B_BE_WDE_DATCHN_CAMREQ_ERR_INT_EN)
+
+#define R_BE_WDE_QTA0_CFG 0x8C40
+#define B_BE_WDE_Q0_MAX_SIZE_MASK GENMASK(27, 16)
+#define B_BE_WDE_Q0_MIN_SIZE_MASK GENMASK(11, 0)
+
+#define R_BE_WDE_QTA1_CFG 0x8C44
+#define B_BE_WDE_Q1_MAX_SIZE_MASK GENMASK(27, 16)
+#define B_BE_WDE_Q1_MIN_SIZE_MASK GENMASK(11, 0)
+
+#define R_BE_WDE_QTA2_CFG 0x8C48
+#define B_BE_WDE_Q2_MAX_SIZE_MASK GENMASK(27, 16)
+#define B_BE_WDE_Q2_MIN_SIZE_MASK GENMASK(11, 0)
+
+#define R_BE_WDE_QTA3_CFG 0x8C4C
+#define B_BE_WDE_Q3_MAX_SIZE_MASK GENMASK(27, 16)
+#define B_BE_WDE_Q3_MIN_SIZE_MASK GENMASK(11, 0)
+
+#define R_BE_WDE_QTA4_CFG 0x8C50
+#define B_BE_WDE_Q4_MAX_SIZE_MASK GENMASK(27, 16)
+#define B_BE_WDE_Q4_MIN_SIZE_MASK GENMASK(11, 0)
+
+#define R_BE_WDE_ERR1_IMR 0x8CC0
+#define B_BE_WDE_QUEMGN_CMACACQ_DEQNTFY_INT_EN BIT(8)
+#define B_BE_WDE_ERR1_IMR_CLR B_BE_WDE_QUEMGN_CMACACQ_DEQNTFY_INT_EN
+#define B_BE_WDE_ERR1_IMR_SET B_BE_WDE_QUEMGN_CMACACQ_DEQNTFY_INT_EN
+
+#define R_BE_PLE_PKTBUF_CFG 0x9008
+#define B_BE_PLE_FREE_PAGE_NUM_MASK GENMASK(28, 16)
+#define B_BE_PLE_START_BOUND_MASK GENMASK(14, 8)
+#define B_BE_PLE_PAGE_SEL_MASK GENMASK(1, 0)
+
+#define R_BE_PLE_ERR_IMR 0x9038
+#define B_BE_PLE_DATCHN_CAMREQ_ERR_INT_EN BIT(29)
+#define B_BE_PLE_DATCHN_ADRERR_ERR_INT_EN BIT(28)
+#define B_BE_PLE_DATCHN_RRDY_ERR_INT_EN BIT(27)
+#define B_BE_PLE_DATCHN_FRZTO_ERR_INT_EN BIT(26)
+#define B_BE_PLE_DATCHN_NULLPG_ERR_INT_EN BIT(25)
+#define B_BE_PLE_DATCHN_ARBT_ERR_INT_EN BIT(24)
+#define B_BE_PLE_QUEMGN_FRZTO_ERR_INT_EN BIT(23)
+#define B_BE_PLE_NXTPKTLL_AD_ERR_INT_EN BIT(22)
+#define B_BE_PLE_PREPKTLLT_AD_ERR_INT_EN BIT(21)
+#define B_BE_PLE_ENQ_PKTCNT_NVAL_ERR_INT_EN BIT(20)
+#define B_BE_PLE_ENQ_PKTCNT_OVRF_ERR_INT_EN BIT(19)
+#define B_BE_PLE_QUE_SRCQUEID_ERR_INT_EN BIT(18)
+#define B_BE_PLE_QUE_DSTQUEID_ERR_INT_EN BIT(17)
+#define B_BE_PLE_QUE_CMDTYPE_ERR_INT_EN BIT(16)
+#define B_BE_PLE_BUFMGN_MRG_SZLMT_ERR_INT_EN BIT(13)
+#define B_BE_PLE_BUFMGN_MRG_QTAID_ERR_INT_EN BIT(12)
+#define B_BE_PLE_BUFMGN_MRG_ENDPKTID_ERR_INT_EN BIT(11)
+#define B_BE_PLE_BUFMGN_MRG_STRPKTID_ERR_INT_EN BIT(10)
+#define B_BE_PLE_BUFMGN_FRZTO_ERR_INT_EN BIT(9)
+#define B_BE_PLE_GETNPG_PGOFST_ERR_INT_EN BIT(8)
+#define B_BE_PLE_GETNPG_STRPG_ERR_INT_EN BIT(7)
+#define B_BE_PLE_BUFREQ_SRCHTAILPG_ERR_INT_EN BIT(6)
+#define B_BE_PLE_BUFRTN_SIZE_ERR_INT_EN BIT(5)
+#define B_BE_PLE_BUFRTN_INVLD_PKTID_ERR_INT_EN BIT(4)
+#define B_BE_PLE_BUFREQ_UNAVAL_ERR_INT_EN BIT(3)
+#define B_BE_PLE_BUFREQ_SIZELMT_INT_EN BIT(2)
+#define B_BE_PLE_BUFREQ_SIZE0_INT_EN BIT(1)
+#define B_BE_PLE_BUFREQ_QTAID_ERR_INT_EN BIT(0)
+#define B_BE_PLE_ERR_IMR_CLR (B_BE_PLE_BUFREQ_QTAID_ERR_INT_EN | \
+			      B_BE_PLE_BUFREQ_SIZE0_INT_EN | \
+			      B_BE_PLE_BUFREQ_SIZELMT_INT_EN | \
+			      B_BE_PLE_BUFREQ_UNAVAL_ERR_INT_EN | \
+			      B_BE_PLE_BUFRTN_INVLD_PKTID_ERR_INT_EN | \
+			      B_BE_PLE_BUFRTN_SIZE_ERR_INT_EN | \
+			      B_BE_PLE_BUFREQ_SRCHTAILPG_ERR_INT_EN | \
+			      B_BE_PLE_GETNPG_STRPG_ERR_INT_EN | \
+			      B_BE_PLE_GETNPG_PGOFST_ERR_INT_EN | \
+			      B_BE_PLE_BUFMGN_FRZTO_ERR_INT_EN | \
+			      B_BE_PLE_BUFMGN_MRG_STRPKTID_ERR_INT_EN | \
+			      B_BE_PLE_BUFMGN_MRG_ENDPKTID_ERR_INT_EN | \
+			      B_BE_PLE_BUFMGN_MRG_QTAID_ERR_INT_EN | \
+			      B_BE_PLE_BUFMGN_MRG_SZLMT_ERR_INT_EN | \
+			      B_BE_PLE_QUE_CMDTYPE_ERR_INT_EN | \
+			      B_BE_PLE_QUE_DSTQUEID_ERR_INT_EN | \
+			      B_BE_PLE_QUE_SRCQUEID_ERR_INT_EN | \
+			      B_BE_PLE_ENQ_PKTCNT_OVRF_ERR_INT_EN | \
+			      B_BE_PLE_ENQ_PKTCNT_NVAL_ERR_INT_EN | \
+			      B_BE_PLE_PREPKTLLT_AD_ERR_INT_EN | \
+			      B_BE_PLE_NXTPKTLL_AD_ERR_INT_EN | \
+			      B_BE_PLE_QUEMGN_FRZTO_ERR_INT_EN | \
+			      B_BE_PLE_DATCHN_ARBT_ERR_INT_EN | \
+			      B_BE_PLE_DATCHN_NULLPG_ERR_INT_EN | \
+			      B_BE_PLE_DATCHN_FRZTO_ERR_INT_EN | \
+			      B_BE_PLE_DATCHN_RRDY_ERR_INT_EN | \
+			      B_BE_PLE_DATCHN_ADRERR_ERR_INT_EN | \
+			      B_BE_PLE_DATCHN_CAMREQ_ERR_INT_EN)
+#define B_BE_PLE_ERR_IMR_SET (B_BE_PLE_BUFREQ_QTAID_ERR_INT_EN | \
+			      B_BE_PLE_BUFREQ_SIZE0_INT_EN | \
+			      B_BE_PLE_BUFREQ_SIZELMT_INT_EN | \
+			      B_BE_PLE_BUFREQ_UNAVAL_ERR_INT_EN | \
+			      B_BE_PLE_BUFRTN_INVLD_PKTID_ERR_INT_EN | \
+			      B_BE_PLE_BUFRTN_SIZE_ERR_INT_EN | \
+			      B_BE_PLE_BUFREQ_SRCHTAILPG_ERR_INT_EN | \
+			      B_BE_PLE_GETNPG_STRPG_ERR_INT_EN | \
+			      B_BE_PLE_GETNPG_PGOFST_ERR_INT_EN | \
+			      B_BE_PLE_BUFMGN_FRZTO_ERR_INT_EN | \
+			      B_BE_PLE_BUFMGN_MRG_STRPKTID_ERR_INT_EN | \
+			      B_BE_PLE_BUFMGN_MRG_ENDPKTID_ERR_INT_EN | \
+			      B_BE_PLE_BUFMGN_MRG_QTAID_ERR_INT_EN | \
+			      B_BE_PLE_BUFMGN_MRG_SZLMT_ERR_INT_EN | \
+			      B_BE_PLE_QUE_CMDTYPE_ERR_INT_EN | \
+			      B_BE_PLE_QUE_DSTQUEID_ERR_INT_EN | \
+			      B_BE_PLE_QUE_SRCQUEID_ERR_INT_EN | \
+			      B_BE_PLE_ENQ_PKTCNT_OVRF_ERR_INT_EN | \
+			      B_BE_PLE_ENQ_PKTCNT_NVAL_ERR_INT_EN | \
+			      B_BE_PLE_PREPKTLLT_AD_ERR_INT_EN | \
+			      B_BE_PLE_NXTPKTLL_AD_ERR_INT_EN | \
+			      B_BE_PLE_QUEMGN_FRZTO_ERR_INT_EN | \
+			      B_BE_PLE_DATCHN_ARBT_ERR_INT_EN | \
+			      B_BE_PLE_DATCHN_NULLPG_ERR_INT_EN | \
+			      B_BE_PLE_DATCHN_FRZTO_ERR_INT_EN | \
+			      B_BE_PLE_DATCHN_RRDY_ERR_INT_EN | \
+			      B_BE_PLE_DATCHN_ADRERR_ERR_INT_EN | \
+			      B_BE_PLE_DATCHN_CAMREQ_ERR_INT_EN)
+
+#define R_BE_PLE_QTA0_CFG 0x9040
+#define B_BE_PLE_Q0_MAX_SIZE_MASK GENMASK(27, 16)
+#define B_BE_PLE_Q0_MIN_SIZE_MASK GENMASK(11, 0)
+
+#define R_BE_PLE_QTA1_CFG 0x9044
+#define B_BE_PLE_Q1_MAX_SIZE_MASK GENMASK(27, 16)
+#define B_BE_PLE_Q1_MIN_SIZE_MASK GENMASK(11, 0)
+
+#define R_BE_PLE_QTA2_CFG 0x9048
+#define B_BE_PLE_Q2_MAX_SIZE_MASK GENMASK(27, 16)
+#define B_BE_PLE_Q2_MIN_SIZE_MASK GENMASK(11, 0)
+
+#define R_BE_PLE_QTA3_CFG 0x904C
+#define B_BE_PLE_Q3_MAX_SIZE_MASK GENMASK(27, 16)
+#define B_BE_PLE_Q3_MIN_SIZE_MASK GENMASK(11, 0)
+
+#define R_BE_PLE_QTA4_CFG 0x9050
+#define B_BE_PLE_Q4_MAX_SIZE_MASK GENMASK(27, 16)
+#define B_BE_PLE_Q4_MIN_SIZE_MASK GENMASK(11, 0)
+
+#define R_BE_PLE_QTA5_CFG 0x9054
+#define B_BE_PLE_Q5_MAX_SIZE_MASK GENMASK(27, 16)
+#define B_BE_PLE_Q5_MIN_SIZE_MASK GENMASK(11, 0)
+
+#define R_BE_PLE_QTA6_CFG 0x9058
+#define B_BE_PLE_Q6_MAX_SIZE_MASK GENMASK(27, 16)
+#define B_BE_PLE_Q6_MIN_SIZE_MASK GENMASK(11, 0)
+
+#define R_BE_PLE_QTA7_CFG 0x905C
+#define B_BE_PLE_Q7_MAX_SIZE_MASK GENMASK(27, 16)
+#define B_BE_PLE_Q7_MIN_SIZE_MASK GENMASK(11, 0)
+
+#define R_BE_PLE_QTA8_CFG 0x9060
+#define B_BE_PLE_Q8_MAX_SIZE_MASK GENMASK(27, 16)
+#define B_BE_PLE_Q8_MIN_SIZE_MASK GENMASK(11, 0)
+
+#define R_BE_PLE_QTA9_CFG 0x9064
+#define B_BE_PLE_Q9_MAX_SIZE_MASK GENMASK(27, 16)
+#define B_BE_PLE_Q9_MIN_SIZE_MASK GENMASK(11, 0)
+
+#define R_BE_PLE_QTA10_CFG 0x9068
+#define B_BE_PLE_Q10_MAX_SIZE_MASK GENMASK(27, 16)
+#define B_BE_PLE_Q10_MIN_SIZE_MASK GENMASK(11, 0)
+
+#define R_BE_PLE_QTA11_CFG 0x906C
+#define B_BE_PLE_Q11_MAX_SIZE_MASK GENMASK(27, 16)
+#define B_BE_PLE_Q11_MIN_SIZE_MASK GENMASK(11, 0)
+
+#define R_BE_PLE_QTA12_CFG 0x9070
+#define B_BE_PLE_Q12_MAX_SIZE_MASK GENMASK(27, 16)
+#define B_BE_PLE_Q12_MIN_SIZE_MASK GENMASK(11, 0)
+
+#define R_BE_PLE_ERRFLAG1_IMR 0x90C0
+#define B_BE_PLE_SRCHPG_PGOFST_IMR BIT(26)
+#define B_BE_PLE_SRCHPG_STRPG_IMR BIT(25)
+#define B_BE_PLE_SRCHPG_FRZTO_IMR BIT(24)
+#define B_BE_PLE_ERRFLAG1_IMR_CLR (B_BE_PLE_SRCHPG_FRZTO_IMR | \
+				   B_BE_PLE_SRCHPG_STRPG_IMR | \
+				   B_BE_PLE_SRCHPG_PGOFST_IMR)
+#define B_BE_PLE_ERRFLAG1_IMR_SET (B_BE_PLE_SRCHPG_FRZTO_IMR | \
+				   B_BE_PLE_SRCHPG_STRPG_IMR | \
+				   B_BE_PLE_SRCHPG_PGOFST_IMR)
+
 #define R_BE_PLE_DBG_FUN_INTF_CTL 0x9110
 #define B_BE_PLE_DFI_ACTIVE BIT(31)
 #define B_BE_PLE_DFI_TRGSEL_MASK GENMASK(19, 16)
@@ -3740,6 +5220,608 @@
 #define R_BE_PLE_DBG_FUN_INTF_DATA 0x9114
 #define B_BE_PLE_DFI_DATA_MASK GENMASK(31, 0)
 
+#define R_BE_WDRLS_CFG 0x9408
+#define B_BE_WDRLS_DIS_AGAC BIT(31)
+#define B_BE_RLSRPT_BUFREQ_TO_MASK GENMASK(15, 8)
+#define B_BE_RLSRPT_BUFREQ_TO_SEL_MASK GENMASK(7, 6)
+#define B_BE_WDRLS_MODE_MASK GENMASK(1, 0)
+
+#define R_BE_WDRLS_ERR_IMR 0x9430
+#define B_BE_WDRLS_RPT3_FRZTO_ERR_INT_EN BIT(21)
+#define B_BE_WDRLS_RPT3_AGGNUM0_ERR_INT_EN BIT(20)
+#define B_BE_WDRLS_RPT2_FRZTO_ERR_INT_EN BIT(17)
+#define B_BE_WDRLS_RPT2_AGGNUM0_ERR_INT_EN BIT(16)
+#define B_BE_WDRLS_RPT1_FRZTO_ERR_INT_EN BIT(13)
+#define B_BE_WDRLS_RPT1_AGGNUM0_ERR_INT_EN BIT(12)
+#define B_BE_WDRLS_RPT0_FRZTO_ERR_INT_EN BIT(9)
+#define B_BE_WDRLS_RPT0_AGGNUM0_ERR_INT_EN BIT(8)
+#define B_BE_WDRLS_PLEBREQ_PKTID_ISNULL_ERR_INT_EN BIT(5)
+#define B_BE_WDRLS_PLEBREQ_TO_ERR_INT_EN BIT(4)
+#define B_BE_WDRLS_CTL_FRZTO_ERR_INT_EN BIT(2)
+#define B_BE_WDRLS_CTL_PLPKTID_ISNULL_ERR_INT_EN BIT(1)
+#define B_BE_WDRLS_CTL_WDPKTID_ISNULL_ERR_INT_EN BIT(0)
+#define B_BE_WDRLS_ERR_IMR_CLR (B_BE_WDRLS_CTL_WDPKTID_ISNULL_ERR_INT_EN | \
+				B_BE_WDRLS_CTL_PLPKTID_ISNULL_ERR_INT_EN | \
+				B_BE_WDRLS_CTL_FRZTO_ERR_INT_EN | \
+				B_BE_WDRLS_PLEBREQ_TO_ERR_INT_EN | \
+				B_BE_WDRLS_PLEBREQ_PKTID_ISNULL_ERR_INT_EN | \
+				B_BE_WDRLS_RPT0_AGGNUM0_ERR_INT_EN | \
+				B_BE_WDRLS_RPT0_FRZTO_ERR_INT_EN | \
+				B_BE_WDRLS_RPT1_AGGNUM0_ERR_INT_EN | \
+				B_BE_WDRLS_RPT1_FRZTO_ERR_INT_EN)
+#define B_BE_WDRLS_ERR_IMR_SET (B_BE_WDRLS_CTL_WDPKTID_ISNULL_ERR_INT_EN | \
+				B_BE_WDRLS_CTL_PLPKTID_ISNULL_ERR_INT_EN | \
+				B_BE_WDRLS_CTL_FRZTO_ERR_INT_EN | \
+				B_BE_WDRLS_PLEBREQ_PKTID_ISNULL_ERR_INT_EN | \
+				B_BE_WDRLS_RPT0_AGGNUM0_ERR_INT_EN | \
+				B_BE_WDRLS_RPT0_FRZTO_ERR_INT_EN | \
+				B_BE_WDRLS_RPT1_AGGNUM0_ERR_INT_EN | \
+				B_BE_WDRLS_RPT1_FRZTO_ERR_INT_EN)
+
+#define R_BE_RLSRPT0_CFG1 0x9444
+#define B_BE_RLSRPT0_FLTR_MAP_MASK GENMASK(27, 24)
+#define S_BE_WDRLS_FLTR_TXOK 1
+#define S_BE_WDRLS_FLTR_RTYLMT 2
+#define S_BE_WDRLS_FLTR_LIFTIM 4
+#define S_BE_WDRLS_FLTR_MACID 8
+#define B_BE_RLSRPT0_TO_MASK GENMASK(23, 16)
+#define B_BE_RLSRPT0_AGGNUM_MASK GENMASK(7, 0)
+
+#define R_BE_BBRPT_COM_ERR_IMR 0x9608
+#define B_BE_BBRPT_COM_EVT01_ISR_EN BIT(1)
+#define B_BE_BBRPT_COM_NULL_PLPKTID_ISR_EN BIT(0)
+#define B_BE_BBRPT_COM_ERR_IMR_CLR (B_BE_BBRPT_COM_NULL_PLPKTID_ISR_EN | \
+				    B_BE_BBRPT_COM_EVT01_ISR_EN)
+#define B_BE_BBRPT_COM_ERR_IMR_SET B_BE_BBRPT_COM_NULL_PLPKTID_ISR_EN
+
+#define R_BE_BBRPT_CHINFO_ERR_IMR 0x9628
+#define B_BE_ERR_BB_ONETEN_INT_EN BIT(1)
+#define B_BE_ERR_GEN_FRZTO_INT_EN BIT(0)
+#define B_BE_BBRPT_CHINFO_ERR_IMR_CLR (B_BE_ERR_GEN_FRZTO_INT_EN | \
+				       B_BE_ERR_BB_ONETEN_INT_EN)
+#define B_BE_BBRPT_CHINFO_ERR_IMR_SET (B_BE_ERR_GEN_FRZTO_INT_EN | \
+				       B_BE_ERR_BB_ONETEN_INT_EN)
+
+#define R_BE_BBRPT_DFS_ERR_IMR 0x9638
+#define B_BE_BBRPT_DFS_TO_ERR_INT_EN BIT(0)
+#define B_BE_BBRPT_DFS_ERR_IMR_CLR B_BE_BBRPT_DFS_TO_ERR_INT_EN
+#define B_BE_BBRPT_DFS_ERR_IMR_SET B_BE_BBRPT_DFS_TO_ERR_INT_EN
+
+#define R_BE_LA_ERRFLAG_IMR 0x9668
+#define B_BE_LA_IMR_DATA_LOSS BIT(0)
+#define B_BE_LA_ERRFLAG_IMR_CLR B_BE_LA_IMR_DATA_LOSS
+#define B_BE_LA_ERRFLAG_IMR_SET B_BE_LA_IMR_DATA_LOSS
+
+#define R_BE_LA_ERRFLAG_ISR 0x966C
+#define B_BE_LA_ISR_DATA_LOSS BIT(0)
+
+#define R_BE_CH_INFO_DBGFLAG_IMR 0x9688
+#define B_BE_BCHN_EVT01_ISR_EN BIT(29)
+#define B_BE_BCHN_REQTO_ISR_EN BIT(28)
+#define B_BE_CHIF_RXDATA_AFACT_ISR_EN BIT(11)
+#define B_BE_CHIF_RXDATA_BFACT_ISR_EN BIT(10)
+#define B_BE_CHIF_HDR_SEGLEN_ISR_EN BIT(9)
+#define B_BE_CHIF_HDR_INVLD_ISR_EN BIT(8)
+#define B_BE_CHIF_BBONL_BFACT_ISR_EN BIT(4)
+#define B_BE_CHIF_RPT_OVF_ISR_EN BIT(3)
+#define B_BE_DBG_CHIF_DATA_LOSS_ISR_EN BIT(2)
+#define B_BE_CHIF_DATA_WTOUT_ISR_EN BIT(1)
+#define B_BE_CHIF_RPT_WTOUT_ISR_EN BIT(0)
+#define B_BE_CH_INFO_DBGFLAG_IMR_CLR (B_BE_CHIF_RPT_WTOUT_ISR_EN | \
+				      B_BE_CHIF_DATA_WTOUT_ISR_EN | \
+				      B_BE_DBG_CHIF_DATA_LOSS_ISR_EN | \
+				      B_BE_CHIF_RPT_OVF_ISR_EN | \
+				      B_BE_CHIF_HDR_INVLD_ISR_EN | \
+				      B_BE_CHIF_HDR_SEGLEN_ISR_EN | \
+				      B_BE_CHIF_RXDATA_BFACT_ISR_EN | \
+				      B_BE_CHIF_RXDATA_AFACT_ISR_EN)
+#define B_BE_CH_INFO_DBGFLAG_IMR_SET 0
+
+#define R_BE_WD_BUF_REQ 0x9800
+#define B_BE_WD_BUF_REQ_EXEC BIT(31)
+#define B_BE_WD_BUF_REQ_QUOTA_ID_MASK GENMASK(23, 16)
+#define B_BE_WD_BUF_REQ_LEN_MASK GENMASK(15, 0)
+
+#define R_BE_WD_BUF_STATUS 0x9804
+#define B_BE_WD_BUF_STAT_DONE BIT(31)
+#define B_BE_WD_BUF_STAT_PKTID_MASK GENMASK(11, 0)
+
+#define R_BE_WD_CPUQ_OP_0 0x9810
+#define B_BE_WD_CPUQ_OP_EXEC BIT(31)
+#define B_BE_WD_CPUQ_OP_CMD_TYPE_MASK GENMASK(27, 24)
+#define B_BE_WD_CPUQ_OP_PKTNUM_MASK GENMASK(7, 0)
+
+#define R_BE_WD_CPUQ_OP_1 0x9814
+#define B_BE_WD_CPUQ_OP_SRC_MACID_MASK GENMASK(19, 12)
+#define B_BE_WD_CPUQ_OP_SRC_QID_MASK GENMASK(9, 4)
+#define B_BE_WD_CPUQ_OP_SRC_PID_MASK GENMASK(2, 0)
+
+#define R_BE_WD_CPUQ_OP_2 0x9818
+#define B_BE_WD_CPUQ_OP_DST_MACID_MASK GENMASK(19, 12)
+#define B_BE_WD_CPUQ_OP_DST_QID_MASK GENMASK(9, 4)
+#define B_BE_WD_CPUQ_OP_DST_PID_MASK GENMASK(2, 0)
+
+#define R_BE_WD_CPUQ_OP_3 0x981C
+#define B_BE_WD_CPUQ_OP_STRT_PKTID_MASK GENMASK(27, 16)
+#define B_BE_WD_CPUQ_OP_END_PKTID_MASK GENMASK(11, 0)
+
+#define R_BE_WD_CPUQ_OP_STATUS 0x9820
+#define B_BE_WD_CPUQ_OP_STAT_DONE BIT(31)
+#define B_BE_WD_CPUQ_OP_PKTCNT_MASK GENMASK(27, 16)
+#define B_BE_WD_CPUQ_OP_PKTID_MASK GENMASK(11, 0)
+
+#define R_BE_PL_BUF_REQ 0x9840
+#define B_BE_PL_BUF_REQ_EXEC BIT(31)
+#define B_BE_PL_BUF_REQ_QUOTA_ID_MASK GENMASK(19, 16)
+#define B_BE_PL_BUF_REQ_LEN_MASK GENMASK(15, 0)
+
+#define R_BE_PL_BUF_STATUS 0x9844
+#define B_BE_PL_BUF_STAT_DONE BIT(31)
+#define B_BE_PL_BUF_STAT_PKTID_MASK GENMASK(11, 0)
+
+#define R_BE_PL_CPUQ_OP_0 0x9850
+#define B_BE_PL_CPUQ_OP_EXEC BIT(31)
+#define B_BE_PL_CPUQ_OP_CMD_TYPE_MASK GENMASK(27, 24)
+#define B_BE_PL_CPUQ_OP_PKTNUM_MASK GENMASK(7, 0)
+
+#define R_BE_PL_CPUQ_OP_1 0x9854
+#define B_BE_PL_CPUQ_OP_SRC_MACID_MASK GENMASK(19, 12)
+#define B_BE_PL_CPUQ_OP_SRC_QID_MASK GENMASK(9, 4)
+#define B_BE_PL_CPUQ_OP_SRC_PID_MASK GENMASK(2, 0)
+
+#define R_BE_PL_CPUQ_OP_2 0x9858
+#define B_BE_PL_CPUQ_OP_DST_MACID_MASK GENMASK(19, 12)
+#define B_BE_PL_CPUQ_OP_DST_QID_MASK GENMASK(9, 4)
+#define B_BE_PL_CPUQ_OP_DST_PID_MASK GENMASK(2, 0)
+
+#define R_BE_PL_CPUQ_OP_3 0x985C
+#define B_BE_PL_CPUQ_OP_STRT_PKTID_MASK GENMASK(27, 16)
+#define B_BE_PL_CPUQ_OP_END_PKTID_MASK GENMASK(11, 0)
+
+#define R_BE_PL_CPUQ_OP_STATUS 0x9860
+#define B_BE_PL_CPUQ_OP_STAT_DONE BIT(31)
+#define B_BE_PL_CPUQ_OP_PKTCNT_MASK GENMASK(27, 16)
+#define B_BE_PL_CPUQ_OP_PKTID_MASK GENMASK(11, 0)
+
+#define R_BE_CPUIO_ERR_IMR 0x9888
+#define B_BE_PLEQUE_OP_ERR_INT_EN BIT(12)
+#define B_BE_PLEBUF_OP_ERR_INT_EN BIT(8)
+#define B_BE_WDEQUE_OP_ERR_INT_EN BIT(4)
+#define B_BE_WDEBUF_OP_ERR_INT_EN BIT(0)
+#define B_BE_CPUIO_ERR_IMR_CLR (B_BE_WDEBUF_OP_ERR_INT_EN | \
+				B_BE_WDEQUE_OP_ERR_INT_EN | \
+				B_BE_PLEBUF_OP_ERR_INT_EN | \
+				B_BE_PLEQUE_OP_ERR_INT_EN)
+#define B_BE_CPUIO_ERR_IMR_SET (B_BE_WDEBUF_OP_ERR_INT_EN | \
+				B_BE_WDEQUE_OP_ERR_INT_EN | \
+				B_BE_PLEBUF_OP_ERR_INT_EN | \
+				B_BE_PLEQUE_OP_ERR_INT_EN)
+
+#define R_BE_PKTIN_ERR_IMR 0x9A20
+#define B_BE_SW_MERGE_ERR_INT_EN BIT(1)
+#define B_BE_GET_NULL_PKTID_ERR_INT_EN BIT(0)
+#define B_BE_PKTIN_ERR_IMR_CLR (B_BE_SW_MERGE_ERR_INT_EN | \
+				B_BE_GET_NULL_PKTID_ERR_INT_EN)
+#define B_BE_PKTIN_ERR_IMR_SET (B_BE_SW_MERGE_ERR_INT_EN | \
+				B_BE_GET_NULL_PKTID_ERR_INT_EN)
+
+#define R_BE_HDR_SHCUT_SETTING 0x9B00
+#define B_BE_TX_ADDR_MLD_TO_LIK BIT(4)
+#define B_BE_TX_HW_SEC_HDR_EN BIT(3)
+#define B_BE_TX_MAC_MPDU_PROC_EN BIT(2)
+#define B_BE_TX_HW_ACK_POLICY_EN BIT(1)
+#define B_BE_TX_HW_SEQ_EN BIT(0)
+
+#define R_BE_MPDU_TX_ERR_IMR 0x9BF4
+#define B_BE_TX_TIMEOUT_ERR_EN BIT(0)
+#define B_BE_MPDU_TX_ERR_IMR_CLR B_BE_TX_TIMEOUT_ERR_EN
+#define B_BE_MPDU_TX_ERR_IMR_SET 0
+
+#define R_BE_MPDU_PROC 0x9C00
+#define B_BE_PORT_SEL BIT(29)
+#define B_BE_WPKT_WLANCPU_QSEL_MASK GENMASK(28, 27)
+#define B_BE_WPKT_DATACPU_QSEL_MASK GENMASK(26, 25)
+#define B_BE_WPKT_FW_RLS BIT(24)
+#define B_BE_FWD_RPKT_MASK GENMASK(23, 16)
+#define B_BE_FWD_WPKT_MASK GENMASK(15, 8)
+#define B_BE_RXFWD_PRIO_MASK GENMASK(5, 4)
+#define B_BE_RXFWD_EN BIT(3)
+#define B_BE_DROP_NONDMA_PPDU BIT(2)
+#define B_BE_APPEND_FCS BIT(0)
+
+#define R_BE_CUT_AMSDU_CTRL 0x9C94
+#define B_BE_EN_CUT_AMSDU BIT(31)
+#define B_BE_CUT_AMSDU_CHKLEN_EN BIT(30)
+#define B_BE_CA_CHK_ADDRCAM_EN BIT(29)
+#define B_BE_MPDU_CUT_CTRL_EN BIT(24)
+#define B_BE_CUT_AMSDU_CHKLEN_L_TH_MASK GENMASK(23, 16)
+#define B_BE_CUT_AMSDU_CHKLEN_H_TH_MASK GENMASK(15, 0)
+
+#define R_BE_RX_HDRTRNS 0x9CC0
+#define B_BE_RX_MGN_MLD_ADDR_EN BIT(6)
+#define B_BE_HDR_INFO_MASK GENMASK(5, 4)
+#define B_BE_HC_ADDR_HIT_EN BIT(3)
+#define B_BE_RX_ADDR_LINK_TO_MLO BIT(2)
+#define B_BE_HDR_CNV BIT(1)
+#define B_BE_RX_HDR_CNV_EN BIT(0)
+#define TRXCFG_MPDU_PROC_RX_HDR_CONV	0x00000000
+
+#define R_BE_MPDU_RX_ERR_IMR 0x9CF4
+#define B_BE_LEN_ERR_IMR BIT(3)
+#define B_BE_TIMEOUT_ERR_IMR BIT(1)
+#define B_BE_MPDU_RX_ERR_IMR_CLR B_BE_TIMEOUT_ERR_IMR
+#define B_BE_MPDU_RX_ERR_IMR_SET 0
+
+#define R_BE_SEC_ENG_CTRL 0x9D00
+#define B_BE_SEC_ENG_EN BIT(31)
+#define B_BE_CCMP_SPP_MIC BIT(30)
+#define B_BE_CCMP_SPP_CTR BIT(29)
+#define B_BE_SEC_CAM_ACC BIT(28)
+#define B_BE_WMAC_SEC_PN_SEL_MASK GENMASK(27, 26)
+#define B_BE_WMAC_SEC_MASKIV BIT(25)
+#define B_BE_WAPI_SPEC BIT(24)
+#define B_BE_REVERT_TA_RA_MLD_EN BIT(23)
+#define B_BE_SEC_DBG_SEL_MASK GENMASK(19, 16)
+#define B_BE_CAM_FORCE_CLK BIT(15)
+#define B_BE_SEC_FORCE_CLK BIT(14)
+#define B_BE_SEC_RX_SHORT_ADD_ICVERR BIT(13)
+#define B_BE_SRAM_IO_PROT BIT(12)
+#define B_BE_SEC_PRE_ENQUE_TX BIT(11)
+#define B_BE_CLK_EN_CGCMP BIT(10)
+#define B_BE_CLK_EN_WAPI BIT(9)
+#define B_BE_CLK_EN_WEP_TKIP BIT(8)
+#define B_BE_BMC_MGNT_DEC BIT(5)
+#define B_BE_UC_MGNT_DEC BIT(4)
+#define B_BE_MC_DEC BIT(3)
+#define B_BE_BC_DEC BIT(2)
+#define B_BE_SEC_RX_DEC BIT(1)
+#define B_BE_SEC_TX_ENC BIT(0)
+
+#define R_BE_SEC_MPDU_PROC 0x9D04
+#define B_BE_DBG_ENGINE_SEL BIT(8)
+#define B_BE_STOP_RX_PKT_HANDLE BIT(7)
+#define B_BE_STOP_TX_PKT_HANDLE BIT(6)
+#define B_BE_QUEUE_FOWARD_SEL BIT(5)
+#define B_BE_RESP1_PROTECT BIT(4)
+#define B_BE_RESP0_PROTECT BIT(3)
+#define B_BE_TX_ACTIVE_PROTECT BIT(2)
+#define B_BE_APPEND_ICV BIT(1)
+#define B_BE_APPEND_MIC BIT(0)
+
+#define R_BE_SEC_CAM_ACCESS 0x9D10
+#define B_BE_SEC_TIME_OUT_MASK GENMASK(31, 16)
+#define B_BE_SEC_CAM_POLL BIT(15)
+#define B_BE_SEC_CAM_RW BIT(14)
+#define B_BE_SEC_CAM_ACC_FAIL BIT(13)
+#define B_BE_SEC_CAM_OFFSET_MASK GENMASK(10, 0)
+
+#define R_BE_SEC_CAM_RDATA 0x9D14
+#define B_BE_SEC_CAM_RDATA_MASK GENMASK(31, 0)
+
+#define R_BE_SEC_DEBUG2 0x9D28
+#define B_BE_DBG_READ_MASK GENMASK(31, 0)
+
+#define R_BE_SEC_ERROR_IMR 0x9D2C
+#define B_BE_QUEUE_OPERATION_HANG_IMR BIT(4)
+#define B_BE_SEC1_RX_HANG_IMR BIT(3)
+#define B_BE_SEC1_TX_HANG_IMR BIT(2)
+#define B_BE_RX_HANG_IMR BIT(1)
+#define B_BE_TX_HANG_IMR BIT(0)
+#define B_BE_SEC_ERROR_IMR_CLR (B_BE_TX_HANG_IMR | \
+				B_BE_RX_HANG_IMR | \
+				B_BE_SEC1_TX_HANG_IMR | \
+				B_BE_SEC1_RX_HANG_IMR | \
+				B_BE_QUEUE_OPERATION_HANG_IMR)
+#define B_BE_SEC_ERROR_IMR_SET (B_BE_TX_HANG_IMR | \
+				B_BE_RX_HANG_IMR | \
+				B_BE_SEC1_TX_HANG_IMR | \
+				B_BE_SEC1_RX_HANG_IMR | \
+				B_BE_QUEUE_OPERATION_HANG_IMR)
+
+#define R_BE_SEC_ERROR_FLAG 0x9D30
+#define B_BE_TXD_DIFF_KEYCAM_TYPE_ERROR BIT(5)
+#define B_BE_QUEUE_OPERATION_HANG_ERROR BIT(4)
+#define B_BE_SEC1_RX_HANG_ERROR BIT(3)
+#define B_BE_SEC1_TX_HANG_ERROR BIT(2)
+#define B_BE_RX_HANG_ERROR BIT(1)
+#define B_BE_TX_HANG_ERROR BIT(0)
+
+#define R_BE_TXPKTCTL_MPDUINFO_CFG 0x9F10
+#define B_BE_MPDUINFO_FEN BIT(31)
+#define B_BE_MPDUINFO_PKTID_MASK GENMASK(27, 16)
+#define B_BE_MPDUINFO_B1_BADDR_MASK GENMASK(5, 0)
+#define MPDU_INFO_B1_OFST 18
+
+#define R_BE_TXPKTCTL_B0_PRELD_CFG0 0x9F48
+#define B_BE_B0_PRELD_FEN BIT(31)
+#define B_BE_B0_PRELD_USEMAXSZ_MASK GENMASK(25, 16)
+#define B_BE_B0_PRELD_CAM_G1ENTNUM_MASK GENMASK(12, 8)
+#define B_BE_B0_PRELD_CAM_G0ENTNUM_MASK GENMASK(4, 0)
+
+#define R_BE_TXPKTCTL_B0_PRELD_CFG1 0x9F4C
+#define B_BE_B0_PRELD_NXT_TXENDWIN_MASK GENMASK(11, 8)
+#define B_BE_B0_PRELD_NXT_RSVMINSZ_MASK GENMASK(7, 0)
+
+#define R_BE_TXPKTCTL_B0_ERRFLAG_IMR 0x9F78
+#define B_BE_B0_IMR_DBG_USRCTL_RLSBMPLEN BIT(25)
+#define B_BE_B0_IMR_DBG_USRCTL_RDNRLSCMD BIT(24)
+#define B_BE_B0_IMR_ERR_PRELD_ENTNUMCFG BIT(17)
+#define B_BE_B0_IMR_ERR_PRELD_RLSPKTSZERR BIT(16)
+#define B_BE_B0_IMR_ERR_CMDPSR_TBLSZ BIT(11)
+#define B_BE_B0_IMR_ERR_CMDPSR_FRZTO BIT(10)
+#define B_BE_B0_IMR_ERR_CMDPSR_CMDTYPE BIT(9)
+#define B_BE_B0_IMR_ERR_CMDPSR_1STCMDERR BIT(8)
+#define B_BE_B0_IMR_ERR_USRCTL_NOINIT BIT(1)
+#define B_BE_B0_IMR_ERR_USRCTL_REINIT BIT(0)
+#define B_BE_TXPKTCTL_B0_ERRFLAG_IMR_CLR (B_BE_B0_IMR_ERR_USRCTL_REINIT | \
+					  B_BE_B0_IMR_ERR_USRCTL_NOINIT | \
+					  B_BE_B0_IMR_DBG_USRCTL_RDNRLSCMD | \
+					  B_BE_B0_IMR_DBG_USRCTL_RLSBMPLEN | \
+					  B_BE_B0_IMR_ERR_CMDPSR_1STCMDERR | \
+					  B_BE_B0_IMR_ERR_CMDPSR_CMDTYPE | \
+					  B_BE_B0_IMR_ERR_CMDPSR_FRZTO | \
+					  B_BE_B0_IMR_ERR_CMDPSR_TBLSZ | \
+					  B_BE_B0_IMR_ERR_PRELD_RLSPKTSZERR | \
+					  B_BE_B0_IMR_ERR_PRELD_ENTNUMCFG)
+#define B_BE_TXPKTCTL_B0_ERRFLAG_IMR_SET (B_BE_B0_IMR_ERR_USRCTL_REINIT | \
+					  B_BE_B0_IMR_ERR_USRCTL_NOINIT | \
+					  B_BE_B0_IMR_ERR_CMDPSR_1STCMDERR | \
+					  B_BE_B0_IMR_ERR_CMDPSR_CMDTYPE | \
+					  B_BE_B0_IMR_ERR_CMDPSR_FRZTO | \
+					  B_BE_B0_IMR_ERR_CMDPSR_TBLSZ | \
+					  B_BE_B0_IMR_ERR_PRELD_RLSPKTSZERR | \
+					  B_BE_B0_IMR_ERR_PRELD_ENTNUMCFG)
+
+#define R_BE_TXPKTCTL_B1_PRELD_CFG0 0x9F88
+#define B_BE_B1_PRELD_FEN BIT(31)
+#define B_BE_B1_PRELD_USEMAXSZ_MASK GENMASK(25, 16)
+#define B_BE_B1_PRELD_CAM_G1ENTNUM_MASK GENMASK(12, 8)
+#define B_BE_B1_PRELD_CAM_G0ENTNUM_MASK GENMASK(4, 0)
+
+#define R_BE_TXPKTCTL_B1_PRELD_CFG1 0x9F8C
+#define B_BE_B1_PRELD_NXT_TXENDWIN_MASK GENMASK(11, 8)
+#define B_BE_B1_PRELD_NXT_RSVMINSZ_MASK GENMASK(7, 0)
+
+#define R_BE_TXPKTCTL_B1_ERRFLAG_IMR 0x9FB8
+#define B_BE_B1_IMR_DBG_USRCTL_RLSBMPLEN BIT(25)
+#define B_BE_B1_IMR_DBG_USRCTL_RDNRLSCMD BIT(24)
+#define B_BE_B1_IMR_ERR_PRELD_ENTNUMCFG BIT(17)
+#define B_BE_B1_IMR_ERR_PRELD_RLSPKTSZERR BIT(16)
+#define B_BE_B1_IMR_ERR_CMDPSR_TBLSZ BIT(11)
+#define B_BE_B1_IMR_ERR_CMDPSR_FRZTO BIT(10)
+#define B_BE_B1_IMR_ERR_CMDPSR_CMDTYPE BIT(9)
+#define B_BE_B1_IMR_ERR_CMDPSR_1STCMDERR BIT(8)
+#define B_BE_B1_IMR_ERR_USRCTL_NOINIT BIT(1)
+#define B_BE_B1_IMR_ERR_USRCTL_REINIT BIT(0)
+#define B_BE_TXPKTCTL_B1_ERRFLAG_IMR_CLR (B_BE_B1_IMR_ERR_USRCTL_REINIT | \
+					  B_BE_B1_IMR_ERR_USRCTL_NOINIT | \
+					  B_BE_B1_IMR_DBG_USRCTL_RDNRLSCMD | \
+					  B_BE_B1_IMR_DBG_USRCTL_RLSBMPLEN | \
+					  B_BE_B1_IMR_ERR_CMDPSR_1STCMDERR | \
+					  B_BE_B1_IMR_ERR_CMDPSR_CMDTYPE | \
+					  B_BE_B1_IMR_ERR_CMDPSR_FRZTO | \
+					  B_BE_B1_IMR_ERR_CMDPSR_TBLSZ | \
+					  B_BE_B1_IMR_ERR_PRELD_RLSPKTSZERR | \
+					  B_BE_B1_IMR_ERR_PRELD_ENTNUMCFG)
+#define B_BE_TXPKTCTL_B1_ERRFLAG_IMR_SET (B_BE_B1_IMR_ERR_USRCTL_REINIT | \
+					  B_BE_B1_IMR_ERR_USRCTL_NOINIT | \
+					  B_BE_B1_IMR_ERR_CMDPSR_1STCMDERR | \
+					  B_BE_B1_IMR_ERR_CMDPSR_CMDTYPE | \
+					  B_BE_B1_IMR_ERR_CMDPSR_FRZTO | \
+					  B_BE_B1_IMR_ERR_CMDPSR_TBLSZ | \
+					  B_BE_B1_IMR_ERR_PRELD_RLSPKTSZERR | \
+					  B_BE_B1_IMR_ERR_PRELD_ENTNUMCFG)
+
+#define R_BE_MLO_INIT_CTL 0xA114
+#define B_BE_MLO_TABLE_INIT_DONE BIT(31)
+#define B_BE_MLO_TABLE_CLR_DONE BIT(30)
+#define B_BE_MLO_TABLE_REINIT BIT(23)
+#define B_BE_MLO_TABLE_HW_FLAG_CLR BIT(22)
+
+#define R_BE_MLO_ERR_IDCT_IMR 0xA128
+#define B_BE_MLO_ERR_IDCT_IMR_0 BIT(31)
+#define B_BE_MLO_ERR_IDCT_IMR_1 BIT(30)
+#define B_BE_MLO_ERR_IDCT_IMR_2 BIT(29)
+#define B_BE_MLO_ERR_IDCT_IMR_3 BIT(28)
+#define B_BE_MLO_ERR_IDCT_IMR_CLR (B_BE_MLO_ERR_IDCT_IMR_2 | \
+				   B_BE_MLO_ERR_IDCT_IMR_1 | \
+				   B_BE_MLO_ERR_IDCT_IMR_0)
+#define B_BE_MLO_ERR_IDCT_IMR_SET (B_BE_MLO_ERR_IDCT_IMR_2 | \
+				   B_BE_MLO_ERR_IDCT_IMR_1 | \
+				   B_BE_MLO_ERR_IDCT_IMR_0)
+
+#define R_BE_MLO_ERR_IDCT_ISR 0xA12C
+#define B_BE_MLO_ISR_IDCT_0 BIT(31)
+#define B_BE_MLO_ISR_IDCT_1 BIT(30)
+#define B_BE_MLO_ISR_IDCT_2 BIT(29)
+#define B_BE_MLO_ISR_IDCT_3 BIT(28)
+
+#define R_BE_PLRLS_ERR_IMR 0xA218
+#define B_BE_PLRLS_CTL_FRZTO_IMR BIT(0)
+#define B_BE_PLRLS_ERR_IMR_CLR B_BE_PLRLS_CTL_FRZTO_IMR
+#define B_BE_PLRLS_ERR_IMR_SET B_BE_PLRLS_CTL_FRZTO_IMR
+
+#define R_BE_PLRLS_ERR_ISR 0xA21C
+#define B_BE_PLRLS_CTL_EVT03_ISR BIT(3)
+#define B_BE_PLRLS_CTL_EVT02_ISR BIT(2)
+#define B_BE_PLRLS_CTL_EVT01_ISR BIT(1)
+#define B_BE_PLRLS_CTL_FRZTO_ISR BIT(0)
+
+#define R_BE_SS_CTRL 0xA310
+#define B_BE_SS_INIT_DONE BIT(31)
+#define B_BE_WDE_STA_DIS BIT(30)
+#define B_BE_WARM_INIT BIT(29)
+#define B_BE_BAND_TRIG_EN BIT(28)
+#define B_BE_RMAC_REQ_DIS BIT(27)
+#define B_BE_DLYTX_SEL_MASK GENMASK(25, 24)
+#define B_BE_WMM3_SWITCH_MASK GENMASK(23, 22)
+#define B_BE_WMM2_SWITCH_MASK GENMASK(21, 20)
+#define B_BE_WMM1_SWITCH_MASK GENMASK(19, 18)
+#define B_BE_WMM0_SWITCH_MASK GENMASK(17, 16)
+#define B_BE_STA_OPTION_CR BIT(15)
+#define B_BE_EMLSR_STA_EMPTY_EN BIT(11)
+#define B_BE_MLO_HW_CHGLINK_EN BIT(10)
+#define B_BE_BAND1_TRIG_EN BIT(9)
+#define B_BE_RMAC1_REQ_DIS BIT(8)
+#define B_BE_MRT_SRAM_EN BIT(7)
+#define B_BE_MRT_INIT_EN BIT(6)
+#define B_BE_AVG_LENG_EN BIT(5)
+#define B_BE_AVG_INIT_EN BIT(4)
+#define B_BE_LENG_INIT_EN BIT(2)
+#define B_BE_PMPA_INIT_EN BIT(1)
+#define B_BE_SS_EN BIT(0)
+
+#define R_BE_INTERRUPT_MASK_REG 0xA3F0
+#define B_BE_PLE_B_PKTID_ERR_IMR BIT(2)
+#define B_BE_RPT_TIMEOUT_IMR BIT(1)
+#define B_BE_SEARCH_TIMEOUT_IMR BIT(0)
+#define B_BE_INTERRUPT_MASK_REG_CLR (B_BE_SEARCH_TIMEOUT_IMR | \
+				     B_BE_RPT_TIMEOUT_IMR | \
+				     B_BE_PLE_B_PKTID_ERR_IMR)
+#define B_BE_INTERRUPT_MASK_REG_SET (B_BE_SEARCH_TIMEOUT_IMR | \
+				     B_BE_RPT_TIMEOUT_IMR | \
+				     B_BE_PLE_B_PKTID_ERR_IMR)
+
+#define R_BE_INTERRUPT_STS_REG 0xA3F4
+#define B_BE_PLE_B_PKTID_ERR_ISR BIT(2)
+#define B_BE_RPT_TIMEOUT_ISR BIT(1)
+#define B_BE_SEARCH_TIMEOUT_ISR BIT(0)
+
+#define R_BE_HAXI_INIT_CFG1 0xB000
+#define B_BE_CFG_WD_PERIOD_IDLE_MASK GENMASK(31, 28)
+#define B_BE_CFG_WD_PERIOD_ACTIVE_MASK GENMASK(27, 24)
+#define B_BE_EN_RO_IDX_UPD_BY_IO BIT(19)
+#define B_BE_RST_KEEP_REG BIT(18)
+#define B_BE_FLUSH_HAXI_MST BIT(17)
+#define B_BE_SET_BDRAM_BOUND BIT(16)
+#define B_BE_ADDRINFO_ALIGN4B_EN BIT(15)
+#define B_BE_RXBD_DONE_MODE_MASK GENMASK(14, 13)
+#define B_BE_RXQ_RXBD_MODE_MASK GENMASK(12, 11)
+#define B_BE_DMA_MODE_MASK GENMASK(10, 8)
+#define S_BE_DMA_MOD_PCIE_NO_DATA_CPU 0x0
+#define S_BE_DMA_MOD_PCIE_DATA_CPU 0x1
+#define S_BE_DMA_MOD_USB 0x4
+#define S_BE_DMA_MOD_SDIO 0x6
+#define B_BE_STOP_AXI_MST BIT(7)
+#define B_BE_RXDMA_ALIGN64B_EN BIT(6)
+#define B_BE_RXDMA_EN BIT(5)
+#define B_BE_TXDMA_EN BIT(4)
+#define B_BE_MAX_RXDMA_MASK GENMASK(3, 2)
+#define B_BE_MAX_TXDMA_MASK GENMASK(1, 0)
+
+#define R_BE_HAXI_DMA_STOP1 0xB010
+#define B_BE_STOP_WPDMA BIT(31)
+#define B_BE_STOP_CH14 BIT(14)
+#define B_BE_STOP_CH13 BIT(13)
+#define B_BE_STOP_CH12 BIT(12)
+#define B_BE_STOP_CH11 BIT(11)
+#define B_BE_STOP_CH10 BIT(10)
+#define B_BE_STOP_CH9 BIT(9)
+#define B_BE_STOP_CH8 BIT(8)
+#define B_BE_STOP_CH7 BIT(7)
+#define B_BE_STOP_CH6 BIT(6)
+#define B_BE_STOP_CH5 BIT(5)
+#define B_BE_STOP_CH4 BIT(4)
+#define B_BE_STOP_CH3 BIT(3)
+#define B_BE_STOP_CH2 BIT(2)
+#define B_BE_STOP_CH1 BIT(1)
+#define B_BE_STOP_CH0 BIT(0)
+
+#define R_BE_HAXI_IDCT_MSK 0xB0B8
+#define B_BE_HAXI_RRESP_ERR_IDCT_MSK BIT(7)
+#define B_BE_HAXI_BRESP_ERR_IDCT_MSK BIT(6)
+#define B_BE_RXDMA_ERR_FLAG_IDCT_MSK BIT(5)
+#define B_BE_SET_FC_ERROR_FLAG_IDCT_MSK BIT(4)
+#define B_BE_TXBD_LEN0_ERR_IDCT_MSK BIT(3)
+#define B_BE_TXBD_4KBOUND_ERR_IDCT_MSK BIT(2)
+#define B_BE_RXMDA_STUCK_IDCT_MSK BIT(1)
+#define B_BE_TXMDA_STUCK_IDCT_MSK BIT(0)
+#define B_BE_HAXI_IDCT_MSK_CLR (B_BE_TXMDA_STUCK_IDCT_MSK | \
+				B_BE_RXMDA_STUCK_IDCT_MSK | \
+				B_BE_TXBD_LEN0_ERR_IDCT_MSK | \
+				B_BE_SET_FC_ERROR_FLAG_IDCT_MSK | \
+				B_BE_RXDMA_ERR_FLAG_IDCT_MSK | \
+				B_BE_HAXI_BRESP_ERR_IDCT_MSK | \
+				B_BE_HAXI_RRESP_ERR_IDCT_MSK)
+#define B_BE_HAXI_IDCT_MSK_SET (B_BE_TXMDA_STUCK_IDCT_MSK | \
+				B_BE_RXMDA_STUCK_IDCT_MSK | \
+				B_BE_TXBD_LEN0_ERR_IDCT_MSK | \
+				B_BE_SET_FC_ERROR_FLAG_IDCT_MSK | \
+				B_BE_RXDMA_ERR_FLAG_IDCT_MSK | \
+				B_BE_HAXI_BRESP_ERR_IDCT_MSK | \
+				B_BE_HAXI_RRESP_ERR_IDCT_MSK)
+
+#define R_BE_HAXI_IDCT 0xB0BC
+#define B_BE_HAXI_RRESP_ERR_IDCT BIT(7)
+#define B_BE_HAXI_BRESP_ERR_IDCT BIT(6)
+#define B_BE_RXDMA_ERR_FLAG_IDCT BIT(5)
+#define B_BE_SET_FC_ERROR_FLAG_IDCT BIT(4)
+#define B_BE__TXBD_LEN0_ERR_IDCT BIT(3)
+#define B_BE__TXBD_4KBOUND_ERR_IDCT BIT(2)
+#define B_BE_RXMDA_STUCK_IDCT BIT(1)
+#define B_BE_TXMDA_STUCK_IDCT BIT(0)
+
+#define R_BE_HCI_FC_CTRL 0xB700
+#define B_BE_WD_PAGE_MODE_MASK GENMASK(17, 16)
+#define B_BE_HCI_FC_CH14_FULL_COND_MASK GENMASK(15, 14)
+#define B_BE_HCI_FC_TWD_FULL_COND_MASK GENMASK(13, 12)
+#define B_BE_HCI_FC_CH12_FULL_COND_MASK GENMASK(11, 10)
+#define B_BE_HCI_FC_WP_CH811_FULL_COND_MASK GENMASK(9, 8)
+#define B_BE_HCI_FC_WP_CH07_FULL_COND_MASK GENMASK(7, 6)
+#define B_BE_HCI_FC_WD_FULL_COND_MASK GENMASK(5, 4)
+#define B_BE_HCI_FC_CH12_EN BIT(3)
+#define B_BE_HCI_FC_MODE_MASK GENMASK(2, 1)
+#define B_BE_HCI_FC_EN BIT(0)
+
+#define R_BE_CH_PAGE_CTRL 0xB704
+#define B_BE_PREC_PAGE_CH12_V1_MASK GENMASK(21, 16)
+#define B_BE_PREC_PAGE_CH011_V1_MASK GENMASK(5, 0)
+
+#define R_BE_PUB_PAGE_INFO3 0xB78C
+#define B_BE_G1_AVAL_PG_MASK GENMASK(28, 16)
+#define B_BE_G0_AVAL_PG_MASK GENMASK(12, 0)
+
+#define R_BE_PUB_PAGE_CTRL1 0xB790
+#define B_BE_PUBPG_G1_MASK GENMASK(28, 16)
+#define B_BE_PUBPG_G0_MASK GENMASK(12, 0)
+
+#define R_BE_PUB_PAGE_CTRL2 0xB794
+#define B_BE_PUBPG_ALL_MASK GENMASK(12, 0)
+
+#define R_BE_PUB_PAGE_INFO1 0xB79C
+#define B_BE_G1_USE_PG_MASK GENMASK(28, 16)
+#define B_BE_G0_USE_PG_MASK GENMASK(12, 0)
+
+#define R_BE_PUB_PAGE_INFO2 0xB7A0
+#define B_BE_PUB_AVAL_PG_MASK GENMASK(12, 0)
+
+#define R_BE_WP_PAGE_CTRL1 0xB7A4
+#define B_BE_PREC_PAGE_WP_CH811_MASK GENMASK(24, 16)
+#define B_BE_PREC_PAGE_WP_CH07_MASK GENMASK(8, 0)
+
+#define R_BE_WP_PAGE_CTRL2 0xB7A8
+#define B_BE_WP_THRD_MASK GENMASK(12, 0)
+
+#define R_BE_WP_PAGE_INFO1 0xB7AC
+#define B_BE_WP_AVAL_PG_MASK GENMASK(28, 16)
+
+#define R_BE_CMAC_SHARE_FUNC_EN 0x0E000
+#define B_BE_CMAC_SHARE_CRPRT BIT(31)
+#define B_BE_CMAC_SHARE_EN BIT(30)
+#define B_BE_FORCE_BTCOEX_REG_GCKEN BIT(24)
+#define B_BE_FORCE_CMAC_SHARE_COMMON_REG_GCKEN BIT(16)
+#define B_BE_FORCE_CMAC_SHARE_REG_GCKEN BIT(15)
+#define B_BE_RESPBA_EN BIT(2)
+#define B_BE_ADDRSRCH_EN BIT(1)
+#define B_BE_BTCOEX_EN BIT(0)
+
+#define R_BE_CMAC_SHARE_ACQCHK_CFG_0 0x0E010
+#define B_BE_ACQCHK_ERR_FLAG_MASK GENMASK(31, 24)
+#define B_BE_R_ACQCHK_ENTRY_IDX_SEL_MASK GENMASK(7, 4)
+#define B_BE_MACID_ACQ_GRP1_CLR_P BIT(3)
+#define B_BE_MACID_ACQ_GRP0_CLR_P BIT(2)
+#define B_BE_R_MACID_ACQ_CHK_EN BIT(0)
+
 #define R_BE_CMAC_FUNC_EN 0x10000
 #define R_BE_CMAC_FUNC_EN_C1 0x14000
 #define B_BE_CMAC_CRPRT BIT(31)
@@ -3772,6 +5854,138 @@
 			       B_BE_CMAC_CRPRT | B_BE_TXTIME_EN | B_BE_RESP_PKTCTL_EN | \
 			       B_BE_SIGB_EN)
 
+#define R_BE_CK_EN 0x10004
+#define R_BE_CK_EN_C1 0x14004
+#define B_BE_CMAC_CKEN BIT(30)
+#define B_BE_BCN_P1_P4_CKEN BIT(15)
+#define B_BE_BCN_P0MB1_15_CKEN BIT(14)
+#define B_BE_TXTIME_CKEN BIT(8)
+#define B_BE_RESP_PKTCTL_CKEN BIT(7)
+#define B_BE_SIGB_CKEN BIT(6)
+#define B_BE_PHYINTF_CKEN BIT(5)
+#define B_BE_CMAC_DMA_CKEN BIT(4)
+#define B_BE_PTCLTOP_CKEN BIT(3)
+#define B_BE_SCHEDULER_CKEN BIT(2)
+#define B_BE_TMAC_CKEN BIT(1)
+#define B_BE_RMAC_CKEN BIT(0)
+#define B_BE_CK_EN_SET (B_BE_CMAC_CKEN | B_BE_PHYINTF_CKEN | B_BE_CMAC_DMA_CKEN | \
+			B_BE_PTCLTOP_CKEN | B_BE_SCHEDULER_CKEN | B_BE_TMAC_CKEN | \
+			B_BE_RMAC_CKEN | B_BE_TXTIME_CKEN | B_BE_RESP_PKTCTL_CKEN | \
+			B_BE_SIGB_CKEN)
+
+#define R_BE_TX_SUB_BAND_VALUE 0x10088
+#define R_BE_TX_SUB_BAND_VALUE_C1 0x14088
+#define B_BE_PRI20_BITMAP_MASK GENMASK(31, 16)
+#define BE_PRI20_BITMAP_MAX 15
+#define B_BE_TXSB_160M_MASK GENMASK(15, 12)
+#define S_BE_TXSB_160M_0 0
+#define S_BE_TXSB_160M_1 1
+#define B_BE_TXSB_80M_MASK GENMASK(11, 8)
+#define S_BE_TXSB_80M_0 0
+#define S_BE_TXSB_80M_2 2
+#define S_BE_TXSB_80M_4 4
+#define B_BE_TXSB_40M_MASK GENMASK(7, 4)
+#define S_BE_TXSB_40M_0 0
+#define S_BE_TXSB_40M_1 1
+#define S_BE_TXSB_40M_4 4
+#define B_BE_TXSB_20M_MASK GENMASK(3, 0)
+#define S_BE_TXSB_20M_8 8
+#define S_BE_TXSB_20M_4 4
+#define S_BE_TXSB_20M_2 2
+
+#define R_BE_PTCL_RRSR0 0x1008C
+#define R_BE_PTCL_RRSR0_C1 0x1408C
+#define B_BE_RRSR_HE_MASK GENMASK(31, 24)
+#define B_BE_RRSR_VHT_MASK GENMASK(23, 16)
+#define B_BE_RRSR_HT_MASK GENMASK(15, 8)
+#define B_BE_RRSR_OFDM_MASK GENMASK(7, 0)
+
+#define R_BE_PTCL_RRSR1 0x10090
+#define R_BE_PTCL_RRSR1_C1 0x14090
+#define B_BE_RRSR_EHT_MASK GENMASK(23, 16)
+#define B_BE_RRSR_RATE_EN_MASK GENMASK(12, 8)
+#define B_BE_RSC_MASK GENMASK(7, 6)
+#define B_BE_RRSR_CCK_MASK GENMASK(3, 0)
+
+#define R_BE_CMAC_ERR_IMR 0x10160
+#define R_BE_CMAC_ERR_IMR_C1 0x14160
+#define B_BE_CMAC_FW_ERR_IDCT_EN BIT(16)
+#define B_BE_PTCL_TX_IDLETO_IDCT_EN BIT(9)
+#define B_BE_WMAC_RX_IDLETO_IDCT_EN BIT(8)
+#define B_BE_WMAC_TX_ERR_IND_EN BIT(7)
+#define B_BE_WMAC_RX_ERR_IND_EN BIT(6)
+#define B_BE_TXPWR_CTRL_ERR_IND_EN BIT(5)
+#define B_BE_PHYINTF_ERR_IND_EN BIT(4)
+#define B_BE_DMA_TOP_ERR_IND_EN BIT(3)
+#define B_BE_RESP_PKTCTL_ERR_IND_EN BIT(2)
+#define B_BE_PTCL_TOP_ERR_IND_EN BIT(1)
+#define B_BE_SCHEDULE_TOP_ERR_IND_EN BIT(0)
+
+#define R_BE_CMAC_ERR_ISR 0x10164
+#define R_BE_CMAC_ERR_ISR_C1 0x14164
+#define B_BE_CMAC_FW_ERR_IDCT BIT(16)
+#define B_BE_PTCL_TX_IDLETO_IDCT BIT(9)
+#define B_BE_WMAC_RX_IDLETO_IDCT BIT(8)
+#define B_BE_WMAC_TX_ERR_IND BIT(7)
+#define B_BE_WMAC_RX_ERR_IND BIT(6)
+#define B_BE_TXPWR_CTRL_ERR_IND BIT(5)
+#define B_BE_PHYINTF_ERR_IND BIT(4)
+#define B_BE_DMA_TOP_ERR_IND BIT(3)
+#define B_BE_RESP_PKTCTL_ERR_IDCT BIT(2)
+#define B_BE_PTCL_TOP_ERR_IND BIT(1)
+#define B_BE_SCHEDULE_TOP_ERR_IND BIT(0)
+
+#define R_BE_SER_L0_DBG_CNT 0x10170
+#define R_BE_SER_L0_DBG_CNT_C1 0x14170
+#define B_BE_SER_L0_PHYINTF_CNT_MASK GENMASK(31, 24)
+#define B_BE_SER_L0_DMA_CNT_MASK GENMASK(23, 16)
+#define B_BE_SER_L0_PTCL_CNT_MASK GENMASK(15, 8)
+#define B_BE_SER_L0_SCH_CNT_MASK GENMASK(7, 0)
+
+#define R_BE_SER_L0_DBG_CNT1 0x10174
+#define R_BE_SER_L0_DBG_CNT1_C1 0x14174
+#define B_BE_SER_L0_TMAC_COUNTER_MASK GENMASK(23, 16)
+#define B_BE_SER_L0_RMAC_COUNTER_MASK GENMASK(15, 8)
+#define B_BE_SER_L0_TXPWR_COUNTER_MASK GENMASK(7, 0)
+
+#define R_BE_SER_L0_DBG_CNT2 0x10178
+#define R_BE_SER_L0_DBG_CNT2_C1 0x14178
+
+#define R_BE_SER_L0_DBG_CNT3 0x1017C
+#define R_BE_SER_L0_DBG_CNT3_C1 0x1417C
+#define B_BE_SER_L0_SUBMODULE_BIT31_CNT BIT(31)
+#define B_BE_SER_L0_SUBMODULE_BIT30_CNT BIT(30)
+#define B_BE_SER_L0_SUBMODULE_BIT29_CNT BIT(29)
+#define B_BE_SER_L0_SUBMODULE_BIT28_CNT BIT(28)
+#define B_BE_SER_L0_SUBMODULE_BIT27_CNT BIT(27)
+#define B_BE_SER_L0_SUBMODULE_BIT26_CNT BIT(26)
+#define B_BE_SER_L0_SUBMODULE_BIT25_CNT BIT(25)
+#define B_BE_SER_L0_SUBMODULE_BIT24_CNT BIT(24)
+#define B_BE_SER_L0_SUBMODULE_BIT23_CNT BIT(23)
+#define B_BE_SER_L0_SUBMODULE_BIT22_CNT BIT(22)
+#define B_BE_SER_L0_SUBMODULE_BIT21_CNT BIT(21)
+#define B_BE_SER_L0_SUBMODULE_BIT20_CNT BIT(20)
+#define B_BE_SER_L0_SUBMODULE_BIT19_CNT BIT(19)
+#define B_BE_SER_L0_SUBMODULE_BIT18_CNT BIT(18)
+#define B_BE_SER_L0_SUBMODULE_BIT17_CNT BIT(17)
+#define B_BE_SER_L0_SUBMODULE_BIT16_CNT BIT(16)
+#define B_BE_SER_L0_SUBMODULE_BIT15_CNT BIT(15)
+#define B_BE_SER_L0_SUBMODULE_BIT14_CNT BIT(14)
+#define B_BE_SER_L0_SUBMODULE_BIT13_CNT BIT(13)
+#define B_BE_SER_L0_SUBMODULE_BIT12_CNT BIT(12)
+#define B_BE_SER_L0_SUBMODULE_BIT11_CNT BIT(11)
+#define B_BE_SER_L0_SUBMODULE_BIT10_CNT BIT(10)
+#define B_BE_SER_L0_SUBMODULE_BIT9_CNT BIT(9)
+#define B_BE_SER_L0_SUBMODULE_BIT8_CNT BIT(8)
+#define B_BE_SER_L0_SUBMODULE_BIT7_CNT BIT(7)
+#define B_BE_SER_L0_SUBMODULE_BIT6_CNT BIT(6)
+#define B_BE_SER_L0_SUBMODULE_BIT5_CNT BIT(5)
+#define B_BE_SER_L0_SUBMODULE_BIT4_CNT BIT(4)
+#define B_BE_SER_L0_SUBMODULE_BIT3_CNT BIT(3)
+#define B_BE_SER_L0_SUBMODULE_BIT2_CNT BIT(2)
+#define B_BE_SER_L0_SUBMODULE_BIT1_CNT BIT(1)
+#define B_BE_SER_L0_SUBMODULE_BIT0_CNT BIT(0)
+
 #define R_BE_PORT_0_TSF_SYNC 0x102A0
 #define R_BE_PORT_0_TSF_SYNC_C1 0x142A0
 #define B_BE_P0_SYNC_NOW_P BIT(30)
@@ -3780,6 +5994,55 @@
 #define B_BE_P0_SYNC_PORT_SRC_SEL_MASK GENMASK(26, 24)
 #define B_BE_P0_TSFTR_SYNC_OFFSET_MASK GENMASK(18, 0)
 
+#define R_BE_EDCA_BCNQ_PARAM 0x10324
+#define R_BE_EDCA_BCNQ_PARAM_C1 0x14324
+#define B_BE_BCNQ_CW_MASK GENMASK(31, 24)
+#define B_BE_BCNQ_AIFS_MASK GENMASK(23, 16)
+#define BCN_IFS_25US 0x19
+#define B_BE_PIFS_MASK GENMASK(15, 8)
+#define B_BE_FORCE_BCN_IFS_MASK GENMASK(7, 0)
+
+#define R_BE_PREBKF_CFG_0 0x10338
+#define R_BE_PREBKF_CFG_0_C1 0x14338
+#define B_BE_100NS_TIME_MASK GENMASK(28, 24)
+#define B_BE_RX_AIR_END_TIME_MASK GENMASK(22, 16)
+#define B_BE_MACTX_LATENCY_MASK GENMASK(10, 8)
+#define B_BE_PREBKF_TIME_MASK GENMASK(4, 0)
+
+#define R_BE_CCA_CFG_0 0x10340
+#define R_BE_CCA_CFG_0_C1 0x14340
+#define B_BE_R_SIFS_AGGR_TIME_V1_MASK GENMASK(31, 24)
+#define B_BE_EDCCA_SEC160_EN BIT(23)
+#define B_BE_EDCCA_SEC80_EN BIT(22)
+#define B_BE_EDCCA_SEC40_EN BIT(21)
+#define B_BE_EDCCA_SEC20_EN BIT(20)
+#define B_BE_SEC160_EN BIT(19)
+#define B_BE_CCA_BITMAP_EN BIT(18)
+#define B_BE_TXPKTCTL_RST_EDCA_EN BIT(17)
+#define B_BE_WMAC_RST_EDCA_EN BIT(16)
+#define B_BE_TXFAIL_BRK_TXOP_EN BIT(11)
+#define B_BE_EDCCA_PER20_BITMAP_SIFS_EN BIT(10)
+#define B_BE_NO_GNT_WL_BRK_TXOP_EN BIT(9)
+#define B_BE_NAV_BRK_TXOP_EN BIT(8)
+#define B_BE_TX_NAV_EN BIT(7)
+#define B_BE_BCN_IGNORE_EDCCA BIT(6)
+#define B_BE_NO_GNT_WL_EN BIT(5)
+#define B_BE_EDCCA_EN BIT(4)
+#define B_BE_SEC80_EN BIT(3)
+#define B_BE_SEC40_EN BIT(2)
+#define B_BE_SEC20_EN BIT(1)
+#define B_BE_CCA_EN BIT(0)
+
+#define R_BE_CTN_CFG_0 0x1034C
+#define R_BE_CTN_CFG_0_C1 0x1434C
+#define B_BE_OTHER_LINK_BKF_BLK_TX_THD_MASK GENMASK(30, 24)
+#define B_BE_CCK_SIFS_COMP_MASK GENMASK(22, 16)
+#define B_BE_PIFS_TIMEUNIT_MASK GENMASK(15, 14)
+#define B_BE_PREBKF_TIME_NONAC_MASK GENMASK(12, 8)
+#define B_BE_SR_TX_EN BIT(2)
+#define B_BE_NAV_BLK_MGQ BIT(1)
+#define B_BE_NAV_BLK_HGQ BIT(0)
+
 #define R_BE_MUEDCA_BE_PARAM_0 0x10350
 #define R_BE_MUEDCA_BK_PARAM_0 0x10354
 #define R_BE_MUEDCA_VI_PARAM_0 0x10358
@@ -3792,6 +6055,74 @@
 #define B_BE_SET_MUEDCATIMER_TF_0 BIT(4)
 #define B_BE_MUEDCA_EN_0 BIT(0)
 
+#define R_BE_TB_CHK_CCA_NAV 0x103AC
+#define R_BE_TB_CHK_CCA_NAV_C1 0x143AC
+#define B_BE_TB_CHK_TX_NAV BIT(15)
+#define B_BE_TB_CHK_INTRA_NAV BIT(14)
+#define B_BE_TB_CHK_BASIC_NAV BIT(13)
+#define B_BE_TB_CHK_NO_GNT_WL BIT(12)
+#define B_BE_TB_CHK_EDCCA_S160 BIT(11)
+#define B_BE_TB_CHK_EDCCA_S80 BIT(10)
+#define B_BE_TB_CHK_EDCCA_S40 BIT(9)
+#define B_BE_TB_CHK_EDCCA_S20 BIT(8)
+#define B_BE_TB_CHK_CCA_S160 BIT(7)
+#define B_BE_TB_CHK_CCA_S80 BIT(6)
+#define B_BE_TB_CHK_CCA_S40 BIT(5)
+#define B_BE_TB_CHK_CCA_S20 BIT(4)
+#define B_BE_TB_CHK_EDCCA_BITMAP BIT(3)
+#define B_BE_TB_CHK_CCA_BITMAP BIT(2)
+#define B_BE_TB_CHK_EDCCA_P20 BIT(1)
+#define B_BE_TB_CHK_CCA_P20 BIT(0)
+
+#define R_BE_HE_SIFS_CHK_CCA_NAV 0x103B4
+#define R_BE_HE_SIFS_CHK_CCA_NAV_C1 0x143B4
+#define B_BE_HE_SIFS_CHK_TX_NAV BIT(15)
+#define B_BE_HE_SIFS_CHK_INTRA_NAV BIT(14)
+#define B_BE_HE_SIFS_CHK_BASIC_NAV BIT(13)
+#define B_BE_HE_SIFS_CHK_NO_GNT_WL BIT(12)
+#define B_BE_HE_SIFS_CHK_EDCCA_S160 BIT(11)
+#define B_BE_HE_SIFS_CHK_EDCCA_S80 BIT(10)
+#define B_BE_HE_SIFS_CHK_EDCCA_S40 BIT(9)
+#define B_BE_HE_SIFS_CHK_EDCCA_S20 BIT(8)
+#define B_BE_HE_SIFS_CHK_CCA_S160 BIT(7)
+#define B_BE_HE_SIFS_CHK_CCA_S80 BIT(6)
+#define B_BE_HE_SIFS_CHK_CCA_S40 BIT(5)
+#define B_BE_HE_SIFS_CHK_CCA_S20 BIT(4)
+#define B_BE_HE_SIFS_CHK_EDCCA_BITMAP BIT(3)
+#define B_BE_HE_SIFS_CHK_CCA_BITMAP BIT(2)
+#define B_BE_HE_SIFS_CHK_EDCCA_P20 BIT(1)
+#define B_BE_HE_SIFS_CHK_CCA_P20 BIT(0)
+
+#define R_BE_HE_CTN_CHK_CCA_NAV 0x103C4
+#define R_BE_HE_CTN_CHK_CCA_NAV_C1 0x143C4
+#define B_BE_HE_CTN_CHK_TX_NAV BIT(15)
+#define B_BE_HE_CTN_CHK_INTRA_NAV BIT(14)
+#define B_BE_HE_CTN_CHK_BASIC_NAV BIT(13)
+#define B_BE_HE_CTN_CHK_NO_GNT_WL BIT(12)
+#define B_BE_HE_CTN_CHK_EDCCA_S160 BIT(11)
+#define B_BE_HE_CTN_CHK_EDCCA_S80 BIT(10)
+#define B_BE_HE_CTN_CHK_EDCCA_S40 BIT(9)
+#define B_BE_HE_CTN_CHK_EDCCA_S20 BIT(8)
+#define B_BE_HE_CTN_CHK_CCA_S160 BIT(7)
+#define B_BE_HE_CTN_CHK_CCA_S80 BIT(6)
+#define B_BE_HE_CTN_CHK_CCA_S40 BIT(5)
+#define B_BE_HE_CTN_CHK_CCA_S20 BIT(4)
+#define B_BE_HE_CTN_CHK_EDCCA_BITMAP BIT(3)
+#define B_BE_HE_CTN_CHK_CCA_BITMAP BIT(2)
+#define B_BE_HE_CTN_CHK_EDCCA_P20 BIT(1)
+#define B_BE_HE_CTN_CHK_CCA_P20 BIT(0)
+
+#define R_BE_SCHEDULE_ERR_IMR 0x103E8
+#define R_BE_SCHEDULE_ERR_IMR_C1 0x143E8
+#define B_BE_FSM_TIMEOUT_ERR_INT_EN BIT(0)
+#define B_BE_SCHEDULE_ERR_IMR_CLR B_BE_FSM_TIMEOUT_ERR_INT_EN
+#define B_BE_SCHEDULE_ERR_IMR_SET B_BE_FSM_TIMEOUT_ERR_INT_EN
+
+#define R_BE_SCHEDULE_ERR_ISR 0x103EC
+#define R_BE_SCHEDULE_ERR_ISR_C1 0x143EC
+#define B_BE_SORT_NON_IDLE_ERR_INT BIT(1)
+#define B_BE_FSM_TIMEOUT_ERR_INT BIT(0)
+
 #define R_BE_PORT_CFG_P0 0x10400
 #define R_BE_PORT_CFG_P0_C1 0x14400
 #define B_BE_BCN_ERLY_SORT_EN_P0 BIT(18)
@@ -3906,12 +6237,51 @@
 #define R_BE_PORT_HGQ_WINDOW_CFG 0x105A0
 #define R_BE_PORT_HGQ_WINDOW_CFG_C1 0x145A0
 
+#define R_BE_PTCL_COMMON_SETTING_0 0x10800
+#define R_BE_PTCL_COMMON_SETTING_0_C1 0x14800
+#define B_BE_PCIE_MODE_MASK GENMASK(15, 14)
+#define B_BE_CPUMGQ_LIFETIME_EN BIT(8)
+#define B_BE_MGQ_LIFETIME_EN BIT(7)
+#define B_BE_LIFETIME_EN BIT(6)
+#define B_BE_DIS_PTCL_CLK_GATING BIT(5)
+#define B_BE_PTCL_TRIGGER_SS_EN_UL BIT(4)
+#define B_BE_PTCL_TRIGGER_SS_EN_1 BIT(3)
+#define B_BE_PTCL_TRIGGER_SS_EN_0 BIT(2)
+#define B_BE_CMAC_TX_MODE_1 BIT(1)
+#define B_BE_CMAC_TX_MODE_0 BIT(0)
+
+#define R_BE_TB_PPDU_CTRL 0x1080C
+#define R_BE_TB_PPDU_CTRL_C1 0x1480C
+#define B_BE_TB_PPDU_BK_DIS BIT(15)
+#define B_BE_TB_PPDU_BE_DIS BIT(14)
+#define B_BE_TB_PPDU_VI_DIS BIT(13)
+#define B_BE_TB_PPDU_VO_DIS BIT(12)
+#define B_BE_QOSNULL_UPD_MUEDCA_EN BIT(3)
+#define B_BE_TB_BYPASS_TXPWR BIT(2)
+#define B_BE_SW_PREFER_AC_MASK GENMASK(1, 0)
+
+#define R_BE_AMPDU_AGG_LIMIT 0x10810
+#define R_BE_AMPDU_AGG_LIMIT_C1 0x14810
+#define B_BE_AMPDU_MAX_TIME_MASK GENMASK(31, 24)
+#define AMPDU_MAX_TIME 0x9E
+#define B_BE_RA_TRY_RATE_AGG_LMT_MASK GENMASK(23, 16)
+#define B_BE_RTS_MAX_AGG_NUM_MASK GENMASK(15, 8)
+#define B_BE_MAX_AGG_NUM_MASK GENMASK(7, 0)
+
 #define R_BE_AGG_LEN_HT_0 0x10814
 #define R_BE_AGG_LEN_HT_0_C1 0x14814
 #define B_BE_AMPDU_MAX_LEN_HT_MASK GENMASK(31, 16)
 #define B_BE_RTS_TXTIME_TH_MASK GENMASK(15, 8)
 #define B_BE_RTS_LEN_TH_MASK GENMASK(7, 0)
 
+#define R_BE_SIFS_SETTING 0x10824
+#define R_BE_SIFS_SETTING_C1 0x14824
+#define B_BE_HW_CTS2SELF_PKT_LEN_TH_MASK GENMASK(31, 24)
+#define B_BE_HW_CTS2SELF_PKT_LEN_TH_TWW_MASK GENMASK(23, 18)
+#define B_BE_HW_CTS2SELF_EN BIT(16)
+#define B_BE_SPEC_SIFS_OFDM_PTCL_MASK GENMASK(15, 8)
+#define B_BE_SPEC_SIFS_CCK_PTCL_MASK GENMASK(7, 0)
+
 #define R_BE_MBSSID_DROP_0 0x1083C
 #define R_BE_MBSSID_DROP_0_C1 0x1483C
 #define B_BE_GI_LTF_FB_SEL BIT(30)
@@ -3930,6 +6300,375 @@
 #define R_BE_PTCL_BSS_COLOR_1_C1 0x148A4
 #define B_BE_BSS_COLOB_BE_PORT_4_MASK GENMASK(5, 0)
 
+#define R_BE_PTCL_IMR_2 0x108B8
+#define R_BE_PTCL_IMR_2_C1 0x148B8
+#define B_BE_NO_TRX_TIMEOUT_IMR BIT(1)
+#define B_BE_TX_IDLE_TIMEOUT_IMR BIT(0)
+#define B_BE_PTCL_IMR_2_CLR B_BE_TX_IDLE_TIMEOUT_IMR
+#define B_BE_PTCL_IMR_2_SET 0
+
+#define R_BE_PTCL_IMR0 0x108C0
+#define R_BE_PTCL_IMR0_C1 0x148C0
+#define B_BE_PTCL_ERROR_FLAG_IMR BIT(31)
+#define B_BE_FSM1_TIMEOUT_ERR_INT_EN BIT(1)
+#define B_BE_FSM_TIMEOUT_ERR_INT_EN BIT(0)
+#define B_BE_PTCL_IMR0_CLR (B_BE_FSM_TIMEOUT_ERR_INT_EN | \
+			    B_BE_FSM1_TIMEOUT_ERR_INT_EN | \
+			    B_BE_PTCL_ERROR_FLAG_IMR)
+#define B_BE_PTCL_IMR0_SET (B_BE_FSM_TIMEOUT_ERR_INT_EN | \
+			    B_BE_FSM1_TIMEOUT_ERR_INT_EN | \
+			    B_BE_PTCL_ERROR_FLAG_IMR)
+
+#define R_BE_PTCL_ISR0 0x108C4
+#define R_BE_PTCL_ISR0_C1 0x148C4
+#define B_BE_PTCL_ERROR_FLAG_ISR BIT(31)
+#define B_BE_FSM1_TIMEOUT_ERR BIT(1)
+#define B_BE_FSM_TIMEOUT_ERR BIT(0)
+
+#define R_BE_PTCL_IMR1 0x108C8
+#define R_BE_PTCL_IMR1_C1 0x148C8
+#define B_BE_F2PCMD_PKTID_IMR BIT(30)
+#define B_BE_F2PCMD_RD_PKTID_IMR BIT(29)
+#define B_BE_F2PCMD_ASSIGN_PKTID_IMR BIT(28)
+#define B_BE_F2PCMD_USER_ALLC_IMR BIT(27)
+#define B_BE_RX_SPF_U0_PKTID_IMR BIT(26)
+#define B_BE_TX_SPF_U1_PKTID_IMR BIT(25)
+#define B_BE_TX_SPF_U2_PKTID_IMR BIT(24)
+#define B_BE_TX_SPF_U3_PKTID_IMR BIT(23)
+#define B_BE_TX_RECORD_PKTID_IMR BIT(22)
+#define B_BE_TWTSP_QSEL_IMR BIT(14)
+#define B_BE_F2P_RLS_CTN_SEL_IMR BIT(13)
+#define B_BE_BCNQ_ORDER_IMR BIT(12)
+#define B_BE_Q_PKTID_IMR BIT(11)
+#define B_BE_D_PKTID_IMR BIT(10)
+#define B_BE_TXPRT_FULL_DROP_IMR BIT(9)
+#define B_BE_F2PCMDRPT_FULL_DROP_IMR BIT(8)
+#define B_BE_PTCL_IMR1_CLR (B_BE_F2PCMDRPT_FULL_DROP_IMR | \
+			    B_BE_TXPRT_FULL_DROP_IMR | \
+			    B_BE_D_PKTID_IMR | \
+			    B_BE_Q_PKTID_IMR | \
+			    B_BE_BCNQ_ORDER_IMR | \
+			    B_BE_F2P_RLS_CTN_SEL_IMR | \
+			    B_BE_TWTSP_QSEL_IMR | \
+			    B_BE_TX_RECORD_PKTID_IMR | \
+			    B_BE_TX_SPF_U3_PKTID_IMR | \
+			    B_BE_TX_SPF_U2_PKTID_IMR | \
+			    B_BE_TX_SPF_U1_PKTID_IMR | \
+			    B_BE_RX_SPF_U0_PKTID_IMR | \
+			    B_BE_F2PCMD_USER_ALLC_IMR | \
+			    B_BE_F2PCMD_ASSIGN_PKTID_IMR | \
+			    B_BE_F2PCMD_RD_PKTID_IMR | \
+			    B_BE_F2PCMD_PKTID_IMR)
+#define B_BE_PTCL_IMR1_SET B_BE_F2PCMD_USER_ALLC_IMR
+
+#define R_BE_PTCL_ISR1 0x108CC
+#define R_BE_PTCL_ISR1_C1 0x148CC
+#define B_BE_F2PCMD_PKTID_ERR BIT(30)
+#define B_BE_F2PCMD_RD_PKTID_ERR BIT(29)
+#define B_BE_F2PCMD_ASSIGN_PKTID_ERR BIT(28)
+#define B_BE_F2PCMD_USER_ALLC_ERR BIT(27)
+#define B_BE_RX_SPF_U0_PKTID_ERR BIT(26)
+#define B_BE_TX_SPF_U1_PKTID_ERR BIT(25)
+#define B_BE_TX_SPF_U2_PKTID_ERR BIT(24)
+#define B_BE_TX_SPF_U3_PKTID_ERR BIT(23)
+#define B_BE_TX_RECORD_PKTID_ERR BIT(22)
+#define B_BE_TWTSP_QSEL_ERR BIT(14)
+#define B_BE_F2P_RLS_CTN_SEL_ERR BIT(13)
+#define B_BE_BCNQ_ORDER_ERR BIT(12)
+#define B_BE_Q_PKTID_ERR BIT(11)
+#define B_BE_D_PKTID_ERR BIT(10)
+#define B_BE_TXPRT_FULL_DROP_ERR BIT(9)
+#define B_BE_F2PCMDRPT_FULL_DROP_ERR BIT(8)
+
+#define R_BE_PTCL_FSM_MON 0x108E8
+#define R_BE_PTCL_FSM_MON_C1 0x148E8
+#define B_BE_PTCL_FSM2_TO_MODE BIT(30)
+#define B_BE_PTCL_FSM2_TO_THR_MASK GENMASK(29, 24)
+#define B_BE_PTCL_FSM1_TO_MODE BIT(22)
+#define B_BE_PTCL_FSM1_TO_THR_MASK GENMASK(21, 16)
+#define B_BE_PTCL_FSM0_TO_MODE BIT(14)
+#define B_BE_PTCL_FSM0_TO_THR_MASK GENMASK(13, 8)
+#define B_BE_PTCL_TX_ARB_TO_MODE BIT(6)
+#define B_BE_PTCL_TX_ARB_TO_THR_MASK GENMASK(5, 0)
+
+#define R_BE_PTCL_TX_CTN_SEL 0x108EC
+#define R_BE_PTCL_TX_CTN_SEL_C1 0x148EC
+#define B_BE_PTCL_TXOP_STAT BIT(8)
+#define B_BE_PTCL_BUSY BIT(7)
+#define B_BE_PTCL_DROP BIT(5)
+#define B_BE_PTCL_TX_QUEUE_IDX_MASK GENMASK(4, 0)
+
+#define R_BE_RX_ERROR_FLAG 0x10C00
+#define R_BE_RX_ERROR_FLAG_C1 0x14C00
+#define B_BE_RX_CSI_NOT_RELEASE_ERROR BIT(31)
+#define B_BE_RX_GET_NULL_PKT_ERROR BIT(30)
+#define B_BE_RX_RU0_FSM_HANG_ERROR BIT(29)
+#define B_BE_RX_RU1_FSM_HANG_ERROR BIT(28)
+#define B_BE_RX_RU2_FSM_HANG_ERROR BIT(27)
+#define B_BE_RX_RU3_FSM_HANG_ERROR BIT(26)
+#define B_BE_RX_RU4_FSM_HANG_ERROR BIT(25)
+#define B_BE_RX_RU5_FSM_HANG_ERROR BIT(24)
+#define B_BE_RX_RU6_FSM_HANG_ERROR BIT(23)
+#define B_BE_RX_RU7_FSM_HANG_ERROR BIT(22)
+#define B_BE_RX_RXSTS_FSM_HANG_ERROR BIT(21)
+#define B_BE_RX_CSI_FSM_HANG_ERROR BIT(20)
+#define B_BE_RX_TXRPT_FSM_HANG_ERROR BIT(19)
+#define B_BE_RX_F2PCMD_FSM_HANG_ERROR BIT(18)
+#define B_BE_RX_RU0_ZERO_LENGTH_ERROR BIT(17)
+#define B_BE_RX_RU1_ZERO_LENGTH_ERROR BIT(16)
+#define B_BE_RX_RU2_ZERO_LENGTH_ERROR BIT(15)
+#define B_BE_RX_RU3_ZERO_LENGTH_ERROR BIT(14)
+#define B_BE_RX_RU4_ZERO_LENGTH_ERROR BIT(13)
+#define B_BE_RX_RU5_ZERO_LENGTH_ERROR BIT(12)
+#define B_BE_RX_RU6_ZERO_LENGTH_ERROR BIT(11)
+#define B_BE_RX_RU7_ZERO_LENGTH_ERROR BIT(10)
+#define B_BE_RX_RXSTS_ZERO_LENGTH_ERROR BIT(9)
+#define B_BE_RX_CSI_ZERO_LENGTH_ERROR BIT(8)
+#define B_BE_PLE_DATA_OPT_FSM_HANG BIT(7)
+#define B_BE_PLE_RXDATA_REQUEST_BUFFER_FSM_HANG BIT(6)
+#define B_BE_PLE_TXRPT_REQUEST_BUFFER_FSM_HANG BIT(5)
+#define B_BE_PLE_WD_OPT_FSM_HANG BIT(4)
+#define B_BE_PLE_ENQ_FSM_HANG BIT(3)
+#define B_BE_RXDATA_ENQUE_ORDER_ERROR BIT(2)
+#define B_BE_RXSTS_ENQUE_ORDER_ERROR BIT(1)
+#define B_BE_RX_CSI_PKT_NUM_ERROR BIT(0)
+
+#define R_BE_RX_ERROR_FLAG_IMR 0x10C04
+#define R_BE_RX_ERROR_FLAG_IMR_C1 0x14C04
+#define B_BE_RX_CSI_NOT_RELEASE_ERROR_IMR BIT(31)
+#define B_BE_RX_GET_NULL_PKT_ERROR_IMR BIT(30)
+#define B_BE_RX_RU0_FSM_HANG_ERROR_IMR BIT(29)
+#define B_BE_RX_RU1_FSM_HANG_ERROR_IMR BIT(28)
+#define B_BE_RX_RU2_FSM_HANG_ERROR_IMR BIT(27)
+#define B_BE_RX_RU3_FSM_HANG_ERROR_IMR BIT(26)
+#define B_BE_RX_RU4_FSM_HANG_ERROR_IMR BIT(25)
+#define B_BE_RX_RU5_FSM_HANG_ERROR_IMR BIT(24)
+#define B_BE_RX_RU6_FSM_HANG_ERROR_IMR BIT(23)
+#define B_BE_RX_RU7_FSM_HANG_ERROR_IMR BIT(22)
+#define B_BE_RX_RXSTS_FSM_HANG_ERROR_IMR BIT(21)
+#define B_BE_RX_CSI_FSM_HANG_ERROR_IMR BIT(20)
+#define B_BE_RX_TXRPT_FSM_HANG_ERROR_IMR BIT(19)
+#define B_BE_RX_F2PCMD_FSM_HANG_ERROR_IMR BIT(18)
+#define B_BE_RX_RU0_ZERO_LENGTH_ERROR_IMR BIT(17)
+#define B_BE_RX_RU1_ZERO_LENGTH_ERROR_IMR BIT(16)
+#define B_BE_RX_RU2_ZERO_LENGTH_ERROR_IMR BIT(15)
+#define B_BE_RX_RU3_ZERO_LENGTH_ERROR_IMR BIT(14)
+#define B_BE_RX_RU4_ZERO_LENGTH_ERROR_IMR BIT(13)
+#define B_BE_RX_RU5_ZERO_LENGTH_ERROR_IMR BIT(12)
+#define B_BE_RX_RU6_ZERO_LENGTH_ERROR_IMR BIT(11)
+#define B_BE_RX_RU7_ZERO_LENGTH_ERROR_IMR BIT(10)
+#define B_BE_RX_RXSTS_ZERO_LENGTH_ERROR_IMR BIT(9)
+#define B_BE_RX_CSI_ZERO_LENGTH_ERROR_IMR BIT(8)
+#define B_BE_PLE_DATA_OPT_FSM_HANG_IMR BIT(7)
+#define B_BE_PLE_RXDATA_REQUEST_BUFFER_FSM_HANG_IMR BIT(6)
+#define B_BE_PLE_TXRPT_REQUEST_BUFFER_FSM_HANG_IMR BIT(5)
+#define B_BE_PLE_WD_OPT_FSM_HANG_IMR BIT(4)
+#define B_BE_PLE_ENQ_FSM_HANG_IMR BIT(3)
+#define B_BE_RXDATA_ENQUE_ORDER_ERROR_IMR BIT(2)
+#define B_BE_RXSTS_ENQUE_ORDER_ERROR_IMR BIT(1)
+#define B_BE_RX_CSI_PKT_NUM_ERROR_IMR BIT(0)
+#define B_BE_RX_ERROR_FLAG_IMR_CLR (B_BE_RX_RXSTS_ZERO_LENGTH_ERROR_IMR | \
+				    B_BE_RX_RU7_ZERO_LENGTH_ERROR_IMR | \
+				    B_BE_RX_RU6_ZERO_LENGTH_ERROR_IMR | \
+				    B_BE_RX_RU5_ZERO_LENGTH_ERROR_IMR | \
+				    B_BE_RX_RU4_ZERO_LENGTH_ERROR_IMR | \
+				    B_BE_RX_RU3_ZERO_LENGTH_ERROR_IMR | \
+				    B_BE_RX_RU2_ZERO_LENGTH_ERROR_IMR | \
+				    B_BE_RX_RU1_ZERO_LENGTH_ERROR_IMR | \
+				    B_BE_RX_RU0_ZERO_LENGTH_ERROR_IMR | \
+				    B_BE_RX_F2PCMD_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_TXRPT_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_CSI_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_RXSTS_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_RU7_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_RU6_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_RU5_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_RU4_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_RU3_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_RU2_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_RU1_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_RU0_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_GET_NULL_PKT_ERROR_IMR)
+#define B_BE_RX_ERROR_FLAG_IMR_SET (B_BE_RX_RXSTS_ZERO_LENGTH_ERROR_IMR | \
+				    B_BE_RX_RU7_ZERO_LENGTH_ERROR_IMR | \
+				    B_BE_RX_RU6_ZERO_LENGTH_ERROR_IMR | \
+				    B_BE_RX_RU5_ZERO_LENGTH_ERROR_IMR | \
+				    B_BE_RX_RU4_ZERO_LENGTH_ERROR_IMR | \
+				    B_BE_RX_RU3_ZERO_LENGTH_ERROR_IMR | \
+				    B_BE_RX_RU2_ZERO_LENGTH_ERROR_IMR | \
+				    B_BE_RX_RU1_ZERO_LENGTH_ERROR_IMR | \
+				    B_BE_RX_RU0_ZERO_LENGTH_ERROR_IMR | \
+				    B_BE_RX_F2PCMD_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_TXRPT_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_CSI_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_RXSTS_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_RU7_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_RU6_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_RU5_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_RU4_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_RU3_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_RU2_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_RU1_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_RU0_FSM_HANG_ERROR_IMR | \
+				    B_BE_RX_GET_NULL_PKT_ERROR_IMR)
+
+#define R_BE_RX_CTRL_1 0x10C0C
+#define R_BE_RX_CTRL_1_C1 0x14C0C
+#define B_BE_RXDMA_TXRPT_QUEUE_ID_SW_MASK GENMASK(30, 25)
+#define B_BE_RXDMA_F2PCMDRPT_QUEUE_ID_SW_MASK GENMASK(23, 18)
+#define B_BE_RXDMA_TXRPT_PORT_ID_SW_MASK GENMASK(17, 14)
+#define B_BE_RXDMA_F2PCMDRPT_PORT_ID_SW_MASK GENMASK(13, 10)
+#define B_BE_DBG_SEL_MASK GENMASK(1, 0)
+#define WLCPU_RXCH2_QID 0xA
+
+#define R_BE_TX_ERROR_FLAG 0x10C6C
+#define R_BE_TX_ERROR_FLAG_C1 0x14C6C
+#define B_BE_TX_RU0_FSM_HANG_ERROR BIT(31)
+#define B_BE_TX_RU1_FSM_HANG_ERROR BIT(30)
+#define B_BE_TX_RU2_FSM_HANG_ERROR BIT(29)
+#define B_BE_TX_RU3_FSM_HANG_ERROR BIT(28)
+#define B_BE_TX_RU4_FSM_HANG_ERROR BIT(27)
+#define B_BE_TX_RU5_FSM_HANG_ERROR BIT(26)
+#define B_BE_TX_RU6_FSM_HANG_ERROR BIT(25)
+#define B_BE_TX_RU7_FSM_HANG_ERROR BIT(24)
+#define B_BE_TX_RU8_FSM_HANG_ERROR BIT(23)
+#define B_BE_TX_RU9_FSM_HANG_ERROR BIT(22)
+#define B_BE_TX_RU10_FSM_HANG_ERROR BIT(21)
+#define B_BE_TX_RU11_FSM_HANG_ERROR BIT(20)
+#define B_BE_TX_RU12_FSM_HANG_ERROR BIT(19)
+#define B_BE_TX_RU13_FSM_HANG_ERROR BIT(18)
+#define B_BE_TX_RU14_FSM_HANG_ERROR BIT(17)
+#define B_BE_TX_RU15_FSM_HANG_ERROR BIT(16)
+#define B_BE_TX_CSI_FSM_HANG_ERROR BIT(15)
+#define B_BE_TX_WD_PLD_ID_FSM_HANG_ERROR BIT(14)
+
+#define R_BE_TX_ERROR_FLAG_IMR 0x10C70
+#define R_BE_TX_ERROR_FLAG_IMR_C1 0x14C70
+#define B_BE_TX_RU0_FSM_HANG_ERROR_IMR BIT(31)
+#define B_BE_TX_RU1_FSM_HANG_ERROR_IMR BIT(30)
+#define B_BE_TX_RU2_FSM_HANG_ERROR_IMR BIT(29)
+#define B_BE_TX_RU3_FSM_HANG_ERROR_IMR BIT(28)
+#define B_BE_TX_RU4_FSM_HANG_ERROR_IMR BIT(27)
+#define B_BE_TX_RU5_FSM_HANG_ERROR_IMR BIT(26)
+#define B_BE_TX_RU6_FSM_HANG_ERROR_IMR BIT(25)
+#define B_BE_TX_RU7_FSM_HANG_ERROR_IMR BIT(24)
+#define B_BE_TX_RU8_FSM_HANG_ERROR_IMR BIT(23)
+#define B_BE_TX_RU9_FSM_HANG_ERROR_IMR BIT(22)
+#define B_BE_TX_RU10_FSM_HANG_ERROR_IMR BIT(21)
+#define B_BE_TX_RU11_FSM_HANG_ERROR_IMR BIT(20)
+#define B_BE_TX_RU12_FSM_HANG_ERROR_IMR BIT(19)
+#define B_BE_TX_RU13_FSM_HANG_ERROR_IMR BIT(18)
+#define B_BE_TX_RU14_FSM_HANG_ERROR_IMR BIT(17)
+#define B_BE_TX_RU15_FSM_HANG_ERROR_IMR BIT(16)
+#define B_BE_TX_CSI_FSM_HANG_ERROR_IMR BIT(15)
+#define B_BE_TX_WD_PLD_ID_FSM_HANG_ERROR_IMR BIT(14)
+#define B_BE_TX_ERROR_FLAG_IMR_CLR (B_BE_TX_WD_PLD_ID_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_CSI_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU15_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU14_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU13_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU12_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU11_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU10_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU9_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU8_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU7_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU6_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU5_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU4_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU3_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU2_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU1_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU0_FSM_HANG_ERROR_IMR)
+#define B_BE_TX_ERROR_FLAG_IMR_SET (B_BE_TX_WD_PLD_ID_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_CSI_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU15_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU14_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU13_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU12_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU11_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU10_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU9_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU8_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU7_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU6_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU5_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU4_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU3_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU2_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU1_FSM_HANG_ERROR_IMR | \
+				    B_BE_TX_RU0_FSM_HANG_ERROR_IMR)
+
+#define R_BE_RX_ERROR_FLAG_1 0x10C84
+#define R_BE_RX_ERROR_FLAG_1_C1 0x14C84
+#define B_BE_RX_RU8_FSM_HANG_ERROR BIT(29)
+#define B_BE_RX_RU9_FSM_HANG_ERROR BIT(28)
+#define B_BE_RX_RU10_FSM_HANG_ERROR BIT(27)
+#define B_BE_RX_RU11_FSM_HANG_ERROR BIT(26)
+#define B_BE_RX_RU12_FSM_HANG_ERROR BIT(25)
+#define B_BE_RX_RU13_FSM_HANG_ERROR BIT(24)
+#define B_BE_RX_RU14_FSM_HANG_ERROR BIT(23)
+#define B_BE_RX_RU15_FSM_HANG_ERROR BIT(22)
+#define B_BE_RX_RU8_ZERO_LENGTH_ERROR BIT(17)
+#define B_BE_RX_RU9_ZERO_LENGTH_ERROR BIT(16)
+#define B_BE_RX_RU10_ZERO_LENGTH_ERROR BIT(15)
+#define B_BE_RX_RU11_ZERO_LENGTH_ERROR BIT(14)
+#define B_BE_RX_RU12_ZERO_LENGTH_ERROR BIT(13)
+#define B_BE_RX_RU13_ZERO_LENGTH_ERROR BIT(12)
+#define B_BE_RX_RU14_ZERO_LENGTH_ERROR BIT(11)
+#define B_BE_RX_RU15_ZERO_LENGTH_ERROR BIT(10)
+
+#define R_BE_RX_ERROR_FLAG_IMR_1 0x10C88
+#define R_BE_RX_ERROR_FLAG_IMR_1_C1 0x14C88
+#define B_BE_RX_RU8_FSM_HANG_ERROR_IMR BIT(29)
+#define B_BE_RX_RU9_FSM_HANG_ERROR_IMR BIT(28)
+#define B_BE_RX_RU10_FSM_HANG_ERROR_IMR BIT(27)
+#define B_BE_RX_RU11_FSM_HANG_ERROR_IMR BIT(26)
+#define B_BE_RX_RU12_FSM_HANG_ERROR_IMR BIT(25)
+#define B_BE_RX_RU13_FSM_HANG_ERROR_IMR BIT(24)
+#define B_BE_RX_RU14_FSM_HANG_ERROR_IMR BIT(23)
+#define B_BE_RX_RU15_FSM_HANG_ERROR_IMR BIT(22)
+#define B_BE_RX_RU8_ZERO_LENGTH_ERROR_IMR BIT(17)
+#define B_BE_RX_RU9_ZERO_LENGTH_ERROR_IMR BIT(16)
+#define B_BE_RX_RU10_ZERO_LENGTH_ERROR_IMR BIT(15)
+#define B_BE_RX_RU11_ZERO_LENGTH_ERROR_IMR BIT(14)
+#define B_BE_RX_RU12_ZERO_LENGTH_ERROR_IMR BIT(13)
+#define B_BE_RX_RU13_ZERO_LENGTH_ERROR_IMR BIT(12)
+#define B_BE_RX_RU14_ZERO_LENGTH_ERROR_IMR BIT(11)
+#define B_BE_RX_RU15_ZERO_LENGTH_ERROR_IMR BIT(10)
+#define B_BE_TX_ERROR_FLAG_IMR_1_CLR (B_BE_RX_RU8_FSM_HANG_ERROR_IMR | \
+				      B_BE_RX_RU9_FSM_HANG_ERROR_IMR | \
+				      B_BE_RX_RU10_FSM_HANG_ERROR_IMR | \
+				      B_BE_RX_RU11_FSM_HANG_ERROR_IMR | \
+				      B_BE_RX_RU12_FSM_HANG_ERROR_IMR | \
+				      B_BE_RX_RU13_FSM_HANG_ERROR_IMR | \
+				      B_BE_RX_RU14_FSM_HANG_ERROR_IMR | \
+				      B_BE_RX_RU15_FSM_HANG_ERROR_IMR | \
+				      B_BE_RX_RU8_ZERO_LENGTH_ERROR_IMR | \
+				      B_BE_RX_RU9_ZERO_LENGTH_ERROR_IMR | \
+				      B_BE_RX_RU10_ZERO_LENGTH_ERROR_IMR | \
+				      B_BE_RX_RU11_ZERO_LENGTH_ERROR_IMR | \
+				      B_BE_RX_RU12_ZERO_LENGTH_ERROR_IMR | \
+				      B_BE_RX_RU13_ZERO_LENGTH_ERROR_IMR | \
+				      B_BE_RX_RU14_ZERO_LENGTH_ERROR_IMR | \
+				      B_BE_RX_RU15_ZERO_LENGTH_ERROR_IMR)
+#define B_BE_TX_ERROR_FLAG_IMR_1_SET (B_BE_RX_RU8_FSM_HANG_ERROR_IMR | \
+				      B_BE_RX_RU9_FSM_HANG_ERROR_IMR | \
+				      B_BE_RX_RU10_FSM_HANG_ERROR_IMR | \
+				      B_BE_RX_RU11_FSM_HANG_ERROR_IMR | \
+				      B_BE_RX_RU12_FSM_HANG_ERROR_IMR | \
+				      B_BE_RX_RU13_FSM_HANG_ERROR_IMR | \
+				      B_BE_RX_RU14_FSM_HANG_ERROR_IMR | \
+				      B_BE_RX_RU15_FSM_HANG_ERROR_IMR | \
+				      B_BE_RX_RU8_ZERO_LENGTH_ERROR_IMR | \
+				      B_BE_RX_RU9_ZERO_LENGTH_ERROR_IMR | \
+				      B_BE_RX_RU10_ZERO_LENGTH_ERROR_IMR | \
+				      B_BE_RX_RU11_ZERO_LENGTH_ERROR_IMR | \
+				      B_BE_RX_RU12_ZERO_LENGTH_ERROR_IMR | \
+				      B_BE_RX_RU13_ZERO_LENGTH_ERROR_IMR | \
+				      B_BE_RX_RU14_ZERO_LENGTH_ERROR_IMR | \
+				      B_BE_RX_RU15_ZERO_LENGTH_ERROR_IMR)
+
 #define R_BE_WMTX_MOREDATA_TSFT_STMP_CTL 0x10E08
 #define R_BE_WMTX_MOREDATA_TSFT_STMP_CTL_C1 0x14E08
 #define B_BE_TSFT_OFS_MASK GENMASK(31, 16)
@@ -3937,6 +6676,173 @@
 #define B_BE_UPD_HGQMD BIT(1)
 #define B_BE_UPD_TIMIE BIT(0)
 
+#define R_BE_WMTX_TCR_BE_4 0x10E2C
+#define R_BE_WMTX_TCR_BE_4_C1 0x14E2C
+#define B_BE_UL_EHT_MUMIMO_LTF_MODE BIT(30)
+#define B_BE_UL_HE_MUMIMO_LTF_MODE BIT(29)
+#define B_BE_EHT_HE_PPDU_4XLTF_ZLD_USTIMER_MASK GENMASK(28, 24)
+#define B_BE_EHT_HE_PPDU_2XLTF_ZLD_USTIMER_MASK GENMASK(20, 16)
+#define B_BE_NON_LEGACY_PPDU_ZLD_USTIMER_MASK GENMASK(12, 8)
+#define B_BE_LEGACY_PPDU_ZLD_USTIMER_MASK GENMASK(4, 0)
+
+#define R_BE_RSP_CHK_SIG 0x11000
+#define R_BE_RSP_CHK_SIG_C1 0x15000
+#define B_BE_RSP_STATIC_RTS_CHK_SERV_BW_EN BIT(30)
+#define B_BE_RSP_TBPPDU_CHK_PWR BIT(29)
+#define B_BE_RESP_PAIR_MACID_LEN_EN BIT(25)
+#define B_BE_RESP_TX_ABORT_TEST_EN BIT(24)
+#define B_BE_RESP_ER_SU_RU106_EN BIT(23)
+#define B_BE_RESP_ER_SU_EN BIT(22)
+#define B_BE_TXDATA_END_PS_OPT BIT(18)
+#define B_BE_CHECK_SOUNDING_SEQ BIT(17)
+#define B_BE_RXBA_IGNOREA2 BIT(16)
+#define B_BE_ACKTO_CCK_MASK GENMASK(15, 8)
+#define B_BE_ACKTO_MASK GENMASK(8, 0)
+
+#define R_BE_TRXPTCL_RESP_0 0x11004
+#define R_BE_TRXPTCL_RESP_0_C1 0x15004
+#define B_BE_WMAC_RESP_STBC_EN BIT(31)
+#define B_BE_WMAC_RXFTM_TXACK_SB BIT(30)
+#define B_BE_WMAC_RXFTM_TXACKBWEQ BIT(29)
+#define B_BE_RESP_TB_CHK_TXTIME BIT(24)
+#define B_BE_RSP_CHK_CCA BIT(23)
+#define B_BE_WMAC_LDPC_EN BIT(22)
+#define B_BE_WMAC_SGIEN BIT(21)
+#define B_BE_WMAC_SPLCPEN BIT(20)
+#define B_BE_RESP_EHT_MCS15_REF BIT(19)
+#define B_BE_RESP_EHT_MCS14_REF BIT(18)
+#define B_BE_WMAC_BESP_EARLY_TXBA BIT(17)
+#define B_BE_WMAC_MBA_DUR_FORCE BIT(16)
+#define B_BE_WMAC_SPEC_SIFS_OFDM_MASK GENMASK(15, 8)
+#define WMAC_SPEC_SIFS_OFDM_1115E 0x11
+#define B_BE_WMAC_SPEC_SIFS_CCK_MASK GENMASK(7, 0)
+
+#define R_BE_TRXPTCL_RESP_1 0x11008
+#define R_BE_TRXPTCL_RESP_1_C1 0x15008
+#define B_BE_WMAC_RESP_SR_MODE_EN BIT(31)
+#define B_BE_FTM_RRSR_RATE_EN_MASK GENMASK(28, 24)
+#define B_BE_NESS_MASK GENMASK(23, 22)
+#define B_BE_WMAC_RESP_DOPPLEB_BE_EN BIT(21)
+#define B_BE_WMAC_RESP_DCM_EN BIT(20)
+#define B_BE_WMAC_CLR_ABORT_RESP_TX_CNT BIT(15)
+#define B_BE_WMAC_RESP_REF_RATE_SEL BIT(12)
+#define B_BE_WMAC_RESP_REF_RATE_MASK GENMASK(11, 0)
+
+#define R_BE_MAC_LOOPBACK 0x11020
+#define R_BE_MAC_LOOPBACK_C1 0x15020
+#define B_BE_MACLBK_DIS_GCLK BIT(30)
+#define B_BE_MACLBK_STS_EN BIT(29)
+#define B_BE_MACLBK_RDY_PERIOD_MASK GENMASK(28, 17)
+#define B_BE_MACLBK_PLCP_DLY_MASK GENMASK(16, 8)
+#define S_BE_MACLBK_PLCP_DLY_DEF 0x28
+#define B_BE_MACLBK_RDY_NUM_MASK GENMASK(7, 3)
+#define B_BE_MACLBK_EN BIT(0)
+
+#define R_BE_WMAC_NAV_CTL 0x11080
+#define R_BE_WMAC_NAV_CTL_C1 0x15080
+#define B_BE_WMAC_NAV_UPPER_EN BIT(26)
+#define B_BE_WMAC_0P125US_TIMER_MASK GENMASK(25, 18)
+#define B_BE_WMAC_PLCP_UP_NAV_EN BIT(17)
+#define B_BE_WMAC_TF_UP_NAV_EN BIT(16)
+#define B_BE_WMAC_NAV_UPPER_MASK GENMASK(15, 8)
+#define NAV_25MS 0xC4
+#define B_BE_WMAC_RTS_RST_DUR_MASK GENMASK(7, 0)
+
+#define R_BE_RXTRIG_TEST_USER_2 0x110B0
+#define R_BE_RXTRIG_TEST_USER_2_C1 0x150B0
+#define B_BE_RXTRIG_MACID_MASK GENMASK(31, 24)
+#define B_BE_RXTRIG_RU26_DIS BIT(21)
+#define B_BE_RXTRIG_FCSCHK_EN BIT(20)
+#define B_BE_RXTRIG_PORT_SEL_MASK GENMASK(19, 17)
+#define B_BE_RXTRIG_EN BIT(16)
+#define B_BE_RXTRIG_USERINFO_2_MASK GENMASK(15, 0)
+
+#define R_BE_TRXPTCL_ERROR_INDICA_MASK 0x110BC
+#define R_BE_TRXPTCL_ERROR_INDICA_MASK_C1 0x150BC
+#define B_BE_WMAC_FTM_TIMEOUT_MODE BIT(30)
+#define B_BE_WMAC_FTM_TIMEOUT_THR_MASK GENMASK(29, 24)
+#define B_BE_WMAC_MODE BIT(22)
+#define B_BE_WMAC_TIMETOUT_THR_MASK GENMASK(21, 16)
+#define B_BE_RMAC_BFMER BIT(9)
+#define B_BE_RMAC_FTM BIT(8)
+#define B_BE_RMAC_CSI BIT(7)
+#define B_BE_TMAC_MIMO_CTRL BIT(6)
+#define B_BE_TMAC_RXTB BIT(5)
+#define B_BE_TMAC_HWSIGB_GEN BIT(4)
+#define B_BE_TMAC_TXPLCP BIT(3)
+#define B_BE_TMAC_RESP BIT(2)
+#define B_BE_TMAC_TXCTL BIT(1)
+#define B_BE_TMAC_MACTX BIT(0)
+#define B_BE_TRXPTCL_ERROR_INDICA_MASK_CLR (B_BE_TMAC_MACTX | \
+					    B_BE_TMAC_TXCTL | \
+					    B_BE_TMAC_RESP | \
+					    B_BE_TMAC_TXPLCP | \
+					    B_BE_TMAC_HWSIGB_GEN | \
+					    B_BE_TMAC_RXTB | \
+					    B_BE_TMAC_MIMO_CTRL | \
+					    B_BE_RMAC_CSI | \
+					    B_BE_RMAC_FTM | \
+					    B_BE_RMAC_BFMER)
+#define B_BE_TRXPTCL_ERROR_INDICA_MASK_SET (B_BE_TMAC_MACTX | \
+					    B_BE_TMAC_TXCTL | \
+					    B_BE_TMAC_RESP | \
+					    B_BE_TMAC_TXPLCP | \
+					    B_BE_TMAC_HWSIGB_GEN | \
+					    B_BE_TMAC_RXTB | \
+					    B_BE_TMAC_MIMO_CTRL | \
+					    B_BE_RMAC_CSI | \
+					    B_BE_RMAC_FTM | \
+					    B_BE_RMAC_BFMER)
+
+#define R_BE_TRXPTCL_ERROR_INDICA 0x110C0
+#define R_BE_TRXPTCL_ERROR_INDICA_C1 0x150C0
+#define B_BE_BFMER_ERR_FLAG BIT(9)
+#define B_BE_FTM_ERROR_FLAG_CLR BIT(8)
+#define B_BE_CSI_ERROR_FLAG_CLR BIT(7)
+#define B_BE_MIMOCTRL_ERROR_FLAG_CLR BIT(6)
+#define B_BE_RXTB_ERROR_FLAG_CLR BIT(5)
+#define B_BE_HWSIGB_GEN_ERROR_FLAG_CLR BIT(4)
+#define B_BE_TXPLCP_ERROR_FLAG_CLR BIT(3)
+#define B_BE_RESP_ERROR_FLAG_CLR BIT(2)
+#define B_BE_TXCTL_ERROR_FLAG_CLR BIT(1)
+#define B_BE_MACTX_ERROR_FLAG_CLR BIT(0)
+
+#define R_BE_DBGSEL_TRXPTCL 0x110F4
+#define R_BE_DBGSEL_TRXPTCL_C1 0x150F4
+#define B_BE_WMAC_CHNSTS_STATE_MASK GENMASK(19, 16)
+#define B_BE_DBGSEL_TRIGCMD_SEL_MASK GENMASK(11, 8)
+#define B_BE_DBGSEL_TRXPTCL_MASK GENMASK(7, 0)
+
+#define R_BE_PHYINFO_ERR_IMR_V1 0x110F8
+#define R_BE_PHYINFO_ERR_IMR_V1_C1 0x150F8
+#define B_BE_PHYINTF_RXTB_WIDTH_MASK GENMASK(31, 30)
+#define B_BE_PHYINTF_RXTB_EN_PHASE_MASK GENMASK(29, 28)
+#define B_BE_PHYINTF_MIMO_WIDTH_MASK GENMASK(27, 26)
+#define B_BE_PHYINTF_MIMO_EN_PHASE_MASK GENMASK(25, 24)
+#define B_BE_PHYINTF_TIMEOUT_THR_V1_MASK GENMASK(21, 16)
+#define B_BE_CSI_ON_TIMEOUT_EN BIT(5)
+#define B_BE_STS_ON_TIMEOUT_EN BIT(4)
+#define B_BE_DATA_ON_TIMEOUT_EN BIT(3)
+#define B_BE_OFDM_CCA_TIMEOUT_EN BIT(2)
+#define B_BE_CCK_CCA_TIMEOUT_EN BIT(1)
+#define B_BE_PHY_TXON_TIMEOUT_EN BIT(0)
+#define  B_BE_PHYINFO_ERR_IMR_V1_CLR (B_BE_PHY_TXON_TIMEOUT_EN | \
+				      B_BE_CCK_CCA_TIMEOUT_EN | \
+				      B_BE_OFDM_CCA_TIMEOUT_EN | \
+				      B_BE_DATA_ON_TIMEOUT_EN | \
+				      B_BE_STS_ON_TIMEOUT_EN | \
+				      B_BE_CSI_ON_TIMEOUT_EN)
+#define B_BE_PHYINFO_ERR_IMR_V1_SET 0
+
+#define R_BE_PHYINFO_ERR_ISR 0x110FC
+#define R_BE_PHYINFO_ERR_ISR_C1 0x150FC
+#define B_BE_CSI_ON_TIMEOUT_ERR BIT(5)
+#define B_BE_STS_ON_TIMEOUT_ERR BIT(4)
+#define B_BE_DATA_ON_TIMEOUT_ERR BIT(3)
+#define B_BE_OFDM_CCA_TIMEOUT_ERR BIT(2)
+#define B_BE_CCK_CCA_TIMEOUT_ERR BIT(1)
+#define B_BE_PHY_TXON_TIMEOUT_ERR BIT(0)
+
 #define R_BE_BFMEE_RESP_OPTION 0x11180
 #define R_BE_BFMEE_RESP_OPTION_C1 0x15180
 #define B_BE_BFMEE_CSI_SEC_TYPE_SH 20
@@ -3992,6 +6898,103 @@
 #define B_BE_BFMEE_HT_CSI_RATE_MASK GENMASK(7, 0)
 #define CSI_INIT_RATE_EHT 0x3
 
+#define R_BE_WMAC_ACK_BA_RESP_LEGACY 0x11200
+#define R_BE_WMAC_ACK_BA_RESP_LEGACY_C1 0x15200
+#define B_BE_ACK_BA_RESP_LEGACY_CHK_NSTR BIT(16)
+#define B_BE_ACK_BA_RESP_LEGACY_CHK_TX_NAV BIT(15)
+#define B_BE_ACK_BA_RESP_LEGACY_CHK_INTRA_NAV BIT(14)
+#define B_BE_ACK_BA_RESP_LEGACY_CHK_BASIC_NAV BIT(13)
+#define B_BE_ACK_BA_RESP_LEGACY_CHK_BTCCA BIT(12)
+#define B_BE_ACK_BA_RESP_LEGACY_CHK_SEC_EDCCA160 BIT(11)
+#define B_BE_ACK_BA_RESP_LEGACY_CHK_SEC_EDCCA80 BIT(10)
+#define B_BE_ACK_BA_RESP_LEGACY_CHK_SEC_EDCCA40 BIT(9)
+#define B_BE_ACK_BA_RESP_LEGACY_CHK_SEC_EDCCA20 BIT(8)
+#define B_BE_ACK_BA_RESP_LEGACY_CHK_EDCCA_PER20_BMP BIT(7)
+#define B_BE_ACK_BA_RESP_LEGACY_CHK_CCA_PER20_BMP BIT(6)
+#define B_BE_ACK_BA_RESP_LEGACY_CHK_SEC_CCA160 BIT(5)
+#define B_BE_ACK_BA_RESP_LEGACY_CHK_SEC_CCA80 BIT(4)
+#define B_BE_ACK_BA_RESP_LEGACY_CHK_SEC_CCA40 BIT(3)
+#define B_BE_ACK_BA_RESP_LEGACY_CHK_SEC_CCA20 BIT(2)
+#define B_BE_ACK_BA_RESP_LEGACY_CHK_EDCCA BIT(1)
+#define B_BE_ACK_BA_RESP_LEGACY_CHK_CCA BIT(0)
+
+#define R_BE_WMAC_ACK_BA_RESP_HE 0x11204
+#define R_BE_WMAC_ACK_BA_RESP_HE_C1 0x15204
+#define B_BE_ACK_BA_RESP_HE_CHK_NSTR BIT(16)
+#define B_BE_ACK_BA_RESP_HE_CHK_TX_NAV BIT(15)
+#define B_BE_ACK_BA_RESP_HE_CHK_INTRA_NAV BIT(14)
+#define B_BE_ACK_BA_RESP_HE_CHK_BASIC_NAV BIT(13)
+#define B_BE_ACK_BA_RESP_HE_CHK_BTCCA BIT(12)
+#define B_BE_ACK_BA_RESP_HE_CHK_SEC_EDCCA160 BIT(11)
+#define B_BE_ACK_BA_RESP_HE_CHK_SEC_EDCCA80 BIT(10)
+#define B_BE_ACK_BA_RESP_HE_CHK_SEC_EDCCA40 BIT(9)
+#define B_BE_ACK_BA_RESP_HE_CHK_SEC_EDCCA20 BIT(8)
+#define B_BE_ACK_BA_RESP_HE_CHK_EDCCA_PER20_BMP BIT(7)
+#define B_BE_ACK_BA_RESP_HE_CHK_CCA_PER20_BMP BIT(6)
+#define B_BE_ACK_BA_RESP_HE_CHK_SEC_CCA160 BIT(5)
+#define B_BE_ACK_BA_RESP_HE_CHK_SEC_CCA80 BIT(4)
+#define B_BE_ACK_BA_RESP_HE_CHK_SEC_CCA40 BIT(3)
+#define B_BE_ACK_BA_RESP_HE_CHK_SEC_CCA20 BIT(2)
+#define B_BE_ACK_BA_RESP_HE_CHK_EDCCA BIT(1)
+#define B_BE_ACK_BA_RESP_HE_CHK_CCA BIT(0)
+
+#define R_BE_WMAC_ACK_BA_RESP_EHT_LEG_PUNC 0x11208
+#define R_BE_WMAC_ACK_BA_RESP_EHT_LEG_PUNC_C1 0x15208
+#define B_BE_ACK_BA_EHT_LEG_PUNC_CHK_NSTR BIT(16)
+#define B_BE_ACK_BA_EHT_LEG_PUNC_CHK_TX_NAV BIT(15)
+#define B_BE_ACK_BA_EHT_LEG_PUNC_CHK_INTRA_NAV BIT(14)
+#define B_BE_ACK_BA_EHT_LEG_PUNC_CHK_BASIC_NAV BIT(13)
+#define B_BE_ACK_BA_EHT_LEG_PUNC_CHK_BTCCA BIT(12)
+#define B_BE_ACK_BA_EHT_LEG_PUNC_CHK_SEC_EDCCA160 BIT(11)
+#define B_BE_ACK_BA_EHT_LEG_PUNC_CHK_SEC_EDCCA80 BIT(10)
+#define B_BE_ACK_BA_EHT_LEG_PUNC_CHK_SEC_EDCCA40 BIT(9)
+#define B_BE_ACK_BA_EHT_LEG_PUNC_CHK_SEC_EDCCA20 BIT(8)
+#define B_BE_ACK_BA_EHT_LEG_PUNC_CHK_EDCCA_PER20_BMP BIT(7)
+#define B_BE_ACK_BA_EHT_LEG_PUNC_CHK_CCA_PER20_BMP BIT(6)
+#define B_BE_ACK_BA_EHT_LEG_PUNC_CHK_SEC_CCA160 BIT(5)
+#define B_BE_ACK_BA_EHT_LEG_PUNC_CHK_SEC_CCA80 BIT(4)
+#define B_BE_ACK_BA_EHT_LEG_PUNC_CHK_SEC_CCA40 BIT(3)
+#define B_BE_ACK_BA_EHT_LEG_PUNC_CHK_SEC_CCA20 BIT(2)
+#define B_BE_ACK_BA_EHT_LEG_PUNC_CHK_EDCCA BIT(1)
+#define B_BE_ACK_BA_EHT_LEG_PUNC_CHK_CCA BIT(0)
+
+#define R_BE_RCR 0x11400
+#define R_BE_RCR_C1 0x15400
+#define B_BE_BUSY_CHKSN BIT(15)
+#define B_BE_DYN_CHEN BIT(14)
+#define B_BE_AUTO_RST BIT(13)
+#define B_BE_TIMER_SEL BIT(12)
+#define B_BE_STOP_RX_IN BIT(11)
+#define B_BE_PSR_RDY_CHKDIS BIT(10)
+#define B_BE_DRV_INFO_SZ_MASK GENMASK(9, 8)
+#define B_BE_HDR_CNV_SZ_MASK GENMASK(7, 6)
+#define B_BE_PHY_RPT_SZ_MASK GENMASK(5, 4)
+#define B_BE_CH_EN BIT(0)
+
+#define R_BE_DLK_PROTECT_CTL 0x11402
+#define R_BE_DLK_PROTECT_CTL_C1 0x15402
+#define B_BE_RX_DLK_CCA_TIME_MASK GENMASK(15, 8)
+#define TRXCFG_RMAC_CCA_TO 32
+#define B_BE_RX_DLK_DATA_TIME_MASK GENMASK(7, 4)
+#define TRXCFG_RMAC_DATA_TO 15
+#define B_BE_RX_DLK_RST_FSM BIT(3)
+#define B_BE_RX_DLK_RST_SKIPDMA BIT(2)
+#define B_BE_RX_DLK_RST_EN BIT(1)
+#define B_BE_RX_DLK_INT_EN BIT(0)
+
+#define R_BE_PLCP_HDR_FLTR 0x11404
+#define R_BE_PLCP_HDR_FLTR_C1 0x15404
+#define B_BE_PLCP_RXFA_RESET_TYPE_MASK GENMASK(15, 12)
+#define B_BE_PLCP_RXFA_RESET_EN BIT(11)
+#define B_BE_DIS_CHK_MIN_LEN BIT(8)
+#define B_BE_HE_SIGB_CRC_CHK BIT(6)
+#define B_BE_VHT_MU_SIGB_CRC_CHK BIT(5)
+#define B_BE_VHT_SU_SIGB_CRC_CHK BIT(4)
+#define B_BE_SIGA_CRC_CHK BIT(3)
+#define B_BE_LSIG_PARITY_CHK_EN BIT(2)
+#define B_BE_CCK_SIG_CHK BIT(1)
+#define B_BE_CCK_CRC_CHK BIT(0)
+
 #define R_BE_RX_FLTR_OPT 0x11420
 #define R_BE_RX_FLTR_OPT_C1 0x15420
 #define B_BE_UID_FILTER_MASK GENMASK(31, 24)
@@ -4011,12 +7014,168 @@
 #define B_BE_A_A1_MATCH BIT(1)
 #define B_BE_SNIFFER_MODE BIT(0)
 
+#define R_BE_CTRL_FLTR 0x11424
+#define R_BE_CTRL_FLTR_C1 0x15424
+#define B_BE_CTRL_STYPE_MASK GENMASK(15, 0)
+#define RX_FLTR_FRAME_DROP_BE 0x0000
+#define RX_FLTR_FRAME_ACCEPT_BE 0xFFFF
+
+#define R_BE_MGNT_FLTR 0x11428
+#define R_BE_MGNT_FLTR_C1 0x15428
+#define B_BE_MGNT_STYPE_MASK GENMASK(15, 0)
+
+#define R_BE_DATA_FLTR 0x1142C
+#define R_BE_DATA_FLTR_C1 0x1542C
+#define B_BE_DATA_STYPE_MASK GENMASK(15, 0)
+
+#define R_BE_ADDR_CAM_CTRL 0x11434
+#define R_BE_ADDR_CAM_CTRL_C1 0x15434
+#define B_BE_ADDR_CAM_RANGE_MASK GENMASK(23, 16)
+#define ADDR_CAM_SERCH_RANGE  0x7f
+#define B_BE_ADDR_CAM_CMPLIMT_MASK GENMASK(15, 12)
+#define B_BE_ADDR_CAM_IORST BIT(10)
+#define B_BE_DIS_ADDR_CLK_GATED BIT(9)
+#define B_BE_ADDR_CAM_CLR BIT(8)
+#define B_BE_ADDR_CAM_A2_B0_CHK BIT(2)
+#define B_BE_ADDR_CAM_SRCH_PERPKT BIT(1)
+#define B_BE_ADDR_CAM_EN BIT(0)
+
+#define R_BE_RESPBA_CAM_CTRL 0x1143C
+#define R_BE_RESPBA_CAM_CTRL_C1 0x1543C
+#define B_BE_BACAM_SKIP_ALL_QOSNULL BIT(24)
+#define B_BE_BACAM_STD_SSN_SEL BIT(20)
+#define B_BE_BACAM_TEMP_SZ_MASK GENMASK(17, 16)
+#define B_BE_BACAM_RST_IDX_MASK GENMASK(15, 8)
+#define B_BE_BACAM_SHIFT_POLL BIT(7)
+#define B_BE_BACAM_IORST BIT(6)
+#define B_BE_BACAM_GCK_DIS BIT(5)
+#define B_BE_COMPL_VAL BIT(3)
+#define B_BE_SSN_SEL BIT(2)
+#define B_BE_BACAM_RST_MASK GENMASK(1, 0)
+#define S_BE_BACAM_RST_DONE 0
+#define S_BE_BACAM_RST_ENT 1
+#define S_BE_BACAM_RST_ALL 2
+
+#define R_BE_RX_SR_CTRL 0x1144A
+#define R_BE_RX_SR_CTRL_C1 0x1544A
+#define B_BE_SR_OP_MODE_MASK GENMASK(5, 4)
+#define B_BE_SRG_CHK_EN BIT(2)
+#define B_BE_SR_CTRL_PLCP_EN BIT(1)
+#define B_BE_SR_EN BIT(0)
+
 #define R_BE_CSIRPT_OPTION 0x11464
 #define R_BE_CSIRPT_OPTION_C1 0x15464
 #define B_BE_CSIPRT_EHTSU_AID_EN BIT(26)
 #define B_BE_CSIPRT_HESU_AID_EN BIT(25)
 #define B_BE_CSIPRT_VHTSU_AID_EN BIT(24)
 
+#define R_BE_RX_ERR_ISR 0x114F4
+#define R_BE_RX_ERR_ISR_C1 0x154F4
+#define B_BE_RX_ERR_TRIG_ACT_TO BIT(9)
+#define B_BE_RX_ERR_STS_ACT_TO BIT(8)
+#define B_BE_RX_ERR_CSI_ACT_TO BIT(7)
+#define B_BE_RX_ERR_ACT_TO BIT(6)
+#define B_BE_CSI_DATAON_ASSERT_TO BIT(5)
+#define B_BE_DATAON_ASSERT_TO BIT(4)
+#define B_BE_CCA_ASSERT_TO BIT(3)
+#define B_BE_RX_ERR_DMA_TO BIT(2)
+#define B_BE_RX_ERR_DATA_TO BIT(1)
+#define B_BE_RX_ERR_CCA_TO BIT(0)
+
+#define R_BE_RX_ERR_IMR 0x114F8
+#define R_BE_RX_ERR_IMR_C1 0x154F8
+#define B_BE_RX_ERR_TRIG_ACT_TO_MSK BIT(9)
+#define B_BE_RX_ERR_STS_ACT_TO_MSK BIT(8)
+#define B_BE_RX_ERR_CSI_ACT_TO_MSK BIT(7)
+#define B_BE_RX_ERR_ACT_TO_MSK BIT(6)
+#define B_BE_CSI_DATAON_ASSERT_TO_MSK BIT(5)
+#define B_BE_DATAON_ASSERT_TO_MSK BIT(4)
+#define B_BE_CCA_ASSERT_TO_MSK BIT(3)
+#define B_BE_RX_ERR_DMA_TO_MSK BIT(2)
+#define B_BE_RX_ERR_DATA_TO_MSK BIT(1)
+#define B_BE_RX_ERR_CCA_TO_MSK BIT(0)
+#define B_BE_RX_ERR_IMR_CLR (B_BE_RX_ERR_CCA_TO_MSK | \
+			     B_BE_RX_ERR_DATA_TO_MSK | \
+			     B_BE_RX_ERR_DMA_TO_MSK | \
+			     B_BE_CCA_ASSERT_TO_MSK | \
+			     B_BE_DATAON_ASSERT_TO_MSK | \
+			     B_BE_CSI_DATAON_ASSERT_TO_MSK | \
+			     B_BE_RX_ERR_ACT_TO_MSK | \
+			     B_BE_RX_ERR_CSI_ACT_TO_MSK | \
+			     B_BE_RX_ERR_STS_ACT_TO_MSK | \
+			     B_BE_RX_ERR_TRIG_ACT_TO_MSK)
+#define B_BE_RX_ERR_IMR_SET (B_BE_RX_ERR_ACT_TO_MSK | \
+			     B_BE_RX_ERR_STS_ACT_TO_MSK | \
+			     B_BE_RX_ERR_TRIG_ACT_TO_MSK)
+
+#define R_BE_RX_PLCP_EXT_OPTION_1 0x11514
+#define R_BE_RX_PLCP_EXT_OPTION_1_C1 0x15514
+#define B_BE_PLCP_CLOSE_RX_UNSPUUORT BIT(19)
+#define B_BE_PLCP_CLOSE_RX_BB_BRK BIT(18)
+#define B_BE_PLCP_CLOSE_RX_PSDU_PRES BIT(17)
+#define B_BE_PLCP_CLOSE_RX_NDP BIT(16)
+#define B_BE_PLCP_NSS_SRC BIT(11)
+#define B_BE_PLCP_DOPPLEB_BE_SRC BIT(10)
+#define B_BE_PLCP_STBC_SRC BIT(9)
+#define B_BE_PLCP_SU_PSDU_LEN_SRC BIT(8)
+#define B_BE_PLCP_RXSB_SRC BIT(7)
+#define B_BE_PLCP_BW_SRC_MASK GENMASK(6, 5)
+#define B_BE_PLCP_GILTF_SRC BIT(4)
+#define B_BE_PLCP_NSTS_SRC BIT(3)
+#define B_BE_PLCP_MCS_SRC BIT(2)
+#define B_BE_PLCP_CH20_WIDATA_SRC BIT(1)
+#define B_BE_PLCP_PPDU_TYPE_SRC BIT(0)
+
+#define R_BE_RESP_CSI_RESERVED_PAGE 0x11810
+#define R_BE_RESP_CSI_RESERVED_PAGE_C1 0x15810
+#define B_BE_CSI_RESERVED_PAGE_NUM_MASK GENMASK(27, 16)
+#define B_BE_CSI_RESERVED_START_PAGE_MASK GENMASK(11, 0)
+
+#define R_BE_RESP_IMR 0x11884
+#define R_BE_RESP_IMR_C1 0x15884
+#define B_BE_RESP_TBL_FLAG_ERR_ISR_EN BIT(17)
+#define B_BE_RESP_SEC_DOUBLE_HIT_ERR_ISR_EN BIT(16)
+#define B_BE_RESP_WRPTR_CROSS_ERR_ISR_EN BIT(15)
+#define B_BE_RESP_TOO_MANY_PLD_ERR_ISR_EN BIT(14)
+#define B_BE_RESP_TXDMA_READ_DATA_ERR_ISR_EN BIT(13)
+#define B_BE_RESP_PLDID_RDY_ERR_ISR_EN BIT(12)
+#define B_BE_RESP_RX_OVERWRITE_ERR_ISR_EN BIT(11)
+#define B_BE_RESP_RXDMA_WRPTR_INVLD_ERR_ISR_EN BIT(10)
+#define B_BE_RESP_RXDMA_REQ_INVLD_ERR_ISR_EN BIT(9)
+#define B_BE_RESP_RXDMA_REQ_MACID_ERR_ISR_EN BIT(8)
+#define B_BE_RESP_TXCMD_TX_ST_ABORT_ERR_ISR_EN BIT(6)
+#define B_BE_RESP_TXCMD_DMAC_PROC_ERR_ISR_EN BIT(5)
+#define B_BE_RESP_TXCMD_TBL_ERR_ISR_EN BIT(4)
+#define B_BE_RESP_INITCMD_RX_ST_ABORT_ERR_ISR_EN BIT(3)
+#define B_BE_RESP_INITCMD_RESERVD_PAGE_ABORT_ERR_ISR_EN BIT(2)
+#define B_BE_RESP_INITCMD_TX_ST_ABORT_ERR_ISR_EN BIT(1)
+#define B_BE_RESP_DMAC_PROC_ERR_ISR_EN BIT(0)
+#define B_BE_RESP_IMR_CLR (B_BE_RESP_DMAC_PROC_ERR_ISR_EN | \
+			   B_BE_RESP_INITCMD_TX_ST_ABORT_ERR_ISR_EN | \
+			   B_BE_RESP_INITCMD_RX_ST_ABORT_ERR_ISR_EN | \
+			   B_BE_RESP_TXCMD_TBL_ERR_ISR_EN | \
+			   B_BE_RESP_TXCMD_DMAC_PROC_ERR_ISR_EN | \
+			   B_BE_RESP_TXCMD_TX_ST_ABORT_ERR_ISR_EN | \
+			   B_BE_RESP_RXDMA_REQ_MACID_ERR_ISR_EN | \
+			   B_BE_RESP_RXDMA_REQ_INVLD_ERR_ISR_EN | \
+			   B_BE_RESP_RXDMA_WRPTR_INVLD_ERR_ISR_EN | \
+			   B_BE_RESP_RX_OVERWRITE_ERR_ISR_EN | \
+			   B_BE_RESP_PLDID_RDY_ERR_ISR_EN | \
+			   B_BE_RESP_TXDMA_READ_DATA_ERR_ISR_EN | \
+			   B_BE_RESP_TOO_MANY_PLD_ERR_ISR_EN | \
+			   B_BE_RESP_WRPTR_CROSS_ERR_ISR_EN | \
+			   B_BE_RESP_SEC_DOUBLE_HIT_ERR_ISR_EN)
+#define B_BE_RESP_IMR_SET (B_BE_RESP_DMAC_PROC_ERR_ISR_EN | \
+			   B_BE_RESP_INITCMD_TX_ST_ABORT_ERR_ISR_EN | \
+			   B_BE_RESP_INITCMD_RX_ST_ABORT_ERR_ISR_EN | \
+			   B_BE_RESP_TXCMD_TBL_ERR_ISR_EN | \
+			   B_BE_RESP_TXCMD_DMAC_PROC_ERR_ISR_EN | \
+			   B_BE_RESP_TXCMD_TX_ST_ABORT_ERR_ISR_EN | \
+			   B_BE_RESP_RX_OVERWRITE_ERR_ISR_EN | \
+			   B_BE_RESP_PLDID_RDY_ERR_ISR_EN | \
+			   B_BE_RESP_WRPTR_CROSS_ERR_ISR_EN | \
+			   B_BE_RESP_SEC_DOUBLE_HIT_ERR_ISR_EN)
+
 #define R_BE_PWR_MODULE 0x11900
 #define R_BE_PWR_MODULE_C1 0x15900
 
@@ -4028,6 +7187,17 @@
 #define R_BE_PWR_RU_LMT 0x12048
 #define R_BE_PWR_RU_LMT_MAX 0x120E4
 
+#define R_BE_C0_TXPWR_IMR 0x128E0
+#define R_BE_C0_TXPWR_IMR_C1 0x168E0
+#define B_BE_FSM_TIMEOUT_ERR_INT_EN BIT(0)
+#define B_BE_C0_TXPWR_IMR_CLR B_BE_FSM_TIMEOUT_ERR_INT_EN
+#define B_BE_C0_TXPWR_IMR_SET B_BE_FSM_TIMEOUT_ERR_INT_EN
+
+#define R_BE_TXPWR_ERR_FLAG 0x128E4
+#define R_BE_TXPWR_ERR_IMR 0x128E0
+#define R_BE_TXPWR_ERR_FLAG_C1 0x158E4
+#define R_BE_TXPWR_ERR_IMR_C1 0x158E0
+
 #define CMAC1_START_ADDR_BE 0x14000
 #define CMAC1_END_ADDR_BE 0x17FFF
 
@@ -4293,6 +7463,11 @@
 #define B_P0_RSTB_WATCH_DOG BIT(0)
 #define B_P1_RSTB_WATCH_DOG BIT(1)
 #define B_UPD_P0_EN BIT(31)
+#define R_SPOOF_CG 0x00B4
+#define B_SPOOF_CG_EN BIT(17)
+#define R_DFS_FFT_CG 0x00B8
+#define B_DFS_CG_EN BIT(1)
+#define B_DFS_FFT_EN BIT(0)
 #define R_ANAPAR_PW15 0x030C
 #define B_ANAPAR_PW15 GENMASK(31, 24)
 #define B_ANAPAR_PW15_H GENMASK(27, 24)
@@ -4355,6 +7530,8 @@
 #define R_PHY_STS_BITMAP_HT 0x076C
 #define R_PHY_STS_BITMAP_VHT 0x0770
 #define R_PHY_STS_BITMAP_HE 0x0774
+#define R_EDCCA_RPTREG_SEL_BE 0x078C
+#define B_EDCCA_RPTREG_SEL_BE_MSK GENMASK(22, 20)
 #define R_PMAC_GNT 0x0980
 #define B_PMAC_GNT_TXEN BIT(0)
 #define B_PMAC_GNT_RXEN BIT(16)
@@ -4414,12 +7591,18 @@
 #define B_IOQ_IQK_DPK_EN BIT(1)
 #define R_GNT_BT_WGT_EN 0x0C6C
 #define B_GNT_BT_WGT_EN BIT(21)
+#define R_TX_COLLISION_T2R_ST 0x0C70
+#define B_TX_COLLISION_T2R_ST_M GENMASK(25, 20)
+#define R_TXGATING 0x0C74
+#define B_TXGATING_EN BIT(4)
 #define R_PD_ARBITER_OFF 0x0C80
 #define B_PD_ARBITER_OFF BIT(31)
 #define R_SNDCCA_A1 0x0C9C
 #define B_SNDCCA_A1_EN GENMASK(19, 12)
 #define R_SNDCCA_A2 0x0CA0
 #define B_SNDCCA_A2_VAL GENMASK(19, 12)
+#define R_TX_COLLISION_T2R_ST_BE 0x0CC8
+#define B_TX_COLLISION_T2R_ST_BE_M GENMASK(13, 8)
 #define R_RXHT_MCS_LIMIT 0x0D18
 #define B_RXHT_MCS_LIMIT GENMASK(9, 8)
 #define R_RXVHT_MCS_LIMIT 0x0D18
@@ -4438,6 +7621,10 @@
 #define R_BRK_ASYNC_RST_EN_1 0x0DC0
 #define R_BRK_ASYNC_RST_EN_2 0x0DC4
 #define R_BRK_ASYNC_RST_EN_3 0x0DC8
+#define R_CTLTOP 0x1008
+#define B_CTLTOP_ON BIT(23)
+#define B_CTLTOP_VAL GENMASK(15, 12)
+#define R_EDCCA_RPT_SEL_BE 0x10CC
 #define R_S0_HW_SI_DIS 0x1200
 #define B_S0_HW_SI_DIS_W_R_TRIG GENMASK(30, 28)
 #define R_P0_RXCK 0x12A0
@@ -4469,6 +7656,14 @@
 #define R_CFO_COMP_SEG0_H 0x1388
 #define R_CFO_COMP_SEG0_CTRL 0x138C
 #define R_DBG32_D 0x1730
+#define R_EDCCA_RPT_A 0x1738
+#define R_EDCCA_RPT_B 0x173c
+#define B_EDCCA_RPT_B_FB BIT(7)
+#define B_EDCCA_RPT_B_P20 BIT(6)
+#define B_EDCCA_RPT_B_S20 BIT(5)
+#define B_EDCCA_RPT_B_S40 BIT(4)
+#define B_EDCCA_RPT_B_S80 BIT(3)
+#define B_EDCCA_RPT_B_PATH_MASK GENMASK(2, 1)
 #define R_SWSI_V1 0x174C
 #define B_SWSI_W_BUSY_V1 BIT(24)
 #define B_SWSI_R_BUSY_V1 BIT(25)
@@ -4530,6 +7725,8 @@
 #define R_S0_ADDCK 0x1E00
 #define B_S0_ADDCK_I GENMASK(9, 0)
 #define B_S0_ADDCK_Q GENMASK(19, 10)
+#define R_EDCCA_RPT_SEL 0x20CC
+#define B_EDCCA_RPT_SEL_MSK GENMASK(2, 0)
 #define R_ADC_FIFO 0x20fc
 #define B_ADC_FIFO_RST GENMASK(31, 24)
 #define B_ADC_FIFO_RXK GENMASK(31, 16)
@@ -4576,6 +7773,8 @@
 #define B_DBCC_80P80_SEL_EVM_RPT2_EN BIT(0)
 #define R_P1_EN_SOUND_WO_NDP 0x2D7C
 #define B_P1_EN_SOUND_WO_NDP BIT(1)
+#define R_EDCCA_RPT_A_BE 0x2E38
+#define R_EDCCA_RPT_B_BE 0x2E3C
 #define R_S1_HW_SI_DIS 0x3200
 #define B_S1_HW_SI_DIS_W_R_TRIG GENMASK(30, 28)
 #define R_P1_RXCK 0x32A0
@@ -4619,6 +7818,7 @@
 #define B_SEG0CSI_EN BIT(23)
 #define R_BSS_CLR_MAP 0x43ac
 #define R_BSS_CLR_MAP_V1 0x43B0
+#define R_BSS_CLR_MAP_V2 0x4EB0
 #define B_BSS_CLR_MAP_VLD0 BIT(28)
 #define B_BSS_CLR_MAP_TGT GENMASK(27, 22)
 #define B_BSS_CLR_MAP_STAID GENMASK(21, 11)
@@ -4783,9 +7983,9 @@
 #define R_SEG0R_PD_V2 0x6A74
 #define R_SEG0R_EDCCA_LVL 0x4840
 #define R_SEG0R_EDCCA_LVL_V1 0x4884
-#define B_SEG0R_PPDU_LVL_MSK GENMASK(31, 24)
-#define B_SEG0R_EDCCA_LVL_P_MSK GENMASK(15, 8)
-#define B_SEG0R_EDCCA_LVL_A_MSK GENMASK(7, 0)
+#define B_EDCCA_LVL_MSK3 GENMASK(31, 24)
+#define B_EDCCA_LVL_MSK1 GENMASK(15, 8)
+#define B_EDCCA_LVL_MSK0 GENMASK(7, 0)
 #define B_SEG0R_PD_SPATIAL_REUSE_EN_MSK_V1 BIT(30)
 #define B_SEG0R_PD_SPATIAL_REUSE_EN_MSK BIT(29)
 #define B_SEG0R_PD_LOWER_BOUND_MSK GENMASK(10, 6)
@@ -4912,6 +8112,8 @@
 #define R_BMODE_PDTH_EN_V1 0x4B74
 #define R_BMODE_PDTH_EN_V2 0x6718
 #define B_BMODE_PDTH_LIMIT_EN_MSK_V1 BIT(30)
+#define R_BSS_CLR_VLD_V2 0x4EBC
+#define B_BSS_CLR_VLD0_V2 BIT(2)
 #define R_CFO_COMP_SEG1_L 0x5384
 #define R_CFO_COMP_SEG1_H 0x5388
 #define R_CFO_COMP_SEG1_CTRL 0x538C
@@ -5039,6 +8241,10 @@
 #define B_DCFO_WEIGHT_MSK_V1 GENMASK(31, 28)
 #define R_DCFO_OPT_V1 0x6260
 #define B_DCFO_OPT_EN_V1 BIT(17)
+#define R_SEG0R_EDCCA_LVL_BE 0x69EC
+#define R_SEG0R_PPDU_LVL_BE 0x69F0
+#define R_SEGSND 0x6A14
+#define B_SEGSND_EN BIT(31)
 #define R_RPL_BIAS_COMP1 0x6DF0
 #define B_RPL_BIAS_COMP1_MASK GENMASK(7, 0)
 #define R_P1_TSSI_ALIM1 0x7630
diff --git a/drivers/net/wireless/realtek/rtw89/regd.c b/drivers/net/wireless/realtek/rtw89/regd.c
index ca99422e600f..d0857ef60ea6 100644
--- a/drivers/net/wireless/realtek/rtw89/regd.c
+++ b/drivers/net/wireless/realtek/rtw89/regd.c
@@ -112,9 +112,9 @@ static const struct rtw89_regd rtw89_regd_map[] = {
 	COUNTRY_REGD("MY", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
 	COUNTRY_REGD("PK", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("PH", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("SG", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
+	COUNTRY_REGD("SG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
 	COUNTRY_REGD("LK", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("TW", RTW89_FCC, RTW89_FCC, RTW89_NA),
+	COUNTRY_REGD("TW", RTW89_FCC, RTW89_FCC, RTW89_ETSI),
 	COUNTRY_REGD("TH", RTW89_ETSI, RTW89_ETSI, RTW89_THAILAND),
 	COUNTRY_REGD("VN", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("AU", RTW89_ACMA, RTW89_ACMA, RTW89_ACMA),
@@ -179,7 +179,7 @@ static const struct rtw89_regd rtw89_regd_map[] = {
 	COUNTRY_REGD("GE", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("GI", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("GL", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("GD", RTW89_FCC, RTW89_FCC, RTW89_NA),
+	COUNTRY_REGD("GD", RTW89_FCC, RTW89_FCC, RTW89_FCC),
 	COUNTRY_REGD("GP", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 	COUNTRY_REGD("GU", RTW89_FCC, RTW89_FCC, RTW89_NA),
 	COUNTRY_REGD("GG", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
@@ -257,7 +257,42 @@ static const struct rtw89_regd rtw89_regd_map[] = {
 	COUNTRY_REGD("PS", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
 };
 
-static const struct rtw89_regd *rtw89_regd_find_reg_by_name(char *alpha2)
+static const char rtw89_alpha2_list_eu[][3] = {
+	"AT",
+	"BE",
+	"CY",
+	"CZ",
+	"DK",
+	"EE",
+	"FI",
+	"FR",
+	"DE",
+	"GR",
+	"HU",
+	"IS",
+	"IE",
+	"IT",
+	"LV",
+	"LI",
+	"LT",
+	"LU",
+	"MT",
+	"MC",
+	"NL",
+	"NO",
+	"PL",
+	"PT",
+	"SK",
+	"SI",
+	"ES",
+	"SE",
+	"CH",
+	"BG",
+	"HR",
+	"RO",
+};
+
+static const struct rtw89_regd *rtw89_regd_find_reg_by_name(const char *alpha2)
 {
 	u32 i;
 
@@ -274,6 +309,24 @@ static bool rtw89_regd_is_ww(const struct rtw89_regd *regd)
 	return regd == &rtw89_ww_regd;
 }
 
+static u8 rtw89_regd_get_index(const struct rtw89_regd *regd)
+{
+	BUILD_BUG_ON(ARRAY_SIZE(rtw89_regd_map) > RTW89_REGD_MAX_COUNTRY_NUM);
+
+	if (rtw89_regd_is_ww(regd))
+		return RTW89_REGD_MAX_COUNTRY_NUM;
+
+	return regd - rtw89_regd_map;
+}
+
+static u8 rtw89_regd_get_index_by_name(const char *alpha2)
+{
+	const struct rtw89_regd *regd;
+
+	regd = rtw89_regd_find_reg_by_name(alpha2);
+	return rtw89_regd_get_index(regd);
+}
+
 #define rtw89_debug_regd(_dev, _regd, _desc, _argv...) \
 do { \
 	typeof(_regd) __r = _regd; \
@@ -291,19 +344,22 @@ static void rtw89_regd_setup_unii4(struct rtw89_dev *rtwdev,
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	bool regd_allow_unii_4 = chip->support_unii4;
 	struct ieee80211_supported_band *sband;
+	struct rtw89_acpi_dsm_result res = {};
 	int ret;
 	u8 val;
 
 	if (!chip->support_unii4)
 		goto bottom;
 
-	ret = rtw89_acpi_evaluate_dsm(rtwdev, RTW89_ACPI_DSM_FUNC_59G_EN, &val);
+	ret = rtw89_acpi_evaluate_dsm(rtwdev, RTW89_ACPI_DSM_FUNC_59G_EN, &res);
 	if (ret) {
 		rtw89_debug(rtwdev, RTW89_DBG_REGD,
 			    "acpi: cannot eval unii 4: %d\n", ret);
 		goto bottom;
 	}
 
+	val = res.u.value;
+
 	rtw89_debug(rtwdev, RTW89_DBG_REGD,
 		    "acpi: eval if allow unii 4: %d\n", val);
 
@@ -332,25 +388,99 @@ bottom:
 	sband->n_channels -= 3;
 }
 
+static void __rtw89_regd_setup_policy_6ghz(struct rtw89_dev *rtwdev, bool block,
+					   const char *alpha2)
+{
+	struct rtw89_regulatory_info *regulatory = &rtwdev->regulatory;
+	u8 index;
+
+	index = rtw89_regd_get_index_by_name(alpha2);
+	if (index == RTW89_REGD_MAX_COUNTRY_NUM) {
+		rtw89_debug(rtwdev, RTW89_DBG_REGD, "%s: unknown alpha2 %c%c\n",
+			    __func__, alpha2[0], alpha2[1]);
+		return;
+	}
+
+	if (block)
+		set_bit(index, regulatory->block_6ghz);
+	else
+		clear_bit(index, regulatory->block_6ghz);
+}
+
+static void rtw89_regd_setup_policy_6ghz(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_regulatory_info *regulatory = &rtwdev->regulatory;
+	const struct rtw89_acpi_country_code *country;
+	const struct rtw89_acpi_policy_6ghz *ptr;
+	struct rtw89_acpi_dsm_result res = {};
+	bool to_block;
+	int i, j;
+	int ret;
+
+	ret = rtw89_acpi_evaluate_dsm(rtwdev, RTW89_ACPI_DSM_FUNC_6G_BP, &res);
+	if (ret) {
+		rtw89_debug(rtwdev, RTW89_DBG_REGD,
+			    "acpi: cannot eval policy 6ghz: %d\n", ret);
+		return;
+	}
+
+	ptr = res.u.policy_6ghz;
+
+	switch (ptr->policy_mode) {
+	case RTW89_ACPI_POLICY_BLOCK:
+		to_block = true;
+		break;
+	case RTW89_ACPI_POLICY_ALLOW:
+		to_block = false;
+		/* only below list is allowed; block all first */
+		bitmap_fill(regulatory->block_6ghz, RTW89_REGD_MAX_COUNTRY_NUM);
+		break;
+	default:
+		rtw89_debug(rtwdev, RTW89_DBG_REGD,
+			    "%s: unknown policy mode: %d\n", __func__,
+			    ptr->policy_mode);
+		goto out;
+	}
+
+	for (i = 0; i < ptr->country_count; i++) {
+		country = &ptr->country_list[i];
+		if (memcmp("EU", country->alpha2, 2) != 0) {
+			__rtw89_regd_setup_policy_6ghz(rtwdev, to_block,
+						       country->alpha2);
+			continue;
+		}
+
+		for (j = 0; j < ARRAY_SIZE(rtw89_alpha2_list_eu); j++)
+			__rtw89_regd_setup_policy_6ghz(rtwdev, to_block,
+						       rtw89_alpha2_list_eu[j]);
+	}
+
+out:
+	kfree(ptr);
+}
+
 static void rtw89_regd_setup_6ghz(struct rtw89_dev *rtwdev, struct wiphy *wiphy)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	bool chip_support_6ghz = chip->support_bands & BIT(NL80211_BAND_6GHZ);
 	bool regd_allow_6ghz = chip_support_6ghz;
 	struct ieee80211_supported_band *sband;
+	struct rtw89_acpi_dsm_result res = {};
 	int ret;
 	u8 val;
 
 	if (!chip_support_6ghz)
 		goto bottom;
 
-	ret = rtw89_acpi_evaluate_dsm(rtwdev, RTW89_ACPI_DSM_FUNC_6G_DIS, &val);
+	ret = rtw89_acpi_evaluate_dsm(rtwdev, RTW89_ACPI_DSM_FUNC_6G_DIS, &res);
 	if (ret) {
 		rtw89_debug(rtwdev, RTW89_DBG_REGD,
 			    "acpi: cannot eval 6ghz: %d\n", ret);
 		goto bottom;
 	}
 
+	val = res.u.value;
+
 	rtw89_debug(rtwdev, RTW89_DBG_REGD,
 		    "acpi: eval if disallow 6ghz: %d\n", val);
 
@@ -369,8 +499,10 @@ bottom:
 	rtw89_debug(rtwdev, RTW89_DBG_REGD, "regd: allow 6ghz: %d\n",
 		    regd_allow_6ghz);
 
-	if (regd_allow_6ghz)
+	if (regd_allow_6ghz) {
+		rtw89_regd_setup_policy_6ghz(rtwdev);
 		return;
+	}
 
 	sband = wiphy->bands[NL80211_BAND_6GHZ];
 	if (!sband)
@@ -430,6 +562,33 @@ int rtw89_regd_init(struct rtw89_dev *rtwdev,
 	return 0;
 }
 
+static void rtw89_regd_apply_policy_6ghz(struct rtw89_dev *rtwdev,
+					 struct wiphy *wiphy)
+{
+	struct rtw89_regulatory_info *regulatory = &rtwdev->regulatory;
+	const struct rtw89_regd *regd = regulatory->regd;
+	struct ieee80211_supported_band *sband;
+	u8 index;
+	int i;
+
+	index = rtw89_regd_get_index(regd);
+	if (index == RTW89_REGD_MAX_COUNTRY_NUM)
+		return;
+
+	if (!test_bit(index, regulatory->block_6ghz))
+		return;
+
+	rtw89_debug(rtwdev, RTW89_DBG_REGD, "%c%c 6 GHz is blocked by policy\n",
+		    regd->alpha2[0], regd->alpha2[1]);
+
+	sband = wiphy->bands[NL80211_BAND_6GHZ];
+	if (!sband)
+		return;
+
+	for (i = 0; i < sband->n_channels; i++)
+		sband->channels[i].flags |= IEEE80211_CHAN_DISABLED;
+}
+
 static void rtw89_regd_notifier_apply(struct rtw89_dev *rtwdev,
 				      struct wiphy *wiphy,
 				      struct regulatory_request *request)
@@ -444,6 +603,8 @@ static void rtw89_regd_notifier_apply(struct rtw89_dev *rtwdev,
 		wiphy->regulatory_flags |= REGULATORY_COUNTRY_IE_IGNORE;
 	else
 		wiphy->regulatory_flags &= ~REGULATORY_COUNTRY_IE_IGNORE;
+
+	rtw89_regd_apply_policy_6ghz(rtwdev, wiphy);
 }
 
 void rtw89_regd_notifier(struct wiphy *wiphy, struct regulatory_request *request)
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index 50522ff85003..5c167a9278ce 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -205,6 +205,20 @@ static const struct rtw89_dig_regs rtw8851b_dig_regs = {
 			      B_PATH1_S20_FOLLOW_BY_PAGCUGC_EN_MSK},
 };
 
+static const struct rtw89_edcca_regs rtw8851b_edcca_regs = {
+	.edcca_level			= R_SEG0R_EDCCA_LVL_V1,
+	.edcca_mask			= B_EDCCA_LVL_MSK0,
+	.edcca_p_mask			= B_EDCCA_LVL_MSK1,
+	.ppdu_level			= R_SEG0R_EDCCA_LVL_V1,
+	.ppdu_mask			= B_EDCCA_LVL_MSK3,
+	.rpt_a				= R_EDCCA_RPT_A,
+	.rpt_b				= R_EDCCA_RPT_B,
+	.rpt_sel			= R_EDCCA_RPT_SEL,
+	.rpt_sel_mask			= B_EDCCA_RPT_SEL_MSK,
+	.tx_collision_t2r_st		= R_TX_COLLISION_T2R_ST,
+	.tx_collision_t2r_st_mask	= B_TX_COLLISION_T2R_ST_M,
+};
+
 static const struct rtw89_btc_rf_trx_para rtw89_btc_8851b_rf_ul[] = {
 	{255, 0, 0, 7}, /* 0 -> original */
 	{255, 2, 0, 7}, /* 1 -> for BT-connected ACI issue && BTG co-rx */
@@ -500,7 +514,8 @@ static void rtw8851b_efuse_parsing_gain_offset(struct rtw89_dev *rtwdev,
 	gain->offset_valid = valid;
 }
 
-static int rtw8851b_read_efuse(struct rtw89_dev *rtwdev, u8 *log_map)
+static int rtw8851b_read_efuse(struct rtw89_dev *rtwdev, u8 *log_map,
+			       enum rtw89_efuse_block block)
 {
 	struct rtw89_efuse *efuse = &rtwdev->efuse;
 	struct rtw8851b_efuse *map;
@@ -2359,8 +2374,8 @@ const struct rtw89_chip_info rtw8851b_chip_info = {
 	.rsvd_ple_ofst		= 0x2f800,
 	.hfc_param_ini		= rtw8851b_hfc_param_ini_pcie,
 	.dle_mem		= rtw8851b_dle_mem_pcie,
-	.wde_qempty_acq_num     = 4,
-	.wde_qempty_mgq_sel     = 4,
+	.wde_qempty_acq_grpnum	= 4,
+	.wde_qempty_mgq_grpsel	= 4,
 	.rf_base_addr		= {0xe000},
 	.pwr_on_seq		= NULL,
 	.pwr_off_seq		= NULL,
@@ -2393,12 +2408,14 @@ const struct rtw89_chip_info rtw8851b_chip_info = {
 	.bacam_num		= 2,
 	.bacam_dynamic_num	= 4,
 	.bacam_ver		= RTW89_BACAM_V0,
+	.ppdu_max_usr		= 4,
 	.sec_ctrl_efuse_size	= 4,
 	.physical_efuse_size	= 1216,
 	.logical_efuse_size	= 2048,
 	.limit_efuse_size	= 1280,
 	.dav_phy_efuse_size	= 0,
 	.dav_log_efuse_size	= 0,
+	.efuse_blocks		= NULL,
 	.phycap_addr		= 0x580,
 	.phycap_size		= 128,
 	.para_ver		= 0,
@@ -2437,13 +2454,15 @@ const struct rtw89_chip_info rtw8851b_chip_info = {
 	.dcfo_comp		= &rtw8851b_dcfo_comp,
 	.dcfo_comp_sft		= 12,
 	.imr_info		= &rtw8851b_imr_info,
+	.imr_dmac_table		= NULL,
+	.imr_cmac_table		= NULL,
 	.rrsr_cfgs		= &rtw8851b_rrsr_cfgs,
 	.bss_clr_vld		= {R_BSS_CLR_MAP_V1, B_BSS_CLR_MAP_VLD0},
 	.bss_clr_map_reg	= R_BSS_CLR_MAP_V1,
 	.dma_ch_mask		= BIT(RTW89_DMA_ACH4) | BIT(RTW89_DMA_ACH5) |
 				  BIT(RTW89_DMA_ACH6) | BIT(RTW89_DMA_ACH7) |
 				  BIT(RTW89_DMA_B1MG) | BIT(RTW89_DMA_B1HI),
-	.edcca_lvl_reg		= R_SEG0R_EDCCA_LVL_V1,
+	.edcca_regs		= &rtw8851b_edcca_regs,
 #ifdef CONFIG_PM
 	.wowlan_stub		= &rtw_wowlan_stub_8851b,
 #endif
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851be.c b/drivers/net/wireless/realtek/rtw89/rtw8851be.c
index 0f7711c50bd1..ade69bd30fc8 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851be.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851be.c
@@ -10,6 +10,7 @@
 #include "rtw8851b.h"
 
 static const struct rtw89_pci_info rtw8851b_pci_info = {
+	.gen_def		= &rtw89_pci_gen_ax,
 	.txbd_trunc_mode	= MAC_AX_BD_TRUNC,
 	.rxbd_trunc_mode	= MAC_AX_BD_TRUNC,
 	.rxbd_mode		= MAC_AX_RXBD_PKT,
@@ -33,6 +34,7 @@ static const struct rtw89_pci_info rtw8851b_pci_info = {
 	.max_tag_num_mask	= B_AX_MAX_TAG_NUM,
 	.rxbd_rwptr_clr_reg	= R_AX_RXBD_RWPTR_CLR,
 	.txbd_rwptr_clr2_reg	= 0,
+	.dma_io_stop		= {R_AX_PCIE_DMA_STOP1, B_AX_STOP_PCIEIO},
 	.dma_stop1		= {R_AX_PCIE_DMA_STOP1, B_AX_TX_STOP1_MASK_V1},
 	.dma_stop2		= {0},
 	.dma_busy1		= {R_AX_PCIE_DMA_BUSY1, DMA_BUSY1_CHECK_V1},
@@ -41,6 +43,7 @@ static const struct rtw89_pci_info rtw8851b_pci_info = {
 
 	.rpwm_addr		= R_AX_PCIE_HRPWM,
 	.cpwm_addr		= R_AX_CPWM,
+	.mit_addr		= R_AX_INT_MIT_RX,
 	.tx_dma_ch_mask		= BIT(RTW89_TXCH_ACH4) | BIT(RTW89_TXCH_ACH5) |
 				  BIT(RTW89_TXCH_ACH6) | BIT(RTW89_TXCH_ACH7) |
 				  BIT(RTW89_TXCH_CH10) | BIT(RTW89_TXCH_CH11),
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index 0c36e6180e25..0c76c52ce22c 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -498,6 +498,20 @@ static const struct rtw89_dig_regs rtw8852a_dig_regs = {
 			      B_PATH1_S20_FOLLOW_BY_PAGCUGC_EN_MSK},
 };
 
+static const struct rtw89_edcca_regs rtw8852a_edcca_regs = {
+	.edcca_level			= R_SEG0R_EDCCA_LVL,
+	.edcca_mask			= B_EDCCA_LVL_MSK0,
+	.edcca_p_mask			= B_EDCCA_LVL_MSK1,
+	.ppdu_level			= R_SEG0R_EDCCA_LVL,
+	.ppdu_mask			= B_EDCCA_LVL_MSK3,
+	.rpt_a				= R_EDCCA_RPT_A,
+	.rpt_b				= R_EDCCA_RPT_B,
+	.rpt_sel			= R_EDCCA_RPT_SEL,
+	.rpt_sel_mask			= B_EDCCA_RPT_SEL_MSK,
+	.tx_collision_t2r_st		= R_TX_COLLISION_T2R_ST,
+	.tx_collision_t2r_st_mask	= B_TX_COLLISION_T2R_ST_M,
+};
+
 static void rtw8852ae_efuse_parsing(struct rtw89_efuse *efuse,
 				    struct rtw8852a_efuse *map)
 {
@@ -537,7 +551,8 @@ static void rtw8852a_efuse_parsing_tssi(struct rtw89_dev *rtwdev,
 	}
 }
 
-static int rtw8852a_read_efuse(struct rtw89_dev *rtwdev, u8 *log_map)
+static int rtw8852a_read_efuse(struct rtw89_dev *rtwdev, u8 *log_map,
+			       enum rtw89_efuse_block block)
 {
 	struct rtw89_efuse *efuse = &rtwdev->efuse;
 	struct rtw8852a_efuse *map;
@@ -2094,8 +2109,8 @@ const struct rtw89_chip_info rtw8852a_chip_info = {
 	.rsvd_ple_ofst		= 0x6f800,
 	.hfc_param_ini		= rtw8852a_hfc_param_ini_pcie,
 	.dle_mem		= rtw8852a_dle_mem_pcie,
-	.wde_qempty_acq_num	= 16,
-	.wde_qempty_mgq_sel	= 16,
+	.wde_qempty_acq_grpnum	= 16,
+	.wde_qempty_mgq_grpsel	= 16,
 	.rf_base_addr		= {0xc000, 0xd000},
 	.pwr_on_seq		= pwr_on_seq_8852a,
 	.pwr_off_seq		= pwr_off_seq_8852a,
@@ -2129,12 +2144,14 @@ const struct rtw89_chip_info rtw8852a_chip_info = {
 	.bacam_num		= 2,
 	.bacam_dynamic_num	= 4,
 	.bacam_ver		= RTW89_BACAM_V0,
+	.ppdu_max_usr		= 4,
 	.sec_ctrl_efuse_size	= 4,
 	.physical_efuse_size	= 1216,
 	.logical_efuse_size	= 1536,
 	.limit_efuse_size	= 1152,
 	.dav_phy_efuse_size	= 0,
 	.dav_log_efuse_size	= 0,
+	.efuse_blocks		= NULL,
 	.phycap_addr		= 0x580,
 	.phycap_size		= 128,
 	.para_ver		= 0x0,
@@ -2174,11 +2191,13 @@ const struct rtw89_chip_info rtw8852a_chip_info = {
 	.dcfo_comp		= &rtw8852a_dcfo_comp,
 	.dcfo_comp_sft		= 10,
 	.imr_info		= &rtw8852a_imr_info,
+	.imr_dmac_table		= NULL,
+	.imr_cmac_table		= NULL,
 	.rrsr_cfgs		= &rtw8852a_rrsr_cfgs,
 	.bss_clr_vld		= {R_BSS_CLR_MAP, B_BSS_CLR_MAP_VLD0},
 	.bss_clr_map_reg	= R_BSS_CLR_MAP,
 	.dma_ch_mask		= 0,
-	.edcca_lvl_reg		= R_SEG0R_EDCCA_LVL,
+	.edcca_regs		= &rtw8852a_edcca_regs,
 #ifdef CONFIG_PM
 	.wowlan_stub		= &rtw_wowlan_stub_8852a,
 #endif
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852ae.c b/drivers/net/wireless/realtek/rtw89/rtw8852ae.c
index d835a44a1d0d..f1e890bde049 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852ae.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852ae.c
@@ -10,6 +10,7 @@
 #include "rtw8852a.h"
 
 static const struct rtw89_pci_info rtw8852a_pci_info = {
+	.gen_def		= &rtw89_pci_gen_ax,
 	.txbd_trunc_mode	= MAC_AX_BD_TRUNC,
 	.rxbd_trunc_mode	= MAC_AX_BD_TRUNC,
 	.rxbd_mode		= MAC_AX_RXBD_PKT,
@@ -24,6 +25,7 @@ static const struct rtw89_pci_info rtw8852a_pci_info = {
 	.autok_en		= MAC_AX_PCIE_DISABLE,
 	.io_rcy_en		= MAC_AX_PCIE_DISABLE,
 	.io_rcy_tmr		= MAC_AX_IO_RCY_ANA_TMR_6MS,
+	.rx_ring_eq_is_full	= false,
 
 	.init_cfg_reg		= R_AX_PCIE_INIT_CFG1,
 	.txhci_en_bit		= B_AX_TXHCI_EN,
@@ -33,6 +35,7 @@ static const struct rtw89_pci_info rtw8852a_pci_info = {
 	.max_tag_num_mask	= B_AX_MAX_TAG_NUM,
 	.rxbd_rwptr_clr_reg	= R_AX_RXBD_RWPTR_CLR,
 	.txbd_rwptr_clr2_reg	= R_AX_TXBD_RWPTR_CLR2,
+	.dma_io_stop		= {R_AX_PCIE_DMA_STOP1, B_AX_STOP_PCIEIO},
 	.dma_stop1		= {R_AX_PCIE_DMA_STOP1, B_AX_TX_STOP1_MASK},
 	.dma_stop2		= {R_AX_PCIE_DMA_STOP2, B_AX_TX_STOP2_ALL},
 	.dma_busy1		= {R_AX_PCIE_DMA_BUSY1, DMA_BUSY1_CHECK},
@@ -41,6 +44,7 @@ static const struct rtw89_pci_info rtw8852a_pci_info = {
 
 	.rpwm_addr		= R_AX_PCIE_HRPWM,
 	.cpwm_addr		= R_AX_CPWM,
+	.mit_addr		= R_AX_INT_MIT_RX,
 	.tx_dma_ch_mask		= 0,
 	.bd_idx_addr_low_power	= NULL,
 	.dma_addr_set		= &rtw89_pci_ch_dma_addr_set,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index 9d4e6f08218d..de887a35f3fb 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -330,6 +330,20 @@ static const struct rtw89_dig_regs rtw8852b_dig_regs = {
 			      B_PATH1_S20_FOLLOW_BY_PAGCUGC_EN_MSK},
 };
 
+static const struct rtw89_edcca_regs rtw8852b_edcca_regs = {
+	.edcca_level			= R_SEG0R_EDCCA_LVL_V1,
+	.edcca_mask			= B_EDCCA_LVL_MSK0,
+	.edcca_p_mask			= B_EDCCA_LVL_MSK1,
+	.ppdu_level			= R_SEG0R_EDCCA_LVL_V1,
+	.ppdu_mask			= B_EDCCA_LVL_MSK3,
+	.rpt_a				= R_EDCCA_RPT_A,
+	.rpt_b				= R_EDCCA_RPT_B,
+	.rpt_sel			= R_EDCCA_RPT_SEL,
+	.rpt_sel_mask			= B_EDCCA_RPT_SEL_MSK,
+	.tx_collision_t2r_st		= R_TX_COLLISION_T2R_ST,
+	.tx_collision_t2r_st_mask	= B_TX_COLLISION_T2R_ST_M,
+};
+
 static const struct rtw89_btc_rf_trx_para rtw89_btc_8852b_rf_ul[] = {
 	{255, 0, 0, 7}, /* 0 -> original */
 	{255, 2, 0, 7}, /* 1 -> for BT-connected ACI issue && BTG co-rx */
@@ -638,7 +652,8 @@ static void rtw8852b_efuse_parsing_gain_offset(struct rtw89_dev *rtwdev,
 	gain->offset_valid = valid;
 }
 
-static int rtw8852b_read_efuse(struct rtw89_dev *rtwdev, u8 *log_map)
+static int rtw8852b_read_efuse(struct rtw89_dev *rtwdev, u8 *log_map,
+			       enum rtw89_efuse_block block)
 {
 	struct rtw89_efuse *efuse = &rtwdev->efuse;
 	struct rtw8852b_efuse *map;
@@ -2528,8 +2543,8 @@ const struct rtw89_chip_info rtw8852b_chip_info = {
 	.rsvd_ple_ofst		= 0x2f800,
 	.hfc_param_ini		= rtw8852b_hfc_param_ini_pcie,
 	.dle_mem		= rtw8852b_dle_mem_pcie,
-	.wde_qempty_acq_num	= 4,
-	.wde_qempty_mgq_sel	= 4,
+	.wde_qempty_acq_grpnum	= 4,
+	.wde_qempty_mgq_grpsel	= 4,
 	.rf_base_addr		= {0xe000, 0xf000},
 	.pwr_on_seq		= NULL,
 	.pwr_off_seq		= NULL,
@@ -2563,12 +2578,14 @@ const struct rtw89_chip_info rtw8852b_chip_info = {
 	.bacam_num		= 2,
 	.bacam_dynamic_num	= 4,
 	.bacam_ver		= RTW89_BACAM_V0,
+	.ppdu_max_usr		= 4,
 	.sec_ctrl_efuse_size	= 4,
 	.physical_efuse_size	= 1216,
 	.logical_efuse_size	= 2048,
 	.limit_efuse_size	= 1280,
 	.dav_phy_efuse_size	= 96,
 	.dav_log_efuse_size	= 16,
+	.efuse_blocks		= NULL,
 	.phycap_addr		= 0x580,
 	.phycap_size		= 128,
 	.para_ver		= 0,
@@ -2608,13 +2625,15 @@ const struct rtw89_chip_info rtw8852b_chip_info = {
 	.dcfo_comp		= &rtw8852b_dcfo_comp,
 	.dcfo_comp_sft		= 10,
 	.imr_info		= &rtw8852b_imr_info,
+	.imr_dmac_table		= NULL,
+	.imr_cmac_table		= NULL,
 	.rrsr_cfgs		= &rtw8852b_rrsr_cfgs,
 	.bss_clr_vld		= {R_BSS_CLR_MAP_V1, B_BSS_CLR_MAP_VLD0},
 	.bss_clr_map_reg	= R_BSS_CLR_MAP_V1,
 	.dma_ch_mask		= BIT(RTW89_DMA_ACH4) | BIT(RTW89_DMA_ACH5) |
 				  BIT(RTW89_DMA_ACH6) | BIT(RTW89_DMA_ACH7) |
 				  BIT(RTW89_DMA_B1MG) | BIT(RTW89_DMA_B1HI),
-	.edcca_lvl_reg		= R_SEG0R_EDCCA_LVL_V1,
+	.edcca_regs		= &rtw8852b_edcca_regs,
 #ifdef CONFIG_PM
 	.wowlan_stub		= &rtw_wowlan_stub_8852b,
 #endif
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852be.c b/drivers/net/wireless/realtek/rtw89/rtw8852be.c
index ecf39d2d9f81..920b20bbcfb7 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852be.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852be.c
@@ -10,6 +10,7 @@
 #include "rtw8852b.h"
 
 static const struct rtw89_pci_info rtw8852b_pci_info = {
+	.gen_def		= &rtw89_pci_gen_ax,
 	.txbd_trunc_mode	= MAC_AX_BD_TRUNC,
 	.rxbd_trunc_mode	= MAC_AX_BD_TRUNC,
 	.rxbd_mode		= MAC_AX_RXBD_PKT,
@@ -24,6 +25,7 @@ static const struct rtw89_pci_info rtw8852b_pci_info = {
 	.autok_en		= MAC_AX_PCIE_DISABLE,
 	.io_rcy_en		= MAC_AX_PCIE_DISABLE,
 	.io_rcy_tmr		= MAC_AX_IO_RCY_ANA_TMR_6MS,
+	.rx_ring_eq_is_full	= false,
 
 	.init_cfg_reg		= R_AX_PCIE_INIT_CFG1,
 	.txhci_en_bit		= B_AX_TXHCI_EN,
@@ -33,6 +35,7 @@ static const struct rtw89_pci_info rtw8852b_pci_info = {
 	.max_tag_num_mask	= B_AX_MAX_TAG_NUM,
 	.rxbd_rwptr_clr_reg	= R_AX_RXBD_RWPTR_CLR,
 	.txbd_rwptr_clr2_reg	= 0,
+	.dma_io_stop		= {R_AX_PCIE_DMA_STOP1, B_AX_STOP_PCIEIO},
 	.dma_stop1		= {R_AX_PCIE_DMA_STOP1, B_AX_TX_STOP1_MASK_V1},
 	.dma_stop2		= {0},
 	.dma_busy1		= {R_AX_PCIE_DMA_BUSY1, DMA_BUSY1_CHECK_V1},
@@ -41,6 +44,7 @@ static const struct rtw89_pci_info rtw8852b_pci_info = {
 
 	.rpwm_addr		= R_AX_PCIE_HRPWM,
 	.cpwm_addr		= R_AX_CPWM,
+	.mit_addr		= R_AX_INT_MIT_RX,
 	.tx_dma_ch_mask		= BIT(RTW89_TXCH_ACH4) | BIT(RTW89_TXCH_ACH5) |
 				  BIT(RTW89_TXCH_ACH6) | BIT(RTW89_TXCH_ACH7) |
 				  BIT(RTW89_TXCH_CH10) | BIT(RTW89_TXCH_CH11),
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index 3b7d8ab39bab..8618d0204f66 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -167,6 +167,20 @@ static const struct rtw89_dig_regs rtw8852c_dig_regs = {
 			      B_PATH1_S20_FOLLOW_BY_PAGCUGC_EN_MSK},
 };
 
+static const struct rtw89_edcca_regs rtw8852c_edcca_regs = {
+	.edcca_level			= R_SEG0R_EDCCA_LVL,
+	.edcca_mask			= B_EDCCA_LVL_MSK0,
+	.edcca_p_mask			= B_EDCCA_LVL_MSK1,
+	.ppdu_level			= R_SEG0R_EDCCA_LVL,
+	.ppdu_mask			= B_EDCCA_LVL_MSK3,
+	.rpt_a				= R_EDCCA_RPT_A,
+	.rpt_b				= R_EDCCA_RPT_B,
+	.rpt_sel			= R_EDCCA_RPT_SEL,
+	.rpt_sel_mask			= B_EDCCA_RPT_SEL_MSK,
+	.tx_collision_t2r_st		= R_TX_COLLISION_T2R_ST,
+	.tx_collision_t2r_st_mask	= B_TX_COLLISION_T2R_ST_M,
+};
+
 static void rtw8852c_ctrl_btg_bt_rx(struct rtw89_dev *rtwdev, bool en,
 				    enum rtw89_phy_idx phy_idx);
 
@@ -426,11 +440,36 @@ static void rtw8852c_efuse_parsing_gain_offset(struct rtw89_dev *rtwdev,
 	valid |= _decode_efuse_gain(map->rx_gain_5g_high,
 				    &gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_5G_HIGH],
 				    &gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_5G_HIGH]);
+	valid |= _decode_efuse_gain(map->rx_gain_6g_l0,
+				    &gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_6G_L0],
+				    &gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_6G_L0]);
+	valid |= _decode_efuse_gain(map->rx_gain_6g_l1,
+				    &gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_6G_L1],
+				    &gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_6G_L1]);
+	valid |= _decode_efuse_gain(map->rx_gain_6g_m0,
+				    &gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_6G_M0],
+				    &gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_6G_M0]);
+	valid |= _decode_efuse_gain(map->rx_gain_6g_m1,
+				    &gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_6G_M1],
+				    &gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_6G_M1]);
+	valid |= _decode_efuse_gain(map->rx_gain_6g_h0,
+				    &gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_6G_H0],
+				    &gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_6G_H0]);
+	valid |= _decode_efuse_gain(map->rx_gain_6g_h1,
+				    &gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_6G_H1],
+				    &gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_6G_H1]);
+	valid |= _decode_efuse_gain(map->rx_gain_6g_uh0,
+				    &gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_6G_UH0],
+				    &gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_6G_UH0]);
+	valid |= _decode_efuse_gain(map->rx_gain_6g_uh1,
+				    &gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_6G_UH1],
+				    &gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_6G_UH1]);
 
 	gain->offset_valid = valid;
 }
 
-static int rtw8852c_read_efuse(struct rtw89_dev *rtwdev, u8 *log_map)
+static int rtw8852c_read_efuse(struct rtw89_dev *rtwdev, u8 *log_map,
+			       enum rtw89_efuse_block block)
 {
 	struct rtw89_efuse *efuse = &rtwdev->efuse;
 	struct rtw8852c_efuse *map;
@@ -2840,8 +2879,8 @@ const struct rtw89_chip_info rtw8852c_chip_info = {
 	.rsvd_ple_ofst		= 0x6f800,
 	.hfc_param_ini		= rtw8852c_hfc_param_ini_pcie,
 	.dle_mem		= rtw8852c_dle_mem_pcie,
-	.wde_qempty_acq_num     = 16,
-	.wde_qempty_mgq_sel     = 16,
+	.wde_qempty_acq_grpnum	= 16,
+	.wde_qempty_mgq_grpsel	= 16,
 	.rf_base_addr		= {0xe000, 0xf000},
 	.pwr_on_seq		= NULL,
 	.pwr_off_seq		= NULL,
@@ -2877,12 +2916,14 @@ const struct rtw89_chip_info rtw8852c_chip_info = {
 	.bacam_num		= 8,
 	.bacam_dynamic_num	= 8,
 	.bacam_ver		= RTW89_BACAM_V0_EXT,
+	.ppdu_max_usr		= 8,
 	.sec_ctrl_efuse_size	= 4,
 	.physical_efuse_size	= 1216,
 	.logical_efuse_size	= 2048,
 	.limit_efuse_size	= 1280,
 	.dav_phy_efuse_size	= 96,
 	.dav_log_efuse_size	= 16,
+	.efuse_blocks		= NULL,
 	.phycap_addr		= 0x590,
 	.phycap_size		= 0x60,
 	.para_ver		= 0x1,
@@ -2923,11 +2964,13 @@ const struct rtw89_chip_info rtw8852c_chip_info = {
 	.dcfo_comp		= &rtw8852c_dcfo_comp,
 	.dcfo_comp_sft		= 12,
 	.imr_info		= &rtw8852c_imr_info,
+	.imr_dmac_table		= NULL,
+	.imr_cmac_table		= NULL,
 	.rrsr_cfgs		= &rtw8852c_rrsr_cfgs,
 	.bss_clr_vld		= {R_BSS_CLR_MAP, B_BSS_CLR_MAP_VLD0},
 	.bss_clr_map_reg	= R_BSS_CLR_MAP,
 	.dma_ch_mask		= 0,
-	.edcca_lvl_reg		= R_SEG0R_EDCCA_LVL,
+	.edcca_regs		= &rtw8852c_edcca_regs,
 #ifdef CONFIG_PM
 	.wowlan_stub		= &rtw_wowlan_stub_8852c,
 #endif
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.h b/drivers/net/wireless/realtek/rtw89/rtw8852c.h
index ac642808a81f..77b05daedd10 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.h
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.h
@@ -73,9 +73,25 @@ struct rtw8852c_efuse {
 	u8 bw40_1s_tssi_6g_a[TSSI_MCS_6G_CH_GROUP_NUM];
 	u8 rsvd14[10];
 	u8 bw40_1s_tssi_6g_b[TSSI_MCS_6G_CH_GROUP_NUM];
-	u8 rsvd15[110];
+	u8 rsvd15[94];
+	u8 rx_gain_6g_l0;
+	u8 rsvd16;
+	u8 rx_gain_6g_l1;
+	u8 rsvd17;
+	u8 rx_gain_6g_m0;
+	u8 rsvd18;
+	u8 rx_gain_6g_m1;
+	u8 rsvd19;
+	u8 rx_gain_6g_h0;
+	u8 rsvd20;
+	u8 rx_gain_6g_h1;
+	u8 rsvd21;
+	u8 rx_gain_6g_uh0;
+	u8 rsvd22;
+	u8 rx_gain_6g_uh1;
+	u8 rsvd23;
 	u8 channel_plan_6g;
-	u8 rsvd16[71];
+	u8 rsvd24[71];
 	union {
 		struct rtw8852c_u_efuse u;
 		struct rtw8852c_e_efuse e;
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852ce.c b/drivers/net/wireless/realtek/rtw89/rtw8852ce.c
index 80490a5437df..4592de3dbd94 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852ce.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852ce.c
@@ -19,6 +19,7 @@ static const struct rtw89_pci_bd_idx_addr rtw8852c_bd_idx_addr_low_power = {
 };
 
 static const struct rtw89_pci_info rtw8852c_pci_info = {
+	.gen_def		= &rtw89_pci_gen_ax,
 	.txbd_trunc_mode	= MAC_AX_BD_TRUNC,
 	.rxbd_trunc_mode	= MAC_AX_BD_TRUNC,
 	.rxbd_mode		= MAC_AX_RXBD_PKT,
@@ -33,6 +34,7 @@ static const struct rtw89_pci_info rtw8852c_pci_info = {
 	.autok_en		= MAC_AX_PCIE_DISABLE,
 	.io_rcy_en		= MAC_AX_PCIE_ENABLE,
 	.io_rcy_tmr		= MAC_AX_IO_RCY_ANA_TMR_6MS,
+	.rx_ring_eq_is_full	= false,
 
 	.init_cfg_reg		= R_AX_HAXI_INIT_CFG1,
 	.txhci_en_bit		= B_AX_TXHCI_EN_V1,
@@ -42,6 +44,7 @@ static const struct rtw89_pci_info rtw8852c_pci_info = {
 	.max_tag_num_mask	= B_AX_MAX_TAG_NUM_V1_MASK,
 	.rxbd_rwptr_clr_reg	= R_AX_RXBD_RWPTR_CLR_V1,
 	.txbd_rwptr_clr2_reg	= R_AX_TXBD_RWPTR_CLR2_V1,
+	.dma_io_stop		= {R_AX_HAXI_INIT_CFG1, B_AX_STOP_AXI_MST},
 	.dma_stop1		= {R_AX_HAXI_DMA_STOP1, B_AX_TX_STOP1_MASK},
 	.dma_stop2		= {R_AX_HAXI_DMA_STOP2, B_AX_TX_STOP2_ALL},
 	.dma_busy1		= {R_AX_HAXI_DMA_BUSY1, DMA_BUSY1_CHECK},
@@ -50,6 +53,7 @@ static const struct rtw89_pci_info rtw8852c_pci_info = {
 
 	.rpwm_addr		= R_AX_PCIE_HRPWM_V1,
 	.cpwm_addr		= R_AX_PCIE_CRPWM,
+	.mit_addr		= R_AX_INT_MIT_RX_V1,
 	.tx_dma_ch_mask		= 0,
 	.bd_idx_addr_low_power	= &rtw8852c_bd_idx_addr_low_power,
 	.dma_addr_set		= &rtw89_pci_ch_dma_addr_set_v1,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
new file mode 100644
index 000000000000..0e7300cc6d9e
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -0,0 +1,710 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/* Copyright(c) 2023  Realtek Corporation
+ */
+
+#include "debug.h"
+#include "efuse.h"
+#include "fw.h"
+#include "mac.h"
+#include "phy.h"
+#include "reg.h"
+#include "rtw8922a.h"
+
+#define RTW8922A_FW_FORMAT_MAX 0
+#define RTW8922A_FW_BASENAME "rtw89/rtw8922a_fw"
+#define RTW8922A_MODULE_FIRMWARE \
+	RTW8922A_FW_BASENAME ".bin"
+
+static const struct rtw89_hfc_ch_cfg rtw8922a_hfc_chcfg_pcie[] = {
+	{2, 1641, grp_0}, /* ACH 0 */
+	{2, 1641, grp_0}, /* ACH 1 */
+	{2, 1641, grp_0}, /* ACH 2 */
+	{2, 1641, grp_0}, /* ACH 3 */
+	{2, 1641, grp_1}, /* ACH 4 */
+	{2, 1641, grp_1}, /* ACH 5 */
+	{2, 1641, grp_1}, /* ACH 6 */
+	{2, 1641, grp_1}, /* ACH 7 */
+	{2, 1641, grp_0}, /* B0MGQ */
+	{2, 1641, grp_0}, /* B0HIQ */
+	{2, 1641, grp_1}, /* B1MGQ */
+	{2, 1641, grp_1}, /* B1HIQ */
+	{0, 0, 0}, /* FWCMDQ */
+	{0, 0, 0}, /* BMC */
+	{0, 0, 0}, /* H2D */
+};
+
+static const struct rtw89_hfc_pub_cfg rtw8922a_hfc_pubcfg_pcie = {
+	1651, /* Group 0 */
+	1651, /* Group 1 */
+	3302, /* Public Max */
+	0, /* WP threshold */
+};
+
+static const struct rtw89_hfc_param_ini rtw8922a_hfc_param_ini_pcie[] = {
+	[RTW89_QTA_SCC] = {rtw8922a_hfc_chcfg_pcie, &rtw8922a_hfc_pubcfg_pcie,
+			   &rtw89_mac_size.hfc_prec_cfg_c0, RTW89_HCIFC_POH},
+	[RTW89_QTA_DLFW] = {NULL, NULL, &rtw89_mac_size.hfc_prec_cfg_c2,
+			    RTW89_HCIFC_POH},
+	[RTW89_QTA_INVALID] = {NULL},
+};
+
+static const struct rtw89_dle_mem rtw8922a_dle_mem_pcie[] = {
+	[RTW89_QTA_SCC] = {RTW89_QTA_SCC, &rtw89_mac_size.wde_size0_v1,
+			   &rtw89_mac_size.ple_size0_v1, &rtw89_mac_size.wde_qt0_v1,
+			   &rtw89_mac_size.wde_qt0_v1, &rtw89_mac_size.ple_qt0,
+			   &rtw89_mac_size.ple_qt1, &rtw89_mac_size.ple_rsvd_qt0,
+			   &rtw89_mac_size.rsvd0_size0, &rtw89_mac_size.rsvd1_size0},
+	[RTW89_QTA_DLFW] = {RTW89_QTA_DLFW, &rtw89_mac_size.wde_size4_v1,
+			    &rtw89_mac_size.ple_size3_v1, &rtw89_mac_size.wde_qt4,
+			    &rtw89_mac_size.wde_qt4, &rtw89_mac_size.ple_qt9,
+			    &rtw89_mac_size.ple_qt9, &rtw89_mac_size.ple_rsvd_qt1,
+			    &rtw89_mac_size.rsvd0_size0, &rtw89_mac_size.rsvd1_size0},
+	[RTW89_QTA_INVALID] = {RTW89_QTA_INVALID, NULL, NULL, NULL, NULL, NULL,
+			       NULL},
+};
+
+static const struct rtw89_reg_imr rtw8922a_imr_dmac_regs[] = {
+	{R_BE_DISP_HOST_IMR, B_BE_DISP_HOST_IMR_CLR, B_BE_DISP_HOST_IMR_SET},
+	{R_BE_DISP_CPU_IMR, B_BE_DISP_CPU_IMR_CLR, B_BE_DISP_CPU_IMR_SET},
+	{R_BE_DISP_OTHER_IMR, B_BE_DISP_OTHER_IMR_CLR, B_BE_DISP_OTHER_IMR_SET},
+	{R_BE_PKTIN_ERR_IMR, B_BE_PKTIN_ERR_IMR_CLR, B_BE_PKTIN_ERR_IMR_SET},
+	{R_BE_INTERRUPT_MASK_REG, B_BE_INTERRUPT_MASK_REG_CLR, B_BE_INTERRUPT_MASK_REG_SET},
+	{R_BE_MLO_ERR_IDCT_IMR, B_BE_MLO_ERR_IDCT_IMR_CLR, B_BE_MLO_ERR_IDCT_IMR_SET},
+	{R_BE_MPDU_TX_ERR_IMR, B_BE_MPDU_TX_ERR_IMR_CLR, B_BE_MPDU_TX_ERR_IMR_SET},
+	{R_BE_MPDU_RX_ERR_IMR, B_BE_MPDU_RX_ERR_IMR_CLR, B_BE_MPDU_RX_ERR_IMR_SET},
+	{R_BE_SEC_ERROR_IMR, B_BE_SEC_ERROR_IMR_CLR, B_BE_SEC_ERROR_IMR_SET},
+	{R_BE_CPUIO_ERR_IMR, B_BE_CPUIO_ERR_IMR_CLR, B_BE_CPUIO_ERR_IMR_SET},
+	{R_BE_WDE_ERR_IMR, B_BE_WDE_ERR_IMR_CLR, B_BE_WDE_ERR_IMR_SET},
+	{R_BE_WDE_ERR1_IMR, B_BE_WDE_ERR1_IMR_CLR, B_BE_WDE_ERR1_IMR_SET},
+	{R_BE_PLE_ERR_IMR, B_BE_PLE_ERR_IMR_CLR, B_BE_PLE_ERR_IMR_SET},
+	{R_BE_PLE_ERRFLAG1_IMR, B_BE_PLE_ERRFLAG1_IMR_CLR, B_BE_PLE_ERRFLAG1_IMR_SET},
+	{R_BE_WDRLS_ERR_IMR, B_BE_WDRLS_ERR_IMR_CLR, B_BE_WDRLS_ERR_IMR_SET},
+	{R_BE_TXPKTCTL_B0_ERRFLAG_IMR, B_BE_TXPKTCTL_B0_ERRFLAG_IMR_CLR,
+	 B_BE_TXPKTCTL_B0_ERRFLAG_IMR_SET},
+	{R_BE_TXPKTCTL_B1_ERRFLAG_IMR, B_BE_TXPKTCTL_B1_ERRFLAG_IMR_CLR,
+	 B_BE_TXPKTCTL_B1_ERRFLAG_IMR_SET},
+	{R_BE_BBRPT_COM_ERR_IMR, B_BE_BBRPT_COM_ERR_IMR_CLR, B_BE_BBRPT_COM_ERR_IMR_SET},
+	{R_BE_BBRPT_CHINFO_ERR_IMR, B_BE_BBRPT_CHINFO_ERR_IMR_CLR,
+	 B_BE_BBRPT_CHINFO_ERR_IMR_SET},
+	{R_BE_BBRPT_DFS_ERR_IMR, B_BE_BBRPT_DFS_ERR_IMR_CLR, B_BE_BBRPT_DFS_ERR_IMR_SET},
+	{R_BE_LA_ERRFLAG_IMR, B_BE_LA_ERRFLAG_IMR_CLR, B_BE_LA_ERRFLAG_IMR_SET},
+	{R_BE_CH_INFO_DBGFLAG_IMR, B_BE_CH_INFO_DBGFLAG_IMR_CLR, B_BE_CH_INFO_DBGFLAG_IMR_SET},
+	{R_BE_PLRLS_ERR_IMR, B_BE_PLRLS_ERR_IMR_CLR, B_BE_PLRLS_ERR_IMR_SET},
+	{R_BE_HAXI_IDCT_MSK, B_BE_HAXI_IDCT_MSK_CLR, B_BE_HAXI_IDCT_MSK_SET},
+};
+
+static const struct rtw89_imr_table rtw8922a_imr_dmac_table = {
+	.regs = rtw8922a_imr_dmac_regs,
+	.n_regs = ARRAY_SIZE(rtw8922a_imr_dmac_regs),
+};
+
+static const struct rtw89_reg_imr rtw8922a_imr_cmac_regs[] = {
+	{R_BE_RESP_IMR, B_BE_RESP_IMR_CLR, B_BE_RESP_IMR_SET},
+	{R_BE_RX_ERROR_FLAG_IMR, B_BE_RX_ERROR_FLAG_IMR_CLR, B_BE_RX_ERROR_FLAG_IMR_SET},
+	{R_BE_TX_ERROR_FLAG_IMR, B_BE_TX_ERROR_FLAG_IMR_CLR, B_BE_TX_ERROR_FLAG_IMR_SET},
+	{R_BE_RX_ERROR_FLAG_IMR_1, B_BE_TX_ERROR_FLAG_IMR_1_CLR, B_BE_TX_ERROR_FLAG_IMR_1_SET},
+	{R_BE_PTCL_IMR1, B_BE_PTCL_IMR1_CLR, B_BE_PTCL_IMR1_SET},
+	{R_BE_PTCL_IMR0, B_BE_PTCL_IMR0_CLR, B_BE_PTCL_IMR0_SET},
+	{R_BE_PTCL_IMR_2, B_BE_PTCL_IMR_2_CLR, B_BE_PTCL_IMR_2_SET},
+	{R_BE_SCHEDULE_ERR_IMR, B_BE_SCHEDULE_ERR_IMR_CLR, B_BE_SCHEDULE_ERR_IMR_SET},
+	{R_BE_C0_TXPWR_IMR, B_BE_C0_TXPWR_IMR_CLR, B_BE_C0_TXPWR_IMR_SET},
+	{R_BE_TRXPTCL_ERROR_INDICA_MASK, B_BE_TRXPTCL_ERROR_INDICA_MASK_CLR,
+	 B_BE_TRXPTCL_ERROR_INDICA_MASK_SET},
+	{R_BE_RX_ERR_IMR, B_BE_RX_ERR_IMR_CLR, B_BE_RX_ERR_IMR_SET},
+	{R_BE_PHYINFO_ERR_IMR_V1, B_BE_PHYINFO_ERR_IMR_V1_CLR, B_BE_PHYINFO_ERR_IMR_V1_SET},
+};
+
+static const struct rtw89_imr_table rtw8922a_imr_cmac_table = {
+	.regs = rtw8922a_imr_cmac_regs,
+	.n_regs = ARRAY_SIZE(rtw8922a_imr_cmac_regs),
+};
+
+static const struct rtw89_efuse_block_cfg rtw8922a_efuse_blocks[] = {
+	[RTW89_EFUSE_BLOCK_SYS]			= {.offset = 0x00000, .size = 0x310},
+	[RTW89_EFUSE_BLOCK_RF]			= {.offset = 0x10000, .size = 0x240},
+	[RTW89_EFUSE_BLOCK_HCI_DIG_PCIE_SDIO]	= {.offset = 0x20000, .size = 0x4800},
+	[RTW89_EFUSE_BLOCK_HCI_DIG_USB]		= {.offset = 0x30000, .size = 0x890},
+	[RTW89_EFUSE_BLOCK_HCI_PHY_PCIE]	= {.offset = 0x40000, .size = 0x200},
+	[RTW89_EFUSE_BLOCK_HCI_PHY_USB3]	= {.offset = 0x50000, .size = 0x80},
+	[RTW89_EFUSE_BLOCK_HCI_PHY_USB2]	= {.offset = 0x60000, .size = 0x0},
+	[RTW89_EFUSE_BLOCK_ADIE]		= {.offset = 0x70000, .size = 0x10},
+};
+
+static int rtw8922a_pwr_on_func(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_hal *hal = &rtwdev->hal;
+	u32 val32;
+	int ret;
+
+	rtw89_write32_clr(rtwdev, R_BE_SYS_PW_CTRL, B_BE_AFSM_WLSUS_EN |
+						    B_BE_AFSM_PCIE_SUS_EN);
+	rtw89_write32_set(rtwdev, R_BE_SYS_PW_CTRL, B_BE_DIS_WLBT_PDNSUSEN_SOPC);
+	rtw89_write32_set(rtwdev, R_BE_WLLPS_CTRL, B_BE_DIS_WLBT_LPSEN_LOPC);
+	rtw89_write32_clr(rtwdev, R_BE_SYS_PW_CTRL, B_BE_APDM_HPDN);
+	rtw89_write32_clr(rtwdev, R_BE_SYS_PW_CTRL, B_BE_APFM_SWLPS);
+
+	ret = read_poll_timeout(rtw89_read32, val32, val32 & B_BE_RDY_SYSPWR,
+				1000, 3000000, false, rtwdev, R_BE_SYS_PW_CTRL);
+	if (ret)
+		return ret;
+
+	rtw89_write32_set(rtwdev, R_BE_SYS_PW_CTRL, B_BE_EN_WLON);
+	rtw89_write32_set(rtwdev, R_BE_WLRESUME_CTRL, B_BE_LPSROP_CMAC0 |
+						      B_BE_LPSROP_CMAC1);
+	rtw89_write32_set(rtwdev, R_BE_SYS_PW_CTRL, B_BE_APFN_ONMAC);
+
+	ret = read_poll_timeout(rtw89_read32, val32, !(val32 & B_BE_APFN_ONMAC),
+				1000, 3000000, false, rtwdev, R_BE_SYS_PW_CTRL);
+	if (ret)
+		return ret;
+
+	rtw89_write32_clr(rtwdev, R_BE_AFE_ON_CTRL1, B_BE_REG_CK_MON_CK960M_EN);
+	rtw89_write8_set(rtwdev, R_BE_ANAPAR_POW_MAC, B_BE_POW_PC_LDO_PORT0 |
+						      B_BE_POW_PC_LDO_PORT1);
+	rtw89_write32_clr(rtwdev, R_BE_FEN_RST_ENABLE, B_BE_R_SYM_ISO_ADDA_P02PP |
+						       B_BE_R_SYM_ISO_ADDA_P12PP);
+	rtw89_write8_set(rtwdev, R_BE_PLATFORM_ENABLE, B_BE_PLATFORM_EN);
+	rtw89_write32_set(rtwdev, R_BE_HCI_OPT_CTRL, B_BE_HAXIDMA_IO_EN);
+
+	ret = read_poll_timeout(rtw89_read32, val32, val32 & B_BE_HAXIDMA_IO_ST,
+				1000, 3000000, false, rtwdev, R_BE_HCI_OPT_CTRL);
+	if (ret)
+		return ret;
+
+	ret = read_poll_timeout(rtw89_read32, val32, !(val32 & B_BE_HAXIDMA_BACKUP_RESTORE_ST),
+				1000, 3000000, false, rtwdev, R_BE_HCI_OPT_CTRL);
+	if (ret)
+		return ret;
+
+	rtw89_write32_set(rtwdev, R_BE_HCI_OPT_CTRL, B_BE_HCI_WLAN_IO_EN);
+
+	ret = read_poll_timeout(rtw89_read32, val32, val32 & B_BE_HCI_WLAN_IO_ST,
+				1000, 3000000, false, rtwdev, R_BE_HCI_OPT_CTRL);
+	if (ret)
+		return ret;
+
+	rtw89_write32_clr(rtwdev, R_BE_SYS_SDIO_CTRL, B_BE_PCIE_FORCE_IBX_EN);
+
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_PLL, 0x02, 0x02);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_PLL, 0x01, 0x01);
+	if (ret)
+		return ret;
+
+	rtw89_write32_set(rtwdev, R_BE_SYS_ADIE_PAD_PWR_CTRL, B_BE_SYM_PADPDN_WL_RFC1_1P3);
+
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0x40, 0x40);
+	if (ret)
+		return ret;
+
+	rtw89_write32_set(rtwdev, R_BE_SYS_ADIE_PAD_PWR_CTRL, B_BE_SYM_PADPDN_WL_RFC0_1P3);
+
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0x20, 0x20);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0x04, 0x04);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0x08, 0x08);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0, 0x10);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_WL_RFC_S0, 0xEB, 0xFF);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_WL_RFC_S1, 0xEB, 0xFF);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0x01, 0x01);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0x02, 0x02);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0, 0x80);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_XREF_RF1, 0, 0x40);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_XREF_RF2, 0, 0x40);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_PLL_1, 0x40, 0x60);
+	if (ret)
+		return ret;
+
+	if (hal->cv != CHIP_CAV) {
+		rtw89_write32_set(rtwdev, R_BE_PMC_DBG_CTRL2, B_BE_SYSON_DIS_PMCR_BE_WRMSK);
+		rtw89_write32_set(rtwdev, R_BE_SYS_ISO_CTRL, B_BE_ISO_EB2CORE);
+		rtw89_write32_clr(rtwdev, R_BE_SYS_ISO_CTRL, B_BE_PWC_EV2EF_B);
+
+		mdelay(1);
+
+		rtw89_write32_clr(rtwdev, R_BE_SYS_ISO_CTRL, B_BE_PWC_EV2EF_S);
+		rtw89_write32_clr(rtwdev, R_BE_PMC_DBG_CTRL2, B_BE_SYSON_DIS_PMCR_BE_WRMSK);
+	}
+
+	rtw89_write32_set(rtwdev, R_BE_DMAC_FUNC_EN,
+			  B_BE_MAC_FUNC_EN | B_BE_DMAC_FUNC_EN | B_BE_MPDU_PROC_EN |
+			  B_BE_WD_RLS_EN | B_BE_DLE_WDE_EN | B_BE_TXPKT_CTRL_EN |
+			  B_BE_STA_SCH_EN | B_BE_DLE_PLE_EN | B_BE_PKT_BUF_EN |
+			  B_BE_DMAC_TBL_EN | B_BE_PKT_IN_EN | B_BE_DLE_CPUIO_EN |
+			  B_BE_DISPATCHER_EN | B_BE_BBRPT_EN | B_BE_MAC_SEC_EN |
+			  B_BE_H_AXIDMA_EN | B_BE_DMAC_MLO_EN | B_BE_PLRLS_EN |
+			  B_BE_P_AXIDMA_EN | B_BE_DLE_DATACPUIO_EN | B_BE_LTR_CTL_EN);
+
+	set_bit(RTW89_FLAG_DMAC_FUNC, rtwdev->flags);
+
+	rtw89_write32_set(rtwdev, R_BE_CMAC_SHARE_FUNC_EN,
+			  B_BE_CMAC_SHARE_EN | B_BE_RESPBA_EN | B_BE_ADDRSRCH_EN |
+			  B_BE_BTCOEX_EN);
+	rtw89_write32_set(rtwdev, R_BE_CMAC_FUNC_EN,
+			  B_BE_CMAC_EN | B_BE_CMAC_TXEN |  B_BE_CMAC_RXEN |
+			  B_BE_SIGB_EN | B_BE_PHYINTF_EN | B_BE_CMAC_DMA_EN |
+			  B_BE_PTCLTOP_EN | B_BE_SCHEDULER_EN | B_BE_TMAC_EN |
+			  B_BE_RMAC_EN | B_BE_TXTIME_EN | B_BE_RESP_PKTCTL_EN);
+
+	set_bit(RTW89_FLAG_CMAC0_FUNC, rtwdev->flags);
+
+	rtw89_write32_set(rtwdev, R_BE_FEN_RST_ENABLE, B_BE_FEN_BB_IP_RSTN |
+						       B_BE_FEN_BBPLAT_RSTB);
+
+	return 0;
+}
+
+static int rtw8922a_pwr_off_func(struct rtw89_dev *rtwdev)
+{
+	u32 val32;
+	int ret;
+
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0x10, 0x10);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0, 0x08);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0, 0x04);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_WL_RFC_S0, 0xC6, 0xFF);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_WL_RFC_S1, 0xC6, 0xFF);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0x80, 0x80);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0, 0x02);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0, 0x01);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_PLL, 0x02, 0xFF);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_PLL, 0x00, 0xFF);
+	if (ret)
+		return ret;
+
+	rtw89_write32_set(rtwdev, R_BE_FEN_RST_ENABLE, B_BE_R_SYM_ISO_ADDA_P02PP |
+						       B_BE_R_SYM_ISO_ADDA_P12PP);
+	rtw89_write8_clr(rtwdev, R_BE_ANAPAR_POW_MAC, B_BE_POW_PC_LDO_PORT0 |
+						      B_BE_POW_PC_LDO_PORT1);
+	rtw89_write32_set(rtwdev, R_BE_SYS_PW_CTRL, B_BE_EN_WLON);
+	rtw89_write8_clr(rtwdev, R_BE_FEN_RST_ENABLE, B_BE_FEN_BB_IP_RSTN |
+						      B_BE_FEN_BBPLAT_RSTB);
+	rtw89_write32_clr(rtwdev, R_BE_SYS_ADIE_PAD_PWR_CTRL, B_BE_SYM_PADPDN_WL_RFC0_1P3);
+
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0, 0x20);
+	if (ret)
+		return ret;
+
+	rtw89_write32_clr(rtwdev, R_BE_SYS_ADIE_PAD_PWR_CTRL, B_BE_SYM_PADPDN_WL_RFC1_1P3);
+
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0, 0x40);
+	if (ret)
+		return ret;
+
+	rtw89_write32_clr(rtwdev, R_BE_HCI_OPT_CTRL, B_BE_HAXIDMA_IO_EN);
+
+	ret = read_poll_timeout(rtw89_read32, val32, !(val32 & B_BE_HAXIDMA_IO_ST),
+				1000, 3000000, false, rtwdev, R_BE_HCI_OPT_CTRL);
+	if (ret)
+		return ret;
+
+	ret = read_poll_timeout(rtw89_read32, val32, !(val32 & B_BE_HAXIDMA_BACKUP_RESTORE_ST),
+				1000, 3000000, false, rtwdev, R_BE_HCI_OPT_CTRL);
+	if (ret)
+		return ret;
+
+	rtw89_write32_clr(rtwdev, R_BE_HCI_OPT_CTRL, B_BE_HCI_WLAN_IO_EN);
+
+	ret = read_poll_timeout(rtw89_read32, val32, !(val32 & B_BE_HCI_WLAN_IO_ST),
+				1000, 3000000, false, rtwdev, R_BE_HCI_OPT_CTRL);
+	if (ret)
+		return ret;
+
+	rtw89_write32_set(rtwdev, R_BE_SYS_PW_CTRL, B_BE_APFM_OFFMAC);
+
+	ret = read_poll_timeout(rtw89_read32, val32, !(val32 & B_BE_APFM_OFFMAC),
+				1000, 3000000, false, rtwdev, R_BE_SYS_PW_CTRL);
+	if (ret)
+		return ret;
+
+	rtw89_write32(rtwdev, R_BE_WLLPS_CTRL, 0x0000A1B2);
+	rtw89_write32_set(rtwdev, R_BE_SYS_PW_CTRL, B_BE_XTAL_OFF_A_DIE);
+	rtw89_write32_set(rtwdev, R_BE_SYS_PW_CTRL, B_BE_APFM_SWLPS);
+	rtw89_write32(rtwdev, R_BE_UDM1, 0);
+
+	return 0;
+}
+
+static void rtw8922a_efuse_parsing_tssi(struct rtw89_dev *rtwdev,
+					struct rtw8922a_efuse *map)
+{
+	struct rtw8922a_tssi_offset *ofst[] = {&map->path_a_tssi, &map->path_b_tssi};
+	u8 *bw40_1s_tssi_6g_ofst[] = {map->bw40_1s_tssi_6g_a, map->bw40_1s_tssi_6g_b};
+	struct rtw89_tssi_info *tssi = &rtwdev->tssi;
+	u8 i, j;
+
+	tssi->thermal[RF_PATH_A] = map->path_a_therm;
+	tssi->thermal[RF_PATH_B] = map->path_b_therm;
+
+	for (i = 0; i < RF_PATH_NUM_8922A; i++) {
+		memcpy(tssi->tssi_cck[i], ofst[i]->cck_tssi,
+		       sizeof(ofst[i]->cck_tssi));
+
+		for (j = 0; j < TSSI_CCK_CH_GROUP_NUM; j++)
+			rtw89_debug(rtwdev, RTW89_DBG_TSSI,
+				    "[TSSI][EFUSE] path=%d cck[%d]=0x%x\n",
+				    i, j, tssi->tssi_cck[i][j]);
+
+		memcpy(tssi->tssi_mcs[i], ofst[i]->bw40_tssi,
+		       sizeof(ofst[i]->bw40_tssi));
+		memcpy(tssi->tssi_mcs[i] + TSSI_MCS_2G_CH_GROUP_NUM,
+		       ofst[i]->bw40_1s_tssi_5g, sizeof(ofst[i]->bw40_1s_tssi_5g));
+		memcpy(tssi->tssi_6g_mcs[i], bw40_1s_tssi_6g_ofst[i],
+		       sizeof(tssi->tssi_6g_mcs[i]));
+
+		for (j = 0; j < TSSI_MCS_CH_GROUP_NUM; j++)
+			rtw89_debug(rtwdev, RTW89_DBG_TSSI,
+				    "[TSSI][EFUSE] path=%d mcs[%d]=0x%x\n",
+				    i, j, tssi->tssi_mcs[i][j]);
+	}
+}
+
+static void rtw8922a_efuse_parsing_gain_offset(struct rtw89_dev *rtwdev,
+					       struct rtw8922a_efuse *map)
+{
+	struct rtw89_phy_efuse_gain *gain = &rtwdev->efuse_gain;
+	bool all_0xff = true, all_0x00 = true;
+	int i, j;
+	u8 t;
+
+	gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_2G_CCK] = map->rx_gain_a._2g_cck;
+	gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_2G_CCK] = map->rx_gain_b._2g_cck;
+	gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_2G_OFDM] = map->rx_gain_a._2g_ofdm;
+	gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_2G_OFDM] = map->rx_gain_b._2g_ofdm;
+	gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_5G_LOW] = map->rx_gain_a._5g_low;
+	gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_5G_LOW] = map->rx_gain_b._5g_low;
+	gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_5G_MID] = map->rx_gain_a._5g_mid;
+	gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_5G_MID] = map->rx_gain_b._5g_mid;
+	gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_5G_HIGH] = map->rx_gain_a._5g_high;
+	gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_5G_HIGH] = map->rx_gain_b._5g_high;
+	gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_6G_L0] = map->rx_gain_6g_a._6g_l0;
+	gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_6G_L0] = map->rx_gain_6g_b._6g_l0;
+	gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_6G_L1] = map->rx_gain_6g_a._6g_l1;
+	gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_6G_L1] = map->rx_gain_6g_b._6g_l1;
+	gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_6G_M0] = map->rx_gain_6g_a._6g_m0;
+	gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_6G_M0] = map->rx_gain_6g_b._6g_m0;
+	gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_6G_M1] = map->rx_gain_6g_a._6g_m1;
+	gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_6G_M1] = map->rx_gain_6g_b._6g_m1;
+	gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_6G_H0] = map->rx_gain_6g_a._6g_h0;
+	gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_6G_H0] = map->rx_gain_6g_b._6g_h0;
+	gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_6G_H1] = map->rx_gain_6g_a._6g_h1;
+	gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_6G_H1] = map->rx_gain_6g_b._6g_h1;
+	gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_6G_UH0] = map->rx_gain_6g_a._6g_uh0;
+	gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_6G_UH0] = map->rx_gain_6g_b._6g_uh0;
+	gain->offset[RF_PATH_A][RTW89_GAIN_OFFSET_6G_UH1] = map->rx_gain_6g_a._6g_uh1;
+	gain->offset[RF_PATH_B][RTW89_GAIN_OFFSET_6G_UH1] = map->rx_gain_6g_b._6g_uh1;
+
+	for (i = RF_PATH_A; i <= RF_PATH_B; i++)
+		for (j = 0; j < RTW89_GAIN_OFFSET_NR; j++) {
+			t = gain->offset[i][j];
+			if (t != 0xff)
+				all_0xff = false;
+			if (t != 0x0)
+				all_0x00 = false;
+
+			/* transform: sign-bit + U(7,2) to S(8,2) */
+			if (t & 0x80)
+				gain->offset[i][j] = (t ^ 0x7f) + 1;
+		}
+
+	gain->offset_valid = !all_0xff && !all_0x00;
+}
+
+static void rtw8922a_read_efuse_mac_addr(struct rtw89_dev *rtwdev, u32 addr)
+{
+	struct rtw89_efuse *efuse = &rtwdev->efuse;
+	u16 val;
+	int i;
+
+	for (i = 0; i < ETH_ALEN; i += 2, addr += 2) {
+		val = rtw89_read16(rtwdev, addr);
+		efuse->addr[i] = val & 0xff;
+		efuse->addr[i + 1] = val >> 8;
+	}
+}
+
+static int rtw8922a_read_efuse_pci_sdio(struct rtw89_dev *rtwdev, u8 *log_map)
+{
+	struct rtw89_efuse *efuse = &rtwdev->efuse;
+
+	if (rtwdev->hci.type == RTW89_HCI_TYPE_PCIE)
+		rtw8922a_read_efuse_mac_addr(rtwdev, 0x3104);
+	else
+		ether_addr_copy(efuse->addr, log_map + 0x001A);
+
+	return 0;
+}
+
+static int rtw8922a_read_efuse_usb(struct rtw89_dev *rtwdev, u8 *log_map)
+{
+	rtw8922a_read_efuse_mac_addr(rtwdev, 0x4078);
+
+	return 0;
+}
+
+static int rtw8922a_read_efuse_rf(struct rtw89_dev *rtwdev, u8 *log_map)
+{
+	struct rtw8922a_efuse *map = (struct rtw8922a_efuse *)log_map;
+	struct rtw89_efuse *efuse = &rtwdev->efuse;
+
+	efuse->rfe_type = map->rfe_type;
+	efuse->xtal_cap = map->xtal_k;
+	efuse->country_code[0] = map->country_code[0];
+	efuse->country_code[1] = map->country_code[1];
+	rtw8922a_efuse_parsing_tssi(rtwdev, map);
+	rtw8922a_efuse_parsing_gain_offset(rtwdev, map);
+
+	rtw89_info(rtwdev, "chip rfe_type is %d\n", efuse->rfe_type);
+
+	return 0;
+}
+
+static int rtw8922a_read_efuse(struct rtw89_dev *rtwdev, u8 *log_map,
+			       enum rtw89_efuse_block block)
+{
+	switch (block) {
+	case RTW89_EFUSE_BLOCK_HCI_DIG_PCIE_SDIO:
+		return rtw8922a_read_efuse_pci_sdio(rtwdev, log_map);
+	case RTW89_EFUSE_BLOCK_HCI_DIG_USB:
+		return rtw8922a_read_efuse_usb(rtwdev, log_map);
+	case RTW89_EFUSE_BLOCK_RF:
+		return rtw8922a_read_efuse_rf(rtwdev, log_map);
+	default:
+		return 0;
+	}
+}
+
+#define THM_TRIM_POSITIVE_MASK BIT(6)
+#define THM_TRIM_MAGNITUDE_MASK GENMASK(5, 0)
+
+static void rtw8922a_phycap_parsing_thermal_trim(struct rtw89_dev *rtwdev,
+						 u8 *phycap_map)
+{
+	static const u32 thm_trim_addr[RF_PATH_NUM_8922A] = {0x1706, 0x1733};
+	struct rtw89_power_trim_info *info = &rtwdev->pwr_trim;
+	u32 addr = rtwdev->chip->phycap_addr;
+	bool pg = true;
+	u8 pg_th;
+	s8 val;
+	u8 i;
+
+	for (i = 0; i < RF_PATH_NUM_8922A; i++) {
+		pg_th = phycap_map[thm_trim_addr[i] - addr];
+		if (pg_th == 0xff) {
+			info->thermal_trim[i] = 0;
+			pg = false;
+			break;
+		}
+
+		val = u8_get_bits(pg_th, THM_TRIM_MAGNITUDE_MASK);
+
+		if (!(pg_th & THM_TRIM_POSITIVE_MASK))
+			val *= -1;
+
+		info->thermal_trim[i] = val;
+
+		rtw89_debug(rtwdev, RTW89_DBG_RFK,
+			    "[THERMAL][TRIM] path=%d thermal_trim=0x%x (%d)\n",
+			    i, pg_th, val);
+	}
+
+	info->pg_thermal_trim = pg;
+}
+
+static void rtw8922a_phycap_parsing_pa_bias_trim(struct rtw89_dev *rtwdev,
+						 u8 *phycap_map)
+{
+	static const u32 pabias_trim_addr[RF_PATH_NUM_8922A] = {0x1707, 0x1734};
+	static const u32 check_pa_pad_trim_addr = 0x1700;
+	struct rtw89_power_trim_info *info = &rtwdev->pwr_trim;
+	u32 addr = rtwdev->chip->phycap_addr;
+	u8 val;
+	u8 i;
+
+	val = phycap_map[check_pa_pad_trim_addr - addr];
+	if (val != 0xff)
+		info->pg_pa_bias_trim = true;
+
+	for (i = 0; i < RF_PATH_NUM_8922A; i++) {
+		info->pa_bias_trim[i] = phycap_map[pabias_trim_addr[i] - addr];
+
+		rtw89_debug(rtwdev, RTW89_DBG_RFK,
+			    "[PA_BIAS][TRIM] path=%d pa_bias_trim=0x%x\n",
+			    i, info->pa_bias_trim[i]);
+	}
+}
+
+static void rtw8922a_phycap_parsing_pad_bias_trim(struct rtw89_dev *rtwdev,
+						  u8 *phycap_map)
+{
+	static const u32 pad_bias_trim_addr[RF_PATH_NUM_8922A] = {0x1708, 0x1735};
+	struct rtw89_power_trim_info *info = &rtwdev->pwr_trim;
+	u32 addr = rtwdev->chip->phycap_addr;
+	u8 i;
+
+	for (i = 0; i < RF_PATH_NUM_8922A; i++) {
+		info->pad_bias_trim[i] = phycap_map[pad_bias_trim_addr[i] - addr];
+
+		rtw89_debug(rtwdev, RTW89_DBG_RFK,
+			    "[PAD_BIAS][TRIM] path=%d pad_bias_trim=0x%x\n",
+			    i, info->pad_bias_trim[i]);
+	}
+}
+
+static int rtw8922a_read_phycap(struct rtw89_dev *rtwdev, u8 *phycap_map)
+{
+	rtw8922a_phycap_parsing_thermal_trim(rtwdev, phycap_map);
+	rtw8922a_phycap_parsing_pa_bias_trim(rtwdev, phycap_map);
+	rtw8922a_phycap_parsing_pad_bias_trim(rtwdev, phycap_map);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static const struct wiphy_wowlan_support rtw_wowlan_stub_8922a = {
+	.flags = WIPHY_WOWLAN_MAGIC_PKT | WIPHY_WOWLAN_DISCONNECT,
+	.n_patterns = RTW89_MAX_PATTERN_NUM,
+	.pattern_max_len = RTW89_MAX_PATTERN_SIZE,
+	.pattern_min_len = 1,
+};
+#endif
+
+static const struct rtw89_chip_ops rtw8922a_chip_ops = {
+	.read_efuse		= rtw8922a_read_efuse,
+	.read_phycap		= rtw8922a_read_phycap,
+	.pwr_on_func		= rtw8922a_pwr_on_func,
+	.pwr_off_func		= rtw8922a_pwr_off_func,
+};
+
+const struct rtw89_chip_info rtw8922a_chip_info = {
+	.chip_id		= RTL8922A,
+	.chip_gen		= RTW89_CHIP_BE,
+	.ops			= &rtw8922a_chip_ops,
+	.mac_def		= &rtw89_mac_gen_be,
+	.phy_def		= &rtw89_phy_gen_be,
+	.fw_basename		= RTW8922A_FW_BASENAME,
+	.fw_format_max		= RTW8922A_FW_FORMAT_MAX,
+	.try_ce_fw		= false,
+	.bbmcu_nr		= 1,
+	.needed_fw_elms		= RTW89_BE_GEN_DEF_NEEDED_FW_ELEMENTS,
+	.fifo_size		= 589824,
+	.small_fifo_size	= false,
+	.dle_scc_rsvd_size	= 0,
+	.max_amsdu_limit	= 8000,
+	.dis_2g_40m_ul_ofdma	= false,
+	.rsvd_ple_ofst		= 0x8f800,
+	.hfc_param_ini		= rtw8922a_hfc_param_ini_pcie,
+	.dle_mem		= rtw8922a_dle_mem_pcie,
+	.wde_qempty_acq_grpnum	= 4,
+	.wde_qempty_mgq_grpsel	= 4,
+	.rf_base_addr		= {0xe000, 0xf000},
+	.pwr_on_seq		= NULL,
+	.pwr_off_seq		= NULL,
+	.bb_table		= NULL,
+	.bb_gain_table		= NULL,
+	.rf_table		= {},
+	.nctl_table		= NULL,
+	.nctl_post_table	= NULL,
+	.dflt_parms		= NULL, /* load parm from fw */
+	.rfe_parms_conf		= NULL, /* load parm from fw */
+	.txpwr_factor_rf	= 2,
+	.txpwr_factor_mac	= 1,
+	.dig_table		= NULL,
+	.tssi_dbw_table		= NULL,
+	.support_chanctx_num	= 1,
+	.support_bands		= BIT(NL80211_BAND_2GHZ) |
+				  BIT(NL80211_BAND_5GHZ) |
+				  BIT(NL80211_BAND_6GHZ),
+	.support_unii4		= true,
+	.ul_tb_waveform_ctrl	= false,
+	.ul_tb_pwr_diff		= false,
+	.hw_sec_hdr		= true,
+	.rf_path_num		= 2,
+	.tx_nss			= 2,
+	.rx_nss			= 2,
+	.acam_num		= 128,
+	.bcam_num		= 20,
+	.scam_num		= 32,
+	.bacam_num		= 8,
+	.bacam_dynamic_num	= 8,
+	.bacam_ver		= RTW89_BACAM_V1,
+	.ppdu_max_usr		= 16,
+	.sec_ctrl_efuse_size	= 4,
+	.physical_efuse_size	= 0x1300,
+	.logical_efuse_size	= 0x70000,
+	.limit_efuse_size	= 0x40000,
+	.dav_phy_efuse_size	= 0,
+	.dav_log_efuse_size	= 0,
+	.efuse_blocks		= rtw8922a_efuse_blocks,
+	.phycap_addr		= 0x1700,
+	.phycap_size		= 0x38,
+
+	.ps_mode_supported	= BIT(RTW89_PS_MODE_RFOFF) |
+				  BIT(RTW89_PS_MODE_CLK_GATED) |
+				  BIT(RTW89_PS_MODE_PWR_GATED),
+	.low_power_hci_modes	= 0,
+	.hci_func_en_addr	= R_BE_HCI_FUNC_EN,
+	.h2c_desc_size		= sizeof(struct rtw89_rxdesc_short_v2),
+	.txwd_body_size		= sizeof(struct rtw89_txwd_body_v2),
+	.txwd_info_size		= sizeof(struct rtw89_txwd_info_v2),
+	.cfo_src_fd		= true,
+	.cfo_hw_comp            = true,
+	.dcfo_comp		= NULL,
+	.dcfo_comp_sft		= 0,
+	.imr_info		= NULL,
+	.imr_dmac_table		= &rtw8922a_imr_dmac_table,
+	.imr_cmac_table		= &rtw8922a_imr_cmac_table,
+	.bss_clr_vld		= {R_BSS_CLR_VLD_V2, B_BSS_CLR_VLD0_V2},
+	.bss_clr_map_reg	= R_BSS_CLR_MAP_V2,
+	.dma_ch_mask		= 0,
+#ifdef CONFIG_PM
+	.wowlan_stub		= &rtw_wowlan_stub_8922a,
+#endif
+	.xtal_info		= NULL,
+};
+EXPORT_SYMBOL(rtw8922a_chip_info);
+
+MODULE_FIRMWARE(RTW8922A_MODULE_FIRMWARE);
+MODULE_AUTHOR("Realtek Corporation");
+MODULE_DESCRIPTION("Realtek 802.11be wireless 8922A driver");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.h b/drivers/net/wireless/realtek/rtw89/rtw8922a.h
new file mode 100644
index 000000000000..597317ab6af7
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/* Copyright(c) 2023  Realtek Corporation
+ */
+
+#ifndef __RTW89_8922A_H__
+#define __RTW89_8922A_H__
+
+#include "core.h"
+
+#define RF_PATH_NUM_8922A 2
+#define BB_PATH_NUM_8922A 2
+
+struct rtw8922a_tssi_offset {
+	u8 cck_tssi[TSSI_CCK_CH_GROUP_NUM];
+	u8 bw40_tssi[TSSI_MCS_2G_CH_GROUP_NUM];
+	u8 rsvd[7];
+	u8 bw40_1s_tssi_5g[TSSI_MCS_5G_CH_GROUP_NUM];
+	u8 bw_diff_5g[10];
+} __packed;
+
+struct rtw8922a_rx_gain {
+	u8 _2g_ofdm;
+	u8 _2g_cck;
+	u8 _5g_low;
+	u8 _5g_mid;
+	u8 _5g_high;
+} __packed;
+
+struct rtw8922a_rx_gain_6g {
+	u8 _6g_l0;
+	u8 _6g_l1;
+	u8 _6g_m0;
+	u8 _6g_m1;
+	u8 _6g_h0;
+	u8 _6g_h1;
+	u8 _6g_uh0;
+	u8 _6g_uh1;
+} __packed;
+
+struct rtw8922a_efuse {
+	u8 country_code[2];
+	u8 rsvd[0xe];
+	struct rtw8922a_tssi_offset path_a_tssi;
+	struct rtw8922a_tssi_offset path_b_tssi;
+	u8 rsvd1[0x54];
+	u8 channel_plan;
+	u8 xtal_k;
+	u8 rsvd2[0x7];
+	u8 board_info;
+	u8 rsvd3[0x8];
+	u8 rfe_type;
+	u8 rsvd4[0x5];
+	u8 path_a_therm;
+	u8 path_b_therm;
+	u8 rsvd5[0x2];
+	struct rtw8922a_rx_gain rx_gain_a;
+	struct rtw8922a_rx_gain rx_gain_b;
+	u8 rsvd6[0x22];
+	u8 bw40_1s_tssi_6g_a[TSSI_MCS_6G_CH_GROUP_NUM];
+	u8 rsvd7[0xa];
+	u8 bw40_1s_tssi_6g_b[TSSI_MCS_6G_CH_GROUP_NUM];
+	u8 rsvd8[0xa];
+	u8 bw40_1s_tssi_6g_c[TSSI_MCS_6G_CH_GROUP_NUM];
+	u8 rsvd9[0xa];
+	u8 bw40_1s_tssi_6g_d[TSSI_MCS_6G_CH_GROUP_NUM];
+	u8 rsvd10[0xa];
+	struct rtw8922a_rx_gain_6g rx_gain_6g_a;
+	struct rtw8922a_rx_gain_6g rx_gain_6g_b;
+} __packed;
+
+extern const struct rtw89_chip_info rtw8922a_chip_info;
+
+#endif
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922ae.c b/drivers/net/wireless/realtek/rtw89/rtw8922ae.c
new file mode 100644
index 000000000000..7b3d98d2c402
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922ae.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/* Copyright(c) 2023  Realtek Corporation
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+
+#include "pci.h"
+#include "reg.h"
+#include "rtw8922a.h"
+
+static const struct rtw89_pci_info rtw8922a_pci_info = {
+	.gen_def		= &rtw89_pci_gen_be,
+	.txbd_trunc_mode	= MAC_AX_BD_TRUNC,
+	.rxbd_trunc_mode	= MAC_AX_BD_TRUNC,
+	.rxbd_mode		= MAC_AX_RXBD_PKT,
+	.tag_mode		= MAC_AX_TAG_MULTI,
+	.tx_burst		= MAC_AX_TX_BURST_V1_256B,
+	.rx_burst		= MAC_AX_RX_BURST_V1_128B,
+	.wd_dma_idle_intvl	= MAC_AX_WD_DMA_INTVL_256NS,
+	.wd_dma_act_intvl	= MAC_AX_WD_DMA_INTVL_256NS,
+	.multi_tag_num		= MAC_AX_TAG_NUM_8,
+	.lbc_en			= MAC_AX_PCIE_ENABLE,
+	.lbc_tmr		= MAC_AX_LBC_TMR_2MS,
+	.autok_en		= MAC_AX_PCIE_DISABLE,
+	.io_rcy_en		= MAC_AX_PCIE_ENABLE,
+	.io_rcy_tmr		= MAC_AX_IO_RCY_ANA_TMR_DEF,
+	.rx_ring_eq_is_full	= true,
+
+	.init_cfg_reg		= R_BE_HAXI_INIT_CFG1,
+	.txhci_en_bit		= B_BE_TXDMA_EN,
+	.rxhci_en_bit		= B_BE_RXDMA_EN,
+	.rxbd_mode_bit		= B_BE_RXQ_RXBD_MODE_MASK,
+	.exp_ctrl_reg		= R_BE_HAXI_EXP_CTRL_V1,
+	.max_tag_num_mask	= B_BE_MAX_TAG_NUM_MASK,
+	.rxbd_rwptr_clr_reg	= R_BE_RXBD_RWPTR_CLR1_V1,
+	.txbd_rwptr_clr2_reg	= R_BE_TXBD_RWPTR_CLR1,
+	.dma_io_stop		= {R_BE_HAXI_INIT_CFG1, B_BE_STOP_AXI_MST},
+	.dma_stop1		= {R_BE_HAXI_DMA_STOP1, B_BE_TX_STOP1_MASK},
+	.dma_stop2		= {0},
+	.dma_busy1		= {R_BE_HAXI_DMA_BUSY1, DMA_BUSY1_CHECK_BE},
+	.dma_busy2_reg		= 0,
+	.dma_busy3_reg		= R_BE_HAXI_DMA_BUSY1,
+
+	.rpwm_addr		= R_BE_PCIE_HRPWM,
+	.cpwm_addr		= R_BE_PCIE_CRPWM,
+	.mit_addr		= R_BE_PCIE_MIT_CH_EN,
+	.tx_dma_ch_mask		= 0,
+	.bd_idx_addr_low_power	= NULL,
+	.dma_addr_set		= &rtw89_pci_ch_dma_addr_set_be,
+	.bd_ram_table		= NULL,
+
+	.ltr_set		= rtw89_pci_ltr_set_v2,
+	.fill_txaddr_info	= rtw89_pci_fill_txaddr_info_v1,
+	.config_intr_mask	= rtw89_pci_config_intr_mask_v2,
+	.enable_intr		= rtw89_pci_enable_intr_v2,
+	.disable_intr		= rtw89_pci_disable_intr_v2,
+	.recognize_intrs	= rtw89_pci_recognize_intrs_v2,
+};
+
+static const struct rtw89_driver_info rtw89_8922ae_info = {
+	.chip = &rtw8922a_chip_info,
+	.bus = {
+		.pci = &rtw8922a_pci_info,
+	},
+};
+
+static const struct pci_device_id rtw89_8922ae_id_table[] = {
+	{
+		PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8922),
+		.driver_data = (kernel_ulong_t)&rtw89_8922ae_info,
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(pci, rtw89_8922ae_id_table);
+
+static struct pci_driver rtw89_8922ae_driver = {
+	.name		= "rtw89_8922ae",
+	.id_table	= rtw89_8922ae_id_table,
+	.probe		= rtw89_pci_probe,
+	.remove		= rtw89_pci_remove,
+	.driver.pm	= &rtw89_pm_ops,
+};
+module_pci_driver(rtw89_8922ae_driver);
+
+MODULE_AUTHOR("Realtek Corporation");
+MODULE_DESCRIPTION("Realtek 802.11be wireless 8922AE driver");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/realtek/rtw89/sar.c b/drivers/net/wireless/realtek/rtw89/sar.c
index aed05b026c6c..1b2a400406ae 100644
--- a/drivers/net/wireless/realtek/rtw89/sar.c
+++ b/drivers/net/wireless/realtek/rtw89/sar.c
@@ -404,16 +404,18 @@ out:
 void rtw89_tas_init(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_tas_info *tas = &rtwdev->tas;
+	struct rtw89_acpi_dsm_result res = {};
 	int ret;
 	u8 val;
 
-	ret = rtw89_acpi_evaluate_dsm(rtwdev, RTW89_ACPI_DSM_FUNC_TAS_EN, &val);
+	ret = rtw89_acpi_evaluate_dsm(rtwdev, RTW89_ACPI_DSM_FUNC_TAS_EN, &res);
 	if (ret) {
 		rtw89_debug(rtwdev, RTW89_DBG_SAR,
 			    "acpi: cannot get TAS: %d\n", ret);
 		return;
 	}
 
+	val = res.u.value;
 	switch (val) {
 	case 0:
 		tas->enable = false;
diff --git a/drivers/net/wireless/realtek/rtw89/ser.c b/drivers/net/wireless/realtek/rtw89/ser.c
index c1644353053f..99896d85d2f8 100644
--- a/drivers/net/wireless/realtek/rtw89/ser.c
+++ b/drivers/net/wireless/realtek/rtw89/ser.c
@@ -361,6 +361,9 @@ static int hal_enable_dma(struct rtw89_ser *ser)
 	ret = rtwdev->hci.ops->mac_lv1_rcvy(rtwdev, RTW89_LV1_RCVY_STEP_2);
 	if (!ret)
 		clear_bit(RTW89_SER_HAL_STOP_DMA, ser->flags);
+	else
+		rtw89_debug(rtwdev, RTW89_DBG_SER,
+			    "lv1 rcvy fail to start dma: %d\n", ret);
 
 	return ret;
 }
@@ -376,6 +379,9 @@ static int hal_stop_dma(struct rtw89_ser *ser)
 	ret = rtwdev->hci.ops->mac_lv1_rcvy(rtwdev, RTW89_LV1_RCVY_STEP_1);
 	if (!ret)
 		set_bit(RTW89_SER_HAL_STOP_DMA, ser->flags);
+	else
+		rtw89_debug(rtwdev, RTW89_DBG_SER,
+			    "lv1 rcvy fail to stop dma: %d\n", ret);
 
 	return ret;
 }
@@ -584,6 +590,14 @@ struct __fw_backtrace_info {
 static_assert(RTW89_FW_BACKTRACE_INFO_SIZE ==
 	      sizeof(struct __fw_backtrace_info));
 
+static u32 convert_addr_from_wcpu(u32 wcpu_addr)
+{
+	if (wcpu_addr < 0x30000000)
+		return wcpu_addr;
+
+	return wcpu_addr & GENMASK(28, 0);
+}
+
 static int rtw89_ser_fw_backtrace_dump(struct rtw89_dev *rtwdev, u8 *buf,
 				       const struct __fw_backtrace_entry *ent)
 {
@@ -591,7 +605,7 @@ static int rtw89_ser_fw_backtrace_dump(struct rtw89_dev *rtwdev, u8 *buf,
 	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	u32 filter_model_addr = mac->filter_model_addr;
 	u32 indir_access_addr = mac->indir_access_addr;
-	u32 fwbt_addr = ent->wcpu_addr & RTW89_WCPU_BASE_MASK;
+	u32 fwbt_addr = convert_addr_from_wcpu(ent->wcpu_addr);
 	u32 fwbt_size = ent->size;
 	u32 fwbt_key = ent->key;
 	u32 i;
diff --git a/drivers/net/wireless/realtek/rtw89/txrx.h b/drivers/net/wireless/realtek/rtw89/txrx.h
index 7142cce167de..c467a80ffa88 100644
--- a/drivers/net/wireless/realtek/rtw89/txrx.h
+++ b/drivers/net/wireless/realtek/rtw89/txrx.h
@@ -416,8 +416,11 @@ struct rtw89_rxinfo {
 } __packed;
 
 #define RTW89_RXINFO_W0_USR_NUM GENMASK(3, 0)
+#define RTW89_RXINFO_W0_USR_NUM_V1 GENMASK(4, 0)
 #define RTW89_RXINFO_W0_FW_DEFINE GENMASK(15, 8)
+#define RTW89_RXINFO_W0_PLCP_LEN_V1 GENMASK(23, 16)
 #define RTW89_RXINFO_W0_LSIG_LEN GENMASK(27, 16)
+#define RTW89_RXINFO_W0_INVALID_V1 BIT(27)
 #define RTW89_RXINFO_W0_IS_TO_SELF BIT(28)
 #define RTW89_RXINFO_W0_RX_CNT_VLD BIT(29)
 #define RTW89_RXINFO_W0_LONG_RXD GENMASK(31, 30)
@@ -430,6 +433,7 @@ struct rtw89_phy_sts_hdr {
 } __packed;
 
 #define RTW89_PHY_STS_HDR_W0_IE_MAP GENMASK(4, 0)
+#define RTW89_PHY_STS_HDR_W0_VALID BIT(7)
 #define RTW89_PHY_STS_HDR_W0_LEN GENMASK(15, 8)
 #define RTW89_PHY_STS_HDR_W0_RSSI_AVG GENMASK(31, 24)
 #define RTW89_PHY_STS_HDR_W1_RSSI_A GENMASK(7, 0)
diff --git a/drivers/net/wireless/realtek/rtw89/wow.c b/drivers/net/wireless/realtek/rtw89/wow.c
index 660bf2ece927..5c7ca36c09b6 100644
--- a/drivers/net/wireless/realtek/rtw89/wow.c
+++ b/drivers/net/wireless/realtek/rtw89/wow.c
@@ -73,13 +73,14 @@ static int rtw89_wow_config_mac(struct rtw89_dev *rtwdev, bool enable_wow)
 
 static void rtw89_wow_set_rx_filter(struct rtw89_dev *rtwdev, bool enable)
 {
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	enum rtw89_mac_fwd_target fwd_target = enable ?
 					       RTW89_FWD_DONT_CARE :
 					       RTW89_FWD_TO_HOST;
 
-	rtw89_mac_typ_fltr_opt(rtwdev, RTW89_MGNT, fwd_target, RTW89_MAC_0);
-	rtw89_mac_typ_fltr_opt(rtwdev, RTW89_CTRL, fwd_target, RTW89_MAC_0);
-	rtw89_mac_typ_fltr_opt(rtwdev, RTW89_DATA, fwd_target, RTW89_MAC_0);
+	mac->typ_fltr_opt(rtwdev, RTW89_MGNT, fwd_target, RTW89_MAC_0);
+	mac->typ_fltr_opt(rtwdev, RTW89_CTRL, fwd_target, RTW89_MAC_0);
+	mac->typ_fltr_opt(rtwdev, RTW89_DATA, fwd_target, RTW89_MAC_0);
 }
 
 static void rtw89_wow_show_wakeup_reason(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/silabs/wfx/sta.c b/drivers/net/wireless/silabs/wfx/sta.c
index 1b6c158457b4..537caf9d914a 100644
--- a/drivers/net/wireless/silabs/wfx/sta.c
+++ b/drivers/net/wireless/silabs/wfx/sta.c
@@ -336,29 +336,38 @@ static int wfx_upload_ap_templates(struct wfx_vif *wvif)
 	return 0;
 }
 
-static void wfx_set_mfp_ap(struct wfx_vif *wvif)
+static int wfx_set_mfp_ap(struct wfx_vif *wvif)
 {
 	struct ieee80211_vif *vif = wvif_to_vif(wvif);
 	struct sk_buff *skb = ieee80211_beacon_get(wvif->wdev->hw, vif, 0);
 	const int ieoffset = offsetof(struct ieee80211_mgmt, u.beacon.variable);
-	const u16 *ptr = (u16 *)cfg80211_find_ie(WLAN_EID_RSN, skb->data + ieoffset,
-						 skb->len - ieoffset);
 	const int pairwise_cipher_suite_count_offset = 8 / sizeof(u16);
 	const int pairwise_cipher_suite_size = 4 / sizeof(u16);
 	const int akm_suite_size = 4 / sizeof(u16);
+	const u16 *ptr;
 
-	if (ptr) {
-		ptr += pairwise_cipher_suite_count_offset;
-		if (WARN_ON(ptr > (u16 *)skb_tail_pointer(skb)))
-			return;
-		ptr += 1 + pairwise_cipher_suite_size * *ptr;
-		if (WARN_ON(ptr > (u16 *)skb_tail_pointer(skb)))
-			return;
-		ptr += 1 + akm_suite_size * *ptr;
-		if (WARN_ON(ptr > (u16 *)skb_tail_pointer(skb)))
-			return;
-		wfx_hif_set_mfp(wvif, *ptr & BIT(7), *ptr & BIT(6));
-	}
+	if (unlikely(!skb))
+		return -ENOMEM;
+
+	ptr = (u16 *)cfg80211_find_ie(WLAN_EID_RSN, skb->data + ieoffset,
+				      skb->len - ieoffset);
+	if (unlikely(!ptr))
+		return -EINVAL;
+
+	ptr += pairwise_cipher_suite_count_offset;
+	if (WARN_ON(ptr > (u16 *)skb_tail_pointer(skb)))
+		return -EINVAL;
+
+	ptr += 1 + pairwise_cipher_suite_size * *ptr;
+	if (WARN_ON(ptr > (u16 *)skb_tail_pointer(skb)))
+		return -EINVAL;
+
+	ptr += 1 + akm_suite_size * *ptr;
+	if (WARN_ON(ptr > (u16 *)skb_tail_pointer(skb)))
+		return -EINVAL;
+
+	wfx_hif_set_mfp(wvif, *ptr & BIT(7), *ptr & BIT(6));
+	return 0;
 }
 
 int wfx_start_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
@@ -376,8 +385,7 @@ int wfx_start_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	ret = wfx_hif_start(wvif, &vif->bss_conf, wvif->channel);
 	if (ret > 0)
 		return -EIO;
-	wfx_set_mfp_ap(wvif);
-	return ret;
+	return wfx_set_mfp_ap(wvif);
 }
 
 void wfx_stop_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c
index c7b4414cc6c3..a84340c2075f 100644
--- a/drivers/net/wireless/virtual/mac80211_hwsim.c
+++ b/drivers/net/wireless/virtual/mac80211_hwsim.c
@@ -190,10 +190,25 @@ static const struct ieee80211_regdomain hwsim_world_regdom_custom_03 = {
 	}
 };
 
+static const struct ieee80211_regdomain hwsim_world_regdom_custom_04 = {
+	.n_reg_rules = 6,
+	.alpha2 =  "99",
+	.reg_rules = {
+		REG_RULE(2412 - 10, 2462 + 10, 40, 0, 20, 0),
+		REG_RULE(2484 - 10, 2484 + 10, 40, 0, 20, 0),
+		REG_RULE(5150 - 10, 5240 + 10, 80, 0, 30, 0),
+		REG_RULE(5260 - 10, 5320 + 10, 80, 0, 30,
+			 NL80211_RRF_DFS_CONCURRENT | NL80211_RRF_DFS),
+		REG_RULE(5745 - 10, 5825 + 10, 80, 0, 30, 0),
+		REG_RULE(5855 - 10, 5925 + 10, 80, 0, 33, 0),
+	}
+};
+
 static const struct ieee80211_regdomain *hwsim_world_regdom_custom[] = {
 	&hwsim_world_regdom_custom_01,
 	&hwsim_world_regdom_custom_02,
 	&hwsim_world_regdom_custom_03,
+	&hwsim_world_regdom_custom_04,
 };
 
 struct hwsim_vif_priv {
@@ -4029,6 +4044,8 @@ static const struct ieee80211_sband_iftype_data sband_capa_2ghz[] = {
 					IEEE80211_HE_MAC_CAP3_OMI_CONTROL |
 					IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3,
 				.mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU,
+				.phy_cap_info[0] =
+					IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G,
 				.phy_cap_info[1] =
 					IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK |
 					IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A |
@@ -4134,6 +4151,8 @@ static const struct ieee80211_sband_iftype_data sband_capa_2ghz[] = {
 					IEEE80211_HE_MAC_CAP3_OMI_CONTROL |
 					IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3,
 				.mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU,
+				.phy_cap_info[0] =
+					IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G,
 				.phy_cap_info[1] =
 					IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK |
 					IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A |
@@ -4237,6 +4256,8 @@ static const struct ieee80211_sband_iftype_data sband_capa_2ghz[] = {
 					IEEE80211_HE_MAC_CAP3_OMI_CONTROL |
 					IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3,
 				.mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU,
+				.phy_cap_info[0] =
+					IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G,
 				.phy_cap_info[1] =
 					IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK |
 					IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A |
@@ -5288,6 +5309,10 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 		schedule_timeout_interruptible(1);
 	}
 
+	/* TODO: Add param */
+	wiphy_ext_feature_set(hw->wiphy,
+			      NL80211_EXT_FEATURE_DFS_CONCURRENT);
+
 	if (param->no_vif)
 		ieee80211_hw_set(hw, NO_AUTO_VIF);
 
diff --git a/drivers/net/wireless/zydas/Kconfig b/drivers/net/wireless/zydas/Kconfig
index 08574433df66..839e1217e855 100644
--- a/drivers/net/wireless/zydas/Kconfig
+++ b/drivers/net/wireless/zydas/Kconfig
@@ -12,25 +12,6 @@ config WLAN_VENDOR_ZYDAS
 
 if WLAN_VENDOR_ZYDAS
 
-config USB_ZD1201
-	tristate "USB ZD1201 based Wireless device support"
-	depends on CFG80211 && USB
-	select WIRELESS_EXT
-	select WEXT_PRIV
-	select FW_LOADER
-	help
-	  Say Y if you want to use wireless LAN adapters based on the ZyDAS
-	  ZD1201 chip.
-
-	  This driver makes the adapter appear as a normal Ethernet interface,
-	  typically on wlan0.
-
-	  The zd1201 device requires external firmware to be loaded.
-	  This can be found at http://linux-lc100020.sourceforge.net/
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called zd1201.
-
 source "drivers/net/wireless/zydas/zd1211rw/Kconfig"
 
 endif # WLAN_VENDOR_ZYDAS
diff --git a/drivers/net/wireless/zydas/Makefile b/drivers/net/wireless/zydas/Makefile
index c70003d30a8f..3e0a51db9874 100644
--- a/drivers/net/wireless/zydas/Makefile
+++ b/drivers/net/wireless/zydas/Makefile
@@ -1,4 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_ZD1211RW)		+= zd1211rw/
-
-obj-$(CONFIG_USB_ZD1201)	+= zd1201.o
diff --git a/drivers/net/wireless/zydas/zd1201.c b/drivers/net/wireless/zydas/zd1201.c
deleted file mode 100644
index 2814df1ecc78..000000000000
--- a/drivers/net/wireless/zydas/zd1201.c
+++ /dev/null
@@ -1,1909 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *	Driver for ZyDAS zd1201 based USB wireless devices.
- *
- *	Copyright (c) 2004, 2005 Jeroen Vreeken (pe1rxq@amsat.org)
- *
- *	Parts of this driver have been derived from a wlan-ng version
- *	modified by ZyDAS. They also made documentation available, thanks!
- *	Copyright (C) 1999 AbsoluteValue Systems, Inc.  All Rights Reserved.
- */
-
-#include <linux/module.h>
-#include <linux/usb.h>
-#include <linux/slab.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/wireless.h>
-#include <net/cfg80211.h>
-#include <net/iw_handler.h>
-#include <linux/string.h>
-#include <linux/if_arp.h>
-#include <linux/firmware.h>
-#include "zd1201.h"
-
-static const struct usb_device_id zd1201_table[] = {
-	{USB_DEVICE(0x0586, 0x3400)}, /* Peabird USB Wireless Adapter */
-	{USB_DEVICE(0x0ace, 0x1201)}, /* ZyDAS ZD1201 USB Wireless Adapter */
-	{USB_DEVICE(0x050d, 0x6051)}, /* Belkin F5D6051 usb  adapter */
-	{USB_DEVICE(0x0db0, 0x6823)}, /* MSI UB11B usb  adapter */
-	{USB_DEVICE(0x1044, 0x8004)}, /* Gigabyte GN-WLBZ101 */
-	{USB_DEVICE(0x1044, 0x8005)}, /* GIGABYTE GN-WLBZ201 usb adapter */
-	{}
-};
-
-static int ap;	/* Are we an AP or a normal station? */
-
-#define ZD1201_VERSION	"0.15"
-
-MODULE_AUTHOR("Jeroen Vreeken <pe1rxq@amsat.org>");
-MODULE_DESCRIPTION("Driver for ZyDAS ZD1201 based USB Wireless adapters");
-MODULE_VERSION(ZD1201_VERSION);
-MODULE_LICENSE("GPL");
-module_param(ap, int, 0);
-MODULE_PARM_DESC(ap, "If non-zero Access Point firmware will be loaded");
-MODULE_DEVICE_TABLE(usb, zd1201_table);
-
-
-static int zd1201_fw_upload(struct usb_device *dev, int apfw)
-{
-	const struct firmware *fw_entry;
-	const char *data;
-	unsigned long len;
-	int err;
-	unsigned char ret;
-	char *buf;
-	char *fwfile;
-
-	if (apfw)
-		fwfile = "zd1201-ap.fw";
-	else
-		fwfile = "zd1201.fw";
-
-	err = request_firmware(&fw_entry, fwfile, &dev->dev);
-	if (err) {
-		dev_err(&dev->dev, "Failed to load %s firmware file!\n", fwfile);
-		dev_err(&dev->dev, "Make sure the hotplug firmware loader is installed.\n");
-		dev_err(&dev->dev, "Goto http://linux-lc100020.sourceforge.net for more info.\n");
-		return err;
-	}
-
-	data = fw_entry->data;
-        len = fw_entry->size;
-
-	buf = kmalloc(1024, GFP_ATOMIC);
-	if (!buf) {
-		err = -ENOMEM;
-		goto exit;
-	}
-	
-	while (len > 0) {
-		int translen = (len > 1024) ? 1024 : len;
-		memcpy(buf, data, translen);
-
-		err = usb_control_msg(dev, usb_sndctrlpipe(dev, 0), 0,
-		    USB_DIR_OUT | 0x40, 0, 0, buf, translen,
-		    ZD1201_FW_TIMEOUT);
-		if (err < 0)
-			goto exit;
-
-		len -= translen;
-		data += translen;
-	}
-                                        
-	err = usb_control_msg(dev, usb_sndctrlpipe(dev, 0), 0x2,
-	    USB_DIR_OUT | 0x40, 0, 0, NULL, 0, ZD1201_FW_TIMEOUT);
-	if (err < 0)
-		goto exit;
-
-	err = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), 0x4,
-	    USB_DIR_IN | 0x40, 0, 0, buf, sizeof(ret), ZD1201_FW_TIMEOUT);
-	if (err < 0)
-		goto exit;
-
-	memcpy(&ret, buf, sizeof(ret));
-
-	if (ret & 0x80) {
-		err = -EIO;
-		goto exit;
-	}
-
-	err = 0;
-exit:
-	kfree(buf);
-	release_firmware(fw_entry);
-	return err;
-}
-
-MODULE_FIRMWARE("zd1201-ap.fw");
-MODULE_FIRMWARE("zd1201.fw");
-
-static void zd1201_usbfree(struct urb *urb)
-{
-	struct zd1201 *zd = urb->context;
-
-	switch(urb->status) {
-		case -EILSEQ:
-		case -ENODEV:
-		case -ETIME:
-		case -ENOENT:
-		case -EPIPE:
-		case -EOVERFLOW:
-		case -ESHUTDOWN:
-			dev_warn(&zd->usb->dev, "%s: urb failed: %d\n", 
-			    zd->dev->name, urb->status);
-	}
-
-	kfree(urb->transfer_buffer);
-	usb_free_urb(urb);
-}
-
-/* cmdreq message: 
-	u32 type
-	u16 cmd
-	u16 parm0
-	u16 parm1
-	u16 parm2
-	u8  pad[4]
-
-	total: 4 + 2 + 2 + 2 + 2 + 4 = 16
-*/
-static int zd1201_docmd(struct zd1201 *zd, int cmd, int parm0,
-			int parm1, int parm2)
-{
-	unsigned char *command;
-	int ret;
-	struct urb *urb;
-
-	command = kmalloc(16, GFP_ATOMIC);
-	if (!command)
-		return -ENOMEM;
-
-	*((__le32*)command) = cpu_to_le32(ZD1201_USB_CMDREQ);
-	*((__le16*)&command[4]) = cpu_to_le16(cmd);
-	*((__le16*)&command[6]) = cpu_to_le16(parm0);
-	*((__le16*)&command[8]) = cpu_to_le16(parm1);
-	*((__le16*)&command[10])= cpu_to_le16(parm2);
-
-	urb = usb_alloc_urb(0, GFP_ATOMIC);
-	if (!urb) {
-		kfree(command);
-		return -ENOMEM;
-	}
-	usb_fill_bulk_urb(urb, zd->usb, usb_sndbulkpipe(zd->usb, zd->endp_out2),
-			  command, 16, zd1201_usbfree, zd);
-	ret = usb_submit_urb(urb, GFP_ATOMIC);
-	if (ret) {
-		kfree(command);
-		usb_free_urb(urb);
-	}
-
-	return ret;
-}
-
-/* Callback after sending out a packet */
-static void zd1201_usbtx(struct urb *urb)
-{
-	struct zd1201 *zd = urb->context;
-	netif_wake_queue(zd->dev);
-}
-
-/* Incoming data */
-static void zd1201_usbrx(struct urb *urb)
-{
-	struct zd1201 *zd = urb->context;
-	int free = 0;
-	unsigned char *data = urb->transfer_buffer;
-	struct sk_buff *skb;
-	unsigned char type;
-
-	if (!zd)
-		return;
-
-	switch(urb->status) {
-		case -EILSEQ:
-		case -ENODEV:
-		case -ETIME:
-		case -ENOENT:
-		case -EPIPE:
-		case -EOVERFLOW:
-		case -ESHUTDOWN:
-			dev_warn(&zd->usb->dev, "%s: rx urb failed: %d\n",
-			    zd->dev->name, urb->status);
-			free = 1;
-			goto exit;
-	}
-	
-	if (urb->status != 0 || urb->actual_length == 0)
-		goto resubmit;
-
-	type = data[0];
-	if (type == ZD1201_PACKET_EVENTSTAT || type == ZD1201_PACKET_RESOURCE) {
-		memcpy(zd->rxdata, data, urb->actual_length);
-		zd->rxlen = urb->actual_length;
-		zd->rxdatas = 1;
-		wake_up(&zd->rxdataq);
-	}
-	/* Info frame */
-	if (type == ZD1201_PACKET_INQUIRE) {
-		int i = 0;
-		unsigned short infotype, copylen;
-		infotype = le16_to_cpu(*(__le16*)&data[6]);
-
-		if (infotype == ZD1201_INF_LINKSTATUS) {
-			short linkstatus;
-
-			linkstatus = le16_to_cpu(*(__le16*)&data[8]);
-			switch(linkstatus) {
-				case 1:
-					netif_carrier_on(zd->dev);
-					break;
-				case 2:
-					netif_carrier_off(zd->dev);
-					break;
-				case 3:
-					netif_carrier_off(zd->dev);
-					break;
-				case 4:
-					netif_carrier_on(zd->dev);
-					break;
-				default:
-					netif_carrier_off(zd->dev);
-			}
-			goto resubmit;
-		}
-		if (infotype == ZD1201_INF_ASSOCSTATUS) {
-			short status = le16_to_cpu(*(__le16*)(data+8));
-			int event;
-			union iwreq_data wrqu;
-
-			switch (status) {
-				case ZD1201_ASSOCSTATUS_STAASSOC:
-				case ZD1201_ASSOCSTATUS_REASSOC:
-					event = IWEVREGISTERED;
-					break;
-				case ZD1201_ASSOCSTATUS_DISASSOC:
-				case ZD1201_ASSOCSTATUS_ASSOCFAIL:
-				case ZD1201_ASSOCSTATUS_AUTHFAIL:
-				default:
-					event = IWEVEXPIRED;
-			}
-			memcpy(wrqu.addr.sa_data, data+10, ETH_ALEN);
-			wrqu.addr.sa_family = ARPHRD_ETHER;
-
-			/* Send event to user space */
-			wireless_send_event(zd->dev, event, &wrqu, NULL);
-
-			goto resubmit;
-		}
-		if (infotype == ZD1201_INF_AUTHREQ) {
-			union iwreq_data wrqu;
-
-			memcpy(wrqu.addr.sa_data, data+8, ETH_ALEN);
-			wrqu.addr.sa_family = ARPHRD_ETHER;
-			/* There isn't a event that trully fits this request.
-			   We assume that userspace will be smart enough to
-			   see a new station being expired and sends back a
-			   authstation ioctl to authorize it. */
-			wireless_send_event(zd->dev, IWEVEXPIRED, &wrqu, NULL);
-			goto resubmit;
-		}
-		/* Other infotypes are handled outside this handler */
-		zd->rxlen = 0;
-		while (i < urb->actual_length) {
-			copylen = le16_to_cpu(*(__le16*)&data[i+2]);
-			/* Sanity check, sometimes we get junk */
-			if (copylen+zd->rxlen > sizeof(zd->rxdata))
-				break;
-			memcpy(zd->rxdata+zd->rxlen, data+i+4, copylen);
-			zd->rxlen += copylen;
-			i += 64;
-		}
-		if (i >= urb->actual_length) {
-			zd->rxdatas = 1;
-			wake_up(&zd->rxdataq);
-		}
-		goto  resubmit;
-	}
-	/* Actual data */
-	if (data[urb->actual_length-1] == ZD1201_PACKET_RXDATA) {
-		int datalen = urb->actual_length-1;
-		unsigned short len, fc, seq;
-
-		len = ntohs(*(__be16 *)&data[datalen-2]);
-		if (len>datalen)
-			len=datalen;
-		fc = le16_to_cpu(*(__le16 *)&data[datalen-16]);
-		seq = le16_to_cpu(*(__le16 *)&data[datalen-24]);
-
-		if (zd->monitor) {
-			if (datalen < 24)
-				goto resubmit;
-			if (!(skb = dev_alloc_skb(datalen+24)))
-				goto resubmit;
-			
-			skb_put_data(skb, &data[datalen - 16], 2);
-			skb_put_data(skb, &data[datalen - 2], 2);
-			skb_put_data(skb, &data[datalen - 14], 6);
-			skb_put_data(skb, &data[datalen - 22], 6);
-			skb_put_data(skb, &data[datalen - 8], 6);
-			skb_put_data(skb, &data[datalen - 24], 2);
-			skb_put_data(skb, data, len);
-			skb->protocol = eth_type_trans(skb, zd->dev);
-			zd->dev->stats.rx_packets++;
-			zd->dev->stats.rx_bytes += skb->len;
-			netif_rx(skb);
-			goto resubmit;
-		}
-			
-		if ((seq & IEEE80211_SCTL_FRAG) ||
-		    (fc & IEEE80211_FCTL_MOREFRAGS)) {
-			struct zd1201_frag *frag = NULL;
-			char *ptr;
-
-			if (datalen<14)
-				goto resubmit;
-			if ((seq & IEEE80211_SCTL_FRAG) == 0) {
-				frag = kmalloc(sizeof(*frag), GFP_ATOMIC);
-				if (!frag)
-					goto resubmit;
-				skb = dev_alloc_skb(IEEE80211_MAX_DATA_LEN +14+2);
-				if (!skb) {
-					kfree(frag);
-					goto resubmit;
-				}
-				frag->skb = skb;
-				frag->seq = seq & IEEE80211_SCTL_SEQ;
-				skb_reserve(skb, 2);
-				skb_put_data(skb, &data[datalen - 14], 12);
-				skb_put_data(skb, &data[6], 2);
-				skb_put_data(skb, data + 8, len);
-				hlist_add_head(&frag->fnode, &zd->fraglist);
-				goto resubmit;
-			}
-			hlist_for_each_entry(frag, &zd->fraglist, fnode)
-				if (frag->seq == (seq&IEEE80211_SCTL_SEQ))
-					break;
-			if (!frag)
-				goto resubmit;
-			skb = frag->skb;
-			ptr = skb_put(skb, len);
-			if (ptr)
-				memcpy(ptr, data+8, len);
-			if (fc & IEEE80211_FCTL_MOREFRAGS)
-				goto resubmit;
-			hlist_del_init(&frag->fnode);
-			kfree(frag);
-		} else {
-			if (datalen<14)
-				goto resubmit;
-			skb = dev_alloc_skb(len + 14 + 2);
-			if (!skb)
-				goto resubmit;
-			skb_reserve(skb, 2);
-			skb_put_data(skb, &data[datalen - 14], 12);
-			skb_put_data(skb, &data[6], 2);
-			skb_put_data(skb, data + 8, len);
-		}
-		skb->protocol = eth_type_trans(skb, zd->dev);
-		zd->dev->stats.rx_packets++;
-		zd->dev->stats.rx_bytes += skb->len;
-		netif_rx(skb);
-	}
-resubmit:
-	memset(data, 0, ZD1201_RXSIZE);
-
-	urb->status = 0;
-	urb->dev = zd->usb;
-	if(usb_submit_urb(urb, GFP_ATOMIC))
-		free = 1;
-
-exit:
-	if (free) {
-		zd->rxlen = 0;
-		zd->rxdatas = 1;
-		wake_up(&zd->rxdataq);
-		kfree(urb->transfer_buffer);
-	}
-}
-
-static int zd1201_getconfig(struct zd1201 *zd, int rid, void *riddata,
-	unsigned int riddatalen)
-{
-	int err;
-	int i = 0;
-	int code;
-	int rid_fid;
-	int length;
-	unsigned char *pdata;
-
-	zd->rxdatas = 0;
-	err = zd1201_docmd(zd, ZD1201_CMDCODE_ACCESS, rid, 0, 0);
-	if (err)
-		return err;
-
-	wait_event_interruptible(zd->rxdataq, zd->rxdatas);
-	if (!zd->rxlen)
-		return -EIO;
-
-	code = le16_to_cpu(*(__le16*)(&zd->rxdata[4]));
-	rid_fid = le16_to_cpu(*(__le16*)(&zd->rxdata[6]));
-	length = le16_to_cpu(*(__le16*)(&zd->rxdata[8]));
-	if (length > zd->rxlen)
-		length = zd->rxlen-6;
-
-	/* If access bit is not on, then error */
-	if ((code & ZD1201_ACCESSBIT) != ZD1201_ACCESSBIT || rid_fid != rid )
-		return -EINVAL;
-
-	/* Not enough buffer for allocating data */
-	if (riddatalen != (length - 4)) {
-		dev_dbg(&zd->usb->dev, "riddatalen mismatches, expected=%u, (packet=%u) length=%u, rid=0x%04X, rid_fid=0x%04X\n",
-		    riddatalen, zd->rxlen, length, rid, rid_fid);
-		return -ENODATA;
-	}
-
-	zd->rxdatas = 0;
-	/* Issue SetRxRid commnd */			
-	err = zd1201_docmd(zd, ZD1201_CMDCODE_SETRXRID, rid, 0, length);
-	if (err)
-		return err;
-
-	/* Receive RID record from resource packets */
-	wait_event_interruptible(zd->rxdataq, zd->rxdatas);
-	if (!zd->rxlen)
-		return -EIO;
-
-	if (zd->rxdata[zd->rxlen - 1] != ZD1201_PACKET_RESOURCE) {
-		dev_dbg(&zd->usb->dev, "Packet type mismatch: 0x%x not 0x3\n",
-		    zd->rxdata[zd->rxlen-1]);
-		return -EINVAL;
-	}
-
-	/* Set the data pointer and received data length */
-	pdata = zd->rxdata;
-	length = zd->rxlen;
-
-	do {
-		int actual_length;
-
-		actual_length = (length > 64) ? 64 : length;
-
-		if (pdata[0] != 0x3) {
-			dev_dbg(&zd->usb->dev, "Rx Resource packet type error: %02X\n",
-			    pdata[0]);
-			return -EINVAL;
-		}
-
-		if (actual_length != 64) {
-			/* Trim the last packet type byte */
-			actual_length--;
-		}
-
-		/* Skip the 4 bytes header (RID length and RID) */
-		if (i == 0) {
-			pdata += 8;
-			actual_length -= 8;
-		} else {
-			pdata += 4;
-			actual_length -= 4;
-		}
-		
-		memcpy(riddata, pdata, actual_length);
-		riddata += actual_length;
-		pdata += actual_length;
-		length -= 64;
-		i++;
-	} while (length > 0);
-
-	return 0;
-}
-
-/*
- *	resreq:
- *		byte	type
- *		byte	sequence
- *		u16	reserved
- *		byte	data[12]
- *	total: 16
- */
-static int zd1201_setconfig(struct zd1201 *zd, int rid, const void *buf, int len, int wait)
-{
-	int err;
-	unsigned char *request;
-	int reqlen;
-	char seq=0;
-	struct urb *urb;
-	gfp_t gfp_mask = wait ? GFP_NOIO : GFP_ATOMIC;
-
-	len += 4;			/* first 4 are for header */
-
-	zd->rxdatas = 0;
-	zd->rxlen = 0;
-	for (seq=0; len > 0; seq++) {
-		request = kzalloc(16, gfp_mask);
-		if (!request)
-			return -ENOMEM;
-		urb = usb_alloc_urb(0, gfp_mask);
-		if (!urb) {
-			kfree(request);
-			return -ENOMEM;
-		}
-		reqlen = len>12 ? 12 : len;
-		request[0] = ZD1201_USB_RESREQ;
-		request[1] = seq;
-		request[2] = 0;
-		request[3] = 0;
-		if (request[1] == 0) {
-			/* add header */
-			*(__le16*)&request[4] = cpu_to_le16((len-2+1)/2);
-			*(__le16*)&request[6] = cpu_to_le16(rid);
-			memcpy(request+8, buf, reqlen-4);
-			buf += reqlen-4;
-		} else {
-			memcpy(request+4, buf, reqlen);
-			buf += reqlen;
-		}
-
-		len -= reqlen;
-
-		usb_fill_bulk_urb(urb, zd->usb, usb_sndbulkpipe(zd->usb,
-		    zd->endp_out2), request, 16, zd1201_usbfree, zd);
-		err = usb_submit_urb(urb, gfp_mask);
-		if (err)
-			goto err;
-	}
-
-	request = kmalloc(16, gfp_mask);
-	if (!request)
-		return -ENOMEM;
-	urb = usb_alloc_urb(0, gfp_mask);
-	if (!urb) {
-		kfree(request);
-		return -ENOMEM;
-	}
-	*((__le32*)request) = cpu_to_le32(ZD1201_USB_CMDREQ);
-	*((__le16*)&request[4]) = 
-	    cpu_to_le16(ZD1201_CMDCODE_ACCESS|ZD1201_ACCESSBIT);
-	*((__le16*)&request[6]) = cpu_to_le16(rid);
-	*((__le16*)&request[8]) = cpu_to_le16(0);
-	*((__le16*)&request[10]) = cpu_to_le16(0);
-	usb_fill_bulk_urb(urb, zd->usb, usb_sndbulkpipe(zd->usb, zd->endp_out2),
-	     request, 16, zd1201_usbfree, zd);
-	err = usb_submit_urb(urb, gfp_mask);
-	if (err)
-		goto err;
-	
-	if (wait) {
-		wait_event_interruptible(zd->rxdataq, zd->rxdatas);
-		if (!zd->rxlen || le16_to_cpu(*(__le16*)&zd->rxdata[6]) != rid) {
-			dev_dbg(&zd->usb->dev, "wrong or no RID received\n");
-		}
-	}
-
-	return 0;
-err:
-	kfree(request);
-	usb_free_urb(urb);
-	return err;
-}
-
-static inline int zd1201_getconfig16(struct zd1201 *zd, int rid, short *val)
-{
-	int err;
-	__le16 zdval;
-
-	err = zd1201_getconfig(zd, rid, &zdval, sizeof(__le16));
-	if (err)
-		return err;
-	*val = le16_to_cpu(zdval);
-	return 0;
-}
-
-static inline int zd1201_setconfig16(struct zd1201 *zd, int rid, short val)
-{
-	__le16 zdval = cpu_to_le16(val);
-	return (zd1201_setconfig(zd, rid, &zdval, sizeof(__le16), 1));
-}
-
-static int zd1201_drvr_start(struct zd1201 *zd)
-{
-	int err, i;
-	short max;
-	__le16 zdmax;
-	unsigned char *buffer;
-
-	buffer = kzalloc(ZD1201_RXSIZE, GFP_KERNEL);
-	if (!buffer)
-		return -ENOMEM;
-
-	usb_fill_bulk_urb(zd->rx_urb, zd->usb, 
-	    usb_rcvbulkpipe(zd->usb, zd->endp_in), buffer, ZD1201_RXSIZE,
-	    zd1201_usbrx, zd);
-
-	err = usb_submit_urb(zd->rx_urb, GFP_KERNEL);
-	if (err)
-		goto err_buffer;
-
-	err = zd1201_docmd(zd, ZD1201_CMDCODE_INIT, 0, 0, 0);
-	if (err)
-		goto err_urb;
-
-	err = zd1201_getconfig(zd, ZD1201_RID_CNFMAXTXBUFFERNUMBER, &zdmax,
-	    sizeof(__le16));
-	if (err)
-		goto err_urb;
-
-	max = le16_to_cpu(zdmax);
-	for (i=0; i<max; i++) {
-		err = zd1201_docmd(zd, ZD1201_CMDCODE_ALLOC, 1514, 0, 0);
-		if (err)
-			goto err_urb;
-	}
-
-	return 0;
-
-err_urb:
-	usb_kill_urb(zd->rx_urb);
-	return err;
-err_buffer:
-	kfree(buffer);
-	return err;
-}
-
-/*	Magic alert: The firmware doesn't seem to like the MAC state being
- *	toggled in promisc (aka monitor) mode.
- *	(It works a number of times, but will halt eventually)
- *	So we turn it of before disabling and on after enabling if needed.
- */
-static int zd1201_enable(struct zd1201 *zd)
-{
-	int err;
-
-	if (zd->mac_enabled)
-		return 0;
-
-	err = zd1201_docmd(zd, ZD1201_CMDCODE_ENABLE, 0, 0, 0);
-	if (!err)
-		zd->mac_enabled = 1;
-
-	if (zd->monitor)
-		err = zd1201_setconfig16(zd, ZD1201_RID_PROMISCUOUSMODE, 1);
-
-	return err;
-}
-
-static int zd1201_disable(struct zd1201 *zd)
-{
-	int err;
-
-	if (!zd->mac_enabled)
-		return 0;
-	if (zd->monitor) {
-		err = zd1201_setconfig16(zd, ZD1201_RID_PROMISCUOUSMODE, 0);
-		if (err)
-			return err;
-	}
-
-	err = zd1201_docmd(zd, ZD1201_CMDCODE_DISABLE, 0, 0, 0);
-	if (!err)
-		zd->mac_enabled = 0;
-	return err;
-}
-
-static int zd1201_mac_reset(struct zd1201 *zd)
-{
-	if (!zd->mac_enabled)
-		return 0;
-	zd1201_disable(zd);
-	return zd1201_enable(zd);
-}
-
-static int zd1201_join(struct zd1201 *zd, char *essid, int essidlen)
-{
-	int err, val;
-	char buf[IW_ESSID_MAX_SIZE+2];
-
-	err = zd1201_disable(zd);
-	if (err)
-		return err;
-
-	val = ZD1201_CNFAUTHENTICATION_OPENSYSTEM;
-	val |= ZD1201_CNFAUTHENTICATION_SHAREDKEY;
-	err = zd1201_setconfig16(zd, ZD1201_RID_CNFAUTHENTICATION, val);
-	if (err)
-		return err;
-
-	*(__le16 *)buf = cpu_to_le16(essidlen);
-	memcpy(buf+2, essid, essidlen);
-	if (!zd->ap) {	/* Normal station */
-		err = zd1201_setconfig(zd, ZD1201_RID_CNFDESIREDSSID, buf,
-		    IW_ESSID_MAX_SIZE+2, 1);
-		if (err)
-			return err;
-	} else {	/* AP */
-		err = zd1201_setconfig(zd, ZD1201_RID_CNFOWNSSID, buf,
-		    IW_ESSID_MAX_SIZE+2, 1);
-		if (err)
-			return err;
-	}
-
-	err = zd1201_setconfig(zd, ZD1201_RID_CNFOWNMACADDR, 
-	    zd->dev->dev_addr, zd->dev->addr_len, 1);
-	if (err)
-		return err;
-
-	err = zd1201_enable(zd);
-	if (err)
-		return err;
-
-	msleep(100);
-	return 0;
-}
-
-static int zd1201_net_open(struct net_device *dev)
-{
-	struct zd1201 *zd = netdev_priv(dev);
-
-	/* Start MAC with wildcard if no essid set */
-	if (!zd->mac_enabled)
-		zd1201_join(zd, zd->essid, zd->essidlen);
-	netif_start_queue(dev);
-
-	return 0;
-}
-
-static int zd1201_net_stop(struct net_device *dev)
-{
-	netif_stop_queue(dev);
-	return 0;
-}
-
-/*
-	RFC 1042 encapsulates Ethernet frames in 802.11 frames
-	by prefixing them with 0xaa, 0xaa, 0x03) followed by a SNAP OID of 0
-	(0x00, 0x00, 0x00). Zd requires an additional padding, copy
-	of ethernet addresses, length of the standard RFC 1042 packet
-	and a command byte (which is nul for tx).
-	
-	tx frame (from Wlan NG):
-	RFC 1042:
-		llc		0xAA 0xAA 0x03 (802.2 LLC)
-		snap		0x00 0x00 0x00 (Ethernet encapsulated)
-		type		2 bytes, Ethernet type field
-		payload		(minus eth header)
-	Zydas specific:
-		padding		1B if (skb->len+8+1)%64==0
-		Eth MAC addr	12 bytes, Ethernet MAC addresses
-		length		2 bytes, RFC 1042 packet length 
-				(llc+snap+type+payload)
-		zd		1 null byte, zd1201 packet type
- */
-static netdev_tx_t zd1201_hard_start_xmit(struct sk_buff *skb,
-						struct net_device *dev)
-{
-	struct zd1201 *zd = netdev_priv(dev);
-	unsigned char *txbuf = zd->txdata;
-	int txbuflen, pad = 0, err;
-	struct urb *urb = zd->tx_urb;
-
-	if (!zd->mac_enabled || zd->monitor) {
-		dev->stats.tx_dropped++;
-		kfree_skb(skb);
-		return NETDEV_TX_OK;
-	}
-	netif_stop_queue(dev);
-
-	txbuflen = skb->len + 8 + 1;
-	if (txbuflen%64 == 0) {
-		pad = 1;
-		txbuflen++;
-	}
-	txbuf[0] = 0xAA;
-	txbuf[1] = 0xAA;
-	txbuf[2] = 0x03;
-	txbuf[3] = 0x00;	/* rfc1042 */
-	txbuf[4] = 0x00;
-	txbuf[5] = 0x00;
-
-	skb_copy_from_linear_data_offset(skb, 12, txbuf + 6, skb->len - 12);
-	if (pad)
-		txbuf[skb->len-12+6]=0;
-	skb_copy_from_linear_data(skb, txbuf + skb->len - 12 + 6 + pad, 12);
-	*(__be16*)&txbuf[skb->len+6+pad] = htons(skb->len-12+6);
-	txbuf[txbuflen-1] = 0;
-
-	usb_fill_bulk_urb(urb, zd->usb, usb_sndbulkpipe(zd->usb, zd->endp_out),
-	    txbuf, txbuflen, zd1201_usbtx, zd);
-
-	err = usb_submit_urb(zd->tx_urb, GFP_ATOMIC);
-	if (err) {
-		dev->stats.tx_errors++;
-		netif_start_queue(dev);
-	} else {
-		dev->stats.tx_packets++;
-		dev->stats.tx_bytes += skb->len;
-	}
-	kfree_skb(skb);
-
-	return NETDEV_TX_OK;
-}
-
-static void zd1201_tx_timeout(struct net_device *dev, unsigned int txqueue)
-{
-	struct zd1201 *zd = netdev_priv(dev);
-
-	if (!zd)
-		return;
-	dev_warn(&zd->usb->dev, "%s: TX timeout, shooting down urb\n",
-	    dev->name);
-	usb_unlink_urb(zd->tx_urb);
-	dev->stats.tx_errors++;
-	/* Restart the timeout to quiet the watchdog: */
-	netif_trans_update(dev); /* prevent tx timeout */
-}
-
-static int zd1201_set_mac_address(struct net_device *dev, void *p)
-{
-	struct sockaddr *addr = p;
-	struct zd1201 *zd = netdev_priv(dev);
-	int err;
-
-	if (!zd)
-		return -ENODEV;
-
-	err = zd1201_setconfig(zd, ZD1201_RID_CNFOWNMACADDR, 
-	    addr->sa_data, dev->addr_len, 1);
-	if (err)
-		return err;
-	eth_hw_addr_set(dev, addr->sa_data);
-
-	return zd1201_mac_reset(zd);
-}
-
-static struct iw_statistics *zd1201_get_wireless_stats(struct net_device *dev)
-{
-	struct zd1201 *zd = netdev_priv(dev);
-
-	return &zd->iwstats;
-}
-
-static void zd1201_set_multicast(struct net_device *dev)
-{
-	struct zd1201 *zd = netdev_priv(dev);
-	struct netdev_hw_addr *ha;
-	unsigned char reqbuf[ETH_ALEN*ZD1201_MAXMULTI];
-	int i;
-
-	if (netdev_mc_count(dev) > ZD1201_MAXMULTI)
-		return;
-
-	i = 0;
-	netdev_for_each_mc_addr(ha, dev)
-		memcpy(reqbuf + i++ * ETH_ALEN, ha->addr, ETH_ALEN);
-	zd1201_setconfig(zd, ZD1201_RID_CNFGROUPADDRESS, reqbuf,
-			 netdev_mc_count(dev) * ETH_ALEN, 0);
-}
-
-static int zd1201_config_commit(struct net_device *dev, 
-	struct iw_request_info *info, union iwreq_data *wrqu, char *essid)
-{
-	struct zd1201 *zd = netdev_priv(dev);
-
-	return zd1201_mac_reset(zd);
-}
-
-static int zd1201_get_name(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *extra)
-{
-	strcpy(wrqu->name, "IEEE 802.11b");
-	return 0;
-}
-
-static int zd1201_set_freq(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *extra)
-{
-	struct iw_freq *freq = &wrqu->freq;
-	struct zd1201 *zd = netdev_priv(dev);
-	short channel = 0;
-	int err;
-
-	if (freq->e == 0)
-		channel = freq->m;
-	else
-		channel = ieee80211_frequency_to_channel(freq->m);
-
-	err = zd1201_setconfig16(zd, ZD1201_RID_CNFOWNCHANNEL, channel);
-	if (err)
-		return err;
-
-	zd1201_mac_reset(zd);
-
-	return 0;
-}
-
-static int zd1201_get_freq(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *extra)
-{
-	struct iw_freq *freq = &wrqu->freq;
-	struct zd1201 *zd = netdev_priv(dev);
-	short channel;
-	int err;
-
-	err = zd1201_getconfig16(zd, ZD1201_RID_CNFOWNCHANNEL, &channel);
-	if (err)
-		return err;
-	freq->e = 0;
-	freq->m = channel;
-
-	return 0;
-}
-
-static int zd1201_set_mode(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *extra)
-{
-	__u32 *mode = &wrqu->mode;
-	struct zd1201 *zd = netdev_priv(dev);
-	short porttype, monitor = 0;
-	unsigned char buffer[IW_ESSID_MAX_SIZE+2];
-	int err;
-
-	if (zd->ap) {
-		if (*mode != IW_MODE_MASTER)
-			return -EINVAL;
-		return 0;
-	}
-
-	err = zd1201_setconfig16(zd, ZD1201_RID_PROMISCUOUSMODE, 0);
-	if (err)
-		return err;
-	zd->dev->type = ARPHRD_ETHER;
-	switch(*mode) {
-		case IW_MODE_MONITOR:
-			monitor = 1;
-			zd->dev->type = ARPHRD_IEEE80211;
-			/* Make sure we are no longer associated with by
-			   setting an 'impossible' essid.
-			   (otherwise we mess up firmware)
-			 */
-			zd1201_join(zd, "\0-*#\0", 5);
-			/* Put port in pIBSS */
-			fallthrough;
-		case 8: /* No pseudo-IBSS in wireless extensions (yet) */
-			porttype = ZD1201_PORTTYPE_PSEUDOIBSS;
-			break;
-		case IW_MODE_ADHOC:
-			porttype = ZD1201_PORTTYPE_IBSS;
-			break;
-		case IW_MODE_INFRA:
-			porttype = ZD1201_PORTTYPE_BSS;
-			break;
-		default:
-			return -EINVAL;
-	}
-
-	err = zd1201_setconfig16(zd, ZD1201_RID_CNFPORTTYPE, porttype);
-	if (err)
-		return err;
-	if (zd->monitor && !monitor) {
-			zd1201_disable(zd);
-			*(__le16 *)buffer = cpu_to_le16(zd->essidlen);
-			memcpy(buffer+2, zd->essid, zd->essidlen);
-			err = zd1201_setconfig(zd, ZD1201_RID_CNFDESIREDSSID,
-			    buffer, IW_ESSID_MAX_SIZE+2, 1);
-			if (err)
-				return err;
-	}
-	zd->monitor = monitor;
-	/* If monitor mode is set we don't actually turn it on here since it
-	 * is done during mac reset anyway (see zd1201_mac_enable).
-	 */
-	zd1201_mac_reset(zd);
-
-	return 0;
-}
-
-static int zd1201_get_mode(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *extra)
-{
-	__u32 *mode = &wrqu->mode;
-	struct zd1201 *zd = netdev_priv(dev);
-	short porttype;
-	int err;
-
-	err = zd1201_getconfig16(zd, ZD1201_RID_CNFPORTTYPE, &porttype);
-	if (err)
-		return err;
-	switch(porttype) {
-		case ZD1201_PORTTYPE_IBSS:
-			*mode = IW_MODE_ADHOC;
-			break;
-		case ZD1201_PORTTYPE_BSS:
-			*mode = IW_MODE_INFRA;
-			break;
-		case ZD1201_PORTTYPE_WDS:
-			*mode = IW_MODE_REPEAT;
-			break;
-		case ZD1201_PORTTYPE_PSEUDOIBSS:
-			*mode = 8;/* No Pseudo-IBSS... */
-			break;
-		case ZD1201_PORTTYPE_AP:
-			*mode = IW_MODE_MASTER;
-			break;
-		default:
-			dev_dbg(&zd->usb->dev, "Unknown porttype: %d\n",
-			    porttype);
-			*mode = IW_MODE_AUTO;
-	}
-	if (zd->monitor)
-		*mode = IW_MODE_MONITOR;
-
-	return 0;
-}
-
-static int zd1201_get_range(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *extra)
-{
-	struct iw_point *wrq = &wrqu->data;
-	struct iw_range *range = (struct iw_range *)extra;
-
-	wrq->length = sizeof(struct iw_range);
-	memset(range, 0, sizeof(struct iw_range));
-	range->we_version_compiled = WIRELESS_EXT;
-	range->we_version_source = WIRELESS_EXT;
-
-	range->max_qual.qual = 128;
-	range->max_qual.level = 128;
-	range->max_qual.noise = 128;
-	range->max_qual.updated = 7;
-
-	range->encoding_size[0] = 5;
-	range->encoding_size[1] = 13;
-	range->num_encoding_sizes = 2;
-	range->max_encoding_tokens = ZD1201_NUMKEYS;
-
-	range->num_bitrates = 4;
-	range->bitrate[0] = 1000000;
-	range->bitrate[1] = 2000000;
-	range->bitrate[2] = 5500000;
-	range->bitrate[3] = 11000000;
-
-	range->min_rts = 0;
-	range->min_frag = ZD1201_FRAGMIN;
-	range->max_rts = ZD1201_RTSMAX;
-	range->min_frag = ZD1201_FRAGMAX;
-
-	return 0;
-}
-
-/*	Little bit of magic here: we only get the quality if we poll
- *	for it, and we never get an actual request to trigger such
- *	a poll. Therefore we 'assume' that the user will soon ask for
- *	the stats after asking the bssid.
- */
-static int zd1201_get_wap(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *extra)
-{
-	struct sockaddr *ap_addr = &wrqu->ap_addr;
-	struct zd1201 *zd = netdev_priv(dev);
-	unsigned char buffer[6];
-
-	if (!zd1201_getconfig(zd, ZD1201_RID_COMMSQUALITY, buffer, 6)) {
-		/* Unfortunately the quality and noise reported is useless.
-		   they seem to be accumulators that increase until you
-		   read them, unless we poll on a fixed interval we can't
-		   use them
-		 */
-		/*zd->iwstats.qual.qual = le16_to_cpu(((__le16 *)buffer)[0]);*/
-		zd->iwstats.qual.level = le16_to_cpu(((__le16 *)buffer)[1]);
-		/*zd->iwstats.qual.noise = le16_to_cpu(((__le16 *)buffer)[2]);*/
-		zd->iwstats.qual.updated = 2;
-	}
-
-	return zd1201_getconfig(zd, ZD1201_RID_CURRENTBSSID, ap_addr->sa_data, 6);
-}
-
-static int zd1201_set_scan(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *extra)
-{
-	/* We do everything in get_scan */
-	return 0;
-}
-
-static int zd1201_get_scan(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *extra)
-{
-	struct iw_point *srq = &wrqu->data;
-	struct zd1201 *zd = netdev_priv(dev);
-	int err, i, j, enabled_save;
-	struct iw_event iwe;
-	char *cev = extra;
-	char *end_buf = extra + IW_SCAN_MAX_DATA;
-
-	/* No scanning in AP mode */
-	if (zd->ap)
-		return -EOPNOTSUPP;
-
-	/* Scan doesn't seem to work if disabled */
-	enabled_save = zd->mac_enabled;
-	zd1201_enable(zd);
-
-	zd->rxdatas = 0;
-	err = zd1201_docmd(zd, ZD1201_CMDCODE_INQUIRE, 
-	     ZD1201_INQ_SCANRESULTS, 0, 0);
-	if (err)
-		return err;
-
-	wait_event_interruptible(zd->rxdataq, zd->rxdatas);
-	if (!zd->rxlen)
-		return -EIO;
-
-	if (le16_to_cpu(*(__le16*)&zd->rxdata[2]) != ZD1201_INQ_SCANRESULTS)
-		return -EIO;
-
-	for(i=8; i<zd->rxlen; i+=62) {
-		iwe.cmd = SIOCGIWAP;
-		iwe.u.ap_addr.sa_family = ARPHRD_ETHER;
-		memcpy(iwe.u.ap_addr.sa_data, zd->rxdata+i+6, 6);
-		cev = iwe_stream_add_event(info, cev, end_buf,
-					   &iwe, IW_EV_ADDR_LEN);
-
-		iwe.cmd = SIOCGIWESSID;
-		iwe.u.data.length = zd->rxdata[i+16];
-		iwe.u.data.flags = 1;
-		cev = iwe_stream_add_point(info, cev, end_buf,
-					   &iwe, zd->rxdata+i+18);
-
-		iwe.cmd = SIOCGIWMODE;
-		if (zd->rxdata[i+14]&0x01)
-			iwe.u.mode = IW_MODE_MASTER;
-		else
-			iwe.u.mode = IW_MODE_ADHOC;
-		cev = iwe_stream_add_event(info, cev, end_buf,
-					   &iwe, IW_EV_UINT_LEN);
-		
-		iwe.cmd = SIOCGIWFREQ;
-		iwe.u.freq.m = zd->rxdata[i+0];
-		iwe.u.freq.e = 0;
-		cev = iwe_stream_add_event(info, cev, end_buf,
-					   &iwe, IW_EV_FREQ_LEN);
-		
-		iwe.cmd = SIOCGIWRATE;
-		iwe.u.bitrate.fixed = 0;
-		iwe.u.bitrate.disabled = 0;
-		for (j=0; j<10; j++) if (zd->rxdata[i+50+j]) {
-			iwe.u.bitrate.value = (zd->rxdata[i+50+j]&0x7f)*500000;
-			cev = iwe_stream_add_event(info, cev, end_buf,
-						   &iwe, IW_EV_PARAM_LEN);
-		}
-		
-		iwe.cmd = SIOCGIWENCODE;
-		iwe.u.data.length = 0;
-		if (zd->rxdata[i+14]&0x10)
-			iwe.u.data.flags = IW_ENCODE_ENABLED;
-		else
-			iwe.u.data.flags = IW_ENCODE_DISABLED;
-		cev = iwe_stream_add_point(info, cev, end_buf, &iwe, NULL);
-		
-		iwe.cmd = IWEVQUAL;
-		iwe.u.qual.qual = zd->rxdata[i+4];
-		iwe.u.qual.noise= zd->rxdata[i+2]/10-100;
-		iwe.u.qual.level = (256+zd->rxdata[i+4]*100)/255-100;
-		iwe.u.qual.updated = 7;
-		cev = iwe_stream_add_event(info, cev, end_buf,
-					   &iwe, IW_EV_QUAL_LEN);
-	}
-
-	if (!enabled_save)
-		zd1201_disable(zd);
-
-	srq->length = cev - extra;
-	srq->flags = 0;
-
-	return 0;
-}
-
-static int zd1201_set_essid(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *essid)
-{
-	struct iw_point *data = &wrqu->data;
-	struct zd1201 *zd = netdev_priv(dev);
-
-	if (data->length > IW_ESSID_MAX_SIZE)
-		return -EINVAL;
-	if (data->length < 1)
-		data->length = 1;
-	zd->essidlen = data->length;
-	memset(zd->essid, 0, IW_ESSID_MAX_SIZE+1);
-	memcpy(zd->essid, essid, data->length);
-	return zd1201_join(zd, zd->essid, zd->essidlen);
-}
-
-static int zd1201_get_essid(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *essid)
-{
-	struct iw_point *data = &wrqu->data;
-	struct zd1201 *zd = netdev_priv(dev);
-
-	memcpy(essid, zd->essid, zd->essidlen);
-	data->flags = 1;
-	data->length = zd->essidlen;
-
-	return 0;
-}
-
-static int zd1201_get_nick(struct net_device *dev, struct iw_request_info *info,
-	union iwreq_data *wrqu, char *nick)
-{
-	struct iw_point *data = &wrqu->data;
-	strcpy(nick, "zd1201");
-	data->flags = 1;
-	data->length = strlen(nick);
-	return 0;
-}
-
-static int zd1201_set_rate(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *rrq = &wrqu->bitrate;
-	struct zd1201 *zd = netdev_priv(dev);
-	short rate;
-	int err;
-
-	switch (rrq->value) {
-		case 1000000:
-			rate = ZD1201_RATEB1;
-			break;
-		case 2000000:
-			rate = ZD1201_RATEB2;
-			break;
-		case 5500000:
-			rate = ZD1201_RATEB5;
-			break;
-		case 11000000:
-		default:
-			rate = ZD1201_RATEB11;
-			break;
-	}
-	if (!rrq->fixed) { /* Also enable all lower bitrates */
-		rate |= rate-1;
-	}
-
-	err = zd1201_setconfig16(zd, ZD1201_RID_TXRATECNTL, rate);
-	if (err)
-		return err;
-
-	return zd1201_mac_reset(zd);
-}
-
-static int zd1201_get_rate(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *rrq = &wrqu->bitrate;
-	struct zd1201 *zd = netdev_priv(dev);
-	short rate;
-	int err;
-
-	err = zd1201_getconfig16(zd, ZD1201_RID_CURRENTTXRATE, &rate);
-	if (err)
-		return err;
-
-	switch(rate) {
-		case 1:
-			rrq->value = 1000000;
-			break;
-		case 2:
-			rrq->value = 2000000;
-			break;
-		case 5:
-			rrq->value = 5500000;
-			break;
-		case 11:
-			rrq->value = 11000000;
-			break;
-		default:
-			rrq->value = 0;
-	}
-	rrq->fixed = 0;
-	rrq->disabled = 0;
-
-	return 0;
-}
-
-static int zd1201_set_rts(struct net_device *dev, struct iw_request_info *info,
-	union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *rts = &wrqu->rts;
-	struct zd1201 *zd = netdev_priv(dev);
-	int err;
-	short val = rts->value;
-
-	if (rts->disabled || !rts->fixed)
-		val = ZD1201_RTSMAX;
-	if (val > ZD1201_RTSMAX)
-		return -EINVAL;
-	if (val < 0)
-		return -EINVAL;
-
-	err = zd1201_setconfig16(zd, ZD1201_RID_CNFRTSTHRESHOLD, val);
-	if (err)
-		return err;
-	return zd1201_mac_reset(zd);
-}
-
-static int zd1201_get_rts(struct net_device *dev, struct iw_request_info *info,
-	union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *rts = &wrqu->rts;
-	struct zd1201 *zd = netdev_priv(dev);
-	short rtst;
-	int err;
-
-	err = zd1201_getconfig16(zd, ZD1201_RID_CNFRTSTHRESHOLD, &rtst);
-	if (err)
-		return err;
-	rts->value = rtst;
-	rts->disabled = (rts->value == ZD1201_RTSMAX);
-	rts->fixed = 1;
-
-	return 0;
-}
-
-static int zd1201_set_frag(struct net_device *dev, struct iw_request_info *info,
-	union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *frag = &wrqu->frag;
-	struct zd1201 *zd = netdev_priv(dev);
-	int err;
-	short val = frag->value;
-
-	if (frag->disabled || !frag->fixed)
-		val = ZD1201_FRAGMAX;
-	if (val > ZD1201_FRAGMAX)
-		return -EINVAL;
-	if (val < ZD1201_FRAGMIN)
-		return -EINVAL;
-	if (val & 1)
-		return -EINVAL;
-	err = zd1201_setconfig16(zd, ZD1201_RID_CNFFRAGTHRESHOLD, val);
-	if (err)
-		return err;
-	return zd1201_mac_reset(zd);
-}
-
-static int zd1201_get_frag(struct net_device *dev, struct iw_request_info *info,
-	union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *frag = &wrqu->frag;
-	struct zd1201 *zd = netdev_priv(dev);
-	short fragt;
-	int err;
-
-	err = zd1201_getconfig16(zd, ZD1201_RID_CNFFRAGTHRESHOLD, &fragt);
-	if (err)
-		return err;
-	frag->value = fragt;
-	frag->disabled = (frag->value == ZD1201_FRAGMAX);
-	frag->fixed = 1;
-
-	return 0;
-}
-
-static int zd1201_set_retry(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *extra)
-{
-	return 0;
-}
-
-static int zd1201_get_retry(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *extra)
-{
-	return 0;
-}
-
-static int zd1201_set_encode(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *key)
-{
-	struct iw_point *erq = &wrqu->encoding;
-	struct zd1201 *zd = netdev_priv(dev);
-	short i;
-	int err, rid;
-
-	if (erq->length > ZD1201_MAXKEYLEN)
-		return -EINVAL;
-
-	i = (erq->flags & IW_ENCODE_INDEX)-1;
-	if (i == -1) {
-		err = zd1201_getconfig16(zd,ZD1201_RID_CNFDEFAULTKEYID,&i);
-		if (err)
-			return err;
-	} else {
-		err = zd1201_setconfig16(zd, ZD1201_RID_CNFDEFAULTKEYID, i);
-		if (err)
-			return err;
-	}
-
-	if (i < 0 || i >= ZD1201_NUMKEYS)
-		return -EINVAL;
-
-	rid = ZD1201_RID_CNFDEFAULTKEY0 + i;
-	err = zd1201_setconfig(zd, rid, key, erq->length, 1);
-	if (err)
-		return err;
-	zd->encode_keylen[i] = erq->length;
-	memcpy(zd->encode_keys[i], key, erq->length);
-
-	i=0;
-	if (!(erq->flags & IW_ENCODE_DISABLED & IW_ENCODE_MODE)) {
-		i |= 0x01;
-		zd->encode_enabled = 1;
-	} else
-		zd->encode_enabled = 0;
-	if (erq->flags & IW_ENCODE_RESTRICTED & IW_ENCODE_MODE) {
-		i |= 0x02;
-		zd->encode_restricted = 1;
-	} else
-		zd->encode_restricted = 0;
-	err = zd1201_setconfig16(zd, ZD1201_RID_CNFWEBFLAGS, i);
-	if (err)
-		return err;
-
-	if (zd->encode_enabled)
-		i = ZD1201_CNFAUTHENTICATION_SHAREDKEY;
-	else
-		i = ZD1201_CNFAUTHENTICATION_OPENSYSTEM;
-	err = zd1201_setconfig16(zd, ZD1201_RID_CNFAUTHENTICATION, i);
-	if (err)
-		return err;
-
-	return zd1201_mac_reset(zd);
-}
-
-static int zd1201_get_encode(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *key)
-{
-	struct iw_point *erq = &wrqu->encoding;
-	struct zd1201 *zd = netdev_priv(dev);
-	short i;
-	int err;
-
-	if (zd->encode_enabled)
-		erq->flags = IW_ENCODE_ENABLED;
-	else
-		erq->flags = IW_ENCODE_DISABLED;
-	if (zd->encode_restricted)
-		erq->flags |= IW_ENCODE_RESTRICTED;
-	else
-		erq->flags |= IW_ENCODE_OPEN;
-
-	i = (erq->flags & IW_ENCODE_INDEX) -1;
-	if (i == -1) {
-		err = zd1201_getconfig16(zd, ZD1201_RID_CNFDEFAULTKEYID, &i);
-		if (err)
-			return err;
-	}
-	if (i<0 || i>= ZD1201_NUMKEYS)
-		return -EINVAL;
-
-	erq->flags |= i+1;
-
-	erq->length = zd->encode_keylen[i];
-	memcpy(key, zd->encode_keys[i], erq->length);
-
-	return 0;
-}
-
-static int zd1201_set_power(struct net_device *dev, 
-	struct iw_request_info *info, union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *vwrq = &wrqu->power;
-	struct zd1201 *zd = netdev_priv(dev);
-	short enabled, duration, level;
-	int err;
-
-	enabled = vwrq->disabled ? 0 : 1;
-	if (enabled) {
-		if (vwrq->flags & IW_POWER_PERIOD) {
-			duration = vwrq->value;
-			err = zd1201_setconfig16(zd, 
-			    ZD1201_RID_CNFMAXSLEEPDURATION, duration);
-			if (err)
-				return err;
-			goto out;
-		}
-		if (vwrq->flags & IW_POWER_TIMEOUT) {
-			err = zd1201_getconfig16(zd, 
-			    ZD1201_RID_CNFMAXSLEEPDURATION, &duration);
-			if (err)
-				return err;
-			level = vwrq->value * 4 / duration;
-			if (level > 4)
-				level = 4;
-			if (level < 0)
-				level = 0;
-			err = zd1201_setconfig16(zd, ZD1201_RID_CNFPMEPS,
-			    level);
-			if (err)
-				return err;
-			goto out;
-		}
-		return -EINVAL;
-	}
-out:
-	return zd1201_setconfig16(zd, ZD1201_RID_CNFPMENABLED, enabled);
-}
-
-static int zd1201_get_power(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *vwrq = &wrqu->power;
-	struct zd1201 *zd = netdev_priv(dev);
-	short enabled, level, duration;
-	int err;
-
-	err = zd1201_getconfig16(zd, ZD1201_RID_CNFPMENABLED, &enabled);
-	if (err)
-		return err;
-	err = zd1201_getconfig16(zd, ZD1201_RID_CNFPMEPS, &level);
-	if (err)
-		return err;
-	err = zd1201_getconfig16(zd, ZD1201_RID_CNFMAXSLEEPDURATION, &duration);
-	if (err)
-		return err;
-	vwrq->disabled = enabled ? 0 : 1;
-	if (vwrq->flags & IW_POWER_TYPE) {
-		if (vwrq->flags & IW_POWER_PERIOD) {
-			vwrq->value = duration;
-			vwrq->flags = IW_POWER_PERIOD;
-		} else {
-			vwrq->value = duration * level / 4;
-			vwrq->flags = IW_POWER_TIMEOUT;
-		}
-	}
-	if (vwrq->flags & IW_POWER_MODE) {
-		if (enabled && level)
-			vwrq->flags = IW_POWER_UNICAST_R;
-		else
-			vwrq->flags = IW_POWER_ALL_R;
-	}
-
-	return 0;
-}
-
-
-static const iw_handler zd1201_iw_handler[] =
-{
-	IW_HANDLER(SIOCSIWCOMMIT,	zd1201_config_commit),
-	IW_HANDLER(SIOCGIWNAME,		zd1201_get_name),
-	IW_HANDLER(SIOCSIWFREQ,		zd1201_set_freq),
-	IW_HANDLER(SIOCGIWFREQ,		zd1201_get_freq),
-	IW_HANDLER(SIOCSIWMODE,		zd1201_set_mode),
-	IW_HANDLER(SIOCGIWMODE,		zd1201_get_mode),
-	IW_HANDLER(SIOCGIWRANGE,	zd1201_get_range),
-	IW_HANDLER(SIOCGIWAP,		zd1201_get_wap),
-	IW_HANDLER(SIOCSIWSCAN,		zd1201_set_scan),
-	IW_HANDLER(SIOCGIWSCAN,		zd1201_get_scan),
-	IW_HANDLER(SIOCSIWESSID,	zd1201_set_essid),
-	IW_HANDLER(SIOCGIWESSID,	zd1201_get_essid),
-	IW_HANDLER(SIOCGIWNICKN,	zd1201_get_nick),
-	IW_HANDLER(SIOCSIWRATE,		zd1201_set_rate),
-	IW_HANDLER(SIOCGIWRATE,		zd1201_get_rate),
-	IW_HANDLER(SIOCSIWRTS,		zd1201_set_rts),
-	IW_HANDLER(SIOCGIWRTS,		zd1201_get_rts),
-	IW_HANDLER(SIOCSIWFRAG,		zd1201_set_frag),
-	IW_HANDLER(SIOCGIWFRAG,		zd1201_get_frag),
-	IW_HANDLER(SIOCSIWRETRY,	zd1201_set_retry),
-	IW_HANDLER(SIOCGIWRETRY,	zd1201_get_retry),
-	IW_HANDLER(SIOCSIWENCODE,	zd1201_set_encode),
-	IW_HANDLER(SIOCGIWENCODE,	zd1201_get_encode),
-	IW_HANDLER(SIOCSIWPOWER,	zd1201_set_power),
-	IW_HANDLER(SIOCGIWPOWER,	zd1201_get_power),
-};
-
-static int zd1201_set_hostauth(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *rrq = &wrqu->param;
-	struct zd1201 *zd = netdev_priv(dev);
-
-	if (!zd->ap)
-		return -EOPNOTSUPP;
-
-	return zd1201_setconfig16(zd, ZD1201_RID_CNFHOSTAUTH, rrq->value);
-}
-
-static int zd1201_get_hostauth(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *rrq = &wrqu->param;
-	struct zd1201 *zd = netdev_priv(dev);
-	short hostauth;
-	int err;
-
-	if (!zd->ap)
-		return -EOPNOTSUPP;
-
-	err = zd1201_getconfig16(zd, ZD1201_RID_CNFHOSTAUTH, &hostauth);
-	if (err)
-		return err;
-	rrq->value = hostauth;
-	rrq->fixed = 1;
-
-	return 0;
-}
-
-static int zd1201_auth_sta(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *extra)
-{
-	struct sockaddr *sta = &wrqu->ap_addr;
-	struct zd1201 *zd = netdev_priv(dev);
-	unsigned char buffer[10];
-
-	if (!zd->ap)
-		return -EOPNOTSUPP;
-
-	memcpy(buffer, sta->sa_data, ETH_ALEN);
-	*(short*)(buffer+6) = 0;	/* 0==success, 1==failure */
-	*(short*)(buffer+8) = 0;
-
-	return zd1201_setconfig(zd, ZD1201_RID_AUTHENTICATESTA, buffer, 10, 1);
-}
-
-static int zd1201_set_maxassoc(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *rrq = &wrqu->param;
-	struct zd1201 *zd = netdev_priv(dev);
-
-	if (!zd->ap)
-		return -EOPNOTSUPP;
-
-	return zd1201_setconfig16(zd, ZD1201_RID_CNFMAXASSOCSTATIONS, rrq->value);
-}
-
-static int zd1201_get_maxassoc(struct net_device *dev,
-	struct iw_request_info *info, union iwreq_data *wrqu, char *extra)
-{
-	struct iw_param *rrq = &wrqu->param;
-	struct zd1201 *zd = netdev_priv(dev);
-	short maxassoc;
-	int err;
-
-	if (!zd->ap)
-		return -EOPNOTSUPP;
-
-	err = zd1201_getconfig16(zd, ZD1201_RID_CNFMAXASSOCSTATIONS, &maxassoc);
-	if (err)
-		return err;
-	rrq->value = maxassoc;
-	rrq->fixed = 1;
-
-	return 0;
-}
-
-static const iw_handler zd1201_private_handler[] = {
-	zd1201_set_hostauth,	/* ZD1201SIWHOSTAUTH */
-	zd1201_get_hostauth,	/* ZD1201GIWHOSTAUTH */
-	zd1201_auth_sta,	/* ZD1201SIWAUTHSTA */
-	NULL,			/* nothing to get */
-	zd1201_set_maxassoc,	/* ZD1201SIMAXASSOC */
-	zd1201_get_maxassoc,	/* ZD1201GIMAXASSOC */
-};
-
-static const struct iw_priv_args zd1201_private_args[] = {
-	{ ZD1201SIWHOSTAUTH, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1,
-	    IW_PRIV_TYPE_NONE, "sethostauth" },
-	{ ZD1201GIWHOSTAUTH, IW_PRIV_TYPE_NONE,
-	    IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "gethostauth" },
-	{ ZD1201SIWAUTHSTA, IW_PRIV_TYPE_ADDR | IW_PRIV_SIZE_FIXED | 1,
-	    IW_PRIV_TYPE_NONE, "authstation" },
-	{ ZD1201SIWMAXASSOC, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1,
-	    IW_PRIV_TYPE_NONE, "setmaxassoc" },
-	{ ZD1201GIWMAXASSOC, IW_PRIV_TYPE_NONE,
-	    IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "getmaxassoc" },
-};
-
-static const struct iw_handler_def zd1201_iw_handlers = {
-	.num_standard 		= ARRAY_SIZE(zd1201_iw_handler),
-	.num_private 		= ARRAY_SIZE(zd1201_private_handler),
-	.num_private_args 	= ARRAY_SIZE(zd1201_private_args),
-	.standard		= zd1201_iw_handler,
-	.private		= zd1201_private_handler,
-	.private_args 		= (struct iw_priv_args *) zd1201_private_args,
-	.get_wireless_stats	= zd1201_get_wireless_stats,
-};
-
-static const struct net_device_ops zd1201_netdev_ops = {
-	.ndo_open		= zd1201_net_open,
-	.ndo_stop		= zd1201_net_stop,
-	.ndo_start_xmit		= zd1201_hard_start_xmit,
-	.ndo_tx_timeout		= zd1201_tx_timeout,
-	.ndo_set_rx_mode	= zd1201_set_multicast,
-	.ndo_set_mac_address	= zd1201_set_mac_address,
-	.ndo_validate_addr	= eth_validate_addr,
-};
-
-static int zd1201_probe(struct usb_interface *interface,
-			const struct usb_device_id *id)
-{
-	struct zd1201 *zd;
-	struct net_device *dev;
-	struct usb_device *usb;
-	int err;
-	short porttype;
-	char buf[IW_ESSID_MAX_SIZE+2];
-	u8 addr[ETH_ALEN];
-
-	usb = interface_to_usbdev(interface);
-
-	dev = alloc_etherdev(sizeof(*zd));
-	if (!dev)
-		return -ENOMEM;
-	zd = netdev_priv(dev);
-	zd->dev = dev;
-
-	zd->ap = ap;
-	zd->usb = usb;
-	zd->removed = 0;
-	init_waitqueue_head(&zd->rxdataq);
-	INIT_HLIST_HEAD(&zd->fraglist);
-	
-	err = zd1201_fw_upload(usb, zd->ap);
-	if (err) {
-		dev_err(&usb->dev, "zd1201 firmware upload failed: %d\n", err);
-		goto err_zd;
-	}
-	
-	zd->endp_in = 1;
-	zd->endp_out = 1;
-	zd->endp_out2 = 2;
-	zd->rx_urb = usb_alloc_urb(0, GFP_KERNEL);
-	zd->tx_urb = usb_alloc_urb(0, GFP_KERNEL);
-	if (!zd->rx_urb || !zd->tx_urb) {
-		err = -ENOMEM;
-		goto err_zd;
-	}
-
-	mdelay(100);
-	err = zd1201_drvr_start(zd);
-	if (err)
-		goto err_zd;
-
-	err = zd1201_setconfig16(zd, ZD1201_RID_CNFMAXDATALEN, 2312);
-	if (err)
-		goto err_start;
-
-	err = zd1201_setconfig16(zd, ZD1201_RID_TXRATECNTL,
-	    ZD1201_RATEB1 | ZD1201_RATEB2 | ZD1201_RATEB5 | ZD1201_RATEB11);
-	if (err)
-		goto err_start;
-
-	dev->netdev_ops = &zd1201_netdev_ops;
-	dev->wireless_handlers = &zd1201_iw_handlers;
-	dev->watchdog_timeo = ZD1201_TX_TIMEOUT;
-	strcpy(dev->name, "wlan%d");
-
-	err = zd1201_getconfig(zd, ZD1201_RID_CNFOWNMACADDR, addr, ETH_ALEN);
-	if (err)
-		goto err_start;
-	eth_hw_addr_set(dev, addr);
-
-	/* Set wildcard essid to match zd->essid */
-	*(__le16 *)buf = cpu_to_le16(0);
-	err = zd1201_setconfig(zd, ZD1201_RID_CNFDESIREDSSID, buf,
-	    IW_ESSID_MAX_SIZE+2, 1);
-	if (err)
-		goto err_start;
-
-	if (zd->ap)
-		porttype = ZD1201_PORTTYPE_AP;
-	else
-		porttype = ZD1201_PORTTYPE_BSS;
-	err = zd1201_setconfig16(zd, ZD1201_RID_CNFPORTTYPE, porttype);
-	if (err)
-		goto err_start;
-
-	SET_NETDEV_DEV(dev, &usb->dev);
-
-	err = register_netdev(dev);
-	if (err)
-		goto err_start;
-	dev_info(&usb->dev, "%s: ZD1201 USB Wireless interface\n",
-	    dev->name);
-
-	usb_set_intfdata(interface, zd);
-	zd1201_enable(zd);	/* zd1201 likes to startup enabled, */
-	zd1201_disable(zd);	/* interfering with all the wifis in range */
-	return 0;
-
-err_start:
-	/* Leave the device in reset state */
-	zd1201_docmd(zd, ZD1201_CMDCODE_INIT, 0, 0, 0);
-err_zd:
-	usb_free_urb(zd->tx_urb);
-	usb_free_urb(zd->rx_urb);
-	free_netdev(dev);
-	return err;
-}
-
-static void zd1201_disconnect(struct usb_interface *interface)
-{
-	struct zd1201 *zd = usb_get_intfdata(interface);
-	struct hlist_node *node2;
-	struct zd1201_frag *frag;
-
-	if (!zd)
-		return;
-	usb_set_intfdata(interface, NULL);
-
-	hlist_for_each_entry_safe(frag, node2, &zd->fraglist, fnode) {
-		hlist_del_init(&frag->fnode);
-		kfree_skb(frag->skb);
-		kfree(frag);
-	}
-
-	if (zd->tx_urb) {
-		usb_kill_urb(zd->tx_urb);
-		usb_free_urb(zd->tx_urb);
-	}
-	if (zd->rx_urb) {
-		usb_kill_urb(zd->rx_urb);
-		usb_free_urb(zd->rx_urb);
-	}
-
-	if (zd->dev) {
-		unregister_netdev(zd->dev);
-		free_netdev(zd->dev);
-	}
-}
-
-#ifdef CONFIG_PM
-
-static int zd1201_suspend(struct usb_interface *interface,
-			   pm_message_t message)
-{
-	struct zd1201 *zd = usb_get_intfdata(interface);
-
-	netif_device_detach(zd->dev);
-
-	zd->was_enabled = zd->mac_enabled;
-
-	if (zd->was_enabled)
-		return zd1201_disable(zd);
-	else
-		return 0;
-}
-
-static int zd1201_resume(struct usb_interface *interface)
-{
-	struct zd1201 *zd = usb_get_intfdata(interface);
-
-	if (!zd || !zd->dev)
-		return -ENODEV;
-
-	netif_device_attach(zd->dev);
-
-	if (zd->was_enabled)
-		return zd1201_enable(zd);
-	else
-		return 0;
-}
-
-#else
-
-#define zd1201_suspend NULL
-#define zd1201_resume  NULL
-
-#endif
-
-static struct usb_driver zd1201_usb = {
-	.name = "zd1201",
-	.probe = zd1201_probe,
-	.disconnect = zd1201_disconnect,
-	.id_table = zd1201_table,
-	.suspend = zd1201_suspend,
-	.resume = zd1201_resume,
-	.disable_hub_initiated_lpm = 1,
-};
-
-module_usb_driver(zd1201_usb);
diff --git a/drivers/net/wireless/zydas/zd1201.h b/drivers/net/wireless/zydas/zd1201.h
deleted file mode 100644
index c46ac87550d1..000000000000
--- a/drivers/net/wireless/zydas/zd1201.h
+++ /dev/null
@@ -1,144 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- *	Copyright (c) 2004, 2005 Jeroen Vreeken (pe1rxq@amsat.org)
- *
- *	Parts of this driver have been derived from a wlan-ng version
- *	modified by ZyDAS.
- *	Copyright (C) 1999 AbsoluteValue Systems, Inc.  All Rights Reserved.
- */
-
-#ifndef _INCLUDE_ZD1201_H_
-#define _INCLUDE_ZD1201_H_
-
-#define ZD1201_NUMKEYS		4
-#define ZD1201_MAXKEYLEN	13
-#define ZD1201_MAXMULTI		16
-#define ZD1201_FRAGMAX		2500
-#define ZD1201_FRAGMIN		256
-#define ZD1201_RTSMAX		2500
-
-#define ZD1201_RXSIZE		3000
-
-struct zd1201 {
-	struct usb_device	*usb;
-	int			removed;
-	struct net_device	*dev;
-	struct iw_statistics	iwstats;
-
-	int			endp_in;
-	int			endp_out;
-	int			endp_out2;
-	struct urb		*rx_urb;
-	struct urb		*tx_urb;
-
-	unsigned char 		rxdata[ZD1201_RXSIZE];
-	int			rxlen;
-	wait_queue_head_t	rxdataq;
-	int			rxdatas;
-	struct hlist_head	fraglist;
-	unsigned char		txdata[ZD1201_RXSIZE];
-
-	int			ap;
-	char			essid[IW_ESSID_MAX_SIZE+1];
-	int			essidlen;
-	int			mac_enabled;
-	int			was_enabled;
-	int			monitor;
-	int			encode_enabled;
-	int			encode_restricted;
-	unsigned char		encode_keys[ZD1201_NUMKEYS][ZD1201_MAXKEYLEN];
-	int			encode_keylen[ZD1201_NUMKEYS];
-};
-
-struct zd1201_frag {
-	struct hlist_node	fnode;
-	int			seq;
-	struct sk_buff		*skb;
-};
-
-#define ZD1201SIWHOSTAUTH SIOCIWFIRSTPRIV
-#define ZD1201GIWHOSTAUTH ZD1201SIWHOSTAUTH+1
-#define ZD1201SIWAUTHSTA SIOCIWFIRSTPRIV+2
-#define ZD1201SIWMAXASSOC SIOCIWFIRSTPRIV+4
-#define ZD1201GIWMAXASSOC ZD1201SIWMAXASSOC+1
-
-#define ZD1201_FW_TIMEOUT	(1000)
-
-#define ZD1201_TX_TIMEOUT	(2000)
-
-#define ZD1201_USB_CMDREQ	0
-#define ZD1201_USB_RESREQ	1
-
-#define	ZD1201_CMDCODE_INIT	0x00
-#define ZD1201_CMDCODE_ENABLE	0x01
-#define ZD1201_CMDCODE_DISABLE	0x02
-#define ZD1201_CMDCODE_ALLOC	0x0a
-#define ZD1201_CMDCODE_INQUIRE	0x11
-#define ZD1201_CMDCODE_SETRXRID	0x17
-#define ZD1201_CMDCODE_ACCESS	0x21
-
-#define ZD1201_PACKET_EVENTSTAT	0x0
-#define ZD1201_PACKET_RXDATA	0x1
-#define ZD1201_PACKET_INQUIRE	0x2
-#define ZD1201_PACKET_RESOURCE	0x3
-
-#define ZD1201_ACCESSBIT	0x0100
-
-#define ZD1201_RID_CNFPORTTYPE		0xfc00
-#define ZD1201_RID_CNFOWNMACADDR	0xfc01
-#define ZD1201_RID_CNFDESIREDSSID	0xfc02
-#define ZD1201_RID_CNFOWNCHANNEL	0xfc03
-#define ZD1201_RID_CNFOWNSSID		0xfc04
-#define ZD1201_RID_CNFMAXDATALEN	0xfc07
-#define ZD1201_RID_CNFPMENABLED		0xfc09
-#define ZD1201_RID_CNFPMEPS		0xfc0a
-#define ZD1201_RID_CNFMAXSLEEPDURATION	0xfc0c
-#define ZD1201_RID_CNFDEFAULTKEYID	0xfc23
-#define ZD1201_RID_CNFDEFAULTKEY0	0xfc24
-#define ZD1201_RID_CNFDEFAULTKEY1	0xfc25
-#define ZD1201_RID_CNFDEFAULTKEY2	0xfc26
-#define ZD1201_RID_CNFDEFAULTKEY3	0xfc27
-#define ZD1201_RID_CNFWEBFLAGS		0xfc28
-#define ZD1201_RID_CNFAUTHENTICATION	0xfc2a
-#define ZD1201_RID_CNFMAXASSOCSTATIONS	0xfc2b
-#define ZD1201_RID_CNFHOSTAUTH		0xfc2e
-#define ZD1201_RID_CNFGROUPADDRESS	0xfc80
-#define ZD1201_RID_CNFFRAGTHRESHOLD	0xfc82
-#define ZD1201_RID_CNFRTSTHRESHOLD	0xfc83
-#define ZD1201_RID_TXRATECNTL		0xfc84
-#define ZD1201_RID_PROMISCUOUSMODE	0xfc85
-#define ZD1201_RID_CNFBASICRATES	0xfcb3
-#define ZD1201_RID_AUTHENTICATESTA	0xfce3
-#define ZD1201_RID_CURRENTBSSID		0xfd42
-#define ZD1201_RID_COMMSQUALITY		0xfd43
-#define ZD1201_RID_CURRENTTXRATE	0xfd44
-#define ZD1201_RID_CNFMAXTXBUFFERNUMBER	0xfda0
-#define ZD1201_RID_CURRENTCHANNEL	0xfdc1
-
-#define ZD1201_INQ_SCANRESULTS		0xf101
-
-#define ZD1201_INF_LINKSTATUS		0xf200
-#define ZD1201_INF_ASSOCSTATUS		0xf201
-#define ZD1201_INF_AUTHREQ		0xf202
-
-#define ZD1201_ASSOCSTATUS_STAASSOC	0x1
-#define ZD1201_ASSOCSTATUS_REASSOC	0x2
-#define ZD1201_ASSOCSTATUS_DISASSOC	0x3
-#define ZD1201_ASSOCSTATUS_ASSOCFAIL	0x4
-#define ZD1201_ASSOCSTATUS_AUTHFAIL	0x5
-
-#define ZD1201_PORTTYPE_IBSS		0
-#define ZD1201_PORTTYPE_BSS		1
-#define ZD1201_PORTTYPE_WDS		2
-#define ZD1201_PORTTYPE_PSEUDOIBSS	3
-#define ZD1201_PORTTYPE_AP		6
-
-#define ZD1201_RATEB1	1
-#define ZD1201_RATEB2	2
-#define ZD1201_RATEB5	4	/* 5.5 really, but 5 is shorter :) */
-#define ZD1201_RATEB11	8
-
-#define ZD1201_CNFAUTHENTICATION_OPENSYSTEM	0x0001
-#define ZD1201_CNFAUTHENTICATION_SHAREDKEY	0x0002
-
-#endif /* _INCLUDE_ZD1201_H_ */
diff --git a/drivers/net/wwan/qcom_bam_dmux.c b/drivers/net/wwan/qcom_bam_dmux.c
index 17d46f4d2913..26ca719fa0de 100644
--- a/drivers/net/wwan/qcom_bam_dmux.c
+++ b/drivers/net/wwan/qcom_bam_dmux.c
@@ -846,7 +846,7 @@ static int bam_dmux_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int bam_dmux_remove(struct platform_device *pdev)
+static void bam_dmux_remove(struct platform_device *pdev)
 {
 	struct bam_dmux *dmux = platform_get_drvdata(pdev);
 	struct device *dev = dmux->dev;
@@ -877,8 +877,6 @@ static int bam_dmux_remove(struct platform_device *pdev)
 	disable_irq(dmux->pc_irq);
 	bam_dmux_power_off(dmux);
 	bam_dmux_free_skbs(dmux->tx_skbs, DMA_TO_DEVICE);
-
-	return 0;
 }
 
 static const struct dev_pm_ops bam_dmux_pm_ops = {
@@ -893,7 +891,7 @@ MODULE_DEVICE_TABLE(of, bam_dmux_of_match);
 
 static struct platform_driver bam_dmux_driver = {
 	.probe = bam_dmux_probe,
-	.remove = bam_dmux_remove,
+	.remove_new = bam_dmux_remove,
 	.driver = {
 		.name = "bam-dmux",
 		.pm = &bam_dmux_pm_ops,
diff --git a/drivers/nfc/virtual_ncidev.c b/drivers/nfc/virtual_ncidev.c
index b027be0b0b6f..590b038e449e 100644
--- a/drivers/nfc/virtual_ncidev.c
+++ b/drivers/nfc/virtual_ncidev.c
@@ -26,10 +26,14 @@ struct virtual_nci_dev {
 	struct mutex mtx;
 	struct sk_buff *send_buff;
 	struct wait_queue_head wq;
+	bool running;
 };
 
 static int virtual_nci_open(struct nci_dev *ndev)
 {
+	struct virtual_nci_dev *vdev = nci_get_drvdata(ndev);
+
+	vdev->running = true;
 	return 0;
 }
 
@@ -40,6 +44,7 @@ static int virtual_nci_close(struct nci_dev *ndev)
 	mutex_lock(&vdev->mtx);
 	kfree_skb(vdev->send_buff);
 	vdev->send_buff = NULL;
+	vdev->running = false;
 	mutex_unlock(&vdev->mtx);
 
 	return 0;
@@ -50,7 +55,7 @@ static int virtual_nci_send(struct nci_dev *ndev, struct sk_buff *skb)
 	struct virtual_nci_dev *vdev = nci_get_drvdata(ndev);
 
 	mutex_lock(&vdev->mtx);
-	if (vdev->send_buff) {
+	if (vdev->send_buff || !vdev->running) {
 		mutex_unlock(&vdev->mtx);
 		kfree_skb(skb);
 		return -1;
diff --git a/drivers/nubus/bus.c b/drivers/nubus/bus.c
index 72921e4f35f6..12df4d88970c 100644
--- a/drivers/nubus/bus.c
+++ b/drivers/nubus/bus.c
@@ -32,12 +32,11 @@ static void nubus_device_remove(struct device *dev)
 		ndrv->remove(to_nubus_board(dev));
 }
 
-struct bus_type nubus_bus_type = {
+static const struct bus_type nubus_bus_type = {
 	.name		= "nubus",
 	.probe		= nubus_device_probe,
 	.remove		= nubus_device_remove,
 };
-EXPORT_SYMBOL(nubus_bus_type);
 
 int nubus_driver_register(struct nubus_driver *ndrv)
 {
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index d5593b0dc700..9372c36e8f76 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -986,7 +986,7 @@ static int btt_arena_write_layout(struct arena_info *arena)
 	if (!super)
 		return -ENOMEM;
 
-	strncpy(super->signature, BTT_SIG, BTT_SIG_LEN);
+	strscpy(super->signature, BTT_SIG, sizeof(super->signature));
 	export_uuid(super->uuid, nd_btt->uuid);
 	export_uuid(super->parent_uuid, parent_uuid);
 	super->flags = cpu_to_le32(arena->flags);
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index 8fe2dd619e80..b309c8be720f 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -107,11 +107,12 @@ config NVME_TCP_TLS
 	  If unsure, say N.
 
 config NVME_HOST_AUTH
-	bool "NVM Express over Fabrics In-Band Authentication"
+	bool "NVMe over Fabrics In-Band Authentication in host side"
 	depends on NVME_CORE
 	select NVME_AUTH
 	help
-	  This provides support for NVMe over Fabrics In-Band Authentication.
+	  This provides support for NVMe over Fabrics In-Band Authentication in
+	  host side.
 
 	  If unsure, say N.
 
diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c
index 48328e36e93b..72c0525c75f5 100644
--- a/drivers/nvme/host/auth.c
+++ b/drivers/nvme/host/auth.c
@@ -757,12 +757,11 @@ static void nvme_queue_auth_work(struct work_struct *work)
 		__func__, chap->qid);
 	mutex_lock(&ctrl->dhchap_auth_mutex);
 	ret = nvme_auth_dhchap_setup_host_response(ctrl, chap);
+	mutex_unlock(&ctrl->dhchap_auth_mutex);
 	if (ret) {
-		mutex_unlock(&ctrl->dhchap_auth_mutex);
 		chap->error = ret;
 		goto fail2;
 	}
-	mutex_unlock(&ctrl->dhchap_auth_mutex);
 
 	/* DH-HMAC-CHAP Step 3: send reply */
 	dev_dbg(ctrl->device, "%s: qid %d send reply\n",
@@ -839,6 +838,8 @@ static void nvme_queue_auth_work(struct work_struct *work)
 	}
 
 fail2:
+	if (chap->status == 0)
+		chap->status = NVME_AUTH_DHCHAP_FAILURE_FAILED;
 	dev_dbg(ctrl->device, "%s: qid %d send failure2, status %x\n",
 		__func__, chap->qid, chap->status);
 	tl = nvme_auth_set_dhchap_failure2_data(ctrl, chap);
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 88b54cdcbd68..0af612387083 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -20,6 +20,7 @@
 #include <linux/ptrace.h>
 #include <linux/nvme_ioctl.h>
 #include <linux/pm_qos.h>
+#include <linux/ratelimit.h>
 #include <asm/unaligned.h>
 
 #include "nvme.h"
@@ -131,7 +132,7 @@ void nvme_queue_scan(struct nvme_ctrl *ctrl)
 	/*
 	 * Only new queue scan work when admin and IO queues are both alive
 	 */
-	if (ctrl->state == NVME_CTRL_LIVE && ctrl->tagset)
+	if (nvme_ctrl_state(ctrl) == NVME_CTRL_LIVE && ctrl->tagset)
 		queue_work(nvme_wq, &ctrl->scan_work);
 }
 
@@ -143,7 +144,7 @@ void nvme_queue_scan(struct nvme_ctrl *ctrl)
  */
 int nvme_try_sched_reset(struct nvme_ctrl *ctrl)
 {
-	if (ctrl->state != NVME_CTRL_RESETTING)
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_RESETTING)
 		return -EBUSY;
 	if (!queue_work(nvme_reset_wq, &ctrl->reset_work))
 		return -EBUSY;
@@ -156,7 +157,7 @@ static void nvme_failfast_work(struct work_struct *work)
 	struct nvme_ctrl *ctrl = container_of(to_delayed_work(work),
 			struct nvme_ctrl, failfast_work);
 
-	if (ctrl->state != NVME_CTRL_CONNECTING)
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_CONNECTING)
 		return;
 
 	set_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
@@ -200,7 +201,7 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
 	ret = nvme_reset_ctrl(ctrl);
 	if (!ret) {
 		flush_work(&ctrl->reset_work);
-		if (ctrl->state != NVME_CTRL_LIVE)
+		if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE)
 			ret = -ENETRESET;
 	}
 
@@ -312,12 +313,12 @@ static void nvme_log_error(struct request *req)
 	struct nvme_request *nr = nvme_req(req);
 
 	if (ns) {
-		pr_err_ratelimited("%s: %s(0x%x) @ LBA %llu, %llu blocks, %s (sct 0x%x / sc 0x%x) %s%s\n",
+		pr_err_ratelimited("%s: %s(0x%x) @ LBA %llu, %u blocks, %s (sct 0x%x / sc 0x%x) %s%s\n",
 		       ns->disk ? ns->disk->disk_name : "?",
 		       nvme_get_opcode_str(nr->cmd->common.opcode),
 		       nr->cmd->common.opcode,
-		       (unsigned long long)nvme_sect_to_lba(ns, blk_rq_pos(req)),
-		       (unsigned long long)blk_rq_bytes(req) >> ns->lba_shift,
+		       nvme_sect_to_lba(ns->head, blk_rq_pos(req)),
+		       blk_rq_bytes(req) >> ns->head->lba_shift,
 		       nvme_get_error_status_str(nr->status),
 		       nr->status >> 8 & 7,	/* Status Code Type */
 		       nr->status & 0xff,	/* Status Code */
@@ -372,9 +373,12 @@ static inline enum nvme_disposition nvme_decide_disposition(struct request *req)
 static inline void nvme_end_req_zoned(struct request *req)
 {
 	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
-	    req_op(req) == REQ_OP_ZONE_APPEND)
-		req->__sector = nvme_lba_to_sect(req->q->queuedata,
+	    req_op(req) == REQ_OP_ZONE_APPEND) {
+		struct nvme_ns *ns = req->q->queuedata;
+
+		req->__sector = nvme_lba_to_sect(ns->head,
 			le64_to_cpu(nvme_req(req)->result.u64));
+	}
 }
 
 static inline void nvme_end_req(struct request *req)
@@ -482,7 +486,6 @@ EXPORT_SYMBOL_GPL(nvme_cancel_tagset);
 
 void nvme_cancel_admin_tagset(struct nvme_ctrl *ctrl)
 {
-	nvme_stop_keep_alive(ctrl);
 	if (ctrl->admin_tagset) {
 		blk_mq_tagset_busy_iter(ctrl->admin_tagset,
 				nvme_cancel_request, ctrl);
@@ -500,7 +503,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 
 	spin_lock_irqsave(&ctrl->lock, flags);
 
-	old_state = ctrl->state;
+	old_state = nvme_ctrl_state(ctrl);
 	switch (new_state) {
 	case NVME_CTRL_LIVE:
 		switch (old_state) {
@@ -568,7 +571,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 	}
 
 	if (changed) {
-		ctrl->state = new_state;
+		WRITE_ONCE(ctrl->state, new_state);
 		wake_up_all(&ctrl->state_wq);
 	}
 
@@ -576,11 +579,11 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 	if (!changed)
 		return false;
 
-	if (ctrl->state == NVME_CTRL_LIVE) {
+	if (new_state == NVME_CTRL_LIVE) {
 		if (old_state == NVME_CTRL_CONNECTING)
 			nvme_stop_failfast_work(ctrl);
 		nvme_kick_requeue_lists(ctrl);
-	} else if (ctrl->state == NVME_CTRL_CONNECTING &&
+	} else if (new_state == NVME_CTRL_CONNECTING &&
 		old_state == NVME_CTRL_RESETTING) {
 		nvme_start_failfast_work(ctrl);
 	}
@@ -593,7 +596,7 @@ EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);
  */
 static bool nvme_state_terminal(struct nvme_ctrl *ctrl)
 {
-	switch (ctrl->state) {
+	switch (nvme_ctrl_state(ctrl)) {
 	case NVME_CTRL_NEW:
 	case NVME_CTRL_LIVE:
 	case NVME_CTRL_RESETTING:
@@ -618,7 +621,7 @@ bool nvme_wait_reset(struct nvme_ctrl *ctrl)
 	wait_event(ctrl->state_wq,
 		   nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING) ||
 		   nvme_state_terminal(ctrl));
-	return ctrl->state == NVME_CTRL_RESETTING;
+	return nvme_ctrl_state(ctrl) == NVME_CTRL_RESETTING;
 }
 EXPORT_SYMBOL_GPL(nvme_wait_reset);
 
@@ -705,9 +708,11 @@ EXPORT_SYMBOL_GPL(nvme_init_request);
 blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
 		struct request *rq)
 {
-	if (ctrl->state != NVME_CTRL_DELETING_NOIO &&
-	    ctrl->state != NVME_CTRL_DELETING &&
-	    ctrl->state != NVME_CTRL_DEAD &&
+	enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
+
+	if (state != NVME_CTRL_DELETING_NOIO &&
+	    state != NVME_CTRL_DELETING &&
+	    state != NVME_CTRL_DEAD &&
 	    !test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) &&
 	    !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
 		return BLK_STS_RESOURCE;
@@ -737,7 +742,7 @@ bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		 * command, which is require to set the queue live in the
 		 * appropinquate states.
 		 */
-		switch (ctrl->state) {
+		switch (nvme_ctrl_state(ctrl)) {
 		case NVME_CTRL_CONNECTING:
 			if (blk_rq_is_passthrough(rq) && nvme_is_fabrics(req->cmd) &&
 			    (req->cmd->fabrics.fctype == nvme_fabrics_type_connect ||
@@ -792,8 +797,8 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 	}
 
 	if (queue_max_discard_segments(req->q) == 1) {
-		u64 slba = nvme_sect_to_lba(ns, blk_rq_pos(req));
-		u32 nlb = blk_rq_sectors(req) >> (ns->lba_shift - 9);
+		u64 slba = nvme_sect_to_lba(ns->head, blk_rq_pos(req));
+		u32 nlb = blk_rq_sectors(req) >> (ns->head->lba_shift - 9);
 
 		range[0].cattr = cpu_to_le32(0);
 		range[0].nlb = cpu_to_le32(nlb);
@@ -801,8 +806,9 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 		n = 1;
 	} else {
 		__rq_for_each_bio(bio, req) {
-			u64 slba = nvme_sect_to_lba(ns, bio->bi_iter.bi_sector);
-			u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift;
+			u64 slba = nvme_sect_to_lba(ns->head,
+						    bio->bi_iter.bi_sector);
+			u32 nlb = bio->bi_iter.bi_size >> ns->head->lba_shift;
 
 			if (n < segments) {
 				range[n].cattr = cpu_to_le32(0);
@@ -840,7 +846,7 @@ static void nvme_set_ref_tag(struct nvme_ns *ns, struct nvme_command *cmnd,
 	u64 ref48;
 
 	/* both rw and write zeroes share the same reftag format */
-	switch (ns->guard_type) {
+	switch (ns->head->guard_type) {
 	case NVME_NVM_NS_16B_GUARD:
 		cmnd->rw.reftag = cpu_to_le32(t10_pi_ref_tag(req));
 		break;
@@ -868,17 +874,18 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
 	cmnd->write_zeroes.opcode = nvme_cmd_write_zeroes;
 	cmnd->write_zeroes.nsid = cpu_to_le32(ns->head->ns_id);
 	cmnd->write_zeroes.slba =
-		cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
+		cpu_to_le64(nvme_sect_to_lba(ns->head, blk_rq_pos(req)));
 	cmnd->write_zeroes.length =
-		cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
+		cpu_to_le16((blk_rq_bytes(req) >> ns->head->lba_shift) - 1);
 
-	if (!(req->cmd_flags & REQ_NOUNMAP) && (ns->features & NVME_NS_DEAC))
+	if (!(req->cmd_flags & REQ_NOUNMAP) &&
+	    (ns->head->features & NVME_NS_DEAC))
 		cmnd->write_zeroes.control |= cpu_to_le16(NVME_WZ_DEAC);
 
-	if (nvme_ns_has_pi(ns)) {
+	if (nvme_ns_has_pi(ns->head)) {
 		cmnd->write_zeroes.control |= cpu_to_le16(NVME_RW_PRINFO_PRACT);
 
-		switch (ns->pi_type) {
+		switch (ns->head->pi_type) {
 		case NVME_NS_DPS_PI_TYPE1:
 		case NVME_NS_DPS_PI_TYPE2:
 			nvme_set_ref_tag(ns, cmnd, req);
@@ -910,13 +917,15 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 	cmnd->rw.cdw2 = 0;
 	cmnd->rw.cdw3 = 0;
 	cmnd->rw.metadata = 0;
-	cmnd->rw.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
-	cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
+	cmnd->rw.slba =
+		cpu_to_le64(nvme_sect_to_lba(ns->head, blk_rq_pos(req)));
+	cmnd->rw.length =
+		cpu_to_le16((blk_rq_bytes(req) >> ns->head->lba_shift) - 1);
 	cmnd->rw.reftag = 0;
 	cmnd->rw.apptag = 0;
 	cmnd->rw.appmask = 0;
 
-	if (ns->ms) {
+	if (ns->head->ms) {
 		/*
 		 * If formated with metadata, the block layer always provides a
 		 * metadata buffer if CONFIG_BLK_DEV_INTEGRITY is enabled.  Else
@@ -924,12 +933,12 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 		 * namespace capacity to zero to prevent any I/O.
 		 */
 		if (!blk_integrity_rq(req)) {
-			if (WARN_ON_ONCE(!nvme_ns_has_pi(ns)))
+			if (WARN_ON_ONCE(!nvme_ns_has_pi(ns->head)))
 				return BLK_STS_NOTSUPP;
 			control |= NVME_RW_PRINFO_PRACT;
 		}
 
-		switch (ns->pi_type) {
+		switch (ns->head->pi_type) {
 		case NVME_NS_DPS_PI_TYPE3:
 			control |= NVME_RW_PRINFO_PRCHK_GUARD;
 			break;
@@ -1193,8 +1202,16 @@ static unsigned long nvme_keep_alive_work_period(struct nvme_ctrl *ctrl)
 
 static void nvme_queue_keep_alive_work(struct nvme_ctrl *ctrl)
 {
-	queue_delayed_work(nvme_wq, &ctrl->ka_work,
-			   nvme_keep_alive_work_period(ctrl));
+	unsigned long now = jiffies;
+	unsigned long delay = nvme_keep_alive_work_period(ctrl);
+	unsigned long ka_next_check_tm = ctrl->ka_last_check_time + delay;
+
+	if (time_after(now, ka_next_check_tm))
+		delay = 0;
+	else
+		delay = ka_next_check_tm - now;
+
+	queue_delayed_work(nvme_wq, &ctrl->ka_work, delay);
 }
 
 static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
@@ -1443,7 +1460,7 @@ free_data:
 	return status;
 }
 
-static int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid,
+int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid,
 			struct nvme_id_ns **id)
 {
 	struct nvme_command c = { };
@@ -1480,7 +1497,8 @@ static int nvme_ns_info_from_identify(struct nvme_ctrl *ctrl,
 	if (id->ncap == 0) {
 		/* namespace not allocated or attached */
 		info->is_removed = true;
-		return -ENODEV;
+		ret = -ENODEV;
+		goto error;
 	}
 
 	info->anagrpid = id->anagrpid;
@@ -1498,8 +1516,10 @@ static int nvme_ns_info_from_identify(struct nvme_ctrl *ctrl,
 		    !memchr_inv(ids->nguid, 0, sizeof(ids->nguid)))
 			memcpy(ids->nguid, id->nguid, sizeof(ids->nguid));
 	}
+
+error:
 	kfree(id);
-	return 0;
+	return ret;
 }
 
 static int nvme_ns_info_from_id_cs_indep(struct nvme_ctrl *ctrl,
@@ -1659,14 +1679,14 @@ int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 }
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
-static void nvme_init_integrity(struct gendisk *disk, struct nvme_ns *ns,
-				u32 max_integrity_segments)
+static void nvme_init_integrity(struct gendisk *disk,
+		struct nvme_ns_head *head, u32 max_integrity_segments)
 {
 	struct blk_integrity integrity = { };
 
-	switch (ns->pi_type) {
+	switch (head->pi_type) {
 	case NVME_NS_DPS_PI_TYPE3:
-		switch (ns->guard_type) {
+		switch (head->guard_type) {
 		case NVME_NVM_NS_16B_GUARD:
 			integrity.profile = &t10_pi_type3_crc;
 			integrity.tag_size = sizeof(u16) + sizeof(u32);
@@ -1684,7 +1704,7 @@ static void nvme_init_integrity(struct gendisk *disk, struct nvme_ns *ns,
 		break;
 	case NVME_NS_DPS_PI_TYPE1:
 	case NVME_NS_DPS_PI_TYPE2:
-		switch (ns->guard_type) {
+		switch (head->guard_type) {
 		case NVME_NVM_NS_16B_GUARD:
 			integrity.profile = &t10_pi_type1_crc;
 			integrity.tag_size = sizeof(u16);
@@ -1705,25 +1725,26 @@ static void nvme_init_integrity(struct gendisk *disk, struct nvme_ns *ns,
 		break;
 	}
 
-	integrity.tuple_size = ns->ms;
+	integrity.tuple_size = head->ms;
 	blk_integrity_register(disk, &integrity);
 	blk_queue_max_integrity_segments(disk->queue, max_integrity_segments);
 }
 #else
-static void nvme_init_integrity(struct gendisk *disk, struct nvme_ns *ns,
-				u32 max_integrity_segments)
+static void nvme_init_integrity(struct gendisk *disk,
+		struct nvme_ns_head *head, u32 max_integrity_segments)
 {
 }
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
-static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns)
+static void nvme_config_discard(struct nvme_ctrl *ctrl, struct gendisk *disk,
+		struct nvme_ns_head *head)
 {
-	struct nvme_ctrl *ctrl = ns->ctrl;
 	struct request_queue *queue = disk->queue;
 	u32 size = queue_logical_block_size(queue);
 
-	if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(ns, UINT_MAX))
-		ctrl->max_discard_sectors = nvme_lba_to_sect(ns, ctrl->dmrsl);
+	if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(head, UINT_MAX))
+		ctrl->max_discard_sectors =
+			nvme_lba_to_sect(head, ctrl->dmrsl);
 
 	if (ctrl->max_discard_sectors == 0) {
 		blk_queue_max_discard_sectors(queue, 0);
@@ -1754,21 +1775,21 @@ static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
 		a->csi == b->csi;
 }
 
-static int nvme_init_ms(struct nvme_ns *ns, struct nvme_id_ns *id)
+static int nvme_init_ms(struct nvme_ctrl *ctrl, struct nvme_ns_head *head,
+		struct nvme_id_ns *id)
 {
 	bool first = id->dps & NVME_NS_DPS_PI_FIRST;
 	unsigned lbaf = nvme_lbaf_index(id->flbas);
-	struct nvme_ctrl *ctrl = ns->ctrl;
 	struct nvme_command c = { };
 	struct nvme_id_ns_nvm *nvm;
 	int ret = 0;
 	u32 elbaf;
 
-	ns->pi_size = 0;
-	ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
+	head->pi_size = 0;
+	head->ms = le16_to_cpu(id->lbaf[lbaf].ms);
 	if (!(ctrl->ctratt & NVME_CTRL_ATTR_ELBAS)) {
-		ns->pi_size = sizeof(struct t10_pi_tuple);
-		ns->guard_type = NVME_NVM_NS_16B_GUARD;
+		head->pi_size = sizeof(struct t10_pi_tuple);
+		head->guard_type = NVME_NVM_NS_16B_GUARD;
 		goto set_pi;
 	}
 
@@ -1777,11 +1798,11 @@ static int nvme_init_ms(struct nvme_ns *ns, struct nvme_id_ns *id)
 		return -ENOMEM;
 
 	c.identify.opcode = nvme_admin_identify;
-	c.identify.nsid = cpu_to_le32(ns->head->ns_id);
+	c.identify.nsid = cpu_to_le32(head->ns_id);
 	c.identify.cns = NVME_ID_CNS_CS_NS;
 	c.identify.csi = NVME_CSI_NVM;
 
-	ret = nvme_submit_sync_cmd(ns->ctrl->admin_q, &c, nvm, sizeof(*nvm));
+	ret = nvme_submit_sync_cmd(ctrl->admin_q, &c, nvm, sizeof(*nvm));
 	if (ret)
 		goto free_data;
 
@@ -1791,13 +1812,13 @@ static int nvme_init_ms(struct nvme_ns *ns, struct nvme_id_ns *id)
 	if (nvme_elbaf_sts(elbaf))
 		goto free_data;
 
-	ns->guard_type = nvme_elbaf_guard_type(elbaf);
-	switch (ns->guard_type) {
+	head->guard_type = nvme_elbaf_guard_type(elbaf);
+	switch (head->guard_type) {
 	case NVME_NVM_NS_64B_GUARD:
-		ns->pi_size = sizeof(struct crc64_pi_tuple);
+		head->pi_size = sizeof(struct crc64_pi_tuple);
 		break;
 	case NVME_NVM_NS_16B_GUARD:
-		ns->pi_size = sizeof(struct t10_pi_tuple);
+		head->pi_size = sizeof(struct t10_pi_tuple);
 		break;
 	default:
 		break;
@@ -1806,24 +1827,26 @@ static int nvme_init_ms(struct nvme_ns *ns, struct nvme_id_ns *id)
 free_data:
 	kfree(nvm);
 set_pi:
-	if (ns->pi_size && (first || ns->ms == ns->pi_size))
-		ns->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
+	if (head->pi_size && (first || head->ms == head->pi_size))
+		head->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
 	else
-		ns->pi_type = 0;
+		head->pi_type = 0;
 
 	return ret;
 }
 
-static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
+static int nvme_configure_metadata(struct nvme_ctrl *ctrl,
+		struct nvme_ns_head *head, struct nvme_id_ns *id)
 {
-	struct nvme_ctrl *ctrl = ns->ctrl;
+	int ret;
 
-	if (nvme_init_ms(ns, id))
-		return;
+	ret = nvme_init_ms(ctrl, head, id);
+	if (ret)
+		return ret;
 
-	ns->features &= ~(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
-	if (!ns->ms || !(ctrl->ops->flags & NVME_F_METADATA_SUPPORTED))
-		return;
+	head->features &= ~(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
+	if (!head->ms || !(ctrl->ops->flags & NVME_F_METADATA_SUPPORTED))
+		return 0;
 
 	if (ctrl->ops->flags & NVME_F_FABRICS) {
 		/*
@@ -1832,9 +1855,9 @@ static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
 		 * remap the separate metadata buffer from the block layer.
 		 */
 		if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT)))
-			return;
+			return 0;
 
-		ns->features |= NVME_NS_EXT_LBAS;
+		head->features |= NVME_NS_EXT_LBAS;
 
 		/*
 		 * The current fabrics transport drivers support namespace
@@ -1845,8 +1868,8 @@ static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
 		 * Note, this check will need to be modified if any drivers
 		 * gain the ability to use other metadata formats.
 		 */
-		if (ctrl->max_integrity_segments && nvme_ns_has_pi(ns))
-			ns->features |= NVME_NS_METADATA_SUPPORTED;
+		if (ctrl->max_integrity_segments && nvme_ns_has_pi(head))
+			head->features |= NVME_NS_METADATA_SUPPORTED;
 	} else {
 		/*
 		 * For PCIe controllers, we can't easily remap the separate
@@ -1855,10 +1878,11 @@ static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
 		 * We allow extended LBAs for the passthrough interface, though.
 		 */
 		if (id->flbas & NVME_NS_FLBAS_META_EXT)
-			ns->features |= NVME_NS_EXT_LBAS;
+			head->features |= NVME_NS_EXT_LBAS;
 		else
-			ns->features |= NVME_NS_METADATA_SUPPORTED;
+			head->features |= NVME_NS_METADATA_SUPPORTED;
 	}
+	return 0;
 }
 
 static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
@@ -1879,18 +1903,19 @@ static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
 	blk_queue_write_cache(q, vwc, vwc);
 }
 
-static void nvme_update_disk_info(struct gendisk *disk,
-		struct nvme_ns *ns, struct nvme_id_ns *id)
+static void nvme_update_disk_info(struct nvme_ctrl *ctrl, struct gendisk *disk,
+		struct nvme_ns_head *head, struct nvme_id_ns *id)
 {
-	sector_t capacity = nvme_lba_to_sect(ns, le64_to_cpu(id->nsze));
-	u32 bs = 1U << ns->lba_shift;
+	sector_t capacity = nvme_lba_to_sect(head, le64_to_cpu(id->nsze));
+	u32 bs = 1U << head->lba_shift;
 	u32 atomic_bs, phys_bs, io_opt = 0;
 
 	/*
 	 * The block layer can't support LBA sizes larger than the page size
-	 * yet, so catch this early and don't allow block I/O.
+	 * or smaller than a sector size yet, so catch this early and don't
+	 * allow block I/O.
 	 */
-	if (ns->lba_shift > PAGE_SHIFT) {
+	if (head->lba_shift > PAGE_SHIFT || head->lba_shift < SECTOR_SHIFT) {
 		capacity = 0;
 		bs = (1 << 9);
 	}
@@ -1907,7 +1932,7 @@ static void nvme_update_disk_info(struct gendisk *disk,
 		if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf)
 			atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
 		else
-			atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs;
+			atomic_bs = (1 + ctrl->subsys->awupf) * bs;
 	}
 
 	if (id->nsfeat & NVME_NS_FEAT_IO_OPT) {
@@ -1933,20 +1958,20 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	 * I/O to namespaces with metadata except when the namespace supports
 	 * PI, as it can strip/insert in that case.
 	 */
-	if (ns->ms) {
+	if (head->ms) {
 		if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) &&
-		    (ns->features & NVME_NS_METADATA_SUPPORTED))
-			nvme_init_integrity(disk, ns,
-					    ns->ctrl->max_integrity_segments);
-		else if (!nvme_ns_has_pi(ns))
+		    (head->features & NVME_NS_METADATA_SUPPORTED))
+			nvme_init_integrity(disk, head,
+					    ctrl->max_integrity_segments);
+		else if (!nvme_ns_has_pi(head))
 			capacity = 0;
 	}
 
 	set_capacity_and_notify(disk, capacity);
 
-	nvme_config_discard(disk, ns);
+	nvme_config_discard(ctrl, disk, head);
 	blk_queue_max_write_zeroes_sectors(disk->queue,
-					   ns->ctrl->max_zeroes_sectors);
+					   ctrl->max_zeroes_sectors);
 }
 
 static bool nvme_ns_is_readonly(struct nvme_ns *ns, struct nvme_ns_info *info)
@@ -1969,7 +1994,7 @@ static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id)
 	    is_power_of_2(ctrl->max_hw_sectors))
 		iob = ctrl->max_hw_sectors;
 	else
-		iob = nvme_lba_to_sect(ns, le16_to_cpu(id->noiob));
+		iob = nvme_lba_to_sect(ns->head, le16_to_cpu(id->noiob));
 
 	if (!iob)
 		return;
@@ -2027,14 +2052,26 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	if (ret)
 		return ret;
 
+	if (id->ncap == 0) {
+		/* namespace not allocated or attached */
+		info->is_removed = true;
+		ret = -ENODEV;
+		goto error;
+	}
+
 	blk_mq_freeze_queue(ns->disk->queue);
 	lbaf = nvme_lbaf_index(id->flbas);
-	ns->lba_shift = id->lbaf[lbaf].ds;
+	ns->head->lba_shift = id->lbaf[lbaf].ds;
+	ns->head->nuse = le64_to_cpu(id->nuse);
 	nvme_set_queue_limits(ns->ctrl, ns->queue);
 
-	nvme_configure_metadata(ns, id);
+	ret = nvme_configure_metadata(ns->ctrl, ns->head, id);
+	if (ret < 0) {
+		blk_mq_unfreeze_queue(ns->disk->queue);
+		goto out;
+	}
 	nvme_set_chunk_sectors(ns, id);
-	nvme_update_disk_info(ns->disk, ns, id);
+	nvme_update_disk_info(ns->ctrl, ns->disk, ns->head, id);
 
 	if (ns->head->ids.csi == NVME_CSI_ZNS) {
 		ret = nvme_update_zone_info(ns, lbaf);
@@ -2051,7 +2088,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	 * do not return zeroes.
 	 */
 	if ((id->dlfeat & 0x7) == 0x1 && (id->dlfeat & (1 << 3)))
-		ns->features |= NVME_NS_DEAC;
+		ns->head->features |= NVME_NS_DEAC;
 	set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info));
 	set_bit(NVME_NS_READY, &ns->flags);
 	blk_mq_unfreeze_queue(ns->disk->queue);
@@ -2064,7 +2101,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 
 	if (nvme_ns_head_multipath(ns->head)) {
 		blk_mq_freeze_queue(ns->head->disk->queue);
-		nvme_update_disk_info(ns->head->disk, ns, id);
+		nvme_update_disk_info(ns->ctrl, ns->head->disk, ns->head, id);
 		set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
 		nvme_mpath_revalidate_paths(ns);
 		blk_stack_limits(&ns->head->disk->queue->limits,
@@ -2084,6 +2121,8 @@ out:
 		set_bit(NVME_NS_READY, &ns->flags);
 		ret = 0;
 	}
+
+error:
 	kfree(id);
 	return ret;
 }
@@ -2523,7 +2562,7 @@ static void nvme_set_latency_tolerance(struct device *dev, s32 val)
 
 	if (ctrl->ps_max_latency_us != latency) {
 		ctrl->ps_max_latency_us = latency;
-		if (ctrl->state == NVME_CTRL_LIVE)
+		if (nvme_ctrl_state(ctrl) == NVME_CTRL_LIVE)
 			nvme_configure_apst(ctrl);
 	}
 }
@@ -2997,6 +3036,42 @@ static int nvme_init_effects(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	return 0;
 }
 
+static int nvme_check_ctrl_fabric_info(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
+{
+	/*
+	 * In fabrics we need to verify the cntlid matches the
+	 * admin connect
+	 */
+	if (ctrl->cntlid != le16_to_cpu(id->cntlid)) {
+		dev_err(ctrl->device,
+			"Mismatching cntlid: Connect %u vs Identify %u, rejecting\n",
+			ctrl->cntlid, le16_to_cpu(id->cntlid));
+		return -EINVAL;
+	}
+
+	if (!nvme_discovery_ctrl(ctrl) && !ctrl->kas) {
+		dev_err(ctrl->device,
+			"keep-alive support is mandatory for fabrics\n");
+		return -EINVAL;
+	}
+
+	if (!nvme_discovery_ctrl(ctrl) && ctrl->ioccsz < 4) {
+		dev_err(ctrl->device,
+			"I/O queue command capsule supported size %d < 4\n",
+			ctrl->ioccsz);
+		return -EINVAL;
+	}
+
+	if (!nvme_discovery_ctrl(ctrl) && ctrl->iorcsz < 1) {
+		dev_err(ctrl->device,
+			"I/O queue response capsule supported size %d < 1\n",
+			ctrl->iorcsz);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int nvme_init_identify(struct nvme_ctrl *ctrl)
 {
 	struct nvme_id_ctrl *id;
@@ -3109,25 +3184,9 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl)
 		ctrl->iorcsz = le32_to_cpu(id->iorcsz);
 		ctrl->maxcmd = le16_to_cpu(id->maxcmd);
 
-		/*
-		 * In fabrics we need to verify the cntlid matches the
-		 * admin connect
-		 */
-		if (ctrl->cntlid != le16_to_cpu(id->cntlid)) {
-			dev_err(ctrl->device,
-				"Mismatching cntlid: Connect %u vs Identify "
-				"%u, rejecting\n",
-				ctrl->cntlid, le16_to_cpu(id->cntlid));
-			ret = -EINVAL;
-			goto out_free;
-		}
-
-		if (!nvme_discovery_ctrl(ctrl) && !ctrl->kas) {
-			dev_err(ctrl->device,
-				"keep-alive support is mandatory for fabrics\n");
-			ret = -EINVAL;
+		ret = nvme_check_ctrl_fabric_info(ctrl, id);
+		if (ret)
 			goto out_free;
-		}
 	} else {
 		ctrl->hmpre = le32_to_cpu(id->hmpre);
 		ctrl->hmmin = le32_to_cpu(id->hmmin);
@@ -3211,7 +3270,7 @@ static int nvme_dev_open(struct inode *inode, struct file *file)
 	struct nvme_ctrl *ctrl =
 		container_of(inode->i_cdev, struct nvme_ctrl, cdev);
 
-	switch (ctrl->state) {
+	switch (nvme_ctrl_state(ctrl)) {
 	case NVME_CTRL_LIVE:
 		break;
 	default:
@@ -3386,6 +3445,8 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
 	head->ns_id = info->nsid;
 	head->ids = info->ids;
 	head->shared = info->is_shared;
+	ratelimit_state_init(&head->rs_nuse, 5 * HZ, 1);
+	ratelimit_set_flags(&head->rs_nuse, RATELIMIT_MSG_ON_RELEASE);
 	kref_init(&head->ref);
 
 	if (head->ids.csi) {
@@ -3633,11 +3694,19 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 		goto out_unlink_ns;
 
 	down_write(&ctrl->namespaces_rwsem);
+	/*
+	 * Ensure that no namespaces are added to the ctrl list after the queues
+	 * are frozen, thereby avoiding a deadlock between scan and reset.
+	 */
+	if (test_bit(NVME_CTRL_FROZEN, &ctrl->flags)) {
+		up_write(&ctrl->namespaces_rwsem);
+		goto out_unlink_ns;
+	}
 	nvme_ns_add_to_ctrl_list(ns);
 	up_write(&ctrl->namespaces_rwsem);
 	nvme_get_ctrl(ctrl);
 
-	if (device_add_disk(ctrl->device, ns->disk, nvme_ns_id_attr_groups))
+	if (device_add_disk(ctrl->device, ns->disk, nvme_ns_attr_groups))
 		goto out_cleanup_ns_from_list;
 
 	if (!nvme_ns_head_multipath(ns->head))
@@ -3897,7 +3966,7 @@ static void nvme_scan_work(struct work_struct *work)
 	int ret;
 
 	/* No tagset on a live ctrl means IO queues could not created */
-	if (ctrl->state != NVME_CTRL_LIVE || !ctrl->tagset)
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE || !ctrl->tagset)
 		return;
 
 	/*
@@ -3967,7 +4036,7 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
 	 * removing the namespaces' disks; fail all the queues now to avoid
 	 * potentially having to clean up the failed sync later.
 	 */
-	if (ctrl->state == NVME_CTRL_DEAD)
+	if (nvme_ctrl_state(ctrl) == NVME_CTRL_DEAD)
 		nvme_mark_namespaces_dead(ctrl);
 
 	/* this is a no-op when called from the controller reset handler */
@@ -4049,7 +4118,7 @@ static void nvme_async_event_work(struct work_struct *work)
 	 * flushing ctrl async_event_work after changing the controller state
 	 * from LIVE and before freeing the admin queue.
 	*/
-	if (ctrl->state == NVME_CTRL_LIVE)
+	if (nvme_ctrl_state(ctrl) == NVME_CTRL_LIVE)
 		ctrl->ops->submit_async_event(ctrl);
 }
 
@@ -4100,6 +4169,8 @@ static void nvme_fw_act_work(struct work_struct *work)
 				struct nvme_ctrl, fw_act_work);
 	unsigned long fw_act_timeout;
 
+	nvme_auth_stop(ctrl);
+
 	if (ctrl->mtfa)
 		fw_act_timeout = jiffies +
 				msecs_to_jiffies(ctrl->mtfa * 100);
@@ -4155,7 +4226,6 @@ static bool nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
 		 * firmware activation.
 		 */
 		if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) {
-			nvme_auth_stop(ctrl);
 			requeue = false;
 			queue_work(nvme_wq, &ctrl->fw_act_work);
 		}
@@ -4348,6 +4418,7 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl)
 {
 	nvme_mpath_stop(ctrl);
 	nvme_auth_stop(ctrl);
+	nvme_stop_keep_alive(ctrl);
 	nvme_stop_failfast_work(ctrl);
 	flush_work(&ctrl->async_event_work);
 	cancel_work_sync(&ctrl->fw_act_work);
@@ -4443,7 +4514,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 {
 	int ret;
 
-	ctrl->state = NVME_CTRL_NEW;
+	WRITE_ONCE(ctrl->state, NVME_CTRL_NEW);
 	clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
 	spin_lock_init(&ctrl->lock);
 	mutex_init(&ctrl->scan_lock);
@@ -4464,6 +4535,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	INIT_DELAYED_WORK(&ctrl->failfast_work, nvme_failfast_work);
 	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
 	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
+	ctrl->ka_last_check_time = jiffies;
 
 	BUILD_BUG_ON(NVME_DSM_MAX_RANGES * sizeof(struct nvme_dsm_range) >
 			PAGE_SIZE);
@@ -4552,6 +4624,7 @@ void nvme_unfreeze(struct nvme_ctrl *ctrl)
 	list_for_each_entry(ns, &ctrl->namespaces, list)
 		blk_mq_unfreeze_queue(ns->queue);
 	up_read(&ctrl->namespaces_rwsem);
+	clear_bit(NVME_CTRL_FROZEN, &ctrl->flags);
 }
 EXPORT_SYMBOL_GPL(nvme_unfreeze);
 
@@ -4585,6 +4658,7 @@ void nvme_start_freeze(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
 
+	set_bit(NVME_CTRL_FROZEN, &ctrl->flags);
 	down_read(&ctrl->namespaces_rwsem);
 	list_for_each_entry(ns, &ctrl->namespaces, list)
 		blk_freeze_queue_start(ns->queue);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 4673ead69c5f..b5752a77ad98 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -387,8 +387,8 @@ static struct nvmf_connect_data *nvmf_connect_data_prep(struct nvme_ctrl *ctrl,
 
 	uuid_copy(&data->hostid, &ctrl->opts->host->id);
 	data->cntlid = cpu_to_le16(cntlid);
-	strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE);
-	strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE);
+	strscpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE);
+	strscpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE);
 
 	return data;
 }
@@ -667,8 +667,10 @@ static const match_table_t opt_tokens = {
 #endif
 	{ NVMF_OPT_FAIL_FAST_TMO,	"fast_io_fail_tmo=%d"	},
 	{ NVMF_OPT_DISCOVERY,		"discovery"		},
+#ifdef CONFIG_NVME_HOST_AUTH
 	{ NVMF_OPT_DHCHAP_SECRET,	"dhchap_secret=%s"	},
 	{ NVMF_OPT_DHCHAP_CTRL_SECRET,	"dhchap_ctrl_secret=%s"	},
+#endif
 #ifdef CONFIG_NVME_TCP_TLS
 	{ NVMF_OPT_TLS,			"tls"			},
 #endif
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 49c3e46eaa1e..16847a316421 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -557,7 +557,7 @@ nvme_fc_rport_get(struct nvme_fc_rport *rport)
 static void
 nvme_fc_resume_controller(struct nvme_fc_ctrl *ctrl)
 {
-	switch (ctrl->ctrl.state) {
+	switch (nvme_ctrl_state(&ctrl->ctrl)) {
 	case NVME_CTRL_NEW:
 	case NVME_CTRL_CONNECTING:
 		/*
@@ -793,7 +793,7 @@ nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl)
 		"NVME-FC{%d}: controller connectivity lost. Awaiting "
 		"Reconnect", ctrl->cnum);
 
-	switch (ctrl->ctrl.state) {
+	switch (nvme_ctrl_state(&ctrl->ctrl)) {
 	case NVME_CTRL_NEW:
 	case NVME_CTRL_LIVE:
 		/*
@@ -1218,10 +1218,10 @@ nvme_fc_connect_admin_queue(struct nvme_fc_ctrl *ctrl,
 	/* Linux supports only Dynamic controllers */
 	assoc_rqst->assoc_cmd.cntlid = cpu_to_be16(0xffff);
 	uuid_copy(&assoc_rqst->assoc_cmd.hostid, &ctrl->ctrl.opts->host->id);
-	strncpy(assoc_rqst->assoc_cmd.hostnqn, ctrl->ctrl.opts->host->nqn,
-		min(FCNVME_ASSOC_HOSTNQN_LEN, NVMF_NQN_SIZE));
-	strncpy(assoc_rqst->assoc_cmd.subnqn, ctrl->ctrl.opts->subsysnqn,
-		min(FCNVME_ASSOC_SUBNQN_LEN, NVMF_NQN_SIZE));
+	strscpy(assoc_rqst->assoc_cmd.hostnqn, ctrl->ctrl.opts->host->nqn,
+		sizeof(assoc_rqst->assoc_cmd.hostnqn));
+	strscpy(assoc_rqst->assoc_cmd.subnqn, ctrl->ctrl.opts->subsysnqn,
+		sizeof(assoc_rqst->assoc_cmd.subnqn));
 
 	lsop->queue = queue;
 	lsreq->rqstaddr = assoc_rqst;
@@ -2530,12 +2530,6 @@ __nvme_fc_abort_outstanding_ios(struct nvme_fc_ctrl *ctrl, bool start_queues)
 	 * clean up the admin queue. Same thing as above.
 	 */
 	nvme_quiesce_admin_queue(&ctrl->ctrl);
-
-	/*
-	 * Open-coding nvme_cancel_admin_tagset() as fc
-	 * is not using nvme_cancel_request().
-	 */
-	nvme_stop_keep_alive(&ctrl->ctrl);
 	blk_sync_queue(ctrl->ctrl.admin_q);
 	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
 				nvme_fc_terminate_exchange, &ctrl->ctrl);
@@ -2554,24 +2548,17 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
 	 * the controller.  Abort any ios on the association and let the
 	 * create_association error path resolve things.
 	 */
-	enum nvme_ctrl_state state;
-	unsigned long flags;
-
-	spin_lock_irqsave(&ctrl->lock, flags);
-	state = ctrl->ctrl.state;
-	if (state == NVME_CTRL_CONNECTING) {
-		set_bit(ASSOC_FAILED, &ctrl->flags);
-		spin_unlock_irqrestore(&ctrl->lock, flags);
+	if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) {
 		__nvme_fc_abort_outstanding_ios(ctrl, true);
+		set_bit(ASSOC_FAILED, &ctrl->flags);
 		dev_warn(ctrl->ctrl.device,
 			"NVME-FC{%d}: transport error during (re)connect\n",
 			ctrl->cnum);
 		return;
 	}
-	spin_unlock_irqrestore(&ctrl->lock, flags);
 
 	/* Otherwise, only proceed if in LIVE state - e.g. on first error */
-	if (state != NVME_CTRL_LIVE)
+	if (ctrl->ctrl.state != NVME_CTRL_LIVE)
 		return;
 
 	dev_warn(ctrl->ctrl.device,
@@ -3138,11 +3125,12 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	nvme_unquiesce_admin_queue(&ctrl->ctrl);
 
 	ret = nvme_init_ctrl_finish(&ctrl->ctrl, false);
-	if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags))
-		ret = -EIO;
 	if (ret)
 		goto out_disconnect_admin_queue;
-
+	if (test_bit(ASSOC_FAILED, &ctrl->flags)) {
+		ret = -EIO;
+		goto out_stop_keep_alive;
+	}
 	/* sanity checks */
 
 	/* FC-NVME does not have other data in the capsule */
@@ -3150,7 +3138,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 		dev_err(ctrl->ctrl.device, "icdoff %d is not supported!\n",
 				ctrl->ctrl.icdoff);
 		ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
-		goto out_disconnect_admin_queue;
+		goto out_stop_keep_alive;
 	}
 
 	/* FC-NVME supports normal SGL Data Block Descriptors */
@@ -3158,7 +3146,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 		dev_err(ctrl->ctrl.device,
 			"Mandatory sgls are not supported!\n");
 		ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
-		goto out_disconnect_admin_queue;
+		goto out_stop_keep_alive;
 	}
 
 	if (opts->queue_size > ctrl->ctrl.maxcmd) {
@@ -3185,16 +3173,12 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 		else
 			ret = nvme_fc_recreate_io_queues(ctrl);
 	}
-
-	spin_lock_irqsave(&ctrl->lock, flags);
 	if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags))
 		ret = -EIO;
-	if (ret) {
-		spin_unlock_irqrestore(&ctrl->lock, flags);
+	if (ret)
 		goto out_term_aen_ops;
-	}
+
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
-	spin_unlock_irqrestore(&ctrl->lock, flags);
 
 	ctrl->ctrl.nr_reconnects = 0;
 
@@ -3205,6 +3189,8 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 
 out_term_aen_ops:
 	nvme_fc_term_aen_ops(ctrl);
+out_stop_keep_alive:
+	nvme_stop_keep_alive(&ctrl->ctrl);
 out_disconnect_admin_queue:
 	dev_warn(ctrl->ctrl.device,
 		"NVME-FC{%d}: create_assoc failed, assoc_id %llx ret %d\n",
@@ -3322,7 +3308,7 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status)
 	unsigned long recon_delay = ctrl->ctrl.opts->reconnect_delay * HZ;
 	bool recon = true;
 
-	if (ctrl->ctrl.state != NVME_CTRL_CONNECTING)
+	if (nvme_ctrl_state(&ctrl->ctrl) != NVME_CTRL_CONNECTING)
 		return;
 
 	if (portptr->port_state == FC_OBJSTATE_ONLINE) {
@@ -3512,10 +3498,6 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 
 	ctrl->ctrl.opts = opts;
 	ctrl->ctrl.nr_reconnects = 0;
-	if (lport->dev)
-		ctrl->ctrl.numa_node = dev_to_node(lport->dev);
-	else
-		ctrl->ctrl.numa_node = NUMA_NO_NODE;
 	INIT_LIST_HEAD(&ctrl->ctrl_list);
 	ctrl->lport = lport;
 	ctrl->rport = rport;
@@ -3560,6 +3542,8 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_fc_ctrl_ops, 0);
 	if (ret)
 		goto out_free_queues;
+	if (lport->dev)
+		ctrl->ctrl.numa_node = dev_to_node(lport->dev);
 
 	/* at this point, teardown path changes to ref counting on nvme ctrl */
 
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 529b9954d2b8..18f5c1be5d67 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -5,7 +5,7 @@
  */
 #include <linux/ptrace.h>	/* for force_successful_syscall_return */
 #include <linux/nvme_ioctl.h>
-#include <linux/io_uring.h>
+#include <linux/io_uring/cmd.h>
 #include "nvme.h"
 
 enum {
@@ -18,15 +18,12 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
 {
 	u32 effects;
 
-	if (capable(CAP_SYS_ADMIN))
-		return true;
-
 	/*
 	 * Do not allow unprivileged passthrough on partitions, as that allows an
 	 * escape from the containment of the partition.
 	 */
 	if (flags & NVME_IOCTL_PARTITION)
-		return false;
+		goto admin;
 
 	/*
 	 * Do not allow unprivileged processes to send vendor specific or fabrics
@@ -34,7 +31,7 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
 	 */
 	if (c->common.opcode >= nvme_cmd_vendor_start ||
 	    c->common.opcode == nvme_fabrics_command)
-		return false;
+		goto admin;
 
 	/*
 	 * Do not allow unprivileged passthrough of admin commands except
@@ -53,7 +50,7 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
 				return true;
 			}
 		}
-		return false;
+		goto admin;
 	}
 
 	/*
@@ -63,7 +60,7 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
 	 */
 	effects = nvme_command_effects(ns->ctrl, ns, c->common.opcode);
 	if (!(effects & NVME_CMD_EFFECTS_CSUPP))
-		return false;
+		goto admin;
 
 	/*
 	 * Don't allow passthrough for command that have intrusive (or unknown)
@@ -72,16 +69,20 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
 	if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC |
 			NVME_CMD_EFFECTS_UUID_SEL |
 			NVME_CMD_EFFECTS_SCOPE_MASK))
-		return false;
+		goto admin;
 
 	/*
 	 * Only allow I/O commands that transfer data to the controller or that
 	 * change the logical block contents if the file descriptor is open for
 	 * writing.
 	 */
-	if (nvme_is_write(c) || (effects & NVME_CMD_EFFECTS_LBCC))
-		return open_for_write;
+	if ((nvme_is_write(c) || (effects & NVME_CMD_EFFECTS_LBCC)) &&
+	    !open_for_write)
+		goto admin;
+
 	return true;
+admin:
+	return capable(CAP_SYS_ADMIN);
 }
 
 /*
@@ -96,58 +97,6 @@ static void __user *nvme_to_user_ptr(uintptr_t ptrval)
 	return (void __user *)ptrval;
 }
 
-static void *nvme_add_user_metadata(struct request *req, void __user *ubuf,
-		unsigned len, u32 seed)
-{
-	struct bio_integrity_payload *bip;
-	int ret = -ENOMEM;
-	void *buf;
-	struct bio *bio = req->bio;
-
-	buf = kmalloc(len, GFP_KERNEL);
-	if (!buf)
-		goto out;
-
-	if (req_op(req) == REQ_OP_DRV_OUT) {
-		ret = -EFAULT;
-		if (copy_from_user(buf, ubuf, len))
-			goto out_free_meta;
-	} else {
-		memset(buf, 0, len);
-	}
-
-	bip = bio_integrity_alloc(bio, GFP_KERNEL, 1);
-	if (IS_ERR(bip)) {
-		ret = PTR_ERR(bip);
-		goto out_free_meta;
-	}
-
-	bip->bip_iter.bi_sector = seed;
-	ret = bio_integrity_add_page(bio, virt_to_page(buf), len,
-			offset_in_page(buf));
-	if (ret != len) {
-		ret = -ENOMEM;
-		goto out_free_meta;
-	}
-
-	req->cmd_flags |= REQ_INTEGRITY;
-	return buf;
-out_free_meta:
-	kfree(buf);
-out:
-	return ERR_PTR(ret);
-}
-
-static int nvme_finish_user_metadata(struct request *req, void __user *ubuf,
-		void *meta, unsigned len, int ret)
-{
-	if (!ret && req_op(req) == REQ_OP_DRV_IN &&
-	    copy_to_user(ubuf, meta, len))
-		ret = -EFAULT;
-	kfree(meta);
-	return ret;
-}
-
 static struct request *nvme_alloc_user_request(struct request_queue *q,
 		struct nvme_command *cmd, blk_opf_t rq_flags,
 		blk_mq_req_flags_t blk_flags)
@@ -164,14 +113,12 @@ static struct request *nvme_alloc_user_request(struct request_queue *q,
 
 static int nvme_map_user_request(struct request *req, u64 ubuffer,
 		unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
-		u32 meta_seed, void **metap, struct io_uring_cmd *ioucmd,
-		unsigned int flags)
+		u32 meta_seed, struct io_uring_cmd *ioucmd, unsigned int flags)
 {
 	struct request_queue *q = req->q;
 	struct nvme_ns *ns = q->queuedata;
 	struct block_device *bdev = ns ? ns->disk->part0 : NULL;
 	struct bio *bio = NULL;
-	void *meta = NULL;
 	int ret;
 
 	if (ioucmd && (ioucmd->flags & IORING_URING_CMD_FIXED)) {
@@ -193,18 +140,17 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
 
 	if (ret)
 		goto out;
+
 	bio = req->bio;
-	if (bdev)
+	if (bdev) {
 		bio_set_dev(bio, bdev);
-
-	if (bdev && meta_buffer && meta_len) {
-		meta = nvme_add_user_metadata(req, meta_buffer, meta_len,
-				meta_seed);
-		if (IS_ERR(meta)) {
-			ret = PTR_ERR(meta);
-			goto out_unmap;
+		if (meta_buffer && meta_len) {
+			ret = bio_integrity_map_user(bio, meta_buffer, meta_len,
+						     meta_seed);
+			if (ret)
+				goto out_unmap;
+			req->cmd_flags |= REQ_INTEGRITY;
 		}
-		*metap = meta;
 	}
 
 	return ret;
@@ -225,7 +171,6 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 	struct nvme_ns *ns = q->queuedata;
 	struct nvme_ctrl *ctrl;
 	struct request *req;
-	void *meta = NULL;
 	struct bio *bio;
 	u32 effects;
 	int ret;
@@ -237,7 +182,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 	req->timeout = timeout;
 	if (ubuffer && bufflen) {
 		ret = nvme_map_user_request(req, ubuffer, bufflen, meta_buffer,
-				meta_len, meta_seed, &meta, NULL, flags);
+				meta_len, meta_seed, NULL, flags);
 		if (ret)
 			return ret;
 	}
@@ -249,9 +194,6 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 	ret = nvme_execute_rq(req, false);
 	if (result)
 		*result = le64_to_cpu(nvme_req(req)->result.u64);
-	if (meta)
-		ret = nvme_finish_user_metadata(req, meta_buffer, meta,
-						meta_len, ret);
 	if (bio)
 		blk_rq_unmap_user(bio);
 	blk_mq_free_request(req);
@@ -283,10 +225,10 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 		return -EINVAL;
 	}
 
-	length = (io.nblocks + 1) << ns->lba_shift;
+	length = (io.nblocks + 1) << ns->head->lba_shift;
 
 	if ((io.control & NVME_RW_PRINFO_PRACT) &&
-	    ns->ms == sizeof(struct t10_pi_tuple)) {
+	    ns->head->ms == sizeof(struct t10_pi_tuple)) {
 		/*
 		 * Protection information is stripped/inserted by the
 		 * controller.
@@ -296,11 +238,11 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 		meta_len = 0;
 		metadata = NULL;
 	} else {
-		meta_len = (io.nblocks + 1) * ns->ms;
+		meta_len = (io.nblocks + 1) * ns->head->ms;
 		metadata = nvme_to_user_ptr(io.metadata);
 	}
 
-	if (ns->features & NVME_NS_EXT_LBAS) {
+	if (ns->head->features & NVME_NS_EXT_LBAS) {
 		length += meta_len;
 		meta_len = 0;
 	} else if (meta_len) {
@@ -446,19 +388,10 @@ struct nvme_uring_data {
  * Expect build errors if this grows larger than that.
  */
 struct nvme_uring_cmd_pdu {
-	union {
-		struct bio *bio;
-		struct request *req;
-	};
-	u32 meta_len;
-	u32 nvme_status;
-	union {
-		struct {
-			void *meta; /* kernel-resident buffer */
-			void __user *meta_buffer;
-		};
-		u64 result;
-	} u;
+	struct request *req;
+	struct bio *bio;
+	u64 result;
+	int status;
 };
 
 static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu(
@@ -467,31 +400,6 @@ static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu(
 	return (struct nvme_uring_cmd_pdu *)&ioucmd->pdu;
 }
 
-static void nvme_uring_task_meta_cb(struct io_uring_cmd *ioucmd,
-				    unsigned issue_flags)
-{
-	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
-	struct request *req = pdu->req;
-	int status;
-	u64 result;
-
-	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
-		status = -EINTR;
-	else
-		status = nvme_req(req)->status;
-
-	result = le64_to_cpu(nvme_req(req)->result.u64);
-
-	if (pdu->meta_len)
-		status = nvme_finish_user_metadata(req, pdu->u.meta_buffer,
-					pdu->u.meta, pdu->meta_len, status);
-	if (req->bio)
-		blk_rq_unmap_user(req->bio);
-	blk_mq_free_request(req);
-
-	io_uring_cmd_done(ioucmd, status, result, issue_flags);
-}
-
 static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd,
 			       unsigned issue_flags)
 {
@@ -499,8 +407,7 @@ static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd,
 
 	if (pdu->bio)
 		blk_rq_unmap_user(pdu->bio);
-
-	io_uring_cmd_done(ioucmd, pdu->nvme_status, pdu->u.result, issue_flags);
+	io_uring_cmd_done(ioucmd, pdu->status, pdu->result, issue_flags);
 }
 
 static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
@@ -509,53 +416,24 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
 	struct io_uring_cmd *ioucmd = req->end_io_data;
 	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
 
-	req->bio = pdu->bio;
-	if (nvme_req(req)->flags & NVME_REQ_CANCELLED) {
-		pdu->nvme_status = -EINTR;
-	} else {
-		pdu->nvme_status = nvme_req(req)->status;
-		if (!pdu->nvme_status)
-			pdu->nvme_status = blk_status_to_errno(err);
-	}
-	pdu->u.result = le64_to_cpu(nvme_req(req)->result.u64);
+	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
+		pdu->status = -EINTR;
+	else
+		pdu->status = nvme_req(req)->status;
+	pdu->result = le64_to_cpu(nvme_req(req)->result.u64);
 
 	/*
 	 * For iopoll, complete it directly.
 	 * Otherwise, move the completion to task work.
 	 */
-	if (blk_rq_is_poll(req)) {
-		WRITE_ONCE(ioucmd->cookie, NULL);
+	if (blk_rq_is_poll(req))
 		nvme_uring_task_cb(ioucmd, IO_URING_F_UNLOCKED);
-	} else {
+	else
 		io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
-	}
 
 	return RQ_END_IO_FREE;
 }
 
-static enum rq_end_io_ret nvme_uring_cmd_end_io_meta(struct request *req,
-						     blk_status_t err)
-{
-	struct io_uring_cmd *ioucmd = req->end_io_data;
-	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
-
-	req->bio = pdu->bio;
-	pdu->req = req;
-
-	/*
-	 * For iopoll, complete it directly.
-	 * Otherwise, move the completion to task work.
-	 */
-	if (blk_rq_is_poll(req)) {
-		WRITE_ONCE(ioucmd->cookie, NULL);
-		nvme_uring_task_meta_cb(ioucmd, IO_URING_F_UNLOCKED);
-	} else {
-		io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_meta_cb);
-	}
-
-	return RQ_END_IO_NONE;
-}
-
 static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 		struct io_uring_cmd *ioucmd, unsigned int issue_flags, bool vec)
 {
@@ -567,7 +445,6 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	struct request *req;
 	blk_opf_t rq_flags = REQ_ALLOC_CACHE;
 	blk_mq_req_flags_t blk_flags = 0;
-	void *meta = NULL;
 	int ret;
 
 	c.common.opcode = READ_ONCE(cmd->opcode);
@@ -615,27 +492,16 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	if (d.addr && d.data_len) {
 		ret = nvme_map_user_request(req, d.addr,
 			d.data_len, nvme_to_user_ptr(d.metadata),
-			d.metadata_len, 0, &meta, ioucmd, vec);
+			d.metadata_len, 0, ioucmd, vec);
 		if (ret)
 			return ret;
 	}
 
-	if (blk_rq_is_poll(req)) {
-		ioucmd->flags |= IORING_URING_CMD_POLLED;
-		WRITE_ONCE(ioucmd->cookie, req);
-	}
-
 	/* to free bio on completion, as req->bio will be null at that time */
 	pdu->bio = req->bio;
-	pdu->meta_len = d.metadata_len;
+	pdu->req = req;
 	req->end_io_data = ioucmd;
-	if (pdu->meta_len) {
-		pdu->u.meta = meta;
-		pdu->u.meta_buffer = nvme_to_user_ptr(d.metadata);
-		req->end_io = nvme_uring_cmd_end_io_meta;
-	} else {
-		req->end_io = nvme_uring_cmd_end_io;
-	}
+	req->end_io = nvme_uring_cmd_end_io;
 	blk_execute_rq_nowait(req, false);
 	return -EIOCBQUEUED;
 }
@@ -786,16 +652,12 @@ int nvme_ns_chr_uring_cmd_iopoll(struct io_uring_cmd *ioucmd,
 				 struct io_comp_batch *iob,
 				 unsigned int poll_flags)
 {
-	struct request *req;
-	int ret = 0;
-
-	if (!(ioucmd->flags & IORING_URING_CMD_POLLED))
-		return 0;
+	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
+	struct request *req = pdu->req;
 
-	req = READ_ONCE(ioucmd->cookie);
 	if (req && blk_rq_is_poll(req))
-		ret = blk_rq_poll(req, iob, poll_flags);
-	return ret;
+		return blk_rq_poll(req, iob, poll_flags);
+	return 0;
 }
 #ifdef CONFIG_NVME_MULTIPATH
 static int nvme_ns_head_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd,
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 0a88d7bdc5e3..2dd4137a08b2 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -579,7 +579,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 	 */
 	if (!test_and_set_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) {
 		rc = device_add_disk(&head->subsys->dev, head->disk,
-				     nvme_ns_id_attr_groups);
+				     nvme_ns_attr_groups);
 		if (rc) {
 			clear_bit(NVME_NSHEAD_DISK_LIVE, &ns->flags);
 			return;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 39a90b7cb125..4be7f6822966 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -16,6 +16,7 @@
 #include <linux/rcupdate.h>
 #include <linux/wait.h>
 #include <linux/t10-pi.h>
+#include <linux/ratelimit_types.h>
 
 #include <trace/events/block.h>
 
@@ -156,6 +157,11 @@ enum nvme_quirks {
 	 * No temperature thresholds for channels other than 0 (Composite).
 	 */
 	NVME_QUIRK_NO_SECONDARY_TEMP_THRESH	= (1 << 19),
+
+	/*
+	 * Disables simple suspend/resume path.
+	 */
+	NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND	= (1 << 20),
 };
 
 /*
@@ -251,6 +257,7 @@ enum nvme_ctrl_flags {
 	NVME_CTRL_STOPPED		= 3,
 	NVME_CTRL_SKIP_ID_CNS_CS	= 4,
 	NVME_CTRL_DIRTY_CAPABILITY	= 5,
+	NVME_CTRL_FROZEN		= 6,
 };
 
 struct nvme_ctrl {
@@ -387,6 +394,11 @@ struct nvme_ctrl {
 	enum nvme_dctype dctype;
 };
 
+static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl)
+{
+	return READ_ONCE(ctrl->state);
+}
+
 enum nvme_iopolicy {
 	NVME_IOPOLICY_NUMA,
 	NVME_IOPOLICY_RR,
@@ -439,13 +451,27 @@ struct nvme_ns_head {
 	struct list_head	list;
 	struct srcu_struct      srcu;
 	struct nvme_subsystem	*subsys;
-	unsigned		ns_id;
 	struct nvme_ns_ids	ids;
 	struct list_head	entry;
 	struct kref		ref;
 	bool			shared;
 	int			instance;
 	struct nvme_effects_log *effects;
+	u64			nuse;
+	unsigned		ns_id;
+	int			lba_shift;
+	u16			ms;
+	u16			pi_size;
+	u8			pi_type;
+	u8			guard_type;
+	u16			sgs;
+	u32			sws;
+#ifdef CONFIG_BLK_DEV_ZONED
+	u64			zsze;
+#endif
+	unsigned long		features;
+
+	struct ratelimit_state	rs_nuse;
 
 	struct cdev		cdev;
 	struct device		cdev_device;
@@ -487,17 +513,6 @@ struct nvme_ns {
 	struct kref kref;
 	struct nvme_ns_head *head;
 
-	int lba_shift;
-	u16 ms;
-	u16 pi_size;
-	u16 sgs;
-	u32 sws;
-	u8 pi_type;
-	u8 guard_type;
-#ifdef CONFIG_BLK_DEV_ZONED
-	u64 zsze;
-#endif
-	unsigned long features;
 	unsigned long flags;
 #define NVME_NS_REMOVING	0
 #define NVME_NS_ANA_PENDING	2
@@ -512,9 +527,9 @@ struct nvme_ns {
 };
 
 /* NVMe ns supports metadata actions by the controller (generate/strip) */
-static inline bool nvme_ns_has_pi(struct nvme_ns *ns)
+static inline bool nvme_ns_has_pi(struct nvme_ns_head *head)
 {
-	return ns->pi_type && ns->ms == ns->pi_size;
+	return head->pi_type && head->ms == head->pi_size;
 }
 
 struct nvme_ctrl_ops {
@@ -646,17 +661,17 @@ static inline int nvme_reset_subsystem(struct nvme_ctrl *ctrl)
 /*
  * Convert a 512B sector number to a device logical block number.
  */
-static inline u64 nvme_sect_to_lba(struct nvme_ns *ns, sector_t sector)
+static inline u64 nvme_sect_to_lba(struct nvme_ns_head *head, sector_t sector)
 {
-	return sector >> (ns->lba_shift - SECTOR_SHIFT);
+	return sector >> (head->lba_shift - SECTOR_SHIFT);
 }
 
 /*
  * Convert a device logical block number to a 512B sector number.
  */
-static inline sector_t nvme_lba_to_sect(struct nvme_ns *ns, u64 lba)
+static inline sector_t nvme_lba_to_sect(struct nvme_ns_head *head, u64 lba)
 {
-	return lba << (ns->lba_shift - SECTOR_SHIFT);
+	return lba << (head->lba_shift - SECTOR_SHIFT);
 }
 
 /*
@@ -862,10 +877,12 @@ int nvme_ns_chr_uring_cmd(struct io_uring_cmd *ioucmd,
 		unsigned int issue_flags);
 int nvme_ns_head_chr_uring_cmd(struct io_uring_cmd *ioucmd,
 		unsigned int issue_flags);
+int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid,
+		struct nvme_id_ns **id);
 int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo);
 int nvme_dev_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags);
 
-extern const struct attribute_group *nvme_ns_id_attr_groups[];
+extern const struct attribute_group *nvme_ns_attr_groups[];
 extern const struct pr_ops nvme_pr_ops;
 extern const struct block_device_operations nvme_ns_head_ops;
 extern const struct attribute_group nvme_dev_attrs_group;
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 507bc149046d..61af7ff1a9d6 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1233,7 +1233,7 @@ static bool nvme_should_reset(struct nvme_dev *dev, u32 csts)
 	bool nssro = dev->subsystem && (csts & NVME_CSTS_NSSRO);
 
 	/* If there is a reset/reinit ongoing, we shouldn't reset again. */
-	switch (dev->ctrl.state) {
+	switch (nvme_ctrl_state(&dev->ctrl)) {
 	case NVME_CTRL_RESETTING:
 	case NVME_CTRL_CONNECTING:
 		return false;
@@ -1321,7 +1321,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	 * cancellation error. All outstanding requests are completed on
 	 * shutdown, so we return BLK_EH_DONE.
 	 */
-	switch (dev->ctrl.state) {
+	switch (nvme_ctrl_state(&dev->ctrl)) {
 	case NVME_CTRL_CONNECTING:
 		nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
 		fallthrough;
@@ -1593,7 +1593,7 @@ static int nvme_setup_io_queues_trylock(struct nvme_dev *dev)
 	/*
 	 * Controller is in wrong state, fail early.
 	 */
-	if (dev->ctrl.state != NVME_CTRL_CONNECTING) {
+	if (nvme_ctrl_state(&dev->ctrl) != NVME_CTRL_CONNECTING) {
 		mutex_unlock(&dev->shutdown_lock);
 		return -ENODEV;
 	}
@@ -2573,13 +2573,13 @@ static bool nvme_pci_ctrl_is_dead(struct nvme_dev *dev)
 
 static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 {
+	enum nvme_ctrl_state state = nvme_ctrl_state(&dev->ctrl);
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 	bool dead;
 
 	mutex_lock(&dev->shutdown_lock);
 	dead = nvme_pci_ctrl_is_dead(dev);
-	if (dev->ctrl.state == NVME_CTRL_LIVE ||
-	    dev->ctrl.state == NVME_CTRL_RESETTING) {
+	if (state == NVME_CTRL_LIVE || state == NVME_CTRL_RESETTING) {
 		if (pci_is_enabled(pdev))
 			nvme_start_freeze(&dev->ctrl);
 		/*
@@ -2690,7 +2690,7 @@ static void nvme_reset_work(struct work_struct *work)
 	bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL);
 	int result;
 
-	if (dev->ctrl.state != NVME_CTRL_RESETTING) {
+	if (nvme_ctrl_state(&dev->ctrl) != NVME_CTRL_RESETTING) {
 		dev_warn(dev->ctrl.device, "ctrl state %d is not RESETTING\n",
 			 dev->ctrl.state);
 		result = -ENODEV;
@@ -2902,6 +2902,18 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
 		if ((dmi_match(DMI_BOARD_VENDOR, "LENOVO")) &&
 		     dmi_match(DMI_BOARD_NAME, "LNVNB161216"))
 			return NVME_QUIRK_SIMPLE_SUSPEND;
+	} else if (pdev->vendor == 0x2646 && (pdev->device == 0x2263 ||
+		   pdev->device == 0x500f)) {
+		/*
+		 * Exclude some Kingston NV1 and A2000 devices from
+		 * NVME_QUIRK_SIMPLE_SUSPEND. Do a full suspend to save a
+		 * lot fo energy with s2idle sleep on some TUXEDO platforms.
+		 */
+		if (dmi_match(DMI_BOARD_NAME, "NS5X_NS7XAU") ||
+		    dmi_match(DMI_BOARD_NAME, "NS5x_7xAU") ||
+		    dmi_match(DMI_BOARD_NAME, "NS5x_7xPU") ||
+		    dmi_match(DMI_BOARD_NAME, "PH4PRX1_PH6PRX1"))
+			return NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND;
 	}
 
 	return 0;
@@ -2932,7 +2944,9 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev,
 	dev->dev = get_device(&pdev->dev);
 
 	quirks |= check_vendor_combination_bug(pdev);
-	if (!noacpi && acpi_storage_d3(&pdev->dev)) {
+	if (!noacpi &&
+	    !(quirks & NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND) &&
+	    acpi_storage_d3(&pdev->dev)) {
 		/*
 		 * Some systems use a bios work around to ask for D3 on
 		 * platforms that support kernel managed suspend.
@@ -3192,7 +3206,7 @@ static int nvme_suspend(struct device *dev)
 	nvme_wait_freeze(ctrl);
 	nvme_sync_queues(ctrl);
 
-	if (ctrl->state != NVME_CTRL_LIVE)
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE)
 		goto unfreeze;
 
 	/*
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index a7fea4cbacd7..c89503da24d7 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -984,10 +984,11 @@ free_ctrl:
 
 static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl)
 {
+	enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl);
+
 	/* If we are resetting/deleting then do nothing */
-	if (ctrl->ctrl.state != NVME_CTRL_CONNECTING) {
-		WARN_ON_ONCE(ctrl->ctrl.state == NVME_CTRL_NEW ||
-			ctrl->ctrl.state == NVME_CTRL_LIVE);
+	if (state != NVME_CTRL_CONNECTING) {
+		WARN_ON_ONCE(state == NVME_CTRL_NEW || state == NVME_CTRL_LIVE);
 		return;
 	}
 
@@ -1059,8 +1060,10 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
 		 * unless we're during creation of a new controller to
 		 * avoid races with teardown flow.
 		 */
-		WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING &&
-			     ctrl->ctrl.state != NVME_CTRL_DELETING_NOIO);
+		enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl);
+
+		WARN_ON_ONCE(state != NVME_CTRL_DELETING &&
+			     state != NVME_CTRL_DELETING_NOIO);
 		WARN_ON_ONCE(new);
 		ret = -EINVAL;
 		goto destroy_io;
@@ -1080,6 +1083,7 @@ destroy_io:
 		nvme_rdma_free_io_queues(ctrl);
 	}
 destroy_admin:
+	nvme_stop_keep_alive(&ctrl->ctrl);
 	nvme_quiesce_admin_queue(&ctrl->ctrl);
 	blk_sync_queue(ctrl->ctrl.admin_q);
 	nvme_rdma_stop_queue(&ctrl->queues[0]);
@@ -1128,8 +1132,10 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
 
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
 		/* state change failure is ok if we started ctrl delete */
-		WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING &&
-			     ctrl->ctrl.state != NVME_CTRL_DELETING_NOIO);
+		enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl);
+
+		WARN_ON_ONCE(state != NVME_CTRL_DELETING &&
+			     state != NVME_CTRL_DELETING_NOIO);
 		return;
 	}
 
@@ -1161,7 +1167,7 @@ static void nvme_rdma_wr_error(struct ib_cq *cq, struct ib_wc *wc,
 	struct nvme_rdma_queue *queue = wc->qp->qp_context;
 	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
 
-	if (ctrl->ctrl.state == NVME_CTRL_LIVE)
+	if (nvme_ctrl_state(&ctrl->ctrl) == NVME_CTRL_LIVE)
 		dev_info(ctrl->ctrl.device,
 			     "%s for CQE 0x%p failed with status %s (%d)\n",
 			     op, wc->wr_cqe,
@@ -1417,7 +1423,7 @@ static int nvme_rdma_map_sg_pi(struct nvme_rdma_queue *queue,
 		goto mr_put;
 
 	nvme_rdma_set_sig_attrs(blk_get_integrity(bio->bi_bdev->bd_disk), c,
-				req->mr->sig_attrs, ns->pi_type);
+				req->mr->sig_attrs, ns->head->pi_type);
 	nvme_rdma_set_prot_checks(c, &req->mr->sig_attrs->check_mask);
 
 	ib_update_fast_reg_key(req->mr, ib_inc_rkey(req->mr->rkey));
@@ -1944,7 +1950,7 @@ static enum blk_eh_timer_return nvme_rdma_timeout(struct request *rq)
 	dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n",
 		 rq->tag, nvme_rdma_queue_idx(queue));
 
-	if (ctrl->ctrl.state != NVME_CTRL_LIVE) {
+	if (nvme_ctrl_state(&ctrl->ctrl) != NVME_CTRL_LIVE) {
 		/*
 		 * If we are resetting, connecting or deleting we should
 		 * complete immediately because we may block controller
@@ -2011,7 +2017,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 	    queue->pi_support &&
 	    (c->common.opcode == nvme_cmd_write ||
 	     c->common.opcode == nvme_cmd_read) &&
-	    nvme_ns_has_pi(ns))
+	    nvme_ns_has_pi(ns->head))
 		req->use_sig_mr = true;
 	else
 		req->use_sig_mr = false;
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index c6b7fbd4d34d..ac24ad102380 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -114,12 +114,97 @@ static ssize_t nsid_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(nsid);
 
-static struct attribute *nvme_ns_id_attrs[] = {
+static ssize_t csi_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	return sysfs_emit(buf, "%u\n", dev_to_ns_head(dev)->ids.csi);
+}
+static DEVICE_ATTR_RO(csi);
+
+static ssize_t metadata_bytes_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%u\n", dev_to_ns_head(dev)->ms);
+}
+static DEVICE_ATTR_RO(metadata_bytes);
+
+static int ns_head_update_nuse(struct nvme_ns_head *head)
+{
+	struct nvme_id_ns *id;
+	struct nvme_ns *ns;
+	int srcu_idx, ret = -EWOULDBLOCK;
+
+	/* Avoid issuing commands too often by rate limiting the update */
+	if (!__ratelimit(&head->rs_nuse))
+		return 0;
+
+	srcu_idx = srcu_read_lock(&head->srcu);
+	ns = nvme_find_path(head);
+	if (!ns)
+		goto out_unlock;
+
+	ret = nvme_identify_ns(ns->ctrl, head->ns_id, &id);
+	if (ret)
+		goto out_unlock;
+
+	head->nuse = le64_to_cpu(id->nuse);
+	kfree(id);
+
+out_unlock:
+	srcu_read_unlock(&head->srcu, srcu_idx);
+	return ret;
+}
+
+static int ns_update_nuse(struct nvme_ns *ns)
+{
+	struct nvme_id_ns *id;
+	int ret;
+
+	/* Avoid issuing commands too often by rate limiting the update. */
+	if (!__ratelimit(&ns->head->rs_nuse))
+		return 0;
+
+	ret = nvme_identify_ns(ns->ctrl, ns->head->ns_id, &id);
+	if (ret)
+		goto out_free_id;
+
+	ns->head->nuse = le64_to_cpu(id->nuse);
+
+out_free_id:
+	kfree(id);
+
+	return ret;
+}
+
+static ssize_t nuse_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	struct nvme_ns_head *head = dev_to_ns_head(dev);
+	struct gendisk *disk = dev_to_disk(dev);
+	struct block_device *bdev = disk->part0;
+	int ret;
+
+	if (IS_ENABLED(CONFIG_NVME_MULTIPATH) &&
+	    bdev->bd_disk->fops == &nvme_ns_head_ops)
+		ret = ns_head_update_nuse(head);
+	else
+		ret = ns_update_nuse(bdev->bd_disk->private_data);
+	if (ret)
+		return ret;
+
+	return sysfs_emit(buf, "%llu\n", head->nuse);
+}
+static DEVICE_ATTR_RO(nuse);
+
+static struct attribute *nvme_ns_attrs[] = {
 	&dev_attr_wwid.attr,
 	&dev_attr_uuid.attr,
 	&dev_attr_nguid.attr,
 	&dev_attr_eui.attr,
+	&dev_attr_csi.attr,
 	&dev_attr_nsid.attr,
+	&dev_attr_metadata_bytes.attr,
+	&dev_attr_nuse.attr,
 #ifdef CONFIG_NVME_MULTIPATH
 	&dev_attr_ana_grpid.attr,
 	&dev_attr_ana_state.attr,
@@ -127,7 +212,7 @@ static struct attribute *nvme_ns_id_attrs[] = {
 	NULL,
 };
 
-static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj,
+static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj,
 		struct attribute *a, int n)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
@@ -157,13 +242,13 @@ static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj,
 	return a->mode;
 }
 
-static const struct attribute_group nvme_ns_id_attr_group = {
-	.attrs		= nvme_ns_id_attrs,
-	.is_visible	= nvme_ns_id_attrs_are_visible,
+static const struct attribute_group nvme_ns_attr_group = {
+	.attrs		= nvme_ns_attrs,
+	.is_visible	= nvme_ns_attrs_are_visible,
 };
 
-const struct attribute_group *nvme_ns_id_attr_groups[] = {
-	&nvme_ns_id_attr_group,
+const struct attribute_group *nvme_ns_attr_groups[] = {
+	&nvme_ns_attr_group,
 	NULL,
 };
 
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 89661a9cf850..08805f027810 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -36,11 +36,11 @@ static int so_priority;
 module_param(so_priority, int, 0644);
 MODULE_PARM_DESC(so_priority, "nvme tcp socket optimize priority");
 
-#ifdef CONFIG_NVME_TCP_TLS
 /*
  * TLS handshake timeout
  */
 static int tls_handshake_timeout = 10;
+#ifdef CONFIG_NVME_TCP_TLS
 module_param(tls_handshake_timeout, int, 0644);
 MODULE_PARM_DESC(tls_handshake_timeout,
 		 "nvme TLS handshake timeout in seconds (default 10)");
@@ -161,10 +161,8 @@ struct nvme_tcp_queue {
 	struct ahash_request	*snd_hash;
 	__le32			exp_ddgst;
 	__le32			recv_ddgst;
-#ifdef CONFIG_NVME_TCP_TLS
 	struct completion       tls_complete;
 	int                     tls_err;
-#endif
 	struct page_frag_cache	pf_cache;
 
 	void (*state_change)(struct sock *);
@@ -207,6 +205,14 @@ static inline int nvme_tcp_queue_id(struct nvme_tcp_queue *queue)
 	return queue - queue->ctrl->queues;
 }
 
+static inline bool nvme_tcp_tls(struct nvme_ctrl *ctrl)
+{
+	if (!IS_ENABLED(CONFIG_NVME_TCP_TLS))
+		return 0;
+
+	return ctrl->opts->tls;
+}
+
 static inline struct blk_mq_tags *nvme_tcp_tagset(struct nvme_tcp_queue *queue)
 {
 	u32 queue_idx = nvme_tcp_queue_id(queue);
@@ -1412,7 +1418,7 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue)
 	memset(&msg, 0, sizeof(msg));
 	iov.iov_base = icresp;
 	iov.iov_len = sizeof(*icresp);
-	if (queue->ctrl->ctrl.opts->tls) {
+	if (nvme_tcp_tls(&queue->ctrl->ctrl)) {
 		msg.msg_control = cbuf;
 		msg.msg_controllen = sizeof(cbuf);
 	}
@@ -1424,7 +1430,7 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue)
 		goto free_icresp;
 	}
 	ret = -ENOTCONN;
-	if (queue->ctrl->ctrl.opts->tls) {
+	if (nvme_tcp_tls(&queue->ctrl->ctrl)) {
 		ctype = tls_get_record_type(queue->sock->sk,
 					    (struct cmsghdr *)cbuf);
 		if (ctype != TLS_RECORD_TYPE_DATA) {
@@ -1548,7 +1554,6 @@ static void nvme_tcp_set_queue_io_cpu(struct nvme_tcp_queue *queue)
 	queue->io_cpu = cpumask_next_wrap(n - 1, cpu_online_mask, -1, false);
 }
 
-#ifdef CONFIG_NVME_TCP_TLS
 static void nvme_tcp_tls_done(void *data, int status, key_serial_t pskid)
 {
 	struct nvme_tcp_queue *queue = data;
@@ -1625,14 +1630,6 @@ static int nvme_tcp_start_tls(struct nvme_ctrl *nctrl,
 	}
 	return ret;
 }
-#else
-static int nvme_tcp_start_tls(struct nvme_ctrl *nctrl,
-			      struct nvme_tcp_queue *queue,
-			      key_serial_t pskid)
-{
-	return -EPROTONOSUPPORT;
-}
-#endif
 
 static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid,
 				key_serial_t pskid)
@@ -1759,7 +1756,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid,
 	}
 
 	/* If PSKs are configured try to start TLS */
-	if (pskid) {
+	if (IS_ENABLED(CONFIG_NVME_TCP_TLS) && pskid) {
 		ret = nvme_tcp_start_tls(nctrl, queue, pskid);
 		if (ret)
 			goto err_init_connect;
@@ -1916,7 +1913,7 @@ static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl)
 	int ret;
 	key_serial_t pskid = 0;
 
-	if (ctrl->opts->tls) {
+	if (nvme_tcp_tls(ctrl)) {
 		if (ctrl->opts->tls_key)
 			pskid = key_serial(ctrl->opts->tls_key);
 		else
@@ -1949,7 +1946,7 @@ static int __nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
 {
 	int i, ret;
 
-	if (ctrl->opts->tls && !ctrl->tls_key) {
+	if (nvme_tcp_tls(ctrl) && !ctrl->tls_key) {
 		dev_err(ctrl->device, "no PSK negotiated\n");
 		return -ENOKEY;
 	}
@@ -2155,10 +2152,11 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 
 static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl)
 {
+	enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
+
 	/* If we are resetting/deleting then do nothing */
-	if (ctrl->state != NVME_CTRL_CONNECTING) {
-		WARN_ON_ONCE(ctrl->state == NVME_CTRL_NEW ||
-			ctrl->state == NVME_CTRL_LIVE);
+	if (state != NVME_CTRL_CONNECTING) {
+		WARN_ON_ONCE(state == NVME_CTRL_NEW || state == NVME_CTRL_LIVE);
 		return;
 	}
 
@@ -2218,8 +2216,10 @@ static int nvme_tcp_setup_ctrl(struct nvme_ctrl *ctrl, bool new)
 		 * unless we're during creation of a new controller to
 		 * avoid races with teardown flow.
 		 */
-		WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING &&
-			     ctrl->state != NVME_CTRL_DELETING_NOIO);
+		enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
+
+		WARN_ON_ONCE(state != NVME_CTRL_DELETING &&
+			     state != NVME_CTRL_DELETING_NOIO);
 		WARN_ON_ONCE(new);
 		ret = -EINVAL;
 		goto destroy_io;
@@ -2237,6 +2237,7 @@ destroy_io:
 		nvme_tcp_destroy_io_queues(ctrl, new);
 	}
 destroy_admin:
+	nvme_stop_keep_alive(ctrl);
 	nvme_tcp_teardown_admin_queue(ctrl, false);
 	return ret;
 }
@@ -2282,8 +2283,10 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work)
 
 	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING)) {
 		/* state change failure is ok if we started ctrl delete */
-		WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING &&
-			     ctrl->state != NVME_CTRL_DELETING_NOIO);
+		enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
+
+		WARN_ON_ONCE(state != NVME_CTRL_DELETING &&
+			     state != NVME_CTRL_DELETING_NOIO);
 		return;
 	}
 
@@ -2313,8 +2316,10 @@ static void nvme_reset_ctrl_work(struct work_struct *work)
 
 	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING)) {
 		/* state change failure is ok if we started ctrl delete */
-		WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING &&
-			     ctrl->state != NVME_CTRL_DELETING_NOIO);
+		enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
+
+		WARN_ON_ONCE(state != NVME_CTRL_DELETING &&
+			     state != NVME_CTRL_DELETING_NOIO);
 		return;
 	}
 
@@ -2432,7 +2437,7 @@ static enum blk_eh_timer_return nvme_tcp_timeout(struct request *rq)
 		nvme_tcp_queue_id(req->queue), nvme_cid(rq), pdu->hdr.type,
 		opc, nvme_opcode_str(qid, opc, fctype));
 
-	if (ctrl->state != NVME_CTRL_LIVE) {
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE) {
 		/*
 		 * If we are resetting, connecting or deleting we should
 		 * complete immediately because we may block controller
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index ec8557810c21..499bbb0eee8d 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -11,7 +11,7 @@ int nvme_revalidate_zones(struct nvme_ns *ns)
 {
 	struct request_queue *q = ns->queue;
 
-	blk_queue_chunk_sectors(q, ns->zsze);
+	blk_queue_chunk_sectors(q, ns->head->zsze);
 	blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append);
 
 	return blk_revalidate_disk_zones(ns->disk, NULL);
@@ -99,16 +99,17 @@ int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
 		goto free_data;
 	}
 
-	ns->zsze = nvme_lba_to_sect(ns, le64_to_cpu(id->lbafe[lbaf].zsze));
-	if (!is_power_of_2(ns->zsze)) {
+	ns->head->zsze =
+		nvme_lba_to_sect(ns->head, le64_to_cpu(id->lbafe[lbaf].zsze));
+	if (!is_power_of_2(ns->head->zsze)) {
 		dev_warn(ns->ctrl->device,
 			"invalid zone size:%llu for namespace:%u\n",
-			ns->zsze, ns->head->ns_id);
+			ns->head->zsze, ns->head->ns_id);
 		status = -ENODEV;
 		goto free_data;
 	}
 
-	disk_set_zoned(ns->disk, BLK_ZONED_HM);
+	disk_set_zoned(ns->disk);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 	disk_set_max_open_zones(ns->disk, le32_to_cpu(id->mor) + 1);
 	disk_set_max_active_zones(ns->disk, le32_to_cpu(id->mar) + 1);
@@ -128,7 +129,7 @@ static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns,
 				   sizeof(struct nvme_zone_descriptor);
 
 	nr_zones = min_t(unsigned int, nr_zones,
-			 get_capacity(ns->disk) >> ilog2(ns->zsze));
+			 get_capacity(ns->disk) >> ilog2(ns->head->zsze));
 
 	bufsize = sizeof(struct nvme_zone_report) +
 		nr_zones * sizeof(struct nvme_zone_descriptor);
@@ -147,7 +148,8 @@ static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns,
 	return NULL;
 }
 
-static int nvme_zone_parse_entry(struct nvme_ns *ns,
+static int nvme_zone_parse_entry(struct nvme_ctrl *ctrl,
+				 struct nvme_ns_head *head,
 				 struct nvme_zone_descriptor *entry,
 				 unsigned int idx, report_zones_cb cb,
 				 void *data)
@@ -155,20 +157,20 @@ static int nvme_zone_parse_entry(struct nvme_ns *ns,
 	struct blk_zone zone = { };
 
 	if ((entry->zt & 0xf) != NVME_ZONE_TYPE_SEQWRITE_REQ) {
-		dev_err(ns->ctrl->device, "invalid zone type %#x\n",
+		dev_err(ctrl->device, "invalid zone type %#x\n",
 				entry->zt);
 		return -EINVAL;
 	}
 
 	zone.type = BLK_ZONE_TYPE_SEQWRITE_REQ;
 	zone.cond = entry->zs >> 4;
-	zone.len = ns->zsze;
-	zone.capacity = nvme_lba_to_sect(ns, le64_to_cpu(entry->zcap));
-	zone.start = nvme_lba_to_sect(ns, le64_to_cpu(entry->zslba));
+	zone.len = head->zsze;
+	zone.capacity = nvme_lba_to_sect(head, le64_to_cpu(entry->zcap));
+	zone.start = nvme_lba_to_sect(head, le64_to_cpu(entry->zslba));
 	if (zone.cond == BLK_ZONE_COND_FULL)
 		zone.wp = zone.start + zone.len;
 	else
-		zone.wp = nvme_lba_to_sect(ns, le64_to_cpu(entry->wp));
+		zone.wp = nvme_lba_to_sect(head, le64_to_cpu(entry->wp));
 
 	return cb(&zone, idx, data);
 }
@@ -196,11 +198,11 @@ int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
 	c.zmr.zrasf = NVME_ZRASF_ZONE_REPORT_ALL;
 	c.zmr.pr = NVME_REPORT_ZONE_PARTIAL;
 
-	sector &= ~(ns->zsze - 1);
+	sector &= ~(ns->head->zsze - 1);
 	while (zone_idx < nr_zones && sector < get_capacity(ns->disk)) {
 		memset(report, 0, buflen);
 
-		c.zmr.slba = cpu_to_le64(nvme_sect_to_lba(ns, sector));
+		c.zmr.slba = cpu_to_le64(nvme_sect_to_lba(ns->head, sector));
 		ret = nvme_submit_sync_cmd(ns->queue, &c, report, buflen);
 		if (ret) {
 			if (ret > 0)
@@ -213,14 +215,15 @@ int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
 			break;
 
 		for (i = 0; i < nz && zone_idx < nr_zones; i++) {
-			ret = nvme_zone_parse_entry(ns, &report->entries[i],
+			ret = nvme_zone_parse_entry(ns->ctrl, ns->head,
+						    &report->entries[i],
 						    zone_idx, cb, data);
 			if (ret)
 				goto out_free;
 			zone_idx++;
 		}
 
-		sector += ns->zsze * nz;
+		sector += ns->head->zsze * nz;
 	}
 
 	if (zone_idx > 0)
@@ -239,7 +242,7 @@ blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
 
 	c->zms.opcode = nvme_cmd_zone_mgmt_send;
 	c->zms.nsid = cpu_to_le32(ns->head->ns_id);
-	c->zms.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
+	c->zms.slba = cpu_to_le64(nvme_sect_to_lba(ns->head, blk_rq_pos(req)));
 	c->zms.zsa = action;
 
 	if (req_op(req) == REQ_OP_ZONE_RESET_ALL)
diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig
index 31633da9427c..872dd1a0acd8 100644
--- a/drivers/nvme/target/Kconfig
+++ b/drivers/nvme/target/Kconfig
@@ -4,6 +4,8 @@ config NVME_TARGET
 	tristate "NVMe Target support"
 	depends on BLOCK
 	depends on CONFIGFS_FS
+	select NVME_KEYRING if NVME_TARGET_TCP_TLS
+	select KEYS if NVME_TARGET_TCP_TLS
 	select BLK_DEV_INTEGRITY_T10 if BLK_DEV_INTEGRITY
 	select SGL_ALLOC
 	help
@@ -87,9 +89,7 @@ config NVME_TARGET_TCP
 config NVME_TARGET_TCP_TLS
 	bool "NVMe over Fabrics TCP target TLS encryption support"
 	depends on NVME_TARGET_TCP
-	select NVME_KEYRING
 	select NET_HANDSHAKE
-	select KEYS
 	help
 	  Enables TLS encryption for the NVMe TCP target using the netlink handshake API.
 
@@ -99,10 +99,11 @@ config NVME_TARGET_TCP_TLS
 	  If unsure, say N.
 
 config NVME_TARGET_AUTH
-	bool "NVMe over Fabrics In-band Authentication support"
+	bool "NVMe over Fabrics In-band Authentication in target side"
 	depends on NVME_TARGET
 	select NVME_AUTH
 	help
-	  This enables support for NVMe over Fabrics In-band Authentication
+	  This enables support for NVMe over Fabrics In-band Authentication in
+	  target side.
 
 	  If unsure, say N.
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index 9eed6e6765ea..2482a0db2504 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -18,6 +18,7 @@
 #include <linux/nvme-keyring.h>
 #include <crypto/hash.h>
 #include <crypto/kpp.h>
+#include <linux/nospec.h>
 
 #include "nvmet.h"
 
@@ -621,6 +622,7 @@ static ssize_t nvmet_ns_ana_grpid_store(struct config_item *item,
 
 	down_write(&nvmet_ana_sem);
 	oldgrpid = ns->anagrpid;
+	newgrpid = array_index_nospec(newgrpid, NVMET_MAX_ANAGRPS);
 	nvmet_ana_group_enabled[newgrpid]++;
 	ns->anagrpid = newgrpid;
 	nvmet_ana_group_enabled[oldgrpid]--;
@@ -1274,7 +1276,7 @@ static ssize_t nvmet_subsys_attr_cntlid_min_store(struct config_item *item,
 		return -EINVAL;
 
 	down_write(&nvmet_config_sem);
-	if (cntlid_min >= to_subsys(item)->cntlid_max)
+	if (cntlid_min > to_subsys(item)->cntlid_max)
 		goto out_unlock;
 	to_subsys(item)->cntlid_min = cntlid_min;
 	up_write(&nvmet_config_sem);
@@ -1304,7 +1306,7 @@ static ssize_t nvmet_subsys_attr_cntlid_max_store(struct config_item *item,
 		return -EINVAL;
 
 	down_write(&nvmet_config_sem);
-	if (cntlid_max <= to_subsys(item)->cntlid_min)
+	if (cntlid_max < to_subsys(item)->cntlid_min)
 		goto out_unlock;
 	to_subsys(item)->cntlid_max = cntlid_max;
 	up_write(&nvmet_config_sem);
@@ -1812,6 +1814,7 @@ static struct config_group *nvmet_ana_groups_make_group(
 	grp->grpid = grpid;
 
 	down_write(&nvmet_ana_sem);
+	grpid = array_index_nospec(grpid, NVMET_MAX_ANAGRPS);
 	nvmet_ana_group_enabled[grpid]++;
 	up_write(&nvmet_ana_sem);
 
@@ -1893,7 +1896,7 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	if (nvme_keyring_id()) {
+	if (IS_ENABLED(CONFIG_NVME_TARGET_TCP_TLS) && nvme_keyring_id()) {
 		port->keyring = key_lookup(nvme_keyring_id());
 		if (IS_ERR(port->keyring)) {
 			pr_warn("NVMe keyring not available, disabling TLS\n");
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 3935165048e7..d26aa30f8702 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -1425,9 +1425,6 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 	if (!ctrl->sqs)
 		goto out_free_changed_ns_list;
 
-	if (subsys->cntlid_min > subsys->cntlid_max)
-		goto out_free_sqs;
-
 	ret = ida_alloc_range(&cntlid_ida,
 			     subsys->cntlid_min, subsys->cntlid_max,
 			     GFP_KERNEL);
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index 43b5bd8bb6a5..d8da840a1c0e 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -244,6 +244,8 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
 		goto out;
 	}
 
+	d->subsysnqn[NVMF_NQN_FIELD_LEN - 1] = '\0';
+	d->hostnqn[NVMF_NQN_FIELD_LEN - 1] = '\0';
 	status = nvmet_alloc_ctrl(d->subsysnqn, d->hostnqn, req,
 				  le32_to_cpu(c->kato), &ctrl);
 	if (status)
@@ -313,6 +315,8 @@ static void nvmet_execute_io_connect(struct nvmet_req *req)
 		goto out;
 	}
 
+	d->subsysnqn[NVMF_NQN_FIELD_LEN - 1] = '\0';
+	d->hostnqn[NVMF_NQN_FIELD_LEN - 1] = '\0';
 	ctrl = nvmet_ctrl_find_get(d->subsysnqn, d->hostnqn,
 				   le16_to_cpu(d->cntlid), req);
 	if (!ctrl) {
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
index 9fe07d7efa96..f2d963e1fe94 100644
--- a/drivers/nvme/target/passthru.c
+++ b/drivers/nvme/target/passthru.c
@@ -602,7 +602,7 @@ int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys)
 		goto out_put_file;
 	}
 
-	old = xa_cmpxchg(&passthru_subsystems, ctrl->cntlid, NULL,
+	old = xa_cmpxchg(&passthru_subsystems, ctrl->instance, NULL,
 			 subsys, GFP_KERNEL);
 	if (xa_is_err(old)) {
 		ret = xa_err(old);
@@ -635,7 +635,7 @@ out_unlock:
 static void __nvmet_passthru_ctrl_disable(struct nvmet_subsys *subsys)
 {
 	if (subsys->passthru_ctrl) {
-		xa_erase(&passthru_subsystems, subsys->passthru_ctrl->cntlid);
+		xa_erase(&passthru_subsystems, subsys->passthru_ctrl->instance);
 		module_put(subsys->passthru_ctrl->ops->module);
 		nvme_put_ctrl(subsys->passthru_ctrl);
 	}
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 92b74d0b8686..4cc27856aa8f 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -1854,6 +1854,8 @@ static int nvmet_tcp_tls_handshake(struct nvmet_tcp_queue *queue)
 	}
 	return ret;
 }
+#else
+static void nvmet_tcp_tls_handshake_timeout(struct work_struct *w) {}
 #endif
 
 static void nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
@@ -1911,9 +1913,9 @@ static void nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
 	list_add_tail(&queue->queue_list, &nvmet_tcp_queue_list);
 	mutex_unlock(&nvmet_tcp_queue_mutex);
 
-#ifdef CONFIG_NVME_TARGET_TCP_TLS
 	INIT_DELAYED_WORK(&queue->tls_handshake_tmo_work,
 			  nvmet_tcp_tls_handshake_timeout);
+#ifdef CONFIG_NVME_TARGET_TCP_TLS
 	if (queue->state == NVMET_TCP_Q_TLS_HANDSHAKE) {
 		struct sock *sk = queue->sock->sk;
 
diff --git a/drivers/nvmem/brcm_nvram.c b/drivers/nvmem/brcm_nvram.c
index 9737104f3b76..5cdf339cfbec 100644
--- a/drivers/nvmem/brcm_nvram.c
+++ b/drivers/nvmem/brcm_nvram.c
@@ -17,9 +17,23 @@
 
 #define NVRAM_MAGIC			"FLSH"
 
+/**
+ * struct brcm_nvram - driver state internal struct
+ *
+ * @dev:		NVMEM device pointer
+ * @nvmem_size:		Size of the whole space available for NVRAM
+ * @data:		NVRAM data copy stored to avoid poking underlaying flash controller
+ * @data_len:		NVRAM data size
+ * @padding_byte:	Padding value used to fill remaining space
+ * @cells:		Array of discovered NVMEM cells
+ * @ncells:		Number of elements in cells
+ */
 struct brcm_nvram {
 	struct device *dev;
-	void __iomem *base;
+	size_t nvmem_size;
+	uint8_t *data;
+	size_t data_len;
+	uint8_t padding_byte;
 	struct nvmem_cell_info *cells;
 	int ncells;
 };
@@ -36,10 +50,47 @@ static int brcm_nvram_read(void *context, unsigned int offset, void *val,
 			   size_t bytes)
 {
 	struct brcm_nvram *priv = context;
-	u8 *dst = val;
+	size_t to_copy;
+
+	if (offset + bytes > priv->data_len)
+		to_copy = max_t(ssize_t, (ssize_t)priv->data_len - offset, 0);
+	else
+		to_copy = bytes;
+
+	memcpy(val, priv->data + offset, to_copy);
+
+	memset((uint8_t *)val + to_copy, priv->padding_byte, bytes - to_copy);
+
+	return 0;
+}
+
+static int brcm_nvram_copy_data(struct brcm_nvram *priv, struct platform_device *pdev)
+{
+	struct resource *res;
+	void __iomem *base;
+
+	base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	priv->nvmem_size = resource_size(res);
+
+	priv->padding_byte = readb(base + priv->nvmem_size - 1);
+	for (priv->data_len = priv->nvmem_size;
+	     priv->data_len;
+	     priv->data_len--) {
+		if (readb(base + priv->data_len - 1) != priv->padding_byte)
+			break;
+	}
+	WARN(priv->data_len > SZ_128K, "Unexpected (big) NVRAM size: %zu B\n", priv->data_len);
+
+	priv->data = devm_kzalloc(priv->dev, priv->data_len, GFP_KERNEL);
+	if (!priv->data)
+		return -ENOMEM;
+
+	memcpy_fromio(priv->data, base, priv->data_len);
 
-	while (bytes--)
-		*dst++ = readb(priv->base + offset++);
+	bcm47xx_nvram_init_from_iomem(base, priv->data_len);
 
 	return 0;
 }
@@ -67,8 +118,13 @@ static int brcm_nvram_add_cells(struct brcm_nvram *priv, uint8_t *data,
 				size_t len)
 {
 	struct device *dev = priv->dev;
-	char *var, *value, *eq;
+	char *var, *value;
+	uint8_t tmp;
 	int idx;
+	int err = 0;
+
+	tmp = priv->data[len - 1];
+	priv->data[len - 1] = '\0';
 
 	priv->ncells = 0;
 	for (var = data + sizeof(struct brcm_nvram_header);
@@ -78,67 +134,68 @@ static int brcm_nvram_add_cells(struct brcm_nvram *priv, uint8_t *data,
 	}
 
 	priv->cells = devm_kcalloc(dev, priv->ncells, sizeof(*priv->cells), GFP_KERNEL);
-	if (!priv->cells)
-		return -ENOMEM;
+	if (!priv->cells) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	for (var = data + sizeof(struct brcm_nvram_header), idx = 0;
 	     var < (char *)data + len && *var;
 	     var = value + strlen(value) + 1, idx++) {
+		char *eq, *name;
+
 		eq = strchr(var, '=');
 		if (!eq)
 			break;
 		*eq = '\0';
+		name = devm_kstrdup(dev, var, GFP_KERNEL);
+		*eq = '=';
+		if (!name) {
+			err = -ENOMEM;
+			goto out;
+		}
 		value = eq + 1;
 
-		priv->cells[idx].name = devm_kstrdup(dev, var, GFP_KERNEL);
-		if (!priv->cells[idx].name)
-			return -ENOMEM;
+		priv->cells[idx].name = name;
 		priv->cells[idx].offset = value - (char *)data;
 		priv->cells[idx].bytes = strlen(value);
 		priv->cells[idx].np = of_get_child_by_name(dev->of_node, priv->cells[idx].name);
-		if (!strcmp(var, "et0macaddr") ||
-		    !strcmp(var, "et1macaddr") ||
-		    !strcmp(var, "et2macaddr")) {
+		if (!strcmp(name, "et0macaddr") ||
+		    !strcmp(name, "et1macaddr") ||
+		    !strcmp(name, "et2macaddr")) {
 			priv->cells[idx].raw_len = strlen(value);
 			priv->cells[idx].bytes = ETH_ALEN;
 			priv->cells[idx].read_post_process = brcm_nvram_read_post_process_macaddr;
 		}
 	}
 
-	return 0;
+out:
+	priv->data[len - 1] = tmp;
+	return err;
 }
 
 static int brcm_nvram_parse(struct brcm_nvram *priv)
 {
+	struct brcm_nvram_header *header = (struct brcm_nvram_header *)priv->data;
 	struct device *dev = priv->dev;
-	struct brcm_nvram_header header;
-	uint8_t *data;
 	size_t len;
 	int err;
 
-	memcpy_fromio(&header, priv->base, sizeof(header));
-
-	if (memcmp(header.magic, NVRAM_MAGIC, 4)) {
+	if (memcmp(header->magic, NVRAM_MAGIC, 4)) {
 		dev_err(dev, "Invalid NVRAM magic\n");
 		return -EINVAL;
 	}
 
-	len = le32_to_cpu(header.len);
-
-	data = kzalloc(len, GFP_KERNEL);
-	if (!data)
-		return -ENOMEM;
-
-	memcpy_fromio(data, priv->base, len);
-	data[len - 1] = '\0';
-
-	err = brcm_nvram_add_cells(priv, data, len);
-	if (err) {
-		dev_err(dev, "Failed to add cells: %d\n", err);
-		return err;
+	len = le32_to_cpu(header->len);
+	if (len > priv->nvmem_size) {
+		dev_err(dev, "NVRAM length (%zd) exceeds mapped size (%zd)\n", len,
+			priv->nvmem_size);
+		return -EINVAL;
 	}
 
-	kfree(data);
+	err = brcm_nvram_add_cells(priv, priv->data, len);
+	if (err)
+		dev_err(dev, "Failed to add cells: %d\n", err);
 
 	return 0;
 }
@@ -150,7 +207,6 @@ static int brcm_nvram_probe(struct platform_device *pdev)
 		.reg_read = brcm_nvram_read,
 	};
 	struct device *dev = &pdev->dev;
-	struct resource *res;
 	struct brcm_nvram *priv;
 	int err;
 
@@ -159,21 +215,19 @@ static int brcm_nvram_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	priv->dev = dev;
 
-	priv->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
-	if (IS_ERR(priv->base))
-		return PTR_ERR(priv->base);
+	err = brcm_nvram_copy_data(priv, pdev);
+	if (err)
+		return err;
 
 	err = brcm_nvram_parse(priv);
 	if (err)
 		return err;
 
-	bcm47xx_nvram_init_from_iomem(priv->base, resource_size(res));
-
 	config.dev = dev;
 	config.cells = priv->cells;
 	config.ncells = priv->ncells;
 	config.priv = priv;
-	config.size = resource_size(res);
+	config.size = priv->nvmem_size;
 
 	return PTR_ERR_OR_ZERO(devm_nvmem_register(dev, &config));
 }
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index bf42b7e826db..608b352a7d91 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -796,6 +796,12 @@ static struct nvmem_layout *nvmem_layout_get(struct nvmem_device *nvmem)
 	if (!layout_np)
 		return NULL;
 
+	/* Fixed layouts don't have a matching driver */
+	if (of_device_is_compatible(layout_np, "fixed-layout")) {
+		of_node_put(layout_np);
+		return NULL;
+	}
+
 	/*
 	 * In case the nvmem device was built-in while the layout was built as a
 	 * module, we shall manually request the layout driver loading otherwise
diff --git a/drivers/of/address.c b/drivers/of/address.c
index b59956310f66..ae46a3605904 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -955,7 +955,6 @@ int of_dma_get_range(struct device_node *np, const struct bus_dma_region **map)
 		r->cpu_start = range.cpu_addr;
 		r->dma_start = range.bus_addr;
 		r->size = range.size;
-		r->offset = range.cpu_addr - range.bus_addr;
 		r++;
 	}
 out:
diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c
index f63250c650ca..3bf27052832f 100644
--- a/drivers/of/dynamic.c
+++ b/drivers/of/dynamic.c
@@ -98,8 +98,9 @@ int of_reconfig_notify(unsigned long action, struct of_reconfig_data *p)
  *
  * Returns the new state of a device based on the notifier used.
  *
- * Return: 0 on device going from enabled to disabled, 1 on device
- * going from disabled to enabled and -1 on no change.
+ * Return: OF_RECONFIG_CHANGE_REMOVE on device going from enabled to
+ * disabled, OF_RECONFIG_CHANGE_ADD on device going from disabled to
+ * enabled and OF_RECONFIG_NO_CHANGE on no change.
  */
 int of_reconfig_get_state_change(unsigned long action, struct of_reconfig_data *pr)
 {
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 84f345c69ea5..c4e0432ae42a 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -201,7 +201,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq_indexed);
  * @opp:	opp for which level value has to be returned for
  *
  * Return: level read from device tree corresponding to the opp, else
- * return 0.
+ * return U32_MAX.
  */
 unsigned int dev_pm_opp_get_level(struct dev_pm_opp *opp)
 {
@@ -221,7 +221,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_level);
  * @index:	index of the required opp
  *
  * Return: performance state read from device tree corresponding to the
- * required opp, else return 0.
+ * required opp, else return U32_MAX.
  */
 unsigned int dev_pm_opp_get_required_pstate(struct dev_pm_opp *opp,
 					    unsigned int index)
@@ -808,6 +808,16 @@ struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev,
 	struct dev_pm_opp *opp;
 
 	opp = _find_key_ceil(dev, &temp, 0, true, _read_level, NULL);
+	if (IS_ERR(opp))
+		return opp;
+
+	/* False match */
+	if (temp == OPP_LEVEL_UNSET) {
+		dev_err(dev, "%s: OPP levels aren't available\n", __func__);
+		dev_pm_opp_put(opp);
+		return ERR_PTR(-ENODEV);
+	}
+
 	*level = temp;
 	return opp;
 }
@@ -832,9 +842,14 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_find_level_ceil);
  * use.
  */
 struct dev_pm_opp *dev_pm_opp_find_level_floor(struct device *dev,
-					       unsigned long *level)
+					       unsigned int *level)
 {
-	return _find_key_floor(dev, level, 0, true, _read_level, NULL);
+	unsigned long temp = *level;
+	struct dev_pm_opp *opp;
+
+	opp = _find_key_floor(dev, &temp, 0, true, _read_level, NULL);
+	*level = temp;
+	return opp;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_level_floor);
 
@@ -948,7 +963,7 @@ _opp_config_clk_single(struct device *dev, struct opp_table *opp_table,
 		dev_err(dev, "%s: failed to set clock rate: %d\n", __func__,
 			ret);
 	} else {
-		opp_table->rate_clk_single = freq;
+		opp_table->current_rate_single_clk = freq;
 	}
 
 	return ret;
@@ -1046,40 +1061,23 @@ static int _set_opp_bw(const struct opp_table *opp_table,
 	return 0;
 }
 
-static int _set_performance_state(struct device *dev, struct device *pd_dev,
-				  struct dev_pm_opp *opp, int i)
+/* This is only called for PM domain for now */
+static int _set_required_opps(struct device *dev, struct opp_table *opp_table,
+			      struct dev_pm_opp *opp, bool up)
 {
-	unsigned int pstate = likely(opp) ? opp->required_opps[i]->level: 0;
-	int ret;
+	struct device **devs = opp_table->required_devs;
+	struct dev_pm_opp *required_opp;
+	int index, target, delta, ret;
 
-	if (!pd_dev)
+	if (!devs)
 		return 0;
 
-	ret = dev_pm_domain_set_performance_state(pd_dev, pstate);
-	if (ret) {
-		dev_err(dev, "Failed to set performance state of %s: %d (%d)\n",
-			dev_name(pd_dev), pstate, ret);
-	}
-
-	return ret;
-}
-
-static int _opp_set_required_opps_generic(struct device *dev,
-	struct opp_table *opp_table, struct dev_pm_opp *opp, bool scaling_down)
-{
-	dev_err(dev, "setting required-opps isn't supported for non-genpd devices\n");
-	return -ENOENT;
-}
-
-static int _opp_set_required_opps_genpd(struct device *dev,
-	struct opp_table *opp_table, struct dev_pm_opp *opp, bool scaling_down)
-{
-	struct device **genpd_virt_devs =
-		opp_table->genpd_virt_devs ? opp_table->genpd_virt_devs : &dev;
-	int index, target, delta, ret;
+	/* required-opps not fully initialized yet */
+	if (lazy_linking_pending(opp_table))
+		return -EBUSY;
 
 	/* Scaling up? Set required OPPs in normal order, else reverse */
-	if (!scaling_down) {
+	if (up) {
 		index = 0;
 		target = opp_table->required_opp_count;
 		delta = 1;
@@ -1090,9 +1088,13 @@ static int _opp_set_required_opps_genpd(struct device *dev,
 	}
 
 	while (index != target) {
-		ret = _set_performance_state(dev, genpd_virt_devs[index], opp, index);
-		if (ret)
-			return ret;
+		if (devs[index]) {
+			required_opp = opp ? opp->required_opps[index] : NULL;
+
+			ret = dev_pm_opp_set_opp(devs[index], required_opp);
+			if (ret)
+				return ret;
+		}
 
 		index += delta;
 	}
@@ -1100,34 +1102,6 @@ static int _opp_set_required_opps_genpd(struct device *dev,
 	return 0;
 }
 
-/* This is only called for PM domain for now */
-static int _set_required_opps(struct device *dev, struct opp_table *opp_table,
-			      struct dev_pm_opp *opp, bool up)
-{
-	/* required-opps not fully initialized yet */
-	if (lazy_linking_pending(opp_table))
-		return -EBUSY;
-
-	if (opp_table->set_required_opps)
-		return opp_table->set_required_opps(dev, opp_table, opp, up);
-
-	return 0;
-}
-
-/* Update set_required_opps handler */
-void _update_set_required_opps(struct opp_table *opp_table)
-{
-	/* Already set */
-	if (opp_table->set_required_opps)
-		return;
-
-	/* All required OPPs will belong to genpd or none */
-	if (opp_table->required_opp_tables[0]->is_genpd)
-		opp_table->set_required_opps = _opp_set_required_opps_genpd;
-	else
-		opp_table->set_required_opps = _opp_set_required_opps_generic;
-}
-
 static int _set_opp_level(struct device *dev, struct opp_table *opp_table,
 			  struct dev_pm_opp *opp)
 {
@@ -1135,7 +1109,7 @@ static int _set_opp_level(struct device *dev, struct opp_table *opp_table,
 	int ret = 0;
 
 	if (opp) {
-		if (!opp->level)
+		if (opp->level == OPP_LEVEL_UNSET)
 			return 0;
 
 		level = opp->level;
@@ -1378,12 +1352,12 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 		 * value of the frequency. In such a case, do not abort but
 		 * configure the hardware to the desired frequency forcefully.
 		 */
-		forced = opp_table->rate_clk_single != target_freq;
+		forced = opp_table->current_rate_single_clk != freq;
 	}
 
-	ret = _set_opp(dev, opp_table, opp, &target_freq, forced);
+	ret = _set_opp(dev, opp_table, opp, &freq, forced);
 
-	if (target_freq)
+	if (freq)
 		dev_pm_opp_put(opp);
 
 put_opp_table:
@@ -1867,6 +1841,8 @@ struct dev_pm_opp *_opp_allocate(struct opp_table *opp_table)
 
 	INIT_LIST_HEAD(&opp->node);
 
+	opp->level = OPP_LEVEL_UNSET;
+
 	return opp;
 }
 
@@ -2388,19 +2364,13 @@ static void _opp_detach_genpd(struct opp_table *opp_table)
 {
 	int index;
 
-	if (!opp_table->genpd_virt_devs)
-		return;
-
 	for (index = 0; index < opp_table->required_opp_count; index++) {
-		if (!opp_table->genpd_virt_devs[index])
+		if (!opp_table->required_devs[index])
 			continue;
 
-		dev_pm_domain_detach(opp_table->genpd_virt_devs[index], false);
-		opp_table->genpd_virt_devs[index] = NULL;
+		dev_pm_domain_detach(opp_table->required_devs[index], false);
+		opp_table->required_devs[index] = NULL;
 	}
-
-	kfree(opp_table->genpd_virt_devs);
-	opp_table->genpd_virt_devs = NULL;
 }
 
 /*
@@ -2427,14 +2397,20 @@ static int _opp_attach_genpd(struct opp_table *opp_table, struct device *dev,
 	int index = 0, ret = -EINVAL;
 	const char * const *name = names;
 
-	if (opp_table->genpd_virt_devs)
-		return 0;
+	if (!opp_table->required_devs) {
+		dev_err(dev, "Required OPPs not available, can't attach genpd\n");
+		return -EINVAL;
+	}
 
-	opp_table->genpd_virt_devs = kcalloc(opp_table->required_opp_count,
-					     sizeof(*opp_table->genpd_virt_devs),
-					     GFP_KERNEL);
-	if (!opp_table->genpd_virt_devs)
-		return -ENOMEM;
+	/* Genpd core takes care of propagation to parent genpd */
+	if (opp_table->is_genpd) {
+		dev_err(dev, "%s: Operation not supported for genpds\n", __func__);
+		return -EOPNOTSUPP;
+	}
+
+	/* Checking only the first one is enough ? */
+	if (opp_table->required_devs[0])
+		return 0;
 
 	while (*name) {
 		if (index >= opp_table->required_opp_count) {
@@ -2450,13 +2426,25 @@ static int _opp_attach_genpd(struct opp_table *opp_table, struct device *dev,
 			goto err;
 		}
 
-		opp_table->genpd_virt_devs[index] = virt_dev;
+		/*
+		 * Add the virtual genpd device as a user of the OPP table, so
+		 * we can call dev_pm_opp_set_opp() on it directly.
+		 *
+		 * This will be automatically removed when the OPP table is
+		 * removed, don't need to handle that here.
+		 */
+		if (!_add_opp_dev(virt_dev, opp_table->required_opp_tables[index])) {
+			ret = -ENOMEM;
+			goto err;
+		}
+
+		opp_table->required_devs[index] = virt_dev;
 		index++;
 		name++;
 	}
 
 	if (virt_devs)
-		*virt_devs = opp_table->genpd_virt_devs;
+		*virt_devs = opp_table->required_devs;
 
 	return 0;
 
@@ -2466,10 +2454,50 @@ err:
 
 }
 
+static int _opp_set_required_devs(struct opp_table *opp_table,
+				  struct device *dev,
+				  struct device **required_devs)
+{
+	int i;
+
+	if (!opp_table->required_devs) {
+		dev_err(dev, "Required OPPs not available, can't set required devs\n");
+		return -EINVAL;
+	}
+
+	/* Another device that shares the OPP table has set the required devs ? */
+	if (opp_table->required_devs[0])
+		return 0;
+
+	for (i = 0; i < opp_table->required_opp_count; i++) {
+		/* Genpd core takes care of propagation to parent genpd */
+		if (required_devs[i] && opp_table->is_genpd &&
+		    opp_table->required_opp_tables[i]->is_genpd) {
+			dev_err(dev, "%s: Operation not supported for genpds\n", __func__);
+			return -EOPNOTSUPP;
+		}
+
+		opp_table->required_devs[i] = required_devs[i];
+	}
+
+	return 0;
+}
+
+static void _opp_put_required_devs(struct opp_table *opp_table)
+{
+	int i;
+
+	for (i = 0; i < opp_table->required_opp_count; i++)
+		opp_table->required_devs[i] = NULL;
+}
+
 static void _opp_clear_config(struct opp_config_data *data)
 {
-	if (data->flags & OPP_CONFIG_GENPD)
+	if (data->flags & OPP_CONFIG_REQUIRED_DEVS)
+		_opp_put_required_devs(data->opp_table);
+	else if (data->flags & OPP_CONFIG_GENPD)
 		_opp_detach_genpd(data->opp_table);
+
 	if (data->flags & OPP_CONFIG_REGULATOR)
 		_opp_put_regulators(data->opp_table);
 	if (data->flags & OPP_CONFIG_SUPPORTED_HW)
@@ -2583,12 +2611,22 @@ int dev_pm_opp_set_config(struct device *dev, struct dev_pm_opp_config *config)
 
 	/* Attach genpds */
 	if (config->genpd_names) {
+		if (config->required_devs)
+			goto err;
+
 		ret = _opp_attach_genpd(opp_table, dev, config->genpd_names,
 					config->virt_devs);
 		if (ret)
 			goto err;
 
 		data->flags |= OPP_CONFIG_GENPD;
+	} else if (config->required_devs) {
+		ret = _opp_set_required_devs(opp_table, dev,
+					     config->required_devs);
+		if (ret)
+			goto err;
+
+		data->flags |= OPP_CONFIG_REQUIRED_DEVS;
 	}
 
 	ret = xa_alloc(&opp_configs, &id, data, XA_LIMIT(1, INT_MAX),
@@ -2975,6 +3013,47 @@ put_table:
 EXPORT_SYMBOL_GPL(dev_pm_opp_adjust_voltage);
 
 /**
+ * dev_pm_opp_sync_regulators() - Sync state of voltage regulators
+ * @dev:	device for which we do this operation
+ *
+ * Sync voltage state of the OPP table regulators.
+ *
+ * Return: 0 on success or a negative error value.
+ */
+int dev_pm_opp_sync_regulators(struct device *dev)
+{
+	struct opp_table *opp_table;
+	struct regulator *reg;
+	int i, ret = 0;
+
+	/* Device may not have OPP table */
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table))
+		return 0;
+
+	/* Regulator may not be required for the device */
+	if (unlikely(!opp_table->regulators))
+		goto put_table;
+
+	/* Nothing to sync if voltage wasn't changed */
+	if (!opp_table->enabled)
+		goto put_table;
+
+	for (i = 0; i < opp_table->regulator_count; i++) {
+		reg = opp_table->regulators[i];
+		ret = regulator_sync_voltage(reg);
+		if (ret)
+			break;
+	}
+put_table:
+	/* Drop reference taken by _find_opp_table() */
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_sync_regulators);
+
+/**
  * dev_pm_opp_enable() - Enable a specific OPP
  * @dev:	device for which we do this operation
  * @freq:	OPP frequency to enable
@@ -3097,44 +3176,3 @@ void dev_pm_opp_remove_table(struct device *dev)
 	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_remove_table);
-
-/**
- * dev_pm_opp_sync_regulators() - Sync state of voltage regulators
- * @dev:	device for which we do this operation
- *
- * Sync voltage state of the OPP table regulators.
- *
- * Return: 0 on success or a negative error value.
- */
-int dev_pm_opp_sync_regulators(struct device *dev)
-{
-	struct opp_table *opp_table;
-	struct regulator *reg;
-	int i, ret = 0;
-
-	/* Device may not have OPP table */
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table))
-		return 0;
-
-	/* Regulator may not be required for the device */
-	if (unlikely(!opp_table->regulators))
-		goto put_table;
-
-	/* Nothing to sync if voltage wasn't changed */
-	if (!opp_table->enabled)
-		goto put_table;
-
-	for (i = 0; i < opp_table->regulator_count; i++) {
-		reg = opp_table->regulators[i];
-		ret = regulator_sync_voltage(reg);
-		if (ret)
-			break;
-	}
-put_table:
-	/* Drop reference taken by _find_opp_table() */
-	dev_pm_opp_put_opp_table(opp_table);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_sync_regulators);
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index 81fa27599d58..f9f0b22bccbb 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -165,7 +165,7 @@ static void _opp_table_alloc_required_tables(struct opp_table *opp_table,
 	struct opp_table **required_opp_tables;
 	struct device_node *required_np, *np;
 	bool lazy = false;
-	int count, i;
+	int count, i, size;
 
 	/* Traversing the first OPP node is all we need */
 	np = of_get_next_available_child(opp_np, NULL);
@@ -179,12 +179,13 @@ static void _opp_table_alloc_required_tables(struct opp_table *opp_table,
 	if (count <= 0)
 		goto put_np;
 
-	required_opp_tables = kcalloc(count, sizeof(*required_opp_tables),
-				      GFP_KERNEL);
+	size = sizeof(*required_opp_tables) + sizeof(*opp_table->required_devs);
+	required_opp_tables = kcalloc(count, size, GFP_KERNEL);
 	if (!required_opp_tables)
 		goto put_np;
 
 	opp_table->required_opp_tables = required_opp_tables;
+	opp_table->required_devs = (void *)(required_opp_tables + count);
 	opp_table->required_opp_count = count;
 
 	for (i = 0; i < count; i++) {
@@ -208,8 +209,6 @@ static void _opp_table_alloc_required_tables(struct opp_table *opp_table,
 		mutex_lock(&opp_table_lock);
 		list_add(&opp_table->lazy, &lazy_opp_tables);
 		mutex_unlock(&opp_table_lock);
-	} else {
-		_update_set_required_opps(opp_table);
 	}
 
 	goto put_np;
@@ -296,7 +295,7 @@ void _of_clear_opp(struct opp_table *opp_table, struct dev_pm_opp *opp)
 	of_node_put(opp->np);
 }
 
-static int _link_required_opps(struct dev_pm_opp *opp,
+static int _link_required_opps(struct dev_pm_opp *opp, struct opp_table *opp_table,
 			       struct opp_table *required_table, int index)
 {
 	struct device_node *np;
@@ -314,6 +313,39 @@ static int _link_required_opps(struct dev_pm_opp *opp,
 		return -ENODEV;
 	}
 
+	/*
+	 * There are two genpd (as required-opp) cases that we need to handle,
+	 * devices with a single genpd and ones with multiple genpds.
+	 *
+	 * The single genpd case requires special handling as we need to use the
+	 * same `dev` structure (instead of a virtual one provided by genpd
+	 * core) for setting the performance state.
+	 *
+	 * It doesn't make sense for a device's DT entry to have both
+	 * "opp-level" and single "required-opps" entry pointing to a genpd's
+	 * OPP, as that would make the OPP core call
+	 * dev_pm_domain_set_performance_state() for two different values for
+	 * the same device structure. Lets treat single genpd configuration as a
+	 * case where the OPP's level is directly available without required-opp
+	 * link in the DT.
+	 *
+	 * Just update the `level` with the right value, which
+	 * dev_pm_opp_set_opp() will take care of in the normal path itself.
+	 *
+	 * There is another case though, where a genpd's OPP table has
+	 * required-opps set to a parent genpd. The OPP core expects the user to
+	 * set the respective required `struct device` pointer via
+	 * dev_pm_opp_set_config().
+	 */
+	if (required_table->is_genpd && opp_table->required_opp_count == 1 &&
+	    !opp_table->required_devs[0]) {
+		/* Genpd core takes care of propagation to parent genpd */
+		if (!opp_table->is_genpd) {
+			if (!WARN_ON(opp->level != OPP_LEVEL_UNSET))
+				opp->level = opp->required_opps[0]->level;
+		}
+	}
+
 	return 0;
 }
 
@@ -338,7 +370,7 @@ static int _of_opp_alloc_required_opps(struct opp_table *opp_table,
 		if (IS_ERR_OR_NULL(required_table))
 			continue;
 
-		ret = _link_required_opps(opp, required_table, i);
+		ret = _link_required_opps(opp, opp_table, required_table, i);
 		if (ret)
 			goto free_required_opps;
 	}
@@ -359,7 +391,7 @@ static int lazy_link_required_opps(struct opp_table *opp_table,
 	int ret;
 
 	list_for_each_entry(opp, &opp_table->opp_list, node) {
-		ret = _link_required_opps(opp, new_table, index);
+		ret = _link_required_opps(opp, opp_table, new_table, index);
 		if (ret)
 			return ret;
 	}
@@ -422,7 +454,6 @@ static void lazy_link_required_opp_table(struct opp_table *new_table)
 
 		/* All required opp-tables found, remove from lazy list */
 		if (!lazy) {
-			_update_set_required_opps(opp_table);
 			list_del_init(&opp_table->lazy);
 
 			list_for_each_entry(opp, &opp_table->opp_list, node)
@@ -1393,8 +1424,14 @@ int of_get_required_opp_performance_state(struct device_node *np, int index)
 
 	opp = _find_opp_of_np(opp_table, required_np);
 	if (opp) {
-		pstate = opp->level;
+		if (opp->level == OPP_LEVEL_UNSET) {
+			pr_err("%s: OPP levels aren't available for %pOF\n",
+			       __func__, np);
+		} else {
+			pstate = opp->level;
+		}
 		dev_pm_opp_put(opp);
+
 	}
 
 	dev_pm_opp_put_opp_table(opp_table);
diff --git a/drivers/opp/opp.h b/drivers/opp/opp.h
index 08366f90f16b..cff1fabd1ae3 100644
--- a/drivers/opp/opp.h
+++ b/drivers/opp/opp.h
@@ -35,6 +35,7 @@ extern struct list_head opp_tables;
 #define OPP_CONFIG_PROP_NAME		BIT(3)
 #define OPP_CONFIG_SUPPORTED_HW		BIT(4)
 #define OPP_CONFIG_GENPD		BIT(5)
+#define OPP_CONFIG_REQUIRED_DEVS	BIT(6)
 
 /**
  * struct opp_config_data - data for set config operations
@@ -49,6 +50,18 @@ struct opp_config_data {
 	unsigned int flags;
 };
 
+/**
+ * struct dev_pm_opp_icc_bw - Interconnect bandwidth values
+ * @avg:	Average bandwidth corresponding to this OPP (in icc units)
+ * @peak:	Peak bandwidth corresponding to this OPP (in icc units)
+ *
+ * This structure stores the bandwidth values for a single interconnect path.
+ */
+struct dev_pm_opp_icc_bw {
+	u32 avg;
+	u32 peak;
+};
+
 /*
  * Internal data structure organization with the OPP layer library is as
  * follows:
@@ -157,12 +170,12 @@ enum opp_table_access {
  * @clock_latency_ns_max: Max clock latency in nanoseconds.
  * @parsed_static_opps: Count of devices for which OPPs are initialized from DT.
  * @shared_opp: OPP is shared between multiple devices.
- * @rate_clk_single: Currently configured frequency for single clk.
+ * @current_rate_single_clk: Currently configured frequency for single clk.
  * @current_opp: Currently configured OPP for the table.
  * @suspend_opp: Pointer to OPP to be used during device suspend.
- * @genpd_virt_devs: List of virtual devices for multiple genpd support.
  * @required_opp_tables: List of device OPP tables that are required by OPPs in
  *		this table.
+ * @required_devs: List of devices for required OPP tables.
  * @required_opp_count: Number of required devices.
  * @supported_hw: Array of version number to support.
  * @supported_hw_count: Number of elements in supported_hw array.
@@ -180,7 +193,6 @@ enum opp_table_access {
  * @path_count: Number of interconnect paths
  * @enabled: Set to true if the device's resources are enabled/configured.
  * @is_genpd: Marks if the OPP table belongs to a genpd.
- * @set_required_opps: Helper responsible to set required OPPs.
  * @dentry:	debugfs dentry pointer of the real device directory (not links).
  * @dentry_name: Name of the real dentry.
  *
@@ -207,12 +219,12 @@ struct opp_table {
 
 	unsigned int parsed_static_opps;
 	enum opp_table_access shared_opp;
-	unsigned long rate_clk_single;
+	unsigned long current_rate_single_clk;
 	struct dev_pm_opp *current_opp;
 	struct dev_pm_opp *suspend_opp;
 
-	struct device **genpd_virt_devs;
 	struct opp_table **required_opp_tables;
+	struct device **required_devs;
 	unsigned int required_opp_count;
 
 	unsigned int *supported_hw;
@@ -229,8 +241,6 @@ struct opp_table {
 	unsigned int path_count;
 	bool enabled;
 	bool is_genpd;
-	int (*set_required_opps)(struct device *dev,
-		struct opp_table *opp_table, struct dev_pm_opp *opp, bool scaling_down);
 
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dentry;
diff --git a/drivers/opp/ti-opp-supply.c b/drivers/opp/ti-opp-supply.c
index 8f3f13fbbb25..e3b97cd1fbbf 100644
--- a/drivers/opp/ti-opp-supply.c
+++ b/drivers/opp/ti-opp-supply.c
@@ -18,6 +18,7 @@
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pm_opp.h>
+#include <linux/property.h>
 #include <linux/regulator/consumer.h>
 #include <linux/slab.h>
 
@@ -373,23 +374,15 @@ static int ti_opp_supply_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device *cpu_dev = get_cpu_device(0);
-	const struct of_device_id *match;
 	const struct ti_opp_supply_of_data *of_data;
 	int ret = 0;
 
-	match = of_match_device(ti_opp_supply_of_match, dev);
-	if (!match) {
-		/* We do not expect this to happen */
-		dev_err(dev, "%s: Unable to match device\n", __func__);
-		return -ENODEV;
-	}
-	if (!match->data) {
+	of_data = device_get_match_data(dev);
+	if (!of_data) {
 		/* Again, unlikely.. but mistakes do happen */
 		dev_err(dev, "%s: Bad data in match\n", __func__);
 		return -EINVAL;
 	}
-	of_data = match->data;
-
 	dev_set_drvdata(dev, (void *)of_data);
 
 	/* If we need optimized voltage */
diff --git a/drivers/parisc/power.c b/drivers/parisc/power.c
index 539d8920c202..bb0d92461b08 100644
--- a/drivers/parisc/power.c
+++ b/drivers/parisc/power.c
@@ -176,7 +176,7 @@ static struct notifier_block parisc_panic_block = {
 static int qemu_power_off(struct sys_off_data *data)
 {
 	/* this turns the system off via SeaBIOS */
-	*(int *)data->cb_data = 0;
+	gsc_writel(0, (unsigned long) data->cb_data);
 	pdc_soft_power_button(1);
 	return NOTIFY_DONE;
 }
diff --git a/drivers/parport/parport_pc.c b/drivers/parport/parport_pc.c
index 1f236aaf7867..f33b5d1ddfc1 100644
--- a/drivers/parport/parport_pc.c
+++ b/drivers/parport/parport_pc.c
@@ -2658,6 +2658,8 @@ enum parport_pc_pci_cards {
 	asix_ax99100,
 	quatech_sppxp100,
 	wch_ch382l,
+	brainboxes_uc146,
+	brainboxes_px203,
 };
 
 
@@ -2737,6 +2739,8 @@ static struct parport_pc_pci {
 	/* asix_ax99100 */		{ 1, { { 0, 1 }, } },
 	/* quatech_sppxp100 */		{ 1, { { 0, 1 }, } },
 	/* wch_ch382l */		{ 1, { { 2, -1 }, } },
+	/* brainboxes_uc146 */	{ 1, { { 3, -1 }, } },
+	/* brainboxes_px203 */	{ 1, { { 0, -1 }, } },
 };
 
 static const struct pci_device_id parport_pc_pci_tbl[] = {
@@ -2833,6 +2837,23 @@ static const struct pci_device_id parport_pc_pci_tbl[] = {
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, quatech_sppxp100 },
 	/* WCH CH382L PCI-E single parallel port card */
 	{ 0x1c00, 0x3050, 0x1c00, 0x3050, 0, 0, wch_ch382l },
+	/* Brainboxes IX-500/550 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x402a,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, oxsemi_pcie_pport },
+	/* Brainboxes UC-146/UC-157 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0be1,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc146 },
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0be2,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc146 },
+	/* Brainboxes PX-146/PX-257 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x401c,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, oxsemi_pcie_pport },
+	/* Brainboxes PX-203 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x4007,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_px203 },
+	/* Brainboxes PX-475 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x401f,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, oxsemi_pcie_pport },
 	{ 0, } /* terminate list */
 };
 MODULE_DEVICE_TABLE(pci, parport_pc_pci_tbl);
diff --git a/drivers/pci/access.c b/drivers/pci/access.c
index 6554a2e89d36..6449056b57dd 100644
--- a/drivers/pci/access.c
+++ b/drivers/pci/access.c
@@ -598,3 +598,15 @@ int pci_write_config_dword(const struct pci_dev *dev, int where,
 	return pci_bus_write_config_dword(dev->bus, dev->devfn, where, val);
 }
 EXPORT_SYMBOL(pci_write_config_dword);
+
+void pci_clear_and_set_config_dword(const struct pci_dev *dev, int pos,
+				    u32 clear, u32 set)
+{
+	u32 val;
+
+	pci_read_config_dword(dev, pos, &val);
+	val &= ~clear;
+	val |= set;
+	pci_write_config_dword(dev, pos, val);
+}
+EXPORT_SYMBOL(pci_clear_and_set_config_dword);
diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index 6902e97719d1..11c80555d975 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -968,9 +968,12 @@ static int qcom_pcie_post_init_2_7_0(struct qcom_pcie *pcie)
 
 static int qcom_pcie_enable_aspm(struct pci_dev *pdev, void *userdata)
 {
-	/* Downstream devices need to be in D0 state before enabling PCI PM substates */
+	/*
+	 * Downstream devices need to be in D0 state before enabling PCI PM
+	 * substates.
+	 */
 	pci_set_power_state(pdev, PCI_D0);
-	pci_enable_link_state(pdev, PCIE_LINK_STATE_ALL);
+	pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL);
 
 	return 0;
 }
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index 30c7dfeccb16..1eaffff40b8d 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -650,13 +650,6 @@ static void hv_arch_irq_unmask(struct irq_data *data)
 			   PCI_FUNC(pdev->devfn);
 	params->int_target.vector = hv_msi_get_int_vector(data);
 
-	/*
-	 * Honoring apic->delivery_mode set to APIC_DELIVERY_MODE_FIXED by
-	 * setting the HV_DEVICE_INTERRUPT_TARGET_MULTICAST flag results in a
-	 * spurious interrupt storm. Not doing so does not seem to have a
-	 * negative effect (yet?).
-	 */
-
 	if (hbus->protocol_version >= PCI_PROTOCOL_VERSION_1_2) {
 		/*
 		 * PCI_PROTOCOL_VERSION_1_2 supports the VP_SET version of the
diff --git a/drivers/pci/controller/pci-loongson.c b/drivers/pci/controller/pci-loongson.c
index d45e7b8dc530..8b34ccff073a 100644
--- a/drivers/pci/controller/pci-loongson.c
+++ b/drivers/pci/controller/pci-loongson.c
@@ -80,13 +80,49 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON,
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON,
 			DEV_LS7A_LPC, system_bus_quirk);
 
+/*
+ * Some Loongson PCIe ports have hardware limitations on their Maximum Read
+ * Request Size. They can't handle anything larger than this.  Sane
+ * firmware will set proper MRRS at boot, so we only need no_inc_mrrs for
+ * bridges. However, some MIPS Loongson firmware doesn't set MRRS properly,
+ * so we have to enforce maximum safe MRRS, which is 256 bytes.
+ */
+#ifdef CONFIG_MIPS
+static void loongson_set_min_mrrs_quirk(struct pci_dev *pdev)
+{
+	struct pci_bus *bus = pdev->bus;
+	struct pci_dev *bridge;
+	static const struct pci_device_id bridge_devids[] = {
+		{ PCI_VDEVICE(LOONGSON, DEV_LS2K_PCIE_PORT0) },
+		{ PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT0) },
+		{ PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT1) },
+		{ PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT2) },
+		{ PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT3) },
+		{ PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT4) },
+		{ PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT5) },
+		{ PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT6) },
+		{ 0, },
+	};
+
+	/* look for the matching bridge */
+	while (!pci_is_root_bus(bus)) {
+		bridge = bus->self;
+		bus = bus->parent;
+
+		if (pci_match_id(bridge_devids, bridge)) {
+			if (pcie_get_readrq(pdev) > 256) {
+				pci_info(pdev, "limiting MRRS to 256\n");
+				pcie_set_readrq(pdev, 256);
+			}
+			break;
+		}
+	}
+}
+DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, loongson_set_min_mrrs_quirk);
+#endif
+
 static void loongson_mrrs_quirk(struct pci_dev *pdev)
 {
-	/*
-	 * Some Loongson PCIe ports have h/w limitations of maximum read
-	 * request size. They can't handle anything larger than this. So
-	 * force this limit on any devices attached under these ports.
-	 */
 	struct pci_host_bridge *bridge = pci_find_host_bridge(pdev->bus);
 
 	bridge->no_inc_mrrs = 1;
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 94ba61fe1c44..0452cbc362ee 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -751,7 +751,7 @@ static int vmd_pm_enable_quirk(struct pci_dev *pdev, void *userdata)
 	if (!(features & VMD_FEAT_BIOS_PM_QUIRK))
 		return 0;
 
-	pci_enable_link_state(pdev, PCIE_LINK_STATE_ALL);
+	pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL);
 
 	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_LTR);
 	if (!pos)
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index 601129772b2d..5b1f271c6034 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -512,15 +512,12 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge)
 				if (pass && dev->subordinate) {
 					check_hotplug_bridge(slot, dev);
 					pcibios_resource_survey_bus(dev->subordinate);
-					if (pci_is_root_bus(bus))
-						__pci_bus_size_bridges(dev->subordinate, &add_list);
+					__pci_bus_size_bridges(dev->subordinate,
+							       &add_list);
 				}
 			}
 		}
-		if (pci_is_root_bus(bus))
-			__pci_bus_assign_resources(bus, &add_list, NULL);
-		else
-			pci_assign_unassigned_bridge_resources(bus->self);
+		__pci_bus_assign_resources(bus, &add_list, NULL);
 	}
 
 	acpiphp_sanitize_bus(bus);
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 55bc3576a985..ae550d71b815 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1219,6 +1219,9 @@ static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout)
 	if (delay > PCI_RESET_WAIT)
 		pci_info(dev, "ready %dms after %s\n", delay - 1,
 			 reset_type);
+	else
+		pci_dbg(dev, "ready %dms after %s\n", delay - 1,
+			reset_type);
 
 	return 0;
 }
@@ -1335,6 +1338,9 @@ static int pci_set_full_power_state(struct pci_dev *dev)
 		pci_restore_bars(dev);
 	}
 
+	if (dev->bus->self)
+		pcie_aspm_pm_state_change(dev->bus->self);
+
 	return 0;
 }
 
@@ -1429,6 +1435,9 @@ static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state)
 				     pci_power_name(dev->current_state),
 				     pci_power_name(state));
 
+	if (dev->bus->self)
+		pcie_aspm_pm_state_change(dev->bus->self);
+
 	return 0;
 }
 
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 5ecbcf041179..f43873049d52 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -569,10 +569,12 @@ int pcie_retrain_link(struct pci_dev *pdev, bool use_lt);
 #ifdef CONFIG_PCIEASPM
 void pcie_aspm_init_link_state(struct pci_dev *pdev);
 void pcie_aspm_exit_link_state(struct pci_dev *pdev);
+void pcie_aspm_pm_state_change(struct pci_dev *pdev);
 void pcie_aspm_powersave_config_link(struct pci_dev *pdev);
 #else
 static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { }
 static inline void pcie_aspm_exit_link_state(struct pci_dev *pdev) { }
+static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev) { }
 static inline void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { }
 #endif
 
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 50b04ae5c394..5a0066ecc3c5 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -426,17 +426,6 @@ static void pcie_aspm_check_latency(struct pci_dev *endpoint)
 	}
 }
 
-static void pci_clear_and_set_dword(struct pci_dev *pdev, int pos,
-				    u32 clear, u32 set)
-{
-	u32 val;
-
-	pci_read_config_dword(pdev, pos, &val);
-	val &= ~clear;
-	val |= set;
-	pci_write_config_dword(pdev, pos, val);
-}
-
 /* Calculate L1.2 PM substate timing parameters */
 static void aspm_calc_l12_info(struct pcie_link_state *link,
 				u32 parent_l1ss_cap, u32 child_l1ss_cap)
@@ -501,10 +490,12 @@ static void aspm_calc_l12_info(struct pcie_link_state *link,
 	cl1_2_enables = cctl1 & PCI_L1SS_CTL1_L1_2_MASK;
 
 	if (pl1_2_enables || cl1_2_enables) {
-		pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
-					PCI_L1SS_CTL1_L1_2_MASK, 0);
-		pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
-					PCI_L1SS_CTL1_L1_2_MASK, 0);
+		pci_clear_and_set_config_dword(child,
+					       child->l1ss + PCI_L1SS_CTL1,
+					       PCI_L1SS_CTL1_L1_2_MASK, 0);
+		pci_clear_and_set_config_dword(parent,
+					       parent->l1ss + PCI_L1SS_CTL1,
+					       PCI_L1SS_CTL1_L1_2_MASK, 0);
 	}
 
 	/* Program T_POWER_ON times in both ports */
@@ -512,22 +503,26 @@ static void aspm_calc_l12_info(struct pcie_link_state *link,
 	pci_write_config_dword(child, child->l1ss + PCI_L1SS_CTL2, ctl2);
 
 	/* Program Common_Mode_Restore_Time in upstream device */
-	pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_CM_RESTORE_TIME, ctl1);
+	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_CM_RESTORE_TIME, ctl1);
 
 	/* Program LTR_L1.2_THRESHOLD time in both ports */
-	pci_clear_and_set_dword(parent,	parent->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
-				PCI_L1SS_CTL1_LTR_L12_TH_SCALE, ctl1);
-	pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
-				PCI_L1SS_CTL1_LTR_L12_TH_SCALE, ctl1);
+	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
+				       PCI_L1SS_CTL1_LTR_L12_TH_SCALE,
+				       ctl1);
+	pci_clear_and_set_config_dword(child, child->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
+				       PCI_L1SS_CTL1_LTR_L12_TH_SCALE,
+				       ctl1);
 
 	if (pl1_2_enables || cl1_2_enables) {
-		pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1, 0,
-					pl1_2_enables);
-		pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1, 0,
-					cl1_2_enables);
+		pci_clear_and_set_config_dword(parent,
+					       parent->l1ss + PCI_L1SS_CTL1, 0,
+					       pl1_2_enables);
+		pci_clear_and_set_config_dword(child,
+					       child->l1ss + PCI_L1SS_CTL1, 0,
+					       cl1_2_enables);
 	}
 }
 
@@ -687,10 +682,10 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 	 */
 
 	/* Disable all L1 substates */
-	pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_L1SS_MASK, 0);
-	pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_L1SS_MASK, 0);
+	pci_clear_and_set_config_dword(child, child->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_L1SS_MASK, 0);
+	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_L1SS_MASK, 0);
 	/*
 	 * If needed, disable L1, and it gets enabled later
 	 * in pcie_config_aspm_link().
@@ -713,10 +708,10 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 		val |= PCI_L1SS_CTL1_PCIPM_L1_2;
 
 	/* Enable what we need to enable */
-	pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_L1SS_MASK, val);
-	pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_L1SS_MASK, val);
+	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_L1SS_MASK, val);
+	pci_clear_and_set_config_dword(child, child->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_L1SS_MASK, val);
 }
 
 static void pcie_config_aspm_dev(struct pci_dev *pdev, u32 val)
@@ -1008,6 +1003,25 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev)
 	up_read(&pci_bus_sem);
 }
 
+/* @pdev: the root port or switch downstream port */
+void pcie_aspm_pm_state_change(struct pci_dev *pdev)
+{
+	struct pcie_link_state *link = pdev->link_state;
+
+	if (aspm_disabled || !link)
+		return;
+	/*
+	 * Devices changed PM state, we should recheck if latency
+	 * meets all functions' requirement
+	 */
+	down_read(&pci_bus_sem);
+	mutex_lock(&aspm_lock);
+	pcie_update_aspm_capable(link->root);
+	pcie_config_aspm_path(link);
+	mutex_unlock(&aspm_lock);
+	up_read(&pci_bus_sem);
+}
+
 void pcie_aspm_powersave_config_link(struct pci_dev *pdev)
 {
 	struct pcie_link_state *link = pdev->link_state;
@@ -1041,7 +1055,7 @@ static struct pcie_link_state *pcie_aspm_get_link(struct pci_dev *pdev)
 	return bridge->link_state;
 }
 
-static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem)
+static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool locked)
 {
 	struct pcie_link_state *link = pcie_aspm_get_link(pdev);
 
@@ -1060,7 +1074,7 @@ static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem)
 		return -EPERM;
 	}
 
-	if (sem)
+	if (!locked)
 		down_read(&pci_bus_sem);
 	mutex_lock(&aspm_lock);
 	if (state & PCIE_LINK_STATE_L0S)
@@ -1082,7 +1096,7 @@ static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem)
 		link->clkpm_disable = 1;
 	pcie_set_clkpm(link, policy_to_clkpm_state(link));
 	mutex_unlock(&aspm_lock);
-	if (sem)
+	if (!locked)
 		up_read(&pci_bus_sem);
 
 	return 0;
@@ -1090,7 +1104,9 @@ static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem)
 
 int pci_disable_link_state_locked(struct pci_dev *pdev, int state)
 {
-	return __pci_disable_link_state(pdev, state, false);
+	lockdep_assert_held_read(&pci_bus_sem);
+
+	return __pci_disable_link_state(pdev, state, true);
 }
 EXPORT_SYMBOL(pci_disable_link_state_locked);
 
@@ -1105,21 +1121,11 @@ EXPORT_SYMBOL(pci_disable_link_state_locked);
  */
 int pci_disable_link_state(struct pci_dev *pdev, int state)
 {
-	return __pci_disable_link_state(pdev, state, true);
+	return __pci_disable_link_state(pdev, state, false);
 }
 EXPORT_SYMBOL(pci_disable_link_state);
 
-/**
- * pci_enable_link_state - Clear and set the default device link state so that
- * the link may be allowed to enter the specified states. Note that if the
- * BIOS didn't grant ASPM control to the OS, this does nothing because we can't
- * touch the LNKCTL register. Also note that this does not enable states
- * disabled by pci_disable_link_state(). Return 0 or a negative errno.
- *
- * @pdev: PCI device
- * @state: Mask of ASPM link states to enable
- */
-int pci_enable_link_state(struct pci_dev *pdev, int state)
+static int __pci_enable_link_state(struct pci_dev *pdev, int state, bool locked)
 {
 	struct pcie_link_state *link = pcie_aspm_get_link(pdev);
 
@@ -1136,7 +1142,8 @@ int pci_enable_link_state(struct pci_dev *pdev, int state)
 		return -EPERM;
 	}
 
-	down_read(&pci_bus_sem);
+	if (!locked)
+		down_read(&pci_bus_sem);
 	mutex_lock(&aspm_lock);
 	link->aspm_default = 0;
 	if (state & PCIE_LINK_STATE_L0S)
@@ -1157,12 +1164,48 @@ int pci_enable_link_state(struct pci_dev *pdev, int state)
 	link->clkpm_default = (state & PCIE_LINK_STATE_CLKPM) ? 1 : 0;
 	pcie_set_clkpm(link, policy_to_clkpm_state(link));
 	mutex_unlock(&aspm_lock);
-	up_read(&pci_bus_sem);
+	if (!locked)
+		up_read(&pci_bus_sem);
 
 	return 0;
 }
+
+/**
+ * pci_enable_link_state - Clear and set the default device link state so that
+ * the link may be allowed to enter the specified states. Note that if the
+ * BIOS didn't grant ASPM control to the OS, this does nothing because we can't
+ * touch the LNKCTL register. Also note that this does not enable states
+ * disabled by pci_disable_link_state(). Return 0 or a negative errno.
+ *
+ * @pdev: PCI device
+ * @state: Mask of ASPM link states to enable
+ */
+int pci_enable_link_state(struct pci_dev *pdev, int state)
+{
+	return __pci_enable_link_state(pdev, state, false);
+}
 EXPORT_SYMBOL(pci_enable_link_state);
 
+/**
+ * pci_enable_link_state_locked - Clear and set the default device link state
+ * so that the link may be allowed to enter the specified states. Note that if
+ * the BIOS didn't grant ASPM control to the OS, this does nothing because we
+ * can't touch the LNKCTL register. Also note that this does not enable states
+ * disabled by pci_disable_link_state(). Return 0 or a negative errno.
+ *
+ * @pdev: PCI device
+ * @state: Mask of ASPM link states to enable
+ *
+ * Context: Caller holds pci_bus_sem read lock.
+ */
+int pci_enable_link_state_locked(struct pci_dev *pdev, int state)
+{
+	lockdep_assert_held_read(&pci_bus_sem);
+
+	return __pci_enable_link_state(pdev, state, true);
+}
+EXPORT_SYMBOL(pci_enable_link_state_locked);
+
 static int pcie_aspm_set_policy(const char *val,
 				const struct kernel_param *kp)
 {
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index ea476252280a..d208047d1b8f 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3787,6 +3787,19 @@ DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_ATI, PCI_ANY_ID,
 			       PCI_CLASS_DISPLAY_VGA, 8, quirk_no_pm_reset);
 
 /*
+ * Spectrum-{1,2,3,4} devices report that a D3hot->D0 transition causes a reset
+ * (i.e., they advertise NoSoftRst-). However, this transition does not have
+ * any effect on the device: It continues to be operational and network ports
+ * remain up. Advertising this support makes it seem as if a PM reset is viable
+ * for these devices. Mark it as unavailable to skip it when testing reset
+ * methods.
+ */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MELLANOX, 0xcb84, quirk_no_pm_reset);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MELLANOX, 0xcf6c, quirk_no_pm_reset);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MELLANOX, 0xcf70, quirk_no_pm_reset);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MELLANOX, 0xcf80, quirk_no_pm_reset);
+
+/*
  * Thunderbolt controllers with broken MSI hotplug signaling:
  * Entire 1st generation (Light Ridge, Eagle Ridge, Light Peak) and part
  * of the 2nd generation (Cactus Ridge 4C up to revision 1, Port Ridge).
diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index 273d67ecf6d2..ec6e0d9194a1 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -217,6 +217,13 @@ config MARVELL_CN10K_DDR_PMU
 	  Enable perf support for Marvell DDR Performance monitoring
 	  event on CN10K platform.
 
+config DWC_PCIE_PMU
+	tristate "Synopsys DesignWare PCIe PMU"
+	depends on PCI
+	help
+	  Enable perf support for Synopsys DesignWare PCIe PMU Performance
+	  monitoring event on platform including the Alibaba Yitian 710.
+
 source "drivers/perf/arm_cspmu/Kconfig"
 
 source "drivers/perf/amlogic/Kconfig"
diff --git a/drivers/perf/Makefile b/drivers/perf/Makefile
index 16b3ec4db916..a06338e3401c 100644
--- a/drivers/perf/Makefile
+++ b/drivers/perf/Makefile
@@ -23,6 +23,7 @@ obj-$(CONFIG_MARVELL_CN10K_TAD_PMU) += marvell_cn10k_tad_pmu.o
 obj-$(CONFIG_MARVELL_CN10K_DDR_PMU) += marvell_cn10k_ddr_pmu.o
 obj-$(CONFIG_APPLE_M1_CPU_PMU) += apple_m1_cpu_pmu.o
 obj-$(CONFIG_ALIBABA_UNCORE_DRW_PMU) += alibaba_uncore_drw_pmu.o
+obj-$(CONFIG_DWC_PCIE_PMU) += dwc_pcie_pmu.o
 obj-$(CONFIG_ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU) += arm_cspmu/
 obj-$(CONFIG_MESON_DDR_PMU) += amlogic/
 obj-$(CONFIG_CXL_PMU) += cxl_pmu.o
diff --git a/drivers/perf/apple_m1_cpu_pmu.c b/drivers/perf/apple_m1_cpu_pmu.c
index cd2de44b61b9..f322e5ca1114 100644
--- a/drivers/perf/apple_m1_cpu_pmu.c
+++ b/drivers/perf/apple_m1_cpu_pmu.c
@@ -524,8 +524,10 @@ static int m1_pmu_set_event_filter(struct hw_perf_event *event,
 {
 	unsigned long config_base = 0;
 
-	if (!attr->exclude_guest)
-		return -EINVAL;
+	if (!attr->exclude_guest) {
+		pr_debug("ARM performance counters do not support mode exclusion\n");
+		return -EOPNOTSUPP;
+	}
 	if (!attr->exclude_kernel)
 		config_base |= M1_PMU_CFG_COUNT_KERNEL;
 	if (!attr->exclude_user)
diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
index 014010d03588..c584165b13ba 100644
--- a/drivers/perf/arm-cmn.c
+++ b/drivers/perf/arm-cmn.c
@@ -811,7 +811,7 @@ static umode_t arm_cmn_event_attr_is_visible(struct kobject *kobj,
 #define CMN_EVENT_HNF_OCC(_model, _name, _event)			\
 	CMN_EVENT_HN_OCC(_model, hnf_##_name, CMN_TYPE_HNF, _event)
 #define CMN_EVENT_HNF_CLS(_model, _name, _event)			\
-	CMN_EVENT_HN_CLS(_model, hnf_##_name, CMN_TYPE_HNS, _event)
+	CMN_EVENT_HN_CLS(_model, hnf_##_name, CMN_TYPE_HNF, _event)
 #define CMN_EVENT_HNF_SNT(_model, _name, _event)			\
 	CMN_EVENT_HN_SNT(_model, hnf_##_name, CMN_TYPE_HNF, _event)
 
@@ -1816,7 +1816,7 @@ static int arm_cmn_event_add(struct perf_event *event, int flags)
 			idx = 0;
 			while (cmn->dtc[j].counters[idx])
 				if (++idx == CMN_DT_NUM_COUNTERS)
-					goto free_dtms;
+					return -ENOSPC;
 		}
 		hw->dtc_idx[j] = idx;
 	}
diff --git a/drivers/perf/arm_cspmu/arm_cspmu.c b/drivers/perf/arm_cspmu/arm_cspmu.c
index 2cc35dded007..50b89b989ce7 100644
--- a/drivers/perf/arm_cspmu/arm_cspmu.c
+++ b/drivers/perf/arm_cspmu/arm_cspmu.c
@@ -1108,7 +1108,6 @@ static int arm_cspmu_request_irq(struct arm_cspmu *cspmu)
 
 static inline int arm_cspmu_find_cpu_container(int cpu, u32 container_uid)
 {
-	u64 acpi_uid;
 	struct device *cpu_dev;
 	struct acpi_device *acpi_dev;
 
@@ -1118,8 +1117,7 @@ static inline int arm_cspmu_find_cpu_container(int cpu, u32 container_uid)
 
 	acpi_dev = ACPI_COMPANION(cpu_dev);
 	while (acpi_dev) {
-		if (acpi_dev_hid_uid_match(acpi_dev, ACPI_PROCESSOR_CONTAINER_HID, NULL) &&
-		    !acpi_dev_uid_to_integer(acpi_dev, &acpi_uid) && acpi_uid == container_uid)
+		if (acpi_dev_hid_uid_match(acpi_dev, ACPI_PROCESSOR_CONTAINER_HID, container_uid))
 			return 0;
 
 		acpi_dev = acpi_dev_parent(acpi_dev);
diff --git a/drivers/perf/arm_dsu_pmu.c b/drivers/perf/arm_dsu_pmu.c
index 8223c49bd082..7ec4498e312f 100644
--- a/drivers/perf/arm_dsu_pmu.c
+++ b/drivers/perf/arm_dsu_pmu.c
@@ -371,7 +371,7 @@ static inline u32 dsu_pmu_get_reset_overflow(void)
 	return __dsu_pmu_get_reset_overflow();
 }
 
-/**
+/*
  * dsu_pmu_set_event_period: Set the period for the counter.
  *
  * All DSU PMU event counters, except the cycle counter are 32bit
@@ -602,7 +602,7 @@ static struct dsu_pmu *dsu_pmu_alloc(struct platform_device *pdev)
 	return dsu_pmu;
 }
 
-/**
+/*
  * dsu_pmu_dt_get_cpus: Get the list of CPUs in the cluster
  * from device tree.
  */
@@ -632,7 +632,7 @@ static int dsu_pmu_dt_get_cpus(struct device *dev, cpumask_t *mask)
 	return 0;
 }
 
-/**
+/*
  * dsu_pmu_acpi_get_cpus: Get the list of CPUs in the cluster
  * from ACPI.
  */
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index d712a19e47ac..8458fe2cebb4 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -445,7 +445,7 @@ __hw_perf_event_init(struct perf_event *event)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
-	int mapping;
+	int mapping, ret;
 
 	hwc->flags = 0;
 	mapping = armpmu->map_event(event);
@@ -470,11 +470,10 @@ __hw_perf_event_init(struct perf_event *event)
 	/*
 	 * Check whether we need to exclude the counter from certain modes.
 	 */
-	if (armpmu->set_event_filter &&
-	    armpmu->set_event_filter(hwc, &event->attr)) {
-		pr_debug("ARM performance counters do not support "
-			 "mode exclusion\n");
-		return -EOPNOTSUPP;
+	if (armpmu->set_event_filter) {
+		ret = armpmu->set_event_filter(hwc, &event->attr);
+		if (ret)
+			return ret;
 	}
 
 	/*
@@ -893,7 +892,6 @@ struct arm_pmu *armpmu_alloc(void)
 		struct pmu_hw_events *events;
 
 		events = per_cpu_ptr(pmu->hw_events, cpu);
-		raw_spin_lock_init(&events->pmu_lock);
 		events->percpu_pmu = pmu;
 	}
 
diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index 6ca7be05229c..23fa6c5da82c 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -15,6 +15,7 @@
 #include <clocksource/arm_arch_timer.h>
 
 #include <linux/acpi.h>
+#include <linux/bitfield.h>
 #include <linux/clocksource.h>
 #include <linux/of.h>
 #include <linux/perf/arm_pmu.h>
@@ -169,7 +170,11 @@ armv8pmu_events_sysfs_show(struct device *dev,
 	PMU_EVENT_ATTR_ID(name, armv8pmu_events_sysfs_show, config)
 
 static struct attribute *armv8_pmuv3_event_attrs[] = {
-	ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR),
+	/*
+	 * Don't expose the sw_incr event in /sys. It's not usable as writes to
+	 * PMSWINC_EL0 will trap as PMUSERENR.{SW,EN}=={0,0} and event rotation
+	 * means we don't have a fixed event<->counter relationship regardless.
+	 */
 	ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL),
 	ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL),
 	ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL),
@@ -294,26 +299,66 @@ static const struct attribute_group armv8_pmuv3_events_attr_group = {
 	.is_visible = armv8pmu_event_attr_is_visible,
 };
 
-PMU_FORMAT_ATTR(event, "config:0-15");
-PMU_FORMAT_ATTR(long, "config1:0");
-PMU_FORMAT_ATTR(rdpmc, "config1:1");
+/* User ABI */
+#define ATTR_CFG_FLD_event_CFG		config
+#define ATTR_CFG_FLD_event_LO		0
+#define ATTR_CFG_FLD_event_HI		15
+#define ATTR_CFG_FLD_long_CFG		config1
+#define ATTR_CFG_FLD_long_LO		0
+#define ATTR_CFG_FLD_long_HI		0
+#define ATTR_CFG_FLD_rdpmc_CFG		config1
+#define ATTR_CFG_FLD_rdpmc_LO		1
+#define ATTR_CFG_FLD_rdpmc_HI		1
+#define ATTR_CFG_FLD_threshold_count_CFG	config1 /* PMEVTYPER.TC[0] */
+#define ATTR_CFG_FLD_threshold_count_LO		2
+#define ATTR_CFG_FLD_threshold_count_HI		2
+#define ATTR_CFG_FLD_threshold_compare_CFG	config1 /* PMEVTYPER.TC[2:1] */
+#define ATTR_CFG_FLD_threshold_compare_LO	3
+#define ATTR_CFG_FLD_threshold_compare_HI	4
+#define ATTR_CFG_FLD_threshold_CFG		config1 /* PMEVTYPER.TH */
+#define ATTR_CFG_FLD_threshold_LO		5
+#define ATTR_CFG_FLD_threshold_HI		16
+
+GEN_PMU_FORMAT_ATTR(event);
+GEN_PMU_FORMAT_ATTR(long);
+GEN_PMU_FORMAT_ATTR(rdpmc);
+GEN_PMU_FORMAT_ATTR(threshold_count);
+GEN_PMU_FORMAT_ATTR(threshold_compare);
+GEN_PMU_FORMAT_ATTR(threshold);
 
 static int sysctl_perf_user_access __read_mostly;
 
-static inline bool armv8pmu_event_is_64bit(struct perf_event *event)
+static bool armv8pmu_event_is_64bit(struct perf_event *event)
+{
+	return ATTR_CFG_GET_FLD(&event->attr, long);
+}
+
+static bool armv8pmu_event_want_user_access(struct perf_event *event)
 {
-	return event->attr.config1 & 0x1;
+	return ATTR_CFG_GET_FLD(&event->attr, rdpmc);
 }
 
-static inline bool armv8pmu_event_want_user_access(struct perf_event *event)
+static u8 armv8pmu_event_threshold_control(struct perf_event_attr *attr)
 {
-	return event->attr.config1 & 0x2;
+	u8 th_compare = ATTR_CFG_GET_FLD(attr, threshold_compare);
+	u8 th_count = ATTR_CFG_GET_FLD(attr, threshold_count);
+
+	/*
+	 * The count bit is always the bottom bit of the full control field, and
+	 * the comparison is the upper two bits, but it's not explicitly
+	 * labelled in the Arm ARM. For the Perf interface we split it into two
+	 * fields, so reconstruct it here.
+	 */
+	return (th_compare << 1) | th_count;
 }
 
 static struct attribute *armv8_pmuv3_format_attrs[] = {
 	&format_attr_event.attr,
 	&format_attr_long.attr,
 	&format_attr_rdpmc.attr,
+	&format_attr_threshold.attr,
+	&format_attr_threshold_compare.attr,
+	&format_attr_threshold_count.attr,
 	NULL,
 };
 
@@ -327,7 +372,7 @@ static ssize_t slots_show(struct device *dev, struct device_attribute *attr,
 {
 	struct pmu *pmu = dev_get_drvdata(dev);
 	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
-	u32 slots = cpu_pmu->reg_pmmir & ARMV8_PMU_SLOTS_MASK;
+	u32 slots = FIELD_GET(ARMV8_PMU_SLOTS, cpu_pmu->reg_pmmir);
 
 	return sysfs_emit(page, "0x%08x\n", slots);
 }
@@ -339,8 +384,7 @@ static ssize_t bus_slots_show(struct device *dev, struct device_attribute *attr,
 {
 	struct pmu *pmu = dev_get_drvdata(dev);
 	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
-	u32 bus_slots = (cpu_pmu->reg_pmmir >> ARMV8_PMU_BUS_SLOTS_SHIFT)
-			& ARMV8_PMU_BUS_SLOTS_MASK;
+	u32 bus_slots = FIELD_GET(ARMV8_PMU_BUS_SLOTS, cpu_pmu->reg_pmmir);
 
 	return sysfs_emit(page, "0x%08x\n", bus_slots);
 }
@@ -352,8 +396,7 @@ static ssize_t bus_width_show(struct device *dev, struct device_attribute *attr,
 {
 	struct pmu *pmu = dev_get_drvdata(dev);
 	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
-	u32 bus_width = (cpu_pmu->reg_pmmir >> ARMV8_PMU_BUS_WIDTH_SHIFT)
-			& ARMV8_PMU_BUS_WIDTH_MASK;
+	u32 bus_width = FIELD_GET(ARMV8_PMU_BUS_WIDTH, cpu_pmu->reg_pmmir);
 	u32 val = 0;
 
 	/* Encoded as Log2(number of bytes), plus one */
@@ -365,10 +408,38 @@ static ssize_t bus_width_show(struct device *dev, struct device_attribute *attr,
 
 static DEVICE_ATTR_RO(bus_width);
 
+static u32 threshold_max(struct arm_pmu *cpu_pmu)
+{
+	/*
+	 * PMMIR.THWIDTH is readable and non-zero on aarch32, but it would be
+	 * impossible to write the threshold in the upper 32 bits of PMEVTYPER.
+	 */
+	if (IS_ENABLED(CONFIG_ARM))
+		return 0;
+
+	/*
+	 * The largest value that can be written to PMEVTYPER<n>_EL0.TH is
+	 * (2 ^ PMMIR.THWIDTH) - 1.
+	 */
+	return (1 << FIELD_GET(ARMV8_PMU_THWIDTH, cpu_pmu->reg_pmmir)) - 1;
+}
+
+static ssize_t threshold_max_show(struct device *dev,
+				  struct device_attribute *attr, char *page)
+{
+	struct pmu *pmu = dev_get_drvdata(dev);
+	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
+
+	return sysfs_emit(page, "0x%08x\n", threshold_max(cpu_pmu));
+}
+
+static DEVICE_ATTR_RO(threshold_max);
+
 static struct attribute *armv8_pmuv3_caps_attrs[] = {
 	&dev_attr_slots.attr,
 	&dev_attr_bus_slots.attr,
 	&dev_attr_bus_width.attr,
+	&dev_attr_threshold_max.attr,
 	NULL,
 };
 
@@ -397,7 +468,7 @@ static bool armv8pmu_has_long_event(struct arm_pmu *cpu_pmu)
 	return (IS_ENABLED(CONFIG_ARM64) && is_pmuv3p5(cpu_pmu->pmuver));
 }
 
-static inline bool armv8pmu_event_has_user_read(struct perf_event *event)
+static bool armv8pmu_event_has_user_read(struct perf_event *event)
 {
 	return event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT;
 }
@@ -407,7 +478,7 @@ static inline bool armv8pmu_event_has_user_read(struct perf_event *event)
  * except when we have allocated the 64bit cycle counter (for CPU
  * cycles event) or when user space counter access is enabled.
  */
-static inline bool armv8pmu_event_is_chained(struct perf_event *event)
+static bool armv8pmu_event_is_chained(struct perf_event *event)
 {
 	int idx = event->hw.idx;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
@@ -428,36 +499,36 @@ static inline bool armv8pmu_event_is_chained(struct perf_event *event)
 #define	ARMV8_IDX_TO_COUNTER(x)	\
 	(((x) - ARMV8_IDX_COUNTER0) & ARMV8_PMU_COUNTER_MASK)
 
-static inline u64 armv8pmu_pmcr_read(void)
+static u64 armv8pmu_pmcr_read(void)
 {
 	return read_pmcr();
 }
 
-static inline void armv8pmu_pmcr_write(u64 val)
+static void armv8pmu_pmcr_write(u64 val)
 {
 	val &= ARMV8_PMU_PMCR_MASK;
 	isb();
 	write_pmcr(val);
 }
 
-static inline int armv8pmu_has_overflowed(u32 pmovsr)
+static int armv8pmu_has_overflowed(u32 pmovsr)
 {
 	return pmovsr & ARMV8_PMU_OVERFLOWED_MASK;
 }
 
-static inline int armv8pmu_counter_has_overflowed(u32 pmnc, int idx)
+static int armv8pmu_counter_has_overflowed(u32 pmnc, int idx)
 {
 	return pmnc & BIT(ARMV8_IDX_TO_COUNTER(idx));
 }
 
-static inline u64 armv8pmu_read_evcntr(int idx)
+static u64 armv8pmu_read_evcntr(int idx)
 {
 	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
 
 	return read_pmevcntrn(counter);
 }
 
-static inline u64 armv8pmu_read_hw_counter(struct perf_event *event)
+static u64 armv8pmu_read_hw_counter(struct perf_event *event)
 {
 	int idx = event->hw.idx;
 	u64 val = armv8pmu_read_evcntr(idx);
@@ -519,14 +590,14 @@ static u64 armv8pmu_read_counter(struct perf_event *event)
 	return  armv8pmu_unbias_long_counter(event, value);
 }
 
-static inline void armv8pmu_write_evcntr(int idx, u64 value)
+static void armv8pmu_write_evcntr(int idx, u64 value)
 {
 	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
 
 	write_pmevcntrn(counter, value);
 }
 
-static inline void armv8pmu_write_hw_counter(struct perf_event *event,
+static void armv8pmu_write_hw_counter(struct perf_event *event,
 					     u64 value)
 {
 	int idx = event->hw.idx;
@@ -552,15 +623,22 @@ static void armv8pmu_write_counter(struct perf_event *event, u64 value)
 		armv8pmu_write_hw_counter(event, value);
 }
 
-static inline void armv8pmu_write_evtype(int idx, u32 val)
+static void armv8pmu_write_evtype(int idx, unsigned long val)
 {
 	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
+	unsigned long mask = ARMV8_PMU_EVTYPE_EVENT |
+			     ARMV8_PMU_INCLUDE_EL2 |
+			     ARMV8_PMU_EXCLUDE_EL0 |
+			     ARMV8_PMU_EXCLUDE_EL1;
 
-	val &= ARMV8_PMU_EVTYPE_MASK;
+	if (IS_ENABLED(CONFIG_ARM64))
+		mask |= ARMV8_PMU_EVTYPE_TC | ARMV8_PMU_EVTYPE_TH;
+
+	val &= mask;
 	write_pmevtypern(counter, val);
 }
 
-static inline void armv8pmu_write_event_type(struct perf_event *event)
+static void armv8pmu_write_event_type(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
@@ -594,7 +672,7 @@ static u32 armv8pmu_event_cnten_mask(struct perf_event *event)
 	return mask;
 }
 
-static inline void armv8pmu_enable_counter(u32 mask)
+static void armv8pmu_enable_counter(u32 mask)
 {
 	/*
 	 * Make sure event configuration register writes are visible before we
@@ -604,7 +682,7 @@ static inline void armv8pmu_enable_counter(u32 mask)
 	write_pmcntenset(mask);
 }
 
-static inline void armv8pmu_enable_event_counter(struct perf_event *event)
+static void armv8pmu_enable_event_counter(struct perf_event *event)
 {
 	struct perf_event_attr *attr = &event->attr;
 	u32 mask = armv8pmu_event_cnten_mask(event);
@@ -616,7 +694,7 @@ static inline void armv8pmu_enable_event_counter(struct perf_event *event)
 		armv8pmu_enable_counter(mask);
 }
 
-static inline void armv8pmu_disable_counter(u32 mask)
+static void armv8pmu_disable_counter(u32 mask)
 {
 	write_pmcntenclr(mask);
 	/*
@@ -626,7 +704,7 @@ static inline void armv8pmu_disable_counter(u32 mask)
 	isb();
 }
 
-static inline void armv8pmu_disable_event_counter(struct perf_event *event)
+static void armv8pmu_disable_event_counter(struct perf_event *event)
 {
 	struct perf_event_attr *attr = &event->attr;
 	u32 mask = armv8pmu_event_cnten_mask(event);
@@ -638,18 +716,18 @@ static inline void armv8pmu_disable_event_counter(struct perf_event *event)
 		armv8pmu_disable_counter(mask);
 }
 
-static inline void armv8pmu_enable_intens(u32 mask)
+static void armv8pmu_enable_intens(u32 mask)
 {
 	write_pmintenset(mask);
 }
 
-static inline void armv8pmu_enable_event_irq(struct perf_event *event)
+static void armv8pmu_enable_event_irq(struct perf_event *event)
 {
 	u32 counter = ARMV8_IDX_TO_COUNTER(event->hw.idx);
 	armv8pmu_enable_intens(BIT(counter));
 }
 
-static inline void armv8pmu_disable_intens(u32 mask)
+static void armv8pmu_disable_intens(u32 mask)
 {
 	write_pmintenclr(mask);
 	isb();
@@ -658,13 +736,13 @@ static inline void armv8pmu_disable_intens(u32 mask)
 	isb();
 }
 
-static inline void armv8pmu_disable_event_irq(struct perf_event *event)
+static void armv8pmu_disable_event_irq(struct perf_event *event)
 {
 	u32 counter = ARMV8_IDX_TO_COUNTER(event->hw.idx);
 	armv8pmu_disable_intens(BIT(counter));
 }
 
-static inline u32 armv8pmu_getreset_flags(void)
+static u32 armv8pmu_getreset_flags(void)
 {
 	u32 value;
 
@@ -672,7 +750,7 @@ static inline u32 armv8pmu_getreset_flags(void)
 	value = read_pmovsclr();
 
 	/* Write to clear flags */
-	value &= ARMV8_PMU_OVSR_MASK;
+	value &= ARMV8_PMU_OVERFLOWED_MASK;
 	write_pmovsclr(value);
 
 	return value;
@@ -914,9 +992,15 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
 				     struct perf_event_attr *attr)
 {
 	unsigned long config_base = 0;
-
-	if (attr->exclude_idle)
-		return -EPERM;
+	struct perf_event *perf_event = container_of(attr, struct perf_event,
+						     attr);
+	struct arm_pmu *cpu_pmu = to_arm_pmu(perf_event->pmu);
+	u32 th;
+
+	if (attr->exclude_idle) {
+		pr_debug("ARM performance counters do not support mode exclusion\n");
+		return -EOPNOTSUPP;
+	}
 
 	/*
 	 * If we're running in hyp mode, then we *are* the hypervisor.
@@ -946,6 +1030,22 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
 		config_base |= ARMV8_PMU_EXCLUDE_EL0;
 
 	/*
+	 * If FEAT_PMUv3_TH isn't implemented, then THWIDTH (threshold_max) will
+	 * be 0 and will also trigger this check, preventing it from being used.
+	 */
+	th = ATTR_CFG_GET_FLD(attr, threshold);
+	if (th > threshold_max(cpu_pmu)) {
+		pr_debug("PMU event threshold exceeds max value\n");
+		return -EINVAL;
+	}
+
+	if (IS_ENABLED(CONFIG_ARM64) && th) {
+		config_base |= FIELD_PREP(ARMV8_PMU_EVTYPE_TH, th);
+		config_base |= FIELD_PREP(ARMV8_PMU_EVTYPE_TC,
+					  armv8pmu_event_threshold_control(attr));
+	}
+
+	/*
 	 * Install the filter into config_base as this is used to
 	 * construct the event type.
 	 */
@@ -1107,8 +1207,7 @@ static void __armv8pmu_probe_pmu(void *info)
 	probe->present = true;
 
 	/* Read the nb of CNTx counters supported from PMNC */
-	cpu_pmu->num_events = (armv8pmu_pmcr_read() >> ARMV8_PMU_PMCR_N_SHIFT)
-		& ARMV8_PMU_PMCR_N_MASK;
+	cpu_pmu->num_events = FIELD_GET(ARMV8_PMU_PMCR_N, armv8pmu_pmcr_read());
 
 	/* Add the CPU cycles counter */
 	cpu_pmu->num_events += 1;
@@ -1221,6 +1320,12 @@ static int name##_pmu_init(struct arm_pmu *cpu_pmu)			\
 	return armv8_pmu_init(cpu_pmu, #name, armv8_pmuv3_map_event);	\
 }
 
+#define PMUV3_INIT_MAP_EVENT(name, map_event)				\
+static int name##_pmu_init(struct arm_pmu *cpu_pmu)			\
+{									\
+	return armv8_pmu_init(cpu_pmu, #name, map_event);		\
+}
+
 PMUV3_INIT_SIMPLE(armv8_pmuv3)
 
 PMUV3_INIT_SIMPLE(armv8_cortex_a34)
@@ -1247,51 +1352,24 @@ PMUV3_INIT_SIMPLE(armv8_neoverse_v1)
 PMUV3_INIT_SIMPLE(armv8_nvidia_carmel)
 PMUV3_INIT_SIMPLE(armv8_nvidia_denver)
 
-static int armv8_a35_pmu_init(struct arm_pmu *cpu_pmu)
-{
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a35", armv8_a53_map_event);
-}
-
-static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu)
-{
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a53", armv8_a53_map_event);
-}
-
-static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu)
-{
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a57", armv8_a57_map_event);
-}
-
-static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu)
-{
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a72", armv8_a57_map_event);
-}
-
-static int armv8_a73_pmu_init(struct arm_pmu *cpu_pmu)
-{
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a73", armv8_a73_map_event);
-}
-
-static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu)
-{
-	return armv8_pmu_init(cpu_pmu, "armv8_cavium_thunder", armv8_thunder_map_event);
-}
-
-static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu)
-{
-	return armv8_pmu_init(cpu_pmu, "armv8_brcm_vulcan", armv8_vulcan_map_event);
-}
+PMUV3_INIT_MAP_EVENT(armv8_cortex_a35, armv8_a53_map_event)
+PMUV3_INIT_MAP_EVENT(armv8_cortex_a53, armv8_a53_map_event)
+PMUV3_INIT_MAP_EVENT(armv8_cortex_a57, armv8_a57_map_event)
+PMUV3_INIT_MAP_EVENT(armv8_cortex_a72, armv8_a57_map_event)
+PMUV3_INIT_MAP_EVENT(armv8_cortex_a73, armv8_a73_map_event)
+PMUV3_INIT_MAP_EVENT(armv8_cavium_thunder, armv8_thunder_map_event)
+PMUV3_INIT_MAP_EVENT(armv8_brcm_vulcan, armv8_vulcan_map_event)
 
 static const struct of_device_id armv8_pmu_of_device_ids[] = {
 	{.compatible = "arm,armv8-pmuv3",	.data = armv8_pmuv3_pmu_init},
 	{.compatible = "arm,cortex-a34-pmu",	.data = armv8_cortex_a34_pmu_init},
-	{.compatible = "arm,cortex-a35-pmu",	.data = armv8_a35_pmu_init},
-	{.compatible = "arm,cortex-a53-pmu",	.data = armv8_a53_pmu_init},
+	{.compatible = "arm,cortex-a35-pmu",	.data = armv8_cortex_a35_pmu_init},
+	{.compatible = "arm,cortex-a53-pmu",	.data = armv8_cortex_a53_pmu_init},
 	{.compatible = "arm,cortex-a55-pmu",	.data = armv8_cortex_a55_pmu_init},
-	{.compatible = "arm,cortex-a57-pmu",	.data = armv8_a57_pmu_init},
+	{.compatible = "arm,cortex-a57-pmu",	.data = armv8_cortex_a57_pmu_init},
 	{.compatible = "arm,cortex-a65-pmu",	.data = armv8_cortex_a65_pmu_init},
-	{.compatible = "arm,cortex-a72-pmu",	.data = armv8_a72_pmu_init},
-	{.compatible = "arm,cortex-a73-pmu",	.data = armv8_a73_pmu_init},
+	{.compatible = "arm,cortex-a72-pmu",	.data = armv8_cortex_a72_pmu_init},
+	{.compatible = "arm,cortex-a73-pmu",	.data = armv8_cortex_a73_pmu_init},
 	{.compatible = "arm,cortex-a75-pmu",	.data = armv8_cortex_a75_pmu_init},
 	{.compatible = "arm,cortex-a76-pmu",	.data = armv8_cortex_a76_pmu_init},
 	{.compatible = "arm,cortex-a77-pmu",	.data = armv8_cortex_a77_pmu_init},
@@ -1309,8 +1387,8 @@ static const struct of_device_id armv8_pmu_of_device_ids[] = {
 	{.compatible = "arm,neoverse-n1-pmu",	.data = armv8_neoverse_n1_pmu_init},
 	{.compatible = "arm,neoverse-n2-pmu",	.data = armv9_neoverse_n2_pmu_init},
 	{.compatible = "arm,neoverse-v1-pmu",	.data = armv8_neoverse_v1_pmu_init},
-	{.compatible = "cavium,thunder-pmu",	.data = armv8_thunder_pmu_init},
-	{.compatible = "brcm,vulcan-pmu",	.data = armv8_vulcan_pmu_init},
+	{.compatible = "cavium,thunder-pmu",	.data = armv8_cavium_thunder_pmu_init},
+	{.compatible = "brcm,vulcan-pmu",	.data = armv8_brcm_vulcan_pmu_init},
 	{.compatible = "nvidia,carmel-pmu",	.data = armv8_nvidia_carmel_pmu_init},
 	{.compatible = "nvidia,denver-pmu",	.data = armv8_nvidia_denver_pmu_init},
 	{},
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index d2b0cbf0e0c4..b622d75d8c9e 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -206,28 +206,6 @@ static const struct attribute_group arm_spe_pmu_cap_group = {
 #define ATTR_CFG_FLD_inv_event_filter_LO	0
 #define ATTR_CFG_FLD_inv_event_filter_HI	63
 
-/* Why does everything I do descend into this? */
-#define __GEN_PMU_FORMAT_ATTR(cfg, lo, hi)				\
-	(lo) == (hi) ? #cfg ":" #lo "\n" : #cfg ":" #lo "-" #hi
-
-#define _GEN_PMU_FORMAT_ATTR(cfg, lo, hi)				\
-	__GEN_PMU_FORMAT_ATTR(cfg, lo, hi)
-
-#define GEN_PMU_FORMAT_ATTR(name)					\
-	PMU_FORMAT_ATTR(name,						\
-	_GEN_PMU_FORMAT_ATTR(ATTR_CFG_FLD_##name##_CFG,			\
-			     ATTR_CFG_FLD_##name##_LO,			\
-			     ATTR_CFG_FLD_##name##_HI))
-
-#define _ATTR_CFG_GET_FLD(attr, cfg, lo, hi)				\
-	((((attr)->cfg) >> lo) & GENMASK(hi - lo, 0))
-
-#define ATTR_CFG_GET_FLD(attr, name)					\
-	_ATTR_CFG_GET_FLD(attr,						\
-			  ATTR_CFG_FLD_##name##_CFG,			\
-			  ATTR_CFG_FLD_##name##_LO,			\
-			  ATTR_CFG_FLD_##name##_HI)
-
 GEN_PMU_FORMAT_ATTR(ts_enable);
 GEN_PMU_FORMAT_ATTR(pa_enable);
 GEN_PMU_FORMAT_ATTR(pct_enable);
diff --git a/drivers/perf/dwc_pcie_pmu.c b/drivers/perf/dwc_pcie_pmu.c
new file mode 100644
index 000000000000..957058ad0099
--- /dev/null
+++ b/drivers/perf/dwc_pcie_pmu.c
@@ -0,0 +1,792 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Synopsys DesignWare PCIe PMU driver
+ *
+ * Copyright (C) 2021-2023 Alibaba Inc.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/cpuhotplug.h>
+#include <linux/cpumask.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/perf_event.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/smp.h>
+#include <linux/sysfs.h>
+#include <linux/types.h>
+
+#define DWC_PCIE_VSEC_RAS_DES_ID		0x02
+#define DWC_PCIE_EVENT_CNT_CTL			0x8
+
+/*
+ * Event Counter Data Select includes two parts:
+ * - 27-24: Group number(4-bit: 0..0x7)
+ * - 23-16: Event number(8-bit: 0..0x13) within the Group
+ *
+ * Put them together as in TRM.
+ */
+#define DWC_PCIE_CNT_EVENT_SEL			GENMASK(27, 16)
+#define DWC_PCIE_CNT_LANE_SEL			GENMASK(11, 8)
+#define DWC_PCIE_CNT_STATUS			BIT(7)
+#define DWC_PCIE_CNT_ENABLE			GENMASK(4, 2)
+#define DWC_PCIE_PER_EVENT_OFF			0x1
+#define DWC_PCIE_PER_EVENT_ON			0x3
+#define DWC_PCIE_EVENT_CLEAR			GENMASK(1, 0)
+#define DWC_PCIE_EVENT_PER_CLEAR		0x1
+
+#define DWC_PCIE_EVENT_CNT_DATA			0xC
+
+#define DWC_PCIE_TIME_BASED_ANAL_CTL		0x10
+#define DWC_PCIE_TIME_BASED_REPORT_SEL		GENMASK(31, 24)
+#define DWC_PCIE_TIME_BASED_DURATION_SEL	GENMASK(15, 8)
+#define DWC_PCIE_DURATION_MANUAL_CTL		0x0
+#define DWC_PCIE_DURATION_1MS			0x1
+#define DWC_PCIE_DURATION_10MS			0x2
+#define DWC_PCIE_DURATION_100MS			0x3
+#define DWC_PCIE_DURATION_1S			0x4
+#define DWC_PCIE_DURATION_2S			0x5
+#define DWC_PCIE_DURATION_4S			0x6
+#define DWC_PCIE_DURATION_4US			0xFF
+#define DWC_PCIE_TIME_BASED_TIMER_START		BIT(0)
+#define DWC_PCIE_TIME_BASED_CNT_ENABLE		0x1
+
+#define DWC_PCIE_TIME_BASED_ANAL_DATA_REG_LOW	0x14
+#define DWC_PCIE_TIME_BASED_ANAL_DATA_REG_HIGH	0x18
+
+/* Event attributes */
+#define DWC_PCIE_CONFIG_EVENTID			GENMASK(15, 0)
+#define DWC_PCIE_CONFIG_TYPE			GENMASK(19, 16)
+#define DWC_PCIE_CONFIG_LANE			GENMASK(27, 20)
+
+#define DWC_PCIE_EVENT_ID(event)	FIELD_GET(DWC_PCIE_CONFIG_EVENTID, (event)->attr.config)
+#define DWC_PCIE_EVENT_TYPE(event)	FIELD_GET(DWC_PCIE_CONFIG_TYPE, (event)->attr.config)
+#define DWC_PCIE_EVENT_LANE(event)	FIELD_GET(DWC_PCIE_CONFIG_LANE, (event)->attr.config)
+
+enum dwc_pcie_event_type {
+	DWC_PCIE_TIME_BASE_EVENT,
+	DWC_PCIE_LANE_EVENT,
+	DWC_PCIE_EVENT_TYPE_MAX,
+};
+
+#define DWC_PCIE_LANE_EVENT_MAX_PERIOD		GENMASK_ULL(31, 0)
+#define DWC_PCIE_MAX_PERIOD			GENMASK_ULL(63, 0)
+
+struct dwc_pcie_pmu {
+	struct pmu		pmu;
+	struct pci_dev		*pdev;		/* Root Port device */
+	u16			ras_des_offset;
+	u32			nr_lanes;
+
+	struct list_head	pmu_node;
+	struct hlist_node	cpuhp_node;
+	struct perf_event	*event[DWC_PCIE_EVENT_TYPE_MAX];
+	int			on_cpu;
+};
+
+#define to_dwc_pcie_pmu(p) (container_of(p, struct dwc_pcie_pmu, pmu))
+
+static int dwc_pcie_pmu_hp_state;
+static struct list_head dwc_pcie_dev_info_head =
+				LIST_HEAD_INIT(dwc_pcie_dev_info_head);
+static bool notify;
+
+struct dwc_pcie_dev_info {
+	struct platform_device *plat_dev;
+	struct pci_dev *pdev;
+	struct list_head dev_node;
+};
+
+struct dwc_pcie_vendor_id {
+	int vendor_id;
+};
+
+static const struct dwc_pcie_vendor_id dwc_pcie_vendor_ids[] = {
+	{.vendor_id = PCI_VENDOR_ID_ALIBABA },
+	{} /* terminator */
+};
+
+static ssize_t cpumask_show(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	struct dwc_pcie_pmu *pcie_pmu = to_dwc_pcie_pmu(dev_get_drvdata(dev));
+
+	return cpumap_print_to_pagebuf(true, buf, cpumask_of(pcie_pmu->on_cpu));
+}
+static DEVICE_ATTR_RO(cpumask);
+
+static struct attribute *dwc_pcie_pmu_cpumask_attrs[] = {
+	&dev_attr_cpumask.attr,
+	NULL
+};
+
+static struct attribute_group dwc_pcie_cpumask_attr_group = {
+	.attrs = dwc_pcie_pmu_cpumask_attrs,
+};
+
+struct dwc_pcie_format_attr {
+	struct device_attribute attr;
+	u64 field;
+	int config;
+};
+
+PMU_FORMAT_ATTR(eventid, "config:0-15");
+PMU_FORMAT_ATTR(type, "config:16-19");
+PMU_FORMAT_ATTR(lane, "config:20-27");
+
+static struct attribute *dwc_pcie_format_attrs[] = {
+	&format_attr_type.attr,
+	&format_attr_eventid.attr,
+	&format_attr_lane.attr,
+	NULL,
+};
+
+static struct attribute_group dwc_pcie_format_attrs_group = {
+	.name = "format",
+	.attrs = dwc_pcie_format_attrs,
+};
+
+struct dwc_pcie_event_attr {
+	struct device_attribute attr;
+	enum dwc_pcie_event_type type;
+	u16 eventid;
+	u8 lane;
+};
+
+static ssize_t dwc_pcie_event_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct dwc_pcie_event_attr *eattr;
+
+	eattr = container_of(attr, typeof(*eattr), attr);
+
+	if (eattr->type == DWC_PCIE_LANE_EVENT)
+		return sysfs_emit(buf, "eventid=0x%x,type=0x%x,lane=?\n",
+				  eattr->eventid, eattr->type);
+	else if (eattr->type == DWC_PCIE_TIME_BASE_EVENT)
+		return sysfs_emit(buf, "eventid=0x%x,type=0x%x\n",
+				  eattr->eventid, eattr->type);
+
+	return 0;
+}
+
+#define DWC_PCIE_EVENT_ATTR(_name, _type, _eventid, _lane)		\
+	(&((struct dwc_pcie_event_attr[]) {{				\
+		.attr = __ATTR(_name, 0444, dwc_pcie_event_show, NULL),	\
+		.type = _type,						\
+		.eventid = _eventid,					\
+		.lane = _lane,						\
+	}})[0].attr.attr)
+
+#define DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(_name, _eventid)		\
+	DWC_PCIE_EVENT_ATTR(_name, DWC_PCIE_TIME_BASE_EVENT, _eventid, 0)
+#define DWC_PCIE_PMU_LANE_EVENT_ATTR(_name, _eventid)			\
+	DWC_PCIE_EVENT_ATTR(_name, DWC_PCIE_LANE_EVENT, _eventid, 0)
+
+static struct attribute *dwc_pcie_pmu_time_event_attrs[] = {
+	/* Group #0 */
+	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(one_cycle, 0x00),
+	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(TX_L0S, 0x01),
+	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(RX_L0S, 0x02),
+	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(L0, 0x03),
+	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(L1, 0x04),
+	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(L1_1, 0x05),
+	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(L1_2, 0x06),
+	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(CFG_RCVRY, 0x07),
+	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(TX_RX_L0S, 0x08),
+	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(L1_AUX, 0x09),
+
+	/* Group #1 */
+	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(Tx_PCIe_TLP_Data_Payload, 0x20),
+	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(Rx_PCIe_TLP_Data_Payload, 0x21),
+	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(Tx_CCIX_TLP_Data_Payload, 0x22),
+	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(Rx_CCIX_TLP_Data_Payload, 0x23),
+
+	/*
+	 * Leave it to the user to specify the lane ID to avoid generating
+	 * a list of hundreds of events.
+	 */
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(tx_ack_dllp, 0x600),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(tx_update_fc_dllp, 0x601),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(rx_ack_dllp, 0x602),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(rx_update_fc_dllp, 0x603),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(rx_nulified_tlp, 0x604),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(tx_nulified_tlp, 0x605),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(rx_duplicate_tl, 0x606),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(tx_memory_write, 0x700),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(tx_memory_read, 0x701),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(tx_configuration_write, 0x702),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(tx_configuration_read, 0x703),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(tx_io_write, 0x704),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(tx_io_read, 0x705),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(tx_completion_without_data, 0x706),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(tx_completion_with_data, 0x707),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(tx_message_tlp, 0x708),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(tx_atomic, 0x709),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(tx_tlp_with_prefix, 0x70A),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(rx_memory_write, 0x70B),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(rx_memory_read, 0x70C),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(rx_io_write, 0x70F),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(rx_io_read, 0x710),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(rx_completion_without_data, 0x711),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(rx_completion_with_data, 0x712),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(rx_message_tlp, 0x713),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(rx_atomic, 0x714),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(rx_tlp_with_prefix, 0x715),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(tx_ccix_tlp, 0x716),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(rx_ccix_tlp, 0x717),
+	NULL
+};
+
+static const struct attribute_group dwc_pcie_event_attrs_group = {
+	.name = "events",
+	.attrs = dwc_pcie_pmu_time_event_attrs,
+};
+
+static const struct attribute_group *dwc_pcie_attr_groups[] = {
+	&dwc_pcie_event_attrs_group,
+	&dwc_pcie_format_attrs_group,
+	&dwc_pcie_cpumask_attr_group,
+	NULL
+};
+
+static void dwc_pcie_pmu_lane_event_enable(struct dwc_pcie_pmu *pcie_pmu,
+					   bool enable)
+{
+	struct pci_dev *pdev = pcie_pmu->pdev;
+	u16 ras_des_offset = pcie_pmu->ras_des_offset;
+
+	if (enable)
+		pci_clear_and_set_config_dword(pdev,
+					ras_des_offset + DWC_PCIE_EVENT_CNT_CTL,
+					DWC_PCIE_CNT_ENABLE, DWC_PCIE_PER_EVENT_ON);
+	else
+		pci_clear_and_set_config_dword(pdev,
+					ras_des_offset + DWC_PCIE_EVENT_CNT_CTL,
+					DWC_PCIE_CNT_ENABLE, DWC_PCIE_PER_EVENT_OFF);
+}
+
+static void dwc_pcie_pmu_time_based_event_enable(struct dwc_pcie_pmu *pcie_pmu,
+					  bool enable)
+{
+	struct pci_dev *pdev = pcie_pmu->pdev;
+	u16 ras_des_offset = pcie_pmu->ras_des_offset;
+
+	pci_clear_and_set_config_dword(pdev,
+				       ras_des_offset + DWC_PCIE_TIME_BASED_ANAL_CTL,
+				       DWC_PCIE_TIME_BASED_TIMER_START, enable);
+}
+
+static u64 dwc_pcie_pmu_read_lane_event_counter(struct perf_event *event)
+{
+	struct dwc_pcie_pmu *pcie_pmu = to_dwc_pcie_pmu(event->pmu);
+	struct pci_dev *pdev = pcie_pmu->pdev;
+	u16 ras_des_offset = pcie_pmu->ras_des_offset;
+	u32 val;
+
+	pci_read_config_dword(pdev, ras_des_offset + DWC_PCIE_EVENT_CNT_DATA, &val);
+
+	return val;
+}
+
+static u64 dwc_pcie_pmu_read_time_based_counter(struct perf_event *event)
+{
+	struct dwc_pcie_pmu *pcie_pmu = to_dwc_pcie_pmu(event->pmu);
+	struct pci_dev *pdev = pcie_pmu->pdev;
+	int event_id = DWC_PCIE_EVENT_ID(event);
+	u16 ras_des_offset = pcie_pmu->ras_des_offset;
+	u32 lo, hi, ss;
+	u64 val;
+
+	/*
+	 * The 64-bit value of the data counter is spread across two
+	 * registers that are not synchronized. In order to read them
+	 * atomically, ensure that the high 32 bits match before and after
+	 * reading the low 32 bits.
+	 */
+	pci_read_config_dword(pdev,
+		ras_des_offset + DWC_PCIE_TIME_BASED_ANAL_DATA_REG_HIGH, &hi);
+	do {
+		/* snapshot the high 32 bits */
+		ss = hi;
+
+		pci_read_config_dword(
+			pdev, ras_des_offset + DWC_PCIE_TIME_BASED_ANAL_DATA_REG_LOW,
+			&lo);
+		pci_read_config_dword(
+			pdev, ras_des_offset + DWC_PCIE_TIME_BASED_ANAL_DATA_REG_HIGH,
+			&hi);
+	} while (hi != ss);
+
+	val = ((u64)hi << 32) | lo;
+	/*
+	 * The Group#1 event measures the amount of data processed in 16-byte
+	 * units. Simplify the end-user interface by multiplying the counter
+	 * at the point of read.
+	 */
+	if (event_id >= 0x20 && event_id <= 0x23)
+		val *= 16;
+
+	return val;
+}
+
+static void dwc_pcie_pmu_event_update(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	enum dwc_pcie_event_type type = DWC_PCIE_EVENT_TYPE(event);
+	u64 delta, prev, now = 0;
+
+	do {
+		prev = local64_read(&hwc->prev_count);
+
+		if (type == DWC_PCIE_LANE_EVENT)
+			now = dwc_pcie_pmu_read_lane_event_counter(event);
+		else if (type == DWC_PCIE_TIME_BASE_EVENT)
+			now = dwc_pcie_pmu_read_time_based_counter(event);
+
+	} while (local64_cmpxchg(&hwc->prev_count, prev, now) != prev);
+
+	delta = (now - prev) & DWC_PCIE_MAX_PERIOD;
+	/* 32-bit counter for Lane Event Counting */
+	if (type == DWC_PCIE_LANE_EVENT)
+		delta &= DWC_PCIE_LANE_EVENT_MAX_PERIOD;
+
+	local64_add(delta, &event->count);
+}
+
+static int dwc_pcie_pmu_event_init(struct perf_event *event)
+{
+	struct dwc_pcie_pmu *pcie_pmu = to_dwc_pcie_pmu(event->pmu);
+	enum dwc_pcie_event_type type = DWC_PCIE_EVENT_TYPE(event);
+	struct perf_event *sibling;
+	u32 lane;
+
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	/* We don't support sampling */
+	if (is_sampling_event(event))
+		return -EINVAL;
+
+	/* We cannot support task bound events */
+	if (event->cpu < 0 || event->attach_state & PERF_ATTACH_TASK)
+		return -EINVAL;
+
+	if (event->group_leader != event &&
+	    !is_software_event(event->group_leader))
+		return -EINVAL;
+
+	for_each_sibling_event(sibling, event->group_leader) {
+		if (sibling->pmu != event->pmu && !is_software_event(sibling))
+			return -EINVAL;
+	}
+
+	if (type < 0 || type >= DWC_PCIE_EVENT_TYPE_MAX)
+		return -EINVAL;
+
+	if (type == DWC_PCIE_LANE_EVENT) {
+		lane = DWC_PCIE_EVENT_LANE(event);
+		if (lane < 0 || lane >= pcie_pmu->nr_lanes)
+			return -EINVAL;
+	}
+
+	event->cpu = pcie_pmu->on_cpu;
+
+	return 0;
+}
+
+static void dwc_pcie_pmu_event_start(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct dwc_pcie_pmu *pcie_pmu = to_dwc_pcie_pmu(event->pmu);
+	enum dwc_pcie_event_type type = DWC_PCIE_EVENT_TYPE(event);
+
+	hwc->state = 0;
+	local64_set(&hwc->prev_count, 0);
+
+	if (type == DWC_PCIE_LANE_EVENT)
+		dwc_pcie_pmu_lane_event_enable(pcie_pmu, true);
+	else if (type == DWC_PCIE_TIME_BASE_EVENT)
+		dwc_pcie_pmu_time_based_event_enable(pcie_pmu, true);
+}
+
+static void dwc_pcie_pmu_event_stop(struct perf_event *event, int flags)
+{
+	struct dwc_pcie_pmu *pcie_pmu = to_dwc_pcie_pmu(event->pmu);
+	enum dwc_pcie_event_type type = DWC_PCIE_EVENT_TYPE(event);
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
+	if (type == DWC_PCIE_LANE_EVENT)
+		dwc_pcie_pmu_lane_event_enable(pcie_pmu, false);
+	else if (type == DWC_PCIE_TIME_BASE_EVENT)
+		dwc_pcie_pmu_time_based_event_enable(pcie_pmu, false);
+
+	dwc_pcie_pmu_event_update(event);
+	hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+}
+
+static int dwc_pcie_pmu_event_add(struct perf_event *event, int flags)
+{
+	struct dwc_pcie_pmu *pcie_pmu = to_dwc_pcie_pmu(event->pmu);
+	struct pci_dev *pdev = pcie_pmu->pdev;
+	struct hw_perf_event *hwc = &event->hw;
+	enum dwc_pcie_event_type type = DWC_PCIE_EVENT_TYPE(event);
+	int event_id = DWC_PCIE_EVENT_ID(event);
+	int lane = DWC_PCIE_EVENT_LANE(event);
+	u16 ras_des_offset = pcie_pmu->ras_des_offset;
+	u32 ctrl;
+
+	/* one counter for each type and it is in use */
+	if (pcie_pmu->event[type])
+		return -ENOSPC;
+
+	pcie_pmu->event[type] = event;
+	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+
+	if (type == DWC_PCIE_LANE_EVENT) {
+		/* EVENT_COUNTER_DATA_REG needs clear manually */
+		ctrl = FIELD_PREP(DWC_PCIE_CNT_EVENT_SEL, event_id) |
+			FIELD_PREP(DWC_PCIE_CNT_LANE_SEL, lane) |
+			FIELD_PREP(DWC_PCIE_CNT_ENABLE, DWC_PCIE_PER_EVENT_OFF) |
+			FIELD_PREP(DWC_PCIE_EVENT_CLEAR, DWC_PCIE_EVENT_PER_CLEAR);
+		pci_write_config_dword(pdev, ras_des_offset + DWC_PCIE_EVENT_CNT_CTL,
+				       ctrl);
+	} else if (type == DWC_PCIE_TIME_BASE_EVENT) {
+		/*
+		 * TIME_BASED_ANAL_DATA_REG is a 64 bit register, we can safely
+		 * use it with any manually controlled duration. And it is
+		 * cleared when next measurement starts.
+		 */
+		ctrl = FIELD_PREP(DWC_PCIE_TIME_BASED_REPORT_SEL, event_id) |
+			FIELD_PREP(DWC_PCIE_TIME_BASED_DURATION_SEL,
+				   DWC_PCIE_DURATION_MANUAL_CTL) |
+			DWC_PCIE_TIME_BASED_CNT_ENABLE;
+		pci_write_config_dword(
+			pdev, ras_des_offset + DWC_PCIE_TIME_BASED_ANAL_CTL, ctrl);
+	}
+
+	if (flags & PERF_EF_START)
+		dwc_pcie_pmu_event_start(event, PERF_EF_RELOAD);
+
+	perf_event_update_userpage(event);
+
+	return 0;
+}
+
+static void dwc_pcie_pmu_event_del(struct perf_event *event, int flags)
+{
+	struct dwc_pcie_pmu *pcie_pmu = to_dwc_pcie_pmu(event->pmu);
+	enum dwc_pcie_event_type type = DWC_PCIE_EVENT_TYPE(event);
+
+	dwc_pcie_pmu_event_stop(event, flags | PERF_EF_UPDATE);
+	perf_event_update_userpage(event);
+	pcie_pmu->event[type] = NULL;
+}
+
+static void dwc_pcie_pmu_remove_cpuhp_instance(void *hotplug_node)
+{
+	cpuhp_state_remove_instance_nocalls(dwc_pcie_pmu_hp_state, hotplug_node);
+}
+
+/*
+ * Find the binded DES capability device info of a PCI device.
+ * @pdev: The PCI device.
+ */
+static struct dwc_pcie_dev_info *dwc_pcie_find_dev_info(struct pci_dev *pdev)
+{
+	struct dwc_pcie_dev_info *dev_info;
+
+	list_for_each_entry(dev_info, &dwc_pcie_dev_info_head, dev_node)
+		if (dev_info->pdev == pdev)
+			return dev_info;
+
+	return NULL;
+}
+
+static void dwc_pcie_unregister_pmu(void *data)
+{
+	struct dwc_pcie_pmu *pcie_pmu = data;
+
+	perf_pmu_unregister(&pcie_pmu->pmu);
+}
+
+static bool dwc_pcie_match_des_cap(struct pci_dev *pdev)
+{
+	const struct dwc_pcie_vendor_id *vid;
+	u16 vsec = 0;
+	u32 val;
+
+	if (!pci_is_pcie(pdev) || !(pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT))
+		return false;
+
+	for (vid = dwc_pcie_vendor_ids; vid->vendor_id; vid++) {
+		vsec = pci_find_vsec_capability(pdev, vid->vendor_id,
+						DWC_PCIE_VSEC_RAS_DES_ID);
+		if (vsec)
+			break;
+	}
+	if (!vsec)
+		return false;
+
+	pci_read_config_dword(pdev, vsec + PCI_VNDR_HEADER, &val);
+	if (PCI_VNDR_HEADER_REV(val) != 0x04)
+		return false;
+
+	pci_dbg(pdev,
+		"Detected PCIe Vendor-Specific Extended Capability RAS DES\n");
+	return true;
+}
+
+static void dwc_pcie_unregister_dev(struct dwc_pcie_dev_info *dev_info)
+{
+	platform_device_unregister(dev_info->plat_dev);
+	list_del(&dev_info->dev_node);
+	kfree(dev_info);
+}
+
+static int dwc_pcie_register_dev(struct pci_dev *pdev)
+{
+	struct platform_device *plat_dev;
+	struct dwc_pcie_dev_info *dev_info;
+	u32 bdf;
+
+	bdf = PCI_DEVID(pdev->bus->number, pdev->devfn);
+	plat_dev = platform_device_register_data(NULL, "dwc_pcie_pmu", bdf,
+						 pdev, sizeof(*pdev));
+
+	if (IS_ERR(plat_dev))
+		return PTR_ERR(plat_dev);
+
+	dev_info = kzalloc(sizeof(*dev_info), GFP_KERNEL);
+	if (!dev_info)
+		return -ENOMEM;
+
+	/* Cache platform device to handle pci device hotplug */
+	dev_info->plat_dev = plat_dev;
+	dev_info->pdev = pdev;
+	list_add(&dev_info->dev_node, &dwc_pcie_dev_info_head);
+
+	return 0;
+}
+
+static int dwc_pcie_pmu_notifier(struct notifier_block *nb,
+				     unsigned long action, void *data)
+{
+	struct device *dev = data;
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct dwc_pcie_dev_info *dev_info;
+
+	switch (action) {
+	case BUS_NOTIFY_ADD_DEVICE:
+		if (!dwc_pcie_match_des_cap(pdev))
+			return NOTIFY_DONE;
+		if (dwc_pcie_register_dev(pdev))
+			return NOTIFY_BAD;
+		break;
+	case BUS_NOTIFY_DEL_DEVICE:
+		dev_info = dwc_pcie_find_dev_info(pdev);
+		if (!dev_info)
+			return NOTIFY_DONE;
+		dwc_pcie_unregister_dev(dev_info);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block dwc_pcie_pmu_nb = {
+	.notifier_call = dwc_pcie_pmu_notifier,
+};
+
+static int dwc_pcie_pmu_probe(struct platform_device *plat_dev)
+{
+	struct pci_dev *pdev = plat_dev->dev.platform_data;
+	struct dwc_pcie_pmu *pcie_pmu;
+	char *name;
+	u32 bdf, val;
+	u16 vsec;
+	int ret;
+
+	vsec = pci_find_vsec_capability(pdev, pdev->vendor,
+					DWC_PCIE_VSEC_RAS_DES_ID);
+	pci_read_config_dword(pdev, vsec + PCI_VNDR_HEADER, &val);
+	bdf = PCI_DEVID(pdev->bus->number, pdev->devfn);
+	name = devm_kasprintf(&plat_dev->dev, GFP_KERNEL, "dwc_rootport_%x", bdf);
+	if (!name)
+		return -ENOMEM;
+
+	pcie_pmu = devm_kzalloc(&plat_dev->dev, sizeof(*pcie_pmu), GFP_KERNEL);
+	if (!pcie_pmu)
+		return -ENOMEM;
+
+	pcie_pmu->pdev = pdev;
+	pcie_pmu->ras_des_offset = vsec;
+	pcie_pmu->nr_lanes = pcie_get_width_cap(pdev);
+	pcie_pmu->on_cpu = -1;
+	pcie_pmu->pmu = (struct pmu){
+		.name		= name,
+		.parent		= &pdev->dev,
+		.module		= THIS_MODULE,
+		.attr_groups	= dwc_pcie_attr_groups,
+		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
+		.task_ctx_nr	= perf_invalid_context,
+		.event_init	= dwc_pcie_pmu_event_init,
+		.add		= dwc_pcie_pmu_event_add,
+		.del		= dwc_pcie_pmu_event_del,
+		.start		= dwc_pcie_pmu_event_start,
+		.stop		= dwc_pcie_pmu_event_stop,
+		.read		= dwc_pcie_pmu_event_update,
+	};
+
+	/* Add this instance to the list used by the offline callback */
+	ret = cpuhp_state_add_instance(dwc_pcie_pmu_hp_state,
+				       &pcie_pmu->cpuhp_node);
+	if (ret) {
+		pci_err(pdev, "Error %d registering hotplug @%x\n", ret, bdf);
+		return ret;
+	}
+
+	/* Unwind when platform driver removes */
+	ret = devm_add_action_or_reset(&plat_dev->dev,
+				       dwc_pcie_pmu_remove_cpuhp_instance,
+				       &pcie_pmu->cpuhp_node);
+	if (ret)
+		return ret;
+
+	ret = perf_pmu_register(&pcie_pmu->pmu, name, -1);
+	if (ret) {
+		pci_err(pdev, "Error %d registering PMU @%x\n", ret, bdf);
+		return ret;
+	}
+	ret = devm_add_action_or_reset(&plat_dev->dev, dwc_pcie_unregister_pmu,
+				       pcie_pmu);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int dwc_pcie_pmu_online_cpu(unsigned int cpu, struct hlist_node *cpuhp_node)
+{
+	struct dwc_pcie_pmu *pcie_pmu;
+
+	pcie_pmu = hlist_entry_safe(cpuhp_node, struct dwc_pcie_pmu, cpuhp_node);
+	if (pcie_pmu->on_cpu == -1)
+		pcie_pmu->on_cpu = cpumask_local_spread(
+			0, dev_to_node(&pcie_pmu->pdev->dev));
+
+	return 0;
+}
+
+static int dwc_pcie_pmu_offline_cpu(unsigned int cpu, struct hlist_node *cpuhp_node)
+{
+	struct dwc_pcie_pmu *pcie_pmu;
+	struct pci_dev *pdev;
+	int node;
+	cpumask_t mask;
+	unsigned int target;
+
+	pcie_pmu = hlist_entry_safe(cpuhp_node, struct dwc_pcie_pmu, cpuhp_node);
+	/* Nothing to do if this CPU doesn't own the PMU */
+	if (cpu != pcie_pmu->on_cpu)
+		return 0;
+
+	pcie_pmu->on_cpu = -1;
+	pdev = pcie_pmu->pdev;
+	node = dev_to_node(&pdev->dev);
+	if (cpumask_and(&mask, cpumask_of_node(node), cpu_online_mask) &&
+	    cpumask_andnot(&mask, &mask, cpumask_of(cpu)))
+		target = cpumask_any(&mask);
+	else
+		target = cpumask_any_but(cpu_online_mask, cpu);
+
+	if (target >= nr_cpu_ids) {
+		pci_err(pdev, "There is no CPU to set\n");
+		return 0;
+	}
+
+	/* This PMU does NOT support interrupt, just migrate context. */
+	perf_pmu_migrate_context(&pcie_pmu->pmu, cpu, target);
+	pcie_pmu->on_cpu = target;
+
+	return 0;
+}
+
+static struct platform_driver dwc_pcie_pmu_driver = {
+	.probe = dwc_pcie_pmu_probe,
+	.driver = {.name = "dwc_pcie_pmu",},
+};
+
+static int __init dwc_pcie_pmu_init(void)
+{
+	struct pci_dev *pdev = NULL;
+	bool found = false;
+	int ret;
+
+	for_each_pci_dev(pdev) {
+		if (!dwc_pcie_match_des_cap(pdev))
+			continue;
+
+		ret = dwc_pcie_register_dev(pdev);
+		if (ret) {
+			pci_dev_put(pdev);
+			return ret;
+		}
+
+		found = true;
+	}
+	if (!found)
+		return -ENODEV;
+
+	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
+				      "perf/dwc_pcie_pmu:online",
+				      dwc_pcie_pmu_online_cpu,
+				      dwc_pcie_pmu_offline_cpu);
+	if (ret < 0)
+		return ret;
+
+	dwc_pcie_pmu_hp_state = ret;
+
+	ret = platform_driver_register(&dwc_pcie_pmu_driver);
+	if (ret)
+		goto platform_driver_register_err;
+
+	ret = bus_register_notifier(&pci_bus_type, &dwc_pcie_pmu_nb);
+	if (ret)
+		goto platform_driver_register_err;
+	notify = true;
+
+	return 0;
+
+platform_driver_register_err:
+	cpuhp_remove_multi_state(dwc_pcie_pmu_hp_state);
+
+	return ret;
+}
+
+static void __exit dwc_pcie_pmu_exit(void)
+{
+	struct dwc_pcie_dev_info *dev_info, *tmp;
+
+	if (notify)
+		bus_unregister_notifier(&pci_bus_type, &dwc_pcie_pmu_nb);
+	list_for_each_entry_safe(dev_info, tmp, &dwc_pcie_dev_info_head, dev_node)
+		dwc_pcie_unregister_dev(dev_info);
+	platform_driver_unregister(&dwc_pcie_pmu_driver);
+	cpuhp_remove_multi_state(dwc_pcie_pmu_hp_state);
+}
+
+module_init(dwc_pcie_pmu_init);
+module_exit(dwc_pcie_pmu_exit);
+
+MODULE_DESCRIPTION("PMU driver for DesignWare Cores PCI Express Controller");
+MODULE_AUTHOR("Shuai Xue <xueshuai@linux.alibaba.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c
index 92611c98120f..7dbfaee372c7 100644
--- a/drivers/perf/fsl_imx8_ddr_perf.c
+++ b/drivers/perf/fsl_imx8_ddr_perf.c
@@ -19,6 +19,8 @@
 #define COUNTER_READ		0x20
 
 #define COUNTER_DPCR1		0x30
+#define COUNTER_MUX_CNTL	0x50
+#define COUNTER_MASK_COMP	0x54
 
 #define CNTL_OVER		0x1
 #define CNTL_CLEAR		0x2
@@ -32,6 +34,13 @@
 #define CNTL_CSV_SHIFT		24
 #define CNTL_CSV_MASK		(0xFFU << CNTL_CSV_SHIFT)
 
+#define READ_PORT_SHIFT		0
+#define READ_PORT_MASK		(0x7 << READ_PORT_SHIFT)
+#define READ_CHANNEL_REVERT	0x00000008	/* bit 3 for read channel select */
+#define WRITE_PORT_SHIFT	8
+#define WRITE_PORT_MASK		(0x7 << WRITE_PORT_SHIFT)
+#define WRITE_CHANNEL_REVERT	0x00000800	/* bit 11 for write channel select */
+
 #define EVENT_CYCLES_ID		0
 #define EVENT_CYCLES_COUNTER	0
 #define NUM_COUNTERS		4
@@ -50,6 +59,7 @@ static DEFINE_IDA(ddr_ida);
 /* DDR Perf hardware feature */
 #define DDR_CAP_AXI_ID_FILTER			0x1     /* support AXI ID filter */
 #define DDR_CAP_AXI_ID_FILTER_ENHANCED		0x3     /* support enhanced AXI ID filter */
+#define DDR_CAP_AXI_ID_PORT_CHANNEL_FILTER	0x4	/* support AXI ID PORT CHANNEL filter */
 
 struct fsl_ddr_devtype_data {
 	unsigned int quirks;    /* quirks needed for different DDR Perf core */
@@ -82,6 +92,11 @@ static const struct fsl_ddr_devtype_data imx8mp_devtype_data = {
 	.identifier = "i.MX8MP",
 };
 
+static const struct fsl_ddr_devtype_data imx8dxl_devtype_data = {
+	.quirks = DDR_CAP_AXI_ID_PORT_CHANNEL_FILTER,
+	.identifier = "i.MX8DXL",
+};
+
 static const struct of_device_id imx_ddr_pmu_dt_ids[] = {
 	{ .compatible = "fsl,imx8-ddr-pmu", .data = &imx8_devtype_data},
 	{ .compatible = "fsl,imx8m-ddr-pmu", .data = &imx8m_devtype_data},
@@ -89,6 +104,7 @@ static const struct of_device_id imx_ddr_pmu_dt_ids[] = {
 	{ .compatible = "fsl,imx8mm-ddr-pmu", .data = &imx8mm_devtype_data},
 	{ .compatible = "fsl,imx8mn-ddr-pmu", .data = &imx8mn_devtype_data},
 	{ .compatible = "fsl,imx8mp-ddr-pmu", .data = &imx8mp_devtype_data},
+	{ .compatible = "fsl,imx8dxl-ddr-pmu", .data = &imx8dxl_devtype_data},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, imx_ddr_pmu_dt_ids);
@@ -144,6 +160,7 @@ static const struct attribute_group ddr_perf_identifier_attr_group = {
 enum ddr_perf_filter_capabilities {
 	PERF_CAP_AXI_ID_FILTER = 0,
 	PERF_CAP_AXI_ID_FILTER_ENHANCED,
+	PERF_CAP_AXI_ID_PORT_CHANNEL_FILTER,
 	PERF_CAP_AXI_ID_FEAT_MAX,
 };
 
@@ -157,6 +174,8 @@ static u32 ddr_perf_filter_cap_get(struct ddr_pmu *pmu, int cap)
 	case PERF_CAP_AXI_ID_FILTER_ENHANCED:
 		quirks &= DDR_CAP_AXI_ID_FILTER_ENHANCED;
 		return quirks == DDR_CAP_AXI_ID_FILTER_ENHANCED;
+	case PERF_CAP_AXI_ID_PORT_CHANNEL_FILTER:
+		return !!(quirks & DDR_CAP_AXI_ID_PORT_CHANNEL_FILTER);
 	default:
 		WARN(1, "unknown filter cap %d\n", cap);
 	}
@@ -187,6 +206,7 @@ static ssize_t ddr_perf_filter_cap_show(struct device *dev,
 static struct attribute *ddr_perf_filter_cap_attr[] = {
 	PERF_FILTER_EXT_ATTR_ENTRY(filter, PERF_CAP_AXI_ID_FILTER),
 	PERF_FILTER_EXT_ATTR_ENTRY(enhanced_filter, PERF_CAP_AXI_ID_FILTER_ENHANCED),
+	PERF_FILTER_EXT_ATTR_ENTRY(super_filter, PERF_CAP_AXI_ID_PORT_CHANNEL_FILTER),
 	NULL,
 };
 
@@ -272,11 +292,15 @@ static const struct attribute_group ddr_perf_events_attr_group = {
 PMU_FORMAT_ATTR(event, "config:0-7");
 PMU_FORMAT_ATTR(axi_id, "config1:0-15");
 PMU_FORMAT_ATTR(axi_mask, "config1:16-31");
+PMU_FORMAT_ATTR(axi_port, "config2:0-2");
+PMU_FORMAT_ATTR(axi_channel, "config2:3-3");
 
 static struct attribute *ddr_perf_format_attrs[] = {
 	&format_attr_event.attr,
 	&format_attr_axi_id.attr,
 	&format_attr_axi_mask.attr,
+	&format_attr_axi_port.attr,
+	&format_attr_axi_channel.attr,
 	NULL,
 };
 
@@ -530,6 +554,7 @@ static int ddr_perf_event_add(struct perf_event *event, int flags)
 	int counter;
 	int cfg = event->attr.config;
 	int cfg1 = event->attr.config1;
+	int cfg2 = event->attr.config2;
 
 	if (pmu->devtype_data->quirks & DDR_CAP_AXI_ID_FILTER) {
 		int i;
@@ -553,6 +578,26 @@ static int ddr_perf_event_add(struct perf_event *event, int flags)
 		return -EOPNOTSUPP;
 	}
 
+	if (pmu->devtype_data->quirks & DDR_CAP_AXI_ID_PORT_CHANNEL_FILTER) {
+		if (ddr_perf_is_filtered(event)) {
+			/* revert axi id masking(axi_mask) value */
+			cfg1 ^= AXI_MASKING_REVERT;
+			writel(cfg1, pmu->base + COUNTER_MASK_COMP + ((counter - 1) << 4));
+
+			if (cfg == 0x41) {
+				/* revert axi read channel(axi_channel) value */
+				cfg2 ^= READ_CHANNEL_REVERT;
+				cfg2 |= FIELD_PREP(READ_PORT_MASK, cfg2);
+			} else {
+				/* revert axi write channel(axi_channel) value */
+				cfg2 ^= WRITE_CHANNEL_REVERT;
+				cfg2 |= FIELD_PREP(WRITE_PORT_MASK, cfg2);
+			}
+
+			writel(cfg2, pmu->base + COUNTER_MUX_CNTL + ((counter - 1) << 4));
+		}
+	}
+
 	pmu->events[counter] = event;
 	hwc->idx = counter;
 
diff --git a/drivers/perf/fsl_imx9_ddr_perf.c b/drivers/perf/fsl_imx9_ddr_perf.c
index 5cf770a1bc31..9685645bfe04 100644
--- a/drivers/perf/fsl_imx9_ddr_perf.c
+++ b/drivers/perf/fsl_imx9_ddr_perf.c
@@ -617,7 +617,7 @@ static int ddr_perf_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, pmu);
 
-	pmu->id = ida_simple_get(&ddr_ida, 0, 0, GFP_KERNEL);
+	pmu->id = ida_alloc(&ddr_ida, GFP_KERNEL);
 	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, DDR_PERF_DEV_NAME "%d", pmu->id);
 	if (!name) {
 		ret = -ENOMEM;
@@ -674,7 +674,7 @@ cpuhp_instance_err:
 	cpuhp_remove_multi_state(pmu->cpuhp_state);
 cpuhp_state_err:
 format_string_err:
-	ida_simple_remove(&ddr_ida, pmu->id);
+	ida_free(&ddr_ida, pmu->id);
 	dev_warn(&pdev->dev, "i.MX9 DDR Perf PMU failed (%d), disabled\n", ret);
 	return ret;
 }
@@ -688,7 +688,7 @@ static int ddr_perf_remove(struct platform_device *pdev)
 
 	perf_pmu_unregister(&pmu->pmu);
 
-	ida_simple_remove(&ddr_ida, pmu->id);
+	ida_free(&ddr_ida, pmu->id);
 
 	return 0;
 }
diff --git a/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c
index 63da05e5831c..636fb79647c8 100644
--- a/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c
@@ -383,8 +383,8 @@ static struct attribute *hisi_uc_pmu_events_attr[] = {
 	HISI_PMU_EVENT_ATTR(cpu_rd,		0x10),
 	HISI_PMU_EVENT_ATTR(cpu_rd64,		0x17),
 	HISI_PMU_EVENT_ATTR(cpu_rs64,		0x19),
-	HISI_PMU_EVENT_ATTR(cpu_mru,		0x1a),
-	HISI_PMU_EVENT_ATTR(cycles,		0x9c),
+	HISI_PMU_EVENT_ATTR(cpu_mru,		0x1c),
+	HISI_PMU_EVENT_ATTR(cycles,		0x95),
 	HISI_PMU_EVENT_ATTR(spipe_hit,		0xb3),
 	HISI_PMU_EVENT_ATTR(hpipe_hit,		0xdb),
 	HISI_PMU_EVENT_ATTR(cring_rxdat_cnt,	0xfa),
diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index 787354b849c7..4cef568231bf 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -87,7 +87,6 @@ source "drivers/phy/motorola/Kconfig"
 source "drivers/phy/mscc/Kconfig"
 source "drivers/phy/qualcomm/Kconfig"
 source "drivers/phy/ralink/Kconfig"
-source "drivers/phy/realtek/Kconfig"
 source "drivers/phy/renesas/Kconfig"
 source "drivers/phy/rockchip/Kconfig"
 source "drivers/phy/samsung/Kconfig"
diff --git a/drivers/phy/Makefile b/drivers/phy/Makefile
index 868a220ed0f6..fb3dc9de6111 100644
--- a/drivers/phy/Makefile
+++ b/drivers/phy/Makefile
@@ -26,7 +26,6 @@ obj-y					+= allwinner/	\
 					   mscc/	\
 					   qualcomm/	\
 					   ralink/	\
-					   realtek/	\
 					   renesas/	\
 					   rockchip/	\
 					   samsung/	\
diff --git a/drivers/phy/mediatek/phy-mtk-mipi-dsi-mt8183.c b/drivers/phy/mediatek/phy-mtk-mipi-dsi-mt8183.c
index f021ec5a70e5..553725e1269c 100644
--- a/drivers/phy/mediatek/phy-mtk-mipi-dsi-mt8183.c
+++ b/drivers/phy/mediatek/phy-mtk-mipi-dsi-mt8183.c
@@ -100,7 +100,7 @@ static void mtk_mipi_tx_pll_disable(struct clk_hw *hw)
 static long mtk_mipi_tx_pll_round_rate(struct clk_hw *hw, unsigned long rate,
 				       unsigned long *prate)
 {
-	return clamp_val(rate, 50000000, 1600000000);
+	return clamp_val(rate, 125000000, 1600000000);
 }
 
 static const struct clk_ops mtk_mipi_tx_pll_ops = {
diff --git a/drivers/phy/realtek/Kconfig b/drivers/phy/realtek/Kconfig
deleted file mode 100644
index 75ac7e7c31ae..000000000000
--- a/drivers/phy/realtek/Kconfig
+++ /dev/null
@@ -1,32 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Phy drivers for Realtek platforms
-#
-
-if ARCH_REALTEK || COMPILE_TEST
-
-config PHY_RTK_RTD_USB2PHY
-	tristate "Realtek RTD USB2 PHY Transceiver Driver"
-	depends on USB_SUPPORT
-	select GENERIC_PHY
-	select USB_PHY
-	select USB_COMMON
-	help
-	  Enable this to support Realtek SoC USB2 phy transceiver.
-	  The DHC (digital home center) RTD series SoCs used the Synopsys
-	  DWC3 USB IP. This driver will do the PHY initialization
-	  of the parameters.
-
-config PHY_RTK_RTD_USB3PHY
-	tristate "Realtek RTD USB3 PHY Transceiver Driver"
-	depends on USB_SUPPORT
-	select GENERIC_PHY
-	select USB_PHY
-	select USB_COMMON
-	help
-	  Enable this to support Realtek SoC USB3 phy transceiver.
-	  The DHC (digital home center) RTD series SoCs used the Synopsys
-	  DWC3 USB IP. This driver will do the PHY initialization
-	  of the parameters.
-
-endif # ARCH_REALTEK || COMPILE_TEST
diff --git a/drivers/phy/realtek/Makefile b/drivers/phy/realtek/Makefile
deleted file mode 100644
index ed7b47ff8a26..000000000000
--- a/drivers/phy/realtek/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_PHY_RTK_RTD_USB2PHY)	+= phy-rtk-usb2.o
-obj-$(CONFIG_PHY_RTK_RTD_USB3PHY)	+= phy-rtk-usb3.o
diff --git a/drivers/phy/realtek/phy-rtk-usb2.c b/drivers/phy/realtek/phy-rtk-usb2.c
deleted file mode 100644
index 0a6426285c67..000000000000
--- a/drivers/phy/realtek/phy-rtk-usb2.c
+++ /dev/null
@@ -1,1325 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- *  phy-rtk-usb2.c RTK usb2.0 PHY driver
- *
- * Copyright (C) 2023 Realtek Semiconductor Corporation
- *
- */
-
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/platform_device.h>
-#include <linux/uaccess.h>
-#include <linux/debugfs.h>
-#include <linux/nvmem-consumer.h>
-#include <linux/regmap.h>
-#include <linux/sys_soc.h>
-#include <linux/mfd/syscon.h>
-#include <linux/phy/phy.h>
-#include <linux/usb.h>
-#include <linux/usb/phy.h>
-#include <linux/usb/hcd.h>
-
-/* GUSB2PHYACCn register */
-#define PHY_NEW_REG_REQ BIT(25)
-#define PHY_VSTS_BUSY   BIT(23)
-#define PHY_VCTRL_SHIFT 8
-#define PHY_REG_DATA_MASK 0xff
-
-#define GET_LOW_NIBBLE(addr) ((addr) & 0x0f)
-#define GET_HIGH_NIBBLE(addr) (((addr) & 0xf0) >> 4)
-
-#define EFUS_USB_DC_CAL_RATE 2
-#define EFUS_USB_DC_CAL_MAX 7
-
-#define EFUS_USB_DC_DIS_RATE 1
-#define EFUS_USB_DC_DIS_MAX 7
-
-#define MAX_PHY_DATA_SIZE 20
-#define OFFEST_PHY_READ 0x20
-
-#define MAX_USB_PHY_NUM 4
-#define MAX_USB_PHY_PAGE0_DATA_SIZE 16
-#define MAX_USB_PHY_PAGE1_DATA_SIZE 16
-#define MAX_USB_PHY_PAGE2_DATA_SIZE 8
-
-#define SET_PAGE_OFFSET 0xf4
-#define SET_PAGE_0 0x9b
-#define SET_PAGE_1 0xbb
-#define SET_PAGE_2 0xdb
-
-#define PAGE_START 0xe0
-#define PAGE0_0XE4 0xe4
-#define PAGE0_0XE6 0xe6
-#define PAGE0_0XE7 0xe7
-#define PAGE1_0XE0 0xe0
-#define PAGE1_0XE2 0xe2
-
-#define SENSITIVITY_CTRL (BIT(4) | BIT(5) | BIT(6))
-#define ENABLE_AUTO_SENSITIVITY_CALIBRATION BIT(2)
-#define DEFAULT_DC_DRIVING_VALUE (0x8)
-#define DEFAULT_DC_DISCONNECTION_VALUE (0x6)
-#define HS_CLK_SELECT BIT(6)
-
-struct phy_reg {
-	void __iomem *reg_wrap_vstatus;
-	void __iomem *reg_gusb2phyacc0;
-	int vstatus_index;
-};
-
-struct phy_data {
-	u8 addr;
-	u8 data;
-};
-
-struct phy_cfg {
-	int page0_size;
-	struct phy_data page0[MAX_USB_PHY_PAGE0_DATA_SIZE];
-	int page1_size;
-	struct phy_data page1[MAX_USB_PHY_PAGE1_DATA_SIZE];
-	int page2_size;
-	struct phy_data page2[MAX_USB_PHY_PAGE2_DATA_SIZE];
-
-	int num_phy;
-
-	bool check_efuse;
-	int check_efuse_version;
-#define CHECK_EFUSE_V1 1
-#define CHECK_EFUSE_V2 2
-	int efuse_dc_driving_rate;
-	int efuse_dc_disconnect_rate;
-	int dc_driving_mask;
-	int dc_disconnect_mask;
-	bool usb_dc_disconnect_at_page0;
-	int driving_updated_for_dev_dis;
-
-	bool do_toggle;
-	bool do_toggle_driving;
-	bool use_default_parameter;
-	bool is_double_sensitivity_mode;
-};
-
-struct phy_parameter {
-	struct phy_reg phy_reg;
-
-	/* Get from efuse */
-	s8 efuse_usb_dc_cal;
-	s8 efuse_usb_dc_dis;
-
-	/* Get from dts */
-	bool inverse_hstx_sync_clock;
-	u32 driving_level;
-	s32 driving_level_compensate;
-	s32 disconnection_compensate;
-};
-
-struct rtk_phy {
-	struct usb_phy phy;
-	struct device *dev;
-
-	struct phy_cfg *phy_cfg;
-	int num_phy;
-	struct phy_parameter *phy_parameter;
-
-	struct dentry *debug_dir;
-};
-
-/* mapping 0xE0 to 0 ... 0xE7 to 7, 0xF0 to 8 ,,, 0xF7 to 15 */
-static inline int page_addr_to_array_index(u8 addr)
-{
-	return (int)((((addr) - PAGE_START) & 0x7) +
-		((((addr) - PAGE_START) & 0x10) >> 1));
-}
-
-static inline u8 array_index_to_page_addr(int index)
-{
-	return ((((index) + PAGE_START) & 0x7) +
-		((((index) & 0x8) << 1) + PAGE_START));
-}
-
-#define PHY_IO_TIMEOUT_USEC		(50000)
-#define PHY_IO_DELAY_US			(100)
-
-static inline int utmi_wait_register(void __iomem *reg, u32 mask, u32 result)
-{
-	int ret;
-	unsigned int val;
-
-	ret = read_poll_timeout(readl, val, ((val & mask) == result),
-				PHY_IO_DELAY_US, PHY_IO_TIMEOUT_USEC, false, reg);
-	if (ret) {
-		pr_err("%s can't program USB phy\n", __func__);
-		return -ETIMEDOUT;
-	}
-
-	return 0;
-}
-
-static char rtk_phy_read(struct phy_reg *phy_reg, char addr)
-{
-	void __iomem *reg_gusb2phyacc0 = phy_reg->reg_gusb2phyacc0;
-	unsigned int val;
-	int ret = 0;
-
-	addr -= OFFEST_PHY_READ;
-
-	/* polling until VBusy == 0 */
-	ret = utmi_wait_register(reg_gusb2phyacc0, PHY_VSTS_BUSY, 0);
-	if (ret)
-		return (char)ret;
-
-	/* VCtrl = low nibble of addr, and set PHY_NEW_REG_REQ */
-	val = PHY_NEW_REG_REQ | (GET_LOW_NIBBLE(addr) << PHY_VCTRL_SHIFT);
-	writel(val, reg_gusb2phyacc0);
-	ret = utmi_wait_register(reg_gusb2phyacc0, PHY_VSTS_BUSY, 0);
-	if (ret)
-		return (char)ret;
-
-	/* VCtrl = high nibble of addr, and set PHY_NEW_REG_REQ */
-	val = PHY_NEW_REG_REQ | (GET_HIGH_NIBBLE(addr) << PHY_VCTRL_SHIFT);
-	writel(val, reg_gusb2phyacc0);
-	ret = utmi_wait_register(reg_gusb2phyacc0, PHY_VSTS_BUSY, 0);
-	if (ret)
-		return (char)ret;
-
-	val = readl(reg_gusb2phyacc0);
-
-	return (char)(val & PHY_REG_DATA_MASK);
-}
-
-static int rtk_phy_write(struct phy_reg *phy_reg, char addr, char data)
-{
-	unsigned int val;
-	void __iomem *reg_wrap_vstatus = phy_reg->reg_wrap_vstatus;
-	void __iomem *reg_gusb2phyacc0 = phy_reg->reg_gusb2phyacc0;
-	int shift_bits = phy_reg->vstatus_index * 8;
-	int ret = 0;
-
-	/* write data to VStatusOut2 (data output to phy) */
-	writel((u32)data << shift_bits, reg_wrap_vstatus);
-
-	ret = utmi_wait_register(reg_gusb2phyacc0, PHY_VSTS_BUSY, 0);
-	if (ret)
-		return ret;
-
-	/* VCtrl = low nibble of addr, set PHY_NEW_REG_REQ */
-	val = PHY_NEW_REG_REQ | (GET_LOW_NIBBLE(addr) << PHY_VCTRL_SHIFT);
-
-	writel(val, reg_gusb2phyacc0);
-	ret = utmi_wait_register(reg_gusb2phyacc0, PHY_VSTS_BUSY, 0);
-	if (ret)
-		return ret;
-
-	/* VCtrl = high nibble of addr, set PHY_NEW_REG_REQ */
-	val = PHY_NEW_REG_REQ | (GET_HIGH_NIBBLE(addr) << PHY_VCTRL_SHIFT);
-
-	writel(val, reg_gusb2phyacc0);
-	ret = utmi_wait_register(reg_gusb2phyacc0, PHY_VSTS_BUSY, 0);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-static int rtk_phy_set_page(struct phy_reg *phy_reg, int page)
-{
-	switch (page) {
-	case 0:
-		return rtk_phy_write(phy_reg, SET_PAGE_OFFSET, SET_PAGE_0);
-	case 1:
-		return rtk_phy_write(phy_reg, SET_PAGE_OFFSET, SET_PAGE_1);
-	case 2:
-		return rtk_phy_write(phy_reg, SET_PAGE_OFFSET, SET_PAGE_2);
-	default:
-		pr_err("%s error page=%d\n", __func__, page);
-	}
-
-	return -EINVAL;
-}
-
-static u8 __updated_dc_disconnect_level_page0_0xe4(struct phy_cfg *phy_cfg,
-						   struct phy_parameter *phy_parameter, u8 data)
-{
-	u8 ret;
-	s32 val;
-	s32 dc_disconnect_mask = phy_cfg->dc_disconnect_mask;
-	int offset = 4;
-
-	val = (s32)((data >> offset) & dc_disconnect_mask)
-		     + phy_parameter->efuse_usb_dc_dis
-		     + phy_parameter->disconnection_compensate;
-
-	if (val > dc_disconnect_mask)
-		val = dc_disconnect_mask;
-	else if (val < 0)
-		val = 0;
-
-	ret = (data & (~(dc_disconnect_mask << offset))) |
-		    (val & dc_disconnect_mask) << offset;
-
-	return ret;
-}
-
-/* updated disconnect level at page0 */
-static void update_dc_disconnect_level_at_page0(struct rtk_phy *rtk_phy,
-						struct phy_parameter *phy_parameter, bool update)
-{
-	struct phy_cfg *phy_cfg;
-	struct phy_reg *phy_reg;
-	struct phy_data *phy_data_page;
-	struct phy_data *phy_data;
-	u8 addr, data;
-	int offset = 4;
-	s32 dc_disconnect_mask;
-	int i;
-
-	phy_cfg = rtk_phy->phy_cfg;
-	phy_reg = &phy_parameter->phy_reg;
-
-	/* Set page 0 */
-	phy_data_page = phy_cfg->page0;
-	rtk_phy_set_page(phy_reg, 0);
-
-	i = page_addr_to_array_index(PAGE0_0XE4);
-	phy_data = phy_data_page + i;
-	if (!phy_data->addr) {
-		phy_data->addr = PAGE0_0XE4;
-		phy_data->data = rtk_phy_read(phy_reg, PAGE0_0XE4);
-	}
-
-	addr = phy_data->addr;
-	data = phy_data->data;
-	dc_disconnect_mask = phy_cfg->dc_disconnect_mask;
-
-	if (update)
-		data = __updated_dc_disconnect_level_page0_0xe4(phy_cfg, phy_parameter, data);
-	else
-		data = (data & ~(dc_disconnect_mask << offset)) |
-			(DEFAULT_DC_DISCONNECTION_VALUE << offset);
-
-	if (rtk_phy_write(phy_reg, addr, data))
-		dev_err(rtk_phy->dev,
-			"%s: Error to set page1 parameter addr=0x%x value=0x%x\n",
-			__func__, addr, data);
-}
-
-static u8 __updated_dc_disconnect_level_page1_0xe2(struct phy_cfg *phy_cfg,
-						   struct phy_parameter *phy_parameter, u8 data)
-{
-	u8 ret;
-	s32 val;
-	s32 dc_disconnect_mask = phy_cfg->dc_disconnect_mask;
-
-	if (phy_cfg->check_efuse_version == CHECK_EFUSE_V1) {
-		val = (s32)(data & dc_disconnect_mask)
-			    + phy_parameter->efuse_usb_dc_dis
-			    + phy_parameter->disconnection_compensate;
-	} else { /* for CHECK_EFUSE_V2 or no efuse */
-		if (phy_parameter->efuse_usb_dc_dis)
-			val = (s32)(phy_parameter->efuse_usb_dc_dis +
-				    phy_parameter->disconnection_compensate);
-		else
-			val = (s32)((data & dc_disconnect_mask) +
-				    phy_parameter->disconnection_compensate);
-	}
-
-	if (val > dc_disconnect_mask)
-		val = dc_disconnect_mask;
-	else if (val < 0)
-		val = 0;
-
-	ret = (data & (~dc_disconnect_mask)) | (val & dc_disconnect_mask);
-
-	return ret;
-}
-
-/* updated disconnect level at page1 */
-static void update_dc_disconnect_level_at_page1(struct rtk_phy *rtk_phy,
-						struct phy_parameter *phy_parameter, bool update)
-{
-	struct phy_cfg *phy_cfg;
-	struct phy_data *phy_data_page;
-	struct phy_data *phy_data;
-	struct phy_reg *phy_reg;
-	u8 addr, data;
-	s32 dc_disconnect_mask;
-	int i;
-
-	phy_cfg = rtk_phy->phy_cfg;
-	phy_reg = &phy_parameter->phy_reg;
-
-	/* Set page 1 */
-	phy_data_page = phy_cfg->page1;
-	rtk_phy_set_page(phy_reg, 1);
-
-	i = page_addr_to_array_index(PAGE1_0XE2);
-	phy_data = phy_data_page + i;
-	if (!phy_data->addr) {
-		phy_data->addr = PAGE1_0XE2;
-		phy_data->data = rtk_phy_read(phy_reg, PAGE1_0XE2);
-	}
-
-	addr = phy_data->addr;
-	data = phy_data->data;
-	dc_disconnect_mask = phy_cfg->dc_disconnect_mask;
-
-	if (update)
-		data = __updated_dc_disconnect_level_page1_0xe2(phy_cfg, phy_parameter, data);
-	else
-		data = (data & ~dc_disconnect_mask) | DEFAULT_DC_DISCONNECTION_VALUE;
-
-	if (rtk_phy_write(phy_reg, addr, data))
-		dev_err(rtk_phy->dev,
-			"%s: Error to set page1 parameter addr=0x%x value=0x%x\n",
-			__func__, addr, data);
-}
-
-static void update_dc_disconnect_level(struct rtk_phy *rtk_phy,
-				       struct phy_parameter *phy_parameter, bool update)
-{
-	struct phy_cfg *phy_cfg = rtk_phy->phy_cfg;
-
-	if (phy_cfg->usb_dc_disconnect_at_page0)
-		update_dc_disconnect_level_at_page0(rtk_phy, phy_parameter, update);
-	else
-		update_dc_disconnect_level_at_page1(rtk_phy, phy_parameter, update);
-}
-
-static u8 __update_dc_driving_page0_0xe4(struct phy_cfg *phy_cfg,
-					 struct phy_parameter *phy_parameter, u8 data)
-{
-	s32 driving_level_compensate = phy_parameter->driving_level_compensate;
-	s32 dc_driving_mask = phy_cfg->dc_driving_mask;
-	s32 val;
-	u8 ret;
-
-	if (phy_cfg->check_efuse_version == CHECK_EFUSE_V1) {
-		val = (s32)(data & dc_driving_mask) + driving_level_compensate
-			    + phy_parameter->efuse_usb_dc_cal;
-	} else { /* for CHECK_EFUSE_V2 or no efuse */
-		if (phy_parameter->efuse_usb_dc_cal)
-			val = (s32)((phy_parameter->efuse_usb_dc_cal & dc_driving_mask)
-				    + driving_level_compensate);
-		else
-			val = (s32)(data & dc_driving_mask);
-	}
-
-	if (val > dc_driving_mask)
-		val = dc_driving_mask;
-	else if (val < 0)
-		val = 0;
-
-	ret = (data & (~dc_driving_mask)) | (val & dc_driving_mask);
-
-	return ret;
-}
-
-static void update_dc_driving_level(struct rtk_phy *rtk_phy,
-				    struct phy_parameter *phy_parameter)
-{
-	struct phy_cfg *phy_cfg;
-	struct phy_reg *phy_reg;
-
-	phy_reg = &phy_parameter->phy_reg;
-	phy_cfg = rtk_phy->phy_cfg;
-	if (!phy_cfg->page0[4].addr) {
-		rtk_phy_set_page(phy_reg, 0);
-		phy_cfg->page0[4].addr = PAGE0_0XE4;
-		phy_cfg->page0[4].data = rtk_phy_read(phy_reg, PAGE0_0XE4);
-	}
-
-	if (phy_parameter->driving_level != DEFAULT_DC_DRIVING_VALUE) {
-		u32 dc_driving_mask;
-		u8 driving_level;
-		u8 data;
-
-		data = phy_cfg->page0[4].data;
-		dc_driving_mask = phy_cfg->dc_driving_mask;
-		driving_level = data & dc_driving_mask;
-
-		dev_dbg(rtk_phy->dev, "%s driving_level=%d => dts driving_level=%d\n",
-			__func__, driving_level, phy_parameter->driving_level);
-
-		phy_cfg->page0[4].data = (data & (~dc_driving_mask)) |
-			    (phy_parameter->driving_level & dc_driving_mask);
-	}
-
-	phy_cfg->page0[4].data = __update_dc_driving_page0_0xe4(phy_cfg,
-								phy_parameter,
-								phy_cfg->page0[4].data);
-}
-
-static void update_hs_clk_select(struct rtk_phy *rtk_phy,
-				 struct phy_parameter *phy_parameter)
-{
-	struct phy_cfg *phy_cfg;
-	struct phy_reg *phy_reg;
-
-	phy_cfg = rtk_phy->phy_cfg;
-	phy_reg = &phy_parameter->phy_reg;
-
-	if (phy_parameter->inverse_hstx_sync_clock) {
-		if (!phy_cfg->page0[6].addr) {
-			rtk_phy_set_page(phy_reg, 0);
-			phy_cfg->page0[6].addr = PAGE0_0XE6;
-			phy_cfg->page0[6].data = rtk_phy_read(phy_reg, PAGE0_0XE6);
-		}
-
-		phy_cfg->page0[6].data = phy_cfg->page0[6].data | HS_CLK_SELECT;
-	}
-}
-
-static void do_rtk_phy_toggle(struct rtk_phy *rtk_phy,
-			      int index, bool connect)
-{
-	struct phy_parameter *phy_parameter;
-	struct phy_cfg *phy_cfg;
-	struct phy_reg *phy_reg;
-	struct phy_data *phy_data_page;
-	u8 addr, data;
-	int i;
-
-	phy_cfg = rtk_phy->phy_cfg;
-	phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index];
-	phy_reg = &phy_parameter->phy_reg;
-
-	if (!phy_cfg->do_toggle)
-		goto out;
-
-	if (phy_cfg->is_double_sensitivity_mode)
-		goto do_toggle_driving;
-
-	/* Set page 0 */
-	rtk_phy_set_page(phy_reg, 0);
-
-	addr = PAGE0_0XE7;
-	data = rtk_phy_read(phy_reg, addr);
-
-	if (connect)
-		rtk_phy_write(phy_reg, addr, data & (~SENSITIVITY_CTRL));
-	else
-		rtk_phy_write(phy_reg, addr, data | (SENSITIVITY_CTRL));
-
-do_toggle_driving:
-
-	if (!phy_cfg->do_toggle_driving)
-		goto do_toggle;
-
-	/* Page 0 addr 0xE4 driving capability */
-
-	/* Set page 0 */
-	phy_data_page = phy_cfg->page0;
-	rtk_phy_set_page(phy_reg, 0);
-
-	i = page_addr_to_array_index(PAGE0_0XE4);
-	addr = phy_data_page[i].addr;
-	data = phy_data_page[i].data;
-
-	if (connect) {
-		rtk_phy_write(phy_reg, addr, data);
-	} else {
-		u8 value;
-		s32 tmp;
-		s32 driving_updated =
-			    phy_cfg->driving_updated_for_dev_dis;
-		s32 dc_driving_mask = phy_cfg->dc_driving_mask;
-
-		tmp = (s32)(data & dc_driving_mask) + driving_updated;
-
-		if (tmp > dc_driving_mask)
-			tmp = dc_driving_mask;
-		else if (tmp < 0)
-			tmp = 0;
-
-		value = (data & (~dc_driving_mask)) | (tmp & dc_driving_mask);
-
-		rtk_phy_write(phy_reg, addr, value);
-	}
-
-do_toggle:
-	/* restore dc disconnect level before toggle */
-	update_dc_disconnect_level(rtk_phy, phy_parameter, false);
-
-	/* Set page 1 */
-	rtk_phy_set_page(phy_reg, 1);
-
-	addr = PAGE1_0XE0;
-	data = rtk_phy_read(phy_reg, addr);
-
-	rtk_phy_write(phy_reg, addr, data &
-		      (~ENABLE_AUTO_SENSITIVITY_CALIBRATION));
-	mdelay(1);
-	rtk_phy_write(phy_reg, addr, data |
-		      (ENABLE_AUTO_SENSITIVITY_CALIBRATION));
-
-	/* update dc disconnect level after toggle */
-	update_dc_disconnect_level(rtk_phy, phy_parameter, true);
-
-out:
-	return;
-}
-
-static int do_rtk_phy_init(struct rtk_phy *rtk_phy, int index)
-{
-	struct phy_parameter *phy_parameter;
-	struct phy_cfg *phy_cfg;
-	struct phy_data *phy_data_page;
-	struct phy_reg *phy_reg;
-	int i;
-
-	phy_cfg = rtk_phy->phy_cfg;
-	phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index];
-	phy_reg = &phy_parameter->phy_reg;
-
-	if (phy_cfg->use_default_parameter) {
-		dev_dbg(rtk_phy->dev, "%s phy#%d use default parameter\n",
-			__func__, index);
-		goto do_toggle;
-	}
-
-	/* Set page 0 */
-	phy_data_page = phy_cfg->page0;
-	rtk_phy_set_page(phy_reg, 0);
-
-	for (i = 0; i < phy_cfg->page0_size; i++) {
-		struct phy_data *phy_data = phy_data_page + i;
-		u8 addr = phy_data->addr;
-		u8 data = phy_data->data;
-
-		if (!addr)
-			continue;
-
-		if (rtk_phy_write(phy_reg, addr, data)) {
-			dev_err(rtk_phy->dev,
-				"%s: Error to set page0 parameter addr=0x%x value=0x%x\n",
-				__func__, addr, data);
-			return -EINVAL;
-		}
-	}
-
-	/* Set page 1 */
-	phy_data_page = phy_cfg->page1;
-	rtk_phy_set_page(phy_reg, 1);
-
-	for (i = 0; i < phy_cfg->page1_size; i++) {
-		struct phy_data *phy_data = phy_data_page + i;
-		u8 addr = phy_data->addr;
-		u8 data = phy_data->data;
-
-		if (!addr)
-			continue;
-
-		if (rtk_phy_write(phy_reg, addr, data)) {
-			dev_err(rtk_phy->dev,
-				"%s: Error to set page1 parameter addr=0x%x value=0x%x\n",
-				__func__, addr, data);
-			return -EINVAL;
-		}
-	}
-
-	if (phy_cfg->page2_size == 0)
-		goto do_toggle;
-
-	/* Set page 2 */
-	phy_data_page = phy_cfg->page2;
-	rtk_phy_set_page(phy_reg, 2);
-
-	for (i = 0; i < phy_cfg->page2_size; i++) {
-		struct phy_data *phy_data = phy_data_page + i;
-		u8 addr = phy_data->addr;
-		u8 data = phy_data->data;
-
-		if (!addr)
-			continue;
-
-		if (rtk_phy_write(phy_reg, addr, data)) {
-			dev_err(rtk_phy->dev,
-				"%s: Error to set page2 parameter addr=0x%x value=0x%x\n",
-				__func__, addr, data);
-			return -EINVAL;
-		}
-	}
-
-do_toggle:
-	do_rtk_phy_toggle(rtk_phy, index, false);
-
-	return 0;
-}
-
-static int rtk_phy_init(struct phy *phy)
-{
-	struct rtk_phy *rtk_phy = phy_get_drvdata(phy);
-	unsigned long phy_init_time = jiffies;
-	int i, ret = 0;
-
-	if (!rtk_phy)
-		return -EINVAL;
-
-	for (i = 0; i < rtk_phy->num_phy; i++)
-		ret = do_rtk_phy_init(rtk_phy, i);
-
-	dev_dbg(rtk_phy->dev, "Initialized RTK USB 2.0 PHY (take %dms)\n",
-		jiffies_to_msecs(jiffies - phy_init_time));
-	return ret;
-}
-
-static int rtk_phy_exit(struct phy *phy)
-{
-	return 0;
-}
-
-static const struct phy_ops ops = {
-	.init		= rtk_phy_init,
-	.exit		= rtk_phy_exit,
-	.owner		= THIS_MODULE,
-};
-
-static void rtk_phy_toggle(struct usb_phy *usb2_phy, bool connect, int port)
-{
-	int index = port;
-	struct rtk_phy *rtk_phy = NULL;
-
-	rtk_phy = dev_get_drvdata(usb2_phy->dev);
-
-	if (index > rtk_phy->num_phy) {
-		dev_err(rtk_phy->dev, "%s: The port=%d is not in usb phy (num_phy=%d)\n",
-			__func__, index, rtk_phy->num_phy);
-		return;
-	}
-
-	do_rtk_phy_toggle(rtk_phy, index, connect);
-}
-
-static int rtk_phy_notify_port_status(struct usb_phy *x, int port,
-				      u16 portstatus, u16 portchange)
-{
-	bool connect = false;
-
-	pr_debug("%s port=%d portstatus=0x%x portchange=0x%x\n",
-		 __func__, port, (int)portstatus, (int)portchange);
-	if (portstatus & USB_PORT_STAT_CONNECTION)
-		connect = true;
-
-	if (portchange & USB_PORT_STAT_C_CONNECTION)
-		rtk_phy_toggle(x, connect, port);
-
-	return 0;
-}
-
-#ifdef CONFIG_DEBUG_FS
-static struct dentry *create_phy_debug_root(void)
-{
-	struct dentry *phy_debug_root;
-
-	phy_debug_root = debugfs_lookup("phy", usb_debug_root);
-	if (!phy_debug_root)
-		phy_debug_root = debugfs_create_dir("phy", usb_debug_root);
-
-	return phy_debug_root;
-}
-
-static int rtk_usb2_parameter_show(struct seq_file *s, void *unused)
-{
-	struct rtk_phy *rtk_phy = s->private;
-	struct phy_cfg *phy_cfg;
-	int i, index;
-
-	phy_cfg = rtk_phy->phy_cfg;
-
-	seq_puts(s, "Property:\n");
-	seq_printf(s, "  check_efuse: %s\n",
-		   phy_cfg->check_efuse ? "Enable" : "Disable");
-	seq_printf(s, "  check_efuse_version: %d\n",
-		   phy_cfg->check_efuse_version);
-	seq_printf(s, "  efuse_dc_driving_rate: %d\n",
-		   phy_cfg->efuse_dc_driving_rate);
-	seq_printf(s, "  dc_driving_mask: 0x%x\n",
-		   phy_cfg->dc_driving_mask);
-	seq_printf(s, "  efuse_dc_disconnect_rate: %d\n",
-		   phy_cfg->efuse_dc_disconnect_rate);
-	seq_printf(s, "  dc_disconnect_mask: 0x%x\n",
-		   phy_cfg->dc_disconnect_mask);
-	seq_printf(s, "  usb_dc_disconnect_at_page0: %s\n",
-		   phy_cfg->usb_dc_disconnect_at_page0 ? "true" : "false");
-	seq_printf(s, "  do_toggle: %s\n",
-		   phy_cfg->do_toggle ? "Enable" : "Disable");
-	seq_printf(s, "  do_toggle_driving: %s\n",
-		   phy_cfg->do_toggle_driving ? "Enable" : "Disable");
-	seq_printf(s, "  driving_updated_for_dev_dis: 0x%x\n",
-		   phy_cfg->driving_updated_for_dev_dis);
-	seq_printf(s, "  use_default_parameter: %s\n",
-		   phy_cfg->use_default_parameter ? "Enable" : "Disable");
-	seq_printf(s, "  is_double_sensitivity_mode: %s\n",
-		   phy_cfg->is_double_sensitivity_mode ? "Enable" : "Disable");
-
-	for (index = 0; index < rtk_phy->num_phy; index++) {
-		struct phy_parameter *phy_parameter;
-		struct phy_reg *phy_reg;
-		struct phy_data *phy_data_page;
-
-		phy_parameter =  &((struct phy_parameter *)rtk_phy->phy_parameter)[index];
-		phy_reg = &phy_parameter->phy_reg;
-
-		seq_printf(s, "PHY %d:\n", index);
-
-		seq_puts(s, "Page 0:\n");
-		/* Set page 0 */
-		phy_data_page = phy_cfg->page0;
-		rtk_phy_set_page(phy_reg, 0);
-
-		for (i = 0; i < phy_cfg->page0_size; i++) {
-			struct phy_data *phy_data = phy_data_page + i;
-			u8 addr = array_index_to_page_addr(i);
-			u8 data = phy_data->data;
-			u8 value = rtk_phy_read(phy_reg, addr);
-
-			if (phy_data->addr)
-				seq_printf(s, "  Page 0: addr=0x%x data=0x%02x ==> read value=0x%02x\n",
-					   addr, data, value);
-			else
-				seq_printf(s, "  Page 0: addr=0x%x data=none ==> read value=0x%02x\n",
-					   addr, value);
-		}
-
-		seq_puts(s, "Page 1:\n");
-		/* Set page 1 */
-		phy_data_page = phy_cfg->page1;
-		rtk_phy_set_page(phy_reg, 1);
-
-		for (i = 0; i < phy_cfg->page1_size; i++) {
-			struct phy_data *phy_data = phy_data_page + i;
-			u8 addr = array_index_to_page_addr(i);
-			u8 data = phy_data->data;
-			u8 value = rtk_phy_read(phy_reg, addr);
-
-			if (phy_data->addr)
-				seq_printf(s, "  Page 1: addr=0x%x data=0x%02x ==> read value=0x%02x\n",
-					   addr, data, value);
-			else
-				seq_printf(s, "  Page 1: addr=0x%x data=none ==> read value=0x%02x\n",
-					   addr, value);
-		}
-
-		if (phy_cfg->page2_size == 0)
-			goto out;
-
-		seq_puts(s, "Page 2:\n");
-		/* Set page 2 */
-		phy_data_page = phy_cfg->page2;
-		rtk_phy_set_page(phy_reg, 2);
-
-		for (i = 0; i < phy_cfg->page2_size; i++) {
-			struct phy_data *phy_data = phy_data_page + i;
-			u8 addr = array_index_to_page_addr(i);
-			u8 data = phy_data->data;
-			u8 value = rtk_phy_read(phy_reg, addr);
-
-			if (phy_data->addr)
-				seq_printf(s, "  Page 2: addr=0x%x data=0x%02x ==> read value=0x%02x\n",
-					   addr, data, value);
-			else
-				seq_printf(s, "  Page 2: addr=0x%x data=none ==> read value=0x%02x\n",
-					   addr, value);
-		}
-
-out:
-		seq_puts(s, "PHY Property:\n");
-		seq_printf(s, "  efuse_usb_dc_cal: %d\n",
-			   (int)phy_parameter->efuse_usb_dc_cal);
-		seq_printf(s, "  efuse_usb_dc_dis: %d\n",
-			   (int)phy_parameter->efuse_usb_dc_dis);
-		seq_printf(s, "  inverse_hstx_sync_clock: %s\n",
-			   phy_parameter->inverse_hstx_sync_clock ? "Enable" : "Disable");
-		seq_printf(s, "  driving_level: %d\n",
-			   phy_parameter->driving_level);
-		seq_printf(s, "  driving_level_compensate: %d\n",
-			   phy_parameter->driving_level_compensate);
-		seq_printf(s, "  disconnection_compensate: %d\n",
-			   phy_parameter->disconnection_compensate);
-	}
-
-	return 0;
-}
-DEFINE_SHOW_ATTRIBUTE(rtk_usb2_parameter);
-
-static inline void create_debug_files(struct rtk_phy *rtk_phy)
-{
-	struct dentry *phy_debug_root = NULL;
-
-	phy_debug_root = create_phy_debug_root();
-	if (!phy_debug_root)
-		return;
-
-	rtk_phy->debug_dir = debugfs_create_dir(dev_name(rtk_phy->dev),
-						phy_debug_root);
-
-	debugfs_create_file("parameter", 0444, rtk_phy->debug_dir, rtk_phy,
-			    &rtk_usb2_parameter_fops);
-
-	return;
-}
-
-static inline void remove_debug_files(struct rtk_phy *rtk_phy)
-{
-	debugfs_remove_recursive(rtk_phy->debug_dir);
-}
-#else
-static inline void create_debug_files(struct rtk_phy *rtk_phy) { }
-static inline void remove_debug_files(struct rtk_phy *rtk_phy) { }
-#endif /* CONFIG_DEBUG_FS */
-
-static int get_phy_data_by_efuse(struct rtk_phy *rtk_phy,
-				 struct phy_parameter *phy_parameter, int index)
-{
-	struct phy_cfg *phy_cfg = rtk_phy->phy_cfg;
-	u8 value = 0;
-	struct nvmem_cell *cell;
-	struct soc_device_attribute rtk_soc_groot[] = {
-		    { .family = "Realtek Groot",},
-		    { /* empty */ } };
-
-	if (!phy_cfg->check_efuse)
-		goto out;
-
-	/* Read efuse for usb dc cal */
-	cell = nvmem_cell_get(rtk_phy->dev, "usb-dc-cal");
-	if (IS_ERR(cell)) {
-		dev_dbg(rtk_phy->dev, "%s no usb-dc-cal: %ld\n",
-			__func__, PTR_ERR(cell));
-	} else {
-		unsigned char *buf;
-		size_t buf_size;
-
-		buf = nvmem_cell_read(cell, &buf_size);
-		if (!IS_ERR(buf)) {
-			value = buf[0] & phy_cfg->dc_driving_mask;
-			kfree(buf);
-		}
-		nvmem_cell_put(cell);
-	}
-
-	if (phy_cfg->check_efuse_version == CHECK_EFUSE_V1) {
-		int rate = phy_cfg->efuse_dc_driving_rate;
-
-		if (value <= EFUS_USB_DC_CAL_MAX)
-			phy_parameter->efuse_usb_dc_cal = (int8_t)(value * rate);
-		else
-			phy_parameter->efuse_usb_dc_cal = -(int8_t)
-				    ((EFUS_USB_DC_CAL_MAX & value) * rate);
-
-		if (soc_device_match(rtk_soc_groot)) {
-			dev_dbg(rtk_phy->dev, "For groot IC we need a workaround to adjust efuse_usb_dc_cal\n");
-
-			/* We don't multiple dc_cal_rate=2 for positive dc cal compensate */
-			if (value <= EFUS_USB_DC_CAL_MAX)
-				phy_parameter->efuse_usb_dc_cal = (int8_t)(value);
-
-			/* We set max dc cal compensate is 0x8 if otp is 0x7 */
-			if (value == 0x7)
-				phy_parameter->efuse_usb_dc_cal = (int8_t)(value + 1);
-		}
-	} else { /* for CHECK_EFUSE_V2 */
-		phy_parameter->efuse_usb_dc_cal = value & phy_cfg->dc_driving_mask;
-	}
-
-	/* Read efuse for usb dc disconnect level */
-	value = 0;
-	cell = nvmem_cell_get(rtk_phy->dev, "usb-dc-dis");
-	if (IS_ERR(cell)) {
-		dev_dbg(rtk_phy->dev, "%s no usb-dc-dis: %ld\n",
-			__func__, PTR_ERR(cell));
-	} else {
-		unsigned char *buf;
-		size_t buf_size;
-
-		buf = nvmem_cell_read(cell, &buf_size);
-		if (!IS_ERR(buf)) {
-			value = buf[0] & phy_cfg->dc_disconnect_mask;
-			kfree(buf);
-		}
-		nvmem_cell_put(cell);
-	}
-
-	if (phy_cfg->check_efuse_version == CHECK_EFUSE_V1) {
-		int rate = phy_cfg->efuse_dc_disconnect_rate;
-
-		if (value <= EFUS_USB_DC_DIS_MAX)
-			phy_parameter->efuse_usb_dc_dis = (int8_t)(value * rate);
-		else
-			phy_parameter->efuse_usb_dc_dis = -(int8_t)
-				    ((EFUS_USB_DC_DIS_MAX & value) * rate);
-	} else { /* for CHECK_EFUSE_V2 */
-		phy_parameter->efuse_usb_dc_dis = value & phy_cfg->dc_disconnect_mask;
-	}
-
-out:
-	return 0;
-}
-
-static int parse_phy_data(struct rtk_phy *rtk_phy)
-{
-	struct device *dev = rtk_phy->dev;
-	struct device_node *np = dev->of_node;
-	struct phy_parameter *phy_parameter;
-	int ret = 0;
-	int index;
-
-	rtk_phy->phy_parameter = devm_kzalloc(dev, sizeof(struct phy_parameter) *
-						rtk_phy->num_phy, GFP_KERNEL);
-	if (!rtk_phy->phy_parameter)
-		return -ENOMEM;
-
-	for (index = 0; index < rtk_phy->num_phy; index++) {
-		phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index];
-
-		phy_parameter->phy_reg.reg_wrap_vstatus = of_iomap(np, 0);
-		phy_parameter->phy_reg.reg_gusb2phyacc0 = of_iomap(np, 1) + index;
-		phy_parameter->phy_reg.vstatus_index = index;
-
-		if (of_property_read_bool(np, "realtek,inverse-hstx-sync-clock"))
-			phy_parameter->inverse_hstx_sync_clock = true;
-		else
-			phy_parameter->inverse_hstx_sync_clock = false;
-
-		if (of_property_read_u32_index(np, "realtek,driving-level",
-					       index, &phy_parameter->driving_level))
-			phy_parameter->driving_level = DEFAULT_DC_DRIVING_VALUE;
-
-		if (of_property_read_u32_index(np, "realtek,driving-level-compensate",
-					       index, &phy_parameter->driving_level_compensate))
-			phy_parameter->driving_level_compensate = 0;
-
-		if (of_property_read_u32_index(np, "realtek,disconnection-compensate",
-					       index, &phy_parameter->disconnection_compensate))
-			phy_parameter->disconnection_compensate = 0;
-
-		get_phy_data_by_efuse(rtk_phy, phy_parameter, index);
-
-		update_dc_driving_level(rtk_phy, phy_parameter);
-
-		update_hs_clk_select(rtk_phy, phy_parameter);
-	}
-
-	return ret;
-}
-
-static int rtk_usb2phy_probe(struct platform_device *pdev)
-{
-	struct rtk_phy *rtk_phy;
-	struct device *dev = &pdev->dev;
-	struct phy *generic_phy;
-	struct phy_provider *phy_provider;
-	const struct phy_cfg *phy_cfg;
-	int ret = 0;
-
-	phy_cfg = of_device_get_match_data(dev);
-	if (!phy_cfg) {
-		dev_err(dev, "phy config are not assigned!\n");
-		return -EINVAL;
-	}
-
-	rtk_phy = devm_kzalloc(dev, sizeof(*rtk_phy), GFP_KERNEL);
-	if (!rtk_phy)
-		return -ENOMEM;
-
-	rtk_phy->dev			= &pdev->dev;
-	rtk_phy->phy.dev		= rtk_phy->dev;
-	rtk_phy->phy.label		= "rtk-usb2phy";
-	rtk_phy->phy.notify_port_status = rtk_phy_notify_port_status;
-
-	rtk_phy->phy_cfg = devm_kzalloc(dev, sizeof(*phy_cfg), GFP_KERNEL);
-
-	memcpy(rtk_phy->phy_cfg, phy_cfg, sizeof(*phy_cfg));
-
-	rtk_phy->num_phy = phy_cfg->num_phy;
-
-	ret = parse_phy_data(rtk_phy);
-	if (ret)
-		goto err;
-
-	platform_set_drvdata(pdev, rtk_phy);
-
-	generic_phy = devm_phy_create(rtk_phy->dev, NULL, &ops);
-	if (IS_ERR(generic_phy))
-		return PTR_ERR(generic_phy);
-
-	phy_set_drvdata(generic_phy, rtk_phy);
-
-	phy_provider = devm_of_phy_provider_register(rtk_phy->dev,
-						     of_phy_simple_xlate);
-	if (IS_ERR(phy_provider))
-		return PTR_ERR(phy_provider);
-
-	ret = usb_add_phy_dev(&rtk_phy->phy);
-	if (ret)
-		goto err;
-
-	create_debug_files(rtk_phy);
-
-err:
-	return ret;
-}
-
-static void rtk_usb2phy_remove(struct platform_device *pdev)
-{
-	struct rtk_phy *rtk_phy = platform_get_drvdata(pdev);
-
-	remove_debug_files(rtk_phy);
-
-	usb_remove_phy(&rtk_phy->phy);
-}
-
-static const struct phy_cfg rtd1295_phy_cfg = {
-	.page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE,
-	.page0 = { [0] = {0xe0, 0x90},
-		   [3] = {0xe3, 0x3a},
-		   [4] = {0xe4, 0x68},
-		   [6] = {0xe6, 0x91},
-		  [13] = {0xf5, 0x81},
-		  [15] = {0xf7, 0x02}, },
-	.page1_size = 8,
-	.page1 = { /* default parameter */ },
-	.page2_size = 0,
-	.page2 = { /* no parameter */ },
-	.num_phy = 1,
-	.check_efuse = false,
-	.check_efuse_version = CHECK_EFUSE_V1,
-	.efuse_dc_driving_rate = 1,
-	.dc_driving_mask = 0xf,
-	.efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE,
-	.dc_disconnect_mask = 0xf,
-	.usb_dc_disconnect_at_page0 = true,
-	.do_toggle = true,
-	.do_toggle_driving = false,
-	.driving_updated_for_dev_dis = 0xf,
-	.use_default_parameter = false,
-	.is_double_sensitivity_mode = false,
-};
-
-static const struct phy_cfg rtd1395_phy_cfg = {
-	.page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE,
-	.page0 = { [4] = {0xe4, 0xac},
-		  [13] = {0xf5, 0x00},
-		  [15] = {0xf7, 0x02}, },
-	.page1_size = 8,
-	.page1 = { /* default parameter */ },
-	.page2_size = 0,
-	.page2 = { /* no parameter */ },
-	.num_phy = 1,
-	.check_efuse = false,
-	.check_efuse_version = CHECK_EFUSE_V1,
-	.efuse_dc_driving_rate = 1,
-	.dc_driving_mask = 0xf,
-	.efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE,
-	.dc_disconnect_mask = 0xf,
-	.usb_dc_disconnect_at_page0 = true,
-	.do_toggle = true,
-	.do_toggle_driving = false,
-	.driving_updated_for_dev_dis = 0xf,
-	.use_default_parameter = false,
-	.is_double_sensitivity_mode = false,
-};
-
-static const struct phy_cfg rtd1395_phy_cfg_2port = {
-	.page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE,
-	.page0 = { [4] = {0xe4, 0xac},
-		  [13] = {0xf5, 0x00},
-		  [15] = {0xf7, 0x02}, },
-	.page1_size = 8,
-	.page1 = { /* default parameter */ },
-	.page2_size = 0,
-	.page2 = { /* no parameter */ },
-	.num_phy = 2,
-	.check_efuse = false,
-	.check_efuse_version = CHECK_EFUSE_V1,
-	.efuse_dc_driving_rate = 1,
-	.dc_driving_mask = 0xf,
-	.efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE,
-	.dc_disconnect_mask = 0xf,
-	.usb_dc_disconnect_at_page0 = true,
-	.do_toggle = true,
-	.do_toggle_driving = false,
-	.driving_updated_for_dev_dis = 0xf,
-	.use_default_parameter = false,
-	.is_double_sensitivity_mode = false,
-};
-
-static const struct phy_cfg rtd1619_phy_cfg = {
-	.page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE,
-	.page0 = { [4] = {0xe4, 0x68}, },
-	.page1_size = 8,
-	.page1 = { /* default parameter */ },
-	.page2_size = 0,
-	.page2 = { /* no parameter */ },
-	.num_phy = 1,
-	.check_efuse = true,
-	.check_efuse_version = CHECK_EFUSE_V1,
-	.efuse_dc_driving_rate = 1,
-	.dc_driving_mask = 0xf,
-	.efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE,
-	.dc_disconnect_mask = 0xf,
-	.usb_dc_disconnect_at_page0 = true,
-	.do_toggle = true,
-	.do_toggle_driving = false,
-	.driving_updated_for_dev_dis = 0xf,
-	.use_default_parameter = false,
-	.is_double_sensitivity_mode = false,
-};
-
-static const struct phy_cfg rtd1319_phy_cfg = {
-	.page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE,
-	.page0 = { [0] = {0xe0, 0x18},
-		   [4] = {0xe4, 0x6a},
-		   [7] = {0xe7, 0x71},
-		  [13] = {0xf5, 0x15},
-		  [15] = {0xf7, 0x32}, },
-	.page1_size = 8,
-	.page1 = { [3] = {0xe3, 0x44}, },
-	.page2_size = MAX_USB_PHY_PAGE2_DATA_SIZE,
-	.page2 = { [0] = {0xe0, 0x01}, },
-	.num_phy = 1,
-	.check_efuse = true,
-	.check_efuse_version = CHECK_EFUSE_V1,
-	.efuse_dc_driving_rate = 1,
-	.dc_driving_mask = 0xf,
-	.efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE,
-	.dc_disconnect_mask = 0xf,
-	.usb_dc_disconnect_at_page0 = true,
-	.do_toggle = true,
-	.do_toggle_driving = true,
-	.driving_updated_for_dev_dis = 0xf,
-	.use_default_parameter = false,
-	.is_double_sensitivity_mode = true,
-};
-
-static const struct phy_cfg rtd1312c_phy_cfg = {
-	.page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE,
-	.page0 = { [0] = {0xe0, 0x14},
-		   [4] = {0xe4, 0x67},
-		   [5] = {0xe5, 0x55}, },
-	.page1_size = 8,
-	.page1 = { [3] = {0xe3, 0x23},
-		   [6] = {0xe6, 0x58}, },
-	.page2_size = MAX_USB_PHY_PAGE2_DATA_SIZE,
-	.page2 = { /* default parameter */ },
-	.num_phy = 1,
-	.check_efuse = true,
-	.check_efuse_version = CHECK_EFUSE_V1,
-	.efuse_dc_driving_rate = 1,
-	.dc_driving_mask = 0xf,
-	.efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE,
-	.dc_disconnect_mask = 0xf,
-	.usb_dc_disconnect_at_page0 = true,
-	.do_toggle = true,
-	.do_toggle_driving = true,
-	.driving_updated_for_dev_dis = 0xf,
-	.use_default_parameter = false,
-	.is_double_sensitivity_mode = true,
-};
-
-static const struct phy_cfg rtd1619b_phy_cfg = {
-	.page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE,
-	.page0 = { [0] = {0xe0, 0xa3},
-		   [4] = {0xe4, 0x88},
-		   [5] = {0xe5, 0x4f},
-		   [6] = {0xe6, 0x02}, },
-	.page1_size = 8,
-	.page1 = { [3] = {0xe3, 0x64}, },
-	.page2_size = MAX_USB_PHY_PAGE2_DATA_SIZE,
-	.page2 = { [7] = {0xe7, 0x45}, },
-	.num_phy = 1,
-	.check_efuse = true,
-	.check_efuse_version = CHECK_EFUSE_V1,
-	.efuse_dc_driving_rate = EFUS_USB_DC_CAL_RATE,
-	.dc_driving_mask = 0x1f,
-	.efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE,
-	.dc_disconnect_mask = 0xf,
-	.usb_dc_disconnect_at_page0 = false,
-	.do_toggle = true,
-	.do_toggle_driving = true,
-	.driving_updated_for_dev_dis = 0x8,
-	.use_default_parameter = false,
-	.is_double_sensitivity_mode = true,
-};
-
-static const struct phy_cfg rtd1319d_phy_cfg = {
-	.page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE,
-	.page0 = { [0] = {0xe0, 0xa3},
-		   [4] = {0xe4, 0x8e},
-		   [5] = {0xe5, 0x4f},
-		   [6] = {0xe6, 0x02}, },
-	.page1_size = MAX_USB_PHY_PAGE1_DATA_SIZE,
-	.page1 = { [14] = {0xf5, 0x1}, },
-	.page2_size = MAX_USB_PHY_PAGE2_DATA_SIZE,
-	.page2 = { [7] = {0xe7, 0x44}, },
-	.check_efuse = true,
-	.num_phy = 1,
-	.check_efuse_version = CHECK_EFUSE_V1,
-	.efuse_dc_driving_rate = EFUS_USB_DC_CAL_RATE,
-	.dc_driving_mask = 0x1f,
-	.efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE,
-	.dc_disconnect_mask = 0xf,
-	.usb_dc_disconnect_at_page0 = false,
-	.do_toggle = true,
-	.do_toggle_driving = false,
-	.driving_updated_for_dev_dis = 0x8,
-	.use_default_parameter = false,
-	.is_double_sensitivity_mode = true,
-};
-
-static const struct phy_cfg rtd1315e_phy_cfg = {
-	.page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE,
-	.page0 = { [0] = {0xe0, 0xa3},
-		   [4] = {0xe4, 0x8c},
-		   [5] = {0xe5, 0x4f},
-		   [6] = {0xe6, 0x02}, },
-	.page1_size = MAX_USB_PHY_PAGE1_DATA_SIZE,
-	.page1 = { [3] = {0xe3, 0x7f},
-		  [14] = {0xf5, 0x01}, },
-	.page2_size = MAX_USB_PHY_PAGE2_DATA_SIZE,
-	.page2 = { [7] = {0xe7, 0x44}, },
-	.num_phy = 1,
-	.check_efuse = true,
-	.check_efuse_version = CHECK_EFUSE_V2,
-	.efuse_dc_driving_rate = EFUS_USB_DC_CAL_RATE,
-	.dc_driving_mask = 0x1f,
-	.efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE,
-	.dc_disconnect_mask = 0xf,
-	.usb_dc_disconnect_at_page0 = false,
-	.do_toggle = true,
-	.do_toggle_driving = false,
-	.driving_updated_for_dev_dis = 0x8,
-	.use_default_parameter = false,
-	.is_double_sensitivity_mode = true,
-};
-
-static const struct of_device_id usbphy_rtk_dt_match[] = {
-	{ .compatible = "realtek,rtd1295-usb2phy", .data = &rtd1295_phy_cfg },
-	{ .compatible = "realtek,rtd1312c-usb2phy", .data = &rtd1312c_phy_cfg },
-	{ .compatible = "realtek,rtd1315e-usb2phy", .data = &rtd1315e_phy_cfg },
-	{ .compatible = "realtek,rtd1319-usb2phy", .data = &rtd1319_phy_cfg },
-	{ .compatible = "realtek,rtd1319d-usb2phy", .data = &rtd1319d_phy_cfg },
-	{ .compatible = "realtek,rtd1395-usb2phy", .data = &rtd1395_phy_cfg },
-	{ .compatible = "realtek,rtd1395-usb2phy-2port", .data = &rtd1395_phy_cfg_2port },
-	{ .compatible = "realtek,rtd1619-usb2phy", .data = &rtd1619_phy_cfg },
-	{ .compatible = "realtek,rtd1619b-usb2phy", .data = &rtd1619b_phy_cfg },
-	{},
-};
-MODULE_DEVICE_TABLE(of, usbphy_rtk_dt_match);
-
-static struct platform_driver rtk_usb2phy_driver = {
-	.probe		= rtk_usb2phy_probe,
-	.remove_new	= rtk_usb2phy_remove,
-	.driver		= {
-		.name	= "rtk-usb2phy",
-		.of_match_table = usbphy_rtk_dt_match,
-	},
-};
-
-module_platform_driver(rtk_usb2phy_driver);
-
-MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform: rtk-usb2phy");
-MODULE_AUTHOR("Stanley Chang <stanley_chang@realtek.com>");
-MODULE_DESCRIPTION("Realtek usb 2.0 phy driver");
diff --git a/drivers/phy/realtek/phy-rtk-usb3.c b/drivers/phy/realtek/phy-rtk-usb3.c
deleted file mode 100644
index 67446a85e968..000000000000
--- a/drivers/phy/realtek/phy-rtk-usb3.c
+++ /dev/null
@@ -1,761 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- *  phy-rtk-usb3.c RTK usb3.0 phy driver
- *
- * copyright (c) 2023 realtek semiconductor corporation
- *
- */
-
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/platform_device.h>
-#include <linux/uaccess.h>
-#include <linux/debugfs.h>
-#include <linux/nvmem-consumer.h>
-#include <linux/regmap.h>
-#include <linux/sys_soc.h>
-#include <linux/mfd/syscon.h>
-#include <linux/phy/phy.h>
-#include <linux/usb.h>
-#include <linux/usb/hcd.h>
-#include <linux/usb/phy.h>
-
-#define USB_MDIO_CTRL_PHY_BUSY BIT(7)
-#define USB_MDIO_CTRL_PHY_WRITE BIT(0)
-#define USB_MDIO_CTRL_PHY_ADDR_SHIFT 8
-#define USB_MDIO_CTRL_PHY_DATA_SHIFT 16
-
-#define MAX_USB_PHY_DATA_SIZE 0x30
-#define PHY_ADDR_0X09 0x09
-#define PHY_ADDR_0X0B 0x0b
-#define PHY_ADDR_0X0D 0x0d
-#define PHY_ADDR_0X10 0x10
-#define PHY_ADDR_0X1F 0x1f
-#define PHY_ADDR_0X20 0x20
-#define PHY_ADDR_0X21 0x21
-#define PHY_ADDR_0X30 0x30
-
-#define REG_0X09_FORCE_CALIBRATION BIT(9)
-#define REG_0X0B_RX_OFFSET_RANGE_MASK 0xc
-#define REG_0X0D_RX_DEBUG_TEST_EN BIT(6)
-#define REG_0X10_DEBUG_MODE_SETTING 0x3c0
-#define REG_0X10_DEBUG_MODE_SETTING_MASK 0x3f8
-#define REG_0X1F_RX_OFFSET_CODE_MASK 0x1e
-
-#define USB_U3_TX_LFPS_SWING_TRIM_SHIFT 4
-#define USB_U3_TX_LFPS_SWING_TRIM_MASK 0xf
-#define AMPLITUDE_CONTROL_COARSE_MASK 0xff
-#define AMPLITUDE_CONTROL_FINE_MASK 0xffff
-#define AMPLITUDE_CONTROL_COARSE_DEFAULT 0xff
-#define AMPLITUDE_CONTROL_FINE_DEFAULT 0xffff
-
-#define PHY_ADDR_MAP_ARRAY_INDEX(addr) (addr)
-#define ARRAY_INDEX_MAP_PHY_ADDR(index) (index)
-
-struct phy_reg {
-	void __iomem *reg_mdio_ctl;
-};
-
-struct phy_data {
-	u8 addr;
-	u16 data;
-};
-
-struct phy_cfg {
-	int param_size;
-	struct phy_data param[MAX_USB_PHY_DATA_SIZE];
-
-	bool check_efuse;
-	bool do_toggle;
-	bool do_toggle_once;
-	bool use_default_parameter;
-	bool check_rx_front_end_offset;
-};
-
-struct phy_parameter {
-	struct phy_reg phy_reg;
-
-	/* Get from efuse */
-	u8 efuse_usb_u3_tx_lfps_swing_trim;
-
-	/* Get from dts */
-	u32 amplitude_control_coarse;
-	u32 amplitude_control_fine;
-};
-
-struct rtk_phy {
-	struct usb_phy phy;
-	struct device *dev;
-
-	struct phy_cfg *phy_cfg;
-	int num_phy;
-	struct phy_parameter *phy_parameter;
-
-	struct dentry *debug_dir;
-};
-
-#define PHY_IO_TIMEOUT_USEC		(50000)
-#define PHY_IO_DELAY_US			(100)
-
-static inline int utmi_wait_register(void __iomem *reg, u32 mask, u32 result)
-{
-	int ret;
-	unsigned int val;
-
-	ret = read_poll_timeout(readl, val, ((val & mask) == result),
-				PHY_IO_DELAY_US, PHY_IO_TIMEOUT_USEC, false, reg);
-	if (ret) {
-		pr_err("%s can't program USB phy\n", __func__);
-		return -ETIMEDOUT;
-	}
-
-	return 0;
-}
-
-static int rtk_phy3_wait_vbusy(struct phy_reg *phy_reg)
-{
-	return utmi_wait_register(phy_reg->reg_mdio_ctl, USB_MDIO_CTRL_PHY_BUSY, 0);
-}
-
-static u16 rtk_phy_read(struct phy_reg *phy_reg, char addr)
-{
-	unsigned int tmp;
-	u32 value;
-
-	tmp = (addr << USB_MDIO_CTRL_PHY_ADDR_SHIFT);
-
-	writel(tmp, phy_reg->reg_mdio_ctl);
-
-	rtk_phy3_wait_vbusy(phy_reg);
-
-	value = readl(phy_reg->reg_mdio_ctl);
-	value = value >> USB_MDIO_CTRL_PHY_DATA_SHIFT;
-
-	return (u16)value;
-}
-
-static int rtk_phy_write(struct phy_reg *phy_reg, char addr, u16 data)
-{
-	unsigned int val;
-
-	val = USB_MDIO_CTRL_PHY_WRITE |
-		    (addr << USB_MDIO_CTRL_PHY_ADDR_SHIFT) |
-		    (data << USB_MDIO_CTRL_PHY_DATA_SHIFT);
-
-	writel(val, phy_reg->reg_mdio_ctl);
-
-	rtk_phy3_wait_vbusy(phy_reg);
-
-	return 0;
-}
-
-static void do_rtk_usb3_phy_toggle(struct rtk_phy *rtk_phy, int index, bool connect)
-{
-	struct phy_cfg *phy_cfg = rtk_phy->phy_cfg;
-	struct phy_reg *phy_reg;
-	struct phy_parameter *phy_parameter;
-	struct phy_data *phy_data;
-	u8 addr;
-	u16 data;
-	int i;
-
-	phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index];
-	phy_reg = &phy_parameter->phy_reg;
-
-	if (!phy_cfg->do_toggle)
-		return;
-
-	i = PHY_ADDR_MAP_ARRAY_INDEX(PHY_ADDR_0X09);
-	phy_data = phy_cfg->param + i;
-	addr = phy_data->addr;
-	data = phy_data->data;
-
-	if (!addr && !data) {
-		addr = PHY_ADDR_0X09;
-		data = rtk_phy_read(phy_reg, addr);
-		phy_data->addr = addr;
-		phy_data->data = data;
-	}
-
-	rtk_phy_write(phy_reg, addr, data & (~REG_0X09_FORCE_CALIBRATION));
-	mdelay(1);
-	rtk_phy_write(phy_reg, addr, data | REG_0X09_FORCE_CALIBRATION);
-}
-
-static int do_rtk_phy_init(struct rtk_phy *rtk_phy, int index)
-{
-	struct phy_cfg *phy_cfg;
-	struct phy_reg *phy_reg;
-	struct phy_parameter *phy_parameter;
-	int i = 0;
-
-	phy_cfg = rtk_phy->phy_cfg;
-	phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index];
-	phy_reg = &phy_parameter->phy_reg;
-
-	if (phy_cfg->use_default_parameter)
-		goto do_toggle;
-
-	for (i = 0; i < phy_cfg->param_size; i++) {
-		struct phy_data *phy_data = phy_cfg->param + i;
-		u8 addr = phy_data->addr;
-		u16 data = phy_data->data;
-
-		if (!addr && !data)
-			continue;
-
-		rtk_phy_write(phy_reg, addr, data);
-	}
-
-do_toggle:
-	if (phy_cfg->do_toggle_once)
-		phy_cfg->do_toggle = true;
-
-	do_rtk_usb3_phy_toggle(rtk_phy, index, false);
-
-	if (phy_cfg->do_toggle_once) {
-		u16 check_value = 0;
-		int count = 10;
-		u16 value_0x0d, value_0x10;
-
-		/* Enable Debug mode by set 0x0D and 0x10 */
-		value_0x0d = rtk_phy_read(phy_reg, PHY_ADDR_0X0D);
-		value_0x10 = rtk_phy_read(phy_reg, PHY_ADDR_0X10);
-
-		rtk_phy_write(phy_reg, PHY_ADDR_0X0D,
-			      value_0x0d | REG_0X0D_RX_DEBUG_TEST_EN);
-		rtk_phy_write(phy_reg, PHY_ADDR_0X10,
-			      (value_0x10 & ~REG_0X10_DEBUG_MODE_SETTING_MASK) |
-			      REG_0X10_DEBUG_MODE_SETTING);
-
-		check_value = rtk_phy_read(phy_reg, PHY_ADDR_0X30);
-
-		while (!(check_value & BIT(15))) {
-			check_value = rtk_phy_read(phy_reg, PHY_ADDR_0X30);
-			mdelay(1);
-			if (count-- < 0)
-				break;
-		}
-
-		if (!(check_value & BIT(15)))
-			dev_info(rtk_phy->dev, "toggle fail addr=0x%02x, data=0x%04x\n",
-				 PHY_ADDR_0X30, check_value);
-
-		/* Disable Debug mode by set 0x0D and 0x10 to default*/
-		rtk_phy_write(phy_reg, PHY_ADDR_0X0D, value_0x0d);
-		rtk_phy_write(phy_reg, PHY_ADDR_0X10, value_0x10);
-
-		phy_cfg->do_toggle = false;
-	}
-
-	if (phy_cfg->check_rx_front_end_offset) {
-		u16 rx_offset_code, rx_offset_range;
-		u16 code_mask = REG_0X1F_RX_OFFSET_CODE_MASK;
-		u16 range_mask = REG_0X0B_RX_OFFSET_RANGE_MASK;
-		bool do_update = false;
-
-		rx_offset_code = rtk_phy_read(phy_reg, PHY_ADDR_0X1F);
-		if (((rx_offset_code & code_mask) == 0x0) ||
-		    ((rx_offset_code & code_mask) == code_mask))
-			do_update = true;
-
-		rx_offset_range = rtk_phy_read(phy_reg, PHY_ADDR_0X0B);
-		if (((rx_offset_range & range_mask) == range_mask) && do_update) {
-			dev_warn(rtk_phy->dev, "Don't update rx_offset_range (rx_offset_code=0x%x, rx_offset_range=0x%x)\n",
-				 rx_offset_code, rx_offset_range);
-			do_update = false;
-		}
-
-		if (do_update) {
-			u16 tmp1, tmp2;
-
-			tmp1 = rx_offset_range & (~range_mask);
-			tmp2 = rx_offset_range & range_mask;
-			tmp2 += (1 << 2);
-			rx_offset_range = tmp1 | (tmp2 & range_mask);
-			rtk_phy_write(phy_reg, PHY_ADDR_0X0B, rx_offset_range);
-			goto do_toggle;
-		}
-	}
-
-	return 0;
-}
-
-static int rtk_phy_init(struct phy *phy)
-{
-	struct rtk_phy *rtk_phy = phy_get_drvdata(phy);
-	int ret = 0;
-	int i;
-	unsigned long phy_init_time = jiffies;
-
-	for (i = 0; i < rtk_phy->num_phy; i++)
-		ret = do_rtk_phy_init(rtk_phy, i);
-
-	dev_dbg(rtk_phy->dev, "Initialized RTK USB 3.0 PHY (take %dms)\n",
-		jiffies_to_msecs(jiffies - phy_init_time));
-
-	return ret;
-}
-
-static int rtk_phy_exit(struct phy *phy)
-{
-	return 0;
-}
-
-static const struct phy_ops ops = {
-	.init		= rtk_phy_init,
-	.exit		= rtk_phy_exit,
-	.owner		= THIS_MODULE,
-};
-
-static void rtk_phy_toggle(struct usb_phy *usb3_phy, bool connect, int port)
-{
-	int index = port;
-	struct rtk_phy *rtk_phy = NULL;
-
-	rtk_phy = dev_get_drvdata(usb3_phy->dev);
-
-	if (index > rtk_phy->num_phy) {
-		dev_err(rtk_phy->dev, "%s: The port=%d is not in usb phy (num_phy=%d)\n",
-			__func__, index, rtk_phy->num_phy);
-		return;
-	}
-
-	do_rtk_usb3_phy_toggle(rtk_phy, index, connect);
-}
-
-static int rtk_phy_notify_port_status(struct usb_phy *x, int port,
-				      u16 portstatus, u16 portchange)
-{
-	bool connect = false;
-
-	pr_debug("%s port=%d portstatus=0x%x portchange=0x%x\n",
-		 __func__, port, (int)portstatus, (int)portchange);
-	if (portstatus & USB_PORT_STAT_CONNECTION)
-		connect = true;
-
-	if (portchange & USB_PORT_STAT_C_CONNECTION)
-		rtk_phy_toggle(x, connect, port);
-
-	return 0;
-}
-
-#ifdef CONFIG_DEBUG_FS
-static struct dentry *create_phy_debug_root(void)
-{
-	struct dentry *phy_debug_root;
-
-	phy_debug_root = debugfs_lookup("phy", usb_debug_root);
-	if (!phy_debug_root)
-		phy_debug_root = debugfs_create_dir("phy", usb_debug_root);
-
-	return phy_debug_root;
-}
-
-static int rtk_usb3_parameter_show(struct seq_file *s, void *unused)
-{
-	struct rtk_phy *rtk_phy = s->private;
-	struct phy_cfg *phy_cfg;
-	int i, index;
-
-	phy_cfg = rtk_phy->phy_cfg;
-
-	seq_puts(s, "Property:\n");
-	seq_printf(s, "  check_efuse: %s\n",
-		   phy_cfg->check_efuse ? "Enable" : "Disable");
-	seq_printf(s, "  do_toggle: %s\n",
-		   phy_cfg->do_toggle ? "Enable" : "Disable");
-	seq_printf(s, "  do_toggle_once: %s\n",
-		   phy_cfg->do_toggle_once ? "Enable" : "Disable");
-	seq_printf(s, "  use_default_parameter: %s\n",
-		   phy_cfg->use_default_parameter ? "Enable" : "Disable");
-
-	for (index = 0; index < rtk_phy->num_phy; index++) {
-		struct phy_reg *phy_reg;
-		struct phy_parameter *phy_parameter;
-
-		phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index];
-		phy_reg = &phy_parameter->phy_reg;
-
-		seq_printf(s, "PHY %d:\n", index);
-
-		for (i = 0; i < phy_cfg->param_size; i++) {
-			struct phy_data *phy_data = phy_cfg->param + i;
-			u8 addr = ARRAY_INDEX_MAP_PHY_ADDR(i);
-			u16 data = phy_data->data;
-
-			if (!phy_data->addr && !data)
-				seq_printf(s, "  addr = 0x%02x, data = none   ==> read value = 0x%04x\n",
-					   addr, rtk_phy_read(phy_reg, addr));
-			else
-				seq_printf(s, "  addr = 0x%02x, data = 0x%04x ==> read value = 0x%04x\n",
-					   addr, data, rtk_phy_read(phy_reg, addr));
-		}
-
-		seq_puts(s, "PHY Property:\n");
-		seq_printf(s, "  efuse_usb_u3_tx_lfps_swing_trim: 0x%x\n",
-			   (int)phy_parameter->efuse_usb_u3_tx_lfps_swing_trim);
-		seq_printf(s, "  amplitude_control_coarse: 0x%x\n",
-			   (int)phy_parameter->amplitude_control_coarse);
-		seq_printf(s, "  amplitude_control_fine: 0x%x\n",
-			   (int)phy_parameter->amplitude_control_fine);
-	}
-
-	return 0;
-}
-DEFINE_SHOW_ATTRIBUTE(rtk_usb3_parameter);
-
-static inline void create_debug_files(struct rtk_phy *rtk_phy)
-{
-	struct dentry *phy_debug_root = NULL;
-
-	phy_debug_root = create_phy_debug_root();
-
-	if (!phy_debug_root)
-		return;
-
-	rtk_phy->debug_dir = debugfs_create_dir(dev_name(rtk_phy->dev), phy_debug_root);
-
-	debugfs_create_file("parameter", 0444, rtk_phy->debug_dir, rtk_phy,
-			    &rtk_usb3_parameter_fops);
-
-	return;
-}
-
-static inline void remove_debug_files(struct rtk_phy *rtk_phy)
-{
-	debugfs_remove_recursive(rtk_phy->debug_dir);
-}
-#else
-static inline void create_debug_files(struct rtk_phy *rtk_phy) { }
-static inline void remove_debug_files(struct rtk_phy *rtk_phy) { }
-#endif /* CONFIG_DEBUG_FS */
-
-static int get_phy_data_by_efuse(struct rtk_phy *rtk_phy,
-				 struct phy_parameter *phy_parameter, int index)
-{
-	struct phy_cfg *phy_cfg = rtk_phy->phy_cfg;
-	u8 value = 0;
-	struct nvmem_cell *cell;
-
-	if (!phy_cfg->check_efuse)
-		goto out;
-
-	cell = nvmem_cell_get(rtk_phy->dev, "usb_u3_tx_lfps_swing_trim");
-	if (IS_ERR(cell)) {
-		dev_dbg(rtk_phy->dev, "%s no usb_u3_tx_lfps_swing_trim: %ld\n",
-			__func__, PTR_ERR(cell));
-	} else {
-		unsigned char *buf;
-		size_t buf_size;
-
-		buf = nvmem_cell_read(cell, &buf_size);
-		if (!IS_ERR(buf)) {
-			value = buf[0] & USB_U3_TX_LFPS_SWING_TRIM_MASK;
-			kfree(buf);
-		}
-		nvmem_cell_put(cell);
-	}
-
-	if (value > 0 && value < 0x8)
-		phy_parameter->efuse_usb_u3_tx_lfps_swing_trim = 0x8;
-	else
-		phy_parameter->efuse_usb_u3_tx_lfps_swing_trim = (u8)value;
-
-out:
-	return 0;
-}
-
-static void update_amplitude_control_value(struct rtk_phy *rtk_phy,
-					   struct phy_parameter *phy_parameter)
-{
-	struct phy_cfg *phy_cfg;
-	struct phy_reg *phy_reg;
-
-	phy_reg = &phy_parameter->phy_reg;
-	phy_cfg = rtk_phy->phy_cfg;
-
-	if (phy_parameter->amplitude_control_coarse != AMPLITUDE_CONTROL_COARSE_DEFAULT) {
-		u16 val_mask = AMPLITUDE_CONTROL_COARSE_MASK;
-		u16 data;
-
-		if (!phy_cfg->param[PHY_ADDR_0X20].addr && !phy_cfg->param[PHY_ADDR_0X20].data) {
-			phy_cfg->param[PHY_ADDR_0X20].addr = PHY_ADDR_0X20;
-			data = rtk_phy_read(phy_reg, PHY_ADDR_0X20);
-		} else {
-			data = phy_cfg->param[PHY_ADDR_0X20].data;
-		}
-
-		data &= (~val_mask);
-		data |= (phy_parameter->amplitude_control_coarse & val_mask);
-
-		phy_cfg->param[PHY_ADDR_0X20].data = data;
-	}
-
-	if (phy_parameter->efuse_usb_u3_tx_lfps_swing_trim) {
-		u8 efuse_val = phy_parameter->efuse_usb_u3_tx_lfps_swing_trim;
-		u16 val_mask = USB_U3_TX_LFPS_SWING_TRIM_MASK;
-		int val_shift = USB_U3_TX_LFPS_SWING_TRIM_SHIFT;
-		u16 data;
-
-		if (!phy_cfg->param[PHY_ADDR_0X20].addr && !phy_cfg->param[PHY_ADDR_0X20].data) {
-			phy_cfg->param[PHY_ADDR_0X20].addr = PHY_ADDR_0X20;
-			data = rtk_phy_read(phy_reg, PHY_ADDR_0X20);
-		} else {
-			data = phy_cfg->param[PHY_ADDR_0X20].data;
-		}
-
-		data &= ~(val_mask << val_shift);
-		data |= ((efuse_val & val_mask) << val_shift);
-
-		phy_cfg->param[PHY_ADDR_0X20].data = data;
-	}
-
-	if (phy_parameter->amplitude_control_fine != AMPLITUDE_CONTROL_FINE_DEFAULT) {
-		u16 val_mask = AMPLITUDE_CONTROL_FINE_MASK;
-
-		if (!phy_cfg->param[PHY_ADDR_0X21].addr && !phy_cfg->param[PHY_ADDR_0X21].data)
-			phy_cfg->param[PHY_ADDR_0X21].addr = PHY_ADDR_0X21;
-
-		phy_cfg->param[PHY_ADDR_0X21].data =
-			    phy_parameter->amplitude_control_fine & val_mask;
-	}
-}
-
-static int parse_phy_data(struct rtk_phy *rtk_phy)
-{
-	struct device *dev = rtk_phy->dev;
-	struct phy_parameter *phy_parameter;
-	int ret = 0;
-	int index;
-
-	rtk_phy->phy_parameter = devm_kzalloc(dev, sizeof(struct phy_parameter) *
-					      rtk_phy->num_phy, GFP_KERNEL);
-	if (!rtk_phy->phy_parameter)
-		return -ENOMEM;
-
-	for (index = 0; index < rtk_phy->num_phy; index++) {
-		phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index];
-
-		phy_parameter->phy_reg.reg_mdio_ctl = of_iomap(dev->of_node, 0) + index;
-
-		/* Amplitude control address 0x20 bit 0 to bit 7 */
-		if (of_property_read_u32(dev->of_node, "realtek,amplitude-control-coarse-tuning",
-					 &phy_parameter->amplitude_control_coarse))
-			phy_parameter->amplitude_control_coarse = AMPLITUDE_CONTROL_COARSE_DEFAULT;
-
-		/* Amplitude control address 0x21 bit 0 to bit 16 */
-		if (of_property_read_u32(dev->of_node, "realtek,amplitude-control-fine-tuning",
-					 &phy_parameter->amplitude_control_fine))
-			phy_parameter->amplitude_control_fine = AMPLITUDE_CONTROL_FINE_DEFAULT;
-
-		get_phy_data_by_efuse(rtk_phy, phy_parameter, index);
-
-		update_amplitude_control_value(rtk_phy, phy_parameter);
-	}
-
-	return ret;
-}
-
-static int rtk_usb3phy_probe(struct platform_device *pdev)
-{
-	struct rtk_phy *rtk_phy;
-	struct device *dev = &pdev->dev;
-	struct phy *generic_phy;
-	struct phy_provider *phy_provider;
-	const struct phy_cfg *phy_cfg;
-	int ret;
-
-	phy_cfg = of_device_get_match_data(dev);
-	if (!phy_cfg) {
-		dev_err(dev, "phy config are not assigned!\n");
-		return -EINVAL;
-	}
-
-	rtk_phy = devm_kzalloc(dev, sizeof(*rtk_phy), GFP_KERNEL);
-	if (!rtk_phy)
-		return -ENOMEM;
-
-	rtk_phy->dev			= &pdev->dev;
-	rtk_phy->phy.dev		= rtk_phy->dev;
-	rtk_phy->phy.label		= "rtk-usb3phy";
-	rtk_phy->phy.notify_port_status = rtk_phy_notify_port_status;
-
-	rtk_phy->phy_cfg = devm_kzalloc(dev, sizeof(*phy_cfg), GFP_KERNEL);
-
-	memcpy(rtk_phy->phy_cfg, phy_cfg, sizeof(*phy_cfg));
-
-	rtk_phy->num_phy = 1;
-
-	ret = parse_phy_data(rtk_phy);
-	if (ret)
-		goto err;
-
-	platform_set_drvdata(pdev, rtk_phy);
-
-	generic_phy = devm_phy_create(rtk_phy->dev, NULL, &ops);
-	if (IS_ERR(generic_phy))
-		return PTR_ERR(generic_phy);
-
-	phy_set_drvdata(generic_phy, rtk_phy);
-
-	phy_provider = devm_of_phy_provider_register(rtk_phy->dev, of_phy_simple_xlate);
-	if (IS_ERR(phy_provider))
-		return PTR_ERR(phy_provider);
-
-	ret = usb_add_phy_dev(&rtk_phy->phy);
-	if (ret)
-		goto err;
-
-	create_debug_files(rtk_phy);
-
-err:
-	return ret;
-}
-
-static void rtk_usb3phy_remove(struct platform_device *pdev)
-{
-	struct rtk_phy *rtk_phy = platform_get_drvdata(pdev);
-
-	remove_debug_files(rtk_phy);
-
-	usb_remove_phy(&rtk_phy->phy);
-}
-
-static const struct phy_cfg rtd1295_phy_cfg = {
-	.param_size = MAX_USB_PHY_DATA_SIZE,
-	.param = {  [0] = {0x01, 0x4008},  [1] = {0x01, 0xe046},
-		    [2] = {0x02, 0x6046},  [3] = {0x03, 0x2779},
-		    [4] = {0x04, 0x72f5},  [5] = {0x05, 0x2ad3},
-		    [6] = {0x06, 0x000e},  [7] = {0x07, 0x2e00},
-		    [8] = {0x08, 0x3591},  [9] = {0x09, 0x525c},
-		   [10] = {0x0a, 0xa600}, [11] = {0x0b, 0xa904},
-		   [12] = {0x0c, 0xc000}, [13] = {0x0d, 0xef1c},
-		   [14] = {0x0e, 0x2000}, [15] = {0x0f, 0x0000},
-		   [16] = {0x10, 0x000c}, [17] = {0x11, 0x4c00},
-		   [18] = {0x12, 0xfc00}, [19] = {0x13, 0x0c81},
-		   [20] = {0x14, 0xde01}, [21] = {0x15, 0x0000},
-		   [22] = {0x16, 0x0000}, [23] = {0x17, 0x0000},
-		   [24] = {0x18, 0x0000}, [25] = {0x19, 0x4004},
-		   [26] = {0x1a, 0x1260}, [27] = {0x1b, 0xff00},
-		   [28] = {0x1c, 0xcb00}, [29] = {0x1d, 0xa03f},
-		   [30] = {0x1e, 0xc2e0}, [31] = {0x1f, 0x2807},
-		   [32] = {0x20, 0x947a}, [33] = {0x21, 0x88aa},
-		   [34] = {0x22, 0x0057}, [35] = {0x23, 0xab66},
-		   [36] = {0x24, 0x0800}, [37] = {0x25, 0x0000},
-		   [38] = {0x26, 0x040a}, [39] = {0x27, 0x01d6},
-		   [40] = {0x28, 0xf8c2}, [41] = {0x29, 0x3080},
-		   [42] = {0x2a, 0x3082}, [43] = {0x2b, 0x2078},
-		   [44] = {0x2c, 0xffff}, [45] = {0x2d, 0xffff},
-		   [46] = {0x2e, 0x0000}, [47] = {0x2f, 0x0040}, },
-	.check_efuse = false,
-	.do_toggle = true,
-	.do_toggle_once = false,
-	.use_default_parameter = false,
-	.check_rx_front_end_offset = false,
-};
-
-static const struct phy_cfg rtd1619_phy_cfg = {
-	.param_size = MAX_USB_PHY_DATA_SIZE,
-	.param = {  [8] = {0x08, 0x3591},
-		   [38] = {0x26, 0x840b},
-		   [40] = {0x28, 0xf842}, },
-	.check_efuse = false,
-	.do_toggle = true,
-	.do_toggle_once = false,
-	.use_default_parameter = false,
-	.check_rx_front_end_offset = false,
-};
-
-static const struct phy_cfg rtd1319_phy_cfg = {
-	.param_size = MAX_USB_PHY_DATA_SIZE,
-	.param = {  [1] = {0x01, 0xac86},
-		    [6] = {0x06, 0x0003},
-		    [9] = {0x09, 0x924c},
-		   [10] = {0x0a, 0xa608},
-		   [11] = {0x0b, 0xb905},
-		   [14] = {0x0e, 0x2010},
-		   [32] = {0x20, 0x705a},
-		   [33] = {0x21, 0xf645},
-		   [34] = {0x22, 0x0013},
-		   [35] = {0x23, 0xcb66},
-		   [41] = {0x29, 0xff00}, },
-	.check_efuse = true,
-	.do_toggle = true,
-	.do_toggle_once = false,
-	.use_default_parameter = false,
-	.check_rx_front_end_offset = false,
-};
-
-static const struct phy_cfg rtd1619b_phy_cfg = {
-	.param_size = MAX_USB_PHY_DATA_SIZE,
-	.param = {  [1] = {0x01, 0xac8c},
-		    [6] = {0x06, 0x0017},
-		    [9] = {0x09, 0x724c},
-		   [10] = {0x0a, 0xb610},
-		   [11] = {0x0b, 0xb90d},
-		   [13] = {0x0d, 0xef2a},
-		   [15] = {0x0f, 0x9050},
-		   [16] = {0x10, 0x000c},
-		   [32] = {0x20, 0x70ff},
-		   [34] = {0x22, 0x0013},
-		   [35] = {0x23, 0xdb66},
-		   [38] = {0x26, 0x8609},
-		   [41] = {0x29, 0xff13},
-		   [42] = {0x2a, 0x3070}, },
-	.check_efuse = true,
-	.do_toggle = false,
-	.do_toggle_once = true,
-	.use_default_parameter = false,
-	.check_rx_front_end_offset = false,
-};
-
-static const  struct phy_cfg rtd1319d_phy_cfg = {
-	.param_size = MAX_USB_PHY_DATA_SIZE,
-	.param = {  [1] = {0x01, 0xac89},
-		    [4] = {0x04, 0xf2f5},
-		    [6] = {0x06, 0x0017},
-		    [9] = {0x09, 0x424c},
-		   [10] = {0x0a, 0x9610},
-		   [11] = {0x0b, 0x9901},
-		   [12] = {0x0c, 0xf000},
-		   [13] = {0x0d, 0xef2a},
-		   [14] = {0x0e, 0x1000},
-		   [15] = {0x0f, 0x9050},
-		   [32] = {0x20, 0x7077},
-		   [35] = {0x23, 0x0b62},
-		   [37] = {0x25, 0x10ec},
-		   [42] = {0x2a, 0x3070}, },
-	.check_efuse = true,
-	.do_toggle = false,
-	.do_toggle_once = true,
-	.use_default_parameter = false,
-	.check_rx_front_end_offset = true,
-};
-
-static const struct of_device_id usbphy_rtk_dt_match[] = {
-	{ .compatible = "realtek,rtd1295-usb3phy", .data = &rtd1295_phy_cfg },
-	{ .compatible = "realtek,rtd1319-usb3phy", .data = &rtd1319_phy_cfg },
-	{ .compatible = "realtek,rtd1319d-usb3phy", .data = &rtd1319d_phy_cfg },
-	{ .compatible = "realtek,rtd1619-usb3phy", .data = &rtd1619_phy_cfg },
-	{ .compatible = "realtek,rtd1619b-usb3phy", .data = &rtd1619b_phy_cfg },
-	{},
-};
-MODULE_DEVICE_TABLE(of, usbphy_rtk_dt_match);
-
-static struct platform_driver rtk_usb3phy_driver = {
-	.probe		= rtk_usb3phy_probe,
-	.remove_new	= rtk_usb3phy_remove,
-	.driver		= {
-		.name	= "rtk-usb3phy",
-		.of_match_table = usbphy_rtk_dt_match,
-	},
-};
-
-module_platform_driver(rtk_usb3phy_driver);
-
-MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform: rtk-usb3phy");
-MODULE_AUTHOR("Stanley Chang <stanley_chang@realtek.com>");
-MODULE_DESCRIPTION("Realtek usb 3.0 phy driver");
diff --git a/drivers/phy/sunplus/phy-sunplus-usb2.c b/drivers/phy/sunplus/phy-sunplus-usb2.c
index 0efe74ac9c6a..637a5fbae6d9 100644
--- a/drivers/phy/sunplus/phy-sunplus-usb2.c
+++ b/drivers/phy/sunplus/phy-sunplus-usb2.c
@@ -275,7 +275,7 @@ static int sp_usb_phy_probe(struct platform_device *pdev)
 
 	phy = devm_phy_create(&pdev->dev, NULL, &sp_uphy_ops);
 	if (IS_ERR(phy)) {
-		ret = -PTR_ERR(phy);
+		ret = PTR_ERR(phy);
 		return ret;
 	}
 
diff --git a/drivers/phy/ti/phy-gmii-sel.c b/drivers/phy/ti/phy-gmii-sel.c
index 555b323f45da..bc847d3879f7 100644
--- a/drivers/phy/ti/phy-gmii-sel.c
+++ b/drivers/phy/ti/phy-gmii-sel.c
@@ -64,6 +64,7 @@ struct phy_gmii_sel_priv {
 	u32 num_ports;
 	u32 reg_offset;
 	u32 qsgmii_main_ports;
+	bool no_offset;
 };
 
 static int phy_gmii_sel_mode(struct phy *phy, enum phy_mode mode, int submode)
@@ -402,7 +403,8 @@ static int phy_gmii_sel_init_ports(struct phy_gmii_sel_priv *priv)
 		priv->num_ports = size / sizeof(u32);
 		if (!priv->num_ports)
 			return -EINVAL;
-		priv->reg_offset = __be32_to_cpu(*offset);
+		if (!priv->no_offset)
+			priv->reg_offset = __be32_to_cpu(*offset);
 	}
 
 	if_phys = devm_kcalloc(dev, priv->num_ports,
@@ -471,6 +473,7 @@ static int phy_gmii_sel_probe(struct platform_device *pdev)
 			dev_err(dev, "Failed to get syscon %d\n", ret);
 			return ret;
 		}
+		priv->no_offset = true;
 	}
 
 	ret = phy_gmii_sel_init_ports(priv);
diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index 1de4e1edede0..b11144bb448c 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -366,6 +366,21 @@ config PINCTRL_PALMAS
 	  open drain configuration for the Palmas series devices like
 	  TPS65913, TPS80036 etc.
 
+config PINCTRL_PEF2256
+	tristate "Lantiq PEF2256 (FALC56) pin controller driver"
+	depends on OF && FRAMER_PEF2256
+	select PINMUX
+	select PINCONF
+	select GENERIC_PINCONF
+	help
+	  This option enables the pin controller support for the Lantiq PEF2256
+	  framer, also known as FALC56.
+
+	  If unsure, say N.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called pinctrl-pef2256.
+
 config PINCTRL_PIC32
 	bool "Microchip PIC32 pin controller driver"
 	depends on OF
diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile
index 37575deb7a69..7ac5d59c83e7 100644
--- a/drivers/pinctrl/Makefile
+++ b/drivers/pinctrl/Makefile
@@ -39,6 +39,7 @@ obj-$(CONFIG_PINCTRL_MICROCHIP_SGPIO)	+= pinctrl-microchip-sgpio.o
 obj-$(CONFIG_PINCTRL_MLXBF3)	+= pinctrl-mlxbf3.o
 obj-$(CONFIG_PINCTRL_OCELOT)	+= pinctrl-ocelot.o
 obj-$(CONFIG_PINCTRL_PALMAS)	+= pinctrl-palmas.o
+obj-$(CONFIG_PINCTRL_PEF2256)	+= pinctrl-pef2256.o
 obj-$(CONFIG_PINCTRL_PIC32)	+= pinctrl-pic32.o
 obj-$(CONFIG_PINCTRL_PISTACHIO)	+= pinctrl-pistachio.o
 obj-$(CONFIG_PINCTRL_RK805)	+= pinctrl-rk805.o
diff --git a/drivers/pinctrl/cirrus/Kconfig b/drivers/pinctrl/cirrus/Kconfig
index d6318cb57aff..e7e827a8877a 100644
--- a/drivers/pinctrl/cirrus/Kconfig
+++ b/drivers/pinctrl/cirrus/Kconfig
@@ -12,7 +12,8 @@ config PINCTRL_CS42L43
 
 config PINCTRL_LOCHNAGAR
 	tristate "Cirrus Logic Lochnagar pinctrl driver"
-	depends on MFD_LOCHNAGAR
+	# Avoid clash caused by MIPS defining RST, which is used in the driver
+	depends on MFD_LOCHNAGAR && !MIPS
 	select GPIOLIB
 	select PINMUX
 	select PINCONF
diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index 1fa89be29b8f..f2977eb65522 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -1262,17 +1262,17 @@ static void pinctrl_link_add(struct pinctrl_dev *pctldev,
 static int pinctrl_commit_state(struct pinctrl *p, struct pinctrl_state *state)
 {
 	struct pinctrl_setting *setting, *setting2;
-	struct pinctrl_state *old_state = p->state;
+	struct pinctrl_state *old_state = READ_ONCE(p->state);
 	int ret;
 
-	if (p->state) {
+	if (old_state) {
 		/*
 		 * For each pinmux setting in the old state, forget SW's record
 		 * of mux owner for that pingroup. Any pingroups which are
 		 * still owned by the new state will be re-acquired by the call
 		 * to pinmux_enable_setting() in the loop below.
 		 */
-		list_for_each_entry(setting, &p->state->settings, node) {
+		list_for_each_entry(setting, &old_state->settings, node) {
 			if (setting->type != PIN_MAP_TYPE_MUX_GROUP)
 				continue;
 			pinmux_disable_setting(setting);
diff --git a/drivers/pinctrl/nxp/pinctrl-s32cc.c b/drivers/pinctrl/nxp/pinctrl-s32cc.c
index 7daff9f186cd..f0cad2c501f7 100644
--- a/drivers/pinctrl/nxp/pinctrl-s32cc.c
+++ b/drivers/pinctrl/nxp/pinctrl-s32cc.c
@@ -843,8 +843,8 @@ static int s32_pinctrl_probe_dt(struct platform_device *pdev,
 	if (!np)
 		return -ENODEV;
 
-	if (mem_regions == 0) {
-		dev_err(&pdev->dev, "mem_regions is 0\n");
+	if (mem_regions == 0 || mem_regions >= 10000) {
+		dev_err(&pdev->dev, "mem_regions is invalid: %u\n", mem_regions);
 		return -EINVAL;
 	}
 
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index fb58acb843d9..03ecb3d1aaf6 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -923,6 +923,15 @@ static int amd_gpio_suspend(struct device *dev)
 
 		raw_spin_lock_irqsave(&gpio_dev->lock, flags);
 		gpio_dev->saved_regs[i] = readl(gpio_dev->base + pin * 4) & ~PIN_IRQ_PENDING;
+
+		/* mask any interrupts not intended to be a wake source */
+		if (!(gpio_dev->saved_regs[i] & WAKE_SOURCE)) {
+			writel(gpio_dev->saved_regs[i] & ~BIT(INTERRUPT_MASK_OFF),
+			       gpio_dev->base + pin * 4);
+			pm_pr_dbg("Disabling GPIO #%d interrupt for suspend.\n",
+				  pin);
+		}
+
 		raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 	}
 
diff --git a/drivers/pinctrl/pinctrl-amd.h b/drivers/pinctrl/pinctrl-amd.h
index 34c5c3e71fb2..cf59089f2776 100644
--- a/drivers/pinctrl/pinctrl-amd.h
+++ b/drivers/pinctrl/pinctrl-amd.h
@@ -80,6 +80,11 @@
 #define FUNCTION_MASK		GENMASK(1, 0)
 #define FUNCTION_INVALID	GENMASK(7, 0)
 
+#define WAKE_SOURCE	(BIT(WAKE_CNTRL_OFF_S0I3) | \
+			 BIT(WAKE_CNTRL_OFF_S3)   | \
+			 BIT(WAKE_CNTRL_OFF_S4)   | \
+			 BIT(WAKECNTRL_Z_OFF))
+
 struct amd_function {
 	const char *name;
 	const char * const groups[NSELECTS];
diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c
index 383309e533c3..a27c01fcbb47 100644
--- a/drivers/pinctrl/pinctrl-at91-pio4.c
+++ b/drivers/pinctrl/pinctrl-at91-pio4.c
@@ -1068,6 +1068,13 @@ static const struct of_device_id atmel_pctrl_of_match[] = {
 	}
 };
 
+/*
+ * This lock class allows to tell lockdep that parent IRQ and children IRQ do
+ * not share the same class so it does not raise false positive
+ */
+static struct lock_class_key atmel_lock_key;
+static struct lock_class_key atmel_request_key;
+
 static int atmel_pinctrl_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -1214,6 +1221,7 @@ static int atmel_pinctrl_probe(struct platform_device *pdev)
 		irq_set_chip_and_handler(irq, &atmel_gpio_irq_chip,
 					 handle_simple_irq);
 		irq_set_chip_data(irq, atmel_pioctrl);
+		irq_set_lockdep_class(irq, &atmel_lock_key, &atmel_request_key);
 		dev_dbg(dev,
 			"atmel gpio irq domain: hwirq: %d, linux irq: %d\n",
 			i, irq);
diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c
index 04285c930e94..fe9545c630a2 100644
--- a/drivers/pinctrl/pinctrl-cy8c95x0.c
+++ b/drivers/pinctrl/pinctrl-cy8c95x0.c
@@ -143,6 +143,7 @@ static const struct dmi_system_id cy8c95x0_dmi_acpi_irq_info[] = {
  * @pinctrl_desc:   pin controller description
  * @name:           Chip controller name
  * @tpin:           Total number of pins
+ * @gpio_reset:     GPIO line handler that can reset the IC
  */
 struct cy8c95x0_pinctrl {
 	struct regmap *regmap;
@@ -307,6 +308,9 @@ static const char * const cy8c95x0_groups[] = {
 	"gp77",
 };
 
+static int cy8c95x0_pinmux_direction(struct cy8c95x0_pinctrl *chip,
+				     unsigned int pin, bool input);
+
 static inline u8 cypress_get_port(struct cy8c95x0_pinctrl *chip, unsigned int pin)
 {
 	/* Account for GPORT2 which only has 4 bits */
@@ -711,6 +715,8 @@ static int cy8c95x0_gpio_get_pincfg(struct cy8c95x0_pinctrl *chip,
 	ret = regmap_read(chip->regmap, reg, &reg_val);
 	if (reg_val & bit)
 		arg = 1;
+	if (param == PIN_CONFIG_OUTPUT_ENABLE)
+		arg = !arg;
 
 	*config = pinconf_to_config_packed(param, (u16)arg);
 out:
@@ -726,6 +732,7 @@ static int cy8c95x0_gpio_set_pincfg(struct cy8c95x0_pinctrl *chip,
 	u8 port = cypress_get_port(chip, off);
 	u8 bit = cypress_get_pin_mask(chip, off);
 	unsigned long param = pinconf_to_config_param(config);
+	unsigned long arg = pinconf_to_config_argument(config);
 	unsigned int reg;
 	int ret;
 
@@ -764,6 +771,12 @@ static int cy8c95x0_gpio_set_pincfg(struct cy8c95x0_pinctrl *chip,
 	case PIN_CONFIG_MODE_PWM:
 		reg = CY8C95X0_PWMSEL;
 		break;
+	case PIN_CONFIG_OUTPUT_ENABLE:
+		ret = cy8c95x0_pinmux_direction(chip, off, !arg);
+		goto out;
+	case PIN_CONFIG_INPUT_ENABLE:
+		ret = cy8c95x0_pinmux_direction(chip, off, arg);
+		goto out;
 	default:
 		ret = -ENOTSUPP;
 		goto out;
@@ -821,7 +834,7 @@ static int cy8c95x0_setup_gpiochip(struct cy8c95x0_pinctrl *chip)
 	gc->get_direction = cy8c95x0_gpio_get_direction;
 	gc->get_multiple = cy8c95x0_gpio_get_multiple;
 	gc->set_multiple = cy8c95x0_gpio_set_multiple;
-	gc->set_config = gpiochip_generic_config,
+	gc->set_config = gpiochip_generic_config;
 	gc->can_sleep = true;
 	gc->add_pin_ranges = cy8c95x0_add_pin_ranges;
 
diff --git a/drivers/pinctrl/pinctrl-pef2256.c b/drivers/pinctrl/pinctrl-pef2256.c
new file mode 100644
index 000000000000..868ea33bec3c
--- /dev/null
+++ b/drivers/pinctrl/pinctrl-pef2256.c
@@ -0,0 +1,358 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * PEF2256 also known as FALC56 driver
+ *
+ * Copyright 2023 CS GROUP France
+ *
+ * Author: Herve Codina <herve.codina@bootlin.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/framer/pef2256.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/pinctrl/pinconf-generic.h>
+#include <linux/pinctrl/pinmux.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+/* Port Configuration 1..4 */
+#define PEF2256_PC1		  0x80
+#define PEF2256_PC2		  0x81
+#define PEF2256_PC3		  0x82
+#define PEF2256_PC4		  0x83
+#define PEF2256_12_PC_RPC_MASK	  GENMASK(6, 4)
+#define PEF2256_12_PC_RPC_SYPR	  FIELD_PREP_CONST(PEF2256_12_PC_RPC_MASK, 0x0)
+#define PEF2256_12_PC_RPC_RFM	  FIELD_PREP_CONST(PEF2256_12_PC_RPC_MASK, 0x1)
+#define PEF2256_12_PC_RPC_RFMB	  FIELD_PREP_CONST(PEF2256_12_PC_RPC_MASK, 0x2)
+#define PEF2256_12_PC_RPC_RSIGM	  FIELD_PREP_CONST(PEF2256_12_PC_RPC_MASK, 0x3)
+#define PEF2256_12_PC_RPC_RSIG	  FIELD_PREP_CONST(PEF2256_12_PC_RPC_MASK, 0x4)
+#define PEF2256_12_PC_RPC_DLR	  FIELD_PREP_CONST(PEF2256_12_PC_RPC_MASK, 0x5)
+#define PEF2256_12_PC_RPC_FREEZE  FIELD_PREP_CONST(PEF2256_12_PC_RPC_MASK, 0x6)
+#define PEF2256_12_PC_RPC_RFSP	  FIELD_PREP_CONST(PEF2256_12_PC_RPC_MASK, 0x7)
+#define PEF2256_12_PC_XPC_MASK    GENMASK(4, 0)
+#define PEF2256_12_PC_XPC_SYPX	  FIELD_PREP_CONST(PEF2256_12_PC_XPC_MASK, 0x0)
+#define PEF2256_12_PC_XPC_XFMS	  FIELD_PREP_CONST(PEF2256_12_PC_XPC_MASK, 0x1)
+#define PEF2256_12_PC_XPC_XSIG	  FIELD_PREP_CONST(PEF2256_12_PC_XPC_MASK, 0x2)
+#define PEF2256_12_PC_XPC_TCLK	  FIELD_PREP_CONST(PEF2256_12_PC_XPC_MASK, 0x3)
+#define PEF2256_12_PC_XPC_XMFB	  FIELD_PREP_CONST(PEF2256_12_PC_XPC_MASK, 0x4)
+#define PEF2256_12_PC_XPC_XSIGM	  FIELD_PREP_CONST(PEF2256_12_PC_XPC_MASK, 0x5)
+#define PEF2256_12_PC_XPC_DLX	  FIELD_PREP_CONST(PEF2256_12_PC_XPC_MASK, 0x6)
+#define PEF2256_12_PC_XPC_XCLK	  FIELD_PREP_CONST(PEF2256_12_PC_XPC_MASK, 0x7)
+#define PEF2256_12_PC_XPC_XLT	  FIELD_PREP_CONST(PEF2256_12_PC_XPC_MASK, 0x8)
+#define PEF2256_2X_PC_RPC_MASK	  GENMASK(7, 4)
+#define PEF2256_2X_PC_RPC_SYPR	  FIELD_PREP_CONST(PEF2256_2X_PC_RPC_MASK, 0x0)
+#define PEF2256_2X_PC_RPC_RFM	  FIELD_PREP_CONST(PEF2256_2X_PC_RPC_MASK, 0x1)
+#define PEF2256_2X_PC_RPC_RFMB	  FIELD_PREP_CONST(PEF2256_2X_PC_RPC_MASK, 0x2)
+#define PEF2256_2X_PC_RPC_RSIGM	  FIELD_PREP_CONST(PEF2256_2X_PC_RPC_MASK, 0x3)
+#define PEF2256_2X_PC_RPC_RSIG	  FIELD_PREP_CONST(PEF2256_2X_PC_RPC_MASK, 0x4)
+#define PEF2256_2X_PC_RPC_DLR	  FIELD_PREP_CONST(PEF2256_2X_PC_RPC_MASK, 0x5)
+#define PEF2256_2X_PC_RPC_FREEZE  FIELD_PREP_CONST(PEF2256_2X_PC_RPC_MASK, 0x6)
+#define PEF2256_2X_PC_RPC_RFSP	  FIELD_PREP_CONST(PEF2256_2X_PC_RPC_MASK, 0x7)
+#define PEF2256_2X_PC_RPC_GPI	  FIELD_PREP_CONST(PEF2256_2X_PC_RPC_MASK, 0x9)
+#define PEF2256_2X_PC_RPC_GPOH	  FIELD_PREP_CONST(PEF2256_2X_PC_RPC_MASK, 0xa)
+#define PEF2256_2X_PC_RPC_GPOL	  FIELD_PREP_CONST(PEF2256_2X_PC_RPC_MASK, 0xb)
+#define PEF2256_2X_PC_RPC_LOS	  FIELD_PREP_CONST(PEF2256_2X_PC_RPC_MASK, 0xc)
+#define PEF2256_2X_PC_XPC_MASK	  GENMASK(3, 0)
+#define PEF2256_2X_PC_XPC_SYPX	  FIELD_PREP_CONST(PEF2256_2X_PC_XPC_MASK, 0x0)
+#define PEF2256_2X_PC_XPC_XFMS	  FIELD_PREP_CONST(PEF2256_2X_PC_XPC_MASK, 0x1)
+#define PEF2256_2X_PC_XPC_XSIG	  FIELD_PREP_CONST(PEF2256_2X_PC_XPC_MASK, 0x2)
+#define PEF2256_2X_PC_XPC_TCLK	  FIELD_PREP_CONST(PEF2256_2X_PC_XPC_MASK, 0x3)
+#define PEF2256_2X_PC_XPC_XMFB	  FIELD_PREP_CONST(PEF2256_2X_PC_XPC_MASK, 0x4)
+#define PEF2256_2X_PC_XPC_XSIGM	  FIELD_PREP_CONST(PEF2256_2X_PC_XPC_MASK, 0x5)
+#define PEF2256_2X_PC_XPC_DLX	  FIELD_PREP_CONST(PEF2256_2X_PC_XPC_MASK, 0x6)
+#define PEF2256_2X_PC_XPC_XCLK	  FIELD_PREP_CONST(PEF2256_2X_PC_XPC_MASK, 0x7)
+#define PEF2256_2X_PC_XPC_XLT	  FIELD_PREP_CONST(PEF2256_2X_PC_XPC_MASK, 0x8)
+#define PEF2256_2X_PC_XPC_GPI	  FIELD_PREP_CONST(PEF2256_2X_PC_XPC_MASK, 0x9)
+#define PEF2256_2X_PC_XPC_GPOH	  FIELD_PREP_CONST(PEF2256_2X_PC_XPC_MASK, 0xa)
+#define PEF2256_2X_PC_XPC_GPOL	  FIELD_PREP_CONST(PEF2256_2X_PC_XPC_MASK, 0xb)
+
+struct pef2256_pinreg_desc {
+	int offset;
+	u8 mask;
+};
+
+struct pef2256_function_desc {
+	const char *name;
+	const char * const*groups;
+	unsigned int ngroups;
+	u8 func_val;
+};
+
+struct pef2256_pinctrl {
+	struct device *dev;
+	struct regmap *regmap;
+	enum pef2256_version version;
+	struct pinctrl_desc pctrl_desc;
+	const struct pef2256_function_desc *functions;
+	unsigned int nfunctions;
+};
+
+static int pef2256_get_groups_count(struct pinctrl_dev *pctldev)
+{
+	struct pef2256_pinctrl *pef2256 = pinctrl_dev_get_drvdata(pctldev);
+
+	/* We map 1 group <-> 1 pin */
+	return pef2256->pctrl_desc.npins;
+}
+
+static const char *pef2256_get_group_name(struct pinctrl_dev *pctldev,
+					  unsigned int selector)
+{
+	struct pef2256_pinctrl *pef2256 = pinctrl_dev_get_drvdata(pctldev);
+
+	/* We map 1 group <-> 1 pin */
+	return pef2256->pctrl_desc.pins[selector].name;
+}
+
+static int pef2256_get_group_pins(struct pinctrl_dev *pctldev, unsigned int selector,
+				  const unsigned int **pins,
+				  unsigned int *num_pins)
+{
+	struct pef2256_pinctrl *pef2256 = pinctrl_dev_get_drvdata(pctldev);
+
+	/* We map 1 group <-> 1 pin */
+	*pins = &pef2256->pctrl_desc.pins[selector].number;
+	*num_pins = 1;
+
+	return 0;
+}
+
+static const struct pinctrl_ops pef2256_pctlops = {
+	.get_groups_count	= pef2256_get_groups_count,
+	.get_group_name		= pef2256_get_group_name,
+	.get_group_pins		= pef2256_get_group_pins,
+	.dt_node_to_map		= pinconf_generic_dt_node_to_map_pin,
+	.dt_free_map		= pinconf_generic_dt_free_map,
+};
+
+static int pef2256_get_functions_count(struct pinctrl_dev *pctldev)
+{
+	struct pef2256_pinctrl *pef2256 = pinctrl_dev_get_drvdata(pctldev);
+
+	return pef2256->nfunctions;
+}
+
+static const char *pef2256_get_function_name(struct pinctrl_dev *pctldev,
+					     unsigned int selector)
+{
+	struct pef2256_pinctrl *pef2256 = pinctrl_dev_get_drvdata(pctldev);
+
+	return pef2256->functions[selector].name;
+}
+
+static int pef2256_get_function_groups(struct pinctrl_dev *pctldev, unsigned int selector,
+				       const char * const **groups,
+				       unsigned * const num_groups)
+{
+	struct pef2256_pinctrl *pef2256 = pinctrl_dev_get_drvdata(pctldev);
+
+	*groups = pef2256->functions[selector].groups;
+	*num_groups = pef2256->functions[selector].ngroups;
+	return 0;
+}
+
+static int pef2256_set_mux(struct pinctrl_dev *pctldev, unsigned int func_selector,
+			   unsigned int group_selector)
+{
+	struct pef2256_pinctrl *pef2256 = pinctrl_dev_get_drvdata(pctldev);
+	const struct pef2256_pinreg_desc *pinreg_desc;
+	u8 func_val;
+
+	/* We map 1 group <-> 1 pin */
+	pinreg_desc = pef2256->pctrl_desc.pins[group_selector].drv_data;
+	func_val = pef2256->functions[func_selector].func_val;
+
+	return regmap_update_bits(pef2256->regmap, pinreg_desc->offset,
+				  pinreg_desc->mask, func_val);
+}
+
+static const struct pinmux_ops pef2256_pmxops = {
+	.get_functions_count	= pef2256_get_functions_count,
+	.get_function_name	= pef2256_get_function_name,
+	.get_function_groups	= pef2256_get_function_groups,
+	.set_mux		= pef2256_set_mux,
+};
+
+#define PEF2256_PINCTRL_PIN(_number, _name, _offset, _mask) { \
+	.number = _number, \
+	.name = _name, \
+	.drv_data = &(struct pef2256_pinreg_desc) { \
+		.offset = _offset, \
+		.mask = _mask, \
+	}, \
+}
+
+static const struct pinctrl_pin_desc pef2256_v12_pins[] = {
+	PEF2256_PINCTRL_PIN(0, "RPA", PEF2256_PC1, PEF2256_12_PC_RPC_MASK),
+	PEF2256_PINCTRL_PIN(1, "RPB", PEF2256_PC2, PEF2256_12_PC_RPC_MASK),
+	PEF2256_PINCTRL_PIN(2, "RPC", PEF2256_PC3, PEF2256_12_PC_RPC_MASK),
+	PEF2256_PINCTRL_PIN(3, "RPD", PEF2256_PC4, PEF2256_12_PC_RPC_MASK),
+	PEF2256_PINCTRL_PIN(4, "XPA", PEF2256_PC1, PEF2256_12_PC_XPC_MASK),
+	PEF2256_PINCTRL_PIN(5, "XPB", PEF2256_PC2, PEF2256_12_PC_XPC_MASK),
+	PEF2256_PINCTRL_PIN(6, "XPC", PEF2256_PC3, PEF2256_12_PC_XPC_MASK),
+	PEF2256_PINCTRL_PIN(7, "XPD", PEF2256_PC4, PEF2256_12_PC_XPC_MASK),
+};
+
+static const struct pinctrl_pin_desc pef2256_v2x_pins[] = {
+	PEF2256_PINCTRL_PIN(0, "RPA", PEF2256_PC1, PEF2256_2X_PC_RPC_MASK),
+	PEF2256_PINCTRL_PIN(1, "RPB", PEF2256_PC2, PEF2256_2X_PC_RPC_MASK),
+	PEF2256_PINCTRL_PIN(2, "RPC", PEF2256_PC3, PEF2256_2X_PC_RPC_MASK),
+	PEF2256_PINCTRL_PIN(3, "RPD", PEF2256_PC4, PEF2256_2X_PC_RPC_MASK),
+	PEF2256_PINCTRL_PIN(4, "XPA", PEF2256_PC1, PEF2256_2X_PC_XPC_MASK),
+	PEF2256_PINCTRL_PIN(5, "XPB", PEF2256_PC2, PEF2256_2X_PC_XPC_MASK),
+	PEF2256_PINCTRL_PIN(6, "XPC", PEF2256_PC3, PEF2256_2X_PC_XPC_MASK),
+	PEF2256_PINCTRL_PIN(7, "XPD", PEF2256_PC4, PEF2256_2X_PC_XPC_MASK),
+};
+
+static const char *const pef2256_rp_groups[] = { "RPA", "RPB", "RPC", "RPD" };
+static const char *const pef2256_xp_groups[] = { "XPA", "XPB", "XPC", "XPD" };
+static const char *const pef2256_all_groups[] = { "RPA", "RPB", "RPC", "RPD",
+						  "XPA", "XPB", "XPC", "XPD" };
+
+#define PEF2256_FUNCTION(_name, _func_val, _groups) { \
+	.name = _name, \
+	.groups = _groups, \
+	.ngroups = ARRAY_SIZE(_groups), \
+	.func_val = _func_val, \
+}
+
+static const struct pef2256_function_desc pef2256_v2x_functions[] = {
+	PEF2256_FUNCTION("SYPR",   PEF2256_2X_PC_RPC_SYPR,   pef2256_rp_groups),
+	PEF2256_FUNCTION("RFM",    PEF2256_2X_PC_RPC_RFM,    pef2256_rp_groups),
+	PEF2256_FUNCTION("RFMB",   PEF2256_2X_PC_RPC_RFMB,   pef2256_rp_groups),
+	PEF2256_FUNCTION("RSIGM",  PEF2256_2X_PC_RPC_RSIGM,  pef2256_rp_groups),
+	PEF2256_FUNCTION("RSIG",   PEF2256_2X_PC_RPC_RSIG,   pef2256_rp_groups),
+	PEF2256_FUNCTION("DLR",    PEF2256_2X_PC_RPC_DLR,    pef2256_rp_groups),
+	PEF2256_FUNCTION("FREEZE", PEF2256_2X_PC_RPC_FREEZE, pef2256_rp_groups),
+	PEF2256_FUNCTION("RFSP",   PEF2256_2X_PC_RPC_RFSP,   pef2256_rp_groups),
+	PEF2256_FUNCTION("LOS",    PEF2256_2X_PC_RPC_LOS,    pef2256_rp_groups),
+
+	PEF2256_FUNCTION("SYPX",  PEF2256_2X_PC_XPC_SYPX,  pef2256_xp_groups),
+	PEF2256_FUNCTION("XFMS",  PEF2256_2X_PC_XPC_XFMS,  pef2256_xp_groups),
+	PEF2256_FUNCTION("XSIG",  PEF2256_2X_PC_XPC_XSIG,  pef2256_xp_groups),
+	PEF2256_FUNCTION("TCLK",  PEF2256_2X_PC_XPC_TCLK,  pef2256_xp_groups),
+	PEF2256_FUNCTION("XMFB",  PEF2256_2X_PC_XPC_XMFB,  pef2256_xp_groups),
+	PEF2256_FUNCTION("XSIGM", PEF2256_2X_PC_XPC_XSIGM, pef2256_xp_groups),
+	PEF2256_FUNCTION("DLX",   PEF2256_2X_PC_XPC_DLX,   pef2256_xp_groups),
+	PEF2256_FUNCTION("XCLK",  PEF2256_2X_PC_XPC_XCLK,  pef2256_xp_groups),
+	PEF2256_FUNCTION("XLT",   PEF2256_2X_PC_XPC_XLT,   pef2256_xp_groups),
+
+	PEF2256_FUNCTION("GPI",  PEF2256_2X_PC_RPC_GPI | PEF2256_2X_PC_XPC_GPI,
+			 pef2256_all_groups),
+	PEF2256_FUNCTION("GPOH", PEF2256_2X_PC_RPC_GPOH | PEF2256_2X_PC_XPC_GPOH,
+			 pef2256_all_groups),
+	PEF2256_FUNCTION("GPOL", PEF2256_2X_PC_RPC_GPOL | PEF2256_2X_PC_XPC_GPOL,
+			 pef2256_all_groups),
+};
+
+static const struct pef2256_function_desc pef2256_v12_functions[] = {
+	PEF2256_FUNCTION("SYPR",   PEF2256_12_PC_RPC_SYPR,   pef2256_rp_groups),
+	PEF2256_FUNCTION("RFM",    PEF2256_12_PC_RPC_RFM,    pef2256_rp_groups),
+	PEF2256_FUNCTION("RFMB",   PEF2256_12_PC_RPC_RFMB,   pef2256_rp_groups),
+	PEF2256_FUNCTION("RSIGM",  PEF2256_12_PC_RPC_RSIGM,  pef2256_rp_groups),
+	PEF2256_FUNCTION("RSIG",   PEF2256_12_PC_RPC_RSIG,   pef2256_rp_groups),
+	PEF2256_FUNCTION("DLR",    PEF2256_12_PC_RPC_DLR,    pef2256_rp_groups),
+	PEF2256_FUNCTION("FREEZE", PEF2256_12_PC_RPC_FREEZE, pef2256_rp_groups),
+	PEF2256_FUNCTION("RFSP",   PEF2256_12_PC_RPC_RFSP,   pef2256_rp_groups),
+
+	PEF2256_FUNCTION("SYPX",  PEF2256_12_PC_XPC_SYPX,  pef2256_xp_groups),
+	PEF2256_FUNCTION("XFMS",  PEF2256_12_PC_XPC_XFMS,  pef2256_xp_groups),
+	PEF2256_FUNCTION("XSIG",  PEF2256_12_PC_XPC_XSIG,  pef2256_xp_groups),
+	PEF2256_FUNCTION("TCLK",  PEF2256_12_PC_XPC_TCLK,  pef2256_xp_groups),
+	PEF2256_FUNCTION("XMFB",  PEF2256_12_PC_XPC_XMFB,  pef2256_xp_groups),
+	PEF2256_FUNCTION("XSIGM", PEF2256_12_PC_XPC_XSIGM, pef2256_xp_groups),
+	PEF2256_FUNCTION("DLX",   PEF2256_12_PC_XPC_DLX,   pef2256_xp_groups),
+	PEF2256_FUNCTION("XCLK",  PEF2256_12_PC_XPC_XCLK,  pef2256_xp_groups),
+	PEF2256_FUNCTION("XLT",   PEF2256_12_PC_XPC_XLT,   pef2256_xp_groups),
+};
+
+static int pef2256_register_pinctrl(struct pef2256_pinctrl *pef2256)
+{
+	struct pinctrl_dev	*pctrl;
+
+	pef2256->pctrl_desc.name    = dev_name(pef2256->dev);
+	pef2256->pctrl_desc.owner   = THIS_MODULE;
+	pef2256->pctrl_desc.pctlops = &pef2256_pctlops;
+	pef2256->pctrl_desc.pmxops  = &pef2256_pmxops;
+	if (pef2256->version == PEF2256_VERSION_1_2) {
+		pef2256->pctrl_desc.pins  = pef2256_v12_pins;
+		pef2256->pctrl_desc.npins = ARRAY_SIZE(pef2256_v12_pins);
+		pef2256->functions  = pef2256_v12_functions;
+		pef2256->nfunctions = ARRAY_SIZE(pef2256_v12_functions);
+	} else {
+		pef2256->pctrl_desc.pins  = pef2256_v2x_pins;
+		pef2256->pctrl_desc.npins = ARRAY_SIZE(pef2256_v2x_pins);
+		pef2256->functions  = pef2256_v2x_functions;
+		pef2256->nfunctions = ARRAY_SIZE(pef2256_v2x_functions);
+	}
+
+	pctrl = devm_pinctrl_register(pef2256->dev, &pef2256->pctrl_desc, pef2256);
+	if (IS_ERR(pctrl))
+		return dev_err_probe(pef2256->dev, PTR_ERR(pctrl),
+				     "pinctrl driver registration failed\n");
+
+	return 0;
+}
+
+static void pef2256_reset_pinmux(struct pef2256_pinctrl *pef2256)
+{
+	u8 val;
+	/*
+	 * Reset values cannot be used.
+	 * They define the SYPR/SYPX pin mux for all the RPx and XPx pins and
+	 * Only one pin can be muxed to SYPR and one pin can be muxed to SYPX.
+	 * Choose here an other reset value.
+	 */
+	if (pef2256->version == PEF2256_VERSION_1_2)
+		val = PEF2256_12_PC_XPC_XCLK | PEF2256_12_PC_RPC_RFSP;
+	else
+		val = PEF2256_2X_PC_XPC_GPI | PEF2256_2X_PC_RPC_GPI;
+
+	regmap_write(pef2256->regmap, PEF2256_PC1, val);
+	regmap_write(pef2256->regmap, PEF2256_PC2, val);
+	regmap_write(pef2256->regmap, PEF2256_PC3, val);
+	regmap_write(pef2256->regmap, PEF2256_PC4, val);
+}
+
+static int pef2256_pinctrl_probe(struct platform_device *pdev)
+{
+	struct pef2256_pinctrl *pef2256_pinctrl;
+	struct pef2256 *pef2256;
+	int ret;
+
+	pef2256_pinctrl = devm_kzalloc(&pdev->dev, sizeof(*pef2256_pinctrl), GFP_KERNEL);
+	if (!pef2256_pinctrl)
+		return -ENOMEM;
+
+	device_set_node(&pdev->dev, dev_fwnode(pdev->dev.parent));
+
+	pef2256 = dev_get_drvdata(pdev->dev.parent);
+
+	pef2256_pinctrl->dev = &pdev->dev;
+	pef2256_pinctrl->regmap = pef2256_get_regmap(pef2256);
+	pef2256_pinctrl->version = pef2256_get_version(pef2256);
+
+	platform_set_drvdata(pdev, pef2256_pinctrl);
+
+	pef2256_reset_pinmux(pef2256_pinctrl);
+	ret = pef2256_register_pinctrl(pef2256_pinctrl);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static struct platform_driver pef2256_pinctrl_driver = {
+	.driver = {
+		.name = "lantiq-pef2256-pinctrl",
+	},
+	.probe = pef2256_pinctrl_probe,
+};
+module_platform_driver(pef2256_pinctrl_driver);
+
+MODULE_AUTHOR("Herve Codina <herve.codina@bootlin.com>");
+MODULE_DESCRIPTION("PEF2256 pin controller driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/pinctrl/realtek/pinctrl-rtd.c b/drivers/pinctrl/realtek/pinctrl-rtd.c
index 9c7a1af4ba69..208896593b61 100644
--- a/drivers/pinctrl/realtek/pinctrl-rtd.c
+++ b/drivers/pinctrl/realtek/pinctrl-rtd.c
@@ -146,7 +146,7 @@ static int rtd_pinctrl_get_function_groups(struct pinctrl_dev *pcdev,
 
 static const struct rtd_pin_desc *rtd_pinctrl_find_mux(struct rtd_pinctrl *data, unsigned int pin)
 {
-	if (!data->info->muxes[pin].name)
+	if (data->info->muxes[pin].name)
 		return &data->info->muxes[pin];
 
 	return NULL;
@@ -249,7 +249,7 @@ static const struct pinctrl_pin_desc
 static const struct rtd_pin_config_desc
 	*rtd_pinctrl_find_config(struct rtd_pinctrl *data, unsigned int pin)
 {
-	if (!data->info->configs[pin].name)
+	if (data->info->configs[pin].name)
 		return &data->info->configs[pin];
 
 	return NULL;
diff --git a/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c b/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c
index ea70b8c61679..b29b0ab9892b 100644
--- a/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c
+++ b/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c
@@ -492,7 +492,7 @@ static int starfive_dt_node_to_map(struct pinctrl_dev *pctldev,
 
 	nmaps = 0;
 	ngroups = 0;
-	for_each_child_of_node(np, child) {
+	for_each_available_child_of_node(np, child) {
 		int npinmux = of_property_count_u32_elems(child, "pinmux");
 		int npins   = of_property_count_u32_elems(child, "pins");
 
@@ -527,7 +527,7 @@ static int starfive_dt_node_to_map(struct pinctrl_dev *pctldev,
 	nmaps = 0;
 	ngroups = 0;
 	mutex_lock(&sfp->mutex);
-	for_each_child_of_node(np, child) {
+	for_each_available_child_of_node(np, child) {
 		int npins;
 		int i;
 
diff --git a/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c b/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c
index 9d71e8c13310..6de11a405734 100644
--- a/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c
+++ b/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c
@@ -135,7 +135,7 @@ static int jh7110_dt_node_to_map(struct pinctrl_dev *pctldev,
 	int ret;
 
 	ngroups = 0;
-	for_each_child_of_node(np, child)
+	for_each_available_child_of_node(np, child)
 		ngroups += 1;
 	nmaps = 2 * ngroups;
 
@@ -150,7 +150,7 @@ static int jh7110_dt_node_to_map(struct pinctrl_dev *pctldev,
 	nmaps = 0;
 	ngroups = 0;
 	mutex_lock(&sfp->mutex);
-	for_each_child_of_node(np, child) {
+	for_each_available_child_of_node(np, child) {
 		int npins = of_property_count_u32_elems(child, "pinmux");
 		int *pins;
 		u32 *pinmux;
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c
index 64e8201c7eac..603f900e88c1 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32.c
@@ -1273,9 +1273,11 @@ static struct stm32_desc_pin *stm32_pctrl_get_desc_pin_from_gpio(struct stm32_pi
 	int i;
 
 	/* With few exceptions (e.g. bank 'Z'), pin number matches with pin index in array */
-	pin_desc = pctl->pins + stm32_pin_nb;
-	if (pin_desc->pin.number == stm32_pin_nb)
-		return pin_desc;
+	if (stm32_pin_nb < pctl->npins) {
+		pin_desc = pctl->pins + stm32_pin_nb;
+		if (pin_desc->pin.number == stm32_pin_nb)
+			return pin_desc;
+	}
 
 	/* Otherwise, loop all array to find the pin with the right number */
 	for (i = 0; i < pctl->npins; i++) {
@@ -1368,6 +1370,11 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl, struct fwnode
 	}
 
 	names = devm_kcalloc(dev, npins, sizeof(char *), GFP_KERNEL);
+	if (!names) {
+		err = -ENOMEM;
+		goto err_clk;
+	}
+
 	for (i = 0; i < npins; i++) {
 		stm32_pin = stm32_pctrl_get_desc_pin_from_gpio(pctl, bank, i);
 		if (stm32_pin && stm32_pin->pin.name)
diff --git a/drivers/platform/chrome/cros_ec_debugfs.c b/drivers/platform/chrome/cros_ec_debugfs.c
index 091fdc154d79..6bf6f0e7b597 100644
--- a/drivers/platform/chrome/cros_ec_debugfs.c
+++ b/drivers/platform/chrome/cros_ec_debugfs.c
@@ -454,7 +454,7 @@ static int cros_ec_create_panicinfo(struct cros_ec_debugfs *debug_info)
 	debug_info->panicinfo_blob.data = data;
 	debug_info->panicinfo_blob.size = ret;
 
-	debugfs_create_blob("panicinfo", S_IFREG | 0444, debug_info->dir,
+	debugfs_create_blob("panicinfo", 0444, debug_info->dir,
 			    &debug_info->panicinfo_blob);
 
 	return 0;
diff --git a/drivers/platform/chrome/cros_ec_sensorhub_ring.c b/drivers/platform/chrome/cros_ec_sensorhub_ring.c
index 71948dade0e2..1205219515d6 100644
--- a/drivers/platform/chrome/cros_ec_sensorhub_ring.c
+++ b/drivers/platform/chrome/cros_ec_sensorhub_ring.c
@@ -103,7 +103,7 @@ EXPORT_SYMBOL_GPL(cros_ec_sensorhub_unregister_push_data);
  * @sensorhub: Sensor Hub object
  * @on: true when events are requested.
  *
- * To be called before sleeping or when noone is listening.
+ * To be called before sleeping or when no one is listening.
  * Return: 0 on success, or an error when we can not communicate with the EC.
  *
  */
@@ -133,33 +133,61 @@ int cros_ec_sensorhub_ring_fifo_enable(struct cros_ec_sensorhub *sensorhub,
 	return ret;
 }
 
-static int cros_ec_sensor_ring_median_cmp(const void *pv1, const void *pv2)
+static void cros_ec_sensor_ring_median_swap(s64 *a, s64 *b)
 {
-	s64 v1 = *(s64 *)pv1;
-	s64 v2 = *(s64 *)pv2;
-
-	if (v1 > v2)
-		return 1;
-	else if (v1 < v2)
-		return -1;
-	else
-		return 0;
+	s64 tmp = *a;
+	*a = *b;
+	*b = tmp;
 }
 
 /*
  * cros_ec_sensor_ring_median: Gets median of an array of numbers
  *
- * For now it's implemented using an inefficient > O(n) sort then return
- * the middle element. A more optimal method would be something like
- * quickselect, but given that n = 64 we can probably live with it in the
- * name of clarity.
+ * It's implemented using the quickselect algorithm, which achieves an
+ * average time complexity of O(n) the middle element. In the worst case,
+ * the runtime of quickselect could regress to O(n^2). To mitigate this,
+ * algorithms like median-of-medians exist, which can guarantee O(n) even
+ * in the worst case. However, these algorithms come with a higher
+ * overhead and are more complex to implement, making quickselect a
+ * pragmatic choice for our use case.
  *
- * Warning: the input array gets modified (sorted)!
+ * Warning: the input array gets modified!
  */
 static s64 cros_ec_sensor_ring_median(s64 *array, size_t length)
 {
-	sort(array, length, sizeof(s64), cros_ec_sensor_ring_median_cmp, NULL);
-	return array[length / 2];
+	int lo = 0;
+	int hi = length - 1;
+
+	while (lo <= hi) {
+		int mid = lo + (hi - lo) / 2;
+		int pivot, i;
+
+		if (array[lo] > array[mid])
+			cros_ec_sensor_ring_median_swap(&array[lo], &array[mid]);
+		if (array[lo] > array[hi])
+			cros_ec_sensor_ring_median_swap(&array[lo], &array[hi]);
+		if (array[mid] < array[hi])
+			cros_ec_sensor_ring_median_swap(&array[mid], &array[hi]);
+
+		pivot = array[hi];
+		i = lo - 1;
+
+		for (int j = lo; j < hi; j++)
+			if (array[j] < pivot)
+				cros_ec_sensor_ring_median_swap(&array[++i], &array[j]);
+
+		/* The pivot's index corresponds to i+1. */
+		cros_ec_sensor_ring_median_swap(&array[i + 1], &array[hi]);
+		if (i + 1 == length / 2)
+			return array[i + 1];
+		if (i + 1 > length / 2)
+			hi = i;
+		else
+			lo = i + 2;
+	}
+
+	/* Should never reach here. */
+	return -1;
 }
 
 /*
@@ -175,8 +203,8 @@ static s64 cros_ec_sensor_ring_median(s64 *array, size_t length)
  *
  * While a and b are recorded at accurate times (due to the EC real time
  * nature); c is pretty untrustworthy, even though it's recorded the
- * first thing in ec_irq_handler(). There is a very good change we'll get
- * added lantency due to:
+ * first thing in ec_irq_handler(). There is a very good chance we'll get
+ * added latency due to:
  *   other irqs
  *   ddrfreq
  *   cpuidle
@@ -511,7 +539,7 @@ cros_ec_sensor_ring_process_event(struct cros_ec_sensorhub *sensorhub,
  *                                 ringbuffer.
  *
  * This is the new spreading code, assumes every sample's timestamp
- * preceeds the sample. Run if tight_timestamps == true.
+ * precedes the sample. Run if tight_timestamps == true.
  *
  * Sometimes the EC receives only one interrupt (hence timestamp) for
  * a batch of samples. Only the first sample will have the correct
@@ -595,7 +623,7 @@ cros_ec_sensor_ring_spread_add(struct cros_ec_sensorhub *sensorhub,
 			} else {
 				/*
 				 * Push first sample in the batch to the,
-				 * kifo, it's guaranteed to be correct, the
+				 * kfifo, it's guaranteed to be correct, the
 				 * rest will follow later on.
 				 */
 				sample_idx = 1;
@@ -701,7 +729,7 @@ done_with_this_batch:
  *           last_out -->
  *
  *
- * We spread time for the samples using perod p = (current - TS1)/4.
+ * We spread time for the samples using period p = (current - TS1)/4.
  * between TS1 and TS2: [TS1+p/4, TS1+2p/4, TS1+3p/4, current_timestamp].
  *
  */
diff --git a/drivers/platform/chrome/cros_ec_vbc.c b/drivers/platform/chrome/cros_ec_vbc.c
index 2e4af10c7679..274ea0c64b33 100644
--- a/drivers/platform/chrome/cros_ec_vbc.c
+++ b/drivers/platform/chrome/cros_ec_vbc.c
@@ -20,10 +20,14 @@ static ssize_t vboot_context_read(struct file *filp, struct kobject *kobj,
 	struct device *dev = kobj_to_dev(kobj);
 	struct cros_ec_dev *ec = to_cros_ec_dev(dev);
 	struct cros_ec_device *ecdev = ec->ec_dev;
-	struct ec_params_vbnvcontext *params;
 	struct cros_ec_command *msg;
+	/*
+	 * This should be a pointer to the same type as op field in
+	 * struct ec_params_vbnvcontext.
+	 */
+	uint32_t *params_op;
 	int err;
-	const size_t para_sz = sizeof(params->op);
+	const size_t para_sz = sizeof(*params_op);
 	const size_t resp_sz = sizeof(struct ec_response_vbnvcontext);
 	const size_t payload = max(para_sz, resp_sz);
 
@@ -32,8 +36,8 @@ static ssize_t vboot_context_read(struct file *filp, struct kobject *kobj,
 		return -ENOMEM;
 
 	/* NB: we only kmalloc()ated enough space for the op field */
-	params = (struct ec_params_vbnvcontext *)msg->data;
-	params->op = EC_VBNV_CONTEXT_OP_READ;
+	params_op = (uint32_t *)msg->data;
+	*params_op = EC_VBNV_CONTEXT_OP_READ;
 
 	msg->version = EC_VER_VBNV_CONTEXT;
 	msg->command = EC_CMD_VBNV_CONTEXT;
diff --git a/drivers/platform/chrome/wilco_ec/event.c b/drivers/platform/chrome/wilco_ec/event.c
index f80a7c83cfba..13291fb4214e 100644
--- a/drivers/platform/chrome/wilco_ec/event.c
+++ b/drivers/platform/chrome/wilco_ec/event.c
@@ -495,7 +495,7 @@ static int event_device_add(struct acpi_device *adev)
 free_dev_data:
 	hangup_device(dev_data);
 free_minor:
-	ida_simple_remove(&event_ida, minor);
+	ida_free(&event_ida, minor);
 	return error;
 }
 
@@ -504,7 +504,7 @@ static void event_device_remove(struct acpi_device *adev)
 	struct event_device_data *dev_data = adev->driver_data;
 
 	cdev_device_del(&dev_data->cdev, &dev_data->dev);
-	ida_simple_remove(&event_ida, MINOR(dev_data->dev.devt));
+	ida_free(&event_ida, MINOR(dev_data->dev.devt));
 	hangup_device(dev_data);
 }
 
diff --git a/drivers/platform/chrome/wilco_ec/telemetry.c b/drivers/platform/chrome/wilco_ec/telemetry.c
index 253098bace63..b7c616f3d179 100644
--- a/drivers/platform/chrome/wilco_ec/telemetry.c
+++ b/drivers/platform/chrome/wilco_ec/telemetry.c
@@ -372,7 +372,7 @@ static int telem_device_probe(struct platform_device *pdev)
 
 	dev_data = kzalloc(sizeof(*dev_data), GFP_KERNEL);
 	if (!dev_data) {
-		ida_simple_remove(&telem_ida, minor);
+		ida_free(&telem_ida, minor);
 		return -ENOMEM;
 	}
 
@@ -393,7 +393,7 @@ static int telem_device_probe(struct platform_device *pdev)
 	error = cdev_device_add(&dev_data->cdev, &dev_data->dev);
 	if (error) {
 		put_device(&dev_data->dev);
-		ida_simple_remove(&telem_ida, minor);
+		ida_free(&telem_ida, minor);
 		return error;
 	}
 
@@ -405,7 +405,7 @@ static void telem_device_remove(struct platform_device *pdev)
 	struct telem_device_data *dev_data = platform_get_drvdata(pdev);
 
 	cdev_device_del(&dev_data->cdev, &dev_data->dev);
-	ida_simple_remove(&telem_ida, MINOR(dev_data->dev.devt));
+	ida_free(&telem_ida, MINOR(dev_data->dev.devt));
 	put_device(&dev_data->dev);
 }
 
diff --git a/drivers/platform/mellanox/mlxbf-bootctl.c b/drivers/platform/mellanox/mlxbf-bootctl.c
index 1ac7dab22c63..c1aef3a8fb2d 100644
--- a/drivers/platform/mellanox/mlxbf-bootctl.c
+++ b/drivers/platform/mellanox/mlxbf-bootctl.c
@@ -20,6 +20,7 @@
 
 #define MLXBF_BOOTCTL_SB_SECURE_MASK		0x03
 #define MLXBF_BOOTCTL_SB_TEST_MASK		0x0c
+#define MLXBF_BOOTCTL_SB_DEV_MASK		BIT(4)
 
 #define MLXBF_SB_KEY_NUM			4
 
@@ -40,11 +41,18 @@ static struct mlxbf_bootctl_name boot_names[] = {
 	{ MLXBF_BOOTCTL_NONE, "none" },
 };
 
+enum {
+	MLXBF_BOOTCTL_SB_LIFECYCLE_PRODUCTION = 0,
+	MLXBF_BOOTCTL_SB_LIFECYCLE_GA_SECURE = 1,
+	MLXBF_BOOTCTL_SB_LIFECYCLE_GA_NON_SECURE = 2,
+	MLXBF_BOOTCTL_SB_LIFECYCLE_RMA = 3
+};
+
 static const char * const mlxbf_bootctl_lifecycle_states[] = {
-	[0] = "Production",
-	[1] = "GA Secured",
-	[2] = "GA Non-Secured",
-	[3] = "RMA",
+	[MLXBF_BOOTCTL_SB_LIFECYCLE_PRODUCTION] = "Production",
+	[MLXBF_BOOTCTL_SB_LIFECYCLE_GA_SECURE] = "GA Secured",
+	[MLXBF_BOOTCTL_SB_LIFECYCLE_GA_NON_SECURE] = "GA Non-Secured",
+	[MLXBF_BOOTCTL_SB_LIFECYCLE_RMA] = "RMA",
 };
 
 /* Log header format. */
@@ -247,25 +255,30 @@ static ssize_t second_reset_action_store(struct device *dev,
 static ssize_t lifecycle_state_show(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
+	int status_bits;
+	int use_dev_key;
+	int test_state;
 	int lc_state;
 
-	lc_state = mlxbf_bootctl_smc(MLXBF_BOOTCTL_GET_TBB_FUSE_STATUS,
-				     MLXBF_BOOTCTL_FUSE_STATUS_LIFECYCLE);
-	if (lc_state < 0)
-		return lc_state;
+	status_bits = mlxbf_bootctl_smc(MLXBF_BOOTCTL_GET_TBB_FUSE_STATUS,
+					MLXBF_BOOTCTL_FUSE_STATUS_LIFECYCLE);
+	if (status_bits < 0)
+		return status_bits;
 
-	lc_state &=
-		MLXBF_BOOTCTL_SB_TEST_MASK | MLXBF_BOOTCTL_SB_SECURE_MASK;
+	use_dev_key = status_bits & MLXBF_BOOTCTL_SB_DEV_MASK;
+	test_state = status_bits & MLXBF_BOOTCTL_SB_TEST_MASK;
+	lc_state = status_bits & MLXBF_BOOTCTL_SB_SECURE_MASK;
 
 	/*
 	 * If the test bits are set, we specify that the current state may be
 	 * due to using the test bits.
 	 */
-	if (lc_state & MLXBF_BOOTCTL_SB_TEST_MASK) {
-		lc_state &= MLXBF_BOOTCTL_SB_SECURE_MASK;
-
+	if (test_state) {
 		return sprintf(buf, "%s(test)\n",
 			       mlxbf_bootctl_lifecycle_states[lc_state]);
+	} else if (use_dev_key &&
+		   (lc_state == MLXBF_BOOTCTL_SB_LIFECYCLE_GA_SECURE)) {
+		return sprintf(buf, "Secured (development)\n");
 	}
 
 	return sprintf(buf, "%s\n", mlxbf_bootctl_lifecycle_states[lc_state]);
diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c
index 0b427fc24a96..1dd84c7a79de 100644
--- a/drivers/platform/mellanox/mlxbf-pmc.c
+++ b/drivers/platform/mellanox/mlxbf-pmc.c
@@ -1771,6 +1771,8 @@ static int mlxbf_pmc_init_perftype_counter(struct device *dev, int blk_num)
 	attr->dev_attr.show = mlxbf_pmc_event_list_show;
 	attr->nr = blk_num;
 	attr->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL, "event_list");
+	if (!attr->dev_attr.attr.name)
+		return -ENOMEM;
 	pmc->block[blk_num].block_attr[i] = &attr->dev_attr.attr;
 	attr = NULL;
 
@@ -1784,6 +1786,8 @@ static int mlxbf_pmc_init_perftype_counter(struct device *dev, int blk_num)
 		attr->nr = blk_num;
 		attr->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL,
 							  "enable");
+		if (!attr->dev_attr.attr.name)
+			return -ENOMEM;
 		pmc->block[blk_num].block_attr[++i] = &attr->dev_attr.attr;
 		attr = NULL;
 	}
@@ -1810,6 +1814,8 @@ static int mlxbf_pmc_init_perftype_counter(struct device *dev, int blk_num)
 		attr->nr = blk_num;
 		attr->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL,
 							  "counter%d", j);
+		if (!attr->dev_attr.attr.name)
+			return -ENOMEM;
 		pmc->block[blk_num].block_attr[++i] = &attr->dev_attr.attr;
 		attr = NULL;
 
@@ -1821,6 +1827,8 @@ static int mlxbf_pmc_init_perftype_counter(struct device *dev, int blk_num)
 		attr->nr = blk_num;
 		attr->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL,
 							  "event%d", j);
+		if (!attr->dev_attr.attr.name)
+			return -ENOMEM;
 		pmc->block[blk_num].block_attr[++i] = &attr->dev_attr.attr;
 		attr = NULL;
 	}
@@ -1853,6 +1861,8 @@ static int mlxbf_pmc_init_perftype_reg(struct device *dev, int blk_num)
 		attr->nr = blk_num;
 		attr->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL,
 							  events[j].evt_name);
+		if (!attr->dev_attr.attr.name)
+			return -ENOMEM;
 		pmc->block[blk_num].block_attr[i] = &attr->dev_attr.attr;
 		attr = NULL;
 		i++;
@@ -1882,6 +1892,8 @@ static int mlxbf_pmc_create_groups(struct device *dev, int blk_num)
 	pmc->block[blk_num].block_attr_grp.attrs = pmc->block[blk_num].block_attr;
 	pmc->block[blk_num].block_attr_grp.name = devm_kasprintf(
 		dev, GFP_KERNEL, pmc->block_name[blk_num]);
+	if (!pmc->block[blk_num].block_attr_grp.name)
+		return -ENOMEM;
 	pmc->groups[pmc->group_num] = &pmc->block[blk_num].block_attr_grp;
 	pmc->group_num++;
 
@@ -2063,6 +2075,8 @@ static int mlxbf_pmc_probe(struct platform_device *pdev)
 
 	pmc->hwmon_dev = devm_hwmon_device_register_with_groups(
 		dev, "bfperf", pmc, pmc->groups);
+	if (IS_ERR(pmc->hwmon_dev))
+		return PTR_ERR(pmc->hwmon_dev);
 	platform_set_drvdata(pdev, pmc);
 
 	return 0;
diff --git a/drivers/platform/mellanox/mlxbf-tmfifo.c b/drivers/platform/mellanox/mlxbf-tmfifo.c
index 5c683b4eaf10..ed16ec422a7b 100644
--- a/drivers/platform/mellanox/mlxbf-tmfifo.c
+++ b/drivers/platform/mellanox/mlxbf-tmfifo.c
@@ -91,7 +91,7 @@ struct mlxbf_tmfifo_vring {
 /* Check whether vring is in drop mode. */
 #define IS_VRING_DROP(_r) ({ \
 	typeof(_r) (r) = (_r); \
-	(r->desc_head == &r->drop_desc ? true : false); })
+	r->desc_head == &r->drop_desc; })
 
 /* A stub length to drop maximum length packet. */
 #define VRING_DROP_DESC_MAX_LEN		GENMASK(15, 0)
diff --git a/drivers/platform/mips/rs780e-acpi.c b/drivers/platform/mips/rs780e-acpi.c
index bb0e8ae0eefd..5b8f9cc32589 100644
--- a/drivers/platform/mips/rs780e-acpi.c
+++ b/drivers/platform/mips/rs780e-acpi.c
@@ -32,29 +32,25 @@ static u8 pmio_read_index(u16 index, u8 reg)
 	return inb(index + 1);
 }
 
-void pm_iowrite(u8 reg, u8 value)
+static void pm_iowrite(u8 reg, u8 value)
 {
 	pmio_write_index(PM_INDEX, reg, value);
 }
-EXPORT_SYMBOL(pm_iowrite);
 
-u8 pm_ioread(u8 reg)
+static u8 pm_ioread(u8 reg)
 {
 	return pmio_read_index(PM_INDEX, reg);
 }
-EXPORT_SYMBOL(pm_ioread);
 
-void pm2_iowrite(u8 reg, u8 value)
+static void pm2_iowrite(u8 reg, u8 value)
 {
 	pmio_write_index(PM2_INDEX, reg, value);
 }
-EXPORT_SYMBOL(pm2_iowrite);
 
-u8 pm2_ioread(u8 reg)
+static u8 pm2_ioread(u8 reg)
 {
 	return pmio_read_index(PM2_INDEX, reg);
 }
-EXPORT_SYMBOL(pm2_ioread);
 
 static void acpi_hw_clear_status(void)
 {
diff --git a/drivers/platform/surface/aggregator/Kconfig b/drivers/platform/surface/aggregator/Kconfig
index 88afc38ffdc5..957c216c180c 100644
--- a/drivers/platform/surface/aggregator/Kconfig
+++ b/drivers/platform/surface/aggregator/Kconfig
@@ -5,7 +5,7 @@ menuconfig SURFACE_AGGREGATOR
 	tristate "Microsoft Surface System Aggregator Module Subsystem and Drivers"
 	depends on SERIAL_DEV_BUS
 	depends on ACPI && !RISCV
-	select CRC_CCITT
+	select CRC_ITU_T
 	help
 	  The Surface System Aggregator Module (Surface SAM or SSAM) is an
 	  embedded controller (EC) found on 5th- and later-generation Microsoft
diff --git a/drivers/platform/surface/aggregator/core.c b/drivers/platform/surface/aggregator/core.c
index 1a6373dea109..6152be38398c 100644
--- a/drivers/platform/surface/aggregator/core.c
+++ b/drivers/platform/surface/aggregator/core.c
@@ -231,9 +231,12 @@ static int ssam_receive_buf(struct serdev_device *dev, const unsigned char *buf,
 			    size_t n)
 {
 	struct ssam_controller *ctrl;
+	int ret;
 
 	ctrl = serdev_device_get_drvdata(dev);
-	return ssam_controller_receive_buf(ctrl, buf, n);
+	ret = ssam_controller_receive_buf(ctrl, buf, n);
+
+	return ret < 0 ? 0 : ret;
 }
 
 static void ssam_write_wakeup(struct serdev_device *dev)
diff --git a/drivers/platform/surface/surface_acpi_notify.c b/drivers/platform/surface/surface_acpi_notify.c
index e4dee920da18..20f3870915d2 100644
--- a/drivers/platform/surface/surface_acpi_notify.c
+++ b/drivers/platform/surface/surface_acpi_notify.c
@@ -736,34 +736,6 @@ do {										\
 #define san_consumer_warn(dev, handle, fmt, ...) \
 	san_consumer_printk(warn, dev, handle, fmt, ##__VA_ARGS__)
 
-static bool is_san_consumer(struct platform_device *pdev, acpi_handle handle)
-{
-	struct acpi_handle_list dep_devices;
-	acpi_handle supplier = ACPI_HANDLE(&pdev->dev);
-	acpi_status status;
-	bool ret = false;
-	int i;
-
-	if (!acpi_has_method(handle, "_DEP"))
-		return false;
-
-	status = acpi_evaluate_reference(handle, "_DEP", NULL, &dep_devices);
-	if (ACPI_FAILURE(status)) {
-		san_consumer_dbg(&pdev->dev, handle, "failed to evaluate _DEP\n");
-		return false;
-	}
-
-	for (i = 0; i < dep_devices.count; i++) {
-		if (dep_devices.handles[i] == supplier) {
-			ret = true;
-			break;
-		}
-	}
-
-	acpi_handle_list_free(&dep_devices);
-	return ret;
-}
-
 static acpi_status san_consumer_setup(acpi_handle handle, u32 lvl,
 				      void *context, void **rv)
 {
@@ -772,7 +744,7 @@ static acpi_status san_consumer_setup(acpi_handle handle, u32 lvl,
 	struct acpi_device *adev;
 	struct device_link *link;
 
-	if (!is_san_consumer(pdev, handle))
+	if (!acpi_device_dep(handle, ACPI_HANDLE(&pdev->dev)))
 		return AE_OK;
 
 	/* Ignore ACPI devices that are not present. */
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 7e69fdaccdd5..bdd302274b9a 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -177,10 +177,12 @@ config ACER_WMI
 	depends on INPUT
 	depends on RFKILL || RFKILL = n
 	depends on ACPI_WMI
-	select ACPI_VIDEO
+	depends on ACPI_VIDEO || ACPI_VIDEO = n
+	depends on HWMON
 	select INPUT_SPARSEKMAP
 	select LEDS_CLASS
 	select NEW_LEDS
+	select ACPI_PLATFORM_PROFILE
 	help
 	  This is a driver for newer Acer (and Wistron) laptops. It adds
 	  wireless radio and bluetooth control, and on some laptops,
@@ -263,6 +265,7 @@ config ASUS_WMI
 	depends on RFKILL || RFKILL = n
 	depends on HOTPLUG_PCI
 	depends on ACPI_VIDEO || ACPI_VIDEO = n
+	depends on SERIO_I8042 || SERIO_I8042 = n
 	select INPUT_SPARSEKMAP
 	select LEDS_CLASS
 	select NEW_LEDS
@@ -279,7 +282,6 @@ config ASUS_WMI
 config ASUS_NB_WMI
 	tristate "Asus Notebook WMI Driver"
 	depends on ASUS_WMI
-	depends on SERIO_I8042 || SERIO_I8042 = n
 	help
 	  This is a driver for newer Asus notebooks. It adds extra features
 	  like wireless radio and bluetooth control, leds, hotkeys, backlight...
@@ -1087,6 +1089,21 @@ config INTEL_SCU_IPC_UTIL
 
 source "drivers/platform/x86/siemens/Kconfig"
 
+config SILICOM_PLATFORM
+	tristate "Silicom Edge Networking device support"
+	depends on HWMON
+	depends on GPIOLIB
+	depends on LEDS_CLASS_MULTICOLOR
+	help
+	  This option enables support for the LEDs/GPIO/etc downstream of the
+	  embedded controller on Silicom "Cordoba" hardware and derivatives.
+
+	  This platform driver provides support for various functions via
+	  the Linux LED framework, GPIO framework, Hardware Monitoring (HWMON)
+	  and device attributes.
+
+	  If you have a Silicom network appliance, say Y or M here.
+
 config WINMATE_FM07_KEYS
 	tristate "Winmate FM07/FM07P front-panel keys driver"
 	depends on INPUT
diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile
index c7a18e95ad8c..1de432e8861e 100644
--- a/drivers/platform/x86/Makefile
+++ b/drivers/platform/x86/Makefile
@@ -136,6 +136,9 @@ obj-$(CONFIG_X86_INTEL_LPSS)		+= pmc_atom.o
 # Siemens Simatic Industrial PCs
 obj-$(CONFIG_SIEMENS_SIMATIC_IPC)	+= siemens/
 
+# Silicom
+obj-$(CONFIG_SILICOM_PLATFORM)		+= silicom-platform.o
+
 # Winmate
 obj-$(CONFIG_WINMATE_FM07_KEYS)		+= winmate-fm07-keys.o
 
diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c
index 0e472aa9bf41..88b826e88ebd 100644
--- a/drivers/platform/x86/acer-wmi.c
+++ b/drivers/platform/x86/acer-wmi.c
@@ -20,6 +20,7 @@
 #include <linux/backlight.h>
 #include <linux/leds.h>
 #include <linux/platform_device.h>
+#include <linux/platform_profile.h>
 #include <linux/acpi.h>
 #include <linux/i8042.h>
 #include <linux/rfkill.h>
@@ -29,6 +30,8 @@
 #include <linux/input.h>
 #include <linux/input/sparse-keymap.h>
 #include <acpi/video.h>
+#include <linux/hwmon.h>
+#include <linux/bitfield.h>
 
 MODULE_AUTHOR("Carlos Corbacho");
 MODULE_DESCRIPTION("Acer Laptop WMI Extras Driver");
@@ -62,9 +65,14 @@ MODULE_LICENSE("GPL");
 
 #define ACER_WMID_SET_GAMING_LED_METHODID 2
 #define ACER_WMID_GET_GAMING_LED_METHODID 4
+#define ACER_WMID_GET_GAMING_SYS_INFO_METHODID 5
 #define ACER_WMID_SET_GAMING_FAN_BEHAVIOR 14
 #define ACER_WMID_SET_GAMING_MISC_SETTING_METHODID 22
 
+#define ACER_PREDATOR_V4_THERMAL_PROFILE_EC_OFFSET 0x54
+
+#define ACER_PREDATOR_V4_FAN_SPEED_READ_BIT_MASK GENMASK(20, 8)
+
 /*
  * Acer ACPI method GUIDs
  */
@@ -90,6 +98,12 @@ enum acer_wmi_event_ids {
 	WMID_GAMING_TURBO_KEY_EVENT = 0x7,
 };
 
+enum acer_wmi_predator_v4_sys_info_command {
+	ACER_WMID_CMD_GET_PREDATOR_V4_BAT_STATUS = 0x02,
+	ACER_WMID_CMD_GET_PREDATOR_V4_CPU_FAN_SPEED = 0x0201,
+	ACER_WMID_CMD_GET_PREDATOR_V4_GPU_FAN_SPEED = 0x0601,
+};
+
 static const struct key_entry acer_wmi_keymap[] __initconst = {
 	{KE_KEY, 0x01, {KEY_WLAN} },     /* WiFi */
 	{KE_KEY, 0x03, {KEY_WLAN} },     /* WiFi */
@@ -229,9 +243,11 @@ struct hotkey_function_type_aa {
 #define ACER_CAP_THREEG			BIT(4)
 #define ACER_CAP_SET_FUNCTION_MODE	BIT(5)
 #define ACER_CAP_KBD_DOCK		BIT(6)
-#define ACER_CAP_TURBO_OC     BIT(7)
-#define ACER_CAP_TURBO_LED     BIT(8)
-#define ACER_CAP_TURBO_FAN     BIT(9)
+#define ACER_CAP_TURBO_OC		BIT(7)
+#define ACER_CAP_TURBO_LED		BIT(8)
+#define ACER_CAP_TURBO_FAN		BIT(9)
+#define ACER_CAP_PLATFORM_PROFILE	BIT(10)
+#define ACER_CAP_FAN_SPEED_READ		BIT(11)
 
 /*
  * Interface type flags
@@ -259,6 +275,7 @@ static bool ec_raw_mode;
 static bool has_type_aa;
 static u16 commun_func_bitmap;
 static u8 commun_fn_key_number;
+static bool cycle_gaming_thermal_profile = true;
 
 module_param(mailled, int, 0444);
 module_param(brightness, int, 0444);
@@ -266,12 +283,15 @@ module_param(threeg, int, 0444);
 module_param(force_series, int, 0444);
 module_param(force_caps, int, 0444);
 module_param(ec_raw_mode, bool, 0444);
+module_param(cycle_gaming_thermal_profile, bool, 0644);
 MODULE_PARM_DESC(mailled, "Set initial state of Mail LED");
 MODULE_PARM_DESC(brightness, "Set initial LCD backlight brightness");
 MODULE_PARM_DESC(threeg, "Set initial state of 3G hardware");
 MODULE_PARM_DESC(force_series, "Force a different laptop series");
 MODULE_PARM_DESC(force_caps, "Force the capability bitmask to this value");
 MODULE_PARM_DESC(ec_raw_mode, "Enable EC raw mode");
+MODULE_PARM_DESC(cycle_gaming_thermal_profile,
+	"Set thermal mode key in cycle mode. Disabling it sets the mode key in turbo toggle mode");
 
 struct acer_data {
 	int mailled;
@@ -321,6 +341,7 @@ struct quirk_entry {
 	u8 turbo;
 	u8 cpu_fans;
 	u8 gpu_fans;
+	u8 predator_v4;
 };
 
 static struct quirk_entry *quirks;
@@ -336,6 +357,10 @@ static void __init set_quirks(void)
 	if (quirks->turbo)
 		interface->capability |= ACER_CAP_TURBO_OC | ACER_CAP_TURBO_LED
 					 | ACER_CAP_TURBO_FAN;
+
+	if (quirks->predator_v4)
+		interface->capability |= ACER_CAP_PLATFORM_PROFILE |
+					 ACER_CAP_FAN_SPEED_READ;
 }
 
 static int __init dmi_matched(const struct dmi_system_id *dmi)
@@ -370,6 +395,10 @@ static struct quirk_entry quirk_acer_predator_ph315_53 = {
 	.gpu_fans = 1,
 };
 
+static struct quirk_entry quirk_acer_predator_v4 = {
+	.predator_v4 = 1,
+};
+
 /* This AMW0 laptop has no bluetooth */
 static struct quirk_entry quirk_medion_md_98300 = {
 	.wireless = 1,
@@ -547,6 +576,15 @@ static const struct dmi_system_id acer_quirks[] __initconst = {
 		.driver_data = &quirk_acer_predator_ph315_53,
 	},
 	{
+		.callback = dmi_matched,
+		.ident = "Acer Predator PHN16-71",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Predator PHN16-71"),
+		},
+		.driver_data = &quirk_acer_predator_v4,
+	},
+	{
 		.callback = set_force_caps,
 		.ident = "Acer Aspire Switch 10E SW3-016",
 		.matches = {
@@ -659,6 +697,31 @@ static const struct dmi_system_id non_acer_quirks[] __initconst = {
 	{}
 };
 
+static struct platform_profile_handler platform_profile_handler;
+static bool platform_profile_support;
+
+/*
+ * The profile used before turbo mode. This variable is needed for
+ * returning from turbo mode when the mode key is in toggle mode.
+ */
+static int last_non_turbo_profile;
+
+enum acer_predator_v4_thermal_profile_ec {
+	ACER_PREDATOR_V4_THERMAL_PROFILE_ECO = 0x04,
+	ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO = 0x03,
+	ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE = 0x02,
+	ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET = 0x01,
+	ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED = 0x00,
+};
+
+enum acer_predator_v4_thermal_profile_wmi {
+	ACER_PREDATOR_V4_THERMAL_PROFILE_ECO_WMI = 0x060B,
+	ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO_WMI = 0x050B,
+	ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE_WMI = 0x040B,
+	ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET_WMI = 0x0B,
+	ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED_WMI = 0x010B,
+};
+
 /* Find which quirks are needed for a particular vendor/ model pair */
 static void __init find_quirks(void)
 {
@@ -1339,7 +1402,7 @@ WMI_gaming_execute_u64(u32 method_id, u64 in, u64 *out)
 	struct acpi_buffer input = { (acpi_size) sizeof(u64), (void *)(&in) };
 	struct acpi_buffer result = { ACPI_ALLOCATE_BUFFER, NULL };
 	union acpi_object *obj;
-	u32 tmp = 0;
+	u64 tmp = 0;
 	acpi_status status;
 
 	status = wmi_evaluate_method(WMID_GUID4, 0, method_id, &input, &result);
@@ -1663,6 +1726,26 @@ static int acer_gsensor_event(void)
 	return 0;
 }
 
+static int acer_get_fan_speed(int fan)
+{
+	if (quirks->predator_v4) {
+		acpi_status status;
+		u64 fanspeed;
+
+		status = WMI_gaming_execute_u64(
+			ACER_WMID_GET_GAMING_SYS_INFO_METHODID,
+			fan == 0 ? ACER_WMID_CMD_GET_PREDATOR_V4_CPU_FAN_SPEED :
+				   ACER_WMID_CMD_GET_PREDATOR_V4_GPU_FAN_SPEED,
+			&fanspeed);
+
+		if (ACPI_FAILURE(status))
+			return -EIO;
+
+		return FIELD_GET(ACER_PREDATOR_V4_FAN_SPEED_READ_BIT_MASK, fanspeed);
+	}
+	return -EOPNOTSUPP;
+}
+
 /*
  *  Predator series turbo button
  */
@@ -1698,6 +1781,199 @@ static int acer_toggle_turbo(void)
 	return turbo_led_state;
 }
 
+static int
+acer_predator_v4_platform_profile_get(struct platform_profile_handler *pprof,
+				      enum platform_profile_option *profile)
+{
+	u8 tp;
+	int err;
+
+	err = ec_read(ACER_PREDATOR_V4_THERMAL_PROFILE_EC_OFFSET, &tp);
+
+	if (err < 0)
+		return err;
+
+	switch (tp) {
+	case ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO:
+		*profile = PLATFORM_PROFILE_PERFORMANCE;
+		break;
+	case ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE:
+		*profile = PLATFORM_PROFILE_BALANCED_PERFORMANCE;
+		break;
+	case ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED:
+		*profile = PLATFORM_PROFILE_BALANCED;
+		break;
+	case ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET:
+		*profile = PLATFORM_PROFILE_QUIET;
+		break;
+	case ACER_PREDATOR_V4_THERMAL_PROFILE_ECO:
+		*profile = PLATFORM_PROFILE_LOW_POWER;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int
+acer_predator_v4_platform_profile_set(struct platform_profile_handler *pprof,
+				      enum platform_profile_option profile)
+{
+	int tp;
+	acpi_status status;
+
+	switch (profile) {
+	case PLATFORM_PROFILE_PERFORMANCE:
+		tp = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO_WMI;
+		break;
+	case PLATFORM_PROFILE_BALANCED_PERFORMANCE:
+		tp = ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE_WMI;
+		break;
+	case PLATFORM_PROFILE_BALANCED:
+		tp = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED_WMI;
+		break;
+	case PLATFORM_PROFILE_QUIET:
+		tp = ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET_WMI;
+		break;
+	case PLATFORM_PROFILE_LOW_POWER:
+		tp = ACER_PREDATOR_V4_THERMAL_PROFILE_ECO_WMI;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	status = WMI_gaming_execute_u64(
+		ACER_WMID_SET_GAMING_MISC_SETTING_METHODID, tp, NULL);
+
+	if (ACPI_FAILURE(status))
+		return -EIO;
+
+	if (tp != ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO_WMI)
+		last_non_turbo_profile = tp;
+
+	return 0;
+}
+
+static int acer_platform_profile_setup(void)
+{
+	if (quirks->predator_v4) {
+		int err;
+
+		platform_profile_handler.profile_get =
+			acer_predator_v4_platform_profile_get;
+		platform_profile_handler.profile_set =
+			acer_predator_v4_platform_profile_set;
+
+		set_bit(PLATFORM_PROFILE_PERFORMANCE,
+			platform_profile_handler.choices);
+		set_bit(PLATFORM_PROFILE_BALANCED_PERFORMANCE,
+			platform_profile_handler.choices);
+		set_bit(PLATFORM_PROFILE_BALANCED,
+			platform_profile_handler.choices);
+		set_bit(PLATFORM_PROFILE_QUIET,
+			platform_profile_handler.choices);
+		set_bit(PLATFORM_PROFILE_LOW_POWER,
+			platform_profile_handler.choices);
+
+		err = platform_profile_register(&platform_profile_handler);
+		if (err)
+			return err;
+
+		platform_profile_support = true;
+
+		/* Set default non-turbo profile  */
+		last_non_turbo_profile =
+			ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED_WMI;
+	}
+	return 0;
+}
+
+static int acer_thermal_profile_change(void)
+{
+	/*
+	 * This mode key can rotate each mode or toggle turbo mode.
+	 * On battery, only ECO and BALANCED mode are available.
+	 */
+	if (quirks->predator_v4) {
+		u8 current_tp;
+		int tp, err;
+		u64 on_AC;
+		acpi_status status;
+
+		err = ec_read(ACER_PREDATOR_V4_THERMAL_PROFILE_EC_OFFSET,
+			      &current_tp);
+
+		if (err < 0)
+			return err;
+
+		/* Check power source */
+		status = WMI_gaming_execute_u64(
+			ACER_WMID_GET_GAMING_SYS_INFO_METHODID,
+			ACER_WMID_CMD_GET_PREDATOR_V4_BAT_STATUS, &on_AC);
+
+		if (ACPI_FAILURE(status))
+			return -EIO;
+
+		switch (current_tp) {
+		case ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO:
+			if (!on_AC)
+				tp = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED_WMI;
+			else if (cycle_gaming_thermal_profile)
+				tp = ACER_PREDATOR_V4_THERMAL_PROFILE_ECO_WMI;
+			else
+				tp = last_non_turbo_profile;
+			break;
+		case ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE:
+			if (!on_AC)
+				tp = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED_WMI;
+			else
+				tp = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO_WMI;
+			break;
+		case ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED:
+			if (!on_AC)
+				tp = ACER_PREDATOR_V4_THERMAL_PROFILE_ECO_WMI;
+			else if (cycle_gaming_thermal_profile)
+				tp = ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE_WMI;
+			else
+				tp = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO_WMI;
+			break;
+		case ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET:
+			if (!on_AC)
+				tp = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED_WMI;
+			else if (cycle_gaming_thermal_profile)
+				tp = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED_WMI;
+			else
+				tp = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO_WMI;
+			break;
+		case ACER_PREDATOR_V4_THERMAL_PROFILE_ECO:
+			if (!on_AC)
+				tp = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED_WMI;
+			else if (cycle_gaming_thermal_profile)
+				tp = ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET_WMI;
+			else
+				tp = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO_WMI;
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+
+		status = WMI_gaming_execute_u64(
+			ACER_WMID_SET_GAMING_MISC_SETTING_METHODID, tp, NULL);
+
+		if (ACPI_FAILURE(status))
+			return -EIO;
+
+		/* Store non-turbo profile for turbo mode toggle*/
+		if (tp != ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO_WMI)
+			last_non_turbo_profile = tp;
+
+		platform_profile_notify();
+	}
+
+	return 0;
+}
+
 /*
  * Switch series keyboard dock status
  */
@@ -1997,6 +2273,8 @@ static void acer_wmi_notify(u32 value, void *context)
 	case WMID_GAMING_TURBO_KEY_EVENT:
 		if (return_value.key_num == 0x4)
 			acer_toggle_turbo();
+		if (return_value.key_num == 0x5 && has_cap(ACER_CAP_PLATFORM_PROFILE))
+			acer_thermal_profile_change();
 		break;
 	default:
 		pr_warn("Unknown function number - %d - %d\n",
@@ -2222,6 +2500,8 @@ static u32 get_wmid_devices(void)
 	return devices;
 }
 
+static int acer_wmi_hwmon_init(void);
+
 /*
  * Platform device
  */
@@ -2245,8 +2525,25 @@ static int acer_platform_probe(struct platform_device *device)
 	if (err)
 		goto error_rfkill;
 
-	return err;
+	if (has_cap(ACER_CAP_PLATFORM_PROFILE)) {
+		err = acer_platform_profile_setup();
+		if (err)
+			goto error_platform_profile;
+	}
+
+	if (has_cap(ACER_CAP_FAN_SPEED_READ)) {
+		err = acer_wmi_hwmon_init();
+		if (err)
+			goto error_hwmon;
+	}
+
+	return 0;
 
+error_hwmon:
+	if (platform_profile_support)
+		platform_profile_remove();
+error_platform_profile:
+	acer_rfkill_exit();
 error_rfkill:
 	if (has_cap(ACER_CAP_BRIGHTNESS))
 		acer_backlight_exit();
@@ -2265,6 +2562,9 @@ static void acer_platform_remove(struct platform_device *device)
 		acer_backlight_exit();
 
 	acer_rfkill_exit();
+
+	if (platform_profile_support)
+		platform_profile_remove();
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -2351,6 +2651,73 @@ static void __init create_debugfs(void)
 			   &interface->debug.wmid_devices);
 }
 
+static umode_t acer_wmi_hwmon_is_visible(const void *data,
+					 enum hwmon_sensor_types type, u32 attr,
+					 int channel)
+{
+	switch (type) {
+	case hwmon_fan:
+		if (acer_get_fan_speed(channel) >= 0)
+			return 0444;
+		break;
+	default:
+		return 0;
+	}
+
+	return 0;
+}
+
+static int acer_wmi_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
+			       u32 attr, int channel, long *val)
+{
+	int ret;
+
+	switch (type) {
+	case hwmon_fan:
+		ret = acer_get_fan_speed(channel);
+		if (ret < 0)
+			return ret;
+		*val = ret;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static const struct hwmon_channel_info *const acer_wmi_hwmon_info[] = {
+	HWMON_CHANNEL_INFO(fan, HWMON_F_INPUT, HWMON_F_INPUT), NULL
+};
+
+static const struct hwmon_ops acer_wmi_hwmon_ops = {
+	.read = acer_wmi_hwmon_read,
+	.is_visible = acer_wmi_hwmon_is_visible,
+};
+
+static const struct hwmon_chip_info acer_wmi_hwmon_chip_info = {
+	.ops = &acer_wmi_hwmon_ops,
+	.info = acer_wmi_hwmon_info,
+};
+
+static int acer_wmi_hwmon_init(void)
+{
+	struct device *dev = &acer_platform_device->dev;
+	struct device *hwmon;
+
+	hwmon = devm_hwmon_device_register_with_info(dev, "acer",
+						     &acer_platform_driver,
+						     &acer_wmi_hwmon_chip_info,
+						     NULL);
+
+	if (IS_ERR(hwmon)) {
+		dev_err(dev, "Could not register acer hwmon device\n");
+		return PTR_ERR(hwmon);
+	}
+
+	return 0;
+}
+
 static int __init acer_wmi_init(void)
 {
 	int err;
diff --git a/drivers/platform/x86/amd/Kconfig b/drivers/platform/x86/amd/Kconfig
index 55f3a2fc6aec..54753213cc61 100644
--- a/drivers/platform/x86/amd/Kconfig
+++ b/drivers/platform/x86/amd/Kconfig
@@ -18,3 +18,17 @@ config AMD_HSMP
 
 	  If you choose to compile this driver as a module the module will be
 	  called amd_hsmp.
+
+config AMD_WBRF
+	bool "AMD Wifi RF Band mitigations (WBRF)"
+	depends on ACPI
+	help
+	  WBRF(Wifi Band RFI mitigation) mechanism allows Wifi drivers
+	  to notify the frequencies they are using so that other hardware
+	  can be reconfigured to avoid harmonic conflicts.
+
+	  AMD provides an ACPI based mechanism to support WBRF on platform with
+	  appropriate underlying support.
+
+	  This mechanism will only be activated on platforms that advertise a
+	  need for it.
diff --git a/drivers/platform/x86/amd/Makefile b/drivers/platform/x86/amd/Makefile
index f04932b7a7d1..dcec0a46f8af 100644
--- a/drivers/platform/x86/amd/Makefile
+++ b/drivers/platform/x86/amd/Makefile
@@ -8,3 +8,4 @@ obj-$(CONFIG_AMD_PMC)		+= pmc/
 amd_hsmp-y			:= hsmp.o
 obj-$(CONFIG_AMD_HSMP)		+= amd_hsmp.o
 obj-$(CONFIG_AMD_PMF)		+= pmf/
+obj-$(CONFIG_AMD_WBRF)		+= wbrf.o
diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c
index 6bbffb081053..b456370166b6 100644
--- a/drivers/platform/x86/amd/pmc/pmc-quirks.c
+++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c
@@ -16,12 +16,17 @@
 
 struct quirk_entry {
 	u32 s2idle_bug_mmio;
+	bool spurious_8042;
 };
 
 static struct quirk_entry quirk_s2idle_bug = {
 	.s2idle_bug_mmio = 0xfed80380,
 };
 
+static struct quirk_entry quirk_spurious_8042 = {
+	.spurious_8042 = true,
+};
+
 static const struct dmi_system_id fwbug_list[] = {
 	{
 		.ident = "L14 Gen2 AMD",
@@ -193,6 +198,16 @@ static const struct dmi_system_id fwbug_list[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "HP Laptop 15s-eq2xxx"),
 		}
 	},
+	/* https://community.frame.work/t/tracking-framework-amd-ryzen-7040-series-lid-wakeup-behavior-feedback/39128 */
+	{
+		.ident = "Framework Laptop 13 (Phoenix)",
+		.driver_data = &quirk_spurious_8042,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Framework"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Laptop 13 (AMD Ryzen 7040Series)"),
+			DMI_MATCH(DMI_BIOS_VERSION, "03.03"),
+		}
+	},
 	{}
 };
 
@@ -235,6 +250,9 @@ void amd_pmc_quirks_init(struct amd_pmc_dev *dev)
 {
 	const struct dmi_system_id *dmi_id;
 
+	if (dev->cpu_id == AMD_CPU_ID_CZN)
+		dev->disable_8042_wakeup = true;
+
 	dmi_id = dmi_first_match(fwbug_list);
 	if (!dmi_id)
 		return;
@@ -242,4 +260,6 @@ void amd_pmc_quirks_init(struct amd_pmc_dev *dev)
 	if (dev->quirks->s2idle_bug_mmio)
 		pr_info("Using s2idle quirk to avoid %s platform firmware bug\n",
 			dmi_id->ident);
+	if (dev->quirks->spurious_8042)
+		dev->disable_8042_wakeup = true;
 }
diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c
index cd6ac04c1468..108e12fd580f 100644
--- a/drivers/platform/x86/amd/pmc/pmc.c
+++ b/drivers/platform/x86/amd/pmc/pmc.c
@@ -31,13 +31,13 @@
 #include "pmc.h"
 
 /* SMU communication registers */
-#define AMD_PMC_REGISTER_MESSAGE	0x538
 #define AMD_PMC_REGISTER_RESPONSE	0x980
 #define AMD_PMC_REGISTER_ARGUMENT	0x9BC
 
 /* PMC Scratch Registers */
 #define AMD_PMC_SCRATCH_REG_CZN		0x94
 #define AMD_PMC_SCRATCH_REG_YC		0xD14
+#define AMD_PMC_SCRATCH_REG_1AH		0xF14
 
 /* STB Registers */
 #define AMD_PMC_STB_PMI_0		0x03E30600
@@ -91,16 +91,6 @@
 #define SMU_MSG_LOG_RESET		0x07
 #define SMU_MSG_LOG_DUMP_DATA		0x08
 #define SMU_MSG_GET_SUP_CONSTRAINTS	0x09
-/* List of supported CPU ids */
-#define AMD_CPU_ID_RV			0x15D0
-#define AMD_CPU_ID_RN			0x1630
-#define AMD_CPU_ID_PCO			AMD_CPU_ID_RV
-#define AMD_CPU_ID_CZN			AMD_CPU_ID_RN
-#define AMD_CPU_ID_YC			0x14B5
-#define AMD_CPU_ID_CB			0x14D8
-#define AMD_CPU_ID_PS			0x14E8
-#define AMD_CPU_ID_SP			0x14A4
-#define PCI_DEVICE_ID_AMD_1AH_M20H_ROOT 0x1507
 
 #define PMC_MSG_DELAY_MIN_US		50
 #define RESPONSE_REGISTER_LOOP_MAX	20000
@@ -155,6 +145,7 @@ static const struct amd_pmc_bit_map soc15_ip_blk[] = {
 	{"JPEG",	BIT(18)},
 	{"IPU",		BIT(19)},
 	{"UMSCH",	BIT(20)},
+	{"VPE",		BIT(21)},
 	{}
 };
 
@@ -360,10 +351,17 @@ static void amd_pmc_get_ip_info(struct amd_pmc_dev *dev)
 	case AMD_CPU_ID_CB:
 		dev->num_ips = 12;
 		dev->s2d_msg_id = 0xBE;
+		dev->smu_msg = 0x538;
 		break;
 	case AMD_CPU_ID_PS:
 		dev->num_ips = 21;
 		dev->s2d_msg_id = 0x85;
+		dev->smu_msg = 0x538;
+		break;
+	case PCI_DEVICE_ID_AMD_1AH_M20H_ROOT:
+		dev->num_ips = 22;
+		dev->s2d_msg_id = 0xDE;
+		dev->smu_msg = 0x938;
 		break;
 	}
 }
@@ -598,6 +596,9 @@ static int amd_pmc_idlemask_read(struct amd_pmc_dev *pdev, struct device *dev,
 	case AMD_CPU_ID_PS:
 		val = amd_pmc_reg_read(pdev, AMD_PMC_SCRATCH_REG_YC);
 		break;
+	case PCI_DEVICE_ID_AMD_1AH_M20H_ROOT:
+		val = amd_pmc_reg_read(pdev, AMD_PMC_SCRATCH_REG_1AH);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -628,6 +629,7 @@ static bool amd_pmc_is_stb_supported(struct amd_pmc_dev *dev)
 	case AMD_CPU_ID_YC:
 	case AMD_CPU_ID_CB:
 	case AMD_CPU_ID_PS:
+	case PCI_DEVICE_ID_AMD_1AH_M20H_ROOT:
 		return true;
 	default:
 		return false;
@@ -663,7 +665,7 @@ static void amd_pmc_dump_registers(struct amd_pmc_dev *dev)
 		argument = AMD_S2D_REGISTER_ARGUMENT;
 		response = AMD_S2D_REGISTER_RESPONSE;
 	} else {
-		message = AMD_PMC_REGISTER_MESSAGE;
+		message = dev->smu_msg;
 		argument = AMD_PMC_REGISTER_ARGUMENT;
 		response = AMD_PMC_REGISTER_RESPONSE;
 	}
@@ -690,7 +692,7 @@ static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, u32 arg, u32 *data, u8 msg,
 		argument = AMD_S2D_REGISTER_ARGUMENT;
 		response = AMD_S2D_REGISTER_RESPONSE;
 	} else {
-		message = AMD_PMC_REGISTER_MESSAGE;
+		message = dev->smu_msg;
 		argument = AMD_PMC_REGISTER_ARGUMENT;
 		response = AMD_PMC_REGISTER_RESPONSE;
 	}
@@ -761,24 +763,28 @@ static int amd_pmc_get_os_hint(struct amd_pmc_dev *dev)
 	case AMD_CPU_ID_YC:
 	case AMD_CPU_ID_CB:
 	case AMD_CPU_ID_PS:
+	case PCI_DEVICE_ID_AMD_1AH_M20H_ROOT:
 		return MSG_OS_HINT_RN;
 	}
 	return -EINVAL;
 }
 
-static int amd_pmc_czn_wa_irq1(struct amd_pmc_dev *pdev)
+static int amd_pmc_wa_irq1(struct amd_pmc_dev *pdev)
 {
 	struct device *d;
 	int rc;
 
-	if (!pdev->major) {
-		rc = amd_pmc_get_smu_version(pdev);
-		if (rc)
-			return rc;
-	}
+	/* cezanne platform firmware has a fix in 64.66.0 */
+	if (pdev->cpu_id == AMD_CPU_ID_CZN) {
+		if (!pdev->major) {
+			rc = amd_pmc_get_smu_version(pdev);
+			if (rc)
+				return rc;
+		}
 
-	if (pdev->major > 64 || (pdev->major == 64 && pdev->minor > 65))
-		return 0;
+		if (pdev->major > 64 || (pdev->major == 64 && pdev->minor > 65))
+			return 0;
+	}
 
 	d = bus_find_device_by_name(&serio_bus, NULL, "serio0");
 	if (!d)
@@ -937,8 +943,8 @@ static int amd_pmc_suspend_handler(struct device *dev)
 {
 	struct amd_pmc_dev *pdev = dev_get_drvdata(dev);
 
-	if (pdev->cpu_id == AMD_CPU_ID_CZN && !disable_workarounds) {
-		int rc = amd_pmc_czn_wa_irq1(pdev);
+	if (pdev->disable_8042_wakeup && !disable_workarounds) {
+		int rc = amd_pmc_wa_irq1(pdev);
 
 		if (rc) {
 			dev_err(pdev->dev, "failed to adjust keyboard wakeup: %d\n", rc);
@@ -964,33 +970,6 @@ static const struct pci_device_id pmc_pci_ids[] = {
 	{ }
 };
 
-static int amd_pmc_get_dram_size(struct amd_pmc_dev *dev)
-{
-	int ret;
-
-	switch (dev->cpu_id) {
-	case AMD_CPU_ID_YC:
-		if (!(dev->major > 90 || (dev->major == 90 && dev->minor > 39))) {
-			ret = -EINVAL;
-			goto err_dram_size;
-		}
-		break;
-	default:
-		ret = -EINVAL;
-		goto err_dram_size;
-	}
-
-	ret = amd_pmc_send_cmd(dev, S2D_DRAM_SIZE, &dev->dram_size, dev->s2d_msg_id, true);
-	if (ret || !dev->dram_size)
-		goto err_dram_size;
-
-	return 0;
-
-err_dram_size:
-	dev_err(dev->dev, "DRAM size command not supported for this platform\n");
-	return ret;
-}
-
 static int amd_pmc_s2d_init(struct amd_pmc_dev *dev)
 {
 	u32 phys_addr_low, phys_addr_hi;
@@ -1001,16 +980,13 @@ static int amd_pmc_s2d_init(struct amd_pmc_dev *dev)
 	/* Spill to DRAM feature uses separate SMU message port */
 	dev->msg_port = 1;
 
-	/* Get num of IP blocks within the SoC */
-	amd_pmc_get_ip_info(dev);
-
 	amd_pmc_send_cmd(dev, S2D_TELEMETRY_SIZE, &size, dev->s2d_msg_id, true);
 	if (size != S2D_TELEMETRY_BYTES_MAX)
 		return -EIO;
 
 	/* Get DRAM size */
-	ret = amd_pmc_get_dram_size(dev);
-	if (ret)
+	ret = amd_pmc_send_cmd(dev, S2D_DRAM_SIZE, &dev->dram_size, dev->s2d_msg_id, true);
+	if (ret || !dev->dram_size)
 		dev->dram_size = S2D_TELEMETRY_DRAMBYTES_MAX;
 
 	/* Get STB DRAM address */
@@ -1111,6 +1087,9 @@ static int amd_pmc_probe(struct platform_device *pdev)
 
 	mutex_init(&dev->lock);
 
+	/* Get num of IP blocks within the SoC */
+	amd_pmc_get_ip_info(dev);
+
 	if (enable_stb && amd_pmc_is_stb_supported(dev)) {
 		err = amd_pmc_s2d_init(dev);
 		if (err)
diff --git a/drivers/platform/x86/amd/pmc/pmc.h b/drivers/platform/x86/amd/pmc/pmc.h
index c27bd6a5642f..827eef65e133 100644
--- a/drivers/platform/x86/amd/pmc/pmc.h
+++ b/drivers/platform/x86/amd/pmc/pmc.h
@@ -26,6 +26,7 @@ struct amd_pmc_dev {
 	u32 dram_size;
 	u32 num_ips;
 	u32 s2d_msg_id;
+	u32 smu_msg;
 /* SMU version information */
 	u8 smu_program;
 	u8 major;
@@ -36,9 +37,21 @@ struct amd_pmc_dev {
 	struct mutex lock; /* generic mutex lock */
 	struct dentry *dbgfs_dir;
 	struct quirk_entry *quirks;
+	bool disable_8042_wakeup;
 };
 
 void amd_pmc_process_restore_quirks(struct amd_pmc_dev *dev);
 void amd_pmc_quirks_init(struct amd_pmc_dev *dev);
 
+/* List of supported CPU ids */
+#define AMD_CPU_ID_RV			0x15D0
+#define AMD_CPU_ID_RN			0x1630
+#define AMD_CPU_ID_PCO			AMD_CPU_ID_RV
+#define AMD_CPU_ID_CZN			AMD_CPU_ID_RN
+#define AMD_CPU_ID_YC			0x14B5
+#define AMD_CPU_ID_CB			0x14D8
+#define AMD_CPU_ID_PS			0x14E8
+#define AMD_CPU_ID_SP			0x14A4
+#define PCI_DEVICE_ID_AMD_1AH_M20H_ROOT 0x1507
+
 #endif /* PMC_H */
diff --git a/drivers/platform/x86/amd/pmf/Kconfig b/drivers/platform/x86/amd/pmf/Kconfig
index 3064bc8ea167..f246252bddd8 100644
--- a/drivers/platform/x86/amd/pmf/Kconfig
+++ b/drivers/platform/x86/amd/pmf/Kconfig
@@ -9,6 +9,7 @@ config AMD_PMF
 	depends on POWER_SUPPLY
 	depends on AMD_NB
 	select ACPI_PLATFORM_PROFILE
+	depends on TEE && AMDTEE
 	help
 	  This driver provides support for the AMD Platform Management Framework.
 	  The goal is to enhance end user experience by making AMD PCs smarter,
diff --git a/drivers/platform/x86/amd/pmf/Makefile b/drivers/platform/x86/amd/pmf/Makefile
index fdededf54392..6b26e48ce8ad 100644
--- a/drivers/platform/x86/amd/pmf/Makefile
+++ b/drivers/platform/x86/amd/pmf/Makefile
@@ -6,4 +6,5 @@
 
 obj-$(CONFIG_AMD_PMF) += amd-pmf.o
 amd-pmf-objs := core.o acpi.o sps.o \
-		auto-mode.o cnqf.o
+		auto-mode.o cnqf.o \
+		tee-if.o spc.o
diff --git a/drivers/platform/x86/amd/pmf/acpi.c b/drivers/platform/x86/amd/pmf/acpi.c
index 3fc5e4547d9f..f2eb07ef855a 100644
--- a/drivers/platform/x86/amd/pmf/acpi.c
+++ b/drivers/platform/x86/amd/pmf/acpi.c
@@ -111,7 +111,6 @@ int apmf_os_power_slider_update(struct amd_pmf_dev *pdev, u8 event)
 	struct os_power_slider args;
 	struct acpi_buffer params;
 	union acpi_object *info;
-	int err = 0;
 
 	args.size = sizeof(args);
 	args.slider_event = event;
@@ -121,10 +120,10 @@ int apmf_os_power_slider_update(struct amd_pmf_dev *pdev, u8 event)
 
 	info = apmf_if_call(pdev, APMF_FUNC_OS_POWER_SLIDER_UPDATE, &params);
 	if (!info)
-		err = -EIO;
+		return -EIO;
 
 	kfree(info);
-	return err;
+	return 0;
 }
 
 static void apmf_sbios_heartbeat_notify(struct work_struct *work)
@@ -135,11 +134,9 @@ static void apmf_sbios_heartbeat_notify(struct work_struct *work)
 	dev_dbg(dev->dev, "Sending heartbeat to SBIOS\n");
 	info = apmf_if_call(dev, APMF_FUNC_SBIOS_HEARTBEAT, NULL);
 	if (!info)
-		goto out;
+		return;
 
 	schedule_delayed_work(&dev->heart_beat, msecs_to_jiffies(dev->hb_interval * 1000));
-
-out:
 	kfree(info);
 }
 
@@ -148,7 +145,6 @@ int apmf_update_fan_idx(struct amd_pmf_dev *pdev, bool manual, u32 idx)
 	union acpi_object *info;
 	struct apmf_fan_idx args;
 	struct acpi_buffer params;
-	int err = 0;
 
 	args.size = sizeof(args);
 	args.fan_ctl_mode = manual;
@@ -158,14 +154,11 @@ int apmf_update_fan_idx(struct amd_pmf_dev *pdev, bool manual, u32 idx)
 	params.pointer = (void *)&args;
 
 	info = apmf_if_call(pdev, APMF_FUNC_SET_FAN_IDX, &params);
-	if (!info) {
-		err = -EIO;
-		goto out;
-	}
+	if (!info)
+		return -EIO;
 
-out:
 	kfree(info);
-	return err;
+	return 0;
 }
 
 int apmf_get_auto_mode_def(struct amd_pmf_dev *pdev, struct apmf_auto_mode *data)
@@ -286,6 +279,43 @@ int apmf_install_handler(struct amd_pmf_dev *pmf_dev)
 	return 0;
 }
 
+static acpi_status apmf_walk_resources(struct acpi_resource *res, void *data)
+{
+	struct amd_pmf_dev *dev = data;
+
+	switch (res->type) {
+	case ACPI_RESOURCE_TYPE_ADDRESS64:
+		dev->policy_addr = res->data.address64.address.minimum;
+		dev->policy_sz = res->data.address64.address.address_length;
+		break;
+	case ACPI_RESOURCE_TYPE_FIXED_MEMORY32:
+		dev->policy_addr = res->data.fixed_memory32.address;
+		dev->policy_sz = res->data.fixed_memory32.address_length;
+		break;
+	}
+
+	if (!dev->policy_addr || dev->policy_sz > POLICY_BUF_MAX_SZ || dev->policy_sz == 0) {
+		pr_err("Incorrect Policy params, possibly a SBIOS bug\n");
+		return AE_ERROR;
+	}
+
+	return AE_OK;
+}
+
+int apmf_check_smart_pc(struct amd_pmf_dev *pmf_dev)
+{
+	acpi_handle ahandle = ACPI_HANDLE(pmf_dev->dev);
+	acpi_status status;
+
+	status = acpi_walk_resources(ahandle, METHOD_NAME__CRS, apmf_walk_resources, pmf_dev);
+	if (ACPI_FAILURE(status)) {
+		dev_err(pmf_dev->dev, "acpi_walk_resources failed :%d\n", status);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 void apmf_acpi_deinit(struct amd_pmf_dev *pmf_dev)
 {
 	acpi_handle ahandle = ACPI_HANDLE(pmf_dev->dev);
diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c
index 78ed3ee22555..feaa09f5b35a 100644
--- a/drivers/platform/x86/amd/pmf/core.c
+++ b/drivers/platform/x86/amd/pmf/core.c
@@ -251,29 +251,37 @@ static const struct pci_device_id pmf_pci_ids[] = {
 	{ }
 };
 
-static void amd_pmf_set_dram_addr(struct amd_pmf_dev *dev)
+int amd_pmf_set_dram_addr(struct amd_pmf_dev *dev, bool alloc_buffer)
 {
 	u64 phys_addr;
 	u32 hi, low;
 
+	/* Get Metrics Table Address */
+	if (alloc_buffer) {
+		dev->buf = kzalloc(sizeof(dev->m_table), GFP_KERNEL);
+		if (!dev->buf)
+			return -ENOMEM;
+	}
+
 	phys_addr = virt_to_phys(dev->buf);
 	hi = phys_addr >> 32;
 	low = phys_addr & GENMASK(31, 0);
 
 	amd_pmf_send_cmd(dev, SET_DRAM_ADDR_HIGH, 0, hi, NULL);
 	amd_pmf_send_cmd(dev, SET_DRAM_ADDR_LOW, 0, low, NULL);
+
+	return 0;
 }
 
 int amd_pmf_init_metrics_table(struct amd_pmf_dev *dev)
 {
-	/* Get Metrics Table Address */
-	dev->buf = kzalloc(sizeof(dev->m_table), GFP_KERNEL);
-	if (!dev->buf)
-		return -ENOMEM;
+	int ret;
 
 	INIT_DELAYED_WORK(&dev->work_buffer, amd_pmf_get_metrics);
 
-	amd_pmf_set_dram_addr(dev);
+	ret = amd_pmf_set_dram_addr(dev, true);
+	if (ret)
+		return ret;
 
 	/*
 	 * Start collecting the metrics data after a small delay
@@ -284,17 +292,30 @@ int amd_pmf_init_metrics_table(struct amd_pmf_dev *dev)
 	return 0;
 }
 
+static int amd_pmf_suspend_handler(struct device *dev)
+{
+	struct amd_pmf_dev *pdev = dev_get_drvdata(dev);
+
+	kfree(pdev->buf);
+
+	return 0;
+}
+
 static int amd_pmf_resume_handler(struct device *dev)
 {
 	struct amd_pmf_dev *pdev = dev_get_drvdata(dev);
+	int ret;
 
-	if (pdev->buf)
-		amd_pmf_set_dram_addr(pdev);
+	if (pdev->buf) {
+		ret = amd_pmf_set_dram_addr(pdev, false);
+		if (ret)
+			return ret;
+	}
 
 	return 0;
 }
 
-static DEFINE_SIMPLE_DEV_PM_OPS(amd_pmf_pm, NULL, amd_pmf_resume_handler);
+static DEFINE_SIMPLE_DEV_PM_OPS(amd_pmf_pm, amd_pmf_suspend_handler, amd_pmf_resume_handler);
 
 static void amd_pmf_init_features(struct amd_pmf_dev *dev)
 {
@@ -309,13 +330,13 @@ static void amd_pmf_init_features(struct amd_pmf_dev *dev)
 		dev_dbg(dev->dev, "SPS enabled and Platform Profiles registered\n");
 	}
 
-	/* Enable Auto Mode */
-	if (is_apmf_func_supported(dev, APMF_FUNC_AUTO_MODE)) {
+	if (!amd_pmf_init_smart_pc(dev)) {
+		dev_dbg(dev->dev, "Smart PC Solution Enabled\n");
+	} else if (is_apmf_func_supported(dev, APMF_FUNC_AUTO_MODE)) {
 		amd_pmf_init_auto_mode(dev);
 		dev_dbg(dev->dev, "Auto Mode Init done\n");
 	} else if (is_apmf_func_supported(dev, APMF_FUNC_DYN_SLIDER_AC) ||
 			  is_apmf_func_supported(dev, APMF_FUNC_DYN_SLIDER_DC)) {
-		/* Enable Cool n Quiet Framework (CnQF) */
 		ret = amd_pmf_init_cnqf(dev);
 		if (ret)
 			dev_warn(dev->dev, "CnQF Init failed\n");
@@ -330,7 +351,9 @@ static void amd_pmf_deinit_features(struct amd_pmf_dev *dev)
 		amd_pmf_deinit_sps(dev);
 	}
 
-	if (is_apmf_func_supported(dev, APMF_FUNC_AUTO_MODE)) {
+	if (!dev->smart_pc_enabled) {
+		amd_pmf_deinit_smart_pc(dev);
+	} else if (is_apmf_func_supported(dev, APMF_FUNC_AUTO_MODE)) {
 		amd_pmf_deinit_auto_mode(dev);
 	} else if (is_apmf_func_supported(dev, APMF_FUNC_DYN_SLIDER_AC) ||
 			  is_apmf_func_supported(dev, APMF_FUNC_DYN_SLIDER_DC)) {
@@ -408,9 +431,9 @@ static int amd_pmf_probe(struct platform_device *pdev)
 
 	apmf_acpi_init(dev);
 	platform_set_drvdata(pdev, dev);
+	amd_pmf_dbgfs_register(dev);
 	amd_pmf_init_features(dev);
 	apmf_install_handler(dev);
-	amd_pmf_dbgfs_register(dev);
 
 	dev_info(dev->dev, "registered PMF device successfully\n");
 
@@ -448,3 +471,4 @@ module_platform_driver(amd_pmf_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("AMD Platform Management Framework Driver");
+MODULE_SOFTDEP("pre: amdtee");
diff --git a/drivers/platform/x86/amd/pmf/pmf.h b/drivers/platform/x86/amd/pmf/pmf.h
index deba88e6e4c8..16999c5b334f 100644
--- a/drivers/platform/x86/amd/pmf/pmf.h
+++ b/drivers/platform/x86/amd/pmf/pmf.h
@@ -14,6 +14,11 @@
 #include <linux/acpi.h>
 #include <linux/platform_profile.h>
 
+#define POLICY_BUF_MAX_SZ		0x4b000
+#define POLICY_SIGN_COOKIE		0x31535024
+#define POLICY_COOKIE_OFFSET		0x10
+#define POLICY_COOKIE_LEN		0x14
+
 /* APMF Functions */
 #define APMF_FUNC_VERIFY_INTERFACE			0
 #define APMF_FUNC_GET_SYS_PARAMS			1
@@ -44,6 +49,7 @@
 #define GET_STT_MIN_LIMIT	0x1F
 #define GET_STT_LIMIT_APU	0x20
 #define GET_STT_LIMIT_HS2	0x21
+#define SET_P3T				0x23 /* P3T: Peak Package Power Limit */
 
 /* OS slider update notification */
 #define DC_BEST_PERF		0
@@ -59,6 +65,24 @@
 #define ARG_NONE 0
 #define AVG_SAMPLE_SIZE 3
 
+/* Policy Actions */
+#define PMF_POLICY_SPL						2
+#define PMF_POLICY_SPPT						3
+#define PMF_POLICY_FPPT						4
+#define PMF_POLICY_SPPT_APU_ONLY				5
+#define PMF_POLICY_STT_MIN					6
+#define PMF_POLICY_STT_SKINTEMP_APU				7
+#define PMF_POLICY_STT_SKINTEMP_HS2				8
+#define PMF_POLICY_SYSTEM_STATE					9
+#define PMF_POLICY_P3T						38
+
+/* TA macros */
+#define PMF_TA_IF_VERSION_MAJOR				1
+#define TA_PMF_ACTION_MAX					32
+#define TA_PMF_UNDO_MAX						8
+#define TA_OUTPUT_RESERVED_MEM				906
+#define MAX_OPERATION_PARAMS					4
+
 /* AMD PMF BIOS interfaces */
 struct apmf_verify_interface {
 	u16 size;
@@ -129,6 +153,21 @@ struct smu_pmf_metrics {
 	u16 infra_gfx_maxfreq; /* in MHz */
 	u16 skin_temp; /* in centi-Celsius */
 	u16 device_state;
+	u16 curtemp; /* in centi-Celsius */
+	u16 filter_alpha_value;
+	u16 avg_gfx_clkfrequency;
+	u16 avg_fclk_frequency;
+	u16 avg_gfx_activity;
+	u16 avg_socclk_frequency;
+	u16 avg_vclk_frequency;
+	u16 avg_vcn_activity;
+	u16 avg_dram_reads;
+	u16 avg_dram_writes;
+	u16 avg_socket_power;
+	u16 avg_core_power[2];
+	u16 avg_core_c0residency[16];
+	u16 spare1;
+	u32 metrics_counter;
 } __packed;
 
 enum amd_stt_skin_temp {
@@ -179,6 +218,19 @@ struct amd_pmf_dev {
 	bool cnqf_enabled;
 	bool cnqf_supported;
 	struct notifier_block pwr_src_notifier;
+	/* Smart PC solution builder */
+	struct dentry *esbin;
+	unsigned char *policy_buf;
+	u32 policy_sz;
+	struct tee_context *tee_ctx;
+	struct tee_shm *fw_shm_pool;
+	u32 session_id;
+	void *shbuf;
+	struct delayed_work pb_work;
+	struct pmf_action_table *prev_data;
+	u64 policy_addr;
+	void *policy_base;
+	bool smart_pc_enabled;
 };
 
 struct apmf_sps_prop_granular {
@@ -389,6 +441,145 @@ struct apmf_dyn_slider_output {
 	struct apmf_cnqf_power_set ps[APMF_CNQF_MAX];
 } __packed;
 
+enum smart_pc_status {
+	PMF_SMART_PC_ENABLED,
+	PMF_SMART_PC_DISABLED,
+};
+
+/* Smart PC - TA internals */
+enum system_state {
+	SYSTEM_STATE_S0i3,
+	SYSTEM_STATE_S4,
+	SYSTEM_STATE_SCREEN_LOCK,
+	SYSTEM_STATE_MAX,
+};
+
+enum ta_slider {
+	TA_BEST_BATTERY,
+	TA_BETTER_BATTERY,
+	TA_BETTER_PERFORMANCE,
+	TA_BEST_PERFORMANCE,
+	TA_MAX,
+};
+
+/* Command ids for TA communication */
+enum ta_pmf_command {
+	TA_PMF_COMMAND_POLICY_BUILDER_INITIALIZE,
+	TA_PMF_COMMAND_POLICY_BUILDER_ENACT_POLICIES,
+};
+
+enum ta_pmf_error_type {
+	TA_PMF_TYPE_SUCCESS,
+	TA_PMF_ERROR_TYPE_GENERIC,
+	TA_PMF_ERROR_TYPE_CRYPTO,
+	TA_PMF_ERROR_TYPE_CRYPTO_VALIDATE,
+	TA_PMF_ERROR_TYPE_CRYPTO_VERIFY_OEM,
+	TA_PMF_ERROR_TYPE_POLICY_BUILDER,
+	TA_PMF_ERROR_TYPE_PB_CONVERT,
+	TA_PMF_ERROR_TYPE_PB_SETUP,
+	TA_PMF_ERROR_TYPE_PB_ENACT,
+	TA_PMF_ERROR_TYPE_ASD_GET_DEVICE_INFO,
+	TA_PMF_ERROR_TYPE_ASD_GET_DEVICE_PCIE_INFO,
+	TA_PMF_ERROR_TYPE_SYS_DRV_FW_VALIDATION,
+	TA_PMF_ERROR_TYPE_MAX,
+};
+
+struct pmf_action_table {
+	enum system_state system_state;
+	u32 spl;		/* in mW */
+	u32 sppt;		/* in mW */
+	u32 sppt_apuonly;	/* in mW */
+	u32 fppt;		/* in mW */
+	u32 stt_minlimit;	/* in mW */
+	u32 stt_skintemp_apu;	/* in C */
+	u32 stt_skintemp_hs2;	/* in C */
+	u32 p3t_limit;		/* in mW */
+};
+
+/* Input conditions */
+struct ta_pmf_condition_info {
+	u32 power_source;
+	u32 bat_percentage;
+	u32 power_slider;
+	u32 lid_state;
+	bool user_present;
+	u32 rsvd1[2];
+	u32 monitor_count;
+	u32 rsvd2[2];
+	u32 bat_design;
+	u32 full_charge_capacity;
+	int drain_rate;
+	bool user_engaged;
+	u32 device_state;
+	u32 socket_power;
+	u32 skin_temperature;
+	u32 rsvd3[5];
+	u32 ambient_light;
+	u32 length;
+	u32 avg_c0residency;
+	u32 max_c0residency;
+	u32 s0i3_entry;
+	u32 gfx_busy;
+	u32 rsvd4[7];
+	bool camera_state;
+	u32 workload_type;
+	u32 display_type;
+	u32 display_state;
+	u32 rsvd5[150];
+};
+
+struct ta_pmf_load_policy_table {
+	u32 table_size;
+	u8 table[POLICY_BUF_MAX_SZ];
+};
+
+/* TA initialization params */
+struct ta_pmf_init_table {
+	u32 frequency; /* SMU sampling frequency */
+	bool validate;
+	bool sku_check;
+	bool metadata_macrocheck;
+	struct ta_pmf_load_policy_table policies_table;
+};
+
+/* Everything the TA needs to Enact Policies */
+struct ta_pmf_enact_table {
+	struct ta_pmf_condition_info ev_info;
+	u32 name;
+};
+
+struct ta_pmf_action {
+	u32 action_index;
+	u32 value;
+};
+
+/* Output actions from TA */
+struct ta_pmf_enact_result {
+	u32 actions_count;
+	struct ta_pmf_action actions_list[TA_PMF_ACTION_MAX];
+	u32 undo_count;
+	struct ta_pmf_action undo_list[TA_PMF_UNDO_MAX];
+};
+
+union ta_pmf_input {
+	struct ta_pmf_enact_table enact_table;
+	struct ta_pmf_init_table init_table;
+};
+
+union ta_pmf_output {
+	struct ta_pmf_enact_result policy_apply_table;
+	u32 rsvd[TA_OUTPUT_RESERVED_MEM];
+};
+
+struct ta_pmf_shared_memory {
+	int command_id;
+	int resp_id;
+	u32 pmf_result;
+	u32 if_version;
+	union ta_pmf_output pmf_output;
+	union ta_pmf_input pmf_input;
+};
+
 /* Core Layer */
 int apmf_acpi_init(struct amd_pmf_dev *pmf_dev);
 void apmf_acpi_deinit(struct amd_pmf_dev *pmf_dev);
@@ -398,6 +589,7 @@ int amd_pmf_init_metrics_table(struct amd_pmf_dev *dev);
 int amd_pmf_get_power_source(void);
 int apmf_install_handler(struct amd_pmf_dev *pmf_dev);
 int apmf_os_power_slider_update(struct amd_pmf_dev *dev, u8 flag);
+int amd_pmf_set_dram_addr(struct amd_pmf_dev *dev, bool alloc_buffer);
 
 /* SPS Layer */
 int amd_pmf_get_pprof_modes(struct amd_pmf_dev *pmf);
@@ -409,7 +601,9 @@ int apmf_get_static_slider_granular(struct amd_pmf_dev *pdev,
 				    struct apmf_static_slider_granular_output *output);
 bool is_pprof_balanced(struct amd_pmf_dev *pmf);
 int amd_pmf_power_slider_update_event(struct amd_pmf_dev *dev);
+const char *amd_pmf_source_as_str(unsigned int state);
 
+const char *amd_pmf_source_as_str(unsigned int state);
 
 int apmf_update_fan_idx(struct amd_pmf_dev *pdev, bool manual, u32 idx);
 int amd_pmf_set_sps_power_limits(struct amd_pmf_dev *pmf);
@@ -433,4 +627,13 @@ void amd_pmf_deinit_cnqf(struct amd_pmf_dev *dev);
 int amd_pmf_trans_cnqf(struct amd_pmf_dev *dev, int socket_power, ktime_t time_lapsed_ms);
 extern const struct attribute_group cnqf_feature_attribute_group;
 
+/* Smart PC builder Layer */
+int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev);
+void amd_pmf_deinit_smart_pc(struct amd_pmf_dev *dev);
+int apmf_check_smart_pc(struct amd_pmf_dev *pmf_dev);
+
+/* Smart PC - TA interfaces */
+void amd_pmf_populate_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in);
+void amd_pmf_dump_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in);
+
 #endif /* PMF_H */
diff --git a/drivers/platform/x86/amd/pmf/spc.c b/drivers/platform/x86/amd/pmf/spc.c
new file mode 100644
index 000000000000..a0423942f771
--- /dev/null
+++ b/drivers/platform/x86/amd/pmf/spc.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * AMD Platform Management Framework Driver - Smart PC Capabilities
+ *
+ * Copyright (c) 2023, Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Authors: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
+ *          Patil Rajesh Reddy <Patil.Reddy@amd.com>
+ */
+
+#include <acpi/button.h>
+#include <linux/power_supply.h>
+#include <linux/units.h>
+#include "pmf.h"
+
+#ifdef CONFIG_AMD_PMF_DEBUG
+static const char *ta_slider_as_str(unsigned int state)
+{
+	switch (state) {
+	case TA_BEST_PERFORMANCE:
+		return "PERFORMANCE";
+	case TA_BETTER_PERFORMANCE:
+		return "BALANCED";
+	case TA_BEST_BATTERY:
+		return "POWER_SAVER";
+	default:
+		return "Unknown TA Slider State";
+	}
+}
+
+void amd_pmf_dump_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in)
+{
+	dev_dbg(dev->dev, "==== TA inputs START ====\n");
+	dev_dbg(dev->dev, "Slider State: %s\n", ta_slider_as_str(in->ev_info.power_slider));
+	dev_dbg(dev->dev, "Power Source: %s\n", amd_pmf_source_as_str(in->ev_info.power_source));
+	dev_dbg(dev->dev, "Battery Percentage: %u\n", in->ev_info.bat_percentage);
+	dev_dbg(dev->dev, "Designed Battery Capacity: %u\n", in->ev_info.bat_design);
+	dev_dbg(dev->dev, "Fully Charged Capacity: %u\n", in->ev_info.full_charge_capacity);
+	dev_dbg(dev->dev, "Drain Rate: %d\n", in->ev_info.drain_rate);
+	dev_dbg(dev->dev, "Socket Power: %u\n", in->ev_info.socket_power);
+	dev_dbg(dev->dev, "Skin Temperature: %u\n", in->ev_info.skin_temperature);
+	dev_dbg(dev->dev, "Avg C0 Residency: %u\n", in->ev_info.avg_c0residency);
+	dev_dbg(dev->dev, "Max C0 Residency: %u\n", in->ev_info.max_c0residency);
+	dev_dbg(dev->dev, "GFX Busy: %u\n", in->ev_info.gfx_busy);
+	dev_dbg(dev->dev, "LID State: %s\n", in->ev_info.lid_state ? "close" : "open");
+	dev_dbg(dev->dev, "==== TA inputs END ====\n");
+}
+#else
+void amd_pmf_dump_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in) {}
+#endif
+
+static void amd_pmf_get_smu_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in)
+{
+	u16 max, avg = 0;
+	int i;
+
+	memset(dev->buf, 0, sizeof(dev->m_table));
+	amd_pmf_send_cmd(dev, SET_TRANSFER_TABLE, 0, 7, NULL);
+	memcpy(&dev->m_table, dev->buf, sizeof(dev->m_table));
+
+	in->ev_info.socket_power = dev->m_table.apu_power + dev->m_table.dgpu_power;
+	in->ev_info.skin_temperature = dev->m_table.skin_temp;
+
+	/* Get the avg and max C0 residency of all the cores */
+	max = dev->m_table.avg_core_c0residency[0];
+	for (i = 0; i < ARRAY_SIZE(dev->m_table.avg_core_c0residency); i++) {
+		avg += dev->m_table.avg_core_c0residency[i];
+		if (dev->m_table.avg_core_c0residency[i] > max)
+			max = dev->m_table.avg_core_c0residency[i];
+	}
+
+	avg = DIV_ROUND_CLOSEST(avg, ARRAY_SIZE(dev->m_table.avg_core_c0residency));
+	in->ev_info.avg_c0residency = avg;
+	in->ev_info.max_c0residency = max;
+	in->ev_info.gfx_busy = dev->m_table.avg_gfx_activity;
+}
+
+static const char * const pmf_battery_supply_name[] = {
+	"BATT",
+	"BAT0",
+};
+
+static int amd_pmf_get_battery_prop(enum power_supply_property prop)
+{
+	union power_supply_propval value;
+	struct power_supply *psy;
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(pmf_battery_supply_name); i++) {
+		psy = power_supply_get_by_name(pmf_battery_supply_name[i]);
+		if (!psy)
+			continue;
+
+		ret = power_supply_get_property(psy, prop, &value);
+		if (ret) {
+			power_supply_put(psy);
+			return ret;
+		}
+	}
+
+	return value.intval;
+}
+
+static int amd_pmf_get_battery_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in)
+{
+	int val;
+
+	val = amd_pmf_get_battery_prop(POWER_SUPPLY_PROP_PRESENT);
+	if (val < 0)
+		return val;
+	if (val != 1)
+		return -ENODEV;
+
+	in->ev_info.bat_percentage = amd_pmf_get_battery_prop(POWER_SUPPLY_PROP_CAPACITY);
+	/* all values in mWh metrics */
+	in->ev_info.bat_design = amd_pmf_get_battery_prop(POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN) /
+		MILLIWATT_PER_WATT;
+	in->ev_info.full_charge_capacity = amd_pmf_get_battery_prop(POWER_SUPPLY_PROP_ENERGY_FULL) /
+		MILLIWATT_PER_WATT;
+	in->ev_info.drain_rate = amd_pmf_get_battery_prop(POWER_SUPPLY_PROP_POWER_NOW) /
+		MILLIWATT_PER_WATT;
+
+	return 0;
+}
+
+static int amd_pmf_get_slider_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in)
+{
+	int val;
+
+	switch (dev->current_profile) {
+	case PLATFORM_PROFILE_PERFORMANCE:
+		val = TA_BEST_PERFORMANCE;
+		break;
+	case PLATFORM_PROFILE_BALANCED:
+		val = TA_BETTER_PERFORMANCE;
+		break;
+	case PLATFORM_PROFILE_LOW_POWER:
+		val = TA_BEST_BATTERY;
+		break;
+	default:
+		dev_err(dev->dev, "Unknown Platform Profile.\n");
+		return -EOPNOTSUPP;
+	}
+	in->ev_info.power_slider = val;
+
+	return 0;
+}
+
+void amd_pmf_populate_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in)
+{
+	/* TA side lid open is 1 and close is 0, hence the ! here */
+	in->ev_info.lid_state = !acpi_lid_open();
+	in->ev_info.power_source = amd_pmf_get_power_source();
+	amd_pmf_get_smu_info(dev, in);
+	amd_pmf_get_battery_info(dev, in);
+	amd_pmf_get_slider_info(dev, in);
+}
diff --git a/drivers/platform/x86/amd/pmf/sps.c b/drivers/platform/x86/amd/pmf/sps.c
index a70e67749be3..33e23e25c8b1 100644
--- a/drivers/platform/x86/amd/pmf/sps.c
+++ b/drivers/platform/x86/amd/pmf/sps.c
@@ -27,7 +27,7 @@ static const char *slider_as_str(unsigned int state)
 	}
 }
 
-static const char *source_as_str(unsigned int state)
+const char *amd_pmf_source_as_str(unsigned int state)
 {
 	switch (state) {
 	case POWER_SOURCE_AC:
@@ -47,7 +47,8 @@ static void amd_pmf_dump_sps_defaults(struct amd_pmf_static_slider_granular *dat
 
 	for (i = 0; i < POWER_SOURCE_MAX; i++) {
 		for (j = 0; j < POWER_MODE_MAX; j++) {
-			pr_debug("--- Source:%s Mode:%s ---\n", source_as_str(i), slider_as_str(j));
+			pr_debug("--- Source:%s Mode:%s ---\n", amd_pmf_source_as_str(i),
+				 slider_as_str(j));
 			pr_debug("SPL: %u mW\n", data->prop[i][j].spl);
 			pr_debug("SPPT: %u mW\n", data->prop[i][j].sppt);
 			pr_debug("SPPT_ApuOnly: %u mW\n", data->prop[i][j].sppt_apu_only);
diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c
new file mode 100644
index 000000000000..502ce93d5cdd
--- /dev/null
+++ b/drivers/platform/x86/amd/pmf/tee-if.c
@@ -0,0 +1,472 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * AMD Platform Management Framework Driver - TEE Interface
+ *
+ * Copyright (c) 2023, Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Author: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
+ */
+
+#include <linux/debugfs.h>
+#include <linux/tee_drv.h>
+#include <linux/uuid.h>
+#include "pmf.h"
+
+#define MAX_TEE_PARAM	4
+
+/* Policy binary actions sampling frequency (in ms) */
+static int pb_actions_ms = MSEC_PER_SEC;
+/* Sideload policy binaries to debug policy failures */
+static bool pb_side_load;
+
+#ifdef CONFIG_AMD_PMF_DEBUG
+module_param(pb_actions_ms, int, 0644);
+MODULE_PARM_DESC(pb_actions_ms, "Policy binary actions sampling frequency (default = 1000ms)");
+module_param(pb_side_load, bool, 0444);
+MODULE_PARM_DESC(pb_side_load, "Sideload policy binaries debug policy failures");
+#endif
+
+static const uuid_t amd_pmf_ta_uuid = UUID_INIT(0x6fd93b77, 0x3fb8, 0x524d,
+						0xb1, 0x2d, 0xc5, 0x29, 0xb1, 0x3d, 0x85, 0x43);
+
+static const char *amd_pmf_uevent_as_str(unsigned int state)
+{
+	switch (state) {
+	case SYSTEM_STATE_S0i3:
+		return "S0i3";
+	case SYSTEM_STATE_S4:
+		return "S4";
+	case SYSTEM_STATE_SCREEN_LOCK:
+		return "SCREEN_LOCK";
+	default:
+		return "Unknown Smart PC event";
+	}
+}
+
+static void amd_pmf_prepare_args(struct amd_pmf_dev *dev, int cmd,
+				 struct tee_ioctl_invoke_arg *arg,
+				 struct tee_param *param)
+{
+	memset(arg, 0, sizeof(*arg));
+	memset(param, 0, MAX_TEE_PARAM * sizeof(*param));
+
+	arg->func = cmd;
+	arg->session = dev->session_id;
+	arg->num_params = MAX_TEE_PARAM;
+
+	/* Fill invoke cmd params */
+	param[0].u.memref.size = sizeof(struct ta_pmf_shared_memory);
+	param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT;
+	param[0].u.memref.shm = dev->fw_shm_pool;
+	param[0].u.memref.shm_offs = 0;
+}
+
+static int amd_pmf_update_uevents(struct amd_pmf_dev *dev, u16 event)
+{
+	char *envp[2] = {};
+
+	envp[0] = kasprintf(GFP_KERNEL, "EVENT_ID=%d", event);
+	if (!envp[0])
+		return -EINVAL;
+
+	kobject_uevent_env(&dev->dev->kobj, KOBJ_CHANGE, envp);
+
+	kfree(envp[0]);
+	return 0;
+}
+
+static void amd_pmf_apply_policies(struct amd_pmf_dev *dev, struct ta_pmf_enact_result *out)
+{
+	u32 val;
+	int idx;
+
+	for (idx = 0; idx < out->actions_count; idx++) {
+		val = out->actions_list[idx].value;
+		switch (out->actions_list[idx].action_index) {
+		case PMF_POLICY_SPL:
+			if (dev->prev_data->spl != val) {
+				amd_pmf_send_cmd(dev, SET_SPL, false, val, NULL);
+				dev_dbg(dev->dev, "update SPL: %u\n", val);
+				dev->prev_data->spl = val;
+			}
+			break;
+
+		case PMF_POLICY_SPPT:
+			if (dev->prev_data->sppt != val) {
+				amd_pmf_send_cmd(dev, SET_SPPT, false, val, NULL);
+				dev_dbg(dev->dev, "update SPPT: %u\n", val);
+				dev->prev_data->sppt = val;
+			}
+			break;
+
+		case PMF_POLICY_FPPT:
+			if (dev->prev_data->fppt != val) {
+				amd_pmf_send_cmd(dev, SET_FPPT, false, val, NULL);
+				dev_dbg(dev->dev, "update FPPT: %u\n", val);
+				dev->prev_data->fppt = val;
+			}
+			break;
+
+		case PMF_POLICY_SPPT_APU_ONLY:
+			if (dev->prev_data->sppt_apuonly != val) {
+				amd_pmf_send_cmd(dev, SET_SPPT_APU_ONLY, false, val, NULL);
+				dev_dbg(dev->dev, "update SPPT_APU_ONLY: %u\n", val);
+				dev->prev_data->sppt_apuonly = val;
+			}
+			break;
+
+		case PMF_POLICY_STT_MIN:
+			if (dev->prev_data->stt_minlimit != val) {
+				amd_pmf_send_cmd(dev, SET_STT_MIN_LIMIT, false, val, NULL);
+				dev_dbg(dev->dev, "update STT_MIN: %u\n", val);
+				dev->prev_data->stt_minlimit = val;
+			}
+			break;
+
+		case PMF_POLICY_STT_SKINTEMP_APU:
+			if (dev->prev_data->stt_skintemp_apu != val) {
+				amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false, val, NULL);
+				dev_dbg(dev->dev, "update STT_SKINTEMP_APU: %u\n", val);
+				dev->prev_data->stt_skintemp_apu = val;
+			}
+			break;
+
+		case PMF_POLICY_STT_SKINTEMP_HS2:
+			if (dev->prev_data->stt_skintemp_hs2 != val) {
+				amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false, val, NULL);
+				dev_dbg(dev->dev, "update STT_SKINTEMP_HS2: %u\n", val);
+				dev->prev_data->stt_skintemp_hs2 = val;
+			}
+			break;
+
+		case PMF_POLICY_P3T:
+			if (dev->prev_data->p3t_limit != val) {
+				amd_pmf_send_cmd(dev, SET_P3T, false, val, NULL);
+				dev_dbg(dev->dev, "update P3T: %u\n", val);
+				dev->prev_data->p3t_limit = val;
+			}
+			break;
+
+		case PMF_POLICY_SYSTEM_STATE:
+			amd_pmf_update_uevents(dev, val);
+			dev_dbg(dev->dev, "update SYSTEM_STATE: %s\n",
+				amd_pmf_uevent_as_str(val));
+			break;
+		}
+	}
+}
+
+static int amd_pmf_invoke_cmd_enact(struct amd_pmf_dev *dev)
+{
+	struct ta_pmf_shared_memory *ta_sm = NULL;
+	struct ta_pmf_enact_result *out = NULL;
+	struct ta_pmf_enact_table *in = NULL;
+	struct tee_param param[MAX_TEE_PARAM];
+	struct tee_ioctl_invoke_arg arg;
+	int ret = 0;
+
+	if (!dev->tee_ctx)
+		return -ENODEV;
+
+	memset(dev->shbuf, 0, dev->policy_sz);
+	ta_sm = dev->shbuf;
+	out = &ta_sm->pmf_output.policy_apply_table;
+	in = &ta_sm->pmf_input.enact_table;
+
+	memset(ta_sm, 0, sizeof(*ta_sm));
+	ta_sm->command_id = TA_PMF_COMMAND_POLICY_BUILDER_ENACT_POLICIES;
+	ta_sm->if_version = PMF_TA_IF_VERSION_MAJOR;
+
+	amd_pmf_populate_ta_inputs(dev, in);
+	amd_pmf_prepare_args(dev, TA_PMF_COMMAND_POLICY_BUILDER_ENACT_POLICIES, &arg, param);
+
+	ret = tee_client_invoke_func(dev->tee_ctx, &arg, param);
+	if (ret < 0 || arg.ret != 0) {
+		dev_err(dev->dev, "TEE enact cmd failed. err: %x, ret:%d\n", arg.ret, ret);
+		return ret;
+	}
+
+	if (ta_sm->pmf_result == TA_PMF_TYPE_SUCCESS && out->actions_count) {
+		amd_pmf_dump_ta_inputs(dev, in);
+		dev_dbg(dev->dev, "action count:%u result:%x\n", out->actions_count,
+			ta_sm->pmf_result);
+		amd_pmf_apply_policies(dev, out);
+	}
+
+	return 0;
+}
+
+static int amd_pmf_invoke_cmd_init(struct amd_pmf_dev *dev)
+{
+	struct ta_pmf_shared_memory *ta_sm = NULL;
+	struct tee_param param[MAX_TEE_PARAM];
+	struct ta_pmf_init_table *in = NULL;
+	struct tee_ioctl_invoke_arg arg;
+	int ret = 0;
+
+	if (!dev->tee_ctx) {
+		dev_err(dev->dev, "Failed to get TEE context\n");
+		return -ENODEV;
+	}
+
+	dev_dbg(dev->dev, "Policy Binary size: %u bytes\n", dev->policy_sz);
+	memset(dev->shbuf, 0, dev->policy_sz);
+	ta_sm = dev->shbuf;
+	in = &ta_sm->pmf_input.init_table;
+
+	ta_sm->command_id = TA_PMF_COMMAND_POLICY_BUILDER_INITIALIZE;
+	ta_sm->if_version = PMF_TA_IF_VERSION_MAJOR;
+
+	in->metadata_macrocheck = false;
+	in->sku_check = false;
+	in->validate = true;
+	in->frequency = pb_actions_ms;
+	in->policies_table.table_size = dev->policy_sz;
+
+	memcpy(in->policies_table.table, dev->policy_buf, dev->policy_sz);
+	amd_pmf_prepare_args(dev, TA_PMF_COMMAND_POLICY_BUILDER_INITIALIZE, &arg, param);
+
+	ret = tee_client_invoke_func(dev->tee_ctx, &arg, param);
+	if (ret < 0 || arg.ret != 0) {
+		dev_err(dev->dev, "Failed to invoke TEE init cmd. err: %x, ret:%d\n", arg.ret, ret);
+		return ret;
+	}
+
+	return ta_sm->pmf_result;
+}
+
+static void amd_pmf_invoke_cmd(struct work_struct *work)
+{
+	struct amd_pmf_dev *dev = container_of(work, struct amd_pmf_dev, pb_work.work);
+
+	amd_pmf_invoke_cmd_enact(dev);
+	schedule_delayed_work(&dev->pb_work, msecs_to_jiffies(pb_actions_ms));
+}
+
+static int amd_pmf_start_policy_engine(struct amd_pmf_dev *dev)
+{
+	u32 cookie, length;
+	int res;
+
+	cookie = readl(dev->policy_buf + POLICY_COOKIE_OFFSET);
+	length = readl(dev->policy_buf + POLICY_COOKIE_LEN);
+
+	if (cookie != POLICY_SIGN_COOKIE || !length)
+		return -EINVAL;
+
+	/* Update the actual length */
+	dev->policy_sz = length + 512;
+	res = amd_pmf_invoke_cmd_init(dev);
+	if (res == TA_PMF_TYPE_SUCCESS) {
+		/* Now its safe to announce that smart pc is enabled */
+		dev->smart_pc_enabled = PMF_SMART_PC_ENABLED;
+		/*
+		 * Start collecting the data from TA FW after a small delay
+		 * or else, we might end up getting stale values.
+		 */
+		schedule_delayed_work(&dev->pb_work, msecs_to_jiffies(pb_actions_ms * 3));
+	} else {
+		dev_err(dev->dev, "ta invoke cmd init failed err: %x\n", res);
+		dev->smart_pc_enabled = PMF_SMART_PC_DISABLED;
+		return res;
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_AMD_PMF_DEBUG
+static void amd_pmf_hex_dump_pb(struct amd_pmf_dev *dev)
+{
+	print_hex_dump_debug("(pb):  ", DUMP_PREFIX_OFFSET, 16, 1, dev->policy_buf,
+			     dev->policy_sz, false);
+}
+
+static ssize_t amd_pmf_get_pb_data(struct file *filp, const char __user *buf,
+				   size_t length, loff_t *pos)
+{
+	struct amd_pmf_dev *dev = filp->private_data;
+	unsigned char *new_policy_buf;
+	int ret;
+
+	/* Policy binary size cannot exceed POLICY_BUF_MAX_SZ */
+	if (length > POLICY_BUF_MAX_SZ || length == 0)
+		return -EINVAL;
+
+	/* re-alloc to the new buffer length of the policy binary */
+	new_policy_buf = kzalloc(length, GFP_KERNEL);
+	if (!new_policy_buf)
+		return -ENOMEM;
+
+	if (copy_from_user(new_policy_buf, buf, length))
+		return -EFAULT;
+
+	kfree(dev->policy_buf);
+	dev->policy_buf = new_policy_buf;
+	dev->policy_sz = length;
+
+	amd_pmf_hex_dump_pb(dev);
+	ret = amd_pmf_start_policy_engine(dev);
+	if (ret)
+		return -EINVAL;
+
+	return length;
+}
+
+static const struct file_operations pb_fops = {
+	.write = amd_pmf_get_pb_data,
+	.open = simple_open,
+};
+
+static void amd_pmf_open_pb(struct amd_pmf_dev *dev, struct dentry *debugfs_root)
+{
+	dev->esbin = debugfs_create_dir("pb", debugfs_root);
+	debugfs_create_file("update_policy", 0644, dev->esbin, dev, &pb_fops);
+}
+
+static void amd_pmf_remove_pb(struct amd_pmf_dev *dev)
+{
+	debugfs_remove_recursive(dev->esbin);
+}
+#else
+static void amd_pmf_open_pb(struct amd_pmf_dev *dev, struct dentry *debugfs_root) {}
+static void amd_pmf_remove_pb(struct amd_pmf_dev *dev) {}
+static void amd_pmf_hex_dump_pb(struct amd_pmf_dev *dev) {}
+#endif
+
+static int amd_pmf_get_bios_buffer(struct amd_pmf_dev *dev)
+{
+	dev->policy_buf = kzalloc(dev->policy_sz, GFP_KERNEL);
+	if (!dev->policy_buf)
+		return -ENOMEM;
+
+	dev->policy_base = devm_ioremap(dev->dev, dev->policy_addr, dev->policy_sz);
+	if (!dev->policy_base)
+		return -ENOMEM;
+
+	memcpy(dev->policy_buf, dev->policy_base, dev->policy_sz);
+
+	amd_pmf_hex_dump_pb(dev);
+	if (pb_side_load)
+		amd_pmf_open_pb(dev, dev->dbgfs_dir);
+
+	return amd_pmf_start_policy_engine(dev);
+}
+
+static int amd_pmf_amdtee_ta_match(struct tee_ioctl_version_data *ver, const void *data)
+{
+	return ver->impl_id == TEE_IMPL_ID_AMDTEE;
+}
+
+static int amd_pmf_ta_open_session(struct tee_context *ctx, u32 *id)
+{
+	struct tee_ioctl_open_session_arg sess_arg = {};
+	int rc;
+
+	export_uuid(sess_arg.uuid, &amd_pmf_ta_uuid);
+	sess_arg.clnt_login = TEE_IOCTL_LOGIN_PUBLIC;
+	sess_arg.num_params = 0;
+
+	rc = tee_client_open_session(ctx, &sess_arg, NULL);
+	if (rc < 0 || sess_arg.ret != 0) {
+		pr_err("Failed to open TEE session err:%#x, rc:%d\n", sess_arg.ret, rc);
+		return rc;
+	}
+
+	*id = sess_arg.session;
+
+	return rc;
+}
+
+static int amd_pmf_tee_init(struct amd_pmf_dev *dev)
+{
+	u32 size;
+	int ret;
+
+	dev->tee_ctx = tee_client_open_context(NULL, amd_pmf_amdtee_ta_match, NULL, NULL);
+	if (IS_ERR(dev->tee_ctx)) {
+		dev_err(dev->dev, "Failed to open TEE context\n");
+		return PTR_ERR(dev->tee_ctx);
+	}
+
+	ret = amd_pmf_ta_open_session(dev->tee_ctx, &dev->session_id);
+	if (ret) {
+		dev_err(dev->dev, "Failed to open TA session (%d)\n", ret);
+		ret = -EINVAL;
+		goto out_ctx;
+	}
+
+	size = sizeof(struct ta_pmf_shared_memory) + dev->policy_sz;
+	dev->fw_shm_pool = tee_shm_alloc_kernel_buf(dev->tee_ctx, size);
+	if (IS_ERR(dev->fw_shm_pool)) {
+		dev_err(dev->dev, "Failed to alloc TEE shared memory\n");
+		ret = PTR_ERR(dev->fw_shm_pool);
+		goto out_sess;
+	}
+
+	dev->shbuf = tee_shm_get_va(dev->fw_shm_pool, 0);
+	if (IS_ERR(dev->shbuf)) {
+		dev_err(dev->dev, "Failed to get TEE virtual address\n");
+		ret = PTR_ERR(dev->shbuf);
+		goto out_shm;
+	}
+	dev_dbg(dev->dev, "TEE init done\n");
+
+	return 0;
+
+out_shm:
+	tee_shm_free(dev->fw_shm_pool);
+out_sess:
+	tee_client_close_session(dev->tee_ctx, dev->session_id);
+out_ctx:
+	tee_client_close_context(dev->tee_ctx);
+
+	return ret;
+}
+
+static void amd_pmf_tee_deinit(struct amd_pmf_dev *dev)
+{
+	tee_shm_free(dev->fw_shm_pool);
+	tee_client_close_session(dev->tee_ctx, dev->session_id);
+	tee_client_close_context(dev->tee_ctx);
+}
+
+int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
+{
+	int ret;
+
+	ret = apmf_check_smart_pc(dev);
+	if (ret) {
+		/*
+		 * Lets not return from here if Smart PC bit is not advertised in
+		 * the BIOS. This way, there will be some amount of power savings
+		 * to the user with static slider (if enabled).
+		 */
+		dev_info(dev->dev, "PMF Smart PC not advertised in BIOS!:%d\n", ret);
+		return -ENODEV;
+	}
+
+	ret = amd_pmf_tee_init(dev);
+	if (ret)
+		return ret;
+
+	INIT_DELAYED_WORK(&dev->pb_work, amd_pmf_invoke_cmd);
+	amd_pmf_set_dram_addr(dev, true);
+	amd_pmf_get_bios_buffer(dev);
+	dev->prev_data = kzalloc(sizeof(*dev->prev_data), GFP_KERNEL);
+	if (!dev->prev_data)
+		return -ENOMEM;
+
+	return dev->smart_pc_enabled;
+}
+
+void amd_pmf_deinit_smart_pc(struct amd_pmf_dev *dev)
+{
+	if (pb_side_load)
+		amd_pmf_remove_pb(dev);
+
+	kfree(dev->prev_data);
+	kfree(dev->policy_buf);
+	cancel_delayed_work_sync(&dev->pb_work);
+	amd_pmf_tee_deinit(dev);
+}
diff --git a/drivers/platform/x86/amd/wbrf.c b/drivers/platform/x86/amd/wbrf.c
new file mode 100644
index 000000000000..dd197b3aebe0
--- /dev/null
+++ b/drivers/platform/x86/amd/wbrf.c
@@ -0,0 +1,317 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Wifi Frequency Band Manage Interface
+ * Copyright (C) 2023 Advanced Micro Devices
+ */
+
+#include <linux/acpi.h>
+#include <linux/acpi_amd_wbrf.h>
+
+/*
+ * Functions bit vector for WBRF method
+ *
+ * Bit 0: WBRF supported.
+ * Bit 1: Function 1 (Add / Remove frequency) is supported.
+ * Bit 2: Function 2 (Get frequency list) is supported.
+ */
+#define WBRF_ENABLED		0x0
+#define WBRF_RECORD			0x1
+#define WBRF_RETRIEVE		0x2
+
+#define WBRF_REVISION		0x1
+
+/*
+ * The data structure used for WBRF_RETRIEVE is not naturally aligned.
+ * And unfortunately the design has been settled down.
+ */
+struct amd_wbrf_ranges_out {
+	u32			num_of_ranges;
+	struct freq_band_range	band_list[MAX_NUM_OF_WBRF_RANGES];
+} __packed;
+
+static const guid_t wifi_acpi_dsm_guid =
+	GUID_INIT(0x7b7656cf, 0xdc3d, 0x4c1c,
+		  0x83, 0xe9, 0x66, 0xe7, 0x21, 0xde, 0x30, 0x70);
+
+/*
+ * Used to notify consumer (amdgpu driver currently) about
+ * the wifi frequency is change.
+ */
+static BLOCKING_NOTIFIER_HEAD(wbrf_chain_head);
+
+static int wbrf_record(struct acpi_device *adev, uint8_t action, struct wbrf_ranges_in_out *in)
+{
+	union acpi_object argv4;
+	union acpi_object *tmp;
+	union acpi_object *obj;
+	u32 num_of_ranges = 0;
+	u32 num_of_elements;
+	u32 arg_idx = 0;
+	int ret;
+	u32 i;
+
+	if (!in)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(in->band_list); i++) {
+		if (in->band_list[i].start && in->band_list[i].end)
+			num_of_ranges++;
+	}
+
+	/*
+	 * The num_of_ranges value in the "in" object supplied by
+	 * the caller is required to be equal to the number of
+	 * entries in the band_list array in there.
+	 */
+	if (num_of_ranges != in->num_of_ranges)
+		return -EINVAL;
+
+	/*
+	 * Every input frequency band comes with two end points(start/end)
+	 * and each is accounted as an element. Meanwhile the range count
+	 * and action type are accounted as an element each.
+	 * So, the total element count = 2 * num_of_ranges + 1 + 1.
+	 */
+	num_of_elements = 2 * num_of_ranges + 2;
+
+	tmp = kcalloc(num_of_elements, sizeof(*tmp), GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
+	argv4.package.type = ACPI_TYPE_PACKAGE;
+	argv4.package.count = num_of_elements;
+	argv4.package.elements = tmp;
+
+	/* save the number of ranges*/
+	tmp[0].integer.type = ACPI_TYPE_INTEGER;
+	tmp[0].integer.value = num_of_ranges;
+
+	/* save the action(WBRF_RECORD_ADD/REMOVE/RETRIEVE) */
+	tmp[1].integer.type = ACPI_TYPE_INTEGER;
+	tmp[1].integer.value = action;
+
+	arg_idx = 2;
+	for (i = 0; i < ARRAY_SIZE(in->band_list); i++) {
+		if (!in->band_list[i].start || !in->band_list[i].end)
+			continue;
+
+		tmp[arg_idx].integer.type = ACPI_TYPE_INTEGER;
+		tmp[arg_idx++].integer.value = in->band_list[i].start;
+		tmp[arg_idx].integer.type = ACPI_TYPE_INTEGER;
+		tmp[arg_idx++].integer.value = in->band_list[i].end;
+	}
+
+	obj = acpi_evaluate_dsm(adev->handle, &wifi_acpi_dsm_guid,
+				WBRF_REVISION, WBRF_RECORD, &argv4);
+
+	if (!obj)
+		return -EINVAL;
+
+	if (obj->type != ACPI_TYPE_INTEGER) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = obj->integer.value;
+	if (ret)
+		ret = -EINVAL;
+
+out:
+	ACPI_FREE(obj);
+	kfree(tmp);
+
+	return ret;
+}
+
+/**
+ * acpi_amd_wbrf_add_remove - add or remove the frequency band the device is using
+ *
+ * @dev: device pointer
+ * @action: remove or add the frequency band into bios
+ * @in: input structure containing the frequency band the device is using
+ *
+ * Broadcast to other consumers the frequency band the device starts
+ * to use. Underneath the surface the information is cached into an
+ * internal buffer first. Then a notification is sent to all those
+ * registered consumers. So then they can retrieve that buffer to
+ * know the latest active frequency bands. Consumers that haven't
+ * yet been registered can retrieve the information from the cache
+ * when they register.
+ *
+ * Return:
+ * 0 for success add/remove wifi frequency band.
+ * Returns a negative error code for failure.
+ */
+int acpi_amd_wbrf_add_remove(struct device *dev, uint8_t action, struct wbrf_ranges_in_out *in)
+{
+	struct acpi_device *adev;
+	int ret;
+
+	adev = ACPI_COMPANION(dev);
+	if (!adev)
+		return -ENODEV;
+
+	ret = wbrf_record(adev, action, in);
+	if (ret)
+		return ret;
+
+	blocking_notifier_call_chain(&wbrf_chain_head, WBRF_CHANGED, NULL);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(acpi_amd_wbrf_add_remove);
+
+/**
+ * acpi_amd_wbrf_supported_producer - determine if the WBRF can be enabled
+ *                                    for the device as a producer
+ *
+ * @dev: device pointer
+ *
+ * Check if the platform equipped with necessary implementations to
+ * support WBRF for the device as a producer.
+ *
+ * Return:
+ * true if WBRF is supported, otherwise returns false
+ */
+bool acpi_amd_wbrf_supported_producer(struct device *dev)
+{
+	struct acpi_device *adev;
+
+	adev = ACPI_COMPANION(dev);
+	if (!adev)
+		return false;
+
+	return acpi_check_dsm(adev->handle, &wifi_acpi_dsm_guid,
+			      WBRF_REVISION, BIT(WBRF_RECORD));
+}
+EXPORT_SYMBOL_GPL(acpi_amd_wbrf_supported_producer);
+
+/**
+ * acpi_amd_wbrf_supported_consumer - determine if the WBRF can be enabled
+ *                                    for the device as a consumer
+ *
+ * @dev: device pointer
+ *
+ * Determine if the platform equipped with necessary implementations to
+ * support WBRF for the device as a consumer.
+ *
+ * Return:
+ * true if WBRF is supported, otherwise returns false.
+ */
+bool acpi_amd_wbrf_supported_consumer(struct device *dev)
+{
+	struct acpi_device *adev;
+
+	adev = ACPI_COMPANION(dev);
+	if (!adev)
+		return false;
+
+	return acpi_check_dsm(adev->handle, &wifi_acpi_dsm_guid,
+			      WBRF_REVISION, BIT(WBRF_RETRIEVE));
+}
+EXPORT_SYMBOL_GPL(acpi_amd_wbrf_supported_consumer);
+
+/**
+ * amd_wbrf_retrieve_freq_band - retrieve current active frequency bands
+ *
+ * @dev: device pointer
+ * @out: output structure containing all the active frequency bands
+ *
+ * Retrieve the current active frequency bands which were broadcasted
+ * by other producers. The consumer who calls this API should take
+ * proper actions if any of the frequency band may cause RFI with its
+ * own frequency band used.
+ *
+ * Return:
+ * 0 for getting wifi freq band successfully.
+ * Returns a negative error code for failure.
+ */
+int amd_wbrf_retrieve_freq_band(struct device *dev, struct wbrf_ranges_in_out *out)
+{
+	struct amd_wbrf_ranges_out acpi_out = {0};
+	struct acpi_device *adev;
+	union acpi_object *obj;
+	union acpi_object param;
+	int ret = 0;
+
+	adev = ACPI_COMPANION(dev);
+	if (!adev)
+		return -ENODEV;
+
+	param.type = ACPI_TYPE_STRING;
+	param.string.length = 0;
+	param.string.pointer = NULL;
+
+	obj = acpi_evaluate_dsm(adev->handle, &wifi_acpi_dsm_guid,
+							WBRF_REVISION, WBRF_RETRIEVE, &param);
+	if (!obj)
+		return -EINVAL;
+
+	/*
+	 * The return buffer is with variable length and the format below:
+	 * number_of_entries(1 DWORD):       Number of entries
+	 * start_freq of 1st entry(1 QWORD): Start frequency of the 1st entry
+	 * end_freq of 1st entry(1 QWORD):   End frequency of the 1st entry
+	 * ...
+	 * ...
+	 * start_freq of the last entry(1 QWORD)
+	 * end_freq of the last entry(1 QWORD)
+	 *
+	 * Thus the buffer length is determined by the number of entries.
+	 * - For zero entry scenario, the buffer length will be 4 bytes.
+	 * - For one entry scenario, the buffer length will be 20 bytes.
+	 */
+	if (obj->buffer.length > sizeof(acpi_out) || obj->buffer.length < 4) {
+		dev_err(dev, "Wrong sized WBRT information");
+		ret = -EINVAL;
+		goto out;
+	}
+	memcpy(&acpi_out, obj->buffer.pointer, obj->buffer.length);
+
+	out->num_of_ranges = acpi_out.num_of_ranges;
+	memcpy(out->band_list, acpi_out.band_list, sizeof(acpi_out.band_list));
+
+out:
+	ACPI_FREE(obj);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(amd_wbrf_retrieve_freq_band);
+
+/**
+ * amd_wbrf_register_notifier - register for notifications of frequency
+ *                                   band update
+ *
+ * @nb: driver notifier block
+ *
+ * The consumer should register itself via this API so that it can get
+ * notified on the frequency band updates from other producers.
+ *
+ * Return:
+ * 0 for registering a consumer driver successfully.
+ * Returns a negative error code for failure.
+ */
+int amd_wbrf_register_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&wbrf_chain_head, nb);
+}
+EXPORT_SYMBOL_GPL(amd_wbrf_register_notifier);
+
+/**
+ * amd_wbrf_unregister_notifier - unregister for notifications of
+ *                                     frequency band update
+ *
+ * @nb: driver notifier block
+ *
+ * The consumer should call this API when it is longer interested with
+ * the frequency band updates from other producers. Usually, this should
+ * be performed during driver cleanup.
+ *
+ * Return:
+ * 0 for unregistering a consumer driver.
+ * Returns a negative error code for failure.
+ */
+int amd_wbrf_unregister_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(&wbrf_chain_head, nb);
+}
+EXPORT_SYMBOL_GPL(amd_wbrf_unregister_notifier);
diff --git a/drivers/platform/x86/asus-laptop.c b/drivers/platform/x86/asus-laptop.c
index 761029f39314..bf03ea1b1274 100644
--- a/drivers/platform/x86/asus-laptop.c
+++ b/drivers/platform/x86/asus-laptop.c
@@ -1816,9 +1816,8 @@ static void asus_dmi_check(void)
 		return;
 
 	/* On L1400B WLED control the sound card, don't mess with it ... */
-	if (strncmp(model, "L1400B", 6) == 0) {
+	if (strncmp(model, "L1400B", 6) == 0)
 		wlan_status = -1;
-	}
 }
 
 static bool asus_device_present;
diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index 9aa1226e74e6..fceffe2082ec 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -48,25 +48,43 @@ module_param(tablet_mode_sw, uint, 0444);
 MODULE_PARM_DESC(tablet_mode_sw, "Tablet mode detect: -1:auto 0:disable 1:kbd-dock 2:lid-flip 3:lid-flip-rog");
 
 static struct quirk_entry *quirks;
+static bool atkbd_reports_vol_keys;
 
-static bool asus_q500a_i8042_filter(unsigned char data, unsigned char str,
-			      struct serio *port)
+static bool asus_i8042_filter(unsigned char data, unsigned char str, struct serio *port)
 {
-	static bool extended;
-	bool ret = false;
+	static bool extended_e0;
+	static bool extended_e1;
 
 	if (str & I8042_STR_AUXDATA)
 		return false;
 
-	if (unlikely(data == 0xe1)) {
-		extended = true;
-		ret = true;
-	} else if (unlikely(extended)) {
-		extended = false;
-		ret = true;
+	if (quirks->filter_i8042_e1_extended_codes) {
+		if (data == 0xe1) {
+			extended_e1 = true;
+			return true;
+		}
+
+		if (extended_e1) {
+			extended_e1 = false;
+			return true;
+		}
 	}
 
-	return ret;
+	if (data == 0xe0) {
+		extended_e0 = true;
+	} else if (extended_e0) {
+		extended_e0 = false;
+
+		switch (data & 0x7f) {
+		case 0x20: /* e0 20 / e0 a0, Volume Mute press / release */
+		case 0x2e: /* e0 2e / e0 ae, Volume Down press / release */
+		case 0x30: /* e0 30 / e0 b0, Volume Up press / release */
+			atkbd_reports_vol_keys = true;
+			break;
+		}
+	}
+
+	return false;
 }
 
 static struct quirk_entry quirk_asus_unknown = {
@@ -75,7 +93,7 @@ static struct quirk_entry quirk_asus_unknown = {
 };
 
 static struct quirk_entry quirk_asus_q500a = {
-	.i8042_filter = asus_q500a_i8042_filter,
+	.filter_i8042_e1_extended_codes = true,
 	.wmi_backlight_set_devstate = true,
 };
 
@@ -503,8 +521,6 @@ static const struct dmi_system_id asus_quirks[] = {
 
 static void asus_nb_wmi_quirks(struct asus_wmi_driver *driver)
 {
-	int ret;
-
 	quirks = &quirk_asus_unknown;
 	dmi_check_system(asus_quirks);
 
@@ -519,15 +535,6 @@ static void asus_nb_wmi_quirks(struct asus_wmi_driver *driver)
 
 	if (tablet_mode_sw != -1)
 		quirks->tablet_switch_mode = tablet_mode_sw;
-
-	if (quirks->i8042_filter) {
-		ret = i8042_install_filter(quirks->i8042_filter);
-		if (ret) {
-			pr_warn("Unable to install key filter\n");
-			return;
-		}
-		pr_info("Using i8042 filter function for receiving events\n");
-	}
 }
 
 static const struct key_entry asus_nb_wmi_keymap[] = {
@@ -618,6 +625,13 @@ static void asus_nb_wmi_key_filter(struct asus_wmi_driver *asus_wmi, int *code,
 			*code = ASUS_WMI_KEY_IGNORE;
 
 		break;
+	case 0x30: /* Volume Up */
+	case 0x31: /* Volume Down */
+	case 0x32: /* Volume Mute */
+		if (atkbd_reports_vol_keys)
+			*code = ASUS_WMI_KEY_IGNORE;
+
+		break;
 	}
 }
 
@@ -630,6 +644,7 @@ static struct asus_wmi_driver asus_nb_wmi_driver = {
 	.input_phys = ASUS_NB_WMI_FILE "/input0",
 	.detect_quirks = asus_nb_wmi_quirks,
 	.key_filter = asus_nb_wmi_key_filter,
+	.i8042_filter = asus_i8042_filter,
 };
 
 
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 6a79f16233ab..18be35fdb381 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -16,6 +16,7 @@
 #include <linux/acpi.h>
 #include <linux/backlight.h>
 #include <linux/debugfs.h>
+#include <linux/delay.h>
 #include <linux/dmi.h>
 #include <linux/fb.h>
 #include <linux/hwmon.h>
@@ -132,6 +133,11 @@ module_param(fnlock_default, bool, 0444);
 #define ASUS_SCREENPAD_BRIGHT_MAX 255
 #define ASUS_SCREENPAD_BRIGHT_DEFAULT 60
 
+/* Controls the power state of the USB0 hub on ROG Ally which input is on */
+#define ASUS_USB0_PWR_EC0_CSEE "\\_SB.PCI0.SBRG.EC0.CSEE"
+/* 300ms so far seems to produce a reliable result on AC and battery */
+#define ASUS_USB0_PWR_EC0_CSEE_WAIT 300
+
 static const char * const ashs_ids[] = { "ATK4001", "ATK4002", NULL };
 
 static int throttle_thermal_policy_write(struct asus_wmi *);
@@ -300,6 +306,9 @@ struct asus_wmi {
 
 	bool fnlock_locked;
 
+	/* The ROG Ally device requires the MCU USB device be disconnected before suspend */
+	bool ally_mcu_usb_switch;
+
 	struct asus_wmi_debug debug;
 
 	struct asus_wmi_driver *driver;
@@ -4488,6 +4497,8 @@ static int asus_wmi_add(struct platform_device *pdev)
 	asus->nv_temp_tgt_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_NV_THERM_TARGET);
 	asus->panel_overdrive_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_PANEL_OD);
 	asus->mini_led_mode_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_MINI_LED_MODE);
+	asus->ally_mcu_usb_switch = acpi_has_method(NULL, ASUS_USB0_PWR_EC0_CSEE)
+						&& dmi_match(DMI_BOARD_NAME, "RC71L");
 
 	err = fan_boost_mode_check_present(asus);
 	if (err)
@@ -4567,6 +4578,12 @@ static int asus_wmi_add(struct platform_device *pdev)
 		goto fail_wmi_handler;
 	}
 
+	if (asus->driver->i8042_filter) {
+		err = i8042_install_filter(asus->driver->i8042_filter);
+		if (err)
+			pr_warn("Unable to install key filter - %d\n", err);
+	}
+
 	asus_wmi_battery_init(asus);
 
 	asus_wmi_debugfs_init(asus);
@@ -4598,11 +4615,13 @@ fail_platform:
 	return err;
 }
 
-static int asus_wmi_remove(struct platform_device *device)
+static void asus_wmi_remove(struct platform_device *device)
 {
 	struct asus_wmi *asus;
 
 	asus = platform_get_drvdata(device);
+	if (asus->driver->i8042_filter)
+		i8042_remove_filter(asus->driver->i8042_filter);
 	wmi_remove_notify_handler(asus->driver->event_guid);
 	asus_wmi_backlight_exit(asus);
 	asus_screenpad_exit(asus);
@@ -4619,7 +4638,6 @@ static int asus_wmi_remove(struct platform_device *device)
 		platform_profile_remove();
 
 	kfree(asus);
-	return 0;
 }
 
 /* Platform driver - hibernate/resume callbacks *******************************/
@@ -4654,6 +4672,43 @@ static int asus_hotk_resume(struct device *device)
 		asus_wmi_fnlock_update(asus);
 
 	asus_wmi_tablet_mode_get_state(asus);
+
+	return 0;
+}
+
+static int asus_hotk_resume_early(struct device *device)
+{
+	struct asus_wmi *asus = dev_get_drvdata(device);
+
+	if (asus->ally_mcu_usb_switch) {
+		if (ACPI_FAILURE(acpi_execute_simple_method(NULL, ASUS_USB0_PWR_EC0_CSEE, 0xB8)))
+			dev_err(device, "ROG Ally MCU failed to connect USB dev\n");
+		else
+			msleep(ASUS_USB0_PWR_EC0_CSEE_WAIT);
+	}
+	return 0;
+}
+
+static int asus_hotk_prepare(struct device *device)
+{
+	struct asus_wmi *asus = dev_get_drvdata(device);
+	int result, err;
+
+	if (asus->ally_mcu_usb_switch) {
+		/* When powersave is enabled it causes many issues with resume of USB hub */
+		result = asus_wmi_get_devstate_simple(asus, ASUS_WMI_DEVID_MCU_POWERSAVE);
+		if (result == 1) {
+			dev_warn(device, "MCU powersave enabled, disabling to prevent resume issues");
+			err = asus_wmi_set_devstate(ASUS_WMI_DEVID_MCU_POWERSAVE, 0, &result);
+			if (err || result != 1)
+				dev_err(device, "Failed to set MCU powersave mode: %d\n", err);
+		}
+		/* sleep required to ensure USB0 is disabled before sleep continues */
+		if (ACPI_FAILURE(acpi_execute_simple_method(NULL, ASUS_USB0_PWR_EC0_CSEE, 0xB7)))
+			dev_err(device, "ROG Ally MCU failed to disconnect USB dev\n");
+		else
+			msleep(ASUS_USB0_PWR_EC0_CSEE_WAIT);
+	}
 	return 0;
 }
 
@@ -4701,6 +4756,8 @@ static const struct dev_pm_ops asus_pm_ops = {
 	.thaw = asus_hotk_thaw,
 	.restore = asus_hotk_restore,
 	.resume = asus_hotk_resume,
+	.resume_early = asus_hotk_resume_early,
+	.prepare = asus_hotk_prepare,
 };
 
 /* Registration ***************************************************************/
@@ -4741,7 +4798,7 @@ int __init_or_module asus_wmi_register_driver(struct asus_wmi_driver *driver)
 		return -EBUSY;
 
 	platform_driver = &driver->platform_driver;
-	platform_driver->remove = asus_wmi_remove;
+	platform_driver->remove_new = asus_wmi_remove;
 	platform_driver->driver.owner = driver->owner;
 	platform_driver->driver.name = driver->name;
 	platform_driver->driver.pm = &asus_pm_ops;
diff --git a/drivers/platform/x86/asus-wmi.h b/drivers/platform/x86/asus-wmi.h
index adb67c925724..cc30f1853847 100644
--- a/drivers/platform/x86/asus-wmi.h
+++ b/drivers/platform/x86/asus-wmi.h
@@ -39,6 +39,7 @@ struct quirk_entry {
 	bool wmi_backlight_set_devstate;
 	bool wmi_force_als_set;
 	bool wmi_ignore_fan;
+	bool filter_i8042_e1_extended_codes;
 	enum asus_wmi_tablet_switch_mode tablet_switch_mode;
 	int wapf;
 	/*
@@ -49,9 +50,6 @@ struct quirk_entry {
 	 */
 	int no_display_toggle;
 	u32 xusb2pr;
-
-	bool (*i8042_filter)(unsigned char data, unsigned char str,
-			     struct serio *serio);
 };
 
 struct asus_wmi_driver {
@@ -73,6 +71,9 @@ struct asus_wmi_driver {
 	 * Return ASUS_WMI_KEY_IGNORE in code if event should be ignored. */
 	void (*key_filter) (struct asus_wmi_driver *driver, int *code,
 			    unsigned int *value, bool *autorelease);
+	/* Optional standard i8042 filter */
+	bool (*i8042_filter)(unsigned char data, unsigned char str,
+			     struct serio *serio);
 
 	int (*probe) (struct platform_device *device);
 	void (*detect_quirks) (struct asus_wmi_driver *driver);
diff --git a/drivers/platform/x86/dell/alienware-wmi.c b/drivers/platform/x86/dell/alienware-wmi.c
index a9477e5432e4..f5ee62ce1753 100644
--- a/drivers/platform/x86/dell/alienware-wmi.c
+++ b/drivers/platform/x86/dell/alienware-wmi.c
@@ -429,7 +429,6 @@ static DEVICE_ATTR(lighting_control_state, 0644, show_control_state,
 static int alienware_zone_init(struct platform_device *dev)
 {
 	u8 zone;
-	char buffer[10];
 	char *name;
 
 	if (interface == WMAX) {
@@ -466,8 +465,7 @@ static int alienware_zone_init(struct platform_device *dev)
 		return -ENOMEM;
 
 	for (zone = 0; zone < quirks->num_zones; zone++) {
-		sprintf(buffer, "zone%02hhX", zone);
-		name = kstrdup(buffer, GFP_KERNEL);
+		name = kasprintf(GFP_KERNEL, "zone%02hhX", zone);
 		if (name == NULL)
 			return 1;
 		sysfs_attr_init(&zone_dev_attrs[zone].attr);
diff --git a/drivers/platform/x86/dell/dell-smbios-wmi.c b/drivers/platform/x86/dell/dell-smbios-wmi.c
index 931cc50136de..ae9012549560 100644
--- a/drivers/platform/x86/dell/dell-smbios-wmi.c
+++ b/drivers/platform/x86/dell/dell-smbios-wmi.c
@@ -6,12 +6,16 @@
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/device.h>
 #include <linux/dmi.h>
+#include <linux/fs.h>
 #include <linux/list.h>
+#include <linux/miscdevice.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/uaccess.h>
 #include <linux/wmi.h>
+#include <uapi/linux/wmi.h>
 #include "dell-smbios.h"
 #include "dell-wmi-descriptor.h"
 
@@ -32,7 +36,8 @@ struct wmi_smbios_priv {
 	struct list_head list;
 	struct wmi_device *wdev;
 	struct device *child;
-	u32 req_buf_size;
+	u64 req_buf_size;
+	struct miscdevice char_dev;
 };
 static LIST_HEAD(wmi_list);
 
@@ -108,48 +113,115 @@ out_wmi_call:
 	return ret;
 }
 
-static long dell_smbios_wmi_filter(struct wmi_device *wdev, unsigned int cmd,
-				   struct wmi_ioctl_buffer *arg)
+static int dell_smbios_wmi_open(struct inode *inode, struct file *filp)
 {
 	struct wmi_smbios_priv *priv;
-	int ret = 0;
-
-	switch (cmd) {
-	case DELL_WMI_SMBIOS_CMD:
-		mutex_lock(&call_mutex);
-		priv = dev_get_drvdata(&wdev->dev);
-		if (!priv) {
-			ret = -ENODEV;
-			goto fail_smbios_cmd;
-		}
-		memcpy(priv->buf, arg, priv->req_buf_size);
-		if (dell_smbios_call_filter(&wdev->dev, &priv->buf->std)) {
-			dev_err(&wdev->dev, "Invalid call %d/%d:%8x\n",
-				priv->buf->std.cmd_class,
-				priv->buf->std.cmd_select,
-				priv->buf->std.input[0]);
-			ret = -EFAULT;
-			goto fail_smbios_cmd;
-		}
-		ret = run_smbios_call(priv->wdev);
-		if (ret)
-			goto fail_smbios_cmd;
-		memcpy(arg, priv->buf, priv->req_buf_size);
-fail_smbios_cmd:
-		mutex_unlock(&call_mutex);
-		break;
-	default:
-		ret = -ENOIOCTLCMD;
+
+	priv = container_of(filp->private_data, struct wmi_smbios_priv, char_dev);
+	filp->private_data = priv;
+
+	return nonseekable_open(inode, filp);
+}
+
+static ssize_t dell_smbios_wmi_read(struct file *filp, char __user *buffer, size_t length,
+				    loff_t *offset)
+{
+	struct wmi_smbios_priv *priv = filp->private_data;
+
+	return simple_read_from_buffer(buffer, length, offset, &priv->req_buf_size,
+				       sizeof(priv->req_buf_size));
+}
+
+static long dell_smbios_wmi_do_ioctl(struct wmi_smbios_priv *priv,
+				     struct dell_wmi_smbios_buffer __user *arg)
+{
+	long ret;
+
+	if (get_user(priv->buf->length, &arg->length))
+		return -EFAULT;
+
+	if (priv->buf->length < priv->req_buf_size)
+		return -EINVAL;
+
+	/* if it's too big, warn, driver will only use what is needed */
+	if (priv->buf->length > priv->req_buf_size)
+		dev_err(&priv->wdev->dev, "Buffer %llu is bigger than required %llu\n",
+			priv->buf->length, priv->req_buf_size);
+
+	if (copy_from_user(priv->buf, arg, priv->req_buf_size))
+		return -EFAULT;
+
+	if (dell_smbios_call_filter(&priv->wdev->dev, &priv->buf->std)) {
+		dev_err(&priv->wdev->dev, "Invalid call %d/%d:%8x\n",
+			priv->buf->std.cmd_class,
+			priv->buf->std.cmd_select,
+			priv->buf->std.input[0]);
+
+		return -EINVAL;
 	}
+
+	ret = run_smbios_call(priv->wdev);
+	if (ret)
+		return ret;
+
+	if (copy_to_user(arg, priv->buf, priv->req_buf_size))
+		return -EFAULT;
+
+	return 0;
+}
+
+static long dell_smbios_wmi_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+	struct dell_wmi_smbios_buffer __user *input = (struct dell_wmi_smbios_buffer __user *)arg;
+	struct wmi_smbios_priv *priv = filp->private_data;
+	long ret;
+
+	if (cmd != DELL_WMI_SMBIOS_CMD)
+		return -ENOIOCTLCMD;
+
+	mutex_lock(&call_mutex);
+	ret = dell_smbios_wmi_do_ioctl(priv, input);
+	mutex_unlock(&call_mutex);
+
 	return ret;
 }
 
+static const struct file_operations dell_smbios_wmi_fops = {
+	.owner		= THIS_MODULE,
+	.open		= dell_smbios_wmi_open,
+	.read		= dell_smbios_wmi_read,
+	.unlocked_ioctl	= dell_smbios_wmi_ioctl,
+	.compat_ioctl	= compat_ptr_ioctl,
+};
+
+static void dell_smbios_wmi_unregister_chardev(void *data)
+{
+	struct miscdevice *char_dev = data;
+
+	misc_deregister(char_dev);
+}
+
+static int dell_smbios_wmi_register_chardev(struct wmi_smbios_priv *priv)
+{
+	int ret;
+
+	priv->char_dev.minor = MISC_DYNAMIC_MINOR;
+	priv->char_dev.name = "wmi/dell-smbios";
+	priv->char_dev.fops = &dell_smbios_wmi_fops;
+	priv->char_dev.mode = 0444;
+
+	ret = misc_register(&priv->char_dev);
+	if (ret < 0)
+		return ret;
+
+	return devm_add_action_or_reset(&priv->wdev->dev, dell_smbios_wmi_unregister_chardev,
+					&priv->char_dev);
+}
+
 static int dell_smbios_wmi_probe(struct wmi_device *wdev, const void *context)
 {
-	struct wmi_driver *wdriver =
-		container_of(wdev->dev.driver, struct wmi_driver, driver);
 	struct wmi_smbios_priv *priv;
-	u32 hotfix;
+	u32 buffer_size, hotfix;
 	int count;
 	int ret;
 
@@ -162,62 +234,58 @@ static int dell_smbios_wmi_probe(struct wmi_device *wdev, const void *context)
 	if (!priv)
 		return -ENOMEM;
 
+	priv->wdev = wdev;
+	dev_set_drvdata(&wdev->dev, priv);
+
 	/* WMI buffer size will be either 4k or 32k depending on machine */
-	if (!dell_wmi_get_size(&priv->req_buf_size))
+	if (!dell_wmi_get_size(&buffer_size))
 		return -EPROBE_DEFER;
 
+	priv->req_buf_size = buffer_size;
+
 	/* some SMBIOS calls fail unless BIOS contains hotfix */
 	if (!dell_wmi_get_hotfix(&hotfix))
 		return -EPROBE_DEFER;
-	if (!hotfix) {
+
+	if (!hotfix)
 		dev_warn(&wdev->dev,
 			"WMI SMBIOS userspace interface not supported(%u), try upgrading to a newer BIOS\n",
 			hotfix);
-		wdriver->filter_callback = NULL;
-	}
 
 	/* add in the length object we will use internally with ioctl */
 	priv->req_buf_size += sizeof(u64);
-	ret = set_required_buffer_size(wdev, priv->req_buf_size);
-	if (ret)
-		return ret;
 
 	count = get_order(priv->req_buf_size);
-	priv->buf = (void *)__get_free_pages(GFP_KERNEL, count);
+	priv->buf = (void *)devm_get_free_pages(&wdev->dev, GFP_KERNEL, count);
 	if (!priv->buf)
 		return -ENOMEM;
 
+	ret = dell_smbios_wmi_register_chardev(priv);
+	if (ret)
+		return ret;
+
 	/* ID is used by dell-smbios to set priority of drivers */
 	wdev->dev.id = 1;
 	ret = dell_smbios_register_device(&wdev->dev, &dell_smbios_wmi_call);
 	if (ret)
-		goto fail_register;
+		return ret;
 
-	priv->wdev = wdev;
-	dev_set_drvdata(&wdev->dev, priv);
 	mutex_lock(&list_mutex);
 	list_add_tail(&priv->list, &wmi_list);
 	mutex_unlock(&list_mutex);
 
 	return 0;
-
-fail_register:
-	free_pages((unsigned long)priv->buf, count);
-	return ret;
 }
 
 static void dell_smbios_wmi_remove(struct wmi_device *wdev)
 {
 	struct wmi_smbios_priv *priv = dev_get_drvdata(&wdev->dev);
-	int count;
 
 	mutex_lock(&call_mutex);
 	mutex_lock(&list_mutex);
 	list_del(&priv->list);
 	mutex_unlock(&list_mutex);
 	dell_smbios_unregister_device(&wdev->dev);
-	count = get_order(priv->req_buf_size);
-	free_pages((unsigned long)priv->buf, count);
 	mutex_unlock(&call_mutex);
 }
 
@@ -256,7 +324,6 @@ static struct wmi_driver dell_smbios_wmi_driver = {
 	.probe = dell_smbios_wmi_probe,
 	.remove = dell_smbios_wmi_remove,
 	.id_table = dell_smbios_wmi_id_table,
-	.filter_callback = dell_smbios_wmi_filter,
 };
 
 int init_dell_smbios_wmi(void)
diff --git a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c
index 5798b49ddaba..8c9f4f3227fc 100644
--- a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c
+++ b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c
@@ -588,17 +588,14 @@ static void release_attributes_data(void)
 static int hp_add_other_attributes(int attr_type)
 {
 	struct kobject *attr_name_kobj;
-	union acpi_object *obj = NULL;
 	int ret;
 	char *attr_name;
 
-	mutex_lock(&bioscfg_drv.mutex);
-
 	attr_name_kobj = kzalloc(sizeof(*attr_name_kobj), GFP_KERNEL);
-	if (!attr_name_kobj) {
-		ret = -ENOMEM;
-		goto err_other_attr_init;
-	}
+	if (!attr_name_kobj)
+		return -ENOMEM;
+
+	mutex_lock(&bioscfg_drv.mutex);
 
 	/* Check if attribute type is supported */
 	switch (attr_type) {
@@ -615,14 +612,14 @@ static int hp_add_other_attributes(int attr_type)
 	default:
 		pr_err("Error: Unknown attr_type: %d\n", attr_type);
 		ret = -EINVAL;
-		goto err_other_attr_init;
+		kfree(attr_name_kobj);
+		goto unlock_drv_mutex;
 	}
 
 	ret = kobject_init_and_add(attr_name_kobj, &attr_name_ktype,
 				   NULL, "%s", attr_name);
 	if (ret) {
 		pr_err("Error encountered [%d]\n", ret);
-		kobject_put(attr_name_kobj);
 		goto err_other_attr_init;
 	}
 
@@ -630,27 +627,26 @@ static int hp_add_other_attributes(int attr_type)
 	switch (attr_type) {
 	case HPWMI_SECURE_PLATFORM_TYPE:
 		ret = hp_populate_secure_platform_data(attr_name_kobj);
-		if (ret)
-			goto err_other_attr_init;
 		break;
 
 	case HPWMI_SURE_START_TYPE:
 		ret = hp_populate_sure_start_data(attr_name_kobj);
-		if (ret)
-			goto err_other_attr_init;
 		break;
 
 	default:
 		ret = -EINVAL;
-		goto err_other_attr_init;
 	}
 
+	if (ret)
+		goto err_other_attr_init;
+
 	mutex_unlock(&bioscfg_drv.mutex);
 	return 0;
 
 err_other_attr_init:
+	kobject_put(attr_name_kobj);
+unlock_drv_mutex:
 	mutex_unlock(&bioscfg_drv.mutex);
-	kfree(obj);
 	return ret;
 }
 
diff --git a/drivers/platform/x86/hp/hp-bioscfg/passwdobj-attributes.c b/drivers/platform/x86/hp/hp-bioscfg/passwdobj-attributes.c
index 03d0188804ba..f7efe217a4bb 100644
--- a/drivers/platform/x86/hp/hp-bioscfg/passwdobj-attributes.c
+++ b/drivers/platform/x86/hp/hp-bioscfg/passwdobj-attributes.c
@@ -7,7 +7,6 @@
  */
 
 #include "bioscfg.h"
-#include <asm-generic/posix_types.h>
 
 GET_INSTANCE_ID(password);
 /*
diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c
index 8ebb7be52ee7..e536604225c5 100644
--- a/drivers/platform/x86/hp/hp-wmi.c
+++ b/drivers/platform/x86/hp/hp-wmi.c
@@ -1478,7 +1478,7 @@ static int __init hp_wmi_bios_setup(struct platform_device *device)
 	return 0;
 }
 
-static int __exit hp_wmi_bios_remove(struct platform_device *device)
+static void __exit hp_wmi_bios_remove(struct platform_device *device)
 {
 	int i;
 
@@ -1502,8 +1502,6 @@ static int __exit hp_wmi_bios_remove(struct platform_device *device)
 
 	if (platform_profile_support)
 		platform_profile_remove();
-
-	return 0;
 }
 
 static int hp_wmi_resume_handler(struct device *device)
@@ -1560,7 +1558,7 @@ static struct platform_driver hp_wmi_driver __refdata = {
 		.pm = &hp_wmi_pm_ops,
 		.dev_groups = hp_wmi_groups,
 	},
-	.remove = __exit_p(hp_wmi_bios_remove),
+	.remove_new = __exit_p(hp_wmi_bios_remove),
 };
 
 static umode_t hp_wmi_hwmon_is_visible(const void *data,
diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index ac037540acfc..88eefccb6ed2 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -1425,18 +1425,17 @@ static int ideapad_kbd_bl_init(struct ideapad_private *priv)
 	if (WARN_ON(priv->kbd_bl.initialized))
 		return -EEXIST;
 
-	brightness = ideapad_kbd_bl_brightness_get(priv);
-	if (brightness < 0)
-		return brightness;
-
-	priv->kbd_bl.last_brightness = brightness;
-
 	if (ideapad_kbd_bl_check_tristate(priv->kbd_bl.type)) {
 		priv->kbd_bl.led.max_brightness = 2;
 	} else {
 		priv->kbd_bl.led.max_brightness = 1;
 	}
 
+	brightness = ideapad_kbd_bl_brightness_get(priv);
+	if (brightness < 0)
+		return brightness;
+
+	priv->kbd_bl.last_brightness = brightness;
 	priv->kbd_bl.led.name                    = "platform::" LED_FUNCTION_KBD_BACKLIGHT;
 	priv->kbd_bl.led.brightness_get          = ideapad_kbd_bl_led_cdev_brightness_get;
 	priv->kbd_bl.led.brightness_set_blocking = ideapad_kbd_bl_led_cdev_brightness_set;
diff --git a/drivers/platform/x86/intel/pmc/Kconfig b/drivers/platform/x86/intel/pmc/Kconfig
index b526597e4deb..d2f651fbec2c 100644
--- a/drivers/platform/x86/intel/pmc/Kconfig
+++ b/drivers/platform/x86/intel/pmc/Kconfig
@@ -7,6 +7,7 @@ config INTEL_PMC_CORE
 	tristate "Intel PMC Core driver"
 	depends on PCI
 	depends on ACPI
+	depends on INTEL_PMT_TELEMETRY
 	help
 	  The Intel Platform Controller Hub for Intel Core SoCs provides access
 	  to Power Management Controller registers via various interfaces. This
diff --git a/drivers/platform/x86/intel/pmc/Makefile b/drivers/platform/x86/intel/pmc/Makefile
index 3a4cf1cbc1ca..389e5419dadf 100644
--- a/drivers/platform/x86/intel/pmc/Makefile
+++ b/drivers/platform/x86/intel/pmc/Makefile
@@ -4,7 +4,7 @@
 #
 
 intel_pmc_core-y			:= core.o core_ssram.o spt.o cnp.o \
-					   icl.o tgl.o adl.o mtl.o
+					   icl.o tgl.o adl.o mtl.o arl.o lnl.o
 obj-$(CONFIG_INTEL_PMC_CORE)		+= intel_pmc_core.o
 intel_pmc_core_pltdrv-y			:= pltdrv.o
 obj-$(CONFIG_INTEL_PMC_CORE)		+= intel_pmc_core_pltdrv.o
diff --git a/drivers/platform/x86/intel/pmc/adl.c b/drivers/platform/x86/intel/pmc/adl.c
index 5006008e01be..e7878558fd90 100644
--- a/drivers/platform/x86/intel/pmc/adl.c
+++ b/drivers/platform/x86/intel/pmc/adl.c
@@ -307,6 +307,8 @@ const struct pmc_reg_map adl_reg_map = {
 	.lpm_sts = adl_lpm_maps,
 	.lpm_status_offset = ADL_LPM_STATUS_OFFSET,
 	.lpm_live_status_offset = ADL_LPM_LIVE_STATUS_OFFSET,
+	.pson_residency_offset = TGL_PSON_RESIDENCY_OFFSET,
+	.pson_residency_counter_step = TGL_PSON_RES_COUNTER_STEP,
 };
 
 int adl_core_init(struct pmc_dev *pmcdev)
@@ -314,16 +316,15 @@ int adl_core_init(struct pmc_dev *pmcdev)
 	struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN];
 	int ret;
 
+	pmcdev->suspend = cnl_suspend;
+	pmcdev->resume = cnl_resume;
+
 	pmc->map = &adl_reg_map;
 	ret = get_primary_reg_base(pmc);
 	if (ret)
 		return ret;
 
-	/* Due to a hardware limitation, the GBE LTR blocks PC10
-	 * when a cable is attached. Tell the PMC to ignore it.
-	 */
-	dev_dbg(&pmcdev->pdev->dev, "ignoring GBE LTR\n");
-	pmc_core_send_ltr_ignore(pmcdev, 3);
+	pmc_core_get_low_power_modes(pmcdev);
 
 	return 0;
 }
diff --git a/drivers/platform/x86/intel/pmc/arl.c b/drivers/platform/x86/intel/pmc/arl.c
new file mode 100644
index 000000000000..683ae828276b
--- /dev/null
+++ b/drivers/platform/x86/intel/pmc/arl.c
@@ -0,0 +1,729 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This file contains platform specific structure definitions
+ * and init function used by Meteor Lake PCH.
+ *
+ * Copyright (c) 2022, Intel Corporation.
+ * All Rights Reserved.
+ *
+ */
+
+#include <linux/pci.h>
+#include "core.h"
+#include "../pmt/telemetry.h"
+
+/* PMC SSRAM PMT Telemetry GUID */
+#define IOEP_LPM_REQ_GUID	0x5077612
+#define SOCS_LPM_REQ_GUID	0x8478657
+#define PCHS_LPM_REQ_GUID	0x9684572
+
+static const u8 ARL_LPM_REG_INDEX[] = {0, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 15, 16, 20};
+
+const struct pmc_bit_map arl_socs_ltr_show_map[] = {
+	{"SOUTHPORT_A",		CNP_PMC_LTR_SPA},
+	{"SOUTHPORT_B",		CNP_PMC_LTR_SPB},
+	{"SATA",		CNP_PMC_LTR_SATA},
+	{"GIGABIT_ETHERNET",	CNP_PMC_LTR_GBE},
+	{"XHCI",		CNP_PMC_LTR_XHCI},
+	{"SOUTHPORT_F",		ADL_PMC_LTR_SPF},
+	{"ME",			CNP_PMC_LTR_ME},
+	/* EVA is Enterprise Value Add, doesn't really exist on PCH */
+	{"SATA1",		CNP_PMC_LTR_EVA},
+	{"SOUTHPORT_C",		CNP_PMC_LTR_SPC},
+	{"HD_AUDIO",		CNP_PMC_LTR_AZ},
+	{"CNV",			CNP_PMC_LTR_CNV},
+	{"LPSS",		CNP_PMC_LTR_LPSS},
+	{"SOUTHPORT_D",		CNP_PMC_LTR_SPD},
+	{"SOUTHPORT_E",		CNP_PMC_LTR_SPE},
+	{"SATA2",		CNP_PMC_LTR_CAM},
+	{"ESPI",		CNP_PMC_LTR_ESPI},
+	{"SCC",			CNP_PMC_LTR_SCC},
+	{"ISH",			CNP_PMC_LTR_ISH},
+	{"UFSX2",		CNP_PMC_LTR_UFSX2},
+	{"EMMC",		CNP_PMC_LTR_EMMC},
+	/*
+	 * Check intel_pmc_core_ids[] users of cnp_reg_map for
+	 * a list of core SoCs using this.
+	 */
+	{"WIGIG",		ICL_PMC_LTR_WIGIG},
+	{"THC0",		TGL_PMC_LTR_THC0},
+	{"THC1",		TGL_PMC_LTR_THC1},
+	{"SOUTHPORT_G",		MTL_PMC_LTR_SPG},
+	{"Reserved",		ARL_SOCS_PMC_LTR_RESERVED},
+	{"IOE_PMC",		MTL_PMC_LTR_IOE_PMC},
+	{"DMI3",		ARL_PMC_LTR_DMI3},
+
+	/* Below two cannot be used for LTR_IGNORE */
+	{"CURRENT_PLATFORM",	CNP_PMC_LTR_CUR_PLT},
+	{"AGGREGATED_SYSTEM",	CNP_PMC_LTR_CUR_ASLT},
+	{}
+};
+
+const struct pmc_bit_map arl_socs_clocksource_status_map[] = {
+	{"AON2_OFF_STS",		BIT(0)},
+	{"AON3_OFF_STS",		BIT(1)},
+	{"AON4_OFF_STS",		BIT(2)},
+	{"AON5_OFF_STS",		BIT(3)},
+	{"AON1_OFF_STS",		BIT(4)},
+	{"XTAL_LVM_OFF_STS",		BIT(5)},
+	{"AON3_SPL_OFF_STS",		BIT(9)},
+	{"DMI3FPW_0_PLL_OFF_STS",	BIT(10)},
+	{"DMI3FPW_1_PLL_OFF_STS",	BIT(11)},
+	{"G5X16FPW_0_PLL_OFF_STS",	BIT(14)},
+	{"G5X16FPW_1_PLL_OFF_STS",	BIT(15)},
+	{"G5X16FPW_2_PLL_OFF_STS",	BIT(16)},
+	{"XTAL_AGGR_OFF_STS",		BIT(17)},
+	{"USB2_PLL_OFF_STS",		BIT(18)},
+	{"G5X16FPW_3_PLL_OFF_STS",	BIT(19)},
+	{"BCLK_EXT_INJ_CLK_OFF_STS",	BIT(20)},
+	{"PHY_OC_EXT_INJ_CLK_OFF_STS",	BIT(21)},
+	{"FILTER_PLL_OFF_STS",		BIT(22)},
+	{"FABRIC_PLL_OFF_STS",		BIT(25)},
+	{"SOC_PLL_OFF_STS",		BIT(26)},
+	{"PCIEFAB_PLL_OFF_STS",		BIT(27)},
+	{"REF_PLL_OFF_STS",		BIT(28)},
+	{"GENLOCK_FILTER_PLL_OFF_STS",	BIT(30)},
+	{"RTC_PLL_OFF_STS",		BIT(31)},
+	{}
+};
+
+const struct pmc_bit_map arl_socs_power_gating_status_0_map[] = {
+	{"PMC_PGD0_PG_STS",		BIT(0)},
+	{"DMI_PGD0_PG_STS",		BIT(1)},
+	{"ESPISPI_PGD0_PG_STS",		BIT(2)},
+	{"XHCI_PGD0_PG_STS",		BIT(3)},
+	{"SPA_PGD0_PG_STS",		BIT(4)},
+	{"SPB_PGD0_PG_STS",		BIT(5)},
+	{"SPC_PGD0_PG_STS",		BIT(6)},
+	{"GBE_PGD0_PG_STS",		BIT(7)},
+	{"SATA_PGD0_PG_STS",		BIT(8)},
+	{"FIACPCB_P5x16_PGD0_PG_STS",	BIT(9)},
+	{"G5x16FPW_PGD0_PG_STS",	BIT(10)},
+	{"FIA_D_PGD0_PG_STS",		BIT(11)},
+	{"MPFPW2_PGD0_PG_STS",		BIT(12)},
+	{"SPD_PGD0_PG_STS",		BIT(13)},
+	{"LPSS_PGD0_PG_STS",		BIT(14)},
+	{"LPC_PGD0_PG_STS",		BIT(15)},
+	{"SMB_PGD0_PG_STS",		BIT(16)},
+	{"ISH_PGD0_PG_STS",		BIT(17)},
+	{"P2S_PGD0_PG_STS",		BIT(18)},
+	{"NPK_PGD0_PG_STS",		BIT(19)},
+	{"DMI3FPW_PGD0_PG_STS",		BIT(20)},
+	{"GBETSN1_PGD0_PG_STS",		BIT(21)},
+	{"FUSE_PGD0_PG_STS",		BIT(22)},
+	{"FIACPCB_D_PGD0_PG_STS",	BIT(23)},
+	{"FUSEGPSB_PGD0_PG_STS",	BIT(24)},
+	{"XDCI_PGD0_PG_STS",		BIT(25)},
+	{"EXI_PGD0_PG_STS",		BIT(26)},
+	{"CSE_PGD0_PG_STS",		BIT(27)},
+	{"KVMCC_PGD0_PG_STS",		BIT(28)},
+	{"PMT_PGD0_PG_STS",		BIT(29)},
+	{"CLINK_PGD0_PG_STS",		BIT(30)},
+	{"PTIO_PGD0_PG_STS",		BIT(31)},
+	{}
+};
+
+const struct pmc_bit_map arl_socs_power_gating_status_1_map[] = {
+	{"USBR0_PGD0_PG_STS",		BIT(0)},
+	{"SUSRAM_PGD0_PG_STS",		BIT(1)},
+	{"SMT1_PGD0_PG_STS",		BIT(2)},
+	{"FIACPCB_U_PGD0_PG_STS",	BIT(3)},
+	{"SMS2_PGD0_PG_STS",		BIT(4)},
+	{"SMS1_PGD0_PG_STS",		BIT(5)},
+	{"CSMERTC_PGD0_PG_STS",		BIT(6)},
+	{"CSMEPSF_PGD0_PG_STS",		BIT(7)},
+	{"SBR0_PGD0_PG_STS",		BIT(8)},
+	{"SBR1_PGD0_PG_STS",		BIT(9)},
+	{"SBR2_PGD0_PG_STS",		BIT(10)},
+	{"SBR3_PGD0_PG_STS",		BIT(11)},
+	{"MPFPW1_PGD0_PG_STS",		BIT(12)},
+	{"SBR5_PGD0_PG_STS",		BIT(13)},
+	{"FIA_X_PGD0_PG_STS",		BIT(14)},
+	{"FIACPCB_X_PGD0_PG_STS",	BIT(15)},
+	{"SBRG_PGD0_PG_STS",		BIT(16)},
+	{"SOC_D2D_PGD1_PG_STS",		BIT(17)},
+	{"PSF4_PGD0_PG_STS",		BIT(18)},
+	{"CNVI_PGD0_PG_STS",		BIT(19)},
+	{"UFSX2_PGD0_PG_STS",		BIT(20)},
+	{"ENDBG_PGD0_PG_STS",		BIT(21)},
+	{"DBG_PSF_PGD0_PG_STS",		BIT(22)},
+	{"SBR6_PGD0_PG_STS",		BIT(23)},
+	{"SOC_D2D_PGD2_PG_STS",		BIT(24)},
+	{"NPK_PGD1_PG_STS",		BIT(25)},
+	{"DMI3_PGD0_PG_STS",		BIT(26)},
+	{"DBG_SBR_PGD0_PG_STS",		BIT(27)},
+	{"SOC_D2D_PGD0_PG_STS",		BIT(28)},
+	{"PSF6_PGD0_PG_STS",		BIT(29)},
+	{"PSF7_PGD0_PG_STS",		BIT(30)},
+	{"MPFPW3_PGD0_PG_STS",		BIT(31)},
+	{}
+};
+
+const struct pmc_bit_map arl_socs_power_gating_status_2_map[] = {
+	{"PSF8_PGD0_PG_STS",		BIT(0)},
+	{"FIA_PGD0_PG_STS",		BIT(1)},
+	{"SOC_D2D_PGD3_PG_STS",		BIT(2)},
+	{"FIA_U_PGD0_PG_STS",		BIT(3)},
+	{"TAM_PGD0_PG_STS",		BIT(4)},
+	{"GBETSN_PGD0_PG_STS",		BIT(5)},
+	{"TBTLSX_PGD0_PG_STS",		BIT(6)},
+	{"THC0_PGD0_PG_STS",		BIT(7)},
+	{"THC1_PGD0_PG_STS",		BIT(8)},
+	{"PMC_PGD1_PG_STS",		BIT(9)},
+	{"FIA_P5x16_PGD0_PG_STS",	BIT(10)},
+	{"GNA_PGD0_PG_STS",		BIT(11)},
+	{"ACE_PGD0_PG_STS",		BIT(12)},
+	{"ACE_PGD1_PG_STS",		BIT(13)},
+	{"ACE_PGD2_PG_STS",		BIT(14)},
+	{"ACE_PGD3_PG_STS",		BIT(15)},
+	{"ACE_PGD4_PG_STS",		BIT(16)},
+	{"ACE_PGD5_PG_STS",		BIT(17)},
+	{"ACE_PGD6_PG_STS",		BIT(18)},
+	{"ACE_PGD7_PG_STS",		BIT(19)},
+	{"ACE_PGD8_PG_STS",		BIT(20)},
+	{"FIA_PGS_PGD0_PG_STS",		BIT(21)},
+	{"FIACPCB_PGS_PGD0_PG_STS",	BIT(22)},
+	{"FUSEPMSB_PGD0_PG_STS",	BIT(23)},
+	{}
+};
+
+const struct pmc_bit_map arl_socs_d3_status_2_map[] = {
+	{"CSMERTC_D3_STS",		BIT(1)},
+	{"SUSRAM_D3_STS",		BIT(2)},
+	{"CSE_D3_STS",			BIT(4)},
+	{"KVMCC_D3_STS",		BIT(5)},
+	{"USBR0_D3_STS",		BIT(6)},
+	{"ISH_D3_STS",			BIT(7)},
+	{"SMT1_D3_STS",			BIT(8)},
+	{"SMT2_D3_STS",			BIT(9)},
+	{"SMT3_D3_STS",			BIT(10)},
+	{"GNA_D3_STS",			BIT(12)},
+	{"CLINK_D3_STS",		BIT(14)},
+	{"PTIO_D3_STS",			BIT(16)},
+	{"PMT_D3_STS",			BIT(17)},
+	{"SMS1_D3_STS",			BIT(18)},
+	{"SMS2_D3_STS",			BIT(19)},
+	{}
+};
+
+const struct pmc_bit_map arl_socs_d3_status_3_map[] = {
+	{"GBETSN_D3_STS",		BIT(13)},
+	{"THC0_D3_STS",			BIT(14)},
+	{"THC1_D3_STS",			BIT(15)},
+	{"ACE_D3_STS",			BIT(23)},
+	{}
+};
+
+const struct pmc_bit_map arl_socs_vnn_req_status_3_map[] = {
+	{"DTS0_VNN_REQ_STS",		BIT(7)},
+	{"GPIOCOM5_VNN_REQ_STS",	BIT(11)},
+	{}
+};
+
+const struct pmc_bit_map *arl_socs_lpm_maps[] = {
+	arl_socs_clocksource_status_map,
+	arl_socs_power_gating_status_0_map,
+	arl_socs_power_gating_status_1_map,
+	arl_socs_power_gating_status_2_map,
+	mtl_socm_d3_status_0_map,
+	mtl_socm_d3_status_1_map,
+	arl_socs_d3_status_2_map,
+	arl_socs_d3_status_3_map,
+	mtl_socm_vnn_req_status_0_map,
+	mtl_socm_vnn_req_status_1_map,
+	mtl_socm_vnn_req_status_2_map,
+	arl_socs_vnn_req_status_3_map,
+	mtl_socm_vnn_misc_status_map,
+	mtl_socm_signal_status_map,
+	NULL
+};
+
+const struct pmc_bit_map arl_socs_pfear_map[] = {
+	{"RSVD64",			BIT(0)},
+	{"RSVD65",			BIT(1)},
+	{"RSVD66",			BIT(2)},
+	{"RSVD67",			BIT(3)},
+	{"RSVD68",			BIT(4)},
+	{"GBETSN",			BIT(5)},
+	{"TBTLSX",			BIT(6)},
+	{}
+};
+
+const struct pmc_bit_map *ext_arl_socs_pfear_map[] = {
+	mtl_socm_pfear_map,
+	arl_socs_pfear_map,
+	NULL
+};
+
+const struct pmc_reg_map arl_socs_reg_map = {
+	.pfear_sts = ext_arl_socs_pfear_map,
+	.ppfear_buckets = ARL_SOCS_PPFEAR_NUM_ENTRIES,
+	.pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT,
+	.lpm_sts = arl_socs_lpm_maps,
+	.ltr_ignore_max = ARL_SOCS_NUM_IP_IGN_ALLOWED,
+	.ltr_show_sts = arl_socs_ltr_show_map,
+	.slp_s0_offset = CNP_PMC_SLP_S0_RES_COUNTER_OFFSET,
+	.slp_s0_res_counter_step = TGL_PMC_SLP_S0_RES_COUNTER_STEP,
+	.lpm_res_counter_step_x2 = TGL_PMC_LPM_RES_COUNTER_STEP_X2,
+	.msr_sts = msr_map,
+	.ltr_ignore_offset = CNP_PMC_LTR_IGNORE_OFFSET,
+	.regmap_length = MTL_SOC_PMC_MMIO_REG_LEN,
+	.ppfear0_offset = CNP_PMC_HOST_PPFEAR0A,
+	.pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET,
+	.lpm_priority_offset = MTL_LPM_PRI_OFFSET,
+	.lpm_en_offset = MTL_LPM_EN_OFFSET,
+	.lpm_residency_offset = MTL_LPM_RESIDENCY_OFFSET,
+	.lpm_status_offset = MTL_LPM_STATUS_OFFSET,
+	.lpm_sts_latch_en_offset = MTL_LPM_STATUS_LATCH_EN_OFFSET,
+	.lpm_live_status_offset = MTL_LPM_LIVE_STATUS_OFFSET,
+	.lpm_num_maps = ADL_LPM_NUM_MAPS,
+	.lpm_reg_index = ARL_LPM_REG_INDEX,
+	.etr3_offset = ETR3_OFFSET,
+	.pson_residency_offset = TGL_PSON_RESIDENCY_OFFSET,
+	.pson_residency_counter_step = TGL_PSON_RES_COUNTER_STEP,
+};
+
+const struct pmc_bit_map arl_pchs_ltr_show_map[] = {
+	{"SOUTHPORT_A",		CNP_PMC_LTR_SPA},
+	{"SOUTHPORT_B",		CNP_PMC_LTR_SPB},
+	{"SATA",		CNP_PMC_LTR_SATA},
+	{"GIGABIT_ETHERNET",	CNP_PMC_LTR_GBE},
+	{"XHCI",		CNP_PMC_LTR_XHCI},
+	{"SOUTHPORT_F",		ADL_PMC_LTR_SPF},
+	{"ME",			CNP_PMC_LTR_ME},
+	/* EVA is Enterprise Value Add, doesn't really exist on PCH */
+	{"SATA1",		CNP_PMC_LTR_EVA},
+	{"SOUTHPORT_C",		CNP_PMC_LTR_SPC},
+	{"HD_AUDIO",		CNP_PMC_LTR_AZ},
+	{"CNV",			CNP_PMC_LTR_CNV},
+	{"LPSS",		CNP_PMC_LTR_LPSS},
+	{"SOUTHPORT_D",		CNP_PMC_LTR_SPD},
+	{"SOUTHPORT_E",		CNP_PMC_LTR_SPE},
+	{"SATA2",		CNP_PMC_LTR_CAM},
+	{"ESPI",		CNP_PMC_LTR_ESPI},
+	{"SCC",			CNP_PMC_LTR_SCC},
+	{"ISH",			CNP_PMC_LTR_ISH},
+	{"UFSX2",		CNP_PMC_LTR_UFSX2},
+	{"EMMC",		CNP_PMC_LTR_EMMC},
+	/*
+	 * Check intel_pmc_core_ids[] users of cnp_reg_map for
+	 * a list of core SoCs using this.
+	 */
+	{"WIGIG",		ICL_PMC_LTR_WIGIG},
+	{"THC0",		TGL_PMC_LTR_THC0},
+	{"THC1",		TGL_PMC_LTR_THC1},
+	{"SOUTHPORT_G",		MTL_PMC_LTR_SPG},
+	{"ESE",			MTL_PMC_LTR_ESE},
+	{"IOE_PMC",		MTL_PMC_LTR_IOE_PMC},
+	{"DMI3",		ARL_PMC_LTR_DMI3},
+
+	/* Below two cannot be used for LTR_IGNORE */
+	{"CURRENT_PLATFORM",	CNP_PMC_LTR_CUR_PLT},
+	{"AGGREGATED_SYSTEM",	CNP_PMC_LTR_CUR_ASLT},
+	{}
+};
+
+const struct pmc_bit_map arl_pchs_clocksource_status_map[] = {
+	{"AON2_OFF_STS",		BIT(0)},
+	{"AON3_OFF_STS",		BIT(1)},
+	{"AON4_OFF_STS",		BIT(2)},
+	{"AON2_SPL_OFF_STS",		BIT(3)},
+	{"AONL_OFF_STS",		BIT(4)},
+	{"XTAL_LVM_OFF_STS",		BIT(5)},
+	{"AON5_ACRO_OFF_STS",		BIT(6)},
+	{"AON6_ACRO_OFF_STS",		BIT(7)},
+	{"USB3_PLL_OFF_STS",		BIT(8)},
+	{"ACRO_OFF_STS",		BIT(9)},
+	{"AUDIO_PLL_OFF_STS",		BIT(10)},
+	{"MAIN_CRO_OFF_STS",		BIT(11)},
+	{"MAIN_DIVIDER_OFF_STS",	BIT(12)},
+	{"REF_PLL_NON_OC_OFF_STS",	BIT(13)},
+	{"DMI_PLL_OFF_STS",		BIT(14)},
+	{"PHY_EXT_INJ_OFF_STS",		BIT(15)},
+	{"AON6_MCRO_OFF_STS",		BIT(16)},
+	{"XTAL_AGGR_OFF_STS",		BIT(17)},
+	{"USB2_PLL_OFF_STS",		BIT(18)},
+	{"TSN0_PLL_OFF_STS",		BIT(19)},
+	{"TSN1_PLL_OFF_STS",		BIT(20)},
+	{"GBE_PLL_OFF_STS",		BIT(21)},
+	{"SATA_PLL_OFF_STS",		BIT(22)},
+	{"PCIE0_PLL_OFF_STS",		BIT(23)},
+	{"PCIE1_PLL_OFF_STS",		BIT(24)},
+	{"PCIE2_PLL_OFF_STS",		BIT(26)},
+	{"PCIE3_PLL_OFF_STS",		BIT(27)},
+	{"REF_PLL_OFF_STS",		BIT(28)},
+	{"PCIE4_PLL_OFF_STS",		BIT(29)},
+	{"PCIE5_PLL_OFF_STS",		BIT(30)},
+	{"REF38P4_PLL_OFF_STS",		BIT(31)},
+	{}
+};
+
+const struct pmc_bit_map arl_pchs_power_gating_status_0_map[] = {
+	{"PMC_PGD0_PG_STS",		BIT(0)},
+	{"DMI_PGD0_PG_STS",		BIT(1)},
+	{"ESPISPI_PGD0_PG_STS",		BIT(2)},
+	{"XHCI_PGD0_PG_STS",		BIT(3)},
+	{"SPA_PGD0_PG_STS",		BIT(4)},
+	{"SPB_PGD0_PG_STS",		BIT(5)},
+	{"SPC_PGD0_PG_STS",		BIT(6)},
+	{"GBE_PGD0_PG_STS",		BIT(7)},
+	{"SATA_PGD0_PG_STS",		BIT(8)},
+	{"FIA_X_PGD0_PG_STS",		BIT(9)},
+	{"MPFPW4_PGD0_PG_STS",		BIT(10)},
+	{"EAH_PGD0_PG_STS",		BIT(11)},
+	{"MPFPW1_PGD0_PG_STS",		BIT(12)},
+	{"SPD_PGD0_PG_STS",		BIT(13)},
+	{"LPSS_PGD0_PG_STS",		BIT(14)},
+	{"LPC_PGD0_PG_STS",		BIT(15)},
+	{"SMB_PGD0_PG_STS",		BIT(16)},
+	{"ISH_PGD0_PG_STS",		BIT(17)},
+	{"P2S_PGD0_PG_STS",		BIT(18)},
+	{"NPK_PGD0_PG_STS",		BIT(19)},
+	{"U3FPW1_PGD0_PG_STS",		BIT(20)},
+	{"PECI_PGD0_PG_STS",		BIT(21)},
+	{"FUSE_PGD0_PG_STS",		BIT(22)},
+	{"SBR8_PGD0_PG_STS",		BIT(23)},
+	{"EXE_PGD0_PG_STS",		BIT(24)},
+	{"XDCI_PGD0_PG_STS",		BIT(25)},
+	{"EXI_PGD0_PG_STS",		BIT(26)},
+	{"CSE_PGD0_PG_STS",		BIT(27)},
+	{"KVMCC_PGD0_PG_STS",		BIT(28)},
+	{"PMT_PGD0_PG_STS",		BIT(29)},
+	{"CLINK_PGD0_PG_STS",		BIT(30)},
+	{"PTIO_PGD0_PG_STS",		BIT(31)},
+	{}
+};
+
+const struct pmc_bit_map arl_pchs_power_gating_status_1_map[] = {
+	{"USBR0_PGD0_PG_STS",		BIT(0)},
+	{"SUSRAM_PGD0_PG_STS",		BIT(1)},
+	{"SMT1_PGD0_PG_STS",		BIT(2)},
+	{"SMT4_PGD0_PG_STS",		BIT(3)},
+	{"SMS2_PGD0_PG_STS",		BIT(4)},
+	{"SMS1_PGD0_PG_STS",		BIT(5)},
+	{"CSMERTC_PGD0_PG_STS",		BIT(6)},
+	{"CSMEPSF_PGD0_PG_STS",		BIT(7)},
+	{"SBR0_PGD0_PG_STS",		BIT(8)},
+	{"SBR1_PGD0_PG_STS",		BIT(9)},
+	{"SBR2_PGD0_PG_STS",		BIT(10)},
+	{"SBR3_PGD0_PG_STS",		BIT(11)},
+	{"SBR4_PGD0_PG_STS",		BIT(12)},
+	{"SBR5_PGD0_PG_STS",		BIT(13)},
+	{"MPFPW3_PGD0_PG_STS",		BIT(14)},
+	{"PSF1_PGD0_PG_STS",		BIT(15)},
+	{"PSF2_PGD0_PG_STS",		BIT(16)},
+	{"PSF3_PGD0_PG_STS",		BIT(17)},
+	{"PSF4_PGD0_PG_STS",		BIT(18)},
+	{"CNVI_PGD0_PG_STS",		BIT(19)},
+	{"DMI3_PGD0_PG_STS",		BIT(20)},
+	{"ENDBG_PGD0_PG_STS",		BIT(21)},
+	{"DBG_SBR_PGD0_PG_STS",		BIT(22)},
+	{"SBR6_PGD0_PG_STS",		BIT(23)},
+	{"SBR7_PGD0_PG_STS",		BIT(24)},
+	{"NPK_PGD1_PG_STS",		BIT(25)},
+	{"U3FPW3_PGD0_PG_STS",		BIT(26)},
+	{"MPFPW2_PGD0_PG_STS",		BIT(27)},
+	{"MPFPW7_PGD0_PG_STS",		BIT(28)},
+	{"GBETSN1_PGD0_PG_STS",		BIT(29)},
+	{"PSF7_PGD0_PG_STS",		BIT(30)},
+	{"FIA2_PGD0_PG_STS",		BIT(31)},
+	{}
+};
+
+const struct pmc_bit_map arl_pchs_power_gating_status_2_map[] = {
+	{"U3FPW2_PGD0_PG_STS",		BIT(0)},
+	{"FIA_PGD0_PG_STS",		BIT(1)},
+	{"FIACPCB_X_PGD0_PG_STS",	BIT(2)},
+	{"FIA1_PGD0_PG_STS",		BIT(3)},
+	{"TAM_PGD0_PG_STS",		BIT(4)},
+	{"GBETSN_PGD0_PG_STS",		BIT(5)},
+	{"SBR9_PGD0_PG_STS",		BIT(6)},
+	{"THC0_PGD0_PG_STS",		BIT(7)},
+	{"THC1_PGD0_PG_STS",		BIT(8)},
+	{"PMC_PGD1_PG_STS",		BIT(9)},
+	{"DBC_PGD0_PG_STS",		BIT(10)},
+	{"DBG_PSF_PGD0_PG_STS",		BIT(11)},
+	{"SPF_PGD0_PG_STS",		BIT(12)},
+	{"ACE_PGD0_PG_STS",		BIT(13)},
+	{"ACE_PGD1_PG_STS",		BIT(14)},
+	{"ACE_PGD2_PG_STS",		BIT(15)},
+	{"ACE_PGD3_PG_STS",		BIT(16)},
+	{"ACE_PGD4_PG_STS",		BIT(17)},
+	{"ACE_PGD5_PG_STS",		BIT(18)},
+	{"ACE_PGD6_PG_STS",		BIT(19)},
+	{"ACE_PGD7_PG_STS",		BIT(20)},
+	{"SPE_PGD0_PG_STS",		BIT(21)},
+	{"MPFPW5_PG_STS",		BIT(22)},
+	{}
+};
+
+const struct pmc_bit_map arl_pchs_d3_status_0_map[] = {
+	{"SPF_D3_STS",			BIT(0)},
+	{"LPSS_D3_STS",			BIT(3)},
+	{"XDCI_D3_STS",			BIT(4)},
+	{"XHCI_D3_STS",			BIT(5)},
+	{"SPA_D3_STS",			BIT(12)},
+	{"SPB_D3_STS",			BIT(13)},
+	{"SPC_D3_STS",			BIT(14)},
+	{"SPD_D3_STS",			BIT(15)},
+	{"SPE_D3_STS",			BIT(16)},
+	{"ESPISPI_D3_STS",		BIT(18)},
+	{"SATA_D3_STS",			BIT(20)},
+	{"PSTH_D3_STS",			BIT(21)},
+	{"DMI_D3_STS",			BIT(22)},
+	{}
+};
+
+const struct pmc_bit_map arl_pchs_d3_status_1_map[] = {
+	{"GBETSN1_D3_STS",		BIT(14)},
+	{"GBE_D3_STS",			BIT(19)},
+	{"ITSS_D3_STS",			BIT(23)},
+	{"P2S_D3_STS",			BIT(24)},
+	{"CNVI_D3_STS",			BIT(27)},
+	{}
+};
+
+const struct pmc_bit_map arl_pchs_d3_status_2_map[] = {
+	{"CSMERTC_D3_STS",		BIT(1)},
+	{"SUSRAM_D3_STS",		BIT(2)},
+	{"CSE_D3_STS",			BIT(4)},
+	{"KVMCC_D3_STS",		BIT(5)},
+	{"USBR0_D3_STS",		BIT(6)},
+	{"ISH_D3_STS",			BIT(7)},
+	{"SMT1_D3_STS",			BIT(8)},
+	{"SMT2_D3_STS",			BIT(9)},
+	{"SMT3_D3_STS",			BIT(10)},
+	{"SMT4_D3_STS",			BIT(11)},
+	{"SMT5_D3_STS",			BIT(12)},
+	{"SMT6_D3_STS",			BIT(13)},
+	{"CLINK_D3_STS",		BIT(14)},
+	{"PTIO_D3_STS",			BIT(16)},
+	{"PMT_D3_STS",			BIT(17)},
+	{"SMS1_D3_STS",			BIT(18)},
+	{"SMS2_D3_STS",			BIT(19)},
+	{}
+};
+
+const struct pmc_bit_map arl_pchs_d3_status_3_map[] = {
+	{"ESE_D3_STS",			BIT(3)},
+	{"GBETSN_D3_STS",		BIT(13)},
+	{"THC0_D3_STS",			BIT(14)},
+	{"THC1_D3_STS",			BIT(15)},
+	{"ACE_D3_STS",			BIT(23)},
+	{}
+};
+
+const struct pmc_bit_map arl_pchs_vnn_req_status_0_map[] = {
+	{"FIA_VNN_REQ_STS",		BIT(17)},
+	{"ESPISPI_VNN_REQ_STS",		BIT(18)},
+	{}
+};
+
+const struct pmc_bit_map arl_pchs_vnn_req_status_1_map[] = {
+	{"NPK_VNN_REQ_STS",		BIT(4)},
+	{"DFXAGG_VNN_REQ_STS",		BIT(8)},
+	{"EXI_VNN_REQ_STS",		BIT(9)},
+	{"GBE_VNN_REQ_STS",		BIT(19)},
+	{"SMB_VNN_REQ_STS",		BIT(25)},
+	{"LPC_VNN_REQ_STS",		BIT(26)},
+	{"CNVI_VNN_REQ_STS",		BIT(27)},
+	{}
+};
+
+const struct pmc_bit_map arl_pchs_vnn_req_status_2_map[] = {
+	{"FIA2_VNN_REQ_STS",		BIT(0)},
+	{"CSMERTC_VNN_REQ_STS",		BIT(1)},
+	{"CSE_VNN_REQ_STS",		BIT(4)},
+	{"ISH_VNN_REQ_STS",		BIT(7)},
+	{"SMT1_VNN_REQ_STS",		BIT(8)},
+	{"SMT4_VNN_REQ_STS",		BIT(11)},
+	{"CLINK_VNN_REQ_STS",		BIT(14)},
+	{"SMS1_VNN_REQ_STS",		BIT(18)},
+	{"SMS2_VNN_REQ_STS",		BIT(19)},
+	{"GPIOCOM4_VNN_REQ_STS",	BIT(20)},
+	{"GPIOCOM3_VNN_REQ_STS",	BIT(21)},
+	{"GPIOCOM2_VNN_REQ_STS",	BIT(22)},
+	{"GPIOCOM1_VNN_REQ_STS",	BIT(23)},
+	{"GPIOCOM0_VNN_REQ_STS",	BIT(24)},
+	{}
+};
+
+const struct pmc_bit_map arl_pchs_vnn_req_status_3_map[] = {
+	{"ESE_VNN_REQ_STS",		BIT(3)},
+	{"DTS0_VNN_REQ_STS",		BIT(7)},
+	{"GPIOCOM5_VNN_REQ_STS",	BIT(11)},
+	{"FIA1_VNN_REQ_STS",		BIT(12)},
+	{}
+};
+
+const struct pmc_bit_map arl_pchs_vnn_misc_status_map[] = {
+	{"CPU_C10_REQ_STS",			BIT(0)},
+	{"TS_OFF_REQ_STS",			BIT(1)},
+	{"PNDE_MET_REQ_STS",			BIT(2)},
+	{"PCIE_DEEP_PM_REQ_STS",		BIT(3)},
+	{"FW_THROTTLE_ALLOWED_REQ_STS",		BIT(4)},
+	{"ISH_VNNAON_REQ_STS",			BIT(7)},
+	{"IOE_COND_MET_S02I2_0_REQ_STS",	BIT(8)},
+	{"IOE_COND_MET_S02I2_1_REQ_STS",	BIT(9)},
+	{"IOE_COND_MET_S02I2_2_REQ_STS",	BIT(10)},
+	{"PLT_GREATER_REQ_STS",			BIT(11)},
+	{"PMC_IDLE_FB_OCP_REQ_STS",		BIT(13)},
+	{"PM_SYNC_STATES_REQ_STS",		BIT(14)},
+	{"EA_REQ_STS",				BIT(15)},
+	{"DMI_CLKREQ_B_REQ_STS",		BIT(16)},
+	{"BRK_EV_EN_REQ_STS",			BIT(17)},
+	{"AUTO_DEMO_EN_REQ_STS",		BIT(18)},
+	{"ITSS_CLK_SRC_REQ_STS",		BIT(19)},
+	{"ARC_IDLE_REQ_STS",			BIT(21)},
+	{"DMI_IN_REQ_STS",			BIT(22)},
+	{"FIA_DEEP_PM_REQ_STS",			BIT(23)},
+	{"XDCI_ATTACHED_REQ_STS",		BIT(24)},
+	{"ARC_INTERRUPT_WAKE_REQ_STS",		BIT(25)},
+	{"PRE_WAKE0_REQ_STS",			BIT(27)},
+	{"PRE_WAKE1_REQ_STS",			BIT(28)},
+	{"PRE_WAKE2_EN_REQ_STS",		BIT(29)},
+	{"CNVI_V1P05_REQ_STS",			BIT(31)},
+	{}
+};
+
+const struct pmc_bit_map arl_pchs_signal_status_map[] = {
+	{"LSX_Wake0_STS",		BIT(0)},
+	{"LSX_Wake1_STS",		BIT(1)},
+	{"LSX_Wake2_STS",		BIT(2)},
+	{"LSX_Wake3_STS",		BIT(3)},
+	{"LSX_Wake4_STS",		BIT(4)},
+	{"LSX_Wake5_STS",		BIT(5)},
+	{"LSX_Wake6_STS",		BIT(6)},
+	{"LSX_Wake7_STS",		BIT(7)},
+	{"Int_Timer_SS_Wake0_STS",	BIT(8)},
+	{"Int_Timer_SS_Wake1_STS",	BIT(9)},
+	{"Int_Timer_SS_Wake0_STS",	BIT(10)},
+	{"Int_Timer_SS_Wake1_STS",	BIT(11)},
+	{"Int_Timer_SS_Wake2_STS",	BIT(12)},
+	{"Int_Timer_SS_Wake3_STS",	BIT(13)},
+	{"Int_Timer_SS_Wake4_STS",	BIT(14)},
+	{"Int_Timer_SS_Wake5_STS",	BIT(15)},
+	{}
+};
+
+const struct pmc_bit_map *arl_pchs_lpm_maps[] = {
+	arl_pchs_clocksource_status_map,
+	arl_pchs_power_gating_status_0_map,
+	arl_pchs_power_gating_status_1_map,
+	arl_pchs_power_gating_status_2_map,
+	arl_pchs_d3_status_0_map,
+	arl_pchs_d3_status_1_map,
+	arl_pchs_d3_status_2_map,
+	arl_pchs_d3_status_3_map,
+	arl_pchs_vnn_req_status_0_map,
+	arl_pchs_vnn_req_status_1_map,
+	arl_pchs_vnn_req_status_2_map,
+	arl_pchs_vnn_req_status_3_map,
+	arl_pchs_vnn_misc_status_map,
+	arl_pchs_signal_status_map,
+	NULL
+};
+
+const struct pmc_reg_map arl_pchs_reg_map = {
+	.pfear_sts = ext_arl_socs_pfear_map,
+	.ppfear_buckets = ARL_SOCS_PPFEAR_NUM_ENTRIES,
+	.pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT,
+	.ltr_ignore_max = ARL_SOCS_NUM_IP_IGN_ALLOWED,
+	.lpm_sts = arl_pchs_lpm_maps,
+	.ltr_show_sts = arl_pchs_ltr_show_map,
+	.slp_s0_offset = CNP_PMC_SLP_S0_RES_COUNTER_OFFSET,
+	.slp_s0_res_counter_step = TGL_PMC_SLP_S0_RES_COUNTER_STEP,
+	.lpm_res_counter_step_x2 = TGL_PMC_LPM_RES_COUNTER_STEP_X2,
+	.msr_sts = msr_map,
+	.ltr_ignore_offset = CNP_PMC_LTR_IGNORE_OFFSET,
+	.regmap_length = ARL_PCH_PMC_MMIO_REG_LEN,
+	.ppfear0_offset = CNP_PMC_HOST_PPFEAR0A,
+	.pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET,
+	.lpm_priority_offset = MTL_LPM_PRI_OFFSET,
+	.lpm_en_offset = MTL_LPM_EN_OFFSET,
+	.lpm_residency_offset = MTL_LPM_RESIDENCY_OFFSET,
+	.lpm_status_offset = MTL_LPM_STATUS_OFFSET,
+	.lpm_sts_latch_en_offset = MTL_LPM_STATUS_LATCH_EN_OFFSET,
+	.lpm_live_status_offset = MTL_LPM_LIVE_STATUS_OFFSET,
+	.lpm_num_maps = ADL_LPM_NUM_MAPS,
+	.lpm_reg_index = ARL_LPM_REG_INDEX,
+	.etr3_offset = ETR3_OFFSET,
+};
+
+#define PMC_DEVID_SOCS 0xae7f
+#define PMC_DEVID_IOEP 0x7ecf
+#define PMC_DEVID_PCHS 0x7f27
+static struct pmc_info arl_pmc_info_list[] = {
+	{
+		.guid	= IOEP_LPM_REQ_GUID,
+		.devid	= PMC_DEVID_IOEP,
+		.map	= &mtl_ioep_reg_map,
+	},
+	{
+		.guid	= SOCS_LPM_REQ_GUID,
+		.devid	= PMC_DEVID_SOCS,
+		.map	= &arl_socs_reg_map,
+	},
+	{
+		.guid	= PCHS_LPM_REQ_GUID,
+		.devid	= PMC_DEVID_PCHS,
+		.map	= &arl_pchs_reg_map,
+	},
+	{}
+};
+
+#define ARL_NPU_PCI_DEV			0xad1d
+/*
+ * Set power state of select devices that do not have drivers to D3
+ * so that they do not block Package C entry.
+ */
+static void arl_d3_fixup(void)
+{
+	pmc_core_set_device_d3(ARL_NPU_PCI_DEV);
+}
+
+static int arl_resume(struct pmc_dev *pmcdev)
+{
+	arl_d3_fixup();
+	pmc_core_send_ltr_ignore(pmcdev, 3, 0);
+
+	return pmc_core_resume_common(pmcdev);
+}
+
+int arl_core_init(struct pmc_dev *pmcdev)
+{
+	struct pmc *pmc = pmcdev->pmcs[PMC_IDX_SOC];
+	int ret;
+	int func = 0;
+	bool ssram_init = true;
+
+	arl_d3_fixup();
+	pmcdev->suspend = cnl_suspend;
+	pmcdev->resume = arl_resume;
+	pmcdev->regmap_list = arl_pmc_info_list;
+
+	/*
+	 * If ssram init fails use legacy method to at least get the
+	 * primary PMC
+	 */
+	ret = pmc_core_ssram_init(pmcdev, func);
+	if (ret) {
+		ssram_init = false;
+		pmc->map = &arl_socs_reg_map;
+
+		ret = get_primary_reg_base(pmc);
+		if (ret)
+			return ret;
+	}
+
+	pmc_core_get_low_power_modes(pmcdev);
+	pmc_core_punit_pmt_init(pmcdev, ARL_PMT_DMU_GUID);
+
+	if (ssram_init)	{
+		ret = pmc_core_ssram_get_lpm_reqs(pmcdev);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
diff --git a/drivers/platform/x86/intel/pmc/cnp.c b/drivers/platform/x86/intel/pmc/cnp.c
index 420aaa1d7c76..dd72974bf71e 100644
--- a/drivers/platform/x86/intel/pmc/cnp.c
+++ b/drivers/platform/x86/intel/pmc/cnp.c
@@ -204,21 +204,37 @@ const struct pmc_reg_map cnp_reg_map = {
 	.etr3_offset = ETR3_OFFSET,
 };
 
+void cnl_suspend(struct pmc_dev *pmcdev)
+{
+	/*
+	 * Due to a hardware limitation, the GBE LTR blocks PC10
+	 * when a cable is attached. To unblock PC10 during suspend,
+	 * tell the PMC to ignore it.
+	 */
+	pmc_core_send_ltr_ignore(pmcdev, 3, 1);
+}
+
+int cnl_resume(struct pmc_dev *pmcdev)
+{
+	pmc_core_send_ltr_ignore(pmcdev, 3, 0);
+
+	return pmc_core_resume_common(pmcdev);
+}
+
 int cnp_core_init(struct pmc_dev *pmcdev)
 {
 	struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN];
 	int ret;
 
+	pmcdev->suspend = cnl_suspend;
+	pmcdev->resume = cnl_resume;
+
 	pmc->map = &cnp_reg_map;
 	ret = get_primary_reg_base(pmc);
 	if (ret)
 		return ret;
 
-	/* Due to a hardware limitation, the GBE LTR blocks PC10
-	 * when a cable is attached. Tell the PMC to ignore it.
-	 */
-	dev_dbg(&pmcdev->pdev->dev, "ignoring GBE LTR\n");
-	pmc_core_send_ltr_ignore(pmcdev, 3);
+	pmc_core_get_low_power_modes(pmcdev);
 
 	return 0;
 }
diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c
index 84c175b9721a..8f9c036809c7 100644
--- a/drivers/platform/x86/intel/pmc/core.c
+++ b/drivers/platform/x86/intel/pmc/core.c
@@ -20,6 +20,7 @@
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/suspend.h>
+#include <linux/units.h>
 
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
@@ -27,6 +28,7 @@
 #include <asm/tsc.h>
 
 #include "core.h"
+#include "../pmt/telemetry.h"
 
 /* Maximum number of modes supported by platfoms that has low power mode capability */
 const char *pmc_lpm_modes[] = {
@@ -206,6 +208,20 @@ static int pmc_core_dev_state_get(void *data, u64 *val)
 
 DEFINE_DEBUGFS_ATTRIBUTE(pmc_core_dev_state, pmc_core_dev_state_get, NULL, "%llu\n");
 
+static int pmc_core_pson_residency_get(void *data, u64 *val)
+{
+	struct pmc *pmc = data;
+	const struct pmc_reg_map *map = pmc->map;
+	u32 value;
+
+	value = pmc_core_reg_read(pmc, map->pson_residency_offset);
+	*val = (u64)value * map->pson_residency_counter_step;
+
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(pmc_core_pson_residency, pmc_core_pson_residency_get, NULL, "%llu\n");
+
 static int pmc_core_check_read_lock_bit(struct pmc *pmc)
 {
 	u32 value;
@@ -460,7 +476,7 @@ out_unlock:
 }
 DEFINE_SHOW_ATTRIBUTE(pmc_core_pll);
 
-int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value)
+int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value, int ignore)
 {
 	struct pmc *pmc;
 	const struct pmc_reg_map *map;
@@ -472,7 +488,7 @@ int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value)
 	 * is based on the contiguous indexes from ltr_show output.
 	 * pmc index and ltr index needs to be calculated from it.
 	 */
-	for (pmc_index = 0; pmc_index < ARRAY_SIZE(pmcdev->pmcs) && ltr_index > 0; pmc_index++) {
+	for (pmc_index = 0; pmc_index < ARRAY_SIZE(pmcdev->pmcs) && ltr_index >= 0; pmc_index++) {
 		pmc = pmcdev->pmcs[pmc_index];
 
 		if (!pmc)
@@ -498,7 +514,10 @@ int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value)
 	mutex_lock(&pmcdev->lock);
 
 	reg = pmc_core_reg_read(pmc, map->ltr_ignore_offset);
-	reg |= BIT(ltr_index);
+	if (ignore)
+		reg |= BIT(ltr_index);
+	else
+		reg &= ~BIT(ltr_index);
 	pmc_core_reg_write(pmc, map->ltr_ignore_offset, reg);
 
 	mutex_unlock(&pmcdev->lock);
@@ -521,7 +540,7 @@ static ssize_t pmc_core_ltr_ignore_write(struct file *file,
 	if (err)
 		return err;
 
-	err = pmc_core_send_ltr_ignore(pmcdev, value);
+	err = pmc_core_send_ltr_ignore(pmcdev, value, 1);
 
 	return err == 0 ? count : err;
 }
@@ -728,7 +747,7 @@ static int pmc_core_substate_l_sts_regs_show(struct seq_file *s, void *unused)
 }
 DEFINE_SHOW_ATTRIBUTE(pmc_core_substate_l_sts_regs);
 
-static void pmc_core_substate_req_header_show(struct seq_file *s)
+static void pmc_core_substate_req_header_show(struct seq_file *s, int pmc_index)
 {
 	struct pmc_dev *pmcdev = s->private;
 	int i, mode;
@@ -743,71 +762,125 @@ static void pmc_core_substate_req_header_show(struct seq_file *s)
 static int pmc_core_substate_req_regs_show(struct seq_file *s, void *unused)
 {
 	struct pmc_dev *pmcdev = s->private;
-	struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN];
-	const struct pmc_bit_map **maps = pmc->map->lpm_sts;
-	const struct pmc_bit_map *map;
-	const int num_maps = pmc->map->lpm_num_maps;
-	u32 sts_offset = pmc->map->lpm_status_offset;
-	u32 *lpm_req_regs = pmc->lpm_req_regs;
-	int mp;
+	u32 sts_offset;
+	u32 *lpm_req_regs;
+	int num_maps, mp, pmc_index;
+
+	for (pmc_index = 0; pmc_index < ARRAY_SIZE(pmcdev->pmcs); ++pmc_index) {
+		struct pmc *pmc = pmcdev->pmcs[pmc_index];
+		const struct pmc_bit_map **maps;
 
-	/* Display the header */
-	pmc_core_substate_req_header_show(s);
+		if (!pmc)
+			continue;
 
-	/* Loop over maps */
-	for (mp = 0; mp < num_maps; mp++) {
-		u32 req_mask = 0;
-		u32 lpm_status;
-		int mode, idx, i, len = 32;
+		maps = pmc->map->lpm_sts;
+		num_maps = pmc->map->lpm_num_maps;
+		sts_offset = pmc->map->lpm_status_offset;
+		lpm_req_regs = pmc->lpm_req_regs;
 
 		/*
-		 * Capture the requirements and create a mask so that we only
-		 * show an element if it's required for at least one of the
-		 * enabled low power modes
+		 * When there are multiple PMCs, though the PMC may exist, the
+		 * requirement register discovery could have failed so check
+		 * before accessing.
 		 */
-		pmc_for_each_mode(idx, mode, pmcdev)
-			req_mask |= lpm_req_regs[mp + (mode * num_maps)];
-
-		/* Get the last latched status for this map */
-		lpm_status = pmc_core_reg_read(pmc, sts_offset + (mp * 4));
-
-		/*  Loop over elements in this map */
-		map = maps[mp];
-		for (i = 0; map[i].name && i < len; i++) {
-			u32 bit_mask = map[i].bit_mask;
-
-			if (!(bit_mask & req_mask))
-				/*
-				 * Not required for any enabled states
-				 * so don't display
-				 */
-				continue;
-
-			/* Display the element name in the first column */
-			seq_printf(s, "%30s |", map[i].name);
-
-			/* Loop over the enabled states and display if required */
-			pmc_for_each_mode(idx, mode, pmcdev) {
-				if (lpm_req_regs[mp + (mode * num_maps)] & bit_mask)
-					seq_printf(s, " %9s |",
-						   "Required");
-				else
-					seq_printf(s, " %9s |", " ");
+		if (!lpm_req_regs)
+			continue;
+
+		/* Display the header */
+		pmc_core_substate_req_header_show(s, pmc_index);
+
+		/* Loop over maps */
+		for (mp = 0; mp < num_maps; mp++) {
+			u32 req_mask = 0;
+			u32 lpm_status;
+			const struct pmc_bit_map *map;
+			int mode, idx, i, len = 32;
+
+			/*
+			 * Capture the requirements and create a mask so that we only
+			 * show an element if it's required for at least one of the
+			 * enabled low power modes
+			 */
+			pmc_for_each_mode(idx, mode, pmcdev)
+				req_mask |= lpm_req_regs[mp + (mode * num_maps)];
+
+			/* Get the last latched status for this map */
+			lpm_status = pmc_core_reg_read(pmc, sts_offset + (mp * 4));
+
+			/*  Loop over elements in this map */
+			map = maps[mp];
+			for (i = 0; map[i].name && i < len; i++) {
+				u32 bit_mask = map[i].bit_mask;
+
+				if (!(bit_mask & req_mask)) {
+					/*
+					 * Not required for any enabled states
+					 * so don't display
+					 */
+					continue;
+				}
+
+				/* Display the element name in the first column */
+				seq_printf(s, "pmc%d: %26s |", pmc_index, map[i].name);
+
+				/* Loop over the enabled states and display if required */
+				pmc_for_each_mode(idx, mode, pmcdev) {
+					bool required = lpm_req_regs[mp + (mode * num_maps)] &
+							bit_mask;
+					seq_printf(s, " %9s |", required ? "Required" : " ");
+				}
+
+				/* In Status column, show the last captured state of this agent */
+				seq_printf(s, " %9s |", lpm_status & bit_mask ? "Yes" : " ");
+
+				seq_puts(s, "\n");
 			}
+		}
+	}
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(pmc_core_substate_req_regs);
 
-			/* In Status column, show the last captured state of this agent */
-			if (lpm_status & bit_mask)
-				seq_printf(s, " %9s |", "Yes");
-			else
-				seq_printf(s, " %9s |", " ");
+static unsigned int pmc_core_get_crystal_freq(void)
+{
+	unsigned int eax_denominator, ebx_numerator, ecx_hz, edx;
 
-			seq_puts(s, "\n");
-		}
+	if (boot_cpu_data.cpuid_level < 0x15)
+		return 0;
+
+	eax_denominator = ebx_numerator = ecx_hz = edx = 0;
+
+	/* CPUID 15H TSC/Crystal ratio, plus optionally Crystal Hz */
+	cpuid(0x15, &eax_denominator, &ebx_numerator, &ecx_hz, &edx);
+
+	if (ebx_numerator == 0 || eax_denominator == 0)
+		return 0;
+
+	return ecx_hz;
+}
+
+static int pmc_core_die_c6_us_show(struct seq_file *s, void *unused)
+{
+	struct pmc_dev *pmcdev = s->private;
+	u64 die_c6_res, count;
+	int ret;
+
+	if (!pmcdev->crystal_freq) {
+		dev_warn_once(&pmcdev->pdev->dev, "Crystal frequency unavailable\n");
+		return -ENXIO;
 	}
 
+	ret = pmt_telem_read(pmcdev->punit_ep, pmcdev->die_c6_offset,
+			     &count, 1);
+	if (ret)
+		return ret;
+
+	die_c6_res = div64_u64(count * HZ_PER_MHZ, pmcdev->crystal_freq);
+	seq_printf(s, "%llu\n", die_c6_res);
+
 	return 0;
 }
-DEFINE_SHOW_ATTRIBUTE(pmc_core_substate_req_regs);
+DEFINE_SHOW_ATTRIBUTE(pmc_core_die_c6_us);
 
 static int pmc_core_lpm_latch_mode_show(struct seq_file *s, void *unused)
 {
@@ -966,9 +1039,8 @@ static bool pmc_core_pri_verify(u32 lpm_pri, u8 *mode_order)
 	return true;
 }
 
-static void pmc_core_get_low_power_modes(struct platform_device *pdev)
+void pmc_core_get_low_power_modes(struct pmc_dev *pmcdev)
 {
-	struct pmc_dev *pmcdev = platform_get_drvdata(pdev);
 	struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN];
 	u8 pri_order[LPM_MAX_NUM_MODES] = LPM_DEFAULT_PRI;
 	u8 mode_order[LPM_MAX_NUM_MODES];
@@ -1000,7 +1072,8 @@ static void pmc_core_get_low_power_modes(struct platform_device *pdev)
 		for (mode = 0; mode < LPM_MAX_NUM_MODES; mode++)
 			pri_order[mode_order[mode]] = mode;
 	else
-		dev_warn(&pdev->dev, "Assuming a default substate order for this platform\n");
+		dev_warn(&pmcdev->pdev->dev,
+			 "Assuming a default substate order for this platform\n");
 
 	/*
 	 * Loop through all modes from lowest to highest priority,
@@ -1036,6 +1109,69 @@ int get_primary_reg_base(struct pmc *pmc)
 	return 0;
 }
 
+void pmc_core_punit_pmt_init(struct pmc_dev *pmcdev, u32 guid)
+{
+	struct telem_endpoint *ep;
+	struct pci_dev *pcidev;
+
+	pcidev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(10, 0));
+	if (!pcidev) {
+		dev_err(&pmcdev->pdev->dev, "PUNIT PMT device not found.");
+		return;
+	}
+
+	ep = pmt_telem_find_and_register_endpoint(pcidev, guid, 0);
+	pci_dev_put(pcidev);
+	if (IS_ERR(ep)) {
+		dev_err(&pmcdev->pdev->dev,
+			"pmc_core: couldn't get DMU telem endpoint %ld",
+			PTR_ERR(ep));
+		return;
+	}
+
+	pmcdev->punit_ep = ep;
+
+	pmcdev->has_die_c6 = true;
+	pmcdev->die_c6_offset = MTL_PMT_DMU_DIE_C6_OFFSET;
+}
+
+void pmc_core_set_device_d3(unsigned int device)
+{
+	struct pci_dev *pcidev;
+
+	pcidev = pci_get_device(PCI_VENDOR_ID_INTEL, device, NULL);
+	if (pcidev) {
+		if (!device_trylock(&pcidev->dev)) {
+			pci_dev_put(pcidev);
+			return;
+		}
+		if (!pcidev->dev.driver) {
+			dev_info(&pcidev->dev, "Setting to D3hot\n");
+			pci_set_power_state(pcidev, PCI_D3hot);
+		}
+		device_unlock(&pcidev->dev);
+		pci_dev_put(pcidev);
+	}
+}
+
+static bool pmc_core_is_pson_residency_enabled(struct pmc_dev *pmcdev)
+{
+	struct platform_device *pdev = pmcdev->pdev;
+	struct acpi_device *adev = ACPI_COMPANION(&pdev->dev);
+	u8 val;
+
+	if (!adev)
+		return false;
+
+	if (fwnode_property_read_u8(acpi_fwnode_handle(adev),
+				    "intel-cec-pson-switching-enabled-in-s0",
+				    &val))
+		return false;
+
+	return val == 1;
+}
+
+
 static void pmc_core_dbgfs_unregister(struct pmc_dev *pmcdev)
 {
 	debugfs_remove_recursive(pmcdev->dbgfs_dir);
@@ -1105,6 +1241,17 @@ static void pmc_core_dbgfs_register(struct pmc_dev *pmcdev)
 				    pmcdev->dbgfs_dir, pmcdev,
 				    &pmc_core_substate_req_regs_fops);
 	}
+
+	if (primary_pmc->map->pson_residency_offset && pmc_core_is_pson_residency_enabled(pmcdev)) {
+		debugfs_create_file("pson_residency_usec", 0444,
+				    pmcdev->dbgfs_dir, primary_pmc, &pmc_core_pson_residency);
+	}
+
+	if (pmcdev->has_die_c6) {
+		debugfs_create_file("die_c6_us_show", 0444,
+				    pmcdev->dbgfs_dir, pmcdev,
+				    &pmc_core_die_c6_us_fops);
+	}
 }
 
 static const struct x86_cpu_id intel_pmc_core_ids[] = {
@@ -1117,18 +1264,20 @@ static const struct x86_cpu_id intel_pmc_core_ids[] = {
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_NNPI,	icl_core_init),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		cnp_core_init),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		cnp_core_init),
-	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L,		tgl_core_init),
+	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L,		tgl_l_core_init),
 	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE,		tgl_core_init),
-	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT,	tgl_core_init),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT,	tgl_l_core_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L,	icl_core_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE,		tgl_core_init),
-	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		tgl_core_init),
-	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,	tgl_core_init),
+	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		tgl_l_core_init),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,	tgl_l_core_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		adl_core_init),
-	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,        tgl_core_init),
+	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,        tgl_l_core_init),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE,		adl_core_init),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S,	adl_core_init),
 	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L,	mtl_core_init),
+	X86_MATCH_INTEL_FAM6_MODEL(ARROWLAKE,		arl_core_init),
+	X86_MATCH_INTEL_FAM6_MODEL(LUNARLAKE_M,         lnl_core_init),
 	{}
 };
 
@@ -1199,6 +1348,10 @@ static void pmc_core_clean_structure(struct platform_device *pdev)
 		pci_dev_put(pmcdev->ssram_pcidev);
 		pci_disable_device(pmcdev->ssram_pcidev);
 	}
+
+	if (pmcdev->punit_ep)
+		pmt_telem_unregister_endpoint(pmcdev->punit_ep);
+
 	platform_set_drvdata(pdev, NULL);
 	mutex_destroy(&pmcdev->lock);
 }
@@ -1219,6 +1372,8 @@ static int pmc_core_probe(struct platform_device *pdev)
 	if (!pmcdev)
 		return -ENOMEM;
 
+	pmcdev->crystal_freq = pmc_core_get_crystal_freq();
+
 	platform_set_drvdata(pdev, pmcdev);
 	pmcdev->pdev = pdev;
 
@@ -1250,7 +1405,6 @@ static int pmc_core_probe(struct platform_device *pdev)
 	}
 
 	pmcdev->pmc_xram_read_bit = pmc_core_check_read_lock_bit(primary_pmc);
-	pmc_core_get_low_power_modes(pdev);
 	pmc_core_do_dmi_quirks(primary_pmc);
 
 	pmc_core_dbgfs_register(pmcdev);
@@ -1279,6 +1433,9 @@ static __maybe_unused int pmc_core_suspend(struct device *dev)
 	struct pmc_dev *pmcdev = dev_get_drvdata(dev);
 	struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN];
 
+	if (pmcdev->suspend)
+		pmcdev->suspend(pmcdev);
+
 	/* Check if the syspend will actually use S0ix */
 	if (pm_suspend_via_firmware())
 		return 0;
diff --git a/drivers/platform/x86/intel/pmc/core.h b/drivers/platform/x86/intel/pmc/core.h
index 0729f593c6a7..54137faaae2b 100644
--- a/drivers/platform/x86/intel/pmc/core.h
+++ b/drivers/platform/x86/intel/pmc/core.h
@@ -16,6 +16,8 @@
 #include <linux/bits.h>
 #include <linux/platform_device.h>
 
+struct telem_endpoint;
+
 #define SLP_S0_RES_COUNTER_MASK			GENMASK(31, 0)
 
 #define PMC_BASE_ADDR_DEFAULT			0xFE000000
@@ -221,6 +223,10 @@ enum ppfear_regs {
 #define TGL_LPM_PRI_OFFSET			0x1C7C
 #define TGL_LPM_NUM_MAPS			6
 
+/* Tigerlake PSON residency register */
+#define TGL_PSON_RESIDENCY_OFFSET		0x18f8
+#define TGL_PSON_RES_COUNTER_STEP		0x7A
+
 /* Extended Test Mode Register 3 (CNL and later) */
 #define ETR3_OFFSET				0x1048
 #define ETR3_CF9GR				BIT(20)
@@ -257,10 +263,25 @@ enum ppfear_regs {
 #define MTL_SOCM_NUM_IP_IGN_ALLOWED		25
 #define MTL_SOC_PMC_MMIO_REG_LEN		0x2708
 #define MTL_PMC_LTR_SPG				0x1B74
+#define ARL_SOCS_PMC_LTR_RESERVED		0x1B88
+#define ARL_SOCS_NUM_IP_IGN_ALLOWED		26
+#define ARL_PMC_LTR_DMI3			0x1BE4
+#define ARL_PCH_PMC_MMIO_REG_LEN		0x2720
 
 /* Meteor Lake PGD PFET Enable Ack Status */
 #define MTL_SOCM_PPFEAR_NUM_ENTRIES		8
 #define MTL_IOE_PPFEAR_NUM_ENTRIES		10
+#define ARL_SOCS_PPFEAR_NUM_ENTRIES		9
+
+/* Die C6 from PUNIT telemetry */
+#define MTL_PMT_DMU_DIE_C6_OFFSET		15
+#define MTL_PMT_DMU_GUID			0x1A067102
+#define ARL_PMT_DMU_GUID			0x1A06A000
+
+#define LNL_PMC_MMIO_REG_LEN			0x2708
+#define LNL_PMC_LTR_OSSE			0x1B88
+#define LNL_NUM_IP_IGN_ALLOWED			27
+#define LNL_PPFEAR_NUM_ENTRIES			12
 
 extern const char *pmc_lpm_modes[];
 
@@ -320,6 +341,9 @@ struct pmc_reg_map {
 	const u32 lpm_status_offset;
 	const u32 lpm_live_status_offset;
 	const u32 etr3_offset;
+	const u8  *lpm_reg_index;
+	const u32 pson_residency_offset;
+	const u32 pson_residency_counter_step;
 };
 
 /**
@@ -329,6 +353,7 @@ struct pmc_reg_map {
  *			specific attributes
  */
 struct pmc_info {
+	u32 guid;
 	u16 devid;
 	const struct pmc_reg_map *map;
 };
@@ -355,6 +380,7 @@ struct pmc {
  * @devs:		pointer to an array of pmc pointers
  * @pdev:		pointer to platform_device struct
  * @ssram_pcidev:	pointer to pci device struct for the PMC SSRAM
+ * @crystal_freq:	crystal frequency from cpuid
  * @dbgfs_dir:		path to debugfs interface
  * @pmc_xram_read_bit:	flag to indicate whether PMC XRAM shadow registers
  *			used to read MPHY PG and PLL status are available
@@ -363,6 +389,7 @@ struct pmc {
  * @s0ix_counter:	S0ix residency (step adjusted)
  * @num_lpm_modes:	Count of enabled modes
  * @lpm_en_modes:	Array of enabled modes from lowest to highest priority
+ * @suspend:		Function to perform platform specific suspend
  * @resume:		Function to perform platform specific resume
  *
  * pmc_dev contains info about power management controller device.
@@ -372,6 +399,7 @@ struct pmc_dev {
 	struct dentry *dbgfs_dir;
 	struct platform_device *pdev;
 	struct pci_dev *ssram_pcidev;
+	unsigned int crystal_freq;
 	int pmc_xram_read_bit;
 	struct mutex lock; /* generic mutex lock for PMC Core */
 
@@ -379,6 +407,7 @@ struct pmc_dev {
 	u64 s0ix_counter;
 	int num_lpm_modes;
 	int lpm_en_modes[LPM_MAX_NUM_MODES];
+	void (*suspend)(struct pmc_dev *pmcdev);
 	int (*resume)(struct pmc_dev *pmcdev);
 
 	bool has_die_c6;
@@ -423,6 +452,7 @@ extern const struct pmc_bit_map tgl_vnn_misc_status_map[];
 extern const struct pmc_bit_map tgl_signal_status_map[];
 extern const struct pmc_bit_map *tgl_lpm_maps[];
 extern const struct pmc_reg_map tgl_reg_map;
+extern const struct pmc_reg_map tgl_h_reg_map;
 extern const struct pmc_bit_map adl_pfear_map[];
 extern const struct pmc_bit_map *ext_adl_pfear_map[];
 extern const struct pmc_bit_map adl_ltr_show_map[];
@@ -484,21 +514,83 @@ extern const struct pmc_bit_map mtl_ioem_power_gating_status_1_map[];
 extern const struct pmc_bit_map mtl_ioem_vnn_req_status_1_map[];
 extern const struct pmc_bit_map *mtl_ioem_lpm_maps[];
 extern const struct pmc_reg_map mtl_ioem_reg_map;
+extern const struct pmc_reg_map lnl_socm_reg_map;
+
+/* LNL */
+extern const struct pmc_bit_map lnl_ltr_show_map[];
+extern const struct pmc_bit_map lnl_clocksource_status_map[];
+extern const struct pmc_bit_map lnl_power_gating_status_0_map[];
+extern const struct pmc_bit_map lnl_power_gating_status_1_map[];
+extern const struct pmc_bit_map lnl_power_gating_status_2_map[];
+extern const struct pmc_bit_map lnl_d3_status_0_map[];
+extern const struct pmc_bit_map lnl_d3_status_1_map[];
+extern const struct pmc_bit_map lnl_d3_status_2_map[];
+extern const struct pmc_bit_map lnl_d3_status_3_map[];
+extern const struct pmc_bit_map lnl_vnn_req_status_0_map[];
+extern const struct pmc_bit_map lnl_vnn_req_status_1_map[];
+extern const struct pmc_bit_map lnl_vnn_req_status_2_map[];
+extern const struct pmc_bit_map lnl_vnn_req_status_3_map[];
+extern const struct pmc_bit_map lnl_vnn_misc_status_map[];
+extern const struct pmc_bit_map *lnl_lpm_maps[];
+extern const struct pmc_bit_map lnl_pfear_map[];
+extern const struct pmc_bit_map *ext_lnl_pfear_map[];
+
+/* ARL */
+extern const struct pmc_bit_map arl_socs_ltr_show_map[];
+extern const struct pmc_bit_map arl_socs_clocksource_status_map[];
+extern const struct pmc_bit_map arl_socs_power_gating_status_0_map[];
+extern const struct pmc_bit_map arl_socs_power_gating_status_1_map[];
+extern const struct pmc_bit_map arl_socs_power_gating_status_2_map[];
+extern const struct pmc_bit_map arl_socs_d3_status_2_map[];
+extern const struct pmc_bit_map arl_socs_d3_status_3_map[];
+extern const struct pmc_bit_map arl_socs_vnn_req_status_3_map[];
+extern const struct pmc_bit_map *arl_socs_lpm_maps[];
+extern const struct pmc_bit_map arl_socs_pfear_map[];
+extern const struct pmc_bit_map *ext_arl_socs_pfear_map[];
+extern const struct pmc_reg_map arl_socs_reg_map;
+extern const struct pmc_bit_map arl_pchs_ltr_show_map[];
+extern const struct pmc_bit_map arl_pchs_clocksource_status_map[];
+extern const struct pmc_bit_map arl_pchs_power_gating_status_0_map[];
+extern const struct pmc_bit_map arl_pchs_power_gating_status_1_map[];
+extern const struct pmc_bit_map arl_pchs_power_gating_status_2_map[];
+extern const struct pmc_bit_map arl_pchs_d3_status_0_map[];
+extern const struct pmc_bit_map arl_pchs_d3_status_1_map[];
+extern const struct pmc_bit_map arl_pchs_d3_status_2_map[];
+extern const struct pmc_bit_map arl_pchs_d3_status_3_map[];
+extern const struct pmc_bit_map arl_pchs_vnn_req_status_0_map[];
+extern const struct pmc_bit_map arl_pchs_vnn_req_status_1_map[];
+extern const struct pmc_bit_map arl_pchs_vnn_req_status_2_map[];
+extern const struct pmc_bit_map arl_pchs_vnn_req_status_3_map[];
+extern const struct pmc_bit_map arl_pchs_vnn_misc_status_map[];
+extern const struct pmc_bit_map arl_pchs_signal_status_map[];
+extern const struct pmc_bit_map *arl_pchs_lpm_maps[];
+extern const struct pmc_reg_map arl_pchs_reg_map;
 
 extern void pmc_core_get_tgl_lpm_reqs(struct platform_device *pdev);
-extern int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value);
+extern int pmc_core_ssram_get_lpm_reqs(struct pmc_dev *pmcdev);
+int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value, int ignore);
 
 int pmc_core_resume_common(struct pmc_dev *pmcdev);
 int get_primary_reg_base(struct pmc *pmc);
+extern void pmc_core_get_low_power_modes(struct pmc_dev *pmcdev);
+extern void pmc_core_punit_pmt_init(struct pmc_dev *pmcdev, u32 guid);
+extern void pmc_core_set_device_d3(unsigned int device);
 
-extern void pmc_core_ssram_init(struct pmc_dev *pmcdev);
+extern int pmc_core_ssram_init(struct pmc_dev *pmcdev, int func);
 
 int spt_core_init(struct pmc_dev *pmcdev);
 int cnp_core_init(struct pmc_dev *pmcdev);
 int icl_core_init(struct pmc_dev *pmcdev);
 int tgl_core_init(struct pmc_dev *pmcdev);
+int tgl_l_core_init(struct pmc_dev *pmcdev);
+int tgl_core_generic_init(struct pmc_dev *pmcdev, int pch_tp);
 int adl_core_init(struct pmc_dev *pmcdev);
 int mtl_core_init(struct pmc_dev *pmcdev);
+int arl_core_init(struct pmc_dev *pmcdev);
+int lnl_core_init(struct pmc_dev *pmcdev);
+
+void cnl_suspend(struct pmc_dev *pmcdev);
+int cnl_resume(struct pmc_dev *pmcdev);
 
 #define pmc_for_each_mode(i, mode, pmcdev)		\
 	for (i = 0, mode = pmcdev->lpm_en_modes[i];	\
diff --git a/drivers/platform/x86/intel/pmc/core_ssram.c b/drivers/platform/x86/intel/pmc/core_ssram.c
index 13fa16f0d52e..1bde86c54eb9 100644
--- a/drivers/platform/x86/intel/pmc/core_ssram.c
+++ b/drivers/platform/x86/intel/pmc/core_ssram.c
@@ -8,10 +8,13 @@
  *
  */
 
+#include <linux/cleanup.h>
 #include <linux/pci.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 
 #include "core.h"
+#include "../vsec.h"
+#include "../pmt/telemetry.h"
 
 #define SSRAM_HDR_SIZE		0x100
 #define SSRAM_PWRM_OFFSET	0x14
@@ -21,6 +24,185 @@
 #define SSRAM_IOE_OFFSET	0x68
 #define SSRAM_DEVID_OFFSET	0x70
 
+/* PCH query */
+#define LPM_HEADER_OFFSET	1
+#define LPM_REG_COUNT		28
+#define LPM_MODE_OFFSET		1
+
+DEFINE_FREE(pmc_core_iounmap, void __iomem *, iounmap(_T));
+
+static u32 pmc_core_find_guid(struct pmc_info *list, const struct pmc_reg_map *map)
+{
+	for (; list->map; ++list)
+		if (list->map == map)
+			return list->guid;
+
+	return 0;
+}
+
+static int pmc_core_get_lpm_req(struct pmc_dev *pmcdev, struct pmc *pmc)
+{
+	struct telem_endpoint *ep;
+	const u8 *lpm_indices;
+	int num_maps, mode_offset = 0;
+	int ret, mode, i;
+	int lpm_size;
+	u32 guid;
+
+	lpm_indices = pmc->map->lpm_reg_index;
+	num_maps = pmc->map->lpm_num_maps;
+	lpm_size = LPM_MAX_NUM_MODES * num_maps;
+
+	guid = pmc_core_find_guid(pmcdev->regmap_list, pmc->map);
+	if (!guid)
+		return -ENXIO;
+
+	ep = pmt_telem_find_and_register_endpoint(pmcdev->ssram_pcidev, guid, 0);
+	if (IS_ERR(ep)) {
+		dev_dbg(&pmcdev->pdev->dev, "couldn't get telem endpoint %ld",
+			PTR_ERR(ep));
+		return -EPROBE_DEFER;
+	}
+
+	pmc->lpm_req_regs = devm_kzalloc(&pmcdev->pdev->dev,
+					 lpm_size * sizeof(u32),
+					 GFP_KERNEL);
+	if (!pmc->lpm_req_regs) {
+		ret = -ENOMEM;
+		goto unregister_ep;
+	}
+
+	/*
+	 * PMC Low Power Mode (LPM) table
+	 *
+	 * In telemetry space, the LPM table contains a 4 byte header followed
+	 * by 8 consecutive mode blocks (one for each LPM mode). Each block
+	 * has a 4 byte header followed by a set of registers that describe the
+	 * IP state requirements for the given mode. The IP mapping is platform
+	 * specific but the same for each block, making for easy analysis.
+	 * Platforms only use a subset of the space to track the requirements
+	 * for their IPs. Callers provide the requirement registers they use as
+	 * a list of indices. Each requirement register is associated with an
+	 * IP map that's maintained by the caller.
+	 *
+	 * Header
+	 * +----+----------------------------+----------------------------+
+	 * |  0 |      REVISION              |      ENABLED MODES         |
+	 * +----+--------------+-------------+-------------+--------------+
+	 *
+	 * Low Power Mode 0 Block
+	 * +----+--------------+-------------+-------------+--------------+
+	 * |  1 |     SUB ID   |     SIZE    |   MAJOR     |   MINOR      |
+	 * +----+--------------+-------------+-------------+--------------+
+	 * |  2 |           LPM0 Requirements 0                           |
+	 * +----+---------------------------------------------------------+
+	 * |    |                  ...                                    |
+	 * +----+---------------------------------------------------------+
+	 * | 29 |           LPM0 Requirements 27                          |
+	 * +----+---------------------------------------------------------+
+	 *
+	 * ...
+	 *
+	 * Low Power Mode 7 Block
+	 * +----+--------------+-------------+-------------+--------------+
+	 * |    |     SUB ID   |     SIZE    |   MAJOR     |   MINOR      |
+	 * +----+--------------+-------------+-------------+--------------+
+	 * | 60 |           LPM7 Requirements 0                           |
+	 * +----+---------------------------------------------------------+
+	 * |    |                  ...                                    |
+	 * +----+---------------------------------------------------------+
+	 * | 87 |           LPM7 Requirements 27                          |
+	 * +----+---------------------------------------------------------+
+	 *
+	 */
+	mode_offset = LPM_HEADER_OFFSET + LPM_MODE_OFFSET;
+	pmc_for_each_mode(i, mode, pmcdev) {
+		u32 *req_offset = pmc->lpm_req_regs + (mode * num_maps);
+		int m;
+
+		for (m = 0; m < num_maps; m++) {
+			u8 sample_id = lpm_indices[m] + mode_offset;
+
+			ret = pmt_telem_read32(ep, sample_id, req_offset, 1);
+			if (ret) {
+				dev_err(&pmcdev->pdev->dev,
+					"couldn't read Low Power Mode requirements: %d\n", ret);
+				devm_kfree(&pmcdev->pdev->dev, pmc->lpm_req_regs);
+				goto unregister_ep;
+			}
+			++req_offset;
+		}
+		mode_offset += LPM_REG_COUNT + LPM_MODE_OFFSET;
+	}
+
+unregister_ep:
+	pmt_telem_unregister_endpoint(ep);
+
+	return ret;
+}
+
+int pmc_core_ssram_get_lpm_reqs(struct pmc_dev *pmcdev)
+{
+	int ret, i;
+
+	if (!pmcdev->ssram_pcidev)
+		return -ENODEV;
+
+	for (i = 0; i < ARRAY_SIZE(pmcdev->pmcs); ++i) {
+		if (!pmcdev->pmcs[i])
+			continue;
+
+		ret = pmc_core_get_lpm_req(pmcdev, pmcdev->pmcs[i]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void
+pmc_add_pmt(struct pmc_dev *pmcdev, u64 ssram_base, void __iomem *ssram)
+{
+	struct pci_dev *pcidev = pmcdev->ssram_pcidev;
+	struct intel_vsec_platform_info info = {};
+	struct intel_vsec_header *headers[2] = {};
+	struct intel_vsec_header header;
+	void __iomem *dvsec;
+	u32 dvsec_offset;
+	u32 table, hdr;
+
+	ssram = ioremap(ssram_base, SSRAM_HDR_SIZE);
+	if (!ssram)
+		return;
+
+	dvsec_offset = readl(ssram + SSRAM_DVSEC_OFFSET);
+	iounmap(ssram);
+
+	dvsec = ioremap(ssram_base + dvsec_offset, SSRAM_DVSEC_SIZE);
+	if (!dvsec)
+		return;
+
+	hdr = readl(dvsec + PCI_DVSEC_HEADER1);
+	header.id = readw(dvsec + PCI_DVSEC_HEADER2);
+	header.rev = PCI_DVSEC_HEADER1_REV(hdr);
+	header.length = PCI_DVSEC_HEADER1_LEN(hdr);
+	header.num_entries = readb(dvsec + INTEL_DVSEC_ENTRIES);
+	header.entry_size = readb(dvsec + INTEL_DVSEC_SIZE);
+
+	table = readl(dvsec + INTEL_DVSEC_TABLE);
+	header.tbir = INTEL_DVSEC_TABLE_BAR(table);
+	header.offset = INTEL_DVSEC_TABLE_OFFSET(table);
+	iounmap(dvsec);
+
+	headers[0] = &header;
+	info.caps = VSEC_CAP_TELEMETRY;
+	info.headers = headers;
+	info.base_addr = ssram_base;
+	info.parent = &pmcdev->pdev->dev;
+
+	intel_vsec_register(pcidev, &info);
+}
+
 static const struct pmc_reg_map *pmc_core_find_regmap(struct pmc_info *list, u16 devid)
 {
 	for (; list->map; ++list)
@@ -35,20 +217,20 @@ static inline u64 get_base(void __iomem *addr, u32 offset)
 	return lo_hi_readq(addr + offset) & GENMASK_ULL(63, 3);
 }
 
-static void
+static int
 pmc_core_pmc_add(struct pmc_dev *pmcdev, u64 pwrm_base,
 		 const struct pmc_reg_map *reg_map, int pmc_index)
 {
 	struct pmc *pmc = pmcdev->pmcs[pmc_index];
 
 	if (!pwrm_base)
-		return;
+		return -ENODEV;
 
 	/* Memory for primary PMC has been allocated in core.c */
 	if (!pmc) {
 		pmc = devm_kzalloc(&pmcdev->pdev->dev, sizeof(*pmc), GFP_KERNEL);
 		if (!pmc)
-			return;
+			return -ENOMEM;
 	}
 
 	pmc->map = reg_map;
@@ -57,77 +239,88 @@ pmc_core_pmc_add(struct pmc_dev *pmcdev, u64 pwrm_base,
 
 	if (!pmc->regbase) {
 		devm_kfree(&pmcdev->pdev->dev, pmc);
-		return;
+		return -ENOMEM;
 	}
 
 	pmcdev->pmcs[pmc_index] = pmc;
+
+	return 0;
 }
 
-static void
-pmc_core_ssram_get_pmc(struct pmc_dev *pmcdev, void __iomem *ssram, u32 offset,
-		       int pmc_idx)
+static int
+pmc_core_ssram_get_pmc(struct pmc_dev *pmcdev, int pmc_idx, u32 offset)
 {
-	u64 pwrm_base;
+	struct pci_dev *ssram_pcidev = pmcdev->ssram_pcidev;
+	void __iomem __free(pmc_core_iounmap) *tmp_ssram = NULL;
+	void __iomem __free(pmc_core_iounmap) *ssram = NULL;
+	const struct pmc_reg_map *map;
+	u64 ssram_base, pwrm_base;
 	u16 devid;
 
-	if (pmc_idx != PMC_IDX_SOC) {
-		u64 ssram_base = get_base(ssram, offset);
+	if (!pmcdev->regmap_list)
+		return -ENOENT;
 
-		if (!ssram_base)
-			return;
+	ssram_base = ssram_pcidev->resource[0].start;
+	tmp_ssram = ioremap(ssram_base, SSRAM_HDR_SIZE);
 
+	if (pmc_idx != PMC_IDX_MAIN) {
+		/*
+		 * The secondary PMC BARS (which are behind hidden PCI devices)
+		 * are read from fixed offsets in MMIO of the primary PMC BAR.
+		 */
+		ssram_base = get_base(tmp_ssram, offset);
 		ssram = ioremap(ssram_base, SSRAM_HDR_SIZE);
 		if (!ssram)
-			return;
+			return -ENOMEM;
+
+	} else {
+		ssram = no_free_ptr(tmp_ssram);
 	}
 
 	pwrm_base = get_base(ssram, SSRAM_PWRM_OFFSET);
 	devid = readw(ssram + SSRAM_DEVID_OFFSET);
 
-	if (pmcdev->regmap_list) {
-		const struct pmc_reg_map *map;
+	/* Find and register and PMC telemetry entries */
+	pmc_add_pmt(pmcdev, ssram_base, ssram);
 
-		map = pmc_core_find_regmap(pmcdev->regmap_list, devid);
-		if (map)
-			pmc_core_pmc_add(pmcdev, pwrm_base, map, pmc_idx);
-	}
+	map = pmc_core_find_regmap(pmcdev->regmap_list, devid);
+	if (!map)
+		return -ENODEV;
 
-	if (pmc_idx != PMC_IDX_SOC)
-		iounmap(ssram);
+	return pmc_core_pmc_add(pmcdev, pwrm_base, map, pmc_idx);
 }
 
-void pmc_core_ssram_init(struct pmc_dev *pmcdev)
+int pmc_core_ssram_init(struct pmc_dev *pmcdev, int func)
 {
-	void __iomem *ssram;
 	struct pci_dev *pcidev;
-	u64 ssram_base;
 	int ret;
 
-	pcidev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(20, 2));
+	pcidev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(20, func));
 	if (!pcidev)
-		goto out;
+		return -ENODEV;
 
 	ret = pcim_enable_device(pcidev);
 	if (ret)
 		goto release_dev;
 
-	ssram_base = pcidev->resource[0].start;
-	ssram = ioremap(ssram_base, SSRAM_HDR_SIZE);
-	if (!ssram)
-		goto disable_dev;
-
 	pmcdev->ssram_pcidev = pcidev;
 
-	pmc_core_ssram_get_pmc(pmcdev, ssram, 0, PMC_IDX_SOC);
-	pmc_core_ssram_get_pmc(pmcdev, ssram, SSRAM_IOE_OFFSET, PMC_IDX_IOE);
-	pmc_core_ssram_get_pmc(pmcdev, ssram, SSRAM_PCH_OFFSET, PMC_IDX_PCH);
+	ret = pmc_core_ssram_get_pmc(pmcdev, PMC_IDX_MAIN, 0);
+	if (ret)
+		goto disable_dev;
 
-	iounmap(ssram);
-out:
-	return;
+	pmc_core_ssram_get_pmc(pmcdev, PMC_IDX_IOE, SSRAM_IOE_OFFSET);
+	pmc_core_ssram_get_pmc(pmcdev, PMC_IDX_PCH, SSRAM_PCH_OFFSET);
+
+	return 0;
 
 disable_dev:
+	pmcdev->ssram_pcidev = NULL;
 	pci_disable_device(pcidev);
 release_dev:
 	pci_dev_put(pcidev);
+
+	return ret;
 }
+MODULE_IMPORT_NS(INTEL_VSEC);
+MODULE_IMPORT_NS(INTEL_PMT_TELEMETRY);
diff --git a/drivers/platform/x86/intel/pmc/icl.c b/drivers/platform/x86/intel/pmc/icl.c
index d08e3174230d..71b0fd6cb7d8 100644
--- a/drivers/platform/x86/intel/pmc/icl.c
+++ b/drivers/platform/x86/intel/pmc/icl.c
@@ -53,7 +53,15 @@ const struct pmc_reg_map icl_reg_map = {
 int icl_core_init(struct pmc_dev *pmcdev)
 {
 	struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN];
+	int ret;
 
 	pmc->map = &icl_reg_map;
-	return get_primary_reg_base(pmc);
+
+	ret = get_primary_reg_base(pmc);
+	if (ret)
+		return ret;
+
+	pmc_core_get_low_power_modes(pmcdev);
+
+	return ret;
 }
diff --git a/drivers/platform/x86/intel/pmc/lnl.c b/drivers/platform/x86/intel/pmc/lnl.c
new file mode 100644
index 000000000000..abad17cdd3d7
--- /dev/null
+++ b/drivers/platform/x86/intel/pmc/lnl.c
@@ -0,0 +1,549 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This file contains platform specific structure definitions
+ * and init function used by Meteor Lake PCH.
+ *
+ * Copyright (c) 2022, Intel Corporation.
+ * All Rights Reserved.
+ *
+ */
+
+#include <linux/cpu.h>
+#include <linux/pci.h>
+
+#include "core.h"
+
+#define SOCM_LPM_REQ_GUID	0x11594920
+
+#define PMC_DEVID_SOCM	0xa87f
+
+static const u8 LNL_LPM_REG_INDEX[] = {0, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 15, 16, 20};
+
+static struct pmc_info lnl_pmc_info_list[] = {
+	{
+		.guid	= SOCM_LPM_REQ_GUID,
+		.devid	= PMC_DEVID_SOCM,
+		.map	= &lnl_socm_reg_map,
+	},
+	{}
+};
+
+const struct pmc_bit_map lnl_ltr_show_map[] = {
+	{"SOUTHPORT_A",		CNP_PMC_LTR_SPA},
+	{"SOUTHPORT_B",		CNP_PMC_LTR_SPB},
+	{"SATA",		CNP_PMC_LTR_SATA},
+	{"GIGABIT_ETHERNET",	CNP_PMC_LTR_GBE},
+	{"XHCI",		CNP_PMC_LTR_XHCI},
+	{"SOUTHPORT_F",		ADL_PMC_LTR_SPF},
+	{"ME",			CNP_PMC_LTR_ME},
+	/* EVA is Enterprise Value Add, doesn't really exist on PCH */
+	{"SATA1",		CNP_PMC_LTR_EVA},
+	{"SOUTHPORT_C",		CNP_PMC_LTR_SPC},
+	{"HD_AUDIO",		CNP_PMC_LTR_AZ},
+	{"CNV",			CNP_PMC_LTR_CNV},
+	{"LPSS",		CNP_PMC_LTR_LPSS},
+	{"SOUTHPORT_D",		CNP_PMC_LTR_SPD},
+	{"SOUTHPORT_E",		CNP_PMC_LTR_SPE},
+	{"SATA2",		CNP_PMC_LTR_CAM},
+	{"ESPI",		CNP_PMC_LTR_ESPI},
+	{"SCC",			CNP_PMC_LTR_SCC},
+	{"ISH",			CNP_PMC_LTR_ISH},
+	{"UFSX2",		CNP_PMC_LTR_UFSX2},
+	{"EMMC",		CNP_PMC_LTR_EMMC},
+	/*
+	 * Check intel_pmc_core_ids[] users of cnp_reg_map for
+	 * a list of core SoCs using this.
+	 */
+	{"WIGIG",		ICL_PMC_LTR_WIGIG},
+	{"THC0",		TGL_PMC_LTR_THC0},
+	{"THC1",		TGL_PMC_LTR_THC1},
+	{"SOUTHPORT_G",		CNP_PMC_LTR_RESERVED},
+
+	{"ESE",			MTL_PMC_LTR_ESE},
+	{"IOE_PMC",		MTL_PMC_LTR_IOE_PMC},
+	{"DMI3",		ARL_PMC_LTR_DMI3},
+	{"OSSE",		LNL_PMC_LTR_OSSE},
+
+	/* Below two cannot be used for LTR_IGNORE */
+	{"CURRENT_PLATFORM",	CNP_PMC_LTR_CUR_PLT},
+	{"AGGREGATED_SYSTEM",	CNP_PMC_LTR_CUR_ASLT},
+	{}
+};
+
+const struct pmc_bit_map lnl_power_gating_status_0_map[] = {
+	{"PMC_PGD0_PG_STS",			BIT(0)},
+	{"FUSE_OSSE_PGD0_PG_STS",		BIT(1)},
+	{"ESPISPI_PGD0_PG_STS",			BIT(2)},
+	{"XHCI_PGD0_PG_STS",			BIT(3)},
+	{"SPA_PGD0_PG_STS",			BIT(4)},
+	{"SPB_PGD0_PG_STS",			BIT(5)},
+	{"SPR16B0_PGD0_PG_STS",			BIT(6)},
+	{"GBE_PGD0_PG_STS",			BIT(7)},
+	{"SBR8B7_PGD0_PG_STS",			BIT(8)},
+	{"SBR8B6_PGD0_PG_STS",			BIT(9)},
+	{"SBR16B1_PGD0_PG_STS",			BIT(10)},
+	{"SBR8B8_PGD0_PG_STS",			BIT(11)},
+	{"ESE_PGD3_PG_STS",			BIT(12)},
+	{"D2D_DISP_PGD0_PG_STS",		BIT(13)},
+	{"LPSS_PGD0_PG_STS",			BIT(14)},
+	{"LPC_PGD0_PG_STS",			BIT(15)},
+	{"SMB_PGD0_PG_STS",			BIT(16)},
+	{"ISH_PGD0_PG_STS",			BIT(17)},
+	{"SBR8B2_PGD0_PG_STS",			BIT(18)},
+	{"NPK_PGD0_PG_STS",			BIT(19)},
+	{"D2D_NOC_PGD0_PG_STS",			BIT(20)},
+	{"SAFSS_PGD0_PG_STS",			BIT(21)},
+	{"FUSE_PGD0_PG_STS",			BIT(22)},
+	{"D2D_DISP_PGD1_PG_STS",		BIT(23)},
+	{"MPFPW1_PGD0_PG_STS",			BIT(24)},
+	{"XDCI_PGD0_PG_STS",			BIT(25)},
+	{"EXI_PGD0_PG_STS",			BIT(26)},
+	{"CSE_PGD0_PG_STS",			BIT(27)},
+	{"KVMCC_PGD0_PG_STS",			BIT(28)},
+	{"PMT_PGD0_PG_STS",			BIT(29)},
+	{"CLINK_PGD0_PG_STS",			BIT(30)},
+	{"PTIO_PGD0_PG_STS",			BIT(31)},
+	{}
+};
+
+const struct pmc_bit_map lnl_power_gating_status_1_map[] = {
+	{"USBR0_PGD0_PG_STS",			BIT(0)},
+	{"SUSRAM_PGD0_PG_STS",			BIT(1)},
+	{"SMT1_PGD0_PG_STS",			BIT(2)},
+	{"U3FPW1_PGD0_PG_STS",			BIT(3)},
+	{"SMS2_PGD0_PG_STS",			BIT(4)},
+	{"SMS1_PGD0_PG_STS",			BIT(5)},
+	{"CSMERTC_PGD0_PG_STS",			BIT(6)},
+	{"CSMEPSF_PGD0_PG_STS",			BIT(7)},
+	{"FIA_PG_PGD0_PG_STS",			BIT(8)},
+	{"SBR16B4_PGD0_PG_STS",			BIT(9)},
+	{"P2SB8B_PGD0_PG_STS",			BIT(10)},
+	{"DBG_SBR_PGD0_PG_STS",			BIT(11)},
+	{"SBR8B9_PGD0_PG_STS",			BIT(12)},
+	{"OSSE_SMT1_PGD0_PG_STS",		BIT(13)},
+	{"SBR8B10_PGD0_PG_STS",			BIT(14)},
+	{"SBR16B3_PGD0_PG_STS",			BIT(15)},
+	{"G5FPW1_PGD0_PG_STS",			BIT(16)},
+	{"SBRG_PGD0_PG_STS",			BIT(17)},
+	{"PSF4_PGD0_PG_STS",			BIT(18)},
+	{"CNVI_PGD0_PG_STS",			BIT(19)},
+	{"USFX2_PGD0_PG_STS",			BIT(20)},
+	{"ENDBG_PGD0_PG_STS",			BIT(21)},
+	{"FIACPCB_P5X4_PGD0_PG_STS",		BIT(22)},
+	{"SBR8B3_PGD0_PG_STS",			BIT(23)},
+	{"SBR8B0_PGD0_PG_STS",			BIT(24)},
+	{"NPK_PGD1_PG_STS",			BIT(25)},
+	{"OSSE_HOTHAM_PGD0_PG_STS",		BIT(26)},
+	{"D2D_NOC_PGD2_PG_STS",			BIT(27)},
+	{"SBR8B1_PGD0_PG_STS",			BIT(28)},
+	{"PSF6_PGD0_PG_STS",			BIT(29)},
+	{"PSF7_PGD0_PG_STS",			BIT(30)},
+	{"FIA_U_PGD0_PG_STS",			BIT(31)},
+	{}
+};
+
+const struct pmc_bit_map lnl_power_gating_status_2_map[] = {
+	{"PSF8_PGD0_PG_STS",			BIT(0)},
+	{"SBR16B2_PGD0_PG_STS",			BIT(1)},
+	{"D2D_IPU_PGD0_PG_STS",			BIT(2)},
+	{"FIACPCB_U_PGD0_PG_STS",		BIT(3)},
+	{"TAM_PGD0_PG_STS",			BIT(4)},
+	{"D2D_NOC_PGD1_PG_STS",			BIT(5)},
+	{"TBTLSX_PGD0_PG_STS",			BIT(6)},
+	{"THC0_PGD0_PG_STS",			BIT(7)},
+	{"THC1_PGD0_PG_STS",			BIT(8)},
+	{"PMC_PGD0_PG_STS",			BIT(9)},
+	{"SBR8B5_PGD0_PG_STS",			BIT(10)},
+	{"UFSPW1_PGD0_PG_STS",			BIT(11)},
+	{"DBC_PGD0_PG_STS",			BIT(12)},
+	{"TCSS_PGD0_PG_STS",			BIT(13)},
+	{"FIA_P5X4_PGD0_PG_STS",		BIT(14)},
+	{"DISP_PGA_PGD0_PG_STS",		BIT(15)},
+	{"DISP_PSF_PGD0_PG_STS",		BIT(16)},
+	{"PSF0_PGD0_PG_STS",			BIT(17)},
+	{"P2SB16B_PGD0_PG_STS",			BIT(18)},
+	{"ACE_PGD0_PG_STS",			BIT(19)},
+	{"ACE_PGD1_PG_STS",			BIT(20)},
+	{"ACE_PGD2_PG_STS",			BIT(21)},
+	{"ACE_PGD3_PG_STS",			BIT(22)},
+	{"ACE_PGD4_PG_STS",			BIT(23)},
+	{"ACE_PGD5_PG_STS",			BIT(24)},
+	{"ACE_PGD6_PG_STS",			BIT(25)},
+	{"ACE_PGD7_PG_STS",			BIT(26)},
+	{"ACE_PGD8_PG_STS",			BIT(27)},
+	{"ACE_PGD9_PG_STS",			BIT(28)},
+	{"ACE_PGD10_PG_STS",			BIT(29)},
+	{"FIACPCB_PG_PGD0_PG_STS",		BIT(30)},
+	{"OSSE_PGD0_PG_STS",			BIT(31)},
+	{}
+};
+
+const struct pmc_bit_map lnl_d3_status_0_map[] = {
+	{"LPSS_D3_STS",				BIT(3)},
+	{"XDCI_D3_STS",				BIT(4)},
+	{"XHCI_D3_STS",				BIT(5)},
+	{"SPA_D3_STS",				BIT(12)},
+	{"SPB_D3_STS",				BIT(13)},
+	{"OSSE_D3_STS",				BIT(15)},
+	{"ESPISPI_D3_STS",			BIT(18)},
+	{"PSTH_D3_STS",				BIT(21)},
+	{}
+};
+
+const struct pmc_bit_map lnl_d3_status_1_map[] = {
+	{"OSSE_SMT1_D3_STS",			BIT(7)},
+	{"GBE_D3_STS",				BIT(19)},
+	{"ITSS_D3_STS",				BIT(23)},
+	{"CNVI_D3_STS",				BIT(27)},
+	{"UFSX2_D3_STS",			BIT(28)},
+	{"OSSE_HOTHAM_D3_STS",			BIT(31)},
+	{}
+};
+
+const struct pmc_bit_map lnl_d3_status_2_map[] = {
+	{"ESE_D3_STS",				BIT(0)},
+	{"CSMERTC_D3_STS",			BIT(1)},
+	{"SUSRAM_D3_STS",			BIT(2)},
+	{"CSE_D3_STS",				BIT(4)},
+	{"KVMCC_D3_STS",			BIT(5)},
+	{"USBR0_D3_STS",			BIT(6)},
+	{"ISH_D3_STS",				BIT(7)},
+	{"SMT1_D3_STS",				BIT(8)},
+	{"SMT2_D3_STS",				BIT(9)},
+	{"SMT3_D3_STS",				BIT(10)},
+	{"OSSE_SMT2_D3_STS",			BIT(13)},
+	{"CLINK_D3_STS",			BIT(14)},
+	{"PTIO_D3_STS",				BIT(16)},
+	{"PMT_D3_STS",				BIT(17)},
+	{"SMS1_D3_STS",				BIT(18)},
+	{"SMS2_D3_STS",				BIT(19)},
+	{}
+};
+
+const struct pmc_bit_map lnl_d3_status_3_map[] = {
+	{"THC0_D3_STS",				BIT(14)},
+	{"THC1_D3_STS",				BIT(15)},
+	{"OSSE_SMT3_D3_STS",			BIT(21)},
+	{"ACE_D3_STS",				BIT(23)},
+	{}
+};
+
+const struct pmc_bit_map lnl_vnn_req_status_0_map[] = {
+	{"LPSS_VNN_REQ_STS",			BIT(3)},
+	{"OSSE_VNN_REQ_STS",			BIT(15)},
+	{"ESPISPI_VNN_REQ_STS",			BIT(18)},
+	{}
+};
+
+const struct pmc_bit_map lnl_vnn_req_status_1_map[] = {
+	{"NPK_VNN_REQ_STS",			BIT(4)},
+	{"OSSE_SMT1_VNN_REQ_STS",		BIT(7)},
+	{"DFXAGG_VNN_REQ_STS",			BIT(8)},
+	{"EXI_VNN_REQ_STS",			BIT(9)},
+	{"P2D_VNN_REQ_STS",			BIT(18)},
+	{"GBE_VNN_REQ_STS",			BIT(19)},
+	{"SMB_VNN_REQ_STS",			BIT(25)},
+	{"LPC_VNN_REQ_STS",			BIT(26)},
+	{}
+};
+
+const struct pmc_bit_map lnl_vnn_req_status_2_map[] = {
+	{"eSE_VNN_REQ_STS",			BIT(0)},
+	{"CSMERTC_VNN_REQ_STS",			BIT(1)},
+	{"CSE_VNN_REQ_STS",			BIT(4)},
+	{"ISH_VNN_REQ_STS",			BIT(7)},
+	{"SMT1_VNN_REQ_STS",			BIT(8)},
+	{"CLINK_VNN_REQ_STS",			BIT(14)},
+	{"SMS1_VNN_REQ_STS",			BIT(18)},
+	{"SMS2_VNN_REQ_STS",			BIT(19)},
+	{"GPIOCOM4_VNN_REQ_STS",		BIT(20)},
+	{"GPIOCOM3_VNN_REQ_STS",		BIT(21)},
+	{"GPIOCOM2_VNN_REQ_STS",		BIT(22)},
+	{"GPIOCOM1_VNN_REQ_STS",		BIT(23)},
+	{"GPIOCOM0_VNN_REQ_STS",		BIT(24)},
+	{}
+};
+
+const struct pmc_bit_map lnl_vnn_req_status_3_map[] = {
+	{"DISP_SHIM_VNN_REQ_STS",		BIT(2)},
+	{"DTS0_VNN_REQ_STS",			BIT(7)},
+	{"GPIOCOM5_VNN_REQ_STS",		BIT(11)},
+	{}
+};
+
+const struct pmc_bit_map lnl_vnn_misc_status_map[] = {
+	{"CPU_C10_REQ_STS",			BIT(0)},
+	{"TS_OFF_REQ_STS",			BIT(1)},
+	{"PNDE_MET_REQ_STS",			BIT(2)},
+	{"PCIE_DEEP_PM_REQ_STS",		BIT(3)},
+	{"PMC_CLK_THROTTLE_EN_REQ_STS",		BIT(4)},
+	{"NPK_VNNAON_REQ_STS",			BIT(5)},
+	{"VNN_SOC_REQ_STS",			BIT(6)},
+	{"ISH_VNNAON_REQ_STS",			BIT(7)},
+	{"D2D_NOC_CFI_QACTIVE_REQ_STS",		BIT(8)},
+	{"D2D_NOC_GPSB_QACTIVE_REQ_STS",	BIT(9)},
+	{"D2D_NOC_IPU_QACTIVE_REQ_STS",		BIT(10)},
+	{"PLT_GREATER_REQ_STS",			BIT(11)},
+	{"PCIE_CLKREQ_REQ_STS",			BIT(12)},
+	{"PMC_IDLE_FB_OCP_REQ_STS",		BIT(13)},
+	{"PM_SYNC_STATES_REQ_STS",		BIT(14)},
+	{"EA_REQ_STS",				BIT(15)},
+	{"MPHY_CORE_OFF_REQ_STS",		BIT(16)},
+	{"BRK_EV_EN_REQ_STS",			BIT(17)},
+	{"AUTO_DEMO_EN_REQ_STS",		BIT(18)},
+	{"ITSS_CLK_SRC_REQ_STS",		BIT(19)},
+	{"LPC_CLK_SRC_REQ_STS",			BIT(20)},
+	{"ARC_IDLE_REQ_STS",			BIT(21)},
+	{"MPHY_SUS_REQ_STS",			BIT(22)},
+	{"FIA_DEEP_PM_REQ_STS",			BIT(23)},
+	{"UXD_CONNECTED_REQ_STS",		BIT(24)},
+	{"ARC_INTERRUPT_WAKE_REQ_STS",	BIT(25)},
+	{"D2D_NOC_DISP_DDI_QACTIVE_REQ_STS",	BIT(26)},
+	{"PRE_WAKE0_REQ_STS",			BIT(27)},
+	{"PRE_WAKE1_REQ_STS",			BIT(28)},
+	{"PRE_WAKE2_EN_REQ_STS",		BIT(29)},
+	{"WOV_REQ_STS",				BIT(30)},
+	{"D2D_NOC_DISP_EDP_QACTIVE_REQ_STS_31",	BIT(31)},
+	{}
+};
+
+const struct pmc_bit_map lnl_clocksource_status_map[] = {
+	{"AON2_OFF_STS",			BIT(0)},
+	{"AON3_OFF_STS",			BIT(1)},
+	{"AON4_OFF_STS",			BIT(2)},
+	{"AON5_OFF_STS",			BIT(3)},
+	{"AON1_OFF_STS",			BIT(4)},
+	{"MPFPW1_0_PLL_OFF_STS",		BIT(6)},
+	{"USB3_PLL_OFF_STS",			BIT(8)},
+	{"AON3_SPL_OFF_STS",			BIT(9)},
+	{"G5FPW1_PLL_OFF_STS",			BIT(15)},
+	{"XTAL_AGGR_OFF_STS",			BIT(17)},
+	{"USB2_PLL_OFF_STS",			BIT(18)},
+	{"SAF_PLL_OFF_STS",			BIT(19)},
+	{"SE_TCSS_PLL_OFF_STS",			BIT(20)},
+	{"DDI_PLL_OFF_STS",			BIT(21)},
+	{"FILTER_PLL_OFF_STS",			BIT(22)},
+	{"ACE_PLL_OFF_STS",			BIT(24)},
+	{"FABRIC_PLL_OFF_STS",			BIT(25)},
+	{"SOC_PLL_OFF_STS",			BIT(26)},
+	{"REF_OFF_STS",				BIT(28)},
+	{"IMG_OFF_STS",				BIT(29)},
+	{"RTC_PLL_OFF_STS",			BIT(31)},
+	{}
+};
+
+const struct pmc_bit_map *lnl_lpm_maps[] = {
+	lnl_clocksource_status_map,
+	lnl_power_gating_status_0_map,
+	lnl_power_gating_status_1_map,
+	lnl_power_gating_status_2_map,
+	lnl_d3_status_0_map,
+	lnl_d3_status_1_map,
+	lnl_d3_status_2_map,
+	lnl_d3_status_3_map,
+	lnl_vnn_req_status_0_map,
+	lnl_vnn_req_status_1_map,
+	lnl_vnn_req_status_2_map,
+	lnl_vnn_req_status_3_map,
+	lnl_vnn_misc_status_map,
+	mtl_socm_signal_status_map,
+	NULL
+};
+
+const struct pmc_bit_map lnl_pfear_map[] = {
+	{"PMC_0",			BIT(0)},
+	{"FUSE_OSSE",			BIT(1)},
+	{"ESPISPI",			BIT(2)},
+	{"XHCI",			BIT(3)},
+	{"SPA",				BIT(4)},
+	{"SPB",				BIT(5)},
+	{"SBR16B0",			BIT(6)},
+	{"GBE",				BIT(7)},
+
+	{"SBR8B7",			BIT(0)},
+	{"SBR8B6",			BIT(1)},
+	{"SBR16B1",			BIT(1)},
+	{"SBR8B8",			BIT(2)},
+	{"ESE",				BIT(3)},
+	{"SBR8B10",			BIT(4)},
+	{"D2D_DISP_0",			BIT(5)},
+	{"LPSS",			BIT(6)},
+	{"LPC",				BIT(7)},
+
+	{"SMB",				BIT(0)},
+	{"ISH",				BIT(1)},
+	{"SBR8B2",			BIT(2)},
+	{"NPK_0",			BIT(3)},
+	{"D2D_NOC_0",			BIT(4)},
+	{"SAFSS",			BIT(5)},
+	{"FUSE",			BIT(6)},
+	{"D2D_DISP_1",			BIT(7)},
+
+	{"MPFPW1",			BIT(0)},
+	{"XDCI",			BIT(1)},
+	{"EXI",				BIT(2)},
+	{"CSE",				BIT(3)},
+	{"KVMCC",			BIT(4)},
+	{"PMT",				BIT(5)},
+	{"CLINK",			BIT(6)},
+	{"PTIO",			BIT(7)},
+
+	{"USBR",			BIT(0)},
+	{"SUSRAM",			BIT(1)},
+	{"SMT1",			BIT(2)},
+	{"U3FPW1",			BIT(3)},
+	{"SMS2",			BIT(4)},
+	{"SMS1",			BIT(5)},
+	{"CSMERTC",			BIT(6)},
+	{"CSMEPSF",			BIT(7)},
+
+	{"FIA_PG",			BIT(0)},
+	{"SBR16B4",			BIT(1)},
+	{"P2SB8B",			BIT(2)},
+	{"DBG_SBR",			BIT(3)},
+	{"SBR8B9",			BIT(4)},
+	{"OSSE_SMT1",			BIT(5)},
+	{"SBR8B10",			BIT(6)},
+	{"SBR16B3",			BIT(7)},
+
+	{"G5FPW1",			BIT(0)},
+	{"SBRG",			BIT(1)},
+	{"PSF4",			BIT(2)},
+	{"CNVI",			BIT(3)},
+	{"UFSX2",			BIT(4)},
+	{"ENDBG",			BIT(5)},
+	{"FIACPCB_P5X4",		BIT(6)},
+	{"SBR8B3",			BIT(7)},
+
+	{"SBR8B0",			BIT(0)},
+	{"NPK_1",			BIT(1)},
+	{"OSSE_HOTHAM",			BIT(2)},
+	{"D2D_NOC_2",			BIT(3)},
+	{"SBR8B1",			BIT(4)},
+	{"PSF6",			BIT(5)},
+	{"PSF7",			BIT(6)},
+	{"FIA_U",			BIT(7)},
+
+	{"PSF8",			BIT(0)},
+	{"SBR16B2",			BIT(1)},
+	{"D2D_IPU",			BIT(2)},
+	{"FIACPCB_U",			BIT(3)},
+	{"TAM",				BIT(4)},
+	{"D2D_NOC_1",			BIT(5)},
+	{"TBTLSX",			BIT(6)},
+	{"THC0",			BIT(7)},
+
+	{"THC1",			BIT(0)},
+	{"PMC_1",			BIT(1)},
+	{"SBR8B5",			BIT(2)},
+	{"UFSPW1",			BIT(3)},
+	{"DBC",				BIT(4)},
+	{"TCSS",			BIT(5)},
+	{"FIA_P5X4",			BIT(6)},
+	{"DISP_PGA",			BIT(7)},
+
+	{"DBG_PSF",			BIT(0)},
+	{"PSF0",			BIT(1)},
+	{"P2SB16B",			BIT(2)},
+	{"ACE0",			BIT(3)},
+	{"ACE1",			BIT(4)},
+	{"ACE2",			BIT(5)},
+	{"ACE3",			BIT(6)},
+	{"ACE4",			BIT(7)},
+
+	{"ACE5",			BIT(0)},
+	{"ACE6",			BIT(1)},
+	{"ACE7",			BIT(2)},
+	{"ACE8",			BIT(3)},
+	{"ACE9",			BIT(4)},
+	{"ACE10",			BIT(5)},
+	{"FIACPCB",			BIT(6)},
+	{"OSSE",			BIT(7)},
+	{}
+};
+
+const struct pmc_bit_map *ext_lnl_pfear_map[] = {
+	lnl_pfear_map,
+	NULL
+};
+
+const struct pmc_reg_map lnl_socm_reg_map = {
+	.pfear_sts = ext_lnl_pfear_map,
+	.slp_s0_offset = CNP_PMC_SLP_S0_RES_COUNTER_OFFSET,
+	.slp_s0_res_counter_step = TGL_PMC_SLP_S0_RES_COUNTER_STEP,
+	.ltr_show_sts = lnl_ltr_show_map,
+	.msr_sts = msr_map,
+	.ltr_ignore_offset = CNP_PMC_LTR_IGNORE_OFFSET,
+	.regmap_length = LNL_PMC_MMIO_REG_LEN,
+	.ppfear0_offset = CNP_PMC_HOST_PPFEAR0A,
+	.ppfear_buckets = LNL_PPFEAR_NUM_ENTRIES,
+	.pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET,
+	.pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT,
+	.ltr_ignore_max = LNL_NUM_IP_IGN_ALLOWED,
+	.lpm_num_maps = ADL_LPM_NUM_MAPS,
+	.lpm_res_counter_step_x2 = TGL_PMC_LPM_RES_COUNTER_STEP_X2,
+	.etr3_offset = ETR3_OFFSET,
+	.lpm_sts_latch_en_offset = MTL_LPM_STATUS_LATCH_EN_OFFSET,
+	.lpm_priority_offset = MTL_LPM_PRI_OFFSET,
+	.lpm_en_offset = MTL_LPM_EN_OFFSET,
+	.lpm_residency_offset = MTL_LPM_RESIDENCY_OFFSET,
+	.lpm_sts = lnl_lpm_maps,
+	.lpm_status_offset = MTL_LPM_STATUS_OFFSET,
+	.lpm_live_status_offset = MTL_LPM_LIVE_STATUS_OFFSET,
+	.lpm_reg_index = LNL_LPM_REG_INDEX,
+};
+
+#define LNL_NPU_PCI_DEV		0x643e
+#define LNL_IPU_PCI_DEV		0x645d
+
+/*
+ * Set power state of select devices that do not have drivers to D3
+ * so that they do not block Package C entry.
+ */
+static void lnl_d3_fixup(void)
+{
+	pmc_core_set_device_d3(LNL_IPU_PCI_DEV);
+	pmc_core_set_device_d3(LNL_NPU_PCI_DEV);
+}
+
+static int lnl_resume(struct pmc_dev *pmcdev)
+{
+	lnl_d3_fixup();
+	pmc_core_send_ltr_ignore(pmcdev, 3, 0);
+
+	return pmc_core_resume_common(pmcdev);
+}
+
+int lnl_core_init(struct pmc_dev *pmcdev)
+{
+	int ret;
+	int func = 2;
+	bool ssram_init = true;
+	struct pmc *pmc = pmcdev->pmcs[PMC_IDX_SOC];
+
+	lnl_d3_fixup();
+
+	pmcdev->suspend = cnl_suspend;
+	pmcdev->resume = lnl_resume;
+	pmcdev->regmap_list = lnl_pmc_info_list;
+	ret = pmc_core_ssram_init(pmcdev, func);
+
+	/* If regbase not assigned, set map and discover using legacy method */
+	if (ret) {
+		ssram_init = false;
+		pmc->map = &lnl_socm_reg_map;
+		ret = get_primary_reg_base(pmc);
+		if (ret)
+			return ret;
+	}
+
+	pmc_core_get_low_power_modes(pmcdev);
+
+	if (ssram_init) {
+		ret = pmc_core_ssram_get_lpm_reqs(pmcdev);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
diff --git a/drivers/platform/x86/intel/pmc/mtl.c b/drivers/platform/x86/intel/pmc/mtl.c
index 2204bc666980..c7d15d864039 100644
--- a/drivers/platform/x86/intel/pmc/mtl.c
+++ b/drivers/platform/x86/intel/pmc/mtl.c
@@ -10,6 +10,14 @@
 
 #include <linux/pci.h>
 #include "core.h"
+#include "../pmt/telemetry.h"
+
+/* PMC SSRAM PMT Telemetry GUIDS */
+#define SOCP_LPM_REQ_GUID	0x2625030
+#define IOEM_LPM_REQ_GUID	0x4357464
+#define IOEP_LPM_REQ_GUID	0x5077612
+
+static const u8 MTL_LPM_REG_INDEX[] = {0, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 15, 16, 20};
 
 /*
  * Die Mapping to Product.
@@ -465,6 +473,7 @@ const struct pmc_reg_map mtl_socm_reg_map = {
 	.lpm_sts = mtl_socm_lpm_maps,
 	.lpm_status_offset = MTL_LPM_STATUS_OFFSET,
 	.lpm_live_status_offset = MTL_LPM_LIVE_STATUS_OFFSET,
+	.lpm_reg_index = MTL_LPM_REG_INDEX,
 };
 
 const struct pmc_bit_map mtl_ioep_pfear_map[] = {
@@ -782,6 +791,13 @@ const struct pmc_reg_map mtl_ioep_reg_map = {
 	.ltr_show_sts = mtl_ioep_ltr_show_map,
 	.ltr_ignore_offset = CNP_PMC_LTR_IGNORE_OFFSET,
 	.ltr_ignore_max = ADL_NUM_IP_IGN_ALLOWED,
+	.lpm_num_maps = ADL_LPM_NUM_MAPS,
+	.lpm_res_counter_step_x2 = TGL_PMC_LPM_RES_COUNTER_STEP_X2,
+	.lpm_residency_offset = MTL_LPM_RESIDENCY_OFFSET,
+	.lpm_priority_offset = MTL_LPM_PRI_OFFSET,
+	.lpm_en_offset = MTL_LPM_EN_OFFSET,
+	.lpm_sts_latch_en_offset = MTL_LPM_STATUS_LATCH_EN_OFFSET,
+	.lpm_reg_index = MTL_LPM_REG_INDEX,
 };
 
 const struct pmc_bit_map mtl_ioem_pfear_map[] = {
@@ -922,6 +938,13 @@ const struct pmc_reg_map mtl_ioem_reg_map = {
 	.ltr_show_sts = mtl_ioep_ltr_show_map,
 	.ltr_ignore_offset = CNP_PMC_LTR_IGNORE_OFFSET,
 	.ltr_ignore_max = ADL_NUM_IP_IGN_ALLOWED,
+	.lpm_sts_latch_en_offset = MTL_LPM_STATUS_LATCH_EN_OFFSET,
+	.lpm_num_maps = ADL_LPM_NUM_MAPS,
+	.lpm_priority_offset = MTL_LPM_PRI_OFFSET,
+	.lpm_en_offset = MTL_LPM_EN_OFFSET,
+	.lpm_res_counter_step_x2 = TGL_PMC_LPM_RES_COUNTER_STEP_X2,
+	.lpm_residency_offset = MTL_LPM_RESIDENCY_OFFSET,
+	.lpm_reg_index = MTL_LPM_REG_INDEX,
 };
 
 #define PMC_DEVID_SOCM	0x7e7f
@@ -929,16 +952,19 @@ const struct pmc_reg_map mtl_ioem_reg_map = {
 #define PMC_DEVID_IOEM	0x7ebf
 static struct pmc_info mtl_pmc_info_list[] = {
 	{
-		.devid = PMC_DEVID_SOCM,
-		.map = &mtl_socm_reg_map,
+		.guid	= SOCP_LPM_REQ_GUID,
+		.devid	= PMC_DEVID_SOCM,
+		.map	= &mtl_socm_reg_map,
 	},
 	{
-		.devid = PMC_DEVID_IOEP,
-		.map = &mtl_ioep_reg_map,
+		.guid	= IOEP_LPM_REQ_GUID,
+		.devid	= PMC_DEVID_IOEP,
+		.map	= &mtl_ioep_reg_map,
 	},
 	{
-		.devid = PMC_DEVID_IOEM,
-		.map = &mtl_ioem_reg_map
+		.guid	= IOEM_LPM_REQ_GUID,
+		.devid	= PMC_DEVID_IOEM,
+		.map	= &mtl_ioem_reg_map
 	},
 	{}
 };
@@ -946,67 +972,58 @@ static struct pmc_info mtl_pmc_info_list[] = {
 #define MTL_GNA_PCI_DEV	0x7e4c
 #define MTL_IPU_PCI_DEV	0x7d19
 #define MTL_VPU_PCI_DEV	0x7d1d
-static void mtl_set_device_d3(unsigned int device)
-{
-	struct pci_dev *pcidev;
-
-	pcidev = pci_get_device(PCI_VENDOR_ID_INTEL, device, NULL);
-	if (pcidev) {
-		if (!device_trylock(&pcidev->dev)) {
-			pci_dev_put(pcidev);
-			return;
-		}
-		if (!pcidev->dev.driver) {
-			dev_info(&pcidev->dev, "Setting to D3hot\n");
-			pci_set_power_state(pcidev, PCI_D3hot);
-		}
-		device_unlock(&pcidev->dev);
-		pci_dev_put(pcidev);
-	}
-}
-
 /*
  * Set power state of select devices that do not have drivers to D3
  * so that they do not block Package C entry.
  */
 static void mtl_d3_fixup(void)
 {
-	mtl_set_device_d3(MTL_GNA_PCI_DEV);
-	mtl_set_device_d3(MTL_IPU_PCI_DEV);
-	mtl_set_device_d3(MTL_VPU_PCI_DEV);
+	pmc_core_set_device_d3(MTL_GNA_PCI_DEV);
+	pmc_core_set_device_d3(MTL_IPU_PCI_DEV);
+	pmc_core_set_device_d3(MTL_VPU_PCI_DEV);
 }
 
 static int mtl_resume(struct pmc_dev *pmcdev)
 {
 	mtl_d3_fixup();
+	pmc_core_send_ltr_ignore(pmcdev, 3, 0);
+
 	return pmc_core_resume_common(pmcdev);
 }
 
 int mtl_core_init(struct pmc_dev *pmcdev)
 {
 	struct pmc *pmc = pmcdev->pmcs[PMC_IDX_SOC];
-	int ret = 0;
+	int ret;
+	int func = 2;
+	bool ssram_init = true;
 
 	mtl_d3_fixup();
 
+	pmcdev->suspend = cnl_suspend;
 	pmcdev->resume = mtl_resume;
-
 	pmcdev->regmap_list = mtl_pmc_info_list;
-	pmc_core_ssram_init(pmcdev);
 
-	/* If regbase not assigned, set map and discover using legacy method */
-	if (!pmc->regbase) {
+	/*
+	 * If ssram init fails use legacy method to at least get the
+	 * primary PMC
+	 */
+	ret = pmc_core_ssram_init(pmcdev, func);
+	if (ret) {
+		ssram_init = false;
+		dev_warn(&pmcdev->pdev->dev,
+			 "ssram init failed, %d, using legacy init\n", ret);
 		pmc->map = &mtl_socm_reg_map;
 		ret = get_primary_reg_base(pmc);
 		if (ret)
 			return ret;
 	}
 
-	/* Due to a hardware limitation, the GBE LTR blocks PC10
-	 * when a cable is attached. Tell the PMC to ignore it.
-	 */
-	dev_dbg(&pmcdev->pdev->dev, "ignoring GBE LTR\n");
-	pmc_core_send_ltr_ignore(pmcdev, 3);
+	pmc_core_get_low_power_modes(pmcdev);
+	pmc_core_punit_pmt_init(pmcdev, MTL_PMT_DMU_GUID);
+
+	if (ssram_init)
+		return pmc_core_ssram_get_lpm_reqs(pmcdev);
 
 	return 0;
 }
diff --git a/drivers/platform/x86/intel/pmc/spt.c b/drivers/platform/x86/intel/pmc/spt.c
index 4b6f5cbda16c..ab993a69e33e 100644
--- a/drivers/platform/x86/intel/pmc/spt.c
+++ b/drivers/platform/x86/intel/pmc/spt.c
@@ -137,7 +137,15 @@ const struct pmc_reg_map spt_reg_map = {
 int spt_core_init(struct pmc_dev *pmcdev)
 {
 	struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN];
+	int ret;
 
 	pmc->map = &spt_reg_map;
-	return get_primary_reg_base(pmc);
+
+	ret = get_primary_reg_base(pmc);
+	if (ret)
+		return ret;
+
+	pmc_core_get_low_power_modes(pmcdev);
+
+	return ret;
 }
diff --git a/drivers/platform/x86/intel/pmc/tgl.c b/drivers/platform/x86/intel/pmc/tgl.c
index 2449940102db..e0580de18077 100644
--- a/drivers/platform/x86/intel/pmc/tgl.c
+++ b/drivers/platform/x86/intel/pmc/tgl.c
@@ -13,6 +13,11 @@
 #define ACPI_S0IX_DSM_UUID		"57a6512e-3979-4e9d-9708-ff13b2508972"
 #define ACPI_GET_LOW_MODE_REGISTERS	1
 
+enum pch_type {
+	PCH_H,
+	PCH_LP
+};
+
 const struct pmc_bit_map tgl_pfear_map[] = {
 	{"PSF9",		BIT(0)},
 	{"RES_66",		BIT(1)},
@@ -205,6 +210,33 @@ const struct pmc_reg_map tgl_reg_map = {
 	.etr3_offset = ETR3_OFFSET,
 };
 
+const struct pmc_reg_map tgl_h_reg_map = {
+	.pfear_sts = ext_tgl_pfear_map,
+	.slp_s0_offset = CNP_PMC_SLP_S0_RES_COUNTER_OFFSET,
+	.slp_s0_res_counter_step = TGL_PMC_SLP_S0_RES_COUNTER_STEP,
+	.ltr_show_sts = cnp_ltr_show_map,
+	.msr_sts = msr_map,
+	.ltr_ignore_offset = CNP_PMC_LTR_IGNORE_OFFSET,
+	.regmap_length = CNP_PMC_MMIO_REG_LEN,
+	.ppfear0_offset = CNP_PMC_HOST_PPFEAR0A,
+	.ppfear_buckets = ICL_PPFEAR_NUM_ENTRIES,
+	.pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET,
+	.pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT,
+	.ltr_ignore_max = TGL_NUM_IP_IGN_ALLOWED,
+	.lpm_num_maps = TGL_LPM_NUM_MAPS,
+	.lpm_res_counter_step_x2 = TGL_PMC_LPM_RES_COUNTER_STEP_X2,
+	.lpm_sts_latch_en_offset = TGL_LPM_STS_LATCH_EN_OFFSET,
+	.lpm_en_offset = TGL_LPM_EN_OFFSET,
+	.lpm_priority_offset = TGL_LPM_PRI_OFFSET,
+	.lpm_residency_offset = TGL_LPM_RESIDENCY_OFFSET,
+	.lpm_sts = tgl_lpm_maps,
+	.lpm_status_offset = TGL_LPM_STATUS_OFFSET,
+	.lpm_live_status_offset = TGL_LPM_LIVE_STATUS_OFFSET,
+	.etr3_offset = ETR3_OFFSET,
+	.pson_residency_offset = TGL_PSON_RESIDENCY_OFFSET,
+	.pson_residency_counter_step = TGL_PSON_RES_COUNTER_STEP,
+};
+
 void pmc_core_get_tgl_lpm_reqs(struct platform_device *pdev)
 {
 	struct pmc_dev *pmcdev = platform_get_drvdata(pdev);
@@ -253,22 +285,35 @@ free_acpi_obj:
 	ACPI_FREE(out_obj);
 }
 
+int tgl_l_core_init(struct pmc_dev *pmcdev)
+{
+	return tgl_core_generic_init(pmcdev, PCH_LP);
+}
+
 int tgl_core_init(struct pmc_dev *pmcdev)
 {
+	return tgl_core_generic_init(pmcdev, PCH_H);
+}
+
+int tgl_core_generic_init(struct pmc_dev *pmcdev, int pch_tp)
+{
 	struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN];
 	int ret;
 
-	pmc->map = &tgl_reg_map;
+	if (pch_tp == PCH_H)
+		pmc->map = &tgl_h_reg_map;
+	else
+		pmc->map = &tgl_reg_map;
+
+	pmcdev->suspend = cnl_suspend;
+	pmcdev->resume = cnl_resume;
+
 	ret = get_primary_reg_base(pmc);
 	if (ret)
 		return ret;
 
+	pmc_core_get_low_power_modes(pmcdev);
 	pmc_core_get_tgl_lpm_reqs(pmcdev->pdev);
-	/* Due to a hardware limitation, the GBE LTR blocks PC10
-	 * when a cable is attached. Tell the PMC to ignore it.
-	 */
-	dev_dbg(&pmcdev->pdev->dev, "ignoring GBE LTR\n");
-	pmc_core_send_ltr_ignore(pmcdev, 3);
 
 	return 0;
 }
diff --git a/drivers/platform/x86/intel/pmt/class.c b/drivers/platform/x86/intel/pmt/class.c
index f32a233470de..4b53940a64e2 100644
--- a/drivers/platform/x86/intel/pmt/class.c
+++ b/drivers/platform/x86/intel/pmt/class.c
@@ -17,7 +17,7 @@
 #include "../vsec.h"
 #include "class.h"
 
-#define PMT_XA_START		0
+#define PMT_XA_START		1
 #define PMT_XA_MAX		INT_MAX
 #define PMT_XA_LIMIT		XA_LIMIT(PMT_XA_START, PMT_XA_MAX)
 #define GUID_SPR_PUNIT		0x9956f43f
@@ -31,7 +31,7 @@ bool intel_pmt_is_early_client_hw(struct device *dev)
 	 * differences from the server platforms (which use the Out Of Band
 	 * Management Services Module OOBMSM).
 	 */
-	return !!(ivdev->info->quirks & VSEC_QUIRK_EARLY_HW);
+	return !!(ivdev->quirks & VSEC_QUIRK_EARLY_HW);
 }
 EXPORT_SYMBOL_NS_GPL(intel_pmt_is_early_client_hw, INTEL_PMT);
 
@@ -159,11 +159,12 @@ static struct class intel_pmt_class = {
 };
 
 static int intel_pmt_populate_entry(struct intel_pmt_entry *entry,
-				    struct intel_pmt_header *header,
-				    struct device *dev,
+				    struct intel_vsec_device *ivdev,
 				    struct resource *disc_res)
 {
-	struct pci_dev *pci_dev = to_pci_dev(dev->parent);
+	struct pci_dev *pci_dev = ivdev->pcidev;
+	struct device *dev = &ivdev->auxdev.dev;
+	struct intel_pmt_header *header = &entry->header;
 	u8 bir;
 
 	/*
@@ -215,6 +216,13 @@ static int intel_pmt_populate_entry(struct intel_pmt_entry *entry,
 
 		break;
 	case ACCESS_BARID:
+		/* Use the provided base address if it exists */
+		if (ivdev->base_addr) {
+			entry->base_addr = ivdev->base_addr +
+				   GET_ADDRESS(header->base_offset);
+			break;
+		}
+
 		/*
 		 * If another BAR was specified then the base offset
 		 * represents the offset within that BAR. SO retrieve the
@@ -239,6 +247,7 @@ static int intel_pmt_dev_register(struct intel_pmt_entry *entry,
 				  struct intel_pmt_namespace *ns,
 				  struct device *parent)
 {
+	struct intel_vsec_device *ivdev = dev_to_ivdev(parent);
 	struct resource res = {0};
 	struct device *dev;
 	int ret;
@@ -262,7 +271,7 @@ static int intel_pmt_dev_register(struct intel_pmt_entry *entry,
 	if (ns->attr_grp) {
 		ret = sysfs_create_group(entry->kobj, ns->attr_grp);
 		if (ret)
-			goto fail_sysfs;
+			goto fail_sysfs_create_group;
 	}
 
 	/* if size is 0 assume no data buffer, so no file needed */
@@ -287,13 +296,23 @@ static int intel_pmt_dev_register(struct intel_pmt_entry *entry,
 	entry->pmt_bin_attr.size = entry->size;
 
 	ret = sysfs_create_bin_file(&dev->kobj, &entry->pmt_bin_attr);
-	if (!ret)
-		return 0;
+	if (ret)
+		goto fail_ioremap;
 
+	if (ns->pmt_add_endpoint) {
+		ret = ns->pmt_add_endpoint(entry, ivdev->pcidev);
+		if (ret)
+			goto fail_add_endpoint;
+	}
+
+	return 0;
+
+fail_add_endpoint:
+	sysfs_remove_bin_file(entry->kobj, &entry->pmt_bin_attr);
 fail_ioremap:
 	if (ns->attr_grp)
 		sysfs_remove_group(entry->kobj, ns->attr_grp);
-fail_sysfs:
+fail_sysfs_create_group:
 	device_unregister(dev);
 fail_dev_create:
 	xa_erase(ns->xa, entry->devid);
@@ -305,7 +324,6 @@ int intel_pmt_dev_create(struct intel_pmt_entry *entry, struct intel_pmt_namespa
 			 struct intel_vsec_device *intel_vsec_dev, int idx)
 {
 	struct device *dev = &intel_vsec_dev->auxdev.dev;
-	struct intel_pmt_header header;
 	struct resource	*disc_res;
 	int ret;
 
@@ -315,16 +333,15 @@ int intel_pmt_dev_create(struct intel_pmt_entry *entry, struct intel_pmt_namespa
 	if (IS_ERR(entry->disc_table))
 		return PTR_ERR(entry->disc_table);
 
-	ret = ns->pmt_header_decode(entry, &header, dev);
+	ret = ns->pmt_header_decode(entry, dev);
 	if (ret)
 		return ret;
 
-	ret = intel_pmt_populate_entry(entry, &header, dev, disc_res);
+	ret = intel_pmt_populate_entry(entry, intel_vsec_dev, disc_res);
 	if (ret)
 		return ret;
 
 	return intel_pmt_dev_register(entry, ns, dev);
-
 }
 EXPORT_SYMBOL_NS_GPL(intel_pmt_dev_create, INTEL_PMT);
 
diff --git a/drivers/platform/x86/intel/pmt/class.h b/drivers/platform/x86/intel/pmt/class.h
index db11d58867ce..d23c63b73ab7 100644
--- a/drivers/platform/x86/intel/pmt/class.h
+++ b/drivers/platform/x86/intel/pmt/class.h
@@ -9,6 +9,7 @@
 #include <linux/io.h>
 
 #include "../vsec.h"
+#include "telemetry.h"
 
 /* PMT access types */
 #define ACCESS_BARID		2
@@ -18,7 +19,26 @@
 #define GET_BIR(v)		((v) & GENMASK(2, 0))
 #define GET_ADDRESS(v)		((v) & GENMASK(31, 3))
 
+struct pci_dev;
+
+struct telem_endpoint {
+	struct pci_dev		*pcidev;
+	struct telem_header	header;
+	void __iomem		*base;
+	bool			present;
+	struct kref		kref;
+};
+
+struct intel_pmt_header {
+	u32	base_offset;
+	u32	size;
+	u32	guid;
+	u8	access_type;
+};
+
 struct intel_pmt_entry {
+	struct telem_endpoint	*ep;
+	struct intel_pmt_header	header;
 	struct bin_attribute	pmt_bin_attr;
 	struct kobject		*kobj;
 	void __iomem		*disc_table;
@@ -29,20 +49,14 @@ struct intel_pmt_entry {
 	int			devid;
 };
 
-struct intel_pmt_header {
-	u32	base_offset;
-	u32	size;
-	u32	guid;
-	u8	access_type;
-};
-
 struct intel_pmt_namespace {
 	const char *name;
 	struct xarray *xa;
 	const struct attribute_group *attr_grp;
 	int (*pmt_header_decode)(struct intel_pmt_entry *entry,
-				 struct intel_pmt_header *header,
 				 struct device *dev);
+	int (*pmt_add_endpoint)(struct intel_pmt_entry *entry,
+				struct pci_dev *pdev);
 };
 
 bool intel_pmt_is_early_client_hw(struct device *dev);
diff --git a/drivers/platform/x86/intel/pmt/crashlog.c b/drivers/platform/x86/intel/pmt/crashlog.c
index bbb3d61d09f4..4014c02cafdb 100644
--- a/drivers/platform/x86/intel/pmt/crashlog.c
+++ b/drivers/platform/x86/intel/pmt/crashlog.c
@@ -223,10 +223,10 @@ static const struct attribute_group pmt_crashlog_group = {
 };
 
 static int pmt_crashlog_header_decode(struct intel_pmt_entry *entry,
-				      struct intel_pmt_header *header,
 				      struct device *dev)
 {
 	void __iomem *disc_table = entry->disc_table;
+	struct intel_pmt_header *header = &entry->header;
 	struct crashlog_entry *crashlog;
 
 	if (!pmt_crashlog_supported(entry))
diff --git a/drivers/platform/x86/intel/pmt/telemetry.c b/drivers/platform/x86/intel/pmt/telemetry.c
index 39cbc87cc28a..09258564dfc4 100644
--- a/drivers/platform/x86/intel/pmt/telemetry.c
+++ b/drivers/platform/x86/intel/pmt/telemetry.c
@@ -30,6 +30,15 @@
 /* Used by client hardware to identify a fixed telemetry entry*/
 #define TELEM_CLIENT_FIXED_BLOCK_GUID	0x10000000
 
+#define NUM_BYTES_QWORD(v)	((v) << 3)
+#define SAMPLE_ID_OFFSET(v)	((v) << 3)
+
+#define NUM_BYTES_DWORD(v)	((v) << 2)
+#define SAMPLE_ID_OFFSET32(v)	((v) << 2)
+
+/* Protects access to the xarray of telemetry endpoint handles */
+static DEFINE_MUTEX(ep_lock);
+
 enum telem_type {
 	TELEM_TYPE_PUNIT = 0,
 	TELEM_TYPE_CRASHLOG,
@@ -58,10 +67,10 @@ static bool pmt_telem_region_overlaps(struct intel_pmt_entry *entry,
 }
 
 static int pmt_telem_header_decode(struct intel_pmt_entry *entry,
-				   struct intel_pmt_header *header,
 				   struct device *dev)
 {
 	void __iomem *disc_table = entry->disc_table;
+	struct intel_pmt_header *header = &entry->header;
 
 	if (pmt_telem_region_overlaps(entry, dev))
 		return 1;
@@ -84,21 +93,195 @@ static int pmt_telem_header_decode(struct intel_pmt_entry *entry,
 	return 0;
 }
 
+static int pmt_telem_add_endpoint(struct intel_pmt_entry *entry,
+				  struct pci_dev *pdev)
+{
+	struct telem_endpoint *ep;
+
+	/* Endpoint lifetimes are managed by kref, not devres */
+	entry->ep = kzalloc(sizeof(*(entry->ep)), GFP_KERNEL);
+	if (!entry->ep)
+		return -ENOMEM;
+
+	ep = entry->ep;
+	ep->pcidev = pdev;
+	ep->header.access_type = entry->header.access_type;
+	ep->header.guid = entry->header.guid;
+	ep->header.base_offset = entry->header.base_offset;
+	ep->header.size = entry->header.size;
+	ep->base = entry->base;
+	ep->present = true;
+
+	kref_init(&ep->kref);
+
+	return 0;
+}
+
 static DEFINE_XARRAY_ALLOC(telem_array);
 static struct intel_pmt_namespace pmt_telem_ns = {
 	.name = "telem",
 	.xa = &telem_array,
 	.pmt_header_decode = pmt_telem_header_decode,
+	.pmt_add_endpoint = pmt_telem_add_endpoint,
 };
 
+/* Called when all users unregister and the device is removed */
+static void pmt_telem_ep_release(struct kref *kref)
+{
+	struct telem_endpoint *ep;
+
+	ep = container_of(kref, struct telem_endpoint, kref);
+	kfree(ep);
+}
+
+unsigned long pmt_telem_get_next_endpoint(unsigned long start)
+{
+	struct intel_pmt_entry *entry;
+	unsigned long found_idx;
+
+	mutex_lock(&ep_lock);
+	xa_for_each_start(&telem_array, found_idx, entry, start) {
+		/*
+		 * Return first found index after start.
+		 * 0 is not valid id.
+		 */
+		if (found_idx > start)
+			break;
+	}
+	mutex_unlock(&ep_lock);
+
+	return found_idx == start ? 0 : found_idx;
+}
+EXPORT_SYMBOL_NS_GPL(pmt_telem_get_next_endpoint, INTEL_PMT_TELEMETRY);
+
+struct telem_endpoint *pmt_telem_register_endpoint(int devid)
+{
+	struct intel_pmt_entry *entry;
+	unsigned long index = devid;
+
+	mutex_lock(&ep_lock);
+	entry = xa_find(&telem_array, &index, index, XA_PRESENT);
+	if (!entry) {
+		mutex_unlock(&ep_lock);
+		return ERR_PTR(-ENXIO);
+	}
+
+	kref_get(&entry->ep->kref);
+	mutex_unlock(&ep_lock);
+
+	return entry->ep;
+}
+EXPORT_SYMBOL_NS_GPL(pmt_telem_register_endpoint, INTEL_PMT_TELEMETRY);
+
+void pmt_telem_unregister_endpoint(struct telem_endpoint *ep)
+{
+	kref_put(&ep->kref, pmt_telem_ep_release);
+}
+EXPORT_SYMBOL_NS_GPL(pmt_telem_unregister_endpoint, INTEL_PMT_TELEMETRY);
+
+int pmt_telem_get_endpoint_info(int devid, struct telem_endpoint_info *info)
+{
+	struct intel_pmt_entry *entry;
+	unsigned long index = devid;
+	int err = 0;
+
+	if (!info)
+		return -EINVAL;
+
+	mutex_lock(&ep_lock);
+	entry = xa_find(&telem_array, &index, index, XA_PRESENT);
+	if (!entry) {
+		err = -ENXIO;
+		goto unlock;
+	}
+
+	info->pdev = entry->ep->pcidev;
+	info->header = entry->ep->header;
+
+unlock:
+	mutex_unlock(&ep_lock);
+	return err;
+
+}
+EXPORT_SYMBOL_NS_GPL(pmt_telem_get_endpoint_info, INTEL_PMT_TELEMETRY);
+
+int pmt_telem_read(struct telem_endpoint *ep, u32 id, u64 *data, u32 count)
+{
+	u32 offset, size;
+
+	if (!ep->present)
+		return -ENODEV;
+
+	offset = SAMPLE_ID_OFFSET(id);
+	size = ep->header.size;
+
+	if (offset + NUM_BYTES_QWORD(count) > size)
+		return -EINVAL;
+
+	memcpy_fromio(data, ep->base + offset, NUM_BYTES_QWORD(count));
+
+	return ep->present ? 0 : -EPIPE;
+}
+EXPORT_SYMBOL_NS_GPL(pmt_telem_read, INTEL_PMT_TELEMETRY);
+
+int pmt_telem_read32(struct telem_endpoint *ep, u32 id, u32 *data, u32 count)
+{
+	u32 offset, size;
+
+	if (!ep->present)
+		return -ENODEV;
+
+	offset = SAMPLE_ID_OFFSET32(id);
+	size = ep->header.size;
+
+	if (offset + NUM_BYTES_DWORD(count) > size)
+		return -EINVAL;
+
+	memcpy_fromio(data, ep->base + offset, NUM_BYTES_DWORD(count));
+
+	return ep->present ? 0 : -EPIPE;
+}
+EXPORT_SYMBOL_NS_GPL(pmt_telem_read32, INTEL_PMT_TELEMETRY);
+
+struct telem_endpoint *
+pmt_telem_find_and_register_endpoint(struct pci_dev *pcidev, u32 guid, u16 pos)
+{
+	int devid = 0;
+	int inst = 0;
+	int err = 0;
+
+	while ((devid = pmt_telem_get_next_endpoint(devid))) {
+		struct telem_endpoint_info ep_info;
+
+		err = pmt_telem_get_endpoint_info(devid, &ep_info);
+		if (err)
+			return ERR_PTR(err);
+
+		if (ep_info.header.guid == guid && ep_info.pdev == pcidev) {
+			if (inst == pos)
+				return pmt_telem_register_endpoint(devid);
+			++inst;
+		}
+	}
+
+	return ERR_PTR(-ENXIO);
+}
+EXPORT_SYMBOL_NS_GPL(pmt_telem_find_and_register_endpoint, INTEL_PMT_TELEMETRY);
+
 static void pmt_telem_remove(struct auxiliary_device *auxdev)
 {
 	struct pmt_telem_priv *priv = auxiliary_get_drvdata(auxdev);
 	int i;
 
-	for (i = 0; i < priv->num_entries; i++)
-		intel_pmt_dev_destroy(&priv->entry[i], &pmt_telem_ns);
-}
+	mutex_lock(&ep_lock);
+	for (i = 0; i < priv->num_entries; i++) {
+		struct intel_pmt_entry *entry = &priv->entry[i];
+
+		kref_put(&entry->ep->kref, pmt_telem_ep_release);
+		intel_pmt_dev_destroy(entry, &pmt_telem_ns);
+	}
+	mutex_unlock(&ep_lock);
+};
 
 static int pmt_telem_probe(struct auxiliary_device *auxdev, const struct auxiliary_device_id *id)
 {
@@ -117,7 +300,9 @@ static int pmt_telem_probe(struct auxiliary_device *auxdev, const struct auxilia
 	for (i = 0; i < intel_vsec_dev->num_resources; i++) {
 		struct intel_pmt_entry *entry = &priv->entry[priv->num_entries];
 
+		mutex_lock(&ep_lock);
 		ret = intel_pmt_dev_create(entry, &pmt_telem_ns, intel_vsec_dev, i);
+		mutex_unlock(&ep_lock);
 		if (ret < 0)
 			goto abort_probe;
 		if (ret)
diff --git a/drivers/platform/x86/intel/pmt/telemetry.h b/drivers/platform/x86/intel/pmt/telemetry.h
new file mode 100644
index 000000000000..d45af5512b4e
--- /dev/null
+++ b/drivers/platform/x86/intel/pmt/telemetry.h
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TELEMETRY_H
+#define _TELEMETRY_H
+
+/* Telemetry types */
+#define PMT_TELEM_TELEMETRY	0
+#define PMT_TELEM_CRASHLOG	1
+
+struct telem_endpoint;
+struct pci_dev;
+
+struct telem_header {
+	u8	access_type;
+	u16	size;
+	u32	guid;
+	u32	base_offset;
+};
+
+struct telem_endpoint_info {
+	struct pci_dev		*pdev;
+	struct telem_header	header;
+};
+
+/**
+ * pmt_telem_get_next_endpoint() - Get next device id for a telemetry endpoint
+ * @start:  starting devid to look from
+ *
+ * This functions can be used in a while loop predicate to retrieve the devid
+ * of all available telemetry endpoints. Functions pmt_telem_get_next_endpoint()
+ * and pmt_telem_register_endpoint() can be used inside of the loop to examine
+ * endpoint info and register to receive a pointer to the endpoint. The pointer
+ * is then usable in the telemetry read calls to access the telemetry data.
+ *
+ * Return:
+ * * devid       - devid of the next present endpoint from start
+ * * 0           - when no more endpoints are present after start
+ */
+unsigned long pmt_telem_get_next_endpoint(unsigned long start);
+
+/**
+ * pmt_telem_register_endpoint() - Register a telemetry endpoint
+ * @devid: device id/handle of the telemetry endpoint
+ *
+ * Increments the kref usage counter for the endpoint.
+ *
+ * Return:
+ * * endpoint    - On success returns pointer to the telemetry endpoint
+ * * -ENXIO      - telemetry endpoint not found
+ */
+struct telem_endpoint *pmt_telem_register_endpoint(int devid);
+
+/**
+ * pmt_telem_unregister_endpoint() - Unregister a telemetry endpoint
+ * @ep:   ep structure to populate.
+ *
+ * Decrements the kref usage counter for the endpoint.
+ */
+void pmt_telem_unregister_endpoint(struct telem_endpoint *ep);
+
+/**
+ * pmt_telem_get_endpoint_info() - Get info for an endpoint from its devid
+ * @devid:  device id/handle of the telemetry endpoint
+ * @info:   Endpoint info structure to be populated
+ *
+ * Return:
+ * * 0           - Success
+ * * -ENXIO      - telemetry endpoint not found for the devid
+ * * -EINVAL     - @info is NULL
+ */
+int pmt_telem_get_endpoint_info(int devid, struct telem_endpoint_info *info);
+
+/**
+ * pmt_telem_find_and_register_endpoint() - Get a telemetry endpoint from
+ * pci_dev device, guid and pos
+ * @pdev:   PCI device inside the Intel vsec
+ * @guid:   GUID of the telemetry space
+ * @pos:    Instance of the guid
+ *
+ * Return:
+ * * endpoint    - On success returns pointer to the telemetry endpoint
+ * * -ENXIO      - telemetry endpoint not found
+ */
+struct telem_endpoint *pmt_telem_find_and_register_endpoint(struct pci_dev *pcidev,
+				u32 guid, u16 pos);
+
+/**
+ * pmt_telem_read() - Read qwords from counter sram using sample id
+ * @ep:     Telemetry endpoint to be read
+ * @id:     The beginning sample id of the metric(s) to be read
+ * @data:   Allocated qword buffer
+ * @count:  Number of qwords requested
+ *
+ * Callers must ensure reads are aligned. When the call returns -ENODEV,
+ * the device has been removed and callers should unregister the telemetry
+ * endpoint.
+ *
+ * Return:
+ * * 0           - Success
+ * * -ENODEV     - The device is not present.
+ * * -EINVAL     - The offset is out bounds
+ * * -EPIPE      - The device was removed during the read. Data written
+ *                 but should be considered invalid.
+ */
+int pmt_telem_read(struct telem_endpoint *ep, u32 id, u64 *data, u32 count);
+
+/**
+ * pmt_telem_read32() - Read qwords from counter sram using sample id
+ * @ep:     Telemetry endpoint to be read
+ * @id:     The beginning sample id of the metric(s) to be read
+ * @data:   Allocated dword buffer
+ * @count:  Number of dwords requested
+ *
+ * Callers must ensure reads are aligned. When the call returns -ENODEV,
+ * the device has been removed and callers should unregister the telemetry
+ * endpoint.
+ *
+ * Return:
+ * * 0           - Success
+ * * -ENODEV     - The device is not present.
+ * * -EINVAL     - The offset is out bounds
+ * * -EPIPE      - The device was removed during the read. Data written
+ *                 but should be considered invalid.
+ */
+int pmt_telem_read32(struct telem_endpoint *ep, u32 id, u32 *data, u32 count);
+
+#endif
diff --git a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
index 0b6d2c864437..2662fbbddf0c 100644
--- a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
+++ b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
@@ -234,6 +234,7 @@ struct perf_level {
  * @saved_clos_configs:	Save SST-CP CLOS configuration to store restore for suspend/resume
  * @saved_clos_assocs:	Save SST-CP CLOS association to store restore for suspend/resume
  * @saved_pp_control:	Save SST-PP control information to store restore for suspend/resume
+ * @write_blocked:	Write operation is blocked, so can't change SST state
  *
  * This structure is used store complete SST information for a power_domain. This information
  * is used to read/write request for any SST IOCTL. Each physical CPU package can have multiple
@@ -259,6 +260,7 @@ struct tpmi_per_power_domain_info {
 	u64 saved_clos_configs[4];
 	u64 saved_clos_assocs[4];
 	u64 saved_pp_control;
+	bool write_blocked;
 };
 
 /**
@@ -515,6 +517,9 @@ static long isst_if_clos_param(void __user *argp)
 		return -EINVAL;
 
 	if (clos_param.get_set) {
+		if (power_domain_info->write_blocked)
+			return -EPERM;
+
 		_write_cp_info("clos.min_freq", clos_param.min_freq_mhz,
 			       (SST_CLOS_CONFIG_0_OFFSET + clos_param.clos * SST_REG_SIZE),
 			       SST_CLOS_CONFIG_MIN_START, SST_CLOS_CONFIG_MIN_WIDTH,
@@ -602,6 +607,9 @@ static long isst_if_clos_assoc(void __user *argp)
 
 		power_domain_info = &sst_inst->power_domain_info[punit_id];
 
+		if (assoc_cmds.get_set && power_domain_info->write_blocked)
+			return -EPERM;
+
 		offset = SST_CLOS_ASSOC_0_OFFSET +
 				(punit_cpu_no / SST_CLOS_ASSOC_CPUS_PER_REG) * SST_REG_SIZE;
 		shift = punit_cpu_no % SST_CLOS_ASSOC_CPUS_PER_REG;
@@ -752,6 +760,9 @@ static int isst_if_set_perf_level(void __user *argp)
 	if (!power_domain_info)
 		return -EINVAL;
 
+	if (power_domain_info->write_blocked)
+		return -EPERM;
+
 	if (!(power_domain_info->pp_header.allowed_level_mask & BIT(perf_level.level)))
 		return -EINVAL;
 
@@ -809,6 +820,9 @@ static int isst_if_set_perf_feature(void __user *argp)
 	if (!power_domain_info)
 		return -EINVAL;
 
+	if (power_domain_info->write_blocked)
+		return -EPERM;
+
 	_write_pp_info("perf_feature", perf_feature.feature, SST_PP_CONTROL_OFFSET,
 		       SST_PP_FEATURE_STATE_START, SST_PP_FEATURE_STATE_WIDTH,
 		       SST_MUL_FACTOR_NONE)
@@ -1257,11 +1271,21 @@ static long isst_if_def_ioctl(struct file *file, unsigned int cmd,
 
 int tpmi_sst_dev_add(struct auxiliary_device *auxdev)
 {
+	bool read_blocked = 0, write_blocked = 0;
 	struct intel_tpmi_plat_info *plat_info;
 	struct tpmi_sst_struct *tpmi_sst;
 	int i, ret, pkg = 0, inst = 0;
 	int num_resources;
 
+	ret = tpmi_get_feature_status(auxdev, TPMI_ID_SST, &read_blocked, &write_blocked);
+	if (ret)
+		dev_info(&auxdev->dev, "Can't read feature status: ignoring read/write blocked status\n");
+
+	if (read_blocked) {
+		dev_info(&auxdev->dev, "Firmware has blocked reads, exiting\n");
+		return -ENODEV;
+	}
+
 	plat_info = tpmi_get_platform_data(auxdev);
 	if (!plat_info) {
 		dev_err(&auxdev->dev, "No platform info\n");
@@ -1306,6 +1330,7 @@ int tpmi_sst_dev_add(struct auxiliary_device *auxdev)
 		tpmi_sst->power_domain_info[i].package_id = pkg;
 		tpmi_sst->power_domain_info[i].power_domain_id = i;
 		tpmi_sst->power_domain_info[i].auxdev = auxdev;
+		tpmi_sst->power_domain_info[i].write_blocked = write_blocked;
 		tpmi_sst->power_domain_info[i].sst_base = devm_ioremap_resource(&auxdev->dev, res);
 		if (IS_ERR(tpmi_sst->power_domain_info[i].sst_base))
 			return PTR_ERR(tpmi_sst->power_domain_info[i].sst_base);
diff --git a/drivers/platform/x86/intel/telemetry/core.c b/drivers/platform/x86/intel/telemetry/core.c
index fdf55b5d6948..e4be40f73eeb 100644
--- a/drivers/platform/x86/intel/telemetry/core.c
+++ b/drivers/platform/x86/intel/telemetry/core.c
@@ -102,7 +102,7 @@ static const struct telemetry_core_ops telm_defpltops = {
 /**
  * telemetry_update_events() - Update telemetry Configuration
  * @pss_evtconfig: PSS related config. No change if num_evts = 0.
- * @pss_evtconfig: IOSS related config. No change if num_evts = 0.
+ * @ioss_evtconfig: IOSS related config. No change if num_evts = 0.
  *
  * This API updates the IOSS & PSS Telemetry configuration. Old config
  * is overwritten. Call telemetry_reset_events when logging is over
@@ -176,7 +176,7 @@ EXPORT_SYMBOL_GPL(telemetry_reset_events);
 /**
  * telemetry_get_eventconfig() - Returns the pss and ioss events enabled
  * @pss_evtconfig: Pointer to PSS related configuration.
- * @pss_evtconfig: Pointer to IOSS related configuration.
+ * @ioss_evtconfig: Pointer to IOSS related configuration.
  * @pss_len:	   Number of u32 elements allocated for pss_evtconfig array
  * @ioss_len:	   Number of u32 elements allocated for ioss_evtconfig array
  *
diff --git a/drivers/platform/x86/intel/tpmi.c b/drivers/platform/x86/intel/tpmi.c
index 311abcac894a..e73cdea67fff 100644
--- a/drivers/platform/x86/intel/tpmi.c
+++ b/drivers/platform/x86/intel/tpmi.c
@@ -171,19 +171,6 @@ struct tpmi_feature_state {
 } __packed;
 
 /*
- * List of supported TMPI IDs.
- * Some TMPI IDs are not used by Linux, so the numbers are not consecutive.
- */
-enum intel_tpmi_id {
-	TPMI_ID_RAPL = 0, /* Running Average Power Limit */
-	TPMI_ID_PEM = 1, /* Power and Perf excursion Monitor */
-	TPMI_ID_UNCORE = 2, /* Uncore Frequency Scaling */
-	TPMI_ID_SST = 5, /* Speed Select Technology */
-	TPMI_CONTROL_ID = 0x80, /* Special ID for getting feature status */
-	TPMI_INFO_ID = 0x81, /* Special ID for PCI BDF and Package ID information */
-};
-
-/*
  * The size from hardware is in u32 units. This size is from a trusted hardware,
  * but better to verify for pre silicon platforms. Set size to 0, when invalid.
  */
@@ -345,8 +332,8 @@ err_unlock:
 	return ret;
 }
 
-int tpmi_get_feature_status(struct auxiliary_device *auxdev, int feature_id,
-			    int *locked, int *disabled)
+int tpmi_get_feature_status(struct auxiliary_device *auxdev,
+			    int feature_id, bool *read_blocked, bool *write_blocked)
 {
 	struct intel_vsec_device *intel_vsec_dev = dev_to_ivdev(auxdev->dev.parent);
 	struct intel_tpmi_info *tpmi_info = auxiliary_get_drvdata(&intel_vsec_dev->auxdev);
@@ -357,8 +344,8 @@ int tpmi_get_feature_status(struct auxiliary_device *auxdev, int feature_id,
 	if (ret)
 		return ret;
 
-	*locked = feature_state.locked;
-	*disabled = !feature_state.enabled;
+	*read_blocked = feature_state.read_blocked;
+	*write_blocked = feature_state.write_blocked;
 
 	return 0;
 }
@@ -598,9 +585,21 @@ static int tpmi_create_device(struct intel_tpmi_info *tpmi_info,
 	struct intel_vsec_device *vsec_dev = tpmi_info->vsec_dev;
 	char feature_id_name[TPMI_FEATURE_NAME_LEN];
 	struct intel_vsec_device *feature_vsec_dev;
+	struct tpmi_feature_state feature_state;
 	struct resource *res, *tmp;
 	const char *name;
-	int i;
+	int i, ret;
+
+	ret = tpmi_read_feature_status(tpmi_info, pfs->pfs_header.tpmi_id, &feature_state);
+	if (ret)
+		return ret;
+
+	/*
+	 * If not enabled, continue to look at other features in the PFS, so return -EOPNOTSUPP.
+	 * This will not cause failure of loading of this driver.
+	 */
+	if (!feature_state.enabled)
+		return -EOPNOTSUPP;
 
 	name = intel_tpmi_name(pfs->pfs_header.tpmi_id);
 	if (!name)
diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
index 4fb790552c47..bd75d61ff8a6 100644
--- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
+++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
@@ -66,6 +66,7 @@ struct tpmi_uncore_struct {
 	int min_ratio;
 	struct tpmi_uncore_power_domain_info *pd_info;
 	struct tpmi_uncore_cluster_info root_cluster;
+	bool write_blocked;
 };
 
 #define UNCORE_GENMASK_MIN_RATIO	GENMASK_ULL(21, 15)
@@ -157,6 +158,9 @@ static int uncore_write_control_freq(struct uncore_data *data, unsigned int inpu
 	cluster_info = container_of(data, struct tpmi_uncore_cluster_info, uncore_data);
 	uncore_root = cluster_info->uncore_root;
 
+	if (uncore_root->write_blocked)
+		return -EPERM;
+
 	/* Update each cluster in a package */
 	if (cluster_info->root_domain) {
 		struct tpmi_uncore_struct *uncore_root = cluster_info->uncore_root;
@@ -233,11 +237,21 @@ static void remove_cluster_entries(struct tpmi_uncore_struct *tpmi_uncore)
 
 static int uncore_probe(struct auxiliary_device *auxdev, const struct auxiliary_device_id *id)
 {
+	bool read_blocked = 0, write_blocked = 0;
 	struct intel_tpmi_plat_info *plat_info;
 	struct tpmi_uncore_struct *tpmi_uncore;
 	int ret, i, pkg = 0;
 	int num_resources;
 
+	ret = tpmi_get_feature_status(auxdev, TPMI_ID_UNCORE, &read_blocked, &write_blocked);
+	if (ret)
+		dev_info(&auxdev->dev, "Can't read feature status: ignoring blocked status\n");
+
+	if (read_blocked) {
+		dev_info(&auxdev->dev, "Firmware has blocked reads, exiting\n");
+		return -ENODEV;
+	}
+
 	/* Get number of power domains, which is equal to number of resources */
 	num_resources = tpmi_get_resource_count(auxdev);
 	if (!num_resources)
@@ -266,6 +280,7 @@ static int uncore_probe(struct auxiliary_device *auxdev, const struct auxiliary_
 	}
 
 	tpmi_uncore->power_domain_count = num_resources;
+	tpmi_uncore->write_blocked = write_blocked;
 
 	/* Get the package ID from the TPMI core */
 	plat_info = tpmi_get_platform_data(auxdev);
diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c
index a3b25253b6fd..a5e0f5c22179 100644
--- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c
+++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c
@@ -205,6 +205,16 @@ static const struct x86_cpu_id intel_uncore_cpu_ids[] = {
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D,	NULL),
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, NULL),
 	X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE, NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L, NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L, NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(CANNONLAKE_L, NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, NULL),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, NULL),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, NULL),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, NULL),
@@ -212,6 +222,9 @@ static const struct x86_cpu_id intel_uncore_cpu_ids[] = {
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, NULL),
 	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, NULL),
 	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(ARROWLAKE, NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(ARROWLAKE_H, NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(LUNARLAKE_M, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_uncore_cpu_ids);
diff --git a/drivers/platform/x86/intel/vbtn.c b/drivers/platform/x86/intel/vbtn.c
index 6fa1735ad7a4..210b0a81b7ec 100644
--- a/drivers/platform/x86/intel/vbtn.c
+++ b/drivers/platform/x86/intel/vbtn.c
@@ -73,10 +73,10 @@ struct intel_vbtn_priv {
 	bool wakeup_mode;
 };
 
-static void detect_tablet_mode(struct platform_device *device)
+static void detect_tablet_mode(struct device *dev)
 {
-	struct intel_vbtn_priv *priv = dev_get_drvdata(&device->dev);
-	acpi_handle handle = ACPI_HANDLE(&device->dev);
+	struct intel_vbtn_priv *priv = dev_get_drvdata(dev);
+	acpi_handle handle = ACPI_HANDLE(dev);
 	unsigned long long vgbs;
 	acpi_status status;
 	int m;
@@ -89,6 +89,8 @@ static void detect_tablet_mode(struct platform_device *device)
 	input_report_switch(priv->switches_dev, SW_TABLET_MODE, m);
 	m = (vgbs & VGBS_DOCK_MODE_FLAG) ? 1 : 0;
 	input_report_switch(priv->switches_dev, SW_DOCK, m);
+
+	input_sync(priv->switches_dev);
 }
 
 /*
@@ -134,7 +136,7 @@ static int intel_vbtn_input_setup(struct platform_device *device)
 	priv->switches_dev->id.bustype = BUS_HOST;
 
 	if (priv->has_switches) {
-		detect_tablet_mode(device);
+		detect_tablet_mode(&device->dev);
 
 		ret = input_register_device(priv->switches_dev);
 		if (ret)
@@ -198,6 +200,9 @@ static void notify_handler(acpi_handle handle, u32 event, void *context)
 	autorelease = val && (!ke_rel || ke_rel->type == KE_IGNORE);
 
 	sparse_keymap_report_event(input_dev, event, val, autorelease);
+
+	/* Some devices need this to report further events */
+	acpi_evaluate_object(handle, "VBDL", NULL, NULL);
 }
 
 /*
@@ -352,7 +357,13 @@ static void intel_vbtn_pm_complete(struct device *dev)
 
 static int intel_vbtn_pm_resume(struct device *dev)
 {
+	struct intel_vbtn_priv *priv = dev_get_drvdata(dev);
+
 	intel_vbtn_pm_complete(dev);
+
+	if (priv->has_switches)
+		detect_tablet_mode(dev);
+
 	return 0;
 }
 
diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c
index c1f9e4471b28..778eb0aa3479 100644
--- a/drivers/platform/x86/intel/vsec.c
+++ b/drivers/platform/x86/intel/vsec.c
@@ -15,6 +15,7 @@
 
 #include <linux/auxiliary_bus.h>
 #include <linux/bits.h>
+#include <linux/cleanup.h>
 #include <linux/delay.h>
 #include <linux/kernel.h>
 #include <linux/idr.h>
@@ -24,13 +25,6 @@
 
 #include "vsec.h"
 
-/* Intel DVSEC offsets */
-#define INTEL_DVSEC_ENTRIES		0xA
-#define INTEL_DVSEC_SIZE		0xB
-#define INTEL_DVSEC_TABLE		0xC
-#define INTEL_DVSEC_TABLE_BAR(x)	((x) & GENMASK(2, 0))
-#define INTEL_DVSEC_TABLE_OFFSET(x)	((x) & GENMASK(31, 3))
-#define TABLE_OFFSET_SHIFT		3
 #define PMT_XA_START			0
 #define PMT_XA_MAX			INT_MAX
 #define PMT_XA_LIMIT			XA_LIMIT(PMT_XA_START, PMT_XA_MAX)
@@ -39,34 +33,6 @@ static DEFINE_IDA(intel_vsec_ida);
 static DEFINE_IDA(intel_vsec_sdsi_ida);
 static DEFINE_XARRAY_ALLOC(auxdev_array);
 
-/**
- * struct intel_vsec_header - Common fields of Intel VSEC and DVSEC registers.
- * @rev:         Revision ID of the VSEC/DVSEC register space
- * @length:      Length of the VSEC/DVSEC register space
- * @id:          ID of the feature
- * @num_entries: Number of instances of the feature
- * @entry_size:  Size of the discovery table for each feature
- * @tbir:        BAR containing the discovery tables
- * @offset:      BAR offset of start of the first discovery table
- */
-struct intel_vsec_header {
-	u8	rev;
-	u16	length;
-	u16	id;
-	u8	num_entries;
-	u8	entry_size;
-	u8	tbir;
-	u32	offset;
-};
-
-enum intel_vsec_id {
-	VSEC_ID_TELEMETRY	= 2,
-	VSEC_ID_WATCHER		= 3,
-	VSEC_ID_CRASHLOG	= 4,
-	VSEC_ID_SDSI		= 65,
-	VSEC_ID_TPMI		= 66,
-};
-
 static const char *intel_vsec_name(enum intel_vsec_id id)
 {
 	switch (id) {
@@ -120,6 +86,8 @@ static void intel_vsec_dev_release(struct device *dev)
 {
 	struct intel_vsec_device *intel_vsec_dev = dev_to_ivdev(dev);
 
+	xa_erase(&auxdev_array, intel_vsec_dev->id);
+
 	mutex_lock(&vsec_ida_lock);
 	ida_free(intel_vsec_dev->ida, intel_vsec_dev->auxdev.id);
 	mutex_unlock(&vsec_ida_lock);
@@ -135,19 +103,28 @@ int intel_vsec_add_aux(struct pci_dev *pdev, struct device *parent,
 	struct auxiliary_device *auxdev = &intel_vsec_dev->auxdev;
 	int ret, id;
 
-	mutex_lock(&vsec_ida_lock);
-	ret = ida_alloc(intel_vsec_dev->ida, GFP_KERNEL);
-	mutex_unlock(&vsec_ida_lock);
+	if (!parent)
+		return -EINVAL;
+
+	ret = xa_alloc(&auxdev_array, &intel_vsec_dev->id, intel_vsec_dev,
+		       PMT_XA_LIMIT, GFP_KERNEL);
 	if (ret < 0) {
 		kfree(intel_vsec_dev->resource);
 		kfree(intel_vsec_dev);
 		return ret;
 	}
 
-	if (!parent)
-		parent = &pdev->dev;
+	mutex_lock(&vsec_ida_lock);
+	id = ida_alloc(intel_vsec_dev->ida, GFP_KERNEL);
+	mutex_unlock(&vsec_ida_lock);
+	if (id < 0) {
+		xa_erase(&auxdev_array, intel_vsec_dev->id);
+		kfree(intel_vsec_dev->resource);
+		kfree(intel_vsec_dev);
+		return id;
+	}
 
-	auxdev->id = ret;
+	auxdev->id = id;
 	auxdev->name = name;
 	auxdev->dev.parent = parent;
 	auxdev->dev.release = intel_vsec_dev_release;
@@ -164,29 +141,27 @@ int intel_vsec_add_aux(struct pci_dev *pdev, struct device *parent,
 		return ret;
 	}
 
-	ret = devm_add_action_or_reset(parent, intel_vsec_remove_aux,
+	return devm_add_action_or_reset(parent, intel_vsec_remove_aux,
 				       auxdev);
-	if (ret < 0)
-		return ret;
-
-	/* Add auxdev to list */
-	ret = xa_alloc(&auxdev_array, &id, intel_vsec_dev, PMT_XA_LIMIT,
-		       GFP_KERNEL);
-	if (ret)
-		return ret;
-
-	return 0;
 }
 EXPORT_SYMBOL_NS_GPL(intel_vsec_add_aux, INTEL_VSEC);
 
 static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *header,
 			      struct intel_vsec_platform_info *info)
 {
-	struct intel_vsec_device *intel_vsec_dev;
-	struct resource *res, *tmp;
+	struct intel_vsec_device __free(kfree) *intel_vsec_dev = NULL;
+	struct resource __free(kfree) *res = NULL;
+	struct resource *tmp;
+	struct device *parent;
 	unsigned long quirks = info->quirks;
+	u64 base_addr;
 	int i;
 
+	if (info->parent)
+		parent = info->parent;
+	else
+		parent = &pdev->dev;
+
 	if (!intel_vsec_supported(header->id, info->caps))
 		return -EINVAL;
 
@@ -205,37 +180,50 @@ static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *he
 		return -ENOMEM;
 
 	res = kcalloc(header->num_entries, sizeof(*res), GFP_KERNEL);
-	if (!res) {
-		kfree(intel_vsec_dev);
+	if (!res)
 		return -ENOMEM;
-	}
 
 	if (quirks & VSEC_QUIRK_TABLE_SHIFT)
 		header->offset >>= TABLE_OFFSET_SHIFT;
 
+	if (info->base_addr)
+		base_addr = info->base_addr;
+	else
+		base_addr = pdev->resource[header->tbir].start;
+
 	/*
 	 * The DVSEC/VSEC contains the starting offset and count for a block of
 	 * discovery tables. Create a resource array of these tables to the
 	 * auxiliary device driver.
 	 */
 	for (i = 0, tmp = res; i < header->num_entries; i++, tmp++) {
-		tmp->start = pdev->resource[header->tbir].start +
-			     header->offset + i * (header->entry_size * sizeof(u32));
+		tmp->start = base_addr + header->offset + i * (header->entry_size * sizeof(u32));
 		tmp->end = tmp->start + (header->entry_size * sizeof(u32)) - 1;
 		tmp->flags = IORESOURCE_MEM;
+
+		/* Check resource is not in use */
+		if (!request_mem_region(tmp->start, resource_size(tmp), ""))
+			return -EBUSY;
+
+		release_mem_region(tmp->start, resource_size(tmp));
 	}
 
 	intel_vsec_dev->pcidev = pdev;
-	intel_vsec_dev->resource = res;
+	intel_vsec_dev->resource = no_free_ptr(res);
 	intel_vsec_dev->num_resources = header->num_entries;
-	intel_vsec_dev->info = info;
+	intel_vsec_dev->quirks = info->quirks;
+	intel_vsec_dev->base_addr = info->base_addr;
 
 	if (header->id == VSEC_ID_SDSI)
 		intel_vsec_dev->ida = &intel_vsec_sdsi_ida;
 	else
 		intel_vsec_dev->ida = &intel_vsec_ida;
 
-	return intel_vsec_add_aux(pdev, NULL, intel_vsec_dev,
+	/*
+	 * Pass the ownership of intel_vsec_dev and resource within it to
+	 * intel_vsec_add_aux()
+	 */
+	return intel_vsec_add_aux(pdev, parent, no_free_ptr(intel_vsec_dev),
 				  intel_vsec_name(header->id));
 }
 
@@ -353,6 +341,16 @@ static bool intel_vsec_walk_vsec(struct pci_dev *pdev,
 	return have_devices;
 }
 
+void intel_vsec_register(struct pci_dev *pdev,
+			 struct intel_vsec_platform_info *info)
+{
+	if (!pdev || !info)
+		return;
+
+	intel_vsec_walk_header(pdev, info);
+}
+EXPORT_SYMBOL_NS_GPL(intel_vsec_register, INTEL_VSEC);
+
 static int intel_vsec_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct intel_vsec_platform_info *info;
@@ -421,6 +419,11 @@ static const struct intel_vsec_platform_info tgl_info = {
 	.quirks = VSEC_QUIRK_TABLE_SHIFT | VSEC_QUIRK_EARLY_HW,
 };
 
+/* LNL info */
+static const struct intel_vsec_platform_info lnl_info = {
+	.caps = VSEC_CAP_TELEMETRY | VSEC_CAP_WATCHER,
+};
+
 #define PCI_DEVICE_ID_INTEL_VSEC_ADL		0x467d
 #define PCI_DEVICE_ID_INTEL_VSEC_DG1		0x490e
 #define PCI_DEVICE_ID_INTEL_VSEC_MTL_M		0x7d0d
@@ -428,6 +431,7 @@ static const struct intel_vsec_platform_info tgl_info = {
 #define PCI_DEVICE_ID_INTEL_VSEC_OOBMSM		0x09a7
 #define PCI_DEVICE_ID_INTEL_VSEC_RPL		0xa77d
 #define PCI_DEVICE_ID_INTEL_VSEC_TGL		0x9a0d
+#define PCI_DEVICE_ID_INTEL_VSEC_LNL_M		0x647d
 static const struct pci_device_id intel_vsec_pci_ids[] = {
 	{ PCI_DEVICE_DATA(INTEL, VSEC_ADL, &tgl_info) },
 	{ PCI_DEVICE_DATA(INTEL, VSEC_DG1, &dg1_info) },
@@ -436,6 +440,7 @@ static const struct pci_device_id intel_vsec_pci_ids[] = {
 	{ PCI_DEVICE_DATA(INTEL, VSEC_OOBMSM, &oobmsm_info) },
 	{ PCI_DEVICE_DATA(INTEL, VSEC_RPL, &tgl_info) },
 	{ PCI_DEVICE_DATA(INTEL, VSEC_TGL, &tgl_info) },
+	{ PCI_DEVICE_DATA(INTEL, VSEC_LNL_M, &lnl_info) },
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, intel_vsec_pci_ids);
diff --git a/drivers/platform/x86/intel/vsec.h b/drivers/platform/x86/intel/vsec.h
index 0fd042c171ba..e23e76129691 100644
--- a/drivers/platform/x86/intel/vsec.h
+++ b/drivers/platform/x86/intel/vsec.h
@@ -11,9 +11,45 @@
 #define VSEC_CAP_SDSI		BIT(3)
 #define VSEC_CAP_TPMI		BIT(4)
 
+/* Intel DVSEC offsets */
+#define INTEL_DVSEC_ENTRIES		0xA
+#define INTEL_DVSEC_SIZE		0xB
+#define INTEL_DVSEC_TABLE		0xC
+#define INTEL_DVSEC_TABLE_BAR(x)	((x) & GENMASK(2, 0))
+#define INTEL_DVSEC_TABLE_OFFSET(x)	((x) & GENMASK(31, 3))
+#define TABLE_OFFSET_SHIFT		3
+
 struct pci_dev;
 struct resource;
 
+enum intel_vsec_id {
+	VSEC_ID_TELEMETRY	= 2,
+	VSEC_ID_WATCHER		= 3,
+	VSEC_ID_CRASHLOG	= 4,
+	VSEC_ID_SDSI		= 65,
+	VSEC_ID_TPMI		= 66,
+};
+
+/**
+ * struct intel_vsec_header - Common fields of Intel VSEC and DVSEC registers.
+ * @rev:         Revision ID of the VSEC/DVSEC register space
+ * @length:      Length of the VSEC/DVSEC register space
+ * @id:          ID of the feature
+ * @num_entries: Number of instances of the feature
+ * @entry_size:  Size of the discovery table for each feature
+ * @tbir:        BAR containing the discovery tables
+ * @offset:      BAR offset of start of the first discovery table
+ */
+struct intel_vsec_header {
+	u8	rev;
+	u16	length;
+	u16	id;
+	u8	num_entries;
+	u8	entry_size;
+	u8	tbir;
+	u32	offset;
+};
+
 enum intel_vsec_quirks {
 	/* Watcher feature not supported */
 	VSEC_QUIRK_NO_WATCHER	= BIT(0),
@@ -33,9 +69,11 @@ enum intel_vsec_quirks {
 
 /* Platform specific data */
 struct intel_vsec_platform_info {
+	struct device *parent;
 	struct intel_vsec_header **headers;
 	unsigned long caps;
 	unsigned long quirks;
+	u64 base_addr;
 };
 
 struct intel_vsec_device {
@@ -43,10 +81,12 @@ struct intel_vsec_device {
 	struct pci_dev *pcidev;
 	struct resource *resource;
 	struct ida *ida;
-	struct intel_vsec_platform_info *info;
 	int num_resources;
+	int id; /* xa */
 	void *priv_data;
 	size_t priv_data_size;
+	unsigned long quirks;
+	u64 base_addr;
 };
 
 int intel_vsec_add_aux(struct pci_dev *pdev, struct device *parent,
@@ -62,4 +102,7 @@ static inline struct intel_vsec_device *auxdev_to_ivdev(struct auxiliary_device
 {
 	return container_of(auxdev, struct intel_vsec_device, auxdev);
 }
+
+void intel_vsec_register(struct pci_dev *pdev,
+			 struct intel_vsec_platform_info *info);
 #endif
diff --git a/drivers/platform/x86/intel/wmi/sbl-fw-update.c b/drivers/platform/x86/intel/wmi/sbl-fw-update.c
index 3c86e0108a24..9cf5ed0f8dc2 100644
--- a/drivers/platform/x86/intel/wmi/sbl-fw-update.c
+++ b/drivers/platform/x86/intel/wmi/sbl-fw-update.c
@@ -25,18 +25,13 @@
 
 static int get_fwu_request(struct device *dev, u32 *out)
 {
-	struct acpi_buffer result = {ACPI_ALLOCATE_BUFFER, NULL};
 	union acpi_object *obj;
-	acpi_status status;
 
-	status = wmi_query_block(INTEL_WMI_SBL_GUID, 0, &result);
-	if (ACPI_FAILURE(status)) {
-		dev_err(dev, "wmi_query_block failed\n");
+	obj = wmidev_block_query(to_wmi_device(dev), 0);
+	if (!obj)
 		return -ENODEV;
-	}
 
-	obj = (union acpi_object *)result.pointer;
-	if (!obj || obj->type != ACPI_TYPE_INTEGER) {
+	if (obj->type != ACPI_TYPE_INTEGER) {
 		dev_warn(dev, "wmi_query_block returned invalid value\n");
 		kfree(obj);
 		return -EINVAL;
@@ -58,7 +53,7 @@ static int set_fwu_request(struct device *dev, u32 in)
 	input.length = sizeof(u32);
 	input.pointer = &value;
 
-	status = wmi_set_block(INTEL_WMI_SBL_GUID, 0, &input);
+	status = wmidev_block_set(to_wmi_device(dev), 0, &input);
 	if (ACPI_FAILURE(status)) {
 		dev_err(dev, "wmi_set_block failed\n");
 		return -ENODEV;
diff --git a/drivers/platform/x86/intel/wmi/thunderbolt.c b/drivers/platform/x86/intel/wmi/thunderbolt.c
index fc333ff82d1e..e2ad3f46f356 100644
--- a/drivers/platform/x86/intel/wmi/thunderbolt.c
+++ b/drivers/platform/x86/intel/wmi/thunderbolt.c
@@ -32,8 +32,7 @@ static ssize_t force_power_store(struct device *dev,
 	mode = hex_to_bin(buf[0]);
 	dev_dbg(dev, "force_power: storing %#x\n", mode);
 	if (mode == 0 || mode == 1) {
-		status = wmi_evaluate_method(INTEL_WMI_THUNDERBOLT_GUID, 0, 1,
-					     &input, NULL);
+		status = wmidev_evaluate_method(to_wmi_device(dev), 0, 1, &input, NULL);
 		if (ACPI_FAILURE(status)) {
 			dev_dbg(dev, "force_power: failed to evaluate ACPI method\n");
 			return -ENODEV;
diff --git a/drivers/platform/x86/intel_ips.c b/drivers/platform/x86/intel_ips.c
index 4dfdbfca6841..ba38649cc142 100644
--- a/drivers/platform/x86/intel_ips.c
+++ b/drivers/platform/x86/intel_ips.c
@@ -590,6 +590,8 @@ static void ips_disable_gpu_turbo(struct ips_driver *ips)
  * @ips: IPS driver struct
  *
  * Check whether the MCP is over its thermal or power budget.
+ *
+ * Returns: %true if the temp or power has exceeded its maximum, else %false
  */
 static bool mcp_exceeded(struct ips_driver *ips)
 {
@@ -619,6 +621,8 @@ static bool mcp_exceeded(struct ips_driver *ips)
  * @cpu: CPU number to check
  *
  * Check a given CPU's average temp or power is over its limit.
+ *
+ * Returns: %true if the temp or power has exceeded its maximum, else %false
  */
 static bool cpu_exceeded(struct ips_driver *ips, int cpu)
 {
@@ -645,6 +649,8 @@ static bool cpu_exceeded(struct ips_driver *ips, int cpu)
  * @ips: IPS driver struct
  *
  * Check the MCH temp & power against their maximums.
+ *
+ * Returns: %true if the temp or power has exceeded its maximum, else %false
  */
 static bool mch_exceeded(struct ips_driver *ips)
 {
@@ -742,12 +748,13 @@ static void update_turbo_limits(struct ips_driver *ips)
  *   - down (at TDP limit)
  *     - adjust both CPU and GPU down if possible
  *
-		cpu+ gpu+	cpu+gpu-	cpu-gpu+	cpu-gpu-
-cpu < gpu <	cpu+gpu+	cpu+		gpu+		nothing
-cpu < gpu >=	cpu+gpu-(mcp<)	cpu+gpu-(mcp<)	gpu-		gpu-
-cpu >= gpu <	cpu-gpu+(mcp<)	cpu-		cpu-gpu+(mcp<)	cpu-
-cpu >= gpu >=	cpu-gpu-	cpu-gpu-	cpu-gpu-	cpu-gpu-
+ *              |cpu+ gpu+      cpu+gpu-        cpu-gpu+        cpu-gpu-
+ * cpu < gpu <  |cpu+gpu+       cpu+            gpu+            nothing
+ * cpu < gpu >= |cpu+gpu-(mcp<) cpu+gpu-(mcp<)  gpu-            gpu-
+ * cpu >= gpu < |cpu-gpu+(mcp<) cpu-            cpu-gpu+(mcp<)  cpu-
+ * cpu >= gpu >=|cpu-gpu-       cpu-gpu-        cpu-gpu-        cpu-gpu-
  *
+ * Returns: %0
  */
 static int ips_adjust(void *data)
 {
@@ -935,11 +942,13 @@ static void monitor_timeout(struct timer_list *t)
  * @data: ips driver structure
  *
  * This is the main function for the IPS driver.  It monitors power and
- * tempurature in the MCP and adjusts CPU and GPU power clams accordingly.
+ * temperature in the MCP and adjusts CPU and GPU power clamps accordingly.
  *
- * We keep a 5s moving average of power consumption and tempurature.  Using
+ * We keep a 5s moving average of power consumption and temperature.  Using
  * that data, along with CPU vs GPU preference, we adjust the power clamps
  * up or down.
+ *
+ * Returns: %0 on success or -errno on error
  */
 static int ips_monitor(void *data)
 {
@@ -1105,39 +1114,6 @@ static int ips_monitor(void *data)
 	return 0;
 }
 
-#if 0
-#define THM_DUMPW(reg) \
-	{ \
-	u16 val = thm_readw(reg); \
-	dev_dbg(ips->dev, #reg ": 0x%04x\n", val); \
-	}
-#define THM_DUMPL(reg) \
-	{ \
-	u32 val = thm_readl(reg); \
-	dev_dbg(ips->dev, #reg ": 0x%08x\n", val); \
-	}
-#define THM_DUMPQ(reg) \
-	{ \
-	u64 val = thm_readq(reg); \
-	dev_dbg(ips->dev, #reg ": 0x%016x\n", val); \
-	}
-
-static void dump_thermal_info(struct ips_driver *ips)
-{
-	u16 ptl;
-
-	ptl = thm_readw(THM_PTL);
-	dev_dbg(ips->dev, "Processor temp limit: %d\n", ptl);
-
-	THM_DUMPW(THM_CTA);
-	THM_DUMPW(THM_TRC);
-	THM_DUMPW(THM_CTV1);
-	THM_DUMPL(THM_STS);
-	THM_DUMPW(THM_PTV);
-	THM_DUMPQ(THM_MGTV);
-}
-#endif
-
 /**
  * ips_irq_handler - handle temperature triggers and other IPS events
  * @irq: irq number
@@ -1146,6 +1122,8 @@ static void dump_thermal_info(struct ips_driver *ips)
  * Handle temperature limit trigger events, generally by lowering the clamps.
  * If we're at a critical limit, we clamp back to the lowest possible value
  * to prevent emergency shutdown.
+ *
+ * Returns: IRQ_NONE or IRQ_HANDLED
  */
 static irqreturn_t ips_irq_handler(int irq, void *arg)
 {
@@ -1293,9 +1271,12 @@ static void ips_debugfs_init(struct ips_driver *ips)
 
 /**
  * ips_detect_cpu - detect whether CPU supports IPS
+ * @ips: IPS driver struct
  *
  * Walk our list and see if we're on a supported CPU.  If we find one,
  * return the limits for it.
+ *
+ * Returns: the &ips_mcp_limits struct that matches the boot CPU or %NULL
  */
 static struct ips_mcp_limits *ips_detect_cpu(struct ips_driver *ips)
 {
@@ -1352,6 +1333,8 @@ static struct ips_mcp_limits *ips_detect_cpu(struct ips_driver *ips)
  * monitor and control graphics turbo mode.  If we can find them, we can
  * enable graphics turbo, otherwise we must disable it to avoid exceeding
  * thermal and power limits in the MCP.
+ *
+ * Returns: %true if the required symbols are found, else %false
  */
 static bool ips_get_i915_syms(struct ips_driver *ips)
 {
diff --git a/drivers/platform/x86/silicom-platform.c b/drivers/platform/x86/silicom-platform.c
new file mode 100644
index 000000000000..6ce43ccb3112
--- /dev/null
+++ b/drivers/platform/x86/silicom-platform.c
@@ -0,0 +1,1004 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// silicom-platform.c - Silicom MEC170x platform driver
+//
+// Copyright (C) 2023 Henry Shi <henrys@silicom-usa.com>
+#include <linux/bitfield.h>
+#include <linux/bits.h>
+#include <linux/dmi.h>
+#include <linux/hwmon.h>
+#include <linux/init.h>
+#include <linux/ioport.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/kobject.h>
+#include <linux/led-class-multicolor.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/platform_device.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include <linux/units.h>
+
+#include <linux/gpio/driver.h>
+
+#define MEC_POWER_CYCLE_ADDR 0x24
+#define MEC_EFUSE_LSB_ADDR   0x28
+#define MEC_GPIO_IN_POS      0x08
+#define MEC_IO_BASE          0x0800
+#define MEC_IO_LEN           0x8
+#define IO_REG_BANK          0x0
+#define DEFAULT_CHAN_LO      0
+#define DEFAULT_CHAN_HI      0
+#define DEFAULT_CHAN_LO_T    0xc
+#define MEC_ADDR             (MEC_IO_BASE + 0x02)
+#define EC_ADDR_LSB          MEC_ADDR
+#define SILICOM_MEC_MAGIC    0x5a
+
+#define MEC_PORT_CHANNEL_MASK GENMASK(2, 0)
+#define MEC_PORT_DWORD_OFFSET GENMASK(31, 3)
+#define MEC_DATA_OFFSET_MASK  GENMASK(1, 0)
+#define MEC_PORT_OFFSET_MASK  GENMASK(7, 2)
+
+#define MEC_TEMP_LOC          GENMASK(31, 16)
+#define MEC_VERSION_LOC       GENMASK(15, 8)
+#define MEC_VERSION_MAJOR     GENMASK(15, 14)
+#define MEC_VERSION_MINOR     GENMASK(13, 8)
+
+#define EC_ADDR_MSB           (MEC_IO_BASE + 0x3)
+#define MEC_DATA_OFFSET(offset) (MEC_IO_BASE + 0x04 + (offset))
+
+#define OFFSET_BIT_TO_CHANNEL(off, bit) ((((off) + 0x014) << 3) | (bit))
+#define CHANNEL_TO_OFFSET(chan) (((chan) >> 3) - 0x14)
+
+static DEFINE_MUTEX(mec_io_mutex);
+static unsigned int efuse_status;
+static unsigned int mec_uc_version;
+static unsigned int power_cycle;
+
+static const struct hwmon_channel_info *silicom_fan_control_info[] = {
+	HWMON_CHANNEL_INFO(fan, HWMON_F_INPUT | HWMON_F_LABEL),
+	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT | HWMON_T_LABEL),
+	NULL
+};
+
+struct silicom_platform_info {
+	int io_base;
+	int io_len;
+	struct led_classdev_mc *led_info;
+	struct gpio_chip *gpiochip;
+	u8 *gpio_channels;
+	u16 ngpio;
+};
+
+static const char * const plat_0222_gpio_names[] = {
+	"AUTOM0_SFP_TX_FAULT",
+	"SLOT2_LED_OUT",
+	"SIM_M2_SLOT2_B_DET",
+	"SIM_M2_SLOT2_A_DET",
+	"SLOT1_LED_OUT",
+	"SIM_M2_SLOT1_B_DET",
+	"SIM_M2_SLOT1_A_DET",
+	"SLOT0_LED_OUT",
+	"WAN_SFP0_RX_LOS",
+	"WAN_SFP0_PRSNT_N",
+	"WAN_SFP0_TX_FAULT",
+	"AUTOM1_SFP_RX_LOS",
+	"AUTOM1_SFP_PRSNT_N",
+	"AUTOM1_SFP_TX_FAULT",
+	"AUTOM0_SFP_RX_LOS",
+	"AUTOM0_SFP_PRSNT_N",
+	"WAN_SFP1_RX_LOS",
+	"WAN_SFP1_PRSNT_N",
+	"WAN_SFP1_TX_FAULT",
+	"SIM_M2_SLOT1_MUX_SEL",
+	"W_DISABLE_M2_SLOT1_N",
+	"W_DISABLE_MPCIE_SLOT0_N",
+	"W_DISABLE_M2_SLOT0_N",
+	"BT_COMMAND_MODE",
+	"WAN_SFP1_TX_DISABLE",
+	"WAN_SFP0_TX_DISABLE",
+	"AUTOM1_SFP_TX_DISABLE",
+	"AUTOM0_SFP_TX_DISABLE",
+	"SIM_M2_SLOT2_MUX_SEL",
+	"W_DISABLE_M2_SLOT2_N",
+	"RST_CTL_M2_SLOT_1_N",
+	"RST_CTL_M2_SLOT_2_N",
+	"PM_USB_PWR_EN_BOT",
+	"PM_USB_PWR_EN_TOP",
+};
+
+static u8 plat_0222_gpio_channels[] = {
+	OFFSET_BIT_TO_CHANNEL(0x00, 0),
+	OFFSET_BIT_TO_CHANNEL(0x00, 1),
+	OFFSET_BIT_TO_CHANNEL(0x00, 2),
+	OFFSET_BIT_TO_CHANNEL(0x00, 3),
+	OFFSET_BIT_TO_CHANNEL(0x00, 4),
+	OFFSET_BIT_TO_CHANNEL(0x00, 5),
+	OFFSET_BIT_TO_CHANNEL(0x00, 6),
+	OFFSET_BIT_TO_CHANNEL(0x00, 7),
+	OFFSET_BIT_TO_CHANNEL(0x01, 0),
+	OFFSET_BIT_TO_CHANNEL(0x01, 1),
+	OFFSET_BIT_TO_CHANNEL(0x01, 2),
+	OFFSET_BIT_TO_CHANNEL(0x01, 3),
+	OFFSET_BIT_TO_CHANNEL(0x01, 4),
+	OFFSET_BIT_TO_CHANNEL(0x01, 5),
+	OFFSET_BIT_TO_CHANNEL(0x01, 6),
+	OFFSET_BIT_TO_CHANNEL(0x01, 7),
+	OFFSET_BIT_TO_CHANNEL(0x02, 0),
+	OFFSET_BIT_TO_CHANNEL(0x02, 1),
+	OFFSET_BIT_TO_CHANNEL(0x02, 2),
+	OFFSET_BIT_TO_CHANNEL(0x09, 0),
+	OFFSET_BIT_TO_CHANNEL(0x09, 1),
+	OFFSET_BIT_TO_CHANNEL(0x09, 2),
+	OFFSET_BIT_TO_CHANNEL(0x09, 3),
+	OFFSET_BIT_TO_CHANNEL(0x0a, 0),
+	OFFSET_BIT_TO_CHANNEL(0x0a, 1),
+	OFFSET_BIT_TO_CHANNEL(0x0a, 2),
+	OFFSET_BIT_TO_CHANNEL(0x0a, 3),
+	OFFSET_BIT_TO_CHANNEL(0x0a, 4),
+	OFFSET_BIT_TO_CHANNEL(0x0a, 5),
+	OFFSET_BIT_TO_CHANNEL(0x0a, 6),
+	OFFSET_BIT_TO_CHANNEL(0x0b, 0),
+	OFFSET_BIT_TO_CHANNEL(0x0b, 1),
+	OFFSET_BIT_TO_CHANNEL(0x0b, 2),
+	OFFSET_BIT_TO_CHANNEL(0x0b, 3),
+};
+
+static struct platform_device *silicom_platform_dev;
+static struct led_classdev_mc *silicom_led_info __initdata;
+static struct gpio_chip *silicom_gpiochip __initdata;
+static u8 *silicom_gpio_channels __initdata;
+
+static int silicom_mec_port_get(unsigned int offset)
+{
+	unsigned short mec_data_addr;
+	unsigned short mec_port_addr;
+	u8 reg;
+
+	mec_data_addr = FIELD_GET(MEC_PORT_DWORD_OFFSET, offset) & MEC_DATA_OFFSET_MASK;
+	mec_port_addr = FIELD_GET(MEC_PORT_DWORD_OFFSET, offset) & MEC_PORT_OFFSET_MASK;
+
+	mutex_lock(&mec_io_mutex);
+	outb(mec_port_addr, MEC_ADDR);
+	reg = inb(MEC_DATA_OFFSET(mec_data_addr));
+	mutex_unlock(&mec_io_mutex);
+
+	return (reg >> (offset & MEC_PORT_CHANNEL_MASK)) & 0x01;
+}
+
+static enum led_brightness silicom_mec_led_get(int channel)
+{
+	/* Outputs are active low */
+	return silicom_mec_port_get(channel) ? LED_OFF : LED_ON;
+}
+
+static void silicom_mec_port_set(int channel, int on)
+{
+
+	unsigned short mec_data_addr;
+	unsigned short mec_port_addr;
+	u8 reg;
+
+	mec_data_addr = FIELD_GET(MEC_PORT_DWORD_OFFSET, channel) & MEC_DATA_OFFSET_MASK;
+	mec_port_addr = FIELD_GET(MEC_PORT_DWORD_OFFSET, channel) & MEC_PORT_OFFSET_MASK;
+
+	mutex_lock(&mec_io_mutex);
+	outb(mec_port_addr, MEC_ADDR);
+	reg = inb(MEC_DATA_OFFSET(mec_data_addr));
+	/* Outputs are active low, so clear the bit for on, or set it for off */
+	if (on)
+		reg &= ~(1 << (channel & MEC_PORT_CHANNEL_MASK));
+	else
+		reg |= 1 << (channel & MEC_PORT_CHANNEL_MASK);
+	outb(reg, MEC_DATA_OFFSET(mec_data_addr));
+	mutex_unlock(&mec_io_mutex);
+}
+
+static enum led_brightness silicom_mec_led_mc_brightness_get(struct led_classdev *led_cdev)
+{
+	struct led_classdev_mc *mc_cdev = lcdev_to_mccdev(led_cdev);
+	enum led_brightness brightness = LED_OFF;
+	int i;
+
+	for (i = 0; i < mc_cdev->num_colors; i++) {
+		mc_cdev->subled_info[i].brightness =
+			silicom_mec_led_get(mc_cdev->subled_info[i].channel);
+		/* Mark the overall brightness as LED_ON if any of the subleds are on */
+		if (mc_cdev->subled_info[i].brightness != LED_OFF)
+			brightness = LED_ON;
+	}
+
+	return brightness;
+}
+
+static void silicom_mec_led_mc_brightness_set(struct led_classdev *led_cdev,
+					      enum led_brightness brightness)
+{
+	struct led_classdev_mc *mc_cdev = lcdev_to_mccdev(led_cdev);
+	int i;
+
+	led_mc_calc_color_components(mc_cdev, brightness);
+	for (i = 0; i < mc_cdev->num_colors; i++) {
+		silicom_mec_port_set(mc_cdev->subled_info[i].channel,
+				     mc_cdev->subled_info[i].brightness);
+	}
+}
+
+static int silicom_gpio_get_direction(struct gpio_chip *gc,
+				      unsigned int offset)
+{
+	u8 *channels = gpiochip_get_data(gc);
+
+	/* Input registers have offsets between [0x00, 0x07] */
+	if (CHANNEL_TO_OFFSET(channels[offset]) < MEC_GPIO_IN_POS)
+		return GPIO_LINE_DIRECTION_IN;
+
+	return GPIO_LINE_DIRECTION_OUT;
+}
+
+static int silicom_gpio_direction_input(struct gpio_chip *gc,
+					unsigned int offset)
+{
+	int direction = silicom_gpio_get_direction(gc, offset);
+
+	return direction == GPIO_LINE_DIRECTION_IN ? 0 : -EINVAL;
+}
+
+static void silicom_gpio_set(struct gpio_chip *gc,
+			     unsigned int offset,
+			     int value)
+{
+	int direction = silicom_gpio_get_direction(gc, offset);
+	u8 *channels = gpiochip_get_data(gc);
+	int channel = channels[offset];
+
+	if (direction == GPIO_LINE_DIRECTION_IN)
+		return;
+
+	if (value)
+		silicom_mec_port_set(channel, 0);
+	else if (value == 0)
+		silicom_mec_port_set(channel, 1);
+	else
+		pr_err("Wrong argument value: %d\n", value);
+}
+
+static int silicom_gpio_direction_output(struct gpio_chip *gc,
+					 unsigned int offset,
+					 int value)
+{
+	int direction = silicom_gpio_get_direction(gc, offset);
+
+	if (direction == GPIO_LINE_DIRECTION_IN)
+		return -EINVAL;
+
+	silicom_gpio_set(gc, offset, value);
+
+	return 0;
+}
+
+static int silicom_gpio_get(struct gpio_chip *gc, unsigned int offset)
+{
+	u8 *channels = gpiochip_get_data(gc);
+	int channel = channels[offset];
+
+	return silicom_mec_port_get(channel);
+}
+
+static struct mc_subled plat_0222_wan_mc_subled_info[] __initdata = {
+	{
+		.color_index = LED_COLOR_ID_WHITE,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x0c, 7),
+	},
+	{
+		.color_index = LED_COLOR_ID_YELLOW,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x0c, 6),
+	},
+	{
+		.color_index = LED_COLOR_ID_RED,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x0c, 5),
+	},
+};
+
+static struct mc_subled plat_0222_sys_mc_subled_info[] __initdata = {
+	{
+		.color_index = LED_COLOR_ID_WHITE,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x0c, 4),
+	},
+	{
+		.color_index = LED_COLOR_ID_AMBER,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x0c, 3),
+	},
+	{
+		.color_index = LED_COLOR_ID_RED,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x0c, 2),
+	},
+};
+
+static struct mc_subled plat_0222_stat1_mc_subled_info[] __initdata = {
+	{
+		.color_index = LED_COLOR_ID_RED,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x0c, 1),
+	},
+	{
+		.color_index = LED_COLOR_ID_GREEN,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x0c, 0),
+	},
+	{
+		.color_index = LED_COLOR_ID_BLUE,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x0d, 7),
+	},
+	{
+		.color_index = LED_COLOR_ID_YELLOW,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x0d, 6),
+	},
+};
+
+static struct mc_subled plat_0222_stat2_mc_subled_info[] __initdata = {
+	{
+		.color_index = LED_COLOR_ID_RED,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x0d, 5),
+	},
+	{
+		.color_index = LED_COLOR_ID_GREEN,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x0d, 4),
+	},
+	{
+		.color_index = LED_COLOR_ID_BLUE,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x0d, 3),
+	},
+	{
+		.color_index = LED_COLOR_ID_YELLOW,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x0d, 2),
+	},
+};
+
+static struct mc_subled plat_0222_stat3_mc_subled_info[] __initdata = {
+	{
+		.color_index = LED_COLOR_ID_RED,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x0d, 1),
+	},
+	{
+		.color_index = LED_COLOR_ID_GREEN,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x0d, 0),
+	},
+	{
+		.color_index = LED_COLOR_ID_BLUE,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x0e, 1),
+	},
+	{
+		.color_index = LED_COLOR_ID_YELLOW,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x0e, 0),
+	},
+};
+
+static struct led_classdev_mc plat_0222_mc_led_info[] __initdata = {
+	{
+		.led_cdev = {
+			.name = "platled::wan",
+			.brightness = 0,
+			.max_brightness = 1,
+			.brightness_set = silicom_mec_led_mc_brightness_set,
+			.brightness_get = silicom_mec_led_mc_brightness_get,
+		},
+		.num_colors = ARRAY_SIZE(plat_0222_wan_mc_subled_info),
+		.subled_info = plat_0222_wan_mc_subled_info,
+	},
+	{
+		.led_cdev = {
+			.name = "platled::sys",
+			.brightness = 0,
+			.max_brightness = 1,
+			.brightness_set = silicom_mec_led_mc_brightness_set,
+			.brightness_get = silicom_mec_led_mc_brightness_get,
+		},
+		.num_colors = ARRAY_SIZE(plat_0222_sys_mc_subled_info),
+		.subled_info = plat_0222_sys_mc_subled_info,
+	},
+	{
+		.led_cdev = {
+			.name = "platled::stat1",
+			.brightness = 0,
+			.max_brightness = 1,
+			.brightness_set = silicom_mec_led_mc_brightness_set,
+			.brightness_get = silicom_mec_led_mc_brightness_get,
+		},
+		.num_colors = ARRAY_SIZE(plat_0222_stat1_mc_subled_info),
+		.subled_info = plat_0222_stat1_mc_subled_info,
+	},
+	{
+		.led_cdev = {
+			.name = "platled::stat2",
+			.brightness = 0,
+			.max_brightness = 1,
+			.brightness_set = silicom_mec_led_mc_brightness_set,
+			.brightness_get = silicom_mec_led_mc_brightness_get,
+		},
+		.num_colors = ARRAY_SIZE(plat_0222_stat2_mc_subled_info),
+		.subled_info = plat_0222_stat2_mc_subled_info,
+	},
+	{
+		.led_cdev = {
+			.name = "platled::stat3",
+			.brightness = 0,
+			.max_brightness = 1,
+			.brightness_set = silicom_mec_led_mc_brightness_set,
+			.brightness_get = silicom_mec_led_mc_brightness_get,
+		},
+		.num_colors = ARRAY_SIZE(plat_0222_stat3_mc_subled_info),
+		.subled_info = plat_0222_stat3_mc_subled_info,
+	},
+	{ },
+};
+
+static struct gpio_chip silicom_gpio_chip = {
+	.label = "silicom-gpio",
+	.get_direction = silicom_gpio_get_direction,
+	.direction_input = silicom_gpio_direction_input,
+	.direction_output = silicom_gpio_direction_output,
+	.get = silicom_gpio_get,
+	.set = silicom_gpio_set,
+	.base = -1,
+	.ngpio = ARRAY_SIZE(plat_0222_gpio_channels),
+	.names = plat_0222_gpio_names,
+	/*
+	 * We're using a mutex to protect the indirect access, so we can sleep
+	 * if the lock blocks
+	 */
+	.can_sleep = true,
+};
+
+static struct silicom_platform_info silicom_plat_0222_cordoba_info __initdata = {
+	.io_base = MEC_IO_BASE,
+	.io_len = MEC_IO_LEN,
+	.led_info = plat_0222_mc_led_info,
+	.gpiochip = &silicom_gpio_chip,
+	.gpio_channels = plat_0222_gpio_channels,
+	/*
+	 * The original generic cordoba does not have the last 4 outputs of the
+	 * plat_0222 variant, the rest are the same, so use the same longer list,
+	 * but ignore the last entries here
+	 */
+	.ngpio = ARRAY_SIZE(plat_0222_gpio_channels),
+
+};
+
+static struct mc_subled cordoba_fp_left_mc_subled_info[] __initdata = {
+	{
+		.color_index = LED_COLOR_ID_RED,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x08, 6),
+	},
+	{
+		.color_index = LED_COLOR_ID_GREEN,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x08, 5),
+	},
+	{
+		.color_index = LED_COLOR_ID_BLUE,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x09, 7),
+	},
+	{
+		.color_index = LED_COLOR_ID_AMBER,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x09, 4),
+	},
+};
+
+static struct mc_subled cordoba_fp_center_mc_subled_info[] __initdata = {
+	{
+		.color_index = LED_COLOR_ID_RED,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x08, 7),
+	},
+	{
+		.color_index = LED_COLOR_ID_GREEN,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x08, 4),
+	},
+	{
+		.color_index = LED_COLOR_ID_BLUE,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x08, 3),
+	},
+	{
+		.color_index = LED_COLOR_ID_AMBER,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x09, 6),
+	},
+};
+
+static struct mc_subled cordoba_fp_right_mc_subled_info[] __initdata = {
+	{
+		.color_index = LED_COLOR_ID_RED,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x08, 2),
+	},
+	{
+		.color_index = LED_COLOR_ID_GREEN,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x08, 1),
+	},
+	{
+		.color_index = LED_COLOR_ID_BLUE,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x08, 0),
+	},
+	{
+		.color_index = LED_COLOR_ID_AMBER,
+		.brightness = 1,
+		.intensity = 0,
+		.channel = OFFSET_BIT_TO_CHANNEL(0x09, 5),
+	},
+};
+
+static struct led_classdev_mc cordoba_mc_led_info[] __initdata = {
+	{
+		.led_cdev = {
+			.name = "platled::fp_left",
+			.brightness = 0,
+			.max_brightness = 1,
+			.brightness_set = silicom_mec_led_mc_brightness_set,
+			.brightness_get = silicom_mec_led_mc_brightness_get,
+		},
+		.num_colors = ARRAY_SIZE(cordoba_fp_left_mc_subled_info),
+		.subled_info = cordoba_fp_left_mc_subled_info,
+	},
+	{
+		.led_cdev = {
+			.name = "platled::fp_center",
+			.brightness = 0,
+			.max_brightness = 1,
+			.brightness_set = silicom_mec_led_mc_brightness_set,
+			.brightness_get = silicom_mec_led_mc_brightness_get,
+		},
+		.num_colors = ARRAY_SIZE(cordoba_fp_center_mc_subled_info),
+		.subled_info = cordoba_fp_center_mc_subled_info,
+	},
+	{
+		.led_cdev = {
+			.name = "platled::fp_right",
+			.brightness = 0,
+			.max_brightness = 1,
+			.brightness_set = silicom_mec_led_mc_brightness_set,
+			.brightness_get = silicom_mec_led_mc_brightness_get,
+		},
+		.num_colors = ARRAY_SIZE(cordoba_fp_right_mc_subled_info),
+		.subled_info = cordoba_fp_right_mc_subled_info,
+	},
+	{ },
+};
+
+static struct silicom_platform_info silicom_generic_cordoba_info __initdata = {
+	.io_base = MEC_IO_BASE,
+	.io_len = MEC_IO_LEN,
+	.led_info = cordoba_mc_led_info,
+	.gpiochip = &silicom_gpio_chip,
+	.gpio_channels = plat_0222_gpio_channels,
+	.ngpio = ARRAY_SIZE(plat_0222_gpio_channels),
+};
+
+/*
+ * sysfs interface
+ */
+static ssize_t efuse_status_show(struct device *dev,
+				 struct device_attribute *attr,
+				 char *buf)
+{
+	u32 reg;
+
+	mutex_lock(&mec_io_mutex);
+	/* Select memory region */
+	outb(IO_REG_BANK, EC_ADDR_MSB);
+	outb(MEC_EFUSE_LSB_ADDR, EC_ADDR_LSB);
+
+	/* Get current data from the address */
+	reg = inl(MEC_DATA_OFFSET(DEFAULT_CHAN_LO));
+	mutex_unlock(&mec_io_mutex);
+
+	efuse_status = reg & 0x1;
+
+	return sysfs_emit(buf, "%u\n", efuse_status);
+}
+static DEVICE_ATTR_RO(efuse_status);
+
+static ssize_t uc_version_show(struct device *dev,
+			       struct device_attribute *attr,
+			       char *buf)
+{
+	int uc_version;
+	u32 reg;
+
+	mutex_lock(&mec_io_mutex);
+	outb(IO_REG_BANK, EC_ADDR_MSB);
+	outb(DEFAULT_CHAN_LO, EC_ADDR_LSB);
+
+	reg = inl(MEC_DATA_OFFSET(DEFAULT_CHAN_LO));
+	mutex_unlock(&mec_io_mutex);
+	uc_version = FIELD_GET(MEC_VERSION_LOC, reg);
+	if (uc_version >= 192)
+		return -EINVAL;
+
+	uc_version = FIELD_GET(MEC_VERSION_MAJOR, reg) * 100 +
+		     FIELD_GET(MEC_VERSION_MINOR, reg);
+
+	mec_uc_version = uc_version;
+
+	return sysfs_emit(buf, "%u\n", mec_uc_version);
+}
+static DEVICE_ATTR_RO(uc_version);
+
+static ssize_t power_cycle_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf)
+{
+	return sysfs_emit(buf, "%u\n", power_cycle);
+}
+
+static void powercycle_uc(void)
+{
+	/* Select memory region */
+	outb(IO_REG_BANK, EC_ADDR_MSB);
+	outb(MEC_POWER_CYCLE_ADDR, EC_ADDR_LSB);
+
+	/* Set to 1 for current data from the address */
+	outb(1, MEC_DATA_OFFSET(DEFAULT_CHAN_LO));
+}
+
+static ssize_t power_cycle_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
+{
+	int rc;
+	unsigned int power_cycle_cmd;
+
+	rc = kstrtou32(buf, 0, &power_cycle_cmd);
+	if (rc)
+		return -EINVAL;
+
+	if (power_cycle_cmd > 0) {
+		mutex_lock(&mec_io_mutex);
+		power_cycle = power_cycle_cmd;
+		powercycle_uc();
+		mutex_unlock(&mec_io_mutex);
+	}
+
+	return count;
+}
+static DEVICE_ATTR_RW(power_cycle);
+
+static struct attribute *silicom_attrs[] = {
+	&dev_attr_efuse_status.attr,
+	&dev_attr_uc_version.attr,
+	&dev_attr_power_cycle.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(silicom);
+
+static struct platform_driver silicom_platform_driver = {
+	.driver = {
+		.name = "silicom-platform",
+		.dev_groups = silicom_groups,
+	},
+};
+
+static int __init silicom_mc_leds_register(struct device *dev,
+					   const struct led_classdev_mc *mc_leds)
+{
+	int size = sizeof(struct mc_subled);
+	struct led_classdev_mc *led;
+	int i, err;
+
+	for (i = 0; mc_leds[i].led_cdev.name; i++) {
+
+		led = devm_kzalloc(dev, sizeof(*led), GFP_KERNEL);
+		if (!led)
+			return -ENOMEM;
+		memcpy(led, &mc_leds[i], sizeof(*led));
+
+		led->subled_info = devm_kzalloc(dev, led->num_colors * size, GFP_KERNEL);
+		if (!led->subled_info)
+			return -ENOMEM;
+		memcpy(led->subled_info, mc_leds[i].subled_info, led->num_colors * size);
+
+		err = devm_led_classdev_multicolor_register(dev, led);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static u32 rpm_get(void)
+{
+	u32 reg;
+
+	mutex_lock(&mec_io_mutex);
+	/* Select memory region */
+	outb(IO_REG_BANK, EC_ADDR_MSB);
+	outb(DEFAULT_CHAN_LO_T, EC_ADDR_LSB);
+	reg = inw(MEC_DATA_OFFSET(DEFAULT_CHAN_LO));
+	mutex_unlock(&mec_io_mutex);
+
+	return reg;
+}
+
+static u32 temp_get(void)
+{
+	u32 reg;
+
+	mutex_lock(&mec_io_mutex);
+	/* Select memory region */
+	outb(IO_REG_BANK, EC_ADDR_MSB);
+	outb(DEFAULT_CHAN_LO_T, EC_ADDR_LSB);
+	reg = inl(MEC_DATA_OFFSET(DEFAULT_CHAN_LO));
+	mutex_unlock(&mec_io_mutex);
+
+	return FIELD_GET(MEC_TEMP_LOC, reg) * 100;
+}
+
+static umode_t silicom_fan_control_fan_is_visible(const u32 attr)
+{
+	switch (attr) {
+	case hwmon_fan_input:
+	case hwmon_fan_label:
+		return 0444;
+	default:
+		return 0;
+	}
+}
+
+static umode_t silicom_fan_control_temp_is_visible(const u32 attr)
+{
+	switch (attr) {
+	case hwmon_temp_input:
+	case hwmon_temp_label:
+		return 0444;
+	default:
+		return 0;
+	}
+}
+
+static int silicom_fan_control_read_fan(struct device *dev, u32 attr, long *val)
+{
+	switch (attr) {
+	case hwmon_fan_input:
+		*val = rpm_get();
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int silicom_fan_control_read_temp(struct device *dev, u32 attr, long *val)
+{
+	switch (attr) {
+	case hwmon_temp_input:
+		*val = temp_get();
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static umode_t silicom_fan_control_is_visible(const void *data,
+					      enum hwmon_sensor_types type,
+					      u32 attr, int channel)
+{
+	switch (type) {
+	case hwmon_fan:
+		return silicom_fan_control_fan_is_visible(attr);
+	case hwmon_temp:
+		return silicom_fan_control_temp_is_visible(attr);
+	default:
+		return 0;
+	}
+}
+
+static int silicom_fan_control_read(struct device *dev,
+				    enum hwmon_sensor_types type,
+				    u32 attr, int channel,
+				    long *val)
+{
+	switch (type) {
+	case hwmon_fan:
+		return silicom_fan_control_read_fan(dev, attr, val);
+	case hwmon_temp:
+		return silicom_fan_control_read_temp(dev, attr, val);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int silicom_fan_control_read_labels(struct device *dev,
+					   enum hwmon_sensor_types type,
+					   u32 attr, int channel,
+					   const char **str)
+{
+	switch (type) {
+	case hwmon_fan:
+		*str = "Silicom_platform: Fan Speed";
+		return 0;
+	case hwmon_temp:
+		*str = "Silicom_platform: Thermostat Sensor";
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static const struct hwmon_ops silicom_fan_control_hwmon_ops = {
+	.is_visible = silicom_fan_control_is_visible,
+	.read = silicom_fan_control_read,
+	.read_string = silicom_fan_control_read_labels,
+};
+
+static const struct hwmon_chip_info silicom_chip_info = {
+	.ops = &silicom_fan_control_hwmon_ops,
+	.info = silicom_fan_control_info,
+};
+
+static int __init silicom_platform_probe(struct platform_device *device)
+{
+	struct device *hwmon_dev;
+	u8 magic, ver;
+	int err;
+
+	if (!devm_request_region(&device->dev, MEC_IO_BASE, MEC_IO_LEN, "mec")) {
+		dev_err(&device->dev, "couldn't reserve MEC io ports\n");
+		return -EBUSY;
+	}
+
+	/* Sanity check magic number read for EC */
+	outb(IO_REG_BANK, MEC_ADDR);
+	magic = inb(MEC_DATA_OFFSET(DEFAULT_CHAN_LO));
+	ver = inb(MEC_DATA_OFFSET(DEFAULT_CHAN_HI));
+	dev_dbg(&device->dev, "EC magic 0x%02x, version 0x%02x\n", magic, ver);
+
+	if (magic != SILICOM_MEC_MAGIC) {
+		dev_err(&device->dev, "Bad EC magic 0x%02x!\n", magic);
+		return -ENODEV;
+	}
+
+	err = silicom_mc_leds_register(&device->dev, silicom_led_info);
+	if (err) {
+		dev_err(&device->dev, "Failed to register LEDs\n");
+		return err;
+	}
+
+	err = devm_gpiochip_add_data(&device->dev, silicom_gpiochip,
+				     silicom_gpio_channels);
+	if (err) {
+		dev_err(&device->dev, "Failed to register gpiochip: %d\n", err);
+		return err;
+	}
+
+	hwmon_dev = devm_hwmon_device_register_with_info(&device->dev, "silicom_fan", NULL,
+							 &silicom_chip_info, NULL);
+	err = PTR_ERR_OR_ZERO(hwmon_dev);
+	if (err) {
+		dev_err(&device->dev, "Failed to register hwmon_dev: %d\n", err);
+		return err;
+	}
+
+	return err;
+}
+
+static int __init silicom_platform_info_init(const struct dmi_system_id *id)
+{
+	struct silicom_platform_info *info = id->driver_data;
+
+	silicom_led_info = info->led_info;
+	silicom_gpio_channels = info->gpio_channels;
+	silicom_gpiochip = info->gpiochip;
+	silicom_gpiochip->ngpio = info->ngpio;
+
+	return 1;
+}
+
+static const struct dmi_system_id silicom_dmi_ids[] __initconst = {
+	{
+		.callback = silicom_platform_info_init,
+		.ident = "Silicom Cordoba (Generic)",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Silicom"),
+			DMI_MATCH(DMI_BOARD_NAME, "80300-0214-G"),
+		},
+		.driver_data = &silicom_generic_cordoba_info,
+	},
+	{
+		.callback = silicom_platform_info_init,
+		.ident = "Silicom Cordoba (Generic)",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Silicom"),
+			DMI_MATCH(DMI_BOARD_NAME, "80500-0214-G"),
+		},
+		.driver_data = &silicom_generic_cordoba_info,
+	},
+	{
+		 .callback = silicom_platform_info_init,
+		 .ident = "Silicom Cordoba (plat_0222)",
+		 .matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Silicom"),
+			DMI_MATCH(DMI_BOARD_NAME, "80300-0222-G"),
+		 },
+		.driver_data = &silicom_plat_0222_cordoba_info,
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(dmi, silicom_dmi_ids);
+
+static int __init silicom_platform_init(void)
+{
+	if (!dmi_check_system(silicom_dmi_ids)) {
+		pr_err("No DMI match for this platform\n");
+		return -ENODEV;
+	}
+	silicom_platform_dev = platform_create_bundle(&silicom_platform_driver,
+						      silicom_platform_probe,
+						      NULL, 0, NULL, 0);
+
+	return PTR_ERR_OR_ZERO(silicom_platform_dev);
+}
+
+static void __exit silicom_platform_exit(void)
+{
+	platform_device_unregister(silicom_platform_dev);
+	platform_driver_unregister(&silicom_platform_driver);
+}
+
+module_init(silicom_platform_init);
+module_exit(silicom_platform_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Henry Shi <henrys@silicom-usa.com>");
+MODULE_DESCRIPTION("Platform driver for Silicom network appliances");
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index d0b5fd4137bc..c4895e9bc714 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -512,10 +512,10 @@ struct tpacpi_quirk {
  * Iterates over a quirks list until one is found that matches the
  * ThinkPad's vendor, BIOS and EC model.
  *
- * Returns 0 if nothing matches, otherwise returns the quirks field of
+ * Returns: %0 if nothing matches, otherwise returns the quirks field of
  * the matching &struct tpacpi_quirk entry.
  *
- * The match criteria is: vendor, ec and bios much match.
+ * The match criteria is: vendor, ec and bios must match.
  */
 static unsigned long __init tpacpi_check_quirks(
 			const struct tpacpi_quirk *qlist,
@@ -7948,8 +7948,19 @@ static struct ibm_struct volume_driver_data = {
  * 	TPACPI_FAN_WR_TPEC is also available and should be used to
  * 	command the fan.  The X31/X40/X41 seems to have 8 fan levels,
  * 	but the ACPI tables just mention level 7.
+ *
+ * TPACPI_FAN_RD_TPEC_NS:
+ *	This mode is used for a few ThinkPads (L13 Yoga Gen2, X13 Yoga Gen2 etc.)
+ *	that are using non-standard EC locations for reporting fan speeds.
+ *	Currently these platforms only provide fan rpm reporting.
+ *
  */
 
+#define FAN_RPM_CAL_CONST 491520	/* FAN RPM calculation offset for some non-standard ECFW */
+
+#define FAN_NS_CTRL_STATUS	BIT(2)		/* Bit which determines control is enabled or not */
+#define FAN_NS_CTRL		BIT(4)		/* Bit which determines control is by host or EC */
+
 enum {					/* Fan control constants */
 	fan_status_offset = 0x2f,	/* EC register 0x2f */
 	fan_rpm_offset = 0x84,		/* EC register 0x84: LSB, 0x85 MSB (RPM)
@@ -7957,6 +7968,11 @@ enum {					/* Fan control constants */
 	fan_select_offset = 0x31,	/* EC register 0x31 (Firmware 7M)
 					   bit 0 selects which fan is active */
 
+	fan_status_offset_ns = 0x93,	/* Special status/control offset for non-standard EC Fan1 */
+	fan2_status_offset_ns = 0x96,	/* Special status/control offset for non-standard EC Fan2 */
+	fan_rpm_status_ns = 0x95,	/* Special offset for Fan1 RPM status for non-standard EC */
+	fan2_rpm_status_ns = 0x98,	/* Special offset for Fan2 RPM status for non-standard EC */
+
 	TP_EC_FAN_FULLSPEED = 0x40,	/* EC fan mode: full speed */
 	TP_EC_FAN_AUTO	    = 0x80,	/* EC fan mode: auto fan control */
 
@@ -7967,6 +7983,7 @@ enum fan_status_access_mode {
 	TPACPI_FAN_NONE = 0,		/* No fan status or control */
 	TPACPI_FAN_RD_ACPI_GFAN,	/* Use ACPI GFAN */
 	TPACPI_FAN_RD_TPEC,		/* Use ACPI EC regs 0x2f, 0x84-0x85 */
+	TPACPI_FAN_RD_TPEC_NS,		/* Use non-standard ACPI EC regs (eg: L13 Yoga gen2 etc.) */
 };
 
 enum fan_control_access_mode {
@@ -7994,6 +8011,8 @@ static u8 fan_control_desired_level;
 static u8 fan_control_resume_level;
 static int fan_watchdog_maxinterval;
 
+static bool fan_with_ns_addr;
+
 static struct mutex fan_mutex;
 
 static void fan_watchdog_fire(struct work_struct *ignored);
@@ -8123,6 +8142,15 @@ static int fan_get_status(u8 *status)
 		}
 
 		break;
+	case TPACPI_FAN_RD_TPEC_NS:
+		/* Default mode is AUTO which means controlled by EC */
+		if (!acpi_ec_read(fan_status_offset_ns, &s))
+			return -EIO;
+
+		if (status)
+			*status = s;
+
+		break;
 
 	default:
 		return -ENXIO;
@@ -8139,7 +8167,8 @@ static int fan_get_status_safe(u8 *status)
 	if (mutex_lock_killable(&fan_mutex))
 		return -ERESTARTSYS;
 	rc = fan_get_status(&s);
-	if (!rc)
+	/* NS EC doesn't have register with level settings */
+	if (!rc && !fan_with_ns_addr)
 		fan_update_desired_level(s);
 	mutex_unlock(&fan_mutex);
 
@@ -8166,7 +8195,13 @@ static int fan_get_speed(unsigned int *speed)
 
 		if (likely(speed))
 			*speed = (hi << 8) | lo;
+		break;
+	case TPACPI_FAN_RD_TPEC_NS:
+		if (!acpi_ec_read(fan_rpm_status_ns, &lo))
+			return -EIO;
 
+		if (speed)
+			*speed = lo ? FAN_RPM_CAL_CONST / lo : 0;
 		break;
 
 	default:
@@ -8178,7 +8213,7 @@ static int fan_get_speed(unsigned int *speed)
 
 static int fan2_get_speed(unsigned int *speed)
 {
-	u8 hi, lo;
+	u8 hi, lo, status;
 	bool rc;
 
 	switch (fan_status_access_mode) {
@@ -8194,7 +8229,21 @@ static int fan2_get_speed(unsigned int *speed)
 
 		if (likely(speed))
 			*speed = (hi << 8) | lo;
+		break;
 
+	case TPACPI_FAN_RD_TPEC_NS:
+		rc = !acpi_ec_read(fan2_status_offset_ns, &status);
+		if (rc)
+			return -EIO;
+		if (!(status & FAN_NS_CTRL_STATUS)) {
+			pr_info("secondary fan control not supported\n");
+			return -EIO;
+		}
+		rc = !acpi_ec_read(fan2_rpm_status_ns, &lo);
+		if (rc)
+			return -EIO;
+		if (speed)
+			*speed = lo ? FAN_RPM_CAL_CONST / lo : 0;
 		break;
 
 	default:
@@ -8697,6 +8746,7 @@ static const struct attribute_group fan_driver_attr_group = {
 #define TPACPI_FAN_2FAN		0x0002		/* EC 0x31 bit 0 selects fan2 */
 #define TPACPI_FAN_2CTL		0x0004		/* selects fan2 control */
 #define TPACPI_FAN_NOFAN	0x0008		/* no fan available */
+#define TPACPI_FAN_NS		0x0010		/* For EC with non-Standard register addresses */
 
 static const struct tpacpi_quirk fan_quirk_table[] __initconst = {
 	TPACPI_QEC_IBM('1', 'Y', TPACPI_FAN_Q1),
@@ -8715,6 +8765,8 @@ static const struct tpacpi_quirk fan_quirk_table[] __initconst = {
 	TPACPI_Q_LNV3('N', '2', 'O', TPACPI_FAN_2CTL),	/* P1 / X1 Extreme (2nd gen) */
 	TPACPI_Q_LNV3('N', '3', '0', TPACPI_FAN_2CTL),	/* P15 (1st gen) / P15v (1st gen) */
 	TPACPI_Q_LNV3('N', '3', '7', TPACPI_FAN_2CTL),  /* T15g (2nd gen) */
+	TPACPI_Q_LNV3('R', '1', 'F', TPACPI_FAN_NS),	/* L13 Yoga Gen 2 */
+	TPACPI_Q_LNV3('N', '2', 'U', TPACPI_FAN_NS),	/* X13 Yoga Gen 2*/
 	TPACPI_Q_LNV3('N', '1', 'O', TPACPI_FAN_NOFAN),	/* X1 Tablet (2nd gen) */
 };
 
@@ -8749,18 +8801,27 @@ static int __init fan_init(struct ibm_init_struct *iibm)
 		return -ENODEV;
 	}
 
+	if (quirks & TPACPI_FAN_NS) {
+		pr_info("ECFW with non-standard fan reg control found\n");
+		fan_with_ns_addr = 1;
+		/* Fan ctrl support from host is undefined for now */
+		tp_features.fan_ctrl_status_undef = 1;
+	}
+
 	if (gfan_handle) {
 		/* 570, 600e/x, 770e, 770x */
 		fan_status_access_mode = TPACPI_FAN_RD_ACPI_GFAN;
 	} else {
 		/* all other ThinkPads: note that even old-style
 		 * ThinkPad ECs supports the fan control register */
-		if (likely(acpi_ec_read(fan_status_offset,
-					&fan_control_initial_status))) {
+		if (fan_with_ns_addr ||
+		    likely(acpi_ec_read(fan_status_offset, &fan_control_initial_status))) {
 			int res;
 			unsigned int speed;
 
-			fan_status_access_mode = TPACPI_FAN_RD_TPEC;
+			fan_status_access_mode = fan_with_ns_addr ?
+				TPACPI_FAN_RD_TPEC_NS : TPACPI_FAN_RD_TPEC;
+
 			if (quirks & TPACPI_FAN_Q1)
 				fan_quirk1_setup();
 			/* Try and probe the 2nd fan */
@@ -8769,7 +8830,8 @@ static int __init fan_init(struct ibm_init_struct *iibm)
 			if (res >= 0 && speed != FAN_NOT_PRESENT) {
 				/* It responded - so let's assume it's there */
 				tp_features.second_fan = 1;
-				tp_features.second_fan_ctl = 1;
+				/* fan control not currently available for ns ECFW */
+				tp_features.second_fan_ctl = !fan_with_ns_addr;
 				pr_info("secondary fan control detected & enabled\n");
 			} else {
 				/* Fan not auto-detected */
@@ -8944,6 +9006,7 @@ static int fan_read(struct seq_file *m)
 			       str_enabled_disabled(status), status);
 		break;
 
+	case TPACPI_FAN_RD_TPEC_NS:
 	case TPACPI_FAN_RD_TPEC:
 		/* all except 570, 600e/x, 770e, 770x */
 		rc = fan_get_status_safe(&status);
@@ -8958,13 +9021,22 @@ static int fan_read(struct seq_file *m)
 
 		seq_printf(m, "speed:\t\t%d\n", speed);
 
-		if (status & TP_EC_FAN_FULLSPEED)
-			/* Disengaged mode takes precedence */
-			seq_printf(m, "level:\t\tdisengaged\n");
-		else if (status & TP_EC_FAN_AUTO)
-			seq_printf(m, "level:\t\tauto\n");
-		else
-			seq_printf(m, "level:\t\t%d\n", status);
+		if (fan_status_access_mode == TPACPI_FAN_RD_TPEC_NS) {
+			/*
+			 * No full speed bit in NS EC
+			 * EC Auto mode is set by default.
+			 * No other levels settings available
+			 */
+			seq_printf(m, "level:\t\t%s\n", status & FAN_NS_CTRL ? "unknown" : "auto");
+		} else {
+			if (status & TP_EC_FAN_FULLSPEED)
+				/* Disengaged mode takes precedence */
+				seq_printf(m, "level:\t\tdisengaged\n");
+			else if (status & TP_EC_FAN_AUTO)
+				seq_printf(m, "level:\t\tauto\n");
+			else
+				seq_printf(m, "level:\t\t%d\n", status);
+		}
 		break;
 
 	case TPACPI_FAN_NONE:
@@ -9303,7 +9375,7 @@ static struct tpacpi_battery_driver_data battery_info;
 
 /* ACPI helpers/functions/probes */
 
-/**
+/*
  * This evaluates a ACPI method call specific to the battery
  * ACPI extension. The specifics are that an error is marked
  * in the 32rd bit of the response, so we just check that here.
diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c
index 5c27b4aa9690..a7cfcbf92432 100644
--- a/drivers/platform/x86/wmi.c
+++ b/drivers/platform/x86/wmi.c
@@ -23,17 +23,14 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
-#include <linux/miscdevice.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/sysfs.h>
 #include <linux/types.h>
-#include <linux/uaccess.h>
 #include <linux/uuid.h>
 #include <linux/wmi.h>
 #include <linux/fs.h>
-#include <uapi/linux/wmi.h>
 
 MODULE_AUTHOR("Carlos Corbacho");
 MODULE_DESCRIPTION("ACPI-WMI Mapping Driver");
@@ -66,12 +63,9 @@ struct wmi_block {
 	struct wmi_device dev;
 	struct list_head list;
 	struct guid_block gblock;
-	struct miscdevice char_dev;
-	struct mutex char_mutex;
 	struct acpi_device *acpi_device;
 	wmi_notify_handler handler;
 	void *handler_data;
-	u64 req_buf_size;
 	unsigned long flags;
 };
 
@@ -85,16 +79,6 @@ struct wmi_block {
 #define ACPI_WMI_STRING      BIT(2)	/* GUID takes & returns a string */
 #define ACPI_WMI_EVENT       BIT(3)	/* GUID is an event */
 
-static bool debug_event;
-module_param(debug_event, bool, 0444);
-MODULE_PARM_DESC(debug_event,
-		 "Log WMI Events [0/1]");
-
-static bool debug_dump_wdg;
-module_param(debug_dump_wdg, bool, 0444);
-MODULE_PARM_DESC(debug_dump_wdg,
-		 "Dump available WMI interfaces [0/1]");
-
 static const struct acpi_device_id wmi_device_ids[] = {
 	{"PNP0C14", 0},
 	{"pnp0c14", 0},
@@ -106,6 +90,8 @@ MODULE_DEVICE_TABLE(acpi, wmi_device_ids);
 static const char * const allow_duplicates[] = {
 	"05901221-D566-11D1-B2F0-00A0C9062910",	/* wmi-bmof */
 	"8A42EA14-4F2A-FD45-6422-0087F7A7E608",	/* dell-wmi-ddv */
+	"44FADEB1-B204-40F2-8581-394BBDC1B651",	/* intel-wmi-sbl-fw-update */
+	"86CCFD48-205E-4A77-9C48-2021CBEDE341",	/* intel-wmi-thunderbolt */
 	NULL
 };
 
@@ -146,23 +132,19 @@ static const void *find_guid_context(struct wmi_block *wblock,
 static int get_subobj_info(acpi_handle handle, const char *pathname,
 			   struct acpi_device_info **info)
 {
-	struct acpi_device_info *dummy_info, **info_ptr;
 	acpi_handle subobj_handle;
 	acpi_status status;
 
-	status = acpi_get_handle(handle, (char *)pathname, &subobj_handle);
+	status = acpi_get_handle(handle, pathname, &subobj_handle);
 	if (status == AE_NOT_FOUND)
 		return -ENOENT;
-	else if (ACPI_FAILURE(status))
-		return -EIO;
 
-	info_ptr = info ? info : &dummy_info;
-	status = acpi_get_object_info(subobj_handle, info_ptr);
 	if (ACPI_FAILURE(status))
 		return -EIO;
 
-	if (!info)
-		kfree(dummy_info);
+	status = acpi_get_object_info(subobj_handle, info);
+	if (ACPI_FAILURE(status))
+		return -EIO;
 
 	return 0;
 }
@@ -265,26 +247,6 @@ static void wmi_device_put(struct wmi_device *wdev)
  */
 
 /**
- * set_required_buffer_size - Sets the buffer size needed for performing IOCTL
- * @wdev: A wmi bus device from a driver
- * @length: Required buffer size
- *
- * Allocates memory needed for buffer, stores the buffer size in that memory.
- *
- * Return: 0 on success or a negative error code for failure.
- */
-int set_required_buffer_size(struct wmi_device *wdev, u64 length)
-{
-	struct wmi_block *wblock;
-
-	wblock = container_of(wdev, struct wmi_block, dev);
-	wblock->req_buf_size = length;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(set_required_buffer_size);
-
-/**
  * wmi_instance_count - Get number of WMI object instances
  * @guid_string: 36 char string of the form fa50ff2b-f2e8-45de-83fa-65417f2f49ba
  *
@@ -536,41 +498,50 @@ EXPORT_SYMBOL_GPL(wmidev_block_query);
  *
  * Return: acpi_status signaling success or error.
  */
-acpi_status wmi_set_block(const char *guid_string, u8 instance,
-			  const struct acpi_buffer *in)
+acpi_status wmi_set_block(const char *guid_string, u8 instance, const struct acpi_buffer *in)
 {
-	struct wmi_block *wblock;
-	struct guid_block *block;
 	struct wmi_device *wdev;
-	acpi_handle handle;
-	struct acpi_object_list input;
-	union acpi_object params[2];
-	char method[WMI_ACPI_METHOD_NAME_SIZE];
 	acpi_status status;
 
-	if (!in)
-		return AE_BAD_DATA;
-
 	wdev = wmi_find_device_by_guid(guid_string);
 	if (IS_ERR(wdev))
 		return AE_ERROR;
 
-	wblock = container_of(wdev, struct wmi_block, dev);
-	block = &wblock->gblock;
-	handle = wblock->acpi_device->handle;
+	status =  wmidev_block_set(wdev, instance, in);
+	wmi_device_put(wdev);
 
-	if (block->instance_count <= instance) {
-		status = AE_BAD_PARAMETER;
+	return status;
+}
+EXPORT_SYMBOL_GPL(wmi_set_block);
 
-		goto err_wdev_put;
-	}
+/**
+ * wmidev_block_set - Write to a WMI block
+ * @wdev: A wmi bus device from a driver
+ * @instance: Instance index
+ * @in: Buffer containing new values for the data block
+ *
+ * Write contents of the input buffer to an ACPI-WMI data block.
+ *
+ * Return: acpi_status signaling success or error.
+ */
+acpi_status wmidev_block_set(struct wmi_device *wdev, u8 instance, const struct acpi_buffer *in)
+{
+	struct wmi_block *wblock = container_of(wdev, struct wmi_block, dev);
+	acpi_handle handle = wblock->acpi_device->handle;
+	struct guid_block *block = &wblock->gblock;
+	char method[WMI_ACPI_METHOD_NAME_SIZE];
+	struct acpi_object_list input;
+	union acpi_object params[2];
 
-	/* Check GUID is a data block */
-	if (block->flags & (ACPI_WMI_EVENT | ACPI_WMI_METHOD)) {
-		status = AE_ERROR;
+	if (!in)
+		return AE_BAD_DATA;
 
-		goto err_wdev_put;
-	}
+	if (block->instance_count <= instance)
+		return AE_BAD_PARAMETER;
+
+	/* Check GUID is a data block */
+	if (block->flags & (ACPI_WMI_EVENT | ACPI_WMI_METHOD))
+		return AE_ERROR;
 
 	input.count = 2;
 	input.pointer = params;
@@ -582,73 +553,9 @@ acpi_status wmi_set_block(const char *guid_string, u8 instance,
 
 	get_acpi_method_name(wblock, 'S', method);
 
-	status = acpi_evaluate_object(handle, method, &input, NULL);
-
-err_wdev_put:
-	wmi_device_put(wdev);
-
-	return status;
-}
-EXPORT_SYMBOL_GPL(wmi_set_block);
-
-static void wmi_dump_wdg(const struct guid_block *g)
-{
-	pr_info("%pUL:\n", &g->guid);
-	if (g->flags & ACPI_WMI_EVENT)
-		pr_info("\tnotify_id: 0x%02X\n", g->notify_id);
-	else
-		pr_info("\tobject_id: %2pE\n", g->object_id);
-	pr_info("\tinstance_count: %d\n", g->instance_count);
-	pr_info("\tflags: %#x", g->flags);
-	if (g->flags) {
-		if (g->flags & ACPI_WMI_EXPENSIVE)
-			pr_cont(" ACPI_WMI_EXPENSIVE");
-		if (g->flags & ACPI_WMI_METHOD)
-			pr_cont(" ACPI_WMI_METHOD");
-		if (g->flags & ACPI_WMI_STRING)
-			pr_cont(" ACPI_WMI_STRING");
-		if (g->flags & ACPI_WMI_EVENT)
-			pr_cont(" ACPI_WMI_EVENT");
-	}
-	pr_cont("\n");
-
-}
-
-static void wmi_notify_debug(u32 value, void *context)
-{
-	struct acpi_buffer response = { ACPI_ALLOCATE_BUFFER, NULL };
-	union acpi_object *obj;
-	acpi_status status;
-
-	status = wmi_get_event_data(value, &response);
-	if (status != AE_OK) {
-		pr_info("bad event status 0x%x\n", status);
-		return;
-	}
-
-	obj = response.pointer;
-	if (!obj)
-		return;
-
-	pr_info("DEBUG: event 0x%02X ", value);
-	switch (obj->type) {
-	case ACPI_TYPE_BUFFER:
-		pr_cont("BUFFER_TYPE - length %u\n", obj->buffer.length);
-		break;
-	case ACPI_TYPE_STRING:
-		pr_cont("STRING_TYPE - %s\n", obj->string.pointer);
-		break;
-	case ACPI_TYPE_INTEGER:
-		pr_cont("INTEGER_TYPE - %llu\n", obj->integer.value);
-		break;
-	case ACPI_TYPE_PACKAGE:
-		pr_cont("PACKAGE_TYPE - %u elements\n", obj->package.count);
-		break;
-	default:
-		pr_cont("object type 0x%X\n", obj->type);
-	}
-	kfree(obj);
+	return acpi_evaluate_object(handle, method, &input, NULL);
 }
+EXPORT_SYMBOL_GPL(wmidev_block_set);
 
 /**
  * wmi_install_notify_handler - Register handler for WMI events (deprecated)
@@ -678,8 +585,7 @@ acpi_status wmi_install_notify_handler(const char *guid,
 		acpi_status wmi_status;
 
 		if (guid_equal(&block->gblock.guid, &guid_input)) {
-			if (block->handler &&
-			    block->handler != wmi_notify_debug)
+			if (block->handler)
 				return AE_ALREADY_ACQUIRED;
 
 			block->handler = handler;
@@ -720,22 +626,14 @@ acpi_status wmi_remove_notify_handler(const char *guid)
 		acpi_status wmi_status;
 
 		if (guid_equal(&block->gblock.guid, &guid_input)) {
-			if (!block->handler ||
-			    block->handler == wmi_notify_debug)
+			if (!block->handler)
 				return AE_NULL_ENTRY;
 
-			if (debug_event) {
-				block->handler = wmi_notify_debug;
-				status = AE_OK;
-			} else {
-				wmi_status = wmi_method_enable(block, false);
-				block->handler = NULL;
-				block->handler_data = NULL;
-				if ((wmi_status != AE_OK) ||
-				    ((wmi_status == AE_OK) &&
-				     (status == AE_NOT_EXIST)))
-					status = wmi_status;
-			}
+			wmi_status = wmi_method_enable(block, false);
+			block->handler = NULL;
+			block->handler_data = NULL;
+			if (wmi_status != AE_OK || (wmi_status == AE_OK && status == AE_NOT_EXIST))
+				status = wmi_status;
 		}
 	}
 
@@ -956,111 +854,12 @@ static int wmi_dev_match(struct device *dev, struct device_driver *driver)
 
 	return 0;
 }
-static int wmi_char_open(struct inode *inode, struct file *filp)
-{
-	/*
-	 * The miscdevice already stores a pointer to itself
-	 * inside filp->private_data
-	 */
-	struct wmi_block *wblock = container_of(filp->private_data, struct wmi_block, char_dev);
-
-	filp->private_data = wblock;
-
-	return nonseekable_open(inode, filp);
-}
-
-static ssize_t wmi_char_read(struct file *filp, char __user *buffer,
-			     size_t length, loff_t *offset)
-{
-	struct wmi_block *wblock = filp->private_data;
-
-	return simple_read_from_buffer(buffer, length, offset,
-				       &wblock->req_buf_size,
-				       sizeof(wblock->req_buf_size));
-}
-
-static long wmi_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
-{
-	struct wmi_ioctl_buffer __user *input =
-		(struct wmi_ioctl_buffer __user *) arg;
-	struct wmi_block *wblock = filp->private_data;
-	struct wmi_ioctl_buffer *buf;
-	struct wmi_driver *wdriver;
-	int ret;
-
-	if (_IOC_TYPE(cmd) != WMI_IOC)
-		return -ENOTTY;
-
-	/* make sure we're not calling a higher instance than exists*/
-	if (_IOC_NR(cmd) >= wblock->gblock.instance_count)
-		return -EINVAL;
-
-	mutex_lock(&wblock->char_mutex);
-	buf = wblock->handler_data;
-	if (get_user(buf->length, &input->length)) {
-		dev_dbg(&wblock->dev.dev, "Read length from user failed\n");
-		ret = -EFAULT;
-		goto out_ioctl;
-	}
-	/* if it's too small, abort */
-	if (buf->length < wblock->req_buf_size) {
-		dev_err(&wblock->dev.dev,
-			"Buffer %lld too small, need at least %lld\n",
-			buf->length, wblock->req_buf_size);
-		ret = -EINVAL;
-		goto out_ioctl;
-	}
-	/* if it's too big, warn, driver will only use what is needed */
-	if (buf->length > wblock->req_buf_size)
-		dev_warn(&wblock->dev.dev,
-			"Buffer %lld is bigger than required %lld\n",
-			buf->length, wblock->req_buf_size);
-
-	/* copy the structure from userspace */
-	if (copy_from_user(buf, input, wblock->req_buf_size)) {
-		dev_dbg(&wblock->dev.dev, "Copy %llu from user failed\n",
-			wblock->req_buf_size);
-		ret = -EFAULT;
-		goto out_ioctl;
-	}
-
-	/* let the driver do any filtering and do the call */
-	wdriver = drv_to_wdrv(wblock->dev.dev.driver);
-	if (!try_module_get(wdriver->driver.owner)) {
-		ret = -EBUSY;
-		goto out_ioctl;
-	}
-	ret = wdriver->filter_callback(&wblock->dev, cmd, buf);
-	module_put(wdriver->driver.owner);
-	if (ret)
-		goto out_ioctl;
-
-	/* return the result (only up to our internal buffer size) */
-	if (copy_to_user(input, buf, wblock->req_buf_size)) {
-		dev_dbg(&wblock->dev.dev, "Copy %llu to user failed\n",
-			wblock->req_buf_size);
-		ret = -EFAULT;
-	}
-
-out_ioctl:
-	mutex_unlock(&wblock->char_mutex);
-	return ret;
-}
-
-static const struct file_operations wmi_fops = {
-	.owner		= THIS_MODULE,
-	.read		= wmi_char_read,
-	.open		= wmi_char_open,
-	.unlocked_ioctl	= wmi_ioctl,
-	.compat_ioctl	= compat_ptr_ioctl,
-};
 
 static int wmi_dev_probe(struct device *dev)
 {
 	struct wmi_block *wblock = dev_to_wblock(dev);
 	struct wmi_driver *wdriver = drv_to_wdrv(dev->driver);
 	int ret = 0;
-	char *buf;
 
 	if (ACPI_FAILURE(wmi_method_enable(wblock, true)))
 		dev_warn(dev, "failed to enable device -- probing anyway\n");
@@ -1068,55 +867,17 @@ static int wmi_dev_probe(struct device *dev)
 	if (wdriver->probe) {
 		ret = wdriver->probe(dev_to_wdev(dev),
 				find_guid_context(wblock, wdriver));
-		if (ret != 0)
-			goto probe_failure;
-	}
+		if (!ret) {
+			if (ACPI_FAILURE(wmi_method_enable(wblock, false)))
+				dev_warn(dev, "Failed to disable device\n");
 
-	/* driver wants a character device made */
-	if (wdriver->filter_callback) {
-		/* check that required buffer size declared by driver or MOF */
-		if (!wblock->req_buf_size) {
-			dev_err(&wblock->dev.dev,
-				"Required buffer size not set\n");
-			ret = -EINVAL;
-			goto probe_failure;
-		}
-
-		wblock->handler_data = kmalloc(wblock->req_buf_size,
-					       GFP_KERNEL);
-		if (!wblock->handler_data) {
-			ret = -ENOMEM;
-			goto probe_failure;
-		}
-
-		buf = kasprintf(GFP_KERNEL, "wmi/%s", wdriver->driver.name);
-		if (!buf) {
-			ret = -ENOMEM;
-			goto probe_string_failure;
-		}
-		wblock->char_dev.minor = MISC_DYNAMIC_MINOR;
-		wblock->char_dev.name = buf;
-		wblock->char_dev.fops = &wmi_fops;
-		wblock->char_dev.mode = 0444;
-		ret = misc_register(&wblock->char_dev);
-		if (ret) {
-			dev_warn(dev, "failed to register char dev: %d\n", ret);
-			ret = -ENOMEM;
-			goto probe_misc_failure;
+			return ret;
 		}
 	}
 
 	set_bit(WMI_PROBED, &wblock->flags);
-	return 0;
 
-probe_misc_failure:
-	kfree(buf);
-probe_string_failure:
-	kfree(wblock->handler_data);
-probe_failure:
-	if (ACPI_FAILURE(wmi_method_enable(wblock, false)))
-		dev_warn(dev, "failed to disable device\n");
-	return ret;
+	return 0;
 }
 
 static void wmi_dev_remove(struct device *dev)
@@ -1126,12 +887,6 @@ static void wmi_dev_remove(struct device *dev)
 
 	clear_bit(WMI_PROBED, &wblock->flags);
 
-	if (wdriver->filter_callback) {
-		misc_deregister(&wblock->char_dev);
-		kfree(wblock->char_dev.name);
-		kfree(wblock->handler_data);
-	}
-
 	if (wdriver->remove)
 		wdriver->remove(dev_to_wdev(dev));
 
@@ -1203,7 +958,6 @@ static int wmi_create_device(struct device *wmi_bus_dev,
 
 	if (wblock->gblock.flags & ACPI_WMI_METHOD) {
 		wblock->dev.dev.type = &wmi_type_method;
-		mutex_init(&wblock->char_mutex);
 		goto out_init;
 	}
 
@@ -1240,9 +994,7 @@ static int wmi_create_device(struct device *wmi_bus_dev,
 	kfree(info);
 
 	get_acpi_method_name(wblock, 'S', method);
-	result = get_subobj_info(device->handle, method, NULL);
-
-	if (result == 0)
+	if (acpi_has_method(device->handle, method))
 		wblock->dev.setable = true;
 
  out_init:
@@ -1337,8 +1089,10 @@ static int parse_wdg(struct device *wmi_bus_dev, struct platform_device *pdev)
 	total = obj->buffer.length / sizeof(struct guid_block);
 
 	for (i = 0; i < total; i++) {
-		if (debug_dump_wdg)
-			wmi_dump_wdg(&gblock[i]);
+		if (!gblock[i].instance_count) {
+			dev_info(wmi_bus_dev, FW_INFO "%pUL has zero instances\n", &gblock[i].guid);
+			continue;
+		}
 
 		if (guid_already_parsed_for_legacy(device, &gblock[i].guid))
 			continue;
@@ -1360,17 +1114,10 @@ static int parse_wdg(struct device *wmi_bus_dev, struct platform_device *pdev)
 
 		list_add_tail(&wblock->list, &wmi_block_list);
 
-		if (debug_event) {
-			wblock->handler = wmi_notify_debug;
-			wmi_method_enable(wblock, true);
-		}
-
 		retval = wmi_add_device(pdev, &wblock->dev);
 		if (retval) {
 			dev_err(wmi_bus_dev, "failed to register %pUL\n",
 				&wblock->gblock.guid);
-			if (debug_event)
-				wmi_method_enable(wblock, false);
 
 			list_del(&wblock->list);
 			put_device(&wblock->dev.dev);
@@ -1391,7 +1138,7 @@ acpi_wmi_ec_space_handler(u32 function, acpi_physical_address address,
 			  u32 bits, u64 *value,
 			  void *handler_context, void *region_context)
 {
-	int result = 0, i = 0;
+	int result = 0;
 	u8 temp = 0;
 
 	if ((address > 0xFF) || !value)
@@ -1405,9 +1152,9 @@ acpi_wmi_ec_space_handler(u32 function, acpi_physical_address address,
 
 	if (function == ACPI_READ) {
 		result = ec_read(address, &temp);
-		(*value) |= ((u64)temp) << i;
+		*value = temp;
 	} else {
-		temp = 0xff & ((*value) >> i);
+		temp = 0xff & *value;
 		result = ec_write(address, temp);
 	}
 
@@ -1423,24 +1170,13 @@ acpi_wmi_ec_space_handler(u32 function, acpi_physical_address address,
 	}
 }
 
-static void acpi_wmi_notify_handler(acpi_handle handle, u32 event,
-				    void *context)
+static int wmi_notify_device(struct device *dev, void *data)
 {
-	struct wmi_block *wblock = NULL, *iter;
-
-	list_for_each_entry(iter, &wmi_block_list, list) {
-		struct guid_block *block = &iter->gblock;
-
-		if (iter->acpi_device->handle == handle &&
-		    (block->flags & ACPI_WMI_EVENT) &&
-		    (block->notify_id == event)) {
-			wblock = iter;
-			break;
-		}
-	}
+	struct wmi_block *wblock = dev_to_wblock(dev);
+	u32 *event = data;
 
-	if (!wblock)
-		return;
+	if (!(wblock->gblock.flags & ACPI_WMI_EVENT && wblock->gblock.notify_id == *event))
+		return 0;
 
 	/* If a driver is bound, then notify the driver. */
 	if (test_bit(WMI_PROBED, &wblock->flags) && wblock->dev.dev.driver) {
@@ -1452,7 +1188,7 @@ static void acpi_wmi_notify_handler(acpi_handle handle, u32 event,
 			status = get_event_data(wblock, &evdata);
 			if (ACPI_FAILURE(status)) {
 				dev_warn(&wblock->dev.dev, "failed to get event data\n");
-				return;
+				return -EIO;
 			}
 		}
 
@@ -1462,16 +1198,20 @@ static void acpi_wmi_notify_handler(acpi_handle handle, u32 event,
 		kfree(evdata.pointer);
 	} else if (wblock->handler) {
 		/* Legacy handler */
-		wblock->handler(event, wblock->handler_data);
+		wblock->handler(*event, wblock->handler_data);
 	}
 
-	if (debug_event)
-		pr_info("DEBUG: GUID %pUL event 0x%02X\n", &wblock->gblock.guid, event);
+	acpi_bus_generate_netlink_event(wblock->acpi_device->pnp.device_class,
+					dev_name(&wblock->dev.dev), *event, 0);
 
-	acpi_bus_generate_netlink_event(
-		wblock->acpi_device->pnp.device_class,
-		dev_name(&wblock->dev.dev),
-		event, 0);
+	return -EBUSY;
+}
+
+static void acpi_wmi_notify_handler(acpi_handle handle, u32 event, void *context)
+{
+	struct device *wmi_bus_dev = context;
+
+	device_for_each_child(wmi_bus_dev, &event, wmi_notify_device);
 }
 
 static int wmi_remove_device(struct device *dev, void *data)
@@ -1486,16 +1226,31 @@ static int wmi_remove_device(struct device *dev, void *data)
 
 static void acpi_wmi_remove(struct platform_device *device)
 {
-	struct acpi_device *acpi_device = ACPI_COMPANION(&device->dev);
 	struct device *wmi_bus_device = dev_get_drvdata(&device->dev);
 
-	acpi_remove_notify_handler(acpi_device->handle, ACPI_ALL_NOTIFY,
-				   acpi_wmi_notify_handler);
-	acpi_remove_address_space_handler(acpi_device->handle,
-				ACPI_ADR_SPACE_EC, &acpi_wmi_ec_space_handler);
-
 	device_for_each_child_reverse(wmi_bus_device, NULL, wmi_remove_device);
-	device_unregister(wmi_bus_device);
+}
+
+static void acpi_wmi_remove_notify_handler(void *data)
+{
+	struct acpi_device *acpi_device = data;
+
+	acpi_remove_notify_handler(acpi_device->handle, ACPI_ALL_NOTIFY, acpi_wmi_notify_handler);
+}
+
+static void acpi_wmi_remove_address_space_handler(void *data)
+{
+	struct acpi_device *acpi_device = data;
+
+	acpi_remove_address_space_handler(acpi_device->handle, ACPI_ADR_SPACE_EC,
+					  &acpi_wmi_ec_space_handler);
+}
+
+static void acpi_wmi_remove_bus_device(void *data)
+{
+	struct device *wmi_bus_dev = data;
+
+	device_unregister(wmi_bus_dev);
 }
 
 static int acpi_wmi_probe(struct platform_device *device)
@@ -1511,6 +1266,17 @@ static int acpi_wmi_probe(struct platform_device *device)
 		return -ENODEV;
 	}
 
+	wmi_bus_dev = device_create(&wmi_bus_class, &device->dev, MKDEV(0, 0), NULL, "wmi_bus-%s",
+				    dev_name(&device->dev));
+	if (IS_ERR(wmi_bus_dev))
+		return PTR_ERR(wmi_bus_dev);
+
+	error = devm_add_action_or_reset(&device->dev, acpi_wmi_remove_bus_device, wmi_bus_dev);
+	if (error < 0)
+		return error;
+
+	dev_set_drvdata(&device->dev, wmi_bus_dev);
+
 	status = acpi_install_address_space_handler(acpi_device->handle,
 						    ACPI_ADR_SPACE_EC,
 						    &acpi_wmi_ec_space_handler,
@@ -1519,46 +1285,29 @@ static int acpi_wmi_probe(struct platform_device *device)
 		dev_err(&device->dev, "Error installing EC region handler\n");
 		return -ENODEV;
 	}
+	error = devm_add_action_or_reset(&device->dev, acpi_wmi_remove_address_space_handler,
+					 acpi_device);
+	if (error < 0)
+		return error;
 
-	status = acpi_install_notify_handler(acpi_device->handle,
-					     ACPI_ALL_NOTIFY,
-					     acpi_wmi_notify_handler,
-					     NULL);
+	status = acpi_install_notify_handler(acpi_device->handle, ACPI_ALL_NOTIFY,
+					     acpi_wmi_notify_handler, wmi_bus_dev);
 	if (ACPI_FAILURE(status)) {
 		dev_err(&device->dev, "Error installing notify handler\n");
-		error = -ENODEV;
-		goto err_remove_ec_handler;
-	}
-
-	wmi_bus_dev = device_create(&wmi_bus_class, &device->dev, MKDEV(0, 0),
-				    NULL, "wmi_bus-%s", dev_name(&device->dev));
-	if (IS_ERR(wmi_bus_dev)) {
-		error = PTR_ERR(wmi_bus_dev);
-		goto err_remove_notify_handler;
+		return -ENODEV;
 	}
-	dev_set_drvdata(&device->dev, wmi_bus_dev);
+	error = devm_add_action_or_reset(&device->dev, acpi_wmi_remove_notify_handler,
+					 acpi_device);
+	if (error < 0)
+		return error;
 
 	error = parse_wdg(wmi_bus_dev, device);
 	if (error) {
 		pr_err("Failed to parse WDG method\n");
-		goto err_remove_busdev;
+		return error;
 	}
 
 	return 0;
-
-err_remove_busdev:
-	device_unregister(wmi_bus_dev);
-
-err_remove_notify_handler:
-	acpi_remove_notify_handler(acpi_device->handle, ACPI_ALL_NOTIFY,
-				   acpi_wmi_notify_handler);
-
-err_remove_ec_handler:
-	acpi_remove_address_space_handler(acpi_device->handle,
-					  ACPI_ADR_SPACE_EC,
-					  &acpi_wmi_ec_space_handler);
-
-	return error;
 }
 
 int __must_check __wmi_driver_register(struct wmi_driver *driver,
diff --git a/drivers/platform/x86/x86-android-tablets/core.c b/drivers/platform/x86/x86-android-tablets/core.c
index b55957bde034..f8221a15575b 100644
--- a/drivers/platform/x86/x86-android-tablets/core.c
+++ b/drivers/platform/x86/x86-android-tablets/core.c
@@ -141,9 +141,11 @@ int x86_acpi_irq_helper_get(const struct x86_acpi_irq_data *data)
 }
 
 static int i2c_client_count;
+static int spi_dev_count;
 static int pdev_count;
 static int serdev_count;
 static struct i2c_client **i2c_clients;
+static struct spi_device **spi_devs;
 static struct platform_device **pdevs;
 static struct serdev_device **serdevs;
 static struct gpio_keys_button *buttons;
@@ -185,6 +187,46 @@ static __init int x86_instantiate_i2c_client(const struct x86_dev_info *dev_info
 	return 0;
 }
 
+static __init int x86_instantiate_spi_dev(const struct x86_dev_info *dev_info, int idx)
+{
+	const struct x86_spi_dev_info *spi_dev_info = &dev_info->spi_dev_info[idx];
+	struct spi_board_info board_info = spi_dev_info->board_info;
+	struct spi_controller *controller;
+	struct acpi_device *adev;
+	acpi_handle handle;
+	acpi_status status;
+
+	board_info.irq = x86_acpi_irq_helper_get(&spi_dev_info->irq_data);
+	if (board_info.irq < 0)
+		return board_info.irq;
+
+	status = acpi_get_handle(NULL, spi_dev_info->ctrl_path, &handle);
+	if (ACPI_FAILURE(status)) {
+		pr_err("Error could not get %s handle\n", spi_dev_info->ctrl_path);
+		return -ENODEV;
+	}
+
+	adev = acpi_fetch_acpi_dev(handle);
+	if (!adev) {
+		pr_err("Error could not get adev for %s\n", spi_dev_info->ctrl_path);
+		return -ENODEV;
+	}
+
+	controller = acpi_spi_find_controller_by_adev(adev);
+	if (!controller) {
+		pr_err("Error could not get SPI controller for %s\n", spi_dev_info->ctrl_path);
+		return -ENODEV;
+	}
+
+	spi_devs[idx] = spi_new_device(controller, &board_info);
+	put_device(&controller->dev);
+	if (!spi_devs[idx])
+		return dev_err_probe(&controller->dev, -ENOMEM,
+				     "creating SPI-device %d\n", idx);
+
+	return 0;
+}
+
 static __init int x86_instantiate_serdev(const struct x86_serdev_info *info, int idx)
 {
 	struct acpi_device *ctrl_adev, *serdev_adev;
@@ -263,6 +305,11 @@ static void x86_android_tablet_remove(struct platform_device *pdev)
 	kfree(pdevs);
 	kfree(buttons);
 
+	for (i = 0; i < spi_dev_count; i++)
+		spi_unregister_device(spi_devs[i]);
+
+	kfree(spi_devs);
+
 	for (i = 0; i < i2c_client_count; i++)
 		i2c_unregister_device(i2c_clients[i]);
 
@@ -333,6 +380,21 @@ static __init int x86_android_tablet_probe(struct platform_device *pdev)
 		}
 	}
 
+	spi_devs = kcalloc(dev_info->spi_dev_count, sizeof(*spi_devs), GFP_KERNEL);
+	if (!spi_devs) {
+		x86_android_tablet_remove(pdev);
+		return -ENOMEM;
+	}
+
+	spi_dev_count = dev_info->spi_dev_count;
+	for (i = 0; i < spi_dev_count; i++) {
+		ret = x86_instantiate_spi_dev(dev_info, i);
+		if (ret < 0) {
+			x86_android_tablet_remove(pdev);
+			return ret;
+		}
+	}
+
 	/* + 1 to make space for (optional) gpio_keys_button pdev */
 	pdevs = kcalloc(dev_info->pdev_count + 1, sizeof(*pdevs), GFP_KERNEL);
 	if (!pdevs) {
diff --git a/drivers/platform/x86/x86-android-tablets/lenovo.c b/drivers/platform/x86/x86-android-tablets/lenovo.c
index c1e68211283f..f1c66a61bfc5 100644
--- a/drivers/platform/x86/x86-android-tablets/lenovo.c
+++ b/drivers/platform/x86/x86-android-tablets/lenovo.c
@@ -12,6 +12,8 @@
 
 #include <linux/efi.h>
 #include <linux/gpio/machine.h>
+#include <linux/mfd/arizona/pdata.h>
+#include <linux/mfd/arizona/registers.h>
 #include <linux/mfd/intel_soc_pmic.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/pinctrl/machine.h>
@@ -32,12 +34,30 @@
  *
  * To avoid having to have a similar hack in the mainline kernel program the
  * LP8557 to directly set the level and use the lp855x_bl driver for control.
+ *
+ * The LP8557 can either be configured to multiply its PWM input and
+ * the I2C register set level (requiring both to be at 100% for 100% output);
+ * or to only take the I2C register set level into account.
+ *
+ * Multiplying the 2 levels is useful because this will turn off the backlight
+ * when the panel goes off and turns off its PWM output.
+ *
+ * But on some models the panel's PWM output defaults to a duty-cycle of
+ * much less then 100%, severely limiting max brightness. In this case
+ * the LP8557 should be configured to only take the I2C register into
+ * account and the i915 driver must turn off the panel and the backlight
+ * separately using e.g. VBT MIPI sequences to turn off the backlight.
  */
-static struct lp855x_platform_data lenovo_lp8557_pdata = {
+static struct lp855x_platform_data lenovo_lp8557_pwm_and_reg_pdata = {
 	.device_control = 0x86,
 	.initial_brightness = 128,
 };
 
+static struct lp855x_platform_data lenovo_lp8557_reg_only_pdata = {
+	.device_control = 0x85,
+	.initial_brightness = 128,
+};
+
 /* Lenovo Yoga Book X90F / X90L's Android factory img has everything hardcoded */
 
 static const struct property_entry lenovo_yb1_x90_wacom_props[] = {
@@ -120,7 +140,7 @@ static const struct x86_i2c_client_info lenovo_yb1_x90_i2c_clients[] __initconst
 			.type = "lp8557",
 			.addr = 0x2c,
 			.dev_name = "lp8557",
-			.platform_data = &lenovo_lp8557_pdata,
+			.platform_data = &lenovo_lp8557_pwm_and_reg_pdata,
 		},
 		.adapter_path = "\\_SB_.PCI0.I2C4",
 	}, {
@@ -356,7 +376,7 @@ static struct x86_i2c_client_info lenovo_yoga_tab2_830_1050_i2c_clients[] __init
 			.type = "lp8557",
 			.addr = 0x2c,
 			.dev_name = "lp8557",
-			.platform_data = &lenovo_lp8557_pdata,
+			.platform_data = &lenovo_lp8557_pwm_and_reg_pdata,
 		},
 		.adapter_path = "\\_SB_.I2C3",
 	},
@@ -653,12 +673,94 @@ static const struct x86_i2c_client_info lenovo_yt3_i2c_clients[] __initconst = {
 			.type = "lp8557",
 			.addr = 0x2c,
 			.dev_name = "lp8557",
-			.platform_data = &lenovo_lp8557_pdata,
+			.platform_data = &lenovo_lp8557_reg_only_pdata,
 		},
 		.adapter_path = "\\_SB_.PCI0.I2C1",
 	}
 };
 
+/*
+ * The AOSP 3.5 mm Headset: Accessory Specification gives the following values:
+ * Function A Play/Pause:           0 ohm
+ * Function D Voice assistant:    135 ohm
+ * Function B Volume Up           240 ohm
+ * Function C Volume Down         470 ohm
+ * Minimum Mic DC resistance     1000 ohm
+ * Minimum Ear speaker impedance   16 ohm
+ * Note the first max value below must be less then the min. speaker impedance,
+ * to allow CTIA/OMTP detection to work. The other max values are the closest
+ * value from extcon-arizona.c:arizona_micd_levels halfway 2 button resistances.
+ */
+static const struct arizona_micd_range arizona_micd_aosp_ranges[] = {
+	{ .max =  11, .key = KEY_PLAYPAUSE },
+	{ .max = 186, .key = KEY_VOICECOMMAND },
+	{ .max = 348, .key = KEY_VOLUMEUP },
+	{ .max = 752, .key = KEY_VOLUMEDOWN },
+};
+
+/* YT3 WM5102 arizona_micd_config comes from Android kernel sources */
+static struct arizona_micd_config lenovo_yt3_wm5102_micd_config[] = {
+	{ 0, 1, 0 },
+	{ ARIZONA_ACCDET_SRC, 2, 1 },
+};
+
+static struct arizona_pdata lenovo_yt3_wm5102_pdata = {
+	.irq_flags = IRQF_TRIGGER_LOW,
+	.micd_detect_debounce = 200,
+	.micd_ranges = arizona_micd_aosp_ranges,
+	.num_micd_ranges = ARRAY_SIZE(arizona_micd_aosp_ranges),
+	.hpdet_channel = ARIZONA_ACCDET_MODE_HPL,
+
+	/* Below settings come from Android kernel sources */
+	.micd_bias_start_time = 1,
+	.micd_rate = 6,
+	.micd_configs = lenovo_yt3_wm5102_micd_config,
+	.num_micd_configs = ARRAY_SIZE(lenovo_yt3_wm5102_micd_config),
+	.micbias = {
+		[0] = { /* MICBIAS1 */
+			.mV = 2800,
+			.ext_cap = 1,
+			.discharge = 1,
+			.soft_start = 0,
+			.bypass = 0,
+		},
+		[1] = { /* MICBIAS2 */
+			.mV = 2800,
+			.ext_cap = 1,
+			.discharge = 1,
+			.soft_start = 0,
+			.bypass = 0,
+		},
+		[2] = { /* MICBIAS2 */
+			.mV = 2800,
+			.ext_cap = 1,
+			.discharge = 1,
+			.soft_start = 0,
+			.bypass = 0,
+		},
+	},
+};
+
+static const struct x86_spi_dev_info lenovo_yt3_spi_devs[] __initconst = {
+	{
+		/* WM5102 codec */
+		.board_info = {
+			.modalias = "wm5102",
+			.platform_data = &lenovo_yt3_wm5102_pdata,
+			.max_speed_hz = 5000000,
+		},
+		.ctrl_path = "\\_SB_.PCI0.SPI1",
+		.irq_data = {
+			.type = X86_ACPI_IRQ_TYPE_GPIOINT,
+			.chip = "INT33FF:00",
+			.index = 91,
+			.trigger = ACPI_LEVEL_SENSITIVE,
+			.polarity = ACPI_ACTIVE_LOW,
+			.con_id = "wm5102_irq",
+		},
+	}
+};
+
 static int __init lenovo_yt3_init(void)
 {
 	int ret;
@@ -702,14 +804,28 @@ static struct gpiod_lookup_table lenovo_yt3_hideep_gpios = {
 	},
 };
 
+static struct gpiod_lookup_table lenovo_yt3_wm5102_gpios = {
+	.dev_id = "spi1.0",
+	.table = {
+		GPIO_LOOKUP("INT33FF:00", 75, "wlf,spkvdd-ena", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("INT33FF:00", 81, "wlf,ldoena", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("INT33FF:00", 82, "reset", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("arizona", 2, "wlf,micd-pol", GPIO_ACTIVE_HIGH),
+		{ }
+	},
+};
+
 static struct gpiod_lookup_table * const lenovo_yt3_gpios[] = {
 	&lenovo_yt3_hideep_gpios,
+	&lenovo_yt3_wm5102_gpios,
 	NULL
 };
 
 const struct x86_dev_info lenovo_yt3_info __initconst = {
 	.i2c_client_info = lenovo_yt3_i2c_clients,
 	.i2c_client_count = ARRAY_SIZE(lenovo_yt3_i2c_clients),
+	.spi_dev_info = lenovo_yt3_spi_devs,
+	.spi_dev_count = ARRAY_SIZE(lenovo_yt3_spi_devs),
 	.gpiod_lookup_tables = lenovo_yt3_gpios,
 	.init = lenovo_yt3_init,
 };
diff --git a/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h b/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h
index 9d2fb7fded6d..49fed9410adb 100644
--- a/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h
+++ b/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h
@@ -14,6 +14,7 @@
 #include <linux/gpio_keys.h>
 #include <linux/i2c.h>
 #include <linux/irqdomain_defs.h>
+#include <linux/spi/spi.h>
 
 struct gpio_desc;
 struct gpiod_lookup_table;
@@ -48,6 +49,12 @@ struct x86_i2c_client_info {
 	struct x86_acpi_irq_data irq_data;
 };
 
+struct x86_spi_dev_info {
+	struct spi_board_info board_info;
+	char *ctrl_path;
+	struct x86_acpi_irq_data irq_data;
+};
+
 struct x86_serdev_info {
 	const char *ctrl_hid;
 	const char *ctrl_uid;
@@ -72,10 +79,12 @@ struct x86_dev_info {
 	const struct software_node *bat_swnode;
 	struct gpiod_lookup_table * const *gpiod_lookup_tables;
 	const struct x86_i2c_client_info *i2c_client_info;
+	const struct x86_spi_dev_info *spi_dev_info;
 	const struct platform_device_info *pdev_info;
 	const struct x86_serdev_info *serdev_info;
 	const struct x86_gpio_button *gpio_button;
 	int i2c_client_count;
+	int spi_dev_count;
 	int pdev_count;
 	int serdev_count;
 	int gpio_button_count;
diff --git a/drivers/pmdomain/arm/scmi_perf_domain.c b/drivers/pmdomain/arm/scmi_perf_domain.c
index bc3f78abb6da..709bbc448fad 100644
--- a/drivers/pmdomain/arm/scmi_perf_domain.c
+++ b/drivers/pmdomain/arm/scmi_perf_domain.c
@@ -35,7 +35,7 @@ scmi_pd_set_perf_state(struct generic_pm_domain *genpd, unsigned int state)
 	if (!state)
 		return -EINVAL;
 
-	ret = pd->perf_ops->level_set(pd->ph, pd->domain_id, state, true);
+	ret = pd->perf_ops->level_set(pd->ph, pd->domain_id, state, false);
 	if (ret)
 		dev_warn(&genpd->dev, "Failed with %d when trying to set %d perf level",
 			 ret, state);
diff --git a/drivers/pmdomain/qcom/rpmpd.c b/drivers/pmdomain/qcom/rpmpd.c
index 07590a3ef19c..7796d65f96e8 100644
--- a/drivers/pmdomain/qcom/rpmpd.c
+++ b/drivers/pmdomain/qcom/rpmpd.c
@@ -1044,6 +1044,7 @@ static int rpmpd_probe(struct platform_device *pdev)
 		rpmpds[i]->pd.power_off = rpmpd_power_off;
 		rpmpds[i]->pd.power_on = rpmpd_power_on;
 		rpmpds[i]->pd.set_performance_state = rpmpd_set_performance;
+		rpmpds[i]->pd.flags = GENPD_FLAG_ACTIVE_WAKEUP;
 		pm_genpd_init(&rpmpds[i]->pd, NULL, true);
 
 		data->domains[i] = &rpmpds[i]->pd;
diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c
index 4f05f610391b..c02ce0834c2c 100644
--- a/drivers/pnp/pnpacpi/rsparser.c
+++ b/drivers/pnp/pnpacpi/rsparser.c
@@ -151,13 +151,13 @@ static int vendor_resource_matches(struct pnp_dev *dev,
 static void pnpacpi_parse_allocated_vendor(struct pnp_dev *dev,
 				    struct acpi_resource_vendor_typed *vendor)
 {
-	if (vendor_resource_matches(dev, vendor, &hp_ccsr_uuid, 16)) {
-		u64 start, length;
+	struct { u64 start, length; } range;
 
-		memcpy(&start, vendor->byte_data, sizeof(start));
-		memcpy(&length, vendor->byte_data + 8, sizeof(length));
-
-		pnp_add_mem_resource(dev, start, start + length - 1, 0);
+	if (vendor_resource_matches(dev, vendor, &hp_ccsr_uuid,
+				    sizeof(range))) {
+		memcpy(&range, vendor->byte_data, sizeof(range));
+		pnp_add_mem_resource(dev, range.start, range.start +
+				     range.length - 1, 0);
 	}
 }
 
diff --git a/drivers/pnp/pnpbios/bioscalls.c b/drivers/pnp/pnpbios/bioscalls.c
index ddc6f2163c8e..1f31dce5835a 100644
--- a/drivers/pnp/pnpbios/bioscalls.c
+++ b/drivers/pnp/pnpbios/bioscalls.c
@@ -60,7 +60,7 @@ do { \
 	set_desc_limit(&gdt[(selname) >> 3], (size) - 1); \
 } while(0)
 
-static struct desc_struct bad_bios_desc = GDT_ENTRY_INIT(0x4092,
+static struct desc_struct bad_bios_desc = GDT_ENTRY_INIT(DESC_DATA32_BIOS,
 			(unsigned long)__va(0x400UL), PAGE_SIZE - 0x400 - 1);
 
 /*
diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c
index 2ff7717530bf..9193c3b8edeb 100644
--- a/drivers/powercap/dtpm_cpu.c
+++ b/drivers/powercap/dtpm_cpu.c
@@ -24,7 +24,6 @@
 #include <linux/of.h>
 #include <linux/pm_qos.h>
 #include <linux/slab.h>
-#include <linux/units.h>
 
 struct dtpm_cpu {
 	struct dtpm dtpm;
@@ -104,8 +103,7 @@ static u64 get_pd_power_uw(struct dtpm *dtpm)
 		if (pd->table[i].frequency < freq)
 			continue;
 
-		return scale_pd_power_uw(pd_mask, pd->table[i].power *
-					 MICROWATT_PER_MILLIWATT);
+		return scale_pd_power_uw(pd_mask, pd->table[i].power);
 	}
 
 	return 0;
@@ -122,11 +120,9 @@ static int update_pd_power_uw(struct dtpm *dtpm)
 	nr_cpus = cpumask_weight(&cpus);
 
 	dtpm->power_min = em->table[0].power;
-	dtpm->power_min *= MICROWATT_PER_MILLIWATT;
 	dtpm->power_min *= nr_cpus;
 
 	dtpm->power_max = em->table[em->nr_perf_states - 1].power;
-	dtpm->power_max *= MICROWATT_PER_MILLIWATT;
 	dtpm->power_max *= nr_cpus;
 
 	return 0;
@@ -144,6 +140,8 @@ static void pd_release(struct dtpm *dtpm)
 	if (policy) {
 		for_each_cpu(dtpm_cpu->cpu, policy->related_cpus)
 			per_cpu(dtpm_per_cpu, dtpm_cpu->cpu) = NULL;
+
+		cpufreq_cpu_put(policy);
 	}
 	
 	kfree(dtpm_cpu);
@@ -195,12 +193,16 @@ static int __dtpm_cpu_setup(int cpu, struct dtpm *parent)
 		return 0;
 
 	pd = em_cpu_get(cpu);
-	if (!pd || em_is_artificial(pd))
-		return -EINVAL;
+	if (!pd || em_is_artificial(pd)) {
+		ret = -EINVAL;
+		goto release_policy;
+	}
 
 	dtpm_cpu = kzalloc(sizeof(*dtpm_cpu), GFP_KERNEL);
-	if (!dtpm_cpu)
-		return -ENOMEM;
+	if (!dtpm_cpu) {
+		ret = -ENOMEM;
+		goto release_policy;
+	}
 
 	dtpm_init(&dtpm_cpu->dtpm, &dtpm_ops);
 	dtpm_cpu->cpu = cpu;
@@ -220,6 +222,7 @@ static int __dtpm_cpu_setup(int cpu, struct dtpm *parent)
 	if (ret)
 		goto out_dtpm_unregister;
 
+	cpufreq_cpu_put(policy);
 	return 0;
 
 out_dtpm_unregister:
@@ -231,6 +234,8 @@ out_kfree_dtpm_cpu:
 		per_cpu(dtpm_per_cpu, cpu) = NULL;
 	kfree(dtpm_cpu);
 
+release_policy:
+	cpufreq_cpu_put(policy);
 	return ret;
 }
 
diff --git a/drivers/powercap/dtpm_devfreq.c b/drivers/powercap/dtpm_devfreq.c
index 91276761a31d..612c3b59dd5b 100644
--- a/drivers/powercap/dtpm_devfreq.c
+++ b/drivers/powercap/dtpm_devfreq.c
@@ -39,10 +39,8 @@ static int update_pd_power_uw(struct dtpm *dtpm)
 	struct em_perf_domain *pd = em_pd_get(dev);
 
 	dtpm->power_min = pd->table[0].power;
-	dtpm->power_min *= MICROWATT_PER_MILLIWATT;
 
 	dtpm->power_max = pd->table[pd->nr_perf_states - 1].power;
-	dtpm->power_max *= MICROWATT_PER_MILLIWATT;
 
 	return 0;
 }
@@ -54,13 +52,10 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit)
 	struct device *dev = devfreq->dev.parent;
 	struct em_perf_domain *pd = em_pd_get(dev);
 	unsigned long freq;
-	u64 power;
 	int i;
 
 	for (i = 0; i < pd->nr_perf_states; i++) {
-
-		power = pd->table[i].power * MICROWATT_PER_MILLIWATT;
-		if (power > power_limit)
+		if (pd->table[i].power > power_limit)
 			break;
 	}
 
@@ -68,7 +63,7 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit)
 
 	dev_pm_qos_update_request(&dtpm_devfreq->qos_req, freq);
 
-	power_limit = pd->table[i - 1].power * MICROWATT_PER_MILLIWATT;
+	power_limit = pd->table[i - 1].power;
 
 	return power_limit;
 }
@@ -110,7 +105,7 @@ static u64 get_pd_power_uw(struct dtpm *dtpm)
 		if (pd->table[i].frequency < freq)
 			continue;
 
-		power = pd->table[i].power * MICROWATT_PER_MILLIWATT;
+		power = pd->table[i].power;
 		power *= status.busy_time;
 		power >>= 10;
 
diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index 3f7a74788802..7513018c9f9a 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -572,7 +572,8 @@ ssize_t ptp_read(struct posix_clock_context *pccontext, uint rdflags,
 
 	for (i = 0; i < cnt; i++) {
 		event[i] = queue->buf[queue->head];
-		queue->head = (queue->head + 1) % PTP_MAX_TIMESTAMPS;
+		/* Paired with READ_ONCE() in queue_cnt() */
+		WRITE_ONCE(queue->head, (queue->head + 1) % PTP_MAX_TIMESTAMPS);
 	}
 
 	spin_unlock_irqrestore(&queue->lock, flags);
diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index 3134568af622..15b804ba4868 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -57,10 +57,11 @@ static void enqueue_external_timestamp(struct timestamp_event_queue *queue,
 	dst->t.sec = seconds;
 	dst->t.nsec = remainder;
 
+	/* Both WRITE_ONCE() are paired with READ_ONCE() in queue_cnt() */
 	if (!queue_free(queue))
-		queue->head = (queue->head + 1) % PTP_MAX_TIMESTAMPS;
+		WRITE_ONCE(queue->head, (queue->head + 1) % PTP_MAX_TIMESTAMPS);
 
-	queue->tail = (queue->tail + 1) % PTP_MAX_TIMESTAMPS;
+	WRITE_ONCE(queue->tail, (queue->tail + 1) % PTP_MAX_TIMESTAMPS);
 
 	spin_unlock_irqrestore(&queue->lock, flags);
 }
diff --git a/drivers/ptp/ptp_ines.c b/drivers/ptp/ptp_ines.c
index ed215b458183..1d2940a78455 100644
--- a/drivers/ptp/ptp_ines.c
+++ b/drivers/ptp/ptp_ines.c
@@ -328,17 +328,15 @@ static u64 ines_find_txts(struct ines_port *port, struct sk_buff *skb)
 	return ns;
 }
 
-static int ines_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
+static int ines_hwtstamp(struct mii_timestamper *mii_ts,
+			 struct kernel_hwtstamp_config *cfg,
+			 struct netlink_ext_ack *extack)
 {
 	struct ines_port *port = container_of(mii_ts, struct ines_port, mii_ts);
 	u32 cm_one_step = 0, port_conf, ts_stat_rx, ts_stat_tx;
-	struct hwtstamp_config cfg;
 	unsigned long flags;
 
-	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
-		return -EFAULT;
-
-	switch (cfg.tx_type) {
+	switch (cfg->tx_type) {
 	case HWTSTAMP_TX_OFF:
 		ts_stat_tx = 0;
 		break;
@@ -353,7 +351,7 @@ static int ines_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	switch (cfg.rx_filter) {
+	switch (cfg->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		ts_stat_rx = 0;
 		break;
@@ -372,7 +370,7 @@ static int ines_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 		ts_stat_rx = TS_ENABLE;
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		break;
 	default:
 		return -ERANGE;
@@ -393,7 +391,7 @@ static int ines_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 
 	spin_unlock_irqrestore(&port->lock, flags);
 
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	return 0;
 }
 
 static void ines_link_state(struct mii_timestamper *mii_ts,
diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c
index 4021d3d325f9..5f858e426bbd 100644
--- a/drivers/ptp/ptp_ocp.c
+++ b/drivers/ptp/ptp_ocp.c
@@ -1716,20 +1716,6 @@ ptp_ocp_get_mem(struct ptp_ocp *bp, struct ocp_resource *r)
 	return __ptp_ocp_get_mem(bp, start, r->size);
 }
 
-static void
-ptp_ocp_set_irq_resource(struct resource *res, int irq)
-{
-	struct resource r = DEFINE_RES_IRQ(irq);
-	*res = r;
-}
-
-static void
-ptp_ocp_set_mem_resource(struct resource *res, resource_size_t start, int size)
-{
-	struct resource r = DEFINE_RES_MEM(start, size);
-	*res = r;
-}
-
 static int
 ptp_ocp_register_spi(struct ptp_ocp *bp, struct ocp_resource *r)
 {
@@ -1741,15 +1727,15 @@ ptp_ocp_register_spi(struct ptp_ocp *bp, struct ocp_resource *r)
 	int id;
 
 	start = pci_resource_start(pdev, 0) + r->offset;
-	ptp_ocp_set_mem_resource(&res[0], start, r->size);
-	ptp_ocp_set_irq_resource(&res[1], pci_irq_vector(pdev, r->irq_vec));
+	res[0] = DEFINE_RES_MEM(start, r->size);
+	res[1] = DEFINE_RES_IRQ(pci_irq_vector(pdev, r->irq_vec));
 
 	info = r->extra;
 	id = pci_dev_id(pdev) << 1;
 	id += info->pci_offset;
 
 	p = platform_device_register_resndata(&pdev->dev, info->name, id,
-					      res, 2, info->data,
+					      res, ARRAY_SIZE(res), info->data,
 					      info->data_size);
 	if (IS_ERR(p))
 		return PTR_ERR(p);
@@ -1768,11 +1754,11 @@ ptp_ocp_i2c_bus(struct pci_dev *pdev, struct ocp_resource *r, int id)
 
 	info = r->extra;
 	start = pci_resource_start(pdev, 0) + r->offset;
-	ptp_ocp_set_mem_resource(&res[0], start, r->size);
-	ptp_ocp_set_irq_resource(&res[1], pci_irq_vector(pdev, r->irq_vec));
+	res[0] = DEFINE_RES_MEM(start, r->size);
+	res[1] = DEFINE_RES_IRQ(pci_irq_vector(pdev, r->irq_vec));
 
 	return platform_device_register_resndata(&pdev->dev, info->name,
-						 id, res, 2,
+						 id, res, ARRAY_SIZE(res),
 						 info->data, info->data_size);
 }
 
@@ -4260,13 +4246,6 @@ static int ptp_ocp_dpll_mode_get(const struct dpll_device *dpll, void *priv,
 	return 0;
 }
 
-static bool ptp_ocp_dpll_mode_supported(const struct dpll_device *dpll,
-					void *priv, const enum dpll_mode mode,
-					struct netlink_ext_ack *extack)
-{
-	return mode == DPLL_MODE_AUTOMATIC;
-}
-
 static int ptp_ocp_dpll_direction_get(const struct dpll_pin *pin,
 				      void *pin_priv,
 				      const struct dpll_device *dpll,
@@ -4350,7 +4329,6 @@ static int ptp_ocp_dpll_frequency_get(const struct dpll_pin *pin,
 static const struct dpll_device_ops dpll_ops = {
 	.lock_status_get = ptp_ocp_dpll_lock_status_get,
 	.mode_get = ptp_ocp_dpll_mode_get,
-	.mode_supported = ptp_ocp_dpll_mode_supported,
 };
 
 static const struct dpll_pin_ops dpll_pins_ops = {
@@ -4492,7 +4470,7 @@ ptp_ocp_remove(struct pci_dev *pdev)
 	cancel_delayed_work_sync(&bp->sync_work);
 	for (i = 0; i < OCP_SMA_NUM; i++) {
 		if (bp->sma[i].dpll_pin) {
-			dpll_pin_unregister(bp->dpll, bp->sma[i].dpll_pin, &dpll_pins_ops, bp);
+			dpll_pin_unregister(bp->dpll, bp->sma[i].dpll_pin, &dpll_pins_ops, &bp->sma[i]);
 			dpll_pin_put(bp->sma[i].dpll_pin);
 		}
 	}
diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h
index 35fde0a05746..45f9002a5dca 100644
--- a/drivers/ptp/ptp_private.h
+++ b/drivers/ptp/ptp_private.h
@@ -85,9 +85,13 @@ struct ptp_vclock {
  * that a writer might concurrently increment the tail does not
  * matter, since the queue remains nonempty nonetheless.
  */
-static inline int queue_cnt(struct timestamp_event_queue *q)
+static inline int queue_cnt(const struct timestamp_event_queue *q)
 {
-	int cnt = q->tail - q->head;
+	/*
+	 * Paired with WRITE_ONCE() in enqueue_external_timestamp(),
+	 * ptp_read(), extts_fifo_show().
+	 */
+	int cnt = READ_ONCE(q->tail) - READ_ONCE(q->head);
 	return cnt < 0 ? PTP_MAX_TIMESTAMPS + cnt : cnt;
 }
 
diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c
index 7d023d9d0acb..f7a499a1bd39 100644
--- a/drivers/ptp/ptp_sysfs.c
+++ b/drivers/ptp/ptp_sysfs.c
@@ -94,7 +94,8 @@ static ssize_t extts_fifo_show(struct device *dev,
 	qcnt = queue_cnt(queue);
 	if (qcnt) {
 		event = queue->buf[queue->head];
-		queue->head = (queue->head + 1) % PTP_MAX_TIMESTAMPS;
+		/* Paired with READ_ONCE() in queue_cnt() */
+		WRITE_ONCE(queue->head, (queue->head + 1) % PTP_MAX_TIMESTAMPS);
 	}
 	spin_unlock_irqrestore(&queue->lock, flags);
 
diff --git a/drivers/pwm/pwm-bcm2835.c b/drivers/pwm/pwm-bcm2835.c
index 9777babd5b95..ab30667f4f95 100644
--- a/drivers/pwm/pwm-bcm2835.c
+++ b/drivers/pwm/pwm-bcm2835.c
@@ -155,6 +155,8 @@ static int bcm2835_pwm_probe(struct platform_device *pdev)
 	pc->chip.ops = &bcm2835_pwm_ops;
 	pc->chip.npwm = 2;
 
+	platform_set_drvdata(pdev, pc);
+
 	ret = devm_pwmchip_add(&pdev->dev, &pc->chip);
 	if (ret < 0)
 		return dev_err_probe(&pdev->dev, ret,
diff --git a/drivers/rapidio/devices/tsi721.c b/drivers/rapidio/devices/tsi721.c
index 83323c3d10af..4b84270a8906 100644
--- a/drivers/rapidio/devices/tsi721.c
+++ b/drivers/rapidio/devices/tsi721.c
@@ -51,8 +51,9 @@ static void tsi721_imsg_handler(struct tsi721_device *priv, int ch);
  * @len: Length (in bytes) of the maintenance transaction
  * @data: Value to be read into
  *
- * Generates a local SREP space read. Returns %0 on
- * success or %-EINVAL on failure.
+ * Generates a local SREP space read.
+ *
+ * Returns: %0 on success or %-EINVAL on failure.
  */
 static int tsi721_lcread(struct rio_mport *mport, int index, u32 offset,
 			 int len, u32 *data)
@@ -75,8 +76,9 @@ static int tsi721_lcread(struct rio_mport *mport, int index, u32 offset,
  * @len: Length (in bytes) of the maintenance transaction
  * @data: Value to be written
  *
- * Generates a local write into SREP configuration space. Returns %0 on
- * success or %-EINVAL on failure.
+ * Generates a local write into SREP configuration space.
+ *
+ * Returns: %0 on success or %-EINVAL on failure.
  */
 static int tsi721_lcwrite(struct rio_mport *mport, int index, u32 offset,
 			  int len, u32 data)
@@ -104,7 +106,7 @@ static int tsi721_lcwrite(struct rio_mport *mport, int index, u32 offset,
  * @do_wr: Operation flag (1 == MAINT_WR)
  *
  * Generates a RapidIO maintenance transaction (Read or Write).
- * Returns %0 on success and %-EINVAL or %-EFAULT on failure.
+ * Returns: %0 on success and %-EINVAL or %-EFAULT on failure.
  */
 static int tsi721_maint_dma(struct tsi721_device *priv, u32 sys_size,
 			u16 destid, u8 hopcount, u32 offset, int len,
@@ -205,10 +207,10 @@ err_out:
  * @hopcount: Number of hops to target device
  * @offset: Offset into configuration space
  * @len: Length (in bytes) of the maintenance transaction
- * @val: Location to be read into
+ * @data: Location to be read into
  *
  * Generates a RapidIO maintenance read transaction.
- * Returns %0 on success and %-EINVAL or %-EFAULT on failure.
+ * Returns: %0 on success and %-EINVAL or %-EFAULT on failure.
  */
 static int tsi721_cread_dma(struct rio_mport *mport, int index, u16 destid,
 			u8 hopcount, u32 offset, int len, u32 *data)
@@ -228,10 +230,10 @@ static int tsi721_cread_dma(struct rio_mport *mport, int index, u16 destid,
  * @hopcount: Number of hops to target device
  * @offset: Offset into configuration space
  * @len: Length (in bytes) of the maintenance transaction
- * @val: Value to be written
+ * @data: Value to be written
  *
  * Generates a RapidIO maintenance write transaction.
- * Returns %0 on success and %-EINVAL or %-EFAULT on failure.
+ * Returns: %0 on success and %-EINVAL or %-EFAULT on failure.
  */
 static int tsi721_cwrite_dma(struct rio_mport *mport, int index, u16 destid,
 			 u8 hopcount, u32 offset, int len, u32 data)
@@ -250,6 +252,8 @@ static int tsi721_cwrite_dma(struct rio_mport *mport, int index, u16 destid,
  * Handles inbound port-write interrupts. Copies PW message from an internal
  * buffer into PW message FIFO and schedules deferred routine to process
  * queued messages.
+ *
+ * Returns: %0
  */
 static int
 tsi721_pw_handler(struct tsi721_device *priv)
@@ -307,6 +311,8 @@ static void tsi721_pw_dpc(struct work_struct *work)
  * tsi721_pw_enable - enable/disable port-write interface init
  * @mport: Master port implementing the port write unit
  * @enable:    1=enable; 0=disable port-write message handling
+ *
+ * Returns: %0
  */
 static int tsi721_pw_enable(struct rio_mport *mport, int enable)
 {
@@ -336,7 +342,9 @@ static int tsi721_pw_enable(struct rio_mport *mport, int enable)
  * @destid: Destination ID of target device
  * @data: 16-bit info field of RapidIO doorbell
  *
- * Sends a RapidIO doorbell message. Always returns %0.
+ * Sends a RapidIO doorbell message.
+ *
+ * Returns: %0
  */
 static int tsi721_dsend(struct rio_mport *mport, int index,
 			u16 destid, u16 data)
@@ -361,6 +369,8 @@ static int tsi721_dsend(struct rio_mport *mport, int index,
  * Handles inbound doorbell interrupts. Copies doorbell entry from an internal
  * buffer into DB message FIFO and schedules deferred  routine to process
  * queued DBs.
+ *
+ * Returns: %0
  */
 static int
 tsi721_dbell_handler(struct tsi721_device *priv)
@@ -453,6 +463,8 @@ static void tsi721_db_dpc(struct work_struct *work)
  *
  * Handles Tsi721 interrupts signaled using MSI and INTA. Checks reported
  * interrupt events and calls an event-specific handler(s).
+ *
+ * Returns: %IRQ_HANDLED or %IRQ_NONE
  */
 static irqreturn_t tsi721_irqhandler(int irq, void *ptr)
 {
@@ -607,6 +619,8 @@ static void tsi721_interrupts_init(struct tsi721_device *priv)
  * @ptr: Pointer to interrupt-specific data (tsi721_device structure)
  *
  * Handles outbound messaging interrupts signaled using MSI-X.
+ *
+ * Returns: %IRQ_HANDLED
  */
 static irqreturn_t tsi721_omsg_msix(int irq, void *ptr)
 {
@@ -624,6 +638,8 @@ static irqreturn_t tsi721_omsg_msix(int irq, void *ptr)
  * @ptr: Pointer to interrupt-specific data (tsi721_device structure)
  *
  * Handles inbound messaging interrupts signaled using MSI-X.
+ *
+ * Returns: %IRQ_HANDLED
  */
 static irqreturn_t tsi721_imsg_msix(int irq, void *ptr)
 {
@@ -641,6 +657,8 @@ static irqreturn_t tsi721_imsg_msix(int irq, void *ptr)
  * @ptr: Pointer to interrupt-specific data (tsi721_device structure)
  *
  * Handles Tsi721 interrupts from SRIO MAC.
+ *
+ * Returns: %IRQ_HANDLED
  */
 static irqreturn_t tsi721_srio_msix(int irq, void *ptr)
 {
@@ -663,6 +681,8 @@ static irqreturn_t tsi721_srio_msix(int irq, void *ptr)
  * Handles Tsi721 interrupts from SR2PC Channel.
  * NOTE: At this moment services only one SR2PC channel associated with inbound
  * doorbells.
+ *
+ * Returns: %IRQ_HANDLED
  */
 static irqreturn_t tsi721_sr2pc_ch_msix(int irq, void *ptr)
 {
@@ -689,6 +709,8 @@ static irqreturn_t tsi721_sr2pc_ch_msix(int irq, void *ptr)
  * Registers MSI-X interrupt service routines for interrupts that are active
  * immediately after mport initialization. Messaging interrupt service routines
  * should be registered during corresponding open requests.
+ *
+ * Returns: %0 on success or -errno value on failure.
  */
 static int tsi721_request_msix(struct tsi721_device *priv)
 {
@@ -717,6 +739,8 @@ static int tsi721_request_msix(struct tsi721_device *priv)
  *
  * Configures MSI-X support for Tsi721. Supports only an exact number
  * of requested vectors.
+ *
+ * Returns: %0 on success or -errno value on failure.
  */
 static int tsi721_enable_msix(struct tsi721_device *priv)
 {
@@ -1334,7 +1358,7 @@ static void tsi721_close_sr2pc_mapping(struct tsi721_device *priv)
  * @priv: pointer to tsi721 private data
  *
  * Initializes inbound port write handler.
- * Returns %0 on success or %-ENOMEM on failure.
+ * Returns: %0 on success or %-ENOMEM on failure.
  */
 static int tsi721_port_write_init(struct tsi721_device *priv)
 {
@@ -1412,7 +1436,8 @@ static void tsi721_doorbell_free(struct tsi721_device *priv)
  *
  * Initialize BDMA channel allocated for RapidIO maintenance read/write
  * request generation
- * Returns %0 on success or %-ENOMEM on failure.
+ *
+ * Returns: %0 on success or %-ENOMEM on failure.
  */
 static int tsi721_bdma_maint_init(struct tsi721_device *priv)
 {
@@ -1662,6 +1687,8 @@ tsi721_omsg_interrupt_disable(struct tsi721_device *priv, int ch,
  * @mbox: Outbound mailbox
  * @buffer: Message to add to outbound queue
  * @len: Length of message
+ *
+ * Returns: %0 on success or -errno value on failure.
  */
 static int
 tsi721_add_outb_message(struct rio_mport *mport, struct rio_dev *rdev, int mbox,
@@ -1869,6 +1896,8 @@ no_sts_update:
  * @dev_id: Device specific pointer to pass on event
  * @mbox: Mailbox to open
  * @entries: Number of entries in the outbound mailbox ring
+ *
+ * Returns: %0 on success or -errno value on failure.
  */
 static int tsi721_open_outb_mbox(struct rio_mport *mport, void *dev_id,
 				 int mbox, int entries)
@@ -2156,6 +2185,8 @@ static void tsi721_imsg_handler(struct tsi721_device *priv, int ch)
  * @dev_id: Device specific pointer to pass on event
  * @mbox: Mailbox to open
  * @entries: Number of entries in the inbound mailbox ring
+ *
+ * Returns: %0 on success or -errno value on failure.
  */
 static int tsi721_open_inb_mbox(struct rio_mport *mport, void *dev_id,
 				int mbox, int entries)
@@ -2409,6 +2440,8 @@ static void tsi721_close_inb_mbox(struct rio_mport *mport, int mbox)
  * @mport: Master port implementing the Inbound Messaging Engine
  * @mbox: Inbound mailbox number
  * @buf: Buffer to add to inbound queue
+ *
+ * Returns: %0 on success or -errno value on failure.
  */
 static int tsi721_add_inb_buffer(struct rio_mport *mport, int mbox, void *buf)
 {
@@ -2439,7 +2472,7 @@ out:
  * @mport: Master port implementing the Inbound Messaging Engine
  * @mbox: Inbound mailbox number
  *
- * Returns pointer to the message on success or NULL on failure.
+ * Returns: pointer to the message on success or %NULL on failure.
  */
 static void *tsi721_get_inb_message(struct rio_mport *mport, int mbox)
 {
@@ -2507,6 +2540,8 @@ out:
  * @priv: pointer to tsi721 private data
  *
  * Configures Tsi721 messaging engine.
+ *
+ * Returns: %0
  */
 static int tsi721_messages_init(struct tsi721_device *priv)
 {
@@ -2539,9 +2574,9 @@ static int tsi721_messages_init(struct tsi721_device *priv)
 /**
  * tsi721_query_mport - Fetch inbound message from the Tsi721 MSG Queue
  * @mport: Master port implementing the Inbound Messaging Engine
- * @mbox: Inbound mailbox number
+ * @attr: mport device attributes
  *
- * Returns pointer to the message on success or NULL on failure.
+ * Returns: pointer to the message on success or %NULL on failure.
  */
 static int tsi721_query_mport(struct rio_mport *mport,
 			      struct rio_mport_attr *attr)
@@ -2653,6 +2688,8 @@ static void tsi721_mport_release(struct device *dev)
  * @priv: pointer to tsi721 private data
  *
  * Configures Tsi721 as RapidIO master port.
+ *
+ * Returns: %0 on success or -errno value on failure.
  */
 static int tsi721_setup_mport(struct tsi721_device *priv)
 {
diff --git a/drivers/rapidio/devices/tsi721_dma.c b/drivers/rapidio/devices/tsi721_dma.c
index d375c02059f3..f77f75172bdc 100644
--- a/drivers/rapidio/devices/tsi721_dma.c
+++ b/drivers/rapidio/devices/tsi721_dma.c
@@ -283,11 +283,13 @@ void tsi721_bdma_handler(struct tsi721_bdma_chan *bdma_chan)
 
 #ifdef CONFIG_PCI_MSI
 /**
- * tsi721_omsg_msix - MSI-X interrupt handler for BDMA channels
+ * tsi721_bdma_msix - MSI-X interrupt handler for BDMA channels
  * @irq: Linux interrupt number
  * @ptr: Pointer to interrupt-specific data (BDMA channel structure)
  *
  * Handles BDMA channel interrupts signaled using MSI-X.
+ *
+ * Returns: %IRQ_HANDLED
  */
 static irqreturn_t tsi721_bdma_msix(int irq, void *ptr)
 {
diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index f3ec24691378..550145f82726 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -56,6 +56,16 @@ config REGULATOR_USERSPACE_CONSUMER
 
 	  If unsure, say no.
 
+config REGULATOR_NETLINK_EVENTS
+	bool "Enable support for receiving regulator events via netlink"
+	depends on NET
+	help
+	  Enabling this option allows the kernel to broadcast regulator events using
+	  the netlink mechanism. User-space applications can subscribe to these events
+	  for real-time updates on various regulator events.
+
+	  If unsure, say no.
+
 config REGULATOR_88PG86X
 	tristate "Marvell 88PG86X voltage regulators"
 	depends on I2C
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index b2b059b5ee56..46fb569e6be8 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -5,6 +5,7 @@
 
 
 obj-$(CONFIG_REGULATOR) += core.o dummy.o fixed-helper.o helpers.o devres.o irq_helpers.o
+obj-$(CONFIG_REGULATOR_NETLINK_EVENTS) += event.o
 obj-$(CONFIG_OF) += of_regulator.o
 obj-$(CONFIG_REGULATOR_FIXED_VOLTAGE) += fixed.o
 obj-$(CONFIG_REGULATOR_VIRTUAL_CONSUMER) += virtual.o
diff --git a/drivers/regulator/arizona-ldo1.c b/drivers/regulator/arizona-ldo1.c
index b465c0010665..4b54068d4f59 100644
--- a/drivers/regulator/arizona-ldo1.c
+++ b/drivers/regulator/arizona-ldo1.c
@@ -339,14 +339,12 @@ static int arizona_ldo1_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int arizona_ldo1_remove(struct platform_device *pdev)
+static void arizona_ldo1_remove(struct platform_device *pdev)
 {
 	struct arizona_ldo1 *ldo1 = platform_get_drvdata(pdev);
 
 	if (ldo1->ena_gpiod)
 		gpiod_put(ldo1->ena_gpiod);
-
-	return 0;
 }
 
 static int madera_ldo1_probe(struct platform_device *pdev)
@@ -377,7 +375,7 @@ static int madera_ldo1_probe(struct platform_device *pdev)
 
 static struct platform_driver arizona_ldo1_driver = {
 	.probe = arizona_ldo1_probe,
-	.remove = arizona_ldo1_remove,
+	.remove_new = arizona_ldo1_remove,
 	.driver		= {
 		.name	= "arizona-ldo1",
 		.probe_type = PROBE_FORCE_SYNCHRONOUS,
@@ -386,7 +384,7 @@ static struct platform_driver arizona_ldo1_driver = {
 
 static struct platform_driver madera_ldo1_driver = {
 	.probe = madera_ldo1_probe,
-	.remove = arizona_ldo1_remove,
+	.remove_new = arizona_ldo1_remove,
 	.driver		= {
 		.name	= "madera-ldo1",
 		.probe_type = PROBE_FORCE_SYNCHRONOUS,
diff --git a/drivers/regulator/bd9571mwv-regulator.c b/drivers/regulator/bd9571mwv-regulator.c
index d469481d8442..c7ceba56e7dc 100644
--- a/drivers/regulator/bd9571mwv-regulator.c
+++ b/drivers/regulator/bd9571mwv-regulator.c
@@ -260,10 +260,9 @@ static const struct dev_pm_ops bd9571mwv_pm  = {
 	SET_SYSTEM_SLEEP_PM_OPS(bd9571mwv_suspend, bd9571mwv_resume)
 };
 
-static int bd9571mwv_regulator_remove(struct platform_device *pdev)
+static void bd9571mwv_regulator_remove(struct platform_device *pdev)
 {
 	device_remove_file(&pdev->dev, &dev_attr_backup_mode);
-	return 0;
 }
 #define DEV_PM_OPS	&bd9571mwv_pm
 #else
@@ -357,7 +356,7 @@ static struct platform_driver bd9571mwv_regulator_driver = {
 		.pm = DEV_PM_OPS,
 	},
 	.probe = bd9571mwv_regulator_probe,
-	.remove = bd9571mwv_regulator_remove,
+	.remove_new = bd9571mwv_regulator_remove,
 	.id_table = bd9571mwv_regulator_id_table,
 };
 module_platform_driver(bd9571mwv_regulator_driver);
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 3137e40fcd3e..a968dabb48f5 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -19,6 +19,7 @@
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
 #include <linux/of.h>
+#include <linux/reboot.h>
 #include <linux/regmap.h>
 #include <linux/regulator/of_regulator.h>
 #include <linux/regulator/consumer.h>
@@ -32,6 +33,7 @@
 
 #include "dummy.h"
 #include "internal.h"
+#include "regnl.h"
 
 static DEFINE_WW_CLASS(regulator_ww_class);
 static DEFINE_MUTEX(regulator_nesting_mutex);
@@ -2918,7 +2920,8 @@ static int _regulator_enable(struct regulator *regulator)
 		/* Fallthrough on positive return values - already enabled */
 	}
 
-	rdev->use_count++;
+	if (regulator->enable_count == 1)
+		rdev->use_count++;
 
 	return 0;
 
@@ -2993,37 +2996,40 @@ static int _regulator_disable(struct regulator *regulator)
 
 	lockdep_assert_held_once(&rdev->mutex.base);
 
-	if (WARN(rdev->use_count <= 0,
+	if (WARN(regulator->enable_count == 0,
 		 "unbalanced disables for %s\n", rdev_get_name(rdev)))
 		return -EIO;
 
-	/* are we the last user and permitted to disable ? */
-	if (rdev->use_count == 1 &&
-	    (rdev->constraints && !rdev->constraints->always_on)) {
-
-		/* we are last user */
-		if (regulator_ops_is_valid(rdev, REGULATOR_CHANGE_STATUS)) {
-			ret = _notifier_call_chain(rdev,
-						   REGULATOR_EVENT_PRE_DISABLE,
-						   NULL);
-			if (ret & NOTIFY_STOP_MASK)
-				return -EINVAL;
-
-			ret = _regulator_do_disable(rdev);
-			if (ret < 0) {
-				rdev_err(rdev, "failed to disable: %pe\n", ERR_PTR(ret));
-				_notifier_call_chain(rdev,
-						REGULATOR_EVENT_ABORT_DISABLE,
+	if (regulator->enable_count == 1) {
+	/* disabling last enable_count from this regulator */
+		/* are we the last user and permitted to disable ? */
+		if (rdev->use_count == 1 &&
+		    (rdev->constraints && !rdev->constraints->always_on)) {
+
+			/* we are last user */
+			if (regulator_ops_is_valid(rdev, REGULATOR_CHANGE_STATUS)) {
+				ret = _notifier_call_chain(rdev,
+							   REGULATOR_EVENT_PRE_DISABLE,
+							   NULL);
+				if (ret & NOTIFY_STOP_MASK)
+					return -EINVAL;
+
+				ret = _regulator_do_disable(rdev);
+				if (ret < 0) {
+					rdev_err(rdev, "failed to disable: %pe\n", ERR_PTR(ret));
+					_notifier_call_chain(rdev,
+							REGULATOR_EVENT_ABORT_DISABLE,
+							NULL);
+					return ret;
+				}
+				_notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE,
 						NULL);
-				return ret;
 			}
-			_notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE,
-					NULL);
-		}
 
-		rdev->use_count = 0;
-	} else if (rdev->use_count > 1) {
-		rdev->use_count--;
+			rdev->use_count = 0;
+		} else if (rdev->use_count > 1) {
+			rdev->use_count--;
+		}
 	}
 
 	if (ret == 0)
@@ -4849,7 +4855,23 @@ static int _notifier_call_chain(struct regulator_dev *rdev,
 				  unsigned long event, void *data)
 {
 	/* call rdev chain first */
-	return blocking_notifier_call_chain(&rdev->notifier, event, data);
+	int ret =  blocking_notifier_call_chain(&rdev->notifier, event, data);
+
+	if (IS_REACHABLE(CONFIG_REGULATOR_NETLINK_EVENTS)) {
+		struct device *parent = rdev->dev.parent;
+		const char *rname = rdev_get_name(rdev);
+		char name[32];
+
+		/* Avoid duplicate debugfs directory names */
+		if (parent && rname == rdev->desc->name) {
+			snprintf(name, sizeof(name), "%s-%s", dev_name(parent),
+				 rname);
+			rname = name;
+		}
+		reg_generate_netlink_event(rname, event);
+	}
+
+	return ret;
 }
 
 int _regulator_bulk_get(struct device *dev, int num_consumers,
@@ -5062,6 +5084,41 @@ void regulator_bulk_free(int num_consumers,
 EXPORT_SYMBOL_GPL(regulator_bulk_free);
 
 /**
+ * regulator_handle_critical - Handle events for system-critical regulators.
+ * @rdev: The regulator device.
+ * @event: The event being handled.
+ *
+ * This function handles critical events such as under-voltage, over-current,
+ * and unknown errors for regulators deemed system-critical. On detecting such
+ * events, it triggers a hardware protection shutdown with a defined timeout.
+ */
+static void regulator_handle_critical(struct regulator_dev *rdev,
+				      unsigned long event)
+{
+	const char *reason = NULL;
+
+	if (!rdev->constraints->system_critical)
+		return;
+
+	switch (event) {
+	case REGULATOR_EVENT_UNDER_VOLTAGE:
+		reason = "System critical regulator: voltage drop detected";
+		break;
+	case REGULATOR_EVENT_OVER_CURRENT:
+		reason = "System critical regulator: over-current detected";
+		break;
+	case REGULATOR_EVENT_FAIL:
+		reason = "System critical regulator: unknown error";
+	}
+
+	if (!reason)
+		return;
+
+	hw_protection_shutdown(reason,
+			       rdev->constraints->uv_less_critical_window_ms);
+}
+
+/**
  * regulator_notifier_call_chain - call regulator event notifier
  * @rdev: regulator source
  * @event: notifier block
@@ -5073,6 +5130,8 @@ EXPORT_SYMBOL_GPL(regulator_bulk_free);
 int regulator_notifier_call_chain(struct regulator_dev *rdev,
 				  unsigned long event, void *data)
 {
+	regulator_handle_critical(rdev, event);
+
 	_notifier_call_chain(rdev, event, data);
 	return NOTIFY_DONE;
 
@@ -6234,6 +6293,14 @@ unlock:
 	return 0;
 }
 
+static bool regulator_ignore_unused;
+static int __init regulator_ignore_unused_setup(char *__unused)
+{
+	regulator_ignore_unused = true;
+	return 1;
+}
+__setup("regulator_ignore_unused", regulator_ignore_unused_setup);
+
 static void regulator_init_complete_work_function(struct work_struct *work)
 {
 	/*
@@ -6246,6 +6313,15 @@ static void regulator_init_complete_work_function(struct work_struct *work)
 	class_for_each_device(&regulator_class, NULL, NULL,
 			      regulator_register_resolve_supply);
 
+	/*
+	 * For debugging purposes, it may be useful to prevent unused
+	 * regulators from being disabled.
+	 */
+	if (regulator_ignore_unused) {
+		pr_warn("regulator: Not disabling unused regulators\n");
+		return;
+	}
+
 	/* If we have a full configuration then disable any regulators
 	 * we have permission to change the status for and which are
 	 * not in use or always_on.  This is effectively the default
diff --git a/drivers/regulator/db8500-prcmu.c b/drivers/regulator/db8500-prcmu.c
index 34c5e485d0af..1e2d54da1b9a 100644
--- a/drivers/regulator/db8500-prcmu.c
+++ b/drivers/regulator/db8500-prcmu.c
@@ -469,11 +469,9 @@ static int db8500_regulator_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int db8500_regulator_remove(struct platform_device *pdev)
+static void db8500_regulator_remove(struct platform_device *pdev)
 {
 	ux500_regulator_debug_exit();
-
-	return 0;
 }
 
 static struct platform_driver db8500_regulator_driver = {
@@ -482,7 +480,7 @@ static struct platform_driver db8500_regulator_driver = {
 		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
 	},
 	.probe = db8500_regulator_probe,
-	.remove = db8500_regulator_remove,
+	.remove_new = db8500_regulator_remove,
 };
 
 static int __init db8500_regulator_init(void)
diff --git a/drivers/regulator/event.c b/drivers/regulator/event.c
new file mode 100644
index 000000000000..ea3bd49544e8
--- /dev/null
+++ b/drivers/regulator/event.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Regulator event over netlink
+ *
+ * Author: Naresh Solanki <Naresh.Solanki@9elements.com>
+ */
+
+#include <regulator/regulator.h>
+#include <net/netlink.h>
+#include <net/genetlink.h>
+#include <linux/atomic.h>
+
+#include "regnl.h"
+
+static atomic_t reg_event_seqnum = ATOMIC_INIT(0);
+
+static const struct genl_multicast_group reg_event_mcgrps[] = {
+	{ .name = REG_GENL_MCAST_GROUP_NAME, },
+};
+
+static struct genl_family reg_event_genl_family __ro_after_init = {
+	.module = THIS_MODULE,
+	.name = REG_GENL_FAMILY_NAME,
+	.version = REG_GENL_VERSION,
+	.maxattr = REG_GENL_ATTR_MAX,
+	.mcgrps = reg_event_mcgrps,
+	.n_mcgrps = ARRAY_SIZE(reg_event_mcgrps),
+};
+
+int reg_generate_netlink_event(const char *reg_name, u64 event)
+{
+	struct sk_buff *skb;
+	struct nlattr *attr;
+	struct reg_genl_event *edata;
+	void *msg_header;
+	int size;
+
+	/* allocate memory */
+	size = nla_total_size(sizeof(struct reg_genl_event)) +
+	    nla_total_size(0);
+
+	skb = genlmsg_new(size, GFP_ATOMIC);
+	if (!skb)
+		return -ENOMEM;
+
+	/* add the genetlink message header */
+	msg_header = genlmsg_put(skb, 0, atomic_inc_return(&reg_event_seqnum),
+				 &reg_event_genl_family, 0, REG_GENL_CMD_EVENT);
+	if (!msg_header) {
+		nlmsg_free(skb);
+		return -ENOMEM;
+	}
+
+	/* fill the data */
+	attr = nla_reserve(skb, REG_GENL_ATTR_EVENT, sizeof(struct reg_genl_event));
+	if (!attr) {
+		nlmsg_free(skb);
+		return -EINVAL;
+	}
+
+	edata = nla_data(attr);
+	memset(edata, 0, sizeof(struct reg_genl_event));
+
+	strscpy(edata->reg_name, reg_name, sizeof(edata->reg_name));
+	edata->event = event;
+
+	/* send multicast genetlink message */
+	genlmsg_end(skb, msg_header);
+	size = genlmsg_multicast(&reg_event_genl_family, skb, 0, 0, GFP_ATOMIC);
+
+	return size;
+}
+
+static int __init reg_event_genetlink_init(void)
+{
+	return genl_register_family(&reg_event_genl_family);
+}
+
+static int __init reg_event_init(void)
+{
+	int error;
+
+	/* create genetlink for acpi event */
+	error = reg_event_genetlink_init();
+	if (error)
+		pr_warn("Failed to create genetlink family for reg event\n");
+
+	return 0;
+}
+
+fs_initcall(reg_event_init);
diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c
index 1b65e5e4e40f..03afc160fc72 100644
--- a/drivers/regulator/of_regulator.c
+++ b/drivers/regulator/of_regulator.c
@@ -131,6 +131,8 @@ static int of_get_regulation_constraints(struct device *dev,
 		constraints->valid_ops_mask |= REGULATOR_CHANGE_STATUS;
 
 	constraints->pull_down = of_property_read_bool(np, "regulator-pull-down");
+	constraints->system_critical = of_property_read_bool(np,
+						"system-critical-regulator");
 
 	if (of_property_read_bool(np, "regulator-allow-bypass"))
 		constraints->valid_ops_mask |= REGULATOR_CHANGE_BYPASS;
@@ -173,6 +175,13 @@ static int of_get_regulation_constraints(struct device *dev,
 	if (!ret)
 		constraints->enable_time = pval;
 
+	ret = of_property_read_u32(np, "regulator-uv-survival-time-ms", &pval);
+	if (!ret)
+		constraints->uv_less_critical_window_ms = pval;
+	else
+		constraints->uv_less_critical_window_ms =
+				REGULATOR_DEF_UV_LESS_CRITICAL_WINDOW_MS;
+
 	constraints->soft_start = of_property_read_bool(np,
 					"regulator-soft-start");
 	ret = of_property_read_u32(np, "regulator-active-discharge", &pval);
diff --git a/drivers/regulator/palmas-regulator.c b/drivers/regulator/palmas-regulator.c
index e0dc033aae0f..60656a815b9e 100644
--- a/drivers/regulator/palmas-regulator.c
+++ b/drivers/regulator/palmas-regulator.c
@@ -1594,7 +1594,7 @@ static const struct of_device_id of_palmas_match_tbl[] = {
 static int palmas_regulators_probe(struct platform_device *pdev)
 {
 	struct palmas *palmas = dev_get_drvdata(pdev->dev.parent);
-	struct palmas_pmic_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	struct palmas_pmic_platform_data *pdata;
 	struct device_node *node = pdev->dev.of_node;
 	struct palmas_pmic_driver_data *driver_data;
 	struct regulator_config config = { };
diff --git a/drivers/regulator/qcom-rpmh-regulator.c b/drivers/regulator/qcom-rpmh-regulator.c
index cf502eec0915..80e304711345 100644
--- a/drivers/regulator/qcom-rpmh-regulator.c
+++ b/drivers/regulator/qcom-rpmh-regulator.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2018-2021, The Linux Foundation. All rights reserved.
+// Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
 
 #define pr_fmt(fmt) "%s: " fmt, __func__
 
@@ -68,10 +69,11 @@ enum rpmh_regulator_type {
  * @regulator_type:		RPMh accelerator type used to manage this
  *				regulator
  * @ops:			Pointer to regulator ops callback structure
- * @voltage_range:		The single range of voltages supported by this
- *				PMIC regulator type
+ * @voltage_ranges:		The possible ranges of voltages supported by this
+ * 				PMIC regulator type
+ * @n_linear_ranges:		Number of entries in voltage_ranges
  * @n_voltages:			The number of unique voltage set points defined
- *				by voltage_range
+ *				by voltage_ranges
  * @hpm_min_load_uA:		Minimum load current in microamps that requires
  *				high power mode (HPM) operation.  This is used
  *				for LDO hardware type regulators only.
@@ -85,7 +87,8 @@ enum rpmh_regulator_type {
 struct rpmh_vreg_hw_data {
 	enum rpmh_regulator_type		regulator_type;
 	const struct regulator_ops		*ops;
-	const struct linear_range	voltage_range;
+	const struct linear_range		*voltage_ranges;
+	int					n_linear_ranges;
 	int					n_voltages;
 	int					hpm_min_load_uA;
 	const int				*pmic_mode_map;
@@ -449,8 +452,8 @@ static int rpmh_regulator_init_vreg(struct rpmh_vreg *vreg, struct device *dev,
 	vreg->mode = REGULATOR_MODE_INVALID;
 
 	if (rpmh_data->hw_data->n_voltages) {
-		vreg->rdesc.linear_ranges = &rpmh_data->hw_data->voltage_range;
-		vreg->rdesc.n_linear_ranges = 1;
+		vreg->rdesc.linear_ranges = rpmh_data->hw_data->voltage_ranges;
+		vreg->rdesc.n_linear_ranges = rpmh_data->hw_data->n_linear_ranges;
 		vreg->rdesc.n_voltages = rpmh_data->hw_data->n_voltages;
 	}
 
@@ -508,6 +511,14 @@ static const int pmic_mode_map_pmic5_ldo[REGULATOR_MODE_STANDBY + 1] = {
 	[REGULATOR_MODE_FAST]    = -EINVAL,
 };
 
+static const int pmic_mode_map_pmic5_ldo_hpm[REGULATOR_MODE_STANDBY + 1] = {
+	[REGULATOR_MODE_INVALID] = -EINVAL,
+	[REGULATOR_MODE_STANDBY] = -EINVAL,
+	[REGULATOR_MODE_IDLE]    = -EINVAL,
+	[REGULATOR_MODE_NORMAL]  = PMIC5_LDO_MODE_HPM,
+	[REGULATOR_MODE_FAST]    = -EINVAL,
+};
+
 static unsigned int rpmh_regulator_pmic4_ldo_of_map_mode(unsigned int rpmh_mode)
 {
 	unsigned int mode;
@@ -613,7 +624,10 @@ static unsigned int rpmh_regulator_pmic4_bob_of_map_mode(unsigned int rpmh_mode)
 static const struct rpmh_vreg_hw_data pmic4_pldo = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_drms_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(1664000, 0, 255, 8000),
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(1664000, 0, 255, 8000),
+	},
+	.n_linear_ranges = 1,
 	.n_voltages = 256,
 	.hpm_min_load_uA = 10000,
 	.pmic_mode_map = pmic_mode_map_pmic4_ldo,
@@ -623,7 +637,10 @@ static const struct rpmh_vreg_hw_data pmic4_pldo = {
 static const struct rpmh_vreg_hw_data pmic4_pldo_lv = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_drms_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(1256000, 0, 127, 8000),
+	.voltage_ranges = (struct linear_range[]) {
+	       REGULATOR_LINEAR_RANGE(1256000, 0, 127, 8000),
+	},
+	.n_linear_ranges = 1,
 	.n_voltages = 128,
 	.hpm_min_load_uA = 10000,
 	.pmic_mode_map = pmic_mode_map_pmic4_ldo,
@@ -633,7 +650,10 @@ static const struct rpmh_vreg_hw_data pmic4_pldo_lv = {
 static const struct rpmh_vreg_hw_data pmic4_nldo = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_drms_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(312000, 0, 127, 8000),
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(312000, 0, 127, 8000),
+	},
+	.n_linear_ranges = 1,
 	.n_voltages = 128,
 	.hpm_min_load_uA = 30000,
 	.pmic_mode_map = pmic_mode_map_pmic4_ldo,
@@ -643,7 +663,10 @@ static const struct rpmh_vreg_hw_data pmic4_nldo = {
 static const struct rpmh_vreg_hw_data pmic4_hfsmps3 = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(320000, 0, 215, 8000),
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(320000, 0, 215, 8000),
+	},
+	.n_linear_ranges = 1,
 	.n_voltages = 216,
 	.pmic_mode_map = pmic_mode_map_pmic4_smps,
 	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
@@ -652,7 +675,10 @@ static const struct rpmh_vreg_hw_data pmic4_hfsmps3 = {
 static const struct rpmh_vreg_hw_data pmic4_ftsmps426 = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(320000, 0, 258, 4000),
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(320000, 0, 258, 4000),
+	},
+	.n_linear_ranges = 1,
 	.n_voltages = 259,
 	.pmic_mode_map = pmic_mode_map_pmic4_smps,
 	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
@@ -661,7 +687,10 @@ static const struct rpmh_vreg_hw_data pmic4_ftsmps426 = {
 static const struct rpmh_vreg_hw_data pmic4_bob = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_bypass_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(1824000, 0, 83, 32000),
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(1824000, 0, 83, 32000),
+	},
+	.n_linear_ranges = 1,
 	.n_voltages = 84,
 	.pmic_mode_map = pmic_mode_map_pmic4_bob,
 	.of_map_mode = rpmh_regulator_pmic4_bob_of_map_mode,
@@ -676,7 +705,10 @@ static const struct rpmh_vreg_hw_data pmic4_lvs = {
 static const struct rpmh_vreg_hw_data pmic5_pldo = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_drms_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(1504000, 0, 255, 8000),
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(1504000, 0, 255, 8000),
+	},
+	.n_linear_ranges = 1,
 	.n_voltages = 256,
 	.hpm_min_load_uA = 10000,
 	.pmic_mode_map = pmic_mode_map_pmic5_ldo,
@@ -686,7 +718,10 @@ static const struct rpmh_vreg_hw_data pmic5_pldo = {
 static const struct rpmh_vreg_hw_data pmic5_pldo_lv = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_drms_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(1504000, 0, 62, 8000),
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(1504000, 0, 62, 8000),
+	},
+	.n_linear_ranges = 1,
 	.n_voltages = 63,
 	.hpm_min_load_uA = 10000,
 	.pmic_mode_map = pmic_mode_map_pmic5_ldo,
@@ -696,17 +731,50 @@ static const struct rpmh_vreg_hw_data pmic5_pldo_lv = {
 static const struct rpmh_vreg_hw_data pmic5_pldo515_mv = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_drms_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(1800000, 0, 187, 8000),
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(1800000, 0, 187, 8000),
+	},
+	.n_linear_ranges = 1,
 	.n_voltages = 188,
 	.hpm_min_load_uA = 10000,
 	.pmic_mode_map = pmic_mode_map_pmic5_ldo,
 	.of_map_mode = rpmh_regulator_pmic4_ldo_of_map_mode,
 };
 
+static const struct rpmh_vreg_hw_data pmic5_pldo502 = {
+	.regulator_type = VRM,
+	.ops = &rpmh_regulator_vrm_ops,
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(1504000, 0, 255, 8000),
+	},
+	.n_linear_ranges = 1,
+	.n_voltages = 256,
+	.pmic_mode_map = pmic_mode_map_pmic5_ldo_hpm,
+	.of_map_mode = rpmh_regulator_pmic4_ldo_of_map_mode,
+};
+
+static const struct rpmh_vreg_hw_data pmic5_pldo502ln = {
+	.regulator_type = VRM,
+	.ops = &rpmh_regulator_vrm_ops,
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(1800000, 0,  2,  200000),
+		REGULATOR_LINEAR_RANGE(2608000, 3,  28, 16000),
+		REGULATOR_LINEAR_RANGE(3104000, 29, 30, 96000),
+		REGULATOR_LINEAR_RANGE(3312000, 31, 31, 0),
+	},
+	.n_linear_ranges = 4,
+	.n_voltages = 32,
+	.pmic_mode_map = pmic_mode_map_pmic5_ldo_hpm,
+	.of_map_mode = rpmh_regulator_pmic4_ldo_of_map_mode,
+};
+
 static const struct rpmh_vreg_hw_data pmic5_nldo = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_drms_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(320000, 0, 123, 8000),
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(320000, 0, 123, 8000),
+	},
+	.n_linear_ranges = 1,
 	.n_voltages = 124,
 	.hpm_min_load_uA = 30000,
 	.pmic_mode_map = pmic_mode_map_pmic5_ldo,
@@ -716,17 +784,36 @@ static const struct rpmh_vreg_hw_data pmic5_nldo = {
 static const struct rpmh_vreg_hw_data pmic5_nldo515 = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_drms_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(320000, 0, 210, 8000),
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(320000, 0, 210, 8000),
+	},
+	.n_linear_ranges = 1,
 	.n_voltages = 211,
 	.hpm_min_load_uA = 30000,
 	.pmic_mode_map = pmic_mode_map_pmic5_ldo,
 	.of_map_mode = rpmh_regulator_pmic4_ldo_of_map_mode,
 };
 
+static const struct rpmh_vreg_hw_data pmic5_nldo502 = {
+	.regulator_type = VRM,
+	.ops = &rpmh_regulator_vrm_drms_ops,
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(528000, 0, 127, 8000),
+	},
+	.n_linear_ranges = 1,
+	.n_voltages = 128,
+	.hpm_min_load_uA = 30000,
+	.pmic_mode_map = pmic_mode_map_pmic5_ldo,
+	.of_map_mode = rpmh_regulator_pmic4_ldo_of_map_mode,
+};
+
 static const struct rpmh_vreg_hw_data pmic5_hfsmps510 = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(320000, 0, 215, 8000),
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(320000, 0, 215, 8000),
+	},
+	.n_linear_ranges = 1,
 	.n_voltages = 216,
 	.pmic_mode_map = pmic_mode_map_pmic5_smps,
 	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
@@ -735,7 +822,10 @@ static const struct rpmh_vreg_hw_data pmic5_hfsmps510 = {
 static const struct rpmh_vreg_hw_data pmic5_ftsmps510 = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(300000, 0, 263, 4000),
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(300000, 0, 263, 4000),
+	},
+	.n_linear_ranges = 1,
 	.n_voltages = 264,
 	.pmic_mode_map = pmic_mode_map_pmic5_smps,
 	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
@@ -744,7 +834,10 @@ static const struct rpmh_vreg_hw_data pmic5_ftsmps510 = {
 static const struct rpmh_vreg_hw_data pmic5_ftsmps520 = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(300000, 0, 263, 4000),
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(300000, 0, 263, 4000),
+	},
+	.n_linear_ranges = 1,
 	.n_voltages = 264,
 	.pmic_mode_map = pmic_mode_map_pmic5_smps,
 	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
@@ -753,7 +846,10 @@ static const struct rpmh_vreg_hw_data pmic5_ftsmps520 = {
 static const struct rpmh_vreg_hw_data pmic5_ftsmps525_lv = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(300000, 0, 267, 4000),
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(300000, 0, 267, 4000),
+	},
+	.n_linear_ranges = 1,
 	.n_voltages = 268,
 	.pmic_mode_map = pmic_mode_map_pmic5_smps,
 	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
@@ -762,7 +858,10 @@ static const struct rpmh_vreg_hw_data pmic5_ftsmps525_lv = {
 static const struct rpmh_vreg_hw_data pmic5_ftsmps525_mv = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(600000, 0, 267, 8000),
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(600000, 0, 267, 8000),
+	},
+	.n_linear_ranges = 1,
 	.n_voltages = 268,
 	.pmic_mode_map = pmic_mode_map_pmic5_smps,
 	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
@@ -771,7 +870,10 @@ static const struct rpmh_vreg_hw_data pmic5_ftsmps525_mv = {
 static const struct rpmh_vreg_hw_data pmic5_ftsmps527 = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(320000, 0, 215, 8000),
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(320000, 0, 215, 8000),
+	},
+	.n_linear_ranges = 1,
 	.n_voltages = 215,
 	.pmic_mode_map = pmic_mode_map_pmic5_smps,
 	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
@@ -780,7 +882,10 @@ static const struct rpmh_vreg_hw_data pmic5_ftsmps527 = {
 static const struct rpmh_vreg_hw_data pmic5_hfsmps515 = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(320000, 0, 235, 16000),
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(320000, 0, 235, 16000),
+	},
+	.n_linear_ranges = 1,
 	.n_voltages = 236,
 	.pmic_mode_map = pmic_mode_map_pmic5_smps,
 	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
@@ -789,7 +894,10 @@ static const struct rpmh_vreg_hw_data pmic5_hfsmps515 = {
 static const struct rpmh_vreg_hw_data pmic5_hfsmps515_1 = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(900000, 0, 4, 16000),
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(900000, 0, 4, 16000),
+	},
+	.n_linear_ranges = 1,
 	.n_voltages = 5,
 	.pmic_mode_map = pmic_mode_map_pmic5_smps,
 	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
@@ -798,7 +906,10 @@ static const struct rpmh_vreg_hw_data pmic5_hfsmps515_1 = {
 static const struct rpmh_vreg_hw_data pmic5_bob = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_bypass_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(3000000, 0, 31, 32000),
+	.voltage_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(3000000, 0, 31, 32000),
+	},
+	.n_linear_ranges = 1,
 	.n_voltages = 32,
 	.pmic_mode_map = pmic_mode_map_pmic5_bob,
 	.of_map_mode = rpmh_regulator_pmic4_bob_of_map_mode,
@@ -1147,6 +1258,16 @@ static const struct rpmh_vreg_init_data pm8009_1_vreg_data[] = {
 	{}
 };
 
+static const struct rpmh_vreg_init_data pm8010_vreg_data[] = {
+	RPMH_VREG("ldo1",   "ldo%s1",  &pmic5_nldo502,   "vdd-l1-l2"),
+	RPMH_VREG("ldo2",   "ldo%s2",  &pmic5_nldo502,   "vdd-l1-l2"),
+	RPMH_VREG("ldo3",   "ldo%s3",  &pmic5_pldo502ln, "vdd-l3-l4"),
+	RPMH_VREG("ldo4",   "ldo%s4",  &pmic5_pldo502ln, "vdd-l3-l4"),
+	RPMH_VREG("ldo5",   "ldo%s5",  &pmic5_pldo502,   "vdd-l5"),
+	RPMH_VREG("ldo6",   "ldo%s6",  &pmic5_pldo502ln, "vdd-l6"),
+	RPMH_VREG("ldo7",   "ldo%s7",  &pmic5_pldo502,   "vdd-l7"),
+};
+
 static const struct rpmh_vreg_init_data pm6150_vreg_data[] = {
 	RPMH_VREG("smps1",  "smp%s1",  &pmic5_ftsmps510, "vdd-s1"),
 	RPMH_VREG("smps2",  "smp%s2",  &pmic5_ftsmps510, "vdd-s2"),
@@ -1463,6 +1584,10 @@ static const struct of_device_id __maybe_unused rpmh_regulator_match_table[] = {
 		.data = pm8009_1_vreg_data,
 	},
 	{
+		.compatible = "qcom,pm8010-rpmh-regulators",
+		.data = pm8010_vreg_data,
+	},
+	{
 		.compatible = "qcom,pm8150-rpmh-regulators",
 		.data = pm8150_vreg_data,
 	},
diff --git a/drivers/regulator/qcom_smd-regulator.c b/drivers/regulator/qcom_smd-regulator.c
index f53ada076252..d1be9568025e 100644
--- a/drivers/regulator/qcom_smd-regulator.c
+++ b/drivers/regulator/qcom_smd-regulator.c
@@ -796,6 +796,7 @@ static const struct rpm_regulator_data rpm_mp5496_regulators[] = {
 	{ "s1", QCOM_SMD_RPM_SMPA, 1, &mp5496_smps, "s1" },
 	{ "s2", QCOM_SMD_RPM_SMPA, 2, &mp5496_smps, "s2" },
 	{ "l2", QCOM_SMD_RPM_LDOA, 2, &mp5496_ldoa2, "l2" },
+	{ "l5", QCOM_SMD_RPM_LDOA, 5, &mp5496_ldoa2, "l5" },
 	{}
 };
 
@@ -1012,6 +1013,39 @@ static const struct rpm_regulator_data rpm_pm8916_regulators[] = {
 	{}
 };
 
+static const struct rpm_regulator_data rpm_pm8937_regulators[] = {
+	{ "s1", QCOM_SMD_RPM_SMPA, 1, &pm8994_hfsmps, "vdd_s1" },
+	{ "s2", QCOM_SMD_RPM_SMPA, 2, &pm8994_hfsmps, "vdd_s2" },
+	{ "s3", QCOM_SMD_RPM_SMPA, 3, &pm8994_hfsmps, "vdd_s3" },
+	{ "s4", QCOM_SMD_RPM_SMPA, 4, &pm8994_hfsmps, "vdd_s4" },
+	/* S5 - S6 are managed by SPMI */
+
+	{ "l1", QCOM_SMD_RPM_LDOA, 1, &pm8953_ult_nldo, "vdd_l1_l19" },
+	{ "l2", QCOM_SMD_RPM_LDOA, 2, &pm8953_ult_nldo, "vdd_l2_l23" },
+	{ "l3", QCOM_SMD_RPM_LDOA, 3, &pm8953_ult_nldo, "vdd_l3" },
+	{ "l4", QCOM_SMD_RPM_LDOA, 4, &pm8950_ult_pldo, "vdd_l4_l5_l6_l7_l16" },
+	{ "l5", QCOM_SMD_RPM_LDOA, 5, &pm8950_ult_pldo, "vdd_l4_l5_l6_l7_l16" },
+	{ "l6", QCOM_SMD_RPM_LDOA, 6, &pm8950_ult_pldo, "vdd_l4_l5_l6_l7_l16" },
+	{ "l7", QCOM_SMD_RPM_LDOA, 7, &pm8950_ult_pldo, "vdd_l4_l5_l6_l7_l16" },
+	{ "l8", QCOM_SMD_RPM_LDOA, 8, &pm8950_ult_pldo, "vdd_l8_l11_l12_l17_l22" },
+	{ "l9", QCOM_SMD_RPM_LDOA, 9, &pm8950_ult_pldo, "vdd_l9_l10_l13_l14_l15_l18" },
+	{ "l10", QCOM_SMD_RPM_LDOA, 10, &pm8950_ult_pldo, "vdd_l9_l10_l13_l14_l15_l18"},
+	{ "l11", QCOM_SMD_RPM_LDOA, 11, &pm8950_ult_pldo, "vdd_l8_l11_l12_l17_l22" },
+	{ "l12", QCOM_SMD_RPM_LDOA, 12, &pm8950_ult_pldo, "vdd_l8_l11_l12_l17_l22" },
+	{ "l13", QCOM_SMD_RPM_LDOA, 13, &pm8950_ult_pldo, "vdd_l9_l10_l13_l14_l15_l18" },
+	{ "l14", QCOM_SMD_RPM_LDOA, 14, &pm8950_ult_pldo, "vdd_l9_l10_l13_l14_l15_l18" },
+	{ "l15", QCOM_SMD_RPM_LDOA, 15, &pm8950_ult_pldo, "vdd_l9_l10_l13_l14_l15_l18" },
+	{ "l16", QCOM_SMD_RPM_LDOA, 16, &pm8950_ult_pldo, "vdd_l4_l5_l6_l7_l16" },
+	{ "l17", QCOM_SMD_RPM_LDOA, 17, &pm8950_ult_pldo, "vdd_l8_l11_l12_l17_l22" },
+	{ "l18", QCOM_SMD_RPM_LDOA, 18, &pm8950_ult_pldo, "vdd_l9_l10_l13_l14_l15_l18" },
+	{ "l19", QCOM_SMD_RPM_LDOA, 19, &pm8953_ult_nldo, "vdd_l1_l19" },
+	{ "l20", QCOM_SMD_RPM_LDOA, 20, &pm8953_lnldo, "vdd_l20_l21" },
+	{ "l21", QCOM_SMD_RPM_LDOA, 21, &pm8953_lnldo, "vdd_l20_l21" },
+	{ "l22", QCOM_SMD_RPM_LDOA, 22, &pm8950_ult_pldo, "vdd_l8_l11_l12_l17_l22" },
+	{ "l23", QCOM_SMD_RPM_LDOA, 23, &pm8994_nldo, "vdd_l2_l23" },
+	{}
+};
+
 static const struct rpm_regulator_data rpm_pm8941_regulators[] = {
 	{ "s1", QCOM_SMD_RPM_SMPA, 1, &pm8x41_hfsmps, "vdd_s1" },
 	{ "s2", QCOM_SMD_RPM_SMPA, 2, &pm8x41_hfsmps, "vdd_s2" },
@@ -1329,6 +1363,7 @@ static const struct of_device_id rpm_of_match[] = {
 	{ .compatible = "qcom,rpm-pm8841-regulators", .data = &rpm_pm8841_regulators },
 	{ .compatible = "qcom,rpm-pm8909-regulators", .data = &rpm_pm8909_regulators },
 	{ .compatible = "qcom,rpm-pm8916-regulators", .data = &rpm_pm8916_regulators },
+	{ .compatible = "qcom,rpm-pm8937-regulators", .data = &rpm_pm8937_regulators },
 	{ .compatible = "qcom,rpm-pm8941-regulators", .data = &rpm_pm8941_regulators },
 	{ .compatible = "qcom,rpm-pm8950-regulators", .data = &rpm_pm8950_regulators },
 	{ .compatible = "qcom,rpm-pm8953-regulators", .data = &rpm_pm8953_regulators },
diff --git a/drivers/regulator/qcom_spmi-regulator.c b/drivers/regulator/qcom_spmi-regulator.c
index 94f9092b29ef..9a9fa20dcd95 100644
--- a/drivers/regulator/qcom_spmi-regulator.c
+++ b/drivers/regulator/qcom_spmi-regulator.c
@@ -2239,6 +2239,39 @@ static const struct spmi_regulator_data pm8916_regulators[] = {
 	{ }
 };
 
+static const struct spmi_regulator_data pm8937_regulators[] = {
+	{ "s1", 0x1400, "vdd_s1", },
+	{ "s2", 0x1700, "vdd_s2", },
+	{ "s3", 0x1a00, "vdd_s3", },
+	{ "s4", 0x1d00, "vdd_s4", },
+	{ "s5", 0x2000, "vdd_s5", },
+	{ "s6", 0x2300, "vdd_s6", },
+	{ "l1", 0x4000, "vdd_l1_l19", },
+	{ "l2", 0x4100, "vdd_l2_l23", },
+	{ "l3", 0x4200, "vdd_l3", },
+	{ "l4", 0x4300, "vdd_l4_l5_l6_l7_l16", },
+	{ "l5", 0x4400, "vdd_l4_l5_l6_l7_l16", },
+	{ "l6", 0x4500, "vdd_l4_l5_l6_l7_l16", },
+	{ "l7", 0x4600, "vdd_l4_l5_l6_l7_l16", },
+	{ "l8", 0x4700, "vdd_l8_l11_l12_l17_l22", },
+	{ "l9", 0x4800, "vdd_l9_l10_l13_l14_l15_l18", },
+	{ "l10", 0x4900, "vdd_l9_l10_l13_l14_l15_l18", },
+	{ "l11", 0x4a00, "vdd_l8_l11_l12_l17_l22", },
+	{ "l12", 0x4b00, "vdd_l8_l11_l12_l17_l22", },
+	{ "l13", 0x4c00, "vdd_l9_l10_l13_l14_l15_l18", },
+	{ "l14", 0x4d00, "vdd_l9_l10_l13_l14_l15_l18", },
+	{ "l15", 0x4e00, "vdd_l9_l10_l13_l14_l15_l18", },
+	{ "l16", 0x4f00, "vdd_l4_l5_l6_l7_l16", },
+	{ "l17", 0x5000, "vdd_l8_l11_l12_l17_l22", },
+	{ "l18", 0x5100, "vdd_l9_l10_l13_l14_l15_l18", },
+	{ "l19", 0x5200, "vdd_l1_l19", },
+	{ "l20", 0x5300, "vdd_l20_l21", },
+	{ "l21", 0x5400, "vdd_l21_l21", },
+	{ "l22", 0x5500, "vdd_l8_l11_l12_l17_l22", },
+	{ "l23", 0x5600, "vdd_l2_l23", },
+	{ }
+};
+
 static const struct spmi_regulator_data pm8941_regulators[] = {
 	{ "s1", 0x1400, "vdd_s1", },
 	{ "s2", 0x1700, "vdd_s2", },
@@ -2453,6 +2486,7 @@ static const struct of_device_id qcom_spmi_regulator_match[] = {
 	{ .compatible = "qcom,pm8841-regulators", .data = &pm8841_regulators },
 	{ .compatible = "qcom,pm8909-regulators", .data = &pm8909_regulators },
 	{ .compatible = "qcom,pm8916-regulators", .data = &pm8916_regulators },
+	{ .compatible = "qcom,pm8937-regulators", .data = &pm8937_regulators },
 	{ .compatible = "qcom,pm8941-regulators", .data = &pm8941_regulators },
 	{ .compatible = "qcom,pm8950-regulators", .data = &pm8950_regulators },
 	{ .compatible = "qcom,pm8994-regulators", .data = &pm8994_regulators },
diff --git a/drivers/regulator/regnl.h b/drivers/regulator/regnl.h
new file mode 100644
index 000000000000..bcba16cc05cc
--- /dev/null
+++ b/drivers/regulator/regnl.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Regulator event over netlink
+ *
+ * Author: Naresh Solanki <Naresh.Solanki@9elements.com>
+ */
+
+#ifndef __REGULATOR_EVENT_H
+#define __REGULATOR_EVENT_H
+
+int reg_generate_netlink_event(const char *reg_name, u64 event);
+
+#endif
diff --git a/drivers/regulator/stm32-vrefbuf.c b/drivers/regulator/stm32-vrefbuf.c
index 717144cbe0f9..40855105dd33 100644
--- a/drivers/regulator/stm32-vrefbuf.c
+++ b/drivers/regulator/stm32-vrefbuf.c
@@ -233,7 +233,7 @@ err_pm_stop:
 	return ret;
 }
 
-static int stm32_vrefbuf_remove(struct platform_device *pdev)
+static void stm32_vrefbuf_remove(struct platform_device *pdev)
 {
 	struct regulator_dev *rdev = platform_get_drvdata(pdev);
 	struct stm32_vrefbuf *priv = rdev_get_drvdata(rdev);
@@ -244,8 +244,6 @@ static int stm32_vrefbuf_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_set_suspended(&pdev->dev);
 	pm_runtime_put_noidle(&pdev->dev);
-
-	return 0;
 };
 
 static int __maybe_unused stm32_vrefbuf_runtime_suspend(struct device *dev)
@@ -282,7 +280,7 @@ MODULE_DEVICE_TABLE(of, stm32_vrefbuf_of_match);
 
 static struct platform_driver stm32_vrefbuf_driver = {
 	.probe = stm32_vrefbuf_probe,
-	.remove = stm32_vrefbuf_remove,
+	.remove_new = stm32_vrefbuf_remove,
 	.driver = {
 		.name  = "stm32-vrefbuf",
 		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
diff --git a/drivers/regulator/stpmic1_regulator.c b/drivers/regulator/stpmic1_regulator.c
index 79d1a3eb18d4..a498df7cb016 100644
--- a/drivers/regulator/stpmic1_regulator.c
+++ b/drivers/regulator/stpmic1_regulator.c
@@ -15,7 +15,7 @@
 #include <dt-bindings/mfd/st,stpmic1.h>
 
 /**
- * struct stpmic1 regulator description: this structure is used as driver data
+ * struct stpmic1_regulator_cfg - this structure is used as driver data
  * @desc: regulator framework description
  * @mask_reset_reg: mask reset register address
  * @mask_reset_mask: mask rank and mask reset register mask
diff --git a/drivers/regulator/uniphier-regulator.c b/drivers/regulator/uniphier-regulator.c
index 1d8304b88bd6..5f868042392f 100644
--- a/drivers/regulator/uniphier-regulator.c
+++ b/drivers/regulator/uniphier-regulator.c
@@ -115,7 +115,7 @@ out_rst_assert:
 	return ret;
 }
 
-static int uniphier_regulator_remove(struct platform_device *pdev)
+static void uniphier_regulator_remove(struct platform_device *pdev)
 {
 	struct uniphier_regulator_priv *priv = platform_get_drvdata(pdev);
 	int i;
@@ -124,8 +124,6 @@ static int uniphier_regulator_remove(struct platform_device *pdev)
 		reset_control_assert(priv->rst[i]);
 
 	clk_bulk_disable_unprepare(priv->data->nclks, priv->clk);
-
-	return 0;
 }
 
 /* USB3 controller data */
@@ -209,7 +207,7 @@ MODULE_DEVICE_TABLE(of, uniphier_regulator_match);
 
 static struct platform_driver uniphier_regulator_driver = {
 	.probe = uniphier_regulator_probe,
-	.remove = uniphier_regulator_remove,
+	.remove_new = uniphier_regulator_remove,
 	.driver = {
 		.name  = "uniphier-regulator",
 		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
diff --git a/drivers/regulator/userspace-consumer.c b/drivers/regulator/userspace-consumer.c
index 97f075ed68c9..53d1b9d6f69c 100644
--- a/drivers/regulator/userspace-consumer.c
+++ b/drivers/regulator/userspace-consumer.c
@@ -194,7 +194,7 @@ err_enable:
 	return ret;
 }
 
-static int regulator_userspace_consumer_remove(struct platform_device *pdev)
+static void regulator_userspace_consumer_remove(struct platform_device *pdev)
 {
 	struct userspace_consumer_data *data = platform_get_drvdata(pdev);
 
@@ -202,8 +202,6 @@ static int regulator_userspace_consumer_remove(struct platform_device *pdev)
 
 	if (data->enabled && !data->no_autoswitch)
 		regulator_bulk_disable(data->num_supplies, data->supplies);
-
-	return 0;
 }
 
 static const struct of_device_id regulator_userspace_consumer_of_match[] = {
@@ -213,7 +211,7 @@ static const struct of_device_id regulator_userspace_consumer_of_match[] = {
 
 static struct platform_driver regulator_userspace_consumer_driver = {
 	.probe		= regulator_userspace_consumer_probe,
-	.remove		= regulator_userspace_consumer_remove,
+	.remove_new	= regulator_userspace_consumer_remove,
 	.driver		= {
 		.name		= "reg-userspace-consumer",
 		.probe_type	= PROBE_PREFER_ASYNCHRONOUS,
diff --git a/drivers/regulator/virtual.c b/drivers/regulator/virtual.c
index d5a160efdae6..0a0ee186c6af 100644
--- a/drivers/regulator/virtual.c
+++ b/drivers/regulator/virtual.c
@@ -345,7 +345,7 @@ static int regulator_virtual_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int regulator_virtual_remove(struct platform_device *pdev)
+static void regulator_virtual_remove(struct platform_device *pdev)
 {
 	struct virtual_consumer_data *drvdata = platform_get_drvdata(pdev);
 
@@ -353,13 +353,11 @@ static int regulator_virtual_remove(struct platform_device *pdev)
 
 	if (drvdata->enabled)
 		regulator_disable(drvdata->regulator);
-
-	return 0;
 }
 
 static struct platform_driver regulator_virtual_consumer_driver = {
 	.probe		= regulator_virtual_probe,
-	.remove		= regulator_virtual_remove,
+	.remove_new	= regulator_virtual_remove,
 	.driver		= {
 		.name		= "reg-virt-consumer",
 		.probe_type	= PROBE_PREFER_ASYNCHRONOUS,
diff --git a/drivers/regulator/wm8350-regulator.c b/drivers/regulator/wm8350-regulator.c
index 1445bafcab40..9939a5d2cbec 100644
--- a/drivers/regulator/wm8350-regulator.c
+++ b/drivers/regulator/wm8350-regulator.c
@@ -1158,14 +1158,12 @@ static int wm8350_regulator_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int wm8350_regulator_remove(struct platform_device *pdev)
+static void wm8350_regulator_remove(struct platform_device *pdev)
 {
 	struct regulator_dev *rdev = platform_get_drvdata(pdev);
 	struct wm8350 *wm8350 = rdev_get_drvdata(rdev);
 
 	wm8350_free_irq(wm8350, wm8350_reg[pdev->id].irq, rdev);
-
-	return 0;
 }
 
 int wm8350_register_regulator(struct wm8350 *wm8350, int reg,
@@ -1306,7 +1304,7 @@ EXPORT_SYMBOL_GPL(wm8350_register_led);
 
 static struct platform_driver wm8350_regulator_driver = {
 	.probe = wm8350_regulator_probe,
-	.remove = wm8350_regulator_remove,
+	.remove_new = wm8350_regulator_remove,
 	.driver		= {
 		.name	= "wm8350-regulator",
 		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
diff --git a/drivers/reset/core.c b/drivers/reset/core.c
index 7ece6a8e9858..4d5a78d3c085 100644
--- a/drivers/reset/core.c
+++ b/drivers/reset/core.c
@@ -807,6 +807,9 @@ static void __reset_control_put_internal(struct reset_control *rstc)
 {
 	lockdep_assert_held(&reset_list_mutex);
 
+	if (IS_ERR_OR_NULL(rstc))
+		return;
+
 	kref_put(&rstc->refcnt, __reset_control_release);
 }
 
@@ -1017,11 +1020,8 @@ EXPORT_SYMBOL_GPL(reset_control_put);
 void reset_control_bulk_put(int num_rstcs, struct reset_control_bulk_data *rstcs)
 {
 	mutex_lock(&reset_list_mutex);
-	while (num_rstcs--) {
-		if (IS_ERR_OR_NULL(rstcs[num_rstcs].rstc))
-			continue;
+	while (num_rstcs--)
 		__reset_control_put_internal(rstcs[num_rstcs].rstc);
-	}
 	mutex_unlock(&reset_list_mutex);
 }
 EXPORT_SYMBOL_GPL(reset_control_bulk_put);
diff --git a/drivers/reset/hisilicon/hi6220_reset.c b/drivers/reset/hisilicon/hi6220_reset.c
index 8d1fce18ded7..5c3267acd2b1 100644
--- a/drivers/reset/hisilicon/hi6220_reset.c
+++ b/drivers/reset/hisilicon/hi6220_reset.c
@@ -163,7 +163,7 @@ static int hi6220_reset_probe(struct platform_device *pdev)
 	if (!data)
 		return -ENOMEM;
 
-	type = (enum hi6220_reset_ctrl_type)of_device_get_match_data(dev);
+	type = (uintptr_t)of_device_get_match_data(dev);
 
 	regmap = syscon_node_to_regmap(np);
 	if (IS_ERR(regmap)) {
diff --git a/drivers/reset/reset-brcmstb.c b/drivers/reset/reset-brcmstb.c
index 42c9d5241c53..810fe76452d6 100644
--- a/drivers/reset/reset-brcmstb.c
+++ b/drivers/reset/reset-brcmstb.c
@@ -90,8 +90,7 @@ static int brcmstb_reset_probe(struct platform_device *pdev)
 	if (!priv)
 		return -ENOMEM;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	priv->base = devm_ioremap_resource(kdev, res);
+	priv->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(priv->base))
 		return PTR_ERR(priv->base);
 
diff --git a/drivers/reset/reset-meson-audio-arb.c b/drivers/reset/reset-meson-audio-arb.c
index 7e46dbc04998..7891d52fa899 100644
--- a/drivers/reset/reset-meson-audio-arb.c
+++ b/drivers/reset/reset-meson-audio-arb.c
@@ -139,7 +139,6 @@ static int meson_audio_arb_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	const struct meson_audio_arb_match_data *data;
 	struct meson_audio_arb_data *arb;
-	struct resource *res;
 	int ret;
 
 	data = of_device_get_match_data(dev);
@@ -155,8 +154,7 @@ static int meson_audio_arb_probe(struct platform_device *pdev)
 	if (IS_ERR(arb->clk))
 		return dev_err_probe(dev, PTR_ERR(arb->clk), "failed to get clock\n");
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	arb->regs = devm_ioremap_resource(dev, res);
+	arb->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(arb->regs))
 		return PTR_ERR(arb->regs);
 
diff --git a/drivers/reset/reset-meson.c b/drivers/reset/reset-meson.c
index a7af051b17fb..f78be97898bc 100644
--- a/drivers/reset/reset-meson.c
+++ b/drivers/reset/reset-meson.c
@@ -108,6 +108,7 @@ static const struct of_device_id meson_reset_dt_ids[] = {
 	 { .compatible = "amlogic,meson-axg-reset",  .data = &meson8b_param},
 	 { .compatible = "amlogic,meson-a1-reset",   .data = &meson_a1_param},
 	 { .compatible = "amlogic,meson-s4-reset",   .data = &meson_s4_param},
+	 { .compatible = "amlogic,c3-reset",   .data = &meson_s4_param},
 	 { /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, meson_reset_dt_ids);
diff --git a/drivers/reset/reset-npcm.c b/drivers/reset/reset-npcm.c
index f6c4f854f2be..8935ef95a2d1 100644
--- a/drivers/reset/reset-npcm.c
+++ b/drivers/reset/reset-npcm.c
@@ -6,8 +6,8 @@
 #include <linux/io.h>
 #include <linux/init.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/reboot.h>
 #include <linux/reset-controller.h>
 #include <linux/spinlock.h>
@@ -351,8 +351,7 @@ static int npcm_usb_reset(struct platform_device *pdev, struct npcm_rc_data *rc)
 		}
 	}
 
-	rc->info = (const struct npcm_reset_info *)
-			of_match_device(dev->driver->of_match_table, dev)->data;
+	rc->info = device_get_match_data(dev);
 	switch (rc->info->bmc_id) {
 	case BMC_NPCM7XX:
 		npcm_usb_reset_npcm7xx(rc);
diff --git a/drivers/reset/reset-qcom-aoss.c b/drivers/reset/reset-qcom-aoss.c
index f52e90e36194..93c84d70ef64 100644
--- a/drivers/reset/reset-qcom-aoss.c
+++ b/drivers/reset/reset-qcom-aoss.c
@@ -90,7 +90,6 @@ static int qcom_aoss_reset_probe(struct platform_device *pdev)
 	struct qcom_aoss_reset_data *data;
 	struct device *dev = &pdev->dev;
 	const struct qcom_aoss_desc *desc;
-	struct resource *res;
 
 	desc = of_device_get_match_data(dev);
 	if (!desc)
@@ -101,8 +100,7 @@ static int qcom_aoss_reset_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	data->desc = desc;
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	data->base = devm_ioremap_resource(dev, res);
+	data->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(data->base))
 		return PTR_ERR(data->base);
 
diff --git a/drivers/reset/reset-qcom-pdc.c b/drivers/reset/reset-qcom-pdc.c
index a3aae3f902e6..dce1fc1a68ad 100644
--- a/drivers/reset/reset-qcom-pdc.c
+++ b/drivers/reset/reset-qcom-pdc.c
@@ -114,7 +114,6 @@ static int qcom_pdc_reset_probe(struct platform_device *pdev)
 	struct qcom_pdc_reset_data *data;
 	struct device *dev = &pdev->dev;
 	void __iomem *base;
-	struct resource *res;
 
 	desc = device_get_match_data(&pdev->dev);
 	if (!desc)
@@ -125,8 +124,7 @@ static int qcom_pdc_reset_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	data->desc = desc;
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	base = devm_ioremap_resource(dev, res);
+	base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(base))
 		return PTR_ERR(base);
 
diff --git a/drivers/reset/reset-simple.c b/drivers/reset/reset-simple.c
index 7ea5adbf2097..818cabcc9fb7 100644
--- a/drivers/reset/reset-simple.c
+++ b/drivers/reset/reset-simple.c
@@ -169,8 +169,7 @@ static int reset_simple_probe(struct platform_device *pdev)
 	if (!data)
 		return -ENOMEM;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	membase = devm_ioremap_resource(dev, res);
+	membase = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(membase))
 		return PTR_ERR(membase);
 
diff --git a/drivers/reset/reset-sunplus.c b/drivers/reset/reset-sunplus.c
index 2f23ecaa7b98..df58decab64d 100644
--- a/drivers/reset/reset-sunplus.c
+++ b/drivers/reset/reset-sunplus.c
@@ -176,8 +176,7 @@ static int sp_reset_probe(struct platform_device *pdev)
 	if (!reset)
 		return -ENOMEM;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	reset->base = devm_ioremap_resource(dev, res);
+	reset->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(reset->base))
 		return PTR_ERR(reset->base);
 
diff --git a/drivers/reset/reset-uniphier-glue.c b/drivers/reset/reset-uniphier-glue.c
index 97b3ddcdade1..5f9f2f7994c0 100644
--- a/drivers/reset/reset-uniphier-glue.c
+++ b/drivers/reset/reset-uniphier-glue.c
@@ -58,8 +58,7 @@ static int uniphier_glue_reset_probe(struct platform_device *pdev)
 		    priv->data->nrsts > MAX_RSTS))
 		return -EINVAL;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	priv->rdata.membase = devm_ioremap_resource(dev, res);
+	priv->rdata.membase = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(priv->rdata.membase))
 		return PTR_ERR(priv->rdata.membase);
 
diff --git a/drivers/reset/sti/reset-syscfg.c b/drivers/reset/sti/reset-syscfg.c
index c1ba04f6f155..2324060b747c 100644
--- a/drivers/reset/sti/reset-syscfg.c
+++ b/drivers/reset/sti/reset-syscfg.c
@@ -7,10 +7,11 @@
  */
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/module.h>
 #include <linux/err.h>
 #include <linux/types.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/regmap.h>
 #include <linux/mfd/syscon.h>
 
@@ -183,14 +184,14 @@ static int syscfg_reset_controller_register(struct device *dev,
 int syscfg_reset_probe(struct platform_device *pdev)
 {
 	struct device *dev = pdev ? &pdev->dev : NULL;
-	const struct of_device_id *match;
+	const void *data;
 
 	if (!dev || !dev->driver)
 		return -ENODEV;
 
-	match = of_match_device(dev->driver->of_match_table, dev);
-	if (!match || !match->data)
+	data = device_get_match_data(&pdev->dev);
+	if (!data)
 		return -EINVAL;
 
-	return syscfg_reset_controller_register(dev, match->data);
+	return syscfg_reset_controller_register(dev, data);
 }
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index d440319a7945..7327e81352e9 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -676,18 +676,20 @@ static void dasd_profile_start(struct dasd_block *block,
 	 * we count each request only once.
 	 */
 	device = cqr->startdev;
-	if (device->profile.data) {
-		counter = 1; /* request is not yet queued on the start device */
-		list_for_each(l, &device->ccw_queue)
-			if (++counter >= 31)
-				break;
-	}
+	if (!device->profile.data)
+		return;
+
+	spin_lock(get_ccwdev_lock(device->cdev));
+	counter = 1; /* request is not yet queued on the start device */
+	list_for_each(l, &device->ccw_queue)
+		if (++counter >= 31)
+			break;
+	spin_unlock(get_ccwdev_lock(device->cdev));
+
 	spin_lock(&device->profile.lock);
-	if (device->profile.data) {
-		device->profile.data->dasd_io_nr_req[counter]++;
-		if (rq_data_dir(req) == READ)
-			device->profile.data->dasd_read_nr_req[counter]++;
-	}
+	device->profile.data->dasd_io_nr_req[counter]++;
+	if (rq_data_dir(req) == READ)
+		device->profile.data->dasd_read_nr_req[counter]++;
 	spin_unlock(&device->profile.lock);
 }
 
@@ -1104,12 +1106,6 @@ static void dasd_statistics_removeroot(void)
 	return;
 }
 
-int dasd_stats_generic_show(struct seq_file *m, void *v)
-{
-	seq_puts(m, "Statistics are not activated in this kernel\n");
-	return 0;
-}
-
 static void dasd_profile_init(struct dasd_profile *profile,
 			      struct dentry *base_dentry)
 {
diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h
index 2e663131adaf..1b1b8a41c4d4 100644
--- a/drivers/s390/block/dasd_int.h
+++ b/drivers/s390/block/dasd_int.h
@@ -283,7 +283,7 @@ struct dasd_pprc_dev_info {
 	__u8 secondary;		/* 7       Secondary device address */
 	__u16 pprc_id;		/* 8-9     Peer-to-Peer Remote Copy ID */
 	__u8 reserved2[12];	/* 10-21   reserved */
-	__u16 prim_cu_ssid;	/* 22-23   Pimary Control Unit SSID */
+	__u16 prim_cu_ssid;	/* 22-23   Primary Control Unit SSID */
 	__u8 reserved3[12];	/* 24-35   reserved */
 	__u16 sec_cu_ssid;	/* 36-37   Secondary Control Unit SSID */
 	__u8 reserved4[90];	/* 38-127  reserved */
diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c
index 3a9cc8a4a230..ade95e91b3c8 100644
--- a/drivers/s390/block/scm_blk.c
+++ b/drivers/s390/block/scm_blk.c
@@ -17,6 +17,7 @@
 #include <linux/blk-mq.h>
 #include <linux/slab.h>
 #include <linux/list.h>
+#include <linux/io.h>
 #include <asm/eadm.h>
 #include "scm_blk.h"
 
@@ -130,7 +131,7 @@ static void scm_request_done(struct scm_request *scmrq)
 
 	for (i = 0; i < nr_requests_per_io && scmrq->request[i]; i++) {
 		msb = &scmrq->aob->msb[i];
-		aidaw = msb->data_addr;
+		aidaw = (u64)phys_to_virt(msb->data_addr);
 
 		if ((msb->flags & MSB_FLAG_IDA) && aidaw &&
 		    IS_ALIGNED(aidaw, PAGE_SIZE))
@@ -195,12 +196,12 @@ static int scm_request_prepare(struct scm_request *scmrq)
 	msb->scm_addr = scmdev->address + ((u64) blk_rq_pos(req) << 9);
 	msb->oc = (rq_data_dir(req) == READ) ? MSB_OC_READ : MSB_OC_WRITE;
 	msb->flags |= MSB_FLAG_IDA;
-	msb->data_addr = (u64) aidaw;
+	msb->data_addr = (u64)virt_to_phys(aidaw);
 
 	rq_for_each_segment(bv, req, iter) {
 		WARN_ON(bv.bv_offset);
 		msb->blk_count += bv.bv_len >> 12;
-		aidaw->data_addr = (u64) page_address(bv.bv_page);
+		aidaw->data_addr = virt_to_phys(page_address(bv.bv_page));
 		aidaw++;
 	}
 
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index f8b04ce61556..64ed55c3aed6 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -219,16 +219,16 @@ EXPORT_SYMBOL_GPL(chsc_sadc);
 
 static int s390_subchannel_remove_chpid(struct subchannel *sch, void *data)
 {
-	spin_lock_irq(sch->lock);
+	spin_lock_irq(&sch->lock);
 	if (sch->driver && sch->driver->chp_event)
 		if (sch->driver->chp_event(sch, data, CHP_OFFLINE) != 0)
 			goto out_unreg;
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 	return 0;
 
 out_unreg:
 	sch->lpm = 0;
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 	css_schedule_eval(sch->schid);
 	return 0;
 }
@@ -258,10 +258,10 @@ void chsc_chp_offline(struct chp_id chpid)
 
 static int __s390_process_res_acc(struct subchannel *sch, void *data)
 {
-	spin_lock_irq(sch->lock);
+	spin_lock_irq(&sch->lock);
 	if (sch->driver && sch->driver->chp_event)
 		sch->driver->chp_event(sch, data, CHP_ONLINE);
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 
 	return 0;
 }
@@ -292,10 +292,10 @@ static void s390_process_res_acc(struct chp_link *link)
 
 static int process_fces_event(struct subchannel *sch, void *data)
 {
-	spin_lock_irq(sch->lock);
+	spin_lock_irq(&sch->lock);
 	if (sch->driver && sch->driver->chp_event)
 		sch->driver->chp_event(sch, data, CHP_FCES_EVENT);
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 	return 0;
 }
 
@@ -769,11 +769,11 @@ static void __s390_subchannel_vary_chpid(struct subchannel *sch,
 
 	memset(&link, 0, sizeof(struct chp_link));
 	link.chpid = chpid;
-	spin_lock_irqsave(sch->lock, flags);
+	spin_lock_irqsave(&sch->lock, flags);
 	if (sch->driver && sch->driver->chp_event)
 		sch->driver->chp_event(sch, &link,
 				       on ? CHP_VARY_ON : CHP_VARY_OFF);
-	spin_unlock_irqrestore(sch->lock, flags);
+	spin_unlock_irqrestore(&sch->lock, flags);
 }
 
 static int s390_subchannel_vary_chpid_off(struct subchannel *sch, void *data)
diff --git a/drivers/s390/cio/chsc_sch.c b/drivers/s390/cio/chsc_sch.c
index 180ab899289c..902237d0baef 100644
--- a/drivers/s390/cio/chsc_sch.c
+++ b/drivers/s390/cio/chsc_sch.c
@@ -211,10 +211,10 @@ static int chsc_async(struct chsc_async_area *chsc_area,
 
 	chsc_area->header.key = PAGE_DEFAULT_KEY >> 4;
 	while ((sch = chsc_get_next_subchannel(sch))) {
-		spin_lock(sch->lock);
+		spin_lock(&sch->lock);
 		private = dev_get_drvdata(&sch->dev);
 		if (private->request) {
-			spin_unlock(sch->lock);
+			spin_unlock(&sch->lock);
 			ret = -EBUSY;
 			continue;
 		}
@@ -239,7 +239,7 @@ static int chsc_async(struct chsc_async_area *chsc_area,
 		default:
 			ret = -ENODEV;
 		}
-		spin_unlock(sch->lock);
+		spin_unlock(&sch->lock);
 		CHSC_MSG(2, "chsc on 0.%x.%04x returned cc=%d\n",
 			 sch->schid.ssid, sch->schid.sch_no, cc);
 		if (ret == -EINPROGRESS)
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index 6127add746d1..a5736b7357b2 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -546,7 +546,7 @@ static irqreturn_t do_cio_interrupt(int irq, void *dummy)
 		return IRQ_HANDLED;
 	}
 	sch = phys_to_virt(tpi_info->intparm);
-	spin_lock(sch->lock);
+	spin_lock(&sch->lock);
 	/* Store interrupt response block to lowcore. */
 	if (tsch(tpi_info->schid, irb) == 0) {
 		/* Keep subchannel information word up to date. */
@@ -558,7 +558,7 @@ static irqreturn_t do_cio_interrupt(int irq, void *dummy)
 			inc_irq_stat(IRQIO_CIO);
 	} else
 		inc_irq_stat(IRQIO_CIO);
-	spin_unlock(sch->lock);
+	spin_unlock(&sch->lock);
 
 	return IRQ_HANDLED;
 }
@@ -663,7 +663,7 @@ struct subchannel *cio_probe_console(void)
 	if (IS_ERR(sch))
 		return sch;
 
-	lockdep_set_class(sch->lock, &console_sch_key);
+	lockdep_set_class(&sch->lock, &console_sch_key);
 	isc_register(CONSOLE_ISC);
 	sch->config.isc = CONSOLE_ISC;
 	sch->config.intparm = (u32)virt_to_phys(sch);
diff --git a/drivers/s390/cio/cio.h b/drivers/s390/cio/cio.h
index fa8df50bb49e..a9057a5b670a 100644
--- a/drivers/s390/cio/cio.h
+++ b/drivers/s390/cio/cio.h
@@ -83,7 +83,7 @@ enum sch_todo {
 /* subchannel data structure used by I/O subroutines */
 struct subchannel {
 	struct subchannel_id schid;
-	spinlock_t *lock;	/* subchannel lock */
+	spinlock_t lock;	/* subchannel lock */
 	struct mutex reg_mutex;
 	enum {
 		SUBCHANNEL_TYPE_IO = 0,
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index 3ff46fc694f8..28a88ed2c3aa 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -148,16 +148,10 @@ out:
 
 static void css_sch_todo(struct work_struct *work);
 
-static int css_sch_create_locks(struct subchannel *sch)
+static void css_sch_create_locks(struct subchannel *sch)
 {
-	sch->lock = kmalloc(sizeof(*sch->lock), GFP_KERNEL);
-	if (!sch->lock)
-		return -ENOMEM;
-
-	spin_lock_init(sch->lock);
+	spin_lock_init(&sch->lock);
 	mutex_init(&sch->reg_mutex);
-
-	return 0;
 }
 
 static void css_subchannel_release(struct device *dev)
@@ -167,7 +161,6 @@ static void css_subchannel_release(struct device *dev)
 	sch->config.intparm = 0;
 	cio_commit_config(sch);
 	kfree(sch->driver_override);
-	kfree(sch->lock);
 	kfree(sch);
 }
 
@@ -219,9 +212,7 @@ struct subchannel *css_alloc_subchannel(struct subchannel_id schid,
 	sch->schib = *schib;
 	sch->st = schib->pmcw.st;
 
-	ret = css_sch_create_locks(sch);
-	if (ret)
-		goto err;
+	css_sch_create_locks(sch);
 
 	INIT_WORK(&sch->todo_work, css_sch_todo);
 	sch->dev.release = &css_subchannel_release;
@@ -233,19 +224,17 @@ struct subchannel *css_alloc_subchannel(struct subchannel_id schid,
 	 */
 	ret = dma_set_coherent_mask(&sch->dev, DMA_BIT_MASK(31));
 	if (ret)
-		goto err_lock;
+		goto err;
 	/*
 	 * But we don't have such restrictions imposed on the stuff that
 	 * is handled by the streaming API.
 	 */
 	ret = dma_set_mask(&sch->dev, DMA_BIT_MASK(64));
 	if (ret)
-		goto err_lock;
+		goto err;
 
 	return sch;
 
-err_lock:
-	kfree(sch->lock);
 err:
 	kfree(sch);
 	return ERR_PTR(ret);
@@ -604,12 +593,12 @@ static void css_sch_todo(struct work_struct *work)
 
 	sch = container_of(work, struct subchannel, todo_work);
 	/* Find out todo. */
-	spin_lock_irq(sch->lock);
+	spin_lock_irq(&sch->lock);
 	todo = sch->todo;
 	CIO_MSG_EVENT(4, "sch_todo: sch=0.%x.%04x, todo=%d\n", sch->schid.ssid,
 		      sch->schid.sch_no, todo);
 	sch->todo = SCH_TODO_NOTHING;
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 	/* Perform todo. */
 	switch (todo) {
 	case SCH_TODO_NOTHING:
@@ -617,9 +606,9 @@ static void css_sch_todo(struct work_struct *work)
 	case SCH_TODO_EVAL:
 		ret = css_evaluate_known_subchannel(sch, 1);
 		if (ret == -EAGAIN) {
-			spin_lock_irq(sch->lock);
+			spin_lock_irq(&sch->lock);
 			css_sched_sch_todo(sch, todo);
-			spin_unlock_irq(sch->lock);
+			spin_unlock_irq(&sch->lock);
 		}
 		break;
 	case SCH_TODO_UNREG:
@@ -1028,12 +1017,7 @@ static int __init setup_css(int nr)
 	css->pseudo_subchannel->dev.parent = &css->device;
 	css->pseudo_subchannel->dev.release = css_subchannel_release;
 	mutex_init(&css->pseudo_subchannel->reg_mutex);
-	ret = css_sch_create_locks(css->pseudo_subchannel);
-	if (ret) {
-		kfree(css->pseudo_subchannel);
-		device_unregister(&css->device);
-		goto out_err;
-	}
+	css_sch_create_locks(css->pseudo_subchannel);
 
 	dev_set_name(&css->pseudo_subchannel->dev, "defunct");
 	ret = device_register(&css->pseudo_subchannel->dev);
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index 4ca5adce9107..0cfb179e1bcb 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -748,7 +748,7 @@ static int io_subchannel_initialize_dev(struct subchannel *sch,
 	mutex_init(&cdev->reg_mutex);
 
 	atomic_set(&priv->onoff, 0);
-	cdev->ccwlock = sch->lock;
+	cdev->ccwlock = &sch->lock;
 	cdev->dev.parent = &sch->dev;
 	cdev->dev.release = ccw_device_release;
 	cdev->dev.bus = &ccw_bus_type;
@@ -764,9 +764,9 @@ static int io_subchannel_initialize_dev(struct subchannel *sch,
 		goto out_put;
 	}
 	priv->flags.initialized = 1;
-	spin_lock_irq(sch->lock);
+	spin_lock_irq(&sch->lock);
 	sch_set_cdev(sch, cdev);
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 	return 0;
 
 out_put:
@@ -851,9 +851,9 @@ static void io_subchannel_register(struct ccw_device *cdev)
 		CIO_MSG_EVENT(0, "Could not register ccw dev 0.%x.%04x: %d\n",
 			      cdev->private->dev_id.ssid,
 			      cdev->private->dev_id.devno, ret);
-		spin_lock_irqsave(sch->lock, flags);
+		spin_lock_irqsave(&sch->lock, flags);
 		sch_set_cdev(sch, NULL);
-		spin_unlock_irqrestore(sch->lock, flags);
+		spin_unlock_irqrestore(&sch->lock, flags);
 		mutex_unlock(&cdev->reg_mutex);
 		/* Release initial device reference. */
 		put_device(&cdev->dev);
@@ -904,9 +904,9 @@ static void io_subchannel_recog(struct ccw_device *cdev, struct subchannel *sch)
 	atomic_inc(&ccw_device_init_count);
 
 	/* Start async. device sensing. */
-	spin_lock_irq(sch->lock);
+	spin_lock_irq(&sch->lock);
 	ccw_device_recognition(cdev);
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 }
 
 static int ccw_device_move_to_sch(struct ccw_device *cdev,
@@ -921,12 +921,12 @@ static int ccw_device_move_to_sch(struct ccw_device *cdev,
 		return -ENODEV;
 
 	if (!sch_is_pseudo_sch(old_sch)) {
-		spin_lock_irq(old_sch->lock);
+		spin_lock_irq(&old_sch->lock);
 		old_enabled = old_sch->schib.pmcw.ena;
 		rc = 0;
 		if (old_enabled)
 			rc = cio_disable_subchannel(old_sch);
-		spin_unlock_irq(old_sch->lock);
+		spin_unlock_irq(&old_sch->lock);
 		if (rc == -EBUSY) {
 			/* Release child reference for new parent. */
 			put_device(&sch->dev);
@@ -944,9 +944,9 @@ static int ccw_device_move_to_sch(struct ccw_device *cdev,
 			      sch->schib.pmcw.dev, rc);
 		if (old_enabled) {
 			/* Try to re-enable the old subchannel. */
-			spin_lock_irq(old_sch->lock);
+			spin_lock_irq(&old_sch->lock);
 			cio_enable_subchannel(old_sch, (u32)virt_to_phys(old_sch));
-			spin_unlock_irq(old_sch->lock);
+			spin_unlock_irq(&old_sch->lock);
 		}
 		/* Release child reference for new parent. */
 		put_device(&sch->dev);
@@ -954,19 +954,19 @@ static int ccw_device_move_to_sch(struct ccw_device *cdev,
 	}
 	/* Clean up old subchannel. */
 	if (!sch_is_pseudo_sch(old_sch)) {
-		spin_lock_irq(old_sch->lock);
+		spin_lock_irq(&old_sch->lock);
 		sch_set_cdev(old_sch, NULL);
-		spin_unlock_irq(old_sch->lock);
+		spin_unlock_irq(&old_sch->lock);
 		css_schedule_eval(old_sch->schid);
 	}
 	/* Release child reference for old parent. */
 	put_device(&old_sch->dev);
 	/* Initialize new subchannel. */
-	spin_lock_irq(sch->lock);
-	cdev->ccwlock = sch->lock;
+	spin_lock_irq(&sch->lock);
+	cdev->ccwlock = &sch->lock;
 	if (!sch_is_pseudo_sch(sch))
 		sch_set_cdev(sch, cdev);
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 	if (!sch_is_pseudo_sch(sch))
 		css_update_ssd_info(sch);
 	return 0;
@@ -1077,9 +1077,9 @@ static int io_subchannel_probe(struct subchannel *sch)
 	return 0;
 
 out_schedule:
-	spin_lock_irq(sch->lock);
+	spin_lock_irq(&sch->lock);
 	css_sched_sch_todo(sch, SCH_TODO_UNREG);
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 	return 0;
 }
 
@@ -1093,10 +1093,10 @@ static void io_subchannel_remove(struct subchannel *sch)
 		goto out_free;
 
 	ccw_device_unregister(cdev);
-	spin_lock_irq(sch->lock);
+	spin_lock_irq(&sch->lock);
 	sch_set_cdev(sch, NULL);
 	set_io_private(sch, NULL);
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 out_free:
 	dma_free_coherent(&sch->dev, sizeof(*io_priv->dma_area),
 			  io_priv->dma_area, io_priv->dma_area_dma);
@@ -1203,7 +1203,7 @@ static void io_subchannel_quiesce(struct subchannel *sch)
 	struct ccw_device *cdev;
 	int ret;
 
-	spin_lock_irq(sch->lock);
+	spin_lock_irq(&sch->lock);
 	cdev = sch_get_cdev(sch);
 	if (cio_is_console(sch->schid))
 		goto out_unlock;
@@ -1220,15 +1220,15 @@ static void io_subchannel_quiesce(struct subchannel *sch)
 		ret = ccw_device_cancel_halt_clear(cdev);
 		if (ret == -EBUSY) {
 			ccw_device_set_timeout(cdev, HZ/10);
-			spin_unlock_irq(sch->lock);
+			spin_unlock_irq(&sch->lock);
 			wait_event(cdev->private->wait_q,
 				   cdev->private->state != DEV_STATE_QUIESCE);
-			spin_lock_irq(sch->lock);
+			spin_lock_irq(&sch->lock);
 		}
 		ret = cio_disable_subchannel(sch);
 	}
 out_unlock:
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 }
 
 static void io_subchannel_shutdown(struct subchannel *sch)
@@ -1439,7 +1439,7 @@ static int io_subchannel_sch_event(struct subchannel *sch, int process)
 	enum io_sch_action action;
 	int rc = -EAGAIN;
 
-	spin_lock_irqsave(sch->lock, flags);
+	spin_lock_irqsave(&sch->lock, flags);
 	if (!device_is_registered(&sch->dev))
 		goto out_unlock;
 	if (work_pending(&sch->todo_work))
@@ -1492,7 +1492,7 @@ static int io_subchannel_sch_event(struct subchannel *sch, int process)
 	default:
 		break;
 	}
-	spin_unlock_irqrestore(sch->lock, flags);
+	spin_unlock_irqrestore(&sch->lock, flags);
 	/* All other actions require process context. */
 	if (!process)
 		goto out;
@@ -1507,9 +1507,9 @@ static int io_subchannel_sch_event(struct subchannel *sch, int process)
 		break;
 	case IO_SCH_UNREG_CDEV:
 	case IO_SCH_UNREG_ATTACH:
-		spin_lock_irqsave(sch->lock, flags);
+		spin_lock_irqsave(&sch->lock, flags);
 		sch_set_cdev(sch, NULL);
-		spin_unlock_irqrestore(sch->lock, flags);
+		spin_unlock_irqrestore(&sch->lock, flags);
 		/* Unregister ccw device. */
 		ccw_device_unregister(cdev);
 		break;
@@ -1538,9 +1538,9 @@ static int io_subchannel_sch_event(struct subchannel *sch, int process)
 			put_device(&cdev->dev);
 			goto out;
 		}
-		spin_lock_irqsave(sch->lock, flags);
+		spin_lock_irqsave(&sch->lock, flags);
 		ccw_device_trigger_reprobe(cdev);
-		spin_unlock_irqrestore(sch->lock, flags);
+		spin_unlock_irqrestore(&sch->lock, flags);
 		/* Release reference from get_ccwdev_by_dev_id() */
 		put_device(&cdev->dev);
 		break;
@@ -1550,7 +1550,7 @@ static int io_subchannel_sch_event(struct subchannel *sch, int process)
 	return 0;
 
 out_unlock:
-	spin_unlock_irqrestore(sch->lock, flags);
+	spin_unlock_irqrestore(&sch->lock, flags);
 out:
 	return rc;
 }
@@ -1846,9 +1846,9 @@ static void ccw_device_todo(struct work_struct *work)
 			css_schedule_eval(sch->schid);
 		fallthrough;
 	case CDEV_TODO_UNREG:
-		spin_lock_irq(sch->lock);
+		spin_lock_irq(&sch->lock);
 		sch_set_cdev(sch, NULL);
-		spin_unlock_irq(sch->lock);
+		spin_unlock_irq(&sch->lock);
 		ccw_device_unregister(cdev);
 		break;
 	default:
diff --git a/drivers/s390/cio/device_pgid.c b/drivers/s390/cio/device_pgid.c
index 3862961697eb..ad90045873e2 100644
--- a/drivers/s390/cio/device_pgid.c
+++ b/drivers/s390/cio/device_pgid.c
@@ -698,29 +698,29 @@ int ccw_device_stlck(struct ccw_device *cdev)
 		return -ENOMEM;
 	init_completion(&data.done);
 	data.rc = -EIO;
-	spin_lock_irq(sch->lock);
+	spin_lock_irq(&sch->lock);
 	rc = cio_enable_subchannel(sch, (u32)virt_to_phys(sch));
 	if (rc)
 		goto out_unlock;
 	/* Perform operation. */
 	cdev->private->state = DEV_STATE_STEAL_LOCK;
 	ccw_device_stlck_start(cdev, &data, &buffer[0], &buffer[32]);
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 	/* Wait for operation to finish. */
 	if (wait_for_completion_interruptible(&data.done)) {
 		/* Got a signal. */
-		spin_lock_irq(sch->lock);
+		spin_lock_irq(&sch->lock);
 		ccw_request_cancel(cdev);
-		spin_unlock_irq(sch->lock);
+		spin_unlock_irq(&sch->lock);
 		wait_for_completion(&data.done);
 	}
 	rc = data.rc;
 	/* Check results. */
-	spin_lock_irq(sch->lock);
+	spin_lock_irq(&sch->lock);
 	cio_disable_subchannel(sch);
 	cdev->private->state = DEV_STATE_BOXED;
 out_unlock:
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 	kfree(buffer);
 
 	return rc;
diff --git a/drivers/s390/cio/eadm_sch.c b/drivers/s390/cio/eadm_sch.c
index 826364d2facd..1caedf931a5f 100644
--- a/drivers/s390/cio/eadm_sch.c
+++ b/drivers/s390/cio/eadm_sch.c
@@ -101,12 +101,12 @@ static void eadm_subchannel_timeout(struct timer_list *t)
 	struct eadm_private *private = from_timer(private, t, timer);
 	struct subchannel *sch = private->sch;
 
-	spin_lock_irq(sch->lock);
+	spin_lock_irq(&sch->lock);
 	EADM_LOG(1, "timeout");
 	EADM_LOG_HEX(1, &sch->schid, sizeof(sch->schid));
 	if (eadm_subchannel_clear(sch))
 		EADM_LOG(0, "clear failed");
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 }
 
 static void eadm_subchannel_set_timeout(struct subchannel *sch, int expires)
@@ -163,16 +163,16 @@ static struct subchannel *eadm_get_idle_sch(void)
 	spin_lock_irqsave(&list_lock, flags);
 	list_for_each_entry(private, &eadm_list, head) {
 		sch = private->sch;
-		spin_lock(sch->lock);
+		spin_lock(&sch->lock);
 		if (private->state == EADM_IDLE) {
 			private->state = EADM_BUSY;
 			list_move_tail(&private->head, &eadm_list);
-			spin_unlock(sch->lock);
+			spin_unlock(&sch->lock);
 			spin_unlock_irqrestore(&list_lock, flags);
 
 			return sch;
 		}
-		spin_unlock(sch->lock);
+		spin_unlock(&sch->lock);
 	}
 	spin_unlock_irqrestore(&list_lock, flags);
 
@@ -190,7 +190,7 @@ int eadm_start_aob(struct aob *aob)
 	if (!sch)
 		return -EBUSY;
 
-	spin_lock_irqsave(sch->lock, flags);
+	spin_lock_irqsave(&sch->lock, flags);
 	eadm_subchannel_set_timeout(sch, EADM_TIMEOUT);
 	ret = eadm_subchannel_start(sch, aob);
 	if (!ret)
@@ -203,7 +203,7 @@ int eadm_start_aob(struct aob *aob)
 	css_sched_sch_todo(sch, SCH_TODO_EVAL);
 
 out_unlock:
-	spin_unlock_irqrestore(sch->lock, flags);
+	spin_unlock_irqrestore(&sch->lock, flags);
 
 	return ret;
 }
@@ -221,7 +221,7 @@ static int eadm_subchannel_probe(struct subchannel *sch)
 	INIT_LIST_HEAD(&private->head);
 	timer_setup(&private->timer, eadm_subchannel_timeout, 0);
 
-	spin_lock_irq(sch->lock);
+	spin_lock_irq(&sch->lock);
 	set_eadm_private(sch, private);
 	private->state = EADM_IDLE;
 	private->sch = sch;
@@ -229,11 +229,11 @@ static int eadm_subchannel_probe(struct subchannel *sch)
 	ret = cio_enable_subchannel(sch, (u32)virt_to_phys(sch));
 	if (ret) {
 		set_eadm_private(sch, NULL);
-		spin_unlock_irq(sch->lock);
+		spin_unlock_irq(&sch->lock);
 		kfree(private);
 		goto out;
 	}
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 
 	spin_lock_irq(&list_lock);
 	list_add(&private->head, &eadm_list);
@@ -248,7 +248,7 @@ static void eadm_quiesce(struct subchannel *sch)
 	DECLARE_COMPLETION_ONSTACK(completion);
 	int ret;
 
-	spin_lock_irq(sch->lock);
+	spin_lock_irq(&sch->lock);
 	if (private->state != EADM_BUSY)
 		goto disable;
 
@@ -256,11 +256,11 @@ static void eadm_quiesce(struct subchannel *sch)
 		goto disable;
 
 	private->completion = &completion;
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 
 	wait_for_completion_io(&completion);
 
-	spin_lock_irq(sch->lock);
+	spin_lock_irq(&sch->lock);
 	private->completion = NULL;
 
 disable:
@@ -269,7 +269,7 @@ disable:
 		ret = cio_disable_subchannel(sch);
 	} while (ret == -EBUSY);
 
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 }
 
 static void eadm_subchannel_remove(struct subchannel *sch)
@@ -282,9 +282,9 @@ static void eadm_subchannel_remove(struct subchannel *sch)
 
 	eadm_quiesce(sch);
 
-	spin_lock_irq(sch->lock);
+	spin_lock_irq(&sch->lock);
 	set_eadm_private(sch, NULL);
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 
 	kfree(private);
 }
@@ -309,7 +309,7 @@ static int eadm_subchannel_sch_event(struct subchannel *sch, int process)
 	struct eadm_private *private;
 	unsigned long flags;
 
-	spin_lock_irqsave(sch->lock, flags);
+	spin_lock_irqsave(&sch->lock, flags);
 	if (!device_is_registered(&sch->dev))
 		goto out_unlock;
 
@@ -325,7 +325,7 @@ static int eadm_subchannel_sch_event(struct subchannel *sch, int process)
 		private->state = EADM_IDLE;
 
 out_unlock:
-	spin_unlock_irqrestore(sch->lock, flags);
+	spin_unlock_irqrestore(&sch->lock, flags);
 
 	return 0;
 }
diff --git a/drivers/s390/cio/vfio_ccw_chp.c b/drivers/s390/cio/vfio_ccw_chp.c
index d3f3a611f95b..38c176cf6295 100644
--- a/drivers/s390/cio/vfio_ccw_chp.c
+++ b/drivers/s390/cio/vfio_ccw_chp.c
@@ -115,7 +115,7 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private,
 
 	/* Notify the guest if more CRWs are on our queue */
 	if (!list_empty(&private->crw) && private->crw_trigger)
-		eventfd_signal(private->crw_trigger, 1);
+		eventfd_signal(private->crw_trigger);
 
 	return ret;
 }
diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index 43601816ea4e..8ad49030a7bf 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -65,14 +65,14 @@ int vfio_ccw_sch_quiesce(struct subchannel *sch)
 		 * cancel/halt/clear completion.
 		 */
 		private->completion = &completion;
-		spin_unlock_irq(sch->lock);
+		spin_unlock_irq(&sch->lock);
 
 		if (ret == -EBUSY)
 			wait_for_completion_timeout(&completion, 3*HZ);
 
 		private->completion = NULL;
 		flush_workqueue(vfio_ccw_work_q);
-		spin_lock_irq(sch->lock);
+		spin_lock_irq(&sch->lock);
 		ret = cio_disable_subchannel(sch);
 	} while (ret == -EBUSY);
 
@@ -112,7 +112,7 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
 		private->state = VFIO_CCW_STATE_IDLE;
 
 	if (private->io_trigger)
-		eventfd_signal(private->io_trigger, 1);
+		eventfd_signal(private->io_trigger);
 }
 
 void vfio_ccw_crw_todo(struct work_struct *work)
@@ -122,7 +122,7 @@ void vfio_ccw_crw_todo(struct work_struct *work)
 	private = container_of(work, struct vfio_ccw_private, crw_work);
 
 	if (!list_empty(&private->crw) && private->crw_trigger)
-		eventfd_signal(private->crw_trigger, 1);
+		eventfd_signal(private->crw_trigger);
 }
 
 /*
@@ -249,7 +249,7 @@ static int vfio_ccw_sch_event(struct subchannel *sch, int process)
 	unsigned long flags;
 	int rc = -EAGAIN;
 
-	spin_lock_irqsave(sch->lock, flags);
+	spin_lock_irqsave(&sch->lock, flags);
 	if (!device_is_registered(&sch->dev))
 		goto out_unlock;
 
@@ -264,7 +264,7 @@ static int vfio_ccw_sch_event(struct subchannel *sch, int process)
 	}
 
 out_unlock:
-	spin_unlock_irqrestore(sch->lock, flags);
+	spin_unlock_irqrestore(&sch->lock, flags);
 
 	return rc;
 }
diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
index 757b73141246..09877b46181d 100644
--- a/drivers/s390/cio/vfio_ccw_fsm.c
+++ b/drivers/s390/cio/vfio_ccw_fsm.c
@@ -25,7 +25,7 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
 	unsigned long flags;
 	int ret;
 
-	spin_lock_irqsave(sch->lock, flags);
+	spin_lock_irqsave(&sch->lock, flags);
 
 	orb = cp_get_orb(&private->cp, sch);
 	if (!orb) {
@@ -72,7 +72,7 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
 		ret = ccode;
 	}
 out:
-	spin_unlock_irqrestore(sch->lock, flags);
+	spin_unlock_irqrestore(&sch->lock, flags);
 	return ret;
 }
 
@@ -83,7 +83,7 @@ static int fsm_do_halt(struct vfio_ccw_private *private)
 	int ccode;
 	int ret;
 
-	spin_lock_irqsave(sch->lock, flags);
+	spin_lock_irqsave(&sch->lock, flags);
 
 	VFIO_CCW_TRACE_EVENT(2, "haltIO");
 	VFIO_CCW_TRACE_EVENT(2, dev_name(&sch->dev));
@@ -111,7 +111,7 @@ static int fsm_do_halt(struct vfio_ccw_private *private)
 	default:
 		ret = ccode;
 	}
-	spin_unlock_irqrestore(sch->lock, flags);
+	spin_unlock_irqrestore(&sch->lock, flags);
 	return ret;
 }
 
@@ -122,7 +122,7 @@ static int fsm_do_clear(struct vfio_ccw_private *private)
 	int ccode;
 	int ret;
 
-	spin_lock_irqsave(sch->lock, flags);
+	spin_lock_irqsave(&sch->lock, flags);
 
 	VFIO_CCW_TRACE_EVENT(2, "clearIO");
 	VFIO_CCW_TRACE_EVENT(2, dev_name(&sch->dev));
@@ -147,7 +147,7 @@ static int fsm_do_clear(struct vfio_ccw_private *private)
 	default:
 		ret = ccode;
 	}
-	spin_unlock_irqrestore(sch->lock, flags);
+	spin_unlock_irqrestore(&sch->lock, flags);
 	return ret;
 }
 
@@ -376,18 +376,18 @@ static void fsm_open(struct vfio_ccw_private *private,
 	struct subchannel *sch = to_subchannel(private->vdev.dev->parent);
 	int ret;
 
-	spin_lock_irq(sch->lock);
+	spin_lock_irq(&sch->lock);
 	sch->isc = VFIO_CCW_ISC;
 	ret = cio_enable_subchannel(sch, (u32)(unsigned long)sch);
 	if (ret)
 		goto err_unlock;
 
 	private->state = VFIO_CCW_STATE_IDLE;
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 	return;
 
 err_unlock:
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_NOT_OPER);
 }
 
@@ -397,7 +397,7 @@ static void fsm_close(struct vfio_ccw_private *private,
 	struct subchannel *sch = to_subchannel(private->vdev.dev->parent);
 	int ret;
 
-	spin_lock_irq(sch->lock);
+	spin_lock_irq(&sch->lock);
 
 	if (!sch->schib.pmcw.ena)
 		goto err_unlock;
@@ -409,12 +409,12 @@ static void fsm_close(struct vfio_ccw_private *private,
 		goto err_unlock;
 
 	private->state = VFIO_CCW_STATE_STANDBY;
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 	cp_free(&private->cp);
 	return;
 
 err_unlock:
-	spin_unlock_irq(sch->lock);
+	spin_unlock_irq(&sch->lock);
 	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_NOT_OPER);
 }
 
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index cba4971618ff..ea532a8a4a0c 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -421,7 +421,7 @@ static int vfio_ccw_mdev_set_irqs(struct vfio_ccw_private *private,
 	case VFIO_IRQ_SET_DATA_NONE:
 	{
 		if (*ctx)
-			eventfd_signal(*ctx, 1);
+			eventfd_signal(*ctx);
 		return 0;
 	}
 	case VFIO_IRQ_SET_DATA_BOOL:
@@ -432,7 +432,7 @@ static int vfio_ccw_mdev_set_irqs(struct vfio_ccw_private *private,
 			return -EFAULT;
 
 		if (trigger && *ctx)
-			eventfd_signal(*ctx, 1);
+			eventfd_signal(*ctx);
 		return 0;
 	}
 	case VFIO_IRQ_SET_DATA_EVENTFD:
@@ -612,7 +612,7 @@ static void vfio_ccw_mdev_request(struct vfio_device *vdev, unsigned int count)
 					       "Relaying device request to user (#%u)\n",
 					       count);
 
-		eventfd_signal(private->req_trigger, 1);
+		eventfd_signal(private->req_trigger);
 	} else if (count == 0) {
 		dev_notice(dev,
 			   "No device request channel registered, blocked until released by user\n");
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 5dd33155d5d5..f46dd6abacd7 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -357,13 +357,12 @@ EXPORT_SYMBOL(ap_test_config_ctrl_domain);
  *	   -1 invalid APQN, TAPQ error or AP queue status which
  *	      indicates there is no APQN.
  */
-static int ap_queue_info(ap_qid_t qid, int *q_type, unsigned int *q_fac,
-			 int *q_depth, int *q_ml, bool *q_decfg, bool *q_cstop)
+static int ap_queue_info(ap_qid_t qid, struct ap_tapq_hwinfo *hwinfo,
+			 bool *decfg, bool *cstop)
 {
 	struct ap_queue_status status;
-	struct ap_tapq_gr2 tapq_info;
 
-	tapq_info.value = 0;
+	hwinfo->value = 0;
 
 	/* make sure we don't run into a specifiation exception */
 	if (AP_QID_CARD(qid) > ap_max_adapter_id ||
@@ -371,7 +370,7 @@ static int ap_queue_info(ap_qid_t qid, int *q_type, unsigned int *q_fac,
 		return -1;
 
 	/* call TAPQ on this APQN */
-	status = ap_test_queue(qid, ap_apft_available(), &tapq_info);
+	status = ap_test_queue(qid, ap_apft_available(), hwinfo);
 
 	switch (status.response_code) {
 	case AP_RESPONSE_NORMAL:
@@ -389,15 +388,11 @@ static int ap_queue_info(ap_qid_t qid, int *q_type, unsigned int *q_fac,
 	}
 
 	/* There should be at least one of the mode bits set */
-	if (WARN_ON_ONCE(!tapq_info.value))
+	if (WARN_ON_ONCE(!hwinfo->value))
 		return 0;
 
-	*q_type = tapq_info.at;
-	*q_fac = tapq_info.fac;
-	*q_depth = tapq_info.qd;
-	*q_ml = tapq_info.ml;
-	*q_decfg = status.response_code == AP_RESPONSE_DECONFIGURED;
-	*q_cstop = status.response_code == AP_RESPONSE_CHECKSTOPPED;
+	*decfg = status.response_code == AP_RESPONSE_DECONFIGURED;
+	*cstop = status.response_code == AP_RESPONSE_CHECKSTOPPED;
 
 	return 1;
 }
@@ -642,11 +637,11 @@ static int ap_uevent(const struct device *dev, struct kobj_uevent_env *env)
 			return rc;
 
 		/* Add MODE=<accel|cca|ep11> */
-		if (ap_test_bit(&ac->functions, AP_FUNC_ACCEL))
+		if (ac->hwinfo.accel)
 			rc = add_uevent_var(env, "MODE=accel");
-		else if (ap_test_bit(&ac->functions, AP_FUNC_COPRO))
+		else if (ac->hwinfo.cca)
 			rc = add_uevent_var(env, "MODE=cca");
-		else if (ap_test_bit(&ac->functions, AP_FUNC_EP11))
+		else if (ac->hwinfo.ep11)
 			rc = add_uevent_var(env, "MODE=ep11");
 		if (rc)
 			return rc;
@@ -654,11 +649,11 @@ static int ap_uevent(const struct device *dev, struct kobj_uevent_env *env)
 		struct ap_queue *aq = to_ap_queue(&ap_dev->device);
 
 		/* Add MODE=<accel|cca|ep11> */
-		if (ap_test_bit(&aq->card->functions, AP_FUNC_ACCEL))
+		if (aq->card->hwinfo.accel)
 			rc = add_uevent_var(env, "MODE=accel");
-		else if (ap_test_bit(&aq->card->functions, AP_FUNC_COPRO))
+		else if (aq->card->hwinfo.cca)
 			rc = add_uevent_var(env, "MODE=cca");
-		else if (ap_test_bit(&aq->card->functions, AP_FUNC_EP11))
+		else if (aq->card->hwinfo.ep11)
 			rc = add_uevent_var(env, "MODE=ep11");
 		if (rc)
 			return rc;
@@ -1799,12 +1794,12 @@ static inline void ap_scan_rm_card_dev_and_queue_devs(struct ap_card *ac)
  */
 static inline void ap_scan_domains(struct ap_card *ac)
 {
-	int rc, dom, depth, type, ml;
+	struct ap_tapq_hwinfo hwinfo;
 	bool decfg, chkstop;
 	struct ap_queue *aq;
 	struct device *dev;
-	unsigned int func;
 	ap_qid_t qid;
+	int rc, dom;
 
 	/*
 	 * Go through the configuration for the domains and compare them
@@ -1827,8 +1822,7 @@ static inline void ap_scan_domains(struct ap_card *ac)
 			goto put_dev_and_continue;
 		}
 		/* domain is valid, get info from this APQN */
-		rc = ap_queue_info(qid, &type, &func, &depth,
-				   &ml, &decfg, &chkstop);
+		rc = ap_queue_info(qid, &hwinfo, &decfg, &chkstop);
 		switch (rc) {
 		case -1:
 			if (dev) {
@@ -1853,6 +1847,7 @@ static inline void ap_scan_domains(struct ap_card *ac)
 			aq->card = ac;
 			aq->config = !decfg;
 			aq->chkstop = chkstop;
+			aq->se_bstate = hwinfo.bs;
 			dev = &aq->ap_dev.device;
 			dev->bus = &ap_bus_type;
 			dev->parent = &ac->ap_dev.device;
@@ -1882,6 +1877,8 @@ static inline void ap_scan_domains(struct ap_card *ac)
 		}
 		/* handle state changes on already existing queue device */
 		spin_lock_bh(&aq->lock);
+		/* SE bind state */
+		aq->se_bstate = hwinfo.bs;
 		/* checkstop state */
 		if (chkstop && !aq->chkstop) {
 			/* checkstop on */
@@ -1955,11 +1952,11 @@ put_dev_and_continue:
  */
 static inline void ap_scan_adapter(int ap)
 {
-	int rc, dom, depth, type, comp_type, ml;
+	struct ap_tapq_hwinfo hwinfo;
+	int rc, dom, comp_type;
 	bool decfg, chkstop;
 	struct ap_card *ac;
 	struct device *dev;
-	unsigned int func;
 	ap_qid_t qid;
 
 	/* Is there currently a card device for this adapter ? */
@@ -1989,8 +1986,7 @@ static inline void ap_scan_adapter(int ap)
 	for (dom = 0; dom <= ap_max_domain_id; dom++)
 		if (ap_test_config_usage_domain(dom)) {
 			qid = AP_MKQID(ap, dom);
-			if (ap_queue_info(qid, &type, &func, &depth,
-					  &ml, &decfg, &chkstop) > 0)
+			if (ap_queue_info(qid, &hwinfo, &decfg, &chkstop) > 0)
 				break;
 		}
 	if (dom > ap_max_domain_id) {
@@ -2006,7 +2002,7 @@ static inline void ap_scan_adapter(int ap)
 		}
 		return;
 	}
-	if (!type) {
+	if (!hwinfo.at) {
 		/* No apdater type info available, an unusable adapter */
 		if (ac) {
 			AP_DBF_INFO("%s(%d) no valid type (0) info, rm card and queue devs\n",
@@ -2019,18 +2015,18 @@ static inline void ap_scan_adapter(int ap)
 		}
 		return;
 	}
+	hwinfo.value &= TAPQ_CARD_HWINFO_MASK; /* filter card specific hwinfo */
 	if (ac) {
 		/* Check APQN against existing card device for changes */
-		if (ac->raw_hwtype != type) {
+		if (ac->hwinfo.at != hwinfo.at) {
 			AP_DBF_INFO("%s(%d) hwtype %d changed, rm card and queue devs\n",
-				    __func__, ap, type);
+				    __func__, ap, hwinfo.at);
 			ap_scan_rm_card_dev_and_queue_devs(ac);
 			put_device(dev);
 			ac = NULL;
-		} else if ((ac->functions & TAPQ_CARD_FUNC_CMP_MASK) !=
-			   (func & TAPQ_CARD_FUNC_CMP_MASK)) {
+		} else if (ac->hwinfo.fac != hwinfo.fac) {
 			AP_DBF_INFO("%s(%d) functions 0x%08x changed, rm card and queue devs\n",
-				    __func__, ap, func);
+				    __func__, ap, hwinfo.fac);
 			ap_scan_rm_card_dev_and_queue_devs(ac);
 			put_device(dev);
 			ac = NULL;
@@ -2064,13 +2060,13 @@ static inline void ap_scan_adapter(int ap)
 
 	if (!ac) {
 		/* Build a new card device */
-		comp_type = ap_get_compatible_type(qid, type, func);
+		comp_type = ap_get_compatible_type(qid, hwinfo.at, hwinfo.fac);
 		if (!comp_type) {
 			AP_DBF_WARN("%s(%d) type %d, can't get compatibility type\n",
-				    __func__, ap, type);
+				    __func__, ap, hwinfo.at);
 			return;
 		}
-		ac = ap_card_create(ap, depth, type, comp_type, func, ml);
+		ac = ap_card_create(ap, hwinfo, comp_type);
 		if (!ac) {
 			AP_DBF_WARN("%s(%d) ap_card_create() failed\n",
 				    __func__, ap);
@@ -2101,13 +2097,13 @@ static inline void ap_scan_adapter(int ap)
 		get_device(dev);
 		if (decfg)
 			AP_DBF_INFO("%s(%d) new (decfg) card dev type=%d func=0x%08x created\n",
-				    __func__, ap, type, func);
+				    __func__, ap, hwinfo.at, hwinfo.fac);
 		else if (chkstop)
 			AP_DBF_INFO("%s(%d) new (chkstop) card dev type=%d func=0x%08x created\n",
-				    __func__, ap, type, func);
+				    __func__, ap, hwinfo.at, hwinfo.fac);
 		else
 			AP_DBF_INFO("%s(%d) new card dev type=%d func=0x%08x created\n",
-				    __func__, ap, type, func);
+				    __func__, ap, hwinfo.at, hwinfo.fac);
 	}
 
 	/* Verify the domains and the queue devices for this card */
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index b0771ca0849b..98814839ef30 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -76,16 +76,6 @@ static inline int ap_test_bit(unsigned int *ptr, unsigned int nr)
 #define AP_DEVICE_TYPE_CEX8	14
 
 /*
- * Known function facilities
- */
-#define AP_FUNC_MEX4K 1
-#define AP_FUNC_CRT4K 2
-#define AP_FUNC_COPRO 3
-#define AP_FUNC_ACCEL 4
-#define AP_FUNC_EP11  5
-#define AP_FUNC_APXA  6
-
-/*
  * AP queue state machine states
  */
 enum ap_sm_state {
@@ -182,9 +172,7 @@ struct ap_device {
 
 struct ap_card {
 	struct ap_device ap_dev;
-	int raw_hwtype;			/* AP raw hardware type. */
-	unsigned int functions;		/* TAPQ GR2 upper 32 facility bits */
-	int queue_depth;		/* AP queue depth.*/
+	struct ap_tapq_hwinfo hwinfo;	/* TAPQ GR2 content */
 	int id;				/* AP card number. */
 	unsigned int maxmsgsize;	/* AP msg limit for this card */
 	bool config;			/* configured state */
@@ -192,7 +180,7 @@ struct ap_card {
 	atomic64_t total_request_count;	/* # requests ever for this AP device.*/
 };
 
-#define TAPQ_CARD_FUNC_CMP_MASK 0xFFFF0000
+#define TAPQ_CARD_HWINFO_MASK 0xFEFF0000FFFF0F0FUL
 #define ASSOC_IDX_INVALID 0x10000
 
 #define to_ap_card(x) container_of((x), struct ap_card, ap_dev.device)
@@ -206,7 +194,7 @@ struct ap_queue {
 	bool config;			/* configured state */
 	bool chkstop;			/* checkstop state */
 	ap_qid_t qid;			/* AP queue id. */
-	bool se_bound;			/* SE bound state */
+	unsigned int se_bstate;		/* SE bind state (BS) */
 	unsigned int assoc_idx;		/* SE association index */
 	int queue_count;		/* # messages currently on AP queue. */
 	int pendingq_count;		/* # requests on pendingq list. */
@@ -290,8 +278,8 @@ void ap_queue_remove(struct ap_queue *aq);
 void ap_queue_init_state(struct ap_queue *aq);
 void _ap_queue_init_state(struct ap_queue *aq);
 
-struct ap_card *ap_card_create(int id, int queue_depth, int raw_type,
-			       int comp_type, unsigned int functions, int ml);
+struct ap_card *ap_card_create(int id, struct ap_tapq_hwinfo info,
+			       int comp_type);
 
 #define APMASKSIZE (BITS_TO_LONGS(AP_DEVICES) * sizeof(unsigned long))
 #define AQMASKSIZE (BITS_TO_LONGS(AP_DOMAINS) * sizeof(unsigned long))
diff --git a/drivers/s390/crypto/ap_card.c b/drivers/s390/crypto/ap_card.c
index b2bd477659a7..ce953cbbd564 100644
--- a/drivers/s390/crypto/ap_card.c
+++ b/drivers/s390/crypto/ap_card.c
@@ -34,7 +34,7 @@ static ssize_t raw_hwtype_show(struct device *dev,
 {
 	struct ap_card *ac = to_ap_card(dev);
 
-	return sysfs_emit(buf, "%d\n", ac->raw_hwtype);
+	return sysfs_emit(buf, "%d\n", ac->hwinfo.at);
 }
 
 static DEVICE_ATTR_RO(raw_hwtype);
@@ -44,7 +44,7 @@ static ssize_t depth_show(struct device *dev, struct device_attribute *attr,
 {
 	struct ap_card *ac = to_ap_card(dev);
 
-	return sysfs_emit(buf, "%d\n", ac->queue_depth);
+	return sysfs_emit(buf, "%d\n", ac->hwinfo.qd);
 }
 
 static DEVICE_ATTR_RO(depth);
@@ -54,7 +54,7 @@ static ssize_t ap_functions_show(struct device *dev,
 {
 	struct ap_card *ac = to_ap_card(dev);
 
-	return sysfs_emit(buf, "0x%08X\n", ac->functions);
+	return sysfs_emit(buf, "0x%08X\n", ac->hwinfo.fac);
 }
 
 static DEVICE_ATTR_RO(ap_functions);
@@ -229,8 +229,8 @@ static void ap_card_device_release(struct device *dev)
 	kfree(ac);
 }
 
-struct ap_card *ap_card_create(int id, int queue_depth, int raw_type,
-			       int comp_type, unsigned int functions, int ml)
+struct ap_card *ap_card_create(int id, struct ap_tapq_hwinfo hwinfo,
+			       int comp_type)
 {
 	struct ap_card *ac;
 
@@ -240,12 +240,10 @@ struct ap_card *ap_card_create(int id, int queue_depth, int raw_type,
 	ac->ap_dev.device.release = ap_card_device_release;
 	ac->ap_dev.device.type = &ap_card_type;
 	ac->ap_dev.device_type = comp_type;
-	ac->raw_hwtype = raw_type;
-	ac->queue_depth = queue_depth;
-	ac->functions = functions;
+	ac->hwinfo = hwinfo;
 	ac->id = id;
-	ac->maxmsgsize = ml > 0 ?
-		ml * AP_TAPQ_ML_FIELD_CHUNK_SIZE : AP_DEFAULT_MAX_MSG_SIZE;
+	ac->maxmsgsize = hwinfo.ml > 0 ?
+		hwinfo.ml * AP_TAPQ_ML_FIELD_CHUNK_SIZE : AP_DEFAULT_MAX_MSG_SIZE;
 
 	return ac;
 }
diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c
index 3934a0cc13e7..682595443145 100644
--- a/drivers/s390/crypto/ap_queue.c
+++ b/drivers/s390/crypto/ap_queue.c
@@ -24,13 +24,12 @@ static void __ap_flush_queue(struct ap_queue *aq);
 
 static inline bool ap_q_supports_bind(struct ap_queue *aq)
 {
-	return ap_test_bit(&aq->card->functions, AP_FUNC_EP11) ||
-		ap_test_bit(&aq->card->functions, AP_FUNC_ACCEL);
+	return aq->card->hwinfo.ep11 || aq->card->hwinfo.accel;
 }
 
 static inline bool ap_q_supports_assoc(struct ap_queue *aq)
 {
-	return ap_test_bit(&aq->card->functions, AP_FUNC_EP11);
+	return aq->card->hwinfo.ep11;
 }
 
 static inline bool ap_q_needs_bind(struct ap_queue *aq)
@@ -257,7 +256,7 @@ static enum ap_sm_wait ap_sm_write(struct ap_queue *aq)
 		list_move_tail(&ap_msg->list, &aq->pendingq);
 		aq->requestq_count--;
 		aq->pendingq_count++;
-		if (aq->queue_count < aq->card->queue_depth) {
+		if (aq->queue_count < aq->card->hwinfo.qd) {
 			aq->sm_state = AP_SM_STATE_WORKING;
 			return AP_SM_WAIT_AGAIN;
 		}
@@ -318,7 +317,6 @@ static enum ap_sm_wait ap_sm_reset(struct ap_queue *aq)
 	case AP_RESPONSE_RESET_IN_PROGRESS:
 		aq->sm_state = AP_SM_STATE_RESET_WAIT;
 		aq->rapq_fbit = 0;
-		aq->se_bound = false;
 		return AP_SM_WAIT_LOW_TIMEOUT;
 	default:
 		aq->dev_state = AP_DEV_STATE_ERROR;
@@ -339,17 +337,15 @@ static enum ap_sm_wait ap_sm_reset(struct ap_queue *aq)
 static enum ap_sm_wait ap_sm_reset_wait(struct ap_queue *aq)
 {
 	struct ap_queue_status status;
+	struct ap_tapq_hwinfo hwinfo;
 	void *lsi_ptr;
 
-	if (aq->queue_count > 0 && aq->reply)
-		/* Try to read a completed message and get the status */
-		status = ap_sm_recv(aq);
-	else
-		/* Get the status with TAPQ */
-		status = ap_tapq(aq->qid, NULL);
+	/* Get the status with TAPQ */
+	status = ap_test_queue(aq->qid, 1, &hwinfo);
 
 	switch (status.response_code) {
 	case AP_RESPONSE_NORMAL:
+		aq->se_bstate = hwinfo.bs;
 		lsi_ptr = ap_airq_ptr();
 		if (lsi_ptr && ap_queue_enable_irq(aq, lsi_ptr) == 0)
 			aq->sm_state = AP_SM_STATE_SETIRQ_WAIT;
@@ -421,9 +417,9 @@ static enum ap_sm_wait ap_sm_setirq_wait(struct ap_queue *aq)
 static enum ap_sm_wait ap_sm_assoc_wait(struct ap_queue *aq)
 {
 	struct ap_queue_status status;
-	struct ap_tapq_gr2 info;
+	struct ap_tapq_hwinfo hwinfo;
 
-	status = ap_test_queue(aq->qid, 1, &info);
+	status = ap_test_queue(aq->qid, 1, &hwinfo);
 	/* handle asynchronous error on this queue */
 	if (status.async && status.response_code) {
 		aq->dev_state = AP_DEV_STATE_ERROR;
@@ -442,8 +438,11 @@ static enum ap_sm_wait ap_sm_assoc_wait(struct ap_queue *aq)
 		return AP_SM_WAIT_NONE;
 	}
 
+	/* update queue's SE bind state */
+	aq->se_bstate = hwinfo.bs;
+
 	/* check bs bits */
-	switch (info.bs) {
+	switch (hwinfo.bs) {
 	case AP_BS_Q_USABLE:
 		/* association is through */
 		aq->sm_state = AP_SM_STATE_IDLE;
@@ -460,7 +459,7 @@ static enum ap_sm_wait ap_sm_assoc_wait(struct ap_queue *aq)
 		aq->dev_state = AP_DEV_STATE_ERROR;
 		aq->last_err_rc = status.response_code;
 		AP_DBF_WARN("%s bs 0x%02x on 0x%02x.%04x -> AP_DEV_STATE_ERROR\n",
-			    __func__, info.bs,
+			    __func__, hwinfo.bs,
 			    AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid));
 		return AP_SM_WAIT_NONE;
 	}
@@ -687,9 +686,9 @@ static ssize_t ap_functions_show(struct device *dev,
 {
 	struct ap_queue *aq = to_ap_queue(dev);
 	struct ap_queue_status status;
-	struct ap_tapq_gr2 info;
+	struct ap_tapq_hwinfo hwinfo;
 
-	status = ap_test_queue(aq->qid, 1, &info);
+	status = ap_test_queue(aq->qid, 1, &hwinfo);
 	if (status.response_code > AP_RESPONSE_BUSY) {
 		AP_DBF_DBG("%s RC 0x%02x on tapq(0x%02x.%04x)\n",
 			   __func__, status.response_code,
@@ -697,7 +696,7 @@ static ssize_t ap_functions_show(struct device *dev,
 		return -EIO;
 	}
 
-	return sysfs_emit(buf, "0x%08X\n", info.fac);
+	return sysfs_emit(buf, "0x%08X\n", hwinfo.fac);
 }
 
 static DEVICE_ATTR_RO(ap_functions);
@@ -840,19 +839,25 @@ static ssize_t se_bind_show(struct device *dev,
 {
 	struct ap_queue *aq = to_ap_queue(dev);
 	struct ap_queue_status status;
-	struct ap_tapq_gr2 info;
+	struct ap_tapq_hwinfo hwinfo;
 
 	if (!ap_q_supports_bind(aq))
 		return sysfs_emit(buf, "-\n");
 
-	status = ap_test_queue(aq->qid, 1, &info);
+	status = ap_test_queue(aq->qid, 1, &hwinfo);
 	if (status.response_code > AP_RESPONSE_BUSY) {
 		AP_DBF_DBG("%s RC 0x%02x on tapq(0x%02x.%04x)\n",
 			   __func__, status.response_code,
 			   AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid));
 		return -EIO;
 	}
-	switch (info.bs) {
+
+	/* update queue's SE bind state */
+	spin_lock_bh(&aq->lock);
+	aq->se_bstate = hwinfo.bs;
+	spin_unlock_bh(&aq->lock);
+
+	switch (hwinfo.bs) {
 	case AP_BS_Q_USABLE:
 	case AP_BS_Q_USABLE_NO_SECURE_KEY:
 		return sysfs_emit(buf, "bound\n");
@@ -867,6 +872,7 @@ static ssize_t se_bind_store(struct device *dev,
 {
 	struct ap_queue *aq = to_ap_queue(dev);
 	struct ap_queue_status status;
+	struct ap_tapq_hwinfo hwinfo;
 	bool value;
 	int rc;
 
@@ -878,39 +884,80 @@ static ssize_t se_bind_store(struct device *dev,
 	if (rc)
 		return rc;
 
-	if (value) {
-		/* bind, do BAPQ */
-		spin_lock_bh(&aq->lock);
-		if (aq->sm_state < AP_SM_STATE_IDLE) {
-			spin_unlock_bh(&aq->lock);
-			return -EBUSY;
-		}
-		status = ap_bapq(aq->qid);
-		spin_unlock_bh(&aq->lock);
-		if (!status.response_code) {
-			aq->se_bound = true;
-			AP_DBF_INFO("%s bapq(0x%02x.%04x) success\n", __func__,
-				    AP_QID_CARD(aq->qid),
-				    AP_QID_QUEUE(aq->qid));
-		} else {
-			AP_DBF_WARN("%s RC 0x%02x on bapq(0x%02x.%04x)\n",
-				    __func__, status.response_code,
-				    AP_QID_CARD(aq->qid),
-				    AP_QID_QUEUE(aq->qid));
-			return -EIO;
-		}
-	} else {
-		/* unbind, set F bit arg and trigger RAPQ */
+	if (!value) {
+		/* Unbind. Set F bit arg and trigger RAPQ */
 		spin_lock_bh(&aq->lock);
 		__ap_flush_queue(aq);
 		aq->rapq_fbit = 1;
-		aq->assoc_idx = ASSOC_IDX_INVALID;
-		aq->sm_state = AP_SM_STATE_RESET_START;
-		ap_wait(ap_sm_event(aq, AP_SM_EVENT_POLL));
-		spin_unlock_bh(&aq->lock);
+		_ap_queue_init_state(aq);
+		rc = count;
+		goto out;
 	}
 
-	return count;
+	/* Bind. Check current SE bind state */
+	status = ap_test_queue(aq->qid, 1, &hwinfo);
+	if (status.response_code) {
+		AP_DBF_WARN("%s RC 0x%02x on tapq(0x%02x.%04x)\n",
+			    __func__, status.response_code,
+			    AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid));
+		return -EIO;
+	}
+
+	/* Update BS state */
+	spin_lock_bh(&aq->lock);
+	aq->se_bstate = hwinfo.bs;
+	if (hwinfo.bs != AP_BS_Q_AVAIL_FOR_BINDING) {
+		AP_DBF_WARN("%s bind attempt with bs %d on queue 0x%02x.%04x\n",
+			    __func__, hwinfo.bs,
+			    AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid));
+		rc = -EINVAL;
+		goto out;
+	}
+
+	/* Check SM state */
+	if (aq->sm_state < AP_SM_STATE_IDLE) {
+		rc = -EBUSY;
+		goto out;
+	}
+
+	/* invoke BAPQ */
+	status = ap_bapq(aq->qid);
+	if (status.response_code) {
+		AP_DBF_WARN("%s RC 0x%02x on bapq(0x%02x.%04x)\n",
+			    __func__, status.response_code,
+			    AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid));
+		rc = -EIO;
+		goto out;
+	}
+	aq->assoc_idx = ASSOC_IDX_INVALID;
+
+	/* verify SE bind state */
+	status = ap_test_queue(aq->qid, 1, &hwinfo);
+	if (status.response_code) {
+		AP_DBF_WARN("%s RC 0x%02x on tapq(0x%02x.%04x)\n",
+			    __func__, status.response_code,
+			    AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid));
+		rc = -EIO;
+		goto out;
+	}
+	aq->se_bstate = hwinfo.bs;
+	if (!(hwinfo.bs == AP_BS_Q_USABLE ||
+	      hwinfo.bs == AP_BS_Q_USABLE_NO_SECURE_KEY)) {
+		AP_DBF_WARN("%s BAPQ success, but bs shows %d on queue 0x%02x.%04x\n",
+			    __func__, hwinfo.bs,
+			    AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid));
+		rc = -EIO;
+		goto out;
+	}
+
+	/* SE bind was successful */
+	AP_DBF_INFO("%s bapq(0x%02x.%04x) success\n", __func__,
+		    AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid));
+	rc = count;
+
+out:
+	spin_unlock_bh(&aq->lock);
+	return rc;
 }
 
 static DEVICE_ATTR_RW(se_bind);
@@ -920,12 +967,12 @@ static ssize_t se_associate_show(struct device *dev,
 {
 	struct ap_queue *aq = to_ap_queue(dev);
 	struct ap_queue_status status;
-	struct ap_tapq_gr2 info;
+	struct ap_tapq_hwinfo hwinfo;
 
 	if (!ap_q_supports_assoc(aq))
 		return sysfs_emit(buf, "-\n");
 
-	status = ap_test_queue(aq->qid, 1, &info);
+	status = ap_test_queue(aq->qid, 1, &hwinfo);
 	if (status.response_code > AP_RESPONSE_BUSY) {
 		AP_DBF_DBG("%s RC 0x%02x on tapq(0x%02x.%04x)\n",
 			   __func__, status.response_code,
@@ -933,7 +980,12 @@ static ssize_t se_associate_show(struct device *dev,
 		return -EIO;
 	}
 
-	switch (info.bs) {
+	/* update queue's SE bind state */
+	spin_lock_bh(&aq->lock);
+	aq->se_bstate = hwinfo.bs;
+	spin_unlock_bh(&aq->lock);
+
+	switch (hwinfo.bs) {
 	case AP_BS_Q_USABLE:
 		if (aq->assoc_idx == ASSOC_IDX_INVALID) {
 			AP_DBF_WARN("%s AP_BS_Q_USABLE but invalid assoc_idx\n", __func__);
@@ -955,6 +1007,7 @@ static ssize_t se_associate_store(struct device *dev,
 {
 	struct ap_queue *aq = to_ap_queue(dev);
 	struct ap_queue_status status;
+	struct ap_tapq_hwinfo hwinfo;
 	unsigned int value;
 	int rc;
 
@@ -968,18 +1021,28 @@ static ssize_t se_associate_store(struct device *dev,
 	if (value >= ASSOC_IDX_INVALID)
 		return -EINVAL;
 
+	/* check current SE bind state */
+	status = ap_test_queue(aq->qid, 1, &hwinfo);
+	if (status.response_code) {
+		AP_DBF_WARN("%s RC 0x%02x on tapq(0x%02x.%04x)\n",
+			    __func__, status.response_code,
+			    AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid));
+		return -EIO;
+	}
 	spin_lock_bh(&aq->lock);
-
-	/* sm should be in idle state */
-	if (aq->sm_state != AP_SM_STATE_IDLE) {
-		spin_unlock_bh(&aq->lock);
-		return -EBUSY;
+	aq->se_bstate = hwinfo.bs;
+	if (hwinfo.bs != AP_BS_Q_USABLE_NO_SECURE_KEY) {
+		AP_DBF_WARN("%s association attempt with bs %d on queue 0x%02x.%04x\n",
+			    __func__, hwinfo.bs,
+			    AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid));
+		rc = -EINVAL;
+		goto out;
 	}
 
-	/* already associated or association pending ? */
-	if (aq->assoc_idx != ASSOC_IDX_INVALID) {
-		spin_unlock_bh(&aq->lock);
-		return -EINVAL;
+	/* check SM state */
+	if (aq->sm_state != AP_SM_STATE_IDLE) {
+		rc = -EBUSY;
+		goto out;
 	}
 
 	/* trigger the asynchronous association request */
@@ -990,17 +1053,20 @@ static ssize_t se_associate_store(struct device *dev,
 		aq->sm_state = AP_SM_STATE_ASSOC_WAIT;
 		aq->assoc_idx = value;
 		ap_wait(ap_sm_event(aq, AP_SM_EVENT_POLL));
-		spin_unlock_bh(&aq->lock);
 		break;
 	default:
-		spin_unlock_bh(&aq->lock);
 		AP_DBF_WARN("%s RC 0x%02x on aapq(0x%02x.%04x)\n",
 			    __func__, status.response_code,
 			    AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid));
-		return -EIO;
+		rc = -EIO;
+		goto out;
 	}
 
-	return count;
+	rc = count;
+
+out:
+	spin_unlock_bh(&aq->lock);
+	return rc;
 }
 
 static DEVICE_ATTR_RW(se_associate);
@@ -1123,7 +1189,9 @@ bool ap_queue_usable(struct ap_queue *aq)
 	}
 
 	/* SE guest's queues additionally need to be bound */
-	if (ap_q_needs_bind(aq) && !aq->se_bound)
+	if (ap_q_needs_bind(aq) &&
+	    !(aq->se_bstate == AP_BS_Q_USABLE ||
+	      aq->se_bstate == AP_BS_Q_USABLE_NO_SECURE_KEY))
 		rc = false;
 
 unlock_and_out:
diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index 4db538a55192..acb710d3d7bc 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -393,8 +393,8 @@ static int ensure_nib_shared(unsigned long addr, struct gmap *gmap)
  * Register the guest ISC to GIB interface and retrieve the
  * host ISC to issue the host side PQAP/AQIC
  *
- * Response.status may be set to AP_RESPONSE_INVALID_ADDRESS in case the
- * vfio_pin_pages failed.
+ * status.response_code may be set to AP_RESPONSE_INVALID_ADDRESS in case the
+ * vfio_pin_pages or kvm_s390_gisc_register failed.
  *
  * Otherwise return the ap_queue_status returned by the ap_aqic(),
  * all retry handling will be done by the guest.
@@ -457,7 +457,8 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q,
 		VFIO_AP_DBF_WARN("%s: gisc registration failed: nisc=%d, isc=%d, apqn=%#04x\n",
 				 __func__, nisc, isc, q->apqn);
 
-		status.response_code = AP_RESPONSE_INVALID_GISA;
+		vfio_unpin_pages(&q->matrix_mdev->vdev, nib, 1);
+		status.response_code = AP_RESPONSE_INVALID_ADDRESS;
 		return status;
 	}
 
@@ -475,8 +476,11 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q,
 		break;
 	case AP_RESPONSE_OTHERWISE_CHANGED:
 		/* We could not modify IRQ settings: clear new configuration */
+		ret = kvm_s390_gisc_unregister(kvm, isc);
+		if (ret)
+			VFIO_AP_DBF_WARN("%s: kvm_s390_gisc_unregister: rc=%d isc=%d, apqn=%#04x\n",
+					 __func__, ret, isc, q->apqn);
 		vfio_unpin_pages(&q->matrix_mdev->vdev, nib, 1);
-		kvm_s390_gisc_unregister(kvm, isc);
 		break;
 	default:
 		pr_warn("%s: apqn %04x: response: %02x\n", __func__, q->apqn,
@@ -1794,7 +1798,7 @@ static void vfio_ap_mdev_request(struct vfio_device *vdev, unsigned int count)
 					       "Relaying device request to user (#%u)\n",
 					       count);
 
-		eventfd_signal(matrix_mdev->req_trigger, 1);
+		eventfd_signal(matrix_mdev->req_trigger);
 	} else if (count == 0) {
 		dev_notice(dev,
 			   "No device request registered, blocked until released by user\n");
@@ -1976,6 +1980,7 @@ static ssize_t status_show(struct device *dev,
 {
 	ssize_t nchars = 0;
 	struct vfio_ap_queue *q;
+	unsigned long apid, apqi;
 	struct ap_matrix_mdev *matrix_mdev;
 	struct ap_device *apdev = to_ap_dev(dev);
 
@@ -1983,8 +1988,21 @@ static ssize_t status_show(struct device *dev,
 	q = dev_get_drvdata(&apdev->device);
 	matrix_mdev = vfio_ap_mdev_for_queue(q);
 
+	/* If the queue is assigned to the matrix mediated device, then
+	 * determine whether it is passed through to a guest; otherwise,
+	 * indicate that it is unassigned.
+	 */
 	if (matrix_mdev) {
-		if (matrix_mdev->kvm)
+		apid = AP_QID_CARD(q->apqn);
+		apqi = AP_QID_QUEUE(q->apqn);
+		/*
+		 * If the queue is passed through to the guest, then indicate
+		 * that it is in use; otherwise, indicate that it is
+		 * merely assigned to a matrix mediated device.
+		 */
+		if (matrix_mdev->kvm &&
+		    test_bit_inv(apid, matrix_mdev->shadow_apcb.apm) &&
+		    test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm))
 			nchars = scnprintf(buf, PAGE_SIZE, "%s\n",
 					   AP_QUEUE_IN_USE);
 		else
@@ -2297,7 +2315,7 @@ static void vfio_ap_filter_apid_by_qtype(unsigned long *apm, unsigned long *aqm)
 	bool apid_cleared;
 	struct ap_queue_status status;
 	unsigned long apid, apqi;
-	struct ap_tapq_gr2 info;
+	struct ap_tapq_hwinfo info;
 
 	for_each_set_bit_inv(apid, apm, AP_DEVICES) {
 		apid_cleared = false;
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index dcd6c7299fa9..74200f54dfff 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -673,7 +673,7 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms,
 	for_each_zcrypt_card(zc) {
 		/* Check for usable accelerator or CCA card */
 		if (!zc->online || !zc->card->config || zc->card->chkstop ||
-		    !(zc->card->functions & 0x18000000))
+		    !(zc->card->hwinfo.accel || zc->card->hwinfo.cca))
 			continue;
 		/* Check for size limits */
 		if (zc->min_mod_size > mex->inputdatalength ||
@@ -778,7 +778,7 @@ static long zcrypt_rsa_crt(struct ap_perms *perms,
 	for_each_zcrypt_card(zc) {
 		/* Check for usable accelerator or CCA card */
 		if (!zc->online || !zc->card->config || zc->card->chkstop ||
-		    !(zc->card->functions & 0x18000000))
+		    !(zc->card->hwinfo.accel || zc->card->hwinfo.cca))
 			continue;
 		/* Check for size limits */
 		if (zc->min_mod_size > crt->inputdatalength ||
@@ -893,7 +893,7 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms,
 	for_each_zcrypt_card(zc) {
 		/* Check for usable CCA card */
 		if (!zc->online || !zc->card->config || zc->card->chkstop ||
-		    !(zc->card->functions & 0x10000000))
+		    !zc->card->hwinfo.cca)
 			continue;
 		/* Check for user selected CCA card */
 		if (xcrb->user_defined != AUTOSELECT &&
@@ -1064,7 +1064,7 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms,
 	for_each_zcrypt_card(zc) {
 		/* Check for usable EP11 card */
 		if (!zc->online || !zc->card->config || zc->card->chkstop ||
-		    !(zc->card->functions & 0x04000000))
+		    !zc->card->hwinfo.ep11)
 			continue;
 		/* Check for user selected EP11 card */
 		if (targets &&
@@ -1177,7 +1177,7 @@ static long zcrypt_rng(char *buffer)
 	for_each_zcrypt_card(zc) {
 		/* Check for usable CCA card */
 		if (!zc->online || !zc->card->config || zc->card->chkstop ||
-		    !(zc->card->functions & 0x10000000))
+		    !zc->card->hwinfo.cca)
 			continue;
 		/* get weight index of the card device	*/
 		wgt = zc->speed_rating[func_code];
@@ -1238,7 +1238,7 @@ static void zcrypt_device_status_mask(struct zcrypt_device_status *devstatus)
 			queue = AP_QID_QUEUE(zq->queue->qid);
 			stat = &devstatus[card * AP_DOMAINS + queue];
 			stat->hwtype = zc->card->ap_dev.device_type;
-			stat->functions = zc->card->functions >> 26;
+			stat->functions = zc->card->hwinfo.fac >> 26;
 			stat->qid = zq->queue->qid;
 			stat->online = zq->online ? 0x01 : 0x00;
 		}
@@ -1263,7 +1263,7 @@ void zcrypt_device_status_mask_ext(struct zcrypt_device_status_ext *devstatus)
 			queue = AP_QID_QUEUE(zq->queue->qid);
 			stat = &devstatus[card * AP_DOMAINS + queue];
 			stat->hwtype = zc->card->ap_dev.device_type;
-			stat->functions = zc->card->functions >> 26;
+			stat->functions = zc->card->hwinfo.fac >> 26;
 			stat->qid = zq->queue->qid;
 			stat->online = zq->online ? 0x01 : 0x00;
 		}
@@ -1286,7 +1286,7 @@ int zcrypt_device_status_ext(int card, int queue,
 			if (card == AP_QID_CARD(zq->queue->qid) &&
 			    queue == AP_QID_QUEUE(zq->queue->qid)) {
 				devstat->hwtype = zc->card->ap_dev.device_type;
-				devstat->functions = zc->card->functions >> 26;
+				devstat->functions = zc->card->hwinfo.fac >> 26;
 				devstat->qid = zq->queue->qid;
 				devstat->online = zq->online ? 0x01 : 0x00;
 				spin_unlock(&zcrypt_list_lock);
diff --git a/drivers/s390/crypto/zcrypt_cex4.c b/drivers/s390/crypto/zcrypt_cex4.c
index 5c4532ab0040..64df7d2f6266 100644
--- a/drivers/s390/crypto/zcrypt_cex4.c
+++ b/drivers/s390/crypto/zcrypt_cex4.c
@@ -477,7 +477,7 @@ static int zcrypt_cex4_card_probe(struct ap_device *ap_dev)
 		return -ENOMEM;
 	zc->card = ac;
 	dev_set_drvdata(&ap_dev->device, zc);
-	if (ap_test_bit(&ac->functions, AP_FUNC_ACCEL)) {
+	if (ac->hwinfo.accel) {
 		if (ac->ap_dev.device_type == AP_DEVICE_TYPE_CEX4) {
 			zc->type_string = "CEX4A";
 			zc->user_space_type = ZCRYPT_CEX4;
@@ -506,8 +506,7 @@ static int zcrypt_cex4_card_probe(struct ap_device *ap_dev)
 			zc->user_space_type = ZCRYPT_CEX6;
 		}
 		zc->min_mod_size = CEX4A_MIN_MOD_SIZE;
-		if (ap_test_bit(&ac->functions, AP_FUNC_MEX4K) &&
-		    ap_test_bit(&ac->functions, AP_FUNC_CRT4K)) {
+		if (ac->hwinfo.mex4k && ac->hwinfo.crt4k) {
 			zc->max_mod_size = CEX4A_MAX_MOD_SIZE_4K;
 			zc->max_exp_bit_length =
 				CEX4A_MAX_MOD_SIZE_4K;
@@ -516,7 +515,7 @@ static int zcrypt_cex4_card_probe(struct ap_device *ap_dev)
 			zc->max_exp_bit_length =
 				CEX4A_MAX_MOD_SIZE_2K;
 		}
-	} else if (ap_test_bit(&ac->functions, AP_FUNC_COPRO)) {
+	} else if (ac->hwinfo.cca) {
 		if (ac->ap_dev.device_type == AP_DEVICE_TYPE_CEX4) {
 			zc->type_string = "CEX4C";
 			zc->speed_rating = CEX4C_SPEED_IDX;
@@ -556,7 +555,7 @@ static int zcrypt_cex4_card_probe(struct ap_device *ap_dev)
 		zc->min_mod_size = CEX4C_MIN_MOD_SIZE;
 		zc->max_mod_size = CEX4C_MAX_MOD_SIZE;
 		zc->max_exp_bit_length = CEX4C_MAX_MOD_SIZE;
-	} else if (ap_test_bit(&ac->functions, AP_FUNC_EP11)) {
+	} else if (ac->hwinfo.ep11) {
 		if (ac->ap_dev.device_type == AP_DEVICE_TYPE_CEX4) {
 			zc->type_string = "CEX4P";
 			zc->user_space_type = ZCRYPT_CEX4;
@@ -599,14 +598,14 @@ static int zcrypt_cex4_card_probe(struct ap_device *ap_dev)
 		return rc;
 	}
 
-	if (ap_test_bit(&ac->functions, AP_FUNC_COPRO)) {
+	if (ac->hwinfo.cca) {
 		rc = sysfs_create_group(&ap_dev->device.kobj,
 					&cca_card_attr_grp);
 		if (rc) {
 			zcrypt_card_unregister(zc);
 			zcrypt_card_free(zc);
 		}
-	} else if (ap_test_bit(&ac->functions, AP_FUNC_EP11)) {
+	} else if (ac->hwinfo.ep11) {
 		rc = sysfs_create_group(&ap_dev->device.kobj,
 					&ep11_card_attr_grp);
 		if (rc) {
@@ -627,9 +626,9 @@ static void zcrypt_cex4_card_remove(struct ap_device *ap_dev)
 	struct zcrypt_card *zc = dev_get_drvdata(&ap_dev->device);
 	struct ap_card *ac = to_ap_card(&ap_dev->device);
 
-	if (ap_test_bit(&ac->functions, AP_FUNC_COPRO))
+	if (ac->hwinfo.cca)
 		sysfs_remove_group(&ap_dev->device.kobj, &cca_card_attr_grp);
-	else if (ap_test_bit(&ac->functions, AP_FUNC_EP11))
+	else if (ac->hwinfo.ep11)
 		sysfs_remove_group(&ap_dev->device.kobj, &ep11_card_attr_grp);
 
 	zcrypt_card_unregister(zc);
@@ -654,19 +653,19 @@ static int zcrypt_cex4_queue_probe(struct ap_device *ap_dev)
 	struct zcrypt_queue *zq;
 	int rc;
 
-	if (ap_test_bit(&aq->card->functions, AP_FUNC_ACCEL)) {
+	if (aq->card->hwinfo.accel) {
 		zq = zcrypt_queue_alloc(aq->card->maxmsgsize);
 		if (!zq)
 			return -ENOMEM;
 		zq->ops = zcrypt_msgtype(MSGTYPE50_NAME,
 					 MSGTYPE50_VARIANT_DEFAULT);
-	} else if (ap_test_bit(&aq->card->functions, AP_FUNC_COPRO)) {
+	} else if (aq->card->hwinfo.cca) {
 		zq = zcrypt_queue_alloc(aq->card->maxmsgsize);
 		if (!zq)
 			return -ENOMEM;
 		zq->ops = zcrypt_msgtype(MSGTYPE06_NAME,
 					 MSGTYPE06_VARIANT_DEFAULT);
-	} else if (ap_test_bit(&aq->card->functions, AP_FUNC_EP11)) {
+	} else if (aq->card->hwinfo.ep11) {
 		zq = zcrypt_queue_alloc(aq->card->maxmsgsize);
 		if (!zq)
 			return -ENOMEM;
@@ -689,14 +688,14 @@ static int zcrypt_cex4_queue_probe(struct ap_device *ap_dev)
 		return rc;
 	}
 
-	if (ap_test_bit(&aq->card->functions, AP_FUNC_COPRO)) {
+	if (aq->card->hwinfo.cca) {
 		rc = sysfs_create_group(&ap_dev->device.kobj,
 					&cca_queue_attr_grp);
 		if (rc) {
 			zcrypt_queue_unregister(zq);
 			zcrypt_queue_free(zq);
 		}
-	} else if (ap_test_bit(&aq->card->functions, AP_FUNC_EP11)) {
+	} else if (aq->card->hwinfo.ep11) {
 		rc = sysfs_create_group(&ap_dev->device.kobj,
 					&ep11_queue_attr_grp);
 		if (rc) {
@@ -717,9 +716,9 @@ static void zcrypt_cex4_queue_remove(struct ap_device *ap_dev)
 	struct zcrypt_queue *zq = dev_get_drvdata(&ap_dev->device);
 	struct ap_queue *aq = to_ap_queue(&ap_dev->device);
 
-	if (ap_test_bit(&aq->card->functions, AP_FUNC_COPRO))
+	if (aq->card->hwinfo.cca)
 		sysfs_remove_group(&ap_dev->device.kobj, &cca_queue_attr_grp);
-	else if (ap_test_bit(&aq->card->functions, AP_FUNC_EP11))
+	else if (aq->card->hwinfo.ep11)
 		sysfs_remove_group(&ap_dev->device.kobj, &ep11_queue_attr_grp);
 
 	zcrypt_queue_unregister(zq);
diff --git a/drivers/s390/net/Kconfig b/drivers/s390/net/Kconfig
index 4902d45e929c..c61e6427384c 100644
--- a/drivers/s390/net/Kconfig
+++ b/drivers/s390/net/Kconfig
@@ -103,10 +103,11 @@ config CCWGROUP
 config ISM
 	tristate "Support for ISM vPCI Adapter"
 	depends on PCI
+	imply SMC
 	default n
 	help
 	  Select this option if you want to use the Internal Shared Memory
-	  vPCI Adapter.
+	  vPCI Adapter. The adapter can be used with the SMC network protocol.
 
 	  To compile as a module choose M. The module name is ism.
 	  If unsure, choose N.
diff --git a/drivers/s390/net/ism.h b/drivers/s390/net/ism.h
index 70c5bbda0fea..047fa6101555 100644
--- a/drivers/s390/net/ism.h
+++ b/drivers/s390/net/ism.h
@@ -16,7 +16,6 @@
  */
 #define ISM_DMB_WORD_OFFSET	1
 #define ISM_DMB_BIT_OFFSET	(ISM_DMB_WORD_OFFSET * 32)
-#define ISM_IDENT_MASK		0x00FFFF
 
 #define ISM_REG_SBA	0x1
 #define ISM_REG_IEQ	0x2
@@ -192,12 +191,6 @@ struct ism_sba {
 #define ISM_CREATE_REQ(dmb, idx, sf, offset)		\
 	((dmb) | (idx) << 24 | (sf) << 23 | (offset))
 
-struct ism_systemeid {
-	u8	seid_string[24];
-	u8	serial_number[4];
-	u8	type[4];
-};
-
 static inline void __ism_read_cmd(struct ism_dev *ism, void *data,
 				  unsigned long offset, unsigned long len)
 {
diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c
index 6df7f377d2f9..2c8e964425dc 100644
--- a/drivers/s390/net/ism_drv.c
+++ b/drivers/s390/net/ism_drv.c
@@ -30,13 +30,13 @@ static const struct pci_device_id ism_device_table[] = {
 MODULE_DEVICE_TABLE(pci, ism_device_table);
 
 static debug_info_t *ism_debug_info;
-static const struct smcd_ops ism_ops;
 
 #define NO_CLIENT		0xff		/* must be >= MAX_CLIENTS */
 static struct ism_client *clients[MAX_CLIENTS];	/* use an array rather than */
 						/* a list for fast mapping  */
 static u8 max_client;
 static DEFINE_MUTEX(clients_lock);
+static bool ism_v2_capable;
 struct ism_dev_list {
 	struct list_head list;
 	struct mutex mutex; /* protects ism device list */
@@ -289,22 +289,6 @@ out:
 	return ret;
 }
 
-static int ism_query_rgid(struct ism_dev *ism, u64 rgid, u32 vid_valid,
-			  u32 vid)
-{
-	union ism_query_rgid cmd;
-
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.request.hdr.cmd = ISM_QUERY_RGID;
-	cmd.request.hdr.len = sizeof(cmd.request);
-
-	cmd.request.rgid = rgid;
-	cmd.request.vlan_valid = vid_valid;
-	cmd.request.vlan_id = vid;
-
-	return ism_cmd(ism, &cmd);
-}
-
 static void ism_free_dmb(struct ism_dev *ism, struct ism_dmb *dmb)
 {
 	clear_bit(dmb->sba_idx, ism->sba_bitmap);
@@ -429,23 +413,6 @@ static int ism_del_vlan_id(struct ism_dev *ism, u64 vlan_id)
 	return ism_cmd(ism, &cmd);
 }
 
-static int ism_signal_ieq(struct ism_dev *ism, u64 rgid, u32 trigger_irq,
-			  u32 event_code, u64 info)
-{
-	union ism_sig_ieq cmd;
-
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.request.hdr.cmd = ISM_SIGNAL_IEQ;
-	cmd.request.hdr.len = sizeof(cmd.request);
-
-	cmd.request.rgid = rgid;
-	cmd.request.trigger_irq = trigger_irq;
-	cmd.request.event_code = event_code;
-	cmd.request.info = info;
-
-	return ism_cmd(ism, &cmd);
-}
-
 static unsigned int max_bytes(unsigned int start, unsigned int len,
 			      unsigned int boundary)
 {
@@ -477,40 +444,6 @@ int ism_move(struct ism_dev *ism, u64 dmb_tok, unsigned int idx, bool sf,
 }
 EXPORT_SYMBOL_GPL(ism_move);
 
-static struct ism_systemeid SYSTEM_EID = {
-	.seid_string = "IBM-SYSZ-ISMSEID00000000",
-	.serial_number = "0000",
-	.type = "0000",
-};
-
-static void ism_create_system_eid(void)
-{
-	struct cpuid id;
-	u16 ident_tail;
-	char tmp[5];
-
-	get_cpu_id(&id);
-	ident_tail = (u16)(id.ident & ISM_IDENT_MASK);
-	snprintf(tmp, 5, "%04X", ident_tail);
-	memcpy(&SYSTEM_EID.serial_number, tmp, 4);
-	snprintf(tmp, 5, "%04X", id.machine);
-	memcpy(&SYSTEM_EID.type, tmp, 4);
-}
-
-u8 *ism_get_seid(void)
-{
-	return SYSTEM_EID.seid_string;
-}
-EXPORT_SYMBOL_GPL(ism_get_seid);
-
-static u16 ism_get_chid(struct ism_dev *ism)
-{
-	if (!ism || !ism->pdev)
-		return 0;
-
-	return to_zpci(ism->pdev)->pchid;
-}
-
 static void ism_handle_event(struct ism_dev *ism)
 {
 	struct ism_event *entry;
@@ -569,11 +502,6 @@ static irqreturn_t ism_handle_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static u64 ism_get_local_gid(struct ism_dev *ism)
-{
-	return ism->local_gid;
-}
-
 static int ism_dev_init(struct ism_dev *ism)
 {
 	struct pci_dev *pdev = ism->pdev;
@@ -607,7 +535,9 @@ static int ism_dev_init(struct ism_dev *ism)
 
 	if (!ism_add_vlan_id(ism, ISM_RESERVED_VLANID))
 		/* hardware is V2 capable */
-		ism_create_system_eid();
+		ism_v2_capable = true;
+	else
+		ism_v2_capable = false;
 
 	mutex_lock(&ism_dev_list.mutex);
 	mutex_lock(&clients_lock);
@@ -712,8 +642,7 @@ static void ism_dev_exit(struct ism_dev *ism)
 	}
 	mutex_unlock(&clients_lock);
 
-	if (SYSTEM_EID.serial_number[0] != '0' ||
-	    SYSTEM_EID.type[0] != '0')
+	if (ism_v2_capable)
 		ism_del_vlan_id(ism, ISM_RESERVED_VLANID);
 	unregister_ieq(ism);
 	unregister_sba(ism);
@@ -774,10 +703,26 @@ module_exit(ism_exit);
 /*************************** SMC-D Implementation *****************************/
 
 #if IS_ENABLED(CONFIG_SMC)
-static int smcd_query_rgid(struct smcd_dev *smcd, u64 rgid, u32 vid_valid,
-			   u32 vid)
+static int ism_query_rgid(struct ism_dev *ism, u64 rgid, u32 vid_valid,
+			  u32 vid)
 {
-	return ism_query_rgid(smcd->priv, rgid, vid_valid, vid);
+	union ism_query_rgid cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_QUERY_RGID;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	cmd.request.rgid = rgid;
+	cmd.request.vlan_valid = vid_valid;
+	cmd.request.vlan_id = vid;
+
+	return ism_cmd(ism, &cmd);
+}
+
+static int smcd_query_rgid(struct smcd_dev *smcd, struct smcd_gid *rgid,
+			   u32 vid_valid, u32 vid)
+{
+	return ism_query_rgid(smcd->priv, rgid->gid, vid_valid, vid);
 }
 
 static int smcd_register_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb,
@@ -811,10 +756,28 @@ static int smcd_reset_vlan_required(struct smcd_dev *smcd)
 	return ism_cmd_simple(smcd->priv, ISM_RESET_VLAN);
 }
 
-static int smcd_signal_ieq(struct smcd_dev *smcd, u64 rgid, u32 trigger_irq,
-			   u32 event_code, u64 info)
+static int ism_signal_ieq(struct ism_dev *ism, u64 rgid, u32 trigger_irq,
+			  u32 event_code, u64 info)
+{
+	union ism_sig_ieq cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_SIGNAL_IEQ;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	cmd.request.rgid = rgid;
+	cmd.request.trigger_irq = trigger_irq;
+	cmd.request.event_code = event_code;
+	cmd.request.info = info;
+
+	return ism_cmd(ism, &cmd);
+}
+
+static int smcd_signal_ieq(struct smcd_dev *smcd, struct smcd_gid *rgid,
+			   u32 trigger_irq, u32 event_code, u64 info)
 {
-	return ism_signal_ieq(smcd->priv, rgid, trigger_irq, event_code, info);
+	return ism_signal_ieq(smcd->priv, rgid->gid,
+			      trigger_irq, event_code, info);
 }
 
 static int smcd_move(struct smcd_dev *smcd, u64 dmb_tok, unsigned int idx,
@@ -826,13 +789,27 @@ static int smcd_move(struct smcd_dev *smcd, u64 dmb_tok, unsigned int idx,
 
 static int smcd_supports_v2(void)
 {
-	return SYSTEM_EID.serial_number[0] != '0' ||
-		SYSTEM_EID.type[0] != '0';
+	return ism_v2_capable;
 }
 
-static u64 smcd_get_local_gid(struct smcd_dev *smcd)
+static u64 ism_get_local_gid(struct ism_dev *ism)
 {
-	return ism_get_local_gid(smcd->priv);
+	return ism->local_gid;
+}
+
+static void smcd_get_local_gid(struct smcd_dev *smcd,
+			       struct smcd_gid *smcd_gid)
+{
+	smcd_gid->gid = ism_get_local_gid(smcd->priv);
+	smcd_gid->gid_ext = 0;
+}
+
+static u16 ism_get_chid(struct ism_dev *ism)
+{
+	if (!ism || !ism->pdev)
+		return 0;
+
+	return to_zpci(ism->pdev)->pchid;
 }
 
 static u16 smcd_get_chid(struct smcd_dev *smcd)
@@ -858,7 +835,6 @@ static const struct smcd_ops ism_ops = {
 	.signal_event = smcd_signal_ieq,
 	.move_data = smcd_move,
 	.supports_v2 = smcd_supports_v2,
-	.get_system_eid = ism_get_seid,
 	.get_local_gid = smcd_get_local_gid,
 	.get_chid = smcd_get_chid,
 	.get_dev = smcd_get_dev,
diff --git a/drivers/s390/scsi/zfcp_fc.c b/drivers/s390/scsi/zfcp_fc.c
index 4f0d0e55f0d4..d6516ab00437 100644
--- a/drivers/s390/scsi/zfcp_fc.c
+++ b/drivers/s390/scsi/zfcp_fc.c
@@ -900,8 +900,19 @@ static void zfcp_fc_rspn(struct zfcp_adapter *adapter,
 	zfcp_fc_ct_ns_init(&rspn_req->ct_hdr, FC_NS_RSPN_ID,
 			   FC_SYMBOLIC_NAME_SIZE);
 	hton24(rspn_req->rspn.fr_fid.fp_fid, fc_host_port_id(shost));
-	len = strlcpy(rspn_req->rspn.fr_name, fc_host_symbolic_name(shost),
-		      FC_SYMBOLIC_NAME_SIZE);
+
+	BUILD_BUG_ON(sizeof(rspn_req->name) !=
+			sizeof(fc_host_symbolic_name(shost)));
+	BUILD_BUG_ON(sizeof(rspn_req->name) !=
+			type_max(typeof(rspn_req->rspn.fr_name_len)) + 1);
+	len = strscpy(rspn_req->name, fc_host_symbolic_name(shost),
+		      sizeof(rspn_req->name));
+	/*
+	 * It should be impossible for this to truncate (see BUILD_BUG_ON()
+	 * above), but be robust anyway.
+	 */
+	if (WARN_ON(len < 0))
+		len = sizeof(rspn_req->name) - 1;
 	rspn_req->rspn.fr_name_len = len;
 
 	sg_init_one(&fc_req->sg_req, rspn_req, sizeof(*rspn_req));
diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c
index 55989eaa2d9f..9bdb75dfdcd7 100644
--- a/drivers/scsi/3w-sas.c
+++ b/drivers/scsi/3w-sas.c
@@ -1326,7 +1326,8 @@ static int twl_reset_sequence(TW_Device_Extension *tw_dev, int soft_reset)
 		}
 
 		/* Load rest of compatibility struct */
-		strncpy(tw_dev->tw_compat_info.driver_version, TW_DRIVER_VERSION, strlen(TW_DRIVER_VERSION));
+		strscpy(tw_dev->tw_compat_info.driver_version, TW_DRIVER_VERSION,
+			sizeof(tw_dev->tw_compat_info.driver_version));
 		tw_dev->tw_compat_info.driver_srl_high = TW_CURRENT_DRIVER_SRL;
 		tw_dev->tw_compat_info.driver_branch_high = TW_CURRENT_DRIVER_BRANCH;
 		tw_dev->tw_compat_info.driver_build_high = TW_CURRENT_DRIVER_BUILD;
diff --git a/drivers/scsi/a3000.c b/drivers/scsi/a3000.c
index c3028726bbe4..378906f77909 100644
--- a/drivers/scsi/a3000.c
+++ b/drivers/scsi/a3000.c
@@ -282,7 +282,7 @@ fail_alloc:
 	return error;
 }
 
-static int __exit amiga_a3000_scsi_remove(struct platform_device *pdev)
+static void __exit amiga_a3000_scsi_remove(struct platform_device *pdev)
 {
 	struct Scsi_Host *instance = platform_get_drvdata(pdev);
 	struct a3000_hostdata *hdata = shost_priv(instance);
@@ -293,11 +293,10 @@ static int __exit amiga_a3000_scsi_remove(struct platform_device *pdev)
 	free_irq(IRQ_AMIGA_PORTS, instance);
 	scsi_host_put(instance);
 	release_mem_region(res->start, resource_size(res));
-	return 0;
 }
 
 static struct platform_driver amiga_a3000_scsi_driver = {
-	.remove = __exit_p(amiga_a3000_scsi_remove),
+	.remove_new = __exit_p(amiga_a3000_scsi_remove),
 	.driver   = {
 		.name	= "amiga-a3000-scsi",
 	},
diff --git a/drivers/scsi/a4000t.c b/drivers/scsi/a4000t.c
index 5e575afce134..e435fc06a624 100644
--- a/drivers/scsi/a4000t.c
+++ b/drivers/scsi/a4000t.c
@@ -95,7 +95,7 @@ static int __init amiga_a4000t_scsi_probe(struct platform_device *pdev)
 	return -ENODEV;
 }
 
-static int __exit amiga_a4000t_scsi_remove(struct platform_device *pdev)
+static void __exit amiga_a4000t_scsi_remove(struct platform_device *pdev)
 {
 	struct Scsi_Host *host = platform_get_drvdata(pdev);
 	struct NCR_700_Host_Parameters *hostdata = shost_priv(host);
@@ -106,11 +106,10 @@ static int __exit amiga_a4000t_scsi_remove(struct platform_device *pdev)
 	kfree(hostdata);
 	free_irq(host->irq, host);
 	release_mem_region(res->start, resource_size(res));
-	return 0;
 }
 
 static struct platform_driver amiga_a4000t_scsi_driver = {
-	.remove = __exit_p(amiga_a4000t_scsi_remove),
+	.remove_new = __exit_p(amiga_a4000t_scsi_remove),
 	.driver   = {
 		.name	= "amiga-a4000t-scsi",
 	},
diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h
index 73b6ac0c01f5..7d5a155073c6 100644
--- a/drivers/scsi/aacraid/aacraid.h
+++ b/drivers/scsi/aacraid/aacraid.h
@@ -1678,7 +1678,6 @@ struct aac_dev
 	u32			handle_pci_error;
 	bool			init_reset;
 	u8			soft_reset_support;
-	u8			use_map_queue;
 };
 
 #define aac_adapter_interrupt(dev) \
diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index 013a9a334972..25cee03d7f97 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -223,12 +223,8 @@ int aac_fib_setup(struct aac_dev * dev)
 struct fib *aac_fib_alloc_tag(struct aac_dev *dev, struct scsi_cmnd *scmd)
 {
 	struct fib *fibptr;
-	u32 blk_tag;
-	int i;
 
-	blk_tag = blk_mq_unique_tag(scsi_cmd_to_rq(scmd));
-	i = blk_mq_unique_tag_to_tag(blk_tag);
-	fibptr = &dev->fibs[i];
+	fibptr = &dev->fibs[scsi_cmd_to_rq(scmd)->tag];
 	/*
 	 *	Null out fields that depend on being zero at the start of
 	 *	each I/O
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index c4a36c0be527..68f4dbcfff49 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -19,7 +19,6 @@
 
 #include <linux/compat.h>
 #include <linux/blkdev.h>
-#include <linux/blk-mq-pci.h>
 #include <linux/completion.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
@@ -505,15 +504,6 @@ common_config:
 	return 0;
 }
 
-static void aac_map_queues(struct Scsi_Host *shost)
-{
-	struct aac_dev *aac = (struct aac_dev *)shost->hostdata;
-
-	blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT],
-			      aac->pdev, 0);
-	aac->use_map_queue = true;
-}
-
 /**
  *	aac_change_queue_depth		-	alter queue depths
  *	@sdev:	SCSI device we are considering
@@ -1498,7 +1488,6 @@ static const struct scsi_host_template aac_driver_template = {
 	.bios_param			= aac_biosparm,
 	.shost_groups			= aac_host_groups,
 	.slave_configure		= aac_slave_configure,
-	.map_queues			= aac_map_queues,
 	.change_queue_depth		= aac_change_queue_depth,
 	.sdev_groups			= aac_dev_groups,
 	.eh_abort_handler		= aac_eh_abort,
@@ -1786,8 +1775,6 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	shost->max_lun = AAC_MAX_LUN;
 
 	pci_set_drvdata(pdev, shost);
-	shost->nr_hw_queues = aac->max_msix;
-	shost->host_tagset = 1;
 
 	error = scsi_add_host(shost, &pdev->dev);
 	if (error)
@@ -1919,7 +1906,6 @@ static void aac_remove_one(struct pci_dev *pdev)
 	struct aac_dev *aac = (struct aac_dev *)shost->hostdata;
 
 	aac_cancel_rescan_worker(aac);
-	aac->use_map_queue = false;
 	scsi_remove_host(shost);
 
 	__aac_shutdown(aac);
diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c
index 61949f374188..11ef58204e96 100644
--- a/drivers/scsi/aacraid/src.c
+++ b/drivers/scsi/aacraid/src.c
@@ -493,10 +493,6 @@ static int aac_src_deliver_message(struct fib *fib)
 #endif
 
 	u16 vector_no;
-	struct scsi_cmnd *scmd;
-	u32 blk_tag;
-	struct Scsi_Host *shost = dev->scsi_host_ptr;
-	struct blk_mq_queue_map *qmap;
 
 	atomic_inc(&q->numpending);
 
@@ -509,25 +505,8 @@ static int aac_src_deliver_message(struct fib *fib)
 		if ((dev->comm_interface == AAC_COMM_MESSAGE_TYPE3)
 			&& dev->sa_firmware)
 			vector_no = aac_get_vector(dev);
-		else {
-			if (!fib->vector_no || !fib->callback_data) {
-				if (shost && dev->use_map_queue) {
-					qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT];
-					vector_no = qmap->mq_map[raw_smp_processor_id()];
-				}
-				/*
-				 *	We hardcode the vector_no for
-				 *	reserved commands as a valid shost is
-				 *	absent during the init
-				 */
-				else
-					vector_no = 0;
-			} else {
-				scmd = (struct scsi_cmnd *)fib->callback_data;
-				blk_tag = blk_mq_unique_tag(scsi_cmd_to_rq(scmd));
-				vector_no = blk_mq_unique_tag_to_hwq(blk_tag);
-			}
-		}
+		else
+			vector_no = fib->vector_no;
 
 		if (native_hba) {
 			if (fib->flags & FIB_CONTEXT_FLAG_NATIVE_HBA_TMF) {
diff --git a/drivers/scsi/aic7xxx/aic7770_osm.c b/drivers/scsi/aic7xxx/aic7770_osm.c
index bdd177e3d762..a19cdd87c453 100644
--- a/drivers/scsi/aic7xxx/aic7770_osm.c
+++ b/drivers/scsi/aic7xxx/aic7770_osm.c
@@ -87,17 +87,17 @@ aic7770_probe(struct device *dev)
 	sprintf(buf, "ahc_eisa:%d", eisaBase >> 12);
 	name = kstrdup(buf, GFP_ATOMIC);
 	if (name == NULL)
-		return (ENOMEM);
+		return -ENOMEM;
 	ahc = ahc_alloc(&aic7xxx_driver_template, name);
 	if (ahc == NULL)
-		return (ENOMEM);
+		return -ENOMEM;
 	ahc->dev = dev;
 	error = aic7770_config(ahc, aic7770_ident_table + edev->id.driver_data,
 			       eisaBase);
 	if (error != 0) {
 		ahc->bsh.ioport = 0;
 		ahc_free(ahc);
-		return (error);
+		return error < 0 ? error : -error;
 	}
 
  	dev_set_drvdata(dev, ahc);
diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.c b/drivers/scsi/aic7xxx/aic7xxx_osm.c
index 4ae0a1c4d374..b0c4f2345321 100644
--- a/drivers/scsi/aic7xxx/aic7xxx_osm.c
+++ b/drivers/scsi/aic7xxx/aic7xxx_osm.c
@@ -1085,7 +1085,7 @@ ahc_linux_register_host(struct ahc_softc *ahc, struct scsi_host_template *templa
 	template->name = ahc->description;
 	host = scsi_host_alloc(template, sizeof(struct ahc_softc *));
 	if (host == NULL)
-		return (ENOMEM);
+		return -ENOMEM;
 
 	*((struct ahc_softc **)host->hostdata) = ahc;
 	ahc->platform_data->host = host;
diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c b/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c
index a07e94fac673..198440dc0918 100644
--- a/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c
+++ b/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c
@@ -241,8 +241,7 @@ ahc_linux_pci_dev_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		ahc_linux_pci_inherit_flags(ahc);
 
 	pci_set_drvdata(pdev, ahc);
-	ahc_linux_register_host(ahc, &aic7xxx_driver_template);
-	return (0);
+	return ahc_linux_register_host(ahc, &aic7xxx_driver_template);
 }
 
 /******************************* PCI Routines *********************************/
diff --git a/drivers/scsi/arcmsr/arcmsr.h b/drivers/scsi/arcmsr/arcmsr.h
index ed8d9319862a..12c4148fe16f 100644
--- a/drivers/scsi/arcmsr/arcmsr.h
+++ b/drivers/scsi/arcmsr/arcmsr.h
@@ -50,7 +50,7 @@ struct device_attribute;
 #define ARCMSR_MAX_OUTSTANDING_CMD	1024
 #define ARCMSR_DEFAULT_OUTSTANDING_CMD	128
 #define ARCMSR_MIN_OUTSTANDING_CMD	32
-#define ARCMSR_DRIVER_VERSION		"v1.50.00.13-20230206"
+#define ARCMSR_DRIVER_VERSION		"v1.51.00.14-20230915"
 #define ARCMSR_SCSI_INITIATOR_ID	255
 #define ARCMSR_MAX_XFER_SECTORS		512
 #define ARCMSR_MAX_XFER_SECTORS_B	4096
@@ -78,9 +78,13 @@ struct device_attribute;
 #ifndef PCI_DEVICE_ID_ARECA_1203
 #define PCI_DEVICE_ID_ARECA_1203	0x1203
 #endif
+#ifndef PCI_DEVICE_ID_ARECA_1883
+#define PCI_DEVICE_ID_ARECA_1883	0x1883
+#endif
 #ifndef PCI_DEVICE_ID_ARECA_1884
 #define PCI_DEVICE_ID_ARECA_1884	0x1884
 #endif
+#define PCI_DEVICE_ID_ARECA_1886_0	0x1886
 #define PCI_DEVICE_ID_ARECA_1886	0x188A
 #define	ARCMSR_HOURS			(1000 * 60 * 60 * 4)
 #define	ARCMSR_MINUTES			(1000 * 60 * 60)
@@ -818,6 +822,23 @@ typedef struct deliver_completeQ {
 	uint16_t	cmdLMID;        // reserved (0)
 	uint16_t	cmdFlag2;       // reserved (0)
 } DeliverQ, CompletionQ, *pDeliver_Q, *pCompletion_Q;
+
+#define ARCMSR_XOR_SEG_SIZE	(1024 * 1024)
+struct HostRamBuf {
+	uint32_t	hrbSignature;	// must be "HRBS"
+	uint32_t	hrbSize;	// total sg size, be multiples of MB
+	uint32_t	hrbRes[2];	// reserved, must be set to 0
+};
+struct	Xor_sg {
+	dma_addr_t	xorPhys;
+	uint64_t	xorBufLen;
+};
+struct	XorHandle {
+	dma_addr_t	xorPhys;
+	uint64_t	xorBufLen;
+	void		*xorVirt;
+};
+
 /*
 *******************************************************************************
 **                 Adapter Control Block
@@ -929,6 +950,7 @@ struct AdapterControlBlock
 	char			firm_model[12];
 	char			firm_version[20];
 	char			device_map[20];			/*21,84-99*/
+	uint32_t		firm_PicStatus;
 	struct work_struct 	arcmsr_do_message_isr_bh;
 	struct timer_list	eternal_timer;
 	unsigned short		fw_flag;
@@ -937,6 +959,7 @@ struct AdapterControlBlock
 #define	FW_DEADLOCK			0x0010
 	uint32_t		maxOutstanding;
 	int			vector_count;
+	int			xor_mega;
 	uint32_t		maxFreeCCB;
 	struct timer_list	refresh_timer;
 	uint32_t		doneq_index;
@@ -946,6 +969,10 @@ struct AdapterControlBlock
 	uint32_t		completionQ_entry;
 	pCompletion_Q		pCompletionQ;
 	uint32_t		completeQ_size;
+	void			*xorVirt;
+	dma_addr_t		xorPhys;
+	unsigned int		init2cfg_size;
+	unsigned int		xorVirtOffset;
 };/* HW_DEVICE_EXTENSION */
 /*
 *******************************************************************************
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index a66221c3b72f..ad227e6cb10e 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -214,8 +214,12 @@ static struct pci_device_id arcmsr_device_id_table[] = {
 		.driver_data = ACB_ADAPTER_TYPE_A},
 	{PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1880),
 		.driver_data = ACB_ADAPTER_TYPE_C},
+	{PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1883),
+		.driver_data = ACB_ADAPTER_TYPE_C},
 	{PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1884),
 		.driver_data = ACB_ADAPTER_TYPE_E},
+	{PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1886_0),
+		.driver_data = ACB_ADAPTER_TYPE_F},
 	{PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1886),
 		.driver_data = ACB_ADAPTER_TYPE_F},
 	{0, 0}, /* Terminating entry */
@@ -747,6 +751,57 @@ static bool arcmsr_alloc_io_queue(struct AdapterControlBlock *acb)
 	return rtn;
 }
 
+static int arcmsr_alloc_xor_buffer(struct AdapterControlBlock *acb)
+{
+	int rc = 0;
+	struct pci_dev *pdev = acb->pdev;
+	void *dma_coherent;
+	dma_addr_t dma_coherent_handle;
+	int i, xor_ram;
+	struct Xor_sg *pXorPhys;
+	void **pXorVirt;
+	struct HostRamBuf *pRamBuf;
+
+	// allocate 1 MB * N physically continuous memory for XOR engine.
+	xor_ram = (acb->firm_PicStatus >> 24) & 0x0f;
+	acb->xor_mega = (xor_ram - 1) * 32 + 128 + 3;
+	acb->init2cfg_size = sizeof(struct HostRamBuf) +
+		(sizeof(struct XorHandle) * acb->xor_mega);
+	dma_coherent = dma_alloc_coherent(&pdev->dev, acb->init2cfg_size,
+		&dma_coherent_handle, GFP_KERNEL);
+	acb->xorVirt = dma_coherent;
+	acb->xorPhys = dma_coherent_handle;
+	pXorPhys = (struct Xor_sg *)((unsigned long)dma_coherent +
+		sizeof(struct HostRamBuf));
+	acb->xorVirtOffset = sizeof(struct HostRamBuf) +
+		(sizeof(struct Xor_sg) * acb->xor_mega);
+	pXorVirt = (void **)((unsigned long)dma_coherent +
+		(unsigned long)acb->xorVirtOffset);
+	for (i = 0; i < acb->xor_mega; i++) {
+		dma_coherent = dma_alloc_coherent(&pdev->dev,
+			ARCMSR_XOR_SEG_SIZE,
+			&dma_coherent_handle, GFP_KERNEL);
+		if (dma_coherent) {
+			pXorPhys->xorPhys = dma_coherent_handle;
+			pXorPhys->xorBufLen = ARCMSR_XOR_SEG_SIZE;
+			*pXorVirt = dma_coherent;
+			pXorPhys++;
+			pXorVirt++;
+		} else {
+			pr_info("arcmsr%d: alloc max XOR buffer = 0x%x MB\n",
+				acb->host->host_no, i);
+			rc = -ENOMEM;
+			break;
+		}
+	}
+	pRamBuf = (struct HostRamBuf *)acb->xorVirt;
+	pRamBuf->hrbSignature = 0x53425248;	//HRBS
+	pRamBuf->hrbSize = i * ARCMSR_XOR_SEG_SIZE;
+	pRamBuf->hrbRes[0] = 0;
+	pRamBuf->hrbRes[1] = 0;
+	return rc;
+}
+
 static int arcmsr_alloc_ccb_pool(struct AdapterControlBlock *acb)
 {
 	struct pci_dev *pdev = acb->pdev;
@@ -836,7 +891,11 @@ static int arcmsr_alloc_ccb_pool(struct AdapterControlBlock *acb)
 		acb->completionQ_entry = acb->ioqueue_size / sizeof(struct deliver_completeQ);
 		acb->doneq_index = 0;
 		break;
-	}	
+	}
+	if ((acb->firm_PicStatus >> 24) & 0x0f) {
+		if (arcmsr_alloc_xor_buffer(acb))
+			return -ENOMEM;
+	}
 	return 0;
 }
 
@@ -2022,6 +2081,29 @@ static void arcmsr_stop_adapter_bgrb(struct AdapterControlBlock *acb)
 
 static void arcmsr_free_ccb_pool(struct AdapterControlBlock *acb)
 {
+	if (acb->xor_mega) {
+		struct Xor_sg *pXorPhys;
+		void **pXorVirt;
+		int i;
+
+		pXorPhys = (struct Xor_sg *)(acb->xorVirt +
+			sizeof(struct HostRamBuf));
+		pXorVirt = (void **)((unsigned long)acb->xorVirt +
+			(unsigned long)acb->xorVirtOffset);
+		for (i = 0; i < acb->xor_mega; i++) {
+			if (pXorPhys->xorPhys) {
+				dma_free_coherent(&acb->pdev->dev,
+					ARCMSR_XOR_SEG_SIZE,
+					*pXorVirt, pXorPhys->xorPhys);
+				pXorPhys->xorPhys = 0;
+				*pXorVirt = NULL;
+			}
+			pXorPhys++;
+			pXorVirt++;
+		}
+		dma_free_coherent(&acb->pdev->dev, acb->init2cfg_size,
+			acb->xorVirt, acb->xorPhys);
+	}
 	dma_free_coherent(&acb->pdev->dev, acb->uncache_size, acb->dma_coherent, acb->dma_coherent_handle);
 }
 
@@ -3309,6 +3391,10 @@ static void arcmsr_get_adapter_config(struct AdapterControlBlock *pACB, uint32_t
 	pACB->firm_sdram_size = readl(&rwbuffer[3]);
 	pACB->firm_hd_channels = readl(&rwbuffer[4]);
 	pACB->firm_cfg_version = readl(&rwbuffer[25]);
+	if (pACB->adapter_type == ACB_ADAPTER_TYPE_F)
+		pACB->firm_PicStatus = readl(&rwbuffer[30]);
+	else
+		pACB->firm_PicStatus = 0;
 	pr_notice("Areca RAID Controller%d: Model %s, F/W %s\n",
 		pACB->host->host_no,
 		pACB->firm_model,
@@ -4096,6 +4182,12 @@ static int arcmsr_iop_confirm(struct AdapterControlBlock *acb)
 		acb->msgcode_rwbuffer[5] = lower_32_bits(acb->dma_coherent_handle2);
 		acb->msgcode_rwbuffer[6] = upper_32_bits(acb->dma_coherent_handle2);
 		acb->msgcode_rwbuffer[7] = acb->completeQ_size;
+		if (acb->xor_mega) {
+			acb->msgcode_rwbuffer[8] = 0x455AA;	//Linux init 2
+			acb->msgcode_rwbuffer[9] = 0;
+			acb->msgcode_rwbuffer[10] = lower_32_bits(acb->xorPhys);
+			acb->msgcode_rwbuffer[11] = upper_32_bits(acb->xorPhys);
+		}
 		writel(ARCMSR_INBOUND_MESG0_SET_CONFIG, &reg->inbound_msgaddr0);
 		acb->out_doorbell ^= ARCMSR_HBEMU_DRV2IOP_MESSAGE_CMD_DONE;
 		writel(acb->out_doorbell, &reg->iobound_doorbell);
@@ -4706,9 +4798,11 @@ static const char *arcmsr_info(struct Scsi_Host *host)
 	case PCI_DEVICE_ID_ARECA_1680:
 	case PCI_DEVICE_ID_ARECA_1681:
 	case PCI_DEVICE_ID_ARECA_1880:
+	case PCI_DEVICE_ID_ARECA_1883:
 	case PCI_DEVICE_ID_ARECA_1884:
 		type = "SAS/SATA";
 		break;
+	case PCI_DEVICE_ID_ARECA_1886_0:
 	case PCI_DEVICE_ID_ARECA_1886:
 		type = "NVMe/SAS/SATA";
 		break;
diff --git a/drivers/scsi/atari_scsi.c b/drivers/scsi/atari_scsi.c
index d401cf27113a..d99e70914817 100644
--- a/drivers/scsi/atari_scsi.c
+++ b/drivers/scsi/atari_scsi.c
@@ -865,7 +865,7 @@ fail_alloc:
 	return error;
 }
 
-static int __exit atari_scsi_remove(struct platform_device *pdev)
+static void __exit atari_scsi_remove(struct platform_device *pdev)
 {
 	struct Scsi_Host *instance = platform_get_drvdata(pdev);
 
@@ -876,11 +876,10 @@ static int __exit atari_scsi_remove(struct platform_device *pdev)
 	scsi_host_put(instance);
 	if (atari_dma_buffer)
 		atari_stram_free(atari_dma_buffer);
-	return 0;
 }
 
 static struct platform_driver atari_scsi_driver = {
-	.remove = __exit_p(atari_scsi_remove),
+	.remove_new = __exit_p(atari_scsi_remove),
 	.driver = {
 		.name	= DRV_MODULE_NAME,
 	},
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index e48f14ad6dfd..06acb5ff609e 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -2710,6 +2710,7 @@ init_wrb_hndl_failed:
 		kfree(pwrb_context->pwrb_handle_base);
 		kfree(pwrb_context->pwrb_handle_basestd);
 	}
+	kfree(phwi_ctxt->be_wrbq);
 	return -ENOMEM;
 }
 
diff --git a/drivers/scsi/bfa/bfad_bsg.c b/drivers/scsi/bfa/bfad_bsg.c
index 520f9152f3bf..d4ceca2d435e 100644
--- a/drivers/scsi/bfa/bfad_bsg.c
+++ b/drivers/scsi/bfa/bfad_bsg.c
@@ -2550,7 +2550,7 @@ out:
 static void bfad_reset_sdev_bflags(struct bfad_im_port_s *im_port,
 				   int lunmask_cfg)
 {
-	const u32 scan_flags = BLIST_NOREPORTLUN | BLIST_SPARSELUN;
+	const blist_flags_t scan_flags = BLIST_NOREPORTLUN | BLIST_SPARSELUN;
 	struct bfad_itnim_s *itnim;
 	struct scsi_device *sdev;
 	unsigned long flags;
diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index 05ddbb9bb7d8..1078c20c5ef6 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -429,7 +429,6 @@ static int bnx2fc_rcv(struct sk_buff *skb, struct net_device *dev,
 	struct fcoe_ctlr *ctlr;
 	struct fcoe_rcv_info *fr;
 	struct fcoe_percpu_s *bg;
-	struct sk_buff *tmp_skb;
 
 	interface = container_of(ptype, struct bnx2fc_interface,
 				 fcoe_packet_type);
@@ -441,11 +440,9 @@ static int bnx2fc_rcv(struct sk_buff *skb, struct net_device *dev,
 		goto err;
 	}
 
-	tmp_skb = skb_share_check(skb, GFP_ATOMIC);
-	if (!tmp_skb)
-		goto err;
-
-	skb = tmp_skb;
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb)
+		return -1;
 
 	if (unlikely(eth_hdr(skb)->h_proto != htons(ETH_P_FCOE))) {
 		printk(KERN_ERR PFX "bnx2fc_rcv: Wrong FC type frame\n");
@@ -1737,32 +1734,32 @@ static int bnx2fc_bind_pcidev(struct bnx2fc_hba *hba)
 
 	switch (pdev->device) {
 	case PCI_DEVICE_ID_NX2_57710:
-		strncpy(hba->chip_num, "BCM57710", BCM_CHIP_LEN);
+		strscpy(hba->chip_num, "BCM57710", sizeof(hba->chip_num));
 		break;
 	case PCI_DEVICE_ID_NX2_57711:
-		strncpy(hba->chip_num, "BCM57711", BCM_CHIP_LEN);
+		strscpy(hba->chip_num, "BCM57711", sizeof(hba->chip_num));
 		break;
 	case PCI_DEVICE_ID_NX2_57712:
 	case PCI_DEVICE_ID_NX2_57712_MF:
 	case PCI_DEVICE_ID_NX2_57712_VF:
-		strncpy(hba->chip_num, "BCM57712", BCM_CHIP_LEN);
+		strscpy(hba->chip_num, "BCM57712", sizeof(hba->chip_num));
 		break;
 	case PCI_DEVICE_ID_NX2_57800:
 	case PCI_DEVICE_ID_NX2_57800_MF:
 	case PCI_DEVICE_ID_NX2_57800_VF:
-		strncpy(hba->chip_num, "BCM57800", BCM_CHIP_LEN);
+		strscpy(hba->chip_num, "BCM57800", sizeof(hba->chip_num));
 		break;
 	case PCI_DEVICE_ID_NX2_57810:
 	case PCI_DEVICE_ID_NX2_57810_MF:
 	case PCI_DEVICE_ID_NX2_57810_VF:
-		strncpy(hba->chip_num, "BCM57810", BCM_CHIP_LEN);
+		strscpy(hba->chip_num, "BCM57810", sizeof(hba->chip_num));
 		break;
 	case PCI_DEVICE_ID_NX2_57840:
 	case PCI_DEVICE_ID_NX2_57840_MF:
 	case PCI_DEVICE_ID_NX2_57840_VF:
 	case PCI_DEVICE_ID_NX2_57840_2_20:
 	case PCI_DEVICE_ID_NX2_57840_4_10:
-		strncpy(hba->chip_num, "BCM57840", BCM_CHIP_LEN);
+		strscpy(hba->chip_num, "BCM57840", sizeof(hba->chip_num));
 		break;
 	default:
 		pr_err(PFX "Unknown device id 0x%x\n", pdev->device);
@@ -1800,7 +1797,7 @@ static int bnx2fc_ulp_get_stats(void *handle)
 	if (!stats_addr)
 		return -EINVAL;
 
-	strncpy(stats_addr->version, BNX2FC_VERSION,
+	strscpy(stats_addr->version, BNX2FC_VERSION,
 		sizeof(stats_addr->version));
 	stats_addr->txq_size = BNX2FC_SQ_WQES_MAX;
 	stats_addr->rxq_size = BNX2FC_CQ_WQES_MAX;
diff --git a/drivers/scsi/bvme6000_scsi.c b/drivers/scsi/bvme6000_scsi.c
index 8d72b25535c5..f893e9779e9d 100644
--- a/drivers/scsi/bvme6000_scsi.c
+++ b/drivers/scsi/bvme6000_scsi.c
@@ -89,7 +89,7 @@ bvme6000_probe(struct platform_device *dev)
 	return -ENODEV;
 }
 
-static int
+static void
 bvme6000_device_remove(struct platform_device *dev)
 {
 	struct Scsi_Host *host = platform_get_drvdata(dev);
@@ -99,8 +99,6 @@ bvme6000_device_remove(struct platform_device *dev)
 	NCR_700_release(host);
 	kfree(hostdata);
 	free_irq(host->irq, host);
-
-	return 0;
 }
 
 static struct platform_driver bvme6000_scsi_driver = {
@@ -108,7 +106,7 @@ static struct platform_driver bvme6000_scsi_driver = {
 		.name		= "bvme6000-scsi",
 	},
 	.probe		= bvme6000_probe,
-	.remove		= bvme6000_device_remove,
+	.remove_new	= bvme6000_device_remove,
 };
 
 static int __init bvme6000_scsi_init(void)
diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c
index cb0a399be1cc..2b864061e073 100644
--- a/drivers/scsi/ch.c
+++ b/drivers/scsi/ch.c
@@ -659,19 +659,23 @@ static long ch_ioctl(struct file *file,
 		memset(&vparams,0,sizeof(vparams));
 		if (ch->counts[CHET_V1]) {
 			vparams.cvp_n1  = ch->counts[CHET_V1];
-			strncpy(vparams.cvp_label1,vendor_labels[0],16);
+			strscpy(vparams.cvp_label1, vendor_labels[0],
+				sizeof(vparams.cvp_label1));
 		}
 		if (ch->counts[CHET_V2]) {
 			vparams.cvp_n2  = ch->counts[CHET_V2];
-			strncpy(vparams.cvp_label2,vendor_labels[1],16);
+			strscpy(vparams.cvp_label2, vendor_labels[1],
+				sizeof(vparams.cvp_label2));
 		}
 		if (ch->counts[CHET_V3]) {
 			vparams.cvp_n3  = ch->counts[CHET_V3];
-			strncpy(vparams.cvp_label3,vendor_labels[2],16);
+			strscpy(vparams.cvp_label3, vendor_labels[2],
+				sizeof(vparams.cvp_label3));
 		}
 		if (ch->counts[CHET_V4]) {
 			vparams.cvp_n4  = ch->counts[CHET_V4];
-			strncpy(vparams.cvp_label4,vendor_labels[3],16);
+			strscpy(vparams.cvp_label4, vendor_labels[3],
+				sizeof(vparams.cvp_label4));
 		}
 		if (copy_to_user(argp, &vparams, sizeof(vparams)))
 			return -EFAULT;
diff --git a/drivers/scsi/csiostor/csio_init.c b/drivers/scsi/csiostor/csio_init.c
index 0c32faefad7c..d649b7a2a879 100644
--- a/drivers/scsi/csiostor/csio_init.c
+++ b/drivers/scsi/csiostor/csio_init.c
@@ -521,7 +521,8 @@ static struct csio_hw *csio_hw_alloc(struct pci_dev *pdev)
 		goto err;
 
 	hw->pdev = pdev;
-	strncpy(hw->drv_version, CSIO_DRV_VERSION, 32);
+	strscpy(hw->drv_version, CSIO_DRV_VERSION,
+		sizeof(hw->drv_version));
 
 	/* memory pool/DMA pool allocation */
 	if (csio_resource_alloc(hw))
diff --git a/drivers/scsi/dc395x.c b/drivers/scsi/dc395x.c
index c8e86f8a631e..d108a86e196e 100644
--- a/drivers/scsi/dc395x.c
+++ b/drivers/scsi/dc395x.c
@@ -1366,7 +1366,7 @@ static u8 start_scsi(struct AdapterCtlBlk* acb, struct DeviceCtlBlk* dcb,
 			"command while another command (0x%p) is active.",
 			srb->cmd,
 			acb->active_dcb->active_srb ?
-			    acb->active_dcb->active_srb->cmd : 0);
+			    acb->active_dcb->active_srb->cmd : NULL);
 		return 1;
 	}
 	if (DC395x_read16(acb, TRM_S1040_SCSI_STATUS) & SCSIINTERRUPT) {
diff --git a/drivers/scsi/elx/libefc/efc_node.h b/drivers/scsi/elx/libefc/efc_node.h
index e9c600ac45d5..e57579988ba4 100644
--- a/drivers/scsi/elx/libefc/efc_node.h
+++ b/drivers/scsi/elx/libefc/efc_node.h
@@ -26,13 +26,13 @@ efc_node_evt_set(struct efc_sm_ctx *ctx, enum efc_sm_event evt,
 	struct efc_node *node = ctx->app;
 
 	if (evt == EFC_EVT_ENTER) {
-		strncpy(node->current_state_name, handler,
-			sizeof(node->current_state_name));
+		strscpy_pad(node->current_state_name, handler,
+			    sizeof(node->current_state_name));
 	} else if (evt == EFC_EVT_EXIT) {
-		strncpy(node->prev_state_name, node->current_state_name,
-			sizeof(node->prev_state_name));
-		strncpy(node->current_state_name, "invalid",
-			sizeof(node->current_state_name));
+		memcpy(node->prev_state_name, node->current_state_name,
+		       sizeof(node->prev_state_name));
+		strscpy_pad(node->current_state_name, "invalid",
+			    sizeof(node->current_state_name));
 	}
 	node->prev_evt = node->current_evt;
 	node->current_evt = evt;
diff --git a/drivers/scsi/fcoe/fcoe_sysfs.c b/drivers/scsi/fcoe/fcoe_sysfs.c
index e17957f8085c..408a806bf4c2 100644
--- a/drivers/scsi/fcoe/fcoe_sysfs.c
+++ b/drivers/scsi/fcoe/fcoe_sysfs.c
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/etherdevice.h>
 #include <linux/ctype.h>
+#include <linux/string.h>
 
 #include <scsi/fcoe_sysfs.h>
 #include <scsi/libfcoe.h>
@@ -214,25 +215,13 @@ static const char *get_fcoe_##title##_name(enum table_type table_key)	\
 	return table[table_key];					\
 }
 
-static char *fip_conn_type_names[] = {
+static const char * const fip_conn_type_names[] = {
 	[ FIP_CONN_TYPE_UNKNOWN ] = "Unknown",
 	[ FIP_CONN_TYPE_FABRIC ]  = "Fabric",
 	[ FIP_CONN_TYPE_VN2VN ]   = "VN2VN",
 };
 fcoe_enum_name_search(ctlr_mode, fip_conn_type, fip_conn_type_names)
 
-static enum fip_conn_type fcoe_parse_mode(const char *buf)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(fip_conn_type_names); i++) {
-		if (strcasecmp(buf, fip_conn_type_names[i]) == 0)
-			return i;
-	}
-
-	return FIP_CONN_TYPE_UNKNOWN;
-}
-
 static char *fcf_state_names[] = {
 	[ FCOE_FCF_STATE_UNKNOWN ]      = "Unknown",
 	[ FCOE_FCF_STATE_DISCONNECTED ] = "Disconnected",
@@ -274,17 +263,10 @@ static ssize_t store_ctlr_mode(struct device *dev,
 			       const char *buf, size_t count)
 {
 	struct fcoe_ctlr_device *ctlr = dev_to_ctlr(dev);
-	char mode[FCOE_MAX_MODENAME_LEN + 1];
 
 	if (count > FCOE_MAX_MODENAME_LEN)
 		return -EINVAL;
 
-	strncpy(mode, buf, count);
-
-	if (mode[count - 1] == '\n')
-		mode[count - 1] = '\0';
-	else
-		mode[count] = '\0';
 
 	switch (ctlr->enabled) {
 	case FCOE_CTLR_ENABLED:
@@ -297,8 +279,8 @@ static ssize_t store_ctlr_mode(struct device *dev,
 			return -ENOTSUPP;
 		}
 
-		ctlr->mode = fcoe_parse_mode(mode);
-		if (ctlr->mode == FIP_CONN_TYPE_UNKNOWN) {
+		ctlr->mode = sysfs_match_string(fip_conn_type_names, buf);
+		if (ctlr->mode < 0 || ctlr->mode == FIP_CONN_TYPE_UNKNOWN) {
 			LIBFCOE_SYSFS_DBG(ctlr, "Unknown mode %s provided.\n",
 					  buf);
 			return -EINVAL;
diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h
index 22cef283b2b9..2074937c05bc 100644
--- a/drivers/scsi/fnic/fnic.h
+++ b/drivers/scsi/fnic/fnic.h
@@ -27,7 +27,7 @@
 
 #define DRV_NAME		"fnic"
 #define DRV_DESCRIPTION		"Cisco FCoE HBA Driver"
-#define DRV_VERSION		"1.6.0.57"
+#define DRV_VERSION		"1.7.0.0"
 #define PFX			DRV_NAME ": "
 #define DFX                     DRV_NAME "%d: "
 
@@ -36,7 +36,6 @@
 #define FNIC_MIN_IO_REQ			256 /* Min IO throttle count */
 #define FNIC_MAX_IO_REQ		1024 /* scsi_cmnd tag map entries */
 #define FNIC_DFLT_IO_REQ        256 /* Default scsi_cmnd tag map entries */
-#define	FNIC_IO_LOCKS		64 /* IO locks: power of 2 */
 #define FNIC_DFLT_QUEUE_DEPTH	256
 #define	FNIC_STATS_RATE_LIMIT	4 /* limit rate at which stats are pulled up */
 
@@ -109,7 +108,7 @@ static inline u64 fnic_flags_and_state(struct scsi_cmnd *cmd)
 #define FNIC_ABT_TERM_DELAY_TIMEOUT  500        /* mSec */
 
 #define FNIC_MAX_FCP_TARGET     256
-
+#define FNIC_PCI_OFFSET		2
 /**
  * state_flags to identify host state along along with fnic's state
  **/
@@ -144,31 +143,48 @@ do {								\
 		} while (0);					\
 } while (0)
 
-#define FNIC_MAIN_DBG(kern_level, host, fmt, args...)		\
+#define FNIC_MAIN_DBG(kern_level, host, fnic_num, fmt, args...)		\
 	FNIC_CHECK_LOGGING(FNIC_MAIN_LOGGING,			\
-			 shost_printk(kern_level, host, fmt, ##args);)
+			 shost_printk(kern_level, host,			\
+				"fnic<%d>: %s: %d: " fmt, fnic_num,\
+				__func__, __LINE__, ##args);)
 
-#define FNIC_FCS_DBG(kern_level, host, fmt, args...)		\
+#define FNIC_FCS_DBG(kern_level, host, fnic_num, fmt, args...)		\
 	FNIC_CHECK_LOGGING(FNIC_FCS_LOGGING,			\
-			 shost_printk(kern_level, host, fmt, ##args);)
+			 shost_printk(kern_level, host,			\
+				"fnic<%d>: %s: %d: " fmt, fnic_num,\
+				__func__, __LINE__, ##args);)
 
-#define FNIC_SCSI_DBG(kern_level, host, fmt, args...)		\
+#define FNIC_SCSI_DBG(kern_level, host, fnic_num, fmt, args...)		\
 	FNIC_CHECK_LOGGING(FNIC_SCSI_LOGGING,			\
-			 shost_printk(kern_level, host, fmt, ##args);)
+			 shost_printk(kern_level, host,			\
+				"fnic<%d>: %s: %d: " fmt, fnic_num,\
+				__func__, __LINE__, ##args);)
 
-#define FNIC_ISR_DBG(kern_level, host, fmt, args...)		\
+#define FNIC_ISR_DBG(kern_level, host, fnic_num, fmt, args...)		\
 	FNIC_CHECK_LOGGING(FNIC_ISR_LOGGING,			\
-			 shost_printk(kern_level, host, fmt, ##args);)
+			 shost_printk(kern_level, host,			\
+				"fnic<%d>: %s: %d: " fmt, fnic_num,\
+				__func__, __LINE__, ##args);)
 
 #define FNIC_MAIN_NOTE(kern_level, host, fmt, args...)          \
 	shost_printk(kern_level, host, fmt, ##args)
 
+#define FNIC_WQ_COPY_MAX 64
+#define FNIC_WQ_MAX 1
+#define FNIC_RQ_MAX 1
+#define FNIC_CQ_MAX (FNIC_WQ_COPY_MAX + FNIC_WQ_MAX + FNIC_RQ_MAX)
+#define FNIC_DFLT_IO_COMPLETIONS 256
+
+#define FNIC_MQ_CQ_INDEX        2
+
 extern const char *fnic_state_str[];
 
 enum fnic_intx_intr_index {
 	FNIC_INTX_WQ_RQ_COPYWQ,
-	FNIC_INTX_ERR,
+	FNIC_INTX_DUMMY,
 	FNIC_INTX_NOTIFY,
+	FNIC_INTX_ERR,
 	FNIC_INTX_INTR_MAX,
 };
 
@@ -176,7 +192,7 @@ enum fnic_msix_intr_index {
 	FNIC_MSIX_RQ,
 	FNIC_MSIX_WQ,
 	FNIC_MSIX_WQ_COPY,
-	FNIC_MSIX_ERR_NOTIFY,
+	FNIC_MSIX_ERR_NOTIFY = FNIC_MSIX_WQ_COPY + FNIC_WQ_COPY_MAX,
 	FNIC_MSIX_INTR_MAX,
 };
 
@@ -185,6 +201,7 @@ struct fnic_msix_entry {
 	char devname[IFNAMSIZ + 11];
 	irqreturn_t (*isr)(int, void *);
 	void *devid;
+	int irq_num;
 };
 
 enum fnic_state {
@@ -194,12 +211,6 @@ enum fnic_state {
 	FNIC_IN_ETH_TRANS_FC_MODE,
 };
 
-#define FNIC_WQ_COPY_MAX 1
-#define FNIC_WQ_MAX 1
-#define FNIC_RQ_MAX 1
-#define FNIC_CQ_MAX (FNIC_WQ_COPY_MAX + FNIC_WQ_MAX + FNIC_RQ_MAX)
-#define FNIC_DFLT_IO_COMPLETIONS 256
-
 struct mempool;
 
 enum fnic_evt {
@@ -214,8 +225,16 @@ struct fnic_event {
 	enum fnic_evt event;
 };
 
+struct fnic_cpy_wq {
+	unsigned long hw_lock_flags;
+	u16 active_ioreq_count;
+	u16 ioreq_table_size;
+	____cacheline_aligned struct fnic_io_req **io_req_table;
+};
+
 /* Per-instance private data structure */
 struct fnic {
+	int fnic_num;
 	struct fc_lport *lport;
 	struct fcoe_ctlr ctlr;		/* FIP FCoE controller structure */
 	struct vnic_dev_bar bar0;
@@ -282,8 +301,8 @@ struct fnic {
 	struct fnic_host_tag *tags;
 	mempool_t *io_req_pool;
 	mempool_t *io_sgl_pool[FNIC_SGL_NUM_CACHES];
-	spinlock_t io_req_lock[FNIC_IO_LOCKS];	/* locks for scsi cmnds */
 
+	unsigned int copy_wq_base;
 	struct work_struct link_work;
 	struct work_struct frame_work;
 	struct sk_buff_head frame_queue;
@@ -302,7 +321,9 @@ struct fnic {
 	/*** FIP related data members  -- end ***/
 
 	/* copy work queue cache line section */
-	____cacheline_aligned struct vnic_wq_copy wq_copy[FNIC_WQ_COPY_MAX];
+	____cacheline_aligned struct vnic_wq_copy hw_copy_wq[FNIC_WQ_COPY_MAX];
+	____cacheline_aligned struct fnic_cpy_wq sw_copy_wq[FNIC_WQ_COPY_MAX];
+
 	/* completion queue cache line section */
 	____cacheline_aligned struct vnic_cq cq[FNIC_CQ_MAX];
 
@@ -330,6 +351,7 @@ extern const struct attribute_group *fnic_host_groups[];
 
 void fnic_clear_intr_mode(struct fnic *fnic);
 int fnic_set_intr_mode(struct fnic *fnic);
+int fnic_set_intr_mode_msix(struct fnic *fnic);
 void fnic_free_intr(struct fnic *fnic);
 int fnic_request_intr(struct fnic *fnic);
 
@@ -356,7 +378,7 @@ void fnic_scsi_cleanup(struct fc_lport *);
 void fnic_scsi_abort_io(struct fc_lport *);
 void fnic_empty_scsi_cleanup(struct fc_lport *);
 void fnic_exch_mgr_reset(struct fc_lport *, u32, u32);
-int fnic_wq_copy_cmpl_handler(struct fnic *fnic, int);
+int fnic_wq_copy_cmpl_handler(struct fnic *fnic, int copy_work_to_do, unsigned int cq_index);
 int fnic_wq_cmpl_handler(struct fnic *fnic, int);
 int fnic_flogi_reg_handler(struct fnic *fnic, u32);
 void fnic_wq_copy_cleanup_handler(struct vnic_wq_copy *wq,
@@ -364,7 +386,7 @@ void fnic_wq_copy_cleanup_handler(struct vnic_wq_copy *wq,
 int fnic_fw_reset_handler(struct fnic *fnic);
 void fnic_terminate_rport_io(struct fc_rport *);
 const char *fnic_state_to_str(unsigned int state);
-
+void fnic_mq_map_queues_cpus(struct Scsi_Host *host);
 void fnic_log_q_error(struct fnic *fnic);
 void fnic_handle_link_event(struct fnic *fnic);
 
diff --git a/drivers/scsi/fnic/fnic_debugfs.c b/drivers/scsi/fnic/fnic_debugfs.c
index c4d9ed0d7d75..2619a2d4f5f1 100644
--- a/drivers/scsi/fnic/fnic_debugfs.c
+++ b/drivers/scsi/fnic/fnic_debugfs.c
@@ -52,9 +52,10 @@ int fnic_debugfs_init(void)
 		fc_trc_flag->fnic_trace = 2;
 		fc_trc_flag->fc_trace = 3;
 		fc_trc_flag->fc_clear = 4;
+		return 0;
 	}
 
-	return 0;
+	return -ENOMEM;
 }
 
 /*
diff --git a/drivers/scsi/fnic/fnic_fcs.c b/drivers/scsi/fnic/fnic_fcs.c
index 55632c67a8f2..5e312a55cc7d 100644
--- a/drivers/scsi/fnic/fnic_fcs.c
+++ b/drivers/scsi/fnic/fnic_fcs.c
@@ -63,8 +63,8 @@ void fnic_handle_link(struct work_struct *work)
 	atomic64_set(&fnic->fnic_stats.misc_stats.current_port_speed,
 			new_port_speed);
 	if (old_port_speed != new_port_speed)
-		FNIC_MAIN_DBG(KERN_INFO, fnic->lport->host,
-				"Current vnic speed set to :  %llu\n",
+		FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+				"Current vnic speed set to: %llu\n",
 				new_port_speed);
 
 	switch (vnic_dev_port_speed(fnic->vdev)) {
@@ -102,6 +102,8 @@ void fnic_handle_link(struct work_struct *work)
 			fnic_fc_trace_set_data(fnic->lport->host->host_no,
 				FNIC_FC_LE, "Link Status: DOWN->DOWN",
 				strlen("Link Status: DOWN->DOWN"));
+			FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+					"down->down\n");
 		} else {
 			if (old_link_down_cnt != fnic->link_down_cnt) {
 				/* UP -> DOWN -> UP */
@@ -113,7 +115,7 @@ void fnic_handle_link(struct work_struct *work)
 					"Link Status:UP_DOWN_UP",
 					strlen("Link_Status:UP_DOWN_UP")
 					);
-				FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host,
+				FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 					     "link down\n");
 				fcoe_ctlr_link_down(&fnic->ctlr);
 				if (fnic->config.flags & VFCF_FIP_CAPABLE) {
@@ -128,8 +130,8 @@ void fnic_handle_link(struct work_struct *work)
 					fnic_fcoe_send_vlan_req(fnic);
 					return;
 				}
-				FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host,
-					     "link up\n");
+				FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+						"up->down->up: Link up\n");
 				fcoe_ctlr_link_up(&fnic->ctlr);
 			} else {
 				/* UP -> UP */
@@ -138,6 +140,8 @@ void fnic_handle_link(struct work_struct *work)
 					fnic->lport->host->host_no, FNIC_FC_LE,
 					"Link Status: UP_UP",
 					strlen("Link Status: UP_UP"));
+				FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+						"up->up\n");
 			}
 		}
 	} else if (fnic->link_status) {
@@ -153,7 +157,8 @@ void fnic_handle_link(struct work_struct *work)
 			return;
 		}
 
-		FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, "link up\n");
+		FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+				"down->up: Link up\n");
 		fnic_fc_trace_set_data(fnic->lport->host->host_no, FNIC_FC_LE,
 				       "Link Status: DOWN_UP", strlen("Link Status: DOWN_UP"));
 		fcoe_ctlr_link_up(&fnic->ctlr);
@@ -161,13 +166,14 @@ void fnic_handle_link(struct work_struct *work)
 		/* UP -> DOWN */
 		fnic->lport->host_stats.link_failure_count++;
 		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, "link down\n");
+		FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+				"up->down: Link down\n");
 		fnic_fc_trace_set_data(
 			fnic->lport->host->host_no, FNIC_FC_LE,
 			"Link Status: UP_DOWN",
 			strlen("Link Status: UP_DOWN"));
 		if (fnic->config.flags & VFCF_FIP_CAPABLE) {
-			FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host,
+			FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 				"deleting fip-timer during link-down\n");
 			del_timer_sync(&fnic->fip_timer);
 		}
@@ -270,12 +276,12 @@ void fnic_handle_event(struct work_struct *work)
 			spin_lock_irqsave(&fnic->fnic_lock, flags);
 			break;
 		case FNIC_EVT_START_FCF_DISC:
-			FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host,
+			FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 				  "Start FCF Discovery\n");
 			fnic_fcoe_start_fcf_disc(fnic);
 			break;
 		default:
-			FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host,
+			FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 				  "Unknown event 0x%x\n", fevt->event);
 			break;
 		}
@@ -370,7 +376,7 @@ static void fnic_fcoe_send_vlan_req(struct fnic *fnic)
 	fnic->set_vlan(fnic, 0);
 
 	if (printk_ratelimit())
-		FNIC_FCS_DBG(KERN_INFO, fnic->lport->host,
+		FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
 			  "Sending VLAN request...\n");
 
 	skb = dev_alloc_skb(sizeof(struct fip_vlan));
@@ -423,12 +429,12 @@ static void fnic_fcoe_process_vlan_resp(struct fnic *fnic, struct sk_buff *skb)
 	u64 sol_time;
 	unsigned long flags;
 
-	FNIC_FCS_DBG(KERN_INFO, fnic->lport->host,
+	FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
 		  "Received VLAN response...\n");
 
 	fiph = (struct fip_header *) skb->data;
 
-	FNIC_FCS_DBG(KERN_INFO, fnic->lport->host,
+	FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
 		  "Received VLAN response... OP 0x%x SUB_OP 0x%x\n",
 		  ntohs(fiph->fip_op), fiph->fip_subcode);
 
@@ -463,7 +469,7 @@ static void fnic_fcoe_process_vlan_resp(struct fnic *fnic, struct sk_buff *skb)
 	if (list_empty(&fnic->vlans)) {
 		/* retry from timer */
 		atomic64_inc(&fnic_stats->vlan_stats.resp_withno_vlanID);
-		FNIC_FCS_DBG(KERN_INFO, fnic->lport->host,
+		FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
 			  "No VLAN descriptors in FIP VLAN response\n");
 		spin_unlock_irqrestore(&fnic->vlans_lock, flags);
 		goto out;
@@ -721,7 +727,8 @@ void fnic_update_mac_locked(struct fnic *fnic, u8 *new)
 		new = ctl;
 	if (ether_addr_equal(data, new))
 		return;
-	FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, "update_mac %pM\n", new);
+	FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+			"update_mac %pM\n", new);
 	if (!is_zero_ether_addr(data) && !ether_addr_equal(data, ctl))
 		vnic_dev_del_addr(fnic->vdev, data);
 	memcpy(data, new, ETH_ALEN);
@@ -763,8 +770,9 @@ void fnic_set_port_id(struct fc_lport *lport, u32 port_id, struct fc_frame *fp)
 	u8 *mac;
 	int ret;
 
-	FNIC_FCS_DBG(KERN_DEBUG, lport->host, "set port_id %x fp %p\n",
-		     port_id, fp);
+	FNIC_FCS_DBG(KERN_DEBUG, lport->host, fnic->fnic_num,
+			"set port_id 0x%x fp 0x%p\n",
+			port_id, fp);
 
 	/*
 	 * If we're clearing the FC_ID, change to use the ctl_src_addr.
@@ -790,10 +798,9 @@ void fnic_set_port_id(struct fc_lport *lport, u32 port_id, struct fc_frame *fp)
 	if (fnic->state == FNIC_IN_ETH_MODE || fnic->state == FNIC_IN_FC_MODE)
 		fnic->state = FNIC_IN_ETH_TRANS_FC_MODE;
 	else {
-		FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host,
-			     "Unexpected fnic state %s while"
-			     " processing flogi resp\n",
-			     fnic_state_to_str(fnic->state));
+		FNIC_FCS_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			     "Unexpected fnic state: %s processing FLOGI response",
+				 fnic_state_to_str(fnic->state));
 		spin_unlock_irq(&fnic->fnic_lock);
 		return;
 	}
@@ -870,7 +877,7 @@ static void fnic_rq_cmpl_frame_recv(struct vnic_rq *rq, struct cq_desc
 		skb_trim(skb, bytes_written);
 		if (!fcs_ok) {
 			atomic64_inc(&fnic_stats->misc_stats.frame_errors);
-			FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host,
+			FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 				     "fcs error.  dropping packet.\n");
 			goto drop;
 		}
@@ -886,7 +893,7 @@ static void fnic_rq_cmpl_frame_recv(struct vnic_rq *rq, struct cq_desc
 
 	if (!fcs_ok || packet_error || !fcoe_fc_crc_ok || fcoe_enc_error) {
 		atomic64_inc(&fnic_stats->misc_stats.frame_errors);
-		FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host,
+		FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 			     "fnic rq_cmpl fcoe x%x fcsok x%x"
 			     " pkterr x%x fcoe_fc_crc_ok x%x, fcoe_enc_err"
 			     " x%x\n",
@@ -967,7 +974,7 @@ int fnic_alloc_rq_frame(struct vnic_rq *rq)
 	len = FC_FRAME_HEADROOM + FC_MAX_FRAME + FC_FRAME_TAILROOM;
 	skb = dev_alloc_skb(len);
 	if (!skb) {
-		FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host,
+		FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 			     "Unable to allocate RQ sk_buff\n");
 		return -ENOMEM;
 	}
@@ -1341,12 +1348,12 @@ void fnic_handle_fip_timer(struct fnic *fnic)
 	}
 
 	vlan = list_first_entry(&fnic->vlans, struct fcoe_vlan, list);
-	FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host,
+	FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 		  "fip_timer: vlan %d state %d sol_count %d\n",
 		  vlan->vid, vlan->state, vlan->sol_count);
 	switch (vlan->state) {
 	case FIP_VLAN_USED:
-		FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host,
+		FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 			  "FIP VLAN is selected for FC transaction\n");
 		spin_unlock_irqrestore(&fnic->vlans_lock, flags);
 		break;
@@ -1365,7 +1372,7 @@ void fnic_handle_fip_timer(struct fnic *fnic)
 			 * no response on this vlan, remove  from the list.
 			 * Try the next vlan
 			 */
-			FNIC_FCS_DBG(KERN_INFO, fnic->lport->host,
+			FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
 				  "Dequeue this VLAN ID %d from list\n",
 				  vlan->vid);
 			list_del(&vlan->list);
@@ -1375,7 +1382,7 @@ void fnic_handle_fip_timer(struct fnic *fnic)
 				/* we exhausted all vlans, restart vlan disc */
 				spin_unlock_irqrestore(&fnic->vlans_lock,
 							flags);
-				FNIC_FCS_DBG(KERN_INFO, fnic->lport->host,
+				FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
 					  "fip_timer: vlan list empty, "
 					  "trigger vlan disc\n");
 				fnic_event_enq(fnic, FNIC_EVT_START_VLAN_DISC);
diff --git a/drivers/scsi/fnic/fnic_isr.c b/drivers/scsi/fnic/fnic_isr.c
index 8896758fed8c..ff85441c6cea 100644
--- a/drivers/scsi/fnic/fnic_isr.c
+++ b/drivers/scsi/fnic/fnic_isr.c
@@ -38,8 +38,13 @@ static irqreturn_t fnic_isr_legacy(int irq, void *data)
 		fnic_log_q_error(fnic);
 	}
 
+	if (pba & (1 << FNIC_INTX_DUMMY)) {
+		atomic64_inc(&fnic->fnic_stats.misc_stats.intx_dummy);
+		vnic_intr_return_all_credits(&fnic->intr[FNIC_INTX_DUMMY]);
+	}
+
 	if (pba & (1 << FNIC_INTX_WQ_RQ_COPYWQ)) {
-		work_done += fnic_wq_copy_cmpl_handler(fnic, io_completions);
+		work_done += fnic_wq_copy_cmpl_handler(fnic, io_completions, FNIC_MQ_CQ_INDEX);
 		work_done += fnic_wq_cmpl_handler(fnic, -1);
 		work_done += fnic_rq_cmpl_handler(fnic, -1);
 
@@ -60,7 +65,7 @@ static irqreturn_t fnic_isr_msi(int irq, void *data)
 	fnic->fnic_stats.misc_stats.last_isr_time = jiffies;
 	atomic64_inc(&fnic->fnic_stats.misc_stats.isr_count);
 
-	work_done += fnic_wq_copy_cmpl_handler(fnic, io_completions);
+	work_done += fnic_wq_copy_cmpl_handler(fnic, io_completions, FNIC_MQ_CQ_INDEX);
 	work_done += fnic_wq_cmpl_handler(fnic, -1);
 	work_done += fnic_rq_cmpl_handler(fnic, -1);
 
@@ -109,12 +114,22 @@ static irqreturn_t fnic_isr_msix_wq_copy(int irq, void *data)
 {
 	struct fnic *fnic = data;
 	unsigned long wq_copy_work_done = 0;
+	int i;
 
 	fnic->fnic_stats.misc_stats.last_isr_time = jiffies;
 	atomic64_inc(&fnic->fnic_stats.misc_stats.isr_count);
 
-	wq_copy_work_done = fnic_wq_copy_cmpl_handler(fnic, io_completions);
-	vnic_intr_return_credits(&fnic->intr[FNIC_MSIX_WQ_COPY],
+	i = irq - fnic->msix[0].irq_num;
+	if (i >= fnic->wq_copy_count + fnic->copy_wq_base ||
+		i < 0 || fnic->msix[i].irq_num != irq) {
+		for (i = fnic->copy_wq_base; i < fnic->wq_copy_count + fnic->copy_wq_base ; i++) {
+			if (fnic->msix[i].irq_num == irq)
+				break;
+		}
+	}
+
+	wq_copy_work_done = fnic_wq_copy_cmpl_handler(fnic, io_completions, i);
+	vnic_intr_return_credits(&fnic->intr[i],
 				 wq_copy_work_done,
 				 1 /* unmask intr */,
 				 1 /* reset intr timer */);
@@ -128,7 +143,7 @@ static irqreturn_t fnic_isr_msix_err_notify(int irq, void *data)
 	fnic->fnic_stats.misc_stats.last_isr_time = jiffies;
 	atomic64_inc(&fnic->fnic_stats.misc_stats.isr_count);
 
-	vnic_intr_return_all_credits(&fnic->intr[FNIC_MSIX_ERR_NOTIFY]);
+	vnic_intr_return_all_credits(&fnic->intr[fnic->err_intr_offset]);
 	fnic_log_q_error(fnic);
 	fnic_handle_link_event(fnic);
 
@@ -186,26 +201,30 @@ int fnic_request_intr(struct fnic *fnic)
 		fnic->msix[FNIC_MSIX_WQ].isr = fnic_isr_msix_wq;
 		fnic->msix[FNIC_MSIX_WQ].devid = fnic;
 
-		sprintf(fnic->msix[FNIC_MSIX_WQ_COPY].devname,
-			"%.11s-scsi-wq", fnic->name);
-		fnic->msix[FNIC_MSIX_WQ_COPY].isr = fnic_isr_msix_wq_copy;
-		fnic->msix[FNIC_MSIX_WQ_COPY].devid = fnic;
+		for (i = fnic->copy_wq_base; i < fnic->wq_copy_count + fnic->copy_wq_base; i++) {
+			sprintf(fnic->msix[i].devname,
+				"%.11s-scsi-wq-%d", fnic->name, i-FNIC_MSIX_WQ_COPY);
+			fnic->msix[i].isr = fnic_isr_msix_wq_copy;
+			fnic->msix[i].devid = fnic;
+		}
 
-		sprintf(fnic->msix[FNIC_MSIX_ERR_NOTIFY].devname,
+		sprintf(fnic->msix[fnic->err_intr_offset].devname,
 			"%.11s-err-notify", fnic->name);
-		fnic->msix[FNIC_MSIX_ERR_NOTIFY].isr =
+		fnic->msix[fnic->err_intr_offset].isr =
 			fnic_isr_msix_err_notify;
-		fnic->msix[FNIC_MSIX_ERR_NOTIFY].devid = fnic;
+		fnic->msix[fnic->err_intr_offset].devid = fnic;
 
-		for (i = 0; i < ARRAY_SIZE(fnic->msix); i++) {
-			err = request_irq(pci_irq_vector(fnic->pdev, i),
-					  fnic->msix[i].isr, 0,
-					  fnic->msix[i].devname,
-					  fnic->msix[i].devid);
+		for (i = 0; i < fnic->intr_count; i++) {
+			fnic->msix[i].irq_num = pci_irq_vector(fnic->pdev, i);
+
+			err = request_irq(fnic->msix[i].irq_num,
+							fnic->msix[i].isr, 0,
+							fnic->msix[i].devname,
+							fnic->msix[i].devid);
 			if (err) {
-				shost_printk(KERN_ERR, fnic->lport->host,
-					     "MSIX: request_irq"
-					     " failed %d\n", err);
+				FNIC_ISR_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+							"request_irq failed with error: %d\n",
+							err);
 				fnic_free_intr(fnic);
 				break;
 			}
@@ -220,44 +239,99 @@ int fnic_request_intr(struct fnic *fnic)
 	return err;
 }
 
-int fnic_set_intr_mode(struct fnic *fnic)
+int fnic_set_intr_mode_msix(struct fnic *fnic)
 {
 	unsigned int n = ARRAY_SIZE(fnic->rq);
 	unsigned int m = ARRAY_SIZE(fnic->wq);
-	unsigned int o = ARRAY_SIZE(fnic->wq_copy);
+	unsigned int o = ARRAY_SIZE(fnic->hw_copy_wq);
+	unsigned int min_irqs = n + m + 1 + 1; /*rq, raw wq, wq, err*/
 
 	/*
-	 * Set interrupt mode (INTx, MSI, MSI-X) depending
-	 * system capabilities.
-	 *
-	 * Try MSI-X first
-	 *
 	 * We need n RQs, m WQs, o Copy WQs, n+m+o CQs, and n+m+o+1 INTRs
 	 * (last INTR is used for WQ/RQ errors and notification area)
 	 */
-	if (fnic->rq_count >= n &&
-	    fnic->raw_wq_count >= m &&
-	    fnic->wq_copy_count >= o &&
-	    fnic->cq_count >= n + m + o) {
-		int vecs = n + m + o + 1;
-
-		if (pci_alloc_irq_vectors(fnic->pdev, vecs, vecs,
-				PCI_IRQ_MSIX) == vecs) {
+	FNIC_ISR_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+		"rq-array size: %d wq-array size: %d copy-wq array size: %d\n",
+		n, m, o);
+	FNIC_ISR_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+		"rq_count: %d raw_wq_count: %d wq_copy_count: %d cq_count: %d\n",
+		fnic->rq_count, fnic->raw_wq_count,
+		fnic->wq_copy_count, fnic->cq_count);
+
+	if (fnic->rq_count <= n && fnic->raw_wq_count <= m &&
+		fnic->wq_copy_count <= o) {
+		int vec_count = 0;
+		int vecs = fnic->rq_count + fnic->raw_wq_count + fnic->wq_copy_count + 1;
+
+		vec_count = pci_alloc_irq_vectors(fnic->pdev, min_irqs, vecs,
+					PCI_IRQ_MSIX | PCI_IRQ_AFFINITY);
+		FNIC_ISR_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+					"allocated %d MSI-X vectors\n",
+					vec_count);
+
+		if (vec_count > 0) {
+			if (vec_count < vecs) {
+				FNIC_ISR_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+				"interrupts number mismatch: vec_count: %d vecs: %d\n",
+				vec_count, vecs);
+				if (vec_count < min_irqs) {
+					FNIC_ISR_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+								"no interrupts for copy wq\n");
+					return 1;
+				}
+			}
+
 			fnic->rq_count = n;
 			fnic->raw_wq_count = m;
-			fnic->wq_copy_count = o;
-			fnic->wq_count = m + o;
-			fnic->cq_count = n + m + o;
-			fnic->intr_count = vecs;
-			fnic->err_intr_offset = FNIC_MSIX_ERR_NOTIFY;
-
-			FNIC_ISR_DBG(KERN_DEBUG, fnic->lport->host,
-				     "Using MSI-X Interrupts\n");
-			vnic_dev_set_intr_mode(fnic->vdev,
-					       VNIC_DEV_INTR_MODE_MSIX);
+			fnic->copy_wq_base = fnic->rq_count + fnic->raw_wq_count;
+			fnic->wq_copy_count = vec_count - n - m - 1;
+			fnic->wq_count = fnic->raw_wq_count + fnic->wq_copy_count;
+			if (fnic->cq_count != vec_count - 1) {
+				FNIC_ISR_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+				"CQ count: %d does not match MSI-X vector count: %d\n",
+				fnic->cq_count, vec_count);
+				fnic->cq_count = vec_count - 1;
+			}
+			fnic->intr_count = vec_count;
+			fnic->err_intr_offset = fnic->rq_count + fnic->wq_count;
+
+			FNIC_ISR_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+				"rq_count: %d raw_wq_count: %d copy_wq_base: %d\n",
+				fnic->rq_count,
+				fnic->raw_wq_count, fnic->copy_wq_base);
+
+			FNIC_ISR_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+				"wq_copy_count: %d wq_count: %d cq_count: %d\n",
+				fnic->wq_copy_count,
+				fnic->wq_count, fnic->cq_count);
+
+			FNIC_ISR_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+				"intr_count: %d err_intr_offset: %u",
+				fnic->intr_count,
+				fnic->err_intr_offset);
+
+			vnic_dev_set_intr_mode(fnic->vdev, VNIC_DEV_INTR_MODE_MSIX);
+			FNIC_ISR_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+					"fnic using MSI-X\n");
 			return 0;
 		}
 	}
+	return 1;
+}
+
+int fnic_set_intr_mode(struct fnic *fnic)
+{
+	int ret_status = 0;
+
+	/*
+	 * Set interrupt mode (INTx, MSI, MSI-X) depending
+	 * system capabilities.
+	 *
+	 * Try MSI-X first
+	 */
+	ret_status = fnic_set_intr_mode_msix(fnic);
+	if (ret_status == 0)
+		return ret_status;
 
 	/*
 	 * Next try MSI
@@ -277,7 +351,7 @@ int fnic_set_intr_mode(struct fnic *fnic)
 		fnic->intr_count = 1;
 		fnic->err_intr_offset = 0;
 
-		FNIC_ISR_DBG(KERN_DEBUG, fnic->lport->host,
+		FNIC_ISR_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 			     "Using MSI Interrupts\n");
 		vnic_dev_set_intr_mode(fnic->vdev, VNIC_DEV_INTR_MODE_MSI);
 
@@ -303,7 +377,7 @@ int fnic_set_intr_mode(struct fnic *fnic)
 		fnic->cq_count = 3;
 		fnic->intr_count = 3;
 
-		FNIC_ISR_DBG(KERN_DEBUG, fnic->lport->host,
+		FNIC_ISR_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 			     "Using Legacy Interrupts\n");
 		vnic_dev_set_intr_mode(fnic->vdev, VNIC_DEV_INTR_MODE_INTX);
 
diff --git a/drivers/scsi/fnic/fnic_main.c b/drivers/scsi/fnic/fnic_main.c
index f27f9319e0b2..5ed1d897311a 100644
--- a/drivers/scsi/fnic/fnic_main.c
+++ b/drivers/scsi/fnic/fnic_main.c
@@ -12,9 +12,11 @@
 #include <linux/pci.h>
 #include <linux/skbuff.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/spinlock.h>
 #include <linux/workqueue.h>
 #include <linux/if_ether.h>
+#include <linux/blk-mq-pci.h>
 #include <scsi/fc/fc_fip.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_transport.h>
@@ -39,6 +41,7 @@ static struct kmem_cache *fnic_sgl_cache[FNIC_SGL_NUM_CACHES];
 static struct kmem_cache *fnic_io_req_cache;
 static LIST_HEAD(fnic_list);
 static DEFINE_SPINLOCK(fnic_list_lock);
+static DEFINE_IDA(fnic_ida);
 
 /* Supported devices by fnic module */
 static struct pci_device_id fnic_id_table[] = {
@@ -113,6 +116,7 @@ static const struct scsi_host_template fnic_host_template = {
 	.shost_groups = fnic_host_groups,
 	.track_queue_depth = 1,
 	.cmd_size = sizeof(struct fnic_cmd_priv),
+	.map_queues = fnic_mq_map_queues_cpus,
 };
 
 static void
@@ -209,7 +213,7 @@ static struct fc_host_statistics *fnic_get_stats(struct Scsi_Host *host)
 	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 
 	if (ret) {
-		FNIC_MAIN_DBG(KERN_DEBUG, fnic->lport->host,
+		FNIC_MAIN_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 			      "fnic: Get vnic stats failed"
 			      " 0x%x", ret);
 		return stats;
@@ -321,7 +325,7 @@ static void fnic_reset_host_stats(struct Scsi_Host *host)
 	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 
 	if (ret) {
-		FNIC_MAIN_DBG(KERN_DEBUG, fnic->lport->host,
+		FNIC_MAIN_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 				"fnic: Reset vnic stats failed"
 				" 0x%x", ret);
 		return;
@@ -354,7 +358,7 @@ void fnic_log_q_error(struct fnic *fnic)
 	}
 
 	for (i = 0; i < fnic->wq_copy_count; i++) {
-		error_status = ioread32(&fnic->wq_copy[i].ctrl->error_status);
+		error_status = ioread32(&fnic->hw_copy_wq[i].ctrl->error_status);
 		if (error_status)
 			shost_printk(KERN_ERR, fnic->lport->host,
 				     "CWQ[%d] error_status"
@@ -389,7 +393,7 @@ static int fnic_notify_set(struct fnic *fnic)
 		err = vnic_dev_notify_set(fnic->vdev, -1);
 		break;
 	case VNIC_DEV_INTR_MODE_MSIX:
-		err = vnic_dev_notify_set(fnic->vdev, FNIC_MSIX_ERR_NOTIFY);
+		err = vnic_dev_notify_set(fnic->vdev, fnic->wq_copy_count + fnic->copy_wq_base);
 		break;
 	default:
 		shost_printk(KERN_ERR, fnic->lport->host,
@@ -475,6 +479,7 @@ static int fnic_cleanup(struct fnic *fnic)
 {
 	unsigned int i;
 	int err;
+	int raw_wq_rq_counts;
 
 	vnic_dev_disable(fnic->vdev);
 	for (i = 0; i < fnic->intr_count; i++)
@@ -491,13 +496,14 @@ static int fnic_cleanup(struct fnic *fnic)
 			return err;
 	}
 	for (i = 0; i < fnic->wq_copy_count; i++) {
-		err = vnic_wq_copy_disable(&fnic->wq_copy[i]);
+		err = vnic_wq_copy_disable(&fnic->hw_copy_wq[i]);
 		if (err)
 			return err;
+		raw_wq_rq_counts = fnic->raw_wq_count + fnic->rq_count;
+		fnic_wq_copy_cmpl_handler(fnic, -1, i + raw_wq_rq_counts);
 	}
 
 	/* Clean up completed IOs and FCS frames */
-	fnic_wq_copy_cmpl_handler(fnic, io_completions);
 	fnic_wq_cmpl_handler(fnic, -1);
 	fnic_rq_cmpl_handler(fnic, -1);
 
@@ -507,7 +513,7 @@ static int fnic_cleanup(struct fnic *fnic)
 	for (i = 0; i < fnic->rq_count; i++)
 		vnic_rq_clean(&fnic->rq[i], fnic_free_rq_buf);
 	for (i = 0; i < fnic->wq_copy_count; i++)
-		vnic_wq_copy_clean(&fnic->wq_copy[i],
+		vnic_wq_copy_clean(&fnic->hw_copy_wq[i],
 				   fnic_wq_copy_cleanup_handler);
 
 	for (i = 0; i < fnic->cq_count; i++)
@@ -560,11 +566,6 @@ static int fnic_scsi_drv_init(struct fnic *fnic)
 	host->max_cmd_len = FCOE_MAX_CMD_LEN;
 
 	host->nr_hw_queues = fnic->wq_copy_count;
-	if (host->nr_hw_queues > 1)
-		shost_printk(KERN_ERR, host,
-				"fnic: blk-mq is not supported");
-
-	host->nr_hw_queues = fnic->wq_copy_count = 1;
 
 	shost_printk(KERN_INFO, host,
 			"fnic: can_queue: %d max_lun: %llu",
@@ -577,15 +578,43 @@ static int fnic_scsi_drv_init(struct fnic *fnic)
 	return 0;
 }
 
+void fnic_mq_map_queues_cpus(struct Scsi_Host *host)
+{
+	struct fc_lport *lp = shost_priv(host);
+	struct fnic *fnic = lport_priv(lp);
+	struct pci_dev *l_pdev = fnic->pdev;
+	int intr_mode = fnic->config.intr_mode;
+	struct blk_mq_queue_map *qmap = &host->tag_set.map[HCTX_TYPE_DEFAULT];
+
+	if (intr_mode == VNIC_DEV_INTR_MODE_MSI || intr_mode == VNIC_DEV_INTR_MODE_INTX) {
+		FNIC_MAIN_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			"intr_mode is not msix\n");
+		return;
+	}
+
+	FNIC_MAIN_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+			"qmap->nr_queues: %d\n", qmap->nr_queues);
+
+	if (l_pdev == NULL) {
+		FNIC_MAIN_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+						"l_pdev is null\n");
+		return;
+	}
+
+	blk_mq_pci_map_queues(qmap, l_pdev, FNIC_PCI_OFFSET);
+}
+
 static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct Scsi_Host *host;
 	struct fc_lport *lp;
 	struct fnic *fnic;
 	mempool_t *pool;
-	int err;
+	int err = 0;
+	int fnic_id = 0;
 	int i;
 	unsigned long flags;
+	int hwq;
 
 	/*
 	 * Allocate SCSI Host and set up association between host,
@@ -597,25 +626,28 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		err = -ENOMEM;
 		goto err_out;
 	}
+
 	host = lp->host;
 	fnic = lport_priv(lp);
+
+	fnic_id = ida_alloc(&fnic_ida, GFP_KERNEL);
+	if (fnic_id < 0) {
+		pr_err("Unable to alloc fnic ID\n");
+		err = fnic_id;
+		goto err_out_ida_alloc;
+	}
 	fnic->lport = lp;
 	fnic->ctlr.lp = lp;
-
 	fnic->link_events = 0;
+	fnic->pdev = pdev;
 
 	snprintf(fnic->name, sizeof(fnic->name) - 1, "%s%d", DRV_NAME,
 		 host->host_no);
 
 	host->transportt = fnic_fc_transport;
-
+	fnic->fnic_num = fnic_id;
 	fnic_stats_debugfs_init(fnic);
 
-	/* Setup PCI resources */
-	pci_set_drvdata(pdev, fnic);
-
-	fnic->pdev = pdev;
-
 	err = pci_enable_device(pdev);
 	if (err) {
 		shost_printk(KERN_ERR, fnic->lport->host,
@@ -717,7 +749,8 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_out_dev_close;
 	}
 
-	fnic_scsi_drv_init(fnic);
+	/* Setup PCI resources */
+	pci_set_drvdata(pdev, fnic);
 
 	fnic_get_res_counts(fnic);
 
@@ -737,6 +770,16 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_out_clear_intr;
 	}
 
+	fnic_scsi_drv_init(fnic);
+
+	for (hwq = 0; hwq < fnic->wq_copy_count; hwq++) {
+		fnic->sw_copy_wq[hwq].ioreq_table_size = fnic->fnic_max_tag_id;
+		fnic->sw_copy_wq[hwq].io_req_table =
+					kzalloc((fnic->sw_copy_wq[hwq].ioreq_table_size + 1) *
+					sizeof(struct fnic_io_req *), GFP_KERNEL);
+	}
+	shost_printk(KERN_INFO, fnic->lport->host, "fnic copy wqs: %d, Q0 ioreq table size: %d\n",
+			fnic->wq_copy_count, fnic->sw_copy_wq[0].ioreq_table_size);
 
 	/* initialize all fnic locks */
 	spin_lock_init(&fnic->fnic_lock);
@@ -751,11 +794,6 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		fnic->fw_ack_index[i] = -1;
 	}
 
-	for (i = 0; i < FNIC_IO_LOCKS; i++)
-		spin_lock_init(&fnic->io_req_lock[i]);
-
-	spin_lock_init(&fnic->sgreset_lock);
-
 	err = -ENOMEM;
 	fnic->io_req_pool = mempool_create_slab_pool(2, fnic_io_req_cache);
 	if (!fnic->io_req_pool)
@@ -823,16 +861,32 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* allocate RQ buffers and post them to RQ*/
 	for (i = 0; i < fnic->rq_count; i++) {
-		vnic_rq_enable(&fnic->rq[i]);
 		err = vnic_rq_fill(&fnic->rq[i], fnic_alloc_rq_frame);
 		if (err) {
 			shost_printk(KERN_ERR, fnic->lport->host,
 				     "fnic_alloc_rq_frame can't alloc "
 				     "frame\n");
-			goto err_out_free_rq_buf;
+			goto err_out_rq_buf;
 		}
 	}
 
+	/* Enable all queues */
+	for (i = 0; i < fnic->raw_wq_count; i++)
+		vnic_wq_enable(&fnic->wq[i]);
+	for (i = 0; i < fnic->rq_count; i++) {
+		if (!ioread32(&fnic->rq[i].ctrl->enable))
+			vnic_rq_enable(&fnic->rq[i]);
+	}
+	for (i = 0; i < fnic->wq_copy_count; i++)
+		vnic_wq_copy_enable(&fnic->hw_copy_wq[i]);
+
+	err = fnic_request_intr(fnic);
+	if (err) {
+		shost_printk(KERN_ERR, fnic->lport->host,
+			     "Unable to request irq.\n");
+		goto err_out_request_intr;
+	}
+
 	/*
 	 * Initialization done with PCI system, hardware, firmware.
 	 * Add host to SCSI
@@ -841,9 +895,10 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err) {
 		shost_printk(KERN_ERR, fnic->lport->host,
 			     "fnic: scsi_add_host failed...exiting\n");
-		goto err_out_free_rq_buf;
+		goto err_out_scsi_add_host;
 	}
 
+
 	/* Start local port initiatialization */
 
 	lp->link_up = 0;
@@ -867,7 +922,7 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!fc_exch_mgr_alloc(lp, FC_CLASS_3, FCPIO_HOST_EXCH_RANGE_START,
 			       FCPIO_HOST_EXCH_RANGE_END, NULL)) {
 		err = -ENOMEM;
-		goto err_out_remove_scsi_host;
+		goto err_out_fc_exch_mgr_alloc;
 	}
 
 	fc_lport_init_stats(lp);
@@ -895,21 +950,8 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	skb_queue_head_init(&fnic->frame_queue);
 	skb_queue_head_init(&fnic->tx_queue);
 
-	/* Enable all queues */
-	for (i = 0; i < fnic->raw_wq_count; i++)
-		vnic_wq_enable(&fnic->wq[i]);
-	for (i = 0; i < fnic->wq_copy_count; i++)
-		vnic_wq_copy_enable(&fnic->wq_copy[i]);
-
 	fc_fabric_login(lp);
 
-	err = fnic_request_intr(fnic);
-	if (err) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-			     "Unable to request irq.\n");
-		goto err_out_free_exch_mgr;
-	}
-
 	vnic_dev_enable(fnic->vdev);
 
 	for (i = 0; i < fnic->intr_count; i++)
@@ -921,12 +963,15 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 err_out_free_exch_mgr:
 	fc_exch_mgr_free(lp);
-err_out_remove_scsi_host:
+err_out_fc_exch_mgr_alloc:
 	fc_remove_host(lp->host);
 	scsi_remove_host(lp->host);
-err_out_free_rq_buf:
+err_out_scsi_add_host:
+	fnic_free_intr(fnic);
+err_out_request_intr:
 	for (i = 0; i < fnic->rq_count; i++)
 		vnic_rq_clean(&fnic->rq[i], fnic_free_rq_buf);
+err_out_rq_buf:
 	vnic_dev_notify_unset(fnic->vdev);
 err_out_free_max_pool:
 	mempool_destroy(fnic->io_sgl_pool[FNIC_SGL_CACHE_MAX]);
@@ -935,6 +980,8 @@ err_out_free_dflt_pool:
 err_out_free_ioreq_pool:
 	mempool_destroy(fnic->io_req_pool);
 err_out_free_resources:
+	for (hwq = 0; hwq < fnic->wq_copy_count; hwq++)
+		kfree(fnic->sw_copy_wq[hwq].io_req_table);
 	fnic_free_vnic_resources(fnic);
 err_out_clear_intr:
 	fnic_clear_intr_mode(fnic);
@@ -951,6 +998,8 @@ err_out_disable_device:
 	pci_disable_device(pdev);
 err_out_free_hba:
 	fnic_stats_debugfs_remove(fnic);
+	ida_free(&fnic_ida, fnic->fnic_num);
+err_out_ida_alloc:
 	scsi_host_put(lp->host);
 err_out:
 	return err;
@@ -961,6 +1010,7 @@ static void fnic_remove(struct pci_dev *pdev)
 	struct fnic *fnic = pci_get_drvdata(pdev);
 	struct fc_lport *lp = fnic->lport;
 	unsigned long flags;
+	int hwq;
 
 	/*
 	 * Mark state so that the workqueue thread stops forwarding
@@ -1021,6 +1071,8 @@ static void fnic_remove(struct pci_dev *pdev)
 
 	fc_remove_host(fnic->lport->host);
 	scsi_remove_host(fnic->lport->host);
+	for (hwq = 0; hwq < fnic->wq_copy_count; hwq++)
+		kfree(fnic->sw_copy_wq[hwq].io_req_table);
 	fc_exch_mgr_free(fnic->lport);
 	vnic_dev_notify_unset(fnic->vdev);
 	fnic_free_intr(fnic);
@@ -1031,6 +1083,7 @@ static void fnic_remove(struct pci_dev *pdev)
 	fnic_iounmap(fnic);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
+	ida_free(&fnic_ida, fnic->fnic_num);
 	scsi_host_put(lp->host);
 }
 
@@ -1168,6 +1221,7 @@ static void __exit fnic_cleanup_module(void)
 	fnic_trace_free();
 	fnic_fc_trace_free();
 	fnic_debugfs_terminate();
+	ida_destroy(&fnic_ida);
 }
 
 module_init(fnic_init_module);
diff --git a/drivers/scsi/fnic/fnic_res.c b/drivers/scsi/fnic/fnic_res.c
index a1c9cfcace7f..33dd27f6f24e 100644
--- a/drivers/scsi/fnic/fnic_res.c
+++ b/drivers/scsi/fnic/fnic_res.c
@@ -57,6 +57,8 @@ int fnic_get_vnic_config(struct fnic *fnic)
 	GET_CONFIG(port_down_timeout);
 	GET_CONFIG(port_down_io_retries);
 	GET_CONFIG(luns_per_tgt);
+	GET_CONFIG(intr_mode);
+	GET_CONFIG(wq_copy_count);
 
 	c->wq_enet_desc_count =
 		min_t(u32, VNIC_FNIC_WQ_DESCS_MAX,
@@ -131,6 +133,12 @@ int fnic_get_vnic_config(struct fnic *fnic)
 	c->intr_timer = min_t(u16, VNIC_INTR_TIMER_MAX, c->intr_timer);
 	c->intr_timer_type = c->intr_timer_type;
 
+	/* for older firmware, GET_CONFIG will not return anything */
+	if (c->wq_copy_count == 0)
+		c->wq_copy_count = 1;
+
+	c->wq_copy_count = min_t(u16, FNIC_WQ_COPY_MAX, c->wq_copy_count);
+
 	shost_printk(KERN_INFO, fnic->lport->host,
 		     "vNIC MAC addr %pM "
 		     "wq/wq_copy/rq %d/%d/%d\n",
@@ -161,6 +169,10 @@ int fnic_get_vnic_config(struct fnic *fnic)
 	shost_printk(KERN_INFO, fnic->lport->host,
 		     "vNIC port dn io retries %d port dn timeout %d\n",
 		     c->port_down_io_retries, c->port_down_timeout);
+	shost_printk(KERN_INFO, fnic->lport->host,
+			"vNIC wq_copy_count: %d\n", c->wq_copy_count);
+	shost_printk(KERN_INFO, fnic->lport->host,
+			"vNIC intr mode: %d\n", c->intr_mode);
 
 	return 0;
 }
@@ -187,12 +199,25 @@ int fnic_set_nic_config(struct fnic *fnic, u8 rss_default_cpu,
 void fnic_get_res_counts(struct fnic *fnic)
 {
 	fnic->wq_count = vnic_dev_get_res_count(fnic->vdev, RES_TYPE_WQ);
-	fnic->raw_wq_count = fnic->wq_count - 1;
-	fnic->wq_copy_count = fnic->wq_count - fnic->raw_wq_count;
+	fnic->raw_wq_count = 1;
+	fnic->wq_copy_count = fnic->config.wq_copy_count;
 	fnic->rq_count = vnic_dev_get_res_count(fnic->vdev, RES_TYPE_RQ);
 	fnic->cq_count = vnic_dev_get_res_count(fnic->vdev, RES_TYPE_CQ);
 	fnic->intr_count = vnic_dev_get_res_count(fnic->vdev,
 		RES_TYPE_INTR_CTRL);
+
+	shost_printk(KERN_INFO, fnic->lport->host,
+		"vNIC fw resources wq_count: %d\n", fnic->wq_count);
+	shost_printk(KERN_INFO, fnic->lport->host,
+		"vNIC fw resources raw_wq_count: %d\n", fnic->raw_wq_count);
+	shost_printk(KERN_INFO, fnic->lport->host,
+		"vNIC fw resources wq_copy_count: %d\n", fnic->wq_copy_count);
+	shost_printk(KERN_INFO, fnic->lport->host,
+		"vNIC fw resources rq_count: %d\n", fnic->rq_count);
+	shost_printk(KERN_INFO, fnic->lport->host,
+		"vNIC fw resources cq_count: %d\n", fnic->cq_count);
+	shost_printk(KERN_INFO, fnic->lport->host,
+		"vNIC fw resources intr_count: %d\n", fnic->intr_count);
 }
 
 void fnic_free_vnic_resources(struct fnic *fnic)
@@ -203,7 +228,7 @@ void fnic_free_vnic_resources(struct fnic *fnic)
 		vnic_wq_free(&fnic->wq[i]);
 
 	for (i = 0; i < fnic->wq_copy_count; i++)
-		vnic_wq_copy_free(&fnic->wq_copy[i]);
+		vnic_wq_copy_free(&fnic->hw_copy_wq[i]);
 
 	for (i = 0; i < fnic->rq_count; i++)
 		vnic_rq_free(&fnic->rq[i]);
@@ -234,10 +259,15 @@ int fnic_alloc_vnic_resources(struct fnic *fnic)
 		     intr_mode == VNIC_DEV_INTR_MODE_MSIX ?
 		     "MSI-X" : "unknown");
 
-	shost_printk(KERN_INFO, fnic->lport->host, "vNIC resources avail: "
-		     "wq %d cp_wq %d raw_wq %d rq %d cq %d intr %d\n",
-		     fnic->wq_count, fnic->wq_copy_count, fnic->raw_wq_count,
-		     fnic->rq_count, fnic->cq_count, fnic->intr_count);
+	shost_printk(KERN_INFO, fnic->lport->host,
+			"vNIC resources avail: wq %d cp_wq %d raw_wq %d rq %d",
+			fnic->wq_count, fnic->wq_copy_count,
+			fnic->raw_wq_count, fnic->rq_count);
+
+	shost_printk(KERN_INFO, fnic->lport->host,
+			"vNIC resources avail: cq %d intr %d cpy-wq desc count %d\n",
+			fnic->cq_count, fnic->intr_count,
+			fnic->config.wq_copy_desc_count);
 
 	/* Allocate Raw WQ used for FCS frames */
 	for (i = 0; i < fnic->raw_wq_count; i++) {
@@ -250,7 +280,7 @@ int fnic_alloc_vnic_resources(struct fnic *fnic)
 
 	/* Allocate Copy WQs used for SCSI IOs */
 	for (i = 0; i < fnic->wq_copy_count; i++) {
-		err = vnic_wq_copy_alloc(fnic->vdev, &fnic->wq_copy[i],
+		err = vnic_wq_copy_alloc(fnic->vdev, &fnic->hw_copy_wq[i],
 			(fnic->raw_wq_count + i),
 			fnic->config.wq_copy_desc_count,
 			sizeof(struct fcpio_host_req));
@@ -357,7 +387,7 @@ int fnic_alloc_vnic_resources(struct fnic *fnic)
 	}
 
 	for (i = 0; i < fnic->wq_copy_count; i++) {
-		vnic_wq_copy_init(&fnic->wq_copy[i],
+		vnic_wq_copy_init(&fnic->hw_copy_wq[i],
 				  0 /* cq_index 0 - always */,
 				  error_interrupt_enable,
 				  error_interrupt_offset);
diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c
index 416d81954819..4d6db4509e75 100644
--- a/drivers/scsi/fnic/fnic_scsi.c
+++ b/drivers/scsi/fnic/fnic_scsi.c
@@ -92,20 +92,6 @@ static const char *fnic_fcpio_status_to_str(unsigned int status)
 
 static void fnic_cleanup_io(struct fnic *fnic);
 
-static inline spinlock_t *fnic_io_lock_hash(struct fnic *fnic,
-					    struct scsi_cmnd *sc)
-{
-	u32 hash = scsi_cmd_to_rq(sc)->tag & (FNIC_IO_LOCKS - 1);
-
-	return &fnic->io_req_lock[hash];
-}
-
-static inline spinlock_t *fnic_io_lock_tag(struct fnic *fnic,
-					    int tag)
-{
-	return &fnic->io_req_lock[tag & (FNIC_IO_LOCKS - 1)];
-}
-
 /*
  * Unmap the data buffer and sense buffer for an io_req,
  * also unmap and free the device-private scatter/gather list.
@@ -129,23 +115,23 @@ static void fnic_release_ioreq_buf(struct fnic *fnic,
 }
 
 /* Free up Copy Wq descriptors. Called with copy_wq lock held */
-static int free_wq_copy_descs(struct fnic *fnic, struct vnic_wq_copy *wq)
+static int free_wq_copy_descs(struct fnic *fnic, struct vnic_wq_copy *wq, unsigned int hwq)
 {
 	/* if no Ack received from firmware, then nothing to clean */
-	if (!fnic->fw_ack_recd[0])
+	if (!fnic->fw_ack_recd[hwq])
 		return 1;
 
 	/*
 	 * Update desc_available count based on number of freed descriptors
 	 * Account for wraparound
 	 */
-	if (wq->to_clean_index <= fnic->fw_ack_index[0])
-		wq->ring.desc_avail += (fnic->fw_ack_index[0]
+	if (wq->to_clean_index <= fnic->fw_ack_index[hwq])
+		wq->ring.desc_avail += (fnic->fw_ack_index[hwq]
 					- wq->to_clean_index + 1);
 	else
 		wq->ring.desc_avail += (wq->ring.desc_count
 					- wq->to_clean_index
-					+ fnic->fw_ack_index[0] + 1);
+					+ fnic->fw_ack_index[hwq] + 1);
 
 	/*
 	 * just bump clean index to ack_index+1 accounting for wraparound
@@ -153,10 +139,10 @@ static int free_wq_copy_descs(struct fnic *fnic, struct vnic_wq_copy *wq)
 	 * to_clean_index and fw_ack_index, both inclusive
 	 */
 	wq->to_clean_index =
-		(fnic->fw_ack_index[0] + 1) % wq->ring.desc_count;
+		(fnic->fw_ack_index[hwq] + 1) % wq->ring.desc_count;
 
 	/* we have processed the acks received so far */
-	fnic->fw_ack_recd[0] = 0;
+	fnic->fw_ack_recd[hwq] = 0;
 	return 0;
 }
 
@@ -170,17 +156,14 @@ __fnic_set_state_flags(struct fnic *fnic, unsigned long st_flags,
 			unsigned long clearbits)
 {
 	unsigned long flags = 0;
-	unsigned long host_lock_flags = 0;
 
 	spin_lock_irqsave(&fnic->fnic_lock, flags);
-	spin_lock_irqsave(fnic->lport->host->host_lock, host_lock_flags);
 
 	if (clearbits)
 		fnic->state_flags &= ~st_flags;
 	else
 		fnic->state_flags |= st_flags;
 
-	spin_unlock_irqrestore(fnic->lport->host->host_lock, host_lock_flags);
 	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 
 	return;
@@ -193,7 +176,7 @@ __fnic_set_state_flags(struct fnic *fnic, unsigned long st_flags,
  */
 int fnic_fw_reset_handler(struct fnic *fnic)
 {
-	struct vnic_wq_copy *wq = &fnic->wq_copy[0];
+	struct vnic_wq_copy *wq = &fnic->hw_copy_wq[0];
 	int ret = 0;
 	unsigned long flags;
 
@@ -210,7 +193,7 @@ int fnic_fw_reset_handler(struct fnic *fnic)
 	spin_lock_irqsave(&fnic->wq_copy_lock[0], flags);
 
 	if (vnic_wq_copy_desc_avail(wq) <= fnic->wq_copy_desc_low[0])
-		free_wq_copy_descs(fnic, wq);
+		free_wq_copy_descs(fnic, wq, 0);
 
 	if (!vnic_wq_copy_desc_avail(wq))
 		ret = -EAGAIN;
@@ -228,12 +211,12 @@ int fnic_fw_reset_handler(struct fnic *fnic)
 
 	if (!ret) {
 		atomic64_inc(&fnic->fnic_stats.reset_stats.fw_resets);
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
-			      "Issued fw reset\n");
+		FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+				"Issued fw reset\n");
 	} else {
 		fnic_clear_state_flags(fnic, FNIC_FLAGS_FWRESET);
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
-			      "Failed to issue fw reset\n");
+		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+				"Failed to issue fw reset\n");
 	}
 
 	return ret;
@@ -246,7 +229,7 @@ int fnic_fw_reset_handler(struct fnic *fnic)
  */
 int fnic_flogi_reg_handler(struct fnic *fnic, u32 fc_id)
 {
-	struct vnic_wq_copy *wq = &fnic->wq_copy[0];
+	struct vnic_wq_copy *wq = &fnic->hw_copy_wq[0];
 	enum fcpio_flogi_reg_format_type format;
 	struct fc_lport *lp = fnic->lport;
 	u8 gw_mac[ETH_ALEN];
@@ -256,7 +239,7 @@ int fnic_flogi_reg_handler(struct fnic *fnic, u32 fc_id)
 	spin_lock_irqsave(&fnic->wq_copy_lock[0], flags);
 
 	if (vnic_wq_copy_desc_avail(wq) <= fnic->wq_copy_desc_low[0])
-		free_wq_copy_descs(fnic, wq);
+		free_wq_copy_descs(fnic, wq, 0);
 
 	if (!vnic_wq_copy_desc_avail(wq)) {
 		ret = -EAGAIN;
@@ -276,15 +259,15 @@ int fnic_flogi_reg_handler(struct fnic *fnic, u32 fc_id)
 						fc_id, gw_mac,
 						fnic->data_src_addr,
 						lp->r_a_tov, lp->e_d_tov);
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 			      "FLOGI FIP reg issued fcid %x src %pM dest %pM\n",
 			      fc_id, fnic->data_src_addr, gw_mac);
 	} else {
 		fnic_queue_wq_copy_desc_flogi_reg(wq, SCSI_NO_TAG,
 						  format, fc_id, gw_mac);
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
-			      "FLOGI reg issued fcid %x map %d dest %pM\n",
-			      fc_id, fnic->ctlr.map_dest, gw_mac);
+		FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+			"FLOGI reg issued fcid 0x%x map %d dest 0x%p\n",
+			fc_id, fnic->ctlr.map_dest, gw_mac);
 	}
 
 	atomic64_inc(&fnic->fnic_stats.fw_stats.active_fw_reqs);
@@ -306,7 +289,9 @@ static inline int fnic_queue_wq_copy_desc(struct fnic *fnic,
 					  struct vnic_wq_copy *wq,
 					  struct fnic_io_req *io_req,
 					  struct scsi_cmnd *sc,
-					  int sg_count)
+					  int sg_count,
+					  uint32_t mqtag,
+					  uint16_t hwq)
 {
 	struct scatterlist *sg;
 	struct fc_rport *rport = starget_to_rport(scsi_target(sc->device));
@@ -314,7 +299,6 @@ static inline int fnic_queue_wq_copy_desc(struct fnic *fnic,
 	struct host_sg_desc *desc;
 	struct misc_stats *misc_stats = &fnic->fnic_stats.misc_stats;
 	unsigned int i;
-	unsigned long intr_flags;
 	int flags;
 	u8 exch_flags;
 	struct scsi_lun fc_lun;
@@ -354,14 +338,11 @@ static inline int fnic_queue_wq_copy_desc(struct fnic *fnic,
 	int_to_scsilun(sc->device->lun, &fc_lun);
 
 	/* Enqueue the descriptor in the Copy WQ */
-	spin_lock_irqsave(&fnic->wq_copy_lock[0], intr_flags);
-
-	if (vnic_wq_copy_desc_avail(wq) <= fnic->wq_copy_desc_low[0])
-		free_wq_copy_descs(fnic, wq);
+	if (vnic_wq_copy_desc_avail(wq) <= fnic->wq_copy_desc_low[hwq])
+		free_wq_copy_descs(fnic, wq, hwq);
 
 	if (unlikely(!vnic_wq_copy_desc_avail(wq))) {
-		spin_unlock_irqrestore(&fnic->wq_copy_lock[0], intr_flags);
-		FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host,
+		FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
 			  "fnic_queue_wq_copy_desc failure - no descriptors\n");
 		atomic64_inc(&misc_stats->io_cpwq_alloc_failures);
 		return SCSI_MLQUEUE_HOST_BUSY;
@@ -378,7 +359,7 @@ static inline int fnic_queue_wq_copy_desc(struct fnic *fnic,
 	    (rp->flags & FC_RP_FLAGS_RETRY))
 		exch_flags |= FCPIO_ICMND_SRFLAG_RETRY;
 
-	fnic_queue_wq_copy_desc_icmnd_16(wq, scsi_cmd_to_rq(sc)->tag,
+	fnic_queue_wq_copy_desc_icmnd_16(wq, mqtag,
 					 0, exch_flags, io_req->sgl_cnt,
 					 SCSI_SENSE_BUFFERSIZE,
 					 io_req->sgl_list_pa,
@@ -399,43 +380,52 @@ static inline int fnic_queue_wq_copy_desc(struct fnic *fnic,
 		atomic64_set(&fnic->fnic_stats.fw_stats.max_fw_reqs,
 		  atomic64_read(&fnic->fnic_stats.fw_stats.active_fw_reqs));
 
-	spin_unlock_irqrestore(&fnic->wq_copy_lock[0], intr_flags);
 	return 0;
 }
 
-/*
- * fnic_queuecommand
- * Routine to send a scsi cdb
- * Called with host_lock held and interrupts disabled.
- */
-static int fnic_queuecommand_lck(struct scsi_cmnd *sc)
+int fnic_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *sc)
 {
+	struct request *const rq = scsi_cmd_to_rq(sc);
+	uint32_t mqtag = 0;
 	void (*done)(struct scsi_cmnd *) = scsi_done;
-	const int tag = scsi_cmd_to_rq(sc)->tag;
 	struct fc_lport *lp = shost_priv(sc->device->host);
 	struct fc_rport *rport;
 	struct fnic_io_req *io_req = NULL;
 	struct fnic *fnic = lport_priv(lp);
 	struct fnic_stats *fnic_stats = &fnic->fnic_stats;
 	struct vnic_wq_copy *wq;
-	int ret;
+	int ret = 1;
 	u64 cmd_trace;
 	int sg_count = 0;
 	unsigned long flags = 0;
 	unsigned long ptr;
-	spinlock_t *io_lock = NULL;
 	int io_lock_acquired = 0;
 	struct fc_rport_libfc_priv *rp;
+	uint16_t hwq = 0;
+
+	mqtag = blk_mq_unique_tag(rq);
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
 
-	if (unlikely(fnic_chk_state_flags_locked(fnic, FNIC_FLAGS_IO_BLOCKED)))
+	if (unlikely(fnic_chk_state_flags_locked(fnic, FNIC_FLAGS_IO_BLOCKED))) {
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			"fnic IO blocked flags: 0x%lx. Returning SCSI_MLQUEUE_HOST_BUSY\n",
+			fnic->state_flags);
 		return SCSI_MLQUEUE_HOST_BUSY;
+	}
 
-	if (unlikely(fnic_chk_state_flags_locked(fnic, FNIC_FLAGS_FWRESET)))
+	if (unlikely(fnic_chk_state_flags_locked(fnic, FNIC_FLAGS_FWRESET))) {
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			"fnic flags: 0x%lx. Returning SCSI_MLQUEUE_HOST_BUSY\n",
+			fnic->state_flags);
 		return SCSI_MLQUEUE_HOST_BUSY;
+	}
 
 	rport = starget_to_rport(scsi_target(sc->device));
 	if (!rport) {
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 				"returning DID_NO_CONNECT for IO as rport is NULL\n");
 		sc->result = DID_NO_CONNECT << 16;
 		done(sc);
@@ -444,7 +434,8 @@ static int fnic_queuecommand_lck(struct scsi_cmnd *sc)
 
 	ret = fc_remote_port_chkready(rport);
 	if (ret) {
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 				"rport is not ready\n");
 		atomic64_inc(&fnic_stats->misc_stats.rport_not_ready);
 		sc->result = ret;
@@ -454,7 +445,8 @@ static int fnic_queuecommand_lck(struct scsi_cmnd *sc)
 
 	rp = rport->dd_data;
 	if (!rp || rp->rp_state == RPORT_ST_DELETE) {
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 			"rport 0x%x removed, returning DID_NO_CONNECT\n",
 			rport->port_id);
 
@@ -465,7 +457,8 @@ static int fnic_queuecommand_lck(struct scsi_cmnd *sc)
 	}
 
 	if (rp->rp_state != RPORT_ST_READY) {
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 			"rport 0x%x in state 0x%x, returning DID_IMM_RETRY\n",
 			rport->port_id, rp->rp_state);
 
@@ -474,17 +467,17 @@ static int fnic_queuecommand_lck(struct scsi_cmnd *sc)
 		return 0;
 	}
 
-	if (lp->state != LPORT_ST_READY || !(lp->link_up))
+	if (lp->state != LPORT_ST_READY || !(lp->link_up)) {
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			"state not ready: %d/link not up: %d Returning HOST_BUSY\n",
+			lp->state, lp->link_up);
 		return SCSI_MLQUEUE_HOST_BUSY;
+	}
 
 	atomic_inc(&fnic->in_flight);
 
-	/*
-	 * Release host lock, use driver resource specific locks from here.
-	 * Don't re-enable interrupts in case they were disabled prior to the
-	 * caller disabling them.
-	 */
-	spin_unlock(lp->host->host_lock);
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 	fnic_priv(sc)->state = FNIC_IOREQ_NOT_INITED;
 	fnic_priv(sc)->flags = FNIC_NO_FLAGS;
 
@@ -501,7 +494,7 @@ static int fnic_queuecommand_lck(struct scsi_cmnd *sc)
 	sg_count = scsi_dma_map(sc);
 	if (sg_count < 0) {
 		FNIC_TRACE(fnic_queuecommand, sc->device->host->host_no,
-			  tag, sc, 0, sc->cmnd[0], sg_count, fnic_priv(sc)->state);
+			  mqtag, sc, 0, sc->cmnd[0], sg_count, fnic_priv(sc)->state);
 		mempool_free(io_req, fnic->io_req_pool);
 		goto out;
 	}
@@ -536,11 +529,10 @@ static int fnic_queuecommand_lck(struct scsi_cmnd *sc)
 	}
 
 	/*
-	* Will acquire lock defore setting to IO initialized.
+	* Will acquire lock before setting to IO initialized.
 	*/
-
-	io_lock = fnic_io_lock_hash(fnic, sc);
-	spin_lock_irqsave(io_lock, flags);
+	hwq = blk_mq_unique_tag_to_hwq(mqtag);
+	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 
 	/* initialize rest of io_req */
 	io_lock_acquired = 1;
@@ -549,28 +541,39 @@ static int fnic_queuecommand_lck(struct scsi_cmnd *sc)
 	fnic_priv(sc)->state = FNIC_IOREQ_CMD_PENDING;
 	fnic_priv(sc)->io_req = io_req;
 	fnic_priv(sc)->flags |= FNIC_IO_INITIALIZED;
+	io_req->sc = sc;
+
+	if (fnic->sw_copy_wq[hwq].io_req_table[blk_mq_unique_tag_to_tag(mqtag)] != NULL) {
+		WARN(1, "fnic<%d>: %s: hwq: %d tag 0x%x already exists\n",
+				fnic->fnic_num, __func__, hwq, blk_mq_unique_tag_to_tag(mqtag));
+		return SCSI_MLQUEUE_HOST_BUSY;
+	}
+
+	fnic->sw_copy_wq[hwq].io_req_table[blk_mq_unique_tag_to_tag(mqtag)] = io_req;
+	io_req->tag = mqtag;
 
 	/* create copy wq desc and enqueue it */
-	wq = &fnic->wq_copy[0];
-	ret = fnic_queue_wq_copy_desc(fnic, wq, io_req, sc, sg_count);
+	wq = &fnic->hw_copy_wq[hwq];
+	atomic64_inc(&fnic_stats->io_stats.ios[hwq]);
+	ret = fnic_queue_wq_copy_desc(fnic, wq, io_req, sc, sg_count, mqtag, hwq);
 	if (ret) {
 		/*
 		 * In case another thread cancelled the request,
 		 * refetch the pointer under the lock.
 		 */
 		FNIC_TRACE(fnic_queuecommand, sc->device->host->host_no,
-			  tag, sc, 0, 0, 0, fnic_flags_and_state(sc));
+			  mqtag, sc, 0, 0, 0, fnic_flags_and_state(sc));
 		io_req = fnic_priv(sc)->io_req;
 		fnic_priv(sc)->io_req = NULL;
+		if (io_req)
+			fnic->sw_copy_wq[hwq].io_req_table[blk_mq_unique_tag_to_tag(mqtag)] = NULL;
 		fnic_priv(sc)->state = FNIC_IOREQ_CMD_COMPLETE;
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		if (io_req) {
 			fnic_release_ioreq_buf(fnic, io_req, sc);
 			mempool_free(io_req, fnic->io_req_pool);
 		}
 		atomic_dec(&fnic->in_flight);
-		/* acquire host lock before returning to SCSI */
-		spin_lock(lp->host->host_lock);
 		return ret;
 	} else {
 		atomic64_inc(&fnic_stats->io_stats.active_ios);
@@ -590,20 +593,17 @@ out:
 			sc->cmnd[5]);
 
 	FNIC_TRACE(fnic_queuecommand, sc->device->host->host_no,
-		   tag, sc, io_req, sg_count, cmd_trace,
+		   mqtag, sc, io_req, sg_count, cmd_trace,
 		   fnic_flags_and_state(sc));
 
 	/* if only we issued IO, will we have the io lock */
 	if (io_lock_acquired)
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 
 	atomic_dec(&fnic->in_flight);
-	/* acquire host lock before returning to SCSI */
-	spin_lock(lp->host->host_lock);
 	return ret;
 }
 
-DEF_SCSI_QCMD(fnic_queuecommand)
 
 /*
  * fnic_fcpio_fw_reset_cmpl_handler
@@ -636,15 +636,14 @@ static int fnic_fcpio_fw_reset_cmpl_handler(struct fnic *fnic,
 	if (fnic->state == FNIC_IN_FC_TRANS_ETH_MODE) {
 		/* Check status of reset completion */
 		if (!hdr_status) {
-			FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
-				      "reset cmpl success\n");
+			FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+					"reset cmpl success\n");
 			/* Ready to send flogi out */
 			fnic->state = FNIC_IN_ETH_MODE;
 		} else {
-			FNIC_SCSI_DBG(KERN_DEBUG,
-				      fnic->lport->host,
-				      "fnic fw_reset : failed %s\n",
-				      fnic_fcpio_status_to_str(hdr_status));
+			FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+				"reset failed with header status: %s\n",
+				fnic_fcpio_status_to_str(hdr_status));
 
 			/*
 			 * Unable to change to eth mode, cannot send out flogi
@@ -657,10 +656,9 @@ static int fnic_fcpio_fw_reset_cmpl_handler(struct fnic *fnic,
 			ret = -1;
 		}
 	} else {
-		FNIC_SCSI_DBG(KERN_DEBUG,
-			      fnic->lport->host,
-			      "Unexpected state %s while processing"
-			      " reset cmpl\n", fnic_state_to_str(fnic->state));
+		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			"Unexpected state while processing reset completion: %s\n",
+			fnic_state_to_str(fnic->state));
 		atomic64_inc(&reset_stats->fw_reset_failures);
 		ret = -1;
 	}
@@ -711,19 +709,19 @@ static int fnic_fcpio_flogi_reg_cmpl_handler(struct fnic *fnic,
 
 		/* Check flogi registration completion status */
 		if (!hdr_status) {
-			FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+			FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 				      "flog reg succeeded\n");
 			fnic->state = FNIC_IN_FC_MODE;
 		} else {
 			FNIC_SCSI_DBG(KERN_DEBUG,
-				      fnic->lport->host,
+				      fnic->lport->host, fnic->fnic_num,
 				      "fnic flogi reg :failed %s\n",
 				      fnic_fcpio_status_to_str(hdr_status));
 			fnic->state = FNIC_IN_ETH_MODE;
 			ret = -1;
 		}
 	} else {
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 			      "Unexpected fnic state %s while"
 			      " processing flogi reg completion\n",
 			      fnic_state_to_str(fnic->state));
@@ -780,20 +778,21 @@ static inline void fnic_fcpio_ack_handler(struct fnic *fnic,
 	u16 request_out = desc->u.ack.request_out;
 	unsigned long flags;
 	u64 *ox_id_tag = (u64 *)(void *)desc;
+	unsigned int wq_index = cq_index;
 
 	/* mark the ack state */
-	wq = &fnic->wq_copy[cq_index - fnic->raw_wq_count - fnic->rq_count];
-	spin_lock_irqsave(&fnic->wq_copy_lock[0], flags);
+	wq = &fnic->hw_copy_wq[cq_index];
+	spin_lock_irqsave(&fnic->wq_copy_lock[wq_index], flags);
 
 	fnic->fnic_stats.misc_stats.last_ack_time = jiffies;
 	if (is_ack_index_in_range(wq, request_out)) {
-		fnic->fw_ack_index[0] = request_out;
-		fnic->fw_ack_recd[0] = 1;
+		fnic->fw_ack_index[wq_index] = request_out;
+		fnic->fw_ack_recd[wq_index] = 1;
 	} else
 		atomic64_inc(
 			&fnic->fnic_stats.misc_stats.ack_index_out_of_range);
 
-	spin_unlock_irqrestore(&fnic->wq_copy_lock[0], flags);
+	spin_unlock_irqrestore(&fnic->wq_copy_lock[wq_index], flags);
 	FNIC_TRACE(fnic_fcpio_ack_handler,
 		  fnic->lport->host->host_no, 0, 0, ox_id_tag[2], ox_id_tag[3],
 		  ox_id_tag[4], ox_id_tag[5]);
@@ -803,12 +802,12 @@ static inline void fnic_fcpio_ack_handler(struct fnic *fnic,
  * fnic_fcpio_icmnd_cmpl_handler
  * Routine to handle icmnd completions
  */
-static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic,
+static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic, unsigned int cq_index,
 					 struct fcpio_fw_req *desc)
 {
 	u8 type;
 	u8 hdr_status;
-	struct fcpio_tag tag;
+	struct fcpio_tag ftag;
 	u32 id;
 	u64 xfer_len = 0;
 	struct fcpio_icmnd_cmpl *icmnd_cmpl;
@@ -816,27 +815,47 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic,
 	struct scsi_cmnd *sc;
 	struct fnic_stats *fnic_stats = &fnic->fnic_stats;
 	unsigned long flags;
-	spinlock_t *io_lock;
 	u64 cmd_trace;
 	unsigned long start_time;
 	unsigned long io_duration_time;
+	unsigned int hwq = 0;
+	unsigned int mqtag = 0;
+	unsigned int tag = 0;
 
 	/* Decode the cmpl description to get the io_req id */
-	fcpio_header_dec(&desc->hdr, &type, &hdr_status, &tag);
-	fcpio_tag_id_dec(&tag, &id);
+	fcpio_header_dec(&desc->hdr, &type, &hdr_status, &ftag);
+	fcpio_tag_id_dec(&ftag, &id);
 	icmnd_cmpl = &desc->u.icmnd_cmpl;
 
-	if (id >= fnic->fnic_max_tag_id) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-			"Tag out of range tag %x hdr status = %s\n",
-			     id, fnic_fcpio_status_to_str(hdr_status));
+	mqtag = id;
+	tag = blk_mq_unique_tag_to_tag(mqtag);
+	hwq = blk_mq_unique_tag_to_hwq(mqtag);
+
+	if (hwq != cq_index) {
+		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			"hwq: %d mqtag: 0x%x tag: 0x%x cq index: %d ",
+			hwq, mqtag, tag, cq_index);
+		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			"hdr status: %s icmnd completion on the wrong queue\n",
+			fnic_fcpio_status_to_str(hdr_status));
+	}
+
+	if (tag >= fnic->fnic_max_tag_id) {
+		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			"hwq: %d mqtag: 0x%x tag: 0x%x cq index: %d ",
+			hwq, mqtag, tag, cq_index);
+		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			"hdr status: %s Out of range tag\n",
+			fnic_fcpio_status_to_str(hdr_status));
 		return;
 	}
+	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 
 	sc = scsi_host_find_tag(fnic->lport->host, id);
 	WARN_ON_ONCE(!sc);
 	if (!sc) {
 		atomic64_inc(&fnic_stats->io_stats.sc_null);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		shost_printk(KERN_ERR, fnic->lport->host,
 			  "icmnd_cmpl sc is null - "
 			  "hdr status = %s tag = 0x%x desc = 0x%p\n",
@@ -852,14 +871,19 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic,
 		return;
 	}
 
-	io_lock = fnic_io_lock_hash(fnic, sc);
-	spin_lock_irqsave(io_lock, flags);
 	io_req = fnic_priv(sc)->io_req;
+	if (fnic->sw_copy_wq[hwq].io_req_table[tag] != io_req) {
+		WARN(1, "%s: %d: hwq: %d mqtag: 0x%x tag: 0x%x io_req tag mismatch\n",
+			__func__, __LINE__, hwq, mqtag, tag);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
+		return;
+	}
+
 	WARN_ON_ONCE(!io_req);
 	if (!io_req) {
 		atomic64_inc(&fnic_stats->io_stats.ioreq_null);
 		fnic_priv(sc)->flags |= FNIC_IO_REQ_NULL;
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		shost_printk(KERN_ERR, fnic->lport->host,
 			  "icmnd_cmpl io_req is null - "
 			  "hdr status = %s tag = 0x%x sc 0x%p\n",
@@ -883,11 +907,11 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic,
 		 */
 		fnic_priv(sc)->flags |= FNIC_IO_DONE;
 		fnic_priv(sc)->flags |= FNIC_IO_ABTS_PENDING;
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		if(FCPIO_ABORTED == hdr_status)
 			fnic_priv(sc)->flags |= FNIC_IO_ABORTED;
 
-		FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host,
+		FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
 			"icmnd_cmpl abts pending "
 			  "hdr status = %s tag = 0x%x sc = 0x%p "
 			  "scsi_status = %x residual = %d\n",
@@ -971,7 +995,11 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic,
 
 	/* Break link with the SCSI command */
 	fnic_priv(sc)->io_req = NULL;
+	io_req->sc = NULL;
 	fnic_priv(sc)->flags |= FNIC_IO_DONE;
+	fnic->sw_copy_wq[hwq].io_req_table[tag] = NULL;
+
+	spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 
 	if (hdr_status != FCPIO_SUCCESS) {
 		atomic64_inc(&fnic_stats->io_stats.io_failures);
@@ -1005,7 +1033,6 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic,
 
 	/* Call SCSI completion function to complete the IO */
 	scsi_done(sc);
-	spin_unlock_irqrestore(io_lock, flags);
 
 	mempool_free(io_req, fnic->io_req_pool);
 
@@ -1042,7 +1069,7 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic,
 /* fnic_fcpio_itmf_cmpl_handler
  * Routine to handle itmf completions
  */
-static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic,
+static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_index,
 					struct fcpio_fw_req *desc)
 {
 	u8 type;
@@ -1056,51 +1083,73 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic,
 	struct terminate_stats *term_stats = &fnic->fnic_stats.term_stats;
 	struct misc_stats *misc_stats = &fnic->fnic_stats.misc_stats;
 	unsigned long flags;
-	spinlock_t *io_lock;
 	unsigned long start_time;
+	unsigned int hwq = cq_index;
+	unsigned int mqtag;
 	unsigned int tag;
 
 	fcpio_header_dec(&desc->hdr, &type, &hdr_status, &ftag);
 	fcpio_tag_id_dec(&ftag, &id);
 
-	tag = id & FNIC_TAG_MASK;
-	if (tag == fnic->fnic_max_tag_id) {
-		if (!(id & FNIC_TAG_DEV_RST)) {
-			shost_printk(KERN_ERR, fnic->lport->host,
-						"Tag out of range id 0x%x hdr status = %s\n",
-						id, fnic_fcpio_status_to_str(hdr_status));
-			return;
-		}
-	} else if (tag > fnic->fnic_max_tag_id) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-					"Tag out of range tag 0x%x hdr status = %s\n",
-					tag, fnic_fcpio_status_to_str(hdr_status));
+	mqtag = id & FNIC_TAG_MASK;
+	tag = blk_mq_unique_tag_to_tag(id & FNIC_TAG_MASK);
+	hwq = blk_mq_unique_tag_to_hwq(id & FNIC_TAG_MASK);
+
+	if (hwq != cq_index) {
+		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			"hwq: %d mqtag: 0x%x tag: 0x%x cq index: %d ",
+			hwq, mqtag, tag, cq_index);
+		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			"hdr status: %s ITMF completion on the wrong queue\n",
+			fnic_fcpio_status_to_str(hdr_status));
+	}
+
+	if (tag > fnic->fnic_max_tag_id) {
+		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			"hwq: %d mqtag: 0x%x tag: 0x%x cq index: %d ",
+			hwq, mqtag, tag, cq_index);
+		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			"hdr status: %s Tag out of range\n",
+			fnic_fcpio_status_to_str(hdr_status));
+		return;
+	}  else if ((tag == fnic->fnic_max_tag_id) && !(id & FNIC_TAG_DEV_RST)) {
+		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			"hwq: %d mqtag: 0x%x tag: 0x%x cq index: %d ",
+			hwq, mqtag, tag, cq_index);
+		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			"hdr status: %s Tag out of range\n",
+			fnic_fcpio_status_to_str(hdr_status));
 		return;
 	}
 
-	if ((tag == fnic->fnic_max_tag_id) && (id & FNIC_TAG_DEV_RST)) {
-		sc = fnic->sgreset_sc;
-		io_lock = &fnic->sgreset_lock;
+	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
+
+	/* If it is sg3utils allocated SC then tag_id
+	 * is max_tag_id and SC is retrieved from io_req
+	 */
+	if ((mqtag == fnic->fnic_max_tag_id) && (id & FNIC_TAG_DEV_RST)) {
+		io_req = fnic->sw_copy_wq[hwq].io_req_table[tag];
+		if (io_req)
+			sc = io_req->sc;
 	} else {
 		sc = scsi_host_find_tag(fnic->lport->host, id & FNIC_TAG_MASK);
-		io_lock = fnic_io_lock_hash(fnic, sc);
 	}
 
 	WARN_ON_ONCE(!sc);
 	if (!sc) {
 		atomic64_inc(&fnic_stats->io_stats.sc_null);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		shost_printk(KERN_ERR, fnic->lport->host,
 			  "itmf_cmpl sc is null - hdr status = %s tag = 0x%x\n",
 			  fnic_fcpio_status_to_str(hdr_status), tag);
 		return;
 	}
 
-	spin_lock_irqsave(io_lock, flags);
 	io_req = fnic_priv(sc)->io_req;
 	WARN_ON_ONCE(!io_req);
 	if (!io_req) {
 		atomic64_inc(&fnic_stats->io_stats.ioreq_null);
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		fnic_priv(sc)->flags |= FNIC_IO_ABT_TERM_REQ_NULL;
 		shost_printk(KERN_ERR, fnic->lport->host,
 			  "itmf_cmpl io_req is null - "
@@ -1113,17 +1162,22 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic,
 	if ((id & FNIC_TAG_ABORT) && (id & FNIC_TAG_DEV_RST)) {
 		/* Abort and terminate completion of device reset req */
 		/* REVISIT : Add asserts about various flags */
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
-			      "dev reset abts cmpl recd. id %x status %s\n",
-			      id, fnic_fcpio_status_to_str(hdr_status));
+		FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+			"hwq: %d mqtag: 0x%x tag: 0x%x hst: %s Abt/term completion received\n",
+			hwq, mqtag, tag,
+			fnic_fcpio_status_to_str(hdr_status));
 		fnic_priv(sc)->state = FNIC_IOREQ_ABTS_COMPLETE;
 		fnic_priv(sc)->abts_status = hdr_status;
 		fnic_priv(sc)->flags |= FNIC_DEV_RST_DONE;
 		if (io_req->abts_done)
 			complete(io_req->abts_done);
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 	} else if (id & FNIC_TAG_ABORT) {
 		/* Completion of abort cmd */
+		shost_printk(KERN_DEBUG, fnic->lport->host,
+			"hwq: %d mqtag: 0x%x tag: 0x%x Abort header status: %s\n",
+			hwq, mqtag, tag,
+			fnic_fcpio_status_to_str(hdr_status));
 		switch (hdr_status) {
 		case FCPIO_SUCCESS:
 			break;
@@ -1135,7 +1189,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic,
 					&term_stats->terminate_fw_timeouts);
 			break;
 		case FCPIO_ITMF_REJECTED:
-			FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host,
+			FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
 				"abort reject recd. id %d\n",
 				(int)(id & FNIC_TAG_MASK));
 			break;
@@ -1156,7 +1210,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic,
 		}
 		if (fnic_priv(sc)->state != FNIC_IOREQ_ABTS_PENDING) {
 			/* This is a late completion. Ignore it */
-			spin_unlock_irqrestore(io_lock, flags);
+			spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 			return;
 		}
 
@@ -1170,7 +1224,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic,
 		if (!(fnic_priv(sc)->flags & (FNIC_IO_ABORTED | FNIC_IO_DONE)))
 			atomic64_inc(&misc_stats->no_icmnd_itmf_cmpls);
 
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 			      "abts cmpl recd. id %d status %s\n",
 			      (int)(id & FNIC_TAG_MASK),
 			      fnic_fcpio_status_to_str(hdr_status));
@@ -1182,14 +1236,19 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic,
 		 */
 		if (io_req->abts_done) {
 			complete(io_req->abts_done);
-			spin_unlock_irqrestore(io_lock, flags);
+			spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
+			shost_printk(KERN_INFO, fnic->lport->host,
+					"hwq: %d mqtag: 0x%x tag: 0x%x Waking up abort thread\n",
+					hwq, mqtag, tag);
 		} else {
-			FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
-				      "abts cmpl, completing IO\n");
+			FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+				"hwq: %d mqtag: 0x%x tag: 0x%x hst: %s Completing IO\n",
+				hwq, mqtag,
+				tag, fnic_fcpio_status_to_str(hdr_status));
 			fnic_priv(sc)->io_req = NULL;
 			sc->result = (DID_ERROR << 16);
-
-			spin_unlock_irqrestore(io_lock, flags);
+			fnic->sw_copy_wq[hwq].io_req_table[tag] = NULL;
+			spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 
 			fnic_release_ioreq_buf(fnic, io_req, sc);
 			mempool_free(io_req, fnic->io_req_pool);
@@ -1213,29 +1272,32 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic,
 		}
 	} else if (id & FNIC_TAG_DEV_RST) {
 		/* Completion of device reset */
+		shost_printk(KERN_INFO, fnic->lport->host,
+			"hwq: %d mqtag: 0x%x tag: 0x%x DR hst: %s\n",
+			hwq, mqtag,
+			tag, fnic_fcpio_status_to_str(hdr_status));
 		fnic_priv(sc)->lr_status = hdr_status;
 		if (fnic_priv(sc)->state == FNIC_IOREQ_ABTS_PENDING) {
-			spin_unlock_irqrestore(io_lock, flags);
+			spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 			fnic_priv(sc)->flags |= FNIC_DEV_RST_ABTS_PENDING;
 			FNIC_TRACE(fnic_fcpio_itmf_cmpl_handler,
 				  sc->device->host->host_no, id, sc,
 				  jiffies_to_msecs(jiffies - start_time),
 				  desc, 0, fnic_flags_and_state(sc));
-			FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
-				"Terminate pending "
-				"dev reset cmpl recd. id %d status %s\n",
-				(int)(id & FNIC_TAG_MASK),
-				fnic_fcpio_status_to_str(hdr_status));
+			FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+				"hwq: %d mqtag: 0x%x tag: 0x%x hst: %s Terminate pending\n",
+				hwq, mqtag,
+				tag, fnic_fcpio_status_to_str(hdr_status));
 			return;
 		}
 		if (fnic_priv(sc)->flags & FNIC_DEV_RST_TIMED_OUT) {
 			/* Need to wait for terminate completion */
-			spin_unlock_irqrestore(io_lock, flags);
+			spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 			FNIC_TRACE(fnic_fcpio_itmf_cmpl_handler,
 				  sc->device->host->host_no, id, sc,
 				  jiffies_to_msecs(jiffies - start_time),
 				  desc, 0, fnic_flags_and_state(sc));
-			FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+			FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 				"dev reset cmpl recd after time out. "
 				"id %d status %s\n",
 				(int)(id & FNIC_TAG_MASK),
@@ -1244,19 +1306,19 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic,
 		}
 		fnic_priv(sc)->state = FNIC_IOREQ_CMD_COMPLETE;
 		fnic_priv(sc)->flags |= FNIC_DEV_RST_DONE;
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
-			      "dev reset cmpl recd. id %d status %s\n",
-			      (int)(id & FNIC_TAG_MASK),
-			      fnic_fcpio_status_to_str(hdr_status));
+		FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+			"hwq: %d mqtag: 0x%x tag: 0x%x hst: %s DR completion received\n",
+			hwq, mqtag,
+			tag, fnic_fcpio_status_to_str(hdr_status));
 		if (io_req->dr_done)
 			complete(io_req->dr_done);
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 
 	} else {
 		shost_printk(KERN_ERR, fnic->lport->host,
-			     "Unexpected itmf io state %s tag %x\n",
-			     fnic_ioreq_state_to_str(fnic_priv(sc)->state), id);
-		spin_unlock_irqrestore(io_lock, flags);
+			"%s: Unexpected itmf io state: hwq: %d tag 0x%x %s\n",
+			__func__, hwq, id, fnic_ioreq_state_to_str(fnic_priv(sc)->state));
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 	}
 
 }
@@ -1283,17 +1345,19 @@ static int fnic_fcpio_cmpl_handler(struct vnic_dev *vdev,
 		break;
 	}
 
+	cq_index -= fnic->copy_wq_base;
+
 	switch (desc->hdr.type) {
 	case FCPIO_ACK: /* fw copied copy wq desc to its queue */
 		fnic_fcpio_ack_handler(fnic, cq_index, desc);
 		break;
 
 	case FCPIO_ICMND_CMPL: /* fw completed a command */
-		fnic_fcpio_icmnd_cmpl_handler(fnic, desc);
+		fnic_fcpio_icmnd_cmpl_handler(fnic, cq_index, desc);
 		break;
 
 	case FCPIO_ITMF_CMPL: /* fw completed itmf (abort cmd, lun reset)*/
-		fnic_fcpio_itmf_cmpl_handler(fnic, desc);
+		fnic_fcpio_itmf_cmpl_handler(fnic, cq_index, desc);
 		break;
 
 	case FCPIO_FLOGI_REG_CMPL: /* fw completed flogi_reg */
@@ -1306,7 +1370,7 @@ static int fnic_fcpio_cmpl_handler(struct vnic_dev *vdev,
 		break;
 
 	default:
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 			      "firmware completion type %d\n",
 			      desc->hdr.type);
 		break;
@@ -1319,10 +1383,8 @@ static int fnic_fcpio_cmpl_handler(struct vnic_dev *vdev,
  * fnic_wq_copy_cmpl_handler
  * Routine to process wq copy
  */
-int fnic_wq_copy_cmpl_handler(struct fnic *fnic, int copy_work_to_do)
+int fnic_wq_copy_cmpl_handler(struct fnic *fnic, int copy_work_to_do, unsigned int cq_index)
 {
-	unsigned int wq_work_done = 0;
-	unsigned int i, cq_index;
 	unsigned int cur_work_done;
 	struct misc_stats *misc_stats = &fnic->fnic_stats.misc_stats;
 	u64 start_jiffies = 0;
@@ -1330,44 +1392,51 @@ int fnic_wq_copy_cmpl_handler(struct fnic *fnic, int copy_work_to_do)
 	u64 delta_jiffies = 0;
 	u64 delta_ms = 0;
 
-	for (i = 0; i < fnic->wq_copy_count; i++) {
-		cq_index = i + fnic->raw_wq_count + fnic->rq_count;
-
-		start_jiffies = jiffies;
-		cur_work_done = vnic_cq_copy_service(&fnic->cq[cq_index],
-						     fnic_fcpio_cmpl_handler,
-						     copy_work_to_do);
-		end_jiffies = jiffies;
-
-		wq_work_done += cur_work_done;
-		delta_jiffies = end_jiffies - start_jiffies;
-		if (delta_jiffies >
-			(u64) atomic64_read(&misc_stats->max_isr_jiffies)) {
-			atomic64_set(&misc_stats->max_isr_jiffies,
-					delta_jiffies);
-			delta_ms = jiffies_to_msecs(delta_jiffies);
-			atomic64_set(&misc_stats->max_isr_time_ms, delta_ms);
-			atomic64_set(&misc_stats->corr_work_done,
-					cur_work_done);
-		}
+	start_jiffies = jiffies;
+	cur_work_done = vnic_cq_copy_service(&fnic->cq[cq_index],
+					fnic_fcpio_cmpl_handler,
+					copy_work_to_do);
+	end_jiffies = jiffies;
+	delta_jiffies = end_jiffies - start_jiffies;
+	if (delta_jiffies > (u64) atomic64_read(&misc_stats->max_isr_jiffies)) {
+		atomic64_set(&misc_stats->max_isr_jiffies, delta_jiffies);
+		delta_ms = jiffies_to_msecs(delta_jiffies);
+		atomic64_set(&misc_stats->max_isr_time_ms, delta_ms);
+		atomic64_set(&misc_stats->corr_work_done, cur_work_done);
 	}
-	return wq_work_done;
+
+	return cur_work_done;
 }
 
 static bool fnic_cleanup_io_iter(struct scsi_cmnd *sc, void *data)
 {
-	const int tag = scsi_cmd_to_rq(sc)->tag;
+	struct request *const rq = scsi_cmd_to_rq(sc);
 	struct fnic *fnic = data;
 	struct fnic_io_req *io_req;
 	unsigned long flags = 0;
-	spinlock_t *io_lock;
 	unsigned long start_time = 0;
 	struct fnic_stats *fnic_stats = &fnic->fnic_stats;
+	uint16_t hwq = 0;
+	int tag;
+	int mqtag;
 
-	io_lock = fnic_io_lock_tag(fnic, tag);
-	spin_lock_irqsave(io_lock, flags);
+	mqtag = blk_mq_unique_tag(rq);
+	hwq = blk_mq_unique_tag_to_hwq(mqtag);
+	tag = blk_mq_unique_tag_to_tag(mqtag);
+
+	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
+
+	fnic->sw_copy_wq[hwq].io_req_table[tag] = NULL;
 
 	io_req = fnic_priv(sc)->io_req;
+	if (!io_req) {
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
+		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			"hwq: %d mqtag: 0x%x tag: 0x%x flags: 0x%x No ioreq. Returning\n",
+			hwq, mqtag, tag, fnic_priv(sc)->flags);
+		return true;
+	}
+
 	if ((fnic_priv(sc)->flags & FNIC_DEVICE_RESET) &&
 	    !(fnic_priv(sc)->flags & FNIC_DEV_RST_DONE)) {
 		/*
@@ -1379,20 +1448,16 @@ static bool fnic_cleanup_io_iter(struct scsi_cmnd *sc, void *data)
 			complete(io_req->dr_done);
 		else if (io_req && io_req->abts_done)
 			complete(io_req->abts_done);
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		return true;
 	} else if (fnic_priv(sc)->flags & FNIC_DEVICE_RESET) {
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		return true;
 	}
-	if (!io_req) {
-		spin_unlock_irqrestore(io_lock, flags);
-		goto cleanup_scsi_cmd;
-	}
 
 	fnic_priv(sc)->io_req = NULL;
-
-	spin_unlock_irqrestore(io_lock, flags);
+	io_req->sc = NULL;
+	spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 
 	/*
 	 * If there is a scsi_cmnd associated with this io_req, then
@@ -1402,23 +1467,16 @@ static bool fnic_cleanup_io_iter(struct scsi_cmnd *sc, void *data)
 	fnic_release_ioreq_buf(fnic, io_req, sc);
 	mempool_free(io_req, fnic->io_req_pool);
 
-cleanup_scsi_cmd:
 	sc->result = DID_TRANSPORT_DISRUPTED << 16;
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
-		      "fnic_cleanup_io: tag:0x%x : sc:0x%p duration = %lu DID_TRANSPORT_DISRUPTED\n",
-		      tag, sc, jiffies - start_time);
+	FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+		"mqtag:0x%x tag: 0x%x sc:0x%p duration = %lu DID_TRANSPORT_DISRUPTED\n",
+		mqtag, tag, sc, (jiffies - start_time));
 
 	if (atomic64_read(&fnic->io_cmpl_skip))
 		atomic64_dec(&fnic->io_cmpl_skip);
 	else
 		atomic64_inc(&fnic_stats->io_stats.io_completions);
 
-	/* Complete the command to SCSI */
-	if (!(fnic_priv(sc)->flags & FNIC_IO_ISSUED))
-		shost_printk(KERN_ERR, fnic->lport->host,
-			     "Calling done for IO not issued to fw: tag:0x%x sc:0x%p\n",
-			     tag, sc);
-
 	FNIC_TRACE(fnic_cleanup_io,
 		   sc->device->host->host_no, tag, sc,
 		   jiffies_to_msecs(jiffies - start_time),
@@ -1447,8 +1505,8 @@ void fnic_wq_copy_cleanup_handler(struct vnic_wq_copy *wq,
 	struct fnic_io_req *io_req;
 	struct scsi_cmnd *sc;
 	unsigned long flags;
-	spinlock_t *io_lock;
 	unsigned long start_time = 0;
+	uint16_t hwq;
 
 	/* get the tag reference */
 	fcpio_tag_id_dec(&desc->hdr.tag, &id);
@@ -1461,8 +1519,8 @@ void fnic_wq_copy_cleanup_handler(struct vnic_wq_copy *wq,
 	if (!sc)
 		return;
 
-	io_lock = fnic_io_lock_hash(fnic, sc);
-	spin_lock_irqsave(io_lock, flags);
+	hwq = blk_mq_unique_tag_to_hwq(id);
+	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 
 	/* Get the IO context which this desc refers to */
 	io_req = fnic_priv(sc)->io_req;
@@ -1470,13 +1528,15 @@ void fnic_wq_copy_cleanup_handler(struct vnic_wq_copy *wq,
 	/* fnic interrupts are turned off by now */
 
 	if (!io_req) {
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		goto wq_copy_cleanup_scsi_cmd;
 	}
 
 	fnic_priv(sc)->io_req = NULL;
+	io_req->sc = NULL;
+	fnic->sw_copy_wq[hwq].io_req_table[blk_mq_unique_tag_to_tag(id)] = NULL;
 
-	spin_unlock_irqrestore(io_lock, flags);
+	spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 
 	start_time = io_req->start_time;
 	fnic_release_ioreq_buf(fnic, io_req, sc);
@@ -1484,7 +1544,7 @@ void fnic_wq_copy_cleanup_handler(struct vnic_wq_copy *wq,
 
 wq_copy_cleanup_scsi_cmd:
 	sc->result = DID_NO_CONNECT << 16;
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, "wq_copy_cleanup_handler:"
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, "wq_copy_cleanup_handler:"
 		      " DID_NO_CONNECT\n");
 
 	FNIC_TRACE(fnic_wq_copy_cleanup_handler,
@@ -1500,31 +1560,31 @@ wq_copy_cleanup_scsi_cmd:
 
 static inline int fnic_queue_abort_io_req(struct fnic *fnic, int tag,
 					  u32 task_req, u8 *fc_lun,
-					  struct fnic_io_req *io_req)
+					  struct fnic_io_req *io_req,
+					  unsigned int hwq)
 {
-	struct vnic_wq_copy *wq = &fnic->wq_copy[0];
-	struct Scsi_Host *host = fnic->lport->host;
+	struct vnic_wq_copy *wq = &fnic->hw_copy_wq[hwq];
 	struct misc_stats *misc_stats = &fnic->fnic_stats.misc_stats;
 	unsigned long flags;
 
-	spin_lock_irqsave(host->host_lock, flags);
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
 	if (unlikely(fnic_chk_state_flags_locked(fnic,
 						FNIC_FLAGS_IO_BLOCKED))) {
-		spin_unlock_irqrestore(host->host_lock, flags);
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 		return 1;
 	} else
 		atomic_inc(&fnic->in_flight);
-	spin_unlock_irqrestore(host->host_lock, flags);
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 
-	spin_lock_irqsave(&fnic->wq_copy_lock[0], flags);
+	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 
-	if (vnic_wq_copy_desc_avail(wq) <= fnic->wq_copy_desc_low[0])
-		free_wq_copy_descs(fnic, wq);
+	if (vnic_wq_copy_desc_avail(wq) <= fnic->wq_copy_desc_low[hwq])
+		free_wq_copy_descs(fnic, wq, hwq);
 
 	if (!vnic_wq_copy_desc_avail(wq)) {
-		spin_unlock_irqrestore(&fnic->wq_copy_lock[0], flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		atomic_dec(&fnic->in_flight);
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 			"fnic_queue_abort_io_req: failure: no descriptors\n");
 		atomic64_inc(&misc_stats->abts_cpwq_alloc_failures);
 		return 1;
@@ -1539,7 +1599,7 @@ static inline int fnic_queue_abort_io_req(struct fnic *fnic, int tag,
 		atomic64_set(&fnic->fnic_stats.fw_stats.max_fw_reqs,
 		  atomic64_read(&fnic->fnic_stats.fw_stats.active_fw_reqs));
 
-	spin_unlock_irqrestore(&fnic->wq_copy_lock[0], flags);
+	spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 	atomic_dec(&fnic->in_flight);
 
 	return 0;
@@ -1553,33 +1613,36 @@ struct fnic_rport_abort_io_iter_data {
 
 static bool fnic_rport_abort_io_iter(struct scsi_cmnd *sc, void *data)
 {
+	struct request *const rq = scsi_cmd_to_rq(sc);
 	struct fnic_rport_abort_io_iter_data *iter_data = data;
 	struct fnic *fnic = iter_data->fnic;
-	int abt_tag = scsi_cmd_to_rq(sc)->tag;
+	int abt_tag = 0;
 	struct fnic_io_req *io_req;
-	spinlock_t *io_lock;
 	unsigned long flags;
 	struct reset_stats *reset_stats = &fnic->fnic_stats.reset_stats;
 	struct terminate_stats *term_stats = &fnic->fnic_stats.term_stats;
 	struct scsi_lun fc_lun;
 	enum fnic_ioreq_state old_ioreq_state;
+	uint16_t hwq = 0;
 
-	io_lock = fnic_io_lock_tag(fnic, abt_tag);
-	spin_lock_irqsave(io_lock, flags);
+	abt_tag = blk_mq_unique_tag(rq);
+	hwq = blk_mq_unique_tag_to_hwq(abt_tag);
+
+	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 
 	io_req = fnic_priv(sc)->io_req;
 
 	if (!io_req || io_req->port_id != iter_data->port_id) {
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		return true;
 	}
 
 	if ((fnic_priv(sc)->flags & FNIC_DEVICE_RESET) &&
 	    !(fnic_priv(sc)->flags & FNIC_DEV_RST_ISSUED)) {
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
-			"fnic_rport_exch_reset dev rst not pending sc 0x%p\n",
-			sc);
-		spin_unlock_irqrestore(io_lock, flags);
+		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			"hwq: %d abt_tag: 0x%x flags: 0x%x Device reset is not pending\n",
+			hwq, abt_tag, fnic_priv(sc)->flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		return true;
 	}
 
@@ -1588,7 +1651,7 @@ static bool fnic_rport_abort_io_iter(struct scsi_cmnd *sc, void *data)
 	 * belongs to rport that went away
 	 */
 	if (fnic_priv(sc)->state == FNIC_IOREQ_ABTS_PENDING) {
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		return true;
 	}
 	if (io_req->abts_done) {
@@ -1612,38 +1675,41 @@ static bool fnic_rport_abort_io_iter(struct scsi_cmnd *sc, void *data)
 		atomic64_inc(&reset_stats->device_reset_terminates);
 		abt_tag |= FNIC_TAG_DEV_RST;
 	}
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 		      "fnic_rport_exch_reset dev rst sc 0x%p\n", sc);
 	BUG_ON(io_req->abts_done);
 
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 		      "fnic_rport_reset_exch: Issuing abts\n");
 
-	spin_unlock_irqrestore(io_lock, flags);
+	spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 
 	/* Now queue the abort command to firmware */
 	int_to_scsilun(sc->device->lun, &fc_lun);
 
 	if (fnic_queue_abort_io_req(fnic, abt_tag,
 				    FCPIO_ITMF_ABT_TASK_TERM,
-				    fc_lun.scsi_lun, io_req)) {
+				    fc_lun.scsi_lun, io_req, hwq)) {
 		/*
 		 * Revert the cmd state back to old state, if
 		 * it hasn't changed in between. This cmd will get
 		 * aborted later by scsi_eh, or cleaned up during
 		 * lun reset
 		 */
-		spin_lock_irqsave(io_lock, flags);
+		spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
+		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			"hwq: %d abt_tag: 0x%x flags: 0x%x Queuing abort failed\n",
+			hwq, abt_tag, fnic_priv(sc)->flags);
 		if (fnic_priv(sc)->state == FNIC_IOREQ_ABTS_PENDING)
 			fnic_priv(sc)->state = old_ioreq_state;
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 	} else {
-		spin_lock_irqsave(io_lock, flags);
+		spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 		if (fnic_priv(sc)->flags & FNIC_DEVICE_RESET)
 			fnic_priv(sc)->flags |= FNIC_DEV_RST_TERM_ISSUED;
 		else
 			fnic_priv(sc)->flags |= FNIC_IO_INTERNAL_TERM_ISSUED;
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		atomic64_inc(&term_stats->terminates);
 		iter_data->term_cnt++;
 	}
@@ -1660,7 +1726,7 @@ static void fnic_rport_exch_reset(struct fnic *fnic, u32 port_id)
 	};
 
 	FNIC_SCSI_DBG(KERN_DEBUG,
-		      fnic->lport->host,
+		      fnic->lport->host, fnic->fnic_num,
 		      "fnic_rport_exch_reset called portid 0x%06x\n",
 		      port_id);
 
@@ -1697,9 +1763,8 @@ void fnic_terminate_rport_io(struct fc_rport *rport)
 		return;
 	}
 	fnic = lport_priv(lport);
-	FNIC_SCSI_DBG(KERN_DEBUG,
-		      fnic->lport->host, "fnic_terminate_rport_io called"
-		      " wwpn 0x%llx, wwnn0x%llx, rport 0x%p, portid 0x%06x\n",
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+		      "wwpn 0x%llx, wwnn0x%llx, rport 0x%p, portid 0x%06x\n",
 		      rport->port_name, rport->node_name, rport,
 		      rport->port_id);
 
@@ -1721,7 +1786,6 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 	struct fnic *fnic;
 	struct fnic_io_req *io_req = NULL;
 	struct fc_rport *rport;
-	spinlock_t *io_lock;
 	unsigned long flags;
 	unsigned long start_time = 0;
 	int ret = SUCCESS;
@@ -1731,8 +1795,10 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 	struct abort_stats *abts_stats;
 	struct terminate_stats *term_stats;
 	enum fnic_ioreq_state old_ioreq_state;
-	const int tag = rq->tag;
+	int mqtag;
 	unsigned long abt_issued_time;
+	uint16_t hwq = 0;
+
 	DECLARE_COMPLETION_ONSTACK(tm_done);
 
 	/* Wait for rport to unblock */
@@ -1742,23 +1808,25 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 	lp = shost_priv(sc->device->host);
 
 	fnic = lport_priv(lp);
+
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
 	fnic_stats = &fnic->fnic_stats;
 	abts_stats = &fnic->fnic_stats.abts_stats;
 	term_stats = &fnic->fnic_stats.term_stats;
 
 	rport = starget_to_rport(scsi_target(sc->device));
-	FNIC_SCSI_DBG(KERN_DEBUG,
-		fnic->lport->host,
-		"Abort Cmd called FCID 0x%x, LUN 0x%llx TAG %x flags %x\n",
-		rport->port_id, sc->device->lun, tag, fnic_priv(sc)->flags);
+	mqtag = blk_mq_unique_tag(rq);
+	hwq = blk_mq_unique_tag_to_hwq(mqtag);
 
 	fnic_priv(sc)->flags = FNIC_NO_FLAGS;
 
 	if (lp->state != LPORT_ST_READY || !(lp->link_up)) {
 		ret = FAILED;
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 		goto fnic_abort_cmd_end;
 	}
 
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 	/*
 	 * Avoid a race between SCSI issuing the abort and the device
 	 * completing the command.
@@ -1771,18 +1839,17 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 	 *
 	 * .io_req will not be cleared except while holding io_req_lock.
 	 */
-	io_lock = fnic_io_lock_hash(fnic, sc);
-	spin_lock_irqsave(io_lock, flags);
+	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 	io_req = fnic_priv(sc)->io_req;
 	if (!io_req) {
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		goto fnic_abort_cmd_end;
 	}
 
 	io_req->abts_done = &tm_done;
 
 	if (fnic_priv(sc)->state == FNIC_IOREQ_ABTS_PENDING) {
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		goto wait_pending;
 	}
 
@@ -1802,8 +1869,9 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 	else
 		atomic64_inc(&abts_stats->abort_issued_greater_than_60_sec);
 
-	FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host,
-		"CBD Opcode: %02x Abort issued time: %lu msec\n", sc->cmnd[0], abt_issued_time);
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+		"CDB Opcode: 0x%02x Abort issued time: %lu msec\n",
+		sc->cmnd[0], abt_issued_time);
 	/*
 	 * Command is still pending, need to abort it
 	 * If the firmware completes the command after this point,
@@ -1814,7 +1882,7 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 	fnic_priv(sc)->state = FNIC_IOREQ_ABTS_PENDING;
 	fnic_priv(sc)->abts_status = FCPIO_INVALID_CODE;
 
-	spin_unlock_irqrestore(io_lock, flags);
+	spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 
 	/*
 	 * Check readiness of the remote port. If the path to remote
@@ -1831,15 +1899,15 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 	/* Now queue the abort command to firmware */
 	int_to_scsilun(sc->device->lun, &fc_lun);
 
-	if (fnic_queue_abort_io_req(fnic, tag, task_req, fc_lun.scsi_lun,
-				    io_req)) {
-		spin_lock_irqsave(io_lock, flags);
+	if (fnic_queue_abort_io_req(fnic, mqtag, task_req, fc_lun.scsi_lun,
+				    io_req, hwq)) {
+		spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 		if (fnic_priv(sc)->state == FNIC_IOREQ_ABTS_PENDING)
 			fnic_priv(sc)->state = old_ioreq_state;
 		io_req = fnic_priv(sc)->io_req;
 		if (io_req)
 			io_req->abts_done = NULL;
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		ret = FAILED;
 		goto fnic_abort_cmd_end;
 	}
@@ -1863,12 +1931,12 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 				     fnic->config.ed_tov));
 
 	/* Check the abort status */
-	spin_lock_irqsave(io_lock, flags);
+	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 
 	io_req = fnic_priv(sc)->io_req;
 	if (!io_req) {
 		atomic64_inc(&fnic_stats->io_stats.ioreq_null);
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		fnic_priv(sc)->flags |= FNIC_IO_ABT_TERM_REQ_NULL;
 		ret = FAILED;
 		goto fnic_abort_cmd_end;
@@ -1877,7 +1945,7 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 
 	/* fw did not complete abort, timed out */
 	if (fnic_priv(sc)->abts_status == FCPIO_INVALID_CODE) {
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		if (task_req == FCPIO_ITMF_ABT_TASK) {
 			atomic64_inc(&abts_stats->abort_drv_timeouts);
 		} else {
@@ -1891,9 +1959,9 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 	/* IO out of order */
 
 	if (!(fnic_priv(sc)->flags & (FNIC_IO_ABORTED | FNIC_IO_DONE))) {
-		spin_unlock_irqrestore(io_lock, flags);
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
-			"Issuing Host reset due to out of order IO\n");
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
+	    FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			"Issuing host reset due to out of order IO\n");
 
 		ret = FAILED;
 		goto fnic_abort_cmd_end;
@@ -1907,15 +1975,18 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 	 * free the io_req if successful. If abort fails,
 	 * Device reset will clean the I/O.
 	 */
-	if (fnic_priv(sc)->abts_status == FCPIO_SUCCESS) {
+	if (fnic_priv(sc)->abts_status == FCPIO_SUCCESS ||
+		(fnic_priv(sc)->abts_status == FCPIO_ABORTED)) {
 		fnic_priv(sc)->io_req = NULL;
+		io_req->sc = NULL;
 	} else {
 		ret = FAILED;
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		goto fnic_abort_cmd_end;
 	}
 
-	spin_unlock_irqrestore(io_lock, flags);
+	fnic->sw_copy_wq[hwq].io_req_table[blk_mq_unique_tag_to_tag(mqtag)] = NULL;
+	spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 
 	fnic_release_ioreq_buf(fnic, io_req, sc);
 	mempool_free(io_req, fnic->io_req_pool);
@@ -1930,14 +2001,14 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 		atomic64_inc(&fnic_stats->io_stats.io_completions);
 
 fnic_abort_cmd_end:
-	FNIC_TRACE(fnic_abort_cmd, sc->device->host->host_no, tag, sc,
+	FNIC_TRACE(fnic_abort_cmd, sc->device->host->host_no, mqtag, sc,
 		  jiffies_to_msecs(jiffies - start_time),
 		  0, ((u64)sc->cmnd[0] << 32 |
 		  (u64)sc->cmnd[2] << 24 | (u64)sc->cmnd[3] << 16 |
 		  (u64)sc->cmnd[4] << 8 | sc->cmnd[5]),
 		  fnic_flags_and_state(sc));
 
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 		      "Returning from abort cmd type %x %s\n", task_req,
 		      (ret == SUCCESS) ?
 		      "SUCCESS" : "FAILED");
@@ -1948,33 +2019,34 @@ static inline int fnic_queue_dr_io_req(struct fnic *fnic,
 				       struct scsi_cmnd *sc,
 				       struct fnic_io_req *io_req)
 {
-	struct vnic_wq_copy *wq = &fnic->wq_copy[0];
-	struct Scsi_Host *host = fnic->lport->host;
+	struct vnic_wq_copy *wq;
 	struct misc_stats *misc_stats = &fnic->fnic_stats.misc_stats;
 	struct scsi_lun fc_lun;
 	int ret = 0;
-	unsigned long intr_flags;
-	unsigned int tag = scsi_cmd_to_rq(sc)->tag;
+	unsigned long flags;
+	uint16_t hwq = 0;
+	uint32_t tag = 0;
 
-	if (tag == SCSI_NO_TAG)
-		tag = io_req->tag;
+	tag = io_req->tag;
+	hwq = blk_mq_unique_tag_to_hwq(tag);
+	wq = &fnic->hw_copy_wq[hwq];
 
-	spin_lock_irqsave(host->host_lock, intr_flags);
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
 	if (unlikely(fnic_chk_state_flags_locked(fnic,
 						FNIC_FLAGS_IO_BLOCKED))) {
-		spin_unlock_irqrestore(host->host_lock, intr_flags);
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 		return FAILED;
 	} else
 		atomic_inc(&fnic->in_flight);
-	spin_unlock_irqrestore(host->host_lock, intr_flags);
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 
-	spin_lock_irqsave(&fnic->wq_copy_lock[0], intr_flags);
+	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 
-	if (vnic_wq_copy_desc_avail(wq) <= fnic->wq_copy_desc_low[0])
-		free_wq_copy_descs(fnic, wq);
+	if (vnic_wq_copy_desc_avail(wq) <= fnic->wq_copy_desc_low[hwq])
+		free_wq_copy_descs(fnic, wq, hwq);
 
 	if (!vnic_wq_copy_desc_avail(wq)) {
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 			  "queue_dr_io_req failure - no descriptors\n");
 		atomic64_inc(&misc_stats->devrst_cpwq_alloc_failures);
 		ret = -EAGAIN;
@@ -1997,7 +2069,7 @@ static inline int fnic_queue_dr_io_req(struct fnic *fnic,
 		  atomic64_read(&fnic->fnic_stats.fw_stats.active_fw_reqs));
 
 lr_io_req_end:
-	spin_unlock_irqrestore(&fnic->wq_copy_lock[0], intr_flags);
+	spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 	atomic_dec(&fnic->in_flight);
 
 	return ret;
@@ -2012,12 +2084,13 @@ struct fnic_pending_aborts_iter_data {
 
 static bool fnic_pending_aborts_iter(struct scsi_cmnd *sc, void *data)
 {
+	struct request *const rq = scsi_cmd_to_rq(sc);
 	struct fnic_pending_aborts_iter_data *iter_data = data;
 	struct fnic *fnic = iter_data->fnic;
 	struct scsi_device *lun_dev = iter_data->lun_dev;
-	int abt_tag = scsi_cmd_to_rq(sc)->tag;
+	unsigned long abt_tag = 0;
+	uint16_t hwq = 0;
 	struct fnic_io_req *io_req;
-	spinlock_t *io_lock;
 	unsigned long flags;
 	struct scsi_lun fc_lun;
 	DECLARE_COMPLETION_ONSTACK(tm_done);
@@ -2026,11 +2099,13 @@ static bool fnic_pending_aborts_iter(struct scsi_cmnd *sc, void *data)
 	if (sc == iter_data->lr_sc || sc->device != lun_dev)
 		return true;
 
-	io_lock = fnic_io_lock_tag(fnic, abt_tag);
-	spin_lock_irqsave(io_lock, flags);
+	abt_tag = blk_mq_unique_tag(rq);
+	hwq = blk_mq_unique_tag_to_hwq(abt_tag);
+
+	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 	io_req = fnic_priv(sc)->io_req;
 	if (!io_req) {
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		return true;
 	}
 
@@ -2038,20 +2113,19 @@ static bool fnic_pending_aborts_iter(struct scsi_cmnd *sc, void *data)
 	 * Found IO that is still pending with firmware and
 	 * belongs to the LUN that we are resetting
 	 */
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 		      "Found IO in %s on lun\n",
 		      fnic_ioreq_state_to_str(fnic_priv(sc)->state));
 
 	if (fnic_priv(sc)->state == FNIC_IOREQ_ABTS_PENDING) {
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		return true;
 	}
 	if ((fnic_priv(sc)->flags & FNIC_DEVICE_RESET) &&
 	    (!(fnic_priv(sc)->flags & FNIC_DEV_RST_ISSUED))) {
-		FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host,
-			      "%s dev rst not pending sc 0x%p\n", __func__,
-			      sc);
-		spin_unlock_irqrestore(io_lock, flags);
+		FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+			      "dev rst not pending sc 0x%p\n", sc);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		return true;
 	}
 
@@ -2072,35 +2146,37 @@ static bool fnic_pending_aborts_iter(struct scsi_cmnd *sc, void *data)
 	BUG_ON(io_req->abts_done);
 
 	if (fnic_priv(sc)->flags & FNIC_DEVICE_RESET) {
-		abt_tag |= FNIC_TAG_DEV_RST;
-		FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host,
-			      "%s: dev rst sc 0x%p\n", __func__, sc);
+		FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+			      "dev rst sc 0x%p\n", sc);
 	}
 
 	fnic_priv(sc)->abts_status = FCPIO_INVALID_CODE;
 	io_req->abts_done = &tm_done;
-	spin_unlock_irqrestore(io_lock, flags);
+	spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 
 	/* Now queue the abort command to firmware */
 	int_to_scsilun(sc->device->lun, &fc_lun);
 
 	if (fnic_queue_abort_io_req(fnic, abt_tag,
 				    FCPIO_ITMF_ABT_TASK_TERM,
-				    fc_lun.scsi_lun, io_req)) {
-		spin_lock_irqsave(io_lock, flags);
+				    fc_lun.scsi_lun, io_req, hwq)) {
+		spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 		io_req = fnic_priv(sc)->io_req;
 		if (io_req)
 			io_req->abts_done = NULL;
 		if (fnic_priv(sc)->state == FNIC_IOREQ_ABTS_PENDING)
 			fnic_priv(sc)->state = old_ioreq_state;
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		iter_data->ret = FAILED;
+		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			"hwq: %d abt_tag: 0x%lx Abort could not be queued\n",
+			hwq, abt_tag);
 		return false;
 	} else {
-		spin_lock_irqsave(io_lock, flags);
+		spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 		if (fnic_priv(sc)->flags & FNIC_DEVICE_RESET)
 			fnic_priv(sc)->flags |= FNIC_DEV_RST_TERM_ISSUED;
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 	}
 	fnic_priv(sc)->flags |= FNIC_IO_INTERNAL_TERM_ISSUED;
 
@@ -2108,10 +2184,10 @@ static bool fnic_pending_aborts_iter(struct scsi_cmnd *sc, void *data)
 				    (fnic->config.ed_tov));
 
 	/* Recheck cmd state to check if it is now aborted */
-	spin_lock_irqsave(io_lock, flags);
+	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 	io_req = fnic_priv(sc)->io_req;
 	if (!io_req) {
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		fnic_priv(sc)->flags |= FNIC_IO_ABT_TERM_REQ_NULL;
 		return true;
 	}
@@ -2120,7 +2196,7 @@ static bool fnic_pending_aborts_iter(struct scsi_cmnd *sc, void *data)
 
 	/* if abort is still pending with fw, fail */
 	if (fnic_priv(sc)->abts_status == FCPIO_INVALID_CODE) {
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		fnic_priv(sc)->flags |= FNIC_IO_ABT_TERM_DONE;
 		iter_data->ret = FAILED;
 		return false;
@@ -2128,9 +2204,11 @@ static bool fnic_pending_aborts_iter(struct scsi_cmnd *sc, void *data)
 	fnic_priv(sc)->state = FNIC_IOREQ_ABTS_COMPLETE;
 
 	/* original sc used for lr is handled by dev reset code */
-	if (sc != iter_data->lr_sc)
+	if (sc != iter_data->lr_sc) {
 		fnic_priv(sc)->io_req = NULL;
-	spin_unlock_irqrestore(io_lock, flags);
+		fnic->sw_copy_wq[hwq].io_req_table[blk_mq_unique_tag_to_tag(abt_tag)] = NULL;
+	}
+	spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 
 	/* original sc used for lr is handled by dev reset code */
 	if (sc != iter_data->lr_sc) {
@@ -2182,8 +2260,8 @@ static int fnic_clean_pending_aborts(struct fnic *fnic,
 		ret = 1;
 
 clean_pending_aborts_end:
-	FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host,
-			"%s: exit status: %d\n", __func__, ret);
+	FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+			"exit status: %d\n", ret);
 	return ret;
 }
 
@@ -2201,15 +2279,15 @@ int fnic_device_reset(struct scsi_cmnd *sc)
 	struct fc_rport *rport;
 	int status;
 	int ret = FAILED;
-	spinlock_t *io_lock;
 	unsigned long flags;
 	unsigned long start_time = 0;
 	struct scsi_lun fc_lun;
 	struct fnic_stats *fnic_stats;
 	struct reset_stats *reset_stats;
-	int tag = rq->tag;
+	int mqtag = rq->tag;
 	DECLARE_COMPLETION_ONSTACK(tm_done);
 	bool new_sc = 0;
+	uint16_t hwq = 0;
 
 	/* Wait for rport to unblock */
 	fc_block_scsi_eh(sc);
@@ -2224,9 +2302,10 @@ int fnic_device_reset(struct scsi_cmnd *sc)
 	atomic64_inc(&reset_stats->device_resets);
 
 	rport = starget_to_rport(scsi_target(sc->device));
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
-		      "Device reset called FCID 0x%x, LUN 0x%llx sc 0x%p\n",
-		      rport->port_id, sc->device->lun, sc);
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+		"fcid: 0x%x lun: 0x%llx hwq: %d mqtag: 0x%x flags: 0x%x Device reset\n",
+		rport->port_id, sc->device->lun, hwq, mqtag,
+		fnic_priv(sc)->flags);
 
 	if (lp->state != LPORT_ST_READY || !(lp->link_up))
 		goto fnic_device_reset_end;
@@ -2239,7 +2318,7 @@ int fnic_device_reset(struct scsi_cmnd *sc)
 
 	fnic_priv(sc)->flags = FNIC_DEVICE_RESET;
 
-	if (unlikely(tag < 0)) {
+	if (unlikely(mqtag < 0)) {
 		/*
 		 * For device reset issued through sg3utils, we let
 		 * only one LUN_RESET to go through and use a special
@@ -2248,17 +2327,14 @@ int fnic_device_reset(struct scsi_cmnd *sc)
 		 * allocated by mid layer.
 		 */
 		mutex_lock(&fnic->sgreset_mutex);
-		tag = fnic->fnic_max_tag_id;
+		mqtag = fnic->fnic_max_tag_id;
 		new_sc = 1;
-		fnic->sgreset_sc = sc;
-		io_lock = &fnic->sgreset_lock;
-		FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host,
-			"fcid: 0x%x lun: 0x%llx flags: 0x%x tag: 0x%x Issuing sgreset\n",
-			rport->port_id, sc->device->lun, fnic_priv(sc)->flags, tag);
-	} else
-		io_lock = fnic_io_lock_hash(fnic, sc);
+	}  else {
+		mqtag = blk_mq_unique_tag(rq);
+		hwq = blk_mq_unique_tag_to_hwq(mqtag);
+	}
 
-	spin_lock_irqsave(io_lock, flags);
+	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 	io_req = fnic_priv(sc)->io_req;
 
 	/*
@@ -2268,36 +2344,43 @@ int fnic_device_reset(struct scsi_cmnd *sc)
 	if (!io_req) {
 		io_req = mempool_alloc(fnic->io_req_pool, GFP_ATOMIC);
 		if (!io_req) {
-			spin_unlock_irqrestore(io_lock, flags);
+			spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 			goto fnic_device_reset_end;
 		}
 		memset(io_req, 0, sizeof(*io_req));
 		io_req->port_id = rport->port_id;
-		io_req->tag = tag;
-		io_req->sc = sc;
+		io_req->tag = mqtag;
 		fnic_priv(sc)->io_req = io_req;
+		io_req->sc = sc;
+
+		if (fnic->sw_copy_wq[hwq].io_req_table[blk_mq_unique_tag_to_tag(mqtag)] != NULL)
+			WARN(1, "fnic<%d>: %s: tag 0x%x already exists\n",
+					fnic->fnic_num, __func__, blk_mq_unique_tag_to_tag(mqtag));
+
+		fnic->sw_copy_wq[hwq].io_req_table[blk_mq_unique_tag_to_tag(mqtag)] =
+				io_req;
 	}
 	io_req->dr_done = &tm_done;
 	fnic_priv(sc)->state = FNIC_IOREQ_CMD_PENDING;
 	fnic_priv(sc)->lr_status = FCPIO_INVALID_CODE;
-	spin_unlock_irqrestore(io_lock, flags);
+	spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, "TAG %x\n", tag);
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, "TAG %x\n", mqtag);
 
 	/*
 	 * issue the device reset, if enqueue failed, clean up the ioreq
 	 * and break assoc with scsi cmd
 	 */
 	if (fnic_queue_dr_io_req(fnic, sc, io_req)) {
-		spin_lock_irqsave(io_lock, flags);
+		spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 		io_req = fnic_priv(sc)->io_req;
 		if (io_req)
 			io_req->dr_done = NULL;
 		goto fnic_device_reset_clean;
 	}
-	spin_lock_irqsave(io_lock, flags);
+	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 	fnic_priv(sc)->flags |= FNIC_DEV_RST_ISSUED;
-	spin_unlock_irqrestore(io_lock, flags);
+	spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 
 	/*
 	 * Wait on the local completion for LUN reset.  The io_req may be
@@ -2306,12 +2389,12 @@ int fnic_device_reset(struct scsi_cmnd *sc)
 	wait_for_completion_timeout(&tm_done,
 				    msecs_to_jiffies(FNIC_LUN_RESET_TIMEOUT));
 
-	spin_lock_irqsave(io_lock, flags);
+	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 	io_req = fnic_priv(sc)->io_req;
 	if (!io_req) {
-		spin_unlock_irqrestore(io_lock, flags);
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
-				"io_req is null tag 0x%x sc 0x%p\n", tag, sc);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+				"io_req is null mqtag 0x%x sc 0x%p\n", mqtag, sc);
 		goto fnic_device_reset_end;
 	}
 	io_req->dr_done = NULL;
@@ -2324,44 +2407,44 @@ int fnic_device_reset(struct scsi_cmnd *sc)
 	 */
 	if (status == FCPIO_INVALID_CODE) {
 		atomic64_inc(&reset_stats->device_reset_timeouts);
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 			      "Device reset timed out\n");
 		fnic_priv(sc)->flags |= FNIC_DEV_RST_TIMED_OUT;
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		int_to_scsilun(sc->device->lun, &fc_lun);
 		/*
 		 * Issue abort and terminate on device reset request.
 		 * If q'ing of terminate fails, retry it after a delay.
 		 */
 		while (1) {
-			spin_lock_irqsave(io_lock, flags);
+			spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 			if (fnic_priv(sc)->flags & FNIC_DEV_RST_TERM_ISSUED) {
-				spin_unlock_irqrestore(io_lock, flags);
+				spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 				break;
 			}
-			spin_unlock_irqrestore(io_lock, flags);
+			spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 			if (fnic_queue_abort_io_req(fnic,
-				tag | FNIC_TAG_DEV_RST,
+				mqtag | FNIC_TAG_DEV_RST,
 				FCPIO_ITMF_ABT_TASK_TERM,
-				fc_lun.scsi_lun, io_req)) {
+				fc_lun.scsi_lun, io_req, hwq)) {
 				wait_for_completion_timeout(&tm_done,
 				msecs_to_jiffies(FNIC_ABT_TERM_DELAY_TIMEOUT));
 			} else {
-				spin_lock_irqsave(io_lock, flags);
+				spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 				fnic_priv(sc)->flags |= FNIC_DEV_RST_TERM_ISSUED;
 				fnic_priv(sc)->state = FNIC_IOREQ_ABTS_PENDING;
 				io_req->abts_done = &tm_done;
-				spin_unlock_irqrestore(io_lock, flags);
-				FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
-				"Abort and terminate issued on Device reset "
-				"tag 0x%x sc 0x%p\n", tag, sc);
+				spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
+				FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+				"Abort and terminate issued on Device reset mqtag 0x%x sc 0x%p\n",
+				mqtag, sc);
 				break;
 			}
 		}
 		while (1) {
-			spin_lock_irqsave(io_lock, flags);
+			spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 			if (!(fnic_priv(sc)->flags & FNIC_DEV_RST_DONE)) {
-				spin_unlock_irqrestore(io_lock, flags);
+				spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 				wait_for_completion_timeout(&tm_done,
 				msecs_to_jiffies(FNIC_LUN_RESET_TIMEOUT));
 				break;
@@ -2372,14 +2455,14 @@ int fnic_device_reset(struct scsi_cmnd *sc)
 			}
 		}
 	} else {
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 	}
 
 	/* Completed, but not successful, clean up the io_req, return fail */
 	if (status != FCPIO_SUCCESS) {
-		spin_lock_irqsave(io_lock, flags);
+		spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 		FNIC_SCSI_DBG(KERN_DEBUG,
-			      fnic->lport->host,
+			      fnic->lport->host, fnic->fnic_num,
 			      "Device reset completed - failed\n");
 		io_req = fnic_priv(sc)->io_req;
 		goto fnic_device_reset_clean;
@@ -2393,26 +2476,29 @@ int fnic_device_reset(struct scsi_cmnd *sc)
 	 * succeeds
 	 */
 	if (fnic_clean_pending_aborts(fnic, sc, new_sc)) {
-		spin_lock_irqsave(io_lock, flags);
+		spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 		io_req = fnic_priv(sc)->io_req;
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 			      "Device reset failed"
 			      " since could not abort all IOs\n");
 		goto fnic_device_reset_clean;
 	}
 
 	/* Clean lun reset command */
-	spin_lock_irqsave(io_lock, flags);
+	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 	io_req = fnic_priv(sc)->io_req;
 	if (io_req)
 		/* Completed, and successful */
 		ret = SUCCESS;
 
 fnic_device_reset_clean:
-	if (io_req)
+	if (io_req) {
 		fnic_priv(sc)->io_req = NULL;
+		io_req->sc = NULL;
+		fnic->sw_copy_wq[hwq].io_req_table[blk_mq_unique_tag_to_tag(io_req->tag)] = NULL;
+	}
 
-	spin_unlock_irqrestore(io_lock, flags);
+	spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 
 	if (io_req) {
 		start_time = io_req->start_time;
@@ -2433,7 +2519,7 @@ fnic_device_reset_end:
 		mutex_unlock(&fnic->sgreset_mutex);
 	}
 
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 		      "Returning from device reset %s\n",
 		      (ret == SUCCESS) ?
 		      "SUCCESS" : "FAILED");
@@ -2456,8 +2542,8 @@ int fnic_reset(struct Scsi_Host *shost)
 	fnic = lport_priv(lp);
 	reset_stats = &fnic->fnic_stats.reset_stats;
 
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
-		      "fnic_reset called\n");
+	FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+			"Issuing fnic reset\n");
 
 	atomic64_inc(&reset_stats->fnic_resets);
 
@@ -2467,10 +2553,9 @@ int fnic_reset(struct Scsi_Host *shost)
 	 */
 	ret = fc_lport_reset(lp);
 
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
-		      "Returning from fnic reset %s\n",
-		      (ret == 0) ?
-		      "SUCCESS" : "FAILED");
+	FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+		"Returning from fnic reset with: %s\n",
+		(ret == 0) ? "SUCCESS" : "FAILED");
 
 	if (ret == 0)
 		atomic64_inc(&reset_stats->fnic_reset_completions);
@@ -2503,7 +2588,7 @@ int fnic_host_reset(struct scsi_cmnd *sc)
 		fnic->internal_reset_inprogress = true;
 	} else {
 		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 			"host reset in progress skipping another host reset\n");
 		return SUCCESS;
 	}
@@ -2578,7 +2663,7 @@ retry_fw_reset:
 
 	spin_lock_irqsave(&fnic->fnic_lock, flags);
 	fnic->remove_wait = NULL;
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
 		      "fnic_scsi_abort_io %s\n",
 		      (fnic->state == FNIC_IN_ETH_MODE) ?
 		      "SUCCESS" : "FAILED");
@@ -2652,12 +2737,17 @@ call_fc_exch_mgr_reset:
 
 static bool fnic_abts_pending_iter(struct scsi_cmnd *sc, void *data)
 {
+	struct request *const rq = scsi_cmd_to_rq(sc);
 	struct fnic_pending_aborts_iter_data *iter_data = data;
 	struct fnic *fnic = iter_data->fnic;
 	int cmd_state;
 	struct fnic_io_req *io_req;
-	spinlock_t *io_lock;
 	unsigned long flags;
+	uint16_t hwq = 0;
+	int tag;
+
+	tag = blk_mq_unique_tag(rq);
+	hwq = blk_mq_unique_tag_to_hwq(tag);
 
 	/*
 	 * ignore this lun reset cmd or cmds that do not belong to
@@ -2668,12 +2758,11 @@ static bool fnic_abts_pending_iter(struct scsi_cmnd *sc, void *data)
 	if (iter_data->lun_dev && sc->device != iter_data->lun_dev)
 		return true;
 
-	io_lock = fnic_io_lock_hash(fnic, sc);
-	spin_lock_irqsave(io_lock, flags);
+	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 
 	io_req = fnic_priv(sc)->io_req;
 	if (!io_req) {
-		spin_unlock_irqrestore(io_lock, flags);
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		return true;
 	}
 
@@ -2681,11 +2770,12 @@ static bool fnic_abts_pending_iter(struct scsi_cmnd *sc, void *data)
 	 * Found IO that is still pending with firmware and
 	 * belongs to the LUN that we are resetting
 	 */
-	FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host,
-		      "Found IO in %s on lun\n",
-		      fnic_ioreq_state_to_str(fnic_priv(sc)->state));
+	FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+		"hwq: %d tag: 0x%x Found IO in state: %s on lun\n",
+		hwq, tag,
+		fnic_ioreq_state_to_str(fnic_priv(sc)->state));
 	cmd_state = fnic_priv(sc)->state;
-	spin_unlock_irqrestore(io_lock, flags);
+	spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 	if (cmd_state == FNIC_IOREQ_ABTS_PENDING)
 		iter_data->ret = 1;
 
diff --git a/drivers/scsi/fnic/fnic_stats.h b/drivers/scsi/fnic/fnic_stats.h
index bdf639eef8cf..9d7f98c452dd 100644
--- a/drivers/scsi/fnic/fnic_stats.h
+++ b/drivers/scsi/fnic/fnic_stats.h
@@ -2,6 +2,7 @@
 /* Copyright 2013 Cisco Systems, Inc.  All rights reserved. */
 #ifndef _FNIC_STATS_H_
 #define _FNIC_STATS_H_
+#define FNIC_MQ_MAX_QUEUES 64
 
 struct stats_timestamps {
 	struct timespec64 last_reset_time;
@@ -26,6 +27,7 @@ struct io_path_stats {
 	atomic64_t io_btw_10000_to_30000_msec;
 	atomic64_t io_greater_than_30000_msec;
 	atomic64_t current_max_io_time;
+	atomic64_t ios[FNIC_MQ_MAX_QUEUES];
 };
 
 struct abort_stats {
@@ -103,6 +105,7 @@ struct misc_stats {
 	atomic64_t rport_not_ready;
 	atomic64_t frame_errors;
 	atomic64_t current_port_speed;
+	atomic64_t intx_dummy;
 };
 
 struct fnic_stats {
diff --git a/drivers/scsi/fnic/fnic_trace.c b/drivers/scsi/fnic/fnic_trace.c
index be0d7c57b242..aaa4ea02fb7c 100644
--- a/drivers/scsi/fnic/fnic_trace.c
+++ b/drivers/scsi/fnic/fnic_trace.c
@@ -204,6 +204,7 @@ int fnic_get_stats_data(struct stats_debug_info *debug,
 	int len = 0;
 	int buf_size = debug->buf_size;
 	struct timespec64 val1, val2;
+	int i = 0;
 
 	ktime_get_real_ts64(&val1);
 	len = scnprintf(debug->debug_buffer + len, buf_size - len,
@@ -267,6 +268,16 @@ int fnic_get_stats_data(struct stats_debug_info *debug,
 		  (u64)atomic64_read(&stats->io_stats.io_greater_than_30000_msec));
 
 	len += scnprintf(debug->debug_buffer + len, buf_size - len,
+			"------------------------------------------\n"
+			"\t\tIO Queues and cumulative IOs\n"
+			"------------------------------------------\n");
+
+	for (i = 0; i < FNIC_MQ_MAX_QUEUES; i++) {
+		len += scnprintf(debug->debug_buffer + len, buf_size - len,
+				"Q:%d -> %lld\n", i, (u64)atomic64_read(&stats->io_stats.ios[i]));
+	}
+
+	len += scnprintf(debug->debug_buffer + len, buf_size - len,
 		  "\nCurrent Max IO time : %lld\n",
 		  (u64)atomic64_read(&stats->io_stats.current_max_io_time));
 
diff --git a/drivers/scsi/fnic/vnic_dev.c b/drivers/scsi/fnic/vnic_dev.c
index 3e5b437c0492..e0b173cc9d5f 100644
--- a/drivers/scsi/fnic/vnic_dev.c
+++ b/drivers/scsi/fnic/vnic_dev.c
@@ -143,6 +143,10 @@ static int vnic_dev_discover_res(struct vnic_dev *vdev,
 		vdev->res[type].vaddr = (char __iomem *)bar->vaddr + bar_offset;
 	}
 
+	pr_info("res_type_wq: %d res_type_rq: %d res_type_cq: %d res_type_intr_ctrl: %d\n",
+		vdev->res[RES_TYPE_WQ].count, vdev->res[RES_TYPE_RQ].count,
+		vdev->res[RES_TYPE_CQ].count, vdev->res[RES_TYPE_INTR_CTRL].count);
+
 	return 0;
 }
 
diff --git a/drivers/scsi/fnic/vnic_scsi.h b/drivers/scsi/fnic/vnic_scsi.h
index 4e12f7b32d9d..f715f7942bfe 100644
--- a/drivers/scsi/fnic/vnic_scsi.h
+++ b/drivers/scsi/fnic/vnic_scsi.h
@@ -26,7 +26,7 @@
 #define VNIC_FNIC_RATOV_MAX                 255000
 
 #define VNIC_FNIC_MAXDATAFIELDSIZE_MIN      256
-#define VNIC_FNIC_MAXDATAFIELDSIZE_MAX      2112
+#define VNIC_FNIC_MAXDATAFIELDSIZE_MAX      2048
 
 #define VNIC_FNIC_FLOGI_RETRIES_MIN         0
 #define VNIC_FNIC_FLOGI_RETRIES_MAX         0xffffffff
@@ -55,7 +55,7 @@
 #define VNIC_FNIC_PORT_DOWN_IO_RETRIES_MAX  255
 
 #define VNIC_FNIC_LUNS_PER_TARGET_MIN       1
-#define VNIC_FNIC_LUNS_PER_TARGET_MAX       1024
+#define VNIC_FNIC_LUNS_PER_TARGET_MAX       4096
 
 /* Device-specific region: scsi configuration */
 struct vnic_fc_config {
@@ -79,10 +79,19 @@ struct vnic_fc_config {
 	u16 ra_tov;
 	u16 intr_timer;
 	u8 intr_timer_type;
+	u8 intr_mode;
+	u8 lun_queue_depth;
+	u8 io_timeout_retry;
+	u16 wq_copy_count;
 };
 
 #define VFCF_FCP_SEQ_LVL_ERR	0x1	/* Enable FCP-2 Error Recovery */
 #define VFCF_PERBI		0x2	/* persistent binding info available */
 #define VFCF_FIP_CAPABLE	0x4	/* firmware can handle FIP */
 
+#define VFCF_FC_INITIATOR         0x20    /* FC Initiator Mode */
+#define VFCF_FC_TARGET            0x40    /* FC Target Mode */
+#define VFCF_FC_NVME_INITIATOR    0x80    /* FC-NVMe Initiator Mode */
+#define VFCF_FC_NVME_TARGET       0x100   /* FC-NVMe Target Mode */
+
 #endif /* _VNIC_SCSI_H_ */
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index d50058b41409..bbb7b2d9ffcf 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1565,12 +1565,12 @@ EXPORT_SYMBOL_GPL(hisi_sas_controller_reset_done);
 static int hisi_sas_controller_prereset(struct hisi_hba *hisi_hba)
 {
 	if (!hisi_hba->hw->soft_reset)
-		return -1;
+		return -ENOENT;
 
 	down(&hisi_hba->sem);
 	if (test_and_set_bit(HISI_SAS_RESETTING_BIT, &hisi_hba->flags)) {
 		up(&hisi_hba->sem);
-		return -1;
+		return -EPERM;
 	}
 
 	if (hisi_sas_debugfs_enable && hisi_hba->debugfs_itct[0].itct)
@@ -1641,7 +1641,10 @@ static int hisi_sas_abort_task(struct sas_task *task)
 	task->task_state_flags |= SAS_TASK_STATE_ABORTED;
 	spin_unlock_irqrestore(&task->task_state_lock, flags);
 
-	if (slot && task->task_proto & SAS_PROTOCOL_SSP) {
+	if (!slot)
+		goto out;
+
+	if (task->task_proto & SAS_PROTOCOL_SSP) {
 		u16 tag = slot->idx;
 		int rc2;
 
@@ -1688,7 +1691,7 @@ static int hisi_sas_abort_task(struct sas_task *task)
 				rc = hisi_sas_softreset_ata_disk(device);
 			}
 		}
-	} else if (slot && task->task_proto & SAS_PROTOCOL_SMP) {
+	} else if (task->task_proto & SAS_PROTOCOL_SMP) {
 		/* SMP */
 		u32 tag = slot->idx;
 		struct hisi_sas_cq *cq = &hisi_hba->cq[slot->dlvry_queue];
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index d8437a98037b..b56fbc61a15a 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -1605,6 +1605,11 @@ static irqreturn_t phy_up_v3_hw(int phy_no, struct hisi_hba *hisi_hba)
 	}
 
 	phy->port_id = port_id;
+	spin_lock(&phy->lock);
+	/* Delete timer and set phy_attached atomically */
+	del_timer(&phy->timer);
+	phy->phy_attached = 1;
+	spin_unlock(&phy->lock);
 
 	/*
 	 * Call pm_runtime_get_noresume() which pairs with
@@ -1618,11 +1623,6 @@ static irqreturn_t phy_up_v3_hw(int phy_no, struct hisi_hba *hisi_hba)
 
 	res = IRQ_HANDLED;
 
-	spin_lock(&phy->lock);
-	/* Delete timer and set phy_attached atomically */
-	del_timer(&phy->timer);
-	phy->phy_attached = 1;
-	spin_unlock(&phy->lock);
 end:
 	if (phy->reset_completion)
 		complete(phy->reset_completion);
@@ -3476,7 +3476,7 @@ static void debugfs_snapshot_global_reg_v3_hw(struct hisi_hba *hisi_hba)
 	u32 *databuf = hisi_hba->debugfs_regs[dump_index][DEBUGFS_GLOBAL].data;
 	int i;
 
-	for (i = 0; i < debugfs_axi_reg.count; i++, databuf++)
+	for (i = 0; i < debugfs_global_reg.count; i++, databuf++)
 		*databuf = hisi_sas_read32(hisi_hba, 4 * i);
 }
 
@@ -4968,6 +4968,7 @@ static void hisi_sas_reset_done_v3_hw(struct pci_dev *pdev)
 {
 	struct sas_ha_struct *sha = pci_get_drvdata(pdev);
 	struct hisi_hba *hisi_hba = sha->lldd_ha;
+	struct Scsi_Host *shost = hisi_hba->shost;
 	struct device *dev = hisi_hba->dev;
 	int rc;
 
@@ -4976,6 +4977,10 @@ static void hisi_sas_reset_done_v3_hw(struct pci_dev *pdev)
 	rc = hw_init_v3_hw(hisi_hba);
 	if (rc) {
 		dev_err(dev, "FLR: hw init failed rc=%d\n", rc);
+		clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
+		scsi_unblock_requests(shost);
+		clear_bit(HISI_SAS_RESETTING_BIT, &hisi_hba->flags);
+		up(&hisi_hba->sem);
 		return;
 	}
 
@@ -5018,7 +5023,7 @@ static int _suspend_v3_hw(struct device *device)
 	}
 
 	if (test_and_set_bit(HISI_SAS_RESETTING_BIT, &hisi_hba->flags))
-		return -1;
+		return -EPERM;
 
 	dev_warn(dev, "entering suspend state\n");
 
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 92c440f2e3a7..46d0b3a0e12f 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -1464,7 +1464,7 @@ static void ibmvfc_gather_partition_info(struct ibmvfc_host *vhost)
 
 	name = of_get_property(rootdn, "ibm,partition-name", NULL);
 	if (name)
-		strncpy(vhost->partition_name, name, sizeof(vhost->partition_name));
+		strscpy(vhost->partition_name, name, sizeof(vhost->partition_name));
 	num = of_get_property(rootdn, "ibm,partition-no", NULL);
 	if (num)
 		vhost->partition_number = *num;
@@ -1513,13 +1513,15 @@ static void ibmvfc_set_login_info(struct ibmvfc_host *vhost)
 	login_info->async.va = cpu_to_be64(vhost->async_crq.msg_token);
 	login_info->async.len = cpu_to_be32(async_crq->size *
 					    sizeof(*async_crq->msgs.async));
-	strncpy(login_info->partition_name, vhost->partition_name, IBMVFC_MAX_NAME);
-	strncpy(login_info->device_name,
-		dev_name(&vhost->host->shost_gendev), IBMVFC_MAX_NAME);
+	strscpy(login_info->partition_name, vhost->partition_name,
+		sizeof(login_info->partition_name));
+
+	strscpy(login_info->device_name,
+		dev_name(&vhost->host->shost_gendev), sizeof(login_info->device_name));
 
 	location = of_get_property(of_node, "ibm,loc-code", NULL);
 	location = location ? location : dev_name(vhost->dev);
-	strncpy(login_info->drc_name, location, IBMVFC_MAX_NAME);
+	strscpy(login_info->drc_name, location, sizeof(login_info->drc_name));
 }
 
 /**
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index 59599299615d..71f3e9563520 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -266,7 +266,7 @@ static void set_adapter_info(struct ibmvscsi_host_data *hostdata)
 	dev_info(hostdata->dev, "SRP_VERSION: %s\n", SRP_VERSION);
 	strcpy(hostdata->madapter_info.srp_version, SRP_VERSION);
 
-	strncpy(hostdata->madapter_info.partition_name, partition_name,
+	strscpy(hostdata->madapter_info.partition_name, partition_name,
 			sizeof(hostdata->madapter_info.partition_name));
 
 	hostdata->madapter_info.partition_number =
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 81e3d464d1f6..3819f7c42788 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -77,7 +77,6 @@
 static LIST_HEAD(ipr_ioa_head);
 static unsigned int ipr_log_level = IPR_DEFAULT_LOG_LEVEL;
 static unsigned int ipr_max_speed = 1;
-static int ipr_testmode = 0;
 static unsigned int ipr_fastfail = 0;
 static unsigned int ipr_transop_timeout = 0;
 static unsigned int ipr_debug = 0;
@@ -193,8 +192,6 @@ module_param_named(max_speed, ipr_max_speed, uint, 0);
 MODULE_PARM_DESC(max_speed, "Maximum bus speed (0-2). Default: 1=U160. Speeds: 0=80 MB/s, 1=U160, 2=U320");
 module_param_named(log_level, ipr_log_level, uint, 0);
 MODULE_PARM_DESC(log_level, "Set to 0 - 4 for increasing verbosity of device driver");
-module_param_named(testmode, ipr_testmode, int, 0);
-MODULE_PARM_DESC(testmode, "DANGEROUS!!! Allows unsupported configurations");
 module_param_named(fastfail, ipr_fastfail, int, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(fastfail, "Reduce timeouts and retries");
 module_param_named(transop_timeout, ipr_transop_timeout, int, 0);
@@ -6416,45 +6413,6 @@ static const struct scsi_host_template driver_template = {
 	.proc_name = IPR_NAME,
 };
 
-#ifdef CONFIG_PPC_PSERIES
-static const u16 ipr_blocked_processors[] = {
-	PVR_NORTHSTAR,
-	PVR_PULSAR,
-	PVR_POWER4,
-	PVR_ICESTAR,
-	PVR_SSTAR,
-	PVR_POWER4p,
-	PVR_630,
-	PVR_630p
-};
-
-/**
- * ipr_invalid_adapter - Determine if this adapter is supported on this hardware
- * @ioa_cfg:	ioa cfg struct
- *
- * Adapters that use Gemstone revision < 3.1 do not work reliably on
- * certain pSeries hardware. This function determines if the given
- * adapter is in one of these confgurations or not.
- *
- * Return value:
- * 	1 if adapter is not supported / 0 if adapter is supported
- **/
-static int ipr_invalid_adapter(struct ipr_ioa_cfg *ioa_cfg)
-{
-	int i;
-
-	if ((ioa_cfg->type == 0x5702) && (ioa_cfg->pdev->revision < 4)) {
-		for (i = 0; i < ARRAY_SIZE(ipr_blocked_processors); i++) {
-			if (pvr_version_is(ipr_blocked_processors[i]))
-				return 1;
-		}
-	}
-	return 0;
-}
-#else
-#define ipr_invalid_adapter(ioa_cfg) 0
-#endif
-
 /**
  * ipr_ioa_bringdown_done - IOA bring down completion.
  * @ipr_cmd:	ipr command struct
@@ -7385,19 +7343,6 @@ static int ipr_ioafp_page0_inquiry(struct ipr_cmnd *ipr_cmd)
 	type[4] = '\0';
 	ioa_cfg->type = simple_strtoul((char *)type, NULL, 16);
 
-	if (ipr_invalid_adapter(ioa_cfg)) {
-		dev_err(&ioa_cfg->pdev->dev,
-			"Adapter not supported in this hardware configuration.\n");
-
-		if (!ipr_testmode) {
-			ioa_cfg->reset_retries += IPR_NUM_RESET_RELOAD_RETRIES;
-			ipr_initiate_ioa_reset(ioa_cfg, IPR_SHUTDOWN_NONE);
-			list_add_tail(&ipr_cmd->queue,
-					&ioa_cfg->hrrq->hrrq_free_q);
-			return IPR_RC_JOB_RETURN;
-		}
-	}
-
 	ipr_cmd->job_step = ipr_ioafp_page3_inquiry;
 
 	ipr_ioafp_inquiry(ipr_cmd, 1, 0,
diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c
index a7b3243b471d..71f711cb0628 100644
--- a/drivers/scsi/isci/request.c
+++ b/drivers/scsi/isci/request.c
@@ -738,8 +738,7 @@ static enum sci_status sci_io_request_construct_basic_ssp(struct isci_request *i
 	return SCI_SUCCESS;
 }
 
-enum sci_status sci_task_request_construct_ssp(
-	struct isci_request *ireq)
+void sci_task_request_construct_ssp(struct isci_request *ireq)
 {
 	/* Construct the SSP Task SCU Task Context */
 	scu_ssp_task_request_construct_task_context(ireq);
@@ -748,8 +747,6 @@ enum sci_status sci_task_request_construct_ssp(
 	sci_task_request_build_ssp_task_iu(ireq);
 
 	sci_change_state(&ireq->sm, SCI_REQ_CONSTRUCTED);
-
-	return SCI_SUCCESS;
 }
 
 static enum sci_status sci_io_request_construct_basic_sata(struct isci_request *ireq)
diff --git a/drivers/scsi/isci/request.h b/drivers/scsi/isci/request.h
index 20b141739e4d..79ddfffbf73c 100644
--- a/drivers/scsi/isci/request.h
+++ b/drivers/scsi/isci/request.h
@@ -300,7 +300,7 @@ sci_task_request_construct(struct isci_host *ihost,
 			    struct isci_remote_device *idev,
 			    u16 io_tag,
 			    struct isci_request *ireq);
-enum sci_status sci_task_request_construct_ssp(struct isci_request *ireq);
+void sci_task_request_construct_ssp(struct isci_request *ireq);
 void sci_smp_request_copy_response(struct isci_request *ireq);
 
 static inline int isci_task_is_ncq_recovery(struct sas_task *task)
diff --git a/drivers/scsi/isci/task.c b/drivers/scsi/isci/task.c
index c514b20293b2..3a25b1a2c52d 100644
--- a/drivers/scsi/isci/task.c
+++ b/drivers/scsi/isci/task.c
@@ -243,9 +243,7 @@ static struct isci_request *isci_task_request_build(struct isci_host *ihost,
 	/* XXX convert to get this from task->tproto like other drivers */
 	if (dev->dev_type == SAS_END_DEVICE) {
 		isci_tmf->proto = SAS_PROTOCOL_SSP;
-		status = sci_task_request_construct_ssp(ireq);
-		if (status != SCI_SUCCESS)
-			return NULL;
+		sci_task_request_construct_ssp(ireq);
 	}
 
 	return ireq;
diff --git a/drivers/scsi/jazz_esp.c b/drivers/scsi/jazz_esp.c
index 0c842fb29aa0..494a671fb556 100644
--- a/drivers/scsi/jazz_esp.c
+++ b/drivers/scsi/jazz_esp.c
@@ -176,7 +176,7 @@ fail:
 	return err;
 }
 
-static int esp_jazz_remove(struct platform_device *dev)
+static void esp_jazz_remove(struct platform_device *dev)
 {
 	struct esp *esp = dev_get_drvdata(&dev->dev);
 	unsigned int irq = esp->host->irq;
@@ -189,8 +189,6 @@ static int esp_jazz_remove(struct platform_device *dev)
 			  esp->command_block_dma);
 
 	scsi_host_put(esp->host);
-
-	return 0;
 }
 
 /* work with hotplug and coldplug */
@@ -198,7 +196,7 @@ MODULE_ALIAS("platform:jazz_esp");
 
 static struct platform_driver esp_jazz_driver = {
 	.probe		= esp_jazz_probe,
-	.remove		= esp_jazz_remove,
+	.remove_new	= esp_jazz_remove,
 	.driver	= {
 		.name	= "jazz_esp",
 	},
diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c
index 945adca5e72f..80be3a936d92 100644
--- a/drivers/scsi/libfc/fc_fcp.c
+++ b/drivers/scsi/libfc/fc_fcp.c
@@ -265,6 +265,11 @@ static int fc_fcp_send_abort(struct fc_fcp_pkt *fsp)
 	if (!fsp->seq_ptr)
 		return -EINVAL;
 
+	if (fsp->state & FC_SRB_ABORT_PENDING) {
+		FC_FCP_DBG(fsp, "abort already pending\n");
+		return -EBUSY;
+	}
+
 	this_cpu_inc(fsp->lp->stats->FcpPktAborts);
 
 	fsp->state |= FC_SRB_ABORT_PENDING;
@@ -1671,7 +1676,7 @@ static void fc_fcp_rec_error(struct fc_fcp_pkt *fsp, struct fc_frame *fp)
 		if (fsp->recov_retry++ < FC_MAX_RECOV_RETRY)
 			fc_fcp_rec(fsp);
 		else
-			fc_fcp_recovery(fsp, FC_ERROR);
+			fc_fcp_recovery(fsp, FC_TIMED_OUT);
 		break;
 	}
 	fc_fcp_unlock_pkt(fsp);
@@ -1690,11 +1695,12 @@ static void fc_fcp_recovery(struct fc_fcp_pkt *fsp, u8 code)
 	fsp->status_code = code;
 	fsp->cdb_status = 0;
 	fsp->io_status = 0;
-	/*
-	 * if this fails then we let the scsi command timer fire and
-	 * scsi-ml escalate.
-	 */
-	fc_fcp_send_abort(fsp);
+	if (!fsp->cmd)
+		/*
+		 * Only abort non-scsi commands; otherwise let the
+		 * scsi command timer fire and scsi-ml escalate.
+		 */
+		fc_fcp_send_abort(fsp);
 }
 
 /**
@@ -2056,9 +2062,9 @@ static void fc_io_compl(struct fc_fcp_pkt *fsp)
 		sc_cmd->result = (DID_PARITY << 16);
 		break;
 	case FC_TIMED_OUT:
-		FC_FCP_DBG(fsp, "Returning DID_BUS_BUSY to scsi-ml "
+		FC_FCP_DBG(fsp, "Returning DID_TIME_OUT to scsi-ml "
 			   "due to FC_TIMED_OUT\n");
-		sc_cmd->result = (DID_BUS_BUSY << 16) | fsp->io_status;
+		sc_cmd->result = (DID_TIME_OUT << 16);
 		break;
 	default:
 		FC_FCP_DBG(fsp, "Returning DID_ERROR to scsi-ml "
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index af15f7a22d25..04d608ea9106 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -33,6 +33,7 @@
 struct lpfc_sli2_slim;
 
 #define ELX_MODEL_NAME_SIZE	80
+#define ELX_FW_NAME_SIZE	84
 
 #define LPFC_PCI_DEV_LP		0x1
 #define LPFC_PCI_DEV_OC		0x2
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index b1c9107d3408..d3a5d6ecdf7d 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -5905,11 +5905,11 @@ LPFC_ATTR_RW(ras_fwlog_level, 0, 0, 4, "Firmware Logging Level");
 /*
  * lpfc_ras_fwlog_func: Firmware logging enabled on function number
  * Default function which has RAS support : 0
- * Value Range is [0..7].
+ * Value Range is [0..3].
  * FW logging is a global action and enablement is via a specific
  * port.
  */
-LPFC_ATTR_RW(ras_fwlog_func, 0, 0, 7, "Firmware Logging Enabled on Function");
+LPFC_ATTR_RW(ras_fwlog_func, 0, 0, 3, "Firmware Logging Enabled on Function");
 
 /*
  * lpfc_enable_bbcr: Enable BB Credit Recovery
@@ -5954,7 +5954,7 @@ LPFC_ATTR_R(enable_mi, 1, 0, 1, "Enable MI");
  *       4 - 255  = vmid support enabled for 4-255 VMs
  *       Value range is [4,255].
  */
-LPFC_ATTR_RW(max_vmid, LPFC_MIN_VMID, LPFC_MIN_VMID, LPFC_MAX_VMID,
+LPFC_ATTR_R(max_vmid, LPFC_MIN_VMID, LPFC_MIN_VMID, LPFC_MAX_VMID,
 	     "Maximum number of VMs supported");
 
 /*
@@ -5962,7 +5962,7 @@ LPFC_ATTR_RW(max_vmid, LPFC_MIN_VMID, LPFC_MIN_VMID, LPFC_MAX_VMID,
  *       0  = Timeout is disabled
  * Value range is [0,24].
  */
-LPFC_ATTR_RW(vmid_inactivity_timeout, 4, 0, 24,
+LPFC_ATTR_R(vmid_inactivity_timeout, 4, 0, 24,
 	     "Inactivity timeout in hours");
 
 /*
@@ -5971,7 +5971,7 @@ LPFC_ATTR_RW(vmid_inactivity_timeout, 4, 0, 24,
  *       1  = Support is enabled
  * Value range is [0,1].
  */
-LPFC_ATTR_RW(vmid_app_header, LPFC_VMID_APP_HEADER_DISABLE,
+LPFC_ATTR_R(vmid_app_header, LPFC_VMID_APP_HEADER_DISABLE,
 	     LPFC_VMID_APP_HEADER_DISABLE, LPFC_VMID_APP_HEADER_ENABLE,
 	     "Enable App Header VMID support");
 
@@ -5982,7 +5982,7 @@ LPFC_ATTR_RW(vmid_app_header, LPFC_VMID_APP_HEADER_DISABLE,
  *       2  = Allow all targets
  * Value range is [0,2].
  */
-LPFC_ATTR_RW(vmid_priority_tagging, LPFC_VMID_PRIO_TAG_DISABLE,
+LPFC_ATTR_R(vmid_priority_tagging, LPFC_VMID_PRIO_TAG_DISABLE,
 	     LPFC_VMID_PRIO_TAG_DISABLE,
 	     LPFC_VMID_PRIO_TAG_ALL_TARGETS,
 	     "Enable Priority Tagging VMID support");
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index f9627eddab08..4d723200690a 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -1130,12 +1130,12 @@ stop_rr_fcf_flogi:
 			 vport->port_state, vport->fc_flag,
 			 sp->cmn.priority_tagging, kref_read(&ndlp->kref));
 
-	if (sp->cmn.priority_tagging)
-		vport->phba->pport->vmid_flag |= (LPFC_VMID_ISSUE_QFPA |
-						  LPFC_VMID_TYPE_PRIO);
 	/* reinitialize the VMID datastructure before returning */
 	if (lpfc_is_vmid_enabled(phba))
 		lpfc_reinit_vmid(vport);
+	if (sp->cmn.priority_tagging)
+		vport->phba->pport->vmid_flag |= (LPFC_VMID_ISSUE_QFPA |
+						  LPFC_VMID_TYPE_PRIO);
 
 	/*
 	 * Address a timing race with dev_loss.  If dev_loss is active on
@@ -2062,8 +2062,9 @@ lpfc_cmpl_els_plogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	/* PLOGI completes to NPort <nlp_DID> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0102 PLOGI completes to NPort x%06x "
-			 "Data: x%x x%x x%x x%x x%x\n",
-			 ndlp->nlp_DID, ndlp->nlp_fc4_type,
+			 "IoTag x%x Data: x%x x%x x%x x%x x%x\n",
+			 ndlp->nlp_DID, iotag,
+			 ndlp->nlp_fc4_type,
 			 ulp_status, ulp_word4,
 			 disc, vport->num_disc_nodes);
 
@@ -2128,8 +2129,8 @@ lpfc_cmpl_els_plogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 						NLP_EVT_DEVICE_RM);
 	} else {
 		/* Good status, call state machine */
-		prsp = list_entry(cmdiocb->cmd_dmabuf->list.next,
-				  struct lpfc_dmabuf, list);
+		prsp = list_get_first(&cmdiocb->cmd_dmabuf->list,
+				      struct lpfc_dmabuf, list);
 		if (!prsp)
 			goto out;
 		if (!lpfc_is_els_acc_rsp(prsp))
@@ -2362,9 +2363,10 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	/* PRLI completes to NPort <nlp_DID> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0103 PRLI completes to NPort x%06x "
-			 "Data: x%x x%x x%x x%x\n",
+			 "Data: x%x x%x x%x x%x x%x\n",
 			 ndlp->nlp_DID, ulp_status, ulp_word4,
-			 vport->num_disc_nodes, ndlp->fc4_prli_sent);
+			 vport->num_disc_nodes, ndlp->fc4_prli_sent,
+			 ndlp->fc4_xpt_flags);
 
 	/* Check to see if link went down during discovery */
 	if (lpfc_els_chk_latt(vport))
@@ -2805,7 +2807,7 @@ lpfc_cmpl_els_adisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	IOCB_t *irsp;
 	struct lpfc_nodelist *ndlp;
 	int  disc;
-	u32 ulp_status, ulp_word4, tmo;
+	u32 ulp_status, ulp_word4, tmo, iotag;
 	bool release_node = false;
 
 	/* we pass cmdiocb to state machine which needs rspiocb as well */
@@ -2818,9 +2820,11 @@ lpfc_cmpl_els_adisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
 	if (phba->sli_rev == LPFC_SLI_REV4) {
 		tmo = get_wqe_tmo(cmdiocb);
+		iotag = get_wqe_reqtag(cmdiocb);
 	} else {
 		irsp = &rspiocb->iocb;
 		tmo = irsp->ulpTimeout;
+		iotag = irsp->ulpIoTag;
 	}
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_CMD,
@@ -2838,9 +2842,11 @@ lpfc_cmpl_els_adisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	/* ADISC completes to NPort <nlp_DID> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0104 ADISC completes to NPort x%x "
-			 "Data: x%x x%x x%x x%x x%x\n",
-			 ndlp->nlp_DID, ulp_status, ulp_word4,
+			 "IoTag x%x Data: x%x x%x x%x x%x x%x\n",
+			 ndlp->nlp_DID, iotag,
+			 ulp_status, ulp_word4,
 			 tmo, disc, vport->num_disc_nodes);
+
 	/* Check to see if link went down during discovery */
 	if (lpfc_els_chk_latt(vport)) {
 		spin_lock_irq(&ndlp->lock);
@@ -3001,7 +3007,7 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	int wake_up_waiter = 0;
 	u32 ulp_status;
 	u32 ulp_word4;
-	u32 tmo;
+	u32 tmo, iotag;
 
 	/* we pass cmdiocb to state machine which needs rspiocb as well */
 	cmdiocb->rsp_iocb = rspiocb;
@@ -3011,9 +3017,11 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
 	if (phba->sli_rev == LPFC_SLI_REV4) {
 		tmo = get_wqe_tmo(cmdiocb);
+		iotag = get_wqe_reqtag(cmdiocb);
 	} else {
 		irsp = &rspiocb->iocb;
 		tmo = irsp->ulpTimeout;
+		iotag = irsp->ulpIoTag;
 	}
 
 	spin_lock_irq(&ndlp->lock);
@@ -3032,9 +3040,11 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	/* LOGO completes to NPort <nlp_DID> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0105 LOGO completes to NPort x%x "
-			 "refcnt %d nflags x%x Data: x%x x%x x%x x%x\n",
-			 ndlp->nlp_DID, kref_read(&ndlp->kref), ndlp->nlp_flag,
-			 ulp_status, ulp_word4,
+			 "IoTag x%x refcnt %d nflags x%x xflags x%x "
+			 "Data: x%x x%x x%x x%x\n",
+			 ndlp->nlp_DID, iotag,
+			 kref_read(&ndlp->kref), ndlp->nlp_flag,
+			 ndlp->fc4_xpt_flags, ulp_status, ulp_word4,
 			 tmo, vport->num_disc_nodes);
 
 	if (lpfc_els_chk_latt(vport)) {
@@ -5075,16 +5085,19 @@ out_retry:
 	if (logerr) {
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 			 "0137 No retry ELS command x%x to remote "
-			 "NPORT x%x: Out of Resources: Error:x%x/%x\n",
-			 cmd, did, ulp_status,
-			 ulp_word4);
+			 "NPORT x%x: Out of Resources: Error:x%x/%x "
+			 "IoTag x%x\n",
+			 cmd, did, ulp_status, ulp_word4,
+			 cmdiocb->iotag);
 	}
 	else {
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
-			 "0108 No retry ELS command x%x to remote "
-			 "NPORT x%x Retried:%d Error:x%x/%x\n",
-			 cmd, did, cmdiocb->retry, ulp_status,
-			 ulp_word4);
+				 "0108 No retry ELS command x%x to remote "
+				 "NPORT x%x Retried:%d Error:x%x/%x "
+				 "IoTag x%x nflags x%x\n",
+				 cmd, did, cmdiocb->retry, ulp_status,
+				 ulp_word4, cmdiocb->iotag,
+				 (ndlp ? ndlp->nlp_flag : 0));
 	}
 	return 0;
 }
@@ -11130,6 +11143,14 @@ mbox_err_exit:
 	lpfc_nlp_put(ndlp);
 
 	mempool_free(pmb, phba->mbox_mem_pool);
+
+	/* reinitialize the VMID datastructure before returning.
+	 * this is specifically for vport
+	 */
+	if (lpfc_is_vmid_enabled(phba))
+		lpfc_reinit_vmid(vport);
+	vport->vmid_flag = vport->phba->pport->vmid_flag;
+
 	return;
 }
 
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 7ef9841f0728..f80bbc315f4c 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -411,7 +411,7 @@ lpfc_check_nlp_post_devloss(struct lpfc_vport *vport,
 				 "port_state = x%x\n",
 				 ndlp->nlp_DID, kref_read(&ndlp->kref), ndlp,
 				 ndlp->nlp_flag, vport->port_state);
-		spin_lock_irqsave(&ndlp->lock, iflags);
+		return;
 	}
 	spin_unlock_irqrestore(&ndlp->lock, iflags);
 }
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index e7c47ee185a4..70bcee64bc8c 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -14721,7 +14721,7 @@ out:
 int
 lpfc_sli4_request_firmware_update(struct lpfc_hba *phba, uint8_t fw_upgrade)
 {
-	uint8_t file_name[ELX_MODEL_NAME_SIZE];
+	char file_name[ELX_FW_NAME_SIZE] = {0};
 	int ret;
 	const struct firmware *fw;
 
@@ -14730,7 +14730,7 @@ lpfc_sli4_request_firmware_update(struct lpfc_hba *phba, uint8_t fw_upgrade)
 	    LPFC_SLI_INTF_IF_TYPE_2)
 		return -EPERM;
 
-	snprintf(file_name, ELX_MODEL_NAME_SIZE, "%s.grp", phba->ModelName);
+	scnprintf(file_name, sizeof(file_name), "%s.grp", phba->ModelName);
 
 	if (fw_upgrade == INT_FW_UPGRADE) {
 		ret = request_firmware_nowait(THIS_MODULE, FW_ACTION_UEVENT,
diff --git a/drivers/scsi/lpfc/lpfc_mbox.c b/drivers/scsi/lpfc/lpfc_mbox.c
index 0dfdc0c4c08c..cadcd16494e1 100644
--- a/drivers/scsi/lpfc/lpfc_mbox.c
+++ b/drivers/scsi/lpfc/lpfc_mbox.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017-2022 Broadcom. All Rights Reserved. The term *
+ * Copyright (C) 2017-2023 Broadcom. All Rights Reserved. The term *
  * “Broadcom� refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
@@ -1814,7 +1814,9 @@ lpfc_sli4_mbox_cmd_free(struct lpfc_hba *phba, struct lpfcMboxq *mbox)
 		dma_free_coherent(&phba->pcidev->dev, SLI4_PAGE_SIZE,
 				  mbox->sge_array->addr[sgentry], phyaddr);
 	}
-	/* Free the sge address array memory */
+	/* Reinitialize the context pointers to avoid stale usage. */
+	mbox->ctx_buf = NULL;
+	mbox->context3 = NULL;
 	kfree(mbox->sge_array);
 	/* Finally, free the mailbox command itself */
 	mempool_free(mbox, phba->mbox_mem_pool);
diff --git a/drivers/scsi/lpfc/lpfc_mem.c b/drivers/scsi/lpfc/lpfc_mem.c
index 89cbeba06aea..2697da3248b3 100644
--- a/drivers/scsi/lpfc/lpfc_mem.c
+++ b/drivers/scsi/lpfc/lpfc_mem.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017-2022 Broadcom. All Rights Reserved. The term *
+ * Copyright (C) 2017-2023 Broadcom. All Rights Reserved. The term *
  * “Broadcom� refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
@@ -48,6 +48,29 @@
 #define LPFC_RRQ_POOL_SIZE	256	/* max elements in non-DMA  pool */
 #define LPFC_MBX_POOL_SIZE	256	/* max elements in MBX non-DMA pool */
 
+/* lpfc_mbox_free_sli_mbox
+ *
+ * @phba: HBA to free memory for
+ * @mbox: mailbox command to free
+ *
+ * This routine detects the mbox type and calls the correct
+ * free routine to fully release all associated memory.
+ */
+static void
+lpfc_mem_free_sli_mbox(struct lpfc_hba *phba, LPFC_MBOXQ_t *mbox)
+{
+	/* Detect if the caller's mbox is an SLI4_CONFIG type.  If so, this
+	 * mailbox type requires a different cleanup routine.  Otherwise, the
+	 * mailbox is just an mbuf and mem_pool release.
+	 */
+	if (phba->sli_rev == LPFC_SLI_REV4 &&
+	    bf_get(lpfc_mqe_command, &mbox->u.mqe) == MBX_SLI4_CONFIG) {
+		lpfc_sli4_mbox_cmd_free(phba, mbox);
+	} else {
+		lpfc_mbox_rsrc_cleanup(phba, mbox, MBOX_THD_UNLOCKED);
+	}
+}
+
 int
 lpfc_mem_alloc_active_rrq_pool_s4(struct lpfc_hba *phba) {
 	size_t bytes;
@@ -288,27 +311,16 @@ lpfc_mem_free_all(struct lpfc_hba *phba)
 {
 	struct lpfc_sli *psli = &phba->sli;
 	LPFC_MBOXQ_t *mbox, *next_mbox;
-	struct lpfc_dmabuf   *mp;
 
 	/* Free memory used in mailbox queue back to mailbox memory pool */
 	list_for_each_entry_safe(mbox, next_mbox, &psli->mboxq, list) {
-		mp = (struct lpfc_dmabuf *)(mbox->ctx_buf);
-		if (mp) {
-			lpfc_mbuf_free(phba, mp->virt, mp->phys);
-			kfree(mp);
-		}
 		list_del(&mbox->list);
-		mempool_free(mbox, phba->mbox_mem_pool);
+		lpfc_mem_free_sli_mbox(phba, mbox);
 	}
 	/* Free memory used in mailbox cmpl list back to mailbox memory pool */
 	list_for_each_entry_safe(mbox, next_mbox, &psli->mboxq_cmpl, list) {
-		mp = (struct lpfc_dmabuf *)(mbox->ctx_buf);
-		if (mp) {
-			lpfc_mbuf_free(phba, mp->virt, mp->phys);
-			kfree(mp);
-		}
 		list_del(&mbox->list);
-		mempool_free(mbox, phba->mbox_mem_pool);
+		lpfc_mem_free_sli_mbox(phba, mbox);
 	}
 	/* Free the active mailbox command back to the mailbox memory pool */
 	spin_lock_irq(&phba->hbalock);
@@ -316,12 +328,7 @@ lpfc_mem_free_all(struct lpfc_hba *phba)
 	spin_unlock_irq(&phba->hbalock);
 	if (psli->mbox_active) {
 		mbox = psli->mbox_active;
-		mp = (struct lpfc_dmabuf *)(mbox->ctx_buf);
-		if (mp) {
-			lpfc_mbuf_free(phba, mp->virt, mp->phys);
-			kfree(mp);
-		}
-		mempool_free(mbox, phba->mbox_mem_pool);
+		lpfc_mem_free_sli_mbox(phba, mbox);
 		psli->mbox_active = NULL;
 	}
 
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 9386e7b44750..46e6f807d1ca 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -2995,8 +2995,9 @@ lpfc_sli4_unreg_rpi_cmpl_clr(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 		     LPFC_SLI_INTF_IF_TYPE_2)) {
 			if (ndlp) {
 				lpfc_printf_vlog(
-					 vport, KERN_INFO, LOG_MBOX | LOG_SLI,
-					 "0010 UNREG_LOGIN vpi:%x "
+					 vport, KERN_INFO,
+					 LOG_MBOX | LOG_SLI | LOG_NODE,
+					 "0010 UNREG_LOGIN vpi:x%x "
 					 "rpi:%x DID:%x defer x%x flg x%x "
 					 "x%px\n",
 					 vport->vpi, ndlp->nlp_rpi,
@@ -3012,7 +3013,8 @@ lpfc_sli4_unreg_rpi_cmpl_clr(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 				    (ndlp->nlp_defer_did !=
 				    NLP_EVT_NOTHING_PENDING)) {
 					lpfc_printf_vlog(
-						vport, KERN_INFO, LOG_DISCOVERY,
+						vport, KERN_INFO,
+						LOG_MBOX | LOG_SLI | LOG_NODE,
 						"4111 UNREG cmpl deferred "
 						"clr x%x on "
 						"NPort x%x Data: x%x x%px\n",
@@ -3938,6 +3940,9 @@ void lpfc_poll_eratt(struct timer_list *t)
 	if (!(phba->hba_flag & HBA_SETUP))
 		return;
 
+	if (phba->pport->load_flag & FC_UNLOADING)
+		return;
+
 	/* Here we will also keep track of interrupts per sec of the hba */
 	sli_intr = phba->sli.slistat.sli_intr;
 
@@ -10141,11 +10146,12 @@ lpfc_sli_issue_mbox_s4(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq,
 	spin_unlock_irqrestore(&phba->hbalock, iflags);
 	lpfc_printf_log(phba, KERN_INFO, LOG_MBOX | LOG_SLI,
 			"(%d):0354 Mbox cmd issue - Enqueue Data: "
-			"x%x (x%x/x%x) x%x x%x x%x\n",
+			"x%x (x%x/x%x) x%x x%x x%x x%x\n",
 			mboxq->vport ? mboxq->vport->vpi : 0xffffff,
 			bf_get(lpfc_mqe_command, &mboxq->u.mqe),
 			lpfc_sli_config_mbox_subsys_get(phba, mboxq),
 			lpfc_sli_config_mbox_opcode_get(phba, mboxq),
+			mboxq->u.mb.un.varUnregLogin.rpi,
 			phba->pport->port_state,
 			psli->sli_flag, MBX_NOWAIT);
 	/* Wake up worker thread to transport mailbox command from head */
@@ -22167,6 +22173,12 @@ struct lpfc_io_buf *lpfc_get_io_buf(struct lpfc_hba *phba,
  * The data will be truncated if datasz is not large enough.
  * Version 1 is not supported with Embedded mbox cmd, so we must use version 0.
  * Returns the actual bytes read from the object.
+ *
+ * This routine is hard coded to use a poll completion.  Unlike other
+ * sli4_config mailboxes, it uses lpfc_mbuf memory which is not
+ * cleaned up in lpfc_sli4_cmd_mbox_free.  If this routine is modified
+ * to use interrupt-based completions, code is needed to fully cleanup
+ * the memory.
  */
 int
 lpfc_read_object(struct lpfc_hba *phba, char *rdobject, uint32_t *datap,
diff --git a/drivers/scsi/lpfc/lpfc_sli.h b/drivers/scsi/lpfc/lpfc_sli.h
index cd33dfec758c..c911a39cb46b 100644
--- a/drivers/scsi/lpfc/lpfc_sli.h
+++ b/drivers/scsi/lpfc/lpfc_sli.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017-2022 Broadcom. All Rights Reserved. The term *
+ * Copyright (C) 2017-2023 Broadcom. All Rights Reserved. The term *
  * “Broadcom� refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
@@ -182,9 +182,11 @@ typedef struct lpfcMboxq {
 		struct lpfc_mqe mqe;
 	} u;
 	struct lpfc_vport *vport; /* virtual port pointer */
-	void *ctx_ndlp;		  /* caller ndlp information */
-	void *ctx_buf;		  /* caller buffer information */
-	void *context3;
+	void *ctx_ndlp;		  /* an lpfc_nodelist pointer */
+	void *ctx_buf;		  /* an lpfc_dmabuf pointer */
+	void *context3;           /* a generic pointer.  Code must
+				   * accommodate the actual datatype.
+				   */
 
 	void (*mbox_cmpl) (struct lpfc_hba *, struct lpfcMboxq *);
 	uint8_t mbox_flag;
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index 88068834cab9..aba1c1cee8c4 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -20,7 +20,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "14.2.0.15"
+#define LPFC_DRIVER_VERSION "14.2.0.17"
 #define LPFC_DRIVER_NAME		"lpfc"
 
 /* Used for SLI 2/3 */
diff --git a/drivers/scsi/lpfc/lpfc_vmid.c b/drivers/scsi/lpfc/lpfc_vmid.c
index cf8ba840d0ea..773e02ae20c3 100644
--- a/drivers/scsi/lpfc/lpfc_vmid.c
+++ b/drivers/scsi/lpfc/lpfc_vmid.c
@@ -321,5 +321,6 @@ lpfc_reinit_vmid(struct lpfc_vport *vport)
 	if (!hash_empty(vport->hash_table))
 		hash_for_each_safe(vport->hash_table, bucket, tmp, cur, hnode)
 			hash_del(&cur->hnode);
+	vport->vmid_flag = 0;
 	write_unlock(&vport->vmid_lock);
 }
diff --git a/drivers/scsi/mac_esp.c b/drivers/scsi/mac_esp.c
index 3f0061b00494..187ae0a65d40 100644
--- a/drivers/scsi/mac_esp.c
+++ b/drivers/scsi/mac_esp.c
@@ -407,7 +407,7 @@ fail:
 	return err;
 }
 
-static int esp_mac_remove(struct platform_device *dev)
+static void esp_mac_remove(struct platform_device *dev)
 {
 	struct mac_esp_priv *mep = platform_get_drvdata(dev);
 	struct esp *esp = mep->esp;
@@ -428,13 +428,11 @@ static int esp_mac_remove(struct platform_device *dev)
 	kfree(esp->command_block);
 
 	scsi_host_put(esp->host);
-
-	return 0;
 }
 
 static struct platform_driver esp_mac_driver = {
 	.probe    = esp_mac_probe,
-	.remove   = esp_mac_remove,
+	.remove_new = esp_mac_remove,
 	.driver   = {
 		.name	= DRV_MODULE_NAME,
 	},
diff --git a/drivers/scsi/mac_scsi.c b/drivers/scsi/mac_scsi.c
index 2e511697fce3..181f16899fdc 100644
--- a/drivers/scsi/mac_scsi.c
+++ b/drivers/scsi/mac_scsi.c
@@ -523,7 +523,7 @@ fail_init:
 	return error;
 }
 
-static int __exit mac_scsi_remove(struct platform_device *pdev)
+static void __exit mac_scsi_remove(struct platform_device *pdev)
 {
 	struct Scsi_Host *instance = platform_get_drvdata(pdev);
 
@@ -532,11 +532,10 @@ static int __exit mac_scsi_remove(struct platform_device *pdev)
 		free_irq(instance->irq, instance);
 	NCR5380_exit(instance);
 	scsi_host_put(instance);
-	return 0;
 }
 
 static struct platform_driver mac_scsi_driver = {
-	.remove = __exit_p(mac_scsi_remove),
+	.remove_new = __exit_p(mac_scsi_remove),
 	.driver = {
 		.name	= DRV_MODULE_NAME,
 	},
diff --git a/drivers/scsi/mpi3mr/mpi/mpi30_ioc.h b/drivers/scsi/mpi3mr/mpi/mpi30_ioc.h
index 1e4a60fc655f..0cb24fc03620 100644
--- a/drivers/scsi/mpi3mr/mpi/mpi30_ioc.h
+++ b/drivers/scsi/mpi3mr/mpi/mpi30_ioc.h
@@ -28,6 +28,7 @@ struct mpi3_ioc_init_request {
 	__le64                   driver_information_address;
 };
 
+#define MPI3_IOCINIT_MSGFLAGS_SCSIIOSTATUSREPLY_SUPPORTED	(0x04)
 #define MPI3_IOCINIT_MSGFLAGS_HOSTMETADATA_MASK          (0x03)
 #define MPI3_IOCINIT_MSGFLAGS_HOSTMETADATA_NOT_USED      (0x00)
 #define MPI3_IOCINIT_MSGFLAGS_HOSTMETADATA_SEPARATED     (0x01)
diff --git a/drivers/scsi/mpi3mr/mpi3mr.h b/drivers/scsi/mpi3mr/mpi3mr.h
index ae98d15c30b1..3de1ee05c44e 100644
--- a/drivers/scsi/mpi3mr/mpi3mr.h
+++ b/drivers/scsi/mpi3mr/mpi3mr.h
@@ -55,8 +55,8 @@ extern struct list_head mrioc_list;
 extern int prot_mask;
 extern atomic64_t event_counter;
 
-#define MPI3MR_DRIVER_VERSION	"8.5.0.0.0"
-#define MPI3MR_DRIVER_RELDATE	"24-July-2023"
+#define MPI3MR_DRIVER_VERSION	"8.5.1.0.0"
+#define MPI3MR_DRIVER_RELDATE	"5-December-2023"
 
 #define MPI3MR_DRIVER_NAME	"mpi3mr"
 #define MPI3MR_DRIVER_LICENSE	"GPL"
@@ -218,14 +218,16 @@ extern atomic64_t event_counter;
  * @length: SGE length
  * @rsvd: Reserved
  * @rsvd1: Reserved
- * @sgl_type: sgl type
+ * @sub_type: sgl sub type
+ * @type: sgl type
  */
 struct mpi3mr_nvme_pt_sge {
-	u64 base_addr;
-	u32 length;
+	__le64 base_addr;
+	__le32 length;
 	u16 rsvd;
 	u8 rsvd1;
-	u8 sgl_type;
+	u8 sub_type:4;
+	u8 type:4;
 };
 
 /**
@@ -247,6 +249,8 @@ struct mpi3mr_buf_map {
 	u32 kern_buf_len;
 	dma_addr_t kern_buf_dma;
 	u8 data_dir;
+	u16 num_dma_desc;
+	struct dma_memory_desc *dma_desc;
 };
 
 /* IOC State definitions */
@@ -477,6 +481,10 @@ struct mpi3mr_throttle_group_info {
 /* HBA port flags */
 #define MPI3MR_HBA_PORT_FLAG_DIRTY	0x01
 
+/* IOCTL data transfer sge*/
+#define MPI3MR_NUM_IOCTL_SGE		256
+#define MPI3MR_IOCTL_SGE_SIZE		(8 * 1024)
+
 /**
  * struct mpi3mr_hba_port - HBA's port information
  * @port_id: Port number
@@ -506,7 +514,7 @@ struct mpi3mr_sas_port {
 	u8 num_phys;
 	u8 marked_responding;
 	int lowest_phy;
-	u32 phy_mask;
+	u64 phy_mask;
 	struct mpi3mr_hba_port *hba_port;
 	struct sas_identify remote_identify;
 	struct sas_rphy *rphy;
@@ -1042,6 +1050,11 @@ struct scmd_priv {
  * @sas_node_lock: Lock to protect SAS node list
  * @hba_port_table_list: List of HBA Ports
  * @enclosure_list: List of Enclosure objects
+ * @ioctl_dma_pool: DMA pool for IOCTL data buffers
+ * @ioctl_sge: DMA buffer descriptors for IOCTL data
+ * @ioctl_chain_sge: DMA buffer descriptor for IOCTL chain
+ * @ioctl_resp_sge: DMA buffer descriptor for Mgmt cmd response
+ * @ioctl_sges_allocated: Flag for IOCTL SGEs allocated or not
  */
 struct mpi3mr_ioc {
 	struct list_head list;
@@ -1227,6 +1240,12 @@ struct mpi3mr_ioc {
 	spinlock_t sas_node_lock;
 	struct list_head hba_port_table_list;
 	struct list_head enclosure_list;
+
+	struct dma_pool *ioctl_dma_pool;
+	struct dma_memory_desc ioctl_sge[MPI3MR_NUM_IOCTL_SGE];
+	struct dma_memory_desc ioctl_chain_sge;
+	struct dma_memory_desc ioctl_resp_sge;
+	bool ioctl_sges_allocated;
 };
 
 /**
diff --git a/drivers/scsi/mpi3mr/mpi3mr_app.c b/drivers/scsi/mpi3mr/mpi3mr_app.c
index 08645a99ad6b..0380996b5ad2 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_app.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_app.c
@@ -223,6 +223,22 @@ static long mpi3mr_bsg_pel_enable(struct mpi3mr_ioc *mrioc,
 		return rval;
 	}
 
+	if (mrioc->unrecoverable) {
+		dprint_bsg_err(mrioc, "%s: unrecoverable controller\n",
+			       __func__);
+		return -EFAULT;
+	}
+
+	if (mrioc->reset_in_progress) {
+		dprint_bsg_err(mrioc, "%s: reset in progress\n", __func__);
+		return -EAGAIN;
+	}
+
+	if (mrioc->stop_bsgs) {
+		dprint_bsg_err(mrioc, "%s: bsgs are blocked\n", __func__);
+		return -EAGAIN;
+	}
+
 	sg_copy_to_buffer(job->request_payload.sg_list,
 			  job->request_payload.sg_cnt,
 			  &pel_enable, sizeof(pel_enable));
@@ -548,7 +564,36 @@ static long mpi3mr_bsg_process_drv_cmds(struct bsg_job *job)
 }
 
 /**
+ * mpi3mr_total_num_ioctl_sges - Count number of SGEs required
+ * @drv_bufs: DMA address of the buffers to be placed in sgl
+ * @bufcnt: Number of DMA buffers
+ *
+ * This function returns total number of data SGEs required
+ * including zero length SGEs and excluding management request
+ * and response buffer for the given list of data buffer
+ * descriptors
+ *
+ * Return: Number of SGE elements needed
+ */
+static inline u16 mpi3mr_total_num_ioctl_sges(struct mpi3mr_buf_map *drv_bufs,
+					      u8 bufcnt)
+{
+	u16 i, sge_count = 0;
+
+	for (i = 0; i < bufcnt; i++, drv_bufs++) {
+		if (drv_bufs->data_dir == DMA_NONE ||
+		    drv_bufs->kern_buf)
+			continue;
+		sge_count += drv_bufs->num_dma_desc;
+		if (!drv_bufs->num_dma_desc)
+			sge_count++;
+	}
+	return sge_count;
+}
+
+/**
  * mpi3mr_bsg_build_sgl - SGL construction for MPI commands
+ * @mrioc: Adapter instance reference
  * @mpi_req: MPI request
  * @sgl_offset: offset to start sgl in the MPI request
  * @drv_bufs: DMA address of the buffers to be placed in sgl
@@ -560,27 +605,45 @@ static long mpi3mr_bsg_process_drv_cmds(struct bsg_job *job)
  * This function places the DMA address of the given buffers in
  * proper format as SGEs in the given MPI request.
  *
- * Return: Nothing
+ * Return: 0 on success,-1 on failure
  */
-static void mpi3mr_bsg_build_sgl(u8 *mpi_req, uint32_t sgl_offset,
-	struct mpi3mr_buf_map *drv_bufs, u8 bufcnt, u8 is_rmc,
-	u8 is_rmr, u8 num_datasges)
+static int mpi3mr_bsg_build_sgl(struct mpi3mr_ioc *mrioc, u8 *mpi_req,
+				u32 sgl_offset, struct mpi3mr_buf_map *drv_bufs,
+				u8 bufcnt, u8 is_rmc, u8 is_rmr, u8 num_datasges)
 {
+	struct mpi3_request_header *mpi_header =
+		(struct mpi3_request_header *)mpi_req;
 	u8 *sgl = (mpi_req + sgl_offset), count = 0;
 	struct mpi3_mgmt_passthrough_request *rmgmt_req =
 	    (struct mpi3_mgmt_passthrough_request *)mpi_req;
 	struct mpi3mr_buf_map *drv_buf_iter = drv_bufs;
-	u8 sgl_flags, sgl_flags_last;
+	u8 flag, sgl_flags, sgl_flag_eob, sgl_flags_last, last_chain_sgl_flag;
+	u16 available_sges, i, sges_needed;
+	u32 sge_element_size = sizeof(struct mpi3_sge_common);
+	bool chain_used = false;
 
 	sgl_flags = MPI3_SGE_FLAGS_ELEMENT_TYPE_SIMPLE |
-		MPI3_SGE_FLAGS_DLAS_SYSTEM | MPI3_SGE_FLAGS_END_OF_BUFFER;
-	sgl_flags_last = sgl_flags | MPI3_SGE_FLAGS_END_OF_LIST;
+		MPI3_SGE_FLAGS_DLAS_SYSTEM;
+	sgl_flag_eob = sgl_flags | MPI3_SGE_FLAGS_END_OF_BUFFER;
+	sgl_flags_last = sgl_flag_eob | MPI3_SGE_FLAGS_END_OF_LIST;
+	last_chain_sgl_flag = MPI3_SGE_FLAGS_ELEMENT_TYPE_LAST_CHAIN |
+	    MPI3_SGE_FLAGS_DLAS_SYSTEM;
+
+	sges_needed = mpi3mr_total_num_ioctl_sges(drv_bufs, bufcnt);
 
 	if (is_rmc) {
 		mpi3mr_add_sg_single(&rmgmt_req->command_sgl,
 		    sgl_flags_last, drv_buf_iter->kern_buf_len,
 		    drv_buf_iter->kern_buf_dma);
-		sgl = (u8 *)drv_buf_iter->kern_buf + drv_buf_iter->bsg_buf_len;
+		sgl = (u8 *)drv_buf_iter->kern_buf +
+			drv_buf_iter->bsg_buf_len;
+		available_sges = (drv_buf_iter->kern_buf_len -
+		    drv_buf_iter->bsg_buf_len) / sge_element_size;
+
+		if (sges_needed > available_sges)
+			return -1;
+
+		chain_used = true;
 		drv_buf_iter++;
 		count++;
 		if (is_rmr) {
@@ -592,23 +655,95 @@ static void mpi3mr_bsg_build_sgl(u8 *mpi_req, uint32_t sgl_offset,
 		} else
 			mpi3mr_build_zero_len_sge(
 			    &rmgmt_req->response_sgl);
+		if (num_datasges) {
+			i = 0;
+			goto build_sges;
+		}
+	} else {
+		if (sgl_offset >= MPI3MR_ADMIN_REQ_FRAME_SZ)
+			return -1;
+		available_sges = (MPI3MR_ADMIN_REQ_FRAME_SZ - sgl_offset) /
+		sge_element_size;
+		if (!available_sges)
+			return -1;
 	}
 	if (!num_datasges) {
 		mpi3mr_build_zero_len_sge(sgl);
-		return;
+		return 0;
 	}
+	if (mpi_header->function == MPI3_BSG_FUNCTION_SMP_PASSTHROUGH) {
+		if ((sges_needed > 2) || (sges_needed > available_sges))
+			return -1;
+		for (; count < bufcnt; count++, drv_buf_iter++) {
+			if (drv_buf_iter->data_dir == DMA_NONE ||
+			    !drv_buf_iter->num_dma_desc)
+				continue;
+			mpi3mr_add_sg_single(sgl, sgl_flags_last,
+					     drv_buf_iter->dma_desc[0].size,
+					     drv_buf_iter->dma_desc[0].dma_addr);
+			sgl += sge_element_size;
+		}
+		return 0;
+	}
+	i = 0;
+
+build_sges:
 	for (; count < bufcnt; count++, drv_buf_iter++) {
 		if (drv_buf_iter->data_dir == DMA_NONE)
 			continue;
-		if (num_datasges == 1 || !is_rmc)
-			mpi3mr_add_sg_single(sgl, sgl_flags_last,
-			    drv_buf_iter->kern_buf_len, drv_buf_iter->kern_buf_dma);
-		else
-			mpi3mr_add_sg_single(sgl, sgl_flags,
-			    drv_buf_iter->kern_buf_len, drv_buf_iter->kern_buf_dma);
-		sgl += sizeof(struct mpi3_sge_common);
+		if (!drv_buf_iter->num_dma_desc) {
+			if (chain_used && !available_sges)
+				return -1;
+			if (!chain_used && (available_sges == 1) &&
+			    (sges_needed > 1))
+				goto setup_chain;
+			flag = sgl_flag_eob;
+			if (num_datasges == 1)
+				flag = sgl_flags_last;
+			mpi3mr_add_sg_single(sgl, flag, 0, 0);
+			sgl += sge_element_size;
+			sges_needed--;
+			available_sges--;
+			num_datasges--;
+			continue;
+		}
+		for (; i < drv_buf_iter->num_dma_desc; i++) {
+			if (chain_used && !available_sges)
+				return -1;
+			if (!chain_used && (available_sges == 1) &&
+			    (sges_needed > 1))
+				goto setup_chain;
+			flag = sgl_flags;
+			if (i == (drv_buf_iter->num_dma_desc - 1)) {
+				if (num_datasges == 1)
+					flag = sgl_flags_last;
+				else
+					flag = sgl_flag_eob;
+			}
+
+			mpi3mr_add_sg_single(sgl, flag,
+					     drv_buf_iter->dma_desc[i].size,
+					     drv_buf_iter->dma_desc[i].dma_addr);
+			sgl += sge_element_size;
+			available_sges--;
+			sges_needed--;
+		}
 		num_datasges--;
+		i = 0;
 	}
+	return 0;
+
+setup_chain:
+	available_sges = mrioc->ioctl_chain_sge.size / sge_element_size;
+	if (sges_needed > available_sges)
+		return -1;
+	mpi3mr_add_sg_single(sgl, last_chain_sgl_flag,
+			     (sges_needed * sge_element_size),
+			     mrioc->ioctl_chain_sge.dma_addr);
+	memset(mrioc->ioctl_chain_sge.addr, 0, mrioc->ioctl_chain_sge.size);
+	sgl = (u8 *)mrioc->ioctl_chain_sge.addr;
+	chain_used = true;
+	goto build_sges;
 }
 
 /**
@@ -648,14 +783,20 @@ static int mpi3mr_build_nvme_sgl(struct mpi3mr_ioc *mrioc,
 	struct mpi3mr_buf_map *drv_bufs, u8 bufcnt)
 {
 	struct mpi3mr_nvme_pt_sge *nvme_sgl;
-	u64 sgl_ptr;
+	__le64 sgl_dma;
 	u8 count;
 	size_t length = 0;
+	u16 available_sges = 0, i;
+	u32 sge_element_size = sizeof(struct mpi3mr_nvme_pt_sge);
 	struct mpi3mr_buf_map *drv_buf_iter = drv_bufs;
 	u64 sgemod_mask = ((u64)((mrioc->facts.sge_mod_mask) <<
 			    mrioc->facts.sge_mod_shift) << 32);
 	u64 sgemod_val = ((u64)(mrioc->facts.sge_mod_value) <<
 			  mrioc->facts.sge_mod_shift) << 32;
+	u32 size;
+
+	nvme_sgl = (struct mpi3mr_nvme_pt_sge *)
+	    ((u8 *)(nvme_encap_request->command) + MPI3MR_NVME_CMD_SGL_OFFSET);
 
 	/*
 	 * Not all commands require a data transfer. If no data, just return
@@ -664,27 +805,59 @@ static int mpi3mr_build_nvme_sgl(struct mpi3mr_ioc *mrioc,
 	for (count = 0; count < bufcnt; count++, drv_buf_iter++) {
 		if (drv_buf_iter->data_dir == DMA_NONE)
 			continue;
-		sgl_ptr = (u64)drv_buf_iter->kern_buf_dma;
 		length = drv_buf_iter->kern_buf_len;
 		break;
 	}
-	if (!length)
+	if (!length || !drv_buf_iter->num_dma_desc)
 		return 0;
 
-	if (sgl_ptr & sgemod_mask) {
+	if (drv_buf_iter->num_dma_desc == 1) {
+		available_sges = 1;
+		goto build_sges;
+	}
+
+	sgl_dma = cpu_to_le64(mrioc->ioctl_chain_sge.dma_addr);
+	if (sgl_dma & sgemod_mask) {
 		dprint_bsg_err(mrioc,
-		    "%s: SGL address collides with SGE modifier\n",
+		    "%s: SGL chain address collides with SGE modifier\n",
 		    __func__);
 		return -1;
 	}
 
-	sgl_ptr &= ~sgemod_mask;
-	sgl_ptr |= sgemod_val;
-	nvme_sgl = (struct mpi3mr_nvme_pt_sge *)
-	    ((u8 *)(nvme_encap_request->command) + MPI3MR_NVME_CMD_SGL_OFFSET);
+	sgl_dma &= ~sgemod_mask;
+	sgl_dma |= sgemod_val;
+
+	memset(mrioc->ioctl_chain_sge.addr, 0, mrioc->ioctl_chain_sge.size);
+	available_sges = mrioc->ioctl_chain_sge.size / sge_element_size;
+	if (available_sges < drv_buf_iter->num_dma_desc)
+		return -1;
 	memset(nvme_sgl, 0, sizeof(struct mpi3mr_nvme_pt_sge));
-	nvme_sgl->base_addr = sgl_ptr;
-	nvme_sgl->length = length;
+	nvme_sgl->base_addr = sgl_dma;
+	size = drv_buf_iter->num_dma_desc * sizeof(struct mpi3mr_nvme_pt_sge);
+	nvme_sgl->length = cpu_to_le32(size);
+	nvme_sgl->type = MPI3MR_NVMESGL_LAST_SEGMENT;
+	nvme_sgl = (struct mpi3mr_nvme_pt_sge *)mrioc->ioctl_chain_sge.addr;
+
+build_sges:
+	for (i = 0; i < drv_buf_iter->num_dma_desc; i++) {
+		sgl_dma = cpu_to_le64(drv_buf_iter->dma_desc[i].dma_addr);
+		if (sgl_dma & sgemod_mask) {
+			dprint_bsg_err(mrioc,
+				       "%s: SGL address collides with SGE modifier\n",
+				       __func__);
+		return -1;
+		}
+
+		sgl_dma &= ~sgemod_mask;
+		sgl_dma |= sgemod_val;
+
+		nvme_sgl->base_addr = sgl_dma;
+		nvme_sgl->length = cpu_to_le32(drv_buf_iter->dma_desc[i].size);
+		nvme_sgl->type = MPI3MR_NVMESGL_DATA_SEGMENT;
+		nvme_sgl++;
+		available_sges--;
+	}
+
 	return 0;
 }
 
@@ -712,7 +885,7 @@ static int mpi3mr_build_nvme_prp(struct mpi3mr_ioc *mrioc,
 	dma_addr_t prp_entry_dma, prp_page_dma, dma_addr;
 	u32 offset, entry_len, dev_pgsz;
 	u32 page_mask_result, page_mask;
-	size_t length = 0;
+	size_t length = 0, desc_len;
 	u8 count;
 	struct mpi3mr_buf_map *drv_buf_iter = drv_bufs;
 	u64 sgemod_mask = ((u64)((mrioc->facts.sge_mod_mask) <<
@@ -721,6 +894,7 @@ static int mpi3mr_build_nvme_prp(struct mpi3mr_ioc *mrioc,
 			  mrioc->facts.sge_mod_shift) << 32;
 	u16 dev_handle = nvme_encap_request->dev_handle;
 	struct mpi3mr_tgt_dev *tgtdev;
+	u16 desc_count = 0;
 
 	tgtdev = mpi3mr_get_tgtdev_by_handle(mrioc, dev_handle);
 	if (!tgtdev) {
@@ -739,6 +913,21 @@ static int mpi3mr_build_nvme_prp(struct mpi3mr_ioc *mrioc,
 
 	dev_pgsz = 1 << (tgtdev->dev_spec.pcie_inf.pgsz);
 	mpi3mr_tgtdev_put(tgtdev);
+	page_mask = dev_pgsz - 1;
+
+	if (dev_pgsz > MPI3MR_IOCTL_SGE_SIZE) {
+		dprint_bsg_err(mrioc,
+			       "%s: NVMe device page size(%d) is greater than ioctl data sge size(%d) for handle 0x%04x\n",
+			       __func__, dev_pgsz,  MPI3MR_IOCTL_SGE_SIZE, dev_handle);
+		return -1;
+	}
+
+	if (MPI3MR_IOCTL_SGE_SIZE % dev_pgsz) {
+		dprint_bsg_err(mrioc,
+			       "%s: ioctl data sge size(%d) is not a multiple of NVMe device page size(%d) for handle 0x%04x\n",
+			       __func__, MPI3MR_IOCTL_SGE_SIZE, dev_pgsz, dev_handle);
+		return -1;
+	}
 
 	/*
 	 * Not all commands require a data transfer. If no data, just return
@@ -747,14 +936,26 @@ static int mpi3mr_build_nvme_prp(struct mpi3mr_ioc *mrioc,
 	for (count = 0; count < bufcnt; count++, drv_buf_iter++) {
 		if (drv_buf_iter->data_dir == DMA_NONE)
 			continue;
-		dma_addr = drv_buf_iter->kern_buf_dma;
 		length = drv_buf_iter->kern_buf_len;
 		break;
 	}
 
-	if (!length)
+	if (!length || !drv_buf_iter->num_dma_desc)
 		return 0;
 
+	for (count = 0; count < drv_buf_iter->num_dma_desc; count++) {
+		dma_addr = drv_buf_iter->dma_desc[count].dma_addr;
+		if (dma_addr & page_mask) {
+			dprint_bsg_err(mrioc,
+				       "%s:dma_addr %pad is not aligned with page size 0x%x\n",
+				       __func__,  &dma_addr, dev_pgsz);
+			return -1;
+		}
+	}
+
+	dma_addr = drv_buf_iter->dma_desc[0].dma_addr;
+	desc_len = drv_buf_iter->dma_desc[0].size;
+
 	mrioc->prp_sz = 0;
 	mrioc->prp_list_virt = dma_alloc_coherent(&mrioc->pdev->dev,
 	    dev_pgsz, &mrioc->prp_list_dma, GFP_KERNEL);
@@ -784,7 +985,6 @@ static int mpi3mr_build_nvme_prp(struct mpi3mr_ioc *mrioc,
 	 * Check if we are within 1 entry of a page boundary we don't
 	 * want our first entry to be a PRP List entry.
 	 */
-	page_mask = dev_pgsz - 1;
 	page_mask_result = (uintptr_t)((u8 *)prp_page + prp_size) & page_mask;
 	if (!page_mask_result) {
 		dprint_bsg_err(mrioc, "%s: PRP page is not page aligned\n",
@@ -898,18 +1098,31 @@ static int mpi3mr_build_nvme_prp(struct mpi3mr_ioc *mrioc,
 			prp_entry_dma += prp_size;
 		}
 
-		/*
-		 * Bump the phys address of the command's data buffer by the
-		 * entry_len.
-		 */
-		dma_addr += entry_len;
-
 		/* decrement length accounting for last partial page. */
-		if (entry_len > length)
+		if (entry_len >= length) {
 			length = 0;
-		else
+		} else {
+			if (entry_len <= desc_len) {
+				dma_addr += entry_len;
+				desc_len -= entry_len;
+			}
+			if (!desc_len) {
+				if ((++desc_count) >=
+				   drv_buf_iter->num_dma_desc) {
+					dprint_bsg_err(mrioc,
+						       "%s: Invalid len %zd while building PRP\n",
+						       __func__, length);
+					goto err_out;
+				}
+				dma_addr =
+				    drv_buf_iter->dma_desc[desc_count].dma_addr;
+				desc_len =
+				    drv_buf_iter->dma_desc[desc_count].size;
+			}
 			length -= entry_len;
+		}
 	}
+
 	return 0;
 err_out:
 	if (mrioc->prp_list_virt) {
@@ -919,10 +1132,66 @@ err_out:
 	}
 	return -1;
 }
+
+/**
+ * mpi3mr_map_data_buffer_dma - build dma descriptors for data
+ *                              buffers
+ * @mrioc: Adapter instance reference
+ * @drv_buf: buffer map descriptor
+ * @desc_count: Number of already consumed dma descriptors
+ *
+ * This function computes how many pre-allocated DMA descriptors
+ * are required for the given data buffer and if those number of
+ * descriptors are free, then setup the mapping of the scattered
+ * DMA address to the given data buffer, if the data direction
+ * of the buffer is DMA_TO_DEVICE then the actual data is copied to
+ * the DMA buffers
+ *
+ * Return: 0 on success, -1 on failure
+ */
+static int mpi3mr_map_data_buffer_dma(struct mpi3mr_ioc *mrioc,
+				      struct mpi3mr_buf_map *drv_buf,
+				      u16 desc_count)
+{
+	u16 i, needed_desc = drv_buf->kern_buf_len / MPI3MR_IOCTL_SGE_SIZE;
+	u32 buf_len = drv_buf->kern_buf_len, copied_len = 0;
+
+	if (drv_buf->kern_buf_len % MPI3MR_IOCTL_SGE_SIZE)
+		needed_desc++;
+	if ((needed_desc + desc_count) > MPI3MR_NUM_IOCTL_SGE) {
+		dprint_bsg_err(mrioc, "%s: DMA descriptor mapping error %d:%d:%d\n",
+			       __func__, needed_desc, desc_count, MPI3MR_NUM_IOCTL_SGE);
+		return -1;
+	}
+	drv_buf->dma_desc = kzalloc(sizeof(*drv_buf->dma_desc) * needed_desc,
+				    GFP_KERNEL);
+	if (!drv_buf->dma_desc)
+		return -1;
+	for (i = 0; i < needed_desc; i++, desc_count++) {
+		drv_buf->dma_desc[i].addr = mrioc->ioctl_sge[desc_count].addr;
+		drv_buf->dma_desc[i].dma_addr =
+		    mrioc->ioctl_sge[desc_count].dma_addr;
+		if (buf_len < mrioc->ioctl_sge[desc_count].size)
+			drv_buf->dma_desc[i].size = buf_len;
+		else
+			drv_buf->dma_desc[i].size =
+			    mrioc->ioctl_sge[desc_count].size;
+		buf_len -= drv_buf->dma_desc[i].size;
+		memset(drv_buf->dma_desc[i].addr, 0,
+		       mrioc->ioctl_sge[desc_count].size);
+		if (drv_buf->data_dir == DMA_TO_DEVICE) {
+			memcpy(drv_buf->dma_desc[i].addr,
+			       drv_buf->bsg_buf + copied_len,
+			       drv_buf->dma_desc[i].size);
+			copied_len += drv_buf->dma_desc[i].size;
+		}
+	}
+	drv_buf->num_dma_desc = needed_desc;
+	return 0;
+}
 /**
  * mpi3mr_bsg_process_mpt_cmds - MPI Pass through BSG handler
  * @job: BSG job reference
- * @reply_payload_rcv_len: length of payload recvd
  *
  * This function is the top level handler for MPI Pass through
  * command, this does basic validation of the input data buffers,
@@ -938,10 +1207,9 @@ err_out:
  * Return: 0 on success and proper error codes on failure
  */
 
-static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job, unsigned int *reply_payload_rcv_len)
+static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job)
 {
 	long rval = -EINVAL;
-
 	struct mpi3mr_ioc *mrioc = NULL;
 	u8 *mpi_req = NULL, *sense_buff_k = NULL;
 	u8 mpi_msg_size = 0;
@@ -949,9 +1217,10 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job, unsigned int *reply
 	struct mpi3mr_bsg_mptcmd *karg;
 	struct mpi3mr_buf_entry *buf_entries = NULL;
 	struct mpi3mr_buf_map *drv_bufs = NULL, *drv_buf_iter = NULL;
-	u8 count, bufcnt = 0, is_rmcb = 0, is_rmrb = 0, din_cnt = 0, dout_cnt = 0;
-	u8 invalid_be = 0, erb_offset = 0xFF, mpirep_offset = 0xFF, sg_entries = 0;
-	u8 block_io = 0, resp_code = 0, nvme_fmt = 0;
+	u8 count, bufcnt = 0, is_rmcb = 0, is_rmrb = 0;
+	u8 din_cnt = 0, dout_cnt = 0;
+	u8 invalid_be = 0, erb_offset = 0xFF, mpirep_offset = 0xFF;
+	u8 block_io = 0, nvme_fmt = 0, resp_code = 0;
 	struct mpi3_request_header *mpi_header = NULL;
 	struct mpi3_status_reply_descriptor *status_desc;
 	struct mpi3_scsi_task_mgmt_request *tm_req;
@@ -963,6 +1232,7 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job, unsigned int *reply
 	u32 din_size = 0, dout_size = 0;
 	u8 *din_buf = NULL, *dout_buf = NULL;
 	u8 *sgl_iter = NULL, *sgl_din_iter = NULL, *sgl_dout_iter = NULL;
+	u16 rmc_size  = 0, desc_count = 0;
 
 	bsg_req = job->request;
 	karg = (struct mpi3mr_bsg_mptcmd *)&bsg_req->cmd.mptcmd;
@@ -971,6 +1241,12 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job, unsigned int *reply
 	if (!mrioc)
 		return -ENODEV;
 
+	if (!mrioc->ioctl_sges_allocated) {
+		dprint_bsg_err(mrioc, "%s: DMA memory was not allocated\n",
+			       __func__);
+		return -ENOMEM;
+	}
+
 	if (karg->timeout < MPI3MR_APP_DEFAULT_TIMEOUT)
 		karg->timeout = MPI3MR_APP_DEFAULT_TIMEOUT;
 
@@ -1011,26 +1287,13 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job, unsigned int *reply
 
 	for (count = 0; count < bufcnt; count++, buf_entries++, drv_buf_iter++) {
 
-		if (sgl_dout_iter > (dout_buf + job->request_payload.payload_len)) {
-			dprint_bsg_err(mrioc, "%s: data_out buffer length mismatch\n",
-				__func__);
-			rval = -EINVAL;
-			goto out;
-		}
-		if (sgl_din_iter > (din_buf + job->reply_payload.payload_len)) {
-			dprint_bsg_err(mrioc, "%s: data_in buffer length mismatch\n",
-				__func__);
-			rval = -EINVAL;
-			goto out;
-		}
-
 		switch (buf_entries->buf_type) {
 		case MPI3MR_BSG_BUFTYPE_RAIDMGMT_CMD:
 			sgl_iter = sgl_dout_iter;
 			sgl_dout_iter += buf_entries->buf_len;
 			drv_buf_iter->data_dir = DMA_TO_DEVICE;
 			is_rmcb = 1;
-			if (count != 0)
+			if ((count != 0) || !buf_entries->buf_len)
 				invalid_be = 1;
 			break;
 		case MPI3MR_BSG_BUFTYPE_RAIDMGMT_RESP:
@@ -1038,7 +1301,7 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job, unsigned int *reply
 			sgl_din_iter += buf_entries->buf_len;
 			drv_buf_iter->data_dir = DMA_FROM_DEVICE;
 			is_rmrb = 1;
-			if (count != 1 || !is_rmcb)
+			if (count != 1 || !is_rmcb || !buf_entries->buf_len)
 				invalid_be = 1;
 			break;
 		case MPI3MR_BSG_BUFTYPE_DATA_IN:
@@ -1046,7 +1309,7 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job, unsigned int *reply
 			sgl_din_iter += buf_entries->buf_len;
 			drv_buf_iter->data_dir = DMA_FROM_DEVICE;
 			din_cnt++;
-			din_size += drv_buf_iter->bsg_buf_len;
+			din_size += buf_entries->buf_len;
 			if ((din_cnt > 1) && !is_rmcb)
 				invalid_be = 1;
 			break;
@@ -1055,7 +1318,7 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job, unsigned int *reply
 			sgl_dout_iter += buf_entries->buf_len;
 			drv_buf_iter->data_dir = DMA_TO_DEVICE;
 			dout_cnt++;
-			dout_size += drv_buf_iter->bsg_buf_len;
+			dout_size += buf_entries->buf_len;
 			if ((dout_cnt > 1) && !is_rmcb)
 				invalid_be = 1;
 			break;
@@ -1064,12 +1327,16 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job, unsigned int *reply
 			sgl_din_iter += buf_entries->buf_len;
 			drv_buf_iter->data_dir = DMA_NONE;
 			mpirep_offset = count;
+			if (!buf_entries->buf_len)
+				invalid_be = 1;
 			break;
 		case MPI3MR_BSG_BUFTYPE_ERR_RESPONSE:
 			sgl_iter = sgl_din_iter;
 			sgl_din_iter += buf_entries->buf_len;
 			drv_buf_iter->data_dir = DMA_NONE;
 			erb_offset = count;
+			if (!buf_entries->buf_len)
+				invalid_be = 1;
 			break;
 		case MPI3MR_BSG_BUFTYPE_MPI_REQUEST:
 			sgl_iter = sgl_dout_iter;
@@ -1096,21 +1363,31 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job, unsigned int *reply
 			goto out;
 		}
 
-		drv_buf_iter->bsg_buf = sgl_iter;
-		drv_buf_iter->bsg_buf_len = buf_entries->buf_len;
-
-	}
-	if (!is_rmcb && (dout_cnt || din_cnt)) {
-		sg_entries = dout_cnt + din_cnt;
-		if (((mpi_msg_size) + (sg_entries *
-		      sizeof(struct mpi3_sge_common))) > MPI3MR_ADMIN_REQ_FRAME_SZ) {
-			dprint_bsg_err(mrioc,
-			    "%s:%d: invalid message size passed\n",
-			    __func__, __LINE__);
+		if (sgl_dout_iter > (dout_buf + job->request_payload.payload_len)) {
+			dprint_bsg_err(mrioc, "%s: data_out buffer length mismatch\n",
+				       __func__);
 			rval = -EINVAL;
 			goto out;
 		}
+		if (sgl_din_iter > (din_buf + job->reply_payload.payload_len)) {
+			dprint_bsg_err(mrioc, "%s: data_in buffer length mismatch\n",
+				       __func__);
+			rval = -EINVAL;
+			goto out;
+		}
+
+		drv_buf_iter->bsg_buf = sgl_iter;
+		drv_buf_iter->bsg_buf_len = buf_entries->buf_len;
 	}
+
+	if (is_rmcb && ((din_size + dout_size) > MPI3MR_MAX_APP_XFER_SIZE)) {
+		dprint_bsg_err(mrioc, "%s:%d: invalid data transfer size passed for function 0x%x din_size = %d, dout_size = %d\n",
+			       __func__, __LINE__, mpi_header->function, din_size,
+			       dout_size);
+		rval = -EINVAL;
+		goto out;
+	}
+
 	if (din_size > MPI3MR_MAX_APP_XFER_SIZE) {
 		dprint_bsg_err(mrioc,
 		    "%s:%d: invalid data transfer size passed for function 0x%x din_size=%d\n",
@@ -1126,30 +1403,64 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job, unsigned int *reply
 		goto out;
 	}
 
+	if (mpi_header->function == MPI3_BSG_FUNCTION_SMP_PASSTHROUGH) {
+		if (din_size > MPI3MR_IOCTL_SGE_SIZE ||
+		    dout_size > MPI3MR_IOCTL_SGE_SIZE) {
+			dprint_bsg_err(mrioc, "%s:%d: invalid message size passed:%d:%d:%d:%d\n",
+				       __func__, __LINE__, din_cnt, dout_cnt, din_size,
+			    dout_size);
+			rval = -EINVAL;
+			goto out;
+		}
+	}
+
 	drv_buf_iter = drv_bufs;
 	for (count = 0; count < bufcnt; count++, drv_buf_iter++) {
 		if (drv_buf_iter->data_dir == DMA_NONE)
 			continue;
 
 		drv_buf_iter->kern_buf_len = drv_buf_iter->bsg_buf_len;
-		if (is_rmcb && !count)
-			drv_buf_iter->kern_buf_len += ((dout_cnt + din_cnt) *
-			    sizeof(struct mpi3_sge_common));
-
-		if (!drv_buf_iter->kern_buf_len)
-			continue;
-
-		drv_buf_iter->kern_buf = dma_alloc_coherent(&mrioc->pdev->dev,
-		    drv_buf_iter->kern_buf_len, &drv_buf_iter->kern_buf_dma,
-		    GFP_KERNEL);
-		if (!drv_buf_iter->kern_buf) {
-			rval = -ENOMEM;
-			goto out;
-		}
-		if (drv_buf_iter->data_dir == DMA_TO_DEVICE) {
+		if (is_rmcb && !count) {
+			drv_buf_iter->kern_buf_len =
+			    mrioc->ioctl_chain_sge.size;
+			drv_buf_iter->kern_buf =
+			    mrioc->ioctl_chain_sge.addr;
+			drv_buf_iter->kern_buf_dma =
+			    mrioc->ioctl_chain_sge.dma_addr;
+			drv_buf_iter->dma_desc = NULL;
+			drv_buf_iter->num_dma_desc = 0;
+			memset(drv_buf_iter->kern_buf, 0,
+			       drv_buf_iter->kern_buf_len);
 			tmplen = min(drv_buf_iter->kern_buf_len,
-			    drv_buf_iter->bsg_buf_len);
+				     drv_buf_iter->bsg_buf_len);
+			rmc_size = tmplen;
 			memcpy(drv_buf_iter->kern_buf, drv_buf_iter->bsg_buf, tmplen);
+		} else if (is_rmrb && (count == 1)) {
+			drv_buf_iter->kern_buf_len =
+			    mrioc->ioctl_resp_sge.size;
+			drv_buf_iter->kern_buf =
+			    mrioc->ioctl_resp_sge.addr;
+			drv_buf_iter->kern_buf_dma =
+			    mrioc->ioctl_resp_sge.dma_addr;
+			drv_buf_iter->dma_desc = NULL;
+			drv_buf_iter->num_dma_desc = 0;
+			memset(drv_buf_iter->kern_buf, 0,
+			       drv_buf_iter->kern_buf_len);
+			tmplen = min(drv_buf_iter->kern_buf_len,
+				     drv_buf_iter->bsg_buf_len);
+			drv_buf_iter->kern_buf_len = tmplen;
+			memset(drv_buf_iter->bsg_buf, 0,
+			       drv_buf_iter->bsg_buf_len);
+		} else {
+			if (!drv_buf_iter->kern_buf_len)
+				continue;
+			if (mpi3mr_map_data_buffer_dma(mrioc, drv_buf_iter, desc_count)) {
+				rval = -ENOMEM;
+				dprint_bsg_err(mrioc, "%s:%d: mapping data buffers failed\n",
+					       __func__, __LINE__);
+			goto out;
+		}
+			desc_count += drv_buf_iter->num_dma_desc;
 		}
 	}
 
@@ -1219,9 +1530,14 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job, unsigned int *reply
 			goto out;
 		}
 	} else {
-		mpi3mr_bsg_build_sgl(mpi_req, (mpi_msg_size),
-		    drv_bufs, bufcnt, is_rmcb, is_rmrb,
-		    (dout_cnt + din_cnt));
+		if (mpi3mr_bsg_build_sgl(mrioc, mpi_req, mpi_msg_size,
+					 drv_bufs, bufcnt, is_rmcb, is_rmrb,
+					 (dout_cnt + din_cnt))) {
+			dprint_bsg_err(mrioc, "%s: sgl build failed\n", __func__);
+			rval = -EAGAIN;
+			mutex_unlock(&mrioc->bsg_cmds.mutex);
+			goto out;
+		}
 	}
 
 	if (mpi_header->function == MPI3_BSG_FUNCTION_SCSI_TASK_MGMT) {
@@ -1257,7 +1573,7 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job, unsigned int *reply
 		if (mpi_header->function == MPI3_BSG_FUNCTION_MGMT_PASSTHROUGH) {
 			drv_buf_iter = &drv_bufs[0];
 			dprint_dump(drv_buf_iter->kern_buf,
-			    drv_buf_iter->kern_buf_len, "mpi3_mgmt_req");
+			    rmc_size, "mpi3_mgmt_req");
 		}
 	}
 
@@ -1292,10 +1608,9 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job, unsigned int *reply
 			    MPI3_BSG_FUNCTION_MGMT_PASSTHROUGH) {
 				drv_buf_iter = &drv_bufs[0];
 				dprint_dump(drv_buf_iter->kern_buf,
-				    drv_buf_iter->kern_buf_len, "mpi3_mgmt_req");
+				    rmc_size, "mpi3_mgmt_req");
 			}
 		}
-
 		if ((mpi_header->function == MPI3_BSG_FUNCTION_NVME_ENCAPSULATED) ||
 		    (mpi_header->function == MPI3_BSG_FUNCTION_SCSI_IO))
 			mpi3mr_issue_tm(mrioc,
@@ -1366,17 +1681,27 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job, unsigned int *reply
 	for (count = 0; count < bufcnt; count++, drv_buf_iter++) {
 		if (drv_buf_iter->data_dir == DMA_NONE)
 			continue;
-		if (drv_buf_iter->data_dir == DMA_FROM_DEVICE) {
-			tmplen = min(drv_buf_iter->kern_buf_len,
-				     drv_buf_iter->bsg_buf_len);
+		if ((count == 1) && is_rmrb) {
 			memcpy(drv_buf_iter->bsg_buf,
-			       drv_buf_iter->kern_buf, tmplen);
+			    drv_buf_iter->kern_buf,
+			    drv_buf_iter->kern_buf_len);
+		} else if (drv_buf_iter->data_dir == DMA_FROM_DEVICE) {
+			tmplen = 0;
+			for (desc_count = 0;
+			    desc_count < drv_buf_iter->num_dma_desc;
+			    desc_count++) {
+				memcpy(((u8 *)drv_buf_iter->bsg_buf + tmplen),
+				       drv_buf_iter->dma_desc[desc_count].addr,
+				       drv_buf_iter->dma_desc[desc_count].size);
+				tmplen +=
+				    drv_buf_iter->dma_desc[desc_count].size;
 		}
 	}
+	}
 
 out_unlock:
 	if (din_buf) {
-		*reply_payload_rcv_len =
+		job->reply_payload_rcv_len =
 			sg_copy_from_buffer(job->reply_payload.sg_list,
 					    job->reply_payload.sg_cnt,
 					    din_buf, job->reply_payload.payload_len);
@@ -1392,13 +1717,8 @@ out:
 	kfree(mpi_req);
 	if (drv_bufs) {
 		drv_buf_iter = drv_bufs;
-		for (count = 0; count < bufcnt; count++, drv_buf_iter++) {
-			if (drv_buf_iter->kern_buf && drv_buf_iter->kern_buf_dma)
-				dma_free_coherent(&mrioc->pdev->dev,
-				    drv_buf_iter->kern_buf_len,
-				    drv_buf_iter->kern_buf,
-				    drv_buf_iter->kern_buf_dma);
-		}
+		for (count = 0; count < bufcnt; count++, drv_buf_iter++)
+			kfree(drv_buf_iter->dma_desc);
 		kfree(drv_bufs);
 	}
 	kfree(bsg_reply_buf);
@@ -1457,7 +1777,7 @@ static int mpi3mr_bsg_request(struct bsg_job *job)
 		rval = mpi3mr_bsg_process_drv_cmds(job);
 		break;
 	case MPI3MR_MPT_CMD:
-		rval = mpi3mr_bsg_process_mpt_cmds(job, &reply_payload_rcv_len);
+		rval = mpi3mr_bsg_process_mpt_cmds(job);
 		break;
 	default:
 		pr_err("%s: unsupported BSG command(0x%08x)\n",
diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c
index f039f1d98647..d8c57a0a518f 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_fw.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c
@@ -1059,6 +1059,114 @@ enum mpi3mr_iocstate mpi3mr_get_iocstate(struct mpi3mr_ioc *mrioc)
 }
 
 /**
+ * mpi3mr_free_ioctl_dma_memory - free memory for ioctl dma
+ * @mrioc: Adapter instance reference
+ *
+ * Free the DMA memory allocated for IOCTL handling purpose.
+
+ *
+ * Return: None
+ */
+static void mpi3mr_free_ioctl_dma_memory(struct mpi3mr_ioc *mrioc)
+{
+	struct dma_memory_desc *mem_desc;
+	u16 i;
+
+	if (!mrioc->ioctl_dma_pool)
+		return;
+
+	for (i = 0; i < MPI3MR_NUM_IOCTL_SGE; i++) {
+		mem_desc = &mrioc->ioctl_sge[i];
+		if (mem_desc->addr) {
+			dma_pool_free(mrioc->ioctl_dma_pool,
+				      mem_desc->addr,
+				      mem_desc->dma_addr);
+			mem_desc->addr = NULL;
+		}
+	}
+	dma_pool_destroy(mrioc->ioctl_dma_pool);
+	mrioc->ioctl_dma_pool = NULL;
+	mem_desc = &mrioc->ioctl_chain_sge;
+
+	if (mem_desc->addr) {
+		dma_free_coherent(&mrioc->pdev->dev, mem_desc->size,
+				  mem_desc->addr, mem_desc->dma_addr);
+		mem_desc->addr = NULL;
+	}
+	mem_desc = &mrioc->ioctl_resp_sge;
+	if (mem_desc->addr) {
+		dma_free_coherent(&mrioc->pdev->dev, mem_desc->size,
+				  mem_desc->addr, mem_desc->dma_addr);
+		mem_desc->addr = NULL;
+	}
+
+	mrioc->ioctl_sges_allocated = false;
+}
+
+/**
+ * mpi3mr_alloc_ioctl_dma_memory - Alloc memory for ioctl dma
+ * @mrioc: Adapter instance reference
+
+ *
+ * This function allocates dmaable memory required to handle the
+ * application issued MPI3 IOCTL requests.
+ *
+ * Return: None
+ */
+static void mpi3mr_alloc_ioctl_dma_memory(struct mpi3mr_ioc *mrioc)
+
+{
+	struct dma_memory_desc *mem_desc;
+	u16 i;
+
+	mrioc->ioctl_dma_pool = dma_pool_create("ioctl dma pool",
+						&mrioc->pdev->dev,
+						MPI3MR_IOCTL_SGE_SIZE,
+						MPI3MR_PAGE_SIZE_4K, 0);
+
+	if (!mrioc->ioctl_dma_pool) {
+		ioc_err(mrioc, "ioctl_dma_pool: dma_pool_create failed\n");
+		goto out_failed;
+	}
+
+	for (i = 0; i < MPI3MR_NUM_IOCTL_SGE; i++) {
+		mem_desc = &mrioc->ioctl_sge[i];
+		mem_desc->size = MPI3MR_IOCTL_SGE_SIZE;
+		mem_desc->addr = dma_pool_zalloc(mrioc->ioctl_dma_pool,
+						 GFP_KERNEL,
+						 &mem_desc->dma_addr);
+		if (!mem_desc->addr)
+			goto out_failed;
+	}
+
+	mem_desc = &mrioc->ioctl_chain_sge;
+	mem_desc->size = MPI3MR_PAGE_SIZE_4K;
+	mem_desc->addr = dma_alloc_coherent(&mrioc->pdev->dev,
+					    mem_desc->size,
+					    &mem_desc->dma_addr,
+					    GFP_KERNEL);
+	if (!mem_desc->addr)
+		goto out_failed;
+
+	mem_desc = &mrioc->ioctl_resp_sge;
+	mem_desc->size = MPI3MR_PAGE_SIZE_4K;
+	mem_desc->addr = dma_alloc_coherent(&mrioc->pdev->dev,
+					    mem_desc->size,
+					    &mem_desc->dma_addr,
+					    GFP_KERNEL);
+	if (!mem_desc->addr)
+		goto out_failed;
+
+	mrioc->ioctl_sges_allocated = true;
+
+	return;
+out_failed:
+	ioc_warn(mrioc, "cannot allocate DMA memory for the mpt commands\n"
+		 "from the applications, application interface for MPT command is disabled\n");
+	mpi3mr_free_ioctl_dma_memory(mrioc);
+}
+
+/**
  * mpi3mr_clear_reset_history - clear reset history
  * @mrioc: Adapter instance reference
  *
@@ -1892,7 +2000,8 @@ static int mpi3mr_create_op_reply_q(struct mpi3mr_ioc *mrioc, u16 qidx)
 
 	reply_qid = qidx + 1;
 	op_reply_q->num_replies = MPI3MR_OP_REP_Q_QD;
-	if (!mrioc->pdev->revision)
+	if ((mrioc->pdev->device == MPI3_MFGPAGE_DEVID_SAS4116) &&
+		!mrioc->pdev->revision)
 		op_reply_q->num_replies = MPI3MR_OP_REP_Q_QD4K;
 	op_reply_q->ci = 0;
 	op_reply_q->ephase = 1;
@@ -3193,6 +3302,9 @@ static int mpi3mr_issue_iocinit(struct mpi3mr_ioc *mrioc)
 	current_time = ktime_get_real();
 	iocinit_req.time_stamp = cpu_to_le64(ktime_to_ms(current_time));
 
+	iocinit_req.msg_flags |=
+	    MPI3_IOCINIT_MSGFLAGS_SCSIIOSTATUSREPLY_SUPPORTED;
+
 	init_completion(&mrioc->init_cmds.done);
 	retval = mpi3mr_admin_request_post(mrioc, &iocinit_req,
 	    sizeof(iocinit_req), 1);
@@ -3870,6 +3982,9 @@ retry_init:
 		}
 	}
 
+	dprint_init(mrioc, "allocating ioctl dma buffers\n");
+	mpi3mr_alloc_ioctl_dma_memory(mrioc);
+
 	if (!mrioc->init_cmds.reply) {
 		retval = mpi3mr_alloc_reply_sense_bufs(mrioc);
 		if (retval) {
@@ -4289,6 +4404,7 @@ void mpi3mr_free_mem(struct mpi3mr_ioc *mrioc)
 	struct mpi3mr_intr_info *intr_info;
 
 	mpi3mr_free_enclosure_list(mrioc);
+	mpi3mr_free_ioctl_dma_memory(mrioc);
 
 	if (mrioc->sense_buf_pool) {
 		if (mrioc->sense_buf)
diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c
index 040031eb0c12..1bffd629c124 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_os.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_os.c
@@ -1047,8 +1047,9 @@ void mpi3mr_rfresh_tgtdevs(struct mpi3mr_ioc *mrioc)
 	list_for_each_entry_safe(tgtdev, tgtdev_next, &mrioc->tgtdev_list,
 	    list) {
 		if ((tgtdev->dev_handle == MPI3MR_INVALID_DEV_HANDLE) &&
-		    tgtdev->host_exposed && tgtdev->starget &&
-		    tgtdev->starget->hostdata) {
+		     tgtdev->is_hidden &&
+		     tgtdev->host_exposed && tgtdev->starget &&
+		     tgtdev->starget->hostdata) {
 			tgt_priv = tgtdev->starget->hostdata;
 			tgt_priv->dev_removed = 1;
 			atomic_set(&tgt_priv->block_io, 0);
@@ -1064,14 +1065,24 @@ void mpi3mr_rfresh_tgtdevs(struct mpi3mr_ioc *mrioc)
 				mpi3mr_remove_tgtdev_from_host(mrioc, tgtdev);
 			mpi3mr_tgtdev_del_from_list(mrioc, tgtdev, true);
 			mpi3mr_tgtdev_put(tgtdev);
+		} else if (tgtdev->is_hidden & tgtdev->host_exposed) {
+			dprint_reset(mrioc, "hiding target device with perst_id(%d)\n",
+				     tgtdev->perst_id);
+			mpi3mr_remove_tgtdev_from_host(mrioc, tgtdev);
 		}
 	}
 
 	tgtdev = NULL;
 	list_for_each_entry(tgtdev, &mrioc->tgtdev_list, list) {
 		if ((tgtdev->dev_handle != MPI3MR_INVALID_DEV_HANDLE) &&
-		    !tgtdev->is_hidden && !tgtdev->host_exposed)
-			mpi3mr_report_tgtdev_to_host(mrioc, tgtdev->perst_id);
+		    !tgtdev->is_hidden) {
+			if (!tgtdev->host_exposed)
+				mpi3mr_report_tgtdev_to_host(mrioc,
+							     tgtdev->perst_id);
+			else if (tgtdev->starget)
+				starget_for_each_device(tgtdev->starget,
+							(void *)tgtdev, mpi3mr_update_sdev);
+	}
 	}
 }
 
@@ -3194,6 +3205,7 @@ void mpi3mr_process_op_reply_desc(struct mpi3mr_ioc *mrioc,
 			tg = stgt_priv_data->throttle_group;
 			throttle_enabled_dev =
 			    stgt_priv_data->io_throttle_enabled;
+			dev_handle = stgt_priv_data->dev_handle;
 		}
 	}
 	if (unlikely((data_len_blks >= mrioc->io_throttle_data_length) &&
@@ -5101,7 +5113,10 @@ mpi3mr_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		mpi3mr_init_drv_cmd(&mrioc->evtack_cmds[i],
 				    MPI3MR_HOSTTAG_EVTACKCMD_MIN + i);
 
-	if (pdev->revision)
+	if ((pdev->device == MPI3_MFGPAGE_DEVID_SAS4116) &&
+		!pdev->revision)
+		mrioc->enable_segqueue = false;
+	else
 		mrioc->enable_segqueue = true;
 
 	init_waitqueue_head(&mrioc->reset_waitq);
@@ -5430,6 +5445,14 @@ static const struct pci_device_id mpi3mr_pci_id_table[] = {
 		PCI_DEVICE_SUB(MPI3_MFGPAGE_VENDORID_BROADCOM,
 		    MPI3_MFGPAGE_DEVID_SAS4116, PCI_ANY_ID, PCI_ANY_ID)
 	},
+	{
+		PCI_DEVICE_SUB(MPI3_MFGPAGE_VENDORID_BROADCOM,
+		    MPI3_MFGPAGE_DEVID_SAS5116_MPI, PCI_ANY_ID, PCI_ANY_ID)
+	},
+	{
+		PCI_DEVICE_SUB(MPI3_MFGPAGE_VENDORID_BROADCOM,
+		    MPI3_MFGPAGE_DEVID_SAS5116_MPI_MGMT, PCI_ANY_ID, PCI_ANY_ID)
+	},
 	{ 0 }
 };
 MODULE_DEVICE_TABLE(pci, mpi3mr_pci_id_table);
diff --git a/drivers/scsi/mpi3mr/mpi3mr_transport.c b/drivers/scsi/mpi3mr/mpi3mr_transport.c
index 82b55e955730..c0c8ab586957 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_transport.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_transport.c
@@ -1587,7 +1587,7 @@ static void mpi3mr_sas_port_remove(struct mpi3mr_ioc *mrioc, u64 sas_address,
  */
 struct host_port {
 	u64	sas_address;
-	u32	phy_mask;
+	u64	phy_mask;
 	u16	handle;
 	u8	iounit_port_id;
 	u8	used;
@@ -1611,7 +1611,7 @@ mpi3mr_update_mr_sas_port(struct mpi3mr_ioc *mrioc, struct host_port *h_port,
 	struct mpi3mr_sas_port *mr_sas_port)
 {
 	struct mpi3mr_sas_phy *mr_sas_phy;
-	u32 phy_mask_xor;
+	u64 phy_mask_xor;
 	u64 phys_to_be_added, phys_to_be_removed;
 	int i;
 
@@ -1619,7 +1619,7 @@ mpi3mr_update_mr_sas_port(struct mpi3mr_ioc *mrioc, struct host_port *h_port,
 	mr_sas_port->marked_responding = 1;
 
 	dev_info(&mr_sas_port->port->dev,
-	    "sas_address(0x%016llx), old: port_id %d phy_mask 0x%x, new: port_id %d phy_mask:0x%x\n",
+	    "sas_address(0x%016llx), old: port_id %d phy_mask 0x%llx, new: port_id %d phy_mask:0x%llx\n",
 	    mr_sas_port->remote_identify.sas_address,
 	    mr_sas_port->hba_port->port_id, mr_sas_port->phy_mask,
 	    h_port->iounit_port_id, h_port->phy_mask);
@@ -1637,7 +1637,7 @@ mpi3mr_update_mr_sas_port(struct mpi3mr_ioc *mrioc, struct host_port *h_port,
 	 * if these phys are previously registered with another port
 	 * then delete these phys from that port first.
 	 */
-	for_each_set_bit(i, (ulong *) &phys_to_be_added, BITS_PER_TYPE(u32)) {
+	for_each_set_bit(i, (ulong *) &phys_to_be_added, BITS_PER_TYPE(u64)) {
 		mr_sas_phy = &mrioc->sas_hba.phy[i];
 		if (mr_sas_phy->phy_belongs_to_port)
 			mpi3mr_del_phy_from_an_existing_port(mrioc,
@@ -1649,7 +1649,7 @@ mpi3mr_update_mr_sas_port(struct mpi3mr_ioc *mrioc, struct host_port *h_port,
 	}
 
 	/* Delete the phys which are not part of current mr_sas_port's port. */
-	for_each_set_bit(i, (ulong *) &phys_to_be_removed, BITS_PER_TYPE(u32)) {
+	for_each_set_bit(i, (ulong *) &phys_to_be_removed, BITS_PER_TYPE(u64)) {
 		mr_sas_phy = &mrioc->sas_hba.phy[i];
 		if (mr_sas_phy->phy_belongs_to_port)
 			mpi3mr_del_phy_from_an_existing_port(mrioc,
@@ -1671,7 +1671,7 @@ mpi3mr_update_mr_sas_port(struct mpi3mr_ioc *mrioc, struct host_port *h_port,
 void
 mpi3mr_refresh_sas_ports(struct mpi3mr_ioc *mrioc)
 {
-	struct host_port h_port[32];
+	struct host_port h_port[64];
 	int i, j, found, host_port_count = 0, port_idx;
 	u16 sz, attached_handle, ioc_status;
 	struct mpi3_sas_io_unit_page0 *sas_io_unit_pg0 = NULL;
@@ -1742,7 +1742,7 @@ mpi3mr_refresh_sas_ports(struct mpi3mr_ioc *mrioc)
 		list_for_each_entry(mr_sas_port, &mrioc->sas_hba.sas_port_list,
 		    port_list) {
 			ioc_info(mrioc,
-			    "port_id:%d, sas_address:(0x%016llx), phy_mask:(0x%x), lowest phy id:%d\n",
+			    "port_id:%d, sas_address:(0x%016llx), phy_mask:(0x%llx), lowest phy id:%d\n",
 			    mr_sas_port->hba_port->port_id,
 			    mr_sas_port->remote_identify.sas_address,
 			    mr_sas_port->phy_mask, mr_sas_port->lowest_phy);
@@ -1751,7 +1751,7 @@ mpi3mr_refresh_sas_ports(struct mpi3mr_ioc *mrioc)
 		ioc_info(mrioc, "Host port details after reset\n");
 		for (i = 0; i < host_port_count; i++) {
 			ioc_info(mrioc,
-			    "port_id:%d, sas_address:(0x%016llx), phy_mask:(0x%x), lowest phy id:%d\n",
+			    "port_id:%d, sas_address:(0x%016llx), phy_mask:(0x%llx), lowest phy id:%d\n",
 			    h_port[i].iounit_port_id, h_port[i].sas_address,
 			    h_port[i].phy_mask, h_port[i].lowest_phy);
 		}
diff --git a/drivers/scsi/mpt3sas/mpi/mpi2_cnfg.h b/drivers/scsi/mpt3sas/mpi/mpi2_cnfg.h
index 4d0be5ab98c1..587f7d248219 100644
--- a/drivers/scsi/mpt3sas/mpi/mpi2_cnfg.h
+++ b/drivers/scsi/mpt3sas/mpi/mpi2_cnfg.h
@@ -643,18 +643,14 @@ typedef struct _MPI2_CHIP_REVISION_ID {
 /*Manufacturing Page 2 */
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check Header.PageLength at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check Header.PageLength at
+ *runtime before using HwSettings[].
  */
-#ifndef MPI2_MAN_PAGE_2_HW_SETTINGS_WORDS
-#define MPI2_MAN_PAGE_2_HW_SETTINGS_WORDS   (1)
-#endif
 
 typedef struct _MPI2_CONFIG_PAGE_MAN_2 {
 	MPI2_CONFIG_PAGE_HEADER Header;                     /*0x00 */
 	MPI2_CHIP_REVISION_ID   ChipId;                     /*0x04 */
-	U32
-		HwSettings[MPI2_MAN_PAGE_2_HW_SETTINGS_WORDS];/*0x08 */
+	U32                     HwSettings[];               /*0x08 */
 } MPI2_CONFIG_PAGE_MAN_2,
 	*PTR_MPI2_CONFIG_PAGE_MAN_2,
 	Mpi2ManufacturingPage2_t,
@@ -666,18 +662,14 @@ typedef struct _MPI2_CONFIG_PAGE_MAN_2 {
 /*Manufacturing Page 3 */
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check Header.PageLength at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check Header.PageLength at
+ *runtime before using Info[].
  */
-#ifndef MPI2_MAN_PAGE_3_INFO_WORDS
-#define MPI2_MAN_PAGE_3_INFO_WORDS          (1)
-#endif
 
 typedef struct _MPI2_CONFIG_PAGE_MAN_3 {
 	MPI2_CONFIG_PAGE_HEADER             Header;         /*0x00 */
 	MPI2_CHIP_REVISION_ID               ChipId;         /*0x04 */
-	U32
-		Info[MPI2_MAN_PAGE_3_INFO_WORDS];/*0x08 */
+	U32                                 Info[];         /*0x08 */
 } MPI2_CONFIG_PAGE_MAN_3,
 	*PTR_MPI2_CONFIG_PAGE_MAN_3,
 	Mpi2ManufacturingPage3_t,
@@ -765,12 +757,9 @@ typedef struct _MPI2_CONFIG_PAGE_MAN_4 {
 /*Manufacturing Page 5 */
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for NumPhys at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check the value returned
+ *for NumPhys at runtime before using Phy[].
  */
-#ifndef MPI2_MAN_PAGE_5_PHY_ENTRIES
-#define MPI2_MAN_PAGE_5_PHY_ENTRIES         (1)
-#endif
 
 typedef struct _MPI2_MANUFACTURING5_ENTRY {
 	U64                                 WWID;           /*0x00 */
@@ -787,8 +776,7 @@ typedef struct _MPI2_CONFIG_PAGE_MAN_5 {
 	U16                                 Reserved2;      /*0x06 */
 	U32                                 Reserved3;      /*0x08 */
 	U32                                 Reserved4;      /*0x0C */
-	MPI2_MANUFACTURING5_ENTRY
-		Phy[MPI2_MAN_PAGE_5_PHY_ENTRIES];/*0x08 */
+	MPI2_MANUFACTURING5_ENTRY           Phy[];          /*0x10 */
 } MPI2_CONFIG_PAGE_MAN_5,
 	*PTR_MPI2_CONFIG_PAGE_MAN_5,
 	Mpi2ManufacturingPage5_t,
@@ -864,12 +852,9 @@ typedef struct _MPI2_MANPAGE7_CONNECTOR_INFO {
 #define MPI2_MANPAGE7_SLOT_UNKNOWN                      (0xFFFF)
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for NumPhys at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check the value returned
+ *for NumPhys at runtime before using ConnectorInfo[].
  */
-#ifndef MPI2_MANPAGE7_CONNECTOR_INFO_MAX
-#define MPI2_MANPAGE7_CONNECTOR_INFO_MAX  (1)
-#endif
 
 typedef struct _MPI2_CONFIG_PAGE_MAN_7 {
 	MPI2_CONFIG_PAGE_HEADER         Header;             /*0x00 */
@@ -880,8 +865,7 @@ typedef struct _MPI2_CONFIG_PAGE_MAN_7 {
 	U8                              NumPhys;            /*0x20 */
 	U8                              Reserved3;          /*0x21 */
 	U16                             Reserved4;          /*0x22 */
-	MPI2_MANPAGE7_CONNECTOR_INFO
-	ConnectorInfo[MPI2_MANPAGE7_CONNECTOR_INFO_MAX]; /*0x24 */
+	MPI2_MANPAGE7_CONNECTOR_INFO    ConnectorInfo[];    /*0x24 */
 } MPI2_CONFIG_PAGE_MAN_7,
 	*PTR_MPI2_CONFIG_PAGE_MAN_7,
 	Mpi2ManufacturingPage7_t,
@@ -990,7 +974,7 @@ typedef struct _MPI2_CONFIG_PAGE_IO_UNIT_1 {
 
 /*
  *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for GPIOCount at runtime.
+ *36 and check the value returned for GPIOCount at runtime.
  */
 #ifndef MPI2_IO_UNIT_PAGE_3_GPIO_VAL_MAX
 #define MPI2_IO_UNIT_PAGE_3_GPIO_VAL_MAX    (36)
@@ -1019,12 +1003,9 @@ typedef struct _MPI2_CONFIG_PAGE_IO_UNIT_3 {
 /*IO Unit Page 5 */
 
 /*
- *Upper layer code (drivers, utilities, etc.) should leave this define set to
- *one and check the value returned for NumDmaEngines at runtime.
+ *Upper layer code (drivers, utilities, etc.) should check the value returned
+ *for NumDmaEngines at runtime before using DmaEngineCapabilities[].
  */
-#ifndef MPI2_IOUNITPAGE5_DMAENGINE_ENTRIES
-#define MPI2_IOUNITPAGE5_DMAENGINE_ENTRIES      (1)
-#endif
 
 typedef struct _MPI2_CONFIG_PAGE_IO_UNIT_5 {
 	MPI2_CONFIG_PAGE_HEADER Header;                     /*0x00 */
@@ -1042,7 +1023,7 @@ typedef struct _MPI2_CONFIG_PAGE_IO_UNIT_5 {
 	U32                     Reserved2;                  /*0x24 */
 	U32                     Reserved3;                  /*0x28 */
 	U32
-	DmaEngineCapabilities[MPI2_IOUNITPAGE5_DMAENGINE_ENTRIES]; /*0x2C */
+		DmaEngineCapabilities[];                    /*0x2C */
 } MPI2_CONFIG_PAGE_IO_UNIT_5,
 	*PTR_MPI2_CONFIG_PAGE_IO_UNIT_5,
 	Mpi2IOUnitPage5_t, *pMpi2IOUnitPage5_t;
@@ -1219,12 +1200,9 @@ typedef struct _MPI2_IOUNIT8_SENSOR {
 #define MPI2_IOUNIT8_SENSOR_FLAGS_T0_ENABLE         (0x0001)
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for NumSensors at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check the value returned
+ *for NumSensors at runtime before using Sensor[].
  */
-#ifndef MPI2_IOUNITPAGE8_SENSOR_ENTRIES
-#define MPI2_IOUNITPAGE8_SENSOR_ENTRIES     (1)
-#endif
 
 typedef struct _MPI2_CONFIG_PAGE_IO_UNIT_8 {
 	MPI2_CONFIG_PAGE_HEADER Header;                 /*0x00 */
@@ -1233,8 +1211,7 @@ typedef struct _MPI2_CONFIG_PAGE_IO_UNIT_8 {
 	U8                      NumSensors;             /*0x0C */
 	U8                      PollingInterval;        /*0x0D */
 	U16                     Reserved3;              /*0x0E */
-	MPI2_IOUNIT8_SENSOR
-		Sensor[MPI2_IOUNITPAGE8_SENSOR_ENTRIES];/*0x10 */
+	MPI2_IOUNIT8_SENSOR     Sensor[];               /*0x10 */
 } MPI2_CONFIG_PAGE_IO_UNIT_8,
 	*PTR_MPI2_CONFIG_PAGE_IO_UNIT_8,
 	Mpi2IOUnitPage8_t, *pMpi2IOUnitPage8_t;
@@ -1259,12 +1236,9 @@ typedef struct _MPI2_IOUNIT9_SENSOR {
 #define MPI2_IOUNIT9_SENSOR_FLAGS_TEMP_VALID        (0x01)
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for NumSensors at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check the value returned
+ *for NumSensors at runtime before using Sensor[].
  */
-#ifndef MPI2_IOUNITPAGE9_SENSOR_ENTRIES
-#define MPI2_IOUNITPAGE9_SENSOR_ENTRIES     (1)
-#endif
 
 typedef struct _MPI2_CONFIG_PAGE_IO_UNIT_9 {
 	MPI2_CONFIG_PAGE_HEADER Header;                 /*0x00 */
@@ -1273,8 +1247,7 @@ typedef struct _MPI2_CONFIG_PAGE_IO_UNIT_9 {
 	U8                      NumSensors;             /*0x0C */
 	U8                      Reserved4;              /*0x0D */
 	U16                     Reserved3;              /*0x0E */
-	MPI2_IOUNIT9_SENSOR
-		Sensor[MPI2_IOUNITPAGE9_SENSOR_ENTRIES];/*0x10 */
+	MPI2_IOUNIT9_SENSOR     Sensor[];               /*0x10 */
 } MPI2_CONFIG_PAGE_IO_UNIT_9,
 	*PTR_MPI2_CONFIG_PAGE_IO_UNIT_9,
 	Mpi2IOUnitPage9_t, *pMpi2IOUnitPage9_t;
@@ -1294,12 +1267,9 @@ typedef struct _MPI2_IOUNIT10_FUNCTION {
 	*pMpi2IOUnit10Function_t;
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for NumFunctions at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check the value returned
+ *for NumFunctions at runtime before using Function[].
  */
-#ifndef MPI2_IOUNITPAGE10_FUNCTION_ENTRIES
-#define MPI2_IOUNITPAGE10_FUNCTION_ENTRIES      (1)
-#endif
 
 typedef struct _MPI2_CONFIG_PAGE_IO_UNIT_10 {
 	MPI2_CONFIG_PAGE_HEADER Header;                      /*0x00 */
@@ -1308,8 +1278,7 @@ typedef struct _MPI2_CONFIG_PAGE_IO_UNIT_10 {
 	U16                     Reserved2;                   /*0x06 */
 	U32                     Reserved3;                   /*0x08 */
 	U32                     Reserved4;                   /*0x0C */
-	MPI2_IOUNIT10_FUNCTION
-		Function[MPI2_IOUNITPAGE10_FUNCTION_ENTRIES];/*0x10 */
+	MPI2_IOUNIT10_FUNCTION  Function[];                  /*0x10 */
 } MPI2_CONFIG_PAGE_IO_UNIT_10,
 	*PTR_MPI2_CONFIG_PAGE_IO_UNIT_10,
 	Mpi2IOUnitPage10_t, *pMpi2IOUnitPage10_t;
@@ -1764,12 +1733,9 @@ typedef struct _MPI2_CONFIG_PAGE_BIOS_3 {
 /*BIOS Page 4 */
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for NumPhys at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check the value returned
+ *for NumPhys at runtime before using Phy[].
  */
-#ifndef MPI2_BIOS_PAGE_4_PHY_ENTRIES
-#define MPI2_BIOS_PAGE_4_PHY_ENTRIES        (1)
-#endif
 
 typedef struct _MPI2_BIOS4_ENTRY {
 	U64                     ReassignmentWWID;       /*0x00 */
@@ -1782,8 +1748,7 @@ typedef struct _MPI2_CONFIG_PAGE_BIOS_4 {
 	U8                      NumPhys;            /*0x04 */
 	U8                      Reserved1;          /*0x05 */
 	U16                     Reserved2;          /*0x06 */
-	MPI2_BIOS4_ENTRY
-		Phy[MPI2_BIOS_PAGE_4_PHY_ENTRIES];  /*0x08 */
+	MPI2_BIOS4_ENTRY        Phy[];              /*0x08 */
 } MPI2_CONFIG_PAGE_BIOS_4, *PTR_MPI2_CONFIG_PAGE_BIOS_4,
 	Mpi2BiosPage4_t, *pMpi2BiosPage4_t;
 
@@ -1836,12 +1801,9 @@ typedef struct _MPI2_RAIDVOL0_SETTINGS {
 #define MPI2_RAIDVOL0_SETTING_ENABLE_WRITE_CACHING      (0x0002)
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for NumPhysDisks at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check the value returned
+ *for NumPhysDisks at runtime before using PhysDisk[].
  */
-#ifndef MPI2_RAID_VOL_PAGE_0_PHYSDISK_MAX
-#define MPI2_RAID_VOL_PAGE_0_PHYSDISK_MAX       (1)
-#endif
 
 typedef struct _MPI2_CONFIG_PAGE_RAID_VOL_0 {
 	MPI2_CONFIG_PAGE_HEADER Header;            /*0x00 */
@@ -1861,8 +1823,7 @@ typedef struct _MPI2_CONFIG_PAGE_RAID_VOL_0 {
 	U8                      Reserved2;         /*0x25 */
 	U8                      Reserved3;         /*0x26 */
 	U8                      InactiveStatus;    /*0x27 */
-	MPI2_RAIDVOL0_PHYS_DISK
-	PhysDisk[MPI2_RAID_VOL_PAGE_0_PHYSDISK_MAX]; /*0x28 */
+	MPI2_RAIDVOL0_PHYS_DISK PhysDisk[];        /*0x28 */
 } MPI2_CONFIG_PAGE_RAID_VOL_0,
 	*PTR_MPI2_CONFIG_PAGE_RAID_VOL_0,
 	Mpi2RaidVolPage0_t, *pMpi2RaidVolPage0_t;
@@ -2045,12 +2006,9 @@ typedef struct _MPI2_CONFIG_PAGE_RD_PDISK_0 {
 /*RAID Physical Disk Page 1 */
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for NumPhysDiskPaths at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check the value returned
+ *for NumPhysDiskPaths at runtime before using PhysicalDiskPath[].
  */
-#ifndef MPI2_RAID_PHYS_DISK1_PATH_MAX
-#define MPI2_RAID_PHYS_DISK1_PATH_MAX   (1)
-#endif
 
 typedef struct _MPI2_RAIDPHYSDISK1_PATH {
 	U16             DevHandle;          /*0x00 */
@@ -2075,8 +2033,7 @@ typedef struct _MPI2_CONFIG_PAGE_RD_PDISK_1 {
 	U8                              PhysDiskNum;        /*0x05 */
 	U16                             Reserved1;          /*0x06 */
 	U32                             Reserved2;          /*0x08 */
-	MPI2_RAIDPHYSDISK1_PATH
-		PhysicalDiskPath[MPI2_RAID_PHYS_DISK1_PATH_MAX];/*0x0C */
+	MPI2_RAIDPHYSDISK1_PATH         PhysicalDiskPath[]; /*0x0C */
 } MPI2_CONFIG_PAGE_RD_PDISK_1,
 	*PTR_MPI2_CONFIG_PAGE_RD_PDISK_1,
 	Mpi2RaidPhysDiskPage1_t,
@@ -2221,12 +2178,9 @@ typedef struct _MPI2_SAS_IO_UNIT0_PHY_DATA {
 	*pMpi2SasIOUnit0PhyData_t;
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for NumPhys at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check the value returned
+ *for NumPhys at runtime before using PhyData[].
  */
-#ifndef MPI2_SAS_IOUNIT0_PHY_MAX
-#define MPI2_SAS_IOUNIT0_PHY_MAX        (1)
-#endif
 
 typedef struct _MPI2_CONFIG_PAGE_SASIOUNIT_0 {
 	MPI2_CONFIG_EXTENDED_PAGE_HEADER    Header;   /*0x00 */
@@ -2234,8 +2188,7 @@ typedef struct _MPI2_CONFIG_PAGE_SASIOUNIT_0 {
 	U8                                  NumPhys;  /*0x0C */
 	U8                                  Reserved2;/*0x0D */
 	U16                                 Reserved3;/*0x0E */
-	MPI2_SAS_IO_UNIT0_PHY_DATA
-		PhyData[MPI2_SAS_IOUNIT0_PHY_MAX];    /*0x10 */
+	MPI2_SAS_IO_UNIT0_PHY_DATA          PhyData[];/*0x10 */
 } MPI2_CONFIG_PAGE_SASIOUNIT_0,
 	*PTR_MPI2_CONFIG_PAGE_SASIOUNIT_0,
 	Mpi2SasIOUnitPage0_t, *pMpi2SasIOUnitPage0_t;
@@ -2296,12 +2249,9 @@ typedef struct _MPI2_SAS_IO_UNIT1_PHY_DATA {
 	*pMpi2SasIOUnit1PhyData_t;
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for NumPhys at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check the value returned
+ *for NumPhys at runtime before using PhyData[].
  */
-#ifndef MPI2_SAS_IOUNIT1_PHY_MAX
-#define MPI2_SAS_IOUNIT1_PHY_MAX        (1)
-#endif
 
 typedef struct _MPI2_CONFIG_PAGE_SASIOUNIT_1 {
 	MPI2_CONFIG_EXTENDED_PAGE_HEADER    Header; /*0x00 */
@@ -2322,7 +2272,7 @@ typedef struct _MPI2_CONFIG_PAGE_SASIOUNIT_1 {
 	U8
 		IODeviceMissingDelay;               /*0x13 */
 	MPI2_SAS_IO_UNIT1_PHY_DATA
-		PhyData[MPI2_SAS_IOUNIT1_PHY_MAX];  /*0x14 */
+		PhyData[];                          /*0x14 */
 } MPI2_CONFIG_PAGE_SASIOUNIT_1,
 	*PTR_MPI2_CONFIG_PAGE_SASIOUNIT_1,
 	Mpi2SasIOUnitPage1_t, *pMpi2SasIOUnitPage1_t;
@@ -2502,12 +2452,9 @@ typedef struct _MPI2_SAS_IO_UNIT5_PHY_PM_SETTINGS {
 #define MPI2_SASIOUNIT5_ITE_ONE_MICROSECOND             (0)
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for NumPhys at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check the value returned
+ *for NumPhys at runtime before using SASPhyPowerManagementSettings[].
  */
-#ifndef MPI2_SAS_IOUNIT5_PHY_MAX
-#define MPI2_SAS_IOUNIT5_PHY_MAX        (1)
-#endif
 
 typedef struct _MPI2_CONFIG_PAGE_SASIOUNIT_5 {
 	MPI2_CONFIG_EXTENDED_PAGE_HEADER    Header;   /*0x00 */
@@ -2516,7 +2463,7 @@ typedef struct _MPI2_CONFIG_PAGE_SASIOUNIT_5 {
 	U16                                 Reserved2;/*0x0A */
 	U32                                 Reserved3;/*0x0C */
 	MPI2_SAS_IO_UNIT5_PHY_PM_SETTINGS
-	SASPhyPowerManagementSettings[MPI2_SAS_IOUNIT5_PHY_MAX];/*0x10 */
+		SASPhyPowerManagementSettings[];      /*0x10 */
 } MPI2_CONFIG_PAGE_SASIOUNIT_5,
 	*PTR_MPI2_CONFIG_PAGE_SASIOUNIT_5,
 	Mpi2SasIOUnitPage5_t, *pMpi2SasIOUnitPage5_t;
@@ -2554,12 +2501,9 @@ typedef struct _MPI2_SAS_IO_UNIT6_PORT_WIDTH_MOD_GROUP_STATUS {
 #define MPI2_SASIOUNIT6_MODULATION_100_PERCENT                  (0x03)
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for NumGroups at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check the value returned
+ *for NumGroups at runtime before using PortWidthModulationGroupStatus[].
  */
-#ifndef MPI2_SAS_IOUNIT6_GROUP_MAX
-#define MPI2_SAS_IOUNIT6_GROUP_MAX      (1)
-#endif
 
 typedef struct _MPI2_CONFIG_PAGE_SASIOUNIT_6 {
 	MPI2_CONFIG_EXTENDED_PAGE_HEADER    Header;                 /*0x00 */
@@ -2569,7 +2513,7 @@ typedef struct _MPI2_CONFIG_PAGE_SASIOUNIT_6 {
 	U8                                  Reserved3;              /*0x11 */
 	U16                                 Reserved4;              /*0x12 */
 	MPI2_SAS_IO_UNIT6_PORT_WIDTH_MOD_GROUP_STATUS
-	PortWidthModulationGroupStatus[MPI2_SAS_IOUNIT6_GROUP_MAX]; /*0x14 */
+		PortWidthModulationGroupStatus[];                   /*0x14 */
 } MPI2_CONFIG_PAGE_SASIOUNIT_6,
 	*PTR_MPI2_CONFIG_PAGE_SASIOUNIT_6,
 	Mpi2SasIOUnitPage6_t, *pMpi2SasIOUnitPage6_t;
@@ -2597,12 +2541,9 @@ typedef struct _MPI2_SAS_IO_UNIT7_PORT_WIDTH_MOD_GROUP_SETTINGS {
 
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for NumGroups at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check the value returned
+ *for NumGroups at runtime before using PortWidthModulationGroupSettings[].
  */
-#ifndef MPI2_SAS_IOUNIT7_GROUP_MAX
-#define MPI2_SAS_IOUNIT7_GROUP_MAX      (1)
-#endif
 
 typedef struct _MPI2_CONFIG_PAGE_SASIOUNIT_7 {
 	MPI2_CONFIG_EXTENDED_PAGE_HEADER Header;             /*0x00 */
@@ -2615,7 +2556,7 @@ typedef struct _MPI2_CONFIG_PAGE_SASIOUNIT_7 {
 	U8                               Reserved4;          /*0x15 */
 	U16                              Reserved5;          /*0x16 */
 	MPI2_SAS_IO_UNIT7_PORT_WIDTH_MOD_GROUP_SETTINGS
-	PortWidthModulationGroupSettings[MPI2_SAS_IOUNIT7_GROUP_MAX];/*0x18 */
+		PortWidthModulationGroupSettings[];          /*0x18 */
 } MPI2_CONFIG_PAGE_SASIOUNIT_7,
 	*PTR_MPI2_CONFIG_PAGE_SASIOUNIT_7,
 	Mpi2SasIOUnitPage7_t, *pMpi2SasIOUnitPage7_t;
@@ -3086,12 +3027,9 @@ typedef struct _MPI2_SASPHY2_PHY_EVENT {
 
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for NumPhyEvents at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check the value returned
+ *for NumPhyEvents at runtime before using PhyEvent[].
  */
-#ifndef MPI2_SASPHY2_PHY_EVENT_MAX
-#define MPI2_SASPHY2_PHY_EVENT_MAX      (1)
-#endif
 
 typedef struct _MPI2_CONFIG_PAGE_SAS_PHY_2 {
 	MPI2_CONFIG_EXTENDED_PAGE_HEADER
@@ -3105,7 +3043,7 @@ typedef struct _MPI2_CONFIG_PAGE_SAS_PHY_2 {
 	U16
 		Reserved3;                  /*0x0E */
 	MPI2_SASPHY2_PHY_EVENT
-		PhyEvent[MPI2_SASPHY2_PHY_EVENT_MAX]; /*0x10 */
+		PhyEvent[];                 /*0x10 */
 } MPI2_CONFIG_PAGE_SAS_PHY_2,
 	*PTR_MPI2_CONFIG_PAGE_SAS_PHY_2,
 	Mpi2SasPhyPage2_t,
@@ -3200,12 +3138,9 @@ typedef struct _MPI2_SASPHY3_PHY_EVENT_CONFIG {
 #define MPI2_SASPHY3_TFLAGS_EVENT_NOTIFY                    (0x0001)
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for NumPhyEvents at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check the value returned
+ *for NumPhyEvents at runtime before using PhyEventConfig[].
  */
-#ifndef MPI2_SASPHY3_PHY_EVENT_MAX
-#define MPI2_SASPHY3_PHY_EVENT_MAX      (1)
-#endif
 
 typedef struct _MPI2_CONFIG_PAGE_SAS_PHY_3 {
 	MPI2_CONFIG_EXTENDED_PAGE_HEADER
@@ -3219,7 +3154,7 @@ typedef struct _MPI2_CONFIG_PAGE_SAS_PHY_3 {
 	U16
 		Reserved3;                  /*0x0E */
 	MPI2_SASPHY3_PHY_EVENT_CONFIG
-		PhyEventConfig[MPI2_SASPHY3_PHY_EVENT_MAX]; /*0x10 */
+		PhyEventConfig[];           /*0x10 */
 } MPI2_CONFIG_PAGE_SAS_PHY_3,
 	*PTR_MPI2_CONFIG_PAGE_SAS_PHY_3,
 	Mpi2SasPhyPage3_t, *pMpi2SasPhyPage3_t;
@@ -3358,12 +3293,9 @@ typedef struct _MPI2_CONFIG_PAGE_SAS_ENCLOSURE_0 {
 /*Log Page 0 */
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for NumLogEntries at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check the value returned
+ *for NumLogEntries at runtime before using LogEntry[].
  */
-#ifndef MPI2_LOG_0_NUM_LOG_ENTRIES
-#define MPI2_LOG_0_NUM_LOG_ENTRIES          (1)
-#endif
 
 #define MPI2_LOG_0_LOG_DATA_LENGTH          (0x1C)
 
@@ -3393,8 +3325,7 @@ typedef struct _MPI2_CONFIG_PAGE_LOG_0 {
 	U32                                 Reserved2;    /*0x0C */
 	U16                                 NumLogEntries;/*0x10 */
 	U16                                 Reserved3;    /*0x12 */
-	MPI2_LOG_0_ENTRY
-		LogEntry[MPI2_LOG_0_NUM_LOG_ENTRIES]; /*0x14 */
+	MPI2_LOG_0_ENTRY                    LogEntry[];   /*0x14 */
 } MPI2_CONFIG_PAGE_LOG_0, *PTR_MPI2_CONFIG_PAGE_LOG_0,
 	Mpi2LogPage0_t, *pMpi2LogPage0_t;
 
@@ -3408,12 +3339,9 @@ typedef struct _MPI2_CONFIG_PAGE_LOG_0 {
 /*RAID Page 0 */
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for NumElements at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check the value returned
+ *for NumElements at runtime before using ConfigElement[].
  */
-#ifndef MPI2_RAIDCONFIG0_MAX_ELEMENTS
-#define MPI2_RAIDCONFIG0_MAX_ELEMENTS       (1)
-#endif
 
 typedef struct _MPI2_RAIDCONFIG0_CONFIG_ELEMENT {
 	U16                     ElementFlags;             /*0x00 */
@@ -3446,8 +3374,7 @@ typedef struct _MPI2_CONFIG_PAGE_RAID_CONFIGURATION_0 {
 	U8                                  NumElements;    /*0x2C */
 	U8                                  Reserved2;      /*0x2D */
 	U16                                 Reserved3;      /*0x2E */
-	MPI2_RAIDCONFIG0_CONFIG_ELEMENT
-		ConfigElement[MPI2_RAIDCONFIG0_MAX_ELEMENTS]; /*0x30 */
+	MPI2_RAIDCONFIG0_CONFIG_ELEMENT     ConfigElement[];/*0x30 */
 } MPI2_CONFIG_PAGE_RAID_CONFIGURATION_0,
 	*PTR_MPI2_CONFIG_PAGE_RAID_CONFIGURATION_0,
 	Mpi2RaidConfigurationPage0_t,
@@ -3687,12 +3614,9 @@ typedef struct _MPI26_PCIE_IO_UNIT0_PHY_DATA {
 	Mpi26PCIeIOUnit0PhyData_t, *pMpi26PCIeIOUnit0PhyData_t;
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for NumPhys at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check the value returned
+ *for NumPhys at runtime before using PhyData[].
  */
-#ifndef MPI26_PCIE_IOUNIT0_PHY_MAX
-#define MPI26_PCIE_IOUNIT0_PHY_MAX      (1)
-#endif
 
 typedef struct _MPI26_CONFIG_PAGE_PIOUNIT_0 {
 	MPI2_CONFIG_EXTENDED_PAGE_HEADER	Header; /*0x00 */
@@ -3701,7 +3625,7 @@ typedef struct _MPI26_CONFIG_PAGE_PIOUNIT_0 {
 	U8	InitStatus;                             /*0x0D */
 	U16	Reserved3;                              /*0x0E */
 	MPI26_PCIE_IO_UNIT0_PHY_DATA
-		PhyData[MPI26_PCIE_IOUNIT0_PHY_MAX];    /*0x10 */
+		PhyData[];                              /*0x10 */
 } MPI26_CONFIG_PAGE_PIOUNIT_0,
 	*PTR_MPI26_CONFIG_PAGE_PIOUNIT_0,
 	Mpi26PCIeIOUnitPage0_t, *pMpi26PCIeIOUnitPage0_t;
@@ -3744,12 +3668,9 @@ typedef struct _MPI26_PCIE_IO_UNIT1_PHY_DATA {
 #define MPI26_PCIEIOUNIT1_LINKFLAGS_SRNS_EN                 (0x02)
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for NumPhys at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check the value returned
+ *for NumPhys at runtime before using PhyData[].
  */
-#ifndef MPI26_PCIE_IOUNIT1_PHY_MAX
-#define MPI26_PCIE_IOUNIT1_PHY_MAX      (1)
-#endif
 
 typedef struct _MPI26_CONFIG_PAGE_PIOUNIT_1 {
 	MPI2_CONFIG_EXTENDED_PAGE_HEADER	Header;	/*0x00 */
@@ -3761,7 +3682,7 @@ typedef struct _MPI26_CONFIG_PAGE_PIOUNIT_1 {
 	U8	DMDReportPCIe;                      /*0x11 */
 	U16	Reserved2;                          /*0x12 */
 	MPI26_PCIE_IO_UNIT1_PHY_DATA
-		PhyData[MPI26_PCIE_IOUNIT1_PHY_MAX];/*0x14 */
+		PhyData[];                          /*0x14 */
 } MPI26_CONFIG_PAGE_PIOUNIT_1,
 	*PTR_MPI26_CONFIG_PAGE_PIOUNIT_1,
 	Mpi26PCIeIOUnitPage1_t, *pMpi26PCIeIOUnitPage1_t;
@@ -3993,12 +3914,9 @@ typedef struct _MPI26_PCIELINK2_LINK_EVENT {
 
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for NumLinkEvents at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check the value returned
+ *for NumLinkEvents at runtime before using LinkEvent[].
  */
-#ifndef MPI26_PCIELINK2_LINK_EVENT_MAX
-#define MPI26_PCIELINK2_LINK_EVENT_MAX      (1)
-#endif
 
 typedef struct _MPI26_CONFIG_PAGE_PCIELINK_2 {
 	MPI2_CONFIG_EXTENDED_PAGE_HEADER	Header;	/*0x00 */
@@ -4009,7 +3927,7 @@ typedef struct _MPI26_CONFIG_PAGE_PCIELINK_2 {
 	U8	Reserved3;                  /*0x0D */
 	U16	Reserved4;                  /*0x0E */
 	MPI26_PCIELINK2_LINK_EVENT
-		LinkEvent[MPI26_PCIELINK2_LINK_EVENT_MAX];	/*0x10 */
+		LinkEvent[];                /*0x10 */
 } MPI26_CONFIG_PAGE_PCIELINK_2, *PTR_MPI26_CONFIG_PAGE_PCIELINK_2,
 	Mpi26PcieLinkPage2_t, *pMpi26PcieLinkPage2_t;
 
@@ -4067,12 +3985,9 @@ typedef struct _MPI26_PCIELINK3_LINK_EVENT_CONFIG {
 #define MPI26_PCIELINK3_TFLAGS_EVENT_NOTIFY                 (0x0001)
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check the value returned for NumLinkEvents at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check the value returned
+ *for NumLinkEvents at runtime before using LinkEventConfig[].
  */
-#ifndef MPI26_PCIELINK3_LINK_EVENT_MAX
-#define MPI26_PCIELINK3_LINK_EVENT_MAX      (1)
-#endif
 
 typedef struct _MPI26_CONFIG_PAGE_PCIELINK_3 {
 	MPI2_CONFIG_EXTENDED_PAGE_HEADER	Header;	/*0x00 */
@@ -4083,7 +3998,7 @@ typedef struct _MPI26_CONFIG_PAGE_PCIELINK_3 {
 	U8	Reserved3;                  /*0x0D */
 	U16	Reserved4;                  /*0x0E */
 	MPI26_PCIELINK3_LINK_EVENT_CONFIG
-		LinkEventConfig[MPI26_PCIELINK3_LINK_EVENT_MAX]; /*0x10 */
+		LinkEventConfig[];          /*0x10 */
 } MPI26_CONFIG_PAGE_PCIELINK_3, *PTR_MPI26_CONFIG_PAGE_PCIELINK_3,
 	Mpi26PcieLinkPage3_t, *pMpi26PcieLinkPage3_t;
 
diff --git a/drivers/scsi/mpt3sas/mpi/mpi2_image.h b/drivers/scsi/mpt3sas/mpi/mpi2_image.h
index 33b9c3a6fd40..798ab6e33eb9 100644
--- a/drivers/scsi/mpt3sas/mpi/mpi2_image.h
+++ b/drivers/scsi/mpt3sas/mpi/mpi2_image.h
@@ -295,20 +295,9 @@ typedef struct _MPI2_EXT_IMAGE_HEADER {
 /*FLASH Layout Extended Image Data */
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check RegionsPerLayout at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check NumberOfLayouts and
+ *RegionsPerLayout at runtime before using Layout[] and Region[].
  */
-#ifndef MPI2_FLASH_NUMBER_OF_REGIONS
-#define MPI2_FLASH_NUMBER_OF_REGIONS        (1)
-#endif
-
-/*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check NumberOfLayouts at runtime.
- */
-#ifndef MPI2_FLASH_NUMBER_OF_LAYOUTS
-#define MPI2_FLASH_NUMBER_OF_LAYOUTS        (1)
-#endif
 
 typedef struct _MPI2_FLASH_REGION {
 	U8 RegionType;		/*0x00 */
@@ -325,7 +314,7 @@ typedef struct _MPI2_FLASH_LAYOUT {
 	U32 Reserved1;		/*0x04 */
 	U32 Reserved2;		/*0x08 */
 	U32 Reserved3;		/*0x0C */
-	MPI2_FLASH_REGION Region[MPI2_FLASH_NUMBER_OF_REGIONS];	/*0x10 */
+	MPI2_FLASH_REGION Region[];	/*0x10 */
 } MPI2_FLASH_LAYOUT, *PTR_MPI2_FLASH_LAYOUT,
 	Mpi2FlashLayout_t, *pMpi2FlashLayout_t;
 
@@ -339,7 +328,7 @@ typedef struct _MPI2_FLASH_LAYOUT_DATA {
 	U16 MinimumSectorAlignment;	/*0x08 */
 	U16 Reserved3;		/*0x0A */
 	U32 Reserved4;		/*0x0C */
-	MPI2_FLASH_LAYOUT Layout[MPI2_FLASH_NUMBER_OF_LAYOUTS];	/*0x10 */
+	MPI2_FLASH_LAYOUT Layout[];	/*0x10 */
 } MPI2_FLASH_LAYOUT_DATA, *PTR_MPI2_FLASH_LAYOUT_DATA,
 	Mpi2FlashLayoutData_t, *pMpi2FlashLayoutData_t;
 
@@ -373,12 +362,9 @@ typedef struct _MPI2_FLASH_LAYOUT_DATA {
 /*Supported Devices Extended Image Data */
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check NumberOfDevices at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check NumberOfDevices at
+ *runtime before using SupportedDevice[].
  */
-#ifndef MPI2_SUPPORTED_DEVICES_IMAGE_NUM_DEVICES
-#define MPI2_SUPPORTED_DEVICES_IMAGE_NUM_DEVICES    (1)
-#endif
 
 typedef struct _MPI2_SUPPORTED_DEVICE {
 	U16 DeviceID;		/*0x00 */
@@ -399,7 +385,7 @@ typedef struct _MPI2_SUPPORTED_DEVICES_DATA {
 	U8 Reserved2;		/*0x03 */
 	U32 Reserved3;		/*0x04 */
 	MPI2_SUPPORTED_DEVICE
-	SupportedDevice[MPI2_SUPPORTED_DEVICES_IMAGE_NUM_DEVICES];/*0x08 */
+	SupportedDevice[];	/*0x08 */
 } MPI2_SUPPORTED_DEVICES_DATA, *PTR_MPI2_SUPPORTED_DEVICES_DATA,
 	Mpi2SupportedDevicesData_t, *pMpi2SupportedDevicesData_t;
 
@@ -464,7 +450,7 @@ typedef struct _MPI25_ENCRYPTED_HASH_ENTRY {
 	U8		EncryptionAlgorithm;	/*0x02 */
 	U8		Reserved1;		/*0x03 */
 	U32		Reserved2;		/*0x04 */
-	U32		EncryptedHash[1];	/*0x08 */ /* variable length */
+	U32		EncryptedHash[];	/*0x08 */
 } MPI25_ENCRYPTED_HASH_ENTRY, *PTR_MPI25_ENCRYPTED_HASH_ENTRY,
 Mpi25EncryptedHashEntry_t, *pMpi25EncryptedHashEntry_t;
 
@@ -508,7 +494,7 @@ typedef struct _MPI25_ENCRYPTED_HASH_DATA {
 	U8				NumHash;		/*0x01 */
 	U16				Reserved1;		/*0x02 */
 	U32				Reserved2;		/*0x04 */
-	MPI25_ENCRYPTED_HASH_ENTRY	EncryptedHashEntry[1];  /*0x08 */
+	MPI25_ENCRYPTED_HASH_ENTRY	EncryptedHashEntry[];	/*0x08 */
 } MPI25_ENCRYPTED_HASH_DATA, *PTR_MPI25_ENCRYPTED_HASH_DATA,
 Mpi25EncryptedHashData_t, *pMpi25EncryptedHashData_t;
 
diff --git a/drivers/scsi/mpt3sas/mpi/mpi2_ioc.h b/drivers/scsi/mpt3sas/mpi/mpi2_ioc.h
index 2c57115172cf..d92852591134 100644
--- a/drivers/scsi/mpt3sas/mpi/mpi2_ioc.h
+++ b/drivers/scsi/mpt3sas/mpi/mpi2_ioc.h
@@ -808,12 +808,9 @@ typedef struct _MPI2_EVENT_DATA_IR_PHYSICAL_DISK {
 /*Integrated RAID Configuration Change List Event data */
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check NumElements at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check NumElements at
+ *runtime before using ConfigElement[].
  */
-#ifndef MPI2_EVENT_IR_CONFIG_ELEMENT_COUNT
-#define MPI2_EVENT_IR_CONFIG_ELEMENT_COUNT          (1)
-#endif
 
 typedef struct _MPI2_EVENT_IR_CONFIG_ELEMENT {
 	U16 ElementFlags;	/*0x00 */
@@ -848,7 +845,7 @@ typedef struct _MPI2_EVENT_DATA_IR_CONFIG_CHANGE_LIST {
 	U8 ConfigNum;		/*0x03 */
 	U32 Flags;		/*0x04 */
 	MPI2_EVENT_IR_CONFIG_ELEMENT
-		ConfigElement[MPI2_EVENT_IR_CONFIG_ELEMENT_COUNT];/*0x08 */
+		ConfigElement[];/*0x08 */
 } MPI2_EVENT_DATA_IR_CONFIG_CHANGE_LIST,
 	*PTR_MPI2_EVENT_DATA_IR_CONFIG_CHANGE_LIST,
 	Mpi2EventDataIrConfigChangeList_t,
@@ -969,12 +966,9 @@ typedef struct _MPI2_EVENT_DATA_SAS_INIT_TABLE_OVERFLOW {
 /*SAS Topology Change List Event data */
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check NumEntries at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check NumEntries at
+ *runtime before using PHY[].
  */
-#ifndef MPI2_EVENT_SAS_TOPO_PHY_COUNT
-#define MPI2_EVENT_SAS_TOPO_PHY_COUNT           (1)
-#endif
 
 typedef struct _MPI2_EVENT_SAS_TOPO_PHY_ENTRY {
 	U16 AttachedDevHandle;	/*0x00 */
@@ -994,7 +988,7 @@ typedef struct _MPI2_EVENT_DATA_SAS_TOPOLOGY_CHANGE_LIST {
 	U8 ExpStatus;		/*0x0A */
 	U8 PhysicalPort;	/*0x0B */
 	MPI2_EVENT_SAS_TOPO_PHY_ENTRY
-	PHY[MPI2_EVENT_SAS_TOPO_PHY_COUNT];	/*0x0C */
+	PHY[];			/*0x0C */
 } MPI2_EVENT_DATA_SAS_TOPOLOGY_CHANGE_LIST,
 	*PTR_MPI2_EVENT_DATA_SAS_TOPOLOGY_CHANGE_LIST,
 	Mpi2EventDataSasTopologyChangeList_t,
@@ -1229,12 +1223,9 @@ typedef struct _MPI26_EVENT_DATA_PCIE_ENUMERATION {
 /*PCIe Topology Change List Event data (MPI v2.6 and later) */
 
 /*
- *Host code (drivers, BIOS, utilities, etc.) should leave this define set to
- *one and check NumEntries at runtime.
+ *Host code (drivers, BIOS, utilities, etc.) should check NumEntries at
+ *runtime before using PortEntry[].
  */
-#ifndef MPI26_EVENT_PCIE_TOPO_PORT_COUNT
-#define MPI26_EVENT_PCIE_TOPO_PORT_COUNT        (1)
-#endif
 
 typedef struct _MPI26_EVENT_PCIE_TOPO_PORT_ENTRY {
 	U16	AttachedDevHandle;      /*0x00 */
@@ -1286,7 +1277,7 @@ typedef struct _MPI26_EVENT_DATA_PCIE_TOPOLOGY_CHANGE_LIST {
 	U8	SwitchStatus;           /*0x0A */
 	U8	PhysicalPort;           /*0x0B */
 	MPI26_EVENT_PCIE_TOPO_PORT_ENTRY
-		PortEntry[MPI26_EVENT_PCIE_TOPO_PORT_COUNT]; /*0x0C */
+		PortEntry[];            /*0x0C */
 } MPI26_EVENT_DATA_PCIE_TOPOLOGY_CHANGE_LIST,
 	*PTR_MPI26_EVENT_DATA_PCIE_TOPOLOGY_CHANGE_LIST,
 	Mpi26EventDataPCIeTopologyChangeList_t,
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index a75f670bf551..8761bc58d965 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -4893,8 +4893,7 @@ mpt3sas_base_update_missing_delay(struct MPT3SAS_ADAPTER *ioc,
 	if (!num_phys)
 		return;
 
-	sz = offsetof(Mpi2SasIOUnitPage1_t, PhyData) + (num_phys *
-	    sizeof(Mpi2SasIOUnit1PhyData_t));
+	sz = struct_size(sas_iounit_pg1, PhyData, num_phys);
 	sas_iounit_pg1 = kzalloc(sz, GFP_KERNEL);
 	if (!sas_iounit_pg1) {
 		ioc_err(ioc, "failure at %s:%d/%s()!\n",
@@ -5044,7 +5043,7 @@ _base_get_event_diag_triggers(struct MPT3SAS_ADAPTER *ioc)
 {
 	Mpi26DriverTriggerPage2_t trigger_pg2;
 	struct SL_WH_EVENT_TRIGGER_T *event_tg;
-	MPI26_DRIVER_MPI_EVENT_TIGGER_ENTRY *mpi_event_tg;
+	MPI26_DRIVER_MPI_EVENT_TRIGGER_ENTRY *mpi_event_tg;
 	Mpi2ConfigReply_t mpi_reply;
 	int r = 0, i = 0;
 	u16 count = 0;
@@ -5096,7 +5095,7 @@ _base_get_scsi_diag_triggers(struct MPT3SAS_ADAPTER *ioc)
 {
 	Mpi26DriverTriggerPage3_t trigger_pg3;
 	struct SL_WH_SCSI_TRIGGER_T *scsi_tg;
-	MPI26_DRIVER_SCSI_SENSE_TIGGER_ENTRY *mpi_scsi_tg;
+	MPI26_DRIVER_SCSI_SENSE_TRIGGER_ENTRY *mpi_scsi_tg;
 	Mpi2ConfigReply_t mpi_reply;
 	int r = 0, i = 0;
 	u16 count = 0;
@@ -5148,7 +5147,7 @@ _base_get_mpi_diag_triggers(struct MPT3SAS_ADAPTER *ioc)
 {
 	Mpi26DriverTriggerPage4_t trigger_pg4;
 	struct SL_WH_MPI_TRIGGER_T *status_tg;
-	MPI26_DRIVER_IOCSTATUS_LOGINFO_TIGGER_ENTRY *mpi_status_tg;
+	MPI26_DRIVER_IOCSTATUS_LOGINFO_TRIGGER_ENTRY *mpi_status_tg;
 	Mpi2ConfigReply_t mpi_reply;
 	int r = 0, i = 0;
 	u16 count = 0;
@@ -5379,10 +5378,9 @@ _base_update_diag_trigger_pages(struct MPT3SAS_ADAPTER *ioc)
 static int _base_assign_fw_reported_qd(struct MPT3SAS_ADAPTER *ioc)
 {
 	Mpi2ConfigReply_t mpi_reply;
-	Mpi2SasIOUnitPage1_t *sas_iounit_pg1 = NULL;
+	Mpi2SasIOUnitPage1_t sas_iounit_pg1;
 	Mpi26PCIeIOUnitPage1_t pcie_iounit_pg1;
 	u16 depth;
-	int sz;
 	int rc = 0;
 
 	ioc->max_wideport_qd = MPT3SAS_SAS_QUEUE_DEPTH;
@@ -5392,28 +5390,21 @@ static int _base_assign_fw_reported_qd(struct MPT3SAS_ADAPTER *ioc)
 	if (!ioc->is_gen35_ioc)
 		goto out;
 	/* sas iounit page 1 */
-	sz = offsetof(Mpi2SasIOUnitPage1_t, PhyData);
-	sas_iounit_pg1 = kzalloc(sizeof(Mpi2SasIOUnitPage1_t), GFP_KERNEL);
-	if (!sas_iounit_pg1) {
-		pr_err("%s: failure at %s:%d/%s()!\n",
-		    ioc->name, __FILE__, __LINE__, __func__);
-		return rc;
-	}
 	rc = mpt3sas_config_get_sas_iounit_pg1(ioc, &mpi_reply,
-	    sas_iounit_pg1, sz);
+	    &sas_iounit_pg1, sizeof(Mpi2SasIOUnitPage1_t));
 	if (rc) {
 		pr_err("%s: failure at %s:%d/%s()!\n",
 		    ioc->name, __FILE__, __LINE__, __func__);
 		goto out;
 	}
 
-	depth = le16_to_cpu(sas_iounit_pg1->SASWideMaxQueueDepth);
+	depth = le16_to_cpu(sas_iounit_pg1.SASWideMaxQueueDepth);
 	ioc->max_wideport_qd = (depth ? depth : MPT3SAS_SAS_QUEUE_DEPTH);
 
-	depth = le16_to_cpu(sas_iounit_pg1->SASNarrowMaxQueueDepth);
+	depth = le16_to_cpu(sas_iounit_pg1.SASNarrowMaxQueueDepth);
 	ioc->max_narrowport_qd = (depth ? depth : MPT3SAS_SAS_QUEUE_DEPTH);
 
-	depth = sas_iounit_pg1->SATAMaxQDepth;
+	depth = sas_iounit_pg1.SATAMaxQDepth;
 	ioc->max_sata_qd = (depth ? depth : MPT3SAS_SATA_QUEUE_DEPTH);
 
 	/* pcie iounit page 1 */
@@ -5432,7 +5423,6 @@ out:
 	    "MaxWidePortQD: 0x%x MaxNarrowPortQD: 0x%x MaxSataQD: 0x%x MaxNvmeQD: 0x%x\n",
 	    ioc->max_wideport_qd, ioc->max_narrowport_qd,
 	    ioc->max_sata_qd, ioc->max_nvme_qd));
-	kfree(sas_iounit_pg1);
 	return rc;
 }
 
@@ -5588,6 +5578,7 @@ out:
 static int
 _base_static_config_pages(struct MPT3SAS_ADAPTER *ioc)
 {
+	Mpi2IOUnitPage8_t iounit_pg8;
 	Mpi2ConfigReply_t mpi_reply;
 	u32 iounit_pg1_flags;
 	int tg_flags = 0;
@@ -5684,7 +5675,7 @@ _base_static_config_pages(struct MPT3SAS_ADAPTER *ioc)
 	rc = mpt3sas_config_get_iounit_pg1(ioc, &mpi_reply, &ioc->iounit_pg1);
 	if (rc)
 		return rc;
-	rc = mpt3sas_config_get_iounit_pg8(ioc, &mpi_reply, &ioc->iounit_pg8);
+	rc = mpt3sas_config_get_iounit_pg8(ioc, &mpi_reply, &iounit_pg8);
 	if (rc)
 		return rc;
 	_base_display_ioc_capabilities(ioc);
@@ -5706,8 +5697,8 @@ _base_static_config_pages(struct MPT3SAS_ADAPTER *ioc)
 	if (rc)
 		return rc;
 
-	if (ioc->iounit_pg8.NumSensors)
-		ioc->temp_sensors_count = ioc->iounit_pg8.NumSensors;
+	if (iounit_pg8.NumSensors)
+		ioc->temp_sensors_count = iounit_pg8.NumSensors;
 	if (ioc->is_aero_ioc) {
 		rc = _base_update_ioc_page1_inlinewith_perf_mode(ioc);
 		if (rc)
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index 1be0850ca17a..6d0bc8c66700 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -1237,7 +1237,6 @@ typedef void (*MPT3SAS_FLUSH_RUNNING_CMDS)(struct MPT3SAS_ADAPTER *ioc);
  * @ioc_pg8: static ioc page 8
  * @iounit_pg0: static iounit page 0
  * @iounit_pg1: static iounit page 1
- * @iounit_pg8: static iounit page 8
  * @sas_hba: sas host object
  * @sas_expander_list: expander object list
  * @enclosure_list: enclosure object list
@@ -1465,7 +1464,6 @@ struct MPT3SAS_ADAPTER {
 	Mpi2IOCPage8_t ioc_pg8;
 	Mpi2IOUnitPage0_t iounit_pg0;
 	Mpi2IOUnitPage1_t iounit_pg1;
-	Mpi2IOUnitPage8_t iounit_pg8;
 	Mpi2IOCPage1_t	ioc_pg1_copy;
 
 	struct _boot_device req_boot_device;
@@ -1983,6 +1981,7 @@ extern const struct attribute_group *mpt3sas_host_groups[];
 extern const struct attribute_group *mpt3sas_dev_groups[];
 void mpt3sas_ctl_init(ushort hbas_to_enumerate);
 void mpt3sas_ctl_exit(ushort hbas_to_enumerate);
+void mpt3sas_ctl_release(struct MPT3SAS_ADAPTER *ioc);
 u8 mpt3sas_ctl_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
 	u32 reply);
 void mpt3sas_ctl_pre_reset_handler(struct MPT3SAS_ADAPTER *ioc);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_config.c b/drivers/scsi/mpt3sas/mpt3sas_config.c
index d114ef381c44..2e88f456fc34 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_config.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_config.c
@@ -2334,7 +2334,7 @@ mpt3sas_config_update_driver_trigger_pg2(struct MPT3SAS_ADAPTER *ioc,
 		tg_pg2.NumMPIEventTrigger = 0;
 		memset(&tg_pg2.MPIEventTriggers[0], 0,
 		    NUM_VALID_ENTRIES * sizeof(
-		    MPI26_DRIVER_MPI_EVENT_TIGGER_ENTRY));
+		    MPI26_DRIVER_MPI_EVENT_TRIGGER_ENTRY));
 	}
 
 	rc = _config_set_driver_trigger_pg2(ioc, &mpi_reply, &tg_pg2);
@@ -2493,7 +2493,7 @@ mpt3sas_config_update_driver_trigger_pg3(struct MPT3SAS_ADAPTER *ioc,
 		tg_pg3.NumSCSISenseTrigger = 0;
 		memset(&tg_pg3.SCSISenseTriggers[0], 0,
 		    NUM_VALID_ENTRIES * sizeof(
-		    MPI26_DRIVER_SCSI_SENSE_TIGGER_ENTRY));
+		    MPI26_DRIVER_SCSI_SENSE_TRIGGER_ENTRY));
 	}
 
 	rc = _config_set_driver_trigger_pg3(ioc, &mpi_reply, &tg_pg3);
@@ -2649,7 +2649,7 @@ mpt3sas_config_update_driver_trigger_pg4(struct MPT3SAS_ADAPTER *ioc,
 		tg_pg4.NumIOCStatusLogInfoTrigger = 0;
 		memset(&tg_pg4.IOCStatusLoginfoTriggers[0], 0,
 		    NUM_VALID_ENTRIES * sizeof(
-		    MPI26_DRIVER_IOCSTATUS_LOGINFO_TIGGER_ENTRY));
+		    MPI26_DRIVER_IOCSTATUS_LOGINFO_TRIGGER_ENTRY));
 	}
 
 	rc = _config_set_driver_trigger_pg4(ioc, &mpi_reply, &tg_pg4);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
index efdb8178db32..147cb7088d55 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
@@ -4157,31 +4157,37 @@ mpt3sas_ctl_init(ushort hbas_to_enumerate)
 }
 
 /**
- * mpt3sas_ctl_exit - exit point for ctl
- * @hbas_to_enumerate: ?
+ * mpt3sas_ctl_release - release dma for ctl
+ * @ioc: per adapter object
  */
 void
-mpt3sas_ctl_exit(ushort hbas_to_enumerate)
+mpt3sas_ctl_release(struct MPT3SAS_ADAPTER *ioc)
 {
-	struct MPT3SAS_ADAPTER *ioc;
 	int i;
 
-	list_for_each_entry(ioc, &mpt3sas_ioc_list, list) {
+	/* free memory associated to diag buffers */
+	for (i = 0; i < MPI2_DIAG_BUF_TYPE_COUNT; i++) {
+		if (!ioc->diag_buffer[i])
+			continue;
+		dma_free_coherent(&ioc->pdev->dev,
+				  ioc->diag_buffer_sz[i],
+				  ioc->diag_buffer[i],
+				  ioc->diag_buffer_dma[i]);
+		ioc->diag_buffer[i] = NULL;
+		ioc->diag_buffer_status[i] = 0;
+	}
 
-		/* free memory associated to diag buffers */
-		for (i = 0; i < MPI2_DIAG_BUF_TYPE_COUNT; i++) {
-			if (!ioc->diag_buffer[i])
-				continue;
-			dma_free_coherent(&ioc->pdev->dev,
-					  ioc->diag_buffer_sz[i],
-					  ioc->diag_buffer[i],
-					  ioc->diag_buffer_dma[i]);
-			ioc->diag_buffer[i] = NULL;
-			ioc->diag_buffer_status[i] = 0;
-		}
+	kfree(ioc->event_log);
+}
+
+/**
+ * mpt3sas_ctl_exit - exit point for ctl
+ * @hbas_to_enumerate: ?
+ */
+void
+mpt3sas_ctl_exit(ushort hbas_to_enumerate)
+{
 
-		kfree(ioc->event_log);
-	}
 	if (hbas_to_enumerate != 1)
 		misc_deregister(&ctl_dev);
 	if (hbas_to_enumerate != 2)
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 605013d3ee83..51b5788da040 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -2431,8 +2431,7 @@ _scsih_get_volume_capabilities(struct MPT3SAS_ADAPTER *ioc,
 	}
 
 	raid_device->num_pds = num_pds;
-	sz = offsetof(Mpi2RaidVolPage0_t, PhysDisk) + (num_pds *
-	    sizeof(Mpi2RaidVol0PhysDisk_t));
+	sz = struct_size(vol_pg0, PhysDisk, num_pds);
 	vol_pg0 = kzalloc(sz, GFP_KERNEL);
 	if (!vol_pg0) {
 		dfailprintk(ioc,
@@ -5966,8 +5965,7 @@ _scsih_update_vphys_after_reset(struct MPT3SAS_ADAPTER *ioc)
 	/*
 	 * Read SASIOUnitPage0 to get each HBA Phy's data.
 	 */
-	sz = offsetof(Mpi2SasIOUnitPage0_t, PhyData) +
-	    (ioc->sas_hba.num_phys * sizeof(Mpi2SasIOUnit0PhyData_t));
+	sz = struct_size(sas_iounit_pg0, PhyData, ioc->sas_hba.num_phys);
 	sas_iounit_pg0 = kzalloc(sz, GFP_KERNEL);
 	if (!sas_iounit_pg0) {
 		ioc_err(ioc, "failure at %s:%d/%s()!\n",
@@ -6145,8 +6143,7 @@ _scsih_get_port_table_after_reset(struct MPT3SAS_ADAPTER *ioc,
 	u64 attached_sas_addr;
 	u8 found = 0, port_count = 0, port_id;
 
-	sz = offsetof(Mpi2SasIOUnitPage0_t, PhyData) + (ioc->sas_hba.num_phys
-	    * sizeof(Mpi2SasIOUnit0PhyData_t));
+	sz = struct_size(sas_iounit_pg0, PhyData, ioc->sas_hba.num_phys);
 	sas_iounit_pg0 = kzalloc(sz, GFP_KERNEL);
 	if (!sas_iounit_pg0) {
 		ioc_err(ioc, "failure at %s:%d/%s()!\n",
@@ -6579,8 +6576,7 @@ _scsih_sas_host_refresh(struct MPT3SAS_ADAPTER *ioc)
 		  ioc_info(ioc, "updating handles for sas_host(0x%016llx)\n",
 			   (u64)ioc->sas_hba.sas_address));
 
-	sz = offsetof(Mpi2SasIOUnitPage0_t, PhyData) + (ioc->sas_hba.num_phys
-	    * sizeof(Mpi2SasIOUnit0PhyData_t));
+	sz = struct_size(sas_iounit_pg0, PhyData, ioc->sas_hba.num_phys);
 	sas_iounit_pg0 = kzalloc(sz, GFP_KERNEL);
 	if (!sas_iounit_pg0) {
 		ioc_err(ioc, "failure at %s:%d/%s()!\n",
@@ -6731,8 +6727,7 @@ _scsih_sas_host_add(struct MPT3SAS_ADAPTER *ioc)
 	ioc->sas_hba.num_phys = num_phys;
 
 	/* sas_iounit page 0 */
-	sz = offsetof(Mpi2SasIOUnitPage0_t, PhyData) + (ioc->sas_hba.num_phys *
-	    sizeof(Mpi2SasIOUnit0PhyData_t));
+	sz = struct_size(sas_iounit_pg0, PhyData, ioc->sas_hba.num_phys);
 	sas_iounit_pg0 = kzalloc(sz, GFP_KERNEL);
 	if (!sas_iounit_pg0) {
 		ioc_err(ioc, "failure at %s:%d/%s()!\n",
@@ -6754,8 +6749,7 @@ _scsih_sas_host_add(struct MPT3SAS_ADAPTER *ioc)
 	}
 
 	/* sas_iounit page 1 */
-	sz = offsetof(Mpi2SasIOUnitPage1_t, PhyData) + (ioc->sas_hba.num_phys *
-	    sizeof(Mpi2SasIOUnit1PhyData_t));
+	sz = struct_size(sas_iounit_pg1, PhyData, ioc->sas_hba.num_phys);
 	sas_iounit_pg1 = kzalloc(sz, GFP_KERNEL);
 	if (!sas_iounit_pg1) {
 		ioc_err(ioc, "failure at %s:%d/%s()!\n",
@@ -10376,8 +10370,8 @@ _scsih_scan_for_devices_after_reset(struct MPT3SAS_ADAPTER *ioc)
 	Mpi2ExpanderPage0_t expander_pg0;
 	Mpi2SasDevicePage0_t sas_device_pg0;
 	Mpi26PCIeDevicePage0_t pcie_device_pg0;
-	Mpi2RaidVolPage1_t *volume_pg1;
-	Mpi2RaidVolPage0_t *volume_pg0;
+	Mpi2RaidVolPage1_t volume_pg1;
+	Mpi2RaidVolPage0_t volume_pg0;
 	Mpi2RaidPhysDiskPage0_t pd_pg0;
 	Mpi2EventIrConfigElement_t element;
 	Mpi2ConfigReply_t mpi_reply;
@@ -10392,16 +10386,6 @@ _scsih_scan_for_devices_after_reset(struct MPT3SAS_ADAPTER *ioc)
 	u8 retry_count;
 	unsigned long flags;
 
-	volume_pg0 = kzalloc(sizeof(*volume_pg0), GFP_KERNEL);
-	if (!volume_pg0)
-		return;
-
-	volume_pg1 = kzalloc(sizeof(*volume_pg1), GFP_KERNEL);
-	if (!volume_pg1) {
-		kfree(volume_pg0);
-		return;
-	}
-
 	ioc_info(ioc, "scan devices: start\n");
 
 	_scsih_sas_host_refresh(ioc);
@@ -10511,7 +10495,7 @@ _scsih_scan_for_devices_after_reset(struct MPT3SAS_ADAPTER *ioc)
 	/* volumes */
 	handle = 0xFFFF;
 	while (!(mpt3sas_config_get_raid_volume_pg1(ioc, &mpi_reply,
-	    volume_pg1, MPI2_RAID_VOLUME_PGAD_FORM_GET_NEXT_HANDLE, handle))) {
+	    &volume_pg1, MPI2_RAID_VOLUME_PGAD_FORM_GET_NEXT_HANDLE, handle))) {
 		ioc_status = le16_to_cpu(mpi_reply.IOCStatus) &
 		    MPI2_IOCSTATUS_MASK;
 		if (ioc_status != MPI2_IOCSTATUS_SUCCESS) {
@@ -10519,15 +10503,15 @@ _scsih_scan_for_devices_after_reset(struct MPT3SAS_ADAPTER *ioc)
 				 ioc_status, le32_to_cpu(mpi_reply.IOCLogInfo));
 			break;
 		}
-		handle = le16_to_cpu(volume_pg1->DevHandle);
+		handle = le16_to_cpu(volume_pg1.DevHandle);
 		spin_lock_irqsave(&ioc->raid_device_lock, flags);
 		raid_device = _scsih_raid_device_find_by_wwid(ioc,
-		    le64_to_cpu(volume_pg1->WWID));
+		    le64_to_cpu(volume_pg1.WWID));
 		spin_unlock_irqrestore(&ioc->raid_device_lock, flags);
 		if (raid_device)
 			continue;
 		if (mpt3sas_config_get_raid_volume_pg0(ioc, &mpi_reply,
-		    volume_pg0, MPI2_RAID_VOLUME_PGAD_FORM_HANDLE, handle,
+		    &volume_pg0, MPI2_RAID_VOLUME_PGAD_FORM_HANDLE, handle,
 		     sizeof(Mpi2RaidVolPage0_t)))
 			continue;
 		ioc_status = le16_to_cpu(mpi_reply.IOCStatus) &
@@ -10537,17 +10521,17 @@ _scsih_scan_for_devices_after_reset(struct MPT3SAS_ADAPTER *ioc)
 				 ioc_status, le32_to_cpu(mpi_reply.IOCLogInfo));
 			break;
 		}
-		if (volume_pg0->VolumeState == MPI2_RAID_VOL_STATE_OPTIMAL ||
-		    volume_pg0->VolumeState == MPI2_RAID_VOL_STATE_ONLINE ||
-		    volume_pg0->VolumeState == MPI2_RAID_VOL_STATE_DEGRADED) {
+		if (volume_pg0.VolumeState == MPI2_RAID_VOL_STATE_OPTIMAL ||
+		    volume_pg0.VolumeState == MPI2_RAID_VOL_STATE_ONLINE ||
+		    volume_pg0.VolumeState == MPI2_RAID_VOL_STATE_DEGRADED) {
 			memset(&element, 0, sizeof(Mpi2EventIrConfigElement_t));
 			element.ReasonCode = MPI2_EVENT_IR_CHANGE_RC_ADDED;
-			element.VolDevHandle = volume_pg1->DevHandle;
+			element.VolDevHandle = volume_pg1.DevHandle;
 			ioc_info(ioc, "\tBEFORE adding volume: handle (0x%04x)\n",
-				 volume_pg1->DevHandle);
+				 volume_pg1.DevHandle);
 			_scsih_sas_volume_add(ioc, &element);
 			ioc_info(ioc, "\tAFTER adding volume: handle (0x%04x)\n",
-				 volume_pg1->DevHandle);
+				 volume_pg1.DevHandle);
 		}
 	}
 
@@ -10636,9 +10620,6 @@ _scsih_scan_for_devices_after_reset(struct MPT3SAS_ADAPTER *ioc)
 			 handle, (u64)le64_to_cpu(pcie_device_pg0.WWID));
 	}
 
-	kfree(volume_pg0);
-	kfree(volume_pg1);
-
 	ioc_info(ioc, "\tpcie devices: pcie end devices complete\n");
 	ioc_info(ioc, "scan devices: complete\n");
 }
@@ -11350,6 +11331,7 @@ static void scsih_remove(struct pci_dev *pdev)
 	}
 
 	mpt3sas_base_detach(ioc);
+	mpt3sas_ctl_release(ioc);
 	spin_lock(&gioc_lock);
 	list_del(&ioc->list);
 	spin_unlock(&gioc_lock);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_transport.c b/drivers/scsi/mpt3sas/mpt3sas_transport.c
index e8a4750f6ec4..421ea511b664 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_transport.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_transport.c
@@ -1792,8 +1792,7 @@ _transport_phy_enable(struct sas_phy *phy, int enable)
 	/* handle hba phys */
 
 	/* read sas_iounit page 0 */
-	sz = offsetof(Mpi2SasIOUnitPage0_t, PhyData) + (ioc->sas_hba.num_phys *
-	    sizeof(Mpi2SasIOUnit0PhyData_t));
+	sz = struct_size(sas_iounit_pg0, PhyData, ioc->sas_hba.num_phys);
 	sas_iounit_pg0 = kzalloc(sz, GFP_KERNEL);
 	if (!sas_iounit_pg0) {
 		ioc_err(ioc, "failure at %s:%d/%s()!\n",
@@ -1833,8 +1832,7 @@ _transport_phy_enable(struct sas_phy *phy, int enable)
 	}
 
 	/* read sas_iounit page 1 */
-	sz = offsetof(Mpi2SasIOUnitPage1_t, PhyData) + (ioc->sas_hba.num_phys *
-	    sizeof(Mpi2SasIOUnit1PhyData_t));
+	sz = struct_size(sas_iounit_pg1, PhyData, ioc->sas_hba.num_phys);
 	sas_iounit_pg1 = kzalloc(sz, GFP_KERNEL);
 	if (!sas_iounit_pg1) {
 		ioc_err(ioc, "failure at %s:%d/%s()!\n",
@@ -1944,8 +1942,7 @@ _transport_phy_speed(struct sas_phy *phy, struct sas_phy_linkrates *rates)
 	/* handle hba phys */
 
 	/* sas_iounit page 1 */
-	sz = offsetof(Mpi2SasIOUnitPage1_t, PhyData) + (ioc->sas_hba.num_phys *
-	    sizeof(Mpi2SasIOUnit1PhyData_t));
+	sz = struct_size(sas_iounit_pg1, PhyData, ioc->sas_hba.num_phys);
 	sas_iounit_pg1 = kzalloc(sz, GFP_KERNEL);
 	if (!sas_iounit_pg1) {
 		ioc_err(ioc, "failure at %s:%d/%s()!\n",
diff --git a/drivers/scsi/mpt3sas/mpt3sas_trigger_pages.h b/drivers/scsi/mpt3sas/mpt3sas_trigger_pages.h
index 5f3328f011a2..edb8fe709089 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_trigger_pages.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_trigger_pages.h
@@ -20,12 +20,12 @@
 
 #define MPI2_CONFIG_EXTPAGETYPE_DRIVER_PERSISTENT_TRIGGER    (0xE0)
 #define MPI26_DRIVER_TRIGGER_PAGE0_PAGEVERSION               (0x01)
-typedef struct _MPI26_CONFIG_PAGE_DRIVER_TIGGER_0 {
+typedef struct _MPI26_CONFIG_PAGE_DRIVER_TRIGGER_0 {
 	MPI2_CONFIG_EXTENDED_PAGE_HEADER	Header;	/* 0x00  */
 	U16	TriggerFlags;		/* 0x08  */
 	U16	Reserved0xA;		/* 0x0A */
 	U32	Reserved0xC[61];	/* 0x0C */
-} _MPI26_CONFIG_PAGE_DRIVER_TIGGER_0, Mpi26DriverTriggerPage0_t;
+} _MPI26_CONFIG_PAGE_DRIVER_TRIGGER_0, Mpi26DriverTriggerPage0_t;
 
 /* Trigger Flags */
 #define  MPI26_DRIVER_TRIGGER0_FLAG_MASTER_TRIGGER_VALID       (0x0001)
@@ -34,61 +34,61 @@ typedef struct _MPI26_CONFIG_PAGE_DRIVER_TIGGER_0 {
 #define  MPI26_DRIVER_TRIGGER0_FLAG_LOGINFO_TRIGGER_VALID      (0x0008)
 
 #define MPI26_DRIVER_TRIGGER_PAGE1_PAGEVERSION               (0x01)
-typedef struct _MPI26_DRIVER_MASTER_TIGGER_ENTRY {
+typedef struct _MPI26_DRIVER_MASTER_TRIGGER_ENTRY {
 	U32	MasterTriggerFlags;
-} MPI26_DRIVER_MASTER_TIGGER_ENTRY;
+} MPI26_DRIVER_MASTER_TRIGGER_ENTRY;
 
 #define MPI26_MAX_MASTER_TRIGGERS                                   (1)
-typedef struct _MPI26_CONFIG_PAGE_DRIVER_TIGGER_1 {
+typedef struct _MPI26_CONFIG_PAGE_DRIVER_TRIGGER_1 {
 	MPI2_CONFIG_EXTENDED_PAGE_HEADER	Header;	/* 0x00 */
 	U16	NumMasterTrigger;	/* 0x08 */
 	U16	Reserved0xA;		/* 0x0A */
-	MPI26_DRIVER_MASTER_TIGGER_ENTRY MasterTriggers[MPI26_MAX_MASTER_TRIGGERS];	/* 0x0C */
-} MPI26_CONFIG_PAGE_DRIVER_TIGGER_1, Mpi26DriverTriggerPage1_t;
+	MPI26_DRIVER_MASTER_TRIGGER_ENTRY MasterTriggers[MPI26_MAX_MASTER_TRIGGERS];	/* 0x0C */
+} MPI26_CONFIG_PAGE_DRIVER_TRIGGER_1, Mpi26DriverTriggerPage1_t;
 
 #define MPI26_DRIVER_TRIGGER_PAGE2_PAGEVERSION               (0x01)
-typedef struct _MPI26_DRIVER_MPI_EVENT_TIGGER_ENTRY {
+typedef struct _MPI26_DRIVER_MPI_EVENT_TRIGGER_ENTRY {
 	U16	MPIEventCode;		/* 0x00 */
 	U16	MPIEventCodeSpecific;	/* 0x02 */
-} MPI26_DRIVER_MPI_EVENT_TIGGER_ENTRY;
+} MPI26_DRIVER_MPI_EVENT_TRIGGER_ENTRY;
 
 #define MPI26_MAX_MPI_EVENT_TRIGGERS                            (20)
-typedef struct _MPI26_CONFIG_PAGE_DRIVER_TIGGER_2 {
+typedef struct _MPI26_CONFIG_PAGE_DRIVER_TRIGGER_2 {
 	MPI2_CONFIG_EXTENDED_PAGE_HEADER        Header;	/* 0x00  */
 	U16	NumMPIEventTrigger;     /* 0x08  */
 	U16	Reserved0xA;		/* 0x0A */
-	MPI26_DRIVER_MPI_EVENT_TIGGER_ENTRY MPIEventTriggers[MPI26_MAX_MPI_EVENT_TRIGGERS]; /* 0x0C */
-} MPI26_CONFIG_PAGE_DRIVER_TIGGER_2, Mpi26DriverTriggerPage2_t;
+	MPI26_DRIVER_MPI_EVENT_TRIGGER_ENTRY MPIEventTriggers[MPI26_MAX_MPI_EVENT_TRIGGERS]; /* 0x0C */
+} MPI26_CONFIG_PAGE_DRIVER_TRIGGER_2, Mpi26DriverTriggerPage2_t;
 
 #define MPI26_DRIVER_TRIGGER_PAGE3_PAGEVERSION               (0x01)
-typedef struct _MPI26_DRIVER_SCSI_SENSE_TIGGER_ENTRY {
+typedef struct _MPI26_DRIVER_SCSI_SENSE_TRIGGER_ENTRY {
 	U8     ASCQ;		/* 0x00 */
 	U8     ASC;		/* 0x01 */
 	U8     SenseKey;	/* 0x02 */
 	U8     Reserved;	/* 0x03 */
-} MPI26_DRIVER_SCSI_SENSE_TIGGER_ENTRY;
+} MPI26_DRIVER_SCSI_SENSE_TRIGGER_ENTRY;
 
 #define MPI26_MAX_SCSI_SENSE_TRIGGERS                            (20)
-typedef struct _MPI26_CONFIG_PAGE_DRIVER_TIGGER_3 {
+typedef struct _MPI26_CONFIG_PAGE_DRIVER_TRIGGER_3 {
 	MPI2_CONFIG_EXTENDED_PAGE_HEADER	Header;	/* 0x00  */
 	U16	NumSCSISenseTrigger;			/* 0x08  */
 	U16	Reserved0xA;				/* 0x0A */
-	MPI26_DRIVER_SCSI_SENSE_TIGGER_ENTRY SCSISenseTriggers[MPI26_MAX_SCSI_SENSE_TRIGGERS];	/* 0x0C */
-} MPI26_CONFIG_PAGE_DRIVER_TIGGER_3, Mpi26DriverTriggerPage3_t;
+	MPI26_DRIVER_SCSI_SENSE_TRIGGER_ENTRY SCSISenseTriggers[MPI26_MAX_SCSI_SENSE_TRIGGERS];	/* 0x0C */
+} MPI26_CONFIG_PAGE_DRIVER_TRIGGER_3, Mpi26DriverTriggerPage3_t;
 
 #define MPI26_DRIVER_TRIGGER_PAGE4_PAGEVERSION               (0x01)
-typedef struct _MPI26_DRIVER_IOCSTATUS_LOGINFO_TIGGER_ENTRY {
+typedef struct _MPI26_DRIVER_IOCSTATUS_LOGINFO_TRIGGER_ENTRY {
 	U16        IOCStatus;      /* 0x00 */
 	U16        Reserved;       /* 0x02 */
 	U32        LogInfo;        /* 0x04 */
-} MPI26_DRIVER_IOCSTATUS_LOGINFO_TIGGER_ENTRY;
+} MPI26_DRIVER_IOCSTATUS_LOGINFO_TRIGGER_ENTRY;
 
 #define MPI26_MAX_LOGINFO_TRIGGERS                            (20)
-typedef struct _MPI26_CONFIG_PAGE_DRIVER_TIGGER_4 {
+typedef struct _MPI26_CONFIG_PAGE_DRIVER_TRIGGER_4 {
 	MPI2_CONFIG_EXTENDED_PAGE_HEADER	Header;	/* 0x00  */
 	U16	NumIOCStatusLogInfoTrigger;		/* 0x08  */
 	U16	Reserved0xA;				/* 0x0A */
-	MPI26_DRIVER_IOCSTATUS_LOGINFO_TIGGER_ENTRY IOCStatusLoginfoTriggers[MPI26_MAX_LOGINFO_TRIGGERS];	/* 0x0C */
-} MPI26_CONFIG_PAGE_DRIVER_TIGGER_4, Mpi26DriverTriggerPage4_t;
+	MPI26_DRIVER_IOCSTATUS_LOGINFO_TRIGGER_ENTRY IOCStatusLoginfoTriggers[MPI26_MAX_LOGINFO_TRIGGERS];	/* 0x0C */
+} MPI26_CONFIG_PAGE_DRIVER_TRIGGER_4, Mpi26DriverTriggerPage4_t;
 
 #endif
diff --git a/drivers/scsi/mpt3sas/mpt3sas_warpdrive.c b/drivers/scsi/mpt3sas/mpt3sas_warpdrive.c
index cc07ba41f507..1d64e5056a8a 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_warpdrive.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_warpdrive.c
@@ -141,8 +141,7 @@ mpt3sas_init_warpdrive_properties(struct MPT3SAS_ADAPTER *ioc,
 		return;
 	}
 
-	sz = offsetof(Mpi2RaidVolPage0_t, PhysDisk) + (num_pds *
-	    sizeof(Mpi2RaidVol0PhysDisk_t));
+	sz = struct_size(vol_pg0, PhysDisk, num_pds);
 	vol_pg0 = kzalloc(sz, GFP_KERNEL);
 	if (!vol_pg0) {
 		ioc_info(ioc, "WarpDrive : Direct IO is disabled Memory allocation failure for RVPG0\n");
diff --git a/drivers/scsi/mvme16x_scsi.c b/drivers/scsi/mvme16x_scsi.c
index 21d638299ab8..e08a38e2a442 100644
--- a/drivers/scsi/mvme16x_scsi.c
+++ b/drivers/scsi/mvme16x_scsi.c
@@ -103,7 +103,7 @@ static int mvme16x_probe(struct platform_device *dev)
 	return -ENODEV;
 }
 
-static int mvme16x_device_remove(struct platform_device *dev)
+static void mvme16x_device_remove(struct platform_device *dev)
 {
 	struct Scsi_Host *host = platform_get_drvdata(dev);
 	struct NCR_700_Host_Parameters *hostdata = shost_priv(host);
@@ -120,8 +120,6 @@ static int mvme16x_device_remove(struct platform_device *dev)
 	NCR_700_release(host);
 	kfree(hostdata);
 	free_irq(host->irq, host);
-
-	return 0;
 }
 
 static struct platform_driver mvme16x_scsi_driver = {
@@ -129,7 +127,7 @@ static struct platform_driver mvme16x_scsi_driver = {
 		.name           = "mvme16x-scsi",
 	},
 	.probe          = mvme16x_probe,
-	.remove         = mvme16x_device_remove,
+	.remove_new     = mvme16x_device_remove,
 };
 
 static int __init mvme16x_scsi_init(void)
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 32d1e73e46ee..03348f605c2e 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1837,8 +1837,16 @@ static void qla2x00_abort_srb(struct qla_qpair *qp, srb_t *sp, const int res,
 		}
 
 		spin_lock_irqsave(qp->qp_lock_ptr, *flags);
-		if (ret_cmd && blk_mq_request_started(scsi_cmd_to_rq(cmd)))
-			sp->done(sp, res);
+		switch (sp->type) {
+		case SRB_SCSI_CMD:
+			if (ret_cmd && blk_mq_request_started(scsi_cmd_to_rq(cmd)))
+				sp->done(sp, res);
+			break;
+		default:
+			if (ret_cmd)
+				sp->done(sp, res);
+			break;
+		}
 	} else {
 		sp->done(sp, res);
 	}
diff --git a/drivers/scsi/qlogicpti.c b/drivers/scsi/qlogicpti.c
index 3b95f7a6216f..5d560d9b8944 100644
--- a/drivers/scsi/qlogicpti.c
+++ b/drivers/scsi/qlogicpti.c
@@ -1409,7 +1409,7 @@ fail_unlink:
 	return -ENODEV;
 }
 
-static int qpti_sbus_remove(struct platform_device *op)
+static void qpti_sbus_remove(struct platform_device *op)
 {
 	struct qlogicpti *qpti = dev_get_drvdata(&op->dev);
 
@@ -1438,8 +1438,6 @@ static int qpti_sbus_remove(struct platform_device *op)
 		of_iounmap(&op->resource[0], qpti->sreg, sizeof(unsigned char));
 
 	scsi_host_put(qpti->qhost);
-
-	return 0;
 }
 
 static const struct of_device_id qpti_match[] = {
@@ -1465,7 +1463,7 @@ static struct platform_driver qpti_sbus_driver = {
 		.of_match_table = qpti_match,
 	},
 	.probe		= qpti_sbus_probe,
-	.remove		= qpti_sbus_remove,
+	.remove_new	= qpti_sbus_remove,
 };
 module_platform_driver(qpti_sbus_driver);
 
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 67922e2c4c19..d03d66f11493 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -339,7 +339,7 @@ struct sdebug_dev_info {
 	bool used;
 
 	/* For ZBC devices */
-	enum blk_zoned_model zmodel;
+	bool zoned;
 	unsigned int zcap;
 	unsigned int zsize;
 	unsigned int zsize_shift;
@@ -844,8 +844,11 @@ static bool write_since_sync;
 static bool sdebug_statistics = DEF_STATISTICS;
 static bool sdebug_wp;
 static bool sdebug_allow_restart;
-/* Following enum: 0: no zbc, def; 1: host aware; 2: host managed */
-static enum blk_zoned_model sdeb_zbc_model = BLK_ZONED_NONE;
+static enum {
+	BLK_ZONED_NONE	= 0,
+	BLK_ZONED_HA	= 1,
+	BLK_ZONED_HM	= 2,
+} sdeb_zbc_model = BLK_ZONED_NONE;
 static char *sdeb_zbc_model_s;
 
 enum sam_lun_addr_method {SAM_LUN_AM_PERIPHERAL = 0x0,
@@ -1019,7 +1022,7 @@ static ssize_t sdebug_error_write(struct file *file, const char __user *ubuf,
 	struct sdebug_err_inject *inject;
 	struct scsi_device *sdev = (struct scsi_device *)file->f_inode->i_private;
 
-	buf = kmalloc(count, GFP_KERNEL);
+	buf = kzalloc(count + 1, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
@@ -1132,7 +1135,6 @@ static const struct file_operations sdebug_target_reset_fail_fops = {
 static int sdebug_target_alloc(struct scsi_target *starget)
 {
 	struct sdebug_target_info *targetip;
-	struct dentry *dentry;
 
 	targetip = kzalloc(sizeof(struct sdebug_target_info), GFP_KERNEL);
 	if (!targetip)
@@ -1140,15 +1142,9 @@ static int sdebug_target_alloc(struct scsi_target *starget)
 
 	targetip->debugfs_entry = debugfs_create_dir(dev_name(&starget->dev),
 				sdebug_debugfs_root);
-	if (IS_ERR_OR_NULL(targetip->debugfs_entry))
-		pr_info("%s: failed to create debugfs directory for target %s\n",
-			__func__, dev_name(&starget->dev));
 
 	debugfs_create_file("fail_reset", 0600, targetip->debugfs_entry, starget,
 				&sdebug_target_reset_fail_fops);
-	if (IS_ERR_OR_NULL(dentry))
-		pr_info("%s: failed to create fail_reset file for target %s\n",
-			__func__, dev_name(&starget->dev));
 
 	starget->hostdata = targetip;
 
@@ -1822,8 +1818,6 @@ static int inquiry_vpd_b1(struct sdebug_dev_info *devip, unsigned char *arr)
 	arr[1] = 1;	/* non rotating medium (e.g. solid state) */
 	arr[2] = 0;
 	arr[3] = 5;	/* less than 1.8" */
-	if (devip->zmodel == BLK_ZONED_HA)
-		arr[4] = 1 << 4;	/* zoned field = 01b */
 
 	return 0x3c;
 }
@@ -1890,7 +1884,7 @@ static int resp_inquiry(struct scsi_cmnd *scp, struct sdebug_dev_info *devip)
 	if (! arr)
 		return DID_REQUEUE << 16;
 	is_disk = (sdebug_ptype == TYPE_DISK);
-	is_zbc = (devip->zmodel != BLK_ZONED_NONE);
+	is_zbc = devip->zoned;
 	is_disk_zbc = (is_disk || is_zbc);
 	have_wlun = scsi_is_wlun(scp->device->lun);
 	if (have_wlun)
@@ -2202,7 +2196,7 @@ static int resp_readcap16(struct scsi_cmnd *scp,
 	 * Since the scsi_debug READ CAPACITY implementation always reports the
 	 * total disk capacity, set RC BASIS = 1 for host-managed ZBC devices.
 	 */
-	if (devip->zmodel == BLK_ZONED_HM)
+	if (devip->zoned)
 		arr[12] |= 1 << 4;
 
 	arr[15] = sdebug_lowest_aligned & 0xff;
@@ -2655,7 +2649,7 @@ static int resp_mode_sense(struct scsi_cmnd *scp,
 	msense_6 = (MODE_SENSE == cmd[0]);
 	llbaa = msense_6 ? false : !!(cmd[1] & 0x10);
 	is_disk = (sdebug_ptype == TYPE_DISK);
-	is_zbc = (devip->zmodel != BLK_ZONED_NONE);
+	is_zbc = devip->zoned;
 	if ((is_disk || is_zbc) && !dbd)
 		bd_len = llbaa ? 16 : 8;
 	else
@@ -3201,8 +3195,6 @@ static int check_zbc_access_params(struct scsi_cmnd *scp,
 	struct sdeb_zone_state *zsp_end = zbc_zone(devip, lba + num - 1);
 
 	if (!write) {
-		if (devip->zmodel == BLK_ZONED_HA)
-			return 0;
 		/* For host-managed, reads cannot cross zone types boundaries */
 		if (zsp->z_type != zsp_end->z_type) {
 			mk_sense_buffer(scp, ILLEGAL_REQUEST,
@@ -5329,7 +5321,7 @@ static int sdebug_device_create_zones(struct sdebug_dev_info *devip)
 	if (devip->zcap < devip->zsize)
 		devip->nr_zones += devip->nr_seq_zones;
 
-	if (devip->zmodel == BLK_ZONED_HM) {
+	if (devip->zoned) {
 		/* zbc_max_open_zones can be 0, meaning "not reported" */
 		if (sdeb_zbc_max_open >= devip->nr_zones - 1)
 			devip->max_open = (devip->nr_zones - 1) / 2;
@@ -5354,7 +5346,7 @@ static int sdebug_device_create_zones(struct sdebug_dev_info *devip)
 			zsp->z_size =
 				min_t(u64, devip->zsize, capacity - zstart);
 		} else if ((zstart & (devip->zsize - 1)) == 0) {
-			if (devip->zmodel == BLK_ZONED_HM)
+			if (devip->zoned)
 				zsp->z_type = ZBC_ZTYPE_SWR;
 			else
 				zsp->z_type = ZBC_ZTYPE_SWP;
@@ -5397,13 +5389,13 @@ static struct sdebug_dev_info *sdebug_device_create(
 		}
 		devip->sdbg_host = sdbg_host;
 		if (sdeb_zbc_in_use) {
-			devip->zmodel = sdeb_zbc_model;
+			devip->zoned = sdeb_zbc_model == BLK_ZONED_HM;
 			if (sdebug_device_create_zones(devip)) {
 				kfree(devip);
 				return NULL;
 			}
 		} else {
-			devip->zmodel = BLK_ZONED_NONE;
+			devip->zoned = false;
 		}
 		devip->create_ts = ktime_get_boottime();
 		atomic_set(&devip->stopped, (sdeb_tur_ms_to_ready > 0 ? 2 : 0));
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index c67cdcdc3ba8..885a7d5df3b9 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -301,6 +301,7 @@ void scsi_eh_scmd_add(struct scsi_cmnd *scmd)
 	int ret;
 
 	WARN_ON_ONCE(!shost->ehandler);
+	WARN_ON_ONCE(!test_bit(SCMD_STATE_INFLIGHT, &scmd->state));
 
 	spin_lock_irqsave(shost->host_lock, flags);
 	if (scsi_host_set_state(shost, SHOST_RECOVERY)) {
@@ -1152,6 +1153,7 @@ retry:
 
 	scsi_log_send(scmd);
 	scmd->submitter = SUBMITTED_BY_SCSI_ERROR_HANDLER;
+	scmd->flags |= SCMD_LAST;
 
 	/*
 	 * Lock sdev->state_mutex to avoid that scsi_device_quiesce() can
@@ -2459,6 +2461,7 @@ scsi_ioctl_reset(struct scsi_device *dev, int __user *arg)
 	scsi_init_command(dev, scmd);
 
 	scmd->submitter = SUBMITTED_BY_SCSI_RESET_IOCTL;
+	scmd->flags |= SCMD_LAST;
 	memset(&scmd->sdb, 0, sizeof(scmd->sdb));
 
 	scmd->cmd_len			= 0;
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 530918cbfce2..0833b3e6aa6e 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1643,24 +1643,21 @@ out:
 	return disk_changed ? DISK_EVENT_MEDIA_CHANGE : 0;
 }
 
-static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr)
+static int sd_sync_cache(struct scsi_disk *sdkp)
 {
 	int retries, res;
 	struct scsi_device *sdp = sdkp->device;
 	const int timeout = sdp->request_queue->rq_timeout
 		* SD_FLUSH_TIMEOUT_MULTIPLIER;
-	struct scsi_sense_hdr my_sshdr;
+	struct scsi_sense_hdr sshdr;
 	const struct scsi_exec_args exec_args = {
 		.req_flags = BLK_MQ_REQ_PM,
-		/* caller might not be interested in sense, but we need it */
-		.sshdr = sshdr ? : &my_sshdr,
+		.sshdr = &sshdr,
 	};
 
 	if (!scsi_device_online(sdp))
 		return -ENODEV;
 
-	sshdr = exec_args.sshdr;
-
 	for (retries = 3; retries > 0; --retries) {
 		unsigned char cmd[16] = { 0 };
 
@@ -1685,15 +1682,23 @@ static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr)
 			return res;
 
 		if (scsi_status_is_check_condition(res) &&
-		    scsi_sense_valid(sshdr)) {
-			sd_print_sense_hdr(sdkp, sshdr);
+		    scsi_sense_valid(&sshdr)) {
+			sd_print_sense_hdr(sdkp, &sshdr);
 
 			/* we need to evaluate the error return  */
-			if (sshdr->asc == 0x3a ||	/* medium not present */
-			    sshdr->asc == 0x20 ||	/* invalid command */
-			    (sshdr->asc == 0x74 && sshdr->ascq == 0x71))	/* drive is password locked */
+			if (sshdr.asc == 0x3a ||	/* medium not present */
+			    sshdr.asc == 0x20 ||	/* invalid command */
+			    (sshdr.asc == 0x74 && sshdr.ascq == 0x71))	/* drive is password locked */
 				/* this is no error here */
 				return 0;
+			/*
+			 * This drive doesn't support sync and there's not much
+			 * we can do because this is called during shutdown
+			 * or suspend so just return success so those operations
+			 * can proceed.
+			 */
+			if (sshdr.sense_key == ILLEGAL_REQUEST)
+				return 0;
 		}
 
 		switch (host_byte(res)) {
@@ -3112,7 +3117,6 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp)
 	struct request_queue *q = sdkp->disk->queue;
 	struct scsi_vpd *vpd;
 	u16 rot;
-	u8 zoned;
 
 	rcu_read_lock();
 	vpd = rcu_dereference(sdkp->device->vpd_pgb1);
@@ -3123,7 +3127,7 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp)
 	}
 
 	rot = get_unaligned_be16(&vpd->data[4]);
-	zoned = (vpd->data[8] >> 4) & 3;
+	sdkp->zoned = (vpd->data[8] >> 4) & 3;
 	rcu_read_unlock();
 
 	if (rot == 1) {
@@ -3131,39 +3135,37 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp)
 		blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q);
 	}
 
+
+#ifdef CONFIG_BLK_DEV_ZONED /* sd_probe rejects ZBD devices early otherwise */
 	if (sdkp->device->type == TYPE_ZBC) {
 		/*
-		 * Host-managed: Per ZBC and ZAC specifications, writes in
-		 * sequential write required zones of host-managed devices must
-		 * be aligned to the device physical block size.
+		 * Host-managed.
+		 */
+		disk_set_zoned(sdkp->disk);
+
+		/*
+		 * Per ZBC and ZAC specifications, writes in sequential write
+		 * required zones of host-managed devices must be aligned to
+		 * the device physical block size.
 		 */
-		disk_set_zoned(sdkp->disk, BLK_ZONED_HM);
 		blk_queue_zone_write_granularity(q, sdkp->physical_block_size);
 	} else {
-		sdkp->zoned = zoned;
-		if (sdkp->zoned == 1) {
-			/* Host-aware */
-			disk_set_zoned(sdkp->disk, BLK_ZONED_HA);
-		} else {
-			/* Regular disk or drive managed disk */
-			disk_set_zoned(sdkp->disk, BLK_ZONED_NONE);
-		}
+		/*
+		 * Host-aware devices are treated as conventional.
+		 */
+		WARN_ON_ONCE(blk_queue_is_zoned(q));
 	}
+#endif /* CONFIG_BLK_DEV_ZONED */
 
 	if (!sdkp->first_scan)
 		return;
 
-	if (blk_queue_is_zoned(q)) {
-		sd_printk(KERN_NOTICE, sdkp, "Host-%s zoned block device\n",
-		      q->limits.zoned == BLK_ZONED_HM ? "managed" : "aware");
-	} else {
-		if (sdkp->zoned == 1)
-			sd_printk(KERN_NOTICE, sdkp,
-				  "Host-aware SMR disk used as regular disk\n");
-		else if (sdkp->zoned == 2)
-			sd_printk(KERN_NOTICE, sdkp,
-				  "Drive-managed SMR disk\n");
-	}
+	if (blk_queue_is_zoned(q))
+		sd_printk(KERN_NOTICE, sdkp, "Host-managed zoned block device\n");
+	else if (sdkp->zoned == 1)
+		sd_printk(KERN_NOTICE, sdkp, "Host-aware SMR disk used as regular disk\n");
+	else if (sdkp->zoned == 2)
+		sd_printk(KERN_NOTICE, sdkp, "Drive-managed SMR disk\n");
 }
 
 /**
@@ -3497,7 +3499,7 @@ static int sd_revalidate_disk(struct gendisk *disk)
 	} else {
 		q->limits.io_opt = 0;
 		rw_max = min_not_zero(logical_to_sectors(sdp, dev_max),
-				      (sector_t)BLK_DEF_MAX_SECTORS);
+				      (sector_t)BLK_DEF_MAX_SECTORS_CAP);
 	}
 
 	/*
@@ -3853,7 +3855,7 @@ static void sd_shutdown(struct device *dev)
 
 	if (sdkp->WCE && sdkp->media_present) {
 		sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n");
-		sd_sync_cache(sdkp, NULL);
+		sd_sync_cache(sdkp);
 	}
 
 	if ((system_state != SYSTEM_RESTART &&
@@ -3874,7 +3876,6 @@ static inline bool sd_do_start_stop(struct scsi_device *sdev, bool runtime)
 static int sd_suspend_common(struct device *dev, bool runtime)
 {
 	struct scsi_disk *sdkp = dev_get_drvdata(dev);
-	struct scsi_sense_hdr sshdr;
 	int ret = 0;
 
 	if (!sdkp)	/* E.g.: runtime suspend following sd_remove() */
@@ -3883,24 +3884,13 @@ static int sd_suspend_common(struct device *dev, bool runtime)
 	if (sdkp->WCE && sdkp->media_present) {
 		if (!sdkp->device->silence_suspend)
 			sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n");
-		ret = sd_sync_cache(sdkp, &sshdr);
-
-		if (ret) {
-			/* ignore OFFLINE device */
-			if (ret == -ENODEV)
-				return 0;
-
-			if (!scsi_sense_valid(&sshdr) ||
-			    sshdr.sense_key != ILLEGAL_REQUEST)
-				return ret;
+		ret = sd_sync_cache(sdkp);
+		/* ignore OFFLINE device */
+		if (ret == -ENODEV)
+			return 0;
 
-			/*
-			 * sshdr.sense_key == ILLEGAL_REQUEST means this drive
-			 * doesn't support sync. There's not much to do and
-			 * suspend shouldn't fail.
-			 */
-			ret = 0;
-		}
+		if (ret)
+			return ret;
 	}
 
 	if (sd_do_start_stop(sdkp->device, runtime)) {
@@ -3956,8 +3946,15 @@ static int sd_resume(struct device *dev, bool runtime)
 
 static int sd_resume_system(struct device *dev)
 {
-	if (pm_runtime_suspended(dev))
+	if (pm_runtime_suspended(dev)) {
+		struct scsi_disk *sdkp = dev_get_drvdata(dev);
+		struct scsi_device *sdp = sdkp ? sdkp->device : NULL;
+
+		if (sdp && sdp->force_runtime_start_on_system_start)
+			pm_request_resume(dev);
+
 		return 0;
+	}
 
 	return sd_resume(dev, false);
 }
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index a25215507668..26af5ab7d7c1 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -836,10 +836,7 @@ int sd_zbc_revalidate_zones(struct scsi_disk *sdkp)
 
 	/*
 	 * For all zoned disks, initialize zone append emulation data if not
-	 * already done. This is necessary also for host-aware disks used as
-	 * regular disks due to the presence of partitions as these partitions
-	 * may be deleted and the disk zoned model changed back from
-	 * BLK_ZONED_NONE to BLK_ZONED_HA.
+	 * already done.
 	 */
 	if (sd_is_zoned(sdkp) && !sdkp->zone_wp_update_buf) {
 		ret = sd_zbc_init_disk(sdkp);
@@ -932,17 +929,6 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, u8 buf[SD_BUF_SIZE])
 	sdkp->device->use_10_for_rw = 0;
 	sdkp->device->use_16_for_sync = 1;
 
-	if (!blk_queue_is_zoned(q)) {
-		/*
-		 * This can happen for a host aware disk with partitions.
-		 * The block device zone model was already cleared by
-		 * disk_set_zoned(). Only free the scsi disk zone
-		 * information and exit early.
-		 */
-		sd_zbc_free_zone_info(sdkp);
-		return 0;
-	}
-
 	/* Check zoned block device characteristics (unconstrained reads) */
 	ret = sd_zbc_check_zoned_characteristics(sdkp, buf);
 	if (ret)
diff --git a/drivers/scsi/sgiwd93.c b/drivers/scsi/sgiwd93.c
index 88e2b5eb9caa..b0bef83db7b6 100644
--- a/drivers/scsi/sgiwd93.c
+++ b/drivers/scsi/sgiwd93.c
@@ -291,7 +291,7 @@ out:
 	return err;
 }
 
-static int sgiwd93_remove(struct platform_device *pdev)
+static void sgiwd93_remove(struct platform_device *pdev)
 {
 	struct Scsi_Host *host = platform_get_drvdata(pdev);
 	struct ip22_hostdata *hdata = (struct ip22_hostdata *) host->hostdata;
@@ -302,12 +302,11 @@ static int sgiwd93_remove(struct platform_device *pdev)
 	dma_free_noncoherent(&pdev->dev, HPC_DMA_SIZE, hdata->cpu, hdata->dma,
 			DMA_TO_DEVICE);
 	scsi_host_put(host);
-	return 0;
 }
 
 static struct platform_driver sgiwd93_driver = {
 	.probe  = sgiwd93_probe,
-	.remove = sgiwd93_remove,
+	.remove_new = sgiwd93_remove,
 	.driver = {
 		.name   = "sgiwd93",
 	}
diff --git a/drivers/scsi/sni_53c710.c b/drivers/scsi/sni_53c710.c
index 678651b9b4dd..9df1c90a24c1 100644
--- a/drivers/scsi/sni_53c710.c
+++ b/drivers/scsi/sni_53c710.c
@@ -104,7 +104,7 @@ static int snirm710_probe(struct platform_device *dev)
 	return -ENODEV;
 }
 
-static int snirm710_driver_remove(struct platform_device *dev)
+static void snirm710_driver_remove(struct platform_device *dev)
 {
 	struct Scsi_Host *host = dev_get_drvdata(&dev->dev);
 	struct NCR_700_Host_Parameters *hostdata =
@@ -115,13 +115,11 @@ static int snirm710_driver_remove(struct platform_device *dev)
 	free_irq(host->irq, host);
 	iounmap(hostdata->base);
 	kfree(hostdata);
-
-	return 0;
 }
 
 static struct platform_driver snirm710_driver = {
 	.probe	= snirm710_probe,
-	.remove	= snirm710_driver_remove,
+	.remove_new = snirm710_driver_remove,
 	.driver	= {
 		.name	= "snirm_53c710",
 	},
diff --git a/drivers/scsi/sun3_scsi.c b/drivers/scsi/sun3_scsi.c
index abf229b847a1..4a8cc2e8238e 100644
--- a/drivers/scsi/sun3_scsi.c
+++ b/drivers/scsi/sun3_scsi.c
@@ -641,7 +641,7 @@ fail_alloc:
 	return error;
 }
 
-static int __exit sun3_scsi_remove(struct platform_device *pdev)
+static void __exit sun3_scsi_remove(struct platform_device *pdev)
 {
 	struct Scsi_Host *instance = platform_get_drvdata(pdev);
 	struct NCR5380_hostdata *hostdata = shost_priv(instance);
@@ -654,11 +654,10 @@ static int __exit sun3_scsi_remove(struct platform_device *pdev)
 	if (udc_regs)
 		dvma_free(udc_regs);
 	iounmap(ioaddr);
-	return 0;
 }
 
 static struct platform_driver sun3_scsi_driver = {
-	.remove = __exit_p(sun3_scsi_remove),
+	.remove_new = __exit_p(sun3_scsi_remove),
 	.driver = {
 		.name	= DRV_MODULE_NAME,
 	},
diff --git a/drivers/scsi/sun3x_esp.c b/drivers/scsi/sun3x_esp.c
index 30f67cbf4a7a..09219c362acc 100644
--- a/drivers/scsi/sun3x_esp.c
+++ b/drivers/scsi/sun3x_esp.c
@@ -243,7 +243,7 @@ fail:
 	return err;
 }
 
-static int esp_sun3x_remove(struct platform_device *dev)
+static void esp_sun3x_remove(struct platform_device *dev)
 {
 	struct esp *esp = dev_get_drvdata(&dev->dev);
 	unsigned int irq = esp->host->irq;
@@ -261,13 +261,11 @@ static int esp_sun3x_remove(struct platform_device *dev)
 			  esp->command_block_dma);
 
 	scsi_host_put(esp->host);
-
-	return 0;
 }
 
 static struct platform_driver esp_sun3x_driver = {
 	.probe          = esp_sun3x_probe,
-	.remove         = esp_sun3x_remove,
+	.remove_new     = esp_sun3x_remove,
 	.driver = {
 		.name   = "sun3x_esp",
 	},
diff --git a/drivers/scsi/sun_esp.c b/drivers/scsi/sun_esp.c
index afa9d02a33ec..64a7c2c6c5ff 100644
--- a/drivers/scsi/sun_esp.c
+++ b/drivers/scsi/sun_esp.c
@@ -550,7 +550,7 @@ static int esp_sbus_probe(struct platform_device *op)
 	return ret;
 }
 
-static int esp_sbus_remove(struct platform_device *op)
+static void esp_sbus_remove(struct platform_device *op)
 {
 	struct esp *esp = dev_get_drvdata(&op->dev);
 	struct platform_device *dma_of = esp->dma;
@@ -581,8 +581,6 @@ static int esp_sbus_remove(struct platform_device *op)
 	dev_set_drvdata(&op->dev, NULL);
 
 	put_device(&dma_of->dev);
-
-	return 0;
 }
 
 static const struct of_device_id esp_match[] = {
@@ -605,7 +603,7 @@ static struct platform_driver esp_sbus_driver = {
 		.of_match_table = esp_match,
 	},
 	.probe		= esp_sbus_probe,
-	.remove		= esp_sbus_remove,
+	.remove_new	= esp_sbus_remove,
 };
 module_platform_driver(esp_sbus_driver);
 
diff --git a/drivers/soc/Kconfig b/drivers/soc/Kconfig
index 10a9ff84ff41..5d924e946507 100644
--- a/drivers/soc/Kconfig
+++ b/drivers/soc/Kconfig
@@ -22,7 +22,6 @@ source "drivers/soc/qcom/Kconfig"
 source "drivers/soc/renesas/Kconfig"
 source "drivers/soc/rockchip/Kconfig"
 source "drivers/soc/samsung/Kconfig"
-source "drivers/soc/sifive/Kconfig"
 source "drivers/soc/sunxi/Kconfig"
 source "drivers/soc/tegra/Kconfig"
 source "drivers/soc/ti/Kconfig"
diff --git a/drivers/soc/Makefile b/drivers/soc/Makefile
index 0706a27d13be..ba8f5b5460e1 100644
--- a/drivers/soc/Makefile
+++ b/drivers/soc/Makefile
@@ -28,7 +28,6 @@ obj-y				+= qcom/
 obj-y				+= renesas/
 obj-y				+= rockchip/
 obj-$(CONFIG_SOC_SAMSUNG)	+= samsung/
-obj-y				+= sifive/
 obj-y				+= sunxi/
 obj-$(CONFIG_ARCH_TEGRA)	+= tegra/
 obj-y				+= ti/
diff --git a/drivers/soc/apple/Kconfig b/drivers/soc/apple/Kconfig
index eff486a77337..6388cbe1e56b 100644
--- a/drivers/soc/apple/Kconfig
+++ b/drivers/soc/apple/Kconfig
@@ -4,9 +4,22 @@ if ARCH_APPLE || COMPILE_TEST
 
 menu "Apple SoC drivers"
 
+config APPLE_MAILBOX
+	tristate "Apple SoC mailboxes"
+	depends on PM
+	depends on ARCH_APPLE || (64BIT && COMPILE_TEST)
+	default ARCH_APPLE
+	help
+	  Apple SoCs have various co-processors required for certain
+	  peripherals to work (NVMe, display controller, etc.). This
+	  driver adds support for the mailbox controller used to
+	  communicate with those.
+
+	  Say Y here if you have an Apple SoC.
+
 config APPLE_RTKIT
 	tristate "Apple RTKit co-processor IPC protocol"
-	depends on MAILBOX
+	depends on APPLE_MAILBOX
 	depends on ARCH_APPLE || COMPILE_TEST
 	default ARCH_APPLE
 	help
diff --git a/drivers/soc/apple/Makefile b/drivers/soc/apple/Makefile
index b241e6a65e5b..4d9ab8f3037b 100644
--- a/drivers/soc/apple/Makefile
+++ b/drivers/soc/apple/Makefile
@@ -1,4 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_APPLE_MAILBOX) += apple-mailbox.o
+apple-mailbox-y = mailbox.o
+
 obj-$(CONFIG_APPLE_RTKIT) += apple-rtkit.o
 apple-rtkit-y = rtkit.o rtkit-crashlog.o
 
diff --git a/drivers/soc/apple/mailbox.c b/drivers/soc/apple/mailbox.c
new file mode 100644
index 000000000000..780199bf351e
--- /dev/null
+++ b/drivers/soc/apple/mailbox.c
@@ -0,0 +1,437 @@
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/*
+ * Apple mailbox driver
+ *
+ * Copyright The Asahi Linux Contributors
+ *
+ * This driver adds support for two mailbox variants (called ASC and M3 by
+ * Apple) found in Apple SoCs such as the M1. It consists of two FIFOs used to
+ * exchange 64+32 bit messages between the main CPU and a co-processor.
+ * Various coprocessors implement different IPC protocols based on these simple
+ * messages and shared memory buffers.
+ *
+ * Both the main CPU and the co-processor see the same set of registers but
+ * the first FIFO (A2I) is always used to transfer messages from the application
+ * processor (us) to the I/O processor and the second one (I2A) for the
+ * other direction.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/bits.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include "mailbox.h"
+
+#define APPLE_ASC_MBOX_CONTROL_FULL BIT(16)
+#define APPLE_ASC_MBOX_CONTROL_EMPTY BIT(17)
+
+#define APPLE_ASC_MBOX_A2I_CONTROL 0x110
+#define APPLE_ASC_MBOX_A2I_SEND0 0x800
+#define APPLE_ASC_MBOX_A2I_SEND1 0x808
+#define APPLE_ASC_MBOX_A2I_RECV0 0x810
+#define APPLE_ASC_MBOX_A2I_RECV1 0x818
+
+#define APPLE_ASC_MBOX_I2A_CONTROL 0x114
+#define APPLE_ASC_MBOX_I2A_SEND0 0x820
+#define APPLE_ASC_MBOX_I2A_SEND1 0x828
+#define APPLE_ASC_MBOX_I2A_RECV0 0x830
+#define APPLE_ASC_MBOX_I2A_RECV1 0x838
+
+#define APPLE_M3_MBOX_CONTROL_FULL BIT(16)
+#define APPLE_M3_MBOX_CONTROL_EMPTY BIT(17)
+
+#define APPLE_M3_MBOX_A2I_CONTROL 0x50
+#define APPLE_M3_MBOX_A2I_SEND0 0x60
+#define APPLE_M3_MBOX_A2I_SEND1 0x68
+#define APPLE_M3_MBOX_A2I_RECV0 0x70
+#define APPLE_M3_MBOX_A2I_RECV1 0x78
+
+#define APPLE_M3_MBOX_I2A_CONTROL 0x80
+#define APPLE_M3_MBOX_I2A_SEND0 0x90
+#define APPLE_M3_MBOX_I2A_SEND1 0x98
+#define APPLE_M3_MBOX_I2A_RECV0 0xa0
+#define APPLE_M3_MBOX_I2A_RECV1 0xa8
+
+#define APPLE_M3_MBOX_IRQ_ENABLE 0x48
+#define APPLE_M3_MBOX_IRQ_ACK 0x4c
+#define APPLE_M3_MBOX_IRQ_A2I_EMPTY BIT(0)
+#define APPLE_M3_MBOX_IRQ_A2I_NOT_EMPTY BIT(1)
+#define APPLE_M3_MBOX_IRQ_I2A_EMPTY BIT(2)
+#define APPLE_M3_MBOX_IRQ_I2A_NOT_EMPTY BIT(3)
+
+#define APPLE_MBOX_MSG1_OUTCNT GENMASK(56, 52)
+#define APPLE_MBOX_MSG1_INCNT GENMASK(51, 48)
+#define APPLE_MBOX_MSG1_OUTPTR GENMASK(47, 44)
+#define APPLE_MBOX_MSG1_INPTR GENMASK(43, 40)
+#define APPLE_MBOX_MSG1_MSG GENMASK(31, 0)
+
+#define APPLE_MBOX_TX_TIMEOUT 500
+
+struct apple_mbox_hw {
+	unsigned int control_full;
+	unsigned int control_empty;
+
+	unsigned int a2i_control;
+	unsigned int a2i_send0;
+	unsigned int a2i_send1;
+
+	unsigned int i2a_control;
+	unsigned int i2a_recv0;
+	unsigned int i2a_recv1;
+
+	bool has_irq_controls;
+	unsigned int irq_enable;
+	unsigned int irq_ack;
+	unsigned int irq_bit_recv_not_empty;
+	unsigned int irq_bit_send_empty;
+};
+
+int apple_mbox_send(struct apple_mbox *mbox, const struct apple_mbox_msg msg,
+		    bool atomic)
+{
+	unsigned long flags;
+	int ret;
+	u32 mbox_ctrl;
+	long t;
+
+	spin_lock_irqsave(&mbox->tx_lock, flags);
+	mbox_ctrl = readl_relaxed(mbox->regs + mbox->hw->a2i_control);
+
+	while (mbox_ctrl & mbox->hw->control_full) {
+		if (atomic) {
+			ret = readl_poll_timeout_atomic(
+				mbox->regs + mbox->hw->a2i_control, mbox_ctrl,
+				!(mbox_ctrl & mbox->hw->control_full), 100,
+				APPLE_MBOX_TX_TIMEOUT * 1000);
+
+			if (ret) {
+				spin_unlock_irqrestore(&mbox->tx_lock, flags);
+				return ret;
+			}
+
+			break;
+		}
+		/*
+		 * The interrupt is level triggered and will keep firing as long as the
+		 * FIFO is empty. It will also keep firing if the FIFO was empty
+		 * at any point in the past until it has been acknowledged at the
+		 * mailbox level. By acknowledging it here we can ensure that we will
+		 * only get the interrupt once the FIFO has been cleared again.
+		 * If the FIFO is already empty before the ack it will fire again
+		 * immediately after the ack.
+		 */
+		if (mbox->hw->has_irq_controls) {
+			writel_relaxed(mbox->hw->irq_bit_send_empty,
+				       mbox->regs + mbox->hw->irq_ack);
+		}
+		enable_irq(mbox->irq_send_empty);
+		reinit_completion(&mbox->tx_empty);
+		spin_unlock_irqrestore(&mbox->tx_lock, flags);
+
+		t = wait_for_completion_interruptible_timeout(
+			&mbox->tx_empty,
+			msecs_to_jiffies(APPLE_MBOX_TX_TIMEOUT));
+		if (t < 0)
+			return t;
+		else if (t == 0)
+			return -ETIMEDOUT;
+
+		spin_lock_irqsave(&mbox->tx_lock, flags);
+		mbox_ctrl = readl_relaxed(mbox->regs + mbox->hw->a2i_control);
+	}
+
+	writeq_relaxed(msg.msg0, mbox->regs + mbox->hw->a2i_send0);
+	writeq_relaxed(FIELD_PREP(APPLE_MBOX_MSG1_MSG, msg.msg1),
+		       mbox->regs + mbox->hw->a2i_send1);
+
+	spin_unlock_irqrestore(&mbox->tx_lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL(apple_mbox_send);
+
+static irqreturn_t apple_mbox_send_empty_irq(int irq, void *data)
+{
+	struct apple_mbox *mbox = data;
+
+	/*
+	 * We don't need to acknowledge the interrupt at the mailbox level
+	 * here even if supported by the hardware. It will keep firing but that
+	 * doesn't matter since it's disabled at the main interrupt controller.
+	 * apple_mbox_send will acknowledge it before enabling
+	 * it at the main controller again.
+	 */
+	spin_lock(&mbox->tx_lock);
+	disable_irq_nosync(mbox->irq_send_empty);
+	complete(&mbox->tx_empty);
+	spin_unlock(&mbox->tx_lock);
+
+	return IRQ_HANDLED;
+}
+
+static int apple_mbox_poll_locked(struct apple_mbox *mbox)
+{
+	struct apple_mbox_msg msg;
+	int ret = 0;
+
+	u32 mbox_ctrl = readl_relaxed(mbox->regs + mbox->hw->i2a_control);
+
+	while (!(mbox_ctrl & mbox->hw->control_empty)) {
+		msg.msg0 = readq_relaxed(mbox->regs + mbox->hw->i2a_recv0);
+		msg.msg1 = FIELD_GET(
+			APPLE_MBOX_MSG1_MSG,
+			readq_relaxed(mbox->regs + mbox->hw->i2a_recv1));
+
+		mbox->rx(mbox, msg, mbox->cookie);
+		ret++;
+		mbox_ctrl = readl_relaxed(mbox->regs + mbox->hw->i2a_control);
+	}
+
+	/*
+	 * The interrupt will keep firing even if there are no more messages
+	 * unless we also acknowledge it at the mailbox level here.
+	 * There's no race if a message comes in between the check in the while
+	 * loop above and the ack below: If a new messages arrives inbetween
+	 * those two the interrupt will just fire again immediately after the
+	 * ack since it's level triggered.
+	 */
+	if (mbox->hw->has_irq_controls) {
+		writel_relaxed(mbox->hw->irq_bit_recv_not_empty,
+			       mbox->regs + mbox->hw->irq_ack);
+	}
+
+	return ret;
+}
+
+static irqreturn_t apple_mbox_recv_irq(int irq, void *data)
+{
+	struct apple_mbox *mbox = data;
+
+	spin_lock(&mbox->rx_lock);
+	apple_mbox_poll_locked(mbox);
+	spin_unlock(&mbox->rx_lock);
+
+	return IRQ_HANDLED;
+}
+
+int apple_mbox_poll(struct apple_mbox *mbox)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&mbox->rx_lock, flags);
+	ret = apple_mbox_poll_locked(mbox);
+	spin_unlock_irqrestore(&mbox->rx_lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL(apple_mbox_poll);
+
+int apple_mbox_start(struct apple_mbox *mbox)
+{
+	int ret;
+
+	if (mbox->active)
+		return 0;
+
+	ret = pm_runtime_resume_and_get(mbox->dev);
+	if (ret)
+		return ret;
+
+	/*
+	 * Only some variants of this mailbox HW provide interrupt control
+	 * at the mailbox level. We therefore need to handle enabling/disabling
+	 * interrupts at the main interrupt controller anyway for hardware that
+	 * doesn't. Just always keep the interrupts we care about enabled at
+	 * the mailbox level so that both hardware revisions behave almost
+	 * the same.
+	 */
+	if (mbox->hw->has_irq_controls) {
+		writel_relaxed(mbox->hw->irq_bit_recv_not_empty |
+				       mbox->hw->irq_bit_send_empty,
+			       mbox->regs + mbox->hw->irq_enable);
+	}
+
+	enable_irq(mbox->irq_recv_not_empty);
+	mbox->active = true;
+	return 0;
+}
+EXPORT_SYMBOL(apple_mbox_start);
+
+void apple_mbox_stop(struct apple_mbox *mbox)
+{
+	if (!mbox->active)
+		return;
+
+	mbox->active = false;
+	disable_irq(mbox->irq_recv_not_empty);
+	pm_runtime_mark_last_busy(mbox->dev);
+	pm_runtime_put_autosuspend(mbox->dev);
+}
+EXPORT_SYMBOL(apple_mbox_stop);
+
+struct apple_mbox *apple_mbox_get(struct device *dev, int index)
+{
+	struct of_phandle_args args;
+	struct platform_device *pdev;
+	struct apple_mbox *mbox;
+	int ret;
+
+	ret = of_parse_phandle_with_args(dev->of_node, "mboxes", "#mbox-cells",
+					 index, &args);
+	if (ret || !args.np)
+		return ERR_PTR(ret);
+
+	pdev = of_find_device_by_node(args.np);
+	of_node_put(args.np);
+
+	if (!pdev)
+		return ERR_PTR(EPROBE_DEFER);
+
+	mbox = platform_get_drvdata(pdev);
+	if (!mbox)
+		return ERR_PTR(EPROBE_DEFER);
+
+	if (!device_link_add(dev, &pdev->dev, DL_FLAG_AUTOREMOVE_CONSUMER))
+		return ERR_PTR(ENODEV);
+
+	return mbox;
+}
+EXPORT_SYMBOL(apple_mbox_get);
+
+struct apple_mbox *apple_mbox_get_byname(struct device *dev, const char *name)
+{
+	int index;
+
+	index = of_property_match_string(dev->of_node, "mbox-names", name);
+	if (index < 0)
+		return ERR_PTR(index);
+
+	return apple_mbox_get(dev, index);
+}
+EXPORT_SYMBOL(apple_mbox_get_byname);
+
+static int apple_mbox_probe(struct platform_device *pdev)
+{
+	int ret;
+	char *irqname;
+	struct apple_mbox *mbox;
+	struct device *dev = &pdev->dev;
+
+	mbox = devm_kzalloc(dev, sizeof(*mbox), GFP_KERNEL);
+	if (!mbox)
+		return -ENOMEM;
+
+	mbox->dev = &pdev->dev;
+	mbox->hw = of_device_get_match_data(dev);
+	if (!mbox->hw)
+		return -EINVAL;
+
+	mbox->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(mbox->regs))
+		return PTR_ERR(mbox->regs);
+
+	mbox->irq_recv_not_empty =
+		platform_get_irq_byname(pdev, "recv-not-empty");
+	if (mbox->irq_recv_not_empty < 0)
+		return -ENODEV;
+
+	mbox->irq_send_empty = platform_get_irq_byname(pdev, "send-empty");
+	if (mbox->irq_send_empty < 0)
+		return -ENODEV;
+
+	spin_lock_init(&mbox->rx_lock);
+	spin_lock_init(&mbox->tx_lock);
+	init_completion(&mbox->tx_empty);
+
+	irqname = devm_kasprintf(dev, GFP_KERNEL, "%s-recv", dev_name(dev));
+	if (!irqname)
+		return -ENOMEM;
+
+	ret = devm_request_irq(dev, mbox->irq_recv_not_empty,
+			       apple_mbox_recv_irq,
+			       IRQF_NO_AUTOEN | IRQF_NO_SUSPEND, irqname, mbox);
+	if (ret)
+		return ret;
+
+	irqname = devm_kasprintf(dev, GFP_KERNEL, "%s-send", dev_name(dev));
+	if (!irqname)
+		return -ENOMEM;
+
+	ret = devm_request_irq(dev, mbox->irq_send_empty,
+			       apple_mbox_send_empty_irq,
+			       IRQF_NO_AUTOEN | IRQF_NO_SUSPEND, irqname, mbox);
+	if (ret)
+		return ret;
+
+	ret = devm_pm_runtime_enable(dev);
+	if (ret)
+		return ret;
+
+	platform_set_drvdata(pdev, mbox);
+	return 0;
+}
+
+static const struct apple_mbox_hw apple_mbox_asc_hw = {
+	.control_full = APPLE_ASC_MBOX_CONTROL_FULL,
+	.control_empty = APPLE_ASC_MBOX_CONTROL_EMPTY,
+
+	.a2i_control = APPLE_ASC_MBOX_A2I_CONTROL,
+	.a2i_send0 = APPLE_ASC_MBOX_A2I_SEND0,
+	.a2i_send1 = APPLE_ASC_MBOX_A2I_SEND1,
+
+	.i2a_control = APPLE_ASC_MBOX_I2A_CONTROL,
+	.i2a_recv0 = APPLE_ASC_MBOX_I2A_RECV0,
+	.i2a_recv1 = APPLE_ASC_MBOX_I2A_RECV1,
+
+	.has_irq_controls = false,
+};
+
+static const struct apple_mbox_hw apple_mbox_m3_hw = {
+	.control_full = APPLE_M3_MBOX_CONTROL_FULL,
+	.control_empty = APPLE_M3_MBOX_CONTROL_EMPTY,
+
+	.a2i_control = APPLE_M3_MBOX_A2I_CONTROL,
+	.a2i_send0 = APPLE_M3_MBOX_A2I_SEND0,
+	.a2i_send1 = APPLE_M3_MBOX_A2I_SEND1,
+
+	.i2a_control = APPLE_M3_MBOX_I2A_CONTROL,
+	.i2a_recv0 = APPLE_M3_MBOX_I2A_RECV0,
+	.i2a_recv1 = APPLE_M3_MBOX_I2A_RECV1,
+
+	.has_irq_controls = true,
+	.irq_enable = APPLE_M3_MBOX_IRQ_ENABLE,
+	.irq_ack = APPLE_M3_MBOX_IRQ_ACK,
+	.irq_bit_recv_not_empty = APPLE_M3_MBOX_IRQ_I2A_NOT_EMPTY,
+	.irq_bit_send_empty = APPLE_M3_MBOX_IRQ_A2I_EMPTY,
+};
+
+static const struct of_device_id apple_mbox_of_match[] = {
+	{ .compatible = "apple,asc-mailbox-v4", .data = &apple_mbox_asc_hw },
+	{ .compatible = "apple,m3-mailbox-v2", .data = &apple_mbox_m3_hw },
+	{}
+};
+MODULE_DEVICE_TABLE(of, apple_mbox_of_match);
+
+static struct platform_driver apple_mbox_driver = {
+	.driver = {
+		.name = "apple-mailbox",
+		.of_match_table = apple_mbox_of_match,
+	},
+	.probe = apple_mbox_probe,
+};
+module_platform_driver(apple_mbox_driver);
+
+MODULE_LICENSE("Dual MIT/GPL");
+MODULE_AUTHOR("Sven Peter <sven@svenpeter.dev>");
+MODULE_DESCRIPTION("Apple Mailbox driver");
diff --git a/drivers/soc/apple/mailbox.h b/drivers/soc/apple/mailbox.h
new file mode 100644
index 000000000000..f73a8913da95
--- /dev/null
+++ b/drivers/soc/apple/mailbox.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0-only OR MIT */
+/*
+ * Apple mailbox message format
+ *
+ * Copyright The Asahi Linux Contributors
+ */
+
+#ifndef _APPLE_MAILBOX_H_
+#define _APPLE_MAILBOX_H_
+
+#include <linux/device.h>
+#include <linux/types.h>
+
+/* encodes a single 96bit message sent over the single channel */
+struct apple_mbox_msg {
+	u64 msg0;
+	u32 msg1;
+};
+
+struct apple_mbox {
+	struct device *dev;
+	void __iomem *regs;
+	const struct apple_mbox_hw *hw;
+	bool active;
+
+	int irq_recv_not_empty;
+	int irq_send_empty;
+
+	spinlock_t rx_lock;
+	spinlock_t tx_lock;
+
+	struct completion tx_empty;
+
+	/** Receive callback for incoming messages */
+	void (*rx)(struct apple_mbox *mbox, struct apple_mbox_msg msg, void *cookie);
+	void *cookie;
+};
+
+struct apple_mbox *apple_mbox_get(struct device *dev, int index);
+struct apple_mbox *apple_mbox_get_byname(struct device *dev, const char *name);
+
+int apple_mbox_start(struct apple_mbox *mbox);
+void apple_mbox_stop(struct apple_mbox *mbox);
+int apple_mbox_poll(struct apple_mbox *mbox);
+int apple_mbox_send(struct apple_mbox *mbox, struct apple_mbox_msg msg,
+		    bool atomic);
+
+#endif
diff --git a/drivers/soc/apple/rtkit-internal.h b/drivers/soc/apple/rtkit-internal.h
index 24bd619ec5e4..27c9fa745fd5 100644
--- a/drivers/soc/apple/rtkit-internal.h
+++ b/drivers/soc/apple/rtkit-internal.h
@@ -7,18 +7,17 @@
 #ifndef _APPLE_RTKIT_INTERAL_H
 #define _APPLE_RTKIT_INTERAL_H
 
-#include <linux/apple-mailbox.h>
 #include <linux/bitfield.h>
 #include <linux/bitmap.h>
 #include <linux/completion.h>
 #include <linux/dma-mapping.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
-#include <linux/mailbox_client.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/soc/apple/rtkit.h>
 #include <linux/workqueue.h>
+#include "mailbox.h"
 
 #define APPLE_RTKIT_APP_ENDPOINT_START 0x20
 #define APPLE_RTKIT_MAX_ENDPOINTS 0x100
@@ -28,10 +27,7 @@ struct apple_rtkit {
 	const struct apple_rtkit_ops *ops;
 	struct device *dev;
 
-	const char *mbox_name;
-	int mbox_idx;
-	struct mbox_client mbox_cl;
-	struct mbox_chan *mbox_chan;
+	struct apple_mbox *mbox;
 
 	struct completion epmap_completion;
 	struct completion iop_pwr_ack_completion;
diff --git a/drivers/soc/apple/rtkit.c b/drivers/soc/apple/rtkit.c
index d9f19dc99da5..e6d940292c9f 100644
--- a/drivers/soc/apple/rtkit.c
+++ b/drivers/soc/apple/rtkit.c
@@ -72,11 +72,6 @@ enum {
 #define APPLE_RTKIT_MIN_SUPPORTED_VERSION 11
 #define APPLE_RTKIT_MAX_SUPPORTED_VERSION 12
 
-struct apple_rtkit_msg {
-	struct completion *completion;
-	struct apple_mbox_msg mbox_msg;
-};
-
 struct apple_rtkit_rx_work {
 	struct apple_rtkit *rtk;
 	u8 ep;
@@ -550,12 +545,12 @@ static void apple_rtkit_rx_work(struct work_struct *work)
 	kfree(rtk_work);
 }
 
-static void apple_rtkit_rx(struct mbox_client *cl, void *mssg)
+static void apple_rtkit_rx(struct apple_mbox *mbox, struct apple_mbox_msg msg,
+			   void *cookie)
 {
-	struct apple_rtkit *rtk = container_of(cl, struct apple_rtkit, mbox_cl);
-	struct apple_mbox_msg *msg = mssg;
+	struct apple_rtkit *rtk = cookie;
 	struct apple_rtkit_rx_work *work;
-	u8 ep = msg->msg1;
+	u8 ep = msg.msg1;
 
 	/*
 	 * The message was read from a MMIO FIFO and we have to make
@@ -571,7 +566,7 @@ static void apple_rtkit_rx(struct mbox_client *cl, void *mssg)
 
 	if (ep >= APPLE_RTKIT_APP_ENDPOINT_START &&
 	    rtk->ops->recv_message_early &&
-	    rtk->ops->recv_message_early(rtk->cookie, ep, msg->msg0))
+	    rtk->ops->recv_message_early(rtk->cookie, ep, msg.msg0))
 		return;
 
 	work = kzalloc(sizeof(*work), GFP_ATOMIC);
@@ -580,30 +575,18 @@ static void apple_rtkit_rx(struct mbox_client *cl, void *mssg)
 
 	work->rtk = rtk;
 	work->ep = ep;
-	work->msg = msg->msg0;
+	work->msg = msg.msg0;
 	INIT_WORK(&work->work, apple_rtkit_rx_work);
 	queue_work(rtk->wq, &work->work);
 }
 
-static void apple_rtkit_tx_done(struct mbox_client *cl, void *mssg, int r)
-{
-	struct apple_rtkit_msg *msg =
-		container_of(mssg, struct apple_rtkit_msg, mbox_msg);
-
-	if (r == -ETIME)
-		return;
-
-	if (msg->completion)
-		complete(msg->completion);
-	kfree(msg);
-}
-
 int apple_rtkit_send_message(struct apple_rtkit *rtk, u8 ep, u64 message,
 			     struct completion *completion, bool atomic)
 {
-	struct apple_rtkit_msg *msg;
-	int ret;
-	gfp_t flags;
+	struct apple_mbox_msg msg = {
+		.msg0 = message,
+		.msg1 = ep,
+	};
 
 	if (rtk->crashed)
 		return -EINVAL;
@@ -611,19 +594,6 @@ int apple_rtkit_send_message(struct apple_rtkit *rtk, u8 ep, u64 message,
 	    !apple_rtkit_is_running(rtk))
 		return -EINVAL;
 
-	if (atomic)
-		flags = GFP_ATOMIC;
-	else
-		flags = GFP_KERNEL;
-
-	msg = kzalloc(sizeof(*msg), flags);
-	if (!msg)
-		return -ENOMEM;
-
-	msg->mbox_msg.msg0 = message;
-	msg->mbox_msg.msg1 = ep;
-	msg->completion = completion;
-
 	/*
 	 * The message will be sent with a MMIO write. We need the barrier
 	 * here to ensure any previous writes to buffers are visible to the
@@ -631,51 +601,13 @@ int apple_rtkit_send_message(struct apple_rtkit *rtk, u8 ep, u64 message,
 	 */
 	dma_wmb();
 
-	ret = mbox_send_message(rtk->mbox_chan, &msg->mbox_msg);
-	if (ret < 0) {
-		kfree(msg);
-		return ret;
-	}
-
-	return 0;
+	return apple_mbox_send(rtk->mbox, msg, atomic);
 }
 EXPORT_SYMBOL_GPL(apple_rtkit_send_message);
 
-int apple_rtkit_send_message_wait(struct apple_rtkit *rtk, u8 ep, u64 message,
-				  unsigned long timeout, bool atomic)
-{
-	DECLARE_COMPLETION_ONSTACK(completion);
-	int ret;
-	long t;
-
-	ret = apple_rtkit_send_message(rtk, ep, message, &completion, atomic);
-	if (ret < 0)
-		return ret;
-
-	if (atomic) {
-		ret = mbox_flush(rtk->mbox_chan, timeout);
-		if (ret < 0)
-			return ret;
-
-		if (try_wait_for_completion(&completion))
-			return 0;
-
-		return -ETIME;
-	} else {
-		t = wait_for_completion_interruptible_timeout(
-			&completion, msecs_to_jiffies(timeout));
-		if (t < 0)
-			return t;
-		else if (t == 0)
-			return -ETIME;
-		return 0;
-	}
-}
-EXPORT_SYMBOL_GPL(apple_rtkit_send_message_wait);
-
 int apple_rtkit_poll(struct apple_rtkit *rtk)
 {
-	return mbox_client_peek_data(rtk->mbox_chan);
+	return apple_mbox_poll(rtk->mbox);
 }
 EXPORT_SYMBOL_GPL(apple_rtkit_poll);
 
@@ -697,20 +629,6 @@ int apple_rtkit_start_ep(struct apple_rtkit *rtk, u8 endpoint)
 }
 EXPORT_SYMBOL_GPL(apple_rtkit_start_ep);
 
-static int apple_rtkit_request_mbox_chan(struct apple_rtkit *rtk)
-{
-	if (rtk->mbox_name)
-		rtk->mbox_chan = mbox_request_channel_byname(&rtk->mbox_cl,
-							     rtk->mbox_name);
-	else
-		rtk->mbox_chan =
-			mbox_request_channel(&rtk->mbox_cl, rtk->mbox_idx);
-
-	if (IS_ERR(rtk->mbox_chan))
-		return PTR_ERR(rtk->mbox_chan);
-	return 0;
-}
-
 struct apple_rtkit *apple_rtkit_init(struct device *dev, void *cookie,
 					    const char *mbox_name, int mbox_idx,
 					    const struct apple_rtkit_ops *ops)
@@ -736,13 +654,18 @@ struct apple_rtkit *apple_rtkit_init(struct device *dev, void *cookie,
 	bitmap_zero(rtk->endpoints, APPLE_RTKIT_MAX_ENDPOINTS);
 	set_bit(APPLE_RTKIT_EP_MGMT, rtk->endpoints);
 
-	rtk->mbox_name = mbox_name;
-	rtk->mbox_idx = mbox_idx;
-	rtk->mbox_cl.dev = dev;
-	rtk->mbox_cl.tx_block = false;
-	rtk->mbox_cl.knows_txdone = false;
-	rtk->mbox_cl.rx_callback = &apple_rtkit_rx;
-	rtk->mbox_cl.tx_done = &apple_rtkit_tx_done;
+	if (mbox_name)
+		rtk->mbox = apple_mbox_get_byname(dev, mbox_name);
+	else
+		rtk->mbox = apple_mbox_get(dev, mbox_idx);
+
+	if (IS_ERR(rtk->mbox)) {
+		ret = PTR_ERR(rtk->mbox);
+		goto free_rtk;
+	}
+
+	rtk->mbox->rx = apple_rtkit_rx;
+	rtk->mbox->cookie = rtk;
 
 	rtk->wq = alloc_ordered_workqueue("rtkit-%s", WQ_MEM_RECLAIM,
 					  dev_name(rtk->dev));
@@ -751,7 +674,7 @@ struct apple_rtkit *apple_rtkit_init(struct device *dev, void *cookie,
 		goto free_rtk;
 	}
 
-	ret = apple_rtkit_request_mbox_chan(rtk);
+	ret = apple_mbox_start(rtk->mbox);
 	if (ret)
 		goto destroy_wq;
 
@@ -782,7 +705,7 @@ static int apple_rtkit_wait_for_completion(struct completion *c)
 int apple_rtkit_reinit(struct apple_rtkit *rtk)
 {
 	/* make sure we don't handle any messages while reinitializing */
-	mbox_free_channel(rtk->mbox_chan);
+	apple_mbox_stop(rtk->mbox);
 	flush_workqueue(rtk->wq);
 
 	apple_rtkit_free_buffer(rtk, &rtk->ioreport_buffer);
@@ -806,7 +729,7 @@ int apple_rtkit_reinit(struct apple_rtkit *rtk)
 	rtk->iop_power_state = APPLE_RTKIT_PWR_STATE_OFF;
 	rtk->ap_power_state = APPLE_RTKIT_PWR_STATE_OFF;
 
-	return apple_rtkit_request_mbox_chan(rtk);
+	return apple_mbox_start(rtk->mbox);
 }
 EXPORT_SYMBOL_GPL(apple_rtkit_reinit);
 
@@ -962,7 +885,7 @@ EXPORT_SYMBOL_GPL(apple_rtkit_wake);
 
 void apple_rtkit_free(struct apple_rtkit *rtk)
 {
-	mbox_free_channel(rtk->mbox_chan);
+	apple_mbox_stop(rtk->mbox);
 	destroy_workqueue(rtk->wq);
 
 	apple_rtkit_free_buffer(rtk, &rtk->ioreport_buffer);
diff --git a/drivers/soc/fsl/qe/qmc.c b/drivers/soc/fsl/qe/qmc.c
index 92ec76c03965..f498db9abe35 100644
--- a/drivers/soc/fsl/qe/qmc.c
+++ b/drivers/soc/fsl/qe/qmc.c
@@ -166,7 +166,7 @@
 struct qmc_xfer_desc {
 	union {
 		void (*tx_complete)(void *context);
-		void (*rx_complete)(void *context, size_t length);
+		void (*rx_complete)(void *context, size_t length, unsigned int flags);
 	};
 	void *context;
 };
@@ -175,9 +175,12 @@ struct qmc_chan {
 	struct list_head list;
 	unsigned int id;
 	struct qmc *qmc;
-	void *__iomem s_param;
+	void __iomem *s_param;
 	enum qmc_mode mode;
+	spinlock_t	ts_lock; /* Protect timeslots */
+	u64	tx_ts_mask_avail;
 	u64	tx_ts_mask;
+	u64	rx_ts_mask_avail;
 	u64	rx_ts_mask;
 	bool is_reverse_data;
 
@@ -203,9 +206,9 @@ struct qmc_chan {
 struct qmc {
 	struct device *dev;
 	struct tsa_serial *tsa_serial;
-	void *__iomem scc_regs;
-	void *__iomem scc_pram;
-	void *__iomem dpram;
+	void __iomem *scc_regs;
+	void __iomem *scc_pram;
+	void __iomem *dpram;
 	u16 scc_pram_offset;
 	cbd_t __iomem *bd_table;
 	dma_addr_t bd_dma_addr;
@@ -214,41 +217,47 @@ struct qmc {
 	u16 __iomem *int_curr;
 	dma_addr_t int_dma_addr;
 	size_t int_size;
+	bool is_tsa_64rxtx;
 	struct list_head chan_head;
 	struct qmc_chan *chans[64];
 };
 
-static inline void qmc_write16(void *__iomem addr, u16 val)
+static void qmc_write16(void __iomem *addr, u16 val)
 {
 	iowrite16be(val, addr);
 }
 
-static inline u16 qmc_read16(void *__iomem addr)
+static u16 qmc_read16(void __iomem *addr)
 {
 	return ioread16be(addr);
 }
 
-static inline void qmc_setbits16(void *__iomem addr, u16 set)
+static void qmc_setbits16(void __iomem *addr, u16 set)
 {
 	qmc_write16(addr, qmc_read16(addr) | set);
 }
 
-static inline void qmc_clrbits16(void *__iomem addr, u16 clr)
+static void qmc_clrbits16(void __iomem *addr, u16 clr)
 {
 	qmc_write16(addr, qmc_read16(addr) & ~clr);
 }
 
-static inline void qmc_write32(void *__iomem addr, u32 val)
+static void qmc_clrsetbits16(void __iomem *addr, u16 clr, u16 set)
+{
+	qmc_write16(addr, (qmc_read16(addr) & ~clr) | set);
+}
+
+static void qmc_write32(void __iomem *addr, u32 val)
 {
 	iowrite32be(val, addr);
 }
 
-static inline u32 qmc_read32(void *__iomem addr)
+static u32 qmc_read32(void __iomem *addr)
 {
 	return ioread32be(addr);
 }
 
-static inline void qmc_setbits32(void *__iomem addr, u32 set)
+static void qmc_setbits32(void __iomem *addr, u32 set)
 {
 	qmc_write32(addr, qmc_read32(addr) | set);
 }
@@ -257,6 +266,7 @@ static inline void qmc_setbits32(void *__iomem addr, u32 set)
 int qmc_chan_get_info(struct qmc_chan *chan, struct qmc_chan_info *info)
 {
 	struct tsa_serial_info tsa_info;
+	unsigned long flags;
 	int ret;
 
 	/* Retrieve info from the TSA related serial */
@@ -264,6 +274,8 @@ int qmc_chan_get_info(struct qmc_chan *chan, struct qmc_chan_info *info)
 	if (ret)
 		return ret;
 
+	spin_lock_irqsave(&chan->ts_lock, flags);
+
 	info->mode = chan->mode;
 	info->rx_fs_rate = tsa_info.rx_fs_rate;
 	info->rx_bit_rate = tsa_info.rx_bit_rate;
@@ -272,10 +284,63 @@ int qmc_chan_get_info(struct qmc_chan *chan, struct qmc_chan_info *info)
 	info->tx_bit_rate = tsa_info.tx_bit_rate;
 	info->nb_rx_ts = hweight64(chan->rx_ts_mask);
 
+	spin_unlock_irqrestore(&chan->ts_lock, flags);
+
 	return 0;
 }
 EXPORT_SYMBOL(qmc_chan_get_info);
 
+int qmc_chan_get_ts_info(struct qmc_chan *chan, struct qmc_chan_ts_info *ts_info)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->ts_lock, flags);
+
+	ts_info->rx_ts_mask_avail = chan->rx_ts_mask_avail;
+	ts_info->tx_ts_mask_avail = chan->tx_ts_mask_avail;
+	ts_info->rx_ts_mask = chan->rx_ts_mask;
+	ts_info->tx_ts_mask = chan->tx_ts_mask;
+
+	spin_unlock_irqrestore(&chan->ts_lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL(qmc_chan_get_ts_info);
+
+int qmc_chan_set_ts_info(struct qmc_chan *chan, const struct qmc_chan_ts_info *ts_info)
+{
+	unsigned long flags;
+	int ret;
+
+	/* Only a subset of available timeslots is allowed */
+	if ((ts_info->rx_ts_mask & chan->rx_ts_mask_avail) != ts_info->rx_ts_mask)
+		return -EINVAL;
+	if ((ts_info->tx_ts_mask & chan->tx_ts_mask_avail) != ts_info->tx_ts_mask)
+		return -EINVAL;
+
+	/* In case of common rx/tx table, rx/tx masks must be identical */
+	if (chan->qmc->is_tsa_64rxtx) {
+		if (ts_info->rx_ts_mask != ts_info->tx_ts_mask)
+			return -EINVAL;
+	}
+
+	spin_lock_irqsave(&chan->ts_lock, flags);
+
+	if ((chan->tx_ts_mask != ts_info->tx_ts_mask && !chan->is_tx_stopped) ||
+	    (chan->rx_ts_mask != ts_info->rx_ts_mask && !chan->is_rx_stopped)) {
+		dev_err(chan->qmc->dev, "Channel rx and/or tx not stopped\n");
+		ret = -EBUSY;
+	} else {
+		chan->tx_ts_mask = ts_info->tx_ts_mask;
+		chan->rx_ts_mask = ts_info->rx_ts_mask;
+		ret = 0;
+	}
+	spin_unlock_irqrestore(&chan->ts_lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL(qmc_chan_set_ts_info);
+
 int qmc_chan_set_param(struct qmc_chan *chan, const struct qmc_chan_param *param)
 {
 	if (param->mode != chan->mode)
@@ -318,7 +383,7 @@ int qmc_chan_write_submit(struct qmc_chan *chan, dma_addr_t addr, size_t length,
 {
 	struct qmc_xfer_desc *xfer_desc;
 	unsigned long flags;
-	cbd_t *__iomem bd;
+	cbd_t __iomem *bd;
 	u16 ctrl;
 	int ret;
 
@@ -374,7 +439,7 @@ static void qmc_chan_write_done(struct qmc_chan *chan)
 	void (*complete)(void *context);
 	unsigned long flags;
 	void *context;
-	cbd_t *__iomem bd;
+	cbd_t __iomem *bd;
 	u16 ctrl;
 
 	/*
@@ -421,11 +486,12 @@ end:
 }
 
 int qmc_chan_read_submit(struct qmc_chan *chan, dma_addr_t addr, size_t length,
-			 void (*complete)(void *context, size_t length), void *context)
+			 void (*complete)(void *context, size_t length, unsigned int flags),
+			 void *context)
 {
 	struct qmc_xfer_desc *xfer_desc;
 	unsigned long flags;
-	cbd_t *__iomem bd;
+	cbd_t __iomem *bd;
 	u16 ctrl;
 	int ret;
 
@@ -454,6 +520,10 @@ int qmc_chan_read_submit(struct qmc_chan *chan, dma_addr_t addr, size_t length,
 	xfer_desc->rx_complete = complete;
 	xfer_desc->context = context;
 
+	/* Clear previous status flags */
+	ctrl &= ~(QMC_BD_RX_L | QMC_BD_RX_F | QMC_BD_RX_LG | QMC_BD_RX_NO |
+		  QMC_BD_RX_AB | QMC_BD_RX_CR);
+
 	/* Activate the descriptor */
 	ctrl |= (QMC_BD_RX_E | QMC_BD_RX_UB);
 	wmb(); /* Be sure to flush data before descriptor activation */
@@ -485,10 +555,10 @@ EXPORT_SYMBOL(qmc_chan_read_submit);
 
 static void qmc_chan_read_done(struct qmc_chan *chan)
 {
-	void (*complete)(void *context, size_t size);
+	void (*complete)(void *context, size_t size, unsigned int flags);
 	struct qmc_xfer_desc *xfer_desc;
 	unsigned long flags;
-	cbd_t *__iomem bd;
+	cbd_t __iomem *bd;
 	void *context;
 	u16 datalen;
 	u16 ctrl;
@@ -527,7 +597,23 @@ static void qmc_chan_read_done(struct qmc_chan *chan)
 
 		if (complete) {
 			spin_unlock_irqrestore(&chan->rx_lock, flags);
-			complete(context, datalen);
+
+			/*
+			 * Avoid conversion between internal hardware flags and
+			 * the software API flags.
+			 * -> Be sure that the software API flags are consistent
+			 *    with the hardware flags
+			 */
+			BUILD_BUG_ON(QMC_RX_FLAG_HDLC_LAST  != QMC_BD_RX_L);
+			BUILD_BUG_ON(QMC_RX_FLAG_HDLC_FIRST != QMC_BD_RX_F);
+			BUILD_BUG_ON(QMC_RX_FLAG_HDLC_OVF   != QMC_BD_RX_LG);
+			BUILD_BUG_ON(QMC_RX_FLAG_HDLC_UNA   != QMC_BD_RX_NO);
+			BUILD_BUG_ON(QMC_RX_FLAG_HDLC_ABORT != QMC_BD_RX_AB);
+			BUILD_BUG_ON(QMC_RX_FLAG_HDLC_CRC   != QMC_BD_RX_CR);
+
+			complete(context, datalen,
+				 ctrl & (QMC_BD_RX_L | QMC_BD_RX_F | QMC_BD_RX_LG |
+					 QMC_BD_RX_NO | QMC_BD_RX_AB | QMC_BD_RX_CR));
 			spin_lock_irqsave(&chan->rx_lock, flags);
 		}
 
@@ -539,6 +625,155 @@ end:
 	spin_unlock_irqrestore(&chan->rx_lock, flags);
 }
 
+static int qmc_chan_setup_tsa_64rxtx(struct qmc_chan *chan, const struct tsa_serial_info *info,
+				     bool enable)
+{
+	unsigned int i;
+	u16 curr;
+	u16 val;
+
+	/*
+	 * Use a common Tx/Rx 64 entries table.
+	 * Tx and Rx related stuffs must be identical
+	 */
+	if (chan->tx_ts_mask != chan->rx_ts_mask) {
+		dev_err(chan->qmc->dev, "chan %u uses different Rx and Tx TS\n", chan->id);
+		return -EINVAL;
+	}
+
+	val = QMC_TSA_VALID | QMC_TSA_MASK | QMC_TSA_CHANNEL(chan->id);
+
+	/* Check entries based on Rx stuff*/
+	for (i = 0; i < info->nb_rx_ts; i++) {
+		if (!(chan->rx_ts_mask & (((u64)1) << i)))
+			continue;
+
+		curr = qmc_read16(chan->qmc->scc_pram + QMC_GBL_TSATRX + (i * 2));
+		if (curr & QMC_TSA_VALID && (curr & ~QMC_TSA_WRAP) != val) {
+			dev_err(chan->qmc->dev, "chan %u TxRx entry %d already used\n",
+				chan->id, i);
+			return -EBUSY;
+		}
+	}
+
+	/* Set entries based on Rx stuff*/
+	for (i = 0; i < info->nb_rx_ts; i++) {
+		if (!(chan->rx_ts_mask & (((u64)1) << i)))
+			continue;
+
+		qmc_clrsetbits16(chan->qmc->scc_pram + QMC_GBL_TSATRX + (i * 2),
+				 ~QMC_TSA_WRAP, enable ? val : 0x0000);
+	}
+
+	return 0;
+}
+
+static int qmc_chan_setup_tsa_32rx(struct qmc_chan *chan, const struct tsa_serial_info *info,
+				   bool enable)
+{
+	unsigned int i;
+	u16 curr;
+	u16 val;
+
+	/* Use a Rx 32 entries table */
+
+	val = QMC_TSA_VALID | QMC_TSA_MASK | QMC_TSA_CHANNEL(chan->id);
+
+	/* Check entries based on Rx stuff */
+	for (i = 0; i < info->nb_rx_ts; i++) {
+		if (!(chan->rx_ts_mask & (((u64)1) << i)))
+			continue;
+
+		curr = qmc_read16(chan->qmc->scc_pram + QMC_GBL_TSATRX + (i * 2));
+		if (curr & QMC_TSA_VALID && (curr & ~QMC_TSA_WRAP) != val) {
+			dev_err(chan->qmc->dev, "chan %u Rx entry %d already used\n",
+				chan->id, i);
+			return -EBUSY;
+		}
+	}
+
+	/* Set entries based on Rx stuff */
+	for (i = 0; i < info->nb_rx_ts; i++) {
+		if (!(chan->rx_ts_mask & (((u64)1) << i)))
+			continue;
+
+		qmc_clrsetbits16(chan->qmc->scc_pram + QMC_GBL_TSATRX + (i * 2),
+				 ~QMC_TSA_WRAP, enable ? val : 0x0000);
+	}
+
+	return 0;
+}
+
+static int qmc_chan_setup_tsa_32tx(struct qmc_chan *chan, const struct tsa_serial_info *info,
+				   bool enable)
+{
+	unsigned int i;
+	u16 curr;
+	u16 val;
+
+	/* Use a Tx 32 entries table */
+
+	val = QMC_TSA_VALID | QMC_TSA_MASK | QMC_TSA_CHANNEL(chan->id);
+
+	/* Check entries based on Tx stuff */
+	for (i = 0; i < info->nb_tx_ts; i++) {
+		if (!(chan->tx_ts_mask & (((u64)1) << i)))
+			continue;
+
+		curr = qmc_read16(chan->qmc->scc_pram + QMC_GBL_TSATTX + (i * 2));
+		if (curr & QMC_TSA_VALID && (curr & ~QMC_TSA_WRAP) != val) {
+			dev_err(chan->qmc->dev, "chan %u Tx entry %d already used\n",
+				chan->id, i);
+			return -EBUSY;
+		}
+	}
+
+	/* Set entries based on Tx stuff */
+	for (i = 0; i < info->nb_tx_ts; i++) {
+		if (!(chan->tx_ts_mask & (((u64)1) << i)))
+			continue;
+
+		qmc_clrsetbits16(chan->qmc->scc_pram + QMC_GBL_TSATTX + (i * 2),
+				 ~QMC_TSA_WRAP, enable ? val : 0x0000);
+	}
+
+	return 0;
+}
+
+static int qmc_chan_setup_tsa_tx(struct qmc_chan *chan, bool enable)
+{
+	struct tsa_serial_info info;
+	int ret;
+
+	/* Retrieve info from the TSA related serial */
+	ret = tsa_serial_get_info(chan->qmc->tsa_serial, &info);
+	if (ret)
+		return ret;
+
+	/* Setup entries */
+	if (chan->qmc->is_tsa_64rxtx)
+		return qmc_chan_setup_tsa_64rxtx(chan, &info, enable);
+
+	return qmc_chan_setup_tsa_32tx(chan, &info, enable);
+}
+
+static int qmc_chan_setup_tsa_rx(struct qmc_chan *chan, bool enable)
+{
+	struct tsa_serial_info info;
+	int ret;
+
+	/* Retrieve info from the TSA related serial */
+	ret = tsa_serial_get_info(chan->qmc->tsa_serial, &info);
+	if (ret)
+		return ret;
+
+	/* Setup entries */
+	if (chan->qmc->is_tsa_64rxtx)
+		return qmc_chan_setup_tsa_64rxtx(chan, &info, enable);
+
+	return qmc_chan_setup_tsa_32rx(chan, &info, enable);
+}
+
 static int qmc_chan_command(struct qmc_chan *chan, u8 qmc_opcode)
 {
 	return cpm_command(chan->id << 2, (qmc_opcode << 4) | 0x0E);
@@ -551,6 +786,12 @@ static int qmc_chan_stop_rx(struct qmc_chan *chan)
 
 	spin_lock_irqsave(&chan->rx_lock, flags);
 
+	if (chan->is_rx_stopped) {
+		/* The channel is already stopped -> simply return ok */
+		ret = 0;
+		goto end;
+	}
+
 	/* Send STOP RECEIVE command */
 	ret = qmc_chan_command(chan, 0x0);
 	if (ret) {
@@ -561,6 +802,15 @@ static int qmc_chan_stop_rx(struct qmc_chan *chan)
 
 	chan->is_rx_stopped = true;
 
+	if (!chan->qmc->is_tsa_64rxtx || chan->is_tx_stopped) {
+		ret = qmc_chan_setup_tsa_rx(chan, false);
+		if (ret) {
+			dev_err(chan->qmc->dev, "chan %u: Disable tsa entries failed (%d)\n",
+				chan->id, ret);
+			goto end;
+		}
+	}
+
 end:
 	spin_unlock_irqrestore(&chan->rx_lock, flags);
 	return ret;
@@ -573,6 +823,12 @@ static int qmc_chan_stop_tx(struct qmc_chan *chan)
 
 	spin_lock_irqsave(&chan->tx_lock, flags);
 
+	if (chan->is_tx_stopped) {
+		/* The channel is already stopped -> simply return ok */
+		ret = 0;
+		goto end;
+	}
+
 	/* Send STOP TRANSMIT command */
 	ret = qmc_chan_command(chan, 0x1);
 	if (ret) {
@@ -583,37 +839,114 @@ static int qmc_chan_stop_tx(struct qmc_chan *chan)
 
 	chan->is_tx_stopped = true;
 
+	if (!chan->qmc->is_tsa_64rxtx || chan->is_rx_stopped) {
+		ret = qmc_chan_setup_tsa_tx(chan, false);
+		if (ret) {
+			dev_err(chan->qmc->dev, "chan %u: Disable tsa entries failed (%d)\n",
+				chan->id, ret);
+			goto end;
+		}
+	}
+
 end:
 	spin_unlock_irqrestore(&chan->tx_lock, flags);
 	return ret;
 }
 
+static int qmc_chan_start_rx(struct qmc_chan *chan);
+
 int qmc_chan_stop(struct qmc_chan *chan, int direction)
 {
-	int ret;
+	bool is_rx_rollback_needed = false;
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(&chan->ts_lock, flags);
 
 	if (direction & QMC_CHAN_READ) {
+		is_rx_rollback_needed = !chan->is_rx_stopped;
 		ret = qmc_chan_stop_rx(chan);
 		if (ret)
-			return ret;
+			goto end;
 	}
 
 	if (direction & QMC_CHAN_WRITE) {
 		ret = qmc_chan_stop_tx(chan);
-		if (ret)
-			return ret;
+		if (ret) {
+			/* Restart rx if needed */
+			if (is_rx_rollback_needed)
+				qmc_chan_start_rx(chan);
+			goto end;
+		}
 	}
 
-	return 0;
+end:
+	spin_unlock_irqrestore(&chan->ts_lock, flags);
+	return ret;
 }
 EXPORT_SYMBOL(qmc_chan_stop);
 
-static void qmc_chan_start_rx(struct qmc_chan *chan)
+static int qmc_setup_chan_trnsync(struct qmc *qmc, struct qmc_chan *chan)
+{
+	struct tsa_serial_info info;
+	u16 first_rx, last_tx;
+	u16 trnsync;
+	int ret;
+
+	/* Retrieve info from the TSA related serial */
+	ret = tsa_serial_get_info(chan->qmc->tsa_serial, &info);
+	if (ret)
+		return ret;
+
+	/* Find the first Rx TS allocated to the channel */
+	first_rx = chan->rx_ts_mask ? __ffs64(chan->rx_ts_mask) + 1 : 0;
+
+	/* Find the last Tx TS allocated to the channel */
+	last_tx = fls64(chan->tx_ts_mask);
+
+	trnsync = 0;
+	if (info.nb_rx_ts)
+		trnsync |= QMC_SPE_TRNSYNC_RX((first_rx % info.nb_rx_ts) * 2);
+	if (info.nb_tx_ts)
+		trnsync |= QMC_SPE_TRNSYNC_TX((last_tx % info.nb_tx_ts) * 2);
+
+	qmc_write16(chan->s_param + QMC_SPE_TRNSYNC, trnsync);
+
+	dev_dbg(qmc->dev, "chan %u: trnsync=0x%04x, rx %u/%u 0x%llx, tx %u/%u 0x%llx\n",
+		chan->id, trnsync,
+		first_rx, info.nb_rx_ts, chan->rx_ts_mask,
+		last_tx, info.nb_tx_ts, chan->tx_ts_mask);
+
+	return 0;
+}
+
+static int qmc_chan_start_rx(struct qmc_chan *chan)
 {
 	unsigned long flags;
+	int ret;
 
 	spin_lock_irqsave(&chan->rx_lock, flags);
 
+	if (!chan->is_rx_stopped) {
+		/* The channel is already started -> simply return ok */
+		ret = 0;
+		goto end;
+	}
+
+	ret = qmc_chan_setup_tsa_rx(chan, true);
+	if (ret) {
+		dev_err(chan->qmc->dev, "chan %u: Enable tsa entries failed (%d)\n",
+			chan->id, ret);
+		goto end;
+	}
+
+	ret = qmc_setup_chan_trnsync(chan->qmc, chan);
+	if (ret) {
+		dev_err(chan->qmc->dev, "chan %u: setup TRNSYNC failed (%d)\n",
+			chan->id, ret);
+		goto end;
+	}
+
 	/* Restart the receiver */
 	if (chan->mode == QMC_TRANSPARENT)
 		qmc_write32(chan->s_param + QMC_SPE_ZDSTATE, 0x18000080);
@@ -624,15 +957,38 @@ static void qmc_chan_start_rx(struct qmc_chan *chan)
 
 	chan->is_rx_stopped = false;
 
+end:
 	spin_unlock_irqrestore(&chan->rx_lock, flags);
+	return ret;
 }
 
-static void qmc_chan_start_tx(struct qmc_chan *chan)
+static int qmc_chan_start_tx(struct qmc_chan *chan)
 {
 	unsigned long flags;
+	int ret;
 
 	spin_lock_irqsave(&chan->tx_lock, flags);
 
+	if (!chan->is_tx_stopped) {
+		/* The channel is already started -> simply return ok */
+		ret = 0;
+		goto end;
+	}
+
+	ret = qmc_chan_setup_tsa_tx(chan, true);
+	if (ret) {
+		dev_err(chan->qmc->dev, "chan %u: Enable tsa entries failed (%d)\n",
+			chan->id, ret);
+		goto end;
+	}
+
+	ret = qmc_setup_chan_trnsync(chan->qmc, chan);
+	if (ret) {
+		dev_err(chan->qmc->dev, "chan %u: setup TRNSYNC failed (%d)\n",
+			chan->id, ret);
+		goto end;
+	}
+
 	/*
 	 * Enable channel transmitter as it could be disabled if
 	 * qmc_chan_reset() was called.
@@ -644,18 +1000,39 @@ static void qmc_chan_start_tx(struct qmc_chan *chan)
 
 	chan->is_tx_stopped = false;
 
+end:
 	spin_unlock_irqrestore(&chan->tx_lock, flags);
+	return ret;
 }
 
 int qmc_chan_start(struct qmc_chan *chan, int direction)
 {
-	if (direction & QMC_CHAN_READ)
-		qmc_chan_start_rx(chan);
+	bool is_rx_rollback_needed = false;
+	unsigned long flags;
+	int ret = 0;
 
-	if (direction & QMC_CHAN_WRITE)
-		qmc_chan_start_tx(chan);
+	spin_lock_irqsave(&chan->ts_lock, flags);
 
-	return 0;
+	if (direction & QMC_CHAN_READ) {
+		is_rx_rollback_needed = chan->is_rx_stopped;
+		ret = qmc_chan_start_rx(chan);
+		if (ret)
+			goto end;
+	}
+
+	if (direction & QMC_CHAN_WRITE) {
+		ret = qmc_chan_start_tx(chan);
+		if (ret) {
+			/* Restop rx if needed */
+			if (is_rx_rollback_needed)
+				qmc_chan_stop_rx(chan);
+			goto end;
+		}
+	}
+
+end:
+	spin_unlock_irqrestore(&chan->ts_lock, flags);
+	return ret;
 }
 EXPORT_SYMBOL(qmc_chan_start);
 
@@ -663,7 +1040,7 @@ static void qmc_chan_reset_rx(struct qmc_chan *chan)
 {
 	struct qmc_xfer_desc *xfer_desc;
 	unsigned long flags;
-	cbd_t *__iomem bd;
+	cbd_t __iomem *bd;
 	u16 ctrl;
 
 	spin_lock_irqsave(&chan->rx_lock, flags);
@@ -685,7 +1062,6 @@ static void qmc_chan_reset_rx(struct qmc_chan *chan)
 		    qmc_read16(chan->s_param + QMC_SPE_RBASE));
 
 	chan->rx_pending = 0;
-	chan->is_rx_stopped = false;
 
 	spin_unlock_irqrestore(&chan->rx_lock, flags);
 }
@@ -694,7 +1070,7 @@ static void qmc_chan_reset_tx(struct qmc_chan *chan)
 {
 	struct qmc_xfer_desc *xfer_desc;
 	unsigned long flags;
-	cbd_t *__iomem bd;
+	cbd_t __iomem *bd;
 	u16 ctrl;
 
 	spin_lock_irqsave(&chan->tx_lock, flags);
@@ -741,10 +1117,7 @@ EXPORT_SYMBOL(qmc_chan_reset);
 static int qmc_check_chans(struct qmc *qmc)
 {
 	struct tsa_serial_info info;
-	bool is_one_table = false;
 	struct qmc_chan *chan;
-	u64 tx_ts_mask = 0;
-	u64 rx_ts_mask = 0;
 	u64 tx_ts_assigned_mask;
 	u64 rx_ts_assigned_mask;
 	int ret;
@@ -768,38 +1141,21 @@ static int qmc_check_chans(struct qmc *qmc)
 			dev_err(qmc->dev, "Number of TSA Tx/Rx TS assigned are not equal\n");
 			return -EINVAL;
 		}
-		is_one_table = true;
 	}
 
 	tx_ts_assigned_mask = info.nb_tx_ts == 64 ? U64_MAX : (((u64)1) << info.nb_tx_ts) - 1;
 	rx_ts_assigned_mask = info.nb_rx_ts == 64 ? U64_MAX : (((u64)1) << info.nb_rx_ts) - 1;
 
 	list_for_each_entry(chan, &qmc->chan_head, list) {
-		if (chan->tx_ts_mask > tx_ts_assigned_mask) {
-			dev_err(qmc->dev, "chan %u uses TSA unassigned Tx TS\n", chan->id);
-			return -EINVAL;
-		}
-		if (tx_ts_mask & chan->tx_ts_mask) {
-			dev_err(qmc->dev, "chan %u uses an already used Tx TS\n", chan->id);
+		if (chan->tx_ts_mask_avail > tx_ts_assigned_mask) {
+			dev_err(qmc->dev, "chan %u can use TSA unassigned Tx TS\n", chan->id);
 			return -EINVAL;
 		}
 
-		if (chan->rx_ts_mask > rx_ts_assigned_mask) {
-			dev_err(qmc->dev, "chan %u uses TSA unassigned Rx TS\n", chan->id);
-			return -EINVAL;
-		}
-		if (rx_ts_mask & chan->rx_ts_mask) {
-			dev_err(qmc->dev, "chan %u uses an already used Rx TS\n", chan->id);
+		if (chan->rx_ts_mask_avail > rx_ts_assigned_mask) {
+			dev_err(qmc->dev, "chan %u can use TSA unassigned Rx TS\n", chan->id);
 			return -EINVAL;
 		}
-
-		if (is_one_table && (chan->tx_ts_mask != chan->rx_ts_mask)) {
-			dev_err(qmc->dev, "chan %u uses different Rx and Tx TS\n", chan->id);
-			return -EINVAL;
-		}
-
-		tx_ts_mask |= chan->tx_ts_mask;
-		rx_ts_mask |= chan->rx_ts_mask;
 	}
 
 	return 0;
@@ -845,6 +1201,7 @@ static int qmc_of_parse_chans(struct qmc *qmc, struct device_node *np)
 		}
 
 		chan->id = chan_id;
+		spin_lock_init(&chan->ts_lock);
 		spin_lock_init(&chan->rx_lock);
 		spin_lock_init(&chan->tx_lock);
 
@@ -855,7 +1212,8 @@ static int qmc_of_parse_chans(struct qmc *qmc, struct device_node *np)
 			of_node_put(chan_np);
 			return ret;
 		}
-		chan->tx_ts_mask = ts_mask;
+		chan->tx_ts_mask_avail = ts_mask;
+		chan->tx_ts_mask = chan->tx_ts_mask_avail;
 
 		ret = of_property_read_u64(chan_np, "fsl,rx-ts-mask", &ts_mask);
 		if (ret) {
@@ -864,7 +1222,8 @@ static int qmc_of_parse_chans(struct qmc *qmc, struct device_node *np)
 			of_node_put(chan_np);
 			return ret;
 		}
-		chan->rx_ts_mask = ts_mask;
+		chan->rx_ts_mask_avail = ts_mask;
+		chan->rx_ts_mask = chan->rx_ts_mask_avail;
 
 		mode = "transparent";
 		ret = of_property_read_string(chan_np, "fsl,operational-mode", &mode);
@@ -895,9 +1254,8 @@ static int qmc_of_parse_chans(struct qmc *qmc, struct device_node *np)
 	return qmc_check_chans(qmc);
 }
 
-static int qmc_setup_tsa_64rxtx(struct qmc *qmc, const struct tsa_serial_info *info)
+static int qmc_init_tsa_64rxtx(struct qmc *qmc, const struct tsa_serial_info *info)
 {
-	struct qmc_chan *chan;
 	unsigned int i;
 	u16 val;
 
@@ -906,23 +1264,12 @@ static int qmc_setup_tsa_64rxtx(struct qmc *qmc, const struct tsa_serial_info *i
 	 * Everything was previously checked, Tx and Rx related stuffs are
 	 * identical -> Used Rx related stuff to build the table
 	 */
+	qmc->is_tsa_64rxtx = true;
 
 	/* Invalidate all entries */
 	for (i = 0; i < 64; i++)
 		qmc_write16(qmc->scc_pram + QMC_GBL_TSATRX + (i * 2), 0x0000);
 
-	/* Set entries based on Rx stuff*/
-	list_for_each_entry(chan, &qmc->chan_head, list) {
-		for (i = 0; i < info->nb_rx_ts; i++) {
-			if (!(chan->rx_ts_mask & (((u64)1) << i)))
-				continue;
-
-			val = QMC_TSA_VALID | QMC_TSA_MASK |
-			      QMC_TSA_CHANNEL(chan->id);
-			qmc_write16(qmc->scc_pram + QMC_GBL_TSATRX + (i * 2), val);
-		}
-	}
-
 	/* Set Wrap bit on last entry */
 	qmc_setbits16(qmc->scc_pram + QMC_GBL_TSATRX + ((info->nb_rx_ts - 1) * 2),
 		      QMC_TSA_WRAP);
@@ -937,9 +1284,8 @@ static int qmc_setup_tsa_64rxtx(struct qmc *qmc, const struct tsa_serial_info *i
 	return 0;
 }
 
-static int qmc_setup_tsa_32rx_32tx(struct qmc *qmc, const struct tsa_serial_info *info)
+static int qmc_init_tsa_32rx_32tx(struct qmc *qmc, const struct tsa_serial_info *info)
 {
-	struct qmc_chan *chan;
 	unsigned int i;
 	u16 val;
 
@@ -947,6 +1293,7 @@ static int qmc_setup_tsa_32rx_32tx(struct qmc *qmc, const struct tsa_serial_info
 	 * Use a Tx 32 entries table and a Rx 32 entries table.
 	 * Everything was previously checked.
 	 */
+	qmc->is_tsa_64rxtx = false;
 
 	/* Invalidate all entries */
 	for (i = 0; i < 32; i++) {
@@ -954,28 +1301,6 @@ static int qmc_setup_tsa_32rx_32tx(struct qmc *qmc, const struct tsa_serial_info
 		qmc_write16(qmc->scc_pram + QMC_GBL_TSATTX + (i * 2), 0x0000);
 	}
 
-	/* Set entries based on Rx and Tx stuff*/
-	list_for_each_entry(chan, &qmc->chan_head, list) {
-		/* Rx part */
-		for (i = 0; i < info->nb_rx_ts; i++) {
-			if (!(chan->rx_ts_mask & (((u64)1) << i)))
-				continue;
-
-			val = QMC_TSA_VALID | QMC_TSA_MASK |
-			      QMC_TSA_CHANNEL(chan->id);
-			qmc_write16(qmc->scc_pram + QMC_GBL_TSATRX + (i * 2), val);
-		}
-		/* Tx part */
-		for (i = 0; i < info->nb_tx_ts; i++) {
-			if (!(chan->tx_ts_mask & (((u64)1) << i)))
-				continue;
-
-			val = QMC_TSA_VALID | QMC_TSA_MASK |
-			      QMC_TSA_CHANNEL(chan->id);
-			qmc_write16(qmc->scc_pram + QMC_GBL_TSATTX + (i * 2), val);
-		}
-	}
-
 	/* Set Wrap bit on last entries */
 	qmc_setbits16(qmc->scc_pram + QMC_GBL_TSATRX + ((info->nb_rx_ts - 1) * 2),
 		      QMC_TSA_WRAP);
@@ -995,7 +1320,7 @@ static int qmc_setup_tsa_32rx_32tx(struct qmc *qmc, const struct tsa_serial_info
 	return 0;
 }
 
-static int qmc_setup_tsa(struct qmc *qmc)
+static int qmc_init_tsa(struct qmc *qmc)
 {
 	struct tsa_serial_info info;
 	int ret;
@@ -1006,46 +1331,12 @@ static int qmc_setup_tsa(struct qmc *qmc)
 		return ret;
 
 	/*
-	 * Setup one common 64 entries table or two 32 entries (one for Tx and
-	 * one for Tx) according to assigned TS numbers.
+	 * Initialize one common 64 entries table or two 32 entries (one for Tx
+	 * and one for Tx) according to assigned TS numbers.
 	 */
 	return ((info.nb_tx_ts > 32) || (info.nb_rx_ts > 32)) ?
-		qmc_setup_tsa_64rxtx(qmc, &info) :
-		qmc_setup_tsa_32rx_32tx(qmc, &info);
-}
-
-static int qmc_setup_chan_trnsync(struct qmc *qmc, struct qmc_chan *chan)
-{
-	struct tsa_serial_info info;
-	u16 first_rx, last_tx;
-	u16 trnsync;
-	int ret;
-
-	/* Retrieve info from the TSA related serial */
-	ret = tsa_serial_get_info(chan->qmc->tsa_serial, &info);
-	if (ret)
-		return ret;
-
-	/* Find the first Rx TS allocated to the channel */
-	first_rx = chan->rx_ts_mask ? __ffs64(chan->rx_ts_mask) + 1 : 0;
-
-	/* Find the last Tx TS allocated to the channel */
-	last_tx = fls64(chan->tx_ts_mask);
-
-	trnsync = 0;
-	if (info.nb_rx_ts)
-		trnsync |= QMC_SPE_TRNSYNC_RX((first_rx % info.nb_rx_ts) * 2);
-	if (info.nb_tx_ts)
-		trnsync |= QMC_SPE_TRNSYNC_TX((last_tx % info.nb_tx_ts) * 2);
-
-	qmc_write16(chan->s_param + QMC_SPE_TRNSYNC, trnsync);
-
-	dev_dbg(qmc->dev, "chan %u: trnsync=0x%04x, rx %u/%u 0x%llx, tx %u/%u 0x%llx\n",
-		chan->id, trnsync,
-		first_rx, info.nb_rx_ts, chan->rx_ts_mask,
-		last_tx, info.nb_tx_ts, chan->tx_ts_mask);
-
-	return 0;
+		qmc_init_tsa_64rxtx(qmc, &info) :
+		qmc_init_tsa_32rx_32tx(qmc, &info);
 }
 
 static int qmc_setup_chan(struct qmc *qmc, struct qmc_chan *chan)
@@ -1367,7 +1658,7 @@ static int qmc_probe(struct platform_device *pdev)
 	qmc_write32(qmc->scc_pram + QMC_GBL_C_MASK32, 0xDEBB20E3);
 	qmc_write16(qmc->scc_pram + QMC_GBL_C_MASK16, 0xF0B8);
 
-	ret = qmc_setup_tsa(qmc);
+	ret = qmc_init_tsa(qmc);
 	if (ret)
 		goto err_tsa_serial_disconnect;
 
@@ -1405,8 +1696,16 @@ static int qmc_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, qmc);
 
+	/* Populate channel related devices */
+	ret = devm_of_platform_populate(qmc->dev);
+	if (ret)
+		goto err_disable_txrx;
+
 	return 0;
 
+err_disable_txrx:
+	qmc_setbits32(qmc->scc_regs + SCC_GSMRL, 0);
+
 err_disable_intr:
 	qmc_write16(qmc->scc_regs + SCC_SCCM, 0);
 
@@ -1445,26 +1744,16 @@ static struct platform_driver qmc_driver = {
 };
 module_platform_driver(qmc_driver);
 
-struct qmc_chan *qmc_chan_get_byphandle(struct device_node *np, const char *phandle_name)
+static struct qmc_chan *qmc_chan_get_from_qmc(struct device_node *qmc_np, unsigned int chan_index)
 {
-	struct of_phandle_args out_args;
 	struct platform_device *pdev;
 	struct qmc_chan *qmc_chan;
 	struct qmc *qmc;
-	int ret;
-
-	ret = of_parse_phandle_with_fixed_args(np, phandle_name, 1, 0,
-					       &out_args);
-	if (ret < 0)
-		return ERR_PTR(ret);
 
-	if (!of_match_node(qmc_driver.driver.of_match_table, out_args.np)) {
-		of_node_put(out_args.np);
+	if (!of_match_node(qmc_driver.driver.of_match_table, qmc_np))
 		return ERR_PTR(-EINVAL);
-	}
 
-	pdev = of_find_device_by_node(out_args.np);
-	of_node_put(out_args.np);
+	pdev = of_find_device_by_node(qmc_np);
 	if (!pdev)
 		return ERR_PTR(-ENODEV);
 
@@ -1474,17 +1763,12 @@ struct qmc_chan *qmc_chan_get_byphandle(struct device_node *np, const char *phan
 		return ERR_PTR(-EPROBE_DEFER);
 	}
 
-	if (out_args.args_count != 1) {
+	if (chan_index >= ARRAY_SIZE(qmc->chans)) {
 		platform_device_put(pdev);
 		return ERR_PTR(-EINVAL);
 	}
 
-	if (out_args.args[0] >= ARRAY_SIZE(qmc->chans)) {
-		platform_device_put(pdev);
-		return ERR_PTR(-EINVAL);
-	}
-
-	qmc_chan = qmc->chans[out_args.args[0]];
+	qmc_chan = qmc->chans[chan_index];
 	if (!qmc_chan) {
 		platform_device_put(pdev);
 		return ERR_PTR(-ENOENT);
@@ -1492,8 +1776,44 @@ struct qmc_chan *qmc_chan_get_byphandle(struct device_node *np, const char *phan
 
 	return qmc_chan;
 }
+
+struct qmc_chan *qmc_chan_get_byphandle(struct device_node *np, const char *phandle_name)
+{
+	struct of_phandle_args out_args;
+	struct qmc_chan *qmc_chan;
+	int ret;
+
+	ret = of_parse_phandle_with_fixed_args(np, phandle_name, 1, 0,
+					       &out_args);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	if (out_args.args_count != 1) {
+		of_node_put(out_args.np);
+		return ERR_PTR(-EINVAL);
+	}
+
+	qmc_chan = qmc_chan_get_from_qmc(out_args.np, out_args.args[0]);
+	of_node_put(out_args.np);
+	return qmc_chan;
+}
 EXPORT_SYMBOL(qmc_chan_get_byphandle);
 
+struct qmc_chan *qmc_chan_get_bychild(struct device_node *np)
+{
+	struct device_node *qmc_np;
+	u32 chan_index;
+	int ret;
+
+	qmc_np = np->parent;
+	ret = of_property_read_u32(np, "reg", &chan_index);
+	if (ret)
+		return ERR_PTR(-EINVAL);
+
+	return qmc_chan_get_from_qmc(qmc_np, chan_index);
+}
+EXPORT_SYMBOL(qmc_chan_get_bychild);
+
 void qmc_chan_put(struct qmc_chan *chan)
 {
 	put_device(chan->qmc->dev);
@@ -1530,6 +1850,28 @@ struct qmc_chan *devm_qmc_chan_get_byphandle(struct device *dev,
 }
 EXPORT_SYMBOL(devm_qmc_chan_get_byphandle);
 
+struct qmc_chan *devm_qmc_chan_get_bychild(struct device *dev,
+					   struct device_node *np)
+{
+	struct qmc_chan *qmc_chan;
+	struct qmc_chan **dr;
+
+	dr = devres_alloc(devm_qmc_chan_release, sizeof(*dr), GFP_KERNEL);
+	if (!dr)
+		return ERR_PTR(-ENOMEM);
+
+	qmc_chan = qmc_chan_get_bychild(np);
+	if (!IS_ERR(qmc_chan)) {
+		*dr = qmc_chan;
+		devres_add(dev, dr);
+	} else {
+		devres_free(dr);
+	}
+
+	return qmc_chan;
+}
+EXPORT_SYMBOL(devm_qmc_chan_get_bychild);
+
 MODULE_AUTHOR("Herve Codina <herve.codina@bootlin.com>");
 MODULE_DESCRIPTION("CPM QMC driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/soc/fsl/qe/tsa.c b/drivers/soc/fsl/qe/tsa.c
index 3f9981335590..6c5741cf5e9d 100644
--- a/drivers/soc/fsl/qe/tsa.c
+++ b/drivers/soc/fsl/qe/tsa.c
@@ -98,9 +98,9 @@
 #define TSA_SIRP	0x10
 
 struct tsa_entries_area {
-	void *__iomem entries_start;
-	void *__iomem entries_next;
-	void *__iomem last_entry;
+	void __iomem *entries_start;
+	void __iomem *entries_next;
+	void __iomem *last_entry;
 };
 
 struct tsa_tdm {
@@ -117,8 +117,8 @@ struct tsa_tdm {
 
 struct tsa {
 	struct device *dev;
-	void *__iomem si_regs;
-	void *__iomem si_ram;
+	void __iomem *si_regs;
+	void __iomem *si_ram;
 	resource_size_t si_ram_sz;
 	spinlock_t	lock;
 	int tdms; /* TSA_TDMx ORed */
@@ -135,27 +135,27 @@ static inline struct tsa *tsa_serial_get_tsa(struct tsa_serial *tsa_serial)
 	return container_of(tsa_serial, struct tsa, serials[tsa_serial->id]);
 }
 
-static inline void tsa_write32(void *__iomem addr, u32 val)
+static inline void tsa_write32(void __iomem *addr, u32 val)
 {
 	iowrite32be(val, addr);
 }
 
-static inline void tsa_write8(void *__iomem addr, u32 val)
+static inline void tsa_write8(void __iomem *addr, u32 val)
 {
 	iowrite8(val, addr);
 }
 
-static inline u32 tsa_read32(void *__iomem addr)
+static inline u32 tsa_read32(void __iomem *addr)
 {
 	return ioread32be(addr);
 }
 
-static inline void tsa_clrbits32(void *__iomem addr, u32 clr)
+static inline void tsa_clrbits32(void __iomem *addr, u32 clr)
 {
 	tsa_write32(addr, tsa_read32(addr) & ~clr);
 }
 
-static inline void tsa_clrsetbits32(void *__iomem addr, u32 clr, u32 set)
+static inline void tsa_clrsetbits32(void __iomem *addr, u32 clr, u32 set)
 {
 	tsa_write32(addr, (tsa_read32(addr) & ~clr) | set);
 }
@@ -313,7 +313,7 @@ static u32 tsa_serial_id2csel(struct tsa *tsa, u32 serial_id)
 static int tsa_add_entry(struct tsa *tsa, struct tsa_entries_area *area,
 			 u32 count, u32 serial_id)
 {
-	void *__iomem addr;
+	void __iomem *addr;
 	u32 left;
 	u32 val;
 	u32 cnt;
diff --git a/drivers/soc/hisilicon/kunpeng_hccs.c b/drivers/soc/hisilicon/kunpeng_hccs.c
index e31791659560..9ff70b38e5e9 100644
--- a/drivers/soc/hisilicon/kunpeng_hccs.c
+++ b/drivers/soc/hisilicon/kunpeng_hccs.c
@@ -85,8 +85,10 @@ static int hccs_get_pcc_chan_id(struct hccs_dev *hdev)
 	struct hccs_register_ctx ctx = {0};
 	acpi_status status;
 
-	if (!acpi_has_method(handle, METHOD_NAME__CRS))
+	if (!acpi_has_method(handle, METHOD_NAME__CRS)) {
+		dev_err(hdev->dev, "No _CRS method.\n");
 		return -ENODEV;
+	}
 
 	ctx.dev = hdev->dev;
 	status = acpi_walk_resources(handle, METHOD_NAME__CRS,
@@ -108,6 +110,14 @@ static void hccs_chan_tx_done(struct mbox_client *cl, void *msg, int ret)
 			 *(u8 *)msg, ret);
 }
 
+static void hccs_pcc_rx_callback(struct mbox_client *cl, void *mssg)
+{
+	struct hccs_mbox_client_info *cl_info =
+			container_of(cl, struct hccs_mbox_client_info, client);
+
+	complete(&cl_info->done);
+}
+
 static void hccs_unregister_pcc_channel(struct hccs_dev *hdev)
 {
 	struct hccs_mbox_client_info *cl_info = &hdev->cl_info;
@@ -129,6 +139,9 @@ static int hccs_register_pcc_channel(struct hccs_dev *hdev)
 	cl->tx_block = false;
 	cl->knows_txdone = true;
 	cl->tx_done = hccs_chan_tx_done;
+	cl->rx_callback = hdev->verspec_data->rx_callback;
+	init_completion(&cl_info->done);
+
 	pcc_chan = pcc_mbox_request_channel(cl, hdev->chan_id);
 	if (IS_ERR(pcc_chan)) {
 		dev_err(dev, "PPC channel request failed.\n");
@@ -145,17 +158,23 @@ static int hccs_register_pcc_channel(struct hccs_dev *hdev)
 	 */
 	cl_info->deadline_us =
 			HCCS_PCC_CMD_WAIT_RETRIES_NUM * pcc_chan->latency;
-	if (cl_info->mbox_chan->mbox->txdone_irq) {
+	if (!hdev->verspec_data->has_txdone_irq &&
+	    cl_info->mbox_chan->mbox->txdone_irq) {
 		dev_err(dev, "PCC IRQ in PCCT is enabled.\n");
 		rc = -EINVAL;
 		goto err_mbx_channel_free;
+	} else if (hdev->verspec_data->has_txdone_irq &&
+		   !cl_info->mbox_chan->mbox->txdone_irq) {
+		dev_err(dev, "PCC IRQ in PCCT isn't supported.\n");
+		rc = -EINVAL;
+		goto err_mbx_channel_free;
 	}
 
 	if (pcc_chan->shmem_base_addr) {
 		cl_info->pcc_comm_addr = ioremap(pcc_chan->shmem_base_addr,
 						 pcc_chan->shmem_size);
 		if (!cl_info->pcc_comm_addr) {
-			dev_err(dev, "Failed to ioremap PCC communication region for channel-%d.\n",
+			dev_err(dev, "Failed to ioremap PCC communication region for channel-%u.\n",
 				hdev->chan_id);
 			rc = -ENOMEM;
 			goto err_mbx_channel_free;
@@ -170,7 +189,7 @@ out:
 	return rc;
 }
 
-static int hccs_check_chan_cmd_complete(struct hccs_dev *hdev)
+static int hccs_wait_cmd_complete_by_poll(struct hccs_dev *hdev)
 {
 	struct hccs_mbox_client_info *cl_info = &hdev->cl_info;
 	struct acpi_pcct_shared_memory __iomem *comm_base =
@@ -192,30 +211,74 @@ static int hccs_check_chan_cmd_complete(struct hccs_dev *hdev)
 	return ret;
 }
 
+static int hccs_wait_cmd_complete_by_irq(struct hccs_dev *hdev)
+{
+	struct hccs_mbox_client_info *cl_info = &hdev->cl_info;
+
+	if (!wait_for_completion_timeout(&cl_info->done,
+			usecs_to_jiffies(cl_info->deadline_us))) {
+		dev_err(hdev->dev, "PCC command executed timeout!\n");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+static inline void hccs_fill_pcc_shared_mem_region(struct hccs_dev *hdev,
+						   u8 cmd,
+						   struct hccs_desc *desc,
+						   void __iomem *comm_space,
+						   u16 space_size)
+{
+	struct acpi_pcct_shared_memory tmp = {
+		.signature = PCC_SIGNATURE | hdev->chan_id,
+		.command = cmd,
+		.status = 0,
+	};
+
+	memcpy_toio(hdev->cl_info.pcc_comm_addr, (void *)&tmp,
+		    sizeof(struct acpi_pcct_shared_memory));
+
+	/* Copy the message to the PCC comm space */
+	memcpy_toio(comm_space, (void *)desc, space_size);
+}
+
+static inline void hccs_fill_ext_pcc_shared_mem_region(struct hccs_dev *hdev,
+						       u8 cmd,
+						       struct hccs_desc *desc,
+						       void __iomem *comm_space,
+						       u16 space_size)
+{
+	struct acpi_pcct_ext_pcc_shared_memory tmp = {
+		.signature = PCC_SIGNATURE | hdev->chan_id,
+		.flags = PCC_CMD_COMPLETION_NOTIFY,
+		.length = HCCS_PCC_SHARE_MEM_BYTES,
+		.command = cmd,
+	};
+
+	memcpy_toio(hdev->cl_info.pcc_comm_addr, (void *)&tmp,
+		    sizeof(struct acpi_pcct_ext_pcc_shared_memory));
+
+	/* Copy the message to the PCC comm space */
+	memcpy_toio(comm_space, (void *)desc, space_size);
+}
+
 static int hccs_pcc_cmd_send(struct hccs_dev *hdev, u8 cmd,
 			     struct hccs_desc *desc)
 {
+	const struct hccs_verspecific_data *verspec_data = hdev->verspec_data;
 	struct hccs_mbox_client_info *cl_info = &hdev->cl_info;
-	void __iomem *comm_space = cl_info->pcc_comm_addr +
-					sizeof(struct acpi_pcct_shared_memory);
 	struct hccs_fw_inner_head *fw_inner_head;
-	struct acpi_pcct_shared_memory tmp = {0};
-	u16 comm_space_size;
+	void __iomem *comm_space;
+	u16 space_size;
 	int ret;
 
-	/* Write signature for this subspace */
-	tmp.signature = PCC_SIGNATURE | hdev->chan_id;
-	/* Write to the shared command region */
-	tmp.command = cmd;
-	/* Clear cmd complete bit */
-	tmp.status = 0;
-	memcpy_toio(cl_info->pcc_comm_addr, (void *)&tmp,
-			sizeof(struct acpi_pcct_shared_memory));
-
-	/* Copy the message to the PCC comm space */
-	comm_space_size = HCCS_PCC_SHARE_MEM_BYTES -
-				sizeof(struct acpi_pcct_shared_memory);
-	memcpy_toio(comm_space, (void *)desc, comm_space_size);
+	comm_space = cl_info->pcc_comm_addr + verspec_data->shared_mem_size;
+	space_size = HCCS_PCC_SHARE_MEM_BYTES - verspec_data->shared_mem_size;
+	verspec_data->fill_pcc_shared_mem(hdev, cmd, desc,
+					  comm_space, space_size);
+	if (verspec_data->has_txdone_irq)
+		reinit_completion(&cl_info->done);
 
 	/* Ring doorbell */
 	ret = mbox_send_message(cl_info->mbox_chan, &cmd);
@@ -225,13 +288,12 @@ static int hccs_pcc_cmd_send(struct hccs_dev *hdev, u8 cmd,
 		goto end;
 	}
 
-	/* Wait for completion */
-	ret = hccs_check_chan_cmd_complete(hdev);
+	ret = verspec_data->wait_cmd_complete(hdev);
 	if (ret)
 		goto end;
 
 	/* Copy response data */
-	memcpy_fromio((void *)desc, comm_space, comm_space_size);
+	memcpy_fromio((void *)desc, comm_space, space_size);
 	fw_inner_head = &desc->rsp.fw_inner_head;
 	if (fw_inner_head->retStatus) {
 		dev_err(hdev->dev, "Execute PCC command failed, error code = %u.\n",
@@ -240,7 +302,10 @@ static int hccs_pcc_cmd_send(struct hccs_dev *hdev, u8 cmd,
 	}
 
 end:
-	mbox_client_txdone(cl_info->mbox_chan, ret);
+	if (verspec_data->has_txdone_irq)
+		mbox_chan_txdone(cl_info->mbox_chan, ret);
+	else
+		mbox_client_txdone(cl_info->mbox_chan, ret);
 	return ret;
 }
 
@@ -527,7 +592,6 @@ out:
 
 static int hccs_query_all_port_info_on_platform(struct hccs_dev *hdev)
 {
-
 	struct device *dev = hdev->dev;
 	struct hccs_chip_info *chip;
 	struct hccs_die_info *die;
@@ -1097,7 +1161,7 @@ static int hccs_create_hccs_dir(struct hccs_dev *hdev,
 	int ret;
 
 	ret = kobject_init_and_add(&port->kobj, &hccs_port_type,
-				   &die->kobj, "hccs%d", port->port_id);
+				   &die->kobj, "hccs%u", port->port_id);
 	if (ret) {
 		kobject_put(&port->kobj);
 		return ret;
@@ -1115,7 +1179,7 @@ static int hccs_create_die_dir(struct hccs_dev *hdev,
 	u16 i;
 
 	ret = kobject_init_and_add(&die->kobj, &hccs_die_type,
-				   &chip->kobj, "die%d", die->die_id);
+				   &chip->kobj, "die%u", die->die_id);
 	if (ret) {
 		kobject_put(&die->kobj);
 		return ret;
@@ -1125,7 +1189,7 @@ static int hccs_create_die_dir(struct hccs_dev *hdev,
 		port = &die->ports[i];
 		ret = hccs_create_hccs_dir(hdev, die, port);
 		if (ret) {
-			dev_err(hdev->dev, "create hccs%d dir failed.\n",
+			dev_err(hdev->dev, "create hccs%u dir failed.\n",
 				port->port_id);
 			goto err;
 		}
@@ -1147,7 +1211,7 @@ static int hccs_create_chip_dir(struct hccs_dev *hdev,
 	u16 id;
 
 	ret = kobject_init_and_add(&chip->kobj, &hccs_chip_type,
-				   &hdev->dev->kobj, "chip%d", chip->chip_id);
+				   &hdev->dev->kobj, "chip%u", chip->chip_id);
 	if (ret) {
 		kobject_put(&chip->kobj);
 		return ret;
@@ -1178,7 +1242,7 @@ static int hccs_create_topo_dirs(struct hccs_dev *hdev)
 		chip = &hdev->chips[id];
 		ret = hccs_create_chip_dir(hdev, chip);
 		if (ret) {
-			dev_err(hdev->dev, "init chip%d dir failed!\n", id);
+			dev_err(hdev->dev, "init chip%u dir failed!\n", id);
 			goto err;
 		}
 	}
@@ -1212,6 +1276,11 @@ static int hccs_probe(struct platform_device *pdev)
 	hdev->dev = &pdev->dev;
 	platform_set_drvdata(pdev, hdev);
 
+	/*
+	 * Here would never be failure as the driver and device has been matched.
+	 */
+	hdev->verspec_data = acpi_device_get_match_data(hdev->dev);
+
 	mutex_init(&hdev->lock);
 	rc = hccs_get_pcc_chan_id(hdev);
 	if (rc)
@@ -1248,9 +1317,26 @@ static void hccs_remove(struct platform_device *pdev)
 	hccs_unregister_pcc_channel(hdev);
 }
 
+static const struct hccs_verspecific_data hisi04b1_verspec_data = {
+	.rx_callback = NULL,
+	.wait_cmd_complete = hccs_wait_cmd_complete_by_poll,
+	.fill_pcc_shared_mem = hccs_fill_pcc_shared_mem_region,
+	.shared_mem_size = sizeof(struct acpi_pcct_shared_memory),
+	.has_txdone_irq = false,
+};
+
+static const struct hccs_verspecific_data hisi04b2_verspec_data = {
+	.rx_callback = hccs_pcc_rx_callback,
+	.wait_cmd_complete = hccs_wait_cmd_complete_by_irq,
+	.fill_pcc_shared_mem = hccs_fill_ext_pcc_shared_mem_region,
+	.shared_mem_size = sizeof(struct acpi_pcct_ext_pcc_shared_memory),
+	.has_txdone_irq = true,
+};
+
 static const struct acpi_device_id hccs_acpi_match[] = {
-	{ "HISI04B1"},
-	{ ""},
+	{ "HISI04B1", (unsigned long)&hisi04b1_verspec_data},
+	{ "HISI04B2", (unsigned long)&hisi04b2_verspec_data},
+	{ }
 };
 MODULE_DEVICE_TABLE(acpi, hccs_acpi_match);
 
diff --git a/drivers/soc/hisilicon/kunpeng_hccs.h b/drivers/soc/hisilicon/kunpeng_hccs.h
index 6012d2776028..c3adbc01b471 100644
--- a/drivers/soc/hisilicon/kunpeng_hccs.h
+++ b/drivers/soc/hisilicon/kunpeng_hccs.h
@@ -51,11 +51,26 @@ struct hccs_mbox_client_info {
 	struct pcc_mbox_chan *pcc_chan;
 	u64 deadline_us;
 	void __iomem *pcc_comm_addr;
+	struct completion done;
+};
+
+struct hccs_desc;
+
+struct hccs_verspecific_data {
+	void (*rx_callback)(struct mbox_client *cl, void *mssg);
+	int (*wait_cmd_complete)(struct hccs_dev *hdev);
+	void (*fill_pcc_shared_mem)(struct hccs_dev *hdev,
+				    u8 cmd, struct hccs_desc *desc,
+				    void __iomem *comm_space,
+				    u16 space_size);
+	u16 shared_mem_size;
+	bool has_txdone_irq;
 };
 
 struct hccs_dev {
 	struct device *dev;
 	struct acpi_device *acpi_dev;
+	const struct hccs_verspecific_data *verspec_data;
 	u64 caps;
 	u8 chip_num;
 	struct hccs_chip_info *chips;
diff --git a/drivers/soc/mediatek/mt8188-mmsys.h b/drivers/soc/mediatek/mt8188-mmsys.h
index 448cc3761b43..6bebf1a69fc0 100644
--- a/drivers/soc/mediatek/mt8188-mmsys.h
+++ b/drivers/soc/mediatek/mt8188-mmsys.h
@@ -3,6 +3,10 @@
 #ifndef __SOC_MEDIATEK_MT8188_MMSYS_H
 #define __SOC_MEDIATEK_MT8188_MMSYS_H
 
+#include <linux/soc/mediatek/mtk-mmsys.h>
+#include <dt-bindings/reset/mt8188-resets.h>
+
+#define MT8188_VDO0_SW0_RST_B				0x190
 #define MT8188_VDO0_OVL_MOUT_EN				0xf14
 #define MT8188_MOUT_DISP_OVL0_TO_DISP_RDMA0		BIT(0)
 #define MT8188_MOUT_DISP_OVL0_TO_DISP_WDMA0		BIT(1)
@@ -67,6 +71,136 @@
 #define MT8188_SOUT_DSC_WRAP0_OUT_TO_VPP_MERGE		BIT(18)
 #define MT8188_SOUT_DSC_WRAP0_OUT_TO_DISP_WDMA0		BIT(19)
 
+#define MT8188_VDO1_SW0_RST_B					0x1d0
+#define MT8188_VDO1_HDR_TOP_CFG					0xd00
+#define MT8188_VDO1_MIXER_IN1_ALPHA				0xd30
+#define MT8188_VDO1_MIXER_IN1_PAD				0xd40
+#define MT8188_VDO1_MIXER_VSYNC_LEN				0xd5c
+#define MT8188_VDO1_MERGE0_ASYNC_CFG_WD				0xe30
+#define MT8188_VDO1_HDRBE_ASYNC_CFG_WD				0xe70
+#define MT8188_VDO1_VPP_MERGE0_P0_SEL_IN			0xf04
+#define MT8188_VPP_MERGE0_P0_SEL_IN_FROM_MDP_RDMA0		1
+#define MT8188_VDO1_VPP_MERGE0_P1_SEL_IN			0xf08
+#define MT8188_VPP_MERGE0_P1_SEL_IN_FROM_MDP_RDMA1		1
+#define MT8188_VDO1_DISP_DPI1_SEL_IN				0xf10
+#define MT8188_DISP_DPI1_SEL_IN_FROM_VPP_MERGE4_MOUT		0
+#define MT8188_VDO1_DISP_DP_INTF0_SEL_IN			0xf14
+#define MT8188_DISP_DP_INTF0_SEL_IN_FROM_VPP_MERGE4_MOUT	0
+#define MT8188_VDO1_MERGE4_SOUT_SEL				0xf18
+#define MT8188_MERGE4_SOUT_TO_DPI1_SEL				BIT(2)
+#define MT8188_MERGE4_SOUT_TO_DP_INTF0_SEL			BIT(3)
+#define MT8188_VDO1_MIXER_IN1_SEL_IN				0xf24
+#define MT8188_MIXER_IN1_SEL_IN_FROM_MERGE0_ASYNC_SOUT		1
+#define MT8188_VDO1_MIXER_IN2_SEL_IN				0xf28
+#define MT8188_MIXER_IN2_SEL_IN_FROM_MERGE1_ASYNC_SOUT		1
+#define MT8188_VDO1_MIXER_IN3_SEL_IN				0xf2c
+#define MT8188_MIXER_IN3_SEL_IN_FROM_MERGE2_ASYNC_SOUT		1
+#define MT8188_VDO1_MIXER_IN4_SEL_IN				0xf30
+#define MT8188_MIXER_IN4_SEL_IN_FROM_MERGE3_ASYNC_SOUT		1
+#define MT8188_VDO1_MIXER_OUT_SOUT_SEL				0xf34
+#define MT8188_MIXER_SOUT_TO_MERGE4_ASYNC_SEL			1
+#define MT8188_VDO1_VPP_MERGE1_P0_SEL_IN			0xf3c
+#define MT8188_VPP_MERGE1_P0_SEL_IN_FROM_MDP_RDMA2		1
+#define MT8188_VDO1_MERGE0_ASYNC_SOUT_SEL			0xf40
+#define MT8188_SOUT_TO_MIXER_IN1_SEL				1
+#define MT8188_VDO1_MERGE1_ASYNC_SOUT_SEL			0xf44
+#define MT8188_SOUT_TO_MIXER_IN2_SEL				1
+#define MT8188_VDO1_MERGE2_ASYNC_SOUT_SEL			0xf48
+#define MT8188_SOUT_TO_MIXER_IN3_SEL				1
+#define MT8188_VDO1_MERGE3_ASYNC_SOUT_SEL			0xf4c
+#define MT8188_SOUT_TO_MIXER_IN4_SEL				1
+#define MT8188_VDO1_MERGE4_ASYNC_SEL_IN				0xf50
+#define MT8188_MERGE4_ASYNC_SEL_IN_FROM_MIXER_OUT_SOUT		1
+#define MT8188_VDO1_MIXER_IN1_SOUT_SEL				0xf58
+#define MT8188_MIXER_IN1_SOUT_TO_DISP_MIXER			0
+#define MT8188_VDO1_MIXER_IN2_SOUT_SEL				0xf5c
+#define MT8188_MIXER_IN2_SOUT_TO_DISP_MIXER			0
+#define MT8188_VDO1_MIXER_IN3_SOUT_SEL				0xf60
+#define MT8188_MIXER_IN3_SOUT_TO_DISP_MIXER			0
+#define MT8188_VDO1_MIXER_IN4_SOUT_SEL				0xf64
+#define MT8188_MIXER_IN4_SOUT_TO_DISP_MIXER			0
+#define MT8188_VDO1_MIXER_SOUT_SEL_IN				0xf68
+#define MT8188_MIXER_SOUT_SEL_IN_FROM_DISP_MIXER		0
+
+static const u8 mmsys_mt8188_vdo0_rst_tb[] = {
+	[MT8188_VDO0_RST_DISP_OVL0]	= MMSYS_RST_NR(0, 0),
+	[MT8188_VDO0_RST_FAKE_ENG0]	= MMSYS_RST_NR(0, 2),
+	[MT8188_VDO0_RST_DISP_CCORR0]	= MMSYS_RST_NR(0, 4),
+	[MT8188_VDO0_RST_DISP_MUTEX0]	= MMSYS_RST_NR(0, 6),
+	[MT8188_VDO0_RST_DISP_GAMMA0]	= MMSYS_RST_NR(0, 8),
+	[MT8188_VDO0_RST_DISP_DITHER0]	= MMSYS_RST_NR(0, 10),
+	[MT8188_VDO0_RST_DISP_WDMA0]	= MMSYS_RST_NR(0, 17),
+	[MT8188_VDO0_RST_DISP_RDMA0]	= MMSYS_RST_NR(0, 19),
+	[MT8188_VDO0_RST_DSI0]		= MMSYS_RST_NR(0, 21),
+	[MT8188_VDO0_RST_DSI1]		= MMSYS_RST_NR(0, 22),
+	[MT8188_VDO0_RST_DSC_WRAP0]	= MMSYS_RST_NR(0, 23),
+	[MT8188_VDO0_RST_VPP_MERGE0]	= MMSYS_RST_NR(0, 24),
+	[MT8188_VDO0_RST_DP_INTF0]	= MMSYS_RST_NR(0, 25),
+	[MT8188_VDO0_RST_DISP_AAL0]	= MMSYS_RST_NR(0, 26),
+	[MT8188_VDO0_RST_INLINEROT0]	= MMSYS_RST_NR(0, 27),
+	[MT8188_VDO0_RST_APB_BUS]	= MMSYS_RST_NR(0, 28),
+	[MT8188_VDO0_RST_DISP_COLOR0]	= MMSYS_RST_NR(0, 29),
+	[MT8188_VDO0_RST_MDP_WROT0]	= MMSYS_RST_NR(0, 30),
+	[MT8188_VDO0_RST_DISP_RSZ0]	= MMSYS_RST_NR(0, 31),
+};
+
+static const u8 mmsys_mt8188_vdo1_rst_tb[] = {
+	[MT8188_VDO1_RST_SMI_LARB2]			= MMSYS_RST_NR(0, 0),
+	[MT8188_VDO1_RST_SMI_LARB3]			= MMSYS_RST_NR(0, 1),
+	[MT8188_VDO1_RST_GALS]				= MMSYS_RST_NR(0, 2),
+	[MT8188_VDO1_RST_FAKE_ENG0]			= MMSYS_RST_NR(0, 3),
+	[MT8188_VDO1_RST_FAKE_ENG1]			= MMSYS_RST_NR(0, 4),
+	[MT8188_VDO1_RST_MDP_RDMA0]			= MMSYS_RST_NR(0, 5),
+	[MT8188_VDO1_RST_MDP_RDMA1]			= MMSYS_RST_NR(0, 6),
+	[MT8188_VDO1_RST_MDP_RDMA2]			= MMSYS_RST_NR(0, 7),
+	[MT8188_VDO1_RST_MDP_RDMA3]			= MMSYS_RST_NR(0, 8),
+	[MT8188_VDO1_RST_VPP_MERGE0]			= MMSYS_RST_NR(0, 9),
+	[MT8188_VDO1_RST_VPP_MERGE1]			= MMSYS_RST_NR(0, 10),
+	[MT8188_VDO1_RST_VPP_MERGE2]			= MMSYS_RST_NR(0, 11),
+	[MT8188_VDO1_RST_VPP_MERGE3]			= MMSYS_RST_NR(1, 0),
+	[MT8188_VDO1_RST_VPP_MERGE4]			= MMSYS_RST_NR(1, 1),
+	[MT8188_VDO1_RST_VPP2_TO_VDO1_DL_ASYNC]		= MMSYS_RST_NR(1, 2),
+	[MT8188_VDO1_RST_VPP3_TO_VDO1_DL_ASYNC]		= MMSYS_RST_NR(1, 3),
+	[MT8188_VDO1_RST_DISP_MUTEX]			= MMSYS_RST_NR(1, 4),
+	[MT8188_VDO1_RST_MDP_RDMA4]			= MMSYS_RST_NR(1, 5),
+	[MT8188_VDO1_RST_MDP_RDMA5]			= MMSYS_RST_NR(1, 6),
+	[MT8188_VDO1_RST_MDP_RDMA6]			= MMSYS_RST_NR(1, 7),
+	[MT8188_VDO1_RST_MDP_RDMA7]			= MMSYS_RST_NR(1, 8),
+	[MT8188_VDO1_RST_DP_INTF1_MMCK]			= MMSYS_RST_NR(1, 9),
+	[MT8188_VDO1_RST_DPI0_MM_CK]			= MMSYS_RST_NR(1, 10),
+	[MT8188_VDO1_RST_DPI1_MM_CK]			= MMSYS_RST_NR(1, 11),
+	[MT8188_VDO1_RST_MERGE0_DL_ASYNC]		= MMSYS_RST_NR(1, 13),
+	[MT8188_VDO1_RST_MERGE1_DL_ASYNC]		= MMSYS_RST_NR(1, 14),
+	[MT8188_VDO1_RST_MERGE2_DL_ASYNC]		= MMSYS_RST_NR(1, 15),
+	[MT8188_VDO1_RST_MERGE3_DL_ASYNC]		= MMSYS_RST_NR(1, 16),
+	[MT8188_VDO1_RST_MERGE4_DL_ASYNC]		= MMSYS_RST_NR(1, 17),
+	[MT8188_VDO1_RST_VDO0_DSC_TO_VDO1_DL_ASYNC]	= MMSYS_RST_NR(1, 18),
+	[MT8188_VDO1_RST_VDO0_MERGE_TO_VDO1_DL_ASYNC]	= MMSYS_RST_NR(1, 19),
+	[MT8188_VDO1_RST_PADDING0]			= MMSYS_RST_NR(1, 20),
+	[MT8188_VDO1_RST_PADDING1]			= MMSYS_RST_NR(1, 21),
+	[MT8188_VDO1_RST_PADDING2]			= MMSYS_RST_NR(1, 22),
+	[MT8188_VDO1_RST_PADDING3]			= MMSYS_RST_NR(1, 23),
+	[MT8188_VDO1_RST_PADDING4]			= MMSYS_RST_NR(1, 24),
+	[MT8188_VDO1_RST_PADDING5]			= MMSYS_RST_NR(1, 25),
+	[MT8188_VDO1_RST_PADDING6]			= MMSYS_RST_NR(1, 26),
+	[MT8188_VDO1_RST_PADDING7]			= MMSYS_RST_NR(1, 27),
+	[MT8188_VDO1_RST_DISP_RSZ0]			= MMSYS_RST_NR(1, 28),
+	[MT8188_VDO1_RST_DISP_RSZ1]			= MMSYS_RST_NR(1, 29),
+	[MT8188_VDO1_RST_DISP_RSZ2]			= MMSYS_RST_NR(1, 30),
+	[MT8188_VDO1_RST_DISP_RSZ3]			= MMSYS_RST_NR(1, 31),
+	[MT8188_VDO1_RST_HDR_VDO_FE0]			= MMSYS_RST_NR(2, 0),
+	[MT8188_VDO1_RST_HDR_GFX_FE0]			= MMSYS_RST_NR(2, 1),
+	[MT8188_VDO1_RST_HDR_VDO_BE]			= MMSYS_RST_NR(2, 2),
+	[MT8188_VDO1_RST_HDR_VDO_FE1]			= MMSYS_RST_NR(2, 16),
+	[MT8188_VDO1_RST_HDR_GFX_FE1]			= MMSYS_RST_NR(2, 17),
+	[MT8188_VDO1_RST_DISP_MIXER]			= MMSYS_RST_NR(2, 18),
+	[MT8188_VDO1_RST_HDR_VDO_FE0_DL_ASYNC]		= MMSYS_RST_NR(2, 19),
+	[MT8188_VDO1_RST_HDR_VDO_FE1_DL_ASYNC]		= MMSYS_RST_NR(2, 20),
+	[MT8188_VDO1_RST_HDR_GFX_FE0_DL_ASYNC]		= MMSYS_RST_NR(2, 21),
+	[MT8188_VDO1_RST_HDR_GFX_FE1_DL_ASYNC]		= MMSYS_RST_NR(2, 22),
+	[MT8188_VDO1_RST_HDR_VDO_BE_DL_ASYNC]		= MMSYS_RST_NR(2, 23),
+};
+
 static const struct mtk_mmsys_routes mmsys_mt8188_routing_table[] = {
 	{
 		DDP_COMPONENT_OVL0, DDP_COMPONENT_RDMA0,
@@ -146,4 +280,80 @@ static const struct mtk_mmsys_routes mmsys_mt8188_routing_table[] = {
 	},
 };
 
+static const struct mtk_mmsys_routes mmsys_mt8188_vdo1_routing_table[] = {
+	{
+		DDP_COMPONENT_MDP_RDMA0, DDP_COMPONENT_MERGE1,
+		MT8188_VDO1_VPP_MERGE0_P0_SEL_IN, GENMASK(0, 0),
+		MT8188_VPP_MERGE0_P0_SEL_IN_FROM_MDP_RDMA0
+	}, {
+		DDP_COMPONENT_MDP_RDMA1, DDP_COMPONENT_MERGE1,
+		MT8188_VDO1_VPP_MERGE0_P1_SEL_IN, GENMASK(0, 0),
+		MT8188_VPP_MERGE0_P1_SEL_IN_FROM_MDP_RDMA1
+	}, {
+		DDP_COMPONENT_MDP_RDMA2, DDP_COMPONENT_MERGE2,
+		MT8188_VDO1_VPP_MERGE1_P0_SEL_IN, GENMASK(0, 0),
+		MT8188_VPP_MERGE1_P0_SEL_IN_FROM_MDP_RDMA2
+	}, {
+		DDP_COMPONENT_MERGE1, DDP_COMPONENT_ETHDR_MIXER,
+		MT8188_VDO1_MERGE0_ASYNC_SOUT_SEL, GENMASK(1, 0),
+		MT8188_SOUT_TO_MIXER_IN1_SEL
+	}, {
+		DDP_COMPONENT_MERGE2, DDP_COMPONENT_ETHDR_MIXER,
+		MT8188_VDO1_MERGE1_ASYNC_SOUT_SEL, GENMASK(1, 0),
+		MT8188_SOUT_TO_MIXER_IN2_SEL
+	}, {
+		DDP_COMPONENT_MERGE3, DDP_COMPONENT_ETHDR_MIXER,
+		MT8188_VDO1_MERGE2_ASYNC_SOUT_SEL, GENMASK(1, 0),
+		MT8188_SOUT_TO_MIXER_IN3_SEL
+	}, {
+		DDP_COMPONENT_MERGE4, DDP_COMPONENT_ETHDR_MIXER,
+		MT8188_VDO1_MERGE3_ASYNC_SOUT_SEL, GENMASK(1, 0),
+		MT8188_SOUT_TO_MIXER_IN4_SEL
+	}, {
+		DDP_COMPONENT_ETHDR_MIXER, DDP_COMPONENT_MERGE5,
+		MT8188_VDO1_MIXER_OUT_SOUT_SEL, GENMASK(0, 0),
+		MT8188_MIXER_SOUT_TO_MERGE4_ASYNC_SEL
+	}, {
+		DDP_COMPONENT_MERGE1, DDP_COMPONENT_ETHDR_MIXER,
+		MT8188_VDO1_MIXER_IN1_SEL_IN, GENMASK(0, 0),
+		MT8188_MIXER_IN1_SEL_IN_FROM_MERGE0_ASYNC_SOUT
+	}, {
+		DDP_COMPONENT_MERGE2, DDP_COMPONENT_ETHDR_MIXER,
+		MT8188_VDO1_MIXER_IN2_SEL_IN, GENMASK(0, 0),
+		MT8188_MIXER_IN2_SEL_IN_FROM_MERGE1_ASYNC_SOUT
+	}, {
+		DDP_COMPONENT_MERGE3, DDP_COMPONENT_ETHDR_MIXER,
+		MT8188_VDO1_MIXER_IN3_SEL_IN, GENMASK(0, 0),
+		MT8188_MIXER_IN3_SEL_IN_FROM_MERGE2_ASYNC_SOUT
+	}, {
+		DDP_COMPONENT_MERGE4, DDP_COMPONENT_ETHDR_MIXER,
+		MT8188_VDO1_MIXER_IN4_SEL_IN, GENMASK(0, 0),
+		MT8188_MIXER_IN4_SEL_IN_FROM_MERGE3_ASYNC_SOUT
+	}, {
+		DDP_COMPONENT_ETHDR_MIXER, DDP_COMPONENT_MERGE5,
+		MT8188_VDO1_MIXER_SOUT_SEL_IN, GENMASK(2, 0),
+		MT8188_MIXER_SOUT_SEL_IN_FROM_DISP_MIXER
+	}, {
+		DDP_COMPONENT_ETHDR_MIXER, DDP_COMPONENT_MERGE5,
+		MT8188_VDO1_MERGE4_ASYNC_SEL_IN, GENMASK(2, 0),
+		MT8188_MERGE4_ASYNC_SEL_IN_FROM_MIXER_OUT_SOUT
+	}, {
+		DDP_COMPONENT_MERGE5, DDP_COMPONENT_DPI1,
+		MT8188_VDO1_DISP_DPI1_SEL_IN, GENMASK(1, 0),
+		MT8188_DISP_DPI1_SEL_IN_FROM_VPP_MERGE4_MOUT
+	}, {
+		DDP_COMPONENT_MERGE5, DDP_COMPONENT_DPI1,
+		MT8188_VDO1_MERGE4_SOUT_SEL, GENMASK(1, 0),
+		MT8188_MERGE4_SOUT_TO_DPI1_SEL
+	}, {
+		DDP_COMPONENT_MERGE5, DDP_COMPONENT_DP_INTF1,
+		MT8188_VDO1_DISP_DP_INTF0_SEL_IN, GENMASK(1, 0),
+		MT8188_DISP_DP_INTF0_SEL_IN_FROM_VPP_MERGE4_MOUT
+	}, {
+		DDP_COMPONENT_MERGE5, DDP_COMPONENT_DP_INTF1,
+		MT8188_VDO1_MERGE4_SOUT_SEL, GENMASK(3, 0),
+		MT8188_MERGE4_SOUT_TO_DP_INTF0_SEL
+	}
+};
+
 #endif /* __SOC_MEDIATEK_MT8188_MMSYS_H */
diff --git a/drivers/soc/mediatek/mtk-mmsys.c b/drivers/soc/mediatek/mtk-mmsys.c
index 88209102ff3b..f370f4ec4b88 100644
--- a/drivers/soc/mediatek/mtk-mmsys.c
+++ b/drivers/soc/mediatek/mtk-mmsys.c
@@ -87,6 +87,29 @@ static const struct mtk_mmsys_driver_data mt8188_vdosys0_driver_data = {
 	.clk_driver = "clk-mt8188-vdo0",
 	.routes = mmsys_mt8188_routing_table,
 	.num_routes = ARRAY_SIZE(mmsys_mt8188_routing_table),
+	.sw0_rst_offset = MT8188_VDO0_SW0_RST_B,
+	.rst_tb = mmsys_mt8188_vdo0_rst_tb,
+	.num_resets = ARRAY_SIZE(mmsys_mt8188_vdo0_rst_tb),
+};
+
+static const struct mtk_mmsys_driver_data mt8188_vdosys1_driver_data = {
+	.clk_driver = "clk-mt8188-vdo1",
+	.routes = mmsys_mt8188_vdo1_routing_table,
+	.num_routes = ARRAY_SIZE(mmsys_mt8188_vdo1_routing_table),
+	.sw0_rst_offset = MT8188_VDO1_SW0_RST_B,
+	.rst_tb = mmsys_mt8188_vdo1_rst_tb,
+	.num_resets = ARRAY_SIZE(mmsys_mt8188_vdo1_rst_tb),
+	.vsync_len = 1,
+};
+
+static const struct mtk_mmsys_driver_data mt8188_vppsys0_driver_data = {
+	.clk_driver = "clk-mt8188-vpp0",
+	.is_vppsys = true,
+};
+
+static const struct mtk_mmsys_driver_data mt8188_vppsys1_driver_data = {
+	.clk_driver = "clk-mt8188-vpp1",
+	.is_vppsys = true,
 };
 
 static const struct mtk_mmsys_driver_data mt8192_mmsys_driver_data = {
@@ -169,6 +192,10 @@ void mtk_mmsys_ddp_connect(struct device *dev,
 		if (cur == routes[i].from_comp && next == routes[i].to_comp)
 			mtk_mmsys_update_bits(mmsys, routes[i].addr, routes[i].mask,
 					      routes[i].val, NULL);
+
+	if (mmsys->data->vsync_len)
+		mtk_mmsys_update_bits(mmsys, MT8188_VDO1_MIXER_VSYNC_LEN, GENMASK(31, 0),
+				      mmsys->data->vsync_len, NULL);
 }
 EXPORT_SYMBOL_GPL(mtk_mmsys_ddp_connect);
 
@@ -302,6 +329,15 @@ static int mtk_mmsys_reset_update(struct reset_controller_dev *rcdev, unsigned l
 	u32 offset;
 	u32 reg;
 
+	if (mmsys->data->rst_tb) {
+		if (id >= mmsys->data->num_resets) {
+			dev_err(rcdev->dev, "Invalid reset ID: %lu (>=%u)\n",
+				id, mmsys->data->num_resets);
+			return -EINVAL;
+		}
+		id = mmsys->data->rst_tb[id];
+	}
+
 	offset = (id / MMSYS_SW_RESET_PER_REG) * sizeof(u32);
 	id = id % MMSYS_SW_RESET_PER_REG;
 	reg = mmsys->data->sw0_rst_offset + offset;
@@ -429,6 +465,9 @@ static const struct of_device_id of_match_mtk_mmsys[] = {
 	{ .compatible = "mediatek,mt8183-mmsys", .data = &mt8183_mmsys_driver_data },
 	{ .compatible = "mediatek,mt8186-mmsys", .data = &mt8186_mmsys_driver_data },
 	{ .compatible = "mediatek,mt8188-vdosys0", .data = &mt8188_vdosys0_driver_data },
+	{ .compatible = "mediatek,mt8188-vdosys1", .data = &mt8188_vdosys1_driver_data },
+	{ .compatible = "mediatek,mt8188-vppsys0", .data = &mt8188_vppsys0_driver_data },
+	{ .compatible = "mediatek,mt8188-vppsys1", .data = &mt8188_vppsys1_driver_data },
 	{ .compatible = "mediatek,mt8192-mmsys", .data = &mt8192_mmsys_driver_data },
 	/* "mediatek,mt8195-mmsys" compatible is deprecated */
 	{ .compatible = "mediatek,mt8195-mmsys", .data = &mt8195_vdosys0_driver_data },
diff --git a/drivers/soc/mediatek/mtk-mmsys.h b/drivers/soc/mediatek/mtk-mmsys.h
index 6725403d2e3a..d370192737ca 100644
--- a/drivers/soc/mediatek/mtk-mmsys.h
+++ b/drivers/soc/mediatek/mtk-mmsys.h
@@ -78,6 +78,8 @@
 #define DSI_SEL_IN_RDMA				0x1
 #define DSI_SEL_IN_MASK				0x1
 
+#define MMSYS_RST_NR(bank, bit) (((bank) * 32) + (bit))
+
 struct mtk_mmsys_routes {
 	u32 from_comp;
 	u32 to_comp;
@@ -86,13 +88,43 @@ struct mtk_mmsys_routes {
 	u32 val;
 };
 
+/**
+ * struct mtk_mmsys_driver_data - Settings of the mmsys
+ * @clk_driver: Clock driver name that the mmsys is using
+ *              (defined in drivers/clk/mediatek/clk-*.c).
+ * @routes: Routing table of the mmsys.
+ *          It provides mux settings from one module to another.
+ * @num_routes: Array size of the routes.
+ * @sw0_rst_offset: Register offset for the reset control.
+ * @num_resets: Number of reset bits that are defined
+ * @is_vppsys: Whether the mmsys is VPPSYS (Video Processing Pipe)
+ *             or VDOSYS (Video). Only VDOSYS needs to be added to drm driver.
+ * @vsync_len: VSYNC length of the MIXER.
+ *             VSYNC is usually triggered by the connector, so its length is a
+ *             fixed value when the frame rate is decided, but ETHDR and
+ *             MIXER generate their own VSYNC due to hardware design, therefore
+ *             MIXER has to sync with ETHDR by adjusting VSYNC length.
+ *             On MT8195, there is no such setting so we use the gap between
+ *             falling edge and rising edge of SOF (Start of Frame) signal to
+ *             do the job, but since MT8188, VSYNC_LEN setting is introduced to
+ *             solve the problem and is given 0x40 (ticks) as the default value.
+ *             Please notice that this value has to be set to 1 (minimum) if
+ *             ETHDR is bypassed, otherwise MIXER could wait too long and causing
+ *             underflow.
+ *
+ * Each MMSYS (multi-media system) may have different settings, they may use
+ * different clock sources, mux settings, reset control ...etc., and these
+ * differences are all stored here.
+ */
 struct mtk_mmsys_driver_data {
 	const char *clk_driver;
 	const struct mtk_mmsys_routes *routes;
 	const unsigned int num_routes;
 	const u16 sw0_rst_offset;
+	const u8 *rst_tb;
 	const u32 num_resets;
 	const bool is_vppsys;
+	const u8 vsync_len;
 };
 
 /*
diff --git a/drivers/soc/mediatek/mtk-mutex.c b/drivers/soc/mediatek/mtk-mutex.c
index 9d9f5ae578ac..73c256d3950b 100644
--- a/drivers/soc/mediatek/mtk-mutex.c
+++ b/drivers/soc/mediatek/mtk-mutex.c
@@ -133,6 +133,30 @@
 #define MT8188_MUTEX_MOD_DISP_POSTMASK0		24
 #define MT8188_MUTEX_MOD2_DISP_PWM0		33
 
+#define MT8188_MUTEX_MOD_DISP1_MDP_RDMA0	0
+#define MT8188_MUTEX_MOD_DISP1_MDP_RDMA1	1
+#define MT8188_MUTEX_MOD_DISP1_MDP_RDMA2	2
+#define MT8188_MUTEX_MOD_DISP1_MDP_RDMA3	3
+#define MT8188_MUTEX_MOD_DISP1_MDP_RDMA4	4
+#define MT8188_MUTEX_MOD_DISP1_MDP_RDMA5	5
+#define MT8188_MUTEX_MOD_DISP1_MDP_RDMA6	6
+#define MT8188_MUTEX_MOD_DISP1_MDP_RDMA7	7
+#define MT8188_MUTEX_MOD_DISP1_PADDING0		8
+#define MT8188_MUTEX_MOD_DISP1_PADDING1		9
+#define MT8188_MUTEX_MOD_DISP1_PADDING2		10
+#define MT8188_MUTEX_MOD_DISP1_PADDING3		11
+#define MT8188_MUTEX_MOD_DISP1_PADDING4		12
+#define MT8188_MUTEX_MOD_DISP1_PADDING5		13
+#define MT8188_MUTEX_MOD_DISP1_PADDING6		14
+#define MT8188_MUTEX_MOD_DISP1_PADDING7		15
+#define MT8188_MUTEX_MOD_DISP1_VPP_MERGE0	20
+#define MT8188_MUTEX_MOD_DISP1_VPP_MERGE1	21
+#define MT8188_MUTEX_MOD_DISP1_VPP_MERGE2	22
+#define MT8188_MUTEX_MOD_DISP1_VPP_MERGE3	23
+#define MT8188_MUTEX_MOD_DISP1_VPP_MERGE4	24
+#define MT8188_MUTEX_MOD_DISP1_DISP_MIXER	30
+#define MT8188_MUTEX_MOD_DISP1_DP_INTF1		39
+
 #define MT8195_MUTEX_MOD_DISP_OVL0		0
 #define MT8195_MUTEX_MOD_DISP_WDMA0		1
 #define MT8195_MUTEX_MOD_DISP_RDMA0		2
@@ -264,6 +288,7 @@
 #define MT8183_MUTEX_SOF_DPI0			2
 #define MT8188_MUTEX_SOF_DSI0			1
 #define MT8188_MUTEX_SOF_DP_INTF0		3
+#define MT8188_MUTEX_SOF_DP_INTF1		4
 #define MT8195_MUTEX_SOF_DSI0			1
 #define MT8195_MUTEX_SOF_DSI1			2
 #define MT8195_MUTEX_SOF_DP_INTF0		3
@@ -275,6 +300,7 @@
 #define MT8183_MUTEX_EOF_DPI0			(MT8183_MUTEX_SOF_DPI0 << 6)
 #define MT8188_MUTEX_EOF_DSI0			(MT8188_MUTEX_SOF_DSI0 << 7)
 #define MT8188_MUTEX_EOF_DP_INTF0		(MT8188_MUTEX_SOF_DP_INTF0 << 7)
+#define MT8188_MUTEX_EOF_DP_INTF1		(MT8188_MUTEX_SOF_DP_INTF1 << 7)
 #define MT8195_MUTEX_EOF_DSI0			(MT8195_MUTEX_SOF_DSI0 << 7)
 #define MT8195_MUTEX_EOF_DSI1			(MT8195_MUTEX_SOF_DSI1 << 7)
 #define MT8195_MUTEX_EOF_DP_INTF0		(MT8195_MUTEX_SOF_DP_INTF0 << 7)
@@ -445,6 +471,29 @@ static const unsigned int mt8188_mutex_mod[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_DSI0] = MT8188_MUTEX_MOD_DISP_DSI0,
 	[DDP_COMPONENT_PWM0] = MT8188_MUTEX_MOD2_DISP_PWM0,
 	[DDP_COMPONENT_DP_INTF0] = MT8188_MUTEX_MOD_DISP_DP_INTF0,
+	[DDP_COMPONENT_DP_INTF1] = MT8188_MUTEX_MOD_DISP1_DP_INTF1,
+	[DDP_COMPONENT_ETHDR_MIXER] = MT8188_MUTEX_MOD_DISP1_DISP_MIXER,
+	[DDP_COMPONENT_MDP_RDMA0] = MT8188_MUTEX_MOD_DISP1_MDP_RDMA0,
+	[DDP_COMPONENT_MDP_RDMA1] = MT8188_MUTEX_MOD_DISP1_MDP_RDMA1,
+	[DDP_COMPONENT_MDP_RDMA2] = MT8188_MUTEX_MOD_DISP1_MDP_RDMA2,
+	[DDP_COMPONENT_MDP_RDMA3] = MT8188_MUTEX_MOD_DISP1_MDP_RDMA3,
+	[DDP_COMPONENT_MDP_RDMA4] = MT8188_MUTEX_MOD_DISP1_MDP_RDMA4,
+	[DDP_COMPONENT_MDP_RDMA5] = MT8188_MUTEX_MOD_DISP1_MDP_RDMA5,
+	[DDP_COMPONENT_MDP_RDMA6] = MT8188_MUTEX_MOD_DISP1_MDP_RDMA6,
+	[DDP_COMPONENT_MDP_RDMA7] = MT8188_MUTEX_MOD_DISP1_MDP_RDMA7,
+	[DDP_COMPONENT_PADDING0] = MT8188_MUTEX_MOD_DISP1_PADDING0,
+	[DDP_COMPONENT_PADDING1] = MT8188_MUTEX_MOD_DISP1_PADDING1,
+	[DDP_COMPONENT_PADDING2] = MT8188_MUTEX_MOD_DISP1_PADDING2,
+	[DDP_COMPONENT_PADDING3] = MT8188_MUTEX_MOD_DISP1_PADDING3,
+	[DDP_COMPONENT_PADDING4] = MT8188_MUTEX_MOD_DISP1_PADDING4,
+	[DDP_COMPONENT_PADDING5] = MT8188_MUTEX_MOD_DISP1_PADDING5,
+	[DDP_COMPONENT_PADDING6] = MT8188_MUTEX_MOD_DISP1_PADDING6,
+	[DDP_COMPONENT_PADDING7] = MT8188_MUTEX_MOD_DISP1_PADDING7,
+	[DDP_COMPONENT_MERGE1] = MT8188_MUTEX_MOD_DISP1_VPP_MERGE0,
+	[DDP_COMPONENT_MERGE2] = MT8188_MUTEX_MOD_DISP1_VPP_MERGE1,
+	[DDP_COMPONENT_MERGE3] = MT8188_MUTEX_MOD_DISP1_VPP_MERGE2,
+	[DDP_COMPONENT_MERGE4] = MT8188_MUTEX_MOD_DISP1_VPP_MERGE3,
+	[DDP_COMPONENT_MERGE5] = MT8188_MUTEX_MOD_DISP1_VPP_MERGE4,
 };
 
 static const unsigned int mt8192_mutex_mod[DDP_COMPONENT_ID_MAX] = {
@@ -605,6 +654,8 @@ static const unsigned int mt8188_mutex_sof[DDP_MUTEX_SOF_MAX] = {
 		MT8188_MUTEX_SOF_DSI0 | MT8188_MUTEX_EOF_DSI0,
 	[MUTEX_SOF_DP_INTF0] =
 		MT8188_MUTEX_SOF_DP_INTF0 | MT8188_MUTEX_EOF_DP_INTF0,
+	[MUTEX_SOF_DP_INTF1] =
+		MT8188_MUTEX_SOF_DP_INTF1 | MT8188_MUTEX_EOF_DP_INTF1,
 };
 
 static const unsigned int mt8195_mutex_sof[DDP_MUTEX_SOF_MAX] = {
diff --git a/drivers/soc/mediatek/mtk-svs.c b/drivers/soc/mediatek/mtk-svs.c
index f31e3bedff50..c832f5c670bc 100644
--- a/drivers/soc/mediatek/mtk-svs.c
+++ b/drivers/soc/mediatek/mtk-svs.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2022 MediaTek Inc.
+ * Copyright (C) 2022 Collabora Ltd.
+ *                    AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
  */
 
 #include <linux/bitfield.h>
@@ -32,16 +34,6 @@
 #include <linux/spinlock.h>
 #include <linux/thermal.h>
 
-/* svs bank 1-line software id */
-#define SVSB_CPU_LITTLE			BIT(0)
-#define SVSB_CPU_BIG			BIT(1)
-#define SVSB_CCI			BIT(2)
-#define SVSB_GPU			BIT(3)
-
-/* svs bank 2-line type */
-#define SVSB_LOW			BIT(8)
-#define SVSB_HIGH			BIT(9)
-
 /* svs bank mode support */
 #define SVSB_MODE_ALL_DISABLE		0
 #define SVSB_MODE_INIT01		BIT(1)
@@ -128,6 +120,13 @@
 #define SVSB_VOPS_FLD_VOP2_6		GENMASK(23, 16)
 #define SVSB_VOPS_FLD_VOP3_7		GENMASK(31, 24)
 
+/* SVS Thermal Coefficients */
+#define SVSB_TS_COEFF_MT8195		250460
+#define SVSB_TS_COEFF_MT8186		204650
+
+/* Algo helpers */
+#define FUSE_DATA_NOT_VALID		U32_MAX
+
 /* svs bank related setting */
 #define BITS8				8
 #define MAX_OPP_ENTRIES			16
@@ -175,6 +174,36 @@ static DEFINE_SPINLOCK(svs_lock);
 #endif
 
 /**
+ * enum svsb_sw_id - SVS Bank Software ID
+ * @SVSB_SWID_CPU_LITTLE: CPU little cluster Bank
+ * @SVSB_SWID_CPU_BIG:    CPU big cluster Bank
+ * @SVSB_SWID_CCI:        Cache Coherent Interconnect Bank
+ * @SVSB_SWID_GPU:        GPU Bank
+ * @SVSB_SWID_MAX:        Total number of Banks
+ */
+enum svsb_sw_id {
+	SVSB_SWID_CPU_LITTLE,
+	SVSB_SWID_CPU_BIG,
+	SVSB_SWID_CCI,
+	SVSB_SWID_GPU,
+	SVSB_SWID_MAX
+};
+
+/**
+ * enum svsb_type - SVS Bank 2-line: Type and Role
+ * @SVSB_TYPE_NONE: One-line type Bank - Global role
+ * @SVSB_TYPE_LOW:  Two-line type Bank - Low bank role
+ * @SVSB_TYPE_HIGH: Two-line type Bank - High bank role
+ * @SVSB_TYPE_MAX:  Total number of bank types
+ */
+enum svsb_type {
+	SVSB_TYPE_NONE,
+	SVSB_TYPE_LOW,
+	SVSB_TYPE_HIGH,
+	SVSB_TYPE_MAX
+};
+
+/**
  * enum svsb_phase - svs bank phase enumeration
  * @SVSB_PHASE_ERROR: svs bank encounters unexpected condition
  * @SVSB_PHASE_INIT01: svs bank basic init for data calibration
@@ -256,60 +285,88 @@ enum svs_reg_index {
 };
 
 static const u32 svs_regs_v2[] = {
-	[DESCHAR]		= 0xc00,
-	[TEMPCHAR]		= 0xc04,
-	[DETCHAR]		= 0xc08,
-	[AGECHAR]		= 0xc0c,
-	[DCCONFIG]		= 0xc10,
-	[AGECONFIG]		= 0xc14,
-	[FREQPCT30]		= 0xc18,
-	[FREQPCT74]		= 0xc1c,
-	[LIMITVALS]		= 0xc20,
-	[VBOOT]			= 0xc24,
-	[DETWINDOW]		= 0xc28,
-	[CONFIG]		= 0xc2c,
-	[TSCALCS]		= 0xc30,
-	[RUNCONFIG]		= 0xc34,
-	[SVSEN]			= 0xc38,
-	[INIT2VALS]		= 0xc3c,
-	[DCVALUES]		= 0xc40,
-	[AGEVALUES]		= 0xc44,
-	[VOP30]			= 0xc48,
-	[VOP74]			= 0xc4c,
-	[TEMP]			= 0xc50,
-	[INTSTS]		= 0xc54,
-	[INTSTSRAW]		= 0xc58,
-	[INTEN]			= 0xc5c,
-	[CHKINT]		= 0xc60,
-	[CHKSHIFT]		= 0xc64,
-	[STATUS]		= 0xc68,
-	[VDESIGN30]		= 0xc6c,
-	[VDESIGN74]		= 0xc70,
-	[DVT30]			= 0xc74,
-	[DVT74]			= 0xc78,
-	[AGECOUNT]		= 0xc7c,
-	[SMSTATE0]		= 0xc80,
-	[SMSTATE1]		= 0xc84,
-	[CTL0]			= 0xc88,
-	[DESDETSEC]		= 0xce0,
-	[TEMPAGESEC]		= 0xce4,
-	[CTRLSPARE0]		= 0xcf0,
-	[CTRLSPARE1]		= 0xcf4,
-	[CTRLSPARE2]		= 0xcf8,
-	[CTRLSPARE3]		= 0xcfc,
-	[CORESEL]		= 0xf00,
-	[THERMINTST]		= 0xf04,
-	[INTST]			= 0xf08,
-	[THSTAGE0ST]		= 0xf0c,
-	[THSTAGE1ST]		= 0xf10,
-	[THSTAGE2ST]		= 0xf14,
-	[THAHBST0]		= 0xf18,
-	[THAHBST1]		= 0xf1c,
-	[SPARE0]		= 0xf20,
-	[SPARE1]		= 0xf24,
-	[SPARE2]		= 0xf28,
-	[SPARE3]		= 0xf2c,
-	[THSLPEVEB]		= 0xf30,
+	[DESCHAR]		= 0x00,
+	[TEMPCHAR]		= 0x04,
+	[DETCHAR]		= 0x08,
+	[AGECHAR]		= 0x0c,
+	[DCCONFIG]		= 0x10,
+	[AGECONFIG]		= 0x14,
+	[FREQPCT30]		= 0x18,
+	[FREQPCT74]		= 0x1c,
+	[LIMITVALS]		= 0x20,
+	[VBOOT]			= 0x24,
+	[DETWINDOW]		= 0x28,
+	[CONFIG]		= 0x2c,
+	[TSCALCS]		= 0x30,
+	[RUNCONFIG]		= 0x34,
+	[SVSEN]			= 0x38,
+	[INIT2VALS]		= 0x3c,
+	[DCVALUES]		= 0x40,
+	[AGEVALUES]		= 0x44,
+	[VOP30]			= 0x48,
+	[VOP74]			= 0x4c,
+	[TEMP]			= 0x50,
+	[INTSTS]		= 0x54,
+	[INTSTSRAW]		= 0x58,
+	[INTEN]			= 0x5c,
+	[CHKINT]		= 0x60,
+	[CHKSHIFT]		= 0x64,
+	[STATUS]		= 0x68,
+	[VDESIGN30]		= 0x6c,
+	[VDESIGN74]		= 0x70,
+	[DVT30]			= 0x74,
+	[DVT74]			= 0x78,
+	[AGECOUNT]		= 0x7c,
+	[SMSTATE0]		= 0x80,
+	[SMSTATE1]		= 0x84,
+	[CTL0]			= 0x88,
+	[DESDETSEC]		= 0xe0,
+	[TEMPAGESEC]		= 0xe4,
+	[CTRLSPARE0]		= 0xf0,
+	[CTRLSPARE1]		= 0xf4,
+	[CTRLSPARE2]		= 0xf8,
+	[CTRLSPARE3]		= 0xfc,
+	[CORESEL]		= 0x300,
+	[THERMINTST]		= 0x304,
+	[INTST]			= 0x308,
+	[THSTAGE0ST]		= 0x30c,
+	[THSTAGE1ST]		= 0x310,
+	[THSTAGE2ST]		= 0x314,
+	[THAHBST0]		= 0x318,
+	[THAHBST1]		= 0x31c,
+	[SPARE0]		= 0x320,
+	[SPARE1]		= 0x324,
+	[SPARE2]		= 0x328,
+	[SPARE3]		= 0x32c,
+	[THSLPEVEB]		= 0x330,
+};
+
+static const char * const svs_swid_names[SVSB_SWID_MAX] = {
+	"SVSB_CPU_LITTLE", "SVSB_CPU_BIG", "SVSB_CCI", "SVSB_GPU"
+};
+
+static const char * const svs_type_names[SVSB_TYPE_MAX] = {
+	"", "_LOW", "_HIGH"
+};
+
+enum svs_fusemap_dev {
+	BDEV_BDES,
+	BDEV_MDES,
+	BDEV_MTDES,
+	BDEV_DCBDET,
+	BDEV_DCMDET,
+	BDEV_MAX
+};
+
+enum svs_fusemap_glb {
+	GLB_FT_PGM,
+	GLB_VMIN,
+	GLB_MAX
+};
+
+struct svs_fusemap {
+	s8 index;
+	u8 ofst;
 };
 
 /**
@@ -317,88 +374,124 @@ static const u32 svs_regs_v2[] = {
  * @base: svs platform register base
  * @dev: svs platform device
  * @main_clk: main clock for svs bank
- * @pbank: svs bank pointer needing to be protected by spin_lock section
  * @banks: svs banks that svs platform supports
  * @rst: svs platform reset control
  * @efuse_max: total number of svs efuse
  * @tefuse_max: total number of thermal efuse
  * @regs: svs platform registers map
- * @bank_max: total number of svs banks
  * @efuse: svs efuse data received from NVMEM framework
  * @tefuse: thermal efuse data received from NVMEM framework
+ * @ts_coeff: thermal sensors coefficient
+ * @bank_max: total number of svs banks
  */
 struct svs_platform {
 	void __iomem *base;
 	struct device *dev;
 	struct clk *main_clk;
-	struct svs_bank *pbank;
 	struct svs_bank *banks;
 	struct reset_control *rst;
 	size_t efuse_max;
 	size_t tefuse_max;
 	const u32 *regs;
-	u32 bank_max;
 	u32 *efuse;
 	u32 *tefuse;
+	u32 ts_coeff;
+	u16 bank_max;
 };
 
 struct svs_platform_data {
 	char *name;
 	struct svs_bank *banks;
-	bool (*efuse_parsing)(struct svs_platform *svsp);
+	bool (*efuse_parsing)(struct svs_platform *svsp, const struct svs_platform_data *pdata);
 	int (*probe)(struct svs_platform *svsp);
+	const struct svs_fusemap *glb_fuse_map;
 	const u32 *regs;
-	u32 bank_max;
+	u32 ts_coeff;
+	u16 bank_max;
+};
+
+/**
+ * struct svs_bank_pdata - SVS Bank immutable config parameters
+ * @dev_fuse_map: Bank fuse map data
+ * @buck_name: Regulator name
+ * @tzone_name: Thermal zone name
+ * @age_config: Bank age configuration
+ * @ctl0: TS-x selection
+ * @dc_config: Bank dc configuration
+ * @int_st: Bank interrupt identification
+ * @turn_freq_base: Reference frequency for 2-line turn point
+ * @tzone_htemp: Thermal zone high temperature threshold
+ * @tzone_ltemp: Thermal zone low temperature threshold
+ * @volt_step: Bank voltage step
+ * @volt_base: Bank voltage base
+ * @tzone_htemp_voffset: Thermal zone high temperature voltage offset
+ * @tzone_ltemp_voffset: Thermal zone low temperature voltage offset
+ * @chk_shift: Bank chicken shift
+ * @cpu_id: CPU core ID for SVS CPU bank use only
+ * @opp_count: Bank opp count
+ * @vboot: Voltage request for bank init01 only
+ * @vco: Bank VCO value
+ * @sw_id: Bank software identification
+ * @type: SVS Bank Type (1 or 2-line) and Role (high/low)
+ * @set_freq_pct: function pointer to set bank frequency percent table
+ * @get_volts: function pointer to get bank voltages
+ */
+struct svs_bank_pdata {
+	const struct svs_fusemap *dev_fuse_map;
+	char *buck_name;
+	char *tzone_name;
+	u32 age_config;
+	u32 ctl0;
+	u32 dc_config;
+	u32 int_st;
+	u32 turn_freq_base;
+	u32 tzone_htemp;
+	u32 tzone_ltemp;
+	u32 volt_step;
+	u32 volt_base;
+	u16 tzone_htemp_voffset;
+	u16 tzone_ltemp_voffset;
+	u8 chk_shift;
+	u8 cpu_id;
+	u8 opp_count;
+	u8 vboot;
+	u8 vco;
+	u8 sw_id;
+	u8 type;
+
+	/* Callbacks */
+	void (*set_freq_pct)(struct svs_platform *svsp, struct svs_bank *svsb);
+	void (*get_volts)(struct svs_platform *svsp, struct svs_bank *svsb);
 };
 
 /**
  * struct svs_bank - svs bank representation
+ * @pdata: SVS Bank immutable config parameters
  * @dev: bank device
  * @opp_dev: device for opp table/buck control
  * @init_completion: the timeout completion for bank init
  * @buck: regulator used by opp_dev
  * @tzd: thermal zone device for getting temperature
  * @lock: mutex lock to protect voltage update process
- * @set_freq_pct: function pointer to set bank frequency percent table
- * @get_volts: function pointer to get bank voltages
  * @name: bank name
- * @buck_name: regulator name
- * @tzone_name: thermal zone name
  * @phase: bank current phase
  * @volt_od: bank voltage overdrive
  * @reg_data: bank register data in different phase for debug purpose
  * @pm_runtime_enabled_count: bank pm runtime enabled count
- * @mode_support: bank mode support.
+ * @mode_support: bank mode support
  * @freq_base: reference frequency for bank init
- * @turn_freq_base: refenrece frequency for 2-line turn point
- * @vboot: voltage request for bank init01 only
  * @opp_dfreq: default opp frequency table
  * @opp_dvolt: default opp voltage table
  * @freq_pct: frequency percent table for bank init
  * @volt: bank voltage table
- * @volt_step: bank voltage step
- * @volt_base: bank voltage base
  * @volt_flags: bank voltage flags
  * @vmax: bank voltage maximum
  * @vmin: bank voltage minimum
- * @age_config: bank age configuration
  * @age_voffset_in: bank age voltage offset
- * @dc_config: bank dc configuration
  * @dc_voffset_in: bank dc voltage offset
  * @dvt_fixed: bank dvt fixed value
- * @vco: bank VCO value
- * @chk_shift: bank chicken shift
  * @core_sel: bank selection
- * @opp_count: bank opp count
- * @int_st: bank interrupt identification
- * @sw_id: bank software identification
- * @cpu_id: cpu core id for SVS CPU bank use only
- * @ctl0: TS-x selection
  * @temp: bank temperature
- * @tzone_htemp: thermal zone high temperature threshold
- * @tzone_htemp_voffset: thermal zone high temperature voltage offset
- * @tzone_ltemp: thermal zone low temperature threshold
- * @tzone_ltemp_voffset: thermal zone low temperature voltage offset
  * @bts: svs efuse data
  * @mts: svs efuse data
  * @bdes: svs efuse data
@@ -408,70 +501,48 @@ struct svs_platform_data {
  * @dcmdet: svs efuse data
  * @turn_pt: 2-line turn point tells which opp_volt calculated by high/low bank
  * @vbin_turn_pt: voltage bin turn point helps know which svsb_volt should be overridden
- * @type: bank type to represent it is 2-line (high/low) bank or 1-line bank
  *
- * Svs bank will generate suitalbe voltages by below general math equation
+ * Svs bank will generate suitable voltages by below general math equation
  * and provide these voltages to opp voltage table.
  *
  * opp_volt[i] = (volt[i] * volt_step) + volt_base;
  */
 struct svs_bank {
+	const struct svs_bank_pdata pdata;
 	struct device *dev;
 	struct device *opp_dev;
 	struct completion init_completion;
 	struct regulator *buck;
 	struct thermal_zone_device *tzd;
-	struct mutex lock;	/* lock to protect voltage update process */
-	void (*set_freq_pct)(struct svs_platform *svsp);
-	void (*get_volts)(struct svs_platform *svsp);
+	struct mutex lock;
+	int pm_runtime_enabled_count;
+	short int volt_od;
 	char *name;
-	char *buck_name;
-	char *tzone_name;
 	enum svsb_phase phase;
-	s32 volt_od;
 	u32 reg_data[SVSB_PHASE_MAX][SVS_REG_MAX];
-	u32 pm_runtime_enabled_count;
-	u32 mode_support;
-	u32 freq_base;
-	u32 turn_freq_base;
-	u32 vboot;
+	u8 mode_support;
 	u32 opp_dfreq[MAX_OPP_ENTRIES];
 	u32 opp_dvolt[MAX_OPP_ENTRIES];
 	u32 freq_pct[MAX_OPP_ENTRIES];
 	u32 volt[MAX_OPP_ENTRIES];
-	u32 volt_step;
-	u32 volt_base;
 	u32 volt_flags;
-	u32 vmax;
-	u32 vmin;
-	u32 age_config;
-	u32 age_voffset_in;
-	u32 dc_config;
-	u32 dc_voffset_in;
-	u32 dvt_fixed;
-	u32 vco;
-	u32 chk_shift;
-	u32 core_sel;
-	u32 opp_count;
-	u32 int_st;
-	u32 sw_id;
-	u32 cpu_id;
-	u32 ctl0;
-	u32 temp;
-	u32 tzone_htemp;
-	u32 tzone_htemp_voffset;
-	u32 tzone_ltemp;
-	u32 tzone_ltemp_voffset;
-	u32 bts;
-	u32 mts;
-	u32 bdes;
-	u32 mdes;
-	u32 mtdes;
-	u32 dcbdet;
-	u32 dcmdet;
+	u32 freq_base;
 	u32 turn_pt;
 	u32 vbin_turn_pt;
-	u32 type;
+	u32 core_sel;
+	u32 temp;
+	u16 age_voffset_in;
+	u16 dc_voffset_in;
+	u8 dvt_fixed;
+	u8 vmax;
+	u8 vmin;
+	u16 bts;
+	u16 mts;
+	u16 bdes;
+	u16 mdes;
+	u8 mtdes;
+	u8 dcbdet;
+	u8 dcmdet;
 };
 
 static u32 percent(u32 numerator, u32 denominator)
@@ -494,10 +565,8 @@ static void svs_writel_relaxed(struct svs_platform *svsp, u32 val,
 	writel_relaxed(val, svsp->base + svsp->regs[rg_i]);
 }
 
-static void svs_switch_bank(struct svs_platform *svsp)
+static void svs_switch_bank(struct svs_platform *svsp, struct svs_bank *svsb)
 {
-	struct svs_bank *svsb = svsp->pbank;
-
 	svs_writel_relaxed(svsp, svsb->core_sel, CORESEL);
 }
 
@@ -515,10 +584,11 @@ static u32 svs_opp_volt_to_bank_volt(u32 opp_u_volt, u32 svsb_volt_step,
 
 static int svs_sync_bank_volts_from_opp(struct svs_bank *svsb)
 {
+	const struct svs_bank_pdata *bdata = &svsb->pdata;
 	struct dev_pm_opp *opp;
 	u32 i, opp_u_volt;
 
-	for (i = 0; i < svsb->opp_count; i++) {
+	for (i = 0; i < bdata->opp_count; i++) {
 		opp = dev_pm_opp_find_freq_exact(svsb->opp_dev,
 						 svsb->opp_dfreq[i],
 						 true);
@@ -530,8 +600,8 @@ static int svs_sync_bank_volts_from_opp(struct svs_bank *svsb)
 
 		opp_u_volt = dev_pm_opp_get_voltage(opp);
 		svsb->volt[i] = svs_opp_volt_to_bank_volt(opp_u_volt,
-							  svsb->volt_step,
-							  svsb->volt_base);
+							  bdata->volt_step,
+							  bdata->volt_base);
 		dev_pm_opp_put(opp);
 	}
 
@@ -541,6 +611,7 @@ static int svs_sync_bank_volts_from_opp(struct svs_bank *svsb)
 static int svs_adjust_pm_opp_volts(struct svs_bank *svsb)
 {
 	int ret = -EPERM, tzone_temp = 0;
+	const struct svs_bank_pdata *bdata = &svsb->pdata;
 	u32 i, svsb_volt, opp_volt, temp_voffset = 0, opp_start, opp_stop;
 
 	mutex_lock(&svsb->lock);
@@ -549,15 +620,15 @@ static int svs_adjust_pm_opp_volts(struct svs_bank *svsb)
 	 * 2-line bank updates its corresponding opp volts.
 	 * 1-line bank updates all opp volts.
 	 */
-	if (svsb->type == SVSB_HIGH) {
+	if (bdata->type == SVSB_TYPE_HIGH) {
 		opp_start = 0;
 		opp_stop = svsb->turn_pt;
-	} else if (svsb->type == SVSB_LOW) {
+	} else if (bdata->type == SVSB_TYPE_LOW) {
 		opp_start = svsb->turn_pt;
-		opp_stop = svsb->opp_count;
+		opp_stop = bdata->opp_count;
 	} else {
 		opp_start = 0;
-		opp_stop = svsb->opp_count;
+		opp_stop = bdata->opp_count;
 	}
 
 	/* Get thermal effect */
@@ -566,20 +637,20 @@ static int svs_adjust_pm_opp_volts(struct svs_bank *svsb)
 		if (ret || (svsb->temp > SVSB_TEMP_UPPER_BOUND &&
 			    svsb->temp < SVSB_TEMP_LOWER_BOUND)) {
 			dev_err(svsb->dev, "%s: %d (0x%x), run default volts\n",
-				svsb->tzone_name, ret, svsb->temp);
+				bdata->tzone_name, ret, svsb->temp);
 			svsb->phase = SVSB_PHASE_ERROR;
 		}
 
-		if (tzone_temp >= svsb->tzone_htemp)
-			temp_voffset += svsb->tzone_htemp_voffset;
-		else if (tzone_temp <= svsb->tzone_ltemp)
-			temp_voffset += svsb->tzone_ltemp_voffset;
+		if (tzone_temp >= bdata->tzone_htemp)
+			temp_voffset += bdata->tzone_htemp_voffset;
+		else if (tzone_temp <= bdata->tzone_ltemp)
+			temp_voffset += bdata->tzone_ltemp_voffset;
 
 		/* 2-line bank update all opp volts when running mon mode */
-		if (svsb->phase == SVSB_PHASE_MON && (svsb->type == SVSB_HIGH ||
-						      svsb->type == SVSB_LOW)) {
+		if (svsb->phase == SVSB_PHASE_MON && (bdata->type == SVSB_TYPE_HIGH ||
+						      bdata->type == SVSB_TYPE_LOW)) {
 			opp_start = 0;
-			opp_stop = svsb->opp_count;
+			opp_stop = bdata->opp_count;
 		}
 	}
 
@@ -596,8 +667,8 @@ static int svs_adjust_pm_opp_volts(struct svs_bank *svsb)
 		case SVSB_PHASE_MON:
 			svsb_volt = max(svsb->volt[i] + temp_voffset, svsb->vmin);
 			opp_volt = svs_bank_volt_to_opp_volt(svsb_volt,
-							     svsb->volt_step,
-							     svsb->volt_base);
+							     bdata->volt_step,
+							     bdata->volt_base);
 			break;
 		default:
 			dev_err(svsb->dev, "unknown phase: %u\n", svsb->phase);
@@ -632,8 +703,7 @@ static void svs_bank_disable_and_restore_default_volts(struct svs_platform *svsp
 		return;
 
 	spin_lock_irqsave(&svs_lock, flags);
-	svsp->pbank = svsb;
-	svs_switch_bank(svsp);
+	svs_switch_bank(svsp, svsb);
 	svs_writel_relaxed(svsp, SVSB_PTPEN_OFF, SVSEN);
 	svs_writel_relaxed(svsp, SVSB_INTSTS_VAL_CLEAN, INTSTS);
 	spin_unlock_irqrestore(&svs_lock, flags);
@@ -760,7 +830,7 @@ static int svs_status_debug_show(struct seq_file *m, void *v)
 			   svsb->name, tzone_temp, svsb->vbin_turn_pt,
 			   svsb->turn_pt);
 
-	for (i = 0; i < svsb->opp_count; i++) {
+	for (i = 0; i < svsb->pdata.opp_count; i++) {
 		opp = dev_pm_opp_find_freq_exact(svsb->opp_dev,
 						 svsb->opp_dfreq[i], true);
 		if (IS_ERR(opp)) {
@@ -865,12 +935,12 @@ static u32 interpolate(u32 f0, u32 f1, u32 v0, u32 v1, u32 fx)
 	return DIV_ROUND_UP(vx, 100);
 }
 
-static void svs_get_bank_volts_v3(struct svs_platform *svsp)
+static void svs_get_bank_volts_v3(struct svs_platform *svsp, struct svs_bank *svsb)
 {
-	struct svs_bank *svsb = svsp->pbank;
+	const struct svs_bank_pdata *bdata = &svsb->pdata;
 	u32 i, j, *vop, vop74, vop30, turn_pt = svsb->turn_pt;
 	u32 b_sft, shift_byte = 0, opp_start = 0, opp_stop = 0;
-	u32 middle_index = (svsb->opp_count / 2);
+	u32 middle_index = (bdata->opp_count / 2);
 
 	if (svsb->phase == SVSB_PHASE_MON &&
 	    svsb->volt_flags & SVSB_MON_VOLT_IGNORE)
@@ -881,7 +951,7 @@ static void svs_get_bank_volts_v3(struct svs_platform *svsp)
 
 	/* Target is to set svsb->volt[] by algorithm */
 	if (turn_pt < middle_index) {
-		if (svsb->type == SVSB_HIGH) {
+		if (bdata->type == SVSB_TYPE_HIGH) {
 			/* volt[0] ~ volt[turn_pt - 1] */
 			for (i = 0; i < turn_pt; i++) {
 				b_sft = BITS8 * (shift_byte % REG_BYTES);
@@ -890,12 +960,12 @@ static void svs_get_bank_volts_v3(struct svs_platform *svsp)
 				svsb->volt[i] = (*vop >> b_sft) & GENMASK(7, 0);
 				shift_byte++;
 			}
-		} else if (svsb->type == SVSB_LOW) {
+		} else if (bdata->type == SVSB_TYPE_LOW) {
 			/* volt[turn_pt] + volt[j] ~ volt[opp_count - 1] */
-			j = svsb->opp_count - 7;
+			j = bdata->opp_count - 7;
 			svsb->volt[turn_pt] = FIELD_GET(SVSB_VOPS_FLD_VOP0_4, vop30);
 			shift_byte++;
-			for (i = j; i < svsb->opp_count; i++) {
+			for (i = j; i < bdata->opp_count; i++) {
 				b_sft = BITS8 * (shift_byte % REG_BYTES);
 				vop = (shift_byte < REG_BYTES) ? &vop30 :
 								 &vop74;
@@ -912,7 +982,7 @@ static void svs_get_bank_volts_v3(struct svs_platform *svsp)
 							    svsb->freq_pct[i]);
 		}
 	} else {
-		if (svsb->type == SVSB_HIGH) {
+		if (bdata->type == SVSB_TYPE_HIGH) {
 			/* volt[0] + volt[j] ~ volt[turn_pt - 1] */
 			j = turn_pt - 7;
 			svsb->volt[0] = FIELD_GET(SVSB_VOPS_FLD_VOP0_4, vop30);
@@ -932,9 +1002,9 @@ static void svs_get_bank_volts_v3(struct svs_platform *svsp)
 							    svsb->volt[0],
 							    svsb->volt[j],
 							    svsb->freq_pct[i]);
-		} else if (svsb->type == SVSB_LOW) {
+		} else if (bdata->type == SVSB_TYPE_LOW) {
 			/* volt[turn_pt] ~ volt[opp_count - 1] */
-			for (i = turn_pt; i < svsb->opp_count; i++) {
+			for (i = turn_pt; i < bdata->opp_count; i++) {
 				b_sft = BITS8 * (shift_byte % REG_BYTES);
 				vop = (shift_byte < REG_BYTES) ? &vop30 :
 								 &vop74;
@@ -944,12 +1014,12 @@ static void svs_get_bank_volts_v3(struct svs_platform *svsp)
 		}
 	}
 
-	if (svsb->type == SVSB_HIGH) {
+	if (bdata->type == SVSB_TYPE_HIGH) {
 		opp_start = 0;
 		opp_stop = svsb->turn_pt;
-	} else if (svsb->type == SVSB_LOW) {
+	} else if (bdata->type == SVSB_TYPE_LOW) {
 		opp_start = svsb->turn_pt;
-		opp_stop = svsb->opp_count;
+		opp_stop = bdata->opp_count;
 	}
 
 	for (i = opp_start; i < opp_stop; i++)
@@ -959,11 +1029,11 @@ static void svs_get_bank_volts_v3(struct svs_platform *svsp)
 	/* For voltage bin support */
 	if (svsb->opp_dfreq[0] > svsb->freq_base) {
 		svsb->volt[0] = svs_opp_volt_to_bank_volt(svsb->opp_dvolt[0],
-							  svsb->volt_step,
-							  svsb->volt_base);
+							  bdata->volt_step,
+							  bdata->volt_base);
 
 		/* Find voltage bin turn point */
-		for (i = 0; i < svsb->opp_count; i++) {
+		for (i = 0; i < bdata->opp_count; i++) {
 			if (svsb->opp_dfreq[i] <= svsb->freq_base) {
 				svsb->vbin_turn_pt = i;
 				break;
@@ -980,15 +1050,15 @@ static void svs_get_bank_volts_v3(struct svs_platform *svsp)
 	}
 }
 
-static void svs_set_bank_freq_pct_v3(struct svs_platform *svsp)
+static void svs_set_bank_freq_pct_v3(struct svs_platform *svsp, struct svs_bank *svsb)
 {
-	struct svs_bank *svsb = svsp->pbank;
+	const struct svs_bank_pdata *bdata = &svsb->pdata;
 	u32 i, j, *freq_pct, freq_pct74 = 0, freq_pct30 = 0;
 	u32 b_sft, shift_byte = 0, turn_pt;
-	u32 middle_index = (svsb->opp_count / 2);
+	u32 middle_index = (bdata->opp_count / 2);
 
-	for (i = 0; i < svsb->opp_count; i++) {
-		if (svsb->opp_dfreq[i] <= svsb->turn_freq_base) {
+	for (i = 0; i < bdata->opp_count; i++) {
+		if (svsb->opp_dfreq[i] <= bdata->turn_freq_base) {
 			svsb->turn_pt = i;
 			break;
 		}
@@ -998,11 +1068,11 @@ static void svs_set_bank_freq_pct_v3(struct svs_platform *svsp)
 
 	/* Target is to fill out freq_pct74 / freq_pct30 by algorithm */
 	if (turn_pt < middle_index) {
-		if (svsb->type == SVSB_HIGH) {
+		if (bdata->type == SVSB_TYPE_HIGH) {
 			/*
 			 * If we don't handle this situation,
-			 * SVSB_HIGH's FREQPCT74 / FREQPCT30 would keep "0"
-			 * and this leads SVSB_LOW to work abnormally.
+			 * SVSB_TYPE_HIGH's FREQPCT74 / FREQPCT30 would keep "0"
+			 * and this leads SVSB_TYPE_LOW to work abnormally.
 			 */
 			if (turn_pt == 0)
 				freq_pct30 = svsb->freq_pct[0];
@@ -1015,15 +1085,15 @@ static void svs_set_bank_freq_pct_v3(struct svs_platform *svsp)
 				*freq_pct |= (svsb->freq_pct[i] << b_sft);
 				shift_byte++;
 			}
-		} else if (svsb->type == SVSB_LOW) {
+		} else if (bdata->type == SVSB_TYPE_LOW) {
 			/*
 			 * freq_pct[turn_pt] +
 			 * freq_pct[opp_count - 7] ~ freq_pct[opp_count -1]
 			 */
 			freq_pct30 = svsb->freq_pct[turn_pt];
 			shift_byte++;
-			j = svsb->opp_count - 7;
-			for (i = j; i < svsb->opp_count; i++) {
+			j = bdata->opp_count - 7;
+			for (i = j; i < bdata->opp_count; i++) {
 				b_sft = BITS8 * (shift_byte % REG_BYTES);
 				freq_pct = (shift_byte < REG_BYTES) ?
 					   &freq_pct30 : &freq_pct74;
@@ -1032,7 +1102,7 @@ static void svs_set_bank_freq_pct_v3(struct svs_platform *svsp)
 			}
 		}
 	} else {
-		if (svsb->type == SVSB_HIGH) {
+		if (bdata->type == SVSB_TYPE_HIGH) {
 			/*
 			 * freq_pct[0] +
 			 * freq_pct[turn_pt - 7] ~ freq_pct[turn_pt - 1]
@@ -1047,9 +1117,9 @@ static void svs_set_bank_freq_pct_v3(struct svs_platform *svsp)
 				*freq_pct |= (svsb->freq_pct[i] << b_sft);
 				shift_byte++;
 			}
-		} else if (svsb->type == SVSB_LOW) {
+		} else if (bdata->type == SVSB_TYPE_LOW) {
 			/* freq_pct[turn_pt] ~ freq_pct[opp_count - 1] */
-			for (i = turn_pt; i < svsb->opp_count; i++) {
+			for (i = turn_pt; i < bdata->opp_count; i++) {
 				b_sft = BITS8 * (shift_byte % REG_BYTES);
 				freq_pct = (shift_byte < REG_BYTES) ?
 					   &freq_pct30 : &freq_pct74;
@@ -1063,9 +1133,9 @@ static void svs_set_bank_freq_pct_v3(struct svs_platform *svsp)
 	svs_writel_relaxed(svsp, freq_pct30, FREQPCT30);
 }
 
-static void svs_get_bank_volts_v2(struct svs_platform *svsp)
+static void svs_get_bank_volts_v2(struct svs_platform *svsp, struct svs_bank *svsb)
 {
-	struct svs_bank *svsb = svsp->pbank;
+	const struct svs_bank_pdata *bdata = &svsb->pdata;
 	u32 temp, i;
 
 	temp = svs_readl_relaxed(svsp, VOP74);
@@ -1093,17 +1163,17 @@ static void svs_get_bank_volts_v2(struct svs_platform *svsp)
 				     svsb->volt[14],
 				     svsb->freq_pct[15]);
 
-	for (i = 0; i < svsb->opp_count; i++)
+	for (i = 0; i < bdata->opp_count; i++)
 		svsb->volt[i] += svsb->volt_od;
 
 	/* For voltage bin support */
 	if (svsb->opp_dfreq[0] > svsb->freq_base) {
 		svsb->volt[0] = svs_opp_volt_to_bank_volt(svsb->opp_dvolt[0],
-							  svsb->volt_step,
-							  svsb->volt_base);
+							  bdata->volt_step,
+							  bdata->volt_base);
 
 		/* Find voltage bin turn point */
-		for (i = 0; i < svsb->opp_count; i++) {
+		for (i = 0; i < bdata->opp_count; i++) {
 			if (svsb->opp_dfreq[i] <= svsb->freq_base) {
 				svsb->vbin_turn_pt = i;
 				break;
@@ -1120,9 +1190,8 @@ static void svs_get_bank_volts_v2(struct svs_platform *svsp)
 	}
 }
 
-static void svs_set_bank_freq_pct_v2(struct svs_platform *svsp)
+static void svs_set_bank_freq_pct_v2(struct svs_platform *svsp, struct svs_bank *svsb)
 {
-	struct svs_bank *svsb = svsp->pbank;
 	u32 freqpct74_val, freqpct30_val;
 
 	freqpct74_val = FIELD_PREP(SVSB_FREQPCTS_FLD_PCT0_4, svsb->freq_pct[8]) |
@@ -1140,18 +1209,20 @@ static void svs_set_bank_freq_pct_v2(struct svs_platform *svsp)
 }
 
 static void svs_set_bank_phase(struct svs_platform *svsp,
+			       unsigned int bank_idx,
 			       enum svsb_phase target_phase)
 {
-	struct svs_bank *svsb = svsp->pbank;
+	struct svs_bank *svsb = &svsp->banks[bank_idx];
+	const struct svs_bank_pdata *bdata = &svsb->pdata;
 	u32 des_char, temp_char, det_char, limit_vals, init2vals, ts_calcs;
 
-	svs_switch_bank(svsp);
+	svs_switch_bank(svsp, svsb);
 
 	des_char = FIELD_PREP(SVSB_DESCHAR_FLD_BDES, svsb->bdes) |
 		   FIELD_PREP(SVSB_DESCHAR_FLD_MDES, svsb->mdes);
 	svs_writel_relaxed(svsp, des_char, DESCHAR);
 
-	temp_char = FIELD_PREP(SVSB_TEMPCHAR_FLD_VCO, svsb->vco) |
+	temp_char = FIELD_PREP(SVSB_TEMPCHAR_FLD_VCO, bdata->vco) |
 		    FIELD_PREP(SVSB_TEMPCHAR_FLD_MTDES, svsb->mtdes) |
 		    FIELD_PREP(SVSB_TEMPCHAR_FLD_DVT_FIXED, svsb->dvt_fixed);
 	svs_writel_relaxed(svsp, temp_char, TEMPCHAR);
@@ -1160,11 +1231,11 @@ static void svs_set_bank_phase(struct svs_platform *svsp,
 		   FIELD_PREP(SVSB_DETCHAR_FLD_DCMDET, svsb->dcmdet);
 	svs_writel_relaxed(svsp, det_char, DETCHAR);
 
-	svs_writel_relaxed(svsp, svsb->dc_config, DCCONFIG);
-	svs_writel_relaxed(svsp, svsb->age_config, AGECONFIG);
+	svs_writel_relaxed(svsp, bdata->dc_config, DCCONFIG);
+	svs_writel_relaxed(svsp, bdata->age_config, AGECONFIG);
 	svs_writel_relaxed(svsp, SVSB_RUNCONFIG_DEFAULT, RUNCONFIG);
 
-	svsb->set_freq_pct(svsp);
+	bdata->set_freq_pct(svsp, svsb);
 
 	limit_vals = FIELD_PREP(SVSB_LIMITVALS_FLD_DTLO, SVSB_VAL_DTLO) |
 		     FIELD_PREP(SVSB_LIMITVALS_FLD_DTHI, SVSB_VAL_DTHI) |
@@ -1174,13 +1245,13 @@ static void svs_set_bank_phase(struct svs_platform *svsp,
 
 	svs_writel_relaxed(svsp, SVSB_DET_WINDOW, DETWINDOW);
 	svs_writel_relaxed(svsp, SVSB_DET_MAX, CONFIG);
-	svs_writel_relaxed(svsp, svsb->chk_shift, CHKSHIFT);
-	svs_writel_relaxed(svsp, svsb->ctl0, CTL0);
+	svs_writel_relaxed(svsp, bdata->chk_shift, CHKSHIFT);
+	svs_writel_relaxed(svsp, bdata->ctl0, CTL0);
 	svs_writel_relaxed(svsp, SVSB_INTSTS_VAL_CLEAN, INTSTS);
 
 	switch (target_phase) {
 	case SVSB_PHASE_INIT01:
-		svs_writel_relaxed(svsp, svsb->vboot, VBOOT);
+		svs_writel_relaxed(svsp, bdata->vboot, VBOOT);
 		svs_writel_relaxed(svsp, SVSB_INTEN_INIT0x, INTEN);
 		svs_writel_relaxed(svsp, SVSB_PTPEN_INIT01, SVSEN);
 		break;
@@ -1206,18 +1277,20 @@ static void svs_set_bank_phase(struct svs_platform *svsp,
 }
 
 static inline void svs_save_bank_register_data(struct svs_platform *svsp,
+					       unsigned short bank_idx,
 					       enum svsb_phase phase)
 {
-	struct svs_bank *svsb = svsp->pbank;
+	struct svs_bank *svsb = &svsp->banks[bank_idx];
 	enum svs_reg_index rg_i;
 
 	for (rg_i = DESCHAR; rg_i < SVS_REG_MAX; rg_i++)
 		svsb->reg_data[phase][rg_i] = svs_readl_relaxed(svsp, rg_i);
 }
 
-static inline void svs_error_isr_handler(struct svs_platform *svsp)
+static inline void svs_error_isr_handler(struct svs_platform *svsp,
+					 unsigned short bank_idx)
 {
-	struct svs_bank *svsb = svsp->pbank;
+	struct svs_bank *svsb = &svsp->banks[bank_idx];
 
 	dev_err(svsb->dev, "%s: CORESEL = 0x%08x\n",
 		__func__, svs_readl_relaxed(svsp, CORESEL));
@@ -1229,27 +1302,29 @@ static inline void svs_error_isr_handler(struct svs_platform *svsp)
 		svs_readl_relaxed(svsp, SMSTATE1));
 	dev_err(svsb->dev, "TEMP = 0x%08x\n", svs_readl_relaxed(svsp, TEMP));
 
-	svs_save_bank_register_data(svsp, SVSB_PHASE_ERROR);
+	svs_save_bank_register_data(svsp, bank_idx, SVSB_PHASE_ERROR);
 
 	svsb->phase = SVSB_PHASE_ERROR;
 	svs_writel_relaxed(svsp, SVSB_PTPEN_OFF, SVSEN);
 	svs_writel_relaxed(svsp, SVSB_INTSTS_VAL_CLEAN, INTSTS);
 }
 
-static inline void svs_init01_isr_handler(struct svs_platform *svsp)
+static inline void svs_init01_isr_handler(struct svs_platform *svsp,
+					  unsigned short bank_idx)
 {
-	struct svs_bank *svsb = svsp->pbank;
+	struct svs_bank *svsb = &svsp->banks[bank_idx];
+	u32 val;
 
 	dev_info(svsb->dev, "%s: VDN74~30:0x%08x~0x%08x, DC:0x%08x\n",
 		 __func__, svs_readl_relaxed(svsp, VDESIGN74),
 		 svs_readl_relaxed(svsp, VDESIGN30),
 		 svs_readl_relaxed(svsp, DCVALUES));
 
-	svs_save_bank_register_data(svsp, SVSB_PHASE_INIT01);
+	svs_save_bank_register_data(svsp, bank_idx, SVSB_PHASE_INIT01);
 
 	svsb->phase = SVSB_PHASE_INIT01;
-	svsb->dc_voffset_in = ~(svs_readl_relaxed(svsp, DCVALUES) &
-				GENMASK(15, 0)) + 1;
+	val = ~(svs_readl_relaxed(svsp, DCVALUES) & GENMASK(15, 0)) + 1;
+	svsb->dc_voffset_in = val & GENMASK(15, 0);
 	if (svsb->volt_flags & SVSB_INIT01_VOLT_IGNORE ||
 	    (svsb->dc_voffset_in & SVSB_DC_SIGNED_BIT &&
 	     svsb->volt_flags & SVSB_INIT01_VOLT_INC_ONLY))
@@ -1263,32 +1338,36 @@ static inline void svs_init01_isr_handler(struct svs_platform *svsp)
 	svsb->core_sel &= ~SVSB_DET_CLK_EN;
 }
 
-static inline void svs_init02_isr_handler(struct svs_platform *svsp)
+static inline void svs_init02_isr_handler(struct svs_platform *svsp,
+					  unsigned short bank_idx)
 {
-	struct svs_bank *svsb = svsp->pbank;
+	struct svs_bank *svsb = &svsp->banks[bank_idx];
+	const struct svs_bank_pdata *bdata = &svsb->pdata;
 
 	dev_info(svsb->dev, "%s: VOP74~30:0x%08x~0x%08x, DC:0x%08x\n",
 		 __func__, svs_readl_relaxed(svsp, VOP74),
 		 svs_readl_relaxed(svsp, VOP30),
 		 svs_readl_relaxed(svsp, DCVALUES));
 
-	svs_save_bank_register_data(svsp, SVSB_PHASE_INIT02);
+	svs_save_bank_register_data(svsp, bank_idx, SVSB_PHASE_INIT02);
 
 	svsb->phase = SVSB_PHASE_INIT02;
-	svsb->get_volts(svsp);
+	bdata->get_volts(svsp, svsb);
 
 	svs_writel_relaxed(svsp, SVSB_PTPEN_OFF, SVSEN);
 	svs_writel_relaxed(svsp, SVSB_INTSTS_F0_COMPLETE, INTSTS);
 }
 
-static inline void svs_mon_mode_isr_handler(struct svs_platform *svsp)
+static inline void svs_mon_mode_isr_handler(struct svs_platform *svsp,
+					    unsigned short bank_idx)
 {
-	struct svs_bank *svsb = svsp->pbank;
+	struct svs_bank *svsb = &svsp->banks[bank_idx];
+	const struct svs_bank_pdata *bdata = &svsb->pdata;
 
-	svs_save_bank_register_data(svsp, SVSB_PHASE_MON);
+	svs_save_bank_register_data(svsp, bank_idx, SVSB_PHASE_MON);
 
 	svsb->phase = SVSB_PHASE_MON;
-	svsb->get_volts(svsp);
+	bdata->get_volts(svsp, svsb);
 
 	svsb->temp = svs_readl_relaxed(svsp, TEMP) & GENMASK(7, 0);
 	svs_writel_relaxed(svsp, SVSB_INTSTS_FLD_MONVOP, INTSTS);
@@ -1297,37 +1376,38 @@ static inline void svs_mon_mode_isr_handler(struct svs_platform *svsp)
 static irqreturn_t svs_isr(int irq, void *data)
 {
 	struct svs_platform *svsp = data;
+	const struct svs_bank_pdata *bdata;
 	struct svs_bank *svsb = NULL;
 	unsigned long flags;
 	u32 idx, int_sts, svs_en;
 
 	for (idx = 0; idx < svsp->bank_max; idx++) {
 		svsb = &svsp->banks[idx];
+		bdata = &svsb->pdata;
 		WARN(!svsb, "%s: svsb(%s) is null", __func__, svsb->name);
 
 		spin_lock_irqsave(&svs_lock, flags);
-		svsp->pbank = svsb;
 
 		/* Find out which svs bank fires interrupt */
-		if (svsb->int_st & svs_readl_relaxed(svsp, INTST)) {
+		if (bdata->int_st & svs_readl_relaxed(svsp, INTST)) {
 			spin_unlock_irqrestore(&svs_lock, flags);
 			continue;
 		}
 
-		svs_switch_bank(svsp);
+		svs_switch_bank(svsp, svsb);
 		int_sts = svs_readl_relaxed(svsp, INTSTS);
 		svs_en = svs_readl_relaxed(svsp, SVSEN);
 
 		if (int_sts == SVSB_INTSTS_F0_COMPLETE &&
 		    svs_en == SVSB_PTPEN_INIT01)
-			svs_init01_isr_handler(svsp);
+			svs_init01_isr_handler(svsp, idx);
 		else if (int_sts == SVSB_INTSTS_F0_COMPLETE &&
 			 svs_en == SVSB_PTPEN_INIT02)
-			svs_init02_isr_handler(svsp);
+			svs_init02_isr_handler(svsp, idx);
 		else if (int_sts & SVSB_INTSTS_FLD_MONVOP)
-			svs_mon_mode_isr_handler(svsp);
+			svs_mon_mode_isr_handler(svsp, idx);
 		else
-			svs_error_isr_handler(svsp);
+			svs_error_isr_handler(svsp, idx);
 
 		spin_unlock_irqrestore(&svs_lock, flags);
 		break;
@@ -1342,20 +1422,35 @@ static irqreturn_t svs_isr(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+static bool svs_mode_available(struct svs_platform *svsp, u8 mode)
+{
+	int i;
+
+	for (i = 0; i < svsp->bank_max; i++)
+		if (svsp->banks[i].mode_support & mode)
+			return true;
+	return false;
+}
+
 static int svs_init01(struct svs_platform *svsp)
 {
+	const struct svs_bank_pdata *bdata;
 	struct svs_bank *svsb;
 	unsigned long flags, time_left;
 	bool search_done;
 	int ret = 0, r;
 	u32 opp_freq, opp_vboot, buck_volt, idx, i;
 
+	if (!svs_mode_available(svsp, SVSB_MODE_INIT01))
+		return 0;
+
 	/* Keep CPUs' core power on for svs_init01 initialization */
 	cpuidle_pause_and_lock();
 
 	 /* Svs bank init01 preparation - power enable */
 	for (idx = 0; idx < svsp->bank_max; idx++) {
 		svsb = &svsp->banks[idx];
+		bdata = &svsb->pdata;
 
 		if (!(svsb->mode_support & SVSB_MODE_INIT01))
 			continue;
@@ -1363,7 +1458,7 @@ static int svs_init01(struct svs_platform *svsp)
 		ret = regulator_enable(svsb->buck);
 		if (ret) {
 			dev_err(svsb->dev, "%s enable fail: %d\n",
-				svsb->buck_name, ret);
+				bdata->buck_name, ret);
 			goto svs_init01_resume_cpuidle;
 		}
 
@@ -1393,6 +1488,7 @@ static int svs_init01(struct svs_platform *svsp)
 	 */
 	for (idx = 0; idx < svsp->bank_max; idx++) {
 		svsb = &svsp->banks[idx];
+		bdata = &svsb->pdata;
 
 		if (!(svsb->mode_support & SVSB_MODE_INIT01))
 			continue;
@@ -1402,11 +1498,11 @@ static int svs_init01(struct svs_platform *svsp)
 		 * fix to that freq until svs_init01 is done.
 		 */
 		search_done = false;
-		opp_vboot = svs_bank_volt_to_opp_volt(svsb->vboot,
-						      svsb->volt_step,
-						      svsb->volt_base);
+		opp_vboot = svs_bank_volt_to_opp_volt(bdata->vboot,
+						      bdata->volt_step,
+						      bdata->volt_base);
 
-		for (i = 0; i < svsb->opp_count; i++) {
+		for (i = 0; i < bdata->opp_count; i++) {
 			opp_freq = svsb->opp_dfreq[i];
 			if (!search_done && svsb->opp_dvolt[i] <= opp_vboot) {
 				ret = dev_pm_opp_adjust_voltage(svsb->opp_dev,
@@ -1438,13 +1534,14 @@ static int svs_init01(struct svs_platform *svsp)
 	/* Svs bank init01 begins */
 	for (idx = 0; idx < svsp->bank_max; idx++) {
 		svsb = &svsp->banks[idx];
+		bdata = &svsb->pdata;
 
 		if (!(svsb->mode_support & SVSB_MODE_INIT01))
 			continue;
 
-		opp_vboot = svs_bank_volt_to_opp_volt(svsb->vboot,
-						      svsb->volt_step,
-						      svsb->volt_base);
+		opp_vboot = svs_bank_volt_to_opp_volt(bdata->vboot,
+						      bdata->volt_step,
+						      bdata->volt_base);
 
 		buck_volt = regulator_get_voltage(svsb->buck);
 		if (buck_volt != opp_vboot) {
@@ -1456,8 +1553,7 @@ static int svs_init01(struct svs_platform *svsp)
 		}
 
 		spin_lock_irqsave(&svs_lock, flags);
-		svsp->pbank = svsb;
-		svs_set_bank_phase(svsp, SVSB_PHASE_INIT01);
+		svs_set_bank_phase(svsp, idx, SVSB_PHASE_INIT01);
 		spin_unlock_irqrestore(&svs_lock, flags);
 
 		time_left = wait_for_completion_timeout(&svsb->init_completion,
@@ -1472,11 +1568,12 @@ static int svs_init01(struct svs_platform *svsp)
 svs_init01_finish:
 	for (idx = 0; idx < svsp->bank_max; idx++) {
 		svsb = &svsp->banks[idx];
+		bdata = &svsb->pdata;
 
 		if (!(svsb->mode_support & SVSB_MODE_INIT01))
 			continue;
 
-		for (i = 0; i < svsb->opp_count; i++) {
+		for (i = 0; i < bdata->opp_count; i++) {
 			r = dev_pm_opp_enable(svsb->opp_dev,
 					      svsb->opp_dfreq[i]);
 			if (r)
@@ -1502,7 +1599,7 @@ svs_init01_finish:
 		r = regulator_disable(svsb->buck);
 		if (r)
 			dev_err(svsb->dev, "%s disable fail: %d\n",
-				svsb->buck_name, r);
+				bdata->buck_name, r);
 	}
 
 svs_init01_resume_cpuidle:
@@ -1513,11 +1610,15 @@ svs_init01_resume_cpuidle:
 
 static int svs_init02(struct svs_platform *svsp)
 {
+	const struct svs_bank_pdata *bdata;
 	struct svs_bank *svsb;
 	unsigned long flags, time_left;
 	int ret;
 	u32 idx;
 
+	if (!svs_mode_available(svsp, SVSB_MODE_INIT02))
+		return 0;
+
 	for (idx = 0; idx < svsp->bank_max; idx++) {
 		svsb = &svsp->banks[idx];
 
@@ -1526,8 +1627,7 @@ static int svs_init02(struct svs_platform *svsp)
 
 		reinit_completion(&svsb->init_completion);
 		spin_lock_irqsave(&svs_lock, flags);
-		svsp->pbank = svsb;
-		svs_set_bank_phase(svsp, SVSB_PHASE_INIT02);
+		svs_set_bank_phase(svsp, idx, SVSB_PHASE_INIT02);
 		spin_unlock_irqrestore(&svs_lock, flags);
 
 		time_left = wait_for_completion_timeout(&svsb->init_completion,
@@ -1546,11 +1646,12 @@ static int svs_init02(struct svs_platform *svsp)
 	 */
 	for (idx = 0; idx < svsp->bank_max; idx++) {
 		svsb = &svsp->banks[idx];
+		bdata = &svsb->pdata;
 
 		if (!(svsb->mode_support & SVSB_MODE_INIT02))
 			continue;
 
-		if (svsb->type == SVSB_HIGH || svsb->type == SVSB_LOW) {
+		if (bdata->type == SVSB_TYPE_HIGH || bdata->type == SVSB_TYPE_LOW) {
 			if (svs_sync_bank_volts_from_opp(svsb)) {
 				dev_err(svsb->dev, "sync volt fail\n");
 				ret = -EPERM;
@@ -1583,8 +1684,7 @@ static void svs_mon_mode(struct svs_platform *svsp)
 			continue;
 
 		spin_lock_irqsave(&svs_lock, flags);
-		svsp->pbank = svsb;
-		svs_set_bank_phase(svsp, SVSB_PHASE_MON);
+		svs_set_bank_phase(svsp, idx, SVSB_PHASE_MON);
 		spin_unlock_irqrestore(&svs_lock, flags);
 	}
 }
@@ -1609,12 +1709,12 @@ static int svs_start(struct svs_platform *svsp)
 static int svs_suspend(struct device *dev)
 {
 	struct svs_platform *svsp = dev_get_drvdata(dev);
-	struct svs_bank *svsb;
 	int ret;
 	u32 idx;
 
 	for (idx = 0; idx < svsp->bank_max; idx++) {
-		svsb = &svsp->banks[idx];
+		struct svs_bank *svsb = &svsp->banks[idx];
+
 		svs_bank_disable_and_restore_default_volts(svsp, svsb);
 	}
 
@@ -1665,6 +1765,7 @@ out_of_resume:
 
 static int svs_bank_resource_setup(struct svs_platform *svsp)
 {
+	const struct svs_bank_pdata *bdata;
 	struct svs_bank *svsb;
 	struct dev_pm_opp *opp;
 	unsigned long freq;
@@ -1675,35 +1776,23 @@ static int svs_bank_resource_setup(struct svs_platform *svsp)
 
 	for (idx = 0; idx < svsp->bank_max; idx++) {
 		svsb = &svsp->banks[idx];
+		bdata = &svsb->pdata;
 
-		switch (svsb->sw_id) {
-		case SVSB_CPU_LITTLE:
-			svsb->name = "SVSB_CPU_LITTLE";
-			break;
-		case SVSB_CPU_BIG:
-			svsb->name = "SVSB_CPU_BIG";
-			break;
-		case SVSB_CCI:
-			svsb->name = "SVSB_CCI";
-			break;
-		case SVSB_GPU:
-			if (svsb->type == SVSB_HIGH)
-				svsb->name = "SVSB_GPU_HIGH";
-			else if (svsb->type == SVSB_LOW)
-				svsb->name = "SVSB_GPU_LOW";
-			else
-				svsb->name = "SVSB_GPU";
-			break;
-		default:
-			dev_err(svsb->dev, "unknown sw_id: %u\n", svsb->sw_id);
+		if (bdata->sw_id >= SVSB_SWID_MAX || bdata->type >= SVSB_TYPE_MAX) {
+			dev_err(svsb->dev, "unknown bank sw_id or type\n");
 			return -EINVAL;
 		}
 
-		svsb->dev = devm_kzalloc(svsp->dev, sizeof(*svsb->dev),
-					 GFP_KERNEL);
+		svsb->dev = devm_kzalloc(svsp->dev, sizeof(*svsb->dev), GFP_KERNEL);
 		if (!svsb->dev)
 			return -ENOMEM;
 
+		svsb->name = devm_kasprintf(svsp->dev, GFP_KERNEL, "%s%s",
+					    svs_swid_names[bdata->sw_id],
+					    svs_type_names[bdata->type]);
+		if (!svsb->name)
+			return -ENOMEM;
+
 		ret = dev_set_name(svsb->dev, "%s", svsb->name);
 		if (ret)
 			return ret;
@@ -1721,32 +1810,32 @@ static int svs_bank_resource_setup(struct svs_platform *svsp)
 
 		if (svsb->mode_support & SVSB_MODE_INIT01) {
 			svsb->buck = devm_regulator_get_optional(svsb->opp_dev,
-								 svsb->buck_name);
+								 bdata->buck_name);
 			if (IS_ERR(svsb->buck)) {
 				dev_err(svsb->dev, "cannot get \"%s-supply\"\n",
-					svsb->buck_name);
+					bdata->buck_name);
 				return PTR_ERR(svsb->buck);
 			}
 		}
 
-		if (!IS_ERR_OR_NULL(svsb->tzone_name)) {
-			svsb->tzd = thermal_zone_get_zone_by_name(svsb->tzone_name);
+		if (!IS_ERR_OR_NULL(bdata->tzone_name)) {
+			svsb->tzd = thermal_zone_get_zone_by_name(bdata->tzone_name);
 			if (IS_ERR(svsb->tzd)) {
 				dev_err(svsb->dev, "cannot get \"%s\" thermal zone\n",
-					svsb->tzone_name);
+					bdata->tzone_name);
 				return PTR_ERR(svsb->tzd);
 			}
 		}
 
 		count = dev_pm_opp_get_opp_count(svsb->opp_dev);
-		if (svsb->opp_count != count) {
+		if (bdata->opp_count != count) {
 			dev_err(svsb->dev,
 				"opp_count not \"%u\" but get \"%d\"?\n",
-				svsb->opp_count, count);
+				bdata->opp_count, count);
 			return count;
 		}
 
-		for (i = 0, freq = U32_MAX; i < svsb->opp_count; i++, freq--) {
+		for (i = 0, freq = ULONG_MAX; i < bdata->opp_count; i++, freq--) {
 			opp = dev_pm_opp_find_freq_floor(svsb->opp_dev, &freq);
 			if (IS_ERR(opp)) {
 				dev_err(svsb->dev, "cannot find freq = %ld\n",
@@ -1780,8 +1869,6 @@ static int svs_get_efuse_data(struct svs_platform *svsp,
 
 	*svsp_efuse = nvmem_cell_read(cell, svsp_efuse_max);
 	if (IS_ERR(*svsp_efuse)) {
-		dev_err(svsp->dev, "cannot read \"%s\" efuse: %ld\n",
-			nvmem_cell_name, PTR_ERR(*svsp_efuse));
 		nvmem_cell_put(cell);
 		return PTR_ERR(*svsp_efuse);
 	}
@@ -1792,139 +1879,91 @@ static int svs_get_efuse_data(struct svs_platform *svsp,
 	return 0;
 }
 
-static bool svs_mt8192_efuse_parsing(struct svs_platform *svsp)
+static u32 svs_get_fuse_val(u32 *fuse_array, const struct svs_fusemap *fmap, u8 nbits)
 {
-	struct svs_bank *svsb;
-	u32 idx, i, vmin, golden_temp;
-	int ret;
-
-	for (i = 0; i < svsp->efuse_max; i++)
-		if (svsp->efuse[i])
-			dev_info(svsp->dev, "M_HW_RES%d: 0x%08x\n",
-				 i, svsp->efuse[i]);
-
-	if (!svsp->efuse[9]) {
-		dev_notice(svsp->dev, "svs_efuse[9] = 0x0?\n");
-		return false;
-	}
-
-	/* Svs efuse parsing */
-	vmin = (svsp->efuse[19] >> 4) & GENMASK(1, 0);
-
-	for (idx = 0; idx < svsp->bank_max; idx++) {
-		svsb = &svsp->banks[idx];
+	u32 val;
 
-		if (vmin == 0x1)
-			svsb->vmin = 0x1e;
-
-		if (svsb->type == SVSB_LOW) {
-			svsb->mtdes = svsp->efuse[10] & GENMASK(7, 0);
-			svsb->bdes = (svsp->efuse[10] >> 16) & GENMASK(7, 0);
-			svsb->mdes = (svsp->efuse[10] >> 24) & GENMASK(7, 0);
-			svsb->dcbdet = (svsp->efuse[17]) & GENMASK(7, 0);
-			svsb->dcmdet = (svsp->efuse[17] >> 8) & GENMASK(7, 0);
-		} else if (svsb->type == SVSB_HIGH) {
-			svsb->mtdes = svsp->efuse[9] & GENMASK(7, 0);
-			svsb->bdes = (svsp->efuse[9] >> 16) & GENMASK(7, 0);
-			svsb->mdes = (svsp->efuse[9] >> 24) & GENMASK(7, 0);
-			svsb->dcbdet = (svsp->efuse[17] >> 16) & GENMASK(7, 0);
-			svsb->dcmdet = (svsp->efuse[17] >> 24) & GENMASK(7, 0);
-		}
+	if (fmap->index < 0)
+		return FUSE_DATA_NOT_VALID;
 
-		svsb->vmax += svsb->dvt_fixed;
-	}
+	val = fuse_array[fmap->index] >> fmap->ofst;
+	val &= GENMASK(nbits - 1, 0);
 
-	ret = svs_get_efuse_data(svsp, "t-calibration-data",
-				 &svsp->tefuse, &svsp->tefuse_max);
-	if (ret)
-		return false;
+	return val;
+}
 
-	for (i = 0; i < svsp->tefuse_max; i++)
-		if (svsp->tefuse[i] != 0)
-			break;
+static bool svs_is_available(struct svs_platform *svsp)
+{
+	int i, num_populated = 0;
 
-	if (i == svsp->tefuse_max)
-		golden_temp = 50; /* All thermal efuse data are 0 */
-	else
-		golden_temp = (svsp->tefuse[0] >> 24) & GENMASK(7, 0);
+	/* If at least two fuse arrays are populated, SVS is calibrated */
+	for (i = 0; i < svsp->efuse_max; i++) {
+		if (svsp->efuse[i])
+			num_populated++;
 
-	for (idx = 0; idx < svsp->bank_max; idx++) {
-		svsb = &svsp->banks[idx];
-		svsb->mts = 500;
-		svsb->bts = (((500 * golden_temp + 250460) / 1000) - 25) * 4;
+		if (num_populated > 1)
+			return true;
 	}
 
-	return true;
+	return false;
 }
 
-static bool svs_mt8188_efuse_parsing(struct svs_platform *svsp)
+static bool svs_common_parse_efuse(struct svs_platform *svsp,
+				   const struct svs_platform_data *pdata)
 {
-	struct svs_bank *svsb;
-	u32 idx, i, golden_temp;
-	int ret;
-
-	for (i = 0; i < svsp->efuse_max; i++)
-		if (svsp->efuse[i])
-			dev_info(svsp->dev, "M_HW_RES%d: 0x%08x\n",
-				 i, svsp->efuse[i]);
+	const struct svs_fusemap *gfmap = pdata->glb_fuse_map;
+	struct svs_fusemap tfm = { 0, 24 };
+	u32 golden_temp, val;
+	u8 ft_pgm, vmin;
+	int i;
 
-	if (!svsp->efuse[5]) {
-		dev_notice(svsp->dev, "svs_efuse[5] = 0x0?\n");
+	if (!svs_is_available(svsp))
 		return false;
-	}
 
-	/* Svs efuse parsing */
-	for (idx = 0; idx < svsp->bank_max; idx++) {
-		svsb = &svsp->banks[idx];
+	/* Get golden temperature from SVS-Thermal calibration */
+	val = svs_get_fuse_val(svsp->tefuse, &tfm, 8);
 
-		if (svsb->type == SVSB_LOW) {
-			svsb->mtdes = svsp->efuse[5] & GENMASK(7, 0);
-			svsb->bdes = (svsp->efuse[5] >> 16) & GENMASK(7, 0);
-			svsb->mdes = (svsp->efuse[5] >> 24) & GENMASK(7, 0);
-			svsb->dcbdet = (svsp->efuse[15] >> 16) & GENMASK(7, 0);
-			svsb->dcmdet = (svsp->efuse[15] >> 24) & GENMASK(7, 0);
-		} else if (svsb->type == SVSB_HIGH) {
-			svsb->mtdes = svsp->efuse[4] & GENMASK(7, 0);
-			svsb->bdes = (svsp->efuse[4] >> 16) & GENMASK(7, 0);
-			svsb->mdes = (svsp->efuse[4] >> 24) & GENMASK(7, 0);
-			svsb->dcbdet = svsp->efuse[14] & GENMASK(7, 0);
-			svsb->dcmdet = (svsp->efuse[14] >> 8) & GENMASK(7, 0);
-		}
+	/* If golden temp is not programmed, use the default of 50 */
+	golden_temp = val ? val : 50;
 
-		svsb->vmax += svsb->dvt_fixed;
-	}
+	/* Parse fused SVS calibration */
+	ft_pgm = svs_get_fuse_val(svsp->efuse, &gfmap[GLB_FT_PGM], 8);
+	vmin = svs_get_fuse_val(svsp->efuse, &gfmap[GLB_VMIN], 2);
 
-	ret = svs_get_efuse_data(svsp, "t-calibration-data",
-				 &svsp->tefuse, &svsp->tefuse_max);
-	if (ret)
-		return false;
+	for (i = 0; i < svsp->bank_max; i++) {
+		struct svs_bank *svsb = &svsp->banks[i];
+		const struct svs_bank_pdata *bdata = &svsb->pdata;
+		const struct svs_fusemap *dfmap = bdata->dev_fuse_map;
 
-	for (i = 0; i < svsp->tefuse_max; i++)
-		if (svsp->tefuse[i] != 0)
-			break;
+		if (vmin == 1)
+			svsb->vmin = 0x1e;
 
-	if (i == svsp->tefuse_max)
-		golden_temp = 50; /* All thermal efuse data are 0 */
-	else
-		golden_temp = (svsp->tefuse[0] >> 24) & GENMASK(7, 0);
+		if (ft_pgm == 0)
+			svsb->volt_flags |= SVSB_INIT01_VOLT_IGNORE;
 
-	for (idx = 0; idx < svsp->bank_max; idx++) {
-		svsb = &svsp->banks[idx];
-		svsb->mts = 500;
-		svsb->bts = (((500 * golden_temp + 250460) / 1000) - 25) * 4;
+		svsb->mtdes = svs_get_fuse_val(svsp->efuse, &dfmap[BDEV_MTDES], 8);
+		svsb->bdes = svs_get_fuse_val(svsp->efuse, &dfmap[BDEV_BDES], 8);
+		svsb->mdes = svs_get_fuse_val(svsp->efuse, &dfmap[BDEV_MDES], 8);
+		svsb->dcbdet = svs_get_fuse_val(svsp->efuse, &dfmap[BDEV_DCBDET], 8);
+		svsb->dcmdet = svs_get_fuse_val(svsp->efuse, &dfmap[BDEV_DCMDET], 8);
+		svsb->vmax += svsb->dvt_fixed;
+
+		svsb->mts = (svsp->ts_coeff * 2) / 1000;
+		svsb->bts = (((500 * golden_temp + svsp->ts_coeff) / 1000) - 25) * 4;
 	}
 
 	return true;
 }
 
-static bool svs_mt8183_efuse_parsing(struct svs_platform *svsp)
+static bool svs_mt8183_efuse_parsing(struct svs_platform *svsp,
+				     const struct svs_platform_data *pdata)
 {
 	struct svs_bank *svsb;
+	const struct svs_bank_pdata *bdata;
 	int format[6], x_roomt[6], o_vtsmcu[5], o_vtsabb, tb_roomt = 0;
 	int adc_ge_t, adc_oe_t, ge, oe, gain, degc_cali, adc_cali_en_t;
 	int o_slope, o_slope_sign, ts_id;
 	u32 idx, i, ft_pgm, mts, temp0, temp1, temp2;
-	int ret;
 
 	for (i = 0; i < svsp->efuse_max; i++)
 		if (svsp->efuse[i])
@@ -1937,74 +1976,48 @@ static bool svs_mt8183_efuse_parsing(struct svs_platform *svsp)
 	}
 
 	/* Svs efuse parsing */
-	ft_pgm = (svsp->efuse[0] >> 4) & GENMASK(3, 0);
+	ft_pgm = svs_get_fuse_val(svsp->efuse, &pdata->glb_fuse_map[GLB_FT_PGM], 4);
 
 	for (idx = 0; idx < svsp->bank_max; idx++) {
 		svsb = &svsp->banks[idx];
+		bdata = &svsb->pdata;
+		const struct svs_fusemap *dfmap = bdata->dev_fuse_map;
 
 		if (ft_pgm <= 1)
 			svsb->volt_flags |= SVSB_INIT01_VOLT_IGNORE;
 
-		switch (svsb->sw_id) {
-		case SVSB_CPU_LITTLE:
-			svsb->bdes = svsp->efuse[16] & GENMASK(7, 0);
-			svsb->mdes = (svsp->efuse[16] >> 8) & GENMASK(7, 0);
-			svsb->dcbdet = (svsp->efuse[16] >> 16) & GENMASK(7, 0);
-			svsb->dcmdet = (svsp->efuse[16] >> 24) & GENMASK(7, 0);
-			svsb->mtdes  = (svsp->efuse[17] >> 16) & GENMASK(7, 0);
+		svsb->mtdes = svs_get_fuse_val(svsp->efuse, &dfmap[BDEV_MTDES], 8);
+		svsb->bdes = svs_get_fuse_val(svsp->efuse, &dfmap[BDEV_BDES], 8);
+		svsb->mdes = svs_get_fuse_val(svsp->efuse, &dfmap[BDEV_MDES], 8);
+		svsb->dcbdet = svs_get_fuse_val(svsp->efuse, &dfmap[BDEV_DCBDET], 8);
+		svsb->dcmdet = svs_get_fuse_val(svsp->efuse, &dfmap[BDEV_DCMDET], 8);
 
+		switch (bdata->sw_id) {
+		case SVSB_SWID_CPU_LITTLE:
+		case SVSB_SWID_CCI:
 			if (ft_pgm <= 3)
 				svsb->volt_od += 10;
 			else
 				svsb->volt_od += 2;
 			break;
-		case SVSB_CPU_BIG:
-			svsb->bdes = svsp->efuse[18] & GENMASK(7, 0);
-			svsb->mdes = (svsp->efuse[18] >> 8) & GENMASK(7, 0);
-			svsb->dcbdet = (svsp->efuse[18] >> 16) & GENMASK(7, 0);
-			svsb->dcmdet = (svsp->efuse[18] >> 24) & GENMASK(7, 0);
-			svsb->mtdes  = svsp->efuse[17] & GENMASK(7, 0);
-
+		case SVSB_SWID_CPU_BIG:
 			if (ft_pgm <= 3)
 				svsb->volt_od += 15;
 			else
 				svsb->volt_od += 12;
 			break;
-		case SVSB_CCI:
-			svsb->bdes = svsp->efuse[4] & GENMASK(7, 0);
-			svsb->mdes = (svsp->efuse[4] >> 8) & GENMASK(7, 0);
-			svsb->dcbdet = (svsp->efuse[4] >> 16) & GENMASK(7, 0);
-			svsb->dcmdet = (svsp->efuse[4] >> 24) & GENMASK(7, 0);
-			svsb->mtdes  = (svsp->efuse[5] >> 16) & GENMASK(7, 0);
-
-			if (ft_pgm <= 3)
-				svsb->volt_od += 10;
-			else
-				svsb->volt_od += 2;
-			break;
-		case SVSB_GPU:
-			svsb->bdes = svsp->efuse[6] & GENMASK(7, 0);
-			svsb->mdes = (svsp->efuse[6] >> 8) & GENMASK(7, 0);
-			svsb->dcbdet = (svsp->efuse[6] >> 16) & GENMASK(7, 0);
-			svsb->dcmdet = (svsp->efuse[6] >> 24) & GENMASK(7, 0);
-			svsb->mtdes  = svsp->efuse[5] & GENMASK(7, 0);
-
-			if (ft_pgm >= 2) {
+		case SVSB_SWID_GPU:
+			if (ft_pgm != FUSE_DATA_NOT_VALID && ft_pgm >= 2) {
 				svsb->freq_base = 800000000; /* 800MHz */
 				svsb->dvt_fixed = 2;
 			}
 			break;
 		default:
-			dev_err(svsb->dev, "unknown sw_id: %u\n", svsb->sw_id);
+			dev_err(svsb->dev, "unknown sw_id: %u\n", bdata->sw_id);
 			return false;
 		}
 	}
 
-	ret = svs_get_efuse_data(svsp, "t-calibration-data",
-				 &svsp->tefuse, &svsp->tefuse_max);
-	if (ret)
-		return false;
-
 	/* Thermal efuse parsing */
 	adc_ge_t = (svsp->tefuse[1] >> 22) & GENMASK(9, 0);
 	adc_oe_t = (svsp->tefuse[1] >> 12) & GENMASK(9, 0);
@@ -2064,23 +2077,24 @@ static bool svs_mt8183_efuse_parsing(struct svs_platform *svsp)
 
 	for (idx = 0; idx < svsp->bank_max; idx++) {
 		svsb = &svsp->banks[idx];
+		bdata = &svsb->pdata;
 		svsb->mts = mts;
 
-		switch (svsb->sw_id) {
-		case SVSB_CPU_LITTLE:
+		switch (bdata->sw_id) {
+		case SVSB_SWID_CPU_LITTLE:
 			tb_roomt = x_roomt[3];
 			break;
-		case SVSB_CPU_BIG:
+		case SVSB_SWID_CPU_BIG:
 			tb_roomt = x_roomt[4];
 			break;
-		case SVSB_CCI:
+		case SVSB_SWID_CCI:
 			tb_roomt = x_roomt[3];
 			break;
-		case SVSB_GPU:
+		case SVSB_SWID_GPU:
 			tb_roomt = x_roomt[1];
 			break;
 		default:
-			dev_err(svsb->dev, "unknown sw_id: %u\n", svsb->sw_id);
+			dev_err(svsb->dev, "unknown sw_id: %u\n", bdata->sw_id);
 			goto remove_mt8183_svsb_mon_mode;
 		}
 
@@ -2153,7 +2167,6 @@ static struct device *svs_add_device_link(struct svs_platform *svsp,
 static int svs_mt8192_platform_probe(struct svs_platform *svsp)
 {
 	struct device *dev;
-	struct svs_bank *svsb;
 	u32 idx;
 
 	svsp->rst = devm_reset_control_get_optional(svsp->dev, "svs_rst");
@@ -2161,18 +2174,33 @@ static int svs_mt8192_platform_probe(struct svs_platform *svsp)
 		return dev_err_probe(svsp->dev, PTR_ERR(svsp->rst),
 				     "cannot get svs reset control\n");
 
-	dev = svs_add_device_link(svsp, "lvts");
+	dev = svs_add_device_link(svsp, "thermal-sensor");
 	if (IS_ERR(dev))
 		return dev_err_probe(svsp->dev, PTR_ERR(dev),
 				     "failed to get lvts device\n");
 
 	for (idx = 0; idx < svsp->bank_max; idx++) {
-		svsb = &svsp->banks[idx];
+		struct svs_bank *svsb = &svsp->banks[idx];
+		const struct svs_bank_pdata *bdata = &svsb->pdata;
 
-		if (svsb->type == SVSB_HIGH)
-			svsb->opp_dev = svs_add_device_link(svsp, "gpu");
-		else if (svsb->type == SVSB_LOW)
-			svsb->opp_dev = svs_get_subsys_device(svsp, "gpu");
+		switch (bdata->sw_id) {
+		case SVSB_SWID_CPU_LITTLE:
+		case SVSB_SWID_CPU_BIG:
+			svsb->opp_dev = get_cpu_device(bdata->cpu_id);
+			break;
+		case SVSB_SWID_CCI:
+			svsb->opp_dev = svs_add_device_link(svsp, "cci");
+			break;
+		case SVSB_SWID_GPU:
+			if (bdata->type == SVSB_TYPE_LOW)
+				svsb->opp_dev = svs_get_subsys_device(svsp, "gpu");
+			else
+				svsb->opp_dev = svs_add_device_link(svsp, "gpu");
+			break;
+		default:
+			dev_err(svsb->dev, "unknown sw_id: %u\n", bdata->sw_id);
+			return -EINVAL;
+		}
 
 		if (IS_ERR(svsb->opp_dev))
 			return dev_err_probe(svsp->dev, PTR_ERR(svsb->opp_dev),
@@ -2186,30 +2214,30 @@ static int svs_mt8192_platform_probe(struct svs_platform *svsp)
 static int svs_mt8183_platform_probe(struct svs_platform *svsp)
 {
 	struct device *dev;
-	struct svs_bank *svsb;
 	u32 idx;
 
-	dev = svs_add_device_link(svsp, "thermal");
+	dev = svs_add_device_link(svsp, "thermal-sensor");
 	if (IS_ERR(dev))
 		return dev_err_probe(svsp->dev, PTR_ERR(dev),
 				     "failed to get thermal device\n");
 
 	for (idx = 0; idx < svsp->bank_max; idx++) {
-		svsb = &svsp->banks[idx];
+		struct svs_bank *svsb = &svsp->banks[idx];
+		const struct svs_bank_pdata *bdata = &svsb->pdata;
 
-		switch (svsb->sw_id) {
-		case SVSB_CPU_LITTLE:
-		case SVSB_CPU_BIG:
-			svsb->opp_dev = get_cpu_device(svsb->cpu_id);
+		switch (bdata->sw_id) {
+		case SVSB_SWID_CPU_LITTLE:
+		case SVSB_SWID_CPU_BIG:
+			svsb->opp_dev = get_cpu_device(bdata->cpu_id);
 			break;
-		case SVSB_CCI:
+		case SVSB_SWID_CCI:
 			svsb->opp_dev = svs_add_device_link(svsp, "cci");
 			break;
-		case SVSB_GPU:
+		case SVSB_SWID_GPU:
 			svsb->opp_dev = svs_add_device_link(svsp, "gpu");
 			break;
 		default:
-			dev_err(svsb->dev, "unknown sw_id: %u\n", svsb->sw_id);
+			dev_err(svsb->dev, "unknown sw_id: %u\n", bdata->sw_id);
 			return -EINVAL;
 		}
 
@@ -2222,241 +2250,544 @@ static int svs_mt8183_platform_probe(struct svs_platform *svsp)
 	return 0;
 }
 
+static struct svs_bank svs_mt8195_banks[] = {
+	{
+		.pdata = (const struct svs_bank_pdata) {
+			.sw_id			= SVSB_SWID_GPU,
+			.type			= SVSB_TYPE_LOW,
+			.set_freq_pct		= svs_set_bank_freq_pct_v3,
+			.get_volts		= svs_get_bank_volts_v3,
+			.opp_count		= MAX_OPP_ENTRIES,
+			.turn_freq_base		= 640000000,
+			.volt_step		= 6250,
+			.volt_base		= 400000,
+			.age_config		= 0x555555,
+			.dc_config		= 0x1,
+			.vco			= 0x18,
+			.chk_shift		= 0x87,
+			.int_st			= BIT(0),
+			.ctl0			= 0x00540003,
+			.dev_fuse_map		= (const struct svs_fusemap[BDEV_MAX]) {
+				{ 10, 16 }, { 10, 24 }, { 10, 0 }, { 8, 0 }, { 8, 8 }
+			}
+		},
+		.mode_support	= SVSB_MODE_INIT02,
+		.volt_flags	= SVSB_REMOVE_DVTFIXED_VOLT,
+		.freq_base	= 640000000,
+		.core_sel	= 0x0fff0100,
+		.dvt_fixed	= 0x1,
+		.vmax		= 0x38,
+		.vmin		= 0x14,
+	},
+	{
+		.pdata = (const struct svs_bank_pdata) {
+			.sw_id			= SVSB_SWID_GPU,
+			.type			= SVSB_TYPE_HIGH,
+			.set_freq_pct		= svs_set_bank_freq_pct_v3,
+			.get_volts		= svs_get_bank_volts_v3,
+			.tzone_name		= "gpu",
+			.opp_count		= MAX_OPP_ENTRIES,
+			.turn_freq_base		= 640000000,
+			.volt_step		= 6250,
+			.volt_base		= 400000,
+			.age_config		= 0x555555,
+			.dc_config		= 0x1,
+			.vco			= 0x18,
+			.chk_shift		= 0x87,
+			.int_st			= BIT(1),
+			.ctl0			= 0x00540003,
+			.tzone_htemp		= 85000,
+			.tzone_htemp_voffset	= 0,
+			.tzone_ltemp		= 25000,
+			.tzone_ltemp_voffset	= 7,
+			.dev_fuse_map		= (const struct svs_fusemap[BDEV_MAX]) {
+				{ 9, 16 }, { 9, 24 }, { 9, 0 }, { 8, 0 }, { 8, 8 }
+			},
+		},
+		.volt_flags	= SVSB_REMOVE_DVTFIXED_VOLT | SVSB_MON_VOLT_IGNORE,
+		.mode_support	= SVSB_MODE_INIT02 | SVSB_MODE_MON,
+		.freq_base	= 880000000,
+		.core_sel	= 0x0fff0101,
+		.dvt_fixed	= 0x6,
+		.vmax		= 0x38,
+		.vmin		= 0x14,
+	},
+};
+
 static struct svs_bank svs_mt8192_banks[] = {
 	{
-		.sw_id			= SVSB_GPU,
-		.type			= SVSB_LOW,
-		.set_freq_pct		= svs_set_bank_freq_pct_v3,
-		.get_volts		= svs_get_bank_volts_v3,
-		.tzone_name		= "gpu1",
-		.volt_flags		= SVSB_REMOVE_DVTFIXED_VOLT,
-		.mode_support		= SVSB_MODE_INIT02,
-		.opp_count		= MAX_OPP_ENTRIES,
-		.freq_base		= 688000000,
-		.turn_freq_base		= 688000000,
-		.volt_step		= 6250,
-		.volt_base		= 400000,
-		.vmax			= 0x60,
-		.vmin			= 0x1a,
-		.age_config		= 0x555555,
-		.dc_config		= 0x1,
-		.dvt_fixed		= 0x1,
-		.vco			= 0x18,
-		.chk_shift		= 0x87,
-		.core_sel		= 0x0fff0100,
-		.int_st			= BIT(0),
-		.ctl0			= 0x00540003,
-		.tzone_htemp		= 85000,
-		.tzone_htemp_voffset	= 0,
-		.tzone_ltemp		= 25000,
-		.tzone_ltemp_voffset	= 7,
+		.pdata = (const struct svs_bank_pdata) {
+			.sw_id			= SVSB_SWID_GPU,
+			.type			= SVSB_TYPE_LOW,
+			.set_freq_pct		= svs_set_bank_freq_pct_v3,
+			.get_volts		= svs_get_bank_volts_v3,
+			.tzone_name		= "gpu",
+			.opp_count		= MAX_OPP_ENTRIES,
+			.turn_freq_base		= 688000000,
+			.volt_step		= 6250,
+			.volt_base		= 400000,
+			.age_config		= 0x555555,
+			.dc_config		= 0x1,
+			.vco			= 0x18,
+			.chk_shift		= 0x87,
+			.int_st			= BIT(0),
+			.ctl0			= 0x00540003,
+			.tzone_htemp		= 85000,
+			.tzone_htemp_voffset	= 0,
+			.tzone_ltemp		= 25000,
+			.tzone_ltemp_voffset	= 7,
+			.dev_fuse_map		= (const struct svs_fusemap[BDEV_MAX]) {
+				{ 10, 16 }, { 10, 24 }, { 10, 0 }, { 17, 0 }, { 17, 8 }
+			}
+		},
+		.volt_flags	= SVSB_REMOVE_DVTFIXED_VOLT,
+		.mode_support	= SVSB_MODE_INIT02,
+		.freq_base	= 688000000,
+		.core_sel	= 0x0fff0100,
+		.dvt_fixed	= 0x1,
+		.vmax		= 0x60,
+		.vmin		= 0x1a,
 	},
 	{
-		.sw_id			= SVSB_GPU,
-		.type			= SVSB_HIGH,
-		.set_freq_pct		= svs_set_bank_freq_pct_v3,
-		.get_volts		= svs_get_bank_volts_v3,
-		.tzone_name		= "gpu1",
-		.volt_flags		= SVSB_REMOVE_DVTFIXED_VOLT |
-					  SVSB_MON_VOLT_IGNORE,
-		.mode_support		= SVSB_MODE_INIT02 | SVSB_MODE_MON,
-		.opp_count		= MAX_OPP_ENTRIES,
-		.freq_base		= 902000000,
-		.turn_freq_base		= 688000000,
-		.volt_step		= 6250,
-		.volt_base		= 400000,
-		.vmax			= 0x60,
-		.vmin			= 0x1a,
-		.age_config		= 0x555555,
-		.dc_config		= 0x1,
-		.dvt_fixed		= 0x6,
-		.vco			= 0x18,
-		.chk_shift		= 0x87,
-		.core_sel		= 0x0fff0101,
-		.int_st			= BIT(1),
-		.ctl0			= 0x00540003,
-		.tzone_htemp		= 85000,
-		.tzone_htemp_voffset	= 0,
-		.tzone_ltemp		= 25000,
-		.tzone_ltemp_voffset	= 7,
+		.pdata = (const struct svs_bank_pdata) {
+			.sw_id			= SVSB_SWID_GPU,
+			.type			= SVSB_TYPE_HIGH,
+			.set_freq_pct		= svs_set_bank_freq_pct_v3,
+			.get_volts		= svs_get_bank_volts_v3,
+			.tzone_name		= "gpu",
+			.opp_count		= MAX_OPP_ENTRIES,
+			.turn_freq_base		= 688000000,
+			.volt_step		= 6250,
+			.volt_base		= 400000,
+			.age_config		= 0x555555,
+			.dc_config		= 0x1,
+			.vco			= 0x18,
+			.chk_shift		= 0x87,
+			.int_st			= BIT(1),
+			.ctl0			= 0x00540003,
+			.tzone_htemp		= 85000,
+			.tzone_htemp_voffset	= 0,
+			.tzone_ltemp		= 25000,
+			.tzone_ltemp_voffset	= 7,
+			.dev_fuse_map		= (const struct svs_fusemap[BDEV_MAX]) {
+				{ 9, 16 }, { 9, 24 }, { 17, 0 }, { 17, 16 }, { 17, 24 }
+			}
+		},
+		.volt_flags	= SVSB_REMOVE_DVTFIXED_VOLT | SVSB_MON_VOLT_IGNORE,
+		.mode_support	= SVSB_MODE_INIT02 | SVSB_MODE_MON,
+		.freq_base	= 902000000,
+		.core_sel	= 0x0fff0101,
+		.dvt_fixed	= 0x6,
+		.vmax		= 0x60,
+		.vmin		= 0x1a,
 	},
 };
 
 static struct svs_bank svs_mt8188_banks[] = {
 	{
-		.sw_id			= SVSB_GPU,
-		.type			= SVSB_LOW,
-		.set_freq_pct		= svs_set_bank_freq_pct_v3,
-		.get_volts		= svs_get_bank_volts_v3,
-		.volt_flags		= SVSB_REMOVE_DVTFIXED_VOLT,
-		.mode_support		= SVSB_MODE_INIT02,
-		.opp_count		= MAX_OPP_ENTRIES,
-		.freq_base		= 640000000,
-		.turn_freq_base		= 640000000,
-		.volt_step		= 6250,
-		.volt_base		= 400000,
-		.vmax			= 0x38,
-		.vmin			= 0x1c,
-		.age_config		= 0x555555,
-		.dc_config		= 0x555555,
-		.dvt_fixed		= 0x1,
-		.vco			= 0x10,
-		.chk_shift		= 0x87,
-		.core_sel		= 0x0fff0000,
-		.int_st			= BIT(0),
-		.ctl0			= 0x00100003,
+		.pdata = (const struct svs_bank_pdata) {
+			.sw_id			= SVSB_SWID_GPU,
+			.type			= SVSB_TYPE_LOW,
+			.set_freq_pct		= svs_set_bank_freq_pct_v3,
+			.get_volts		= svs_get_bank_volts_v3,
+			.opp_count		= MAX_OPP_ENTRIES,
+			.turn_freq_base		= 640000000,
+			.volt_step		= 6250,
+			.volt_base		= 400000,
+			.age_config		= 0x555555,
+			.dc_config		= 0x555555,
+			.vco			= 0x10,
+			.chk_shift		= 0x87,
+			.int_st			= BIT(0),
+			.ctl0			= 0x00100003,
+			.dev_fuse_map		= (const struct svs_fusemap[BDEV_MAX]) {
+				{ 5, 16 }, { 5, 24 }, { 5, 0 }, { 15, 16 }, { 15, 24 }
+			}
+		},
+		.volt_flags	= SVSB_REMOVE_DVTFIXED_VOLT,
+		.mode_support	= SVSB_MODE_INIT02,
+		.freq_base	= 640000000,
+		.core_sel	= 0x0fff0000,
+		.dvt_fixed	= 0x1,
+		.vmax		= 0x38,
+		.vmin		= 0x1c,
+	},
+	{
+		.pdata = (const struct svs_bank_pdata) {
+			.sw_id			= SVSB_SWID_GPU,
+			.type			= SVSB_TYPE_HIGH,
+			.set_freq_pct		= svs_set_bank_freq_pct_v3,
+			.get_volts		= svs_get_bank_volts_v3,
+			.tzone_name		= "gpu",
+			.opp_count		= MAX_OPP_ENTRIES,
+			.turn_freq_base		= 640000000,
+			.volt_step		= 6250,
+			.volt_base		= 400000,
+			.age_config		= 0x555555,
+			.dc_config		= 0x555555,
+			.vco			= 0x10,
+			.chk_shift		= 0x87,
+			.int_st			= BIT(1),
+			.ctl0			= 0x00100003,
+			.tzone_htemp		= 85000,
+			.tzone_htemp_voffset	= 0,
+			.tzone_ltemp		= 25000,
+			.tzone_ltemp_voffset	= 7,
+			.dev_fuse_map		= (const struct svs_fusemap[BDEV_MAX]) {
+				{ 4, 16 }, { 4, 24 }, { 4, 0 }, { 14, 0 }, { 14, 8 }
+			}
+		},
+		.volt_flags	= SVSB_REMOVE_DVTFIXED_VOLT | SVSB_MON_VOLT_IGNORE,
+		.mode_support	= SVSB_MODE_INIT02 | SVSB_MODE_MON,
+		.freq_base	= 880000000,
+		.core_sel	= 0x0fff0001,
+		.dvt_fixed	= 0x4,
+		.vmax		= 0x38,
+		.vmin		= 0x1c,
+	},
+};
+
+static struct svs_bank svs_mt8186_banks[] = {
+	{
+		.pdata = (const struct svs_bank_pdata) {
+			.sw_id			= SVSB_SWID_CPU_BIG,
+			.type			= SVSB_TYPE_LOW,
+			.set_freq_pct		= svs_set_bank_freq_pct_v3,
+			.get_volts		= svs_get_bank_volts_v3,
+			.cpu_id			= 6,
+			.opp_count		= MAX_OPP_ENTRIES,
+			.turn_freq_base		= 1670000000,
+			.volt_step		= 6250,
+			.volt_base		= 400000,
+			.age_config		= 0x1,
+			.dc_config		= 0x1,
+			.vco			= 0x10,
+			.chk_shift		= 0x87,
+			.int_st			= BIT(0),
+			.ctl0			= 0x00540003,
+			.dev_fuse_map		= (const struct svs_fusemap[BDEV_MAX]) {
+				{ 3, 16 }, { 3, 24 }, { 3, 0 }, { 14, 16 }, { 14, 24 }
+			}
+		},
+		.volt_flags	= SVSB_REMOVE_DVTFIXED_VOLT,
+		.volt_od	= 4,
+		.mode_support	= SVSB_MODE_INIT02,
+		.freq_base	= 1670000000,
+		.core_sel	= 0x0fff0100,
+		.dvt_fixed	= 0x3,
+		.vmax		= 0x59,
+		.vmin		= 0x20,
+	},
+	{
+		.pdata = (const struct svs_bank_pdata) {
+			.sw_id			= SVSB_SWID_CPU_BIG,
+			.type			= SVSB_TYPE_HIGH,
+			.set_freq_pct		= svs_set_bank_freq_pct_v3,
+			.get_volts		= svs_get_bank_volts_v3,
+			.cpu_id			= 6,
+			.tzone_name		= "cpu-big",
+			.opp_count		= MAX_OPP_ENTRIES,
+			.turn_freq_base		= 1670000000,
+			.volt_step		= 6250,
+			.volt_base		= 400000,
+			.age_config		= 0x1,
+			.dc_config		= 0x1,
+			.vco			= 0x10,
+			.chk_shift		= 0x87,
+			.int_st			= BIT(1),
+			.ctl0			= 0x00540003,
+			.tzone_htemp		= 85000,
+			.tzone_htemp_voffset	= 8,
+			.tzone_ltemp		= 25000,
+			.tzone_ltemp_voffset	= 8,
+			.dev_fuse_map		= (const struct svs_fusemap[BDEV_MAX]) {
+				{ 2, 16 }, { 2, 24 }, { 2, 0 }, { 13, 0 }, { 13, 8 }
+			}
+		},
+		.volt_flags	= SVSB_REMOVE_DVTFIXED_VOLT | SVSB_MON_VOLT_IGNORE,
+		.volt_od	= 4,
+		.mode_support	= SVSB_MODE_INIT02 | SVSB_MODE_MON,
+		.freq_base	= 2050000000,
+		.core_sel	= 0x0fff0101,
+		.dvt_fixed	= 0x6,
+		.vmax		= 0x73,
+		.vmin		= 0x20,
+	},
+	{
+		.pdata = (const struct svs_bank_pdata) {
+			.sw_id			= SVSB_SWID_CPU_LITTLE,
+			.set_freq_pct		= svs_set_bank_freq_pct_v2,
+			.get_volts		= svs_get_bank_volts_v2,
+			.cpu_id			= 0,
+			.tzone_name		= "cpu-little",
+			.opp_count		= MAX_OPP_ENTRIES,
+			.volt_step		= 6250,
+			.volt_base		= 400000,
+			.age_config		= 0x1,
+			.dc_config		= 0x1,
+			.vco			= 0x10,
+			.chk_shift		= 0x87,
+			.int_st			= BIT(2),
+			.ctl0			= 0x3210000f,
+			.tzone_htemp		= 85000,
+			.tzone_htemp_voffset	= 8,
+			.tzone_ltemp		= 25000,
+			.tzone_ltemp_voffset	= 8,
+			.dev_fuse_map		= (const struct svs_fusemap[BDEV_MAX]) {
+				{ 4, 16 }, { 4, 24 }, { 4, 0 }, { 14, 0 }, { 14, 8 }
+			}
+		},
+		.volt_flags	= SVSB_REMOVE_DVTFIXED_VOLT | SVSB_MON_VOLT_IGNORE,
+		.volt_od	= 3,
+		.mode_support	= SVSB_MODE_INIT02 | SVSB_MODE_MON,
+		.freq_base	= 2000000000,
+		.core_sel	= 0x0fff0102,
+		.dvt_fixed	= 0x6,
+		.vmax		= 0x65,
+		.vmin		= 0x20,
 	},
 	{
-		.sw_id			= SVSB_GPU,
-		.type			= SVSB_HIGH,
-		.set_freq_pct		= svs_set_bank_freq_pct_v3,
-		.get_volts		= svs_get_bank_volts_v3,
-		.tzone_name		= "gpu1",
-		.volt_flags		= SVSB_REMOVE_DVTFIXED_VOLT |
-					  SVSB_MON_VOLT_IGNORE,
-		.mode_support		= SVSB_MODE_INIT02 | SVSB_MODE_MON,
-		.opp_count		= MAX_OPP_ENTRIES,
-		.freq_base		= 880000000,
-		.turn_freq_base		= 640000000,
-		.volt_step		= 6250,
-		.volt_base		= 400000,
-		.vmax			= 0x38,
-		.vmin			= 0x1c,
-		.age_config		= 0x555555,
-		.dc_config		= 0x555555,
-		.dvt_fixed		= 0x4,
-		.vco			= 0x10,
-		.chk_shift		= 0x87,
-		.core_sel		= 0x0fff0001,
-		.int_st			= BIT(1),
-		.ctl0			= 0x00100003,
-		.tzone_htemp		= 85000,
-		.tzone_htemp_voffset	= 0,
-		.tzone_ltemp		= 25000,
-		.tzone_ltemp_voffset	= 7,
+		.pdata = (const struct svs_bank_pdata) {
+			.sw_id			= SVSB_SWID_CCI,
+			.set_freq_pct		= svs_set_bank_freq_pct_v2,
+			.get_volts		= svs_get_bank_volts_v2,
+			.tzone_name		= "cci",
+			.opp_count		= MAX_OPP_ENTRIES,
+			.volt_step		= 6250,
+			.volt_base		= 400000,
+			.age_config		= 0x1,
+			.dc_config		= 0x1,
+			.vco			= 0x10,
+			.chk_shift		= 0x87,
+			.int_st			= BIT(3),
+			.ctl0			= 0x3210000f,
+			.tzone_htemp		= 85000,
+			.tzone_htemp_voffset	= 8,
+			.tzone_ltemp		= 25000,
+			.tzone_ltemp_voffset	= 8,
+			.dev_fuse_map		= (const struct svs_fusemap[BDEV_MAX]) {
+				{ 5, 16 }, { 5, 24 }, { 5, 0 }, { 15, 16 }, { 15, 24 }
+			}
+		},
+		.volt_flags	= SVSB_REMOVE_DVTFIXED_VOLT | SVSB_MON_VOLT_IGNORE,
+		.volt_od	= 3,
+		.mode_support	= SVSB_MODE_INIT02 | SVSB_MODE_MON,
+		.freq_base	= 1400000000,
+		.core_sel	= 0x0fff0103,
+		.dvt_fixed	= 0x6,
+		.vmax		= 0x65,
+		.vmin		= 0x20,
+	},
+	{
+		.pdata = (const struct svs_bank_pdata) {
+			.sw_id			= SVSB_SWID_GPU,
+			.set_freq_pct		= svs_set_bank_freq_pct_v2,
+			.get_volts		= svs_get_bank_volts_v2,
+			.tzone_name		= "gpu",
+			.opp_count		= MAX_OPP_ENTRIES,
+			.volt_step		= 6250,
+			.volt_base		= 400000,
+			.age_config		= 0x555555,
+			.dc_config		= 0x1,
+			.vco			= 0x10,
+			.chk_shift		= 0x87,
+			.int_st			= BIT(4),
+			.ctl0			= 0x00100003,
+			.tzone_htemp		= 85000,
+			.tzone_htemp_voffset	= 8,
+			.tzone_ltemp		= 25000,
+			.tzone_ltemp_voffset	= 7,
+			.dev_fuse_map		= (const struct svs_fusemap[BDEV_MAX]) {
+				{ 6, 16 }, { 6, 24 }, { 6, 0 }, { 15, 8 }, { 15, 0 }
+			}
+		},
+		.volt_flags	= SVSB_REMOVE_DVTFIXED_VOLT | SVSB_MON_VOLT_IGNORE,
+		.mode_support	= SVSB_MODE_INIT02 | SVSB_MODE_MON,
+		.freq_base	= 850000000,
+		.core_sel	= 0x0fff0104,
+		.dvt_fixed	= 0x4,
+		.vmax		= 0x58,
+		.vmin		= 0x20,
 	},
 };
 
 static struct svs_bank svs_mt8183_banks[] = {
 	{
-		.sw_id			= SVSB_CPU_LITTLE,
-		.set_freq_pct		= svs_set_bank_freq_pct_v2,
-		.get_volts		= svs_get_bank_volts_v2,
-		.cpu_id			= 0,
-		.buck_name		= "proc",
-		.volt_flags		= SVSB_INIT01_VOLT_INC_ONLY,
-		.mode_support		= SVSB_MODE_INIT01 | SVSB_MODE_INIT02,
-		.opp_count		= MAX_OPP_ENTRIES,
-		.freq_base		= 1989000000,
-		.vboot			= 0x30,
-		.volt_step		= 6250,
-		.volt_base		= 500000,
-		.vmax			= 0x64,
-		.vmin			= 0x18,
-		.age_config		= 0x555555,
-		.dc_config		= 0x555555,
-		.dvt_fixed		= 0x7,
-		.vco			= 0x10,
-		.chk_shift		= 0x77,
-		.core_sel		= 0x8fff0000,
-		.int_st			= BIT(0),
-		.ctl0			= 0x00010001,
+		.pdata = (const struct svs_bank_pdata) {
+			.sw_id			= SVSB_SWID_CPU_LITTLE,
+			.set_freq_pct		= svs_set_bank_freq_pct_v2,
+			.get_volts		= svs_get_bank_volts_v2,
+			.cpu_id			= 0,
+			.buck_name		= "proc",
+			.opp_count		= MAX_OPP_ENTRIES,
+			.vboot			= 0x30,
+			.volt_step		= 6250,
+			.volt_base		= 500000,
+			.age_config		= 0x555555,
+			.dc_config		= 0x555555,
+			.vco			= 0x10,
+			.chk_shift		= 0x77,
+			.int_st			= BIT(0),
+			.ctl0			= 0x00010001,
+			.dev_fuse_map		= (const struct svs_fusemap[BDEV_MAX]) {
+				{ 16, 0 }, { 16, 8 }, { 17, 16 }, { 16, 16 }, { 16, 24 }
+			}
+		},
+		.volt_flags	= SVSB_INIT01_VOLT_INC_ONLY,
+		.mode_support	= SVSB_MODE_INIT01 | SVSB_MODE_INIT02,
+		.freq_base	= 1989000000,
+		.core_sel	= 0x8fff0000,
+		.dvt_fixed	= 0x7,
+		.vmax		= 0x64,
+		.vmin		= 0x18,
+
 	},
 	{
-		.sw_id			= SVSB_CPU_BIG,
-		.set_freq_pct		= svs_set_bank_freq_pct_v2,
-		.get_volts		= svs_get_bank_volts_v2,
-		.cpu_id			= 4,
-		.buck_name		= "proc",
-		.volt_flags		= SVSB_INIT01_VOLT_INC_ONLY,
-		.mode_support		= SVSB_MODE_INIT01 | SVSB_MODE_INIT02,
-		.opp_count		= MAX_OPP_ENTRIES,
-		.freq_base		= 1989000000,
-		.vboot			= 0x30,
-		.volt_step		= 6250,
-		.volt_base		= 500000,
-		.vmax			= 0x58,
-		.vmin			= 0x10,
-		.age_config		= 0x555555,
-		.dc_config		= 0x555555,
-		.dvt_fixed		= 0x7,
-		.vco			= 0x10,
-		.chk_shift		= 0x77,
-		.core_sel		= 0x8fff0001,
-		.int_st			= BIT(1),
-		.ctl0			= 0x00000001,
+		.pdata = (const struct svs_bank_pdata) {
+			.sw_id			= SVSB_SWID_CPU_BIG,
+			.set_freq_pct		= svs_set_bank_freq_pct_v2,
+			.get_volts		= svs_get_bank_volts_v2,
+			.cpu_id			= 4,
+			.buck_name		= "proc",
+			.opp_count		= MAX_OPP_ENTRIES,
+			.vboot			= 0x30,
+			.volt_step		= 6250,
+			.volt_base		= 500000,
+			.age_config		= 0x555555,
+			.dc_config		= 0x555555,
+			.vco			= 0x10,
+			.chk_shift		= 0x77,
+			.int_st			= BIT(1),
+			.ctl0			= 0x00000001,
+			.dev_fuse_map		= (const struct svs_fusemap[BDEV_MAX]) {
+				{ 18, 0 }, { 18, 8 }, { 17, 0 }, { 18, 16 }, { 18, 24 }
+			}
+		},
+		.volt_flags	= SVSB_INIT01_VOLT_INC_ONLY,
+		.mode_support	= SVSB_MODE_INIT01 | SVSB_MODE_INIT02,
+		.freq_base	= 1989000000,
+		.core_sel	= 0x8fff0001,
+		.dvt_fixed	= 0x7,
+		.vmax		= 0x58,
+		.vmin		= 0x10,
+
 	},
 	{
-		.sw_id			= SVSB_CCI,
-		.set_freq_pct		= svs_set_bank_freq_pct_v2,
-		.get_volts		= svs_get_bank_volts_v2,
-		.buck_name		= "proc",
-		.volt_flags		= SVSB_INIT01_VOLT_INC_ONLY,
-		.mode_support		= SVSB_MODE_INIT01 | SVSB_MODE_INIT02,
-		.opp_count		= MAX_OPP_ENTRIES,
-		.freq_base		= 1196000000,
-		.vboot			= 0x30,
-		.volt_step		= 6250,
-		.volt_base		= 500000,
-		.vmax			= 0x64,
-		.vmin			= 0x18,
-		.age_config		= 0x555555,
-		.dc_config		= 0x555555,
-		.dvt_fixed		= 0x7,
-		.vco			= 0x10,
-		.chk_shift		= 0x77,
-		.core_sel		= 0x8fff0002,
-		.int_st			= BIT(2),
-		.ctl0			= 0x00100003,
+		.pdata = (const struct svs_bank_pdata) {
+			.sw_id			= SVSB_SWID_CCI,
+			.set_freq_pct		= svs_set_bank_freq_pct_v2,
+			.get_volts		= svs_get_bank_volts_v2,
+			.buck_name		= "proc",
+			.opp_count		= MAX_OPP_ENTRIES,
+			.vboot			= 0x30,
+			.volt_step		= 6250,
+			.volt_base		= 500000,
+			.age_config		= 0x555555,
+			.dc_config		= 0x555555,
+			.vco			= 0x10,
+			.chk_shift		= 0x77,
+			.int_st			= BIT(2),
+			.ctl0			= 0x00100003,
+			.dev_fuse_map		= (const struct svs_fusemap[BDEV_MAX]) {
+				{ 4, 0 }, { 4, 8 }, { 5, 16 }, { 4, 16 }, { 4, 24 }
+			}
+		},
+		.volt_flags	= SVSB_INIT01_VOLT_INC_ONLY,
+		.mode_support	= SVSB_MODE_INIT01 | SVSB_MODE_INIT02,
+		.freq_base	= 1196000000,
+		.core_sel	= 0x8fff0002,
+		.dvt_fixed	= 0x7,
+		.vmax		= 0x64,
+		.vmin		= 0x18,
 	},
 	{
-		.sw_id			= SVSB_GPU,
-		.set_freq_pct		= svs_set_bank_freq_pct_v2,
-		.get_volts		= svs_get_bank_volts_v2,
-		.buck_name		= "mali",
-		.tzone_name		= "tzts2",
-		.volt_flags		= SVSB_INIT01_PD_REQ |
-					  SVSB_INIT01_VOLT_INC_ONLY,
-		.mode_support		= SVSB_MODE_INIT01 | SVSB_MODE_INIT02 |
-					  SVSB_MODE_MON,
-		.opp_count		= MAX_OPP_ENTRIES,
-		.freq_base		= 900000000,
-		.vboot			= 0x30,
-		.volt_step		= 6250,
-		.volt_base		= 500000,
-		.vmax			= 0x40,
-		.vmin			= 0x14,
-		.age_config		= 0x555555,
-		.dc_config		= 0x555555,
-		.dvt_fixed		= 0x3,
-		.vco			= 0x10,
-		.chk_shift		= 0x77,
-		.core_sel		= 0x8fff0003,
-		.int_st			= BIT(3),
-		.ctl0			= 0x00050001,
-		.tzone_htemp		= 85000,
-		.tzone_htemp_voffset	= 0,
-		.tzone_ltemp		= 25000,
-		.tzone_ltemp_voffset	= 3,
+		.pdata = (const struct svs_bank_pdata) {
+			.sw_id			= SVSB_SWID_GPU,
+			.set_freq_pct		= svs_set_bank_freq_pct_v2,
+			.get_volts		= svs_get_bank_volts_v2,
+			.buck_name		= "mali",
+			.tzone_name		= "gpu",
+			.opp_count		= MAX_OPP_ENTRIES,
+			.vboot			= 0x30,
+			.volt_step		= 6250,
+			.volt_base		= 500000,
+			.age_config		= 0x555555,
+			.dc_config		= 0x555555,
+			.vco			= 0x10,
+			.chk_shift		= 0x77,
+			.int_st			= BIT(3),
+			.ctl0			= 0x00050001,
+			.tzone_htemp		= 85000,
+			.tzone_htemp_voffset	= 0,
+			.tzone_ltemp		= 25000,
+			.tzone_ltemp_voffset	= 3,
+			.dev_fuse_map		= (const struct svs_fusemap[BDEV_MAX]) {
+				{ 6, 0 }, { 6, 8 }, { 5, 0 }, { 6, 16 }, { 6, 24 }
+			}
+		},
+		.volt_flags	= SVSB_INIT01_PD_REQ | SVSB_INIT01_VOLT_INC_ONLY,
+		.mode_support	= SVSB_MODE_INIT01 | SVSB_MODE_INIT02 | SVSB_MODE_MON,
+		.freq_base	= 900000000,
+		.core_sel	= 0x8fff0003,
+		.dvt_fixed	= 0x3,
+		.vmax		= 0x40,
+		.vmin		= 0x14,
 	},
 };
 
+static const struct svs_platform_data svs_mt8195_platform_data = {
+	.name = "mt8195-svs",
+	.banks = svs_mt8195_banks,
+	.efuse_parsing = svs_common_parse_efuse,
+	.probe = svs_mt8192_platform_probe,
+	.regs = svs_regs_v2,
+	.bank_max = ARRAY_SIZE(svs_mt8195_banks),
+	.ts_coeff = SVSB_TS_COEFF_MT8195,
+	.glb_fuse_map = (const struct svs_fusemap[GLB_MAX]) {
+		{ 0, 0 }, { 19, 4 }
+	}
+};
+
 static const struct svs_platform_data svs_mt8192_platform_data = {
 	.name = "mt8192-svs",
 	.banks = svs_mt8192_banks,
-	.efuse_parsing = svs_mt8192_efuse_parsing,
+	.efuse_parsing = svs_common_parse_efuse,
 	.probe = svs_mt8192_platform_probe,
 	.regs = svs_regs_v2,
 	.bank_max = ARRAY_SIZE(svs_mt8192_banks),
+	.ts_coeff = SVSB_TS_COEFF_MT8195,
+	.glb_fuse_map = (const struct svs_fusemap[GLB_MAX]) {
+		/* FT_PGM not present */
+		{ -1, 0 }, { 19, 4 }
+	}
 };
 
 static const struct svs_platform_data svs_mt8188_platform_data = {
 	.name = "mt8188-svs",
 	.banks = svs_mt8188_banks,
-	.efuse_parsing = svs_mt8188_efuse_parsing,
+	.efuse_parsing = svs_common_parse_efuse,
 	.probe = svs_mt8192_platform_probe,
 	.regs = svs_regs_v2,
 	.bank_max = ARRAY_SIZE(svs_mt8188_banks),
+	.ts_coeff = SVSB_TS_COEFF_MT8195,
+	.glb_fuse_map = (const struct svs_fusemap[GLB_MAX]) {
+		/* FT_PGM and VMIN not present */
+		{ -1, 0 }, { -1, 0 }
+	}
+};
+
+static const struct svs_platform_data svs_mt8186_platform_data = {
+	.name = "mt8186-svs",
+	.banks = svs_mt8186_banks,
+	.efuse_parsing = svs_common_parse_efuse,
+	.probe = svs_mt8192_platform_probe,
+	.regs = svs_regs_v2,
+	.bank_max = ARRAY_SIZE(svs_mt8186_banks),
+	.ts_coeff = SVSB_TS_COEFF_MT8186,
+	.glb_fuse_map = (const struct svs_fusemap[GLB_MAX]) {
+		/* FT_PGM and VMIN not present */
+		{ -1, 0 }, { -1, 0 }
+	}
 };
 
 static const struct svs_platform_data svs_mt8183_platform_data = {
@@ -2466,21 +2797,19 @@ static const struct svs_platform_data svs_mt8183_platform_data = {
 	.probe = svs_mt8183_platform_probe,
 	.regs = svs_regs_v2,
 	.bank_max = ARRAY_SIZE(svs_mt8183_banks),
+	.glb_fuse_map = (const struct svs_fusemap[GLB_MAX]) {
+		/* VMIN not present */
+		{ 0, 4 }, { -1, 0 }
+	}
 };
 
 static const struct of_device_id svs_of_match[] = {
-	{
-		.compatible = "mediatek,mt8192-svs",
-		.data = &svs_mt8192_platform_data,
-	}, {
-		.compatible = "mediatek,mt8188-svs",
-		.data = &svs_mt8188_platform_data,
-	}, {
-		.compatible = "mediatek,mt8183-svs",
-		.data = &svs_mt8183_platform_data,
-	}, {
-		/* Sentinel */
-	},
+	{ .compatible = "mediatek,mt8195-svs", .data = &svs_mt8195_platform_data },
+	{ .compatible = "mediatek,mt8192-svs", .data = &svs_mt8192_platform_data },
+	{ .compatible = "mediatek,mt8188-svs", .data = &svs_mt8188_platform_data },
+	{ .compatible = "mediatek,mt8186-svs", .data = &svs_mt8186_platform_data },
+	{ .compatible = "mediatek,mt8183-svs", .data = &svs_mt8183_platform_data },
+	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, svs_of_match);
 
@@ -2500,6 +2829,7 @@ static int svs_probe(struct platform_device *pdev)
 	svsp->banks = svsp_data->banks;
 	svsp->regs = svsp_data->regs;
 	svsp->bank_max = svsp_data->bank_max;
+	svsp->ts_coeff = svsp_data->ts_coeff;
 
 	ret = svsp_data->probe(svsp);
 	if (ret)
@@ -2507,20 +2837,24 @@ static int svs_probe(struct platform_device *pdev)
 
 	ret = svs_get_efuse_data(svsp, "svs-calibration-data",
 				 &svsp->efuse, &svsp->efuse_max);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret, "Cannot read SVS calibration\n");
+
+	ret = svs_get_efuse_data(svsp, "t-calibration-data",
+				 &svsp->tefuse, &svsp->tefuse_max);
 	if (ret) {
-		ret = -EPERM;
+		dev_err_probe(&pdev->dev, ret, "Cannot read SVS-Thermal calibration\n");
 		goto svs_probe_free_efuse;
 	}
 
-	if (!svsp_data->efuse_parsing(svsp)) {
-		dev_err(svsp->dev, "efuse data parsing failed\n");
-		ret = -EPERM;
+	if (!svsp_data->efuse_parsing(svsp, svsp_data)) {
+		ret = dev_err_probe(svsp->dev, -EINVAL, "efuse data parsing failed\n");
 		goto svs_probe_free_tefuse;
 	}
 
 	ret = svs_bank_resource_setup(svsp);
 	if (ret) {
-		dev_err(svsp->dev, "svs bank resource setup fail: %d\n", ret);
+		dev_err_probe(svsp->dev, ret, "svs bank resource setup fail\n");
 		goto svs_probe_free_tefuse;
 	}
 
@@ -2532,43 +2866,40 @@ static int svs_probe(struct platform_device *pdev)
 
 	svsp->main_clk = devm_clk_get(svsp->dev, "main");
 	if (IS_ERR(svsp->main_clk)) {
-		dev_err(svsp->dev, "failed to get clock: %ld\n",
-			PTR_ERR(svsp->main_clk));
-		ret = PTR_ERR(svsp->main_clk);
+		ret = dev_err_probe(svsp->dev, PTR_ERR(svsp->main_clk),
+				    "failed to get clock\n");
 		goto svs_probe_free_tefuse;
 	}
 
 	ret = clk_prepare_enable(svsp->main_clk);
 	if (ret) {
-		dev_err(svsp->dev, "cannot enable main clk: %d\n", ret);
+		dev_err_probe(svsp->dev, ret, "cannot enable main clk\n");
 		goto svs_probe_free_tefuse;
 	}
 
 	svsp->base = of_iomap(svsp->dev->of_node, 0);
 	if (IS_ERR_OR_NULL(svsp->base)) {
-		dev_err(svsp->dev, "cannot find svs register base\n");
-		ret = -EINVAL;
+		ret = dev_err_probe(svsp->dev, -EINVAL, "cannot find svs register base\n");
 		goto svs_probe_clk_disable;
 	}
 
 	ret = devm_request_threaded_irq(svsp->dev, svsp_irq, NULL, svs_isr,
 					IRQF_ONESHOT, svsp_data->name, svsp);
 	if (ret) {
-		dev_err(svsp->dev, "register irq(%d) failed: %d\n",
-			svsp_irq, ret);
+		dev_err_probe(svsp->dev, ret, "register irq(%d) failed\n", svsp_irq);
 		goto svs_probe_iounmap;
 	}
 
 	ret = svs_start(svsp);
 	if (ret) {
-		dev_err(svsp->dev, "svs start fail: %d\n", ret);
+		dev_err_probe(svsp->dev, ret, "svs start fail\n");
 		goto svs_probe_iounmap;
 	}
 
 #ifdef CONFIG_DEBUG_FS
 	ret = svs_create_debug_cmds(svsp);
 	if (ret) {
-		dev_err(svsp->dev, "svs create debug cmds fail: %d\n", ret);
+		dev_err_probe(svsp->dev, ret, "svs create debug cmds fail\n");
 		goto svs_probe_iounmap;
 	}
 #endif
@@ -2577,18 +2908,12 @@ static int svs_probe(struct platform_device *pdev)
 
 svs_probe_iounmap:
 	iounmap(svsp->base);
-
 svs_probe_clk_disable:
 	clk_disable_unprepare(svsp->main_clk);
-
 svs_probe_free_tefuse:
-	if (!IS_ERR_OR_NULL(svsp->tefuse))
-		kfree(svsp->tefuse);
-
+	kfree(svsp->tefuse);
 svs_probe_free_efuse:
-	if (!IS_ERR_OR_NULL(svsp->efuse))
-		kfree(svsp->efuse);
-
+	kfree(svsp->efuse);
 	return ret;
 }
 
@@ -2606,5 +2931,6 @@ static struct platform_driver svs_driver = {
 module_platform_driver(svs_driver);
 
 MODULE_AUTHOR("Roger Lu <roger.lu@mediatek.com>");
+MODULE_AUTHOR("AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>");
 MODULE_DESCRIPTION("MediaTek SVS driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/soc/microchip/Kconfig b/drivers/soc/microchip/Kconfig
index eb656b33156b..9b0fdd95276e 100644
--- a/drivers/soc/microchip/Kconfig
+++ b/drivers/soc/microchip/Kconfig
@@ -1,6 +1,7 @@
 config POLARFIRE_SOC_SYS_CTRL
 	tristate "POLARFIRE_SOC_SYS_CTRL"
 	depends on POLARFIRE_SOC_MAILBOX
+	depends on MTD
 	help
 	  This driver adds support for the PolarFire SoC (MPFS) system controller.
 
diff --git a/drivers/soc/microchip/mpfs-sys-controller.c b/drivers/soc/microchip/mpfs-sys-controller.c
index 0935e9e94172..7a4936019329 100644
--- a/drivers/soc/microchip/mpfs-sys-controller.c
+++ b/drivers/soc/microchip/mpfs-sys-controller.c
@@ -12,6 +12,8 @@
 #include <linux/kref.h>
 #include <linux/module.h>
 #include <linux/jiffies.h>
+#include <linux/mtd/mtd.h>
+#include <linux/spi/spi.h>
 #include <linux/interrupt.h>
 #include <linux/of.h>
 #include <linux/mailbox_client.h>
@@ -30,6 +32,7 @@ struct mpfs_sys_controller {
 	struct mbox_client client;
 	struct mbox_chan *chan;
 	struct completion c;
+	struct mtd_info *flash;
 	struct kref consumers;
 };
 
@@ -63,7 +66,9 @@ int mpfs_blocking_transaction(struct mpfs_sys_controller *sys_controller, struct
 	 */
 	if (!wait_for_completion_timeout(&sys_controller->c, timeout)) {
 		ret = -EBADMSG;
-		dev_warn(sys_controller->client.dev, "MPFS sys controller service failed\n");
+		dev_warn(sys_controller->client.dev,
+			 "MPFS sys controller service failed with status: %d\n",
+			 msg->response->resp_status);
 	} else {
 		ret = 0;
 	}
@@ -99,6 +104,12 @@ static void mpfs_sys_controller_put(void *data)
 	kref_put(&sys_controller->consumers, mpfs_sys_controller_delete);
 }
 
+struct mtd_info *mpfs_sys_controller_get_flash(struct mpfs_sys_controller *mpfs_client)
+{
+	return mpfs_client->flash;
+}
+EXPORT_SYMBOL(mpfs_sys_controller_get_flash);
+
 static struct platform_device subdevs[] = {
 	{
 		.name		= "mpfs-rng",
@@ -107,19 +118,34 @@ static struct platform_device subdevs[] = {
 	{
 		.name		= "mpfs-generic-service",
 		.id		= -1,
-	}
+	},
+	{
+		.name		= "mpfs-auto-update",
+		.id		= -1,
+	},
 };
 
 static int mpfs_sys_controller_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct mpfs_sys_controller *sys_controller;
+	struct device_node *np;
 	int i, ret;
 
 	sys_controller = kzalloc(sizeof(*sys_controller), GFP_KERNEL);
 	if (!sys_controller)
 		return -ENOMEM;
 
+	np = of_parse_phandle(dev->of_node, "microchip,bitstream-flash", 0);
+	if (!np)
+		goto no_flash;
+
+	sys_controller->flash = of_get_mtd_device_by_node(np);
+	of_node_put(np);
+	if (IS_ERR(sys_controller->flash))
+		return dev_err_probe(dev, PTR_ERR(sys_controller->flash), "Failed to get flash\n");
+
+no_flash:
 	sys_controller->client.dev = dev;
 	sys_controller->client.rx_callback = mpfs_sys_controller_rx_callback;
 	sys_controller->client.tx_block = 1U;
@@ -138,7 +164,6 @@ static int mpfs_sys_controller_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, sys_controller);
 
-	dev_info(&pdev->dev, "Registered MPFS system controller\n");
 
 	for (i = 0; i < ARRAY_SIZE(subdevs); i++) {
 		subdevs[i].dev.parent = dev;
@@ -146,6 +171,8 @@ static int mpfs_sys_controller_probe(struct platform_device *pdev)
 			dev_warn(dev, "Error registering sub device %s\n", subdevs[i].name);
 	}
 
+	dev_info(&pdev->dev, "Registered MPFS system controller\n");
+
 	return 0;
 }
 
diff --git a/drivers/soc/pxa/ssp.c b/drivers/soc/pxa/ssp.c
index a1e8a07f7275..7af04e8b8163 100644
--- a/drivers/soc/pxa/ssp.c
+++ b/drivers/soc/pxa/ssp.c
@@ -152,11 +152,11 @@ static int pxa_ssp_probe(struct platform_device *pdev)
 	if (dev->of_node) {
 		const struct of_device_id *id =
 			of_match_device(of_match_ptr(pxa_ssp_of_ids), dev);
-		ssp->type = (int) id->data;
+		ssp->type = (uintptr_t) id->data;
 	} else {
 		const struct platform_device_id *id =
 			platform_get_device_id(pdev);
-		ssp->type = (int) id->driver_data;
+		ssp->type = id->driver_data;
 
 		/* PXA2xx/3xx SSP ports starts from 1 and the internal pdev->id
 		 * starts from 0, do a translation here
diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig
index b3634e10f6f5..aa5956246f60 100644
--- a/drivers/soc/qcom/Kconfig
+++ b/drivers/soc/qcom/Kconfig
@@ -77,6 +77,18 @@ config QCOM_PDR_HELPERS
 	select QCOM_QMI_HELPERS
 	depends on NET
 
+config QCOM_PMIC_PDCHARGER_ULOG
+	tristate "Qualcomm PMIC PDCharger ULOG driver"
+	depends on RPMSG
+	depends on EVENT_TRACING
+	help
+	  The Qualcomm PMIC PDCharger ULOG driver provides access to logs of
+	  the ADSP firmware PDCharger module in charge of Battery and Power
+	  Delivery on modern systems.
+
+	  Say yes here to support PDCharger ULOG event tracing on modern
+	  Qualcomm platforms.
+
 config QCOM_PMIC_GLINK
 	tristate "Qualcomm PMIC GLINK driver"
 	depends on RPMSG
@@ -209,6 +221,7 @@ config QCOM_STATS
 	tristate "Qualcomm Technologies, Inc. (QTI) Sleep stats driver"
 	depends on (ARCH_QCOM && DEBUG_FS) || COMPILE_TEST
 	depends on QCOM_SMEM
+	depends on QCOM_AOSS_QMP || QCOM_AOSS_QMP=n
 	help
 	  Qualcomm Technologies, Inc. (QTI) Sleep stats driver to read
 	  the shared memory exported by the remote processor related to
diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile
index bbca2e1e55bb..05b3d54e8dc9 100644
--- a/drivers/soc/qcom/Makefile
+++ b/drivers/soc/qcom/Makefile
@@ -9,6 +9,8 @@ obj-$(CONFIG_QCOM_OCMEM)	+= ocmem.o
 obj-$(CONFIG_QCOM_PDR_HELPERS)	+= pdr_interface.o
 obj-$(CONFIG_QCOM_PMIC_GLINK)	+= pmic_glink.o
 obj-$(CONFIG_QCOM_PMIC_GLINK)	+= pmic_glink_altmode.o
+obj-$(CONFIG_QCOM_PMIC_PDCHARGER_ULOG)	+= pmic_pdcharger_ulog.o
+CFLAGS_pmic_pdcharger_ulog.o	:=  -I$(src)
 obj-$(CONFIG_QCOM_QMI_HELPERS)	+= qmi_helpers.o
 qmi_helpers-y	+= qmi_encdec.o qmi_interface.o
 obj-$(CONFIG_QCOM_RAMP_CTRL)	+= ramp_controller.o
diff --git a/drivers/soc/qcom/llcc-qcom.c b/drivers/soc/qcom/llcc-qcom.c
index 674abd0d6700..4ca88eaebf06 100644
--- a/drivers/soc/qcom/llcc-qcom.c
+++ b/drivers/soc/qcom/llcc-qcom.c
@@ -47,7 +47,7 @@
 #define LLCC_TRP_STATUSn(n)           (4 + n * SZ_4K)
 #define LLCC_TRP_ATTR0_CFGn(n)        (0x21000 + SZ_8 * n)
 #define LLCC_TRP_ATTR1_CFGn(n)        (0x21004 + SZ_8 * n)
-#define LLCC_TRP_ATTR2_CFGn(n)        (0x21100 + SZ_8 * n)
+#define LLCC_TRP_ATTR2_CFGn(n)        (0x21100 + SZ_4 * n)
 
 #define LLCC_TRP_SCID_DIS_CAP_ALLOC   0x21f00
 #define LLCC_TRP_PCB_ACT              0x21f04
@@ -92,6 +92,19 @@
  * @write_scid_en: Bit enables write cache support for a given scid.
  * @write_scid_cacheable_en: Enables write cache cacheable support for a
  *			     given scid (not supported on v2 or older hardware).
+ * @stale_en: Bit enables stale.
+ * @stale_cap_en: Bit enables stale only if current scid is over-cap.
+ * @mru_uncap_en: Roll-over on reserved cache ways if current scid is
+ *                under-cap.
+ * @mru_rollover: Roll-over on reserved cache ways.
+ * @alloc_oneway_en: Allways allocate one way on over-cap even if there's no
+ *                   same-scid lines for replacement.
+ * @ovcap_en: Once current scid is over-capacity, allocate other over-cap SCID.
+ * @ovcap_prio: Once current scid is over-capacity, allocate other low priority
+ *              over-cap scid. Depends on corresponding bit being set in
+ *              ovcap_en.
+ * @vict_prio: When current scid is under-capacity, allocate over other
+ *             lower-than victim priority-line threshold scid.
  */
 struct llcc_slice_config {
 	u32 usecase_id;
@@ -362,6 +375,33 @@ static const struct llcc_slice_config sm8550_data[] =  {
 	{LLCC_VIDVSP,   28,  256, 4, 1, 0xFFFFFF, 0x0,   0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, },
 };
 
+static const struct llcc_slice_config sm8650_data[] = {
+	{LLCC_CPUSS,     1, 5120, 1, 0, 0xFFFFFF, 0x0,      0, 0x0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_VIDSC0,    2,  512, 3, 1, 0xFFFFFF, 0x0,      0, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_AUDIO,     6,  512, 1, 1, 0xFFFFFF, 0x0,      0, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_MDMHPGRW, 25, 1024, 3, 0, 0xFFFFFF, 0x0,      0, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_MODHW,    26, 1024, 1, 1, 0xFFFFFF, 0x0,      0, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_CMPT,     10, 4096, 1, 1, 0xFFFFFF, 0x0,      0, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_GPUHTW,   11,  512, 1, 1, 0xFFFFFF, 0x0,      0, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_GPU,       9, 3096, 1, 0, 0xFFFFFF, 0x0,      0, 0x0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_MMUHWT,   18,  768, 1, 1, 0xFFFFFF, 0x0,      0, 0x0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_DISP,     16, 6144, 1, 1, 0xFFFFFF, 0x0,      2, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_MDMHPFX,  24, 1024, 3, 1, 0xFFFFFF, 0x0,      0, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_MDMPNG,   27, 1024, 0, 1, 0x000000, 0x0,      0, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_AUDHW,    22, 1024, 1, 1, 0xFFFFFF, 0x0,      0, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_CVP,       8,  256, 3, 1, 0xFFFFFF, 0x0,      0, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_MODPE,    29,  128, 1, 1, 0xF00000, 0x0,      0, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0},
+	{LLCC_WRCACHE,  31,  512, 1, 1, 0xFFFFFF, 0x0,      0, 0x0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_CAMEXP0,   4,  256, 3, 1,      0xF, 0x0,      0, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_CAMEXP1,   7, 3200, 3, 1, 0xFFFFF0, 0x0,      2, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_CMPTHCP,  17,  256, 3, 1, 0xFFFFFF, 0x0,      0, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_LCPDARE,  30,  128, 3, 1, 0xFFFFFF, 0x0,      0, 0x0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0},
+	{LLCC_AENPU,     3, 3072, 1, 1, 0xFFFFFF, 0x0,      2, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_ISLAND1,  12, 5888, 7, 1,      0x0, 0x7FFFFF, 0, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_DISP_WB,  23, 1024, 3, 1, 0xFFFFFF, 0x0,      0, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_VIDVSP,   28,  256, 3, 1, 0xFFFFFF, 0x0,      0, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+};
+
 static const struct llcc_slice_config qdu1000_data_2ch[] = {
 	{ LLCC_MDMHPGRW, 7, 512, 1, 1, 0xfff, 0x0, 0, 0, 0, 1, 0, 0, 0 },
 	{ LLCC_MODHW,    9, 256, 1, 1, 0xfff, 0x0, 0, 0, 0, 1, 0, 0, 0 },
@@ -392,6 +432,29 @@ static const struct llcc_slice_config qdu1000_data_8ch[] = {
 	{ LLCC_WRCACHE, 31, 512,  1, 1, 0x3,   0x0, 0, 0, 0, 0, 1, 0, 0 },
 };
 
+static const struct llcc_slice_config x1e80100_data[] = {
+	{LLCC_CPUSS,	 1, 6144, 1, 1, 0xFFF, 0x0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_VIDSC0,	 2,  512, 3, 1, 0xFFF, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_AUDIO,	 6, 3072, 1, 1, 0xFFF, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_CMPT,     10, 6144, 1, 1, 0xFFF, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_GPUHTW,   11, 1024, 1, 1, 0xFFF, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_GPU,       9, 4096, 1, 1, 0xFFF, 0x0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_MMUHWT,   18,  512, 1, 1, 0xFFF, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_AUDHW,    22, 1024, 1, 1, 0xFFF, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_CVP,       8,  512, 3, 1, 0xFFF, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_WRCACHE,  31,  512, 1, 1, 0xFFF, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_CAMEXP1,   7, 3072, 2, 1, 0xFFF, 0x0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_LCPDARE,  30,  512, 3, 1, 0xFFF, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_AENPU,     3, 3072, 1, 1, 0xFFF, 0x0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_ISLAND1,  12,  512, 7, 1,   0x1, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_ISLAND2,  13,  512, 7, 1,   0x2, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_ISLAND3,  14,  512, 7, 1,   0x3, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_ISLAND4,  15,  512, 7, 1,   0x4, 0x0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_CAMEXP2,  19, 3072, 3, 1, 0xFFF, 0x0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_CAMEXP3,  20, 3072, 3, 1, 0xFFF, 0x0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+	{LLCC_CAMEXP4,  21, 3072, 3, 1, 0xFFF, 0x0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+};
+
 static const struct llcc_edac_reg_offset llcc_v1_edac_reg_offset = {
 	.trp_ecc_error_status0 = 0x20344,
 	.trp_ecc_error_status1 = 0x20348,
@@ -610,6 +673,26 @@ static const struct qcom_llcc_config sm8550_cfg[] = {
 	},
 };
 
+static const struct qcom_llcc_config sm8650_cfg[] = {
+	{
+		.sct_data       = sm8650_data,
+		.size           = ARRAY_SIZE(sm8650_data),
+		.need_llcc_cfg	= true,
+		.reg_offset	= llcc_v2_1_reg_offset,
+		.edac_reg_offset = &llcc_v2_1_edac_reg_offset,
+	},
+};
+
+static const struct qcom_llcc_config x1e80100_cfg[] = {
+	{
+		.sct_data	= x1e80100_data,
+		.size		= ARRAY_SIZE(x1e80100_data),
+		.need_llcc_cfg	= true,
+		.reg_offset	= llcc_v2_1_reg_offset,
+		.edac_reg_offset = &llcc_v2_1_edac_reg_offset,
+	},
+};
+
 static const struct qcom_sct_config qdu1000_cfgs = {
 	.llcc_config	= qdu1000_cfg,
 	.num_config	= ARRAY_SIZE(qdu1000_cfg),
@@ -675,6 +758,16 @@ static const struct qcom_sct_config sm8550_cfgs = {
 	.num_config	= ARRAY_SIZE(sm8550_cfg),
 };
 
+static const struct qcom_sct_config sm8650_cfgs = {
+	.llcc_config	= sm8650_cfg,
+	.num_config	= ARRAY_SIZE(sm8650_cfg),
+};
+
+static const struct qcom_sct_config x1e80100_cfgs = {
+	.llcc_config	= x1e80100_cfg,
+	.num_config	= ARRAY_SIZE(x1e80100_cfg),
+};
+
 static struct llcc_drv_data *drv_data = (void *) -EPROBE_DEFER;
 
 /**
@@ -715,7 +808,7 @@ struct llcc_slice_desc *llcc_slice_getd(u32 uid)
 EXPORT_SYMBOL_GPL(llcc_slice_getd);
 
 /**
- * llcc_slice_putd - llcc slice descritpor
+ * llcc_slice_putd - llcc slice descriptor
  * @desc: Pointer to llcc slice descriptor
  */
 void llcc_slice_putd(struct llcc_slice_desc *desc)
@@ -941,15 +1034,15 @@ static int _qcom_llcc_cfg_program(const struct llcc_slice_config *config,
 		u32 disable_cap_alloc, retain_pc;
 
 		disable_cap_alloc = config->dis_cap_alloc << config->slice_id;
-		ret = regmap_write(drv_data->bcast_regmap,
-				LLCC_TRP_SCID_DIS_CAP_ALLOC, disable_cap_alloc);
+		ret = regmap_update_bits(drv_data->bcast_regmap, LLCC_TRP_SCID_DIS_CAP_ALLOC,
+					 BIT(config->slice_id), disable_cap_alloc);
 		if (ret)
 			return ret;
 
 		if (drv_data->version < LLCC_VERSION_4_1_0_0) {
 			retain_pc = config->retain_on_pc << config->slice_id;
-			ret = regmap_write(drv_data->bcast_regmap,
-					LLCC_TRP_PCB_ACT, retain_pc);
+			ret = regmap_update_bits(drv_data->bcast_regmap, LLCC_TRP_PCB_ACT,
+						 BIT(config->slice_id), retain_pc);
 			if (ret)
 				return ret;
 		}
@@ -1249,6 +1342,8 @@ static const struct of_device_id qcom_llcc_of_match[] = {
 	{ .compatible = "qcom,sm8350-llcc", .data = &sm8350_cfgs },
 	{ .compatible = "qcom,sm8450-llcc", .data = &sm8450_cfgs },
 	{ .compatible = "qcom,sm8550-llcc", .data = &sm8550_cfgs },
+	{ .compatible = "qcom,sm8650-llcc", .data = &sm8650_cfgs },
+	{ .compatible = "qcom,x1e80100-llcc", .data = &x1e80100_cfgs },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, qcom_llcc_of_match);
diff --git a/drivers/soc/qcom/pmic_glink.c b/drivers/soc/qcom/pmic_glink.c
index 914057331afd..f4bfd24386f1 100644
--- a/drivers/soc/qcom/pmic_glink.c
+++ b/drivers/soc/qcom/pmic_glink.c
@@ -18,9 +18,6 @@ enum {
 	PMIC_GLINK_CLIENT_UCSI,
 };
 
-#define PMIC_GLINK_CLIENT_DEFAULT	(BIT(PMIC_GLINK_CLIENT_BATT) |	\
-					 BIT(PMIC_GLINK_CLIENT_ALTMODE))
-
 struct pmic_glink {
 	struct device *dev;
 	struct pdr_handle *pdr;
@@ -263,10 +260,10 @@ static int pmic_glink_probe(struct platform_device *pdev)
 	mutex_init(&pg->state_lock);
 
 	match_data = (unsigned long *)of_device_get_match_data(&pdev->dev);
-	if (match_data)
-		pg->client_mask = *match_data;
-	else
-		pg->client_mask = PMIC_GLINK_CLIENT_DEFAULT;
+	if (!match_data)
+		return -EINVAL;
+
+	pg->client_mask = *match_data;
 
 	if (pg->client_mask & BIT(PMIC_GLINK_CLIENT_UCSI)) {
 		ret = pmic_glink_add_aux_device(pg, &pg->ucsi_aux, "ucsi");
@@ -336,14 +333,17 @@ static void pmic_glink_remove(struct platform_device *pdev)
 	mutex_unlock(&__pmic_glink_lock);
 }
 
+static const unsigned long pmic_glink_sc8180x_client_mask = BIT(PMIC_GLINK_CLIENT_BATT) |
+							    BIT(PMIC_GLINK_CLIENT_ALTMODE);
+
 static const unsigned long pmic_glink_sm8450_client_mask = BIT(PMIC_GLINK_CLIENT_BATT) |
 							   BIT(PMIC_GLINK_CLIENT_ALTMODE) |
 							   BIT(PMIC_GLINK_CLIENT_UCSI);
 
 static const struct of_device_id pmic_glink_of_match[] = {
-	{ .compatible = "qcom,sm8450-pmic-glink", .data = &pmic_glink_sm8450_client_mask },
-	{ .compatible = "qcom,sm8550-pmic-glink", .data = &pmic_glink_sm8450_client_mask },
-	{ .compatible = "qcom,pmic-glink" },
+	{ .compatible = "qcom,sc8180x-pmic-glink", .data = &pmic_glink_sc8180x_client_mask },
+	{ .compatible = "qcom,sc8280xp-pmic-glink", .data = &pmic_glink_sc8180x_client_mask },
+	{ .compatible = "qcom,pmic-glink", .data = &pmic_glink_sm8450_client_mask },
 	{}
 };
 MODULE_DEVICE_TABLE(of, pmic_glink_of_match);
@@ -363,14 +363,14 @@ static int pmic_glink_init(void)
 	register_rpmsg_driver(&pmic_glink_rpmsg_driver);
 
 	return 0;
-};
+}
 module_init(pmic_glink_init);
 
 static void pmic_glink_exit(void)
 {
 	unregister_rpmsg_driver(&pmic_glink_rpmsg_driver);
 	platform_driver_unregister(&pmic_glink_driver);
-};
+}
 module_exit(pmic_glink_exit);
 
 MODULE_DESCRIPTION("Qualcomm PMIC GLINK driver");
diff --git a/drivers/soc/qcom/pmic_glink_altmode.c b/drivers/soc/qcom/pmic_glink_altmode.c
index b78279e2f54c..ad922f0dca6b 100644
--- a/drivers/soc/qcom/pmic_glink_altmode.c
+++ b/drivers/soc/qcom/pmic_glink_altmode.c
@@ -236,7 +236,7 @@ static void pmic_glink_altmode_worker(struct work_struct *work)
 		drm_bridge_hpd_notify(&alt_port->bridge, connector_status_disconnected);
 
 	pmic_glink_altmode_request(altmode, ALTMODE_PAN_ACK, alt_port->index);
-};
+}
 
 static enum typec_orientation pmic_glink_altmode_orientation(unsigned int orientation)
 {
@@ -285,7 +285,7 @@ static void pmic_glink_altmode_sc8180xp_notify(struct pmic_glink_altmode *altmod
 
 	svid = mux == 2 ? USB_TYPEC_DP_SID : 0;
 
-	if (!altmode->ports[port].altmode) {
+	if (port >= ARRAY_SIZE(altmode->ports) || !altmode->ports[port].altmode) {
 		dev_dbg(altmode->dev, "notification on undefined port %d\n", port);
 		return;
 	}
@@ -328,7 +328,7 @@ static void pmic_glink_altmode_sc8280xp_notify(struct pmic_glink_altmode *altmod
 	hpd_state = FIELD_GET(SC8280XP_HPD_STATE_MASK, notify->payload[8]);
 	hpd_irq = FIELD_GET(SC8280XP_HPD_IRQ_MASK, notify->payload[8]);
 
-	if (!altmode->ports[port].altmode) {
+	if (port >= ARRAY_SIZE(altmode->ports) || !altmode->ports[port].altmode) {
 		dev_dbg(altmode->dev, "notification on undefined port %d\n", port);
 		return;
 	}
diff --git a/drivers/soc/qcom/pmic_pdcharger_ulog.c b/drivers/soc/qcom/pmic_pdcharger_ulog.c
new file mode 100644
index 000000000000..238cd38589dc
--- /dev/null
+++ b/drivers/soc/qcom/pmic_pdcharger_ulog.c
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2019-2022, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2023, Linaro Ltd
+ */
+#include <linux/of_device.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/rpmsg.h>
+#include <linux/slab.h>
+#include <linux/soc/qcom/pdr.h>
+#include <linux/debugfs.h>
+
+#define CREATE_TRACE_POINTS
+#include "pmic_pdcharger_ulog.h"
+
+#define MSG_OWNER_CHG_ULOG		32778
+#define MSG_TYPE_REQ_RESP		1
+
+#define GET_CHG_ULOG_REQ		0x18
+#define SET_CHG_ULOG_PROP_REQ		0x19
+
+#define LOG_DEFAULT_TIME_MS		1000
+
+#define MAX_ULOG_SIZE			8192
+
+struct pmic_pdcharger_ulog_hdr {
+	__le32 owner;
+	__le32 type;
+	__le32 opcode;
+};
+
+struct pmic_pdcharger_ulog {
+	struct rpmsg_device *rpdev;
+	struct delayed_work ulog_work;
+};
+
+struct get_ulog_req_msg {
+	struct pmic_pdcharger_ulog_hdr	hdr;
+	u32				log_size;
+};
+
+struct get_ulog_resp_msg {
+	struct pmic_pdcharger_ulog_hdr	hdr;
+	u8				buf[MAX_ULOG_SIZE];
+};
+
+static int pmic_pdcharger_ulog_write_async(struct pmic_pdcharger_ulog *pg, void *data, size_t len)
+{
+	return rpmsg_send(pg->rpdev->ept, data, len);
+}
+
+static int pmic_pdcharger_ulog_request(struct pmic_pdcharger_ulog *pg)
+{
+	struct get_ulog_req_msg req_msg = {
+		.hdr = {
+			.owner = cpu_to_le32(MSG_OWNER_CHG_ULOG),
+			.type = cpu_to_le32(MSG_TYPE_REQ_RESP),
+			.opcode = cpu_to_le32(GET_CHG_ULOG_REQ)
+		},
+		.log_size = MAX_ULOG_SIZE
+	};
+
+	return pmic_pdcharger_ulog_write_async(pg, &req_msg, sizeof(req_msg));
+}
+
+static void pmic_pdcharger_ulog_work(struct work_struct *work)
+{
+	struct pmic_pdcharger_ulog *pg = container_of(work, struct pmic_pdcharger_ulog,
+						      ulog_work.work);
+	int rc;
+
+	rc = pmic_pdcharger_ulog_request(pg);
+	if (rc) {
+		dev_err(&pg->rpdev->dev, "Error requesting ulog, rc=%d\n", rc);
+		return;
+	}
+}
+
+static void pmic_pdcharger_ulog_handle_message(struct pmic_pdcharger_ulog *pg,
+					       struct get_ulog_resp_msg *resp_msg,
+					       size_t len)
+{
+	char *token, *buf = resp_msg->buf;
+
+	if (len != sizeof(*resp_msg)) {
+		dev_err(&pg->rpdev->dev, "Expected data length: %zu, received: %zu\n",
+			sizeof(*resp_msg), len);
+		return;
+	}
+
+	buf[MAX_ULOG_SIZE - 1] = '\0';
+
+	do {
+		token = strsep((char **)&buf, "\n");
+		if (token && strlen(token))
+			trace_pmic_pdcharger_ulog_msg(token);
+	} while (token);
+}
+
+static int pmic_pdcharger_ulog_rpmsg_callback(struct rpmsg_device *rpdev, void *data,
+					      int len, void *priv, u32 addr)
+{
+	struct pmic_pdcharger_ulog *pg = dev_get_drvdata(&rpdev->dev);
+	struct pmic_pdcharger_ulog_hdr *hdr = data;
+	u32 opcode;
+
+	opcode = le32_to_cpu(hdr->opcode);
+
+	switch (opcode) {
+	case GET_CHG_ULOG_REQ:
+		schedule_delayed_work(&pg->ulog_work, msecs_to_jiffies(LOG_DEFAULT_TIME_MS));
+		pmic_pdcharger_ulog_handle_message(pg, data, len);
+		break;
+	default:
+		dev_err(&pg->rpdev->dev, "Unknown opcode %u\n", opcode);
+		break;
+	}
+
+	return 0;
+}
+
+static int pmic_pdcharger_ulog_rpmsg_probe(struct rpmsg_device *rpdev)
+{
+	struct pmic_pdcharger_ulog *pg;
+	struct device *dev = &rpdev->dev;
+
+	pg = devm_kzalloc(dev, sizeof(*pg), GFP_KERNEL);
+	if (!pg)
+		return -ENOMEM;
+
+	pg->rpdev = rpdev;
+	INIT_DELAYED_WORK(&pg->ulog_work, pmic_pdcharger_ulog_work);
+
+	dev_set_drvdata(dev, pg);
+
+	pmic_pdcharger_ulog_request(pg);
+
+	return 0;
+}
+
+static void pmic_pdcharger_ulog_rpmsg_remove(struct rpmsg_device *rpdev)
+{
+	struct pmic_pdcharger_ulog *pg = dev_get_drvdata(&rpdev->dev);
+
+	cancel_delayed_work_sync(&pg->ulog_work);
+}
+
+static const struct rpmsg_device_id pmic_pdcharger_ulog_rpmsg_id_match[] = {
+	{ "PMIC_LOGS_ADSP_APPS" },
+	{}
+};
+
+static struct rpmsg_driver pmic_pdcharger_ulog_rpmsg_driver = {
+	.probe = pmic_pdcharger_ulog_rpmsg_probe,
+	.remove = pmic_pdcharger_ulog_rpmsg_remove,
+	.callback = pmic_pdcharger_ulog_rpmsg_callback,
+	.id_table = pmic_pdcharger_ulog_rpmsg_id_match,
+	.drv  = {
+		.name  = "qcom_pmic_pdcharger_ulog_rpmsg",
+	},
+};
+
+module_rpmsg_driver(pmic_pdcharger_ulog_rpmsg_driver);
+MODULE_DESCRIPTION("Qualcomm PMIC ChargerPD ULOG driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/soc/qcom/pmic_pdcharger_ulog.h b/drivers/soc/qcom/pmic_pdcharger_ulog.h
new file mode 100644
index 000000000000..152e3a6b5480
--- /dev/null
+++ b/drivers/soc/qcom/pmic_pdcharger_ulog.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2023, Linaro Ltd
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM pmic_pdcharger_ulog
+
+#if !defined(_TRACE_PMIC_PDCHARGER_ULOG_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_PMIC_PDCHARGER_ULOG_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(pmic_pdcharger_ulog_msg,
+	TP_PROTO(char *msg),
+	TP_ARGS(msg),
+	TP_STRUCT__entry(
+		__string(msg, msg)
+	),
+	TP_fast_assign(
+		__assign_str(msg, msg);
+	),
+	TP_printk("%s", __get_str(msg))
+);
+
+#endif /* _TRACE_PMIC_PDCHARGER_ULOG_H */
+
+/* This part must be outside protection */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE pmic_pdcharger_ulog
+
+#include <trace/define_trace.h>
diff --git a/drivers/soc/qcom/socinfo.c b/drivers/soc/qcom/socinfo.c
index 51e05bec5bfc..6349a0debeb5 100644
--- a/drivers/soc/qcom/socinfo.c
+++ b/drivers/soc/qcom/socinfo.c
@@ -51,6 +51,11 @@
 #define SMEM_IMAGE_TABLE_ADSP_INDEX     12
 #define SMEM_IMAGE_TABLE_CNSS_INDEX     13
 #define SMEM_IMAGE_TABLE_VIDEO_INDEX    14
+#define SMEM_IMAGE_TABLE_DSPS_INDEX     15
+#define SMEM_IMAGE_TABLE_CDSP_INDEX     16
+#define SMEM_IMAGE_TABLE_CDSP1_INDEX    19
+#define SMEM_IMAGE_TABLE_GPDSP_INDEX    20
+#define SMEM_IMAGE_TABLE_GPDSP1_INDEX   21
 #define SMEM_IMAGE_VERSION_TABLE       469
 
 /*
@@ -65,6 +70,11 @@ static const char *const socinfo_image_names[] = {
 	[SMEM_IMAGE_TABLE_RPM_INDEX] = "rpm",
 	[SMEM_IMAGE_TABLE_TZ_INDEX] = "tz",
 	[SMEM_IMAGE_TABLE_VIDEO_INDEX] = "video",
+	[SMEM_IMAGE_TABLE_DSPS_INDEX] = "dsps",
+	[SMEM_IMAGE_TABLE_CDSP_INDEX] = "cdsp",
+	[SMEM_IMAGE_TABLE_CDSP1_INDEX] = "cdsp1",
+	[SMEM_IMAGE_TABLE_GPDSP_INDEX] = "gpdsp",
+	[SMEM_IMAGE_TABLE_GPDSP1_INDEX] = "gpdsp1",
 };
 
 static const char *const pmic_models[] = {
@@ -93,7 +103,7 @@ static const char *const pmic_models[] = {
 	[22] = "PM8821",
 	[23] = "PM8038",
 	[24] = "PM8005/PM8922",
-	[25] = "PM8917",
+	[25] = "PM8917/PM8937",
 	[26] = "PM660L",
 	[27] = "PM660",
 	[30] = "PM8150",
@@ -417,6 +427,7 @@ static const struct soc_id soc_id[] = {
 	{ qcom_board_id(SA8775P) },
 	{ qcom_board_id(QRU1000) },
 	{ qcom_board_id(QDU1000) },
+	{ qcom_board_id(SM8650) },
 	{ qcom_board_id(SM4450) },
 	{ qcom_board_id(QDU1010) },
 	{ qcom_board_id(QRU1032) },
diff --git a/drivers/soc/renesas/Kconfig b/drivers/soc/renesas/Kconfig
index 0071864c2111..0986672f6375 100644
--- a/drivers/soc/renesas/Kconfig
+++ b/drivers/soc/renesas/Kconfig
@@ -340,6 +340,7 @@ if RISCV
 config ARCH_R9A07G043
 	bool "RISC-V Platform support for RZ/Five"
 	depends on NONPORTABLE
+	depends on !DMA_DIRECT_REMAP
 	depends on RISCV_ALTERNATIVE
 	depends on !RISCV_ISA_ZICBOM
 	depends on RISCV_SBI
diff --git a/drivers/soc/renesas/renesas-soc.c b/drivers/soc/renesas/renesas-soc.c
index c732d4a5b26a..27eae1a354ab 100644
--- a/drivers/soc/renesas/renesas-soc.c
+++ b/drivers/soc/renesas/renesas-soc.c
@@ -486,10 +486,6 @@ static int __init renesas_soc_init(void)
 		return -ENOMEM;
 	}
 
-	np = of_find_node_by_path("/");
-	of_property_read_string(np, "model", &soc_dev_attr->machine);
-	of_node_put(np);
-
 	soc_dev_attr->family = kstrdup_const(family->name, GFP_KERNEL);
 	soc_dev_attr->soc_id = kstrdup_const(soc_id, GFP_KERNEL);
 
diff --git a/drivers/soc/samsung/exynos-chipid.c b/drivers/soc/samsung/exynos-chipid.c
index 3fd0f2b84dd3..b1118d37779e 100644
--- a/drivers/soc/samsung/exynos-chipid.c
+++ b/drivers/soc/samsung/exynos-chipid.c
@@ -59,6 +59,7 @@ static const struct exynos_soc_id {
 	{ "EXYNOS7885", 0xE7885000 },
 	{ "EXYNOS850", 0xE3830000 },
 	{ "EXYNOSAUTOV9", 0xAAA80000 },
+	{ "EXYNOSAUTOV920", 0x0A920000 },
 };
 
 static const char *product_id_to_soc_id(unsigned int product_id)
diff --git a/drivers/soc/sifive/Kconfig b/drivers/soc/sifive/Kconfig
deleted file mode 100644
index 139884addc41..000000000000
--- a/drivers/soc/sifive/Kconfig
+++ /dev/null
@@ -1,10 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-
-if ARCH_SIFIVE || ARCH_STARFIVE
-
-config SIFIVE_CCACHE
-	bool "Sifive Composable Cache controller"
-	help
-	  Support for the composable cache controller on SiFive platforms.
-
-endif
diff --git a/drivers/soc/sifive/Makefile b/drivers/soc/sifive/Makefile
deleted file mode 100644
index 1f5dc339bf82..000000000000
--- a/drivers/soc/sifive/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-
-obj-$(CONFIG_SIFIVE_CCACHE)	+= sifive_ccache.o
diff --git a/drivers/soc/ti/k3-socinfo.c b/drivers/soc/ti/k3-socinfo.c
index 7fc3548e084c..59101bf7cf23 100644
--- a/drivers/soc/ti/k3-socinfo.c
+++ b/drivers/soc/ti/k3-socinfo.c
@@ -33,19 +33,35 @@
 
 #define CTRLMMR_WKUP_JTAGID_MFG_TI		0x17
 
+#define JTAG_ID_PARTNO_AM65X		0xBB5A
+#define JTAG_ID_PARTNO_J721E		0xBB64
+#define JTAG_ID_PARTNO_J7200		0xBB6D
+#define JTAG_ID_PARTNO_AM64X		0xBB38
+#define JTAG_ID_PARTNO_J721S2		0xBB75
+#define JTAG_ID_PARTNO_AM62X		0xBB7E
+#define JTAG_ID_PARTNO_J784S4		0xBB80
+#define JTAG_ID_PARTNO_AM62AX		0xBB8D
+#define JTAG_ID_PARTNO_AM62PX		0xBB9D
+#define JTAG_ID_PARTNO_J722S		0xBBA0
+
 static const struct k3_soc_id {
 	unsigned int id;
 	const char *family_name;
 } k3_soc_ids[] = {
-	{ 0xBB5A, "AM65X" },
-	{ 0xBB64, "J721E" },
-	{ 0xBB6D, "J7200" },
-	{ 0xBB38, "AM64X" },
-	{ 0xBB75, "J721S2"},
-	{ 0xBB7E, "AM62X" },
-	{ 0xBB80, "J784S4" },
-	{ 0xBB8D, "AM62AX" },
-	{ 0xBB9D, "AM62PX" },
+	{ JTAG_ID_PARTNO_AM65X, "AM65X" },
+	{ JTAG_ID_PARTNO_J721E, "J721E" },
+	{ JTAG_ID_PARTNO_J7200, "J7200" },
+	{ JTAG_ID_PARTNO_AM64X, "AM64X" },
+	{ JTAG_ID_PARTNO_J721S2, "J721S2"},
+	{ JTAG_ID_PARTNO_AM62X, "AM62X" },
+	{ JTAG_ID_PARTNO_J784S4, "J784S4" },
+	{ JTAG_ID_PARTNO_AM62AX, "AM62AX" },
+	{ JTAG_ID_PARTNO_AM62PX, "AM62PX" },
+	{ JTAG_ID_PARTNO_J722S, "J722S" },
+};
+
+static const char * const j721e_rev_string_map[] = {
+	"1.0", "1.1",
 };
 
 static int
@@ -63,6 +79,32 @@ k3_chipinfo_partno_to_names(unsigned int partno,
 	return -ENODEV;
 }
 
+static int
+k3_chipinfo_variant_to_sr(unsigned int partno, unsigned int variant,
+			  struct soc_device_attribute *soc_dev_attr)
+{
+	switch (partno) {
+	case JTAG_ID_PARTNO_J721E:
+		if (variant >= ARRAY_SIZE(j721e_rev_string_map))
+			goto err_unknown_variant;
+		soc_dev_attr->revision = kasprintf(GFP_KERNEL, "SR%s",
+						   j721e_rev_string_map[variant]);
+		break;
+	default:
+		variant++;
+		soc_dev_attr->revision = kasprintf(GFP_KERNEL, "SR%x.0",
+						   variant);
+	}
+
+	if (!soc_dev_attr->revision)
+		return -ENOMEM;
+
+	return 0;
+
+err_unknown_variant:
+	return -ENODEV;
+}
+
 static int k3_chipinfo_probe(struct platform_device *pdev)
 {
 	struct device_node *node = pdev->dev.of_node;
@@ -94,7 +136,6 @@ static int k3_chipinfo_probe(struct platform_device *pdev)
 
 	variant = (jtag_id & CTRLMMR_WKUP_JTAGID_VARIANT_MASK) >>
 		  CTRLMMR_WKUP_JTAGID_VARIANT_SHIFT;
-	variant++;
 
 	partno_id = (jtag_id & CTRLMMR_WKUP_JTAGID_PARTNO_MASK) >>
 		 CTRLMMR_WKUP_JTAGID_PARTNO_SHIFT;
@@ -103,16 +144,16 @@ static int k3_chipinfo_probe(struct platform_device *pdev)
 	if (!soc_dev_attr)
 		return -ENOMEM;
 
-	soc_dev_attr->revision = kasprintf(GFP_KERNEL, "SR%x.0", variant);
-	if (!soc_dev_attr->revision) {
-		ret = -ENOMEM;
+	ret = k3_chipinfo_partno_to_names(partno_id, soc_dev_attr);
+	if (ret) {
+		dev_err(dev, "Unknown SoC JTAGID[0x%08X]: %d\n", jtag_id, ret);
 		goto err;
 	}
 
-	ret = k3_chipinfo_partno_to_names(partno_id, soc_dev_attr);
+	ret = k3_chipinfo_variant_to_sr(partno_id, variant, soc_dev_attr);
 	if (ret) {
-		dev_err(dev, "Unknown SoC JTAGID[0x%08X]: %d\n", jtag_id, ret);
-		goto err_free_rev;
+		dev_err(dev, "Unknown SoC SR[0x%08X]: %d\n", jtag_id, ret);
+		goto err;
 	}
 
 	node = of_find_node_by_path("/");
diff --git a/drivers/soc/xilinx/xlnx_event_manager.c b/drivers/soc/xilinx/xlnx_event_manager.c
index 86a048a10a13..042553abe1bf 100644
--- a/drivers/soc/xilinx/xlnx_event_manager.c
+++ b/drivers/soc/xilinx/xlnx_event_manager.c
@@ -477,7 +477,7 @@ static void xlnx_call_notify_cb_handler(const u32 *payload)
 		}
 	}
 	if (!is_callback_found)
-		pr_warn("Didn't find any registered callback for 0x%x 0x%x\n",
+		pr_warn("Unhandled SGI node 0x%x event 0x%x. Expected with Xen hypervisor\n",
 			payload[1], payload[2]);
 }
 
@@ -555,7 +555,7 @@ static void xlnx_disable_percpu_irq(void *data)
 static int xlnx_event_init_sgi(struct platform_device *pdev)
 {
 	int ret = 0;
-	int cpu = smp_processor_id();
+	int cpu;
 	/*
 	 * IRQ related structures are used for the following:
 	 * for each SGI interrupt ensure its mapped by GIC IRQ domain
@@ -592,9 +592,12 @@ static int xlnx_event_init_sgi(struct platform_device *pdev)
 	sgi_fwspec.param[0] = sgi_num;
 	virq_sgi = irq_create_fwspec_mapping(&sgi_fwspec);
 
+	cpu = get_cpu();
 	per_cpu(cpu_number1, cpu) = cpu;
 	ret = request_percpu_irq(virq_sgi, xlnx_event_handler, "xlnx_event_mgmt",
 				 &cpu_number1);
+	put_cpu();
+
 	WARN_ON(ret);
 	if (ret) {
 		irq_dispose_mapping(virq_sgi);
diff --git a/drivers/soc/xilinx/zynqmp_power.c b/drivers/soc/xilinx/zynqmp_power.c
index c2c819701eec..07d735b38b49 100644
--- a/drivers/soc/xilinx/zynqmp_power.c
+++ b/drivers/soc/xilinx/zynqmp_power.c
@@ -83,9 +83,11 @@ static irqreturn_t zynqmp_pm_isr(int irq, void *data)
 			pm_suspend(PM_SUSPEND_MEM);
 			break;
 		default:
-			pr_err("%s Unsupported InitSuspendCb reason "
-				"code %d\n", __func__, payload[1]);
+			pr_err("%s Unsupported InitSuspendCb reason code %d\n",
+			       __func__, payload[1]);
 		}
+	} else {
+		pr_err("%s() Unsupported Callback %d\n", __func__, payload[0]);
 	}
 
 	return IRQ_HANDLED;
@@ -252,8 +254,8 @@ static int zynqmp_pm_probe(struct platform_device *pdev)
 						dev_name(&pdev->dev),
 						&pdev->dev);
 		if (ret) {
-			dev_err(&pdev->dev, "devm_request_threaded_irq '%d' "
-					    "failed with %d\n", irq, ret);
+			dev_err(&pdev->dev, "devm_request_threaded_irq '%d' failed with %d\n",
+				irq, ret);
 			return ret;
 		}
 	} else {
@@ -275,7 +277,7 @@ static int zynqmp_pm_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int zynqmp_pm_remove(struct platform_device *pdev)
+static void zynqmp_pm_remove(struct platform_device *pdev)
 {
 	sysfs_remove_file(&pdev->dev.kobj, &dev_attr_suspend_mode.attr);
 	if (event_registered)
@@ -283,8 +285,6 @@ static int zynqmp_pm_remove(struct platform_device *pdev)
 
 	if (!rx_chan)
 		mbox_free_channel(rx_chan);
-
-	return 0;
 }
 
 static const struct of_device_id pm_of_match[] = {
@@ -295,7 +295,7 @@ MODULE_DEVICE_TABLE(of, pm_of_match);
 
 static struct platform_driver zynqmp_pm_platform_driver = {
 	.probe = zynqmp_pm_probe,
-	.remove = zynqmp_pm_remove,
+	.remove_new = zynqmp_pm_remove,
 	.driver = {
 		.name = "zynqmp_power",
 		.of_match_table = pm_of_match,
diff --git a/drivers/soundwire/intel_ace2x.c b/drivers/soundwire/intel_ace2x.c
index 82672fcbc2aa..8280baa3254b 100644
--- a/drivers/soundwire/intel_ace2x.c
+++ b/drivers/soundwire/intel_ace2x.c
@@ -23,8 +23,9 @@
 static void intel_shim_vs_init(struct sdw_intel *sdw)
 {
 	void __iomem *shim_vs = sdw->link_res->shim_vs;
-	u16 act = 0;
+	u16 act;
 
+	act = intel_readw(shim_vs, SDW_SHIM2_INTEL_VS_ACTMCTL);
 	u16p_replace_bits(&act, 0x1, SDW_SHIM2_INTEL_VS_ACTMCTL_DOAIS);
 	act |= SDW_SHIM2_INTEL_VS_ACTMCTL_DACTQE;
 	act |=  SDW_SHIM2_INTEL_VS_ACTMCTL_DODS;
diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
index 69719b335bcb..f048b3d55b2e 100644
--- a/drivers/soundwire/stream.c
+++ b/drivers/soundwire/stream.c
@@ -742,14 +742,15 @@ error_1:
  * sdw_ml_sync_bank_switch: Multilink register bank switch
  *
  * @bus: SDW bus instance
+ * @multi_link: whether this is a multi-link stream with hardware-based sync
  *
  * Caller function should free the buffers on error
  */
-static int sdw_ml_sync_bank_switch(struct sdw_bus *bus)
+static int sdw_ml_sync_bank_switch(struct sdw_bus *bus, bool multi_link)
 {
 	unsigned long time_left;
 
-	if (!bus->multi_link)
+	if (!multi_link)
 		return 0;
 
 	/* Wait for completion of transfer */
@@ -847,7 +848,7 @@ static int do_bank_switch(struct sdw_stream_runtime *stream)
 			bus->bank_switch_timeout = DEFAULT_BANK_SWITCH_TIMEOUT;
 
 		/* Check if bank switch was successful */
-		ret = sdw_ml_sync_bank_switch(bus);
+		ret = sdw_ml_sync_bank_switch(bus, multi_link);
 		if (ret < 0) {
 			dev_err(bus->dev,
 				"multi link bank switch failed: %d\n", ret);
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 70c9dd6b6a31..ddae0fde798e 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -1177,9 +1177,10 @@ config SPI_ZYNQ_QSPI
 
 config SPI_ZYNQMP_GQSPI
 	tristate "Xilinx ZynqMP GQSPI controller"
-	depends on (SPI_MASTER && HAS_DMA) || COMPILE_TEST
+	depends on (SPI_MEM && HAS_DMA) || COMPILE_TEST
 	help
 	  Enables Xilinx GQSPI controller driver for Zynq UltraScale+ MPSoC.
+	  This controller only supports SPI memory interface.
 
 config SPI_AMD
 	tristate "AMD SPI controller"
diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c
index 3d1252566134..370c4d1572ed 100644
--- a/drivers/spi/atmel-quadspi.c
+++ b/drivers/spi/atmel-quadspi.c
@@ -272,7 +272,7 @@ static int atmel_qspi_find_mode(const struct spi_mem_op *op)
 		if (atmel_qspi_is_compatible(op, &atmel_qspi_modes[i]))
 			return i;
 
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static bool atmel_qspi_supports_op(struct spi_mem *mem,
diff --git a/drivers/spi/spi-ath79.c b/drivers/spi/spi-ath79.c
index c9f1d1e1dcf7..b7ada981464a 100644
--- a/drivers/spi/spi-ath79.c
+++ b/drivers/spi/spi-ath79.c
@@ -146,7 +146,7 @@ static int ath79_exec_mem_op(struct spi_mem *mem,
 	/* Only use for fast-read op. */
 	if (op->cmd.opcode != 0x0b || op->data.dir != SPI_MEM_DATA_IN ||
 	    op->addr.nbytes != 3 || op->dummy.nbytes != 1)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	/* disable GPIO mode */
 	ath79_spi_wr(sp, AR71XX_SPI_REG_FS, 0);
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index 6aa8adbe4170..bad34998454a 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -22,6 +22,7 @@
 #include <linux/gpio/consumer.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/pm_runtime.h>
+#include <linux/iopoll.h>
 #include <trace/events/spi.h>
 
 /* SPI register offsets */
@@ -233,9 +234,6 @@
  */
 #define DMA_MIN_BYTES	16
 
-#define SPI_DMA_MIN_TIMEOUT	(msecs_to_jiffies(1000))
-#define SPI_DMA_TIMEOUT_PER_10K	(msecs_to_jiffies(4))
-
 #define AUTOSUSPEND_TIMEOUT	2000
 
 struct atmel_spi_caps {
@@ -279,6 +277,7 @@ struct atmel_spi {
 	bool			keep_cs;
 
 	u32			fifo_size;
+	bool			last_polarity;
 	u8			native_cs_free;
 	u8			native_cs_for_gpio;
 };
@@ -292,6 +291,22 @@ struct atmel_spi_device {
 #define INVALID_DMA_ADDRESS	0xffffffff
 
 /*
+ * This frequency can be anything supported by the controller, but to avoid
+ * unnecessary delay, the highest possible frequency is chosen.
+ *
+ * This frequency is the highest possible which is not interfering with other
+ * chip select registers (see Note for Serial Clock Bit Rate configuration in
+ * Atmel-11121F-ATARM-SAMA5D3-Series-Datasheet_02-Feb-16, page 1283)
+ */
+#define DUMMY_MSG_FREQUENCY	0x02
+/*
+ * 8 bits is the minimum data the controller is capable of sending.
+ *
+ * This message can be anything as it should not be treated by any SPI device.
+ */
+#define DUMMY_MSG		0xAA
+
+/*
  * Version 2 of the SPI controller has
  *  - CR.LASTXFER
  *  - SPI_MR.DIV32 may become FDIV or must-be-zero (here: always zero)
@@ -305,6 +320,43 @@ static bool atmel_spi_is_v2(struct atmel_spi *as)
 }
 
 /*
+ * Send a dummy message.
+ *
+ * This is sometimes needed when using a CS GPIO to force clock transition when
+ * switching between devices with different polarities.
+ */
+static void atmel_spi_send_dummy(struct atmel_spi *as, struct spi_device *spi, int chip_select)
+{
+	u32 status;
+	u32 csr;
+
+	/*
+	 * Set a clock frequency to allow sending message on SPI bus.
+	 * The frequency here can be anything, but is needed for
+	 * the controller to send the data.
+	 */
+	csr = spi_readl(as, CSR0 + 4 * chip_select);
+	csr = SPI_BFINS(SCBR, DUMMY_MSG_FREQUENCY, csr);
+	spi_writel(as, CSR0 + 4 * chip_select, csr);
+
+	/*
+	 * Read all data coming from SPI bus, needed to be able to send
+	 * the message.
+	 */
+	spi_readl(as, RDR);
+	while (spi_readl(as, SR) & SPI_BIT(RDRF)) {
+		spi_readl(as, RDR);
+		cpu_relax();
+	}
+
+	spi_writel(as, TDR, DUMMY_MSG);
+
+	readl_poll_timeout_atomic(as->regs + SPI_SR, status,
+				  (status & SPI_BIT(TXEMPTY)), 1, 1000);
+}
+
+
+/*
  * Earlier SPI controllers (e.g. on at91rm9200) have a design bug whereby
  * they assume that spi slave device state will not change on deselect, so
  * that automagic deselection is OK.  ("NPCSx rises if no data is to be
@@ -320,11 +372,17 @@ static bool atmel_spi_is_v2(struct atmel_spi *as)
  * Master on Chip Select 0.")  No workaround exists for that ... so for
  * nCS0 on that chip, we (a) don't use the GPIO, (b) can't support CS_HIGH,
  * and (c) will trigger that first erratum in some cases.
+ *
+ * When changing the clock polarity, the SPI controller waits for the next
+ * transmission to enforce the default clock state. This may be an issue when
+ * using a GPIO as Chip Select: the clock level is applied only when the first
+ * packet is sent, once the CS has already been asserted. The workaround is to
+ * avoid this by sending a first (dummy) message before toggling the CS state.
  */
-
 static void cs_activate(struct atmel_spi *as, struct spi_device *spi)
 {
 	struct atmel_spi_device *asd = spi->controller_state;
+	bool new_polarity;
 	int chip_select;
 	u32 mr;
 
@@ -353,6 +411,25 @@ static void cs_activate(struct atmel_spi *as, struct spi_device *spi)
 		}
 
 		mr = spi_readl(as, MR);
+
+		/*
+		 * Ensures the clock polarity is valid before we actually
+		 * assert the CS to avoid spurious clock edges to be
+		 * processed by the spi devices.
+		 */
+		if (spi_get_csgpiod(spi, 0)) {
+			new_polarity = (asd->csr & SPI_BIT(CPOL)) != 0;
+			if (new_polarity != as->last_polarity) {
+				/*
+				 * Need to disable the GPIO before sending the dummy
+				 * message because it is already set by the spi core.
+				 */
+				gpiod_set_value_cansleep(spi_get_csgpiod(spi, 0), 0);
+				atmel_spi_send_dummy(as, spi, chip_select);
+				as->last_polarity = new_polarity;
+				gpiod_set_value_cansleep(spi_get_csgpiod(spi, 0), 1);
+			}
+		}
 	} else {
 		u32 cpol = (spi->mode & SPI_CPOL) ? SPI_BIT(CPOL) : 0;
 		int i;
@@ -1336,12 +1413,10 @@ static int atmel_spi_one_transfer(struct spi_controller *host,
 		}
 
 		dma_timeout = msecs_to_jiffies(spi_controller_xfer_timeout(host, xfer));
-		ret_timeout = wait_for_completion_interruptible_timeout(&as->xfer_completion,
-									dma_timeout);
-		if (ret_timeout <= 0) {
-			dev_err(&spi->dev, "spi transfer %s\n",
-				!ret_timeout ? "timeout" : "canceled");
-			as->done_status = ret_timeout < 0 ? ret_timeout : -EIO;
+		ret_timeout = wait_for_completion_timeout(&as->xfer_completion, dma_timeout);
+		if (!ret_timeout) {
+			dev_err(&spi->dev, "spi transfer timeout\n");
+			as->done_status = -EIO;
 		}
 
 		if (as->done_status)
diff --git a/drivers/spi/spi-axi-spi-engine.c b/drivers/spi/spi-axi-spi-engine.c
index b96e55f59d1a..9ace259d2d29 100644
--- a/drivers/spi/spi-axi-spi-engine.c
+++ b/drivers/spi/spi-axi-spi-engine.c
@@ -6,12 +6,14 @@
  */
 
 #include <linux/clk.h>
+#include <linux/idr.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/spi/spi.h>
+#include <linux/timer.h>
 
 #define SPI_ENGINE_VERSION_MAJOR(x)	((x >> 16) & 0xff)
 #define SPI_ENGINE_VERSION_MINOR(x)	((x >> 8) & 0xff)
@@ -52,6 +54,7 @@
 
 #define SPI_ENGINE_CMD_REG_CLK_DIV		0x0
 #define SPI_ENGINE_CMD_REG_CONFIG		0x1
+#define SPI_ENGINE_CMD_REG_XFER_BITS		0x2
 
 #define SPI_ENGINE_MISC_SYNC			0x0
 #define SPI_ENGINE_MISC_SLEEP			0x1
@@ -78,29 +81,42 @@ struct spi_engine_program {
 	uint16_t instructions[];
 };
 
-struct spi_engine {
-	struct clk *clk;
-	struct clk *ref_clk;
-
-	spinlock_t lock;
-
-	void __iomem *base;
-
-	struct spi_message *msg;
+/**
+ * struct spi_engine_message_state - SPI engine per-message state
+ */
+struct spi_engine_message_state {
+	/** @p: Instructions for executing this message. */
 	struct spi_engine_program *p;
+	/** @cmd_length: Number of elements in cmd_buf array. */
 	unsigned cmd_length;
+	/** @cmd_buf: Array of commands not yet written to CMD FIFO. */
 	const uint16_t *cmd_buf;
-
+	/** @tx_xfer: Next xfer with tx_buf not yet fully written to TX FIFO. */
 	struct spi_transfer *tx_xfer;
+	/** @tx_length: Size of tx_buf in bytes. */
 	unsigned int tx_length;
+	/** @tx_buf: Bytes not yet written to TX FIFO. */
 	const uint8_t *tx_buf;
-
+	/** @rx_xfer: Next xfer with rx_buf not yet fully written to RX FIFO. */
 	struct spi_transfer *rx_xfer;
+	/** @rx_length: Size of tx_buf in bytes. */
 	unsigned int rx_length;
+	/** @rx_buf: Bytes not yet written to the RX FIFO. */
 	uint8_t *rx_buf;
+	/** @sync_id: ID to correlate SYNC interrupts with this message. */
+	u8 sync_id;
+};
+
+struct spi_engine {
+	struct clk *clk;
+	struct clk *ref_clk;
+
+	spinlock_t lock;
 
-	unsigned int sync_id;
-	unsigned int completed_id;
+	void __iomem *base;
+	struct ida sync_ida;
+	struct timer_list watchdog_timer;
+	struct spi_controller *controller;
 
 	unsigned int int_enable;
 };
@@ -127,25 +143,17 @@ static unsigned int spi_engine_get_config(struct spi_device *spi)
 	return config;
 }
 
-static unsigned int spi_engine_get_clk_div(struct spi_engine *spi_engine,
-	struct spi_device *spi, struct spi_transfer *xfer)
-{
-	unsigned int clk_div;
-
-	clk_div = DIV_ROUND_UP(clk_get_rate(spi_engine->ref_clk),
-		xfer->speed_hz * 2);
-	if (clk_div > 255)
-		clk_div = 255;
-	else if (clk_div > 0)
-		clk_div -= 1;
-
-	return clk_div;
-}
-
 static void spi_engine_gen_xfer(struct spi_engine_program *p, bool dry,
 	struct spi_transfer *xfer)
 {
-	unsigned int len = xfer->len;
+	unsigned int len;
+
+	if (xfer->bits_per_word <= 8)
+		len = xfer->len;
+	else if (xfer->bits_per_word <= 16)
+		len = xfer->len / 2;
+	else
+		len = xfer->len / 4;
 
 	while (len) {
 		unsigned int n = min(len, 256U);
@@ -163,22 +171,16 @@ static void spi_engine_gen_xfer(struct spi_engine_program *p, bool dry,
 }
 
 static void spi_engine_gen_sleep(struct spi_engine_program *p, bool dry,
-	struct spi_engine *spi_engine, unsigned int clk_div,
-	struct spi_transfer *xfer)
+				 int delay_ns, u32 sclk_hz)
 {
-	unsigned int spi_clk = clk_get_rate(spi_engine->ref_clk);
 	unsigned int t;
-	int delay;
 
-	delay = spi_delay_to_ns(&xfer->delay, xfer);
-	if (delay < 0)
+	/* negative delay indicates error, e.g. from spi_delay_to_ns() */
+	if (delay_ns <= 0)
 		return;
-	delay /= 1000;
 
-	if (delay == 0)
-		return;
-
-	t = DIV_ROUND_UP(delay * spi_clk, (clk_div + 1) * 2);
+	/* rounding down since executing the instruction adds a couple of ticks delay */
+	t = DIV_ROUND_DOWN_ULL((u64)delay_ns * sclk_hz, NSEC_PER_SEC);
 	while (t) {
 		unsigned int n = min(t, 256U);
 
@@ -195,53 +197,105 @@ static void spi_engine_gen_cs(struct spi_engine_program *p, bool dry,
 	if (assert)
 		mask ^= BIT(spi_get_chipselect(spi, 0));
 
-	spi_engine_program_add_cmd(p, dry, SPI_ENGINE_CMD_ASSERT(1, mask));
+	spi_engine_program_add_cmd(p, dry, SPI_ENGINE_CMD_ASSERT(0, mask));
+}
+
+/*
+ * Performs precompile steps on the message.
+ *
+ * The SPI core does most of the message/transfer validation and filling in
+ * fields for us via __spi_validate(). This fixes up anything remaining not
+ * done there.
+ *
+ * NB: This is separate from spi_engine_compile_message() because the latter
+ * is called twice and would otherwise result in double-evaluation.
+ */
+static void spi_engine_precompile_message(struct spi_message *msg)
+{
+	unsigned int clk_div, max_hz = msg->spi->controller->max_speed_hz;
+	struct spi_transfer *xfer;
+
+	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+		clk_div = DIV_ROUND_UP(max_hz, xfer->speed_hz);
+		xfer->effective_speed_hz = max_hz / min(clk_div, 256U);
+	}
 }
 
-static int spi_engine_compile_message(struct spi_engine *spi_engine,
-	struct spi_message *msg, bool dry, struct spi_engine_program *p)
+static void spi_engine_compile_message(struct spi_message *msg, bool dry,
+				       struct spi_engine_program *p)
 {
 	struct spi_device *spi = msg->spi;
+	struct spi_controller *host = spi->controller;
 	struct spi_transfer *xfer;
 	int clk_div, new_clk_div;
-	bool cs_change = true;
+	bool keep_cs = false;
+	u8 bits_per_word = 0;
 
-	clk_div = -1;
+	clk_div = 1;
 
 	spi_engine_program_add_cmd(p, dry,
 		SPI_ENGINE_CMD_WRITE(SPI_ENGINE_CMD_REG_CONFIG,
 			spi_engine_get_config(spi)));
 
+	xfer = list_first_entry(&msg->transfers, struct spi_transfer, transfer_list);
+	spi_engine_gen_cs(p, dry, spi, !xfer->cs_off);
+
 	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
-		new_clk_div = spi_engine_get_clk_div(spi_engine, spi, xfer);
+		new_clk_div = host->max_speed_hz / xfer->effective_speed_hz;
 		if (new_clk_div != clk_div) {
 			clk_div = new_clk_div;
+			/* actual divider used is register value + 1 */
 			spi_engine_program_add_cmd(p, dry,
 				SPI_ENGINE_CMD_WRITE(SPI_ENGINE_CMD_REG_CLK_DIV,
-					clk_div));
+					clk_div - 1));
 		}
 
-		if (cs_change)
-			spi_engine_gen_cs(p, dry, spi, true);
+		if (bits_per_word != xfer->bits_per_word) {
+			bits_per_word = xfer->bits_per_word;
+			spi_engine_program_add_cmd(p, dry,
+				SPI_ENGINE_CMD_WRITE(SPI_ENGINE_CMD_REG_XFER_BITS,
+					bits_per_word));
+		}
 
 		spi_engine_gen_xfer(p, dry, xfer);
-		spi_engine_gen_sleep(p, dry, spi_engine, clk_div, xfer);
-
-		cs_change = xfer->cs_change;
-		if (list_is_last(&xfer->transfer_list, &msg->transfers))
-			cs_change = !cs_change;
-
-		if (cs_change)
-			spi_engine_gen_cs(p, dry, spi, false);
+		spi_engine_gen_sleep(p, dry, spi_delay_to_ns(&xfer->delay, xfer),
+				     xfer->effective_speed_hz);
+
+		if (xfer->cs_change) {
+			if (list_is_last(&xfer->transfer_list, &msg->transfers)) {
+				keep_cs = true;
+			} else {
+				if (!xfer->cs_off)
+					spi_engine_gen_cs(p, dry, spi, false);
+
+				spi_engine_gen_sleep(p, dry, spi_delay_to_ns(
+					&xfer->cs_change_delay, xfer),
+					xfer->effective_speed_hz);
+
+				if (!list_next_entry(xfer, transfer_list)->cs_off)
+					spi_engine_gen_cs(p, dry, spi, true);
+			}
+		} else if (!list_is_last(&xfer->transfer_list, &msg->transfers) &&
+			   xfer->cs_off != list_next_entry(xfer, transfer_list)->cs_off) {
+			spi_engine_gen_cs(p, dry, spi, xfer->cs_off);
+		}
 	}
 
-	return 0;
+	if (!keep_cs)
+		spi_engine_gen_cs(p, dry, spi, false);
+
+	/*
+	 * Restore clockdiv to default so that future gen_sleep commands don't
+	 * have to be aware of the current register state.
+	 */
+	if (clk_div != 1)
+		spi_engine_program_add_cmd(p, dry,
+			SPI_ENGINE_CMD_WRITE(SPI_ENGINE_CMD_REG_CLK_DIV, 0));
 }
 
-static void spi_engine_xfer_next(struct spi_engine *spi_engine,
+static void spi_engine_xfer_next(struct spi_message *msg,
 	struct spi_transfer **_xfer)
 {
-	struct spi_message *msg = spi_engine->msg;
 	struct spi_transfer *xfer = *_xfer;
 
 	if (!xfer) {
@@ -256,147 +310,192 @@ static void spi_engine_xfer_next(struct spi_engine *spi_engine,
 	*_xfer = xfer;
 }
 
-static void spi_engine_tx_next(struct spi_engine *spi_engine)
+static void spi_engine_tx_next(struct spi_message *msg)
 {
-	struct spi_transfer *xfer = spi_engine->tx_xfer;
+	struct spi_engine_message_state *st = msg->state;
+	struct spi_transfer *xfer = st->tx_xfer;
 
 	do {
-		spi_engine_xfer_next(spi_engine, &xfer);
+		spi_engine_xfer_next(msg, &xfer);
 	} while (xfer && !xfer->tx_buf);
 
-	spi_engine->tx_xfer = xfer;
+	st->tx_xfer = xfer;
 	if (xfer) {
-		spi_engine->tx_length = xfer->len;
-		spi_engine->tx_buf = xfer->tx_buf;
+		st->tx_length = xfer->len;
+		st->tx_buf = xfer->tx_buf;
 	} else {
-		spi_engine->tx_buf = NULL;
+		st->tx_buf = NULL;
 	}
 }
 
-static void spi_engine_rx_next(struct spi_engine *spi_engine)
+static void spi_engine_rx_next(struct spi_message *msg)
 {
-	struct spi_transfer *xfer = spi_engine->rx_xfer;
+	struct spi_engine_message_state *st = msg->state;
+	struct spi_transfer *xfer = st->rx_xfer;
 
 	do {
-		spi_engine_xfer_next(spi_engine, &xfer);
+		spi_engine_xfer_next(msg, &xfer);
 	} while (xfer && !xfer->rx_buf);
 
-	spi_engine->rx_xfer = xfer;
+	st->rx_xfer = xfer;
 	if (xfer) {
-		spi_engine->rx_length = xfer->len;
-		spi_engine->rx_buf = xfer->rx_buf;
+		st->rx_length = xfer->len;
+		st->rx_buf = xfer->rx_buf;
 	} else {
-		spi_engine->rx_buf = NULL;
+		st->rx_buf = NULL;
 	}
 }
 
-static bool spi_engine_write_cmd_fifo(struct spi_engine *spi_engine)
+static bool spi_engine_write_cmd_fifo(struct spi_engine *spi_engine,
+				      struct spi_message *msg)
 {
 	void __iomem *addr = spi_engine->base + SPI_ENGINE_REG_CMD_FIFO;
+	struct spi_engine_message_state *st = msg->state;
 	unsigned int n, m, i;
 	const uint16_t *buf;
 
 	n = readl_relaxed(spi_engine->base + SPI_ENGINE_REG_CMD_FIFO_ROOM);
-	while (n && spi_engine->cmd_length) {
-		m = min(n, spi_engine->cmd_length);
-		buf = spi_engine->cmd_buf;
+	while (n && st->cmd_length) {
+		m = min(n, st->cmd_length);
+		buf = st->cmd_buf;
 		for (i = 0; i < m; i++)
 			writel_relaxed(buf[i], addr);
-		spi_engine->cmd_buf += m;
-		spi_engine->cmd_length -= m;
+		st->cmd_buf += m;
+		st->cmd_length -= m;
 		n -= m;
 	}
 
-	return spi_engine->cmd_length != 0;
+	return st->cmd_length != 0;
 }
 
-static bool spi_engine_write_tx_fifo(struct spi_engine *spi_engine)
+static bool spi_engine_write_tx_fifo(struct spi_engine *spi_engine,
+				     struct spi_message *msg)
 {
 	void __iomem *addr = spi_engine->base + SPI_ENGINE_REG_SDO_DATA_FIFO;
+	struct spi_engine_message_state *st = msg->state;
 	unsigned int n, m, i;
-	const uint8_t *buf;
 
 	n = readl_relaxed(spi_engine->base + SPI_ENGINE_REG_SDO_FIFO_ROOM);
-	while (n && spi_engine->tx_length) {
-		m = min(n, spi_engine->tx_length);
-		buf = spi_engine->tx_buf;
-		for (i = 0; i < m; i++)
-			writel_relaxed(buf[i], addr);
-		spi_engine->tx_buf += m;
-		spi_engine->tx_length -= m;
+	while (n && st->tx_length) {
+		if (st->tx_xfer->bits_per_word <= 8) {
+			const u8 *buf = st->tx_buf;
+
+			m = min(n, st->tx_length);
+			for (i = 0; i < m; i++)
+				writel_relaxed(buf[i], addr);
+			st->tx_buf += m;
+			st->tx_length -= m;
+		} else if (st->tx_xfer->bits_per_word <= 16) {
+			const u16 *buf = (const u16 *)st->tx_buf;
+
+			m = min(n, st->tx_length / 2);
+			for (i = 0; i < m; i++)
+				writel_relaxed(buf[i], addr);
+			st->tx_buf += m * 2;
+			st->tx_length -= m * 2;
+		} else {
+			const u32 *buf = (const u32 *)st->tx_buf;
+
+			m = min(n, st->tx_length / 4);
+			for (i = 0; i < m; i++)
+				writel_relaxed(buf[i], addr);
+			st->tx_buf += m * 4;
+			st->tx_length -= m * 4;
+		}
 		n -= m;
-		if (spi_engine->tx_length == 0)
-			spi_engine_tx_next(spi_engine);
+		if (st->tx_length == 0)
+			spi_engine_tx_next(msg);
 	}
 
-	return spi_engine->tx_length != 0;
+	return st->tx_length != 0;
 }
 
-static bool spi_engine_read_rx_fifo(struct spi_engine *spi_engine)
+static bool spi_engine_read_rx_fifo(struct spi_engine *spi_engine,
+				    struct spi_message *msg)
 {
 	void __iomem *addr = spi_engine->base + SPI_ENGINE_REG_SDI_DATA_FIFO;
+	struct spi_engine_message_state *st = msg->state;
 	unsigned int n, m, i;
-	uint8_t *buf;
 
 	n = readl_relaxed(spi_engine->base + SPI_ENGINE_REG_SDI_FIFO_LEVEL);
-	while (n && spi_engine->rx_length) {
-		m = min(n, spi_engine->rx_length);
-		buf = spi_engine->rx_buf;
-		for (i = 0; i < m; i++)
-			buf[i] = readl_relaxed(addr);
-		spi_engine->rx_buf += m;
-		spi_engine->rx_length -= m;
+	while (n && st->rx_length) {
+		if (st->rx_xfer->bits_per_word <= 8) {
+			u8 *buf = st->rx_buf;
+
+			m = min(n, st->rx_length);
+			for (i = 0; i < m; i++)
+				buf[i] = readl_relaxed(addr);
+			st->rx_buf += m;
+			st->rx_length -= m;
+		} else if (st->rx_xfer->bits_per_word <= 16) {
+			u16 *buf = (u16 *)st->rx_buf;
+
+			m = min(n, st->rx_length / 2);
+			for (i = 0; i < m; i++)
+				buf[i] = readl_relaxed(addr);
+			st->rx_buf += m * 2;
+			st->rx_length -= m * 2;
+		} else {
+			u32 *buf = (u32 *)st->rx_buf;
+
+			m = min(n, st->rx_length / 4);
+			for (i = 0; i < m; i++)
+				buf[i] = readl_relaxed(addr);
+			st->rx_buf += m * 4;
+			st->rx_length -= m * 4;
+		}
 		n -= m;
-		if (spi_engine->rx_length == 0)
-			spi_engine_rx_next(spi_engine);
+		if (st->rx_length == 0)
+			spi_engine_rx_next(msg);
 	}
 
-	return spi_engine->rx_length != 0;
+	return st->rx_length != 0;
 }
 
 static irqreturn_t spi_engine_irq(int irq, void *devid)
 {
 	struct spi_controller *host = devid;
+	struct spi_message *msg = host->cur_msg;
 	struct spi_engine *spi_engine = spi_controller_get_devdata(host);
 	unsigned int disable_int = 0;
 	unsigned int pending;
+	int completed_id = -1;
 
 	pending = readl_relaxed(spi_engine->base + SPI_ENGINE_REG_INT_PENDING);
 
 	if (pending & SPI_ENGINE_INT_SYNC) {
 		writel_relaxed(SPI_ENGINE_INT_SYNC,
 			spi_engine->base + SPI_ENGINE_REG_INT_PENDING);
-		spi_engine->completed_id = readl_relaxed(
+		completed_id = readl_relaxed(
 			spi_engine->base + SPI_ENGINE_REG_SYNC_ID);
 	}
 
 	spin_lock(&spi_engine->lock);
 
 	if (pending & SPI_ENGINE_INT_CMD_ALMOST_EMPTY) {
-		if (!spi_engine_write_cmd_fifo(spi_engine))
+		if (!spi_engine_write_cmd_fifo(spi_engine, msg))
 			disable_int |= SPI_ENGINE_INT_CMD_ALMOST_EMPTY;
 	}
 
 	if (pending & SPI_ENGINE_INT_SDO_ALMOST_EMPTY) {
-		if (!spi_engine_write_tx_fifo(spi_engine))
+		if (!spi_engine_write_tx_fifo(spi_engine, msg))
 			disable_int |= SPI_ENGINE_INT_SDO_ALMOST_EMPTY;
 	}
 
 	if (pending & (SPI_ENGINE_INT_SDI_ALMOST_FULL | SPI_ENGINE_INT_SYNC)) {
-		if (!spi_engine_read_rx_fifo(spi_engine))
+		if (!spi_engine_read_rx_fifo(spi_engine, msg))
 			disable_int |= SPI_ENGINE_INT_SDI_ALMOST_FULL;
 	}
 
-	if (pending & SPI_ENGINE_INT_SYNC) {
-		if (spi_engine->msg &&
-		    spi_engine->completed_id == spi_engine->sync_id) {
-			struct spi_message *msg = spi_engine->msg;
-
-			kfree(spi_engine->p);
-			msg->status = 0;
-			msg->actual_length = msg->frame_length;
-			spi_engine->msg = NULL;
-			spi_finalize_current_message(host);
+	if (pending & SPI_ENGINE_INT_SYNC && msg) {
+		struct spi_engine_message_state *st = msg->state;
+
+		if (completed_id == st->sync_id) {
+			if (timer_delete_sync(&spi_engine->watchdog_timer)) {
+				msg->status = 0;
+				msg->actual_length = msg->frame_length;
+				spi_finalize_current_message(host);
+			}
 			disable_int |= SPI_ENGINE_INT_SYNC;
 		}
 	}
@@ -412,43 +511,86 @@ static irqreturn_t spi_engine_irq(int irq, void *devid)
 	return IRQ_HANDLED;
 }
 
-static int spi_engine_transfer_one_message(struct spi_controller *host,
-	struct spi_message *msg)
+static int spi_engine_prepare_message(struct spi_controller *host,
+				      struct spi_message *msg)
 {
 	struct spi_engine_program p_dry, *p;
 	struct spi_engine *spi_engine = spi_controller_get_devdata(host);
-	unsigned int int_enable = 0;
-	unsigned long flags;
+	struct spi_engine_message_state *st;
 	size_t size;
+	int ret;
+
+	st = kzalloc(sizeof(*st), GFP_KERNEL);
+	if (!st)
+		return -ENOMEM;
+
+	spi_engine_precompile_message(msg);
 
 	p_dry.length = 0;
-	spi_engine_compile_message(spi_engine, msg, true, &p_dry);
+	spi_engine_compile_message(msg, true, &p_dry);
 
 	size = sizeof(*p->instructions) * (p_dry.length + 1);
 	p = kzalloc(sizeof(*p) + size, GFP_KERNEL);
-	if (!p)
+	if (!p) {
+		kfree(st);
 		return -ENOMEM;
-	spi_engine_compile_message(spi_engine, msg, false, p);
+	}
 
-	spin_lock_irqsave(&spi_engine->lock, flags);
-	spi_engine->sync_id = (spi_engine->sync_id + 1) & 0xff;
-	spi_engine_program_add_cmd(p, false,
-		SPI_ENGINE_CMD_SYNC(spi_engine->sync_id));
+	ret = ida_alloc_range(&spi_engine->sync_ida, 0, U8_MAX, GFP_KERNEL);
+	if (ret < 0) {
+		kfree(p);
+		kfree(st);
+		return ret;
+	}
+
+	st->sync_id = ret;
+
+	spi_engine_compile_message(msg, false, p);
+
+	spi_engine_program_add_cmd(p, false, SPI_ENGINE_CMD_SYNC(st->sync_id));
+
+	st->p = p;
+	st->cmd_buf = p->instructions;
+	st->cmd_length = p->length;
+	msg->state = st;
+
+	return 0;
+}
+
+static int spi_engine_unprepare_message(struct spi_controller *host,
+					struct spi_message *msg)
+{
+	struct spi_engine *spi_engine = spi_controller_get_devdata(host);
+	struct spi_engine_message_state *st = msg->state;
+
+	ida_free(&spi_engine->sync_ida, st->sync_id);
+	kfree(st->p);
+	kfree(st);
 
-	spi_engine->msg = msg;
-	spi_engine->p = p;
+	return 0;
+}
 
-	spi_engine->cmd_buf = p->instructions;
-	spi_engine->cmd_length = p->length;
-	if (spi_engine_write_cmd_fifo(spi_engine))
+static int spi_engine_transfer_one_message(struct spi_controller *host,
+	struct spi_message *msg)
+{
+	struct spi_engine *spi_engine = spi_controller_get_devdata(host);
+	struct spi_engine_message_state *st = msg->state;
+	unsigned int int_enable = 0;
+	unsigned long flags;
+
+	mod_timer(&spi_engine->watchdog_timer, jiffies + msecs_to_jiffies(5000));
+
+	spin_lock_irqsave(&spi_engine->lock, flags);
+
+	if (spi_engine_write_cmd_fifo(spi_engine, msg))
 		int_enable |= SPI_ENGINE_INT_CMD_ALMOST_EMPTY;
 
-	spi_engine_tx_next(spi_engine);
-	if (spi_engine_write_tx_fifo(spi_engine))
+	spi_engine_tx_next(msg);
+	if (spi_engine_write_tx_fifo(spi_engine, msg))
 		int_enable |= SPI_ENGINE_INT_SDO_ALMOST_EMPTY;
 
-	spi_engine_rx_next(spi_engine);
-	if (spi_engine->rx_length != 0)
+	spi_engine_rx_next(msg);
+	if (st->rx_length != 0)
 		int_enable |= SPI_ENGINE_INT_SDI_ALMOST_FULL;
 
 	int_enable |= SPI_ENGINE_INT_SYNC;
@@ -461,6 +603,29 @@ static int spi_engine_transfer_one_message(struct spi_controller *host,
 	return 0;
 }
 
+static void spi_engine_timeout(struct timer_list *timer)
+{
+	struct spi_engine *spi_engine = from_timer(spi_engine, timer, watchdog_timer);
+	struct spi_controller *host = spi_engine->controller;
+
+	if (WARN_ON(!host->cur_msg))
+		return;
+
+	dev_err(&host->dev,
+		"Timeout occurred while waiting for transfer to complete. Hardware is probably broken.\n");
+	host->cur_msg->status = -ETIMEDOUT;
+	spi_finalize_current_message(host);
+}
+
+static void spi_engine_release_hw(void *p)
+{
+	struct spi_engine *spi_engine = p;
+
+	writel_relaxed(0xff, spi_engine->base + SPI_ENGINE_REG_INT_PENDING);
+	writel_relaxed(0x00, spi_engine->base + SPI_ENGINE_REG_INT_ENABLE);
+	writel_relaxed(0x01, spi_engine->base + SPI_ENGINE_REG_RESET);
+}
+
 static int spi_engine_probe(struct platform_device *pdev)
 {
 	struct spi_engine *spi_engine;
@@ -473,35 +638,28 @@ static int spi_engine_probe(struct platform_device *pdev)
 	if (irq < 0)
 		return irq;
 
-	spi_engine = devm_kzalloc(&pdev->dev, sizeof(*spi_engine), GFP_KERNEL);
-	if (!spi_engine)
-		return -ENOMEM;
-
-	host = spi_alloc_host(&pdev->dev, 0);
+	host = devm_spi_alloc_host(&pdev->dev, sizeof(*spi_engine));
 	if (!host)
 		return -ENOMEM;
 
-	spi_controller_set_devdata(host, spi_engine);
+	spi_engine = spi_controller_get_devdata(host);
 
 	spin_lock_init(&spi_engine->lock);
+	ida_init(&spi_engine->sync_ida);
+	timer_setup(&spi_engine->watchdog_timer, spi_engine_timeout, TIMER_IRQSAFE);
+	spi_engine->controller = host;
 
 	spi_engine->clk = devm_clk_get_enabled(&pdev->dev, "s_axi_aclk");
-	if (IS_ERR(spi_engine->clk)) {
-		ret = PTR_ERR(spi_engine->clk);
-		goto err_put_host;
-	}
+	if (IS_ERR(spi_engine->clk))
+		return PTR_ERR(spi_engine->clk);
 
 	spi_engine->ref_clk = devm_clk_get_enabled(&pdev->dev, "spi_clk");
-	if (IS_ERR(spi_engine->ref_clk)) {
-		ret = PTR_ERR(spi_engine->ref_clk);
-		goto err_put_host;
-	}
+	if (IS_ERR(spi_engine->ref_clk))
+		return PTR_ERR(spi_engine->ref_clk);
 
 	spi_engine->base = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(spi_engine->base)) {
-		ret = PTR_ERR(spi_engine->base);
-		goto err_put_host;
-	}
+	if (IS_ERR(spi_engine->base))
+		return PTR_ERR(spi_engine->base);
 
 	version = readl(spi_engine->base + SPI_ENGINE_REG_VERSION);
 	if (SPI_ENGINE_VERSION_MAJOR(version) != 1) {
@@ -509,54 +667,42 @@ static int spi_engine_probe(struct platform_device *pdev)
 			SPI_ENGINE_VERSION_MAJOR(version),
 			SPI_ENGINE_VERSION_MINOR(version),
 			SPI_ENGINE_VERSION_PATCH(version));
-		ret = -ENODEV;
-		goto err_put_host;
+		return -ENODEV;
 	}
 
 	writel_relaxed(0x00, spi_engine->base + SPI_ENGINE_REG_RESET);
 	writel_relaxed(0xff, spi_engine->base + SPI_ENGINE_REG_INT_PENDING);
 	writel_relaxed(0x00, spi_engine->base + SPI_ENGINE_REG_INT_ENABLE);
 
-	ret = request_irq(irq, spi_engine_irq, 0, pdev->name, host);
+	ret = devm_add_action_or_reset(&pdev->dev, spi_engine_release_hw,
+				       spi_engine);
 	if (ret)
-		goto err_put_host;
+		return ret;
+
+	ret = devm_request_irq(&pdev->dev, irq, spi_engine_irq, 0, pdev->name,
+			       host);
+	if (ret)
+		return ret;
 
 	host->dev.of_node = pdev->dev.of_node;
 	host->mode_bits = SPI_CPOL | SPI_CPHA | SPI_3WIRE;
-	host->bits_per_word_mask = SPI_BPW_MASK(8);
+	host->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 32);
 	host->max_speed_hz = clk_get_rate(spi_engine->ref_clk) / 2;
 	host->transfer_one_message = spi_engine_transfer_one_message;
+	host->prepare_message = spi_engine_prepare_message;
+	host->unprepare_message = spi_engine_unprepare_message;
 	host->num_chipselect = 8;
 
-	ret = spi_register_controller(host);
+	if (host->max_speed_hz == 0)
+		return dev_err_probe(&pdev->dev, -EINVAL, "spi_clk rate is 0");
+
+	ret = devm_spi_register_controller(&pdev->dev, host);
 	if (ret)
-		goto err_free_irq;
+		return ret;
 
 	platform_set_drvdata(pdev, host);
 
 	return 0;
-err_free_irq:
-	free_irq(irq, host);
-err_put_host:
-	spi_controller_put(host);
-	return ret;
-}
-
-static void spi_engine_remove(struct platform_device *pdev)
-{
-	struct spi_controller *host = spi_controller_get(platform_get_drvdata(pdev));
-	struct spi_engine *spi_engine = spi_controller_get_devdata(host);
-	int irq = platform_get_irq(pdev, 0);
-
-	spi_unregister_controller(host);
-
-	free_irq(irq, host);
-
-	spi_controller_put(host);
-
-	writel_relaxed(0xff, spi_engine->base + SPI_ENGINE_REG_INT_PENDING);
-	writel_relaxed(0x00, spi_engine->base + SPI_ENGINE_REG_INT_ENABLE);
-	writel_relaxed(0x01, spi_engine->base + SPI_ENGINE_REG_RESET);
 }
 
 static const struct of_device_id spi_engine_match_table[] = {
@@ -567,7 +713,6 @@ MODULE_DEVICE_TABLE(of, spi_engine_match_table);
 
 static struct platform_driver spi_engine_driver = {
 	.probe = spi_engine_probe,
-	.remove_new = spi_engine_remove,
 	.driver = {
 		.name = "spi-engine",
 		.of_match_table = spi_engine_match_table,
diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c
index ef08fcac2f6d..d96222e6d7d2 100644
--- a/drivers/spi/spi-bcm-qspi.c
+++ b/drivers/spi/spi-bcm-qspi.c
@@ -1199,7 +1199,7 @@ static int bcm_qspi_exec_mem_op(struct spi_mem *mem,
 
 	if (!op->data.nbytes || !op->addr.nbytes || op->addr.nbytes > 4 ||
 	    op->data.dir != SPI_MEM_DATA_IN)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	buf = op->data.buf.in;
 	addr = op->addr.val;
diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index 3d7bf62da11c..f94e0d370d46 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -1840,7 +1840,7 @@ static int cqspi_probe(struct platform_device *pdev)
 		if (ddata->jh7110_clk_init) {
 			ret = cqspi_jh7110_clk_init(pdev, cqspi);
 			if (ret)
-				goto probe_clk_failed;
+				goto probe_reset_failed;
 		}
 
 		if (of_device_is_compatible(pdev->dev.of_node,
@@ -1901,6 +1901,8 @@ static int cqspi_probe(struct platform_device *pdev)
 probe_setup_failed:
 	cqspi_controller_enable(cqspi, 0);
 probe_reset_failed:
+	if (cqspi->is_jh7110)
+		cqspi_jh7110_disable_clk(pdev, cqspi);
 	clk_disable_unprepare(cqspi->clk);
 probe_clk_failed:
 	return ret;
diff --git a/drivers/spi/spi-cadence-xspi.c b/drivers/spi/spi-cadence-xspi.c
index b7e04b03be58..8648b8eb080d 100644
--- a/drivers/spi/spi-cadence-xspi.c
+++ b/drivers/spi/spi-cadence-xspi.c
@@ -619,7 +619,6 @@ MODULE_DEVICE_TABLE(of, cdns_xspi_of_match);
 
 static struct platform_driver cdns_xspi_platform_driver = {
 	.probe          = cdns_xspi_probe,
-	.remove         = NULL,
 	.driver = {
 		.name = CDNS_XSPI_NAME,
 		.of_match_table = cdns_xspi_of_match,
diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c
index 1f2f8c717df6..a50eb4db79de 100644
--- a/drivers/spi/spi-cadence.c
+++ b/drivers/spi/spi-cadence.c
@@ -451,7 +451,6 @@ static int cdns_transfer_one(struct spi_controller *ctlr,
 		udelay(10);
 
 	cdns_spi_process_fifo(xspi, xspi->tx_fifo_depth, 0);
-	spi_transfer_delay_exec(transfer);
 
 	cdns_spi_write(xspi, CDNS_SPI_IER, CDNS_SPI_IXR_DEFAULT);
 	return transfer->len;
diff --git a/drivers/spi/spi-cs42l43.c b/drivers/spi/spi-cs42l43.c
index d239fc5a49cc..f13073e12593 100644
--- a/drivers/spi/spi-cs42l43.c
+++ b/drivers/spi/spi-cs42l43.c
@@ -213,7 +213,7 @@ static int cs42l43_spi_probe(struct platform_device *pdev)
 	if (!priv)
 		return -ENOMEM;
 
-	priv->ctlr = devm_spi_alloc_master(&pdev->dev, sizeof(*priv->ctlr));
+	priv->ctlr = devm_spi_alloc_host(&pdev->dev, sizeof(*priv->ctlr));
 	if (!priv->ctlr)
 		return -ENOMEM;
 
diff --git a/drivers/spi/spi-dw-mmio.c b/drivers/spi/spi-dw-mmio.c
index 46801189a651..cc74cbe03431 100644
--- a/drivers/spi/spi-dw-mmio.c
+++ b/drivers/spi/spi-dw-mmio.c
@@ -411,7 +411,6 @@ static const struct of_device_id dw_spi_mmio_of_match[] = {
 	{ .compatible = "renesas,rzn1-spi", .data = dw_spi_pssi_init},
 	{ .compatible = "snps,dwc-ssi-1.01a", .data = dw_spi_hssi_init},
 	{ .compatible = "intel,keembay-ssi", .data = dw_spi_intel_init},
-	{ .compatible = "intel,thunderbay-ssi", .data = dw_spi_intel_init},
 	{
 		.compatible = "intel,mountevans-imc-ssi",
 		.data = dw_spi_mountevans_imc_init,
diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c
index b956a32a4162..15f84e68d4d2 100644
--- a/drivers/spi/spi-geni-qcom.c
+++ b/drivers/spi/spi-geni-qcom.c
@@ -145,10 +145,10 @@ static int get_spi_clk_cfg(unsigned int speed_hz,
 	return ret;
 }
 
-static void handle_se_timeout(struct spi_master *spi,
-				struct spi_message *msg)
+static void handle_se_timeout(struct spi_controller *spi,
+			      struct spi_message *msg)
 {
-	struct spi_geni_master *mas = spi_master_get_devdata(spi);
+	struct spi_geni_master *mas = spi_controller_get_devdata(spi);
 	unsigned long time_left;
 	struct geni_se *se = &mas->se;
 	const struct spi_transfer *xfer;
@@ -160,9 +160,9 @@ static void handle_se_timeout(struct spi_master *spi,
 	xfer = mas->cur_xfer;
 	mas->cur_xfer = NULL;
 
-	if (spi->slave) {
+	if (spi->target) {
 		/*
-		 * skip CMD Cancel sequnece since spi slave
+		 * skip CMD Cancel sequnece since spi target
 		 * doesn`t support CMD Cancel sequnece
 		 */
 		spin_unlock_irq(&mas->lock);
@@ -225,17 +225,17 @@ reset_if_dma:
 	}
 }
 
-static void handle_gpi_timeout(struct spi_master *spi, struct spi_message *msg)
+static void handle_gpi_timeout(struct spi_controller *spi, struct spi_message *msg)
 {
-	struct spi_geni_master *mas = spi_master_get_devdata(spi);
+	struct spi_geni_master *mas = spi_controller_get_devdata(spi);
 
 	dmaengine_terminate_sync(mas->tx);
 	dmaengine_terminate_sync(mas->rx);
 }
 
-static void spi_geni_handle_err(struct spi_master *spi, struct spi_message *msg)
+static void spi_geni_handle_err(struct spi_controller *spi, struct spi_message *msg)
 {
-	struct spi_geni_master *mas = spi_master_get_devdata(spi);
+	struct spi_geni_master *mas = spi_controller_get_devdata(spi);
 
 	switch (mas->cur_xfer_mode) {
 	case GENI_SE_FIFO:
@@ -286,8 +286,8 @@ static bool spi_geni_is_abort_still_pending(struct spi_geni_master *mas)
 
 static void spi_geni_set_cs(struct spi_device *slv, bool set_flag)
 {
-	struct spi_geni_master *mas = spi_master_get_devdata(slv->master);
-	struct spi_master *spi = dev_get_drvdata(mas->dev);
+	struct spi_geni_master *mas = spi_controller_get_devdata(slv->controller);
+	struct spi_controller *spi = dev_get_drvdata(mas->dev);
 	struct geni_se *se = &mas->se;
 	unsigned long time_left;
 
@@ -395,9 +395,9 @@ static int geni_spi_set_clock_and_bw(struct spi_geni_master *mas,
 }
 
 static int setup_fifo_params(struct spi_device *spi_slv,
-					struct spi_master *spi)
+					struct spi_controller *spi)
 {
-	struct spi_geni_master *mas = spi_master_get_devdata(spi);
+	struct spi_geni_master *mas = spi_controller_get_devdata(spi);
 	struct geni_se *se = &mas->se;
 	u32 loopback_cfg = 0, cpol = 0, cpha = 0, demux_output_inv = 0;
 	u32 demux_sel;
@@ -434,7 +434,7 @@ static int setup_fifo_params(struct spi_device *spi_slv,
 static void
 spi_gsi_callback_result(void *cb, const struct dmaengine_result *result)
 {
-	struct spi_master *spi = cb;
+	struct spi_controller *spi = cb;
 
 	spi->cur_msg->status = -EIO;
 	if (result->result != DMA_TRANS_NOERROR) {
@@ -454,7 +454,7 @@ spi_gsi_callback_result(void *cb, const struct dmaengine_result *result)
 }
 
 static int setup_gsi_xfer(struct spi_transfer *xfer, struct spi_geni_master *mas,
-			  struct spi_device *spi_slv, struct spi_master *spi)
+			  struct spi_device *spi_slv, struct spi_controller *spi)
 {
 	unsigned long flags = DMA_PREP_INTERRUPT | DMA_CTRL_ACK;
 	struct dma_slave_config config = {};
@@ -560,14 +560,14 @@ static u32 get_xfer_len_in_words(struct spi_transfer *xfer,
 static bool geni_can_dma(struct spi_controller *ctlr,
 			 struct spi_device *slv, struct spi_transfer *xfer)
 {
-	struct spi_geni_master *mas = spi_master_get_devdata(slv->master);
+	struct spi_geni_master *mas = spi_controller_get_devdata(slv->controller);
 	u32 len, fifo_size;
 
 	if (mas->cur_xfer_mode == GENI_GPI_DMA)
 		return true;
 
-	/* Set SE DMA mode for SPI slave. */
-	if (ctlr->slave)
+	/* Set SE DMA mode for SPI target. */
+	if (ctlr->target)
 		return true;
 
 	len = get_xfer_len_in_words(xfer, mas);
@@ -579,10 +579,10 @@ static bool geni_can_dma(struct spi_controller *ctlr,
 		return false;
 }
 
-static int spi_geni_prepare_message(struct spi_master *spi,
-					struct spi_message *spi_msg)
+static int spi_geni_prepare_message(struct spi_controller *spi,
+				    struct spi_message *spi_msg)
 {
-	struct spi_geni_master *mas = spi_master_get_devdata(spi);
+	struct spi_geni_master *mas = spi_controller_get_devdata(spi);
 	int ret;
 
 	switch (mas->cur_xfer_mode) {
@@ -657,7 +657,7 @@ static int spi_geni_init(struct spi_geni_master *mas)
 
 	proto = geni_se_read_proto(se);
 
-	if (spi->slave) {
+	if (spi->target) {
 		if (proto != GENI_SE_SPI_SLAVE) {
 			dev_err(mas->dev, "Invalid proto %d\n", proto);
 			goto out_pm;
@@ -715,7 +715,7 @@ static int spi_geni_init(struct spi_geni_master *mas)
 	}
 
 	/* We always control CS manually */
-	if (!spi->slave) {
+	if (!spi->target) {
 		spi_tx_cfg = readl(se->base + SE_SPI_TRANS_CFG);
 		spi_tx_cfg &= ~CS_TOGGLE;
 		writel(spi_tx_cfg, se->base + SE_SPI_TRANS_CFG);
@@ -824,7 +824,7 @@ static void geni_spi_handle_rx(struct spi_geni_master *mas)
 
 static int setup_se_xfer(struct spi_transfer *xfer,
 				struct spi_geni_master *mas,
-				u16 mode, struct spi_master *spi)
+				u16 mode, struct spi_controller *spi)
 {
 	u32 m_cmd = 0;
 	u32 len;
@@ -913,11 +913,11 @@ static int setup_se_xfer(struct spi_transfer *xfer,
 	return ret;
 }
 
-static int spi_geni_transfer_one(struct spi_master *spi,
-				struct spi_device *slv,
-				struct spi_transfer *xfer)
+static int spi_geni_transfer_one(struct spi_controller *spi,
+				 struct spi_device *slv,
+				 struct spi_transfer *xfer)
 {
-	struct spi_geni_master *mas = spi_master_get_devdata(spi);
+	struct spi_geni_master *mas = spi_controller_get_devdata(spi);
 	int ret;
 
 	if (spi_geni_is_abort_still_pending(mas))
@@ -939,8 +939,8 @@ static int spi_geni_transfer_one(struct spi_master *spi,
 
 static irqreturn_t geni_spi_isr(int irq, void *data)
 {
-	struct spi_master *spi = data;
-	struct spi_geni_master *mas = spi_master_get_devdata(spi);
+	struct spi_controller *spi = data;
+	struct spi_geni_master *mas = spi_controller_get_devdata(spi);
 	struct geni_se *se = &mas->se;
 	u32 m_irq;
 
@@ -1042,7 +1042,7 @@ static irqreturn_t geni_spi_isr(int irq, void *data)
 static int spi_geni_probe(struct platform_device *pdev)
 {
 	int ret, irq;
-	struct spi_master *spi;
+	struct spi_controller *spi;
 	struct spi_geni_master *mas;
 	void __iomem *base;
 	struct clk *clk;
@@ -1064,12 +1064,12 @@ static int spi_geni_probe(struct platform_device *pdev)
 	if (IS_ERR(clk))
 		return PTR_ERR(clk);
 
-	spi = devm_spi_alloc_master(dev, sizeof(*mas));
+	spi = devm_spi_alloc_host(dev, sizeof(*mas));
 	if (!spi)
 		return -ENOMEM;
 
 	platform_set_drvdata(pdev, spi);
-	mas = spi_master_get_devdata(spi);
+	mas = spi_controller_get_devdata(spi);
 	mas->irq = irq;
 	mas->dev = dev;
 	mas->se.dev = dev;
@@ -1113,7 +1113,7 @@ static int spi_geni_probe(struct platform_device *pdev)
 	pm_runtime_enable(dev);
 
 	if (device_property_read_bool(&pdev->dev, "spi-slave"))
-		spi->slave = true;
+		spi->target = true;
 
 	ret = geni_icc_get(&mas->se, NULL);
 	if (ret)
@@ -1135,7 +1135,7 @@ static int spi_geni_probe(struct platform_device *pdev)
 	 * for dma (gsi) mode, the gsi will set cs based on params passed in
 	 * TRE
 	 */
-	if (!spi->slave && mas->cur_xfer_mode == GENI_SE_FIFO)
+	if (!spi->target && mas->cur_xfer_mode == GENI_SE_FIFO)
 		spi->set_cs = spi_geni_set_cs;
 
 	/*
@@ -1148,7 +1148,7 @@ static int spi_geni_probe(struct platform_device *pdev)
 	if (ret)
 		goto spi_geni_release_dma;
 
-	ret = spi_register_master(spi);
+	ret = spi_register_controller(spi);
 	if (ret)
 		goto spi_geni_probe_free_irq;
 
@@ -1164,11 +1164,11 @@ spi_geni_probe_runtime_disable:
 
 static void spi_geni_remove(struct platform_device *pdev)
 {
-	struct spi_master *spi = platform_get_drvdata(pdev);
-	struct spi_geni_master *mas = spi_master_get_devdata(spi);
+	struct spi_controller *spi = platform_get_drvdata(pdev);
+	struct spi_geni_master *mas = spi_controller_get_devdata(spi);
 
 	/* Unregister _before_ disabling pm_runtime() so we stop transfers */
-	spi_unregister_master(spi);
+	spi_unregister_controller(spi);
 
 	spi_geni_release_dma_chan(mas);
 
@@ -1178,8 +1178,8 @@ static void spi_geni_remove(struct platform_device *pdev)
 
 static int __maybe_unused spi_geni_runtime_suspend(struct device *dev)
 {
-	struct spi_master *spi = dev_get_drvdata(dev);
-	struct spi_geni_master *mas = spi_master_get_devdata(spi);
+	struct spi_controller *spi = dev_get_drvdata(dev);
+	struct spi_geni_master *mas = spi_controller_get_devdata(spi);
 	int ret;
 
 	/* Drop the performance state vote */
@@ -1194,8 +1194,8 @@ static int __maybe_unused spi_geni_runtime_suspend(struct device *dev)
 
 static int __maybe_unused spi_geni_runtime_resume(struct device *dev)
 {
-	struct spi_master *spi = dev_get_drvdata(dev);
-	struct spi_geni_master *mas = spi_master_get_devdata(spi);
+	struct spi_controller *spi = dev_get_drvdata(dev);
+	struct spi_geni_master *mas = spi_controller_get_devdata(spi);
 	int ret;
 
 	ret = geni_icc_enable(&mas->se);
@@ -1211,30 +1211,30 @@ static int __maybe_unused spi_geni_runtime_resume(struct device *dev)
 
 static int __maybe_unused spi_geni_suspend(struct device *dev)
 {
-	struct spi_master *spi = dev_get_drvdata(dev);
+	struct spi_controller *spi = dev_get_drvdata(dev);
 	int ret;
 
-	ret = spi_master_suspend(spi);
+	ret = spi_controller_suspend(spi);
 	if (ret)
 		return ret;
 
 	ret = pm_runtime_force_suspend(dev);
 	if (ret)
-		spi_master_resume(spi);
+		spi_controller_resume(spi);
 
 	return ret;
 }
 
 static int __maybe_unused spi_geni_resume(struct device *dev)
 {
-	struct spi_master *spi = dev_get_drvdata(dev);
+	struct spi_controller *spi = dev_get_drvdata(dev);
 	int ret;
 
 	ret = pm_runtime_force_resume(dev);
 	if (ret)
 		return ret;
 
-	ret = spi_master_resume(spi);
+	ret = spi_controller_resume(spi);
 	if (ret)
 		pm_runtime_force_suspend(dev);
 
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 498e35c8db2c..272bc871a848 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -659,11 +659,18 @@ static int mx51_ecspi_prepare_transfer(struct spi_imx_data *spi_imx,
 		ctrl |= (spi_imx->target_burst * 8 - 1)
 			<< MX51_ECSPI_CTRL_BL_OFFSET;
 	else {
-		if (spi_imx->count >= 512)
-			ctrl |= 0xFFF << MX51_ECSPI_CTRL_BL_OFFSET;
-		else
-			ctrl |= (spi_imx->count * spi_imx->bits_per_word - 1)
+		if (spi_imx->usedma) {
+			ctrl |= (spi_imx->bits_per_word *
+				spi_imx_bytes_per_word(spi_imx->bits_per_word) - 1)
 				<< MX51_ECSPI_CTRL_BL_OFFSET;
+		} else {
+			if (spi_imx->count >= MX51_ECSPI_CTRL_MAX_BURST)
+				ctrl |= (MX51_ECSPI_CTRL_MAX_BURST - 1)
+						<< MX51_ECSPI_CTRL_BL_OFFSET;
+			else
+				ctrl |= (spi_imx->count * spi_imx->bits_per_word - 1)
+						<< MX51_ECSPI_CTRL_BL_OFFSET;
+		}
 	}
 
 	/* set clock speed */
diff --git a/drivers/spi/spi-ingenic.c b/drivers/spi/spi-ingenic.c
index cc366936d72b..003a6d21c4c3 100644
--- a/drivers/spi/spi-ingenic.c
+++ b/drivers/spi/spi-ingenic.c
@@ -346,14 +346,17 @@ static bool spi_ingenic_can_dma(struct spi_controller *ctlr,
 static int spi_ingenic_request_dma(struct spi_controller *ctlr,
 				   struct device *dev)
 {
-	ctlr->dma_tx = dma_request_slave_channel(dev, "tx");
-	if (!ctlr->dma_tx)
-		return -ENODEV;
+	struct dma_chan *chan;
 
-	ctlr->dma_rx = dma_request_slave_channel(dev, "rx");
+	chan = dma_request_chan(dev, "tx");
+	if (IS_ERR(chan))
+		return PTR_ERR(chan);
+	ctlr->dma_tx = chan;
 
-	if (!ctlr->dma_rx)
-		return -ENODEV;
+	chan = dma_request_chan(dev, "rx");
+	if (IS_ERR(chan))
+		return PTR_ERR(chan);
+	ctlr->dma_rx = chan;
 
 	ctlr->can_dma = spi_ingenic_can_dma;
 
diff --git a/drivers/spi/spi-intel.c b/drivers/spi/spi-intel.c
index 98ec4dc22b81..3654ae35d2db 100644
--- a/drivers/spi/spi-intel.c
+++ b/drivers/spi/spi-intel.c
@@ -711,8 +711,7 @@ static bool intel_spi_cmp_mem_op(const struct intel_spi_mem_op *iop,
 {
 	if (iop->mem_op.cmd.nbytes != op->cmd.nbytes ||
 	    iop->mem_op.cmd.buswidth != op->cmd.buswidth ||
-	    iop->mem_op.cmd.dtr != op->cmd.dtr ||
-	    iop->mem_op.cmd.opcode != op->cmd.opcode)
+	    iop->mem_op.cmd.dtr != op->cmd.dtr)
 		return false;
 
 	if (iop->mem_op.addr.nbytes != op->addr.nbytes ||
@@ -737,11 +736,12 @@ intel_spi_match_mem_op(struct intel_spi *ispi, const struct spi_mem_op *op)
 	const struct intel_spi_mem_op *iop;
 
 	for (iop = ispi->mem_ops; iop->mem_op.cmd.opcode; iop++) {
-		if (intel_spi_cmp_mem_op(iop, op))
-			break;
+		if (iop->mem_op.cmd.opcode == op->cmd.opcode &&
+		    intel_spi_cmp_mem_op(iop, op))
+			return iop;
 	}
 
-	return iop->mem_op.cmd.opcode ? iop : NULL;
+	return NULL;
 }
 
 static bool intel_spi_supports_mem_op(struct spi_mem *mem,
diff --git a/drivers/spi/spi-ljca.c b/drivers/spi/spi-ljca.c
index c5a066c73817..1cc1422ddba0 100644
--- a/drivers/spi/spi-ljca.c
+++ b/drivers/spi/spi-ljca.c
@@ -223,7 +223,7 @@ static int ljca_spi_probe(struct auxiliary_device *auxdev,
 	struct ljca_spi_dev *ljca_spi;
 	int ret;
 
-	controller = devm_spi_alloc_master(&auxdev->dev, sizeof(*ljca_spi));
+	controller = devm_spi_alloc_host(&auxdev->dev, sizeof(*ljca_spi));
 	if (!controller)
 		return -ENOMEM;
 
diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index edd7430d4c05..2dc8ceb85374 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -323,7 +323,7 @@ int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 		return ret;
 
 	if (!spi_mem_internal_supports_op(mem, op))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (ctlr->mem_ops && ctlr->mem_ops->exec_op && !spi_get_csgpiod(mem->spi, 0)) {
 		ret = spi_mem_access_start(mem);
@@ -339,7 +339,7 @@ int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 		 * read path) and expect the core to use the regular SPI
 		 * interface in other cases.
 		 */
-		if (!ret || ret != -ENOTSUPP)
+		if (!ret || ret != -ENOTSUPP || ret != -EOPNOTSUPP)
 			return ret;
 	}
 
@@ -559,7 +559,7 @@ spi_mem_dirmap_create(struct spi_mem *mem,
 	if (ret) {
 		desc->nodirmap = true;
 		if (!spi_mem_supports_op(desc->mem, &desc->info.op_tmpl))
-			ret = -ENOTSUPP;
+			ret = -EOPNOTSUPP;
 		else
 			ret = 0;
 	}
diff --git a/drivers/spi/spi-mpc52xx.c b/drivers/spi/spi-mpc52xx.c
index 4a6c984b6bff..d5ac60c135c2 100644
--- a/drivers/spi/spi-mpc52xx.c
+++ b/drivers/spi/spi-mpc52xx.c
@@ -22,6 +22,7 @@
 #include <linux/slab.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/platform_device.h>
 
 #include <asm/time.h>
 #include <asm/mpc52xx.h>
diff --git a/drivers/spi/spi-npcm-fiu.c b/drivers/spi/spi-npcm-fiu.c
index 03db9f016a11..f3bb8bbc192f 100644
--- a/drivers/spi/spi-npcm-fiu.c
+++ b/drivers/spi/spi-npcm-fiu.c
@@ -556,7 +556,7 @@ static int npcm_fiu_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 		op->data.nbytes);
 
 	if (fiu->spix_mode || op->addr.nbytes > 4)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (fiu->clkrate != chip->clkrate) {
 		ret = clk_set_rate(fiu->clk, chip->clkrate);
diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c
index d1b6110b38fc..de63cf0557ce 100644
--- a/drivers/spi/spi-pl022.c
+++ b/drivers/spi/spi-pl022.c
@@ -338,14 +338,8 @@ struct vendor_data {
  * @clk: outgoing clock "SPICLK" for the SPI bus
  * @host: SPI framework hookup
  * @host_info: controller-specific data from machine setup
- * @pump_transfers: Tasklet used in Interrupt Transfer mode
- * @cur_msg: Pointer to current spi_message being processed
  * @cur_transfer: Pointer to current spi_transfer
  * @cur_chip: pointer to current clients chip(assigned from controller_state)
- * @next_msg_cs_active: the next message in the queue has been examined
- *  and it was found that it uses the same chip select as the previous
- *  message, so we left it active after the previous transfer, and it's
- *  active already.
  * @tx: current position in TX buffer to be read
  * @tx_end: end position in TX buffer to be read
  * @rx: current position in RX buffer to be written
@@ -362,7 +356,6 @@ struct vendor_data {
  * @dummypage: a dummy page used for driving data on the bus with DMA
  * @dma_running: indicates whether DMA is in operation
  * @cur_cs: current chip select index
- * @cur_gpiod: current chip select GPIO descriptor
  */
 struct pl022 {
 	struct amba_device		*adev;
@@ -372,12 +365,8 @@ struct pl022 {
 	struct clk			*clk;
 	struct spi_controller		*host;
 	struct pl022_ssp_controller	*host_info;
-	/* Message per-transfer pump */
-	struct tasklet_struct		pump_transfers;
-	struct spi_message		*cur_msg;
 	struct spi_transfer		*cur_transfer;
 	struct chip_data		*cur_chip;
-	bool				next_msg_cs_active;
 	void				*tx;
 	void				*tx_end;
 	void				*rx;
@@ -397,7 +386,6 @@ struct pl022 {
 	bool				dma_running;
 #endif
 	int cur_cs;
-	struct gpio_desc *cur_gpiod;
 };
 
 /**
@@ -431,99 +419,29 @@ struct chip_data {
 /**
  * internal_cs_control - Control chip select signals via SSP_CSR.
  * @pl022: SSP driver private data structure
- * @command: select/delect the chip
+ * @enable: select/delect the chip
  *
  * Used on controller with internal chip select control via SSP_CSR register
  * (vendor extension). Each of the 5 LSB in the register controls one chip
  * select signal.
  */
-static void internal_cs_control(struct pl022 *pl022, u32 command)
+static void internal_cs_control(struct pl022 *pl022, bool enable)
 {
 	u32 tmp;
 
 	tmp = readw(SSP_CSR(pl022->virtbase));
-	if (command == SSP_CHIP_SELECT)
+	if (enable)
 		tmp &= ~BIT(pl022->cur_cs);
 	else
 		tmp |= BIT(pl022->cur_cs);
 	writew(tmp, SSP_CSR(pl022->virtbase));
 }
 
-static void pl022_cs_control(struct pl022 *pl022, u32 command)
+static void pl022_cs_control(struct spi_device *spi, bool enable)
 {
+	struct pl022 *pl022 = spi_controller_get_devdata(spi->controller);
 	if (pl022->vendor->internal_cs_ctrl)
-		internal_cs_control(pl022, command);
-	else if (pl022->cur_gpiod)
-		/*
-		 * This needs to be inverted since with GPIOLIB in
-		 * control, the inversion will be handled by
-		 * GPIOLIB's active low handling. The "command"
-		 * passed into this function will be SSP_CHIP_SELECT
-		 * which is enum:ed to 0, so we need the inverse
-		 * (1) to activate chip select.
-		 */
-		gpiod_set_value(pl022->cur_gpiod, !command);
-}
-
-/**
- * giveback - current spi_message is over, schedule next message and call
- * callback of this message. Assumes that caller already
- * set message->status; dma and pio irqs are blocked
- * @pl022: SSP driver private data structure
- */
-static void giveback(struct pl022 *pl022)
-{
-	struct spi_transfer *last_transfer;
-	pl022->next_msg_cs_active = false;
-
-	last_transfer = list_last_entry(&pl022->cur_msg->transfers,
-					struct spi_transfer, transfer_list);
-
-	/* Delay if requested before any change in chip select */
-	/*
-	 * FIXME: This runs in interrupt context.
-	 * Is this really smart?
-	 */
-	spi_transfer_delay_exec(last_transfer);
-
-	if (!last_transfer->cs_change) {
-		struct spi_message *next_msg;
-
-		/*
-		 * cs_change was not set. We can keep the chip select
-		 * enabled if there is message in the queue and it is
-		 * for the same spi device.
-		 *
-		 * We cannot postpone this until pump_messages, because
-		 * after calling msg->complete (below) the driver that
-		 * sent the current message could be unloaded, which
-		 * could invalidate the cs_control() callback...
-		 */
-		/* get a pointer to the next message, if any */
-		next_msg = spi_get_next_queued_message(pl022->host);
-
-		/*
-		 * see if the next and current messages point
-		 * to the same spi device.
-		 */
-		if (next_msg && next_msg->spi != pl022->cur_msg->spi)
-			next_msg = NULL;
-		if (!next_msg || pl022->cur_msg->state == STATE_ERROR)
-			pl022_cs_control(pl022, SSP_CHIP_DESELECT);
-		else
-			pl022->next_msg_cs_active = true;
-
-	}
-
-	pl022->cur_msg = NULL;
-	pl022->cur_transfer = NULL;
-	pl022->cur_chip = NULL;
-
-	/* disable the SPI/SSP operation */
-	writew((readw(SSP_CR1(pl022->virtbase)) &
-		(~SSP_CR1_MASK_SSE)), SSP_CR1(pl022->virtbase));
-
-	spi_finalize_current_message(pl022->host);
+		internal_cs_control(pl022, enable);
 }
 
 /**
@@ -757,30 +675,6 @@ static void readwriter(struct pl022 *pl022)
 	 */
 }
 
-/**
- * next_transfer - Move to the Next transfer in the current spi message
- * @pl022: SSP driver private data structure
- *
- * This function moves though the linked list of spi transfers in the
- * current spi message and returns with the state of current spi
- * message i.e whether its last transfer is done(STATE_DONE) or
- * Next transfer is ready(STATE_RUNNING)
- */
-static void *next_transfer(struct pl022 *pl022)
-{
-	struct spi_message *msg = pl022->cur_msg;
-	struct spi_transfer *trans = pl022->cur_transfer;
-
-	/* Move to next transfer */
-	if (trans->transfer_list.next != &msg->transfers) {
-		pl022->cur_transfer =
-		    list_entry(trans->transfer_list.next,
-			       struct spi_transfer, transfer_list);
-		return STATE_RUNNING;
-	}
-	return STATE_DONE;
-}
-
 /*
  * This DMA functionality is only compiled in if we have
  * access to the generic DMA devices/DMA engine.
@@ -800,7 +694,6 @@ static void unmap_free_dma_scatter(struct pl022 *pl022)
 static void dma_callback(void *data)
 {
 	struct pl022 *pl022 = data;
-	struct spi_message *msg = pl022->cur_msg;
 
 	BUG_ON(!pl022->sgt_rx.sgl);
 
@@ -845,13 +738,7 @@ static void dma_callback(void *data)
 
 	unmap_free_dma_scatter(pl022);
 
-	/* Update total bytes transferred */
-	msg->actual_length += pl022->cur_transfer->len;
-	/* Move to next transfer */
-	msg->state = next_transfer(pl022);
-	if (msg->state != STATE_DONE && pl022->cur_transfer->cs_change)
-		pl022_cs_control(pl022, SSP_CHIP_DESELECT);
-	tasklet_schedule(&pl022->pump_transfers);
+	spi_finalize_current_transfer(pl022->host);
 }
 
 static void setup_dma_scatter(struct pl022 *pl022,
@@ -1189,6 +1076,9 @@ err_no_rxchan:
 
 static void terminate_dma(struct pl022 *pl022)
 {
+	if (!pl022->dma_running)
+		return;
+
 	struct dma_chan *rxchan = pl022->dma_rx_channel;
 	struct dma_chan *txchan = pl022->dma_tx_channel;
 
@@ -1200,8 +1090,7 @@ static void terminate_dma(struct pl022 *pl022)
 
 static void pl022_dma_remove(struct pl022 *pl022)
 {
-	if (pl022->dma_running)
-		terminate_dma(pl022);
+	terminate_dma(pl022);
 	if (pl022->dma_tx_channel)
 		dma_release_channel(pl022->dma_tx_channel);
 	if (pl022->dma_rx_channel)
@@ -1225,6 +1114,10 @@ static inline int pl022_dma_probe(struct pl022 *pl022)
 	return 0;
 }
 
+static inline void terminate_dma(struct pl022 *pl022)
+{
+}
+
 static inline void pl022_dma_remove(struct pl022 *pl022)
 {
 }
@@ -1246,16 +1139,7 @@ static inline void pl022_dma_remove(struct pl022 *pl022)
 static irqreturn_t pl022_interrupt_handler(int irq, void *dev_id)
 {
 	struct pl022 *pl022 = dev_id;
-	struct spi_message *msg = pl022->cur_msg;
 	u16 irq_status = 0;
-
-	if (unlikely(!msg)) {
-		dev_err(&pl022->adev->dev,
-			"bad message state in interrupt handler");
-		/* Never fail */
-		return IRQ_HANDLED;
-	}
-
 	/* Read the Interrupt Status Register */
 	irq_status = readw(SSP_MIS(pl022->virtbase));
 
@@ -1287,10 +1171,8 @@ static irqreturn_t pl022_interrupt_handler(int irq, void *dev_id)
 		writew(CLEAR_ALL_INTERRUPTS, SSP_ICR(pl022->virtbase));
 		writew((readw(SSP_CR1(pl022->virtbase)) &
 			(~SSP_CR1_MASK_SSE)), SSP_CR1(pl022->virtbase));
-		msg->state = STATE_ERROR;
-
-		/* Schedule message queue handler */
-		tasklet_schedule(&pl022->pump_transfers);
+		pl022->cur_transfer->error |= SPI_TRANS_FAIL_IO;
+		spi_finalize_current_transfer(pl022->host);
 		return IRQ_HANDLED;
 	}
 
@@ -1318,13 +1200,7 @@ static irqreturn_t pl022_interrupt_handler(int irq, void *dev_id)
 				 "number of bytes on a 16bit bus?)\n",
 				 (u32) (pl022->rx - pl022->rx_end));
 		}
-		/* Update total bytes transferred */
-		msg->actual_length += pl022->cur_transfer->len;
-		/* Move to next transfer */
-		msg->state = next_transfer(pl022);
-		if (msg->state != STATE_DONE && pl022->cur_transfer->cs_change)
-			pl022_cs_control(pl022, SSP_CHIP_DESELECT);
-		tasklet_schedule(&pl022->pump_transfers);
+		spi_finalize_current_transfer(pl022->host);
 		return IRQ_HANDLED;
 	}
 
@@ -1361,98 +1237,20 @@ static int set_up_next_transfer(struct pl022 *pl022,
 	return 0;
 }
 
-/**
- * pump_transfers - Tasklet function which schedules next transfer
- * when running in interrupt or DMA transfer mode.
- * @data: SSP driver private data structure
- *
- */
-static void pump_transfers(unsigned long data)
+static int do_interrupt_dma_transfer(struct pl022 *pl022)
 {
-	struct pl022 *pl022 = (struct pl022 *) data;
-	struct spi_message *message = NULL;
-	struct spi_transfer *transfer = NULL;
-	struct spi_transfer *previous = NULL;
-
-	/* Get current state information */
-	message = pl022->cur_msg;
-	transfer = pl022->cur_transfer;
-
-	/* Handle for abort */
-	if (message->state == STATE_ERROR) {
-		message->status = -EIO;
-		giveback(pl022);
-		return;
-	}
-
-	/* Handle end of message */
-	if (message->state == STATE_DONE) {
-		message->status = 0;
-		giveback(pl022);
-		return;
-	}
-
-	/* Delay if requested at end of transfer before CS change */
-	if (message->state == STATE_RUNNING) {
-		previous = list_entry(transfer->transfer_list.prev,
-					struct spi_transfer,
-					transfer_list);
-		/*
-		 * FIXME: This runs in interrupt context.
-		 * Is this really smart?
-		 */
-		spi_transfer_delay_exec(previous);
-
-		/* Reselect chip select only if cs_change was requested */
-		if (previous->cs_change)
-			pl022_cs_control(pl022, SSP_CHIP_SELECT);
-	} else {
-		/* STATE_START */
-		message->state = STATE_RUNNING;
-	}
-
-	if (set_up_next_transfer(pl022, transfer)) {
-		message->state = STATE_ERROR;
-		message->status = -EIO;
-		giveback(pl022);
-		return;
-	}
-	/* Flush the FIFOs and let's go! */
-	flush(pl022);
-
-	if (pl022->cur_chip->enable_dma) {
-		if (configure_dma(pl022)) {
-			dev_dbg(&pl022->adev->dev,
-				"configuration of DMA failed, fall back to interrupt mode\n");
-			goto err_config_dma;
-		}
-		return;
-	}
-
-err_config_dma:
-	/* enable all interrupts except RX */
-	writew(ENABLE_ALL_INTERRUPTS & ~SSP_IMSC_MASK_RXIM, SSP_IMSC(pl022->virtbase));
-}
+	int ret;
 
-static void do_interrupt_dma_transfer(struct pl022 *pl022)
-{
 	/*
 	 * Default is to enable all interrupts except RX -
 	 * this will be enabled once TX is complete
 	 */
 	u32 irqflags = (u32)(ENABLE_ALL_INTERRUPTS & ~SSP_IMSC_MASK_RXIM);
 
-	/* Enable target chip, if not already active */
-	if (!pl022->next_msg_cs_active)
-		pl022_cs_control(pl022, SSP_CHIP_SELECT);
+	ret = set_up_next_transfer(pl022, pl022->cur_transfer);
+	if (ret)
+		return ret;
 
-	if (set_up_next_transfer(pl022, pl022->cur_transfer)) {
-		/* Error path */
-		pl022->cur_msg->state = STATE_ERROR;
-		pl022->cur_msg->status = -EIO;
-		giveback(pl022);
-		return;
-	}
 	/* If we're using DMA, set up DMA here */
 	if (pl022->cur_chip->enable_dma) {
 		/* Configure DMA transfer */
@@ -1469,6 +1267,7 @@ err_config_dma:
 	writew((readw(SSP_CR1(pl022->virtbase)) | SSP_CR1_MASK_SSE),
 	       SSP_CR1(pl022->virtbase));
 	writew(irqflags, SSP_IMSC(pl022->virtbase));
+	return 1;
 }
 
 static void print_current_status(struct pl022 *pl022)
@@ -1495,111 +1294,65 @@ static void print_current_status(struct pl022 *pl022)
 
 }
 
-static void do_polling_transfer(struct pl022 *pl022)
+static int do_polling_transfer(struct pl022 *pl022)
 {
-	struct spi_message *message = NULL;
-	struct spi_transfer *transfer = NULL;
-	struct spi_transfer *previous = NULL;
+	int ret;
 	unsigned long time, timeout;
 
-	message = pl022->cur_msg;
-
-	while (message->state != STATE_DONE) {
-		/* Handle for abort */
-		if (message->state == STATE_ERROR)
-			break;
-		transfer = pl022->cur_transfer;
-
-		/* Delay if requested at end of transfer */
-		if (message->state == STATE_RUNNING) {
-			previous =
-			    list_entry(transfer->transfer_list.prev,
-				       struct spi_transfer, transfer_list);
-			spi_transfer_delay_exec(previous);
-			if (previous->cs_change)
-				pl022_cs_control(pl022, SSP_CHIP_SELECT);
-		} else {
-			/* STATE_START */
-			message->state = STATE_RUNNING;
-			if (!pl022->next_msg_cs_active)
-				pl022_cs_control(pl022, SSP_CHIP_SELECT);
-		}
-
-		/* Configuration Changing Per Transfer */
-		if (set_up_next_transfer(pl022, transfer)) {
-			/* Error path */
-			message->state = STATE_ERROR;
-			break;
-		}
-		/* Flush FIFOs and enable SSP */
-		flush(pl022);
-		writew((readw(SSP_CR1(pl022->virtbase)) | SSP_CR1_MASK_SSE),
-		       SSP_CR1(pl022->virtbase));
-
-		dev_dbg(&pl022->adev->dev, "polling transfer ongoing ...\n");
-
-		timeout = jiffies + msecs_to_jiffies(SPI_POLLING_TIMEOUT);
-		while (pl022->tx < pl022->tx_end || pl022->rx < pl022->rx_end) {
-			time = jiffies;
-			readwriter(pl022);
-			if (time_after(time, timeout)) {
-				dev_warn(&pl022->adev->dev,
-				"%s: timeout!\n", __func__);
-				message->state = STATE_TIMEOUT;
-				print_current_status(pl022);
-				goto out;
-			}
-			cpu_relax();
+	/* Configuration Changing Per Transfer */
+	ret = set_up_next_transfer(pl022, pl022->cur_transfer);
+	if (ret)
+		return ret;
+	/* Flush FIFOs and enable SSP */
+	flush(pl022);
+	writew((readw(SSP_CR1(pl022->virtbase)) | SSP_CR1_MASK_SSE),
+		SSP_CR1(pl022->virtbase));
+
+	dev_dbg(&pl022->adev->dev, "polling transfer ongoing ...\n");
+
+	timeout = jiffies + msecs_to_jiffies(SPI_POLLING_TIMEOUT);
+	while (pl022->tx < pl022->tx_end || pl022->rx < pl022->rx_end) {
+		time = jiffies;
+		readwriter(pl022);
+		if (time_after(time, timeout)) {
+			dev_warn(&pl022->adev->dev,
+			"%s: timeout!\n", __func__);
+			print_current_status(pl022);
+			return -ETIMEDOUT;
 		}
-
-		/* Update total byte transferred */
-		message->actual_length += pl022->cur_transfer->len;
-		/* Move to next transfer */
-		message->state = next_transfer(pl022);
-		if (message->state != STATE_DONE
-		    && pl022->cur_transfer->cs_change)
-			pl022_cs_control(pl022, SSP_CHIP_DESELECT);
+		cpu_relax();
 	}
-out:
-	/* Handle end of message */
-	if (message->state == STATE_DONE)
-		message->status = 0;
-	else if (message->state == STATE_TIMEOUT)
-		message->status = -EAGAIN;
-	else
-		message->status = -EIO;
 
-	giveback(pl022);
-	return;
+	return 0;
 }
 
-static int pl022_transfer_one_message(struct spi_controller *host,
-				      struct spi_message *msg)
+static int pl022_transfer_one(struct spi_controller *host, struct spi_device *spi,
+			      struct spi_transfer *transfer)
 {
 	struct pl022 *pl022 = spi_controller_get_devdata(host);
 
-	/* Initial message state */
-	pl022->cur_msg = msg;
-	msg->state = STATE_START;
-
-	pl022->cur_transfer = list_entry(msg->transfers.next,
-					 struct spi_transfer, transfer_list);
+	pl022->cur_transfer = transfer;
 
 	/* Setup the SPI using the per chip configuration */
-	pl022->cur_chip = spi_get_ctldata(msg->spi);
-	pl022->cur_cs = spi_get_chipselect(msg->spi, 0);
-	/* This is always available but may be set to -ENOENT */
-	pl022->cur_gpiod = spi_get_csgpiod(msg->spi, 0);
+	pl022->cur_chip = spi_get_ctldata(spi);
+	pl022->cur_cs = spi_get_chipselect(spi, 0);
 
 	restore_state(pl022);
 	flush(pl022);
 
 	if (pl022->cur_chip->xfer_type == POLLING_TRANSFER)
-		do_polling_transfer(pl022);
+		return do_polling_transfer(pl022);
 	else
-		do_interrupt_dma_transfer(pl022);
+		return do_interrupt_dma_transfer(pl022);
+}
 
-	return 0;
+static void pl022_handle_err(struct spi_controller *ctlr, struct spi_message *message)
+{
+	struct pl022 *pl022 = spi_controller_get_devdata(ctlr);
+
+	terminate_dma(pl022);
+	writew(DISABLE_ALL_INTERRUPTS, SSP_IMSC(pl022->virtbase));
+	writew(CLEAR_ALL_INTERRUPTS, SSP_ICR(pl022->virtbase));
 }
 
 static int pl022_unprepare_transfer_hardware(struct spi_controller *host)
@@ -2138,7 +1891,9 @@ static int pl022_probe(struct amba_device *adev, const struct amba_id *id)
 	host->cleanup = pl022_cleanup;
 	host->setup = pl022_setup;
 	host->auto_runtime_pm = true;
-	host->transfer_one_message = pl022_transfer_one_message;
+	host->transfer_one = pl022_transfer_one;
+	host->set_cs = pl022_cs_control;
+	host->handle_err = pl022_handle_err;
 	host->unprepare_transfer_hardware = pl022_unprepare_transfer_hardware;
 	host->rt = platform_info->rt;
 	host->dev.of_node = dev->of_node;
@@ -2175,10 +1930,6 @@ static int pl022_probe(struct amba_device *adev, const struct amba_id *id)
 		goto err_no_clk;
 	}
 
-	/* Initialize transfer pump */
-	tasklet_init(&pl022->pump_transfers, pump_transfers,
-		     (unsigned long)pl022);
-
 	/* Disable SSP */
 	writew((readw(SSP_CR1(pl022->virtbase)) & (~SSP_CR1_MASK_SSE)),
 	       SSP_CR1(pl022->virtbase));
@@ -2261,7 +2012,6 @@ pl022_remove(struct amba_device *adev)
 		pl022_dma_remove(pl022);
 
 	amba_release_regions(adev);
-	tasklet_disable(&pl022->pump_transfers);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index fb452bc78372..cfc3b1ddbd22 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -29,12 +29,15 @@
 
 #include <asm/unaligned.h>
 
+#define SH_MSIOF_FLAG_FIXED_DTDL_200	BIT(0)
+
 struct sh_msiof_chipdata {
 	u32 bits_per_word_mask;
 	u16 tx_fifo_size;
 	u16 rx_fifo_size;
 	u16 ctlr_flags;
 	u16 min_div_pow;
+	u32 flags;
 };
 
 struct sh_msiof_spi_priv {
@@ -1072,6 +1075,16 @@ static const struct sh_msiof_chipdata rcar_gen3_data = {
 	.min_div_pow = 1,
 };
 
+static const struct sh_msiof_chipdata rcar_r8a7795_data = {
+	.bits_per_word_mask = SPI_BPW_MASK(8) | SPI_BPW_MASK(16) |
+			      SPI_BPW_MASK(24) | SPI_BPW_MASK(32),
+	.tx_fifo_size = 64,
+	.rx_fifo_size = 64,
+	.ctlr_flags = SPI_CONTROLLER_MUST_TX,
+	.min_div_pow = 1,
+	.flags = SH_MSIOF_FLAG_FIXED_DTDL_200,
+};
+
 static const struct of_device_id sh_msiof_match[] __maybe_unused = {
 	{ .compatible = "renesas,sh-mobile-msiof", .data = &sh_data },
 	{ .compatible = "renesas,msiof-r8a7743",   .data = &rcar_gen2_data },
@@ -1082,6 +1095,7 @@ static const struct of_device_id sh_msiof_match[] __maybe_unused = {
 	{ .compatible = "renesas,msiof-r8a7793",   .data = &rcar_gen2_data },
 	{ .compatible = "renesas,msiof-r8a7794",   .data = &rcar_gen2_data },
 	{ .compatible = "renesas,rcar-gen2-msiof", .data = &rcar_gen2_data },
+	{ .compatible = "renesas,msiof-r8a7795",   .data = &rcar_r8a7795_data },
 	{ .compatible = "renesas,msiof-r8a7796",   .data = &rcar_gen3_data },
 	{ .compatible = "renesas,rcar-gen3-msiof", .data = &rcar_gen3_data },
 	{ .compatible = "renesas,rcar-gen4-msiof", .data = &rcar_gen3_data },
@@ -1279,6 +1293,9 @@ static int sh_msiof_spi_probe(struct platform_device *pdev)
 		return -ENXIO;
 	}
 
+	if (chipdata->flags & SH_MSIOF_FLAG_FIXED_DTDL_200)
+		info->dtdl = 200;
+
 	if (info->mode == MSIOF_SPI_TARGET)
 		ctlr = spi_alloc_target(&pdev->dev,
 				        sizeof(struct sh_msiof_spi_priv));
diff --git a/drivers/spi/spi-sprd-adi.c b/drivers/spi/spi-sprd-adi.c
index bf01feedbf93..262c11d977ea 100644
--- a/drivers/spi/spi-sprd-adi.c
+++ b/drivers/spi/spi-sprd-adi.c
@@ -138,8 +138,7 @@ struct sprd_adi_data {
 	u32 slave_offset;
 	u32 slave_addr_size;
 	int (*read_check)(u32 val, u32 reg);
-	int (*restart)(struct notifier_block *this,
-		       unsigned long mode, void *cmd);
+	int (*restart)(struct sys_off_data *data);
 	void (*wdg_rst)(void *p);
 };
 
@@ -150,7 +149,6 @@ struct sprd_adi {
 	struct hwspinlock	*hwlock;
 	unsigned long		slave_vbase;
 	unsigned long		slave_pbase;
-	struct notifier_block	restart_handler;
 	const struct sprd_adi_data *data;
 };
 
@@ -370,11 +368,9 @@ static void sprd_adi_set_wdt_rst_mode(void *p)
 #endif
 }
 
-static int sprd_adi_restart(struct notifier_block *this, unsigned long mode,
-				  void *cmd, struct sprd_adi_wdg *wdg)
+static int sprd_adi_restart(struct sprd_adi *sadi, unsigned long mode,
+			    const char *cmd, struct sprd_adi_wdg *wdg)
 {
-	struct sprd_adi *sadi = container_of(this, struct sprd_adi,
-					     restart_handler);
 	u32 val, reboot_mode = 0;
 
 	if (!cmd)
@@ -448,8 +444,7 @@ static int sprd_adi_restart(struct notifier_block *this, unsigned long mode,
 	return NOTIFY_DONE;
 }
 
-static int sprd_adi_restart_sc9860(struct notifier_block *this,
-					   unsigned long mode, void *cmd)
+static int sprd_adi_restart_sc9860(struct sys_off_data *data)
 {
 	struct sprd_adi_wdg wdg = {
 		.base = PMIC_WDG_BASE,
@@ -458,7 +453,7 @@ static int sprd_adi_restart_sc9860(struct notifier_block *this,
 		.wdg_clk = PMIC_CLK_EN,
 	};
 
-	return sprd_adi_restart(this, mode, cmd, &wdg);
+	return sprd_adi_restart(data->cb_data, data->mode, data->cmd, &wdg);
 }
 
 static void sprd_adi_hw_init(struct sprd_adi *sadi)
@@ -533,7 +528,7 @@ static int sprd_adi_probe(struct platform_device *pdev)
 	pdev->id = of_alias_get_id(np, "spi");
 	num_chipselect = of_get_child_count(np);
 
-	ctlr = spi_alloc_master(&pdev->dev, sizeof(struct sprd_adi));
+	ctlr = spi_alloc_host(&pdev->dev, sizeof(struct sprd_adi));
 	if (!ctlr)
 		return -ENOMEM;
 
@@ -590,9 +585,9 @@ static int sprd_adi_probe(struct platform_device *pdev)
 	}
 
 	if (sadi->data->restart) {
-		sadi->restart_handler.notifier_call = sadi->data->restart;
-		sadi->restart_handler.priority = 128;
-		ret = register_restart_handler(&sadi->restart_handler);
+		ret = devm_register_restart_handler(&pdev->dev,
+						    sadi->data->restart,
+						    sadi);
 		if (ret) {
 			dev_err(&pdev->dev, "can not register restart handler\n");
 			goto put_ctlr;
@@ -606,14 +601,6 @@ put_ctlr:
 	return ret;
 }
 
-static void sprd_adi_remove(struct platform_device *pdev)
-{
-	struct spi_controller *ctlr = dev_get_drvdata(&pdev->dev);
-	struct sprd_adi *sadi = spi_controller_get_devdata(ctlr);
-
-	unregister_restart_handler(&sadi->restart_handler);
-}
-
 static struct sprd_adi_data sc9860_data = {
 	.slave_offset = ADI_10BIT_SLAVE_OFFSET,
 	.slave_addr_size = ADI_10BIT_SLAVE_ADDR_SIZE,
@@ -657,7 +644,6 @@ static struct platform_driver sprd_adi_driver = {
 		.of_match_table = sprd_adi_of_match,
 	},
 	.probe = sprd_adi_probe,
-	.remove_new = sprd_adi_remove,
 };
 module_platform_driver(sprd_adi_driver);
 
diff --git a/drivers/spi/spi-sprd.c b/drivers/spi/spi-sprd.c
index 95377cf748c0..831ebae10fe0 100644
--- a/drivers/spi/spi-sprd.c
+++ b/drivers/spi/spi-sprd.c
@@ -578,7 +578,7 @@ static void sprd_spi_dma_release(struct sprd_spi *ss)
 static int sprd_spi_dma_txrx_bufs(struct spi_device *sdev,
 				  struct spi_transfer *t)
 {
-	struct sprd_spi *ss = spi_master_get_devdata(sdev->master);
+	struct sprd_spi *ss = spi_controller_get_devdata(sdev->controller);
 	u32 trans_len = ss->trans_len;
 	int ret, write_size = 0;
 
@@ -923,7 +923,7 @@ static int sprd_spi_probe(struct platform_device *pdev)
 	int ret;
 
 	pdev->id = of_alias_get_id(pdev->dev.of_node, "spi");
-	sctlr = spi_alloc_master(&pdev->dev, sizeof(*ss));
+	sctlr = spi_alloc_host(&pdev->dev, sizeof(*ss));
 	if (!sctlr)
 		return -ENOMEM;
 
diff --git a/drivers/spi/spi-st-ssc4.c b/drivers/spi/spi-st-ssc4.c
index 7fcff9c539e2..e064025e2fd6 100644
--- a/drivers/spi/spi-st-ssc4.c
+++ b/drivers/spi/spi-st-ssc4.c
@@ -6,7 +6,7 @@
  *          Patrice Chotard <patrice.chotard@st.com>
  *          Lee Jones <lee.jones@linaro.org>
  *
- *  SPI master mode controller driver, used in STMicroelectronics devices.
+ *  SPI host mode controller driver, used in STMicroelectronics devices.
  */
 
 #include <linux/clk.h>
@@ -115,10 +115,10 @@ static void ssc_read_rx_fifo(struct spi_st *spi_st)
 	spi_st->words_remaining -= count;
 }
 
-static int spi_st_transfer_one(struct spi_master *master,
+static int spi_st_transfer_one(struct spi_controller *host,
 			       struct spi_device *spi, struct spi_transfer *t)
 {
-	struct spi_st *spi_st = spi_master_get_devdata(master);
+	struct spi_st *spi_st = spi_controller_get_devdata(host);
 	uint32_t ctl = 0;
 
 	/* Setup transfer */
@@ -165,7 +165,7 @@ static int spi_st_transfer_one(struct spi_master *master,
 	if (ctl)
 		writel_relaxed(ctl, spi_st->base + SSC_CTL);
 
-	spi_finalize_current_transfer(spi->master);
+	spi_finalize_current_transfer(spi->controller);
 
 	return t->len;
 }
@@ -174,7 +174,7 @@ static int spi_st_transfer_one(struct spi_master *master,
 #define MODEBITS  (SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST | SPI_LOOP | SPI_CS_HIGH)
 static int spi_st_setup(struct spi_device *spi)
 {
-	struct spi_st *spi_st = spi_master_get_devdata(spi->master);
+	struct spi_st *spi_st = spi_controller_get_devdata(spi->controller);
 	u32 spi_st_clk, sscbrg, var;
 	u32 hz = spi->max_speed_hz;
 
@@ -274,35 +274,35 @@ static irqreturn_t spi_st_irq(int irq, void *dev_id)
 static int spi_st_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
-	struct spi_master *master;
+	struct spi_controller *host;
 	struct spi_st *spi_st;
 	int irq, ret = 0;
 	u32 var;
 
-	master = spi_alloc_master(&pdev->dev, sizeof(*spi_st));
-	if (!master)
+	host = spi_alloc_host(&pdev->dev, sizeof(*spi_st));
+	if (!host)
 		return -ENOMEM;
 
-	master->dev.of_node		= np;
-	master->mode_bits		= MODEBITS;
-	master->setup			= spi_st_setup;
-	master->transfer_one		= spi_st_transfer_one;
-	master->bits_per_word_mask	= SPI_BPW_MASK(8) | SPI_BPW_MASK(16);
-	master->auto_runtime_pm		= true;
-	master->bus_num			= pdev->id;
-	master->use_gpio_descriptors	= true;
-	spi_st				= spi_master_get_devdata(master);
+	host->dev.of_node		= np;
+	host->mode_bits			= MODEBITS;
+	host->setup			= spi_st_setup;
+	host->transfer_one		= spi_st_transfer_one;
+	host->bits_per_word_mask	= SPI_BPW_MASK(8) | SPI_BPW_MASK(16);
+	host->auto_runtime_pm		= true;
+	host->bus_num			= pdev->id;
+	host->use_gpio_descriptors	= true;
+	spi_st				= spi_controller_get_devdata(host);
 
 	spi_st->clk = devm_clk_get(&pdev->dev, "ssc");
 	if (IS_ERR(spi_st->clk)) {
 		dev_err(&pdev->dev, "Unable to request clock\n");
 		ret = PTR_ERR(spi_st->clk);
-		goto put_master;
+		goto put_host;
 	}
 
 	ret = clk_prepare_enable(spi_st->clk);
 	if (ret)
-		goto put_master;
+		goto put_host;
 
 	init_completion(&spi_st->done);
 
@@ -324,7 +324,7 @@ static int spi_st_probe(struct platform_device *pdev)
 	var &= ~SSC_CTL_SR;
 	writel_relaxed(var, spi_st->base + SSC_CTL);
 
-	/* Set SSC into slave mode before reconfiguring PIO pins */
+	/* Set SSC into target mode before reconfiguring PIO pins */
 	var = readl_relaxed(spi_st->base + SSC_CTL);
 	var &= ~SSC_CTL_MS;
 	writel_relaxed(var, spi_st->base + SSC_CTL);
@@ -347,11 +347,11 @@ static int spi_st_probe(struct platform_device *pdev)
 	pm_runtime_set_active(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
 
-	platform_set_drvdata(pdev, master);
+	platform_set_drvdata(pdev, host);
 
-	ret = devm_spi_register_master(&pdev->dev, master);
+	ret = devm_spi_register_controller(&pdev->dev, host);
 	if (ret) {
-		dev_err(&pdev->dev, "Failed to register master\n");
+		dev_err(&pdev->dev, "Failed to register host\n");
 		goto rpm_disable;
 	}
 
@@ -361,15 +361,15 @@ rpm_disable:
 	pm_runtime_disable(&pdev->dev);
 clk_disable:
 	clk_disable_unprepare(spi_st->clk);
-put_master:
-	spi_master_put(master);
+put_host:
+	spi_controller_put(host);
 	return ret;
 }
 
 static void spi_st_remove(struct platform_device *pdev)
 {
-	struct spi_master *master = platform_get_drvdata(pdev);
-	struct spi_st *spi_st = spi_master_get_devdata(master);
+	struct spi_controller *host = platform_get_drvdata(pdev);
+	struct spi_st *spi_st = spi_controller_get_devdata(host);
 
 	pm_runtime_disable(&pdev->dev);
 
@@ -381,8 +381,8 @@ static void spi_st_remove(struct platform_device *pdev)
 #ifdef CONFIG_PM
 static int spi_st_runtime_suspend(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct spi_st *spi_st = spi_master_get_devdata(master);
+	struct spi_controller *host = dev_get_drvdata(dev);
+	struct spi_st *spi_st = spi_controller_get_devdata(host);
 
 	writel_relaxed(0, spi_st->base + SSC_IEN);
 	pinctrl_pm_select_sleep_state(dev);
@@ -394,8 +394,8 @@ static int spi_st_runtime_suspend(struct device *dev)
 
 static int spi_st_runtime_resume(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct spi_st *spi_st = spi_master_get_devdata(master);
+	struct spi_controller *host = dev_get_drvdata(dev);
+	struct spi_st *spi_st = spi_controller_get_devdata(host);
 	int ret;
 
 	ret = clk_prepare_enable(spi_st->clk);
@@ -408,10 +408,10 @@ static int spi_st_runtime_resume(struct device *dev)
 #ifdef CONFIG_PM_SLEEP
 static int spi_st_suspend(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
+	struct spi_controller *host = dev_get_drvdata(dev);
 	int ret;
 
-	ret = spi_master_suspend(master);
+	ret = spi_controller_suspend(host);
 	if (ret)
 		return ret;
 
@@ -420,10 +420,10 @@ static int spi_st_suspend(struct device *dev)
 
 static int spi_st_resume(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
+	struct spi_controller *host = dev_get_drvdata(dev);
 	int ret;
 
-	ret = spi_master_resume(master);
+	ret = spi_controller_resume(host);
 	if (ret)
 		return ret;
 
diff --git a/drivers/spi/spi-stm32-qspi.c b/drivers/spi/spi-stm32-qspi.c
index def74ae9b5f6..385832030459 100644
--- a/drivers/spi/spi-stm32-qspi.c
+++ b/drivers/spi/spi-stm32-qspi.c
@@ -357,7 +357,7 @@ static int stm32_qspi_get_mode(u8 buswidth)
 
 static int stm32_qspi_send(struct spi_device *spi, const struct spi_mem_op *op)
 {
-	struct stm32_qspi *qspi = spi_controller_get_devdata(spi->master);
+	struct stm32_qspi *qspi = spi_controller_get_devdata(spi->controller);
 	struct stm32_qspi_flash *flash = &qspi->flash[spi_get_chipselect(spi, 0)];
 	u32 ccr, cr;
 	int timeout, err = 0, err_poll_status = 0;
@@ -448,7 +448,7 @@ static int stm32_qspi_poll_status(struct spi_mem *mem, const struct spi_mem_op *
 				  unsigned long polling_rate_us,
 				  unsigned long timeout_ms)
 {
-	struct stm32_qspi *qspi = spi_controller_get_devdata(mem->spi->master);
+	struct stm32_qspi *qspi = spi_controller_get_devdata(mem->spi->controller);
 	int ret;
 
 	if (!spi_mem_supports_op(mem, op))
@@ -476,7 +476,7 @@ static int stm32_qspi_poll_status(struct spi_mem *mem, const struct spi_mem_op *
 
 static int stm32_qspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 {
-	struct stm32_qspi *qspi = spi_controller_get_devdata(mem->spi->master);
+	struct stm32_qspi *qspi = spi_controller_get_devdata(mem->spi->controller);
 	int ret;
 
 	ret = pm_runtime_resume_and_get(qspi->dev);
@@ -500,7 +500,7 @@ static int stm32_qspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 
 static int stm32_qspi_dirmap_create(struct spi_mem_dirmap_desc *desc)
 {
-	struct stm32_qspi *qspi = spi_controller_get_devdata(desc->mem->spi->master);
+	struct stm32_qspi *qspi = spi_controller_get_devdata(desc->mem->spi->controller);
 
 	if (desc->info.op_tmpl.data.dir == SPI_MEM_DATA_OUT)
 		return -EOPNOTSUPP;
@@ -518,7 +518,7 @@ static int stm32_qspi_dirmap_create(struct spi_mem_dirmap_desc *desc)
 static ssize_t stm32_qspi_dirmap_read(struct spi_mem_dirmap_desc *desc,
 				      u64 offs, size_t len, void *buf)
 {
-	struct stm32_qspi *qspi = spi_controller_get_devdata(desc->mem->spi->master);
+	struct stm32_qspi *qspi = spi_controller_get_devdata(desc->mem->spi->controller);
 	struct spi_mem_op op;
 	u32 addr_max;
 	int ret;
@@ -640,7 +640,7 @@ end_of_transfer:
 
 static int stm32_qspi_setup(struct spi_device *spi)
 {
-	struct spi_controller *ctrl = spi->master;
+	struct spi_controller *ctrl = spi->controller;
 	struct stm32_qspi *qspi = spi_controller_get_devdata(ctrl);
 	struct stm32_qspi_flash *flash;
 	u32 presc, mode;
@@ -775,7 +775,7 @@ static int stm32_qspi_probe(struct platform_device *pdev)
 	struct resource *res;
 	int ret, irq;
 
-	ctrl = devm_spi_alloc_master(dev, sizeof(*qspi));
+	ctrl = devm_spi_alloc_host(dev, sizeof(*qspi));
 	if (!ctrl)
 		return -ENOMEM;
 
@@ -861,7 +861,7 @@ static int stm32_qspi_probe(struct platform_device *pdev)
 	pm_runtime_enable(dev);
 	pm_runtime_get_noresume(dev);
 
-	ret = spi_register_master(ctrl);
+	ret = spi_register_controller(ctrl);
 	if (ret)
 		goto err_pm_runtime_free;
 
@@ -892,7 +892,7 @@ static void stm32_qspi_remove(struct platform_device *pdev)
 	struct stm32_qspi *qspi = platform_get_drvdata(pdev);
 
 	pm_runtime_get_sync(qspi->dev);
-	spi_unregister_master(qspi->ctrl);
+	spi_unregister_controller(qspi->ctrl);
 	/* disable qspi */
 	writel_relaxed(0, qspi->io_base + QSPI_CR);
 	stm32_qspi_dma_free(qspi);
diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index e6e3e4ea29f9..e61302ef3c21 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -22,58 +22,65 @@
 
 #define DRIVER_NAME "spi_stm32"
 
-/* STM32F4 SPI registers */
-#define STM32F4_SPI_CR1			0x00
-#define STM32F4_SPI_CR2			0x04
-#define STM32F4_SPI_SR			0x08
-#define STM32F4_SPI_DR			0x0C
-#define STM32F4_SPI_I2SCFGR		0x1C
-
-/* STM32F4_SPI_CR1 bit fields */
-#define STM32F4_SPI_CR1_CPHA		BIT(0)
-#define STM32F4_SPI_CR1_CPOL		BIT(1)
-#define STM32F4_SPI_CR1_MSTR		BIT(2)
-#define STM32F4_SPI_CR1_BR_SHIFT	3
-#define STM32F4_SPI_CR1_BR		GENMASK(5, 3)
-#define STM32F4_SPI_CR1_SPE		BIT(6)
-#define STM32F4_SPI_CR1_LSBFRST		BIT(7)
-#define STM32F4_SPI_CR1_SSI		BIT(8)
-#define STM32F4_SPI_CR1_SSM		BIT(9)
-#define STM32F4_SPI_CR1_RXONLY		BIT(10)
+/* STM32F4/7 SPI registers */
+#define STM32FX_SPI_CR1			0x00
+#define STM32FX_SPI_CR2			0x04
+#define STM32FX_SPI_SR			0x08
+#define STM32FX_SPI_DR			0x0C
+#define STM32FX_SPI_I2SCFGR		0x1C
+
+/* STM32FX_SPI_CR1 bit fields */
+#define STM32FX_SPI_CR1_CPHA		BIT(0)
+#define STM32FX_SPI_CR1_CPOL		BIT(1)
+#define STM32FX_SPI_CR1_MSTR		BIT(2)
+#define STM32FX_SPI_CR1_BR_SHIFT	3
+#define STM32FX_SPI_CR1_BR		GENMASK(5, 3)
+#define STM32FX_SPI_CR1_SPE		BIT(6)
+#define STM32FX_SPI_CR1_LSBFRST		BIT(7)
+#define STM32FX_SPI_CR1_SSI		BIT(8)
+#define STM32FX_SPI_CR1_SSM		BIT(9)
+#define STM32FX_SPI_CR1_RXONLY		BIT(10)
 #define STM32F4_SPI_CR1_DFF		BIT(11)
-#define STM32F4_SPI_CR1_CRCNEXT		BIT(12)
-#define STM32F4_SPI_CR1_CRCEN		BIT(13)
-#define STM32F4_SPI_CR1_BIDIOE		BIT(14)
-#define STM32F4_SPI_CR1_BIDIMODE	BIT(15)
-#define STM32F4_SPI_CR1_BR_MIN		0
-#define STM32F4_SPI_CR1_BR_MAX		(GENMASK(5, 3) >> 3)
-
-/* STM32F4_SPI_CR2 bit fields */
-#define STM32F4_SPI_CR2_RXDMAEN		BIT(0)
-#define STM32F4_SPI_CR2_TXDMAEN		BIT(1)
-#define STM32F4_SPI_CR2_SSOE		BIT(2)
-#define STM32F4_SPI_CR2_FRF		BIT(4)
-#define STM32F4_SPI_CR2_ERRIE		BIT(5)
-#define STM32F4_SPI_CR2_RXNEIE		BIT(6)
-#define STM32F4_SPI_CR2_TXEIE		BIT(7)
-
-/* STM32F4_SPI_SR bit fields */
-#define STM32F4_SPI_SR_RXNE		BIT(0)
-#define STM32F4_SPI_SR_TXE		BIT(1)
-#define STM32F4_SPI_SR_CHSIDE		BIT(2)
-#define STM32F4_SPI_SR_UDR		BIT(3)
-#define STM32F4_SPI_SR_CRCERR		BIT(4)
-#define STM32F4_SPI_SR_MODF		BIT(5)
-#define STM32F4_SPI_SR_OVR		BIT(6)
-#define STM32F4_SPI_SR_BSY		BIT(7)
-#define STM32F4_SPI_SR_FRE		BIT(8)
-
-/* STM32F4_SPI_I2SCFGR bit fields */
-#define STM32F4_SPI_I2SCFGR_I2SMOD	BIT(11)
+#define STM32F7_SPI_CR1_CRCL		BIT(11)
+#define STM32FX_SPI_CR1_CRCNEXT		BIT(12)
+#define STM32FX_SPI_CR1_CRCEN		BIT(13)
+#define STM32FX_SPI_CR1_BIDIOE		BIT(14)
+#define STM32FX_SPI_CR1_BIDIMODE	BIT(15)
+#define STM32FX_SPI_CR1_BR_MIN		0
+#define STM32FX_SPI_CR1_BR_MAX		(GENMASK(5, 3) >> 3)
+
+/* STM32FX_SPI_CR2 bit fields */
+#define STM32FX_SPI_CR2_RXDMAEN		BIT(0)
+#define STM32FX_SPI_CR2_TXDMAEN		BIT(1)
+#define STM32FX_SPI_CR2_SSOE		BIT(2)
+#define STM32FX_SPI_CR2_FRF		BIT(4)
+#define STM32FX_SPI_CR2_ERRIE		BIT(5)
+#define STM32FX_SPI_CR2_RXNEIE		BIT(6)
+#define STM32FX_SPI_CR2_TXEIE		BIT(7)
+#define STM32F7_SPI_CR2_DS		GENMASK(11, 8)
+#define STM32F7_SPI_CR2_FRXTH		BIT(12)
+#define STM32F7_SPI_CR2_LDMA_RX		BIT(13)
+#define STM32F7_SPI_CR2_LDMA_TX		BIT(14)
+
+/* STM32FX_SPI_SR bit fields */
+#define STM32FX_SPI_SR_RXNE		BIT(0)
+#define STM32FX_SPI_SR_TXE		BIT(1)
+#define STM32FX_SPI_SR_CHSIDE		BIT(2)
+#define STM32FX_SPI_SR_UDR		BIT(3)
+#define STM32FX_SPI_SR_CRCERR		BIT(4)
+#define STM32FX_SPI_SR_MODF		BIT(5)
+#define STM32FX_SPI_SR_OVR		BIT(6)
+#define STM32FX_SPI_SR_BSY		BIT(7)
+#define STM32FX_SPI_SR_FRE		BIT(8)
+#define STM32F7_SPI_SR_FRLVL		GENMASK(10, 9)
+#define STM32F7_SPI_SR_FTLVL		GENMASK(12, 11)
+
+/* STM32FX_SPI_I2SCFGR bit fields */
+#define STM32FX_SPI_I2SCFGR_I2SMOD	BIT(11)
 
 /* STM32F4 SPI Baud Rate min/max divisor */
-#define STM32F4_SPI_BR_DIV_MIN		(2 << STM32F4_SPI_CR1_BR_MIN)
-#define STM32F4_SPI_BR_DIV_MAX		(2 << STM32F4_SPI_CR1_BR_MAX)
+#define STM32FX_SPI_BR_DIV_MIN		(2 << STM32FX_SPI_CR1_BR_MIN)
+#define STM32FX_SPI_BR_DIV_MAX		(2 << STM32FX_SPI_CR1_BR_MAX)
 
 /* STM32H7 SPI registers */
 #define STM32H7_SPI_CR1			0x00
@@ -147,6 +154,20 @@
 /* STM32H7_SPI_I2SCFGR bit fields */
 #define STM32H7_SPI_I2SCFGR_I2SMOD	BIT(0)
 
+/* STM32MP25 SPI registers bit fields */
+#define STM32MP25_SPI_HWCFGR1			0x3F0
+
+/* STM32MP25_SPI_CR2 bit fields */
+#define STM32MP25_SPI_TSIZE_MAX_LIMITED		GENMASK(9, 0)
+
+/* STM32MP25_SPI_HWCFGR1 */
+#define STM32MP25_SPI_HWCFGR1_FULLCFG		GENMASK(27, 24)
+#define STM32MP25_SPI_HWCFGR1_FULLCFG_LIMITED	0x0
+#define STM32MP25_SPI_HWCFGR1_FULLCFG_FULL	0x1
+#define STM32MP25_SPI_HWCFGR1_DSCFG		GENMASK(19, 16)
+#define STM32MP25_SPI_HWCFGR1_DSCFG_16_B	0x0
+#define STM32MP25_SPI_HWCFGR1_DSCFG_32_B	0x1
+
 /* STM32H7 SPI Master Baud Rate min/max divisor */
 #define STM32H7_SPI_MBR_DIV_MIN		(2 << STM32H7_SPI_CFG1_MBR_MIN)
 #define STM32H7_SPI_MBR_DIV_MAX		(2 << STM32H7_SPI_CFG1_MBR_MAX)
@@ -173,7 +194,7 @@
 #define SPI_DMA_MIN_BYTES	16
 
 /* STM32 SPI driver helpers */
-#define STM32_SPI_MASTER_MODE(stm32_spi) (!(stm32_spi)->device_mode)
+#define STM32_SPI_HOST_MODE(stm32_spi) (!(stm32_spi)->device_mode)
 #define STM32_SPI_DEVICE_MODE(stm32_spi) ((stm32_spi)->device_mode)
 
 /**
@@ -200,6 +221,7 @@ struct stm32_spi_reg {
  * @br: baud rate register and bitfields
  * @rx: SPI RX data register
  * @tx: SPI TX data register
+ * @fullcfg: SPI full or limited feature set register
  */
 struct stm32_spi_regspec {
 	const struct stm32_spi_reg en;
@@ -212,6 +234,7 @@ struct stm32_spi_regspec {
 	const struct stm32_spi_reg br;
 	const struct stm32_spi_reg rx;
 	const struct stm32_spi_reg tx;
+	const struct stm32_spi_reg fullcfg;
 };
 
 struct stm32_spi;
@@ -222,13 +245,15 @@ struct stm32_spi;
  * @get_fifo_size: routine to get fifo size
  * @get_bpw_mask: routine to get bits per word mask
  * @disable: routine to disable controller
- * @config: routine to configure controller as SPI Master
+ * @config: routine to configure controller as SPI Host
  * @set_bpw: routine to configure registers to for bits per word
  * @set_mode: routine to configure registers to desired mode
  * @set_data_idleness: optional routine to configure registers to desired idle
  * time between frames (if driver has this functionality)
  * @set_number_of_data: optional routine to configure registers to desired
  * number of data (if driver has this functionality)
+ * @write_tx: routine to write to transmit register/FIFO
+ * @read_rx: routine to read from receive register/FIFO
  * @transfer_one_dma_start: routine to start transfer a single spi_transfer
  * using DMA
  * @dma_rx_cb: routine to call after DMA RX channel operation is complete
@@ -241,6 +266,7 @@ struct stm32_spi;
  * @has_fifo: boolean to know if fifo is used for driver
  * @has_device_mode: is this compatible capable to switch on device mode
  * @flags: compatible specific SPI controller flags used at registration time
+ * @prevent_dma_burst: boolean to indicate to prevent DMA burst
  */
 struct stm32_spi_cfg {
 	const struct stm32_spi_regspec *regs;
@@ -252,6 +278,8 @@ struct stm32_spi_cfg {
 	int (*set_mode)(struct stm32_spi *spi, unsigned int comm_type);
 	void (*set_data_idleness)(struct stm32_spi *spi, u32 length);
 	int (*set_number_of_data)(struct stm32_spi *spi, u32 length);
+	void (*write_tx)(struct stm32_spi *spi);
+	void (*read_rx)(struct stm32_spi *spi);
 	void (*transfer_one_dma_start)(struct stm32_spi *spi);
 	void (*dma_rx_cb)(void *data);
 	void (*dma_tx_cb)(void *data);
@@ -263,6 +291,7 @@ struct stm32_spi_cfg {
 	bool has_fifo;
 	bool has_device_mode;
 	u16 flags;
+	bool prevent_dma_burst;
 };
 
 /**
@@ -276,7 +305,9 @@ struct stm32_spi_cfg {
  * @lock: prevent I/O concurrent access
  * @irq: SPI controller interrupt line
  * @fifo_size: size of the embedded fifo in bytes
- * @cur_midi: master inter-data idleness in ns
+ * @t_size_max: maximum number of data of one transfer
+ * @feature_set: SPI full or limited feature set
+ * @cur_midi: host inter-data idleness in ns
  * @cur_speed: speed configured in Hz
  * @cur_half_period: time of a half bit in us
  * @cur_bpw: number of bits in a single SPI data frame
@@ -303,6 +334,10 @@ struct stm32_spi {
 	spinlock_t lock; /* prevent I/O concurrent access */
 	int irq;
 	unsigned int fifo_size;
+	unsigned int t_size_max;
+	unsigned int feature_set;
+#define STM32_SPI_FEATURE_LIMITED	STM32MP25_SPI_HWCFGR1_FULLCFG_LIMITED	/* 0x0 */
+#define STM32_SPI_FEATURE_FULL		STM32MP25_SPI_HWCFGR1_FULLCFG_FULL	/* 0x1 */
 
 	unsigned int cur_midi;
 	unsigned int cur_speed;
@@ -324,20 +359,20 @@ struct stm32_spi {
 	bool device_mode;
 };
 
-static const struct stm32_spi_regspec stm32f4_spi_regspec = {
-	.en = { STM32F4_SPI_CR1, STM32F4_SPI_CR1_SPE },
+static const struct stm32_spi_regspec stm32fx_spi_regspec = {
+	.en = { STM32FX_SPI_CR1, STM32FX_SPI_CR1_SPE },
 
-	.dma_rx_en = { STM32F4_SPI_CR2, STM32F4_SPI_CR2_RXDMAEN },
-	.dma_tx_en = { STM32F4_SPI_CR2, STM32F4_SPI_CR2_TXDMAEN },
+	.dma_rx_en = { STM32FX_SPI_CR2, STM32FX_SPI_CR2_RXDMAEN },
+	.dma_tx_en = { STM32FX_SPI_CR2, STM32FX_SPI_CR2_TXDMAEN },
 
-	.cpol = { STM32F4_SPI_CR1, STM32F4_SPI_CR1_CPOL },
-	.cpha = { STM32F4_SPI_CR1, STM32F4_SPI_CR1_CPHA },
-	.lsb_first = { STM32F4_SPI_CR1, STM32F4_SPI_CR1_LSBFRST },
+	.cpol = { STM32FX_SPI_CR1, STM32FX_SPI_CR1_CPOL },
+	.cpha = { STM32FX_SPI_CR1, STM32FX_SPI_CR1_CPHA },
+	.lsb_first = { STM32FX_SPI_CR1, STM32FX_SPI_CR1_LSBFRST },
 	.cs_high = {},
-	.br = { STM32F4_SPI_CR1, STM32F4_SPI_CR1_BR, STM32F4_SPI_CR1_BR_SHIFT },
+	.br = { STM32FX_SPI_CR1, STM32FX_SPI_CR1_BR, STM32FX_SPI_CR1_BR_SHIFT },
 
-	.rx = { STM32F4_SPI_DR },
-	.tx = { STM32F4_SPI_DR },
+	.rx = { STM32FX_SPI_DR },
+	.tx = { STM32FX_SPI_DR },
 };
 
 static const struct stm32_spi_regspec stm32h7_spi_regspec = {
@@ -360,6 +395,28 @@ static const struct stm32_spi_regspec stm32h7_spi_regspec = {
 	.tx = { STM32H7_SPI_TXDR },
 };
 
+static const struct stm32_spi_regspec stm32mp25_spi_regspec = {
+	/* SPI data transfer is enabled but spi_ker_ck is idle.
+	 * CFG1 and CFG2 registers are write protected when SPE is enabled.
+	 */
+	.en = { STM32H7_SPI_CR1, STM32H7_SPI_CR1_SPE },
+
+	.dma_rx_en = { STM32H7_SPI_CFG1, STM32H7_SPI_CFG1_RXDMAEN },
+	.dma_tx_en = { STM32H7_SPI_CFG1, STM32H7_SPI_CFG1_TXDMAEN },
+
+	.cpol = { STM32H7_SPI_CFG2, STM32H7_SPI_CFG2_CPOL },
+	.cpha = { STM32H7_SPI_CFG2, STM32H7_SPI_CFG2_CPHA },
+	.lsb_first = { STM32H7_SPI_CFG2, STM32H7_SPI_CFG2_LSBFRST },
+	.cs_high = { STM32H7_SPI_CFG2, STM32H7_SPI_CFG2_SSIOP },
+	.br = { STM32H7_SPI_CFG1, STM32H7_SPI_CFG1_MBR,
+		STM32H7_SPI_CFG1_MBR_SHIFT },
+
+	.rx = { STM32H7_SPI_RXDR },
+	.tx = { STM32H7_SPI_TXDR },
+
+	.fullcfg = { STM32MP25_SPI_HWCFGR1, STM32MP25_SPI_HWCFGR1_FULLCFG },
+};
+
 static inline void stm32_spi_set_bits(struct stm32_spi *spi,
 				      u32 offset, u32 bits)
 {
@@ -410,6 +467,16 @@ static int stm32f4_spi_get_bpw_mask(struct stm32_spi *spi)
 }
 
 /**
+ * stm32f7_spi_get_bpw_mask - Return bits per word mask
+ * @spi: pointer to the spi controller data structure
+ */
+static int stm32f7_spi_get_bpw_mask(struct stm32_spi *spi)
+{
+	dev_dbg(spi->dev, "16-bit maximum data frame\n");
+	return SPI_BPW_RANGE_MASK(4, 16);
+}
+
+/**
  * stm32h7_spi_get_bpw_mask - Return bits per word mask
  * @spi: pointer to the spi controller data structure
  */
@@ -437,6 +504,28 @@ static int stm32h7_spi_get_bpw_mask(struct stm32_spi *spi)
 }
 
 /**
+ * stm32mp25_spi_get_bpw_mask - Return bits per word mask
+ * @spi: pointer to the spi controller data structure
+ */
+static int stm32mp25_spi_get_bpw_mask(struct stm32_spi *spi)
+{
+	u32 dscfg, max_bpw;
+
+	if (spi->feature_set == STM32_SPI_FEATURE_LIMITED) {
+		dev_dbg(spi->dev, "8-bit or 16-bit data frame supported\n");
+		return SPI_BPW_MASK(8) | SPI_BPW_MASK(16);
+	}
+
+	dscfg = FIELD_GET(STM32MP25_SPI_HWCFGR1_DSCFG,
+			  readl_relaxed(spi->base + STM32MP25_SPI_HWCFGR1));
+	max_bpw = 16;
+	if (dscfg == STM32MP25_SPI_HWCFGR1_DSCFG_32_B)
+		max_bpw = 32;
+	dev_dbg(spi->dev, "%d-bit maximum data frame\n", max_bpw);
+	return SPI_BPW_RANGE_MASK(4, max_bpw);
+}
+
+/**
  * stm32_spi_prepare_mbr - Determine baud rate divisor value
  * @spi: pointer to the spi controller data structure
  * @speed_hz: requested speed
@@ -502,19 +591,48 @@ static u32 stm32h7_spi_prepare_fthlv(struct stm32_spi *spi, u32 xfer_len)
  */
 static void stm32f4_spi_write_tx(struct stm32_spi *spi)
 {
-	if ((spi->tx_len > 0) && (readl_relaxed(spi->base + STM32F4_SPI_SR) &
-				  STM32F4_SPI_SR_TXE)) {
+	if ((spi->tx_len > 0) && (readl_relaxed(spi->base + STM32FX_SPI_SR) &
+				  STM32FX_SPI_SR_TXE)) {
 		u32 offs = spi->cur_xferlen - spi->tx_len;
 
 		if (spi->cur_bpw == 16) {
 			const u16 *tx_buf16 = (const u16 *)(spi->tx_buf + offs);
 
-			writew_relaxed(*tx_buf16, spi->base + STM32F4_SPI_DR);
+			writew_relaxed(*tx_buf16, spi->base + STM32FX_SPI_DR);
 			spi->tx_len -= sizeof(u16);
 		} else {
 			const u8 *tx_buf8 = (const u8 *)(spi->tx_buf + offs);
 
-			writeb_relaxed(*tx_buf8, spi->base + STM32F4_SPI_DR);
+			writeb_relaxed(*tx_buf8, spi->base + STM32FX_SPI_DR);
+			spi->tx_len -= sizeof(u8);
+		}
+	}
+
+	dev_dbg(spi->dev, "%s: %d bytes left\n", __func__, spi->tx_len);
+}
+
+/**
+ * stm32f7_spi_write_tx - Write bytes to Transmit Data Register
+ * @spi: pointer to the spi controller data structure
+ *
+ * Read from tx_buf depends on remaining bytes to avoid to read beyond
+ * tx_buf end.
+ */
+static void stm32f7_spi_write_tx(struct stm32_spi *spi)
+{
+	if ((spi->tx_len > 0) && (readl_relaxed(spi->base + STM32FX_SPI_SR) &
+				  STM32FX_SPI_SR_TXE)) {
+		u32 offs = spi->cur_xferlen - spi->tx_len;
+
+		if (spi->tx_len >= sizeof(u16)) {
+			const u16 *tx_buf16 = (const u16 *)(spi->tx_buf + offs);
+
+			writew_relaxed(*tx_buf16, spi->base + STM32FX_SPI_DR);
+			spi->tx_len -= sizeof(u16);
+		} else {
+			const u8 *tx_buf8 = (const u8 *)(spi->tx_buf + offs);
+
+			writeb_relaxed(*tx_buf8, spi->base + STM32FX_SPI_DR);
 			spi->tx_len -= sizeof(u8);
 		}
 	}
@@ -566,19 +684,19 @@ static void stm32h7_spi_write_txfifo(struct stm32_spi *spi)
  */
 static void stm32f4_spi_read_rx(struct stm32_spi *spi)
 {
-	if ((spi->rx_len > 0) && (readl_relaxed(spi->base + STM32F4_SPI_SR) &
-				  STM32F4_SPI_SR_RXNE)) {
+	if ((spi->rx_len > 0) && (readl_relaxed(spi->base + STM32FX_SPI_SR) &
+				  STM32FX_SPI_SR_RXNE)) {
 		u32 offs = spi->cur_xferlen - spi->rx_len;
 
 		if (spi->cur_bpw == 16) {
 			u16 *rx_buf16 = (u16 *)(spi->rx_buf + offs);
 
-			*rx_buf16 = readw_relaxed(spi->base + STM32F4_SPI_DR);
+			*rx_buf16 = readw_relaxed(spi->base + STM32FX_SPI_DR);
 			spi->rx_len -= sizeof(u16);
 		} else {
 			u8 *rx_buf8 = (u8 *)(spi->rx_buf + offs);
 
-			*rx_buf8 = readb_relaxed(spi->base + STM32F4_SPI_DR);
+			*rx_buf8 = readb_relaxed(spi->base + STM32FX_SPI_DR);
 			spi->rx_len -= sizeof(u8);
 		}
 	}
@@ -587,6 +705,46 @@ static void stm32f4_spi_read_rx(struct stm32_spi *spi)
 }
 
 /**
+ * stm32f7_spi_read_rx - Read bytes from Receive Data Register
+ * @spi: pointer to the spi controller data structure
+ *
+ * Write in rx_buf depends on remaining bytes to avoid to write beyond
+ * rx_buf end.
+ */
+static void stm32f7_spi_read_rx(struct stm32_spi *spi)
+{
+	u32 sr = readl_relaxed(spi->base + STM32FX_SPI_SR);
+	u32 frlvl = FIELD_GET(STM32F7_SPI_SR_FRLVL, sr);
+
+	while ((spi->rx_len > 0) && (frlvl > 0)) {
+		u32 offs = spi->cur_xferlen - spi->rx_len;
+
+		if ((spi->rx_len >= sizeof(u16)) && (frlvl >= 2)) {
+			u16 *rx_buf16 = (u16 *)(spi->rx_buf + offs);
+
+			*rx_buf16 = readw_relaxed(spi->base + STM32FX_SPI_DR);
+			spi->rx_len -= sizeof(u16);
+		} else {
+			u8 *rx_buf8 = (u8 *)(spi->rx_buf + offs);
+
+			*rx_buf8 = readb_relaxed(spi->base + STM32FX_SPI_DR);
+			spi->rx_len -= sizeof(u8);
+		}
+
+		sr = readl_relaxed(spi->base + STM32FX_SPI_SR);
+		frlvl = FIELD_GET(STM32F7_SPI_SR_FRLVL, sr);
+	}
+
+	if (spi->rx_len >= sizeof(u16))
+		stm32_spi_clr_bits(spi, STM32FX_SPI_CR2, STM32F7_SPI_CR2_FRXTH);
+	else
+		stm32_spi_set_bits(spi, STM32FX_SPI_CR2, STM32F7_SPI_CR2_FRXTH);
+
+	dev_dbg(spi->dev, "%s: %d bytes left (sr=%08x)\n",
+		__func__, spi->rx_len, sr);
+}
+
+/**
  * stm32h7_spi_read_rxfifo - Read bytes in Receive Data Register
  * @spi: pointer to the spi controller data structure
  *
@@ -645,10 +803,10 @@ static void stm32_spi_enable(struct stm32_spi *spi)
 }
 
 /**
- * stm32f4_spi_disable - Disable SPI controller
+ * stm32fx_spi_disable - Disable SPI controller
  * @spi: pointer to the spi controller data structure
  */
-static void stm32f4_spi_disable(struct stm32_spi *spi)
+static void stm32fx_spi_disable(struct stm32_spi *spi)
 {
 	unsigned long flags;
 	u32 sr;
@@ -657,20 +815,20 @@ static void stm32f4_spi_disable(struct stm32_spi *spi)
 
 	spin_lock_irqsave(&spi->lock, flags);
 
-	if (!(readl_relaxed(spi->base + STM32F4_SPI_CR1) &
-	      STM32F4_SPI_CR1_SPE)) {
+	if (!(readl_relaxed(spi->base + STM32FX_SPI_CR1) &
+	      STM32FX_SPI_CR1_SPE)) {
 		spin_unlock_irqrestore(&spi->lock, flags);
 		return;
 	}
 
 	/* Disable interrupts */
-	stm32_spi_clr_bits(spi, STM32F4_SPI_CR2, STM32F4_SPI_CR2_TXEIE |
-						 STM32F4_SPI_CR2_RXNEIE |
-						 STM32F4_SPI_CR2_ERRIE);
+	stm32_spi_clr_bits(spi, STM32FX_SPI_CR2, STM32FX_SPI_CR2_TXEIE |
+						 STM32FX_SPI_CR2_RXNEIE |
+						 STM32FX_SPI_CR2_ERRIE);
 
 	/* Wait until BSY = 0 */
-	if (readl_relaxed_poll_timeout_atomic(spi->base + STM32F4_SPI_SR,
-					      sr, !(sr & STM32F4_SPI_SR_BSY),
+	if (readl_relaxed_poll_timeout_atomic(spi->base + STM32FX_SPI_SR,
+					      sr, !(sr & STM32FX_SPI_SR_BSY),
 					      10, 100000) < 0) {
 		dev_warn(spi->dev, "disabling condition timeout\n");
 	}
@@ -680,14 +838,14 @@ static void stm32f4_spi_disable(struct stm32_spi *spi)
 	if (spi->cur_usedma && spi->dma_rx)
 		dmaengine_terminate_async(spi->dma_rx);
 
-	stm32_spi_clr_bits(spi, STM32F4_SPI_CR1, STM32F4_SPI_CR1_SPE);
+	stm32_spi_clr_bits(spi, STM32FX_SPI_CR1, STM32FX_SPI_CR1_SPE);
 
-	stm32_spi_clr_bits(spi, STM32F4_SPI_CR2, STM32F4_SPI_CR2_TXDMAEN |
-						 STM32F4_SPI_CR2_RXDMAEN);
+	stm32_spi_clr_bits(spi, STM32FX_SPI_CR2, STM32FX_SPI_CR2_TXDMAEN |
+						 STM32FX_SPI_CR2_RXDMAEN);
 
 	/* Sequence to clear OVR flag */
-	readl_relaxed(spi->base + STM32F4_SPI_DR);
-	readl_relaxed(spi->base + STM32F4_SPI_SR);
+	readl_relaxed(spi->base + STM32FX_SPI_DR);
+	readl_relaxed(spi->base + STM32FX_SPI_SR);
 
 	spin_unlock_irqrestore(&spi->lock, flags);
 }
@@ -763,11 +921,11 @@ static bool stm32_spi_can_dma(struct spi_controller *ctrl,
 }
 
 /**
- * stm32f4_spi_irq_event - Interrupt handler for SPI controller events
+ * stm32fx_spi_irq_event - Interrupt handler for SPI controller events
  * @irq: interrupt line
  * @dev_id: SPI controller ctrl interface
  */
-static irqreturn_t stm32f4_spi_irq_event(int irq, void *dev_id)
+static irqreturn_t stm32fx_spi_irq_event(int irq, void *dev_id)
 {
 	struct spi_controller *ctrl = dev_id;
 	struct stm32_spi *spi = spi_controller_get_devdata(ctrl);
@@ -776,26 +934,26 @@ static irqreturn_t stm32f4_spi_irq_event(int irq, void *dev_id)
 
 	spin_lock(&spi->lock);
 
-	sr = readl_relaxed(spi->base + STM32F4_SPI_SR);
+	sr = readl_relaxed(spi->base + STM32FX_SPI_SR);
 	/*
 	 * BSY flag is not handled in interrupt but it is normal behavior when
 	 * this flag is set.
 	 */
-	sr &= ~STM32F4_SPI_SR_BSY;
+	sr &= ~STM32FX_SPI_SR_BSY;
 
 	if (!spi->cur_usedma && (spi->cur_comm == SPI_SIMPLEX_TX ||
 				 spi->cur_comm == SPI_3WIRE_TX)) {
 		/* OVR flag shouldn't be handled for TX only mode */
-		sr &= ~(STM32F4_SPI_SR_OVR | STM32F4_SPI_SR_RXNE);
-		mask |= STM32F4_SPI_SR_TXE;
+		sr &= ~(STM32FX_SPI_SR_OVR | STM32FX_SPI_SR_RXNE);
+		mask |= STM32FX_SPI_SR_TXE;
 	}
 
 	if (!spi->cur_usedma && (spi->cur_comm == SPI_FULL_DUPLEX ||
 				spi->cur_comm == SPI_SIMPLEX_RX ||
 				spi->cur_comm == SPI_3WIRE_RX)) {
 		/* TXE flag is set and is handled when RXNE flag occurs */
-		sr &= ~STM32F4_SPI_SR_TXE;
-		mask |= STM32F4_SPI_SR_RXNE | STM32F4_SPI_SR_OVR;
+		sr &= ~STM32FX_SPI_SR_TXE;
+		mask |= STM32FX_SPI_SR_RXNE | STM32FX_SPI_SR_OVR;
 	}
 
 	if (!(sr & mask)) {
@@ -804,12 +962,12 @@ static irqreturn_t stm32f4_spi_irq_event(int irq, void *dev_id)
 		return IRQ_NONE;
 	}
 
-	if (sr & STM32F4_SPI_SR_OVR) {
+	if (sr & STM32FX_SPI_SR_OVR) {
 		dev_warn(spi->dev, "Overrun: received value discarded\n");
 
 		/* Sequence to clear OVR flag */
-		readl_relaxed(spi->base + STM32F4_SPI_DR);
-		readl_relaxed(spi->base + STM32F4_SPI_SR);
+		readl_relaxed(spi->base + STM32FX_SPI_DR);
+		readl_relaxed(spi->base + STM32FX_SPI_SR);
 
 		/*
 		 * If overrun is detected, it means that something went wrong,
@@ -820,28 +978,28 @@ static irqreturn_t stm32f4_spi_irq_event(int irq, void *dev_id)
 		goto end_irq;
 	}
 
-	if (sr & STM32F4_SPI_SR_TXE) {
+	if (sr & STM32FX_SPI_SR_TXE) {
 		if (spi->tx_buf)
-			stm32f4_spi_write_tx(spi);
+			spi->cfg->write_tx(spi);
 		if (spi->tx_len == 0)
 			end = true;
 	}
 
-	if (sr & STM32F4_SPI_SR_RXNE) {
-		stm32f4_spi_read_rx(spi);
+	if (sr & STM32FX_SPI_SR_RXNE) {
+		spi->cfg->read_rx(spi);
 		if (spi->rx_len == 0)
 			end = true;
 		else if (spi->tx_buf)/* Load data for discontinuous mode */
-			stm32f4_spi_write_tx(spi);
+			spi->cfg->write_tx(spi);
 	}
 
 end_irq:
 	if (end) {
 		/* Immediately disable interrupts to do not generate new one */
-		stm32_spi_clr_bits(spi, STM32F4_SPI_CR2,
-					STM32F4_SPI_CR2_TXEIE |
-					STM32F4_SPI_CR2_RXNEIE |
-					STM32F4_SPI_CR2_ERRIE);
+		stm32_spi_clr_bits(spi, STM32FX_SPI_CR2,
+					STM32FX_SPI_CR2_TXEIE |
+					STM32FX_SPI_CR2_RXNEIE |
+					STM32FX_SPI_CR2_ERRIE);
 		spin_unlock(&spi->lock);
 		return IRQ_WAKE_THREAD;
 	}
@@ -851,17 +1009,17 @@ end_irq:
 }
 
 /**
- * stm32f4_spi_irq_thread - Thread of interrupt handler for SPI controller
+ * stm32fx_spi_irq_thread - Thread of interrupt handler for SPI controller
  * @irq: interrupt line
  * @dev_id: SPI controller interface
  */
-static irqreturn_t stm32f4_spi_irq_thread(int irq, void *dev_id)
+static irqreturn_t stm32fx_spi_irq_thread(int irq, void *dev_id)
 {
 	struct spi_controller *ctrl = dev_id;
 	struct stm32_spi *spi = spi_controller_get_devdata(ctrl);
 
 	spi_finalize_current_transfer(ctrl);
-	stm32f4_spi_disable(spi);
+	stm32fx_spi_disable(spi);
 
 	return IRQ_HANDLED;
 }
@@ -974,7 +1132,7 @@ static int stm32_spi_prepare_msg(struct spi_controller *ctrl,
 	unsigned long flags;
 	u32 clrb = 0, setb = 0;
 
-	/* SPI slave device may need time between data frames */
+	/* SPI target device may need time between data frames */
 	spi->cur_midi = 0;
 	if (np && !of_property_read_u32(np, "st,spi-midi-ns", &spi->cur_midi))
 		dev_dbg(spi->dev, "%dns inter-data idleness\n", spi->cur_midi);
@@ -1013,7 +1171,7 @@ static int stm32_spi_prepare_msg(struct spi_controller *ctrl,
 		int ret;
 
 		ret = spi_split_transfers_maxwords(ctrl, msg,
-						   STM32H7_SPI_TSIZE_MAX,
+						   spi->t_size_max,
 						   GFP_KERNEL | GFP_DMA);
 		if (ret)
 			return ret;
@@ -1034,18 +1192,18 @@ static int stm32_spi_prepare_msg(struct spi_controller *ctrl,
 }
 
 /**
- * stm32f4_spi_dma_tx_cb - dma callback
+ * stm32fx_spi_dma_tx_cb - dma callback
  * @data: pointer to the spi controller data structure
  *
  * DMA callback is called when the transfer is complete for DMA TX channel.
  */
-static void stm32f4_spi_dma_tx_cb(void *data)
+static void stm32fx_spi_dma_tx_cb(void *data)
 {
 	struct stm32_spi *spi = data;
 
 	if (spi->cur_comm == SPI_SIMPLEX_TX || spi->cur_comm == SPI_3WIRE_TX) {
 		spi_finalize_current_transfer(spi->ctrl);
-		stm32f4_spi_disable(spi);
+		stm32fx_spi_disable(spi);
 	}
 }
 
@@ -1067,15 +1225,19 @@ static void stm32_spi_dma_rx_cb(void *data)
  * stm32_spi_dma_config - configure dma slave channel depending on current
  *			  transfer bits_per_word.
  * @spi: pointer to the spi controller data structure
+ * @dma_chan: pointer to the DMA channel
  * @dma_conf: pointer to the dma_slave_config structure
  * @dir: direction of the dma transfer
  */
 static void stm32_spi_dma_config(struct stm32_spi *spi,
+				 struct dma_chan *dma_chan,
 				 struct dma_slave_config *dma_conf,
 				 enum dma_transfer_direction dir)
 {
 	enum dma_slave_buswidth buswidth;
-	u32 maxburst;
+	struct dma_slave_caps caps;
+	u32 maxburst = 1;
+	int ret;
 
 	if (spi->cur_bpw <= 8)
 		buswidth = DMA_SLAVE_BUSWIDTH_1_BYTE;
@@ -1084,15 +1246,14 @@ static void stm32_spi_dma_config(struct stm32_spi *spi,
 	else
 		buswidth = DMA_SLAVE_BUSWIDTH_4_BYTES;
 
-	if (spi->cfg->has_fifo) {
-		/* Valid for DMA Half or Full Fifo threshold */
-		if (spi->cur_fthlv == 2)
-			maxburst = 1;
-		else
-			maxburst = spi->cur_fthlv;
-	} else {
-		maxburst = 1;
-	}
+	/* Valid for DMA Half or Full Fifo threshold */
+	if (!spi->cfg->prevent_dma_burst && spi->cfg->has_fifo && spi->cur_fthlv != 2)
+		maxburst = spi->cur_fthlv;
+
+	/* Get the DMA channel caps, and adjust maxburst if possible */
+	ret = dma_get_slave_caps(dma_chan, &caps);
+	if (!ret)
+		maxburst = min(maxburst, caps.max_burst);
 
 	memset(dma_conf, 0, sizeof(struct dma_slave_config));
 	dma_conf->direction = dir;
@@ -1114,21 +1275,21 @@ static void stm32_spi_dma_config(struct stm32_spi *spi,
 }
 
 /**
- * stm32f4_spi_transfer_one_irq - transfer a single spi_transfer using
+ * stm32fx_spi_transfer_one_irq - transfer a single spi_transfer using
  *				  interrupts
  * @spi: pointer to the spi controller data structure
  *
  * It must returns 0 if the transfer is finished or 1 if the transfer is still
  * in progress.
  */
-static int stm32f4_spi_transfer_one_irq(struct stm32_spi *spi)
+static int stm32fx_spi_transfer_one_irq(struct stm32_spi *spi)
 {
 	unsigned long flags;
 	u32 cr2 = 0;
 
 	/* Enable the interrupts relative to the current communication mode */
 	if (spi->cur_comm == SPI_SIMPLEX_TX || spi->cur_comm == SPI_3WIRE_TX) {
-		cr2 |= STM32F4_SPI_CR2_TXEIE;
+		cr2 |= STM32FX_SPI_CR2_TXEIE;
 	} else if (spi->cur_comm == SPI_FULL_DUPLEX ||
 				spi->cur_comm == SPI_SIMPLEX_RX ||
 				spi->cur_comm == SPI_3WIRE_RX) {
@@ -1136,20 +1297,20 @@ static int stm32f4_spi_transfer_one_irq(struct stm32_spi *spi)
 		 * since the received data are never read. Therefore set OVR
 		 * interrupt only when rx buffer is available.
 		 */
-		cr2 |= STM32F4_SPI_CR2_RXNEIE | STM32F4_SPI_CR2_ERRIE;
+		cr2 |= STM32FX_SPI_CR2_RXNEIE | STM32FX_SPI_CR2_ERRIE;
 	} else {
 		return -EINVAL;
 	}
 
 	spin_lock_irqsave(&spi->lock, flags);
 
-	stm32_spi_set_bits(spi, STM32F4_SPI_CR2, cr2);
+	stm32_spi_set_bits(spi, STM32FX_SPI_CR2, cr2);
 
 	stm32_spi_enable(spi);
 
 	/* starting data transfer when buffer is loaded */
 	if (spi->tx_buf)
-		stm32f4_spi_write_tx(spi);
+		spi->cfg->write_tx(spi);
 
 	spin_unlock_irqrestore(&spi->lock, flags);
 
@@ -1189,7 +1350,7 @@ static int stm32h7_spi_transfer_one_irq(struct stm32_spi *spi)
 	if (spi->tx_buf)
 		stm32h7_spi_write_txfifo(spi);
 
-	if (STM32_SPI_MASTER_MODE(spi))
+	if (STM32_SPI_HOST_MODE(spi))
 		stm32_spi_set_bits(spi, STM32H7_SPI_CR1, STM32H7_SPI_CR1_CSTART);
 
 	writel_relaxed(ier, spi->base + STM32H7_SPI_IER);
@@ -1200,11 +1361,11 @@ static int stm32h7_spi_transfer_one_irq(struct stm32_spi *spi)
 }
 
 /**
- * stm32f4_spi_transfer_one_dma_start - Set SPI driver registers to start
+ * stm32fx_spi_transfer_one_dma_start - Set SPI driver registers to start
  *					transfer using DMA
  * @spi: pointer to the spi controller data structure
  */
-static void stm32f4_spi_transfer_one_dma_start(struct stm32_spi *spi)
+static void stm32fx_spi_transfer_one_dma_start(struct stm32_spi *spi)
 {
 	/* In DMA mode end of transfer is handled by DMA TX or RX callback. */
 	if (spi->cur_comm == SPI_SIMPLEX_RX || spi->cur_comm == SPI_3WIRE_RX ||
@@ -1214,13 +1375,29 @@ static void stm32f4_spi_transfer_one_dma_start(struct stm32_spi *spi)
 		 * since the received data are never read. Therefore set OVR
 		 * interrupt only when rx buffer is available.
 		 */
-		stm32_spi_set_bits(spi, STM32F4_SPI_CR2, STM32F4_SPI_CR2_ERRIE);
+		stm32_spi_set_bits(spi, STM32FX_SPI_CR2, STM32FX_SPI_CR2_ERRIE);
 	}
 
 	stm32_spi_enable(spi);
 }
 
 /**
+ * stm32f7_spi_transfer_one_dma_start - Set SPI driver registers to start
+ *					transfer using DMA
+ * @spi: pointer to the spi controller data structure
+ */
+static void stm32f7_spi_transfer_one_dma_start(struct stm32_spi *spi)
+{
+	/* Configure DMA request trigger threshold according to DMA width */
+	if (spi->cur_bpw <= 8)
+		stm32_spi_set_bits(spi, STM32FX_SPI_CR2, STM32F7_SPI_CR2_FRXTH);
+	else
+		stm32_spi_clr_bits(spi, STM32FX_SPI_CR2, STM32F7_SPI_CR2_FRXTH);
+
+	stm32fx_spi_transfer_one_dma_start(spi);
+}
+
+/**
  * stm32h7_spi_transfer_one_dma_start - Set SPI driver registers to start
  *					transfer using DMA
  * @spi: pointer to the spi controller data structure
@@ -1237,7 +1414,7 @@ static void stm32h7_spi_transfer_one_dma_start(struct stm32_spi *spi)
 
 	stm32_spi_enable(spi);
 
-	if (STM32_SPI_MASTER_MODE(spi))
+	if (STM32_SPI_HOST_MODE(spi))
 		stm32_spi_set_bits(spi, STM32H7_SPI_CR1, STM32H7_SPI_CR1_CSTART);
 }
 
@@ -1260,7 +1437,7 @@ static int stm32_spi_transfer_one_dma(struct stm32_spi *spi,
 
 	rx_dma_desc = NULL;
 	if (spi->rx_buf && spi->dma_rx) {
-		stm32_spi_dma_config(spi, &rx_dma_conf, DMA_DEV_TO_MEM);
+		stm32_spi_dma_config(spi, spi->dma_rx, &rx_dma_conf, DMA_DEV_TO_MEM);
 		dmaengine_slave_config(spi->dma_rx, &rx_dma_conf);
 
 		/* Enable Rx DMA request */
@@ -1276,7 +1453,7 @@ static int stm32_spi_transfer_one_dma(struct stm32_spi *spi,
 
 	tx_dma_desc = NULL;
 	if (spi->tx_buf && spi->dma_tx) {
-		stm32_spi_dma_config(spi, &tx_dma_conf, DMA_MEM_TO_DEV);
+		stm32_spi_dma_config(spi, spi->dma_tx, &tx_dma_conf, DMA_MEM_TO_DEV);
 		dmaengine_slave_config(spi->dma_tx, &tx_dma_conf);
 
 		tx_dma_desc = dmaengine_prep_slave_sg(
@@ -1353,9 +1530,34 @@ dma_desc_error:
 static void stm32f4_spi_set_bpw(struct stm32_spi *spi)
 {
 	if (spi->cur_bpw == 16)
-		stm32_spi_set_bits(spi, STM32F4_SPI_CR1, STM32F4_SPI_CR1_DFF);
+		stm32_spi_set_bits(spi, STM32FX_SPI_CR1, STM32F4_SPI_CR1_DFF);
+	else
+		stm32_spi_clr_bits(spi, STM32FX_SPI_CR1, STM32F4_SPI_CR1_DFF);
+}
+
+/**
+ * stm32f7_spi_set_bpw - Configure bits per word
+ * @spi: pointer to the spi controller data structure
+ */
+static void stm32f7_spi_set_bpw(struct stm32_spi *spi)
+{
+	u32 bpw;
+	u32 cr2_clrb = 0, cr2_setb = 0;
+
+	bpw = spi->cur_bpw - 1;
+
+	cr2_clrb |= STM32F7_SPI_CR2_DS;
+	cr2_setb |= FIELD_PREP(STM32F7_SPI_CR2_DS, bpw);
+
+	if (spi->rx_len >= sizeof(u16))
+		cr2_clrb |= STM32F7_SPI_CR2_FRXTH;
 	else
-		stm32_spi_clr_bits(spi, STM32F4_SPI_CR1, STM32F4_SPI_CR1_DFF);
+		cr2_setb |= STM32F7_SPI_CR2_FRXTH;
+
+	writel_relaxed(
+		(readl_relaxed(spi->base + STM32FX_SPI_CR2) &
+		 ~cr2_clrb) | cr2_setb,
+		spi->base + STM32FX_SPI_CR2);
 }
 
 /**
@@ -1385,7 +1587,7 @@ static void stm32h7_spi_set_bpw(struct stm32_spi *spi)
 }
 
 /**
- * stm32_spi_set_mbr - Configure baud rate divisor in master mode
+ * stm32_spi_set_mbr - Configure baud rate divisor in host mode
  * @spi: pointer to the spi controller data structure
  * @mbrdiv: baud rate divisor value
  */
@@ -1433,26 +1635,26 @@ static unsigned int stm32_spi_communication_type(struct spi_device *spi_dev,
 }
 
 /**
- * stm32f4_spi_set_mode - configure communication mode
+ * stm32fx_spi_set_mode - configure communication mode
  * @spi: pointer to the spi controller data structure
  * @comm_type: type of communication to configure
  */
-static int stm32f4_spi_set_mode(struct stm32_spi *spi, unsigned int comm_type)
+static int stm32fx_spi_set_mode(struct stm32_spi *spi, unsigned int comm_type)
 {
 	if (comm_type == SPI_3WIRE_TX || comm_type == SPI_SIMPLEX_TX) {
-		stm32_spi_set_bits(spi, STM32F4_SPI_CR1,
-					STM32F4_SPI_CR1_BIDIMODE |
-					STM32F4_SPI_CR1_BIDIOE);
+		stm32_spi_set_bits(spi, STM32FX_SPI_CR1,
+					STM32FX_SPI_CR1_BIDIMODE |
+					STM32FX_SPI_CR1_BIDIOE);
 	} else if (comm_type == SPI_FULL_DUPLEX ||
 				comm_type == SPI_SIMPLEX_RX) {
-		stm32_spi_clr_bits(spi, STM32F4_SPI_CR1,
-					STM32F4_SPI_CR1_BIDIMODE |
-					STM32F4_SPI_CR1_BIDIOE);
+		stm32_spi_clr_bits(spi, STM32FX_SPI_CR1,
+					STM32FX_SPI_CR1_BIDIMODE |
+					STM32FX_SPI_CR1_BIDIOE);
 	} else if (comm_type == SPI_3WIRE_RX) {
-		stm32_spi_set_bits(spi, STM32F4_SPI_CR1,
-					STM32F4_SPI_CR1_BIDIMODE);
-		stm32_spi_clr_bits(spi, STM32F4_SPI_CR1,
-					STM32F4_SPI_CR1_BIDIOE);
+		stm32_spi_set_bits(spi, STM32FX_SPI_CR1,
+					STM32FX_SPI_CR1_BIDIMODE);
+		stm32_spi_clr_bits(spi, STM32FX_SPI_CR1,
+					STM32FX_SPI_CR1_BIDIOE);
 	} else {
 		return -EINVAL;
 	}
@@ -1497,7 +1699,7 @@ static int stm32h7_spi_set_mode(struct stm32_spi *spi, unsigned int comm_type)
 
 /**
  * stm32h7_spi_data_idleness - configure minimum time delay inserted between two
- *			       consecutive data frames in master mode
+ *			       consecutive data frames in host mode
  * @spi: pointer to the spi controller data structure
  * @len: transfer len
  */
@@ -1531,7 +1733,7 @@ static void stm32h7_spi_data_idleness(struct stm32_spi *spi, u32 len)
  */
 static int stm32h7_spi_number_of_data(struct stm32_spi *spi, u32 nb_words)
 {
-	if (nb_words <= STM32H7_SPI_TSIZE_MAX) {
+	if (nb_words <= spi->t_size_max) {
 		writel_relaxed(FIELD_PREP(STM32H7_SPI_CR2_TSIZE, nb_words),
 			       spi->base + STM32H7_SPI_CR2);
 	} else {
@@ -1566,7 +1768,7 @@ static int stm32_spi_transfer_one_setup(struct stm32_spi *spi,
 	spi->cfg->set_bpw(spi);
 
 	/* Update spi->cur_speed with real clock speed */
-	if (STM32_SPI_MASTER_MODE(spi)) {
+	if (STM32_SPI_HOST_MODE(spi)) {
 		mbr = stm32_spi_prepare_mbr(spi, transfer->speed_hz,
 					    spi->cfg->baud_rate_div_min,
 					    spi->cfg->baud_rate_div_max);
@@ -1586,7 +1788,7 @@ static int stm32_spi_transfer_one_setup(struct stm32_spi *spi,
 
 	spi->cur_comm = comm_type;
 
-	if (STM32_SPI_MASTER_MODE(spi) && spi->cfg->set_data_idleness)
+	if (STM32_SPI_HOST_MODE(spi) && spi->cfg->set_data_idleness)
 		spi->cfg->set_data_idleness(spi, transfer->len);
 
 	if (spi->cur_bpw <= 8)
@@ -1607,7 +1809,7 @@ static int stm32_spi_transfer_one_setup(struct stm32_spi *spi,
 	dev_dbg(spi->dev,
 		"data frame of %d-bit, data packet of %d data frames\n",
 		spi->cur_bpw, spi->cur_fthlv);
-	if (STM32_SPI_MASTER_MODE(spi))
+	if (STM32_SPI_HOST_MODE(spi))
 		dev_dbg(spi->dev, "speed set to %dHz\n", spi->cur_speed);
 	dev_dbg(spi->dev, "transfer of %d bytes (%d data frames)\n",
 		spi->cur_xferlen, nb_words);
@@ -1672,30 +1874,30 @@ static int stm32_spi_unprepare_msg(struct spi_controller *ctrl,
 }
 
 /**
- * stm32f4_spi_config - Configure SPI controller as SPI master
+ * stm32fx_spi_config - Configure SPI controller as SPI host
  * @spi: pointer to the spi controller data structure
  */
-static int stm32f4_spi_config(struct stm32_spi *spi)
+static int stm32fx_spi_config(struct stm32_spi *spi)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&spi->lock, flags);
 
 	/* Ensure I2SMOD bit is kept cleared */
-	stm32_spi_clr_bits(spi, STM32F4_SPI_I2SCFGR,
-			   STM32F4_SPI_I2SCFGR_I2SMOD);
+	stm32_spi_clr_bits(spi, STM32FX_SPI_I2SCFGR,
+			   STM32FX_SPI_I2SCFGR_I2SMOD);
 
 	/*
 	 * - SS input value high
 	 * - transmitter half duplex direction
-	 * - Set the master mode (default Motorola mode)
-	 * - Consider 1 master/n slaves configuration and
+	 * - Set the host mode (default Motorola mode)
+	 * - Consider 1 host/n targets configuration and
 	 *   SS input value is determined by the SSI bit
 	 */
-	stm32_spi_set_bits(spi, STM32F4_SPI_CR1, STM32F4_SPI_CR1_SSI |
-						 STM32F4_SPI_CR1_BIDIOE |
-						 STM32F4_SPI_CR1_MSTR |
-						 STM32F4_SPI_CR1_SSM);
+	stm32_spi_set_bits(spi, STM32FX_SPI_CR1, STM32FX_SPI_CR1_SSI |
+						 STM32FX_SPI_CR1_BIDIOE |
+						 STM32FX_SPI_CR1_MSTR |
+						 STM32FX_SPI_CR1_SSM);
 
 	spin_unlock_irqrestore(&spi->lock, flags);
 
@@ -1729,8 +1931,8 @@ static int stm32h7_spi_config(struct stm32_spi *spi)
 		cr1 |= STM32H7_SPI_CR1_HDDIR | STM32H7_SPI_CR1_MASRX | STM32H7_SPI_CR1_SSI;
 
 		/*
-		 * - Set the master mode (default Motorola mode)
-		 * - Consider 1 master/n devices configuration and
+		 * - Set the host mode (default Motorola mode)
+		 * - Consider 1 host/n devices configuration and
 		 *   SS input value is determined by the SSI bit
 		 * - keep control of all associated GPIOs
 		 */
@@ -1746,25 +1948,48 @@ static int stm32h7_spi_config(struct stm32_spi *spi)
 }
 
 static const struct stm32_spi_cfg stm32f4_spi_cfg = {
-	.regs = &stm32f4_spi_regspec,
+	.regs = &stm32fx_spi_regspec,
 	.get_bpw_mask = stm32f4_spi_get_bpw_mask,
-	.disable = stm32f4_spi_disable,
-	.config = stm32f4_spi_config,
+	.disable = stm32fx_spi_disable,
+	.config = stm32fx_spi_config,
 	.set_bpw = stm32f4_spi_set_bpw,
-	.set_mode = stm32f4_spi_set_mode,
-	.transfer_one_dma_start = stm32f4_spi_transfer_one_dma_start,
-	.dma_tx_cb = stm32f4_spi_dma_tx_cb,
+	.set_mode = stm32fx_spi_set_mode,
+	.write_tx = stm32f4_spi_write_tx,
+	.read_rx = stm32f4_spi_read_rx,
+	.transfer_one_dma_start = stm32fx_spi_transfer_one_dma_start,
+	.dma_tx_cb = stm32fx_spi_dma_tx_cb,
 	.dma_rx_cb = stm32_spi_dma_rx_cb,
-	.transfer_one_irq = stm32f4_spi_transfer_one_irq,
-	.irq_handler_event = stm32f4_spi_irq_event,
-	.irq_handler_thread = stm32f4_spi_irq_thread,
-	.baud_rate_div_min = STM32F4_SPI_BR_DIV_MIN,
-	.baud_rate_div_max = STM32F4_SPI_BR_DIV_MAX,
+	.transfer_one_irq = stm32fx_spi_transfer_one_irq,
+	.irq_handler_event = stm32fx_spi_irq_event,
+	.irq_handler_thread = stm32fx_spi_irq_thread,
+	.baud_rate_div_min = STM32FX_SPI_BR_DIV_MIN,
+	.baud_rate_div_max = STM32FX_SPI_BR_DIV_MAX,
 	.has_fifo = false,
 	.has_device_mode = false,
 	.flags = SPI_CONTROLLER_MUST_TX,
 };
 
+static const struct stm32_spi_cfg stm32f7_spi_cfg = {
+	.regs = &stm32fx_spi_regspec,
+	.get_bpw_mask = stm32f7_spi_get_bpw_mask,
+	.disable = stm32fx_spi_disable,
+	.config = stm32fx_spi_config,
+	.set_bpw = stm32f7_spi_set_bpw,
+	.set_mode = stm32fx_spi_set_mode,
+	.write_tx = stm32f7_spi_write_tx,
+	.read_rx = stm32f7_spi_read_rx,
+	.transfer_one_dma_start = stm32f7_spi_transfer_one_dma_start,
+	.dma_tx_cb = stm32fx_spi_dma_tx_cb,
+	.dma_rx_cb = stm32_spi_dma_rx_cb,
+	.transfer_one_irq = stm32fx_spi_transfer_one_irq,
+	.irq_handler_event = stm32fx_spi_irq_event,
+	.irq_handler_thread = stm32fx_spi_irq_thread,
+	.baud_rate_div_min = STM32FX_SPI_BR_DIV_MIN,
+	.baud_rate_div_max = STM32FX_SPI_BR_DIV_MAX,
+	.has_fifo = false,
+	.flags = SPI_CONTROLLER_MUST_TX,
+};
+
 static const struct stm32_spi_cfg stm32h7_spi_cfg = {
 	.regs = &stm32h7_spi_regspec,
 	.get_fifo_size = stm32h7_spi_get_fifo_size,
@@ -1775,6 +2000,8 @@ static const struct stm32_spi_cfg stm32h7_spi_cfg = {
 	.set_mode = stm32h7_spi_set_mode,
 	.set_data_idleness = stm32h7_spi_data_idleness,
 	.set_number_of_data = stm32h7_spi_number_of_data,
+	.write_tx = stm32h7_spi_write_txfifo,
+	.read_rx = stm32h7_spi_read_rxfifo,
 	.transfer_one_dma_start = stm32h7_spi_transfer_one_dma_start,
 	.dma_rx_cb = stm32_spi_dma_rx_cb,
 	/*
@@ -1789,9 +2016,40 @@ static const struct stm32_spi_cfg stm32h7_spi_cfg = {
 	.has_device_mode = true,
 };
 
+/*
+ * STM32MP2 is compatible with the STM32H7 except:
+ * - enforce the DMA maxburst value to 1
+ * - spi8 have limited feature set (TSIZE_MAX = 1024, BPW of 8 OR 16)
+ */
+static const struct stm32_spi_cfg stm32mp25_spi_cfg = {
+	.regs = &stm32mp25_spi_regspec,
+	.get_fifo_size = stm32h7_spi_get_fifo_size,
+	.get_bpw_mask = stm32mp25_spi_get_bpw_mask,
+	.disable = stm32h7_spi_disable,
+	.config = stm32h7_spi_config,
+	.set_bpw = stm32h7_spi_set_bpw,
+	.set_mode = stm32h7_spi_set_mode,
+	.set_data_idleness = stm32h7_spi_data_idleness,
+	.set_number_of_data = stm32h7_spi_number_of_data,
+	.transfer_one_dma_start = stm32h7_spi_transfer_one_dma_start,
+	.dma_rx_cb = stm32_spi_dma_rx_cb,
+	/*
+	 * dma_tx_cb is not necessary since in case of TX, dma is followed by
+	 * SPI access hence handling is performed within the SPI interrupt
+	 */
+	.transfer_one_irq = stm32h7_spi_transfer_one_irq,
+	.irq_handler_thread = stm32h7_spi_irq_thread,
+	.baud_rate_div_min = STM32H7_SPI_MBR_DIV_MIN,
+	.baud_rate_div_max = STM32H7_SPI_MBR_DIV_MAX,
+	.has_fifo = true,
+	.prevent_dma_burst = true,
+};
+
 static const struct of_device_id stm32_spi_of_match[] = {
+	{ .compatible = "st,stm32mp25-spi", .data = (void *)&stm32mp25_spi_cfg },
 	{ .compatible = "st,stm32h7-spi", .data = (void *)&stm32h7_spi_cfg },
 	{ .compatible = "st,stm32f4-spi", .data = (void *)&stm32f4_spi_cfg },
+	{ .compatible = "st,stm32f7-spi", .data = (void *)&stm32f7_spi_cfg },
 	{},
 };
 MODULE_DEVICE_TABLE(of, stm32_spi_of_match);
@@ -1820,9 +2078,9 @@ static int stm32_spi_probe(struct platform_device *pdev)
 	}
 
 	if (device_mode)
-		ctrl = devm_spi_alloc_slave(&pdev->dev, sizeof(struct stm32_spi));
+		ctrl = devm_spi_alloc_target(&pdev->dev, sizeof(struct stm32_spi));
 	else
-		ctrl = devm_spi_alloc_master(&pdev->dev, sizeof(struct stm32_spi));
+		ctrl = devm_spi_alloc_host(&pdev->dev, sizeof(struct stm32_spi));
 	if (!ctrl) {
 		dev_err(&pdev->dev, "spi controller allocation failed\n");
 		return -ENOMEM;
@@ -1892,6 +2150,22 @@ static int stm32_spi_probe(struct platform_device *pdev)
 	if (spi->cfg->has_fifo)
 		spi->fifo_size = spi->cfg->get_fifo_size(spi);
 
+	spi->feature_set = STM32_SPI_FEATURE_FULL;
+	if (spi->cfg->regs->fullcfg.reg) {
+		spi->feature_set =
+			FIELD_GET(STM32MP25_SPI_HWCFGR1_FULLCFG,
+				  readl_relaxed(spi->base + spi->cfg->regs->fullcfg.reg));
+
+		dev_dbg(spi->dev, "%s feature set\n",
+			spi->feature_set == STM32_SPI_FEATURE_FULL ? "full" : "limited");
+	}
+
+	/* Only for STM32H7 and after */
+	spi->t_size_max = spi->feature_set == STM32_SPI_FEATURE_FULL ?
+				STM32H7_SPI_TSIZE_MAX :
+				STM32MP25_SPI_TSIZE_MAX_LIMITED;
+	dev_dbg(spi->dev, "one message max size %d\n", spi->t_size_max);
+
 	ret = spi->cfg->config(spi);
 	if (ret) {
 		dev_err(&pdev->dev, "controller configuration failed: %d\n",
@@ -1913,7 +2187,7 @@ static int stm32_spi_probe(struct platform_device *pdev)
 	ctrl->unprepare_message = stm32_spi_unprepare_msg;
 	ctrl->flags = spi->cfg->flags;
 	if (STM32_SPI_DEVICE_MODE(spi))
-		ctrl->slave_abort = stm32h7_spi_device_abort;
+		ctrl->target_abort = stm32h7_spi_device_abort;
 
 	spi->dma_tx = dma_request_chan(spi->dev, "tx");
 	if (IS_ERR(spi->dma_tx)) {
@@ -1960,7 +2234,7 @@ static int stm32_spi_probe(struct platform_device *pdev)
 	pm_runtime_put_autosuspend(&pdev->dev);
 
 	dev_info(&pdev->dev, "driver initialized (%s mode)\n",
-		 STM32_SPI_MASTER_MODE(spi) ? "master" : "device");
+		 STM32_SPI_HOST_MODE(spi) ? "host" : "device");
 
 	return 0;
 
diff --git a/drivers/spi/spi-sun4i.c b/drivers/spi/spi-sun4i.c
index b8947265d329..11d8bd27b3e9 100644
--- a/drivers/spi/spi-sun4i.c
+++ b/drivers/spi/spi-sun4i.c
@@ -75,7 +75,7 @@
 #define SUN4I_FIFO_STA_TF_CNT_BITS		16
 
 struct sun4i_spi {
-	struct spi_master	*master;
+	struct spi_controller	*host;
 	void __iomem		*base_addr;
 	struct clk		*hclk;
 	struct clk		*mclk;
@@ -161,7 +161,7 @@ static inline void sun4i_spi_fill_fifo(struct sun4i_spi *sspi, int len)
 
 static void sun4i_spi_set_cs(struct spi_device *spi, bool enable)
 {
-	struct sun4i_spi *sspi = spi_master_get_devdata(spi->master);
+	struct sun4i_spi *sspi = spi_controller_get_devdata(spi->controller);
 	u32 reg;
 
 	reg = sun4i_spi_read(sspi, SUN4I_CTL_REG);
@@ -201,11 +201,11 @@ static size_t sun4i_spi_max_transfer_size(struct spi_device *spi)
 	return SUN4I_MAX_XFER_SIZE - 1;
 }
 
-static int sun4i_spi_transfer_one(struct spi_master *master,
+static int sun4i_spi_transfer_one(struct spi_controller *host,
 				  struct spi_device *spi,
 				  struct spi_transfer *tfr)
 {
-	struct sun4i_spi *sspi = spi_master_get_devdata(master);
+	struct sun4i_spi *sspi = spi_controller_get_devdata(host);
 	unsigned int mclk_rate, div, timeout;
 	unsigned int start, end, tx_time;
 	unsigned int tx_len = 0;
@@ -331,7 +331,7 @@ static int sun4i_spi_transfer_one(struct spi_master *master,
 					      msecs_to_jiffies(tx_time));
 	end = jiffies;
 	if (!timeout) {
-		dev_warn(&master->dev,
+		dev_warn(&host->dev,
 			 "%s: timeout transferring %u bytes@%iHz for %i(%i)ms",
 			 dev_name(&spi->dev), tfr->len, tfr->speed_hz,
 			 jiffies_to_msecs(end - start), tx_time);
@@ -386,8 +386,8 @@ static irqreturn_t sun4i_spi_handler(int irq, void *dev_id)
 
 static int sun4i_spi_runtime_resume(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct sun4i_spi *sspi = spi_master_get_devdata(master);
+	struct spi_controller *host = dev_get_drvdata(dev);
+	struct sun4i_spi *sspi = spi_controller_get_devdata(host);
 	int ret;
 
 	ret = clk_prepare_enable(sspi->hclk);
@@ -415,8 +415,8 @@ out:
 
 static int sun4i_spi_runtime_suspend(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct sun4i_spi *sspi = spi_master_get_devdata(master);
+	struct spi_controller *host = dev_get_drvdata(dev);
+	struct sun4i_spi *sspi = spi_controller_get_devdata(host);
 
 	clk_disable_unprepare(sspi->mclk);
 	clk_disable_unprepare(sspi->hclk);
@@ -426,62 +426,62 @@ static int sun4i_spi_runtime_suspend(struct device *dev)
 
 static int sun4i_spi_probe(struct platform_device *pdev)
 {
-	struct spi_master *master;
+	struct spi_controller *host;
 	struct sun4i_spi *sspi;
 	int ret = 0, irq;
 
-	master = spi_alloc_master(&pdev->dev, sizeof(struct sun4i_spi));
-	if (!master) {
-		dev_err(&pdev->dev, "Unable to allocate SPI Master\n");
+	host = spi_alloc_host(&pdev->dev, sizeof(struct sun4i_spi));
+	if (!host) {
+		dev_err(&pdev->dev, "Unable to allocate SPI Host\n");
 		return -ENOMEM;
 	}
 
-	platform_set_drvdata(pdev, master);
-	sspi = spi_master_get_devdata(master);
+	platform_set_drvdata(pdev, host);
+	sspi = spi_controller_get_devdata(host);
 
 	sspi->base_addr = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(sspi->base_addr)) {
 		ret = PTR_ERR(sspi->base_addr);
-		goto err_free_master;
+		goto err_free_host;
 	}
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
 		ret = -ENXIO;
-		goto err_free_master;
+		goto err_free_host;
 	}
 
 	ret = devm_request_irq(&pdev->dev, irq, sun4i_spi_handler,
 			       0, "sun4i-spi", sspi);
 	if (ret) {
 		dev_err(&pdev->dev, "Cannot request IRQ\n");
-		goto err_free_master;
+		goto err_free_host;
 	}
 
-	sspi->master = master;
-	master->max_speed_hz = 100 * 1000 * 1000;
-	master->min_speed_hz = 3 * 1000;
-	master->set_cs = sun4i_spi_set_cs;
-	master->transfer_one = sun4i_spi_transfer_one;
-	master->num_chipselect = 4;
-	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LSB_FIRST;
-	master->bits_per_word_mask = SPI_BPW_MASK(8);
-	master->dev.of_node = pdev->dev.of_node;
-	master->auto_runtime_pm = true;
-	master->max_transfer_size = sun4i_spi_max_transfer_size;
+	sspi->host = host;
+	host->max_speed_hz = 100 * 1000 * 1000;
+	host->min_speed_hz = 3 * 1000;
+	host->set_cs = sun4i_spi_set_cs;
+	host->transfer_one = sun4i_spi_transfer_one;
+	host->num_chipselect = 4;
+	host->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LSB_FIRST;
+	host->bits_per_word_mask = SPI_BPW_MASK(8);
+	host->dev.of_node = pdev->dev.of_node;
+	host->auto_runtime_pm = true;
+	host->max_transfer_size = sun4i_spi_max_transfer_size;
 
 	sspi->hclk = devm_clk_get(&pdev->dev, "ahb");
 	if (IS_ERR(sspi->hclk)) {
 		dev_err(&pdev->dev, "Unable to acquire AHB clock\n");
 		ret = PTR_ERR(sspi->hclk);
-		goto err_free_master;
+		goto err_free_host;
 	}
 
 	sspi->mclk = devm_clk_get(&pdev->dev, "mod");
 	if (IS_ERR(sspi->mclk)) {
 		dev_err(&pdev->dev, "Unable to acquire module clock\n");
 		ret = PTR_ERR(sspi->mclk);
-		goto err_free_master;
+		goto err_free_host;
 	}
 
 	init_completion(&sspi->done);
@@ -493,16 +493,16 @@ static int sun4i_spi_probe(struct platform_device *pdev)
 	ret = sun4i_spi_runtime_resume(&pdev->dev);
 	if (ret) {
 		dev_err(&pdev->dev, "Couldn't resume the device\n");
-		goto err_free_master;
+		goto err_free_host;
 	}
 
 	pm_runtime_set_active(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
 	pm_runtime_idle(&pdev->dev);
 
-	ret = devm_spi_register_master(&pdev->dev, master);
+	ret = devm_spi_register_controller(&pdev->dev, host);
 	if (ret) {
-		dev_err(&pdev->dev, "cannot register SPI master\n");
+		dev_err(&pdev->dev, "cannot register SPI host\n");
 		goto err_pm_disable;
 	}
 
@@ -511,8 +511,8 @@ static int sun4i_spi_probe(struct platform_device *pdev)
 err_pm_disable:
 	pm_runtime_disable(&pdev->dev);
 	sun4i_spi_runtime_suspend(&pdev->dev);
-err_free_master:
-	spi_master_put(master);
+err_free_host:
+	spi_controller_put(host);
 	return ret;
 }
 
diff --git a/drivers/spi/spi-sun6i.c b/drivers/spi/spi-sun6i.c
index fddc63309773..cd018ea1abf1 100644
--- a/drivers/spi/spi-sun6i.c
+++ b/drivers/spi/spi-sun6i.c
@@ -97,7 +97,7 @@ struct sun6i_spi_cfg {
 };
 
 struct sun6i_spi {
-	struct spi_master	*master;
+	struct spi_controller	*host;
 	void __iomem		*base_addr;
 	dma_addr_t		dma_addr_rx;
 	dma_addr_t		dma_addr_tx;
@@ -181,7 +181,7 @@ static inline void sun6i_spi_fill_fifo(struct sun6i_spi *sspi)
 
 static void sun6i_spi_set_cs(struct spi_device *spi, bool enable)
 {
-	struct sun6i_spi *sspi = spi_master_get_devdata(spi->master);
+	struct sun6i_spi *sspi = spi_controller_get_devdata(spi->controller);
 	u32 reg;
 
 	reg = sun6i_spi_read(sspi, SUN6I_TFR_CTL_REG);
@@ -212,7 +212,7 @@ static int sun6i_spi_prepare_dma(struct sun6i_spi *sspi,
 				 struct spi_transfer *tfr)
 {
 	struct dma_async_tx_descriptor *rxdesc, *txdesc;
-	struct spi_master *master = sspi->master;
+	struct spi_controller *host = sspi->host;
 
 	rxdesc = NULL;
 	if (tfr->rx_buf) {
@@ -223,9 +223,9 @@ static int sun6i_spi_prepare_dma(struct sun6i_spi *sspi,
 			.src_maxburst = 8,
 		};
 
-		dmaengine_slave_config(master->dma_rx, &rxconf);
+		dmaengine_slave_config(host->dma_rx, &rxconf);
 
-		rxdesc = dmaengine_prep_slave_sg(master->dma_rx,
+		rxdesc = dmaengine_prep_slave_sg(host->dma_rx,
 						 tfr->rx_sg.sgl,
 						 tfr->rx_sg.nents,
 						 DMA_DEV_TO_MEM,
@@ -245,38 +245,38 @@ static int sun6i_spi_prepare_dma(struct sun6i_spi *sspi,
 			.dst_maxburst = 8,
 		};
 
-		dmaengine_slave_config(master->dma_tx, &txconf);
+		dmaengine_slave_config(host->dma_tx, &txconf);
 
-		txdesc = dmaengine_prep_slave_sg(master->dma_tx,
+		txdesc = dmaengine_prep_slave_sg(host->dma_tx,
 						 tfr->tx_sg.sgl,
 						 tfr->tx_sg.nents,
 						 DMA_MEM_TO_DEV,
 						 DMA_PREP_INTERRUPT);
 		if (!txdesc) {
 			if (rxdesc)
-				dmaengine_terminate_sync(master->dma_rx);
+				dmaengine_terminate_sync(host->dma_rx);
 			return -EINVAL;
 		}
 	}
 
 	if (tfr->rx_buf) {
 		dmaengine_submit(rxdesc);
-		dma_async_issue_pending(master->dma_rx);
+		dma_async_issue_pending(host->dma_rx);
 	}
 
 	if (tfr->tx_buf) {
 		dmaengine_submit(txdesc);
-		dma_async_issue_pending(master->dma_tx);
+		dma_async_issue_pending(host->dma_tx);
 	}
 
 	return 0;
 }
 
-static int sun6i_spi_transfer_one(struct spi_master *master,
+static int sun6i_spi_transfer_one(struct spi_controller *host,
 				  struct spi_device *spi,
 				  struct spi_transfer *tfr)
 {
-	struct sun6i_spi *sspi = spi_master_get_devdata(master);
+	struct sun6i_spi *sspi = spi_controller_get_devdata(host);
 	unsigned int div, div_cdr1, div_cdr2, timeout;
 	unsigned int start, end, tx_time;
 	unsigned int trig_level;
@@ -293,7 +293,7 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 	sspi->tx_buf = tfr->tx_buf;
 	sspi->rx_buf = tfr->rx_buf;
 	sspi->len = tfr->len;
-	use_dma = master->can_dma ? master->can_dma(master, spi, tfr) : false;
+	use_dma = host->can_dma ? host->can_dma(host, spi, tfr) : false;
 
 	/* Clear pending interrupts */
 	sun6i_spi_write(sspi, SUN6I_INT_STA_REG, ~0);
@@ -463,7 +463,7 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 	} else {
 		ret = sun6i_spi_prepare_dma(sspi, tfr);
 		if (ret) {
-			dev_warn(&master->dev,
+			dev_warn(&host->dev,
 				 "%s: prepare DMA failed, ret=%d",
 				 dev_name(&spi->dev), ret);
 			return ret;
@@ -486,7 +486,7 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 	reg = sun6i_spi_read(sspi, SUN6I_TFR_CTL_REG);
 	sun6i_spi_write(sspi, SUN6I_TFR_CTL_REG, reg | SUN6I_TFR_CTL_XCH);
 
-	tx_time = spi_controller_xfer_timeout(master, tfr);
+	tx_time = spi_controller_xfer_timeout(host, tfr);
 	start = jiffies;
 	timeout = wait_for_completion_timeout(&sspi->done,
 					      msecs_to_jiffies(tx_time));
@@ -502,13 +502,13 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 			timeout = wait_for_completion_timeout(&sspi->dma_rx_done,
 							      timeout);
 			if (!timeout)
-				dev_warn(&master->dev, "RX DMA timeout\n");
+				dev_warn(&host->dev, "RX DMA timeout\n");
 		}
 	}
 
 	end = jiffies;
 	if (!timeout) {
-		dev_warn(&master->dev,
+		dev_warn(&host->dev,
 			 "%s: timeout transferring %u bytes@%iHz for %i(%i)ms",
 			 dev_name(&spi->dev), tfr->len, tfr->speed_hz,
 			 jiffies_to_msecs(end - start), tx_time);
@@ -518,8 +518,8 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 	sun6i_spi_write(sspi, SUN6I_INT_CTL_REG, 0);
 
 	if (ret && use_dma) {
-		dmaengine_terminate_sync(master->dma_rx);
-		dmaengine_terminate_sync(master->dma_tx);
+		dmaengine_terminate_sync(host->dma_rx);
+		dmaengine_terminate_sync(host->dma_tx);
 	}
 
 	return ret;
@@ -564,8 +564,8 @@ static irqreturn_t sun6i_spi_handler(int irq, void *dev_id)
 
 static int sun6i_spi_runtime_resume(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct sun6i_spi *sspi = spi_master_get_devdata(master);
+	struct spi_controller *host = dev_get_drvdata(dev);
+	struct sun6i_spi *sspi = spi_controller_get_devdata(host);
 	int ret;
 
 	ret = clk_prepare_enable(sspi->hclk);
@@ -601,8 +601,8 @@ out:
 
 static int sun6i_spi_runtime_suspend(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct sun6i_spi *sspi = spi_master_get_devdata(master);
+	struct spi_controller *host = dev_get_drvdata(dev);
+	struct sun6i_spi *sspi = spi_controller_get_devdata(host);
 
 	reset_control_assert(sspi->rstc);
 	clk_disable_unprepare(sspi->mclk);
@@ -611,11 +611,11 @@ static int sun6i_spi_runtime_suspend(struct device *dev)
 	return 0;
 }
 
-static bool sun6i_spi_can_dma(struct spi_master *master,
+static bool sun6i_spi_can_dma(struct spi_controller *host,
 			      struct spi_device *spi,
 			      struct spi_transfer *xfer)
 {
-	struct sun6i_spi *sspi = spi_master_get_devdata(master);
+	struct sun6i_spi *sspi = spi_controller_get_devdata(host);
 
 	/*
 	 * If the number of spi words to transfer is less or equal than
@@ -627,67 +627,67 @@ static bool sun6i_spi_can_dma(struct spi_master *master,
 
 static int sun6i_spi_probe(struct platform_device *pdev)
 {
-	struct spi_master *master;
+	struct spi_controller *host;
 	struct sun6i_spi *sspi;
 	struct resource *mem;
 	int ret = 0, irq;
 
-	master = spi_alloc_master(&pdev->dev, sizeof(struct sun6i_spi));
-	if (!master) {
-		dev_err(&pdev->dev, "Unable to allocate SPI Master\n");
+	host = spi_alloc_host(&pdev->dev, sizeof(struct sun6i_spi));
+	if (!host) {
+		dev_err(&pdev->dev, "Unable to allocate SPI Host\n");
 		return -ENOMEM;
 	}
 
-	platform_set_drvdata(pdev, master);
-	sspi = spi_master_get_devdata(master);
+	platform_set_drvdata(pdev, host);
+	sspi = spi_controller_get_devdata(host);
 
 	sspi->base_addr = devm_platform_get_and_ioremap_resource(pdev, 0, &mem);
 	if (IS_ERR(sspi->base_addr)) {
 		ret = PTR_ERR(sspi->base_addr);
-		goto err_free_master;
+		goto err_free_host;
 	}
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
 		ret = -ENXIO;
-		goto err_free_master;
+		goto err_free_host;
 	}
 
 	ret = devm_request_irq(&pdev->dev, irq, sun6i_spi_handler,
 			       0, "sun6i-spi", sspi);
 	if (ret) {
 		dev_err(&pdev->dev, "Cannot request IRQ\n");
-		goto err_free_master;
+		goto err_free_host;
 	}
 
-	sspi->master = master;
+	sspi->host = host;
 	sspi->cfg = of_device_get_match_data(&pdev->dev);
 
-	master->max_speed_hz = 100 * 1000 * 1000;
-	master->min_speed_hz = 3 * 1000;
-	master->use_gpio_descriptors = true;
-	master->set_cs = sun6i_spi_set_cs;
-	master->transfer_one = sun6i_spi_transfer_one;
-	master->num_chipselect = 4;
-	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LSB_FIRST |
-			    sspi->cfg->mode_bits;
-	master->bits_per_word_mask = SPI_BPW_MASK(8);
-	master->dev.of_node = pdev->dev.of_node;
-	master->auto_runtime_pm = true;
-	master->max_transfer_size = sun6i_spi_max_transfer_size;
+	host->max_speed_hz = 100 * 1000 * 1000;
+	host->min_speed_hz = 3 * 1000;
+	host->use_gpio_descriptors = true;
+	host->set_cs = sun6i_spi_set_cs;
+	host->transfer_one = sun6i_spi_transfer_one;
+	host->num_chipselect = 4;
+	host->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LSB_FIRST |
+			  sspi->cfg->mode_bits;
+	host->bits_per_word_mask = SPI_BPW_MASK(8);
+	host->dev.of_node = pdev->dev.of_node;
+	host->auto_runtime_pm = true;
+	host->max_transfer_size = sun6i_spi_max_transfer_size;
 
 	sspi->hclk = devm_clk_get(&pdev->dev, "ahb");
 	if (IS_ERR(sspi->hclk)) {
 		dev_err(&pdev->dev, "Unable to acquire AHB clock\n");
 		ret = PTR_ERR(sspi->hclk);
-		goto err_free_master;
+		goto err_free_host;
 	}
 
 	sspi->mclk = devm_clk_get(&pdev->dev, "mod");
 	if (IS_ERR(sspi->mclk)) {
 		dev_err(&pdev->dev, "Unable to acquire module clock\n");
 		ret = PTR_ERR(sspi->mclk);
-		goto err_free_master;
+		goto err_free_host;
 	}
 
 	init_completion(&sspi->done);
@@ -697,34 +697,34 @@ static int sun6i_spi_probe(struct platform_device *pdev)
 	if (IS_ERR(sspi->rstc)) {
 		dev_err(&pdev->dev, "Couldn't get reset controller\n");
 		ret = PTR_ERR(sspi->rstc);
-		goto err_free_master;
+		goto err_free_host;
 	}
 
-	master->dma_tx = dma_request_chan(&pdev->dev, "tx");
-	if (IS_ERR(master->dma_tx)) {
+	host->dma_tx = dma_request_chan(&pdev->dev, "tx");
+	if (IS_ERR(host->dma_tx)) {
 		/* Check tx to see if we need defer probing driver */
-		if (PTR_ERR(master->dma_tx) == -EPROBE_DEFER) {
+		if (PTR_ERR(host->dma_tx) == -EPROBE_DEFER) {
 			ret = -EPROBE_DEFER;
-			goto err_free_master;
+			goto err_free_host;
 		}
 		dev_warn(&pdev->dev, "Failed to request TX DMA channel\n");
-		master->dma_tx = NULL;
+		host->dma_tx = NULL;
 	}
 
-	master->dma_rx = dma_request_chan(&pdev->dev, "rx");
-	if (IS_ERR(master->dma_rx)) {
-		if (PTR_ERR(master->dma_rx) == -EPROBE_DEFER) {
+	host->dma_rx = dma_request_chan(&pdev->dev, "rx");
+	if (IS_ERR(host->dma_rx)) {
+		if (PTR_ERR(host->dma_rx) == -EPROBE_DEFER) {
 			ret = -EPROBE_DEFER;
 			goto err_free_dma_tx;
 		}
 		dev_warn(&pdev->dev, "Failed to request RX DMA channel\n");
-		master->dma_rx = NULL;
+		host->dma_rx = NULL;
 	}
 
-	if (master->dma_tx && master->dma_rx) {
+	if (host->dma_tx && host->dma_rx) {
 		sspi->dma_addr_tx = mem->start + SUN6I_TXDATA_REG;
 		sspi->dma_addr_rx = mem->start + SUN6I_RXDATA_REG;
-		master->can_dma = sun6i_spi_can_dma;
+		host->can_dma = sun6i_spi_can_dma;
 	}
 
 	/*
@@ -742,9 +742,9 @@ static int sun6i_spi_probe(struct platform_device *pdev)
 	pm_runtime_set_active(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
 
-	ret = devm_spi_register_master(&pdev->dev, master);
+	ret = devm_spi_register_controller(&pdev->dev, host);
 	if (ret) {
-		dev_err(&pdev->dev, "cannot register SPI master\n");
+		dev_err(&pdev->dev, "cannot register SPI host\n");
 		goto err_pm_disable;
 	}
 
@@ -754,26 +754,26 @@ err_pm_disable:
 	pm_runtime_disable(&pdev->dev);
 	sun6i_spi_runtime_suspend(&pdev->dev);
 err_free_dma_rx:
-	if (master->dma_rx)
-		dma_release_channel(master->dma_rx);
+	if (host->dma_rx)
+		dma_release_channel(host->dma_rx);
 err_free_dma_tx:
-	if (master->dma_tx)
-		dma_release_channel(master->dma_tx);
-err_free_master:
-	spi_master_put(master);
+	if (host->dma_tx)
+		dma_release_channel(host->dma_tx);
+err_free_host:
+	spi_controller_put(host);
 	return ret;
 }
 
 static void sun6i_spi_remove(struct platform_device *pdev)
 {
-	struct spi_master *master = platform_get_drvdata(pdev);
+	struct spi_controller *host = platform_get_drvdata(pdev);
 
 	pm_runtime_force_suspend(&pdev->dev);
 
-	if (master->dma_tx)
-		dma_release_channel(master->dma_tx);
-	if (master->dma_rx)
-		dma_release_channel(master->dma_rx);
+	if (host->dma_tx)
+		dma_release_channel(host->dma_tx);
+	if (host->dma_rx)
+		dma_release_channel(host->dma_rx);
 }
 
 static const struct sun6i_spi_cfg sun6i_a31_spi_cfg = {
diff --git a/drivers/spi/spi-sunplus-sp7021.c b/drivers/spi/spi-sunplus-sp7021.c
index eb8f835a4771..4e481380c259 100644
--- a/drivers/spi/spi-sunplus-sp7021.c
+++ b/drivers/spi/spi-sunplus-sp7021.c
@@ -70,8 +70,8 @@
 #define SP7021_FIFO_DATA_LEN		(16)
 
 enum {
-	SP7021_MASTER_MODE = 0,
-	SP7021_SLAVE_MODE = 1,
+	SP7021_HOST_MODE = 0,
+	SP7021_TARGET_MODE = 1,
 };
 
 struct sp7021_spi_ctlr {
@@ -88,7 +88,7 @@ struct sp7021_spi_ctlr {
 	// data xfer lock
 	struct mutex buf_lock;
 	struct completion isr_done;
-	struct completion slave_isr;
+	struct completion target_isr;
 	unsigned int  rx_cur_len;
 	unsigned int  tx_cur_len;
 	unsigned int  data_unit;
@@ -96,7 +96,7 @@ struct sp7021_spi_ctlr {
 	u8 *rx_buf;
 };
 
-static irqreturn_t sp7021_spi_slave_irq(int irq, void *dev)
+static irqreturn_t sp7021_spi_target_irq(int irq, void *dev)
 {
 	struct sp7021_spi_ctlr *pspim = dev;
 	unsigned int data_status;
@@ -104,25 +104,25 @@ static irqreturn_t sp7021_spi_slave_irq(int irq, void *dev)
 	data_status = readl(pspim->s_base + SP7021_DATA_RDY_REG);
 	data_status |= SP7021_SLAVE_CLR_INT;
 	writel(data_status , pspim->s_base + SP7021_DATA_RDY_REG);
-	complete(&pspim->slave_isr);
+	complete(&pspim->target_isr);
 	return IRQ_HANDLED;
 }
 
-static int sp7021_spi_slave_abort(struct spi_controller *ctlr)
+static int sp7021_spi_target_abort(struct spi_controller *ctlr)
 {
-	struct sp7021_spi_ctlr *pspim = spi_master_get_devdata(ctlr);
+	struct sp7021_spi_ctlr *pspim = spi_controller_get_devdata(ctlr);
 
-	complete(&pspim->slave_isr);
+	complete(&pspim->target_isr);
 	complete(&pspim->isr_done);
 	return 0;
 }
 
-static int sp7021_spi_slave_tx(struct spi_device *spi, struct spi_transfer *xfer)
+static int sp7021_spi_target_tx(struct spi_device *spi, struct spi_transfer *xfer)
 {
 	struct sp7021_spi_ctlr *pspim = spi_controller_get_devdata(spi->controller);
 	u32 value;
 
-	reinit_completion(&pspim->slave_isr);
+	reinit_completion(&pspim->target_isr);
 	value = SP7021_SLAVE_DMA_EN | SP7021_SLAVE_DMA_RW | FIELD_PREP(SP7021_SLAVE_DMA_CMD, 3);
 	writel(value, pspim->s_base + SP7021_SLAVE_DMA_CTRL_REG);
 	writel(xfer->len, pspim->s_base + SP7021_SLAVE_DMA_LENGTH_REG);
@@ -137,7 +137,7 @@ static int sp7021_spi_slave_tx(struct spi_device *spi, struct spi_transfer *xfer
 	return 0;
 }
 
-static int sp7021_spi_slave_rx(struct spi_device *spi, struct spi_transfer *xfer)
+static int sp7021_spi_target_rx(struct spi_device *spi, struct spi_transfer *xfer)
 {
 	struct sp7021_spi_ctlr *pspim = spi_controller_get_devdata(spi->controller);
 	u32 value;
@@ -155,7 +155,7 @@ static int sp7021_spi_slave_rx(struct spi_device *spi, struct spi_transfer *xfer
 	return 0;
 }
 
-static void sp7021_spi_master_rb(struct sp7021_spi_ctlr *pspim, unsigned int len)
+static void sp7021_spi_host_rb(struct sp7021_spi_ctlr *pspim, unsigned int len)
 {
 	int i;
 
@@ -166,7 +166,7 @@ static void sp7021_spi_master_rb(struct sp7021_spi_ctlr *pspim, unsigned int len
 	}
 }
 
-static void sp7021_spi_master_wb(struct sp7021_spi_ctlr *pspim, unsigned int len)
+static void sp7021_spi_host_wb(struct sp7021_spi_ctlr *pspim, unsigned int len)
 {
 	int i;
 
@@ -177,7 +177,7 @@ static void sp7021_spi_master_wb(struct sp7021_spi_ctlr *pspim, unsigned int len
 	}
 }
 
-static irqreturn_t sp7021_spi_master_irq(int irq, void *dev)
+static irqreturn_t sp7021_spi_host_irq(int irq, void *dev)
 {
 	struct sp7021_spi_ctlr *pspim = dev;
 	unsigned int tx_cnt, total_len;
@@ -206,9 +206,9 @@ static irqreturn_t sp7021_spi_master_irq(int irq, void *dev)
 		fd_status, rx_cnt, tx_cnt, tx_len);
 
 	if (rx_cnt > 0)
-		sp7021_spi_master_rb(pspim, rx_cnt);
+		sp7021_spi_host_rb(pspim, rx_cnt);
 	if (tx_cnt > 0)
-		sp7021_spi_master_wb(pspim, tx_cnt);
+		sp7021_spi_host_wb(pspim, tx_cnt);
 
 	fd_status = readl(pspim->m_base + SP7021_SPI_STATUS_REG);
 	tx_len = FIELD_GET(SP7021_TX_LEN_MASK, fd_status);
@@ -224,7 +224,7 @@ static irqreturn_t sp7021_spi_master_irq(int irq, void *dev)
 				rx_cnt = FIELD_GET(SP7021_RX_CNT_MASK, fd_status);
 
 			if (rx_cnt > 0)
-				sp7021_spi_master_rb(pspim, rx_cnt);
+				sp7021_spi_host_rb(pspim, rx_cnt);
 		}
 		value = readl(pspim->m_base + SP7021_INT_BUSY_REG);
 		value |= SP7021_CLR_MASTER_INT;
@@ -240,7 +240,7 @@ static irqreturn_t sp7021_spi_master_irq(int irq, void *dev)
 
 static void sp7021_prep_transfer(struct spi_controller *ctlr, struct spi_device *spi)
 {
-	struct sp7021_spi_ctlr *pspim = spi_master_get_devdata(ctlr);
+	struct sp7021_spi_ctlr *pspim = spi_controller_get_devdata(ctlr);
 
 	pspim->tx_cur_len = 0;
 	pspim->rx_cur_len = 0;
@@ -251,7 +251,7 @@ static void sp7021_prep_transfer(struct spi_controller *ctlr, struct spi_device
 static int sp7021_spi_controller_prepare_message(struct spi_controller *ctlr,
 						 struct spi_message *msg)
 {
-	struct sp7021_spi_ctlr *pspim = spi_master_get_devdata(ctlr);
+	struct sp7021_spi_ctlr *pspim = spi_controller_get_devdata(ctlr);
 	struct spi_device *s = msg->spi;
 	u32 valus, rs = 0;
 
@@ -283,7 +283,7 @@ static int sp7021_spi_controller_prepare_message(struct spi_controller *ctlr,
 
 static void sp7021_spi_setup_clk(struct spi_controller *ctlr, struct spi_transfer *xfer)
 {
-	struct sp7021_spi_ctlr *pspim = spi_master_get_devdata(ctlr);
+	struct sp7021_spi_ctlr *pspim = spi_controller_get_devdata(ctlr);
 	u32 clk_rate, clk_sel, div;
 
 	clk_rate = clk_get_rate(pspim->spi_clk);
@@ -295,10 +295,10 @@ static void sp7021_spi_setup_clk(struct spi_controller *ctlr, struct spi_transfe
 	writel(pspim->xfer_conf, pspim->m_base + SP7021_SPI_CONFIG_REG);
 }
 
-static int sp7021_spi_master_transfer_one(struct spi_controller *ctlr, struct spi_device *spi,
+static int sp7021_spi_host_transfer_one(struct spi_controller *ctlr, struct spi_device *spi,
 				       struct spi_transfer *xfer)
 {
-	struct sp7021_spi_ctlr *pspim = spi_master_get_devdata(ctlr);
+	struct sp7021_spi_ctlr *pspim = spi_controller_get_devdata(ctlr);
 	unsigned long timeout = msecs_to_jiffies(1000);
 	unsigned int xfer_cnt, xfer_len, last_len;
 	unsigned int i, len_temp;
@@ -323,7 +323,7 @@ static int sp7021_spi_master_transfer_one(struct spi_controller *ctlr, struct sp
 
 		if (pspim->tx_cur_len < xfer_len) {
 			len_temp = min(pspim->data_unit, xfer_len);
-			sp7021_spi_master_wb(pspim, len_temp);
+			sp7021_spi_host_wb(pspim, len_temp);
 		}
 		reg_temp = readl(pspim->m_base + SP7021_SPI_CONFIG_REG);
 		reg_temp &= ~SP7021_CLEAN_RW_BYTE;
@@ -359,10 +359,10 @@ static int sp7021_spi_master_transfer_one(struct spi_controller *ctlr, struct sp
 	return 0;
 }
 
-static int sp7021_spi_slave_transfer_one(struct spi_controller *ctlr, struct spi_device *spi,
+static int sp7021_spi_target_transfer_one(struct spi_controller *ctlr, struct spi_device *spi,
 				       struct spi_transfer *xfer)
 {
-	struct sp7021_spi_ctlr *pspim = spi_master_get_devdata(ctlr);
+	struct sp7021_spi_ctlr *pspim = spi_controller_get_devdata(ctlr);
 	struct device *dev = pspim->dev;
 	int ret;
 
@@ -371,14 +371,14 @@ static int sp7021_spi_slave_transfer_one(struct spi_controller *ctlr, struct spi
 					      xfer->len, DMA_TO_DEVICE);
 		if (dma_mapping_error(dev, xfer->tx_dma))
 			return -ENOMEM;
-		ret = sp7021_spi_slave_tx(spi, xfer);
+		ret = sp7021_spi_target_tx(spi, xfer);
 		dma_unmap_single(dev, xfer->tx_dma, xfer->len, DMA_TO_DEVICE);
 	} else if (xfer->rx_buf && !xfer->tx_buf) {
 		xfer->rx_dma = dma_map_single(dev, xfer->rx_buf, xfer->len,
 					      DMA_FROM_DEVICE);
 		if (dma_mapping_error(dev, xfer->rx_dma))
 			return -ENOMEM;
-		ret = sp7021_spi_slave_rx(spi, xfer);
+		ret = sp7021_spi_target_rx(spi, xfer);
 		dma_unmap_single(dev, xfer->rx_dma, xfer->len, DMA_FROM_DEVICE);
 	} else {
 		dev_dbg(&ctlr->dev, "%s() wrong command\n", __func__);
@@ -409,14 +409,14 @@ static int sp7021_spi_controller_probe(struct platform_device *pdev)
 	pdev->id = of_alias_get_id(pdev->dev.of_node, "sp_spi");
 
 	if (device_property_read_bool(dev, "spi-slave"))
-		mode = SP7021_SLAVE_MODE;
+		mode = SP7021_TARGET_MODE;
 	else
-		mode = SP7021_MASTER_MODE;
+		mode = SP7021_HOST_MODE;
 
-	if (mode == SP7021_SLAVE_MODE)
-		ctlr = devm_spi_alloc_slave(dev, sizeof(*pspim));
+	if (mode == SP7021_TARGET_MODE)
+		ctlr = devm_spi_alloc_target(dev, sizeof(*pspim));
 	else
-		ctlr = devm_spi_alloc_master(dev, sizeof(*pspim));
+		ctlr = devm_spi_alloc_host(dev, sizeof(*pspim));
 	if (!ctlr)
 		return -ENOMEM;
 	device_set_node(&ctlr->dev, dev_fwnode(dev));
@@ -424,9 +424,9 @@ static int sp7021_spi_controller_probe(struct platform_device *pdev)
 	ctlr->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LSB_FIRST;
 	ctlr->auto_runtime_pm = true;
 	ctlr->prepare_message = sp7021_spi_controller_prepare_message;
-	if (mode == SP7021_SLAVE_MODE) {
-		ctlr->transfer_one = sp7021_spi_slave_transfer_one;
-		ctlr->slave_abort = sp7021_spi_slave_abort;
+	if (mode == SP7021_TARGET_MODE) {
+		ctlr->transfer_one = sp7021_spi_target_transfer_one;
+		ctlr->target_abort = sp7021_spi_target_abort;
 		ctlr->flags = SPI_CONTROLLER_HALF_DUPLEX;
 	} else {
 		ctlr->bits_per_word_mask = SPI_BPW_MASK(8);
@@ -434,7 +434,7 @@ static int sp7021_spi_controller_probe(struct platform_device *pdev)
 		ctlr->max_speed_hz = 25000000;
 		ctlr->use_gpio_descriptors = true;
 		ctlr->flags = SPI_CONTROLLER_MUST_RX | SPI_CONTROLLER_MUST_TX;
-		ctlr->transfer_one = sp7021_spi_master_transfer_one;
+		ctlr->transfer_one = sp7021_spi_host_transfer_one;
 	}
 	platform_set_drvdata(pdev, ctlr);
 	pspim = spi_controller_get_devdata(ctlr);
@@ -443,7 +443,7 @@ static int sp7021_spi_controller_probe(struct platform_device *pdev)
 	pspim->dev = dev;
 	mutex_init(&pspim->buf_lock);
 	init_completion(&pspim->isr_done);
-	init_completion(&pspim->slave_isr);
+	init_completion(&pspim->target_isr);
 
 	pspim->m_base = devm_platform_ioremap_resource_byname(pdev, "master");
 	if (IS_ERR(pspim->m_base))
@@ -485,12 +485,12 @@ static int sp7021_spi_controller_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	ret = devm_request_irq(dev, pspim->m_irq, sp7021_spi_master_irq,
+	ret = devm_request_irq(dev, pspim->m_irq, sp7021_spi_host_irq,
 			       IRQF_TRIGGER_RISING, pdev->name, pspim);
 	if (ret)
 		return ret;
 
-	ret = devm_request_irq(dev, pspim->s_irq, sp7021_spi_slave_irq,
+	ret = devm_request_irq(dev, pspim->s_irq, sp7021_spi_target_irq,
 			       IRQF_TRIGGER_RISING, pdev->name, pspim);
 	if (ret)
 		return ret;
@@ -499,7 +499,7 @@ static int sp7021_spi_controller_probe(struct platform_device *pdev)
 	ret = spi_register_controller(ctlr);
 	if (ret) {
 		pm_runtime_disable(dev);
-		return dev_err_probe(dev, ret, "spi_register_master fail\n");
+		return dev_err_probe(dev, ret, "spi_register_controller fail\n");
 	}
 	return 0;
 }
@@ -516,7 +516,7 @@ static void sp7021_spi_controller_remove(struct platform_device *pdev)
 static int __maybe_unused sp7021_spi_controller_suspend(struct device *dev)
 {
 	struct spi_controller *ctlr = dev_get_drvdata(dev);
-	struct sp7021_spi_ctlr *pspim = spi_master_get_devdata(ctlr);
+	struct sp7021_spi_ctlr *pspim = spi_controller_get_devdata(ctlr);
 
 	return reset_control_assert(pspim->rstc);
 }
@@ -524,7 +524,7 @@ static int __maybe_unused sp7021_spi_controller_suspend(struct device *dev)
 static int __maybe_unused sp7021_spi_controller_resume(struct device *dev)
 {
 	struct spi_controller *ctlr = dev_get_drvdata(dev);
-	struct sp7021_spi_ctlr *pspim = spi_master_get_devdata(ctlr);
+	struct sp7021_spi_ctlr *pspim = spi_controller_get_devdata(ctlr);
 
 	reset_control_deassert(pspim->rstc);
 	return clk_prepare_enable(pspim->spi_clk);
@@ -534,7 +534,7 @@ static int __maybe_unused sp7021_spi_controller_resume(struct device *dev)
 static int sp7021_spi_runtime_suspend(struct device *dev)
 {
 	struct spi_controller *ctlr = dev_get_drvdata(dev);
-	struct sp7021_spi_ctlr *pspim = spi_master_get_devdata(ctlr);
+	struct sp7021_spi_ctlr *pspim = spi_controller_get_devdata(ctlr);
 
 	return reset_control_assert(pspim->rstc);
 }
@@ -542,7 +542,7 @@ static int sp7021_spi_runtime_suspend(struct device *dev)
 static int sp7021_spi_runtime_resume(struct device *dev)
 {
 	struct spi_controller *ctlr = dev_get_drvdata(dev);
-	struct sp7021_spi_ctlr *pspim = spi_master_get_devdata(ctlr);
+	struct sp7021_spi_ctlr *pspim = spi_controller_get_devdata(ctlr);
 
 	return reset_control_deassert(pspim->rstc);
 }
diff --git a/drivers/spi/spi-synquacer.c b/drivers/spi/spi-synquacer.c
index aeaf7db022f0..7cb4301a6fb2 100644
--- a/drivers/spi/spi-synquacer.c
+++ b/drivers/spi/spi-synquacer.c
@@ -225,11 +225,11 @@ static int write_fifo(struct synquacer_spi *sspi)
 	return 0;
 }
 
-static int synquacer_spi_config(struct spi_master *master,
+static int synquacer_spi_config(struct spi_controller *host,
 				struct spi_device *spi,
 				struct spi_transfer *xfer)
 {
-	struct synquacer_spi *sspi = spi_master_get_devdata(master);
+	struct synquacer_spi *sspi = spi_controller_get_devdata(host);
 	unsigned int speed, mode, bpw, cs, bus_width, transfer_mode;
 	u32 rate, val, div;
 
@@ -263,7 +263,7 @@ static int synquacer_spi_config(struct spi_master *master,
 	}
 
 	sspi->transfer_mode = transfer_mode;
-	rate = master->max_speed_hz;
+	rate = host->max_speed_hz;
 
 	div = DIV_ROUND_UP(rate, speed);
 	if (div > 254) {
@@ -350,11 +350,11 @@ static int synquacer_spi_config(struct spi_master *master,
 	return 0;
 }
 
-static int synquacer_spi_transfer_one(struct spi_master *master,
+static int synquacer_spi_transfer_one(struct spi_controller *host,
 				      struct spi_device *spi,
 				      struct spi_transfer *xfer)
 {
-	struct synquacer_spi *sspi = spi_master_get_devdata(master);
+	struct synquacer_spi *sspi = spi_controller_get_devdata(host);
 	int ret;
 	int status = 0;
 	u32 words;
@@ -378,7 +378,7 @@ static int synquacer_spi_transfer_one(struct spi_master *master,
 	if (bpw == 8 && !(xfer->len % 4) && !(spi->mode & SPI_LSB_FIRST))
 		xfer->bits_per_word = 32;
 
-	ret = synquacer_spi_config(master, spi, xfer);
+	ret = synquacer_spi_config(host, spi, xfer);
 
 	/* restore */
 	xfer->bits_per_word = bpw;
@@ -482,7 +482,7 @@ static int synquacer_spi_transfer_one(struct spi_master *master,
 
 static void synquacer_spi_set_cs(struct spi_device *spi, bool enable)
 {
-	struct synquacer_spi *sspi = spi_master_get_devdata(spi->master);
+	struct synquacer_spi *sspi = spi_controller_get_devdata(spi->controller);
 	u32 val;
 
 	val = readl(sspi->regs + SYNQUACER_HSSPI_REG_DMSTART);
@@ -517,11 +517,11 @@ static int synquacer_spi_wait_status_update(struct synquacer_spi *sspi,
 	return -EBUSY;
 }
 
-static int synquacer_spi_enable(struct spi_master *master)
+static int synquacer_spi_enable(struct spi_controller *host)
 {
 	u32 val;
 	int status;
-	struct synquacer_spi *sspi = spi_master_get_devdata(master);
+	struct synquacer_spi *sspi = spi_controller_get_devdata(host);
 
 	/* Disable module */
 	writel(0, sspi->regs + SYNQUACER_HSSPI_REG_MCTRL);
@@ -601,18 +601,18 @@ static irqreturn_t sq_spi_tx_handler(int irq, void *priv)
 static int synquacer_spi_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
-	struct spi_master *master;
+	struct spi_controller *host;
 	struct synquacer_spi *sspi;
 	int ret;
 	int rx_irq, tx_irq;
 
-	master = spi_alloc_master(&pdev->dev, sizeof(*sspi));
-	if (!master)
+	host = spi_alloc_host(&pdev->dev, sizeof(*sspi));
+	if (!host)
 		return -ENOMEM;
 
-	platform_set_drvdata(pdev, master);
+	platform_set_drvdata(pdev, host);
 
-	sspi = spi_master_get_devdata(master);
+	sspi = spi_controller_get_devdata(host);
 	sspi->dev = &pdev->dev;
 
 	init_completion(&sspi->transfer_done);
@@ -625,7 +625,7 @@ static int synquacer_spi_probe(struct platform_device *pdev)
 
 	sspi->clk_src_type = SYNQUACER_HSSPI_CLOCK_SRC_IHCLK; /* Default */
 	device_property_read_u32(&pdev->dev, "socionext,ihclk-rate",
-				 &master->max_speed_hz); /* for ACPI */
+				 &host->max_speed_hz); /* for ACPI */
 
 	if (dev_of_node(&pdev->dev)) {
 		if (device_property_match_string(&pdev->dev,
@@ -655,21 +655,21 @@ static int synquacer_spi_probe(struct platform_device *pdev)
 			goto put_spi;
 		}
 
-		master->max_speed_hz = clk_get_rate(sspi->clk);
+		host->max_speed_hz = clk_get_rate(sspi->clk);
 	}
 
-	if (!master->max_speed_hz) {
+	if (!host->max_speed_hz) {
 		dev_err(&pdev->dev, "missing clock source\n");
 		ret = -EINVAL;
 		goto disable_clk;
 	}
-	master->min_speed_hz = master->max_speed_hz / 254;
+	host->min_speed_hz = host->max_speed_hz / 254;
 
 	sspi->aces = device_property_read_bool(&pdev->dev,
 					       "socionext,set-aces");
 	sspi->rtm = device_property_read_bool(&pdev->dev, "socionext,use-rtm");
 
-	master->num_chipselect = SYNQUACER_HSSPI_NUM_CHIP_SELECT;
+	host->num_chipselect = SYNQUACER_HSSPI_NUM_CHIP_SELECT;
 
 	rx_irq = platform_get_irq(pdev, 0);
 	if (rx_irq <= 0) {
@@ -699,27 +699,27 @@ static int synquacer_spi_probe(struct platform_device *pdev)
 		goto disable_clk;
 	}
 
-	master->dev.of_node = np;
-	master->dev.fwnode = pdev->dev.fwnode;
-	master->auto_runtime_pm = true;
-	master->bus_num = pdev->id;
+	host->dev.of_node = np;
+	host->dev.fwnode = pdev->dev.fwnode;
+	host->auto_runtime_pm = true;
+	host->bus_num = pdev->id;
 
-	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_TX_DUAL | SPI_RX_DUAL |
-			    SPI_TX_QUAD | SPI_RX_QUAD;
-	master->bits_per_word_mask = SPI_BPW_MASK(32) | SPI_BPW_MASK(24) |
-				     SPI_BPW_MASK(16) | SPI_BPW_MASK(8);
+	host->mode_bits = SPI_CPOL | SPI_CPHA | SPI_TX_DUAL | SPI_RX_DUAL |
+			  SPI_TX_QUAD | SPI_RX_QUAD;
+	host->bits_per_word_mask = SPI_BPW_MASK(32) | SPI_BPW_MASK(24) |
+				   SPI_BPW_MASK(16) | SPI_BPW_MASK(8);
 
-	master->set_cs = synquacer_spi_set_cs;
-	master->transfer_one = synquacer_spi_transfer_one;
+	host->set_cs = synquacer_spi_set_cs;
+	host->transfer_one = synquacer_spi_transfer_one;
 
-	ret = synquacer_spi_enable(master);
+	ret = synquacer_spi_enable(host);
 	if (ret)
 		goto disable_clk;
 
 	pm_runtime_set_active(sspi->dev);
 	pm_runtime_enable(sspi->dev);
 
-	ret = devm_spi_register_master(sspi->dev, master);
+	ret = devm_spi_register_controller(sspi->dev, host);
 	if (ret)
 		goto disable_pm;
 
@@ -730,15 +730,15 @@ disable_pm:
 disable_clk:
 	clk_disable_unprepare(sspi->clk);
 put_spi:
-	spi_master_put(master);
+	spi_controller_put(host);
 
 	return ret;
 }
 
 static void synquacer_spi_remove(struct platform_device *pdev)
 {
-	struct spi_master *master = platform_get_drvdata(pdev);
-	struct synquacer_spi *sspi = spi_master_get_devdata(master);
+	struct spi_controller *host = platform_get_drvdata(pdev);
+	struct synquacer_spi *sspi = spi_controller_get_devdata(host);
 
 	pm_runtime_disable(sspi->dev);
 
@@ -747,11 +747,11 @@ static void synquacer_spi_remove(struct platform_device *pdev)
 
 static int __maybe_unused synquacer_spi_suspend(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct synquacer_spi *sspi = spi_master_get_devdata(master);
+	struct spi_controller *host = dev_get_drvdata(dev);
+	struct synquacer_spi *sspi = spi_controller_get_devdata(host);
 	int ret;
 
-	ret = spi_master_suspend(master);
+	ret = spi_controller_suspend(host);
 	if (ret)
 		return ret;
 
@@ -763,8 +763,8 @@ static int __maybe_unused synquacer_spi_suspend(struct device *dev)
 
 static int __maybe_unused synquacer_spi_resume(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct synquacer_spi *sspi = spi_master_get_devdata(master);
+	struct spi_controller *host = dev_get_drvdata(dev);
+	struct synquacer_spi *sspi = spi_controller_get_devdata(host);
 	int ret;
 
 	if (!pm_runtime_suspended(dev)) {
@@ -778,7 +778,7 @@ static int __maybe_unused synquacer_spi_resume(struct device *dev)
 			return ret;
 		}
 
-		ret = synquacer_spi_enable(master);
+		ret = synquacer_spi_enable(host);
 		if (ret) {
 			clk_disable_unprepare(sspi->clk);
 			dev_err(dev, "failed to enable spi (%d)\n", ret);
@@ -786,7 +786,7 @@ static int __maybe_unused synquacer_spi_resume(struct device *dev)
 		}
 	}
 
-	ret = spi_master_resume(master);
+	ret = spi_controller_resume(host);
 	if (ret < 0)
 		clk_disable_unprepare(sspi->clk);
 
diff --git a/drivers/spi/spi-tegra114.c b/drivers/spi/spi-tegra114.c
index 460f232dad50..bc7cc4088eea 100644
--- a/drivers/spi/spi-tegra114.c
+++ b/drivers/spi/spi-tegra114.c
@@ -164,7 +164,7 @@ struct tegra_spi_client_data {
 
 struct tegra_spi_data {
 	struct device				*dev;
-	struct spi_master			*master;
+	struct spi_controller			*host;
 	spinlock_t				lock;
 
 	struct clk				*clk;
@@ -718,7 +718,7 @@ static void tegra_spi_deinit_dma_param(struct tegra_spi_data *tspi,
 
 static int tegra_spi_set_hw_cs_timing(struct spi_device *spi)
 {
-	struct tegra_spi_data *tspi = spi_master_get_devdata(spi->master);
+	struct tegra_spi_data *tspi = spi_controller_get_devdata(spi->controller);
 	struct spi_delay *setup = &spi->cs_setup;
 	struct spi_delay *hold = &spi->cs_hold;
 	struct spi_delay *inactive = &spi->cs_inactive;
@@ -772,7 +772,7 @@ static u32 tegra_spi_setup_transfer_one(struct spi_device *spi,
 					bool is_first_of_msg,
 					bool is_single_xfer)
 {
-	struct tegra_spi_data *tspi = spi_master_get_devdata(spi->master);
+	struct tegra_spi_data *tspi = spi_controller_get_devdata(spi->controller);
 	struct tegra_spi_client_data *cdata = spi->controller_data;
 	u32 speed = t->speed_hz;
 	u8 bits_per_word = t->bits_per_word;
@@ -865,7 +865,7 @@ static u32 tegra_spi_setup_transfer_one(struct spi_device *spi,
 static int tegra_spi_start_transfer_one(struct spi_device *spi,
 		struct spi_transfer *t, u32 command1)
 {
-	struct tegra_spi_data *tspi = spi_master_get_devdata(spi->master);
+	struct tegra_spi_data *tspi = spi_controller_get_devdata(spi->controller);
 	unsigned total_fifo_words;
 	int ret;
 
@@ -912,10 +912,10 @@ static struct tegra_spi_client_data
 	*tegra_spi_parse_cdata_dt(struct spi_device *spi)
 {
 	struct tegra_spi_client_data *cdata;
-	struct device_node *slave_np;
+	struct device_node *target_np;
 
-	slave_np = spi->dev.of_node;
-	if (!slave_np) {
+	target_np = spi->dev.of_node;
+	if (!target_np) {
 		dev_dbg(&spi->dev, "device node not found\n");
 		return NULL;
 	}
@@ -924,9 +924,9 @@ static struct tegra_spi_client_data
 	if (!cdata)
 		return NULL;
 
-	of_property_read_u32(slave_np, "nvidia,tx-clk-tap-delay",
+	of_property_read_u32(target_np, "nvidia,tx-clk-tap-delay",
 			     &cdata->tx_clk_tap_delay);
-	of_property_read_u32(slave_np, "nvidia,rx-clk-tap-delay",
+	of_property_read_u32(target_np, "nvidia,rx-clk-tap-delay",
 			     &cdata->rx_clk_tap_delay);
 	return cdata;
 }
@@ -942,7 +942,7 @@ static void tegra_spi_cleanup(struct spi_device *spi)
 
 static int tegra_spi_setup(struct spi_device *spi)
 {
-	struct tegra_spi_data *tspi = spi_master_get_devdata(spi->master);
+	struct tegra_spi_data *tspi = spi_controller_get_devdata(spi->controller);
 	struct tegra_spi_client_data *cdata = spi->controller_data;
 	u32 val;
 	unsigned long flags;
@@ -993,7 +993,7 @@ static int tegra_spi_setup(struct spi_device *spi)
 
 static void tegra_spi_transfer_end(struct spi_device *spi)
 {
-	struct tegra_spi_data *tspi = spi_master_get_devdata(spi->master);
+	struct tegra_spi_data *tspi = spi_controller_get_devdata(spi->controller);
 	int cs_val = (spi->mode & SPI_CS_HIGH) ? 0 : 1;
 
 	/* GPIO based chip select control */
@@ -1025,11 +1025,11 @@ static void tegra_spi_dump_regs(struct tegra_spi_data *tspi)
 		tegra_spi_readl(tspi, SPI_FIFO_STATUS));
 }
 
-static int tegra_spi_transfer_one_message(struct spi_master *master,
+static int tegra_spi_transfer_one_message(struct spi_controller *host,
 			struct spi_message *msg)
 {
 	bool is_first_msg = true;
-	struct tegra_spi_data *tspi = spi_master_get_devdata(master);
+	struct tegra_spi_data *tspi = spi_controller_get_devdata(host);
 	struct spi_transfer *xfer;
 	struct spi_device *spi = msg->spi;
 	int ret;
@@ -1078,7 +1078,7 @@ static int tegra_spi_transfer_one_message(struct spi_master *master,
 			reset_control_assert(tspi->rst);
 			udelay(2);
 			reset_control_deassert(tspi->rst);
-			tspi->last_used_cs = master->num_chipselect + 1;
+			tspi->last_used_cs = host->num_chipselect + 1;
 			goto complete_xfer;
 		}
 
@@ -1112,7 +1112,7 @@ complete_xfer:
 	ret = 0;
 exit:
 	msg->status = ret;
-	spi_finalize_current_message(master);
+	spi_finalize_current_message(host);
 	return ret;
 }
 
@@ -1293,40 +1293,40 @@ MODULE_DEVICE_TABLE(of, tegra_spi_of_match);
 
 static int tegra_spi_probe(struct platform_device *pdev)
 {
-	struct spi_master	*master;
+	struct spi_controller	*host;
 	struct tegra_spi_data	*tspi;
 	struct resource		*r;
 	int ret, spi_irq;
 	int bus_num;
 
-	master = spi_alloc_master(&pdev->dev, sizeof(*tspi));
-	if (!master) {
-		dev_err(&pdev->dev, "master allocation failed\n");
+	host = spi_alloc_host(&pdev->dev, sizeof(*tspi));
+	if (!host) {
+		dev_err(&pdev->dev, "host allocation failed\n");
 		return -ENOMEM;
 	}
-	platform_set_drvdata(pdev, master);
-	tspi = spi_master_get_devdata(master);
+	platform_set_drvdata(pdev, host);
+	tspi = spi_controller_get_devdata(host);
 
 	if (of_property_read_u32(pdev->dev.of_node, "spi-max-frequency",
-				 &master->max_speed_hz))
-		master->max_speed_hz = 25000000; /* 25MHz */
+				 &host->max_speed_hz))
+		host->max_speed_hz = 25000000; /* 25MHz */
 
 	/* the spi->mode bits understood by this driver: */
-	master->use_gpio_descriptors = true;
-	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LSB_FIRST |
-			    SPI_TX_DUAL | SPI_RX_DUAL | SPI_3WIRE;
-	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32);
-	master->setup = tegra_spi_setup;
-	master->cleanup = tegra_spi_cleanup;
-	master->transfer_one_message = tegra_spi_transfer_one_message;
-	master->set_cs_timing = tegra_spi_set_hw_cs_timing;
-	master->num_chipselect = MAX_CHIP_SELECT;
-	master->auto_runtime_pm = true;
+	host->use_gpio_descriptors = true;
+	host->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LSB_FIRST |
+			  SPI_TX_DUAL | SPI_RX_DUAL | SPI_3WIRE;
+	host->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32);
+	host->setup = tegra_spi_setup;
+	host->cleanup = tegra_spi_cleanup;
+	host->transfer_one_message = tegra_spi_transfer_one_message;
+	host->set_cs_timing = tegra_spi_set_hw_cs_timing;
+	host->num_chipselect = MAX_CHIP_SELECT;
+	host->auto_runtime_pm = true;
 	bus_num = of_alias_get_id(pdev->dev.of_node, "spi");
 	if (bus_num >= 0)
-		master->bus_num = bus_num;
+		host->bus_num = bus_num;
 
-	tspi->master = master;
+	tspi->host = host;
 	tspi->dev = &pdev->dev;
 	spin_lock_init(&tspi->lock);
 
@@ -1334,20 +1334,20 @@ static int tegra_spi_probe(struct platform_device *pdev)
 	if (!tspi->soc_data) {
 		dev_err(&pdev->dev, "unsupported tegra\n");
 		ret = -ENODEV;
-		goto exit_free_master;
+		goto exit_free_host;
 	}
 
 	tspi->base = devm_platform_get_and_ioremap_resource(pdev, 0, &r);
 	if (IS_ERR(tspi->base)) {
 		ret = PTR_ERR(tspi->base);
-		goto exit_free_master;
+		goto exit_free_host;
 	}
 	tspi->phys = r->start;
 
 	spi_irq = platform_get_irq(pdev, 0);
 	if (spi_irq < 0) {
 		ret = spi_irq;
-		goto exit_free_master;
+		goto exit_free_host;
 	}
 	tspi->irq = spi_irq;
 
@@ -1355,14 +1355,14 @@ static int tegra_spi_probe(struct platform_device *pdev)
 	if (IS_ERR(tspi->clk)) {
 		dev_err(&pdev->dev, "can not get clock\n");
 		ret = PTR_ERR(tspi->clk);
-		goto exit_free_master;
+		goto exit_free_host;
 	}
 
 	tspi->rst = devm_reset_control_get_exclusive(&pdev->dev, "spi");
 	if (IS_ERR(tspi->rst)) {
 		dev_err(&pdev->dev, "can not get reset\n");
 		ret = PTR_ERR(tspi->rst);
-		goto exit_free_master;
+		goto exit_free_host;
 	}
 
 	tspi->max_buf_size = SPI_FIFO_DEPTH << 2;
@@ -1370,7 +1370,7 @@ static int tegra_spi_probe(struct platform_device *pdev)
 
 	ret = tegra_spi_init_dma_param(tspi, true);
 	if (ret < 0)
-		goto exit_free_master;
+		goto exit_free_host;
 	ret = tegra_spi_init_dma_param(tspi, false);
 	if (ret < 0)
 		goto exit_rx_dma_free;
@@ -1401,7 +1401,7 @@ static int tegra_spi_probe(struct platform_device *pdev)
 	tspi->spi_cs_timing1 = tegra_spi_readl(tspi, SPI_CS_TIMING1);
 	tspi->spi_cs_timing2 = tegra_spi_readl(tspi, SPI_CS_TIMING2);
 	tspi->def_command2_reg = tegra_spi_readl(tspi, SPI_COMMAND2);
-	tspi->last_used_cs = master->num_chipselect + 1;
+	tspi->last_used_cs = host->num_chipselect + 1;
 	pm_runtime_put(&pdev->dev);
 	ret = request_threaded_irq(tspi->irq, tegra_spi_isr,
 				   tegra_spi_isr_thread, IRQF_ONESHOT,
@@ -1412,10 +1412,10 @@ static int tegra_spi_probe(struct platform_device *pdev)
 		goto exit_pm_disable;
 	}
 
-	master->dev.of_node = pdev->dev.of_node;
-	ret = devm_spi_register_master(&pdev->dev, master);
+	host->dev.of_node = pdev->dev.of_node;
+	ret = devm_spi_register_controller(&pdev->dev, host);
 	if (ret < 0) {
-		dev_err(&pdev->dev, "can not register to master err %d\n", ret);
+		dev_err(&pdev->dev, "can not register to host err %d\n", ret);
 		goto exit_free_irq;
 	}
 	return ret;
@@ -1429,15 +1429,15 @@ exit_pm_disable:
 	tegra_spi_deinit_dma_param(tspi, false);
 exit_rx_dma_free:
 	tegra_spi_deinit_dma_param(tspi, true);
-exit_free_master:
-	spi_master_put(master);
+exit_free_host:
+	spi_controller_put(host);
 	return ret;
 }
 
 static void tegra_spi_remove(struct platform_device *pdev)
 {
-	struct spi_master *master = platform_get_drvdata(pdev);
-	struct tegra_spi_data	*tspi = spi_master_get_devdata(master);
+	struct spi_controller *host = platform_get_drvdata(pdev);
+	struct tegra_spi_data	*tspi = spi_controller_get_devdata(host);
 
 	free_irq(tspi->irq, tspi);
 
@@ -1455,15 +1455,15 @@ static void tegra_spi_remove(struct platform_device *pdev)
 #ifdef CONFIG_PM_SLEEP
 static int tegra_spi_suspend(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
+	struct spi_controller *host = dev_get_drvdata(dev);
 
-	return spi_master_suspend(master);
+	return spi_controller_suspend(host);
 }
 
 static int tegra_spi_resume(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct tegra_spi_data *tspi = spi_master_get_devdata(master);
+	struct spi_controller *host = dev_get_drvdata(dev);
+	struct tegra_spi_data *tspi = spi_controller_get_devdata(host);
 	int ret;
 
 	ret = pm_runtime_resume_and_get(dev);
@@ -1473,17 +1473,17 @@ static int tegra_spi_resume(struct device *dev)
 	}
 	tegra_spi_writel(tspi, tspi->command1_reg, SPI_COMMAND1);
 	tegra_spi_writel(tspi, tspi->def_command2_reg, SPI_COMMAND2);
-	tspi->last_used_cs = master->num_chipselect + 1;
+	tspi->last_used_cs = host->num_chipselect + 1;
 	pm_runtime_put(dev);
 
-	return spi_master_resume(master);
+	return spi_controller_resume(host);
 }
 #endif
 
 static int tegra_spi_runtime_suspend(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct tegra_spi_data *tspi = spi_master_get_devdata(master);
+	struct spi_controller *host = dev_get_drvdata(dev);
+	struct tegra_spi_data *tspi = spi_controller_get_devdata(host);
 
 	/* Flush all write which are in PPSB queue by reading back */
 	tegra_spi_readl(tspi, SPI_COMMAND1);
@@ -1494,8 +1494,8 @@ static int tegra_spi_runtime_suspend(struct device *dev)
 
 static int tegra_spi_runtime_resume(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct tegra_spi_data *tspi = spi_master_get_devdata(master);
+	struct spi_controller *host = dev_get_drvdata(dev);
+	struct tegra_spi_data *tspi = spi_controller_get_devdata(host);
 	int ret;
 
 	ret = clk_prepare_enable(tspi->clk);
diff --git a/drivers/spi/spi-tegra20-sflash.c b/drivers/spi/spi-tegra20-sflash.c
index 0c5507473f97..9f6b9f89be5b 100644
--- a/drivers/spi/spi-tegra20-sflash.c
+++ b/drivers/spi/spi-tegra20-sflash.c
@@ -102,7 +102,7 @@
 
 struct tegra_sflash_data {
 	struct device				*dev;
-	struct spi_master			*master;
+	struct spi_controller			*host;
 	spinlock_t				lock;
 
 	struct clk				*clk;
@@ -251,7 +251,7 @@ static int tegra_sflash_start_transfer_one(struct spi_device *spi,
 		struct spi_transfer *t, bool is_first_of_msg,
 		bool is_single_xfer)
 {
-	struct tegra_sflash_data *tsd = spi_master_get_devdata(spi->master);
+	struct tegra_sflash_data *tsd = spi_controller_get_devdata(spi->controller);
 	u32 speed;
 	u32 command;
 
@@ -303,12 +303,12 @@ static int tegra_sflash_start_transfer_one(struct spi_device *spi,
 	return tegra_sflash_start_cpu_based_transfer(tsd, t);
 }
 
-static int tegra_sflash_transfer_one_message(struct spi_master *master,
+static int tegra_sflash_transfer_one_message(struct spi_controller *host,
 			struct spi_message *msg)
 {
 	bool is_first_msg = true;
 	int single_xfer;
-	struct tegra_sflash_data *tsd = spi_master_get_devdata(master);
+	struct tegra_sflash_data *tsd = spi_controller_get_devdata(host);
 	struct spi_transfer *xfer;
 	struct spi_device *spi = msg->spi;
 	int ret;
@@ -351,7 +351,7 @@ static int tegra_sflash_transfer_one_message(struct spi_master *master,
 exit:
 	tegra_sflash_writel(tsd, tsd->def_command_reg, SPI_COMMAND);
 	msg->status = ret;
-	spi_finalize_current_message(master);
+	spi_finalize_current_message(host);
 	return ret;
 }
 
@@ -416,7 +416,7 @@ MODULE_DEVICE_TABLE(of, tegra_sflash_of_match);
 
 static int tegra_sflash_probe(struct platform_device *pdev)
 {
-	struct spi_master	*master;
+	struct spi_controller	*host;
 	struct tegra_sflash_data	*tsd;
 	int ret;
 	const struct of_device_id *match;
@@ -427,37 +427,37 @@ static int tegra_sflash_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	master = spi_alloc_master(&pdev->dev, sizeof(*tsd));
-	if (!master) {
-		dev_err(&pdev->dev, "master allocation failed\n");
+	host = spi_alloc_host(&pdev->dev, sizeof(*tsd));
+	if (!host) {
+		dev_err(&pdev->dev, "host allocation failed\n");
 		return -ENOMEM;
 	}
 
 	/* the spi->mode bits understood by this driver: */
-	master->mode_bits = SPI_CPOL | SPI_CPHA;
-	master->transfer_one_message = tegra_sflash_transfer_one_message;
-	master->auto_runtime_pm = true;
-	master->num_chipselect = MAX_CHIP_SELECT;
-
-	platform_set_drvdata(pdev, master);
-	tsd = spi_master_get_devdata(master);
-	tsd->master = master;
+	host->mode_bits = SPI_CPOL | SPI_CPHA;
+	host->transfer_one_message = tegra_sflash_transfer_one_message;
+	host->auto_runtime_pm = true;
+	host->num_chipselect = MAX_CHIP_SELECT;
+
+	platform_set_drvdata(pdev, host);
+	tsd = spi_controller_get_devdata(host);
+	tsd->host = host;
 	tsd->dev = &pdev->dev;
 	spin_lock_init(&tsd->lock);
 
 	if (of_property_read_u32(tsd->dev->of_node, "spi-max-frequency",
-				 &master->max_speed_hz))
-		master->max_speed_hz = 25000000; /* 25MHz */
+				 &host->max_speed_hz))
+		host->max_speed_hz = 25000000; /* 25MHz */
 
 	tsd->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(tsd->base)) {
 		ret = PTR_ERR(tsd->base);
-		goto exit_free_master;
+		goto exit_free_host;
 	}
 
 	ret = platform_get_irq(pdev, 0);
 	if (ret < 0)
-		goto exit_free_master;
+		goto exit_free_host;
 	tsd->irq = ret;
 
 	ret = request_irq(tsd->irq, tegra_sflash_isr, 0,
@@ -465,7 +465,7 @@ static int tegra_sflash_probe(struct platform_device *pdev)
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Failed to register ISR for IRQ %d\n",
 					tsd->irq);
-		goto exit_free_master;
+		goto exit_free_host;
 	}
 
 	tsd->clk = devm_clk_get(&pdev->dev, NULL);
@@ -505,10 +505,10 @@ static int tegra_sflash_probe(struct platform_device *pdev)
 	tegra_sflash_writel(tsd, tsd->def_command_reg, SPI_COMMAND);
 	pm_runtime_put(&pdev->dev);
 
-	master->dev.of_node = pdev->dev.of_node;
-	ret = devm_spi_register_master(&pdev->dev, master);
+	host->dev.of_node = pdev->dev.of_node;
+	ret = devm_spi_register_controller(&pdev->dev, host);
 	if (ret < 0) {
-		dev_err(&pdev->dev, "can not register to master err %d\n", ret);
+		dev_err(&pdev->dev, "can not register to host err %d\n", ret);
 		goto exit_pm_disable;
 	}
 	return ret;
@@ -519,15 +519,15 @@ exit_pm_disable:
 		tegra_sflash_runtime_suspend(&pdev->dev);
 exit_free_irq:
 	free_irq(tsd->irq, tsd);
-exit_free_master:
-	spi_master_put(master);
+exit_free_host:
+	spi_controller_put(host);
 	return ret;
 }
 
 static void tegra_sflash_remove(struct platform_device *pdev)
 {
-	struct spi_master *master = platform_get_drvdata(pdev);
-	struct tegra_sflash_data	*tsd = spi_master_get_devdata(master);
+	struct spi_controller *host = platform_get_drvdata(pdev);
+	struct tegra_sflash_data	*tsd = spi_controller_get_devdata(host);
 
 	free_irq(tsd->irq, tsd);
 
@@ -539,15 +539,15 @@ static void tegra_sflash_remove(struct platform_device *pdev)
 #ifdef CONFIG_PM_SLEEP
 static int tegra_sflash_suspend(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
+	struct spi_controller *host = dev_get_drvdata(dev);
 
-	return spi_master_suspend(master);
+	return spi_controller_suspend(host);
 }
 
 static int tegra_sflash_resume(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct tegra_sflash_data *tsd = spi_master_get_devdata(master);
+	struct spi_controller *host = dev_get_drvdata(dev);
+	struct tegra_sflash_data *tsd = spi_controller_get_devdata(host);
 	int ret;
 
 	ret = pm_runtime_resume_and_get(dev);
@@ -558,14 +558,14 @@ static int tegra_sflash_resume(struct device *dev)
 	tegra_sflash_writel(tsd, tsd->command_reg, SPI_COMMAND);
 	pm_runtime_put(dev);
 
-	return spi_master_resume(master);
+	return spi_controller_resume(host);
 }
 #endif
 
 static int tegra_sflash_runtime_suspend(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct tegra_sflash_data *tsd = spi_master_get_devdata(master);
+	struct spi_controller *host = dev_get_drvdata(dev);
+	struct tegra_sflash_data *tsd = spi_controller_get_devdata(host);
 
 	/* Flush all write which are in PPSB queue by reading back */
 	tegra_sflash_readl(tsd, SPI_COMMAND);
@@ -576,8 +576,8 @@ static int tegra_sflash_runtime_suspend(struct device *dev)
 
 static int tegra_sflash_runtime_resume(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct tegra_sflash_data *tsd = spi_master_get_devdata(master);
+	struct spi_controller *host = dev_get_drvdata(dev);
+	struct tegra_sflash_data *tsd = spi_controller_get_devdata(host);
 	int ret;
 
 	ret = clk_prepare_enable(tsd->clk);
diff --git a/drivers/spi/spi-tegra20-slink.c b/drivers/spi/spi-tegra20-slink.c
index f5cd365c913a..ed1393d159ae 100644
--- a/drivers/spi/spi-tegra20-slink.c
+++ b/drivers/spi/spi-tegra20-slink.c
@@ -152,7 +152,7 @@ struct tegra_slink_chip_data {
 
 struct tegra_slink_data {
 	struct device				*dev;
-	struct spi_master			*master;
+	struct spi_controller			*host;
 	const struct tegra_slink_chip_data	*chip_data;
 	spinlock_t				lock;
 
@@ -671,7 +671,7 @@ static void tegra_slink_deinit_dma_param(struct tegra_slink_data *tspi,
 static int tegra_slink_start_transfer_one(struct spi_device *spi,
 		struct spi_transfer *t)
 {
-	struct tegra_slink_data *tspi = spi_master_get_devdata(spi->master);
+	struct tegra_slink_data *tspi = spi_controller_get_devdata(spi->controller);
 	u32 speed;
 	u8 bits_per_word;
 	unsigned total_fifo_words;
@@ -737,7 +737,7 @@ static int tegra_slink_setup(struct spi_device *spi)
 			SLINK_CS_POLARITY3,
 	};
 
-	struct tegra_slink_data *tspi = spi_master_get_devdata(spi->master);
+	struct tegra_slink_data *tspi = spi_controller_get_devdata(spi->controller);
 	u32 val;
 	unsigned long flags;
 	int ret;
@@ -768,10 +768,10 @@ static int tegra_slink_setup(struct spi_device *spi)
 	return 0;
 }
 
-static int tegra_slink_prepare_message(struct spi_master *master,
+static int tegra_slink_prepare_message(struct spi_controller *host,
 				       struct spi_message *msg)
 {
-	struct tegra_slink_data *tspi = spi_master_get_devdata(master);
+	struct tegra_slink_data *tspi = spi_controller_get_devdata(host);
 	struct spi_device *spi = msg->spi;
 
 	tegra_slink_clear_status(tspi);
@@ -794,11 +794,11 @@ static int tegra_slink_prepare_message(struct spi_master *master,
 	return 0;
 }
 
-static int tegra_slink_transfer_one(struct spi_master *master,
+static int tegra_slink_transfer_one(struct spi_controller *host,
 				    struct spi_device *spi,
 				    struct spi_transfer *xfer)
 {
-	struct tegra_slink_data *tspi = spi_master_get_devdata(master);
+	struct tegra_slink_data *tspi = spi_controller_get_devdata(host);
 	int ret;
 
 	reinit_completion(&tspi->xfer_completion);
@@ -825,10 +825,10 @@ static int tegra_slink_transfer_one(struct spi_master *master,
 	return 0;
 }
 
-static int tegra_slink_unprepare_message(struct spi_master *master,
+static int tegra_slink_unprepare_message(struct spi_controller *host,
 					 struct spi_message *msg)
 {
-	struct tegra_slink_data *tspi = spi_master_get_devdata(master);
+	struct tegra_slink_data *tspi = spi_controller_get_devdata(host);
 
 	tegra_slink_writel(tspi, tspi->def_command_reg, SLINK_COMMAND);
 	tegra_slink_writel(tspi, tspi->def_command2_reg, SLINK_COMMAND2);
@@ -999,7 +999,7 @@ MODULE_DEVICE_TABLE(of, tegra_slink_of_match);
 
 static int tegra_slink_probe(struct platform_device *pdev)
 {
-	struct spi_master	*master;
+	struct spi_controller	*host;
 	struct tegra_slink_data	*tspi;
 	struct resource		*r;
 	int ret, spi_irq;
@@ -1007,36 +1007,36 @@ static int tegra_slink_probe(struct platform_device *pdev)
 
 	cdata = of_device_get_match_data(&pdev->dev);
 
-	master = spi_alloc_master(&pdev->dev, sizeof(*tspi));
-	if (!master) {
-		dev_err(&pdev->dev, "master allocation failed\n");
+	host = spi_alloc_host(&pdev->dev, sizeof(*tspi));
+	if (!host) {
+		dev_err(&pdev->dev, "host allocation failed\n");
 		return -ENOMEM;
 	}
 
 	/* the spi->mode bits understood by this driver: */
-	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
-	master->setup = tegra_slink_setup;
-	master->prepare_message = tegra_slink_prepare_message;
-	master->transfer_one = tegra_slink_transfer_one;
-	master->unprepare_message = tegra_slink_unprepare_message;
-	master->auto_runtime_pm = true;
-	master->num_chipselect = MAX_CHIP_SELECT;
-
-	platform_set_drvdata(pdev, master);
-	tspi = spi_master_get_devdata(master);
-	tspi->master = master;
+	host->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
+	host->setup = tegra_slink_setup;
+	host->prepare_message = tegra_slink_prepare_message;
+	host->transfer_one = tegra_slink_transfer_one;
+	host->unprepare_message = tegra_slink_unprepare_message;
+	host->auto_runtime_pm = true;
+	host->num_chipselect = MAX_CHIP_SELECT;
+
+	platform_set_drvdata(pdev, host);
+	tspi = spi_controller_get_devdata(host);
+	tspi->host = host;
 	tspi->dev = &pdev->dev;
 	tspi->chip_data = cdata;
 	spin_lock_init(&tspi->lock);
 
 	if (of_property_read_u32(tspi->dev->of_node, "spi-max-frequency",
-				 &master->max_speed_hz))
-		master->max_speed_hz = 25000000; /* 25MHz */
+				 &host->max_speed_hz))
+		host->max_speed_hz = 25000000; /* 25MHz */
 
 	tspi->base = devm_platform_get_and_ioremap_resource(pdev, 0, &r);
 	if (IS_ERR(tspi->base)) {
 		ret = PTR_ERR(tspi->base);
-		goto exit_free_master;
+		goto exit_free_host;
 	}
 	tspi->phys = r->start;
 
@@ -1045,26 +1045,26 @@ static int tegra_slink_probe(struct platform_device *pdev)
 	if (IS_ERR(tspi->clk)) {
 		ret = PTR_ERR(tspi->clk);
 		dev_err(&pdev->dev, "Can not get clock %d\n", ret);
-		goto exit_free_master;
+		goto exit_free_host;
 	}
 
 	tspi->rst = devm_reset_control_get_exclusive(&pdev->dev, "spi");
 	if (IS_ERR(tspi->rst)) {
 		dev_err(&pdev->dev, "can not get reset\n");
 		ret = PTR_ERR(tspi->rst);
-		goto exit_free_master;
+		goto exit_free_host;
 	}
 
 	ret = devm_tegra_core_dev_init_opp_table_common(&pdev->dev);
 	if (ret)
-		goto exit_free_master;
+		goto exit_free_host;
 
 	tspi->max_buf_size = SLINK_FIFO_DEPTH << 2;
 	tspi->dma_buf_size = DEFAULT_SPI_DMA_BUF_LEN;
 
 	ret = tegra_slink_init_dma_param(tspi, true);
 	if (ret < 0)
-		goto exit_free_master;
+		goto exit_free_host;
 	ret = tegra_slink_init_dma_param(tspi, false);
 	if (ret < 0)
 		goto exit_rx_dma_free;
@@ -1103,10 +1103,10 @@ static int tegra_slink_probe(struct platform_device *pdev)
 	tegra_slink_writel(tspi, tspi->def_command_reg, SLINK_COMMAND);
 	tegra_slink_writel(tspi, tspi->def_command2_reg, SLINK_COMMAND2);
 
-	master->dev.of_node = pdev->dev.of_node;
-	ret = spi_register_master(master);
+	host->dev.of_node = pdev->dev.of_node;
+	ret = spi_register_controller(host);
 	if (ret < 0) {
-		dev_err(&pdev->dev, "can not register to master err %d\n", ret);
+		dev_err(&pdev->dev, "can not register to host err %d\n", ret);
 		goto exit_free_irq;
 	}
 
@@ -1124,17 +1124,17 @@ exit_pm_disable:
 	tegra_slink_deinit_dma_param(tspi, false);
 exit_rx_dma_free:
 	tegra_slink_deinit_dma_param(tspi, true);
-exit_free_master:
-	spi_master_put(master);
+exit_free_host:
+	spi_controller_put(host);
 	return ret;
 }
 
 static void tegra_slink_remove(struct platform_device *pdev)
 {
-	struct spi_master *master = spi_master_get(platform_get_drvdata(pdev));
-	struct tegra_slink_data	*tspi = spi_master_get_devdata(master);
+	struct spi_controller *host = spi_controller_get(platform_get_drvdata(pdev));
+	struct tegra_slink_data	*tspi = spi_controller_get_devdata(host);
 
-	spi_unregister_master(master);
+	spi_unregister_controller(host);
 
 	free_irq(tspi->irq, tspi);
 
@@ -1146,21 +1146,21 @@ static void tegra_slink_remove(struct platform_device *pdev)
 	if (tspi->rx_dma_chan)
 		tegra_slink_deinit_dma_param(tspi, true);
 
-	spi_master_put(master);
+	spi_controller_put(host);
 }
 
 #ifdef CONFIG_PM_SLEEP
 static int tegra_slink_suspend(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
+	struct spi_controller *host = dev_get_drvdata(dev);
 
-	return spi_master_suspend(master);
+	return spi_controller_suspend(host);
 }
 
 static int tegra_slink_resume(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct tegra_slink_data *tspi = spi_master_get_devdata(master);
+	struct spi_controller *host = dev_get_drvdata(dev);
+	struct tegra_slink_data *tspi = spi_controller_get_devdata(host);
 	int ret;
 
 	ret = pm_runtime_resume_and_get(dev);
@@ -1172,14 +1172,14 @@ static int tegra_slink_resume(struct device *dev)
 	tegra_slink_writel(tspi, tspi->command2_reg, SLINK_COMMAND2);
 	pm_runtime_put(dev);
 
-	return spi_master_resume(master);
+	return spi_controller_resume(host);
 }
 #endif
 
 static int __maybe_unused tegra_slink_runtime_suspend(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct tegra_slink_data *tspi = spi_master_get_devdata(master);
+	struct spi_controller *host = dev_get_drvdata(dev);
+	struct tegra_slink_data *tspi = spi_controller_get_devdata(host);
 
 	/* Flush all write which are in PPSB queue by reading back */
 	tegra_slink_readl(tspi, SLINK_MAS_DATA);
@@ -1190,8 +1190,8 @@ static int __maybe_unused tegra_slink_runtime_suspend(struct device *dev)
 
 static int __maybe_unused tegra_slink_runtime_resume(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct tegra_slink_data *tspi = spi_master_get_devdata(master);
+	struct spi_controller *host = dev_get_drvdata(dev);
+	struct tegra_slink_data *tspi = spi_controller_get_devdata(host);
 	int ret;
 
 	ret = clk_prepare_enable(tspi->clk);
diff --git a/drivers/spi/spi-tegra210-quad.c b/drivers/spi/spi-tegra210-quad.c
index e9ad9b0b598b..afbd64a217eb 100644
--- a/drivers/spi/spi-tegra210-quad.c
+++ b/drivers/spi/spi-tegra210-quad.c
@@ -175,7 +175,7 @@ struct tegra_qspi_client_data {
 
 struct tegra_qspi {
 	struct device				*dev;
-	struct spi_master			*master;
+	struct spi_controller			*host;
 	/* lock to protect data accessed by irq */
 	spinlock_t				lock;
 
@@ -809,7 +809,7 @@ err_out:
 static u32 tegra_qspi_setup_transfer_one(struct spi_device *spi, struct spi_transfer *t,
 					 bool is_first_of_msg)
 {
-	struct tegra_qspi *tqspi = spi_master_get_devdata(spi->master);
+	struct tegra_qspi *tqspi = spi_controller_get_devdata(spi->controller);
 	struct tegra_qspi_client_data *cdata = spi->controller_data;
 	u32 command1, command2, speed = t->speed_hz;
 	u8 bits_per_word = t->bits_per_word;
@@ -870,7 +870,7 @@ static u32 tegra_qspi_setup_transfer_one(struct spi_device *spi, struct spi_tran
 static int tegra_qspi_start_transfer_one(struct spi_device *spi,
 					 struct spi_transfer *t, u32 command1)
 {
-	struct tegra_qspi *tqspi = spi_master_get_devdata(spi->master);
+	struct tegra_qspi *tqspi = spi_controller_get_devdata(spi->controller);
 	unsigned int total_fifo_words;
 	u8 bus_width = 0;
 	int ret;
@@ -925,7 +925,7 @@ static int tegra_qspi_start_transfer_one(struct spi_device *spi,
 static struct tegra_qspi_client_data *tegra_qspi_parse_cdata_dt(struct spi_device *spi)
 {
 	struct tegra_qspi_client_data *cdata;
-	struct tegra_qspi *tqspi = spi_master_get_devdata(spi->master);
+	struct tegra_qspi *tqspi = spi_controller_get_devdata(spi->controller);
 
 	cdata = devm_kzalloc(tqspi->dev, sizeof(*cdata), GFP_KERNEL);
 	if (!cdata)
@@ -941,7 +941,7 @@ static struct tegra_qspi_client_data *tegra_qspi_parse_cdata_dt(struct spi_devic
 
 static int tegra_qspi_setup(struct spi_device *spi)
 {
-	struct tegra_qspi *tqspi = spi_master_get_devdata(spi->master);
+	struct tegra_qspi *tqspi = spi_controller_get_devdata(spi->controller);
 	struct tegra_qspi_client_data *cdata = spi->controller_data;
 	unsigned long flags;
 	u32 val;
@@ -1005,7 +1005,7 @@ static void tegra_qspi_handle_error(struct tegra_qspi *tqspi)
 
 static void tegra_qspi_transfer_end(struct spi_device *spi)
 {
-	struct tegra_qspi *tqspi = spi_master_get_devdata(spi->master);
+	struct tegra_qspi *tqspi = spi_controller_get_devdata(spi->controller);
 	int cs_val = (spi->mode & SPI_CS_HIGH) ? 0 : 1;
 
 	if (cs_val)
@@ -1316,10 +1316,10 @@ static bool tegra_qspi_validate_cmb_seq(struct tegra_qspi *tqspi,
 	return true;
 }
 
-static int tegra_qspi_transfer_one_message(struct spi_master *master,
+static int tegra_qspi_transfer_one_message(struct spi_controller *host,
 					   struct spi_message *msg)
 {
-	struct tegra_qspi *tqspi = spi_master_get_devdata(master);
+	struct tegra_qspi *tqspi = spi_controller_get_devdata(host);
 	int ret;
 
 	if (tegra_qspi_validate_cmb_seq(tqspi, msg))
@@ -1327,7 +1327,7 @@ static int tegra_qspi_transfer_one_message(struct spi_master *master,
 	else
 		ret = tegra_qspi_non_combined_seq_xfer(tqspi, msg);
 
-	spi_finalize_current_message(master);
+	spi_finalize_current_message(host);
 
 	return ret;
 }
@@ -1533,38 +1533,38 @@ MODULE_DEVICE_TABLE(acpi, tegra_qspi_acpi_match);
 
 static int tegra_qspi_probe(struct platform_device *pdev)
 {
-	struct spi_master	*master;
+	struct spi_controller	*host;
 	struct tegra_qspi	*tqspi;
 	struct resource		*r;
 	int ret, qspi_irq;
 	int bus_num;
 
-	master = devm_spi_alloc_master(&pdev->dev, sizeof(*tqspi));
-	if (!master)
+	host = devm_spi_alloc_host(&pdev->dev, sizeof(*tqspi));
+	if (!host)
 		return -ENOMEM;
 
-	platform_set_drvdata(pdev, master);
-	tqspi = spi_master_get_devdata(master);
+	platform_set_drvdata(pdev, host);
+	tqspi = spi_controller_get_devdata(host);
 
-	master->mode_bits = SPI_MODE_0 | SPI_MODE_3 | SPI_CS_HIGH |
-			    SPI_TX_DUAL | SPI_RX_DUAL | SPI_TX_QUAD | SPI_RX_QUAD;
-	master->bits_per_word_mask = SPI_BPW_MASK(32) | SPI_BPW_MASK(16) | SPI_BPW_MASK(8);
-	master->flags = SPI_CONTROLLER_HALF_DUPLEX;
-	master->setup = tegra_qspi_setup;
-	master->transfer_one_message = tegra_qspi_transfer_one_message;
-	master->num_chipselect = 1;
-	master->auto_runtime_pm = true;
+	host->mode_bits = SPI_MODE_0 | SPI_MODE_3 | SPI_CS_HIGH |
+			  SPI_TX_DUAL | SPI_RX_DUAL | SPI_TX_QUAD | SPI_RX_QUAD;
+	host->bits_per_word_mask = SPI_BPW_MASK(32) | SPI_BPW_MASK(16) | SPI_BPW_MASK(8);
+	host->flags = SPI_CONTROLLER_HALF_DUPLEX;
+	host->setup = tegra_qspi_setup;
+	host->transfer_one_message = tegra_qspi_transfer_one_message;
+	host->num_chipselect = 1;
+	host->auto_runtime_pm = true;
 
 	bus_num = of_alias_get_id(pdev->dev.of_node, "spi");
 	if (bus_num >= 0)
-		master->bus_num = bus_num;
+		host->bus_num = bus_num;
 
-	tqspi->master = master;
+	tqspi->host = host;
 	tqspi->dev = &pdev->dev;
 	spin_lock_init(&tqspi->lock);
 
 	tqspi->soc_data = device_get_match_data(&pdev->dev);
-	master->num_chipselect = tqspi->soc_data->cs_count;
+	host->num_chipselect = tqspi->soc_data->cs_count;
 	tqspi->base = devm_platform_get_and_ioremap_resource(pdev, 0, &r);
 	if (IS_ERR(tqspi->base))
 		return PTR_ERR(tqspi->base);
@@ -1625,10 +1625,10 @@ static int tegra_qspi_probe(struct platform_device *pdev)
 		goto exit_pm_disable;
 	}
 
-	master->dev.of_node = pdev->dev.of_node;
-	ret = spi_register_master(master);
+	host->dev.of_node = pdev->dev.of_node;
+	ret = spi_register_controller(host);
 	if (ret < 0) {
-		dev_err(&pdev->dev, "failed to register master: %d\n", ret);
+		dev_err(&pdev->dev, "failed to register host: %d\n", ret);
 		goto exit_free_irq;
 	}
 
@@ -1644,10 +1644,10 @@ exit_pm_disable:
 
 static void tegra_qspi_remove(struct platform_device *pdev)
 {
-	struct spi_master *master = platform_get_drvdata(pdev);
-	struct tegra_qspi *tqspi = spi_master_get_devdata(master);
+	struct spi_controller *host = platform_get_drvdata(pdev);
+	struct tegra_qspi *tqspi = spi_controller_get_devdata(host);
 
-	spi_unregister_master(master);
+	spi_unregister_controller(host);
 	free_irq(tqspi->irq, tqspi);
 	pm_runtime_force_suspend(&pdev->dev);
 	tegra_qspi_deinit_dma(tqspi);
@@ -1655,15 +1655,15 @@ static void tegra_qspi_remove(struct platform_device *pdev)
 
 static int __maybe_unused tegra_qspi_suspend(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
+	struct spi_controller *host = dev_get_drvdata(dev);
 
-	return spi_master_suspend(master);
+	return spi_controller_suspend(host);
 }
 
 static int __maybe_unused tegra_qspi_resume(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct tegra_qspi *tqspi = spi_master_get_devdata(master);
+	struct spi_controller *host = dev_get_drvdata(dev);
+	struct tegra_qspi *tqspi = spi_controller_get_devdata(host);
 	int ret;
 
 	ret = pm_runtime_resume_and_get(dev);
@@ -1676,13 +1676,13 @@ static int __maybe_unused tegra_qspi_resume(struct device *dev)
 	tegra_qspi_writel(tqspi, tqspi->def_command2_reg, QSPI_COMMAND2);
 	pm_runtime_put(dev);
 
-	return spi_master_resume(master);
+	return spi_controller_resume(host);
 }
 
 static int __maybe_unused tegra_qspi_runtime_suspend(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct tegra_qspi *tqspi = spi_master_get_devdata(master);
+	struct spi_controller *host = dev_get_drvdata(dev);
+	struct tegra_qspi *tqspi = spi_controller_get_devdata(host);
 
 	/* Runtime pm disabled with ACPI */
 	if (has_acpi_companion(tqspi->dev))
@@ -1697,8 +1697,8 @@ static int __maybe_unused tegra_qspi_runtime_suspend(struct device *dev)
 
 static int __maybe_unused tegra_qspi_runtime_resume(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct tegra_qspi *tqspi = spi_master_get_devdata(master);
+	struct spi_controller *host = dev_get_drvdata(dev);
+	struct tegra_qspi *tqspi = spi_controller_get_devdata(host);
 	int ret;
 
 	/* Runtime pm disabled with ACPI */
diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c
index 4c81516b67db..0fe6899e78dd 100644
--- a/drivers/spi/spi-ti-qspi.c
+++ b/drivers/spi/spi-ti-qspi.c
@@ -40,7 +40,7 @@ struct ti_qspi {
 	/* list synchronization */
 	struct mutex            list_lock;
 
-	struct spi_master	*master;
+	struct spi_controller	*host;
 	void __iomem            *base;
 	void __iomem            *mmap_base;
 	size_t			mmap_size;
@@ -137,20 +137,20 @@ static inline void ti_qspi_write(struct ti_qspi *qspi,
 
 static int ti_qspi_setup(struct spi_device *spi)
 {
-	struct ti_qspi	*qspi = spi_master_get_devdata(spi->master);
+	struct ti_qspi	*qspi = spi_controller_get_devdata(spi->controller);
 	int ret;
 
-	if (spi->master->busy) {
-		dev_dbg(qspi->dev, "master busy doing other transfers\n");
+	if (spi->controller->busy) {
+		dev_dbg(qspi->dev, "host busy doing other transfers\n");
 		return -EBUSY;
 	}
 
-	if (!qspi->master->max_speed_hz) {
+	if (!qspi->host->max_speed_hz) {
 		dev_err(qspi->dev, "spi max frequency not defined\n");
 		return -EINVAL;
 	}
 
-	spi->max_speed_hz = min(spi->max_speed_hz, qspi->master->max_speed_hz);
+	spi->max_speed_hz = min(spi->max_speed_hz, qspi->host->max_speed_hz);
 
 	ret = pm_runtime_resume_and_get(qspi->dev);
 	if (ret < 0) {
@@ -526,7 +526,7 @@ static int ti_qspi_dma_xfer_sg(struct ti_qspi *qspi, struct sg_table rx_sg,
 
 static void ti_qspi_enable_memory_map(struct spi_device *spi)
 {
-	struct ti_qspi  *qspi = spi_master_get_devdata(spi->master);
+	struct ti_qspi  *qspi = spi_controller_get_devdata(spi->controller);
 
 	ti_qspi_write(qspi, MM_SWITCH, QSPI_SPI_SWITCH_REG);
 	if (qspi->ctrl_base) {
@@ -540,7 +540,7 @@ static void ti_qspi_enable_memory_map(struct spi_device *spi)
 
 static void ti_qspi_disable_memory_map(struct spi_device *spi)
 {
-	struct ti_qspi  *qspi = spi_master_get_devdata(spi->master);
+	struct ti_qspi  *qspi = spi_controller_get_devdata(spi->controller);
 
 	ti_qspi_write(qspi, 0, QSPI_SPI_SWITCH_REG);
 	if (qspi->ctrl_base)
@@ -554,7 +554,7 @@ static void ti_qspi_setup_mmap_read(struct spi_device *spi, u8 opcode,
 				    u8 data_nbits, u8 addr_width,
 				    u8 dummy_bytes)
 {
-	struct ti_qspi  *qspi = spi_master_get_devdata(spi->master);
+	struct ti_qspi  *qspi = spi_controller_get_devdata(spi->controller);
 	u32 memval = opcode;
 
 	switch (data_nbits) {
@@ -576,7 +576,7 @@ static void ti_qspi_setup_mmap_read(struct spi_device *spi, u8 opcode,
 
 static int ti_qspi_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op)
 {
-	struct ti_qspi *qspi = spi_controller_get_devdata(mem->spi->master);
+	struct ti_qspi *qspi = spi_controller_get_devdata(mem->spi->controller);
 	size_t max_len;
 
 	if (op->data.dir == SPI_MEM_DATA_IN) {
@@ -606,19 +606,19 @@ static int ti_qspi_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op)
 static int ti_qspi_exec_mem_op(struct spi_mem *mem,
 			       const struct spi_mem_op *op)
 {
-	struct ti_qspi *qspi = spi_master_get_devdata(mem->spi->master);
+	struct ti_qspi *qspi = spi_controller_get_devdata(mem->spi->controller);
 	u32 from = 0;
 	int ret = 0;
 
 	/* Only optimize read path. */
 	if (!op->data.nbytes || op->data.dir != SPI_MEM_DATA_IN ||
 	    !op->addr.nbytes || op->addr.nbytes > 4)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	/* Address exceeds MMIO window size, fall back to regular mode. */
 	from = op->addr.val;
 	if (from + op->data.nbytes > qspi->mmap_size)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	mutex_lock(&qspi->list_lock);
 
@@ -633,10 +633,10 @@ static int ti_qspi_exec_mem_op(struct spi_mem *mem,
 		struct sg_table sgt;
 
 		if (virt_addr_valid(op->data.buf.in) &&
-		    !spi_controller_dma_map_mem_op_data(mem->spi->master, op,
+		    !spi_controller_dma_map_mem_op_data(mem->spi->controller, op,
 							&sgt)) {
 			ret = ti_qspi_dma_xfer_sg(qspi, sgt, from);
-			spi_controller_dma_unmap_mem_op_data(mem->spi->master,
+			spi_controller_dma_unmap_mem_op_data(mem->spi->controller,
 							     op, &sgt);
 		} else {
 			ret = ti_qspi_dma_bounce_buffer(qspi, from,
@@ -658,10 +658,10 @@ static const struct spi_controller_mem_ops ti_qspi_mem_ops = {
 	.adjust_op_size = ti_qspi_adjust_op_size,
 };
 
-static int ti_qspi_start_transfer_one(struct spi_master *master,
+static int ti_qspi_start_transfer_one(struct spi_controller *host,
 		struct spi_message *m)
 {
-	struct ti_qspi *qspi = spi_master_get_devdata(master);
+	struct ti_qspi *qspi = spi_controller_get_devdata(host);
 	struct spi_device *spi = m->spi;
 	struct spi_transfer *t;
 	int status = 0, ret;
@@ -720,7 +720,7 @@ static int ti_qspi_start_transfer_one(struct spi_master *master,
 
 	ti_qspi_write(qspi, qspi->cmd | QSPI_INVAL, QSPI_SPI_CMD_REG);
 	m->status = status;
-	spi_finalize_current_message(master);
+	spi_finalize_current_message(host);
 
 	return status;
 }
@@ -756,33 +756,33 @@ MODULE_DEVICE_TABLE(of, ti_qspi_match);
 static int ti_qspi_probe(struct platform_device *pdev)
 {
 	struct  ti_qspi *qspi;
-	struct spi_master *master;
+	struct spi_controller *host;
 	struct resource         *r, *res_mmap;
 	struct device_node *np = pdev->dev.of_node;
 	u32 max_freq;
 	int ret = 0, num_cs, irq;
 	dma_cap_mask_t mask;
 
-	master = spi_alloc_master(&pdev->dev, sizeof(*qspi));
-	if (!master)
+	host = spi_alloc_host(&pdev->dev, sizeof(*qspi));
+	if (!host)
 		return -ENOMEM;
 
-	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_RX_DUAL | SPI_RX_QUAD;
+	host->mode_bits = SPI_CPOL | SPI_CPHA | SPI_RX_DUAL | SPI_RX_QUAD;
 
-	master->flags = SPI_CONTROLLER_HALF_DUPLEX;
-	master->setup = ti_qspi_setup;
-	master->auto_runtime_pm = true;
-	master->transfer_one_message = ti_qspi_start_transfer_one;
-	master->dev.of_node = pdev->dev.of_node;
-	master->bits_per_word_mask = SPI_BPW_MASK(32) | SPI_BPW_MASK(16) |
-				     SPI_BPW_MASK(8);
-	master->mem_ops = &ti_qspi_mem_ops;
+	host->flags = SPI_CONTROLLER_HALF_DUPLEX;
+	host->setup = ti_qspi_setup;
+	host->auto_runtime_pm = true;
+	host->transfer_one_message = ti_qspi_start_transfer_one;
+	host->dev.of_node = pdev->dev.of_node;
+	host->bits_per_word_mask = SPI_BPW_MASK(32) | SPI_BPW_MASK(16) |
+				   SPI_BPW_MASK(8);
+	host->mem_ops = &ti_qspi_mem_ops;
 
 	if (!of_property_read_u32(np, "num-cs", &num_cs))
-		master->num_chipselect = num_cs;
+		host->num_chipselect = num_cs;
 
-	qspi = spi_master_get_devdata(master);
-	qspi->master = master;
+	qspi = spi_controller_get_devdata(host);
+	qspi->host = host;
 	qspi->dev = &pdev->dev;
 	platform_set_drvdata(pdev, qspi);
 
@@ -792,7 +792,7 @@ static int ti_qspi_probe(struct platform_device *pdev)
 		if (r == NULL) {
 			dev_err(&pdev->dev, "missing platform data\n");
 			ret = -ENODEV;
-			goto free_master;
+			goto free_host;
 		}
 	}
 
@@ -812,7 +812,7 @@ static int ti_qspi_probe(struct platform_device *pdev)
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
 		ret = irq;
-		goto free_master;
+		goto free_host;
 	}
 
 	mutex_init(&qspi->list_lock);
@@ -820,7 +820,7 @@ static int ti_qspi_probe(struct platform_device *pdev)
 	qspi->base = devm_ioremap_resource(&pdev->dev, r);
 	if (IS_ERR(qspi->base)) {
 		ret = PTR_ERR(qspi->base);
-		goto free_master;
+		goto free_host;
 	}
 
 
@@ -830,7 +830,7 @@ static int ti_qspi_probe(struct platform_device *pdev)
 						"syscon-chipselects");
 		if (IS_ERR(qspi->ctrl_base)) {
 			ret = PTR_ERR(qspi->ctrl_base);
-			goto free_master;
+			goto free_host;
 		}
 		ret = of_property_read_u32_index(np,
 						 "syscon-chipselects",
@@ -838,7 +838,7 @@ static int ti_qspi_probe(struct platform_device *pdev)
 		if (ret) {
 			dev_err(&pdev->dev,
 				"couldn't get ctrl_mod reg index\n");
-			goto free_master;
+			goto free_host;
 		}
 	}
 
@@ -853,7 +853,7 @@ static int ti_qspi_probe(struct platform_device *pdev)
 	pm_runtime_enable(&pdev->dev);
 
 	if (!of_property_read_u32(np, "spi-max-frequency", &max_freq))
-		master->max_speed_hz = max_freq;
+		host->max_speed_hz = max_freq;
 
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_MEMCPY, mask);
@@ -876,7 +876,7 @@ static int ti_qspi_probe(struct platform_device *pdev)
 		dma_release_channel(qspi->rx_chan);
 		goto no_dma;
 	}
-	master->dma_rx = qspi->rx_chan;
+	host->dma_rx = qspi->rx_chan;
 	init_completion(&qspi->transfer_complete);
 	if (res_mmap)
 		qspi->mmap_phys_base = (dma_addr_t)res_mmap->start;
@@ -889,39 +889,40 @@ no_dma:
 				 "mmap failed with error %ld using PIO mode\n",
 				 PTR_ERR(qspi->mmap_base));
 			qspi->mmap_base = NULL;
-			master->mem_ops = NULL;
+			host->mem_ops = NULL;
 		}
 	}
 	qspi->mmap_enabled = false;
 	qspi->current_cs = -1;
 
-	ret = devm_spi_register_master(&pdev->dev, master);
+	ret = devm_spi_register_controller(&pdev->dev, host);
 	if (!ret)
 		return 0;
 
 	ti_qspi_dma_cleanup(qspi);
 
 	pm_runtime_disable(&pdev->dev);
-free_master:
-	spi_master_put(master);
+free_host:
+	spi_controller_put(host);
 	return ret;
 }
 
-static int ti_qspi_remove(struct platform_device *pdev)
+static void ti_qspi_remove(struct platform_device *pdev)
 {
 	struct ti_qspi *qspi = platform_get_drvdata(pdev);
 	int rc;
 
-	rc = spi_master_suspend(qspi->master);
-	if (rc)
-		return rc;
+	rc = spi_controller_suspend(qspi->host);
+	if (rc) {
+		dev_alert(&pdev->dev, "spi_controller_suspend() failed (%pe)\n",
+			  ERR_PTR(rc));
+		return;
+	}
 
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
 	ti_qspi_dma_cleanup(qspi);
-
-	return 0;
 }
 
 static const struct dev_pm_ops ti_qspi_pm_ops = {
@@ -930,7 +931,7 @@ static const struct dev_pm_ops ti_qspi_pm_ops = {
 
 static struct platform_driver ti_qspi_driver = {
 	.probe	= ti_qspi_probe,
-	.remove = ti_qspi_remove,
+	.remove_new = ti_qspi_remove,
 	.driver = {
 		.name	= "ti-qspi",
 		.pm =   &ti_qspi_pm_ops,
diff --git a/drivers/spi/spi-topcliff-pch.c b/drivers/spi/spi-topcliff-pch.c
index af5846cfe5e9..271f3e7f834b 100644
--- a/drivers/spi/spi-topcliff-pch.c
+++ b/drivers/spi/spi-topcliff-pch.c
@@ -124,7 +124,7 @@ struct pch_spi_dma_ctrl {
  * struct pch_spi_data - Holds the SPI channel specific details
  * @io_remap_addr:		The remapped PCI base address
  * @io_base_addr:		Base address
- * @master:			Pointer to the SPI master structure
+ * @host:			Pointer to the SPI controller structure
  * @work:			Reference to work queue handler
  * @wait:			Wait queue for waking up upon receiving an
  *				interrupt.
@@ -161,7 +161,7 @@ struct pch_spi_dma_ctrl {
 struct pch_spi_data {
 	void __iomem *io_remap_addr;
 	unsigned long io_base_addr;
-	struct spi_master *master;
+	struct spi_controller *host;
 	struct work_struct work;
 	wait_queue_head_t wait;
 	u8 transfer_complete;
@@ -216,48 +216,48 @@ static const struct pci_device_id pch_spi_pcidev_id[] = {
 
 /**
  * pch_spi_writereg() - Performs  register writes
- * @master:	Pointer to struct spi_master.
+ * @host:	Pointer to struct spi_controller.
  * @idx:	Register offset.
  * @val:	Value to be written to register.
  */
-static inline void pch_spi_writereg(struct spi_master *master, int idx, u32 val)
+static inline void pch_spi_writereg(struct spi_controller *host, int idx, u32 val)
 {
-	struct pch_spi_data *data = spi_master_get_devdata(master);
+	struct pch_spi_data *data = spi_controller_get_devdata(host);
 	iowrite32(val, (data->io_remap_addr + idx));
 }
 
 /**
  * pch_spi_readreg() - Performs register reads
- * @master:	Pointer to struct spi_master.
+ * @host:	Pointer to struct spi_controller.
  * @idx:	Register offset.
  */
-static inline u32 pch_spi_readreg(struct spi_master *master, int idx)
+static inline u32 pch_spi_readreg(struct spi_controller *host, int idx)
 {
-	struct pch_spi_data *data = spi_master_get_devdata(master);
+	struct pch_spi_data *data = spi_controller_get_devdata(host);
 	return ioread32(data->io_remap_addr + idx);
 }
 
-static inline void pch_spi_setclr_reg(struct spi_master *master, int idx,
+static inline void pch_spi_setclr_reg(struct spi_controller *host, int idx,
 				      u32 set, u32 clr)
 {
-	u32 tmp = pch_spi_readreg(master, idx);
+	u32 tmp = pch_spi_readreg(host, idx);
 	tmp = (tmp & ~clr) | set;
-	pch_spi_writereg(master, idx, tmp);
+	pch_spi_writereg(host, idx, tmp);
 }
 
-static void pch_spi_set_master_mode(struct spi_master *master)
+static void pch_spi_set_host_mode(struct spi_controller *host)
 {
-	pch_spi_setclr_reg(master, PCH_SPCR, SPCR_MSTR_BIT, 0);
+	pch_spi_setclr_reg(host, PCH_SPCR, SPCR_MSTR_BIT, 0);
 }
 
 /**
  * pch_spi_clear_fifo() - Clears the Transmit and Receive FIFOs
- * @master:	Pointer to struct spi_master.
+ * @host:	Pointer to struct spi_controller.
  */
-static void pch_spi_clear_fifo(struct spi_master *master)
+static void pch_spi_clear_fifo(struct spi_controller *host)
 {
-	pch_spi_setclr_reg(master, PCH_SPCR, SPCR_FICLR_BIT, 0);
-	pch_spi_setclr_reg(master, PCH_SPCR, 0, SPCR_FICLR_BIT);
+	pch_spi_setclr_reg(host, PCH_SPCR, SPCR_FICLR_BIT, 0);
+	pch_spi_setclr_reg(host, PCH_SPCR, 0, SPCR_FICLR_BIT);
 }
 
 static void pch_spi_handler_sub(struct pch_spi_data *data, u32 reg_spsr_val,
@@ -312,7 +312,7 @@ static void pch_spi_handler_sub(struct pch_spi_data *data, u32 reg_spsr_val,
 		if (reg_spsr_val & SPSR_FI_BIT) {
 			if ((tx_index == bpw_len) && (rx_index == tx_index)) {
 				/* disable interrupts */
-				pch_spi_setclr_reg(data->master, PCH_SPCR, 0,
+				pch_spi_setclr_reg(data->host, PCH_SPCR, 0,
 						   PCH_ALL);
 
 				/* transfer is completed;
@@ -321,7 +321,7 @@ static void pch_spi_handler_sub(struct pch_spi_data *data, u32 reg_spsr_val,
 				data->transfer_active = false;
 				wake_up(&data->wait);
 			} else {
-				dev_vdbg(&data->master->dev,
+				dev_vdbg(&data->host->dev,
 					"%s : Transfer is not completed",
 					__func__);
 			}
@@ -383,10 +383,10 @@ static irqreturn_t pch_spi_handler(int irq, void *dev_id)
 
 /**
  * pch_spi_set_baud_rate() - Sets SPBR field in SPBRR
- * @master:	Pointer to struct spi_master.
+ * @host:	Pointer to struct spi_controller.
  * @speed_hz:	Baud rate.
  */
-static void pch_spi_set_baud_rate(struct spi_master *master, u32 speed_hz)
+static void pch_spi_set_baud_rate(struct spi_controller *host, u32 speed_hz)
 {
 	u32 n_spbr = PCH_CLOCK_HZ / (speed_hz * 2);
 
@@ -394,21 +394,21 @@ static void pch_spi_set_baud_rate(struct spi_master *master, u32 speed_hz)
 	if (n_spbr > PCH_MAX_SPBR)
 		n_spbr = PCH_MAX_SPBR;
 
-	pch_spi_setclr_reg(master, PCH_SPBRR, n_spbr, MASK_SPBRR_SPBR_BITS);
+	pch_spi_setclr_reg(host, PCH_SPBRR, n_spbr, MASK_SPBRR_SPBR_BITS);
 }
 
 /**
  * pch_spi_set_bits_per_word() - Sets SIZE field in SPBRR
- * @master:		Pointer to struct spi_master.
+ * @host:		Pointer to struct spi_controller.
  * @bits_per_word:	Bits per word for SPI transfer.
  */
-static void pch_spi_set_bits_per_word(struct spi_master *master,
+static void pch_spi_set_bits_per_word(struct spi_controller *host,
 				      u8 bits_per_word)
 {
 	if (bits_per_word == 8)
-		pch_spi_setclr_reg(master, PCH_SPBRR, 0, SPBRR_SIZE_BIT);
+		pch_spi_setclr_reg(host, PCH_SPBRR, 0, SPBRR_SIZE_BIT);
 	else
-		pch_spi_setclr_reg(master, PCH_SPBRR, SPBRR_SIZE_BIT, 0);
+		pch_spi_setclr_reg(host, PCH_SPBRR, SPBRR_SIZE_BIT, 0);
 }
 
 /**
@@ -420,12 +420,12 @@ static void pch_spi_setup_transfer(struct spi_device *spi)
 	u32 flags = 0;
 
 	dev_dbg(&spi->dev, "%s SPBRR content =%x setting baud rate=%d\n",
-		__func__, pch_spi_readreg(spi->master, PCH_SPBRR),
+		__func__, pch_spi_readreg(spi->controller, PCH_SPBRR),
 		spi->max_speed_hz);
-	pch_spi_set_baud_rate(spi->master, spi->max_speed_hz);
+	pch_spi_set_baud_rate(spi->controller, spi->max_speed_hz);
 
 	/* set bits per word */
-	pch_spi_set_bits_per_word(spi->master, spi->bits_per_word);
+	pch_spi_set_bits_per_word(spi->controller, spi->bits_per_word);
 
 	if (!(spi->mode & SPI_LSB_FIRST))
 		flags |= SPCR_LSBF_BIT;
@@ -433,29 +433,29 @@ static void pch_spi_setup_transfer(struct spi_device *spi)
 		flags |= SPCR_CPOL_BIT;
 	if (spi->mode & SPI_CPHA)
 		flags |= SPCR_CPHA_BIT;
-	pch_spi_setclr_reg(spi->master, PCH_SPCR, flags,
+	pch_spi_setclr_reg(spi->controller, PCH_SPCR, flags,
 			   (SPCR_LSBF_BIT | SPCR_CPOL_BIT | SPCR_CPHA_BIT));
 
 	/* Clear the FIFO by toggling  FICLR to 1 and back to 0 */
-	pch_spi_clear_fifo(spi->master);
+	pch_spi_clear_fifo(spi->controller);
 }
 
 /**
  * pch_spi_reset() - Clears SPI registers
- * @master:	Pointer to struct spi_master.
+ * @host:	Pointer to struct spi_controller.
  */
-static void pch_spi_reset(struct spi_master *master)
+static void pch_spi_reset(struct spi_controller *host)
 {
 	/* write 1 to reset SPI */
-	pch_spi_writereg(master, PCH_SRST, 0x1);
+	pch_spi_writereg(host, PCH_SRST, 0x1);
 
 	/* clear reset */
-	pch_spi_writereg(master, PCH_SRST, 0x0);
+	pch_spi_writereg(host, PCH_SRST, 0x0);
 }
 
 static int pch_spi_transfer(struct spi_device *pspi, struct spi_message *pmsg)
 {
-	struct pch_spi_data *data = spi_master_get_devdata(pspi->master);
+	struct pch_spi_data *data = spi_controller_get_devdata(pspi->controller);
 	int retval;
 	unsigned long flags;
 
@@ -524,15 +524,15 @@ static void pch_spi_set_tx(struct pch_spi_data *data, int *bpw)
 
 	/* set baud rate if needed */
 	if (data->cur_trans->speed_hz) {
-		dev_dbg(&data->master->dev, "%s:setting baud rate\n", __func__);
-		pch_spi_set_baud_rate(data->master, data->cur_trans->speed_hz);
+		dev_dbg(&data->host->dev, "%s:setting baud rate\n", __func__);
+		pch_spi_set_baud_rate(data->host, data->cur_trans->speed_hz);
 	}
 
 	/* set bits per word if needed */
 	if (data->cur_trans->bits_per_word &&
 	    (data->current_msg->spi->bits_per_word != data->cur_trans->bits_per_word)) {
-		dev_dbg(&data->master->dev, "%s:set bits per word\n", __func__);
-		pch_spi_set_bits_per_word(data->master,
+		dev_dbg(&data->host->dev, "%s:set bits per word\n", __func__);
+		pch_spi_set_bits_per_word(data->host,
 					  data->cur_trans->bits_per_word);
 		*bpw = data->cur_trans->bits_per_word;
 	} else {
@@ -590,13 +590,13 @@ static void pch_spi_set_tx(struct pch_spi_data *data, int *bpw)
 	if (n_writes > PCH_MAX_FIFO_DEPTH)
 		n_writes = PCH_MAX_FIFO_DEPTH;
 
-	dev_dbg(&data->master->dev,
+	dev_dbg(&data->host->dev,
 		"\n%s:Pulling down SSN low - writing 0x2 to SSNXCR\n",
 		__func__);
-	pch_spi_writereg(data->master, PCH_SSNXCR, SSN_LOW);
+	pch_spi_writereg(data->host, PCH_SSNXCR, SSN_LOW);
 
 	for (j = 0; j < n_writes; j++)
-		pch_spi_writereg(data->master, PCH_SPDWR, data->pkt_tx_buff[j]);
+		pch_spi_writereg(data->host, PCH_SPDWR, data->pkt_tx_buff[j]);
 
 	/* update tx_index */
 	data->tx_index = j;
@@ -609,13 +609,13 @@ static void pch_spi_set_tx(struct pch_spi_data *data, int *bpw)
 static void pch_spi_nomore_transfer(struct pch_spi_data *data)
 {
 	struct spi_message *pmsg, *tmp;
-	dev_dbg(&data->master->dev, "%s called\n", __func__);
+	dev_dbg(&data->host->dev, "%s called\n", __func__);
 	/* Invoke complete callback
 	 * [To the spi core..indicating end of transfer] */
 	data->current_msg->status = 0;
 
 	if (data->current_msg->complete) {
-		dev_dbg(&data->master->dev,
+		dev_dbg(&data->host->dev,
 			"%s:Invoking callback of SPI core\n", __func__);
 		data->current_msg->complete(data->current_msg->context);
 	}
@@ -623,7 +623,7 @@ static void pch_spi_nomore_transfer(struct pch_spi_data *data)
 	/* update status in global variable */
 	data->bcurrent_msg_processing = false;
 
-	dev_dbg(&data->master->dev,
+	dev_dbg(&data->host->dev,
 		"%s:data->bcurrent_msg_processing = false\n", __func__);
 
 	data->current_msg = NULL;
@@ -638,11 +638,11 @@ static void pch_spi_nomore_transfer(struct pch_spi_data *data)
 		 * bpw;sfer requests in the current message or there are
 		 *more messages)
 		 */
-		dev_dbg(&data->master->dev, "%s:Invoke queue_work\n", __func__);
+		dev_dbg(&data->host->dev, "%s:Invoke queue_work\n", __func__);
 		schedule_work(&data->work);
 	} else if (data->board_dat->suspend_sts ||
 		   data->status == STATUS_EXITING) {
-		dev_dbg(&data->master->dev,
+		dev_dbg(&data->host->dev,
 			"%s suspend/remove initiated, flushing queue\n",
 			__func__);
 		list_for_each_entry_safe(pmsg, tmp, data->queue.next, queue) {
@@ -662,14 +662,14 @@ static void pch_spi_set_ir(struct pch_spi_data *data)
 	/* enable interrupts, set threshold, enable SPI */
 	if ((data->bpw_len) > PCH_MAX_FIFO_DEPTH)
 		/* set receive threshold to PCH_RX_THOLD */
-		pch_spi_setclr_reg(data->master, PCH_SPCR,
+		pch_spi_setclr_reg(data->host, PCH_SPCR,
 				   PCH_RX_THOLD << SPCR_RFIC_FIELD |
 				   SPCR_FIE_BIT | SPCR_RFIE_BIT |
 				   SPCR_ORIE_BIT | SPCR_SPE_BIT,
 				   MASK_RFIC_SPCR_BITS | PCH_ALL);
 	else
 		/* set receive threshold to maximum */
-		pch_spi_setclr_reg(data->master, PCH_SPCR,
+		pch_spi_setclr_reg(data->host, PCH_SPCR,
 				   PCH_RX_THOLD_MAX << SPCR_RFIC_FIELD |
 				   SPCR_FIE_BIT | SPCR_ORIE_BIT |
 				   SPCR_SPE_BIT,
@@ -677,18 +677,18 @@ static void pch_spi_set_ir(struct pch_spi_data *data)
 
 	/* Wait until the transfer completes; go to sleep after
 				 initiating the transfer. */
-	dev_dbg(&data->master->dev,
+	dev_dbg(&data->host->dev,
 		"%s:waiting for transfer to get over\n", __func__);
 
 	wait_event_interruptible(data->wait, data->transfer_complete);
 
 	/* clear all interrupts */
-	pch_spi_writereg(data->master, PCH_SPSR,
-			 pch_spi_readreg(data->master, PCH_SPSR));
+	pch_spi_writereg(data->host, PCH_SPSR,
+			 pch_spi_readreg(data->host, PCH_SPSR));
 	/* Disable interrupts and SPI transfer */
-	pch_spi_setclr_reg(data->master, PCH_SPCR, 0, PCH_ALL | SPCR_SPE_BIT);
+	pch_spi_setclr_reg(data->host, PCH_SPCR, 0, PCH_ALL | SPCR_SPE_BIT);
 	/* clear FIFO */
-	pch_spi_clear_fifo(data->master);
+	pch_spi_clear_fifo(data->host);
 }
 
 static void pch_spi_copy_rx_data(struct pch_spi_data *data, int bpw)
@@ -750,25 +750,25 @@ static int pch_spi_start_transfer(struct pch_spi_data *data)
 	spin_lock_irqsave(&data->lock, flags);
 
 	/* disable interrupts, SPI set enable */
-	pch_spi_setclr_reg(data->master, PCH_SPCR, SPCR_SPE_BIT, PCH_ALL);
+	pch_spi_setclr_reg(data->host, PCH_SPCR, SPCR_SPE_BIT, PCH_ALL);
 
 	spin_unlock_irqrestore(&data->lock, flags);
 
 	/* Wait until the transfer completes; go to sleep after
 				 initiating the transfer. */
-	dev_dbg(&data->master->dev,
+	dev_dbg(&data->host->dev,
 		"%s:waiting for transfer to get over\n", __func__);
 	rtn = wait_event_interruptible_timeout(data->wait,
 					       data->transfer_complete,
 					       msecs_to_jiffies(2 * HZ));
 	if (!rtn)
-		dev_err(&data->master->dev,
+		dev_err(&data->host->dev,
 			"%s wait-event timeout\n", __func__);
 
-	dma_sync_sg_for_cpu(&data->master->dev, dma->sg_rx_p, dma->nent,
+	dma_sync_sg_for_cpu(&data->host->dev, dma->sg_rx_p, dma->nent,
 			    DMA_FROM_DEVICE);
 
-	dma_sync_sg_for_cpu(&data->master->dev, dma->sg_tx_p, dma->nent,
+	dma_sync_sg_for_cpu(&data->host->dev, dma->sg_tx_p, dma->nent,
 			    DMA_FROM_DEVICE);
 	memset(data->dma.tx_buf_virt, 0, PAGE_SIZE);
 
@@ -780,14 +780,14 @@ static int pch_spi_start_transfer(struct pch_spi_data *data)
 	spin_lock_irqsave(&data->lock, flags);
 
 	/* clear fifo threshold, disable interrupts, disable SPI transfer */
-	pch_spi_setclr_reg(data->master, PCH_SPCR, 0,
+	pch_spi_setclr_reg(data->host, PCH_SPCR, 0,
 			   MASK_RFIC_SPCR_BITS | MASK_TFIC_SPCR_BITS | PCH_ALL |
 			   SPCR_SPE_BIT);
 	/* clear all interrupts */
-	pch_spi_writereg(data->master, PCH_SPSR,
-			 pch_spi_readreg(data->master, PCH_SPSR));
+	pch_spi_writereg(data->host, PCH_SPSR,
+			 pch_spi_readreg(data->host, PCH_SPSR));
 	/* clear FIFO */
-	pch_spi_clear_fifo(data->master);
+	pch_spi_clear_fifo(data->host);
 
 	spin_unlock_irqrestore(&data->lock, flags);
 
@@ -846,7 +846,7 @@ static void pch_spi_request_dma(struct pch_spi_data *data, int bpw)
 	param->width = width;
 	chan = dma_request_channel(mask, pch_spi_filter, param);
 	if (!chan) {
-		dev_err(&data->master->dev,
+		dev_err(&data->host->dev,
 			"ERROR: dma_request_channel FAILS(Tx)\n");
 		goto out;
 	}
@@ -860,7 +860,7 @@ static void pch_spi_request_dma(struct pch_spi_data *data, int bpw)
 	param->width = width;
 	chan = dma_request_channel(mask, pch_spi_filter, param);
 	if (!chan) {
-		dev_err(&data->master->dev,
+		dev_err(&data->host->dev,
 			"ERROR: dma_request_channel FAILS(Rx)\n");
 		dma_release_channel(dma->chan_tx);
 		dma->chan_tx = NULL;
@@ -913,9 +913,9 @@ static void pch_spi_handle_dma(struct pch_spi_data *data, int *bpw)
 
 	/* set baud rate if needed */
 	if (data->cur_trans->speed_hz) {
-		dev_dbg(&data->master->dev, "%s:setting baud rate\n", __func__);
+		dev_dbg(&data->host->dev, "%s:setting baud rate\n", __func__);
 		spin_lock_irqsave(&data->lock, flags);
-		pch_spi_set_baud_rate(data->master, data->cur_trans->speed_hz);
+		pch_spi_set_baud_rate(data->host, data->cur_trans->speed_hz);
 		spin_unlock_irqrestore(&data->lock, flags);
 	}
 
@@ -923,9 +923,9 @@ static void pch_spi_handle_dma(struct pch_spi_data *data, int *bpw)
 	if (data->cur_trans->bits_per_word &&
 	    (data->current_msg->spi->bits_per_word !=
 	     data->cur_trans->bits_per_word)) {
-		dev_dbg(&data->master->dev, "%s:set bits per word\n", __func__);
+		dev_dbg(&data->host->dev, "%s:set bits per word\n", __func__);
 		spin_lock_irqsave(&data->lock, flags);
-		pch_spi_set_bits_per_word(data->master,
+		pch_spi_set_bits_per_word(data->host,
 					  data->cur_trans->bits_per_word);
 		spin_unlock_irqrestore(&data->lock, flags);
 		*bpw = data->cur_trans->bits_per_word;
@@ -969,12 +969,12 @@ static void pch_spi_handle_dma(struct pch_spi_data *data, int *bpw)
 		size = data->bpw_len;
 		rem = data->bpw_len;
 	}
-	dev_dbg(&data->master->dev, "%s num=%d size=%d rem=%d\n",
+	dev_dbg(&data->host->dev, "%s num=%d size=%d rem=%d\n",
 		__func__, num, size, rem);
 	spin_lock_irqsave(&data->lock, flags);
 
 	/* set receive fifo threshold and transmit fifo threshold */
-	pch_spi_setclr_reg(data->master, PCH_SPCR,
+	pch_spi_setclr_reg(data->host, PCH_SPCR,
 			   ((size - 1) << SPCR_RFIC_FIELD) |
 			   (PCH_TX_THOLD << SPCR_TFIC_FIELD),
 			   MASK_RFIC_SPCR_BITS | MASK_TFIC_SPCR_BITS);
@@ -1016,11 +1016,11 @@ static void pch_spi_handle_dma(struct pch_spi_data *data, int *bpw)
 					num, DMA_DEV_TO_MEM,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc_rx) {
-		dev_err(&data->master->dev,
+		dev_err(&data->host->dev,
 			"%s:dmaengine_prep_slave_sg Failed\n", __func__);
 		return;
 	}
-	dma_sync_sg_for_device(&data->master->dev, sg, num, DMA_FROM_DEVICE);
+	dma_sync_sg_for_device(&data->host->dev, sg, num, DMA_FROM_DEVICE);
 	desc_rx->callback = pch_dma_rx_complete;
 	desc_rx->callback_param = data;
 	dma->nent = num;
@@ -1078,20 +1078,20 @@ static void pch_spi_handle_dma(struct pch_spi_data *data, int *bpw)
 					sg, num, DMA_MEM_TO_DEV,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc_tx) {
-		dev_err(&data->master->dev,
+		dev_err(&data->host->dev,
 			"%s:dmaengine_prep_slave_sg Failed\n", __func__);
 		return;
 	}
-	dma_sync_sg_for_device(&data->master->dev, sg, num, DMA_TO_DEVICE);
+	dma_sync_sg_for_device(&data->host->dev, sg, num, DMA_TO_DEVICE);
 	desc_tx->callback = NULL;
 	desc_tx->callback_param = data;
 	dma->nent = num;
 	dma->desc_tx = desc_tx;
 
-	dev_dbg(&data->master->dev, "%s:Pulling down SSN low - writing 0x2 to SSNXCR\n", __func__);
+	dev_dbg(&data->host->dev, "%s:Pulling down SSN low - writing 0x2 to SSNXCR\n", __func__);
 
 	spin_lock_irqsave(&data->lock, flags);
-	pch_spi_writereg(data->master, PCH_SSNXCR, SSN_LOW);
+	pch_spi_writereg(data->host, PCH_SSNXCR, SSN_LOW);
 	desc_rx->tx_submit(desc_rx);
 	desc_tx->tx_submit(desc_tx);
 	spin_unlock_irqrestore(&data->lock, flags);
@@ -1107,12 +1107,12 @@ static void pch_spi_process_messages(struct work_struct *pwork)
 	int bpw;
 
 	data = container_of(pwork, struct pch_spi_data, work);
-	dev_dbg(&data->master->dev, "%s data initialized\n", __func__);
+	dev_dbg(&data->host->dev, "%s data initialized\n", __func__);
 
 	spin_lock(&data->lock);
 	/* check if suspend has been initiated;if yes flush queue */
 	if (data->board_dat->suspend_sts || (data->status == STATUS_EXITING)) {
-		dev_dbg(&data->master->dev,
+		dev_dbg(&data->host->dev,
 			"%s suspend/remove initiated, flushing queue\n", __func__);
 		list_for_each_entry_safe(pmsg, tmp, data->queue.next, queue) {
 			pmsg->status = -EIO;
@@ -1132,7 +1132,7 @@ static void pch_spi_process_messages(struct work_struct *pwork)
 	}
 
 	data->bcurrent_msg_processing = true;
-	dev_dbg(&data->master->dev,
+	dev_dbg(&data->host->dev,
 		"%s Set data->bcurrent_msg_processing= true\n", __func__);
 
 	/* Get the message from the queue and delete it from there. */
@@ -1150,7 +1150,7 @@ static void pch_spi_process_messages(struct work_struct *pwork)
 	if (data->use_dma)
 		pch_spi_request_dma(data,
 				    data->current_msg->spi->bits_per_word);
-	pch_spi_writereg(data->master, PCH_SSNXCR, SSN_NO_CONTROL);
+	pch_spi_writereg(data->host, PCH_SSNXCR, SSN_NO_CONTROL);
 	do {
 		int cnt;
 		/* If we are already processing a message get the next
@@ -1161,14 +1161,14 @@ static void pch_spi_process_messages(struct work_struct *pwork)
 			data->cur_trans =
 				list_entry(data->current_msg->transfers.next,
 					   struct spi_transfer, transfer_list);
-			dev_dbg(&data->master->dev,
+			dev_dbg(&data->host->dev,
 				"%s :Getting 1st transfer message\n",
 				__func__);
 		} else {
 			data->cur_trans =
 				list_entry(data->cur_trans->transfer_list.next,
 					   struct spi_transfer, transfer_list);
-			dev_dbg(&data->master->dev,
+			dev_dbg(&data->host->dev,
 				"%s :Getting next transfer message\n",
 				__func__);
 		}
@@ -1210,7 +1210,7 @@ static void pch_spi_process_messages(struct work_struct *pwork)
 		data->cur_trans->len = data->save_total_len;
 		data->current_msg->actual_length += data->cur_trans->len;
 
-		dev_dbg(&data->master->dev,
+		dev_dbg(&data->host->dev,
 			"%s:data->current_msg->actual_length=%d\n",
 			__func__, data->current_msg->actual_length);
 
@@ -1229,7 +1229,7 @@ static void pch_spi_process_messages(struct work_struct *pwork)
 	} while (data->cur_trans != NULL);
 
 out:
-	pch_spi_writereg(data->master, PCH_SSNXCR, SSN_HIGH);
+	pch_spi_writereg(data->host, PCH_SSNXCR, SSN_HIGH);
 	if (data->use_dma)
 		pch_spi_release_dma(data);
 }
@@ -1248,7 +1248,7 @@ static int pch_spi_get_resources(struct pch_spi_board_data *board_dat,
 	dev_dbg(&board_dat->pdev->dev, "%s ENTRY\n", __func__);
 
 	/* reset PCH SPI h/w */
-	pch_spi_reset(data->master);
+	pch_spi_reset(data->host);
 	dev_dbg(&board_dat->pdev->dev,
 		"%s pch_spi_reset invoked successfully\n", __func__);
 
@@ -1297,22 +1297,22 @@ static int pch_alloc_dma_buf(struct pch_spi_board_data *board_dat,
 static int pch_spi_pd_probe(struct platform_device *plat_dev)
 {
 	int ret;
-	struct spi_master *master;
+	struct spi_controller *host;
 	struct pch_spi_board_data *board_dat = dev_get_platdata(&plat_dev->dev);
 	struct pch_spi_data *data;
 
 	dev_dbg(&plat_dev->dev, "%s:debug\n", __func__);
 
-	master = spi_alloc_master(&board_dat->pdev->dev,
+	host = spi_alloc_host(&board_dat->pdev->dev,
 				  sizeof(struct pch_spi_data));
-	if (!master) {
-		dev_err(&plat_dev->dev, "spi_alloc_master[%d] failed.\n",
+	if (!host) {
+		dev_err(&plat_dev->dev, "spi_alloc_host[%d] failed.\n",
 			plat_dev->id);
 		return -ENOMEM;
 	}
 
-	data = spi_master_get_devdata(master);
-	data->master = master;
+	data = spi_controller_get_devdata(host);
+	data->host = host;
 
 	platform_set_drvdata(plat_dev, data);
 
@@ -1330,13 +1330,13 @@ static int pch_spi_pd_probe(struct platform_device *plat_dev)
 	dev_dbg(&plat_dev->dev, "[ch%d] remap_addr=%p\n",
 		plat_dev->id, data->io_remap_addr);
 
-	/* initialize members of SPI master */
-	master->num_chipselect = PCH_MAX_CS;
-	master->transfer = pch_spi_transfer;
-	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST;
-	master->bits_per_word_mask = SPI_BPW_MASK(8) | SPI_BPW_MASK(16);
-	master->max_speed_hz = PCH_MAX_BAUDRATE;
-	master->flags = SPI_CONTROLLER_MUST_RX | SPI_CONTROLLER_MUST_TX;
+	/* initialize members of SPI host */
+	host->num_chipselect = PCH_MAX_CS;
+	host->transfer = pch_spi_transfer;
+	host->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST;
+	host->bits_per_word_mask = SPI_BPW_MASK(8) | SPI_BPW_MASK(16);
+	host->max_speed_hz = PCH_MAX_BAUDRATE;
+	host->flags = SPI_CONTROLLER_MUST_RX | SPI_CONTROLLER_MUST_TX;
 
 	data->board_dat = board_dat;
 	data->plat_dev = plat_dev;
@@ -1365,25 +1365,25 @@ static int pch_spi_pd_probe(struct platform_device *plat_dev)
 	}
 	data->irq_reg_sts = true;
 
-	pch_spi_set_master_mode(master);
+	pch_spi_set_host_mode(host);
 
 	if (use_dma) {
 		dev_info(&plat_dev->dev, "Use DMA for data transfers\n");
 		ret = pch_alloc_dma_buf(board_dat, data);
 		if (ret)
-			goto err_spi_register_master;
+			goto err_spi_register_controller;
 	}
 
-	ret = spi_register_master(master);
+	ret = spi_register_controller(host);
 	if (ret != 0) {
 		dev_err(&plat_dev->dev,
-			"%s spi_register_master FAILED\n", __func__);
-		goto err_spi_register_master;
+			"%s spi_register_controller FAILED\n", __func__);
+		goto err_spi_register_controller;
 	}
 
 	return 0;
 
-err_spi_register_master:
+err_spi_register_controller:
 	pch_free_dma_buf(board_dat, data);
 	free_irq(board_dat->pdev->irq, data);
 err_request_irq:
@@ -1391,7 +1391,7 @@ err_request_irq:
 err_spi_get_resources:
 	pci_iounmap(board_dat->pdev, data->io_remap_addr);
 err_pci_iomap:
-	spi_master_put(master);
+	spi_controller_put(host);
 
 	return ret;
 }
@@ -1427,13 +1427,13 @@ static void pch_spi_pd_remove(struct platform_device *plat_dev)
 	/* disable interrupts & free IRQ */
 	if (data->irq_reg_sts) {
 		/* disable interrupts */
-		pch_spi_setclr_reg(data->master, PCH_SPCR, 0, PCH_ALL);
+		pch_spi_setclr_reg(data->host, PCH_SPCR, 0, PCH_ALL);
 		data->irq_reg_sts = false;
 		free_irq(board_dat->pdev->irq, data);
 	}
 
 	pci_iounmap(board_dat->pdev, data->io_remap_addr);
-	spi_unregister_master(data->master);
+	spi_unregister_controller(data->host);
 }
 #ifdef CONFIG_PM
 static int pch_spi_pd_suspend(struct platform_device *pd_dev,
@@ -1463,8 +1463,8 @@ static int pch_spi_pd_suspend(struct platform_device *pd_dev,
 	/* Free IRQ */
 	if (data->irq_reg_sts) {
 		/* disable all interrupts */
-		pch_spi_setclr_reg(data->master, PCH_SPCR, 0, PCH_ALL);
-		pch_spi_reset(data->master);
+		pch_spi_setclr_reg(data->host, PCH_SPCR, 0, PCH_ALL);
+		pch_spi_reset(data->host);
 		free_irq(board_dat->pdev->irq, data);
 
 		data->irq_reg_sts = false;
@@ -1498,8 +1498,8 @@ static int pch_spi_pd_resume(struct platform_device *pd_dev)
 		}
 
 		/* reset PCH SPI h/w */
-		pch_spi_reset(data->master);
-		pch_spi_set_master_mode(data->master);
+		pch_spi_reset(data->host);
+		pch_spi_set_host_mode(data->host);
 		data->irq_reg_sts = true;
 	}
 	return 0;
diff --git a/drivers/spi/spi-uniphier.c b/drivers/spi/spi-uniphier.c
index f5344527af0b..4a18cf896194 100644
--- a/drivers/spi/spi-uniphier.c
+++ b/drivers/spi/spi-uniphier.c
@@ -26,7 +26,7 @@ struct uniphier_spi_priv {
 	void __iomem *base;
 	dma_addr_t base_dma_addr;
 	struct clk *clk;
-	struct spi_master *master;
+	struct spi_controller *host;
 	struct completion xfer_done;
 
 	int error;
@@ -127,7 +127,7 @@ static inline void uniphier_spi_irq_disable(struct uniphier_spi_priv *priv,
 
 static void uniphier_spi_set_mode(struct spi_device *spi)
 {
-	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	struct uniphier_spi_priv *priv = spi_controller_get_devdata(spi->controller);
 	u32 val1, val2;
 
 	/*
@@ -180,7 +180,7 @@ static void uniphier_spi_set_mode(struct spi_device *spi)
 
 static void uniphier_spi_set_transfer_size(struct spi_device *spi, int size)
 {
-	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	struct uniphier_spi_priv *priv = spi_controller_get_devdata(spi->controller);
 	u32 val;
 
 	val = readl(priv->base + SSI_TXWDS);
@@ -198,7 +198,7 @@ static void uniphier_spi_set_transfer_size(struct spi_device *spi, int size)
 static void uniphier_spi_set_baudrate(struct spi_device *spi,
 				      unsigned int speed)
 {
-	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	struct uniphier_spi_priv *priv = spi_controller_get_devdata(spi->controller);
 	u32 val, ckdiv;
 
 	/*
@@ -217,7 +217,7 @@ static void uniphier_spi_set_baudrate(struct spi_device *spi,
 static void uniphier_spi_setup_transfer(struct spi_device *spi,
 				       struct spi_transfer *t)
 {
-	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	struct uniphier_spi_priv *priv = spi_controller_get_devdata(spi->controller);
 	u32 val;
 
 	priv->error = 0;
@@ -333,7 +333,7 @@ static void uniphier_spi_fill_tx_fifo(struct uniphier_spi_priv *priv)
 
 static void uniphier_spi_set_cs(struct spi_device *spi, bool enable)
 {
-	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	struct uniphier_spi_priv *priv = spi_controller_get_devdata(spi->controller);
 	u32 val;
 
 	val = readl(priv->base + SSI_FPS);
@@ -346,16 +346,16 @@ static void uniphier_spi_set_cs(struct spi_device *spi, bool enable)
 	writel(val, priv->base + SSI_FPS);
 }
 
-static bool uniphier_spi_can_dma(struct spi_master *master,
+static bool uniphier_spi_can_dma(struct spi_controller *host,
 				 struct spi_device *spi,
 				 struct spi_transfer *t)
 {
-	struct uniphier_spi_priv *priv = spi_master_get_devdata(master);
+	struct uniphier_spi_priv *priv = spi_controller_get_devdata(host);
 	unsigned int bpw = bytes_per_word(priv->bits_per_word);
 
-	if ((!master->dma_tx && !master->dma_rx)
-	    || (!master->dma_tx && t->tx_buf)
-	    || (!master->dma_rx && t->rx_buf))
+	if ((!host->dma_tx && !host->dma_rx)
+	    || (!host->dma_tx && t->tx_buf)
+	    || (!host->dma_rx && t->rx_buf))
 		return false;
 
 	return DIV_ROUND_UP(t->len, bpw) > SSI_FIFO_DEPTH;
@@ -363,33 +363,33 @@ static bool uniphier_spi_can_dma(struct spi_master *master,
 
 static void uniphier_spi_dma_rxcb(void *data)
 {
-	struct spi_master *master = data;
-	struct uniphier_spi_priv *priv = spi_master_get_devdata(master);
+	struct spi_controller *host = data;
+	struct uniphier_spi_priv *priv = spi_controller_get_devdata(host);
 	int state = atomic_fetch_andnot(SSI_DMA_RX_BUSY, &priv->dma_busy);
 
 	uniphier_spi_irq_disable(priv, SSI_IE_RXRE);
 
 	if (!(state & SSI_DMA_TX_BUSY))
-		spi_finalize_current_transfer(master);
+		spi_finalize_current_transfer(host);
 }
 
 static void uniphier_spi_dma_txcb(void *data)
 {
-	struct spi_master *master = data;
-	struct uniphier_spi_priv *priv = spi_master_get_devdata(master);
+	struct spi_controller *host = data;
+	struct uniphier_spi_priv *priv = spi_controller_get_devdata(host);
 	int state = atomic_fetch_andnot(SSI_DMA_TX_BUSY, &priv->dma_busy);
 
 	uniphier_spi_irq_disable(priv, SSI_IE_TXRE);
 
 	if (!(state & SSI_DMA_RX_BUSY))
-		spi_finalize_current_transfer(master);
+		spi_finalize_current_transfer(host);
 }
 
-static int uniphier_spi_transfer_one_dma(struct spi_master *master,
+static int uniphier_spi_transfer_one_dma(struct spi_controller *host,
 					 struct spi_device *spi,
 					 struct spi_transfer *t)
 {
-	struct uniphier_spi_priv *priv = spi_master_get_devdata(master);
+	struct uniphier_spi_priv *priv = spi_controller_get_devdata(host);
 	struct dma_async_tx_descriptor *rxdesc = NULL, *txdesc = NULL;
 	int buswidth;
 
@@ -412,23 +412,23 @@ static int uniphier_spi_transfer_one_dma(struct spi_master *master,
 			.src_maxburst = SSI_FIFO_BURST_NUM,
 		};
 
-		dmaengine_slave_config(master->dma_rx, &rxconf);
+		dmaengine_slave_config(host->dma_rx, &rxconf);
 
 		rxdesc = dmaengine_prep_slave_sg(
-			master->dma_rx,
+			host->dma_rx,
 			t->rx_sg.sgl, t->rx_sg.nents,
 			DMA_DEV_TO_MEM, DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 		if (!rxdesc)
 			goto out_err_prep;
 
 		rxdesc->callback = uniphier_spi_dma_rxcb;
-		rxdesc->callback_param = master;
+		rxdesc->callback_param = host;
 
 		uniphier_spi_irq_enable(priv, SSI_IE_RXRE);
 		atomic_or(SSI_DMA_RX_BUSY, &priv->dma_busy);
 
 		dmaengine_submit(rxdesc);
-		dma_async_issue_pending(master->dma_rx);
+		dma_async_issue_pending(host->dma_rx);
 	}
 
 	if (priv->tx_buf) {
@@ -439,23 +439,23 @@ static int uniphier_spi_transfer_one_dma(struct spi_master *master,
 			.dst_maxburst = SSI_FIFO_BURST_NUM,
 		};
 
-		dmaengine_slave_config(master->dma_tx, &txconf);
+		dmaengine_slave_config(host->dma_tx, &txconf);
 
 		txdesc = dmaengine_prep_slave_sg(
-			master->dma_tx,
+			host->dma_tx,
 			t->tx_sg.sgl, t->tx_sg.nents,
 			DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 		if (!txdesc)
 			goto out_err_prep;
 
 		txdesc->callback = uniphier_spi_dma_txcb;
-		txdesc->callback_param = master;
+		txdesc->callback_param = host;
 
 		uniphier_spi_irq_enable(priv, SSI_IE_TXRE);
 		atomic_or(SSI_DMA_TX_BUSY, &priv->dma_busy);
 
 		dmaengine_submit(txdesc);
-		dma_async_issue_pending(master->dma_tx);
+		dma_async_issue_pending(host->dma_tx);
 	}
 
 	/* signal that we need to wait for completion */
@@ -463,17 +463,17 @@ static int uniphier_spi_transfer_one_dma(struct spi_master *master,
 
 out_err_prep:
 	if (rxdesc)
-		dmaengine_terminate_sync(master->dma_rx);
+		dmaengine_terminate_sync(host->dma_rx);
 
 	return -EINVAL;
 }
 
-static int uniphier_spi_transfer_one_irq(struct spi_master *master,
+static int uniphier_spi_transfer_one_irq(struct spi_controller *host,
 					 struct spi_device *spi,
 					 struct spi_transfer *t)
 {
-	struct uniphier_spi_priv *priv = spi_master_get_devdata(master);
-	struct device *dev = master->dev.parent;
+	struct uniphier_spi_priv *priv = spi_controller_get_devdata(host);
+	struct device *dev = host->dev.parent;
 	unsigned long time_left;
 
 	reinit_completion(&priv->xfer_done);
@@ -495,11 +495,11 @@ static int uniphier_spi_transfer_one_irq(struct spi_master *master,
 	return priv->error;
 }
 
-static int uniphier_spi_transfer_one_poll(struct spi_master *master,
+static int uniphier_spi_transfer_one_poll(struct spi_controller *host,
 					  struct spi_device *spi,
 					  struct spi_transfer *t)
 {
-	struct uniphier_spi_priv *priv = spi_master_get_devdata(master);
+	struct uniphier_spi_priv *priv = spi_controller_get_devdata(host);
 	int loop = SSI_POLL_TIMEOUT_US * 10;
 
 	while (priv->tx_bytes) {
@@ -520,14 +520,14 @@ static int uniphier_spi_transfer_one_poll(struct spi_master *master,
 	return 0;
 
 irq_transfer:
-	return uniphier_spi_transfer_one_irq(master, spi, t);
+	return uniphier_spi_transfer_one_irq(host, spi, t);
 }
 
-static int uniphier_spi_transfer_one(struct spi_master *master,
+static int uniphier_spi_transfer_one(struct spi_controller *host,
 				     struct spi_device *spi,
 				     struct spi_transfer *t)
 {
-	struct uniphier_spi_priv *priv = spi_master_get_devdata(master);
+	struct uniphier_spi_priv *priv = spi_controller_get_devdata(host);
 	unsigned long threshold;
 	bool use_dma;
 
@@ -537,9 +537,9 @@ static int uniphier_spi_transfer_one(struct spi_master *master,
 
 	uniphier_spi_setup_transfer(spi, t);
 
-	use_dma = master->can_dma ? master->can_dma(master, spi, t) : false;
+	use_dma = host->can_dma ? host->can_dma(host, spi, t) : false;
 	if (use_dma)
-		return uniphier_spi_transfer_one_dma(master, spi, t);
+		return uniphier_spi_transfer_one_dma(host, spi, t);
 
 	/*
 	 * If the transfer operation will take longer than
@@ -548,33 +548,33 @@ static int uniphier_spi_transfer_one(struct spi_master *master,
 	threshold = DIV_ROUND_UP(SSI_POLL_TIMEOUT_US * priv->speed_hz,
 					USEC_PER_SEC * BITS_PER_BYTE);
 	if (t->len > threshold)
-		return uniphier_spi_transfer_one_irq(master, spi, t);
+		return uniphier_spi_transfer_one_irq(host, spi, t);
 	else
-		return uniphier_spi_transfer_one_poll(master, spi, t);
+		return uniphier_spi_transfer_one_poll(host, spi, t);
 }
 
-static int uniphier_spi_prepare_transfer_hardware(struct spi_master *master)
+static int uniphier_spi_prepare_transfer_hardware(struct spi_controller *host)
 {
-	struct uniphier_spi_priv *priv = spi_master_get_devdata(master);
+	struct uniphier_spi_priv *priv = spi_controller_get_devdata(host);
 
 	writel(SSI_CTL_EN, priv->base + SSI_CTL);
 
 	return 0;
 }
 
-static int uniphier_spi_unprepare_transfer_hardware(struct spi_master *master)
+static int uniphier_spi_unprepare_transfer_hardware(struct spi_controller *host)
 {
-	struct uniphier_spi_priv *priv = spi_master_get_devdata(master);
+	struct uniphier_spi_priv *priv = spi_controller_get_devdata(host);
 
 	writel(0, priv->base + SSI_CTL);
 
 	return 0;
 }
 
-static void uniphier_spi_handle_err(struct spi_master *master,
+static void uniphier_spi_handle_err(struct spi_controller *host,
 				    struct spi_message *msg)
 {
-	struct uniphier_spi_priv *priv = spi_master_get_devdata(master);
+	struct uniphier_spi_priv *priv = spi_controller_get_devdata(host);
 	u32 val;
 
 	/* stop running spi transfer */
@@ -587,12 +587,12 @@ static void uniphier_spi_handle_err(struct spi_master *master,
 	uniphier_spi_irq_disable(priv, SSI_IE_ALL_MASK);
 
 	if (atomic_read(&priv->dma_busy) & SSI_DMA_TX_BUSY) {
-		dmaengine_terminate_async(master->dma_tx);
+		dmaengine_terminate_async(host->dma_tx);
 		atomic_andnot(SSI_DMA_TX_BUSY, &priv->dma_busy);
 	}
 
 	if (atomic_read(&priv->dma_busy) & SSI_DMA_RX_BUSY) {
-		dmaengine_terminate_async(master->dma_rx);
+		dmaengine_terminate_async(host->dma_rx);
 		atomic_andnot(SSI_DMA_RX_BUSY, &priv->dma_busy);
 	}
 }
@@ -641,7 +641,7 @@ done:
 static int uniphier_spi_probe(struct platform_device *pdev)
 {
 	struct uniphier_spi_priv *priv;
-	struct spi_master *master;
+	struct spi_controller *host;
 	struct resource *res;
 	struct dma_slave_caps caps;
 	u32 dma_tx_burst = 0, dma_rx_burst = 0;
@@ -649,20 +649,20 @@ static int uniphier_spi_probe(struct platform_device *pdev)
 	int irq;
 	int ret;
 
-	master = spi_alloc_master(&pdev->dev, sizeof(*priv));
-	if (!master)
+	host = spi_alloc_host(&pdev->dev, sizeof(*priv));
+	if (!host)
 		return -ENOMEM;
 
-	platform_set_drvdata(pdev, master);
+	platform_set_drvdata(pdev, host);
 
-	priv = spi_master_get_devdata(master);
-	priv->master = master;
+	priv = spi_controller_get_devdata(host);
+	priv->host = host;
 	priv->is_save_param = false;
 
 	priv->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(priv->base)) {
 		ret = PTR_ERR(priv->base);
-		goto out_master_put;
+		goto out_host_put;
 	}
 	priv->base_dma_addr = res->start;
 
@@ -670,12 +670,12 @@ static int uniphier_spi_probe(struct platform_device *pdev)
 	if (IS_ERR(priv->clk)) {
 		dev_err(&pdev->dev, "failed to get clock\n");
 		ret = PTR_ERR(priv->clk);
-		goto out_master_put;
+		goto out_host_put;
 	}
 
 	ret = clk_prepare_enable(priv->clk);
 	if (ret)
-		goto out_master_put;
+		goto out_host_put;
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
@@ -694,35 +694,35 @@ static int uniphier_spi_probe(struct platform_device *pdev)
 
 	clk_rate = clk_get_rate(priv->clk);
 
-	master->max_speed_hz = DIV_ROUND_UP(clk_rate, SSI_MIN_CLK_DIVIDER);
-	master->min_speed_hz = DIV_ROUND_UP(clk_rate, SSI_MAX_CLK_DIVIDER);
-	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LSB_FIRST;
-	master->dev.of_node = pdev->dev.of_node;
-	master->bus_num = pdev->id;
-	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 32);
+	host->max_speed_hz = DIV_ROUND_UP(clk_rate, SSI_MIN_CLK_DIVIDER);
+	host->min_speed_hz = DIV_ROUND_UP(clk_rate, SSI_MAX_CLK_DIVIDER);
+	host->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LSB_FIRST;
+	host->dev.of_node = pdev->dev.of_node;
+	host->bus_num = pdev->id;
+	host->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 32);
 
-	master->set_cs = uniphier_spi_set_cs;
-	master->transfer_one = uniphier_spi_transfer_one;
-	master->prepare_transfer_hardware
+	host->set_cs = uniphier_spi_set_cs;
+	host->transfer_one = uniphier_spi_transfer_one;
+	host->prepare_transfer_hardware
 				= uniphier_spi_prepare_transfer_hardware;
-	master->unprepare_transfer_hardware
+	host->unprepare_transfer_hardware
 				= uniphier_spi_unprepare_transfer_hardware;
-	master->handle_err = uniphier_spi_handle_err;
-	master->can_dma = uniphier_spi_can_dma;
+	host->handle_err = uniphier_spi_handle_err;
+	host->can_dma = uniphier_spi_can_dma;
 
-	master->num_chipselect = 1;
-	master->flags = SPI_CONTROLLER_MUST_RX | SPI_CONTROLLER_MUST_TX;
+	host->num_chipselect = 1;
+	host->flags = SPI_CONTROLLER_MUST_RX | SPI_CONTROLLER_MUST_TX;
 
-	master->dma_tx = dma_request_chan(&pdev->dev, "tx");
-	if (IS_ERR_OR_NULL(master->dma_tx)) {
-		if (PTR_ERR(master->dma_tx) == -EPROBE_DEFER) {
+	host->dma_tx = dma_request_chan(&pdev->dev, "tx");
+	if (IS_ERR_OR_NULL(host->dma_tx)) {
+		if (PTR_ERR(host->dma_tx) == -EPROBE_DEFER) {
 			ret = -EPROBE_DEFER;
 			goto out_disable_clk;
 		}
-		master->dma_tx = NULL;
+		host->dma_tx = NULL;
 		dma_tx_burst = INT_MAX;
 	} else {
-		ret = dma_get_slave_caps(master->dma_tx, &caps);
+		ret = dma_get_slave_caps(host->dma_tx, &caps);
 		if (ret) {
 			dev_err(&pdev->dev, "failed to get TX DMA capacities: %d\n",
 				ret);
@@ -731,16 +731,16 @@ static int uniphier_spi_probe(struct platform_device *pdev)
 		dma_tx_burst = caps.max_burst;
 	}
 
-	master->dma_rx = dma_request_chan(&pdev->dev, "rx");
-	if (IS_ERR_OR_NULL(master->dma_rx)) {
-		if (PTR_ERR(master->dma_rx) == -EPROBE_DEFER) {
+	host->dma_rx = dma_request_chan(&pdev->dev, "rx");
+	if (IS_ERR_OR_NULL(host->dma_rx)) {
+		if (PTR_ERR(host->dma_rx) == -EPROBE_DEFER) {
 			ret = -EPROBE_DEFER;
 			goto out_release_dma;
 		}
-		master->dma_rx = NULL;
+		host->dma_rx = NULL;
 		dma_rx_burst = INT_MAX;
 	} else {
-		ret = dma_get_slave_caps(master->dma_rx, &caps);
+		ret = dma_get_slave_caps(host->dma_rx, &caps);
 		if (ret) {
 			dev_err(&pdev->dev, "failed to get RX DMA capacities: %d\n",
 				ret);
@@ -749,41 +749,41 @@ static int uniphier_spi_probe(struct platform_device *pdev)
 		dma_rx_burst = caps.max_burst;
 	}
 
-	master->max_dma_len = min(dma_tx_burst, dma_rx_burst);
+	host->max_dma_len = min(dma_tx_burst, dma_rx_burst);
 
-	ret = devm_spi_register_master(&pdev->dev, master);
+	ret = devm_spi_register_controller(&pdev->dev, host);
 	if (ret)
 		goto out_release_dma;
 
 	return 0;
 
 out_release_dma:
-	if (!IS_ERR_OR_NULL(master->dma_rx)) {
-		dma_release_channel(master->dma_rx);
-		master->dma_rx = NULL;
+	if (!IS_ERR_OR_NULL(host->dma_rx)) {
+		dma_release_channel(host->dma_rx);
+		host->dma_rx = NULL;
 	}
-	if (!IS_ERR_OR_NULL(master->dma_tx)) {
-		dma_release_channel(master->dma_tx);
-		master->dma_tx = NULL;
+	if (!IS_ERR_OR_NULL(host->dma_tx)) {
+		dma_release_channel(host->dma_tx);
+		host->dma_tx = NULL;
 	}
 
 out_disable_clk:
 	clk_disable_unprepare(priv->clk);
 
-out_master_put:
-	spi_master_put(master);
+out_host_put:
+	spi_controller_put(host);
 	return ret;
 }
 
 static void uniphier_spi_remove(struct platform_device *pdev)
 {
-	struct spi_master *master = platform_get_drvdata(pdev);
-	struct uniphier_spi_priv *priv = spi_master_get_devdata(master);
+	struct spi_controller *host = platform_get_drvdata(pdev);
+	struct uniphier_spi_priv *priv = spi_controller_get_devdata(host);
 
-	if (master->dma_tx)
-		dma_release_channel(master->dma_tx);
-	if (master->dma_rx)
-		dma_release_channel(master->dma_rx);
+	if (host->dma_tx)
+		dma_release_channel(host->dma_tx);
+	if (host->dma_rx)
+		dma_release_channel(host->dma_rx);
 
 	clk_disable_unprepare(priv->clk);
 }
diff --git a/drivers/spi/spi-wpcm-fiu.c b/drivers/spi/spi-wpcm-fiu.c
index 852ffe013d32..6b16a22cc3a4 100644
--- a/drivers/spi/spi-wpcm-fiu.c
+++ b/drivers/spi/spi-wpcm-fiu.c
@@ -361,7 +361,7 @@ static int wpcm_fiu_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 
 	wpcm_fiu_stall_host(fiu, false);
 
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static int wpcm_fiu_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op)
@@ -441,7 +441,7 @@ static int wpcm_fiu_probe(struct platform_device *pdev)
 	struct wpcm_fiu_spi *fiu;
 	struct resource *res;
 
-	ctrl = devm_spi_alloc_master(dev, sizeof(*fiu));
+	ctrl = devm_spi_alloc_host(dev, sizeof(*fiu));
 	if (!ctrl)
 		return -ENOMEM;
 
diff --git a/drivers/spi/spi-xcomm.c b/drivers/spi/spi-xcomm.c
index a3d57554f5ba..63354dd3110f 100644
--- a/drivers/spi/spi-xcomm.c
+++ b/drivers/spi/spi-xcomm.c
@@ -132,10 +132,10 @@ static int spi_xcomm_txrx_bufs(struct spi_xcomm *spi_xcomm,
 	return t->len;
 }
 
-static int spi_xcomm_transfer_one(struct spi_master *master,
+static int spi_xcomm_transfer_one(struct spi_controller *host,
 	struct spi_message *msg)
 {
-	struct spi_xcomm *spi_xcomm = spi_master_get_devdata(master);
+	struct spi_xcomm *spi_xcomm = spi_controller_get_devdata(host);
 	unsigned int settings = spi_xcomm->settings;
 	struct spi_device *spi = msg->spi;
 	unsigned cs_change = 0;
@@ -197,7 +197,7 @@ static int spi_xcomm_transfer_one(struct spi_master *master,
 		spi_xcomm_chipselect(spi_xcomm, spi, false);
 
 	msg->status = status;
-	spi_finalize_current_message(master);
+	spi_finalize_current_message(host);
 
 	return status;
 }
@@ -205,27 +205,27 @@ static int spi_xcomm_transfer_one(struct spi_master *master,
 static int spi_xcomm_probe(struct i2c_client *i2c)
 {
 	struct spi_xcomm *spi_xcomm;
-	struct spi_master *master;
+	struct spi_controller *host;
 	int ret;
 
-	master = spi_alloc_master(&i2c->dev, sizeof(*spi_xcomm));
-	if (!master)
+	host = spi_alloc_host(&i2c->dev, sizeof(*spi_xcomm));
+	if (!host)
 		return -ENOMEM;
 
-	spi_xcomm = spi_master_get_devdata(master);
+	spi_xcomm = spi_controller_get_devdata(host);
 	spi_xcomm->i2c = i2c;
 
-	master->num_chipselect = 16;
-	master->mode_bits = SPI_CPHA | SPI_CPOL | SPI_3WIRE;
-	master->bits_per_word_mask = SPI_BPW_MASK(8);
-	master->flags = SPI_CONTROLLER_HALF_DUPLEX;
-	master->transfer_one_message = spi_xcomm_transfer_one;
-	master->dev.of_node = i2c->dev.of_node;
-	i2c_set_clientdata(i2c, master);
+	host->num_chipselect = 16;
+	host->mode_bits = SPI_CPHA | SPI_CPOL | SPI_3WIRE;
+	host->bits_per_word_mask = SPI_BPW_MASK(8);
+	host->flags = SPI_CONTROLLER_HALF_DUPLEX;
+	host->transfer_one_message = spi_xcomm_transfer_one;
+	host->dev.of_node = i2c->dev.of_node;
+	i2c_set_clientdata(i2c, host);
 
-	ret = devm_spi_register_master(&i2c->dev, master);
+	ret = devm_spi_register_controller(&i2c->dev, host);
 	if (ret < 0)
-		spi_master_put(master);
+		spi_controller_put(host);
 
 	return ret;
 }
diff --git a/drivers/spi/spi-xilinx.c b/drivers/spi/spi-xilinx.c
index 8e6e3876aa9a..12355957be97 100644
--- a/drivers/spi/spi-xilinx.c
+++ b/drivers/spi/spi-xilinx.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Xilinx SPI controller driver (master mode only)
+ * Xilinx SPI controller driver (host mode only)
  *
  * Author: MontaVista Software, Inc.
  *	source@mvista.com
@@ -83,7 +83,7 @@ struct xilinx_spi {
 	void __iomem	*regs;	/* virt. address of the control registers */
 
 	int		irq;
-	bool force_irq;		/* force irq to setup master inhibit */
+	bool force_irq;		/* force irq to setup host inhibit */
 	u8 *rx_ptr;		/* pointer in the Tx buffer */
 	const u8 *tx_ptr;	/* pointer in the Rx buffer */
 	u8 bytes_per_word;
@@ -174,10 +174,10 @@ static void xspi_init_hw(struct xilinx_spi *xspi)
 			regs_base + XIPIF_V123B_IIER_OFFSET);
 	/* Disable the global IPIF interrupt */
 	xspi->write_fn(0, regs_base + XIPIF_V123B_DGIER_OFFSET);
-	/* Deselect the slave on the SPI bus */
+	/* Deselect the Target on the SPI bus */
 	xspi->write_fn(0xffff, regs_base + XSPI_SSR_OFFSET);
-	/* Disable the transmitter, enable Manual Slave Select Assertion,
-	 * put SPI controller into master mode, and enable it */
+	/* Disable the transmitter, enable Manual Target Select Assertion,
+	 * put SPI controller into host mode, and enable it */
 	xspi->write_fn(XSPI_CR_MANUAL_SSELECT |	XSPI_CR_MASTER_MODE |
 		XSPI_CR_ENABLE | XSPI_CR_TXFIFO_RESET |	XSPI_CR_RXFIFO_RESET,
 		regs_base + XSPI_CR_OFFSET);
@@ -185,12 +185,12 @@ static void xspi_init_hw(struct xilinx_spi *xspi)
 
 static void xilinx_spi_chipselect(struct spi_device *spi, int is_on)
 {
-	struct xilinx_spi *xspi = spi_master_get_devdata(spi->master);
+	struct xilinx_spi *xspi = spi_controller_get_devdata(spi->controller);
 	u16 cr;
 	u32 cs;
 
 	if (is_on == BITBANG_CS_INACTIVE) {
-		/* Deselect the slave on the SPI bus */
+		/* Deselect the target on the SPI bus */
 		xspi->write_fn(xspi->cs_inactive, xspi->regs + XSPI_SSR_OFFSET);
 		return;
 	}
@@ -225,7 +225,7 @@ static void xilinx_spi_chipselect(struct spi_device *spi, int is_on)
 static int xilinx_spi_setup_transfer(struct spi_device *spi,
 		struct spi_transfer *t)
 {
-	struct xilinx_spi *xspi = spi_master_get_devdata(spi->master);
+	struct xilinx_spi *xspi = spi_controller_get_devdata(spi->controller);
 
 	if (spi->mode & SPI_CS_HIGH)
 		xspi->cs_inactive &= ~BIT(spi_get_chipselect(spi, 0));
@@ -237,7 +237,7 @@ static int xilinx_spi_setup_transfer(struct spi_device *spi,
 
 static int xilinx_spi_txrx_bufs(struct spi_device *spi, struct spi_transfer *t)
 {
-	struct xilinx_spi *xspi = spi_master_get_devdata(spi->master);
+	struct xilinx_spi *xspi = spi_controller_get_devdata(spi->controller);
 	int remaining_words;	/* the number of words left to transfer */
 	bool use_irq = false;
 	u16 cr = 0;
@@ -335,9 +335,9 @@ static int xilinx_spi_txrx_bufs(struct spi_device *spi, struct spi_transfer *t)
 }
 
 
-/* This driver supports single master mode only. Hence Tx FIFO Empty
+/* This driver supports single host mode only. Hence Tx FIFO Empty
  * is the only interrupt we care about.
- * Receive FIFO Overrun, Transmit FIFO Underrun, Mode Fault, and Slave Mode
+ * Receive FIFO Overrun, Transmit FIFO Underrun, Mode Fault, and Target Mode
  * Fault are not to happen.
  */
 static irqreturn_t xilinx_spi_irq(int irq, void *dev_id)
@@ -393,7 +393,7 @@ static int xilinx_spi_probe(struct platform_device *pdev)
 	struct xspi_platform_data *pdata;
 	struct resource *res;
 	int ret, num_cs = 0, bits_per_word;
-	struct spi_master *master;
+	struct spi_controller *host;
 	bool force_irq = false;
 	u32 tmp;
 	u8 i;
@@ -415,26 +415,26 @@ static int xilinx_spi_probe(struct platform_device *pdev)
 
 	if (!num_cs) {
 		dev_err(&pdev->dev,
-			"Missing slave select configuration data\n");
+			"Missing target select configuration data\n");
 		return -EINVAL;
 	}
 
 	if (num_cs > XILINX_SPI_MAX_CS) {
-		dev_err(&pdev->dev, "Invalid number of spi slaves\n");
+		dev_err(&pdev->dev, "Invalid number of spi targets\n");
 		return -EINVAL;
 	}
 
-	master = devm_spi_alloc_master(&pdev->dev, sizeof(struct xilinx_spi));
-	if (!master)
+	host = devm_spi_alloc_host(&pdev->dev, sizeof(struct xilinx_spi));
+	if (!host)
 		return -ENODEV;
 
 	/* the spi->mode bits understood by this driver: */
-	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST | SPI_LOOP |
-			    SPI_CS_HIGH;
+	host->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST | SPI_LOOP |
+			  SPI_CS_HIGH;
 
-	xspi = spi_master_get_devdata(master);
+	xspi = spi_controller_get_devdata(host);
 	xspi->cs_inactive = 0xffffffff;
-	xspi->bitbang.master = master;
+	xspi->bitbang.master = host;
 	xspi->bitbang.chipselect = xilinx_spi_chipselect;
 	xspi->bitbang.setup_transfer = xilinx_spi_setup_transfer;
 	xspi->bitbang.txrx_bufs = xilinx_spi_txrx_bufs;
@@ -444,9 +444,9 @@ static int xilinx_spi_probe(struct platform_device *pdev)
 	if (IS_ERR(xspi->regs))
 		return PTR_ERR(xspi->regs);
 
-	master->bus_num = pdev->id;
-	master->num_chipselect = num_cs;
-	master->dev.of_node = pdev->dev.of_node;
+	host->bus_num = pdev->id;
+	host->num_chipselect = num_cs;
+	host->dev.of_node = pdev->dev.of_node;
 
 	/*
 	 * Detect endianess on the IP via loop bit in CR. Detection
@@ -466,7 +466,7 @@ static int xilinx_spi_probe(struct platform_device *pdev)
 		xspi->write_fn = xspi_write32_be;
 	}
 
-	master->bits_per_word_mask = SPI_BPW_MASK(bits_per_word);
+	host->bits_per_word_mask = SPI_BPW_MASK(bits_per_word);
 	xspi->bytes_per_word = bits_per_word / 8;
 	xspi->buffer_size = xilinx_spi_find_buffer_size(xspi);
 
@@ -496,17 +496,17 @@ static int xilinx_spi_probe(struct platform_device *pdev)
 
 	if (pdata) {
 		for (i = 0; i < pdata->num_devices; i++)
-			spi_new_device(master, pdata->devices + i);
+			spi_new_device(host, pdata->devices + i);
 	}
 
-	platform_set_drvdata(pdev, master);
+	platform_set_drvdata(pdev, host);
 	return 0;
 }
 
 static void xilinx_spi_remove(struct platform_device *pdev)
 {
-	struct spi_master *master = platform_get_drvdata(pdev);
-	struct xilinx_spi *xspi = spi_master_get_devdata(master);
+	struct spi_controller *host = platform_get_drvdata(pdev);
+	struct xilinx_spi *xspi = spi_controller_get_devdata(host);
 	void __iomem *regs_base = xspi->regs;
 
 	spi_bitbang_stop(&xspi->bitbang);
@@ -516,7 +516,7 @@ static void xilinx_spi_remove(struct platform_device *pdev)
 	/* Disable the global IPIF interrupt */
 	xspi->write_fn(0, regs_base + XIPIF_V123B_DGIER_OFFSET);
 
-	spi_master_put(xspi->bitbang.master);
+	spi_controller_put(xspi->bitbang.master);
 }
 
 /* work with hotplug and coldplug */
diff --git a/drivers/spi/spi-xlp.c b/drivers/spi/spi-xlp.c
index 3b91cdd5ae21..49302364b7bd 100644
--- a/drivers/spi/spi-xlp.c
+++ b/drivers/spi/spi-xlp.c
@@ -95,7 +95,7 @@ struct xlp_spi_priv {
 	int			rx_len;		/* rx xfer length */
 	int			txerrors;	/* TXFIFO underflow count */
 	int			rxerrors;	/* RXFIFO overflow count */
-	int			cs;		/* slave device chip select */
+	int			cs;		/* target device chip select */
 	u32			spi_clk;	/* spi clock frequency */
 	bool			cmd_cont;	/* cs active */
 	struct completion	done;		/* completion notification */
@@ -138,7 +138,7 @@ static int xlp_spi_setup(struct spi_device *spi)
 	u32 fdiv, cfg;
 	int cs;
 
-	xspi = spi_master_get_devdata(spi->master);
+	xspi = spi_controller_get_devdata(spi->controller);
 	cs = spi_get_chipselect(spi, 0);
 	/*
 	 * The value of fdiv must be between 4 and 65535.
@@ -343,17 +343,17 @@ static int xlp_spi_txrx_bufs(struct xlp_spi_priv *xs, struct spi_transfer *t)
 	return bytesleft;
 }
 
-static int xlp_spi_transfer_one(struct spi_master *master,
+static int xlp_spi_transfer_one(struct spi_controller *host,
 					struct spi_device *spi,
 					struct spi_transfer *t)
 {
-	struct xlp_spi_priv *xspi = spi_master_get_devdata(master);
+	struct xlp_spi_priv *xspi = spi_controller_get_devdata(host);
 	int ret = 0;
 
 	xspi->cs = spi_get_chipselect(spi, 0);
 	xspi->dev = spi->dev;
 
-	if (spi_transfer_is_last(master, t))
+	if (spi_transfer_is_last(host, t))
 		xspi->cmd_cont = 0;
 	else
 		xspi->cmd_cont = 1;
@@ -361,13 +361,13 @@ static int xlp_spi_transfer_one(struct spi_master *master,
 	if (xlp_spi_txrx_bufs(xspi, t))
 		ret = -EIO;
 
-	spi_finalize_current_transfer(master);
+	spi_finalize_current_transfer(host);
 	return ret;
 }
 
 static int xlp_spi_probe(struct platform_device *pdev)
 {
-	struct spi_master *master;
+	struct spi_controller *host;
 	struct xlp_spi_priv *xspi;
 	struct clk *clk;
 	int irq, err;
@@ -398,28 +398,28 @@ static int xlp_spi_probe(struct platform_device *pdev)
 
 	xspi->spi_clk = clk_get_rate(clk);
 
-	master = spi_alloc_master(&pdev->dev, 0);
-	if (!master) {
-		dev_err(&pdev->dev, "could not alloc master\n");
+	host = spi_alloc_host(&pdev->dev, 0);
+	if (!host) {
+		dev_err(&pdev->dev, "could not alloc host\n");
 		return -ENOMEM;
 	}
 
-	master->bus_num = 0;
-	master->num_chipselect = XLP_SPI_MAX_CS;
-	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
-	master->setup = xlp_spi_setup;
-	master->transfer_one = xlp_spi_transfer_one;
-	master->dev.of_node = pdev->dev.of_node;
+	host->bus_num = 0;
+	host->num_chipselect = XLP_SPI_MAX_CS;
+	host->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
+	host->setup = xlp_spi_setup;
+	host->transfer_one = xlp_spi_transfer_one;
+	host->dev.of_node = pdev->dev.of_node;
 
 	init_completion(&xspi->done);
-	spi_master_set_devdata(master, xspi);
+	spi_controller_set_devdata(host, xspi);
 	xlp_spi_sysctl_setup(xspi);
 
 	/* register spi controller */
-	err = devm_spi_register_master(&pdev->dev, master);
+	err = devm_spi_register_controller(&pdev->dev, host);
 	if (err) {
-		dev_err(&pdev->dev, "spi register master failed!\n");
-		spi_master_put(master);
+		dev_err(&pdev->dev, "spi register host failed!\n");
+		spi_controller_put(host);
 		return err;
 	}
 
diff --git a/drivers/spi/spi-xtensa-xtfpga.c b/drivers/spi/spi-xtensa-xtfpga.c
index dbd85d7a1526..3c7721894376 100644
--- a/drivers/spi/spi-xtensa-xtfpga.c
+++ b/drivers/spi/spi-xtensa-xtfpga.c
@@ -53,7 +53,7 @@ static inline void xtfpga_spi_wait_busy(struct xtfpga_spi *xspi)
 static u32 xtfpga_spi_txrx_word(struct spi_device *spi, unsigned nsecs,
 				u32 v, u8 bits, unsigned flags)
 {
-	struct xtfpga_spi *xspi = spi_master_get_devdata(spi->master);
+	struct xtfpga_spi *xspi = spi_controller_get_devdata(spi->controller);
 
 	xspi->data = (xspi->data << bits) | (v & GENMASK(bits - 1, 0));
 	xspi->data_sz += bits;
@@ -71,7 +71,7 @@ static u32 xtfpga_spi_txrx_word(struct spi_device *spi, unsigned nsecs,
 
 static void xtfpga_spi_chipselect(struct spi_device *spi, int is_on)
 {
-	struct xtfpga_spi *xspi = spi_master_get_devdata(spi->master);
+	struct xtfpga_spi *xspi = spi_controller_get_devdata(spi->controller);
 
 	WARN_ON(xspi->data_sz != 0);
 	xspi->data_sz = 0;
@@ -81,19 +81,19 @@ static int xtfpga_spi_probe(struct platform_device *pdev)
 {
 	struct xtfpga_spi *xspi;
 	int ret;
-	struct spi_master *master;
+	struct spi_controller *host;
 
-	master = devm_spi_alloc_master(&pdev->dev, sizeof(struct xtfpga_spi));
-	if (!master)
+	host = devm_spi_alloc_host(&pdev->dev, sizeof(struct xtfpga_spi));
+	if (!host)
 		return -ENOMEM;
 
-	master->flags = SPI_CONTROLLER_NO_RX;
-	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 16);
-	master->bus_num = pdev->dev.id;
-	master->dev.of_node = pdev->dev.of_node;
+	host->flags = SPI_CONTROLLER_NO_RX;
+	host->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 16);
+	host->bus_num = pdev->dev.id;
+	host->dev.of_node = pdev->dev.of_node;
 
-	xspi = spi_master_get_devdata(master);
-	xspi->bitbang.master = master;
+	xspi = spi_controller_get_devdata(host);
+	xspi->bitbang.master = host;
 	xspi->bitbang.chipselect = xtfpga_spi_chipselect;
 	xspi->bitbang.txrx_word[SPI_MODE_0] = xtfpga_spi_txrx_word;
 	xspi->regs = devm_platform_ioremap_resource(pdev, 0);
@@ -113,17 +113,17 @@ static int xtfpga_spi_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	platform_set_drvdata(pdev, master);
+	platform_set_drvdata(pdev, host);
 	return 0;
 }
 
 static void xtfpga_spi_remove(struct platform_device *pdev)
 {
-	struct spi_master *master = platform_get_drvdata(pdev);
-	struct xtfpga_spi *xspi = spi_master_get_devdata(master);
+	struct spi_controller *host = platform_get_drvdata(pdev);
+	struct xtfpga_spi *xspi = spi_controller_get_devdata(host);
 
 	spi_bitbang_stop(&xspi->bitbang);
-	spi_master_put(master);
+	spi_controller_put(host);
 }
 
 MODULE_ALIAS("platform:" XTFPGA_SPI_NAME);
diff --git a/drivers/spi/spi-zynq-qspi.c b/drivers/spi/spi-zynq-qspi.c
index 0db69a2a72ff..d6325c6be3d4 100644
--- a/drivers/spi/spi-zynq-qspi.c
+++ b/drivers/spi/spi-zynq-qspi.c
@@ -54,10 +54,10 @@
 #define ZYNQ_QSPI_CONFIG_MSTREN_MASK	BIT(0) /* Master Mode */
 
 /*
- * QSPI Configuration Register - Baud rate and slave select
+ * QSPI Configuration Register - Baud rate and target select
  *
  * These are the values used in the calculation of baud rate divisor and
- * setting the slave select.
+ * setting the target select.
  */
 #define ZYNQ_QSPI_CONFIG_BAUD_DIV_MAX	GENMASK(2, 0) /* Baud rate maximum */
 #define ZYNQ_QSPI_CONFIG_BAUD_DIV_SHIFT	3 /* Baud rate divisor shift */
@@ -164,14 +164,14 @@ static inline void zynq_qspi_write(struct zynq_qspi *xqspi, u32 offset,
  *
  * The default settings of the QSPI controller's configurable parameters on
  * reset are
- *	- Master mode
+ *	- Host mode
  *	- Baud rate divisor is set to 2
  *	- Tx threshold set to 1l Rx threshold set to 32
  *	- Flash memory interface mode enabled
  *	- Size of the word to be transferred as 8 bit
  * This function performs the following actions
  *	- Disable and clear all the interrupts
- *	- Enable manual slave select
+ *	- Enable manual target select
  *	- Enable manual start
  *	- Deselect all the chip select lines
  *	- Set the size of the word to be transferred as 32 bit
@@ -289,7 +289,7 @@ static void zynq_qspi_txfifo_op(struct zynq_qspi *xqspi, unsigned int size)
  */
 static void zynq_qspi_chipselect(struct spi_device *spi, bool assert)
 {
-	struct spi_controller *ctlr = spi->master;
+	struct spi_controller *ctlr = spi->controller;
 	struct zynq_qspi *xqspi = spi_controller_get_devdata(ctlr);
 	u32 config_reg;
 
@@ -377,7 +377,7 @@ static int zynq_qspi_config_op(struct zynq_qspi *xqspi, struct spi_device *spi)
  */
 static int zynq_qspi_setup_op(struct spi_device *spi)
 {
-	struct spi_controller *ctlr = spi->master;
+	struct spi_controller *ctlr = spi->controller;
 	struct zynq_qspi *qspi = spi_controller_get_devdata(ctlr);
 
 	if (ctlr->busy)
@@ -525,7 +525,7 @@ static irqreturn_t zynq_qspi_irq(int irq, void *dev_id)
 static int zynq_qspi_exec_mem_op(struct spi_mem *mem,
 				 const struct spi_mem_op *op)
 {
-	struct zynq_qspi *xqspi = spi_controller_get_devdata(mem->spi->master);
+	struct zynq_qspi *xqspi = spi_controller_get_devdata(mem->spi->controller);
 	int err = 0, i;
 	u8 *tmpbuf;
 
@@ -637,7 +637,7 @@ static int zynq_qspi_probe(struct platform_device *pdev)
 	struct zynq_qspi *xqspi;
 	u32 num_cs;
 
-	ctlr = spi_alloc_master(&pdev->dev, sizeof(*xqspi));
+	ctlr = spi_alloc_host(&pdev->dev, sizeof(*xqspi));
 	if (!ctlr)
 		return -ENOMEM;
 
@@ -647,14 +647,14 @@ static int zynq_qspi_probe(struct platform_device *pdev)
 	xqspi->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(xqspi->regs)) {
 		ret = PTR_ERR(xqspi->regs);
-		goto remove_master;
+		goto remove_ctlr;
 	}
 
 	xqspi->pclk = devm_clk_get(&pdev->dev, "pclk");
 	if (IS_ERR(xqspi->pclk)) {
 		dev_err(&pdev->dev, "pclk clock not found.\n");
 		ret = PTR_ERR(xqspi->pclk);
-		goto remove_master;
+		goto remove_ctlr;
 	}
 
 	init_completion(&xqspi->data_completion);
@@ -663,13 +663,13 @@ static int zynq_qspi_probe(struct platform_device *pdev)
 	if (IS_ERR(xqspi->refclk)) {
 		dev_err(&pdev->dev, "ref_clk clock not found.\n");
 		ret = PTR_ERR(xqspi->refclk);
-		goto remove_master;
+		goto remove_ctlr;
 	}
 
 	ret = clk_prepare_enable(xqspi->pclk);
 	if (ret) {
 		dev_err(&pdev->dev, "Unable to enable APB clock.\n");
-		goto remove_master;
+		goto remove_ctlr;
 	}
 
 	ret = clk_prepare_enable(xqspi->refclk);
@@ -715,7 +715,7 @@ static int zynq_qspi_probe(struct platform_device *pdev)
 
 	ret = devm_spi_register_controller(&pdev->dev, ctlr);
 	if (ret) {
-		dev_err(&pdev->dev, "spi_register_master failed\n");
+		dev_err(&pdev->dev, "devm_spi_register_controller failed\n");
 		goto clk_dis_all;
 	}
 
@@ -725,7 +725,7 @@ clk_dis_all:
 	clk_disable_unprepare(xqspi->refclk);
 clk_dis_pclk:
 	clk_disable_unprepare(xqspi->pclk);
-remove_master:
+remove_ctlr:
 	spi_controller_put(ctlr);
 
 	return ret;
diff --git a/drivers/spi/spi-zynqmp-gqspi.c b/drivers/spi/spi-zynqmp-gqspi.c
index 9a46b2478f4e..99524a3c9f38 100644
--- a/drivers/spi/spi-zynqmp-gqspi.c
+++ b/drivers/spi/spi-zynqmp-gqspi.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Xilinx Zynq UltraScale+ MPSoC Quad-SPI (QSPI) controller driver
- * (master mode only)
+ * (host mode only)
  *
  * Copyright (C) 2009 - 2015 Xilinx, Inc.
  */
@@ -235,21 +235,21 @@ static inline void zynqmp_gqspi_write(struct zynqmp_qspi *xqspi, u32 offset,
 }
 
 /**
- * zynqmp_gqspi_selectslave - For selection of slave device
+ * zynqmp_gqspi_selecttarget - For selection of target device
  * @instanceptr:	Pointer to the zynqmp_qspi structure
- * @slavecs:	For chip select
- * @slavebus:	To check which bus is selected- upper or lower
+ * @targetcs:	For chip select
+ * @targetbus:	To check which bus is selected- upper or lower
  */
-static void zynqmp_gqspi_selectslave(struct zynqmp_qspi *instanceptr,
-				     u8 slavecs, u8 slavebus)
+static void zynqmp_gqspi_selecttarget(struct zynqmp_qspi *instanceptr,
+				      u8 targetcs, u8 targetbus)
 {
 	/*
 	 * Bus and CS lines selected here will be updated in the instance and
 	 * used for subsequent GENFIFO entries during transfer.
 	 */
 
-	/* Choose slave select line */
-	switch (slavecs) {
+	/* Choose target select line */
+	switch (targetcs) {
 	case GQSPI_SELECT_FLASH_CS_BOTH:
 		instanceptr->genfifocs = GQSPI_GENFIFO_CS_LOWER |
 			GQSPI_GENFIFO_CS_UPPER;
@@ -261,11 +261,11 @@ static void zynqmp_gqspi_selectslave(struct zynqmp_qspi *instanceptr,
 		instanceptr->genfifocs = GQSPI_GENFIFO_CS_LOWER;
 		break;
 	default:
-		dev_warn(instanceptr->dev, "Invalid slave select\n");
+		dev_warn(instanceptr->dev, "Invalid target select\n");
 	}
 
 	/* Choose the bus */
-	switch (slavebus) {
+	switch (targetbus) {
 	case GQSPI_SELECT_FLASH_BUS_BOTH:
 		instanceptr->genfifobus = GQSPI_GENFIFO_BUS_LOWER |
 			GQSPI_GENFIFO_BUS_UPPER;
@@ -277,7 +277,7 @@ static void zynqmp_gqspi_selectslave(struct zynqmp_qspi *instanceptr,
 		instanceptr->genfifobus = GQSPI_GENFIFO_BUS_LOWER;
 		break;
 	default:
-		dev_warn(instanceptr->dev, "Invalid slave bus\n");
+		dev_warn(instanceptr->dev, "Invalid target bus\n");
 	}
 }
 
@@ -337,13 +337,13 @@ static void zynqmp_qspi_set_tapdelay(struct zynqmp_qspi *xqspi, u32 baudrateval)
  *
  * The default settings of the QSPI controller's configurable parameters on
  * reset are
- *	- Master mode
+ *	- Host mode
  *	- TX threshold set to 1
  *	- RX threshold set to 1
  *	- Flash memory interface mode enabled
  * This function performs the following actions
  *	- Disable and clear all the interrupts
- *	- Enable manual slave select
+ *	- Enable manual target select
  *	- Enable manual start
  *	- Deselect all the chip select lines
  *	- Set the little endian mode of TX FIFO
@@ -426,9 +426,9 @@ static void zynqmp_qspi_init_hw(struct zynqmp_qspi *xqspi)
 			   GQSPI_RX_FIFO_THRESHOLD);
 	zynqmp_gqspi_write(xqspi, GQSPI_GF_THRESHOLD_OFST,
 			   GQSPI_GEN_FIFO_THRESHOLD_RESET_VAL);
-	zynqmp_gqspi_selectslave(xqspi,
-				 GQSPI_SELECT_FLASH_CS_LOWER,
-				 GQSPI_SELECT_FLASH_BUS_LOWER);
+	zynqmp_gqspi_selecttarget(xqspi,
+				  GQSPI_SELECT_FLASH_CS_LOWER,
+				  GQSPI_SELECT_FLASH_BUS_LOWER);
 	/* Initialize DMA */
 	zynqmp_gqspi_write(xqspi,
 			   GQSPI_QSPIDMA_DST_CTRL_OFST,
@@ -459,7 +459,7 @@ static void zynqmp_qspi_copy_read_data(struct zynqmp_qspi *xqspi,
  */
 static void zynqmp_qspi_chipselect(struct spi_device *qspi, bool is_high)
 {
-	struct zynqmp_qspi *xqspi = spi_master_get_devdata(qspi->master);
+	struct zynqmp_qspi *xqspi = spi_controller_get_devdata(qspi->controller);
 	ulong timeout;
 	u32 genfifoentry = 0, statusreg;
 
@@ -594,7 +594,7 @@ static int zynqmp_qspi_config_op(struct zynqmp_qspi *xqspi,
  */
 static int zynqmp_qspi_setup_op(struct spi_device *qspi)
 {
-	struct spi_controller *ctlr = qspi->master;
+	struct spi_controller *ctlr = qspi->controller;
 	struct zynqmp_qspi *xqspi = spi_controller_get_devdata(ctlr);
 
 	if (ctlr->busy)
@@ -1048,7 +1048,7 @@ static int zynqmp_qspi_exec_op(struct spi_mem *mem,
 			       const struct spi_mem_op *op)
 {
 	struct zynqmp_qspi *xqspi = spi_controller_get_devdata
-				    (mem->spi->master);
+				    (mem->spi->controller);
 	int err = 0, i;
 	u32 genfifoentry = 0;
 	u16 opcode = op->cmd.opcode;
@@ -1224,7 +1224,7 @@ static int zynqmp_qspi_probe(struct platform_device *pdev)
 	u32 num_cs;
 	const struct qspi_platform_data *p_data;
 
-	ctlr = spi_alloc_master(&pdev->dev, sizeof(*xqspi));
+	ctlr = spi_alloc_host(&pdev->dev, sizeof(*xqspi));
 	if (!ctlr)
 		return -ENOMEM;
 
@@ -1240,27 +1240,27 @@ static int zynqmp_qspi_probe(struct platform_device *pdev)
 	xqspi->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(xqspi->regs)) {
 		ret = PTR_ERR(xqspi->regs);
-		goto remove_master;
+		goto remove_ctlr;
 	}
 
 	xqspi->pclk = devm_clk_get(&pdev->dev, "pclk");
 	if (IS_ERR(xqspi->pclk)) {
 		dev_err(dev, "pclk clock not found.\n");
 		ret = PTR_ERR(xqspi->pclk);
-		goto remove_master;
+		goto remove_ctlr;
 	}
 
 	xqspi->refclk = devm_clk_get(&pdev->dev, "ref_clk");
 	if (IS_ERR(xqspi->refclk)) {
 		dev_err(dev, "ref_clk clock not found.\n");
 		ret = PTR_ERR(xqspi->refclk);
-		goto remove_master;
+		goto remove_ctlr;
 	}
 
 	ret = clk_prepare_enable(xqspi->pclk);
 	if (ret) {
 		dev_err(dev, "Unable to enable APB clock.\n");
-		goto remove_master;
+		goto remove_ctlr;
 	}
 
 	ret = clk_prepare_enable(xqspi->refclk);
@@ -1346,7 +1346,7 @@ clk_dis_all:
 	clk_disable_unprepare(xqspi->refclk);
 clk_dis_pclk:
 	clk_disable_unprepare(xqspi->pclk);
-remove_master:
+remove_ctlr:
 	spi_controller_put(ctlr);
 
 	return ret;
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 8ead7acb99f3..7477a11e12be 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -612,10 +612,21 @@ static int spi_dev_check(struct device *dev, void *data)
 {
 	struct spi_device *spi = to_spi_device(dev);
 	struct spi_device *new_spi = data;
-
-	if (spi->controller == new_spi->controller &&
-	    spi_get_chipselect(spi, 0) == spi_get_chipselect(new_spi, 0))
-		return -EBUSY;
+	int idx, nw_idx;
+	u8 cs, cs_nw;
+
+	if (spi->controller == new_spi->controller) {
+		for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) {
+			cs = spi_get_chipselect(spi, idx);
+			for (nw_idx = 0; nw_idx < SPI_CS_CNT_MAX; nw_idx++) {
+				cs_nw = spi_get_chipselect(new_spi, nw_idx);
+				if (cs != 0xFF && cs_nw != 0xFF && cs == cs_nw) {
+					dev_err(dev, "chipselect %d already in use\n", cs_nw);
+					return -EBUSY;
+				}
+			}
+		}
+	}
 	return 0;
 }
 
@@ -629,13 +640,32 @@ static int __spi_add_device(struct spi_device *spi)
 {
 	struct spi_controller *ctlr = spi->controller;
 	struct device *dev = ctlr->dev.parent;
-	int status;
+	int status, idx, nw_idx;
+	u8 cs, nw_cs;
+
+	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) {
+		/* Chipselects are numbered 0..max; validate. */
+		cs = spi_get_chipselect(spi, idx);
+		if (cs != 0xFF && cs >= ctlr->num_chipselect) {
+			dev_err(dev, "cs%d >= max %d\n", spi_get_chipselect(spi, idx),
+				ctlr->num_chipselect);
+			return -EINVAL;
+		}
+	}
 
-	/* Chipselects are numbered 0..max; validate. */
-	if (spi_get_chipselect(spi, 0) >= ctlr->num_chipselect) {
-		dev_err(dev, "cs%d >= max %d\n", spi_get_chipselect(spi, 0),
-			ctlr->num_chipselect);
-		return -EINVAL;
+	/*
+	 * Make sure that multiple logical CS doesn't map to the same physical CS.
+	 * For example, spi->chip_select[0] != spi->chip_select[1] and so on.
+	 */
+	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) {
+		cs = spi_get_chipselect(spi, idx);
+		for (nw_idx = idx + 1; nw_idx < SPI_CS_CNT_MAX; nw_idx++) {
+			nw_cs = spi_get_chipselect(spi, nw_idx);
+			if (cs != 0xFF && nw_cs != 0xFF && cs == nw_cs) {
+				dev_err(dev, "chipselect %d already in use\n", nw_cs);
+				return -EBUSY;
+			}
+		}
 	}
 
 	/* Set the bus ID string */
@@ -647,11 +677,8 @@ static int __spi_add_device(struct spi_device *spi)
 	 * its configuration.
 	 */
 	status = bus_for_each_dev(&spi_bus_type, NULL, spi, spi_dev_check);
-	if (status) {
-		dev_err(dev, "chipselect %d already in use\n",
-				spi_get_chipselect(spi, 0));
+	if (status)
 		return status;
-	}
 
 	/* Controller may unregister concurrently */
 	if (IS_ENABLED(CONFIG_SPI_DYNAMIC) &&
@@ -659,8 +686,15 @@ static int __spi_add_device(struct spi_device *spi)
 		return -ENODEV;
 	}
 
-	if (ctlr->cs_gpiods)
-		spi_set_csgpiod(spi, 0, ctlr->cs_gpiods[spi_get_chipselect(spi, 0)]);
+	if (ctlr->cs_gpiods) {
+		u8 cs;
+
+		for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) {
+			cs = spi_get_chipselect(spi, idx);
+			if (cs != 0xFF)
+				spi_set_csgpiod(spi, idx, ctlr->cs_gpiods[cs]);
+		}
+	}
 
 	/*
 	 * Drivers may modify this initial i/o setup, but will
@@ -701,6 +735,9 @@ int spi_add_device(struct spi_device *spi)
 	struct spi_controller *ctlr = spi->controller;
 	int status;
 
+	/* Set the bus ID string */
+	spi_dev_set_name(spi);
+
 	mutex_lock(&ctlr->add_lock);
 	status = __spi_add_device(spi);
 	mutex_unlock(&ctlr->add_lock);
@@ -727,6 +764,7 @@ struct spi_device *spi_new_device(struct spi_controller *ctlr,
 {
 	struct spi_device	*proxy;
 	int			status;
+	u8                      idx;
 
 	/*
 	 * NOTE:  caller did any chip->bus_num checks necessary.
@@ -742,6 +780,18 @@ struct spi_device *spi_new_device(struct spi_controller *ctlr,
 
 	WARN_ON(strlen(chip->modalias) >= sizeof(proxy->modalias));
 
+	/*
+	 * Zero(0) is a valid physical CS value and can be located at any
+	 * logical CS in the spi->chip_select[]. If all the physical CS
+	 * are initialized to 0 then It would be difficult to differentiate
+	 * between a valid physical CS 0 & an unused logical CS whose physical
+	 * CS can be 0. As a solution to this issue initialize all the CS to 0xFF.
+	 * Now all the unused logical CS will have 0xFF physical CS value & can be
+	 * ignore while performing physical CS validity checks.
+	 */
+	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++)
+		spi_set_chipselect(proxy, idx, 0xFF);
+
 	spi_set_chipselect(proxy, 0, chip->chip_select);
 	proxy->max_speed_hz = chip->max_speed_hz;
 	proxy->mode = chip->mode;
@@ -750,6 +800,15 @@ struct spi_device *spi_new_device(struct spi_controller *ctlr,
 	proxy->dev.platform_data = (void *) chip->platform_data;
 	proxy->controller_data = chip->controller_data;
 	proxy->controller_state = NULL;
+	/*
+	 * spi->chip_select[i] gives the corresponding physical CS for logical CS i
+	 * logical CS number is represented by setting the ith bit in spi->cs_index_mask
+	 * So, for example, if spi->cs_index_mask = 0x01 then logical CS number is 0 and
+	 * spi->chip_select[0] will give the physical CS.
+	 * By default spi->chip_select[0] will hold the physical CS number so, set
+	 * spi->cs_index_mask as 0x01.
+	 */
+	proxy->cs_index_mask = 0x01;
 
 	if (chip->swnode) {
 		status = device_add_software_node(&proxy->dev, chip->swnode);
@@ -942,32 +1001,51 @@ static void spi_res_release(struct spi_controller *ctlr, struct spi_message *mes
 }
 
 /*-------------------------------------------------------------------------*/
+static inline bool spi_is_last_cs(struct spi_device *spi)
+{
+	u8 idx;
+	bool last = false;
+
+	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) {
+		if ((spi->cs_index_mask >> idx) & 0x01) {
+			if (spi->controller->last_cs[idx] == spi_get_chipselect(spi, idx))
+				last = true;
+		}
+	}
+	return last;
+}
+
 
 static void spi_set_cs(struct spi_device *spi, bool enable, bool force)
 {
 	bool activate = enable;
+	u8 idx;
 
 	/*
 	 * Avoid calling into the driver (or doing delays) if the chip select
 	 * isn't actually changing from the last time this was called.
 	 */
-	if (!force && ((enable && spi->controller->last_cs == spi_get_chipselect(spi, 0)) ||
-		       (!enable && spi->controller->last_cs != spi_get_chipselect(spi, 0))) &&
+	if (!force && ((enable && spi->controller->last_cs_index_mask == spi->cs_index_mask &&
+			spi_is_last_cs(spi)) ||
+		       (!enable && spi->controller->last_cs_index_mask == spi->cs_index_mask &&
+			!spi_is_last_cs(spi))) &&
 	    (spi->controller->last_cs_mode_high == (spi->mode & SPI_CS_HIGH)))
 		return;
 
 	trace_spi_set_cs(spi, activate);
 
-	spi->controller->last_cs = enable ? spi_get_chipselect(spi, 0) : -1;
+	spi->controller->last_cs_index_mask = spi->cs_index_mask;
+	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++)
+		spi->controller->last_cs[idx] = enable ? spi_get_chipselect(spi, 0) : -1;
 	spi->controller->last_cs_mode_high = spi->mode & SPI_CS_HIGH;
 
-	if ((spi_get_csgpiod(spi, 0) || !spi->controller->set_cs_timing) && !activate)
-		spi_delay_exec(&spi->cs_hold, NULL);
-
 	if (spi->mode & SPI_CS_HIGH)
 		enable = !enable;
 
-	if (spi_get_csgpiod(spi, 0)) {
+	if (spi_is_csgpiod(spi)) {
+		if (!spi->controller->set_cs_timing && !activate)
+			spi_delay_exec(&spi->cs_hold, NULL);
+
 		if (!(spi->mode & SPI_NO_CS)) {
 			/*
 			 * Historically ACPI has no means of the GPIO polarity and
@@ -979,26 +1057,38 @@ static void spi_set_cs(struct spi_device *spi, bool enable, bool force)
 			 * ambiguity. That's why we use enable, that takes SPI_CS_HIGH
 			 * into account.
 			 */
-			if (has_acpi_companion(&spi->dev))
-				gpiod_set_value_cansleep(spi_get_csgpiod(spi, 0), !enable);
-			else
-				/* Polarity handled by GPIO library */
-				gpiod_set_value_cansleep(spi_get_csgpiod(spi, 0), activate);
+			for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) {
+				if (((spi->cs_index_mask >> idx) & 0x01) &&
+				    spi_get_csgpiod(spi, idx)) {
+					if (has_acpi_companion(&spi->dev))
+						gpiod_set_value_cansleep(spi_get_csgpiod(spi, idx),
+									 !enable);
+					else
+						/* Polarity handled by GPIO library */
+						gpiod_set_value_cansleep(spi_get_csgpiod(spi, idx),
+									 activate);
+
+					if (activate)
+						spi_delay_exec(&spi->cs_setup, NULL);
+					else
+						spi_delay_exec(&spi->cs_inactive, NULL);
+				}
+			}
 		}
 		/* Some SPI masters need both GPIO CS & slave_select */
 		if ((spi->controller->flags & SPI_CONTROLLER_GPIO_SS) &&
 		    spi->controller->set_cs)
 			spi->controller->set_cs(spi, !enable);
+
+		if (!spi->controller->set_cs_timing) {
+			if (activate)
+				spi_delay_exec(&spi->cs_setup, NULL);
+			else
+				spi_delay_exec(&spi->cs_inactive, NULL);
+		}
 	} else if (spi->controller->set_cs) {
 		spi->controller->set_cs(spi, !enable);
 	}
-
-	if (spi_get_csgpiod(spi, 0) || !spi->controller->set_cs_timing) {
-		if (activate)
-			spi_delay_exec(&spi->cs_setup, NULL);
-		else
-			spi_delay_exec(&spi->cs_inactive, NULL);
-	}
 }
 
 #ifdef CONFIG_HAS_DMA
@@ -1361,6 +1451,9 @@ static int spi_transfer_wait(struct spi_controller *ctlr,
 				"SPI transfer timed out\n");
 			return -ETIMEDOUT;
 		}
+
+		if (xfer->error & SPI_TRANS_FAIL_IO)
+			return -EIO;
 	}
 
 	return 0;
@@ -2222,8 +2315,8 @@ static void of_spi_parse_dt_cs_delay(struct device_node *nc,
 static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi,
 			   struct device_node *nc)
 {
-	u32 value;
-	int rc;
+	u32 value, cs[SPI_CS_CNT_MAX];
+	int rc, idx;
 
 	/* Mode (clock phase/polarity/etc.) */
 	if (of_property_read_bool(nc, "spi-cpha"))
@@ -2295,14 +2388,53 @@ static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi,
 		return 0;
 	}
 
+	if (ctlr->num_chipselect > SPI_CS_CNT_MAX) {
+		dev_err(&ctlr->dev, "No. of CS is more than max. no. of supported CS\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Zero(0) is a valid physical CS value and can be located at any
+	 * logical CS in the spi->chip_select[]. If all the physical CS
+	 * are initialized to 0 then It would be difficult to differentiate
+	 * between a valid physical CS 0 & an unused logical CS whose physical
+	 * CS can be 0. As a solution to this issue initialize all the CS to 0xFF.
+	 * Now all the unused logical CS will have 0xFF physical CS value & can be
+	 * ignore while performing physical CS validity checks.
+	 */
+	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++)
+		spi_set_chipselect(spi, idx, 0xFF);
+
 	/* Device address */
-	rc = of_property_read_u32(nc, "reg", &value);
-	if (rc) {
+	rc = of_property_read_variable_u32_array(nc, "reg", &cs[0], 1,
+						 SPI_CS_CNT_MAX);
+	if (rc < 0) {
 		dev_err(&ctlr->dev, "%pOF has no valid 'reg' property (%d)\n",
 			nc, rc);
 		return rc;
 	}
-	spi_set_chipselect(spi, 0, value);
+	if (rc > ctlr->num_chipselect) {
+		dev_err(&ctlr->dev, "%pOF has number of CS > ctlr->num_chipselect (%d)\n",
+			nc, rc);
+		return rc;
+	}
+	if ((of_property_read_bool(nc, "parallel-memories")) &&
+	    (!(ctlr->flags & SPI_CONTROLLER_MULTI_CS))) {
+		dev_err(&ctlr->dev, "SPI controller doesn't support multi CS\n");
+		return -EINVAL;
+	}
+	for (idx = 0; idx < rc; idx++)
+		spi_set_chipselect(spi, idx, cs[idx]);
+
+	/*
+	 * spi->chip_select[i] gives the corresponding physical CS for logical CS i
+	 * logical CS number is represented by setting the ith bit in spi->cs_index_mask
+	 * So, for example, if spi->cs_index_mask = 0x01 then logical CS number is 0 and
+	 * spi->chip_select[0] will give the physical CS.
+	 * By default spi->chip_select[0] will hold the physical CS number so, set
+	 * spi->cs_index_mask as 0x01.
+	 */
+	spi->cs_index_mask = 0x01;
 
 	/* Device speed */
 	if (!of_property_read_u32(nc, "spi-max-frequency", &value))
@@ -2408,6 +2540,7 @@ struct spi_device *spi_new_ancillary_device(struct spi_device *spi,
 	struct spi_controller *ctlr = spi->controller;
 	struct spi_device *ancillary;
 	int rc = 0;
+	u8 idx;
 
 	/* Alloc an spi_device */
 	ancillary = spi_alloc_device(ctlr);
@@ -2418,12 +2551,33 @@ struct spi_device *spi_new_ancillary_device(struct spi_device *spi,
 
 	strscpy(ancillary->modalias, "dummy", sizeof(ancillary->modalias));
 
+	/*
+	 * Zero(0) is a valid physical CS value and can be located at any
+	 * logical CS in the spi->chip_select[]. If all the physical CS
+	 * are initialized to 0 then It would be difficult to differentiate
+	 * between a valid physical CS 0 & an unused logical CS whose physical
+	 * CS can be 0. As a solution to this issue initialize all the CS to 0xFF.
+	 * Now all the unused logical CS will have 0xFF physical CS value & can be
+	 * ignore while performing physical CS validity checks.
+	 */
+	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++)
+		spi_set_chipselect(ancillary, idx, 0xFF);
+
 	/* Use provided chip-select for ancillary device */
 	spi_set_chipselect(ancillary, 0, chip_select);
 
 	/* Take over SPI mode/speed from SPI main device */
 	ancillary->max_speed_hz = spi->max_speed_hz;
 	ancillary->mode = spi->mode;
+	/*
+	 * spi->chip_select[i] gives the corresponding physical CS for logical CS i
+	 * logical CS number is represented by setting the ith bit in spi->cs_index_mask
+	 * So, for example, if spi->cs_index_mask = 0x01 then logical CS number is 0 and
+	 * spi->chip_select[0] will give the physical CS.
+	 * By default spi->chip_select[0] will hold the physical CS number so, set
+	 * spi->cs_index_mask as 0x01.
+	 */
+	ancillary->cs_index_mask = 0x01;
 
 	WARN_ON(!mutex_is_locked(&ctlr->add_lock));
 
@@ -2626,6 +2780,7 @@ struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr,
 	struct acpi_spi_lookup lookup = {};
 	struct spi_device *spi;
 	int ret;
+	u8 idx;
 
 	if (!ctlr && index == -1)
 		return ERR_PTR(-EINVAL);
@@ -2661,12 +2816,33 @@ struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr,
 		return ERR_PTR(-ENOMEM);
 	}
 
+	/*
+	 * Zero(0) is a valid physical CS value and can be located at any
+	 * logical CS in the spi->chip_select[]. If all the physical CS
+	 * are initialized to 0 then It would be difficult to differentiate
+	 * between a valid physical CS 0 & an unused logical CS whose physical
+	 * CS can be 0. As a solution to this issue initialize all the CS to 0xFF.
+	 * Now all the unused logical CS will have 0xFF physical CS value & can be
+	 * ignore while performing physical CS validity checks.
+	 */
+	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++)
+		spi_set_chipselect(spi, idx, 0xFF);
+
 	ACPI_COMPANION_SET(&spi->dev, adev);
 	spi->max_speed_hz	= lookup.max_speed_hz;
 	spi->mode		|= lookup.mode;
 	spi->irq		= lookup.irq;
 	spi->bits_per_word	= lookup.bits_per_word;
 	spi_set_chipselect(spi, 0, lookup.chip_select);
+	/*
+	 * spi->chip_select[i] gives the corresponding physical CS for logical CS i
+	 * logical CS number is represented by setting the ith bit in spi->cs_index_mask
+	 * So, for example, if spi->cs_index_mask = 0x01 then logical CS number is 0 and
+	 * spi->chip_select[0] will give the physical CS.
+	 * By default spi->chip_select[0] will hold the physical CS number so, set
+	 * spi->cs_index_mask as 0x01.
+	 */
+	spi->cs_index_mask	= 0x01;
 
 	return spi;
 }
@@ -3100,6 +3276,7 @@ int spi_register_controller(struct spi_controller *ctlr)
 	struct boardinfo	*bi;
 	int			first_dynamic;
 	int			status;
+	int			idx;
 
 	if (!dev)
 		return -ENODEV;
@@ -3164,7 +3341,8 @@ int spi_register_controller(struct spi_controller *ctlr)
 	}
 
 	/* Setting last_cs to -1 means no chip selected */
-	ctlr->last_cs = -1;
+	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++)
+		ctlr->last_cs[idx] = -1;
 
 	status = device_add(&ctlr->dev);
 	if (status < 0)
@@ -3889,7 +4067,7 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message)
 	 * cs_change is set for each transfer.
 	 */
 	if ((spi->mode & SPI_CS_WORD) && (!(ctlr->mode_bits & SPI_CS_WORD) ||
-					  spi_get_csgpiod(spi, 0))) {
+					  spi_is_csgpiod(spi))) {
 		size_t maxsize = BITS_TO_BYTES(spi->bits_per_word);
 		int ret;
 
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 49d9167bb263..80b7d85030d0 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -470,6 +470,7 @@ static int core_scsi3_pr_seq_non_holder(struct se_cmd *cmd, u32 pr_reg_type,
 	case INQUIRY:
 	case LOG_SENSE:
 	case SERVICE_ACTION_IN_12:
+	case READ_CAPACITY:
 	case REPORT_LUNS:
 	case REQUEST_SENSE:
 	case PERSISTENT_RESERVE_IN:
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index 91ed015b588c..4128631c9dfd 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -15,6 +15,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/list.h>
+#include <linux/rculist.h>
 #include <linux/configfs.h>
 #include <linux/ratelimit.h>
 #include <scsi/scsi_proto.h>
diff --git a/drivers/tee/optee/call.c b/drivers/tee/optee/call.c
index df5fb5410b72..a91e50be11be 100644
--- a/drivers/tee/optee/call.c
+++ b/drivers/tee/optee/call.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (c) 2015-2021, Linaro Limited
+ * Copyright (c) 2015-2021, 2023 Linaro Limited
  */
 #include <linux/device.h>
 #include <linux/err.h>
@@ -39,9 +39,29 @@ struct optee_shm_arg_entry {
 	DECLARE_BITMAP(map, MAX_ARG_COUNT_PER_ENTRY);
 };
 
+void optee_cq_init(struct optee_call_queue *cq, int thread_count)
+{
+	mutex_init(&cq->mutex);
+	INIT_LIST_HEAD(&cq->waiters);
+
+	/*
+	 * If cq->total_thread_count is 0 then we're not trying to keep
+	 * track of how many free threads we have, instead we're relying on
+	 * the secure world to tell us when we're out of thread and have to
+	 * wait for another thread to become available.
+	 */
+	cq->total_thread_count = thread_count;
+	cq->free_thread_count = thread_count;
+}
+
 void optee_cq_wait_init(struct optee_call_queue *cq,
-			struct optee_call_waiter *w)
+			struct optee_call_waiter *w, bool sys_thread)
 {
+	unsigned int free_thread_threshold;
+	bool need_wait = false;
+
+	memset(w, 0, sizeof(*w));
+
 	/*
 	 * We're preparing to make a call to secure world. In case we can't
 	 * allocate a thread in secure world we'll end up waiting in
@@ -60,8 +80,38 @@ void optee_cq_wait_init(struct optee_call_queue *cq,
 	 */
 	init_completion(&w->c);
 	list_add_tail(&w->list_node, &cq->waiters);
+	w->sys_thread = sys_thread;
+
+	if (cq->total_thread_count) {
+		if (sys_thread || !cq->sys_thread_req_count)
+			free_thread_threshold = 0;
+		else
+			free_thread_threshold = 1;
+
+		if (cq->free_thread_count > free_thread_threshold)
+			cq->free_thread_count--;
+		else
+			need_wait = true;
+	}
 
 	mutex_unlock(&cq->mutex);
+
+	while (need_wait) {
+		optee_cq_wait_for_completion(cq, w);
+		mutex_lock(&cq->mutex);
+
+		if (sys_thread || !cq->sys_thread_req_count)
+			free_thread_threshold = 0;
+		else
+			free_thread_threshold = 1;
+
+		if (cq->free_thread_count > free_thread_threshold) {
+			cq->free_thread_count--;
+			need_wait = false;
+		}
+
+		mutex_unlock(&cq->mutex);
+	}
 }
 
 void optee_cq_wait_for_completion(struct optee_call_queue *cq,
@@ -83,6 +133,14 @@ static void optee_cq_complete_one(struct optee_call_queue *cq)
 {
 	struct optee_call_waiter *w;
 
+	/* Wake a waiting system session if any, prior to a normal session */
+	list_for_each_entry(w, &cq->waiters, list_node) {
+		if (w->sys_thread && !completion_done(&w->c)) {
+			complete(&w->c);
+			return;
+		}
+	}
+
 	list_for_each_entry(w, &cq->waiters, list_node) {
 		if (!completion_done(&w->c)) {
 			complete(&w->c);
@@ -104,6 +162,8 @@ void optee_cq_wait_final(struct optee_call_queue *cq,
 	/* Get out of the list */
 	list_del(&w->list_node);
 
+	cq->free_thread_count++;
+
 	/* Wake up one eventual waiting task */
 	optee_cq_complete_one(cq);
 
@@ -119,6 +179,28 @@ void optee_cq_wait_final(struct optee_call_queue *cq,
 	mutex_unlock(&cq->mutex);
 }
 
+/* Count registered system sessions to reserved a system thread or not */
+static bool optee_cq_incr_sys_thread_count(struct optee_call_queue *cq)
+{
+	if (cq->total_thread_count <= 1)
+		return false;
+
+	mutex_lock(&cq->mutex);
+	cq->sys_thread_req_count++;
+	mutex_unlock(&cq->mutex);
+
+	return true;
+}
+
+static void optee_cq_decr_sys_thread_count(struct optee_call_queue *cq)
+{
+	mutex_lock(&cq->mutex);
+	cq->sys_thread_req_count--;
+	/* If there's someone waiting, let it resume */
+	optee_cq_complete_one(cq);
+	mutex_unlock(&cq->mutex);
+}
+
 /* Requires the filpstate mutex to be held */
 static struct optee_session *find_session(struct optee_context_data *ctxdata,
 					  u32 session_id)
@@ -328,7 +410,8 @@ int optee_open_session(struct tee_context *ctx,
 		goto out;
 	}
 
-	if (optee->ops->do_call_with_arg(ctx, shm, offs)) {
+	if (optee->ops->do_call_with_arg(ctx, shm, offs,
+					 sess->use_sys_thread)) {
 		msg_arg->ret = TEEC_ERROR_COMMUNICATION;
 		msg_arg->ret_origin = TEEC_ORIGIN_COMMS;
 	}
@@ -360,7 +443,29 @@ out:
 	return rc;
 }
 
-int optee_close_session_helper(struct tee_context *ctx, u32 session)
+int optee_system_session(struct tee_context *ctx, u32 session)
+{
+	struct optee *optee = tee_get_drvdata(ctx->teedev);
+	struct optee_context_data *ctxdata = ctx->data;
+	struct optee_session *sess;
+	int rc = -EINVAL;
+
+	mutex_lock(&ctxdata->mutex);
+
+	sess = find_session(ctxdata, session);
+	if (sess && (sess->use_sys_thread ||
+		     optee_cq_incr_sys_thread_count(&optee->call_queue))) {
+		sess->use_sys_thread = true;
+		rc = 0;
+	}
+
+	mutex_unlock(&ctxdata->mutex);
+
+	return rc;
+}
+
+int optee_close_session_helper(struct tee_context *ctx, u32 session,
+			       bool system_thread)
 {
 	struct optee *optee = tee_get_drvdata(ctx->teedev);
 	struct optee_shm_arg_entry *entry;
@@ -374,10 +479,13 @@ int optee_close_session_helper(struct tee_context *ctx, u32 session)
 
 	msg_arg->cmd = OPTEE_MSG_CMD_CLOSE_SESSION;
 	msg_arg->session = session;
-	optee->ops->do_call_with_arg(ctx, shm, offs);
+	optee->ops->do_call_with_arg(ctx, shm, offs, system_thread);
 
 	optee_free_msg_arg(ctx, entry, offs);
 
+	if (system_thread)
+		optee_cq_decr_sys_thread_count(&optee->call_queue);
+
 	return 0;
 }
 
@@ -385,6 +493,7 @@ int optee_close_session(struct tee_context *ctx, u32 session)
 {
 	struct optee_context_data *ctxdata = ctx->data;
 	struct optee_session *sess;
+	bool system_thread;
 
 	/* Check that the session is valid and remove it from the list */
 	mutex_lock(&ctxdata->mutex);
@@ -394,9 +503,10 @@ int optee_close_session(struct tee_context *ctx, u32 session)
 	mutex_unlock(&ctxdata->mutex);
 	if (!sess)
 		return -EINVAL;
+	system_thread = sess->use_sys_thread;
 	kfree(sess);
 
-	return optee_close_session_helper(ctx, session);
+	return optee_close_session_helper(ctx, session, system_thread);
 }
 
 int optee_invoke_func(struct tee_context *ctx, struct tee_ioctl_invoke_arg *arg,
@@ -408,12 +518,15 @@ int optee_invoke_func(struct tee_context *ctx, struct tee_ioctl_invoke_arg *arg,
 	struct optee_msg_arg *msg_arg;
 	struct optee_session *sess;
 	struct tee_shm *shm;
+	bool system_thread;
 	u_int offs;
 	int rc;
 
 	/* Check that the session is valid */
 	mutex_lock(&ctxdata->mutex);
 	sess = find_session(ctxdata, arg->session);
+	if (sess)
+		system_thread = sess->use_sys_thread;
 	mutex_unlock(&ctxdata->mutex);
 	if (!sess)
 		return -EINVAL;
@@ -432,7 +545,7 @@ int optee_invoke_func(struct tee_context *ctx, struct tee_ioctl_invoke_arg *arg,
 	if (rc)
 		goto out;
 
-	if (optee->ops->do_call_with_arg(ctx, shm, offs)) {
+	if (optee->ops->do_call_with_arg(ctx, shm, offs, system_thread)) {
 		msg_arg->ret = TEEC_ERROR_COMMUNICATION;
 		msg_arg->ret_origin = TEEC_ORIGIN_COMMS;
 	}
@@ -457,12 +570,15 @@ int optee_cancel_req(struct tee_context *ctx, u32 cancel_id, u32 session)
 	struct optee_shm_arg_entry *entry;
 	struct optee_msg_arg *msg_arg;
 	struct optee_session *sess;
+	bool system_thread;
 	struct tee_shm *shm;
 	u_int offs;
 
 	/* Check that the session is valid */
 	mutex_lock(&ctxdata->mutex);
 	sess = find_session(ctxdata, session);
+	if (sess)
+		system_thread = sess->use_sys_thread;
 	mutex_unlock(&ctxdata->mutex);
 	if (!sess)
 		return -EINVAL;
@@ -474,7 +590,7 @@ int optee_cancel_req(struct tee_context *ctx, u32 cancel_id, u32 session)
 	msg_arg->cmd = OPTEE_MSG_CMD_CANCEL;
 	msg_arg->session = session;
 	msg_arg->cancel_id = cancel_id;
-	optee->ops->do_call_with_arg(ctx, shm, offs);
+	optee->ops->do_call_with_arg(ctx, shm, offs, system_thread);
 
 	optee_free_msg_arg(ctx, entry, offs);
 	return 0;
@@ -524,3 +640,32 @@ int optee_check_mem_type(unsigned long start, size_t num_pages)
 
 	return rc;
 }
+
+static int simple_call_with_arg(struct tee_context *ctx, u32 cmd)
+{
+	struct optee *optee = tee_get_drvdata(ctx->teedev);
+	struct optee_shm_arg_entry *entry;
+	struct optee_msg_arg *msg_arg;
+	struct tee_shm *shm;
+	u_int offs;
+
+	msg_arg = optee_get_msg_arg(ctx, 0, &entry, &shm, &offs);
+	if (IS_ERR(msg_arg))
+		return PTR_ERR(msg_arg);
+
+	msg_arg->cmd = cmd;
+	optee->ops->do_call_with_arg(ctx, shm, offs, false);
+
+	optee_free_msg_arg(ctx, entry, offs);
+	return 0;
+}
+
+int optee_do_bottom_half(struct tee_context *ctx)
+{
+	return simple_call_with_arg(ctx, OPTEE_MSG_CMD_DO_BOTTOM_HALF);
+}
+
+int optee_stop_async_notif(struct tee_context *ctx)
+{
+	return simple_call_with_arg(ctx, OPTEE_MSG_CMD_STOP_ASYNC_NOTIF);
+}
diff --git a/drivers/tee/optee/core.c b/drivers/tee/optee/core.c
index 2a258bd3b6b5..3aed554bc8d8 100644
--- a/drivers/tee/optee/core.c
+++ b/drivers/tee/optee/core.c
@@ -15,7 +15,6 @@
 #include <linux/string.h>
 #include <linux/tee_drv.h>
 #include <linux/types.h>
-#include <linux/workqueue.h>
 #include "optee_private.h"
 
 int optee_pool_op_alloc_helper(struct tee_shm_pool *pool, struct tee_shm *shm,
@@ -26,46 +25,46 @@ int optee_pool_op_alloc_helper(struct tee_shm_pool *pool, struct tee_shm *shm,
 						   size_t num_pages,
 						   unsigned long start))
 {
-	unsigned int order = get_order(size);
-	struct page *page;
+	size_t nr_pages = roundup(size, PAGE_SIZE) / PAGE_SIZE;
+	struct page **pages;
+	unsigned int i;
 	int rc = 0;
 
 	/*
 	 * Ignore alignment since this is already going to be page aligned
 	 * and there's no need for any larger alignment.
 	 */
-	page = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
-	if (!page)
+	shm->kaddr = alloc_pages_exact(nr_pages * PAGE_SIZE,
+				       GFP_KERNEL | __GFP_ZERO);
+	if (!shm->kaddr)
 		return -ENOMEM;
 
-	shm->kaddr = page_address(page);
-	shm->paddr = page_to_phys(page);
-	shm->size = PAGE_SIZE << order;
+	shm->paddr = virt_to_phys(shm->kaddr);
+	shm->size = nr_pages * PAGE_SIZE;
 
-	if (shm_register) {
-		unsigned int nr_pages = 1 << order, i;
-		struct page **pages;
+	pages = kcalloc(nr_pages, sizeof(*pages), GFP_KERNEL);
+	if (!pages) {
+		rc = -ENOMEM;
+		goto err;
+	}
 
-		pages = kcalloc(nr_pages, sizeof(*pages), GFP_KERNEL);
-		if (!pages) {
-			rc = -ENOMEM;
-			goto err;
-		}
+	for (i = 0; i < nr_pages; i++)
+		pages[i] = virt_to_page((u8 *)shm->kaddr + i * PAGE_SIZE);
 
-		for (i = 0; i < nr_pages; i++)
-			pages[i] = page + i;
+	shm->pages = pages;
+	shm->num_pages = nr_pages;
 
+	if (shm_register) {
 		rc = shm_register(shm->ctx, shm, pages, nr_pages,
 				  (unsigned long)shm->kaddr);
-		kfree(pages);
 		if (rc)
 			goto err;
 	}
 
 	return 0;
-
 err:
-	free_pages((unsigned long)shm->kaddr, order);
+	free_pages_exact(shm->kaddr, shm->size);
+	shm->kaddr = NULL;
 	return rc;
 }
 
@@ -75,8 +74,10 @@ void optee_pool_op_free_helper(struct tee_shm_pool *pool, struct tee_shm *shm,
 {
 	if (shm_unregister)
 		shm_unregister(shm->ctx, shm);
-	free_pages((unsigned long)shm->kaddr, get_order(shm->size));
+	free_pages_exact(shm->kaddr, shm->size);
 	shm->kaddr = NULL;
+	kfree(shm->pages);
+	shm->pages = NULL;
 }
 
 static void optee_bus_scan(struct work_struct *work)
@@ -110,12 +111,7 @@ int optee_open(struct tee_context *ctx, bool cap_memref_null)
 
 		if (!optee->scan_bus_done) {
 			INIT_WORK(&optee->scan_bus_work, optee_bus_scan);
-			optee->scan_bus_wq = create_workqueue("optee_bus_scan");
-			if (!optee->scan_bus_wq) {
-				kfree(ctxdata);
-				return -ECHILD;
-			}
-			queue_work(optee->scan_bus_wq, &optee->scan_bus_work);
+			schedule_work(&optee->scan_bus_work);
 			optee->scan_bus_done = true;
 		}
 	}
@@ -129,7 +125,8 @@ int optee_open(struct tee_context *ctx, bool cap_memref_null)
 
 static void optee_release_helper(struct tee_context *ctx,
 				 int (*close_session)(struct tee_context *ctx,
-						      u32 session))
+						      u32 session,
+						      bool system_thread))
 {
 	struct optee_context_data *ctxdata = ctx->data;
 	struct optee_session *sess;
@@ -141,7 +138,7 @@ static void optee_release_helper(struct tee_context *ctx,
 	list_for_each_entry_safe(sess, sess_tmp, &ctxdata->sess_list,
 				 list_node) {
 		list_del(&sess->list_node);
-		close_session(ctx, sess->session_id);
+		close_session(ctx, sess->session_id, sess->use_sys_thread);
 		kfree(sess);
 	}
 	kfree(ctxdata);
@@ -158,10 +155,7 @@ void optee_release_supp(struct tee_context *ctx)
 	struct optee *optee = tee_get_drvdata(ctx->teedev);
 
 	optee_release_helper(ctx, optee_close_session_helper);
-	if (optee->scan_bus_wq) {
-		destroy_workqueue(optee->scan_bus_wq);
-		optee->scan_bus_wq = NULL;
-	}
+
 	optee_supp_release(&optee->supp);
 }
 
diff --git a/drivers/tee/optee/device.c b/drivers/tee/optee/device.c
index 64f0e047c23d..4b1092127694 100644
--- a/drivers/tee/optee/device.c
+++ b/drivers/tee/optee/device.c
@@ -60,7 +60,16 @@ static void optee_release_device(struct device *dev)
 	kfree(optee_device);
 }
 
-static int optee_register_device(const uuid_t *device_uuid)
+static ssize_t need_supplicant_show(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf)
+{
+	return 0;
+}
+
+static DEVICE_ATTR_RO(need_supplicant);
+
+static int optee_register_device(const uuid_t *device_uuid, u32 func)
 {
 	struct tee_client_device *optee_device = NULL;
 	int rc;
@@ -83,6 +92,10 @@ static int optee_register_device(const uuid_t *device_uuid)
 		put_device(&optee_device->dev);
 	}
 
+	if (func == PTA_CMD_GET_DEVICES_SUPP)
+		device_create_file(&optee_device->dev,
+				   &dev_attr_need_supplicant);
+
 	return rc;
 }
 
@@ -142,7 +155,7 @@ static int __optee_enumerate_devices(u32 func)
 	num_devices = shm_size / sizeof(uuid_t);
 
 	for (idx = 0; idx < num_devices; idx++) {
-		rc = optee_register_device(&device_uuid[idx]);
+		rc = optee_register_device(&device_uuid[idx], func);
 		if (rc)
 			goto out_shm;
 	}
diff --git a/drivers/tee/optee/ffa_abi.c b/drivers/tee/optee/ffa_abi.c
index 0828240f27e6..ecb5eb079408 100644
--- a/drivers/tee/optee/ffa_abi.c
+++ b/drivers/tee/optee/ffa_abi.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (c) 2021, Linaro Limited
+ * Copyright (c) 2021, 2023 Linaro Limited
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -528,7 +528,8 @@ static void optee_handle_ffa_rpc(struct tee_context *ctx, struct optee *optee,
 
 static int optee_ffa_yielding_call(struct tee_context *ctx,
 				   struct ffa_send_direct_data *data,
-				   struct optee_msg_arg *rpc_arg)
+				   struct optee_msg_arg *rpc_arg,
+				   bool system_thread)
 {
 	struct optee *optee = tee_get_drvdata(ctx->teedev);
 	struct ffa_device *ffa_dev = optee->ffa.ffa_dev;
@@ -541,7 +542,7 @@ static int optee_ffa_yielding_call(struct tee_context *ctx,
 	int rc;
 
 	/* Initialize waiter */
-	optee_cq_wait_init(&optee->call_queue, &w);
+	optee_cq_wait_init(&optee->call_queue, &w, system_thread);
 	while (true) {
 		rc = msg_ops->sync_send_receive(ffa_dev, data);
 		if (rc)
@@ -604,6 +605,7 @@ done:
  * @ctx:	calling context
  * @shm:	shared memory holding the message to pass to secure world
  * @offs:	offset of the message in @shm
+ * @system_thread: true if caller requests TEE system thread support
  *
  * Does a FF-A call to OP-TEE in secure world and handles eventual resulting
  * Remote Procedure Calls (RPC) from OP-TEE.
@@ -612,7 +614,8 @@ done:
  */
 
 static int optee_ffa_do_call_with_arg(struct tee_context *ctx,
-				      struct tee_shm *shm, u_int offs)
+				      struct tee_shm *shm, u_int offs,
+				      bool system_thread)
 {
 	struct ffa_send_direct_data data = {
 		.data0 = OPTEE_FFA_YIELDING_CALL_WITH_ARG,
@@ -642,7 +645,7 @@ static int optee_ffa_do_call_with_arg(struct tee_context *ctx,
 	if (IS_ERR(rpc_arg))
 		return PTR_ERR(rpc_arg);
 
-	return optee_ffa_yielding_call(ctx, &data, rpc_arg);
+	return optee_ffa_yielding_call(ctx, &data, rpc_arg, system_thread);
 }
 
 /*
@@ -692,7 +695,8 @@ static bool optee_ffa_api_is_compatbile(struct ffa_device *ffa_dev,
 static bool optee_ffa_exchange_caps(struct ffa_device *ffa_dev,
 				    const struct ffa_ops *ops,
 				    u32 *sec_caps,
-				    unsigned int *rpc_param_count)
+				    unsigned int *rpc_param_count,
+				    unsigned int *max_notif_value)
 {
 	struct ffa_send_direct_data data = { OPTEE_FFA_EXCHANGE_CAPABILITIES };
 	int rc;
@@ -709,10 +713,39 @@ static bool optee_ffa_exchange_caps(struct ffa_device *ffa_dev,
 
 	*rpc_param_count = (u8)data.data1;
 	*sec_caps = data.data2;
+	if (data.data3)
+		*max_notif_value = data.data3;
+	else
+		*max_notif_value = OPTEE_DEFAULT_MAX_NOTIF_VALUE;
 
 	return true;
 }
 
+static void notif_callback(int notify_id, void *cb_data)
+{
+	struct optee *optee = cb_data;
+
+	if (notify_id == optee->ffa.bottom_half_value)
+		optee_do_bottom_half(optee->ctx);
+	else
+		optee_notif_send(optee, notify_id);
+}
+
+static int enable_async_notif(struct optee *optee)
+{
+	struct ffa_device *ffa_dev = optee->ffa.ffa_dev;
+	struct ffa_send_direct_data data = {
+		.data0 = OPTEE_FFA_ENABLE_ASYNC_NOTIF,
+		.data1 = optee->ffa.bottom_half_value,
+	};
+	int rc;
+
+	rc = ffa_dev->ops->msg_ops->sync_send_receive(ffa_dev, &data);
+	if (rc)
+		return rc;
+	return data.data0;
+}
+
 static void optee_ffa_get_version(struct tee_device *teedev,
 				  struct tee_ioctl_version_data *vers)
 {
@@ -775,7 +808,11 @@ static const struct optee_ops optee_ffa_ops = {
 static void optee_ffa_remove(struct ffa_device *ffa_dev)
 {
 	struct optee *optee = ffa_dev_get_drvdata(ffa_dev);
+	u32 bottom_half_id = optee->ffa.bottom_half_value;
 
+	if (bottom_half_id != U32_MAX)
+		ffa_dev->ops->notifier_ops->notify_relinquish(ffa_dev,
+							      bottom_half_id);
 	optee_remove_common(optee);
 
 	mutex_destroy(&optee->ffa.mutex);
@@ -784,9 +821,51 @@ static void optee_ffa_remove(struct ffa_device *ffa_dev)
 	kfree(optee);
 }
 
+static int optee_ffa_async_notif_init(struct ffa_device *ffa_dev,
+				      struct optee *optee)
+{
+	bool is_per_vcpu = false;
+	u32 notif_id = 0;
+	int rc;
+
+	while (true) {
+		rc = ffa_dev->ops->notifier_ops->notify_request(ffa_dev,
+								is_per_vcpu,
+								notif_callback,
+								optee,
+								notif_id);
+		if (!rc)
+			break;
+		/*
+		 * -EACCES means that the notification ID was
+		 * already bound, try the next one as long as we
+		 * haven't reached the max. Any other error is a
+		 * permanent error, so skip asynchronous
+		 * notifications in that case.
+		 */
+		if (rc != -EACCES)
+			return rc;
+		notif_id++;
+		if (notif_id >= OPTEE_FFA_MAX_ASYNC_NOTIF_VALUE)
+			return rc;
+	}
+	optee->ffa.bottom_half_value = notif_id;
+
+	rc = enable_async_notif(optee);
+	if (rc < 0) {
+		ffa_dev->ops->notifier_ops->notify_relinquish(ffa_dev,
+							      notif_id);
+		optee->ffa.bottom_half_value = U32_MAX;
+	}
+
+	return rc;
+}
+
 static int optee_ffa_probe(struct ffa_device *ffa_dev)
 {
+	const struct ffa_notifier_ops *notif_ops;
 	const struct ffa_ops *ffa_ops;
+	unsigned int max_notif_value;
 	unsigned int rpc_param_count;
 	struct tee_shm_pool *pool;
 	struct tee_device *teedev;
@@ -797,12 +876,13 @@ static int optee_ffa_probe(struct ffa_device *ffa_dev)
 	int rc;
 
 	ffa_ops = ffa_dev->ops;
+	notif_ops = ffa_ops->notifier_ops;
 
 	if (!optee_ffa_api_is_compatbile(ffa_dev, ffa_ops))
 		return -EINVAL;
 
 	if (!optee_ffa_exchange_caps(ffa_dev, ffa_ops, &sec_caps,
-				     &rpc_param_count))
+				     &rpc_param_count, &max_notif_value))
 		return -EINVAL;
 	if (sec_caps & OPTEE_FFA_SEC_CAP_ARG_OFFSET)
 		arg_cache_flags |= OPTEE_SHM_ARG_SHARED;
@@ -820,6 +900,7 @@ static int optee_ffa_probe(struct ffa_device *ffa_dev)
 
 	optee->ops = &optee_ffa_ops;
 	optee->ffa.ffa_dev = ffa_dev;
+	optee->ffa.bottom_half_value = U32_MAX;
 	optee->rpc_param_count = rpc_param_count;
 
 	teedev = tee_device_alloc(&optee_ffa_clnt_desc, NULL, optee->pool,
@@ -850,8 +931,7 @@ static int optee_ffa_probe(struct ffa_device *ffa_dev)
 	if (rc)
 		goto err_unreg_supp_teedev;
 	mutex_init(&optee->ffa.mutex);
-	mutex_init(&optee->call_queue.mutex);
-	INIT_LIST_HEAD(&optee->call_queue.waiters);
+	optee_cq_init(&optee->call_queue, 0);
 	optee_supp_init(&optee->supp);
 	optee_shm_arg_cache_init(optee, arg_cache_flags);
 	ffa_dev_set_drvdata(ffa_dev, optee);
@@ -864,6 +944,12 @@ static int optee_ffa_probe(struct ffa_device *ffa_dev)
 	rc = optee_notif_init(optee, OPTEE_DEFAULT_MAX_NOTIF_VALUE);
 	if (rc)
 		goto err_close_ctx;
+	if (sec_caps & OPTEE_FFA_SEC_CAP_ASYNC_NOTIF) {
+		rc = optee_ffa_async_notif_init(ffa_dev, optee);
+		if (rc < 0)
+			pr_err("Failed to initialize async notifications: %d",
+			       rc);
+	}
 
 	rc = optee_enumerate_devices(PTA_CMD_GET_DEVICES);
 	if (rc)
@@ -874,6 +960,9 @@ static int optee_ffa_probe(struct ffa_device *ffa_dev)
 
 err_unregister_devices:
 	optee_unregister_devices();
+	if (optee->ffa.bottom_half_value != U32_MAX)
+		notif_ops->notify_relinquish(ffa_dev,
+					     optee->ffa.bottom_half_value);
 	optee_notif_uninit(optee);
 err_close_ctx:
 	teedev_close_context(ctx);
diff --git a/drivers/tee/optee/optee_ffa.h b/drivers/tee/optee/optee_ffa.h
index 97266243deaa..5db779dc00de 100644
--- a/drivers/tee/optee/optee_ffa.h
+++ b/drivers/tee/optee/optee_ffa.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: BSD-2-Clause */
 /*
- * Copyright (c) 2019-2021, Linaro Limited
+ * Copyright (c) 2019-2021, 2023 Linaro Limited
  */
 
 /*
@@ -73,7 +73,7 @@
  *
  * Call register usage:
  * w3:    Service ID, OPTEE_FFA_EXCHANGE_CAPABILITIES
- * w4-w7: Note used (MBZ)
+ * w4-w7: Not used (MBZ)
  *
  * Return register usage:
  * w3:    Error code, 0 on success
@@ -82,14 +82,16 @@
  *                   OPTEE_FFA_YIELDING_CALL_WITH_ARG.
  *        Bit[31:8]: Reserved (MBZ)
  * w5:	  Bitfield of secure world capabilities OPTEE_FFA_SEC_CAP_* below,
- *	  unused bits MBZ.
- * w6-w7: Not used (MBZ)
+ * w6:	  The maximum secure world notification number
+ * w7:	  Not used (MBZ)
  */
 /*
  * Secure world supports giving an offset into the argument shared memory
  * object, see also OPTEE_FFA_YIELDING_CALL_WITH_ARG
  */
 #define OPTEE_FFA_SEC_CAP_ARG_OFFSET	BIT(0)
+/* OP-TEE supports asynchronous notification via FF-A */
+#define OPTEE_FFA_SEC_CAP_ASYNC_NOTIF	BIT(1)
 
 #define OPTEE_FFA_EXCHANGE_CAPABILITIES OPTEE_FFA_BLOCKING_CALL(2)
 
@@ -109,6 +111,24 @@
 #define OPTEE_FFA_UNREGISTER_SHM	OPTEE_FFA_BLOCKING_CALL(3)
 
 /*
+ * Inform OP-TEE that the normal world is able to receive asynchronous
+ * notifications.
+ *
+ * Call register usage:
+ * w3:    Service ID, OPTEE_FFA_ENABLE_ASYNC_NOTIF
+ * w4:	  Notification value to request bottom half processing, should be
+ *	  less than OPTEE_FFA_MAX_ASYNC_NOTIF_VALUE.
+ * w5-w7: Not used (MBZ)
+ *
+ * Return register usage:
+ * w3:    Error code, 0 on success
+ * w4-w7: Note used (MBZ)
+ */
+#define OPTEE_FFA_ENABLE_ASYNC_NOTIF	OPTEE_FFA_BLOCKING_CALL(5)
+
+#define OPTEE_FFA_MAX_ASYNC_NOTIF_VALUE 64
+
+/*
  * Call with struct optee_msg_arg as argument in the supplied shared memory
  * with a zero internal offset and normal cached memory attributes.
  * Register usage:
diff --git a/drivers/tee/optee/optee_private.h b/drivers/tee/optee/optee_private.h
index 6bb5cae09688..7a5243c78b55 100644
--- a/drivers/tee/optee/optee_private.h
+++ b/drivers/tee/optee/optee_private.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (c) 2015-2021, Linaro Limited
+ * Copyright (c) 2015-2021, 2023 Linaro Limited
  */
 
 #ifndef OPTEE_PRIVATE_H
@@ -40,15 +40,33 @@ typedef void (optee_invoke_fn)(unsigned long, unsigned long, unsigned long,
 				unsigned long, unsigned long,
 				struct arm_smccc_res *);
 
+/*
+ * struct optee_call_waiter - TEE entry may need to wait for a free TEE thread
+ * @list_node		Reference in waiters list
+ * @c			Waiting completion reference
+ * @sys_thread		True if waiter belongs to a system thread
+ */
 struct optee_call_waiter {
 	struct list_head list_node;
 	struct completion c;
+	bool sys_thread;
 };
 
+/*
+ * struct optee_call_queue - OP-TEE call queue management
+ * @mutex			Serializes access to this struct
+ * @waiters			List of threads waiting to enter OP-TEE
+ * @total_thread_count		Overall number of thread context in OP-TEE or 0
+ * @free_thread_count		Number of threads context free in OP-TEE
+ * @sys_thread_req_count	Number of registered system thread sessions
+ */
 struct optee_call_queue {
 	/* Serializes access to this struct */
 	struct mutex mutex;
 	struct list_head waiters;
+	int total_thread_count;
+	int free_thread_count;
+	int sys_thread_req_count;
 };
 
 struct optee_notif {
@@ -129,12 +147,14 @@ struct optee_smc {
  * struct optee_ffa_data -  FFA communication struct
  * @ffa_dev		FFA device, contains the destination id, the id of
  *			OP-TEE in secure world
- * @ffa_ops		FFA operations
+ * @bottom_half_value	Notification ID used for bottom half signalling or
+ *			U32_MAX if unused
  * @mutex		Serializes access to @global_ids
  * @global_ids		FF-A shared memory global handle translation
  */
 struct optee_ffa {
 	struct ffa_device *ffa_dev;
+	u32 bottom_half_value;
 	/* Serializes access to @global_ids */
 	struct mutex mutex;
 	struct rhashtable global_ids;
@@ -154,7 +174,8 @@ struct optee;
  */
 struct optee_ops {
 	int (*do_call_with_arg)(struct tee_context *ctx,
-				struct tee_shm *shm_arg, u_int offs);
+				struct tee_shm *shm_arg, u_int offs,
+				bool system_thread);
 	int (*to_msg_param)(struct optee *optee,
 			    struct optee_msg_param *msg_params,
 			    size_t num_params, const struct tee_param *params);
@@ -178,7 +199,6 @@ struct optee_ops {
  * @pool:		shared memory pool
  * @rpc_param_count:	If > 0 number of RPC parameters to make room for
  * @scan_bus_done	flag if device registation was already done.
- * @scan_bus_wq		workqueue to scan optee bus and register optee drivers
  * @scan_bus_work	workq to scan optee bus and register optee drivers
  */
 struct optee {
@@ -197,13 +217,13 @@ struct optee {
 	struct tee_shm_pool *pool;
 	unsigned int rpc_param_count;
 	bool   scan_bus_done;
-	struct workqueue_struct *scan_bus_wq;
 	struct work_struct scan_bus_work;
 };
 
 struct optee_session {
 	struct list_head list_node;
 	u32 session_id;
+	bool use_sys_thread;
 };
 
 struct optee_context_data {
@@ -250,7 +270,9 @@ int optee_supp_send(struct tee_context *ctx, u32 ret, u32 num_params,
 int optee_open_session(struct tee_context *ctx,
 		       struct tee_ioctl_open_session_arg *arg,
 		       struct tee_param *param);
-int optee_close_session_helper(struct tee_context *ctx, u32 session);
+int optee_system_session(struct tee_context *ctx, u32 session);
+int optee_close_session_helper(struct tee_context *ctx, u32 session,
+			       bool system_thread);
 int optee_close_session(struct tee_context *ctx, u32 session);
 int optee_invoke_func(struct tee_context *ctx, struct tee_ioctl_invoke_arg *arg,
 		      struct tee_param *param);
@@ -298,8 +320,9 @@ static inline void optee_to_msg_param_value(struct optee_msg_param *mp,
 	mp->u.value.c = p->u.value.c;
 }
 
+void optee_cq_init(struct optee_call_queue *cq, int thread_count);
 void optee_cq_wait_init(struct optee_call_queue *cq,
-			struct optee_call_waiter *w);
+			struct optee_call_waiter *w, bool sys_thread);
 void optee_cq_wait_for_completion(struct optee_call_queue *cq,
 				  struct optee_call_waiter *w);
 void optee_cq_wait_final(struct optee_call_queue *cq,
@@ -323,6 +346,9 @@ void optee_rpc_cmd_free_suppl(struct tee_context *ctx, struct tee_shm *shm);
 void optee_rpc_cmd(struct tee_context *ctx, struct optee *optee,
 		   struct optee_msg_arg *arg);
 
+int optee_do_bottom_half(struct tee_context *ctx);
+int optee_stop_async_notif(struct tee_context *ctx);
+
 /*
  * Small helpers
  */
diff --git a/drivers/tee/optee/smc_abi.c b/drivers/tee/optee/smc_abi.c
index d5b28fd35d66..a37f87087e5c 100644
--- a/drivers/tee/optee/smc_abi.c
+++ b/drivers/tee/optee/smc_abi.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (c) 2015-2021, Linaro Limited
+ * Copyright (c) 2015-2021, 2023 Linaro Limited
  * Copyright (c) 2016, EPAM Systems
  */
 
@@ -283,7 +283,7 @@ static void optee_enable_shm_cache(struct optee *optee)
 	struct optee_call_waiter w;
 
 	/* We need to retry until secure world isn't busy. */
-	optee_cq_wait_init(&optee->call_queue, &w);
+	optee_cq_wait_init(&optee->call_queue, &w, false);
 	while (true) {
 		struct arm_smccc_res res;
 
@@ -308,7 +308,7 @@ static void __optee_disable_shm_cache(struct optee *optee, bool is_mapped)
 	struct optee_call_waiter w;
 
 	/* We need to retry until secure world isn't busy. */
-	optee_cq_wait_init(&optee->call_queue, &w);
+	optee_cq_wait_init(&optee->call_queue, &w, false);
 	while (true) {
 		union {
 			struct arm_smccc_res smccc;
@@ -507,7 +507,7 @@ static int optee_shm_register(struct tee_context *ctx, struct tee_shm *shm,
 	msg_arg->params->u.tmem.buf_ptr = virt_to_phys(pages_list) |
 	  (tee_shm_get_page_offset(shm) & (OPTEE_MSG_NONCONTIG_PAGE_SIZE - 1));
 
-	if (optee->ops->do_call_with_arg(ctx, shm_arg, 0) ||
+	if (optee->ops->do_call_with_arg(ctx, shm_arg, 0, false) ||
 	    msg_arg->ret != TEEC_SUCCESS)
 		rc = -EINVAL;
 
@@ -550,7 +550,7 @@ static int optee_shm_unregister(struct tee_context *ctx, struct tee_shm *shm)
 	msg_arg->params[0].attr = OPTEE_MSG_ATTR_TYPE_RMEM_INPUT;
 	msg_arg->params[0].u.rmem.shm_ref = (unsigned long)shm;
 
-	if (optee->ops->do_call_with_arg(ctx, shm_arg, 0) ||
+	if (optee->ops->do_call_with_arg(ctx, shm_arg, 0, false) ||
 	    msg_arg->ret != TEEC_SUCCESS)
 		rc = -EINVAL;
 out:
@@ -678,10 +678,11 @@ static void handle_rpc_func_cmd_shm_alloc(struct tee_context *ctx,
 					  struct optee_msg_arg *arg,
 					  struct optee_call_ctx *call_ctx)
 {
-	phys_addr_t pa;
 	struct tee_shm *shm;
 	size_t sz;
 	size_t n;
+	struct page **pages;
+	size_t page_count;
 
 	arg->ret_origin = TEEC_ORIGIN_COMMS;
 
@@ -716,32 +717,23 @@ static void handle_rpc_func_cmd_shm_alloc(struct tee_context *ctx,
 		return;
 	}
 
-	if (tee_shm_get_pa(shm, 0, &pa)) {
-		arg->ret = TEEC_ERROR_BAD_PARAMETERS;
-		goto bad;
-	}
-
-	sz = tee_shm_get_size(shm);
-
-	if (tee_shm_is_dynamic(shm)) {
-		struct page **pages;
+	/*
+	 * If there are pages it's dynamically allocated shared memory (not
+	 * from the reserved shared memory pool) and needs to be
+	 * registered.
+	 */
+	pages = tee_shm_get_pages(shm, &page_count);
+	if (pages) {
 		u64 *pages_list;
-		size_t page_num;
-
-		pages = tee_shm_get_pages(shm, &page_num);
-		if (!pages || !page_num) {
-			arg->ret = TEEC_ERROR_OUT_OF_MEMORY;
-			goto bad;
-		}
 
-		pages_list = optee_allocate_pages_list(page_num);
+		pages_list = optee_allocate_pages_list(page_count);
 		if (!pages_list) {
 			arg->ret = TEEC_ERROR_OUT_OF_MEMORY;
 			goto bad;
 		}
 
 		call_ctx->pages_list = pages_list;
-		call_ctx->num_entries = page_num;
+		call_ctx->num_entries = page_count;
 
 		arg->params[0].attr = OPTEE_MSG_ATTR_TYPE_TMEM_OUTPUT |
 				      OPTEE_MSG_ATTR_NONCONTIG;
@@ -752,17 +744,22 @@ static void handle_rpc_func_cmd_shm_alloc(struct tee_context *ctx,
 		arg->params[0].u.tmem.buf_ptr = virt_to_phys(pages_list) |
 			(tee_shm_get_page_offset(shm) &
 			 (OPTEE_MSG_NONCONTIG_PAGE_SIZE - 1));
-		arg->params[0].u.tmem.size = tee_shm_get_size(shm);
-		arg->params[0].u.tmem.shm_ref = (unsigned long)shm;
 
-		optee_fill_pages_list(pages_list, pages, page_num,
+		optee_fill_pages_list(pages_list, pages, page_count,
 				      tee_shm_get_page_offset(shm));
 	} else {
+		phys_addr_t pa;
+
+		if (tee_shm_get_pa(shm, 0, &pa)) {
+			arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+			goto bad;
+		}
+
 		arg->params[0].attr = OPTEE_MSG_ATTR_TYPE_TMEM_OUTPUT;
 		arg->params[0].u.tmem.buf_ptr = pa;
-		arg->params[0].u.tmem.size = sz;
-		arg->params[0].u.tmem.shm_ref = (unsigned long)shm;
 	}
+	arg->params[0].u.tmem.size = tee_shm_get_size(shm);
+	arg->params[0].u.tmem.shm_ref = (unsigned long)shm;
 
 	arg->ret = TEEC_SUCCESS;
 	return;
@@ -806,6 +803,7 @@ static void handle_rpc_func_cmd(struct tee_context *ctx, struct optee *optee,
 /**
  * optee_handle_rpc() - handle RPC from secure world
  * @ctx:	context doing the RPC
+ * @rpc_arg:	pointer to RPC arguments if any, or NULL if none
  * @param:	value of registers for the RPC
  * @call_ctx:	call context. Preserved during one OP-TEE invocation
  *
@@ -878,6 +876,7 @@ static void optee_handle_rpc(struct tee_context *ctx,
  * @ctx:	calling context
  * @shm:	shared memory holding the message to pass to secure world
  * @offs:	offset of the message in @shm
+ * @system_thread: true if caller requests TEE system thread support
  *
  * Does and SMC to OP-TEE in secure world and handles eventual resulting
  * Remote Procedure Calls (RPC) from OP-TEE.
@@ -885,7 +884,8 @@ static void optee_handle_rpc(struct tee_context *ctx,
  * Returns return code from secure world, 0 is OK
  */
 static int optee_smc_do_call_with_arg(struct tee_context *ctx,
-				      struct tee_shm *shm, u_int offs)
+				      struct tee_shm *shm, u_int offs,
+				      bool system_thread)
 {
 	struct optee *optee = tee_get_drvdata(ctx->teedev);
 	struct optee_call_waiter w;
@@ -926,7 +926,7 @@ static int optee_smc_do_call_with_arg(struct tee_context *ctx,
 		reg_pair_from_64(&param.a1, &param.a2, parg);
 	}
 	/* Initialize waiter */
-	optee_cq_wait_init(&optee->call_queue, &w);
+	optee_cq_wait_init(&optee->call_queue, &w, system_thread);
 	while (true) {
 		struct arm_smccc_res res;
 
@@ -965,34 +965,6 @@ static int optee_smc_do_call_with_arg(struct tee_context *ctx,
 	return rc;
 }
 
-static int simple_call_with_arg(struct tee_context *ctx, u32 cmd)
-{
-	struct optee_shm_arg_entry *entry;
-	struct optee_msg_arg *msg_arg;
-	struct tee_shm *shm;
-	u_int offs;
-
-	msg_arg = optee_get_msg_arg(ctx, 0, &entry, &shm, &offs);
-	if (IS_ERR(msg_arg))
-		return PTR_ERR(msg_arg);
-
-	msg_arg->cmd = cmd;
-	optee_smc_do_call_with_arg(ctx, shm, offs);
-
-	optee_free_msg_arg(ctx, entry, offs);
-	return 0;
-}
-
-static int optee_smc_do_bottom_half(struct tee_context *ctx)
-{
-	return simple_call_with_arg(ctx, OPTEE_MSG_CMD_DO_BOTTOM_HALF);
-}
-
-static int optee_smc_stop_async_notif(struct tee_context *ctx)
-{
-	return simple_call_with_arg(ctx, OPTEE_MSG_CMD_STOP_ASYNC_NOTIF);
-}
-
 /*
  * 5. Asynchronous notification
  */
@@ -1048,7 +1020,7 @@ static irqreturn_t notif_irq_thread_fn(int irq, void *dev_id)
 {
 	struct optee *optee = dev_id;
 
-	optee_smc_do_bottom_half(optee->ctx);
+	optee_do_bottom_half(optee->ctx);
 
 	return IRQ_HANDLED;
 }
@@ -1086,7 +1058,7 @@ static void notif_pcpu_irq_work_fn(struct work_struct *work)
 						   notif_pcpu_work);
 	struct optee *optee = container_of(optee_smc, struct optee, smc);
 
-	optee_smc_do_bottom_half(optee->ctx);
+	optee_do_bottom_half(optee->ctx);
 }
 
 static int init_pcpu_irq(struct optee *optee, u_int irq)
@@ -1158,7 +1130,7 @@ static void uninit_pcpu_irq(struct optee *optee)
 static void optee_smc_notif_uninit_irq(struct optee *optee)
 {
 	if (optee->smc.sec_caps & OPTEE_SMC_SEC_CAP_ASYNC_NOTIF) {
-		optee_smc_stop_async_notif(optee->ctx);
+		optee_stop_async_notif(optee->ctx);
 		if (optee->smc.notif_irq) {
 			if (irq_is_percpu_devid(optee->smc.notif_irq))
 				uninit_pcpu_irq(optee);
@@ -1210,6 +1182,7 @@ static const struct tee_driver_ops optee_clnt_ops = {
 	.release = optee_release,
 	.open_session = optee_open_session,
 	.close_session = optee_close_session,
+	.system_session = optee_system_session,
 	.invoke_func = optee_invoke_func,
 	.cancel_req = optee_cancel_req,
 	.shm_register = optee_shm_register,
@@ -1357,6 +1330,16 @@ static bool optee_msg_exchange_capabilities(optee_invoke_fn *invoke_fn,
 	return true;
 }
 
+static unsigned int optee_msg_get_thread_count(optee_invoke_fn *invoke_fn)
+{
+	struct arm_smccc_res res;
+
+	invoke_fn(OPTEE_SMC_GET_THREAD_COUNT, 0, 0, 0, 0, 0, 0, 0, &res);
+	if (res.a0)
+		return 0;
+	return res.a1;
+}
+
 static struct tee_shm_pool *
 optee_config_shm_memremap(optee_invoke_fn *invoke_fn, void **memremaped_shm)
 {
@@ -1609,6 +1592,7 @@ static int optee_probe(struct platform_device *pdev)
 	struct optee *optee = NULL;
 	void *memremaped_shm = NULL;
 	unsigned int rpc_param_count;
+	unsigned int thread_count;
 	struct tee_device *teedev;
 	struct tee_context *ctx;
 	u32 max_notif_value;
@@ -1636,6 +1620,7 @@ static int optee_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
+	thread_count = optee_msg_get_thread_count(invoke_fn);
 	if (!optee_msg_exchange_capabilities(invoke_fn, &sec_caps,
 					     &max_notif_value,
 					     &rpc_param_count)) {
@@ -1725,8 +1710,7 @@ static int optee_probe(struct platform_device *pdev)
 	if (rc)
 		goto err_unreg_supp_teedev;
 
-	mutex_init(&optee->call_queue.mutex);
-	INIT_LIST_HEAD(&optee->call_queue.waiters);
+	optee_cq_init(&optee->call_queue, thread_count);
 	optee_supp_init(&optee->supp);
 	optee->smc.memremaped_shm = memremaped_shm;
 	optee->pool = pool;
diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c
index 5ddfd5d9ac7f..792d6fae4354 100644
--- a/drivers/tee/tee_core.c
+++ b/drivers/tee/tee_core.c
@@ -1173,6 +1173,14 @@ int tee_client_close_session(struct tee_context *ctx, u32 session)
 }
 EXPORT_SYMBOL_GPL(tee_client_close_session);
 
+int tee_client_system_session(struct tee_context *ctx, u32 session)
+{
+	if (!ctx->teedev->desc->ops->system_session)
+		return -EINVAL;
+	return ctx->teedev->desc->ops->system_session(ctx, session);
+}
+EXPORT_SYMBOL_GPL(tee_client_system_session);
+
 int tee_client_invoke_func(struct tee_context *ctx,
 			   struct tee_ioctl_invoke_arg *arg,
 			   struct tee_param *param)
diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c
index 673cf0359494..731d9028b67f 100644
--- a/drivers/tee/tee_shm.c
+++ b/drivers/tee/tee_shm.c
@@ -22,23 +22,12 @@ static void shm_put_kernel_pages(struct page **pages, size_t page_count)
 		put_page(pages[n]);
 }
 
-static int shm_get_kernel_pages(unsigned long start, size_t page_count,
-				struct page **pages)
+static void shm_get_kernel_pages(struct page **pages, size_t page_count)
 {
-	struct page *page;
 	size_t n;
 
-	if (WARN_ON_ONCE(is_vmalloc_addr((void *)start) ||
-			 is_kmap_addr((void *)start)))
-		return -EINVAL;
-
-	page = virt_to_page((void *)start);
-	for (n = 0; n < page_count; n++) {
-		pages[n] = page + n;
+	for (n = 0; n < page_count; n++)
 		get_page(pages[n]);
-	}
-
-	return page_count;
 }
 
 static void release_registered_pages(struct tee_shm *shm)
@@ -214,13 +203,14 @@ struct tee_shm *tee_shm_alloc_priv_buf(struct tee_context *ctx, size_t size)
 EXPORT_SYMBOL_GPL(tee_shm_alloc_priv_buf);
 
 static struct tee_shm *
-register_shm_helper(struct tee_context *ctx, unsigned long addr,
-		    size_t length, u32 flags, int id)
+register_shm_helper(struct tee_context *ctx, struct iov_iter *iter, u32 flags,
+		    int id)
 {
 	struct tee_device *teedev = ctx->teedev;
 	struct tee_shm *shm;
-	unsigned long start;
-	size_t num_pages;
+	unsigned long start, addr;
+	size_t num_pages, off;
+	ssize_t len;
 	void *ret;
 	int rc;
 
@@ -245,31 +235,38 @@ register_shm_helper(struct tee_context *ctx, unsigned long addr,
 	shm->flags = flags;
 	shm->ctx = ctx;
 	shm->id = id;
-	addr = untagged_addr(addr);
+	addr = untagged_addr((unsigned long)iter_iov_addr(iter));
 	start = rounddown(addr, PAGE_SIZE);
-	shm->offset = addr - start;
-	shm->size = length;
-	num_pages = (roundup(addr + length, PAGE_SIZE) - start) / PAGE_SIZE;
+	num_pages = iov_iter_npages(iter, INT_MAX);
+	if (!num_pages) {
+		ret = ERR_PTR(-ENOMEM);
+		goto err_ctx_put;
+	}
+
 	shm->pages = kcalloc(num_pages, sizeof(*shm->pages), GFP_KERNEL);
 	if (!shm->pages) {
 		ret = ERR_PTR(-ENOMEM);
 		goto err_free_shm;
 	}
 
-	if (flags & TEE_SHM_USER_MAPPED)
-		rc = pin_user_pages_fast(start, num_pages, FOLL_WRITE,
-					 shm->pages);
-	else
-		rc = shm_get_kernel_pages(start, num_pages, shm->pages);
-	if (rc > 0)
-		shm->num_pages = rc;
-	if (rc != num_pages) {
-		if (rc >= 0)
-			rc = -ENOMEM;
-		ret = ERR_PTR(rc);
-		goto err_put_shm_pages;
+	len = iov_iter_extract_pages(iter, &shm->pages, LONG_MAX, num_pages, 0,
+				     &off);
+	if (unlikely(len <= 0)) {
+		ret = len ? ERR_PTR(len) : ERR_PTR(-ENOMEM);
+		goto err_free_shm_pages;
 	}
 
+	/*
+	 * iov_iter_extract_kvec_pages does not get reference on the pages,
+	 * get a reference on them.
+	 */
+	if (iov_iter_is_kvec(iter))
+		shm_get_kernel_pages(shm->pages, num_pages);
+
+	shm->offset = off;
+	shm->size = len;
+	shm->num_pages = num_pages;
+
 	rc = teedev->desc->ops->shm_register(ctx, shm, shm->pages,
 					     shm->num_pages, start);
 	if (rc) {
@@ -279,10 +276,11 @@ register_shm_helper(struct tee_context *ctx, unsigned long addr,
 
 	return shm;
 err_put_shm_pages:
-	if (flags & TEE_SHM_USER_MAPPED)
+	if (!iov_iter_is_kvec(iter))
 		unpin_user_pages(shm->pages, shm->num_pages);
 	else
 		shm_put_kernel_pages(shm->pages, shm->num_pages);
+err_free_shm_pages:
 	kfree(shm->pages);
 err_free_shm:
 	kfree(shm);
@@ -307,6 +305,7 @@ struct tee_shm *tee_shm_register_user_buf(struct tee_context *ctx,
 	u32 flags = TEE_SHM_USER_MAPPED | TEE_SHM_DYNAMIC;
 	struct tee_device *teedev = ctx->teedev;
 	struct tee_shm *shm;
+	struct iov_iter iter;
 	void *ret;
 	int id;
 
@@ -319,7 +318,8 @@ struct tee_shm *tee_shm_register_user_buf(struct tee_context *ctx,
 	if (id < 0)
 		return ERR_PTR(id);
 
-	shm = register_shm_helper(ctx, addr, length, flags, id);
+	iov_iter_ubuf(&iter, ITER_DEST,  (void __user *)addr, length);
+	shm = register_shm_helper(ctx, &iter, flags, id);
 	if (IS_ERR(shm)) {
 		mutex_lock(&teedev->mutex);
 		idr_remove(&teedev->idr, id);
@@ -352,8 +352,14 @@ struct tee_shm *tee_shm_register_kernel_buf(struct tee_context *ctx,
 					    void *addr, size_t length)
 {
 	u32 flags = TEE_SHM_DYNAMIC;
+	struct kvec kvec;
+	struct iov_iter iter;
+
+	kvec.iov_base = addr;
+	kvec.iov_len = length;
+	iov_iter_kvec(&iter, ITER_DEST, &kvec, 1, length);
 
-	return register_shm_helper(ctx, (unsigned long)addr, length, flags, -1);
+	return register_shm_helper(ctx, &iter, flags, -1);
 }
 EXPORT_SYMBOL_GPL(tee_shm_register_kernel_buf);
 
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index c81a00fbca7d..59883502eff4 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -76,10 +76,6 @@ config THERMAL_OF
 	  Say 'Y' here if you need to build thermal infrastructure
 	  based on device tree.
 
-config THERMAL_ACPI
-       depends on ACPI
-       bool
-
 config THERMAL_WRITABLE_TRIPS
 	bool "Enable writable trip points"
 	help
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index c934cab309ae..a8318d671036 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -13,7 +13,6 @@ thermal_sys-$(CONFIG_THERMAL_NETLINK)		+= thermal_netlink.o
 # interface to/from other layers providing sensors
 thermal_sys-$(CONFIG_THERMAL_HWMON)		+= thermal_hwmon.o
 thermal_sys-$(CONFIG_THERMAL_OF)		+= thermal_of.o
-thermal_sys-$(CONFIG_THERMAL_ACPI)		+= thermal_acpi.o
 
 # governors
 CFLAGS_gov_power_allocator.o			:= -I$(src)
diff --git a/drivers/thermal/amlogic_thermal.c b/drivers/thermal/amlogic_thermal.c
index 5877cde25b79..df7a5ed55385 100644
--- a/drivers/thermal/amlogic_thermal.c
+++ b/drivers/thermal/amlogic_thermal.c
@@ -167,13 +167,11 @@ static int amlogic_thermal_enable(struct amlogic_thermal *data)
 	return 0;
 }
 
-static int amlogic_thermal_disable(struct amlogic_thermal *data)
+static void amlogic_thermal_disable(struct amlogic_thermal *data)
 {
 	regmap_update_bits(data->regmap, TSENSOR_CFG_REG1,
 			   TSENSOR_CFG_REG1_ENABLE, 0);
 	clk_disable_unprepare(data->clk);
-
-	return 0;
 }
 
 static int amlogic_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
@@ -298,27 +296,30 @@ static void amlogic_thermal_remove(struct platform_device *pdev)
 	amlogic_thermal_disable(data);
 }
 
-static int __maybe_unused amlogic_thermal_suspend(struct device *dev)
+static int amlogic_thermal_suspend(struct device *dev)
 {
 	struct amlogic_thermal *data = dev_get_drvdata(dev);
 
-	return amlogic_thermal_disable(data);
+	amlogic_thermal_disable(data);
+
+	return 0;
 }
 
-static int __maybe_unused amlogic_thermal_resume(struct device *dev)
+static int amlogic_thermal_resume(struct device *dev)
 {
 	struct amlogic_thermal *data = dev_get_drvdata(dev);
 
 	return amlogic_thermal_enable(data);
 }
 
-static SIMPLE_DEV_PM_OPS(amlogic_thermal_pm_ops,
-			 amlogic_thermal_suspend, amlogic_thermal_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(amlogic_thermal_pm_ops,
+				amlogic_thermal_suspend,
+				amlogic_thermal_resume);
 
 static struct platform_driver amlogic_thermal_driver = {
 	.driver = {
 		.name		= "amlogic_thermal",
-		.pm		= &amlogic_thermal_pm_ops,
+		.pm		= pm_ptr(&amlogic_thermal_pm_ops),
 		.of_match_table = of_amlogic_thermal_match,
 	},
 	.probe = amlogic_thermal_probe,
diff --git a/drivers/thermal/cpuidle_cooling.c b/drivers/thermal/cpuidle_cooling.c
index 69f4c0a8dfcc..f678c1281862 100644
--- a/drivers/thermal/cpuidle_cooling.c
+++ b/drivers/thermal/cpuidle_cooling.c
@@ -66,7 +66,7 @@ static unsigned int cpuidle_cooling_runtime(unsigned int idle_duration_us,
  * @state : a pointer to the state variable to be filled
  *
  * The function always returns 100 as the injection ratio. It is
- * percentile based for consistency accross different platforms.
+ * percentile based for consistency across different platforms.
  *
  * Return: The function can not fail, it is always zero
  */
@@ -146,7 +146,7 @@ static int cpuidle_cooling_set_cur_state(struct thermal_cooling_device *cdev,
 	return 0;
 }
 
-/**
+/*
  * cpuidle_cooling_ops - thermal cooling device ops
  */
 static struct thermal_cooling_device_ops cpuidle_cooling_ops = {
diff --git a/drivers/thermal/gov_power_allocator.c b/drivers/thermal/gov_power_allocator.c
index 83d4f451b1a9..7b6aa265ff6a 100644
--- a/drivers/thermal/gov_power_allocator.c
+++ b/drivers/thermal/gov_power_allocator.c
@@ -47,6 +47,22 @@ static inline s64 div_frac(s64 x, s64 y)
 }
 
 /**
+ * struct power_actor - internal power information for power actor
+ * @req_power:		requested power value (not weighted)
+ * @max_power:		max allocatable power for this actor
+ * @granted_power:	granted power for this actor
+ * @extra_actor_power:	extra power that this actor can receive
+ * @weighted_req_power:	weighted requested power as input to IPA
+ */
+struct power_actor {
+	u32 req_power;
+	u32 max_power;
+	u32 granted_power;
+	u32 extra_actor_power;
+	u32 weighted_req_power;
+};
+
+/**
  * struct power_allocator_params - parameters for the power allocator governor
  * @allocated_tzp:	whether we have allocated tzp for this thermal zone and
  *			it needs to be freed on unbind
@@ -59,9 +75,12 @@ static inline s64 div_frac(s64 x, s64 y)
  *			governor switches on when this trip point is crossed.
  *			If the thermal zone only has one passive trip point,
  *			@trip_switch_on should be NULL.
- * @trip_max_desired_temperature:	last passive trip point of the thermal
- *					zone.  The temperature we are
- *					controlling for.
+ * @trip_max:		last passive trip point of the thermal zone. The
+ *			temperature we are controlling for.
+ * @total_weight:	Sum of all thermal instances weights
+ * @num_actors:		number of cooling devices supporting IPA callbacks
+ * @buffer_size:	internal buffer size, to avoid runtime re-calculation
+ * @power:		buffer for all power actors internal power information
  */
 struct power_allocator_params {
 	bool allocated_tzp;
@@ -69,9 +88,20 @@ struct power_allocator_params {
 	s32 prev_err;
 	u32 sustainable_power;
 	const struct thermal_trip *trip_switch_on;
-	const struct thermal_trip *trip_max_desired_temperature;
+	const struct thermal_trip *trip_max;
+	int total_weight;
+	unsigned int num_actors;
+	unsigned int buffer_size;
+	struct power_actor *power;
 };
 
+static bool power_actor_is_valid(struct power_allocator_params *params,
+				 struct thermal_instance *instance)
+{
+	return (instance->trip == params->trip_max &&
+		 cdev_is_power_actor(instance->cdev));
+}
+
 /**
  * estimate_sustainable_power() - Estimate the sustainable power of a thermal zone
  * @tz: thermal zone we are operating in
@@ -85,20 +115,17 @@ struct power_allocator_params {
  */
 static u32 estimate_sustainable_power(struct thermal_zone_device *tz)
 {
-	u32 sustainable_power = 0;
-	struct thermal_instance *instance;
 	struct power_allocator_params *params = tz->governor_data;
+	struct thermal_cooling_device *cdev;
+	struct thermal_instance *instance;
+	u32 sustainable_power = 0;
+	u32 min_power;
 
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
-		struct thermal_cooling_device *cdev = instance->cdev;
-		u32 min_power;
-
-		if (instance->trip != params->trip_max_desired_temperature)
-			continue;
-
-		if (!cdev_is_power_actor(cdev))
+		if (!power_actor_is_valid(params, instance))
 			continue;
 
+		cdev = instance->cdev;
 		if (cdev->ops->state2power(cdev, instance->upper, &min_power))
 			continue;
 
@@ -212,10 +239,10 @@ static u32 pid_controller(struct thermal_zone_device *tz,
 			  int control_temp,
 			  u32 max_allocatable_power)
 {
+	struct power_allocator_params *params = tz->governor_data;
 	s64 p, i, d, power_range;
 	s32 err, max_power_frac;
 	u32 sustainable_power;
-	struct power_allocator_params *params = tz->governor_data;
 
 	max_power_frac = int_to_frac(max_allocatable_power);
 
@@ -303,15 +330,10 @@ power_actor_set_power(struct thermal_cooling_device *cdev,
 
 /**
  * divvy_up_power() - divvy the allocated power between the actors
- * @req_power:	each actor's requested power
- * @max_power:	each actor's maximum available power
- * @num_actors:	size of the @req_power, @max_power and @granted_power's array
- * @total_req_power: sum of @req_power
+ * @power:		buffer for all power actors internal power information
+ * @num_actors:		number of power actors in this thermal zone
+ * @total_req_power:	sum of all weighted requested power for all actors
  * @power_range:	total allocated power
- * @granted_power:	output array: each actor's granted power
- * @extra_actor_power:	an appropriately sized array to be used in the
- *			function as temporary storage of the extra power given
- *			to the actors
  *
  * This function divides the total allocated power (@power_range)
  * fairly between the actors.  It first tries to give each actor a
@@ -324,15 +346,12 @@ power_actor_set_power(struct thermal_cooling_device *cdev,
  * If any actor received more than their maximum power, then that
  * surplus is re-divvied among the actors based on how far they are
  * from their respective maximums.
- *
- * Granted power for each actor is written to @granted_power, which
- * should've been allocated by the calling function.
  */
-static void divvy_up_power(u32 *req_power, u32 *max_power, int num_actors,
-			   u32 total_req_power, u32 power_range,
-			   u32 *granted_power, u32 *extra_actor_power)
+static void divvy_up_power(struct power_actor *power, int num_actors,
+			   u32 total_req_power, u32 power_range)
 {
-	u32 extra_power, capped_extra_power;
+	u32 capped_extra_power = 0;
+	u32 extra_power = 0;
 	int i;
 
 	/*
@@ -341,24 +360,23 @@ static void divvy_up_power(u32 *req_power, u32 *max_power, int num_actors,
 	if (!total_req_power)
 		total_req_power = 1;
 
-	capped_extra_power = 0;
-	extra_power = 0;
 	for (i = 0; i < num_actors; i++) {
-		u64 req_range = (u64)req_power[i] * power_range;
+		struct power_actor *pa = &power[i];
+		u64 req_range = (u64)pa->req_power * power_range;
 
-		granted_power[i] = DIV_ROUND_CLOSEST_ULL(req_range,
-							 total_req_power);
+		pa->granted_power = DIV_ROUND_CLOSEST_ULL(req_range,
+							  total_req_power);
 
-		if (granted_power[i] > max_power[i]) {
-			extra_power += granted_power[i] - max_power[i];
-			granted_power[i] = max_power[i];
+		if (pa->granted_power > pa->max_power) {
+			extra_power += pa->granted_power - pa->max_power;
+			pa->granted_power = pa->max_power;
 		}
 
-		extra_actor_power[i] = max_power[i] - granted_power[i];
-		capped_extra_power += extra_actor_power[i];
+		pa->extra_actor_power = pa->max_power - pa->granted_power;
+		capped_extra_power += pa->extra_actor_power;
 	}
 
-	if (!extra_power)
+	if (!extra_power || !capped_extra_power)
 		return;
 
 	/*
@@ -366,127 +384,95 @@ static void divvy_up_power(u32 *req_power, u32 *max_power, int num_actors,
 	 * how far they are from the max
 	 */
 	extra_power = min(extra_power, capped_extra_power);
-	if (capped_extra_power > 0)
-		for (i = 0; i < num_actors; i++) {
-			u64 extra_range = (u64)extra_actor_power[i] * extra_power;
-			granted_power[i] += DIV_ROUND_CLOSEST_ULL(extra_range,
-							 capped_extra_power);
-		}
+
+	for (i = 0; i < num_actors; i++) {
+		struct power_actor *pa = &power[i];
+		u64 extra_range = pa->extra_actor_power;
+
+		extra_range *= extra_power;
+		pa->granted_power += DIV_ROUND_CLOSEST_ULL(extra_range,
+						capped_extra_power);
+	}
 }
 
-static int allocate_power(struct thermal_zone_device *tz,
-			  int control_temp)
+static int allocate_power(struct thermal_zone_device *tz, int control_temp)
 {
-	struct thermal_instance *instance;
 	struct power_allocator_params *params = tz->governor_data;
-	const struct thermal_trip *trip_max_desired_temperature =
-					params->trip_max_desired_temperature;
-	u32 *req_power, *max_power, *granted_power, *extra_actor_power;
-	u32 *weighted_req_power;
-	u32 total_req_power, max_allocatable_power, total_weighted_req_power;
-	u32 total_granted_power, power_range;
-	int i, num_actors, total_weight, ret = 0;
-
-	num_actors = 0;
-	total_weight = 0;
-	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
-		if ((instance->trip == trip_max_desired_temperature) &&
-		    cdev_is_power_actor(instance->cdev)) {
-			num_actors++;
-			total_weight += instance->weight;
-		}
-	}
+	unsigned int num_actors = params->num_actors;
+	struct power_actor *power = params->power;
+	struct thermal_cooling_device *cdev;
+	struct thermal_instance *instance;
+	u32 total_weighted_req_power = 0;
+	u32 max_allocatable_power = 0;
+	u32 total_granted_power = 0;
+	u32 total_req_power = 0;
+	u32 power_range, weight;
+	int i = 0, ret;
 
 	if (!num_actors)
 		return -ENODEV;
 
-	/*
-	 * We need to allocate five arrays of the same size:
-	 * req_power, max_power, granted_power, extra_actor_power and
-	 * weighted_req_power.  They are going to be needed until this
-	 * function returns.  Allocate them all in one go to simplify
-	 * the allocation and deallocation logic.
-	 */
-	BUILD_BUG_ON(sizeof(*req_power) != sizeof(*max_power));
-	BUILD_BUG_ON(sizeof(*req_power) != sizeof(*granted_power));
-	BUILD_BUG_ON(sizeof(*req_power) != sizeof(*extra_actor_power));
-	BUILD_BUG_ON(sizeof(*req_power) != sizeof(*weighted_req_power));
-	req_power = kcalloc(num_actors * 5, sizeof(*req_power), GFP_KERNEL);
-	if (!req_power)
-		return -ENOMEM;
-
-	max_power = &req_power[num_actors];
-	granted_power = &req_power[2 * num_actors];
-	extra_actor_power = &req_power[3 * num_actors];
-	weighted_req_power = &req_power[4 * num_actors];
-
-	i = 0;
-	total_weighted_req_power = 0;
-	total_req_power = 0;
-	max_allocatable_power = 0;
+	/* Clean all buffers for new power estimations */
+	memset(power, 0, params->buffer_size);
 
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
-		int weight;
-		struct thermal_cooling_device *cdev = instance->cdev;
+		struct power_actor *pa = &power[i];
 
-		if (instance->trip != trip_max_desired_temperature)
+		if (!power_actor_is_valid(params, instance))
 			continue;
 
-		if (!cdev_is_power_actor(cdev))
-			continue;
+		cdev = instance->cdev;
 
-		if (cdev->ops->get_requested_power(cdev, &req_power[i]))
+		ret = cdev->ops->get_requested_power(cdev, &pa->req_power);
+		if (ret)
 			continue;
 
-		if (!total_weight)
+		if (!params->total_weight)
 			weight = 1 << FRAC_BITS;
 		else
 			weight = instance->weight;
 
-		weighted_req_power[i] = frac_to_int(weight * req_power[i]);
+		pa->weighted_req_power = frac_to_int(weight * pa->req_power);
 
-		if (cdev->ops->state2power(cdev, instance->lower,
-					   &max_power[i]))
+		ret = cdev->ops->state2power(cdev, instance->lower,
+					     &pa->max_power);
+		if (ret)
 			continue;
 
-		total_req_power += req_power[i];
-		max_allocatable_power += max_power[i];
-		total_weighted_req_power += weighted_req_power[i];
+		total_req_power += pa->req_power;
+		max_allocatable_power += pa->max_power;
+		total_weighted_req_power += pa->weighted_req_power;
 
 		i++;
 	}
 
 	power_range = pid_controller(tz, control_temp, max_allocatable_power);
 
-	divvy_up_power(weighted_req_power, max_power, num_actors,
-		       total_weighted_req_power, power_range, granted_power,
-		       extra_actor_power);
+	divvy_up_power(power, num_actors, total_weighted_req_power,
+		       power_range);
 
-	total_granted_power = 0;
 	i = 0;
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
-		if (instance->trip != trip_max_desired_temperature)
-			continue;
+		struct power_actor *pa = &power[i];
 
-		if (!cdev_is_power_actor(instance->cdev))
+		if (!power_actor_is_valid(params, instance))
 			continue;
 
 		power_actor_set_power(instance->cdev, instance,
-				      granted_power[i]);
-		total_granted_power += granted_power[i];
+				      pa->granted_power);
+		total_granted_power += pa->granted_power;
 
+		trace_thermal_power_actor(tz, i, pa->req_power,
+					  pa->granted_power);
 		i++;
 	}
 
-	trace_thermal_power_allocator(tz, req_power, total_req_power,
-				      granted_power, total_granted_power,
+	trace_thermal_power_allocator(tz, total_req_power, total_granted_power,
 				      num_actors, power_range,
 				      max_allocatable_power, tz->temperature,
 				      control_temp - tz->temperature);
 
-	kfree(req_power);
-
-	return ret;
+	return 0;
 }
 
 /**
@@ -531,13 +517,13 @@ static void get_governor_trips(struct thermal_zone_device *tz,
 
 	if (last_passive) {
 		params->trip_switch_on = first_passive;
-		params->trip_max_desired_temperature = last_passive;
+		params->trip_max = last_passive;
 	} else if (first_passive) {
 		params->trip_switch_on = NULL;
-		params->trip_max_desired_temperature = first_passive;
+		params->trip_max = first_passive;
 	} else {
 		params->trip_switch_on = NULL;
-		params->trip_max_desired_temperature = last_active;
+		params->trip_max = last_active;
 	}
 }
 
@@ -549,19 +535,19 @@ static void reset_pid_controller(struct power_allocator_params *params)
 
 static void allow_maximum_power(struct thermal_zone_device *tz, bool update)
 {
-	struct thermal_instance *instance;
 	struct power_allocator_params *params = tz->governor_data;
+	struct thermal_cooling_device *cdev;
+	struct thermal_instance *instance;
 	u32 req_power;
 
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
-		struct thermal_cooling_device *cdev = instance->cdev;
-
-		if (instance->trip != params->trip_max_desired_temperature ||
-		    (!cdev_is_power_actor(instance->cdev)))
+		if (!power_actor_is_valid(params, instance))
 			continue;
 
+		cdev = instance->cdev;
+
 		instance->target = 0;
-		mutex_lock(&instance->cdev->lock);
+		mutex_lock(&cdev->lock);
 		/*
 		 * Call for updating the cooling devices local stats and avoid
 		 * periods of dozen of seconds when those have not been
@@ -570,9 +556,9 @@ static void allow_maximum_power(struct thermal_zone_device *tz, bool update)
 		cdev->ops->get_requested_power(cdev, &req_power);
 
 		if (update)
-			__thermal_cdev_update(instance->cdev);
+			__thermal_cdev_update(cdev);
 
-		mutex_unlock(&instance->cdev->lock);
+		mutex_unlock(&cdev->lock);
 	}
 }
 
@@ -580,30 +566,99 @@ static void allow_maximum_power(struct thermal_zone_device *tz, bool update)
  * check_power_actors() - Check all cooling devices and warn when they are
  *			not power actors
  * @tz:		thermal zone to operate on
+ * @params:	power allocator private data
  *
  * Check all cooling devices in the @tz and warn every time they are missing
  * power actor API. The warning should help to investigate the issue, which
  * could be e.g. lack of Energy Model for a given device.
  *
- * Return: 0 on success, -EINVAL if any cooling device does not implement
- * the power actor API.
+ * If all of the cooling devices currently attached to @tz implement the power
+ * actor API, return the number of them (which may be 0, because some cooling
+ * devices may be attached later). Otherwise, return -EINVAL.
  */
-static int check_power_actors(struct thermal_zone_device *tz)
+static int check_power_actors(struct thermal_zone_device *tz,
+			      struct power_allocator_params *params)
 {
 	struct thermal_instance *instance;
 	int ret = 0;
 
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+		if (instance->trip != params->trip_max)
+			continue;
+
 		if (!cdev_is_power_actor(instance->cdev)) {
 			dev_warn(&tz->device, "power_allocator: %s is not a power actor\n",
 				 instance->cdev->type);
-			ret = -EINVAL;
+			return -EINVAL;
 		}
+		ret++;
 	}
 
 	return ret;
 }
 
+static int allocate_actors_buffer(struct power_allocator_params *params,
+				  int num_actors)
+{
+	int ret;
+
+	kfree(params->power);
+
+	/* There might be no cooling devices yet. */
+	if (!num_actors) {
+		ret = -EINVAL;
+		goto clean_state;
+	}
+
+	params->power = kcalloc(num_actors, sizeof(struct power_actor),
+				GFP_KERNEL);
+	if (!params->power) {
+		ret = -ENOMEM;
+		goto clean_state;
+	}
+
+	params->num_actors = num_actors;
+	params->buffer_size = num_actors * sizeof(struct power_actor);
+
+	return 0;
+
+clean_state:
+	params->num_actors = 0;
+	params->buffer_size = 0;
+	params->power = NULL;
+	return ret;
+}
+
+static void power_allocator_update_tz(struct thermal_zone_device *tz,
+				      enum thermal_notify_event reason)
+{
+	struct power_allocator_params *params = tz->governor_data;
+	struct thermal_instance *instance;
+	int num_actors = 0;
+
+	switch (reason) {
+	case THERMAL_TZ_BIND_CDEV:
+	case THERMAL_TZ_UNBIND_CDEV:
+		list_for_each_entry(instance, &tz->thermal_instances, tz_node)
+			if (power_actor_is_valid(params, instance))
+				num_actors++;
+
+		if (num_actors == params->num_actors)
+			return;
+
+		allocate_actors_buffer(params, num_actors);
+		break;
+	case THERMAL_INSTANCE_WEIGHT_CHANGED:
+		params->total_weight = 0;
+		list_for_each_entry(instance, &tz->thermal_instances, tz_node)
+			if (power_actor_is_valid(params, instance))
+				params->total_weight += instance->weight;
+		break;
+	default:
+		break;
+	}
+}
+
 /**
  * power_allocator_bind() - bind the power_allocator governor to a thermal zone
  * @tz:	thermal zone to bind it to
@@ -616,17 +671,34 @@ static int check_power_actors(struct thermal_zone_device *tz)
  */
 static int power_allocator_bind(struct thermal_zone_device *tz)
 {
-	int ret;
 	struct power_allocator_params *params;
-
-	ret = check_power_actors(tz);
-	if (ret)
-		return ret;
+	int ret;
 
 	params = kzalloc(sizeof(*params), GFP_KERNEL);
 	if (!params)
 		return -ENOMEM;
 
+	get_governor_trips(tz, params);
+	if (!params->trip_max) {
+		dev_warn(&tz->device, "power_allocator: missing trip_max\n");
+		kfree(params);
+		return -EINVAL;
+	}
+
+	ret = check_power_actors(tz, params);
+	if (ret < 0) {
+		dev_warn(&tz->device, "power_allocator: binding failed\n");
+		kfree(params);
+		return ret;
+	}
+
+	ret = allocate_actors_buffer(params, ret);
+	if (ret) {
+		dev_warn(&tz->device, "power_allocator: allocation failed\n");
+		kfree(params);
+		return ret;
+	}
+
 	if (!tz->tzp) {
 		tz->tzp = kzalloc(sizeof(*tz->tzp), GFP_KERNEL);
 		if (!tz->tzp) {
@@ -640,14 +712,9 @@ static int power_allocator_bind(struct thermal_zone_device *tz)
 	if (!tz->tzp->sustainable_power)
 		dev_warn(&tz->device, "power_allocator: sustainable_power will be estimated\n");
 
-	get_governor_trips(tz, params);
-
-	if (params->trip_max_desired_temperature) {
-		int temp = params->trip_max_desired_temperature->temperature;
-
-		estimate_pid_constants(tz, tz->tzp->sustainable_power,
-				       params->trip_switch_on, temp);
-	}
+	estimate_pid_constants(tz, tz->tzp->sustainable_power,
+			       params->trip_switch_on,
+			       params->trip_max->temperature);
 
 	reset_pid_controller(params);
 
@@ -656,6 +723,7 @@ static int power_allocator_bind(struct thermal_zone_device *tz)
 	return 0;
 
 free_params:
+	kfree(params->power);
 	kfree(params);
 
 	return ret;
@@ -672,6 +740,7 @@ static void power_allocator_unbind(struct thermal_zone_device *tz)
 		tz->tzp = NULL;
 	}
 
+	kfree(params->power);
 	kfree(tz->governor_data);
 	tz->governor_data = NULL;
 }
@@ -688,7 +757,7 @@ static int power_allocator_throttle(struct thermal_zone_device *tz,
 	 * We get called for every trip point but we only need to do
 	 * our calculations once
 	 */
-	if (trip != params->trip_max_desired_temperature)
+	if (trip != params->trip_max)
 		return 0;
 
 	trip = params->trip_switch_on;
@@ -702,7 +771,7 @@ static int power_allocator_throttle(struct thermal_zone_device *tz,
 
 	tz->passive = 1;
 
-	return allocate_power(tz, params->trip_max_desired_temperature->temperature);
+	return allocate_power(tz, params->trip_max->temperature);
 }
 
 static struct thermal_governor thermal_gov_power_allocator = {
@@ -710,5 +779,6 @@ static struct thermal_governor thermal_gov_power_allocator = {
 	.bind_to_tz	= power_allocator_bind,
 	.unbind_from_tz	= power_allocator_unbind,
 	.throttle	= power_allocator_throttle,
+	.update_tz	= power_allocator_update_tz,
 };
 THERMAL_GOVERNOR_DECLARE(thermal_gov_power_allocator);
diff --git a/drivers/thermal/intel/Kconfig b/drivers/thermal/intel/Kconfig
index ecd7e07eece0..b43953b5539f 100644
--- a/drivers/thermal/intel/Kconfig
+++ b/drivers/thermal/intel/Kconfig
@@ -85,7 +85,7 @@ config INTEL_BXT_PMIC_THERMAL
 config INTEL_PCH_THERMAL
 	tristate "Intel PCH Thermal Reporting Driver"
 	depends on X86 && PCI
-	select THERMAL_ACPI if ACPI
+	select ACPI_THERMAL_LIB if ACPI
 	help
 	  Enable this to support thermal reporting on certain intel PCHs.
 	  Thermal reporting device will provide temperature reading,
diff --git a/drivers/thermal/intel/int340x_thermal/Kconfig b/drivers/thermal/intel/int340x_thermal/Kconfig
index 300ea53e9b33..e76b13e44d03 100644
--- a/drivers/thermal/intel/int340x_thermal/Kconfig
+++ b/drivers/thermal/intel/int340x_thermal/Kconfig
@@ -9,7 +9,7 @@ config INT340X_THERMAL
 	select THERMAL_GOV_USER_SPACE
 	select ACPI_THERMAL_REL
 	select ACPI_FAN
-	select THERMAL_ACPI
+	select ACPI_THERMAL_LIB
 	select INTEL_SOC_DTS_IOSF_CORE
 	select INTEL_TCC
 	select PROC_THERMAL_MMIO_RAPL if POWERCAP
diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
index a03b67579dd9..3e4bfe817fac 100644
--- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
+++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
@@ -225,7 +225,8 @@ EXPORT_SYMBOL_GPL(int340x_thermal_zone_remove);
 
 static int int340x_update_one_trip(struct thermal_trip *trip, void *arg)
 {
-	struct acpi_device *zone_adev = arg;
+	struct int34x_thermal_zone *int34x_zone = arg;
+	struct acpi_device *zone_adev = int34x_zone->adev;
 	int temp, err;
 
 	switch (trip->type) {
@@ -249,14 +250,15 @@ static int int340x_update_one_trip(struct thermal_trip *trip, void *arg)
 	if (err)
 		temp = THERMAL_TEMP_INVALID;
 
-	trip->temperature = temp;
+	thermal_zone_set_trip_temp(int34x_zone->zone, trip, temp);
+
 	return 0;
 }
 
 void int340x_thermal_update_trips(struct int34x_thermal_zone *int34x_zone)
 {
 	thermal_zone_for_each_trip(int34x_zone->zone, int340x_update_one_trip,
-				   int34x_zone->adev);
+				   int34x_zone);
 }
 EXPORT_SYMBOL_GPL(int340x_thermal_update_trips);
 
diff --git a/drivers/thermal/intel/intel_hfi.c b/drivers/thermal/intel/intel_hfi.c
index c69db6c90869..22445403b520 100644
--- a/drivers/thermal/intel/intel_hfi.c
+++ b/drivers/thermal/intel/intel_hfi.c
@@ -24,6 +24,7 @@
 #include <linux/bitops.h>
 #include <linux/cpufeature.h>
 #include <linux/cpumask.h>
+#include <linux/delay.h>
 #include <linux/gfp.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
@@ -347,6 +348,52 @@ static void init_hfi_instance(struct hfi_instance *hfi_instance)
 	hfi_instance->data = hfi_instance->hdr + hfi_features.hdr_size;
 }
 
+/* Caller must hold hfi_instance_lock. */
+static void hfi_enable(void)
+{
+	u64 msr_val;
+
+	rdmsrl(MSR_IA32_HW_FEEDBACK_CONFIG, msr_val);
+	msr_val |= HW_FEEDBACK_CONFIG_HFI_ENABLE_BIT;
+	wrmsrl(MSR_IA32_HW_FEEDBACK_CONFIG, msr_val);
+}
+
+static void hfi_set_hw_table(struct hfi_instance *hfi_instance)
+{
+	phys_addr_t hw_table_pa;
+	u64 msr_val;
+
+	hw_table_pa = virt_to_phys(hfi_instance->hw_table);
+	msr_val = hw_table_pa | HW_FEEDBACK_PTR_VALID_BIT;
+	wrmsrl(MSR_IA32_HW_FEEDBACK_PTR, msr_val);
+}
+
+/* Caller must hold hfi_instance_lock. */
+static void hfi_disable(void)
+{
+	u64 msr_val;
+	int i;
+
+	rdmsrl(MSR_IA32_HW_FEEDBACK_CONFIG, msr_val);
+	msr_val &= ~HW_FEEDBACK_CONFIG_HFI_ENABLE_BIT;
+	wrmsrl(MSR_IA32_HW_FEEDBACK_CONFIG, msr_val);
+
+	/*
+	 * Wait for hardware to acknowledge the disabling of HFI. Some
+	 * processors may not do it. Wait for ~2ms. This is a reasonable
+	 * time for hardware to complete any pending actions on the HFI
+	 * memory.
+	 */
+	for (i = 0; i < 2000; i++) {
+		rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val);
+		if (msr_val & PACKAGE_THERM_STATUS_HFI_UPDATED)
+			break;
+
+		udelay(1);
+		cpu_relax();
+	}
+}
+
 /**
  * intel_hfi_online() - Enable HFI on @cpu
  * @cpu:	CPU in which the HFI will be enabled
@@ -364,8 +411,6 @@ void intel_hfi_online(unsigned int cpu)
 {
 	struct hfi_instance *hfi_instance;
 	struct hfi_cpu_info *info;
-	phys_addr_t hw_table_pa;
-	u64 msr_val;
 	u16 die_id;
 
 	/* Nothing to do if hfi_instances are missing. */
@@ -392,25 +437,26 @@ void intel_hfi_online(unsigned int cpu)
 	/*
 	 * Now check if the HFI instance of the package/die of @cpu has been
 	 * initialized (by checking its header). In such case, all we have to
-	 * do is to add @cpu to this instance's cpumask.
+	 * do is to add @cpu to this instance's cpumask and enable the instance
+	 * if needed.
 	 */
 	mutex_lock(&hfi_instance_lock);
-	if (hfi_instance->hdr) {
-		cpumask_set_cpu(cpu, hfi_instance->cpus);
-		goto unlock;
-	}
+	if (hfi_instance->hdr)
+		goto enable;
 
 	/*
 	 * Hardware is programmed with the physical address of the first page
 	 * frame of the table. Hence, the allocated memory must be page-aligned.
+	 *
+	 * Some processors do not forget the initial address of the HFI table
+	 * even after having been reprogrammed. Keep using the same pages. Do
+	 * not free them.
 	 */
 	hfi_instance->hw_table = alloc_pages_exact(hfi_features.nr_table_pages,
 						   GFP_KERNEL | __GFP_ZERO);
 	if (!hfi_instance->hw_table)
 		goto unlock;
 
-	hw_table_pa = virt_to_phys(hfi_instance->hw_table);
-
 	/*
 	 * Allocate memory to keep a local copy of the table that
 	 * hardware generates.
@@ -420,31 +466,20 @@ void intel_hfi_online(unsigned int cpu)
 	if (!hfi_instance->local_table)
 		goto free_hw_table;
 
-	/*
-	 * Program the address of the feedback table of this die/package. On
-	 * some processors, hardware remembers the old address of the HFI table
-	 * even after having been reprogrammed and re-enabled. Thus, do not free
-	 * the pages allocated for the table or reprogram the hardware with a
-	 * new base address. Namely, program the hardware only once.
-	 */
-	msr_val = hw_table_pa | HW_FEEDBACK_PTR_VALID_BIT;
-	wrmsrl(MSR_IA32_HW_FEEDBACK_PTR, msr_val);
-
 	init_hfi_instance(hfi_instance);
 
 	INIT_DELAYED_WORK(&hfi_instance->update_work, hfi_update_work_fn);
 	raw_spin_lock_init(&hfi_instance->table_lock);
 	raw_spin_lock_init(&hfi_instance->event_lock);
 
+enable:
 	cpumask_set_cpu(cpu, hfi_instance->cpus);
 
-	/*
-	 * Enable the hardware feedback interface and never disable it. See
-	 * comment on programming the address of the table.
-	 */
-	rdmsrl(MSR_IA32_HW_FEEDBACK_CONFIG, msr_val);
-	msr_val |= HW_FEEDBACK_CONFIG_HFI_ENABLE_BIT;
-	wrmsrl(MSR_IA32_HW_FEEDBACK_CONFIG, msr_val);
+	/* Enable this HFI instance if this is its first online CPU. */
+	if (cpumask_weight(hfi_instance->cpus) == 1) {
+		hfi_set_hw_table(hfi_instance);
+		hfi_enable();
+	}
 
 unlock:
 	mutex_unlock(&hfi_instance_lock);
@@ -484,6 +519,10 @@ void intel_hfi_offline(unsigned int cpu)
 
 	mutex_lock(&hfi_instance_lock);
 	cpumask_clear_cpu(cpu, hfi_instance->cpus);
+
+	if (!cpumask_weight(hfi_instance->cpus))
+		hfi_disable();
+
 	mutex_unlock(&hfi_instance_lock);
 }
 
diff --git a/drivers/thermal/loongson2_thermal.c b/drivers/thermal/loongson2_thermal.c
index 133098dc0854..99ca0c7bc41c 100644
--- a/drivers/thermal/loongson2_thermal.c
+++ b/drivers/thermal/loongson2_thermal.c
@@ -127,7 +127,7 @@ static int loongson2_thermal_probe(struct platform_device *pdev)
 		if (!IS_ERR(tzd))
 			break;
 
-		if (PTR_ERR(tzd) != ENODEV)
+		if (PTR_ERR(tzd) != -ENODEV)
 			continue;
 
 		return dev_err_probe(dev, PTR_ERR(tzd), "failed to register");
diff --git a/drivers/thermal/samsung/exynos_tmu.c b/drivers/thermal/samsung/exynos_tmu.c
index 123ec81e1943..6482513bfe66 100644
--- a/drivers/thermal/samsung/exynos_tmu.c
+++ b/drivers/thermal/samsung/exynos_tmu.c
@@ -138,12 +138,10 @@ enum soc_type {
 /**
  * struct exynos_tmu_data : A structure to hold the private data of the TMU
  *			    driver
- * @id: identifier of the one instance of the TMU controller.
  * @base: base address of the single instance of the TMU controller.
  * @base_second: base address of the common registers of the TMU controller.
  * @irq: irq number of the TMU controller.
  * @soc: id of the SOC type.
- * @irq_work: pointer to the irq work structure.
  * @lock: lock to implement synchronization.
  * @clk: pointer to the clock structure.
  * @clk_sec: pointer to the clock structure for accessing the base_second.
@@ -159,13 +157,13 @@ enum soc_type {
  * @reference_voltage: reference voltage of amplifier
  *	in the positive-TC generator block
  *	0 < reference_voltage <= 31
- * @regulator: pointer to the TMU regulator structure.
- * @reg_conf: pointer to structure to register with core thermal.
  * @tzd: pointer to thermal_zone_device structure
- * @ntrip: number of supported trip points.
  * @enabled: current status of TMU device
- * @tmu_set_trip_temp: SoC specific method to set trip (rising threshold)
- * @tmu_set_trip_hyst: SoC specific to set hysteresis (falling threshold)
+ * @tmu_set_low_temp: SoC specific method to set trip (falling threshold)
+ * @tmu_set_high_temp: SoC specific method to set trip (rising threshold)
+ * @tmu_set_crit_temp: SoC specific method to set critical temperature
+ * @tmu_disable_low: SoC specific method to disable an interrupt (falling threshold)
+ * @tmu_disable_high: SoC specific method to disable an interrupt (rising threshold)
  * @tmu_initialize: SoC specific TMU initialization method
  * @tmu_control: SoC specific TMU control method
  * @tmu_read: SoC specific TMU temperature read method
@@ -173,12 +171,10 @@ enum soc_type {
  * @tmu_clear_irqs: SoC specific TMU interrupts clearing method
  */
 struct exynos_tmu_data {
-	int id;
 	void __iomem *base;
 	void __iomem *base_second;
 	int irq;
 	enum soc_type soc;
-	struct work_struct irq_work;
 	struct mutex lock;
 	struct clk *clk, *clk_sec, *sclk;
 	u32 cal_type;
@@ -188,15 +184,14 @@ struct exynos_tmu_data {
 	u16 temp_error1, temp_error2;
 	u8 gain;
 	u8 reference_voltage;
-	struct regulator *regulator;
 	struct thermal_zone_device *tzd;
-	unsigned int ntrip;
 	bool enabled;
 
-	void (*tmu_set_trip_temp)(struct exynos_tmu_data *data, int trip,
-				 u8 temp);
-	void (*tmu_set_trip_hyst)(struct exynos_tmu_data *data, int trip,
-				 u8 temp, u8 hyst);
+	void (*tmu_set_low_temp)(struct exynos_tmu_data *data, u8 temp);
+	void (*tmu_set_high_temp)(struct exynos_tmu_data *data, u8 temp);
+	void (*tmu_set_crit_temp)(struct exynos_tmu_data *data, u8 temp);
+	void (*tmu_disable_low)(struct exynos_tmu_data *data);
+	void (*tmu_disable_high)(struct exynos_tmu_data *data);
 	void (*tmu_initialize)(struct platform_device *pdev);
 	void (*tmu_control)(struct platform_device *pdev, bool on);
 	int (*tmu_read)(struct exynos_tmu_data *data);
@@ -258,25 +253,8 @@ static void sanitize_temp_error(struct exynos_tmu_data *data, u32 trim_info)
 static int exynos_tmu_initialize(struct platform_device *pdev)
 {
 	struct exynos_tmu_data *data = platform_get_drvdata(pdev);
-	struct thermal_zone_device *tzd = data->tzd;
-	int num_trips = thermal_zone_get_num_trips(tzd);
 	unsigned int status;
-	int ret = 0, temp;
-
-	ret = thermal_zone_get_crit_temp(tzd, &temp);
-	if (ret && data->soc != SOC_ARCH_EXYNOS5433) { /* FIXME */
-		dev_err(&pdev->dev,
-			"No CRITICAL trip point defined in device tree!\n");
-		goto out;
-	}
-
-	if (num_trips > data->ntrip) {
-		dev_info(&pdev->dev,
-			 "More trip points than supported by this TMU.\n");
-		dev_info(&pdev->dev,
-			 "%d trip points should be configured in polling mode.\n",
-			 num_trips - data->ntrip);
-	}
+	int ret = 0;
 
 	mutex_lock(&data->lock);
 	clk_enable(data->clk);
@@ -287,34 +265,44 @@ static int exynos_tmu_initialize(struct platform_device *pdev)
 	if (!status) {
 		ret = -EBUSY;
 	} else {
-		int i, ntrips =
-			min_t(int, num_trips, data->ntrip);
-
 		data->tmu_initialize(pdev);
+		data->tmu_clear_irqs(data);
+	}
 
-		/* Write temperature code for rising and falling threshold */
-		for (i = 0; i < ntrips; i++) {
+	if (!IS_ERR(data->clk_sec))
+		clk_disable(data->clk_sec);
+	clk_disable(data->clk);
+	mutex_unlock(&data->lock);
 
-			struct thermal_trip trip;
+	return ret;
+}
 
-			ret = thermal_zone_get_trip(tzd, i, &trip);
-			if (ret)
-				goto err;
+static int exynos_thermal_zone_configure(struct platform_device *pdev)
+{
+	struct exynos_tmu_data *data = platform_get_drvdata(pdev);
+	struct thermal_zone_device *tzd = data->tzd;
+	int ret, temp;
 
-			data->tmu_set_trip_temp(data, i, trip.temperature / MCELSIUS);
-			data->tmu_set_trip_hyst(data, i, trip.temperature / MCELSIUS,
-						trip.hysteresis / MCELSIUS);
-		}
+	ret = thermal_zone_get_crit_temp(tzd, &temp);
+	if (ret) {
+		/* FIXME: Remove this special case */
+		if (data->soc == SOC_ARCH_EXYNOS5433)
+			return 0;
 
-		data->tmu_clear_irqs(data);
+		dev_err(&pdev->dev,
+			"No CRITICAL trip point defined in device tree!\n");
+		return ret;
 	}
-err:
+
+	mutex_lock(&data->lock);
+	clk_enable(data->clk);
+
+	data->tmu_set_crit_temp(data, temp / MCELSIUS);
+
 	clk_disable(data->clk);
 	mutex_unlock(&data->lock);
-	if (!IS_ERR(data->clk_sec))
-		clk_disable(data->clk_sec);
-out:
-	return ret;
+
+	return 0;
 }
 
 static u32 get_con_reg(struct exynos_tmu_data *data, u32 con)
@@ -347,30 +335,74 @@ static void exynos_tmu_control(struct platform_device *pdev, bool on)
 	mutex_unlock(&data->lock);
 }
 
-static void exynos4210_tmu_set_trip_temp(struct exynos_tmu_data *data,
-					 int trip_id, u8 temp)
+static void exynos_tmu_update_bit(struct exynos_tmu_data *data, int reg_off,
+				  int bit_off, bool enable)
+{
+	u32 interrupt_en;
+
+	interrupt_en = readl(data->base + reg_off);
+	if (enable)
+		interrupt_en |= BIT(bit_off);
+	else
+		interrupt_en &= ~BIT(bit_off);
+	writel(interrupt_en, data->base + reg_off);
+}
+
+static void exynos_tmu_update_temp(struct exynos_tmu_data *data, int reg_off,
+				   int bit_off, u8 temp)
 {
-	struct thermal_trip trip;
-	u8 ref, th_code;
+	u16 tmu_temp_mask;
+	u32 th;
 
-	if (thermal_zone_get_trip(data->tzd, 0, &trip))
-		return;
+	tmu_temp_mask =
+		(data->soc == SOC_ARCH_EXYNOS7) ? EXYNOS7_TMU_TEMP_MASK
+						: EXYNOS_TMU_TEMP_MASK;
 
-	ref = trip.temperature / MCELSIUS;
+	th = readl(data->base + reg_off);
+	th &= ~(tmu_temp_mask << bit_off);
+	th |= temp_to_code(data, temp) << bit_off;
+	writel(th, data->base + reg_off);
+}
 
-	if (trip_id == 0) {
-		th_code = temp_to_code(data, ref);
-		writeb(th_code, data->base + EXYNOS4210_TMU_REG_THRESHOLD_TEMP);
-	}
+static void exynos4210_tmu_set_low_temp(struct exynos_tmu_data *data, u8 temp)
+{
+	/*
+	 * Failing thresholds are not supported on Exynos 4210.
+	 * We use polling instead.
+	 */
+}
+
+static void exynos4210_tmu_set_high_temp(struct exynos_tmu_data *data, u8 temp)
+{
+	temp = temp_to_code(data, temp);
+	writeb(temp, data->base + EXYNOS4210_TMU_REG_TRIG_LEVEL0 + 4);
+	exynos_tmu_update_bit(data, EXYNOS_TMU_REG_INTEN,
+			      EXYNOS_TMU_INTEN_RISE0_SHIFT + 4, true);
+}
 
-	temp -= ref;
-	writeb(temp, data->base + EXYNOS4210_TMU_REG_TRIG_LEVEL0 + trip_id * 4);
+static void exynos4210_tmu_disable_low(struct exynos_tmu_data *data)
+{
+	/* Again, this is handled by polling. */
 }
 
-/* failing thresholds are not supported on Exynos4210 */
-static void exynos4210_tmu_set_trip_hyst(struct exynos_tmu_data *data,
-					 int trip, u8 temp, u8 hyst)
+static void exynos4210_tmu_disable_high(struct exynos_tmu_data *data)
 {
+	exynos_tmu_update_bit(data, EXYNOS_TMU_REG_INTEN,
+			      EXYNOS_TMU_INTEN_RISE0_SHIFT + 4, false);
+}
+
+static void exynos4210_tmu_set_crit_temp(struct exynos_tmu_data *data, u8 temp)
+{
+	/*
+	 * Hardware critical temperature handling is not supported on Exynos 4210.
+	 * We still set the critical temperature threshold, but this is only to
+	 * make sure it is handled as soon as possible. It is just a normal interrupt.
+	 */
+
+	temp = temp_to_code(data, temp);
+	writeb(temp, data->base + EXYNOS4210_TMU_REG_TRIG_LEVEL0 + 12);
+	exynos_tmu_update_bit(data, EXYNOS_TMU_REG_INTEN,
+			      EXYNOS_TMU_INTEN_RISE0_SHIFT + 12, true);
 }
 
 static void exynos4210_tmu_initialize(struct platform_device *pdev)
@@ -378,35 +410,35 @@ static void exynos4210_tmu_initialize(struct platform_device *pdev)
 	struct exynos_tmu_data *data = platform_get_drvdata(pdev);
 
 	sanitize_temp_error(data, readl(data->base + EXYNOS_TMU_REG_TRIMINFO));
+
+	writeb(0, data->base + EXYNOS4210_TMU_REG_THRESHOLD_TEMP);
 }
 
-static void exynos4412_tmu_set_trip_temp(struct exynos_tmu_data *data,
-					 int trip, u8 temp)
+static void exynos4412_tmu_set_low_temp(struct exynos_tmu_data *data, u8 temp)
 {
-	u32 th, con;
-
-	th = readl(data->base + EXYNOS_THD_TEMP_RISE);
-	th &= ~(0xff << 8 * trip);
-	th |= temp_to_code(data, temp) << 8 * trip;
-	writel(th, data->base + EXYNOS_THD_TEMP_RISE);
+	exynos_tmu_update_temp(data, EXYNOS_THD_TEMP_FALL, 0, temp);
+	exynos_tmu_update_bit(data, EXYNOS_TMU_REG_INTEN,
+			      EXYNOS_TMU_INTEN_FALL0_SHIFT, true);
+}
 
-	if (trip == 3) {
-		con = readl(data->base + EXYNOS_TMU_REG_CONTROL);
-		con |= (1 << EXYNOS_TMU_THERM_TRIP_EN_SHIFT);
-		writel(con, data->base + EXYNOS_TMU_REG_CONTROL);
-	}
+static void exynos4412_tmu_set_high_temp(struct exynos_tmu_data *data, u8 temp)
+{
+	exynos_tmu_update_temp(data, EXYNOS_THD_TEMP_RISE, 8, temp);
+	exynos_tmu_update_bit(data, EXYNOS_TMU_REG_INTEN,
+			      EXYNOS_TMU_INTEN_RISE0_SHIFT + 4, true);
 }
 
-static void exynos4412_tmu_set_trip_hyst(struct exynos_tmu_data *data,
-					 int trip, u8 temp, u8 hyst)
+static void exynos4412_tmu_disable_low(struct exynos_tmu_data *data)
 {
-	u32 th;
+	exynos_tmu_update_bit(data, EXYNOS_TMU_REG_INTEN,
+			      EXYNOS_TMU_INTEN_FALL0_SHIFT, false);
+}
 
-	th = readl(data->base + EXYNOS_THD_TEMP_FALL);
-	th &= ~(0xff << 8 * trip);
-	if (hyst)
-		th |= temp_to_code(data, temp - hyst) << 8 * trip;
-	writel(th, data->base + EXYNOS_THD_TEMP_FALL);
+static void exynos4412_tmu_set_crit_temp(struct exynos_tmu_data *data, u8 temp)
+{
+	exynos_tmu_update_temp(data, EXYNOS_THD_TEMP_RISE, 24, temp);
+	exynos_tmu_update_bit(data, EXYNOS_TMU_REG_CONTROL,
+			      EXYNOS_TMU_THERM_TRIP_EN_SHIFT, true);
 }
 
 static void exynos4412_tmu_initialize(struct platform_device *pdev)
@@ -436,44 +468,39 @@ static void exynos4412_tmu_initialize(struct platform_device *pdev)
 	sanitize_temp_error(data, trim_info);
 }
 
-static void exynos5433_tmu_set_trip_temp(struct exynos_tmu_data *data,
-					 int trip, u8 temp)
+static void exynos5433_tmu_set_low_temp(struct exynos_tmu_data *data, u8 temp)
 {
-	unsigned int reg_off, j;
-	u32 th;
-
-	if (trip > 3) {
-		reg_off = EXYNOS5433_THD_TEMP_RISE7_4;
-		j = trip - 4;
-	} else {
-		reg_off = EXYNOS5433_THD_TEMP_RISE3_0;
-		j = trip;
-	}
+	exynos_tmu_update_temp(data, EXYNOS5433_THD_TEMP_FALL3_0, 0, temp);
+	exynos_tmu_update_bit(data, EXYNOS5433_TMU_REG_INTEN,
+			      EXYNOS_TMU_INTEN_FALL0_SHIFT, true);
+}
 
-	th = readl(data->base + reg_off);
-	th &= ~(0xff << j * 8);
-	th |= (temp_to_code(data, temp) << j * 8);
-	writel(th, data->base + reg_off);
+static void exynos5433_tmu_set_high_temp(struct exynos_tmu_data *data, u8 temp)
+{
+	exynos_tmu_update_temp(data, EXYNOS5433_THD_TEMP_RISE3_0, 8, temp);
+	exynos_tmu_update_bit(data, EXYNOS5433_TMU_REG_INTEN,
+			      EXYNOS7_TMU_INTEN_RISE0_SHIFT + 1, true);
 }
 
-static void exynos5433_tmu_set_trip_hyst(struct exynos_tmu_data *data,
-					 int trip, u8 temp, u8 hyst)
+static void exynos5433_tmu_disable_low(struct exynos_tmu_data *data)
 {
-	unsigned int reg_off, j;
-	u32 th;
+	exynos_tmu_update_bit(data, EXYNOS5433_TMU_REG_INTEN,
+			      EXYNOS_TMU_INTEN_FALL0_SHIFT, false);
+}
 
-	if (trip > 3) {
-		reg_off = EXYNOS5433_THD_TEMP_FALL7_4;
-		j = trip - 4;
-	} else {
-		reg_off = EXYNOS5433_THD_TEMP_FALL3_0;
-		j = trip;
-	}
+static void exynos5433_tmu_disable_high(struct exynos_tmu_data *data)
+{
+	exynos_tmu_update_bit(data, EXYNOS5433_TMU_REG_INTEN,
+			      EXYNOS7_TMU_INTEN_RISE0_SHIFT + 1, false);
+}
 
-	th = readl(data->base + reg_off);
-	th &= ~(0xff << j * 8);
-	th |= (temp_to_code(data, temp - hyst) << j * 8);
-	writel(th, data->base + reg_off);
+static void exynos5433_tmu_set_crit_temp(struct exynos_tmu_data *data, u8 temp)
+{
+	exynos_tmu_update_temp(data, EXYNOS5433_THD_TEMP_RISE7_4, 24, temp);
+	exynos_tmu_update_bit(data, EXYNOS_TMU_REG_CONTROL,
+			      EXYNOS_TMU_THERM_TRIP_EN_SHIFT, true);
+	exynos_tmu_update_bit(data, EXYNOS5433_TMU_REG_INTEN,
+			      EXYNOS7_TMU_INTEN_RISE0_SHIFT + 7, true);
 }
 
 static void exynos5433_tmu_initialize(struct platform_device *pdev)
@@ -509,34 +536,41 @@ static void exynos5433_tmu_initialize(struct platform_device *pdev)
 			cal_type ?  2 : 1);
 }
 
-static void exynos7_tmu_set_trip_temp(struct exynos_tmu_data *data,
-				      int trip, u8 temp)
+static void exynos7_tmu_set_low_temp(struct exynos_tmu_data *data, u8 temp)
 {
-	unsigned int reg_off, bit_off;
-	u32 th;
-
-	reg_off = ((7 - trip) / 2) * 4;
-	bit_off = ((8 - trip) % 2);
+	exynos_tmu_update_temp(data, EXYNOS7_THD_TEMP_FALL7_6 + 12, 0, temp);
+	exynos_tmu_update_bit(data, EXYNOS7_TMU_REG_INTEN,
+			      EXYNOS_TMU_INTEN_FALL0_SHIFT + 0, true);
+}
 
-	th = readl(data->base + EXYNOS7_THD_TEMP_RISE7_6 + reg_off);
-	th &= ~(EXYNOS7_TMU_TEMP_MASK << (16 * bit_off));
-	th |= temp_to_code(data, temp) << (16 * bit_off);
-	writel(th, data->base + EXYNOS7_THD_TEMP_RISE7_6 + reg_off);
+static void exynos7_tmu_set_high_temp(struct exynos_tmu_data *data, u8 temp)
+{
+	exynos_tmu_update_temp(data, EXYNOS7_THD_TEMP_RISE7_6 + 12, 16, temp);
+	exynos_tmu_update_bit(data, EXYNOS7_TMU_REG_INTEN,
+			      EXYNOS7_TMU_INTEN_RISE0_SHIFT + 1, true);
 }
 
-static void exynos7_tmu_set_trip_hyst(struct exynos_tmu_data *data,
-				      int trip, u8 temp, u8 hyst)
+static void exynos7_tmu_disable_low(struct exynos_tmu_data *data)
 {
-	unsigned int reg_off, bit_off;
-	u32 th;
+	exynos_tmu_update_bit(data, EXYNOS7_TMU_REG_INTEN,
+			      EXYNOS_TMU_INTEN_FALL0_SHIFT + 0, false);
+}
 
-	reg_off = ((7 - trip) / 2) * 4;
-	bit_off = ((8 - trip) % 2);
+static void exynos7_tmu_disable_high(struct exynos_tmu_data *data)
+{
+	exynos_tmu_update_bit(data, EXYNOS7_TMU_REG_INTEN,
+			      EXYNOS7_TMU_INTEN_RISE0_SHIFT + 1, false);
+}
 
-	th = readl(data->base + EXYNOS7_THD_TEMP_FALL7_6 + reg_off);
-	th &= ~(EXYNOS7_TMU_TEMP_MASK << (16 * bit_off));
-	th |= temp_to_code(data, temp - hyst) << (16 * bit_off);
-	writel(th, data->base + EXYNOS7_THD_TEMP_FALL7_6 + reg_off);
+static void exynos7_tmu_set_crit_temp(struct exynos_tmu_data *data, u8 temp)
+{
+	/*
+	 * Like Exynos 4210, Exynos 7 does not seem to support critical temperature
+	 * handling in hardware. Again, we still set a separate interrupt for it.
+	 */
+	exynos_tmu_update_temp(data, EXYNOS7_THD_TEMP_RISE7_6 + 0, 16, temp);
+	exynos_tmu_update_bit(data, EXYNOS7_TMU_REG_INTEN,
+			      EXYNOS7_TMU_INTEN_RISE0_SHIFT + 7, true);
 }
 
 static void exynos7_tmu_initialize(struct platform_device *pdev)
@@ -551,95 +585,51 @@ static void exynos7_tmu_initialize(struct platform_device *pdev)
 static void exynos4210_tmu_control(struct platform_device *pdev, bool on)
 {
 	struct exynos_tmu_data *data = platform_get_drvdata(pdev);
-	struct thermal_zone_device *tz = data->tzd;
-	struct thermal_trip trip;
-	unsigned int con, interrupt_en = 0, i;
+	unsigned int con;
 
 	con = get_con_reg(data, readl(data->base + EXYNOS_TMU_REG_CONTROL));
 
-	if (on) {
-		for (i = 0; i < data->ntrip; i++) {
-			if (thermal_zone_get_trip(tz, i, &trip))
-				continue;
-
-			interrupt_en |=
-				(1 << (EXYNOS_TMU_INTEN_RISE0_SHIFT + i * 4));
-		}
-
-		if (data->soc != SOC_ARCH_EXYNOS4210)
-			interrupt_en |=
-				interrupt_en << EXYNOS_TMU_INTEN_FALL0_SHIFT;
-
-		con |= (1 << EXYNOS_TMU_CORE_EN_SHIFT);
-	} else {
-		con &= ~(1 << EXYNOS_TMU_CORE_EN_SHIFT);
-	}
+	if (on)
+		con |= BIT(EXYNOS_TMU_CORE_EN_SHIFT);
+	else
+		con &= ~BIT(EXYNOS_TMU_CORE_EN_SHIFT);
 
-	writel(interrupt_en, data->base + EXYNOS_TMU_REG_INTEN);
 	writel(con, data->base + EXYNOS_TMU_REG_CONTROL);
 }
 
 static void exynos5433_tmu_control(struct platform_device *pdev, bool on)
 {
 	struct exynos_tmu_data *data = platform_get_drvdata(pdev);
-	struct thermal_zone_device *tz = data->tzd;
-	struct thermal_trip trip;
-	unsigned int con, interrupt_en = 0, pd_det_en, i;
+	unsigned int con, pd_det_en;
 
 	con = get_con_reg(data, readl(data->base + EXYNOS_TMU_REG_CONTROL));
 
-	if (on) {
-		for (i = 0; i < data->ntrip; i++) {
-			if (thermal_zone_get_trip(tz, i, &trip))
-				continue;
-
-			interrupt_en |=
-				(1 << (EXYNOS7_TMU_INTEN_RISE0_SHIFT + i));
-		}
-
-		interrupt_en |=
-			interrupt_en << EXYNOS_TMU_INTEN_FALL0_SHIFT;
-
-		con |= (1 << EXYNOS_TMU_CORE_EN_SHIFT);
-	} else
-		con &= ~(1 << EXYNOS_TMU_CORE_EN_SHIFT);
+	if (on)
+		con |= BIT(EXYNOS_TMU_CORE_EN_SHIFT);
+	else
+		con &= ~BIT(EXYNOS_TMU_CORE_EN_SHIFT);
 
 	pd_det_en = on ? EXYNOS5433_PD_DET_EN : 0;
 
 	writel(pd_det_en, data->base + EXYNOS5433_TMU_PD_DET_EN);
-	writel(interrupt_en, data->base + EXYNOS5433_TMU_REG_INTEN);
 	writel(con, data->base + EXYNOS_TMU_REG_CONTROL);
 }
 
 static void exynos7_tmu_control(struct platform_device *pdev, bool on)
 {
 	struct exynos_tmu_data *data = platform_get_drvdata(pdev);
-	struct thermal_zone_device *tz = data->tzd;
-	struct thermal_trip trip;
-	unsigned int con, interrupt_en = 0, i;
+	unsigned int con;
 
 	con = get_con_reg(data, readl(data->base + EXYNOS_TMU_REG_CONTROL));
 
 	if (on) {
-		for (i = 0; i < data->ntrip; i++) {
-			if (thermal_zone_get_trip(tz, i, &trip))
-				continue;
-
-			interrupt_en |=
-				(1 << (EXYNOS7_TMU_INTEN_RISE0_SHIFT + i));
-		}
-
-		interrupt_en |=
-			interrupt_en << EXYNOS_TMU_INTEN_FALL0_SHIFT;
-
-		con |= (1 << EXYNOS_TMU_CORE_EN_SHIFT);
-		con |= (1 << EXYNOS7_PD_DET_EN_SHIFT);
+		con |= BIT(EXYNOS_TMU_CORE_EN_SHIFT);
+		con |= BIT(EXYNOS7_PD_DET_EN_SHIFT);
 	} else {
-		con &= ~(1 << EXYNOS_TMU_CORE_EN_SHIFT);
-		con &= ~(1 << EXYNOS7_PD_DET_EN_SHIFT);
+		con &= ~BIT(EXYNOS_TMU_CORE_EN_SHIFT);
+		con &= ~BIT(EXYNOS7_PD_DET_EN_SHIFT);
 	}
 
-	writel(interrupt_en, data->base + EXYNOS7_TMU_REG_INTEN);
 	writel(con, data->base + EXYNOS_TMU_REG_CONTROL);
 }
 
@@ -766,10 +756,9 @@ static int exynos7_tmu_read(struct exynos_tmu_data *data)
 		EXYNOS7_TMU_TEMP_MASK;
 }
 
-static void exynos_tmu_work(struct work_struct *work)
+static irqreturn_t exynos_tmu_threaded_irq(int irq, void *id)
 {
-	struct exynos_tmu_data *data = container_of(work,
-			struct exynos_tmu_data, irq_work);
+	struct exynos_tmu_data *data = id;
 
 	thermal_zone_device_update(data->tzd, THERMAL_EVENT_UNSPECIFIED);
 
@@ -781,7 +770,8 @@ static void exynos_tmu_work(struct work_struct *work)
 
 	clk_disable(data->clk);
 	mutex_unlock(&data->lock);
-	enable_irq(data->irq);
+
+	return IRQ_HANDLED;
 }
 
 static void exynos4210_tmu_clear_irqs(struct exynos_tmu_data *data)
@@ -815,16 +805,6 @@ static void exynos4210_tmu_clear_irqs(struct exynos_tmu_data *data)
 	writel(val_irq, data->base + tmu_intclear);
 }
 
-static irqreturn_t exynos_tmu_irq(int irq, void *id)
-{
-	struct exynos_tmu_data *data = id;
-
-	disable_irq_nosync(irq);
-	schedule_work(&data->irq_work);
-
-	return IRQ_HANDLED;
-}
-
 static const struct of_device_id exynos_tmu_match[] = {
 	{
 		.compatible = "samsung,exynos3250-tmu",
@@ -866,10 +846,6 @@ static int exynos_map_dt_data(struct platform_device *pdev)
 	if (!data || !pdev->dev.of_node)
 		return -ENODEV;
 
-	data->id = of_alias_get_id(pdev->dev.of_node, "tmuctrl");
-	if (data->id < 0)
-		data->id = 0;
-
 	data->irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
 	if (data->irq <= 0) {
 		dev_err(&pdev->dev, "failed to get IRQ\n");
@@ -891,13 +867,15 @@ static int exynos_map_dt_data(struct platform_device *pdev)
 
 	switch (data->soc) {
 	case SOC_ARCH_EXYNOS4210:
-		data->tmu_set_trip_temp = exynos4210_tmu_set_trip_temp;
-		data->tmu_set_trip_hyst = exynos4210_tmu_set_trip_hyst;
+		data->tmu_set_low_temp = exynos4210_tmu_set_low_temp;
+		data->tmu_set_high_temp = exynos4210_tmu_set_high_temp;
+		data->tmu_disable_low = exynos4210_tmu_disable_low;
+		data->tmu_disable_high = exynos4210_tmu_disable_high;
+		data->tmu_set_crit_temp = exynos4210_tmu_set_crit_temp;
 		data->tmu_initialize = exynos4210_tmu_initialize;
 		data->tmu_control = exynos4210_tmu_control;
 		data->tmu_read = exynos4210_tmu_read;
 		data->tmu_clear_irqs = exynos4210_tmu_clear_irqs;
-		data->ntrip = 4;
 		data->gain = 15;
 		data->reference_voltage = 7;
 		data->efuse_value = 55;
@@ -910,14 +888,16 @@ static int exynos_map_dt_data(struct platform_device *pdev)
 	case SOC_ARCH_EXYNOS5260:
 	case SOC_ARCH_EXYNOS5420:
 	case SOC_ARCH_EXYNOS5420_TRIMINFO:
-		data->tmu_set_trip_temp = exynos4412_tmu_set_trip_temp;
-		data->tmu_set_trip_hyst = exynos4412_tmu_set_trip_hyst;
+		data->tmu_set_low_temp = exynos4412_tmu_set_low_temp;
+		data->tmu_set_high_temp = exynos4412_tmu_set_high_temp;
+		data->tmu_disable_low = exynos4412_tmu_disable_low;
+		data->tmu_disable_high = exynos4210_tmu_disable_high;
+		data->tmu_set_crit_temp = exynos4412_tmu_set_crit_temp;
 		data->tmu_initialize = exynos4412_tmu_initialize;
 		data->tmu_control = exynos4210_tmu_control;
 		data->tmu_read = exynos4412_tmu_read;
 		data->tmu_set_emulation = exynos4412_tmu_set_emulation;
 		data->tmu_clear_irqs = exynos4210_tmu_clear_irqs;
-		data->ntrip = 4;
 		data->gain = 8;
 		data->reference_voltage = 16;
 		data->efuse_value = 55;
@@ -929,14 +909,16 @@ static int exynos_map_dt_data(struct platform_device *pdev)
 		data->max_efuse_value = 100;
 		break;
 	case SOC_ARCH_EXYNOS5433:
-		data->tmu_set_trip_temp = exynos5433_tmu_set_trip_temp;
-		data->tmu_set_trip_hyst = exynos5433_tmu_set_trip_hyst;
+		data->tmu_set_low_temp = exynos5433_tmu_set_low_temp;
+		data->tmu_set_high_temp = exynos5433_tmu_set_high_temp;
+		data->tmu_disable_low = exynos5433_tmu_disable_low;
+		data->tmu_disable_high = exynos5433_tmu_disable_high;
+		data->tmu_set_crit_temp = exynos5433_tmu_set_crit_temp;
 		data->tmu_initialize = exynos5433_tmu_initialize;
 		data->tmu_control = exynos5433_tmu_control;
 		data->tmu_read = exynos4412_tmu_read;
 		data->tmu_set_emulation = exynos4412_tmu_set_emulation;
 		data->tmu_clear_irqs = exynos4210_tmu_clear_irqs;
-		data->ntrip = 8;
 		data->gain = 8;
 		if (res.start == EXYNOS5433_G3D_BASE)
 			data->reference_voltage = 23;
@@ -947,14 +929,16 @@ static int exynos_map_dt_data(struct platform_device *pdev)
 		data->max_efuse_value = 150;
 		break;
 	case SOC_ARCH_EXYNOS7:
-		data->tmu_set_trip_temp = exynos7_tmu_set_trip_temp;
-		data->tmu_set_trip_hyst = exynos7_tmu_set_trip_hyst;
+		data->tmu_set_low_temp = exynos7_tmu_set_low_temp;
+		data->tmu_set_high_temp = exynos7_tmu_set_high_temp;
+		data->tmu_disable_low = exynos7_tmu_disable_low;
+		data->tmu_disable_high = exynos7_tmu_disable_high;
+		data->tmu_set_crit_temp = exynos7_tmu_set_crit_temp;
 		data->tmu_initialize = exynos7_tmu_initialize;
 		data->tmu_control = exynos7_tmu_control;
 		data->tmu_read = exynos7_tmu_read;
 		data->tmu_set_emulation = exynos4412_tmu_set_emulation;
 		data->tmu_clear_irqs = exynos4210_tmu_clear_irqs;
-		data->ntrip = 8;
 		data->gain = 9;
 		data->reference_voltage = 17;
 		data->efuse_value = 75;
@@ -990,9 +974,32 @@ static int exynos_map_dt_data(struct platform_device *pdev)
 	return 0;
 }
 
+static int exynos_set_trips(struct thermal_zone_device *tz, int low, int high)
+{
+	struct exynos_tmu_data *data = thermal_zone_device_priv(tz);
+
+	mutex_lock(&data->lock);
+	clk_enable(data->clk);
+
+	if (low > INT_MIN)
+		data->tmu_set_low_temp(data, low / MCELSIUS);
+	else
+		data->tmu_disable_low(data);
+	if (high < INT_MAX)
+		data->tmu_set_high_temp(data, high / MCELSIUS);
+	else
+		data->tmu_disable_high(data);
+
+	clk_disable(data->clk);
+	mutex_unlock(&data->lock);
+
+	return 0;
+}
+
 static const struct thermal_zone_device_ops exynos_sensor_ops = {
 	.get_temp = exynos_get_temp,
 	.set_emul_temp = exynos_tmu_set_emulation,
+	.set_trips = exynos_set_trips,
 };
 
 static int exynos_tmu_probe(struct platform_device *pdev)
@@ -1013,44 +1020,40 @@ static int exynos_tmu_probe(struct platform_device *pdev)
 	 * TODO: Add regulator as an SOC feature, so that regulator enable
 	 * is a compulsory call.
 	 */
-	data->regulator = devm_regulator_get_optional(&pdev->dev, "vtmu");
-	if (!IS_ERR(data->regulator)) {
-		ret = regulator_enable(data->regulator);
-		if (ret) {
-			dev_err(&pdev->dev, "failed to enable vtmu\n");
-			return ret;
-		}
-	} else {
-		if (PTR_ERR(data->regulator) == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
-		dev_info(&pdev->dev, "Regulator node (vtmu) not found\n");
+	ret = devm_regulator_get_enable_optional(&pdev->dev, "vtmu");
+	switch (ret) {
+	case 0:
+	case -ENODEV:
+		break;
+	case -EPROBE_DEFER:
+		return -EPROBE_DEFER;
+	default:
+		dev_err(&pdev->dev, "Failed to get enabled regulator: %d\n",
+			ret);
+		return ret;
 	}
 
 	ret = exynos_map_dt_data(pdev);
 	if (ret)
-		goto err_sensor;
-
-	INIT_WORK(&data->irq_work, exynos_tmu_work);
+		return ret;
 
 	data->clk = devm_clk_get(&pdev->dev, "tmu_apbif");
 	if (IS_ERR(data->clk)) {
 		dev_err(&pdev->dev, "Failed to get clock\n");
-		ret = PTR_ERR(data->clk);
-		goto err_sensor;
+		return PTR_ERR(data->clk);
 	}
 
 	data->clk_sec = devm_clk_get(&pdev->dev, "tmu_triminfo_apbif");
 	if (IS_ERR(data->clk_sec)) {
 		if (data->soc == SOC_ARCH_EXYNOS5420_TRIMINFO) {
 			dev_err(&pdev->dev, "Failed to get triminfo clock\n");
-			ret = PTR_ERR(data->clk_sec);
-			goto err_sensor;
+			return PTR_ERR(data->clk_sec);
 		}
 	} else {
 		ret = clk_prepare(data->clk_sec);
 		if (ret) {
 			dev_err(&pdev->dev, "Failed to get clock\n");
-			goto err_sensor;
+			return ret;
 		}
 	}
 
@@ -1080,10 +1083,12 @@ static int exynos_tmu_probe(struct platform_device *pdev)
 		break;
 	}
 
-	/*
-	 * data->tzd must be registered before calling exynos_tmu_initialize(),
-	 * requesting irq and calling exynos_tmu_control().
-	 */
+	ret = exynos_tmu_initialize(pdev);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to initialize TMU\n");
+		goto err_sclk;
+	}
+
 	data->tzd = devm_thermal_of_zone_register(&pdev->dev, 0, data,
 						  &exynos_sensor_ops);
 	if (IS_ERR(data->tzd)) {
@@ -1094,14 +1099,17 @@ static int exynos_tmu_probe(struct platform_device *pdev)
 		goto err_sclk;
 	}
 
-	ret = exynos_tmu_initialize(pdev);
+	ret = exynos_thermal_zone_configure(pdev);
 	if (ret) {
-		dev_err(&pdev->dev, "Failed to initialize TMU\n");
+		dev_err(&pdev->dev, "Failed to configure the thermal zone\n");
 		goto err_sclk;
 	}
 
-	ret = devm_request_irq(&pdev->dev, data->irq, exynos_tmu_irq,
-		IRQF_TRIGGER_RISING | IRQF_SHARED, dev_name(&pdev->dev), data);
+	ret = devm_request_threaded_irq(&pdev->dev, data->irq, NULL,
+					exynos_tmu_threaded_irq,
+					IRQF_TRIGGER_RISING
+						| IRQF_SHARED | IRQF_ONESHOT,
+					dev_name(&pdev->dev), data);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to request irq: %d\n", data->irq);
 		goto err_sclk;
@@ -1117,10 +1125,6 @@ err_clk:
 err_clk_sec:
 	if (!IS_ERR(data->clk_sec))
 		clk_unprepare(data->clk_sec);
-err_sensor:
-	if (!IS_ERR(data->regulator))
-		regulator_disable(data->regulator);
-
 	return ret;
 }
 
@@ -1134,9 +1138,6 @@ static void exynos_tmu_remove(struct platform_device *pdev)
 	clk_unprepare(data->clk);
 	if (!IS_ERR(data->clk_sec))
 		clk_unprepare(data->clk_sec);
-
-	if (!IS_ERR(data->regulator))
-		regulator_disable(data->regulator);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/thermal/sun8i_thermal.c b/drivers/thermal/sun8i_thermal.c
index f989b55a8aa8..6a8e386dbc8d 100644
--- a/drivers/thermal/sun8i_thermal.c
+++ b/drivers/thermal/sun8i_thermal.c
@@ -606,6 +606,18 @@ static const struct ths_thermal_chip sun50i_h6_ths = {
 	.calc_temp = sun8i_ths_calc_temp,
 };
 
+static const struct ths_thermal_chip sun20i_d1_ths = {
+	.sensor_num = 1,
+	.has_bus_clk_reset = true,
+	.offset = 188552,
+	.scale = 673,
+	.temp_data_base = SUN50I_H6_THS_TEMP_DATA,
+	.calibrate = sun50i_h6_ths_calibrate,
+	.init = sun50i_h6_thermal_init,
+	.irq_ack = sun50i_h6_irq_ack,
+	.calc_temp = sun8i_ths_calc_temp,
+};
+
 static const struct of_device_id of_ths_match[] = {
 	{ .compatible = "allwinner,sun8i-a83t-ths", .data = &sun8i_a83t_ths },
 	{ .compatible = "allwinner,sun8i-h3-ths", .data = &sun8i_h3_ths },
@@ -614,6 +626,7 @@ static const struct of_device_id of_ths_match[] = {
 	{ .compatible = "allwinner,sun50i-a100-ths", .data = &sun50i_a100_ths },
 	{ .compatible = "allwinner,sun50i-h5-ths", .data = &sun50i_h5_ths },
 	{ .compatible = "allwinner,sun50i-h6-ths", .data = &sun50i_h6_ths },
+	{ .compatible = "allwinner,sun20i-d1-ths", .data = &sun20i_d1_ths },
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, of_ths_match);
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 9c17d35ccbbd..fa88d8707241 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -37,8 +37,6 @@ static LIST_HEAD(thermal_governor_list);
 static DEFINE_MUTEX(thermal_list_lock);
 static DEFINE_MUTEX(thermal_governor_lock);
 
-static atomic_t in_suspend;
-
 static struct thermal_governor *def_governor;
 
 /*
@@ -203,9 +201,6 @@ int thermal_zone_device_set_policy(struct thermal_zone_device *tz,
 	mutex_lock(&thermal_governor_lock);
 	mutex_lock(&tz->lock);
 
-	if (!device_is_registered(&tz->device))
-		goto exit;
-
 	gov = __find_governor(strim(policy));
 	if (!gov)
 		goto exit;
@@ -314,21 +309,43 @@ static void handle_non_critical_trips(struct thermal_zone_device *tz,
 		       def_governor->throttle(tz, trip);
 }
 
-void thermal_zone_device_critical(struct thermal_zone_device *tz)
+void thermal_governor_update_tz(struct thermal_zone_device *tz,
+				enum thermal_notify_event reason)
+{
+	if (!tz->governor || !tz->governor->update_tz)
+		return;
+
+	tz->governor->update_tz(tz, reason);
+}
+
+static void thermal_zone_device_halt(struct thermal_zone_device *tz, bool shutdown)
 {
 	/*
 	 * poweroff_delay_ms must be a carefully profiled positive value.
 	 * Its a must for forced_emergency_poweroff_work to be scheduled.
 	 */
 	int poweroff_delay_ms = CONFIG_THERMAL_EMERGENCY_POWEROFF_DELAY_MS;
+	const char *msg = "Temperature too high";
 
-	dev_emerg(&tz->device, "%s: critical temperature reached, "
-		  "shutting down\n", tz->type);
+	dev_emerg(&tz->device, "%s: critical temperature reached\n", tz->type);
+
+	if (shutdown)
+		hw_protection_shutdown(msg, poweroff_delay_ms);
+	else
+		hw_protection_reboot(msg, poweroff_delay_ms);
+}
 
-	hw_protection_shutdown("Temperature too high", poweroff_delay_ms);
+void thermal_zone_device_critical(struct thermal_zone_device *tz)
+{
+	thermal_zone_device_halt(tz, true);
 }
 EXPORT_SYMBOL(thermal_zone_device_critical);
 
+void thermal_zone_device_critical_reboot(struct thermal_zone_device *tz)
+{
+	thermal_zone_device_halt(tz, false);
+}
+
 static void handle_critical_trips(struct thermal_zone_device *tz,
 				  const struct thermal_trip *trip)
 {
@@ -345,22 +362,51 @@ static void handle_critical_trips(struct thermal_zone_device *tz,
 }
 
 static void handle_thermal_trip(struct thermal_zone_device *tz,
-				const struct thermal_trip *trip)
+				struct thermal_trip *trip)
 {
 	if (trip->temperature == THERMAL_TEMP_INVALID)
 		return;
 
-	if (tz->last_temperature != THERMAL_TEMP_INVALID) {
-		if (tz->last_temperature < trip->temperature &&
-		    tz->temperature >= trip->temperature)
+	if (tz->last_temperature == THERMAL_TEMP_INVALID) {
+		/* Initialization. */
+		trip->threshold = trip->temperature;
+		if (tz->temperature >= trip->threshold)
+			trip->threshold -= trip->hysteresis;
+	} else if (tz->last_temperature < trip->threshold) {
+		/*
+		 * The trip threshold is equal to the trip temperature, unless
+		 * the latter has changed in the meantime.  In either case,
+		 * the trip is crossed if the current zone temperature is at
+		 * least equal to its temperature, but otherwise ensure that
+		 * the threshold and the trip temperature will be equal.
+		 */
+		if (tz->temperature >= trip->temperature) {
 			thermal_notify_tz_trip_up(tz->id,
 						  thermal_zone_trip_id(tz, trip),
 						  tz->temperature);
-		if (tz->last_temperature >= trip->temperature &&
-		    tz->temperature < trip->temperature - trip->hysteresis)
+			trip->threshold = trip->temperature - trip->hysteresis;
+		} else {
+			trip->threshold = trip->temperature;
+		}
+	} else {
+		/*
+		 * The previous zone temperature was above or equal to the trip
+		 * threshold, which would be equal to the "low temperature" of
+		 * the trip (its temperature minus its hysteresis), unless the
+		 * trip temperature or hysteresis had changed.  In either case,
+		 * the trip is crossed if the current zone temperature is below
+		 * the low temperature of the trip, but otherwise ensure that
+		 * the trip threshold will be equal to the low temperature of
+		 * the trip.
+		 */
+		if (tz->temperature < trip->temperature - trip->hysteresis) {
 			thermal_notify_tz_trip_down(tz->id,
 						    thermal_zone_trip_id(tz, trip),
 						    tz->temperature);
+			trip->threshold = trip->temperature;
+		} else {
+			trip->threshold = trip->temperature - trip->hysteresis;
+		}
 	}
 
 	if (trip->type == THERMAL_TRIP_CRITICAL || trip->type == THERMAL_TRIP_HOT)
@@ -390,9 +436,20 @@ static void update_temperature(struct thermal_zone_device *tz)
 	thermal_genl_sampling_temp(tz->id, temp);
 }
 
+static void thermal_zone_device_check(struct work_struct *work)
+{
+	struct thermal_zone_device *tz = container_of(work, struct
+						      thermal_zone_device,
+						      poll_queue.work);
+	thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
+}
+
 static void thermal_zone_device_init(struct thermal_zone_device *tz)
 {
 	struct thermal_instance *pos;
+
+	INIT_DELAYED_WORK(&tz->poll_queue, thermal_zone_device_check);
+
 	tz->temperature = THERMAL_TEMP_INVALID;
 	tz->prev_low_trip = -INT_MAX;
 	tz->prev_high_trip = INT_MAX;
@@ -403,14 +460,9 @@ static void thermal_zone_device_init(struct thermal_zone_device *tz)
 void __thermal_zone_device_update(struct thermal_zone_device *tz,
 				  enum thermal_notify_event event)
 {
-	const struct thermal_trip *trip;
-
-	if (atomic_read(&in_suspend))
-		return;
+	struct thermal_trip *trip;
 
-	if (WARN_ONCE(!tz->ops->get_temp,
-		      "'%s' must not be called without 'get_temp' ops set\n",
-		      __func__))
+	if (tz->suspended)
 		return;
 
 	if (!thermal_zone_device_is_enabled(tz))
@@ -442,12 +494,6 @@ static int thermal_zone_device_set_mode(struct thermal_zone_device *tz,
 		return ret;
 	}
 
-	if (!device_is_registered(&tz->device)) {
-		mutex_unlock(&tz->lock);
-
-		return -ENODEV;
-	}
-
 	if (tz->ops->change_mode)
 		ret = tz->ops->change_mode(tz, mode);
 
@@ -485,24 +531,21 @@ int thermal_zone_device_is_enabled(struct thermal_zone_device *tz)
 	return tz->mode == THERMAL_DEVICE_ENABLED;
 }
 
+static bool thermal_zone_is_present(struct thermal_zone_device *tz)
+{
+	return !list_empty(&tz->node);
+}
+
 void thermal_zone_device_update(struct thermal_zone_device *tz,
 				enum thermal_notify_event event)
 {
 	mutex_lock(&tz->lock);
-	if (device_is_registered(&tz->device))
+	if (thermal_zone_is_present(tz))
 		__thermal_zone_device_update(tz, event);
 	mutex_unlock(&tz->lock);
 }
 EXPORT_SYMBOL_GPL(thermal_zone_device_update);
 
-static void thermal_zone_device_check(struct work_struct *work)
-{
-	struct thermal_zone_device *tz = container_of(work, struct
-						      thermal_zone_device,
-						      poll_queue.work);
-	thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
-}
-
 int for_each_thermal_governor(int (*cb)(struct thermal_governor *, void *),
 			      void *data)
 {
@@ -694,6 +737,8 @@ int thermal_bind_cdev_to_trip(struct thermal_zone_device *tz,
 		list_add_tail(&dev->tz_node, &tz->thermal_instances);
 		list_add_tail(&dev->cdev_node, &cdev->thermal_instances);
 		atomic_set(&tz->need_update, 1);
+
+		thermal_governor_update_tz(tz, THERMAL_TZ_BIND_CDEV);
 	}
 	mutex_unlock(&cdev->lock);
 	mutex_unlock(&tz->lock);
@@ -752,6 +797,9 @@ int thermal_unbind_cdev_from_trip(struct thermal_zone_device *tz,
 		if (pos->tz == tz && pos->trip == trip && pos->cdev == cdev) {
 			list_del(&pos->tz_node);
 			list_del(&pos->cdev_node);
+
+			thermal_governor_update_tz(tz, THERMAL_TZ_UNBIND_CDEV);
+
 			mutex_unlock(&cdev->lock);
 			mutex_unlock(&tz->lock);
 			goto unbind;
@@ -793,7 +841,7 @@ static void thermal_release(struct device *dev)
 		tz = to_thermal_zone(dev);
 		thermal_zone_destroy_device_groups(tz);
 		mutex_destroy(&tz->lock);
-		kfree(tz);
+		complete(&tz->removal);
 	} else if (!strncmp(dev_name(dev), "cooling_device",
 			    sizeof("cooling_device") - 1)) {
 		cdev = to_cooling_device(dev);
@@ -1260,7 +1308,7 @@ thermal_zone_device_register_with_trips(const char *type, struct thermal_trip *t
 		return ERR_PTR(-EINVAL);
 	}
 
-	if (!ops) {
+	if (!ops || !ops->get_temp) {
 		pr_err("Thermal zone device ops not defined\n");
 		return ERR_PTR(-EINVAL);
 	}
@@ -1284,8 +1332,10 @@ thermal_zone_device_register_with_trips(const char *type, struct thermal_trip *t
 	}
 
 	INIT_LIST_HEAD(&tz->thermal_instances);
+	INIT_LIST_HEAD(&tz->node);
 	ida_init(&tz->ida);
 	mutex_init(&tz->lock);
+	init_completion(&tz->removal);
 	id = ida_alloc(&thermal_tz_ida, GFP_KERNEL);
 	if (id < 0) {
 		result = id;
@@ -1348,14 +1398,14 @@ thermal_zone_device_register_with_trips(const char *type, struct thermal_trip *t
 	}
 
 	mutex_lock(&thermal_list_lock);
+	mutex_lock(&tz->lock);
 	list_add_tail(&tz->node, &thermal_tz_list);
+	mutex_unlock(&tz->lock);
 	mutex_unlock(&thermal_list_lock);
 
 	/* Bind cooling devices for this zone */
 	bind_tz(tz);
 
-	INIT_DELAYED_WORK(&tz->poll_queue, thermal_zone_device_check);
-
 	thermal_zone_device_init(tz);
 	/* Update the new thermal zone and mark it as already updated. */
 	if (atomic_cmpxchg(&tz->need_update, 1, 0))
@@ -1369,7 +1419,6 @@ unregister:
 	device_del(&tz->device);
 release_device:
 	put_device(&tz->device);
-	tz = NULL;
 remove_id:
 	ida_free(&thermal_tz_ida, id);
 free_tzp:
@@ -1439,7 +1488,10 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 		mutex_unlock(&thermal_list_lock);
 		return;
 	}
+
+	mutex_lock(&tz->lock);
 	list_del(&tz->node);
+	mutex_unlock(&tz->lock);
 
 	/* Unbind all cdevs associated with 'this' thermal zone */
 	list_for_each_entry(cdev, &thermal_cdev_list, node)
@@ -1456,15 +1508,16 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 	ida_free(&thermal_tz_ida, tz->id);
 	ida_destroy(&tz->ida);
 
-	mutex_lock(&tz->lock);
 	device_del(&tz->device);
-	mutex_unlock(&tz->lock);
 
 	kfree(tz->tzp);
 
 	put_device(&tz->device);
 
 	thermal_notify_tz_delete(tz_id);
+
+	wait_for_completion(&tz->removal);
+	kfree(tz);
 }
 EXPORT_SYMBOL_GPL(thermal_zone_device_unregister);
 
@@ -1506,6 +1559,22 @@ exit:
 }
 EXPORT_SYMBOL_GPL(thermal_zone_get_zone_by_name);
 
+static void thermal_zone_device_resume(struct work_struct *work)
+{
+	struct thermal_zone_device *tz;
+
+	tz = container_of(work, struct thermal_zone_device, poll_queue.work);
+
+	mutex_lock(&tz->lock);
+
+	tz->suspended = false;
+
+	thermal_zone_device_init(tz);
+	__thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
+
+	mutex_unlock(&tz->lock);
+}
+
 static int thermal_pm_notify(struct notifier_block *nb,
 			     unsigned long mode, void *_unused)
 {
@@ -1515,17 +1584,43 @@ static int thermal_pm_notify(struct notifier_block *nb,
 	case PM_HIBERNATION_PREPARE:
 	case PM_RESTORE_PREPARE:
 	case PM_SUSPEND_PREPARE:
-		atomic_set(&in_suspend, 1);
+		mutex_lock(&thermal_list_lock);
+
+		list_for_each_entry(tz, &thermal_tz_list, node) {
+			mutex_lock(&tz->lock);
+
+			tz->suspended = true;
+
+			mutex_unlock(&tz->lock);
+		}
+
+		mutex_unlock(&thermal_list_lock);
 		break;
 	case PM_POST_HIBERNATION:
 	case PM_POST_RESTORE:
 	case PM_POST_SUSPEND:
-		atomic_set(&in_suspend, 0);
+		mutex_lock(&thermal_list_lock);
+
 		list_for_each_entry(tz, &thermal_tz_list, node) {
-			thermal_zone_device_init(tz);
-			thermal_zone_device_update(tz,
-						   THERMAL_EVENT_UNSPECIFIED);
+			mutex_lock(&tz->lock);
+
+			cancel_delayed_work(&tz->poll_queue);
+
+			/*
+			 * Replace the work function with the resume one, which
+			 * will restore the original work function and schedule
+			 * the polling work if needed.
+			 */
+			INIT_DELAYED_WORK(&tz->poll_queue,
+					  thermal_zone_device_resume);
+			/* Queue up the work without a delay. */
+			mod_delayed_work(system_freezable_power_efficient_wq,
+					 &tz->poll_queue, 0);
+
+			mutex_unlock(&tz->lock);
 		}
+
+		mutex_unlock(&thermal_list_lock);
 		break;
 	default:
 		break;
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index 0a3b3ec5120b..4e023d54fd27 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -114,16 +114,19 @@ int thermal_zone_device_set_policy(struct thermal_zone_device *, char *);
 int thermal_build_list_of_policies(char *buf);
 void __thermal_zone_device_update(struct thermal_zone_device *tz,
 				  enum thermal_notify_event event);
+void thermal_zone_device_critical_reboot(struct thermal_zone_device *tz);
+void thermal_governor_update_tz(struct thermal_zone_device *tz,
+				enum thermal_notify_event reason);
 
 /* Helpers */
 #define for_each_trip(__tz, __trip)	\
 	for (__trip = __tz->trips; __trip - __tz->trips < __tz->num_trips; __trip++)
 
 void __thermal_zone_set_trips(struct thermal_zone_device *tz);
-int __thermal_zone_get_trip(struct thermal_zone_device *tz, int trip_id,
-			    struct thermal_trip *trip);
-int thermal_zone_trip_id(struct thermal_zone_device *tz,
+int thermal_zone_trip_id(const struct thermal_zone_device *tz,
 			 const struct thermal_trip *trip);
+void thermal_zone_trip_updated(struct thermal_zone_device *tz,
+			       const struct thermal_trip *trip);
 int __thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp);
 
 /* sysfs I/F */
diff --git a/drivers/thermal/thermal_helpers.c b/drivers/thermal/thermal_helpers.c
index 69e8ea4aa908..c3982e0f0075 100644
--- a/drivers/thermal/thermal_helpers.c
+++ b/drivers/thermal/thermal_helpers.c
@@ -82,20 +82,18 @@ EXPORT_SYMBOL(get_thermal_instance);
  */
 int __thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	int ret = -EINVAL;
-	int count;
+	const struct thermal_trip *trip;
 	int crit_temp = INT_MAX;
-	struct thermal_trip trip;
+	int ret = -EINVAL;
 
 	lockdep_assert_held(&tz->lock);
 
 	ret = tz->ops->get_temp(tz, temp);
 
 	if (IS_ENABLED(CONFIG_THERMAL_EMULATION) && tz->emul_temperature) {
-		for (count = 0; count < tz->num_trips; count++) {
-			ret = __thermal_zone_get_trip(tz, count, &trip);
-			if (!ret && trip.type == THERMAL_TRIP_CRITICAL) {
-				crit_temp = trip.temperature;
+		for_each_trip(tz, trip) {
+			if (trip->type == THERMAL_TRIP_CRITICAL) {
+				crit_temp = trip->temperature;
 				break;
 			}
 		}
@@ -139,10 +137,7 @@ int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp)
 		goto unlock;
 	}
 
-	if (device_is_registered(&tz->device))
-		ret = __thermal_zone_get_temp(tz, temp);
-	else
-		ret = -ENODEV;
+	ret = __thermal_zone_get_temp(tz, temp);
 
 unlock:
 	mutex_unlock(&tz->lock);
diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c
index c3ae44659b81..252116f1e535 100644
--- a/drivers/thermal/thermal_hwmon.c
+++ b/drivers/thermal/thermal_hwmon.c
@@ -80,10 +80,7 @@ temp_crit_show(struct device *dev, struct device_attribute *attr, char *buf)
 
 	mutex_lock(&tz->lock);
 
-	if (device_is_registered(&tz->device))
-		ret = tz->ops->get_crit_temp(tz, &temperature);
-	else
-		ret = -ENODEV;
+	ret = tz->ops->get_crit_temp(tz, &temperature);
 
 	mutex_unlock(&tz->lock);
 
diff --git a/drivers/thermal/thermal_netlink.c b/drivers/thermal/thermal_netlink.c
index 08bc46c3ec7b..332052e24a86 100644
--- a/drivers/thermal/thermal_netlink.c
+++ b/drivers/thermal/thermal_netlink.c
@@ -13,9 +13,14 @@
 
 #include "thermal_core.h"
 
+enum thermal_genl_multicast_groups {
+	THERMAL_GENL_SAMPLING_GROUP = 0,
+	THERMAL_GENL_EVENT_GROUP = 1,
+};
+
 static const struct genl_multicast_group thermal_genl_mcgrps[] = {
-	{ .name = THERMAL_GENL_SAMPLING_GROUP_NAME, },
-	{ .name = THERMAL_GENL_EVENT_GROUP_NAME,  },
+	[THERMAL_GENL_SAMPLING_GROUP] = { .name = THERMAL_GENL_SAMPLING_GROUP_NAME, },
+	[THERMAL_GENL_EVENT_GROUP]  = { .name = THERMAL_GENL_EVENT_GROUP_NAME,  },
 };
 
 static const struct nla_policy thermal_genl_policy[THERMAL_GENL_ATTR_MAX + 1] = {
@@ -71,6 +76,11 @@ typedef int (*cb_t)(struct param *);
 
 static struct genl_family thermal_gnl_family;
 
+static int thermal_group_has_listeners(enum thermal_genl_multicast_groups group)
+{
+	return genl_has_listeners(&thermal_gnl_family, &init_net, group);
+}
+
 /************************** Sampling encoding *******************************/
 
 int thermal_genl_sampling_temp(int id, int temp)
@@ -78,6 +88,9 @@ int thermal_genl_sampling_temp(int id, int temp)
 	struct sk_buff *skb;
 	void *hdr;
 
+	if (!thermal_group_has_listeners(THERMAL_GENL_SAMPLING_GROUP))
+		return 0;
+
 	skb = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb)
 		return -ENOMEM;
@@ -95,7 +108,7 @@ int thermal_genl_sampling_temp(int id, int temp)
 
 	genlmsg_end(skb, hdr);
 
-	genlmsg_multicast(&thermal_gnl_family, skb, 0, 0, GFP_KERNEL);
+	genlmsg_multicast(&thermal_gnl_family, skb, 0, THERMAL_GENL_SAMPLING_GROUP, GFP_KERNEL);
 
 	return 0;
 out_cancel:
@@ -275,6 +288,9 @@ static int thermal_genl_send_event(enum thermal_genl_event event,
 	int ret = -EMSGSIZE;
 	void *hdr;
 
+	if (!thermal_group_has_listeners(THERMAL_GENL_EVENT_GROUP))
+		return 0;
+
 	msg = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!msg)
 		return -ENOMEM;
@@ -290,7 +306,7 @@ static int thermal_genl_send_event(enum thermal_genl_event event,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(&thermal_gnl_family, msg, 0, 1, GFP_KERNEL);
+	genlmsg_multicast(&thermal_gnl_family, msg, 0, THERMAL_GENL_EVENT_GROUP, GFP_KERNEL);
 
 	return 0;
 
@@ -450,10 +466,10 @@ out_cancel_nest:
 static int thermal_genl_cmd_tz_get_trip(struct param *p)
 {
 	struct sk_buff *msg = p->msg;
+	const struct thermal_trip *trip;
 	struct thermal_zone_device *tz;
 	struct nlattr *start_trip;
-	struct thermal_trip trip;
-	int ret, i, id;
+	int id;
 
 	if (!p->attrs[THERMAL_GENL_ATTR_TZ_ID])
 		return -EINVAL;
@@ -470,16 +486,12 @@ static int thermal_genl_cmd_tz_get_trip(struct param *p)
 
 	mutex_lock(&tz->lock);
 
-	for (i = 0; i < tz->num_trips; i++) {
-
-		ret = __thermal_zone_get_trip(tz, i, &trip);
-		if (ret)
-			goto out_cancel_nest;
-
-		if (nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TRIP_ID, i) ||
-		    nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TRIP_TYPE, trip.type) ||
-		    nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TRIP_TEMP, trip.temperature) ||
-		    nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TRIP_HYST, trip.hysteresis))
+	for_each_trip(tz, trip) {
+		if (nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TRIP_ID,
+				thermal_zone_trip_id(tz, trip)) ||
+		    nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TRIP_TYPE, trip->type) ||
+		    nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TRIP_TEMP, trip->temperature) ||
+		    nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TRIP_HYST, trip->hysteresis))
 			goto out_cancel_nest;
 	}
 
diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c
index 1e0655b63259..4d6c22e0ed85 100644
--- a/drivers/thermal/thermal_of.c
+++ b/drivers/thermal/thermal_of.c
@@ -475,6 +475,7 @@ static struct thermal_zone_device *thermal_of_zone_register(struct device_node *
 	struct thermal_zone_params tzp = {};
 	struct thermal_zone_device_ops *of_ops;
 	struct device_node *np;
+	const char *action;
 	int delay, pdelay;
 	int ntrips, mask;
 	int ret;
@@ -511,6 +512,11 @@ static struct thermal_zone_device *thermal_of_zone_register(struct device_node *
 
 	mask = GENMASK_ULL((ntrips) - 1, 0);
 
+	ret = of_property_read_string(np, "critical-action", &action);
+	if (!ret)
+		if (!of_ops->critical && !strcasecmp(action, "reboot"))
+			of_ops->critical = thermal_zone_device_critical_reboot;
+
 	tz = thermal_zone_device_register_with_trips(np->name, trips, ntrips,
 						     mask, data, of_ops, &tzp,
 						     pdelay, delay);
diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c
index eef40d4f3063..f4033865b093 100644
--- a/drivers/thermal/thermal_sysfs.c
+++ b/drivers/thermal/thermal_sysfs.c
@@ -83,25 +83,12 @@ trip_point_type_show(struct device *dev, struct device_attribute *attr,
 		     char *buf)
 {
 	struct thermal_zone_device *tz = to_thermal_zone(dev);
-	struct thermal_trip trip;
-	int trip_id, result;
+	int trip_id;
 
 	if (sscanf(attr->attr.name, "trip_point_%d_type", &trip_id) != 1)
 		return -EINVAL;
 
-	mutex_lock(&tz->lock);
-
-	if (device_is_registered(dev))
-		result = __thermal_zone_get_trip(tz, trip_id, &trip);
-	else
-		result = -ENODEV;
-
-	mutex_unlock(&tz->lock);
-
-	if (result)
-		return result;
-
-	switch (trip.type) {
+	switch (tz->trips[trip_id].type) {
 	case THERMAL_TRIP_CRITICAL:
 		return sprintf(buf, "critical\n");
 	case THERMAL_TRIP_HOT:
@@ -120,28 +107,33 @@ trip_point_temp_store(struct device *dev, struct device_attribute *attr,
 		      const char *buf, size_t count)
 {
 	struct thermal_zone_device *tz = to_thermal_zone(dev);
-	struct thermal_trip trip;
+	struct thermal_trip *trip;
 	int trip_id, ret;
+	int temp;
+
+	ret = kstrtoint(buf, 10, &temp);
+	if (ret)
+		return -EINVAL;
 
 	if (sscanf(attr->attr.name, "trip_point_%d_temp", &trip_id) != 1)
 		return -EINVAL;
 
 	mutex_lock(&tz->lock);
 
-	if (!device_is_registered(dev)) {
-		ret = -ENODEV;
-		goto unlock;
-	}
+	trip = &tz->trips[trip_id];
 
-	ret = __thermal_zone_get_trip(tz, trip_id, &trip);
-	if (ret)
-		goto unlock;
+	if (temp != trip->temperature) {
+		if (tz->ops->set_trip_temp) {
+			ret = tz->ops->set_trip_temp(tz, trip_id, temp);
+			if (ret)
+				goto unlock;
+		}
 
-	ret = kstrtoint(buf, 10, &trip.temperature);
-	if (ret)
-		goto unlock;
+		thermal_zone_set_trip_temp(tz, trip, temp);
+
+		__thermal_zone_device_update(tz, THERMAL_TRIP_CHANGED);
+	}
 
-	ret = thermal_zone_set_trip(tz, trip_id, &trip);
 unlock:
 	mutex_unlock(&tz->lock);
 	
@@ -153,25 +145,12 @@ trip_point_temp_show(struct device *dev, struct device_attribute *attr,
 		     char *buf)
 {
 	struct thermal_zone_device *tz = to_thermal_zone(dev);
-	struct thermal_trip trip;
-	int trip_id, ret;
+	int trip_id;
 
 	if (sscanf(attr->attr.name, "trip_point_%d_temp", &trip_id) != 1)
 		return -EINVAL;
 
-	mutex_lock(&tz->lock);
-
-	if (device_is_registered(dev))
-		ret = __thermal_zone_get_trip(tz, trip_id, &trip);
-	else
-		ret = -ENODEV;
-
-	mutex_unlock(&tz->lock);
-
-	if (ret)
-		return ret;
-
-	return sprintf(buf, "%d\n", trip.temperature);
+	return sprintf(buf, "%d\n", tz->trips[trip_id].temperature);
 }
 
 static ssize_t
@@ -179,28 +158,33 @@ trip_point_hyst_store(struct device *dev, struct device_attribute *attr,
 		      const char *buf, size_t count)
 {
 	struct thermal_zone_device *tz = to_thermal_zone(dev);
-	struct thermal_trip trip;
+	struct thermal_trip *trip;
 	int trip_id, ret;
+	int hyst;
+
+	ret = kstrtoint(buf, 10, &hyst);
+	if (ret || hyst < 0)
+		return -EINVAL;
 
 	if (sscanf(attr->attr.name, "trip_point_%d_hyst", &trip_id) != 1)
 		return -EINVAL;
 
 	mutex_lock(&tz->lock);
 
-	if (!device_is_registered(dev)) {
-		ret = -ENODEV;
-		goto unlock;
-	}
+	trip = &tz->trips[trip_id];
 
-	ret = __thermal_zone_get_trip(tz, trip_id, &trip);
-	if (ret)
-		goto unlock;
+	if (hyst != trip->hysteresis) {
+		if (tz->ops->set_trip_hyst) {
+			ret = tz->ops->set_trip_hyst(tz, trip_id, hyst);
+			if (ret)
+				goto unlock;
+		}
 
-	ret = kstrtoint(buf, 10, &trip.hysteresis);
-	if (ret)
-		goto unlock;
+		trip->hysteresis = hyst;
+
+		thermal_zone_trip_updated(tz, trip);
+	}
 
-	ret = thermal_zone_set_trip(tz, trip_id, &trip);
 unlock:
 	mutex_unlock(&tz->lock);
 
@@ -212,22 +196,12 @@ trip_point_hyst_show(struct device *dev, struct device_attribute *attr,
 		     char *buf)
 {
 	struct thermal_zone_device *tz = to_thermal_zone(dev);
-	struct thermal_trip trip;
-	int trip_id, ret;
+	int trip_id;
 
 	if (sscanf(attr->attr.name, "trip_point_%d_hyst", &trip_id) != 1)
 		return -EINVAL;
 
-	mutex_lock(&tz->lock);
-
-	if (device_is_registered(dev))
-		ret = __thermal_zone_get_trip(tz, trip_id, &trip);
-	else
-		ret = -ENODEV;
-
-	mutex_unlock(&tz->lock);
-
-	return ret ? ret : sprintf(buf, "%d\n", trip.hysteresis);
+	return sprintf(buf, "%d\n", tz->trips[trip_id].hysteresis);
 }
 
 static ssize_t
@@ -276,11 +250,6 @@ emul_temp_store(struct device *dev, struct device_attribute *attr,
 
 	mutex_lock(&tz->lock);
 
-	if (!device_is_registered(dev)) {
-		ret = -ENODEV;
-		goto unlock;
-	}
-
 	if (!tz->ops->set_emul_temp)
 		tz->emul_temperature = temperature;
 	else
@@ -289,7 +258,6 @@ emul_temp_store(struct device *dev, struct device_attribute *attr,
 	if (!ret)
 		__thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
 
-unlock:
 	mutex_unlock(&tz->lock);
 
 	return ret ? ret : count;
@@ -968,7 +936,16 @@ ssize_t weight_store(struct device *dev, struct device_attribute *attr,
 		return ret;
 
 	instance = container_of(attr, struct thermal_instance, weight_attr);
+
+	/* Don't race with governors using the 'weight' value */
+	mutex_lock(&instance->tz->lock);
+
 	instance->weight = weight;
 
+	thermal_governor_update_tz(instance->tz,
+				   THERMAL_INSTANCE_WEIGHT_CHANGED);
+
+	mutex_unlock(&instance->tz->lock);
+
 	return count;
 }
diff --git a/drivers/thermal/thermal_trace_ipa.h b/drivers/thermal/thermal_trace_ipa.h
index 84568db5421b..b16b5dd863d9 100644
--- a/drivers/thermal/thermal_trace_ipa.h
+++ b/drivers/thermal/thermal_trace_ipa.h
@@ -8,19 +8,14 @@
 #include <linux/tracepoint.h>
 
 TRACE_EVENT(thermal_power_allocator,
-	TP_PROTO(struct thermal_zone_device *tz, u32 *req_power,
-		 u32 total_req_power, u32 *granted_power,
-		 u32 total_granted_power, size_t num_actors,
-		 u32 power_range, u32 max_allocatable_power,
-		 int current_temp, s32 delta_temp),
-	TP_ARGS(tz, req_power, total_req_power, granted_power,
-		total_granted_power, num_actors, power_range,
-		max_allocatable_power, current_temp, delta_temp),
+	TP_PROTO(struct thermal_zone_device *tz, u32 total_req_power,
+		 u32 total_granted_power, int num_actors, u32 power_range,
+		 u32 max_allocatable_power, int current_temp, s32 delta_temp),
+	TP_ARGS(tz, total_req_power, total_granted_power, num_actors,
+		power_range, max_allocatable_power, current_temp, delta_temp),
 	TP_STRUCT__entry(
 		__field(int,           tz_id          )
-		__dynamic_array(u32,   req_power, num_actors    )
 		__field(u32,           total_req_power          )
-		__dynamic_array(u32,   granted_power, num_actors)
 		__field(u32,           total_granted_power      )
 		__field(size_t,        num_actors               )
 		__field(u32,           power_range              )
@@ -30,11 +25,7 @@ TRACE_EVENT(thermal_power_allocator,
 	),
 	TP_fast_assign(
 		__entry->tz_id = tz->id;
-		memcpy(__get_dynamic_array(req_power), req_power,
-			num_actors * sizeof(*req_power));
 		__entry->total_req_power = total_req_power;
-		memcpy(__get_dynamic_array(granted_power), granted_power,
-			num_actors * sizeof(*granted_power));
 		__entry->total_granted_power = total_granted_power;
 		__entry->num_actors = num_actors;
 		__entry->power_range = power_range;
@@ -43,18 +34,35 @@ TRACE_EVENT(thermal_power_allocator,
 		__entry->delta_temp = delta_temp;
 	),
 
-	TP_printk("thermal_zone_id=%d req_power={%s} total_req_power=%u granted_power={%s} total_granted_power=%u power_range=%u max_allocatable_power=%u current_temperature=%d delta_temperature=%d",
-		__entry->tz_id,
-		__print_array(__get_dynamic_array(req_power),
-                              __entry->num_actors, 4),
-		__entry->total_req_power,
-		__print_array(__get_dynamic_array(granted_power),
-                              __entry->num_actors, 4),
+	TP_printk("thermal_zone_id=%d total_req_power=%u total_granted_power=%u power_range=%u max_allocatable_power=%u current_temperature=%d delta_temperature=%d",
+		__entry->tz_id,	__entry->total_req_power,
 		__entry->total_granted_power, __entry->power_range,
 		__entry->max_allocatable_power, __entry->current_temp,
 		__entry->delta_temp)
 );
 
+TRACE_EVENT(thermal_power_actor,
+	TP_PROTO(struct thermal_zone_device *tz, int actor_id, u32 req_power,
+		 u32 granted_power),
+	TP_ARGS(tz, actor_id, req_power, granted_power),
+	TP_STRUCT__entry(
+		__field(int, tz_id)
+		__field(int, actor_id)
+		__field(u32, req_power)
+		__field(u32, granted_power)
+	),
+	TP_fast_assign(
+		__entry->tz_id = tz->id;
+		__entry->actor_id = actor_id;
+		__entry->req_power = req_power;
+		__entry->granted_power = granted_power;
+	),
+
+	TP_printk("thermal_zone_id=%d actor_id=%d req_power=%u granted_power=%u",
+		__entry->tz_id,	__entry->actor_id, __entry->req_power,
+		__entry->granted_power)
+);
+
 TRACE_EVENT(thermal_power_allocator_pid,
 	TP_PROTO(struct thermal_zone_device *tz, s32 err, s32 err_integral,
 		 s64 p, s64 i, s64 d, s32 output),
diff --git a/drivers/thermal/thermal_trip.c b/drivers/thermal/thermal_trip.c
index e42456442c68..8bffa1e5e206 100644
--- a/drivers/thermal/thermal_trip.c
+++ b/drivers/thermal/thermal_trip.c
@@ -63,25 +63,21 @@ EXPORT_SYMBOL_GPL(thermal_zone_get_num_trips);
  */
 void __thermal_zone_set_trips(struct thermal_zone_device *tz)
 {
-	struct thermal_trip trip;
+	const struct thermal_trip *trip;
 	int low = -INT_MAX, high = INT_MAX;
 	bool same_trip = false;
-	int i, ret;
+	int ret;
 
 	lockdep_assert_held(&tz->lock);
 
 	if (!tz->ops->set_trips)
 		return;
 
-	for (i = 0; i < tz->num_trips; i++) {
+	for_each_trip(tz, trip) {
 		bool low_set = false;
 		int trip_low;
 
-		ret = __thermal_zone_get_trip(tz, i , &trip);
-		if (ret)
-			return;
-
-		trip_low = trip.temperature - trip.hysteresis;
+		trip_low = trip->temperature - trip->hysteresis;
 
 		if (trip_low < tz->temperature && trip_low > low) {
 			low = trip_low;
@@ -89,9 +85,9 @@ void __thermal_zone_set_trips(struct thermal_zone_device *tz)
 			same_trip = false;
 		}
 
-		if (trip.temperature > tz->temperature &&
-		    trip.temperature < high) {
-			high = trip.temperature;
+		if (trip->temperature > tz->temperature &&
+		    trip->temperature < high) {
+			high = trip->temperature;
 			same_trip = low_set;
 		}
 	}
@@ -147,46 +143,7 @@ int thermal_zone_get_trip(struct thermal_zone_device *tz, int trip_id,
 }
 EXPORT_SYMBOL_GPL(thermal_zone_get_trip);
 
-int thermal_zone_set_trip(struct thermal_zone_device *tz, int trip_id,
-			  const struct thermal_trip *trip)
-{
-	struct thermal_trip t;
-	int ret;
-
-	if (!tz->ops->set_trip_temp && !tz->ops->set_trip_hyst && !tz->trips)
-		return -EINVAL;
-
-	ret = __thermal_zone_get_trip(tz, trip_id, &t);
-	if (ret)
-		return ret;
-
-	if (t.type != trip->type)
-		return -EINVAL;
-
-	if (t.temperature != trip->temperature && tz->ops->set_trip_temp) {
-		ret = tz->ops->set_trip_temp(tz, trip_id, trip->temperature);
-		if (ret)
-			return ret;
-	}
-
-	if (t.hysteresis != trip->hysteresis && tz->ops->set_trip_hyst) {
-		ret = tz->ops->set_trip_hyst(tz, trip_id, trip->hysteresis);
-		if (ret)
-			return ret;
-	}
-
-	if (tz->trips && (t.temperature != trip->temperature || t.hysteresis != trip->hysteresis))
-		tz->trips[trip_id] = *trip;
-
-	thermal_notify_tz_trip_change(tz->id, trip_id, trip->type,
-				      trip->temperature, trip->hysteresis);
-
-	__thermal_zone_device_update(tz, THERMAL_TRIP_CHANGED);
-
-	return 0;
-}
-
-int thermal_zone_trip_id(struct thermal_zone_device *tz,
+int thermal_zone_trip_id(const struct thermal_zone_device *tz,
 			 const struct thermal_trip *trip)
 {
 	/*
@@ -195,3 +152,24 @@ int thermal_zone_trip_id(struct thermal_zone_device *tz,
 	 */
 	return trip - tz->trips;
 }
+void thermal_zone_trip_updated(struct thermal_zone_device *tz,
+			       const struct thermal_trip *trip)
+{
+	thermal_notify_tz_trip_change(tz->id, thermal_zone_trip_id(tz, trip),
+				      trip->type, trip->temperature,
+				      trip->hysteresis);
+	__thermal_zone_device_update(tz, THERMAL_TRIP_CHANGED);
+}
+
+void thermal_zone_set_trip_temp(struct thermal_zone_device *tz,
+				struct thermal_trip *trip, int temp)
+{
+	if (trip->temperature == temp)
+		return;
+
+	trip->temperature = temp;
+	thermal_notify_tz_trip_change(tz->id, thermal_zone_trip_id(tz, trip),
+				      trip->type, trip->temperature,
+				      trip->hysteresis);
+}
+EXPORT_SYMBOL_GPL(thermal_zone_set_trip_temp);
diff --git a/drivers/thunderbolt/debugfs.c b/drivers/thunderbolt/debugfs.c
index c9ddd49138d8..e324cd899719 100644
--- a/drivers/thunderbolt/debugfs.c
+++ b/drivers/thunderbolt/debugfs.c
@@ -959,7 +959,7 @@ static void margining_port_remove(struct tb_port *port)
 	snprintf(dir_name, sizeof(dir_name), "port%d", port->port);
 	parent = debugfs_lookup(dir_name, port->sw->debugfs_dir);
 	if (parent)
-		debugfs_remove_recursive(debugfs_lookup("margining", parent));
+		debugfs_lookup_and_remove("margining", parent);
 
 	kfree(port->usb4->margining);
 	port->usb4->margining = NULL;
diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c
index 1e15ffa79295..44e9b09de47a 100644
--- a/drivers/thunderbolt/switch.c
+++ b/drivers/thunderbolt/switch.c
@@ -1143,7 +1143,7 @@ int tb_port_lane_bonding_enable(struct tb_port *port)
 	 * Only set bonding if the link was not already bonded. This
 	 * avoids the lane adapter to re-enter bonding state.
 	 */
-	if (width == TB_LINK_WIDTH_SINGLE) {
+	if (width == TB_LINK_WIDTH_SINGLE && !tb_is_upstream_port(port)) {
 		ret = tb_port_set_lane_bonding(port, true);
 		if (ret)
 			goto err_lane1;
@@ -2880,6 +2880,7 @@ static int tb_switch_lane_bonding_disable(struct tb_switch *sw)
 	return tb_port_wait_for_link_width(down, TB_LINK_WIDTH_SINGLE, 100);
 }
 
+/* Note updating sw->link_width done in tb_switch_update_link_attributes() */
 static int tb_switch_asym_enable(struct tb_switch *sw, enum tb_link_width width)
 {
 	struct tb_port *up, *down, *port;
@@ -2919,10 +2920,10 @@ static int tb_switch_asym_enable(struct tb_switch *sw, enum tb_link_width width)
 			return ret;
 	}
 
-	sw->link_width = width;
 	return 0;
 }
 
+/* Note updating sw->link_width done in tb_switch_update_link_attributes() */
 static int tb_switch_asym_disable(struct tb_switch *sw)
 {
 	struct tb_port *up, *down;
@@ -2957,7 +2958,6 @@ static int tb_switch_asym_disable(struct tb_switch *sw)
 			return ret;
 	}
 
-	sw->link_width = TB_LINK_WIDTH_DUAL;
 	return 0;
 }
 
diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c
index 5acdeb766860..fd49f86e0353 100644
--- a/drivers/thunderbolt/tb.c
+++ b/drivers/thunderbolt/tb.c
@@ -213,7 +213,17 @@ static void tb_add_dp_resources(struct tb_switch *sw)
 		if (!tb_switch_query_dp_resource(sw, port))
 			continue;
 
-		list_add(&port->list, &tcm->dp_resources);
+		/*
+		 * If DP IN on device router exist, position it at the
+		 * beginning of the DP resources list, so that it is used
+		 * before DP IN of the host router. This way external GPU(s)
+		 * will be prioritized when pairing DP IN to a DP OUT.
+		 */
+		if (tb_route(sw))
+			list_add(&port->list, &tcm->dp_resources);
+		else
+			list_add_tail(&port->list, &tcm->dp_resources);
+
 		tb_port_dbg(port, "DP IN resource available\n");
 	}
 }
diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c
index 4277733d0021..f8f0d24ff6e4 100644
--- a/drivers/thunderbolt/usb4.c
+++ b/drivers/thunderbolt/usb4.c
@@ -2311,13 +2311,13 @@ int usb4_usb3_port_release_bandwidth(struct tb_port *port, int *upstream_bw,
 		goto err_request;
 
 	/*
-	 * Always keep 1000 Mb/s to make sure xHCI has at least some
+	 * Always keep 900 Mb/s to make sure xHCI has at least some
 	 * bandwidth available for isochronous traffic.
 	 */
-	if (consumed_up < 1000)
-		consumed_up = 1000;
-	if (consumed_down < 1000)
-		consumed_down = 1000;
+	if (consumed_up < 900)
+		consumed_up = 900;
+	if (consumed_down < 900)
+		consumed_down = 900;
 
 	ret = usb4_usb3_port_write_allocated_bandwidth(port, consumed_up,
 						       consumed_down);
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index b94f567647cb..e6218766d0c8 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -777,6 +777,7 @@ static const struct acpi_device_id dw8250_acpi_match[] = {
 	{ "INT33C5", (kernel_ulong_t)&dw8250_dw_apb },
 	{ "INT3434", (kernel_ulong_t)&dw8250_dw_apb },
 	{ "INT3435", (kernel_ulong_t)&dw8250_dw_apb },
+	{ "INTC10EE", (kernel_ulong_t)&dw8250_dw_apb },
 	{ },
 };
 MODULE_DEVICE_TABLE(acpi, dw8250_acpi_match);
diff --git a/drivers/tty/serial/8250/8250_early.c b/drivers/tty/serial/8250/8250_early.c
index 9837a27739fd..e3f482fd3de4 100644
--- a/drivers/tty/serial/8250/8250_early.c
+++ b/drivers/tty/serial/8250/8250_early.c
@@ -189,5 +189,6 @@ static int __init early_omap8250_setup(struct earlycon_device *device,
 OF_EARLYCON_DECLARE(omap8250, "ti,omap2-uart", early_omap8250_setup);
 OF_EARLYCON_DECLARE(omap8250, "ti,omap3-uart", early_omap8250_setup);
 OF_EARLYCON_DECLARE(omap8250, "ti,omap4-uart", early_omap8250_setup);
+OF_EARLYCON_DECLARE(omap8250, "ti,am654-uart", early_omap8250_setup);
 
 #endif
diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c
index 2d42f485c987..578f35895b27 100644
--- a/drivers/tty/serial/8250/8250_omap.c
+++ b/drivers/tty/serial/8250/8250_omap.c
@@ -933,7 +933,7 @@ static void __dma_rx_do_complete(struct uart_8250_port *p)
 	if (priv->habit & UART_HAS_RHR_IT_DIS) {
 		reg = serial_in(p, UART_OMAP_IER2);
 		reg &= ~UART_OMAP_IER2_RHR_IT_DIS;
-		serial_out(p, UART_OMAP_IER2, UART_OMAP_IER2_RHR_IT_DIS);
+		serial_out(p, UART_OMAP_IER2, reg);
 	}
 
 	dmaengine_tx_status(rxchan, cookie, &state);
@@ -1079,7 +1079,7 @@ static int omap_8250_rx_dma(struct uart_8250_port *p)
 	if (priv->habit & UART_HAS_RHR_IT_DIS) {
 		reg = serial_in(p, UART_OMAP_IER2);
 		reg |= UART_OMAP_IER2_RHR_IT_DIS;
-		serial_out(p, UART_OMAP_IER2, UART_OMAP_IER2_RHR_IT_DIS);
+		serial_out(p, UART_OMAP_IER2, reg);
 	}
 
 	dma_async_issue_pending(dma->rxchan);
@@ -1298,10 +1298,12 @@ static int omap_8250_dma_handle_irq(struct uart_port *port)
 
 	status = serial_port_in(port, UART_LSR);
 
-	if (priv->habit & UART_HAS_EFR2)
-		am654_8250_handle_rx_dma(up, iir, status);
-	else
-		status = omap_8250_handle_rx_dma(up, iir, status);
+	if ((iir & 0x3f) != UART_IIR_THRI) {
+		if (priv->habit & UART_HAS_EFR2)
+			am654_8250_handle_rx_dma(up, iir, status);
+		else
+			status = omap_8250_handle_rx_dma(up, iir, status);
+	}
 
 	serial8250_modem_status(up);
 	if (status & UART_LSR_THRE && up->dma->tx_err) {
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 61cc24cd90e4..b7635363373e 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -218,17 +218,18 @@ static struct vendor_data vendor_st = {
 
 /* Deals with DMA transactions */
 
-struct pl011_sgbuf {
-	struct scatterlist sg;
-	char *buf;
+struct pl011_dmabuf {
+	dma_addr_t		dma;
+	size_t			len;
+	char			*buf;
 };
 
 struct pl011_dmarx_data {
 	struct dma_chan		*chan;
 	struct completion	complete;
 	bool			use_buf_b;
-	struct pl011_sgbuf	sgbuf_a;
-	struct pl011_sgbuf	sgbuf_b;
+	struct pl011_dmabuf	dbuf_a;
+	struct pl011_dmabuf	dbuf_b;
 	dma_cookie_t		cookie;
 	bool			running;
 	struct timer_list	timer;
@@ -241,7 +242,8 @@ struct pl011_dmarx_data {
 
 struct pl011_dmatx_data {
 	struct dma_chan		*chan;
-	struct scatterlist	sg;
+	dma_addr_t		dma;
+	size_t			len;
 	char			*buf;
 	bool			queued;
 };
@@ -366,32 +368,24 @@ static int pl011_fifo_to_tty(struct uart_amba_port *uap)
 
 #define PL011_DMA_BUFFER_SIZE PAGE_SIZE
 
-static int pl011_sgbuf_init(struct dma_chan *chan, struct pl011_sgbuf *sg,
+static int pl011_dmabuf_init(struct dma_chan *chan, struct pl011_dmabuf *db,
 	enum dma_data_direction dir)
 {
-	dma_addr_t dma_addr;
-
-	sg->buf = dma_alloc_coherent(chan->device->dev,
-		PL011_DMA_BUFFER_SIZE, &dma_addr, GFP_KERNEL);
-	if (!sg->buf)
+	db->buf = dma_alloc_coherent(chan->device->dev, PL011_DMA_BUFFER_SIZE,
+				     &db->dma, GFP_KERNEL);
+	if (!db->buf)
 		return -ENOMEM;
-
-	sg_init_table(&sg->sg, 1);
-	sg_set_page(&sg->sg, phys_to_page(dma_addr),
-		PL011_DMA_BUFFER_SIZE, offset_in_page(dma_addr));
-	sg_dma_address(&sg->sg) = dma_addr;
-	sg_dma_len(&sg->sg) = PL011_DMA_BUFFER_SIZE;
+	db->len = PL011_DMA_BUFFER_SIZE;
 
 	return 0;
 }
 
-static void pl011_sgbuf_free(struct dma_chan *chan, struct pl011_sgbuf *sg,
+static void pl011_dmabuf_free(struct dma_chan *chan, struct pl011_dmabuf *db,
 	enum dma_data_direction dir)
 {
-	if (sg->buf) {
+	if (db->buf) {
 		dma_free_coherent(chan->device->dev,
-			PL011_DMA_BUFFER_SIZE, sg->buf,
-			sg_dma_address(&sg->sg));
+				  PL011_DMA_BUFFER_SIZE, db->buf, db->dma);
 	}
 }
 
@@ -552,8 +546,8 @@ static void pl011_dma_tx_callback(void *data)
 
 	uart_port_lock_irqsave(&uap->port, &flags);
 	if (uap->dmatx.queued)
-		dma_unmap_sg(dmatx->chan->device->dev, &dmatx->sg, 1,
-			     DMA_TO_DEVICE);
+		dma_unmap_single(dmatx->chan->device->dev, dmatx->dma,
+				dmatx->len, DMA_TO_DEVICE);
 
 	dmacr = uap->dmacr;
 	uap->dmacr = dmacr & ~UART011_TXDMAE;
@@ -639,18 +633,19 @@ static int pl011_dma_tx_refill(struct uart_amba_port *uap)
 			memcpy(&dmatx->buf[first], &xmit->buf[0], second);
 	}
 
-	dmatx->sg.length = count;
-
-	if (dma_map_sg(dma_dev->dev, &dmatx->sg, 1, DMA_TO_DEVICE) != 1) {
+	dmatx->len = count;
+	dmatx->dma = dma_map_single(dma_dev->dev, dmatx->buf, count,
+				    DMA_TO_DEVICE);
+	if (dmatx->dma == DMA_MAPPING_ERROR) {
 		uap->dmatx.queued = false;
 		dev_dbg(uap->port.dev, "unable to map TX DMA\n");
 		return -EBUSY;
 	}
 
-	desc = dmaengine_prep_slave_sg(chan, &dmatx->sg, 1, DMA_MEM_TO_DEV,
+	desc = dmaengine_prep_slave_single(chan, dmatx->dma, dmatx->len, DMA_MEM_TO_DEV,
 					     DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc) {
-		dma_unmap_sg(dma_dev->dev, &dmatx->sg, 1, DMA_TO_DEVICE);
+		dma_unmap_single(dma_dev->dev, dmatx->dma, dmatx->len, DMA_TO_DEVICE);
 		uap->dmatx.queued = false;
 		/*
 		 * If DMA cannot be used right now, we complete this
@@ -813,8 +808,8 @@ __acquires(&uap->port.lock)
 	dmaengine_terminate_async(uap->dmatx.chan);
 
 	if (uap->dmatx.queued) {
-		dma_unmap_sg(uap->dmatx.chan->device->dev, &uap->dmatx.sg, 1,
-			     DMA_TO_DEVICE);
+		dma_unmap_single(uap->dmatx.chan->device->dev, uap->dmatx.dma,
+				 uap->dmatx.len, DMA_TO_DEVICE);
 		uap->dmatx.queued = false;
 		uap->dmacr &= ~UART011_TXDMAE;
 		pl011_write(uap->dmacr, uap, REG_DMACR);
@@ -828,15 +823,15 @@ static int pl011_dma_rx_trigger_dma(struct uart_amba_port *uap)
 	struct dma_chan *rxchan = uap->dmarx.chan;
 	struct pl011_dmarx_data *dmarx = &uap->dmarx;
 	struct dma_async_tx_descriptor *desc;
-	struct pl011_sgbuf *sgbuf;
+	struct pl011_dmabuf *dbuf;
 
 	if (!rxchan)
 		return -EIO;
 
 	/* Start the RX DMA job */
-	sgbuf = uap->dmarx.use_buf_b ?
-		&uap->dmarx.sgbuf_b : &uap->dmarx.sgbuf_a;
-	desc = dmaengine_prep_slave_sg(rxchan, &sgbuf->sg, 1,
+	dbuf = uap->dmarx.use_buf_b ?
+		&uap->dmarx.dbuf_b : &uap->dmarx.dbuf_a;
+	desc = dmaengine_prep_slave_single(rxchan, dbuf->dma, dbuf->len,
 					DMA_DEV_TO_MEM,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	/*
@@ -876,8 +871,8 @@ static void pl011_dma_rx_chars(struct uart_amba_port *uap,
 			       bool readfifo)
 {
 	struct tty_port *port = &uap->port.state->port;
-	struct pl011_sgbuf *sgbuf = use_buf_b ?
-		&uap->dmarx.sgbuf_b : &uap->dmarx.sgbuf_a;
+	struct pl011_dmabuf *dbuf = use_buf_b ?
+		&uap->dmarx.dbuf_b : &uap->dmarx.dbuf_a;
 	int dma_count = 0;
 	u32 fifotaken = 0; /* only used for vdbg() */
 
@@ -886,7 +881,7 @@ static void pl011_dma_rx_chars(struct uart_amba_port *uap,
 
 	if (uap->dmarx.poll_rate) {
 		/* The data can be taken by polling */
-		dmataken = sgbuf->sg.length - dmarx->last_residue;
+		dmataken = dbuf->len - dmarx->last_residue;
 		/* Recalculate the pending size */
 		if (pending >= dmataken)
 			pending -= dmataken;
@@ -900,7 +895,7 @@ static void pl011_dma_rx_chars(struct uart_amba_port *uap,
 		 * Note that tty_insert_flip_buf() tries to take as many chars
 		 * as it can.
 		 */
-		dma_count = tty_insert_flip_string(port, sgbuf->buf + dmataken,
+		dma_count = tty_insert_flip_string(port, dbuf->buf + dmataken,
 				pending);
 
 		uap->port.icount.rx += dma_count;
@@ -911,7 +906,7 @@ static void pl011_dma_rx_chars(struct uart_amba_port *uap,
 
 	/* Reset the last_residue for Rx DMA poll */
 	if (uap->dmarx.poll_rate)
-		dmarx->last_residue = sgbuf->sg.length;
+		dmarx->last_residue = dbuf->len;
 
 	/*
 	 * Only continue with trying to read the FIFO if all DMA chars have
@@ -946,8 +941,8 @@ static void pl011_dma_rx_irq(struct uart_amba_port *uap)
 {
 	struct pl011_dmarx_data *dmarx = &uap->dmarx;
 	struct dma_chan *rxchan = dmarx->chan;
-	struct pl011_sgbuf *sgbuf = dmarx->use_buf_b ?
-		&dmarx->sgbuf_b : &dmarx->sgbuf_a;
+	struct pl011_dmabuf *dbuf = dmarx->use_buf_b ?
+		&dmarx->dbuf_b : &dmarx->dbuf_a;
 	size_t pending;
 	struct dma_tx_state state;
 	enum dma_status dmastat;
@@ -969,7 +964,7 @@ static void pl011_dma_rx_irq(struct uart_amba_port *uap)
 	pl011_write(uap->dmacr, uap, REG_DMACR);
 	uap->dmarx.running = false;
 
-	pending = sgbuf->sg.length - state.residue;
+	pending = dbuf->len - state.residue;
 	BUG_ON(pending > PL011_DMA_BUFFER_SIZE);
 	/* Then we terminate the transfer - we now know our residue */
 	dmaengine_terminate_all(rxchan);
@@ -996,8 +991,8 @@ static void pl011_dma_rx_callback(void *data)
 	struct pl011_dmarx_data *dmarx = &uap->dmarx;
 	struct dma_chan *rxchan = dmarx->chan;
 	bool lastbuf = dmarx->use_buf_b;
-	struct pl011_sgbuf *sgbuf = dmarx->use_buf_b ?
-		&dmarx->sgbuf_b : &dmarx->sgbuf_a;
+	struct pl011_dmabuf *dbuf = dmarx->use_buf_b ?
+		&dmarx->dbuf_b : &dmarx->dbuf_a;
 	size_t pending;
 	struct dma_tx_state state;
 	int ret;
@@ -1015,7 +1010,7 @@ static void pl011_dma_rx_callback(void *data)
 	 * the DMA irq handler. So we check the residue here.
 	 */
 	rxchan->device->device_tx_status(rxchan, dmarx->cookie, &state);
-	pending = sgbuf->sg.length - state.residue;
+	pending = dbuf->len - state.residue;
 	BUG_ON(pending > PL011_DMA_BUFFER_SIZE);
 	/* Then we terminate the transfer - we now know our residue */
 	dmaengine_terminate_all(rxchan);
@@ -1067,16 +1062,16 @@ static void pl011_dma_rx_poll(struct timer_list *t)
 	unsigned long flags;
 	unsigned int dmataken = 0;
 	unsigned int size = 0;
-	struct pl011_sgbuf *sgbuf;
+	struct pl011_dmabuf *dbuf;
 	int dma_count;
 	struct dma_tx_state state;
 
-	sgbuf = dmarx->use_buf_b ? &uap->dmarx.sgbuf_b : &uap->dmarx.sgbuf_a;
+	dbuf = dmarx->use_buf_b ? &uap->dmarx.dbuf_b : &uap->dmarx.dbuf_a;
 	rxchan->device->device_tx_status(rxchan, dmarx->cookie, &state);
 	if (likely(state.residue < dmarx->last_residue)) {
-		dmataken = sgbuf->sg.length - dmarx->last_residue;
+		dmataken = dbuf->len - dmarx->last_residue;
 		size = dmarx->last_residue - state.residue;
-		dma_count = tty_insert_flip_string(port, sgbuf->buf + dmataken,
+		dma_count = tty_insert_flip_string(port, dbuf->buf + dmataken,
 				size);
 		if (dma_count == size)
 			dmarx->last_residue =  state.residue;
@@ -1123,7 +1118,7 @@ static void pl011_dma_startup(struct uart_amba_port *uap)
 		return;
 	}
 
-	sg_init_one(&uap->dmatx.sg, uap->dmatx.buf, PL011_DMA_BUFFER_SIZE);
+	uap->dmatx.len = PL011_DMA_BUFFER_SIZE;
 
 	/* The DMA buffer is now the FIFO the TTY subsystem can use */
 	uap->port.fifosize = PL011_DMA_BUFFER_SIZE;
@@ -1133,7 +1128,7 @@ static void pl011_dma_startup(struct uart_amba_port *uap)
 		goto skip_rx;
 
 	/* Allocate and map DMA RX buffers */
-	ret = pl011_sgbuf_init(uap->dmarx.chan, &uap->dmarx.sgbuf_a,
+	ret = pl011_dmabuf_init(uap->dmarx.chan, &uap->dmarx.dbuf_a,
 			       DMA_FROM_DEVICE);
 	if (ret) {
 		dev_err(uap->port.dev, "failed to init DMA %s: %d\n",
@@ -1141,12 +1136,12 @@ static void pl011_dma_startup(struct uart_amba_port *uap)
 		goto skip_rx;
 	}
 
-	ret = pl011_sgbuf_init(uap->dmarx.chan, &uap->dmarx.sgbuf_b,
+	ret = pl011_dmabuf_init(uap->dmarx.chan, &uap->dmarx.dbuf_b,
 			       DMA_FROM_DEVICE);
 	if (ret) {
 		dev_err(uap->port.dev, "failed to init DMA %s: %d\n",
 			"RX buffer B", ret);
-		pl011_sgbuf_free(uap->dmarx.chan, &uap->dmarx.sgbuf_a,
+		pl011_dmabuf_free(uap->dmarx.chan, &uap->dmarx.dbuf_a,
 				 DMA_FROM_DEVICE);
 		goto skip_rx;
 	}
@@ -1200,8 +1195,9 @@ static void pl011_dma_shutdown(struct uart_amba_port *uap)
 		/* In theory, this should already be done by pl011_dma_flush_buffer */
 		dmaengine_terminate_all(uap->dmatx.chan);
 		if (uap->dmatx.queued) {
-			dma_unmap_sg(uap->dmatx.chan->device->dev, &uap->dmatx.sg, 1,
-				     DMA_TO_DEVICE);
+			dma_unmap_single(uap->dmatx.chan->device->dev,
+					 uap->dmatx.dma, uap->dmatx.len,
+					 DMA_TO_DEVICE);
 			uap->dmatx.queued = false;
 		}
 
@@ -1212,8 +1208,8 @@ static void pl011_dma_shutdown(struct uart_amba_port *uap)
 	if (uap->using_rx_dma) {
 		dmaengine_terminate_all(uap->dmarx.chan);
 		/* Clean up the RX DMA */
-		pl011_sgbuf_free(uap->dmarx.chan, &uap->dmarx.sgbuf_a, DMA_FROM_DEVICE);
-		pl011_sgbuf_free(uap->dmarx.chan, &uap->dmarx.sgbuf_b, DMA_FROM_DEVICE);
+		pl011_dmabuf_free(uap->dmarx.chan, &uap->dmarx.dbuf_a, DMA_FROM_DEVICE);
+		pl011_dmabuf_free(uap->dmarx.chan, &uap->dmarx.dbuf_b, DMA_FROM_DEVICE);
 		if (uap->dmarx.poll_rate)
 			del_timer_sync(&uap->dmarx.timer);
 		uap->using_rx_dma = false;
diff --git a/drivers/tty/serial/ma35d1_serial.c b/drivers/tty/serial/ma35d1_serial.c
index a6a7c405892e..21b574f78b86 100644
--- a/drivers/tty/serial/ma35d1_serial.c
+++ b/drivers/tty/serial/ma35d1_serial.c
@@ -552,11 +552,19 @@ static void ma35d1serial_console_putchar(struct uart_port *port, unsigned char c
  */
 static void ma35d1serial_console_write(struct console *co, const char *s, u32 count)
 {
-	struct uart_ma35d1_port *up = &ma35d1serial_ports[co->index];
+	struct uart_ma35d1_port *up;
 	unsigned long flags;
 	int locked = 1;
 	u32 ier;
 
+	if ((co->index < 0) || (co->index >= MA35_UART_NR)) {
+		pr_warn("Failed to write on ononsole port %x, out of range\n",
+			co->index);
+		return;
+	}
+
+	up = &ma35d1serial_ports[co->index];
+
 	if (up->port.sysrq)
 		locked = 0;
 	else if (oops_in_progress)
diff --git a/drivers/tty/serial/samsung_tty.c b/drivers/tty/serial/samsung_tty.c
index 3bd552841cd2..66bd6c090ace 100644
--- a/drivers/tty/serial/samsung_tty.c
+++ b/drivers/tty/serial/samsung_tty.c
@@ -2492,14 +2492,25 @@ static const struct s3c24xx_serial_drv_data exynos850_serial_drv_data = {
 	.fifosize = { 256, 64, 64, 64 },
 };
 
+/*
+ * Common drv_data struct for platforms that specify samsung,uart-fifosize in
+ * device tree.
+ */
+static const struct s3c24xx_serial_drv_data exynos_fifoszdt_serial_drv_data = {
+	EXYNOS_COMMON_SERIAL_DRV_DATA(),
+	.fifosize = { 0 },
+};
+
 #define EXYNOS4210_SERIAL_DRV_DATA (&exynos4210_serial_drv_data)
 #define EXYNOS5433_SERIAL_DRV_DATA (&exynos5433_serial_drv_data)
 #define EXYNOS850_SERIAL_DRV_DATA (&exynos850_serial_drv_data)
+#define EXYNOS_FIFOSZDT_DRV_DATA (&exynos_fifoszdt_serial_drv_data)
 
 #else
 #define EXYNOS4210_SERIAL_DRV_DATA NULL
 #define EXYNOS5433_SERIAL_DRV_DATA NULL
 #define EXYNOS850_SERIAL_DRV_DATA NULL
+#define EXYNOS_FIFOSZDT_DRV_DATA NULL
 #endif
 
 #ifdef CONFIG_ARCH_APPLE
@@ -2583,6 +2594,9 @@ static const struct platform_device_id s3c24xx_serial_driver_ids[] = {
 	}, {
 		.name		= "artpec8-uart",
 		.driver_data	= (kernel_ulong_t)ARTPEC8_SERIAL_DRV_DATA,
+	}, {
+		.name		= "gs101-uart",
+		.driver_data	= (kernel_ulong_t)EXYNOS_FIFOSZDT_DRV_DATA,
 	},
 	{ },
 };
@@ -2604,6 +2618,8 @@ static const struct of_device_id s3c24xx_uart_dt_match[] = {
 		.data = EXYNOS850_SERIAL_DRV_DATA },
 	{ .compatible = "axis,artpec8-uart",
 		.data = ARTPEC8_SERIAL_DRV_DATA },
+	{ .compatible = "google,gs101-uart",
+		.data = EXYNOS_FIFOSZDT_DRV_DATA },
 	{},
 };
 MODULE_DEVICE_TABLE(of, s3c24xx_uart_dt_match);
diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index db2bb1c0d36c..cf0c6120d30e 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -766,6 +766,18 @@ static bool sc16is7xx_port_irq(struct sc16is7xx_port *s, int portno)
 		case SC16IS7XX_IIR_RTOI_SRC:
 		case SC16IS7XX_IIR_XOFFI_SRC:
 			rxlen = sc16is7xx_port_read(port, SC16IS7XX_RXLVL_REG);
+
+			/*
+			 * There is a silicon bug that makes the chip report a
+			 * time-out interrupt but no data in the FIFO. This is
+			 * described in errata section 18.1.4.
+			 *
+			 * When this happens, read one byte from the FIFO to
+			 * clear the interrupt.
+			 */
+			if (iir == SC16IS7XX_IIR_RTOI_SRC && !rxlen)
+				rxlen = 1;
+
 			if (rxlen)
 				sc16is7xx_handle_rx(port, rxlen, iir);
 			break;
diff --git a/drivers/ufs/core/ufs-fault-injection.c b/drivers/ufs/core/ufs-fault-injection.c
index 5b1184aac585..169540417079 100644
--- a/drivers/ufs/core/ufs-fault-injection.c
+++ b/drivers/ufs/core/ufs-fault-injection.c
@@ -4,6 +4,7 @@
 #include <linux/types.h>
 #include <linux/fault-inject.h>
 #include <linux/module.h>
+#include <ufs/ufshcd.h>
 #include "ufs-fault-injection.h"
 
 static int ufs_fault_get(char *buffer, const struct kernel_param *kp);
@@ -59,12 +60,22 @@ static int ufs_fault_set(const char *val, const struct kernel_param *kp)
 	return 0;
 }
 
-bool ufs_trigger_eh(void)
+void ufs_fault_inject_hba_init(struct ufs_hba *hba)
 {
-	return should_fail(&ufs_trigger_eh_attr, 1);
+	hba->trigger_eh_attr = ufs_trigger_eh_attr;
+	hba->timeout_attr = ufs_timeout_attr;
+#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
+	fault_create_debugfs_attr("trigger_eh_inject", hba->debugfs_root, &hba->trigger_eh_attr);
+	fault_create_debugfs_attr("timeout_inject", hba->debugfs_root, &hba->timeout_attr);
+#endif
 }
 
-bool ufs_fail_completion(void)
+bool ufs_trigger_eh(struct ufs_hba *hba)
 {
-	return should_fail(&ufs_timeout_attr, 1);
+	return should_fail(&hba->trigger_eh_attr, 1);
+}
+
+bool ufs_fail_completion(struct ufs_hba *hba)
+{
+	return should_fail(&hba->timeout_attr, 1);
 }
diff --git a/drivers/ufs/core/ufs-fault-injection.h b/drivers/ufs/core/ufs-fault-injection.h
index 6d0cd8e10c87..996a35769781 100644
--- a/drivers/ufs/core/ufs-fault-injection.h
+++ b/drivers/ufs/core/ufs-fault-injection.h
@@ -7,15 +7,20 @@
 #include <linux/types.h>
 
 #ifdef CONFIG_SCSI_UFS_FAULT_INJECTION
-bool ufs_trigger_eh(void);
-bool ufs_fail_completion(void);
+void ufs_fault_inject_hba_init(struct ufs_hba *hba);
+bool ufs_trigger_eh(struct ufs_hba *hba);
+bool ufs_fail_completion(struct ufs_hba *hba);
 #else
-static inline bool ufs_trigger_eh(void)
+static inline void ufs_fault_inject_hba_init(struct ufs_hba *hba)
+{
+}
+
+static inline bool ufs_trigger_eh(struct ufs_hba *hba)
 {
 	return false;
 }
 
-static inline bool ufs_fail_completion(void)
+static inline bool ufs_fail_completion(struct ufs_hba *hba)
 {
 	return false;
 }
diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c
index 2ba8ec254dce..0787456c2b89 100644
--- a/drivers/ufs/core/ufs-mcq.c
+++ b/drivers/ufs/core/ufs-mcq.c
@@ -436,7 +436,7 @@ int ufshcd_mcq_init(struct ufs_hba *hba)
 
 	for (i = 0; i < hba->nr_hw_queues; i++) {
 		hwq = &hba->uhq[i];
-		hwq->max_entries = hba->nutrs;
+		hwq->max_entries = hba->nutrs + 1;
 		spin_lock_init(&hwq->sq_lock);
 		spin_lock_init(&hwq->cq_lock);
 		mutex_init(&hwq->sq_mutex);
@@ -630,6 +630,7 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd)
 	int tag = scsi_cmd_to_rq(cmd)->tag;
 	struct ufshcd_lrb *lrbp = &hba->lrb[tag];
 	struct ufs_hw_queue *hwq;
+	unsigned long flags;
 	int err = FAILED;
 
 	if (!ufshcd_cmd_inflight(lrbp->cmd)) {
@@ -670,8 +671,10 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd)
 	}
 
 	err = SUCCESS;
+	spin_lock_irqsave(&hwq->cq_lock, flags);
 	if (ufshcd_cmd_inflight(lrbp->cmd))
 		ufshcd_release_scsi_cmd(hba, lrbp);
+	spin_unlock_irqrestore(&hwq->cq_lock, flags);
 
 out:
 	return err;
diff --git a/drivers/ufs/core/ufs-sysfs.c b/drivers/ufs/core/ufs-sysfs.c
index c95906443d5f..e6d12289e017 100644
--- a/drivers/ufs/core/ufs-sysfs.c
+++ b/drivers/ufs/core/ufs-sysfs.c
@@ -7,9 +7,56 @@
 #include <asm/unaligned.h>
 
 #include <ufs/ufs.h>
+#include <ufs/unipro.h>
 #include "ufs-sysfs.h"
 #include "ufshcd-priv.h"
 
+static const char *ufs_pa_pwr_mode_to_string(enum ufs_pa_pwr_mode mode)
+{
+	switch (mode) {
+	case FAST_MODE:		return "FAST_MODE";
+	case SLOW_MODE:		return "SLOW_MODE";
+	case FASTAUTO_MODE:	return "FASTAUTO_MODE";
+	case SLOWAUTO_MODE:	return "SLOWAUTO_MODE";
+	default:		return "UNKNOWN";
+	}
+}
+
+static const char *ufs_hs_gear_rate_to_string(enum ufs_hs_gear_rate rate)
+{
+	switch (rate) {
+	case PA_HS_MODE_A:	return "HS_RATE_A";
+	case PA_HS_MODE_B:	return "HS_RATE_B";
+	default:		return "UNKNOWN";
+	}
+}
+
+static const char *ufs_pwm_gear_to_string(enum ufs_pwm_gear_tag gear)
+{
+	switch (gear) {
+	case UFS_PWM_G1:	return "PWM_GEAR1";
+	case UFS_PWM_G2:	return "PWM_GEAR2";
+	case UFS_PWM_G3:	return "PWM_GEAR3";
+	case UFS_PWM_G4:	return "PWM_GEAR4";
+	case UFS_PWM_G5:	return "PWM_GEAR5";
+	case UFS_PWM_G6:	return "PWM_GEAR6";
+	case UFS_PWM_G7:	return "PWM_GEAR7";
+	default:		return "UNKNOWN";
+	}
+}
+
+static const char *ufs_hs_gear_to_string(enum ufs_hs_gear_tag gear)
+{
+	switch (gear) {
+	case UFS_HS_G1:	return "HS_GEAR1";
+	case UFS_HS_G2:	return "HS_GEAR2";
+	case UFS_HS_G3:	return "HS_GEAR3";
+	case UFS_HS_G4:	return "HS_GEAR4";
+	case UFS_HS_G5:	return "HS_GEAR5";
+	default:	return "UNKNOWN";
+	}
+}
+
 static const char *ufshcd_uic_link_state_to_string(
 			enum uic_link_state state)
 {
@@ -255,6 +302,35 @@ out:
 	return res < 0 ? res : count;
 }
 
+static ssize_t rtc_update_ms_show(struct device *dev, struct device_attribute *attr,
+				  char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%d\n", hba->dev_info.rtc_update_period);
+}
+
+static ssize_t rtc_update_ms_store(struct device *dev, struct device_attribute *attr,
+				   const char *buf, size_t count)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+	unsigned int ms;
+	bool resume_period_update = false;
+
+	if (kstrtouint(buf, 0, &ms))
+		return -EINVAL;
+
+	if (!hba->dev_info.rtc_update_period && ms > 0)
+		resume_period_update =  true;
+	/* Minimum and maximum update frequency should be synchronized with all UFS vendors */
+	hba->dev_info.rtc_update_period = ms;
+
+	if (resume_period_update)
+		schedule_delayed_work(&hba->ufs_rtc_update_work,
+				      msecs_to_jiffies(hba->dev_info.rtc_update_period));
+	return count;
+}
+
 static ssize_t enable_wb_buf_flush_show(struct device *dev,
 				    struct device_attribute *attr,
 				    char *buf)
@@ -339,6 +415,7 @@ static DEVICE_ATTR_RW(auto_hibern8);
 static DEVICE_ATTR_RW(wb_on);
 static DEVICE_ATTR_RW(enable_wb_buf_flush);
 static DEVICE_ATTR_RW(wb_flush_threshold);
+static DEVICE_ATTR_RW(rtc_update_ms);
 
 static struct attribute *ufs_sysfs_ufshcd_attrs[] = {
 	&dev_attr_rpm_lvl.attr,
@@ -351,6 +428,7 @@ static struct attribute *ufs_sysfs_ufshcd_attrs[] = {
 	&dev_attr_wb_on.attr,
 	&dev_attr_enable_wb_buf_flush.attr,
 	&dev_attr_wb_flush_threshold.attr,
+	&dev_attr_rtc_update_ms.attr,
 	NULL
 };
 
@@ -628,6 +706,78 @@ static const struct attribute_group ufs_sysfs_monitor_group = {
 	.attrs = ufs_sysfs_monitor_attrs,
 };
 
+static ssize_t lane_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%u\n", hba->pwr_info.lane_rx);
+}
+
+static ssize_t mode_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%s\n", ufs_pa_pwr_mode_to_string(hba->pwr_info.pwr_rx));
+}
+
+static ssize_t rate_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%s\n", ufs_hs_gear_rate_to_string(hba->pwr_info.hs_rate));
+}
+
+static ssize_t gear_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%s\n", hba->pwr_info.hs_rate ?
+			  ufs_hs_gear_to_string(hba->pwr_info.gear_rx) :
+			  ufs_pwm_gear_to_string(hba->pwr_info.gear_rx));
+}
+
+static ssize_t dev_pm_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%s\n", ufshcd_ufs_dev_pwr_mode_to_string(hba->curr_dev_pwr_mode));
+}
+
+static ssize_t link_state_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%s\n", ufshcd_uic_link_state_to_string(hba->uic_link_state));
+}
+
+static DEVICE_ATTR_RO(lane);
+static DEVICE_ATTR_RO(mode);
+static DEVICE_ATTR_RO(rate);
+static DEVICE_ATTR_RO(gear);
+static DEVICE_ATTR_RO(dev_pm);
+static DEVICE_ATTR_RO(link_state);
+
+static struct attribute *ufs_power_info_attrs[] = {
+	&dev_attr_lane.attr,
+	&dev_attr_mode.attr,
+	&dev_attr_rate.attr,
+	&dev_attr_gear.attr,
+	&dev_attr_dev_pm.attr,
+	&dev_attr_link_state.attr,
+	NULL
+};
+
+static const struct attribute_group ufs_sysfs_power_info_group = {
+	.name = "power_info",
+	.attrs = ufs_power_info_attrs,
+};
+
 static ssize_t ufs_sysfs_read_desc_param(struct ufs_hba *hba,
 				  enum desc_idn desc_id,
 				  u8 desc_index,
@@ -1233,6 +1383,7 @@ static const struct attribute_group *ufs_sysfs_groups[] = {
 	&ufs_sysfs_default_group,
 	&ufs_sysfs_capabilities_group,
 	&ufs_sysfs_monitor_group,
+	&ufs_sysfs_power_info_group,
 	&ufs_sysfs_device_descriptor_group,
 	&ufs_sysfs_interconnect_descriptor_group,
 	&ufs_sysfs_geometry_descriptor_group,
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 8b1031fb0a44..d1e33328ff3f 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -99,6 +99,9 @@
 /* Polling time to wait for fDeviceInit */
 #define FDEVICEINIT_COMPL_TIMEOUT 1500 /* millisecs */
 
+/* Default RTC update every 10 seconds */
+#define UFS_RTC_UPDATE_INTERVAL_MS (10 * MSEC_PER_SEC)
+
 /* UFSHC 4.0 compliant HC support this mode. */
 static bool use_mcq_mode = true;
 
@@ -235,6 +238,12 @@ ufs_get_desired_pm_lvl_for_dev_link_state(enum ufs_dev_pwr_mode dev_state,
 	return UFS_PM_LVL_0;
 }
 
+static bool ufshcd_is_ufs_dev_busy(struct ufs_hba *hba)
+{
+	return (hba->clk_gating.active_reqs || hba->outstanding_reqs || hba->outstanding_tasks ||
+		hba->active_uic_cmd || hba->uic_async_done);
+}
+
 static const struct ufs_dev_quirk ufs_fixups[] = {
 	/* UFS cards deviations table */
 	{ .wmanufacturerid = UFS_VENDOR_MICRON,
@@ -289,21 +298,23 @@ static void ufshcd_wb_toggle_buf_flush_during_h8(struct ufs_hba *hba,
 static void ufshcd_hba_vreg_set_lpm(struct ufs_hba *hba);
 static void ufshcd_hba_vreg_set_hpm(struct ufs_hba *hba);
 
-static inline void ufshcd_enable_irq(struct ufs_hba *hba)
+void ufshcd_enable_irq(struct ufs_hba *hba)
 {
 	if (!hba->is_irq_enabled) {
 		enable_irq(hba->irq);
 		hba->is_irq_enabled = true;
 	}
 }
+EXPORT_SYMBOL_GPL(ufshcd_enable_irq);
 
-static inline void ufshcd_disable_irq(struct ufs_hba *hba)
+void ufshcd_disable_irq(struct ufs_hba *hba)
 {
 	if (hba->is_irq_enabled) {
 		disable_irq(hba->irq);
 		hba->is_irq_enabled = false;
 	}
 }
+EXPORT_SYMBOL_GPL(ufshcd_disable_irq);
 
 static void ufshcd_configure_wb(struct ufs_hba *hba)
 {
@@ -677,6 +688,8 @@ static void ufshcd_device_reset(struct ufs_hba *hba)
 			hba->dev_info.wb_enabled = false;
 			hba->dev_info.wb_buf_flush_enabled = false;
 		}
+		if (hba->dev_info.rtc_type == UFS_RTC_RELATIVE)
+			hba->dev_info.rtc_time_baseline = 0;
 	}
 	if (err != -EOPNOTSUPP)
 		ufshcd_update_evt_hist(hba, UFS_EVT_DEV_RESET, err);
@@ -1917,10 +1930,7 @@ static void ufshcd_gate_work(struct work_struct *work)
 		goto rel_lock;
 	}
 
-	if (hba->clk_gating.active_reqs
-		|| hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL
-		|| hba->outstanding_reqs || hba->outstanding_tasks
-		|| hba->active_uic_cmd || hba->uic_async_done)
+	if (ufshcd_is_ufs_dev_busy(hba) || hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL)
 		goto rel_lock;
 
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
@@ -2274,9 +2284,10 @@ void ufshcd_send_command(struct ufs_hba *hba, unsigned int task_tag,
 	if (is_mcq_enabled(hba)) {
 		int utrd_size = sizeof(struct utp_transfer_req_desc);
 		struct utp_transfer_req_desc *src = lrbp->utr_descriptor_ptr;
-		struct utp_transfer_req_desc *dest = hwq->sqe_base_addr + hwq->sq_tail_slot;
+		struct utp_transfer_req_desc *dest;
 
 		spin_lock(&hwq->sq_lock);
+		dest = hwq->sqe_base_addr + hwq->sq_tail_slot;
 		memcpy(dest, src, utrd_size);
 		ufshcd_inc_sq_tail(hwq);
 		spin_unlock(&hwq->sq_lock);
@@ -2720,6 +2731,8 @@ void ufshcd_prepare_utp_scsi_cmd_upiu(struct ufshcd_lrb *lrbp, u8 upiu_flags)
 		.command_set_type = UPIU_COMMAND_SET_TYPE_SCSI,
 	};
 
+	WARN_ON_ONCE(ucd_req_ptr->header.task_tag != lrbp->task_tag);
+
 	ucd_req_ptr->sc.exp_data_transfer_len = cpu_to_be32(cmd->sdb.length);
 
 	cdb_len = min_t(unsigned short, cmd->cmd_len, UFS_CDB_SIZE);
@@ -2992,7 +3005,7 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 	ufshcd_send_command(hba, tag, hwq);
 
 out:
-	if (ufs_trigger_eh()) {
+	if (ufs_trigger_eh(hba)) {
 		unsigned long flags;
 
 		spin_lock_irqsave(hba->host->host_lock, flags);
@@ -4401,40 +4414,32 @@ int ufshcd_uic_hibern8_exit(struct ufs_hba *hba)
 }
 EXPORT_SYMBOL_GPL(ufshcd_uic_hibern8_exit);
 
-void ufshcd_auto_hibern8_update(struct ufs_hba *hba, u32 ahit)
+static void ufshcd_configure_auto_hibern8(struct ufs_hba *hba)
 {
-	unsigned long flags;
-	bool update = false;
-
 	if (!ufshcd_is_auto_hibern8_supported(hba))
 		return;
 
-	spin_lock_irqsave(hba->host->host_lock, flags);
-	if (hba->ahit != ahit) {
-		hba->ahit = ahit;
-		update = true;
-	}
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
+	ufshcd_writel(hba, hba->ahit, REG_AUTO_HIBERNATE_IDLE_TIMER);
+}
+
+void ufshcd_auto_hibern8_update(struct ufs_hba *hba, u32 ahit)
+{
+	const u32 cur_ahit = READ_ONCE(hba->ahit);
+
+	if (!ufshcd_is_auto_hibern8_supported(hba) || cur_ahit == ahit)
+		return;
 
-	if (update &&
-	    !pm_runtime_suspended(&hba->ufs_device_wlun->sdev_gendev)) {
+	WRITE_ONCE(hba->ahit, ahit);
+	if (!pm_runtime_suspended(&hba->ufs_device_wlun->sdev_gendev)) {
 		ufshcd_rpm_get_sync(hba);
 		ufshcd_hold(hba);
-		ufshcd_auto_hibern8_enable(hba);
+		ufshcd_configure_auto_hibern8(hba);
 		ufshcd_release(hba);
 		ufshcd_rpm_put_sync(hba);
 	}
 }
 EXPORT_SYMBOL_GPL(ufshcd_auto_hibern8_update);
 
-void ufshcd_auto_hibern8_enable(struct ufs_hba *hba)
-{
-	if (!ufshcd_is_auto_hibern8_supported(hba))
-		return;
-
-	ufshcd_writel(hba, hba->ahit, REG_AUTO_HIBERNATE_IDLE_TIMER);
-}
-
  /**
  * ufshcd_init_pwr_info - setting the POR (power on reset)
  * values in hba power info
@@ -5649,7 +5654,7 @@ static irqreturn_t ufshcd_transfer_req_compl(struct ufs_hba *hba)
 	    !(hba->quirks & UFSHCI_QUIRK_SKIP_RESET_INTR_AGGR))
 		ufshcd_reset_intr_aggr(hba);
 
-	if (ufs_fail_completion())
+	if (ufs_fail_completion(hba))
 		return IRQ_HANDLED;
 
 	/*
@@ -6444,11 +6449,24 @@ static bool ufshcd_abort_one(struct request *rq, void *priv)
 	struct scsi_device *sdev = cmd->device;
 	struct Scsi_Host *shost = sdev->host;
 	struct ufs_hba *hba = shost_priv(shost);
+	struct ufshcd_lrb *lrbp = &hba->lrb[tag];
+	struct ufs_hw_queue *hwq;
+	unsigned long flags;
 
 	*ret = ufshcd_try_to_abort_task(hba, tag);
 	dev_err(hba->dev, "Aborting tag %d / CDB %#02x %s\n", tag,
 		hba->lrb[tag].cmd ? hba->lrb[tag].cmd->cmnd[0] : -1,
 		*ret ? "failed" : "succeeded");
+
+	/* Release cmd in MCQ mode if abort succeeds */
+	if (is_mcq_enabled(hba) && (*ret == 0)) {
+		hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(lrbp->cmd));
+		spin_lock_irqsave(&hwq->cq_lock, flags);
+		if (ufshcd_cmd_inflight(lrbp->cmd))
+			ufshcd_release_scsi_cmd(hba, lrbp);
+		spin_unlock_irqrestore(&hwq->cq_lock, flags);
+	}
+
 	return *ret == 0;
 }
 
@@ -8185,6 +8203,79 @@ static void ufs_fixup_device_setup(struct ufs_hba *hba)
 	ufshcd_vops_fixup_dev_quirks(hba);
 }
 
+static void ufshcd_update_rtc(struct ufs_hba *hba)
+{
+	struct timespec64 ts64;
+	int err;
+	u32 val;
+
+	ktime_get_real_ts64(&ts64);
+
+	if (ts64.tv_sec < hba->dev_info.rtc_time_baseline) {
+		dev_warn_once(hba->dev, "%s: Current time precedes previous setting!\n", __func__);
+		return;
+	}
+
+	/*
+	 * The Absolute RTC mode has a 136-year limit, spanning from 2010 to 2146. If a time beyond
+	 * 2146 is required, it is recommended to choose the relative RTC mode.
+	 */
+	val = ts64.tv_sec - hba->dev_info.rtc_time_baseline;
+
+	ufshcd_rpm_get_sync(hba);
+	err = ufshcd_query_attr(hba, UPIU_QUERY_OPCODE_WRITE_ATTR, QUERY_ATTR_IDN_SECONDS_PASSED,
+				0, 0, &val);
+	ufshcd_rpm_put_sync(hba);
+
+	if (err)
+		dev_err(hba->dev, "%s: Failed to update rtc %d\n", __func__, err);
+	else if (hba->dev_info.rtc_type == UFS_RTC_RELATIVE)
+		hba->dev_info.rtc_time_baseline = ts64.tv_sec;
+}
+
+static void ufshcd_rtc_work(struct work_struct *work)
+{
+	struct ufs_hba *hba;
+
+	hba = container_of(to_delayed_work(work), struct ufs_hba, ufs_rtc_update_work);
+
+	 /* Update RTC only when there are no requests in progress and UFSHCI is operational */
+	if (!ufshcd_is_ufs_dev_busy(hba) && hba->ufshcd_state == UFSHCD_STATE_OPERATIONAL)
+		ufshcd_update_rtc(hba);
+
+	if (ufshcd_is_ufs_dev_active(hba) && hba->dev_info.rtc_update_period)
+		schedule_delayed_work(&hba->ufs_rtc_update_work,
+				      msecs_to_jiffies(hba->dev_info.rtc_update_period));
+}
+
+static void ufs_init_rtc(struct ufs_hba *hba, u8 *desc_buf)
+{
+	u16 periodic_rtc_update = get_unaligned_be16(&desc_buf[DEVICE_DESC_PARAM_FRQ_RTC]);
+	struct ufs_dev_info *dev_info = &hba->dev_info;
+
+	if (periodic_rtc_update & UFS_RTC_TIME_BASELINE) {
+		dev_info->rtc_type = UFS_RTC_ABSOLUTE;
+
+		/*
+		 * The concept of measuring time in Linux as the number of seconds elapsed since
+		 * 00:00:00 UTC on January 1, 1970, and UFS ABS RTC is elapsed from January 1st
+		 * 2010 00:00, here we need to adjust ABS baseline.
+		 */
+		dev_info->rtc_time_baseline = mktime64(2010, 1, 1, 0, 0, 0) -
+							mktime64(1970, 1, 1, 0, 0, 0);
+	} else {
+		dev_info->rtc_type = UFS_RTC_RELATIVE;
+		dev_info->rtc_time_baseline = 0;
+	}
+
+	/*
+	 * We ignore TIME_PERIOD defined in wPeriodicRTCUpdate because Spec does not clearly state
+	 * how to calculate the specific update period for each time unit. And we disable periodic
+	 * RTC update work, let user configure by sysfs node according to specific circumstance.
+	 */
+	dev_info->rtc_update_period = 0;
+}
+
 static int ufs_get_device_desc(struct ufs_hba *hba)
 {
 	int err;
@@ -8237,6 +8328,8 @@ static int ufs_get_device_desc(struct ufs_hba *hba)
 
 	ufshcd_temp_notif_probe(hba, desc_buf);
 
+	ufs_init_rtc(hba, desc_buf);
+
 	if (hba->ext_iid_sup)
 		ufshcd_ext_iid_probe(hba, desc_buf);
 
@@ -8790,6 +8883,8 @@ static int ufshcd_device_init(struct ufs_hba *hba, bool init_dev_params)
 	ufshcd_force_reset_auto_bkops(hba);
 
 	ufshcd_set_timestamp_attr(hba);
+	schedule_delayed_work(&hba->ufs_rtc_update_work,
+			      msecs_to_jiffies(UFS_RTC_UPDATE_INTERVAL_MS));
 
 	/* Gear up to HS gear if supported */
 	if (hba->max_pwr_info.is_valid) {
@@ -8864,8 +8959,7 @@ static int ufshcd_probe_hba(struct ufs_hba *hba, bool init_dev_params)
 
 	if (hba->ee_usr_mask)
 		ufshcd_write_ee_control(hba);
-	/* Enable Auto-Hibernate if configured */
-	ufshcd_auto_hibern8_enable(hba);
+	ufshcd_configure_auto_hibern8(hba);
 
 out:
 	spin_lock_irqsave(hba->host->host_lock, flags);
@@ -9348,6 +9442,7 @@ static int ufshcd_hba_init(struct ufs_hba *hba)
 		goto out_disable_vreg;
 
 	ufs_debugfs_hba_init(hba);
+	ufs_fault_inject_hba_init(hba);
 
 	hba->is_powered = true;
 	goto out;
@@ -9746,6 +9841,8 @@ vops_suspend:
 	ret = ufshcd_vops_suspend(hba, pm_op, POST_CHANGE);
 	if (ret)
 		goto set_link_active;
+
+	cancel_delayed_work_sync(&hba->ufs_rtc_update_work);
 	goto out;
 
 set_link_active:
@@ -9840,6 +9937,8 @@ static int __ufshcd_wl_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 		if (ret)
 			goto set_old_link_state;
 		ufshcd_set_timestamp_attr(hba);
+		schedule_delayed_work(&hba->ufs_rtc_update_work,
+				      msecs_to_jiffies(UFS_RTC_UPDATE_INTERVAL_MS));
 	}
 
 	if (ufshcd_keep_autobkops_enabled_except_suspend(hba))
@@ -9862,8 +9961,7 @@ static int __ufshcd_wl_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 		cancel_delayed_work(&hba->rpm_dev_flush_recheck_work);
 	}
 
-	/* Enable Auto-Hibernate if configured */
-	ufshcd_auto_hibern8_enable(hba);
+	ufshcd_configure_auto_hibern8(hba);
 
 	goto out;
 
@@ -10536,8 +10634,8 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 						UFS_SLEEP_PWR_MODE,
 						UIC_LINK_HIBERN8_STATE);
 
-	INIT_DELAYED_WORK(&hba->rpm_dev_flush_recheck_work,
-			  ufshcd_rpm_dev_flush_recheck_work);
+	INIT_DELAYED_WORK(&hba->rpm_dev_flush_recheck_work, ufshcd_rpm_dev_flush_recheck_work);
+	INIT_DELAYED_WORK(&hba->ufs_rtc_update_work, ufshcd_rtc_work);
 
 	/* Set the default auto-hiberate idle timer value to 150 ms */
 	if (ufshcd_is_auto_hibern8_supported(hba) && !hba->ahit) {
diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c
index 71bd6dbc0547..734d40f99e31 100644
--- a/drivers/ufs/host/ufs-exynos.c
+++ b/drivers/ufs/host/ufs-exynos.c
@@ -765,7 +765,7 @@ static int exynos_ufs_pre_pwr_mode(struct ufs_hba *hba,
 {
 	struct exynos_ufs *ufs = ufshcd_get_variant(hba);
 	struct phy *generic_phy = ufs->phy;
-	struct ufs_dev_params ufs_exynos_cap;
+	struct ufs_host_params host_params;
 	int ret;
 
 	if (!dev_req_params) {
@@ -774,10 +774,9 @@ static int exynos_ufs_pre_pwr_mode(struct ufs_hba *hba,
 		goto out;
 	}
 
-	ufshcd_init_pwr_dev_param(&ufs_exynos_cap);
+	ufshcd_init_host_params(&host_params);
 
-	ret = ufshcd_get_pwr_dev_param(&ufs_exynos_cap,
-				       dev_max_params, dev_req_params);
+	ret = ufshcd_negotiate_pwr_params(&host_params, dev_max_params, dev_req_params);
 	if (ret) {
 		pr_err("%s: failed to determine capabilities\n", __func__);
 		goto out;
diff --git a/drivers/ufs/host/ufs-hisi.c b/drivers/ufs/host/ufs-hisi.c
index 0229ac0a8dbe..5ee73ff05251 100644
--- a/drivers/ufs/host/ufs-hisi.c
+++ b/drivers/ufs/host/ufs-hisi.c
@@ -293,9 +293,9 @@ static int ufs_hisi_link_startup_notify(struct ufs_hba *hba,
 	return err;
 }
 
-static void ufs_hisi_set_dev_cap(struct ufs_dev_params *hisi_param)
+static void ufs_hisi_set_dev_cap(struct ufs_host_params *host_params)
 {
-	ufshcd_init_pwr_dev_param(hisi_param);
+	ufshcd_init_host_params(host_params);
 }
 
 static void ufs_hisi_pwr_change_pre_change(struct ufs_hba *hba)
@@ -365,7 +365,7 @@ static int ufs_hisi_pwr_change_notify(struct ufs_hba *hba,
 				       struct ufs_pa_layer_attr *dev_max_params,
 				       struct ufs_pa_layer_attr *dev_req_params)
 {
-	struct ufs_dev_params ufs_hisi_cap;
+	struct ufs_host_params host_params;
 	int ret = 0;
 
 	if (!dev_req_params) {
@@ -377,9 +377,8 @@ static int ufs_hisi_pwr_change_notify(struct ufs_hba *hba,
 
 	switch (status) {
 	case PRE_CHANGE:
-		ufs_hisi_set_dev_cap(&ufs_hisi_cap);
-		ret = ufshcd_get_pwr_dev_param(&ufs_hisi_cap,
-					       dev_max_params, dev_req_params);
+		ufs_hisi_set_dev_cap(&host_params);
+		ret = ufshcd_negotiate_pwr_params(&host_params, dev_max_params, dev_req_params);
 		if (ret) {
 			dev_err(hba->dev,
 			    "%s: failed to determine capabilities\n", __func__);
diff --git a/drivers/ufs/host/ufs-mediatek.c b/drivers/ufs/host/ufs-mediatek.c
index fc61790d289b..776bca4f70c8 100644
--- a/drivers/ufs/host/ufs-mediatek.c
+++ b/drivers/ufs/host/ufs-mediatek.c
@@ -996,16 +996,14 @@ static int ufs_mtk_pre_pwr_change(struct ufs_hba *hba,
 				  struct ufs_pa_layer_attr *dev_req_params)
 {
 	struct ufs_mtk_host *host = ufshcd_get_variant(hba);
-	struct ufs_dev_params host_cap;
+	struct ufs_host_params host_params;
 	int ret;
 
-	ufshcd_init_pwr_dev_param(&host_cap);
-	host_cap.hs_rx_gear = UFS_HS_G5;
-	host_cap.hs_tx_gear = UFS_HS_G5;
+	ufshcd_init_host_params(&host_params);
+	host_params.hs_rx_gear = UFS_HS_G5;
+	host_params.hs_tx_gear = UFS_HS_G5;
 
-	ret = ufshcd_get_pwr_dev_param(&host_cap,
-				       dev_max_params,
-				       dev_req_params);
+	ret = ufshcd_negotiate_pwr_params(&host_params, dev_max_params, dev_req_params);
 	if (ret) {
 		pr_info("%s: failed to determine capabilities\n",
 			__func__);
diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c
index 96cb8b5b4e66..480787048e75 100644
--- a/drivers/ufs/host/ufs-qcom.c
+++ b/drivers/ufs/host/ufs-qcom.c
@@ -4,26 +4,26 @@
  */
 
 #include <linux/acpi.h>
-#include <linux/time.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
+#include <linux/devfreq.h>
+#include <linux/gpio/consumer.h>
 #include <linux/interconnect.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/platform_device.h>
 #include <linux/phy/phy.h>
-#include <linux/gpio/consumer.h>
+#include <linux/platform_device.h>
 #include <linux/reset-controller.h>
-#include <linux/devfreq.h>
+#include <linux/time.h>
 
 #include <soc/qcom/ice.h>
 
 #include <ufs/ufshcd.h>
-#include "ufshcd-pltfrm.h"
-#include <ufs/unipro.h>
-#include "ufs-qcom.h"
 #include <ufs/ufshci.h>
 #include <ufs/ufs_quirks.h>
+#include <ufs/unipro.h>
+#include "ufshcd-pltfrm.h"
+#include "ufs-qcom.h"
 
 #define MCQ_QCFGPTR_MASK	GENMASK(7, 0)
 #define MCQ_QCFGPTR_UNIT	0x200
@@ -90,8 +90,6 @@ static const struct __ufs_qcom_bw_table {
 	[MODE_MAX][0][0]		    = { 7643136,	307200 },
 };
 
-static struct ufs_qcom_host *ufs_qcom_hosts[MAX_UFS_QCOM_HOSTS];
-
 static void ufs_qcom_get_default_testbus_cfg(struct ufs_qcom_host *host);
 static int ufs_qcom_set_core_clk_ctrl(struct ufs_hba *hba, bool is_scale_up);
 
@@ -158,7 +156,7 @@ static int ufs_qcom_ice_program_key(struct ufs_hba *hba,
 	cap = hba->crypto_cap_array[cfg->crypto_cap_idx];
 	if (cap.algorithm_id != UFS_CRYPTO_ALG_AES_XTS ||
 	    cap.key_size != UFS_CRYPTO_KEY_SIZE_256)
-		return -EINVAL;
+		return -EOPNOTSUPP;
 
 	if (config_enable)
 		return qcom_ice_program_key(host->ice,
@@ -194,52 +192,12 @@ static inline int ufs_qcom_ice_suspend(struct ufs_qcom_host *host)
 }
 #endif
 
-static int ufs_qcom_host_clk_get(struct device *dev,
-		const char *name, struct clk **clk_out, bool optional)
-{
-	struct clk *clk;
-	int err = 0;
-
-	clk = devm_clk_get(dev, name);
-	if (!IS_ERR(clk)) {
-		*clk_out = clk;
-		return 0;
-	}
-
-	err = PTR_ERR(clk);
-
-	if (optional && err == -ENOENT) {
-		*clk_out = NULL;
-		return 0;
-	}
-
-	if (err != -EPROBE_DEFER)
-		dev_err(dev, "failed to get %s err %d\n", name, err);
-
-	return err;
-}
-
-static int ufs_qcom_host_clk_enable(struct device *dev,
-		const char *name, struct clk *clk)
-{
-	int err = 0;
-
-	err = clk_prepare_enable(clk);
-	if (err)
-		dev_err(dev, "%s: %s enable failed %d\n", __func__, name, err);
-
-	return err;
-}
-
 static void ufs_qcom_disable_lane_clks(struct ufs_qcom_host *host)
 {
 	if (!host->is_lane_clks_enabled)
 		return;
 
-	clk_disable_unprepare(host->tx_l1_sync_clk);
-	clk_disable_unprepare(host->tx_l0_sync_clk);
-	clk_disable_unprepare(host->rx_l1_sync_clk);
-	clk_disable_unprepare(host->rx_l0_sync_clk);
+	clk_bulk_disable_unprepare(host->num_clks, host->clks);
 
 	host->is_lane_clks_enabled = false;
 }
@@ -247,73 +205,29 @@ static void ufs_qcom_disable_lane_clks(struct ufs_qcom_host *host)
 static int ufs_qcom_enable_lane_clks(struct ufs_qcom_host *host)
 {
 	int err;
-	struct device *dev = host->hba->dev;
-
-	if (host->is_lane_clks_enabled)
-		return 0;
 
-	err = ufs_qcom_host_clk_enable(dev, "rx_lane0_sync_clk",
-		host->rx_l0_sync_clk);
+	err = clk_bulk_prepare_enable(host->num_clks, host->clks);
 	if (err)
 		return err;
 
-	err = ufs_qcom_host_clk_enable(dev, "tx_lane0_sync_clk",
-		host->tx_l0_sync_clk);
-	if (err)
-		goto disable_rx_l0;
-
-	err = ufs_qcom_host_clk_enable(dev, "rx_lane1_sync_clk",
-			host->rx_l1_sync_clk);
-	if (err)
-		goto disable_tx_l0;
-
-	err = ufs_qcom_host_clk_enable(dev, "tx_lane1_sync_clk",
-			host->tx_l1_sync_clk);
-	if (err)
-		goto disable_rx_l1;
-
 	host->is_lane_clks_enabled = true;
 
 	return 0;
-
-disable_rx_l1:
-	clk_disable_unprepare(host->rx_l1_sync_clk);
-disable_tx_l0:
-	clk_disable_unprepare(host->tx_l0_sync_clk);
-disable_rx_l0:
-	clk_disable_unprepare(host->rx_l0_sync_clk);
-
-	return err;
 }
 
 static int ufs_qcom_init_lane_clks(struct ufs_qcom_host *host)
 {
-	int err = 0;
+	int err;
 	struct device *dev = host->hba->dev;
 
 	if (has_acpi_companion(dev))
 		return 0;
 
-	err = ufs_qcom_host_clk_get(dev, "rx_lane0_sync_clk",
-					&host->rx_l0_sync_clk, false);
-	if (err)
-		return err;
-
-	err = ufs_qcom_host_clk_get(dev, "tx_lane0_sync_clk",
-					&host->tx_l0_sync_clk, false);
-	if (err)
+	err = devm_clk_bulk_get_all(dev, &host->clks);
+	if (err <= 0)
 		return err;
 
-	/* In case of single lane per direction, don't read lane1 clocks */
-	if (host->hba->lanes_per_direction > 1) {
-		err = ufs_qcom_host_clk_get(dev, "rx_lane1_sync_clk",
-			&host->rx_l1_sync_clk, false);
-		if (err)
-			return err;
-
-		err = ufs_qcom_host_clk_get(dev, "tx_lane1_sync_clk",
-			&host->tx_l1_sync_clk, true);
-	}
+	host->num_clks = err;
 
 	return 0;
 }
@@ -321,7 +235,7 @@ static int ufs_qcom_init_lane_clks(struct ufs_qcom_host *host)
 static int ufs_qcom_check_hibern8(struct ufs_hba *hba)
 {
 	int err;
-	u32 tx_fsm_val = 0;
+	u32 tx_fsm_val;
 	unsigned long timeout = jiffies + msecs_to_jiffies(HBRN8_POLL_TOUT_MS);
 
 	do {
@@ -360,9 +274,7 @@ static int ufs_qcom_check_hibern8(struct ufs_hba *hba)
 
 static void ufs_qcom_select_unipro_mode(struct ufs_qcom_host *host)
 {
-	ufshcd_rmwl(host->hba, QUNIPRO_SEL,
-		   ufs_qcom_cap_qunipro(host) ? QUNIPRO_SEL : 0,
-		   REG_UFS_CFG1);
+	ufshcd_rmwl(host->hba, QUNIPRO_SEL, QUNIPRO_SEL, REG_UFS_CFG1);
 
 	if (host->hw_ver.major >= 0x05)
 		ufshcd_rmwl(host->hba, QUNIPRO_G4_SEL, 0, REG_UFS_CFG0);
@@ -376,18 +288,15 @@ static void ufs_qcom_select_unipro_mode(struct ufs_qcom_host *host)
  */
 static int ufs_qcom_host_reset(struct ufs_hba *hba)
 {
-	int ret = 0;
+	int ret;
 	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
-	bool reenable_intr = false;
+	bool reenable_intr;
 
-	if (!host->core_reset) {
-		dev_warn(hba->dev, "%s: reset control not set\n", __func__);
+	if (!host->core_reset)
 		return 0;
-	}
 
 	reenable_intr = hba->is_irq_enabled;
-	disable_irq(hba->irq);
-	hba->is_irq_enabled = false;
+	ufshcd_disable_irq(hba);
 
 	ret = reset_control_assert(host->core_reset);
 	if (ret) {
@@ -404,16 +313,16 @@ static int ufs_qcom_host_reset(struct ufs_hba *hba)
 	usleep_range(200, 210);
 
 	ret = reset_control_deassert(host->core_reset);
-	if (ret)
+	if (ret) {
 		dev_err(hba->dev, "%s: core_reset deassert failed, err = %d\n",
 				 __func__, ret);
+		return ret;
+	}
 
 	usleep_range(1000, 1100);
 
-	if (reenable_intr) {
-		enable_irq(hba->irq);
-		hba->is_irq_enabled = true;
-	}
+	if (reenable_intr)
+		ufshcd_enable_irq(hba);
 
 	return 0;
 }
@@ -422,18 +331,8 @@ static u32 ufs_qcom_get_hs_gear(struct ufs_hba *hba)
 {
 	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
 
-	if (host->hw_ver.major == 0x1) {
-		/*
-		 * HS-G3 operations may not reliably work on legacy QCOM
-		 * UFS host controller hardware even though capability
-		 * exchange during link startup phase may end up
-		 * negotiating maximum supported gear as G3.
-		 * Hence downgrade the maximum supported gear to HS-G2.
-		 */
-		return UFS_HS_G2;
-	} else if (host->hw_ver.major >= 0x4) {
+	if (host->hw_ver.major >= 0x4)
 		return UFS_QCOM_MAX_GEAR(ufshcd_readl(hba, REG_UFS_PARAM0));
-	}
 
 	/* Default is HS-G3 */
 	return UFS_HS_G3;
@@ -442,14 +341,29 @@ static u32 ufs_qcom_get_hs_gear(struct ufs_hba *hba)
 static int ufs_qcom_power_up_sequence(struct ufs_hba *hba)
 {
 	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
+	struct ufs_host_params *host_params = &host->host_params;
 	struct phy *phy = host->generic_phy;
+	enum phy_mode mode;
 	int ret;
 
+	/*
+	 * HW ver 5 can only support up to HS-G5 Rate-A due to HW limitations.
+	 * If the HS-G5 PHY gear is used, update host_params->hs_rate to Rate-A,
+	 * so that the subsequent power mode change shall stick to Rate-A.
+	 */
+	if (host->hw_ver.major == 0x5) {
+		if (host->phy_gear == UFS_HS_G5)
+			host_params->hs_rate = PA_HS_MODE_A;
+		else
+			host_params->hs_rate = PA_HS_MODE_B;
+	}
+
+	mode = host_params->hs_rate == PA_HS_MODE_B ? PHY_MODE_UFS_HS_B : PHY_MODE_UFS_HS_A;
+
 	/* Reset UFS Host Controller and PHY */
 	ret = ufs_qcom_host_reset(hba);
 	if (ret)
-		dev_warn(hba->dev, "%s: host reset returned %d\n",
-				  __func__, ret);
+		return ret;
 
 	/* phy initialization - calibrate the phy */
 	ret = phy_init(phy);
@@ -459,7 +373,9 @@ static int ufs_qcom_power_up_sequence(struct ufs_hba *hba)
 		return ret;
 	}
 
-	phy_set_mode_ext(phy, PHY_MODE_UFS_HS_B, host->phy_gear);
+	ret = phy_set_mode_ext(phy, mode, host->phy_gear);
+	if (ret)
+		goto out_disable_phy;
 
 	/* power on phy - start serdes and phy's power and clocks */
 	ret = phy_power_on(phy);
@@ -489,9 +405,8 @@ out_disable_phy:
  */
 static void ufs_qcom_enable_hw_clk_gating(struct ufs_hba *hba)
 {
-	ufshcd_writel(hba,
-		ufshcd_readl(hba, REG_UFS_CFG2) | REG_UFS_CFG2_CGC_EN_ALL,
-		REG_UFS_CFG2);
+	ufshcd_rmwl(hba, REG_UFS_CFG2_CGC_EN_ALL, REG_UFS_CFG2_CGC_EN_ALL,
+		    REG_UFS_CFG2);
 
 	/* Ensure that HW clock gating is enabled before next operations */
 	mb();
@@ -501,11 +416,14 @@ static int ufs_qcom_hce_enable_notify(struct ufs_hba *hba,
 				      enum ufs_notify_change_status status)
 {
 	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
-	int err = 0;
+	int err;
 
 	switch (status) {
 	case PRE_CHANGE:
-		ufs_qcom_power_up_sequence(hba);
+		err = ufs_qcom_power_up_sequence(hba);
+		if (err)
+			return err;
+
 		/*
 		 * The PHY PLL output is the source of tx/rx lane symbol
 		 * clocks, hence, enable the lane clocks only after PHY
@@ -544,41 +462,16 @@ static int ufs_qcom_cfg_timers(struct ufs_hba *hba, u32 gear,
 {
 	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
 	struct ufs_clk_info *clki;
-	u32 core_clk_period_in_ns;
-	u32 tx_clk_cycles_per_us = 0;
 	unsigned long core_clk_rate = 0;
-	u32 core_clk_cycles_per_us = 0;
-
-	static u32 pwm_fr_table[][2] = {
-		{UFS_PWM_G1, 0x1},
-		{UFS_PWM_G2, 0x1},
-		{UFS_PWM_G3, 0x1},
-		{UFS_PWM_G4, 0x1},
-	};
-
-	static u32 hs_fr_table_rA[][2] = {
-		{UFS_HS_G1, 0x1F},
-		{UFS_HS_G2, 0x3e},
-		{UFS_HS_G3, 0x7D},
-	};
-
-	static u32 hs_fr_table_rB[][2] = {
-		{UFS_HS_G1, 0x24},
-		{UFS_HS_G2, 0x49},
-		{UFS_HS_G3, 0x92},
-	};
+	u32 core_clk_cycles_per_us;
 
 	/*
-	 * The Qunipro controller does not use following registers:
-	 * SYS1CLK_1US_REG, TX_SYMBOL_CLK_1US_REG, CLK_NS_REG &
-	 * UFS_REG_PA_LINK_STARTUP_TIMER.
-	 * However UTP controller uses SYS1CLK_1US_REG register for Interrupt
+	 * UTP controller uses SYS1CLK_1US_REG register for Interrupt
 	 * Aggregation logic.
 	 * It is mandatory to write SYS1CLK_1US_REG register on UFS host
 	 * controller V4.0.0 onwards.
 	 */
-	if (host->hw_ver.major < 4 && ufs_qcom_cap_qunipro(host) &&
-	    !ufshcd_is_intr_aggr_allowed(hba))
+	if (host->hw_ver.major < 4 && !ufshcd_is_intr_aggr_allowed(hba))
 		return 0;
 
 	if (gear == 0) {
@@ -611,79 +504,6 @@ static int ufs_qcom_cfg_timers(struct ufs_hba *hba, u32 gear,
 		mb();
 	}
 
-	if (ufs_qcom_cap_qunipro(host))
-		return 0;
-
-	core_clk_period_in_ns = NSEC_PER_SEC / core_clk_rate;
-	core_clk_period_in_ns <<= OFFSET_CLK_NS_REG;
-	core_clk_period_in_ns &= MASK_CLK_NS_REG;
-
-	switch (hs) {
-	case FASTAUTO_MODE:
-	case FAST_MODE:
-		if (rate == PA_HS_MODE_A) {
-			if (gear > ARRAY_SIZE(hs_fr_table_rA)) {
-				dev_err(hba->dev,
-					"%s: index %d exceeds table size %zu\n",
-					__func__, gear,
-					ARRAY_SIZE(hs_fr_table_rA));
-				return -EINVAL;
-			}
-			tx_clk_cycles_per_us = hs_fr_table_rA[gear-1][1];
-		} else if (rate == PA_HS_MODE_B) {
-			if (gear > ARRAY_SIZE(hs_fr_table_rB)) {
-				dev_err(hba->dev,
-					"%s: index %d exceeds table size %zu\n",
-					__func__, gear,
-					ARRAY_SIZE(hs_fr_table_rB));
-				return -EINVAL;
-			}
-			tx_clk_cycles_per_us = hs_fr_table_rB[gear-1][1];
-		} else {
-			dev_err(hba->dev, "%s: invalid rate = %d\n",
-				__func__, rate);
-			return -EINVAL;
-		}
-		break;
-	case SLOWAUTO_MODE:
-	case SLOW_MODE:
-		if (gear > ARRAY_SIZE(pwm_fr_table)) {
-			dev_err(hba->dev,
-					"%s: index %d exceeds table size %zu\n",
-					__func__, gear,
-					ARRAY_SIZE(pwm_fr_table));
-			return -EINVAL;
-		}
-		tx_clk_cycles_per_us = pwm_fr_table[gear-1][1];
-		break;
-	case UNCHANGED:
-	default:
-		dev_err(hba->dev, "%s: invalid mode = %d\n", __func__, hs);
-		return -EINVAL;
-	}
-
-	if (ufshcd_readl(hba, REG_UFS_TX_SYMBOL_CLK_NS_US) !=
-	    (core_clk_period_in_ns | tx_clk_cycles_per_us)) {
-		/* this register 2 fields shall be written at once */
-		ufshcd_writel(hba, core_clk_period_in_ns | tx_clk_cycles_per_us,
-			      REG_UFS_TX_SYMBOL_CLK_NS_US);
-		/*
-		 * make sure above write gets applied before we return from
-		 * this function.
-		 */
-		mb();
-	}
-
-	if (update_link_startup_timer && host->hw_ver.major != 0x5) {
-		ufshcd_writel(hba, ((core_clk_rate / MSEC_PER_SEC) * 100),
-			      REG_UFS_CFG0);
-		/*
-		 * make sure that this configuration is applied before
-		 * we return
-		 */
-		mb();
-	}
-
 	return 0;
 }
 
@@ -691,7 +511,6 @@ static int ufs_qcom_link_startup_notify(struct ufs_hba *hba,
 					enum ufs_notify_change_status status)
 {
 	int err = 0;
-	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
 
 	switch (status) {
 	case PRE_CHANGE:
@@ -702,11 +521,9 @@ static int ufs_qcom_link_startup_notify(struct ufs_hba *hba,
 			return -EINVAL;
 		}
 
-		if (ufs_qcom_cap_qunipro(host)) {
-			err = ufs_qcom_set_core_clk_ctrl(hba, true);
-			if (err)
-				dev_err(hba->dev, "cfg core clk ctrl failed\n");
-		}
+		err = ufs_qcom_set_core_clk_ctrl(hba, true);
+		if (err)
+			dev_err(hba->dev, "cfg core clk ctrl failed\n");
 		/*
 		 * Some UFS devices (and may be host) have issues if LCC is
 		 * enabled. So we are setting PA_Local_TX_LCC_Enable to 0
@@ -898,7 +715,7 @@ static int ufs_qcom_pwr_change_notify(struct ufs_hba *hba,
 				struct ufs_pa_layer_attr *dev_req_params)
 {
 	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
-	struct ufs_dev_params ufs_qcom_cap;
+	struct ufs_host_params *host_params = &host->host_params;
 	int ret = 0;
 
 	if (!dev_req_params) {
@@ -908,15 +725,7 @@ static int ufs_qcom_pwr_change_notify(struct ufs_hba *hba,
 
 	switch (status) {
 	case PRE_CHANGE:
-		ufshcd_init_pwr_dev_param(&ufs_qcom_cap);
-		ufs_qcom_cap.hs_rate = UFS_QCOM_LIMIT_HS_RATE;
-
-		/* This driver only supports symmetic gear setting i.e., hs_tx_gear == hs_rx_gear */
-		ufs_qcom_cap.hs_tx_gear = ufs_qcom_cap.hs_rx_gear = ufs_qcom_get_hs_gear(hba);
-
-		ret = ufshcd_get_pwr_dev_param(&ufs_qcom_cap,
-					       dev_max_params,
-					       dev_req_params);
+		ret = ufshcd_negotiate_pwr_params(host_params, dev_max_params, dev_req_params);
 		if (ret) {
 			dev_err(hba->dev, "%s: failed to determine capabilities\n",
 					__func__);
@@ -924,11 +733,12 @@ static int ufs_qcom_pwr_change_notify(struct ufs_hba *hba,
 		}
 
 		/*
-		 * Update phy_gear only when the gears are scaled to a higher value. This is
-		 * because, the PHY gear settings are backwards compatible and we only need to
-		 * change the PHY gear settings while scaling to higher gears.
+		 * During UFS driver probe, always update the PHY gear to match the negotiated
+		 * gear, so that, if quirk UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH is enabled,
+		 * the second init can program the optimal PHY settings. This allows one to start
+		 * the first init with either the minimum or the maximum support gear.
 		 */
-		if (dev_req_params->gear_tx > host->phy_gear)
+		if (hba->ufshcd_state == UFSHCD_STATE_RESET)
 			host->phy_gear = dev_req_params->gear_tx;
 
 		/* enable the device ref clock before changing to HS mode */
@@ -1005,12 +815,7 @@ static int ufs_qcom_apply_dev_quirks(struct ufs_hba *hba)
 
 static u32 ufs_qcom_get_ufs_hci_version(struct ufs_hba *hba)
 {
-	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
-
-	if (host->hw_ver.major == 0x1)
-		return ufshci_version(1, 1);
-	else
-		return ufshci_version(2, 0);
+	return ufshci_version(2, 0);
 }
 
 /**
@@ -1026,46 +831,69 @@ static void ufs_qcom_advertise_quirks(struct ufs_hba *hba)
 {
 	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
 
-	if (host->hw_ver.major == 0x01) {
-		hba->quirks |= UFSHCD_QUIRK_DELAY_BEFORE_DME_CMDS
-			    | UFSHCD_QUIRK_BROKEN_PA_RXHSUNTERMCAP
-			    | UFSHCD_QUIRK_DME_PEER_ACCESS_AUTO_MODE;
+	if (host->hw_ver.major == 0x2)
+		hba->quirks |= UFSHCD_QUIRK_BROKEN_UFS_HCI_VERSION;
 
-		if (host->hw_ver.minor == 0x0001 && host->hw_ver.step == 0x0001)
-			hba->quirks |= UFSHCD_QUIRK_BROKEN_INTR_AGGR;
+	if (host->hw_ver.major > 0x3)
+		hba->quirks |= UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH;
+}
 
-		hba->quirks |= UFSHCD_QUIRK_BROKEN_LCC;
-	}
+static void ufs_qcom_set_phy_gear(struct ufs_qcom_host *host)
+{
+	struct ufs_host_params *host_params = &host->host_params;
+	u32 val, dev_major;
 
-	if (host->hw_ver.major == 0x2) {
-		hba->quirks |= UFSHCD_QUIRK_BROKEN_UFS_HCI_VERSION;
+	host->phy_gear = host_params->hs_tx_gear;
 
-		if (!ufs_qcom_cap_qunipro(host))
-			/* Legacy UniPro mode still need following quirks */
-			hba->quirks |= (UFSHCD_QUIRK_DELAY_BEFORE_DME_CMDS
-				| UFSHCD_QUIRK_DME_PEER_ACCESS_AUTO_MODE
-				| UFSHCD_QUIRK_BROKEN_PA_RXHSUNTERMCAP);
-	}
+	if (host->hw_ver.major < 0x4) {
+		/*
+		 * For controllers whose major HW version is < 4, power up the
+		 * PHY using minimum supported gear (UFS_HS_G2). Switching to
+		 * max gear will be performed during reinit if supported.
+		 * For newer controllers, whose major HW version is >= 4, power
+		 * up the PHY using max supported gear.
+		 */
+		host->phy_gear = UFS_HS_G2;
+	} else if (host->hw_ver.major >= 0x5) {
+		val = ufshcd_readl(host->hba, REG_UFS_DEBUG_SPARE_CFG);
+		dev_major = FIELD_GET(UFS_DEV_VER_MAJOR_MASK, val);
 
-	if (host->hw_ver.major > 0x3)
-		hba->quirks |= UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH;
+		/*
+		 * Since the UFS device version is populated, let's remove the
+		 * REINIT quirk as the negotiated gear won't change during boot.
+		 * So there is no need to do reinit.
+		 */
+		if (dev_major != 0x0)
+			host->hba->quirks &= ~UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH;
+
+		/*
+		 * For UFS 3.1 device and older, power up the PHY using HS-G4
+		 * PHY gear to save power.
+		 */
+		if (dev_major > 0x0 && dev_major < 0x4)
+			host->phy_gear = UFS_HS_G4;
+	}
 }
 
-static void ufs_qcom_set_caps(struct ufs_hba *hba)
+static void ufs_qcom_set_host_params(struct ufs_hba *hba)
 {
 	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
+	struct ufs_host_params *host_params = &host->host_params;
+
+	ufshcd_init_host_params(host_params);
+
+	/* This driver only supports symmetic gear setting i.e., hs_tx_gear == hs_rx_gear */
+	host_params->hs_tx_gear = host_params->hs_rx_gear = ufs_qcom_get_hs_gear(hba);
+}
 
+static void ufs_qcom_set_caps(struct ufs_hba *hba)
+{
 	hba->caps |= UFSHCD_CAP_CLK_GATING | UFSHCD_CAP_HIBERN8_WITH_CLK_GATING;
 	hba->caps |= UFSHCD_CAP_CLK_SCALING | UFSHCD_CAP_WB_WITH_CLK_SCALING;
 	hba->caps |= UFSHCD_CAP_AUTO_BKOPS_SUSPEND;
 	hba->caps |= UFSHCD_CAP_WB_EN;
 	hba->caps |= UFSHCD_CAP_AGGR_POWER_COLLAPSE;
 	hba->caps |= UFSHCD_CAP_RPM_AUTOSUSPEND;
-
-	if (host->hw_ver.major >= 0x2) {
-		host->caps = UFS_QCOM_CAP_QUNIPRO |
-			     UFS_QCOM_CAP_RETAIN_SEC_CFG_AFTER_PWR_COLLAPSE;
-	}
 }
 
 /**
@@ -1188,16 +1016,12 @@ static int ufs_qcom_init(struct ufs_hba *hba)
 {
 	int err;
 	struct device *dev = hba->dev;
-	struct platform_device *pdev = to_platform_device(dev);
 	struct ufs_qcom_host *host;
-	struct resource *res;
 	struct ufs_clk_info *clki;
 
 	host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL);
-	if (!host) {
-		dev_err(dev, "%s: no memory for qcom ufs host\n", __func__);
+	if (!host)
 		return -ENOMEM;
-	}
 
 	/* Make a two way bind between the qcom host and the hba */
 	host->hba = hba;
@@ -1235,34 +1059,16 @@ static int ufs_qcom_init(struct ufs_hba *hba)
 	host->device_reset = devm_gpiod_get_optional(dev, "reset",
 						     GPIOD_OUT_HIGH);
 	if (IS_ERR(host->device_reset)) {
-		err = PTR_ERR(host->device_reset);
-		if (err != -EPROBE_DEFER)
-			dev_err(dev, "failed to acquire reset gpio: %d\n", err);
+		err = dev_err_probe(dev, PTR_ERR(host->device_reset),
+				    "Failed to acquire device reset gpio\n");
 		goto out_variant_clear;
 	}
 
 	ufs_qcom_get_controller_revision(hba, &host->hw_ver.major,
 		&host->hw_ver.minor, &host->hw_ver.step);
 
-	/*
-	 * for newer controllers, device reference clock control bit has
-	 * moved inside UFS controller register address space itself.
-	 */
-	if (host->hw_ver.major >= 0x02) {
-		host->dev_ref_clk_ctrl_mmio = hba->mmio_base + REG_UFS_CFG1;
-		host->dev_ref_clk_en_mask = BIT(26);
-	} else {
-		/* "dev_ref_clk_ctrl_mem" is optional resource */
-		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-						   "dev_ref_clk_ctrl_mem");
-		if (res) {
-			host->dev_ref_clk_ctrl_mmio =
-					devm_ioremap_resource(dev, res);
-			if (IS_ERR(host->dev_ref_clk_ctrl_mmio))
-				host->dev_ref_clk_ctrl_mmio = NULL;
-			host->dev_ref_clk_en_mask = BIT(5);
-		}
-	}
+	host->dev_ref_clk_ctrl_mmio = hba->mmio_base + REG_UFS_CFG1;
+	host->dev_ref_clk_en_mask = BIT(26);
 
 	list_for_each_entry(clki, &hba->clk_list_head, list) {
 		if (!strcmp(clki->name, "core_clk_unipro"))
@@ -1275,6 +1081,8 @@ static int ufs_qcom_init(struct ufs_hba *hba)
 
 	ufs_qcom_set_caps(hba);
 	ufs_qcom_advertise_quirks(hba);
+	ufs_qcom_set_host_params(hba);
+	ufs_qcom_set_phy_gear(host);
 
 	err = ufs_qcom_ice_init(host);
 	if (err)
@@ -1282,9 +1090,6 @@ static int ufs_qcom_init(struct ufs_hba *hba)
 
 	ufs_qcom_setup_clocks(hba, true, POST_CHANGE);
 
-	if (hba->dev->id < MAX_UFS_QCOM_HOSTS)
-		ufs_qcom_hosts[hba->dev->id] = host;
-
 	ufs_qcom_get_default_testbus_cfg(host);
 	err = ufs_qcom_testbus_config(host);
 	if (err)
@@ -1292,12 +1097,6 @@ static int ufs_qcom_init(struct ufs_hba *hba)
 		dev_warn(dev, "%s: failed to configure the testbus %d\n",
 				__func__, err);
 
-	/*
-	 * Power up the PHY using the minimum supported gear (UFS_HS_G2).
-	 * Switching to max gear will be performed during reinit if supported.
-	 */
-	host->phy_gear = UFS_HS_G2;
-
 	return 0;
 
 out_variant_clear:
@@ -1391,7 +1190,7 @@ static int ufs_qcom_set_core_clk_ctrl(struct ufs_hba *hba, bool is_scale_up)
 	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
 	struct list_head *head = &hba->clk_list_head;
 	struct ufs_clk_info *clki;
-	u32 cycles_in_1us;
+	u32 cycles_in_1us = 0;
 	u32 core_clk_ctrl_reg;
 	int err;
 
@@ -1444,9 +1243,6 @@ static int ufs_qcom_clk_scale_up_pre_change(struct ufs_hba *hba)
 	struct ufs_pa_layer_attr *attr = &host->dev_req_params;
 	int ret;
 
-	if (!ufs_qcom_cap_qunipro(host))
-		return 0;
-
 	ret = ufs_qcom_cfg_timers(hba, attr->gear_rx, attr->pwr_rx,
 				  attr->hs_rate, false, true);
 	if (ret) {
@@ -1464,13 +1260,9 @@ static int ufs_qcom_clk_scale_up_post_change(struct ufs_hba *hba)
 
 static int ufs_qcom_clk_scale_down_pre_change(struct ufs_hba *hba)
 {
-	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
 	int err;
 	u32 core_clk_ctrl_reg;
 
-	if (!ufs_qcom_cap_qunipro(host))
-		return 0;
-
 	err = ufshcd_dme_get(hba,
 			    UIC_ARG_MIB(DME_VS_CORE_CLK_CTRL),
 			    &core_clk_ctrl_reg);
@@ -1489,11 +1281,6 @@ static int ufs_qcom_clk_scale_down_pre_change(struct ufs_hba *hba)
 
 static int ufs_qcom_clk_scale_down_post_change(struct ufs_hba *hba)
 {
-	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
-
-	if (!ufs_qcom_cap_qunipro(host))
-		return 0;
-
 	/* set unipro core clock attributes and clear clock divider */
 	return ufs_qcom_set_core_clk_ctrl(hba, false);
 }
@@ -1502,7 +1289,7 @@ static int ufs_qcom_clk_scale_notify(struct ufs_hba *hba,
 		bool scale_up, enum ufs_notify_change_status status)
 {
 	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
-	int err = 0;
+	int err;
 
 	/* check the host controller state before sending hibern8 cmd */
 	if (!ufshcd_is_hba_active(hba))
@@ -1516,9 +1303,11 @@ static int ufs_qcom_clk_scale_notify(struct ufs_hba *hba,
 			err = ufs_qcom_clk_scale_up_pre_change(hba);
 		else
 			err = ufs_qcom_clk_scale_down_pre_change(hba);
-		if (err)
-			ufshcd_uic_hibern8_exit(hba);
 
+		if (err) {
+			ufshcd_uic_hibern8_exit(hba);
+			return err;
+		}
 	} else {
 		if (scale_up)
 			err = ufs_qcom_clk_scale_up_post_change(hba);
@@ -1773,7 +1562,7 @@ static int ufs_qcom_mcq_config_resource(struct ufs_hba *hba)
 	struct platform_device *pdev = to_platform_device(hba->dev);
 	struct ufshcd_res_info *res;
 	struct resource *res_mem, *res_mcq;
-	int i, ret = 0;
+	int i, ret;
 
 	memcpy(hba->res, ufs_res_info, sizeof(ufs_res_info));
 
@@ -1785,7 +1574,7 @@ static int ufs_qcom_mcq_config_resource(struct ufs_hba *hba)
 		if (!res->resource) {
 			dev_info(hba->dev, "Resource %s not provided\n", res->name);
 			if (i == RES_UFS)
-				return -ENOMEM;
+				return -ENODEV;
 			continue;
 		} else if (i == RES_UFS) {
 			res_mem = res->resource;
@@ -1956,11 +1745,10 @@ static int ufs_qcom_config_esi(struct ufs_hba *hba)
 		platform_msi_domain_free_irqs(hba->dev);
 	} else {
 		if (host->hw_ver.major == 6 && host->hw_ver.minor == 0 &&
-		    host->hw_ver.step == 0) {
-			ufshcd_writel(hba,
-				      ufshcd_readl(hba, REG_UFS_CFG3) | 0x1F000,
-				      REG_UFS_CFG3);
-		}
+		    host->hw_ver.step == 0)
+			ufshcd_rmwl(hba, ESI_VEC_MASK,
+				    FIELD_PREP(ESI_VEC_MASK, MAX_ESI_VEC - 1),
+				    REG_UFS_CFG3);
 		ufshcd_mcq_enable_esi(hba);
 	}
 
diff --git a/drivers/ufs/host/ufs-qcom.h b/drivers/ufs/host/ufs-qcom.h
index 9950a0089475..9dd9a391ebb7 100644
--- a/drivers/ufs/host/ufs-qcom.h
+++ b/drivers/ufs/host/ufs-qcom.h
@@ -10,22 +10,17 @@
 #include <soc/qcom/ice.h>
 #include <ufs/ufshcd.h>
 
-#define MAX_UFS_QCOM_HOSTS	1
-#define MAX_U32                 (~(u32)0)
 #define MPHY_TX_FSM_STATE       0x41
 #define TX_FSM_HIBERN8          0x1
 #define HBRN8_POLL_TOUT_MS      100
 #define DEFAULT_CLK_RATE_HZ     1000000
-#define BUS_VECTOR_NAME_LEN     32
 #define MAX_SUPP_MAC		64
+#define MAX_ESI_VEC		32
 
 #define UFS_HW_VER_MAJOR_MASK	GENMASK(31, 28)
 #define UFS_HW_VER_MINOR_MASK	GENMASK(27, 16)
 #define UFS_HW_VER_STEP_MASK	GENMASK(15, 0)
-
-/* vendor specific pre-defined parameters */
-#define SLOW 1
-#define FAST 2
+#define UFS_DEV_VER_MAJOR_MASK	GENMASK(7, 4)
 
 #define UFS_QCOM_LIMIT_HS_RATE		PA_HS_MODE_B
 
@@ -56,6 +51,8 @@ enum {
 	UFS_AH8_CFG				= 0xFC,
 
 	REG_UFS_CFG3				= 0x271C,
+
+	REG_UFS_DEBUG_SPARE_CFG			= 0x284C,
 };
 
 /* QCOM UFS host controller vendor specific debug registers */
@@ -93,9 +90,6 @@ enum {
 #define TEST_BUS_SEL		GENMASK(22, 19)
 #define UFS_REG_TEST_BUS_EN	BIT(30)
 
-#define UFS_PHY_RESET_ENABLE	1
-#define UFS_PHY_RESET_DISABLE	0
-
 /* bit definitions for REG_UFS_CFG2 register */
 #define UAWM_HW_CGC_EN		BIT(0)
 #define UARM_HW_CGC_EN		BIT(1)
@@ -106,6 +100,9 @@ enum {
 #define TMRLUT_HW_CGC_EN	BIT(6)
 #define OCSC_HW_CGC_EN		BIT(7)
 
+/* bit definitions for REG_UFS_CFG3 register */
+#define ESI_VEC_MASK		GENMASK(22, 12)
+
 /* bit definitions for REG_UFS_PARAM0 */
 #define MAX_HS_GEAR_MASK	GENMASK(6, 4)
 #define UFS_QCOM_MAX_GEAR(x)	FIELD_GET(MAX_HS_GEAR_MASK, (x))
@@ -118,13 +115,6 @@ enum {
 				 DFC_HW_CGC_EN | TRLUT_HW_CGC_EN |\
 				 TMRLUT_HW_CGC_EN | OCSC_HW_CGC_EN)
 
-/* bit offset */
-#define OFFSET_CLK_NS_REG		0xa
-
-/* bit masks */
-#define MASK_TX_SYMBOL_CLK_1US_REG	GENMASK(9, 0)
-#define MASK_CLK_NS_REG			GENMASK(23, 10)
-
 /* QUniPro Vendor specific attributes */
 #define PA_VS_CONFIG_REG1	0x9000
 #define DME_VS_CORE_CLK_CTRL	0xD002
@@ -158,8 +148,7 @@ ufs_qcom_get_controller_revision(struct ufs_hba *hba,
 
 static inline void ufs_qcom_assert_reset(struct ufs_hba *hba)
 {
-	ufshcd_rmwl(hba, UFS_PHY_SOFT_RESET, FIELD_PREP(UFS_PHY_SOFT_RESET, UFS_PHY_RESET_ENABLE),
-		    REG_UFS_CFG1);
+	ufshcd_rmwl(hba, UFS_PHY_SOFT_RESET, UFS_PHY_SOFT_RESET, REG_UFS_CFG1);
 
 	/*
 	 * Make sure assertion of ufs phy reset is written to
@@ -170,8 +159,7 @@ static inline void ufs_qcom_assert_reset(struct ufs_hba *hba)
 
 static inline void ufs_qcom_deassert_reset(struct ufs_hba *hba)
 {
-	ufshcd_rmwl(hba, UFS_PHY_SOFT_RESET, FIELD_PREP(UFS_PHY_SOFT_RESET, UFS_PHY_RESET_DISABLE),
-		    REG_UFS_CFG1);
+	ufshcd_rmwl(hba, UFS_PHY_SOFT_RESET, 0, REG_UFS_CFG1);
 
 	/*
 	 * Make sure de-assertion of ufs phy reset is written to
@@ -195,28 +183,11 @@ struct ufs_qcom_testbus {
 struct gpio_desc;
 
 struct ufs_qcom_host {
-	/*
-	 * Set this capability if host controller supports the QUniPro mode
-	 * and if driver wants the Host controller to operate in QUniPro mode.
-	 * Note: By default this capability will be kept enabled if host
-	 * controller supports the QUniPro mode.
-	 */
-	#define UFS_QCOM_CAP_QUNIPRO	0x1
-
-	/*
-	 * Set this capability if host controller can retain the secure
-	 * configuration even after UFS controller core power collapse.
-	 */
-	#define UFS_QCOM_CAP_RETAIN_SEC_CFG_AFTER_PWR_COLLAPSE	0x2
-	u32 caps;
-
 	struct phy *generic_phy;
 	struct ufs_hba *hba;
 	struct ufs_pa_layer_attr dev_req_params;
-	struct clk *rx_l0_sync_clk;
-	struct clk *tx_l0_sync_clk;
-	struct clk *rx_l1_sync_clk;
-	struct clk *tx_l1_sync_clk;
+	struct clk_bulk_data *clks;
+	u32 num_clks;
 	bool is_lane_clks_enabled;
 
 	struct icc_path *icc_ddr;
@@ -240,6 +211,7 @@ struct ufs_qcom_host {
 
 	struct gpio_desc *device_reset;
 
+	struct ufs_host_params host_params;
 	u32 phy_gear;
 
 	bool esi_enabled;
@@ -261,9 +233,4 @@ ufs_qcom_get_debug_reg_offset(struct ufs_qcom_host *host, u32 reg)
 
 int ufs_qcom_testbus_config(struct ufs_qcom_host *host);
 
-static inline bool ufs_qcom_cap_qunipro(struct ufs_qcom_host *host)
-{
-	return host->caps & UFS_QCOM_CAP_QUNIPRO;
-}
-
 #endif /* UFS_QCOM_H_ */
diff --git a/drivers/ufs/host/ufshcd-pltfrm.c b/drivers/ufs/host/ufshcd-pltfrm.c
index da2558e274b4..a3e69ecafd27 100644
--- a/drivers/ufs/host/ufshcd-pltfrm.c
+++ b/drivers/ufs/host/ufshcd-pltfrm.c
@@ -8,6 +8,7 @@
  *	Vinayak Holikatti <h.vinayak@samsung.com>
  */
 
+#include <linux/clk.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/pm_opp.h>
@@ -213,6 +214,55 @@ static void ufshcd_init_lanes_per_dir(struct ufs_hba *hba)
 	}
 }
 
+/**
+ * ufshcd_parse_clock_min_max_freq  - Parse MIN and MAX clocks freq
+ * @hba: per adapter instance
+ *
+ * This function parses MIN and MAX frequencies of all clocks required
+ * by the host drivers.
+ *
+ * Returns 0 for success and non-zero for failure
+ */
+static int ufshcd_parse_clock_min_max_freq(struct ufs_hba *hba)
+{
+	struct list_head *head = &hba->clk_list_head;
+	struct ufs_clk_info *clki;
+	struct dev_pm_opp *opp;
+	unsigned long freq;
+	u8 idx = 0;
+
+	list_for_each_entry(clki, head, list) {
+		if (!clki->name)
+			continue;
+
+		clki->clk = devm_clk_get(hba->dev, clki->name);
+		if (IS_ERR(clki->clk))
+			continue;
+
+		/* Find Max Freq */
+		freq = ULONG_MAX;
+		opp = dev_pm_opp_find_freq_floor_indexed(hba->dev, &freq, idx);
+		if (IS_ERR(opp)) {
+			dev_err(hba->dev, "Failed to find OPP for MAX frequency\n");
+			return PTR_ERR(opp);
+		}
+		clki->max_freq = dev_pm_opp_get_freq_indexed(opp, idx);
+		dev_pm_opp_put(opp);
+
+		/* Find Min Freq */
+		freq = 0;
+		opp = dev_pm_opp_find_freq_ceil_indexed(hba->dev, &freq, idx);
+		if (IS_ERR(opp)) {
+			dev_err(hba->dev, "Failed to find OPP for MIN frequency\n");
+			return PTR_ERR(opp);
+		}
+		clki->min_freq = dev_pm_opp_get_freq_indexed(opp, idx++);
+		dev_pm_opp_put(opp);
+	}
+
+	return 0;
+}
+
 static int ufshcd_parse_operating_points(struct ufs_hba *hba)
 {
 	struct device *dev = hba->dev;
@@ -279,67 +329,70 @@ static int ufshcd_parse_operating_points(struct ufs_hba *hba)
 		return ret;
 	}
 
+	ret = ufshcd_parse_clock_min_max_freq(hba);
+	if (ret)
+		return ret;
+
 	hba->use_pm_opp = true;
 
 	return 0;
 }
 
 /**
- * ufshcd_get_pwr_dev_param - get finally agreed attributes for
- *                            power mode change
- * @pltfrm_param: pointer to platform parameters
+ * ufshcd_negotiate_pwr_params - find power mode settings that are supported by
+ *				 both the controller and the device
+ * @host_params: pointer to host parameters
  * @dev_max: pointer to device attributes
  * @agreed_pwr: returned agreed attributes
  *
  * Return: 0 on success, non-zero value on failure.
  */
-int ufshcd_get_pwr_dev_param(const struct ufs_dev_params *pltfrm_param,
-			     const struct ufs_pa_layer_attr *dev_max,
-			     struct ufs_pa_layer_attr *agreed_pwr)
+int ufshcd_negotiate_pwr_params(const struct ufs_host_params *host_params,
+				const struct ufs_pa_layer_attr *dev_max,
+				struct ufs_pa_layer_attr *agreed_pwr)
 {
-	int min_pltfrm_gear;
+	int min_host_gear;
 	int min_dev_gear;
 	bool is_dev_sup_hs = false;
-	bool is_pltfrm_max_hs = false;
+	bool is_host_max_hs = false;
 
 	if (dev_max->pwr_rx == FAST_MODE)
 		is_dev_sup_hs = true;
 
-	if (pltfrm_param->desired_working_mode == UFS_HS_MODE) {
-		is_pltfrm_max_hs = true;
-		min_pltfrm_gear = min_t(u32, pltfrm_param->hs_rx_gear,
-					pltfrm_param->hs_tx_gear);
+	if (host_params->desired_working_mode == UFS_HS_MODE) {
+		is_host_max_hs = true;
+		min_host_gear = min_t(u32, host_params->hs_rx_gear,
+					host_params->hs_tx_gear);
 	} else {
-		min_pltfrm_gear = min_t(u32, pltfrm_param->pwm_rx_gear,
-					pltfrm_param->pwm_tx_gear);
+		min_host_gear = min_t(u32, host_params->pwm_rx_gear,
+					host_params->pwm_tx_gear);
 	}
 
 	/*
-	 * device doesn't support HS but
-	 * pltfrm_param->desired_working_mode is HS,
-	 * thus device and pltfrm_param don't agree
+	 * device doesn't support HS but host_params->desired_working_mode is HS,
+	 * thus device and host_params don't agree
 	 */
-	if (!is_dev_sup_hs && is_pltfrm_max_hs) {
+	if (!is_dev_sup_hs && is_host_max_hs) {
 		pr_info("%s: device doesn't support HS\n",
 			__func__);
 		return -ENOTSUPP;
-	} else if (is_dev_sup_hs && is_pltfrm_max_hs) {
+	} else if (is_dev_sup_hs && is_host_max_hs) {
 		/*
 		 * since device supports HS, it supports FAST_MODE.
-		 * since pltfrm_param->desired_working_mode is also HS
+		 * since host_params->desired_working_mode is also HS
 		 * then final decision (FAST/FASTAUTO) is done according
 		 * to pltfrm_params as it is the restricting factor
 		 */
-		agreed_pwr->pwr_rx = pltfrm_param->rx_pwr_hs;
+		agreed_pwr->pwr_rx = host_params->rx_pwr_hs;
 		agreed_pwr->pwr_tx = agreed_pwr->pwr_rx;
 	} else {
 		/*
-		 * here pltfrm_param->desired_working_mode is PWM.
+		 * here host_params->desired_working_mode is PWM.
 		 * it doesn't matter whether device supports HS or PWM,
-		 * in both cases pltfrm_param->desired_working_mode will
+		 * in both cases host_params->desired_working_mode will
 		 * determine the mode
 		 */
-		agreed_pwr->pwr_rx = pltfrm_param->rx_pwr_pwm;
+		agreed_pwr->pwr_rx = host_params->rx_pwr_pwm;
 		agreed_pwr->pwr_tx = agreed_pwr->pwr_rx;
 	}
 
@@ -349,9 +402,9 @@ int ufshcd_get_pwr_dev_param(const struct ufs_dev_params *pltfrm_param,
 	 * the same decision will be made for rx
 	 */
 	agreed_pwr->lane_tx = min_t(u32, dev_max->lane_tx,
-				    pltfrm_param->tx_lanes);
+				    host_params->tx_lanes);
 	agreed_pwr->lane_rx = min_t(u32, dev_max->lane_rx,
-				    pltfrm_param->rx_lanes);
+				    host_params->rx_lanes);
 
 	/* device maximum gear is the minimum between device rx and tx gears */
 	min_dev_gear = min_t(u32, dev_max->gear_rx, dev_max->gear_tx);
@@ -364,26 +417,26 @@ int ufshcd_get_pwr_dev_param(const struct ufs_dev_params *pltfrm_param,
 	 * what is the gear, as it is the one that also decided previously what
 	 * pwr the device will be configured to.
 	 */
-	if ((is_dev_sup_hs && is_pltfrm_max_hs) ||
-	    (!is_dev_sup_hs && !is_pltfrm_max_hs)) {
+	if ((is_dev_sup_hs && is_host_max_hs) ||
+	    (!is_dev_sup_hs && !is_host_max_hs)) {
 		agreed_pwr->gear_rx =
-			min_t(u32, min_dev_gear, min_pltfrm_gear);
+			min_t(u32, min_dev_gear, min_host_gear);
 	} else if (!is_dev_sup_hs) {
 		agreed_pwr->gear_rx = min_dev_gear;
 	} else {
-		agreed_pwr->gear_rx = min_pltfrm_gear;
+		agreed_pwr->gear_rx = min_host_gear;
 	}
 	agreed_pwr->gear_tx = agreed_pwr->gear_rx;
 
-	agreed_pwr->hs_rate = pltfrm_param->hs_rate;
+	agreed_pwr->hs_rate = host_params->hs_rate;
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(ufshcd_get_pwr_dev_param);
+EXPORT_SYMBOL_GPL(ufshcd_negotiate_pwr_params);
 
-void ufshcd_init_pwr_dev_param(struct ufs_dev_params *dev_param)
+void ufshcd_init_host_params(struct ufs_host_params *host_params)
 {
-	*dev_param = (struct ufs_dev_params){
+	*host_params = (struct ufs_host_params){
 		.tx_lanes = UFS_LANE_2,
 		.rx_lanes = UFS_LANE_2,
 		.hs_rx_gear = UFS_HS_G3,
@@ -398,7 +451,7 @@ void ufshcd_init_pwr_dev_param(struct ufs_dev_params *dev_param)
 		.desired_working_mode = UFS_HS_MODE,
 	};
 }
-EXPORT_SYMBOL_GPL(ufshcd_init_pwr_dev_param);
+EXPORT_SYMBOL_GPL(ufshcd_init_host_params);
 
 /**
  * ufshcd_pltfrm_init - probe routine of the driver
diff --git a/drivers/ufs/host/ufshcd-pltfrm.h b/drivers/ufs/host/ufshcd-pltfrm.h
index a86a3ada4bef..df387be5216b 100644
--- a/drivers/ufs/host/ufshcd-pltfrm.h
+++ b/drivers/ufs/host/ufshcd-pltfrm.h
@@ -10,7 +10,7 @@
 #define UFS_PWM_MODE 1
 #define UFS_HS_MODE  2
 
-struct ufs_dev_params {
+struct ufs_host_params {
 	u32 pwm_rx_gear;        /* pwm rx gear to work in */
 	u32 pwm_tx_gear;        /* pwm tx gear to work in */
 	u32 hs_rx_gear;         /* hs rx gear to work in */
@@ -25,10 +25,10 @@ struct ufs_dev_params {
 	u32 desired_working_mode;
 };
 
-int ufshcd_get_pwr_dev_param(const struct ufs_dev_params *dev_param,
-			     const struct ufs_pa_layer_attr *dev_max,
-			     struct ufs_pa_layer_attr *agreed_pwr);
-void ufshcd_init_pwr_dev_param(struct ufs_dev_params *dev_param);
+int ufshcd_negotiate_pwr_params(const struct ufs_host_params *host_params,
+				const struct ufs_pa_layer_attr *dev_max,
+				struct ufs_pa_layer_attr *agreed_pwr);
+void ufshcd_init_host_params(struct ufs_host_params *host_params);
 int ufshcd_pltfrm_init(struct platform_device *pdev,
 		       const struct ufs_hba_variant_ops *vops);
 int ufshcd_populate_vreg(struct device *dev, const char *name,
diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c
index af981778382d..02f297f5637d 100644
--- a/drivers/usb/cdns3/cdnsp-ring.c
+++ b/drivers/usb/cdns3/cdnsp-ring.c
@@ -1529,6 +1529,7 @@ irqreturn_t cdnsp_thread_irq_handler(int irq, void *data)
 	unsigned long flags;
 	int counter = 0;
 
+	local_bh_disable();
 	spin_lock_irqsave(&pdev->lock, flags);
 
 	if (pdev->cdnsp_state & (CDNSP_STATE_HALTED | CDNSP_STATE_DYING)) {
@@ -1541,6 +1542,7 @@ irqreturn_t cdnsp_thread_irq_handler(int irq, void *data)
 			cdnsp_died(pdev);
 
 		spin_unlock_irqrestore(&pdev->lock, flags);
+		local_bh_enable();
 		return IRQ_HANDLED;
 	}
 
@@ -1557,6 +1559,7 @@ irqreturn_t cdnsp_thread_irq_handler(int irq, void *data)
 	cdnsp_update_erst_dequeue(pdev, event_ring_deq, 1);
 
 	spin_unlock_irqrestore(&pdev->lock, flags);
+	local_bh_enable();
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index b19e38d5fd10..7f8d33f92ddb 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -1047,7 +1047,7 @@ int usb_get_bos_descriptor(struct usb_device *dev)
 
 		if (cap->bDescriptorType != USB_DT_DEVICE_CAPABILITY) {
 			dev_notice(ddev, "descriptor type invalid, skip\n");
-			continue;
+			goto skip_to_next_descriptor;
 		}
 
 		switch (cap_type) {
@@ -1078,6 +1078,7 @@ int usb_get_bos_descriptor(struct usb_device *dev)
 			break;
 		}
 
+skip_to_next_descriptor:
 		total_len -= length;
 		buffer += length;
 	}
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index b4584a0cd484..87480a6e6d93 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -622,29 +622,6 @@ static int hub_ext_port_status(struct usb_hub *hub, int port1, int type,
 		ret = 0;
 	}
 	mutex_unlock(&hub->status_mutex);
-
-	/*
-	 * There is no need to lock status_mutex here, because status_mutex
-	 * protects hub->status, and the phy driver only checks the port
-	 * status without changing the status.
-	 */
-	if (!ret) {
-		struct usb_device *hdev = hub->hdev;
-
-		/*
-		 * Only roothub will be notified of port state changes,
-		 * since the USB PHY only cares about changes at the next
-		 * level.
-		 */
-		if (is_root_hub(hdev)) {
-			struct usb_hcd *hcd = bus_to_hcd(hdev->bus);
-
-			if (hcd->usb_phy)
-				usb_phy_notify_port_status(hcd->usb_phy,
-							   port1 - 1, *status, *change);
-		}
-	}
-
 	return ret;
 }
 
diff --git a/drivers/usb/dwc2/hcd_intr.c b/drivers/usb/dwc2/hcd_intr.c
index 0144ca8350c3..5c7538d498dd 100644
--- a/drivers/usb/dwc2/hcd_intr.c
+++ b/drivers/usb/dwc2/hcd_intr.c
@@ -2015,15 +2015,17 @@ static void dwc2_hc_n_intr(struct dwc2_hsotg *hsotg, int chnum)
 {
 	struct dwc2_qtd *qtd;
 	struct dwc2_host_chan *chan;
-	u32 hcint, hcintmsk;
+	u32 hcint, hcintraw, hcintmsk;
 
 	chan = hsotg->hc_ptr_array[chnum];
 
-	hcint = dwc2_readl(hsotg, HCINT(chnum));
+	hcintraw = dwc2_readl(hsotg, HCINT(chnum));
 	hcintmsk = dwc2_readl(hsotg, HCINTMSK(chnum));
+	hcint = hcintraw & hcintmsk;
+	dwc2_writel(hsotg, hcint, HCINT(chnum));
+
 	if (!chan) {
 		dev_err(hsotg->dev, "## hc_ptr_array for channel is NULL ##\n");
-		dwc2_writel(hsotg, hcint, HCINT(chnum));
 		return;
 	}
 
@@ -2032,11 +2034,9 @@ static void dwc2_hc_n_intr(struct dwc2_hsotg *hsotg, int chnum)
 			 chnum);
 		dev_vdbg(hsotg->dev,
 			 "  hcint 0x%08x, hcintmsk 0x%08x, hcint&hcintmsk 0x%08x\n",
-			 hcint, hcintmsk, hcint & hcintmsk);
+			 hcintraw, hcintmsk, hcint);
 	}
 
-	dwc2_writel(hsotg, hcint, HCINT(chnum));
-
 	/*
 	 * If we got an interrupt after someone called
 	 * dwc2_hcd_endpoint_disable() we don't want to crash below
@@ -2046,8 +2046,7 @@ static void dwc2_hc_n_intr(struct dwc2_hsotg *hsotg, int chnum)
 		return;
 	}
 
-	chan->hcint = hcint;
-	hcint &= hcintmsk;
+	chan->hcint = hcintraw;
 
 	/*
 	 * If the channel was halted due to a dequeue, the qtd list might
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 0328c86ef806..b101dbf8c5dc 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -2034,6 +2034,8 @@ static int dwc3_probe(struct platform_device *pdev)
 
 	pm_runtime_put(dev);
 
+	dma_set_max_seg_size(dev, UINT_MAX);
+
 	return 0;
 
 err_exit_debugfs:
diff --git a/drivers/usb/dwc3/drd.c b/drivers/usb/dwc3/drd.c
index 039bf241769a..57ddd2e43022 100644
--- a/drivers/usb/dwc3/drd.c
+++ b/drivers/usb/dwc3/drd.c
@@ -505,6 +505,7 @@ static int dwc3_setup_role_switch(struct dwc3 *dwc)
 		dwc->role_switch_default_mode = USB_DR_MODE_PERIPHERAL;
 		mode = DWC3_GCTL_PRTCAP_DEVICE;
 	}
+	dwc3_set_mode(dwc, mode);
 
 	dwc3_role_switch.fwnode = dev_fwnode(dwc->dev);
 	dwc3_role_switch.set = dwc3_usb_role_switch_set;
@@ -526,7 +527,6 @@ static int dwc3_setup_role_switch(struct dwc3 *dwc)
 		}
 	}
 
-	dwc3_set_mode(dwc, mode);
 	return 0;
 }
 #else
diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c
index 3de43df6bbe8..fdf6d5d3c2ad 100644
--- a/drivers/usb/dwc3/dwc3-qcom.c
+++ b/drivers/usb/dwc3/dwc3-qcom.c
@@ -546,10 +546,9 @@ static int dwc3_qcom_setup_irq(struct platform_device *pdev)
 				pdata ? pdata->hs_phy_irq_index : -1);
 	if (irq > 0) {
 		/* Keep wakeup interrupts disabled until suspend */
-		irq_set_status_flags(irq, IRQ_NOAUTOEN);
 		ret = devm_request_threaded_irq(qcom->dev, irq, NULL,
 					qcom_dwc3_resume_irq,
-					IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
+					IRQF_ONESHOT | IRQF_NO_AUTOEN,
 					"qcom_dwc3 HS", qcom);
 		if (ret) {
 			dev_err(qcom->dev, "hs_phy_irq failed: %d\n", ret);
@@ -561,10 +560,9 @@ static int dwc3_qcom_setup_irq(struct platform_device *pdev)
 	irq = dwc3_qcom_get_irq(pdev, "dp_hs_phy_irq",
 				pdata ? pdata->dp_hs_phy_irq_index : -1);
 	if (irq > 0) {
-		irq_set_status_flags(irq, IRQ_NOAUTOEN);
 		ret = devm_request_threaded_irq(qcom->dev, irq, NULL,
 					qcom_dwc3_resume_irq,
-					IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
+					IRQF_ONESHOT | IRQF_NO_AUTOEN,
 					"qcom_dwc3 DP_HS", qcom);
 		if (ret) {
 			dev_err(qcom->dev, "dp_hs_phy_irq failed: %d\n", ret);
@@ -576,10 +574,9 @@ static int dwc3_qcom_setup_irq(struct platform_device *pdev)
 	irq = dwc3_qcom_get_irq(pdev, "dm_hs_phy_irq",
 				pdata ? pdata->dm_hs_phy_irq_index : -1);
 	if (irq > 0) {
-		irq_set_status_flags(irq, IRQ_NOAUTOEN);
 		ret = devm_request_threaded_irq(qcom->dev, irq, NULL,
 					qcom_dwc3_resume_irq,
-					IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
+					IRQF_ONESHOT | IRQF_NO_AUTOEN,
 					"qcom_dwc3 DM_HS", qcom);
 		if (ret) {
 			dev_err(qcom->dev, "dm_hs_phy_irq failed: %d\n", ret);
@@ -591,10 +588,9 @@ static int dwc3_qcom_setup_irq(struct platform_device *pdev)
 	irq = dwc3_qcom_get_irq(pdev, "ss_phy_irq",
 				pdata ? pdata->ss_phy_irq_index : -1);
 	if (irq > 0) {
-		irq_set_status_flags(irq, IRQ_NOAUTOEN);
 		ret = devm_request_threaded_irq(qcom->dev, irq, NULL,
 					qcom_dwc3_resume_irq,
-					IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
+					IRQF_ONESHOT | IRQF_NO_AUTOEN,
 					"qcom_dwc3 SS", qcom);
 		if (ret) {
 			dev_err(qcom->dev, "ss_phy_irq failed: %d\n", ret);
@@ -758,6 +754,7 @@ static int dwc3_qcom_of_register_core(struct platform_device *pdev)
 	if (!qcom->dwc3) {
 		ret = -ENODEV;
 		dev_err(dev, "failed to get dwc3 platform device\n");
+		of_platform_depopulate(dev);
 	}
 
 node_put:
@@ -766,9 +763,9 @@ node_put:
 	return ret;
 }
 
-static struct platform_device *
-dwc3_qcom_create_urs_usb_platdev(struct device *dev)
+static struct platform_device *dwc3_qcom_create_urs_usb_platdev(struct device *dev)
 {
+	struct platform_device *urs_usb = NULL;
 	struct fwnode_handle *fwh;
 	struct acpi_device *adev;
 	char name[8];
@@ -788,9 +785,26 @@ dwc3_qcom_create_urs_usb_platdev(struct device *dev)
 
 	adev = to_acpi_device_node(fwh);
 	if (!adev)
-		return NULL;
+		goto err_put_handle;
+
+	urs_usb = acpi_create_platform_device(adev, NULL);
+	if (IS_ERR_OR_NULL(urs_usb))
+		goto err_put_handle;
+
+	return urs_usb;
+
+err_put_handle:
+	fwnode_handle_put(fwh);
+
+	return urs_usb;
+}
 
-	return acpi_create_platform_device(adev, NULL);
+static void dwc3_qcom_destroy_urs_usb_platdev(struct platform_device *urs_usb)
+{
+	struct fwnode_handle *fwh = urs_usb->dev.fwnode;
+
+	platform_device_unregister(urs_usb);
+	fwnode_handle_put(fwh);
 }
 
 static int dwc3_qcom_probe(struct platform_device *pdev)
@@ -874,13 +888,13 @@ static int dwc3_qcom_probe(struct platform_device *pdev)
 	qcom->qscratch_base = devm_ioremap_resource(dev, parent_res);
 	if (IS_ERR(qcom->qscratch_base)) {
 		ret = PTR_ERR(qcom->qscratch_base);
-		goto clk_disable;
+		goto free_urs;
 	}
 
 	ret = dwc3_qcom_setup_irq(pdev);
 	if (ret) {
 		dev_err(dev, "failed to setup IRQs, err=%d\n", ret);
-		goto clk_disable;
+		goto free_urs;
 	}
 
 	/*
@@ -899,7 +913,7 @@ static int dwc3_qcom_probe(struct platform_device *pdev)
 
 	if (ret) {
 		dev_err(dev, "failed to register DWC3 Core, err=%d\n", ret);
-		goto depopulate;
+		goto free_urs;
 	}
 
 	ret = dwc3_qcom_interconnect_init(qcom);
@@ -931,10 +945,16 @@ static int dwc3_qcom_probe(struct platform_device *pdev)
 interconnect_exit:
 	dwc3_qcom_interconnect_exit(qcom);
 depopulate:
-	if (np)
+	if (np) {
 		of_platform_depopulate(&pdev->dev);
-	else
-		platform_device_put(pdev);
+	} else {
+		device_remove_software_node(&qcom->dwc3->dev);
+		platform_device_del(qcom->dwc3);
+	}
+	platform_device_put(qcom->dwc3);
+free_urs:
+	if (qcom->urs_usb)
+		dwc3_qcom_destroy_urs_usb_platdev(qcom->urs_usb);
 clk_disable:
 	for (i = qcom->num_clocks - 1; i >= 0; i--) {
 		clk_disable_unprepare(qcom->clks[i]);
@@ -953,11 +973,16 @@ static void dwc3_qcom_remove(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	int i;
 
-	device_remove_software_node(&qcom->dwc3->dev);
-	if (np)
+	if (np) {
 		of_platform_depopulate(&pdev->dev);
-	else
-		platform_device_put(pdev);
+	} else {
+		device_remove_software_node(&qcom->dwc3->dev);
+		platform_device_del(qcom->dwc3);
+	}
+	platform_device_put(qcom->dwc3);
+
+	if (qcom->urs_usb)
+		dwc3_qcom_destroy_urs_usb_platdev(qcom->urs_usb);
 
 	for (i = qcom->num_clocks - 1; i >= 0; i--) {
 		clk_disable_unprepare(qcom->clks[i]);
diff --git a/drivers/usb/dwc3/dwc3-rtk.c b/drivers/usb/dwc3/dwc3-rtk.c
index 590028e8fdcb..3cd6b184551c 100644
--- a/drivers/usb/dwc3/dwc3-rtk.c
+++ b/drivers/usb/dwc3/dwc3-rtk.c
@@ -183,10 +183,13 @@ static enum usb_device_speed __get_dwc3_maximum_speed(struct device_node *np)
 
 	ret = of_property_read_string(dwc3_np, "maximum-speed", &maximum_speed);
 	if (ret < 0)
-		return USB_SPEED_UNKNOWN;
+		goto out;
 
 	ret = match_string(speed_names, ARRAY_SIZE(speed_names), maximum_speed);
 
+out:
+	of_node_put(dwc3_np);
+
 	return (ret < 0) ? USB_SPEED_UNKNOWN : ret;
 }
 
@@ -339,6 +342,9 @@ static int dwc3_rtk_probe_dwc3_core(struct dwc3_rtk *rtk)
 
 	switch_usb2_role(rtk, rtk->cur_role);
 
+	platform_device_put(dwc3_pdev);
+	of_node_put(dwc3_node);
+
 	return 0;
 
 err_pdev_put:
diff --git a/drivers/usb/fotg210/fotg210-hcd.c b/drivers/usb/fotg210/fotg210-hcd.c
index 929106c16b29..7bf810a0c98a 100644
--- a/drivers/usb/fotg210/fotg210-hcd.c
+++ b/drivers/usb/fotg210/fotg210-hcd.c
@@ -428,8 +428,6 @@ static void qh_lines(struct fotg210_hcd *fotg210, struct fotg210_qh *qh,
 			temp = size;
 		size -= temp;
 		next += temp;
-		if (temp == size)
-			goto done;
 	}
 
 	temp = snprintf(next, size, "\n");
@@ -439,7 +437,6 @@ static void qh_lines(struct fotg210_hcd *fotg210, struct fotg210_qh *qh,
 	size -= temp;
 	next += temp;
 
-done:
 	*sizep = size;
 	*nextp = next;
 }
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index efe3e3b85769..fdd0fc7b8f25 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -831,7 +831,7 @@ static void ffs_user_copy_worker(struct work_struct *work)
 	io_data->kiocb->ki_complete(io_data->kiocb, ret);
 
 	if (io_data->ffs->ffs_eventfd && !kiocb_has_eventfd)
-		eventfd_signal(io_data->ffs->ffs_eventfd, 1);
+		eventfd_signal(io_data->ffs->ffs_eventfd);
 
 	if (io_data->read)
 		kfree(io_data->to_free);
@@ -2738,7 +2738,7 @@ static void __ffs_event_add(struct ffs_data *ffs,
 	ffs->ev.types[ffs->ev.count++] = type;
 	wake_up_locked(&ffs->ev.waitq);
 	if (ffs->ffs_eventfd)
-		eventfd_signal(ffs->ffs_eventfd, 1);
+		eventfd_signal(ffs->ffs_eventfd);
 }
 
 static void ffs_event_add(struct ffs_data *ffs,
diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c
index ea85e2c701a1..3c8a9dd585c0 100644
--- a/drivers/usb/gadget/function/f_hid.c
+++ b/drivers/usb/gadget/function/f_hid.c
@@ -92,6 +92,7 @@ static void hidg_release(struct device *dev)
 {
 	struct f_hidg *hidg = container_of(dev, struct f_hidg, dev);
 
+	kfree(hidg->report_desc);
 	kfree(hidg->set_report_buf);
 	kfree(hidg);
 }
@@ -1287,9 +1288,9 @@ static struct usb_function *hidg_alloc(struct usb_function_instance *fi)
 	hidg->report_length = opts->report_length;
 	hidg->report_desc_length = opts->report_desc_length;
 	if (opts->report_desc) {
-		hidg->report_desc = devm_kmemdup(&hidg->dev, opts->report_desc,
-						 opts->report_desc_length,
-						 GFP_KERNEL);
+		hidg->report_desc = kmemdup(opts->report_desc,
+					    opts->report_desc_length,
+					    GFP_KERNEL);
 		if (!hidg->report_desc) {
 			ret = -ENOMEM;
 			goto err_put_device;
diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c
index ded9531f141b..d59f94464b87 100644
--- a/drivers/usb/gadget/udc/core.c
+++ b/drivers/usb/gadget/udc/core.c
@@ -1646,8 +1646,6 @@ static void gadget_unbind_driver(struct device *dev)
 
 	dev_dbg(&udc->dev, "unbinding gadget driver [%s]\n", driver->function);
 
-	kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE);
-
 	udc->allow_connect = false;
 	cancel_work_sync(&udc->vbus_work);
 	mutex_lock(&udc->connect_lock);
@@ -1667,6 +1665,8 @@ static void gadget_unbind_driver(struct device *dev)
 	driver->is_bound = false;
 	udc->driver = NULL;
 	mutex_unlock(&udc_lock);
+
+	kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE);
 }
 
 /* ------------------------------------------------------------------------- */
diff --git a/drivers/usb/gadget/udc/max3420_udc.c b/drivers/usb/gadget/udc/max3420_udc.c
index 2d57786d3db7..89e8cf2a2a7d 100644
--- a/drivers/usb/gadget/udc/max3420_udc.c
+++ b/drivers/usb/gadget/udc/max3420_udc.c
@@ -1201,7 +1201,7 @@ static int max3420_probe(struct spi_device *spi)
 	int err, irq;
 	u8 reg[8];
 
-	if (spi->master->flags & SPI_MASTER_HALF_DUPLEX) {
+	if (spi->master->flags & SPI_CONTROLLER_HALF_DUPLEX) {
 		dev_err(&spi->dev, "UDC needs full duplex to work\n");
 		return -EINVAL;
 	}
diff --git a/drivers/usb/host/fsl-mph-dr-of.c b/drivers/usb/host/fsl-mph-dr-of.c
index 8508d37a2aff..6cdc3d805c32 100644
--- a/drivers/usb/host/fsl-mph-dr-of.c
+++ b/drivers/usb/host/fsl-mph-dr-of.c
@@ -288,7 +288,7 @@ static void fsl_usb2_mph_dr_of_remove(struct platform_device *ofdev)
 #define PHYCTRL_LSFE		(1 << 1)	/* Line State Filter Enable */
 #define PHYCTRL_PXE		(1 << 0)	/* PHY oscillator enable */
 
-int fsl_usb2_mpc5121_init(struct platform_device *pdev)
+static int fsl_usb2_mpc5121_init(struct platform_device *pdev)
 {
 	struct fsl_usb2_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	struct clk *clk;
diff --git a/drivers/usb/host/xhci-mtk-sch.c b/drivers/usb/host/xhci-mtk-sch.c
index 5b3cd455adec..61f3f8bbdcea 100644
--- a/drivers/usb/host/xhci-mtk-sch.c
+++ b/drivers/usb/host/xhci-mtk-sch.c
@@ -650,9 +650,8 @@ static int check_isoc_ss_overlap(struct mu3h_sch_ep_info *sch_ep, u32 offset)
 
 		if (sch_ep->ep_type == ISOC_OUT_EP) {
 			for (j = 0; j < sch_ep->num_budget_microframes; j++) {
-				k = XHCI_MTK_BW_INDEX(base + j + CS_OFFSET);
-				/* use cs to indicate existence of in-ss @(base+j) */
-				if (tt->fs_bus_bw_in[k])
+				k = XHCI_MTK_BW_INDEX(base + j);
+				if (tt->in_ss_cnt[k])
 					return -ESCH_SS_OVERLAP;
 			}
 		} else if (sch_ep->ep_type == ISOC_IN_EP || sch_ep->ep_type == INT_IN_EP) {
@@ -769,6 +768,14 @@ static void update_sch_tt(struct mu3h_sch_ep_info *sch_ep, bool used)
 				tt->fs_frame_bw[f] -= (u16)sch_ep->bw_budget_table[j];
 			}
 		}
+
+		if (sch_ep->ep_type == ISOC_IN_EP || sch_ep->ep_type == INT_IN_EP) {
+			k = XHCI_MTK_BW_INDEX(base);
+			if (used)
+				tt->in_ss_cnt[k]++;
+			else
+				tt->in_ss_cnt[k]--;
+		}
 	}
 
 	if (used)
diff --git a/drivers/usb/host/xhci-mtk.h b/drivers/usb/host/xhci-mtk.h
index 865b55e23b15..39f7ae7d3087 100644
--- a/drivers/usb/host/xhci-mtk.h
+++ b/drivers/usb/host/xhci-mtk.h
@@ -38,6 +38,7 @@
  * @fs_bus_bw_in: save bandwidth used by FS/LS IN eps in each uframes
  * @ls_bus_bw: save bandwidth used by LS eps in each uframes
  * @fs_frame_bw: save bandwidth used by FS/LS eps in each FS frames
+ * @in_ss_cnt: the count of Start-Split for IN eps
  * @ep_list: Endpoints using this TT
  */
 struct mu3h_sch_tt {
@@ -45,6 +46,7 @@ struct mu3h_sch_tt {
 	u16 fs_bus_bw_in[XHCI_MTK_MAX_ESIT];
 	u8 ls_bus_bw[XHCI_MTK_MAX_ESIT];
 	u16 fs_frame_bw[XHCI_MTK_FRAMES_CNT];
+	u8 in_ss_cnt[XHCI_MTK_MAX_ESIT];
 	struct list_head ep_list;
 };
 
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 95ed9404f6f8..d6fc08e5db8f 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -535,8 +535,6 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 	/* xHC spec requires PCI devices to support D3hot and D3cold */
 	if (xhci->hci_version >= 0x120)
 		xhci->quirks |= XHCI_DEFAULT_PM_RUNTIME_ALLOW;
-	else if (pdev->vendor == PCI_VENDOR_ID_AMD && xhci->hci_version >= 0x110)
-		xhci->quirks |= XHCI_DEFAULT_PM_RUNTIME_ALLOW;
 
 	if (xhci->quirks & XHCI_RESET_ON_RESUME)
 		xhci_dbg_trace(xhci, trace_xhci_dbg_quirks,
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index b93161374293..732cdeb73920 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/usb/phy.h>
 #include <linux/slab.h>
@@ -148,7 +149,7 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s
 	int			ret;
 	int			irq;
 	struct xhci_plat_priv	*priv = NULL;
-
+	bool			of_match;
 
 	if (usb_disabled())
 		return -ENODEV;
@@ -253,16 +254,23 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s
 					 &xhci->imod_interval);
 	}
 
-	hcd->usb_phy = devm_usb_get_phy_by_phandle(sysdev, "usb-phy", 0);
-	if (IS_ERR(hcd->usb_phy)) {
-		ret = PTR_ERR(hcd->usb_phy);
-		if (ret == -EPROBE_DEFER)
-			goto disable_clk;
-		hcd->usb_phy = NULL;
-	} else {
-		ret = usb_phy_init(hcd->usb_phy);
-		if (ret)
-			goto disable_clk;
+	/*
+	 * Drivers such as dwc3 manages PHYs themself (and rely on driver name
+	 * matching for the xhci platform device).
+	 */
+	of_match = of_match_device(pdev->dev.driver->of_match_table, &pdev->dev);
+	if (of_match) {
+		hcd->usb_phy = devm_usb_get_phy_by_phandle(sysdev, "usb-phy", 0);
+		if (IS_ERR(hcd->usb_phy)) {
+			ret = PTR_ERR(hcd->usb_phy);
+			if (ret == -EPROBE_DEFER)
+				goto disable_clk;
+			hcd->usb_phy = NULL;
+		} else {
+			ret = usb_phy_init(hcd->usb_phy);
+			if (ret)
+				goto disable_clk;
+		}
 	}
 
 	hcd->tpl_support = of_usb_host_tpl_support(sysdev->of_node);
@@ -285,15 +293,17 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s
 			goto dealloc_usb2_hcd;
 		}
 
-		xhci->shared_hcd->usb_phy = devm_usb_get_phy_by_phandle(sysdev,
-			    "usb-phy", 1);
-		if (IS_ERR(xhci->shared_hcd->usb_phy)) {
-			xhci->shared_hcd->usb_phy = NULL;
-		} else {
-			ret = usb_phy_init(xhci->shared_hcd->usb_phy);
-			if (ret)
-				dev_err(sysdev, "%s init usb3phy fail (ret=%d)\n",
-					    __func__, ret);
+		if (of_match) {
+			xhci->shared_hcd->usb_phy = devm_usb_get_phy_by_phandle(sysdev,
+										"usb-phy", 1);
+			if (IS_ERR(xhci->shared_hcd->usb_phy)) {
+				xhci->shared_hcd->usb_phy = NULL;
+			} else {
+				ret = usb_phy_init(xhci->shared_hcd->usb_phy);
+				if (ret)
+					dev_err(sysdev, "%s init usb3phy fail (ret=%d)\n",
+						__func__, ret);
+			}
 		}
 
 		xhci->shared_hcd->tpl_support = hcd->tpl_support;
diff --git a/drivers/usb/misc/onboard_usb_hub.c b/drivers/usb/misc/onboard_usb_hub.c
index a341b2fbb7b4..2b45404e9732 100644
--- a/drivers/usb/misc/onboard_usb_hub.c
+++ b/drivers/usb/misc/onboard_usb_hub.c
@@ -432,6 +432,8 @@ static const struct usb_device_id onboard_hub_id_table[] = {
 	{ USB_DEVICE(VENDOR_ID_MICROCHIP, 0x2412) }, /* USB2412 USB 2.0 */
 	{ USB_DEVICE(VENDOR_ID_MICROCHIP, 0x2514) }, /* USB2514B USB 2.0 */
 	{ USB_DEVICE(VENDOR_ID_MICROCHIP, 0x2517) }, /* USB2517 USB 2.0 */
+	{ USB_DEVICE(VENDOR_ID_MICROCHIP, 0x2744) }, /* USB5744 USB 2.0 */
+	{ USB_DEVICE(VENDOR_ID_MICROCHIP, 0x5744) }, /* USB5744 USB 3.0 */
 	{ USB_DEVICE(VENDOR_ID_REALTEK, 0x0411) }, /* RTS5411 USB 3.1 */
 	{ USB_DEVICE(VENDOR_ID_REALTEK, 0x5411) }, /* RTS5411 USB 2.1 */
 	{ USB_DEVICE(VENDOR_ID_REALTEK, 0x0414) }, /* RTS5414 USB 3.2 */
diff --git a/drivers/usb/misc/onboard_usb_hub.h b/drivers/usb/misc/onboard_usb_hub.h
index c4e24a7b9290..292110e64a1d 100644
--- a/drivers/usb/misc/onboard_usb_hub.h
+++ b/drivers/usb/misc/onboard_usb_hub.h
@@ -16,6 +16,11 @@ static const struct onboard_hub_pdata microchip_usb424_data = {
 	.num_supplies = 1,
 };
 
+static const struct onboard_hub_pdata microchip_usb5744_data = {
+	.reset_us = 0,
+	.num_supplies = 2,
+};
+
 static const struct onboard_hub_pdata realtek_rts5411_data = {
 	.reset_us = 0,
 	.num_supplies = 1,
@@ -50,6 +55,8 @@ static const struct of_device_id onboard_hub_match[] = {
 	{ .compatible = "usb424,2412", .data = &microchip_usb424_data, },
 	{ .compatible = "usb424,2514", .data = &microchip_usb424_data, },
 	{ .compatible = "usb424,2517", .data = &microchip_usb424_data, },
+	{ .compatible = "usb424,2744", .data = &microchip_usb5744_data, },
+	{ .compatible = "usb424,5744", .data = &microchip_usb5744_data, },
 	{ .compatible = "usb451,8140", .data = &ti_tusb8041_data, },
 	{ .compatible = "usb451,8142", .data = &ti_tusb8041_data, },
 	{ .compatible = "usb4b4,6504", .data = &cypress_hx3_data, },
diff --git a/drivers/usb/misc/usb-ljca.c b/drivers/usb/misc/usb-ljca.c
index c9decd0396d4..35770e608c64 100644
--- a/drivers/usb/misc/usb-ljca.c
+++ b/drivers/usb/misc/usb-ljca.c
@@ -457,8 +457,8 @@ static void ljca_auxdev_acpi_bind(struct ljca_adapter *adap,
 				  u64 adr, u8 id)
 {
 	struct ljca_match_ids_walk_data wd = { 0 };
-	struct acpi_device *parent, *adev;
 	struct device *dev = adap->dev;
+	struct acpi_device *parent;
 	char uid[4];
 
 	parent = ACPI_COMPANION(dev);
@@ -466,17 +466,7 @@ static void ljca_auxdev_acpi_bind(struct ljca_adapter *adap,
 		return;
 
 	/*
-	 * get auxdev ACPI handle from the ACPI device directly
-	 * under the parent that matches _ADR.
-	 */
-	adev = acpi_find_child_device(parent, adr, false);
-	if (adev) {
-		ACPI_COMPANION_SET(&auxdev->dev, adev);
-		return;
-	}
-
-	/*
-	 * _ADR is a grey area in the ACPI specification, some
+	 * Currently LJCA hw doesn't use _ADR instead the shipped
 	 * platforms use _HID to distinguish children devices.
 	 */
 	switch (adr) {
@@ -656,10 +646,11 @@ static int ljca_enumerate_spi(struct ljca_adapter *adap)
 	unsigned int i;
 	int ret;
 
+	/* Not all LJCA chips implement SPI, a timeout reading the descriptors is normal */
 	ret = ljca_send(adap, LJCA_CLIENT_MNG, LJCA_MNG_ENUM_SPI, NULL, 0, buf,
 			sizeof(buf), true, LJCA_ENUM_CLIENT_TIMEOUT_MS);
 	if (ret < 0)
-		return ret;
+		return (ret == -ETIMEDOUT) ? 0 : ret;
 
 	/* check firmware response */
 	desc = (struct ljca_spi_descriptor *)buf;
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 1bf23611be12..13a56783830d 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -1033,9 +1033,9 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(FTDI_VID, ACTISENSE_USG_PID) },
 	{ USB_DEVICE(FTDI_VID, ACTISENSE_NGT_PID) },
 	{ USB_DEVICE(FTDI_VID, ACTISENSE_NGW_PID) },
-	{ USB_DEVICE(FTDI_VID, ACTISENSE_D9AC_PID) },
-	{ USB_DEVICE(FTDI_VID, ACTISENSE_D9AD_PID) },
-	{ USB_DEVICE(FTDI_VID, ACTISENSE_D9AE_PID) },
+	{ USB_DEVICE(FTDI_VID, ACTISENSE_UID_PID) },
+	{ USB_DEVICE(FTDI_VID, ACTISENSE_USA_PID) },
+	{ USB_DEVICE(FTDI_VID, ACTISENSE_NGX_PID) },
 	{ USB_DEVICE(FTDI_VID, ACTISENSE_D9AF_PID) },
 	{ USB_DEVICE(FTDI_VID, CHETCO_SEAGAUGE_PID) },
 	{ USB_DEVICE(FTDI_VID, CHETCO_SEASWITCH_PID) },
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index e2099445db70..21a2b5a25fc0 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -1568,9 +1568,9 @@
 #define ACTISENSE_USG_PID		0xD9A9 /* USG USB Serial Adapter */
 #define ACTISENSE_NGT_PID		0xD9AA /* NGT NMEA2000 Interface */
 #define ACTISENSE_NGW_PID		0xD9AB /* NGW NMEA2000 Gateway */
-#define ACTISENSE_D9AC_PID		0xD9AC /* Actisense Reserved */
-#define ACTISENSE_D9AD_PID		0xD9AD /* Actisense Reserved */
-#define ACTISENSE_D9AE_PID		0xD9AE /* Actisense Reserved */
+#define ACTISENSE_UID_PID		0xD9AC /* USB Isolating Device */
+#define ACTISENSE_USA_PID		0xD9AD /* USB to Serial Adapter */
+#define ACTISENSE_NGX_PID		0xD9AE /* NGX NMEA2000 Gateway */
 #define ACTISENSE_D9AF_PID		0xD9AF /* Actisense Reserved */
 #define CHETCO_SEAGAUGE_PID		0xA548 /* SeaGauge USB Adapter */
 #define CHETCO_SEASWITCH_PID		0xA549 /* SeaSwitch USB Adapter */
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 45dcfaadaf98..72390dbf0769 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -203,8 +203,8 @@ static void option_instat_callback(struct urb *urb);
 #define DELL_PRODUCT_5829E_ESIM			0x81e4
 #define DELL_PRODUCT_5829E			0x81e6
 
-#define DELL_PRODUCT_FM101R			0x8213
-#define DELL_PRODUCT_FM101R_ESIM		0x8215
+#define DELL_PRODUCT_FM101R_ESIM		0x8213
+#define DELL_PRODUCT_FM101R			0x8215
 
 #define KYOCERA_VENDOR_ID			0x0c88
 #define KYOCERA_PRODUCT_KPC650			0x17da
@@ -272,6 +272,7 @@ static void option_instat_callback(struct urb *urb);
 #define QUECTEL_PRODUCT_RM500Q			0x0800
 #define QUECTEL_PRODUCT_RM520N			0x0801
 #define QUECTEL_PRODUCT_EC200U			0x0901
+#define QUECTEL_PRODUCT_EG912Y			0x6001
 #define QUECTEL_PRODUCT_EC200S_CN		0x6002
 #define QUECTEL_PRODUCT_EC200A			0x6005
 #define QUECTEL_PRODUCT_EM061K_LWW		0x6008
@@ -609,6 +610,8 @@ static void option_instat_callback(struct urb *urb);
 #define UNISOC_VENDOR_ID			0x1782
 /* TOZED LT70-C based on UNISOC SL8563 uses UNISOC's vendor ID */
 #define TOZED_PRODUCT_LT70C			0x4055
+/* Luat Air72*U series based on UNISOC UIS8910 uses UNISOC's vendor ID */
+#define LUAT_PRODUCT_AIR720U			0x4e00
 
 /* Device flags */
 
@@ -1230,6 +1233,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, 0x0700, 0xff), /* BG95 */
 	  .driver_info = RSVD(3) | ZLP },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x30) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0, 0x40) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x10),
 	  .driver_info = ZLP },
@@ -1242,6 +1246,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200U, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200S_CN, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200T, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG912Y, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500K, 0xff, 0x00, 0x00) },
 
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) },
@@ -1546,7 +1551,8 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0165, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0167, 0xff, 0xff, 0xff),
 	  .driver_info = RSVD(4) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0189, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0189, 0xff, 0xff, 0xff),
+	  .driver_info = RSVD(4) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0191, 0xff, 0xff, 0xff), /* ZTE EuFi890 */
 	  .driver_info = RSVD(4) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0196, 0xff, 0xff, 0xff) },
@@ -2239,6 +2245,8 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = RSVD(0) | RSVD(1) | RSVD(6) },
 	{ USB_DEVICE(0x0489, 0xe0b5),						/* Foxconn T77W968 ESIM */
 	  .driver_info = RSVD(0) | RSVD(1) | RSVD(6) },
+	{ USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0da, 0xff),                     /* Foxconn T99W265 MBIM variant */
+	  .driver_info = RSVD(3) | RSVD(5) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0db, 0xff),			/* Foxconn T99W265 MBIM */
 	  .driver_info = RSVD(3) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0ee, 0xff),			/* Foxconn T99W368 MBIM */
@@ -2249,6 +2257,7 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = RSVD(4) | RSVD(5) | RSVD(6) },
 	{ USB_DEVICE(0x1782, 0x4d10) },						/* Fibocom L610 (AT mode) */
 	{ USB_DEVICE_INTERFACE_CLASS(0x1782, 0x4d11, 0xff) },			/* Fibocom L610 (ECM/RNDIS mode) */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x0001, 0xff, 0xff, 0xff) },	/* Fibocom L716-EU (ECM/RNDIS mode) */
 	{ USB_DEVICE(0x2cb7, 0x0104),						/* Fibocom NL678 series */
 	  .driver_info = RSVD(4) | RSVD(5) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0105, 0xff),			/* Fibocom NL678 series */
@@ -2271,6 +2280,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x40) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, LUAT_PRODUCT_AIR720U, 0xff, 0, 0) },
 	{ } /* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, option_ids);
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 20dcbccb290b..fd68204374f2 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -1306,6 +1306,17 @@ UNUSUAL_DEV(  0x090c, 0x6000, 0x0100, 0x0100,
 		US_FL_INITIAL_READ10 ),
 
 /*
+ * Patch by Tasos Sahanidis <tasos@tasossah.com>
+ * This flash drive always shows up with write protect enabled
+ * during the first mode sense.
+ */
+UNUSUAL_DEV(0x0951, 0x1697, 0x0100, 0x0100,
+		"Kingston",
+		"DT Ultimate G3",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_WP_DETECT),
+
+/*
  * This Pentax still camera is not conformant
  * to the USB storage specification: -
  * - It does not like the INQUIRY command. So we must handle this command
diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c
index 2e0451bd336e..16a670828dde 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -267,7 +267,7 @@ static void typec_altmode_put_partner(struct altmode *altmode)
 	if (!partner)
 		return;
 
-	adev = &partner->adev;
+	adev = &altmode->adev;
 
 	if (is_typec_plug(adev->dev.parent)) {
 		struct typec_plug *plug = to_typec_plug(adev->dev.parent);
@@ -497,7 +497,8 @@ static void typec_altmode_release(struct device *dev)
 {
 	struct altmode *alt = to_altmode(to_typec_altmode(dev));
 
-	typec_altmode_put_partner(alt);
+	if (!is_typec_port(dev->parent))
+		typec_altmode_put_partner(alt);
 
 	altmode_id_remove(alt->adev.dev.parent, alt->id);
 	kfree(alt);
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 058d5b853b57..bfb6f9481e87 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -4273,7 +4273,8 @@ static void run_state_machine(struct tcpm_port *port)
 				current_lim = PD_P_SNK_STDBY_MW / 5;
 			tcpm_set_current_limit(port, current_lim, 5000);
 			/* Not sink vbus if operational current is 0mA */
-			tcpm_set_charge(port, !!pdo_max_current(port->snk_pdo[0]));
+			tcpm_set_charge(port, !port->pd_supported ||
+					pdo_max_current(port->snk_pdo[0]));
 
 			if (!port->pd_supported)
 				tcpm_set_state(port, SNK_READY, 0);
@@ -5391,6 +5392,15 @@ static void _tcpm_pd_hard_reset(struct tcpm_port *port)
 	if (port->bist_request == BDO_MODE_TESTDATA && port->tcpc->set_bist_data)
 		port->tcpc->set_bist_data(port->tcpc, false);
 
+	switch (port->state) {
+	case ERROR_RECOVERY:
+	case PORT_RESET:
+	case PORT_RESET_WAIT_OFF:
+		return;
+	default:
+		break;
+	}
+
 	if (port->ams != NONE_AMS)
 		port->ams = NONE_AMS;
 	if (port->hard_reset_count < PD_N_HARD_RESET_COUNT)
diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c
index 0e867f531d34..196535ad996d 100644
--- a/drivers/usb/typec/tipd/core.c
+++ b/drivers/usb/typec/tipd/core.c
@@ -968,16 +968,17 @@ static int tps25750_start_patch_burst_mode(struct tps6598x *tps)
 	ret = of_property_match_string(np, "reg-names", "patch-address");
 	if (ret < 0) {
 		dev_err(tps->dev, "failed to get patch-address %d\n", ret);
-		return ret;
+		goto release_fw;
 	}
 
 	ret = of_property_read_u32_index(np, "reg", ret, &addr);
 	if (ret)
-		return ret;
+		goto release_fw;
 
 	if (addr == 0 || (addr >= 0x20 && addr <= 0x23)) {
 		dev_err(tps->dev, "wrong patch address %u\n", addr);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto release_fw;
 	}
 
 	bpms_data.addr = (u8)addr;
@@ -1226,7 +1227,10 @@ static int tps6598x_probe(struct i2c_client *client)
 			TPS_REG_INT_PLUG_EVENT;
 	}
 
-	tps->data = device_get_match_data(tps->dev);
+	if (dev_fwnode(tps->dev))
+		tps->data = device_get_match_data(tps->dev);
+	else
+		tps->data = i2c_get_match_data(client);
 	if (!tps->data)
 		return -EINVAL;
 
@@ -1425,7 +1429,7 @@ static const struct of_device_id tps6598x_of_match[] = {
 MODULE_DEVICE_TABLE(of, tps6598x_of_match);
 
 static const struct i2c_device_id tps6598x_id[] = {
-	{ "tps6598x" },
+	{ "tps6598x", (kernel_ulong_t)&tps6598x_data },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, tps6598x_id);
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index 61b64558f96c..5392ec698959 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -578,6 +578,9 @@ static int ucsi_read_pdos(struct ucsi_connector *con,
 	u64 command;
 	int ret;
 
+	if (ucsi->quirks & UCSI_NO_PARTNER_PDOS)
+		return 0;
+
 	command = UCSI_COMMAND(UCSI_GET_PDOS) | UCSI_CONNECTOR_NUMBER(con->num);
 	command |= UCSI_GET_PDOS_PARTNER_PDO(is_partner);
 	command |= UCSI_GET_PDOS_PDO_OFFSET(offset);
diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h
index 474315a72c77..6478016d5cb8 100644
--- a/drivers/usb/typec/ucsi/ucsi.h
+++ b/drivers/usb/typec/ucsi/ucsi.h
@@ -317,6 +317,9 @@ struct ucsi {
 #define EVENT_PENDING	0
 #define COMMAND_PENDING	1
 #define ACK_PENDING	2
+
+	unsigned long quirks;
+#define UCSI_NO_PARTNER_PDOS	BIT(0)	/* Don't read partner's PDOs */
 };
 
 #define UCSI_MAX_SVID		5
diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c
index db6e248f8208..53a7ede8556d 100644
--- a/drivers/usb/typec/ucsi/ucsi_glink.c
+++ b/drivers/usb/typec/ucsi/ucsi_glink.c
@@ -6,6 +6,7 @@
 #include <linux/auxiliary_bus.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/of_device.h>
 #include <linux/property.h>
 #include <linux/soc/qcom/pdr.h>
 #include <linux/usb/typec_mux.h>
@@ -228,7 +229,7 @@ static void pmic_glink_ucsi_notify(struct work_struct *work)
 
 	con_num = UCSI_CCI_CONNECTOR(cci);
 	if (con_num) {
-		if (con_num < PMIC_GLINK_MAX_PORTS &&
+		if (con_num <= PMIC_GLINK_MAX_PORTS &&
 		    ucsi->port_orientation[con_num - 1]) {
 			int orientation = gpiod_get_value(ucsi->port_orientation[con_num - 1]);
 
@@ -296,11 +297,19 @@ static void pmic_glink_ucsi_destroy(void *data)
 	mutex_unlock(&ucsi->lock);
 }
 
+static const struct of_device_id pmic_glink_ucsi_of_quirks[] = {
+	{ .compatible = "qcom,sc8180x-pmic-glink", .data = (void *)UCSI_NO_PARTNER_PDOS, },
+	{ .compatible = "qcom,sc8280xp-pmic-glink", .data = (void *)UCSI_NO_PARTNER_PDOS, },
+	{ .compatible = "qcom,sm8350-pmic-glink", .data = (void *)UCSI_NO_PARTNER_PDOS, },
+	{}
+};
+
 static int pmic_glink_ucsi_probe(struct auxiliary_device *adev,
 				 const struct auxiliary_device_id *id)
 {
 	struct pmic_glink_ucsi *ucsi;
 	struct device *dev = &adev->dev;
+	const struct of_device_id *match;
 	struct fwnode_handle *fwnode;
 	int ret;
 
@@ -327,6 +336,10 @@ static int pmic_glink_ucsi_probe(struct auxiliary_device *adev,
 	if (ret)
 		return ret;
 
+	match = of_match_device(pmic_glink_ucsi_of_quirks, dev->parent);
+	if (match)
+		ucsi->ucsi->quirks = (unsigned long)match->data;
+
 	ucsi_set_drvdata(ucsi->ucsi, ucsi);
 
 	device_for_each_child_node(dev, fwnode) {
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 12ac3397f39b..26ba7da6b410 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -2815,13 +2815,18 @@ static int setup_cvq_vring(struct mlx5_vdpa_dev *mvdev)
 	struct mlx5_control_vq *cvq = &mvdev->cvq;
 	int err = 0;
 
-	if (mvdev->actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ))
+	if (mvdev->actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ)) {
+		u16 idx = cvq->vring.last_avail_idx;
+
 		err = vringh_init_iotlb(&cvq->vring, mvdev->actual_features,
 					MLX5_CVQ_MAX_ENT, false,
 					(struct vring_desc *)(uintptr_t)cvq->desc_addr,
 					(struct vring_avail *)(uintptr_t)cvq->driver_addr,
 					(struct vring_used *)(uintptr_t)cvq->device_addr);
 
+		if (!err)
+			cvq->vring.last_avail_idx = cvq->vring.last_used_idx = idx;
+	}
 	return err;
 }
 
diff --git a/drivers/vdpa/pds/debugfs.c b/drivers/vdpa/pds/debugfs.c
index 9b04aad6ec35..c328e694f6e7 100644
--- a/drivers/vdpa/pds/debugfs.c
+++ b/drivers/vdpa/pds/debugfs.c
@@ -261,7 +261,7 @@ void pds_vdpa_debugfs_add_vdpadev(struct pds_vdpa_aux *vdpa_aux)
 	debugfs_create_file("config", 0400, vdpa_aux->dentry, vdpa_aux->pdsv, &config_fops);
 
 	for (i = 0; i < vdpa_aux->pdsv->num_vqs; i++) {
-		char name[8];
+		char name[16];
 
 		snprintf(name, sizeof(name), "vq%02d", i);
 		debugfs_create_file(name, 0400, vdpa_aux->dentry,
diff --git a/drivers/vdpa/pds/vdpa_dev.c b/drivers/vdpa/pds/vdpa_dev.c
index 52b2449182ad..25c0fe5ec3d5 100644
--- a/drivers/vdpa/pds/vdpa_dev.c
+++ b/drivers/vdpa/pds/vdpa_dev.c
@@ -318,9 +318,8 @@ static int pds_vdpa_set_driver_features(struct vdpa_device *vdpa_dev, u64 featur
 		return -EOPNOTSUPP;
 	}
 
-	pdsv->negotiated_features = nego_features;
-
 	driver_features = pds_vdpa_get_driver_features(vdpa_dev);
+	pdsv->negotiated_features = nego_features;
 	dev_dbg(dev, "%s: %#llx => %#llx\n",
 		__func__, driver_features, nego_features);
 
@@ -461,8 +460,10 @@ static void pds_vdpa_set_status(struct vdpa_device *vdpa_dev, u8 status)
 
 	pds_vdpa_cmd_set_status(pdsv, status);
 
-	/* Note: still working with FW on the need for this reset cmd */
 	if (status == 0) {
+		struct vdpa_callback null_cb = { };
+
+		pds_vdpa_set_config_cb(vdpa_dev, &null_cb);
 		pds_vdpa_cmd_reset(pdsv);
 
 		for (i = 0; i < pdsv->num_vqs; i++) {
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
index b3a3cb165795..b137f3679343 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
@@ -437,7 +437,7 @@ static int vdpasim_blk_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
 	if (blk->shared_backend) {
 		blk->buffer = shared_buffer;
 	} else {
-		blk->buffer = kvmalloc(VDPASIM_BLK_CAPACITY << SECTOR_SHIFT,
+		blk->buffer = kvzalloc(VDPASIM_BLK_CAPACITY << SECTOR_SHIFT,
 				       GFP_KERNEL);
 		if (!blk->buffer) {
 			ret = -ENOMEM;
@@ -495,7 +495,7 @@ static int __init vdpasim_blk_init(void)
 		goto parent_err;
 
 	if (shared_backend) {
-		shared_buffer = kvmalloc(VDPASIM_BLK_CAPACITY << SECTOR_SHIFT,
+		shared_buffer = kvzalloc(VDPASIM_BLK_CAPACITY << SECTOR_SHIFT,
 					 GFP_KERNEL);
 		if (!shared_buffer) {
 			ret = -ENOMEM;
diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
index 0ddd4b8abecb..1d24da79c399 100644
--- a/drivers/vdpa/vdpa_user/vduse_dev.c
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -493,7 +493,7 @@ static void vduse_vq_kick(struct vduse_virtqueue *vq)
 		goto unlock;
 
 	if (vq->kickfd)
-		eventfd_signal(vq->kickfd, 1);
+		eventfd_signal(vq->kickfd);
 	else
 		vq->kicked = true;
 unlock:
@@ -911,7 +911,7 @@ static int vduse_kickfd_setup(struct vduse_dev *dev,
 		eventfd_ctx_put(vq->kickfd);
 	vq->kickfd = ctx;
 	if (vq->ready && vq->kicked && vq->kickfd) {
-		eventfd_signal(vq->kickfd, 1);
+		eventfd_signal(vq->kickfd);
 		vq->kicked = false;
 	}
 	spin_unlock(&vq->kick_lock);
@@ -960,7 +960,7 @@ static bool vduse_vq_signal_irqfd(struct vduse_virtqueue *vq)
 
 	spin_lock_irq(&vq->irq_lock);
 	if (vq->ready && vq->cb.trigger) {
-		eventfd_signal(vq->cb.trigger, 1);
+		eventfd_signal(vq->cb.trigger);
 		signal = true;
 	}
 	spin_unlock_irq(&vq->irq_lock);
@@ -1157,7 +1157,7 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd,
 			fput(f);
 			break;
 		}
-		ret = receive_fd(f, perm_to_file_flags(entry.perm));
+		ret = receive_fd(f, NULL, perm_to_file_flags(entry.perm));
 		fput(f);
 		break;
 	}
diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c
index c51229fccbd6..d62fbfff20b8 100644
--- a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c
+++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c
@@ -54,7 +54,7 @@ static irqreturn_t vfio_fsl_mc_irq_handler(int irq_num, void *arg)
 {
 	struct vfio_fsl_mc_irq *mc_irq = (struct vfio_fsl_mc_irq *)arg;
 
-	eventfd_signal(mc_irq->trigger, 1);
+	eventfd_signal(mc_irq->trigger);
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/vfio/pci/pds/pci_drv.c b/drivers/vfio/pci/pds/pci_drv.c
index dd8c00c895a2..a34dda516629 100644
--- a/drivers/vfio/pci/pds/pci_drv.c
+++ b/drivers/vfio/pci/pds/pci_drv.c
@@ -55,10 +55,10 @@ static void pds_vfio_recovery(struct pds_vfio_pci_device *pds_vfio)
 	 * VFIO_DEVICE_STATE_RUNNING.
 	 */
 	if (deferred_reset_needed) {
-		spin_lock(&pds_vfio->reset_lock);
+		mutex_lock(&pds_vfio->reset_mutex);
 		pds_vfio->deferred_reset = true;
 		pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_ERROR;
-		spin_unlock(&pds_vfio->reset_lock);
+		mutex_unlock(&pds_vfio->reset_mutex);
 	}
 }
 
diff --git a/drivers/vfio/pci/pds/vfio_dev.c b/drivers/vfio/pci/pds/vfio_dev.c
index 649b18ee394b..4c351c59d05a 100644
--- a/drivers/vfio/pci/pds/vfio_dev.c
+++ b/drivers/vfio/pci/pds/vfio_dev.c
@@ -29,7 +29,7 @@ struct pds_vfio_pci_device *pds_vfio_pci_drvdata(struct pci_dev *pdev)
 void pds_vfio_state_mutex_unlock(struct pds_vfio_pci_device *pds_vfio)
 {
 again:
-	spin_lock(&pds_vfio->reset_lock);
+	mutex_lock(&pds_vfio->reset_mutex);
 	if (pds_vfio->deferred_reset) {
 		pds_vfio->deferred_reset = false;
 		if (pds_vfio->state == VFIO_DEVICE_STATE_ERROR) {
@@ -39,23 +39,23 @@ again:
 		}
 		pds_vfio->state = pds_vfio->deferred_reset_state;
 		pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_RUNNING;
-		spin_unlock(&pds_vfio->reset_lock);
+		mutex_unlock(&pds_vfio->reset_mutex);
 		goto again;
 	}
 	mutex_unlock(&pds_vfio->state_mutex);
-	spin_unlock(&pds_vfio->reset_lock);
+	mutex_unlock(&pds_vfio->reset_mutex);
 }
 
 void pds_vfio_reset(struct pds_vfio_pci_device *pds_vfio)
 {
-	spin_lock(&pds_vfio->reset_lock);
+	mutex_lock(&pds_vfio->reset_mutex);
 	pds_vfio->deferred_reset = true;
 	pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_RUNNING;
 	if (!mutex_trylock(&pds_vfio->state_mutex)) {
-		spin_unlock(&pds_vfio->reset_lock);
+		mutex_unlock(&pds_vfio->reset_mutex);
 		return;
 	}
-	spin_unlock(&pds_vfio->reset_lock);
+	mutex_unlock(&pds_vfio->reset_mutex);
 	pds_vfio_state_mutex_unlock(pds_vfio);
 }
 
@@ -155,6 +155,9 @@ static int pds_vfio_init_device(struct vfio_device *vdev)
 
 	pds_vfio->vf_id = vf_id;
 
+	mutex_init(&pds_vfio->state_mutex);
+	mutex_init(&pds_vfio->reset_mutex);
+
 	vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P;
 	vdev->mig_ops = &pds_vfio_lm_ops;
 	vdev->log_ops = &pds_vfio_log_ops;
@@ -168,6 +171,17 @@ static int pds_vfio_init_device(struct vfio_device *vdev)
 	return 0;
 }
 
+static void pds_vfio_release_device(struct vfio_device *vdev)
+{
+	struct pds_vfio_pci_device *pds_vfio =
+		container_of(vdev, struct pds_vfio_pci_device,
+			     vfio_coredev.vdev);
+
+	mutex_destroy(&pds_vfio->state_mutex);
+	mutex_destroy(&pds_vfio->reset_mutex);
+	vfio_pci_core_release_dev(vdev);
+}
+
 static int pds_vfio_open_device(struct vfio_device *vdev)
 {
 	struct pds_vfio_pci_device *pds_vfio =
@@ -179,7 +193,6 @@ static int pds_vfio_open_device(struct vfio_device *vdev)
 	if (err)
 		return err;
 
-	mutex_init(&pds_vfio->state_mutex);
 	pds_vfio->state = VFIO_DEVICE_STATE_RUNNING;
 	pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_RUNNING;
 
@@ -199,14 +212,13 @@ static void pds_vfio_close_device(struct vfio_device *vdev)
 	pds_vfio_put_save_file(pds_vfio);
 	pds_vfio_dirty_disable(pds_vfio, true);
 	mutex_unlock(&pds_vfio->state_mutex);
-	mutex_destroy(&pds_vfio->state_mutex);
 	vfio_pci_core_close_device(vdev);
 }
 
 static const struct vfio_device_ops pds_vfio_ops = {
 	.name = "pds-vfio",
 	.init = pds_vfio_init_device,
-	.release = vfio_pci_core_release_dev,
+	.release = pds_vfio_release_device,
 	.open_device = pds_vfio_open_device,
 	.close_device = pds_vfio_close_device,
 	.ioctl = vfio_pci_core_ioctl,
diff --git a/drivers/vfio/pci/pds/vfio_dev.h b/drivers/vfio/pci/pds/vfio_dev.h
index b8f2d667608f..e7b01080a1ec 100644
--- a/drivers/vfio/pci/pds/vfio_dev.h
+++ b/drivers/vfio/pci/pds/vfio_dev.h
@@ -18,7 +18,7 @@ struct pds_vfio_pci_device {
 	struct pds_vfio_dirty dirty;
 	struct mutex state_mutex; /* protect migration state */
 	enum vfio_device_mig_state state;
-	spinlock_t reset_lock; /* protect reset_done flow */
+	struct mutex reset_mutex; /* protect reset_done flow */
 	u8 deferred_reset;
 	enum vfio_device_mig_state deferred_reset_state;
 	struct notifier_block nb;
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 1929103ee59a..1cbc990d42e0 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -443,7 +443,7 @@ static int vfio_pci_core_runtime_resume(struct device *dev)
 	 */
 	down_write(&vdev->memory_lock);
 	if (vdev->pm_wake_eventfd_ctx) {
-		eventfd_signal(vdev->pm_wake_eventfd_ctx, 1);
+		eventfd_signal(vdev->pm_wake_eventfd_ctx);
 		__vfio_pci_runtime_pm_exit(vdev);
 	}
 	up_write(&vdev->memory_lock);
@@ -1883,7 +1883,7 @@ void vfio_pci_core_request(struct vfio_device *core_vdev, unsigned int count)
 			pci_notice_ratelimited(pdev,
 				"Relaying device request to user (#%u)\n",
 				count);
-		eventfd_signal(vdev->req_trigger, 1);
+		eventfd_signal(vdev->req_trigger);
 	} else if (count == 0) {
 		pci_warn(pdev,
 			"No device request channel registered, blocked until released by user\n");
@@ -2302,7 +2302,7 @@ pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev,
 	mutex_lock(&vdev->igate);
 
 	if (vdev->err_trigger)
-		eventfd_signal(vdev->err_trigger, 1);
+		eventfd_signal(vdev->err_trigger);
 
 	mutex_unlock(&vdev->igate);
 
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index cbb4bcbfbf83..237beac83809 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -94,7 +94,7 @@ static void vfio_send_intx_eventfd(void *opaque, void *unused)
 		ctx = vfio_irq_ctx_get(vdev, 0);
 		if (WARN_ON_ONCE(!ctx))
 			return;
-		eventfd_signal(ctx->trigger, 1);
+		eventfd_signal(ctx->trigger);
 	}
 }
 
@@ -342,7 +342,7 @@ static irqreturn_t vfio_msihandler(int irq, void *arg)
 {
 	struct eventfd_ctx *trigger = arg;
 
-	eventfd_signal(trigger, 1);
+	eventfd_signal(trigger);
 	return IRQ_HANDLED;
 }
 
@@ -689,11 +689,11 @@ static int vfio_pci_set_msi_trigger(struct vfio_pci_core_device *vdev,
 		if (!ctx)
 			continue;
 		if (flags & VFIO_IRQ_SET_DATA_NONE) {
-			eventfd_signal(ctx->trigger, 1);
+			eventfd_signal(ctx->trigger);
 		} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
 			uint8_t *bools = data;
 			if (bools[i - start])
-				eventfd_signal(ctx->trigger, 1);
+				eventfd_signal(ctx->trigger);
 		}
 	}
 	return 0;
@@ -707,7 +707,7 @@ static int vfio_pci_set_ctx_trigger_single(struct eventfd_ctx **ctx,
 	if (flags & VFIO_IRQ_SET_DATA_NONE) {
 		if (*ctx) {
 			if (count) {
-				eventfd_signal(*ctx, 1);
+				eventfd_signal(*ctx);
 			} else {
 				eventfd_ctx_put(*ctx);
 				*ctx = NULL;
@@ -722,7 +722,7 @@ static int vfio_pci_set_ctx_trigger_single(struct eventfd_ctx **ctx,
 
 		trigger = *(uint8_t *)data;
 		if (trigger && *ctx)
-			eventfd_signal(*ctx, 1);
+			eventfd_signal(*ctx);
 
 		return 0;
 	} else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
diff --git a/drivers/vfio/platform/vfio_platform_irq.c b/drivers/vfio/platform/vfio_platform_irq.c
index 665197caed89..61a1bfb68ac7 100644
--- a/drivers/vfio/platform/vfio_platform_irq.c
+++ b/drivers/vfio/platform/vfio_platform_irq.c
@@ -155,7 +155,7 @@ static irqreturn_t vfio_automasked_irq_handler(int irq, void *dev_id)
 	spin_unlock_irqrestore(&irq_ctx->lock, flags);
 
 	if (ret == IRQ_HANDLED)
-		eventfd_signal(irq_ctx->trigger, 1);
+		eventfd_signal(irq_ctx->trigger);
 
 	return ret;
 }
@@ -164,7 +164,7 @@ static irqreturn_t vfio_irq_handler(int irq, void *dev_id)
 {
 	struct vfio_platform_irq *irq_ctx = dev_id;
 
-	eventfd_signal(irq_ctx->trigger, 1);
+	eventfd_signal(irq_ctx->trigger);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 30df5c58db73..173beda74b38 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -178,7 +178,7 @@ static irqreturn_t vhost_vdpa_virtqueue_cb(void *private)
 	struct eventfd_ctx *call_ctx = vq->call_ctx.ctx;
 
 	if (call_ctx)
-		eventfd_signal(call_ctx, 1);
+		eventfd_signal(call_ctx);
 
 	return IRQ_HANDLED;
 }
@@ -189,7 +189,7 @@ static irqreturn_t vhost_vdpa_config_cb(void *private)
 	struct eventfd_ctx *config_ctx = v->config_ctx;
 
 	if (config_ctx)
-		eventfd_signal(config_ctx, 1);
+		eventfd_signal(config_ctx);
 
 	return IRQ_HANDLED;
 }
@@ -1582,7 +1582,6 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)
 
 err:
 	put_device(&v->dev);
-	ida_simple_remove(&vhost_vdpa_ida, v->minor);
 	return r;
 }
 
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index e0c181ad17e3..045f666b4f12 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -2248,7 +2248,7 @@ int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
 		len -= l;
 		if (!len) {
 			if (vq->log_ctx)
-				eventfd_signal(vq->log_ctx, 1);
+				eventfd_signal(vq->log_ctx);
 			return 0;
 		}
 	}
@@ -2271,7 +2271,7 @@ static int vhost_update_used_flags(struct vhost_virtqueue *vq)
 		log_used(vq, (used - (void __user *)vq->used),
 			 sizeof vq->used->flags);
 		if (vq->log_ctx)
-			eventfd_signal(vq->log_ctx, 1);
+			eventfd_signal(vq->log_ctx);
 	}
 	return 0;
 }
@@ -2289,7 +2289,7 @@ static int vhost_update_avail_event(struct vhost_virtqueue *vq)
 		log_used(vq, (used - (void __user *)vq->used),
 			 sizeof *vhost_avail_event(vq));
 		if (vq->log_ctx)
-			eventfd_signal(vq->log_ctx, 1);
+			eventfd_signal(vq->log_ctx);
 	}
 	return 0;
 }
@@ -2715,7 +2715,7 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
 		log_used(vq, offsetof(struct vring_used, idx),
 			 sizeof vq->used->idx);
 		if (vq->log_ctx)
-			eventfd_signal(vq->log_ctx, 1);
+			eventfd_signal(vq->log_ctx);
 	}
 	return r;
 }
@@ -2763,7 +2763,7 @@ void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
 	/* Signal the Guest tell them we used something up. */
 	if (vq->call_ctx.ctx && vhost_notify(dev, vq))
-		eventfd_signal(vq->call_ctx.ctx, 1);
+		eventfd_signal(vq->call_ctx.ctx);
 }
 EXPORT_SYMBOL_GPL(vhost_signal);
 
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index f60d5f7bef94..9e942fcda5c3 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -249,7 +249,7 @@ void vhost_iotlb_map_free(struct vhost_iotlb *iotlb,
 #define vq_err(vq, fmt, ...) do {                                  \
 		pr_debug(pr_fmt(fmt), ##__VA_ARGS__);       \
 		if ((vq)->error_ctx)                               \
-				eventfd_signal((vq)->error_ctx, 1);\
+				eventfd_signal((vq)->error_ctx);\
 	} while (0)
 
 enum {
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index f75731396b7e..ec20ecff85c7 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -449,6 +449,7 @@ static struct virtio_transport vhost_transport = {
 		.notify_send_pre_enqueue  = virtio_transport_notify_send_pre_enqueue,
 		.notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
 		.notify_buffer_size       = virtio_transport_notify_buffer_size,
+		.notify_set_rcvlowat      = virtio_transport_notify_set_rcvlowat,
 
 		.read_skb = virtio_transport_read_skb,
 	},
diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c
index a80939fe2ee6..6a29d2594b91 100644
--- a/drivers/video/fbdev/hyperv_fb.c
+++ b/drivers/video/fbdev/hyperv_fb.c
@@ -927,8 +927,8 @@ static phys_addr_t hvfb_get_phymem(struct hv_device *hdev,
 	if (request_size == 0)
 		return -1;
 
-	if (order <= MAX_ORDER) {
-		/* Call alloc_pages if the size is less than 2^MAX_ORDER */
+	if (order <= MAX_PAGE_ORDER) {
+		/* Call alloc_pages if the size is less than 2^MAX_PAGE_ORDER */
 		page = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
 		if (!page)
 			return -1;
@@ -958,7 +958,7 @@ static void hvfb_release_phymem(struct hv_device *hdev,
 {
 	unsigned int order = get_order(size);
 
-	if (order <= MAX_ORDER)
+	if (order <= MAX_PAGE_ORDER)
 		__free_pages(pfn_to_page(paddr >> PAGE_SHIFT), order);
 	else
 		dma_free_coherent(&hdev->device,
diff --git a/drivers/video/fbdev/vermilion/vermilion.c b/drivers/video/fbdev/vermilion/vermilion.c
index 840ead69654b..a32e5b2924c9 100644
--- a/drivers/video/fbdev/vermilion/vermilion.c
+++ b/drivers/video/fbdev/vermilion/vermilion.c
@@ -197,7 +197,7 @@ static int vmlfb_alloc_vram(struct vml_info *vinfo,
 		va = &vinfo->vram[i];
 		order = 0;
 
-		while (requested > (PAGE_SIZE << order) && order <= MAX_ORDER)
+		while (requested > (PAGE_SIZE << order) && order <= MAX_PAGE_ORDER)
 			order++;
 
 		err = vmlfb_alloc_vram_area(va, order, 0);
diff --git a/drivers/virt/acrn/ioeventfd.c b/drivers/virt/acrn/ioeventfd.c
index ac4037e9f947..4e845c6ca0b5 100644
--- a/drivers/virt/acrn/ioeventfd.c
+++ b/drivers/virt/acrn/ioeventfd.c
@@ -223,7 +223,7 @@ static int acrn_ioeventfd_handler(struct acrn_ioreq_client *client,
 	mutex_lock(&client->vm->ioeventfds_lock);
 	p = hsm_ioeventfd_match(client->vm, addr, val, size, req->type);
 	if (p)
-		eventfd_signal(p->eventfd, 1);
+		eventfd_signal(p->eventfd);
 	mutex_unlock(&client->vm->ioeventfds_lock);
 
 	return 0;
diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c
index bc564adcf499..87f241825bc3 100644
--- a/drivers/virt/coco/sev-guest/sev-guest.c
+++ b/drivers/virt/coco/sev-guest/sev-guest.c
@@ -994,7 +994,7 @@ e_unmap:
 	return ret;
 }
 
-static int __exit sev_guest_remove(struct platform_device *pdev)
+static void __exit sev_guest_remove(struct platform_device *pdev)
 {
 	struct snp_guest_dev *snp_dev = platform_get_drvdata(pdev);
 
@@ -1003,8 +1003,6 @@ static int __exit sev_guest_remove(struct platform_device *pdev)
 	free_shared_pages(snp_dev->request, sizeof(struct snp_guest_msg));
 	deinit_crypto(snp_dev->crypto);
 	misc_deregister(&snp_dev->misc);
-
-	return 0;
 }
 
 /*
@@ -1013,7 +1011,7 @@ static int __exit sev_guest_remove(struct platform_device *pdev)
  * with the SEV-SNP support, it is named "sev-guest".
  */
 static struct platform_driver sev_guest_driver = {
-	.remove		= __exit_p(sev_guest_remove),
+	.remove_new	= __exit_p(sev_guest_remove),
 	.driver		= {
 		.name = "sev-guest",
 	},
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 1fe93e93f5bc..59cdc0292dce 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -33,7 +33,7 @@
 #define VIRTIO_BALLOON_FREE_PAGE_ALLOC_FLAG (__GFP_NORETRY | __GFP_NOWARN | \
 					     __GFP_NOMEMALLOC)
 /* The order of free page blocks to report to host */
-#define VIRTIO_BALLOON_HINT_BLOCK_ORDER MAX_ORDER
+#define VIRTIO_BALLOON_HINT_BLOCK_ORDER MAX_PAGE_ORDER
 /* The size of a free page block in bytes */
 #define VIRTIO_BALLOON_HINT_BLOCK_BYTES \
 	(1 << (VIRTIO_BALLOON_HINT_BLOCK_ORDER + PAGE_SHIFT))
diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index fa5226c198cc..8e3223294442 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -1154,13 +1154,13 @@ static void virtio_mem_clear_fake_offline(unsigned long pfn,
  */
 static void virtio_mem_fake_online(unsigned long pfn, unsigned long nr_pages)
 {
-	unsigned long order = MAX_ORDER;
+	unsigned long order = MAX_PAGE_ORDER;
 	unsigned long i;
 
 	/*
 	 * We might get called for ranges that don't cover properly aligned
-	 * MAX_ORDER pages; however, we can only online properly aligned
-	 * pages with an order of MAX_ORDER at maximum.
+	 * MAX_PAGE_ORDER pages; however, we can only online properly aligned
+	 * pages with an order of MAX_PAGE_ORDER at maximum.
 	 */
 	while (!IS_ALIGNED(pfn | nr_pages, 1 << order))
 		order--;
@@ -1280,7 +1280,7 @@ static void virtio_mem_online_page(struct virtio_mem *vm,
 	bool do_online;
 
 	/*
-	 * We can get called with any order up to MAX_ORDER. If our subblock
+	 * We can get called with any order up to MAX_PAGE_ORDER. If our subblock
 	 * size is smaller than that and we have a mixture of plugged and
 	 * unplugged subblocks within such a page, we have to process in
 	 * smaller granularity. In that case we'll adjust the order exactly once
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index c2524a7207cf..7a5593997e0e 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -242,7 +242,7 @@ void vp_del_vqs(struct virtio_device *vdev)
 			if (v != VIRTIO_MSI_NO_VECTOR) {
 				int irq = pci_irq_vector(vp_dev->pci_dev, v);
 
-				irq_set_affinity_hint(irq, NULL);
+				irq_update_affinity_hint(irq, NULL);
 				free_irq(irq, vq);
 			}
 		}
@@ -443,10 +443,10 @@ int vp_set_vq_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask)
 		mask = vp_dev->msix_affinity_masks[info->msix_vector];
 		irq = pci_irq_vector(vp_dev->pci_dev, info->msix_vector);
 		if (!cpu_mask)
-			irq_set_affinity_hint(irq, NULL);
+			irq_update_affinity_hint(irq, NULL);
 		else {
 			cpumask_copy(mask, cpu_mask);
-			irq_set_affinity_hint(irq, mask);
+			irq_set_affinity_and_hint(irq, mask);
 		}
 	}
 	return 0;
diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c
index e2a1fe7bb66c..7de8b1ebabac 100644
--- a/drivers/virtio/virtio_pci_modern_dev.c
+++ b/drivers/virtio/virtio_pci_modern_dev.c
@@ -294,9 +294,10 @@ int vp_modern_probe(struct virtio_pci_modern_device *mdev)
 
 	err = -EINVAL;
 	mdev->common = vp_modern_map_capability(mdev, common,
-				      sizeof(struct virtio_pci_common_cfg), 4,
-				      0, sizeof(struct virtio_pci_modern_common_cfg),
-				      &mdev->common_len, NULL);
+			      sizeof(struct virtio_pci_common_cfg), 4, 0,
+			      offsetofend(struct virtio_pci_modern_common_cfg,
+					  queue_reset),
+			      &mdev->common_len, NULL);
 	if (!mdev->common)
 		goto err_map_common;
 	mdev->isr = vp_modern_map_capability(mdev, isr, sizeof(u8), 1,
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 51d8f3299c10..49299b1f9ec7 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -3219,8 +3219,7 @@ void virtqueue_dma_sync_single_range_for_cpu(struct virtqueue *_vq,
 	if (!vq->use_dma_api)
 		return;
 
-	dma_sync_single_range_for_cpu(dev, addr, offset, size,
-				      DMA_BIDIRECTIONAL);
+	dma_sync_single_range_for_cpu(dev, addr, offset, size, dir);
 }
 EXPORT_SYMBOL_GPL(virtqueue_dma_sync_single_range_for_cpu);
 
@@ -3246,8 +3245,7 @@ void virtqueue_dma_sync_single_range_for_device(struct virtqueue *_vq,
 	if (!vq->use_dma_api)
 		return;
 
-	dma_sync_single_range_for_device(dev, addr, offset, size,
-					 DMA_BIDIRECTIONAL);
+	dma_sync_single_range_for_device(dev, addr, offset, size, dir);
 }
 EXPORT_SYMBOL_GPL(virtqueue_dma_sync_single_range_for_device);
 
diff --git a/drivers/watchdog/s3c2410_wdt.c b/drivers/watchdog/s3c2410_wdt.c
index 0b4bd883ff28..349d30462c8c 100644
--- a/drivers/watchdog/s3c2410_wdt.c
+++ b/drivers/watchdog/s3c2410_wdt.c
@@ -9,6 +9,7 @@
  *     (c) Copyright 1996 Alan Cox <alan@lxorguk.ukuu.org.uk>
  */
 
+#include <linux/bits.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -34,9 +35,10 @@
 
 #define S3C2410_WTCNT_MAXCNT	0xffff
 
-#define S3C2410_WTCON_RSTEN	(1 << 0)
-#define S3C2410_WTCON_INTEN	(1 << 2)
-#define S3C2410_WTCON_ENABLE	(1 << 5)
+#define S3C2410_WTCON_RSTEN		BIT(0)
+#define S3C2410_WTCON_INTEN		BIT(2)
+#define S3C2410_WTCON_ENABLE		BIT(5)
+#define S3C2410_WTCON_DBGACK_MASK	BIT(16)
 
 #define S3C2410_WTCON_DIV16	(0 << 3)
 #define S3C2410_WTCON_DIV32	(1 << 3)
@@ -67,6 +69,13 @@
 #define EXYNOSAUTOV9_CLUSTER0_WDTRESET_BIT	25
 #define EXYNOSAUTOV9_CLUSTER1_WDTRESET_BIT	24
 
+#define GS_CLUSTER0_NONCPU_OUT			0x1220
+#define GS_CLUSTER1_NONCPU_OUT			0x1420
+#define GS_CLUSTER0_NONCPU_INT_EN		0x1244
+#define GS_CLUSTER1_NONCPU_INT_EN		0x1444
+#define GS_CLUSTER2_NONCPU_INT_EN		0x1644
+#define GS_RST_STAT_REG_OFFSET			0x3B44
+
 /**
  * DOC: Quirk flags for different Samsung watchdog IP-cores
  *
@@ -100,12 +109,17 @@
  * %QUIRK_HAS_PMU_CNT_EN: PMU block has some register (e.g. CLUSTERx_NONCPU_OUT)
  * with "watchdog counter enable" bit. That bit should be set to make watchdog
  * counter running.
+ *
+ * %QUIRK_HAS_DBGACK_BIT: WTCON register has DBGACK_MASK bit. Setting the
+ * DBGACK_MASK bit disables the watchdog outputs when the SoC is in debug mode.
+ * Debug mode is determined by the DBGACK CPU signal.
  */
-#define QUIRK_HAS_WTCLRINT_REG			(1 << 0)
-#define QUIRK_HAS_PMU_MASK_RESET		(1 << 1)
-#define QUIRK_HAS_PMU_RST_STAT			(1 << 2)
-#define QUIRK_HAS_PMU_AUTO_DISABLE		(1 << 3)
-#define QUIRK_HAS_PMU_CNT_EN			(1 << 4)
+#define QUIRK_HAS_WTCLRINT_REG			BIT(0)
+#define QUIRK_HAS_PMU_MASK_RESET		BIT(1)
+#define QUIRK_HAS_PMU_RST_STAT			BIT(2)
+#define QUIRK_HAS_PMU_AUTO_DISABLE		BIT(3)
+#define QUIRK_HAS_PMU_CNT_EN			BIT(4)
+#define QUIRK_HAS_DBGACK_BIT			BIT(5)
 
 /* These quirks require that we have a PMU register map */
 #define QUIRKS_HAVE_PMUREG \
@@ -263,7 +277,35 @@ static const struct s3c2410_wdt_variant drv_data_exynosautov9_cl1 = {
 		  QUIRK_HAS_PMU_RST_STAT | QUIRK_HAS_PMU_CNT_EN,
 };
 
+static const struct s3c2410_wdt_variant drv_data_gs101_cl0 = {
+	.mask_reset_reg = GS_CLUSTER0_NONCPU_INT_EN,
+	.mask_bit = 2,
+	.mask_reset_inv = true,
+	.rst_stat_reg = GS_RST_STAT_REG_OFFSET,
+	.rst_stat_bit = 0,
+	.cnt_en_reg = GS_CLUSTER0_NONCPU_OUT,
+	.cnt_en_bit = 8,
+	.quirks = QUIRK_HAS_PMU_RST_STAT | QUIRK_HAS_PMU_MASK_RESET |
+		  QUIRK_HAS_PMU_CNT_EN | QUIRK_HAS_WTCLRINT_REG |
+		  QUIRK_HAS_DBGACK_BIT,
+};
+
+static const struct s3c2410_wdt_variant drv_data_gs101_cl1 = {
+	.mask_reset_reg = GS_CLUSTER1_NONCPU_INT_EN,
+	.mask_bit = 2,
+	.mask_reset_inv = true,
+	.rst_stat_reg = GS_RST_STAT_REG_OFFSET,
+	.rst_stat_bit = 1,
+	.cnt_en_reg = GS_CLUSTER1_NONCPU_OUT,
+	.cnt_en_bit = 7,
+	.quirks = QUIRK_HAS_PMU_RST_STAT | QUIRK_HAS_PMU_MASK_RESET |
+		  QUIRK_HAS_PMU_CNT_EN | QUIRK_HAS_WTCLRINT_REG |
+		  QUIRK_HAS_DBGACK_BIT,
+};
+
 static const struct of_device_id s3c2410_wdt_match[] = {
+	{ .compatible = "google,gs101-wdt",
+	  .data = &drv_data_gs101_cl0 },
 	{ .compatible = "samsung,s3c2410-wdt",
 	  .data = &drv_data_s3c2410 },
 	{ .compatible = "samsung,s3c6410-wdt",
@@ -375,6 +417,19 @@ static int s3c2410wdt_enable(struct s3c2410_wdt *wdt, bool en)
 	return 0;
 }
 
+/* Disable watchdog outputs if CPU is in debug mode */
+static void s3c2410wdt_mask_dbgack(struct s3c2410_wdt *wdt)
+{
+	unsigned long wtcon;
+
+	if (!(wdt->drv_data->quirks & QUIRK_HAS_DBGACK_BIT))
+		return;
+
+	wtcon = readl(wdt->reg_base + S3C2410_WTCON);
+	wtcon |= S3C2410_WTCON_DBGACK_MASK;
+	writel(wtcon, wdt->reg_base + S3C2410_WTCON);
+}
+
 static int s3c2410wdt_keepalive(struct watchdog_device *wdd)
 {
 	struct s3c2410_wdt *wdt = watchdog_get_drvdata(wdd);
@@ -587,7 +642,8 @@ s3c2410_get_wdt_drv_data(struct platform_device *pdev, struct s3c2410_wdt *wdt)
 #ifdef CONFIG_OF
 	/* Choose Exynos850/ExynosAutov9 driver data w.r.t. cluster index */
 	if (variant == &drv_data_exynos850_cl0 ||
-	    variant == &drv_data_exynosautov9_cl0) {
+	    variant == &drv_data_exynosautov9_cl0 ||
+	    variant == &drv_data_gs101_cl0) {
 		u32 index;
 		int err;
 
@@ -600,9 +656,12 @@ s3c2410_get_wdt_drv_data(struct platform_device *pdev, struct s3c2410_wdt *wdt)
 		case 0:
 			break;
 		case 1:
-			variant = (variant == &drv_data_exynos850_cl0) ?
-				&drv_data_exynos850_cl1 :
-				&drv_data_exynosautov9_cl1;
+			if (variant == &drv_data_exynos850_cl0)
+				variant = &drv_data_exynos850_cl1;
+			else if (variant == &drv_data_exynosautov9_cl0)
+				variant = &drv_data_exynosautov9_cl1;
+			else if (variant == &drv_data_gs101_cl0)
+				variant = &drv_data_gs101_cl1;
 			break;
 		default:
 			return dev_err_probe(dev, -EINVAL, "wrong cluster index: %u\n", index);
@@ -700,6 +759,8 @@ static int s3c2410wdt_probe(struct platform_device *pdev)
 	wdt->wdt_device.bootstatus = s3c2410wdt_get_bootstatus(wdt);
 	wdt->wdt_device.parent = dev;
 
+	s3c2410wdt_mask_dbgack(wdt);
+
 	/*
 	 * If "tmr_atboot" param is non-zero, start the watchdog right now. Also
 	 * set WDOG_HW_RUNNING bit, so that watchdog core can kick the watchdog.
diff --git a/drivers/xen/events/events_2l.c b/drivers/xen/events/events_2l.c
index b8f2f971c2f0..e3585330cf98 100644
--- a/drivers/xen/events/events_2l.c
+++ b/drivers/xen/events/events_2l.c
@@ -171,11 +171,11 @@ static void evtchn_2l_handle_events(unsigned cpu, struct evtchn_loop_ctrl *ctrl)
 	int i;
 	struct shared_info *s = HYPERVISOR_shared_info;
 	struct vcpu_info *vcpu_info = __this_cpu_read(xen_vcpu);
+	evtchn_port_t evtchn;
 
 	/* Timer interrupt has highest priority. */
-	irq = irq_from_virq(cpu, VIRQ_TIMER);
+	irq = irq_evtchn_from_virq(cpu, VIRQ_TIMER, &evtchn);
 	if (irq != -1) {
-		evtchn_port_t evtchn = evtchn_from_irq(irq);
 		word_idx = evtchn / BITS_PER_LONG;
 		bit_idx = evtchn % BITS_PER_LONG;
 		if (active_evtchns(cpu, s, word_idx) & (1ULL << bit_idx))
@@ -328,9 +328,9 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id)
 	for (i = 0; i < EVTCHN_2L_NR_CHANNELS; i++) {
 		if (sync_test_bit(i, BM(sh->evtchn_pending))) {
 			int word_idx = i / BITS_PER_EVTCHN_WORD;
-			printk("  %d: event %d -> irq %d%s%s%s\n",
+			printk("  %d: event %d -> irq %u%s%s%s\n",
 			       cpu_from_evtchn(i), i,
-			       get_evtchn_to_irq(i),
+			       irq_from_evtchn(i),
 			       sync_test_bit(word_idx, BM(&v->evtchn_pending_sel))
 			       ? "" : " l2-clear",
 			       !sync_test_bit(i, BM(sh->evtchn_mask))
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 6de6b084ea60..b8cfea7812d6 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -164,6 +164,8 @@ static DEFINE_PER_CPU(int [NR_VIRQS], virq_to_irq) = {[0 ... NR_VIRQS-1] = -1};
 
 /* IRQ <-> IPI mapping */
 static DEFINE_PER_CPU(int [XEN_NR_IPIS], ipi_to_irq) = {[0 ... XEN_NR_IPIS-1] = -1};
+/* Cache for IPI event channels - needed for hot cpu unplug (avoid RCU usage). */
+static DEFINE_PER_CPU(evtchn_port_t [XEN_NR_IPIS], ipi_to_evtchn) = {[0 ... XEN_NR_IPIS-1] = 0};
 
 /* Event channel distribution data */
 static atomic_t channels_on_cpu[NR_CPUS];
@@ -172,7 +174,7 @@ static int **evtchn_to_irq;
 #ifdef CONFIG_X86
 static unsigned long *pirq_eoi_map;
 #endif
-static bool (*pirq_needs_eoi)(unsigned irq);
+static bool (*pirq_needs_eoi)(struct irq_info *info);
 
 #define EVTCHN_ROW(e)  (e / (PAGE_SIZE/sizeof(**evtchn_to_irq)))
 #define EVTCHN_COL(e)  (e % (PAGE_SIZE/sizeof(**evtchn_to_irq)))
@@ -188,7 +190,6 @@ static struct irq_chip xen_lateeoi_chip;
 static struct irq_chip xen_percpu_chip;
 static struct irq_chip xen_pirq_chip;
 static void enable_dynirq(struct irq_data *data);
-static void disable_dynirq(struct irq_data *data);
 
 static DEFINE_PER_CPU(unsigned int, irq_epoch);
 
@@ -246,15 +247,6 @@ static int set_evtchn_to_irq(evtchn_port_t evtchn, unsigned int irq)
 	return 0;
 }
 
-int get_evtchn_to_irq(evtchn_port_t evtchn)
-{
-	if (evtchn >= xen_evtchn_max_channels())
-		return -1;
-	if (evtchn_to_irq[EVTCHN_ROW(evtchn)] == NULL)
-		return -1;
-	return READ_ONCE(evtchn_to_irq[EVTCHN_ROW(evtchn)][EVTCHN_COL(evtchn)]);
-}
-
 /* Get info for IRQ */
 static struct irq_info *info_for_irq(unsigned irq)
 {
@@ -272,6 +264,19 @@ static void set_info_for_irq(unsigned int irq, struct irq_info *info)
 		irq_set_chip_data(irq, info);
 }
 
+static struct irq_info *evtchn_to_info(evtchn_port_t evtchn)
+{
+	int irq;
+
+	if (evtchn >= xen_evtchn_max_channels())
+		return NULL;
+	if (evtchn_to_irq[EVTCHN_ROW(evtchn)] == NULL)
+		return NULL;
+	irq = READ_ONCE(evtchn_to_irq[EVTCHN_ROW(evtchn)][EVTCHN_COL(evtchn)]);
+
+	return (irq < 0) ? NULL : info_for_irq(irq);
+}
+
 /* Per CPU channel accounting */
 static void channels_on_cpu_dec(struct irq_info *info)
 {
@@ -298,6 +303,13 @@ static void channels_on_cpu_inc(struct irq_info *info)
 	info->is_accounted = 1;
 }
 
+static void xen_irq_free_desc(unsigned int irq)
+{
+	/* Legacy IRQ descriptors are managed by the arch. */
+	if (irq >= nr_legacy_irqs())
+		irq_free_desc(irq);
+}
+
 static void delayed_free_irq(struct work_struct *work)
 {
 	struct irq_info *info = container_of(to_rcu_work(work), struct irq_info,
@@ -309,14 +321,11 @@ static void delayed_free_irq(struct work_struct *work)
 
 	kfree(info);
 
-	/* Legacy IRQ descriptors are managed by the arch. */
-	if (irq >= nr_legacy_irqs())
-		irq_free_desc(irq);
+	xen_irq_free_desc(irq);
 }
 
 /* Constructors for packed IRQ information. */
 static int xen_irq_info_common_setup(struct irq_info *info,
-				     unsigned irq,
 				     enum xen_irq_type type,
 				     evtchn_port_t evtchn,
 				     unsigned short cpu)
@@ -326,29 +335,27 @@ static int xen_irq_info_common_setup(struct irq_info *info,
 	BUG_ON(info->type != IRQT_UNBOUND && info->type != type);
 
 	info->type = type;
-	info->irq = irq;
 	info->evtchn = evtchn;
 	info->cpu = cpu;
 	info->mask_reason = EVT_MASK_REASON_EXPLICIT;
 	raw_spin_lock_init(&info->lock);
 
-	ret = set_evtchn_to_irq(evtchn, irq);
+	ret = set_evtchn_to_irq(evtchn, info->irq);
 	if (ret < 0)
 		return ret;
 
-	irq_clear_status_flags(irq, IRQ_NOREQUEST|IRQ_NOAUTOEN);
+	irq_clear_status_flags(info->irq, IRQ_NOREQUEST | IRQ_NOAUTOEN);
 
 	return xen_evtchn_port_setup(evtchn);
 }
 
-static int xen_irq_info_evtchn_setup(unsigned irq,
+static int xen_irq_info_evtchn_setup(struct irq_info *info,
 				     evtchn_port_t evtchn,
 				     struct xenbus_device *dev)
 {
-	struct irq_info *info = info_for_irq(irq);
 	int ret;
 
-	ret = xen_irq_info_common_setup(info, irq, IRQT_EVTCHN, evtchn, 0);
+	ret = xen_irq_info_common_setup(info, IRQT_EVTCHN, evtchn, 0);
 	info->u.interdomain = dev;
 	if (dev)
 		atomic_inc(&dev->event_channels);
@@ -356,49 +363,37 @@ static int xen_irq_info_evtchn_setup(unsigned irq,
 	return ret;
 }
 
-static int xen_irq_info_ipi_setup(unsigned cpu,
-				  unsigned irq,
-				  evtchn_port_t evtchn,
-				  enum ipi_vector ipi)
+static int xen_irq_info_ipi_setup(struct irq_info *info, unsigned int cpu,
+				  evtchn_port_t evtchn, enum ipi_vector ipi)
 {
-	struct irq_info *info = info_for_irq(irq);
-
 	info->u.ipi = ipi;
 
-	per_cpu(ipi_to_irq, cpu)[ipi] = irq;
+	per_cpu(ipi_to_irq, cpu)[ipi] = info->irq;
+	per_cpu(ipi_to_evtchn, cpu)[ipi] = evtchn;
 
-	return xen_irq_info_common_setup(info, irq, IRQT_IPI, evtchn, 0);
+	return xen_irq_info_common_setup(info, IRQT_IPI, evtchn, 0);
 }
 
-static int xen_irq_info_virq_setup(unsigned cpu,
-				   unsigned irq,
-				   evtchn_port_t evtchn,
-				   unsigned virq)
+static int xen_irq_info_virq_setup(struct irq_info *info, unsigned int cpu,
+				   evtchn_port_t evtchn, unsigned int virq)
 {
-	struct irq_info *info = info_for_irq(irq);
-
 	info->u.virq = virq;
 
-	per_cpu(virq_to_irq, cpu)[virq] = irq;
+	per_cpu(virq_to_irq, cpu)[virq] = info->irq;
 
-	return xen_irq_info_common_setup(info, irq, IRQT_VIRQ, evtchn, 0);
+	return xen_irq_info_common_setup(info, IRQT_VIRQ, evtchn, 0);
 }
 
-static int xen_irq_info_pirq_setup(unsigned irq,
-				   evtchn_port_t evtchn,
-				   unsigned pirq,
-				   unsigned gsi,
-				   uint16_t domid,
-				   unsigned char flags)
+static int xen_irq_info_pirq_setup(struct irq_info *info, evtchn_port_t evtchn,
+				   unsigned int pirq, unsigned int gsi,
+				   uint16_t domid, unsigned char flags)
 {
-	struct irq_info *info = info_for_irq(irq);
-
 	info->u.pirq.pirq = pirq;
 	info->u.pirq.gsi = gsi;
 	info->u.pirq.domid = domid;
 	info->u.pirq.flags = flags;
 
-	return xen_irq_info_common_setup(info, irq, IRQT_PIRQ, evtchn, 0);
+	return xen_irq_info_common_setup(info, IRQT_PIRQ, evtchn, 0);
 }
 
 static void xen_irq_info_cleanup(struct irq_info *info)
@@ -412,7 +407,7 @@ static void xen_irq_info_cleanup(struct irq_info *info)
 /*
  * Accessors for packed IRQ information.
  */
-evtchn_port_t evtchn_from_irq(unsigned irq)
+static evtchn_port_t evtchn_from_irq(unsigned int irq)
 {
 	const struct irq_info *info = NULL;
 
@@ -426,64 +421,51 @@ evtchn_port_t evtchn_from_irq(unsigned irq)
 
 unsigned int irq_from_evtchn(evtchn_port_t evtchn)
 {
-	return get_evtchn_to_irq(evtchn);
+	struct irq_info *info = evtchn_to_info(evtchn);
+
+	return info ? info->irq : -1;
 }
 EXPORT_SYMBOL_GPL(irq_from_evtchn);
 
-int irq_from_virq(unsigned int cpu, unsigned int virq)
+int irq_evtchn_from_virq(unsigned int cpu, unsigned int virq,
+			 evtchn_port_t *evtchn)
 {
-	return per_cpu(virq_to_irq, cpu)[virq];
+	int irq = per_cpu(virq_to_irq, cpu)[virq];
+
+	*evtchn = evtchn_from_irq(irq);
+
+	return irq;
 }
 
-static enum ipi_vector ipi_from_irq(unsigned irq)
+static enum ipi_vector ipi_from_irq(struct irq_info *info)
 {
-	struct irq_info *info = info_for_irq(irq);
-
 	BUG_ON(info == NULL);
 	BUG_ON(info->type != IRQT_IPI);
 
 	return info->u.ipi;
 }
 
-static unsigned virq_from_irq(unsigned irq)
+static unsigned int virq_from_irq(struct irq_info *info)
 {
-	struct irq_info *info = info_for_irq(irq);
-
 	BUG_ON(info == NULL);
 	BUG_ON(info->type != IRQT_VIRQ);
 
 	return info->u.virq;
 }
 
-static unsigned pirq_from_irq(unsigned irq)
+static unsigned int pirq_from_irq(struct irq_info *info)
 {
-	struct irq_info *info = info_for_irq(irq);
-
 	BUG_ON(info == NULL);
 	BUG_ON(info->type != IRQT_PIRQ);
 
 	return info->u.pirq.pirq;
 }
 
-static enum xen_irq_type type_from_irq(unsigned irq)
-{
-	return info_for_irq(irq)->type;
-}
-
-static unsigned cpu_from_irq(unsigned irq)
-{
-	return info_for_irq(irq)->cpu;
-}
-
 unsigned int cpu_from_evtchn(evtchn_port_t evtchn)
 {
-	int irq = get_evtchn_to_irq(evtchn);
-	unsigned ret = 0;
-
-	if (irq != -1)
-		ret = cpu_from_irq(irq);
+	struct irq_info *info = evtchn_to_info(evtchn);
 
-	return ret;
+	return info ? info->cpu : 0;
 }
 
 static void do_mask(struct irq_info *info, u8 reason)
@@ -515,36 +497,30 @@ static void do_unmask(struct irq_info *info, u8 reason)
 }
 
 #ifdef CONFIG_X86
-static bool pirq_check_eoi_map(unsigned irq)
+static bool pirq_check_eoi_map(struct irq_info *info)
 {
-	return test_bit(pirq_from_irq(irq), pirq_eoi_map);
+	return test_bit(pirq_from_irq(info), pirq_eoi_map);
 }
 #endif
 
-static bool pirq_needs_eoi_flag(unsigned irq)
+static bool pirq_needs_eoi_flag(struct irq_info *info)
 {
-	struct irq_info *info = info_for_irq(irq);
 	BUG_ON(info->type != IRQT_PIRQ);
 
 	return info->u.pirq.flags & PIRQ_NEEDS_EOI;
 }
 
-static void bind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int cpu,
+static void bind_evtchn_to_cpu(struct irq_info *info, unsigned int cpu,
 			       bool force_affinity)
 {
-	int irq = get_evtchn_to_irq(evtchn);
-	struct irq_info *info = info_for_irq(irq);
-
-	BUG_ON(irq == -1);
-
 	if (IS_ENABLED(CONFIG_SMP) && force_affinity) {
-		struct irq_data *data = irq_get_irq_data(irq);
+		struct irq_data *data = irq_get_irq_data(info->irq);
 
 		irq_data_update_affinity(data, cpumask_of(cpu));
 		irq_data_update_effective_affinity(data, cpumask_of(cpu));
 	}
 
-	xen_evtchn_port_bind_to_cpu(evtchn, cpu, info->cpu);
+	xen_evtchn_port_bind_to_cpu(info->evtchn, cpu, info->cpu);
 
 	channels_on_cpu_dec(info);
 	info->cpu = cpu;
@@ -601,7 +577,9 @@ static void lateeoi_list_add(struct irq_info *info)
 
 	spin_lock_irqsave(&eoi->eoi_list_lock, flags);
 
-	if (list_empty(&eoi->eoi_list)) {
+	elem = list_first_entry_or_null(&eoi->eoi_list, struct irq_info,
+					eoi_list);
+	if (!elem || info->eoi_time < elem->eoi_time) {
 		list_add(&info->eoi_list, &eoi->eoi_list);
 		mod_delayed_work_on(info->eoi_cpu, system_wq,
 				    &eoi->delayed, delay);
@@ -732,50 +710,49 @@ void xen_irq_lateeoi(unsigned int irq, unsigned int eoi_flags)
 }
 EXPORT_SYMBOL_GPL(xen_irq_lateeoi);
 
-static void xen_irq_init(unsigned irq)
+static struct irq_info *xen_irq_init(unsigned int irq)
 {
 	struct irq_info *info;
 
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
-	if (info == NULL)
-		panic("Unable to allocate metadata for IRQ%d\n", irq);
+	if (info) {
+		info->irq = irq;
+		info->type = IRQT_UNBOUND;
+		info->refcnt = -1;
+		INIT_RCU_WORK(&info->rwork, delayed_free_irq);
 
-	info->type = IRQT_UNBOUND;
-	info->refcnt = -1;
-	INIT_RCU_WORK(&info->rwork, delayed_free_irq);
+		set_info_for_irq(irq, info);
+		/*
+		 * Interrupt affinity setting can be immediate. No point
+		 * in delaying it until an interrupt is handled.
+		 */
+		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
 
-	set_info_for_irq(irq, info);
-	/*
-	 * Interrupt affinity setting can be immediate. No point
-	 * in delaying it until an interrupt is handled.
-	 */
-	irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
+		INIT_LIST_HEAD(&info->eoi_list);
+		list_add_tail(&info->list, &xen_irq_list_head);
+	}
 
-	INIT_LIST_HEAD(&info->eoi_list);
-	list_add_tail(&info->list, &xen_irq_list_head);
+	return info;
 }
 
-static int __must_check xen_allocate_irqs_dynamic(int nvec)
+static struct irq_info *xen_allocate_irq_dynamic(void)
 {
-	int i, irq = irq_alloc_descs(-1, 0, nvec, -1);
+	int irq = irq_alloc_desc_from(0, -1);
+	struct irq_info *info = NULL;
 
 	if (irq >= 0) {
-		for (i = 0; i < nvec; i++)
-			xen_irq_init(irq + i);
+		info = xen_irq_init(irq);
+		if (!info)
+			xen_irq_free_desc(irq);
 	}
 
-	return irq;
-}
-
-static inline int __must_check xen_allocate_irq_dynamic(void)
-{
-
-	return xen_allocate_irqs_dynamic(1);
+	return info;
 }
 
-static int __must_check xen_allocate_irq_gsi(unsigned gsi)
+static struct irq_info *xen_allocate_irq_gsi(unsigned int gsi)
 {
 	int irq;
+	struct irq_info *info;
 
 	/*
 	 * A PV guest has no concept of a GSI (since it has no ACPI
@@ -792,15 +769,15 @@ static int __must_check xen_allocate_irq_gsi(unsigned gsi)
 	else
 		irq = irq_alloc_desc_at(gsi, -1);
 
-	xen_irq_init(irq);
+	info = xen_irq_init(irq);
+	if (!info)
+		xen_irq_free_desc(irq);
 
-	return irq;
+	return info;
 }
 
-static void xen_free_irq(unsigned irq)
+static void xen_free_irq(struct irq_info *info)
 {
-	struct irq_info *info = info_for_irq(irq);
-
 	if (WARN_ON(!info))
 		return;
 
@@ -821,14 +798,11 @@ static void event_handler_exit(struct irq_info *info)
 	clear_evtchn(info->evtchn);
 }
 
-static void pirq_query_unmask(int irq)
+static void pirq_query_unmask(struct irq_info *info)
 {
 	struct physdev_irq_status_query irq_status;
-	struct irq_info *info = info_for_irq(irq);
-
-	BUG_ON(info->type != IRQT_PIRQ);
 
-	irq_status.irq = pirq_from_irq(irq);
+	irq_status.irq = pirq_from_irq(info);
 	if (HYPERVISOR_physdev_op(PHYSDEVOP_irq_status_query, &irq_status))
 		irq_status.flags = 0;
 
@@ -837,61 +811,81 @@ static void pirq_query_unmask(int irq)
 		info->u.pirq.flags |= PIRQ_NEEDS_EOI;
 }
 
-static void eoi_pirq(struct irq_data *data)
+static void do_eoi_pirq(struct irq_info *info)
 {
-	struct irq_info *info = info_for_irq(data->irq);
-	evtchn_port_t evtchn = info ? info->evtchn : 0;
-	struct physdev_eoi eoi = { .irq = pirq_from_irq(data->irq) };
+	struct physdev_eoi eoi = { .irq = pirq_from_irq(info) };
 	int rc = 0;
 
-	if (!VALID_EVTCHN(evtchn))
+	if (!VALID_EVTCHN(info->evtchn))
 		return;
 
 	event_handler_exit(info);
 
-	if (pirq_needs_eoi(data->irq)) {
+	if (pirq_needs_eoi(info)) {
 		rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
 		WARN_ON(rc);
 	}
 }
 
+static void eoi_pirq(struct irq_data *data)
+{
+	struct irq_info *info = info_for_irq(data->irq);
+
+	do_eoi_pirq(info);
+}
+
+static void do_disable_dynirq(struct irq_info *info)
+{
+	if (VALID_EVTCHN(info->evtchn))
+		do_mask(info, EVT_MASK_REASON_EXPLICIT);
+}
+
+static void disable_dynirq(struct irq_data *data)
+{
+	struct irq_info *info = info_for_irq(data->irq);
+
+	if (info)
+		do_disable_dynirq(info);
+}
+
 static void mask_ack_pirq(struct irq_data *data)
 {
-	disable_dynirq(data);
-	eoi_pirq(data);
+	struct irq_info *info = info_for_irq(data->irq);
+
+	if (info) {
+		do_disable_dynirq(info);
+		do_eoi_pirq(info);
+	}
 }
 
-static unsigned int __startup_pirq(unsigned int irq)
+static unsigned int __startup_pirq(struct irq_info *info)
 {
 	struct evtchn_bind_pirq bind_pirq;
-	struct irq_info *info = info_for_irq(irq);
-	evtchn_port_t evtchn = evtchn_from_irq(irq);
+	evtchn_port_t evtchn = info->evtchn;
 	int rc;
 
-	BUG_ON(info->type != IRQT_PIRQ);
-
 	if (VALID_EVTCHN(evtchn))
 		goto out;
 
-	bind_pirq.pirq = pirq_from_irq(irq);
+	bind_pirq.pirq = pirq_from_irq(info);
 	/* NB. We are happy to share unless we are probing. */
 	bind_pirq.flags = info->u.pirq.flags & PIRQ_SHAREABLE ?
 					BIND_PIRQ__WILL_SHARE : 0;
 	rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_pirq, &bind_pirq);
 	if (rc != 0) {
-		pr_warn("Failed to obtain physical IRQ %d\n", irq);
+		pr_warn("Failed to obtain physical IRQ %d\n", info->irq);
 		return 0;
 	}
 	evtchn = bind_pirq.port;
 
-	pirq_query_unmask(irq);
+	pirq_query_unmask(info);
 
-	rc = set_evtchn_to_irq(evtchn, irq);
+	rc = set_evtchn_to_irq(evtchn, info->irq);
 	if (rc)
 		goto err;
 
 	info->evtchn = evtchn;
-	bind_evtchn_to_cpu(evtchn, 0, false);
+	bind_evtchn_to_cpu(info, 0, false);
 
 	rc = xen_evtchn_port_setup(evtchn);
 	if (rc)
@@ -900,26 +894,28 @@ static unsigned int __startup_pirq(unsigned int irq)
 out:
 	do_unmask(info, EVT_MASK_REASON_EXPLICIT);
 
-	eoi_pirq(irq_get_irq_data(irq));
+	do_eoi_pirq(info);
 
 	return 0;
 
 err:
-	pr_err("irq%d: Failed to set port to irq mapping (%d)\n", irq, rc);
+	pr_err("irq%d: Failed to set port to irq mapping (%d)\n", info->irq,
+	       rc);
 	xen_evtchn_close(evtchn);
 	return 0;
 }
 
 static unsigned int startup_pirq(struct irq_data *data)
 {
-	return __startup_pirq(data->irq);
+	struct irq_info *info = info_for_irq(data->irq);
+
+	return __startup_pirq(info);
 }
 
 static void shutdown_pirq(struct irq_data *data)
 {
-	unsigned int irq = data->irq;
-	struct irq_info *info = info_for_irq(irq);
-	evtchn_port_t evtchn = evtchn_from_irq(irq);
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info->evtchn;
 
 	BUG_ON(info->type != IRQT_PIRQ);
 
@@ -957,10 +953,14 @@ int xen_irq_from_gsi(unsigned gsi)
 }
 EXPORT_SYMBOL_GPL(xen_irq_from_gsi);
 
-static void __unbind_from_irq(unsigned int irq)
+static void __unbind_from_irq(struct irq_info *info, unsigned int irq)
 {
-	evtchn_port_t evtchn = evtchn_from_irq(irq);
-	struct irq_info *info = info_for_irq(irq);
+	evtchn_port_t evtchn;
+
+	if (!info) {
+		xen_irq_free_desc(irq);
+		return;
+	}
 
 	if (info->refcnt > 0) {
 		info->refcnt--;
@@ -968,19 +968,22 @@ static void __unbind_from_irq(unsigned int irq)
 			return;
 	}
 
+	evtchn = info->evtchn;
+
 	if (VALID_EVTCHN(evtchn)) {
-		unsigned int cpu = cpu_from_irq(irq);
+		unsigned int cpu = info->cpu;
 		struct xenbus_device *dev;
 
 		if (!info->is_static)
 			xen_evtchn_close(evtchn);
 
-		switch (type_from_irq(irq)) {
+		switch (info->type) {
 		case IRQT_VIRQ:
-			per_cpu(virq_to_irq, cpu)[virq_from_irq(irq)] = -1;
+			per_cpu(virq_to_irq, cpu)[virq_from_irq(info)] = -1;
 			break;
 		case IRQT_IPI:
-			per_cpu(ipi_to_irq, cpu)[ipi_from_irq(irq)] = -1;
+			per_cpu(ipi_to_irq, cpu)[ipi_from_irq(info)] = -1;
+			per_cpu(ipi_to_evtchn, cpu)[ipi_from_irq(info)] = 0;
 			break;
 		case IRQT_EVTCHN:
 			dev = info->u.interdomain;
@@ -994,7 +997,7 @@ static void __unbind_from_irq(unsigned int irq)
 		xen_irq_info_cleanup(info);
 	}
 
-	xen_free_irq(irq);
+	xen_free_irq(info);
 }
 
 /*
@@ -1010,24 +1013,24 @@ static void __unbind_from_irq(unsigned int irq)
 int xen_bind_pirq_gsi_to_irq(unsigned gsi,
 			     unsigned pirq, int shareable, char *name)
 {
-	int irq;
+	struct irq_info *info;
 	struct physdev_irq irq_op;
 	int ret;
 
 	mutex_lock(&irq_mapping_update_lock);
 
-	irq = xen_irq_from_gsi(gsi);
-	if (irq != -1) {
+	ret = xen_irq_from_gsi(gsi);
+	if (ret != -1) {
 		pr_info("%s: returning irq %d for gsi %u\n",
-			__func__, irq, gsi);
+			__func__, ret, gsi);
 		goto out;
 	}
 
-	irq = xen_allocate_irq_gsi(gsi);
-	if (irq < 0)
+	info = xen_allocate_irq_gsi(gsi);
+	if (!info)
 		goto out;
 
-	irq_op.irq = irq;
+	irq_op.irq = info->irq;
 	irq_op.vector = 0;
 
 	/* Only the privileged domain can do this. For non-priv, the pcifront
@@ -1035,20 +1038,19 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi,
 	 * this in the priv domain. */
 	if (xen_initial_domain() &&
 	    HYPERVISOR_physdev_op(PHYSDEVOP_alloc_irq_vector, &irq_op)) {
-		xen_free_irq(irq);
-		irq = -ENOSPC;
+		xen_free_irq(info);
+		ret = -ENOSPC;
 		goto out;
 	}
 
-	ret = xen_irq_info_pirq_setup(irq, 0, pirq, gsi, DOMID_SELF,
+	ret = xen_irq_info_pirq_setup(info, 0, pirq, gsi, DOMID_SELF,
 			       shareable ? PIRQ_SHAREABLE : 0);
 	if (ret < 0) {
-		__unbind_from_irq(irq);
-		irq = ret;
+		__unbind_from_irq(info, info->irq);
 		goto out;
 	}
 
-	pirq_query_unmask(irq);
+	pirq_query_unmask(info);
 	/* We try to use the handler with the appropriate semantic for the
 	 * type of interrupt: if the interrupt is an edge triggered
 	 * interrupt we use handle_edge_irq.
@@ -1065,16 +1067,18 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi,
 	 * is the right choice either way.
 	 */
 	if (shareable)
-		irq_set_chip_and_handler_name(irq, &xen_pirq_chip,
+		irq_set_chip_and_handler_name(info->irq, &xen_pirq_chip,
 				handle_fasteoi_irq, name);
 	else
-		irq_set_chip_and_handler_name(irq, &xen_pirq_chip,
+		irq_set_chip_and_handler_name(info->irq, &xen_pirq_chip,
 				handle_edge_irq, name);
 
+	ret = info->irq;
+
 out:
 	mutex_unlock(&irq_mapping_update_lock);
 
-	return irq;
+	return ret;
 }
 
 #ifdef CONFIG_PCI_MSI
@@ -1096,17 +1100,24 @@ int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
 			     int pirq, int nvec, const char *name, domid_t domid)
 {
 	int i, irq, ret;
+	struct irq_info *info;
 
 	mutex_lock(&irq_mapping_update_lock);
 
-	irq = xen_allocate_irqs_dynamic(nvec);
+	irq = irq_alloc_descs(-1, 0, nvec, -1);
 	if (irq < 0)
 		goto out;
 
 	for (i = 0; i < nvec; i++) {
+		info = xen_irq_init(irq + i);
+		if (!info) {
+			ret = -ENOMEM;
+			goto error_irq;
+		}
+
 		irq_set_chip_and_handler_name(irq + i, &xen_pirq_chip, handle_edge_irq, name);
 
-		ret = xen_irq_info_pirq_setup(irq + i, 0, pirq + i, 0, domid,
+		ret = xen_irq_info_pirq_setup(info, 0, pirq + i, 0, domid,
 					      i == 0 ? 0 : PIRQ_MSI_GROUP);
 		if (ret < 0)
 			goto error_irq;
@@ -1118,9 +1129,12 @@ int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
 out:
 	mutex_unlock(&irq_mapping_update_lock);
 	return irq;
+
 error_irq:
-	while (nvec--)
-		__unbind_from_irq(irq + nvec);
+	while (nvec--) {
+		info = info_for_irq(irq + nvec);
+		__unbind_from_irq(info, irq + nvec);
+	}
 	mutex_unlock(&irq_mapping_update_lock);
 	return ret;
 }
@@ -1156,67 +1170,45 @@ int xen_destroy_irq(int irq)
 		}
 	}
 
-	xen_free_irq(irq);
+	xen_free_irq(info);
 
 out:
 	mutex_unlock(&irq_mapping_update_lock);
 	return rc;
 }
 
-int xen_irq_from_pirq(unsigned pirq)
-{
-	int irq;
-
-	struct irq_info *info;
-
-	mutex_lock(&irq_mapping_update_lock);
-
-	list_for_each_entry(info, &xen_irq_list_head, list) {
-		if (info->type != IRQT_PIRQ)
-			continue;
-		irq = info->irq;
-		if (info->u.pirq.pirq == pirq)
-			goto out;
-	}
-	irq = -1;
-out:
-	mutex_unlock(&irq_mapping_update_lock);
-
-	return irq;
-}
-
-
 int xen_pirq_from_irq(unsigned irq)
 {
-	return pirq_from_irq(irq);
+	struct irq_info *info = info_for_irq(irq);
+
+	return pirq_from_irq(info);
 }
 EXPORT_SYMBOL_GPL(xen_pirq_from_irq);
 
 static int bind_evtchn_to_irq_chip(evtchn_port_t evtchn, struct irq_chip *chip,
 				   struct xenbus_device *dev)
 {
-	int irq;
-	int ret;
+	int ret = -ENOMEM;
+	struct irq_info *info;
 
 	if (evtchn >= xen_evtchn_max_channels())
 		return -ENOMEM;
 
 	mutex_lock(&irq_mapping_update_lock);
 
-	irq = get_evtchn_to_irq(evtchn);
+	info = evtchn_to_info(evtchn);
 
-	if (irq == -1) {
-		irq = xen_allocate_irq_dynamic();
-		if (irq < 0)
+	if (!info) {
+		info = xen_allocate_irq_dynamic();
+		if (!info)
 			goto out;
 
-		irq_set_chip_and_handler_name(irq, chip,
+		irq_set_chip_and_handler_name(info->irq, chip,
 					      handle_edge_irq, "event");
 
-		ret = xen_irq_info_evtchn_setup(irq, evtchn, dev);
+		ret = xen_irq_info_evtchn_setup(info, evtchn, dev);
 		if (ret < 0) {
-			__unbind_from_irq(irq);
-			irq = ret;
+			__unbind_from_irq(info, info->irq);
 			goto out;
 		}
 		/*
@@ -1226,17 +1218,17 @@ static int bind_evtchn_to_irq_chip(evtchn_port_t evtchn, struct irq_chip *chip,
 		 * affinity setting is not invoked on them so nothing would
 		 * bind the channel.
 		 */
-		bind_evtchn_to_cpu(evtchn, 0, false);
-	} else {
-		struct irq_info *info = info_for_irq(irq);
-		if (!WARN_ON(!info || info->type != IRQT_EVTCHN))
-			info->refcnt++;
+		bind_evtchn_to_cpu(info, 0, false);
+	} else if (!WARN_ON(info->type != IRQT_EVTCHN)) {
+		info->refcnt++;
 	}
 
+	ret = info->irq;
+
 out:
 	mutex_unlock(&irq_mapping_update_lock);
 
-	return irq;
+	return ret;
 }
 
 int bind_evtchn_to_irq(evtchn_port_t evtchn)
@@ -1255,18 +1247,19 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 {
 	struct evtchn_bind_ipi bind_ipi;
 	evtchn_port_t evtchn;
-	int ret, irq;
+	struct irq_info *info;
+	int ret;
 
 	mutex_lock(&irq_mapping_update_lock);
 
-	irq = per_cpu(ipi_to_irq, cpu)[ipi];
+	ret = per_cpu(ipi_to_irq, cpu)[ipi];
 
-	if (irq == -1) {
-		irq = xen_allocate_irq_dynamic();
-		if (irq < 0)
+	if (ret == -1) {
+		info = xen_allocate_irq_dynamic();
+		if (!info)
 			goto out;
 
-		irq_set_chip_and_handler_name(irq, &xen_percpu_chip,
+		irq_set_chip_and_handler_name(info->irq, &xen_percpu_chip,
 					      handle_percpu_irq, "ipi");
 
 		bind_ipi.vcpu = xen_vcpu_nr(cpu);
@@ -1275,25 +1268,25 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 			BUG();
 		evtchn = bind_ipi.port;
 
-		ret = xen_irq_info_ipi_setup(cpu, irq, evtchn, ipi);
+		ret = xen_irq_info_ipi_setup(info, cpu, evtchn, ipi);
 		if (ret < 0) {
-			__unbind_from_irq(irq);
-			irq = ret;
+			__unbind_from_irq(info, info->irq);
 			goto out;
 		}
 		/*
 		 * Force the affinity mask to the target CPU so proc shows
 		 * the correct target.
 		 */
-		bind_evtchn_to_cpu(evtchn, cpu, true);
+		bind_evtchn_to_cpu(info, cpu, true);
+		ret = info->irq;
 	} else {
-		struct irq_info *info = info_for_irq(irq);
+		info = info_for_irq(ret);
 		WARN_ON(info == NULL || info->type != IRQT_IPI);
 	}
 
  out:
 	mutex_unlock(&irq_mapping_update_lock);
-	return irq;
+	return ret;
 }
 
 static int bind_interdomain_evtchn_to_irq_chip(struct xenbus_device *dev,
@@ -1361,22 +1354,23 @@ int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu)
 {
 	struct evtchn_bind_virq bind_virq;
 	evtchn_port_t evtchn = 0;
-	int irq, ret;
+	struct irq_info *info;
+	int ret;
 
 	mutex_lock(&irq_mapping_update_lock);
 
-	irq = per_cpu(virq_to_irq, cpu)[virq];
+	ret = per_cpu(virq_to_irq, cpu)[virq];
 
-	if (irq == -1) {
-		irq = xen_allocate_irq_dynamic();
-		if (irq < 0)
+	if (ret == -1) {
+		info = xen_allocate_irq_dynamic();
+		if (!info)
 			goto out;
 
 		if (percpu)
-			irq_set_chip_and_handler_name(irq, &xen_percpu_chip,
+			irq_set_chip_and_handler_name(info->irq, &xen_percpu_chip,
 						      handle_percpu_irq, "virq");
 		else
-			irq_set_chip_and_handler_name(irq, &xen_dynamic_chip,
+			irq_set_chip_and_handler_name(info->irq, &xen_dynamic_chip,
 						      handle_edge_irq, "virq");
 
 		bind_virq.virq = virq;
@@ -1391,10 +1385,9 @@ int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu)
 			BUG_ON(ret < 0);
 		}
 
-		ret = xen_irq_info_virq_setup(cpu, irq, evtchn, virq);
+		ret = xen_irq_info_virq_setup(info, cpu, evtchn, virq);
 		if (ret < 0) {
-			__unbind_from_irq(irq);
-			irq = ret;
+			__unbind_from_irq(info, info->irq);
 			goto out;
 		}
 
@@ -1402,22 +1395,26 @@ int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu)
 		 * Force the affinity mask for percpu interrupts so proc
 		 * shows the correct target.
 		 */
-		bind_evtchn_to_cpu(evtchn, cpu, percpu);
+		bind_evtchn_to_cpu(info, cpu, percpu);
+		ret = info->irq;
 	} else {
-		struct irq_info *info = info_for_irq(irq);
+		info = info_for_irq(ret);
 		WARN_ON(info == NULL || info->type != IRQT_VIRQ);
 	}
 
 out:
 	mutex_unlock(&irq_mapping_update_lock);
 
-	return irq;
+	return ret;
 }
 
 static void unbind_from_irq(unsigned int irq)
 {
+	struct irq_info *info;
+
 	mutex_lock(&irq_mapping_update_lock);
-	__unbind_from_irq(irq);
+	info = info_for_irq(irq);
+	__unbind_from_irq(info, irq);
 	mutex_unlock(&irq_mapping_update_lock);
 }
 
@@ -1568,13 +1565,7 @@ EXPORT_SYMBOL_GPL(xen_set_irq_priority);
 
 int evtchn_make_refcounted(evtchn_port_t evtchn, bool is_static)
 {
-	int irq = get_evtchn_to_irq(evtchn);
-	struct irq_info *info;
-
-	if (irq == -1)
-		return -ENOENT;
-
-	info = info_for_irq(irq);
+	struct irq_info *info = evtchn_to_info(evtchn);
 
 	if (!info)
 		return -ENOENT;
@@ -1590,7 +1581,6 @@ EXPORT_SYMBOL_GPL(evtchn_make_refcounted);
 
 int evtchn_get(evtchn_port_t evtchn)
 {
-	int irq;
 	struct irq_info *info;
 	int err = -ENOENT;
 
@@ -1599,11 +1589,7 @@ int evtchn_get(evtchn_port_t evtchn)
 
 	mutex_lock(&irq_mapping_update_lock);
 
-	irq = get_evtchn_to_irq(evtchn);
-	if (irq == -1)
-		goto done;
-
-	info = info_for_irq(irq);
+	info = evtchn_to_info(evtchn);
 
 	if (!info)
 		goto done;
@@ -1623,16 +1609,17 @@ EXPORT_SYMBOL_GPL(evtchn_get);
 
 void evtchn_put(evtchn_port_t evtchn)
 {
-	int irq = get_evtchn_to_irq(evtchn);
-	if (WARN_ON(irq == -1))
+	struct irq_info *info = evtchn_to_info(evtchn);
+
+	if (WARN_ON(!info))
 		return;
-	unbind_from_irq(irq);
+	unbind_from_irq(info->irq);
 }
 EXPORT_SYMBOL_GPL(evtchn_put);
 
 void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector)
 {
-	int irq;
+	evtchn_port_t evtchn;
 
 #ifdef CONFIG_X86
 	if (unlikely(vector == XEN_NMI_VECTOR)) {
@@ -1643,9 +1630,9 @@ void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector)
 		return;
 	}
 #endif
-	irq = per_cpu(ipi_to_irq, cpu)[vector];
-	BUG_ON(irq < 0);
-	notify_remote_via_irq(irq);
+	evtchn = per_cpu(ipi_to_evtchn, cpu)[vector];
+	BUG_ON(evtchn == 0);
+	notify_remote_via_evtchn(evtchn);
 }
 
 struct evtchn_loop_ctrl {
@@ -1656,12 +1643,10 @@ struct evtchn_loop_ctrl {
 
 void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl)
 {
-	int irq;
-	struct irq_info *info;
+	struct irq_info *info = evtchn_to_info(port);
 	struct xenbus_device *dev;
 
-	irq = get_evtchn_to_irq(port);
-	if (irq == -1)
+	if (!info)
 		return;
 
 	/*
@@ -1686,7 +1671,6 @@ void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl)
 		}
 	}
 
-	info = info_for_irq(irq);
 	if (xchg_acquire(&info->is_active, 1))
 		return;
 
@@ -1700,7 +1684,7 @@ void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl)
 		info->eoi_time = get_jiffies_64() + event_eoi_delay;
 	}
 
-	generic_handle_irq(irq);
+	generic_handle_irq(info->irq);
 }
 
 int xen_evtchn_do_upcall(void)
@@ -1758,16 +1742,17 @@ void rebind_evtchn_irq(evtchn_port_t evtchn, int irq)
 	mutex_lock(&irq_mapping_update_lock);
 
 	/* After resume the irq<->evtchn mappings are all cleared out */
-	BUG_ON(get_evtchn_to_irq(evtchn) != -1);
+	BUG_ON(evtchn_to_info(evtchn));
 	/* Expect irq to have been bound before,
 	   so there should be a proper type */
 	BUG_ON(info->type == IRQT_UNBOUND);
 
-	(void)xen_irq_info_evtchn_setup(irq, evtchn, NULL);
+	info->irq = irq;
+	(void)xen_irq_info_evtchn_setup(info, evtchn, NULL);
 
 	mutex_unlock(&irq_mapping_update_lock);
 
-	bind_evtchn_to_cpu(evtchn, info->cpu, false);
+	bind_evtchn_to_cpu(info, info->cpu, false);
 
 	/* Unmask the event channel. */
 	enable_irq(irq);
@@ -1801,7 +1786,7 @@ static int xen_rebind_evtchn_to_cpu(struct irq_info *info, unsigned int tcpu)
 	 * it, but don't do the xenlinux-level rebind in that case.
 	 */
 	if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0)
-		bind_evtchn_to_cpu(evtchn, tcpu, false);
+		bind_evtchn_to_cpu(info, tcpu, false);
 
 	do_unmask(info, EVT_MASK_REASON_TEMPORARY);
 
@@ -1858,28 +1843,30 @@ static void enable_dynirq(struct irq_data *data)
 		do_unmask(info, EVT_MASK_REASON_EXPLICIT);
 }
 
-static void disable_dynirq(struct irq_data *data)
+static void do_ack_dynirq(struct irq_info *info)
 {
-	struct irq_info *info = info_for_irq(data->irq);
-	evtchn_port_t evtchn = info ? info->evtchn : 0;
+	evtchn_port_t evtchn = info->evtchn;
 
 	if (VALID_EVTCHN(evtchn))
-		do_mask(info, EVT_MASK_REASON_EXPLICIT);
+		event_handler_exit(info);
 }
 
 static void ack_dynirq(struct irq_data *data)
 {
 	struct irq_info *info = info_for_irq(data->irq);
-	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
-	if (VALID_EVTCHN(evtchn))
-		event_handler_exit(info);
+	if (info)
+		do_ack_dynirq(info);
 }
 
 static void mask_ack_dynirq(struct irq_data *data)
 {
-	disable_dynirq(data);
-	ack_dynirq(data);
+	struct irq_info *info = info_for_irq(data->irq);
+
+	if (info) {
+		do_disable_dynirq(info);
+		do_ack_dynirq(info);
+	}
 }
 
 static void lateeoi_ack_dynirq(struct irq_data *data)
@@ -1952,13 +1939,13 @@ static void restore_pirqs(void)
 		if (rc) {
 			pr_warn("xen map irq failed gsi=%d irq=%d pirq=%d rc=%d\n",
 				gsi, irq, pirq, rc);
-			xen_free_irq(irq);
+			xen_free_irq(info);
 			continue;
 		}
 
 		printk(KERN_DEBUG "xen: --> irq=%d, pirq=%d\n", irq, map_irq.pirq);
 
-		__startup_pirq(irq);
+		__startup_pirq(info);
 	}
 }
 
@@ -1966,13 +1953,15 @@ static void restore_cpu_virqs(unsigned int cpu)
 {
 	struct evtchn_bind_virq bind_virq;
 	evtchn_port_t evtchn;
+	struct irq_info *info;
 	int virq, irq;
 
 	for (virq = 0; virq < NR_VIRQS; virq++) {
 		if ((irq = per_cpu(virq_to_irq, cpu)[virq]) == -1)
 			continue;
+		info = info_for_irq(irq);
 
-		BUG_ON(virq_from_irq(irq) != virq);
+		BUG_ON(virq_from_irq(info) != virq);
 
 		/* Get a new binding from Xen. */
 		bind_virq.virq = virq;
@@ -1983,9 +1972,9 @@ static void restore_cpu_virqs(unsigned int cpu)
 		evtchn = bind_virq.port;
 
 		/* Record the new mapping. */
-		(void)xen_irq_info_virq_setup(cpu, irq, evtchn, virq);
+		xen_irq_info_virq_setup(info, cpu, evtchn, virq);
 		/* The affinity mask is still valid */
-		bind_evtchn_to_cpu(evtchn, cpu, false);
+		bind_evtchn_to_cpu(info, cpu, false);
 	}
 }
 
@@ -1993,13 +1982,15 @@ static void restore_cpu_ipis(unsigned int cpu)
 {
 	struct evtchn_bind_ipi bind_ipi;
 	evtchn_port_t evtchn;
+	struct irq_info *info;
 	int ipi, irq;
 
 	for (ipi = 0; ipi < XEN_NR_IPIS; ipi++) {
 		if ((irq = per_cpu(ipi_to_irq, cpu)[ipi]) == -1)
 			continue;
+		info = info_for_irq(irq);
 
-		BUG_ON(ipi_from_irq(irq) != ipi);
+		BUG_ON(ipi_from_irq(info) != ipi);
 
 		/* Get a new binding from Xen. */
 		bind_ipi.vcpu = xen_vcpu_nr(cpu);
@@ -2009,9 +2000,9 @@ static void restore_cpu_ipis(unsigned int cpu)
 		evtchn = bind_ipi.port;
 
 		/* Record the new mapping. */
-		(void)xen_irq_info_ipi_setup(cpu, irq, evtchn, ipi);
+		xen_irq_info_ipi_setup(info, cpu, evtchn, ipi);
 		/* The affinity mask is still valid */
-		bind_evtchn_to_cpu(evtchn, cpu, false);
+		bind_evtchn_to_cpu(info, cpu, false);
 	}
 }
 
@@ -2025,13 +2016,6 @@ void xen_clear_irq_pending(int irq)
 		event_handler_exit(info);
 }
 EXPORT_SYMBOL(xen_clear_irq_pending);
-void xen_set_irq_pending(int irq)
-{
-	evtchn_port_t evtchn = evtchn_from_irq(irq);
-
-	if (VALID_EVTCHN(evtchn))
-		set_evtchn(evtchn);
-}
 
 bool xen_test_irq_pending(int irq)
 {
diff --git a/drivers/xen/events/events_internal.h b/drivers/xen/events/events_internal.h
index 4d3398eff9cd..19ae31695edc 100644
--- a/drivers/xen/events/events_internal.h
+++ b/drivers/xen/events/events_internal.h
@@ -33,7 +33,6 @@ struct evtchn_ops {
 
 extern const struct evtchn_ops *evtchn_ops;
 
-int get_evtchn_to_irq(evtchn_port_t evtchn);
 void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl);
 
 unsigned int cpu_from_evtchn(evtchn_port_t evtchn);
diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c
index b3e3d1bb37f3..508655273145 100644
--- a/drivers/xen/pcpu.c
+++ b/drivers/xen/pcpu.c
@@ -47,6 +47,9 @@
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 
+#ifdef CONFIG_ACPI
+#include <acpi/processor.h>
+#endif
 
 /*
  * @cpu_id: Xen physical cpu logic number
@@ -400,4 +403,23 @@ bool __init xen_processor_present(uint32_t acpi_id)
 
 	return online;
 }
+
+void xen_sanitize_proc_cap_bits(uint32_t *cap)
+{
+	struct xen_platform_op op = {
+		.cmd			= XENPF_set_processor_pminfo,
+		.u.set_pminfo.id	= -1,
+		.u.set_pminfo.type	= XEN_PM_PDC,
+	};
+	u32 buf[3] = { ACPI_PDC_REVISION_ID, 1, *cap };
+	int ret;
+
+	set_xen_guest_handle(op.u.set_pminfo.pdc, buf);
+	ret = HYPERVISOR_platform_op(&op);
+	if (ret)
+		pr_err("sanitize of _PDC buffer bits from Xen failed: %d\n",
+		       ret);
+	else
+		*cap = buf[2];
+}
 #endif
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 1ce7f3c7a950..35b6e306026a 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -1115,7 +1115,7 @@ struct privcmd_kernel_ioreq {
 	spinlock_t lock; /* Protects ioeventfds list */
 	struct list_head ioeventfds;
 	struct list_head list;
-	struct ioreq_port ports[0];
+	struct ioreq_port ports[] __counted_by(vcpus);
 };
 
 static irqreturn_t ioeventfd_interrupt(int irq, void *dev_id)
@@ -1147,7 +1147,7 @@ static irqreturn_t ioeventfd_interrupt(int irq, void *dev_id)
 		if (ioreq->addr == kioeventfd->addr + VIRTIO_MMIO_QUEUE_NOTIFY &&
 		    ioreq->size == kioeventfd->addr_len &&
 		    (ioreq->data & QUEUE_NOTIFY_VQ_MASK) == kioeventfd->vq) {
-			eventfd_signal(kioeventfd->eventfd, 1);
+			eventfd_signal(kioeventfd->eventfd);
 			state = STATE_IORESP_READY;
 			break;
 		}
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 946bd56f0ac5..0e6c6c25d154 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -405,4 +405,5 @@ const struct dma_map_ops xen_swiotlb_dma_ops = {
 	.get_sgtable = dma_common_get_sgtable,
 	.alloc_pages = dma_common_alloc_pages,
 	.free_pages = dma_common_free_pages,
+	.max_mapping_size = swiotlb_max_mapping_size,
 };
diff --git a/drivers/xen/xen-front-pgdir-shbuf.c b/drivers/xen/xen-front-pgdir-shbuf.c
index b52e0fa595a9..223870a0111b 100644
--- a/drivers/xen/xen-front-pgdir-shbuf.c
+++ b/drivers/xen/xen-front-pgdir-shbuf.c
@@ -21,7 +21,7 @@
 
 #include <xen/xen-front-pgdir-shbuf.h>
 
-/**
+/*
  * This structure represents the structure of a shared page
  * that contains grant references to the pages of the shared
  * buffer. This structure is common to many Xen para-virtualized
@@ -33,7 +33,7 @@ struct xen_page_directory {
 	grant_ref_t gref[]; /* Variable length */
 };
 
-/**
+/*
  * Shared buffer ops which are differently implemented
  * depending on the allocation mode, e.g. if the buffer
  * is allocated by the corresponding backend or frontend.
@@ -61,7 +61,7 @@ struct xen_front_pgdir_shbuf_ops {
 	int (*unmap)(struct xen_front_pgdir_shbuf *buf);
 };
 
-/**
+/*
  * Get granted reference to the very first page of the
  * page directory. Usually this is passed to the backend,
  * so it can find/fill the grant references to the buffer's
@@ -81,7 +81,7 @@ xen_front_pgdir_shbuf_get_dir_start(struct xen_front_pgdir_shbuf *buf)
 }
 EXPORT_SYMBOL_GPL(xen_front_pgdir_shbuf_get_dir_start);
 
-/**
+/*
  * Map granted references of the shared buffer.
  *
  * Depending on the shared buffer mode of allocation
@@ -102,7 +102,7 @@ int xen_front_pgdir_shbuf_map(struct xen_front_pgdir_shbuf *buf)
 }
 EXPORT_SYMBOL_GPL(xen_front_pgdir_shbuf_map);
 
-/**
+/*
  * Unmap granted references of the shared buffer.
  *
  * Depending on the shared buffer mode of allocation
@@ -123,7 +123,7 @@ int xen_front_pgdir_shbuf_unmap(struct xen_front_pgdir_shbuf *buf)
 }
 EXPORT_SYMBOL_GPL(xen_front_pgdir_shbuf_unmap);
 
-/**
+/*
  * Free all the resources of the shared buffer.
  *
  * \param buf shared buffer which resources to be freed.
@@ -150,7 +150,7 @@ EXPORT_SYMBOL_GPL(xen_front_pgdir_shbuf_free);
 				 offsetof(struct xen_page_directory, \
 					  gref)) / sizeof(grant_ref_t))
 
-/**
+/*
  * Get the number of pages the page directory consumes itself.
  *
  * \param buf shared buffer.
@@ -160,7 +160,7 @@ static int get_num_pages_dir(struct xen_front_pgdir_shbuf *buf)
 	return DIV_ROUND_UP(buf->num_pages, XEN_NUM_GREFS_PER_PAGE);
 }
 
-/**
+/*
  * Calculate the number of grant references needed to share the buffer
  * and its pages when backend allocates the buffer.
  *
@@ -172,7 +172,7 @@ static void backend_calc_num_grefs(struct xen_front_pgdir_shbuf *buf)
 	buf->num_grefs = get_num_pages_dir(buf);
 }
 
-/**
+/*
  * Calculate the number of grant references needed to share the buffer
  * and its pages when frontend allocates the buffer.
  *
@@ -190,7 +190,7 @@ static void guest_calc_num_grefs(struct xen_front_pgdir_shbuf *buf)
 #define xen_page_to_vaddr(page) \
 	((uintptr_t)pfn_to_kaddr(page_to_xen_pfn(page)))
 
-/**
+/*
  * Unmap the buffer previously mapped with grant references
  * provided by the backend.
  *
@@ -238,7 +238,7 @@ static int backend_unmap(struct xen_front_pgdir_shbuf *buf)
 	return ret;
 }
 
-/**
+/*
  * Map the buffer with grant references provided by the backend.
  *
  * \param buf shared buffer.
@@ -320,7 +320,7 @@ static int backend_map(struct xen_front_pgdir_shbuf *buf)
 	return ret;
 }
 
-/**
+/*
  * Fill page directory with grant references to the pages of the
  * page directory itself.
  *
@@ -350,7 +350,7 @@ static void backend_fill_page_dir(struct xen_front_pgdir_shbuf *buf)
 	page_dir->gref_dir_next_page = XEN_GREF_LIST_END;
 }
 
-/**
+/*
  * Fill page directory with grant references to the pages of the
  * page directory and the buffer we share with the backend.
  *
@@ -389,7 +389,7 @@ static void guest_fill_page_dir(struct xen_front_pgdir_shbuf *buf)
 	}
 }
 
-/**
+/*
  * Grant references to the frontend's buffer pages.
  *
  * These will be shared with the backend, so it can
@@ -418,7 +418,7 @@ static int guest_grant_refs_for_buffer(struct xen_front_pgdir_shbuf *buf,
 	return 0;
 }
 
-/**
+/*
  * Grant all the references needed to share the buffer.
  *
  * Grant references to the page directory pages and, if
@@ -466,7 +466,7 @@ static int grant_references(struct xen_front_pgdir_shbuf *buf)
 	return 0;
 }
 
-/**
+/*
  * Allocate all required structures to mange shared buffer.
  *
  * \param buf shared buffer.
@@ -506,7 +506,7 @@ static const struct xen_front_pgdir_shbuf_ops local_ops = {
 	.grant_refs_for_buffer = guest_grant_refs_for_buffer,
 };
 
-/**
+/*
  * Allocate a new instance of a shared buffer.
  *
  * \param cfg configuration to be used while allocating a new shared buffer.
diff --git a/fs/Kconfig b/fs/Kconfig
index fd1f655b4f1f..a3159831ba98 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -18,6 +18,10 @@ config VALIDATE_FS_PARSER
 config FS_IOMAP
 	bool
 
+# Stackable filesystems
+config FS_STACK
+	bool
+
 config BUFFER_HEAD
 	bool
 
@@ -254,7 +258,7 @@ config TMPFS_QUOTA
 config ARCH_SUPPORTS_HUGETLBFS
 	def_bool n
 
-config HUGETLBFS
+menuconfig HUGETLBFS
 	bool "HugeTLB file system support"
 	depends on X86 || SPARC64 || ARCH_SUPPORTS_HUGETLBFS || BROKEN
 	depends on (SYSFS || SYSCTL)
@@ -266,22 +270,25 @@ config HUGETLBFS
 
 	  If unsure, say N.
 
-config HUGETLB_PAGE
-	def_bool HUGETLBFS
-
-config HUGETLB_PAGE_OPTIMIZE_VMEMMAP
-	def_bool HUGETLB_PAGE
-	depends on ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP
-	depends on SPARSEMEM_VMEMMAP
-
+if HUGETLBFS
 config HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON
 	bool "HugeTLB Vmemmap Optimization (HVO) defaults to on"
 	default n
 	depends on HUGETLB_PAGE_OPTIMIZE_VMEMMAP
 	help
-	  The HugeTLB VmemmapvOptimization (HVO) defaults to off. Say Y here to
+	  The HugeTLB Vmemmap Optimization (HVO) defaults to off. Say Y here to
 	  enable HVO by default. It can be disabled via hugetlb_free_vmemmap=off
 	  (boot command line) or hugetlb_optimize_vmemmap (sysctl).
+endif # HUGETLBFS
+
+config HUGETLB_PAGE
+	def_bool HUGETLBFS
+	select XARRAY_MULTI
+
+config HUGETLB_PAGE_OPTIMIZE_VMEMMAP
+	def_bool HUGETLB_PAGE
+	depends on ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP
+	depends on SPARSEMEM_VMEMMAP
 
 config ARCH_HAS_GIGANTIC_PAGE
 	bool
diff --git a/fs/Makefile b/fs/Makefile
index 75522f88e763..a6962c588962 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -39,6 +39,7 @@ obj-$(CONFIG_COMPAT_BINFMT_ELF)	+= compat_binfmt_elf.o
 obj-$(CONFIG_BINFMT_ELF_FDPIC)	+= binfmt_elf_fdpic.o
 obj-$(CONFIG_BINFMT_FLAT)	+= binfmt_flat.o
 
+obj-$(CONFIG_FS_STACK)		+= backing-file.o
 obj-$(CONFIG_FS_MBCACHE)	+= mbcache.o
 obj-$(CONFIG_FS_POSIX_ACL)	+= posix_acl.o
 obj-$(CONFIG_NFS_COMMON)	+= nfs_common/
diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c
index 3081edb09e46..a183e213a4a5 100644
--- a/fs/adfs/inode.c
+++ b/fs/adfs/inode.c
@@ -5,6 +5,7 @@
  *  Copyright (C) 1997-1999 Russell King
  */
 #include <linux/buffer_head.h>
+#include <linux/mpage.h>
 #include <linux/writeback.h>
 #include "adfs.h"
 
@@ -33,9 +34,10 @@ abort_toobig:
 	return 0;
 }
 
-static int adfs_writepage(struct page *page, struct writeback_control *wbc)
+static int adfs_writepages(struct address_space *mapping,
+		struct writeback_control *wbc)
 {
-	return block_write_full_page(page, adfs_get_block, wbc);
+	return mpage_writepages(mapping, wbc, adfs_get_block);
 }
 
 static int adfs_read_folio(struct file *file, struct folio *folio)
@@ -76,10 +78,11 @@ static const struct address_space_operations adfs_aops = {
 	.dirty_folio	= block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
 	.read_folio	= adfs_read_folio,
-	.writepage	= adfs_writepage,
+	.writepages	= adfs_writepages,
 	.write_begin	= adfs_write_begin,
 	.write_end	= generic_write_end,
-	.bmap		= _adfs_bmap
+	.migrate_folio	= buffer_migrate_folio,
+	.bmap		= _adfs_bmap,
 };
 
 /*
diff --git a/fs/afs/Makefile b/fs/afs/Makefile
index e8956b65d7ff..dcdc0f1bb76f 100644
--- a/fs/afs/Makefile
+++ b/fs/afs/Makefile
@@ -5,6 +5,7 @@
 
 kafs-y := \
 	addr_list.o \
+	addr_prefs.o \
 	callback.o \
 	cell.o \
 	cmservice.o \
@@ -27,6 +28,7 @@ kafs-y := \
 	server.o \
 	server_list.o \
 	super.o \
+	validation.o \
 	vlclient.o \
 	vl_alias.o \
 	vl_list.o \
diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c
index de1ae0bead3b..6d42f85c6be5 100644
--- a/fs/afs/addr_list.c
+++ b/fs/afs/addr_list.c
@@ -13,26 +13,55 @@
 #include "internal.h"
 #include "afs_fs.h"
 
+static void afs_free_addrlist(struct rcu_head *rcu)
+{
+	struct afs_addr_list *alist = container_of(rcu, struct afs_addr_list, rcu);
+	unsigned int i;
+
+	for (i = 0; i < alist->nr_addrs; i++)
+		rxrpc_kernel_put_peer(alist->addrs[i].peer);
+	trace_afs_alist(alist->debug_id, refcount_read(&alist->usage), afs_alist_trace_free);
+	kfree(alist);
+}
+
 /*
  * Release an address list.
  */
-void afs_put_addrlist(struct afs_addr_list *alist)
+void afs_put_addrlist(struct afs_addr_list *alist, enum afs_alist_trace reason)
+{
+	unsigned int debug_id;
+	bool dead;
+	int r;
+
+	if (!alist)
+		return;
+	debug_id = alist->debug_id;
+	dead = __refcount_dec_and_test(&alist->usage, &r);
+	trace_afs_alist(debug_id, r - 1, reason);
+	if (dead)
+		call_rcu(&alist->rcu, afs_free_addrlist);
+}
+
+struct afs_addr_list *afs_get_addrlist(struct afs_addr_list *alist, enum afs_alist_trace reason)
 {
-	if (alist && refcount_dec_and_test(&alist->usage))
-		kfree_rcu(alist, rcu);
+	int r;
+
+	if (alist) {
+		__refcount_inc(&alist->usage, &r);
+		trace_afs_alist(alist->debug_id, r + 1, reason);
+	}
+	return alist;
 }
 
 /*
  * Allocate an address list.
  */
-struct afs_addr_list *afs_alloc_addrlist(unsigned int nr,
-					 unsigned short service,
-					 unsigned short port)
+struct afs_addr_list *afs_alloc_addrlist(unsigned int nr)
 {
 	struct afs_addr_list *alist;
-	unsigned int i;
+	static atomic_t debug_id;
 
-	_enter("%u,%u,%u", nr, service, port);
+	_enter("%u", nr);
 
 	if (nr > AFS_MAX_ADDRESSES)
 		nr = AFS_MAX_ADDRESSES;
@@ -43,17 +72,8 @@ struct afs_addr_list *afs_alloc_addrlist(unsigned int nr,
 
 	refcount_set(&alist->usage, 1);
 	alist->max_addrs = nr;
-
-	for (i = 0; i < nr; i++) {
-		struct sockaddr_rxrpc *srx = &alist->addrs[i];
-		srx->srx_family			= AF_RXRPC;
-		srx->srx_service		= service;
-		srx->transport_type		= SOCK_DGRAM;
-		srx->transport_len		= sizeof(srx->transport.sin6);
-		srx->transport.sin6.sin6_family	= AF_INET6;
-		srx->transport.sin6.sin6_port	= htons(port);
-	}
-
+	alist->debug_id = atomic_inc_return(&debug_id);
+	trace_afs_alist(alist->debug_id, 1, afs_alist_trace_alloc);
 	return alist;
 }
 
@@ -126,7 +146,7 @@ struct afs_vlserver_list *afs_parse_text_addrs(struct afs_net *net,
 	if (!vllist->servers[0].server)
 		goto error_vl;
 
-	alist = afs_alloc_addrlist(nr, service, AFS_VL_PORT);
+	alist = afs_alloc_addrlist(nr);
 	if (!alist)
 		goto error;
 
@@ -197,9 +217,11 @@ struct afs_vlserver_list *afs_parse_text_addrs(struct afs_net *net,
 		}
 
 		if (family == AF_INET)
-			afs_merge_fs_addr4(alist, x[0], xport);
+			ret = afs_merge_fs_addr4(net, alist, x[0], xport);
 		else
-			afs_merge_fs_addr6(alist, x, xport);
+			ret = afs_merge_fs_addr6(net, alist, x, xport);
+		if (ret < 0)
+			goto error;
 
 	} while (p < end);
 
@@ -216,26 +238,13 @@ bad_address:
 	       problem, p - text, (int)len, (int)len, text);
 	ret = -EINVAL;
 error:
-	afs_put_addrlist(alist);
+	afs_put_addrlist(alist, afs_alist_trace_put_parse_error);
 error_vl:
 	afs_put_vlserverlist(net, vllist);
 	return ERR_PTR(ret);
 }
 
 /*
- * Compare old and new address lists to see if there's been any change.
- * - How to do this in better than O(Nlog(N)) time?
- *   - We don't really want to sort the address list, but would rather take the
- *     list as we got it so as not to undo record rotation by the DNS server.
- */
-#if 0
-static int afs_cmp_addr_list(const struct afs_addr_list *a1,
-			     const struct afs_addr_list *a2)
-{
-}
-#endif
-
-/*
  * Perform a DNS query for VL servers and build a up an address list.
  */
 struct afs_vlserver_list *afs_dns_query(struct afs_cell *cell, time64_t *_expiry)
@@ -271,25 +280,33 @@ struct afs_vlserver_list *afs_dns_query(struct afs_cell *cell, time64_t *_expiry
 /*
  * Merge an IPv4 entry into a fileserver address list.
  */
-void afs_merge_fs_addr4(struct afs_addr_list *alist, __be32 xdr, u16 port)
+int afs_merge_fs_addr4(struct afs_net *net, struct afs_addr_list *alist,
+		       __be32 xdr, u16 port)
 {
-	struct sockaddr_rxrpc *srx;
-	u32 addr = ntohl(xdr);
+	struct sockaddr_rxrpc srx;
+	struct rxrpc_peer *peer;
 	int i;
 
 	if (alist->nr_addrs >= alist->max_addrs)
-		return;
+		return 0;
 
-	for (i = 0; i < alist->nr_ipv4; i++) {
-		struct sockaddr_in *a = &alist->addrs[i].transport.sin;
-		u32 a_addr = ntohl(a->sin_addr.s_addr);
-		u16 a_port = ntohs(a->sin_port);
+	srx.srx_family = AF_RXRPC;
+	srx.transport_type = SOCK_DGRAM;
+	srx.transport_len = sizeof(srx.transport.sin);
+	srx.transport.sin.sin_family = AF_INET;
+	srx.transport.sin.sin_port = htons(port);
+	srx.transport.sin.sin_addr.s_addr = xdr;
 
-		if (addr == a_addr && port == a_port)
-			return;
-		if (addr == a_addr && port < a_port)
-			break;
-		if (addr < a_addr)
+	peer = rxrpc_kernel_lookup_peer(net->socket, &srx, GFP_KERNEL);
+	if (!peer)
+		return -ENOMEM;
+
+	for (i = 0; i < alist->nr_ipv4; i++) {
+		if (peer == alist->addrs[i].peer) {
+			rxrpc_kernel_put_peer(peer);
+			return 0;
+		}
+		if (peer <= alist->addrs[i].peer)
 			break;
 	}
 
@@ -298,38 +315,42 @@ void afs_merge_fs_addr4(struct afs_addr_list *alist, __be32 xdr, u16 port)
 			alist->addrs + i,
 			sizeof(alist->addrs[0]) * (alist->nr_addrs - i));
 
-	srx = &alist->addrs[i];
-	srx->srx_family = AF_RXRPC;
-	srx->transport_type = SOCK_DGRAM;
-	srx->transport_len = sizeof(srx->transport.sin);
-	srx->transport.sin.sin_family = AF_INET;
-	srx->transport.sin.sin_port = htons(port);
-	srx->transport.sin.sin_addr.s_addr = xdr;
+	alist->addrs[i].peer = peer;
 	alist->nr_ipv4++;
 	alist->nr_addrs++;
+	return 0;
 }
 
 /*
  * Merge an IPv6 entry into a fileserver address list.
  */
-void afs_merge_fs_addr6(struct afs_addr_list *alist, __be32 *xdr, u16 port)
+int afs_merge_fs_addr6(struct afs_net *net, struct afs_addr_list *alist,
+		       __be32 *xdr, u16 port)
 {
-	struct sockaddr_rxrpc *srx;
-	int i, diff;
+	struct sockaddr_rxrpc srx;
+	struct rxrpc_peer *peer;
+	int i;
 
 	if (alist->nr_addrs >= alist->max_addrs)
-		return;
+		return 0;
 
-	for (i = alist->nr_ipv4; i < alist->nr_addrs; i++) {
-		struct sockaddr_in6 *a = &alist->addrs[i].transport.sin6;
-		u16 a_port = ntohs(a->sin6_port);
+	srx.srx_family = AF_RXRPC;
+	srx.transport_type = SOCK_DGRAM;
+	srx.transport_len = sizeof(srx.transport.sin6);
+	srx.transport.sin6.sin6_family = AF_INET6;
+	srx.transport.sin6.sin6_port = htons(port);
+	memcpy(&srx.transport.sin6.sin6_addr, xdr, 16);
 
-		diff = memcmp(xdr, &a->sin6_addr, 16);
-		if (diff == 0 && port == a_port)
-			return;
-		if (diff == 0 && port < a_port)
-			break;
-		if (diff < 0)
+	peer = rxrpc_kernel_lookup_peer(net->socket, &srx, GFP_KERNEL);
+	if (!peer)
+		return -ENOMEM;
+
+	for (i = alist->nr_ipv4; i < alist->nr_addrs; i++) {
+		if (peer == alist->addrs[i].peer) {
+			rxrpc_kernel_put_peer(peer);
+			return 0;
+		}
+		if (peer <= alist->addrs[i].peer)
 			break;
 	}
 
@@ -337,68 +358,7 @@ void afs_merge_fs_addr6(struct afs_addr_list *alist, __be32 *xdr, u16 port)
 		memmove(alist->addrs + i + 1,
 			alist->addrs + i,
 			sizeof(alist->addrs[0]) * (alist->nr_addrs - i));
-
-	srx = &alist->addrs[i];
-	srx->srx_family = AF_RXRPC;
-	srx->transport_type = SOCK_DGRAM;
-	srx->transport_len = sizeof(srx->transport.sin6);
-	srx->transport.sin6.sin6_family = AF_INET6;
-	srx->transport.sin6.sin6_port = htons(port);
-	memcpy(&srx->transport.sin6.sin6_addr, xdr, 16);
+	alist->addrs[i].peer = peer;
 	alist->nr_addrs++;
-}
-
-/*
- * Get an address to try.
- */
-bool afs_iterate_addresses(struct afs_addr_cursor *ac)
-{
-	unsigned long set, failed;
-	int index;
-
-	if (!ac->alist)
-		return false;
-
-	set = ac->alist->responded;
-	failed = ac->alist->failed;
-	_enter("%lx-%lx-%lx,%d", set, failed, ac->tried, ac->index);
-
-	ac->nr_iterations++;
-
-	set &= ~(failed | ac->tried);
-
-	if (!set)
-		return false;
-
-	index = READ_ONCE(ac->alist->preferred);
-	if (test_bit(index, &set))
-		goto selected;
-
-	index = __ffs(set);
-
-selected:
-	ac->index = index;
-	set_bit(index, &ac->tried);
-	ac->responded = false;
-	return true;
-}
-
-/*
- * Release an address list cursor.
- */
-int afs_end_cursor(struct afs_addr_cursor *ac)
-{
-	struct afs_addr_list *alist;
-
-	alist = ac->alist;
-	if (alist) {
-		if (ac->responded &&
-		    ac->index != alist->preferred &&
-		    test_bit(ac->alist->preferred, &ac->tried))
-			WRITE_ONCE(alist->preferred, ac->index);
-		afs_put_addrlist(alist);
-		ac->alist = NULL;
-	}
-
-	return ac->error;
+	return 0;
 }
diff --git a/fs/afs/addr_prefs.c b/fs/afs/addr_prefs.c
new file mode 100644
index 000000000000..a189ff8a5034
--- /dev/null
+++ b/fs/afs/addr_prefs.c
@@ -0,0 +1,531 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Address preferences management
+ *
+ * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": addr_prefs: " fmt
+#include <linux/slab.h>
+#include <linux/ctype.h>
+#include <linux/inet.h>
+#include <linux/seq_file.h>
+#include <keys/rxrpc-type.h>
+#include "internal.h"
+
+static inline struct afs_net *afs_seq2net_single(struct seq_file *m)
+{
+	return afs_net(seq_file_single_net(m));
+}
+
+/*
+ * Split a NUL-terminated string up to the first newline around spaces.  The
+ * source string will be modified to have NUL-terminations inserted.
+ */
+static int afs_split_string(char **pbuf, char *strv[], unsigned int maxstrv)
+{
+	unsigned int count = 0;
+	char *p = *pbuf;
+
+	maxstrv--; /* Allow for terminal NULL */
+	for (;;) {
+		/* Skip over spaces */
+		while (isspace(*p)) {
+			if (*p == '\n') {
+				p++;
+				break;
+			}
+			p++;
+		}
+		if (!*p)
+			break;
+
+		/* Mark start of word */
+		if (count >= maxstrv) {
+			pr_warn("Too many elements in string\n");
+			return -EINVAL;
+		}
+		strv[count++] = p;
+
+		/* Skip over word */
+		while (!isspace(*p))
+			p++;
+		if (!*p)
+			break;
+
+		/* Mark end of word */
+		if (*p == '\n') {
+			*p++ = 0;
+			break;
+		}
+		*p++ = 0;
+	}
+
+	*pbuf = p;
+	strv[count] = NULL;
+	return count;
+}
+
+/*
+ * Parse an address with an optional subnet mask.
+ */
+static int afs_parse_address(char *p, struct afs_addr_preference *pref)
+{
+	const char *stop;
+	unsigned long mask, tmp;
+	char *end = p + strlen(p);
+	bool bracket = false;
+
+	if (*p == '[') {
+		p++;
+		bracket = true;
+	}
+
+#if 0
+	if (*p == '[') {
+		p++;
+		q = memchr(p, ']', end - p);
+		if (!q) {
+			pr_warn("Can't find closing ']'\n");
+			return -EINVAL;
+		}
+	} else {
+		for (q = p; q < end; q++)
+			if (*q == '/')
+				break;
+	}
+#endif
+
+	if (in4_pton(p, end - p, (u8 *)&pref->ipv4_addr, -1, &stop)) {
+		pref->family = AF_INET;
+		mask = 32;
+	} else if (in6_pton(p, end - p, (u8 *)&pref->ipv6_addr, -1, &stop)) {
+		pref->family = AF_INET6;
+		mask = 128;
+	} else {
+		pr_warn("Can't determine address family\n");
+		return -EINVAL;
+	}
+
+	p = (char *)stop;
+	if (bracket) {
+		if (*p != ']') {
+			pr_warn("Can't find closing ']'\n");
+			return -EINVAL;
+		}
+		p++;
+	}
+
+	if (*p == '/') {
+		p++;
+		tmp = simple_strtoul(p, &p, 10);
+		if (tmp > mask) {
+			pr_warn("Subnet mask too large\n");
+			return -EINVAL;
+		}
+		if (tmp == 0) {
+			pr_warn("Subnet mask too small\n");
+			return -EINVAL;
+		}
+		mask = tmp;
+	}
+
+	if (*p) {
+		pr_warn("Invalid address\n");
+		return -EINVAL;
+	}
+
+	pref->subnet_mask = mask;
+	return 0;
+}
+
+enum cmp_ret {
+	CONTINUE_SEARCH,
+	INSERT_HERE,
+	EXACT_MATCH,
+	SUBNET_MATCH,
+};
+
+/*
+ * See if a candidate address matches a listed address.
+ */
+static enum cmp_ret afs_cmp_address_pref(const struct afs_addr_preference *a,
+					 const struct afs_addr_preference *b)
+{
+	int subnet = min(a->subnet_mask, b->subnet_mask);
+	const __be32 *pa, *pb;
+	u32 mask, na, nb;
+	int diff;
+
+	if (a->family != b->family)
+		return INSERT_HERE;
+
+	switch (a->family) {
+	case AF_INET6:
+		pa = a->ipv6_addr.s6_addr32;
+		pb = b->ipv6_addr.s6_addr32;
+		break;
+	case AF_INET:
+		pa = &a->ipv4_addr.s_addr;
+		pb = &b->ipv4_addr.s_addr;
+		break;
+	}
+
+	while (subnet > 32) {
+		diff = ntohl(*pa++) - ntohl(*pb++);
+		if (diff < 0)
+			return INSERT_HERE; /* a<b */
+		if (diff > 0)
+			return CONTINUE_SEARCH; /* a>b */
+		subnet -= 32;
+	}
+
+	if (subnet == 0)
+		return EXACT_MATCH;
+
+	mask = 0xffffffffU << (32 - subnet);
+	na = ntohl(*pa);
+	nb = ntohl(*pb);
+	diff = (na & mask) - (nb & mask);
+	//kdebug("diff %08x %08x %08x %d", na, nb, mask, diff);
+	if (diff < 0)
+		return INSERT_HERE; /* a<b */
+	if (diff > 0)
+		return CONTINUE_SEARCH; /* a>b */
+	if (a->subnet_mask == b->subnet_mask)
+		return EXACT_MATCH;
+	if (a->subnet_mask > b->subnet_mask)
+		return SUBNET_MATCH; /* a binds tighter than b */
+	return CONTINUE_SEARCH; /* b binds tighter than a */
+}
+
+/*
+ * Insert an address preference.
+ */
+static int afs_insert_address_pref(struct afs_addr_preference_list **_preflist,
+				   struct afs_addr_preference *pref,
+				   int index)
+{
+	struct afs_addr_preference_list *preflist = *_preflist, *old = preflist;
+	size_t size, max_prefs;
+
+	_enter("{%u/%u/%u},%u", preflist->ipv6_off, preflist->nr, preflist->max_prefs, index);
+
+	if (preflist->nr == 255)
+		return -ENOSPC;
+	if (preflist->nr >= preflist->max_prefs) {
+		max_prefs = preflist->max_prefs + 1;
+		size = struct_size(preflist, prefs, max_prefs);
+		size = roundup_pow_of_two(size);
+		max_prefs = min_t(size_t, (size - sizeof(*preflist)) / sizeof(*pref), 255);
+		preflist = kmalloc(size, GFP_KERNEL);
+		if (!preflist)
+			return -ENOMEM;
+		*preflist = **_preflist;
+		preflist->max_prefs = max_prefs;
+		*_preflist = preflist;
+
+		if (index < preflist->nr)
+			memcpy(preflist->prefs + index + 1, old->prefs + index,
+			       sizeof(*pref) * (preflist->nr - index));
+		if (index > 0)
+			memcpy(preflist->prefs, old->prefs, sizeof(*pref) * index);
+	} else {
+		if (index < preflist->nr)
+			memmove(preflist->prefs + index + 1, preflist->prefs + index,
+			       sizeof(*pref) * (preflist->nr - index));
+	}
+
+	preflist->prefs[index] = *pref;
+	preflist->nr++;
+	if (pref->family == AF_INET)
+		preflist->ipv6_off++;
+	return 0;
+}
+
+/*
+ * Add an address preference.
+ *	echo "add <proto> <IP>[/<mask>] <prior>" >/proc/fs/afs/addr_prefs
+ */
+static int afs_add_address_pref(struct afs_net *net, struct afs_addr_preference_list **_preflist,
+				int argc, char **argv)
+{
+	struct afs_addr_preference_list *preflist = *_preflist;
+	struct afs_addr_preference pref;
+	enum cmp_ret cmp;
+	int ret, i, stop;
+
+	if (argc != 3) {
+		pr_warn("Wrong number of params\n");
+		return -EINVAL;
+	}
+
+	if (strcmp(argv[0], "udp") != 0) {
+		pr_warn("Unsupported protocol\n");
+		return -EINVAL;
+	}
+
+	ret = afs_parse_address(argv[1], &pref);
+	if (ret < 0)
+		return ret;
+
+	ret = kstrtou16(argv[2], 10, &pref.prio);
+	if (ret < 0) {
+		pr_warn("Invalid priority\n");
+		return ret;
+	}
+
+	if (pref.family == AF_INET) {
+		i = 0;
+		stop = preflist->ipv6_off;
+	} else {
+		i = preflist->ipv6_off;
+		stop = preflist->nr;
+	}
+
+	for (; i < stop; i++) {
+		cmp = afs_cmp_address_pref(&pref, &preflist->prefs[i]);
+		switch (cmp) {
+		case CONTINUE_SEARCH:
+			continue;
+		case INSERT_HERE:
+		case SUBNET_MATCH:
+			return afs_insert_address_pref(_preflist, &pref, i);
+		case EXACT_MATCH:
+			preflist->prefs[i].prio = pref.prio;
+			return 0;
+		}
+	}
+
+	return afs_insert_address_pref(_preflist, &pref, i);
+}
+
+/*
+ * Delete an address preference.
+ */
+static int afs_delete_address_pref(struct afs_addr_preference_list **_preflist,
+				   int index)
+{
+	struct afs_addr_preference_list *preflist = *_preflist;
+
+	_enter("{%u/%u/%u},%u", preflist->ipv6_off, preflist->nr, preflist->max_prefs, index);
+
+	if (preflist->nr == 0)
+		return -ENOENT;
+
+	if (index < preflist->nr - 1)
+		memmove(preflist->prefs + index, preflist->prefs + index + 1,
+			sizeof(preflist->prefs[0]) * (preflist->nr - index - 1));
+
+	if (index < preflist->ipv6_off)
+		preflist->ipv6_off--;
+	preflist->nr--;
+	return 0;
+}
+
+/*
+ * Delete an address preference.
+ *	echo "del <proto> <IP>[/<mask>]" >/proc/fs/afs/addr_prefs
+ */
+static int afs_del_address_pref(struct afs_net *net, struct afs_addr_preference_list **_preflist,
+				int argc, char **argv)
+{
+	struct afs_addr_preference_list *preflist = *_preflist;
+	struct afs_addr_preference pref;
+	enum cmp_ret cmp;
+	int ret, i, stop;
+
+	if (argc != 2) {
+		pr_warn("Wrong number of params\n");
+		return -EINVAL;
+	}
+
+	if (strcmp(argv[0], "udp") != 0) {
+		pr_warn("Unsupported protocol\n");
+		return -EINVAL;
+	}
+
+	ret = afs_parse_address(argv[1], &pref);
+	if (ret < 0)
+		return ret;
+
+	if (pref.family == AF_INET) {
+		i = 0;
+		stop = preflist->ipv6_off;
+	} else {
+		i = preflist->ipv6_off;
+		stop = preflist->nr;
+	}
+
+	for (; i < stop; i++) {
+		cmp = afs_cmp_address_pref(&pref, &preflist->prefs[i]);
+		switch (cmp) {
+		case CONTINUE_SEARCH:
+			continue;
+		case INSERT_HERE:
+		case SUBNET_MATCH:
+			return 0;
+		case EXACT_MATCH:
+			return afs_delete_address_pref(_preflist, i);
+		}
+	}
+
+	return -ENOANO;
+}
+
+/*
+ * Handle writes to /proc/fs/afs/addr_prefs
+ */
+int afs_proc_addr_prefs_write(struct file *file, char *buf, size_t size)
+{
+	struct afs_addr_preference_list *preflist, *old;
+	struct seq_file *m = file->private_data;
+	struct afs_net *net = afs_seq2net_single(m);
+	size_t psize;
+	char *argv[5];
+	int ret, argc, max_prefs;
+
+	inode_lock(file_inode(file));
+
+	/* Allocate a candidate new list and initialise it from the old. */
+	old = rcu_dereference_protected(net->address_prefs,
+					lockdep_is_held(&file_inode(file)->i_rwsem));
+
+	if (old)
+		max_prefs = old->nr + 1;
+	else
+		max_prefs = 1;
+
+	psize = struct_size(old, prefs, max_prefs);
+	psize = roundup_pow_of_two(psize);
+	max_prefs = min_t(size_t, (psize - sizeof(*old)) / sizeof(old->prefs[0]), 255);
+
+	ret = -ENOMEM;
+	preflist = kmalloc(struct_size(preflist, prefs, max_prefs), GFP_KERNEL);
+	if (!preflist)
+		goto done;
+
+	if (old)
+		memcpy(preflist, old, struct_size(preflist, prefs, old->nr));
+	else
+		memset(preflist, 0, sizeof(*preflist));
+	preflist->max_prefs = max_prefs;
+
+	do {
+		argc = afs_split_string(&buf, argv, ARRAY_SIZE(argv));
+		if (argc < 0)
+			return argc;
+		if (argc < 2)
+			goto inval;
+
+		if (strcmp(argv[0], "add") == 0)
+			ret = afs_add_address_pref(net, &preflist, argc - 1, argv + 1);
+		else if (strcmp(argv[0], "del") == 0)
+			ret = afs_del_address_pref(net, &preflist, argc - 1, argv + 1);
+		else
+			goto inval;
+		if (ret < 0)
+			goto done;
+	} while (*buf);
+
+	preflist->version++;
+	rcu_assign_pointer(net->address_prefs, preflist);
+	/* Store prefs before version */
+	smp_store_release(&net->address_pref_version, preflist->version);
+	kfree_rcu(old, rcu);
+	preflist = NULL;
+	ret = 0;
+
+done:
+	kfree(preflist);
+	inode_unlock(file_inode(file));
+	_leave(" = %d", ret);
+	return ret;
+
+inval:
+	pr_warn("Invalid Command\n");
+	ret = -EINVAL;
+	goto done;
+}
+
+/*
+ * Mark the priorities on an address list if the address preferences table has
+ * changed.  The caller must hold the RCU read lock.
+ */
+void afs_get_address_preferences_rcu(struct afs_net *net, struct afs_addr_list *alist)
+{
+	const struct afs_addr_preference_list *preflist =
+		rcu_dereference(net->address_prefs);
+	const struct sockaddr_in6 *sin6;
+	const struct sockaddr_in *sin;
+	const struct sockaddr *sa;
+	struct afs_addr_preference test;
+	enum cmp_ret cmp;
+	int i, j;
+
+	if (!preflist || !preflist->nr || !alist->nr_addrs ||
+	    smp_load_acquire(&alist->addr_pref_version) == preflist->version)
+		return;
+
+	test.family = AF_INET;
+	test.subnet_mask = 32;
+	test.prio = 0;
+	for (i = 0; i < alist->nr_ipv4; i++) {
+		sa = rxrpc_kernel_remote_addr(alist->addrs[i].peer);
+		sin = (const struct sockaddr_in *)sa;
+		test.ipv4_addr = sin->sin_addr;
+		for (j = 0; j < preflist->ipv6_off; j++) {
+			cmp = afs_cmp_address_pref(&test, &preflist->prefs[j]);
+			switch (cmp) {
+			case CONTINUE_SEARCH:
+				continue;
+			case INSERT_HERE:
+				break;
+			case EXACT_MATCH:
+			case SUBNET_MATCH:
+				WRITE_ONCE(alist->addrs[i].prio, preflist->prefs[j].prio);
+				break;
+			}
+		}
+	}
+
+	test.family = AF_INET6;
+	test.subnet_mask = 128;
+	test.prio = 0;
+	for (; i < alist->nr_addrs; i++) {
+		sa = rxrpc_kernel_remote_addr(alist->addrs[i].peer);
+		sin6 = (const struct sockaddr_in6 *)sa;
+		test.ipv6_addr = sin6->sin6_addr;
+		for (j = preflist->ipv6_off; j < preflist->nr; j++) {
+			cmp = afs_cmp_address_pref(&test, &preflist->prefs[j]);
+			switch (cmp) {
+			case CONTINUE_SEARCH:
+				continue;
+			case INSERT_HERE:
+				break;
+			case EXACT_MATCH:
+			case SUBNET_MATCH:
+				WRITE_ONCE(alist->addrs[i].prio, preflist->prefs[j].prio);
+				break;
+			}
+		}
+	}
+
+	smp_store_release(&alist->addr_pref_version, preflist->version);
+}
+
+/*
+ * Mark the priorities on an address list if the address preferences table has
+ * changed.  Avoid taking the RCU read lock if we can.
+ */
+void afs_get_address_preferences(struct afs_net *net, struct afs_addr_list *alist)
+{
+	if (!net->address_prefs ||
+	    /* Load version before prefs */
+	    smp_load_acquire(&net->address_pref_version) == alist->addr_pref_version)
+		return;
+
+	rcu_read_lock();
+	afs_get_address_preferences_rcu(net, alist);
+	rcu_read_unlock();
+}
diff --git a/fs/afs/afs.h b/fs/afs/afs.h
index 81815724db6c..b488072aee87 100644
--- a/fs/afs/afs.h
+++ b/fs/afs/afs.h
@@ -165,7 +165,8 @@ struct afs_status_cb {
  * AFS volume synchronisation information
  */
 struct afs_volsync {
-	time64_t		creation;	/* volume creation time */
+	time64_t		creation;	/* Volume creation time (or TIME64_MIN) */
+	time64_t		update;		/* Volume update time (or TIME64_MIN) */
 };
 
 /*
diff --git a/fs/afs/callback.c b/fs/afs/callback.c
index a484fa642808..99b2c8172021 100644
--- a/fs/afs/callback.c
+++ b/fs/afs/callback.c
@@ -33,22 +33,20 @@ void afs_invalidate_mmap_work(struct work_struct *work)
 	unmap_mapping_pages(vnode->netfs.inode.i_mapping, 0, 0, false);
 }
 
-void afs_server_init_callback_work(struct work_struct *work)
+static void afs_volume_init_callback(struct afs_volume *volume)
 {
-	struct afs_server *server = container_of(work, struct afs_server, initcb_work);
 	struct afs_vnode *vnode;
-	struct afs_cell *cell = server->cell;
 
-	down_read(&cell->fs_open_mmaps_lock);
+	down_read(&volume->open_mmaps_lock);
 
-	list_for_each_entry(vnode, &cell->fs_open_mmaps, cb_mmap_link) {
-		if (vnode->cb_server == server) {
-			clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
+	list_for_each_entry(vnode, &volume->open_mmaps, cb_mmap_link) {
+		if (vnode->cb_v_check != atomic_read(&volume->cb_v_break)) {
+			atomic64_set(&vnode->cb_expires_at, AFS_NO_CB_PROMISE);
 			queue_work(system_unbound_wq, &vnode->cb_work);
 		}
 	}
 
-	up_read(&cell->fs_open_mmaps_lock);
+	up_read(&volume->open_mmaps_lock);
 }
 
 /*
@@ -57,15 +55,20 @@ void afs_server_init_callback_work(struct work_struct *work)
  */
 void afs_init_callback_state(struct afs_server *server)
 {
-	rcu_read_lock();
-	do {
-		server->cb_s_break++;
-		atomic_inc(&server->cell->fs_s_break);
-		if (!list_empty(&server->cell->fs_open_mmaps))
-			queue_work(system_unbound_wq, &server->initcb_work);
+	struct afs_server_entry *se;
 
-	} while ((server = rcu_dereference(server->uuid_next)));
-	rcu_read_unlock();
+	down_read(&server->cell->vs_lock);
+
+	list_for_each_entry(se, &server->volumes, slink) {
+		se->cb_expires_at = AFS_NO_CB_PROMISE;
+		se->volume->cb_expires_at = AFS_NO_CB_PROMISE;
+		trace_afs_cb_v_break(se->volume->vid, atomic_read(&se->volume->cb_v_break),
+				     afs_cb_break_for_s_reinit);
+		if (!list_empty(&se->volume->open_mmaps))
+			afs_volume_init_callback(se->volume);
+	}
+
+	up_read(&server->cell->vs_lock);
 }
 
 /*
@@ -76,9 +79,9 @@ void __afs_break_callback(struct afs_vnode *vnode, enum afs_cb_break_reason reas
 	_enter("");
 
 	clear_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags);
-	if (test_and_clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
+	if (atomic64_xchg(&vnode->cb_expires_at, AFS_NO_CB_PROMISE) != AFS_NO_CB_PROMISE) {
 		vnode->cb_break++;
-		vnode->cb_v_break = vnode->volume->cb_v_break;
+		vnode->cb_v_check = atomic_read(&vnode->volume->cb_v_break);
 		afs_clear_permits(vnode);
 
 		if (vnode->lock_state == AFS_VNODE_LOCK_WAITING_FOR_CB)
@@ -110,13 +113,14 @@ static struct afs_volume *afs_lookup_volume_rcu(struct afs_cell *cell,
 {
 	struct afs_volume *volume = NULL;
 	struct rb_node *p;
-	int seq = 0;
+	int seq = 1;
 
-	do {
+	for (;;) {
 		/* Unfortunately, rbtree walking doesn't give reliable results
 		 * under just the RCU read lock, so we have to check for
 		 * changes.
 		 */
+		seq++; /* 2 on the 1st/lockless path, otherwise odd */
 		read_seqbegin_or_lock(&cell->volume_lock, &seq);
 
 		p = rcu_dereference_raw(cell->volumes.rb_node);
@@ -132,35 +136,63 @@ static struct afs_volume *afs_lookup_volume_rcu(struct afs_cell *cell,
 			volume = NULL;
 		}
 
-	} while (need_seqretry(&cell->volume_lock, seq));
+		if (volume && afs_try_get_volume(volume, afs_volume_trace_get_callback))
+			break;
+		if (!need_seqretry(&cell->volume_lock, seq))
+			break;
+		seq |= 1; /* Want a lock next time */
+	}
 
 	done_seqretry(&cell->volume_lock, seq);
 	return volume;
 }
 
 /*
+ * Allow the fileserver to break callbacks at the volume-level.  This is
+ * typically done when, for example, a R/W volume is snapshotted to a R/O
+ * volume (the only way to change an R/O volume).  It may also, however, happen
+ * when a volserver takes control of a volume (offlining it, moving it, etc.).
+ *
+ * Every file in that volume will need to be reevaluated.
+ */
+static void afs_break_volume_callback(struct afs_server *server,
+				      struct afs_volume *volume)
+	__releases(RCU)
+{
+	struct afs_server_list *slist = rcu_dereference(volume->servers);
+	unsigned int i, cb_v_break;
+
+	write_lock(&volume->cb_v_break_lock);
+
+	for (i = 0; i < slist->nr_servers; i++)
+		if (slist->servers[i].server == server)
+			slist->servers[i].cb_expires_at = AFS_NO_CB_PROMISE;
+	volume->cb_expires_at = AFS_NO_CB_PROMISE;
+
+	cb_v_break = atomic_inc_return_release(&volume->cb_v_break);
+	trace_afs_cb_v_break(volume->vid, cb_v_break, afs_cb_break_for_volume_callback);
+
+	write_unlock(&volume->cb_v_break_lock);
+	rcu_read_unlock();
+
+	if (!list_empty(&volume->open_mmaps))
+		afs_volume_init_callback(volume);
+}
+
+/*
  * allow the fileserver to explicitly break one callback
  * - happens when
  *   - the backing file is changed
  *   - a lock is released
  */
-static void afs_break_one_callback(struct afs_volume *volume,
+static void afs_break_one_callback(struct afs_server *server,
+				   struct afs_volume *volume,
 				   struct afs_fid *fid)
 {
 	struct super_block *sb;
 	struct afs_vnode *vnode;
 	struct inode *inode;
 
-	if (fid->vnode == 0 && fid->unique == 0) {
-		/* The callback break applies to an entire volume. */
-		write_lock(&volume->cb_v_break_lock);
-		volume->cb_v_break++;
-		trace_afs_cb_break(fid, volume->cb_v_break,
-				   afs_cb_break_for_volume_callback, false);
-		write_unlock(&volume->cb_v_break_lock);
-		return;
-	}
-
 	/* See if we can find a matching inode - even an I_NEW inode needs to
 	 * be marked as it can have its callback broken before we finish
 	 * setting up the local inode.
@@ -187,25 +219,35 @@ static void afs_break_some_callbacks(struct afs_server *server,
 	afs_volid_t vid = cbb->fid.vid;
 	size_t i;
 
+	rcu_read_lock();
 	volume = afs_lookup_volume_rcu(server->cell, vid);
+	if (cbb->fid.vnode == 0 && cbb->fid.unique == 0) {
+		afs_break_volume_callback(server, volume);
+		*_count -= 1;
+		if (*_count)
+			memmove(cbb, cbb + 1, sizeof(*cbb) * *_count);
+	} else {
+		/* TODO: Find all matching volumes if we couldn't match the server and
+		 * break them anyway.
+		 */
 
-	/* TODO: Find all matching volumes if we couldn't match the server and
-	 * break them anyway.
-	 */
-
-	for (i = *_count; i > 0; cbb++, i--) {
-		if (cbb->fid.vid == vid) {
-			_debug("- Fid { vl=%08llx n=%llu u=%u }",
-			       cbb->fid.vid,
-			       cbb->fid.vnode,
-			       cbb->fid.unique);
-			--*_count;
-			if (volume)
-				afs_break_one_callback(volume, &cbb->fid);
-		} else {
-			*residue++ = *cbb;
+		for (i = *_count; i > 0; cbb++, i--) {
+			if (cbb->fid.vid == vid) {
+				_debug("- Fid { vl=%08llx n=%llu u=%u }",
+				       cbb->fid.vid,
+				       cbb->fid.vnode,
+				       cbb->fid.unique);
+				--*_count;
+				if (volume)
+					afs_break_one_callback(server, volume, &cbb->fid);
+			} else {
+				*residue++ = *cbb;
+			}
 		}
+		rcu_read_unlock();
 	}
+
+	afs_put_volume(volume, afs_volume_trace_put_callback);
 }
 
 /*
@@ -218,11 +260,6 @@ void afs_break_callbacks(struct afs_server *server, size_t count,
 
 	ASSERT(server != NULL);
 
-	rcu_read_lock();
-
 	while (count > 0)
 		afs_break_some_callbacks(server, callbacks, &count);
-
-	rcu_read_unlock();
-	return;
 }
diff --git a/fs/afs/cell.c b/fs/afs/cell.c
index 988c2ac7cece..caa09875f520 100644
--- a/fs/afs/cell.c
+++ b/fs/afs/cell.c
@@ -161,13 +161,12 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net,
 	refcount_set(&cell->ref, 1);
 	atomic_set(&cell->active, 0);
 	INIT_WORK(&cell->manager, afs_manage_cell_work);
+	init_rwsem(&cell->vs_lock);
 	cell->volumes = RB_ROOT;
 	INIT_HLIST_HEAD(&cell->proc_volumes);
 	seqlock_init(&cell->volume_lock);
 	cell->fs_servers = RB_ROOT;
 	seqlock_init(&cell->fs_lock);
-	INIT_LIST_HEAD(&cell->fs_open_mmaps);
-	init_rwsem(&cell->fs_open_mmaps_lock);
 	rwlock_init(&cell->vl_servers_lock);
 	cell->flags = (1 << AFS_CELL_FL_CHECK_ALIAS);
 
@@ -409,10 +408,12 @@ static int afs_update_cell(struct afs_cell *cell)
 		if (ret == -ENOMEM)
 			goto out_wake;
 
-		ret = -ENOMEM;
 		vllist = afs_alloc_vlserver_list(0);
-		if (!vllist)
+		if (!vllist) {
+			if (ret >= 0)
+				ret = -ENOMEM;
 			goto out_wake;
+		}
 
 		switch (ret) {
 		case -ENODATA:
@@ -815,7 +816,7 @@ done:
 
 final_destruction:
 	/* The root volume is pinning the cell */
-	afs_put_volume(cell->net, cell->root_volume, afs_volume_trace_put_cell_root);
+	afs_put_volume(cell->root_volume, afs_volume_trace_put_cell_root);
 	cell->root_volume = NULL;
 	afs_put_cell(cell, afs_cell_trace_put_destroy);
 }
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index d4ddb20d6732..99a3f20bc786 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -146,10 +146,11 @@ static int afs_find_cm_server_by_peer(struct afs_call *call)
 {
 	struct sockaddr_rxrpc srx;
 	struct afs_server *server;
+	struct rxrpc_peer *peer;
 
-	rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx);
+	peer = rxrpc_kernel_get_call_peer(call->net->socket, call->rxcall);
 
-	server = afs_find_server(call->net, &srx);
+	server = afs_find_server(call->net, peer);
 	if (!server) {
 		trace_afs_cm_no_server(call, &srx);
 		return 0;
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 5219182e52e1..c14533ef108f 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -693,8 +693,9 @@ static void afs_do_lookup_success(struct afs_operation *op)
 			vp = &op->file[0];
 			abort_code = vp->scb.status.abort_code;
 			if (abort_code != 0) {
-				op->ac.abort_code = abort_code;
-				op->error = afs_abort_to_error(abort_code);
+				op->call_abort_code = abort_code;
+				afs_op_set_error(op, afs_abort_to_error(abort_code));
+				op->cumul_error.abort_code = abort_code;
 			}
 			break;
 
@@ -806,8 +807,8 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry,
 		cookie->fids[i].vid = dvnode->fid.vid;
 	cookie->ctx.actor = afs_lookup_filldir;
 	cookie->name = dentry->d_name;
-	cookie->nr_fids = 2; /* slot 0 is saved for the fid we actually want
-			      * and slot 1 for the directory */
+	cookie->nr_fids = 2; /* slot 1 is saved for the fid we actually want
+			      * and slot 0 for the directory */
 
 	if (!afs_server_supports_ibulk(dvnode))
 		cookie->one_only = true;
@@ -846,13 +847,14 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry,
 	_debug("nr_files %u", op->nr_files);
 
 	/* Need space for examining all the selected files */
-	op->error = -ENOMEM;
 	if (op->nr_files > 2) {
 		op->more_files = kvcalloc(op->nr_files - 2,
 					  sizeof(struct afs_vnode_param),
 					  GFP_KERNEL);
-		if (!op->more_files)
+		if (!op->more_files) {
+			afs_op_nomem(op);
 			goto out_op;
+		}
 
 		for (i = 2; i < op->nr_files; i++) {
 			vp = &op->more_files[i - 2];
@@ -878,14 +880,14 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry,
 	 * lookups contained therein are stored in the reply without aborting
 	 * the whole operation.
 	 */
-	op->error = -ENOTSUPP;
+	afs_op_set_error(op, -ENOTSUPP);
 	if (!cookie->one_only) {
 		op->ops = &afs_inline_bulk_status_operation;
 		afs_begin_vnode_operation(op);
 		afs_wait_for_operation(op);
 	}
 
-	if (op->error == -ENOTSUPP) {
+	if (afs_op_error(op) == -ENOTSUPP) {
 		/* We could try FS.BulkStatus next, but this aborts the entire
 		 * op if any of the lookups fails - so, for the moment, revert
 		 * to FS.FetchStatus for op->file[1].
@@ -895,10 +897,10 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry,
 		afs_begin_vnode_operation(op);
 		afs_wait_for_operation(op);
 	}
-	inode = ERR_PTR(op->error);
+	inode = ERR_PTR(afs_op_error(op));
 
 out_op:
-	if (op->error == 0) {
+	if (!afs_op_error(op)) {
 		inode = &op->file[1].vnode->netfs.inode;
 		op->file[1].vnode = NULL;
 	}
@@ -1116,7 +1118,12 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
 	dir = AFS_FS_I(d_inode(parent));
 
 	/* validate the parent directory */
-	afs_validate(dir, key);
+	ret = afs_validate(dir, key);
+	if (ret == -ERESTARTSYS) {
+		dput(parent);
+		key_put(key);
+		return ret;
+	}
 
 	if (test_bit(AFS_VNODE_DELETED, &dir->flags)) {
 		_debug("%pd: parent dir deleted", dentry);
@@ -1255,9 +1262,10 @@ void afs_check_for_remote_deletion(struct afs_operation *op)
 {
 	struct afs_vnode *vnode = op->file[0].vnode;
 
-	switch (op->ac.abort_code) {
+	switch (afs_op_abort_code(op)) {
 	case VNOVNODE:
 		set_bit(AFS_VNODE_DELETED, &vnode->flags);
+		clear_nlink(&vnode->netfs.inode);
 		afs_break_callback(vnode, afs_cb_break_for_deleted);
 	}
 }
@@ -1273,20 +1281,20 @@ static void afs_vnode_new_inode(struct afs_operation *op)
 
 	_enter("");
 
-	ASSERTCMP(op->error, ==, 0);
+	ASSERTCMP(afs_op_error(op), ==, 0);
 
 	inode = afs_iget(op, vp);
 	if (IS_ERR(inode)) {
 		/* ENOMEM or EINTR at a really inconvenient time - just abandon
 		 * the new directory on the server.
 		 */
-		op->error = PTR_ERR(inode);
+		afs_op_accumulate_error(op, PTR_ERR(inode), 0);
 		return;
 	}
 
 	vnode = AFS_FS_I(inode);
 	set_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags);
-	if (!op->error)
+	if (!afs_op_error(op))
 		afs_cache_permit(vnode, op->key, vnode->cb_break, &vp->scb);
 	d_instantiate(op->dentry, inode);
 }
@@ -1320,7 +1328,7 @@ static void afs_create_put(struct afs_operation *op)
 {
 	_enter("op=%08x", op->debug_id);
 
-	if (op->error)
+	if (afs_op_error(op))
 		d_drop(op->dentry);
 }
 
@@ -1373,7 +1381,7 @@ static void afs_dir_remove_subdir(struct dentry *dentry)
 
 		clear_nlink(&vnode->netfs.inode);
 		set_bit(AFS_VNODE_DELETED, &vnode->flags);
-		clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
+		atomic64_set(&vnode->cb_expires_at, AFS_NO_CB_PROMISE);
 		clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags);
 	}
 }
@@ -1480,7 +1488,7 @@ static void afs_dir_remove_link(struct afs_operation *op)
 	struct dentry *dentry = op->dentry;
 	int ret;
 
-	if (op->error != 0 ||
+	if (afs_op_error(op) ||
 	    (op->file[1].scb.have_status && op->file[1].scb.have_error))
 		return;
 	if (d_really_is_positive(dentry))
@@ -1504,10 +1512,10 @@ static void afs_dir_remove_link(struct afs_operation *op)
 
 		ret = afs_validate(vnode, op->key);
 		if (ret != -ESTALE)
-			op->error = ret;
+			afs_op_set_error(op, ret);
 	}
 
-	_debug("nlink %d [val %d]", vnode->netfs.inode.i_nlink, op->error);
+	_debug("nlink %d [val %d]", vnode->netfs.inode.i_nlink, afs_op_error(op));
 }
 
 static void afs_unlink_success(struct afs_operation *op)
@@ -1538,7 +1546,7 @@ static void afs_unlink_edit_dir(struct afs_operation *op)
 static void afs_unlink_put(struct afs_operation *op)
 {
 	_enter("op=%08x", op->debug_id);
-	if (op->unlink.need_rehash && op->error < 0 && op->error != -ENOENT)
+	if (op->unlink.need_rehash && afs_op_error(op) < 0 && afs_op_error(op) != -ENOENT)
 		d_rehash(op->dentry);
 }
 
@@ -1579,7 +1587,7 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry)
 	/* Try to make sure we have a callback promise on the victim. */
 	ret = afs_validate(vnode, op->key);
 	if (ret < 0) {
-		op->error = ret;
+		afs_op_set_error(op, ret);
 		goto error;
 	}
 
@@ -1588,7 +1596,7 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry)
 		spin_unlock(&dentry->d_lock);
 		/* Start asynchronous writeout of the inode */
 		write_inode_now(d_inode(dentry), 0);
-		op->error = afs_sillyrename(dvnode, vnode, dentry, op->key);
+		afs_op_set_error(op, afs_sillyrename(dvnode, vnode, dentry, op->key));
 		goto error;
 	}
 	if (!d_unhashed(dentry)) {
@@ -1609,7 +1617,7 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry)
 	/* If there was a conflict with a third party, check the status of the
 	 * unlinked vnode.
 	 */
-	if (op->error == 0 && (op->flags & AFS_OPERATION_DIR_CONFLICT)) {
+	if (afs_op_error(op) == 0 && (op->flags & AFS_OPERATION_DIR_CONFLICT)) {
 		op->file[1].update_ctime = false;
 		op->fetch_status.which = 1;
 		op->ops = &afs_fetch_status_operation;
@@ -1691,7 +1699,7 @@ static void afs_link_success(struct afs_operation *op)
 static void afs_link_put(struct afs_operation *op)
 {
 	_enter("op=%08x", op->debug_id);
-	if (op->error)
+	if (afs_op_error(op))
 		d_drop(op->dentry);
 }
 
@@ -1889,7 +1897,7 @@ static void afs_rename_put(struct afs_operation *op)
 	if (op->rename.rehash)
 		d_rehash(op->rename.rehash);
 	dput(op->rename.tmp);
-	if (op->error)
+	if (afs_op_error(op))
 		d_rehash(op->dentry);
 }
 
@@ -1934,7 +1942,7 @@ static int afs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 		return PTR_ERR(op);
 
 	ret = afs_validate(vnode, op->key);
-	op->error = ret;
+	afs_op_set_error(op, ret);
 	if (ret < 0)
 		goto error;
 
@@ -1971,7 +1979,7 @@ static int afs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 			op->rename.tmp = d_alloc(new_dentry->d_parent,
 						 &new_dentry->d_name);
 			if (!op->rename.tmp) {
-				op->error = -ENOMEM;
+				afs_op_nomem(op);
 				goto error;
 			}
 
@@ -1979,7 +1987,7 @@ static int afs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 					      AFS_FS_I(d_inode(new_dentry)),
 					      new_dentry, op->key);
 			if (ret) {
-				op->error = ret;
+				afs_op_set_error(op, ret);
 				goto error;
 			}
 
diff --git a/fs/afs/dir_silly.c b/fs/afs/dir_silly.c
index bb5807e87fa4..a1e581946b93 100644
--- a/fs/afs/dir_silly.c
+++ b/fs/afs/dir_silly.c
@@ -218,7 +218,7 @@ static int afs_do_silly_unlink(struct afs_vnode *dvnode, struct afs_vnode *vnode
 	/* If there was a conflict with a third party, check the status of the
 	 * unlinked vnode.
 	 */
-	if (op->error == 0 && (op->flags & AFS_OPERATION_DIR_CONFLICT)) {
+	if (op->cumul_error.error == 0 && (op->flags & AFS_OPERATION_DIR_CONFLICT)) {
 		op->file[1].update_ctime = false;
 		op->fetch_status.which = 1;
 		op->ops = &afs_fetch_status_operation;
diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index 4d04ef2d3ae7..1f656005018e 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -114,6 +114,7 @@ static int afs_probe_cell_name(struct dentry *dentry)
 	struct afs_net *net = afs_d2net(dentry);
 	const char *name = dentry->d_name.name;
 	size_t len = dentry->d_name.len;
+	char *result = NULL;
 	int ret;
 
 	/* Names prefixed with a dot are R/W mounts. */
@@ -131,9 +132,22 @@ static int afs_probe_cell_name(struct dentry *dentry)
 	}
 
 	ret = dns_query(net->net, "afsdb", name, len, "srv=1",
-			NULL, NULL, false);
-	if (ret == -ENODATA)
-		ret = -EDESTADDRREQ;
+			&result, NULL, false);
+	if (ret == -ENODATA || ret == -ENOKEY || ret == 0)
+		ret = -ENOENT;
+	if (ret > 0 && ret >= sizeof(struct dns_server_list_v1_header)) {
+		struct dns_server_list_v1_header *v1 = (void *)result;
+
+		if (v1->hdr.zero == 0 &&
+		    v1->hdr.content == DNS_PAYLOAD_IS_SERVER_LIST &&
+		    v1->hdr.version == 1 &&
+		    (v1->status != DNS_LOOKUP_GOOD &&
+		     v1->status != DNS_LOOKUP_GOOD_WITH_BAD))
+			return -ENOENT;
+
+	}
+
+	kfree(result);
 	return ret;
 }
 
@@ -252,20 +266,9 @@ static int afs_dynroot_d_revalidate(struct dentry *dentry, unsigned int flags)
 	return 1;
 }
 
-/*
- * Allow the VFS to enquire as to whether a dentry should be unhashed (mustn't
- * sleep)
- * - called from dput() when d_count is going to 0.
- * - return 1 to request dentry be unhashed, 0 otherwise
- */
-static int afs_dynroot_d_delete(const struct dentry *dentry)
-{
-	return d_really_is_positive(dentry);
-}
-
 const struct dentry_operations afs_dynroot_dentry_operations = {
 	.d_revalidate	= afs_dynroot_d_revalidate,
-	.d_delete	= afs_dynroot_d_delete,
+	.d_delete	= always_delete_dentry,
 	.d_release	= afs_d_release,
 	.d_automount	= afs_d_automount,
 };
diff --git a/fs/afs/file.c b/fs/afs/file.c
index d37dd201752b..30914e0d9cb2 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -243,12 +243,9 @@ static void afs_fetch_data_notify(struct afs_operation *op)
 {
 	struct afs_read *req = op->fetch.req;
 	struct netfs_io_subrequest *subreq = req->subreq;
-	int error = op->error;
+	int error = afs_op_error(op);
 
-	if (error == -ECONNABORTED)
-		error = afs_abort_to_error(op->ac.abort_code);
 	req->error = error;
-
 	if (subreq) {
 		__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
 		netfs_subreq_terminated(subreq, error ?: req->actual_len, false);
@@ -271,7 +268,7 @@ static void afs_fetch_data_success(struct afs_operation *op)
 
 static void afs_fetch_data_put(struct afs_operation *op)
 {
-	op->fetch.req->error = op->error;
+	op->fetch.req->error = afs_op_error(op);
 	afs_put_read(op->fetch.req);
 }
 
@@ -517,13 +514,12 @@ static bool afs_release_folio(struct folio *folio, gfp_t gfp)
 static void afs_add_open_mmap(struct afs_vnode *vnode)
 {
 	if (atomic_inc_return(&vnode->cb_nr_mmap) == 1) {
-		down_write(&vnode->volume->cell->fs_open_mmaps_lock);
+		down_write(&vnode->volume->open_mmaps_lock);
 
 		if (list_empty(&vnode->cb_mmap_link))
-			list_add_tail(&vnode->cb_mmap_link,
-				      &vnode->volume->cell->fs_open_mmaps);
+			list_add_tail(&vnode->cb_mmap_link, &vnode->volume->open_mmaps);
 
-		up_write(&vnode->volume->cell->fs_open_mmaps_lock);
+		up_write(&vnode->volume->open_mmaps_lock);
 	}
 }
 
@@ -532,12 +528,12 @@ static void afs_drop_open_mmap(struct afs_vnode *vnode)
 	if (!atomic_dec_and_test(&vnode->cb_nr_mmap))
 		return;
 
-	down_write(&vnode->volume->cell->fs_open_mmaps_lock);
+	down_write(&vnode->volume->open_mmaps_lock);
 
 	if (atomic_read(&vnode->cb_nr_mmap) == 0)
 		list_del_init(&vnode->cb_mmap_link);
 
-	up_write(&vnode->volume->cell->fs_open_mmaps_lock);
+	up_write(&vnode->volume->open_mmaps_lock);
 	flush_work(&vnode->cb_work);
 }
 
@@ -573,7 +569,7 @@ static vm_fault_t afs_vm_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pg
 {
 	struct afs_vnode *vnode = AFS_FS_I(file_inode(vmf->vma->vm_file));
 
-	if (afs_pagecache_valid(vnode))
+	if (afs_check_validity(vnode))
 		return filemap_map_pages(vmf, start_pgoff, end_pgoff);
 	return 0;
 }
diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c
index 7a3803ce3a22..3546b087e791 100644
--- a/fs/afs/fs_operation.c
+++ b/fs/afs/fs_operation.c
@@ -35,13 +35,15 @@ struct afs_operation *afs_alloc_operation(struct key *key, struct afs_volume *vo
 		key_get(key);
 	}
 
-	op->key		= key;
-	op->volume	= afs_get_volume(volume, afs_volume_trace_get_new_op);
-	op->net		= volume->cell->net;
-	op->cb_v_break	= volume->cb_v_break;
-	op->debug_id	= atomic_inc_return(&afs_operation_debug_counter);
-	op->error	= -EDESTADDRREQ;
-	op->ac.error	= SHRT_MAX;
+	op->key			= key;
+	op->volume		= afs_get_volume(volume, afs_volume_trace_get_new_op);
+	op->net			= volume->cell->net;
+	op->cb_v_break		= atomic_read(&volume->cb_v_break);
+	op->pre_volsync.creation = volume->creation_time;
+	op->pre_volsync.update	= volume->update_time;
+	op->debug_id		= atomic_inc_return(&afs_operation_debug_counter);
+	op->nr_iterations	= -1;
+	afs_op_set_error(op, -EDESTADDRREQ);
 
 	_leave(" = [op=%08x]", op->debug_id);
 	return op;
@@ -71,7 +73,7 @@ static bool afs_get_io_locks(struct afs_operation *op)
 		swap(vnode, vnode2);
 
 	if (mutex_lock_interruptible(&vnode->io_lock) < 0) {
-		op->error = -ERESTARTSYS;
+		afs_op_set_error(op, -ERESTARTSYS);
 		op->flags |= AFS_OPERATION_STOP;
 		_leave(" = f [I 0]");
 		return false;
@@ -80,7 +82,7 @@ static bool afs_get_io_locks(struct afs_operation *op)
 
 	if (vnode2) {
 		if (mutex_lock_interruptible_nested(&vnode2->io_lock, 1) < 0) {
-			op->error = -ERESTARTSYS;
+			afs_op_set_error(op, -ERESTARTSYS);
 			op->flags |= AFS_OPERATION_STOP;
 			mutex_unlock(&vnode->io_lock);
 			op->flags &= ~AFS_OPERATION_LOCK_0;
@@ -147,7 +149,7 @@ bool afs_begin_vnode_operation(struct afs_operation *op)
 
 	afs_prepare_vnode(op, &op->file[0], 0);
 	afs_prepare_vnode(op, &op->file[1], 1);
-	op->cb_v_break = op->volume->cb_v_break;
+	op->cb_v_break = atomic_read(&op->volume->cb_v_break);
 	_leave(" = true");
 	return true;
 }
@@ -159,16 +161,16 @@ static void afs_end_vnode_operation(struct afs_operation *op)
 {
 	_enter("");
 
-	if (op->error == -EDESTADDRREQ ||
-	    op->error == -EADDRNOTAVAIL ||
-	    op->error == -ENETUNREACH ||
-	    op->error == -EHOSTUNREACH)
+	switch (afs_op_error(op)) {
+	case -EDESTADDRREQ:
+	case -EADDRNOTAVAIL:
+	case -ENETUNREACH:
+	case -EHOSTUNREACH:
 		afs_dump_edestaddrreq(op);
+		break;
+	}
 
 	afs_drop_io_locks(op);
-
-	if (op->error == -ECONNABORTED)
-		op->error = afs_abort_to_error(op->ac.abort_code);
 }
 
 /*
@@ -179,37 +181,43 @@ void afs_wait_for_operation(struct afs_operation *op)
 	_enter("");
 
 	while (afs_select_fileserver(op)) {
-		op->cb_s_break = op->server->cb_s_break;
+		op->call_responded = false;
+		op->call_error = 0;
+		op->call_abort_code = 0;
 		if (test_bit(AFS_SERVER_FL_IS_YFS, &op->server->flags) &&
 		    op->ops->issue_yfs_rpc)
 			op->ops->issue_yfs_rpc(op);
 		else if (op->ops->issue_afs_rpc)
 			op->ops->issue_afs_rpc(op);
 		else
-			op->ac.error = -ENOTSUPP;
-
-		if (op->call)
-			op->error = afs_wait_for_call_to_complete(op->call, &op->ac);
+			op->call_error = -ENOTSUPP;
+
+		if (op->call) {
+			afs_wait_for_call_to_complete(op->call);
+			op->call_abort_code = op->call->abort_code;
+			op->call_error = op->call->error;
+			op->call_responded = op->call->responded;
+			afs_put_call(op->call);
+		}
 	}
 
-	switch (op->error) {
-	case 0:
+	if (op->call_responded)
+		set_bit(AFS_SERVER_FL_RESPONDING, &op->server->flags);
+
+	if (!afs_op_error(op)) {
 		_debug("success");
 		op->ops->success(op);
-		break;
-	case -ECONNABORTED:
+	} else if (op->cumul_error.aborted) {
 		if (op->ops->aborted)
 			op->ops->aborted(op);
-		fallthrough;
-	default:
+	} else {
 		if (op->ops->failed)
 			op->ops->failed(op);
-		break;
 	}
 
 	afs_end_vnode_operation(op);
 
-	if (op->error == 0 && op->ops->edit_dir) {
+	if (!afs_op_error(op) && op->ops->edit_dir) {
 		_debug("edit_dir");
 		op->ops->edit_dir(op);
 	}
@@ -221,7 +229,8 @@ void afs_wait_for_operation(struct afs_operation *op)
  */
 int afs_put_operation(struct afs_operation *op)
 {
-	int i, ret = op->error;
+	struct afs_addr_list *alist;
+	int i, ret = afs_op_error(op);
 
 	_enter("op=%08x,%d", op->debug_id, ret);
 
@@ -243,9 +252,19 @@ int afs_put_operation(struct afs_operation *op)
 		kfree(op->more_files);
 	}
 
-	afs_end_cursor(&op->ac);
+	if (op->estate) {
+		alist = op->estate->addresses;
+		if (alist) {
+			if (op->call_responded &&
+			    op->addr_index != alist->preferred &&
+			    test_bit(alist->preferred, &op->addr_tried))
+				WRITE_ONCE(alist->preferred, op->addr_index);
+		}
+	}
+
+	afs_clear_server_states(op);
 	afs_put_serverlist(op->net, op->server_list);
-	afs_put_volume(op->net, op->volume, afs_volume_trace_put_put_op);
+	afs_put_volume(op->volume, afs_volume_trace_put_put_op);
 	key_put(op->key);
 	kfree(op);
 	return ret;
diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c
index daaf3810cc92..580de4adaaf6 100644
--- a/fs/afs/fs_probe.c
+++ b/fs/afs/fs_probe.c
@@ -15,6 +15,42 @@
 static unsigned int afs_fs_probe_fast_poll_interval = 30 * HZ;
 static unsigned int afs_fs_probe_slow_poll_interval = 5 * 60 * HZ;
 
+struct afs_endpoint_state *afs_get_endpoint_state(struct afs_endpoint_state *estate,
+						  enum afs_estate_trace where)
+{
+	if (estate) {
+		int r;
+
+		__refcount_inc(&estate->ref, &r);
+		trace_afs_estate(estate->server_id, estate->probe_seq, r, where);
+	}
+	return estate;
+}
+
+static void afs_endpoint_state_rcu(struct rcu_head *rcu)
+{
+	struct afs_endpoint_state *estate = container_of(rcu, struct afs_endpoint_state, rcu);
+
+	trace_afs_estate(estate->server_id, estate->probe_seq, refcount_read(&estate->ref),
+			 afs_estate_trace_free);
+	afs_put_addrlist(estate->addresses, afs_alist_trace_put_estate);
+	kfree(estate);
+}
+
+void afs_put_endpoint_state(struct afs_endpoint_state *estate, enum afs_estate_trace where)
+{
+	if (estate) {
+		unsigned int server_id = estate->server_id, probe_seq = estate->probe_seq;
+		bool dead;
+		int r;
+
+		dead = __refcount_dec_and_test(&estate->ref, &r);
+		trace_afs_estate(server_id, probe_seq, r, where);
+		if (dead)
+			call_rcu(&estate->rcu, afs_endpoint_state_rcu);
+	}
+}
+
 /*
  * Start the probe polling timer.  We have to supply it with an inc on the
  * outstanding server count.
@@ -38,9 +74,10 @@ static void afs_schedule_fs_probe(struct afs_net *net,
 /*
  * Handle the completion of a set of probes.
  */
-static void afs_finished_fs_probe(struct afs_net *net, struct afs_server *server)
+static void afs_finished_fs_probe(struct afs_net *net, struct afs_server *server,
+				  struct afs_endpoint_state *estate)
 {
-	bool responded = server->probe.responded;
+	bool responded = test_bit(AFS_ESTATE_RESPONDED, &estate->flags);
 
 	write_seqlock(&net->fs_lock);
 	if (responded) {
@@ -50,6 +87,7 @@ static void afs_finished_fs_probe(struct afs_net *net, struct afs_server *server
 		clear_bit(AFS_SERVER_FL_RESPONDING, &server->flags);
 		list_add_tail(&server->probe_link, &net->fs_probe_fast);
 	}
+
 	write_sequnlock(&net->fs_lock);
 
 	afs_schedule_fs_probe(net, server, !responded);
@@ -58,12 +96,13 @@ static void afs_finished_fs_probe(struct afs_net *net, struct afs_server *server
 /*
  * Handle the completion of a probe.
  */
-static void afs_done_one_fs_probe(struct afs_net *net, struct afs_server *server)
+static void afs_done_one_fs_probe(struct afs_net *net, struct afs_server *server,
+				  struct afs_endpoint_state *estate)
 {
 	_enter("");
 
-	if (atomic_dec_and_test(&server->probe_outstanding))
-		afs_finished_fs_probe(net, server);
+	if (atomic_dec_and_test(&estate->nr_probing))
+		afs_finished_fs_probe(net, server, estate);
 
 	wake_up_all(&server->probe_wq);
 }
@@ -74,24 +113,22 @@ static void afs_done_one_fs_probe(struct afs_net *net, struct afs_server *server
  */
 static void afs_fs_probe_not_done(struct afs_net *net,
 				  struct afs_server *server,
-				  struct afs_addr_cursor *ac)
+				  struct afs_endpoint_state *estate,
+				  int index)
 {
-	struct afs_addr_list *alist = ac->alist;
-	unsigned int index = ac->index;
-
 	_enter("");
 
 	trace_afs_io_error(0, -ENOMEM, afs_io_error_fs_probe_fail);
 	spin_lock(&server->probe_lock);
 
-	server->probe.local_failure = true;
-	if (server->probe.error == 0)
-		server->probe.error = -ENOMEM;
+	set_bit(AFS_ESTATE_LOCAL_FAILURE, &estate->flags);
+	if (estate->error == 0)
+		estate->error = -ENOMEM;
 
-	set_bit(index, &alist->failed);
+	set_bit(index, &estate->failed_set);
 
 	spin_unlock(&server->probe_lock);
-	return afs_done_one_fs_probe(net, server);
+	return afs_done_one_fs_probe(net, server, estate);
 }
 
 /*
@@ -100,30 +137,34 @@ static void afs_fs_probe_not_done(struct afs_net *net,
  */
 void afs_fileserver_probe_result(struct afs_call *call)
 {
-	struct afs_addr_list *alist = call->alist;
+	struct afs_endpoint_state *estate = call->probe;
+	struct afs_addr_list *alist = estate->addresses;
+	struct afs_address *addr = &alist->addrs[call->probe_index];
 	struct afs_server *server = call->server;
-	unsigned int index = call->addr_ix;
-	unsigned int rtt_us = 0, cap0;
+	unsigned int index = call->probe_index;
+	unsigned int rtt_us = -1, cap0;
 	int ret = call->error;
 
 	_enter("%pU,%u", &server->uuid, index);
 
+	WRITE_ONCE(addr->last_error, ret);
+
 	spin_lock(&server->probe_lock);
 
 	switch (ret) {
 	case 0:
-		server->probe.error = 0;
+		estate->error = 0;
 		goto responded;
 	case -ECONNABORTED:
-		if (!server->probe.responded) {
-			server->probe.abort_code = call->abort_code;
-			server->probe.error = ret;
+		if (!test_bit(AFS_ESTATE_RESPONDED, &estate->flags)) {
+			estate->abort_code = call->abort_code;
+			estate->error = ret;
 		}
 		goto responded;
 	case -ENOMEM:
 	case -ENONET:
-		clear_bit(index, &alist->responded);
-		server->probe.local_failure = true;
+		clear_bit(index, &estate->responsive_set);
+		set_bit(AFS_ESTATE_LOCAL_FAILURE, &estate->flags);
 		trace_afs_io_error(call->debug_id, ret, afs_io_error_fs_probe_fail);
 		goto out;
 	case -ECONNRESET: /* Responded, but call expired. */
@@ -136,29 +177,29 @@ void afs_fileserver_probe_result(struct afs_call *call)
 	case -ETIMEDOUT:
 	case -ETIME:
 	default:
-		clear_bit(index, &alist->responded);
-		set_bit(index, &alist->failed);
-		if (!server->probe.responded &&
-		    (server->probe.error == 0 ||
-		     server->probe.error == -ETIMEDOUT ||
-		     server->probe.error == -ETIME))
-			server->probe.error = ret;
+		clear_bit(index, &estate->responsive_set);
+		set_bit(index, &estate->failed_set);
+		if (!test_bit(AFS_ESTATE_RESPONDED, &estate->flags) &&
+		    (estate->error == 0 ||
+		     estate->error == -ETIMEDOUT ||
+		     estate->error == -ETIME))
+			estate->error = ret;
 		trace_afs_io_error(call->debug_id, ret, afs_io_error_fs_probe_fail);
 		goto out;
 	}
 
 responded:
-	clear_bit(index, &alist->failed);
+	clear_bit(index, &estate->failed_set);
 
 	if (call->service_id == YFS_FS_SERVICE) {
-		server->probe.is_yfs = true;
+		set_bit(AFS_ESTATE_IS_YFS, &estate->flags);
 		set_bit(AFS_SERVER_FL_IS_YFS, &server->flags);
-		alist->addrs[index].srx_service = call->service_id;
+		server->service_id = call->service_id;
 	} else {
-		server->probe.not_yfs = true;
-		if (!server->probe.is_yfs) {
+		set_bit(AFS_ESTATE_NOT_YFS, &estate->flags);
+		if (!test_bit(AFS_ESTATE_IS_YFS, &estate->flags)) {
 			clear_bit(AFS_SERVER_FL_IS_YFS, &server->flags);
-			alist->addrs[index].srx_service = call->service_id;
+			server->service_id = call->service_id;
 		}
 		cap0 = ntohl(call->tmp);
 		if (cap0 & AFS3_VICED_CAPABILITY_64BITFILES)
@@ -167,116 +208,136 @@ responded:
 			clear_bit(AFS_SERVER_FL_HAS_FS64, &server->flags);
 	}
 
-	rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us);
-	if (rtt_us < server->probe.rtt) {
-		server->probe.rtt = rtt_us;
+	rtt_us = rxrpc_kernel_get_srtt(addr->peer);
+	if (rtt_us < estate->rtt) {
+		estate->rtt = rtt_us;
 		server->rtt = rtt_us;
 		alist->preferred = index;
 	}
 
 	smp_wmb(); /* Set rtt before responded. */
-	server->probe.responded = true;
-	set_bit(index, &alist->responded);
+	set_bit(AFS_ESTATE_RESPONDED, &estate->flags);
+	set_bit(index, &estate->responsive_set);
 	set_bit(AFS_SERVER_FL_RESPONDING, &server->flags);
 out:
 	spin_unlock(&server->probe_lock);
 
-	_debug("probe %pU [%u] %pISpc rtt=%u ret=%d",
-	       &server->uuid, index, &alist->addrs[index].transport,
+	trace_afs_fs_probe(server, false, estate, index, call->error, call->abort_code, rtt_us);
+	_debug("probe[%x] %pU [%u] %pISpc rtt=%d ret=%d",
+	       estate->probe_seq, &server->uuid, index,
+	       rxrpc_kernel_remote_addr(alist->addrs[index].peer),
 	       rtt_us, ret);
 
-	return afs_done_one_fs_probe(call->net, server);
+	return afs_done_one_fs_probe(call->net, server, estate);
 }
 
 /*
- * Probe one or all of a fileserver's addresses to find out the best route and
- * to query its capabilities.
+ * Probe all of a fileserver's addresses to find out the best route and to
+ * query its capabilities.
  */
 void afs_fs_probe_fileserver(struct afs_net *net, struct afs_server *server,
-			     struct key *key, bool all)
+			     struct afs_addr_list *new_alist, struct key *key)
 {
-	struct afs_addr_cursor ac = {
-		.index = 0,
-	};
+	struct afs_endpoint_state *estate, *old;
+	struct afs_addr_list *alist;
+	unsigned long unprobed;
 
 	_enter("%pU", &server->uuid);
 
-	read_lock(&server->fs_lock);
-	ac.alist = rcu_dereference_protected(server->addresses,
-					     lockdep_is_held(&server->fs_lock));
-	afs_get_addrlist(ac.alist);
-	read_unlock(&server->fs_lock);
+	estate = kzalloc(sizeof(*estate), GFP_KERNEL);
+	if (!estate)
+		return;
+
+	refcount_set(&estate->ref, 1);
+	estate->server_id = server->debug_id;
+	estate->rtt = UINT_MAX;
+
+	write_lock(&server->fs_lock);
+
+	old = rcu_dereference_protected(server->endpoint_state,
+					lockdep_is_held(&server->fs_lock));
+	estate->responsive_set = old->responsive_set;
+	estate->addresses = afs_get_addrlist(new_alist ?: old->addresses,
+					     afs_alist_trace_get_estate);
+	alist = estate->addresses;
+	estate->probe_seq = ++server->probe_counter;
+	atomic_set(&estate->nr_probing, alist->nr_addrs);
+
+	rcu_assign_pointer(server->endpoint_state, estate);
+	set_bit(AFS_ESTATE_SUPERSEDED, &old->flags);
+	write_unlock(&server->fs_lock);
+
+	trace_afs_estate(estate->server_id, estate->probe_seq, refcount_read(&estate->ref),
+			 afs_estate_trace_alloc_probe);
+
+	afs_get_address_preferences(net, alist);
 
 	server->probed_at = jiffies;
-	atomic_set(&server->probe_outstanding, all ? ac.alist->nr_addrs : 1);
-	memset(&server->probe, 0, sizeof(server->probe));
-	server->probe.rtt = UINT_MAX;
-
-	ac.index = ac.alist->preferred;
-	if (ac.index < 0 || ac.index >= ac.alist->nr_addrs)
-		all = true;
-
-	if (all) {
-		for (ac.index = 0; ac.index < ac.alist->nr_addrs; ac.index++)
-			if (!afs_fs_get_capabilities(net, server, &ac, key))
-				afs_fs_probe_not_done(net, server, &ac);
-	} else {
-		if (!afs_fs_get_capabilities(net, server, &ac, key))
-			afs_fs_probe_not_done(net, server, &ac);
+	unprobed = (1UL << alist->nr_addrs) - 1;
+	while (unprobed) {
+		unsigned int index = 0, i;
+		int best_prio = -1;
+
+		for (i = 0; i < alist->nr_addrs; i++) {
+			if (test_bit(i, &unprobed) &&
+			    alist->addrs[i].prio > best_prio) {
+				index = i;
+				best_prio = alist->addrs[i].prio;
+			}
+		}
+		__clear_bit(index, &unprobed);
+
+		trace_afs_fs_probe(server, true, estate, index, 0, 0, 0);
+		if (!afs_fs_get_capabilities(net, server, estate, index, key))
+			afs_fs_probe_not_done(net, server, estate, index);
 	}
 
-	afs_put_addrlist(ac.alist);
+	afs_put_endpoint_state(old, afs_estate_trace_put_probe);
 }
 
 /*
- * Wait for the first as-yet untried fileserver to respond.
+ * Wait for the first as-yet untried fileserver to respond, for the probe state
+ * to be superseded or for all probes to finish.
  */
-int afs_wait_for_fs_probes(struct afs_server_list *slist, unsigned long untried)
+int afs_wait_for_fs_probes(struct afs_operation *op, struct afs_server_state *states, bool intr)
 {
-	struct wait_queue_entry *waits;
-	struct afs_server *server;
-	unsigned int rtt = UINT_MAX, rtt_s;
-	bool have_responders = false;
-	int pref = -1, i;
+	struct afs_endpoint_state *estate;
+	struct afs_server_list *slist = op->server_list;
+	bool still_probing = true;
+	int ret = 0, i;
 
-	_enter("%u,%lx", slist->nr_servers, untried);
+	_enter("%u", slist->nr_servers);
 
-	/* Only wait for servers that have a probe outstanding. */
 	for (i = 0; i < slist->nr_servers; i++) {
-		if (test_bit(i, &untried)) {
-			server = slist->servers[i].server;
-			if (!atomic_read(&server->probe_outstanding))
-				__clear_bit(i, &untried);
-			if (server->probe.responded)
-				have_responders = true;
-		}
+		estate = states[i].endpoint_state;
+		if (test_bit(AFS_ESTATE_SUPERSEDED, &estate->flags))
+			return 2;
+		if (atomic_read(&estate->nr_probing))
+			still_probing = true;
+		if (estate->responsive_set & states[i].untried_addrs)
+			return 1;
 	}
-	if (have_responders || !untried)
+	if (!still_probing)
 		return 0;
 
-	waits = kmalloc(array_size(slist->nr_servers, sizeof(*waits)), GFP_KERNEL);
-	if (!waits)
-		return -ENOMEM;
-
-	for (i = 0; i < slist->nr_servers; i++) {
-		if (test_bit(i, &untried)) {
-			server = slist->servers[i].server;
-			init_waitqueue_entry(&waits[i], current);
-			add_wait_queue(&server->probe_wq, &waits[i]);
-		}
-	}
+	for (i = 0; i < slist->nr_servers; i++)
+		add_wait_queue(&slist->servers[i].server->probe_wq, &states[i].probe_waiter);
 
 	for (;;) {
-		bool still_probing = false;
+		still_probing = false;
 
-		set_current_state(TASK_INTERRUPTIBLE);
+		set_current_state(intr ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);
 		for (i = 0; i < slist->nr_servers; i++) {
-			if (test_bit(i, &untried)) {
-				server = slist->servers[i].server;
-				if (server->probe.responded)
-					goto stop;
-				if (atomic_read(&server->probe_outstanding))
-					still_probing = true;
+			estate = states[i].endpoint_state;
+			if (test_bit(AFS_ESTATE_SUPERSEDED, &estate->flags)) {
+				ret = 2;
+				goto stop;
+			}
+			if (atomic_read(&estate->nr_probing))
+				still_probing = true;
+			if (estate->responsive_set & states[i].untried_addrs) {
+				ret = 1;
+				goto stop;
 			}
 		}
 
@@ -288,28 +349,12 @@ int afs_wait_for_fs_probes(struct afs_server_list *slist, unsigned long untried)
 stop:
 	set_current_state(TASK_RUNNING);
 
-	for (i = 0; i < slist->nr_servers; i++) {
-		if (test_bit(i, &untried)) {
-			server = slist->servers[i].server;
-			rtt_s = READ_ONCE(server->rtt);
-			if (test_bit(AFS_SERVER_FL_RESPONDING, &server->flags) &&
-			    rtt_s < rtt) {
-				pref = i;
-				rtt = rtt_s;
-			}
-
-			remove_wait_queue(&server->probe_wq, &waits[i]);
-		}
-	}
-
-	kfree(waits);
-
-	if (pref == -1 && signal_pending(current))
-		return -ERESTARTSYS;
+	for (i = 0; i < slist->nr_servers; i++)
+		remove_wait_queue(&slist->servers[i].server->probe_wq, &states[i].probe_waiter);
 
-	if (pref >= 0)
-		slist->preferred = pref;
-	return 0;
+	if (!ret && signal_pending(current))
+		ret = -ERESTARTSYS;
+	return ret;
 }
 
 /*
@@ -327,7 +372,7 @@ void afs_fs_probe_timer(struct timer_list *timer)
 /*
  * Dispatch a probe to a server.
  */
-static void afs_dispatch_fs_probe(struct afs_net *net, struct afs_server *server, bool all)
+static void afs_dispatch_fs_probe(struct afs_net *net, struct afs_server *server)
 	__releases(&net->fs_lock)
 {
 	struct key *key = NULL;
@@ -340,7 +385,7 @@ static void afs_dispatch_fs_probe(struct afs_net *net, struct afs_server *server
 	afs_get_server(server, afs_server_trace_get_probe);
 	write_sequnlock(&net->fs_lock);
 
-	afs_fs_probe_fileserver(net, server, key, all);
+	afs_fs_probe_fileserver(net, server, NULL, key);
 	afs_put_server(net, server, afs_server_trace_put_probe);
 }
 
@@ -352,7 +397,7 @@ void afs_probe_fileserver(struct afs_net *net, struct afs_server *server)
 {
 	write_seqlock(&net->fs_lock);
 	if (!list_empty(&server->probe_link))
-		return afs_dispatch_fs_probe(net, server, true);
+		return afs_dispatch_fs_probe(net, server);
 	write_sequnlock(&net->fs_lock);
 }
 
@@ -412,7 +457,7 @@ again:
 		_debug("probe %pU", &server->uuid);
 
 	if (server && (first_pass || !need_resched())) {
-		afs_dispatch_fs_probe(net, server, server == fast);
+		afs_dispatch_fs_probe(net, server);
 		first_pass = false;
 		goto again;
 	}
@@ -436,12 +481,13 @@ again:
 /*
  * Wait for a probe on a particular fileserver to complete for 2s.
  */
-int afs_wait_for_one_fs_probe(struct afs_server *server, bool is_intr)
+int afs_wait_for_one_fs_probe(struct afs_server *server, struct afs_endpoint_state *estate,
+			      unsigned long exclude, bool is_intr)
 {
 	struct wait_queue_entry wait;
 	unsigned long timo = 2 * HZ;
 
-	if (atomic_read(&server->probe_outstanding) == 0)
+	if (atomic_read(&estate->nr_probing) == 0)
 		goto dont_wait;
 
 	init_wait_entry(&wait, 0);
@@ -449,8 +495,9 @@ int afs_wait_for_one_fs_probe(struct afs_server *server, bool is_intr)
 		prepare_to_wait_event(&server->probe_wq, &wait,
 				      is_intr ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);
 		if (timo == 0 ||
-		    server->probe.responded ||
-		    atomic_read(&server->probe_outstanding) == 0 ||
+		    test_bit(AFS_ESTATE_SUPERSEDED, &estate->flags) ||
+		    (estate->responsive_set & ~exclude) ||
+		    atomic_read(&estate->nr_probing) == 0 ||
 		    (is_intr && signal_pending(current)))
 			break;
 		timo = schedule_timeout(timo);
@@ -459,7 +506,9 @@ int afs_wait_for_one_fs_probe(struct afs_server *server, bool is_intr)
 	finish_wait(&server->probe_wq, &wait);
 
 dont_wait:
-	if (server->probe.responded)
+	if (estate->responsive_set & ~exclude)
+		return 1;
+	if (test_bit(AFS_ESTATE_SUPERSEDED, &estate->flags))
 		return 0;
 	if (is_intr && signal_pending(current))
 		return -ERESTARTSYS;
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 7d37f63ef0f0..79cd30775b7a 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -290,6 +290,7 @@ void afs_fs_fetch_status(struct afs_operation *op)
 	bp[2] = htonl(vp->fid.vnode);
 	bp[3] = htonl(vp->fid.unique);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -442,6 +443,7 @@ static void afs_fs_fetch_data64(struct afs_operation *op)
 	bp[6] = 0;
 	bp[7] = htonl(lower_32_bits(req->len));
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -476,6 +478,7 @@ void afs_fs_fetch_data(struct afs_operation *op)
 	bp[4] = htonl(lower_32_bits(req->pos));
 	bp[5] = htonl(lower_32_bits(req->len));
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -559,6 +562,7 @@ void afs_fs_create_file(struct afs_operation *op)
 	*bp++ = htonl(op->create.mode & S_IALLUGO); /* unix mode */
 	*bp++ = 0; /* segment size */
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -612,6 +616,7 @@ void afs_fs_make_dir(struct afs_operation *op)
 	*bp++ = htonl(op->create.mode & S_IALLUGO); /* unix mode */
 	*bp++ = 0; /* segment size */
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -685,6 +690,7 @@ void afs_fs_remove_file(struct afs_operation *op)
 		bp = (void *) bp + padsz;
 	}
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -732,6 +738,7 @@ void afs_fs_remove_dir(struct afs_operation *op)
 		bp = (void *) bp + padsz;
 	}
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -812,6 +819,7 @@ void afs_fs_link(struct afs_operation *op)
 	*bp++ = htonl(vp->fid.vnode);
 	*bp++ = htonl(vp->fid.unique);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call1(call, &vp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -907,6 +915,7 @@ void afs_fs_symlink(struct afs_operation *op)
 	*bp++ = htonl(S_IRWXUGO); /* unix mode */
 	*bp++ = 0; /* segment size */
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1003,6 +1012,7 @@ void afs_fs_rename(struct afs_operation *op)
 		bp = (void *) bp + n_padsz;
 	}
 
+	call->fid = orig_dvp->fid;
 	trace_afs_make_fs_call2(call, &orig_dvp->fid, orig_name, new_name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1090,6 +1100,7 @@ static void afs_fs_store_data64(struct afs_operation *op)
 	*bp++ = htonl(upper_32_bits(op->store.i_size));
 	*bp++ = htonl(lower_32_bits(op->store.i_size));
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1140,6 +1151,7 @@ void afs_fs_store_data(struct afs_operation *op)
 	*bp++ = htonl(lower_32_bits(op->store.size));
 	*bp++ = htonl(lower_32_bits(op->store.i_size));
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1206,6 +1218,7 @@ static void afs_fs_setattr_size64(struct afs_operation *op)
 	*bp++ = htonl(upper_32_bits(attr->ia_size));	/* new file length */
 	*bp++ = htonl(lower_32_bits(attr->ia_size));
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1247,6 +1260,7 @@ static void afs_fs_setattr_size(struct afs_operation *op)
 	*bp++ = 0;				/* size of write */
 	*bp++ = htonl(attr->ia_size);		/* new file length */
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1283,6 +1297,7 @@ void afs_fs_setattr(struct afs_operation *op)
 
 	xdr_encode_AFS_StoreStatus(&bp, op->setattr.attr);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1446,6 +1461,7 @@ void afs_fs_get_volume_status(struct afs_operation *op)
 	bp[0] = htonl(FSGETVOLUMESTATUS);
 	bp[1] = htonl(vp->fid.vid);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1528,6 +1544,7 @@ void afs_fs_set_lock(struct afs_operation *op)
 	*bp++ = htonl(vp->fid.unique);
 	*bp++ = htonl(op->lock.type);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_calli(call, &vp->fid, op->lock.type);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1554,6 +1571,7 @@ void afs_fs_extend_lock(struct afs_operation *op)
 	*bp++ = htonl(vp->fid.vnode);
 	*bp++ = htonl(vp->fid.unique);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1580,6 +1598,7 @@ void afs_fs_release_lock(struct afs_operation *op)
 	*bp++ = htonl(vp->fid.vnode);
 	*bp++ = htonl(vp->fid.unique);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1605,13 +1624,12 @@ static const struct afs_call_type afs_RXFSGiveUpAllCallBacks = {
 /*
  * Flush all the callbacks we have on a server.
  */
-int afs_fs_give_up_all_callbacks(struct afs_net *net,
-				 struct afs_server *server,
-				 struct afs_addr_cursor *ac,
-				 struct key *key)
+int afs_fs_give_up_all_callbacks(struct afs_net *net, struct afs_server *server,
+				 struct afs_address *addr, struct key *key)
 {
 	struct afs_call *call;
 	__be32 *bp;
+	int ret;
 
 	_enter("");
 
@@ -1619,15 +1637,22 @@ int afs_fs_give_up_all_callbacks(struct afs_net *net,
 	if (!call)
 		return -ENOMEM;
 
-	call->key = key;
+	call->key	= key;
+	call->peer	= rxrpc_kernel_get_peer(addr->peer);
+	call->service_id = server->service_id;
 
 	/* marshall the parameters */
 	bp = call->request;
 	*bp++ = htonl(FSGIVEUPALLCALLBACKS);
 
 	call->server = afs_use_server(server, afs_server_trace_give_up_cb);
-	afs_make_call(ac, call, GFP_NOFS);
-	return afs_wait_for_call_to_complete(call, ac);
+	afs_make_call(call, GFP_NOFS);
+	afs_wait_for_call_to_complete(call);
+	ret = call->error;
+	if (call->responded)
+		set_bit(AFS_SERVER_FL_RESPONDING, &server->flags);
+	afs_put_call(call);
+	return ret;
 }
 
 /*
@@ -1689,6 +1714,12 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call)
 	return 0;
 }
 
+static void afs_fs_get_capabilities_destructor(struct afs_call *call)
+{
+	afs_put_endpoint_state(call->probe, afs_estate_trace_put_getcaps);
+	afs_flat_call_destructor(call);
+}
+
 /*
  * FS.GetCapabilities operation type
  */
@@ -1697,7 +1728,7 @@ static const struct afs_call_type afs_RXFSGetCapabilities = {
 	.op		= afs_FS_GetCapabilities,
 	.deliver	= afs_deliver_fs_get_capabilities,
 	.done		= afs_fileserver_probe_result,
-	.destructor	= afs_flat_call_destructor,
+	.destructor	= afs_fs_get_capabilities_destructor,
 };
 
 /*
@@ -1707,7 +1738,8 @@ static const struct afs_call_type afs_RXFSGetCapabilities = {
  * ->done() - otherwise we return false to indicate we didn't even try.
  */
 bool afs_fs_get_capabilities(struct afs_net *net, struct afs_server *server,
-			     struct afs_addr_cursor *ac, struct key *key)
+			     struct afs_endpoint_state *estate, unsigned int addr_index,
+			     struct key *key)
 {
 	struct afs_call *call;
 	__be32 *bp;
@@ -1718,10 +1750,14 @@ bool afs_fs_get_capabilities(struct afs_net *net, struct afs_server *server,
 	if (!call)
 		return false;
 
-	call->key = key;
-	call->server = afs_use_server(server, afs_server_trace_get_caps);
-	call->upgrade = true;
-	call->async = true;
+	call->key	= key;
+	call->server	= afs_use_server(server, afs_server_trace_get_caps);
+	call->peer	= rxrpc_kernel_get_peer(estate->addresses->addrs[addr_index].peer);
+	call->probe	= afs_get_endpoint_state(estate, afs_estate_trace_get_getcaps);
+	call->probe_index = addr_index;
+	call->service_id = server->service_id;
+	call->upgrade	= true;
+	call->async	= true;
 	call->max_lifespan = AFS_PROBE_MAX_LIFESPAN;
 
 	/* marshall the parameters */
@@ -1729,7 +1765,7 @@ bool afs_fs_get_capabilities(struct afs_net *net, struct afs_server *server,
 	*bp++ = htonl(FSGETCAPABILITIES);
 
 	trace_afs_make_fs_call(call, NULL);
-	afs_make_call(ac, call, GFP_NOFS);
+	afs_make_call(call, GFP_NOFS);
 	afs_put_call(call);
 	return true;
 }
@@ -1853,7 +1889,10 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call)
 			return ret;
 
 		bp = call->buffer;
-		xdr_decode_AFSVolSync(&bp, &op->volsync);
+		/* Unfortunately, prior to OpenAFS-1.6, volsync here is filled
+		 * with rubbish.
+		 */
+		xdr_decode_AFSVolSync(&bp, NULL);
 
 		call->unmarshall++;
 		fallthrough;
@@ -1899,7 +1938,7 @@ void afs_fs_inline_bulk_status(struct afs_operation *op)
 	int i;
 
 	if (test_bit(AFS_SERVER_FL_NO_IBULK, &op->server->flags)) {
-		op->error = -ENOTSUPP;
+		afs_op_set_error(op, -ENOTSUPP);
 		return;
 	}
 
@@ -1928,6 +1967,7 @@ void afs_fs_inline_bulk_status(struct afs_operation *op)
 		*bp++ = htonl(op->more_files[i].fid.unique);
 	}
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -2033,6 +2073,7 @@ void afs_fs_fetch_acl(struct afs_operation *op)
 	bp[2] = htonl(vp->fid.vnode);
 	bp[3] = htonl(vp->fid.unique);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_KERNEL);
 }
@@ -2078,6 +2119,7 @@ void afs_fs_store_acl(struct afs_operation *op)
 	if (acl->size != size)
 		memset((void *)&bp[5] + acl->size, 0, size - acl->size);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_KERNEL);
 }
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 78efc9719349..4f04f6f33f46 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -85,8 +85,7 @@ static int afs_inode_init_from_status(struct afs_operation *op,
 
 	write_seqlock(&vnode->cb_lock);
 
-	vnode->cb_v_break = op->cb_v_break;
-	vnode->cb_s_break = op->cb_s_break;
+	vnode->cb_v_check = op->cb_v_break;
 	vnode->status = *status;
 
 	t = status->mtime_client;
@@ -146,11 +145,10 @@ static int afs_inode_init_from_status(struct afs_operation *op,
 	if (!vp->scb.have_cb) {
 		/* it's a symlink we just created (the fileserver
 		 * didn't give us a callback) */
-		vnode->cb_expires_at = ktime_get_real_seconds();
+		atomic64_set(&vnode->cb_expires_at, AFS_NO_CB_PROMISE);
 	} else {
-		vnode->cb_expires_at = vp->scb.callback.expires_at;
 		vnode->cb_server = op->server;
-		set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
+		atomic64_set(&vnode->cb_expires_at, vp->scb.callback.expires_at);
 	}
 
 	write_sequnlock(&vnode->cb_lock);
@@ -214,7 +212,8 @@ static void afs_apply_status(struct afs_operation *op,
 	vnode->status = *status;
 
 	if (vp->dv_before + vp->dv_delta != status->data_version) {
-		if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags))
+		if (vnode->cb_ro_snapshot == atomic_read(&vnode->volume->cb_ro_snapshot) &&
+		    atomic64_read(&vnode->cb_expires_at) != AFS_NO_CB_PROMISE)
 			pr_warn("kAFS: vnode modified {%llx:%llu} %llx->%llx %s (op=%x)\n",
 				vnode->fid.vid, vnode->fid.vnode,
 				(unsigned long long)vp->dv_before + vp->dv_delta,
@@ -268,9 +267,9 @@ static void afs_apply_callback(struct afs_operation *op,
 	struct afs_vnode *vnode = vp->vnode;
 
 	if (!afs_cb_is_broken(vp->cb_break_before, vnode)) {
-		vnode->cb_expires_at	= cb->expires_at;
-		vnode->cb_server	= op->server;
-		set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
+		if (op->volume->type == AFSVL_RWVOL)
+			vnode->cb_server = op->server;
+		atomic64_set(&vnode->cb_expires_at, cb->expires_at);
 	}
 }
 
@@ -331,7 +330,7 @@ static void afs_fetch_status_success(struct afs_operation *op)
 
 	if (vnode->netfs.inode.i_state & I_NEW) {
 		ret = afs_inode_init_from_status(op, vp, vnode);
-		op->error = ret;
+		afs_op_set_error(op, ret);
 		if (ret == 0)
 			afs_cache_permit(vnode, op->key, vp->cb_break_before, &vp->scb);
 	} else {
@@ -542,7 +541,7 @@ struct inode *afs_root_iget(struct super_block *sb, struct key *key)
 	BUG_ON(!(inode->i_state & I_NEW));
 
 	vnode = AFS_FS_I(inode);
-	vnode->cb_v_break = as->volume->cb_v_break,
+	vnode->cb_v_check = atomic_read(&as->volume->cb_v_break),
 	afs_set_netfs_context(vnode);
 
 	op = afs_alloc_operation(key, as->volume);
@@ -573,180 +572,6 @@ error:
 }
 
 /*
- * mark the data attached to an inode as obsolete due to a write on the server
- * - might also want to ditch all the outstanding writes and dirty pages
- */
-static void afs_zap_data(struct afs_vnode *vnode)
-{
-	_enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode);
-
-	afs_invalidate_cache(vnode, 0);
-
-	/* nuke all the non-dirty pages that aren't locked, mapped or being
-	 * written back in a regular file and completely discard the pages in a
-	 * directory or symlink */
-	if (S_ISREG(vnode->netfs.inode.i_mode))
-		invalidate_remote_inode(&vnode->netfs.inode);
-	else
-		invalidate_inode_pages2(vnode->netfs.inode.i_mapping);
-}
-
-/*
- * Check to see if we have a server currently serving this volume and that it
- * hasn't been reinitialised or dropped from the list.
- */
-static bool afs_check_server_good(struct afs_vnode *vnode)
-{
-	struct afs_server_list *slist;
-	struct afs_server *server;
-	bool good;
-	int i;
-
-	if (vnode->cb_fs_s_break == atomic_read(&vnode->volume->cell->fs_s_break))
-		return true;
-
-	rcu_read_lock();
-
-	slist = rcu_dereference(vnode->volume->servers);
-	for (i = 0; i < slist->nr_servers; i++) {
-		server = slist->servers[i].server;
-		if (server == vnode->cb_server) {
-			good = (vnode->cb_s_break == server->cb_s_break);
-			rcu_read_unlock();
-			return good;
-		}
-	}
-
-	rcu_read_unlock();
-	return false;
-}
-
-/*
- * Check the validity of a vnode/inode.
- */
-bool afs_check_validity(struct afs_vnode *vnode)
-{
-	enum afs_cb_break_reason need_clear = afs_cb_break_no_break;
-	time64_t now = ktime_get_real_seconds();
-	unsigned int cb_break;
-	int seq = 0;
-
-	do {
-		read_seqbegin_or_lock(&vnode->cb_lock, &seq);
-		cb_break = vnode->cb_break;
-
-		if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
-			if (vnode->cb_v_break != vnode->volume->cb_v_break)
-				need_clear = afs_cb_break_for_v_break;
-			else if (!afs_check_server_good(vnode))
-				need_clear = afs_cb_break_for_s_reinit;
-			else if (test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags))
-				need_clear = afs_cb_break_for_zap;
-			else if (vnode->cb_expires_at - 10 <= now)
-				need_clear = afs_cb_break_for_lapsed;
-		} else if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
-			;
-		} else {
-			need_clear = afs_cb_break_no_promise;
-		}
-
-	} while (need_seqretry(&vnode->cb_lock, seq));
-
-	done_seqretry(&vnode->cb_lock, seq);
-
-	if (need_clear == afs_cb_break_no_break)
-		return true;
-
-	write_seqlock(&vnode->cb_lock);
-	if (need_clear == afs_cb_break_no_promise)
-		vnode->cb_v_break = vnode->volume->cb_v_break;
-	else if (cb_break == vnode->cb_break)
-		__afs_break_callback(vnode, need_clear);
-	else
-		trace_afs_cb_miss(&vnode->fid, need_clear);
-	write_sequnlock(&vnode->cb_lock);
-	return false;
-}
-
-/*
- * Returns true if the pagecache is still valid.  Does not sleep.
- */
-bool afs_pagecache_valid(struct afs_vnode *vnode)
-{
-	if (unlikely(test_bit(AFS_VNODE_DELETED, &vnode->flags))) {
-		if (vnode->netfs.inode.i_nlink)
-			clear_nlink(&vnode->netfs.inode);
-		return true;
-	}
-
-	if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags) &&
-	    afs_check_validity(vnode))
-		return true;
-
-	return false;
-}
-
-/*
- * validate a vnode/inode
- * - there are several things we need to check
- *   - parent dir data changes (rm, rmdir, rename, mkdir, create, link,
- *     symlink)
- *   - parent dir metadata changed (security changes)
- *   - dentry data changed (write, truncate)
- *   - dentry metadata changed (security changes)
- */
-int afs_validate(struct afs_vnode *vnode, struct key *key)
-{
-	int ret;
-
-	_enter("{v={%llx:%llu} fl=%lx},%x",
-	       vnode->fid.vid, vnode->fid.vnode, vnode->flags,
-	       key_serial(key));
-
-	if (afs_pagecache_valid(vnode))
-		goto valid;
-
-	down_write(&vnode->validate_lock);
-
-	/* if the promise has expired, we need to check the server again to get
-	 * a new promise - note that if the (parent) directory's metadata was
-	 * changed then the security may be different and we may no longer have
-	 * access */
-	if (!test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
-		_debug("not promised");
-		ret = afs_fetch_status(vnode, key, false, NULL);
-		if (ret < 0) {
-			if (ret == -ENOENT) {
-				set_bit(AFS_VNODE_DELETED, &vnode->flags);
-				ret = -ESTALE;
-			}
-			goto error_unlock;
-		}
-		_debug("new promise [fl=%lx]", vnode->flags);
-	}
-
-	if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
-		_debug("file already deleted");
-		ret = -ESTALE;
-		goto error_unlock;
-	}
-
-	/* if the vnode's data version number changed then its contents are
-	 * different */
-	if (test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags))
-		afs_zap_data(vnode);
-	up_write(&vnode->validate_lock);
-valid:
-	_leave(" = 0");
-	return 0;
-
-error_unlock:
-	up_write(&vnode->validate_lock);
-	_leave(" = %d", ret);
-	return ret;
-}
-
-/*
  * read the attributes of an inode
  */
 int afs_getattr(struct mnt_idmap *idmap, const struct path *path,
@@ -755,13 +580,13 @@ int afs_getattr(struct mnt_idmap *idmap, const struct path *path,
 	struct inode *inode = d_inode(path->dentry);
 	struct afs_vnode *vnode = AFS_FS_I(inode);
 	struct key *key;
-	int ret, seq = 0;
+	int ret, seq;
 
 	_enter("{ ino=%lu v=%u }", inode->i_ino, inode->i_generation);
 
 	if (vnode->volume &&
 	    !(query_flags & AT_STATX_DONT_SYNC) &&
-	    !test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
+	    atomic64_read(&vnode->cb_expires_at) == AFS_NO_CB_PROMISE) {
 		key = afs_request_key(vnode->volume->cell);
 		if (IS_ERR(key))
 			return PTR_ERR(key);
@@ -772,7 +597,7 @@ int afs_getattr(struct mnt_idmap *idmap, const struct path *path,
 	}
 
 	do {
-		read_seqbegin_or_lock(&vnode->cb_lock, &seq);
+		seq = read_seqbegin(&vnode->cb_lock);
 		generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat);
 		if (test_bit(AFS_VNODE_SILLY_DELETED, &vnode->flags) &&
 		    stat->nlink > 0)
@@ -784,9 +609,8 @@ int afs_getattr(struct mnt_idmap *idmap, const struct path *path,
 		 */
 		if (S_ISDIR(inode->i_mode))
 			stat->size = vnode->netfs.remote_i_size;
-	} while (need_seqretry(&vnode->cb_lock, seq));
+	} while (read_seqretry(&vnode->cb_lock, seq));
 
-	done_seqretry(&vnode->cb_lock, seq);
 	return 0;
 }
 
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index c9cef3782b4a..55aa0679d8ce 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -33,6 +33,7 @@
 struct pagevec;
 struct afs_call;
 struct afs_vnode;
+struct afs_server_probe;
 
 /*
  * Partial file-locking emulation mode.  (The problem being that AFS3 only
@@ -73,21 +74,51 @@ enum afs_call_state {
 };
 
 /*
+ * Address preferences.
+ */
+struct afs_addr_preference {
+	union {
+		struct in_addr	ipv4_addr;	/* AF_INET address to compare against */
+		struct in6_addr	ipv6_addr;	/* AF_INET6 address to compare against */
+	};
+	sa_family_t		family;		/* Which address to use */
+	u16			prio;		/* Priority */
+	u8			subnet_mask;	/* How many bits to compare */
+};
+
+struct afs_addr_preference_list {
+	struct rcu_head		rcu;
+	u16			version;	/* Incremented when prefs list changes */
+	u8			ipv6_off;	/* Offset of IPv6 addresses */
+	u8			nr;		/* Number of addresses in total */
+	u8			max_prefs;	/* Number of prefs allocated */
+	struct afs_addr_preference prefs[] __counted_by(max_prefs);
+};
+
+struct afs_address {
+	struct rxrpc_peer	*peer;
+	short			last_error;	/* Last error from this address */
+	u16			prio;		/* Address priority */
+};
+
+/*
  * List of server addresses.
  */
 struct afs_addr_list {
 	struct rcu_head		rcu;
 	refcount_t		usage;
 	u32			version;	/* Version */
+	unsigned int		debug_id;
+	unsigned int		addr_pref_version; /* Version of address preference list */
 	unsigned char		max_addrs;
 	unsigned char		nr_addrs;
 	unsigned char		preferred;	/* Preferred address */
 	unsigned char		nr_ipv4;	/* Number of IPv4 addresses */
 	enum dns_record_source	source:8;
 	enum dns_lookup_status	status:8;
-	unsigned long		failed;		/* Mask of addrs that failed locally/ICMP */
+	unsigned long		probe_failed;	/* Mask of addrs that failed locally/ICMP */
 	unsigned long		responded;	/* Mask of addrs that responded */
-	struct sockaddr_rxrpc	addrs[] __counted_by(max_addrs);
+	struct afs_address	addrs[] __counted_by(max_addrs);
 #define AFS_MAX_ADDRESSES ((unsigned int)(sizeof(unsigned long) * 8))
 };
 
@@ -96,11 +127,11 @@ struct afs_addr_list {
  */
 struct afs_call {
 	const struct afs_call_type *type;	/* type of call */
-	struct afs_addr_list	*alist;		/* Address is alist[addr_ix] */
 	wait_queue_head_t	waitq;		/* processes awaiting completion */
 	struct work_struct	async_work;	/* async I/O processor */
 	struct work_struct	work;		/* actual work processor */
 	struct rxrpc_call	*rxcall;	/* RxRPC call handle */
+	struct rxrpc_peer	*peer;		/* Remote endpoint */
 	struct key		*key;		/* security for this call */
 	struct afs_net		*net;		/* The network namespace */
 	struct afs_server	*server;	/* The fileserver record if fs op (pins ref) */
@@ -116,11 +147,14 @@ struct afs_call {
 	};
 	void			*buffer;	/* reply receive buffer */
 	union {
-		long			ret0;	/* Value to reply with instead of 0 */
+		struct afs_endpoint_state *probe;
+		struct afs_addr_list	*vl_probe;
 		struct afs_addr_list	*ret_alist;
 		struct afs_vldb_entry	*ret_vldb;
 		char			*ret_str;
 	};
+	struct afs_fid		fid;		/* Primary vnode ID (or all zeroes) */
+	unsigned char		probe_index;	/* Address in ->probe_alist */
 	struct afs_operation	*op;
 	unsigned int		server_index;
 	refcount_t		ref;
@@ -133,13 +167,13 @@ struct afs_call {
 	unsigned		reply_max;	/* maximum size of reply */
 	unsigned		count2;		/* count used in unmarshalling */
 	unsigned char		unmarshall;	/* unmarshalling phase */
-	unsigned char		addr_ix;	/* Address in ->alist */
 	bool			drop_ref;	/* T if need to drop ref for incoming call */
 	bool			need_attention;	/* T if RxRPC poked us */
 	bool			async;		/* T if asynchronous */
 	bool			upgrade;	/* T to request service upgrade */
 	bool			intr;		/* T if interruptible */
 	bool			unmarshalling_error; /* T if an unmarshalling error occurred */
+	bool			responded;	/* Got a response from the call (may be abort) */
 	u16			service_id;	/* Actual service ID (after upgrade) */
 	unsigned int		debug_id;	/* Trace ID */
 	u32			operation_ID;	/* operation ID for an incoming call */
@@ -306,6 +340,8 @@ struct afs_net {
 	struct proc_dir_entry	*proc_afs;	/* /proc/net/afs directory */
 	struct afs_sysnames	*sysnames;
 	rwlock_t		sysnames_lock;
+	struct afs_addr_preference_list __rcu *address_prefs;
+	u16			address_pref_version;
 
 	/* Statistics counters */
 	atomic_t		n_lookup;	/* Number of lookups done */
@@ -379,6 +415,7 @@ struct afs_cell {
 	unsigned int		debug_id;
 
 	/* The volumes belonging to this cell */
+	struct rw_semaphore	vs_lock;	/* Lock for server->volumes */
 	struct rb_root		volumes;	/* Tree of volumes on this server */
 	struct hlist_head	proc_volumes;	/* procfs volume list */
 	seqlock_t		volume_lock;	/* For volumes */
@@ -386,9 +423,6 @@ struct afs_cell {
 	/* Active fileserver interaction state. */
 	struct rb_root		fs_servers;	/* afs_server (by server UUID) */
 	seqlock_t		fs_lock;	/* For fs_servers  */
-	struct rw_semaphore	fs_open_mmaps_lock;
-	struct list_head	fs_open_mmaps;	/* List of vnodes that are mmapped */
-	atomic_t		fs_s_break;	/* Counter of CB.InitCallBackState messages */
 
 	/* VL server list. */
 	rwlock_t		vl_servers_lock; /* Lock on vl_servers */
@@ -412,13 +446,14 @@ struct afs_vlserver {
 	rwlock_t		lock;		/* Lock on addresses */
 	refcount_t		ref;
 	unsigned int		rtt;		/* Server's current RTT in uS */
+	unsigned int		debug_id;
 
 	/* Probe state */
 	wait_queue_head_t	probe_wq;
 	atomic_t		probe_outstanding;
 	spinlock_t		probe_lock;
 	struct {
-		unsigned int	rtt;		/* RTT in uS */
+		unsigned int	rtt;		/* Best RTT in uS (or UINT_MAX) */
 		u32		abort_code;
 		short		error;
 		unsigned short	flags;
@@ -428,6 +463,7 @@ struct afs_vlserver {
 #define AFS_VLSERVER_PROBE_LOCAL_FAILURE	0x08 /* A local failure prevented a probe */
 	} probe;
 
+	u16			service_id;	/* Service ID we're using */
 	u16			port;
 	u16			name_len;	/* Length of name */
 	char			name[];		/* Server name, case-flattened */
@@ -477,6 +513,7 @@ struct afs_vldb_entry {
 #define AFS_VOL_VTM_RW	0x01 /* R/W version of the volume is available (on this server) */
 #define AFS_VOL_VTM_RO	0x02 /* R/O version of the volume is available (on this server) */
 #define AFS_VOL_VTM_BAK	0x04 /* backup version of the volume is available (on this server) */
+	u8			vlsf_flags[AFS_NMAXNSERVERS];
 	short			error;
 	u8			nr_servers;	/* Number of server records */
 	u8			name_len;
@@ -484,6 +521,32 @@ struct afs_vldb_entry {
 };
 
 /*
+ * Fileserver endpoint state.  The records the addresses of a fileserver's
+ * endpoints and the state and result of a round of probing on them.  This
+ * allows the rotation algorithm to access those results without them being
+ * erased by a subsequent round of probing.
+ */
+struct afs_endpoint_state {
+	struct rcu_head		rcu;
+	struct afs_addr_list	*addresses;	/* The addresses being probed */
+	unsigned long		responsive_set;	/* Bitset of responsive endpoints */
+	unsigned long		failed_set;	/* Bitset of endpoints we failed to probe */
+	refcount_t		ref;
+	unsigned int		server_id;	/* Debug ID of server */
+	unsigned int		probe_seq;	/* Probe sequence (from server::probe_counter) */
+	atomic_t		nr_probing;	/* Number of outstanding probes */
+	unsigned int		rtt;		/* Best RTT in uS (or UINT_MAX) */
+	s32			abort_code;
+	short			error;
+	unsigned long		flags;
+#define AFS_ESTATE_RESPONDED	0		/* Set if the server responded */
+#define AFS_ESTATE_SUPERSEDED	1		/* Set if this record has been superseded */
+#define AFS_ESTATE_IS_YFS	2		/* Set if probe upgraded to YFS */
+#define AFS_ESTATE_NOT_YFS	3		/* Set if probe didn't upgrade to YFS */
+#define AFS_ESTATE_LOCAL_FAILURE 4		/* Set if there was a local failure (eg. ENOMEM) */
+};
+
+/*
  * Record of fileserver with which we're actively communicating.
  */
 struct afs_server {
@@ -493,7 +556,6 @@ struct afs_server {
 		struct afs_uuid	_uuid;
 	};
 
-	struct afs_addr_list	__rcu *addresses;
 	struct afs_cell		*cell;		/* Cell to which belongs (pins ref) */
 	struct rb_node		uuid_rb;	/* Link in net->fs_servers */
 	struct afs_server __rcu	*uuid_next;	/* Next server with same UUID */
@@ -502,7 +564,7 @@ struct afs_server {
 	struct hlist_node	addr4_link;	/* Link in net->fs_addresses4 */
 	struct hlist_node	addr6_link;	/* Link in net->fs_addresses6 */
 	struct hlist_node	proc_link;	/* Link in net->fs_proc */
-	struct work_struct	initcb_work;	/* Work for CB.InitCallBackState* */
+	struct list_head	volumes;	/* RCU list of afs_server_entry objects */
 	struct afs_server	*gc_next;	/* Next server in manager's list */
 	time64_t		unuse_time;	/* Time at which last unused */
 	unsigned long		flags;
@@ -520,43 +582,47 @@ struct afs_server {
 	refcount_t		ref;		/* Object refcount */
 	atomic_t		active;		/* Active user count */
 	u32			addr_version;	/* Address list version */
+	u16			service_id;	/* Service ID we're using. */
 	unsigned int		rtt;		/* Server's current RTT in uS */
 	unsigned int		debug_id;	/* Debugging ID for traces */
 
 	/* file service access */
 	rwlock_t		fs_lock;	/* access lock */
 
-	/* callback promise management */
-	unsigned		cb_s_break;	/* Break-everything counter. */
-
 	/* Probe state */
+	struct afs_endpoint_state __rcu *endpoint_state; /* Latest endpoint/probe state */
 	unsigned long		probed_at;	/* Time last probe was dispatched (jiffies) */
 	wait_queue_head_t	probe_wq;
-	atomic_t		probe_outstanding;
+	unsigned int		probe_counter;	/* Number of probes issued */
 	spinlock_t		probe_lock;
-	struct {
-		unsigned int	rtt;		/* RTT in uS */
-		u32		abort_code;
-		short		error;
-		bool		responded:1;
-		bool		is_yfs:1;
-		bool		not_yfs:1;
-		bool		local_failure:1;
-	} probe;
 };
 
+enum afs_ro_replicating {
+	AFS_RO_NOT_REPLICATING,			/* Not doing replication */
+	AFS_RO_REPLICATING_USE_OLD,		/* Replicating; use old version */
+	AFS_RO_REPLICATING_USE_NEW,		/* Replicating; switch to new version */
+} __mode(byte);
+
 /*
  * Replaceable volume server list.
  */
 struct afs_server_entry {
 	struct afs_server	*server;
+	struct afs_volume	*volume;
+	struct list_head	slink;		/* Link in server->volumes */
+	time64_t		cb_expires_at;	/* Time at which volume-level callback expires */
+	unsigned long		flags;
+#define AFS_SE_EXCLUDED		0		/* Set if server is to be excluded in rotation */
+#define AFS_SE_VOLUME_OFFLINE	1		/* Set if volume offline notice given */
+#define AFS_SE_VOLUME_BUSY	2		/* Set if volume busy notice given */
 };
 
 struct afs_server_list {
-	afs_volid_t		vids[AFS_MAXTYPES]; /* Volume IDs */
+	struct rcu_head		rcu;
 	refcount_t		usage;
+	bool			attached;	/* T if attached to servers */
+	enum afs_ro_replicating	ro_replicating;	/* RW->RO update (probably) in progress */
 	unsigned char		nr_servers;
-	unsigned char		preferred;	/* Preferred server */
 	unsigned short		vnovol_mask;	/* Servers to be skipped due to VNOVOL */
 	unsigned int		seq;		/* Set to ->servers_seq when installed */
 	rwlock_t		lock;
@@ -567,24 +633,23 @@ struct afs_server_list {
  * Live AFS volume management.
  */
 struct afs_volume {
-	union {
-		struct rcu_head	rcu;
-		afs_volid_t	vid;		/* volume ID */
-	};
+	struct rcu_head	rcu;
+	afs_volid_t		vid;		/* The volume ID of this volume */
+	afs_volid_t		vids[AFS_MAXTYPES]; /* All associated volume IDs */
 	refcount_t		ref;
 	time64_t		update_at;	/* Time at which to next update */
 	struct afs_cell		*cell;		/* Cell to which belongs (pins ref) */
 	struct rb_node		cell_node;	/* Link in cell->volumes */
 	struct hlist_node	proc_link;	/* Link in cell->proc_volumes */
 	struct super_block __rcu *sb;		/* Superblock on which inodes reside */
+	struct work_struct	destructor;	/* Deferred destructor */
 	unsigned long		flags;
 #define AFS_VOLUME_NEEDS_UPDATE	0	/* - T if an update needs performing */
 #define AFS_VOLUME_UPDATING	1	/* - T if an update is in progress */
 #define AFS_VOLUME_WAIT		2	/* - T if users must wait for update */
 #define AFS_VOLUME_DELETED	3	/* - T if volume appears deleted */
-#define AFS_VOLUME_OFFLINE	4	/* - T if volume offline notice given */
-#define AFS_VOLUME_BUSY		5	/* - T if volume busy notice given */
-#define AFS_VOLUME_MAYBE_NO_IBULK 6	/* - T if some servers don't have InlineBulkStatus */
+#define AFS_VOLUME_MAYBE_NO_IBULK 4	/* - T if some servers don't have InlineBulkStatus */
+#define AFS_VOLUME_RM_TREE	5	/* - Set if volume removed from cell->volumes */
 #ifdef CONFIG_AFS_FSCACHE
 	struct fscache_volume	*cache;		/* Caching cookie */
 #endif
@@ -592,8 +657,21 @@ struct afs_volume {
 	rwlock_t		servers_lock;	/* Lock for ->servers */
 	unsigned int		servers_seq;	/* Incremented each time ->servers changes */
 
-	unsigned		cb_v_break;	/* Break-everything counter. */
+	/* RO release tracking */
+	struct mutex		volsync_lock;	/* Time/state evaluation lock */
+	time64_t		creation_time;	/* Volume creation time (or TIME64_MIN) */
+	time64_t		update_time;	/* Volume update time (or TIME64_MIN) */
+
+	/* Callback management */
+	struct mutex		cb_check_lock;	/* Lock to control race to check after v_break */
+	time64_t		cb_expires_at;	/* Earliest volume callback expiry time */
+	atomic_t		cb_ro_snapshot;	/* RO volume update-from-snapshot counter */
+	atomic_t		cb_v_break;	/* Volume-break event counter. */
+	atomic_t		cb_v_check;	/* Volume-break has-been-checked counter. */
+	atomic_t		cb_scrub;	/* Scrub-all-data event counter. */
 	rwlock_t		cb_v_break_lock;
+	struct rw_semaphore	open_mmaps_lock;
+	struct list_head	open_mmaps;	/* List of vnodes that are mmapped */
 
 	afs_voltype_t		type;		/* type of volume */
 	char			type_force;	/* force volume type (suppress R/O -> R/W) */
@@ -632,7 +710,6 @@ struct afs_vnode {
 	spinlock_t		wb_lock;	/* lock for wb_keys */
 	spinlock_t		lock;		/* waitqueue/flags lock */
 	unsigned long		flags;
-#define AFS_VNODE_CB_PROMISED	0		/* Set if vnode has a callback promise */
 #define AFS_VNODE_UNSET		1		/* set if vnode attributes not yet set */
 #define AFS_VNODE_DIR_VALID	2		/* Set if dir contents are valid */
 #define AFS_VNODE_ZAP_DATA	3		/* set if vnode's data should be invalidated */
@@ -658,13 +735,14 @@ struct afs_vnode {
 	struct list_head	cb_mmap_link;	/* Link in cell->fs_open_mmaps */
 	void			*cb_server;	/* Server with callback/filelock */
 	atomic_t		cb_nr_mmap;	/* Number of mmaps */
-	unsigned int		cb_fs_s_break;	/* Mass server break counter (cell->fs_s_break) */
-	unsigned int		cb_s_break;	/* Mass break counter on ->server */
-	unsigned int		cb_v_break;	/* Mass break counter on ->volume */
+	unsigned int		cb_ro_snapshot;	/* RO volume release counter on ->volume */
+	unsigned int		cb_scrub;	/* Scrub counter on ->volume */
 	unsigned int		cb_break;	/* Break counter on vnode */
+	unsigned int		cb_v_check;	/* Break check counter on ->volume */
 	seqlock_t		cb_lock;	/* Lock for ->cb_server, ->status, ->cb_*break */
 
-	time64_t		cb_expires_at;	/* time at which callback expires */
+	atomic64_t		cb_expires_at;	/* time at which callback expires */
+#define AFS_NO_CB_PROMISE TIME64_MIN
 };
 
 static inline struct fscache_cookie *afs_vnode_cache(struct afs_vnode *vnode)
@@ -712,40 +790,49 @@ struct afs_permits {
  * Error prioritisation and accumulation.
  */
 struct afs_error {
-	short	error;			/* Accumulated error */
+	s32	abort_code;		/* Cumulative abort code */
+	short	error;			/* Cumulative error */
 	bool	responded;		/* T if server responded */
-};
-
-/*
- * Cursor for iterating over a server's address list.
- */
-struct afs_addr_cursor {
-	struct afs_addr_list	*alist;		/* Current address list (pins ref) */
-	unsigned long		tried;		/* Tried addresses */
-	signed char		index;		/* Current address */
-	bool			responded;	/* T if the current address responded */
-	unsigned short		nr_iterations;	/* Number of address iterations */
-	short			error;
-	u32			abort_code;
+	bool	aborted;		/* T if ->error is from an abort */
 };
 
 /*
  * Cursor for iterating over a set of volume location servers.
  */
 struct afs_vl_cursor {
-	struct afs_addr_cursor	ac;
 	struct afs_cell		*cell;		/* The cell we're querying */
 	struct afs_vlserver_list *server_list;	/* Current server list (pins ref) */
 	struct afs_vlserver	*server;	/* Server on which this resides */
+	struct afs_addr_list	*alist;		/* Current address list (pins ref) */
 	struct key		*key;		/* Key for the server */
-	unsigned long		untried;	/* Bitmask of untried servers */
-	short			index;		/* Current server */
-	short			error;
+	unsigned long		untried_servers; /* Bitmask of untried servers */
+	unsigned long		addr_tried;	/* Tried addresses */
+	struct afs_error	cumul_error;	/* Cumulative error */
+	unsigned int		debug_id;
+	s32			call_abort_code;
+	short			call_error;	/* Error from single call */
+	short			server_index;	/* Current server */
+	signed char		addr_index;	/* Current address */
 	unsigned short		flags;
 #define AFS_VL_CURSOR_STOP	0x0001		/* Set to cease iteration */
 #define AFS_VL_CURSOR_RETRY	0x0002		/* Set to do a retry */
 #define AFS_VL_CURSOR_RETRIED	0x0004		/* Set if started a retry */
-	unsigned short		nr_iterations;	/* Number of server iterations */
+	short			nr_iterations;	/* Number of server iterations */
+	bool			call_responded;	/* T if the current address responded */
+};
+
+/*
+ * Fileserver state tracking for an operation.  An array of these is kept,
+ * indexed by server index.
+ */
+struct afs_server_state {
+	/* Tracking of fileserver probe state.  Other operations may interfere
+	 * by probing a fileserver when accessing other volumes.
+	 */
+	unsigned int		probe_seq;
+	unsigned long		untried_addrs;	/* Addresses we haven't tried yet */
+	struct wait_queue_entry	probe_waiter;
+	struct afs_endpoint_state *endpoint_state; /* Endpoint state being monitored */
 };
 
 /*
@@ -766,7 +853,7 @@ struct afs_vnode_param {
 	struct afs_fid		fid;		/* Fid to access */
 	struct afs_status_cb	scb;		/* Returned status and callback promise */
 	afs_dataversion_t	dv_before;	/* Data version before the call */
-	unsigned int		cb_break_before; /* cb_break + cb_s_break before the call */
+	unsigned int		cb_break_before; /* cb_break before the call */
 	u8			dv_delta;	/* Expected change in data version */
 	bool			put_vnode:1;	/* T if we have a ref on the vnode */
 	bool			need_io_lock:1;	/* T if we need the I/O lock on this */
@@ -791,17 +878,17 @@ struct afs_operation {
 	struct afs_volume	*volume;	/* Volume being accessed */
 	struct afs_vnode_param	file[2];
 	struct afs_vnode_param	*more_files;
-	struct afs_volsync	volsync;
+	struct afs_volsync	pre_volsync;	/* Volsync before op */
+	struct afs_volsync	volsync;	/* Volsync returned by op */
 	struct dentry		*dentry;	/* Dentry to be altered */
 	struct dentry		*dentry_2;	/* Second dentry to be altered */
 	struct timespec64	mtime;		/* Modification time to record */
 	struct timespec64	ctime;		/* Change time to set */
+	struct afs_error	cumul_error;	/* Cumulative error */
 	short			nr_files;	/* Number of entries in file[], more_files */
-	short			error;
 	unsigned int		debug_id;
 
 	unsigned int		cb_v_break;	/* Volume break counter before op */
-	unsigned int		cb_s_break;	/* Server break counter before op */
 
 	union {
 		struct {
@@ -846,13 +933,19 @@ struct afs_operation {
 	};
 
 	/* Fileserver iteration state */
-	struct afs_addr_cursor	ac;
 	struct afs_server_list	*server_list;	/* Current server list (pins ref) */
 	struct afs_server	*server;	/* Server we're using (ref pinned by server_list) */
+	struct afs_endpoint_state *estate;	/* Current endpoint state (doesn't pin ref) */
+	struct afs_server_state	*server_states;	/* States of the servers involved */
 	struct afs_call		*call;
-	unsigned long		untried;	/* Bitmask of untried servers */
-	short			index;		/* Current server */
-	unsigned short		nr_iterations;	/* Number of server iterations */
+	unsigned long		untried_servers; /* Bitmask of untried servers */
+	unsigned long		addr_tried;	/* Tried addresses */
+	s32			call_abort_code; /* Abort code from single call */
+	short			call_error;	/* Error from single call */
+	short			server_index;	/* Current server */
+	short			nr_iterations;	/* Number of server iterations */
+	signed char		addr_index;	/* Current address */
+	bool			call_responded;	/* T if the current address responded */
 
 	unsigned int		flags;
 #define AFS_OPERATION_STOP		0x0001	/* Set to cease iteration */
@@ -954,31 +1047,32 @@ static inline bool afs_is_folio_dirty_mmapped(unsigned long priv)
 /*
  * addr_list.c
  */
-static inline struct afs_addr_list *afs_get_addrlist(struct afs_addr_list *alist)
-{
-	if (alist)
-		refcount_inc(&alist->usage);
-	return alist;
-}
-extern struct afs_addr_list *afs_alloc_addrlist(unsigned int,
-						unsigned short,
-						unsigned short);
-extern void afs_put_addrlist(struct afs_addr_list *);
+struct afs_addr_list *afs_get_addrlist(struct afs_addr_list *alist, enum afs_alist_trace reason);
+extern struct afs_addr_list *afs_alloc_addrlist(unsigned int nr);
+extern void afs_put_addrlist(struct afs_addr_list *alist, enum afs_alist_trace reason);
 extern struct afs_vlserver_list *afs_parse_text_addrs(struct afs_net *,
 						      const char *, size_t, char,
 						      unsigned short, unsigned short);
+bool afs_addr_list_same(const struct afs_addr_list *a,
+			const struct afs_addr_list *b);
 extern struct afs_vlserver_list *afs_dns_query(struct afs_cell *, time64_t *);
-extern bool afs_iterate_addresses(struct afs_addr_cursor *);
-extern int afs_end_cursor(struct afs_addr_cursor *);
 
-extern void afs_merge_fs_addr4(struct afs_addr_list *, __be32, u16);
-extern void afs_merge_fs_addr6(struct afs_addr_list *, __be32 *, u16);
+extern int afs_merge_fs_addr4(struct afs_net *net, struct afs_addr_list *addr,
+			      __be32 xdr, u16 port);
+extern int afs_merge_fs_addr6(struct afs_net *net, struct afs_addr_list *addr,
+			      __be32 *xdr, u16 port);
+
+/*
+ * addr_prefs.c
+ */
+int afs_proc_addr_prefs_write(struct file *file, char *buf, size_t size);
+void afs_get_address_preferences_rcu(struct afs_net *net, struct afs_addr_list *alist);
+void afs_get_address_preferences(struct afs_net *net, struct afs_addr_list *alist);
 
 /*
  * callback.c
  */
 extern void afs_invalidate_mmap_work(struct work_struct *);
-extern void afs_server_init_callback_work(struct work_struct *work);
 extern void afs_init_callback_state(struct afs_server *);
 extern void __afs_break_callback(struct afs_vnode *, enum afs_cb_break_reason);
 extern void afs_break_callback(struct afs_vnode *, enum afs_cb_break_reason);
@@ -986,13 +1080,15 @@ extern void afs_break_callbacks(struct afs_server *, size_t, struct afs_callback
 
 static inline unsigned int afs_calc_vnode_cb_break(struct afs_vnode *vnode)
 {
-	return vnode->cb_break + vnode->cb_v_break;
+	return vnode->cb_break + vnode->cb_ro_snapshot + vnode->cb_scrub;
 }
 
 static inline bool afs_cb_is_broken(unsigned int cb_break,
 				    const struct afs_vnode *vnode)
 {
-	return cb_break != (vnode->cb_break + vnode->volume->cb_v_break);
+	return cb_break != (vnode->cb_break +
+			    atomic_read(&vnode->volume->cb_ro_snapshot) +
+			    atomic_read(&vnode->volume->cb_scrub));
 }
 
 /*
@@ -1108,15 +1204,16 @@ extern void afs_fs_get_volume_status(struct afs_operation *);
 extern void afs_fs_set_lock(struct afs_operation *);
 extern void afs_fs_extend_lock(struct afs_operation *);
 extern void afs_fs_release_lock(struct afs_operation *);
-extern int afs_fs_give_up_all_callbacks(struct afs_net *, struct afs_server *,
-					struct afs_addr_cursor *, struct key *);
-extern bool afs_fs_get_capabilities(struct afs_net *, struct afs_server *,
-				    struct afs_addr_cursor *, struct key *);
+int afs_fs_give_up_all_callbacks(struct afs_net *net, struct afs_server *server,
+				 struct afs_address *addr, struct key *key);
+bool afs_fs_get_capabilities(struct afs_net *net, struct afs_server *server,
+			     struct afs_endpoint_state *estate, unsigned int addr_index,
+			     struct key *key);
 extern void afs_fs_inline_bulk_status(struct afs_operation *);
 
 struct afs_acl {
 	u32	size;
-	u8	data[];
+	u8	data[] __counted_by(size);
 };
 
 extern void afs_fs_fetch_acl(struct afs_operation *);
@@ -1131,11 +1228,6 @@ extern bool afs_begin_vnode_operation(struct afs_operation *);
 extern void afs_wait_for_operation(struct afs_operation *);
 extern int afs_do_sync_operation(struct afs_operation *);
 
-static inline void afs_op_nomem(struct afs_operation *op)
-{
-	op->error = -ENOMEM;
-}
-
 static inline void afs_op_set_vnode(struct afs_operation *op, unsigned int n,
 				    struct afs_vnode *vnode)
 {
@@ -1152,12 +1244,17 @@ static inline void afs_op_set_fid(struct afs_operation *op, unsigned int n,
 /*
  * fs_probe.c
  */
+struct afs_endpoint_state *afs_get_endpoint_state(struct afs_endpoint_state *estate,
+						  enum afs_estate_trace where);
+void afs_put_endpoint_state(struct afs_endpoint_state *estate, enum afs_estate_trace where);
 extern void afs_fileserver_probe_result(struct afs_call *);
-extern void afs_fs_probe_fileserver(struct afs_net *, struct afs_server *, struct key *, bool);
-extern int afs_wait_for_fs_probes(struct afs_server_list *, unsigned long);
+void afs_fs_probe_fileserver(struct afs_net *net, struct afs_server *server,
+			     struct afs_addr_list *new_addrs, struct key *key);
+int afs_wait_for_fs_probes(struct afs_operation *op, struct afs_server_state *states, bool intr);
 extern void afs_probe_fileserver(struct afs_net *, struct afs_server *);
 extern void afs_fs_probe_dispatcher(struct work_struct *);
-extern int afs_wait_for_one_fs_probe(struct afs_server *, bool);
+int afs_wait_for_one_fs_probe(struct afs_server *server, struct afs_endpoint_state *estate,
+			      unsigned long exclude, bool is_intr);
 extern void afs_fs_probe_cleanup(struct afs_net *);
 
 /*
@@ -1171,9 +1268,6 @@ extern int afs_ilookup5_test_by_fid(struct inode *, void *);
 extern struct inode *afs_iget_pseudo_dir(struct super_block *, bool);
 extern struct inode *afs_iget(struct afs_operation *, struct afs_vnode_param *);
 extern struct inode *afs_root_iget(struct super_block *, struct key *);
-extern bool afs_check_validity(struct afs_vnode *);
-extern int afs_validate(struct afs_vnode *, struct key *);
-bool afs_pagecache_valid(struct afs_vnode *);
 extern int afs_getattr(struct mnt_idmap *idmap, const struct path *,
 		       struct kstat *, u32, unsigned int);
 extern int afs_setattr(struct mnt_idmap *idmap, struct dentry *, struct iattr *);
@@ -1229,6 +1323,31 @@ static inline void __afs_stat(atomic_t *s)
 extern int afs_abort_to_error(u32);
 extern void afs_prioritise_error(struct afs_error *, int, u32);
 
+static inline void afs_op_nomem(struct afs_operation *op)
+{
+	op->cumul_error.error = -ENOMEM;
+}
+
+static inline int afs_op_error(const struct afs_operation *op)
+{
+	return op->cumul_error.error;
+}
+
+static inline s32 afs_op_abort_code(const struct afs_operation *op)
+{
+	return op->cumul_error.abort_code;
+}
+
+static inline int afs_op_set_error(struct afs_operation *op, int error)
+{
+	return op->cumul_error.error = error;
+}
+
+static inline void afs_op_accumulate_error(struct afs_operation *op, int error, s32 abort_code)
+{
+	afs_prioritise_error(&op->cumul_error, error, abort_code);
+}
+
 /*
  * mntpt.c
  */
@@ -1259,6 +1378,7 @@ static inline void afs_put_sysnames(struct afs_sysnames *sysnames) {}
 /*
  * rotate.c
  */
+void afs_clear_server_states(struct afs_operation *op);
 extern bool afs_select_fileserver(struct afs_operation *);
 extern void afs_dump_edestaddrreq(const struct afs_operation *);
 
@@ -1271,8 +1391,8 @@ extern int __net_init afs_open_socket(struct afs_net *);
 extern void __net_exit afs_close_socket(struct afs_net *);
 extern void afs_charge_preallocation(struct work_struct *);
 extern void afs_put_call(struct afs_call *);
-extern void afs_make_call(struct afs_addr_cursor *, struct afs_call *, gfp_t);
-extern long afs_wait_for_call_to_complete(struct afs_call *, struct afs_addr_cursor *);
+void afs_make_call(struct afs_call *call, gfp_t gfp);
+void afs_wait_for_call_to_complete(struct afs_call *call);
 extern struct afs_call *afs_alloc_flat_call(struct afs_net *,
 					    const struct afs_call_type *,
 					    size_t, size_t);
@@ -1285,12 +1405,16 @@ extern int afs_protocol_error(struct afs_call *, enum afs_eproto_cause);
 static inline void afs_make_op_call(struct afs_operation *op, struct afs_call *call,
 				    gfp_t gfp)
 {
-	op->call = call;
-	op->type = call->type;
-	call->op = op;
-	call->key = op->key;
-	call->intr = !(op->flags & AFS_OPERATION_UNINTR);
-	afs_make_call(&op->ac, call, gfp);
+	struct afs_addr_list *alist = op->estate->addresses;
+
+	op->call	= call;
+	op->type	= call->type;
+	call->op	= op;
+	call->key	= op->key;
+	call->intr	= !(op->flags & AFS_OPERATION_UNINTR);
+	call->peer	= rxrpc_kernel_get_peer(alist->addrs[op->addr_index].peer);
+	call->service_id = op->server->service_id;
+	afs_make_call(call, gfp);
 }
 
 static inline void afs_extract_begin(struct afs_call *call, void *buf, size_t size)
@@ -1399,8 +1523,7 @@ extern void __exit afs_clean_up_permit_cache(void);
  */
 extern spinlock_t afs_server_peer_lock;
 
-extern struct afs_server *afs_find_server(struct afs_net *,
-					  const struct sockaddr_rxrpc *);
+extern struct afs_server *afs_find_server(struct afs_net *, const struct rxrpc_peer *);
 extern struct afs_server *afs_find_server_by_uuid(struct afs_net *, const uuid_t *);
 extern struct afs_server *afs_lookup_server(struct afs_cell *, struct key *, const uuid_t *, u32);
 extern struct afs_server *afs_get_server(struct afs_server *, enum afs_server_trace);
@@ -1412,7 +1535,7 @@ extern void afs_manage_servers(struct work_struct *);
 extern void afs_servers_timer(struct timer_list *);
 extern void afs_fs_probe_timer(struct timer_list *);
 extern void __net_exit afs_purge_servers(struct afs_net *);
-extern bool afs_check_server_record(struct afs_operation *, struct afs_server *);
+bool afs_check_server_record(struct afs_operation *op, struct afs_server *server, struct key *key);
 
 static inline void afs_inc_servers_outstanding(struct afs_net *net)
 {
@@ -1440,10 +1563,14 @@ static inline struct afs_server_list *afs_get_serverlist(struct afs_server_list
 }
 
 extern void afs_put_serverlist(struct afs_net *, struct afs_server_list *);
-extern struct afs_server_list *afs_alloc_server_list(struct afs_cell *, struct key *,
-						     struct afs_vldb_entry *,
-						     u8);
+struct afs_server_list *afs_alloc_server_list(struct afs_volume *volume,
+					      struct key *key,
+					      struct afs_vldb_entry *vldb);
 extern bool afs_annotate_server_list(struct afs_server_list *, struct afs_server_list *);
+void afs_attach_volume_to_servers(struct afs_volume *volume, struct afs_server_list *slist);
+void afs_reattach_volume_to_servers(struct afs_volume *volume, struct afs_server_list *slist,
+				    struct afs_server_list *old);
+void afs_detach_volume_from_servers(struct afs_volume *volume, struct afs_server_list *slist);
 
 /*
  * super.c
@@ -1452,13 +1579,24 @@ extern int __init afs_fs_init(void);
 extern void afs_fs_exit(void);
 
 /*
+ * validation.c
+ */
+bool afs_check_validity(const struct afs_vnode *vnode);
+int afs_update_volume_state(struct afs_operation *op);
+int afs_validate(struct afs_vnode *vnode, struct key *key);
+
+/*
  * vlclient.c
  */
 extern struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_vl_cursor *,
 							 const char *, int);
 extern struct afs_addr_list *afs_vl_get_addrs_u(struct afs_vl_cursor *, const uuid_t *);
-extern struct afs_call *afs_vl_get_capabilities(struct afs_net *, struct afs_addr_cursor *,
-						struct key *, struct afs_vlserver *, unsigned int);
+struct afs_call *afs_vl_get_capabilities(struct afs_net *net,
+					 struct afs_addr_list *alist,
+					 unsigned int addr_index,
+					 struct key *key,
+					 struct afs_vlserver *server,
+					 unsigned int server_index);
 extern struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_vl_cursor *, const uuid_t *);
 extern char *afs_yfsvl_get_cell_name(struct afs_vl_cursor *);
 
@@ -1512,8 +1650,9 @@ extern struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *,
 extern struct afs_volume *afs_create_volume(struct afs_fs_context *);
 extern int afs_activate_volume(struct afs_volume *);
 extern void afs_deactivate_volume(struct afs_volume *);
+bool afs_try_get_volume(struct afs_volume *volume, enum afs_volume_trace reason);
 extern struct afs_volume *afs_get_volume(struct afs_volume *, enum afs_volume_trace);
-extern void afs_put_volume(struct afs_net *, struct afs_volume *, enum afs_volume_trace);
+void afs_put_volume(struct afs_volume *volume, enum afs_volume_trace reason);
 extern int afs_check_volume_status(struct afs_volume *, struct afs_operation *);
 
 /*
@@ -1600,7 +1739,7 @@ static inline void afs_update_dentry_version(struct afs_operation *op,
 					     struct afs_vnode_param *dir_vp,
 					     struct dentry *dentry)
 {
-	if (!op->error)
+	if (!op->cumul_error.error)
 		dentry->d_fsdata =
 			(void *)(unsigned long)dir_vp->scb.status.data_version;
 }
diff --git a/fs/afs/main.c b/fs/afs/main.c
index 6425c81d07de..1b3bd21c168a 100644
--- a/fs/afs/main.c
+++ b/fs/afs/main.c
@@ -156,6 +156,7 @@ static void __net_exit afs_net_exit(struct net *net_ns)
 	afs_close_socket(net);
 	afs_proc_cleanup(net);
 	afs_put_sysnames(net->sysnames);
+	kfree_rcu(rcu_access_pointer(net->address_prefs), rcu);
 }
 
 static struct pernet_operations afs_net_ops = {
diff --git a/fs/afs/misc.c b/fs/afs/misc.c
index 805328ca5428..b8180bf2281f 100644
--- a/fs/afs/misc.c
+++ b/fs/afs/misc.c
@@ -116,6 +116,8 @@ void afs_prioritise_error(struct afs_error *e, int error, u32 abort_code)
 {
 	switch (error) {
 	case 0:
+		e->aborted = false;
+		e->error = 0;
 		return;
 	default:
 		if (e->error == -ETIMEDOUT ||
@@ -161,12 +163,16 @@ void afs_prioritise_error(struct afs_error *e, int error, u32 abort_code)
 		if (e->responded)
 			return;
 		e->error = error;
+		e->aborted = false;
 		return;
 
 	case -ECONNABORTED:
-		error = afs_abort_to_error(abort_code);
-		fallthrough;
+		e->error = afs_abort_to_error(abort_code);
+		e->aborted = true;
+		e->responded = true;
+		return;
 	case -ENETRESET: /* Responded, but we seem to have changed address */
+		e->aborted = false;
 		e->responded = true;
 		e->error = error;
 		return;
diff --git a/fs/afs/proc.c b/fs/afs/proc.c
index 2a0c83d71565..3bd02571f30d 100644
--- a/fs/afs/proc.c
+++ b/fs/afs/proc.c
@@ -147,6 +147,55 @@ inval:
 }
 
 /*
+ * Display the list of addr_prefs known to the namespace.
+ */
+static int afs_proc_addr_prefs_show(struct seq_file *m, void *v)
+{
+	struct afs_addr_preference_list *preflist;
+	struct afs_addr_preference *pref;
+	struct afs_net *net = afs_seq2net_single(m);
+	union {
+		struct sockaddr_in sin;
+		struct sockaddr_in6 sin6;
+	} addr;
+	unsigned int i;
+	char buf[44]; /* Maximum ipv6 + max subnet is 43 */
+
+	rcu_read_lock();
+	preflist = rcu_dereference(net->address_prefs);
+
+	if (!preflist) {
+		seq_puts(m, "NO PREFS\n");
+		return 0;
+	}
+
+	seq_printf(m, "PROT SUBNET                                      PRIOR (v=%u n=%u/%u/%u)\n",
+		   preflist->version, preflist->ipv6_off, preflist->nr, preflist->max_prefs);
+
+	memset(&addr, 0, sizeof(addr));
+
+	for (i = 0; i < preflist->nr; i++) {
+		pref = &preflist->prefs[i];
+
+		addr.sin.sin_family = pref->family;
+		if (pref->family == AF_INET) {
+			memcpy(&addr.sin.sin_addr, &pref->ipv4_addr,
+			       sizeof(addr.sin.sin_addr));
+			snprintf(buf, sizeof(buf), "%pISc/%u", &addr.sin, pref->subnet_mask);
+			seq_printf(m, "UDP  %-43.43s %5u\n", buf, pref->prio);
+		} else {
+			memcpy(&addr.sin6.sin6_addr, &pref->ipv6_addr,
+			       sizeof(addr.sin6.sin6_addr));
+			snprintf(buf, sizeof(buf), "%pISc/%u", &addr.sin6, pref->subnet_mask);
+			seq_printf(m, "UDP  %-43.43s %5u\n", buf, pref->prio);
+		}
+	}
+
+	rcu_read_lock();
+	return 0;
+}
+
+/*
  * Display the name of the current workstation cell.
  */
 static int afs_proc_rootcell_show(struct seq_file *m, void *v)
@@ -307,7 +356,7 @@ static int afs_proc_cell_vlservers_show(struct seq_file *m, void *v)
 		for (i = 0; i < alist->nr_addrs; i++)
 			seq_printf(m, " %c %pISpc\n",
 				   alist->preferred == i ? '>' : '-',
-				   &alist->addrs[i].transport);
+				   rxrpc_kernel_remote_addr(alist->addrs[i].peer));
 	}
 	seq_printf(m, " info: fl=%lx rtt=%d\n", vlserver->flags, vlserver->rtt);
 	seq_printf(m, " probe: fl=%x e=%d ac=%d out=%d\n",
@@ -375,32 +424,45 @@ static const struct seq_operations afs_proc_cell_vlservers_ops = {
  */
 static int afs_proc_servers_show(struct seq_file *m, void *v)
 {
-	struct afs_server *server;
+	struct afs_endpoint_state *estate;
 	struct afs_addr_list *alist;
+	struct afs_server *server;
+	unsigned long failed;
 	int i;
 
 	if (v == SEQ_START_TOKEN) {
-		seq_puts(m, "UUID                                 REF ACT\n");
+		seq_puts(m, "UUID                                 REF ACT CELL\n");
 		return 0;
 	}
 
 	server = list_entry(v, struct afs_server, proc_link);
-	alist = rcu_dereference(server->addresses);
-	seq_printf(m, "%pU %3d %3d\n",
+	estate = rcu_dereference(server->endpoint_state);
+	alist = estate->addresses;
+	seq_printf(m, "%pU %3d %3d %s\n",
 		   &server->uuid,
 		   refcount_read(&server->ref),
-		   atomic_read(&server->active));
-	seq_printf(m, "  - info: fl=%lx rtt=%u brk=%x\n",
-		   server->flags, server->rtt, server->cb_s_break);
-	seq_printf(m, "  - probe: last=%d out=%d\n",
-		   (int)(jiffies - server->probed_at) / HZ,
-		   atomic_read(&server->probe_outstanding));
-	seq_printf(m, "  - ALIST v=%u rsp=%lx f=%lx\n",
-		   alist->version, alist->responded, alist->failed);
-	for (i = 0; i < alist->nr_addrs; i++)
-		seq_printf(m, "    [%x] %pISpc%s\n",
-			   i, &alist->addrs[i].transport,
-			   alist->preferred == i ? "*" : "");
+		   atomic_read(&server->active),
+		   server->cell->name);
+	seq_printf(m, "  - info: fl=%lx rtt=%u\n",
+		   server->flags, server->rtt);
+	seq_printf(m, "  - probe: last=%d\n",
+		   (int)(jiffies - server->probed_at) / HZ);
+	failed = estate->failed_set;
+	seq_printf(m, "  - ESTATE pq=%x np=%u rsp=%lx f=%lx\n",
+		   estate->probe_seq, atomic_read(&estate->nr_probing),
+		   estate->responsive_set, estate->failed_set);
+	seq_printf(m, "  - ALIST v=%u ap=%u\n",
+		   alist->version, alist->addr_pref_version);
+	for (i = 0; i < alist->nr_addrs; i++) {
+		const struct afs_address *addr = &alist->addrs[i];
+
+		seq_printf(m, "    [%x] %pISpc%s rtt=%d err=%d p=%u\n",
+			   i, rxrpc_kernel_remote_addr(addr->peer),
+			   alist->preferred == i ? "*" :
+			   test_bit(i, &failed) ? "!" : "",
+			   rxrpc_kernel_get_srtt(addr->peer),
+			   addr->last_error, addr->prio);
+	}
 	return 0;
 }
 
@@ -681,7 +743,11 @@ int afs_proc_init(struct afs_net *net)
 					&afs_proc_sysname_ops,
 					afs_proc_sysname_write,
 					sizeof(struct seq_net_private),
-					NULL))
+					NULL) ||
+	    !proc_create_net_single_write("addr_prefs", 0644, p,
+					  afs_proc_addr_prefs_show,
+					  afs_proc_addr_prefs_write,
+					  NULL))
 		goto error_tree;
 
 	net->proc_afs = p;
diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index a840c3588ebb..700a27bc8c25 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -13,6 +13,19 @@
 #include <linux/sched/signal.h>
 #include "internal.h"
 #include "afs_fs.h"
+#include "protocol_uae.h"
+
+void afs_clear_server_states(struct afs_operation *op)
+{
+	unsigned int i;
+
+	if (op->server_states) {
+		for (i = 0; i < op->server_list->nr_servers; i++)
+			afs_put_endpoint_state(op->server_states[i].endpoint_state,
+					       afs_estate_trace_put_server_state);
+		kfree(op->server_states);
+	}
+}
 
 /*
  * Begin iteration through a server list, starting with the vnode's last used
@@ -25,14 +38,41 @@ static bool afs_start_fs_iteration(struct afs_operation *op,
 	void *cb_server;
 	int i;
 
+	trace_afs_rotate(op, afs_rotate_trace_start, 0);
+
 	read_lock(&op->volume->servers_lock);
 	op->server_list = afs_get_serverlist(
 		rcu_dereference_protected(op->volume->servers,
 					  lockdep_is_held(&op->volume->servers_lock)));
 	read_unlock(&op->volume->servers_lock);
 
-	op->untried = (1UL << op->server_list->nr_servers) - 1;
-	op->index = READ_ONCE(op->server_list->preferred);
+	op->server_states = kcalloc(op->server_list->nr_servers, sizeof(op->server_states[0]),
+				    GFP_KERNEL);
+	if (!op->server_states) {
+		afs_op_nomem(op);
+		trace_afs_rotate(op, afs_rotate_trace_nomem, 0);
+		return false;
+	}
+
+	rcu_read_lock();
+	for (i = 0; i < op->server_list->nr_servers; i++) {
+		struct afs_endpoint_state *estate;
+		struct afs_server_state *s = &op->server_states[i];
+
+		server = op->server_list->servers[i].server;
+		estate = rcu_dereference(server->endpoint_state);
+		s->endpoint_state = afs_get_endpoint_state(estate,
+							   afs_estate_trace_get_server_state);
+		s->probe_seq = estate->probe_seq;
+		s->untried_addrs = (1UL << estate->addresses->nr_addrs) - 1;
+		init_waitqueue_entry(&s->probe_waiter, current);
+		afs_get_address_preferences(op->net, estate->addresses);
+	}
+	rcu_read_unlock();
+
+
+	op->untried_servers = (1UL << op->server_list->nr_servers) - 1;
+	op->server_index = -1;
 
 	cb_server = vnode->cb_server;
 	if (cb_server) {
@@ -40,7 +80,7 @@ static bool afs_start_fs_iteration(struct afs_operation *op,
 		for (i = 0; i < op->server_list->nr_servers; i++) {
 			server = op->server_list->servers[i].server;
 			if (server == cb_server) {
-				op->index = i;
+				op->server_index = i;
 				goto found_interest;
 			}
 		}
@@ -50,7 +90,8 @@ static bool afs_start_fs_iteration(struct afs_operation *op,
 		 * and have to return an error.
 		 */
 		if (op->flags & AFS_OPERATION_CUR_ONLY) {
-			op->error = -ESTALE;
+			afs_op_set_error(op, -ESTALE);
+			trace_afs_rotate(op, afs_rotate_trace_stale_lock, 0);
 			return false;
 		}
 
@@ -58,7 +99,7 @@ static bool afs_start_fs_iteration(struct afs_operation *op,
 		write_seqlock(&vnode->cb_lock);
 		ASSERTCMP(cb_server, ==, vnode->cb_server);
 		vnode->cb_server = NULL;
-		if (test_and_clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags))
+		if (atomic64_xchg(&vnode->cb_expires_at, AFS_NO_CB_PROMISE) != AFS_NO_CB_PROMISE)
 			vnode->cb_break++;
 		write_sequnlock(&vnode->cb_lock);
 	}
@@ -70,7 +111,7 @@ found_interest:
 /*
  * Post volume busy note.
  */
-static void afs_busy(struct afs_volume *volume, u32 abort_code)
+static void afs_busy(struct afs_operation *op, u32 abort_code)
 {
 	const char *m;
 
@@ -81,7 +122,8 @@ static void afs_busy(struct afs_volume *volume, u32 abort_code)
 	default:		m = "busy";		break;
 	}
 
-	pr_notice("kAFS: Volume %llu '%s' is %s\n", volume->vid, volume->name, m);
+	pr_notice("kAFS: Volume %llu '%s' on server %pU is %s\n",
+		  op->volume->vid, op->volume->name, &op->server->uuid, m);
 }
 
 /*
@@ -89,10 +131,11 @@ static void afs_busy(struct afs_volume *volume, u32 abort_code)
  */
 static bool afs_sleep_and_retry(struct afs_operation *op)
 {
+	trace_afs_rotate(op, afs_rotate_trace_busy_sleep, 0);
 	if (!(op->flags & AFS_OPERATION_UNINTR)) {
 		msleep_interruptible(1000);
 		if (signal_pending(current)) {
-			op->error = -ERESTARTSYS;
+			afs_op_set_error(op, -ERESTARTSYS);
 			return false;
 		}
 	} else {
@@ -111,62 +154,105 @@ bool afs_select_fileserver(struct afs_operation *op)
 	struct afs_addr_list *alist;
 	struct afs_server *server;
 	struct afs_vnode *vnode = op->file[0].vnode;
-	struct afs_error e;
-	u32 rtt;
-	int error = op->ac.error, i;
+	unsigned long set, failed;
+	s32 abort_code = op->call_abort_code;
+	int best_prio = 0;
+	int error = op->call_error, addr_index, i, j;
+
+	op->nr_iterations++;
 
-	_enter("%lx[%d],%lx[%d],%d,%d",
-	       op->untried, op->index,
-	       op->ac.tried, op->ac.index,
-	       error, op->ac.abort_code);
+	_enter("OP=%x+%x,%llx,%u{%lx},%u{%lx},%d,%d",
+	       op->debug_id, op->nr_iterations, op->volume->vid,
+	       op->server_index, op->untried_servers,
+	       op->addr_index, op->addr_tried,
+	       error, abort_code);
 
 	if (op->flags & AFS_OPERATION_STOP) {
+		trace_afs_rotate(op, afs_rotate_trace_stopped, 0);
 		_leave(" = f [stopped]");
 		return false;
 	}
 
-	op->nr_iterations++;
-
-	/* Evaluate the result of the previous operation, if there was one. */
-	switch (error) {
-	case SHRT_MAX:
+	if (op->nr_iterations == 0)
 		goto start;
 
+	WRITE_ONCE(op->estate->addresses->addrs[op->addr_index].last_error, error);
+	trace_afs_rotate(op, afs_rotate_trace_iter, op->call_error);
+
+	/* Evaluate the result of the previous operation, if there was one. */
+	switch (op->call_error) {
 	case 0:
+		clear_bit(AFS_SE_VOLUME_OFFLINE,
+			  &op->server_list->servers[op->server_index].flags);
+		clear_bit(AFS_SE_VOLUME_BUSY,
+			  &op->server_list->servers[op->server_index].flags);
+		op->cumul_error.responded = true;
+
+		/* We succeeded, but we may need to redo the op from another
+		 * server if we're looking at a set of RO volumes where some of
+		 * the servers have not yet been brought up to date lest we
+		 * regress the data.  We only switch to the new version once
+		 * >=50% of the servers are updated.
+		 */
+		error = afs_update_volume_state(op);
+		if (error != 0) {
+			if (error == 1) {
+				afs_sleep_and_retry(op);
+				goto restart_from_beginning;
+			}
+			afs_op_set_error(op, error);
+			goto failed;
+		}
+		fallthrough;
 	default:
 		/* Success or local failure.  Stop. */
-		op->error = error;
+		afs_op_set_error(op, error);
 		op->flags |= AFS_OPERATION_STOP;
+		trace_afs_rotate(op, afs_rotate_trace_stop, error);
 		_leave(" = f [okay/local %d]", error);
 		return false;
 
 	case -ECONNABORTED:
 		/* The far side rejected the operation on some grounds.  This
 		 * might involve the server being busy or the volume having been moved.
+		 *
+		 * Note that various V* errors should not be sent to a cache manager
+		 * by a fileserver as they should be translated to more modern UAE*
+		 * errors instead.  IBM AFS and OpenAFS fileservers, however, do leak
+		 * these abort codes.
 		 */
-		switch (op->ac.abort_code) {
+		trace_afs_rotate(op, afs_rotate_trace_aborted, abort_code);
+		op->cumul_error.responded = true;
+		switch (abort_code) {
 		case VNOVOL:
 			/* This fileserver doesn't know about the volume.
 			 * - May indicate that the VL is wrong - retry once and compare
 			 *   the results.
 			 * - May indicate that the fileserver couldn't attach to the vol.
+			 * - The volume might have been temporarily removed so that it can
+			 *   be replaced by a volume restore.  "vos" might have ended one
+			 *   transaction and has yet to create the next.
+			 * - The volume might not be blessed or might not be in-service
+			 *   (administrative action).
 			 */
 			if (op->flags & AFS_OPERATION_VNOVOL) {
-				op->error = -EREMOTEIO;
+				afs_op_accumulate_error(op, -EREMOTEIO, abort_code);
 				goto next_server;
 			}
 
 			write_lock(&op->volume->servers_lock);
-			op->server_list->vnovol_mask |= 1 << op->index;
+			op->server_list->vnovol_mask |= 1 << op->server_index;
 			write_unlock(&op->volume->servers_lock);
 
 			set_bit(AFS_VOLUME_NEEDS_UPDATE, &op->volume->flags);
 			error = afs_check_volume_status(op->volume, op);
-			if (error < 0)
-				goto failed_set_error;
+			if (error < 0) {
+				afs_op_set_error(op, error);
+				goto failed;
+			}
 
 			if (test_bit(AFS_VOLUME_DELETED, &op->volume->flags)) {
-				op->error = -ENOMEDIUM;
+				afs_op_set_error(op, -ENOMEDIUM);
 				goto failed;
 			}
 
@@ -174,7 +260,7 @@ bool afs_select_fileserver(struct afs_operation *op)
 			 * it's the fileserver having trouble.
 			 */
 			if (rcu_access_pointer(op->volume->servers) == op->server_list) {
-				op->error = -EREMOTEIO;
+				afs_op_accumulate_error(op, -EREMOTEIO, abort_code);
 				goto next_server;
 			}
 
@@ -183,50 +269,99 @@ bool afs_select_fileserver(struct afs_operation *op)
 			_leave(" = t [vnovol]");
 			return true;
 
-		case VSALVAGE: /* TODO: Should this return an error or iterate? */
 		case VVOLEXISTS:
-		case VNOSERVICE:
 		case VONLINE:
-		case VDISKFULL:
-		case VOVERQUOTA:
-			op->error = afs_abort_to_error(op->ac.abort_code);
+			/* These should not be returned from the fileserver. */
+			pr_warn("Fileserver returned unexpected abort %d\n",
+				abort_code);
+			afs_op_accumulate_error(op, -EREMOTEIO, abort_code);
 			goto next_server;
 
+		case VNOSERVICE:
+			/* Prior to AFS 3.2 VNOSERVICE was returned from the fileserver
+			 * if the volume was neither in-service nor administratively
+			 * blessed.  All usage was replaced by VNOVOL because AFS 3.1 and
+			 * earlier cache managers did not handle VNOSERVICE and assumed
+			 * it was the client OSes errno 105.
+			 *
+			 * Starting with OpenAFS 1.4.8 VNOSERVICE was repurposed as the
+			 * fileserver idle dead time error which was sent in place of
+			 * RX_CALL_TIMEOUT (-3).  The error was intended to be sent if the
+			 * fileserver took too long to send a reply to the client.
+			 * RX_CALL_TIMEOUT would have caused the cache manager to mark the
+			 * server down whereas VNOSERVICE since AFS 3.2 would cause cache
+			 * manager to temporarily (up to 15 minutes) mark the volume
+			 * instance as unusable.
+			 *
+			 * The idle dead logic resulted in cache inconsistency since a
+			 * state changing call that the cache manager assumed was dead
+			 * could still be processed to completion by the fileserver.  This
+			 * logic was removed in OpenAFS 1.8.0 and VNOSERVICE is no longer
+			 * returned.  However, many 1.4.8 through 1.6.24 fileservers are
+			 * still in existence.
+			 *
+			 * AuriStorFS fileservers have never returned VNOSERVICE.
+			 *
+			 * VNOSERVICE should be treated as an alias for RX_CALL_TIMEOUT.
+			 */
+		case RX_CALL_TIMEOUT:
+			afs_op_accumulate_error(op, -ETIMEDOUT, abort_code);
+			goto next_server;
+
+		case VSALVAGING: /* This error should not be leaked to cache managers
+				  * but is from OpenAFS demand attach fileservers.
+				  * It should be treated as an alias for VOFFLINE.
+				  */
+		case VSALVAGE: /* VSALVAGE should be treated as a synonym of VOFFLINE */
 		case VOFFLINE:
-			if (!test_and_set_bit(AFS_VOLUME_OFFLINE, &op->volume->flags)) {
-				afs_busy(op->volume, op->ac.abort_code);
-				clear_bit(AFS_VOLUME_BUSY, &op->volume->flags);
+			/* The volume is in use by the volserver or another volume utility
+			 * for an operation that might alter the contents.  The volume is
+			 * expected to come back but it might take a long time (could be
+			 * days).
+			 */
+			if (!test_and_set_bit(AFS_SE_VOLUME_OFFLINE,
+					      &op->server_list->servers[op->server_index].flags)) {
+				afs_busy(op, abort_code);
+				clear_bit(AFS_SE_VOLUME_BUSY,
+					  &op->server_list->servers[op->server_index].flags);
 			}
 			if (op->flags & AFS_OPERATION_NO_VSLEEP) {
-				op->error = -EADV;
-				goto failed;
-			}
-			if (op->flags & AFS_OPERATION_CUR_ONLY) {
-				op->error = -ESTALE;
+				afs_op_set_error(op, -EADV);
 				goto failed;
 			}
 			goto busy;
 
-		case VSALVAGING:
-		case VRESTARTING:
+		case VRESTARTING: /* The fileserver is either shutting down or starting up. */
 		case VBUSY:
-			/* Retry after going round all the servers unless we
-			 * have a file lock we need to maintain.
+			/* The volume is in use by the volserver or another volume
+			 * utility for an operation that is not expected to alter the
+			 * contents of the volume.  VBUSY does not need to be returned
+			 * for a ROVOL or BACKVOL bound to an ITBusy volserver
+			 * transaction.  The fileserver is permitted to continue serving
+			 * content from ROVOLs and BACKVOLs during an ITBusy transaction
+			 * because the content will not change.  However, many fileserver
+			 * releases do return VBUSY for ROVOL and BACKVOL instances under
+			 * many circumstances.
+			 *
+			 * Retry after going round all the servers unless we have a file
+			 * lock we need to maintain.
 			 */
 			if (op->flags & AFS_OPERATION_NO_VSLEEP) {
-				op->error = -EBUSY;
+				afs_op_set_error(op, -EBUSY);
 				goto failed;
 			}
-			if (!test_and_set_bit(AFS_VOLUME_BUSY, &op->volume->flags)) {
-				afs_busy(op->volume, op->ac.abort_code);
-				clear_bit(AFS_VOLUME_OFFLINE, &op->volume->flags);
+			if (!test_and_set_bit(AFS_SE_VOLUME_BUSY,
+					      &op->server_list->servers[op->server_index].flags)) {
+				afs_busy(op, abort_code);
+				clear_bit(AFS_SE_VOLUME_OFFLINE,
+					  &op->server_list->servers[op->server_index].flags);
 			}
 		busy:
 			if (op->flags & AFS_OPERATION_CUR_ONLY) {
 				if (!afs_sleep_and_retry(op))
 					goto failed;
 
-				 /* Retry with same server & address */
+				/* Retry with same server & address */
 				_leave(" = t [vbusy]");
 				return true;
 			}
@@ -243,7 +378,7 @@ bool afs_select_fileserver(struct afs_operation *op)
 			 * honour, just in case someone sets up a loop.
 			 */
 			if (op->flags & AFS_OPERATION_VMOVED) {
-				op->error = -EREMOTEIO;
+				afs_op_set_error(op, -EREMOTEIO);
 				goto failed;
 			}
 			op->flags |= AFS_OPERATION_VMOVED;
@@ -251,8 +386,10 @@ bool afs_select_fileserver(struct afs_operation *op)
 			set_bit(AFS_VOLUME_WAIT, &op->volume->flags);
 			set_bit(AFS_VOLUME_NEEDS_UPDATE, &op->volume->flags);
 			error = afs_check_volume_status(op->volume, op);
-			if (error < 0)
-				goto failed_set_error;
+			if (error < 0) {
+				afs_op_set_error(op, error);
+				goto failed;
+			}
 
 			/* If the server list didn't change, then the VLDB is
 			 * out of sync with the fileservers.  This is hopefully
@@ -264,22 +401,50 @@ bool afs_select_fileserver(struct afs_operation *op)
 			 * TODO: Retry a few times with sleeps.
 			 */
 			if (rcu_access_pointer(op->volume->servers) == op->server_list) {
-				op->error = -ENOMEDIUM;
+				afs_op_accumulate_error(op, -ENOMEDIUM, abort_code);
 				goto failed;
 			}
 
 			goto restart_from_beginning;
 
+		case UAEIO:
+		case VIO:
+			afs_op_accumulate_error(op, -EREMOTEIO, abort_code);
+			if (op->volume->type != AFSVL_RWVOL)
+				goto next_server;
+			goto failed;
+
+		case VDISKFULL:
+		case UAENOSPC:
+			/* The partition is full.  Only applies to RWVOLs.
+			 * Translate locally and return ENOSPC.
+			 * No replicas to failover to.
+			 */
+			afs_op_set_error(op, -ENOSPC);
+			goto failed_but_online;
+
+		case VOVERQUOTA:
+		case UAEDQUOT:
+			/* Volume is full.  Only applies to RWVOLs.
+			 * Translate locally and return EDQUOT.
+			 * No replicas to failover to.
+			 */
+			afs_op_set_error(op, -EDQUOT);
+			goto failed_but_online;
+
 		default:
-			clear_bit(AFS_VOLUME_OFFLINE, &op->volume->flags);
-			clear_bit(AFS_VOLUME_BUSY, &op->volume->flags);
-			op->error = afs_abort_to_error(op->ac.abort_code);
+			afs_op_accumulate_error(op, error, abort_code);
+		failed_but_online:
+			clear_bit(AFS_SE_VOLUME_OFFLINE,
+				  &op->server_list->servers[op->server_index].flags);
+			clear_bit(AFS_SE_VOLUME_BUSY,
+				  &op->server_list->servers[op->server_index].flags);
 			goto failed;
 		}
 
 	case -ETIMEDOUT:
 	case -ETIME:
-		if (op->error != -EDESTADDRREQ)
+		if (afs_op_error(op) != -EDESTADDRREQ)
 			goto iterate_address;
 		fallthrough;
 	case -ERFKILL:
@@ -289,7 +454,7 @@ bool afs_select_fileserver(struct afs_operation *op)
 	case -EHOSTDOWN:
 	case -ECONNREFUSED:
 		_debug("no conn");
-		op->error = error;
+		afs_op_accumulate_error(op, error, 0);
 		goto iterate_address;
 
 	case -ENETRESET:
@@ -298,24 +463,31 @@ bool afs_select_fileserver(struct afs_operation *op)
 		fallthrough;
 	case -ECONNRESET:
 		_debug("call reset");
-		op->error = error;
+		afs_op_set_error(op, error);
 		goto failed;
 	}
 
 restart_from_beginning:
+	trace_afs_rotate(op, afs_rotate_trace_restart, 0);
 	_debug("restart");
-	afs_end_cursor(&op->ac);
+	op->estate = NULL;
 	op->server = NULL;
+	afs_clear_server_states(op);
+	op->server_states = NULL;
 	afs_put_serverlist(op->net, op->server_list);
 	op->server_list = NULL;
 start:
 	_debug("start");
+	ASSERTCMP(op->estate, ==, NULL);
 	/* See if we need to do an update of the volume record.  Note that the
 	 * volume may have moved or even have been deleted.
 	 */
 	error = afs_check_volume_status(op->volume, op);
-	if (error < 0)
-		goto failed_set_error;
+	trace_afs_rotate(op, afs_rotate_trace_check_vol_status, error);
+	if (error < 0) {
+		afs_op_set_error(op, error);
+		goto failed;
+	}
 
 	if (!afs_start_fs_iteration(op, vnode))
 		goto failed;
@@ -323,52 +495,83 @@ start:
 	_debug("__ VOL %llx __", op->volume->vid);
 
 pick_server:
-	_debug("pick [%lx]", op->untried);
+	_debug("pick [%lx]", op->untried_servers);
+	ASSERTCMP(op->estate, ==, NULL);
 
-	error = afs_wait_for_fs_probes(op->server_list, op->untried);
-	if (error < 0)
-		goto failed_set_error;
+	error = afs_wait_for_fs_probes(op, op->server_states,
+				       !(op->flags & AFS_OPERATION_UNINTR));
+	switch (error) {
+	case 0: /* No untried responsive servers and no outstanding probes */
+		trace_afs_rotate(op, afs_rotate_trace_probe_none, 0);
+		goto no_more_servers;
+	case 1: /* Got a response */
+		trace_afs_rotate(op, afs_rotate_trace_probe_response, 0);
+		break;
+	case 2: /* Probe data superseded */
+		trace_afs_rotate(op, afs_rotate_trace_probe_superseded, 0);
+		goto restart_from_beginning;
+	default:
+		trace_afs_rotate(op, afs_rotate_trace_probe_error, error);
+		afs_op_set_error(op, error);
+		goto failed;
+	}
 
-	/* Pick the untried server with the lowest RTT.  If we have outstanding
-	 * callbacks, we stick with the server we're already using if we can.
+	/* Pick the untried server with the highest priority untried endpoint.
+	 * If we have outstanding callbacks, we stick with the server we're
+	 * already using if we can.
 	 */
 	if (op->server) {
-		_debug("server %u", op->index);
-		if (test_bit(op->index, &op->untried))
+		_debug("server %u", op->server_index);
+		if (test_bit(op->server_index, &op->untried_servers))
 			goto selected_server;
 		op->server = NULL;
 		_debug("no server");
 	}
 
-	op->index = -1;
-	rtt = U32_MAX;
+	rcu_read_lock();
+	op->server_index = -1;
+	best_prio = -1;
 	for (i = 0; i < op->server_list->nr_servers; i++) {
-		struct afs_server *s = op->server_list->servers[i].server;
+		struct afs_endpoint_state *es;
+		struct afs_server_entry *se = &op->server_list->servers[i];
+		struct afs_addr_list *sal;
+		struct afs_server *s = se->server;
 
-		if (!test_bit(i, &op->untried) ||
+		if (!test_bit(i, &op->untried_servers) ||
+		    test_bit(AFS_SE_EXCLUDED, &se->flags) ||
 		    !test_bit(AFS_SERVER_FL_RESPONDING, &s->flags))
 			continue;
-		if (s->probe.rtt < rtt) {
-			op->index = i;
-			rtt = s->probe.rtt;
+		es = op->server_states->endpoint_state;
+		sal = es->addresses;
+
+		afs_get_address_preferences_rcu(op->net, sal);
+		for (j = 0; j < sal->nr_addrs; j++) {
+			if (!sal->addrs[j].peer)
+				continue;
+			if (sal->addrs[j].prio > best_prio) {
+				op->server_index = i;
+				best_prio = sal->addrs[j].prio;
+			}
 		}
 	}
+	rcu_read_unlock();
 
-	if (op->index == -1)
+	if (op->server_index == -1)
 		goto no_more_servers;
 
 selected_server:
-	_debug("use %d", op->index);
-	__clear_bit(op->index, &op->untried);
+	trace_afs_rotate(op, afs_rotate_trace_selected_server, best_prio);
+	_debug("use %d prio %u", op->server_index, best_prio);
+	__clear_bit(op->server_index, &op->untried_servers);
 
 	/* We're starting on a different fileserver from the list.  We need to
 	 * check it, create a callback intercept, find its address list and
 	 * probe its capabilities before we use it.
 	 */
-	ASSERTCMP(op->ac.alist, ==, NULL);
-	server = op->server_list->servers[op->index].server;
+	ASSERTCMP(op->estate, ==, NULL);
+	server = op->server_list->servers[op->server_index].server;
 
-	if (!afs_check_server_record(op, server))
+	if (!afs_check_server_record(op, server, op->key))
 		goto failed;
 
 	_debug("USING SERVER: %pU", &server->uuid);
@@ -377,58 +580,73 @@ selected_server:
 	op->server = server;
 	if (vnode->cb_server != server) {
 		vnode->cb_server = server;
-		vnode->cb_s_break = server->cb_s_break;
-		vnode->cb_fs_s_break = atomic_read(&server->cell->fs_s_break);
-		vnode->cb_v_break = vnode->volume->cb_v_break;
-		clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
+		vnode->cb_v_check = atomic_read(&vnode->volume->cb_v_break);
+		atomic64_set(&vnode->cb_expires_at, AFS_NO_CB_PROMISE);
 	}
 
-	read_lock(&server->fs_lock);
-	alist = rcu_dereference_protected(server->addresses,
-					  lockdep_is_held(&server->fs_lock));
-	afs_get_addrlist(alist);
-	read_unlock(&server->fs_lock);
-
 retry_server:
-	memset(&op->ac, 0, sizeof(op->ac));
-
-	if (!op->ac.alist)
-		op->ac.alist = alist;
-	else
-		afs_put_addrlist(alist);
-
-	op->ac.index = -1;
+	op->addr_tried = 0;
+	op->addr_index = -1;
 
 iterate_address:
-	ASSERT(op->ac.alist);
 	/* Iterate over the current server's address list to try and find an
 	 * address on which it will respond to us.
 	 */
-	if (!afs_iterate_addresses(&op->ac))
-		goto out_of_addresses;
+	op->estate = op->server_states[op->server_index].endpoint_state;
+	set = READ_ONCE(op->estate->responsive_set);
+	failed = READ_ONCE(op->estate->failed_set);
+	_debug("iterate ES=%x rs=%lx fs=%lx", op->estate->probe_seq, set, failed);
+	set &= ~(failed | op->addr_tried);
+	trace_afs_rotate(op, afs_rotate_trace_iterate_addr, set);
+	if (!set)
+		goto wait_for_more_probe_results;
+
+	alist = op->estate->addresses;
+	for (i = 0; i < alist->nr_addrs; i++) {
+		if (alist->addrs[i].prio > best_prio) {
+			addr_index = i;
+			best_prio = alist->addrs[i].prio;
+		}
+	}
 
-	_debug("address [%u] %u/%u %pISp",
-	       op->index, op->ac.index, op->ac.alist->nr_addrs,
-	       &op->ac.alist->addrs[op->ac.index].transport);
+	addr_index = READ_ONCE(alist->preferred);
+	if (!test_bit(addr_index, &set))
+		addr_index = __ffs(set);
 
+	op->addr_index = addr_index;
+	set_bit(addr_index, &op->addr_tried);
+
+	op->volsync.creation = TIME64_MIN;
+	op->volsync.update = TIME64_MIN;
+	op->call_responded = false;
+	_debug("address [%u] %u/%u %pISp",
+	       op->server_index, addr_index, alist->nr_addrs,
+	       rxrpc_kernel_remote_addr(alist->addrs[op->addr_index].peer));
 	_leave(" = t");
 	return true;
 
-out_of_addresses:
+wait_for_more_probe_results:
+	error = afs_wait_for_one_fs_probe(op->server, op->estate, op->addr_tried,
+					  !(op->flags & AFS_OPERATION_UNINTR));
+	if (!error)
+		goto iterate_address;
+
 	/* We've now had a failure to respond on all of a server's addresses -
 	 * immediately probe them again and consider retrying the server.
 	 */
+	trace_afs_rotate(op, afs_rotate_trace_probe_fileserver, 0);
 	afs_probe_fileserver(op->net, op->server);
 	if (op->flags & AFS_OPERATION_RETRY_SERVER) {
-		alist = op->ac.alist;
-		error = afs_wait_for_one_fs_probe(
-			op->server, !(op->flags & AFS_OPERATION_UNINTR));
+		error = afs_wait_for_one_fs_probe(op->server, op->estate, op->addr_tried,
+						  !(op->flags & AFS_OPERATION_UNINTR));
 		switch (error) {
 		case 0:
 			op->flags &= ~AFS_OPERATION_RETRY_SERVER;
+			trace_afs_rotate(op, afs_rotate_trace_retry_server, 0);
 			goto retry_server;
 		case -ERESTARTSYS:
-			goto failed_set_error;
+			afs_op_set_error(op, error);
+			goto failed;
 		case -ETIME:
 		case -EDESTADDRREQ:
 			goto next_server;
@@ -436,34 +654,51 @@ out_of_addresses:
 	}
 
 next_server:
+	trace_afs_rotate(op, afs_rotate_trace_next_server, 0);
 	_debug("next");
-	afs_end_cursor(&op->ac);
+	ASSERT(op->estate);
+	alist = op->estate->addresses;
+	if (op->call_responded &&
+	    op->addr_index != READ_ONCE(alist->preferred) &&
+	    test_bit(alist->preferred, &op->addr_tried))
+		WRITE_ONCE(alist->preferred, op->addr_index);
+	op->estate = NULL;
 	goto pick_server;
 
 no_more_servers:
 	/* That's all the servers poked to no good effect.  Try again if some
 	 * of them were busy.
 	 */
-	if (op->flags & AFS_OPERATION_VBUSY)
+	trace_afs_rotate(op, afs_rotate_trace_no_more_servers, 0);
+	if (op->flags & AFS_OPERATION_VBUSY) {
+		afs_sleep_and_retry(op);
+		op->flags &= ~AFS_OPERATION_VBUSY;
 		goto restart_from_beginning;
+	}
 
-	e.error = -EDESTADDRREQ;
-	e.responded = false;
+	rcu_read_lock();
 	for (i = 0; i < op->server_list->nr_servers; i++) {
-		struct afs_server *s = op->server_list->servers[i].server;
+		struct afs_endpoint_state *estate;
 
-		afs_prioritise_error(&e, READ_ONCE(s->probe.error),
-				     s->probe.abort_code);
+		estate = op->server_states->endpoint_state;
+		error = READ_ONCE(estate->error);
+		if (error < 0)
+			afs_op_accumulate_error(op, error, estate->abort_code);
 	}
+	rcu_read_unlock();
 
-	error = e.error;
-
-failed_set_error:
-	op->error = error;
 failed:
+	trace_afs_rotate(op, afs_rotate_trace_failed, 0);
 	op->flags |= AFS_OPERATION_STOP;
-	afs_end_cursor(&op->ac);
-	_leave(" = f [failed %d]", op->error);
+	if (op->estate) {
+		alist = op->estate->addresses;
+		if (op->call_responded &&
+		    op->addr_index != READ_ONCE(alist->preferred) &&
+		    test_bit(alist->preferred, &op->addr_tried))
+			WRITE_ONCE(alist->preferred, op->addr_index);
+		op->estate = NULL;
+	}
+	_leave(" = f [failed %d]", afs_op_error(op));
 	return false;
 }
 
@@ -482,37 +717,40 @@ void afs_dump_edestaddrreq(const struct afs_operation *op)
 	rcu_read_lock();
 
 	pr_notice("EDESTADDR occurred\n");
-	pr_notice("FC: cbb=%x cbb2=%x fl=%x err=%hd\n",
+	pr_notice("OP: cbb=%x cbb2=%x fl=%x err=%hd\n",
 		  op->file[0].cb_break_before,
-		  op->file[1].cb_break_before, op->flags, op->error);
-	pr_notice("FC: ut=%lx ix=%d ni=%u\n",
-		  op->untried, op->index, op->nr_iterations);
+		  op->file[1].cb_break_before, op->flags, op->cumul_error.error);
+	pr_notice("OP: ut=%lx ix=%d ni=%u\n",
+		  op->untried_servers, op->server_index, op->nr_iterations);
+	pr_notice("OP: call  er=%d ac=%d r=%u\n",
+		  op->call_error, op->call_abort_code, op->call_responded);
 
 	if (op->server_list) {
 		const struct afs_server_list *sl = op->server_list;
-		pr_notice("FC: SL nr=%u pr=%u vnov=%hx\n",
-			  sl->nr_servers, sl->preferred, sl->vnovol_mask);
+
+		pr_notice("FC: SL nr=%u vnov=%hx\n",
+			  sl->nr_servers, sl->vnovol_mask);
 		for (i = 0; i < sl->nr_servers; i++) {
 			const struct afs_server *s = sl->servers[i].server;
+			const struct afs_endpoint_state *e =
+				rcu_dereference(s->endpoint_state);
+			const struct afs_addr_list *a = e->addresses;
+
 			pr_notice("FC: server fl=%lx av=%u %pU\n",
 				  s->flags, s->addr_version, &s->uuid);
-			if (s->addresses) {
-				const struct afs_addr_list *a =
-					rcu_dereference(s->addresses);
+			pr_notice("FC:  - pq=%x R=%lx F=%lx\n",
+				  e->probe_seq, e->responsive_set, e->failed_set);
+			if (a) {
 				pr_notice("FC:  - av=%u nr=%u/%u/%u pr=%u\n",
 					  a->version,
 					  a->nr_ipv4, a->nr_addrs, a->max_addrs,
 					  a->preferred);
-				pr_notice("FC:  - R=%lx F=%lx\n",
-					  a->responded, a->failed);
-				if (a == op->ac.alist)
+				if (a == e->addresses)
 					pr_notice("FC:  - current\n");
 			}
 		}
 	}
 
-	pr_notice("AC: t=%lx ax=%u ac=%d er=%d r=%u ni=%u\n",
-		  op->ac.tried, op->ac.index, op->ac.abort_code, op->ac.error,
-		  op->ac.responded, op->ac.nr_iterations);
+	pr_notice("AC: t=%lx ax=%d\n", op->addr_tried, op->addr_index);
 	rcu_read_unlock();
 }
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index ed1644e7683f..c453428f3c8b 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -178,6 +178,8 @@ void afs_put_call(struct afs_call *call)
 		ASSERT(!work_pending(&call->async_work));
 		ASSERT(call->type->name != NULL);
 
+		rxrpc_kernel_put_peer(call->peer);
+
 		if (call->rxcall) {
 			rxrpc_kernel_shutdown_call(net->socket, call->rxcall);
 			rxrpc_kernel_put_call(net->socket, call->rxcall);
@@ -187,7 +189,6 @@ void afs_put_call(struct afs_call *call)
 			call->type->destructor(call);
 
 		afs_unuse_server_notime(call->net, call->server, afs_server_trace_put_call);
-		afs_put_addrlist(call->alist);
 		kfree(call->request);
 
 		trace_afs_call(call->debug_id, afs_call_trace_free, 0, o,
@@ -294,9 +295,8 @@ static void afs_notify_end_request_tx(struct sock *sock,
  * Initiate a call and synchronously queue up the parameters for dispatch.  Any
  * error is stored into the call struct, which the caller must check for.
  */
-void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
+void afs_make_call(struct afs_call *call, gfp_t gfp)
 {
-	struct sockaddr_rxrpc *srx = &ac->alist->addrs[ac->index];
 	struct rxrpc_call *rxcall;
 	struct msghdr msg;
 	struct kvec iov[1];
@@ -304,7 +304,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
 	s64 tx_total_len;
 	int ret;
 
-	_enter(",{%pISp},", &srx->transport);
+	_enter(",{%pISp+%u},", rxrpc_kernel_remote_addr(call->peer), call->service_id);
 
 	ASSERT(call->type != NULL);
 	ASSERT(call->type->name != NULL);
@@ -313,8 +313,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
 	       call, call->type->name, key_serial(call->key),
 	       atomic_read(&call->net->nr_outstanding_calls));
 
-	call->addr_ix = ac->index;
-	call->alist = afs_get_addrlist(ac->alist);
+	trace_afs_make_call(call);
 
 	/* Work out the length we're going to transmit.  This is awkward for
 	 * calls such as FS.StoreData where there's an extra injection of data
@@ -333,7 +332,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
 	}
 
 	/* create a call */
-	rxcall = rxrpc_kernel_begin_call(call->net->socket, srx, call->key,
+	rxcall = rxrpc_kernel_begin_call(call->net->socket, call->peer, call->key,
 					 (unsigned long)call,
 					 tx_total_len,
 					 call->max_lifespan,
@@ -341,6 +340,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
 					 (call->async ?
 					  afs_wake_up_async_call :
 					  afs_wake_up_call_waiter),
+					 call->service_id,
 					 call->upgrade,
 					 (call->intr ? RXRPC_PREINTERRUPTIBLE :
 					  RXRPC_UNINTERRUPTIBLE),
@@ -390,7 +390,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
 	/* Note that at this point, we may have received the reply or an abort
 	 * - and an asynchronous call may already have completed.
 	 *
-	 * afs_wait_for_call_to_complete(call, ac)
+	 * afs_wait_for_call_to_complete(call)
 	 * must be called to synchronously clean up.
 	 */
 	return;
@@ -406,8 +406,7 @@ error_do_abort:
 		rxrpc_kernel_recv_data(call->net->socket, rxcall,
 				       &msg.msg_iter, &len, false,
 				       &call->abort_code, &call->service_id);
-		ac->abort_code = call->abort_code;
-		ac->responded = true;
+		call->responded = true;
 	}
 	call->error = ret;
 	trace_afs_call_done(call);
@@ -424,10 +423,10 @@ error_kill_call:
 	if (call->async) {
 		if (cancel_work_sync(&call->async_work))
 			afs_put_call(call);
-		afs_put_call(call);
+		afs_set_call_complete(call, ret, 0);
 	}
 
-	ac->error = ret;
+	call->error = ret;
 	call->state = AFS_CALL_COMPLETE;
 	_leave(" = %d", ret);
 }
@@ -461,7 +460,7 @@ static void afs_log_error(struct afs_call *call, s32 remote_abort)
 		max = m + 1;
 		pr_notice("kAFS: Peer reported %s failure on %s [%pISp]\n",
 			  msg, call->type->name,
-			  &call->alist->addrs[call->addr_ix].transport);
+			  rxrpc_kernel_remote_addr(call->peer));
 	}
 }
 
@@ -508,6 +507,7 @@ static void afs_deliver_to_call(struct afs_call *call)
 			ret = -EBADMSG;
 		switch (ret) {
 		case 0:
+			call->responded = true;
 			afs_queue_call_work(call);
 			if (state == AFS_CALL_CL_PROC_REPLY) {
 				if (call->op)
@@ -522,9 +522,11 @@ static void afs_deliver_to_call(struct afs_call *call)
 			goto out;
 		case -ECONNABORTED:
 			ASSERTCMP(state, ==, AFS_CALL_COMPLETE);
+			call->responded = true;
 			afs_log_error(call, call->abort_code);
 			goto done;
 		case -ENOTSUPP:
+			call->responded = true;
 			abort_code = RXGEN_OPCODE;
 			rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
 						abort_code, ret,
@@ -571,50 +573,46 @@ call_complete:
 }
 
 /*
- * Wait synchronously for a call to complete and clean up the call struct.
+ * Wait synchronously for a call to complete.
  */
-long afs_wait_for_call_to_complete(struct afs_call *call,
-				   struct afs_addr_cursor *ac)
+void afs_wait_for_call_to_complete(struct afs_call *call)
 {
-	long ret;
 	bool rxrpc_complete = false;
 
-	DECLARE_WAITQUEUE(myself, current);
-
 	_enter("");
 
-	ret = call->error;
-	if (ret < 0)
-		goto out;
+	if (!afs_check_call_state(call, AFS_CALL_COMPLETE)) {
+		DECLARE_WAITQUEUE(myself, current);
+
+		add_wait_queue(&call->waitq, &myself);
+		for (;;) {
+			set_current_state(TASK_UNINTERRUPTIBLE);
+
+			/* deliver any messages that are in the queue */
+			if (!afs_check_call_state(call, AFS_CALL_COMPLETE) &&
+			    call->need_attention) {
+				call->need_attention = false;
+				__set_current_state(TASK_RUNNING);
+				afs_deliver_to_call(call);
+				continue;
+			}
 
-	add_wait_queue(&call->waitq, &myself);
-	for (;;) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
-
-		/* deliver any messages that are in the queue */
-		if (!afs_check_call_state(call, AFS_CALL_COMPLETE) &&
-		    call->need_attention) {
-			call->need_attention = false;
-			__set_current_state(TASK_RUNNING);
-			afs_deliver_to_call(call);
-			continue;
-		}
+			if (afs_check_call_state(call, AFS_CALL_COMPLETE))
+				break;
 
-		if (afs_check_call_state(call, AFS_CALL_COMPLETE))
-			break;
+			if (!rxrpc_kernel_check_life(call->net->socket, call->rxcall)) {
+				/* rxrpc terminated the call. */
+				rxrpc_complete = true;
+				break;
+			}
 
-		if (!rxrpc_kernel_check_life(call->net->socket, call->rxcall)) {
-			/* rxrpc terminated the call. */
-			rxrpc_complete = true;
-			break;
+			schedule();
 		}
 
-		schedule();
+		remove_wait_queue(&call->waitq, &myself);
+		__set_current_state(TASK_RUNNING);
 	}
 
-	remove_wait_queue(&call->waitq, &myself);
-	__set_current_state(TASK_RUNNING);
-
 	if (!afs_check_call_state(call, AFS_CALL_COMPLETE)) {
 		if (rxrpc_complete) {
 			afs_set_call_complete(call, call->error, call->abort_code);
@@ -627,29 +625,6 @@ long afs_wait_for_call_to_complete(struct afs_call *call,
 				afs_set_call_complete(call, -EINTR, 0);
 		}
 	}
-
-	spin_lock_bh(&call->state_lock);
-	ac->abort_code = call->abort_code;
-	ac->error = call->error;
-	spin_unlock_bh(&call->state_lock);
-
-	ret = ac->error;
-	switch (ret) {
-	case 0:
-		ret = call->ret0;
-		call->ret0 = 0;
-
-		fallthrough;
-	case -ECONNABORTED:
-		ac->responded = true;
-		break;
-	}
-
-out:
-	_debug("call complete");
-	afs_put_call(call);
-	_leave(" = %p", (void *)ret);
-	return ret;
 }
 
 /*
diff --git a/fs/afs/server.c b/fs/afs/server.c
index b5237206eac3..e169121f603e 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -21,13 +21,13 @@ static void __afs_put_server(struct afs_net *, struct afs_server *);
 /*
  * Find a server by one of its addresses.
  */
-struct afs_server *afs_find_server(struct afs_net *net,
-				   const struct sockaddr_rxrpc *srx)
+struct afs_server *afs_find_server(struct afs_net *net, const struct rxrpc_peer *peer)
 {
+	const struct afs_endpoint_state *estate;
 	const struct afs_addr_list *alist;
 	struct afs_server *server = NULL;
 	unsigned int i;
-	int seq = 0, diff;
+	int seq = 1;
 
 	rcu_read_lock();
 
@@ -35,39 +35,15 @@ struct afs_server *afs_find_server(struct afs_net *net,
 		if (server)
 			afs_unuse_server_notime(net, server, afs_server_trace_put_find_rsq);
 		server = NULL;
+		seq++; /* 2 on the 1st/lockless path, otherwise odd */
 		read_seqbegin_or_lock(&net->fs_addr_lock, &seq);
 
-		if (srx->transport.family == AF_INET6) {
-			const struct sockaddr_in6 *a = &srx->transport.sin6, *b;
-			hlist_for_each_entry_rcu(server, &net->fs_addresses6, addr6_link) {
-				alist = rcu_dereference(server->addresses);
-				for (i = alist->nr_ipv4; i < alist->nr_addrs; i++) {
-					b = &alist->addrs[i].transport.sin6;
-					diff = ((u16 __force)a->sin6_port -
-						(u16 __force)b->sin6_port);
-					if (diff == 0)
-						diff = memcmp(&a->sin6_addr,
-							      &b->sin6_addr,
-							      sizeof(struct in6_addr));
-					if (diff == 0)
-						goto found;
-				}
-			}
-		} else {
-			const struct sockaddr_in *a = &srx->transport.sin, *b;
-			hlist_for_each_entry_rcu(server, &net->fs_addresses4, addr4_link) {
-				alist = rcu_dereference(server->addresses);
-				for (i = 0; i < alist->nr_ipv4; i++) {
-					b = &alist->addrs[i].transport.sin;
-					diff = ((u16 __force)a->sin_port -
-						(u16 __force)b->sin_port);
-					if (diff == 0)
-						diff = ((u32 __force)a->sin_addr.s_addr -
-							(u32 __force)b->sin_addr.s_addr);
-					if (diff == 0)
-						goto found;
-				}
-			}
+		hlist_for_each_entry_rcu(server, &net->fs_addresses6, addr6_link) {
+			estate = rcu_dereference(server->endpoint_state);
+			alist = estate->addresses;
+			for (i = 0; i < alist->nr_addrs; i++)
+				if (alist->addrs[i].peer == peer)
+					goto found;
 		}
 
 		server = NULL;
@@ -90,7 +66,7 @@ struct afs_server *afs_find_server_by_uuid(struct afs_net *net, const uuid_t *uu
 {
 	struct afs_server *server = NULL;
 	struct rb_node *p;
-	int diff, seq = 0;
+	int diff, seq = 1;
 
 	_enter("%pU", uuid);
 
@@ -102,7 +78,7 @@ struct afs_server *afs_find_server_by_uuid(struct afs_net *net, const uuid_t *uu
 		if (server)
 			afs_unuse_server(net, server, afs_server_trace_put_uuid_rsq);
 		server = NULL;
-
+		seq++; /* 2 on the 1st/lockless path, otherwise odd */
 		read_seqbegin_or_lock(&net->fs_lock, &seq);
 
 		p = net->fs_servers.rb_node;
@@ -137,6 +113,7 @@ struct afs_server *afs_find_server_by_uuid(struct afs_net *net, const uuid_t *uu
 static struct afs_server *afs_install_server(struct afs_cell *cell,
 					     struct afs_server *candidate)
 {
+	const struct afs_endpoint_state *estate;
 	const struct afs_addr_list *alist;
 	struct afs_server *server, *next;
 	struct afs_net *net = cell->net;
@@ -188,8 +165,9 @@ static struct afs_server *afs_install_server(struct afs_cell *cell,
 
 added_dup:
 	write_seqlock(&net->fs_addr_lock);
-	alist = rcu_dereference_protected(server->addresses,
-					  lockdep_is_held(&net->fs_addr_lock.lock));
+	estate = rcu_dereference_protected(server->endpoint_state,
+					   lockdep_is_held(&net->fs_addr_lock.lock));
+	alist = estate->addresses;
 
 	/* Secondly, if the server has any IPv4 and/or IPv6 addresses, install
 	 * it in the IPv4 and/or IPv6 reverse-map lists.
@@ -219,6 +197,7 @@ static struct afs_server *afs_alloc_server(struct afs_cell *cell,
 					   const uuid_t *uuid,
 					   struct afs_addr_list *alist)
 {
+	struct afs_endpoint_state *estate;
 	struct afs_server *server;
 	struct afs_net *net = cell->net;
 
@@ -228,25 +207,41 @@ static struct afs_server *afs_alloc_server(struct afs_cell *cell,
 	if (!server)
 		goto enomem;
 
+	estate = kzalloc(sizeof(struct afs_endpoint_state), GFP_KERNEL);
+	if (!estate)
+		goto enomem_server;
+
 	refcount_set(&server->ref, 1);
 	atomic_set(&server->active, 1);
 	server->debug_id = atomic_inc_return(&afs_server_debug_id);
-	RCU_INIT_POINTER(server->addresses, alist);
 	server->addr_version = alist->version;
 	server->uuid = *uuid;
 	rwlock_init(&server->fs_lock);
-	INIT_WORK(&server->initcb_work, afs_server_init_callback_work);
+	INIT_LIST_HEAD(&server->volumes);
 	init_waitqueue_head(&server->probe_wq);
 	INIT_LIST_HEAD(&server->probe_link);
 	spin_lock_init(&server->probe_lock);
 	server->cell = cell;
 	server->rtt = UINT_MAX;
+	server->service_id = FS_SERVICE;
+
+	server->probe_counter = 1;
+	server->probed_at = jiffies - LONG_MAX / 2;
+	refcount_set(&estate->ref, 1);
+	estate->addresses = alist;
+	estate->server_id = server->debug_id;
+	estate->probe_seq = 1;
+	rcu_assign_pointer(server->endpoint_state, estate);
 
 	afs_inc_servers_outstanding(net);
 	trace_afs_server(server->debug_id, 1, 1, afs_server_trace_alloc);
+	trace_afs_estate(estate->server_id, estate->probe_seq, refcount_read(&estate->ref),
+			 afs_estate_trace_alloc_server);
 	_leave(" = %p", server);
 	return server;
 
+enomem_server:
+	kfree(server);
 enomem:
 	_leave(" = NULL [nomem]");
 	return NULL;
@@ -301,20 +296,20 @@ struct afs_server *afs_lookup_server(struct afs_cell *cell, struct key *key,
 
 	candidate = afs_alloc_server(cell, uuid, alist);
 	if (!candidate) {
-		afs_put_addrlist(alist);
+		afs_put_addrlist(alist, afs_alist_trace_put_server_oom);
 		return ERR_PTR(-ENOMEM);
 	}
 
 	server = afs_install_server(cell, candidate);
 	if (server != candidate) {
-		afs_put_addrlist(alist);
+		afs_put_addrlist(alist, afs_alist_trace_put_server_dup);
 		kfree(candidate);
 	} else {
 		/* Immediately dispatch an asynchronous probe to each interface
 		 * on the fileserver.  This will make sure the repeat-probing
 		 * service is started.
 		 */
-		afs_fs_probe_fileserver(cell->net, server, key, true);
+		afs_fs_probe_fileserver(cell->net, server, alist, key);
 	}
 
 	return server;
@@ -447,7 +442,8 @@ static void afs_server_rcu(struct rcu_head *rcu)
 
 	trace_afs_server(server->debug_id, refcount_read(&server->ref),
 			 atomic_read(&server->active), afs_server_trace_free);
-	afs_put_addrlist(rcu_access_pointer(server->addresses));
+	afs_put_endpoint_state(rcu_access_pointer(server->endpoint_state),
+			       afs_estate_trace_put_server);
 	kfree(server);
 }
 
@@ -459,14 +455,10 @@ static void __afs_put_server(struct afs_net *net, struct afs_server *server)
 
 static void afs_give_up_callbacks(struct afs_net *net, struct afs_server *server)
 {
-	struct afs_addr_list *alist = rcu_access_pointer(server->addresses);
-	struct afs_addr_cursor ac = {
-		.alist	= alist,
-		.index	= alist->preferred,
-		.error	= 0,
-	};
-
-	afs_fs_give_up_all_callbacks(net, server, &ac, NULL);
+	struct afs_endpoint_state *estate = rcu_access_pointer(server->endpoint_state);
+	struct afs_addr_list *alist = estate->addresses;
+
+	afs_fs_give_up_all_callbacks(net, server, &alist->addrs[alist->preferred], NULL);
 }
 
 /*
@@ -477,7 +469,6 @@ static void afs_destroy_server(struct afs_net *net, struct afs_server *server)
 	if (test_bit(AFS_SERVER_FL_MAY_HAVE_CB, &server->flags))
 		afs_give_up_callbacks(net, server);
 
-	flush_work(&server->initcb_work);
 	afs_put_server(net, server, afs_server_trace_destroy);
 }
 
@@ -636,9 +627,12 @@ void afs_purge_servers(struct afs_net *net)
  * Get an update for a server's address list.
  */
 static noinline bool afs_update_server_record(struct afs_operation *op,
-					      struct afs_server *server)
+					      struct afs_server *server,
+					      struct key *key)
 {
-	struct afs_addr_list *alist, *discard;
+	struct afs_endpoint_state *estate;
+	struct afs_addr_list *alist;
+	bool has_addrs;
 
 	_enter("");
 
@@ -648,29 +642,27 @@ static noinline bool afs_update_server_record(struct afs_operation *op,
 
 	alist = afs_vl_lookup_addrs(op->volume->cell, op->key, &server->uuid);
 	if (IS_ERR(alist)) {
+		rcu_read_lock();
+		estate = rcu_dereference(server->endpoint_state);
+		has_addrs = estate->addresses;
+		rcu_read_unlock();
+
 		if ((PTR_ERR(alist) == -ERESTARTSYS ||
 		     PTR_ERR(alist) == -EINTR) &&
 		    (op->flags & AFS_OPERATION_UNINTR) &&
-		    server->addresses) {
+		    has_addrs) {
 			_leave(" = t [intr]");
 			return true;
 		}
-		op->error = PTR_ERR(alist);
-		_leave(" = f [%d]", op->error);
+		afs_op_set_error(op, PTR_ERR(alist));
+		_leave(" = f [%d]", afs_op_error(op));
 		return false;
 	}
 
-	discard = alist;
-	if (server->addr_version != alist->version) {
-		write_lock(&server->fs_lock);
-		discard = rcu_dereference_protected(server->addresses,
-						    lockdep_is_held(&server->fs_lock));
-		rcu_assign_pointer(server->addresses, alist);
-		server->addr_version = alist->version;
-		write_unlock(&server->fs_lock);
-	}
+	if (server->addr_version != alist->version)
+		afs_fs_probe_fileserver(op->net, server, alist, key);
 
-	afs_put_addrlist(discard);
+	afs_put_addrlist(alist, afs_alist_trace_put_server_update);
 	_leave(" = t");
 	return true;
 }
@@ -678,7 +670,8 @@ static noinline bool afs_update_server_record(struct afs_operation *op,
 /*
  * See if a server's address list needs updating.
  */
-bool afs_check_server_record(struct afs_operation *op, struct afs_server *server)
+bool afs_check_server_record(struct afs_operation *op, struct afs_server *server,
+			     struct key *key)
 {
 	bool success;
 	int ret, retries = 0;
@@ -698,7 +691,7 @@ retry:
 update:
 	if (!test_and_set_bit_lock(AFS_SERVER_FL_UPDATING, &server->flags)) {
 		clear_bit(AFS_SERVER_FL_NEEDS_UPDATE, &server->flags);
-		success = afs_update_server_record(op, server);
+		success = afs_update_server_record(op, server, key);
 		clear_bit_unlock(AFS_SERVER_FL_UPDATING, &server->flags);
 		wake_up_bit(&server->flags, AFS_SERVER_FL_UPDATING);
 		_leave(" = %d", success);
@@ -710,7 +703,7 @@ wait:
 			  (op->flags & AFS_OPERATION_UNINTR) ?
 			  TASK_UNINTERRUPTIBLE : TASK_INTERRUPTIBLE);
 	if (ret == -ERESTARTSYS) {
-		op->error = ret;
+		afs_op_set_error(op, ret);
 		_leave(" = f [intr]");
 		return false;
 	}
diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c
index ed9056703505..7e7e567a7f8a 100644
--- a/fs/afs/server_list.c
+++ b/fs/afs/server_list.c
@@ -17,42 +17,69 @@ void afs_put_serverlist(struct afs_net *net, struct afs_server_list *slist)
 		for (i = 0; i < slist->nr_servers; i++)
 			afs_unuse_server(net, slist->servers[i].server,
 					 afs_server_trace_put_slist);
-		kfree(slist);
+		kfree_rcu(slist, rcu);
 	}
 }
 
 /*
  * Build a server list from a VLDB record.
  */
-struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell,
+struct afs_server_list *afs_alloc_server_list(struct afs_volume *volume,
 					      struct key *key,
-					      struct afs_vldb_entry *vldb,
-					      u8 type_mask)
+					      struct afs_vldb_entry *vldb)
 {
 	struct afs_server_list *slist;
 	struct afs_server *server;
-	int ret = -ENOMEM, nr_servers = 0, i, j;
-
-	for (i = 0; i < vldb->nr_servers; i++)
-		if (vldb->fs_mask[i] & type_mask)
-			nr_servers++;
+	unsigned int type_mask = 1 << volume->type;
+	bool use_newrepsites = false;
+	int ret = -ENOMEM, nr_servers = 0, newrep = 0, i, j, usable = 0;
+
+	/* Work out if we're going to restrict to NEWREPSITE-marked servers or
+	 * not.  If at least one site is marked as NEWREPSITE, then it's likely
+	 * that "vos release" is busy updating RO sites.  We cut over from one
+	 * to the other when >=50% of the sites have been updated.  Sites that
+	 * are in the process of being updated are marked DONTUSE.
+	 */
+	for (i = 0; i < vldb->nr_servers; i++) {
+		if (!(vldb->fs_mask[i] & type_mask))
+			continue;
+		nr_servers++;
+		if (vldb->vlsf_flags[i] & AFS_VLSF_DONTUSE)
+			continue;
+		usable++;
+		if (vldb->vlsf_flags[i] & AFS_VLSF_NEWREPSITE)
+			newrep++;
+	}
 
 	slist = kzalloc(struct_size(slist, servers, nr_servers), GFP_KERNEL);
 	if (!slist)
 		goto error;
 
+	if (newrep) {
+		if (newrep < usable / 2) {
+			slist->ro_replicating = AFS_RO_REPLICATING_USE_OLD;
+		} else {
+			slist->ro_replicating = AFS_RO_REPLICATING_USE_NEW;
+			use_newrepsites = true;
+		}
+	}
+
 	refcount_set(&slist->usage, 1);
 	rwlock_init(&slist->lock);
 
-	for (i = 0; i < AFS_MAXTYPES; i++)
-		slist->vids[i] = vldb->vid[i];
-
 	/* Make sure a records exists for each server in the list. */
 	for (i = 0; i < vldb->nr_servers; i++) {
+		unsigned long se_flags = 0;
+		bool newrepsite = vldb->vlsf_flags[i] & AFS_VLSF_NEWREPSITE;
+
 		if (!(vldb->fs_mask[i] & type_mask))
 			continue;
+		if (vldb->vlsf_flags[i] & AFS_VLSF_DONTUSE)
+			__set_bit(AFS_SE_EXCLUDED, &se_flags);
+		if (newrep && (newrepsite ^ use_newrepsites))
+			__set_bit(AFS_SE_EXCLUDED, &se_flags);
 
-		server = afs_lookup_server(cell, key, &vldb->fs_server[i],
+		server = afs_lookup_server(volume->cell, key, &vldb->fs_server[i],
 					   vldb->addr_version[i]);
 		if (IS_ERR(server)) {
 			ret = PTR_ERR(server);
@@ -70,7 +97,7 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell,
 				break;
 		if (j < slist->nr_servers) {
 			if (slist->servers[j].server == server) {
-				afs_put_server(cell->net, server,
+				afs_put_server(volume->cell->net, server,
 					       afs_server_trace_put_slist_isort);
 				continue;
 			}
@@ -81,6 +108,9 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell,
 		}
 
 		slist->servers[j].server = server;
+		slist->servers[j].volume = volume;
+		slist->servers[j].flags = se_flags;
+		slist->servers[j].cb_expires_at = AFS_NO_CB_PROMISE;
 		slist->nr_servers++;
 	}
 
@@ -92,7 +122,7 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell,
 	return slist;
 
 error_2:
-	afs_put_serverlist(cell->net, slist);
+	afs_put_serverlist(volume->cell->net, slist);
 error:
 	return ERR_PTR(ret);
 }
@@ -103,27 +133,117 @@ error:
 bool afs_annotate_server_list(struct afs_server_list *new,
 			      struct afs_server_list *old)
 {
-	struct afs_server *cur;
-	int i, j;
+	unsigned long mask = 1UL << AFS_SE_EXCLUDED;
+	int i;
 
-	if (old->nr_servers != new->nr_servers)
+	if (old->nr_servers != new->nr_servers ||
+	    old->ro_replicating != new->ro_replicating)
 		goto changed;
 
-	for (i = 0; i < old->nr_servers; i++)
+	for (i = 0; i < old->nr_servers; i++) {
 		if (old->servers[i].server != new->servers[i].server)
 			goto changed;
-
+		if ((old->servers[i].flags & mask) != (new->servers[i].flags & mask))
+			goto changed;
+	}
 	return false;
-
 changed:
-	/* Maintain the same preferred server as before if possible. */
-	cur = old->servers[old->preferred].server;
-	for (j = 0; j < new->nr_servers; j++) {
-		if (new->servers[j].server == cur) {
-			new->preferred = j;
-			break;
+	return true;
+}
+
+/*
+ * Attach a volume to the servers it is going to use.
+ */
+void afs_attach_volume_to_servers(struct afs_volume *volume, struct afs_server_list *slist)
+{
+	struct afs_server_entry *se, *pe;
+	struct afs_server *server;
+	struct list_head *p;
+	unsigned int i;
+
+	down_write(&volume->cell->vs_lock);
+
+	for (i = 0; i < slist->nr_servers; i++) {
+		se = &slist->servers[i];
+		server = se->server;
+
+		list_for_each(p, &server->volumes) {
+			pe = list_entry(p, struct afs_server_entry, slink);
+			if (volume->vid <= pe->volume->vid)
+				break;
 		}
+		list_add_tail(&se->slink, p);
 	}
 
-	return true;
+	slist->attached = true;
+	up_write(&volume->cell->vs_lock);
+}
+
+/*
+ * Reattach a volume to the servers it is going to use when server list is
+ * replaced.  We try to switch the attachment points to avoid rewalking the
+ * lists.
+ */
+void afs_reattach_volume_to_servers(struct afs_volume *volume, struct afs_server_list *new,
+				    struct afs_server_list *old)
+{
+	unsigned int n = 0, o = 0;
+
+	down_write(&volume->cell->vs_lock);
+
+	while (n < new->nr_servers || o < old->nr_servers) {
+		struct afs_server_entry *pn = n < new->nr_servers ? &new->servers[n] : NULL;
+		struct afs_server_entry *po = o < old->nr_servers ? &old->servers[o] : NULL;
+		struct afs_server_entry *s;
+		struct list_head *p;
+		int diff;
+
+		if (pn && po && pn->server == po->server) {
+			pn->cb_expires_at = po->cb_expires_at;
+			list_replace(&po->slink, &pn->slink);
+			n++;
+			o++;
+			continue;
+		}
+
+		if (pn && po)
+			diff = memcmp(&pn->server->uuid, &po->server->uuid,
+				      sizeof(pn->server->uuid));
+		else
+			diff = pn ? -1 : 1;
+
+		if (diff < 0) {
+			list_for_each(p, &pn->server->volumes) {
+				s = list_entry(p, struct afs_server_entry, slink);
+				if (volume->vid <= s->volume->vid)
+					break;
+			}
+			list_add_tail(&pn->slink, p);
+			n++;
+		} else {
+			list_del(&po->slink);
+			o++;
+		}
+	}
+
+	up_write(&volume->cell->vs_lock);
+}
+
+/*
+ * Detach a volume from the servers it has been using.
+ */
+void afs_detach_volume_from_servers(struct afs_volume *volume, struct afs_server_list *slist)
+{
+	unsigned int i;
+
+	if (!slist->attached)
+		return;
+
+	down_write(&volume->cell->vs_lock);
+
+	for (i = 0; i < slist->nr_servers; i++)
+		list_del(&slist->servers[i].slink);
+
+	slist->attached = false;
+	up_write(&volume->cell->vs_lock);
 }
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 95d713074dc8..ae2d66a52add 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -381,8 +381,7 @@ static int afs_validate_fc(struct fs_context *fc)
 		ctx->key = key;
 
 		if (ctx->volume) {
-			afs_put_volume(ctx->net, ctx->volume,
-				       afs_volume_trace_put_validate_fc);
+			afs_put_volume(ctx->volume, afs_volume_trace_put_validate_fc);
 			ctx->volume = NULL;
 		}
 
@@ -407,6 +406,10 @@ static int afs_validate_fc(struct fs_context *fc)
 			return PTR_ERR(volume);
 
 		ctx->volume = volume;
+		if (volume->type != AFSVL_RWVOL) {
+			ctx->flock_mode = afs_flock_mode_local;
+			fc->sb_flags |= SB_RDONLY;
+		}
 	}
 
 	return 0;
@@ -525,7 +528,7 @@ static void afs_destroy_sbi(struct afs_super_info *as)
 {
 	if (as) {
 		struct afs_net *net = afs_net(as->net_ns);
-		afs_put_volume(net, as->volume, afs_volume_trace_put_destroy_sbi);
+		afs_put_volume(as->volume, afs_volume_trace_put_destroy_sbi);
 		afs_unuse_cell(net, as->cell, afs_cell_trace_unuse_sbi);
 		put_net(as->net_ns);
 		kfree(as);
@@ -611,7 +614,7 @@ static void afs_free_fc(struct fs_context *fc)
 	struct afs_fs_context *ctx = fc->fs_private;
 
 	afs_destroy_sbi(fc->s_fs_info);
-	afs_put_volume(ctx->net, ctx->volume, afs_volume_trace_put_free_fc);
+	afs_put_volume(ctx->volume, afs_volume_trace_put_free_fc);
 	afs_unuse_cell(ctx->net, ctx->cell, afs_cell_trace_unuse_fc);
 	key_put(ctx->key);
 	kfree(ctx);
diff --git a/fs/afs/validation.c b/fs/afs/validation.c
new file mode 100644
index 000000000000..46b37f2cce7d
--- /dev/null
+++ b/fs/afs/validation.c
@@ -0,0 +1,473 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* vnode and volume validity verification.
+ *
+ * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include "internal.h"
+
+/*
+ * Data validation is managed through a number of mechanisms from the server:
+ *
+ *  (1) On first contact with a server (such as if it has just been rebooted),
+ *      the server sends us a CB.InitCallBackState* request.
+ *
+ *  (2) On a RW volume, in response to certain vnode (inode)-accessing RPC
+ *      calls, the server maintains a time-limited per-vnode promise that it
+ *      will send us a CB.CallBack request if a third party alters the vnodes
+ *      accessed.
+ *
+ *      Note that a vnode-level callbacks may also be sent for other reasons,
+ *      such as filelock release.
+ *
+ *  (3) On a RO (or Backup) volume, in response to certain vnode-accessing RPC
+ *      calls, each server maintains a time-limited per-volume promise that it
+ *      will send us a CB.CallBack request if the RO volume is updated to a
+ *      snapshot of the RW volume ("vos release").  This is an atomic event
+ *      that cuts over all instances of the RO volume across multiple servers
+ *      simultaneously.
+ *
+ *	Note that a volume-level callbacks may also be sent for other reasons,
+ *	such as the volumeserver taking over control of the volume from the
+ *	fileserver.
+ *
+ *	Note also that each server maintains an independent time limit on an
+ *	independent callback.
+ *
+ *  (4) Certain RPC calls include a volume information record "VolSync" in
+ *      their reply.  This contains a creation date for the volume that should
+ *      remain unchanged for a RW volume (but will be changed if the volume is
+ *      restored from backup) or will be bumped to the time of snapshotting
+ *      when a RO volume is released.
+ *
+ * In order to track this events, the following are provided:
+ *
+ *	->cb_v_break.  A counter of events that might mean that the contents of
+ *	a volume have been altered since we last checked a vnode.
+ *
+ *	->cb_v_check.  A counter of the number of events that we've sent a
+ *	query to the server for.  Everything's up to date if this equals
+ *	cb_v_break.
+ *
+ *	->cb_scrub.  A counter of the number of regression events for which we
+ *	have to completely wipe the cache.
+ *
+ *	->cb_ro_snapshot.  A counter of the number of times that we've
+ *      recognised that a RO volume has been updated.
+ *
+ *	->cb_break.  A counter of events that might mean that the contents of a
+ *      vnode have been altered.
+ *
+ *	->cb_expires_at.  The time at which the callback promise expires or
+ *      AFS_NO_CB_PROMISE if we have no promise.
+ *
+ * The way we manage things is:
+ *
+ *  (1) When a volume-level CB.CallBack occurs, we increment ->cb_v_break on
+ *      the volume and reset ->cb_expires_at (ie. set AFS_NO_CB_PROMISE) on the
+ *      volume and volume's server record.
+ *
+ *  (2) When a CB.InitCallBackState occurs, we treat this as a volume-level
+ *	callback break on all the volumes that have been using that volume
+ *	(ie. increment ->cb_v_break and reset ->cb_expires_at).
+ *
+ *  (3) When a vnode-level CB.CallBack occurs, we increment ->cb_break on the
+ *	vnode and reset its ->cb_expires_at.  If the vnode is mmapped, we also
+ *	dispatch a work item to unmap all PTEs to the vnode's pagecache to
+ *	force reentry to the filesystem for revalidation.
+ *
+ *  (4) When entering the filesystem, we call afs_validate() to check the
+ *	validity of a vnode.  This first checks to see if ->cb_v_check and
+ *	->cb_v_break match, and if they don't, we lock volume->cb_check_lock
+ *	exclusively and perform an FS.FetchStatus on the vnode.
+ *
+ *	After checking the volume, we check the vnode.  If there's a mismatch
+ *	between the volume counters and the vnode's mirrors of those counters,
+ *	we lock vnode->validate_lock and issue an FS.FetchStatus on the vnode.
+ *
+ *  (5) When the reply from FS.FetchStatus arrives, the VolSync record is
+ *      parsed:
+ *
+ *	(A) If the Creation timestamp has changed on a RW volume or regressed
+ *	    on a RO volume, we try to increment ->cb_scrub; if it advances on a
+ *	    RO volume, we assume "vos release" happened and try to increment
+ *	    ->cb_ro_snapshot.
+ *
+ *      (B) If the Update timestamp has regressed, we try to increment
+ *	    ->cb_scrub.
+ *
+ *      Note that in both of these cases, we only do the increment if we can
+ *      cmpxchg the value of the timestamp from the value we noted before the
+ *      op.  This tries to prevent parallel ops from fighting one another.
+ *
+ *	volume->cb_v_check is then set to ->cb_v_break.
+ *
+ *  (6) The AFSCallBack record included in the FS.FetchStatus reply is also
+ *	parsed and used to set the promise in ->cb_expires_at for the vnode,
+ *	the volume and the volume's server record.
+ *
+ *  (7) If ->cb_scrub is seen to have advanced, we invalidate the pagecache for
+ *      the vnode.
+ */
+
+/*
+ * Check the validity of a vnode/inode and its parent volume.
+ */
+bool afs_check_validity(const struct afs_vnode *vnode)
+{
+	const struct afs_volume *volume = vnode->volume;
+	time64_t deadline = ktime_get_real_seconds() + 10;
+
+	if (atomic_read(&volume->cb_v_check) != atomic_read(&volume->cb_v_break) ||
+	    atomic64_read(&vnode->cb_expires_at)  <= deadline ||
+	    volume->cb_expires_at <= deadline ||
+	    vnode->cb_ro_snapshot != atomic_read(&volume->cb_ro_snapshot) ||
+	    vnode->cb_scrub	  != atomic_read(&volume->cb_scrub) ||
+	    test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags)) {
+		_debug("inval");
+		return false;
+	}
+
+	return true;
+}
+
+/*
+ * See if the server we've just talked to is currently excluded.
+ */
+static bool __afs_is_server_excluded(struct afs_operation *op, struct afs_volume *volume)
+{
+	const struct afs_server_entry *se;
+	const struct afs_server_list *slist;
+	bool is_excluded = true;
+	int i;
+
+	rcu_read_lock();
+
+	slist = rcu_dereference(volume->servers);
+	for (i = 0; i < slist->nr_servers; i++) {
+		se = &slist->servers[i];
+		if (op->server == se->server) {
+			is_excluded = test_bit(AFS_SE_EXCLUDED, &se->flags);
+			break;
+		}
+	}
+
+	rcu_read_unlock();
+	return is_excluded;
+}
+
+/*
+ * Update the volume's server list when the creation time changes and see if
+ * the server we've just talked to is currently excluded.
+ */
+static int afs_is_server_excluded(struct afs_operation *op, struct afs_volume *volume)
+{
+	int ret;
+
+	if (__afs_is_server_excluded(op, volume))
+		return 1;
+
+	set_bit(AFS_VOLUME_NEEDS_UPDATE, &volume->flags);
+	ret = afs_check_volume_status(op->volume, op);
+	if (ret < 0)
+		return ret;
+
+	return __afs_is_server_excluded(op, volume);
+}
+
+/*
+ * Handle a change to the volume creation time in the VolSync record.
+ */
+static int afs_update_volume_creation_time(struct afs_operation *op, struct afs_volume *volume)
+{
+	unsigned int snap;
+	time64_t cur = volume->creation_time;
+	time64_t old = op->pre_volsync.creation;
+	time64_t new = op->volsync.creation;
+	int ret;
+
+	_enter("%llx,%llx,%llx->%llx", volume->vid, cur, old, new);
+
+	if (cur == TIME64_MIN) {
+		volume->creation_time = new;
+		return 0;
+	}
+
+	if (new == cur)
+		return 0;
+
+	/* Try to advance the creation timestamp from what we had before the
+	 * operation to what we got back from the server.  This should
+	 * hopefully ensure that in a race between multiple operations only one
+	 * of them will do this.
+	 */
+	if (cur != old)
+		return 0;
+
+	/* If the creation time changes in an unexpected way, we need to scrub
+	 * our caches.  For a RW vol, this will only change if the volume is
+	 * restored from a backup; for a RO/Backup vol, this will advance when
+	 * the volume is updated to a new snapshot (eg. "vos release").
+	 */
+	if (volume->type == AFSVL_RWVOL)
+		goto regressed;
+	if (volume->type == AFSVL_BACKVOL) {
+		if (new < old)
+			goto regressed;
+		goto advance;
+	}
+
+	/* We have an RO volume, we need to query the VL server and look at the
+	 * server flags to see if RW->RO replication is in progress.
+	 */
+	ret = afs_is_server_excluded(op, volume);
+	if (ret < 0)
+		return ret;
+	if (ret > 0) {
+		snap = atomic_read(&volume->cb_ro_snapshot);
+		trace_afs_cb_v_break(volume->vid, snap, afs_cb_break_volume_excluded);
+		return ret;
+	}
+
+advance:
+	snap = atomic_inc_return(&volume->cb_ro_snapshot);
+	trace_afs_cb_v_break(volume->vid, snap, afs_cb_break_for_vos_release);
+	volume->creation_time = new;
+	return 0;
+
+regressed:
+	atomic_inc(&volume->cb_scrub);
+	trace_afs_cb_v_break(volume->vid, 0, afs_cb_break_for_creation_regress);
+	volume->creation_time = new;
+	return 0;
+}
+
+/*
+ * Handle a change to the volume update time in the VolSync record.
+ */
+static void afs_update_volume_update_time(struct afs_operation *op, struct afs_volume *volume)
+{
+	enum afs_cb_break_reason reason = afs_cb_break_no_break;
+	time64_t cur = volume->update_time;
+	time64_t old = op->pre_volsync.update;
+	time64_t new = op->volsync.update;
+
+	_enter("%llx,%llx,%llx->%llx", volume->vid, cur, old, new);
+
+	if (cur == TIME64_MIN) {
+		volume->update_time = new;
+		return;
+	}
+
+	if (new == cur)
+		return;
+
+	/* If the volume update time changes in an unexpected way, we need to
+	 * scrub our caches.  For a RW vol, this will advance on every
+	 * modification op; for a RO/Backup vol, this will advance when the
+	 * volume is updated to a new snapshot (eg. "vos release").
+	 */
+	if (new < old)
+		reason = afs_cb_break_for_update_regress;
+
+	/* Try to advance the update timestamp from what we had before the
+	 * operation to what we got back from the server.  This should
+	 * hopefully ensure that in a race between multiple operations only one
+	 * of them will do this.
+	 */
+	if (cur == old) {
+		if (reason == afs_cb_break_for_update_regress) {
+			atomic_inc(&volume->cb_scrub);
+			trace_afs_cb_v_break(volume->vid, 0, reason);
+		}
+		volume->update_time = new;
+	}
+}
+
+static int afs_update_volume_times(struct afs_operation *op, struct afs_volume *volume)
+{
+	int ret = 0;
+
+	if (likely(op->volsync.creation == volume->creation_time &&
+		   op->volsync.update == volume->update_time))
+		return 0;
+
+	mutex_lock(&volume->volsync_lock);
+	if (op->volsync.creation != volume->creation_time) {
+		ret = afs_update_volume_creation_time(op, volume);
+		if (ret < 0)
+			goto out;
+	}
+	if (op->volsync.update != volume->update_time)
+		afs_update_volume_update_time(op, volume);
+out:
+	mutex_unlock(&volume->volsync_lock);
+	return ret;
+}
+
+/*
+ * Update the state of a volume, including recording the expiration time of the
+ * callback promise.  Returns 1 to redo the operation from the start.
+ */
+int afs_update_volume_state(struct afs_operation *op)
+{
+	struct afs_server_list *slist = op->server_list;
+	struct afs_server_entry *se = &slist->servers[op->server_index];
+	struct afs_callback *cb = &op->file[0].scb.callback;
+	struct afs_volume *volume = op->volume;
+	unsigned int cb_v_break = atomic_read(&volume->cb_v_break);
+	unsigned int cb_v_check = atomic_read(&volume->cb_v_check);
+	int ret;
+
+	_enter("%llx", op->volume->vid);
+
+	if (op->volsync.creation != TIME64_MIN || op->volsync.update != TIME64_MIN) {
+		ret = afs_update_volume_times(op, volume);
+		if (ret != 0) {
+			_leave(" = %d", ret);
+			return ret;
+		}
+	}
+
+	if (op->cb_v_break == cb_v_break &&
+	    (op->file[0].scb.have_cb || op->file[1].scb.have_cb)) {
+		time64_t expires_at = cb->expires_at;
+
+		if (!op->file[0].scb.have_cb)
+			expires_at = op->file[1].scb.callback.expires_at;
+
+		se->cb_expires_at = expires_at;
+		volume->cb_expires_at = expires_at;
+	}
+	if (cb_v_check < op->cb_v_break)
+		atomic_cmpxchg(&volume->cb_v_check, cb_v_check, op->cb_v_break);
+	return 0;
+}
+
+/*
+ * mark the data attached to an inode as obsolete due to a write on the server
+ * - might also want to ditch all the outstanding writes and dirty pages
+ */
+static void afs_zap_data(struct afs_vnode *vnode)
+{
+	_enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode);
+
+	afs_invalidate_cache(vnode, 0);
+
+	/* nuke all the non-dirty pages that aren't locked, mapped or being
+	 * written back in a regular file and completely discard the pages in a
+	 * directory or symlink */
+	if (S_ISREG(vnode->netfs.inode.i_mode))
+		invalidate_remote_inode(&vnode->netfs.inode);
+	else
+		invalidate_inode_pages2(vnode->netfs.inode.i_mapping);
+}
+
+/*
+ * validate a vnode/inode
+ * - there are several things we need to check
+ *   - parent dir data changes (rm, rmdir, rename, mkdir, create, link,
+ *     symlink)
+ *   - parent dir metadata changed (security changes)
+ *   - dentry data changed (write, truncate)
+ *   - dentry metadata changed (security changes)
+ */
+int afs_validate(struct afs_vnode *vnode, struct key *key)
+{
+	struct afs_volume *volume = vnode->volume;
+	unsigned int cb_ro_snapshot, cb_scrub;
+	time64_t deadline = ktime_get_real_seconds() + 10;
+	bool zap = false, locked_vol = false;
+	int ret;
+
+	_enter("{v={%llx:%llu} fl=%lx},%x",
+	       vnode->fid.vid, vnode->fid.vnode, vnode->flags,
+	       key_serial(key));
+
+	if (afs_check_validity(vnode))
+		return 0;
+
+	ret = down_write_killable(&vnode->validate_lock);
+	if (ret < 0)
+		goto error;
+
+	/* Validate a volume after the v_break has changed or the volume
+	 * callback expired.  We only want to do this once per volume per
+	 * v_break change.  The actual work will be done when parsing the
+	 * status fetch reply.
+	 */
+	if (volume->cb_expires_at <= deadline ||
+	    atomic_read(&volume->cb_v_check) != atomic_read(&volume->cb_v_break)) {
+		ret = mutex_lock_interruptible(&volume->cb_check_lock);
+		if (ret < 0)
+			goto error_unlock;
+		locked_vol = true;
+	}
+
+	cb_ro_snapshot = atomic_read(&volume->cb_ro_snapshot);
+	cb_scrub = atomic_read(&volume->cb_scrub);
+	if (vnode->cb_ro_snapshot != cb_ro_snapshot ||
+	    vnode->cb_scrub	  != cb_scrub)
+		unmap_mapping_pages(vnode->netfs.inode.i_mapping, 0, 0, false);
+
+	if (vnode->cb_ro_snapshot != cb_ro_snapshot ||
+	    vnode->cb_scrub	  != cb_scrub ||
+	    volume->cb_expires_at <= deadline ||
+	    atomic_read(&volume->cb_v_check) != atomic_read(&volume->cb_v_break) ||
+	    atomic64_read(&vnode->cb_expires_at) <= deadline
+	    ) {
+		ret = afs_fetch_status(vnode, key, false, NULL);
+		if (ret < 0) {
+			if (ret == -ENOENT) {
+				set_bit(AFS_VNODE_DELETED, &vnode->flags);
+				ret = -ESTALE;
+			}
+			goto error_unlock;
+		}
+
+		_debug("new promise [fl=%lx]", vnode->flags);
+	}
+
+	/* We can drop the volume lock now as. */
+	if (locked_vol) {
+		mutex_unlock(&volume->cb_check_lock);
+		locked_vol = false;
+	}
+
+	cb_ro_snapshot = atomic_read(&volume->cb_ro_snapshot);
+	cb_scrub = atomic_read(&volume->cb_scrub);
+	_debug("vnode inval %x==%x %x==%x",
+	       vnode->cb_ro_snapshot, cb_ro_snapshot,
+	       vnode->cb_scrub, cb_scrub);
+	if (vnode->cb_scrub != cb_scrub)
+		zap = true;
+	vnode->cb_ro_snapshot = cb_ro_snapshot;
+	vnode->cb_scrub = cb_scrub;
+
+	if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
+		_debug("file already deleted");
+		ret = -ESTALE;
+		goto error_unlock;
+	}
+
+	/* if the vnode's data version number changed then its contents are
+	 * different */
+	zap |= test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags);
+	if (zap)
+		afs_zap_data(vnode);
+	up_write(&vnode->validate_lock);
+	_leave(" = 0");
+	return 0;
+
+error_unlock:
+	if (locked_vol)
+		mutex_unlock(&volume->cb_check_lock);
+	up_write(&vnode->validate_lock);
+error:
+	_leave(" = %d", ret);
+	return ret;
+}
diff --git a/fs/afs/vl_alias.c b/fs/afs/vl_alias.c
index f04a80e4f5c3..9f36e14f1c2d 100644
--- a/fs/afs/vl_alias.c
+++ b/fs/afs/vl_alias.c
@@ -33,55 +33,6 @@ static struct afs_volume *afs_sample_volume(struct afs_cell *cell, struct key *k
 }
 
 /*
- * Compare two addresses.
- */
-static int afs_compare_addrs(const struct sockaddr_rxrpc *srx_a,
-			     const struct sockaddr_rxrpc *srx_b)
-{
-	short port_a, port_b;
-	int addr_a, addr_b, diff;
-
-	diff = (short)srx_a->transport_type - (short)srx_b->transport_type;
-	if (diff)
-		goto out;
-
-	switch (srx_a->transport_type) {
-	case AF_INET: {
-		const struct sockaddr_in *a = &srx_a->transport.sin;
-		const struct sockaddr_in *b = &srx_b->transport.sin;
-		addr_a = ntohl(a->sin_addr.s_addr);
-		addr_b = ntohl(b->sin_addr.s_addr);
-		diff = addr_a - addr_b;
-		if (diff == 0) {
-			port_a = ntohs(a->sin_port);
-			port_b = ntohs(b->sin_port);
-			diff = port_a - port_b;
-		}
-		break;
-	}
-
-	case AF_INET6: {
-		const struct sockaddr_in6 *a = &srx_a->transport.sin6;
-		const struct sockaddr_in6 *b = &srx_b->transport.sin6;
-		diff = memcmp(&a->sin6_addr, &b->sin6_addr, 16);
-		if (diff == 0) {
-			port_a = ntohs(a->sin6_port);
-			port_b = ntohs(b->sin6_port);
-			diff = port_a - port_b;
-		}
-		break;
-	}
-
-	default:
-		WARN_ON(1);
-		diff = 1;
-	}
-
-out:
-	return diff;
-}
-
-/*
  * Compare the address lists of a pair of fileservers.
  */
 static int afs_compare_fs_alists(const struct afs_server *server_a,
@@ -90,13 +41,13 @@ static int afs_compare_fs_alists(const struct afs_server *server_a,
 	const struct afs_addr_list *la, *lb;
 	int a = 0, b = 0, addr_matches = 0;
 
-	la = rcu_dereference(server_a->addresses);
-	lb = rcu_dereference(server_b->addresses);
+	la = rcu_dereference(server_a->endpoint_state)->addresses;
+	lb = rcu_dereference(server_b->endpoint_state)->addresses;
 
 	while (a < la->nr_addrs && b < lb->nr_addrs) {
-		const struct sockaddr_rxrpc *srx_a = &la->addrs[a];
-		const struct sockaddr_rxrpc *srx_b = &lb->addrs[b];
-		int diff = afs_compare_addrs(srx_a, srx_b);
+		unsigned long pa = (unsigned long)la->addrs[a].peer;
+		unsigned long pb = (unsigned long)lb->addrs[b].peer;
+		long diff = pa - pb;
 
 		if (diff < 0) {
 			a++;
@@ -126,7 +77,7 @@ static int afs_compare_volume_slists(const struct afs_volume *vol_a,
 	lb = rcu_dereference(vol_b->servers);
 
 	for (i = 0; i < AFS_MAXTYPES; i++)
-		if (la->vids[i] != lb->vids[i])
+		if (vol_a->vids[i] != vol_b->vids[i])
 			return 0;
 
 	while (a < la->nr_servers && b < lb->nr_servers) {
@@ -205,7 +156,7 @@ static int afs_query_for_alias_one(struct afs_cell *cell, struct key *key,
 	/* And see if it's in the new cell. */
 	volume = afs_sample_volume(cell, key, pvol->name, pvol->name_len);
 	if (IS_ERR(volume)) {
-		afs_put_volume(cell->net, pvol, afs_volume_trace_put_query_alias);
+		afs_put_volume(pvol, afs_volume_trace_put_query_alias);
 		if (PTR_ERR(volume) != -ENOMEDIUM)
 			return PTR_ERR(volume);
 		/* That volume is not in the new cell, so not an alias */
@@ -223,8 +174,8 @@ static int afs_query_for_alias_one(struct afs_cell *cell, struct key *key,
 		rcu_read_unlock();
 	}
 
-	afs_put_volume(cell->net, volume, afs_volume_trace_put_query_alias);
-	afs_put_volume(cell->net, pvol, afs_volume_trace_put_query_alias);
+	afs_put_volume(volume, afs_volume_trace_put_query_alias);
+	afs_put_volume(pvol, afs_volume_trace_put_query_alias);
 	return ret;
 }
 
@@ -285,7 +236,7 @@ static char *afs_vl_get_cell_name(struct afs_cell *cell, struct key *key)
 
 	while (afs_select_vlserver(&vc)) {
 		if (!test_bit(AFS_VLSERVER_FL_IS_YFS, &vc.server->flags)) {
-			vc.ac.error = -EOPNOTSUPP;
+			vc.call_error = -EOPNOTSUPP;
 			skipped = true;
 			continue;
 		}
diff --git a/fs/afs/vl_list.c b/fs/afs/vl_list.c
index acc48216136a..9b1c20daac53 100644
--- a/fs/afs/vl_list.c
+++ b/fs/afs/vl_list.c
@@ -13,6 +13,7 @@ struct afs_vlserver *afs_alloc_vlserver(const char *name, size_t name_len,
 					unsigned short port)
 {
 	struct afs_vlserver *vlserver;
+	static atomic_t debug_ids;
 
 	vlserver = kzalloc(struct_size(vlserver, name, name_len + 1),
 			   GFP_KERNEL);
@@ -21,8 +22,10 @@ struct afs_vlserver *afs_alloc_vlserver(const char *name, size_t name_len,
 		rwlock_init(&vlserver->lock);
 		init_waitqueue_head(&vlserver->probe_wq);
 		spin_lock_init(&vlserver->probe_lock);
+		vlserver->debug_id = atomic_inc_return(&debug_ids);
 		vlserver->rtt = UINT_MAX;
 		vlserver->name_len = name_len;
+		vlserver->service_id = VL_SERVICE;
 		vlserver->port = port;
 		memcpy(vlserver->name, name, name_len);
 	}
@@ -33,7 +36,8 @@ static void afs_vlserver_rcu(struct rcu_head *rcu)
 {
 	struct afs_vlserver *vlserver = container_of(rcu, struct afs_vlserver, rcu);
 
-	afs_put_addrlist(rcu_access_pointer(vlserver->addresses));
+	afs_put_addrlist(rcu_access_pointer(vlserver->addresses),
+			 afs_alist_trace_put_vlserver);
 	kfree_rcu(vlserver, rcu);
 }
 
@@ -83,14 +87,15 @@ static u16 afs_extract_le16(const u8 **_b)
 /*
  * Build a VL server address list from a DNS queried server list.
  */
-static struct afs_addr_list *afs_extract_vl_addrs(const u8 **_b, const u8 *end,
+static struct afs_addr_list *afs_extract_vl_addrs(struct afs_net *net,
+						  const u8 **_b, const u8 *end,
 						  u8 nr_addrs, u16 port)
 {
 	struct afs_addr_list *alist;
 	const u8 *b = *_b;
 	int ret = -EINVAL;
 
-	alist = afs_alloc_addrlist(nr_addrs, VL_SERVICE, port);
+	alist = afs_alloc_addrlist(nr_addrs);
 	if (!alist)
 		return ERR_PTR(-ENOMEM);
 	if (nr_addrs == 0)
@@ -109,7 +114,9 @@ static struct afs_addr_list *afs_extract_vl_addrs(const u8 **_b, const u8 *end,
 				goto error;
 			}
 			memcpy(x, b, 4);
-			afs_merge_fs_addr4(alist, x[0], port);
+			ret = afs_merge_fs_addr4(net, alist, x[0], port);
+			if (ret < 0)
+				goto error;
 			b += 4;
 			break;
 
@@ -119,7 +126,9 @@ static struct afs_addr_list *afs_extract_vl_addrs(const u8 **_b, const u8 *end,
 				goto error;
 			}
 			memcpy(x, b, 16);
-			afs_merge_fs_addr6(alist, x, port);
+			ret = afs_merge_fs_addr6(net, alist, x, port);
+			if (ret < 0)
+				goto error;
 			b += 16;
 			break;
 
@@ -140,7 +149,7 @@ static struct afs_addr_list *afs_extract_vl_addrs(const u8 **_b, const u8 *end,
 
 error:
 	*_b = b;
-	afs_put_addrlist(alist);
+	afs_put_addrlist(alist, afs_alist_trace_put_parse_error);
 	return ERR_PTR(ret);
 }
 
@@ -247,7 +256,7 @@ struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *cell,
 		/* Extract the addresses - note that we can't skip this as we
 		 * have to advance the payload pointer.
 		 */
-		addrs = afs_extract_vl_addrs(&b, end, bs.nr_addrs, bs.port);
+		addrs = afs_extract_vl_addrs(cell->net, &b, end, bs.nr_addrs, bs.port);
 		if (IS_ERR(addrs)) {
 			ret = PTR_ERR(addrs);
 			goto error_2;
@@ -255,7 +264,7 @@ struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *cell,
 
 		if (vllist->nr_servers >= nr_servers) {
 			_debug("skip %u >= %u", vllist->nr_servers, nr_servers);
-			afs_put_addrlist(addrs);
+			afs_put_addrlist(addrs, afs_alist_trace_put_parse_empty);
 			afs_put_vlserver(cell->net, server);
 			continue;
 		}
@@ -264,7 +273,7 @@ struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *cell,
 		addrs->status = bs.status;
 
 		if (addrs->nr_addrs == 0) {
-			afs_put_addrlist(addrs);
+			afs_put_addrlist(addrs, afs_alist_trace_put_parse_empty);
 			if (!rcu_access_pointer(server->addresses)) {
 				afs_put_vlserver(cell->net, server);
 				continue;
@@ -276,7 +285,7 @@ struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *cell,
 			old = rcu_replace_pointer(server->addresses, old,
 						  lockdep_is_held(&server->lock));
 			write_unlock(&server->lock);
-			afs_put_addrlist(old);
+			afs_put_addrlist(old, afs_alist_trace_put_vlserver_old);
 		}
 
 
diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c
index 58452b86e672..3d2e0c925460 100644
--- a/fs/afs/vl_probe.c
+++ b/fs/afs/vl_probe.c
@@ -46,11 +46,12 @@ static void afs_done_one_vl_probe(struct afs_vlserver *server, bool wake_up)
  */
 void afs_vlserver_probe_result(struct afs_call *call)
 {
-	struct afs_addr_list *alist = call->alist;
+	struct afs_addr_list *alist = call->vl_probe;
 	struct afs_vlserver *server = call->vlserver;
+	struct afs_address *addr = &alist->addrs[call->probe_index];
 	unsigned int server_index = call->server_index;
 	unsigned int rtt_us = 0;
-	unsigned int index = call->addr_ix;
+	unsigned int index = call->probe_index;
 	bool have_result = false;
 	int ret = call->error;
 
@@ -89,7 +90,7 @@ void afs_vlserver_probe_result(struct afs_call *call)
 	case -ETIME:
 	default:
 		clear_bit(index, &alist->responded);
-		set_bit(index, &alist->failed);
+		set_bit(index, &alist->probe_failed);
 		if (!(server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED) &&
 		    (server->probe.error == 0 ||
 		     server->probe.error == -ETIMEDOUT ||
@@ -101,21 +102,21 @@ void afs_vlserver_probe_result(struct afs_call *call)
 
 responded:
 	set_bit(index, &alist->responded);
-	clear_bit(index, &alist->failed);
+	clear_bit(index, &alist->probe_failed);
 
 	if (call->service_id == YFS_VL_SERVICE) {
 		server->probe.flags |= AFS_VLSERVER_PROBE_IS_YFS;
 		set_bit(AFS_VLSERVER_FL_IS_YFS, &server->flags);
-		alist->addrs[index].srx_service = call->service_id;
+		server->service_id = call->service_id;
 	} else {
 		server->probe.flags |= AFS_VLSERVER_PROBE_NOT_YFS;
 		if (!(server->probe.flags & AFS_VLSERVER_PROBE_IS_YFS)) {
 			clear_bit(AFS_VLSERVER_FL_IS_YFS, &server->flags);
-			alist->addrs[index].srx_service = call->service_id;
+			server->service_id = call->service_id;
 		}
 	}
 
-	rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us);
+	rtt_us = rxrpc_kernel_get_srtt(addr->peer);
 	if (rtt_us < server->probe.rtt) {
 		server->probe.rtt = rtt_us;
 		server->rtt = rtt_us;
@@ -130,8 +131,10 @@ responded:
 out:
 	spin_unlock(&server->probe_lock);
 
-	_debug("probe [%u][%u] %pISpc rtt=%u ret=%d",
-	       server_index, index, &alist->addrs[index].transport, rtt_us, ret);
+	trace_afs_vl_probe(server, false, alist, index, call->error, call->abort_code, rtt_us);
+	_debug("probe [%u][%u] %pISpc rtt=%d ret=%d",
+	       server_index, index, rxrpc_kernel_remote_addr(addr->peer),
+	       rtt_us, ret);
 
 	afs_done_one_vl_probe(server, have_result);
 }
@@ -146,35 +149,52 @@ static bool afs_do_probe_vlserver(struct afs_net *net,
 				  unsigned int server_index,
 				  struct afs_error *_e)
 {
-	struct afs_addr_cursor ac = {
-		.index = 0,
-	};
+	struct afs_addr_list *alist;
 	struct afs_call *call;
+	unsigned long unprobed;
+	unsigned int index, i;
 	bool in_progress = false;
+	int best_prio;
 
 	_enter("%s", server->name);
 
 	read_lock(&server->lock);
-	ac.alist = rcu_dereference_protected(server->addresses,
-					     lockdep_is_held(&server->lock));
+	alist = rcu_dereference_protected(server->addresses,
+					  lockdep_is_held(&server->lock));
+	afs_get_addrlist(alist, afs_alist_trace_get_vlprobe);
 	read_unlock(&server->lock);
 
-	atomic_set(&server->probe_outstanding, ac.alist->nr_addrs);
+	atomic_set(&server->probe_outstanding, alist->nr_addrs);
 	memset(&server->probe, 0, sizeof(server->probe));
 	server->probe.rtt = UINT_MAX;
 
-	for (ac.index = 0; ac.index < ac.alist->nr_addrs; ac.index++) {
-		call = afs_vl_get_capabilities(net, &ac, key, server,
+	unprobed = (1UL << alist->nr_addrs) - 1;
+	while (unprobed) {
+		best_prio = -1;
+		index = 0;
+		for (i = 0; i < alist->nr_addrs; i++) {
+			if (test_bit(i, &unprobed) &&
+			    alist->addrs[i].prio > best_prio) {
+				index = i;
+				best_prio = alist->addrs[i].prio;
+			}
+		}
+		__clear_bit(index, &unprobed);
+
+		trace_afs_vl_probe(server, true, alist, index, 0, 0, 0);
+		call = afs_vl_get_capabilities(net, alist, index, key, server,
 					       server_index);
 		if (!IS_ERR(call)) {
+			afs_prioritise_error(_e, call->error, call->abort_code);
 			afs_put_call(call);
 			in_progress = true;
 		} else {
-			afs_prioritise_error(_e, PTR_ERR(call), ac.abort_code);
+			afs_prioritise_error(_e, PTR_ERR(call), 0);
 			afs_done_one_vl_probe(server, false);
 		}
 	}
 
+	afs_put_addrlist(alist, afs_alist_trace_put_vlprobe);
 	return in_progress;
 }
 
@@ -185,12 +205,10 @@ int afs_send_vl_probes(struct afs_net *net, struct key *key,
 		       struct afs_vlserver_list *vllist)
 {
 	struct afs_vlserver *server;
-	struct afs_error e;
+	struct afs_error e = {};
 	bool in_progress = false;
 	int i;
 
-	e.error = 0;
-	e.responded = false;
 	for (i = 0; i < vllist->nr_servers; i++) {
 		server = vllist->servers[i].server;
 		if (test_bit(AFS_VLSERVER_FL_PROBED, &server->flags))
diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c
index 488e58490b16..d8f79f6ada3d 100644
--- a/fs/afs/vl_rotate.c
+++ b/fs/afs/vl_rotate.c
@@ -17,18 +17,21 @@
 bool afs_begin_vlserver_operation(struct afs_vl_cursor *vc, struct afs_cell *cell,
 				  struct key *key)
 {
+	static atomic_t debug_ids;
+
 	memset(vc, 0, sizeof(*vc));
 	vc->cell = cell;
 	vc->key = key;
-	vc->error = -EDESTADDRREQ;
-	vc->ac.error = SHRT_MAX;
+	vc->cumul_error.error = -EDESTADDRREQ;
+	vc->nr_iterations = -1;
 
 	if (signal_pending(current)) {
-		vc->error = -EINTR;
+		vc->cumul_error.error = -EINTR;
 		vc->flags |= AFS_VL_CURSOR_STOP;
 		return false;
 	}
 
+	vc->debug_id = atomic_inc_return(&debug_ids);
 	return true;
 }
 
@@ -52,14 +55,20 @@ static bool afs_start_vl_iteration(struct afs_vl_cursor *vc)
 				    &cell->dns_lookup_count,
 				    smp_load_acquire(&cell->dns_lookup_count)
 				    != dns_lookup_count) < 0) {
-				vc->error = -ERESTARTSYS;
+				vc->cumul_error.error = -ERESTARTSYS;
 				return false;
 			}
 		}
 
 		/* Status load is ordered after lookup counter load */
+		if (cell->dns_status == DNS_LOOKUP_GOT_NOT_FOUND) {
+			pr_warn("No record of cell %s\n", cell->name);
+			vc->cumul_error.error = -ENOENT;
+			return false;
+		}
+
 		if (cell->dns_source == DNS_RECORD_UNAVAILABLE) {
-			vc->error = -EDESTADDRREQ;
+			vc->cumul_error.error = -EDESTADDRREQ;
 			return false;
 		}
 	}
@@ -72,8 +81,8 @@ static bool afs_start_vl_iteration(struct afs_vl_cursor *vc)
 	if (!vc->server_list->nr_servers)
 		return false;
 
-	vc->untried = (1UL << vc->server_list->nr_servers) - 1;
-	vc->index = -1;
+	vc->untried_servers = (1UL << vc->server_list->nr_servers) - 1;
+	vc->server_index = -1;
 	return true;
 }
 
@@ -83,54 +92,57 @@ static bool afs_start_vl_iteration(struct afs_vl_cursor *vc)
  */
 bool afs_select_vlserver(struct afs_vl_cursor *vc)
 {
-	struct afs_addr_list *alist;
+	struct afs_addr_list *alist = vc->alist;
 	struct afs_vlserver *vlserver;
-	struct afs_error e;
-	u32 rtt;
-	int error = vc->ac.error, i;
+	unsigned long set, failed;
+	unsigned int rtt;
+	s32 abort_code = vc->call_abort_code;
+	int error = vc->call_error, i;
 
-	_enter("%lx[%d],%lx[%d],%d,%d",
-	       vc->untried, vc->index,
-	       vc->ac.tried, vc->ac.index,
-	       error, vc->ac.abort_code);
+	vc->nr_iterations++;
+
+	_enter("VC=%x+%x,%d{%lx},%d{%lx},%d,%d",
+	       vc->debug_id, vc->nr_iterations, vc->server_index, vc->untried_servers,
+	       vc->addr_index, vc->addr_tried,
+	       error, abort_code);
 
 	if (vc->flags & AFS_VL_CURSOR_STOP) {
 		_leave(" = f [stopped]");
 		return false;
 	}
 
-	vc->nr_iterations++;
+	if (vc->nr_iterations == 0)
+		goto start;
+
+	WRITE_ONCE(alist->addrs[vc->addr_index].last_error, error);
 
 	/* Evaluate the result of the previous operation, if there was one. */
 	switch (error) {
-	case SHRT_MAX:
-		goto start;
-
 	default:
 	case 0:
 		/* Success or local failure.  Stop. */
-		vc->error = error;
+		vc->cumul_error.error = error;
 		vc->flags |= AFS_VL_CURSOR_STOP;
-		_leave(" = f [okay/local %d]", vc->ac.error);
+		_leave(" = f [okay/local %d]", vc->cumul_error.error);
 		return false;
 
 	case -ECONNABORTED:
 		/* The far side rejected the operation on some grounds.  This
 		 * might involve the server being busy or the volume having been moved.
 		 */
-		switch (vc->ac.abort_code) {
+		switch (abort_code) {
 		case AFSVL_IO:
 		case AFSVL_BADVOLOPER:
 		case AFSVL_NOMEM:
 			/* The server went weird. */
-			vc->error = -EREMOTEIO;
+			afs_prioritise_error(&vc->cumul_error, -EREMOTEIO, abort_code);
 			//write_lock(&vc->cell->vl_servers_lock);
-			//vc->server_list->weird_mask |= 1 << vc->index;
+			//vc->server_list->weird_mask |= 1 << vc->server_index;
 			//write_unlock(&vc->cell->vl_servers_lock);
 			goto next_server;
 
 		default:
-			vc->error = afs_abort_to_error(vc->ac.abort_code);
+			afs_prioritise_error(&vc->cumul_error, error, abort_code);
 			goto failed;
 		}
 
@@ -143,12 +155,12 @@ bool afs_select_vlserver(struct afs_vl_cursor *vc)
 	case -ETIMEDOUT:
 	case -ETIME:
 		_debug("no conn %d", error);
-		vc->error = error;
+		afs_prioritise_error(&vc->cumul_error, error, 0);
 		goto iterate_address;
 
 	case -ECONNRESET:
 		_debug("call reset");
-		vc->error = error;
+		afs_prioritise_error(&vc->cumul_error, error, 0);
 		vc->flags |= AFS_VL_CURSOR_RETRY;
 		goto next_server;
 
@@ -159,7 +171,13 @@ bool afs_select_vlserver(struct afs_vl_cursor *vc)
 
 restart_from_beginning:
 	_debug("restart");
-	afs_end_cursor(&vc->ac);
+	if (vc->call_responded &&
+	    vc->addr_index != vc->alist->preferred &&
+	    test_bit(alist->preferred, &vc->addr_tried))
+		WRITE_ONCE(alist->preferred, vc->addr_index);
+	afs_put_addrlist(alist, afs_alist_trace_put_vlrotate_restart);
+	alist = vc->alist = NULL;
+
 	afs_put_vlserverlist(vc->cell->net, vc->server_list);
 	vc->server_list = NULL;
 	if (vc->flags & AFS_VL_CURSOR_RETRIED)
@@ -167,53 +185,58 @@ restart_from_beginning:
 	vc->flags |= AFS_VL_CURSOR_RETRIED;
 start:
 	_debug("start");
+	ASSERTCMP(alist, ==, NULL);
 
 	if (!afs_start_vl_iteration(vc))
 		goto failed;
 
 	error = afs_send_vl_probes(vc->cell->net, vc->key, vc->server_list);
-	if (error < 0)
-		goto failed_set_error;
+	if (error < 0) {
+		afs_prioritise_error(&vc->cumul_error, error, 0);
+		goto failed;
+	}
 
 pick_server:
-	_debug("pick [%lx]", vc->untried);
+	_debug("pick [%lx]", vc->untried_servers);
+	ASSERTCMP(alist, ==, NULL);
 
-	error = afs_wait_for_vl_probes(vc->server_list, vc->untried);
-	if (error < 0)
-		goto failed_set_error;
+	error = afs_wait_for_vl_probes(vc->server_list, vc->untried_servers);
+	if (error < 0) {
+		afs_prioritise_error(&vc->cumul_error, error, 0);
+		goto failed;
+	}
 
 	/* Pick the untried server with the lowest RTT. */
-	vc->index = vc->server_list->preferred;
-	if (test_bit(vc->index, &vc->untried))
+	vc->server_index = vc->server_list->preferred;
+	if (test_bit(vc->server_index, &vc->untried_servers))
 		goto selected_server;
 
-	vc->index = -1;
-	rtt = U32_MAX;
+	vc->server_index = -1;
+	rtt = UINT_MAX;
 	for (i = 0; i < vc->server_list->nr_servers; i++) {
 		struct afs_vlserver *s = vc->server_list->servers[i].server;
 
-		if (!test_bit(i, &vc->untried) ||
+		if (!test_bit(i, &vc->untried_servers) ||
 		    !test_bit(AFS_VLSERVER_FL_RESPONDING, &s->flags))
 			continue;
-		if (s->probe.rtt < rtt) {
-			vc->index = i;
+		if (s->probe.rtt <= rtt) {
+			vc->server_index = i;
 			rtt = s->probe.rtt;
 		}
 	}
 
-	if (vc->index == -1)
+	if (vc->server_index == -1)
 		goto no_more_servers;
 
 selected_server:
-	_debug("use %d", vc->index);
-	__clear_bit(vc->index, &vc->untried);
+	_debug("use %d", vc->server_index);
+	__clear_bit(vc->server_index, &vc->untried_servers);
 
 	/* We're starting on a different vlserver from the list.  We need to
 	 * check it, find its address list and probe its capabilities before we
 	 * use it.
 	 */
-	ASSERTCMP(vc->ac.alist, ==, NULL);
-	vlserver = vc->server_list->servers[vc->index].server;
+	vlserver = vc->server_list->servers[vc->server_index].server;
 	vc->server = vlserver;
 
 	_debug("USING VLSERVER: %s", vlserver->name);
@@ -221,34 +244,48 @@ selected_server:
 	read_lock(&vlserver->lock);
 	alist = rcu_dereference_protected(vlserver->addresses,
 					  lockdep_is_held(&vlserver->lock));
-	afs_get_addrlist(alist);
+	vc->alist = afs_get_addrlist(alist, afs_alist_trace_get_vlrotate_set);
 	read_unlock(&vlserver->lock);
 
-	memset(&vc->ac, 0, sizeof(vc->ac));
-
-	if (!vc->ac.alist)
-		vc->ac.alist = alist;
-	else
-		afs_put_addrlist(alist);
-
-	vc->ac.index = -1;
+	vc->addr_tried = 0;
+	vc->addr_index = -1;
 
 iterate_address:
-	ASSERT(vc->ac.alist);
 	/* Iterate over the current server's address list to try and find an
 	 * address on which it will respond to us.
 	 */
-	if (!afs_iterate_addresses(&vc->ac))
+	set = READ_ONCE(alist->responded);
+	failed = READ_ONCE(alist->probe_failed);
+	vc->addr_index = READ_ONCE(alist->preferred);
+
+	_debug("%lx-%lx-%lx,%d", set, failed, vc->addr_tried, vc->addr_index);
+
+	set &= ~(failed | vc->addr_tried);
+
+	if (!set)
 		goto next_server;
 
-	_debug("VL address %d/%d", vc->ac.index, vc->ac.alist->nr_addrs);
+	if (!test_bit(vc->addr_index, &set))
+		vc->addr_index = __ffs(set);
+
+	set_bit(vc->addr_index, &vc->addr_tried);
+	vc->alist = alist;
 
-	_leave(" = t %pISpc", &vc->ac.alist->addrs[vc->ac.index].transport);
+	_debug("VL address %d/%d", vc->addr_index, alist->nr_addrs);
+
+	vc->call_responded = false;
+	_leave(" = t %pISpc", rxrpc_kernel_remote_addr(alist->addrs[vc->addr_index].peer));
 	return true;
 
 next_server:
 	_debug("next");
-	afs_end_cursor(&vc->ac);
+	ASSERT(alist);
+	if (vc->call_responded &&
+	    vc->addr_index != alist->preferred &&
+	    test_bit(alist->preferred, &vc->addr_tried))
+		WRITE_ONCE(alist->preferred, vc->addr_index);
+	afs_put_addrlist(alist, afs_alist_trace_put_vlrotate_next);
+	alist = vc->alist = NULL;
 	goto pick_server;
 
 no_more_servers:
@@ -258,25 +295,26 @@ no_more_servers:
 	if (vc->flags & AFS_VL_CURSOR_RETRY)
 		goto restart_from_beginning;
 
-	e.error = -EDESTADDRREQ;
-	e.responded = false;
 	for (i = 0; i < vc->server_list->nr_servers; i++) {
 		struct afs_vlserver *s = vc->server_list->servers[i].server;
 
 		if (test_bit(AFS_VLSERVER_FL_RESPONDING, &s->flags))
-			e.responded = true;
-		afs_prioritise_error(&e, READ_ONCE(s->probe.error),
+			vc->cumul_error.responded = true;
+		afs_prioritise_error(&vc->cumul_error, READ_ONCE(s->probe.error),
 				     s->probe.abort_code);
 	}
 
-	error = e.error;
-
-failed_set_error:
-	vc->error = error;
 failed:
+	if (alist) {
+		if (vc->call_responded &&
+		    vc->addr_index != alist->preferred &&
+		    test_bit(alist->preferred, &vc->addr_tried))
+			WRITE_ONCE(alist->preferred, vc->addr_index);
+		afs_put_addrlist(alist, afs_alist_trace_put_vlrotate_fail);
+		alist = vc->alist = NULL;
+	}
 	vc->flags |= AFS_VL_CURSOR_STOP;
-	afs_end_cursor(&vc->ac);
-	_leave(" = f [failed %d]", vc->error);
+	_leave(" = f [failed %d]", vc->cumul_error.error);
 	return false;
 }
 
@@ -285,6 +323,7 @@ failed:
  */
 static void afs_vl_dump_edestaddrreq(const struct afs_vl_cursor *vc)
 {
+	struct afs_cell *cell = vc->cell;
 	static int count;
 	int i;
 
@@ -294,8 +333,14 @@ static void afs_vl_dump_edestaddrreq(const struct afs_vl_cursor *vc)
 
 	rcu_read_lock();
 	pr_notice("EDESTADDR occurred\n");
+	pr_notice("CELL: %s err=%d\n", cell->name, cell->error);
+	pr_notice("DNS: src=%u st=%u lc=%x\n",
+		  cell->dns_source, cell->dns_status, cell->dns_lookup_count);
 	pr_notice("VC: ut=%lx ix=%u ni=%hu fl=%hx err=%hd\n",
-		  vc->untried, vc->index, vc->nr_iterations, vc->flags, vc->error);
+		  vc->untried_servers, vc->server_index, vc->nr_iterations,
+		  vc->flags, vc->cumul_error.error);
+	pr_notice("VC: call  er=%d ac=%d r=%u\n",
+		  vc->call_error, vc->call_abort_code, vc->call_responded);
 
 	if (vc->server_list) {
 		const struct afs_vlserver_list *sl = vc->server_list;
@@ -312,16 +357,14 @@ static void afs_vl_dump_edestaddrreq(const struct afs_vl_cursor *vc)
 					  a->nr_ipv4, a->nr_addrs, a->max_addrs,
 					  a->preferred);
 				pr_notice("VC:  - R=%lx F=%lx\n",
-					  a->responded, a->failed);
-				if (a == vc->ac.alist)
+					  a->responded, a->probe_failed);
+				if (a == vc->alist)
 					pr_notice("VC:  - current\n");
 			}
 		}
 	}
 
-	pr_notice("AC: t=%lx ax=%u ac=%d er=%d r=%u ni=%u\n",
-		  vc->ac.tried, vc->ac.index, vc->ac.abort_code, vc->ac.error,
-		  vc->ac.responded, vc->ac.nr_iterations);
+	pr_notice("AC: t=%lx ax=%u\n", vc->addr_tried, vc->addr_index);
 	rcu_read_unlock();
 }
 
@@ -332,17 +375,25 @@ int afs_end_vlserver_operation(struct afs_vl_cursor *vc)
 {
 	struct afs_net *net = vc->cell->net;
 
-	if (vc->error == -EDESTADDRREQ ||
-	    vc->error == -EADDRNOTAVAIL ||
-	    vc->error == -ENETUNREACH ||
-	    vc->error == -EHOSTUNREACH)
+	_enter("VC=%x+%x", vc->debug_id, vc->nr_iterations);
+
+	switch (vc->cumul_error.error) {
+	case -EDESTADDRREQ:
+	case -EADDRNOTAVAIL:
+	case -ENETUNREACH:
+	case -EHOSTUNREACH:
 		afs_vl_dump_edestaddrreq(vc);
+		break;
+	}
 
-	afs_end_cursor(&vc->ac);
+	if (vc->alist) {
+		if (vc->call_responded &&
+		    vc->addr_index != vc->alist->preferred &&
+		    test_bit(vc->alist->preferred, &vc->addr_tried))
+			WRITE_ONCE(vc->alist->preferred, vc->addr_index);
+		afs_put_addrlist(vc->alist, afs_alist_trace_put_vlrotate_end);
+		vc->alist = NULL;
+	}
 	afs_put_vlserverlist(net, vc->server_list);
-
-	if (vc->error == -ECONNABORTED)
-		vc->error = afs_abort_to_error(vc->ac.abort_code);
-
-	return vc->error;
+	return vc->cumul_error.error;
 }
diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c
index 00fca3c66ba6..cac75f89b64a 100644
--- a/fs/afs/vlclient.c
+++ b/fs/afs/vlclient.c
@@ -18,8 +18,7 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
 {
 	struct afs_uvldbentry__xdr *uvldb;
 	struct afs_vldb_entry *entry;
-	bool new_only = false;
-	u32 tmp, nr_servers, vlflags;
+	u32 nr_servers, vlflags;
 	int i, ret;
 
 	_enter("");
@@ -41,27 +40,14 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
 	entry->name[i] = 0;
 	entry->name_len = strlen(entry->name);
 
-	/* If there is a new replication site that we can use, ignore all the
-	 * sites that aren't marked as new.
-	 */
-	for (i = 0; i < nr_servers; i++) {
-		tmp = ntohl(uvldb->serverFlags[i]);
-		if (!(tmp & AFS_VLSF_DONTUSE) &&
-		    (tmp & AFS_VLSF_NEWREPSITE))
-			new_only = true;
-	}
-
 	vlflags = ntohl(uvldb->flags);
 	for (i = 0; i < nr_servers; i++) {
 		struct afs_uuid__xdr *xdr;
 		struct afs_uuid *uuid;
+		u32 tmp = ntohl(uvldb->serverFlags[i]);
 		int j;
 		int n = entry->nr_servers;
 
-		tmp = ntohl(uvldb->serverFlags[i]);
-		if (tmp & AFS_VLSF_DONTUSE ||
-		    (new_only && !(tmp & AFS_VLSF_NEWREPSITE)))
-			continue;
 		if (tmp & AFS_VLSF_RWVOL) {
 			entry->fs_mask[n] |= AFS_VOL_VTM_RW;
 			if (vlflags & AFS_VLF_BACKEXISTS)
@@ -82,6 +68,7 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
 		for (j = 0; j < 6; j++)
 			uuid->node[j] = (u8)ntohl(xdr->node[j]);
 
+		entry->vlsf_flags[n] = tmp;
 		entry->addr_version[n] = ntohl(uvldb->serverUnique[i]);
 		entry->nr_servers++;
 	}
@@ -106,12 +93,6 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
 	return 0;
 }
 
-static void afs_destroy_vl_get_entry_by_name_u(struct afs_call *call)
-{
-	kfree(call->ret_vldb);
-	afs_flat_call_destructor(call);
-}
-
 /*
  * VL.GetEntryByNameU operation type.
  */
@@ -119,7 +100,7 @@ static const struct afs_call_type afs_RXVLGetEntryByNameU = {
 	.name		= "VL.GetEntryByNameU",
 	.op		= afs_VL_GetEntryByNameU,
 	.deliver	= afs_deliver_vl_get_entry_by_name_u,
-	.destructor	= afs_destroy_vl_get_entry_by_name_u,
+	.destructor	= afs_flat_call_destructor,
 };
 
 /*
@@ -155,6 +136,8 @@ struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_vl_cursor *vc,
 	call->key = vc->key;
 	call->ret_vldb = entry;
 	call->max_lifespan = AFS_VL_MAX_LIFESPAN;
+	call->peer = rxrpc_kernel_get_peer(vc->alist->addrs[vc->addr_index].peer);
+	call->service_id = vc->server->service_id;
 
 	/* Marshall the parameters */
 	bp = call->request;
@@ -165,8 +148,17 @@ struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_vl_cursor *vc,
 		memset((void *)bp + volnamesz, 0, padsz);
 
 	trace_afs_make_vl_call(call);
-	afs_make_call(&vc->ac, call, GFP_KERNEL);
-	return (struct afs_vldb_entry *)afs_wait_for_call_to_complete(call, &vc->ac);
+	afs_make_call(call, GFP_KERNEL);
+	afs_wait_for_call_to_complete(call);
+	vc->call_abort_code	= call->abort_code;
+	vc->call_error		= call->error;
+	vc->call_responded	= call->responded;
+	afs_put_call(call);
+	if (vc->call_error) {
+		kfree(entry);
+		return ERR_PTR(vc->call_error);
+	}
+	return entry;
 }
 
 /*
@@ -208,7 +200,7 @@ static int afs_deliver_vl_get_addrs_u(struct afs_call *call)
 		count		= ntohl(*bp);
 
 		nentries = min(nentries, count);
-		alist = afs_alloc_addrlist(nentries, FS_SERVICE, AFS_FS_PORT);
+		alist = afs_alloc_addrlist(nentries);
 		if (!alist)
 			return -ENOMEM;
 		alist->version = uniquifier;
@@ -230,9 +222,13 @@ static int afs_deliver_vl_get_addrs_u(struct afs_call *call)
 		alist = call->ret_alist;
 		bp = call->buffer;
 		count = min(call->count, 4U);
-		for (i = 0; i < count; i++)
-			if (alist->nr_addrs < call->count2)
-				afs_merge_fs_addr4(alist, *bp++, AFS_FS_PORT);
+		for (i = 0; i < count; i++) {
+			if (alist->nr_addrs < call->count2) {
+				ret = afs_merge_fs_addr4(call->net, alist, *bp++, AFS_FS_PORT);
+				if (ret < 0)
+					return ret;
+			}
+		}
 
 		call->count -= count;
 		if (call->count > 0)
@@ -245,12 +241,6 @@ static int afs_deliver_vl_get_addrs_u(struct afs_call *call)
 	return 0;
 }
 
-static void afs_vl_get_addrs_u_destructor(struct afs_call *call)
-{
-	afs_put_addrlist(call->ret_alist);
-	return afs_flat_call_destructor(call);
-}
-
 /*
  * VL.GetAddrsU operation type.
  */
@@ -258,7 +248,7 @@ static const struct afs_call_type afs_RXVLGetAddrsU = {
 	.name		= "VL.GetAddrsU",
 	.op		= afs_VL_GetAddrsU,
 	.deliver	= afs_deliver_vl_get_addrs_u,
-	.destructor	= afs_vl_get_addrs_u_destructor,
+	.destructor	= afs_flat_call_destructor,
 };
 
 /*
@@ -269,6 +259,7 @@ struct afs_addr_list *afs_vl_get_addrs_u(struct afs_vl_cursor *vc,
 					 const uuid_t *uuid)
 {
 	struct afs_ListAddrByAttributes__xdr *r;
+	struct afs_addr_list *alist;
 	const struct afs_uuid *u = (const struct afs_uuid *)uuid;
 	struct afs_call *call;
 	struct afs_net *net = vc->cell->net;
@@ -286,6 +277,8 @@ struct afs_addr_list *afs_vl_get_addrs_u(struct afs_vl_cursor *vc,
 	call->key = vc->key;
 	call->ret_alist = NULL;
 	call->max_lifespan = AFS_VL_MAX_LIFESPAN;
+	call->peer = rxrpc_kernel_get_peer(vc->alist->addrs[vc->addr_index].peer);
+	call->service_id = vc->server->service_id;
 
 	/* Marshall the parameters */
 	bp = call->request;
@@ -304,8 +297,18 @@ struct afs_addr_list *afs_vl_get_addrs_u(struct afs_vl_cursor *vc,
 		r->uuid.node[i] = htonl(u->node[i]);
 
 	trace_afs_make_vl_call(call);
-	afs_make_call(&vc->ac, call, GFP_KERNEL);
-	return (struct afs_addr_list *)afs_wait_for_call_to_complete(call, &vc->ac);
+	afs_make_call(call, GFP_KERNEL);
+	afs_wait_for_call_to_complete(call);
+	vc->call_abort_code	= call->abort_code;
+	vc->call_error		= call->error;
+	vc->call_responded	= call->responded;
+	alist			= call->ret_alist;
+	afs_put_call(call);
+	if (vc->call_error) {
+		afs_put_addrlist(alist, afs_alist_trace_put_getaddru);
+		return ERR_PTR(vc->call_error);
+	}
+	return alist;
 }
 
 /*
@@ -355,6 +358,7 @@ static int afs_deliver_vl_get_capabilities(struct afs_call *call)
 
 static void afs_destroy_vl_get_capabilities(struct afs_call *call)
 {
+	afs_put_addrlist(call->vl_probe, afs_alist_trace_put_vlgetcaps);
 	afs_put_vlserver(call->net, call->vlserver);
 	afs_flat_call_destructor(call);
 }
@@ -378,7 +382,8 @@ static const struct afs_call_type afs_RXVLGetCapabilities = {
  * other end supports.
  */
 struct afs_call *afs_vl_get_capabilities(struct afs_net *net,
-					 struct afs_addr_cursor *ac,
+					 struct afs_addr_list *alist,
+					 unsigned int addr_index,
 					 struct key *key,
 					 struct afs_vlserver *server,
 					 unsigned int server_index)
@@ -395,6 +400,10 @@ struct afs_call *afs_vl_get_capabilities(struct afs_net *net,
 	call->key = key;
 	call->vlserver = afs_get_vlserver(server);
 	call->server_index = server_index;
+	call->peer = rxrpc_kernel_get_peer(alist->addrs[addr_index].peer);
+	call->vl_probe = afs_get_addrlist(alist, afs_alist_trace_get_vlgetcaps);
+	call->probe_index = addr_index;
+	call->service_id = server->service_id;
 	call->upgrade = true;
 	call->async = true;
 	call->max_lifespan = AFS_PROBE_MAX_LIFESPAN;
@@ -405,7 +414,7 @@ struct afs_call *afs_vl_get_capabilities(struct afs_net *net,
 
 	/* Can't take a ref on server */
 	trace_afs_make_vl_call(call);
-	afs_make_call(ac, call, GFP_KERNEL);
+	afs_make_call(call, GFP_KERNEL);
 	return call;
 }
 
@@ -450,7 +459,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call)
 		if (call->count > YFS_MAXENDPOINTS)
 			return afs_protocol_error(call, afs_eproto_yvl_fsendpt_num);
 
-		alist = afs_alloc_addrlist(call->count, FS_SERVICE, AFS_FS_PORT);
+		alist = afs_alloc_addrlist(call->count);
 		if (!alist)
 			return -ENOMEM;
 		alist->version = uniquifier;
@@ -488,14 +497,18 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call)
 			if (ntohl(bp[0]) != sizeof(__be32) * 2)
 				return afs_protocol_error(
 					call, afs_eproto_yvl_fsendpt4_len);
-			afs_merge_fs_addr4(alist, bp[1], ntohl(bp[2]));
+			ret = afs_merge_fs_addr4(call->net, alist, bp[1], ntohl(bp[2]));
+			if (ret < 0)
+				return ret;
 			bp += 3;
 			break;
 		case YFS_ENDPOINT_IPV6:
 			if (ntohl(bp[0]) != sizeof(__be32) * 5)
 				return afs_protocol_error(
 					call, afs_eproto_yvl_fsendpt6_len);
-			afs_merge_fs_addr6(alist, bp + 1, ntohl(bp[5]));
+			ret = afs_merge_fs_addr6(call->net, alist, bp + 1, ntohl(bp[5]));
+			if (ret < 0)
+				return ret;
 			bp += 6;
 			break;
 		default:
@@ -610,7 +623,7 @@ static const struct afs_call_type afs_YFSVLGetEndpoints = {
 	.name		= "YFSVL.GetEndpoints",
 	.op		= afs_YFSVL_GetEndpoints,
 	.deliver	= afs_deliver_yfsvl_get_endpoints,
-	.destructor	= afs_vl_get_addrs_u_destructor,
+	.destructor	= afs_flat_call_destructor,
 };
 
 /*
@@ -620,6 +633,7 @@ static const struct afs_call_type afs_YFSVLGetEndpoints = {
 struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_vl_cursor *vc,
 					      const uuid_t *uuid)
 {
+	struct afs_addr_list *alist;
 	struct afs_call *call;
 	struct afs_net *net = vc->cell->net;
 	__be32 *bp;
@@ -635,6 +649,8 @@ struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_vl_cursor *vc,
 	call->key = vc->key;
 	call->ret_alist = NULL;
 	call->max_lifespan = AFS_VL_MAX_LIFESPAN;
+	call->peer = rxrpc_kernel_get_peer(vc->alist->addrs[vc->addr_index].peer);
+	call->service_id = vc->server->service_id;
 
 	/* Marshall the parameters */
 	bp = call->request;
@@ -643,8 +659,18 @@ struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_vl_cursor *vc,
 	memcpy(bp, uuid, sizeof(*uuid)); /* Type opr_uuid */
 
 	trace_afs_make_vl_call(call);
-	afs_make_call(&vc->ac, call, GFP_KERNEL);
-	return (struct afs_addr_list *)afs_wait_for_call_to_complete(call, &vc->ac);
+	afs_make_call(call, GFP_KERNEL);
+	afs_wait_for_call_to_complete(call);
+	vc->call_abort_code	= call->abort_code;
+	vc->call_error		= call->error;
+	vc->call_responded	= call->responded;
+	alist			= call->ret_alist;
+	afs_put_call(call);
+	if (vc->call_error) {
+		afs_put_addrlist(alist, afs_alist_trace_put_getaddru);
+		return ERR_PTR(vc->call_error);
+	}
+	return alist;
 }
 
 /*
@@ -709,12 +735,6 @@ static int afs_deliver_yfsvl_get_cell_name(struct afs_call *call)
 	return 0;
 }
 
-static void afs_destroy_yfsvl_get_cell_name(struct afs_call *call)
-{
-	kfree(call->ret_str);
-	afs_flat_call_destructor(call);
-}
-
 /*
  * VL.GetCapabilities operation type
  */
@@ -722,7 +742,7 @@ static const struct afs_call_type afs_YFSVLGetCellName = {
 	.name		= "YFSVL.GetCellName",
 	.op		= afs_YFSVL_GetCellName,
 	.deliver	= afs_deliver_yfsvl_get_cell_name,
-	.destructor	= afs_destroy_yfsvl_get_cell_name,
+	.destructor	= afs_flat_call_destructor,
 };
 
 /*
@@ -737,6 +757,7 @@ char *afs_yfsvl_get_cell_name(struct afs_vl_cursor *vc)
 	struct afs_call *call;
 	struct afs_net *net = vc->cell->net;
 	__be32 *bp;
+	char *cellname;
 
 	_enter("");
 
@@ -747,6 +768,8 @@ char *afs_yfsvl_get_cell_name(struct afs_vl_cursor *vc)
 	call->key = vc->key;
 	call->ret_str = NULL;
 	call->max_lifespan = AFS_VL_MAX_LIFESPAN;
+	call->peer = rxrpc_kernel_get_peer(vc->alist->addrs[vc->addr_index].peer);
+	call->service_id = vc->server->service_id;
 
 	/* marshall the parameters */
 	bp = call->request;
@@ -754,6 +777,16 @@ char *afs_yfsvl_get_cell_name(struct afs_vl_cursor *vc)
 
 	/* Can't take a ref on server */
 	trace_afs_make_vl_call(call);
-	afs_make_call(&vc->ac, call, GFP_KERNEL);
-	return (char *)afs_wait_for_call_to_complete(call, &vc->ac);
+	afs_make_call(call, GFP_KERNEL);
+	afs_wait_for_call_to_complete(call);
+	vc->call_abort_code	= call->abort_code;
+	vc->call_error		= call->error;
+	vc->call_responded	= call->responded;
+	cellname		= call->ret_str;
+	afs_put_call(call);
+	if (vc->call_error) {
+		kfree(cellname);
+		return ERR_PTR(vc->call_error);
+	}
+	return cellname;
 }
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index 29d483c80281..020ecd45e476 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -11,6 +11,8 @@
 
 static unsigned __read_mostly afs_volume_record_life = 60 * 60;
 
+static void afs_destroy_volume(struct work_struct *work);
+
 /*
  * Insert a volume into a cell.  If there's an existing volume record, that is
  * returned instead with a ref held.
@@ -32,8 +34,13 @@ static struct afs_volume *afs_insert_volume_into_cell(struct afs_cell *cell,
 		} else if (p->vid > volume->vid) {
 			pp = &(*pp)->rb_right;
 		} else {
-			volume = afs_get_volume(p, afs_volume_trace_get_cell_insert);
-			goto found;
+			if (afs_try_get_volume(p, afs_volume_trace_get_cell_insert)) {
+				volume = p;
+				goto found;
+			}
+
+			set_bit(AFS_VOLUME_RM_TREE, &volume->flags);
+			rb_replace_node_rcu(&p->cell_node, &volume->cell_node, &cell->volumes);
 		}
 	}
 
@@ -56,7 +63,8 @@ static void afs_remove_volume_from_cell(struct afs_volume *volume)
 				 afs_volume_trace_remove);
 		write_seqlock(&cell->volume_lock);
 		hlist_del_rcu(&volume->proc_link);
-		rb_erase(&volume->cell_node, &cell->volumes);
+		if (!test_and_set_bit(AFS_VOLUME_RM_TREE, &volume->flags))
+			rb_erase(&volume->cell_node, &cell->volumes);
 		write_sequnlock(&cell->volume_lock);
 	}
 }
@@ -66,11 +74,11 @@ static void afs_remove_volume_from_cell(struct afs_volume *volume)
  */
 static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params,
 					   struct afs_vldb_entry *vldb,
-					   unsigned long type_mask)
+					   struct afs_server_list **_slist)
 {
 	struct afs_server_list *slist;
 	struct afs_volume *volume;
-	int ret = -ENOMEM;
+	int ret = -ENOMEM, i;
 
 	volume = kzalloc(sizeof(struct afs_volume), GFP_KERNEL);
 	if (!volume)
@@ -82,20 +90,30 @@ static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params,
 	volume->type		= params->type;
 	volume->type_force	= params->force;
 	volume->name_len	= vldb->name_len;
+	volume->creation_time	= TIME64_MIN;
+	volume->update_time	= TIME64_MIN;
 
 	refcount_set(&volume->ref, 1);
 	INIT_HLIST_NODE(&volume->proc_link);
+	INIT_WORK(&volume->destructor, afs_destroy_volume);
 	rwlock_init(&volume->servers_lock);
+	mutex_init(&volume->volsync_lock);
+	mutex_init(&volume->cb_check_lock);
 	rwlock_init(&volume->cb_v_break_lock);
+	INIT_LIST_HEAD(&volume->open_mmaps);
+	init_rwsem(&volume->open_mmaps_lock);
 	memcpy(volume->name, vldb->name, vldb->name_len + 1);
 
-	slist = afs_alloc_server_list(params->cell, params->key, vldb, type_mask);
+	for (i = 0; i < AFS_MAXTYPES; i++)
+		volume->vids[i] = vldb->vid[i];
+
+	slist = afs_alloc_server_list(volume, params->key, vldb);
 	if (IS_ERR(slist)) {
 		ret = PTR_ERR(slist);
 		goto error_1;
 	}
 
-	refcount_set(&slist->usage, 1);
+	*_slist = slist;
 	rcu_assign_pointer(volume->servers, slist);
 	trace_afs_volume(volume->vid, 1, afs_volume_trace_alloc);
 	return volume;
@@ -111,18 +129,20 @@ error_0:
  * Look up or allocate a volume record.
  */
 static struct afs_volume *afs_lookup_volume(struct afs_fs_context *params,
-					    struct afs_vldb_entry *vldb,
-					    unsigned long type_mask)
+					    struct afs_vldb_entry *vldb)
 {
+	struct afs_server_list *slist;
 	struct afs_volume *candidate, *volume;
 
-	candidate = afs_alloc_volume(params, vldb, type_mask);
+	candidate = afs_alloc_volume(params, vldb, &slist);
 	if (IS_ERR(candidate))
 		return candidate;
 
 	volume = afs_insert_volume_into_cell(params->cell, candidate);
-	if (volume != candidate)
-		afs_put_volume(params->net, candidate, afs_volume_trace_put_cell_dup);
+	if (volume == candidate)
+		afs_attach_volume_to_servers(volume, slist);
+	else
+		afs_put_volume(candidate, afs_volume_trace_put_cell_dup);
 	return volume;
 }
 
@@ -202,8 +222,7 @@ struct afs_volume *afs_create_volume(struct afs_fs_context *params)
 		goto error;
 	}
 
-	type_mask = 1UL << params->type;
-	volume = afs_lookup_volume(params, vldb, type_mask);
+	volume = afs_lookup_volume(params, vldb);
 
 error:
 	kfree(vldb);
@@ -213,16 +232,20 @@ error:
 /*
  * Destroy a volume record
  */
-static void afs_destroy_volume(struct afs_net *net, struct afs_volume *volume)
+static void afs_destroy_volume(struct work_struct *work)
 {
+	struct afs_volume *volume = container_of(work, struct afs_volume, destructor);
+	struct afs_server_list *slist = rcu_access_pointer(volume->servers);
+
 	_enter("%p", volume);
 
 #ifdef CONFIG_AFS_FSCACHE
 	ASSERTCMP(volume->cache, ==, NULL);
 #endif
 
+	afs_detach_volume_from_servers(volume, slist);
 	afs_remove_volume_from_cell(volume);
-	afs_put_serverlist(net, rcu_access_pointer(volume->servers));
+	afs_put_serverlist(volume->cell->net, slist);
 	afs_put_cell(volume->cell, afs_cell_trace_put_vol);
 	trace_afs_volume(volume->vid, refcount_read(&volume->ref),
 			 afs_volume_trace_free);
@@ -232,6 +255,20 @@ static void afs_destroy_volume(struct afs_net *net, struct afs_volume *volume)
 }
 
 /*
+ * Try to get a reference on a volume record.
+ */
+bool afs_try_get_volume(struct afs_volume *volume, enum afs_volume_trace reason)
+{
+	int r;
+
+	if (__refcount_inc_not_zero(&volume->ref, &r)) {
+		trace_afs_volume(volume->vid, r + 1, reason);
+		return true;
+	}
+	return false;
+}
+
+/*
  * Get a reference on a volume record.
  */
 struct afs_volume *afs_get_volume(struct afs_volume *volume,
@@ -250,8 +287,7 @@ struct afs_volume *afs_get_volume(struct afs_volume *volume,
 /*
  * Drop a reference on a volume record.
  */
-void afs_put_volume(struct afs_net *net, struct afs_volume *volume,
-		    enum afs_volume_trace reason)
+void afs_put_volume(struct afs_volume *volume, enum afs_volume_trace reason)
 {
 	if (volume) {
 		afs_volid_t vid = volume->vid;
@@ -261,7 +297,7 @@ void afs_put_volume(struct afs_net *net, struct afs_volume *volume,
 		zero = __refcount_dec_and_test(&volume->ref, &r);
 		trace_afs_volume(vid, r - 1, reason);
 		if (zero)
-			afs_destroy_volume(net, volume);
+			schedule_work(&volume->destructor);
 	}
 }
 
@@ -342,8 +378,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key)
 	}
 
 	/* See if the volume's server list got updated. */
-	new = afs_alloc_server_list(volume->cell, key,
-				    vldb, (1 << volume->type));
+	new = afs_alloc_server_list(volume, key, vldb);
 	if (IS_ERR(new)) {
 		ret = PTR_ERR(new);
 		goto error_vldb;
@@ -362,11 +397,17 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key)
 		discard = old;
 	}
 
-	volume->update_at = ktime_get_real_seconds() + afs_volume_record_life;
+	/* Check more often if replication is ongoing. */
+	if (new->ro_replicating)
+		volume->update_at = ktime_get_real_seconds() + 10 * 60;
+	else
+		volume->update_at = ktime_get_real_seconds() + afs_volume_record_life;
 	write_unlock(&volume->servers_lock);
-	ret = 0;
 
+	if (discard == old)
+		afs_reattach_volume_to_servers(volume, new, old);
 	afs_put_serverlist(volume->cell->net, discard);
+	ret = 0;
 error_vldb:
 	kfree(vldb);
 error:
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 4a168781936b..61d34ad2ca7d 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -242,7 +242,7 @@ static void afs_kill_pages(struct address_space *mapping,
 		folio_clear_uptodate(folio);
 		folio_end_writeback(folio);
 		folio_lock(folio);
-		generic_error_remove_page(mapping, &folio->page);
+		generic_error_remove_folio(mapping, folio);
 		folio_unlock(folio);
 		folio_put(folio);
 
@@ -366,7 +366,7 @@ static void afs_store_data_success(struct afs_operation *op)
 
 	op->ctime = op->file[0].scb.status.mtime_client;
 	afs_vnode_commit_status(op, &op->file[0]);
-	if (op->error == 0) {
+	if (!afs_op_error(op)) {
 		if (!op->store.laundering)
 			afs_pages_written_back(vnode, op->store.pos, op->store.size);
 		afs_stat_v(vnode, n_stores);
@@ -428,7 +428,7 @@ try_next_key:
 
 	afs_wait_for_operation(op);
 
-	switch (op->error) {
+	switch (afs_op_error(op)) {
 	case -EACCES:
 	case -EPERM:
 	case -ENOKEY:
@@ -447,7 +447,7 @@ try_next_key:
 	}
 
 	afs_put_wb_key(wbk);
-	_leave(" = %d", op->error);
+	_leave(" = %d", afs_op_error(op));
 	return afs_put_operation(op);
 }
 
@@ -559,8 +559,7 @@ static void afs_extend_writeback(struct address_space *mapping,
 
 			if (!folio_clear_dirty_for_io(folio))
 				BUG();
-			if (folio_start_writeback(folio))
-				BUG();
+			folio_start_writeback(folio);
 			afs_folio_start_fscache(caching, folio);
 
 			*_count -= folio_nr_pages(folio);
@@ -595,8 +594,7 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping,
 
 	_enter(",%lx,%llx-%llx", folio_index(folio), start, end);
 
-	if (folio_start_writeback(folio))
-		BUG();
+	folio_start_writeback(folio);
 	afs_folio_start_fscache(caching, folio);
 
 	count -= folio_nr_pages(folio);
diff --git a/fs/afs/xattr.c b/fs/afs/xattr.c
index 64b2c0224f62..e19f396aa370 100644
--- a/fs/afs/xattr.c
+++ b/fs/afs/xattr.c
@@ -75,7 +75,7 @@ static bool afs_make_acl(struct afs_operation *op,
 {
 	struct afs_acl *acl;
 
-	acl = kmalloc(sizeof(*acl) + size, GFP_KERNEL);
+	acl = kmalloc(struct_size(acl, data, size), GFP_KERNEL);
 	if (!acl) {
 		afs_op_nomem(op);
 		return false;
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index 11571cca86c1..f521e66d3bf6 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -245,12 +245,15 @@ static void xdr_decode_YFSVolSync(const __be32 **_bp,
 				  struct afs_volsync *volsync)
 {
 	struct yfs_xdr_YFSVolSync *x = (void *)*_bp;
-	u64 creation;
+	u64 creation, update;
 
 	if (volsync) {
 		creation = xdr_to_u64(x->vol_creation_date);
 		do_div(creation, 10 * 1000 * 1000);
 		volsync->creation = creation;
+		update = xdr_to_u64(x->vol_update_date);
+		do_div(update, 10 * 1000 * 1000);
+		volsync->update = update;
 	}
 
 	*_bp += xdr_size(x);
@@ -490,6 +493,7 @@ void yfs_fs_fetch_data(struct afs_operation *op)
 	bp = xdr_encode_u64(bp, req->len);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -572,6 +576,7 @@ void yfs_fs_create_file(struct afs_operation *op)
 	bp = xdr_encode_u32(bp, yfs_LockNone); /* ViceLockType */
 	yfs_check_req(call, bp);
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -620,6 +625,7 @@ void yfs_fs_make_dir(struct afs_operation *op)
 	bp = xdr_encode_YFSStoreStatus(bp, &op->create.mode, &op->mtime);
 	yfs_check_req(call, bp);
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -704,6 +710,7 @@ void yfs_fs_remove_file2(struct afs_operation *op)
 	bp = xdr_encode_name(bp, name);
 	yfs_check_req(call, bp);
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -773,6 +780,7 @@ void yfs_fs_remove_file(struct afs_operation *op)
 	bp = xdr_encode_name(bp, name);
 	yfs_check_req(call, bp);
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -814,6 +822,7 @@ void yfs_fs_remove_dir(struct afs_operation *op)
 	bp = xdr_encode_name(bp, name);
 	yfs_check_req(call, bp);
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -887,6 +896,7 @@ void yfs_fs_link(struct afs_operation *op)
 	bp = xdr_encode_YFSFid(bp, &vp->fid);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call1(call, &vp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -968,6 +978,7 @@ void yfs_fs_symlink(struct afs_operation *op)
 	bp = xdr_encode_YFSStoreStatus(bp, &mode, &op->mtime);
 	yfs_check_req(call, bp);
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1047,6 +1058,7 @@ void yfs_fs_rename(struct afs_operation *op)
 	bp = xdr_encode_name(bp, new_name);
 	yfs_check_req(call, bp);
 
+	call->fid = orig_dvp->fid;
 	trace_afs_make_fs_call2(call, &orig_dvp->fid, orig_name, new_name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1102,6 +1114,7 @@ void yfs_fs_store_data(struct afs_operation *op)
 	bp = xdr_encode_u64(bp, op->store.i_size);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1158,6 +1171,7 @@ static void yfs_fs_setattr_size(struct afs_operation *op)
 	bp = xdr_encode_u64(bp, attr->ia_size);	/* new file length */
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1196,6 +1210,7 @@ void yfs_fs_setattr(struct afs_operation *op)
 	bp = xdr_encode_YFS_StoreStatus(bp, attr);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1366,6 +1381,7 @@ void yfs_fs_get_volume_status(struct afs_operation *op)
 	bp = xdr_encode_u64(bp, vp->fid.vid);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1430,6 +1446,7 @@ void yfs_fs_set_lock(struct afs_operation *op)
 	bp = xdr_encode_u32(bp, op->lock.type);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_calli(call, &vp->fid, op->lock.type);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1460,6 +1477,7 @@ void yfs_fs_extend_lock(struct afs_operation *op)
 	bp = xdr_encode_YFSFid(bp, &vp->fid);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1490,6 +1508,7 @@ void yfs_fs_release_lock(struct afs_operation *op)
 	bp = xdr_encode_YFSFid(bp, &vp->fid);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1556,6 +1575,7 @@ void yfs_fs_fetch_status(struct afs_operation *op)
 	bp = xdr_encode_YFSFid(bp, &vp->fid);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1736,6 +1756,7 @@ void yfs_fs_inline_bulk_status(struct afs_operation *op)
 		bp = xdr_encode_YFSFid(bp, &op->more_files[i].fid);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1898,6 +1919,7 @@ void yfs_fs_fetch_opaque_acl(struct afs_operation *op)
 	bp = xdr_encode_YFSFid(bp, &vp->fid);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_KERNEL);
 }
@@ -1948,6 +1970,7 @@ void yfs_fs_store_opaque_acl2(struct afs_operation *op)
 	bp += size / sizeof(__be32);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_KERNEL);
 }
diff --git a/fs/aio.c b/fs/aio.c
index f8589caef9c1..bb2ff48991f3 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -239,7 +239,6 @@ static struct ctl_table aio_sysctls[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_doulongvec_minmax,
 	},
-	{}
 };
 
 static void __init aio_sysctl_init(void)
@@ -266,7 +265,7 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 		return ERR_CAST(inode);
 
 	inode->i_mapping->a_ops = &aio_ctx_aops;
-	inode->i_mapping->private_data = ctx;
+	inode->i_mapping->i_private_data = ctx;
 	inode->i_size = PAGE_SIZE * nr_pages;
 
 	file = alloc_file_pseudo(inode, aio_mnt, "[aio]",
@@ -316,10 +315,10 @@ static void put_aio_ring_file(struct kioctx *ctx)
 
 		/* Prevent further access to the kioctx from migratepages */
 		i_mapping = aio_ring_file->f_mapping;
-		spin_lock(&i_mapping->private_lock);
-		i_mapping->private_data = NULL;
+		spin_lock(&i_mapping->i_private_lock);
+		i_mapping->i_private_data = NULL;
 		ctx->aio_ring_file = NULL;
-		spin_unlock(&i_mapping->private_lock);
+		spin_unlock(&i_mapping->i_private_lock);
 
 		fput(aio_ring_file);
 	}
@@ -422,9 +421,9 @@ static int aio_migrate_folio(struct address_space *mapping, struct folio *dst,
 
 	rc = 0;
 
-	/* mapping->private_lock here protects against the kioctx teardown.  */
-	spin_lock(&mapping->private_lock);
-	ctx = mapping->private_data;
+	/* mapping->i_private_lock here protects against the kioctx teardown.  */
+	spin_lock(&mapping->i_private_lock);
+	ctx = mapping->i_private_data;
 	if (!ctx) {
 		rc = -EINVAL;
 		goto out;
@@ -476,7 +475,7 @@ static int aio_migrate_folio(struct address_space *mapping, struct folio *dst,
 out_unlock:
 	mutex_unlock(&ctx->ring_lock);
 out:
-	spin_unlock(&mapping->private_lock);
+	spin_unlock(&mapping->i_private_lock);
 	return rc;
 }
 #else
@@ -1106,6 +1105,11 @@ static inline void iocb_destroy(struct aio_kiocb *iocb)
 	kmem_cache_free(kiocb_cachep, iocb);
 }
 
+struct aio_waiter {
+	struct wait_queue_entry	w;
+	size_t			min_nr;
+};
+
 /* aio_complete
  *	Called when the io request on the given iocb is complete.
  */
@@ -1114,7 +1118,7 @@ static void aio_complete(struct aio_kiocb *iocb)
 	struct kioctx	*ctx = iocb->ki_ctx;
 	struct aio_ring	*ring;
 	struct io_event	*ev_page, *event;
-	unsigned tail, pos, head;
+	unsigned tail, pos, head, avail;
 	unsigned long	flags;
 
 	/*
@@ -1156,6 +1160,10 @@ static void aio_complete(struct aio_kiocb *iocb)
 	ctx->completed_events++;
 	if (ctx->completed_events > 1)
 		refill_reqs_available(ctx, head, tail);
+
+	avail = tail > head
+		? tail - head
+		: tail + ctx->nr_events - head;
 	spin_unlock_irqrestore(&ctx->completion_lock, flags);
 
 	pr_debug("added to ring %p at [%u]\n", iocb, tail);
@@ -1166,7 +1174,7 @@ static void aio_complete(struct aio_kiocb *iocb)
 	 * from IRQ context.
 	 */
 	if (iocb->ki_eventfd)
-		eventfd_signal(iocb->ki_eventfd, 1);
+		eventfd_signal(iocb->ki_eventfd);
 
 	/*
 	 * We have to order our ring_info tail store above and test
@@ -1176,8 +1184,18 @@ static void aio_complete(struct aio_kiocb *iocb)
 	 */
 	smp_mb();
 
-	if (waitqueue_active(&ctx->wait))
-		wake_up(&ctx->wait);
+	if (waitqueue_active(&ctx->wait)) {
+		struct aio_waiter *curr, *next;
+		unsigned long flags;
+
+		spin_lock_irqsave(&ctx->wait.lock, flags);
+		list_for_each_entry_safe(curr, next, &ctx->wait.head, w.entry)
+			if (avail >= curr->min_nr) {
+				list_del_init_careful(&curr->w.entry);
+				wake_up_process(curr->w.private);
+			}
+		spin_unlock_irqrestore(&ctx->wait.lock, flags);
+	}
 }
 
 static inline void iocb_put(struct aio_kiocb *iocb)
@@ -1290,7 +1308,9 @@ static long read_events(struct kioctx *ctx, long min_nr, long nr,
 			struct io_event __user *event,
 			ktime_t until)
 {
-	long ret = 0;
+	struct hrtimer_sleeper	t;
+	struct aio_waiter	w;
+	long ret = 0, ret2 = 0;
 
 	/*
 	 * Note that aio_read_events() is being called as the conditional - i.e.
@@ -1306,12 +1326,38 @@ static long read_events(struct kioctx *ctx, long min_nr, long nr,
 	 * the ringbuffer empty. So in practice we should be ok, but it's
 	 * something to be aware of when touching this code.
 	 */
-	if (until == 0)
-		aio_read_events(ctx, min_nr, nr, event, &ret);
-	else
-		wait_event_interruptible_hrtimeout(ctx->wait,
-				aio_read_events(ctx, min_nr, nr, event, &ret),
-				until);
+	aio_read_events(ctx, min_nr, nr, event, &ret);
+	if (until == 0 || ret < 0 || ret >= min_nr)
+		return ret;
+
+	hrtimer_init_sleeper_on_stack(&t, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	if (until != KTIME_MAX) {
+		hrtimer_set_expires_range_ns(&t.timer, until, current->timer_slack_ns);
+		hrtimer_sleeper_start_expires(&t, HRTIMER_MODE_REL);
+	}
+
+	init_wait(&w.w);
+
+	while (1) {
+		unsigned long nr_got = ret;
+
+		w.min_nr = min_nr - ret;
+
+		ret2 = prepare_to_wait_event(&ctx->wait, &w.w, TASK_INTERRUPTIBLE);
+		if (!ret2 && !t.task)
+			ret2 = -ETIME;
+
+		if (aio_read_events(ctx, min_nr, nr, event, &ret) || ret2)
+			break;
+
+		if (nr_got == ret)
+			schedule();
+	}
+
+	finish_wait(&ctx->wait, &w.w);
+	hrtimer_cancel(&t.timer);
+	destroy_hrtimer_on_stack(&t.timer);
+
 	return ret;
 }
 
@@ -1498,7 +1544,7 @@ static ssize_t aio_setup_rw(int rw, const struct iocb *iocb,
 	size_t len = iocb->aio_nbytes;
 
 	if (!vectored) {
-		ssize_t ret = import_single_range(rw, buf, len, *iovec, iter);
+		ssize_t ret = import_ubuf(rw, buf, len, iter);
 		*iovec = NULL;
 		return ret;
 	}
diff --git a/fs/attr.c b/fs/attr.c
index bdf5deb06ea9..5a13f0c8495f 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -157,7 +157,7 @@ static bool chgrp_ok(struct mnt_idmap *idmap,
  * the vfsmount must be passed through @idmap. This function will then
  * take care to map the inode according to @idmap before checking
  * permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs @nop_mnt_idmap.
+ * performed on the raw inode simply pass @nop_mnt_idmap.
  *
  * Should be called as the first thing in ->setattr implementations,
  * possibly after taking additional locks.
diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c
index a5083d447a62..1f5db6863663 100644
--- a/fs/autofs/inode.c
+++ b/fs/autofs/inode.c
@@ -309,9 +309,7 @@ static int autofs_fill_super(struct super_block *s, struct fs_context *fc)
 	struct autofs_fs_context *ctx = fc->fs_private;
 	struct autofs_sb_info *sbi = s->s_fs_info;
 	struct inode *root_inode;
-	struct dentry *root;
 	struct autofs_info *ino;
-	int ret = -ENOMEM;
 
 	pr_debug("starting up, sbi = %p\n", sbi);
 
@@ -328,56 +326,44 @@ static int autofs_fill_super(struct super_block *s, struct fs_context *fc)
 	 */
 	ino = autofs_new_ino(sbi);
 	if (!ino)
-		goto fail;
+		return -ENOMEM;
 
 	root_inode = autofs_get_inode(s, S_IFDIR | 0755);
+	if (!root_inode)
+		return -ENOMEM;
+
 	root_inode->i_uid = ctx->uid;
 	root_inode->i_gid = ctx->gid;
+	root_inode->i_fop = &autofs_root_operations;
+	root_inode->i_op = &autofs_dir_inode_operations;
 
-	root = d_make_root(root_inode);
-	if (!root)
-		goto fail_ino;
-
-	root->d_fsdata = ino;
+	s->s_root = d_make_root(root_inode);
+	if (unlikely(!s->s_root)) {
+		autofs_free_ino(ino);
+		return -ENOMEM;
+	}
+	s->s_root->d_fsdata = ino;
 
 	if (ctx->pgrp_set) {
 		sbi->oz_pgrp = find_get_pid(ctx->pgrp);
-		if (!sbi->oz_pgrp) {
-			ret = invalf(fc, "Could not find process group %d",
-				     ctx->pgrp);
-			goto fail_dput;
-		}
-	} else {
+		if (!sbi->oz_pgrp)
+			return invalf(fc, "Could not find process group %d",
+				      ctx->pgrp);
+	} else
 		sbi->oz_pgrp = get_task_pid(current, PIDTYPE_PGID);
-	}
 
 	if (autofs_type_trigger(sbi->type))
-		__managed_dentry_set_managed(root);
-
-	root_inode->i_fop = &autofs_root_operations;
-	root_inode->i_op = &autofs_dir_inode_operations;
+		/* s->s_root won't be contended so there's little to
+		 * be gained by not taking the d_lock when setting
+		 * d_flags, even when a lot mounts are being done.
+		 */
+		managed_dentry_set_managed(s->s_root);
 
 	pr_debug("pipe fd = %d, pgrp = %u\n",
 		 sbi->pipefd, pid_nr(sbi->oz_pgrp));
 
 	sbi->flags &= ~AUTOFS_SBI_CATATONIC;
-
-	/*
-	 * Success! Install the root dentry now to indicate completion.
-	 */
-	s->s_root = root;
 	return 0;
-
-	/*
-	 * Failure ... clean up.
-	 */
-fail_dput:
-	dput(root);
-	goto fail;
-fail_ino:
-	autofs_free_ino(ino);
-fail:
-	return ret;
 }
 
 /*
diff --git a/fs/backing-file.c b/fs/backing-file.c
new file mode 100644
index 000000000000..a681f38d84d8
--- /dev/null
+++ b/fs/backing-file.c
@@ -0,0 +1,336 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Common helpers for stackable filesystems and backing files.
+ *
+ * Forked from fs/overlayfs/file.c.
+ *
+ * Copyright (C) 2017 Red Hat, Inc.
+ * Copyright (C) 2023 CTERA Networks.
+ */
+
+#include <linux/fs.h>
+#include <linux/backing-file.h>
+#include <linux/splice.h>
+#include <linux/mm.h>
+
+#include "internal.h"
+
+/**
+ * backing_file_open - open a backing file for kernel internal use
+ * @user_path:	path that the user reuqested to open
+ * @flags:	open flags
+ * @real_path:	path of the backing file
+ * @cred:	credentials for open
+ *
+ * Open a backing file for a stackable filesystem (e.g., overlayfs).
+ * @user_path may be on the stackable filesystem and @real_path on the
+ * underlying filesystem.  In this case, we want to be able to return the
+ * @user_path of the stackable filesystem. This is done by embedding the
+ * returned file into a container structure that also stores the stacked
+ * file's path, which can be retrieved using backing_file_user_path().
+ */
+struct file *backing_file_open(const struct path *user_path, int flags,
+			       const struct path *real_path,
+			       const struct cred *cred)
+{
+	struct file *f;
+	int error;
+
+	f = alloc_empty_backing_file(flags, cred);
+	if (IS_ERR(f))
+		return f;
+
+	path_get(user_path);
+	*backing_file_user_path(f) = *user_path;
+	error = vfs_open(real_path, f);
+	if (error) {
+		fput(f);
+		f = ERR_PTR(error);
+	}
+
+	return f;
+}
+EXPORT_SYMBOL_GPL(backing_file_open);
+
+struct backing_aio {
+	struct kiocb iocb;
+	refcount_t ref;
+	struct kiocb *orig_iocb;
+	/* used for aio completion */
+	void (*end_write)(struct file *);
+	struct work_struct work;
+	long res;
+};
+
+static struct kmem_cache *backing_aio_cachep;
+
+#define BACKING_IOCB_MASK \
+	(IOCB_NOWAIT | IOCB_HIPRI | IOCB_DSYNC | IOCB_SYNC | IOCB_APPEND)
+
+static rwf_t iocb_to_rw_flags(int flags)
+{
+	return (__force rwf_t)(flags & BACKING_IOCB_MASK);
+}
+
+static void backing_aio_put(struct backing_aio *aio)
+{
+	if (refcount_dec_and_test(&aio->ref)) {
+		fput(aio->iocb.ki_filp);
+		kmem_cache_free(backing_aio_cachep, aio);
+	}
+}
+
+static void backing_aio_cleanup(struct backing_aio *aio, long res)
+{
+	struct kiocb *iocb = &aio->iocb;
+	struct kiocb *orig_iocb = aio->orig_iocb;
+
+	if (aio->end_write)
+		aio->end_write(orig_iocb->ki_filp);
+
+	orig_iocb->ki_pos = iocb->ki_pos;
+	backing_aio_put(aio);
+}
+
+static void backing_aio_rw_complete(struct kiocb *iocb, long res)
+{
+	struct backing_aio *aio = container_of(iocb, struct backing_aio, iocb);
+	struct kiocb *orig_iocb = aio->orig_iocb;
+
+	if (iocb->ki_flags & IOCB_WRITE)
+		kiocb_end_write(iocb);
+
+	backing_aio_cleanup(aio, res);
+	orig_iocb->ki_complete(orig_iocb, res);
+}
+
+static void backing_aio_complete_work(struct work_struct *work)
+{
+	struct backing_aio *aio = container_of(work, struct backing_aio, work);
+
+	backing_aio_rw_complete(&aio->iocb, aio->res);
+}
+
+static void backing_aio_queue_completion(struct kiocb *iocb, long res)
+{
+	struct backing_aio *aio = container_of(iocb, struct backing_aio, iocb);
+
+	/*
+	 * Punt to a work queue to serialize updates of mtime/size.
+	 */
+	aio->res = res;
+	INIT_WORK(&aio->work, backing_aio_complete_work);
+	queue_work(file_inode(aio->orig_iocb->ki_filp)->i_sb->s_dio_done_wq,
+		   &aio->work);
+}
+
+static int backing_aio_init_wq(struct kiocb *iocb)
+{
+	struct super_block *sb = file_inode(iocb->ki_filp)->i_sb;
+
+	if (sb->s_dio_done_wq)
+		return 0;
+
+	return sb_init_dio_done_wq(sb);
+}
+
+
+ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter,
+			       struct kiocb *iocb, int flags,
+			       struct backing_file_ctx *ctx)
+{
+	struct backing_aio *aio = NULL;
+	const struct cred *old_cred;
+	ssize_t ret;
+
+	if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING)))
+		return -EIO;
+
+	if (!iov_iter_count(iter))
+		return 0;
+
+	if (iocb->ki_flags & IOCB_DIRECT &&
+	    !(file->f_mode & FMODE_CAN_ODIRECT))
+		return -EINVAL;
+
+	old_cred = override_creds(ctx->cred);
+	if (is_sync_kiocb(iocb)) {
+		rwf_t rwf = iocb_to_rw_flags(flags);
+
+		ret = vfs_iter_read(file, iter, &iocb->ki_pos, rwf);
+	} else {
+		ret = -ENOMEM;
+		aio = kmem_cache_zalloc(backing_aio_cachep, GFP_KERNEL);
+		if (!aio)
+			goto out;
+
+		aio->orig_iocb = iocb;
+		kiocb_clone(&aio->iocb, iocb, get_file(file));
+		aio->iocb.ki_complete = backing_aio_rw_complete;
+		refcount_set(&aio->ref, 2);
+		ret = vfs_iocb_iter_read(file, &aio->iocb, iter);
+		backing_aio_put(aio);
+		if (ret != -EIOCBQUEUED)
+			backing_aio_cleanup(aio, ret);
+	}
+out:
+	revert_creds(old_cred);
+
+	if (ctx->accessed)
+		ctx->accessed(ctx->user_file);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(backing_file_read_iter);
+
+ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter,
+				struct kiocb *iocb, int flags,
+				struct backing_file_ctx *ctx)
+{
+	const struct cred *old_cred;
+	ssize_t ret;
+
+	if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING)))
+		return -EIO;
+
+	if (!iov_iter_count(iter))
+		return 0;
+
+	ret = file_remove_privs(ctx->user_file);
+	if (ret)
+		return ret;
+
+	if (iocb->ki_flags & IOCB_DIRECT &&
+	    !(file->f_mode & FMODE_CAN_ODIRECT))
+		return -EINVAL;
+
+	/*
+	 * Stacked filesystems don't support deferred completions, don't copy
+	 * this property in case it is set by the issuer.
+	 */
+	flags &= ~IOCB_DIO_CALLER_COMP;
+
+	old_cred = override_creds(ctx->cred);
+	if (is_sync_kiocb(iocb)) {
+		rwf_t rwf = iocb_to_rw_flags(flags);
+
+		ret = vfs_iter_write(file, iter, &iocb->ki_pos, rwf);
+		if (ctx->end_write)
+			ctx->end_write(ctx->user_file);
+	} else {
+		struct backing_aio *aio;
+
+		ret = backing_aio_init_wq(iocb);
+		if (ret)
+			goto out;
+
+		ret = -ENOMEM;
+		aio = kmem_cache_zalloc(backing_aio_cachep, GFP_KERNEL);
+		if (!aio)
+			goto out;
+
+		aio->orig_iocb = iocb;
+		aio->end_write = ctx->end_write;
+		kiocb_clone(&aio->iocb, iocb, get_file(file));
+		aio->iocb.ki_flags = flags;
+		aio->iocb.ki_complete = backing_aio_queue_completion;
+		refcount_set(&aio->ref, 2);
+		ret = vfs_iocb_iter_write(file, &aio->iocb, iter);
+		backing_aio_put(aio);
+		if (ret != -EIOCBQUEUED)
+			backing_aio_cleanup(aio, ret);
+	}
+out:
+	revert_creds(old_cred);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(backing_file_write_iter);
+
+ssize_t backing_file_splice_read(struct file *in, loff_t *ppos,
+				 struct pipe_inode_info *pipe, size_t len,
+				 unsigned int flags,
+				 struct backing_file_ctx *ctx)
+{
+	const struct cred *old_cred;
+	ssize_t ret;
+
+	if (WARN_ON_ONCE(!(in->f_mode & FMODE_BACKING)))
+		return -EIO;
+
+	old_cred = override_creds(ctx->cred);
+	ret = vfs_splice_read(in, ppos, pipe, len, flags);
+	revert_creds(old_cred);
+
+	if (ctx->accessed)
+		ctx->accessed(ctx->user_file);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(backing_file_splice_read);
+
+ssize_t backing_file_splice_write(struct pipe_inode_info *pipe,
+				  struct file *out, loff_t *ppos, size_t len,
+				  unsigned int flags,
+				  struct backing_file_ctx *ctx)
+{
+	const struct cred *old_cred;
+	ssize_t ret;
+
+	if (WARN_ON_ONCE(!(out->f_mode & FMODE_BACKING)))
+		return -EIO;
+
+	ret = file_remove_privs(ctx->user_file);
+	if (ret)
+		return ret;
+
+	old_cred = override_creds(ctx->cred);
+	file_start_write(out);
+	ret = iter_file_splice_write(pipe, out, ppos, len, flags);
+	file_end_write(out);
+	revert_creds(old_cred);
+
+	if (ctx->end_write)
+		ctx->end_write(ctx->user_file);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(backing_file_splice_write);
+
+int backing_file_mmap(struct file *file, struct vm_area_struct *vma,
+		      struct backing_file_ctx *ctx)
+{
+	const struct cred *old_cred;
+	int ret;
+
+	if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING)) ||
+	    WARN_ON_ONCE(ctx->user_file != vma->vm_file))
+		return -EIO;
+
+	if (!file->f_op->mmap)
+		return -ENODEV;
+
+	vma_set_file(vma, file);
+
+	old_cred = override_creds(ctx->cred);
+	ret = call_mmap(vma->vm_file, vma);
+	revert_creds(old_cred);
+
+	if (ctx->accessed)
+		ctx->accessed(ctx->user_file);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(backing_file_mmap);
+
+static int __init backing_aio_init(void)
+{
+	backing_aio_cachep = kmem_cache_create("backing_aio",
+					       sizeof(struct backing_aio),
+					       0, SLAB_HWCACHE_ALIGN, NULL);
+	if (!backing_aio_cachep)
+		return -ENOMEM;
+
+	return 0;
+}
+fs_initcall(backing_aio_init);
diff --git a/fs/bcachefs/Kconfig b/fs/bcachefs/Kconfig
index c08c2c7d6fbb..5cdfef3b551a 100644
--- a/fs/bcachefs/Kconfig
+++ b/fs/bcachefs/Kconfig
@@ -33,19 +33,23 @@ config BCACHEFS_QUOTA
 	depends on BCACHEFS_FS
 	select QUOTACTL
 
+config BCACHEFS_ERASURE_CODING
+	bool "bcachefs erasure coding (RAID5/6) support (EXPERIMENTAL)"
+	depends on BCACHEFS_FS
+	select QUOTACTL
+	help
+	This enables the "erasure_code" filesysystem and inode option, which
+	organizes data into reed-solomon stripes instead of ordinary
+	replication.
+
+	WARNING: this feature is still undergoing on disk format changes, and
+	should only be enabled for testing purposes.
+
 config BCACHEFS_POSIX_ACL
 	bool "bcachefs POSIX ACL support"
 	depends on BCACHEFS_FS
 	select FS_POSIX_ACL
 
-config BCACHEFS_DEBUG_TRANSACTIONS
-	bool "bcachefs runtime info"
-	depends on BCACHEFS_FS
-	help
-	This makes the list of running btree transactions available in debugfs.
-
-	This is a highly useful debugging feature but does add a small amount of overhead.
-
 config BCACHEFS_DEBUG
 	bool "bcachefs debugging"
 	depends on BCACHEFS_FS
@@ -73,6 +77,16 @@ config BCACHEFS_NO_LATENCY_ACCT
 	help
 	This disables device latency tracking and time stats, only for performance testing
 
+config BCACHEFS_SIX_OPTIMISTIC_SPIN
+	bool "Optimistic spinning for six locks"
+	depends on BCACHEFS_FS
+	depends on SMP
+	default y
+	help
+	Instead of immediately sleeping when attempting to take a six lock that
+	is held by another thread, spin for a short while, as long as the
+	thread owning the lock is running.
+
 config MEAN_AND_VARIANCE_UNIT_TEST
 	tristate "mean_and_variance unit tests" if !KUNIT_ALL_TESTS
 	depends on KUNIT
diff --git a/fs/bcachefs/Makefile b/fs/bcachefs/Makefile
index 45b64f89258c..7423a3557c68 100644
--- a/fs/bcachefs/Makefile
+++ b/fs/bcachefs/Makefile
@@ -28,6 +28,7 @@ bcachefs-y		:=	\
 	clock.o			\
 	compress.o		\
 	counters.o		\
+	darray.o		\
 	debug.o			\
 	dirent.o		\
 	disk_groups.o		\
@@ -70,6 +71,7 @@ bcachefs-y		:=	\
 	reflink.o		\
 	replicas.o		\
 	sb-clean.o		\
+	sb-downgrade.o		\
 	sb-errors.o		\
 	sb-members.o		\
 	siphash.o		\
@@ -80,6 +82,7 @@ bcachefs-y		:=	\
 	super-io.o		\
 	sysfs.o			\
 	tests.o			\
+	thread_with_file.o	\
 	trace.o			\
 	two_state_shared_lock.o	\
 	util.o			\
diff --git a/fs/bcachefs/acl.c b/fs/bcachefs/acl.c
index f3809897f00a..3640f417cce1 100644
--- a/fs/bcachefs/acl.c
+++ b/fs/bcachefs/acl.c
@@ -366,7 +366,8 @@ retry:
 	bch2_trans_begin(trans);
 	acl = _acl;
 
-	ret = bch2_inode_peek(trans, &inode_iter, &inode_u, inode_inum(inode),
+	ret   = bch2_subvol_is_ro_trans(trans, inode->ei_subvol) ?:
+		bch2_inode_peek(trans, &inode_iter, &inode_u, inode_inum(inode),
 			      BTREE_ITER_INTENT);
 	if (ret)
 		goto btree_err;
diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c
index 1fec0e67891f..a09b9d00226a 100644
--- a/fs/bcachefs/alloc_background.c
+++ b/fs/bcachefs/alloc_background.c
@@ -261,10 +261,8 @@ int bch2_alloc_v4_invalid(struct bch_fs *c, struct bkey_s_c k,
 	case BCH_DATA_free:
 	case BCH_DATA_need_gc_gens:
 	case BCH_DATA_need_discard:
-		bkey_fsck_err_on(a.v->dirty_sectors ||
-				 a.v->cached_sectors ||
-				 a.v->stripe, c, err,
-				 alloc_key_empty_but_have_data,
+		bkey_fsck_err_on(bch2_bucket_sectors(*a.v) || a.v->stripe,
+				 c, err, alloc_key_empty_but_have_data,
 				 "empty data type free but have data");
 		break;
 	case BCH_DATA_sb:
@@ -272,22 +270,21 @@ int bch2_alloc_v4_invalid(struct bch_fs *c, struct bkey_s_c k,
 	case BCH_DATA_btree:
 	case BCH_DATA_user:
 	case BCH_DATA_parity:
-		bkey_fsck_err_on(!a.v->dirty_sectors, c, err,
-				 alloc_key_dirty_sectors_0,
+		bkey_fsck_err_on(!bch2_bucket_sectors_dirty(*a.v),
+				 c, err, alloc_key_dirty_sectors_0,
 				 "data_type %s but dirty_sectors==0",
 				 bch2_data_types[a.v->data_type]);
 		break;
 	case BCH_DATA_cached:
 		bkey_fsck_err_on(!a.v->cached_sectors ||
-				 a.v->dirty_sectors ||
-				 a.v->stripe, c, err,
-				 alloc_key_cached_inconsistency,
+				 bch2_bucket_sectors_dirty(*a.v) ||
+				 a.v->stripe,
+				 c, err, alloc_key_cached_inconsistency,
 				 "data type inconsistency");
 
 		bkey_fsck_err_on(!a.v->io_time[READ] &&
 				 c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_to_lru_refs,
-				 c, err,
-				 alloc_key_cached_but_read_time_zero,
+				 c, err, alloc_key_cached_but_read_time_zero,
 				 "cached bucket with read_time == 0");
 		break;
 	case BCH_DATA_stripe:
@@ -537,18 +534,12 @@ void bch2_bucket_gens_to_text(struct printbuf *out, struct bch_fs *c, struct bke
 int bch2_bucket_gens_init(struct bch_fs *c)
 {
 	struct btree_trans *trans = bch2_trans_get(c);
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	struct bch_alloc_v4 a;
 	struct bkey_i_bucket_gens g;
 	bool have_bucket_gens_key = false;
-	unsigned offset;
-	struct bpos pos;
-	u8 gen;
 	int ret;
 
-	for_each_btree_key(trans, iter, BTREE_ID_alloc, POS_MIN,
-			   BTREE_ITER_PREFETCH, k, ret) {
+	ret = for_each_btree_key(trans, iter, BTREE_ID_alloc, POS_MIN,
+				 BTREE_ITER_PREFETCH, k, ({
 		/*
 		 * Not a fsck error because this is checked/repaired by
 		 * bch2_check_alloc_key() which runs later:
@@ -556,13 +547,14 @@ int bch2_bucket_gens_init(struct bch_fs *c)
 		if (!bch2_dev_bucket_exists(c, k.k->p))
 			continue;
 
-		gen = bch2_alloc_to_v4(k, &a)->gen;
-		pos = alloc_gens_pos(iter.pos, &offset);
+		struct bch_alloc_v4 a;
+		u8 gen = bch2_alloc_to_v4(k, &a)->gen;
+		unsigned offset;
+		struct bpos pos = alloc_gens_pos(iter.pos, &offset);
 
 		if (have_bucket_gens_key && bkey_cmp(iter.pos, pos)) {
 			ret = commit_do(trans, NULL, NULL,
-					BTREE_INSERT_NOFAIL|
-					BTREE_INSERT_LAZY_RW,
+					BCH_TRANS_COMMIT_no_enospc,
 				bch2_btree_insert_trans(trans, BTREE_ID_bucket_gens, &g.k_i, 0));
 			if (ret)
 				break;
@@ -576,45 +568,37 @@ int bch2_bucket_gens_init(struct bch_fs *c)
 		}
 
 		g.v.gens[offset] = gen;
-	}
-	bch2_trans_iter_exit(trans, &iter);
+		0;
+	}));
 
 	if (have_bucket_gens_key && !ret)
 		ret = commit_do(trans, NULL, NULL,
-				BTREE_INSERT_NOFAIL|
-				BTREE_INSERT_LAZY_RW,
+				BCH_TRANS_COMMIT_no_enospc,
 			bch2_btree_insert_trans(trans, BTREE_ID_bucket_gens, &g.k_i, 0));
 
 	bch2_trans_put(trans);
 
-	if (ret)
-		bch_err_fn(c, ret);
+	bch_err_fn(c, ret);
 	return ret;
 }
 
 int bch2_alloc_read(struct bch_fs *c)
 {
 	struct btree_trans *trans = bch2_trans_get(c);
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	struct bch_dev *ca;
 	int ret;
 
 	down_read(&c->gc_lock);
 
 	if (c->sb.version_upgrade_complete >= bcachefs_metadata_version_bucket_gens) {
-		const struct bch_bucket_gens *g;
-		u64 b;
-
-		for_each_btree_key(trans, iter, BTREE_ID_bucket_gens, POS_MIN,
-				   BTREE_ITER_PREFETCH, k, ret) {
+		ret = for_each_btree_key(trans, iter, BTREE_ID_bucket_gens, POS_MIN,
+					 BTREE_ITER_PREFETCH, k, ({
 			u64 start = bucket_gens_pos_to_alloc(k.k->p, 0).offset;
 			u64 end = bucket_gens_pos_to_alloc(bpos_nosnap_successor(k.k->p), 0).offset;
 
 			if (k.k->type != KEY_TYPE_bucket_gens)
 				continue;
 
-			g = bkey_s_c_to_bucket_gens(k).v;
+			const struct bch_bucket_gens *g = bkey_s_c_to_bucket_gens(k).v;
 
 			/*
 			 * Not a fsck error because this is checked/repaired by
@@ -623,19 +607,17 @@ int bch2_alloc_read(struct bch_fs *c)
 			if (!bch2_dev_exists2(c, k.k->p.inode))
 				continue;
 
-			ca = bch_dev_bkey_exists(c, k.k->p.inode);
+			struct bch_dev *ca = bch_dev_bkey_exists(c, k.k->p.inode);
 
-			for (b = max_t(u64, ca->mi.first_bucket, start);
+			for (u64 b = max_t(u64, ca->mi.first_bucket, start);
 			     b < min_t(u64, ca->mi.nbuckets, end);
 			     b++)
 				*bucket_gen(ca, b) = g->gens[b & KEY_TYPE_BUCKET_GENS_MASK];
-		}
-		bch2_trans_iter_exit(trans, &iter);
+			0;
+		}));
 	} else {
-		struct bch_alloc_v4 a;
-
-		for_each_btree_key(trans, iter, BTREE_ID_alloc, POS_MIN,
-				   BTREE_ITER_PREFETCH, k, ret) {
+		ret = for_each_btree_key(trans, iter, BTREE_ID_alloc, POS_MIN,
+					 BTREE_ITER_PREFETCH, k, ({
 			/*
 			 * Not a fsck error because this is checked/repaired by
 			 * bch2_check_alloc_key() which runs later:
@@ -643,19 +625,18 @@ int bch2_alloc_read(struct bch_fs *c)
 			if (!bch2_dev_bucket_exists(c, k.k->p))
 				continue;
 
-			ca = bch_dev_bkey_exists(c, k.k->p.inode);
+			struct bch_dev *ca = bch_dev_bkey_exists(c, k.k->p.inode);
 
+			struct bch_alloc_v4 a;
 			*bucket_gen(ca, k.k->p.offset) = bch2_alloc_to_v4(k, &a)->gen;
-		}
-		bch2_trans_iter_exit(trans, &iter);
+			0;
+		}));
 	}
 
 	bch2_trans_put(trans);
 	up_read(&c->gc_lock);
 
-	if (ret)
-		bch_err_fn(c, ret);
-
+	bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -768,83 +749,177 @@ static noinline int bch2_bucket_gen_update(struct btree_trans *trans,
 	return ret;
 }
 
-int bch2_trans_mark_alloc(struct btree_trans *trans,
-			  enum btree_id btree_id, unsigned level,
-			  struct bkey_s_c old, struct bkey_i *new,
-			  unsigned flags)
+int bch2_trigger_alloc(struct btree_trans *trans,
+		       enum btree_id btree, unsigned level,
+		       struct bkey_s_c old, struct bkey_s new,
+		       unsigned flags)
 {
 	struct bch_fs *c = trans->c;
-	struct bch_alloc_v4 old_a_convert, *new_a;
-	const struct bch_alloc_v4 *old_a;
-	u64 old_lru, new_lru;
 	int ret = 0;
 
-	/*
-	 * Deletion only happens in the device removal path, with
-	 * BTREE_TRIGGER_NORUN:
-	 */
-	BUG_ON(new->k.type != KEY_TYPE_alloc_v4);
+	if (bch2_trans_inconsistent_on(!bch2_dev_bucket_exists(c, new.k->p), trans,
+				       "alloc key for invalid device or bucket"))
+		return -EIO;
 
-	old_a = bch2_alloc_to_v4(old, &old_a_convert);
-	new_a = &bkey_i_to_alloc_v4(new)->v;
+	struct bch_dev *ca = bch_dev_bkey_exists(c, new.k->p.inode);
 
-	new_a->data_type = alloc_data_type(*new_a, new_a->data_type);
+	struct bch_alloc_v4 old_a_convert;
+	const struct bch_alloc_v4 *old_a = bch2_alloc_to_v4(old, &old_a_convert);
 
-	if (new_a->dirty_sectors > old_a->dirty_sectors ||
-	    new_a->cached_sectors > old_a->cached_sectors) {
-		new_a->io_time[READ] = max_t(u64, 1, atomic64_read(&c->io_clock[READ].now));
-		new_a->io_time[WRITE]= max_t(u64, 1, atomic64_read(&c->io_clock[WRITE].now));
-		SET_BCH_ALLOC_V4_NEED_INC_GEN(new_a, true);
-		SET_BCH_ALLOC_V4_NEED_DISCARD(new_a, true);
-	}
+	if (flags & BTREE_TRIGGER_TRANSACTIONAL) {
+		struct bch_alloc_v4 *new_a = bkey_s_to_alloc_v4(new).v;
 
-	if (data_type_is_empty(new_a->data_type) &&
-	    BCH_ALLOC_V4_NEED_INC_GEN(new_a) &&
-	    !bch2_bucket_is_open_safe(c, new->k.p.inode, new->k.p.offset)) {
-		new_a->gen++;
-		SET_BCH_ALLOC_V4_NEED_INC_GEN(new_a, false);
-	}
+		new_a->data_type = alloc_data_type(*new_a, new_a->data_type);
 
-	if (old_a->data_type != new_a->data_type ||
-	    (new_a->data_type == BCH_DATA_free &&
-	     alloc_freespace_genbits(*old_a) != alloc_freespace_genbits(*new_a))) {
-		ret =   bch2_bucket_do_index(trans, old, old_a, false) ?:
-			bch2_bucket_do_index(trans, bkey_i_to_s_c(new), new_a, true);
-		if (ret)
-			return ret;
-	}
+		if (bch2_bucket_sectors(*new_a) > bch2_bucket_sectors(*old_a)) {
+			new_a->io_time[READ] = max_t(u64, 1, atomic64_read(&c->io_clock[READ].now));
+			new_a->io_time[WRITE]= max_t(u64, 1, atomic64_read(&c->io_clock[WRITE].now));
+			SET_BCH_ALLOC_V4_NEED_INC_GEN(new_a, true);
+			SET_BCH_ALLOC_V4_NEED_DISCARD(new_a, true);
+		}
+
+		if (data_type_is_empty(new_a->data_type) &&
+		    BCH_ALLOC_V4_NEED_INC_GEN(new_a) &&
+		    !bch2_bucket_is_open_safe(c, new.k->p.inode, new.k->p.offset)) {
+			new_a->gen++;
+			SET_BCH_ALLOC_V4_NEED_INC_GEN(new_a, false);
+		}
 
-	if (new_a->data_type == BCH_DATA_cached &&
-	    !new_a->io_time[READ])
-		new_a->io_time[READ] = max_t(u64, 1, atomic64_read(&c->io_clock[READ].now));
+		if (old_a->data_type != new_a->data_type ||
+		    (new_a->data_type == BCH_DATA_free &&
+		     alloc_freespace_genbits(*old_a) != alloc_freespace_genbits(*new_a))) {
+			ret =   bch2_bucket_do_index(trans, old, old_a, false) ?:
+				bch2_bucket_do_index(trans, new.s_c, new_a, true);
+			if (ret)
+				return ret;
+		}
 
-	old_lru = alloc_lru_idx_read(*old_a);
-	new_lru = alloc_lru_idx_read(*new_a);
+		if (new_a->data_type == BCH_DATA_cached &&
+		    !new_a->io_time[READ])
+			new_a->io_time[READ] = max_t(u64, 1, atomic64_read(&c->io_clock[READ].now));
 
-	if (old_lru != new_lru) {
-		ret = bch2_lru_change(trans, new->k.p.inode,
-				      bucket_to_u64(new->k.p),
-				      old_lru, new_lru);
-		if (ret)
-			return ret;
+		u64 old_lru = alloc_lru_idx_read(*old_a);
+		u64 new_lru = alloc_lru_idx_read(*new_a);
+		if (old_lru != new_lru) {
+			ret = bch2_lru_change(trans, new.k->p.inode,
+					      bucket_to_u64(new.k->p),
+					      old_lru, new_lru);
+			if (ret)
+				return ret;
+		}
+
+		new_a->fragmentation_lru = alloc_lru_idx_fragmentation(*new_a,
+						bch_dev_bkey_exists(c, new.k->p.inode));
+		if (old_a->fragmentation_lru != new_a->fragmentation_lru) {
+			ret = bch2_lru_change(trans,
+					BCH_LRU_FRAGMENTATION_START,
+					bucket_to_u64(new.k->p),
+					old_a->fragmentation_lru, new_a->fragmentation_lru);
+			if (ret)
+				return ret;
+		}
+
+		if (old_a->gen != new_a->gen) {
+			ret = bch2_bucket_gen_update(trans, new.k->p, new_a->gen);
+			if (ret)
+				return ret;
+		}
+
+		/*
+		 * need to know if we're getting called from the invalidate path or
+		 * not:
+		 */
+
+		if ((flags & BTREE_TRIGGER_BUCKET_INVALIDATE) &&
+		    old_a->cached_sectors) {
+			ret = bch2_update_cached_sectors_list(trans, new.k->p.inode,
+							      -((s64) old_a->cached_sectors));
+			if (ret)
+				return ret;
+		}
 	}
 
-	new_a->fragmentation_lru = alloc_lru_idx_fragmentation(*new_a,
-					bch_dev_bkey_exists(c, new->k.p.inode));
+	if (!(flags & BTREE_TRIGGER_TRANSACTIONAL) && (flags & BTREE_TRIGGER_INSERT)) {
+		struct bch_alloc_v4 *new_a = bkey_s_to_alloc_v4(new).v;
+		u64 journal_seq = trans->journal_res.seq;
+		u64 bucket_journal_seq = new_a->journal_seq;
 
-	if (old_a->fragmentation_lru != new_a->fragmentation_lru) {
-		ret = bch2_lru_change(trans,
-				BCH_LRU_FRAGMENTATION_START,
-				bucket_to_u64(new->k.p),
-				old_a->fragmentation_lru, new_a->fragmentation_lru);
-		if (ret)
-			return ret;
+		if ((flags & BTREE_TRIGGER_INSERT) &&
+		    data_type_is_empty(old_a->data_type) !=
+		    data_type_is_empty(new_a->data_type) &&
+		    new.k->type == KEY_TYPE_alloc_v4) {
+			struct bch_alloc_v4 *v = bkey_s_to_alloc_v4(new).v;
+
+			/*
+			 * If the btree updates referring to a bucket weren't flushed
+			 * before the bucket became empty again, then the we don't have
+			 * to wait on a journal flush before we can reuse the bucket:
+			 */
+			v->journal_seq = bucket_journal_seq =
+				data_type_is_empty(new_a->data_type) &&
+				(journal_seq == v->journal_seq ||
+				 bch2_journal_noflush_seq(&c->journal, v->journal_seq))
+				? 0 : journal_seq;
+		}
+
+		if (!data_type_is_empty(old_a->data_type) &&
+		    data_type_is_empty(new_a->data_type) &&
+		    bucket_journal_seq) {
+			ret = bch2_set_bucket_needs_journal_commit(&c->buckets_waiting_for_journal,
+					c->journal.flushed_seq_ondisk,
+					new.k->p.inode, new.k->p.offset,
+					bucket_journal_seq);
+			if (ret) {
+				bch2_fs_fatal_error(c,
+					"error setting bucket_needs_journal_commit: %i", ret);
+				return ret;
+			}
+		}
+
+		percpu_down_read(&c->mark_lock);
+		if (new_a->gen != old_a->gen)
+			*bucket_gen(ca, new.k->p.offset) = new_a->gen;
+
+		bch2_dev_usage_update(c, ca, old_a, new_a, journal_seq, false);
+
+		if (new_a->data_type == BCH_DATA_free &&
+		    (!new_a->journal_seq || new_a->journal_seq < c->journal.flushed_seq_ondisk))
+			closure_wake_up(&c->freelist_wait);
+
+		if (new_a->data_type == BCH_DATA_need_discard &&
+		    (!bucket_journal_seq || bucket_journal_seq < c->journal.flushed_seq_ondisk))
+			bch2_do_discards(c);
+
+		if (old_a->data_type != BCH_DATA_cached &&
+		    new_a->data_type == BCH_DATA_cached &&
+		    should_invalidate_buckets(ca, bch2_dev_usage_read(ca)))
+			bch2_do_invalidates(c);
+
+		if (new_a->data_type == BCH_DATA_need_gc_gens)
+			bch2_do_gc_gens(c);
+		percpu_up_read(&c->mark_lock);
 	}
 
-	if (old_a->gen != new_a->gen) {
-		ret = bch2_bucket_gen_update(trans, new->k.p, new_a->gen);
-		if (ret)
-			return ret;
+	if ((flags & BTREE_TRIGGER_GC) &&
+	    (flags & BTREE_TRIGGER_BUCKET_INVALIDATE)) {
+		struct bch_alloc_v4 new_a_convert;
+		const struct bch_alloc_v4 *new_a = bch2_alloc_to_v4(new.s_c, &new_a_convert);
+
+		percpu_down_read(&c->mark_lock);
+		struct bucket *g = gc_bucket(ca, new.k->p.offset);
+
+		bucket_lock(g);
+
+		g->gen_valid		= 1;
+		g->gen			= new_a->gen;
+		g->data_type		= new_a->data_type;
+		g->stripe		= new_a->stripe;
+		g->stripe_redundancy	= new_a->stripe_redundancy;
+		g->dirty_sectors	= new_a->dirty_sectors;
+		g->cached_sectors	= new_a->cached_sectors;
+
+		bucket_unlock(g);
+		percpu_up_read(&c->mark_lock);
 	}
 
 	return 0;
@@ -869,8 +944,9 @@ static struct bkey_s_c bch2_get_key_or_hole(struct btree_iter *iter, struct bpos
 
 		bch2_trans_copy_iter(&iter2, iter);
 
-		if (!bpos_eq(iter->path->l[0].b->key.k.p, SPOS_MAX))
-			end = bkey_min(end, bpos_nosnap_successor(iter->path->l[0].b->key.k.p));
+		struct btree_path *path = btree_iter_path(iter->trans, iter);
+		if (!bpos_eq(path->l[0].b->key.k.p, SPOS_MAX))
+			end = bkey_min(end, bpos_nosnap_successor(path->l[0].b->key.k.p));
 
 		end = bkey_min(end, POS(iter->pos.inode, iter->pos.offset + U32_MAX - 1));
 
@@ -898,7 +974,6 @@ static struct bkey_s_c bch2_get_key_or_hole(struct btree_iter *iter, struct bpos
 static bool next_bucket(struct bch_fs *c, struct bpos *bucket)
 {
 	struct bch_dev *ca;
-	unsigned iter;
 
 	if (bch2_dev_bucket_exists(c, *bucket))
 		return true;
@@ -916,8 +991,7 @@ static bool next_bucket(struct bch_fs *c, struct bpos *bucket)
 	}
 
 	rcu_read_lock();
-	iter = bucket->inode;
-	ca = __bch2_next_dev(c, &iter, NULL);
+	ca = __bch2_next_dev_idx(c, bucket->inode, NULL);
 	if (ca)
 		*bucket = POS(ca->dev_idx, ca->mi.first_bucket);
 	rcu_read_unlock();
@@ -1158,9 +1232,6 @@ int bch2_check_alloc_hole_bucket_gens(struct btree_trans *trans,
 	unsigned i, gens_offset, gens_end_offset;
 	int ret;
 
-	if (c->sb.version < bcachefs_metadata_version_bucket_gens)
-		return 0;
-
 	bch2_btree_iter_set_pos(bucket_gens_iter, alloc_gens_pos(start, &gens_offset));
 
 	k = bch2_btree_iter_peek_slot(bucket_gens_iter);
@@ -1212,7 +1283,7 @@ fsck_err:
 	return ret;
 }
 
-static noinline_for_stack int __bch2_check_discard_freespace_key(struct btree_trans *trans,
+static noinline_for_stack int bch2_check_discard_freespace_key(struct btree_trans *trans,
 					      struct btree_iter *iter)
 {
 	struct bch_fs *c = trans->c;
@@ -1267,28 +1338,10 @@ delete:
 	ret =   bch2_btree_delete_extent_at(trans, iter,
 			iter->btree_id == BTREE_ID_freespace ? 1 : 0, 0) ?:
 		bch2_trans_commit(trans, NULL, NULL,
-			BTREE_INSERT_NOFAIL|BTREE_INSERT_LAZY_RW);
+			BCH_TRANS_COMMIT_no_enospc);
 	goto out;
 }
 
-static int bch2_check_discard_freespace_key(struct btree_trans *trans,
-					    struct btree_iter *iter,
-					    struct bpos end)
-{
-	if (!btree_id_is_extents(iter->btree_id)) {
-		return __bch2_check_discard_freespace_key(trans, iter);
-	} else {
-		int ret = 0;
-
-		while (!bkey_eq(iter->pos, end) &&
-		       !(ret = btree_trans_too_many_iters(trans) ?:
-			       __bch2_check_discard_freespace_key(trans, iter)))
-			bch2_btree_iter_set_pos(iter, bpos_nosnap_successor(iter->pos));
-
-		return ret;
-	}
-}
-
 /*
  * We've already checked that generation numbers in the bucket_gens btree are
  * valid for buckets that exist; this just checks for keys for nonexistent
@@ -1422,8 +1475,7 @@ int bch2_check_alloc_info(struct bch_fs *c)
 		}
 
 		ret = bch2_trans_commit(trans, NULL, NULL,
-					BTREE_INSERT_NOFAIL|
-					BTREE_INSERT_LAZY_RW);
+					BCH_TRANS_COMMIT_no_enospc);
 		if (ret)
 			goto bkey_err;
 
@@ -1442,23 +1494,50 @@ bkey_err:
 	if (ret < 0)
 		goto err;
 
-	ret = for_each_btree_key2(trans, iter,
+	ret = for_each_btree_key(trans, iter,
 			BTREE_ID_need_discard, POS_MIN,
 			BTREE_ITER_PREFETCH, k,
-		bch2_check_discard_freespace_key(trans, &iter, k.k->p)) ?:
-	      for_each_btree_key2(trans, iter,
-			BTREE_ID_freespace, POS_MIN,
-			BTREE_ITER_PREFETCH, k,
-		bch2_check_discard_freespace_key(trans, &iter, k.k->p)) ?:
-	      for_each_btree_key_commit(trans, iter,
+		bch2_check_discard_freespace_key(trans, &iter));
+	if (ret)
+		goto err;
+
+	bch2_trans_iter_init(trans, &iter, BTREE_ID_freespace, POS_MIN,
+			     BTREE_ITER_PREFETCH);
+	while (1) {
+		bch2_trans_begin(trans);
+		k = bch2_btree_iter_peek(&iter);
+		if (!k.k)
+			break;
+
+		ret = bkey_err(k) ?:
+			bch2_check_discard_freespace_key(trans, &iter);
+		if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) {
+			ret = 0;
+			continue;
+		}
+		if (ret) {
+			struct printbuf buf = PRINTBUF;
+			bch2_bkey_val_to_text(&buf, c, k);
+
+			bch_err(c, "while checking %s", buf.buf);
+			printbuf_exit(&buf);
+			break;
+		}
+
+		bch2_btree_iter_set_pos(&iter, bpos_nosnap_successor(iter.pos));
+	}
+	bch2_trans_iter_exit(trans, &iter);
+	if (ret)
+		goto err;
+
+	ret = for_each_btree_key_commit(trans, iter,
 			BTREE_ID_bucket_gens, POS_MIN,
 			BTREE_ITER_PREFETCH, k,
-			NULL, NULL, BTREE_INSERT_NOFAIL|BTREE_INSERT_LAZY_RW,
+			NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 		bch2_check_bucket_gens_key(trans, &iter, k));
 err:
 	bch2_trans_put(trans);
-	if (ret)
-		bch_err_fn(c, ret);
+	bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -1486,6 +1565,27 @@ static int bch2_check_alloc_to_lru_ref(struct btree_trans *trans,
 	if (a->data_type != BCH_DATA_cached)
 		return 0;
 
+	if (fsck_err_on(!a->io_time[READ], c,
+			alloc_key_cached_but_read_time_zero,
+			"cached bucket with read_time 0\n"
+			"  %s",
+		(printbuf_reset(&buf),
+		 bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf))) {
+		struct bkey_i_alloc_v4 *a_mut =
+			bch2_alloc_to_v4_mut(trans, alloc_k);
+		ret = PTR_ERR_OR_ZERO(a_mut);
+		if (ret)
+			goto err;
+
+		a_mut->v.io_time[READ] = atomic64_read(&c->io_clock[READ].now);
+		ret = bch2_trans_update(trans, alloc_iter,
+					&a_mut->k_i, BTREE_TRIGGER_NORUN);
+		if (ret)
+			goto err;
+
+		a = &a_mut->v;
+	}
+
 	lru_k = bch2_bkey_get_iter(trans, &lru_iter, BTREE_ID_lru,
 			     lru_pos(alloc_k.k->p.inode,
 				     bucket_to_u64(alloc_k.k->p),
@@ -1494,41 +1594,18 @@ static int bch2_check_alloc_to_lru_ref(struct btree_trans *trans,
 	if (ret)
 		return ret;
 
-	if (fsck_err_on(!a->io_time[READ], c,
-			alloc_key_cached_but_read_time_zero,
-			"cached bucket with read_time 0\n"
-			"  %s",
-		(printbuf_reset(&buf),
-		 bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf)) ||
-	    fsck_err_on(lru_k.k->type != KEY_TYPE_set, c,
+	if (fsck_err_on(lru_k.k->type != KEY_TYPE_set, c,
 			alloc_key_to_missing_lru_entry,
 			"missing lru entry\n"
 			"  %s",
 			(printbuf_reset(&buf),
 			 bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf))) {
-		u64 read_time = a->io_time[READ] ?:
-			atomic64_read(&c->io_clock[READ].now);
-
 		ret = bch2_lru_set(trans,
 				   alloc_k.k->p.inode,
 				   bucket_to_u64(alloc_k.k->p),
-				   read_time);
+				   a->io_time[READ]);
 		if (ret)
 			goto err;
-
-		if (a->io_time[READ] != read_time) {
-			struct bkey_i_alloc_v4 *a_mut =
-				bch2_alloc_to_v4_mut(trans, alloc_k);
-			ret = PTR_ERR_OR_ZERO(a_mut);
-			if (ret)
-				goto err;
-
-			a_mut->v.io_time[READ] = read_time;
-			ret = bch2_trans_update(trans, alloc_iter,
-						&a_mut->k_i, BTREE_TRIGGER_NORUN);
-			if (ret)
-				goto err;
-		}
 	}
 err:
 fsck_err:
@@ -1539,17 +1616,12 @@ fsck_err:
 
 int bch2_check_alloc_to_lru_refs(struct bch_fs *c)
 {
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	int ret = 0;
-
-	ret = bch2_trans_run(c,
+	int ret = bch2_trans_run(c,
 		for_each_btree_key_commit(trans, iter, BTREE_ID_alloc,
 				POS_MIN, BTREE_ITER_PREFETCH, k,
-				NULL, NULL, BTREE_INSERT_NOFAIL|BTREE_INSERT_LAZY_RW,
+				NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 			bch2_check_alloc_to_lru_ref(trans, &iter)));
-	if (ret)
-		bch_err_fn(c, ret);
+	bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -1655,11 +1727,11 @@ write:
 	ret =   bch2_trans_update(trans, &iter, &a->k_i, 0) ?:
 		bch2_trans_commit(trans, NULL, NULL,
 				  BCH_WATERMARK_btree|
-				  BTREE_INSERT_NOFAIL);
+				  BCH_TRANS_COMMIT_no_enospc);
 	if (ret)
 		goto out;
 
-	this_cpu_inc(c->counters[BCH_COUNTER_bucket_discard]);
+	count_event(c, bucket_discard);
 	(*discarded)++;
 out:
 	(*seen)++;
@@ -1672,8 +1744,6 @@ out:
 static void bch2_do_discards_work(struct work_struct *work)
 {
 	struct bch_fs *c = container_of(work, struct bch_fs, discard_work);
-	struct btree_iter iter;
-	struct bkey_s_c k;
 	u64 seen = 0, open = 0, need_journal_commit = 0, discarded = 0;
 	struct bpos discard_pos_done = POS_MAX;
 	int ret;
@@ -1684,8 +1754,8 @@ static void bch2_do_discards_work(struct work_struct *work)
 	 * successful commit:
 	 */
 	ret = bch2_trans_run(c,
-		for_each_btree_key2(trans, iter,
-				BTREE_ID_need_discard, POS_MIN, 0, k,
+		for_each_btree_key(trans, iter,
+				   BTREE_ID_need_discard, POS_MIN, 0, k,
 			bch2_discard_one_bucket(trans, &iter, &discard_pos_done,
 						&seen,
 						&open,
@@ -1760,7 +1830,7 @@ static int invalidate_one_bucket(struct btree_trans *trans,
 				BTREE_TRIGGER_BUCKET_INVALIDATE) ?:
 		bch2_trans_commit(trans, NULL, NULL,
 				  BCH_WATERMARK_btree|
-				  BTREE_INSERT_NOFAIL);
+				  BCH_TRANS_COMMIT_no_enospc);
 	if (ret)
 		goto out;
 
@@ -1795,22 +1865,18 @@ err:
 static void bch2_do_invalidates_work(struct work_struct *work)
 {
 	struct bch_fs *c = container_of(work, struct bch_fs, invalidate_work);
-	struct bch_dev *ca;
 	struct btree_trans *trans = bch2_trans_get(c);
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	unsigned i;
 	int ret = 0;
 
-	ret = bch2_btree_write_buffer_flush(trans);
+	ret = bch2_btree_write_buffer_tryflush(trans);
 	if (ret)
 		goto err;
 
-	for_each_member_device(ca, c, i) {
+	for_each_member_device(c, ca) {
 		s64 nr_to_invalidate =
 			should_invalidate_buckets(ca, bch2_dev_usage_read(ca));
 
-		ret = for_each_btree_key2_upto(trans, iter, BTREE_ID_lru,
+		ret = for_each_btree_key_upto(trans, iter, BTREE_ID_lru,
 				lru_pos(ca->dev_idx, 0, 0),
 				lru_pos(ca->dev_idx, U64_MAX, LRU_TIME_MAX),
 				BTREE_ITER_INTENT, k,
@@ -1884,8 +1950,7 @@ int bch2_dev_freespace_init(struct bch_fs *c, struct bch_dev *ca,
 
 			ret =   bch2_bucket_do_index(trans, k, a, true) ?:
 				bch2_trans_commit(trans, NULL, NULL,
-						  BTREE_INSERT_LAZY_RW|
-						  BTREE_INSERT_NOFAIL);
+						  BCH_TRANS_COMMIT_no_enospc);
 			if (ret)
 				goto bkey_err;
 
@@ -1905,8 +1970,7 @@ int bch2_dev_freespace_init(struct bch_fs *c, struct bch_dev *ca,
 
 			ret = bch2_btree_insert_trans(trans, BTREE_ID_freespace, freespace, 0) ?:
 				bch2_trans_commit(trans, NULL, NULL,
-						  BTREE_INSERT_LAZY_RW|
-						  BTREE_INSERT_NOFAIL);
+						  BCH_TRANS_COMMIT_no_enospc);
 			if (ret)
 				goto bkey_err;
 
@@ -1937,8 +2001,6 @@ bkey_err:
 
 int bch2_fs_freespace_init(struct bch_fs *c)
 {
-	struct bch_dev *ca;
-	unsigned i;
 	int ret = 0;
 	bool doing_init = false;
 
@@ -1947,7 +2009,7 @@ int bch2_fs_freespace_init(struct bch_fs *c)
 	 * every mount:
 	 */
 
-	for_each_member_device(ca, c, i) {
+	for_each_member_device(c, ca) {
 		if (ca->mi.freespace_initialized)
 			continue;
 
@@ -2007,15 +2069,13 @@ out:
 
 void bch2_recalc_capacity(struct bch_fs *c)
 {
-	struct bch_dev *ca;
 	u64 capacity = 0, reserved_sectors = 0, gc_reserve;
 	unsigned bucket_size_max = 0;
 	unsigned long ra_pages = 0;
-	unsigned i;
 
 	lockdep_assert_held(&c->state_lock);
 
-	for_each_online_member(ca, c, i) {
+	for_each_online_member(c, ca) {
 		struct backing_dev_info *bdi = ca->disk_sb.bdev->bd_disk->bdi;
 
 		ra_pages += bdi->ra_pages;
@@ -2023,7 +2083,7 @@ void bch2_recalc_capacity(struct bch_fs *c)
 
 	bch2_set_ra_pages(c, ra_pages);
 
-	for_each_rw_member(ca, c, i) {
+	for_each_rw_member(c, ca) {
 		u64 dev_reserve = 0;
 
 		/*
@@ -2079,11 +2139,9 @@ void bch2_recalc_capacity(struct bch_fs *c)
 
 u64 bch2_min_rw_member_capacity(struct bch_fs *c)
 {
-	struct bch_dev *ca;
-	unsigned i;
 	u64 ret = U64_MAX;
 
-	for_each_rw_member(ca, c, i)
+	for_each_rw_member(c, ca)
 		ret = min(ret, ca->mi.nbuckets * ca->mi.bucket_size);
 	return ret;
 }
diff --git a/fs/bcachefs/alloc_background.h b/fs/bcachefs/alloc_background.h
index 73faf99a222a..e7f7e842ee1b 100644
--- a/fs/bcachefs/alloc_background.h
+++ b/fs/bcachefs/alloc_background.h
@@ -71,6 +71,24 @@ static inline enum bch_data_type bucket_data_type(enum bch_data_type data_type)
 	return data_type == BCH_DATA_stripe ? BCH_DATA_user : data_type;
 }
 
+static inline unsigned bch2_bucket_sectors(struct bch_alloc_v4 a)
+{
+	return a.dirty_sectors + a.cached_sectors;
+}
+
+static inline unsigned bch2_bucket_sectors_dirty(struct bch_alloc_v4 a)
+{
+	return a.dirty_sectors;
+}
+
+static inline unsigned bch2_bucket_sectors_fragmented(struct bch_dev *ca,
+						 struct bch_alloc_v4 a)
+{
+	int d = bch2_bucket_sectors_dirty(a);
+
+	return d ? max(0, ca->mi.bucket_size - d) : 0;
+}
+
 static inline u64 alloc_lru_idx_read(struct bch_alloc_v4 a)
 {
 	return a.data_type == BCH_DATA_cached ? a.io_time[READ] : 0;
@@ -90,10 +108,11 @@ static inline u64 alloc_lru_idx_fragmentation(struct bch_alloc_v4 a,
 					      struct bch_dev *ca)
 {
 	if (!data_type_movable(a.data_type) ||
-	    a.dirty_sectors >= ca->mi.bucket_size)
+	    !bch2_bucket_sectors_fragmented(ca, a))
 		return 0;
 
-	return div_u64((u64) a.dirty_sectors * (1ULL << 31), ca->mi.bucket_size);
+	u64 d = bch2_bucket_sectors_dirty(a);
+	return div_u64(d * (1ULL << 31), ca->mi.bucket_size);
 }
 
 static inline u64 alloc_freespace_genbits(struct bch_alloc_v4 a)
@@ -163,24 +182,21 @@ void bch2_alloc_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
 #define bch2_bkey_ops_alloc ((struct bkey_ops) {	\
 	.key_invalid	= bch2_alloc_v1_invalid,	\
 	.val_to_text	= bch2_alloc_to_text,		\
-	.trans_trigger	= bch2_trans_mark_alloc,	\
-	.atomic_trigger	= bch2_mark_alloc,		\
+	.trigger	= bch2_trigger_alloc,		\
 	.min_val_size	= 8,				\
 })
 
 #define bch2_bkey_ops_alloc_v2 ((struct bkey_ops) {	\
 	.key_invalid	= bch2_alloc_v2_invalid,	\
 	.val_to_text	= bch2_alloc_to_text,		\
-	.trans_trigger	= bch2_trans_mark_alloc,	\
-	.atomic_trigger	= bch2_mark_alloc,		\
+	.trigger	= bch2_trigger_alloc,		\
 	.min_val_size	= 8,				\
 })
 
 #define bch2_bkey_ops_alloc_v3 ((struct bkey_ops) {	\
 	.key_invalid	= bch2_alloc_v3_invalid,	\
 	.val_to_text	= bch2_alloc_to_text,		\
-	.trans_trigger	= bch2_trans_mark_alloc,	\
-	.atomic_trigger	= bch2_mark_alloc,		\
+	.trigger	= bch2_trigger_alloc,		\
 	.min_val_size	= 16,				\
 })
 
@@ -188,8 +204,7 @@ void bch2_alloc_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
 	.key_invalid	= bch2_alloc_v4_invalid,	\
 	.val_to_text	= bch2_alloc_to_text,		\
 	.swab		= bch2_alloc_v4_swab,		\
-	.trans_trigger	= bch2_trans_mark_alloc,	\
-	.atomic_trigger	= bch2_mark_alloc,		\
+	.trigger	= bch2_trigger_alloc,		\
 	.min_val_size	= 48,				\
 })
 
@@ -213,8 +228,8 @@ static inline bool bkey_is_alloc(const struct bkey *k)
 
 int bch2_alloc_read(struct bch_fs *);
 
-int bch2_trans_mark_alloc(struct btree_trans *, enum btree_id, unsigned,
-			  struct bkey_s_c, struct bkey_i *, unsigned);
+int bch2_trigger_alloc(struct btree_trans *, enum btree_id, unsigned,
+		       struct bkey_s_c, struct bkey_s, unsigned);
 int bch2_check_alloc_info(struct bch_fs *);
 int bch2_check_alloc_to_lru_refs(struct bch_fs *);
 void bch2_do_discards(struct bch_fs *);
diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c
index b85c7765272f..b0ff47998a94 100644
--- a/fs/bcachefs/alloc_foreground.c
+++ b/fs/bcachefs/alloc_foreground.c
@@ -69,11 +69,8 @@ const char * const bch2_watermarks[] = {
 
 void bch2_reset_alloc_cursors(struct bch_fs *c)
 {
-	struct bch_dev *ca;
-	unsigned i;
-
 	rcu_read_lock();
-	for_each_member_device_rcu(ca, c, i, NULL)
+	for_each_member_device_rcu(c, ca, NULL)
 		ca->alloc_cursor = 0;
 	rcu_read_unlock();
 }
@@ -239,9 +236,8 @@ static struct open_bucket *__try_alloc_bucket(struct bch_fs *c, struct bch_dev *
 		if (cl)
 			closure_wait(&c->open_buckets_wait, cl);
 
-		if (!c->blocked_allocate_open_bucket)
-			c->blocked_allocate_open_bucket = local_clock();
-
+		track_event_change(&c->times[BCH_TIME_blocked_allocate_open_bucket],
+				   &c->blocked_allocate_open_bucket, true);
 		spin_unlock(&c->freelist_lock);
 		return ERR_PTR(-BCH_ERR_open_buckets_empty);
 	}
@@ -267,19 +263,11 @@ static struct open_bucket *__try_alloc_bucket(struct bch_fs *c, struct bch_dev *
 	ca->nr_open_buckets++;
 	bch2_open_bucket_hash_add(c, ob);
 
-	if (c->blocked_allocate_open_bucket) {
-		bch2_time_stats_update(
-			&c->times[BCH_TIME_blocked_allocate_open_bucket],
-			c->blocked_allocate_open_bucket);
-		c->blocked_allocate_open_bucket = 0;
-	}
+	track_event_change(&c->times[BCH_TIME_blocked_allocate_open_bucket],
+			   &c->blocked_allocate_open_bucket, false);
 
-	if (c->blocked_allocate) {
-		bch2_time_stats_update(
-			&c->times[BCH_TIME_blocked_allocate],
-			c->blocked_allocate);
-		c->blocked_allocate = 0;
-	}
+	track_event_change(&c->times[BCH_TIME_blocked_allocate],
+			   &c->blocked_allocate, false);
 
 	spin_unlock(&c->freelist_lock);
 	return ob;
@@ -377,9 +365,9 @@ static struct open_bucket *try_alloc_bucket(struct btree_trans *trans, struct bc
 
 	ob = __try_alloc_bucket(c, ca, b, watermark, a, s, cl);
 	if (!ob)
-		iter.path->preserve = false;
+		set_btree_iter_dontneed(&iter);
 err:
-	if (iter.trans && iter.path)
+	if (iter.path)
 		set_btree_iter_dontneed(&iter);
 	bch2_trans_iter_exit(trans, &iter);
 	printbuf_exit(&buf);
@@ -447,7 +435,7 @@ again:
 
 		ob = __try_alloc_bucket(trans->c, ca, k.k->p.offset, watermark, a, s, cl);
 next:
-		citer.path->preserve = false;
+		set_btree_iter_dontneed(&citer);
 		bch2_trans_iter_exit(trans, &citer);
 		if (ob)
 			break;
@@ -502,7 +490,7 @@ again:
 			ob = try_alloc_bucket(trans, ca, watermark,
 					      alloc_cursor, s, k, cl);
 			if (ob) {
-				iter.path->preserve = false;
+				set_btree_iter_dontneed(&iter);
 				break;
 			}
 		}
@@ -567,8 +555,8 @@ again:
 			goto again;
 		}
 
-		if (!c->blocked_allocate)
-			c->blocked_allocate = local_clock();
+		track_event_change(&c->times[BCH_TIME_blocked_allocate],
+				   &c->blocked_allocate, true);
 
 		ob = ERR_PTR(-BCH_ERR_freelist_empty);
 		goto err;
@@ -697,11 +685,9 @@ static int add_new_bucket(struct bch_fs *c,
 		bch_dev_bkey_exists(c, ob->dev)->mi.durability;
 
 	BUG_ON(*nr_effective >= nr_replicas);
-	BUG_ON(flags & BCH_WRITE_ONLY_SPECIFIED_DEVS);
 
 	__clear_bit(ob->dev, devs_may_alloc->d);
-	*nr_effective	+= (flags & BCH_WRITE_ONLY_SPECIFIED_DEVS)
-		? durability : 1;
+	*nr_effective	+= durability;
 	*have_cache	|= !durability;
 
 	ob_push(c, ptrs, ob);
@@ -972,8 +958,8 @@ static int __open_bucket_add_buckets(struct btree_trans *trans,
 	devs = target_rw_devs(c, wp->data_type, target);
 
 	/* Don't allocate from devices we already have pointers to: */
-	for (i = 0; i < devs_have->nr; i++)
-		__clear_bit(devs_have->devs[i], devs.d);
+	darray_for_each(*devs_have, i)
+		__clear_bit(*i, devs.d);
 
 	open_bucket_for_each(c, ptrs, ob, i)
 		__clear_bit(ob->dev, devs.d);
@@ -1297,6 +1283,30 @@ out:
 	return wp;
 }
 
+static noinline void
+deallocate_extra_replicas(struct bch_fs *c,
+			  struct open_buckets *ptrs,
+			  struct open_buckets *ptrs_no_use,
+			  unsigned extra_replicas)
+{
+	struct open_buckets ptrs2 = { 0 };
+	struct open_bucket *ob;
+	unsigned i;
+
+	open_bucket_for_each(c, ptrs, ob, i) {
+		unsigned d = bch_dev_bkey_exists(c, ob->dev)->mi.durability;
+
+		if (d && d <= extra_replicas) {
+			extra_replicas -= d;
+			ob_push(c, ptrs_no_use, ob);
+		} else {
+			ob_push(c, &ptrs2, ob);
+		}
+	}
+
+	*ptrs = ptrs2;
+}
+
 /*
  * Get us an open_bucket we can allocate from, return with it locked:
  */
@@ -1321,6 +1331,9 @@ int bch2_alloc_sectors_start_trans(struct btree_trans *trans,
 	int ret;
 	int i;
 
+	if (!IS_ENABLED(CONFIG_BCACHEFS_ERASURE_CODING))
+		erasure_code = false;
+
 	BUG_ON(flags & BCH_WRITE_ONLY_SPECIFIED_DEVS);
 
 	BUG_ON(!nr_replicas || !nr_replicas_required);
@@ -1347,8 +1360,17 @@ retry:
 			goto alloc_done;
 
 		/* Don't retry from all devices if we're out of open buckets: */
-		if (bch2_err_matches(ret, BCH_ERR_open_buckets_empty))
-			goto allocate_blocking;
+		if (bch2_err_matches(ret, BCH_ERR_open_buckets_empty)) {
+			int ret = open_bucket_add_buckets(trans, &ptrs, wp, devs_have,
+					      target, erasure_code,
+					      nr_replicas, &nr_effective,
+					      &have_cache, watermark,
+					      flags, cl);
+			if (!ret ||
+			    bch2_err_matches(ret, BCH_ERR_transaction_restart) ||
+			    bch2_err_matches(ret, BCH_ERR_open_buckets_empty))
+				goto alloc_done;
+		}
 
 		/*
 		 * Only try to allocate cache (durability = 0 devices) from the
@@ -1362,7 +1384,6 @@ retry:
 					      &have_cache, watermark,
 					      flags, cl);
 	} else {
-allocate_blocking:
 		ret = open_bucket_add_buckets(trans, &ptrs, wp, devs_have,
 					      target, erasure_code,
 					      nr_replicas, &nr_effective,
@@ -1382,6 +1403,9 @@ alloc_done:
 	if (ret)
 		goto err;
 
+	if (nr_effective > nr_replicas)
+		deallocate_extra_replicas(c, &ptrs, &wp->ptrs, nr_effective - nr_replicas);
+
 	/* Free buckets we didn't use: */
 	open_bucket_for_each(c, &wp->ptrs, ob, i)
 		open_bucket_free_unused(c, ob);
diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c
index ef02c9bb0354..e358a2ffffde 100644
--- a/fs/bcachefs/backpointers.c
+++ b/fs/bcachefs/backpointers.c
@@ -3,6 +3,7 @@
 #include "bbpos.h"
 #include "alloc_background.h"
 #include "backpointers.h"
+#include "bkey_buf.h"
 #include "btree_cache.h"
 #include "btree_update.h"
 #include "btree_update_interior.h"
@@ -136,15 +137,30 @@ static noinline int backpointer_mod_err(struct btree_trans *trans,
 }
 
 int bch2_bucket_backpointer_mod_nowritebuffer(struct btree_trans *trans,
-				struct bkey_i_backpointer *bp_k,
+				struct bpos bucket,
 				struct bch_backpointer bp,
 				struct bkey_s_c orig_k,
 				bool insert)
 {
 	struct btree_iter bp_iter;
 	struct bkey_s_c k;
+	struct bkey_i_backpointer *bp_k;
 	int ret;
 
+	bp_k = bch2_trans_kmalloc_nomemzero(trans, sizeof(struct bkey_i_backpointer));
+	ret = PTR_ERR_OR_ZERO(bp_k);
+	if (ret)
+		return ret;
+
+	bkey_backpointer_init(&bp_k->k_i);
+	bp_k->k.p = bucket_pos_to_bp(trans->c, bucket, bp.bucket_offset);
+	bp_k->v = bp;
+
+	if (!insert) {
+		bp_k->k.type = KEY_TYPE_deleted;
+		set_bkey_val_u64s(&bp_k->k, 0);
+	}
+
 	k = bch2_bkey_get_iter(trans, &bp_iter, BTREE_ID_backpointers,
 			       bp_k->k.p,
 			       BTREE_ITER_INTENT|
@@ -313,17 +329,17 @@ struct btree *bch2_backpointer_get_node(struct btree_trans *trans,
 				  bp.level - 1,
 				  0);
 	b = bch2_btree_iter_peek_node(iter);
-	if (IS_ERR(b))
+	if (IS_ERR_OR_NULL(b))
 		goto err;
 
 	BUG_ON(b->c.level != bp.level - 1);
 
-	if (b && extent_matches_bp(c, bp.btree_id, bp.level,
-				   bkey_i_to_s_c(&b->key),
-				   bucket, bp))
+	if (extent_matches_bp(c, bp.btree_id, bp.level,
+			      bkey_i_to_s_c(&b->key),
+			      bucket, bp))
 		return b;
 
-	if (b && btree_node_will_make_reachable(b)) {
+	if (btree_node_will_make_reachable(b)) {
 		b = ERR_PTR(-BCH_ERR_backpointer_to_overwritten_btree_node);
 	} else {
 		backpointer_not_found(trans, bp_pos, bp, bkey_i_to_s_c(&b->key));
@@ -375,39 +391,32 @@ fsck_err:
 /* verify that every backpointer has a corresponding alloc key */
 int bch2_check_btree_backpointers(struct bch_fs *c)
 {
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	int ret;
-
-	ret = bch2_trans_run(c,
+	int ret = bch2_trans_run(c,
 		for_each_btree_key_commit(trans, iter,
 			BTREE_ID_backpointers, POS_MIN, 0, k,
-			NULL, NULL, BTREE_INSERT_LAZY_RW|BTREE_INSERT_NOFAIL,
+			NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 		  bch2_check_btree_backpointer(trans, &iter, k)));
-	if (ret)
-		bch_err_fn(c, ret);
+	bch_err_fn(c, ret);
 	return ret;
 }
 
-struct bpos_level {
-	unsigned	level;
-	struct bpos	pos;
-};
-
 static int check_bp_exists(struct btree_trans *trans,
 			   struct bpos bucket,
 			   struct bch_backpointer bp,
 			   struct bkey_s_c orig_k,
 			   struct bpos bucket_start,
 			   struct bpos bucket_end,
-			   struct bpos_level *last_flushed)
+			   struct bkey_buf *last_flushed)
 {
 	struct bch_fs *c = trans->c;
 	struct btree_iter bp_iter = { NULL };
 	struct printbuf buf = PRINTBUF;
 	struct bkey_s_c bp_k;
+	struct bkey_buf tmp;
 	int ret;
 
+	bch2_bkey_buf_init(&tmp);
+
 	if (bpos_lt(bucket, bucket_start) ||
 	    bpos_gt(bucket, bucket_end))
 		return 0;
@@ -424,13 +433,22 @@ static int check_bp_exists(struct btree_trans *trans,
 
 	if (bp_k.k->type != KEY_TYPE_backpointer ||
 	    memcmp(bkey_s_c_to_backpointer(bp_k).v, &bp, sizeof(bp))) {
-		if (last_flushed->level != bp.level ||
-		    !bpos_eq(last_flushed->pos, orig_k.k->p)) {
-			last_flushed->level = bp.level;
-			last_flushed->pos = orig_k.k->p;
+		if (!bpos_eq(orig_k.k->p, last_flushed->k->k.p) ||
+		    bkey_bytes(orig_k.k) != bkey_bytes(&last_flushed->k->k) ||
+		    memcmp(orig_k.v, &last_flushed->k->v, bkey_val_bytes(orig_k.k))) {
+			bch2_bkey_buf_reassemble(&tmp, c, orig_k);
+
+			if (bp.level) {
+				bch2_trans_unlock(trans);
+				bch2_btree_interior_updates_flush(c);
+			}
 
-			ret = bch2_btree_write_buffer_flush_sync(trans) ?:
-				-BCH_ERR_transaction_restart_write_buffer_flush;
+			ret = bch2_btree_write_buffer_flush_sync(trans);
+			if (ret)
+				goto err;
+
+			bch2_bkey_buf_copy(last_flushed, c, tmp.k);
+			ret = -BCH_ERR_transaction_restart_write_buffer_flush;
 			goto out;
 		}
 		goto missing;
@@ -439,6 +457,7 @@ out:
 err:
 fsck_err:
 	bch2_trans_iter_exit(trans, &bp_iter);
+	bch2_bkey_buf_exit(&tmp, c);
 	printbuf_exit(&buf);
 	return ret;
 missing:
@@ -448,8 +467,7 @@ missing:
 	prt_printf(&buf, "\nbp pos ");
 	bch2_bpos_to_text(&buf, bp_iter.pos);
 
-	if (c->sb.version_upgrade_complete < bcachefs_metadata_version_backpointers ||
-	    c->opts.reconstruct_alloc ||
+	if (c->opts.reconstruct_alloc ||
 	    fsck_err(c, ptr_to_missing_backpointer, "%s", buf.buf))
 		ret = bch2_bucket_backpointer_mod(trans, bucket, bp, orig_k, true);
 
@@ -457,25 +475,18 @@ missing:
 }
 
 static int check_extent_to_backpointers(struct btree_trans *trans,
-					struct btree_iter *iter,
+					enum btree_id btree, unsigned level,
 					struct bpos bucket_start,
 					struct bpos bucket_end,
-					struct bpos_level *last_flushed)
+					struct bkey_buf *last_flushed,
+					struct bkey_s_c k)
 {
 	struct bch_fs *c = trans->c;
 	struct bkey_ptrs_c ptrs;
 	const union bch_extent_entry *entry;
 	struct extent_ptr_decoded p;
-	struct bkey_s_c k;
 	int ret;
 
-	k = bch2_btree_iter_peek_all_levels(iter);
-	ret = bkey_err(k);
-	if (ret)
-		return ret;
-	if (!k.k)
-		return 0;
-
 	ptrs = bch2_bkey_ptrs_c(k);
 	bkey_for_each_ptr_decode(k.k, ptrs, p, entry) {
 		struct bpos bucket_pos;
@@ -484,7 +495,7 @@ static int check_extent_to_backpointers(struct btree_trans *trans,
 		if (p.ptr.cached)
 			continue;
 
-		bch2_extent_ptr_to_bp(c, iter->btree_id, iter->path->level,
+		bch2_extent_ptr_to_bp(c, btree, level,
 				      k, p, &bucket_pos, &bp);
 
 		ret = check_bp_exists(trans, bucket_pos, bp, k,
@@ -501,44 +512,33 @@ static int check_btree_root_to_backpointers(struct btree_trans *trans,
 					    enum btree_id btree_id,
 					    struct bpos bucket_start,
 					    struct bpos bucket_end,
-					    struct bpos_level *last_flushed)
+					    struct bkey_buf *last_flushed,
+					    int *level)
 {
 	struct bch_fs *c = trans->c;
-	struct btree_root *r = bch2_btree_id_root(c, btree_id);
 	struct btree_iter iter;
 	struct btree *b;
 	struct bkey_s_c k;
-	struct bkey_ptrs_c ptrs;
-	struct extent_ptr_decoded p;
-	const union bch_extent_entry *entry;
 	int ret;
-
-	bch2_trans_node_iter_init(trans, &iter, btree_id, POS_MIN, 0, r->level, 0);
+retry:
+	bch2_trans_node_iter_init(trans, &iter, btree_id, POS_MIN,
+				  0, bch2_btree_id_root(c, btree_id)->b->c.level, 0);
 	b = bch2_btree_iter_peek_node(&iter);
 	ret = PTR_ERR_OR_ZERO(b);
 	if (ret)
 		goto err;
 
-	BUG_ON(b != btree_node_root(c, b));
-
-	k = bkey_i_to_s_c(&b->key);
-	ptrs = bch2_bkey_ptrs_c(k);
-	bkey_for_each_ptr_decode(k.k, ptrs, p, entry) {
-		struct bpos bucket_pos;
-		struct bch_backpointer bp;
-
-		if (p.ptr.cached)
-			continue;
+	if (b != btree_node_root(c, b)) {
+		bch2_trans_iter_exit(trans, &iter);
+		goto retry;
+	}
 
-		bch2_extent_ptr_to_bp(c, iter.btree_id, b->c.level + 1,
-				      k, p, &bucket_pos, &bp);
+	*level = b->c.level;
 
-		ret = check_bp_exists(trans, bucket_pos, bp, k,
+	k = bkey_i_to_s_c(&b->key);
+	ret = check_extent_to_backpointers(trans, btree_id, b->c.level + 1,
 				      bucket_start, bucket_end,
-				      last_flushed);
-		if (ret)
-			goto err;
-	}
+				      last_flushed, k);
 err:
 	bch2_trans_iter_exit(trans, &iter);
 	return ret;
@@ -616,43 +616,60 @@ static int bch2_check_extents_to_backpointers_pass(struct btree_trans *trans,
 	struct bch_fs *c = trans->c;
 	struct btree_iter iter;
 	enum btree_id btree_id;
-	struct bpos_level last_flushed = { UINT_MAX, POS_MIN };
+	struct bkey_s_c k;
+	struct bkey_buf last_flushed;
 	int ret = 0;
 
-	for (btree_id = 0; btree_id < btree_id_nr_alive(c); btree_id++) {
-		unsigned depth = btree_type_has_ptrs(btree_id) ? 0 : 1;
-
-		bch2_trans_node_iter_init(trans, &iter, btree_id, POS_MIN, 0,
-					  depth,
-					  BTREE_ITER_ALL_LEVELS|
-					  BTREE_ITER_PREFETCH);
-
-		do {
-			ret = commit_do(trans, NULL, NULL,
-					BTREE_INSERT_LAZY_RW|
-					BTREE_INSERT_NOFAIL,
-					check_extent_to_backpointers(trans, &iter,
-								bucket_start, bucket_end,
-								&last_flushed));
-			if (ret)
-				break;
-		} while (!bch2_btree_iter_advance(&iter));
-
-		bch2_trans_iter_exit(trans, &iter);
+	bch2_bkey_buf_init(&last_flushed);
+	bkey_init(&last_flushed.k->k);
 
-		if (ret)
-			break;
+	for (btree_id = 0; btree_id < btree_id_nr_alive(c); btree_id++) {
+		int level, depth = btree_type_has_ptrs(btree_id) ? 0 : 1;
 
 		ret = commit_do(trans, NULL, NULL,
-				BTREE_INSERT_LAZY_RW|
-				BTREE_INSERT_NOFAIL,
+				BCH_TRANS_COMMIT_no_enospc,
 				check_btree_root_to_backpointers(trans, btree_id,
 							bucket_start, bucket_end,
-							&last_flushed));
+							&last_flushed, &level));
 		if (ret)
-			break;
+			return ret;
+
+		while (level >= depth) {
+			bch2_trans_node_iter_init(trans, &iter, btree_id, POS_MIN, 0,
+						  level,
+						  BTREE_ITER_PREFETCH);
+			while (1) {
+				bch2_trans_begin(trans);
+				k = bch2_btree_iter_peek(&iter);
+				if (!k.k)
+					break;
+				ret = bkey_err(k) ?:
+					check_extent_to_backpointers(trans, btree_id, level,
+								     bucket_start, bucket_end,
+								     &last_flushed, k) ?:
+					bch2_trans_commit(trans, NULL, NULL,
+							  BCH_TRANS_COMMIT_no_enospc);
+				if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) {
+					ret = 0;
+					continue;
+				}
+				if (ret)
+					break;
+				if (bpos_eq(iter.pos, SPOS_MAX))
+					break;
+				bch2_btree_iter_advance(&iter);
+			}
+			bch2_trans_iter_exit(trans, &iter);
+
+			if (ret)
+				return ret;
+
+			--level;
+		}
 	}
-	return ret;
+
+	bch2_bkey_buf_exit(&last_flushed, c);
+	return 0;
 }
 
 static struct bpos bucket_pos_to_bp_safe(const struct bch_fs *c,
@@ -746,8 +763,7 @@ int bch2_check_extents_to_backpointers(struct bch_fs *c)
 	}
 	bch2_trans_put(trans);
 
-	if (ret)
-		bch_err_fn(c, ret);
+	bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -801,13 +817,11 @@ static int bch2_check_backpointers_to_extents_pass(struct btree_trans *trans,
 						   struct bbpos start,
 						   struct bbpos end)
 {
-	struct btree_iter iter;
-	struct bkey_s_c k;
 	struct bpos last_flushed_pos = SPOS_MAX;
 
 	return for_each_btree_key_commit(trans, iter, BTREE_ID_backpointers,
 				  POS_MIN, BTREE_ITER_PREFETCH, k,
-				  NULL, NULL, BTREE_INSERT_LAZY_RW|BTREE_INSERT_NOFAIL,
+				  NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 		check_one_backpointer(trans, start, end,
 				      bkey_s_c_to_backpointer(k),
 				      &last_flushed_pos));
@@ -854,7 +868,6 @@ int bch2_check_backpointers_to_extents(struct bch_fs *c)
 	}
 	bch2_trans_put(trans);
 
-	if (ret)
-		bch_err_fn(c, ret);
+	bch_err_fn(c, ret);
 	return ret;
 }
diff --git a/fs/bcachefs/backpointers.h b/fs/bcachefs/backpointers.h
index ab866feeaf66..737e2396ade7 100644
--- a/fs/bcachefs/backpointers.h
+++ b/fs/bcachefs/backpointers.h
@@ -63,7 +63,7 @@ static inline struct bpos bucket_pos_to_bp(const struct bch_fs *c,
 	return ret;
 }
 
-int bch2_bucket_backpointer_mod_nowritebuffer(struct btree_trans *, struct bkey_i_backpointer *,
+int bch2_bucket_backpointer_mod_nowritebuffer(struct btree_trans *, struct bpos bucket,
 				struct bch_backpointer, struct bkey_s_c, bool);
 
 static inline int bch2_bucket_backpointer_mod(struct btree_trans *trans,
@@ -72,28 +72,21 @@ static inline int bch2_bucket_backpointer_mod(struct btree_trans *trans,
 				struct bkey_s_c orig_k,
 				bool insert)
 {
-	struct bch_fs *c = trans->c;
-	struct bkey_i_backpointer *bp_k;
-	int ret;
+	if (unlikely(bch2_backpointers_no_use_write_buffer))
+		return bch2_bucket_backpointer_mod_nowritebuffer(trans, bucket, bp, orig_k, insert);
 
-	bp_k = bch2_trans_kmalloc_nomemzero(trans, sizeof(struct bkey_i_backpointer));
-	ret = PTR_ERR_OR_ZERO(bp_k);
-	if (ret)
-		return ret;
+	struct bkey_i_backpointer bp_k;
 
-	bkey_backpointer_init(&bp_k->k_i);
-	bp_k->k.p = bucket_pos_to_bp(c, bucket, bp.bucket_offset);
-	bp_k->v = bp;
+	bkey_backpointer_init(&bp_k.k_i);
+	bp_k.k.p = bucket_pos_to_bp(trans->c, bucket, bp.bucket_offset);
+	bp_k.v = bp;
 
 	if (!insert) {
-		bp_k->k.type = KEY_TYPE_deleted;
-		set_bkey_val_u64s(&bp_k->k, 0);
+		bp_k.k.type = KEY_TYPE_deleted;
+		set_bkey_val_u64s(&bp_k.k, 0);
 	}
 
-	if (unlikely(bch2_backpointers_no_use_write_buffer))
-		return bch2_bucket_backpointer_mod_nowritebuffer(trans, bp_k, bp, orig_k, insert);
-
-	return bch2_trans_update_buffered(trans, BTREE_ID_backpointers, &bp_k->k_i);
+	return bch2_trans_update_buffered(trans, BTREE_ID_backpointers, &bp_k.k_i);
 }
 
 static inline enum bch_data_type bkey_ptr_data_type(enum btree_id btree_id, unsigned level,
diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index 9cb8684959ee..dac383e37181 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -193,6 +193,7 @@
 #include <linux/mutex.h>
 #include <linux/percpu-refcount.h>
 #include <linux/percpu-rwsem.h>
+#include <linux/refcount.h>
 #include <linux/rhashtable.h>
 #include <linux/rwsem.h>
 #include <linux/semaphore.h>
@@ -223,9 +224,11 @@
 
 #define race_fault(...)			dynamic_fault("bcachefs:race")
 
+#define count_event(_c, _name)	this_cpu_inc((_c)->counters[BCH_COUNTER_##_name])
+
 #define trace_and_count(_c, _name, ...)					\
 do {									\
-	this_cpu_inc((_c)->counters[BCH_COUNTER_##_name]);		\
+	count_event(_c, _name);						\
 	trace_##_name(__VA_ARGS__);					\
 } while (0)
 
@@ -262,46 +265,76 @@ do {									\
 
 #define bch2_fmt(_c, fmt)		bch2_log_msg(_c, fmt "\n")
 
+__printf(2, 3)
+void __bch2_print(struct bch_fs *c, const char *fmt, ...);
+
+#define maybe_dev_to_fs(_c)	_Generic((_c),				\
+	struct bch_dev *:	((struct bch_dev *) (_c))->fs,		\
+	struct bch_fs *:	(_c))
+
+#define bch2_print(_c, ...) __bch2_print(maybe_dev_to_fs(_c), __VA_ARGS__)
+
+#define bch2_print_ratelimited(_c, ...)					\
+do {									\
+	static DEFINE_RATELIMIT_STATE(_rs,				\
+				      DEFAULT_RATELIMIT_INTERVAL,	\
+				      DEFAULT_RATELIMIT_BURST);		\
+									\
+	if (__ratelimit(&_rs))						\
+		bch2_print(_c, __VA_ARGS__);				\
+} while (0)
+
 #define bch_info(c, fmt, ...) \
-	printk(KERN_INFO bch2_fmt(c, fmt), ##__VA_ARGS__)
+	bch2_print(c, KERN_INFO bch2_fmt(c, fmt), ##__VA_ARGS__)
 #define bch_notice(c, fmt, ...) \
-	printk(KERN_NOTICE bch2_fmt(c, fmt), ##__VA_ARGS__)
+	bch2_print(c, KERN_NOTICE bch2_fmt(c, fmt), ##__VA_ARGS__)
 #define bch_warn(c, fmt, ...) \
-	printk(KERN_WARNING bch2_fmt(c, fmt), ##__VA_ARGS__)
+	bch2_print(c, KERN_WARNING bch2_fmt(c, fmt), ##__VA_ARGS__)
 #define bch_warn_ratelimited(c, fmt, ...) \
-	printk_ratelimited(KERN_WARNING bch2_fmt(c, fmt), ##__VA_ARGS__)
+	bch2_print_ratelimited(c, KERN_WARNING bch2_fmt(c, fmt), ##__VA_ARGS__)
 
 #define bch_err(c, fmt, ...) \
-	printk(KERN_ERR bch2_fmt(c, fmt), ##__VA_ARGS__)
+	bch2_print(c, KERN_ERR bch2_fmt(c, fmt), ##__VA_ARGS__)
 #define bch_err_dev(ca, fmt, ...) \
-	printk(KERN_ERR bch2_fmt_dev(ca, fmt), ##__VA_ARGS__)
+	bch2_print(c, KERN_ERR bch2_fmt_dev(ca, fmt), ##__VA_ARGS__)
 #define bch_err_dev_offset(ca, _offset, fmt, ...) \
-	printk(KERN_ERR bch2_fmt_dev_offset(ca, _offset, fmt), ##__VA_ARGS__)
+	bch2_print(c, KERN_ERR bch2_fmt_dev_offset(ca, _offset, fmt), ##__VA_ARGS__)
 #define bch_err_inum(c, _inum, fmt, ...) \
-	printk(KERN_ERR bch2_fmt_inum(c, _inum, fmt), ##__VA_ARGS__)
+	bch2_print(c, KERN_ERR bch2_fmt_inum(c, _inum, fmt), ##__VA_ARGS__)
 #define bch_err_inum_offset(c, _inum, _offset, fmt, ...) \
-	printk(KERN_ERR bch2_fmt_inum_offset(c, _inum, _offset, fmt), ##__VA_ARGS__)
+	bch2_print(c, KERN_ERR bch2_fmt_inum_offset(c, _inum, _offset, fmt), ##__VA_ARGS__)
 
 #define bch_err_ratelimited(c, fmt, ...) \
-	printk_ratelimited(KERN_ERR bch2_fmt(c, fmt), ##__VA_ARGS__)
+	bch2_print_ratelimited(c, KERN_ERR bch2_fmt(c, fmt), ##__VA_ARGS__)
 #define bch_err_dev_ratelimited(ca, fmt, ...) \
-	printk_ratelimited(KERN_ERR bch2_fmt_dev(ca, fmt), ##__VA_ARGS__)
+	bch2_print_ratelimited(ca, KERN_ERR bch2_fmt_dev(ca, fmt), ##__VA_ARGS__)
 #define bch_err_dev_offset_ratelimited(ca, _offset, fmt, ...) \
-	printk_ratelimited(KERN_ERR bch2_fmt_dev_offset(ca, _offset, fmt), ##__VA_ARGS__)
+	bch2_print_ratelimited(ca, KERN_ERR bch2_fmt_dev_offset(ca, _offset, fmt), ##__VA_ARGS__)
 #define bch_err_inum_ratelimited(c, _inum, fmt, ...) \
-	printk_ratelimited(KERN_ERR bch2_fmt_inum(c, _inum, fmt), ##__VA_ARGS__)
+	bch2_print_ratelimited(c, KERN_ERR bch2_fmt_inum(c, _inum, fmt), ##__VA_ARGS__)
 #define bch_err_inum_offset_ratelimited(c, _inum, _offset, fmt, ...) \
-	printk_ratelimited(KERN_ERR bch2_fmt_inum_offset(c, _inum, _offset, fmt), ##__VA_ARGS__)
+	bch2_print_ratelimited(c, KERN_ERR bch2_fmt_inum_offset(c, _inum, _offset, fmt), ##__VA_ARGS__)
+
+static inline bool should_print_err(int err)
+{
+	return err && !bch2_err_matches(err, BCH_ERR_transaction_restart);
+}
 
 #define bch_err_fn(_c, _ret)						\
 do {									\
-	if (_ret && !bch2_err_matches(_ret, BCH_ERR_transaction_restart))\
+	if (should_print_err(_ret))					\
 		bch_err(_c, "%s(): error %s", __func__, bch2_err_str(_ret));\
 } while (0)
 
+#define bch_err_fn_ratelimited(_c, _ret)				\
+do {									\
+	if (should_print_err(_ret))					\
+		bch_err_ratelimited(_c, "%s(): error %s", __func__, bch2_err_str(_ret));\
+} while (0)
+
 #define bch_err_msg(_c, _ret, _msg, ...)				\
 do {									\
-	if (_ret && !bch2_err_matches(_ret, BCH_ERR_transaction_restart))\
+	if (should_print_err(_ret))					\
 		bch_err(_c, "%s(): error " _msg " %s", __func__,	\
 			##__VA_ARGS__, bch2_err_str(_ret));		\
 } while (0)
@@ -392,6 +425,7 @@ BCH_DEBUG_PARAMS_DEBUG()
 	x(btree_node_merge)			\
 	x(btree_node_sort)			\
 	x(btree_node_read)			\
+	x(btree_node_read_done)			\
 	x(btree_interior_update_foreground)	\
 	x(btree_interior_update_total)		\
 	x(btree_gc)				\
@@ -401,9 +435,12 @@ BCH_DEBUG_PARAMS_DEBUG()
 	x(journal_flush_write)			\
 	x(journal_noflush_write)		\
 	x(journal_flush_seq)			\
-	x(blocked_journal)			\
+	x(blocked_journal_low_on_space)		\
+	x(blocked_journal_low_on_pin)		\
+	x(blocked_journal_max_in_flight)	\
 	x(blocked_allocate)			\
 	x(blocked_allocate_open_bucket)		\
+	x(blocked_write_buffer_full)		\
 	x(nocow_lock_contended)
 
 enum bch_time_stats {
@@ -428,6 +465,7 @@ enum bch_time_stats {
 #include "replicas_types.h"
 #include "subvolume_types.h"
 #include "super_types.h"
+#include "thread_with_file_types.h"
 
 /* Number of nodes btree coalesce will try to coalesce at once */
 #define GC_MERGE_NODES		4U
@@ -564,32 +602,35 @@ struct bch_dev {
 	struct io_count __percpu *io_done;
 };
 
-enum {
-	/* startup: */
-	BCH_FS_STARTED,
-	BCH_FS_MAY_GO_RW,
-	BCH_FS_RW,
-	BCH_FS_WAS_RW,
-
-	/* shutdown: */
-	BCH_FS_STOPPING,
-	BCH_FS_EMERGENCY_RO,
-	BCH_FS_GOING_RO,
-	BCH_FS_WRITE_DISABLE_COMPLETE,
-	BCH_FS_CLEAN_SHUTDOWN,
-
-	/* fsck passes: */
-	BCH_FS_FSCK_DONE,
-	BCH_FS_INITIAL_GC_UNFIXED,	/* kill when we enumerate fsck errors */
-	BCH_FS_NEED_ANOTHER_GC,
-
-	BCH_FS_NEED_DELETE_DEAD_SNAPSHOTS,
-
-	/* errors: */
-	BCH_FS_ERROR,
-	BCH_FS_TOPOLOGY_ERROR,
-	BCH_FS_ERRORS_FIXED,
-	BCH_FS_ERRORS_NOT_FIXED,
+/*
+ * initial_gc_unfixed
+ * error
+ * topology error
+ */
+
+#define BCH_FS_FLAGS()			\
+	x(started)			\
+	x(may_go_rw)			\
+	x(rw)				\
+	x(was_rw)			\
+	x(stopping)			\
+	x(emergency_ro)			\
+	x(going_ro)			\
+	x(write_disable_complete)	\
+	x(clean_shutdown)		\
+	x(fsck_running)			\
+	x(initial_gc_unfixed)		\
+	x(need_another_gc)		\
+	x(need_delete_dead_snapshots)	\
+	x(error)			\
+	x(topology_error)		\
+	x(errors_fixed)			\
+	x(errors_not_fixed)
+
+enum bch_fs_flags {
+#define x(n)		BCH_FS_##n,
+	BCH_FS_FLAGS()
+#undef x
 };
 
 struct btree_debug {
@@ -599,10 +640,11 @@ struct btree_debug {
 #define BCH_TRANSACTIONS_NR 128
 
 struct btree_transaction_stats {
+	struct bch2_time_stats	duration;
 	struct bch2_time_stats	lock_hold_times;
 	struct mutex		lock;
 	unsigned		nr_max_paths;
-	unsigned		wb_updates_size;
+	unsigned		journal_entries_size;
 	unsigned		max_mem;
 	char			*max_paths_text;
 };
@@ -617,7 +659,7 @@ struct journal_seq_blacklist_table {
 		u64		start;
 		u64		end;
 		bool		dirty;
-	}			entries[0];
+	}			entries[];
 };
 
 struct journal_keys {
@@ -638,6 +680,8 @@ struct journal_keys {
 	size_t			gap;
 	size_t			nr;
 	size_t			size;
+	atomic_t		ref;
+	bool			initial_ref_held;
 };
 
 struct btree_trans_buf {
@@ -662,7 +706,8 @@ struct btree_trans_buf {
 	x(invalidate)							\
 	x(delete_dead_snapshots)					\
 	x(snapshot_delete_pagecache)					\
-	x(sysfs)
+	x(sysfs)							\
+	x(btree_write_buffer)
 
 enum bch_write_ref {
 #define x(n) BCH_WRITE_REF_##n,
@@ -687,6 +732,8 @@ struct bch_fs {
 	struct super_block	*vfs_sb;
 	dev_t			dev;
 	char			name[40];
+	struct stdio_redirect	*stdio;
+	struct task_struct	*stdio_filter;
 
 	/* ro/rw, add/remove/resize devices: */
 	struct rw_semaphore	state_lock;
@@ -697,6 +744,13 @@ struct bch_fs {
 #else
 	struct percpu_ref	writes;
 #endif
+	/*
+	 * Analagous to c->writes, for asynchronous ops that don't necessarily
+	 * need fs to be read-write
+	 */
+	refcount_t		ro_ref;
+	wait_queue_head_t	ro_ref_wait;
+
 	struct work_struct	read_only_work;
 
 	struct bch_dev __rcu	*devs[BCH_SB_MEMBERS_MAX];
@@ -735,6 +789,7 @@ struct bch_fs {
 		unsigned	nsec_per_time_unit;
 		u64		features;
 		u64		compat;
+		unsigned long	errors_silent[BITS_TO_LONGS(BCH_SB_ERR_MAX)];
 	}			sb;
 
 
@@ -929,7 +984,7 @@ struct bch_fs {
 	mempool_t		compression_bounce[2];
 	mempool_t		compress_workspace[BCH_COMPRESSION_TYPE_NR];
 	mempool_t		decompress_workspace;
-	ZSTD_parameters		zstd_params;
+	size_t			zstd_workspace_size;
 
 	struct crypto_shash	*sha256;
 	struct crypto_sync_skcipher *chacha20;
@@ -999,10 +1054,21 @@ struct bch_fs {
 	/* RECOVERY */
 	u64			journal_replay_seq_start;
 	u64			journal_replay_seq_end;
+	/*
+	 * Two different uses:
+	 * "Has this fsck pass?" - i.e. should this type of error be an
+	 * emergency read-only
+	 * And, in certain situations fsck will rewind to an earlier pass: used
+	 * for signaling to the toplevel code which pass we want to run now.
+	 */
 	enum bch_recovery_pass	curr_recovery_pass;
 	/* bitmap of explicitly enabled recovery passes: */
 	u64			recovery_passes_explicit;
+	/* bitmask of recovery passes that we actually ran */
 	u64			recovery_passes_complete;
+	/* never rewinds version of curr_recovery_pass */
+	enum bch_recovery_pass	recovery_pass_done;
+	struct semaphore	online_fsck_mutex;
 
 	/* DEBUG JUNK */
 	struct dentry		*fs_debug_dir;
@@ -1062,10 +1128,20 @@ static inline void bch2_write_ref_get(struct bch_fs *c, enum bch_write_ref ref)
 #endif
 }
 
+static inline bool __bch2_write_ref_tryget(struct bch_fs *c, enum bch_write_ref ref)
+{
+#ifdef BCH_WRITE_REF_DEBUG
+	return !test_bit(BCH_FS_going_ro, &c->flags) &&
+		atomic_long_inc_not_zero(&c->writes[ref]);
+#else
+	return percpu_ref_tryget(&c->writes);
+#endif
+}
+
 static inline bool bch2_write_ref_tryget(struct bch_fs *c, enum bch_write_ref ref)
 {
 #ifdef BCH_WRITE_REF_DEBUG
-	return !test_bit(BCH_FS_GOING_RO, &c->flags) &&
+	return !test_bit(BCH_FS_going_ro, &c->flags) &&
 		atomic_long_inc_not_zero(&c->writes[ref]);
 #else
 	return percpu_ref_tryget_live(&c->writes);
@@ -1084,13 +1160,27 @@ static inline void bch2_write_ref_put(struct bch_fs *c, enum bch_write_ref ref)
 		if (atomic_long_read(&c->writes[i]))
 			return;
 
-	set_bit(BCH_FS_WRITE_DISABLE_COMPLETE, &c->flags);
+	set_bit(BCH_FS_write_disable_complete, &c->flags);
 	wake_up(&bch2_read_only_wait);
 #else
 	percpu_ref_put(&c->writes);
 #endif
 }
 
+static inline bool bch2_ro_ref_tryget(struct bch_fs *c)
+{
+	if (test_bit(BCH_FS_stopping, &c->flags))
+		return false;
+
+	return refcount_inc_not_zero(&c->ro_ref);
+}
+
+static inline void bch2_ro_ref_put(struct bch_fs *c)
+{
+	if (refcount_dec_and_test(&c->ro_ref))
+		wake_up(&c->ro_ref_wait);
+}
+
 static inline void bch2_set_ra_pages(struct bch_fs *c, unsigned ra_pages)
 {
 #ifndef NO_BCACHEFS_FS
@@ -1155,6 +1245,15 @@ static inline bool bch2_dev_exists2(const struct bch_fs *c, unsigned dev)
 	return dev < c->sb.nr_devices && c->devs[dev];
 }
 
+static inline struct stdio_redirect *bch2_fs_stdio_redirect(struct bch_fs *c)
+{
+	struct stdio_redirect *stdio = c->stdio;
+
+	if (c->stdio_filter && c->stdio_filter != current)
+		stdio = NULL;
+	return stdio;
+}
+
 #define BKEY_PADDED_ONSTACK(key, pad)				\
 	struct { struct bkey_i key; __u64 key ## _pad[pad]; }
 
diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index 0a750953ff92..0d5ac4184fbc 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -151,7 +151,11 @@ struct bpos {
 #else
 #error edit for your odd byteorder.
 #endif
-} __packed __aligned(4);
+} __packed
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+__aligned(4)
+#endif
+;
 
 #define KEY_INODE_MAX			((__u64)~0ULL)
 #define KEY_OFFSET_MAX			((__u64)~0ULL)
@@ -303,6 +307,13 @@ struct bkey_i {
 	struct bch_val	v;
 };
 
+#define POS_KEY(_pos)							\
+((struct bkey) {							\
+	.u64s		= BKEY_U64s,					\
+	.format		= KEY_FORMAT_CURRENT,				\
+	.p		= _pos,						\
+})
+
 #define KEY(_inode, _offset, _size)					\
 ((struct bkey) {							\
 	.u64s		= BKEY_U64s,					\
@@ -1203,19 +1214,21 @@ struct bch_sb_field {
 };
 
 #define BCH_SB_FIELDS()				\
-	x(journal,	0)			\
-	x(members_v1,	1)			\
-	x(crypt,	2)			\
-	x(replicas_v0,	3)			\
-	x(quota,	4)			\
-	x(disk_groups,	5)			\
-	x(clean,	6)			\
-	x(replicas,	7)			\
-	x(journal_seq_blacklist, 8)		\
-	x(journal_v2,	9)			\
-	x(counters,	10)			\
-	x(members_v2,	11)			\
-	x(errors,	12)
+	x(journal,			0)	\
+	x(members_v1,			1)	\
+	x(crypt,			2)	\
+	x(replicas_v0,			3)	\
+	x(quota,			4)	\
+	x(disk_groups,			5)	\
+	x(clean,			6)	\
+	x(replicas,			7)	\
+	x(journal_seq_blacklist,	8)	\
+	x(journal_v2,			9)	\
+	x(counters,			10)	\
+	x(members_v2,			11)	\
+	x(errors,			12)	\
+	x(ext,				13)	\
+	x(downgrade,			14)
 
 enum bch_sb_field_type {
 #define x(f, nr)	BCH_SB_FIELD_##f = nr,
@@ -1290,6 +1303,7 @@ struct bch_member {
 	__le64			errors[BCH_MEMBER_ERROR_NR];
 	__le64			errors_at_reset[BCH_MEMBER_ERROR_NR];
 	__le64			errors_reset_time;
+	__le64			seq;
 };
 
 #define BCH_MEMBER_V1_BYTES	56
@@ -1436,7 +1450,7 @@ struct bch_sb_field_replicas_v0 {
 	struct bch_replicas_entry_v0 entries[];
 } __packed __aligned(8);
 
-struct bch_replicas_entry {
+struct bch_replicas_entry_v1 {
 	__u8			data_type;
 	__u8			nr_devs;
 	__u8			nr_required;
@@ -1448,7 +1462,7 @@ struct bch_replicas_entry {
 
 struct bch_sb_field_replicas {
 	struct bch_sb_field	field;
-	struct bch_replicas_entry entries[];
+	struct bch_replicas_entry_v1 entries[];
 } __packed __aligned(8);
 
 /* BCH_SB_FIELD_quota: */
@@ -1528,7 +1542,7 @@ struct bch_sb_field_disk_groups {
 	x(move_extent_write,				36)	\
 	x(move_extent_finish,				37)	\
 	x(move_extent_fail,				38)	\
-	x(move_extent_alloc_mem_fail,			39)	\
+	x(move_extent_start_fail,			39)	\
 	x(copygc,					40)	\
 	x(copygc_wait,					41)	\
 	x(gc_gens_end,					42)	\
@@ -1565,7 +1579,9 @@ struct bch_sb_field_disk_groups {
 	x(write_super,					73)	\
 	x(trans_restart_would_deadlock_recursion_limit,	74)	\
 	x(trans_restart_write_buffer_flush,		75)	\
-	x(trans_restart_split_race,			76)
+	x(trans_restart_split_race,			76)	\
+	x(write_buffer_flush_slowpath,			77)	\
+	x(write_buffer_flush_sync,			78)
 
 enum bch_persistent_counters {
 #define x(t, n, ...) BCH_COUNTER_##t,
@@ -1627,6 +1643,24 @@ struct bch_sb_field_errors {
 LE64_BITMASK(BCH_SB_ERROR_ENTRY_ID,	struct bch_sb_field_error_entry, v,  0, 16);
 LE64_BITMASK(BCH_SB_ERROR_ENTRY_NR,	struct bch_sb_field_error_entry, v, 16, 64);
 
+struct bch_sb_field_ext {
+	struct bch_sb_field	field;
+	__le64			recovery_passes_required[2];
+	__le64			errors_silent[8];
+};
+
+struct bch_sb_field_downgrade_entry {
+	__le16			version;
+	__le64			recovery_passes[2];
+	__le16			nr_errors;
+	__le16			errors[] __counted_by(nr_errors);
+} __packed __aligned(2);
+
+struct bch_sb_field_downgrade {
+	struct bch_sb_field	field;
+	struct bch_sb_field_downgrade_entry entries[];
+};
+
 /* Superblock: */
 
 /*
@@ -1638,64 +1672,41 @@ LE64_BITMASK(BCH_SB_ERROR_ENTRY_NR,	struct bch_sb_field_error_entry, v, 16, 64);
 #define BCH_VERSION_MINOR(_v)		((__u16) ((_v) & ~(~0U << 10)))
 #define BCH_VERSION(_major, _minor)	(((_major) << 10)|(_minor) << 0)
 
-#define RECOVERY_PASS_ALL_FSCK		(1ULL << 63)
-
+/*
+ * field 1:		version name
+ * field 2:		BCH_VERSION(major, minor)
+ * field 3:		recovery passess required on upgrade
+ */
 #define BCH_METADATA_VERSIONS()						\
-	x(bkey_renumber,		BCH_VERSION(0, 10),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(inode_btree_change,		BCH_VERSION(0, 11),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(snapshot,			BCH_VERSION(0, 12),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(inode_backpointers,		BCH_VERSION(0, 13),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(btree_ptr_sectors_written,	BCH_VERSION(0, 14),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(snapshot_2,			BCH_VERSION(0, 15),		\
-	  BIT_ULL(BCH_RECOVERY_PASS_fs_upgrade_for_subvolumes)|		\
-	  BIT_ULL(BCH_RECOVERY_PASS_initialize_subvolumes)|		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(reflink_p_fix,		BCH_VERSION(0, 16),		\
-	  BIT_ULL(BCH_RECOVERY_PASS_fix_reflink_p))			\
-	x(subvol_dirent,		BCH_VERSION(0, 17),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(inode_v2,			BCH_VERSION(0, 18),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(freespace,			BCH_VERSION(0, 19),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(alloc_v4,			BCH_VERSION(0, 20),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(new_data_types,		BCH_VERSION(0, 21),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(backpointers,			BCH_VERSION(0, 22),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(inode_v3,			BCH_VERSION(0, 23),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(unwritten_extents,		BCH_VERSION(0, 24),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(bucket_gens,			BCH_VERSION(0, 25),		\
-	  BIT_ULL(BCH_RECOVERY_PASS_bucket_gens_init)|			\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(lru_v2,			BCH_VERSION(0, 26),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(fragmentation_lru,		BCH_VERSION(0, 27),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(no_bps_in_alloc_keys,		BCH_VERSION(0, 28),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(snapshot_trees,		BCH_VERSION(0, 29),		\
-	  RECOVERY_PASS_ALL_FSCK)					\
-	x(major_minor,			BCH_VERSION(1,  0),		\
-	  0)								\
-	x(snapshot_skiplists,		BCH_VERSION(1,  1),		\
-	  BIT_ULL(BCH_RECOVERY_PASS_check_snapshots))			\
-	x(deleted_inodes,		BCH_VERSION(1,  2),		\
-	  BIT_ULL(BCH_RECOVERY_PASS_check_inodes))			\
-	x(rebalance_work,		BCH_VERSION(1,  3),		\
-	  BIT_ULL(BCH_RECOVERY_PASS_set_fs_needs_rebalance))
+	x(bkey_renumber,		BCH_VERSION(0, 10))		\
+	x(inode_btree_change,		BCH_VERSION(0, 11))		\
+	x(snapshot,			BCH_VERSION(0, 12))		\
+	x(inode_backpointers,		BCH_VERSION(0, 13))		\
+	x(btree_ptr_sectors_written,	BCH_VERSION(0, 14))		\
+	x(snapshot_2,			BCH_VERSION(0, 15))		\
+	x(reflink_p_fix,		BCH_VERSION(0, 16))		\
+	x(subvol_dirent,		BCH_VERSION(0, 17))		\
+	x(inode_v2,			BCH_VERSION(0, 18))		\
+	x(freespace,			BCH_VERSION(0, 19))		\
+	x(alloc_v4,			BCH_VERSION(0, 20))		\
+	x(new_data_types,		BCH_VERSION(0, 21))		\
+	x(backpointers,			BCH_VERSION(0, 22))		\
+	x(inode_v3,			BCH_VERSION(0, 23))		\
+	x(unwritten_extents,		BCH_VERSION(0, 24))		\
+	x(bucket_gens,			BCH_VERSION(0, 25))		\
+	x(lru_v2,			BCH_VERSION(0, 26))		\
+	x(fragmentation_lru,		BCH_VERSION(0, 27))		\
+	x(no_bps_in_alloc_keys,		BCH_VERSION(0, 28))		\
+	x(snapshot_trees,		BCH_VERSION(0, 29))		\
+	x(major_minor,			BCH_VERSION(1,  0))		\
+	x(snapshot_skiplists,		BCH_VERSION(1,  1))		\
+	x(deleted_inodes,		BCH_VERSION(1,  2))		\
+	x(rebalance_work,		BCH_VERSION(1,  3))		\
+	x(member_seq,			BCH_VERSION(1,  4))
 
 enum bcachefs_metadata_version {
 	bcachefs_metadata_version_min = 9,
-#define x(t, n, upgrade_passes)	bcachefs_metadata_version_##t = n,
+#define x(t, n)	bcachefs_metadata_version_##t = n,
 	BCH_METADATA_VERSIONS()
 #undef x
 	bcachefs_metadata_version_max
@@ -1757,7 +1768,8 @@ struct bch_sb {
 	__le32			time_base_hi;
 	__le32			time_precision;
 
-	__le64			flags[8];
+	__le64			flags[7];
+	__le64			write_time;
 	__le64			features[2];
 	__le64			compat[2];
 
@@ -2124,7 +2136,8 @@ static inline __u64 __bset_magic(struct bch_sb *sb)
 	x(clock,		7)		\
 	x(dev_usage,		8)		\
 	x(log,			9)		\
-	x(overwrite,		10)
+	x(overwrite,		10)		\
+	x(write_buffer_keys,	11)
 
 enum {
 #define x(f, nr)	BCH_JSET_ENTRY_##f	= nr,
@@ -2133,6 +2146,19 @@ enum {
 	BCH_JSET_ENTRY_NR
 };
 
+static inline bool jset_entry_is_key(struct jset_entry *e)
+{
+	switch (e->type) {
+	case BCH_JSET_ENTRY_btree_keys:
+	case BCH_JSET_ENTRY_btree_root:
+	case BCH_JSET_ENTRY_overwrite:
+	case BCH_JSET_ENTRY_write_buffer_keys:
+		return true;
+	}
+
+	return false;
+}
+
 /*
  * Journal sequence numbers can be blacklisted: bsets record the max sequence
  * number of all the journal entries they contain updates for, so that on
@@ -2174,7 +2200,7 @@ struct jset_entry_usage {
 struct jset_entry_data_usage {
 	struct jset_entry	entry;
 	__le64			v;
-	struct bch_replicas_entry r;
+	struct bch_replicas_entry_v1 r;
 } __packed;
 
 struct jset_entry_clock {
@@ -2195,8 +2221,8 @@ struct jset_entry_dev_usage {
 	__le32			dev;
 	__u32			pad;
 
-	__le64			buckets_ec;
-	__le64			_buckets_unavailable; /* No longer used */
+	__le64			_buckets_ec;		/* No longer used */
+	__le64			_buckets_unavailable;	/* No longer used */
 
 	struct jset_entry_dev_usage_type d[];
 };
@@ -2210,7 +2236,7 @@ static inline unsigned jset_entry_dev_usage_nr_types(struct jset_entry_dev_usage
 struct jset_entry_log {
 	struct jset_entry	entry;
 	u8			d[];
-} __packed;
+} __packed __aligned(8);
 
 /*
  * On disk format for a journal entry:
diff --git a/fs/bcachefs/bcachefs_ioctl.h b/fs/bcachefs/bcachefs_ioctl.h
index f05881f7e113..4b8fba754b1c 100644
--- a/fs/bcachefs/bcachefs_ioctl.h
+++ b/fs/bcachefs/bcachefs_ioctl.h
@@ -81,6 +81,11 @@ struct bch_ioctl_incremental {
 #define BCH_IOCTL_SUBVOLUME_CREATE _IOW(0xbc,	16,  struct bch_ioctl_subvolume)
 #define BCH_IOCTL_SUBVOLUME_DESTROY _IOW(0xbc,	17,  struct bch_ioctl_subvolume)
 
+#define BCH_IOCTL_DEV_USAGE_V2	_IOWR(0xbc,	18, struct bch_ioctl_dev_usage_v2)
+
+#define BCH_IOCTL_FSCK_OFFLINE	_IOW(0xbc,	19,  struct bch_ioctl_fsck_offline)
+#define BCH_IOCTL_FSCK_ONLINE	_IOW(0xbc,	20,  struct bch_ioctl_fsck_online)
+
 /* ioctl below act on a particular file, not the filesystem as a whole: */
 
 #define BCHFS_IOC_REINHERIT_ATTRS	_IOR(0xbc, 64, const char __user *)
@@ -173,12 +178,18 @@ struct bch_ioctl_disk_set_state {
 	__u64			dev;
 };
 
+#define BCH_DATA_OPS()			\
+	x(scrub,		0)	\
+	x(rereplicate,		1)	\
+	x(migrate,		2)	\
+	x(rewrite_old_nodes,	3)	\
+	x(drop_extra_replicas,	4)
+
 enum bch_data_ops {
-	BCH_DATA_OP_SCRUB		= 0,
-	BCH_DATA_OP_REREPLICATE		= 1,
-	BCH_DATA_OP_MIGRATE		= 2,
-	BCH_DATA_OP_REWRITE_OLD_NODES	= 3,
-	BCH_DATA_OP_NR			= 4,
+#define x(t, n) BCH_DATA_OP_##t = n,
+	BCH_DATA_OPS()
+#undef x
+	BCH_DATA_OP_NR
 };
 
 /*
@@ -237,7 +248,7 @@ struct bch_ioctl_data_event {
 
 struct bch_replicas_usage {
 	__u64			sectors;
-	struct bch_replicas_entry r;
+	struct bch_replicas_entry_v1 r;
 } __packed;
 
 static inline struct bch_replicas_usage *
@@ -268,7 +279,7 @@ struct bch_ioctl_fs_usage {
 	__u32			replica_entries_bytes;
 	__u32			pad;
 
-	struct bch_replicas_usage replicas[0];
+	struct bch_replicas_usage replicas[];
 };
 
 /*
@@ -292,7 +303,20 @@ struct bch_ioctl_dev_usage {
 		__u64		buckets;
 		__u64		sectors;
 		__u64		fragmented;
-	}			d[BCH_DATA_NR];
+	}			d[10];
+};
+
+struct bch_ioctl_dev_usage_v2 {
+	__u64			dev;
+	__u32			flags;
+	__u8			state;
+	__u8			nr_data_types;
+	__u8			pad[6];
+
+	__u32			bucket_size;
+	__u64			nr_buckets;
+
+	struct bch_ioctl_dev_usage_type d[];
 };
 
 /*
@@ -365,4 +389,24 @@ struct bch_ioctl_subvolume {
 #define BCH_SUBVOL_SNAPSHOT_CREATE	(1U << 0)
 #define BCH_SUBVOL_SNAPSHOT_RO		(1U << 1)
 
+/*
+ * BCH_IOCTL_FSCK_OFFLINE: run fsck from the 'bcachefs fsck' userspace command,
+ * but with the kernel's implementation of fsck:
+ */
+struct bch_ioctl_fsck_offline {
+	__u64			flags;
+	__u64			opts;		/* string */
+	__u64			nr_devs;
+	__u64			devs[] __counted_by(nr_devs);
+};
+
+/*
+ * BCH_IOCTL_FSCK_ONLINE: run fsck from the 'bcachefs fsck' userspace command,
+ * but with the kernel's implementation of fsck:
+ */
+struct bch_ioctl_fsck_online {
+	__u64			flags;
+	__u64			opts;		/* string */
+};
+
 #endif /* _BCACHEFS_IOCTL_H */
diff --git a/fs/bcachefs/bkey_methods.h b/fs/bcachefs/bkey_methods.h
index 3a370b7087ac..ee82283722b7 100644
--- a/fs/bcachefs/bkey_methods.h
+++ b/fs/bcachefs/bkey_methods.h
@@ -28,10 +28,8 @@ struct bkey_ops {
 	void		(*swab)(struct bkey_s);
 	bool		(*key_normalize)(struct bch_fs *, struct bkey_s);
 	bool		(*key_merge)(struct bch_fs *, struct bkey_s, struct bkey_s_c);
-	int		(*trans_trigger)(struct btree_trans *, enum btree_id, unsigned,
-					 struct bkey_s_c, struct bkey_i *, unsigned);
-	int		(*atomic_trigger)(struct btree_trans *, enum btree_id, unsigned,
-					  struct bkey_s_c, struct bkey_s_c, unsigned);
+	int		(*trigger)(struct btree_trans *, enum btree_id, unsigned,
+				   struct bkey_s_c, struct bkey_s, unsigned);
 	void		(*compat)(enum btree_id id, unsigned version,
 				  unsigned big_endian, int write,
 				  struct bkey_s);
@@ -78,84 +76,86 @@ static inline bool bch2_bkey_maybe_mergable(const struct bkey *l, const struct b
 
 bool bch2_bkey_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c);
 
-static inline int bch2_mark_key(struct btree_trans *trans,
-		enum btree_id btree, unsigned level,
-		struct bkey_s_c old, struct bkey_s_c new,
-		unsigned flags)
-{
-	const struct bkey_ops *ops = bch2_bkey_type_ops(old.k->type ?: new.k->type);
-
-	return ops->atomic_trigger
-		? ops->atomic_trigger(trans, btree, level, old, new, flags)
-		: 0;
-}
-
 enum btree_update_flags {
 	__BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE = __BTREE_ITER_FLAGS_END,
 	__BTREE_UPDATE_NOJOURNAL,
-	__BTREE_UPDATE_PREJOURNAL,
 	__BTREE_UPDATE_KEY_CACHE_RECLAIM,
 
-	__BTREE_TRIGGER_NORUN,		/* Don't run triggers at all */
-
+	__BTREE_TRIGGER_NORUN,
+	__BTREE_TRIGGER_TRANSACTIONAL,
 	__BTREE_TRIGGER_INSERT,
 	__BTREE_TRIGGER_OVERWRITE,
-
 	__BTREE_TRIGGER_GC,
 	__BTREE_TRIGGER_BUCKET_INVALIDATE,
-	__BTREE_TRIGGER_NOATOMIC,
 };
 
 #define BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE (1U << __BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE)
 #define BTREE_UPDATE_NOJOURNAL		(1U << __BTREE_UPDATE_NOJOURNAL)
-#define BTREE_UPDATE_PREJOURNAL		(1U << __BTREE_UPDATE_PREJOURNAL)
 #define BTREE_UPDATE_KEY_CACHE_RECLAIM	(1U << __BTREE_UPDATE_KEY_CACHE_RECLAIM)
 
+/* Don't run triggers at all */
 #define BTREE_TRIGGER_NORUN		(1U << __BTREE_TRIGGER_NORUN)
 
+/*
+ * If set, we're running transactional triggers as part of a transaction commit:
+ * triggers may generate new updates
+ *
+ * If cleared, and either BTREE_TRIGGER_INSERT|BTREE_TRIGGER_OVERWRITE are set,
+ * we're running atomic triggers during a transaction commit: we have our
+ * journal reservation, we're holding btree node write locks, and we know the
+ * transaction is going to commit (returning an error here is a fatal error,
+ * causing us to go emergency read-only)
+ */
+#define BTREE_TRIGGER_TRANSACTIONAL	(1U << __BTREE_TRIGGER_TRANSACTIONAL)
+
+/* @new is entering the btree */
 #define BTREE_TRIGGER_INSERT		(1U << __BTREE_TRIGGER_INSERT)
+
+/* @old is leaving the btree */
 #define BTREE_TRIGGER_OVERWRITE		(1U << __BTREE_TRIGGER_OVERWRITE)
 
+/* We're in gc/fsck: running triggers to recalculate e.g. disk usage */
 #define BTREE_TRIGGER_GC		(1U << __BTREE_TRIGGER_GC)
+
+/* signal from bucket invalidate path to alloc trigger */
 #define BTREE_TRIGGER_BUCKET_INVALIDATE	(1U << __BTREE_TRIGGER_BUCKET_INVALIDATE)
-#define BTREE_TRIGGER_NOATOMIC		(1U << __BTREE_TRIGGER_NOATOMIC)
 
-static inline int bch2_trans_mark_key(struct btree_trans *trans,
-				      enum btree_id btree_id, unsigned level,
-				      struct bkey_s_c old, struct bkey_i *new,
-				      unsigned flags)
+static inline int bch2_key_trigger(struct btree_trans *trans,
+		enum btree_id btree, unsigned level,
+		struct bkey_s_c old, struct bkey_s new,
+		unsigned flags)
 {
-	const struct bkey_ops *ops = bch2_bkey_type_ops(old.k->type ?: new->k.type);
+	const struct bkey_ops *ops = bch2_bkey_type_ops(old.k->type ?: new.k->type);
 
-	return ops->trans_trigger
-		? ops->trans_trigger(trans, btree_id, level, old, new, flags)
+	return ops->trigger
+		? ops->trigger(trans, btree, level, old, new, flags)
 		: 0;
 }
 
-static inline int bch2_trans_mark_old(struct btree_trans *trans,
-				      enum btree_id btree_id, unsigned level,
-				      struct bkey_s_c old, unsigned flags)
+static inline int bch2_key_trigger_old(struct btree_trans *trans,
+				       enum btree_id btree_id, unsigned level,
+				       struct bkey_s_c old, unsigned flags)
 {
 	struct bkey_i deleted;
 
 	bkey_init(&deleted.k);
 	deleted.k.p = old.k->p;
 
-	return bch2_trans_mark_key(trans, btree_id, level, old, &deleted,
-				   BTREE_TRIGGER_OVERWRITE|flags);
+	return bch2_key_trigger(trans, btree_id, level, old, bkey_i_to_s(&deleted),
+				BTREE_TRIGGER_OVERWRITE|flags);
 }
 
-static inline int bch2_trans_mark_new(struct btree_trans *trans,
-				      enum btree_id btree_id, unsigned level,
-				      struct bkey_i *new, unsigned flags)
+static inline int bch2_key_trigger_new(struct btree_trans *trans,
+				       enum btree_id btree_id, unsigned level,
+				       struct bkey_s new, unsigned flags)
 {
 	struct bkey_i deleted;
 
 	bkey_init(&deleted.k);
-	deleted.k.p = new->k.p;
+	deleted.k.p = new.k->p;
 
-	return bch2_trans_mark_key(trans, btree_id, level, bkey_i_to_s_c(&deleted), new,
-				   BTREE_TRIGGER_INSERT|flags);
+	return bch2_key_trigger(trans, btree_id, level, bkey_i_to_s_c(&deleted), new,
+				BTREE_TRIGGER_INSERT|flags);
 }
 
 void bch2_bkey_renumber(enum btree_node_type, struct bkey_packed *, int);
diff --git a/fs/bcachefs/bset.c b/fs/bcachefs/bset.c
index bb73ba9017b0..74bf8eb90a4c 100644
--- a/fs/bcachefs/bset.c
+++ b/fs/bcachefs/bset.c
@@ -68,6 +68,12 @@ void bch2_dump_bset(struct bch_fs *c, struct btree *b,
 	     _k = _n) {
 		_n = bkey_p_next(_k);
 
+		if (!_k->u64s) {
+			printk(KERN_ERR "block %u key %5zu - u64s 0? aieee!\n", set,
+			       _k->_data - i->_data);
+			break;
+		}
+
 		k = bkey_disassemble(b, _k, &uk);
 
 		printbuf_reset(&buf);
diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c
index 47e7770d0583..8e2488a4b58d 100644
--- a/fs/bcachefs/btree_cache.c
+++ b/fs/bcachefs/btree_cache.c
@@ -9,6 +9,7 @@
 #include "debug.h"
 #include "errcode.h"
 #include "error.h"
+#include "journal.h"
 #include "trace.h"
 
 #include <linux/prefetch.h>
@@ -424,14 +425,11 @@ void bch2_fs_btree_cache_exit(struct bch_fs *c)
 		BUG_ON(btree_node_read_in_flight(b) ||
 		       btree_node_write_in_flight(b));
 
-		if (btree_node_dirty(b))
-			bch2_btree_complete_write(c, b, btree_current_write(b));
-		clear_btree_node_dirty_acct(c, b);
-
 		btree_node_data_free(c, b);
 	}
 
-	BUG_ON(atomic_read(&c->btree_cache.dirty));
+	BUG_ON(!bch2_journal_error(&c->journal) &&
+	       atomic_read(&c->btree_cache.dirty));
 
 	list_splice(&bc->freed_pcpu, &bc->freed_nonpcpu);
 
@@ -502,19 +500,21 @@ void bch2_fs_btree_cache_init_early(struct btree_cache *bc)
  * cannibalize_bucket() will take. This means every time we unlock the root of
  * the btree, we need to release this lock if we have it held.
  */
-void bch2_btree_cache_cannibalize_unlock(struct bch_fs *c)
+void bch2_btree_cache_cannibalize_unlock(struct btree_trans *trans)
 {
+	struct bch_fs *c = trans->c;
 	struct btree_cache *bc = &c->btree_cache;
 
 	if (bc->alloc_lock == current) {
-		trace_and_count(c, btree_cache_cannibalize_unlock, c);
+		trace_and_count(c, btree_cache_cannibalize_unlock, trans);
 		bc->alloc_lock = NULL;
 		closure_wake_up(&bc->alloc_wait);
 	}
 }
 
-int bch2_btree_cache_cannibalize_lock(struct bch_fs *c, struct closure *cl)
+int bch2_btree_cache_cannibalize_lock(struct btree_trans *trans, struct closure *cl)
 {
+	struct bch_fs *c = trans->c;
 	struct btree_cache *bc = &c->btree_cache;
 	struct task_struct *old;
 
@@ -523,7 +523,7 @@ int bch2_btree_cache_cannibalize_lock(struct bch_fs *c, struct closure *cl)
 		goto success;
 
 	if (!cl) {
-		trace_and_count(c, btree_cache_cannibalize_lock_fail, c);
+		trace_and_count(c, btree_cache_cannibalize_lock_fail, trans);
 		return -BCH_ERR_ENOMEM_btree_cache_cannibalize_lock;
 	}
 
@@ -537,11 +537,11 @@ int bch2_btree_cache_cannibalize_lock(struct bch_fs *c, struct closure *cl)
 		goto success;
 	}
 
-	trace_and_count(c, btree_cache_cannibalize_lock_fail, c);
+	trace_and_count(c, btree_cache_cannibalize_lock_fail, trans);
 	return -BCH_ERR_btree_cache_cannibalize_lock_blocked;
 
 success:
-	trace_and_count(c, btree_cache_cannibalize_lock, c);
+	trace_and_count(c, btree_cache_cannibalize_lock, trans);
 	return 0;
 }
 
@@ -675,7 +675,7 @@ err:
 
 		mutex_unlock(&bc->lock);
 
-		trace_and_count(c, btree_cache_cannibalize, c);
+		trace_and_count(c, btree_cache_cannibalize, trans);
 		goto out;
 	}
 
@@ -719,12 +719,6 @@ static noinline struct btree *bch2_btree_node_fill(struct btree_trans *trans,
 	if (IS_ERR(b))
 		return b;
 
-	/*
-	 * Btree nodes read in from disk should not have the accessed bit set
-	 * initially, so that linear scans don't thrash the cache:
-	 */
-	clear_btree_node_accessed(b);
-
 	bkey_copy(&b->key, k);
 	if (bch2_btree_node_hash_insert(bc, b, level, btree_id)) {
 		/* raced with another fill: */
@@ -751,7 +745,7 @@ static noinline struct btree *bch2_btree_node_fill(struct btree_trans *trans,
 	if (path && sync)
 		bch2_trans_unlock_noassert(trans);
 
-	bch2_btree_node_read(c, b, sync);
+	bch2_btree_node_read(trans, b, sync);
 
 	if (!sync)
 		return NULL;
@@ -1041,7 +1035,7 @@ retry:
 			goto retry;
 
 		if (IS_ERR(b) &&
-		    !bch2_btree_cache_cannibalize_lock(c, NULL))
+		    !bch2_btree_cache_cannibalize_lock(trans, NULL))
 			goto retry;
 
 		if (IS_ERR(b))
@@ -1089,7 +1083,7 @@ lock_node:
 	EBUG_ON(BTREE_NODE_LEVEL(b->data) != level);
 	btree_check_header(c, b);
 out:
-	bch2_btree_cache_cannibalize_unlock(c);
+	bch2_btree_cache_cannibalize_unlock(trans);
 	return b;
 }
 
diff --git a/fs/bcachefs/btree_cache.h b/fs/bcachefs/btree_cache.h
index cfb80b201d61..4e1af5882052 100644
--- a/fs/bcachefs/btree_cache.h
+++ b/fs/bcachefs/btree_cache.h
@@ -17,8 +17,8 @@ int __bch2_btree_node_hash_insert(struct btree_cache *, struct btree *);
 int bch2_btree_node_hash_insert(struct btree_cache *, struct btree *,
 				unsigned, enum btree_id);
 
-void bch2_btree_cache_cannibalize_unlock(struct bch_fs *);
-int bch2_btree_cache_cannibalize_lock(struct bch_fs *, struct closure *);
+void bch2_btree_cache_cannibalize_unlock(struct btree_trans *);
+int bch2_btree_cache_cannibalize_lock(struct btree_trans *, struct closure *);
 
 struct btree *__bch2_btree_node_mem_alloc(struct bch_fs *);
 struct btree *bch2_btree_node_mem_alloc(struct btree_trans *, bool);
diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index 0b5d09c8475d..49b4ade758c3 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -41,6 +41,14 @@
 #define DROP_THIS_NODE		10
 #define DROP_PREV_NODE		11
 
+static struct bkey_s unsafe_bkey_s_c_to_s(struct bkey_s_c k)
+{
+	return (struct bkey_s) {{{
+		(struct bkey *) k.k,
+		(struct bch_val *) k.v
+	}}};
+}
+
 static bool should_restart_for_topology_repair(struct bch_fs *c)
 {
 	return c->opts.fix_errors != FSCK_FIX_no &&
@@ -108,7 +116,7 @@ static int bch2_gc_check_topology(struct bch_fs *c,
 				ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_topology);
 				goto err;
 			} else {
-				set_bit(BCH_FS_INITIAL_GC_UNFIXED, &c->flags);
+				set_bit(BCH_FS_initial_gc_unfixed, &c->flags);
 			}
 		}
 	}
@@ -134,7 +142,7 @@ static int bch2_gc_check_topology(struct bch_fs *c,
 			ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_topology);
 			goto err;
 		} else {
-			set_bit(BCH_FS_INITIAL_GC_UNFIXED, &c->flags);
+			set_bit(BCH_FS_initial_gc_unfixed, &c->flags);
 		}
 	}
 
@@ -414,10 +422,9 @@ again:
 			continue;
 		}
 
-		if (ret) {
-			bch_err_msg(c, ret, "getting btree node");
+		bch_err_msg(c, ret, "getting btree node");
+		if (ret)
 			break;
-		}
 
 		ret = btree_repair_node_boundaries(c, b, prev, cur);
 
@@ -482,10 +489,9 @@ again:
 					false);
 		ret = PTR_ERR_OR_ZERO(cur);
 
-		if (ret) {
-			bch_err_msg(c, ret, "getting btree node");
+		bch_err_msg(c, ret, "getting btree node");
+		if (ret)
 			goto err;
-		}
 
 		ret = bch2_btree_repair_topology_recurse(trans, cur);
 		six_unlock_read(&cur->c.lock);
@@ -619,7 +625,7 @@ static int bch2_check_fix_ptrs(struct btree_trans *trans, enum btree_id btree_id
 				g->data_type		= 0;
 				g->dirty_sectors	= 0;
 				g->cached_sectors	= 0;
-				set_bit(BCH_FS_NEED_ANOTHER_GC, &c->flags);
+				set_bit(BCH_FS_need_another_gc, &c->flags);
 			} else {
 				do_update = true;
 			}
@@ -664,7 +670,7 @@ static int bch2_check_fix_ptrs(struct btree_trans *trans, enum btree_id btree_id
 				 bch2_bkey_val_to_text(&buf, c, *k), buf.buf))) {
 			if (data_type == BCH_DATA_btree) {
 				g->data_type	= data_type;
-				set_bit(BCH_FS_NEED_ANOTHER_GC, &c->flags);
+				set_bit(BCH_FS_need_another_gc, &c->flags);
 			} else {
 				do_update = true;
 			}
@@ -707,8 +713,8 @@ static int bch2_check_fix_ptrs(struct btree_trans *trans, enum btree_id btree_id
 
 		new = kmalloc(bkey_bytes(k->k), GFP_KERNEL);
 		if (!new) {
-			bch_err_msg(c, ret, "allocating new key");
 			ret = -BCH_ERR_ENOMEM_gc_repair_key;
+			bch_err_msg(c, ret, "allocating new key");
 			goto err;
 		}
 
@@ -807,9 +813,6 @@ static int bch2_gc_mark_key(struct btree_trans *trans, enum btree_id btree_id,
 	struct bch_fs *c = trans->c;
 	struct bkey deleted = KEY(0, 0, 0);
 	struct bkey_s_c old = (struct bkey_s_c) { &deleted, NULL };
-	unsigned flags =
-		BTREE_TRIGGER_GC|
-		(initial ? BTREE_TRIGGER_NOATOMIC : 0);
 	int ret = 0;
 
 	deleted.p = k->k->p;
@@ -831,11 +834,10 @@ static int bch2_gc_mark_key(struct btree_trans *trans, enum btree_id btree_id,
 	}
 
 	ret = commit_do(trans, NULL, NULL, 0,
-			bch2_mark_key(trans, btree_id, level, old, *k, flags));
+			bch2_key_trigger(trans, btree_id, level, old, unsafe_bkey_s_c_to_s(*k), BTREE_TRIGGER_GC));
 fsck_err:
 err:
-	if (ret)
-		bch_err_fn(c, ret);
+	bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -996,7 +998,7 @@ static int bch2_gc_btree_init_recurse(struct btree_trans *trans, struct btree *b
 					/* Continue marking when opted to not
 					 * fix the error: */
 					ret = 0;
-					set_bit(BCH_FS_INITIAL_GC_UNFIXED, &c->flags);
+					set_bit(BCH_FS_initial_gc_unfixed, &c->flags);
 					continue;
 				}
 			} else if (ret) {
@@ -1068,8 +1070,7 @@ static int bch2_gc_btree_init(struct btree_trans *trans,
 fsck_err:
 	six_unlock_read(&b->c.lock);
 
-	if (ret < 0)
-		bch_err_fn(c, ret);
+	bch_err_fn(c, ret);
 	printbuf_exit(&buf);
 	return ret;
 }
@@ -1105,10 +1106,8 @@ static int bch2_gc_btrees(struct bch_fs *c, bool initial, bool metadata_only)
 			: bch2_gc_btree(trans, i, initial, metadata_only);
 	}
 
-	if (ret < 0)
-		bch_err_fn(c, ret);
-
 	bch2_trans_put(trans);
+	bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -1159,13 +1158,10 @@ static void bch2_mark_dev_superblock(struct bch_fs *c, struct bch_dev *ca,
 
 static void bch2_mark_superblocks(struct bch_fs *c)
 {
-	struct bch_dev *ca;
-	unsigned i;
-
 	mutex_lock(&c->sb_lock);
 	gc_pos_set(c, gc_phase(GC_PHASE_SB));
 
-	for_each_online_member(ca, c, i)
+	for_each_online_member(c, ca)
 		bch2_mark_dev_superblock(c, ca, BTREE_TRIGGER_GC);
 	mutex_unlock(&c->sb_lock);
 }
@@ -1190,13 +1186,10 @@ static void bch2_mark_pending_btree_node_frees(struct bch_fs *c)
 
 static void bch2_gc_free(struct bch_fs *c)
 {
-	struct bch_dev *ca;
-	unsigned i;
-
 	genradix_free(&c->reflink_gc_table);
 	genradix_free(&c->gc_stripes);
 
-	for_each_member_device(ca, c, i) {
+	for_each_member_device(c, ca) {
 		kvpfree(rcu_dereference_protected(ca->buckets_gc, 1),
 			sizeof(struct bucket_array) +
 			ca->mi.nbuckets * sizeof(struct bucket));
@@ -1218,7 +1211,7 @@ static int bch2_gc_done(struct bch_fs *c,
 	bool verify = !metadata_only &&
 		!c->opts.reconstruct_alloc &&
 		(!initial || (c->sb.compat & (1ULL << BCH_COMPAT_alloc_info)));
-	unsigned i, dev;
+	unsigned i;
 	int ret = 0;
 
 	percpu_down_write(&c->mark_lock);
@@ -1230,14 +1223,14 @@ static int bch2_gc_done(struct bch_fs *c,
 		      , ##__VA_ARGS__, dst->_f, src->_f)))		\
 		dst->_f = src->_f
 #define copy_dev_field(_err, _f, _msg, ...)				\
-	copy_field(_err, _f, "dev %u has wrong " _msg, dev, ##__VA_ARGS__)
+	copy_field(_err, _f, "dev %u has wrong " _msg, ca->dev_idx, ##__VA_ARGS__)
 #define copy_fs_field(_err, _f, _msg, ...)				\
 	copy_field(_err, _f, "fs has wrong " _msg, ##__VA_ARGS__)
 
 	for (i = 0; i < ARRAY_SIZE(c->usage); i++)
 		bch2_fs_usage_acc_to_base(c, i);
 
-	for_each_member_device(ca, c, dev) {
+	__for_each_member_device(c, ca) {
 		struct bch_dev_usage *dst = ca->usage_base;
 		struct bch_dev_usage *src = (void *)
 			bch2_acc_percpu_u64s((u64 __percpu *) ca->usage_gc,
@@ -1251,9 +1244,6 @@ static int bch2_gc_done(struct bch_fs *c,
 			copy_dev_field(dev_usage_fragmented_wrong,
 				       d[i].fragmented,	"%s fragmented", bch2_data_types[i]);
 		}
-
-		copy_dev_field(dev_usage_buckets_ec_wrong,
-			       buckets_ec,		"buckets_ec");
 	}
 
 	{
@@ -1284,7 +1274,7 @@ static int bch2_gc_done(struct bch_fs *c,
 		}
 
 		for (i = 0; i < c->replicas.nr; i++) {
-			struct bch_replicas_entry *e =
+			struct bch_replicas_entry_v1 *e =
 				cpu_replicas_entry(&c->replicas, i);
 
 			if (metadata_only &&
@@ -1307,8 +1297,7 @@ static int bch2_gc_done(struct bch_fs *c,
 fsck_err:
 	if (ca)
 		percpu_ref_put(&ca->ref);
-	if (ret)
-		bch_err_fn(c, ret);
+	bch_err_fn(c, ret);
 
 	percpu_up_write(&c->mark_lock);
 	printbuf_exit(&buf);
@@ -1317,9 +1306,6 @@ fsck_err:
 
 static int bch2_gc_start(struct bch_fs *c)
 {
-	struct bch_dev *ca = NULL;
-	unsigned i;
-
 	BUG_ON(c->usage_gc);
 
 	c->usage_gc = __alloc_percpu_gfp(fs_usage_u64s(c) * sizeof(u64),
@@ -1329,7 +1315,7 @@ static int bch2_gc_start(struct bch_fs *c)
 		return -BCH_ERR_ENOMEM_gc_start;
 	}
 
-	for_each_member_device(ca, c, i) {
+	for_each_member_device(c, ca) {
 		BUG_ON(ca->usage_gc);
 
 		ca->usage_gc = alloc_percpu(struct bch_dev_usage);
@@ -1348,10 +1334,7 @@ static int bch2_gc_start(struct bch_fs *c)
 
 static int bch2_gc_reset(struct bch_fs *c)
 {
-	struct bch_dev *ca;
-	unsigned i;
-
-	for_each_member_device(ca, c, i) {
+	for_each_member_device(c, ca) {
 		free_percpu(ca->usage_gc);
 		ca->usage_gc = NULL;
 	}
@@ -1389,9 +1372,6 @@ static int bch2_alloc_write_key(struct btree_trans *trans,
 	enum bch_data_type type;
 	int ret;
 
-	if (bkey_ge(iter->pos, POS(ca->dev_idx, ca->mi.nbuckets)))
-		return 1;
-
 	old = bch2_alloc_to_v4(k, &old_convert);
 	new = *old;
 
@@ -1488,52 +1468,36 @@ fsck_err:
 
 static int bch2_gc_alloc_done(struct bch_fs *c, bool metadata_only)
 {
-	struct btree_trans *trans = bch2_trans_get(c);
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	struct bch_dev *ca;
-	unsigned i;
 	int ret = 0;
 
-	for_each_member_device(ca, c, i) {
-		ret = for_each_btree_key_commit(trans, iter, BTREE_ID_alloc,
-				POS(ca->dev_idx, ca->mi.first_bucket),
-				BTREE_ITER_SLOTS|BTREE_ITER_PREFETCH, k,
-				NULL, NULL, BTREE_INSERT_LAZY_RW,
-			bch2_alloc_write_key(trans, &iter, k, metadata_only));
-
-		if (ret < 0) {
-			bch_err_fn(c, ret);
+	for_each_member_device(c, ca) {
+		ret = bch2_trans_run(c,
+			for_each_btree_key_upto_commit(trans, iter, BTREE_ID_alloc,
+					POS(ca->dev_idx, ca->mi.first_bucket),
+					POS(ca->dev_idx, ca->mi.nbuckets - 1),
+					BTREE_ITER_SLOTS|BTREE_ITER_PREFETCH, k,
+					NULL, NULL, BCH_TRANS_COMMIT_lazy_rw,
+				bch2_alloc_write_key(trans, &iter, k, metadata_only)));
+		if (ret) {
 			percpu_ref_put(&ca->ref);
 			break;
 		}
 	}
 
-	bch2_trans_put(trans);
-	return ret < 0 ? ret : 0;
+	bch_err_fn(c, ret);
+	return ret;
 }
 
 static int bch2_gc_alloc_start(struct bch_fs *c, bool metadata_only)
 {
-	struct bch_dev *ca;
-	struct btree_trans *trans = bch2_trans_get(c);
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	struct bucket *g;
-	struct bch_alloc_v4 a_convert;
-	const struct bch_alloc_v4 *a;
-	unsigned i;
-	int ret;
-
-	for_each_member_device(ca, c, i) {
+	for_each_member_device(c, ca) {
 		struct bucket_array *buckets = kvpmalloc(sizeof(struct bucket_array) +
 				ca->mi.nbuckets * sizeof(struct bucket),
 				GFP_KERNEL|__GFP_ZERO);
 		if (!buckets) {
 			percpu_ref_put(&ca->ref);
 			bch_err(c, "error allocating ca->buckets[gc]");
-			ret = -BCH_ERR_ENOMEM_gc_alloc_start;
-			goto err;
+			return -BCH_ERR_ENOMEM_gc_alloc_start;
 		}
 
 		buckets->first_bucket	= ca->mi.first_bucket;
@@ -1541,41 +1505,38 @@ static int bch2_gc_alloc_start(struct bch_fs *c, bool metadata_only)
 		rcu_assign_pointer(ca->buckets_gc, buckets);
 	}
 
-	for_each_btree_key(trans, iter, BTREE_ID_alloc, POS_MIN,
-			   BTREE_ITER_PREFETCH, k, ret) {
-		ca = bch_dev_bkey_exists(c, k.k->p.inode);
-		g = gc_bucket(ca, k.k->p.offset);
-
-		a = bch2_alloc_to_v4(k, &a_convert);
-
-		g->gen_valid	= 1;
-		g->gen		= a->gen;
-
-		if (metadata_only &&
-		    (a->data_type == BCH_DATA_user ||
-		     a->data_type == BCH_DATA_cached ||
-		     a->data_type == BCH_DATA_parity)) {
-			g->data_type		= a->data_type;
-			g->dirty_sectors	= a->dirty_sectors;
-			g->cached_sectors	= a->cached_sectors;
-			g->stripe		= a->stripe;
-			g->stripe_redundancy	= a->stripe_redundancy;
-		}
-	}
-	bch2_trans_iter_exit(trans, &iter);
-err:
-	bch2_trans_put(trans);
-	if (ret)
-		bch_err_fn(c, ret);
+	int ret = bch2_trans_run(c,
+		for_each_btree_key(trans, iter, BTREE_ID_alloc, POS_MIN,
+					 BTREE_ITER_PREFETCH, k, ({
+			struct bch_dev *ca = bch_dev_bkey_exists(c, k.k->p.inode);
+			struct bucket *g = gc_bucket(ca, k.k->p.offset);
+
+			struct bch_alloc_v4 a_convert;
+			const struct bch_alloc_v4 *a = bch2_alloc_to_v4(k, &a_convert);
+
+			g->gen_valid	= 1;
+			g->gen		= a->gen;
+
+			if (metadata_only &&
+			    (a->data_type == BCH_DATA_user ||
+			     a->data_type == BCH_DATA_cached ||
+			     a->data_type == BCH_DATA_parity)) {
+				g->data_type		= a->data_type;
+				g->dirty_sectors	= a->dirty_sectors;
+				g->cached_sectors	= a->cached_sectors;
+				g->stripe		= a->stripe;
+				g->stripe_redundancy	= a->stripe_redundancy;
+			}
+
+			0;
+		})));
+	bch_err_fn(c, ret);
 	return ret;
 }
 
 static void bch2_gc_alloc_reset(struct bch_fs *c, bool metadata_only)
 {
-	struct bch_dev *ca;
-	unsigned i;
-
-	for_each_member_device(ca, c, i) {
+	for_each_member_device(c, ca) {
 		struct bucket_array *buckets = gc_bucket_array(ca);
 		struct bucket *g;
 
@@ -1633,7 +1594,7 @@ static int bch2_gc_write_reflink_key(struct btree_trans *trans,
 		if (!r->refcount)
 			new->k.type = KEY_TYPE_deleted;
 		else
-			*bkey_refcount(new) = cpu_to_le64(r->refcount);
+			*bkey_refcount(bkey_i_to_s(new)) = cpu_to_le64(r->refcount);
 	}
 fsck_err:
 	printbuf_exit(&buf);
@@ -1642,64 +1603,52 @@ fsck_err:
 
 static int bch2_gc_reflink_done(struct bch_fs *c, bool metadata_only)
 {
-	struct btree_trans *trans;
-	struct btree_iter iter;
-	struct bkey_s_c k;
 	size_t idx = 0;
-	int ret = 0;
 
 	if (metadata_only)
 		return 0;
 
-	trans = bch2_trans_get(c);
-
-	ret = for_each_btree_key_commit(trans, iter,
-			BTREE_ID_reflink, POS_MIN,
-			BTREE_ITER_PREFETCH, k,
-			NULL, NULL, BTREE_INSERT_NOFAIL,
-		bch2_gc_write_reflink_key(trans, &iter, k, &idx));
-
+	int ret = bch2_trans_run(c,
+		for_each_btree_key_commit(trans, iter,
+				BTREE_ID_reflink, POS_MIN,
+				BTREE_ITER_PREFETCH, k,
+				NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
+			bch2_gc_write_reflink_key(trans, &iter, k, &idx)));
 	c->reflink_gc_nr = 0;
-	bch2_trans_put(trans);
 	return ret;
 }
 
 static int bch2_gc_reflink_start(struct bch_fs *c,
 				 bool metadata_only)
 {
-	struct btree_trans *trans;
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	struct reflink_gc *r;
-	int ret = 0;
 
 	if (metadata_only)
 		return 0;
 
-	trans = bch2_trans_get(c);
 	c->reflink_gc_nr = 0;
 
-	for_each_btree_key(trans, iter, BTREE_ID_reflink, POS_MIN,
-			   BTREE_ITER_PREFETCH, k, ret) {
-		const __le64 *refcount = bkey_refcount_c(k);
+	int ret = bch2_trans_run(c,
+		for_each_btree_key(trans, iter, BTREE_ID_reflink, POS_MIN,
+				   BTREE_ITER_PREFETCH, k, ({
+			const __le64 *refcount = bkey_refcount_c(k);
 
-		if (!refcount)
-			continue;
+			if (!refcount)
+				continue;
 
-		r = genradix_ptr_alloc(&c->reflink_gc_table, c->reflink_gc_nr++,
-				       GFP_KERNEL);
-		if (!r) {
-			ret = -BCH_ERR_ENOMEM_gc_reflink_start;
-			break;
-		}
+			struct reflink_gc *r = genradix_ptr_alloc(&c->reflink_gc_table,
+							c->reflink_gc_nr++, GFP_KERNEL);
+			if (!r) {
+				ret = -BCH_ERR_ENOMEM_gc_reflink_start;
+				break;
+			}
 
-		r->offset	= k.k->p.offset;
-		r->size		= k.k->size;
-		r->refcount	= 0;
-	}
-	bch2_trans_iter_exit(trans, &iter);
+			r->offset	= k.k->p.offset;
+			r->size		= k.k->size;
+			r->refcount	= 0;
+			0;
+		})));
 
-	bch2_trans_put(trans);
+	bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -1767,24 +1716,15 @@ fsck_err:
 
 static int bch2_gc_stripes_done(struct bch_fs *c, bool metadata_only)
 {
-	struct btree_trans *trans;
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	int ret = 0;
-
 	if (metadata_only)
 		return 0;
 
-	trans = bch2_trans_get(c);
-
-	ret = for_each_btree_key_commit(trans, iter,
-			BTREE_ID_stripes, POS_MIN,
-			BTREE_ITER_PREFETCH, k,
-			NULL, NULL, BTREE_INSERT_NOFAIL,
-		bch2_gc_write_stripes_key(trans, &iter, k));
-
-	bch2_trans_put(trans);
-	return ret;
+	return bch2_trans_run(c,
+		for_each_btree_key_commit(trans, iter,
+				BTREE_ID_stripes, POS_MIN,
+				BTREE_ITER_PREFETCH, k,
+				NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
+			bch2_gc_write_stripes_key(trans, &iter, k)));
 }
 
 static void bch2_gc_stripes_reset(struct bch_fs *c, bool metadata_only)
@@ -1847,7 +1787,7 @@ again:
 #endif
 	c->gc_count++;
 
-	if (test_bit(BCH_FS_NEED_ANOTHER_GC, &c->flags) ||
+	if (test_bit(BCH_FS_need_another_gc, &c->flags) ||
 	    (!iter && bch2_test_restart_gc)) {
 		if (iter++ > 2) {
 			bch_info(c, "Unable to fix bucket gens, looping");
@@ -1859,7 +1799,7 @@ again:
 		 * XXX: make sure gens we fixed got saved
 		 */
 		bch_info(c, "Second GC pass needed, restarting:");
-		clear_bit(BCH_FS_NEED_ANOTHER_GC, &c->flags);
+		clear_bit(BCH_FS_need_another_gc, &c->flags);
 		__gc_pos_set(c, gc_phase(GC_PHASE_NOT_RUNNING));
 
 		bch2_gc_stripes_reset(c, metadata_only);
@@ -1899,9 +1839,7 @@ out:
 	 * allocator thread - issue wakeup in case they blocked on gc_lock:
 	 */
 	closure_wake_up(&c->freelist_wait);
-
-	if (ret)
-		bch_err_fn(c, ret);
+	bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -1911,7 +1849,6 @@ static int gc_btree_gens_key(struct btree_trans *trans,
 {
 	struct bch_fs *c = trans->c;
 	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
-	const struct bch_extent_ptr *ptr;
 	struct bkey_i *u;
 	int ret;
 
@@ -1969,12 +1906,7 @@ static int bch2_alloc_write_oldest_gen(struct btree_trans *trans, struct btree_i
 
 int bch2_gc_gens(struct bch_fs *c)
 {
-	struct btree_trans *trans;
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	struct bch_dev *ca;
 	u64 b, start_time = local_clock();
-	unsigned i;
 	int ret;
 
 	/*
@@ -1987,9 +1919,8 @@ int bch2_gc_gens(struct bch_fs *c)
 
 	trace_and_count(c, gc_gens_start, c);
 	down_read(&c->gc_lock);
-	trans = bch2_trans_get(c);
 
-	for_each_member_device(ca, c, i) {
+	for_each_member_device(c, ca) {
 		struct bucket_gens *gens = bucket_gens(ca);
 
 		BUG_ON(ca->oldest_gen);
@@ -2006,33 +1937,31 @@ int bch2_gc_gens(struct bch_fs *c)
 			ca->oldest_gen[b] = gens->b[b];
 	}
 
-	for (i = 0; i < BTREE_ID_NR; i++)
+	for (unsigned i = 0; i < BTREE_ID_NR; i++)
 		if (btree_type_has_ptrs(i)) {
 			c->gc_gens_btree = i;
 			c->gc_gens_pos = POS_MIN;
 
-			ret = for_each_btree_key_commit(trans, iter, i,
-					POS_MIN,
-					BTREE_ITER_PREFETCH|BTREE_ITER_ALL_SNAPSHOTS,
-					k,
-					NULL, NULL,
-					BTREE_INSERT_NOFAIL,
-				gc_btree_gens_key(trans, &iter, k));
-			if (ret && !bch2_err_matches(ret, EROFS))
-				bch_err_fn(c, ret);
+			ret = bch2_trans_run(c,
+				for_each_btree_key_commit(trans, iter, i,
+						POS_MIN,
+						BTREE_ITER_PREFETCH|BTREE_ITER_ALL_SNAPSHOTS,
+						k,
+						NULL, NULL,
+						BCH_TRANS_COMMIT_no_enospc,
+					gc_btree_gens_key(trans, &iter, k)));
 			if (ret)
 				goto err;
 		}
 
-	ret = for_each_btree_key_commit(trans, iter, BTREE_ID_alloc,
-			POS_MIN,
-			BTREE_ITER_PREFETCH,
-			k,
-			NULL, NULL,
-			BTREE_INSERT_NOFAIL,
-		bch2_alloc_write_oldest_gen(trans, &iter, k));
-	if (ret && !bch2_err_matches(ret, EROFS))
-		bch_err_fn(c, ret);
+	ret = bch2_trans_run(c,
+		for_each_btree_key_commit(trans, iter, BTREE_ID_alloc,
+				POS_MIN,
+				BTREE_ITER_PREFETCH,
+				k,
+				NULL, NULL,
+				BCH_TRANS_COMMIT_no_enospc,
+			bch2_alloc_write_oldest_gen(trans, &iter, k)));
 	if (ret)
 		goto err;
 
@@ -2044,14 +1973,15 @@ int bch2_gc_gens(struct bch_fs *c)
 	bch2_time_stats_update(&c->times[BCH_TIME_btree_gc], start_time);
 	trace_and_count(c, gc_gens_end, c);
 err:
-	for_each_member_device(ca, c, i) {
+	for_each_member_device(c, ca) {
 		kvfree(ca->oldest_gen);
 		ca->oldest_gen = NULL;
 	}
 
-	bch2_trans_put(trans);
 	up_read(&c->gc_lock);
 	mutex_unlock(&c->gc_gens_lock);
+	if (!bch2_err_matches(ret, EROFS))
+		bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -2061,7 +1991,6 @@ static int bch2_gc_thread(void *arg)
 	struct io_clock *clock = &c->io_clock[WRITE];
 	unsigned long last = atomic64_read(&clock->now);
 	unsigned last_kick = atomic_read(&c->kick_gc);
-	int ret;
 
 	set_freezable();
 
@@ -2101,11 +2030,8 @@ static int bch2_gc_thread(void *arg)
 #if 0
 		ret = bch2_gc(c, false, false);
 #else
-		ret = bch2_gc_gens(c);
+		bch2_gc_gens(c);
 #endif
-		if (ret < 0)
-			bch_err_fn(c, ret);
-
 		debug_check_no_locks_held();
 	}
 
diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index 37d896edb06e..33db48e2153f 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -524,7 +524,8 @@ static void btree_err_msg(struct printbuf *out, struct bch_fs *c,
 	prt_printf(out, "at btree ");
 	bch2_btree_pos_to_text(out, c, b);
 
-	prt_printf(out, "\n  node offset %u", b->written);
+	prt_printf(out, "\n  node offset %u/%u",
+		   b->written, btree_ptr_sectors_written(&b->key));
 	if (i)
 		prt_printf(out, " bset u64s %u", le16_to_cpu(i->u64s));
 	prt_str(out, ": ");
@@ -830,6 +831,23 @@ static int bset_key_invalid(struct bch_fs *c, struct btree *b,
 		(rw == WRITE ? bch2_bkey_val_invalid(c, k, READ, err) : 0);
 }
 
+static bool __bkey_valid(struct bch_fs *c, struct btree *b,
+			 struct bset *i, struct bkey_packed *k)
+{
+	if (bkey_p_next(k) > vstruct_last(i))
+		return false;
+
+	if (k->format > KEY_FORMAT_CURRENT)
+		return false;
+
+	struct printbuf buf = PRINTBUF;
+	struct bkey tmp;
+	struct bkey_s u = __bkey_disassemble(b, k, &tmp);
+	bool ret = __bch2_bkey_invalid(c, u.s_c, btree_node_type(b), READ, &buf);
+	printbuf_exit(&buf);
+	return ret;
+}
+
 static int validate_bset_keys(struct bch_fs *c, struct btree *b,
 			 struct bset *i, int write,
 			 bool have_retry, bool *saw_error)
@@ -845,6 +863,7 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b,
 	     k != vstruct_last(i);) {
 		struct bkey_s u;
 		struct bkey tmp;
+		unsigned next_good_key;
 
 		if (btree_err_on(bkey_p_next(k) > vstruct_last(i),
 				 -BCH_ERR_btree_node_read_err_fixable,
@@ -859,12 +878,8 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b,
 				 -BCH_ERR_btree_node_read_err_fixable,
 				 c, NULL, b, i,
 				 btree_node_bkey_bad_format,
-				 "invalid bkey format %u", k->format)) {
-			i->u64s = cpu_to_le16(le16_to_cpu(i->u64s) - k->u64s);
-			memmove_u64s_down(k, bkey_p_next(k),
-					  (u64 *) vstruct_end(i) - (u64 *) k);
-			continue;
-		}
+				 "invalid bkey format %u", k->format))
+			goto drop_this_key;
 
 		/* XXX: validate k->u64s */
 		if (!write)
@@ -885,11 +900,7 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b,
 				  c, NULL, b, i,
 				  btree_node_bad_bkey,
 				  "invalid bkey: %s", buf.buf);
-
-			i->u64s = cpu_to_le16(le16_to_cpu(i->u64s) - k->u64s);
-			memmove_u64s_down(k, bkey_p_next(k),
-					  (u64 *) vstruct_end(i) - (u64 *) k);
-			continue;
+			goto drop_this_key;
 		}
 
 		if (write)
@@ -906,21 +917,45 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b,
 			prt_printf(&buf, " > ");
 			bch2_bkey_to_text(&buf, u.k);
 
-			bch2_dump_bset(c, b, i, 0);
-
 			if (btree_err(-BCH_ERR_btree_node_read_err_fixable,
 				      c, NULL, b, i,
 				      btree_node_bkey_out_of_order,
-				      "%s", buf.buf)) {
-				i->u64s = cpu_to_le16(le16_to_cpu(i->u64s) - k->u64s);
-				memmove_u64s_down(k, bkey_p_next(k),
-						  (u64 *) vstruct_end(i) - (u64 *) k);
-				continue;
-			}
+				      "%s", buf.buf))
+				goto drop_this_key;
 		}
 
 		prev = k;
 		k = bkey_p_next(k);
+		continue;
+drop_this_key:
+		next_good_key = k->u64s;
+
+		if (!next_good_key ||
+		    (BSET_BIG_ENDIAN(i) == CPU_BIG_ENDIAN &&
+		     version >= bcachefs_metadata_version_snapshot)) {
+			/*
+			 * only do scanning if bch2_bkey_compat() has nothing to
+			 * do
+			 */
+
+			if (!__bkey_valid(c, b, i, (void *) ((u64 *) k + next_good_key))) {
+				for (next_good_key = 1;
+				     next_good_key < (u64 *) vstruct_last(i) - (u64 *) k;
+				     next_good_key++)
+					if (__bkey_valid(c, b, i, (void *) ((u64 *) k + next_good_key)))
+						goto got_good_key;
+
+			}
+
+			/*
+			 * didn't find a good key, have to truncate the rest of
+			 * the bset
+			 */
+			next_good_key = (u64 *) vstruct_last(i) - (u64 *) k;
+		}
+got_good_key:
+		le16_add_cpu(&i->u64s, -next_good_key);
+		memmove_u64s_down(k, bkey_p_next(k), (u64 *) vstruct_end(i) - (u64 *) k);
 	}
 fsck_err:
 	printbuf_exit(&buf);
@@ -934,7 +969,6 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 	struct sort_iter *iter;
 	struct btree_node *sorted;
 	struct bkey_packed *k;
-	struct bch_extent_ptr *ptr;
 	struct bset *i;
 	bool used_mempool, blacklisted;
 	bool updated_range = b->key.k.type == KEY_TYPE_btree_ptr_v2 &&
@@ -943,6 +977,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 	unsigned ptr_written = btree_ptr_sectors_written(&b->key);
 	struct printbuf buf = PRINTBUF;
 	int ret = 0, retry_read = 0, write = READ;
+	u64 start_time = local_clock();
 
 	b->version_ondisk = U16_MAX;
 	/* We might get called multiple times on read retry: */
@@ -968,12 +1003,20 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 		struct bch_btree_ptr_v2 *bp =
 			&bkey_i_to_btree_ptr_v2(&b->key)->v;
 
+		bch2_bpos_to_text(&buf, b->data->min_key);
+		prt_str(&buf, "-");
+		bch2_bpos_to_text(&buf, b->data->max_key);
+
 		btree_err_on(b->data->keys.seq != bp->seq,
 			     -BCH_ERR_btree_node_read_err_must_retry,
 			     c, ca, b, NULL,
 			     btree_node_bad_seq,
-			     "got wrong btree node (seq %llx want %llx)",
-			     b->data->keys.seq, bp->seq);
+			     "got wrong btree node (want %llx got %llx)\n"
+			     "got btree %s level %llu pos %s",
+			     bp->seq, b->data->keys.seq,
+			     bch2_btree_id_str(BTREE_NODE_ID(b->data)),
+			     BTREE_NODE_LEVEL(b->data),
+			     buf.buf);
 	} else {
 		btree_err_on(!b->data->keys.seq,
 			     -BCH_ERR_btree_node_read_err_must_retry,
@@ -999,8 +1042,8 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 
 			nonce = btree_nonce(i, b->written << 9);
 
-			csum_bad = bch2_crc_cmp(b->data->csum,
-				csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, b->data));
+			struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, b->data);
+			csum_bad = bch2_crc_cmp(b->data->csum, csum);
 			if (csum_bad)
 				bch2_io_error(ca, BCH_MEMBER_ERROR_checksum);
 
@@ -1008,7 +1051,10 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 				     -BCH_ERR_btree_node_read_err_want_retry,
 				     c, ca, b, i,
 				     bset_bad_csum,
-				     "invalid checksum");
+				     "%s",
+				     (printbuf_reset(&buf),
+				      bch2_csum_err_msg(&buf, BSET_CSUM_TYPE(i), b->data->csum, csum),
+				      buf.buf));
 
 			ret = bset_encrypt(c, i, b->written << 9);
 			if (bch2_fs_fatal_err_on(ret, c,
@@ -1037,8 +1083,8 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 				     "unknown checksum type %llu", BSET_CSUM_TYPE(i));
 
 			nonce = btree_nonce(i, b->written << 9);
-			csum_bad = bch2_crc_cmp(bne->csum,
-				csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, bne));
+			struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, bne);
+			csum_bad = bch2_crc_cmp(bne->csum, csum);
 			if (csum_bad)
 				bch2_io_error(ca, BCH_MEMBER_ERROR_checksum);
 
@@ -1046,7 +1092,10 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 				     -BCH_ERR_btree_node_read_err_want_retry,
 				     c, ca, b, i,
 				     bset_bad_csum,
-				     "invalid checksum");
+				     "%s",
+				     (printbuf_reset(&buf),
+				      bch2_csum_err_msg(&buf, BSET_CSUM_TYPE(i), bne->csum, csum),
+				      buf.buf));
 
 			ret = bset_encrypt(c, i, b->written << 9);
 			if (bch2_fs_fatal_err_on(ret, c,
@@ -1202,6 +1251,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 out:
 	mempool_free(iter, &c->fill_iter);
 	printbuf_exit(&buf);
+	bch2_time_stats_update(&c->times[BCH_TIME_btree_node_read_done], start_time);
 	return retry_read;
 fsck_err:
 	if (ret == -BCH_ERR_btree_node_read_err_want_retry ||
@@ -1358,10 +1408,9 @@ static bool btree_node_has_extra_bsets(struct bch_fs *c, unsigned offset, void *
 	return offset;
 }
 
-static void btree_node_read_all_replicas_done(struct closure *cl)
+static CLOSURE_CALLBACK(btree_node_read_all_replicas_done)
 {
-	struct btree_node_read_all *ra =
-		container_of(cl, struct btree_node_read_all, cl);
+	closure_type(ra, struct btree_node_read_all, cl);
 	struct bch_fs *c = ra->c;
 	struct btree *b = ra->b;
 	struct printbuf buf = PRINTBUF;
@@ -1567,7 +1616,7 @@ static int btree_node_read_all_replicas(struct bch_fs *c, struct btree *b, bool
 
 	if (sync) {
 		closure_sync(&ra->cl);
-		btree_node_read_all_replicas_done(&ra->cl);
+		btree_node_read_all_replicas_done(&ra->cl.work);
 	} else {
 		continue_at(&ra->cl, btree_node_read_all_replicas_done,
 			    c->io_complete_wq);
@@ -1576,16 +1625,17 @@ static int btree_node_read_all_replicas(struct bch_fs *c, struct btree *b, bool
 	return 0;
 }
 
-void bch2_btree_node_read(struct bch_fs *c, struct btree *b,
+void bch2_btree_node_read(struct btree_trans *trans, struct btree *b,
 			  bool sync)
 {
+	struct bch_fs *c = trans->c;
 	struct extent_ptr_decoded pick;
 	struct btree_read_bio *rb;
 	struct bch_dev *ca;
 	struct bio *bio;
 	int ret;
 
-	trace_and_count(c, btree_node_read, c, b);
+	trace_and_count(c, btree_node_read, trans, b);
 
 	if (bch2_verify_all_btree_replicas &&
 	    !btree_node_read_all_replicas(c, b, sync))
@@ -1638,7 +1688,7 @@ void bch2_btree_node_read(struct bch_fs *c, struct btree *b,
 
 		if (sync) {
 			submit_bio_wait(bio);
-
+			bch2_latency_acct(ca, rb->start_time, READ);
 			btree_node_read_work(&rb->work);
 		} else {
 			submit_bio(bio);
@@ -1664,12 +1714,12 @@ static int __bch2_btree_root_read(struct btree_trans *trans, enum btree_id id,
 	closure_init_stack(&cl);
 
 	do {
-		ret = bch2_btree_cache_cannibalize_lock(c, &cl);
+		ret = bch2_btree_cache_cannibalize_lock(trans, &cl);
 		closure_sync(&cl);
 	} while (ret);
 
 	b = bch2_btree_node_mem_alloc(trans, level != 0);
-	bch2_btree_cache_cannibalize_unlock(c);
+	bch2_btree_cache_cannibalize_unlock(trans);
 
 	BUG_ON(IS_ERR(b));
 
@@ -1678,7 +1728,7 @@ static int __bch2_btree_root_read(struct btree_trans *trans, enum btree_id id,
 
 	set_btree_node_read_in_flight(b);
 
-	bch2_btree_node_read(c, b, true);
+	bch2_btree_node_read(trans, b, true);
 
 	if (btree_node_read_error(b)) {
 		bch2_btree_node_hash_remove(&c->btree_cache, b);
@@ -1705,8 +1755,8 @@ int bch2_btree_root_read(struct bch_fs *c, enum btree_id id,
 	return bch2_trans_run(c, __bch2_btree_root_read(trans, id, k, level));
 }
 
-void bch2_btree_complete_write(struct bch_fs *c, struct btree *b,
-			      struct btree_write *w)
+static void bch2_btree_complete_write(struct bch_fs *c, struct btree *b,
+				      struct btree_write *w)
 {
 	unsigned long old, new, v = READ_ONCE(b->will_make_reachable);
 
@@ -1790,8 +1840,10 @@ static void btree_node_write_work(struct work_struct *work)
 	bch2_bkey_drop_ptrs(bkey_i_to_s(&wbio->key), ptr,
 		bch2_dev_list_has_dev(wbio->wbio.failed, ptr->dev));
 
-	if (!bch2_bkey_nr_ptrs(bkey_i_to_s_c(&wbio->key)))
+	if (!bch2_bkey_nr_ptrs(bkey_i_to_s_c(&wbio->key))) {
+		ret = -BCH_ERR_btree_write_all_failed;
 		goto err;
+	}
 
 	if (wbio->wbio.first_btree_write) {
 		if (wbio->wbio.failed.nr) {
@@ -1801,9 +1853,9 @@ static void btree_node_write_work(struct work_struct *work)
 		ret = bch2_trans_do(c, NULL, NULL, 0,
 			bch2_btree_node_update_key_get_iter(trans, b, &wbio->key,
 					BCH_WATERMARK_reclaim|
-					BTREE_INSERT_JOURNAL_RECLAIM|
-					BTREE_INSERT_NOFAIL|
-					BTREE_INSERT_NOCHECK_RW,
+					BCH_TRANS_COMMIT_journal_reclaim|
+					BCH_TRANS_COMMIT_no_enospc|
+					BCH_TRANS_COMMIT_no_check_rw,
 					!wbio->wbio.failed.nr));
 		if (ret)
 			goto err;
@@ -1886,7 +1938,6 @@ static int validate_bset_for_write(struct bch_fs *c, struct btree *b,
 static void btree_write_submit(struct work_struct *work)
 {
 	struct btree_write_bio *wbio = container_of(work, struct btree_write_bio, work);
-	struct bch_extent_ptr *ptr;
 	BKEY_PADDED_ONSTACK(k, BKEY_BTREE_PTR_VAL_U64s_MAX) tmp;
 
 	bkey_copy(&tmp.k, &wbio->key);
diff --git a/fs/bcachefs/btree_io.h b/fs/bcachefs/btree_io.h
index 7e03dd76fb38..e251cb6b965f 100644
--- a/fs/bcachefs/btree_io.h
+++ b/fs/bcachefs/btree_io.h
@@ -130,13 +130,10 @@ void bch2_btree_init_next(struct btree_trans *, struct btree *);
 
 int bch2_btree_node_read_done(struct bch_fs *, struct bch_dev *,
 			      struct btree *, bool, bool *);
-void bch2_btree_node_read(struct bch_fs *, struct btree *, bool);
+void bch2_btree_node_read(struct btree_trans *, struct btree *, bool);
 int bch2_btree_root_read(struct bch_fs *, enum btree_id,
 			 const struct bkey_i *, unsigned);
 
-void bch2_btree_complete_write(struct bch_fs *, struct btree *,
-			      struct btree_write *);
-
 bool bch2_btree_post_write_cleanup(struct bch_fs *, struct btree *);
 
 enum btree_write_flags {
diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c
index c2adf3fbb0b3..fa298289e016 100644
--- a/fs/bcachefs/btree_iter.c
+++ b/fs/bcachefs/btree_iter.c
@@ -13,6 +13,7 @@
 #include "error.h"
 #include "extents.h"
 #include "journal.h"
+#include "journal_io.h"
 #include "replicas.h"
 #include "snapshot.h"
 #include "trace.h"
@@ -21,8 +22,8 @@
 #include <linux/prefetch.h>
 
 static inline void btree_path_list_remove(struct btree_trans *, struct btree_path *);
-static inline void btree_path_list_add(struct btree_trans *, struct btree_path *,
-				       struct btree_path *);
+static inline void btree_path_list_add(struct btree_trans *,
+			btree_path_idx_t, btree_path_idx_t);
 
 static inline unsigned long btree_iter_ip_allocated(struct btree_iter *iter)
 {
@@ -33,7 +34,8 @@ static inline unsigned long btree_iter_ip_allocated(struct btree_iter *iter)
 #endif
 }
 
-static struct btree_path *btree_path_alloc(struct btree_trans *, struct btree_path *);
+static btree_path_idx_t btree_path_alloc(struct btree_trans *, btree_path_idx_t);
+static void bch2_trans_srcu_lock(struct btree_trans *);
 
 static inline int __btree_path_cmp(const struct btree_path *l,
 				   enum btree_id	r_btree_id,
@@ -239,8 +241,9 @@ static void bch2_btree_path_verify(struct btree_trans *trans,
 void bch2_trans_verify_paths(struct btree_trans *trans)
 {
 	struct btree_path *path;
+	unsigned iter;
 
-	trans_for_each_path(trans, path)
+	trans_for_each_path(trans, path, iter)
 		bch2_btree_path_verify(trans, path);
 }
 
@@ -250,7 +253,7 @@ static void bch2_btree_iter_verify(struct btree_iter *iter)
 
 	BUG_ON(iter->btree_id >= BTREE_ID_NR);
 
-	BUG_ON(!!(iter->flags & BTREE_ITER_CACHED) != iter->path->cached);
+	BUG_ON(!!(iter->flags & BTREE_ITER_CACHED) != btree_iter_path(trans, iter)->cached);
 
 	BUG_ON((iter->flags & BTREE_ITER_IS_EXTENTS) &&
 	       (iter->flags & BTREE_ITER_ALL_SNAPSHOTS));
@@ -260,8 +263,8 @@ static void bch2_btree_iter_verify(struct btree_iter *iter)
 	       !btree_type_has_snapshot_field(iter->btree_id));
 
 	if (iter->update_path)
-		bch2_btree_path_verify(trans, iter->update_path);
-	bch2_btree_path_verify(trans, iter->path);
+		bch2_btree_path_verify(trans, &trans->paths[iter->update_path]);
+	bch2_btree_path_verify(trans, btree_iter_path(trans, iter));
 }
 
 static void bch2_btree_iter_verify_entry_exit(struct btree_iter *iter)
@@ -330,12 +333,12 @@ void bch2_assert_pos_locked(struct btree_trans *trans, enum btree_id id,
 			    struct bpos pos, bool key_cache)
 {
 	struct btree_path *path;
-	unsigned idx;
+	struct trans_for_each_path_inorder_iter iter;
 	struct printbuf buf = PRINTBUF;
 
 	btree_trans_sort_paths(trans);
 
-	trans_for_each_path_inorder(trans, path, idx) {
+	trans_for_each_path_inorder(trans, path, iter) {
 		int cmp = cmp_int(path->btree_id, id) ?:
 			cmp_int(path->cached, key_cache);
 
@@ -415,8 +418,9 @@ void bch2_btree_path_fix_key_modified(struct btree_trans *trans,
 				      struct bkey_packed *where)
 {
 	struct btree_path *path;
+	unsigned i;
 
-	trans_for_each_path_with_node(trans, b, path) {
+	trans_for_each_path_with_node(trans, b, path, i) {
 		__bch2_btree_path_fix_key_modified(path, b, where);
 		bch2_btree_path_verify_level(trans, path, b->c.level);
 	}
@@ -523,6 +527,7 @@ void bch2_btree_node_iter_fix(struct btree_trans *trans,
 {
 	struct bset_tree *t = bch2_bkey_to_bset_inlined(b, where);
 	struct btree_path *linked;
+	unsigned i;
 
 	if (node_iter != &path->l[b->c.level].iter) {
 		__bch2_btree_node_iter_fix(path, b, node_iter, t,
@@ -532,7 +537,7 @@ void bch2_btree_node_iter_fix(struct btree_trans *trans,
 			bch2_btree_node_iter_verify(node_iter, b);
 	}
 
-	trans_for_each_path_with_node(trans, b, linked) {
+	trans_for_each_path_with_node(trans, b, linked, i) {
 		__bch2_btree_node_iter_fix(linked, b,
 					   &linked->l[b->c.level].iter, t,
 					   where, clobber_u64s, new_u64s);
@@ -647,7 +652,6 @@ void bch2_btree_path_level_init(struct btree_trans *trans,
 static void bch2_trans_revalidate_updates_in_node(struct btree_trans *trans, struct btree *b)
 {
 	struct bch_fs *c = trans->c;
-	struct btree_insert_entry *i;
 
 	trans_for_each_update(trans, i)
 		if (!i->cached &&
@@ -655,7 +659,7 @@ static void bch2_trans_revalidate_updates_in_node(struct btree_trans *trans, str
 		    i->btree_id	== b->c.btree_id &&
 		    bpos_cmp(i->k->k.p, b->data->min_key) >= 0 &&
 		    bpos_cmp(i->k->k.p, b->data->max_key) <= 0) {
-			i->old_v = bch2_btree_path_peek_slot(i->path, &i->old_k).v;
+			i->old_v = bch2_btree_path_peek_slot(trans->paths + i->path, &i->old_k).v;
 
 			if (unlikely(trans->journal_replay_not_finished)) {
 				struct bkey_i *j_k =
@@ -674,14 +678,22 @@ static void bch2_trans_revalidate_updates_in_node(struct btree_trans *trans, str
  * A btree node is being replaced - update the iterator to point to the new
  * node:
  */
-void bch2_trans_node_add(struct btree_trans *trans, struct btree *b)
+void bch2_trans_node_add(struct btree_trans *trans,
+			 struct btree_path *path,
+			 struct btree *b)
 {
-	struct btree_path *path;
+	struct btree_path *prev;
+
+	BUG_ON(!btree_path_pos_in_node(path, b));
+
+	while ((prev = prev_btree_path(trans, path)) &&
+	       btree_path_pos_in_node(prev, b))
+		path = prev;
 
-	trans_for_each_path(trans, path)
-		if (path->uptodate == BTREE_ITER_UPTODATE &&
-		    !path->cached &&
-		    btree_path_pos_in_node(path, b)) {
+	for (;
+	     path && btree_path_pos_in_node(path, b);
+	     path = next_btree_path(trans, path))
+		if (path->uptodate == BTREE_ITER_UPTODATE && !path->cached) {
 			enum btree_node_locked_type t =
 				btree_lock_want(path, b->c.level);
 
@@ -704,8 +716,9 @@ void bch2_trans_node_add(struct btree_trans *trans, struct btree *b)
 void bch2_trans_node_reinit_iter(struct btree_trans *trans, struct btree *b)
 {
 	struct btree_path *path;
+	unsigned i;
 
-	trans_for_each_path_with_node(trans, b, path)
+	trans_for_each_path_with_node(trans, b, path, i)
 		__btree_path_level_init(path, b->c.level);
 
 	bch2_trans_revalidate_updates_in_node(trans, b);
@@ -781,7 +794,7 @@ static int btree_path_prefetch(struct btree_trans *trans, struct btree_path *pat
 	struct btree_node_iter node_iter = l->iter;
 	struct bkey_packed *k;
 	struct bkey_buf tmp;
-	unsigned nr = test_bit(BCH_FS_STARTED, &c->flags)
+	unsigned nr = test_bit(BCH_FS_started, &c->flags)
 		? (path->level > 1 ? 0 :  2)
 		: (path->level > 1 ? 1 : 16);
 	bool was_locked = btree_node_locked(path, path->level);
@@ -816,7 +829,7 @@ static int btree_path_prefetch_j(struct btree_trans *trans, struct btree_path *p
 	struct bch_fs *c = trans->c;
 	struct bkey_s_c k;
 	struct bkey_buf tmp;
-	unsigned nr = test_bit(BCH_FS_STARTED, &c->flags)
+	unsigned nr = test_bit(BCH_FS_started, &c->flags)
 		? (path->level > 1 ? 0 :  2)
 		: (path->level > 1 ? 1 : 16);
 	bool was_locked = btree_node_locked(path, path->level);
@@ -884,7 +897,8 @@ static noinline int btree_node_iter_and_journal_peek(struct btree_trans *trans,
 
 	bch2_bkey_buf_reassemble(out, c, k);
 
-	if (flags & BTREE_ITER_PREFETCH)
+	if ((flags & BTREE_ITER_PREFETCH) &&
+	    c->opts.btree_node_prefetch)
 		ret = btree_path_prefetch_j(trans, path, &jiter);
 
 	bch2_btree_and_journal_iter_exit(&jiter);
@@ -916,7 +930,8 @@ static __always_inline int btree_path_down(struct btree_trans *trans,
 		bch2_bkey_buf_unpack(&tmp, c, l->b,
 				 bch2_btree_node_iter_peek(&l->iter, l->b));
 
-		if (flags & BTREE_ITER_PREFETCH) {
+		if ((flags & BTREE_ITER_PREFETCH) &&
+		    c->opts.btree_node_prefetch) {
 			ret = btree_path_prefetch(trans, path);
 			if (ret)
 				goto err;
@@ -953,7 +968,8 @@ static int bch2_btree_path_traverse_all(struct btree_trans *trans)
 	struct bch_fs *c = trans->c;
 	struct btree_path *path;
 	unsigned long trace_ip = _RET_IP_;
-	int i, ret = 0;
+	unsigned i;
+	int ret = 0;
 
 	if (trans->in_traverse_all)
 		return -BCH_ERR_transaction_restart_in_traverse_all;
@@ -963,7 +979,7 @@ retry_all:
 	trans->restarted = 0;
 	trans->last_restarted_ip = 0;
 
-	trans_for_each_path(trans, path)
+	trans_for_each_path(trans, path, i)
 		path->should_be_locked = false;
 
 	btree_trans_sort_paths(trans);
@@ -977,7 +993,7 @@ retry_all:
 		closure_init_stack(&cl);
 
 		do {
-			ret = bch2_btree_cache_cannibalize_lock(c, &cl);
+			ret = bch2_btree_cache_cannibalize_lock(trans, &cl);
 			closure_sync(&cl);
 		} while (ret);
 	}
@@ -985,16 +1001,16 @@ retry_all:
 	/* Now, redo traversals in correct order: */
 	i = 0;
 	while (i < trans->nr_sorted) {
-		path = trans->paths + trans->sorted[i];
+		btree_path_idx_t idx = trans->sorted[i];
 
 		/*
 		 * Traversing a path can cause another path to be added at about
 		 * the same position:
 		 */
-		if (path->uptodate) {
-			__btree_path_get(path, false);
-			ret = bch2_btree_path_traverse_one(trans, path, 0, _THIS_IP_);
-			__btree_path_put(path, false);
+		if (trans->paths[idx].uptodate) {
+			__btree_path_get(&trans->paths[idx], false);
+			ret = bch2_btree_path_traverse_one(trans, idx, 0, _THIS_IP_);
+			__btree_path_put(&trans->paths[idx], false);
 
 			if (bch2_err_matches(ret, BCH_ERR_transaction_restart) ||
 			    bch2_err_matches(ret, ENOMEM))
@@ -1013,7 +1029,7 @@ retry_all:
 	 * then failed to relock a path - that's fine.
 	 */
 err:
-	bch2_btree_cache_cannibalize_unlock(c);
+	bch2_btree_cache_cannibalize_unlock(trans);
 
 	trans->in_traverse_all = false;
 
@@ -1099,10 +1115,11 @@ static inline unsigned btree_path_up_until_good_node(struct btree_trans *trans,
  * stashed in the iterator and returned from bch2_trans_exit().
  */
 int bch2_btree_path_traverse_one(struct btree_trans *trans,
-				 struct btree_path *path,
+				 btree_path_idx_t path_idx,
 				 unsigned flags,
 				 unsigned long trace_ip)
 {
+	struct btree_path *path = &trans->paths[path_idx];
 	unsigned depth_want = path->level;
 	int ret = -((int) trans->restarted);
 
@@ -1126,6 +1143,8 @@ int bch2_btree_path_traverse_one(struct btree_trans *trans,
 		goto out;
 	}
 
+	path = &trans->paths[path_idx];
+
 	if (unlikely(path->level >= BTREE_MAX_DEPTH))
 		goto out;
 
@@ -1188,39 +1207,38 @@ static inline void btree_path_copy(struct btree_trans *trans, struct btree_path
 	}
 }
 
-static struct btree_path *btree_path_clone(struct btree_trans *trans, struct btree_path *src,
-					   bool intent)
+static btree_path_idx_t btree_path_clone(struct btree_trans *trans, btree_path_idx_t src,
+					 bool intent)
 {
-	struct btree_path *new = btree_path_alloc(trans, src);
-
-	btree_path_copy(trans, new, src);
-	__btree_path_get(new, intent);
+	btree_path_idx_t new = btree_path_alloc(trans, src);
+	btree_path_copy(trans, trans->paths + new, trans->paths + src);
+	__btree_path_get(trans->paths + new, intent);
 	return new;
 }
 
 __flatten
-struct btree_path *__bch2_btree_path_make_mut(struct btree_trans *trans,
-			 struct btree_path *path, bool intent,
-			 unsigned long ip)
+btree_path_idx_t __bch2_btree_path_make_mut(struct btree_trans *trans,
+			btree_path_idx_t path, bool intent, unsigned long ip)
 {
-	__btree_path_put(path, intent);
+	__btree_path_put(trans->paths + path, intent);
 	path = btree_path_clone(trans, path, intent);
-	path->preserve = false;
+	trans->paths[path].preserve = false;
 	return path;
 }
 
-struct btree_path * __must_check
+btree_path_idx_t __must_check
 __bch2_btree_path_set_pos(struct btree_trans *trans,
-		   struct btree_path *path, struct bpos new_pos,
-		   bool intent, unsigned long ip, int cmp)
+			  btree_path_idx_t path_idx, struct bpos new_pos,
+			  bool intent, unsigned long ip)
 {
-	unsigned level = path->level;
+	int cmp = bpos_cmp(new_pos, trans->paths[path_idx].pos);
 
 	bch2_trans_verify_not_in_restart(trans);
-	EBUG_ON(!path->ref);
+	EBUG_ON(!trans->paths[path_idx].ref);
 
-	path = bch2_btree_path_make_mut(trans, path, intent, ip);
+	path_idx = bch2_btree_path_make_mut(trans, path_idx, intent, ip);
 
+	struct btree_path *path = trans->paths + path_idx;
 	path->pos		= new_pos;
 	trans->paths_sorted	= false;
 
@@ -1231,7 +1249,7 @@ __bch2_btree_path_set_pos(struct btree_trans *trans,
 		goto out;
 	}
 
-	level = btree_path_up_until_good_node(trans, path, cmp);
+	unsigned level = btree_path_up_until_good_node(trans, path, cmp);
 
 	if (btree_path_node(path, level)) {
 		struct btree_path_level *l = &path->l[level];
@@ -1261,7 +1279,7 @@ __bch2_btree_path_set_pos(struct btree_trans *trans,
 	}
 out:
 	bch2_btree_path_verify(trans, path);
-	return path;
+	return path_idx;
 }
 
 /* Btree path: main interface: */
@@ -1296,19 +1314,16 @@ static struct btree_path *have_node_at_pos(struct btree_trans *trans, struct btr
 	return NULL;
 }
 
-static inline void __bch2_path_free(struct btree_trans *trans, struct btree_path *path)
+static inline void __bch2_path_free(struct btree_trans *trans, btree_path_idx_t path)
 {
-	__bch2_btree_path_unlock(trans, path);
-	btree_path_list_remove(trans, path);
-	trans->paths_allocated &= ~(1ULL << path->idx);
+	__bch2_btree_path_unlock(trans, trans->paths + path);
+	btree_path_list_remove(trans, trans->paths + path);
+	__clear_bit(path, trans->paths_allocated);
 }
 
-void bch2_path_put(struct btree_trans *trans, struct btree_path *path, bool intent)
+void bch2_path_put(struct btree_trans *trans, btree_path_idx_t path_idx, bool intent)
 {
-	struct btree_path *dup;
-
-	EBUG_ON(trans->paths + path->idx != path);
-	EBUG_ON(!path->ref);
+	struct btree_path *path = trans->paths + path_idx, *dup;
 
 	if (!__btree_path_put(path, intent))
 		return;
@@ -1330,16 +1345,13 @@ void bch2_path_put(struct btree_trans *trans, struct btree_path *path, bool inte
 		dup->should_be_locked	|= path->should_be_locked;
 	}
 
-	__bch2_path_free(trans, path);
+	__bch2_path_free(trans, path_idx);
 }
 
-static void bch2_path_put_nokeep(struct btree_trans *trans, struct btree_path *path,
+static void bch2_path_put_nokeep(struct btree_trans *trans, btree_path_idx_t path,
 				 bool intent)
 {
-	EBUG_ON(trans->paths + path->idx != path);
-	EBUG_ON(!path->ref);
-
-	if (!__btree_path_put(path, intent))
+	if (!__btree_path_put(trans->paths + path, intent))
 		return;
 
 	__bch2_path_free(trans, path);
@@ -1362,9 +1374,6 @@ void __noreturn bch2_trans_in_restart_error(struct btree_trans *trans)
 noinline __cold
 void bch2_trans_updates_to_text(struct printbuf *buf, struct btree_trans *trans)
 {
-	struct btree_insert_entry *i;
-	struct btree_write_buffered_key *wb;
-
 	prt_printf(buf, "transaction updates for %s journal seq %llu",
 	       trans->fn, trans->journal_res.seq);
 	prt_newline(buf);
@@ -1388,16 +1397,10 @@ void bch2_trans_updates_to_text(struct printbuf *buf, struct btree_trans *trans)
 		prt_newline(buf);
 	}
 
-	trans_for_each_wb_update(trans, wb) {
-		prt_printf(buf, "update: btree=%s wb=1 %pS",
-		       bch2_btree_id_str(wb->btree),
-		       (void *) i->ip_allocated);
-		prt_newline(buf);
-
-		prt_printf(buf, "  new ");
-		bch2_bkey_val_to_text(buf, trans->c, bkey_i_to_s_c(&wb->k));
-		prt_newline(buf);
-	}
+	for (struct jset_entry *e = trans->journal_entries;
+	     e != btree_trans_journal_entries_top(trans);
+	     e = vstruct_next(e))
+		bch2_journal_entry_to_text(buf, trans->c, e);
 
 	printbuf_indent_sub(buf, 2);
 }
@@ -1412,11 +1415,12 @@ void bch2_dump_trans_updates(struct btree_trans *trans)
 	printbuf_exit(&buf);
 }
 
-noinline __cold
-void bch2_btree_path_to_text(struct printbuf *out, struct btree_path *path)
+static void bch2_btree_path_to_text(struct printbuf *out, struct btree_trans *trans, btree_path_idx_t path_idx)
 {
+	struct btree_path *path = trans->paths + path_idx;
+
 	prt_printf(out, "path: idx %2u ref %u:%u %c %c btree=%s l=%u pos ",
-		   path->idx, path->ref, path->intent_ref,
+		   path_idx, path->ref, path->intent_ref,
 		   path->preserve ? 'P' : ' ',
 		   path->should_be_locked ? 'S' : ' ',
 		   bch2_btree_id_str(path->btree_id),
@@ -1434,14 +1438,13 @@ static noinline __cold
 void __bch2_trans_paths_to_text(struct printbuf *out, struct btree_trans *trans,
 				bool nosort)
 {
-	struct btree_path *path;
-	unsigned idx;
+	struct trans_for_each_path_inorder_iter iter;
 
 	if (!nosort)
 		btree_trans_sort_paths(trans);
 
-	trans_for_each_path_inorder(trans, path, idx)
-		bch2_btree_path_to_text(out, path);
+	trans_for_each_path_idx_inorder(trans, iter)
+		bch2_btree_path_to_text(out, trans, iter.path_idx);
 }
 
 noinline __cold
@@ -1473,17 +1476,14 @@ static void bch2_trans_update_max_paths(struct btree_trans *trans)
 {
 	struct btree_transaction_stats *s = btree_trans_stats(trans);
 	struct printbuf buf = PRINTBUF;
-
-	if (!s)
-		return;
+	size_t nr = bitmap_weight(trans->paths_allocated, trans->nr_paths);
 
 	bch2_trans_paths_to_text(&buf, trans);
 
 	if (!buf.allocation_failure) {
 		mutex_lock(&s->lock);
-		if (s->nr_max_paths < hweight64(trans->paths_allocated)) {
-			s->nr_max_paths = trans->nr_max_paths =
-				hweight64(trans->paths_allocated);
+		if (nr > s->nr_max_paths) {
+			s->nr_max_paths = nr;
 			swap(s->max_paths_text, buf.buf);
 		}
 		mutex_unlock(&s->lock);
@@ -1491,64 +1491,121 @@ static void bch2_trans_update_max_paths(struct btree_trans *trans)
 
 	printbuf_exit(&buf);
 
-	trans->nr_max_paths = hweight64(trans->paths_allocated);
+	trans->nr_paths_max = nr;
+}
+
+noinline __cold
+int __bch2_btree_trans_too_many_iters(struct btree_trans *trans)
+{
+	if (trace_trans_restart_too_many_iters_enabled()) {
+		struct printbuf buf = PRINTBUF;
+
+		bch2_trans_paths_to_text(&buf, trans);
+		trace_trans_restart_too_many_iters(trans, _THIS_IP_, buf.buf);
+		printbuf_exit(&buf);
+	}
+
+	count_event(trans->c, trans_restart_too_many_iters);
+
+	return btree_trans_restart(trans, BCH_ERR_transaction_restart_too_many_iters);
 }
 
 static noinline void btree_path_overflow(struct btree_trans *trans)
 {
 	bch2_dump_trans_paths_updates(trans);
-	panic("trans path overflow\n");
+	bch_err(trans->c, "trans path overflow");
 }
 
-static inline struct btree_path *btree_path_alloc(struct btree_trans *trans,
-						  struct btree_path *pos)
+static noinline void btree_paths_realloc(struct btree_trans *trans)
 {
-	struct btree_path *path;
-	unsigned idx;
+	unsigned nr = trans->nr_paths * 2;
+
+	void *p = kzalloc(BITS_TO_LONGS(nr) * sizeof(unsigned long) +
+			  sizeof(struct btree_trans_paths) +
+			  nr * sizeof(struct btree_path) +
+			  nr * sizeof(btree_path_idx_t) + 8 +
+			  nr * sizeof(struct btree_insert_entry), GFP_KERNEL|__GFP_NOFAIL);
 
-	if (unlikely(trans->paths_allocated ==
-		     ~((~0ULL << 1) << (BTREE_ITER_MAX - 1))))
-		btree_path_overflow(trans);
+	unsigned long *paths_allocated = p;
+	memcpy(paths_allocated, trans->paths_allocated, BITS_TO_LONGS(trans->nr_paths) * sizeof(unsigned long));
+	p += BITS_TO_LONGS(nr) * sizeof(unsigned long);
 
-	idx = __ffs64(~trans->paths_allocated);
+	p += sizeof(struct btree_trans_paths);
+	struct btree_path *paths = p;
+	*trans_paths_nr(paths) = nr;
+	memcpy(paths, trans->paths, trans->nr_paths * sizeof(struct btree_path));
+	p += nr * sizeof(struct btree_path);
+
+	btree_path_idx_t *sorted = p;
+	memcpy(sorted, trans->sorted, trans->nr_sorted * sizeof(btree_path_idx_t));
+	p += nr * sizeof(btree_path_idx_t) + 8;
+
+	struct btree_insert_entry *updates = p;
+	memcpy(updates, trans->updates, trans->nr_paths * sizeof(struct btree_insert_entry));
+
+	unsigned long *old = trans->paths_allocated;
+
+	rcu_assign_pointer(trans->paths_allocated,	paths_allocated);
+	rcu_assign_pointer(trans->paths,		paths);
+	rcu_assign_pointer(trans->sorted,		sorted);
+	rcu_assign_pointer(trans->updates,		updates);
+
+	trans->nr_paths		= nr;
+
+	if (old != trans->_paths_allocated)
+		kfree_rcu_mightsleep(old);
+}
+
+static inline btree_path_idx_t btree_path_alloc(struct btree_trans *trans,
+						btree_path_idx_t pos)
+{
+	btree_path_idx_t idx = find_first_zero_bit(trans->paths_allocated, trans->nr_paths);
+
+	if (unlikely(idx == trans->nr_paths)) {
+		if (trans->nr_paths == BTREE_ITER_MAX) {
+			btree_path_overflow(trans);
+			return 0;
+		}
+
+		btree_paths_realloc(trans);
+	}
 
 	/*
 	 * Do this before marking the new path as allocated, since it won't be
 	 * initialized yet:
 	 */
-	if (unlikely(idx > trans->nr_max_paths))
+	if (unlikely(idx > trans->nr_paths_max))
 		bch2_trans_update_max_paths(trans);
 
-	trans->paths_allocated |= 1ULL << idx;
+	__set_bit(idx, trans->paths_allocated);
 
-	path = &trans->paths[idx];
-	path->idx		= idx;
+	struct btree_path *path = &trans->paths[idx];
 	path->ref		= 0;
 	path->intent_ref	= 0;
 	path->nodes_locked	= 0;
-	path->alloc_seq++;
 
-	btree_path_list_add(trans, pos, path);
+	btree_path_list_add(trans, pos, idx);
 	trans->paths_sorted = false;
-	return path;
+	return idx;
 }
 
-struct btree_path *bch2_path_get(struct btree_trans *trans,
-				 enum btree_id btree_id, struct bpos pos,
-				 unsigned locks_want, unsigned level,
-				 unsigned flags, unsigned long ip)
+btree_path_idx_t bch2_path_get(struct btree_trans *trans,
+			     enum btree_id btree_id, struct bpos pos,
+			     unsigned locks_want, unsigned level,
+			     unsigned flags, unsigned long ip)
 {
-	struct btree_path *path, *path_pos = NULL;
+	struct btree_path *path;
 	bool cached = flags & BTREE_ITER_CACHED;
 	bool intent = flags & BTREE_ITER_INTENT;
-	int i;
+	struct trans_for_each_path_inorder_iter iter;
+	btree_path_idx_t path_pos = 0, path_idx;
 
 	bch2_trans_verify_not_in_restart(trans);
 	bch2_trans_verify_locks(trans);
 
 	btree_trans_sort_paths(trans);
 
-	trans_for_each_path_inorder(trans, path, i) {
+	trans_for_each_path_inorder(trans, path, iter) {
 		if (__btree_path_cmp(path,
 				     btree_id,
 				     cached,
@@ -1556,18 +1613,19 @@ struct btree_path *bch2_path_get(struct btree_trans *trans,
 				     level) > 0)
 			break;
 
-		path_pos = path;
+		path_pos = iter.path_idx;
 	}
 
 	if (path_pos &&
-	    path_pos->cached	== cached &&
-	    path_pos->btree_id	== btree_id &&
-	    path_pos->level	== level) {
-		__btree_path_get(path_pos, intent);
-		path = bch2_btree_path_set_pos(trans, path_pos, pos, intent, ip);
+	    trans->paths[path_pos].cached	== cached &&
+	    trans->paths[path_pos].btree_id	== btree_id &&
+	    trans->paths[path_pos].level	== level) {
+		__btree_path_get(trans->paths + path_pos, intent);
+		path_idx = bch2_btree_path_set_pos(trans, path_pos, pos, intent, ip);
+		path = trans->paths + path_idx;
 	} else {
-		path = btree_path_alloc(trans, path_pos);
-		path_pos = NULL;
+		path_idx = btree_path_alloc(trans, path_pos);
+		path = trans->paths + path_idx;
 
 		__btree_path_get(path, intent);
 		path->pos			= pos;
@@ -1578,7 +1636,7 @@ struct btree_path *bch2_path_get(struct btree_trans *trans,
 		path->level			= level;
 		path->locks_want		= locks_want;
 		path->nodes_locked		= 0;
-		for (i = 0; i < ARRAY_SIZE(path->l); i++)
+		for (unsigned i = 0; i < ARRAY_SIZE(path->l); i++)
 			path->l[i].b		= ERR_PTR(-BCH_ERR_no_btree_node_init);
 #ifdef TRACK_PATH_ALLOCATED
 		path->ip_allocated		= ip;
@@ -1604,7 +1662,7 @@ struct btree_path *bch2_path_get(struct btree_trans *trans,
 	if (locks_want > path->locks_want)
 		bch2_btree_path_upgrade_noupgrade_sibs(trans, path, locks_want, NULL);
 
-	return path;
+	return path_idx;
 }
 
 struct bkey_s_c bch2_btree_path_peek_slot(struct btree_path *path, struct bkey *u)
@@ -1659,9 +1717,10 @@ __bch2_btree_iter_traverse(struct btree_iter *iter)
 int __must_check
 bch2_btree_iter_traverse(struct btree_iter *iter)
 {
+	struct btree_trans *trans = iter->trans;
 	int ret;
 
-	iter->path = bch2_btree_path_set_pos(iter->trans, iter->path,
+	iter->path = bch2_btree_path_set_pos(trans, iter->path,
 					btree_iter_search_key(iter),
 					iter->flags & BTREE_ITER_INTENT,
 					btree_iter_ip_allocated(iter));
@@ -1670,7 +1729,7 @@ bch2_btree_iter_traverse(struct btree_iter *iter)
 	if (ret)
 		return ret;
 
-	btree_path_set_should_be_locked(iter->path);
+	btree_path_set_should_be_locked(trans->paths + iter->path);
 	return 0;
 }
 
@@ -1682,14 +1741,15 @@ struct btree *bch2_btree_iter_peek_node(struct btree_iter *iter)
 	struct btree *b = NULL;
 	int ret;
 
-	EBUG_ON(iter->path->cached);
+	EBUG_ON(trans->paths[iter->path].cached);
 	bch2_btree_iter_verify(iter);
 
 	ret = bch2_btree_path_traverse(trans, iter->path, iter->flags);
 	if (ret)
 		goto err;
 
-	b = btree_path_node(iter->path, iter->path->level);
+	struct btree_path *path = btree_iter_path(trans, iter);
+	b = btree_path_node(path, path->level);
 	if (!b)
 		goto out;
 
@@ -1701,7 +1761,7 @@ struct btree *bch2_btree_iter_peek_node(struct btree_iter *iter)
 	iter->path = bch2_btree_path_set_pos(trans, iter->path, b->key.k.p,
 					iter->flags & BTREE_ITER_INTENT,
 					btree_iter_ip_allocated(iter));
-	btree_path_set_should_be_locked(iter->path);
+	btree_path_set_should_be_locked(btree_iter_path(trans, iter));
 out:
 	bch2_btree_iter_verify_entry_exit(iter);
 	bch2_btree_iter_verify(iter);
@@ -1726,14 +1786,15 @@ struct btree *bch2_btree_iter_peek_node_and_restart(struct btree_iter *iter)
 struct btree *bch2_btree_iter_next_node(struct btree_iter *iter)
 {
 	struct btree_trans *trans = iter->trans;
-	struct btree_path *path = iter->path;
 	struct btree *b = NULL;
 	int ret;
 
+	EBUG_ON(trans->paths[iter->path].cached);
 	bch2_trans_verify_not_in_restart(trans);
-	EBUG_ON(iter->path->cached);
 	bch2_btree_iter_verify(iter);
 
+	struct btree_path *path = btree_iter_path(trans, iter);
+
 	/* already at end? */
 	if (!btree_path_node(path, path->level))
 		return NULL;
@@ -1763,17 +1824,19 @@ struct btree *bch2_btree_iter_next_node(struct btree_iter *iter)
 		 * Haven't gotten to the end of the parent node: go back down to
 		 * the next child node
 		 */
-		path = iter->path =
-			bch2_btree_path_set_pos(trans, path, bpos_successor(iter->pos),
-					   iter->flags & BTREE_ITER_INTENT,
-					   btree_iter_ip_allocated(iter));
+		iter->path = bch2_btree_path_set_pos(trans, iter->path,
+					bpos_successor(iter->pos),
+					iter->flags & BTREE_ITER_INTENT,
+					btree_iter_ip_allocated(iter));
 
+		path = btree_iter_path(trans, iter);
 		btree_path_set_level_down(trans, path, iter->min_depth);
 
-		ret = bch2_btree_path_traverse(trans, path, iter->flags);
+		ret = bch2_btree_path_traverse(trans, iter->path, iter->flags);
 		if (ret)
 			goto err;
 
+		path = btree_iter_path(trans, iter);
 		b = path->l[path->level].b;
 	}
 
@@ -1783,8 +1846,8 @@ struct btree *bch2_btree_iter_next_node(struct btree_iter *iter)
 	iter->path = bch2_btree_path_set_pos(trans, iter->path, b->key.k.p,
 					iter->flags & BTREE_ITER_INTENT,
 					btree_iter_ip_allocated(iter));
-	btree_path_set_should_be_locked(iter->path);
-	BUG_ON(iter->path->uptodate);
+	btree_path_set_should_be_locked(btree_iter_path(trans, iter));
+	EBUG_ON(btree_iter_path(trans, iter)->uptodate);
 out:
 	bch2_btree_iter_verify_entry_exit(iter);
 	bch2_btree_iter_verify(iter);
@@ -1799,23 +1862,15 @@ err:
 
 inline bool bch2_btree_iter_advance(struct btree_iter *iter)
 {
-	if (likely(!(iter->flags & BTREE_ITER_ALL_LEVELS))) {
-		struct bpos pos = iter->k.p;
-		bool ret = !(iter->flags & BTREE_ITER_ALL_SNAPSHOTS
-			     ? bpos_eq(pos, SPOS_MAX)
-			     : bkey_eq(pos, SPOS_MAX));
-
-		if (ret && !(iter->flags & BTREE_ITER_IS_EXTENTS))
-			pos = bkey_successor(iter, pos);
-		bch2_btree_iter_set_pos(iter, pos);
-		return ret;
-	} else {
-		if (!btree_path_node(iter->path, iter->path->level))
-			return true;
+	struct bpos pos = iter->k.p;
+	bool ret = !(iter->flags & BTREE_ITER_ALL_SNAPSHOTS
+		     ? bpos_eq(pos, SPOS_MAX)
+		     : bkey_eq(pos, SPOS_MAX));
 
-		iter->advanced = true;
-		return false;
-	}
+	if (ret && !(iter->flags & BTREE_ITER_IS_EXTENTS))
+		pos = bkey_successor(iter, pos);
+	bch2_btree_iter_set_pos(iter, pos);
+	return ret;
 }
 
 inline bool bch2_btree_iter_rewind(struct btree_iter *iter)
@@ -1832,58 +1887,70 @@ inline bool bch2_btree_iter_rewind(struct btree_iter *iter)
 }
 
 static noinline
-struct bkey_i *__bch2_btree_trans_peek_updates(struct btree_iter *iter)
+void bch2_btree_trans_peek_prev_updates(struct btree_trans *trans, struct btree_iter *iter,
+					struct bkey_s_c *k)
 {
-	struct btree_insert_entry *i;
-	struct bkey_i *ret = NULL;
+	struct bpos end = path_l(btree_iter_path(trans, iter))->b->data->min_key;
 
-	trans_for_each_update(iter->trans, i) {
-		if (i->btree_id < iter->btree_id)
-			continue;
-		if (i->btree_id > iter->btree_id)
-			break;
-		if (bpos_lt(i->k->k.p, iter->path->pos))
-			continue;
-		if (i->key_cache_already_flushed)
-			continue;
-		if (!ret || bpos_lt(i->k->k.p, ret->k.p))
-			ret = i->k;
-	}
+	trans_for_each_update(trans, i)
+		if (!i->key_cache_already_flushed &&
+		    i->btree_id == iter->btree_id &&
+		    bpos_le(i->k->k.p, iter->pos) &&
+		    bpos_ge(i->k->k.p, k->k ? k->k->p : end)) {
+			iter->k = i->k->k;
+			*k = bkey_i_to_s_c(i->k);
+		}
+}
 
-	return ret;
+static noinline
+void bch2_btree_trans_peek_updates(struct btree_trans *trans, struct btree_iter *iter,
+				   struct bkey_s_c *k)
+{
+	struct btree_path *path = btree_iter_path(trans, iter);
+	struct bpos end = path_l(path)->b->key.k.p;
+
+	trans_for_each_update(trans, i)
+		if (!i->key_cache_already_flushed &&
+		    i->btree_id == iter->btree_id &&
+		    bpos_ge(i->k->k.p, path->pos) &&
+		    bpos_le(i->k->k.p, k->k ? k->k->p : end)) {
+			iter->k = i->k->k;
+			*k = bkey_i_to_s_c(i->k);
+		}
 }
 
-static inline struct bkey_i *btree_trans_peek_updates(struct btree_iter *iter)
+static noinline
+void bch2_btree_trans_peek_slot_updates(struct btree_trans *trans, struct btree_iter *iter,
+					struct bkey_s_c *k)
 {
-	return iter->flags & BTREE_ITER_WITH_UPDATES
-		? __bch2_btree_trans_peek_updates(iter)
-		: NULL;
+	trans_for_each_update(trans, i)
+		if (!i->key_cache_already_flushed &&
+		    i->btree_id == iter->btree_id &&
+		    bpos_eq(i->k->k.p, iter->pos)) {
+			iter->k = i->k->k;
+			*k = bkey_i_to_s_c(i->k);
+		}
 }
 
 static struct bkey_i *bch2_btree_journal_peek(struct btree_trans *trans,
 					      struct btree_iter *iter,
 					      struct bpos end_pos)
 {
-	struct bkey_i *k;
-
-	if (bpos_lt(iter->path->pos, iter->journal_pos))
-		iter->journal_idx = 0;
+	struct btree_path *path = btree_iter_path(trans, iter);
 
-	k = bch2_journal_keys_peek_upto(trans->c, iter->btree_id,
-					iter->path->level,
-					iter->path->pos,
-					end_pos,
-					&iter->journal_idx);
-
-	iter->journal_pos = k ? k->k.p : end_pos;
-	return k;
+	return bch2_journal_keys_peek_upto(trans->c, iter->btree_id,
+					   path->level,
+					   path->pos,
+					   end_pos,
+					   &iter->journal_idx);
 }
 
 static noinline
 struct bkey_s_c btree_trans_peek_slot_journal(struct btree_trans *trans,
 					      struct btree_iter *iter)
 {
-	struct bkey_i *k = bch2_btree_journal_peek(trans, iter, iter->path->pos);
+	struct btree_path *path = btree_iter_path(trans, iter);
+	struct bkey_i *k = bch2_btree_journal_peek(trans, iter, path->pos);
 
 	if (k) {
 		iter->k = k->k;
@@ -1898,9 +1965,10 @@ struct bkey_s_c btree_trans_peek_journal(struct btree_trans *trans,
 					 struct btree_iter *iter,
 					 struct bkey_s_c k)
 {
+	struct btree_path *path = btree_iter_path(trans, iter);
 	struct bkey_i *next_journal =
 		bch2_btree_journal_peek(trans, iter,
-				k.k ? k.k->p : path_l(iter->path)->b->key.k.p);
+				k.k ? k.k->p : path_l(path)->b->key.k.p);
 
 	if (next_journal) {
 		iter->k = next_journal->k;
@@ -1943,13 +2011,13 @@ struct bkey_s_c btree_trans_peek_key_cache(struct btree_iter *iter, struct bpos
 
 	ret =   bch2_btree_path_traverse(trans, iter->key_cache_path,
 					 iter->flags|BTREE_ITER_CACHED) ?:
-		bch2_btree_path_relock(trans, iter->path, _THIS_IP_);
+		bch2_btree_path_relock(trans, btree_iter_path(trans, iter), _THIS_IP_);
 	if (unlikely(ret))
 		return bkey_s_c_err(ret);
 
-	btree_path_set_should_be_locked(iter->key_cache_path);
+	btree_path_set_should_be_locked(trans->paths + iter->key_cache_path);
 
-	k = bch2_btree_path_peek_slot(iter->key_cache_path, &u);
+	k = bch2_btree_path_peek_slot(trans->paths + iter->key_cache_path, &u);
 	if (k.k && !bkey_err(k)) {
 		iter->k = u;
 		k.k = &iter->k;
@@ -1960,11 +2028,10 @@ struct bkey_s_c btree_trans_peek_key_cache(struct btree_iter *iter, struct bpos
 static struct bkey_s_c __bch2_btree_iter_peek(struct btree_iter *iter, struct bpos search_key)
 {
 	struct btree_trans *trans = iter->trans;
-	struct bkey_i *next_update;
 	struct bkey_s_c k, k2;
 	int ret;
 
-	EBUG_ON(iter->path->cached);
+	EBUG_ON(btree_iter_path(trans, iter)->cached);
 	bch2_btree_iter_verify(iter);
 
 	while (1) {
@@ -1982,7 +2049,8 @@ static struct bkey_s_c __bch2_btree_iter_peek(struct btree_iter *iter, struct bp
 			goto out;
 		}
 
-		l = path_l(iter->path);
+		struct btree_path *path = btree_iter_path(trans, iter);
+		l = path_l(path);
 
 		if (unlikely(!l->b)) {
 			/* No btree nodes at requested level: */
@@ -1991,7 +2059,7 @@ static struct bkey_s_c __bch2_btree_iter_peek(struct btree_iter *iter, struct bp
 			goto out;
 		}
 
-		btree_path_set_should_be_locked(iter->path);
+		btree_path_set_should_be_locked(path);
 
 		k = btree_path_level_peek_all(trans->c, l, &iter->k);
 
@@ -2009,14 +2077,9 @@ static struct bkey_s_c __bch2_btree_iter_peek(struct btree_iter *iter, struct bp
 		if (unlikely(iter->flags & BTREE_ITER_WITH_JOURNAL))
 			k = btree_trans_peek_journal(trans, iter, k);
 
-		next_update = btree_trans_peek_updates(iter);
-
-		if (next_update &&
-		    bpos_le(next_update->k.p,
-			    k.k ? k.k->p : l->b->key.k.p)) {
-			iter->k = next_update->k;
-			k = bkey_i_to_s_c(next_update);
-		}
+		if (unlikely((iter->flags & BTREE_ITER_WITH_UPDATES) &&
+			     trans->nr_updates))
+			bch2_btree_trans_peek_updates(trans, iter, &k);
 
 		if (k.k && bkey_deleted(k.k)) {
 			/*
@@ -2066,13 +2129,12 @@ struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos e
 	struct bpos iter_pos;
 	int ret;
 
-	EBUG_ON(iter->flags & BTREE_ITER_ALL_LEVELS);
 	EBUG_ON((iter->flags & BTREE_ITER_FILTER_SNAPSHOTS) && bkey_eq(end, POS_MAX));
 
 	if (iter->update_path) {
 		bch2_path_put_nokeep(trans, iter->update_path,
 				     iter->flags & BTREE_ITER_INTENT);
-		iter->update_path = NULL;
+		iter->update_path = 0;
 	}
 
 	bch2_btree_iter_verify_entry_exit(iter);
@@ -2085,25 +2147,23 @@ struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos e
 			goto out_no_locked;
 
 		/*
-		 * iter->pos should be mononotically increasing, and always be
-		 * equal to the key we just returned - except extents can
-		 * straddle iter->pos:
+		 * We need to check against @end before FILTER_SNAPSHOTS because
+		 * if we get to a different inode that requested we might be
+		 * seeing keys for a different snapshot tree that will all be
+		 * filtered out.
+		 *
+		 * But we can't do the full check here, because bkey_start_pos()
+		 * isn't monotonically increasing before FILTER_SNAPSHOTS, and
+		 * that's what we check against in extents mode:
 		 */
-		if (!(iter->flags & BTREE_ITER_IS_EXTENTS))
-			iter_pos = k.k->p;
-		else
-			iter_pos = bkey_max(iter->pos, bkey_start_pos(k.k));
-
-		if (unlikely(!(iter->flags & BTREE_ITER_IS_EXTENTS)
-			     ? bkey_gt(iter_pos, end)
-			     : bkey_ge(iter_pos, end)))
+		if (k.k->p.inode > end.inode)
 			goto end;
 
 		if (iter->update_path &&
-		    !bkey_eq(iter->update_path->pos, k.k->p)) {
+		    !bkey_eq(trans->paths[iter->update_path].pos, k.k->p)) {
 			bch2_path_put_nokeep(trans, iter->update_path,
 					     iter->flags & BTREE_ITER_INTENT);
-			iter->update_path = NULL;
+			iter->update_path = 0;
 		}
 
 		if ((iter->flags & BTREE_ITER_FILTER_SNAPSHOTS) &&
@@ -2123,7 +2183,7 @@ struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos e
 			 * advance, same as on exit for iter->path, but only up
 			 * to snapshot
 			 */
-			__btree_path_get(iter->path, iter->flags & BTREE_ITER_INTENT);
+			__btree_path_get(trans->paths + iter->path, iter->flags & BTREE_ITER_INTENT);
 			iter->update_path = iter->path;
 
 			iter->update_path = bch2_btree_path_set_pos(trans,
@@ -2155,6 +2215,21 @@ struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos e
 			continue;
 		}
 
+		/*
+		 * iter->pos should be mononotically increasing, and always be
+		 * equal to the key we just returned - except extents can
+		 * straddle iter->pos:
+		 */
+		if (!(iter->flags & BTREE_ITER_IS_EXTENTS))
+			iter_pos = k.k->p;
+		else
+			iter_pos = bkey_max(iter->pos, bkey_start_pos(k.k));
+
+		if (unlikely(!(iter->flags & BTREE_ITER_IS_EXTENTS)
+			     ? bkey_gt(iter_pos, end)
+			     : bkey_ge(iter_pos, end)))
+			goto end;
+
 		break;
 	}
 
@@ -2164,14 +2239,14 @@ struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos e
 				iter->flags & BTREE_ITER_INTENT,
 				btree_iter_ip_allocated(iter));
 
-	btree_path_set_should_be_locked(iter->path);
+	btree_path_set_should_be_locked(btree_iter_path(trans, iter));
 out_no_locked:
 	if (iter->update_path) {
-		ret = bch2_btree_path_relock(trans, iter->update_path, _THIS_IP_);
+		ret = bch2_btree_path_relock(trans, trans->paths + iter->update_path, _THIS_IP_);
 		if (unlikely(ret))
 			k = bkey_s_c_err(ret);
 		else
-			btree_path_set_should_be_locked(iter->update_path);
+			btree_path_set_should_be_locked(trans->paths + iter->update_path);
 	}
 
 	if (!(iter->flags & BTREE_ITER_ALL_SNAPSHOTS))
@@ -2193,103 +2268,6 @@ end:
 }
 
 /**
- * bch2_btree_iter_peek_all_levels() - returns the first key greater than or
- * equal to iterator's current position, returning keys from every level of the
- * btree. For keys at different levels of the btree that compare equal, the key
- * from the lower level (leaf) is returned first.
- * @iter:	iterator to peek from
- *
- * Returns:	key if found, or an error extractable with bkey_err().
- */
-struct bkey_s_c bch2_btree_iter_peek_all_levels(struct btree_iter *iter)
-{
-	struct btree_trans *trans = iter->trans;
-	struct bkey_s_c k;
-	int ret;
-
-	EBUG_ON(iter->path->cached);
-	bch2_btree_iter_verify(iter);
-	BUG_ON(iter->path->level < iter->min_depth);
-	BUG_ON(!(iter->flags & BTREE_ITER_ALL_SNAPSHOTS));
-	EBUG_ON(!(iter->flags & BTREE_ITER_ALL_LEVELS));
-
-	while (1) {
-		iter->path = bch2_btree_path_set_pos(trans, iter->path, iter->pos,
-					iter->flags & BTREE_ITER_INTENT,
-					btree_iter_ip_allocated(iter));
-
-		ret = bch2_btree_path_traverse(trans, iter->path, iter->flags);
-		if (unlikely(ret)) {
-			/* ensure that iter->k is consistent with iter->pos: */
-			bch2_btree_iter_set_pos(iter, iter->pos);
-			k = bkey_s_c_err(ret);
-			goto out_no_locked;
-		}
-
-		/* Already at end? */
-		if (!btree_path_node(iter->path, iter->path->level)) {
-			k = bkey_s_c_null;
-			goto out_no_locked;
-		}
-
-		k = btree_path_level_peek_all(trans->c,
-				&iter->path->l[iter->path->level], &iter->k);
-
-		/* Check if we should go up to the parent node: */
-		if (!k.k ||
-		    (iter->advanced &&
-		     bpos_eq(path_l(iter->path)->b->key.k.p, iter->pos))) {
-			iter->pos = path_l(iter->path)->b->key.k.p;
-			btree_path_set_level_up(trans, iter->path);
-			iter->advanced = false;
-			continue;
-		}
-
-		/*
-		 * Check if we should go back down to a leaf:
-		 * If we're not in a leaf node, we only return the current key
-		 * if it exactly matches iter->pos - otherwise we first have to
-		 * go back to the leaf:
-		 */
-		if (iter->path->level != iter->min_depth &&
-		    (iter->advanced ||
-		     !k.k ||
-		     !bpos_eq(iter->pos, k.k->p))) {
-			btree_path_set_level_down(trans, iter->path, iter->min_depth);
-			iter->pos = bpos_successor(iter->pos);
-			iter->advanced = false;
-			continue;
-		}
-
-		/* Check if we should go to the next key: */
-		if (iter->path->level == iter->min_depth &&
-		    iter->advanced &&
-		    k.k &&
-		    bpos_eq(iter->pos, k.k->p)) {
-			iter->pos = bpos_successor(iter->pos);
-			iter->advanced = false;
-			continue;
-		}
-
-		if (iter->advanced &&
-		    iter->path->level == iter->min_depth &&
-		    !bpos_eq(k.k->p, iter->pos))
-			iter->advanced = false;
-
-		BUG_ON(iter->advanced);
-		BUG_ON(!k.k);
-		break;
-	}
-
-	iter->pos = k.k->p;
-	btree_path_set_should_be_locked(iter->path);
-out_no_locked:
-	bch2_btree_iter_verify(iter);
-
-	return k;
-}
-
-/**
  * bch2_btree_iter_next() - returns first key greater than iterator's current
  * position
  * @iter:	iterator to peek from
@@ -2315,14 +2293,14 @@ struct bkey_s_c bch2_btree_iter_peek_prev(struct btree_iter *iter)
 {
 	struct btree_trans *trans = iter->trans;
 	struct bpos search_key = iter->pos;
-	struct btree_path *saved_path = NULL;
 	struct bkey_s_c k;
 	struct bkey saved_k;
 	const struct bch_val *saved_v;
+	btree_path_idx_t saved_path = 0;
 	int ret;
 
-	EBUG_ON(iter->path->cached || iter->path->level);
-	EBUG_ON(iter->flags & BTREE_ITER_WITH_UPDATES);
+	EBUG_ON(btree_iter_path(trans, iter)->cached ||
+		btree_iter_path(trans, iter)->level);
 
 	if (iter->flags & BTREE_ITER_WITH_JOURNAL)
 		return bkey_s_c_err(-EIO);
@@ -2346,14 +2324,18 @@ struct bkey_s_c bch2_btree_iter_peek_prev(struct btree_iter *iter)
 			goto out_no_locked;
 		}
 
-		k = btree_path_level_peek(trans, iter->path,
-					  &iter->path->l[0], &iter->k);
+		struct btree_path *path = btree_iter_path(trans, iter);
+
+		k = btree_path_level_peek(trans, path, &path->l[0], &iter->k);
 		if (!k.k ||
 		    ((iter->flags & BTREE_ITER_IS_EXTENTS)
 		     ? bpos_ge(bkey_start_pos(k.k), search_key)
 		     : bpos_gt(k.k->p, search_key)))
-			k = btree_path_level_prev(trans, iter->path,
-						  &iter->path->l[0], &iter->k);
+			k = btree_path_level_prev(trans, path, &path->l[0], &iter->k);
+
+		if (unlikely((iter->flags & BTREE_ITER_WITH_UPDATES) &&
+			     trans->nr_updates))
+			bch2_btree_trans_peek_prev_updates(trans, iter, &k);
 
 		if (likely(k.k)) {
 			if (iter->flags & BTREE_ITER_FILTER_SNAPSHOTS) {
@@ -2369,13 +2351,13 @@ struct bkey_s_c bch2_btree_iter_peek_prev(struct btree_iter *iter)
 					bch2_path_put_nokeep(trans, iter->path,
 						      iter->flags & BTREE_ITER_INTENT);
 					iter->path = saved_path;
-					saved_path = NULL;
+					saved_path = 0;
 					iter->k	= saved_k;
 					k.v	= saved_v;
 					goto got_key;
 				}
 
-				if (bch2_snapshot_is_ancestor(iter->trans->c,
+				if (bch2_snapshot_is_ancestor(trans->c,
 							      iter->snapshot,
 							      k.k->p.snapshot)) {
 					if (saved_path)
@@ -2383,6 +2365,7 @@ struct bkey_s_c bch2_btree_iter_peek_prev(struct btree_iter *iter)
 						      iter->flags & BTREE_ITER_INTENT);
 					saved_path = btree_path_clone(trans, iter->path,
 								iter->flags & BTREE_ITER_INTENT);
+					path = btree_iter_path(trans, iter);
 					saved_k = *k.k;
 					saved_v = k.v;
 				}
@@ -2399,10 +2382,11 @@ got_key:
 				continue;
 			}
 
+			btree_path_set_should_be_locked(path);
 			break;
-		} else if (likely(!bpos_eq(iter->path->l[0].b->data->min_key, POS_MIN))) {
+		} else if (likely(!bpos_eq(path->l[0].b->data->min_key, POS_MIN))) {
 			/* Advance to previous leaf node: */
-			search_key = bpos_predecessor(iter->path->l[0].b->data->min_key);
+			search_key = bpos_predecessor(path->l[0].b->data->min_key);
 		} else {
 			/* Start of btree: */
 			bch2_btree_iter_set_pos(iter, POS_MIN);
@@ -2419,8 +2403,6 @@ got_key:
 
 	if (iter->flags & BTREE_ITER_FILTER_SNAPSHOTS)
 		iter->pos.snapshot = iter->snapshot;
-
-	btree_path_set_should_be_locked(iter->path);
 out_no_locked:
 	if (saved_path)
 		bch2_path_put_nokeep(trans, saved_path, iter->flags & BTREE_ITER_INTENT);
@@ -2455,8 +2437,7 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_iter *iter)
 
 	bch2_btree_iter_verify(iter);
 	bch2_btree_iter_verify_entry_exit(iter);
-	EBUG_ON(iter->flags & BTREE_ITER_ALL_LEVELS);
-	EBUG_ON(iter->path->level && (iter->flags & BTREE_ITER_WITH_KEY_CACHE));
+	EBUG_ON(btree_iter_path(trans, iter)->level && (iter->flags & BTREE_ITER_WITH_KEY_CACHE));
 
 	/* extents can't span inode numbers: */
 	if ((iter->flags & BTREE_ITER_IS_EXTENTS) &&
@@ -2480,13 +2461,13 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_iter *iter)
 
 	if ((iter->flags & BTREE_ITER_CACHED) ||
 	    !(iter->flags & (BTREE_ITER_IS_EXTENTS|BTREE_ITER_FILTER_SNAPSHOTS))) {
-		struct bkey_i *next_update;
+		k = bkey_s_c_null;
 
-		if ((next_update = btree_trans_peek_updates(iter)) &&
-		    bpos_eq(next_update->k.p, iter->pos)) {
-			iter->k = next_update->k;
-			k = bkey_i_to_s_c(next_update);
-			goto out;
+		if (unlikely((iter->flags & BTREE_ITER_WITH_UPDATES) &&
+			     trans->nr_updates)) {
+			bch2_btree_trans_peek_slot_updates(trans, iter, &k);
+			if (k.k)
+				goto out;
 		}
 
 		if (unlikely(iter->flags & BTREE_ITER_WITH_JOURNAL) &&
@@ -2501,7 +2482,7 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_iter *iter)
 			goto out_no_locked;
 		}
 
-		k = bch2_btree_path_peek_slot(iter->path, &iter->k);
+		k = bch2_btree_path_peek_slot(trans->paths + iter->path, &iter->k);
 		if (unlikely(!k.k))
 			goto out_no_locked;
 	} else {
@@ -2511,7 +2492,7 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_iter *iter)
 		if (iter->flags & BTREE_ITER_IS_EXTENTS)
 			end.offset = U64_MAX;
 
-		EBUG_ON(iter->path->level);
+		EBUG_ON(btree_iter_path(trans, iter)->level);
 
 		if (iter->flags & BTREE_ITER_INTENT) {
 			struct btree_iter iter2;
@@ -2557,7 +2538,7 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_iter *iter)
 		}
 	}
 out:
-	btree_path_set_should_be_locked(iter->path);
+	btree_path_set_should_be_locked(btree_iter_path(trans, iter));
 out_no_locked:
 	bch2_btree_iter_verify_entry_exit(iter);
 	bch2_btree_iter_verify(iter);
@@ -2604,17 +2585,17 @@ static void btree_trans_verify_sorted_refs(struct btree_trans *trans)
 	struct btree_path *path;
 	unsigned i;
 
-	BUG_ON(trans->nr_sorted != hweight64(trans->paths_allocated));
+	BUG_ON(trans->nr_sorted != bitmap_weight(trans->paths_allocated, trans->nr_paths) - 1);
 
-	trans_for_each_path(trans, path) {
+	trans_for_each_path(trans, path, i) {
 		BUG_ON(path->sorted_idx >= trans->nr_sorted);
-		BUG_ON(trans->sorted[path->sorted_idx] != path->idx);
+		BUG_ON(trans->sorted[path->sorted_idx] != i);
 	}
 
 	for (i = 0; i < trans->nr_sorted; i++) {
 		unsigned idx = trans->sorted[i];
 
-		EBUG_ON(!(trans->paths_allocated & (1ULL << idx)));
+		BUG_ON(!test_bit(idx, trans->paths_allocated));
 		BUG_ON(trans->paths[idx].sorted_idx != i);
 	}
 }
@@ -2622,12 +2603,12 @@ static void btree_trans_verify_sorted_refs(struct btree_trans *trans)
 static void btree_trans_verify_sorted(struct btree_trans *trans)
 {
 	struct btree_path *path, *prev = NULL;
-	unsigned i;
+	struct trans_for_each_path_inorder_iter iter;
 
 	if (!bch2_debug_check_iterators)
 		return;
 
-	trans_for_each_path_inorder(trans, path, i) {
+	trans_for_each_path_inorder(trans, path, iter) {
 		if (prev && btree_path_cmp(prev, path) > 0) {
 			__bch2_dump_trans_paths_updates(trans, true);
 			panic("trans paths out of order!\n");
@@ -2684,42 +2665,40 @@ out:
 static inline void btree_path_list_remove(struct btree_trans *trans,
 					  struct btree_path *path)
 {
-	unsigned i;
-
 	EBUG_ON(path->sorted_idx >= trans->nr_sorted);
 #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 	trans->nr_sorted--;
 	memmove_u64s_down_small(trans->sorted + path->sorted_idx,
 				trans->sorted + path->sorted_idx + 1,
-				DIV_ROUND_UP(trans->nr_sorted - path->sorted_idx, 8));
+				DIV_ROUND_UP(trans->nr_sorted - path->sorted_idx,
+					     sizeof(u64) / sizeof(btree_path_idx_t)));
 #else
 	array_remove_item(trans->sorted, trans->nr_sorted, path->sorted_idx);
 #endif
-	for (i = path->sorted_idx; i < trans->nr_sorted; i++)
+	for (unsigned i = path->sorted_idx; i < trans->nr_sorted; i++)
 		trans->paths[trans->sorted[i]].sorted_idx = i;
-
-	path->sorted_idx = U8_MAX;
 }
 
 static inline void btree_path_list_add(struct btree_trans *trans,
-				       struct btree_path *pos,
-				       struct btree_path *path)
+				       btree_path_idx_t pos,
+				       btree_path_idx_t path_idx)
 {
-	unsigned i;
+	struct btree_path *path = trans->paths + path_idx;
 
-	path->sorted_idx = pos ? pos->sorted_idx + 1 : trans->nr_sorted;
+	path->sorted_idx = pos ? trans->paths[pos].sorted_idx + 1 : trans->nr_sorted;
 
 #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 	memmove_u64s_up_small(trans->sorted + path->sorted_idx + 1,
 			      trans->sorted + path->sorted_idx,
-			      DIV_ROUND_UP(trans->nr_sorted - path->sorted_idx, 8));
+			      DIV_ROUND_UP(trans->nr_sorted - path->sorted_idx,
+					   sizeof(u64) / sizeof(btree_path_idx_t)));
 	trans->nr_sorted++;
-	trans->sorted[path->sorted_idx] = path->idx;
+	trans->sorted[path->sorted_idx] = path_idx;
 #else
-	array_insert_item(trans->sorted, trans->nr_sorted, path->sorted_idx, path->idx);
+	array_insert_item(trans->sorted, trans->nr_sorted, path->sorted_idx, path_idx);
 #endif
 
-	for (i = path->sorted_idx; i < trans->nr_sorted; i++)
+	for (unsigned i = path->sorted_idx; i < trans->nr_sorted; i++)
 		trans->paths[trans->sorted[i]].sorted_idx = i;
 
 	btree_trans_verify_sorted_refs(trans);
@@ -2736,9 +2715,10 @@ void bch2_trans_iter_exit(struct btree_trans *trans, struct btree_iter *iter)
 	if (iter->key_cache_path)
 		bch2_path_put(trans, iter->key_cache_path,
 			      iter->flags & BTREE_ITER_INTENT);
-	iter->path = NULL;
-	iter->update_path = NULL;
-	iter->key_cache_path = NULL;
+	iter->path		= 0;
+	iter->update_path	= 0;
+	iter->key_cache_path	= 0;
+	iter->trans		= NULL;
 }
 
 void bch2_trans_iter_init_outlined(struct btree_trans *trans,
@@ -2769,41 +2749,46 @@ void bch2_trans_node_iter_init(struct btree_trans *trans,
 
 	iter->min_depth	= depth;
 
-	BUG_ON(iter->path->locks_want	 < min(locks_want, BTREE_MAX_DEPTH));
-	BUG_ON(iter->path->level	!= depth);
-	BUG_ON(iter->min_depth		!= depth);
+	struct btree_path *path = btree_iter_path(trans, iter);
+	BUG_ON(path->locks_want	 < min(locks_want, BTREE_MAX_DEPTH));
+	BUG_ON(path->level	!= depth);
+	BUG_ON(iter->min_depth	!= depth);
 }
 
 void bch2_trans_copy_iter(struct btree_iter *dst, struct btree_iter *src)
 {
+	struct btree_trans *trans = src->trans;
+
 	*dst = *src;
 	if (src->path)
-		__btree_path_get(src->path, src->flags & BTREE_ITER_INTENT);
+		__btree_path_get(trans->paths + src->path, src->flags & BTREE_ITER_INTENT);
 	if (src->update_path)
-		__btree_path_get(src->update_path, src->flags & BTREE_ITER_INTENT);
-	dst->key_cache_path = NULL;
+		__btree_path_get(trans->paths + src->update_path, src->flags & BTREE_ITER_INTENT);
+	dst->key_cache_path = 0;
 }
 
 void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size)
 {
+	struct bch_fs *c = trans->c;
 	unsigned new_top = trans->mem_top + size;
-	size_t old_bytes = trans->mem_bytes;
-	size_t new_bytes = roundup_pow_of_two(new_top);
+	unsigned old_bytes = trans->mem_bytes;
+	unsigned new_bytes = roundup_pow_of_two(new_top);
 	int ret;
 	void *new_mem;
 	void *p;
 
-	trans->mem_max = max(trans->mem_max, new_top);
-
 	WARN_ON_ONCE(new_bytes > BTREE_TRANS_MEM_MAX);
 
+	struct btree_transaction_stats *s = btree_trans_stats(trans);
+	s->max_mem = max(s->max_mem, new_bytes);
+
 	new_mem = krealloc(trans->mem, new_bytes, GFP_NOWAIT|__GFP_NOWARN);
 	if (unlikely(!new_mem)) {
 		bch2_trans_unlock(trans);
 
 		new_mem = krealloc(trans->mem, new_bytes, GFP_KERNEL);
 		if (!new_mem && new_bytes <= BTREE_TRANS_MEM_MAX) {
-			new_mem = mempool_alloc(&trans->c->btree_trans_mem_pool, GFP_KERNEL);
+			new_mem = mempool_alloc(&c->btree_trans_mem_pool, GFP_KERNEL);
 			new_bytes = BTREE_TRANS_MEM_MAX;
 			kfree(trans->mem);
 		}
@@ -2823,7 +2808,7 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size)
 	trans->mem_bytes = new_bytes;
 
 	if (old_bytes) {
-		trace_and_count(trans->c, trans_restart_mem_realloced, trans, _RET_IP_, new_bytes);
+		trace_and_count(c, trans_restart_mem_realloced, trans, _RET_IP_, new_bytes);
 		return ERR_PTR(btree_trans_restart(trans, BCH_ERR_transaction_restart_mem_realloced));
 	}
 
@@ -2845,8 +2830,9 @@ void bch2_trans_srcu_unlock(struct btree_trans *trans)
 	if (trans->srcu_held) {
 		struct bch_fs *c = trans->c;
 		struct btree_path *path;
+		unsigned i;
 
-		trans_for_each_path(trans, path)
+		trans_for_each_path(trans, path, i)
 			if (path->cached && !btree_node_locked(path, 0))
 				path->l[0].b = ERR_PTR(-BCH_ERR_no_btree_node_srcu_reset);
 
@@ -2856,7 +2842,7 @@ void bch2_trans_srcu_unlock(struct btree_trans *trans)
 	}
 }
 
-void bch2_trans_srcu_lock(struct btree_trans *trans)
+static void bch2_trans_srcu_lock(struct btree_trans *trans)
 {
 	if (!trans->srcu_held) {
 		trans->srcu_idx = srcu_read_lock(&trans->c->btree_trans_barrier);
@@ -2878,14 +2864,16 @@ void bch2_trans_srcu_lock(struct btree_trans *trans)
 u32 bch2_trans_begin(struct btree_trans *trans)
 {
 	struct btree_path *path;
+	unsigned i;
 	u64 now;
 
 	bch2_trans_reset_updates(trans);
 
 	trans->restart_count++;
 	trans->mem_top			= 0;
+	trans->journal_entries		= NULL;
 
-	trans_for_each_path(trans, path) {
+	trans_for_each_path(trans, path, i) {
 		path->should_be_locked = false;
 
 		/*
@@ -2902,15 +2890,21 @@ u32 bch2_trans_begin(struct btree_trans *trans)
 		 * iterators if we do that
 		 */
 		if (!path->ref && !path->preserve)
-			__bch2_path_free(trans, path);
+			__bch2_path_free(trans, i);
 		else
 			path->preserve = false;
 	}
 
 	now = local_clock();
+
+	if (!IS_ENABLED(CONFIG_BCACHEFS_NO_LATENCY_ACCT) &&
+	    time_after64(now, trans->last_begin_time + 10))
+		__bch2_time_stats_update(&btree_trans_stats(trans)->duration,
+					 trans->last_begin_time, now);
+
 	if (!trans->restarted &&
 	    (need_resched() ||
-	     now - trans->last_begin_time > BTREE_TRANS_MAX_LOCK_HOLD_TIME_NS)) {
+	     time_after64(now, trans->last_begin_time + BTREE_TRANS_MAX_LOCK_HOLD_TIME_NS))) {
 		drop_locks_do(trans, (cond_resched(), 0));
 		now = local_clock();
 	}
@@ -2929,32 +2923,11 @@ u32 bch2_trans_begin(struct btree_trans *trans)
 	return trans->restart_count;
 }
 
-static struct btree_trans *bch2_trans_alloc(struct bch_fs *c)
-{
-	struct btree_trans *trans;
-
-	if (IS_ENABLED(__KERNEL__)) {
-		trans = this_cpu_xchg(c->btree_trans_bufs->trans, NULL);
-		if (trans)
-			return trans;
-	}
-
-	trans = mempool_alloc(&c->btree_trans_pool, GFP_NOFS);
-	/*
-	 * paths need to be zeroed, bch2_check_for_deadlock looks at
-	 * paths in other threads
-	 */
-	memset(&trans->paths, 0, sizeof(trans->paths));
-	return trans;
-}
-
-const char *bch2_btree_transaction_fns[BCH_TRANSACTIONS_NR];
+const char *bch2_btree_transaction_fns[BCH_TRANSACTIONS_NR] = { "(unknown)" };
 
 unsigned bch2_trans_get_fn_idx(const char *fn)
 {
-	unsigned i;
-
-	for (i = 0; i < ARRAY_SIZE(bch2_btree_transaction_fns); i++)
+	for (unsigned i = 0; i < ARRAY_SIZE(bch2_btree_transaction_fns); i++)
 		if (!bch2_btree_transaction_fns[i] ||
 		    bch2_btree_transaction_fns[i] == fn) {
 			bch2_btree_transaction_fns[i] = fn;
@@ -2962,75 +2935,92 @@ unsigned bch2_trans_get_fn_idx(const char *fn)
 		}
 
 	pr_warn_once("BCH_TRANSACTIONS_NR not big enough!");
-	return i;
+	return 0;
 }
 
 struct btree_trans *__bch2_trans_get(struct bch_fs *c, unsigned fn_idx)
 	__acquires(&c->btree_trans_barrier)
 {
 	struct btree_trans *trans;
-	struct btree_transaction_stats *s;
-
-	trans = bch2_trans_alloc(c);
-
-	memset(trans, 0, sizeof(*trans));
-	trans->c		= c;
-	trans->fn		= fn_idx < ARRAY_SIZE(bch2_btree_transaction_fns)
-		? bch2_btree_transaction_fns[fn_idx] : NULL;
-	trans->last_begin_time	= local_clock();
-	trans->fn_idx		= fn_idx;
-	trans->locking_wait.task = current;
-	trans->journal_replay_not_finished =
-		!test_bit(JOURNAL_REPLAY_DONE, &c->journal.flags);
-	closure_init_stack(&trans->ref);
-
-	s = btree_trans_stats(trans);
-	if (s && s->max_mem) {
-		unsigned expected_mem_bytes = roundup_pow_of_two(s->max_mem);
-
-		trans->mem = kmalloc(expected_mem_bytes, GFP_KERNEL);
 
-		if (!unlikely(trans->mem)) {
-			trans->mem = mempool_alloc(&c->btree_trans_mem_pool, GFP_KERNEL);
-			trans->mem_bytes = BTREE_TRANS_MEM_MAX;
-		} else {
-			trans->mem_bytes = expected_mem_bytes;
+	if (IS_ENABLED(__KERNEL__)) {
+		trans = this_cpu_xchg(c->btree_trans_bufs->trans, NULL);
+		if (trans) {
+			memset(trans, 0, offsetof(struct btree_trans, list));
+			goto got_trans;
 		}
 	}
 
-	if (s) {
-		trans->nr_max_paths = s->nr_max_paths;
-		trans->wb_updates_size = s->wb_updates_size;
-	}
-
-	trans->srcu_idx		= srcu_read_lock(&c->btree_trans_barrier);
-	trans->srcu_lock_time	= jiffies;
-	trans->srcu_held	= true;
+	trans = mempool_alloc(&c->btree_trans_pool, GFP_NOFS);
+	memset(trans, 0, sizeof(*trans));
+	closure_init_stack(&trans->ref);
 
-	if (IS_ENABLED(CONFIG_BCACHEFS_DEBUG_TRANSACTIONS)) {
+	seqmutex_lock(&c->btree_trans_lock);
+	if (IS_ENABLED(CONFIG_BCACHEFS_DEBUG)) {
 		struct btree_trans *pos;
+		pid_t pid = current->pid;
+
+		trans->locking_wait.task = current;
 
-		seqmutex_lock(&c->btree_trans_lock);
 		list_for_each_entry(pos, &c->btree_trans_list, list) {
+			struct task_struct *pos_task = READ_ONCE(pos->locking_wait.task);
 			/*
 			 * We'd much prefer to be stricter here and completely
 			 * disallow multiple btree_trans in the same thread -
 			 * but the data move path calls bch2_write when we
 			 * already have a btree_trans initialized.
 			 */
-			BUG_ON(trans->locking_wait.task->pid == pos->locking_wait.task->pid &&
+			BUG_ON(pos_task &&
+			       pid == pos_task->pid &&
 			       bch2_trans_locked(pos));
 
-			if (trans->locking_wait.task->pid < pos->locking_wait.task->pid) {
+			if (pos_task && pid < pos_task->pid) {
 				list_add_tail(&trans->list, &pos->list);
 				goto list_add_done;
 			}
 		}
-		list_add_tail(&trans->list, &c->btree_trans_list);
+	}
+	list_add_tail(&trans->list, &c->btree_trans_list);
 list_add_done:
-		seqmutex_unlock(&c->btree_trans_lock);
+	seqmutex_unlock(&c->btree_trans_lock);
+got_trans:
+	trans->c		= c;
+	trans->last_begin_time	= local_clock();
+	trans->fn_idx		= fn_idx;
+	trans->locking_wait.task = current;
+	trans->journal_replay_not_finished =
+		unlikely(!test_bit(JOURNAL_REPLAY_DONE, &c->journal.flags)) &&
+		atomic_inc_not_zero(&c->journal_keys.ref);
+	trans->nr_paths		= ARRAY_SIZE(trans->_paths);
+	trans->paths_allocated	= trans->_paths_allocated;
+	trans->sorted		= trans->_sorted;
+	trans->paths		= trans->_paths;
+	trans->updates		= trans->_updates;
+
+	*trans_paths_nr(trans->paths) = BTREE_ITER_INITIAL;
+
+	trans->paths_allocated[0] = 1;
+
+	if (fn_idx < BCH_TRANSACTIONS_NR) {
+		trans->fn = bch2_btree_transaction_fns[fn_idx];
+
+		struct btree_transaction_stats *s = &c->btree_transaction_stats[fn_idx];
+
+		if (s->max_mem) {
+			unsigned expected_mem_bytes = roundup_pow_of_two(s->max_mem);
+
+			trans->mem = kmalloc(expected_mem_bytes, GFP_KERNEL);
+			if (likely(trans->mem))
+				trans->mem_bytes = expected_mem_bytes;
+		}
+
+		trans->nr_paths_max = s->nr_max_paths;
+		trans->journal_entries_size = s->journal_entries_size;
 	}
 
+	trans->srcu_idx		= srcu_read_lock(&c->btree_trans_barrier);
+	trans->srcu_lock_time	= jiffies;
+	trans->srcu_held	= true;
 	return trans;
 }
 
@@ -3039,14 +3029,15 @@ static void check_btree_paths_leaked(struct btree_trans *trans)
 #ifdef CONFIG_BCACHEFS_DEBUG
 	struct bch_fs *c = trans->c;
 	struct btree_path *path;
+	unsigned i;
 
-	trans_for_each_path(trans, path)
+	trans_for_each_path(trans, path, i)
 		if (path->ref)
 			goto leaked;
 	return;
 leaked:
 	bch_err(c, "btree paths leaked from %s!", trans->fn);
-	trans_for_each_path(trans, path)
+	trans_for_each_path(trans, path, i)
 		if (path->ref)
 			printk(KERN_ERR "  btree %s %pS\n",
 			       bch2_btree_id_str(path->btree_id),
@@ -3059,26 +3050,14 @@ leaked:
 void bch2_trans_put(struct btree_trans *trans)
 	__releases(&c->btree_trans_barrier)
 {
-	struct btree_insert_entry *i;
 	struct bch_fs *c = trans->c;
-	struct btree_transaction_stats *s = btree_trans_stats(trans);
 
 	bch2_trans_unlock(trans);
 
-	if (IS_ENABLED(CONFIG_BCACHEFS_DEBUG_TRANSACTIONS)) {
-		seqmutex_lock(&c->btree_trans_lock);
-		list_del(&trans->list);
-		seqmutex_unlock(&c->btree_trans_lock);
-	}
-
-	closure_sync(&trans->ref);
-
-	if (s)
-		s->max_mem = max(s->max_mem, trans->mem_max);
-
 	trans_for_each_update(trans, i)
-		__btree_path_put(i->path, true);
-	trans->nr_updates		= 0;
+		__btree_path_put(trans->paths + i->path, true);
+	trans->nr_updates	= 0;
+	trans->locking_wait.task = NULL;
 
 	check_btree_paths_leaked(trans);
 
@@ -3087,10 +3066,6 @@ void bch2_trans_put(struct btree_trans *trans)
 		srcu_read_unlock(&c->btree_trans_barrier, trans->srcu_idx);
 	}
 
-	bch2_journal_preres_put(&c->journal, &trans->journal_preres);
-
-	kfree(trans->extra_journal_entries.data);
-
 	if (trans->fs_usage_deltas) {
 		if (trans->fs_usage_deltas->size + sizeof(trans->fs_usage_deltas) ==
 		    REPLICAS_DELTA_LIST_MAX)
@@ -3100,6 +3075,16 @@ void bch2_trans_put(struct btree_trans *trans)
 			kfree(trans->fs_usage_deltas);
 	}
 
+	if (unlikely(trans->journal_replay_not_finished))
+		bch2_journal_keys_put(c);
+
+	unsigned long *paths_allocated = trans->paths_allocated;
+	trans->paths_allocated	= NULL;
+	trans->paths		= NULL;
+
+	if (paths_allocated != trans->_paths_allocated)
+		kfree_rcu_mightsleep(paths_allocated);
+
 	if (trans->mem_bytes == BTREE_TRANS_MEM_MAX)
 		mempool_free(trans->mem, &c->btree_trans_mem_pool);
 	else
@@ -3108,8 +3093,16 @@ void bch2_trans_put(struct btree_trans *trans)
 	/* Userspace doesn't have a real percpu implementation: */
 	if (IS_ENABLED(__KERNEL__))
 		trans = this_cpu_xchg(c->btree_trans_bufs->trans, trans);
-	if (trans)
+
+	if (trans) {
+		closure_sync(&trans->ref);
+
+		seqmutex_lock(&c->btree_trans_lock);
+		list_del(&trans->list);
+		seqmutex_unlock(&c->btree_trans_lock);
+
 		mempool_free(trans, &c->btree_trans_pool);
+	}
 }
 
 static void __maybe_unused
@@ -3137,24 +3130,38 @@ bch2_btree_bkey_cached_common_to_text(struct printbuf *out,
 
 void bch2_btree_trans_to_text(struct printbuf *out, struct btree_trans *trans)
 {
-	struct btree_path *path;
 	struct btree_bkey_cached_common *b;
 	static char lock_types[] = { 'r', 'i', 'w' };
+	struct task_struct *task = READ_ONCE(trans->locking_wait.task);
 	unsigned l, idx;
 
+	/* before rcu_read_lock(): */
+	bch2_printbuf_make_room(out, 4096);
+
 	if (!out->nr_tabstops) {
 		printbuf_tabstop_push(out, 16);
 		printbuf_tabstop_push(out, 32);
 	}
 
-	prt_printf(out, "%i %s\n", trans->locking_wait.task->pid, trans->fn);
+	prt_printf(out, "%i %s\n", task ? task->pid : 0, trans->fn);
+
+	/* trans->paths is rcu protected vs. freeing */
+	rcu_read_lock();
+	out->atomic++;
 
-	trans_for_each_path_safe(trans, path, idx) {
+	struct btree_path *paths = rcu_dereference(trans->paths);
+	if (!paths)
+		goto out;
+
+	unsigned long *paths_allocated = trans_paths_allocated(paths);
+
+	trans_for_each_path_idx_from(paths_allocated, *trans_paths_nr(paths), idx, 1) {
+		struct btree_path *path = paths + idx;
 		if (!path->nodes_locked)
 			continue;
 
 		prt_printf(out, "  path %u %c l=%u %s:",
-		       path->idx,
+		       idx,
 		       path->cached ? 'c' : 'b',
 		       path->level,
 		       bch2_btree_id_str(path->btree_id));
@@ -3182,6 +3189,9 @@ void bch2_btree_trans_to_text(struct printbuf *out, struct btree_trans *trans)
 		bch2_btree_bkey_cached_common_to_text(out, b);
 		prt_newline(out);
 	}
+out:
+	--out->atomic;
+	rcu_read_unlock();
 }
 
 void bch2_fs_btree_iter_exit(struct bch_fs *c)
@@ -3190,15 +3200,26 @@ void bch2_fs_btree_iter_exit(struct bch_fs *c)
 	struct btree_trans *trans;
 	int cpu;
 
+	if (c->btree_trans_bufs)
+		for_each_possible_cpu(cpu) {
+			struct btree_trans *trans =
+				per_cpu_ptr(c->btree_trans_bufs, cpu)->trans;
+
+			if (trans) {
+				closure_sync(&trans->ref);
+
+				seqmutex_lock(&c->btree_trans_lock);
+				list_del(&trans->list);
+				seqmutex_unlock(&c->btree_trans_lock);
+			}
+			kfree(trans);
+		}
+	free_percpu(c->btree_trans_bufs);
+
 	trans = list_first_entry_or_null(&c->btree_trans_list, struct btree_trans, list);
 	if (trans)
 		panic("%s leaked btree_trans\n", trans->fn);
 
-	if (c->btree_trans_bufs)
-		for_each_possible_cpu(cpu)
-			kfree(per_cpu_ptr(c->btree_trans_bufs, cpu)->trans);
-	free_percpu(c->btree_trans_bufs);
-
 	for (s = c->btree_transaction_stats;
 	     s < c->btree_transaction_stats + ARRAY_SIZE(c->btree_transaction_stats);
 	     s++) {
@@ -3212,20 +3233,25 @@ void bch2_fs_btree_iter_exit(struct bch_fs *c)
 	mempool_exit(&c->btree_trans_pool);
 }
 
-int bch2_fs_btree_iter_init(struct bch_fs *c)
+void bch2_fs_btree_iter_init_early(struct bch_fs *c)
 {
 	struct btree_transaction_stats *s;
-	int ret;
 
 	for (s = c->btree_transaction_stats;
 	     s < c->btree_transaction_stats + ARRAY_SIZE(c->btree_transaction_stats);
 	     s++) {
+		bch2_time_stats_init(&s->duration);
 		bch2_time_stats_init(&s->lock_hold_times);
 		mutex_init(&s->lock);
 	}
 
 	INIT_LIST_HEAD(&c->btree_trans_list);
 	seqmutex_init(&c->btree_trans_lock);
+}
+
+int bch2_fs_btree_iter_init(struct bch_fs *c)
+{
+	int ret;
 
 	c->btree_trans_bufs = alloc_percpu(struct btree_trans_buf);
 	if (!c->btree_trans_bufs)
diff --git a/fs/bcachefs/btree_iter.h b/fs/bcachefs/btree_iter.h
index 85e7cb52f6b6..da2b74fa63fc 100644
--- a/fs/bcachefs/btree_iter.h
+++ b/fs/bcachefs/btree_iter.h
@@ -63,60 +63,57 @@ static inline void btree_trans_sort_paths(struct btree_trans *trans)
 	__bch2_btree_trans_sort_paths(trans);
 }
 
-static inline struct btree_path *
-__trans_next_path(struct btree_trans *trans, unsigned idx)
+static inline unsigned long *trans_paths_nr(struct btree_path *paths)
 {
-	u64 l;
-
-	if (idx == BTREE_ITER_MAX)
-		return NULL;
-
-	l = trans->paths_allocated >> idx;
-	if (!l)
-		return NULL;
-
-	idx += __ffs64(l);
-	EBUG_ON(idx >= BTREE_ITER_MAX);
-	EBUG_ON(trans->paths[idx].idx != idx);
-	return &trans->paths[idx];
+	return &container_of(paths, struct btree_trans_paths, paths[0])->nr_paths;
 }
 
-#define trans_for_each_path_from(_trans, _path, _start)			\
-	for (_path = __trans_next_path((_trans), _start);		\
-	     (_path);							\
-	     _path = __trans_next_path((_trans), (_path)->idx + 1))
-
-#define trans_for_each_path(_trans, _path)				\
-	trans_for_each_path_from(_trans, _path, 0)
-
-static inline struct btree_path *
-__trans_next_path_safe(struct btree_trans *trans, unsigned *idx)
+static inline unsigned long *trans_paths_allocated(struct btree_path *paths)
 {
-	u64 l;
+	unsigned long *v = trans_paths_nr(paths);
+	return v - BITS_TO_LONGS(*v);
+}
 
-	if (*idx == BTREE_ITER_MAX)
-		return NULL;
+#define trans_for_each_path_idx_from(_paths_allocated, _nr, _idx, _start)\
+	for (_idx = _start;						\
+	     (_idx = find_next_bit(_paths_allocated, _nr, _idx)) < _nr;	\
+	     _idx++)
 
-	l = trans->paths_allocated >> *idx;
-	if (!l)
-		return NULL;
+static inline struct btree_path *
+__trans_next_path(struct btree_trans *trans, unsigned *idx)
+{
+	unsigned long *w = trans->paths_allocated + *idx / BITS_PER_LONG;
+	/*
+	 * Open coded find_next_bit(), because
+	 *  - this is fast path, we can't afford the function call
+	 *  - and we know that nr_paths is a multiple of BITS_PER_LONG,
+	 */
+	while (*idx < trans->nr_paths) {
+		unsigned long v = *w >> (*idx & (BITS_PER_LONG - 1));
+		if (v) {
+			*idx += __ffs(v);
+			return trans->paths + *idx;
+		}
+
+		*idx += BITS_PER_LONG;
+		*idx &= ~(BITS_PER_LONG - 1);
+		w++;
+	}
 
-	*idx += __ffs64(l);
-	EBUG_ON(*idx >= BTREE_ITER_MAX);
-	return &trans->paths[*idx];
+	return NULL;
 }
 
 /*
  * This version is intended to be safe for use on a btree_trans that is owned by
  * another thread, for bch2_btree_trans_to_text();
  */
-#define trans_for_each_path_safe_from(_trans, _path, _idx, _start)	\
+#define trans_for_each_path_from(_trans, _path, _idx, _start)		\
 	for (_idx = _start;						\
-	     (_path = __trans_next_path_safe((_trans), &_idx));		\
+	     (_path = __trans_next_path((_trans), &_idx));		\
 	     _idx++)
 
-#define trans_for_each_path_safe(_trans, _path, _idx)			\
-	trans_for_each_path_safe_from(_trans, _path, _idx, 0)
+#define trans_for_each_path(_trans, _path, _idx)			\
+	trans_for_each_path_from(_trans, _path, _idx, 1)
 
 static inline struct btree_path *next_btree_path(struct btree_trans *trans, struct btree_path *path)
 {
@@ -138,10 +135,23 @@ static inline struct btree_path *prev_btree_path(struct btree_trans *trans, stru
 		: NULL;
 }
 
-#define trans_for_each_path_inorder(_trans, _path, _i)			\
-	for (_i = 0;							\
-	     ((_path) = (_trans)->paths + trans->sorted[_i]), (_i) < (_trans)->nr_sorted;\
-	     _i++)
+#define trans_for_each_path_idx_inorder(_trans, _iter)			\
+	for (_iter = (struct trans_for_each_path_inorder_iter) { 0 };	\
+	     (_iter.path_idx = trans->sorted[_iter.sorted_idx],		\
+	      _iter.sorted_idx < (_trans)->nr_sorted);			\
+	     _iter.sorted_idx++)
+
+struct trans_for_each_path_inorder_iter {
+	btree_path_idx_t	sorted_idx;
+	btree_path_idx_t	path_idx;
+};
+
+#define trans_for_each_path_inorder(_trans, _path, _iter)		\
+	for (_iter = (struct trans_for_each_path_inorder_iter) { 0 };	\
+	     (_iter.path_idx = trans->sorted[_iter.sorted_idx],		\
+	      _path = (_trans)->paths + _iter.path_idx,			\
+	      _iter.sorted_idx < (_trans)->nr_sorted);			\
+	     _iter.sorted_idx++)
 
 #define trans_for_each_path_inorder_reverse(_trans, _path, _i)		\
 	for (_i = trans->nr_sorted - 1;					\
@@ -157,67 +167,65 @@ static inline bool __path_has_node(const struct btree_path *path,
 
 static inline struct btree_path *
 __trans_next_path_with_node(struct btree_trans *trans, struct btree *b,
-			    unsigned idx)
+			    unsigned *idx)
 {
-	struct btree_path *path = __trans_next_path(trans, idx);
+	struct btree_path *path;
 
-	while (path && !__path_has_node(path, b))
-		path = __trans_next_path(trans, path->idx + 1);
+	while ((path = __trans_next_path(trans, idx)) &&
+		!__path_has_node(path, b))
+	       (*idx)++;
 
 	return path;
 }
 
-#define trans_for_each_path_with_node(_trans, _b, _path)		\
-	for (_path = __trans_next_path_with_node((_trans), (_b), 0);	\
-	     (_path);							\
-	     _path = __trans_next_path_with_node((_trans), (_b),	\
-						 (_path)->idx + 1))
+#define trans_for_each_path_with_node(_trans, _b, _path, _iter)		\
+	for (_iter = 1;							\
+	     (_path = __trans_next_path_with_node((_trans), (_b), &_iter));\
+	     _iter++)
 
-struct btree_path *__bch2_btree_path_make_mut(struct btree_trans *, struct btree_path *,
-			 bool, unsigned long);
+btree_path_idx_t __bch2_btree_path_make_mut(struct btree_trans *, btree_path_idx_t,
+					    bool, unsigned long);
 
-static inline struct btree_path * __must_check
+static inline btree_path_idx_t __must_check
 bch2_btree_path_make_mut(struct btree_trans *trans,
-			 struct btree_path *path, bool intent,
+			 btree_path_idx_t path, bool intent,
 			 unsigned long ip)
 {
-	if (path->ref > 1 || path->preserve)
+	if (trans->paths[path].ref > 1 ||
+	    trans->paths[path].preserve)
 		path = __bch2_btree_path_make_mut(trans, path, intent, ip);
-	path->should_be_locked = false;
+	trans->paths[path].should_be_locked = false;
 	return path;
 }
 
-struct btree_path * __must_check
-__bch2_btree_path_set_pos(struct btree_trans *, struct btree_path *,
-			struct bpos, bool, unsigned long, int);
+btree_path_idx_t __must_check
+__bch2_btree_path_set_pos(struct btree_trans *, btree_path_idx_t,
+			  struct bpos, bool, unsigned long);
 
-static inline struct btree_path * __must_check
+static inline btree_path_idx_t __must_check
 bch2_btree_path_set_pos(struct btree_trans *trans,
-		   struct btree_path *path, struct bpos new_pos,
-		   bool intent, unsigned long ip)
+			btree_path_idx_t path, struct bpos new_pos,
+			bool intent, unsigned long ip)
 {
-	int cmp = bpos_cmp(new_pos, path->pos);
-
-	return cmp
-		? __bch2_btree_path_set_pos(trans, path, new_pos, intent, ip, cmp)
+	return !bpos_eq(new_pos, trans->paths[path].pos)
+		? __bch2_btree_path_set_pos(trans, path, new_pos, intent, ip)
 		: path;
 }
 
-int __must_check bch2_btree_path_traverse_one(struct btree_trans *, struct btree_path *,
+int __must_check bch2_btree_path_traverse_one(struct btree_trans *,
+					      btree_path_idx_t,
 					      unsigned, unsigned long);
 
 static inline int __must_check bch2_btree_path_traverse(struct btree_trans *trans,
-					  struct btree_path *path, unsigned flags)
+					  btree_path_idx_t path, unsigned flags)
 {
-	if (path->uptodate < BTREE_ITER_NEED_RELOCK)
+	if (trans->paths[path].uptodate < BTREE_ITER_NEED_RELOCK)
 		return 0;
 
 	return bch2_btree_path_traverse_one(trans, path, flags, _RET_IP_);
 }
 
-int __must_check bch2_btree_path_traverse(struct btree_trans *,
-					  struct btree_path *, unsigned);
-struct btree_path *bch2_path_get(struct btree_trans *, enum btree_id, struct bpos,
+btree_path_idx_t bch2_path_get(struct btree_trans *, enum btree_id, struct bpos,
 				 unsigned, unsigned, unsigned, unsigned long);
 struct bkey_s_c bch2_btree_path_peek_slot(struct btree_path *, struct bkey *);
 
@@ -269,7 +277,7 @@ void bch2_btree_node_iter_fix(struct btree_trans *trans, struct btree_path *,
 
 int bch2_btree_path_relock_intent(struct btree_trans *, struct btree_path *);
 
-void bch2_path_put(struct btree_trans *, struct btree_path *, bool);
+void bch2_path_put(struct btree_trans *, btree_path_idx_t, bool);
 
 int bch2_trans_relock(struct btree_trans *);
 int bch2_trans_relock_notrace(struct btree_trans *);
@@ -335,7 +343,7 @@ static inline void bch2_btree_path_downgrade(struct btree_trans *trans,
 
 void bch2_trans_downgrade(struct btree_trans *);
 
-void bch2_trans_node_add(struct btree_trans *trans, struct btree *);
+void bch2_trans_node_add(struct btree_trans *trans, struct btree_path *, struct btree *);
 void bch2_trans_node_reinit_iter(struct btree_trans *, struct btree *);
 
 int __must_check __bch2_btree_iter_traverse(struct btree_iter *iter);
@@ -348,8 +356,6 @@ struct btree *bch2_btree_iter_next_node(struct btree_iter *);
 struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *, struct bpos);
 struct bkey_s_c bch2_btree_iter_next(struct btree_iter *);
 
-struct bkey_s_c bch2_btree_iter_peek_all_levels(struct btree_iter *);
-
 static inline struct bkey_s_c bch2_btree_iter_peek(struct btree_iter *iter)
 {
 	return bch2_btree_iter_peek_upto(iter, SPOS_MAX);
@@ -376,10 +382,12 @@ static inline void __bch2_btree_iter_set_pos(struct btree_iter *iter, struct bpo
 
 static inline void bch2_btree_iter_set_pos(struct btree_iter *iter, struct bpos new_pos)
 {
+	struct btree_trans *trans = iter->trans;
+
 	if (unlikely(iter->update_path))
-		bch2_path_put(iter->trans, iter->update_path,
+		bch2_path_put(trans, iter->update_path,
 			      iter->flags & BTREE_ITER_INTENT);
-	iter->update_path = NULL;
+	iter->update_path = 0;
 
 	if (!(iter->flags & BTREE_ITER_ALL_SNAPSHOTS))
 		new_pos.snapshot = iter->snapshot;
@@ -408,9 +416,6 @@ static inline unsigned __bch2_btree_iter_flags(struct btree_trans *trans,
 					       unsigned btree_id,
 					       unsigned flags)
 {
-	if (flags & BTREE_ITER_ALL_LEVELS)
-		flags |= BTREE_ITER_ALL_SNAPSHOTS|__BTREE_ITER_ALL_SNAPSHOTS;
-
 	if (!(flags & (BTREE_ITER_ALL_SNAPSHOTS|BTREE_ITER_NOT_EXTENTS)) &&
 	    btree_id_is_extents(btree_id))
 		flags |= BTREE_ITER_IS_EXTENTS;
@@ -450,14 +455,16 @@ static inline void bch2_trans_iter_init_common(struct btree_trans *trans,
 					  unsigned flags,
 					  unsigned long ip)
 {
-	memset(iter, 0, sizeof(*iter));
-	iter->trans	= trans;
-	iter->btree_id	= btree_id;
-	iter->flags	= flags;
-	iter->snapshot	= pos.snapshot;
-	iter->pos	= pos;
-	iter->k.p	= pos;
-
+	iter->trans		= trans;
+	iter->update_path	= 0;
+	iter->key_cache_path	= 0;
+	iter->btree_id		= btree_id;
+	iter->min_depth		= 0;
+	iter->flags		= flags;
+	iter->snapshot		= pos.snapshot;
+	iter->pos		= pos;
+	iter->k			= POS_KEY(pos);
+	iter->journal_idx	= 0;
 #ifdef CONFIG_BCACHEFS_DEBUG
 	iter->ip_allocated = ip;
 #endif
@@ -489,8 +496,10 @@ void bch2_trans_copy_iter(struct btree_iter *, struct btree_iter *);
 
 static inline void set_btree_iter_dontneed(struct btree_iter *iter)
 {
-	if (!iter->trans->restarted)
-		iter->path->preserve = false;
+	struct btree_trans *trans = iter->trans;
+
+	if (!trans->restarted)
+		btree_iter_path(trans, iter)->preserve = false;
 }
 
 void *__bch2_trans_kmalloc(struct btree_trans *, size_t);
@@ -512,7 +521,7 @@ static inline void *bch2_trans_kmalloc(struct btree_trans *trans, size_t size)
 
 static inline void *bch2_trans_kmalloc_nomemzero(struct btree_trans *trans, size_t size)
 {
-	size = roundup(size, 8);
+	size = round_up(size, 8);
 
 	if (likely(trans->mem_top + size <= trans->mem_bytes)) {
 		void *p = trans->mem + trans->mem_top;
@@ -581,7 +590,6 @@ static inline int __bch2_bkey_get_val_typed(struct btree_trans *trans,
 				  KEY_TYPE_##_type, sizeof(*_val), _val)
 
 void bch2_trans_srcu_unlock(struct btree_trans *);
-void bch2_trans_srcu_lock(struct btree_trans *);
 
 u32 bch2_trans_begin(struct btree_trans *);
 
@@ -606,8 +614,6 @@ u32 bch2_trans_begin(struct btree_trans *);
 static inline struct bkey_s_c bch2_btree_iter_peek_prev_type(struct btree_iter *iter,
 							     unsigned flags)
 {
-	BUG_ON(flags & BTREE_ITER_ALL_LEVELS);
-
 	return  flags & BTREE_ITER_SLOTS      ? bch2_btree_iter_peek_slot(iter) :
 						bch2_btree_iter_peek_prev(iter);
 }
@@ -615,8 +621,7 @@ static inline struct bkey_s_c bch2_btree_iter_peek_prev_type(struct btree_iter *
 static inline struct bkey_s_c bch2_btree_iter_peek_type(struct btree_iter *iter,
 							unsigned flags)
 {
-	return  flags & BTREE_ITER_ALL_LEVELS ? bch2_btree_iter_peek_all_levels(iter) :
-		flags & BTREE_ITER_SLOTS      ? bch2_btree_iter_peek_slot(iter) :
+	return  flags & BTREE_ITER_SLOTS      ? bch2_btree_iter_peek_slot(iter) :
 						bch2_btree_iter_peek(iter);
 }
 
@@ -633,61 +638,34 @@ static inline struct bkey_s_c bch2_btree_iter_peek_upto_type(struct btree_iter *
 	return bch2_btree_iter_peek_slot(iter);
 }
 
+int __bch2_btree_trans_too_many_iters(struct btree_trans *);
+
 static inline int btree_trans_too_many_iters(struct btree_trans *trans)
 {
-	if (hweight64(trans->paths_allocated) > BTREE_ITER_MAX - 8) {
-		trace_and_count(trans->c, trans_restart_too_many_iters, trans, _THIS_IP_);
-		return btree_trans_restart(trans, BCH_ERR_transaction_restart_too_many_iters);
-	}
+	if (bitmap_weight(trans->paths_allocated, trans->nr_paths) > BTREE_ITER_INITIAL - 8)
+		return __bch2_btree_trans_too_many_iters(trans);
 
 	return 0;
 }
 
-struct bkey_s_c bch2_btree_iter_peek_and_restart_outlined(struct btree_iter *);
-
-static inline struct bkey_s_c
-__bch2_btree_iter_peek_and_restart(struct btree_trans *trans,
-				   struct btree_iter *iter, unsigned flags)
-{
-	struct bkey_s_c k;
-
-	while (btree_trans_too_many_iters(trans) ||
-	       (k = bch2_btree_iter_peek_type(iter, flags),
-		bch2_err_matches(bkey_err(k), BCH_ERR_transaction_restart)))
-		bch2_trans_begin(trans);
-
-	return k;
-}
-
-static inline struct bkey_s_c
-__bch2_btree_iter_peek_upto_and_restart(struct btree_trans *trans,
-					struct btree_iter *iter,
-					struct bpos end,
-					unsigned flags)
-{
-	struct bkey_s_c k;
-
-	while (btree_trans_too_many_iters(trans) ||
-	       (k = bch2_btree_iter_peek_upto_type(iter, end, flags),
-		bch2_err_matches(bkey_err(k), BCH_ERR_transaction_restart)))
-		bch2_trans_begin(trans);
-
-	return k;
-}
-
+/*
+ * goto instead of loop, so that when used inside for_each_btree_key2()
+ * break/continue work correctly
+ */
 #define lockrestart_do(_trans, _do)					\
 ({									\
+	__label__ transaction_restart;					\
 	u32 _restart_count;						\
 	int _ret2;							\
+transaction_restart:							\
+	_restart_count = bch2_trans_begin(_trans);			\
+	_ret2 = (_do);							\
 									\
-	do {								\
-		_restart_count = bch2_trans_begin(_trans);		\
-		_ret2 = (_do);						\
-	} while (bch2_err_matches(_ret2, BCH_ERR_transaction_restart));	\
+	if (bch2_err_matches(_ret2, BCH_ERR_transaction_restart))	\
+		goto transaction_restart;				\
 									\
 	if (!_ret2)							\
 		bch2_trans_verify_not_restarted(_trans, _restart_count);\
-									\
 	_ret2;								\
 })
 
@@ -716,91 +694,56 @@ __bch2_btree_iter_peek_upto_and_restart(struct btree_trans *trans,
 	_ret2 ?: trans_was_restarted(_trans, _restart_count);		\
 })
 
-#define for_each_btree_key2(_trans, _iter, _btree_id,			\
-			    _start, _flags, _k, _do)			\
+#define for_each_btree_key_upto(_trans, _iter, _btree_id,		\
+				_start, _end, _flags, _k, _do)		\
 ({									\
+	struct btree_iter _iter;					\
+	struct bkey_s_c _k;						\
 	int _ret3 = 0;							\
 									\
 	bch2_trans_iter_init((_trans), &(_iter), (_btree_id),		\
 			     (_start), (_flags));			\
 									\
-	while (1) {							\
-		u32 _restart_count = bch2_trans_begin(_trans);		\
-									\
-		_ret3 = 0;						\
-		(_k) = bch2_btree_iter_peek_type(&(_iter), (_flags));	\
-		if (!(_k).k)						\
-			break;						\
+	do {								\
+		_ret3 = lockrestart_do(_trans, ({			\
+			(_k) = bch2_btree_iter_peek_upto_type(&(_iter),	\
+						_end, (_flags));	\
+			if (!(_k).k)					\
+				break;					\
 									\
-		_ret3 = bkey_err(_k) ?: (_do);				\
-		if (bch2_err_matches(_ret3, BCH_ERR_transaction_restart))\
-			continue;					\
-		if (_ret3)						\
-			break;						\
-		bch2_trans_verify_not_restarted(_trans, _restart_count);\
-		if (!bch2_btree_iter_advance(&(_iter)))			\
-			break;						\
-	}								\
+			bkey_err(_k) ?: (_do);				\
+		}));							\
+	} while (!_ret3 && bch2_btree_iter_advance(&(_iter)));		\
 									\
 	bch2_trans_iter_exit((_trans), &(_iter));			\
 	_ret3;								\
 })
 
-#define for_each_btree_key2_upto(_trans, _iter, _btree_id,		\
-			    _start, _end, _flags, _k, _do)		\
-({									\
-	int _ret3 = 0;							\
-									\
-	bch2_trans_iter_init((_trans), &(_iter), (_btree_id),		\
-			     (_start), (_flags));			\
-									\
-	while (1) {							\
-		u32 _restart_count = bch2_trans_begin(_trans);		\
-									\
-		_ret3 = 0;						\
-		(_k) = bch2_btree_iter_peek_upto_type(&(_iter), _end, (_flags));\
-		if (!(_k).k)						\
-			break;						\
-									\
-		_ret3 = bkey_err(_k) ?: (_do);				\
-		if (bch2_err_matches(_ret3, BCH_ERR_transaction_restart))\
-			continue;					\
-		if (_ret3)						\
-			break;						\
-		bch2_trans_verify_not_restarted(_trans, _restart_count);\
-		if (!bch2_btree_iter_advance(&(_iter)))			\
-			break;						\
-	}								\
-									\
-	bch2_trans_iter_exit((_trans), &(_iter));			\
-	_ret3;								\
-})
+#define for_each_btree_key(_trans, _iter, _btree_id,			\
+			   _start, _flags, _k, _do)			\
+	for_each_btree_key_upto(_trans, _iter, _btree_id, _start,	\
+				 SPOS_MAX, _flags, _k, _do)
 
 #define for_each_btree_key_reverse(_trans, _iter, _btree_id,		\
 				   _start, _flags, _k, _do)		\
 ({									\
+	struct btree_iter _iter;					\
+	struct bkey_s_c _k;						\
 	int _ret3 = 0;							\
 									\
 	bch2_trans_iter_init((_trans), &(_iter), (_btree_id),		\
 			     (_start), (_flags));			\
 									\
-	while (1) {							\
-		u32 _restart_count = bch2_trans_begin(_trans);		\
-		(_k) = bch2_btree_iter_peek_prev_type(&(_iter), (_flags));\
-		if (!(_k).k) {						\
-			_ret3 = 0;					\
-			break;						\
-		}							\
+	do {								\
+		_ret3 = lockrestart_do(_trans, ({			\
+			(_k) = bch2_btree_iter_peek_prev_type(&(_iter),	\
+							(_flags));	\
+			if (!(_k).k)					\
+				break;					\
 									\
-		_ret3 = bkey_err(_k) ?: (_do);				\
-		if (bch2_err_matches(_ret3, BCH_ERR_transaction_restart))\
-			continue;					\
-		if (_ret3)						\
-			break;						\
-		bch2_trans_verify_not_restarted(_trans, _restart_count);\
-		if (!bch2_btree_iter_rewind(&(_iter)))			\
-			break;						\
-	}								\
+			bkey_err(_k) ?: (_do);				\
+		}));							\
+	} while (!_ret3 && bch2_btree_iter_rewind(&(_iter)));		\
 									\
 	bch2_trans_iter_exit((_trans), &(_iter));			\
 	_ret3;								\
@@ -810,7 +753,7 @@ __bch2_btree_iter_peek_upto_and_restart(struct btree_trans *trans,
 				  _start, _iter_flags, _k,		\
 				  _disk_res, _journal_seq, _commit_flags,\
 				  _do)					\
-	for_each_btree_key2(_trans, _iter, _btree_id, _start, _iter_flags, _k,\
+	for_each_btree_key(_trans, _iter, _btree_id, _start, _iter_flags, _k,\
 			    (_do) ?: bch2_trans_commit(_trans, (_disk_res),\
 					(_journal_seq), (_commit_flags)))
 
@@ -826,32 +769,31 @@ __bch2_btree_iter_peek_upto_and_restart(struct btree_trans *trans,
 				  _start, _end, _iter_flags, _k,	\
 				  _disk_res, _journal_seq, _commit_flags,\
 				  _do)					\
-	for_each_btree_key2_upto(_trans, _iter, _btree_id, _start, _end, _iter_flags, _k,\
+	for_each_btree_key_upto(_trans, _iter, _btree_id, _start, _end, _iter_flags, _k,\
 			    (_do) ?: bch2_trans_commit(_trans, (_disk_res),\
 					(_journal_seq), (_commit_flags)))
 
-#define for_each_btree_key(_trans, _iter, _btree_id,			\
-			   _start, _flags, _k, _ret)			\
-	for (bch2_trans_iter_init((_trans), &(_iter), (_btree_id),	\
-				  (_start), (_flags));			\
-	     (_k) = __bch2_btree_iter_peek_and_restart((_trans), &(_iter), _flags),\
-	     !((_ret) = bkey_err(_k)) && (_k).k;			\
-	     bch2_btree_iter_advance(&(_iter)))
+struct bkey_s_c bch2_btree_iter_peek_and_restart_outlined(struct btree_iter *);
 
-#define for_each_btree_key_upto(_trans, _iter, _btree_id,		\
-				_start, _end, _flags, _k, _ret)		\
-	for (bch2_trans_iter_init((_trans), &(_iter), (_btree_id),	\
-				  (_start), (_flags));			\
-	     (_k) = __bch2_btree_iter_peek_upto_and_restart((_trans),	\
-						&(_iter), _end, _flags),\
-	     !((_ret) = bkey_err(_k)) && (_k).k;			\
-	     bch2_btree_iter_advance(&(_iter)))
+static inline struct bkey_s_c
+__bch2_btree_iter_peek_and_restart(struct btree_trans *trans,
+				   struct btree_iter *iter, unsigned flags)
+{
+	struct bkey_s_c k;
 
-#define for_each_btree_key_norestart(_trans, _iter, _btree_id,		\
+	while (btree_trans_too_many_iters(trans) ||
+	       (k = bch2_btree_iter_peek_type(iter, flags),
+		bch2_err_matches(bkey_err(k), BCH_ERR_transaction_restart)))
+		bch2_trans_begin(trans);
+
+	return k;
+}
+
+#define for_each_btree_key_old(_trans, _iter, _btree_id,		\
 			   _start, _flags, _k, _ret)			\
 	for (bch2_trans_iter_init((_trans), &(_iter), (_btree_id),	\
 				  (_start), (_flags));			\
-	     (_k) = bch2_btree_iter_peek_type(&(_iter), _flags),	\
+	     (_k) = __bch2_btree_iter_peek_and_restart((_trans), &(_iter), _flags),\
 	     !((_ret) = bkey_err(_k)) && (_k).k;			\
 	     bch2_btree_iter_advance(&(_iter)))
 
@@ -863,24 +805,20 @@ __bch2_btree_iter_peek_upto_and_restart(struct btree_trans *trans,
 	     !((_ret) = bkey_err(_k)) && (_k).k;			\
 	     bch2_btree_iter_advance(&(_iter)))
 
-#define for_each_btree_key_continue(_trans, _iter, _flags, _k, _ret)	\
-	for (;								\
-	     (_k) = __bch2_btree_iter_peek_and_restart((_trans), &(_iter), _flags),\
-	     !((_ret) = bkey_err(_k)) && (_k).k;			\
-	     bch2_btree_iter_advance(&(_iter)))
-
-#define for_each_btree_key_continue_norestart(_iter, _flags, _k, _ret)	\
-	for (;								\
-	     (_k) = bch2_btree_iter_peek_type(&(_iter), _flags),	\
-	     !((_ret) = bkey_err(_k)) && (_k).k;			\
-	     bch2_btree_iter_advance(&(_iter)))
-
 #define for_each_btree_key_upto_continue_norestart(_iter, _end, _flags, _k, _ret)\
 	for (;									\
 	     (_k) = bch2_btree_iter_peek_upto_type(&(_iter), _end, _flags),	\
 	     !((_ret) = bkey_err(_k)) && (_k).k;				\
 	     bch2_btree_iter_advance(&(_iter)))
 
+#define for_each_btree_key_norestart(_trans, _iter, _btree_id,		\
+			   _start, _flags, _k, _ret)			\
+	for_each_btree_key_upto_norestart(_trans, _iter, _btree_id, _start,\
+					  SPOS_MAX, _flags, _k, _ret)
+
+#define for_each_btree_key_continue_norestart(_iter, _flags, _k, _ret)	\
+	for_each_btree_key_upto_continue_norestart(_iter, SPOS_MAX, _flags, _k, _ret)
+
 #define drop_locks_do(_trans, _do)					\
 ({									\
 	bch2_trans_unlock(_trans);					\
@@ -912,10 +850,7 @@ __bch2_btree_iter_peek_upto_and_restart(struct btree_trans *trans,
 	_p;								\
 })
 
-/* new multiple iterator interface: */
-
 void bch2_trans_updates_to_text(struct printbuf *, struct btree_trans *);
-void bch2_btree_path_to_text(struct printbuf *, struct btree_path *);
 void bch2_trans_paths_to_text(struct printbuf *, struct btree_trans *);
 void bch2_dump_trans_updates(struct btree_trans *);
 void bch2_dump_trans_paths_updates(struct btree_trans *);
@@ -938,6 +873,7 @@ unsigned bch2_trans_get_fn_idx(const char *);
 void bch2_btree_trans_to_text(struct printbuf *, struct btree_trans *);
 
 void bch2_fs_btree_iter_exit(struct bch_fs *);
+void bch2_fs_btree_iter_init_early(struct bch_fs *);
 int bch2_fs_btree_iter_init(struct bch_fs *);
 
 #endif /* _BCACHEFS_BTREE_ITER_H */
diff --git a/fs/bcachefs/btree_journal_iter.c b/fs/bcachefs/btree_journal_iter.c
index 58a981bcf3aa..719a94a84950 100644
--- a/fs/bcachefs/btree_journal_iter.c
+++ b/fs/bcachefs/btree_journal_iter.c
@@ -73,6 +73,7 @@ static size_t bch2_journal_key_search(struct journal_keys *keys,
 	return idx_to_pos(keys, __bch2_journal_key_search(keys, id, level, pos));
 }
 
+/* Returns first non-overwritten key >= search key: */
 struct bkey_i *bch2_journal_keys_peek_upto(struct bch_fs *c, enum btree_id btree_id,
 					   unsigned level, struct bpos pos,
 					   struct bpos end_pos, size_t *idx)
@@ -80,16 +81,32 @@ struct bkey_i *bch2_journal_keys_peek_upto(struct bch_fs *c, enum btree_id btree
 	struct journal_keys *keys = &c->journal_keys;
 	unsigned iters = 0;
 	struct journal_key *k;
+
+	BUG_ON(*idx > keys->nr);
 search:
 	if (!*idx)
 		*idx = __bch2_journal_key_search(keys, btree_id, level, pos);
 
+	while (*idx &&
+	       __journal_key_cmp(btree_id, level, end_pos, idx_to_key(keys, *idx - 1)) <= 0) {
+		--(*idx);
+		iters++;
+		if (iters == 10) {
+			*idx = 0;
+			goto search;
+		}
+	}
+
 	while ((k = *idx < keys->nr ? idx_to_key(keys, *idx) : NULL)) {
 		if (__journal_key_cmp(btree_id, level, end_pos, k) < 0)
 			return NULL;
 
-		if (__journal_key_cmp(btree_id, level, pos, k) <= 0 &&
-		    !k->overwritten)
+		if (k->overwritten) {
+			(*idx)++;
+			continue;
+		}
+
+		if (__journal_key_cmp(btree_id, level, pos, k) <= 0)
 			return k->k;
 
 		(*idx)++;
@@ -160,7 +177,7 @@ int bch2_journal_key_insert_take(struct bch_fs *c, enum btree_id id,
 	struct journal_keys *keys = &c->journal_keys;
 	size_t idx = bch2_journal_key_search(keys, id, level, k->k.p);
 
-	BUG_ON(test_bit(BCH_FS_RW, &c->flags));
+	BUG_ON(test_bit(BCH_FS_rw, &c->flags));
 
 	if (idx < keys->size &&
 	    journal_key_cmp(&n, &keys->d[idx]) == 0) {
@@ -189,10 +206,12 @@ int bch2_journal_key_insert_take(struct bch_fs *c, enum btree_id id,
 		/* Since @keys was full, there was no gap: */
 		memcpy(new_keys.d, keys->d, sizeof(keys->d[0]) * keys->nr);
 		kvfree(keys->d);
-		*keys = new_keys;
+		keys->d		= new_keys.d;
+		keys->nr	= new_keys.nr;
+		keys->size	= new_keys.size;
 
 		/* And now the gap is at the end: */
-		keys->gap = keys->nr;
+		keys->gap	= keys->nr;
 	}
 
 	journal_iters_move_gap(c, keys->gap, idx);
@@ -415,10 +434,16 @@ static int journal_sort_key_cmp(const void *_l, const void *_r)
 		cmp_int(l->journal_offset, r->journal_offset);
 }
 
-void bch2_journal_keys_free(struct journal_keys *keys)
+void bch2_journal_keys_put(struct bch_fs *c)
 {
+	struct journal_keys *keys = &c->journal_keys;
 	struct journal_key *i;
 
+	BUG_ON(atomic_read(&keys->ref) <= 0);
+
+	if (!atomic_dec_and_test(&keys->ref))
+		return;
+
 	move_gap(keys->d, keys->nr, keys->size, keys->gap, keys->nr);
 	keys->gap = keys->nr;
 
@@ -429,6 +454,8 @@ void bch2_journal_keys_free(struct journal_keys *keys)
 	kvfree(keys->d);
 	keys->d = NULL;
 	keys->nr = keys->gap = keys->size = 0;
+
+	bch2_journal_entries_free(c);
 }
 
 static void __journal_keys_sort(struct journal_keys *keys)
@@ -440,9 +467,7 @@ static void __journal_keys_sort(struct journal_keys *keys)
 	src = dst = keys->d;
 	while (src < keys->d + keys->nr) {
 		while (src + 1 < keys->d + keys->nr &&
-		       src[0].btree_id	== src[1].btree_id &&
-		       src[0].level	== src[1].level &&
-		       bpos_eq(src[0].k->k.p, src[1].k->k.p))
+		       !journal_key_cmp(src, src + 1))
 			src++;
 
 		*dst++ = *src++;
diff --git a/fs/bcachefs/btree_journal_iter.h b/fs/bcachefs/btree_journal_iter.h
index 5d64e7e22f26..8ca4c100b2e3 100644
--- a/fs/bcachefs/btree_journal_iter.h
+++ b/fs/bcachefs/btree_journal_iter.h
@@ -49,7 +49,15 @@ void bch2_btree_and_journal_iter_init_node_iter(struct btree_and_journal_iter *,
 						struct bch_fs *,
 						struct btree *);
 
-void bch2_journal_keys_free(struct journal_keys *);
+void bch2_journal_keys_put(struct bch_fs *);
+
+static inline void bch2_journal_keys_put_initial(struct bch_fs *c)
+{
+	if (c->journal_keys.initial_ref_held)
+		bch2_journal_keys_put(c);
+	c->journal_keys.initial_ref_held = false;
+}
+
 void bch2_journal_entries_free(struct bch_fs *);
 
 int bch2_journal_keys_sort(struct bch_fs *);
diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c
index 9b78f78a75b5..74e52fd28abe 100644
--- a/fs/bcachefs/btree_key_cache.c
+++ b/fs/bcachefs/btree_key_cache.c
@@ -89,10 +89,13 @@ static void bkey_cached_free(struct btree_key_cache *bc,
 	ck->btree_trans_barrier_seq =
 		start_poll_synchronize_srcu(&c->btree_trans_barrier);
 
-	if (ck->c.lock.readers)
+	if (ck->c.lock.readers) {
 		list_move_tail(&ck->list, &bc->freed_pcpu);
-	else
+		bc->nr_freed_pcpu++;
+	} else {
 		list_move_tail(&ck->list, &bc->freed_nonpcpu);
+		bc->nr_freed_nonpcpu++;
+	}
 	atomic_long_inc(&bc->nr_freed);
 
 	kfree(ck->k);
@@ -109,6 +112,8 @@ static void __bkey_cached_move_to_freelist_ordered(struct btree_key_cache *bc,
 {
 	struct bkey_cached *pos;
 
+	bc->nr_freed_nonpcpu++;
+
 	list_for_each_entry_reverse(pos, &bc->freed_nonpcpu, list) {
 		if (ULONG_CMP_GE(ck->btree_trans_barrier_seq,
 				 pos->btree_trans_barrier_seq)) {
@@ -158,6 +163,7 @@ static void bkey_cached_move_to_freelist(struct btree_key_cache *bc,
 #else
 		mutex_lock(&bc->lock);
 		list_move_tail(&ck->list, &bc->freed_nonpcpu);
+		bc->nr_freed_nonpcpu++;
 		mutex_unlock(&bc->lock);
 #endif
 	} else {
@@ -217,6 +223,7 @@ bkey_cached_alloc(struct btree_trans *trans, struct btree_path *path,
 			       f->nr < ARRAY_SIZE(f->objs) / 2) {
 				ck = list_last_entry(&bc->freed_nonpcpu, struct bkey_cached, list);
 				list_del_init(&ck->list);
+				bc->nr_freed_nonpcpu--;
 				f->objs[f->nr++] = ck;
 			}
 
@@ -229,6 +236,7 @@ bkey_cached_alloc(struct btree_trans *trans, struct btree_path *path,
 		if (!list_empty(&bc->freed_nonpcpu)) {
 			ck = list_last_entry(&bc->freed_nonpcpu, struct bkey_cached, list);
 			list_del_init(&ck->list);
+			bc->nr_freed_nonpcpu--;
 		}
 		mutex_unlock(&bc->lock);
 #endif
@@ -622,7 +630,7 @@ static int btree_key_cache_flush_pos(struct btree_trans *trans,
 	if (ret)
 		goto out;
 
-	ck = (void *) c_iter.path->l[0].b;
+	ck = (void *) btree_iter_path(trans, &c_iter)->l[0].b;
 	if (!ck)
 		goto out;
 
@@ -637,22 +645,29 @@ static int btree_key_cache_flush_pos(struct btree_trans *trans,
 	if (journal_seq && ck->journal.seq != journal_seq)
 		goto out;
 
+	trans->journal_res.seq = ck->journal.seq;
+
 	/*
-	 * Since journal reclaim depends on us making progress here, and the
-	 * allocator/copygc depend on journal reclaim making progress, we need
-	 * to be using alloc reserves:
+	 * If we're at the end of the journal, we really want to free up space
+	 * in the journal right away - we don't want to pin that old journal
+	 * sequence number with a new btree node write, we want to re-journal
+	 * the update
 	 */
+	if (ck->journal.seq == journal_last_seq(j))
+		commit_flags |= BCH_WATERMARK_reclaim;
+
+	if (ck->journal.seq != journal_last_seq(j) ||
+	    j->watermark == BCH_WATERMARK_stripe)
+		commit_flags |= BCH_TRANS_COMMIT_no_journal_res;
+
 	ret   = bch2_btree_iter_traverse(&b_iter) ?:
 		bch2_trans_update(trans, &b_iter, ck->k,
 				  BTREE_UPDATE_KEY_CACHE_RECLAIM|
 				  BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE|
 				  BTREE_TRIGGER_NORUN) ?:
 		bch2_trans_commit(trans, NULL, NULL,
-				  BTREE_INSERT_NOCHECK_RW|
-				  BTREE_INSERT_NOFAIL|
-				  (ck->journal.seq == journal_last_seq(j)
-				   ? BCH_WATERMARK_reclaim
-				   : 0)|
+				  BCH_TRANS_COMMIT_no_check_rw|
+				  BCH_TRANS_COMMIT_no_enospc|
 				  commit_flags);
 
 	bch2_fs_fatal_err_on(ret &&
@@ -664,9 +679,9 @@ static int btree_key_cache_flush_pos(struct btree_trans *trans,
 		goto out;
 
 	bch2_journal_pin_drop(j, &ck->journal);
-	bch2_journal_preres_put(j, &ck->res);
 
-	BUG_ON(!btree_node_locked(c_iter.path, 0));
+	struct btree_path *path = btree_iter_path(trans, &c_iter);
+	BUG_ON(!btree_node_locked(path, 0));
 
 	if (!evict) {
 		if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) {
@@ -675,19 +690,20 @@ static int btree_key_cache_flush_pos(struct btree_trans *trans,
 		}
 	} else {
 		struct btree_path *path2;
+		unsigned i;
 evict:
-		trans_for_each_path(trans, path2)
-			if (path2 != c_iter.path)
+		trans_for_each_path(trans, path2, i)
+			if (path2 != path)
 				__bch2_btree_path_unlock(trans, path2);
 
-		bch2_btree_node_lock_write_nofail(trans, c_iter.path, &ck->c);
+		bch2_btree_node_lock_write_nofail(trans, path, &ck->c);
 
 		if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) {
 			clear_bit(BKEY_CACHED_DIRTY, &ck->flags);
 			atomic_long_dec(&c->btree_key_cache.nr_dirty);
 		}
 
-		mark_btree_node_locked_noreset(c_iter.path, 0, BTREE_NODE_UNLOCKED);
+		mark_btree_node_locked_noreset(path, 0, BTREE_NODE_UNLOCKED);
 		bkey_cached_evict(&c->btree_key_cache, ck);
 		bkey_cached_free_fast(&c->btree_key_cache, ck);
 	}
@@ -725,9 +741,9 @@ int bch2_btree_key_cache_journal_flush(struct journal *j,
 	}
 	six_unlock_read(&ck->c.lock);
 
-	ret = commit_do(trans, NULL, NULL, 0,
+	ret = lockrestart_do(trans,
 		btree_key_cache_flush_pos(trans, key, seq,
-				BTREE_INSERT_JOURNAL_RECLAIM, false));
+				BCH_TRANS_COMMIT_journal_reclaim, false));
 unlock:
 	srcu_read_unlock(&c->btree_trans_barrier, srcu_idx);
 
@@ -735,50 +751,22 @@ unlock:
 	return ret;
 }
 
-/*
- * Flush and evict a key from the key cache:
- */
-int bch2_btree_key_cache_flush(struct btree_trans *trans,
-			       enum btree_id id, struct bpos pos)
-{
-	struct bch_fs *c = trans->c;
-	struct bkey_cached_key key = { id, pos };
-
-	/* Fastpath - assume it won't be found: */
-	if (!bch2_btree_key_cache_find(c, id, pos))
-		return 0;
-
-	return btree_key_cache_flush_pos(trans, key, 0, 0, true);
-}
-
 bool bch2_btree_insert_key_cached(struct btree_trans *trans,
 				  unsigned flags,
 				  struct btree_insert_entry *insert_entry)
 {
 	struct bch_fs *c = trans->c;
-	struct bkey_cached *ck = (void *) insert_entry->path->l[0].b;
+	struct bkey_cached *ck = (void *) (trans->paths + insert_entry->path)->l[0].b;
 	struct bkey_i *insert = insert_entry->k;
 	bool kick_reclaim = false;
 
 	BUG_ON(insert->k.u64s > ck->u64s);
 
-	if (likely(!(flags & BTREE_INSERT_JOURNAL_REPLAY))) {
-		int difference;
-
-		BUG_ON(jset_u64s(insert->k.u64s) > trans->journal_preres.u64s);
-
-		difference = jset_u64s(insert->k.u64s) - ck->res.u64s;
-		if (difference > 0) {
-			trans->journal_preres.u64s	-= difference;
-			ck->res.u64s			+= difference;
-		}
-	}
-
 	bkey_copy(ck->k, insert);
 	ck->valid = true;
 
 	if (!test_bit(BKEY_CACHED_DIRTY, &ck->flags)) {
-		EBUG_ON(test_bit(BCH_FS_CLEAN_SHUTDOWN, &c->flags));
+		EBUG_ON(test_bit(BCH_FS_clean_shutdown, &c->flags));
 		set_bit(BKEY_CACHED_DIRTY, &ck->flags);
 		atomic_long_inc(&c->btree_key_cache.nr_dirty);
 
@@ -850,6 +838,8 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink,
 	 * Newest freed entries are at the end of the list - once we hit one
 	 * that's too new to be freed, we can bail out:
 	 */
+	scanned += bc->nr_freed_nonpcpu;
+
 	list_for_each_entry_safe(ck, t, &bc->freed_nonpcpu, list) {
 		if (!poll_state_synchronize_srcu(&c->btree_trans_barrier,
 						 ck->btree_trans_barrier_seq))
@@ -859,13 +849,15 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink,
 		six_lock_exit(&ck->c.lock);
 		kmem_cache_free(bch2_key_cache, ck);
 		atomic_long_dec(&bc->nr_freed);
-		scanned++;
 		freed++;
+		bc->nr_freed_nonpcpu--;
 	}
 
 	if (scanned >= nr)
 		goto out;
 
+	scanned += bc->nr_freed_pcpu;
+
 	list_for_each_entry_safe(ck, t, &bc->freed_pcpu, list) {
 		if (!poll_state_synchronize_srcu(&c->btree_trans_barrier,
 						 ck->btree_trans_barrier_seq))
@@ -875,8 +867,8 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink,
 		six_lock_exit(&ck->c.lock);
 		kmem_cache_free(bch2_key_cache, ck);
 		atomic_long_dec(&bc->nr_freed);
-		scanned++;
 		freed++;
+		bc->nr_freed_pcpu--;
 	}
 
 	if (scanned >= nr)
@@ -982,6 +974,9 @@ void bch2_fs_btree_key_cache_exit(struct btree_key_cache *bc)
 	}
 #endif
 
+	BUG_ON(list_count_nodes(&bc->freed_pcpu) != bc->nr_freed_pcpu);
+	BUG_ON(list_count_nodes(&bc->freed_nonpcpu) != bc->nr_freed_nonpcpu);
+
 	list_splice(&bc->freed_pcpu,	&items);
 	list_splice(&bc->freed_nonpcpu,	&items);
 
@@ -990,9 +985,6 @@ void bch2_fs_btree_key_cache_exit(struct btree_key_cache *bc)
 	list_for_each_entry_safe(ck, n, &items, list) {
 		cond_resched();
 
-		bch2_journal_pin_drop(&c->journal, &ck->journal);
-		bch2_journal_preres_put(&c->journal, &ck->res);
-
 		list_del(&ck->list);
 		kfree(ck->k);
 		six_lock_exit(&ck->c.lock);
@@ -1001,7 +993,7 @@ void bch2_fs_btree_key_cache_exit(struct btree_key_cache *bc)
 
 	if (atomic_long_read(&bc->nr_dirty) &&
 	    !bch2_journal_error(&c->journal) &&
-	    test_bit(BCH_FS_WAS_RW, &c->flags))
+	    test_bit(BCH_FS_was_rw, &c->flags))
 		panic("btree key cache shutdown error: nr_dirty nonzero (%li)\n",
 		      atomic_long_read(&bc->nr_dirty));
 
diff --git a/fs/bcachefs/btree_key_cache.h b/fs/bcachefs/btree_key_cache.h
index be3acde2caa0..e6b2cd0dd2c1 100644
--- a/fs/bcachefs/btree_key_cache.h
+++ b/fs/bcachefs/btree_key_cache.h
@@ -31,8 +31,6 @@ int bch2_btree_path_traverse_cached(struct btree_trans *, struct btree_path *,
 
 bool bch2_btree_insert_key_cached(struct btree_trans *, unsigned,
 			struct btree_insert_entry *);
-int bch2_btree_key_cache_flush(struct btree_trans *,
-			       enum btree_id, struct bpos);
 void bch2_btree_key_cache_drop(struct btree_trans *,
 			       struct btree_path *);
 
diff --git a/fs/bcachefs/btree_key_cache_types.h b/fs/bcachefs/btree_key_cache_types.h
new file mode 100644
index 000000000000..290e4e57df5b
--- /dev/null
+++ b/fs/bcachefs/btree_key_cache_types.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_BTREE_KEY_CACHE_TYPES_H
+#define _BCACHEFS_BTREE_KEY_CACHE_TYPES_H
+
+struct btree_key_cache_freelist {
+	struct bkey_cached	*objs[16];
+	unsigned		nr;
+};
+
+struct btree_key_cache {
+	struct mutex		lock;
+	struct rhashtable	table;
+	bool			table_init_done;
+
+	struct list_head	freed_pcpu;
+	size_t			nr_freed_pcpu;
+	struct list_head	freed_nonpcpu;
+	size_t			nr_freed_nonpcpu;
+
+	struct shrinker		*shrink;
+	unsigned		shrink_iter;
+	struct btree_key_cache_freelist __percpu *pcpu_freed;
+
+	atomic_long_t		nr_freed;
+	atomic_long_t		nr_keys;
+	atomic_long_t		nr_dirty;
+};
+
+struct bkey_cached_key {
+	u32			btree_id;
+	struct bpos		pos;
+} __packed __aligned(4);
+
+#endif /* _BCACHEFS_BTREE_KEY_CACHE_TYPES_H */
diff --git a/fs/bcachefs/btree_locking.c b/fs/bcachefs/btree_locking.c
index 3d48834d091f..2d1c95c42f24 100644
--- a/fs/bcachefs/btree_locking.c
+++ b/fs/bcachefs/btree_locking.c
@@ -32,13 +32,14 @@ struct six_lock_count bch2_btree_node_lock_counts(struct btree_trans *trans,
 {
 	struct btree_path *path;
 	struct six_lock_count ret;
+	unsigned i;
 
 	memset(&ret, 0, sizeof(ret));
 
 	if (IS_ERR_OR_NULL(b))
 		return ret;
 
-	trans_for_each_path(trans, path)
+	trans_for_each_path(trans, path, i)
 		if (path != skip && &path->l[level].b->c == b) {
 			int t = btree_node_locked_type(path, level);
 
@@ -85,8 +86,14 @@ static noinline void print_cycle(struct printbuf *out, struct lock_graph *g)
 	prt_printf(out, "Found lock cycle (%u entries):", g->nr);
 	prt_newline(out);
 
-	for (i = g->g; i < g->g + g->nr; i++)
+	for (i = g->g; i < g->g + g->nr; i++) {
+		struct task_struct *task = READ_ONCE(i->trans->locking_wait.task);
+		if (!task)
+			continue;
+
 		bch2_btree_trans_to_text(out, i->trans);
+		bch2_prt_task_backtrace(out, task, i == g->g ? 5 : 1);
+	}
 }
 
 static noinline void print_chain(struct printbuf *out, struct lock_graph *g)
@@ -94,9 +101,10 @@ static noinline void print_chain(struct printbuf *out, struct lock_graph *g)
 	struct trans_waiting_for_lock *i;
 
 	for (i = g->g; i != g->g + g->nr; i++) {
+		struct task_struct *task = i->trans->locking_wait.task;
 		if (i != g->g)
 			prt_str(out, "<- ");
-		prt_printf(out, "%u ", i->trans->locking_wait.task->pid);
+		prt_printf(out, "%u ", task ?task->pid : 0);
 	}
 	prt_newline(out);
 }
@@ -142,10 +150,27 @@ static bool lock_graph_remove_non_waiters(struct lock_graph *g)
 	return false;
 }
 
+static void trace_would_deadlock(struct lock_graph *g, struct btree_trans *trans)
+{
+	struct bch_fs *c = trans->c;
+
+	count_event(c, trans_restart_would_deadlock);
+
+	if (trace_trans_restart_would_deadlock_enabled()) {
+		struct printbuf buf = PRINTBUF;
+
+		buf.atomic++;
+		print_cycle(&buf, g);
+
+		trace_trans_restart_would_deadlock(trans, buf.buf);
+		printbuf_exit(&buf);
+	}
+}
+
 static int abort_lock(struct lock_graph *g, struct trans_waiting_for_lock *i)
 {
 	if (i == g->g) {
-		trace_and_count(i->trans->c, trans_restart_would_deadlock, i->trans, _RET_IP_);
+		trace_would_deadlock(g, i->trans);
 		return btree_trans_restart(i->trans, BCH_ERR_transaction_restart_would_deadlock);
 	} else {
 		i->trans->lock_must_abort = true;
@@ -202,7 +227,7 @@ static noinline int break_cycle(struct lock_graph *g, struct printbuf *cycle)
 			prt_printf(&buf, "backtrace:");
 			prt_newline(&buf);
 			printbuf_indent_add(&buf, 2);
-			bch2_prt_task_backtrace(&buf, trans->locking_wait.task);
+			bch2_prt_task_backtrace(&buf, trans->locking_wait.task, 2);
 			printbuf_indent_sub(&buf, 2);
 			prt_newline(&buf);
 		}
@@ -262,27 +287,40 @@ int bch2_check_for_deadlock(struct btree_trans *trans, struct printbuf *cycle)
 	struct lock_graph g;
 	struct trans_waiting_for_lock *top;
 	struct btree_bkey_cached_common *b;
-	struct btree_path *path;
-	unsigned path_idx;
-	int ret;
+	btree_path_idx_t path_idx;
+	int ret = 0;
+
+	g.nr = 0;
 
 	if (trans->lock_must_abort) {
 		if (cycle)
 			return -1;
 
-		trace_and_count(trans->c, trans_restart_would_deadlock, trans, _RET_IP_);
+		trace_would_deadlock(&g, trans);
 		return btree_trans_restart(trans, BCH_ERR_transaction_restart_would_deadlock);
 	}
 
-	g.nr = 0;
 	lock_graph_down(&g, trans);
+
+	/* trans->paths is rcu protected vs. freeing */
+	rcu_read_lock();
+	if (cycle)
+		cycle->atomic++;
 next:
 	if (!g.nr)
-		return 0;
+		goto out;
 
 	top = &g.g[g.nr - 1];
 
-	trans_for_each_path_safe_from(top->trans, path, path_idx, top->path_idx) {
+	struct btree_path *paths = rcu_dereference(top->trans->paths);
+	if (!paths)
+		goto up;
+
+	unsigned long *paths_allocated = trans_paths_allocated(paths);
+
+	trans_for_each_path_idx_from(paths_allocated, *trans_paths_nr(paths),
+				     path_idx, top->path_idx) {
+		struct btree_path *path = paths + path_idx;
 		if (!path->nodes_locked)
 			continue;
 
@@ -348,18 +386,23 @@ next:
 
 				ret = lock_graph_descend(&g, trans, cycle);
 				if (ret)
-					return ret;
+					goto out;
 				goto next;
 
 			}
 			raw_spin_unlock(&b->lock.wait_lock);
 		}
 	}
-
+up:
 	if (g.nr > 1 && cycle)
 		print_chain(cycle, &g);
 	lock_graph_up(&g);
 	goto next;
+out:
+	if (cycle)
+		--cycle->atomic;
+	rcu_read_unlock();
+	return ret;
 }
 
 int bch2_six_check_for_deadlock(struct six_lock *lock, void *p)
@@ -398,7 +441,7 @@ void bch2_btree_node_lock_write_nofail(struct btree_trans *trans,
 				       struct btree_bkey_cached_common *b)
 {
 	struct btree_path *linked;
-	unsigned i;
+	unsigned i, iter;
 	int ret;
 
 	/*
@@ -412,7 +455,7 @@ void bch2_btree_node_lock_write_nofail(struct btree_trans *trans,
 	 * already taken are no longer needed:
 	 */
 
-	trans_for_each_path(trans, linked) {
+	trans_for_each_path(trans, linked, iter) {
 		if (!linked->nodes_locked)
 			continue;
 
@@ -624,8 +667,6 @@ bool __bch2_btree_path_upgrade(struct btree_trans *trans,
 			       unsigned new_locks_want,
 			       struct get_locks_fail *f)
 {
-	struct btree_path *linked;
-
 	if (bch2_btree_path_upgrade_noupgrade_sibs(trans, path, new_locks_want, f))
 		return true;
 
@@ -648,8 +689,11 @@ bool __bch2_btree_path_upgrade(struct btree_trans *trans,
 	 * before interior nodes - now that's handled by
 	 * bch2_btree_path_traverse_all().
 	 */
-	if (!path->cached && !trans->in_traverse_all)
-		trans_for_each_path(trans, linked)
+	if (!path->cached && !trans->in_traverse_all) {
+		struct btree_path *linked;
+		unsigned i;
+
+		trans_for_each_path(trans, linked, i)
 			if (linked != path &&
 			    linked->cached == path->cached &&
 			    linked->btree_id == path->btree_id &&
@@ -657,6 +701,7 @@ bool __bch2_btree_path_upgrade(struct btree_trans *trans,
 				linked->locks_want = new_locks_want;
 				btree_path_get_locks(trans, linked, true, NULL);
 			}
+	}
 
 	return false;
 }
@@ -665,7 +710,7 @@ void __bch2_btree_path_downgrade(struct btree_trans *trans,
 				 struct btree_path *path,
 				 unsigned new_locks_want)
 {
-	unsigned l;
+	unsigned l, old_locks_want = path->locks_want;
 
 	if (trans->restarted)
 		return;
@@ -689,8 +734,7 @@ void __bch2_btree_path_downgrade(struct btree_trans *trans,
 
 	bch2_btree_path_verify_locks(path);
 
-	path->downgrade_seq++;
-	trace_path_downgrade(trans, _RET_IP_, path);
+	trace_path_downgrade(trans, _RET_IP_, path, old_locks_want);
 }
 
 /* Btree transaction locking: */
@@ -698,22 +742,24 @@ void __bch2_btree_path_downgrade(struct btree_trans *trans,
 void bch2_trans_downgrade(struct btree_trans *trans)
 {
 	struct btree_path *path;
+	unsigned i;
 
 	if (trans->restarted)
 		return;
 
-	trans_for_each_path(trans, path)
+	trans_for_each_path(trans, path, i)
 		bch2_btree_path_downgrade(trans, path);
 }
 
 int bch2_trans_relock(struct btree_trans *trans)
 {
 	struct btree_path *path;
+	unsigned i;
 
 	if (unlikely(trans->restarted))
 		return -((int) trans->restarted);
 
-	trans_for_each_path(trans, path)
+	trans_for_each_path(trans, path, i)
 		if (path->should_be_locked &&
 		    !bch2_btree_path_relock_norestart(trans, path, _RET_IP_)) {
 			trace_and_count(trans->c, trans_restart_relock, trans, _RET_IP_, path);
@@ -725,11 +771,12 @@ int bch2_trans_relock(struct btree_trans *trans)
 int bch2_trans_relock_notrace(struct btree_trans *trans)
 {
 	struct btree_path *path;
+	unsigned i;
 
 	if (unlikely(trans->restarted))
 		return -((int) trans->restarted);
 
-	trans_for_each_path(trans, path)
+	trans_for_each_path(trans, path, i)
 		if (path->should_be_locked &&
 		    !bch2_btree_path_relock_norestart(trans, path, _RET_IP_)) {
 			return btree_trans_restart(trans, BCH_ERR_transaction_restart_relock);
@@ -740,16 +787,18 @@ int bch2_trans_relock_notrace(struct btree_trans *trans)
 void bch2_trans_unlock_noassert(struct btree_trans *trans)
 {
 	struct btree_path *path;
+	unsigned i;
 
-	trans_for_each_path(trans, path)
+	trans_for_each_path(trans, path, i)
 		__bch2_btree_path_unlock(trans, path);
 }
 
 void bch2_trans_unlock(struct btree_trans *trans)
 {
 	struct btree_path *path;
+	unsigned i;
 
-	trans_for_each_path(trans, path)
+	trans_for_each_path(trans, path, i)
 		__bch2_btree_path_unlock(trans, path);
 }
 
@@ -762,8 +811,9 @@ void bch2_trans_unlock_long(struct btree_trans *trans)
 bool bch2_trans_locked(struct btree_trans *trans)
 {
 	struct btree_path *path;
+	unsigned i;
 
-	trans_for_each_path(trans, path)
+	trans_for_each_path(trans, path, i)
 		if (path->nodes_locked)
 			return true;
 	return false;
@@ -809,8 +859,9 @@ void bch2_btree_path_verify_locks(struct btree_path *path)
 void bch2_trans_verify_locks(struct btree_trans *trans)
 {
 	struct btree_path *path;
+	unsigned i;
 
-	trans_for_each_path(trans, path)
+	trans_for_each_path(trans, path, i)
 		bch2_btree_path_verify_locks(path);
 }
 
diff --git a/fs/bcachefs/btree_locking.h b/fs/bcachefs/btree_locking.h
index 11b0a2c8cd69..cc5500a957a1 100644
--- a/fs/bcachefs/btree_locking.h
+++ b/fs/bcachefs/btree_locking.h
@@ -122,12 +122,9 @@ static void btree_trans_lock_hold_time_update(struct btree_trans *trans,
 					      struct btree_path *path, unsigned level)
 {
 #ifdef CONFIG_BCACHEFS_LOCK_TIME_STATS
-	struct btree_transaction_stats *s = btree_trans_stats(trans);
-
-	if (s)
-		__bch2_time_stats_update(&s->lock_hold_times,
-					 path->l[level].lock_taken_time,
-					 local_clock());
+	__bch2_time_stats_update(&btree_trans_stats(trans)->lock_hold_times,
+				 path->l[level].lock_taken_time,
+				 local_clock());
 #endif
 }
 
@@ -175,6 +172,7 @@ bch2_btree_node_unlock_write_inlined(struct btree_trans *trans, struct btree_pat
 				     struct btree *b)
 {
 	struct btree_path *linked;
+	unsigned i;
 
 	EBUG_ON(path->l[b->c.level].b != b);
 	EBUG_ON(path->l[b->c.level].lock_seq != six_lock_seq(&b->c.lock));
@@ -182,7 +180,7 @@ bch2_btree_node_unlock_write_inlined(struct btree_trans *trans, struct btree_pat
 
 	mark_btree_node_locked_noreset(path, b->c.level, BTREE_NODE_INTENT_LOCKED);
 
-	trans_for_each_path_with_node(trans, b, linked)
+	trans_for_each_path_with_node(trans, b, linked, i)
 		linked->l[b->c.level].lock_seq++;
 
 	six_unlock_write(&b->c.lock);
@@ -242,8 +240,9 @@ static inline bool btree_node_lock_increment(struct btree_trans *trans,
 					     enum btree_node_locked_type want)
 {
 	struct btree_path *path;
+	unsigned i;
 
-	trans_for_each_path(trans, path)
+	trans_for_each_path(trans, path, i)
 		if (&path->l[level].b->c == b &&
 		    btree_node_locked_type(path, level) >= want) {
 			six_lock_increment(&b->lock, (enum six_lock_type) want);
@@ -263,7 +262,6 @@ static inline int btree_node_lock(struct btree_trans *trans,
 	int ret = 0;
 
 	EBUG_ON(level >= BTREE_MAX_DEPTH);
-	EBUG_ON(!(trans->paths_allocated & (1ULL << path->idx)));
 
 	if (likely(six_trylock_type(&b->lock, type)) ||
 	    btree_node_lock_increment(trans, b, level, (enum btree_node_locked_type) type) ||
diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c
index decad7b66c59..90eb8065ff2d 100644
--- a/fs/bcachefs/btree_trans_commit.c
+++ b/fs/bcachefs/btree_trans_commit.c
@@ -12,6 +12,7 @@
 #include "errcode.h"
 #include "error.h"
 #include "journal.h"
+#include "journal_io.h"
 #include "journal_reclaim.h"
 #include "replicas.h"
 #include "snapshot.h"
@@ -23,7 +24,7 @@ static void verify_update_old_key(struct btree_trans *trans, struct btree_insert
 #ifdef CONFIG_BCACHEFS_DEBUG
 	struct bch_fs *c = trans->c;
 	struct bkey u;
-	struct bkey_s_c k = bch2_btree_path_peek_slot_exact(i->path, &u);
+	struct bkey_s_c k = bch2_btree_path_peek_slot_exact(trans->paths + i->path, &u);
 
 	if (unlikely(trans->journal_replay_not_finished)) {
 		struct bkey_i *j_k =
@@ -41,23 +42,23 @@ static void verify_update_old_key(struct btree_trans *trans, struct btree_insert
 #endif
 }
 
-static inline struct btree_path_level *insert_l(struct btree_insert_entry *i)
+static inline struct btree_path_level *insert_l(struct btree_trans *trans, struct btree_insert_entry *i)
 {
-	return i->path->l + i->level;
+	return (trans->paths + i->path)->l + i->level;
 }
 
 static inline bool same_leaf_as_prev(struct btree_trans *trans,
 				     struct btree_insert_entry *i)
 {
 	return i != trans->updates &&
-		insert_l(&i[0])->b == insert_l(&i[-1])->b;
+		insert_l(trans, &i[0])->b == insert_l(trans, &i[-1])->b;
 }
 
 static inline bool same_leaf_as_next(struct btree_trans *trans,
 				     struct btree_insert_entry *i)
 {
 	return i + 1 < trans->updates + trans->nr_updates &&
-		insert_l(&i[0])->b == insert_l(&i[1])->b;
+		insert_l(trans, &i[0])->b == insert_l(trans, &i[1])->b;
 }
 
 inline void bch2_btree_node_prep_for_write(struct btree_trans *trans,
@@ -78,6 +79,49 @@ inline void bch2_btree_node_prep_for_write(struct btree_trans *trans,
 		bch2_btree_init_next(trans, b);
 }
 
+static noinline int trans_lock_write_fail(struct btree_trans *trans, struct btree_insert_entry *i)
+{
+	while (--i >= trans->updates) {
+		if (same_leaf_as_prev(trans, i))
+			continue;
+
+		bch2_btree_node_unlock_write(trans, trans->paths + i->path, insert_l(trans, i)->b);
+	}
+
+	trace_and_count(trans->c, trans_restart_would_deadlock_write, trans);
+	return btree_trans_restart(trans, BCH_ERR_transaction_restart_would_deadlock_write);
+}
+
+static inline int bch2_trans_lock_write(struct btree_trans *trans)
+{
+	EBUG_ON(trans->write_locked);
+
+	trans_for_each_update(trans, i) {
+		if (same_leaf_as_prev(trans, i))
+			continue;
+
+		if (bch2_btree_node_lock_write(trans, trans->paths + i->path, &insert_l(trans, i)->b->c))
+			return trans_lock_write_fail(trans, i);
+
+		if (!i->cached)
+			bch2_btree_node_prep_for_write(trans, trans->paths + i->path, insert_l(trans, i)->b);
+	}
+
+	trans->write_locked = true;
+	return 0;
+}
+
+static inline void bch2_trans_unlock_write(struct btree_trans *trans)
+{
+	if (likely(trans->write_locked)) {
+		trans_for_each_update(trans, i)
+			if (!same_leaf_as_prev(trans, i))
+				bch2_btree_node_unlock_write_inlined(trans,
+						trans->paths + i->path, insert_l(trans, i)->b);
+		trans->write_locked = false;
+	}
+}
+
 /* Inserting into a given leaf node (last stage of insert): */
 
 /* Handle overwrites and do insert, for non extents: */
@@ -240,7 +284,7 @@ inline void bch2_btree_insert_key_leaf(struct btree_trans *trans,
 	bch2_btree_add_journal_pin(c, b, journal_seq);
 
 	if (unlikely(!btree_node_dirty(b))) {
-		EBUG_ON(test_bit(BCH_FS_CLEAN_SHUTDOWN, &c->flags));
+		EBUG_ON(test_bit(BCH_FS_clean_shutdown, &c->flags));
 		set_btree_node_dirty_acct(c, b);
 	}
 
@@ -264,10 +308,12 @@ inline void bch2_btree_insert_key_leaf(struct btree_trans *trans,
 static inline void btree_insert_entry_checks(struct btree_trans *trans,
 					     struct btree_insert_entry *i)
 {
-	BUG_ON(!bpos_eq(i->k->k.p, i->path->pos));
-	BUG_ON(i->cached	!= i->path->cached);
-	BUG_ON(i->level		!= i->path->level);
-	BUG_ON(i->btree_id	!= i->path->btree_id);
+	struct btree_path *path = trans->paths + i->path;
+
+	BUG_ON(!bpos_eq(i->k->k.p, path->pos));
+	BUG_ON(i->cached	!= path->cached);
+	BUG_ON(i->level		!= path->level);
+	BUG_ON(i->btree_id	!= path->btree_id);
 	EBUG_ON(!i->level &&
 		btree_type_has_snapshots(i->btree_id) &&
 		!(i->flags & BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE) &&
@@ -276,17 +322,6 @@ static inline void btree_insert_entry_checks(struct btree_trans *trans,
 		bch2_snapshot_is_internal_node(trans->c, i->k->k.p.snapshot));
 }
 
-static noinline int
-bch2_trans_journal_preres_get_cold(struct btree_trans *trans, unsigned flags,
-				   unsigned long trace_ip)
-{
-	return drop_locks_do(trans,
-		bch2_journal_preres_get(&trans->c->journal,
-			&trans->journal_preres,
-			trans->journal_preres_u64s,
-			(flags & BCH_WATERMARK_MASK)));
-}
-
 static __always_inline int bch2_trans_journal_res_get(struct btree_trans *trans,
 						      unsigned flags)
 {
@@ -321,12 +356,48 @@ static inline int btree_key_can_insert(struct btree_trans *trans,
 	return 0;
 }
 
+noinline static int
+btree_key_can_insert_cached_slowpath(struct btree_trans *trans, unsigned flags,
+				     struct btree_path *path, unsigned new_u64s)
+{
+	struct bkey_cached *ck = (void *) path->l[0].b;
+	struct bkey_i *new_k;
+	int ret;
+
+	bch2_trans_unlock_write(trans);
+	bch2_trans_unlock(trans);
+
+	new_k = kmalloc(new_u64s * sizeof(u64), GFP_KERNEL);
+	if (!new_k) {
+		bch_err(trans->c, "error allocating memory for key cache key, btree %s u64s %u",
+			bch2_btree_id_str(path->btree_id), new_u64s);
+		return -BCH_ERR_ENOMEM_btree_key_cache_insert;
+	}
+
+	ret =   bch2_trans_relock(trans) ?:
+		bch2_trans_lock_write(trans);
+	if (unlikely(ret)) {
+		kfree(new_k);
+		return ret;
+	}
+
+	memcpy(new_k, ck->k, ck->u64s * sizeof(u64));
+
+	trans_for_each_update(trans, i)
+		if (i->old_v == &ck->k->v)
+			i->old_v = &new_k->v;
+
+	kfree(ck->k);
+	ck->u64s	= new_u64s;
+	ck->k		= new_k;
+	return 0;
+}
+
 static int btree_key_can_insert_cached(struct btree_trans *trans, unsigned flags,
 				       struct btree_path *path, unsigned u64s)
 {
 	struct bch_fs *c = trans->c;
 	struct bkey_cached *ck = (void *) path->l[0].b;
-	struct btree_insert_entry *i;
 	unsigned new_u64s;
 	struct bkey_i *new_k;
 
@@ -334,7 +405,7 @@ static int btree_key_can_insert_cached(struct btree_trans *trans, unsigned flags
 
 	if (!test_bit(BKEY_CACHED_DIRTY, &ck->flags) &&
 	    bch2_btree_key_cache_must_wait(c) &&
-	    !(flags & BTREE_INSERT_JOURNAL_RECLAIM))
+	    !(flags & BCH_TRANS_COMMIT_journal_reclaim))
 		return -BCH_ERR_btree_insert_need_journal_reclaim;
 
 	/*
@@ -347,12 +418,9 @@ static int btree_key_can_insert_cached(struct btree_trans *trans, unsigned flags
 		return 0;
 
 	new_u64s	= roundup_pow_of_two(u64s);
-	new_k		= krealloc(ck->k, new_u64s * sizeof(u64), GFP_NOFS);
-	if (!new_k) {
-		bch_err(c, "error allocating memory for key cache key, btree %s u64s %u",
-			bch2_btree_id_str(path->btree_id), new_u64s);
-		return -BCH_ERR_ENOMEM_btree_key_cache_insert;
-	}
+	new_k		= krealloc(ck->k, new_u64s * sizeof(u64), GFP_NOWAIT);
+	if (unlikely(!new_k))
+		return btree_key_can_insert_cached_slowpath(trans, flags, path, new_u64s);
 
 	trans_for_each_update(trans, i)
 		if (i->old_v == &ck->k->v)
@@ -383,22 +451,15 @@ static int run_one_mem_trigger(struct btree_trans *trans,
 	if (!btree_node_type_needs_gc(__btree_node_type(i->level, i->btree_id)))
 		return 0;
 
-	if (old_ops->atomic_trigger == new_ops->atomic_trigger) {
-		ret   = bch2_mark_key(trans, i->btree_id, i->level,
-				old, bkey_i_to_s_c(new),
+	if (old_ops->trigger == new_ops->trigger) {
+		ret   = bch2_key_trigger(trans, i->btree_id, i->level,
+				old, bkey_i_to_s(new),
 				BTREE_TRIGGER_INSERT|BTREE_TRIGGER_OVERWRITE|flags);
 	} else {
-		struct bkey		_deleted = KEY(0, 0, 0);
-		struct bkey_s_c		deleted = (struct bkey_s_c) { &_deleted, NULL };
-
-		_deleted.p = i->path->pos;
-
-		ret   = bch2_mark_key(trans, i->btree_id, i->level,
-				deleted, bkey_i_to_s_c(new),
-				BTREE_TRIGGER_INSERT|flags) ?:
-			bch2_mark_key(trans, i->btree_id, i->level,
-				old, deleted,
-				BTREE_TRIGGER_OVERWRITE|flags);
+		ret   = bch2_key_trigger_new(trans, i->btree_id, i->level,
+				bkey_i_to_s(new), flags) ?:
+			bch2_key_trigger_old(trans, i->btree_id, i->level,
+				old, flags);
 	}
 
 	return ret;
@@ -416,6 +477,7 @@ static int run_one_trans_trigger(struct btree_trans *trans, struct btree_insert_
 	struct bkey_s_c old = { &old_k, i->old_v };
 	const struct bkey_ops *old_ops = bch2_bkey_type_ops(old.k->type);
 	const struct bkey_ops *new_ops = bch2_bkey_type_ops(i->k->k.type);
+	unsigned flags = i->flags|BTREE_TRIGGER_TRANSACTIONAL;
 
 	verify_update_old_key(trans, i);
 
@@ -425,19 +487,18 @@ static int run_one_trans_trigger(struct btree_trans *trans, struct btree_insert_
 
 	if (!i->insert_trigger_run &&
 	    !i->overwrite_trigger_run &&
-	    old_ops->trans_trigger == new_ops->trans_trigger) {
+	    old_ops->trigger == new_ops->trigger) {
 		i->overwrite_trigger_run = true;
 		i->insert_trigger_run = true;
-		return bch2_trans_mark_key(trans, i->btree_id, i->level, old, i->k,
-					   BTREE_TRIGGER_INSERT|
-					   BTREE_TRIGGER_OVERWRITE|
-					   i->flags) ?: 1;
+		return bch2_key_trigger(trans, i->btree_id, i->level, old, bkey_i_to_s(i->k),
+					BTREE_TRIGGER_INSERT|
+					BTREE_TRIGGER_OVERWRITE|flags) ?: 1;
 	} else if (overwrite && !i->overwrite_trigger_run) {
 		i->overwrite_trigger_run = true;
-		return bch2_trans_mark_old(trans, i->btree_id, i->level, old, i->flags) ?: 1;
+		return bch2_key_trigger_old(trans, i->btree_id, i->level, old, flags) ?: 1;
 	} else if (!overwrite && !i->insert_trigger_run) {
 		i->insert_trigger_run = true;
-		return bch2_trans_mark_new(trans, i->btree_id, i->level, i->k, i->flags) ?: 1;
+		return bch2_key_trigger_new(trans, i->btree_id, i->level, bkey_i_to_s(i->k), flags) ?: 1;
 	} else {
 		return 0;
 	}
@@ -479,7 +540,7 @@ static int run_btree_triggers(struct btree_trans *trans, enum btree_id btree_id,
 
 static int bch2_trans_commit_run_triggers(struct btree_trans *trans)
 {
-	struct btree_insert_entry *i = NULL, *btree_id_start = trans->updates;
+	struct btree_insert_entry *btree_id_start = trans->updates;
 	unsigned btree_id = 0;
 	int ret = 0;
 
@@ -526,7 +587,6 @@ static int bch2_trans_commit_run_triggers(struct btree_trans *trans)
 static noinline int bch2_trans_commit_run_gc_triggers(struct btree_trans *trans)
 {
 	struct bch_fs *c = trans->c;
-	struct btree_insert_entry *i;
 	int ret = 0;
 
 	trans_for_each_update(trans, i) {
@@ -536,7 +596,7 @@ static noinline int bch2_trans_commit_run_gc_triggers(struct btree_trans *trans)
 		 */
 		BUG_ON(i->cached || i->level);
 
-		if (gc_visited(c, gc_pos_btree_node(insert_l(i)->b))) {
+		if (gc_visited(c, gc_pos_btree_node(insert_l(trans, i)->b))) {
 			ret = run_one_mem_trigger(trans, i, i->flags|BTREE_TRIGGER_GC);
 			if (ret)
 				break;
@@ -552,8 +612,6 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags,
 			       unsigned long trace_ip)
 {
 	struct bch_fs *c = trans->c;
-	struct btree_insert_entry *i;
-	struct btree_write_buffered_key *wb;
 	struct btree_trans_commit_hook *h;
 	unsigned u64s = 0;
 	int ret;
@@ -578,23 +636,21 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags,
 
 		u64s += i->k->k.u64s;
 		ret = !i->cached
-			? btree_key_can_insert(trans, insert_l(i)->b, u64s)
-			: btree_key_can_insert_cached(trans, flags, i->path, u64s);
+			? btree_key_can_insert(trans, insert_l(trans, i)->b, u64s)
+			: btree_key_can_insert_cached(trans, flags, trans->paths + i->path, u64s);
 		if (ret) {
 			*stopped_at = i;
 			return ret;
 		}
-	}
 
-	if (trans->nr_wb_updates &&
-	    trans->nr_wb_updates + c->btree_write_buffer.state.nr > c->btree_write_buffer.size)
-		return -BCH_ERR_btree_insert_need_flush_buffer;
+		i->k->k.needs_whiteout = false;
+	}
 
 	/*
 	 * Don't get journal reservation until after we know insert will
 	 * succeed:
 	 */
-	if (likely(!(flags & BTREE_INSERT_JOURNAL_REPLAY))) {
+	if (likely(!(flags & BCH_TRANS_COMMIT_no_journal_res))) {
 		ret = bch2_trans_journal_res_get(trans,
 				(flags & BCH_WATERMARK_MASK)|
 				JOURNAL_RES_GET_NONBLOCK);
@@ -603,8 +659,6 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags,
 
 		if (unlikely(trans->journal_transaction_names))
 			journal_transaction_name(trans);
-	} else {
-		trans->journal_res.seq = c->journal.replay_journal_seq;
 	}
 
 	/*
@@ -613,7 +667,7 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags,
 	 */
 
 	if (IS_ENABLED(CONFIG_BCACHEFS_DEBUG) &&
-	    !(flags & BTREE_INSERT_JOURNAL_REPLAY)) {
+	    !(flags & BCH_TRANS_COMMIT_no_journal_res)) {
 		if (bch2_journal_seq_verify)
 			trans_for_each_update(trans, i)
 				i->k->k.version.lo = trans->journal_res.seq;
@@ -626,14 +680,6 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags,
 	    bch2_trans_fs_usage_apply(trans, trans->fs_usage_deltas))
 		return -BCH_ERR_btree_insert_need_mark_replicas;
 
-	if (trans->nr_wb_updates) {
-		EBUG_ON(flags & BTREE_INSERT_JOURNAL_REPLAY);
-
-		ret = bch2_btree_insert_keys_write_buffer(trans);
-		if (ret)
-			goto revert_fs_usage;
-	}
-
 	h = trans->hooks;
 	while (h) {
 		ret = h->fn(trans, h);
@@ -655,16 +701,7 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags,
 			goto fatal_err;
 	}
 
-	if (unlikely(trans->extra_journal_entries.nr)) {
-		memcpy_u64s_small(journal_res_entry(&c->journal, &trans->journal_res),
-				  trans->extra_journal_entries.data,
-				  trans->extra_journal_entries.nr);
-
-		trans->journal_res.offset	+= trans->extra_journal_entries.nr;
-		trans->journal_res.u64s		-= trans->extra_journal_entries.nr;
-	}
-
-	if (likely(!(flags & BTREE_INSERT_JOURNAL_REPLAY))) {
+	if (likely(!(flags & BCH_TRANS_COMMIT_no_journal_res))) {
 		struct journal *j = &c->journal;
 		struct jset_entry *entry;
 
@@ -693,33 +730,27 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags,
 			bkey_copy((struct bkey_i *) entry->start, i->k);
 		}
 
-		trans_for_each_wb_update(trans, wb) {
-			entry = bch2_journal_add_entry(j, &trans->journal_res,
-					       BCH_JSET_ENTRY_btree_keys,
-					       wb->btree, 0,
-					       wb->k.k.u64s);
-			bkey_copy((struct bkey_i *) entry->start, &wb->k);
-		}
+		memcpy_u64s_small(journal_res_entry(&c->journal, &trans->journal_res),
+				  trans->journal_entries,
+				  trans->journal_entries_u64s);
+
+		trans->journal_res.offset	+= trans->journal_entries_u64s;
+		trans->journal_res.u64s		-= trans->journal_entries_u64s;
 
 		if (trans->journal_seq)
 			*trans->journal_seq = trans->journal_res.seq;
 	}
 
 	trans_for_each_update(trans, i) {
-		i->k->k.needs_whiteout = false;
+		struct btree_path *path = trans->paths + i->path;
 
 		if (!i->cached) {
-			u64 seq = trans->journal_res.seq;
-
-			if (i->flags & BTREE_UPDATE_PREJOURNAL)
-				seq = i->seq;
-
-			bch2_btree_insert_key_leaf(trans, i->path, i->k, seq);
+			bch2_btree_insert_key_leaf(trans, path, i->k, trans->journal_res.seq);
 		} else if (!i->key_cache_already_flushed)
 			bch2_btree_insert_key_cached(trans, flags, i);
 		else {
-			bch2_btree_key_cache_drop(trans, i->path);
-			btree_path_set_dirty(i->path, BTREE_ITER_NEED_TRAVERSE);
+			bch2_btree_key_cache_drop(trans, path);
+			btree_path_set_dirty(path, BTREE_ITER_NEED_TRAVERSE);
 		}
 	}
 
@@ -732,47 +763,10 @@ revert_fs_usage:
 	return ret;
 }
 
-static noinline int trans_lock_write_fail(struct btree_trans *trans, struct btree_insert_entry *i)
-{
-	while (--i >= trans->updates) {
-		if (same_leaf_as_prev(trans, i))
-			continue;
-
-		bch2_btree_node_unlock_write(trans, i->path, insert_l(i)->b);
-	}
-
-	trace_and_count(trans->c, trans_restart_would_deadlock_write, trans);
-	return btree_trans_restart(trans, BCH_ERR_transaction_restart_would_deadlock_write);
-}
-
-static inline int trans_lock_write(struct btree_trans *trans)
-{
-	struct btree_insert_entry *i;
-
-	trans_for_each_update(trans, i) {
-		if (same_leaf_as_prev(trans, i))
-			continue;
-
-		if (bch2_btree_node_lock_write(trans, i->path, &insert_l(i)->b->c))
-			return trans_lock_write_fail(trans, i);
-
-		if (!i->cached)
-			bch2_btree_node_prep_for_write(trans, i->path, insert_l(i)->b);
-	}
-
-	return 0;
-}
-
 static noinline void bch2_drop_overwrites_from_journal(struct btree_trans *trans)
 {
-	struct btree_insert_entry *i;
-	struct btree_write_buffered_key *wb;
-
 	trans_for_each_update(trans, i)
 		bch2_journal_key_overwritten(trans->c, i->btree_id, i->level, i->k->k.p);
-
-	trans_for_each_wb_update(trans, wb)
-		bch2_journal_key_overwritten(trans->c, wb->btree, 0, wb->k.k.p);
 }
 
 static noinline int bch2_trans_commit_bkey_invalid(struct btree_trans *trans,
@@ -800,6 +794,33 @@ static noinline int bch2_trans_commit_bkey_invalid(struct btree_trans *trans,
 	return -EINVAL;
 }
 
+static noinline int bch2_trans_commit_journal_entry_invalid(struct btree_trans *trans,
+						   struct jset_entry *i)
+{
+	struct bch_fs *c = trans->c;
+	struct printbuf buf = PRINTBUF;
+
+	prt_printf(&buf, "invalid bkey on insert from %s", trans->fn);
+	prt_newline(&buf);
+	printbuf_indent_add(&buf, 2);
+
+	bch2_journal_entry_to_text(&buf, c, i);
+	prt_newline(&buf);
+
+	bch2_print_string_as_lines(KERN_ERR, buf.buf);
+
+	bch2_inconsistent_error(c);
+	bch2_dump_trans_updates(trans);
+
+	return -EINVAL;
+}
+
+static int bch2_trans_commit_journal_pin_flush(struct journal *j,
+				struct journal_entry_pin *_pin, u64 seq)
+{
+	return 0;
+}
+
 /*
  * Get journal reservation, take write locks, and attempt to do btree update(s):
  */
@@ -808,7 +829,6 @@ static inline int do_bch2_trans_commit(struct btree_trans *trans, unsigned flags
 				       unsigned long trace_ip)
 {
 	struct bch_fs *c = trans->c;
-	struct btree_insert_entry *i;
 	int ret = 0, u64s_delta = 0;
 
 	trans_for_each_update(trans, i) {
@@ -830,15 +850,7 @@ static inline int do_bch2_trans_commit(struct btree_trans *trans, unsigned flags
 		}
 	}
 
-	ret = bch2_journal_preres_get(&c->journal,
-			&trans->journal_preres, trans->journal_preres_u64s,
-			(flags & BCH_WATERMARK_MASK)|JOURNAL_RES_GET_NONBLOCK);
-	if (unlikely(ret == -BCH_ERR_journal_preres_get_blocked))
-		ret = bch2_trans_journal_preres_get_cold(trans, flags, trace_ip);
-	if (unlikely(ret))
-		return ret;
-
-	ret = trans_lock_write(trans);
+	ret = bch2_trans_lock_write(trans);
 	if (unlikely(ret))
 		return ret;
 
@@ -847,20 +859,19 @@ static inline int do_bch2_trans_commit(struct btree_trans *trans, unsigned flags
 	if (!ret && unlikely(trans->journal_replay_not_finished))
 		bch2_drop_overwrites_from_journal(trans);
 
-	trans_for_each_update(trans, i)
-		if (!same_leaf_as_prev(trans, i))
-			bch2_btree_node_unlock_write_inlined(trans, i->path,
-							insert_l(i)->b);
+	bch2_trans_unlock_write(trans);
 
 	if (!ret && trans->journal_pin)
 		bch2_journal_pin_add(&c->journal, trans->journal_res.seq,
-				     trans->journal_pin, NULL);
+				     trans->journal_pin,
+				     bch2_trans_commit_journal_pin_flush);
 
 	/*
 	 * Drop journal reservation after dropping write locks, since dropping
 	 * the journal reservation may kick off a journal write:
 	 */
-	bch2_journal_res_put(&c->journal, &trans->journal_res);
+	if (likely(!(flags & BCH_TRANS_COMMIT_no_journal_res)))
+		bch2_journal_res_put(&c->journal, &trans->journal_res);
 
 	return ret;
 }
@@ -886,7 +897,8 @@ int bch2_trans_commit_error(struct btree_trans *trans, unsigned flags,
 	case -BCH_ERR_btree_insert_btree_node_full:
 		ret = bch2_btree_split_leaf(trans, i->path, flags);
 		if (bch2_err_matches(ret, BCH_ERR_transaction_restart))
-			trace_and_count(c, trans_restart_btree_node_split, trans, trace_ip, i->path);
+			trace_and_count(c, trans_restart_btree_node_split, trans,
+					trace_ip, trans->paths + i->path);
 		break;
 	case -BCH_ERR_btree_insert_need_mark_replicas:
 		ret = drop_locks_do(trans,
@@ -897,7 +909,7 @@ int bch2_trans_commit_error(struct btree_trans *trans, unsigned flags,
 		 * XXX: this should probably be a separate BTREE_INSERT_NONBLOCK
 		 * flag
 		 */
-		if ((flags & BTREE_INSERT_JOURNAL_RECLAIM) &&
+		if ((flags & BCH_TRANS_COMMIT_journal_reclaim) &&
 		    (flags & BCH_WATERMARK_MASK) != BCH_WATERMARK_reclaim) {
 			ret = -BCH_ERR_journal_reclaim_would_deadlock;
 			break;
@@ -920,30 +932,6 @@ int bch2_trans_commit_error(struct btree_trans *trans, unsigned flags,
 
 		ret = bch2_trans_relock(trans);
 		break;
-	case -BCH_ERR_btree_insert_need_flush_buffer: {
-		struct btree_write_buffer *wb = &c->btree_write_buffer;
-
-		ret = 0;
-
-		if (wb->state.nr > wb->size * 3 / 4) {
-			bch2_trans_unlock(trans);
-			mutex_lock(&wb->flush_lock);
-
-			if (wb->state.nr > wb->size * 3 / 4) {
-				bch2_trans_begin(trans);
-				ret = __bch2_btree_write_buffer_flush(trans,
-						flags|BTREE_INSERT_NOCHECK_RW, true);
-				if (!ret) {
-					trace_and_count(c, trans_restart_write_buffer_flush, trans, _THIS_IP_);
-					ret = btree_trans_restart(trans, BCH_ERR_transaction_restart_write_buffer_flush);
-				}
-			} else {
-				mutex_unlock(&wb->flush_lock);
-				ret = bch2_trans_relock(trans);
-			}
-		}
-		break;
-	}
 	default:
 		BUG_ON(ret >= 0);
 		break;
@@ -952,8 +940,7 @@ int bch2_trans_commit_error(struct btree_trans *trans, unsigned flags,
 	BUG_ON(bch2_err_matches(ret, BCH_ERR_transaction_restart) != !!trans->restarted);
 
 	bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOSPC) &&
-				!(flags & BTREE_INSERT_NOWAIT) &&
-				(flags & BTREE_INSERT_NOFAIL), c,
+				(flags & BCH_TRANS_COMMIT_no_enospc), c,
 		"%s: incorrectly got %s\n", __func__, bch2_err_str(ret));
 
 	return ret;
@@ -965,8 +952,8 @@ bch2_trans_commit_get_rw_cold(struct btree_trans *trans, unsigned flags)
 	struct bch_fs *c = trans->c;
 	int ret;
 
-	if (likely(!(flags & BTREE_INSERT_LAZY_RW)) ||
-	    test_bit(BCH_FS_STARTED, &c->flags))
+	if (likely(!(flags & BCH_TRANS_COMMIT_lazy_rw)) ||
+	    test_bit(BCH_FS_started, &c->flags))
 		return -BCH_ERR_erofs_trans_commit;
 
 	ret = drop_locks_do(trans, bch2_fs_read_write_early(c));
@@ -986,7 +973,6 @@ static noinline int
 do_bch2_trans_commit_to_journal_replay(struct btree_trans *trans)
 {
 	struct bch_fs *c = trans->c;
-	struct btree_insert_entry *i;
 	int ret = 0;
 
 	trans_for_each_update(trans, i) {
@@ -1000,20 +986,14 @@ do_bch2_trans_commit_to_journal_replay(struct btree_trans *trans)
 
 int __bch2_trans_commit(struct btree_trans *trans, unsigned flags)
 {
+	struct btree_insert_entry *errored_at = NULL;
 	struct bch_fs *c = trans->c;
-	struct btree_insert_entry *i = NULL;
-	struct btree_write_buffered_key *wb;
-	unsigned u64s;
 	int ret = 0;
 
 	if (!trans->nr_updates &&
-	    !trans->nr_wb_updates &&
-	    !trans->extra_journal_entries.nr)
+	    !trans->journal_entries_u64s)
 		goto out_reset;
 
-	if (flags & BTREE_INSERT_GC_LOCK_HELD)
-		lockdep_assert_held(&c->gc_lock);
-
 	ret = bch2_trans_commit_run_triggers(trans);
 	if (ret)
 		goto out_reset;
@@ -1022,7 +1002,7 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags)
 		struct printbuf buf = PRINTBUF;
 		enum bkey_invalid_flags invalid_flags = 0;
 
-		if (!(flags & BTREE_INSERT_JOURNAL_REPLAY))
+		if (!(flags & BCH_TRANS_COMMIT_no_journal_res))
 			invalid_flags |= BKEY_INVALID_WRITE|BKEY_INVALID_COMMIT;
 
 		if (unlikely(bch2_bkey_invalid(c, bkey_i_to_s_c(i->k),
@@ -1035,88 +1015,82 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags)
 			return ret;
 	}
 
-	if (unlikely(!test_bit(BCH_FS_MAY_GO_RW, &c->flags))) {
+	for (struct jset_entry *i = trans->journal_entries;
+	     i != (void *) ((u64 *) trans->journal_entries + trans->journal_entries_u64s);
+	     i = vstruct_next(i)) {
+		enum bkey_invalid_flags invalid_flags = 0;
+
+		if (!(flags & BCH_TRANS_COMMIT_no_journal_res))
+			invalid_flags |= BKEY_INVALID_WRITE|BKEY_INVALID_COMMIT;
+
+		if (unlikely(bch2_journal_entry_validate(c, NULL, i,
+					bcachefs_metadata_version_current,
+					CPU_BIG_ENDIAN, invalid_flags)))
+			ret = bch2_trans_commit_journal_entry_invalid(trans, i);
+
+		if (ret)
+			return ret;
+	}
+
+	if (unlikely(!test_bit(BCH_FS_may_go_rw, &c->flags))) {
 		ret = do_bch2_trans_commit_to_journal_replay(trans);
 		goto out_reset;
 	}
 
-	if (!(flags & BTREE_INSERT_NOCHECK_RW) &&
+	if (!(flags & BCH_TRANS_COMMIT_no_check_rw) &&
 	    unlikely(!bch2_write_ref_tryget(c, BCH_WRITE_REF_trans))) {
 		ret = bch2_trans_commit_get_rw_cold(trans, flags);
 		if (ret)
 			goto out_reset;
 	}
 
-	if (c->btree_write_buffer.state.nr > c->btree_write_buffer.size / 2 &&
-	    mutex_trylock(&c->btree_write_buffer.flush_lock)) {
-		bch2_trans_begin(trans);
-		bch2_trans_unlock(trans);
-
-		ret = __bch2_btree_write_buffer_flush(trans,
-					flags|BTREE_INSERT_NOCHECK_RW, true);
-		if (!ret) {
-			trace_and_count(c, trans_restart_write_buffer_flush, trans, _THIS_IP_);
-			ret = btree_trans_restart(trans, BCH_ERR_transaction_restart_write_buffer_flush);
-		}
-		goto out;
-	}
-
-	EBUG_ON(test_bit(BCH_FS_CLEAN_SHUTDOWN, &c->flags));
-
-	memset(&trans->journal_preres, 0, sizeof(trans->journal_preres));
-
-	trans->journal_u64s		= trans->extra_journal_entries.nr;
-	trans->journal_preres_u64s	= 0;
+	EBUG_ON(test_bit(BCH_FS_clean_shutdown, &c->flags));
 
+	trans->journal_u64s		= trans->journal_entries_u64s;
 	trans->journal_transaction_names = READ_ONCE(c->opts.journal_transaction_names);
-
 	if (trans->journal_transaction_names)
 		trans->journal_u64s += jset_u64s(JSET_ENTRY_LOG_U64s);
 
 	trans_for_each_update(trans, i) {
-		EBUG_ON(!i->path->should_be_locked);
+		struct btree_path *path = trans->paths + i->path;
 
-		ret = bch2_btree_path_upgrade(trans, i->path, i->level + 1);
+		EBUG_ON(!path->should_be_locked);
+
+		ret = bch2_btree_path_upgrade(trans, path, i->level + 1);
 		if (unlikely(ret))
 			goto out;
 
-		EBUG_ON(!btree_node_intent_locked(i->path, i->level));
+		EBUG_ON(!btree_node_intent_locked(path, i->level));
 
 		if (i->key_cache_already_flushed)
 			continue;
 
-		/* we're going to journal the key being updated: */
-		u64s = jset_u64s(i->k->k.u64s);
-		if (i->cached &&
-		    likely(!(flags & BTREE_INSERT_JOURNAL_REPLAY)))
-			trans->journal_preres_u64s += u64s;
-
 		if (i->flags & BTREE_UPDATE_NOJOURNAL)
 			continue;
 
-		trans->journal_u64s += u64s;
+		/* we're going to journal the key being updated: */
+		trans->journal_u64s += jset_u64s(i->k->k.u64s);
 
 		/* and we're also going to log the overwrite: */
 		if (trans->journal_transaction_names)
 			trans->journal_u64s += jset_u64s(i->old_k.u64s);
 	}
 
-	trans_for_each_wb_update(trans, wb)
-		trans->journal_u64s += jset_u64s(wb->k.k.u64s);
-
-	if (trans->extra_journal_res) {
+	if (trans->extra_disk_res) {
 		ret = bch2_disk_reservation_add(c, trans->disk_res,
-				trans->extra_journal_res,
-				(flags & BTREE_INSERT_NOFAIL)
+				trans->extra_disk_res,
+				(flags & BCH_TRANS_COMMIT_no_enospc)
 				? BCH_DISK_RESERVATION_NOFAIL : 0);
 		if (ret)
 			goto err;
 	}
 retry:
+	errored_at = NULL;
 	bch2_trans_verify_not_in_restart(trans);
-	memset(&trans->journal_res, 0, sizeof(trans->journal_res));
+	if (likely(!(flags & BCH_TRANS_COMMIT_no_journal_res)))
+		memset(&trans->journal_res, 0, sizeof(trans->journal_res));
 
-	ret = do_bch2_trans_commit(trans, flags, &i, _RET_IP_);
+	ret = do_bch2_trans_commit(trans, flags, &errored_at, _RET_IP_);
 
 	/* make sure we didn't drop or screw up locks: */
 	bch2_trans_verify_locks(trans);
@@ -1126,9 +1100,7 @@ retry:
 
 	trace_and_count(c, transaction_commit, trans, _RET_IP_);
 out:
-	bch2_journal_preres_put(&c->journal, &trans->journal_preres);
-
-	if (likely(!(flags & BTREE_INSERT_NOCHECK_RW)))
+	if (likely(!(flags & BCH_TRANS_COMMIT_no_check_rw)))
 		bch2_write_ref_put(c, BCH_WRITE_REF_trans);
 out_reset:
 	if (!ret)
@@ -1137,9 +1109,21 @@ out_reset:
 
 	return ret;
 err:
-	ret = bch2_trans_commit_error(trans, flags, i, ret, _RET_IP_);
+	ret = bch2_trans_commit_error(trans, flags, errored_at, ret, _RET_IP_);
 	if (ret)
 		goto out;
 
+	/*
+	 * We might have done another transaction commit in the error path -
+	 * i.e. btree write buffer flush - which will have made use of
+	 * trans->journal_res, but with BCH_TRANS_COMMIT_no_journal_res that is
+	 * how the journal sequence number to pin is passed in - so we must
+	 * restart:
+	 */
+	if (flags & BCH_TRANS_COMMIT_no_journal_res) {
+		ret = -BCH_ERR_transaction_restart_nested;
+		goto out;
+	}
+
 	goto retry;
 }
diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h
index 941841a0c5bf..d530307046f4 100644
--- a/fs/bcachefs/btree_types.h
+++ b/fs/bcachefs/btree_types.h
@@ -5,7 +5,7 @@
 #include <linux/list.h>
 #include <linux/rhashtable.h>
 
-//#include "bkey_methods.h"
+#include "btree_key_cache_types.h"
 #include "buckets_types.h"
 #include "darray.h"
 #include "errcode.h"
@@ -185,33 +185,32 @@ struct btree_node_iter {
  * Iterate over all possible positions, synthesizing deleted keys for holes:
  */
 static const __maybe_unused u16 BTREE_ITER_SLOTS		= 1 << 0;
-static const __maybe_unused u16 BTREE_ITER_ALL_LEVELS		= 1 << 1;
 /*
  * Indicates that intent locks should be taken on leaf nodes, because we expect
  * to be doing updates:
  */
-static const __maybe_unused u16 BTREE_ITER_INTENT		= 1 << 2;
+static const __maybe_unused u16 BTREE_ITER_INTENT		= 1 << 1;
 /*
  * Causes the btree iterator code to prefetch additional btree nodes from disk:
  */
-static const __maybe_unused u16 BTREE_ITER_PREFETCH		= 1 << 3;
+static const __maybe_unused u16 BTREE_ITER_PREFETCH		= 1 << 2;
 /*
  * Used in bch2_btree_iter_traverse(), to indicate whether we're searching for
  * @pos or the first key strictly greater than @pos
  */
-static const __maybe_unused u16 BTREE_ITER_IS_EXTENTS		= 1 << 4;
-static const __maybe_unused u16 BTREE_ITER_NOT_EXTENTS		= 1 << 5;
-static const __maybe_unused u16 BTREE_ITER_CACHED		= 1 << 6;
-static const __maybe_unused u16 BTREE_ITER_WITH_KEY_CACHE	= 1 << 7;
-static const __maybe_unused u16 BTREE_ITER_WITH_UPDATES		= 1 << 8;
-static const __maybe_unused u16 BTREE_ITER_WITH_JOURNAL		= 1 << 9;
-static const __maybe_unused u16 __BTREE_ITER_ALL_SNAPSHOTS	= 1 << 10;
-static const __maybe_unused u16 BTREE_ITER_ALL_SNAPSHOTS	= 1 << 11;
-static const __maybe_unused u16 BTREE_ITER_FILTER_SNAPSHOTS	= 1 << 12;
-static const __maybe_unused u16 BTREE_ITER_NOPRESERVE		= 1 << 13;
-static const __maybe_unused u16 BTREE_ITER_CACHED_NOFILL	= 1 << 14;
-static const __maybe_unused u16 BTREE_ITER_KEY_CACHE_FILL	= 1 << 15;
-#define __BTREE_ITER_FLAGS_END					       16
+static const __maybe_unused u16 BTREE_ITER_IS_EXTENTS		= 1 << 3;
+static const __maybe_unused u16 BTREE_ITER_NOT_EXTENTS		= 1 << 4;
+static const __maybe_unused u16 BTREE_ITER_CACHED		= 1 << 5;
+static const __maybe_unused u16 BTREE_ITER_WITH_KEY_CACHE	= 1 << 6;
+static const __maybe_unused u16 BTREE_ITER_WITH_UPDATES		= 1 << 7;
+static const __maybe_unused u16 BTREE_ITER_WITH_JOURNAL		= 1 << 8;
+static const __maybe_unused u16 __BTREE_ITER_ALL_SNAPSHOTS	= 1 << 9;
+static const __maybe_unused u16 BTREE_ITER_ALL_SNAPSHOTS	= 1 << 10;
+static const __maybe_unused u16 BTREE_ITER_FILTER_SNAPSHOTS	= 1 << 11;
+static const __maybe_unused u16 BTREE_ITER_NOPRESERVE		= 1 << 12;
+static const __maybe_unused u16 BTREE_ITER_CACHED_NOFILL	= 1 << 13;
+static const __maybe_unused u16 BTREE_ITER_KEY_CACHE_FILL	= 1 << 14;
+#define __BTREE_ITER_FLAGS_END					       15
 
 enum btree_path_uptodate {
 	BTREE_ITER_UPTODATE		= 0,
@@ -223,13 +222,12 @@ enum btree_path_uptodate {
 #define TRACK_PATH_ALLOCATED
 #endif
 
+typedef u16 btree_path_idx_t;
+
 struct btree_path {
-	u8			idx;
-	u8			sorted_idx;
+	btree_path_idx_t	sorted_idx;
 	u8			ref;
 	u8			intent_ref;
-	u32			alloc_seq;
-	u32			downgrade_seq;
 
 	/* btree_iter_copy starts here: */
 	struct bpos		pos;
@@ -283,13 +281,12 @@ static inline unsigned long btree_path_ip_allocated(struct btree_path *path)
  */
 struct btree_iter {
 	struct btree_trans	*trans;
-	struct btree_path	*path;
-	struct btree_path	*update_path;
-	struct btree_path	*key_cache_path;
+	btree_path_idx_t	path;
+	btree_path_idx_t	update_path;
+	btree_path_idx_t	key_cache_path;
 
 	enum btree_id		btree_id:8;
-	unsigned		min_depth:3;
-	unsigned		advanced:1;
+	u8			min_depth;
 
 	/* btree_iter_copy starts here: */
 	u16			flags;
@@ -306,37 +303,11 @@ struct btree_iter {
 
 	/* BTREE_ITER_WITH_JOURNAL: */
 	size_t			journal_idx;
-	struct bpos		journal_pos;
 #ifdef TRACK_PATH_ALLOCATED
 	unsigned long		ip_allocated;
 #endif
 };
 
-struct btree_key_cache_freelist {
-	struct bkey_cached	*objs[16];
-	unsigned		nr;
-};
-
-struct btree_key_cache {
-	struct mutex		lock;
-	struct rhashtable	table;
-	bool			table_init_done;
-	struct list_head	freed_pcpu;
-	struct list_head	freed_nonpcpu;
-	struct shrinker		*shrink;
-	unsigned		shrink_iter;
-	struct btree_key_cache_freelist __percpu *pcpu_freed;
-
-	atomic_long_t		nr_freed;
-	atomic_long_t		nr_keys;
-	atomic_long_t		nr_dirty;
-};
-
-struct bkey_cached_key {
-	u32			btree_id;
-	struct bpos		pos;
-} __packed __aligned(4);
-
 #define BKEY_CACHED_ACCESSED		0
 #define BKEY_CACHED_DIRTY		1
 
@@ -352,7 +323,6 @@ struct bkey_cached {
 	struct rhash_head	hash;
 	struct list_head	list;
 
-	struct journal_preres	res;
 	struct journal_entry_pin journal;
 	u64			seq;
 
@@ -380,20 +350,16 @@ struct btree_insert_entry {
 	 * to the size of the key being overwritten in the btree:
 	 */
 	u8			old_btree_u64s;
+	btree_path_idx_t	path;
 	struct bkey_i		*k;
-	struct btree_path	*path;
-	u64			seq;
 	/* key being overwritten: */
 	struct bkey		old_k;
 	const struct bch_val	*old_v;
 	unsigned long		ip_allocated;
 };
 
-#ifndef CONFIG_LOCKDEP
-#define BTREE_ITER_MAX		64
-#else
-#define BTREE_ITER_MAX		32
-#endif
+#define BTREE_ITER_INITIAL		64
+#define BTREE_ITER_MAX			(1U << 10)
 
 struct btree_trans_commit_hook;
 typedef int (btree_trans_commit_hook_fn)(struct btree_trans *, struct btree_trans_commit_hook *);
@@ -407,25 +373,30 @@ struct btree_trans_commit_hook {
 
 #define BTREE_TRANS_MAX_LOCK_HOLD_TIME_NS	10000
 
+struct btree_trans_paths {
+	unsigned long		nr_paths;
+	struct btree_path	paths[];
+};
+
 struct btree_trans {
 	struct bch_fs		*c;
-	const char		*fn;
-	struct closure		ref;
-	struct list_head	list;
-	u64			last_begin_time;
 
-	u8			lock_may_not_fail;
-	u8			lock_must_abort;
-	struct btree_bkey_cached_common *locking;
-	struct six_lock_waiter	locking_wait;
+	unsigned long		*paths_allocated;
+	struct btree_path	*paths;
+	btree_path_idx_t	*sorted;
+	struct btree_insert_entry *updates;
 
-	int			srcu_idx;
+	void			*mem;
+	unsigned		mem_top;
+	unsigned		mem_bytes;
 
+	btree_path_idx_t	nr_sorted;
+	btree_path_idx_t	nr_paths;
+	btree_path_idx_t	nr_paths_max;
 	u8			fn_idx;
-	u8			nr_sorted;
 	u8			nr_updates;
-	u8			nr_wb_updates;
-	u8			wb_updates_size;
+	u8			lock_must_abort;
+	bool			lock_may_not_fail:1;
 	bool			srcu_held:1;
 	bool			used_mempool:1;
 	bool			in_traverse_all:1;
@@ -434,45 +405,59 @@ struct btree_trans {
 	bool			journal_transaction_names:1;
 	bool			journal_replay_not_finished:1;
 	bool			notrace_relock_fail:1;
+	bool			write_locked:1;
 	enum bch_errcode	restarted:16;
 	u32			restart_count;
+
+	u64			last_begin_time;
 	unsigned long		last_begin_ip;
 	unsigned long		last_restarted_ip;
 	unsigned long		srcu_lock_time;
 
-	/*
-	 * For when bch2_trans_update notices we'll be splitting a compressed
-	 * extent:
-	 */
-	unsigned		extra_journal_res;
-	unsigned		nr_max_paths;
-
-	u64			paths_allocated;
-
-	unsigned		mem_top;
-	unsigned		mem_max;
-	unsigned		mem_bytes;
-	void			*mem;
-
-	u8			sorted[BTREE_ITER_MAX + 8];
-	struct btree_path	paths[BTREE_ITER_MAX];
-	struct btree_insert_entry updates[BTREE_ITER_MAX];
-	struct btree_write_buffered_key *wb_updates;
+	const char		*fn;
+	struct btree_bkey_cached_common *locking;
+	struct six_lock_waiter	locking_wait;
+	int			srcu_idx;
 
 	/* update path: */
+	u16			journal_entries_u64s;
+	u16			journal_entries_size;
+	struct jset_entry	*journal_entries;
+
 	struct btree_trans_commit_hook *hooks;
-	darray_u64		extra_journal_entries;
 	struct journal_entry_pin *journal_pin;
 
 	struct journal_res	journal_res;
-	struct journal_preres	journal_preres;
 	u64			*journal_seq;
 	struct disk_reservation *disk_res;
 	unsigned		journal_u64s;
-	unsigned		journal_preres_u64s;
+	unsigned		extra_disk_res; /* XXX kill */
 	struct replicas_delta_list *fs_usage_deltas;
+
+	/* Entries before this are zeroed out on every bch2_trans_get() call */
+
+	struct list_head	list;
+	struct closure		ref;
+
+	unsigned long		_paths_allocated[BITS_TO_LONGS(BTREE_ITER_INITIAL)];
+	struct btree_trans_paths trans_paths;
+	struct btree_path	_paths[BTREE_ITER_INITIAL];
+	btree_path_idx_t	_sorted[BTREE_ITER_INITIAL + 4];
+	struct btree_insert_entry _updates[BTREE_ITER_INITIAL];
 };
 
+static inline struct btree_path *btree_iter_path(struct btree_trans *trans, struct btree_iter *iter)
+{
+	return trans->paths + iter->path;
+}
+
+static inline struct btree_path *btree_iter_key_cache_path(struct btree_trans *trans, struct btree_iter *iter)
+{
+	return iter->key_cache_path
+		? trans->paths + iter->key_cache_path
+		: NULL;
+}
+
 #define BCH_BTREE_WRITE_TYPES()						\
 	x(initial,		0)					\
 	x(init_next_bset,	1)					\
diff --git a/fs/bcachefs/btree_update.c b/fs/bcachefs/btree_update.c
index 324767c0ddcc..c3ff365acce9 100644
--- a/fs/bcachefs/btree_update.c
+++ b/fs/bcachefs/btree_update.c
@@ -24,7 +24,7 @@ static inline int btree_insert_entry_cmp(const struct btree_insert_entry *l,
 }
 
 static int __must_check
-bch2_trans_update_by_path(struct btree_trans *, struct btree_path *,
+bch2_trans_update_by_path(struct btree_trans *, btree_path_idx_t,
 			  struct bkey_i *, enum btree_update_flags,
 			  unsigned long ip);
 
@@ -186,8 +186,11 @@ int bch2_trans_update_extent_overwrite(struct btree_trans *trans,
 	enum btree_id btree_id = iter->btree_id;
 	struct bkey_i *update;
 	struct bpos new_start = bkey_start_pos(new.k);
-	bool front_split = bkey_lt(bkey_start_pos(old.k), new_start);
-	bool back_split  = bkey_gt(old.k->p, new.k->p);
+	unsigned front_split = bkey_lt(bkey_start_pos(old.k), new_start);
+	unsigned back_split  = bkey_gt(old.k->p, new.k->p);
+	unsigned middle_split = (front_split || back_split) &&
+		old.k->p.snapshot != new.k->p.snapshot;
+	unsigned nr_splits = front_split + back_split + middle_split;
 	int ret = 0, compressed_sectors;
 
 	/*
@@ -195,10 +198,9 @@ int bch2_trans_update_extent_overwrite(struct btree_trans *trans,
 	 * so that __bch2_trans_commit() can increase our disk
 	 * reservation:
 	 */
-	if (((front_split && back_split) ||
-	     ((front_split || back_split) && old.k->p.snapshot != new.k->p.snapshot)) &&
+	if (nr_splits > 1 &&
 	    (compressed_sectors = bch2_bkey_sectors_compressed(old)))
-		trans->extra_journal_res += compressed_sectors;
+		trans->extra_disk_res += compressed_sectors * (nr_splits - 1);
 
 	if (front_split) {
 		update = bch2_bkey_make_mut_noupdate(trans, old);
@@ -216,8 +218,7 @@ int bch2_trans_update_extent_overwrite(struct btree_trans *trans,
 	}
 
 	/* If we're overwriting in a different snapshot - middle split: */
-	if (old.k->p.snapshot != new.k->p.snapshot &&
-	    (front_split || back_split)) {
+	if (middle_split) {
 		update = bch2_bkey_make_mut_noupdate(trans, old);
 		if ((ret = PTR_ERR_OR_ZERO(update)))
 			return ret;
@@ -338,21 +339,22 @@ err:
 }
 
 static noinline int flush_new_cached_update(struct btree_trans *trans,
-					    struct btree_path *path,
 					    struct btree_insert_entry *i,
 					    enum btree_update_flags flags,
 					    unsigned long ip)
 {
-	struct btree_path *btree_path;
 	struct bkey k;
 	int ret;
 
-	btree_path = bch2_path_get(trans, path->btree_id, path->pos, 1, 0,
-				   BTREE_ITER_INTENT, _THIS_IP_);
-	ret = bch2_btree_path_traverse(trans, btree_path, 0);
+	btree_path_idx_t path_idx =
+		bch2_path_get(trans, i->btree_id, i->old_k.p, 1, 0,
+			      BTREE_ITER_INTENT, _THIS_IP_);
+	ret = bch2_btree_path_traverse(trans, path_idx, 0);
 	if (ret)
 		goto out;
 
+	struct btree_path *btree_path = trans->paths + path_idx;
+
 	/*
 	 * The old key in the insert entry might actually refer to an existing
 	 * key in the btree that has been deleted from cache and not yet
@@ -367,43 +369,34 @@ static noinline int flush_new_cached_update(struct btree_trans *trans,
 	i->flags |= BTREE_TRIGGER_NORUN;
 
 	btree_path_set_should_be_locked(btree_path);
-	ret = bch2_trans_update_by_path(trans, btree_path, i->k, flags, ip);
+	ret = bch2_trans_update_by_path(trans, path_idx, i->k, flags, ip);
 out:
-	bch2_path_put(trans, btree_path, true);
+	bch2_path_put(trans, path_idx, true);
 	return ret;
 }
 
 static int __must_check
-bch2_trans_update_by_path(struct btree_trans *trans, struct btree_path *path,
+bch2_trans_update_by_path(struct btree_trans *trans, btree_path_idx_t path_idx,
 			  struct bkey_i *k, enum btree_update_flags flags,
 			  unsigned long ip)
 {
 	struct bch_fs *c = trans->c;
 	struct btree_insert_entry *i, n;
-	u64 seq = 0;
 	int cmp;
 
+	struct btree_path *path = trans->paths + path_idx;
 	EBUG_ON(!path->should_be_locked);
-	EBUG_ON(trans->nr_updates >= BTREE_ITER_MAX);
+	EBUG_ON(trans->nr_updates >= trans->nr_paths);
 	EBUG_ON(!bpos_eq(k->k.p, path->pos));
 
-	/*
-	 * The transaction journal res hasn't been allocated at this point.
-	 * That occurs at commit time. Reuse the seq field to pass in the seq
-	 * of a prejournaled key.
-	 */
-	if (flags & BTREE_UPDATE_PREJOURNAL)
-		seq = trans->journal_res.seq;
-
 	n = (struct btree_insert_entry) {
 		.flags		= flags,
 		.bkey_type	= __btree_node_type(path->level, path->btree_id),
 		.btree_id	= path->btree_id,
 		.level		= path->level,
 		.cached		= path->cached,
-		.path		= path,
+		.path		= path_idx,
 		.k		= k,
-		.seq		= seq,
 		.ip_allocated	= ip,
 	};
 
@@ -417,7 +410,7 @@ bch2_trans_update_by_path(struct btree_trans *trans, struct btree_path *path,
 	 * Pending updates are kept sorted: first, find position of new update,
 	 * then delete/trim any updates the new update overwrites:
 	 */
-	trans_for_each_update(trans, i) {
+	for (i = trans->updates; i < trans->updates + trans->nr_updates; i++) {
 		cmp = btree_insert_entry_cmp(&n, i);
 		if (cmp <= 0)
 			break;
@@ -431,7 +424,6 @@ bch2_trans_update_by_path(struct btree_trans *trans, struct btree_path *path,
 		i->cached	= n.cached;
 		i->k		= n.k;
 		i->path		= n.path;
-		i->seq		= n.seq;
 		i->ip_allocated	= n.ip_allocated;
 	} else {
 		array_insert_item(trans->updates, trans->nr_updates,
@@ -451,7 +443,7 @@ bch2_trans_update_by_path(struct btree_trans *trans, struct btree_path *path,
 		}
 	}
 
-	__btree_path_get(i->path, true);
+	__btree_path_get(trans->paths + i->path, true);
 
 	/*
 	 * If a key is present in the key cache, it must also exist in the
@@ -461,7 +453,7 @@ bch2_trans_update_by_path(struct btree_trans *trans, struct btree_path *path,
 	 * work:
 	 */
 	if (path->cached && bkey_deleted(&i->old_k))
-		return flush_new_cached_update(trans, path, i, flags, ip);
+		return flush_new_cached_update(trans, i, flags, ip);
 
 	return 0;
 }
@@ -470,9 +462,11 @@ static noinline int bch2_trans_update_get_key_cache(struct btree_trans *trans,
 						    struct btree_iter *iter,
 						    struct btree_path *path)
 {
-	if (!iter->key_cache_path ||
-	    !iter->key_cache_path->should_be_locked ||
-	    !bpos_eq(iter->key_cache_path->pos, iter->pos)) {
+	struct btree_path *key_cache_path = btree_iter_key_cache_path(trans, iter);
+
+	if (!key_cache_path ||
+	    !key_cache_path->should_be_locked ||
+	    !bpos_eq(key_cache_path->pos, iter->pos)) {
 		struct bkey_cached *ck;
 		int ret;
 
@@ -487,19 +481,18 @@ static noinline int bch2_trans_update_get_key_cache(struct btree_trans *trans,
 						iter->flags & BTREE_ITER_INTENT,
 						_THIS_IP_);
 
-		ret = bch2_btree_path_traverse(trans, iter->key_cache_path,
-					       BTREE_ITER_CACHED);
+		ret = bch2_btree_path_traverse(trans, iter->key_cache_path, BTREE_ITER_CACHED);
 		if (unlikely(ret))
 			return ret;
 
-		ck = (void *) iter->key_cache_path->l[0].b;
+		ck = (void *) trans->paths[iter->key_cache_path].l[0].b;
 
 		if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) {
 			trace_and_count(trans->c, trans_restart_key_cache_raced, trans, _RET_IP_);
 			return btree_trans_restart(trans, BCH_ERR_transaction_restart_key_cache_raced);
 		}
 
-		btree_path_set_should_be_locked(iter->key_cache_path);
+		btree_path_set_should_be_locked(trans->paths + iter->key_cache_path);
 	}
 
 	return 0;
@@ -508,7 +501,7 @@ static noinline int bch2_trans_update_get_key_cache(struct btree_trans *trans,
 int __must_check bch2_trans_update(struct btree_trans *trans, struct btree_iter *iter,
 				   struct bkey_i *k, enum btree_update_flags flags)
 {
-	struct btree_path *path = iter->update_path ?: iter->path;
+	btree_path_idx_t path_idx = iter->update_path ?: iter->path;
 	int ret;
 
 	if (iter->flags & BTREE_ITER_IS_EXTENTS)
@@ -528,6 +521,7 @@ int __must_check bch2_trans_update(struct btree_trans *trans, struct btree_iter
 	/*
 	 * Ensure that updates to cached btrees go to the key cache:
 	 */
+	struct btree_path *path = trans->paths + path_idx;
 	if (!(flags & BTREE_UPDATE_KEY_CACHE_RECLAIM) &&
 	    !path->cached &&
 	    !path->level &&
@@ -536,75 +530,49 @@ int __must_check bch2_trans_update(struct btree_trans *trans, struct btree_iter
 		if (ret)
 			return ret;
 
-		path = iter->key_cache_path;
+		path_idx = iter->key_cache_path;
 	}
 
-	return bch2_trans_update_by_path(trans, path, k, flags, _RET_IP_);
+	return bch2_trans_update_by_path(trans, path_idx, k, flags, _RET_IP_);
 }
 
-/*
- * Add a transaction update for a key that has already been journaled.
- */
-int __must_check bch2_trans_update_seq(struct btree_trans *trans, u64 seq,
-				       struct btree_iter *iter, struct bkey_i *k,
-				       enum btree_update_flags flags)
+int bch2_btree_insert_clone_trans(struct btree_trans *trans,
+				  enum btree_id btree,
+				  struct bkey_i *k)
 {
-	trans->journal_res.seq = seq;
-	return bch2_trans_update(trans, iter, k, flags|BTREE_UPDATE_NOJOURNAL|
-						 BTREE_UPDATE_PREJOURNAL);
+	struct bkey_i *n = bch2_trans_kmalloc(trans, bkey_bytes(&k->k));
+	int ret = PTR_ERR_OR_ZERO(n);
+	if (ret)
+		return ret;
+
+	bkey_copy(n, k);
+	return bch2_btree_insert_trans(trans, btree, n, 0);
 }
 
-int __must_check bch2_trans_update_buffered(struct btree_trans *trans,
-					    enum btree_id btree,
-					    struct bkey_i *k)
+struct jset_entry *__bch2_trans_jset_entry_alloc(struct btree_trans *trans, unsigned u64s)
 {
-	struct btree_write_buffered_key *i;
-	int ret;
+	unsigned new_top = trans->journal_entries_u64s + u64s;
+	unsigned old_size = trans->journal_entries_size;
 
-	EBUG_ON(trans->nr_wb_updates > trans->wb_updates_size);
-	EBUG_ON(k->k.u64s > BTREE_WRITE_BUFERED_U64s_MAX);
+	if (new_top > trans->journal_entries_size) {
+		trans->journal_entries_size = roundup_pow_of_two(new_top);
 
-	trans_for_each_wb_update(trans, i) {
-		if (i->btree == btree && bpos_eq(i->k.k.p, k->k.p)) {
-			bkey_copy(&i->k, k);
-			return 0;
-		}
+		btree_trans_stats(trans)->journal_entries_size = trans->journal_entries_size;
 	}
 
-	if (!trans->wb_updates ||
-	    trans->nr_wb_updates == trans->wb_updates_size) {
-		struct btree_write_buffered_key *u;
+	struct jset_entry *n =
+		bch2_trans_kmalloc_nomemzero(trans,
+				trans->journal_entries_size * sizeof(u64));
+	if (IS_ERR(n))
+		return ERR_CAST(n);
 
-		if (trans->nr_wb_updates == trans->wb_updates_size) {
-			struct btree_transaction_stats *s = btree_trans_stats(trans);
+	if (trans->journal_entries)
+		memcpy(n, trans->journal_entries, old_size * sizeof(u64));
+	trans->journal_entries = n;
 
-			BUG_ON(trans->wb_updates_size > U8_MAX / 2);
-			trans->wb_updates_size = max(1, trans->wb_updates_size * 2);
-			if (s)
-				s->wb_updates_size = trans->wb_updates_size;
-		}
-
-		u = bch2_trans_kmalloc_nomemzero(trans,
-					trans->wb_updates_size *
-					sizeof(struct btree_write_buffered_key));
-		ret = PTR_ERR_OR_ZERO(u);
-		if (ret)
-			return ret;
-
-		if (trans->nr_wb_updates)
-			memcpy(u, trans->wb_updates, trans->nr_wb_updates *
-			       sizeof(struct btree_write_buffered_key));
-		trans->wb_updates = u;
-	}
-
-	trans->wb_updates[trans->nr_wb_updates] = (struct btree_write_buffered_key) {
-		.btree	= btree,
-	};
-
-	bkey_copy(&trans->wb_updates[trans->nr_wb_updates].k, k);
-	trans->nr_wb_updates++;
-
-	return 0;
+	struct jset_entry *e = btree_trans_journal_entries_top(trans);
+	trans->journal_entries_u64s = new_top;
+	return e;
 }
 
 int bch2_bkey_get_empty_slot(struct btree_trans *trans, struct btree_iter *iter,
@@ -716,20 +684,6 @@ int bch2_btree_delete_at(struct btree_trans *trans,
 	return bch2_btree_delete_extent_at(trans, iter, 0, update_flags);
 }
 
-int bch2_btree_delete_at_buffered(struct btree_trans *trans,
-				  enum btree_id btree, struct bpos pos)
-{
-	struct bkey_i *k;
-
-	k = bch2_trans_kmalloc(trans, sizeof(*k));
-	if (IS_ERR(k))
-		return PTR_ERR(k);
-
-	bkey_init(&k->k);
-	k->k.p = pos;
-	return bch2_trans_update_buffered(trans, btree, k);
-}
-
 int bch2_btree_delete(struct btree_trans *trans,
 		      enum btree_id btree, struct bpos pos,
 		      unsigned update_flags)
@@ -792,7 +746,7 @@ int bch2_btree_delete_range_trans(struct btree_trans *trans, enum btree_id id,
 
 		ret   = bch2_trans_update(trans, &iter, &delete, update_flags) ?:
 			bch2_trans_commit(trans, &disk_res, journal_seq,
-					  BTREE_INSERT_NOFAIL);
+					  BCH_TRANS_COMMIT_no_enospc);
 		bch2_disk_reservation_put(trans->c, &disk_res);
 err:
 		/*
@@ -834,56 +788,26 @@ int bch2_btree_delete_range(struct bch_fs *c, enum btree_id id,
 int bch2_btree_bit_mod(struct btree_trans *trans, enum btree_id btree,
 		       struct bpos pos, bool set)
 {
-	struct bkey_i *k;
-	int ret = 0;
+	struct bkey_i k;
 
-	k = bch2_trans_kmalloc_nomemzero(trans, sizeof(*k));
-	ret = PTR_ERR_OR_ZERO(k);
-	if (unlikely(ret))
-		return ret;
+	bkey_init(&k.k);
+	k.k.type = set ? KEY_TYPE_set : KEY_TYPE_deleted;
+	k.k.p = pos;
 
-	bkey_init(&k->k);
-	k->k.type = set ? KEY_TYPE_set : KEY_TYPE_deleted;
-	k->k.p = pos;
-
-	return bch2_trans_update_buffered(trans, btree, k);
+	return bch2_trans_update_buffered(trans, btree, &k);
 }
 
-__printf(2, 0)
-static int __bch2_trans_log_msg(darray_u64 *entries, const char *fmt, va_list args)
+static int __bch2_trans_log_msg(struct btree_trans *trans, struct printbuf *buf, unsigned u64s)
 {
-	struct printbuf buf = PRINTBUF;
-	struct jset_entry_log *l;
-	unsigned u64s;
-	int ret;
-
-	prt_vprintf(&buf, fmt, args);
-	ret = buf.allocation_failure ? -BCH_ERR_ENOMEM_trans_log_msg : 0;
-	if (ret)
-		goto err;
-
-	u64s = DIV_ROUND_UP(buf.pos, sizeof(u64));
-
-	ret = darray_make_room(entries, jset_u64s(u64s));
+	struct jset_entry *e = bch2_trans_jset_entry_alloc(trans, jset_u64s(u64s));
+	int ret = PTR_ERR_OR_ZERO(e);
 	if (ret)
-		goto err;
+		return ret;
 
-	l = (void *) &darray_top(*entries);
-	l->entry.u64s		= cpu_to_le16(u64s);
-	l->entry.btree_id	= 0;
-	l->entry.level		= 1;
-	l->entry.type		= BCH_JSET_ENTRY_log;
-	l->entry.pad[0]		= 0;
-	l->entry.pad[1]		= 0;
-	l->entry.pad[2]		= 0;
-	memcpy(l->d, buf.buf, buf.pos);
-	while (buf.pos & 7)
-		l->d[buf.pos++] = '\0';
-
-	entries->nr += jset_u64s(u64s);
-err:
-	printbuf_exit(&buf);
-	return ret;
+	struct jset_entry_log *l = container_of(e, struct jset_entry_log, entry);
+	journal_entry_init(e, BCH_JSET_ENTRY_log, 0, 1, u64s);
+	memcpy(l->d, buf->buf, buf->pos);
+	return 0;
 }
 
 __printf(3, 0)
@@ -891,16 +815,32 @@ static int
 __bch2_fs_log_msg(struct bch_fs *c, unsigned commit_flags, const char *fmt,
 		  va_list args)
 {
-	int ret;
+	struct printbuf buf = PRINTBUF;
+	prt_vprintf(&buf, fmt, args);
+
+	unsigned u64s = DIV_ROUND_UP(buf.pos, sizeof(u64));
+	prt_chars(&buf, '\0', u64s * sizeof(u64) - buf.pos);
+
+	int ret = buf.allocation_failure ? -BCH_ERR_ENOMEM_trans_log_msg : 0;
+	if (ret)
+		goto err;
 
 	if (!test_bit(JOURNAL_STARTED, &c->journal.flags)) {
-		ret = __bch2_trans_log_msg(&c->journal.early_journal_entries, fmt, args);
+		ret = darray_make_room(&c->journal.early_journal_entries, jset_u64s(u64s));
+		if (ret)
+			goto err;
+
+		struct jset_entry_log *l = (void *) &darray_top(c->journal.early_journal_entries);
+		journal_entry_init(&l->entry, BCH_JSET_ENTRY_log, 0, 1, u64s);
+		memcpy(l->d, buf.buf, buf.pos);
+		c->journal.early_journal_entries.nr += jset_u64s(u64s);
 	} else {
 		ret = bch2_trans_do(c, NULL, NULL,
-			BTREE_INSERT_LAZY_RW|commit_flags,
-			__bch2_trans_log_msg(&trans->extra_journal_entries, fmt, args));
+			BCH_TRANS_COMMIT_lazy_rw|commit_flags,
+			__bch2_trans_log_msg(trans, &buf, u64s));
 	}
-
+err:
+	printbuf_exit(&buf);
 	return ret;
 }
 
diff --git a/fs/bcachefs/btree_update.h b/fs/bcachefs/btree_update.h
index 9816d2286540..b9382b7b288b 100644
--- a/fs/bcachefs/btree_update.h
+++ b/fs/bcachefs/btree_update.h
@@ -21,42 +21,32 @@ void bch2_btree_add_journal_pin(struct bch_fs *, struct btree *, u64);
 void bch2_btree_insert_key_leaf(struct btree_trans *, struct btree_path *,
 				struct bkey_i *, u64);
 
-enum btree_insert_flags {
+#define BCH_TRANS_COMMIT_FLAGS()							\
+	x(no_enospc,	"don't check for enospc")					\
+	x(no_check_rw,	"don't attempt to take a ref on c->writes")			\
+	x(lazy_rw,	"go read-write if we haven't yet - only for use in recovery")	\
+	x(no_journal_res, "don't take a journal reservation, instead "			\
+			"pin journal entry referred to by trans->journal_res.seq")	\
+	x(journal_reclaim, "operation required for journal reclaim; may return error"	\
+			"instead of deadlocking if BCH_WATERMARK_reclaim not specified")\
+
+enum __bch_trans_commit_flags {
 	/* First bits for bch_watermark: */
-	__BTREE_INSERT_NOFAIL = BCH_WATERMARK_BITS,
-	__BTREE_INSERT_NOCHECK_RW,
-	__BTREE_INSERT_LAZY_RW,
-	__BTREE_INSERT_JOURNAL_REPLAY,
-	__BTREE_INSERT_JOURNAL_RECLAIM,
-	__BTREE_INSERT_NOWAIT,
-	__BTREE_INSERT_GC_LOCK_HELD,
-	__BCH_HASH_SET_MUST_CREATE,
-	__BCH_HASH_SET_MUST_REPLACE,
+	__BCH_TRANS_COMMIT_FLAGS_START = BCH_WATERMARK_BITS,
+#define x(n, ...)	__BCH_TRANS_COMMIT_##n,
+	BCH_TRANS_COMMIT_FLAGS()
+#undef x
 };
 
-/* Don't check for -ENOSPC: */
-#define BTREE_INSERT_NOFAIL		BIT(__BTREE_INSERT_NOFAIL)
-
-#define BTREE_INSERT_NOCHECK_RW		BIT(__BTREE_INSERT_NOCHECK_RW)
-#define BTREE_INSERT_LAZY_RW		BIT(__BTREE_INSERT_LAZY_RW)
-
-/* Insert is for journal replay - don't get journal reservations: */
-#define BTREE_INSERT_JOURNAL_REPLAY	BIT(__BTREE_INSERT_JOURNAL_REPLAY)
-
-/* Insert is being called from journal reclaim path: */
-#define BTREE_INSERT_JOURNAL_RECLAIM	BIT(__BTREE_INSERT_JOURNAL_RECLAIM)
-
-/* Don't block on allocation failure (for new btree nodes: */
-#define BTREE_INSERT_NOWAIT		BIT(__BTREE_INSERT_NOWAIT)
-#define BTREE_INSERT_GC_LOCK_HELD	BIT(__BTREE_INSERT_GC_LOCK_HELD)
-
-#define BCH_HASH_SET_MUST_CREATE	BIT(__BCH_HASH_SET_MUST_CREATE)
-#define BCH_HASH_SET_MUST_REPLACE	BIT(__BCH_HASH_SET_MUST_REPLACE)
+enum bch_trans_commit_flags {
+#define x(n, ...)	BCH_TRANS_COMMIT_##n = BIT(__BCH_TRANS_COMMIT_##n),
+	BCH_TRANS_COMMIT_FLAGS()
+#undef x
+};
 
 int bch2_btree_delete_extent_at(struct btree_trans *, struct btree_iter *,
 				unsigned, unsigned);
 int bch2_btree_delete_at(struct btree_trans *, struct btree_iter *, unsigned);
-int bch2_btree_delete_at_buffered(struct btree_trans *, enum btree_id, struct bpos);
 int bch2_btree_delete(struct btree_trans *, enum btree_id, struct bpos, unsigned);
 
 int bch2_btree_insert_nonextent(struct btree_trans *, enum btree_id,
@@ -74,6 +64,12 @@ int bch2_btree_delete_range(struct bch_fs *, enum btree_id,
 
 int bch2_btree_bit_mod(struct btree_trans *, enum btree_id, struct bpos, bool);
 
+static inline int bch2_btree_delete_at_buffered(struct btree_trans *trans,
+						enum btree_id btree, struct bpos pos)
+{
+	return bch2_btree_bit_mod(trans, btree, pos, false);
+}
+
 int __bch2_insert_snapshot_whiteouts(struct btree_trans *, enum btree_id,
 				     struct bpos, struct bpos);
 
@@ -105,10 +101,44 @@ int bch2_bkey_get_empty_slot(struct btree_trans *, struct btree_iter *,
 
 int __must_check bch2_trans_update(struct btree_trans *, struct btree_iter *,
 				   struct bkey_i *, enum btree_update_flags);
-int __must_check bch2_trans_update_seq(struct btree_trans *, u64, struct btree_iter *,
-				       struct bkey_i *, enum btree_update_flags);
-int __must_check bch2_trans_update_buffered(struct btree_trans *,
-					    enum btree_id, struct bkey_i *);
+
+struct jset_entry *__bch2_trans_jset_entry_alloc(struct btree_trans *, unsigned);
+
+static inline struct jset_entry *btree_trans_journal_entries_top(struct btree_trans *trans)
+{
+	return (void *) ((u64 *) trans->journal_entries + trans->journal_entries_u64s);
+}
+
+static inline struct jset_entry *
+bch2_trans_jset_entry_alloc(struct btree_trans *trans, unsigned u64s)
+{
+	if (!trans->journal_entries ||
+	    trans->journal_entries_u64s + u64s > trans->journal_entries_size)
+		return __bch2_trans_jset_entry_alloc(trans, u64s);
+
+	struct jset_entry *e = btree_trans_journal_entries_top(trans);
+	trans->journal_entries_u64s += u64s;
+	return e;
+}
+
+int bch2_btree_insert_clone_trans(struct btree_trans *, enum btree_id, struct bkey_i *);
+
+static inline int __must_check bch2_trans_update_buffered(struct btree_trans *trans,
+					    enum btree_id btree,
+					    struct bkey_i *k)
+{
+	if (unlikely(trans->journal_replay_not_finished))
+		return bch2_btree_insert_clone_trans(trans, btree, k);
+
+	struct jset_entry *e = bch2_trans_jset_entry_alloc(trans, jset_u64s(k->k.u64s));
+	int ret = PTR_ERR_OR_ZERO(e);
+	if (ret)
+		return ret;
+
+	journal_entry_init(e, BCH_JSET_ENTRY_write_buffer_keys, btree, 0, k->k.u64s);
+	bkey_copy(e->start, k);
+	return 0;
+}
 
 void bch2_trans_commit_hook(struct btree_trans *,
 			    struct btree_trans_commit_hook *);
@@ -157,28 +187,19 @@ static inline int bch2_trans_commit(struct btree_trans *trans,
 	bch2_trans_run(_c, commit_do(trans, _disk_res, _journal_seq, _flags, _do))
 
 #define trans_for_each_update(_trans, _i)				\
-	for ((_i) = (_trans)->updates;					\
+	for (struct btree_insert_entry *_i = (_trans)->updates;		\
 	     (_i) < (_trans)->updates + (_trans)->nr_updates;		\
 	     (_i)++)
 
-#define trans_for_each_wb_update(_trans, _i)				\
-	for ((_i) = (_trans)->wb_updates;				\
-	     (_i) < (_trans)->wb_updates + (_trans)->nr_wb_updates;	\
-	     (_i)++)
-
 static inline void bch2_trans_reset_updates(struct btree_trans *trans)
 {
-	struct btree_insert_entry *i;
-
 	trans_for_each_update(trans, i)
 		bch2_path_put(trans, i->path, true);
 
-	trans->extra_journal_res	= 0;
 	trans->nr_updates		= 0;
-	trans->nr_wb_updates		= 0;
-	trans->wb_updates		= NULL;
+	trans->journal_entries_u64s	= 0;
 	trans->hooks			= NULL;
-	trans->extra_journal_entries.nr	= 0;
+	trans->extra_disk_res		= 0;
 
 	if (trans->fs_usage_deltas) {
 		trans->fs_usage_deltas->used = 0;
diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index 39c2db68123b..44f9dfa28a09 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -25,24 +25,24 @@
 #include <linux/random.h>
 
 static int bch2_btree_insert_node(struct btree_update *, struct btree_trans *,
-				  struct btree_path *, struct btree *,
+				  btree_path_idx_t, struct btree *,
 				  struct keylist *, unsigned);
 static void bch2_btree_update_add_new_node(struct btree_update *, struct btree *);
 
-static struct btree_path *get_unlocked_mut_path(struct btree_trans *trans,
-						enum btree_id btree_id,
-						unsigned level,
-						struct bpos pos)
+static btree_path_idx_t get_unlocked_mut_path(struct btree_trans *trans,
+					      enum btree_id btree_id,
+					      unsigned level,
+					      struct bpos pos)
 {
-	struct btree_path *path;
-
-	path = bch2_path_get(trans, btree_id, pos, level + 1, level,
+	btree_path_idx_t path_idx = bch2_path_get(trans, btree_id, pos, level + 1, level,
 			     BTREE_ITER_NOPRESERVE|
 			     BTREE_ITER_INTENT, _RET_IP_);
-	path = bch2_btree_path_make_mut(trans, path, true, _RET_IP_);
+	path_idx = bch2_btree_path_make_mut(trans, path_idx, true, _RET_IP_);
+
+	struct btree_path *path = trans->paths + path_idx;
 	bch2_btree_path_downgrade(trans, path);
 	__bch2_btree_path_unlock(trans, path);
-	return path;
+	return path_idx;
 }
 
 /* Debug code: */
@@ -99,7 +99,7 @@ static void btree_node_interior_verify(struct bch_fs *c, struct btree *b)
 
 /* Calculate ideal packed bkey format for new btree nodes: */
 
-void __bch2_btree_calc_format(struct bkey_format_state *s, struct btree *b)
+static void __bch2_btree_calc_format(struct bkey_format_state *s, struct btree *b)
 {
 	struct bkey_packed *k;
 	struct bset_tree *t;
@@ -125,21 +125,20 @@ static struct bkey_format bch2_btree_calc_format(struct btree *b)
 	return bch2_bkey_format_done(&s);
 }
 
-static size_t btree_node_u64s_with_format(struct btree *b,
+static size_t btree_node_u64s_with_format(struct btree_nr_keys nr,
+					  struct bkey_format *old_f,
 					  struct bkey_format *new_f)
 {
-	struct bkey_format *old_f = &b->format;
-
 	/* stupid integer promotion rules */
 	ssize_t delta =
 	    (((int) new_f->key_u64s - old_f->key_u64s) *
-	     (int) b->nr.packed_keys) +
+	     (int) nr.packed_keys) +
 	    (((int) new_f->key_u64s - BKEY_U64s) *
-	     (int) b->nr.unpacked_keys);
+	     (int) nr.unpacked_keys);
 
-	BUG_ON(delta + b->nr.live_u64s < 0);
+	BUG_ON(delta + nr.live_u64s < 0);
 
-	return b->nr.live_u64s + delta;
+	return nr.live_u64s + delta;
 }
 
 /**
@@ -147,25 +146,29 @@ static size_t btree_node_u64s_with_format(struct btree *b,
  *
  * @c:		filesystem handle
  * @b:		btree node to rewrite
+ * @nr:		number of keys for new node (i.e. b->nr)
  * @new_f:	bkey format to translate keys to
  *
  * Returns: true if all re-packed keys will be able to fit in a new node.
  *
  * Assumes all keys will successfully pack with the new format.
  */
-bool bch2_btree_node_format_fits(struct bch_fs *c, struct btree *b,
+static bool bch2_btree_node_format_fits(struct bch_fs *c, struct btree *b,
+				 struct btree_nr_keys nr,
 				 struct bkey_format *new_f)
 {
-	size_t u64s = btree_node_u64s_with_format(b, new_f);
+	size_t u64s = btree_node_u64s_with_format(nr, &b->format, new_f);
 
 	return __vstruct_bytes(struct btree_node, u64s) < btree_bytes(c);
 }
 
 /* Btree node freeing/allocation: */
 
-static void __btree_node_free(struct bch_fs *c, struct btree *b)
+static void __btree_node_free(struct btree_trans *trans, struct btree *b)
 {
-	trace_and_count(c, btree_node_free, c, b);
+	struct bch_fs *c = trans->c;
+
+	trace_and_count(c, btree_node_free, trans, b);
 
 	BUG_ON(btree_node_write_blocked(b));
 	BUG_ON(btree_node_dirty(b));
@@ -187,15 +190,15 @@ static void bch2_btree_node_free_inmem(struct btree_trans *trans,
 				       struct btree *b)
 {
 	struct bch_fs *c = trans->c;
-	unsigned level = b->c.level;
+	unsigned i, level = b->c.level;
 
 	bch2_btree_node_lock_write_nofail(trans, path, &b->c);
 	bch2_btree_node_hash_remove(&c->btree_cache, b);
-	__btree_node_free(c, b);
+	__btree_node_free(trans, b);
 	six_unlock_write(&b->c.lock);
 	mark_btree_node_locked_noreset(path, level, BTREE_NODE_INTENT_LOCKED);
 
-	trans_for_each_path(trans, path)
+	trans_for_each_path(trans, path, i)
 		if (path->l[level].b == b) {
 			btree_node_unlock(trans, path, level);
 			path->l[level].b = ERR_PTR(-BCH_ERR_no_btree_node_init);
@@ -209,7 +212,7 @@ static void bch2_btree_node_free_never_used(struct btree_update *as,
 	struct bch_fs *c = as->c;
 	struct prealloc_nodes *p = &as->prealloc_nodes[b->c.lock.readers != NULL];
 	struct btree_path *path;
-	unsigned level = b->c.level;
+	unsigned i, level = b->c.level;
 
 	BUG_ON(!list_empty(&b->write_blocked));
 	BUG_ON(b->will_make_reachable != (1UL|(unsigned long) as));
@@ -232,7 +235,7 @@ static void bch2_btree_node_free_never_used(struct btree_update *as,
 
 	six_unlock_intent(&b->c.lock);
 
-	trans_for_each_path(trans, path)
+	trans_for_each_path(trans, path, i)
 		if (path->l[level].b == b) {
 			btree_node_unlock(trans, path, level);
 			path->l[level].b = ERR_PTR(-BCH_ERR_no_btree_node_init);
@@ -362,7 +365,7 @@ static struct btree *bch2_btree_node_alloc(struct btree_update *as,
 	ret = bch2_btree_node_hash_insert(&c->btree_cache, b, level, as->btree_id);
 	BUG_ON(ret);
 
-	trace_and_count(c, btree_node_alloc, c, b);
+	trace_and_count(c, btree_node_alloc, trans, b);
 	bch2_increment_clock(c, btree_sectors(c), WRITE);
 	return b;
 }
@@ -391,7 +394,7 @@ static struct btree *bch2_btree_node_alloc_replacement(struct btree_update *as,
 	 * The keys might expand with the new format - if they wouldn't fit in
 	 * the btree node anymore, use the old format for now:
 	 */
-	if (!bch2_btree_node_format_fits(as->c, b, &format))
+	if (!bch2_btree_node_format_fits(as->c, b, b->nr, &format))
 		format = b->format;
 
 	SET_BTREE_NODE_SEQ(n->data, BTREE_NODE_SEQ(b->data) + 1);
@@ -452,7 +455,7 @@ static void bch2_btree_reserve_put(struct btree_update *as, struct btree_trans *
 
 			btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_intent);
 			btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_write);
-			__btree_node_free(c, b);
+			__btree_node_free(trans, b);
 			six_unlock_write(&b->c.lock);
 			six_unlock_intent(&b->c.lock);
 		}
@@ -465,7 +468,6 @@ static int bch2_btree_reserve_get(struct btree_trans *trans,
 				  unsigned flags,
 				  struct closure *cl)
 {
-	struct bch_fs *c = as->c;
 	struct btree *b;
 	unsigned interior;
 	int ret = 0;
@@ -475,11 +477,8 @@ static int bch2_btree_reserve_get(struct btree_trans *trans,
 	/*
 	 * Protects reaping from the btree node cache and using the btree node
 	 * open bucket reserve:
-	 *
-	 * BTREE_INSERT_NOWAIT only applies to btree node allocation, not
-	 * blocking on this lock:
 	 */
-	ret = bch2_btree_cache_cannibalize_lock(c, cl);
+	ret = bch2_btree_cache_cannibalize_lock(trans, cl);
 	if (ret)
 		return ret;
 
@@ -487,9 +486,8 @@ static int bch2_btree_reserve_get(struct btree_trans *trans,
 		struct prealloc_nodes *p = as->prealloc_nodes + interior;
 
 		while (p->nr < nr_nodes[interior]) {
-			b = __bch2_btree_node_alloc(trans, &as->disk_res,
-					flags & BTREE_INSERT_NOWAIT ? NULL : cl,
-					interior, flags);
+			b = __bch2_btree_node_alloc(trans, &as->disk_res, cl,
+						    interior, flags);
 			if (IS_ERR(b)) {
 				ret = PTR_ERR(b);
 				goto err;
@@ -499,7 +497,7 @@ static int bch2_btree_reserve_get(struct btree_trans *trans,
 		}
 	}
 err:
-	bch2_btree_cache_cannibalize_unlock(c);
+	bch2_btree_cache_cannibalize_unlock(trans);
 	return ret;
 }
 
@@ -513,8 +511,6 @@ static void bch2_btree_update_free(struct btree_update *as, struct btree_trans *
 		up_read(&c->gc_lock);
 	as->took_gc_lock = false;
 
-	bch2_journal_preres_put(&c->journal, &as->journal_preres);
-
 	bch2_journal_pin_drop(&c->journal, &as->journal);
 	bch2_journal_pin_flush(&c->journal, &as->journal);
 	bch2_disk_reservation_put(c, &as->disk_res);
@@ -560,24 +556,20 @@ static void btree_update_add_key(struct btree_update *as,
 static int btree_update_nodes_written_trans(struct btree_trans *trans,
 					    struct btree_update *as)
 {
-	struct bkey_i *k;
-	int ret;
-
-	ret = darray_make_room(&trans->extra_journal_entries, as->journal_u64s);
+	struct jset_entry *e = bch2_trans_jset_entry_alloc(trans, as->journal_u64s);
+	int ret = PTR_ERR_OR_ZERO(e);
 	if (ret)
 		return ret;
 
-	memcpy(&darray_top(trans->extra_journal_entries),
-	       as->journal_entries,
-	       as->journal_u64s * sizeof(u64));
-	trans->extra_journal_entries.nr += as->journal_u64s;
+	memcpy(e, as->journal_entries, as->journal_u64s * sizeof(u64));
 
 	trans->journal_pin = &as->journal;
 
 	for_each_keylist_key(&as->old_keys, k) {
 		unsigned level = bkey_i_to_btree_ptr_v2(k)->v.mem_ptr;
 
-		ret = bch2_trans_mark_old(trans, as->btree_id, level, bkey_i_to_s_c(k), 0);
+		ret = bch2_key_trigger_old(trans, as->btree_id, level, bkey_i_to_s_c(k),
+					   BTREE_TRIGGER_TRANSACTIONAL);
 		if (ret)
 			return ret;
 	}
@@ -585,7 +577,8 @@ static int btree_update_nodes_written_trans(struct btree_trans *trans,
 	for_each_keylist_key(&as->new_keys, k) {
 		unsigned level = bkey_i_to_btree_ptr_v2(k)->v.mem_ptr;
 
-		ret = bch2_trans_mark_new(trans, as->btree_id, level, k, 0);
+		ret = bch2_key_trigger_new(trans, as->btree_id, level, bkey_i_to_s(k),
+					   BTREE_TRIGGER_TRANSACTIONAL);
 		if (ret)
 			return ret;
 	}
@@ -646,9 +639,9 @@ static void btree_update_nodes_written(struct btree_update *as)
 	 */
 	ret = commit_do(trans, &as->disk_res, &journal_seq,
 			BCH_WATERMARK_reclaim|
-			BTREE_INSERT_NOFAIL|
-			BTREE_INSERT_NOCHECK_RW|
-			BTREE_INSERT_JOURNAL_RECLAIM,
+			BCH_TRANS_COMMIT_no_enospc|
+			BCH_TRANS_COMMIT_no_check_rw|
+			BCH_TRANS_COMMIT_journal_reclaim,
 			btree_update_nodes_written_trans(trans, as));
 	bch2_trans_unlock(trans);
 
@@ -656,10 +649,11 @@ static void btree_update_nodes_written(struct btree_update *as)
 			     "%s(): error %s", __func__, bch2_err_str(ret));
 err:
 	if (as->b) {
-		struct btree_path *path;
 
 		b = as->b;
-		path = get_unlocked_mut_path(trans, as->btree_id, b->c.level, b->key.k.p);
+		btree_path_idx_t path_idx = get_unlocked_mut_path(trans,
+						as->btree_id, b->c.level, b->key.k.p);
+		struct btree_path *path = trans->paths + path_idx;
 		/*
 		 * @b is the node we did the final insert into:
 		 *
@@ -729,13 +723,11 @@ err:
 
 		btree_node_write_if_need(c, b, SIX_LOCK_intent);
 		btree_node_unlock(trans, path, b->c.level);
-		bch2_path_put(trans, path, true);
+		bch2_path_put(trans, path_idx, true);
 	}
 
 	bch2_journal_pin_drop(&c->journal, &as->journal);
 
-	bch2_journal_preres_put(&c->journal, &as->journal_preres);
-
 	mutex_lock(&c->btree_interior_update_lock);
 	for (i = 0; i < as->nr_new_nodes; i++) {
 		b = as->new_nodes[i];
@@ -782,9 +774,9 @@ static void btree_interior_update_work(struct work_struct *work)
 	}
 }
 
-static void btree_update_set_nodes_written(struct closure *cl)
+static CLOSURE_CALLBACK(btree_update_set_nodes_written)
 {
-	struct btree_update *as = container_of(cl, struct btree_update, cl);
+	closure_type(as, struct btree_update, cl);
 	struct bch_fs *c = as->c;
 
 	mutex_lock(&c->btree_interior_update_lock);
@@ -818,6 +810,12 @@ static void btree_update_updated_node(struct btree_update *as, struct btree *b)
 	mutex_unlock(&c->btree_interior_update_lock);
 }
 
+static int bch2_update_reparent_journal_pin_flush(struct journal *j,
+				struct journal_entry_pin *_pin, u64 seq)
+{
+	return 0;
+}
+
 static void btree_update_reparent(struct btree_update *as,
 				  struct btree_update *child)
 {
@@ -828,7 +826,8 @@ static void btree_update_reparent(struct btree_update *as,
 	child->b = NULL;
 	child->mode = BTREE_INTERIOR_UPDATING_AS;
 
-	bch2_journal_pin_copy(&c->journal, &as->journal, &child->journal, NULL);
+	bch2_journal_pin_copy(&c->journal, &as->journal, &child->journal,
+			      bch2_update_reparent_journal_pin_flush);
 }
 
 static void btree_update_updated_root(struct btree_update *as, struct btree *b)
@@ -937,6 +936,12 @@ static void bch2_btree_update_get_open_buckets(struct btree_update *as, struct b
 			b->ob.v[--b->ob.nr];
 }
 
+static int bch2_btree_update_will_free_node_journal_pin_flush(struct journal *j,
+				struct journal_entry_pin *_pin, u64 seq)
+{
+	return 0;
+}
+
 /*
  * @b is being split/rewritten: it may have pointers to not-yet-written btree
  * nodes and thus outstanding btree_updates - redirect @b's
@@ -988,11 +993,13 @@ static void bch2_btree_interior_update_will_free_node(struct btree_update *as,
 	 * when the new nodes are persistent and reachable on disk:
 	 */
 	w = btree_current_write(b);
-	bch2_journal_pin_copy(&c->journal, &as->journal, &w->journal, NULL);
+	bch2_journal_pin_copy(&c->journal, &as->journal, &w->journal,
+			      bch2_btree_update_will_free_node_journal_pin_flush);
 	bch2_journal_pin_drop(&c->journal, &w->journal);
 
 	w = btree_prev_write(b);
-	bch2_journal_pin_copy(&c->journal, &as->journal, &w->journal, NULL);
+	bch2_journal_pin_copy(&c->journal, &as->journal, &w->journal,
+			      bch2_btree_update_will_free_node_journal_pin_flush);
 	bch2_journal_pin_drop(&c->journal, &w->journal);
 
 	mutex_unlock(&c->btree_interior_update_lock);
@@ -1042,12 +1049,11 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 	struct bch_fs *c = trans->c;
 	struct btree_update *as;
 	u64 start_time = local_clock();
-	int disk_res_flags = (flags & BTREE_INSERT_NOFAIL)
+	int disk_res_flags = (flags & BCH_TRANS_COMMIT_no_enospc)
 		? BCH_DISK_RESERVATION_NOFAIL : 0;
 	unsigned nr_nodes[2] = { 0, 0 };
 	unsigned update_level = level;
 	enum bch_watermark watermark = flags & BCH_WATERMARK_MASK;
-	unsigned journal_flags = 0;
 	int ret = 0;
 	u32 restart_count = trans->restart_count;
 
@@ -1061,9 +1067,16 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 	flags &= ~BCH_WATERMARK_MASK;
 	flags |= watermark;
 
-	if (flags & BTREE_INSERT_JOURNAL_RECLAIM)
-		journal_flags |= JOURNAL_RES_GET_NONBLOCK;
-	journal_flags |= watermark;
+	if (!(flags & BCH_TRANS_COMMIT_journal_reclaim) &&
+	    watermark < c->journal.watermark) {
+		struct journal_res res = { 0 };
+
+		ret = drop_locks_do(trans,
+			bch2_journal_res_get(&c->journal, &res, 1,
+					     watermark|JOURNAL_RES_GET_CHECK));
+		if (ret)
+			return ERR_PTR(ret);
+	}
 
 	while (1) {
 		nr_nodes[!!update_level] += 1 + split;
@@ -1080,16 +1093,18 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 			break;
 		}
 
+		/*
+		 * Always check for space for two keys, even if we won't have to
+		 * split at prior level - it might have been a merge instead:
+		 */
 		if (bch2_btree_node_insert_fits(c, path->l[update_level].b,
-					BKEY_BTREE_PTR_U64s_MAX * (1 + split)))
+						BKEY_BTREE_PTR_U64s_MAX * 2))
 			break;
 
 		split = path->l[update_level].b->nr.live_u64s > BTREE_SPLIT_THRESHOLD(c);
 	}
 
-	if (flags & BTREE_INSERT_GC_LOCK_HELD)
-		lockdep_assert_held(&c->gc_lock);
-	else if (!down_read_trylock(&c->gc_lock)) {
+	if (!down_read_trylock(&c->gc_lock)) {
 		ret = drop_locks_do(trans, (down_read(&c->gc_lock), 0));
 		if (ret) {
 			up_read(&c->gc_lock);
@@ -1103,7 +1118,7 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 	as->c		= c;
 	as->start_time	= start_time;
 	as->mode	= BTREE_INTERIOR_NO_UPDATE;
-	as->took_gc_lock = !(flags & BTREE_INSERT_GC_LOCK_HELD);
+	as->took_gc_lock = true;
 	as->btree_id	= path->btree_id;
 	as->update_level = update_level;
 	INIT_LIST_HEAD(&as->list);
@@ -1129,27 +1144,6 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 	if (ret)
 		goto err;
 
-	ret = bch2_journal_preres_get(&c->journal, &as->journal_preres,
-				      BTREE_UPDATE_JOURNAL_RES,
-				      journal_flags|JOURNAL_RES_GET_NONBLOCK);
-	if (ret) {
-		if (flags & BTREE_INSERT_JOURNAL_RECLAIM) {
-			ret = -BCH_ERR_journal_reclaim_would_deadlock;
-			goto err;
-		}
-
-		ret = drop_locks_do(trans,
-			bch2_journal_preres_get(&c->journal, &as->journal_preres,
-					      BTREE_UPDATE_JOURNAL_RES,
-					      journal_flags));
-		if (ret == -BCH_ERR_journal_preres_get_blocked) {
-			trace_and_count(c, trans_restart_journal_preres_get, trans, _RET_IP_, journal_flags);
-			ret = btree_trans_restart(trans, BCH_ERR_transaction_restart_journal_preres_get);
-		}
-		if (ret)
-			goto err;
-	}
-
 	ret = bch2_disk_reservation_get(c, &as->disk_res,
 			(nr_nodes[0] + nr_nodes[1]) * btree_sectors(c),
 			c->opts.metadata_replicas,
@@ -1167,7 +1161,7 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 		 * flag
 		 */
 		if (bch2_err_matches(ret, ENOSPC) &&
-		    (flags & BTREE_INSERT_JOURNAL_RECLAIM) &&
+		    (flags & BCH_TRANS_COMMIT_journal_reclaim) &&
 		    watermark != BCH_WATERMARK_reclaim) {
 			ret = -BCH_ERR_journal_reclaim_would_deadlock;
 			goto err;
@@ -1197,6 +1191,9 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 	return as;
 err:
 	bch2_btree_update_free(as, trans);
+	if (!bch2_err_matches(ret, ENOSPC) &&
+	    !bch2_err_matches(ret, EROFS))
+		bch_err_fn_ratelimited(c, ret);
 	return ERR_PTR(ret);
 }
 
@@ -1228,7 +1225,7 @@ static void bch2_btree_set_root(struct btree_update *as,
 	struct bch_fs *c = as->c;
 	struct btree *old;
 
-	trace_and_count(c, btree_node_set_root, c, b);
+	trace_and_count(c, btree_node_set_root, trans, b);
 
 	old = btree_node_root(c, b);
 
@@ -1360,8 +1357,11 @@ static void __btree_split_node(struct btree_update *as,
 	struct bkey_packed *out[2];
 	struct bkey uk;
 	unsigned u64s, n1_u64s = (b->nr.live_u64s * 3) / 5;
+	struct { unsigned nr_keys, val_u64s; } nr_keys[2];
 	int i;
 
+	memset(&nr_keys, 0, sizeof(nr_keys));
+
 	for (i = 0; i < 2; i++) {
 		BUG_ON(n[i]->nsets != 1);
 
@@ -1383,6 +1383,9 @@ static void __btree_split_node(struct btree_update *as,
 		if (!i)
 			n1_pos = uk.p;
 		bch2_bkey_format_add_key(&format[i], &uk);
+
+		nr_keys[i].nr_keys++;
+		nr_keys[i].val_u64s += bkeyp_val_u64s(&b->format, k);
 	}
 
 	btree_set_min(n[0], b->data->min_key);
@@ -1395,6 +1398,12 @@ static void __btree_split_node(struct btree_update *as,
 		bch2_bkey_format_add_pos(&format[i], n[i]->data->max_key);
 
 		n[i]->data->format = bch2_bkey_format_done(&format[i]);
+
+		unsigned u64s = nr_keys[i].nr_keys * n[i]->data->format.key_u64s +
+			nr_keys[i].val_u64s;
+		if (__vstruct_bytes(struct btree_node, u64s) > btree_bytes(as->c))
+			n[i]->data->format = b->format;
+
 		btree_node_set_format(n[i], n[i]->data->format);
 	}
 
@@ -1447,10 +1456,12 @@ static void __btree_split_node(struct btree_update *as,
  */
 static void btree_split_insert_keys(struct btree_update *as,
 				    struct btree_trans *trans,
-				    struct btree_path *path,
+				    btree_path_idx_t path_idx,
 				    struct btree *b,
 				    struct keylist *keys)
 {
+	struct btree_path *path = trans->paths + path_idx;
+
 	if (!bch2_keylist_empty(keys) &&
 	    bpos_le(bch2_keylist_front(keys)->k.p, b->data->max_key)) {
 		struct btree_node_iter node_iter;
@@ -1464,25 +1475,25 @@ static void btree_split_insert_keys(struct btree_update *as,
 }
 
 static int btree_split(struct btree_update *as, struct btree_trans *trans,
-		       struct btree_path *path, struct btree *b,
+		       btree_path_idx_t path, struct btree *b,
 		       struct keylist *keys, unsigned flags)
 {
 	struct bch_fs *c = as->c;
-	struct btree *parent = btree_node_parent(path, b);
+	struct btree *parent = btree_node_parent(trans->paths + path, b);
 	struct btree *n1, *n2 = NULL, *n3 = NULL;
-	struct btree_path *path1 = NULL, *path2 = NULL;
+	btree_path_idx_t path1 = 0, path2 = 0;
 	u64 start_time = local_clock();
 	int ret = 0;
 
 	BUG_ON(!parent && (b != btree_node_root(c, b)));
-	BUG_ON(parent && !btree_node_intent_locked(path, b->c.level + 1));
+	BUG_ON(parent && !btree_node_intent_locked(trans->paths + path, b->c.level + 1));
 
 	bch2_btree_interior_update_will_free_node(as, b);
 
 	if (b->nr.live_u64s > BTREE_SPLIT_THRESHOLD(c)) {
 		struct btree *n[2];
 
-		trace_and_count(c, btree_node_split, c, b);
+		trace_and_count(c, btree_node_split, trans, b);
 
 		n[0] = n1 = bch2_btree_node_alloc(as, trans, b->c.level);
 		n[1] = n2 = bch2_btree_node_alloc(as, trans, b->c.level);
@@ -1503,15 +1514,15 @@ static int btree_split(struct btree_update *as, struct btree_trans *trans,
 		six_unlock_write(&n2->c.lock);
 		six_unlock_write(&n1->c.lock);
 
-		path1 = get_unlocked_mut_path(trans, path->btree_id, n1->c.level, n1->key.k.p);
+		path1 = get_unlocked_mut_path(trans, as->btree_id, n1->c.level, n1->key.k.p);
 		six_lock_increment(&n1->c.lock, SIX_LOCK_intent);
-		mark_btree_node_locked(trans, path1, n1->c.level, BTREE_NODE_INTENT_LOCKED);
-		bch2_btree_path_level_init(trans, path1, n1);
+		mark_btree_node_locked(trans, trans->paths + path1, n1->c.level, BTREE_NODE_INTENT_LOCKED);
+		bch2_btree_path_level_init(trans, trans->paths + path1, n1);
 
-		path2 = get_unlocked_mut_path(trans, path->btree_id, n2->c.level, n2->key.k.p);
+		path2 = get_unlocked_mut_path(trans, as->btree_id, n2->c.level, n2->key.k.p);
 		six_lock_increment(&n2->c.lock, SIX_LOCK_intent);
-		mark_btree_node_locked(trans, path2, n2->c.level, BTREE_NODE_INTENT_LOCKED);
-		bch2_btree_path_level_init(trans, path2, n2);
+		mark_btree_node_locked(trans, trans->paths + path2, n2->c.level, BTREE_NODE_INTENT_LOCKED);
+		bch2_btree_path_level_init(trans, trans->paths + path2, n2);
 
 		/*
 		 * Note that on recursive parent_keys == keys, so we
@@ -1528,11 +1539,11 @@ static int btree_split(struct btree_update *as, struct btree_trans *trans,
 			bch2_btree_update_add_new_node(as, n3);
 			six_unlock_write(&n3->c.lock);
 
-			path2->locks_want++;
-			BUG_ON(btree_node_locked(path2, n3->c.level));
+			trans->paths[path2].locks_want++;
+			BUG_ON(btree_node_locked(trans->paths + path2, n3->c.level));
 			six_lock_increment(&n3->c.lock, SIX_LOCK_intent);
-			mark_btree_node_locked(trans, path2, n3->c.level, BTREE_NODE_INTENT_LOCKED);
-			bch2_btree_path_level_init(trans, path2, n3);
+			mark_btree_node_locked(trans, trans->paths + path2, n3->c.level, BTREE_NODE_INTENT_LOCKED);
+			bch2_btree_path_level_init(trans, trans->paths + path2, n3);
 
 			n3->sib_u64s[0] = U16_MAX;
 			n3->sib_u64s[1] = U16_MAX;
@@ -1540,7 +1551,7 @@ static int btree_split(struct btree_update *as, struct btree_trans *trans,
 			btree_split_insert_keys(as, trans, path, n3, &as->parent_keys);
 		}
 	} else {
-		trace_and_count(c, btree_node_compact, c, b);
+		trace_and_count(c, btree_node_compact, trans, b);
 
 		n1 = bch2_btree_node_alloc_replacement(as, trans, b);
 
@@ -1553,10 +1564,10 @@ static int btree_split(struct btree_update *as, struct btree_trans *trans,
 		bch2_btree_update_add_new_node(as, n1);
 		six_unlock_write(&n1->c.lock);
 
-		path1 = get_unlocked_mut_path(trans, path->btree_id, n1->c.level, n1->key.k.p);
+		path1 = get_unlocked_mut_path(trans, as->btree_id, n1->c.level, n1->key.k.p);
 		six_lock_increment(&n1->c.lock, SIX_LOCK_intent);
-		mark_btree_node_locked(trans, path1, n1->c.level, BTREE_NODE_INTENT_LOCKED);
-		bch2_btree_path_level_init(trans, path1, n1);
+		mark_btree_node_locked(trans, trans->paths + path1, n1->c.level, BTREE_NODE_INTENT_LOCKED);
+		bch2_btree_path_level_init(trans, trans->paths + path1, n1);
 
 		if (parent)
 			bch2_keylist_add(&as->parent_keys, &n1->key);
@@ -1570,10 +1581,10 @@ static int btree_split(struct btree_update *as, struct btree_trans *trans,
 		if (ret)
 			goto err;
 	} else if (n3) {
-		bch2_btree_set_root(as, trans, path, n3);
+		bch2_btree_set_root(as, trans, trans->paths + path, n3);
 	} else {
 		/* Root filled up but didn't need to be split */
-		bch2_btree_set_root(as, trans, path, n1);
+		bch2_btree_set_root(as, trans, trans->paths + path, n1);
 	}
 
 	if (n3) {
@@ -1593,13 +1604,13 @@ static int btree_split(struct btree_update *as, struct btree_trans *trans,
 	 * node after another thread has locked and updated the new node, thus
 	 * seeing stale data:
 	 */
-	bch2_btree_node_free_inmem(trans, path, b);
+	bch2_btree_node_free_inmem(trans, trans->paths + path, b);
 
 	if (n3)
-		bch2_trans_node_add(trans, n3);
+		bch2_trans_node_add(trans, trans->paths + path, n3);
 	if (n2)
-		bch2_trans_node_add(trans, n2);
-	bch2_trans_node_add(trans, n1);
+		bch2_trans_node_add(trans, trans->paths + path2, n2);
+	bch2_trans_node_add(trans, trans->paths + path1, n1);
 
 	if (n3)
 		six_unlock_intent(&n3->c.lock);
@@ -1608,11 +1619,11 @@ static int btree_split(struct btree_update *as, struct btree_trans *trans,
 	six_unlock_intent(&n1->c.lock);
 out:
 	if (path2) {
-		__bch2_btree_path_unlock(trans, path2);
+		__bch2_btree_path_unlock(trans, trans->paths + path2);
 		bch2_path_put(trans, path2, true);
 	}
 	if (path1) {
-		__bch2_btree_path_unlock(trans, path1);
+		__bch2_btree_path_unlock(trans, trans->paths + path1);
 		bch2_path_put(trans, path1, true);
 	}
 
@@ -1640,13 +1651,14 @@ bch2_btree_insert_keys_interior(struct btree_update *as,
 				struct keylist *keys)
 {
 	struct btree_path *linked;
+	unsigned i;
 
 	__bch2_btree_insert_keys_interior(as, trans, path, b,
 					  path->l[b->c.level].iter, keys);
 
 	btree_update_updated_node(as, b);
 
-	trans_for_each_path_with_node(trans, b, linked)
+	trans_for_each_path_with_node(trans, b, linked, i)
 		bch2_btree_node_iter_peek(&linked->l[b->c.level].iter, b);
 
 	bch2_trans_verify_paths(trans);
@@ -1657,7 +1669,7 @@ bch2_btree_insert_keys_interior(struct btree_update *as,
  *
  * @as:			btree_update object
  * @trans:		btree_trans object
- * @path:		path that points to current node
+ * @path_idx:		path that points to current node
  * @b:			node to insert keys into
  * @keys:		list of keys to insert
  * @flags:		transaction commit flags
@@ -1669,10 +1681,11 @@ bch2_btree_insert_keys_interior(struct btree_update *as,
  * for leaf nodes -- inserts into interior nodes have to be atomic.
  */
 static int bch2_btree_insert_node(struct btree_update *as, struct btree_trans *trans,
-				  struct btree_path *path, struct btree *b,
+				  btree_path_idx_t path_idx, struct btree *b,
 				  struct keylist *keys, unsigned flags)
 {
 	struct bch_fs *c = as->c;
+	struct btree_path *path = trans->paths + path_idx;
 	int old_u64s = le16_to_cpu(btree_bset_last(b)->u64s);
 	int old_live_u64s = b->nr.live_u64s;
 	int live_u64s_added, u64s_added;
@@ -1725,19 +1738,22 @@ split:
 		return btree_trans_restart(trans, BCH_ERR_transaction_restart_split_race);
 	}
 
-	return btree_split(as, trans, path, b, keys, flags);
+	return btree_split(as, trans, path_idx, b, keys, flags);
 }
 
 int bch2_btree_split_leaf(struct btree_trans *trans,
-			  struct btree_path *path,
+			  btree_path_idx_t path,
 			  unsigned flags)
 {
-	struct btree *b = path_l(path)->b;
+	/* btree_split & merge may both cause paths array to be reallocated */
+
+	struct btree *b = path_l(trans->paths + path)->b;
 	struct btree_update *as;
 	unsigned l;
 	int ret = 0;
 
-	as = bch2_btree_update_start(trans, path, path->level,
+	as = bch2_btree_update_start(trans, trans->paths + path,
+				     trans->paths[path].level,
 				     true, flags);
 	if (IS_ERR(as))
 		return PTR_ERR(as);
@@ -1750,20 +1766,21 @@ int bch2_btree_split_leaf(struct btree_trans *trans,
 
 	bch2_btree_update_done(as, trans);
 
-	for (l = path->level + 1; btree_node_intent_locked(path, l) && !ret; l++)
+	for (l = trans->paths[path].level + 1;
+	     btree_node_intent_locked(&trans->paths[path], l) && !ret;
+	     l++)
 		ret = bch2_foreground_maybe_merge(trans, path, l, flags);
 
 	return ret;
 }
 
 int __bch2_foreground_maybe_merge(struct btree_trans *trans,
-				  struct btree_path *path,
+				  btree_path_idx_t path,
 				  unsigned level,
 				  unsigned flags,
 				  enum btree_node_sibling sib)
 {
 	struct bch_fs *c = trans->c;
-	struct btree_path *sib_path = NULL, *new_path = NULL;
 	struct btree_update *as;
 	struct bkey_format_state new_s;
 	struct bkey_format new_f;
@@ -1771,13 +1788,15 @@ int __bch2_foreground_maybe_merge(struct btree_trans *trans,
 	struct btree *b, *m, *n, *prev, *next, *parent;
 	struct bpos sib_pos;
 	size_t sib_u64s;
+	enum btree_id btree = trans->paths[path].btree_id;
+	btree_path_idx_t sib_path = 0, new_path = 0;
 	u64 start_time = local_clock();
 	int ret = 0;
 
-	BUG_ON(!path->should_be_locked);
-	BUG_ON(!btree_node_locked(path, level));
+	BUG_ON(!trans->paths[path].should_be_locked);
+	BUG_ON(!btree_node_locked(&trans->paths[path], level));
 
-	b = path->l[level].b;
+	b = trans->paths[path].l[level].b;
 
 	if ((sib == btree_prev_sib && bpos_eq(b->data->min_key, POS_MIN)) ||
 	    (sib == btree_next_sib && bpos_eq(b->data->max_key, SPOS_MAX))) {
@@ -1789,18 +1808,18 @@ int __bch2_foreground_maybe_merge(struct btree_trans *trans,
 		? bpos_predecessor(b->data->min_key)
 		: bpos_successor(b->data->max_key);
 
-	sib_path = bch2_path_get(trans, path->btree_id, sib_pos,
+	sib_path = bch2_path_get(trans, btree, sib_pos,
 				 U8_MAX, level, BTREE_ITER_INTENT, _THIS_IP_);
 	ret = bch2_btree_path_traverse(trans, sib_path, false);
 	if (ret)
 		goto err;
 
-	btree_path_set_should_be_locked(sib_path);
+	btree_path_set_should_be_locked(trans->paths + sib_path);
 
-	m = sib_path->l[level].b;
+	m = trans->paths[sib_path].l[level].b;
 
-	if (btree_node_parent(path, b) !=
-	    btree_node_parent(sib_path, m)) {
+	if (btree_node_parent(trans->paths + path, b) !=
+	    btree_node_parent(trans->paths + sib_path, m)) {
 		b->sib_u64s[sib] = U16_MAX;
 		goto out;
 	}
@@ -1837,8 +1856,8 @@ int __bch2_foreground_maybe_merge(struct btree_trans *trans,
 	bch2_bkey_format_add_pos(&new_s, next->data->max_key);
 	new_f = bch2_bkey_format_done(&new_s);
 
-	sib_u64s = btree_node_u64s_with_format(b, &new_f) +
-		btree_node_u64s_with_format(m, &new_f);
+	sib_u64s = btree_node_u64s_with_format(b->nr, &b->format, &new_f) +
+		btree_node_u64s_with_format(m->nr, &m->format, &new_f);
 
 	if (sib_u64s > BTREE_FOREGROUND_MERGE_HYSTERESIS(c)) {
 		sib_u64s -= BTREE_FOREGROUND_MERGE_HYSTERESIS(c);
@@ -1853,14 +1872,14 @@ int __bch2_foreground_maybe_merge(struct btree_trans *trans,
 	if (b->sib_u64s[sib] > c->btree_foreground_merge_threshold)
 		goto out;
 
-	parent = btree_node_parent(path, b);
-	as = bch2_btree_update_start(trans, path, level, false,
-				     BTREE_INSERT_NOFAIL|flags);
+	parent = btree_node_parent(trans->paths + path, b);
+	as = bch2_btree_update_start(trans, trans->paths + path, level, false,
+				     BCH_TRANS_COMMIT_no_enospc|flags);
 	ret = PTR_ERR_OR_ZERO(as);
 	if (ret)
 		goto err;
 
-	trace_and_count(c, btree_node_merge, c, b);
+	trace_and_count(c, btree_node_merge, trans, b);
 
 	bch2_btree_interior_update_will_free_node(as, b);
 	bch2_btree_interior_update_will_free_node(as, m);
@@ -1884,10 +1903,10 @@ int __bch2_foreground_maybe_merge(struct btree_trans *trans,
 	bch2_btree_update_add_new_node(as, n);
 	six_unlock_write(&n->c.lock);
 
-	new_path = get_unlocked_mut_path(trans, path->btree_id, n->c.level, n->key.k.p);
+	new_path = get_unlocked_mut_path(trans, btree, n->c.level, n->key.k.p);
 	six_lock_increment(&n->c.lock, SIX_LOCK_intent);
-	mark_btree_node_locked(trans, new_path, n->c.level, BTREE_NODE_INTENT_LOCKED);
-	bch2_btree_path_level_init(trans, new_path, n);
+	mark_btree_node_locked(trans, trans->paths + new_path, n->c.level, BTREE_NODE_INTENT_LOCKED);
+	bch2_btree_path_level_init(trans, trans->paths + new_path, n);
 
 	bkey_init(&delete.k);
 	delete.k.p = prev->key.k.p;
@@ -1905,10 +1924,10 @@ int __bch2_foreground_maybe_merge(struct btree_trans *trans,
 	bch2_btree_update_get_open_buckets(as, n);
 	bch2_btree_node_write(c, n, SIX_LOCK_intent, 0);
 
-	bch2_btree_node_free_inmem(trans, path, b);
-	bch2_btree_node_free_inmem(trans, sib_path, m);
+	bch2_btree_node_free_inmem(trans, trans->paths + path, b);
+	bch2_btree_node_free_inmem(trans, trans->paths + sib_path, m);
 
-	bch2_trans_node_add(trans, n);
+	bch2_trans_node_add(trans, trans->paths + path, n);
 
 	bch2_trans_verify_paths(trans);
 
@@ -1936,16 +1955,16 @@ int bch2_btree_node_rewrite(struct btree_trans *trans,
 			    unsigned flags)
 {
 	struct bch_fs *c = trans->c;
-	struct btree_path *new_path = NULL;
 	struct btree *n, *parent;
 	struct btree_update *as;
+	btree_path_idx_t new_path = 0;
 	int ret;
 
-	flags |= BTREE_INSERT_NOFAIL;
+	flags |= BCH_TRANS_COMMIT_no_enospc;
 
-	parent = btree_node_parent(iter->path, b);
-	as = bch2_btree_update_start(trans, iter->path, b->c.level,
-				     false, flags);
+	struct btree_path *path = btree_iter_path(trans, iter);
+	parent = btree_node_parent(path, b);
+	as = bch2_btree_update_start(trans, path, b->c.level, false, flags);
 	ret = PTR_ERR_OR_ZERO(as);
 	if (ret)
 		goto out;
@@ -1960,27 +1979,27 @@ int bch2_btree_node_rewrite(struct btree_trans *trans,
 
 	new_path = get_unlocked_mut_path(trans, iter->btree_id, n->c.level, n->key.k.p);
 	six_lock_increment(&n->c.lock, SIX_LOCK_intent);
-	mark_btree_node_locked(trans, new_path, n->c.level, BTREE_NODE_INTENT_LOCKED);
-	bch2_btree_path_level_init(trans, new_path, n);
+	mark_btree_node_locked(trans, trans->paths + new_path, n->c.level, BTREE_NODE_INTENT_LOCKED);
+	bch2_btree_path_level_init(trans, trans->paths + new_path, n);
 
-	trace_and_count(c, btree_node_rewrite, c, b);
+	trace_and_count(c, btree_node_rewrite, trans, b);
 
 	if (parent) {
 		bch2_keylist_add(&as->parent_keys, &n->key);
-		ret = bch2_btree_insert_node(as, trans, iter->path, parent,
-					     &as->parent_keys, flags);
+		ret = bch2_btree_insert_node(as, trans, iter->path,
+					     parent, &as->parent_keys, flags);
 		if (ret)
 			goto err;
 	} else {
-		bch2_btree_set_root(as, trans, iter->path, n);
+		bch2_btree_set_root(as, trans, btree_iter_path(trans, iter), n);
 	}
 
 	bch2_btree_update_get_open_buckets(as, n);
 	bch2_btree_node_write(c, n, SIX_LOCK_intent, 0);
 
-	bch2_btree_node_free_inmem(trans, iter->path, b);
+	bch2_btree_node_free_inmem(trans, btree_iter_path(trans, iter), b);
 
-	bch2_trans_node_add(trans, n);
+	bch2_trans_node_add(trans, trans->paths + iter->path, n);
 	six_unlock_intent(&n->c.lock);
 
 	bch2_btree_update_done(as, trans);
@@ -2049,8 +2068,7 @@ static void async_btree_node_rewrite_work(struct work_struct *work)
 
 	ret = bch2_trans_do(c, NULL, NULL, 0,
 		      async_btree_node_rewrite_trans(trans, a));
-	if (ret)
-		bch_err_fn(c, ret);
+	bch_err_fn(c, ret);
 	bch2_write_ref_put(c, BCH_WRITE_REF_node_rewrite);
 	kfree(a);
 }
@@ -2073,7 +2091,7 @@ void bch2_btree_node_rewrite_async(struct bch_fs *c, struct btree *b)
 	a->seq		= b->data->keys.seq;
 	INIT_WORK(&a->work, async_btree_node_rewrite_work);
 
-	if (unlikely(!test_bit(BCH_FS_MAY_GO_RW, &c->flags))) {
+	if (unlikely(!test_bit(BCH_FS_may_go_rw, &c->flags))) {
 		mutex_lock(&c->pending_node_rewrites_lock);
 		list_add(&a->list, &c->pending_node_rewrites);
 		mutex_unlock(&c->pending_node_rewrites_lock);
@@ -2081,15 +2099,15 @@ void bch2_btree_node_rewrite_async(struct bch_fs *c, struct btree *b)
 	}
 
 	if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_node_rewrite)) {
-		if (test_bit(BCH_FS_STARTED, &c->flags)) {
+		if (test_bit(BCH_FS_started, &c->flags)) {
 			bch_err(c, "%s: error getting c->writes ref", __func__);
 			kfree(a);
 			return;
 		}
 
 		ret = bch2_fs_read_write_early(c);
+		bch_err_msg(c, ret, "going read-write");
 		if (ret) {
-			bch_err_msg(c, ret, "going read-write");
 			kfree(a);
 			return;
 		}
@@ -2140,13 +2158,12 @@ static int __bch2_btree_node_update_key(struct btree_trans *trans,
 	int ret;
 
 	if (!skip_triggers) {
-		ret = bch2_trans_mark_old(trans, b->c.btree_id, b->c.level + 1,
-					  bkey_i_to_s_c(&b->key), 0);
-		if (ret)
-			return ret;
-
-		ret = bch2_trans_mark_new(trans, b->c.btree_id, b->c.level + 1,
-					  new_key, 0);
+		ret   = bch2_key_trigger_old(trans, b->c.btree_id, b->c.level + 1,
+					     bkey_i_to_s_c(&b->key),
+					     BTREE_TRIGGER_TRANSACTIONAL) ?:
+			bch2_key_trigger_new(trans, b->c.btree_id, b->c.level + 1,
+					     bkey_i_to_s(new_key),
+					     BTREE_TRIGGER_TRANSACTIONAL);
 		if (ret)
 			return ret;
 	}
@@ -2158,7 +2175,7 @@ static int __bch2_btree_node_update_key(struct btree_trans *trans,
 		BUG_ON(ret);
 	}
 
-	parent = btree_node_parent(iter->path, b);
+	parent = btree_node_parent(btree_iter_path(trans, iter), b);
 	if (parent) {
 		bch2_trans_copy_iter(&iter2, iter);
 
@@ -2166,10 +2183,11 @@ static int __bch2_btree_node_update_key(struct btree_trans *trans,
 				iter2.flags & BTREE_ITER_INTENT,
 				_THIS_IP_);
 
-		BUG_ON(iter2.path->level != b->c.level);
-		BUG_ON(!bpos_eq(iter2.path->pos, new_key->k.p));
+		struct btree_path *path2 = btree_iter_path(trans, &iter2);
+		BUG_ON(path2->level != b->c.level);
+		BUG_ON(!bpos_eq(path2->pos, new_key->k.p));
 
-		btree_path_set_level_up(trans, iter2.path);
+		btree_path_set_level_up(trans, path2);
 
 		trans->paths_sorted = false;
 
@@ -2180,23 +2198,23 @@ static int __bch2_btree_node_update_key(struct btree_trans *trans,
 	} else {
 		BUG_ON(btree_node_root(c, b) != b);
 
-		ret = darray_make_room(&trans->extra_journal_entries,
+		struct jset_entry *e = bch2_trans_jset_entry_alloc(trans,
 				       jset_u64s(new_key->k.u64s));
+		ret = PTR_ERR_OR_ZERO(e);
 		if (ret)
 			return ret;
 
-		journal_entry_set((void *) &darray_top(trans->extra_journal_entries),
+		journal_entry_set(e,
 				  BCH_JSET_ENTRY_btree_root,
 				  b->c.btree_id, b->c.level,
 				  new_key, new_key->k.u64s);
-		trans->extra_journal_entries.nr += jset_u64s(new_key->k.u64s);
 	}
 
 	ret = bch2_trans_commit(trans, NULL, NULL, commit_flags);
 	if (ret)
 		goto err;
 
-	bch2_btree_node_lock_write_nofail(trans, iter->path, &b->c);
+	bch2_btree_node_lock_write_nofail(trans, btree_iter_path(trans, iter), &b->c);
 
 	if (new_hash) {
 		mutex_lock(&c->btree_cache.lock);
@@ -2211,7 +2229,7 @@ static int __bch2_btree_node_update_key(struct btree_trans *trans,
 		bkey_copy(&b->key, new_key);
 	}
 
-	bch2_btree_node_unlock_write(trans, iter->path, b);
+	bch2_btree_node_unlock_write(trans, btree_iter_path(trans, iter), b);
 out:
 	bch2_trans_iter_exit(trans, &iter2);
 	return ret;
@@ -2230,7 +2248,7 @@ int bch2_btree_node_update_key(struct btree_trans *trans, struct btree_iter *ite
 {
 	struct bch_fs *c = trans->c;
 	struct btree *new_hash = NULL;
-	struct btree_path *path = iter->path;
+	struct btree_path *path = btree_iter_path(trans, iter);
 	struct closure cl;
 	int ret = 0;
 
@@ -2245,7 +2263,7 @@ int bch2_btree_node_update_key(struct btree_trans *trans, struct btree_iter *ite
 	 * btree_iter_traverse():
 	 */
 	if (btree_ptr_hash_val(new_key) != b->hash_val) {
-		ret = bch2_btree_cache_cannibalize_lock(c, &cl);
+		ret = bch2_btree_cache_cannibalize_lock(trans, &cl);
 		if (ret) {
 			ret = drop_locks_do(trans, (closure_sync(&cl), 0));
 			if (ret)
@@ -2269,7 +2287,7 @@ int bch2_btree_node_update_key(struct btree_trans *trans, struct btree_iter *ite
 		six_unlock_intent(&new_hash->c.lock);
 	}
 	closure_sync(&cl);
-	bch2_btree_cache_cannibalize_unlock(c);
+	bch2_btree_cache_cannibalize_unlock(trans);
 	return ret;
 }
 
@@ -2288,7 +2306,7 @@ int bch2_btree_node_update_key_get_iter(struct btree_trans *trans,
 		goto out;
 
 	/* has node been freed? */
-	if (iter.path->l[b->c.level].b != b) {
+	if (btree_iter_path(trans, &iter)->l[b->c.level].b != b) {
 		/* node has been freed: */
 		BUG_ON(!btree_node_dying(b));
 		goto out;
@@ -2296,6 +2314,10 @@ int bch2_btree_node_update_key_get_iter(struct btree_trans *trans,
 
 	BUG_ON(!btree_node_hashed(b));
 
+	struct bch_extent_ptr *ptr;
+	bch2_bkey_drop_ptrs(bkey_i_to_s(new_key), ptr,
+			    !bch2_bkey_has_device(bkey_i_to_s(&b->key), ptr->dev));
+
 	ret = bch2_btree_node_update_key(trans, &iter, b, new_key,
 					 commit_flags, skip_triggers);
 out:
@@ -2326,12 +2348,12 @@ static int __bch2_btree_root_alloc(struct btree_trans *trans, enum btree_id id)
 	closure_init_stack(&cl);
 
 	do {
-		ret = bch2_btree_cache_cannibalize_lock(c, &cl);
+		ret = bch2_btree_cache_cannibalize_lock(trans, &cl);
 		closure_sync(&cl);
 	} while (ret);
 
 	b = bch2_btree_node_mem_alloc(trans, false);
-	bch2_btree_cache_cannibalize_unlock(c);
+	bch2_btree_cache_cannibalize_unlock(trans);
 
 	set_btree_node_fake(b);
 	set_btree_node_need_rewrite(b);
diff --git a/fs/bcachefs/btree_update_interior.h b/fs/bcachefs/btree_update_interior.h
index 4df21512d640..adfc62083844 100644
--- a/fs/bcachefs/btree_update_interior.h
+++ b/fs/bcachefs/btree_update_interior.h
@@ -6,10 +6,6 @@
 #include "btree_locking.h"
 #include "btree_update.h"
 
-void __bch2_btree_calc_format(struct bkey_format_state *, struct btree *);
-bool bch2_btree_node_format_fits(struct bch_fs *c, struct btree *,
-				struct bkey_format *);
-
 #define BTREE_UPDATE_NODES_MAX		((BTREE_MAX_DEPTH - 2) * 2 + GC_MERGE_NODES)
 
 #define BTREE_UPDATE_JOURNAL_RES	(BTREE_UPDATE_NODES_MAX * (BKEY_BTREE_PTR_U64s_MAX + 1))
@@ -55,7 +51,6 @@ struct btree_update {
 	unsigned			update_level;
 
 	struct disk_reservation		disk_res;
-	struct journal_preres		journal_preres;
 
 	/*
 	 * BTREE_INTERIOR_UPDATING_NODE:
@@ -122,16 +117,17 @@ struct btree *__bch2_btree_node_alloc_replacement(struct btree_update *,
 						  struct btree *,
 						  struct bkey_format);
 
-int bch2_btree_split_leaf(struct btree_trans *, struct btree_path *, unsigned);
+int bch2_btree_split_leaf(struct btree_trans *, btree_path_idx_t, unsigned);
 
-int __bch2_foreground_maybe_merge(struct btree_trans *, struct btree_path *,
+int __bch2_foreground_maybe_merge(struct btree_trans *, btree_path_idx_t,
 				  unsigned, unsigned, enum btree_node_sibling);
 
 static inline int bch2_foreground_maybe_merge_sibling(struct btree_trans *trans,
-					struct btree_path *path,
+					btree_path_idx_t path_idx,
 					unsigned level, unsigned flags,
 					enum btree_node_sibling sib)
 {
+	struct btree_path *path = trans->paths + path_idx;
 	struct btree *b;
 
 	EBUG_ON(!btree_node_locked(path, level));
@@ -140,11 +136,11 @@ static inline int bch2_foreground_maybe_merge_sibling(struct btree_trans *trans,
 	if (b->sib_u64s[sib] > trans->c->btree_foreground_merge_threshold)
 		return 0;
 
-	return __bch2_foreground_maybe_merge(trans, path, level, flags, sib);
+	return __bch2_foreground_maybe_merge(trans, path_idx, level, flags, sib);
 }
 
 static inline int bch2_foreground_maybe_merge(struct btree_trans *trans,
-					      struct btree_path *path,
+					      btree_path_idx_t path,
 					      unsigned level,
 					      unsigned flags)
 {
diff --git a/fs/bcachefs/btree_write_buffer.c b/fs/bcachefs/btree_write_buffer.c
index 4e6241db518b..5c1169c78daf 100644
--- a/fs/bcachefs/btree_write_buffer.c
+++ b/fs/bcachefs/btree_write_buffer.c
@@ -7,45 +7,144 @@
 #include "btree_write_buffer.h"
 #include "error.h"
 #include "journal.h"
+#include "journal_io.h"
 #include "journal_reclaim.h"
 
-#include <linux/sort.h>
+#include <linux/prefetch.h>
 
-static int btree_write_buffered_key_cmp(const void *_l, const void *_r)
+static int bch2_btree_write_buffer_journal_flush(struct journal *,
+				struct journal_entry_pin *, u64);
+
+static int bch2_journal_keys_to_write_buffer(struct bch_fs *, struct journal_buf *);
+
+static inline bool __wb_key_ref_cmp(const struct wb_key_ref *l, const struct wb_key_ref *r)
+{
+	return (cmp_int(l->hi, r->hi) ?:
+		cmp_int(l->mi, r->mi) ?:
+		cmp_int(l->lo, r->lo)) >= 0;
+}
+
+static inline bool wb_key_ref_cmp(const struct wb_key_ref *l, const struct wb_key_ref *r)
+{
+#ifdef CONFIG_X86_64
+	int cmp;
+
+	asm("mov   (%[l]), %%rax;"
+	    "sub   (%[r]), %%rax;"
+	    "mov  8(%[l]), %%rax;"
+	    "sbb  8(%[r]), %%rax;"
+	    "mov 16(%[l]), %%rax;"
+	    "sbb 16(%[r]), %%rax;"
+	    : "=@ccae" (cmp)
+	    : [l] "r" (l), [r] "r" (r)
+	    : "rax", "cc");
+
+	EBUG_ON(cmp != __wb_key_ref_cmp(l, r));
+	return cmp;
+#else
+	return __wb_key_ref_cmp(l, r);
+#endif
+}
+
+/* Compare excluding idx, the low 24 bits: */
+static inline bool wb_key_eq(const void *_l, const void *_r)
 {
-	const struct btree_write_buffered_key *l = _l;
-	const struct btree_write_buffered_key *r = _r;
+	const struct wb_key_ref *l = _l;
+	const struct wb_key_ref *r = _r;
 
-	return  cmp_int(l->btree, r->btree) ?:
-		bpos_cmp(l->k.k.p, r->k.k.p) ?:
-		cmp_int(l->journal_seq, r->journal_seq) ?:
-		cmp_int(l->journal_offset, r->journal_offset);
+	return !((l->hi ^ r->hi)|
+		 (l->mi ^ r->mi)|
+		 ((l->lo >> 24) ^ (r->lo >> 24)));
 }
 
-static int btree_write_buffered_journal_cmp(const void *_l, const void *_r)
+static noinline void wb_sort(struct wb_key_ref *base, size_t num)
 {
-	const struct btree_write_buffered_key *l = _l;
-	const struct btree_write_buffered_key *r = _r;
+	size_t n = num, a = num / 2;
+
+	if (!a)		/* num < 2 || size == 0 */
+		return;
+
+	for (;;) {
+		size_t b, c, d;
+
+		if (a)			/* Building heap: sift down --a */
+			--a;
+		else if (--n)		/* Sorting: Extract root to --n */
+			swap(base[0], base[n]);
+		else			/* Sort complete */
+			break;
 
-	return  cmp_int(l->journal_seq, r->journal_seq);
+		/*
+		 * Sift element at "a" down into heap.  This is the
+		 * "bottom-up" variant, which significantly reduces
+		 * calls to cmp_func(): we find the sift-down path all
+		 * the way to the leaves (one compare per level), then
+		 * backtrack to find where to insert the target element.
+		 *
+		 * Because elements tend to sift down close to the leaves,
+		 * this uses fewer compares than doing two per level
+		 * on the way down.  (A bit more than half as many on
+		 * average, 3/4 worst-case.)
+		 */
+		for (b = a; c = 2*b + 1, (d = c + 1) < n;)
+			b = wb_key_ref_cmp(base + c, base + d) ? c : d;
+		if (d == n)		/* Special case last leaf with no sibling */
+			b = c;
+
+		/* Now backtrack from "b" to the correct location for "a" */
+		while (b != a && wb_key_ref_cmp(base + a, base + b))
+			b = (b - 1) / 2;
+		c = b;			/* Where "a" belongs */
+		while (b != a) {	/* Shift it into place */
+			b = (b - 1) / 2;
+			swap(base[b], base[c]);
+		}
+	}
+}
+
+static noinline int wb_flush_one_slowpath(struct btree_trans *trans,
+					  struct btree_iter *iter,
+					  struct btree_write_buffered_key *wb)
+{
+	struct btree_path *path = btree_iter_path(trans, iter);
+
+	bch2_btree_node_unlock_write(trans, path, path->l[0].b);
+
+	trans->journal_res.seq = wb->journal_seq;
+
+	return bch2_trans_update(trans, iter, &wb->k,
+				 BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE) ?:
+		bch2_trans_commit(trans, NULL, NULL,
+				  BCH_TRANS_COMMIT_no_enospc|
+				  BCH_TRANS_COMMIT_no_check_rw|
+				  BCH_TRANS_COMMIT_no_journal_res|
+				  BCH_TRANS_COMMIT_journal_reclaim);
 }
 
-static int bch2_btree_write_buffer_flush_one(struct btree_trans *trans,
-					     struct btree_iter *iter,
-					     struct btree_write_buffered_key *wb,
-					     unsigned commit_flags,
-					     bool *write_locked,
-					     size_t *fast)
+static inline int wb_flush_one(struct btree_trans *trans, struct btree_iter *iter,
+			       struct btree_write_buffered_key *wb,
+			       bool *write_locked, size_t *fast)
 {
 	struct bch_fs *c = trans->c;
 	struct btree_path *path;
 	int ret;
 
+	EBUG_ON(!wb->journal_seq);
+	EBUG_ON(!c->btree_write_buffer.flushing.pin.seq);
+	EBUG_ON(c->btree_write_buffer.flushing.pin.seq > wb->journal_seq);
+
 	ret = bch2_btree_iter_traverse(iter);
 	if (ret)
 		return ret;
 
-	path = iter->path;
+	/*
+	 * We can't clone a path that has write locks: unshare it now, before
+	 * set_pos and traverse():
+	 */
+	if (btree_iter_path(trans, iter)->ref > 1)
+		iter->path = __bch2_btree_path_make_mut(trans, iter->path, true, _THIS_IP_);
+
+	path = btree_iter_path(trans, iter);
 
 	if (!*write_locked) {
 		ret = bch2_btree_node_lock_write(trans, path, &path->l[0].b->c);
@@ -56,52 +155,14 @@ static int bch2_btree_write_buffer_flush_one(struct btree_trans *trans,
 		*write_locked = true;
 	}
 
-	if (!bch2_btree_node_insert_fits(c, path->l[0].b, wb->k.k.u64s)) {
-		bch2_btree_node_unlock_write(trans, path, path->l[0].b);
+	if (unlikely(!bch2_btree_node_insert_fits(c, path->l[0].b, wb->k.k.u64s))) {
 		*write_locked = false;
-		goto trans_commit;
+		return wb_flush_one_slowpath(trans, iter, wb);
 	}
 
 	bch2_btree_insert_key_leaf(trans, path, &wb->k, wb->journal_seq);
 	(*fast)++;
-
-	if (path->ref > 1) {
-		/*
-		 * We can't clone a path that has write locks: if the path is
-		 * shared, unlock before set_pos(), traverse():
-		 */
-		bch2_btree_node_unlock_write(trans, path, path->l[0].b);
-		*write_locked = false;
-	}
 	return 0;
-trans_commit:
-	return  bch2_trans_update_seq(trans, wb->journal_seq, iter, &wb->k,
-				      BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE) ?:
-		bch2_trans_commit(trans, NULL, NULL,
-				  commit_flags|
-				  BTREE_INSERT_NOCHECK_RW|
-				  BTREE_INSERT_NOFAIL|
-				  BTREE_INSERT_JOURNAL_RECLAIM);
-}
-
-static union btree_write_buffer_state btree_write_buffer_switch(struct btree_write_buffer *wb)
-{
-	union btree_write_buffer_state old, new;
-	u64 v = READ_ONCE(wb->state.v);
-
-	do {
-		old.v = new.v = v;
-
-		new.nr = 0;
-		new.idx++;
-	} while ((v = atomic64_cmpxchg_acquire(&wb->state.counter, old.v, new.v)) != old.v);
-
-	while (old.idx == 0 ? wb->state.ref0 : wb->state.ref1)
-		cpu_relax();
-
-	smp_mb();
-
-	return old;
 }
 
 /*
@@ -124,41 +185,87 @@ btree_write_buffered_insert(struct btree_trans *trans,
 	bch2_trans_iter_init(trans, &iter, wb->btree, bkey_start_pos(&wb->k.k),
 			     BTREE_ITER_CACHED|BTREE_ITER_INTENT);
 
+	trans->journal_res.seq = wb->journal_seq;
+
 	ret   = bch2_btree_iter_traverse(&iter) ?:
-		bch2_trans_update_seq(trans, wb->journal_seq, &iter, &wb->k,
-				      BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE);
+		bch2_trans_update(trans, &iter, &wb->k,
+				  BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE);
 	bch2_trans_iter_exit(trans, &iter);
 	return ret;
 }
 
-int __bch2_btree_write_buffer_flush(struct btree_trans *trans, unsigned commit_flags,
-				    bool locked)
+static void move_keys_from_inc_to_flushing(struct btree_write_buffer *wb)
+{
+	struct bch_fs *c = container_of(wb, struct bch_fs, btree_write_buffer);
+	struct journal *j = &c->journal;
+
+	if (!wb->inc.keys.nr)
+		return;
+
+	bch2_journal_pin_add(j, wb->inc.keys.data[0].journal_seq, &wb->flushing.pin,
+			     bch2_btree_write_buffer_journal_flush);
+
+	darray_resize(&wb->flushing.keys, min_t(size_t, 1U << 20, wb->flushing.keys.nr + wb->inc.keys.nr));
+	darray_resize(&wb->sorted, wb->flushing.keys.size);
+
+	if (!wb->flushing.keys.nr && wb->sorted.size >= wb->inc.keys.nr) {
+		swap(wb->flushing.keys, wb->inc.keys);
+		goto out;
+	}
+
+	size_t nr = min(darray_room(wb->flushing.keys),
+			wb->sorted.size - wb->flushing.keys.nr);
+	nr = min(nr, wb->inc.keys.nr);
+
+	memcpy(&darray_top(wb->flushing.keys),
+	       wb->inc.keys.data,
+	       sizeof(wb->inc.keys.data[0]) * nr);
+
+	memmove(wb->inc.keys.data,
+		wb->inc.keys.data + nr,
+	       sizeof(wb->inc.keys.data[0]) * (wb->inc.keys.nr - nr));
+
+	wb->flushing.keys.nr	+= nr;
+	wb->inc.keys.nr		-= nr;
+out:
+	if (!wb->inc.keys.nr)
+		bch2_journal_pin_drop(j, &wb->inc.pin);
+	else
+		bch2_journal_pin_update(j, wb->inc.keys.data[0].journal_seq, &wb->inc.pin,
+					bch2_btree_write_buffer_journal_flush);
+
+	if (j->watermark) {
+		spin_lock(&j->lock);
+		bch2_journal_set_watermark(j);
+		spin_unlock(&j->lock);
+	}
+
+	BUG_ON(wb->sorted.size < wb->flushing.keys.nr);
+}
+
+static int bch2_btree_write_buffer_flush_locked(struct btree_trans *trans)
 {
 	struct bch_fs *c = trans->c;
 	struct journal *j = &c->journal;
 	struct btree_write_buffer *wb = &c->btree_write_buffer;
-	struct journal_entry_pin pin;
-	struct btree_write_buffered_key *i, *keys;
 	struct btree_iter iter = { NULL };
-	size_t nr = 0, skipped = 0, fast = 0, slowpath = 0;
+	size_t skipped = 0, fast = 0, slowpath = 0;
 	bool write_locked = false;
-	union btree_write_buffer_state s;
 	int ret = 0;
 
-	memset(&pin, 0, sizeof(pin));
-
-	if (!locked && !mutex_trylock(&wb->flush_lock))
-		return 0;
-
-	bch2_journal_pin_copy(j, &pin, &wb->journal_pin, NULL);
-	bch2_journal_pin_drop(j, &wb->journal_pin);
+	bch2_trans_unlock(trans);
+	bch2_trans_begin(trans);
 
-	s = btree_write_buffer_switch(wb);
-	keys = wb->keys[s.idx];
-	nr = s.nr;
+	mutex_lock(&wb->inc.lock);
+	move_keys_from_inc_to_flushing(wb);
+	mutex_unlock(&wb->inc.lock);
 
-	if (race_fault())
-		goto slowpath;
+	for (size_t i = 0; i < wb->flushing.keys.nr; i++) {
+		wb->sorted.data[i].idx = i;
+		wb->sorted.data[i].btree = wb->flushing.keys.data[i].btree;
+		memcpy(&wb->sorted.data[i].pos, &wb->flushing.keys.data[i].k.k.p, sizeof(struct bpos));
+	}
+	wb->sorted.nr = wb->flushing.keys.nr;
 
 	/*
 	 * We first sort so that we can detect and skip redundant updates, and
@@ -168,208 +275,373 @@ int __bch2_btree_write_buffer_flush(struct btree_trans *trans, unsigned commit_f
 	 * However, since we're not flushing in the order they appear in the
 	 * journal we won't be able to drop our journal pin until everything is
 	 * flushed - which means this could deadlock the journal if we weren't
-	 * passing BTREE_INSERT_JOURNAL_RECLAIM. This causes the update to fail
+	 * passing BCH_TRANS_COMMIT_journal_reclaim. This causes the update to fail
 	 * if it would block taking a journal reservation.
 	 *
 	 * If that happens, simply skip the key so we can optimistically insert
 	 * as many keys as possible in the fast path.
 	 */
-	sort(keys, nr, sizeof(keys[0]),
-	     btree_write_buffered_key_cmp, NULL);
+	wb_sort(wb->sorted.data, wb->sorted.nr);
+
+	darray_for_each(wb->sorted, i) {
+		struct btree_write_buffered_key *k = &wb->flushing.keys.data[i->idx];
+
+		for (struct wb_key_ref *n = i + 1; n < min(i + 4, &darray_top(wb->sorted)); n++)
+			prefetch(&wb->flushing.keys.data[n->idx]);
+
+		BUG_ON(!k->journal_seq);
+
+		if (i + 1 < &darray_top(wb->sorted) &&
+		    wb_key_eq(i, i + 1)) {
+			struct btree_write_buffered_key *n = &wb->flushing.keys.data[i[1].idx];
 
-	for (i = keys; i < keys + nr; i++) {
-		if (i + 1 < keys + nr &&
-		    i[0].btree == i[1].btree &&
-		    bpos_eq(i[0].k.k.p, i[1].k.k.p)) {
 			skipped++;
-			i->journal_seq = 0;
+			n->journal_seq = min_t(u64, n->journal_seq, k->journal_seq);
+			k->journal_seq = 0;
 			continue;
 		}
 
-		if (write_locked &&
-		    (iter.path->btree_id != i->btree ||
-		     bpos_gt(i->k.k.p, iter.path->l[0].b->key.k.p))) {
-			bch2_btree_node_unlock_write(trans, iter.path, iter.path->l[0].b);
-			write_locked = false;
+		if (write_locked) {
+			struct btree_path *path = btree_iter_path(trans, &iter);
+
+			if (path->btree_id != i->btree ||
+			    bpos_gt(k->k.k.p, path->l[0].b->key.k.p)) {
+				bch2_btree_node_unlock_write(trans, path, path->l[0].b);
+				write_locked = false;
+			}
 		}
 
-		if (!iter.path || iter.path->btree_id != i->btree) {
+		if (!iter.path || iter.btree_id != k->btree) {
 			bch2_trans_iter_exit(trans, &iter);
-			bch2_trans_iter_init(trans, &iter, i->btree, i->k.k.p,
+			bch2_trans_iter_init(trans, &iter, k->btree, k->k.k.p,
 					     BTREE_ITER_INTENT|BTREE_ITER_ALL_SNAPSHOTS);
 		}
 
-		bch2_btree_iter_set_pos(&iter, i->k.k.p);
-		iter.path->preserve = false;
+		bch2_btree_iter_set_pos(&iter, k->k.k.p);
+		btree_iter_path(trans, &iter)->preserve = false;
 
 		do {
-			ret = bch2_btree_write_buffer_flush_one(trans, &iter, i,
-						commit_flags, &write_locked, &fast);
+			if (race_fault()) {
+				ret = -BCH_ERR_journal_reclaim_would_deadlock;
+				break;
+			}
+
+			ret = wb_flush_one(trans, &iter, k, &write_locked, &fast);
 			if (!write_locked)
 				bch2_trans_begin(trans);
 		} while (bch2_err_matches(ret, BCH_ERR_transaction_restart));
 
-		if (ret == -BCH_ERR_journal_reclaim_would_deadlock) {
+		if (!ret) {
+			k->journal_seq = 0;
+		} else if (ret == -BCH_ERR_journal_reclaim_would_deadlock) {
 			slowpath++;
-			continue;
-		}
-		if (ret)
+			ret = 0;
+		} else
 			break;
-
-		i->journal_seq = 0;
 	}
 
-	if (write_locked)
-		bch2_btree_node_unlock_write(trans, iter.path, iter.path->l[0].b);
+	if (write_locked) {
+		struct btree_path *path = btree_iter_path(trans, &iter);
+		bch2_btree_node_unlock_write(trans, path, path->l[0].b);
+	}
 	bch2_trans_iter_exit(trans, &iter);
 
-	trace_write_buffer_flush(trans, nr, skipped, fast, wb->size);
-
-	if (slowpath)
-		goto slowpath;
+	if (ret)
+		goto err;
 
+	if (slowpath) {
+		/*
+		 * Flush in the order they were present in the journal, so that
+		 * we can release journal pins:
+		 * The fastpath zapped the seq of keys that were successfully flushed so
+		 * we can skip those here.
+		 */
+		trace_and_count(c, write_buffer_flush_slowpath, trans, slowpath, wb->flushing.keys.nr);
+
+		darray_for_each(wb->flushing.keys, i) {
+			if (!i->journal_seq)
+				continue;
+
+			bch2_journal_pin_update(j, i->journal_seq, &wb->flushing.pin,
+						bch2_btree_write_buffer_journal_flush);
+
+			bch2_trans_begin(trans);
+
+			ret = commit_do(trans, NULL, NULL,
+					BCH_WATERMARK_reclaim|
+					BCH_TRANS_COMMIT_no_check_rw|
+					BCH_TRANS_COMMIT_no_enospc|
+					BCH_TRANS_COMMIT_no_journal_res|
+					BCH_TRANS_COMMIT_journal_reclaim,
+					btree_write_buffered_insert(trans, i));
+			if (ret)
+				goto err;
+		}
+	}
+err:
 	bch2_fs_fatal_err_on(ret, c, "%s: insert error %s", __func__, bch2_err_str(ret));
-out:
-	bch2_journal_pin_drop(j, &pin);
-	mutex_unlock(&wb->flush_lock);
+	trace_write_buffer_flush(trans, wb->flushing.keys.nr, skipped, fast, 0);
+	bch2_journal_pin_drop(j, &wb->flushing.pin);
+	wb->flushing.keys.nr = 0;
 	return ret;
-slowpath:
-	trace_write_buffer_flush_slowpath(trans, i - keys, nr);
+}
 
-	/*
-	 * Now sort the rest by journal seq and bump the journal pin as we go.
-	 * The slowpath zapped the seq of keys that were successfully flushed so
-	 * we can skip those here.
-	 */
-	sort(keys, nr, sizeof(keys[0]),
-	     btree_write_buffered_journal_cmp,
-	     NULL);
+static int fetch_wb_keys_from_journal(struct bch_fs *c, u64 seq)
+{
+	struct journal *j = &c->journal;
+	struct journal_buf *buf;
+	int ret = 0;
 
-	commit_flags &= ~BCH_WATERMARK_MASK;
-	commit_flags |= BCH_WATERMARK_reclaim;
+	while (!ret && (buf = bch2_next_write_buffer_flush_journal_buf(j, seq))) {
+		ret = bch2_journal_keys_to_write_buffer(c, buf);
+		mutex_unlock(&j->buf_lock);
+	}
 
-	for (i = keys; i < keys + nr; i++) {
-		if (!i->journal_seq)
-			continue;
+	return ret;
+}
 
-		if (i->journal_seq > pin.seq) {
-			struct journal_entry_pin pin2;
+static int btree_write_buffer_flush_seq(struct btree_trans *trans, u64 seq)
+{
+	struct bch_fs *c = trans->c;
+	struct btree_write_buffer *wb = &c->btree_write_buffer;
+	int ret = 0, fetch_from_journal_err;
 
-			memset(&pin2, 0, sizeof(pin2));
+	do {
+		bch2_trans_unlock(trans);
 
-			bch2_journal_pin_add(j, i->journal_seq, &pin2, NULL);
-			bch2_journal_pin_drop(j, &pin);
-			bch2_journal_pin_copy(j, &pin, &pin2, NULL);
-			bch2_journal_pin_drop(j, &pin2);
-		}
+		fetch_from_journal_err = fetch_wb_keys_from_journal(c, seq);
 
-		ret = commit_do(trans, NULL, NULL,
-				commit_flags|
-				BTREE_INSERT_NOFAIL|
-				BTREE_INSERT_JOURNAL_RECLAIM,
-				btree_write_buffered_insert(trans, i));
-		if (bch2_fs_fatal_err_on(ret, c, "%s: insert error %s", __func__, bch2_err_str(ret)))
-			break;
-	}
+		/*
+		 * On memory allocation failure, bch2_btree_write_buffer_flush_locked()
+		 * is not guaranteed to empty wb->inc:
+		 */
+		mutex_lock(&wb->flushing.lock);
+		ret = bch2_btree_write_buffer_flush_locked(trans);
+		mutex_unlock(&wb->flushing.lock);
+	} while (!ret &&
+		 (fetch_from_journal_err ||
+		  (wb->inc.pin.seq && wb->inc.pin.seq <= seq) ||
+		  (wb->flushing.pin.seq && wb->flushing.pin.seq <= seq)));
 
-	goto out;
+	return ret;
 }
 
-int bch2_btree_write_buffer_flush_sync(struct btree_trans *trans)
+static int bch2_btree_write_buffer_journal_flush(struct journal *j,
+				struct journal_entry_pin *_pin, u64 seq)
 {
-	bch2_trans_unlock(trans);
-	mutex_lock(&trans->c->btree_write_buffer.flush_lock);
-	return __bch2_btree_write_buffer_flush(trans, 0, true);
+	struct bch_fs *c = container_of(j, struct bch_fs, journal);
+
+	return bch2_trans_run(c, btree_write_buffer_flush_seq(trans, seq));
 }
 
-int bch2_btree_write_buffer_flush(struct btree_trans *trans)
+int bch2_btree_write_buffer_flush_sync(struct btree_trans *trans)
 {
-	return __bch2_btree_write_buffer_flush(trans, 0, false);
+	struct bch_fs *c = trans->c;
+
+	trace_and_count(c, write_buffer_flush_sync, trans, _RET_IP_);
+
+	return btree_write_buffer_flush_seq(trans, journal_cur_seq(&c->journal));
 }
 
-static int bch2_btree_write_buffer_journal_flush(struct journal *j,
-				struct journal_entry_pin *_pin, u64 seq)
+int bch2_btree_write_buffer_flush_nocheck_rw(struct btree_trans *trans)
 {
-	struct bch_fs *c = container_of(j, struct bch_fs, journal);
+	struct bch_fs *c = trans->c;
 	struct btree_write_buffer *wb = &c->btree_write_buffer;
+	int ret = 0;
 
-	mutex_lock(&wb->flush_lock);
+	if (mutex_trylock(&wb->flushing.lock)) {
+		ret = bch2_btree_write_buffer_flush_locked(trans);
+		mutex_unlock(&wb->flushing.lock);
+	}
 
-	return bch2_trans_run(c,
-			__bch2_btree_write_buffer_flush(trans, BTREE_INSERT_NOCHECK_RW, true));
+	return ret;
 }
 
-static inline u64 btree_write_buffer_ref(int idx)
+int bch2_btree_write_buffer_tryflush(struct btree_trans *trans)
 {
-	return ((union btree_write_buffer_state) {
-		.ref0 = idx == 0,
-		.ref1 = idx == 1,
-	}).v;
+	struct bch_fs *c = trans->c;
+
+	if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_btree_write_buffer))
+		return -BCH_ERR_erofs_no_writes;
+
+	int ret = bch2_btree_write_buffer_flush_nocheck_rw(trans);
+	bch2_write_ref_put(c, BCH_WRITE_REF_btree_write_buffer);
+	return ret;
 }
 
-int bch2_btree_insert_keys_write_buffer(struct btree_trans *trans)
+static void bch2_btree_write_buffer_flush_work(struct work_struct *work)
 {
-	struct bch_fs *c = trans->c;
+	struct bch_fs *c = container_of(work, struct bch_fs, btree_write_buffer.flush_work);
 	struct btree_write_buffer *wb = &c->btree_write_buffer;
-	struct btree_write_buffered_key *i;
-	union btree_write_buffer_state old, new;
-	int ret = 0;
-	u64 v;
+	int ret;
 
-	trans_for_each_wb_update(trans, i) {
-		EBUG_ON(i->k.k.u64s > BTREE_WRITE_BUFERED_U64s_MAX);
+	mutex_lock(&wb->flushing.lock);
+	do {
+		ret = bch2_trans_run(c, bch2_btree_write_buffer_flush_locked(trans));
+	} while (!ret && bch2_btree_write_buffer_should_flush(c));
+	mutex_unlock(&wb->flushing.lock);
+
+	bch2_write_ref_put(c, BCH_WRITE_REF_btree_write_buffer);
+}
 
-		i->journal_seq		= trans->journal_res.seq;
-		i->journal_offset	= trans->journal_res.offset;
+int bch2_journal_key_to_wb_slowpath(struct bch_fs *c,
+			     struct journal_keys_to_wb *dst,
+			     enum btree_id btree, struct bkey_i *k)
+{
+	struct btree_write_buffer *wb = &c->btree_write_buffer;
+	int ret;
+retry:
+	ret = darray_make_room_gfp(&dst->wb->keys, 1, GFP_KERNEL);
+	if (!ret && dst->wb == &wb->flushing)
+		ret = darray_resize(&wb->sorted, wb->flushing.keys.size);
+
+	if (unlikely(ret)) {
+		if (dst->wb == &c->btree_write_buffer.flushing) {
+			mutex_unlock(&dst->wb->lock);
+			dst->wb = &c->btree_write_buffer.inc;
+			bch2_journal_pin_add(&c->journal, dst->seq, &dst->wb->pin,
+					     bch2_btree_write_buffer_journal_flush);
+			goto retry;
+		}
+
+		return ret;
 	}
 
-	preempt_disable();
-	v = READ_ONCE(wb->state.v);
-	do {
-		old.v = new.v = v;
+	dst->room = darray_room(dst->wb->keys);
+	if (dst->wb == &wb->flushing)
+		dst->room = min(dst->room, wb->sorted.size - wb->flushing.keys.nr);
+	BUG_ON(!dst->room);
+	BUG_ON(!dst->seq);
+
+	struct btree_write_buffered_key *wb_k = &darray_top(dst->wb->keys);
+	wb_k->journal_seq	= dst->seq;
+	wb_k->btree		= btree;
+	bkey_copy(&wb_k->k, k);
+	dst->wb->keys.nr++;
+	dst->room--;
+	return 0;
+}
+
+void bch2_journal_keys_to_write_buffer_start(struct bch_fs *c, struct journal_keys_to_wb *dst, u64 seq)
+{
+	struct btree_write_buffer *wb = &c->btree_write_buffer;
+
+	if (mutex_trylock(&wb->flushing.lock)) {
+		mutex_lock(&wb->inc.lock);
+		move_keys_from_inc_to_flushing(wb);
 
-		new.v += btree_write_buffer_ref(new.idx);
-		new.nr += trans->nr_wb_updates;
-		if (new.nr > wb->size) {
-			ret = -BCH_ERR_btree_insert_need_flush_buffer;
-			goto out;
+		/*
+		 * Attempt to skip wb->inc, and add keys directly to
+		 * wb->flushing, saving us a copy later:
+		 */
+
+		if (!wb->inc.keys.nr) {
+			dst->wb = &wb->flushing;
+		} else {
+			mutex_unlock(&wb->flushing.lock);
+			dst->wb = &wb->inc;
 		}
-	} while ((v = atomic64_cmpxchg_acquire(&wb->state.counter, old.v, new.v)) != old.v);
+	} else {
+		mutex_lock(&wb->inc.lock);
+		dst->wb = &wb->inc;
+	}
 
-	memcpy(wb->keys[new.idx] + old.nr,
-	       trans->wb_updates,
-	       sizeof(trans->wb_updates[0]) * trans->nr_wb_updates);
+	dst->room = darray_room(dst->wb->keys);
+	if (dst->wb == &wb->flushing)
+		dst->room = min(dst->room, wb->sorted.size - wb->flushing.keys.nr);
+	dst->seq = seq;
 
-	bch2_journal_pin_add(&c->journal, trans->journal_res.seq, &wb->journal_pin,
+	bch2_journal_pin_add(&c->journal, seq, &dst->wb->pin,
 			     bch2_btree_write_buffer_journal_flush);
+}
+
+void bch2_journal_keys_to_write_buffer_end(struct bch_fs *c, struct journal_keys_to_wb *dst)
+{
+	struct btree_write_buffer *wb = &c->btree_write_buffer;
+
+	if (!dst->wb->keys.nr)
+		bch2_journal_pin_drop(&c->journal, &dst->wb->pin);
+
+	if (bch2_btree_write_buffer_should_flush(c) &&
+	    __bch2_write_ref_tryget(c, BCH_WRITE_REF_btree_write_buffer) &&
+	    !queue_work(system_unbound_wq, &c->btree_write_buffer.flush_work))
+		bch2_write_ref_put(c, BCH_WRITE_REF_btree_write_buffer);
+
+	if (dst->wb == &wb->flushing)
+		mutex_unlock(&wb->flushing.lock);
+	mutex_unlock(&wb->inc.lock);
+}
+
+static int bch2_journal_keys_to_write_buffer(struct bch_fs *c, struct journal_buf *buf)
+{
+	struct journal_keys_to_wb dst;
+	struct jset_entry *entry;
+	struct bkey_i *k;
+	int ret = 0;
+
+	bch2_journal_keys_to_write_buffer_start(c, &dst, le64_to_cpu(buf->data->seq));
 
-	atomic64_sub_return_release(btree_write_buffer_ref(new.idx), &wb->state.counter);
+	for_each_jset_entry_type(entry, buf->data, BCH_JSET_ENTRY_write_buffer_keys) {
+		jset_entry_for_each_key(entry, k) {
+			ret = bch2_journal_key_to_wb(c, &dst, entry->btree_id, k);
+			if (ret)
+				goto out;
+		}
+
+		entry->type = BCH_JSET_ENTRY_btree_keys;
+	}
+
+	buf->need_flush_to_write_buffer = false;
 out:
-	preempt_enable();
+	bch2_journal_keys_to_write_buffer_end(c, &dst);
+	return ret;
+}
+
+static int wb_keys_resize(struct btree_write_buffer_keys *wb, size_t new_size)
+{
+	if (wb->keys.size >= new_size)
+		return 0;
+
+	if (!mutex_trylock(&wb->lock))
+		return -EINTR;
+
+	int ret = darray_resize(&wb->keys, new_size);
+	mutex_unlock(&wb->lock);
 	return ret;
 }
 
+int bch2_btree_write_buffer_resize(struct bch_fs *c, size_t new_size)
+{
+	struct btree_write_buffer *wb = &c->btree_write_buffer;
+
+	return wb_keys_resize(&wb->flushing, new_size) ?:
+		wb_keys_resize(&wb->inc, new_size);
+}
+
 void bch2_fs_btree_write_buffer_exit(struct bch_fs *c)
 {
 	struct btree_write_buffer *wb = &c->btree_write_buffer;
 
-	BUG_ON(wb->state.nr && !bch2_journal_error(&c->journal));
+	BUG_ON((wb->inc.keys.nr || wb->flushing.keys.nr) &&
+	       !bch2_journal_error(&c->journal));
 
-	kvfree(wb->keys[1]);
-	kvfree(wb->keys[0]);
+	darray_exit(&wb->sorted);
+	darray_exit(&wb->flushing.keys);
+	darray_exit(&wb->inc.keys);
 }
 
 int bch2_fs_btree_write_buffer_init(struct bch_fs *c)
 {
 	struct btree_write_buffer *wb = &c->btree_write_buffer;
 
-	mutex_init(&wb->flush_lock);
-	wb->size = c->opts.btree_write_buffer_size;
+	mutex_init(&wb->inc.lock);
+	mutex_init(&wb->flushing.lock);
+	INIT_WORK(&wb->flush_work, bch2_btree_write_buffer_flush_work);
 
-	wb->keys[0] = kvmalloc_array(wb->size, sizeof(*wb->keys[0]), GFP_KERNEL);
-	wb->keys[1] = kvmalloc_array(wb->size, sizeof(*wb->keys[1]), GFP_KERNEL);
-	if (!wb->keys[0] || !wb->keys[1])
-		return -BCH_ERR_ENOMEM_fs_btree_write_buffer_init;
+	/* Will be resized by journal as needed: */
+	unsigned initial_size = 1 << 16;
 
-	return 0;
+	return  darray_make_room(&wb->inc.keys, initial_size) ?:
+		darray_make_room(&wb->flushing.keys, initial_size) ?:
+		darray_make_room(&wb->sorted, initial_size);
 }
diff --git a/fs/bcachefs/btree_write_buffer.h b/fs/bcachefs/btree_write_buffer.h
index 322df1c8304e..eebcd2b15249 100644
--- a/fs/bcachefs/btree_write_buffer.h
+++ b/fs/bcachefs/btree_write_buffer.h
@@ -2,12 +2,59 @@
 #ifndef _BCACHEFS_BTREE_WRITE_BUFFER_H
 #define _BCACHEFS_BTREE_WRITE_BUFFER_H
 
-int __bch2_btree_write_buffer_flush(struct btree_trans *, unsigned, bool);
+#include "bkey.h"
+
+static inline bool bch2_btree_write_buffer_should_flush(struct bch_fs *c)
+{
+	struct btree_write_buffer *wb = &c->btree_write_buffer;
+
+	return wb->inc.keys.nr + wb->flushing.keys.nr > wb->inc.keys.size / 4;
+}
+
+static inline bool bch2_btree_write_buffer_must_wait(struct bch_fs *c)
+{
+	struct btree_write_buffer *wb = &c->btree_write_buffer;
+
+	return wb->inc.keys.nr > wb->inc.keys.size * 3 / 4;
+}
+
+struct btree_trans;
 int bch2_btree_write_buffer_flush_sync(struct btree_trans *);
-int bch2_btree_write_buffer_flush(struct btree_trans *);
+int bch2_btree_write_buffer_flush_nocheck_rw(struct btree_trans *);
+int bch2_btree_write_buffer_tryflush(struct btree_trans *);
+
+struct journal_keys_to_wb {
+	struct btree_write_buffer_keys	*wb;
+	size_t				room;
+	u64				seq;
+};
+
+int bch2_journal_key_to_wb_slowpath(struct bch_fs *,
+			     struct journal_keys_to_wb *,
+			     enum btree_id, struct bkey_i *);
+
+static inline int bch2_journal_key_to_wb(struct bch_fs *c,
+			     struct journal_keys_to_wb *dst,
+			     enum btree_id btree, struct bkey_i *k)
+{
+	EBUG_ON(!dst->seq);
+
+	if (unlikely(!dst->room))
+		return bch2_journal_key_to_wb_slowpath(c, dst, btree, k);
+
+	struct btree_write_buffered_key *wb_k = &darray_top(dst->wb->keys);
+	wb_k->journal_seq	= dst->seq;
+	wb_k->btree		= btree;
+	bkey_copy(&wb_k->k, k);
+	dst->wb->keys.nr++;
+	dst->room--;
+	return 0;
+}
 
-int bch2_btree_insert_keys_write_buffer(struct btree_trans *);
+void bch2_journal_keys_to_write_buffer_start(struct bch_fs *, struct journal_keys_to_wb *, u64);
+void bch2_journal_keys_to_write_buffer_end(struct bch_fs *, struct journal_keys_to_wb *);
 
+int bch2_btree_write_buffer_resize(struct bch_fs *, size_t);
 void bch2_fs_btree_write_buffer_exit(struct bch_fs *);
 int bch2_fs_btree_write_buffer_init(struct bch_fs *);
 
diff --git a/fs/bcachefs/btree_write_buffer_types.h b/fs/bcachefs/btree_write_buffer_types.h
index 99993ba77aea..9b9433de9c36 100644
--- a/fs/bcachefs/btree_write_buffer_types.h
+++ b/fs/bcachefs/btree_write_buffer_types.h
@@ -2,43 +2,56 @@
 #ifndef _BCACHEFS_BTREE_WRITE_BUFFER_TYPES_H
 #define _BCACHEFS_BTREE_WRITE_BUFFER_TYPES_H
 
+#include "darray.h"
 #include "journal_types.h"
 
 #define BTREE_WRITE_BUFERED_VAL_U64s_MAX	4
 #define BTREE_WRITE_BUFERED_U64s_MAX	(BKEY_U64s + BTREE_WRITE_BUFERED_VAL_U64s_MAX)
 
-struct btree_write_buffered_key {
-	u64			journal_seq;
-	unsigned		journal_offset;
-	enum btree_id		btree;
-	__BKEY_PADDED(k, BTREE_WRITE_BUFERED_VAL_U64s_MAX);
-};
-
-union btree_write_buffer_state {
+struct wb_key_ref {
+union {
 	struct {
-		atomic64_t	counter;
-	};
-
-	struct {
-		u64		v;
-	};
-
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+		unsigned			idx:24;
+		u8				pos[sizeof(struct bpos)];
+		enum btree_id			btree:8;
+#else
+		enum btree_id			btree:8;
+		u8				pos[sizeof(struct bpos)];
+		unsigned			idx:24;
+#endif
+	} __packed;
 	struct {
-		u64			nr:23;
-		u64			idx:1;
-		u64			ref0:20;
-		u64			ref1:20;
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+		u64 lo;
+		u64 mi;
+		u64 hi;
+#else
+		u64 hi;
+		u64 mi;
+		u64 lo;
+#endif
 	};
 };
+};
 
-struct btree_write_buffer {
-	struct mutex			flush_lock;
-	struct journal_entry_pin	journal_pin;
+struct btree_write_buffered_key {
+	enum btree_id			btree:8;
+	u64				journal_seq:56;
+	__BKEY_PADDED(k, BTREE_WRITE_BUFERED_VAL_U64s_MAX);
+};
 
-	union btree_write_buffer_state	state;
-	size_t				size;
+struct btree_write_buffer_keys {
+	DARRAY(struct btree_write_buffered_key) keys;
+	struct journal_entry_pin	pin;
+	struct mutex			lock;
+};
 
-	struct btree_write_buffered_key	*keys[2];
+struct btree_write_buffer {
+	DARRAY(struct wb_key_ref)	sorted;
+	struct btree_write_buffer_keys	inc;
+	struct btree_write_buffer_keys	flushing;
+	struct work_struct		flush_work;
 };
 
 #endif /* _BCACHEFS_BTREE_WRITE_BUFFER_TYPES_H */
diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c
index 58d8c6ffd955..d83ea0e53df3 100644
--- a/fs/bcachefs/buckets.c
+++ b/fs/bcachefs/buckets.c
@@ -47,27 +47,23 @@ static inline void fs_usage_data_type_to_base(struct bch_fs_usage *fs_usage,
 
 void bch2_fs_usage_initialize(struct bch_fs *c)
 {
-	struct bch_fs_usage *usage;
-	struct bch_dev *ca;
-	unsigned i;
-
 	percpu_down_write(&c->mark_lock);
-	usage = c->usage_base;
+	struct bch_fs_usage *usage = c->usage_base;
 
-	for (i = 0; i < ARRAY_SIZE(c->usage); i++)
+	for (unsigned i = 0; i < ARRAY_SIZE(c->usage); i++)
 		bch2_fs_usage_acc_to_base(c, i);
 
-	for (i = 0; i < BCH_REPLICAS_MAX; i++)
+	for (unsigned i = 0; i < BCH_REPLICAS_MAX; i++)
 		usage->reserved += usage->persistent_reserved[i];
 
-	for (i = 0; i < c->replicas.nr; i++) {
-		struct bch_replicas_entry *e =
+	for (unsigned i = 0; i < c->replicas.nr; i++) {
+		struct bch_replicas_entry_v1 *e =
 			cpu_replicas_entry(&c->replicas, i);
 
 		fs_usage_data_type_to_base(usage, e->data_type, usage->replicas[i]);
 	}
 
-	for_each_member_device(ca, c, i) {
+	for_each_member_device(c, ca) {
 		struct bch_dev_usage dev = bch2_dev_usage_read(ca);
 
 		usage->hidden += (dev.d[BCH_DATA_sb].buckets +
@@ -158,8 +154,7 @@ retry:
 
 void bch2_fs_usage_acc_to_base(struct bch_fs *c, unsigned idx)
 {
-	struct bch_dev *ca;
-	unsigned i, u64s = fs_usage_u64s(c);
+	unsigned u64s = fs_usage_u64s(c);
 
 	BUG_ON(idx >= ARRAY_SIZE(c->usage));
 
@@ -171,7 +166,7 @@ void bch2_fs_usage_acc_to_base(struct bch_fs *c, unsigned idx)
 	percpu_memset(c->usage[idx], 0, u64s * sizeof(u64));
 
 	rcu_read_lock();
-	for_each_member_device_rcu(ca, c, i, NULL) {
+	for_each_member_device_rcu(c, ca, NULL) {
 		u64s = dev_usage_u64s();
 
 		acc_u64s_percpu((u64 *) ca->usage_base,
@@ -214,7 +209,7 @@ void bch2_fs_usage_to_text(struct printbuf *out,
 	}
 
 	for (i = 0; i < c->replicas.nr; i++) {
-		struct bch_replicas_entry *e =
+		struct bch_replicas_entry_v1 *e =
 			cpu_replicas_entry(&c->replicas, i);
 
 		prt_printf(out, "\t");
@@ -277,18 +272,34 @@ void bch2_dev_usage_init(struct bch_dev *ca)
 	ca->usage_base->d[BCH_DATA_free].buckets = ca->mi.nbuckets - ca->mi.first_bucket;
 }
 
-static inline int bucket_sectors_fragmented(struct bch_dev *ca,
-					    struct bch_alloc_v4 a)
+void bch2_dev_usage_to_text(struct printbuf *out, struct bch_dev_usage *usage)
 {
-	return a.dirty_sectors
-		? max(0, (int) ca->mi.bucket_size - (int) a.dirty_sectors)
-		: 0;
+	prt_tab(out);
+	prt_str(out, "buckets");
+	prt_tab_rjust(out);
+	prt_str(out, "sectors");
+	prt_tab_rjust(out);
+	prt_str(out, "fragmented");
+	prt_tab_rjust(out);
+	prt_newline(out);
+
+	for (unsigned i = 0; i < BCH_DATA_NR; i++) {
+		prt_str(out, bch2_data_types[i]);
+		prt_tab(out);
+		prt_u64(out, usage->d[i].buckets);
+		prt_tab_rjust(out);
+		prt_u64(out, usage->d[i].sectors);
+		prt_tab_rjust(out);
+		prt_u64(out, usage->d[i].fragmented);
+		prt_tab_rjust(out);
+		prt_newline(out);
+	}
 }
 
-static void bch2_dev_usage_update(struct bch_fs *c, struct bch_dev *ca,
-				  struct bch_alloc_v4 old,
-				  struct bch_alloc_v4 new,
-				  u64 journal_seq, bool gc)
+void bch2_dev_usage_update(struct bch_fs *c, struct bch_dev *ca,
+			   const struct bch_alloc_v4 *old,
+			   const struct bch_alloc_v4 *new,
+			   u64 journal_seq, bool gc)
 {
 	struct bch_fs_usage *fs_usage;
 	struct bch_dev_usage *u;
@@ -296,56 +307,51 @@ static void bch2_dev_usage_update(struct bch_fs *c, struct bch_dev *ca,
 	preempt_disable();
 	fs_usage = fs_usage_ptr(c, journal_seq, gc);
 
-	if (data_type_is_hidden(old.data_type))
+	if (data_type_is_hidden(old->data_type))
 		fs_usage->hidden -= ca->mi.bucket_size;
-	if (data_type_is_hidden(new.data_type))
+	if (data_type_is_hidden(new->data_type))
 		fs_usage->hidden += ca->mi.bucket_size;
 
 	u = dev_usage_ptr(ca, journal_seq, gc);
 
-	u->d[old.data_type].buckets--;
-	u->d[new.data_type].buckets++;
-
-	u->buckets_ec -= (int) !!old.stripe;
-	u->buckets_ec += (int) !!new.stripe;
+	u->d[old->data_type].buckets--;
+	u->d[new->data_type].buckets++;
 
-	u->d[old.data_type].sectors -= old.dirty_sectors;
-	u->d[new.data_type].sectors += new.dirty_sectors;
+	u->d[old->data_type].sectors -= bch2_bucket_sectors_dirty(*old);
+	u->d[new->data_type].sectors += bch2_bucket_sectors_dirty(*new);
 
-	u->d[BCH_DATA_cached].sectors += new.cached_sectors;
-	u->d[BCH_DATA_cached].sectors -= old.cached_sectors;
+	u->d[BCH_DATA_cached].sectors += new->cached_sectors;
+	u->d[BCH_DATA_cached].sectors -= old->cached_sectors;
 
-	u->d[old.data_type].fragmented -= bucket_sectors_fragmented(ca, old);
-	u->d[new.data_type].fragmented += bucket_sectors_fragmented(ca, new);
+	u->d[old->data_type].fragmented -= bch2_bucket_sectors_fragmented(ca, *old);
+	u->d[new->data_type].fragmented += bch2_bucket_sectors_fragmented(ca, *new);
 
 	preempt_enable();
 }
 
-static void bch2_dev_usage_update_m(struct bch_fs *c, struct bch_dev *ca,
-				    struct bucket old, struct bucket new,
-				    u64 journal_seq, bool gc)
+static inline struct bch_alloc_v4 bucket_m_to_alloc(struct bucket b)
 {
-	struct bch_alloc_v4 old_a = {
-		.gen		= old.gen,
-		.data_type	= old.data_type,
-		.dirty_sectors	= old.dirty_sectors,
-		.cached_sectors	= old.cached_sectors,
-		.stripe		= old.stripe,
-	};
-	struct bch_alloc_v4 new_a = {
-		.gen		= new.gen,
-		.data_type	= new.data_type,
-		.dirty_sectors	= new.dirty_sectors,
-		.cached_sectors	= new.cached_sectors,
-		.stripe		= new.stripe,
+	return (struct bch_alloc_v4) {
+		.gen		= b.gen,
+		.data_type	= b.data_type,
+		.dirty_sectors	= b.dirty_sectors,
+		.cached_sectors	= b.cached_sectors,
+		.stripe		= b.stripe,
 	};
+}
+
+void bch2_dev_usage_update_m(struct bch_fs *c, struct bch_dev *ca,
+			     struct bucket *old, struct bucket *new)
+{
+	struct bch_alloc_v4 old_a = bucket_m_to_alloc(*old);
+	struct bch_alloc_v4 new_a = bucket_m_to_alloc(*new);
 
-	bch2_dev_usage_update(c, ca, old_a, new_a, journal_seq, gc);
+	bch2_dev_usage_update(c, ca, &old_a, &new_a, 0, true);
 }
 
 static inline int __update_replicas(struct bch_fs *c,
 				    struct bch_fs_usage *fs_usage,
-				    struct bch_replicas_entry *r,
+				    struct bch_replicas_entry_v1 *r,
 				    s64 sectors)
 {
 	int idx = bch2_replicas_entry_idx(c, r);
@@ -358,9 +364,9 @@ static inline int __update_replicas(struct bch_fs *c,
 	return 0;
 }
 
-static inline int update_replicas(struct bch_fs *c, struct bkey_s_c k,
-			struct bch_replicas_entry *r, s64 sectors,
-			unsigned journal_seq, bool gc)
+int bch2_update_replicas(struct bch_fs *c, struct bkey_s_c k,
+			 struct bch_replicas_entry_v1 *r, s64 sectors,
+			 unsigned journal_seq, bool gc)
 {
 	struct bch_fs_usage *fs_usage;
 	int idx, ret = 0;
@@ -407,7 +413,7 @@ static inline int update_cached_sectors(struct bch_fs *c,
 
 	bch2_replicas_entry_cached(&r.e, dev);
 
-	return update_replicas(c, k, &r.e, sectors, journal_seq, gc);
+	return bch2_update_replicas(c, k, &r.e, sectors, journal_seq, gc);
 }
 
 static int __replicas_deltas_realloc(struct btree_trans *trans, unsigned more,
@@ -453,9 +459,9 @@ int bch2_replicas_deltas_realloc(struct btree_trans *trans, unsigned more)
 				__replicas_deltas_realloc(trans, more, _gfp));
 }
 
-static inline int update_replicas_list(struct btree_trans *trans,
-					struct bch_replicas_entry *r,
-					s64 sectors)
+int bch2_update_replicas_list(struct btree_trans *trans,
+			 struct bch_replicas_entry_v1 *r,
+			 s64 sectors)
 {
 	struct replicas_delta_list *d;
 	struct replicas_delta *n;
@@ -481,139 +487,13 @@ static inline int update_replicas_list(struct btree_trans *trans,
 	return 0;
 }
 
-static inline int update_cached_sectors_list(struct btree_trans *trans,
-					      unsigned dev, s64 sectors)
+int bch2_update_cached_sectors_list(struct btree_trans *trans, unsigned dev, s64 sectors)
 {
 	struct bch_replicas_padded r;
 
 	bch2_replicas_entry_cached(&r.e, dev);
 
-	return update_replicas_list(trans, &r.e, sectors);
-}
-
-int bch2_mark_alloc(struct btree_trans *trans,
-		    enum btree_id btree, unsigned level,
-		    struct bkey_s_c old, struct bkey_s_c new,
-		    unsigned flags)
-{
-	bool gc = flags & BTREE_TRIGGER_GC;
-	u64 journal_seq = trans->journal_res.seq;
-	u64 bucket_journal_seq;
-	struct bch_fs *c = trans->c;
-	struct bch_alloc_v4 old_a_convert, new_a_convert;
-	const struct bch_alloc_v4 *old_a, *new_a;
-	struct bch_dev *ca;
-	int ret = 0;
-
-	/*
-	 * alloc btree is read in by bch2_alloc_read, not gc:
-	 */
-	if ((flags & BTREE_TRIGGER_GC) &&
-	    !(flags & BTREE_TRIGGER_BUCKET_INVALIDATE))
-		return 0;
-
-	if (bch2_trans_inconsistent_on(!bch2_dev_bucket_exists(c, new.k->p), trans,
-				       "alloc key for invalid device or bucket"))
-		return -EIO;
-
-	ca = bch_dev_bkey_exists(c, new.k->p.inode);
-
-	old_a = bch2_alloc_to_v4(old, &old_a_convert);
-	new_a = bch2_alloc_to_v4(new, &new_a_convert);
-
-	bucket_journal_seq = new_a->journal_seq;
-
-	if ((flags & BTREE_TRIGGER_INSERT) &&
-	    data_type_is_empty(old_a->data_type) !=
-	    data_type_is_empty(new_a->data_type) &&
-	    new.k->type == KEY_TYPE_alloc_v4) {
-		struct bch_alloc_v4 *v = (struct bch_alloc_v4 *) new.v;
-
-		EBUG_ON(!journal_seq);
-
-		/*
-		 * If the btree updates referring to a bucket weren't flushed
-		 * before the bucket became empty again, then the we don't have
-		 * to wait on a journal flush before we can reuse the bucket:
-		 */
-		v->journal_seq = bucket_journal_seq =
-			data_type_is_empty(new_a->data_type) &&
-			(journal_seq == v->journal_seq ||
-			 bch2_journal_noflush_seq(&c->journal, v->journal_seq))
-			? 0 : journal_seq;
-	}
-
-	if (!data_type_is_empty(old_a->data_type) &&
-	    data_type_is_empty(new_a->data_type) &&
-	    bucket_journal_seq) {
-		ret = bch2_set_bucket_needs_journal_commit(&c->buckets_waiting_for_journal,
-				c->journal.flushed_seq_ondisk,
-				new.k->p.inode, new.k->p.offset,
-				bucket_journal_seq);
-		if (ret) {
-			bch2_fs_fatal_error(c,
-				"error setting bucket_needs_journal_commit: %i", ret);
-			return ret;
-		}
-	}
-
-	percpu_down_read(&c->mark_lock);
-	if (!gc && new_a->gen != old_a->gen)
-		*bucket_gen(ca, new.k->p.offset) = new_a->gen;
-
-	bch2_dev_usage_update(c, ca, *old_a, *new_a, journal_seq, gc);
-
-	if (gc) {
-		struct bucket *g = gc_bucket(ca, new.k->p.offset);
-
-		bucket_lock(g);
-
-		g->gen_valid		= 1;
-		g->gen			= new_a->gen;
-		g->data_type		= new_a->data_type;
-		g->stripe		= new_a->stripe;
-		g->stripe_redundancy	= new_a->stripe_redundancy;
-		g->dirty_sectors	= new_a->dirty_sectors;
-		g->cached_sectors	= new_a->cached_sectors;
-
-		bucket_unlock(g);
-	}
-	percpu_up_read(&c->mark_lock);
-
-	/*
-	 * need to know if we're getting called from the invalidate path or
-	 * not:
-	 */
-
-	if ((flags & BTREE_TRIGGER_BUCKET_INVALIDATE) &&
-	    old_a->cached_sectors) {
-		ret = update_cached_sectors(c, new, ca->dev_idx,
-					    -((s64) old_a->cached_sectors),
-					    journal_seq, gc);
-		if (ret) {
-			bch2_fs_fatal_error(c, "%s(): no replicas entry while updating cached sectors",
-					    __func__);
-			return ret;
-		}
-	}
-
-	if (new_a->data_type == BCH_DATA_free &&
-	    (!new_a->journal_seq || new_a->journal_seq < c->journal.flushed_seq_ondisk))
-		closure_wake_up(&c->freelist_wait);
-
-	if (new_a->data_type == BCH_DATA_need_discard &&
-	    (!bucket_journal_seq || bucket_journal_seq < c->journal.flushed_seq_ondisk))
-		bch2_do_discards(c);
-
-	if (old_a->data_type != BCH_DATA_cached &&
-	    new_a->data_type == BCH_DATA_cached &&
-	    should_invalidate_buckets(ca, bch2_dev_usage_read(ca)))
-		bch2_do_invalidates(c);
-
-	if (new_a->data_type == BCH_DATA_need_gc_gens)
-		bch2_do_gc_gens(c);
-
-	return 0;
+	return bch2_update_replicas_list(trans, &r.e, sectors);
 }
 
 int bch2_mark_metadata_bucket(struct bch_fs *c, struct bch_dev *ca,
@@ -658,31 +538,27 @@ int bch2_mark_metadata_bucket(struct bch_fs *c, struct bch_dev *ca,
 		goto err;
 	}
 
-
 	g->data_type = data_type;
 	g->dirty_sectors += sectors;
 	new = *g;
 err:
 	bucket_unlock(g);
 	if (!ret)
-		bch2_dev_usage_update_m(c, ca, old, new, 0, true);
+		bch2_dev_usage_update_m(c, ca, &old, &new);
 	percpu_up_read(&c->mark_lock);
 	return ret;
 }
 
-static int check_bucket_ref(struct btree_trans *trans,
-			    struct bkey_s_c k,
-			    const struct bch_extent_ptr *ptr,
-			    s64 sectors, enum bch_data_type ptr_data_type,
-			    u8 b_gen, u8 bucket_data_type,
-			    u32 dirty_sectors, u32 cached_sectors)
+int bch2_check_bucket_ref(struct btree_trans *trans,
+			  struct bkey_s_c k,
+			  const struct bch_extent_ptr *ptr,
+			  s64 sectors, enum bch_data_type ptr_data_type,
+			  u8 b_gen, u8 bucket_data_type,
+			  u32 bucket_sectors)
 {
 	struct bch_fs *c = trans->c;
 	struct bch_dev *ca = bch_dev_bkey_exists(c, ptr->dev);
 	size_t bucket_nr = PTR_BUCKET_NR(ca, ptr);
-	u32 bucket_sectors = !ptr->cached
-		? dirty_sectors
-		: cached_sectors;
 	struct printbuf buf = PRINTBUF;
 	int ret = 0;
 
@@ -777,504 +653,6 @@ err:
 	goto out;
 }
 
-static int mark_stripe_bucket(struct btree_trans *trans,
-			      struct bkey_s_c k,
-			      unsigned ptr_idx,
-			      unsigned flags)
-{
-	struct bch_fs *c = trans->c;
-	u64 journal_seq = trans->journal_res.seq;
-	const struct bch_stripe *s = bkey_s_c_to_stripe(k).v;
-	unsigned nr_data = s->nr_blocks - s->nr_redundant;
-	bool parity = ptr_idx >= nr_data;
-	enum bch_data_type data_type = parity ? BCH_DATA_parity : BCH_DATA_stripe;
-	s64 sectors = parity ? le16_to_cpu(s->sectors) : 0;
-	const struct bch_extent_ptr *ptr = s->ptrs + ptr_idx;
-	struct bch_dev *ca = bch_dev_bkey_exists(c, ptr->dev);
-	struct bucket old, new, *g;
-	struct printbuf buf = PRINTBUF;
-	int ret = 0;
-
-	BUG_ON(!(flags & BTREE_TRIGGER_GC));
-
-	/* * XXX doesn't handle deletion */
-
-	percpu_down_read(&c->mark_lock);
-	g = PTR_GC_BUCKET(ca, ptr);
-
-	if (g->dirty_sectors ||
-	    (g->stripe && g->stripe != k.k->p.offset)) {
-		bch2_fs_inconsistent(c,
-			      "bucket %u:%zu gen %u: multiple stripes using same bucket\n%s",
-			      ptr->dev, PTR_BUCKET_NR(ca, ptr), g->gen,
-			      (bch2_bkey_val_to_text(&buf, c, k), buf.buf));
-		ret = -EINVAL;
-		goto err;
-	}
-
-	bucket_lock(g);
-	old = *g;
-
-	ret = check_bucket_ref(trans, k, ptr, sectors, data_type,
-			       g->gen, g->data_type,
-			       g->dirty_sectors, g->cached_sectors);
-	if (ret)
-		goto err;
-
-	g->data_type = data_type;
-	g->dirty_sectors += sectors;
-
-	g->stripe		= k.k->p.offset;
-	g->stripe_redundancy	= s->nr_redundant;
-	new = *g;
-err:
-	bucket_unlock(g);
-	if (!ret)
-		bch2_dev_usage_update_m(c, ca, old, new, journal_seq, true);
-	percpu_up_read(&c->mark_lock);
-	printbuf_exit(&buf);
-	return ret;
-}
-
-static int __mark_pointer(struct btree_trans *trans,
-			  struct bkey_s_c k,
-			  const struct bch_extent_ptr *ptr,
-			  s64 sectors, enum bch_data_type ptr_data_type,
-			  u8 bucket_gen, u8 *bucket_data_type,
-			  u32 *dirty_sectors, u32 *cached_sectors)
-{
-	u32 *dst_sectors = !ptr->cached
-		? dirty_sectors
-		: cached_sectors;
-	int ret = check_bucket_ref(trans, k, ptr, sectors, ptr_data_type,
-				   bucket_gen, *bucket_data_type,
-				   *dirty_sectors, *cached_sectors);
-
-	if (ret)
-		return ret;
-
-	*dst_sectors += sectors;
-	*bucket_data_type = *dirty_sectors || *cached_sectors
-		? ptr_data_type : 0;
-	return 0;
-}
-
-static int bch2_mark_pointer(struct btree_trans *trans,
-			     enum btree_id btree_id, unsigned level,
-			     struct bkey_s_c k,
-			     struct extent_ptr_decoded p,
-			     s64 sectors,
-			     unsigned flags)
-{
-	u64 journal_seq = trans->journal_res.seq;
-	struct bch_fs *c = trans->c;
-	struct bch_dev *ca = bch_dev_bkey_exists(c, p.ptr.dev);
-	struct bucket old, new, *g;
-	enum bch_data_type data_type = bkey_ptr_data_type(btree_id, level, k, p);
-	u8 bucket_data_type;
-	int ret = 0;
-
-	BUG_ON(!(flags & BTREE_TRIGGER_GC));
-
-	percpu_down_read(&c->mark_lock);
-	g = PTR_GC_BUCKET(ca, &p.ptr);
-	bucket_lock(g);
-	old = *g;
-
-	bucket_data_type = g->data_type;
-	ret = __mark_pointer(trans, k, &p.ptr, sectors,
-			     data_type, g->gen,
-			     &bucket_data_type,
-			     &g->dirty_sectors,
-			     &g->cached_sectors);
-	if (!ret)
-		g->data_type = bucket_data_type;
-
-	new = *g;
-	bucket_unlock(g);
-	if (!ret)
-		bch2_dev_usage_update_m(c, ca, old, new, journal_seq, true);
-	percpu_up_read(&c->mark_lock);
-
-	return ret;
-}
-
-static int bch2_mark_stripe_ptr(struct btree_trans *trans,
-				struct bkey_s_c k,
-				struct bch_extent_stripe_ptr p,
-				enum bch_data_type data_type,
-				s64 sectors,
-				unsigned flags)
-{
-	struct bch_fs *c = trans->c;
-	struct bch_replicas_padded r;
-	struct gc_stripe *m;
-
-	BUG_ON(!(flags & BTREE_TRIGGER_GC));
-
-	m = genradix_ptr_alloc(&c->gc_stripes, p.idx, GFP_KERNEL);
-	if (!m) {
-		bch_err(c, "error allocating memory for gc_stripes, idx %llu",
-			(u64) p.idx);
-		return -BCH_ERR_ENOMEM_mark_stripe_ptr;
-	}
-
-	mutex_lock(&c->ec_stripes_heap_lock);
-
-	if (!m || !m->alive) {
-		mutex_unlock(&c->ec_stripes_heap_lock);
-		bch_err_ratelimited(c, "pointer to nonexistent stripe %llu",
-				    (u64) p.idx);
-		bch2_inconsistent_error(c);
-		return -EIO;
-	}
-
-	m->block_sectors[p.block] += sectors;
-
-	r = m->r;
-	mutex_unlock(&c->ec_stripes_heap_lock);
-
-	r.e.data_type = data_type;
-	update_replicas(c, k, &r.e, sectors, trans->journal_res.seq, true);
-
-	return 0;
-}
-
-static int __mark_extent(struct btree_trans *trans,
-			 enum btree_id btree_id, unsigned level,
-			 struct bkey_s_c k, unsigned flags)
-{
-	u64 journal_seq = trans->journal_res.seq;
-	struct bch_fs *c = trans->c;
-	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
-	const union bch_extent_entry *entry;
-	struct extent_ptr_decoded p;
-	struct bch_replicas_padded r;
-	enum bch_data_type data_type = bkey_is_btree_ptr(k.k)
-		? BCH_DATA_btree
-		: BCH_DATA_user;
-	s64 sectors = bkey_is_btree_ptr(k.k)
-		? btree_sectors(c)
-		: k.k->size;
-	s64 dirty_sectors = 0;
-	bool stale;
-	int ret;
-
-	BUG_ON(!(flags & BTREE_TRIGGER_GC));
-
-	r.e.data_type	= data_type;
-	r.e.nr_devs	= 0;
-	r.e.nr_required	= 1;
-
-	bkey_for_each_ptr_decode(k.k, ptrs, p, entry) {
-		s64 disk_sectors = ptr_disk_sectors(sectors, p);
-
-		if (flags & BTREE_TRIGGER_OVERWRITE)
-			disk_sectors = -disk_sectors;
-
-		ret = bch2_mark_pointer(trans, btree_id, level, k, p, disk_sectors, flags);
-		if (ret < 0)
-			return ret;
-
-		stale = ret > 0;
-
-		if (p.ptr.cached) {
-			if (!stale) {
-				ret = update_cached_sectors(c, k, p.ptr.dev,
-						disk_sectors, journal_seq, true);
-				if (ret) {
-					bch2_fs_fatal_error(c, "%s(): no replicas entry while updating cached sectors",
-							    __func__);
-					return ret;
-				}
-			}
-		} else if (!p.has_ec) {
-			dirty_sectors	       += disk_sectors;
-			r.e.devs[r.e.nr_devs++]	= p.ptr.dev;
-		} else {
-			ret = bch2_mark_stripe_ptr(trans, k, p.ec, data_type,
-					disk_sectors, flags);
-			if (ret)
-				return ret;
-
-			/*
-			 * There may be other dirty pointers in this extent, but
-			 * if so they're not required for mounting if we have an
-			 * erasure coded pointer in this extent:
-			 */
-			r.e.nr_required = 0;
-		}
-	}
-
-	if (r.e.nr_devs) {
-		ret = update_replicas(c, k, &r.e, dirty_sectors, journal_seq, true);
-		if (ret) {
-			struct printbuf buf = PRINTBUF;
-
-			bch2_bkey_val_to_text(&buf, c, k);
-			bch2_fs_fatal_error(c, "%s(): no replicas entry for %s", __func__, buf.buf);
-			printbuf_exit(&buf);
-			return ret;
-		}
-	}
-
-	return 0;
-}
-
-int bch2_mark_extent(struct btree_trans *trans,
-		     enum btree_id btree_id, unsigned level,
-		     struct bkey_s_c old, struct bkey_s_c new,
-		     unsigned flags)
-{
-	return mem_trigger_run_overwrite_then_insert(__mark_extent, trans, btree_id, level, old, new, flags);
-}
-
-int bch2_mark_stripe(struct btree_trans *trans,
-		     enum btree_id btree_id, unsigned level,
-		     struct bkey_s_c old, struct bkey_s_c new,
-		     unsigned flags)
-{
-	bool gc = flags & BTREE_TRIGGER_GC;
-	u64 journal_seq = trans->journal_res.seq;
-	struct bch_fs *c = trans->c;
-	u64 idx = new.k->p.offset;
-	const struct bch_stripe *old_s = old.k->type == KEY_TYPE_stripe
-		? bkey_s_c_to_stripe(old).v : NULL;
-	const struct bch_stripe *new_s = new.k->type == KEY_TYPE_stripe
-		? bkey_s_c_to_stripe(new).v : NULL;
-	unsigned i;
-	int ret;
-
-	BUG_ON(gc && old_s);
-
-	if (!gc) {
-		struct stripe *m = genradix_ptr(&c->stripes, idx);
-
-		if (!m) {
-			struct printbuf buf1 = PRINTBUF;
-			struct printbuf buf2 = PRINTBUF;
-
-			bch2_bkey_val_to_text(&buf1, c, old);
-			bch2_bkey_val_to_text(&buf2, c, new);
-			bch_err_ratelimited(c, "error marking nonexistent stripe %llu while marking\n"
-					    "old %s\n"
-					    "new %s", idx, buf1.buf, buf2.buf);
-			printbuf_exit(&buf2);
-			printbuf_exit(&buf1);
-			bch2_inconsistent_error(c);
-			return -1;
-		}
-
-		if (!new_s) {
-			bch2_stripes_heap_del(c, m, idx);
-
-			memset(m, 0, sizeof(*m));
-		} else {
-			m->sectors	= le16_to_cpu(new_s->sectors);
-			m->algorithm	= new_s->algorithm;
-			m->nr_blocks	= new_s->nr_blocks;
-			m->nr_redundant	= new_s->nr_redundant;
-			m->blocks_nonempty = 0;
-
-			for (i = 0; i < new_s->nr_blocks; i++)
-				m->blocks_nonempty += !!stripe_blockcount_get(new_s, i);
-
-			if (!old_s)
-				bch2_stripes_heap_insert(c, m, idx);
-			else
-				bch2_stripes_heap_update(c, m, idx);
-		}
-	} else {
-		struct gc_stripe *m =
-			genradix_ptr_alloc(&c->gc_stripes, idx, GFP_KERNEL);
-
-		if (!m) {
-			bch_err(c, "error allocating memory for gc_stripes, idx %llu",
-				idx);
-			return -BCH_ERR_ENOMEM_mark_stripe;
-		}
-		/*
-		 * This will be wrong when we bring back runtime gc: we should
-		 * be unmarking the old key and then marking the new key
-		 */
-		m->alive	= true;
-		m->sectors	= le16_to_cpu(new_s->sectors);
-		m->nr_blocks	= new_s->nr_blocks;
-		m->nr_redundant	= new_s->nr_redundant;
-
-		for (i = 0; i < new_s->nr_blocks; i++)
-			m->ptrs[i] = new_s->ptrs[i];
-
-		bch2_bkey_to_replicas(&m->r.e, new);
-
-		/*
-		 * gc recalculates this field from stripe ptr
-		 * references:
-		 */
-		memset(m->block_sectors, 0, sizeof(m->block_sectors));
-
-		for (i = 0; i < new_s->nr_blocks; i++) {
-			ret = mark_stripe_bucket(trans, new, i, flags);
-			if (ret)
-				return ret;
-		}
-
-		ret = update_replicas(c, new, &m->r.e,
-				      ((s64) m->sectors * m->nr_redundant),
-				      journal_seq, gc);
-		if (ret) {
-			struct printbuf buf = PRINTBUF;
-
-			bch2_bkey_val_to_text(&buf, c, new);
-			bch2_fs_fatal_error(c, "no replicas entry for %s", buf.buf);
-			printbuf_exit(&buf);
-			return ret;
-		}
-	}
-
-	return 0;
-}
-
-static int __mark_reservation(struct btree_trans *trans,
-			      enum btree_id btree_id, unsigned level,
-			      struct bkey_s_c k, unsigned flags)
-{
-	struct bch_fs *c = trans->c;
-	struct bch_fs_usage *fs_usage;
-	unsigned replicas = bkey_s_c_to_reservation(k).v->nr_replicas;
-	s64 sectors = (s64) k.k->size;
-
-	BUG_ON(!(flags & BTREE_TRIGGER_GC));
-
-	if (flags & BTREE_TRIGGER_OVERWRITE)
-		sectors = -sectors;
-	sectors *= replicas;
-
-	percpu_down_read(&c->mark_lock);
-	preempt_disable();
-
-	fs_usage = fs_usage_ptr(c, trans->journal_res.seq, flags & BTREE_TRIGGER_GC);
-	replicas = clamp_t(unsigned, replicas, 1,
-			   ARRAY_SIZE(fs_usage->persistent_reserved));
-
-	fs_usage->reserved				+= sectors;
-	fs_usage->persistent_reserved[replicas - 1]	+= sectors;
-
-	preempt_enable();
-	percpu_up_read(&c->mark_lock);
-
-	return 0;
-}
-
-int bch2_mark_reservation(struct btree_trans *trans,
-			  enum btree_id btree_id, unsigned level,
-			  struct bkey_s_c old, struct bkey_s_c new,
-			  unsigned flags)
-{
-	return mem_trigger_run_overwrite_then_insert(__mark_reservation, trans, btree_id, level, old, new, flags);
-}
-
-static s64 __bch2_mark_reflink_p(struct btree_trans *trans,
-				 struct bkey_s_c_reflink_p p,
-				 u64 start, u64 end,
-				 u64 *idx, unsigned flags, size_t r_idx)
-{
-	struct bch_fs *c = trans->c;
-	struct reflink_gc *r;
-	int add = !(flags & BTREE_TRIGGER_OVERWRITE) ? 1 : -1;
-	u64 next_idx = end;
-	s64 ret = 0;
-	struct printbuf buf = PRINTBUF;
-
-	if (r_idx >= c->reflink_gc_nr)
-		goto not_found;
-
-	r = genradix_ptr(&c->reflink_gc_table, r_idx);
-	next_idx = min(next_idx, r->offset - r->size);
-	if (*idx < next_idx)
-		goto not_found;
-
-	BUG_ON((s64) r->refcount + add < 0);
-
-	r->refcount += add;
-	*idx = r->offset;
-	return 0;
-not_found:
-	if (fsck_err(c, reflink_p_to_missing_reflink_v,
-		     "pointer to missing indirect extent\n"
-		     "  %s\n"
-		     "  missing range %llu-%llu",
-		     (bch2_bkey_val_to_text(&buf, c, p.s_c), buf.buf),
-		     *idx, next_idx)) {
-		struct bkey_i_error *new;
-
-		new = bch2_trans_kmalloc(trans, sizeof(*new));
-		ret = PTR_ERR_OR_ZERO(new);
-		if (ret)
-			goto err;
-
-		bkey_init(&new->k);
-		new->k.type	= KEY_TYPE_error;
-		new->k.p		= bkey_start_pos(p.k);
-		new->k.p.offset += *idx - start;
-		bch2_key_resize(&new->k, next_idx - *idx);
-		ret = bch2_btree_insert_trans(trans, BTREE_ID_extents, &new->k_i,
-					  BTREE_TRIGGER_NORUN);
-	}
-
-	*idx = next_idx;
-err:
-fsck_err:
-	printbuf_exit(&buf);
-	return ret;
-}
-
-static int __mark_reflink_p(struct btree_trans *trans,
-			    enum btree_id btree_id, unsigned level,
-			    struct bkey_s_c k, unsigned flags)
-{
-	struct bch_fs *c = trans->c;
-	struct bkey_s_c_reflink_p p = bkey_s_c_to_reflink_p(k);
-	struct reflink_gc *ref;
-	size_t l, r, m;
-	u64 idx = le64_to_cpu(p.v->idx), start = idx;
-	u64 end = le64_to_cpu(p.v->idx) + p.k->size;
-	int ret = 0;
-
-	BUG_ON(!(flags & BTREE_TRIGGER_GC));
-
-	if (c->sb.version_upgrade_complete >= bcachefs_metadata_version_reflink_p_fix) {
-		idx -= le32_to_cpu(p.v->front_pad);
-		end += le32_to_cpu(p.v->back_pad);
-	}
-
-	l = 0;
-	r = c->reflink_gc_nr;
-	while (l < r) {
-		m = l + (r - l) / 2;
-
-		ref = genradix_ptr(&c->reflink_gc_table, m);
-		if (ref->offset <= idx)
-			l = m + 1;
-		else
-			r = m;
-	}
-
-	while (idx < end && !ret)
-		ret = __bch2_mark_reflink_p(trans, p, start, end,
-					    &idx, flags, l++);
-
-	return ret;
-}
-
-int bch2_mark_reflink_p(struct btree_trans *trans,
-			enum btree_id btree_id, unsigned level,
-			struct bkey_s_c old, struct bkey_s_c new,
-			unsigned flags)
-{
-	return mem_trigger_run_overwrite_then_insert(__mark_reflink_p, trans, btree_id, level, old, new, flags);
-}
-
 void bch2_trans_fs_usage_revert(struct btree_trans *trans,
 				struct replicas_delta_list *deltas)
 {
@@ -1394,92 +772,184 @@ need_mark:
 	return -1;
 }
 
-/* trans_mark: */
+/* KEY_TYPE_extent: */
 
-static inline int bch2_trans_mark_pointer(struct btree_trans *trans,
-				   enum btree_id btree_id, unsigned level,
-				   struct bkey_s_c k, struct extent_ptr_decoded p,
-				   unsigned flags)
+static int __mark_pointer(struct btree_trans *trans,
+			  struct bkey_s_c k,
+			  const struct bch_extent_ptr *ptr,
+			  s64 sectors, enum bch_data_type ptr_data_type,
+			  u8 bucket_gen, u8 *bucket_data_type,
+			  u32 *dirty_sectors, u32 *cached_sectors)
+{
+	u32 *dst_sectors = !ptr->cached
+		? dirty_sectors
+		: cached_sectors;
+	int ret = bch2_check_bucket_ref(trans, k, ptr, sectors, ptr_data_type,
+				   bucket_gen, *bucket_data_type, *dst_sectors);
+
+	if (ret)
+		return ret;
+
+	*dst_sectors += sectors;
+
+	if (!*dirty_sectors && !*cached_sectors)
+		*bucket_data_type = 0;
+	else if (*bucket_data_type != BCH_DATA_stripe)
+		*bucket_data_type = ptr_data_type;
+
+	return 0;
+}
+
+static int bch2_trigger_pointer(struct btree_trans *trans,
+			enum btree_id btree_id, unsigned level,
+			struct bkey_s_c k, struct extent_ptr_decoded p,
+			s64 *sectors,
+			unsigned flags)
 {
 	bool insert = !(flags & BTREE_TRIGGER_OVERWRITE);
-	struct btree_iter iter;
-	struct bkey_i_alloc_v4 *a;
 	struct bpos bucket;
 	struct bch_backpointer bp;
-	s64 sectors;
-	int ret;
 
 	bch2_extent_ptr_to_bp(trans->c, btree_id, level, k, p, &bucket, &bp);
-	sectors = bp.bucket_len;
-	if (!insert)
-		sectors = -sectors;
+	*sectors = insert ? bp.bucket_len : -((s64) bp.bucket_len);
 
-	a = bch2_trans_start_alloc_update(trans, &iter, bucket);
-	if (IS_ERR(a))
-		return PTR_ERR(a);
+	if (flags & BTREE_TRIGGER_TRANSACTIONAL) {
+		struct btree_iter iter;
+		struct bkey_i_alloc_v4 *a = bch2_trans_start_alloc_update(trans, &iter, bucket);
+		int ret = PTR_ERR_OR_ZERO(a);
+		if (ret)
+			return ret;
 
-	ret = __mark_pointer(trans, k, &p.ptr, sectors, bp.data_type,
-			     a->v.gen, &a->v.data_type,
-			     &a->v.dirty_sectors, &a->v.cached_sectors) ?:
-		bch2_trans_update(trans, &iter, &a->k_i, 0);
-	bch2_trans_iter_exit(trans, &iter);
+		ret = __mark_pointer(trans, k, &p.ptr, *sectors, bp.data_type,
+				     a->v.gen, &a->v.data_type,
+				     &a->v.dirty_sectors, &a->v.cached_sectors) ?:
+			bch2_trans_update(trans, &iter, &a->k_i, 0);
+		bch2_trans_iter_exit(trans, &iter);
 
-	if (ret)
-		return ret;
-
-	if (!p.ptr.cached) {
-		ret = bch2_bucket_backpointer_mod(trans, bucket, bp, k, insert);
 		if (ret)
 			return ret;
+
+		if (!p.ptr.cached) {
+			ret = bch2_bucket_backpointer_mod(trans, bucket, bp, k, insert);
+			if (ret)
+				return ret;
+		}
+	}
+
+	if (flags & BTREE_TRIGGER_GC) {
+		struct bch_fs *c = trans->c;
+		struct bch_dev *ca = bch_dev_bkey_exists(c, p.ptr.dev);
+		enum bch_data_type data_type = bkey_ptr_data_type(btree_id, level, k, p);
+
+		percpu_down_read(&c->mark_lock);
+		struct bucket *g = PTR_GC_BUCKET(ca, &p.ptr);
+		bucket_lock(g);
+		struct bucket old = *g;
+
+		u8 bucket_data_type = g->data_type;
+		int ret = __mark_pointer(trans, k, &p.ptr, *sectors,
+				     data_type, g->gen,
+				     &bucket_data_type,
+				     &g->dirty_sectors,
+				     &g->cached_sectors);
+		if (ret) {
+			bucket_unlock(g);
+			percpu_up_read(&c->mark_lock);
+			return ret;
+		}
+
+		g->data_type = bucket_data_type;
+		struct bucket new = *g;
+		bucket_unlock(g);
+		bch2_dev_usage_update_m(c, ca, &old, &new);
+		percpu_up_read(&c->mark_lock);
 	}
 
 	return 0;
 }
 
-static int bch2_trans_mark_stripe_ptr(struct btree_trans *trans,
-			struct extent_ptr_decoded p,
-			s64 sectors, enum bch_data_type data_type)
+static int bch2_trigger_stripe_ptr(struct btree_trans *trans,
+				struct bkey_s_c k,
+				struct extent_ptr_decoded p,
+				enum bch_data_type data_type,
+				s64 sectors, unsigned flags)
 {
-	struct btree_iter iter;
-	struct bkey_i_stripe *s;
-	struct bch_replicas_padded r;
-	int ret = 0;
+	if (flags & BTREE_TRIGGER_TRANSACTIONAL) {
+		struct btree_iter iter;
+		struct bkey_i_stripe *s = bch2_bkey_get_mut_typed(trans, &iter,
+				BTREE_ID_stripes, POS(0, p.ec.idx),
+				BTREE_ITER_WITH_UPDATES, stripe);
+		int ret = PTR_ERR_OR_ZERO(s);
+		if (unlikely(ret)) {
+			bch2_trans_inconsistent_on(bch2_err_matches(ret, ENOENT), trans,
+				"pointer to nonexistent stripe %llu",
+				(u64) p.ec.idx);
+			goto err;
+		}
 
-	s = bch2_bkey_get_mut_typed(trans, &iter,
-			BTREE_ID_stripes, POS(0, p.ec.idx),
-			BTREE_ITER_WITH_UPDATES, stripe);
-	ret = PTR_ERR_OR_ZERO(s);
-	if (unlikely(ret)) {
-		bch2_trans_inconsistent_on(bch2_err_matches(ret, ENOENT), trans,
-			"pointer to nonexistent stripe %llu",
-			(u64) p.ec.idx);
-		goto err;
-	}
+		if (!bch2_ptr_matches_stripe(&s->v, p)) {
+			bch2_trans_inconsistent(trans,
+				"stripe pointer doesn't match stripe %llu",
+				(u64) p.ec.idx);
+			ret = -EIO;
+			goto err;
+		}
 
-	if (!bch2_ptr_matches_stripe(&s->v, p)) {
-		bch2_trans_inconsistent(trans,
-			"stripe pointer doesn't match stripe %llu",
-			(u64) p.ec.idx);
-		ret = -EIO;
-		goto err;
+		stripe_blockcount_set(&s->v, p.ec.block,
+			stripe_blockcount_get(&s->v, p.ec.block) +
+			sectors);
+
+		struct bch_replicas_padded r;
+		bch2_bkey_to_replicas(&r.e, bkey_i_to_s_c(&s->k_i));
+		r.e.data_type = data_type;
+		ret = bch2_update_replicas_list(trans, &r.e, sectors);
+err:
+		bch2_trans_iter_exit(trans, &iter);
+		return ret;
 	}
 
-	stripe_blockcount_set(&s->v, p.ec.block,
-		stripe_blockcount_get(&s->v, p.ec.block) +
-		sectors);
+	if (flags & BTREE_TRIGGER_GC) {
+		struct bch_fs *c = trans->c;
 
-	bch2_bkey_to_replicas(&r.e, bkey_i_to_s_c(&s->k_i));
-	r.e.data_type = data_type;
-	ret = update_replicas_list(trans, &r.e, sectors);
-err:
-	bch2_trans_iter_exit(trans, &iter);
-	return ret;
+		BUG_ON(!(flags & BTREE_TRIGGER_GC));
+
+		struct gc_stripe *m = genradix_ptr_alloc(&c->gc_stripes, p.ec.idx, GFP_KERNEL);
+		if (!m) {
+			bch_err(c, "error allocating memory for gc_stripes, idx %llu",
+				(u64) p.ec.idx);
+			return -BCH_ERR_ENOMEM_mark_stripe_ptr;
+		}
+
+		mutex_lock(&c->ec_stripes_heap_lock);
+
+		if (!m || !m->alive) {
+			mutex_unlock(&c->ec_stripes_heap_lock);
+			struct printbuf buf = PRINTBUF;
+			bch2_bkey_val_to_text(&buf, c, k);
+			bch_err_ratelimited(c, "pointer to nonexistent stripe %llu\n  while marking %s",
+					    (u64) p.ec.idx, buf.buf);
+			printbuf_exit(&buf);
+			bch2_inconsistent_error(c);
+			return -EIO;
+		}
+
+		m->block_sectors[p.ec.block] += sectors;
+
+		struct bch_replicas_padded r = m->r;
+		mutex_unlock(&c->ec_stripes_heap_lock);
+
+		r.e.data_type = data_type;
+		bch2_update_replicas(c, k, &r.e, sectors, trans->journal_res.seq, true);
+	}
+
+	return 0;
 }
 
-static int __trans_mark_extent(struct btree_trans *trans,
-			       enum btree_id btree_id, unsigned level,
-			       struct bkey_s_c k, unsigned flags)
+static int __trigger_extent(struct btree_trans *trans,
+			    enum btree_id btree_id, unsigned level,
+			    struct bkey_s_c k, unsigned flags)
 {
+	bool gc = flags & BTREE_TRIGGER_GC;
 	struct bch_fs *c = trans->c;
 	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
 	const union bch_extent_entry *entry;
@@ -1488,11 +958,7 @@ static int __trans_mark_extent(struct btree_trans *trans,
 	enum bch_data_type data_type = bkey_is_btree_ptr(k.k)
 		? BCH_DATA_btree
 		: BCH_DATA_user;
-	s64 sectors = bkey_is_btree_ptr(k.k)
-		? btree_sectors(c)
-		: k.k->size;
 	s64 dirty_sectors = 0;
-	bool stale;
 	int ret = 0;
 
 	r.e.data_type	= data_type;
@@ -1500,21 +966,20 @@ static int __trans_mark_extent(struct btree_trans *trans,
 	r.e.nr_required	= 1;
 
 	bkey_for_each_ptr_decode(k.k, ptrs, p, entry) {
-		s64 disk_sectors = ptr_disk_sectors(sectors, p);
-
-		if (flags & BTREE_TRIGGER_OVERWRITE)
-			disk_sectors = -disk_sectors;
-
-		ret = bch2_trans_mark_pointer(trans, btree_id, level, k, p, flags);
+		s64 disk_sectors;
+		ret = bch2_trigger_pointer(trans, btree_id, level, k, p, &disk_sectors, flags);
 		if (ret < 0)
 			return ret;
 
-		stale = ret > 0;
+		bool stale = ret > 0;
 
 		if (p.ptr.cached) {
 			if (!stale) {
-				ret = update_cached_sectors_list(trans, p.ptr.dev,
-								 disk_sectors);
+				ret = !gc
+					? bch2_update_cached_sectors_list(trans, p.ptr.dev, disk_sectors)
+					: update_cached_sectors(c, k, p.ptr.dev, disk_sectors, 0, true);
+				bch2_fs_fatal_err_on(ret && gc, c, "%s(): no replicas entry while updating cached sectors",
+						     __func__);
 				if (ret)
 					return ret;
 			}
@@ -1522,324 +987,122 @@ static int __trans_mark_extent(struct btree_trans *trans,
 			dirty_sectors	       += disk_sectors;
 			r.e.devs[r.e.nr_devs++]	= p.ptr.dev;
 		} else {
-			ret = bch2_trans_mark_stripe_ptr(trans, p,
-					disk_sectors, data_type);
+			ret = bch2_trigger_stripe_ptr(trans, k, p, data_type, disk_sectors, flags);
 			if (ret)
 				return ret;
 
+			/*
+			 * There may be other dirty pointers in this extent, but
+			 * if so they're not required for mounting if we have an
+			 * erasure coded pointer in this extent:
+			 */
 			r.e.nr_required = 0;
 		}
 	}
 
-	if (r.e.nr_devs)
-		ret = update_replicas_list(trans, &r.e, dirty_sectors);
-
-	return ret;
-}
-
-int bch2_trans_mark_extent(struct btree_trans *trans,
-			   enum btree_id btree_id, unsigned level,
-			   struct bkey_s_c old, struct bkey_i *new,
-			   unsigned flags)
-{
-	struct bch_fs *c = trans->c;
-	int mod = (int) bch2_bkey_needs_rebalance(c, bkey_i_to_s_c(new)) -
-		  (int) bch2_bkey_needs_rebalance(c, old);
+	if (r.e.nr_devs) {
+		ret = !gc
+			? bch2_update_replicas_list(trans, &r.e, dirty_sectors)
+			: bch2_update_replicas(c, k, &r.e, dirty_sectors, 0, true);
+		if (unlikely(ret && gc)) {
+			struct printbuf buf = PRINTBUF;
 
-	if (mod) {
-		int ret = bch2_btree_bit_mod(trans, BTREE_ID_rebalance_work, new->k.p, mod > 0);
+			bch2_bkey_val_to_text(&buf, c, k);
+			bch2_fs_fatal_error(c, "%s(): no replicas entry for %s", __func__, buf.buf);
+			printbuf_exit(&buf);
+		}
 		if (ret)
 			return ret;
 	}
 
-	return trigger_run_overwrite_then_insert(__trans_mark_extent, trans, btree_id, level, old, new, flags);
-}
-
-static int bch2_trans_mark_stripe_bucket(struct btree_trans *trans,
-					 struct bkey_s_c_stripe s,
-					 unsigned idx, bool deleting)
-{
-	struct bch_fs *c = trans->c;
-	const struct bch_extent_ptr *ptr = &s.v->ptrs[idx];
-	struct btree_iter iter;
-	struct bkey_i_alloc_v4 *a;
-	enum bch_data_type data_type = idx >= s.v->nr_blocks - s.v->nr_redundant
-		? BCH_DATA_parity : 0;
-	s64 sectors = data_type ? le16_to_cpu(s.v->sectors) : 0;
-	int ret = 0;
-
-	if (deleting)
-		sectors = -sectors;
-
-	a = bch2_trans_start_alloc_update(trans, &iter, PTR_BUCKET_POS(c, ptr));
-	if (IS_ERR(a))
-		return PTR_ERR(a);
-
-	ret = check_bucket_ref(trans, s.s_c, ptr, sectors, data_type,
-			       a->v.gen, a->v.data_type,
-			       a->v.dirty_sectors, a->v.cached_sectors);
-	if (ret)
-		goto err;
-
-	if (!deleting) {
-		if (bch2_trans_inconsistent_on(a->v.stripe ||
-					       a->v.stripe_redundancy, trans,
-				"bucket %llu:%llu gen %u data type %s dirty_sectors %u: multiple stripes using same bucket (%u, %llu)",
-				iter.pos.inode, iter.pos.offset, a->v.gen,
-				bch2_data_types[a->v.data_type],
-				a->v.dirty_sectors,
-				a->v.stripe, s.k->p.offset)) {
-			ret = -EIO;
-			goto err;
-		}
-
-		if (bch2_trans_inconsistent_on(data_type && a->v.dirty_sectors, trans,
-				"bucket %llu:%llu gen %u data type %s dirty_sectors %u: data already in stripe bucket %llu",
-				iter.pos.inode, iter.pos.offset, a->v.gen,
-				bch2_data_types[a->v.data_type],
-				a->v.dirty_sectors,
-				s.k->p.offset)) {
-			ret = -EIO;
-			goto err;
-		}
-
-		a->v.stripe		= s.k->p.offset;
-		a->v.stripe_redundancy	= s.v->nr_redundant;
-		a->v.data_type		= BCH_DATA_stripe;
-	} else {
-		if (bch2_trans_inconsistent_on(a->v.stripe != s.k->p.offset ||
-					       a->v.stripe_redundancy != s.v->nr_redundant, trans,
-				"bucket %llu:%llu gen %u: not marked as stripe when deleting stripe %llu (got %u)",
-				iter.pos.inode, iter.pos.offset, a->v.gen,
-				s.k->p.offset, a->v.stripe)) {
-			ret = -EIO;
-			goto err;
-		}
-
-		a->v.stripe		= 0;
-		a->v.stripe_redundancy	= 0;
-		a->v.data_type		= alloc_data_type(a->v, BCH_DATA_user);
-	}
-
-	a->v.dirty_sectors += sectors;
-	if (data_type)
-		a->v.data_type = !deleting ? data_type : 0;
-
-	ret = bch2_trans_update(trans, &iter, &a->k_i, 0);
-	if (ret)
-		goto err;
-err:
-	bch2_trans_iter_exit(trans, &iter);
-	return ret;
+	return 0;
 }
 
-int bch2_trans_mark_stripe(struct btree_trans *trans,
-			   enum btree_id btree_id, unsigned level,
-			   struct bkey_s_c old, struct bkey_i *new,
-			   unsigned flags)
+int bch2_trigger_extent(struct btree_trans *trans,
+			enum btree_id btree_id, unsigned level,
+			struct bkey_s_c old, struct bkey_s new,
+			unsigned flags)
 {
-	const struct bch_stripe *old_s = NULL;
-	struct bch_stripe *new_s = NULL;
-	struct bch_replicas_padded r;
-	unsigned i, nr_blocks;
-	int ret = 0;
-
-	if (old.k->type == KEY_TYPE_stripe)
-		old_s = bkey_s_c_to_stripe(old).v;
-	if (new->k.type == KEY_TYPE_stripe)
-		new_s = &bkey_i_to_stripe(new)->v;
-
-	/*
-	 * If the pointers aren't changing, we don't need to do anything:
-	 */
-	if (new_s && old_s &&
-	    new_s->nr_blocks	== old_s->nr_blocks &&
-	    new_s->nr_redundant	== old_s->nr_redundant &&
-	    !memcmp(old_s->ptrs, new_s->ptrs,
-		    new_s->nr_blocks * sizeof(struct bch_extent_ptr)))
+	struct bkey_ptrs_c new_ptrs = bch2_bkey_ptrs_c(new.s_c);
+	struct bkey_ptrs_c old_ptrs = bch2_bkey_ptrs_c(old);
+	unsigned new_ptrs_bytes = (void *) new_ptrs.end - (void *) new_ptrs.start;
+	unsigned old_ptrs_bytes = (void *) old_ptrs.end - (void *) old_ptrs.start;
+
+	/* if pointers aren't changing - nothing to do: */
+	if (new_ptrs_bytes == old_ptrs_bytes &&
+	    !memcmp(new_ptrs.start,
+		    old_ptrs.start,
+		    new_ptrs_bytes))
 		return 0;
 
-	BUG_ON(new_s && old_s &&
-	       (new_s->nr_blocks	!= old_s->nr_blocks ||
-		new_s->nr_redundant	!= old_s->nr_redundant));
-
-	nr_blocks = new_s ? new_s->nr_blocks : old_s->nr_blocks;
-
-	if (new_s) {
-		s64 sectors = le16_to_cpu(new_s->sectors);
-
-		bch2_bkey_to_replicas(&r.e, bkey_i_to_s_c(new));
-		ret = update_replicas_list(trans, &r.e, sectors * new_s->nr_redundant);
-		if (ret)
-			return ret;
-	}
-
-	if (old_s) {
-		s64 sectors = -((s64) le16_to_cpu(old_s->sectors));
-
-		bch2_bkey_to_replicas(&r.e, old);
-		ret = update_replicas_list(trans, &r.e, sectors * old_s->nr_redundant);
-		if (ret)
-			return ret;
-	}
+	if (flags & BTREE_TRIGGER_TRANSACTIONAL) {
+		struct bch_fs *c = trans->c;
+		int mod = (int) bch2_bkey_needs_rebalance(c, new.s_c) -
+			  (int) bch2_bkey_needs_rebalance(c, old);
 
-	for (i = 0; i < nr_blocks; i++) {
-		if (new_s && old_s &&
-		    !memcmp(&new_s->ptrs[i],
-			    &old_s->ptrs[i],
-			    sizeof(new_s->ptrs[i])))
-			continue;
-
-		if (new_s) {
-			ret = bch2_trans_mark_stripe_bucket(trans,
-					bkey_i_to_s_c_stripe(new), i, false);
+		if (mod) {
+			int ret = bch2_btree_bit_mod(trans, BTREE_ID_rebalance_work, new.k->p, mod > 0);
 			if (ret)
-				break;
-		}
-
-		if (old_s) {
-			ret = bch2_trans_mark_stripe_bucket(trans,
-					bkey_s_c_to_stripe(old), i, true);
-			if (ret)
-				break;
+				return ret;
 		}
 	}
 
-	return ret;
+	if (flags & (BTREE_TRIGGER_TRANSACTIONAL|BTREE_TRIGGER_GC))
+		return trigger_run_overwrite_then_insert(__trigger_extent, trans, btree_id, level, old, new, flags);
+
+	return 0;
 }
 
-static int __trans_mark_reservation(struct btree_trans *trans,
-				    enum btree_id btree_id, unsigned level,
-				    struct bkey_s_c k, unsigned flags)
+/* KEY_TYPE_reservation */
+
+static int __trigger_reservation(struct btree_trans *trans,
+				 enum btree_id btree_id, unsigned level,
+				 struct bkey_s_c k, unsigned flags)
 {
+	struct bch_fs *c = trans->c;
 	unsigned replicas = bkey_s_c_to_reservation(k).v->nr_replicas;
-	s64 sectors = (s64) k.k->size;
-	struct replicas_delta_list *d;
-	int ret;
+	s64 sectors = (s64) k.k->size * replicas;
 
 	if (flags & BTREE_TRIGGER_OVERWRITE)
 		sectors = -sectors;
-	sectors *= replicas;
-
-	ret = bch2_replicas_deltas_realloc(trans, 0);
-	if (ret)
-		return ret;
 
-	d = trans->fs_usage_deltas;
-	replicas = clamp_t(unsigned, replicas, 1,
-			   ARRAY_SIZE(d->persistent_reserved));
-
-	d->persistent_reserved[replicas - 1] += sectors;
-	return 0;
-}
-
-int bch2_trans_mark_reservation(struct btree_trans *trans,
-				enum btree_id btree_id, unsigned level,
-				struct bkey_s_c old,
-				struct bkey_i *new,
-				unsigned flags)
-{
-	return trigger_run_overwrite_then_insert(__trans_mark_reservation, trans, btree_id, level, old, new, flags);
-}
-
-static int trans_mark_reflink_p_segment(struct btree_trans *trans,
-			struct bkey_s_c_reflink_p p,
-			u64 *idx, unsigned flags)
-{
-	struct bch_fs *c = trans->c;
-	struct btree_iter iter;
-	struct bkey_i *k;
-	__le64 *refcount;
-	int add = !(flags & BTREE_TRIGGER_OVERWRITE) ? 1 : -1;
-	struct printbuf buf = PRINTBUF;
-	int ret;
+	if (flags & BTREE_TRIGGER_TRANSACTIONAL) {
+		int ret = bch2_replicas_deltas_realloc(trans, 0);
+		if (ret)
+			return ret;
 
-	k = bch2_bkey_get_mut_noupdate(trans, &iter,
-			BTREE_ID_reflink, POS(0, *idx),
-			BTREE_ITER_WITH_UPDATES);
-	ret = PTR_ERR_OR_ZERO(k);
-	if (ret)
-		goto err;
+		struct replicas_delta_list *d = trans->fs_usage_deltas;
+		replicas = min(replicas, ARRAY_SIZE(d->persistent_reserved));
 
-	refcount = bkey_refcount(k);
-	if (!refcount) {
-		bch2_bkey_val_to_text(&buf, c, p.s_c);
-		bch2_trans_inconsistent(trans,
-			"nonexistent indirect extent at %llu while marking\n  %s",
-			*idx, buf.buf);
-		ret = -EIO;
-		goto err;
+		d->persistent_reserved[replicas - 1] += sectors;
 	}
 
-	if (!*refcount && (flags & BTREE_TRIGGER_OVERWRITE)) {
-		bch2_bkey_val_to_text(&buf, c, p.s_c);
-		bch2_trans_inconsistent(trans,
-			"indirect extent refcount underflow at %llu while marking\n  %s",
-			*idx, buf.buf);
-		ret = -EIO;
-		goto err;
-	}
+	if (flags & BTREE_TRIGGER_GC) {
+		percpu_down_read(&c->mark_lock);
+		preempt_disable();
 
-	if (flags & BTREE_TRIGGER_INSERT) {
-		struct bch_reflink_p *v = (struct bch_reflink_p *) p.v;
-		u64 pad;
+		struct bch_fs_usage *fs_usage = this_cpu_ptr(c->usage_gc);
 
-		pad = max_t(s64, le32_to_cpu(v->front_pad),
-			    le64_to_cpu(v->idx) - bkey_start_offset(&k->k));
-		BUG_ON(pad > U32_MAX);
-		v->front_pad = cpu_to_le32(pad);
+		replicas = min(replicas, ARRAY_SIZE(fs_usage->persistent_reserved));
+		fs_usage->reserved				+= sectors;
+		fs_usage->persistent_reserved[replicas - 1]	+= sectors;
 
-		pad = max_t(s64, le32_to_cpu(v->back_pad),
-			    k->k.p.offset - p.k->size - le64_to_cpu(v->idx));
-		BUG_ON(pad > U32_MAX);
-		v->back_pad = cpu_to_le32(pad);
+		preempt_enable();
+		percpu_up_read(&c->mark_lock);
 	}
 
-	le64_add_cpu(refcount, add);
-
-	bch2_btree_iter_set_pos_to_extent_start(&iter);
-	ret = bch2_trans_update(trans, &iter, k, 0);
-	if (ret)
-		goto err;
-
-	*idx = k->k.p.offset;
-err:
-	bch2_trans_iter_exit(trans, &iter);
-	printbuf_exit(&buf);
-	return ret;
+	return 0;
 }
 
-static int __trans_mark_reflink_p(struct btree_trans *trans,
-				enum btree_id btree_id, unsigned level,
-				struct bkey_s_c k, unsigned flags)
+int bch2_trigger_reservation(struct btree_trans *trans,
+			  enum btree_id btree_id, unsigned level,
+			  struct bkey_s_c old, struct bkey_s new,
+			  unsigned flags)
 {
-	struct bkey_s_c_reflink_p p = bkey_s_c_to_reflink_p(k);
-	u64 idx, end_idx;
-	int ret = 0;
-
-	idx	= le64_to_cpu(p.v->idx) - le32_to_cpu(p.v->front_pad);
-	end_idx = le64_to_cpu(p.v->idx) + p.k->size +
-		le32_to_cpu(p.v->back_pad);
-
-	while (idx < end_idx && !ret)
-		ret = trans_mark_reflink_p_segment(trans, p, &idx, flags);
-	return ret;
+	return trigger_run_overwrite_then_insert(__trigger_reservation, trans, btree_id, level, old, new, flags);
 }
 
-int bch2_trans_mark_reflink_p(struct btree_trans *trans,
-			      enum btree_id btree_id, unsigned level,
-			      struct bkey_s_c old,
-			      struct bkey_i *new,
-			      unsigned flags)
-{
-	if (flags & BTREE_TRIGGER_INSERT) {
-		struct bch_reflink_p *v = &bkey_i_to_reflink_p(new)->v;
-
-		v->front_pad = v->back_pad = 0;
-	}
-
-	return trigger_run_overwrite_then_insert(__trans_mark_reflink_p, trans, btree_id, level, old, new, flags);
-}
+/* Mark superblocks: */
 
 static int __bch2_trans_mark_metadata_bucket(struct btree_trans *trans,
 				    struct bch_dev *ca, size_t b,
@@ -1970,17 +1233,13 @@ int bch2_trans_mark_dev_sb(struct bch_fs *c, struct bch_dev *ca)
 {
 	int ret = bch2_trans_run(c, __bch2_trans_mark_dev_sb(trans, ca));
 
-	if (ret)
-		bch_err_fn(c, ret);
+	bch_err_fn(c, ret);
 	return ret;
 }
 
 int bch2_trans_mark_dev_sbs(struct bch_fs *c)
 {
-	struct bch_dev *ca;
-	unsigned i;
-
-	for_each_online_member(ca, c, i) {
+	for_each_online_member(c, ca) {
 		int ret = bch2_trans_mark_dev_sb(c, ca);
 		if (ret) {
 			percpu_ref_put(&ca->ref);
@@ -2091,8 +1350,6 @@ int bch2_dev_buckets_resize(struct bch_fs *c, struct bch_dev *ca, u64 nbuckets)
 	bucket_gens->first_bucket = ca->mi.first_bucket;
 	bucket_gens->nbuckets	= nbuckets;
 
-	bch2_copygc_stop(c);
-
 	if (resize) {
 		down_write(&c->gc_lock);
 		down_write(&ca->bucket_lock);
diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h
index 21f6cb356921..2c95cc5d86be 100644
--- a/fs/bcachefs/buckets.h
+++ b/fs/bcachefs/buckets.h
@@ -203,6 +203,7 @@ static inline struct bch_dev_usage bch2_dev_usage_read(struct bch_dev *ca)
 }
 
 void bch2_dev_usage_init(struct bch_dev *);
+void bch2_dev_usage_to_text(struct printbuf *, struct bch_dev_usage *);
 
 static inline u64 bch2_dev_buckets_reserved(struct bch_dev *ca, enum bch_watermark watermark)
 {
@@ -301,6 +302,12 @@ u64 bch2_fs_sectors_used(struct bch_fs *, struct bch_fs_usage_online *);
 struct bch_fs_usage_short
 bch2_fs_usage_read_short(struct bch_fs *);
 
+void bch2_dev_usage_update(struct bch_fs *, struct bch_dev *,
+			   const struct bch_alloc_v4 *,
+			   const struct bch_alloc_v4 *, u64, bool);
+void bch2_dev_usage_update_m(struct bch_fs *, struct bch_dev *,
+			     struct bucket *, struct bucket *);
+
 /* key/bucket marking: */
 
 static inline struct bch_fs_usage *fs_usage_ptr(struct bch_fs *c,
@@ -315,44 +322,40 @@ static inline struct bch_fs_usage *fs_usage_ptr(struct bch_fs *c,
 			    : c->usage[journal_seq & JOURNAL_BUF_MASK]);
 }
 
+int bch2_update_replicas(struct bch_fs *, struct bkey_s_c,
+			 struct bch_replicas_entry_v1 *, s64,
+			 unsigned, bool);
+int bch2_update_replicas_list(struct btree_trans *,
+			 struct bch_replicas_entry_v1 *, s64);
+int bch2_update_cached_sectors_list(struct btree_trans *, unsigned, s64);
 int bch2_replicas_deltas_realloc(struct btree_trans *, unsigned);
 
 void bch2_fs_usage_initialize(struct bch_fs *);
 
+int bch2_check_bucket_ref(struct btree_trans *, struct bkey_s_c,
+			  const struct bch_extent_ptr *,
+			  s64, enum bch_data_type, u8, u8, u32);
+
 int bch2_mark_metadata_bucket(struct bch_fs *, struct bch_dev *,
 			      size_t, enum bch_data_type, unsigned,
 			      struct gc_pos, unsigned);
 
-int bch2_mark_alloc(struct btree_trans *, enum btree_id, unsigned,
-		    struct bkey_s_c, struct bkey_s_c, unsigned);
-int bch2_mark_extent(struct btree_trans *, enum btree_id, unsigned,
-		     struct bkey_s_c, struct bkey_s_c, unsigned);
-int bch2_mark_stripe(struct btree_trans *, enum btree_id, unsigned,
-		     struct bkey_s_c, struct bkey_s_c, unsigned);
-int bch2_mark_reservation(struct btree_trans *, enum btree_id, unsigned,
-			  struct bkey_s_c, struct bkey_s_c, unsigned);
-int bch2_mark_reflink_p(struct btree_trans *, enum btree_id, unsigned,
-			struct bkey_s_c, struct bkey_s_c, unsigned);
-
-int bch2_trans_mark_extent(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_i *, unsigned);
-int bch2_trans_mark_stripe(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_i *, unsigned);
-int bch2_trans_mark_reservation(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_i *, unsigned);
-int bch2_trans_mark_reflink_p(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_i *, unsigned);
-
-#define mem_trigger_run_overwrite_then_insert(_fn, _trans, _btree_id, _level, _old, _new, _flags)\
+int bch2_trigger_extent(struct btree_trans *, enum btree_id, unsigned,
+			struct bkey_s_c, struct bkey_s, unsigned);
+int bch2_trigger_reservation(struct btree_trans *, enum btree_id, unsigned,
+			  struct bkey_s_c, struct bkey_s, unsigned);
+
+#define trigger_run_overwrite_then_insert(_fn, _trans, _btree_id, _level, _old, _new, _flags)\
 ({												\
 	int ret = 0;										\
 												\
 	if (_old.k->type)									\
 		ret = _fn(_trans, _btree_id, _level, _old, _flags & ~BTREE_TRIGGER_INSERT);	\
 	if (!ret && _new.k->type)								\
-		ret = _fn(_trans, _btree_id, _level, _new, _flags & ~BTREE_TRIGGER_OVERWRITE);	\
+		ret = _fn(_trans, _btree_id, _level, _new.s_c, _flags & ~BTREE_TRIGGER_OVERWRITE);\
 	ret;											\
 })
 
-#define trigger_run_overwrite_then_insert(_fn, _trans, _btree_id, _level, _old, _new, _flags)	\
-	mem_trigger_run_overwrite_then_insert(_fn, _trans, _btree_id, _level, _old, bkey_i_to_s_c(_new), _flags)
-
 void bch2_trans_fs_usage_revert(struct btree_trans *, struct replicas_delta_list *);
 int bch2_trans_fs_usage_apply(struct btree_trans *, struct replicas_delta_list *);
 
diff --git a/fs/bcachefs/buckets_types.h b/fs/bcachefs/buckets_types.h
index 2a9dab9006ef..783f71017204 100644
--- a/fs/bcachefs/buckets_types.h
+++ b/fs/bcachefs/buckets_types.h
@@ -33,8 +33,6 @@ struct bucket_gens {
 };
 
 struct bch_dev_usage {
-	u64			buckets_ec;
-
 	struct {
 		u64		buckets;
 		u64		sectors; /* _compressed_ sectors: */
diff --git a/fs/bcachefs/chardev.c b/fs/bcachefs/chardev.c
index 4bb88aefed12..226b39c17667 100644
--- a/fs/bcachefs/chardev.c
+++ b/fs/bcachefs/chardev.c
@@ -7,22 +7,27 @@
 #include "chardev.h"
 #include "journal.h"
 #include "move.h"
+#include "recovery.h"
 #include "replicas.h"
 #include "super.h"
 #include "super-io.h"
+#include "thread_with_file.h"
 
-#include <linux/anon_inodes.h>
 #include <linux/cdev.h>
 #include <linux/device.h>
-#include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/ioctl.h>
-#include <linux/kthread.h>
 #include <linux/major.h>
 #include <linux/sched/task.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 
+__must_check
+static int copy_to_user_errcode(void __user *to, const void *from, unsigned long n)
+{
+	return copy_to_user(to, from, n) ? -EFAULT : 0;
+}
+
 /* returns with ref on ca->ref */
 static struct bch_dev *bch2_device_lookup(struct bch_fs *c, u64 dev,
 					  unsigned flags)
@@ -132,8 +137,106 @@ static long bch2_ioctl_incremental(struct bch_ioctl_incremental __user *user_arg
 }
 #endif
 
+struct fsck_thread {
+	struct thread_with_stdio thr;
+	struct bch_fs		*c;
+	char			**devs;
+	size_t			nr_devs;
+	struct bch_opts		opts;
+};
+
+static void bch2_fsck_thread_exit(struct thread_with_stdio *_thr)
+{
+	struct fsck_thread *thr = container_of(_thr, struct fsck_thread, thr);
+	if (thr->devs)
+		for (size_t i = 0; i < thr->nr_devs; i++)
+			kfree(thr->devs[i]);
+	kfree(thr->devs);
+	kfree(thr);
+}
+
+static int bch2_fsck_offline_thread_fn(void *arg)
+{
+	struct fsck_thread *thr = container_of(arg, struct fsck_thread, thr);
+	struct bch_fs *c = bch2_fs_open(thr->devs, thr->nr_devs, thr->opts);
+
+	thr->thr.thr.ret = PTR_ERR_OR_ZERO(c);
+	if (!thr->thr.thr.ret)
+		bch2_fs_stop(c);
+
+	thread_with_stdio_done(&thr->thr);
+	return 0;
+}
+
+static long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *user_arg)
+{
+	struct bch_ioctl_fsck_offline arg;
+	struct fsck_thread *thr = NULL;
+	u64 *devs = NULL;
+	long ret = 0;
+
+	if (copy_from_user(&arg, user_arg, sizeof(arg)))
+		return -EFAULT;
+
+	if (arg.flags)
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!(devs = kcalloc(arg.nr_devs, sizeof(*devs), GFP_KERNEL)) ||
+	    !(thr = kzalloc(sizeof(*thr), GFP_KERNEL)) ||
+	    !(thr->devs = kcalloc(arg.nr_devs, sizeof(*thr->devs), GFP_KERNEL))) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	thr->opts = bch2_opts_empty();
+	thr->nr_devs = arg.nr_devs;
+
+	if (copy_from_user(devs, &user_arg->devs[0],
+			   array_size(sizeof(user_arg->devs[0]), arg.nr_devs))) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	for (size_t i = 0; i < arg.nr_devs; i++) {
+		thr->devs[i] = strndup_user((char __user *)(unsigned long) devs[i], PATH_MAX);
+		ret = PTR_ERR_OR_ZERO(thr->devs[i]);
+		if (ret)
+			goto err;
+	}
+
+	if (arg.opts) {
+		char *optstr = strndup_user((char __user *)(unsigned long) arg.opts, 1 << 16);
+
+		ret =   PTR_ERR_OR_ZERO(optstr) ?:
+			bch2_parse_mount_opts(NULL, &thr->opts, optstr);
+		kfree(optstr);
+
+		if (ret)
+			goto err;
+	}
+
+	opt_set(thr->opts, stdio, (u64)(unsigned long)&thr->thr.stdio);
+
+	ret = bch2_run_thread_with_stdio(&thr->thr,
+			bch2_fsck_thread_exit,
+			bch2_fsck_offline_thread_fn);
+err:
+	if (ret < 0) {
+		if (thr)
+			bch2_fsck_thread_exit(&thr->thr);
+		pr_err("ret %s", bch2_err_str(ret));
+	}
+	kfree(devs);
+	return ret;
+}
+
 static long bch2_global_ioctl(unsigned cmd, void __user *arg)
 {
+	long ret;
+
 	switch (cmd) {
 #if 0
 	case BCH_IOCTL_ASSEMBLE:
@@ -141,18 +244,25 @@ static long bch2_global_ioctl(unsigned cmd, void __user *arg)
 	case BCH_IOCTL_INCREMENTAL:
 		return bch2_ioctl_incremental(arg);
 #endif
+	case BCH_IOCTL_FSCK_OFFLINE: {
+		ret = bch2_ioctl_fsck_offline(arg);
+		break;
+	}
 	default:
-		return -ENOTTY;
+		ret = -ENOTTY;
+		break;
 	}
+
+	if (ret < 0)
+		ret = bch2_err_class(ret);
+	return ret;
 }
 
 static long bch2_ioctl_query_uuid(struct bch_fs *c,
 			struct bch_ioctl_query_uuid __user *user_arg)
 {
-	if (copy_to_user(&user_arg->uuid, &c->sb.user_uuid,
-			 sizeof(c->sb.user_uuid)))
-		return -EFAULT;
-	return 0;
+	return copy_to_user_errcode(&user_arg->uuid, &c->sb.user_uuid,
+				    sizeof(c->sb.user_uuid));
 }
 
 #if 0
@@ -295,31 +405,27 @@ static long bch2_ioctl_disk_set_state(struct bch_fs *c,
 }
 
 struct bch_data_ctx {
+	struct thread_with_file		thr;
+
 	struct bch_fs			*c;
 	struct bch_ioctl_data		arg;
 	struct bch_move_stats		stats;
-
-	int				ret;
-
-	struct task_struct		*thread;
 };
 
 static int bch2_data_thread(void *arg)
 {
-	struct bch_data_ctx *ctx = arg;
-
-	ctx->ret = bch2_data_job(ctx->c, &ctx->stats, ctx->arg);
+	struct bch_data_ctx *ctx = container_of(arg, struct bch_data_ctx, thr);
 
+	ctx->thr.ret = bch2_data_job(ctx->c, &ctx->stats, ctx->arg);
 	ctx->stats.data_type = U8_MAX;
 	return 0;
 }
 
 static int bch2_data_job_release(struct inode *inode, struct file *file)
 {
-	struct bch_data_ctx *ctx = file->private_data;
+	struct bch_data_ctx *ctx = container_of(file->private_data, struct bch_data_ctx, thr);
 
-	kthread_stop(ctx->thread);
-	put_task_struct(ctx->thread);
+	bch2_thread_with_file_exit(&ctx->thr);
 	kfree(ctx);
 	return 0;
 }
@@ -327,7 +433,7 @@ static int bch2_data_job_release(struct inode *inode, struct file *file)
 static ssize_t bch2_data_job_read(struct file *file, char __user *buf,
 				  size_t len, loff_t *ppos)
 {
-	struct bch_data_ctx *ctx = file->private_data;
+	struct bch_data_ctx *ctx = container_of(file->private_data, struct bch_data_ctx, thr);
 	struct bch_fs *c = ctx->c;
 	struct bch_ioctl_data_event e = {
 		.type			= BCH_DATA_EVENT_PROGRESS,
@@ -341,10 +447,7 @@ static ssize_t bch2_data_job_read(struct file *file, char __user *buf,
 	if (len < sizeof(e))
 		return -EINVAL;
 
-	if (copy_to_user(buf, &e, sizeof(e)))
-		return -EFAULT;
-
-	return sizeof(e);
+	return copy_to_user_errcode(buf, &e, sizeof(e)) ?: sizeof(e);
 }
 
 static const struct file_operations bcachefs_data_ops = {
@@ -356,10 +459,8 @@ static const struct file_operations bcachefs_data_ops = {
 static long bch2_ioctl_data(struct bch_fs *c,
 			    struct bch_ioctl_data arg)
 {
-	struct bch_data_ctx *ctx = NULL;
-	struct file *file = NULL;
-	unsigned flags = O_RDONLY|O_CLOEXEC|O_NONBLOCK;
-	int ret, fd = -1;
+	struct bch_data_ctx *ctx;
+	int ret;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -374,36 +475,11 @@ static long bch2_ioctl_data(struct bch_fs *c,
 	ctx->c = c;
 	ctx->arg = arg;
 
-	ctx->thread = kthread_create(bch2_data_thread, ctx,
-				     "bch-data/%s", c->name);
-	if (IS_ERR(ctx->thread)) {
-		ret = PTR_ERR(ctx->thread);
-		goto err;
-	}
-
-	ret = get_unused_fd_flags(flags);
+	ret = bch2_run_thread_with_file(&ctx->thr,
+			&bcachefs_data_ops,
+			bch2_data_thread);
 	if (ret < 0)
-		goto err;
-	fd = ret;
-
-	file = anon_inode_getfile("[bcachefs]", &bcachefs_data_ops, ctx, flags);
-	if (IS_ERR(file)) {
-		ret = PTR_ERR(file);
-		goto err;
-	}
-
-	fd_install(fd, file);
-
-	get_task_struct(ctx->thread);
-	wake_up_process(ctx->thread);
-
-	return fd;
-err:
-	if (fd >= 0)
-		put_unused_fd(fd);
-	if (!IS_ERR_OR_NULL(ctx->thread))
-		kthread_stop(ctx->thread);
-	kfree(ctx);
+		kfree(ctx);
 	return ret;
 }
 
@@ -417,7 +493,7 @@ static long bch2_ioctl_fs_usage(struct bch_fs *c,
 	unsigned i;
 	int ret = 0;
 
-	if (!test_bit(BCH_FS_STARTED, &c->flags))
+	if (!test_bit(BCH_FS_started, &c->flags))
 		return -EINVAL;
 
 	if (get_user(replica_entries_bytes, &user_arg->replica_entries_bytes))
@@ -444,7 +520,7 @@ static long bch2_ioctl_fs_usage(struct bch_fs *c,
 	dst_end = (void *) arg->replicas + replica_entries_bytes;
 
 	for (i = 0; i < c->replicas.nr; i++) {
-		struct bch_replicas_entry *src_e =
+		struct bch_replicas_entry_v1 *src_e =
 			cpu_replicas_entry(&c->replicas, i);
 
 		/* check that we have enough space for one replicas entry */
@@ -474,14 +550,15 @@ static long bch2_ioctl_fs_usage(struct bch_fs *c,
 
 	if (ret)
 		goto err;
-	if (copy_to_user(user_arg, arg,
-			 sizeof(*arg) + arg->replica_entries_bytes))
-		ret = -EFAULT;
+
+	ret = copy_to_user_errcode(user_arg, arg,
+			sizeof(*arg) + arg->replica_entries_bytes);
 err:
 	kfree(arg);
 	return ret;
 }
 
+/* obsolete, didn't allow for new data types: */
 static long bch2_ioctl_dev_usage(struct bch_fs *c,
 				 struct bch_ioctl_dev_usage __user *user_arg)
 {
@@ -490,7 +567,7 @@ static long bch2_ioctl_dev_usage(struct bch_fs *c,
 	struct bch_dev *ca;
 	unsigned i;
 
-	if (!test_bit(BCH_FS_STARTED, &c->flags))
+	if (!test_bit(BCH_FS_started, &c->flags))
 		return -EINVAL;
 
 	if (copy_from_user(&arg, user_arg, sizeof(arg)))
@@ -511,7 +588,6 @@ static long bch2_ioctl_dev_usage(struct bch_fs *c,
 	arg.state		= ca->mi.state;
 	arg.bucket_size		= ca->mi.bucket_size;
 	arg.nr_buckets		= ca->mi.nbuckets - ca->mi.first_bucket;
-	arg.buckets_ec		= src.buckets_ec;
 
 	for (i = 0; i < BCH_DATA_NR; i++) {
 		arg.d[i].buckets	= src.d[i].buckets;
@@ -521,10 +597,58 @@ static long bch2_ioctl_dev_usage(struct bch_fs *c,
 
 	percpu_ref_put(&ca->ref);
 
-	if (copy_to_user(user_arg, &arg, sizeof(arg)))
+	return copy_to_user_errcode(user_arg, &arg, sizeof(arg));
+}
+
+static long bch2_ioctl_dev_usage_v2(struct bch_fs *c,
+				 struct bch_ioctl_dev_usage_v2 __user *user_arg)
+{
+	struct bch_ioctl_dev_usage_v2 arg;
+	struct bch_dev_usage src;
+	struct bch_dev *ca;
+	int ret = 0;
+
+	if (!test_bit(BCH_FS_started, &c->flags))
+		return -EINVAL;
+
+	if (copy_from_user(&arg, user_arg, sizeof(arg)))
 		return -EFAULT;
 
-	return 0;
+	if ((arg.flags & ~BCH_BY_INDEX) ||
+	    arg.pad[0] ||
+	    arg.pad[1] ||
+	    arg.pad[2])
+		return -EINVAL;
+
+	ca = bch2_device_lookup(c, arg.dev, arg.flags);
+	if (IS_ERR(ca))
+		return PTR_ERR(ca);
+
+	src = bch2_dev_usage_read(ca);
+
+	arg.state		= ca->mi.state;
+	arg.bucket_size		= ca->mi.bucket_size;
+	arg.nr_data_types	= min(arg.nr_data_types, BCH_DATA_NR);
+	arg.nr_buckets		= ca->mi.nbuckets - ca->mi.first_bucket;
+
+	ret = copy_to_user_errcode(user_arg, &arg, sizeof(arg));
+	if (ret)
+		goto err;
+
+	for (unsigned i = 0; i < arg.nr_data_types; i++) {
+		struct bch_ioctl_dev_usage_type t = {
+			.buckets	= src.d[i].buckets,
+			.sectors	= src.d[i].sectors,
+			.fragmented	= src.d[i].fragmented,
+		};
+
+		ret = copy_to_user_errcode(&user_arg->d[i], &t, sizeof(t));
+		if (ret)
+			goto err;
+	}
+err:
+	percpu_ref_put(&ca->ref);
+	return ret;
 }
 
 static long bch2_ioctl_read_super(struct bch_fs *c,
@@ -561,9 +685,8 @@ static long bch2_ioctl_read_super(struct bch_fs *c,
 		goto err;
 	}
 
-	if (copy_to_user((void __user *)(unsigned long)arg.sb, sb,
-			 vstruct_bytes(sb)))
-		ret = -EFAULT;
+	ret = copy_to_user_errcode((void __user *)(unsigned long)arg.sb, sb,
+				   vstruct_bytes(sb));
 err:
 	if (!IS_ERR_OR_NULL(ca))
 		percpu_ref_put(&ca->ref);
@@ -575,8 +698,6 @@ static long bch2_ioctl_disk_get_idx(struct bch_fs *c,
 				    struct bch_ioctl_disk_get_idx arg)
 {
 	dev_t dev = huge_decode_dev(arg.dev);
-	struct bch_dev *ca;
-	unsigned i;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -584,10 +705,10 @@ static long bch2_ioctl_disk_get_idx(struct bch_fs *c,
 	if (!dev)
 		return -EINVAL;
 
-	for_each_online_member(ca, c, i)
+	for_each_online_member(c, ca)
 		if (ca->dev == dev) {
 			percpu_ref_put(&ca->io_ref);
-			return i;
+			return ca->dev_idx;
 		}
 
 	return -BCH_ERR_ENOENT_dev_idx_not_found;
@@ -642,6 +763,97 @@ static long bch2_ioctl_disk_resize_journal(struct bch_fs *c,
 	return ret;
 }
 
+static int bch2_fsck_online_thread_fn(void *arg)
+{
+	struct fsck_thread *thr = container_of(arg, struct fsck_thread, thr);
+	struct bch_fs *c = thr->c;
+
+	c->stdio_filter = current;
+	c->stdio = &thr->thr.stdio;
+
+	/*
+	 * XXX: can we figure out a way to do this without mucking with c->opts?
+	 */
+	unsigned old_fix_errors = c->opts.fix_errors;
+	if (opt_defined(thr->opts, fix_errors))
+		c->opts.fix_errors = thr->opts.fix_errors;
+	else
+		c->opts.fix_errors = FSCK_FIX_ask;
+
+	c->opts.fsck = true;
+	set_bit(BCH_FS_fsck_running, &c->flags);
+
+	c->curr_recovery_pass = BCH_RECOVERY_PASS_check_alloc_info;
+	int ret = bch2_run_online_recovery_passes(c);
+
+	clear_bit(BCH_FS_fsck_running, &c->flags);
+	bch_err_fn(c, ret);
+
+	c->stdio = NULL;
+	c->stdio_filter = NULL;
+	c->opts.fix_errors = old_fix_errors;
+
+	thread_with_stdio_done(&thr->thr);
+
+	up(&c->online_fsck_mutex);
+	bch2_ro_ref_put(c);
+	return 0;
+}
+
+static long bch2_ioctl_fsck_online(struct bch_fs *c,
+				   struct bch_ioctl_fsck_online arg)
+{
+	struct fsck_thread *thr = NULL;
+	long ret = 0;
+
+	if (arg.flags)
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!bch2_ro_ref_tryget(c))
+		return -EROFS;
+
+	if (down_trylock(&c->online_fsck_mutex)) {
+		bch2_ro_ref_put(c);
+		return -EAGAIN;
+	}
+
+	thr = kzalloc(sizeof(*thr), GFP_KERNEL);
+	if (!thr) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	thr->c = c;
+	thr->opts = bch2_opts_empty();
+
+	if (arg.opts) {
+		char *optstr = strndup_user((char __user *)(unsigned long) arg.opts, 1 << 16);
+
+		ret =   PTR_ERR_OR_ZERO(optstr) ?:
+			bch2_parse_mount_opts(c, &thr->opts, optstr);
+		kfree(optstr);
+
+		if (ret)
+			goto err;
+	}
+
+	ret = bch2_run_thread_with_stdio(&thr->thr,
+			bch2_fsck_thread_exit,
+			bch2_fsck_online_thread_fn);
+err:
+	if (ret < 0) {
+		bch_err_fn(c, ret);
+		if (thr)
+			bch2_fsck_thread_exit(&thr->thr);
+		up(&c->online_fsck_mutex);
+		bch2_ro_ref_put(c);
+	}
+	return ret;
+}
+
 #define BCH_IOCTL(_name, _argtype)					\
 do {									\
 	_argtype i;							\
@@ -663,6 +875,8 @@ long bch2_fs_ioctl(struct bch_fs *c, unsigned cmd, void __user *arg)
 		return bch2_ioctl_fs_usage(c, arg);
 	case BCH_IOCTL_DEV_USAGE:
 		return bch2_ioctl_dev_usage(c, arg);
+	case BCH_IOCTL_DEV_USAGE_V2:
+		return bch2_ioctl_dev_usage_v2(c, arg);
 #if 0
 	case BCH_IOCTL_START:
 		BCH_IOCTL(start, struct bch_ioctl_start);
@@ -675,7 +889,7 @@ long bch2_fs_ioctl(struct bch_fs *c, unsigned cmd, void __user *arg)
 		BCH_IOCTL(disk_get_idx, struct bch_ioctl_disk_get_idx);
 	}
 
-	if (!test_bit(BCH_FS_STARTED, &c->flags))
+	if (!test_bit(BCH_FS_started, &c->flags))
 		return -EINVAL;
 
 	switch (cmd) {
@@ -695,7 +909,8 @@ long bch2_fs_ioctl(struct bch_fs *c, unsigned cmd, void __user *arg)
 		BCH_IOCTL(disk_resize, struct bch_ioctl_disk_resize);
 	case BCH_IOCTL_DISK_RESIZE_JOURNAL:
 		BCH_IOCTL(disk_resize_journal, struct bch_ioctl_disk_resize_journal);
-
+	case BCH_IOCTL_FSCK_ONLINE:
+		BCH_IOCTL(fsck_online, struct bch_ioctl_fsck_online);
 	default:
 		return -ENOTTY;
 	}
diff --git a/fs/bcachefs/checksum.h b/fs/bcachefs/checksum.h
index 13998388c545..1b8c2c1016dc 100644
--- a/fs/bcachefs/checksum.h
+++ b/fs/bcachefs/checksum.h
@@ -45,6 +45,29 @@ struct bch_csum bch2_checksum(struct bch_fs *, unsigned, struct nonce,
 	bch2_checksum(_c, _type, _nonce, _start, vstruct_end(_i) - _start);\
 })
 
+static inline void bch2_csum_to_text(struct printbuf *out,
+				     enum bch_csum_type type,
+				     struct bch_csum csum)
+{
+	const u8 *p = (u8 *) &csum;
+	unsigned bytes = type < BCH_CSUM_NR ? bch_crc_bytes[type] : 16;
+
+	for (unsigned i = 0; i < bytes; i++)
+		prt_hex_byte(out, p[i]);
+}
+
+static inline void bch2_csum_err_msg(struct printbuf *out,
+				     enum bch_csum_type type,
+				     struct bch_csum expected,
+				     struct bch_csum got)
+{
+	prt_printf(out, "checksum error: got ");
+	bch2_csum_to_text(out, type, got);
+	prt_str(out, " should be ");
+	bch2_csum_to_text(out, type, expected);
+	prt_printf(out, " type %s", bch2_csum_types[type]);
+}
+
 int bch2_chacha_encrypt_key(struct bch_key *, struct nonce, void *, size_t);
 int bch2_request_key(struct bch_sb *, struct bch_key *);
 #ifndef __KERNEL__
diff --git a/fs/bcachefs/compress.c b/fs/bcachefs/compress.c
index a8b148ec2a2b..33df8cf86bd8 100644
--- a/fs/bcachefs/compress.c
+++ b/fs/bcachefs/compress.c
@@ -354,8 +354,7 @@ static int attempt_compress(struct bch_fs *c,
 		 */
 		unsigned level = min((compression.level * 3) / 2, zstd_max_clevel());
 		ZSTD_parameters params = zstd_get_params(level, c->opts.encoded_extent_max);
-		ZSTD_CCtx *ctx = zstd_init_cctx(workspace,
-			zstd_cctx_workspace_bound(&params.cParams));
+		ZSTD_CCtx *ctx = zstd_init_cctx(workspace, c->zstd_workspace_size);
 
 		/*
 		 * ZSTD requires that when we decompress we pass in the exact
@@ -371,7 +370,7 @@ static int attempt_compress(struct bch_fs *c,
 		size_t len = zstd_compress_cctx(ctx,
 				dst + 4,	dst_len - 4 - 7,
 				src,		src_len,
-				&c->zstd_params);
+				&params);
 		if (zstd_is_error(len))
 			return 0;
 
@@ -572,6 +571,9 @@ static int __bch2_fs_compress_init(struct bch_fs *c, u64 features)
 	size_t decompress_workspace_size = 0;
 	ZSTD_parameters params = zstd_get_params(zstd_max_clevel(),
 						 c->opts.encoded_extent_max);
+
+	c->zstd_workspace_size = zstd_cctx_workspace_bound(&params.cParams);
+
 	struct {
 		unsigned			feature;
 		enum bch_compression_type	type;
@@ -585,13 +587,11 @@ static int __bch2_fs_compress_init(struct bch_fs *c, u64 features)
 			zlib_deflate_workspacesize(MAX_WBITS, DEF_MEM_LEVEL),
 			zlib_inflate_workspacesize(), },
 		{ BCH_FEATURE_zstd, BCH_COMPRESSION_TYPE_zstd,
-			zstd_cctx_workspace_bound(&params.cParams),
+			c->zstd_workspace_size,
 			zstd_dctx_workspace_bound() },
 	}, *i;
 	bool have_compressed = false;
 
-	c->zstd_params = params;
-
 	for (i = compression_types;
 	     i < compression_types + ARRAY_SIZE(compression_types);
 	     i++)
diff --git a/fs/bcachefs/darray.c b/fs/bcachefs/darray.c
new file mode 100644
index 000000000000..ac35b8b705ae
--- /dev/null
+++ b/fs/bcachefs/darray.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/log2.h>
+#include <linux/slab.h>
+#include "darray.h"
+
+int __bch2_darray_resize(darray_char *d, size_t element_size, size_t new_size, gfp_t gfp)
+{
+	if (new_size > d->size) {
+		new_size = roundup_pow_of_two(new_size);
+
+		void *data = kvmalloc_array(new_size, element_size, gfp);
+		if (!data)
+			return -ENOMEM;
+
+		memcpy(data, d->data, d->size * element_size);
+		if (d->data != d->preallocated)
+			kvfree(d->data);
+		d->data	= data;
+		d->size = new_size;
+	}
+
+	return 0;
+}
diff --git a/fs/bcachefs/darray.h b/fs/bcachefs/darray.h
index 87b4b2d1ec76..4b340d13caac 100644
--- a/fs/bcachefs/darray.h
+++ b/fs/bcachefs/darray.h
@@ -8,39 +8,49 @@
  * Inspired by CCAN's darray
  */
 
-#include "util.h"
 #include <linux/slab.h>
 
-#define DARRAY(type)							\
+#define DARRAY_PREALLOCATED(_type, _nr)					\
 struct {								\
 	size_t nr, size;						\
-	type *data;							\
+	_type *data;							\
+	_type preallocated[_nr];					\
 }
 
-typedef DARRAY(void) darray_void;
+#define DARRAY(_type) DARRAY_PREALLOCATED(_type, 0)
 
-static inline int __darray_make_room(darray_void *d, size_t t_size, size_t more, gfp_t gfp)
+typedef DARRAY(char)	darray_char;
+typedef DARRAY(char *) darray_str;
+
+int __bch2_darray_resize(darray_char *, size_t, size_t, gfp_t);
+
+static inline int __darray_resize(darray_char *d, size_t element_size,
+				  size_t new_size, gfp_t gfp)
 {
-	if (d->nr + more > d->size) {
-		size_t new_size = roundup_pow_of_two(d->nr + more);
-		void *data = krealloc_array(d->data, new_size, t_size, gfp);
+	return unlikely(new_size > d->size)
+		? __bch2_darray_resize(d, element_size, new_size, gfp)
+		: 0;
+}
 
-		if (!data)
-			return -ENOMEM;
+#define darray_resize_gfp(_d, _new_size, _gfp)				\
+	unlikely(__darray_resize((darray_char *) (_d), sizeof((_d)->data[0]), (_new_size), _gfp))
 
-		d->data	= data;
-		d->size = new_size;
-	}
+#define darray_resize(_d, _new_size)					\
+	darray_resize_gfp(_d, _new_size, GFP_KERNEL)
 
-	return 0;
+static inline int __darray_make_room(darray_char *d, size_t t_size, size_t more, gfp_t gfp)
+{
+	return __darray_resize(d, t_size, d->nr + more, gfp);
 }
 
 #define darray_make_room_gfp(_d, _more, _gfp)				\
-	__darray_make_room((darray_void *) (_d), sizeof((_d)->data[0]), (_more), _gfp)
+	__darray_make_room((darray_char *) (_d), sizeof((_d)->data[0]), (_more), _gfp)
 
 #define darray_make_room(_d, _more)					\
 	darray_make_room_gfp(_d, _more, GFP_KERNEL)
 
+#define darray_room(_d)		((_d).size - (_d).nr)
+
 #define darray_top(_d)		((_d).data[(_d).nr])
 
 #define darray_push_gfp(_d, _item, _gfp)				\
@@ -72,21 +82,27 @@ static inline int __darray_make_room(darray_void *d, size_t t_size, size_t more,
 #define darray_remove_item(_d, _pos)					\
 	array_remove_item((_d)->data, (_d)->nr, (_pos) - (_d)->data)
 
+#define __darray_for_each(_d, _i)						\
+	for ((_i) = (_d).data; _i < (_d).data + (_d).nr; _i++)
+
 #define darray_for_each(_d, _i)						\
-	for (_i = (_d).data; _i < (_d).data + (_d).nr; _i++)
+	for (typeof(&(_d).data[0]) _i = (_d).data; _i < (_d).data + (_d).nr; _i++)
 
 #define darray_for_each_reverse(_d, _i)					\
-	for (_i = (_d).data + (_d).nr - 1; _i >= (_d).data; --_i)
+	for (typeof(&(_d).data[0]) _i = (_d).data + (_d).nr - 1; _i >= (_d).data; --_i)
 
 #define darray_init(_d)							\
 do {									\
-	(_d)->data = NULL;						\
-	(_d)->nr = (_d)->size = 0;					\
+	(_d)->nr = 0;							\
+	(_d)->size = ARRAY_SIZE((_d)->preallocated);			\
+	(_d)->data = (_d)->size ? (_d)->preallocated : NULL;		\
 } while (0)
 
 #define darray_exit(_d)							\
 do {									\
-	kfree((_d)->data);						\
+	if (!ARRAY_SIZE((_d)->preallocated) ||				\
+	    (_d)->data != (_d)->preallocated)				\
+		kvfree((_d)->data);					\
 	darray_init(_d);						\
 } while (0)
 
diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c
index 0771a6d880bf..6f13477ff652 100644
--- a/fs/bcachefs/data_update.c
+++ b/fs/bcachefs/data_update.c
@@ -239,6 +239,48 @@ restart_drop_extra_replicas:
 
 		next_pos = insert->k.p;
 
+		/*
+		 * Check for nonce offset inconsistency:
+		 * This is debug code - we've been seeing this bug rarely, and
+		 * it's been hard to reproduce, so this should give us some more
+		 * information when it does occur:
+		 */
+		struct printbuf err = PRINTBUF;
+		int invalid = bch2_bkey_invalid(c, bkey_i_to_s_c(insert), __btree_node_type(0, m->btree_id), 0, &err);
+		printbuf_exit(&err);
+
+		if (invalid) {
+			struct printbuf buf = PRINTBUF;
+
+			prt_str(&buf, "about to insert invalid key in data update path");
+			prt_str(&buf, "\nold: ");
+			bch2_bkey_val_to_text(&buf, c, old);
+			prt_str(&buf, "\nk:   ");
+			bch2_bkey_val_to_text(&buf, c, k);
+			prt_str(&buf, "\nnew: ");
+			bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(insert));
+
+			bch2_print_string_as_lines(KERN_ERR, buf.buf);
+			printbuf_exit(&buf);
+
+			bch2_fatal_error(c);
+			goto out;
+		}
+
+		if (trace_data_update_enabled()) {
+			struct printbuf buf = PRINTBUF;
+
+			prt_str(&buf, "\nold: ");
+			bch2_bkey_val_to_text(&buf, c, old);
+			prt_str(&buf, "\nk:   ");
+			bch2_bkey_val_to_text(&buf, c, k);
+			prt_str(&buf, "\nnew: ");
+			bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(insert));
+
+			trace_data_update(c, buf.buf);
+			printbuf_exit(&buf);
+		}
+
 		ret =   bch2_insert_snapshot_whiteouts(trans, m->btree_id,
 						k.k->p, bkey_start_pos(&insert->k)) ?:
 			bch2_insert_snapshot_whiteouts(trans, m->btree_id,
@@ -250,8 +292,8 @@ restart_drop_extra_replicas:
 				BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE) ?:
 			bch2_trans_commit(trans, &op->res,
 				NULL,
-				BTREE_INSERT_NOCHECK_RW|
-				BTREE_INSERT_NOFAIL|
+				BCH_TRANS_COMMIT_no_check_rw|
+				BCH_TRANS_COMMIT_no_enospc|
 				m->data_opts.btree_insert_flags);
 		if (!ret) {
 			bch2_btree_iter_set_pos(&iter, next_pos);
@@ -272,14 +314,14 @@ next:
 		}
 		continue;
 nowork:
-		if (m->stats && m->stats) {
+		if (m->stats) {
 			BUG_ON(k.k->p.offset <= iter.pos.offset);
 			atomic64_inc(&m->stats->keys_raced);
 			atomic64_add(k.k->p.offset - iter.pos.offset,
 				     &m->stats->sectors_raced);
 		}
 
-		this_cpu_inc(c->counters[BCH_COUNTER_move_extent_fail]);
+		count_event(c, move_extent_fail);
 
 		bch2_btree_iter_advance(&iter);
 		goto next;
@@ -314,7 +356,6 @@ void bch2_data_update_exit(struct data_update *update)
 	struct bch_fs *c = update->op.c;
 	struct bkey_ptrs_c ptrs =
 		bch2_bkey_ptrs_c(bkey_i_to_s_c(update->k.k));
-	const struct bch_extent_ptr *ptr;
 
 	bkey_for_each_ptr(ptrs, ptr) {
 		if (c->opts.nocow_enabled)
@@ -328,14 +369,13 @@ void bch2_data_update_exit(struct data_update *update)
 	bch2_bio_free_pages_pool(c, &update->op.wbio.bio);
 }
 
-void bch2_update_unwritten_extent(struct btree_trans *trans,
+static void bch2_update_unwritten_extent(struct btree_trans *trans,
 				  struct data_update *update)
 {
 	struct bch_fs *c = update->op.c;
 	struct bio *bio = &update->op.wbio.bio;
 	struct bkey_i_extent *e;
 	struct write_point *wp;
-	struct bch_extent_ptr *ptr;
 	struct closure cl;
 	struct btree_iter iter;
 	struct bkey_s_c k;
@@ -376,6 +416,8 @@ void bch2_update_unwritten_extent(struct btree_trans *trans,
 			continue;
 		}
 
+		bch_err_fn_ratelimited(c, ret);
+
 		if (ret)
 			return;
 
@@ -408,7 +450,51 @@ void bch2_update_unwritten_extent(struct btree_trans *trans,
 	}
 }
 
+int bch2_extent_drop_ptrs(struct btree_trans *trans,
+			  struct btree_iter *iter,
+			  struct bkey_s_c k,
+			  struct data_update_opts data_opts)
+{
+	struct bch_fs *c = trans->c;
+	struct bkey_i *n;
+	int ret;
+
+	n = bch2_bkey_make_mut_noupdate(trans, k);
+	ret = PTR_ERR_OR_ZERO(n);
+	if (ret)
+		return ret;
+
+	while (data_opts.kill_ptrs) {
+		unsigned i = 0, drop = __fls(data_opts.kill_ptrs);
+		struct bch_extent_ptr *ptr;
+
+		bch2_bkey_drop_ptrs(bkey_i_to_s(n), ptr, i++ == drop);
+		data_opts.kill_ptrs ^= 1U << drop;
+	}
+
+	/*
+	 * If the new extent no longer has any pointers, bch2_extent_normalize()
+	 * will do the appropriate thing with it (turning it into a
+	 * KEY_TYPE_error key, or just a discard if it was a cached extent)
+	 */
+	bch2_extent_normalize(c, bkey_i_to_s(n));
+
+	/*
+	 * Since we're not inserting through an extent iterator
+	 * (BTREE_ITER_ALL_SNAPSHOTS iterators aren't extent iterators),
+	 * we aren't using the extent overwrite path to delete, we're
+	 * just using the normal key deletion path:
+	 */
+	if (bkey_deleted(&n->k) && !(iter->flags & BTREE_ITER_IS_EXTENTS))
+		n->k.size = 0;
+
+	return bch2_trans_relock(trans) ?:
+		bch2_trans_update(trans, iter, n, BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE) ?:
+		bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc);
+}
+
 int bch2_data_update_init(struct btree_trans *trans,
+			  struct btree_iter *iter,
 			  struct moving_context *ctxt,
 			  struct data_update *m,
 			  struct write_point_specifier wp,
@@ -421,10 +507,9 @@ int bch2_data_update_init(struct btree_trans *trans,
 	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
 	const union bch_extent_entry *entry;
 	struct extent_ptr_decoded p;
-	const struct bch_extent_ptr *ptr;
 	unsigned i, reserve_sectors = k.k->size * data_opts.extra_replicas;
 	unsigned ptrs_locked = 0;
-	int ret;
+	int ret = 0;
 
 	bch2_bkey_buf_init(&m->k);
 	bch2_bkey_buf_reassemble(&m->k, c, k);
@@ -450,6 +535,8 @@ int bch2_data_update_init(struct btree_trans *trans,
 	bkey_for_each_ptr(ptrs, ptr)
 		percpu_ref_get(&bch_dev_bkey_exists(c, ptr->dev)->ref);
 
+	unsigned durability_have = 0, durability_removing = 0;
+
 	i = 0;
 	bkey_for_each_ptr_decode(k.k, ptrs, p, entry) {
 		bool locked;
@@ -461,8 +548,11 @@ int bch2_data_update_init(struct btree_trans *trans,
 				reserve_sectors += k.k->size;
 
 			m->op.nr_replicas += bch2_extent_ptr_desired_durability(c, &p);
-		} else if (!p.ptr.cached) {
+			durability_removing += bch2_extent_ptr_desired_durability(c, &p);
+		} else if (!p.ptr.cached &&
+			   !((1U << i) & m->data_opts.kill_ptrs)) {
 			bch2_dev_list_add_dev(&m->op.devs_have, p.ptr.dev);
+			durability_have += bch2_extent_ptr_durability(c, &p);
 		}
 
 		/*
@@ -483,7 +573,8 @@ int bch2_data_update_init(struct btree_trans *trans,
 				move_ctxt_wait_event(ctxt,
 						(locked = bch2_bucket_nocow_trylock(&c->nocow_locks,
 									  PTR_BUCKET_POS(c, &p.ptr), 0)) ||
-						!atomic_read(&ctxt->read_sectors));
+						(!atomic_read(&ctxt->read_sectors) &&
+						 !atomic_read(&ctxt->write_sectors)));
 
 				if (!locked)
 					bch2_bucket_nocow_lock(&c->nocow_locks,
@@ -501,6 +592,30 @@ int bch2_data_update_init(struct btree_trans *trans,
 		i++;
 	}
 
+	/*
+	 * If current extent durability is less than io_opts.data_replicas,
+	 * we're not trying to rereplicate the extent up to data_replicas here -
+	 * unless extra_replicas was specified
+	 *
+	 * Increasing replication is an explicit operation triggered by
+	 * rereplicate, currently, so that users don't get an unexpected -ENOSPC
+	 */
+	if (!(m->data_opts.write_flags & BCH_WRITE_CACHED) &&
+	    durability_have >= io_opts.data_replicas) {
+		m->data_opts.kill_ptrs |= m->data_opts.rewrite_ptrs;
+		m->data_opts.rewrite_ptrs = 0;
+		/* if iter == NULL, it's just a promote */
+		if (iter)
+			ret = bch2_extent_drop_ptrs(trans, iter, k, m->data_opts);
+		goto done;
+	}
+
+	m->op.nr_replicas = min(durability_removing, io_opts.data_replicas - durability_have) +
+		m->data_opts.extra_replicas;
+	m->op.nr_replicas_required = m->op.nr_replicas;
+
+	BUG_ON(!m->op.nr_replicas);
+
 	if (reserve_sectors) {
 		ret = bch2_disk_reservation_add(c, &m->op.res, reserve_sectors,
 				m->data_opts.extra_replicas
@@ -510,14 +625,11 @@ int bch2_data_update_init(struct btree_trans *trans,
 			goto err;
 	}
 
-	m->op.nr_replicas += m->data_opts.extra_replicas;
-	m->op.nr_replicas_required = m->op.nr_replicas;
-
-	BUG_ON(!m->op.nr_replicas);
+	if (bkey_extent_is_unwritten(k)) {
+		bch2_update_unwritten_extent(trans, m);
+		goto done;
+	}
 
-	/* Special handling required: */
-	if (bkey_extent_is_unwritten(k))
-		return -BCH_ERR_unwritten_extent_update;
 	return 0;
 err:
 	i = 0;
@@ -532,12 +644,14 @@ err:
 	bch2_bkey_buf_exit(&m->k, c);
 	bch2_bio_free_pages_pool(c, &m->op.wbio.bio);
 	return ret;
+done:
+	bch2_data_update_exit(m);
+	return ret ?: -BCH_ERR_data_update_done;
 }
 
 void bch2_data_update_opts_normalize(struct bkey_s_c k, struct data_update_opts *opts)
 {
 	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
-	const struct bch_extent_ptr *ptr;
 	unsigned i = 0;
 
 	bkey_for_each_ptr(ptrs, ptr) {
diff --git a/fs/bcachefs/data_update.h b/fs/bcachefs/data_update.h
index 9dc17b9d8379..991095bbd469 100644
--- a/fs/bcachefs/data_update.h
+++ b/fs/bcachefs/data_update.h
@@ -32,9 +32,14 @@ int bch2_data_update_index_update(struct bch_write_op *);
 void bch2_data_update_read_done(struct data_update *,
 				struct bch_extent_crc_unpacked);
 
+int bch2_extent_drop_ptrs(struct btree_trans *,
+			  struct btree_iter *,
+			  struct bkey_s_c,
+			  struct data_update_opts);
+
 void bch2_data_update_exit(struct data_update *);
-void bch2_update_unwritten_extent(struct btree_trans *, struct data_update *);
-int bch2_data_update_init(struct btree_trans *, struct moving_context *,
+int bch2_data_update_init(struct btree_trans *, struct btree_iter *,
+			  struct moving_context *,
 			  struct data_update *,
 			  struct write_point_specifier,
 			  struct bch_io_opts, struct data_update_opts,
diff --git a/fs/bcachefs/debug.c b/fs/bcachefs/debug.c
index 57c5128db173..d6418948495f 100644
--- a/fs/bcachefs/debug.c
+++ b/fs/bcachefs/debug.c
@@ -366,35 +366,23 @@ static ssize_t bch2_read_btree(struct file *file, char __user *buf,
 			       size_t size, loff_t *ppos)
 {
 	struct dump_iter *i = file->private_data;
-	struct btree_trans *trans;
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	ssize_t ret;
 
 	i->ubuf = buf;
 	i->size	= size;
 	i->ret	= 0;
 
-	ret = flush_buf(i);
-	if (ret)
-		return ret;
-
-	trans = bch2_trans_get(i->c);
-	ret = for_each_btree_key2(trans, iter, i->id, i->from,
-				  BTREE_ITER_PREFETCH|
-				  BTREE_ITER_ALL_SNAPSHOTS, k, ({
-		bch2_bkey_val_to_text(&i->buf, i->c, k);
-		prt_newline(&i->buf);
-		drop_locks_do(trans, flush_buf(i));
-	}));
-	i->from = iter.pos;
-
-	bch2_trans_put(trans);
-
-	if (!ret)
-		ret = flush_buf(i);
-
-	return ret ?: i->ret;
+	return flush_buf(i) ?:
+		bch2_trans_run(i->c,
+			for_each_btree_key(trans, iter, i->id, i->from,
+					   BTREE_ITER_PREFETCH|
+					   BTREE_ITER_ALL_SNAPSHOTS, k, ({
+				bch2_bkey_val_to_text(&i->buf, i->c, k);
+				prt_newline(&i->buf);
+				bch2_trans_unlock(trans);
+				i->from = bpos_successor(iter.pos);
+				flush_buf(i);
+			}))) ?:
+		i->ret;
 }
 
 static const struct file_operations btree_debug_ops = {
@@ -462,44 +450,32 @@ static ssize_t bch2_read_bfloat_failed(struct file *file, char __user *buf,
 				       size_t size, loff_t *ppos)
 {
 	struct dump_iter *i = file->private_data;
-	struct btree_trans *trans;
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	ssize_t ret;
 
 	i->ubuf = buf;
 	i->size	= size;
 	i->ret	= 0;
 
-	ret = flush_buf(i);
-	if (ret)
-		return ret;
-
-	trans = bch2_trans_get(i->c);
-
-	ret = for_each_btree_key2(trans, iter, i->id, i->from,
-				  BTREE_ITER_PREFETCH|
-				  BTREE_ITER_ALL_SNAPSHOTS, k, ({
-		struct btree_path_level *l = &iter.path->l[0];
-		struct bkey_packed *_k =
-			bch2_btree_node_iter_peek(&l->iter, l->b);
-
-		if (bpos_gt(l->b->key.k.p, i->prev_node)) {
-			bch2_btree_node_to_text(&i->buf, i->c, l->b);
-			i->prev_node = l->b->key.k.p;
-		}
-
-		bch2_bfloat_to_text(&i->buf, l->b, _k);
-		drop_locks_do(trans, flush_buf(i));
-	}));
-	i->from = iter.pos;
-
-	bch2_trans_put(trans);
-
-	if (!ret)
-		ret = flush_buf(i);
-
-	return ret ?: i->ret;
+	return flush_buf(i) ?:
+		bch2_trans_run(i->c,
+			for_each_btree_key(trans, iter, i->id, i->from,
+					   BTREE_ITER_PREFETCH|
+					   BTREE_ITER_ALL_SNAPSHOTS, k, ({
+				struct btree_path_level *l =
+					&btree_iter_path(trans, &iter)->l[0];
+				struct bkey_packed *_k =
+					bch2_btree_node_iter_peek(&l->iter, l->b);
+
+				if (bpos_gt(l->b->key.k.p, i->prev_node)) {
+					bch2_btree_node_to_text(&i->buf, i->c, l->b);
+					i->prev_node = l->b->key.k.p;
+				}
+
+				bch2_bfloat_to_text(&i->buf, l->b, _k);
+				bch2_trans_unlock(trans);
+				i->from = bpos_successor(iter.pos);
+				flush_buf(i);
+			}))) ?:
+		i->ret;
 }
 
 static const struct file_operations bfloat_failed_debug_ops = {
@@ -616,7 +592,6 @@ static const struct file_operations cached_btree_nodes_ops = {
 	.read		= bch2_cached_btree_nodes_read,
 };
 
-#ifdef CONFIG_BCACHEFS_DEBUG_TRANSACTIONS
 static ssize_t bch2_btree_transactions_read(struct file *file, char __user *buf,
 					    size_t size, loff_t *ppos)
 {
@@ -632,7 +607,9 @@ static ssize_t bch2_btree_transactions_read(struct file *file, char __user *buf,
 restart:
 	seqmutex_lock(&c->btree_trans_lock);
 	list_for_each_entry(trans, &c->btree_trans_list, list) {
-		if (trans->locking_wait.task->pid <= i->iter)
+		struct task_struct *task = READ_ONCE(trans->locking_wait.task);
+
+		if (!task || task->pid <= i->iter)
 			continue;
 
 		closure_get(&trans->ref);
@@ -650,11 +627,11 @@ restart:
 		prt_printf(&i->buf, "backtrace:");
 		prt_newline(&i->buf);
 		printbuf_indent_add(&i->buf, 2);
-		bch2_prt_task_backtrace(&i->buf, trans->locking_wait.task);
+		bch2_prt_task_backtrace(&i->buf, task, 0);
 		printbuf_indent_sub(&i->buf, 2);
 		prt_newline(&i->buf);
 
-		i->iter = trans->locking_wait.task->pid;
+		i->iter = task->pid;
 
 		closure_put(&trans->ref);
 
@@ -678,7 +655,6 @@ static const struct file_operations btree_transactions_ops = {
 	.release	= bch2_dump_release,
 	.read		= bch2_btree_transactions_read,
 };
-#endif /* CONFIG_BCACHEFS_DEBUG_TRANSACTIONS */
 
 static ssize_t bch2_journal_pins_read(struct file *file, char __user *buf,
 				      size_t size, loff_t *ppos)
@@ -717,7 +693,7 @@ static const struct file_operations journal_pins_ops = {
 	.read		= bch2_journal_pins_read,
 };
 
-static int lock_held_stats_open(struct inode *inode, struct file *file)
+static int btree_transaction_stats_open(struct inode *inode, struct file *file)
 {
 	struct bch_fs *c = inode->i_private;
 	struct dump_iter *i;
@@ -727,7 +703,7 @@ static int lock_held_stats_open(struct inode *inode, struct file *file)
 	if (!i)
 		return -ENOMEM;
 
-	i->iter = 0;
+	i->iter = 1;
 	i->c    = c;
 	i->buf  = PRINTBUF;
 	file->private_data = i;
@@ -735,7 +711,7 @@ static int lock_held_stats_open(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static int lock_held_stats_release(struct inode *inode, struct file *file)
+static int btree_transaction_stats_release(struct inode *inode, struct file *file)
 {
 	struct dump_iter *i = file->private_data;
 
@@ -745,8 +721,8 @@ static int lock_held_stats_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static ssize_t lock_held_stats_read(struct file *file, char __user *buf,
-				      size_t size, loff_t *ppos)
+static ssize_t btree_transaction_stats_read(struct file *file, char __user *buf,
+					    size_t size, loff_t *ppos)
 {
 	struct dump_iter        *i = file->private_data;
 	struct bch_fs *c = i->c;
@@ -779,6 +755,13 @@ static ssize_t lock_held_stats_read(struct file *file, char __user *buf,
 		prt_printf(&i->buf, "Max mem used: %u", s->max_mem);
 		prt_newline(&i->buf);
 
+		prt_printf(&i->buf, "Transaction duration:");
+		prt_newline(&i->buf);
+
+		printbuf_indent_add(&i->buf, 2);
+		bch2_time_stats_to_text(&i->buf, &s->duration);
+		printbuf_indent_sub(&i->buf, 2);
+
 		if (IS_ENABLED(CONFIG_BCACHEFS_LOCK_TIME_STATS)) {
 			prt_printf(&i->buf, "Lock hold times:");
 			prt_newline(&i->buf);
@@ -810,11 +793,11 @@ static ssize_t lock_held_stats_read(struct file *file, char __user *buf,
 	return i->ret;
 }
 
-static const struct file_operations lock_held_stats_op = {
-	.owner = THIS_MODULE,
-	.open = lock_held_stats_open,
-	.release = lock_held_stats_release,
-	.read = lock_held_stats_read,
+static const struct file_operations btree_transaction_stats_op = {
+	.owner		= THIS_MODULE,
+	.open		= btree_transaction_stats_open,
+	.release	= btree_transaction_stats_release,
+	.read		= btree_transaction_stats_read,
 };
 
 static ssize_t bch2_btree_deadlock_read(struct file *file, char __user *buf,
@@ -835,7 +818,9 @@ static ssize_t bch2_btree_deadlock_read(struct file *file, char __user *buf,
 restart:
 	seqmutex_lock(&c->btree_trans_lock);
 	list_for_each_entry(trans, &c->btree_trans_list, list) {
-		if (trans->locking_wait.task->pid <= i->iter)
+		struct task_struct *task = READ_ONCE(trans->locking_wait.task);
+
+		if (!task || task->pid <= i->iter)
 			continue;
 
 		closure_get(&trans->ref);
@@ -850,7 +835,7 @@ restart:
 
 		bch2_check_for_deadlock(trans, &i->buf);
 
-		i->iter = trans->locking_wait.task->pid;
+		i->iter = task->pid;
 
 		closure_put(&trans->ref);
 
@@ -897,16 +882,14 @@ void bch2_fs_debug_init(struct bch_fs *c)
 	debugfs_create_file("cached_btree_nodes", 0400, c->fs_debug_dir,
 			    c->btree_debug, &cached_btree_nodes_ops);
 
-#ifdef CONFIG_BCACHEFS_DEBUG_TRANSACTIONS
 	debugfs_create_file("btree_transactions", 0400, c->fs_debug_dir,
 			    c->btree_debug, &btree_transactions_ops);
-#endif
 
 	debugfs_create_file("journal_pins", 0400, c->fs_debug_dir,
 			    c->btree_debug, &journal_pins_ops);
 
 	debugfs_create_file("btree_transaction_stats", 0400, c->fs_debug_dir,
-			    c, &lock_held_stats_op);
+			    c, &btree_transaction_stats_op);
 
 	debugfs_create_file("btree_deadlock", 0400, c->fs_debug_dir,
 			    c->btree_debug, &btree_deadlock_ops);
@@ -947,8 +930,6 @@ void bch2_debug_exit(void)
 
 int __init bch2_debug_init(void)
 {
-	int ret = 0;
-
 	bch_debug = debugfs_create_dir("bcachefs", NULL);
-	return ret;
+	return 0;
 }
diff --git a/fs/bcachefs/dirent.c b/fs/bcachefs/dirent.c
index 1a0f2d571569..4ae1e9f002a0 100644
--- a/fs/bcachefs/dirent.c
+++ b/fs/bcachefs/dirent.c
@@ -65,7 +65,7 @@ static bool dirent_cmp_key(struct bkey_s_c _l, const void *_r)
 	const struct qstr l_name = bch2_dirent_get_name(l);
 	const struct qstr *r_name = _r;
 
-	return l_name.len - r_name->len ?: memcmp(l_name.name, r_name->name, l_name.len);
+	return !qstr_eq(l_name, *r_name);
 }
 
 static bool dirent_cmp_bkey(struct bkey_s_c _l, struct bkey_s_c _r)
@@ -75,7 +75,7 @@ static bool dirent_cmp_bkey(struct bkey_s_c _l, struct bkey_s_c _r)
 	const struct qstr l_name = bch2_dirent_get_name(l);
 	const struct qstr r_name = bch2_dirent_get_name(r);
 
-	return l_name.len - r_name.len ?: memcmp(l_name.name, r_name.name, l_name.len);
+	return !qstr_eq(l_name, r_name);
 }
 
 static bool dirent_is_visible(subvol_inum inum, struct bkey_s_c k)
@@ -198,10 +198,39 @@ static struct bkey_i_dirent *dirent_create_key(struct btree_trans *trans,
 	return dirent;
 }
 
+int bch2_dirent_create_snapshot(struct btree_trans *trans,
+			u64 dir, u32 snapshot,
+			const struct bch_hash_info *hash_info,
+			u8 type, const struct qstr *name, u64 dst_inum,
+			u64 *dir_offset,
+			bch_str_hash_flags_t str_hash_flags)
+{
+	subvol_inum zero_inum = { 0 };
+	struct bkey_i_dirent *dirent;
+	int ret;
+
+	dirent = dirent_create_key(trans, zero_inum, type, name, dst_inum);
+	ret = PTR_ERR_OR_ZERO(dirent);
+	if (ret)
+		return ret;
+
+	dirent->k.p.inode	= dir;
+	dirent->k.p.snapshot	= snapshot;
+
+	ret = bch2_hash_set_snapshot(trans, bch2_dirent_hash_desc, hash_info,
+				     zero_inum, snapshot,
+				     &dirent->k_i, str_hash_flags,
+				     BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE);
+	*dir_offset = dirent->k.p.offset;
+
+	return ret;
+}
+
 int bch2_dirent_create(struct btree_trans *trans, subvol_inum dir,
 		       const struct bch_hash_info *hash_info,
 		       u8 type, const struct qstr *name, u64 dst_inum,
-		       u64 *dir_offset, int flags)
+		       u64 *dir_offset,
+		       bch_str_hash_flags_t str_hash_flags)
 {
 	struct bkey_i_dirent *dirent;
 	int ret;
@@ -212,7 +241,7 @@ int bch2_dirent_create(struct btree_trans *trans, subvol_inum dir,
 		return ret;
 
 	ret = bch2_hash_set(trans, bch2_dirent_hash_desc, hash_info,
-			    dir, &dirent->k_i, flags);
+			    dir, &dirent->k_i, str_hash_flags);
 	*dir_offset = dirent->k.p.offset;
 
 	return ret;
@@ -470,35 +499,24 @@ u64 bch2_dirent_lookup(struct bch_fs *c, subvol_inum dir,
 		       const struct qstr *name, subvol_inum *inum)
 {
 	struct btree_trans *trans = bch2_trans_get(c);
-	struct btree_iter iter;
-	int ret;
-retry:
-	bch2_trans_begin(trans);
+	struct btree_iter iter = { NULL };
 
-	ret = __bch2_dirent_lookup_trans(trans, &iter, dir, hash_info,
-					  name, inum, 0);
-	if (bch2_err_matches(ret, BCH_ERR_transaction_restart))
-		goto retry;
-	if (!ret)
-		bch2_trans_iter_exit(trans, &iter);
+	int ret = lockrestart_do(trans,
+		__bch2_dirent_lookup_trans(trans, &iter, dir, hash_info, name, inum, 0));
+	bch2_trans_iter_exit(trans, &iter);
 	bch2_trans_put(trans);
 	return ret;
 }
 
-int bch2_empty_dir_trans(struct btree_trans *trans, subvol_inum dir)
+int bch2_empty_dir_snapshot(struct btree_trans *trans, u64 dir, u32 snapshot)
 {
 	struct btree_iter iter;
 	struct bkey_s_c k;
-	u32 snapshot;
 	int ret;
 
-	ret = bch2_subvolume_get_snapshot(trans, dir.subvol, &snapshot);
-	if (ret)
-		return ret;
-
 	for_each_btree_key_upto_norestart(trans, iter, BTREE_ID_dirents,
-			   SPOS(dir.inum, 0, snapshot),
-			   POS(dir.inum, U64_MAX), 0, k, ret)
+			   SPOS(dir, 0, snapshot),
+			   POS(dir, U64_MAX), 0, k, ret)
 		if (k.k->type == KEY_TYPE_dirent) {
 			ret = -ENOTEMPTY;
 			break;
@@ -508,6 +526,14 @@ int bch2_empty_dir_trans(struct btree_trans *trans, subvol_inum dir)
 	return ret;
 }
 
+int bch2_empty_dir_trans(struct btree_trans *trans, subvol_inum dir)
+{
+	u32 snapshot;
+
+	return bch2_subvolume_get_snapshot(trans, dir.subvol, &snapshot) ?:
+		bch2_empty_dir_snapshot(trans, dir.inum, snapshot);
+}
+
 int bch2_readdir(struct bch_fs *c, subvol_inum inum, struct dir_context *ctx)
 {
 	struct btree_trans *trans = bch2_trans_get(c);
diff --git a/fs/bcachefs/dirent.h b/fs/bcachefs/dirent.h
index cd262bf4d9c5..21ffeb78f02e 100644
--- a/fs/bcachefs/dirent.h
+++ b/fs/bcachefs/dirent.h
@@ -35,9 +35,14 @@ static inline unsigned dirent_val_u64s(unsigned len)
 int bch2_dirent_read_target(struct btree_trans *, subvol_inum,
 			    struct bkey_s_c_dirent, subvol_inum *);
 
+int bch2_dirent_create_snapshot(struct btree_trans *, u64, u32,
+			const struct bch_hash_info *, u8,
+			const struct qstr *, u64, u64 *,
+			bch_str_hash_flags_t);
 int bch2_dirent_create(struct btree_trans *, subvol_inum,
 		       const struct bch_hash_info *, u8,
-		       const struct qstr *, u64, u64 *, int);
+		       const struct qstr *, u64, u64 *,
+		       bch_str_hash_flags_t);
 
 static inline unsigned vfs_d_type(unsigned type)
 {
@@ -64,6 +69,7 @@ u64 bch2_dirent_lookup(struct bch_fs *, subvol_inum,
 		       const struct bch_hash_info *,
 		       const struct qstr *, subvol_inum *);
 
+int bch2_empty_dir_snapshot(struct btree_trans *, u64, u32);
 int bch2_empty_dir_trans(struct btree_trans *, subvol_inum);
 int bch2_readdir(struct bch_fs *, subvol_inum, struct dir_context *);
 
diff --git a/fs/bcachefs/disk_groups.c b/fs/bcachefs/disk_groups.c
index d613695abf9f..06a7df529b40 100644
--- a/fs/bcachefs/disk_groups.c
+++ b/fs/bcachefs/disk_groups.c
@@ -89,19 +89,14 @@ err:
 
 void bch2_disk_groups_to_text(struct printbuf *out, struct bch_fs *c)
 {
-	struct bch_disk_groups_cpu *g;
-	struct bch_dev *ca;
-	int i;
-	unsigned iter;
-
 	out->atomic++;
 	rcu_read_lock();
 
-	g = rcu_dereference(c->disk_groups);
+	struct bch_disk_groups_cpu *g = rcu_dereference(c->disk_groups);
 	if (!g)
 		goto out;
 
-	for (i = 0; i < g->nr; i++) {
+	for (unsigned i = 0; i < g->nr; i++) {
 		if (i)
 			prt_printf(out, " ");
 
@@ -111,7 +106,7 @@ void bch2_disk_groups_to_text(struct printbuf *out, struct bch_fs *c)
 		}
 
 		prt_printf(out, "[parent %d devs", g->entries[i].parent);
-		for_each_member_device_rcu(ca, c, iter, &g->entries[i].devs)
+		for_each_member_device_rcu(c, ca, &g->entries[i].devs)
 			prt_printf(out, " %s", ca->name);
 		prt_printf(out, "]");
 	}
@@ -555,13 +550,14 @@ void bch2_target_to_text(struct printbuf *out, struct bch_fs *c, unsigned v)
 	case TARGET_DEV: {
 		struct bch_dev *ca;
 
+		out->atomic++;
 		rcu_read_lock();
 		ca = t.dev < c->sb.nr_devices
 			? rcu_dereference(c->devs[t.dev])
 			: NULL;
 
 		if (ca && percpu_ref_tryget(&ca->io_ref)) {
-			prt_printf(out, "/dev/%pg", ca->disk_sb.bdev);
+			prt_printf(out, "/dev/%s", ca->name);
 			percpu_ref_put(&ca->io_ref);
 		} else if (ca) {
 			prt_printf(out, "offline device %u", t.dev);
@@ -570,6 +566,7 @@ void bch2_target_to_text(struct printbuf *out, struct bch_fs *c, unsigned v)
 		}
 
 		rcu_read_unlock();
+		out->atomic--;
 		break;
 	}
 	case TARGET_GROUP:
@@ -580,7 +577,7 @@ void bch2_target_to_text(struct printbuf *out, struct bch_fs *c, unsigned v)
 	}
 }
 
-void bch2_target_to_text_sb(struct printbuf *out, struct bch_sb *sb, unsigned v)
+static void bch2_target_to_text_sb(struct printbuf *out, struct bch_sb *sb, unsigned v)
 {
 	struct target t = target_decode(v);
 
diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c
index 875f7c5a6fca..d802bc63c8d0 100644
--- a/fs/bcachefs/ec.c
+++ b/fs/bcachefs/ec.c
@@ -3,6 +3,7 @@
 /* erasure coding */
 
 #include "bcachefs.h"
+#include "alloc_background.h"
 #include "alloc_foreground.h"
 #include "backpointers.h"
 #include "bkey_buf.h"
@@ -156,12 +157,311 @@ void bch2_stripe_to_text(struct printbuf *out, struct bch_fs *c,
 	}
 }
 
+/* Triggers: */
+
+static int bch2_trans_mark_stripe_bucket(struct btree_trans *trans,
+					 struct bkey_s_c_stripe s,
+					 unsigned idx, bool deleting)
+{
+	struct bch_fs *c = trans->c;
+	const struct bch_extent_ptr *ptr = &s.v->ptrs[idx];
+	struct btree_iter iter;
+	struct bkey_i_alloc_v4 *a;
+	enum bch_data_type data_type = idx >= s.v->nr_blocks - s.v->nr_redundant
+		? BCH_DATA_parity : 0;
+	s64 sectors = data_type ? le16_to_cpu(s.v->sectors) : 0;
+	int ret = 0;
+
+	if (deleting)
+		sectors = -sectors;
+
+	a = bch2_trans_start_alloc_update(trans, &iter, PTR_BUCKET_POS(c, ptr));
+	if (IS_ERR(a))
+		return PTR_ERR(a);
+
+	ret = bch2_check_bucket_ref(trans, s.s_c, ptr, sectors, data_type,
+				    a->v.gen, a->v.data_type,
+				    a->v.dirty_sectors);
+	if (ret)
+		goto err;
+
+	if (!deleting) {
+		if (bch2_trans_inconsistent_on(a->v.stripe ||
+					       a->v.stripe_redundancy, trans,
+				"bucket %llu:%llu gen %u data type %s dirty_sectors %u: multiple stripes using same bucket (%u, %llu)",
+				iter.pos.inode, iter.pos.offset, a->v.gen,
+				bch2_data_types[a->v.data_type],
+				a->v.dirty_sectors,
+				a->v.stripe, s.k->p.offset)) {
+			ret = -EIO;
+			goto err;
+		}
+
+		if (bch2_trans_inconsistent_on(data_type && a->v.dirty_sectors, trans,
+				"bucket %llu:%llu gen %u data type %s dirty_sectors %u: data already in stripe bucket %llu",
+				iter.pos.inode, iter.pos.offset, a->v.gen,
+				bch2_data_types[a->v.data_type],
+				a->v.dirty_sectors,
+				s.k->p.offset)) {
+			ret = -EIO;
+			goto err;
+		}
+
+		a->v.stripe		= s.k->p.offset;
+		a->v.stripe_redundancy	= s.v->nr_redundant;
+		a->v.data_type		= BCH_DATA_stripe;
+	} else {
+		if (bch2_trans_inconsistent_on(a->v.stripe != s.k->p.offset ||
+					       a->v.stripe_redundancy != s.v->nr_redundant, trans,
+				"bucket %llu:%llu gen %u: not marked as stripe when deleting stripe %llu (got %u)",
+				iter.pos.inode, iter.pos.offset, a->v.gen,
+				s.k->p.offset, a->v.stripe)) {
+			ret = -EIO;
+			goto err;
+		}
+
+		a->v.stripe		= 0;
+		a->v.stripe_redundancy	= 0;
+		a->v.data_type		= alloc_data_type(a->v, BCH_DATA_user);
+	}
+
+	a->v.dirty_sectors += sectors;
+	if (data_type)
+		a->v.data_type = !deleting ? data_type : 0;
+
+	ret = bch2_trans_update(trans, &iter, &a->k_i, 0);
+	if (ret)
+		goto err;
+err:
+	bch2_trans_iter_exit(trans, &iter);
+	return ret;
+}
+
+static int mark_stripe_bucket(struct btree_trans *trans,
+			      struct bkey_s_c k,
+			      unsigned ptr_idx,
+			      unsigned flags)
+{
+	struct bch_fs *c = trans->c;
+	const struct bch_stripe *s = bkey_s_c_to_stripe(k).v;
+	unsigned nr_data = s->nr_blocks - s->nr_redundant;
+	bool parity = ptr_idx >= nr_data;
+	enum bch_data_type data_type = parity ? BCH_DATA_parity : BCH_DATA_stripe;
+	s64 sectors = parity ? le16_to_cpu(s->sectors) : 0;
+	const struct bch_extent_ptr *ptr = s->ptrs + ptr_idx;
+	struct bch_dev *ca = bch_dev_bkey_exists(c, ptr->dev);
+	struct bucket old, new, *g;
+	struct printbuf buf = PRINTBUF;
+	int ret = 0;
+
+	BUG_ON(!(flags & BTREE_TRIGGER_GC));
+
+	/* * XXX doesn't handle deletion */
+
+	percpu_down_read(&c->mark_lock);
+	g = PTR_GC_BUCKET(ca, ptr);
+
+	if (g->dirty_sectors ||
+	    (g->stripe && g->stripe != k.k->p.offset)) {
+		bch2_fs_inconsistent(c,
+			      "bucket %u:%zu gen %u: multiple stripes using same bucket\n%s",
+			      ptr->dev, PTR_BUCKET_NR(ca, ptr), g->gen,
+			      (bch2_bkey_val_to_text(&buf, c, k), buf.buf));
+		ret = -EINVAL;
+		goto err;
+	}
+
+	bucket_lock(g);
+	old = *g;
+
+	ret = bch2_check_bucket_ref(trans, k, ptr, sectors, data_type,
+				    g->gen, g->data_type,
+				    g->dirty_sectors);
+	if (ret)
+		goto err;
+
+	g->data_type = data_type;
+	g->dirty_sectors += sectors;
+
+	g->stripe		= k.k->p.offset;
+	g->stripe_redundancy	= s->nr_redundant;
+	new = *g;
+err:
+	bucket_unlock(g);
+	if (!ret)
+		bch2_dev_usage_update_m(c, ca, &old, &new);
+	percpu_up_read(&c->mark_lock);
+	printbuf_exit(&buf);
+	return ret;
+}
+
+int bch2_trigger_stripe(struct btree_trans *trans,
+			enum btree_id btree_id, unsigned level,
+			struct bkey_s_c old, struct bkey_s _new,
+			unsigned flags)
+{
+	struct bkey_s_c new = _new.s_c;
+	struct bch_fs *c = trans->c;
+	u64 idx = new.k->p.offset;
+	const struct bch_stripe *old_s = old.k->type == KEY_TYPE_stripe
+		? bkey_s_c_to_stripe(old).v : NULL;
+	const struct bch_stripe *new_s = new.k->type == KEY_TYPE_stripe
+		? bkey_s_c_to_stripe(new).v : NULL;
+
+	if (flags & BTREE_TRIGGER_TRANSACTIONAL) {
+		/*
+		 * If the pointers aren't changing, we don't need to do anything:
+		 */
+		if (new_s && old_s &&
+		    new_s->nr_blocks	== old_s->nr_blocks &&
+		    new_s->nr_redundant	== old_s->nr_redundant &&
+		    !memcmp(old_s->ptrs, new_s->ptrs,
+			    new_s->nr_blocks * sizeof(struct bch_extent_ptr)))
+			return 0;
+
+		BUG_ON(new_s && old_s &&
+		       (new_s->nr_blocks	!= old_s->nr_blocks ||
+			new_s->nr_redundant	!= old_s->nr_redundant));
+
+		if (new_s) {
+			s64 sectors = le16_to_cpu(new_s->sectors);
+
+			struct bch_replicas_padded r;
+			bch2_bkey_to_replicas(&r.e, new);
+			int ret = bch2_update_replicas_list(trans, &r.e, sectors * new_s->nr_redundant);
+			if (ret)
+				return ret;
+		}
+
+		if (old_s) {
+			s64 sectors = -((s64) le16_to_cpu(old_s->sectors));
+
+			struct bch_replicas_padded r;
+			bch2_bkey_to_replicas(&r.e, old);
+			int ret = bch2_update_replicas_list(trans, &r.e, sectors * old_s->nr_redundant);
+			if (ret)
+				return ret;
+		}
+
+		unsigned nr_blocks = new_s ? new_s->nr_blocks : old_s->nr_blocks;
+		for (unsigned i = 0; i < nr_blocks; i++) {
+			if (new_s && old_s &&
+			    !memcmp(&new_s->ptrs[i],
+				    &old_s->ptrs[i],
+				    sizeof(new_s->ptrs[i])))
+				continue;
+
+			if (new_s) {
+				int ret = bch2_trans_mark_stripe_bucket(trans,
+						bkey_s_c_to_stripe(new), i, false);
+				if (ret)
+					return ret;
+			}
+
+			if (old_s) {
+				int ret = bch2_trans_mark_stripe_bucket(trans,
+						bkey_s_c_to_stripe(old), i, true);
+				if (ret)
+					return ret;
+			}
+		}
+	}
+
+	if (!(flags & (BTREE_TRIGGER_TRANSACTIONAL|BTREE_TRIGGER_GC))) {
+		struct stripe *m = genradix_ptr(&c->stripes, idx);
+
+		if (!m) {
+			struct printbuf buf1 = PRINTBUF;
+			struct printbuf buf2 = PRINTBUF;
+
+			bch2_bkey_val_to_text(&buf1, c, old);
+			bch2_bkey_val_to_text(&buf2, c, new);
+			bch_err_ratelimited(c, "error marking nonexistent stripe %llu while marking\n"
+					    "old %s\n"
+					    "new %s", idx, buf1.buf, buf2.buf);
+			printbuf_exit(&buf2);
+			printbuf_exit(&buf1);
+			bch2_inconsistent_error(c);
+			return -1;
+		}
+
+		if (!new_s) {
+			bch2_stripes_heap_del(c, m, idx);
+
+			memset(m, 0, sizeof(*m));
+		} else {
+			m->sectors	= le16_to_cpu(new_s->sectors);
+			m->algorithm	= new_s->algorithm;
+			m->nr_blocks	= new_s->nr_blocks;
+			m->nr_redundant	= new_s->nr_redundant;
+			m->blocks_nonempty = 0;
+
+			for (unsigned i = 0; i < new_s->nr_blocks; i++)
+				m->blocks_nonempty += !!stripe_blockcount_get(new_s, i);
+
+			if (!old_s)
+				bch2_stripes_heap_insert(c, m, idx);
+			else
+				bch2_stripes_heap_update(c, m, idx);
+		}
+	}
+
+	if (flags & BTREE_TRIGGER_GC) {
+		struct gc_stripe *m =
+			genradix_ptr_alloc(&c->gc_stripes, idx, GFP_KERNEL);
+
+		if (!m) {
+			bch_err(c, "error allocating memory for gc_stripes, idx %llu",
+				idx);
+			return -BCH_ERR_ENOMEM_mark_stripe;
+		}
+		/*
+		 * This will be wrong when we bring back runtime gc: we should
+		 * be unmarking the old key and then marking the new key
+		 */
+		m->alive	= true;
+		m->sectors	= le16_to_cpu(new_s->sectors);
+		m->nr_blocks	= new_s->nr_blocks;
+		m->nr_redundant	= new_s->nr_redundant;
+
+		for (unsigned i = 0; i < new_s->nr_blocks; i++)
+			m->ptrs[i] = new_s->ptrs[i];
+
+		bch2_bkey_to_replicas(&m->r.e, new);
+
+		/*
+		 * gc recalculates this field from stripe ptr
+		 * references:
+		 */
+		memset(m->block_sectors, 0, sizeof(m->block_sectors));
+
+		for (unsigned i = 0; i < new_s->nr_blocks; i++) {
+			int ret = mark_stripe_bucket(trans, new, i, flags);
+			if (ret)
+				return ret;
+		}
+
+		int ret = bch2_update_replicas(c, new, &m->r.e,
+				      ((s64) m->sectors * m->nr_redundant),
+				      0, true);
+		if (ret) {
+			struct printbuf buf = PRINTBUF;
+
+			bch2_bkey_val_to_text(&buf, c, new);
+			bch2_fs_fatal_error(c, "no replicas entry for %s", buf.buf);
+			printbuf_exit(&buf);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
 /* returns blocknr in stripe that we matched: */
 static const struct bch_extent_ptr *bkey_matches_stripe(struct bch_stripe *s,
 						struct bkey_s_c k, unsigned *block)
 {
 	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
-	const struct bch_extent_ptr *ptr;
 	unsigned i, nr_data = s->nr_blocks - s->nr_redundant;
 
 	bkey_for_each_ptr(ptrs, ptr)
@@ -791,28 +1091,22 @@ static void ec_stripe_delete_work(struct work_struct *work)
 {
 	struct bch_fs *c =
 		container_of(work, struct bch_fs, ec_stripe_delete_work);
-	struct btree_trans *trans = bch2_trans_get(c);
-	int ret;
-	u64 idx;
 
 	while (1) {
 		mutex_lock(&c->ec_stripes_heap_lock);
-		idx = stripe_idx_to_delete(c);
+		u64 idx = stripe_idx_to_delete(c);
 		mutex_unlock(&c->ec_stripes_heap_lock);
 
 		if (!idx)
 			break;
 
-		ret = commit_do(trans, NULL, NULL, BTREE_INSERT_NOFAIL,
-				ec_stripe_delete(trans, idx));
-		if (ret) {
-			bch_err_fn(c, ret);
+		int ret = bch2_trans_do(c, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
+					ec_stripe_delete(trans, idx));
+		bch_err_fn(c, ret);
+		if (ret)
 			break;
-		}
 	}
 
-	bch2_trans_put(trans);
-
 	bch2_write_ref_put(c, BCH_WRITE_REF_stripe_delete);
 }
 
@@ -983,8 +1277,8 @@ static int ec_stripe_update_bucket(struct btree_trans *trans, struct ec_stripe_b
 
 	while (1) {
 		ret = commit_do(trans, NULL, NULL,
-				BTREE_INSERT_NOCHECK_RW|
-				BTREE_INSERT_NOFAIL,
+				BCH_TRANS_COMMIT_no_check_rw|
+				BCH_TRANS_COMMIT_no_enospc,
 			ec_stripe_update_extent(trans, bucket_pos, bucket.gen,
 						s, &bp_pos));
 		if (ret)
@@ -1005,7 +1299,7 @@ static int ec_stripe_update_extents(struct bch_fs *c, struct ec_stripe_buf *s)
 	unsigned i, nr_data = v->nr_blocks - v->nr_redundant;
 	int ret = 0;
 
-	ret = bch2_btree_write_buffer_flush(trans);
+	ret = bch2_btree_write_buffer_flush_sync(trans);
 	if (ret)
 		goto err;
 
@@ -1121,21 +1415,20 @@ static void ec_stripe_create(struct ec_stripe_new *s)
 	}
 
 	ret = bch2_trans_do(c, &s->res, NULL,
-			    BTREE_INSERT_NOCHECK_RW|
-			    BTREE_INSERT_NOFAIL,
+			    BCH_TRANS_COMMIT_no_check_rw|
+			    BCH_TRANS_COMMIT_no_enospc,
 			    ec_stripe_key_update(trans,
 					bkey_i_to_stripe(&s->new_stripe.key),
 					!s->have_existing_stripe));
+	bch_err_msg(c, ret, "creating stripe key");
 	if (ret) {
-		bch_err(c, "error creating stripe: error creating stripe key");
 		goto err;
 	}
 
 	ret = ec_stripe_update_extents(c, &s->new_stripe);
-	if (ret) {
-		bch_err_msg(c, ret, "creating stripe: error updating pointers");
+	bch_err_msg(c, ret, "error updating extents");
+	if (ret)
 		goto err;
-	}
 err:
 	bch2_disk_reservation_put(c, &s->res);
 
@@ -1250,18 +1543,17 @@ static int unsigned_cmp(const void *_l, const void *_r)
 static unsigned pick_blocksize(struct bch_fs *c,
 			       struct bch_devs_mask *devs)
 {
-	struct bch_dev *ca;
-	unsigned i, nr = 0, sizes[BCH_SB_MEMBERS_MAX];
+	unsigned nr = 0, sizes[BCH_SB_MEMBERS_MAX];
 	struct {
 		unsigned nr, size;
 	} cur = { 0, 0 }, best = { 0, 0 };
 
-	for_each_member_device_rcu(ca, c, i, devs)
+	for_each_member_device_rcu(c, ca, devs)
 		sizes[nr++] = ca->mi.bucket_size;
 
 	sort(sizes, nr, sizeof(unsigned), unsigned_cmp, NULL);
 
-	for (i = 0; i < nr; i++) {
+	for (unsigned i = 0; i < nr; i++) {
 		if (sizes[i] != cur.size) {
 			if (cur.nr > best.nr)
 				best = cur;
@@ -1344,8 +1636,6 @@ ec_new_stripe_head_alloc(struct bch_fs *c, unsigned target,
 			 enum bch_watermark watermark)
 {
 	struct ec_stripe_head *h;
-	struct bch_dev *ca;
-	unsigned i;
 
 	h = kzalloc(sizeof(*h), GFP_KERNEL);
 	if (!h)
@@ -1362,17 +1652,26 @@ ec_new_stripe_head_alloc(struct bch_fs *c, unsigned target,
 	rcu_read_lock();
 	h->devs = target_rw_devs(c, BCH_DATA_user, target);
 
-	for_each_member_device_rcu(ca, c, i, &h->devs)
+	for_each_member_device_rcu(c, ca, &h->devs)
 		if (!ca->mi.durability)
-			__clear_bit(i, h->devs.d);
+			__clear_bit(ca->dev_idx, h->devs.d);
 
 	h->blocksize = pick_blocksize(c, &h->devs);
 
-	for_each_member_device_rcu(ca, c, i, &h->devs)
+	for_each_member_device_rcu(c, ca, &h->devs)
 		if (ca->mi.bucket_size == h->blocksize)
 			h->nr_active_devs++;
 
 	rcu_read_unlock();
+
+	/*
+	 * If we only have redundancy + 1 devices, we're better off with just
+	 * replication:
+	 */
+	if (h->nr_active_devs < h->redundancy + 2)
+		bch_err(c, "insufficient devices available to create stripe (have %u, need %u) - mismatched bucket sizes?",
+			h->nr_active_devs, h->redundancy + 2);
+
 	list_add(&h->list, &c->ec_stripe_head_list);
 	return h;
 }
@@ -1406,7 +1705,7 @@ __bch2_ec_stripe_head_get(struct btree_trans *trans,
 	if (ret)
 		return ERR_PTR(ret);
 
-	if (test_bit(BCH_FS_GOING_RO, &c->flags)) {
+	if (test_bit(BCH_FS_going_ro, &c->flags)) {
 		h = ERR_PTR(-BCH_ERR_erofs_no_writes);
 		goto found;
 	}
@@ -1424,6 +1723,11 @@ __bch2_ec_stripe_head_get(struct btree_trans *trans,
 
 	h = ec_new_stripe_head_alloc(c, target, algo, redundancy, watermark);
 found:
+	if (!IS_ERR_OR_NULL(h) &&
+	    h->nr_active_devs < h->redundancy + 2) {
+		mutex_unlock(&h->lock);
+		h = NULL;
+	}
 	mutex_unlock(&c->ec_stripe_head_lock);
 	return h;
 }
@@ -1681,8 +1985,6 @@ struct ec_stripe_head *bch2_ec_stripe_head_get(struct btree_trans *trans,
 	int ret;
 
 	h = __bch2_ec_stripe_head_get(trans, target, algo, redundancy, watermark);
-	if (!h)
-		bch_err(c, "no stripe head");
 	if (IS_ERR_OR_NULL(h))
 		return h;
 
@@ -1821,44 +2123,32 @@ void bch2_fs_ec_flush(struct bch_fs *c)
 
 int bch2_stripes_read(struct bch_fs *c)
 {
-	struct btree_trans *trans = bch2_trans_get(c);
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	const struct bch_stripe *s;
-	struct stripe *m;
-	unsigned i;
-	int ret;
-
-	for_each_btree_key(trans, iter, BTREE_ID_stripes, POS_MIN,
-			   BTREE_ITER_PREFETCH, k, ret) {
-		if (k.k->type != KEY_TYPE_stripe)
-			continue;
-
-		ret = __ec_stripe_mem_alloc(c, k.k->p.offset, GFP_KERNEL);
-		if (ret)
-			break;
-
-		s = bkey_s_c_to_stripe(k).v;
+	int ret = bch2_trans_run(c,
+		for_each_btree_key(trans, iter, BTREE_ID_stripes, POS_MIN,
+				   BTREE_ITER_PREFETCH, k, ({
+			if (k.k->type != KEY_TYPE_stripe)
+				continue;
 
-		m = genradix_ptr(&c->stripes, k.k->p.offset);
-		m->sectors	= le16_to_cpu(s->sectors);
-		m->algorithm	= s->algorithm;
-		m->nr_blocks	= s->nr_blocks;
-		m->nr_redundant	= s->nr_redundant;
-		m->blocks_nonempty = 0;
+			ret = __ec_stripe_mem_alloc(c, k.k->p.offset, GFP_KERNEL);
+			if (ret)
+				break;
 
-		for (i = 0; i < s->nr_blocks; i++)
-			m->blocks_nonempty += !!stripe_blockcount_get(s, i);
+			const struct bch_stripe *s = bkey_s_c_to_stripe(k).v;
 
-		bch2_stripes_heap_insert(c, m, k.k->p.offset);
-	}
-	bch2_trans_iter_exit(trans, &iter);
+			struct stripe *m = genradix_ptr(&c->stripes, k.k->p.offset);
+			m->sectors	= le16_to_cpu(s->sectors);
+			m->algorithm	= s->algorithm;
+			m->nr_blocks	= s->nr_blocks;
+			m->nr_redundant	= s->nr_redundant;
+			m->blocks_nonempty = 0;
 
-	bch2_trans_put(trans);
-
-	if (ret)
-		bch_err_fn(c, ret);
+			for (unsigned i = 0; i < s->nr_blocks; i++)
+				m->blocks_nonempty += !!stripe_blockcount_get(s, i);
 
+			bch2_stripes_heap_insert(c, m, k.k->p.offset);
+			0;
+		})));
+	bch_err_fn(c, ret);
 	return ret;
 }
 
diff --git a/fs/bcachefs/ec.h b/fs/bcachefs/ec.h
index 7d0237c9819f..f4369b02e805 100644
--- a/fs/bcachefs/ec.h
+++ b/fs/bcachefs/ec.h
@@ -12,13 +12,14 @@ int bch2_stripe_invalid(struct bch_fs *, struct bkey_s_c,
 			enum bkey_invalid_flags, struct printbuf *);
 void bch2_stripe_to_text(struct printbuf *, struct bch_fs *,
 			 struct bkey_s_c);
+int bch2_trigger_stripe(struct btree_trans *, enum btree_id, unsigned,
+			struct bkey_s_c, struct bkey_s, unsigned);
 
 #define bch2_bkey_ops_stripe ((struct bkey_ops) {	\
 	.key_invalid	= bch2_stripe_invalid,		\
 	.val_to_text	= bch2_stripe_to_text,		\
 	.swab		= bch2_ptr_swab,		\
-	.trans_trigger	= bch2_trans_mark_stripe,	\
-	.atomic_trigger	= bch2_mark_stripe,		\
+	.trigger	= bch2_trigger_stripe,		\
 	.min_val_size	= 8,				\
 })
 
diff --git a/fs/bcachefs/ec_types.h b/fs/bcachefs/ec_types.h
index e2b02a82de32..976426da3a12 100644
--- a/fs/bcachefs/ec_types.h
+++ b/fs/bcachefs/ec_types.h
@@ -5,7 +5,7 @@
 #include "bcachefs_format.h"
 
 struct bch_replicas_padded {
-	struct bch_replicas_entry	e;
+	struct bch_replicas_entry_v1	e;
 	u8				pad[BCH_BKEY_PTRS_MAX];
 };
 
diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h
index 68a1a96bb7ca..8c40c2067a04 100644
--- a/fs/bcachefs/errcode.h
+++ b/fs/bcachefs/errcode.h
@@ -73,7 +73,6 @@
 	x(ENOMEM,			ENOMEM_fsck_add_nlink)			\
 	x(ENOMEM,			ENOMEM_journal_key_insert)		\
 	x(ENOMEM,			ENOMEM_journal_keys_sort)		\
-	x(ENOMEM,			ENOMEM_journal_replay)			\
 	x(ENOMEM,			ENOMEM_read_superblock_clean)		\
 	x(ENOMEM,			ENOMEM_fs_alloc)			\
 	x(ENOMEM,			ENOMEM_fs_name_alloc)			\
@@ -95,6 +94,7 @@
 	x(ENOSPC,			ENOSPC_sb_members)			\
 	x(ENOSPC,			ENOSPC_sb_members_v2)			\
 	x(ENOSPC,			ENOSPC_sb_crypt)			\
+	x(ENOSPC,			ENOSPC_sb_downgrade)			\
 	x(ENOSPC,			ENOSPC_btree_slot)			\
 	x(ENOSPC,			ENOSPC_snapshot_tree)			\
 	x(ENOENT,			ENOENT_bkey_type_mismatch)		\
@@ -151,7 +151,6 @@
 	x(BCH_ERR_btree_insert_fail,	btree_insert_need_mark_replicas)	\
 	x(BCH_ERR_btree_insert_fail,	btree_insert_need_journal_res)		\
 	x(BCH_ERR_btree_insert_fail,	btree_insert_need_journal_reclaim)	\
-	x(BCH_ERR_btree_insert_fail,	btree_insert_need_flush_buffer)		\
 	x(0,				backpointer_to_overwritten_btree_node)	\
 	x(0,				lock_fail_root_changed)			\
 	x(0,				journal_reclaim_would_deadlock)		\
@@ -162,7 +161,7 @@
 	x(BCH_ERR_fsck,			fsck_repair_unimplemented)		\
 	x(BCH_ERR_fsck,			fsck_repair_impossible)			\
 	x(0,				restart_recovery)			\
-	x(0,				unwritten_extent_update)		\
+	x(0,				data_update_done)			\
 	x(EINVAL,			device_state_not_allowed)		\
 	x(EINVAL,			member_info_missing)			\
 	x(EINVAL,			mismatched_block_size)			\
@@ -171,10 +170,12 @@
 	x(EINVAL,			device_size_too_small)			\
 	x(EINVAL,			device_not_a_member_of_filesystem)	\
 	x(EINVAL,			device_has_been_removed)		\
+	x(EINVAL,			device_splitbrain)			\
 	x(EINVAL,			device_already_online)			\
 	x(EINVAL,			insufficient_devices_to_start)		\
 	x(EINVAL,			invalid)				\
 	x(EINVAL,			internal_fsck_err)			\
+	x(EINVAL,			opt_parse_error)			\
 	x(EROFS,			erofs_trans_commit)			\
 	x(EROFS,			erofs_no_writes)			\
 	x(EROFS,			erofs_journal_err)			\
@@ -210,6 +211,7 @@
 	x(BCH_ERR_invalid_sb,		invalid_sb_members)			\
 	x(BCH_ERR_invalid_sb,		invalid_sb_disk_groups)			\
 	x(BCH_ERR_invalid_sb,		invalid_sb_replicas)			\
+	x(BCH_ERR_invalid_sb,		invalid_replicas_entry)			\
 	x(BCH_ERR_invalid_sb,		invalid_sb_journal)			\
 	x(BCH_ERR_invalid_sb,		invalid_sb_journal_seq_blacklist)	\
 	x(BCH_ERR_invalid_sb,		invalid_sb_crypt)			\
@@ -217,9 +219,13 @@
 	x(BCH_ERR_invalid_sb,		invalid_sb_quota)			\
 	x(BCH_ERR_invalid_sb,		invalid_sb_errors)			\
 	x(BCH_ERR_invalid_sb,		invalid_sb_opt_compression)		\
+	x(BCH_ERR_invalid_sb,		invalid_sb_ext)				\
+	x(BCH_ERR_invalid_sb,		invalid_sb_downgrade)			\
 	x(BCH_ERR_invalid,		invalid_bkey)				\
 	x(BCH_ERR_operation_blocked,    nocow_lock_blocked)			\
 	x(EIO,				btree_node_read_err)			\
+	x(EIO,				sb_not_downgraded)			\
+	x(EIO,				btree_write_all_failed)			\
 	x(BCH_ERR_btree_node_read_err,	btree_node_read_err_fixable)		\
 	x(BCH_ERR_btree_node_read_err,	btree_node_read_err_want_retry)		\
 	x(BCH_ERR_btree_node_read_err,	btree_node_read_err_must_retry)		\
@@ -231,6 +237,7 @@
 	x(BCH_ERR_nopromote,		nopromote_unwritten)			\
 	x(BCH_ERR_nopromote,		nopromote_congested)			\
 	x(BCH_ERR_nopromote,		nopromote_in_flight)			\
+	x(BCH_ERR_nopromote,		nopromote_no_writes)			\
 	x(BCH_ERR_nopromote,		nopromote_enomem)
 
 enum bch_errcode {
diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c
index 7b28d37922fd..d32c8bebe46c 100644
--- a/fs/bcachefs/error.c
+++ b/fs/bcachefs/error.c
@@ -2,12 +2,13 @@
 #include "bcachefs.h"
 #include "error.h"
 #include "super.h"
+#include "thread_with_file.h"
 
 #define FSCK_ERR_RATELIMIT_NR	10
 
 bool bch2_inconsistent_error(struct bch_fs *c)
 {
-	set_bit(BCH_FS_ERROR, &c->flags);
+	set_bit(BCH_FS_error, &c->flags);
 
 	switch (c->opts.errors) {
 	case BCH_ON_ERROR_continue:
@@ -26,8 +27,8 @@ bool bch2_inconsistent_error(struct bch_fs *c)
 
 void bch2_topology_error(struct bch_fs *c)
 {
-	set_bit(BCH_FS_TOPOLOGY_ERROR, &c->flags);
-	if (test_bit(BCH_FS_FSCK_DONE, &c->flags))
+	set_bit(BCH_FS_topology_error, &c->flags);
+	if (!test_bit(BCH_FS_fsck_running, &c->flags))
 		bch2_inconsistent_error(c);
 }
 
@@ -69,40 +70,66 @@ enum ask_yn {
 	YN_ALLYES,
 };
 
+static enum ask_yn parse_yn_response(char *buf)
+{
+	buf = strim(buf);
+
+	if (strlen(buf) == 1)
+		switch (buf[0]) {
+		case 'n':
+			return YN_NO;
+		case 'y':
+			return YN_YES;
+		case 'N':
+			return YN_ALLNO;
+		case 'Y':
+			return YN_ALLYES;
+		}
+	return -1;
+}
+
 #ifdef __KERNEL__
-#define bch2_fsck_ask_yn()	YN_NO
+static enum ask_yn bch2_fsck_ask_yn(struct bch_fs *c)
+{
+	struct stdio_redirect *stdio = c->stdio;
+
+	if (c->stdio_filter && c->stdio_filter != current)
+		stdio = NULL;
+
+	if (!stdio)
+		return YN_NO;
+
+	char buf[100];
+	int ret;
+
+	do {
+		bch2_print(c, " (y,n, or Y,N for all errors of this type) ");
+
+		int r = bch2_stdio_redirect_readline(stdio, buf, sizeof(buf) - 1);
+		if (r < 0)
+			return YN_NO;
+		buf[r] = '\0';
+	} while ((ret = parse_yn_response(buf)) < 0);
+
+	return ret;
+}
 #else
 
 #include "tools-util.h"
 
-enum ask_yn bch2_fsck_ask_yn(void)
+static enum ask_yn bch2_fsck_ask_yn(struct bch_fs *c)
 {
 	char *buf = NULL;
 	size_t buflen = 0;
-	bool ret;
+	int ret;
 
-	while (true) {
+	do {
 		fputs(" (y,n, or Y,N for all errors of this type) ", stdout);
 		fflush(stdout);
 
 		if (getline(&buf, &buflen, stdin) < 0)
 			die("error reading from standard input");
-
-		strim(buf);
-		if (strlen(buf) != 1)
-			continue;
-
-		switch (buf[0]) {
-		case 'n':
-			return YN_NO;
-		case 'y':
-			return YN_YES;
-		case 'N':
-			return YN_ALLNO;
-		case 'Y':
-			return YN_ALLYES;
-		}
-	}
+	} while ((ret = parse_yn_response(buf)) < 0);
 
 	free(buf);
 	return ret;
@@ -114,7 +141,7 @@ static struct fsck_err_state *fsck_err_get(struct bch_fs *c, const char *fmt)
 {
 	struct fsck_err_state *s;
 
-	if (test_bit(BCH_FS_FSCK_DONE, &c->flags))
+	if (!test_bit(BCH_FS_fsck_running, &c->flags))
 		return NULL;
 
 	list_for_each_entry(s, &c->fsck_error_msgs, list)
@@ -152,6 +179,10 @@ int bch2_fsck_err(struct bch_fs *c,
 	struct printbuf buf = PRINTBUF, *out = &buf;
 	int ret = -BCH_ERR_fsck_ignore;
 
+	if ((flags & FSCK_CAN_FIX) &&
+	    test_bit(err, c->sb.errors_silent))
+		return -BCH_ERR_fsck_fix;
+
 	bch2_sb_error_count(c, err);
 
 	va_start(args, fmt);
@@ -193,7 +224,7 @@ int bch2_fsck_err(struct bch_fs *c,
 		prt_printf(out, bch2_log_msg(c, ""));
 #endif
 
-	if (test_bit(BCH_FS_FSCK_DONE, &c->flags)) {
+	if (!test_bit(BCH_FS_fsck_running, &c->flags)) {
 		if (c->opts.errors != BCH_ON_ERROR_continue ||
 		    !(flags & (FSCK_CAN_FIX|FSCK_CAN_IGNORE))) {
 			prt_str(out, ", shutting down");
@@ -218,10 +249,13 @@ int bch2_fsck_err(struct bch_fs *c,
 			int ask;
 
 			prt_str(out, ": fix?");
-			bch2_print_string_as_lines(KERN_ERR, out->buf);
+			if (bch2_fs_stdio_redirect(c))
+				bch2_print(c, "%s", out->buf);
+			else
+				bch2_print_string_as_lines(KERN_ERR, out->buf);
 			print = false;
 
-			ask = bch2_fsck_ask_yn();
+			ask = bch2_fsck_ask_yn(c);
 
 			if (ask >= YN_ALLNO && s)
 				s->fix = ask == YN_ALLNO
@@ -250,10 +284,14 @@ int bch2_fsck_err(struct bch_fs *c,
 	     !(flags & FSCK_CAN_IGNORE)))
 		ret = -BCH_ERR_fsck_errors_not_fixed;
 
-	if (print)
-		bch2_print_string_as_lines(KERN_ERR, out->buf);
+	if (print) {
+		if (bch2_fs_stdio_redirect(c))
+			bch2_print(c, "%s\n", out->buf);
+		else
+			bch2_print_string_as_lines(KERN_ERR, out->buf);
+	}
 
-	if (!test_bit(BCH_FS_FSCK_DONE, &c->flags) &&
+	if (test_bit(BCH_FS_fsck_running, &c->flags) &&
 	    (ret != -BCH_ERR_fsck_fix &&
 	     ret != -BCH_ERR_fsck_ignore))
 		bch_err(c, "Unable to continue, halting");
@@ -271,10 +309,10 @@ int bch2_fsck_err(struct bch_fs *c,
 		bch2_inconsistent_error(c);
 
 	if (ret == -BCH_ERR_fsck_fix) {
-		set_bit(BCH_FS_ERRORS_FIXED, &c->flags);
+		set_bit(BCH_FS_errors_fixed, &c->flags);
 	} else {
-		set_bit(BCH_FS_ERRORS_NOT_FIXED, &c->flags);
-		set_bit(BCH_FS_ERROR, &c->flags);
+		set_bit(BCH_FS_errors_not_fixed, &c->flags);
+		set_bit(BCH_FS_error, &c->flags);
 	}
 
 	return ret;
diff --git a/fs/bcachefs/error.h b/fs/bcachefs/error.h
index d167d65986e0..fec17d1353d1 100644
--- a/fs/bcachefs/error.h
+++ b/fs/bcachefs/error.h
@@ -157,6 +157,7 @@ void bch2_flush_fsck_errs(struct bch_fs *);
 #define fsck_err_on(cond, c, _err_type, ...)				\
 	__fsck_err_on(cond, c, FSCK_CAN_FIX|FSCK_CAN_IGNORE, _err_type, __VA_ARGS__)
 
+__printf(4, 0)
 static inline void bch2_bkey_fsck_err(struct bch_fs *c,
 				     struct printbuf *err_msg,
 				     enum bch_sb_error_id err_type,
@@ -167,7 +168,6 @@ static inline void bch2_bkey_fsck_err(struct bch_fs *c,
 	va_start(args, fmt);
 	prt_vprintf(err_msg, fmt, args);
 	va_end(args);
-
 }
 
 #define bkey_fsck_err(c, _err_msg, _err_type, ...)			\
diff --git a/fs/bcachefs/extent_update.c b/fs/bcachefs/extent_update.c
index 21af6fb8cecf..b9033bb4f11c 100644
--- a/fs/bcachefs/extent_update.c
+++ b/fs/bcachefs/extent_update.c
@@ -100,7 +100,7 @@ static int count_iters_for_insert(struct btree_trans *trans,
 	return ret2 ?: ret;
 }
 
-#define EXTENT_ITERS_MAX	(BTREE_ITER_MAX / 3)
+#define EXTENT_ITERS_MAX	(BTREE_ITER_INITIAL / 3)
 
 int bch2_extent_atomic_end(struct btree_trans *trans,
 			   struct btree_iter *iter,
diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c
index a864de231b69..82ec056f4cdb 100644
--- a/fs/bcachefs/extents.c
+++ b/fs/bcachefs/extents.c
@@ -649,37 +649,31 @@ unsigned bch2_bkey_replicas(struct bch_fs *c, struct bkey_s_c k)
 	return replicas;
 }
 
-unsigned bch2_extent_ptr_desired_durability(struct bch_fs *c, struct extent_ptr_decoded *p)
+static inline unsigned __extent_ptr_durability(struct bch_dev *ca, struct extent_ptr_decoded *p)
 {
-	struct bch_dev *ca;
-
 	if (p->ptr.cached)
 		return 0;
 
-	ca = bch_dev_bkey_exists(c, p->ptr.dev);
-
-	return ca->mi.durability +
-		(p->has_ec
-		 ? p->ec.redundancy
-		 : 0);
+	return p->has_ec
+		? p->ec.redundancy + 1
+		: ca->mi.durability;
 }
 
-unsigned bch2_extent_ptr_durability(struct bch_fs *c, struct extent_ptr_decoded *p)
+unsigned bch2_extent_ptr_desired_durability(struct bch_fs *c, struct extent_ptr_decoded *p)
 {
-	struct bch_dev *ca;
+	struct bch_dev *ca = bch_dev_bkey_exists(c, p->ptr.dev);
 
-	if (p->ptr.cached)
-		return 0;
+	return __extent_ptr_durability(ca, p);
+}
 
-	ca = bch_dev_bkey_exists(c, p->ptr.dev);
+unsigned bch2_extent_ptr_durability(struct bch_fs *c, struct extent_ptr_decoded *p)
+{
+	struct bch_dev *ca = bch_dev_bkey_exists(c, p->ptr.dev);
 
 	if (ca->mi.state == BCH_MEMBER_STATE_failed)
 		return 0;
 
-	return ca->mi.durability +
-		(p->has_ec
-		 ? p->ec.redundancy
-		 : 0);
+	return __extent_ptr_durability(ca, p);
 }
 
 unsigned bch2_bkey_durability(struct bch_fs *c, struct bkey_s_c k)
@@ -849,7 +843,6 @@ void bch2_bkey_drop_device_noerror(struct bkey_s k, unsigned dev)
 const struct bch_extent_ptr *bch2_bkey_has_device_c(struct bkey_s_c k, unsigned dev)
 {
 	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
-	const struct bch_extent_ptr *ptr;
 
 	bkey_for_each_ptr(ptrs, ptr)
 		if (ptr->dev == dev)
@@ -861,7 +854,6 @@ const struct bch_extent_ptr *bch2_bkey_has_device_c(struct bkey_s_c k, unsigned
 bool bch2_bkey_has_target(struct bch_fs *c, struct bkey_s_c k, unsigned target)
 {
 	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
-	const struct bch_extent_ptr *ptr;
 
 	bkey_for_each_ptr(ptrs, ptr)
 		if (bch2_dev_in_target(c, ptr->dev, target) &&
@@ -1071,7 +1063,6 @@ static int extent_ptr_invalid(struct bch_fs *c,
 			      struct printbuf *err)
 {
 	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
-	const struct bch_extent_ptr *ptr2;
 	u64 bucket;
 	u32 bucket_offset;
 	struct bch_dev *ca;
@@ -1300,7 +1291,8 @@ unsigned bch2_bkey_ptrs_need_rebalance(struct bch_fs *c, struct bkey_s_c k,
 		unsigned i = 0;
 
 		bkey_for_each_ptr_decode(k.k, ptrs, p, entry) {
-			if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible) {
+			if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible ||
+			    p.ptr.unwritten) {
 				rewrite_ptrs = 0;
 				goto incompressible;
 			}
@@ -1312,7 +1304,6 @@ unsigned bch2_bkey_ptrs_need_rebalance(struct bch_fs *c, struct bkey_s_c k,
 	}
 incompressible:
 	if (target && bch2_target_accepts_data(c, BCH_DATA_user, target)) {
-		const struct bch_extent_ptr *ptr;
 		unsigned i = 0;
 
 		bkey_for_each_ptr(ptrs, ptr) {
diff --git a/fs/bcachefs/extents.h b/fs/bcachefs/extents.h
index a2ce8a3be13c..a855c94d43dd 100644
--- a/fs/bcachefs/extents.h
+++ b/fs/bcachefs/extents.h
@@ -300,7 +300,7 @@ static inline struct bkey_ptrs bch2_bkey_ptrs(struct bkey_s k)
 	bkey_extent_entry_for_each_from(_p, _entry, _p.start)
 
 #define __bkey_for_each_ptr(_start, _end, _ptr)				\
-	for ((_ptr) = (_start);						\
+	for (typeof(_start) (_ptr) = (_start);				\
 	     ((_ptr) = __bkey_ptr_next(_ptr, _end));			\
 	     (_ptr)++)
 
@@ -415,8 +415,7 @@ void bch2_btree_ptr_v2_compat(enum btree_id, unsigned, unsigned,
 	.key_invalid	= bch2_btree_ptr_invalid,		\
 	.val_to_text	= bch2_btree_ptr_to_text,		\
 	.swab		= bch2_ptr_swab,			\
-	.trans_trigger	= bch2_trans_mark_extent,		\
-	.atomic_trigger	= bch2_mark_extent,			\
+	.trigger	= bch2_trigger_extent,			\
 })
 
 #define bch2_bkey_ops_btree_ptr_v2 ((struct bkey_ops) {		\
@@ -424,8 +423,7 @@ void bch2_btree_ptr_v2_compat(enum btree_id, unsigned, unsigned,
 	.val_to_text	= bch2_btree_ptr_v2_to_text,		\
 	.swab		= bch2_ptr_swab,			\
 	.compat		= bch2_btree_ptr_v2_compat,		\
-	.trans_trigger	= bch2_trans_mark_extent,		\
-	.atomic_trigger	= bch2_mark_extent,			\
+	.trigger	= bch2_trigger_extent,			\
 	.min_val_size	= 40,					\
 })
 
@@ -439,8 +437,7 @@ bool bch2_extent_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c);
 	.swab		= bch2_ptr_swab,			\
 	.key_normalize	= bch2_extent_normalize,		\
 	.key_merge	= bch2_extent_merge,			\
-	.trans_trigger	= bch2_trans_mark_extent,		\
-	.atomic_trigger	= bch2_mark_extent,			\
+	.trigger	= bch2_trigger_extent,			\
 })
 
 /* KEY_TYPE_reservation: */
@@ -454,8 +451,7 @@ bool bch2_reservation_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c);
 	.key_invalid	= bch2_reservation_invalid,		\
 	.val_to_text	= bch2_reservation_to_text,		\
 	.key_merge	= bch2_reservation_merge,		\
-	.trans_trigger	= bch2_trans_mark_reservation,		\
-	.atomic_trigger	= bch2_mark_reservation,		\
+	.trigger	= bch2_trigger_reservation,		\
 	.min_val_size	= 8,					\
 })
 
@@ -547,7 +543,6 @@ static inline bool bkey_extent_is_allocation(const struct bkey *k)
 static inline bool bkey_extent_is_unwritten(struct bkey_s_c k)
 {
 	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
-	const struct bch_extent_ptr *ptr;
 
 	bkey_for_each_ptr(ptrs, ptr)
 		if (ptr->unwritten)
@@ -565,10 +560,9 @@ static inline struct bch_devs_list bch2_bkey_devs(struct bkey_s_c k)
 {
 	struct bch_devs_list ret = (struct bch_devs_list) { 0 };
 	struct bkey_ptrs_c p = bch2_bkey_ptrs_c(k);
-	const struct bch_extent_ptr *ptr;
 
 	bkey_for_each_ptr(p, ptr)
-		ret.devs[ret.nr++] = ptr->dev;
+		ret.data[ret.nr++] = ptr->dev;
 
 	return ret;
 }
@@ -577,11 +571,10 @@ static inline struct bch_devs_list bch2_bkey_dirty_devs(struct bkey_s_c k)
 {
 	struct bch_devs_list ret = (struct bch_devs_list) { 0 };
 	struct bkey_ptrs_c p = bch2_bkey_ptrs_c(k);
-	const struct bch_extent_ptr *ptr;
 
 	bkey_for_each_ptr(p, ptr)
 		if (!ptr->cached)
-			ret.devs[ret.nr++] = ptr->dev;
+			ret.data[ret.nr++] = ptr->dev;
 
 	return ret;
 }
@@ -590,11 +583,10 @@ static inline struct bch_devs_list bch2_bkey_cached_devs(struct bkey_s_c k)
 {
 	struct bch_devs_list ret = (struct bch_devs_list) { 0 };
 	struct bkey_ptrs_c p = bch2_bkey_ptrs_c(k);
-	const struct bch_extent_ptr *ptr;
 
 	bkey_for_each_ptr(p, ptr)
 		if (ptr->cached)
-			ret.devs[ret.nr++] = ptr->dev;
+			ret.data[ret.nr++] = ptr->dev;
 
 	return ret;
 }
diff --git a/fs/bcachefs/eytzinger.h b/fs/bcachefs/eytzinger.h
index 05429c9631cd..9637f636e32d 100644
--- a/fs/bcachefs/eytzinger.h
+++ b/fs/bcachefs/eytzinger.h
@@ -261,11 +261,11 @@ static inline ssize_t eytzinger0_find_le(void *base, size_t nr, size_t size,
 
 #define eytzinger0_find(base, nr, size, _cmp, search)			\
 ({									\
-	void *_base	= (base);					\
-	void *_search	= (search);					\
-	size_t _nr	= (nr);						\
-	size_t _size	= (size);					\
-	size_t _i	= 0;						\
+	void *_base		= (base);				\
+	const void *_search	= (search);				\
+	size_t _nr		= (nr);					\
+	size_t _size		= (size);				\
+	size_t _i		= 0;					\
 	int _res;							\
 									\
 	while (_i < _nr &&						\
diff --git a/fs/bcachefs/fs-common.c b/fs/bcachefs/fs-common.c
index 4496cf91a4c1..1c1ea0f0c692 100644
--- a/fs/bcachefs/fs-common.c
+++ b/fs/bcachefs/fs-common.c
@@ -166,10 +166,8 @@ int bch2_create_trans(struct btree_trans *trans,
 		if (ret)
 			goto err;
 
-		if (c->sb.version >= bcachefs_metadata_version_inode_backpointers) {
-			new_inode->bi_dir		= dir_u->bi_inum;
-			new_inode->bi_dir_offset	= dir_offset;
-		}
+		new_inode->bi_dir		= dir_u->bi_inum;
+		new_inode->bi_dir_offset	= dir_offset;
 	}
 
 	inode_iter.flags &= ~BTREE_ITER_ALL_SNAPSHOTS;
@@ -228,10 +226,8 @@ int bch2_link_trans(struct btree_trans *trans,
 	if (ret)
 		goto err;
 
-	if (c->sb.version >= bcachefs_metadata_version_inode_backpointers) {
-		inode_u->bi_dir		= dir.inum;
-		inode_u->bi_dir_offset	= dir_offset;
-	}
+	inode_u->bi_dir		= dir.inum;
+	inode_u->bi_dir_offset	= dir_offset;
 
 	ret =   bch2_inode_write(trans, &dir_iter, dir_u) ?:
 		bch2_inode_write(trans, &inode_iter, inode_u);
@@ -414,21 +410,19 @@ int bch2_rename_trans(struct btree_trans *trans,
 			goto err;
 	}
 
-	if (c->sb.version >= bcachefs_metadata_version_inode_backpointers) {
-		src_inode_u->bi_dir		= dst_dir_u->bi_inum;
-		src_inode_u->bi_dir_offset	= dst_offset;
+	src_inode_u->bi_dir		= dst_dir_u->bi_inum;
+	src_inode_u->bi_dir_offset	= dst_offset;
 
-		if (mode == BCH_RENAME_EXCHANGE) {
-			dst_inode_u->bi_dir		= src_dir_u->bi_inum;
-			dst_inode_u->bi_dir_offset	= src_offset;
-		}
+	if (mode == BCH_RENAME_EXCHANGE) {
+		dst_inode_u->bi_dir		= src_dir_u->bi_inum;
+		dst_inode_u->bi_dir_offset	= src_offset;
+	}
 
-		if (mode == BCH_RENAME_OVERWRITE &&
-		    dst_inode_u->bi_dir		== dst_dir_u->bi_inum &&
-		    dst_inode_u->bi_dir_offset	== src_offset) {
-			dst_inode_u->bi_dir		= 0;
-			dst_inode_u->bi_dir_offset	= 0;
-		}
+	if (mode == BCH_RENAME_OVERWRITE &&
+	    dst_inode_u->bi_dir		== dst_dir_u->bi_inum &&
+	    dst_inode_u->bi_dir_offset	== src_offset) {
+		dst_inode_u->bi_dir		= 0;
+		dst_inode_u->bi_dir_offset	= 0;
 	}
 
 	if (mode == BCH_RENAME_OVERWRITE) {
diff --git a/fs/bcachefs/fs-io-buffered.c b/fs/bcachefs/fs-io-buffered.c
index 52f0e7acda3d..73c12e565af5 100644
--- a/fs/bcachefs/fs-io-buffered.c
+++ b/fs/bcachefs/fs-io-buffered.c
@@ -52,26 +52,20 @@ struct readpages_iter {
 static int readpages_iter_init(struct readpages_iter *iter,
 			       struct readahead_control *ractl)
 {
-	struct folio **fi;
-	int ret;
-
-	memset(iter, 0, sizeof(*iter));
+	struct folio *folio;
 
-	iter->mapping = ractl->mapping;
+	*iter = (struct readpages_iter) { ractl->mapping };
 
-	ret = bch2_filemap_get_contig_folios_d(iter->mapping,
-				ractl->_index << PAGE_SHIFT,
-				(ractl->_index + ractl->_nr_pages) << PAGE_SHIFT,
-				0, mapping_gfp_mask(iter->mapping),
-				&iter->folios);
-	if (ret)
-		return ret;
+	while ((folio = __readahead_folio(ractl))) {
+		if (!bch2_folio_create(folio, GFP_KERNEL) ||
+		    darray_push(&iter->folios, folio)) {
+			bch2_folio_release(folio);
+			ractl->_nr_pages += folio_nr_pages(folio);
+			ractl->_index -= folio_nr_pages(folio);
+			return iter->folios.nr ? 0 : -ENOMEM;
+		}
 
-	darray_for_each(iter->folios, fi) {
-		ractl->_nr_pages -= 1U << folio_order(*fi);
-		__bch2_folio_create(*fi, __GFP_NOFAIL|GFP_KERNEL);
-		folio_put(*fi);
-		folio_put(*fi);
+		folio_put(folio);
 	}
 
 	return 0;
@@ -273,12 +267,12 @@ void bch2_readahead(struct readahead_control *ractl)
 	struct btree_trans *trans = bch2_trans_get(c);
 	struct folio *folio;
 	struct readpages_iter readpages_iter;
-	int ret;
 
 	bch2_inode_opts_get(&opts, c, &inode->ei_inode);
 
-	ret = readpages_iter_init(&readpages_iter, ractl);
-	BUG_ON(ret);
+	int ret = readpages_iter_init(&readpages_iter, ractl);
+	if (ret)
+		return;
 
 	bch2_pagecache_add_get(inode);
 
@@ -638,7 +632,7 @@ do_io:
 		/* Check for writing past i_size: */
 		WARN_ONCE((bio_end_sector(&w->io->op.wbio.bio) << 9) >
 			  round_up(i_size, block_bytes(c)) &&
-			  !test_bit(BCH_FS_EMERGENCY_RO, &c->flags),
+			  !test_bit(BCH_FS_emergency_ro, &c->flags),
 			  "writing past i_size: %llu > %llu (unrounded %llu)\n",
 			  bio_end_sector(&w->io->op.wbio.bio) << 9,
 			  round_up(i_size, block_bytes(c)),
@@ -826,7 +820,7 @@ static int __bch2_buffered_write(struct bch_inode_info *inode,
 	struct bch_fs *c = inode->v.i_sb->s_fs_info;
 	struct bch2_folio_reservation res;
 	folios fs;
-	struct folio **fi, *f;
+	struct folio *f;
 	unsigned copied = 0, f_offset, f_copied;
 	u64 end = pos + len, f_pos, f_len;
 	loff_t last_folio_pos = inode->v.i_size;
diff --git a/fs/bcachefs/fs-io-direct.c b/fs/bcachefs/fs-io-direct.c
index 5b42a76c4796..fdd57c5785c9 100644
--- a/fs/bcachefs/fs-io-direct.c
+++ b/fs/bcachefs/fs-io-direct.c
@@ -35,9 +35,9 @@ static void bio_check_or_release(struct bio *bio, bool check_dirty)
 	}
 }
 
-static void bch2_dio_read_complete(struct closure *cl)
+static CLOSURE_CALLBACK(bch2_dio_read_complete)
 {
-	struct dio_read *dio = container_of(cl, struct dio_read, cl);
+	closure_type(dio, struct dio_read, cl);
 
 	dio->req->ki_complete(dio->req, dio->ret);
 	bio_check_or_release(&dio->rbio.bio, dio->should_dirty);
@@ -77,9 +77,6 @@ static int bch2_direct_IO_read(struct kiocb *req, struct iov_iter *iter)
 
 	bch2_inode_opts_get(&opts, c, &inode->ei_inode);
 
-	if ((offset|iter->count) & (block_bytes(c) - 1))
-		return -EINVAL;
-
 	ret = min_t(loff_t, iter->count,
 		    max_t(loff_t, 0, i_size_read(&inode->v) - offset));
 
@@ -216,11 +213,11 @@ struct dio_write {
 	struct address_space		*mapping;
 	struct bch_inode_info		*inode;
 	struct mm_struct		*mm;
+	const struct iovec		*iov;
 	unsigned			loop:1,
 					extending:1,
 					sync:1,
-					flush:1,
-					free_iov:1;
+					flush:1;
 	struct quota_res		quota_res;
 	u64				written;
 
@@ -312,12 +309,10 @@ static noinline int bch2_dio_write_copy_iov(struct dio_write *dio)
 		return -1;
 
 	if (dio->iter.nr_segs > ARRAY_SIZE(dio->inline_vecs)) {
-		iov = kmalloc_array(dio->iter.nr_segs, sizeof(*iov),
+		dio->iov = iov = kmalloc_array(dio->iter.nr_segs, sizeof(*iov),
 				    GFP_KERNEL);
 		if (unlikely(!iov))
 			return -ENOMEM;
-
-		dio->free_iov = true;
 	}
 
 	memcpy(iov, dio->iter.__iov, dio->iter.nr_segs * sizeof(*iov));
@@ -325,9 +320,9 @@ static noinline int bch2_dio_write_copy_iov(struct dio_write *dio)
 	return 0;
 }
 
-static void bch2_dio_write_flush_done(struct closure *cl)
+static CLOSURE_CALLBACK(bch2_dio_write_flush_done)
 {
-	struct dio_write *dio = container_of(cl, struct dio_write, op.cl);
+	closure_type(dio, struct dio_write, op.cl);
 	struct bch_fs *c = dio->op.c;
 
 	closure_debug_destroy(cl);
@@ -381,8 +376,7 @@ static __always_inline long bch2_dio_write_done(struct dio_write *dio)
 
 	bch2_pagecache_block_put(inode);
 
-	if (dio->free_iov)
-		kfree(dio->iter.__iov);
+	kfree(dio->iov);
 
 	ret = dio->op.error ?: ((long) dio->written << 9);
 	bio_put(&dio->op.wbio.bio);
@@ -626,11 +620,11 @@ ssize_t bch2_direct_write(struct kiocb *req, struct iov_iter *iter)
 	dio->mapping		= mapping;
 	dio->inode		= inode;
 	dio->mm			= current->mm;
+	dio->iov		= NULL;
 	dio->loop		= false;
 	dio->extending		= extending;
 	dio->sync		= is_sync_kiocb(req) || extending;
 	dio->flush		= iocb_is_dsync(req) && !c->opts.journal_flush_disabled;
-	dio->free_iov		= false;
 	dio->quota_res.sectors	= 0;
 	dio->written		= 0;
 	dio->iter		= *iter;
diff --git a/fs/bcachefs/fs-io-pagecache.c b/fs/bcachefs/fs-io-pagecache.c
index 8bd9bcdd27f7..ff664fd0d8ef 100644
--- a/fs/bcachefs/fs-io-pagecache.c
+++ b/fs/bcachefs/fs-io-pagecache.c
@@ -13,7 +13,7 @@
 
 int bch2_filemap_get_contig_folios_d(struct address_space *mapping,
 				     loff_t start, u64 end,
-				     int fgp_flags, gfp_t gfp,
+				     fgf_t fgp_flags, gfp_t gfp,
 				     folios *fs)
 {
 	struct folio *f;
diff --git a/fs/bcachefs/fs-io-pagecache.h b/fs/bcachefs/fs-io-pagecache.h
index a2222ad586e9..27f712ae37a6 100644
--- a/fs/bcachefs/fs-io-pagecache.h
+++ b/fs/bcachefs/fs-io-pagecache.h
@@ -7,7 +7,7 @@
 typedef DARRAY(struct folio *) folios;
 
 int bch2_filemap_get_contig_folios_d(struct address_space *, loff_t,
-				     u64, int, gfp_t, folios *);
+				     u64, fgf_t, gfp_t, folios *);
 int bch2_write_invalidate_inode_pages_range(struct address_space *, loff_t, loff_t);
 
 /*
diff --git a/fs/bcachefs/fs-io.c b/fs/bcachefs/fs-io.c
index b0e8144ec550..98bd5babab19 100644
--- a/fs/bcachefs/fs-io.c
+++ b/fs/bcachefs/fs-io.c
@@ -192,13 +192,17 @@ int bch2_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	struct bch_inode_info *inode = file_bch_inode(file);
 	struct bch_fs *c = inode->v.i_sb->s_fs_info;
-	int ret, ret2, ret3;
+	int ret;
 
 	ret = file_write_and_wait_range(file, start, end);
-	ret2 = sync_inode_metadata(&inode->v, 1);
-	ret3 = bch2_flush_inode(c, inode);
-
-	return bch2_err_class(ret ?: ret2 ?: ret3);
+	if (ret)
+		goto out;
+	ret = sync_inode_metadata(&inode->v, 1);
+	if (ret)
+		goto out;
+	ret = bch2_flush_inode(c, inode);
+out:
+	return bch2_err_class(ret);
 }
 
 /* truncate: */
@@ -861,7 +865,8 @@ loff_t bch2_remap_file_range(struct file *file_src, loff_t pos_src,
 	    abs(pos_src - pos_dst) < len)
 		return -EINVAL;
 
-	bch2_lock_inodes(INODE_LOCK|INODE_PAGECACHE_BLOCK, src, dst);
+	lock_two_nondirectories(&src->v, &dst->v);
+	bch2_lock_inodes(INODE_PAGECACHE_BLOCK, src, dst);
 
 	inode_dio_wait(&src->v);
 	inode_dio_wait(&dst->v);
@@ -914,7 +919,8 @@ loff_t bch2_remap_file_range(struct file *file_src, loff_t pos_src,
 		ret = bch2_flush_inode(c, dst);
 err:
 	bch2_quota_reservation_put(c, dst, &quota_res);
-	bch2_unlock_inodes(INODE_LOCK|INODE_PAGECACHE_BLOCK, src, dst);
+	bch2_unlock_inodes(INODE_PAGECACHE_BLOCK, src, dst);
+	unlock_two_nondirectories(&src->v, &dst->v);
 
 	return bch2_err_class(ret);
 }
diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c
index 5a39bcb597a3..946cc610eef5 100644
--- a/fs/bcachefs/fs-ioctl.c
+++ b/fs/bcachefs/fs-ioctl.c
@@ -100,7 +100,8 @@ static int bch2_ioc_setflags(struct bch_fs *c,
 	}
 
 	mutex_lock(&inode->ei_update_lock);
-	ret = bch2_write_inode(c, inode, bch2_inode_flags_set, &s,
+	ret   = bch2_subvol_is_ro(c, inode->ei_subvol) ?:
+		bch2_write_inode(c, inode, bch2_inode_flags_set, &s,
 			       ATTR_CTIME);
 	mutex_unlock(&inode->ei_update_lock);
 
@@ -183,13 +184,10 @@ static int bch2_ioc_fssetxattr(struct bch_fs *c,
 	}
 
 	mutex_lock(&inode->ei_update_lock);
-	ret = bch2_set_projid(c, inode, fa.fsx_projid);
-	if (ret)
-		goto err_unlock;
-
-	ret = bch2_write_inode(c, inode, fssetxattr_inode_update_fn, &s,
+	ret   = bch2_subvol_is_ro(c, inode->ei_subvol) ?:
+		bch2_set_projid(c, inode, fa.fsx_projid) ?:
+		bch2_write_inode(c, inode, fssetxattr_inode_update_fn, &s,
 			       ATTR_CTIME);
-err_unlock:
 	mutex_unlock(&inode->ei_update_lock);
 err:
 	inode_unlock(&inode->v);
@@ -287,34 +285,26 @@ static int bch2_ioc_goingdown(struct bch_fs *c, u32 __user *arg)
 
 	bch_notice(c, "shutdown by ioctl type %u", flags);
 
-	down_write(&c->vfs_sb->s_umount);
-
 	switch (flags) {
 	case FSOP_GOING_FLAGS_DEFAULT:
-		ret = freeze_bdev(c->vfs_sb->s_bdev);
+		ret = bdev_freeze(c->vfs_sb->s_bdev);
 		if (ret)
-			goto err;
-
+			break;
 		bch2_journal_flush(&c->journal);
-		c->vfs_sb->s_flags |= SB_RDONLY;
 		bch2_fs_emergency_read_only(c);
-		thaw_bdev(c->vfs_sb->s_bdev);
+		bdev_thaw(c->vfs_sb->s_bdev);
 		break;
-
 	case FSOP_GOING_FLAGS_LOGFLUSH:
 		bch2_journal_flush(&c->journal);
 		fallthrough;
-
 	case FSOP_GOING_FLAGS_NOLOGFLUSH:
-		c->vfs_sb->s_flags |= SB_RDONLY;
 		bch2_fs_emergency_read_only(c);
 		break;
 	default:
 		ret = -EINVAL;
 		break;
 	}
-err:
-	up_write(&c->vfs_sb->s_umount);
+
 	return ret;
 }
 
@@ -413,7 +403,7 @@ retry:
 
 	if ((arg.flags & BCH_SUBVOL_SNAPSHOT_CREATE) &&
 	    !arg.src_ptr)
-		snapshot_src.subvol = to_bch_ei(dir)->ei_inode.bi_subvol;
+		snapshot_src.subvol = inode_inum(to_bch_ei(dir)).subvol;
 
 	inode = __bch2_create(file_mnt_idmap(filp), to_bch_ei(dir),
 			      dst_dentry, arg.mode|S_IFDIR,
diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index 166d8d8abe68..ec419b8e2c43 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -93,7 +93,7 @@ retry:
 				BTREE_ITER_INTENT) ?:
 		(set ? set(trans, inode, &inode_u, p) : 0) ?:
 		bch2_inode_write(trans, &iter, &inode_u) ?:
-		bch2_trans_commit(trans, NULL, NULL, BTREE_INSERT_NOFAIL);
+		bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc);
 
 	/*
 	 * the btree node lock protects inode->ei_inode, not ei_update_lock;
@@ -258,7 +258,8 @@ __bch2_create(struct mnt_idmap *idmap,
 retry:
 	bch2_trans_begin(trans);
 
-	ret   = bch2_create_trans(trans,
+	ret   = bch2_subvol_is_ro_trans(trans, dir->ei_subvol) ?:
+		bch2_create_trans(trans,
 				  inode_inum(dir), &dir_u, &inode_u,
 				  !(flags & BCH_CREATE_TMPFILE)
 				  ? &dentry->d_name : NULL,
@@ -430,7 +431,9 @@ static int bch2_link(struct dentry *old_dentry, struct inode *vdir,
 
 	lockdep_assert_held(&inode->v.i_rwsem);
 
-	ret = __bch2_link(c, inode, dir, dentry);
+	ret   = bch2_subvol_is_ro(c, dir->ei_subvol) ?:
+		bch2_subvol_is_ro(c, inode->ei_subvol) ?:
+		__bch2_link(c, inode, dir, dentry);
 	if (unlikely(ret))
 		return ret;
 
@@ -452,7 +455,7 @@ int __bch2_unlink(struct inode *vdir, struct dentry *dentry,
 	bch2_lock_inodes(INODE_UPDATE_LOCK, dir, inode);
 
 	ret = commit_do(trans, NULL, NULL,
-			BTREE_INSERT_NOFAIL,
+			BCH_TRANS_COMMIT_no_enospc,
 		bch2_unlink_trans(trans,
 				  inode_inum(dir), &dir_u,
 				  &inode_u, &dentry->d_name,
@@ -481,7 +484,11 @@ err:
 
 static int bch2_unlink(struct inode *vdir, struct dentry *dentry)
 {
-	return __bch2_unlink(vdir, dentry, false);
+	struct bch_inode_info *dir= to_bch_ei(vdir);
+	struct bch_fs *c = dir->v.i_sb->s_fs_info;
+
+	return bch2_subvol_is_ro(c, dir->ei_subvol) ?:
+		__bch2_unlink(vdir, dentry, false);
 }
 
 static int bch2_symlink(struct mnt_idmap *idmap,
@@ -562,6 +569,11 @@ static int bch2_rename2(struct mnt_idmap *idmap,
 			 src_inode,
 			 dst_inode);
 
+	ret   = bch2_subvol_is_ro_trans(trans, src_dir->ei_subvol) ?:
+		bch2_subvol_is_ro_trans(trans, dst_dir->ei_subvol);
+	if (ret)
+		goto err;
+
 	if (inode_attr_changing(dst_dir, src_inode, Inode_opt_project)) {
 		ret = bch2_fs_quota_transfer(c, src_inode,
 					     dst_dir->ei_qid,
@@ -717,7 +729,7 @@ retry:
 
 	ret =   bch2_inode_write(trans, &inode_iter, &inode_u) ?:
 		bch2_trans_commit(trans, NULL, NULL,
-				  BTREE_INSERT_NOFAIL);
+				  BCH_TRANS_COMMIT_no_enospc);
 btree_err:
 	bch2_trans_iter_exit(trans, &inode_iter);
 
@@ -783,11 +795,13 @@ static int bch2_setattr(struct mnt_idmap *idmap,
 			struct dentry *dentry, struct iattr *iattr)
 {
 	struct bch_inode_info *inode = to_bch_ei(dentry->d_inode);
+	struct bch_fs *c = inode->v.i_sb->s_fs_info;
 	int ret;
 
 	lockdep_assert_held(&inode->v.i_rwsem);
 
-	ret = setattr_prepare(idmap, dentry, iattr);
+	ret   = bch2_subvol_is_ro(c, inode->ei_subvol) ?:
+		setattr_prepare(idmap, dentry, iattr);
 	if (ret)
 		return ret;
 
@@ -998,24 +1012,36 @@ static int bch2_vfs_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct bch_inode_info *inode = file_bch_inode(file);
 	struct bch_fs *c = inode->v.i_sb->s_fs_info;
-	int ret;
 
 	if (!dir_emit_dots(file, ctx))
 		return 0;
 
-	ret = bch2_readdir(c, inode_inum(inode), ctx);
-	if (ret)
-		bch_err_fn(c, ret);
+	int ret = bch2_readdir(c, inode_inum(inode), ctx);
 
+	bch_err_fn(c, ret);
 	return bch2_err_class(ret);
 }
 
+static int bch2_open(struct inode *vinode, struct file *file)
+{
+	if (file->f_flags & (O_WRONLY|O_RDWR)) {
+		struct bch_inode_info *inode = to_bch_ei(vinode);
+		struct bch_fs *c = inode->v.i_sb->s_fs_info;
+
+		int ret = bch2_subvol_is_ro(c, inode->ei_subvol);
+		if (ret)
+			return ret;
+	}
+
+	return generic_file_open(vinode, file);
+}
+
 static const struct file_operations bch_file_operations = {
+	.open		= bch2_open,
 	.llseek		= bch2_llseek,
 	.read_iter	= bch2_read_iter,
 	.write_iter	= bch2_write_iter,
 	.mmap		= bch2_mmap,
-	.open		= generic_file_open,
 	.fsync		= bch2_fsync,
 	.splice_read	= filemap_splice_read,
 	.splice_write	= iter_file_splice_write,
@@ -1103,7 +1129,7 @@ static const struct address_space_operations bch_address_space_operations = {
 #ifdef CONFIG_MIGRATION
 	.migrate_folio	= filemap_migrate_folio,
 #endif
-	.error_remove_page = generic_error_remove_page,
+	.error_remove_folio = generic_error_remove_folio,
 };
 
 struct bcachefs_fid {
@@ -1143,24 +1169,33 @@ static int bch2_encode_fh(struct inode *vinode, u32 *fh, int *len,
 {
 	struct bch_inode_info *inode	= to_bch_ei(vinode);
 	struct bch_inode_info *dir	= to_bch_ei(vdir);
-
-	if (*len < sizeof(struct bcachefs_fid_with_parent) / sizeof(u32))
-		return FILEID_INVALID;
+	int min_len;
 
 	if (!S_ISDIR(inode->v.i_mode) && dir) {
 		struct bcachefs_fid_with_parent *fid = (void *) fh;
 
+		min_len = sizeof(*fid) / sizeof(u32);
+		if (*len < min_len) {
+			*len = min_len;
+			return FILEID_INVALID;
+		}
+
 		fid->fid = bch2_inode_to_fid(inode);
 		fid->dir = bch2_inode_to_fid(dir);
 
-		*len = sizeof(*fid) / sizeof(u32);
+		*len = min_len;
 		return FILEID_BCACHEFS_WITH_PARENT;
 	} else {
 		struct bcachefs_fid *fid = (void *) fh;
 
+		min_len = sizeof(*fid) / sizeof(u32);
+		if (*len < min_len) {
+			*len = min_len;
+			return FILEID_INVALID;
+		}
 		*fid = bch2_inode_to_fid(inode);
 
-		*len = sizeof(*fid) / sizeof(u32);
+		*len = min_len;
 		return FILEID_BCACHEFS_WITHOUT_PARENT;
 	}
 }
@@ -1463,7 +1498,7 @@ static void bch2_evict_inode(struct inode *vinode)
 
 void bch2_evict_subvolume_inodes(struct bch_fs *c, snapshot_id_list *s)
 {
-	struct bch_inode_info *inode, **i;
+	struct bch_inode_info *inode;
 	DARRAY(struct bch_inode_info *) grabbed;
 	bool clean_pass = false, this_pass_clean;
 
@@ -1589,43 +1624,18 @@ static struct bch_fs *bch2_path_to_fs(const char *path)
 	return c ?: ERR_PTR(-ENOENT);
 }
 
-static char **split_devs(const char *_dev_name, unsigned *nr)
-{
-	char *dev_name = NULL, **devs = NULL, *s;
-	size_t i = 0, nr_devs = 0;
-
-	dev_name = kstrdup(_dev_name, GFP_KERNEL);
-	if (!dev_name)
-		return NULL;
-
-	for (s = dev_name; s; s = strchr(s + 1, ':'))
-		nr_devs++;
-
-	devs = kcalloc(nr_devs + 1, sizeof(const char *), GFP_KERNEL);
-	if (!devs) {
-		kfree(dev_name);
-		return NULL;
-	}
-
-	while ((s = strsep(&dev_name, ":")))
-		devs[i++] = s;
-
-	*nr = nr_devs;
-	return devs;
-}
-
 static int bch2_remount(struct super_block *sb, int *flags, char *data)
 {
 	struct bch_fs *c = sb->s_fs_info;
 	struct bch_opts opts = bch2_opts_empty();
 	int ret;
 
-	opt_set(opts, read_only, (*flags & SB_RDONLY) != 0);
-
 	ret = bch2_parse_mount_opts(c, &opts, data);
 	if (ret)
 		goto err;
 
+	opt_set(opts, read_only, (*flags & SB_RDONLY) != 0);
+
 	if (opts.read_only != c->opts.read_only) {
 		down_write(&c->state_lock);
 
@@ -1659,16 +1669,13 @@ err:
 static int bch2_show_devname(struct seq_file *seq, struct dentry *root)
 {
 	struct bch_fs *c = root->d_sb->s_fs_info;
-	struct bch_dev *ca;
-	unsigned i;
 	bool first = true;
 
-	for_each_online_member(ca, c, i) {
+	for_each_online_member(c, ca) {
 		if (!first)
 			seq_putc(seq, ':');
 		first = false;
-		seq_puts(seq, "/dev/");
-		seq_puts(seq, ca->name);
+		seq_puts(seq, ca->disk_sb.sb_name);
 	}
 
 	return 0;
@@ -1734,6 +1741,9 @@ static int bch2_unfreeze(struct super_block *sb)
 	struct bch_fs *c = sb->s_fs_info;
 	int ret;
 
+	if (test_bit(BCH_FS_emergency_ro, &c->flags))
+		return 0;
+
 	down_write(&c->state_lock);
 	ret = bch2_fs_read_write(c);
 	up_write(&c->state_lock);
@@ -1766,17 +1776,18 @@ static int bch2_noset_super(struct super_block *s, void *data)
 	return -EBUSY;
 }
 
+typedef DARRAY(struct bch_fs *) darray_fs;
+
 static int bch2_test_super(struct super_block *s, void *data)
 {
 	struct bch_fs *c = s->s_fs_info;
-	struct bch_fs **devs = data;
-	unsigned i;
+	darray_fs *d = data;
 
 	if (!c)
 		return false;
 
-	for (i = 0; devs[i]; i++)
-		if (c != devs[i])
+	darray_for_each(*d, i)
+		if (c != *i)
 			return false;
 	return true;
 }
@@ -1785,13 +1796,9 @@ static struct dentry *bch2_mount(struct file_system_type *fs_type,
 				 int flags, const char *dev_name, void *data)
 {
 	struct bch_fs *c;
-	struct bch_dev *ca;
 	struct super_block *sb;
 	struct inode *vinode;
 	struct bch_opts opts = bch2_opts_empty();
-	char **devs;
-	struct bch_fs **devs_to_fs = NULL;
-	unsigned i, nr_devs;
 	int ret;
 
 	opt_set(opts, read_only, (flags & SB_RDONLY) != 0);
@@ -1803,25 +1810,25 @@ static struct dentry *bch2_mount(struct file_system_type *fs_type,
 	if (!dev_name || strlen(dev_name) == 0)
 		return ERR_PTR(-EINVAL);
 
-	devs = split_devs(dev_name, &nr_devs);
-	if (!devs)
-		return ERR_PTR(-ENOMEM);
+	darray_str devs;
+	ret = bch2_split_devs(dev_name, &devs);
+	if (ret)
+		return ERR_PTR(ret);
 
-	devs_to_fs = kcalloc(nr_devs + 1, sizeof(void *), GFP_KERNEL);
-	if (!devs_to_fs) {
-		sb = ERR_PTR(-ENOMEM);
-		goto got_sb;
+	darray_fs devs_to_fs = {};
+	darray_for_each(devs, i) {
+		ret = darray_push(&devs_to_fs, bch2_path_to_fs(*i));
+		if (ret) {
+			sb = ERR_PTR(ret);
+			goto got_sb;
+		}
 	}
 
-	for (i = 0; i < nr_devs; i++)
-		devs_to_fs[i] = bch2_path_to_fs(devs[i]);
-
-	sb = sget(fs_type, bch2_test_super, bch2_noset_super,
-		  flags|SB_NOSEC, devs_to_fs);
+	sb = sget(fs_type, bch2_test_super, bch2_noset_super, flags|SB_NOSEC, &devs_to_fs);
 	if (!IS_ERR(sb))
 		goto got_sb;
 
-	c = bch2_fs_open(devs, nr_devs, opts);
+	c = bch2_fs_open(devs.data, devs.nr, opts);
 	if (IS_ERR(c)) {
 		sb = ERR_CAST(c);
 		goto got_sb;
@@ -1841,9 +1848,8 @@ static struct dentry *bch2_mount(struct file_system_type *fs_type,
 	if (IS_ERR(sb))
 		bch2_fs_stop(c);
 got_sb:
-	kfree(devs_to_fs);
-	kfree(devs[0]);
-	kfree(devs);
+	darray_exit(&devs_to_fs);
+	bch2_darray_str_exit(&devs);
 
 	if (IS_ERR(sb)) {
 		ret = PTR_ERR(sb);
@@ -1884,7 +1890,7 @@ got_sb:
 
 	sb->s_bdi->ra_pages		= VM_READAHEAD_PAGES;
 
-	for_each_online_member(ca, c, i) {
+	for_each_online_member(c, ca) {
 		struct block_device *bdev = ca->disk_sb.bdev;
 
 		/* XXX: create an anonymous device for multi device filesystems */
@@ -1905,10 +1911,9 @@ got_sb:
 
 	vinode = bch2_vfs_inode_get(c, BCACHEFS_ROOT_SUBVOL_INUM);
 	ret = PTR_ERR_OR_ZERO(vinode);
-	if (ret) {
-		bch_err_msg(c, ret, "mounting: error getting root inode");
+	bch_err_msg(c, ret, "mounting: error getting root inode");
+	if (ret)
 		goto err_put_super;
-	}
 
 	sb->s_root = d_make_root(vinode);
 	if (!sb->s_root) {
@@ -1922,10 +1927,7 @@ out:
 	return dget(sb->s_root);
 
 err_put_super:
-	sb->s_fs_info = NULL;
-	c->vfs_sb = NULL;
 	deactivate_locked_super(sb);
-	bch2_fs_stop(c);
 	return ERR_PTR(bch2_err_class(ret));
 }
 
@@ -1933,11 +1935,8 @@ static void bch2_kill_sb(struct super_block *sb)
 {
 	struct bch_fs *c = sb->s_fs_info;
 
-	if (c)
-		c->vfs_sb = NULL;
 	generic_shutdown_super(sb);
-	if (c)
-		bch2_fs_free(c);
+	bch2_fs_free(c);
 }
 
 static struct file_system_type bcache_fs_type = {
diff --git a/fs/bcachefs/fs.h b/fs/bcachefs/fs.h
index 5edf1d4b9e6b..c3af7225ff69 100644
--- a/fs/bcachefs/fs.h
+++ b/fs/bcachefs/fs.h
@@ -77,9 +77,8 @@ static inline int ptrcmp(void *l, void *r)
 }
 
 enum bch_inode_lock_op {
-	INODE_LOCK		= (1U << 0),
-	INODE_PAGECACHE_BLOCK	= (1U << 1),
-	INODE_UPDATE_LOCK	= (1U << 2),
+	INODE_PAGECACHE_BLOCK	= (1U << 0),
+	INODE_UPDATE_LOCK	= (1U << 1),
 };
 
 #define bch2_lock_inodes(_locks, ...)					\
@@ -91,8 +90,6 @@ do {									\
 									\
 	for (i = 1; i < ARRAY_SIZE(a); i++)				\
 		if (a[i] != a[i - 1]) {					\
-			if ((_locks) & INODE_LOCK)			\
-				down_write_nested(&a[i]->v.i_rwsem, i);	\
 			if ((_locks) & INODE_PAGECACHE_BLOCK)		\
 				bch2_pagecache_block_get(a[i]);\
 			if ((_locks) & INODE_UPDATE_LOCK)			\
@@ -109,8 +106,6 @@ do {									\
 									\
 	for (i = 1; i < ARRAY_SIZE(a); i++)				\
 		if (a[i] != a[i - 1]) {					\
-			if ((_locks) & INODE_LOCK)			\
-				up_write(&a[i]->v.i_rwsem);		\
 			if ((_locks) & INODE_PAGECACHE_BLOCK)		\
 				bch2_pagecache_block_put(a[i]);\
 			if ((_locks) & INODE_UPDATE_LOCK)			\
diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 9f3e9bd3d767..4f0ecd605675 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -20,8 +20,6 @@
 #include <linux/bsearch.h>
 #include <linux/dcache.h> /* struct qstr */
 
-#define QSTR(n) { { { .len = strlen(n) } }, .name = n }
-
 /*
  * XXX: this is handling transaction restarts without returning
  * -BCH_ERR_transaction_restart_nested, this is not how we do things anymore:
@@ -29,19 +27,16 @@
 static s64 bch2_count_inode_sectors(struct btree_trans *trans, u64 inum,
 				    u32 snapshot)
 {
-	struct btree_iter iter;
-	struct bkey_s_c k;
 	u64 sectors = 0;
-	int ret;
 
-	for_each_btree_key_upto(trans, iter, BTREE_ID_extents,
+	int ret = for_each_btree_key_upto(trans, iter, BTREE_ID_extents,
 				SPOS(inum, 0, snapshot),
 				POS(inum, U64_MAX),
-				0, k, ret)
+				0, k, ({
 		if (bkey_extent_is_allocation(k.k))
 			sectors += k.k->size;
-
-	bch2_trans_iter_exit(trans, &iter);
+		0;
+	}));
 
 	return ret ?: sectors;
 }
@@ -49,45 +44,23 @@ static s64 bch2_count_inode_sectors(struct btree_trans *trans, u64 inum,
 static s64 bch2_count_subdirs(struct btree_trans *trans, u64 inum,
 				    u32 snapshot)
 {
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	struct bkey_s_c_dirent d;
 	u64 subdirs = 0;
-	int ret;
-
-	for_each_btree_key_upto(trans, iter, BTREE_ID_dirents,
-				SPOS(inum, 0, snapshot),
-				POS(inum, U64_MAX),
-				0, k, ret) {
-		if (k.k->type != KEY_TYPE_dirent)
-			continue;
 
-		d = bkey_s_c_to_dirent(k);
-		if (d.v->d_type == DT_DIR)
+	int ret = for_each_btree_key_upto(trans, iter, BTREE_ID_dirents,
+				    SPOS(inum, 0, snapshot),
+				    POS(inum, U64_MAX),
+				    0, k, ({
+		if (k.k->type == KEY_TYPE_dirent &&
+		    bkey_s_c_to_dirent(k).v->d_type == DT_DIR)
 			subdirs++;
-	}
-	bch2_trans_iter_exit(trans, &iter);
+		0;
+	}));
 
 	return ret ?: subdirs;
 }
 
-static int __snapshot_lookup_subvol(struct btree_trans *trans, u32 snapshot,
-				    u32 *subvol)
-{
-	struct bch_snapshot s;
-	int ret = bch2_bkey_get_val_typed(trans, BTREE_ID_snapshots,
-					  POS(0, snapshot), 0,
-					  snapshot, &s);
-	if (!ret)
-		*subvol = le32_to_cpu(s.subvol);
-	else if (bch2_err_matches(ret, ENOENT))
-		bch_err(trans->c, "snapshot %u not found", snapshot);
-	return ret;
-
-}
-
-static int __subvol_lookup(struct btree_trans *trans, u32 subvol,
-			   u32 *snapshot, u64 *inum)
+static int subvol_lookup(struct btree_trans *trans, u32 subvol,
+			 u32 *snapshot, u64 *inum)
 {
 	struct bch_subvolume s;
 	int ret;
@@ -99,12 +72,6 @@ static int __subvol_lookup(struct btree_trans *trans, u32 subvol,
 	return ret;
 }
 
-static int subvol_lookup(struct btree_trans *trans, u32 subvol,
-			 u32 *snapshot, u64 *inum)
-{
-	return lockrestart_do(trans, __subvol_lookup(trans, subvol, snapshot, inum));
-}
-
 static int lookup_first_inode(struct btree_trans *trans, u64 inode_nr,
 			      struct bch_inode_unpacked *inode)
 {
@@ -132,7 +99,7 @@ err:
 	return ret;
 }
 
-static int __lookup_inode(struct btree_trans *trans, u64 inode_nr,
+static int lookup_inode(struct btree_trans *trans, u64 inode_nr,
 			  struct bch_inode_unpacked *inode,
 			  u32 *snapshot)
 {
@@ -157,13 +124,6 @@ err:
 	return ret;
 }
 
-static int lookup_inode(struct btree_trans *trans, u64 inode_nr,
-			struct bch_inode_unpacked *inode,
-			u32 *snapshot)
-{
-	return lockrestart_do(trans, __lookup_inode(trans, inode_nr, inode, snapshot));
-}
-
 static int __lookup_dirent(struct btree_trans *trans,
 			   struct bch_hash_info hash_info,
 			   subvol_inum dir, struct qstr *name,
@@ -207,12 +167,9 @@ static int fsck_write_inode(struct btree_trans *trans,
 			    struct bch_inode_unpacked *inode,
 			    u32 snapshot)
 {
-	int ret = commit_do(trans, NULL, NULL,
-				  BTREE_INSERT_NOFAIL|
-				  BTREE_INSERT_LAZY_RW,
-				  __write_inode(trans, inode, snapshot));
-	if (ret)
-		bch_err_fn(trans->c, ret);
+	int ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
+			    __write_inode(trans, inode, snapshot));
+	bch_err_fn(trans->c, ret);
 	return ret;
 }
 
@@ -242,35 +199,43 @@ err:
 }
 
 /* Get lost+found, create if it doesn't exist: */
-static int lookup_lostfound(struct btree_trans *trans, u32 subvol,
+static int lookup_lostfound(struct btree_trans *trans, u32 snapshot,
 			    struct bch_inode_unpacked *lostfound)
 {
 	struct bch_fs *c = trans->c;
-	struct bch_inode_unpacked root;
-	struct bch_hash_info root_hash_info;
 	struct qstr lostfound_str = QSTR("lost+found");
-	subvol_inum root_inum = { .subvol = subvol };
 	u64 inum = 0;
 	unsigned d_type = 0;
-	u32 snapshot;
 	int ret;
 
-	ret = __subvol_lookup(trans, subvol, &snapshot, &root_inum.inum);
+	struct bch_snapshot_tree st;
+	ret = bch2_snapshot_tree_lookup(trans,
+			bch2_snapshot_tree(c, snapshot), &st);
+	if (ret)
+		return ret;
+
+	subvol_inum root_inum = { .subvol = le32_to_cpu(st.master_subvol) };
+	u32 subvol_snapshot;
+
+	ret = subvol_lookup(trans, le32_to_cpu(st.master_subvol),
+			    &subvol_snapshot, &root_inum.inum);
+	bch_err_msg(c, ret, "looking up root subvol");
 	if (ret)
 		return ret;
 
-	ret = __lookup_inode(trans, root_inum.inum, &root, &snapshot);
+	struct bch_inode_unpacked root_inode;
+	struct bch_hash_info root_hash_info;
+	ret = lookup_inode(trans, root_inum.inum, &root_inode, &snapshot);
+	bch_err_msg(c, ret, "looking up root inode");
 	if (ret)
 		return ret;
 
-	root_hash_info = bch2_hash_info_init(c, &root);
+	root_hash_info = bch2_hash_info_init(c, &root_inode);
 
 	ret = __lookup_dirent(trans, root_hash_info, root_inum,
-			    &lostfound_str, &inum, &d_type);
-	if (bch2_err_matches(ret, ENOENT)) {
-		bch_notice(c, "creating lost+found");
+			      &lostfound_str, &inum, &d_type);
+	if (bch2_err_matches(ret, ENOENT))
 		goto create_lostfound;
-	}
 
 	bch_err_fn(c, ret);
 	if (ret)
@@ -285,20 +250,50 @@ static int lookup_lostfound(struct btree_trans *trans, u32 subvol,
 	 * The bch2_check_dirents pass has already run, dangling dirents
 	 * shouldn't exist here:
 	 */
-	return __lookup_inode(trans, inum, lostfound, &snapshot);
+	return lookup_inode(trans, inum, lostfound, &snapshot);
 
 create_lostfound:
+	/*
+	 * XXX: we could have a nicer log message here  if we had a nice way to
+	 * walk backpointers to print a path
+	 */
+	bch_notice(c, "creating lost+found in snapshot %u", le32_to_cpu(st.root_snapshot));
+
+	u64 now = bch2_current_time(c);
+	struct btree_iter lostfound_iter = { NULL };
+	u64 cpu = raw_smp_processor_id();
+
 	bch2_inode_init_early(c, lostfound);
+	bch2_inode_init_late(lostfound, now, 0, 0, S_IFDIR|0700, 0, &root_inode);
+	lostfound->bi_dir = root_inode.bi_inum;
+
+	root_inode.bi_nlink++;
+
+	ret = bch2_inode_create(trans, &lostfound_iter, lostfound, snapshot, cpu);
+	if (ret)
+		goto err;
+
+	bch2_btree_iter_set_snapshot(&lostfound_iter, snapshot);
+	ret = bch2_btree_iter_traverse(&lostfound_iter);
+	if (ret)
+		goto err;
 
-	ret = bch2_create_trans(trans, root_inum, &root,
-				lostfound, &lostfound_str,
-				0, 0, S_IFDIR|0700, 0, NULL, NULL,
-				(subvol_inum) { }, 0);
+	ret =   bch2_dirent_create_snapshot(trans,
+				root_inode.bi_inum, snapshot, &root_hash_info,
+				mode_to_type(lostfound->bi_mode),
+				&lostfound_str,
+				lostfound->bi_inum,
+				&lostfound->bi_dir_offset,
+				BCH_HASH_SET_MUST_CREATE) ?:
+		bch2_inode_write_flags(trans, &lostfound_iter, lostfound,
+				       BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE);
+err:
 	bch_err_msg(c, ret, "creating lost+found");
+	bch2_trans_iter_exit(trans, &lostfound_iter);
 	return ret;
 }
 
-static int __reattach_inode(struct btree_trans *trans,
+static int reattach_inode(struct btree_trans *trans,
 			  struct bch_inode_unpacked *inode,
 			  u32 inode_snapshot)
 {
@@ -307,14 +302,9 @@ static int __reattach_inode(struct btree_trans *trans,
 	char name_buf[20];
 	struct qstr name;
 	u64 dir_offset = 0;
-	u32 subvol;
 	int ret;
 
-	ret = __snapshot_lookup_subvol(trans, inode_snapshot, &subvol);
-	if (ret)
-		return ret;
-
-	ret = lookup_lostfound(trans, subvol, &lostfound);
+	ret = lookup_lostfound(trans, inode_snapshot, &lostfound);
 	if (ret)
 		return ret;
 
@@ -331,15 +321,12 @@ static int __reattach_inode(struct btree_trans *trans,
 	snprintf(name_buf, sizeof(name_buf), "%llu", inode->bi_inum);
 	name = (struct qstr) QSTR(name_buf);
 
-	ret = bch2_dirent_create(trans,
-				 (subvol_inum) {
-					.subvol = subvol,
-					.inum = lostfound.bi_inum,
-				 },
-				 &dir_hash,
-				 inode_d_type(inode),
-				 &name, inode->bi_inum, &dir_offset,
-				 BCH_HASH_SET_MUST_CREATE);
+	ret = bch2_dirent_create_snapshot(trans,
+				lostfound.bi_inum, inode_snapshot,
+				&dir_hash,
+				inode_d_type(inode),
+				&name, inode->bi_inum, &dir_offset,
+				BCH_HASH_SET_MUST_CREATE);
 	if (ret)
 		return ret;
 
@@ -349,18 +336,6 @@ static int __reattach_inode(struct btree_trans *trans,
 	return __write_inode(trans, inode, inode_snapshot);
 }
 
-static int reattach_inode(struct btree_trans *trans,
-			  struct bch_inode_unpacked *inode,
-			  u32 inode_snapshot)
-{
-	int ret = commit_do(trans, NULL, NULL,
-				  BTREE_INSERT_LAZY_RW|
-				  BTREE_INSERT_NOFAIL,
-			__reattach_inode(trans, inode, inode_snapshot));
-	bch_err_msg(trans->c, ret, "reattaching inode %llu", inode->bi_inum);
-	return ret;
-}
-
 static int remove_backpointer(struct btree_trans *trans,
 			      struct bch_inode_unpacked *inode)
 {
@@ -405,7 +380,7 @@ static int snapshots_seen_add_inorder(struct bch_fs *c, struct snapshots_seen *s
 	};
 	int ret = 0;
 
-	darray_for_each(s->ids, i) {
+	__darray_for_each(s->ids, i) {
 		if (i->id == id)
 			return 0;
 		if (i->id > id)
@@ -422,7 +397,7 @@ static int snapshots_seen_add_inorder(struct bch_fs *c, struct snapshots_seen *s
 static int snapshots_seen_update(struct bch_fs *c, struct snapshots_seen *s,
 				 enum btree_id btree_id, struct bpos pos)
 {
-	struct snapshots_seen_entry *i, n = {
+	struct snapshots_seen_entry n = {
 		.id	= pos.snapshot,
 		.equiv	= bch2_snapshot_equiv(c, pos.snapshot),
 	};
@@ -448,7 +423,7 @@ static int snapshots_seen_update(struct bch_fs *c, struct snapshots_seen *s,
 				bch2_btree_id_str(btree_id),
 				pos.inode, pos.offset,
 				i->id, n.id, n.equiv);
-			set_bit(BCH_FS_NEED_DELETE_DEAD_SNAPSHOTS, &c->flags);
+			set_bit(BCH_FS_need_delete_dead_snapshots, &c->flags);
 			return bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_delete_dead_snapshots);
 		}
 	}
@@ -593,14 +568,13 @@ static int get_inodes_all_snapshots(struct btree_trans *trans,
 	struct bch_fs *c = trans->c;
 	struct btree_iter iter;
 	struct bkey_s_c k;
-	u32 restart_count = trans->restart_count;
 	int ret;
 
 	w->recalculate_sums = false;
 	w->inodes.nr = 0;
 
-	for_each_btree_key(trans, iter, BTREE_ID_inodes, POS(0, inum),
-			   BTREE_ITER_ALL_SNAPSHOTS, k, ret) {
+	for_each_btree_key_norestart(trans, iter, BTREE_ID_inodes, POS(0, inum),
+				     BTREE_ITER_ALL_SNAPSHOTS, k, ret) {
 		if (k.k->p.offset != inum)
 			break;
 
@@ -613,8 +587,7 @@ static int get_inodes_all_snapshots(struct btree_trans *trans,
 		return ret;
 
 	w->first_this_inode = true;
-
-	return trans_was_restarted(trans, restart_count);
+	return 0;
 }
 
 static struct inode_walker_entry *
@@ -625,7 +598,7 @@ lookup_inode_for_snapshot(struct bch_fs *c, struct inode_walker *w,
 
 	snapshot = bch2_snapshot_equiv(c, snapshot);
 
-	darray_for_each(w->inodes, i)
+	__darray_for_each(w->inodes, i)
 		if (bch2_snapshot_is_ancestor(c, snapshot, i->snapshot))
 			goto found;
 
@@ -667,11 +640,8 @@ static struct inode_walker_entry *walk_inode(struct btree_trans *trans,
 		if (ret)
 			return ERR_PTR(ret);
 	} else if (bkey_cmp(w->last_pos, pos)) {
-		struct inode_walker_entry *i;
-
 		darray_for_each(w->inodes, i)
 			i->seen_this_pos = false;
-
 	}
 
 	w->last_pos = pos;
@@ -756,9 +726,7 @@ static int hash_redo_key(struct btree_trans *trans,
 				       k.k->p.snapshot, tmp,
 				       BCH_HASH_SET_MUST_CREATE,
 				       BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE) ?:
-		bch2_trans_commit(trans, NULL, NULL,
-				  BTREE_INSERT_NOFAIL|
-				  BTREE_INSERT_LAZY_RW);
+		bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc);
 }
 
 static int hash_check_key(struct btree_trans *trans,
@@ -826,6 +794,18 @@ fsck_err:
 	goto out;
 }
 
+static int check_inode_deleted_list(struct btree_trans *trans, struct bpos p)
+{
+	struct btree_iter iter;
+	struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_deleted_inodes, p, 0);
+	int ret = bkey_err(k);
+	if (ret)
+		return ret;
+
+	bch2_trans_iter_exit(trans, &iter);
+	return k.k->type == KEY_TYPE_set;
+}
+
 static int check_inode(struct btree_trans *trans,
 		       struct btree_iter *iter,
 		       struct bkey_s_c k,
@@ -867,7 +847,7 @@ static int check_inode(struct btree_trans *trans,
 			c, inode_snapshot_mismatch,
 			"inodes in different snapshots don't match")) {
 		bch_err(c, "repair not implemented yet");
-		return -EINVAL;
+		return -BCH_ERR_fsck_repair_unimplemented;
 	}
 
 	if ((u.bi_flags & (BCH_INODE_i_size_dirty|BCH_INODE_unlinked)) &&
@@ -890,14 +870,22 @@ static int check_inode(struct btree_trans *trans,
 		return 0;
 	}
 
+	if (u.bi_flags & BCH_INODE_unlinked) {
+		ret = check_inode_deleted_list(trans, k.k->p);
+		if (ret < 0)
+			return ret;
+
+		fsck_err_on(ret, c, unlinked_inode_not_on_deleted_list,
+			    "inode %llu:%u unlinked, but not on deleted list",
+			    u.bi_inum, k.k->p.snapshot);
+		ret = 0;
+	}
+
 	if (u.bi_flags & BCH_INODE_unlinked &&
 	    (!c->sb.clean ||
 	     fsck_err(c, inode_unlinked_but_clean,
 		      "filesystem marked clean, but inode %llu unlinked",
 		      u.bi_inum))) {
-		bch2_trans_unlock(trans);
-		bch2_fs_lazy_rw(c);
-
 		ret = bch2_inode_rm_snapshot(trans, u.bi_inum, iter->pos.snapshot);
 		bch_err_msg(c, ret, "in fsck deleting inode");
 		return ret;
@@ -910,9 +898,6 @@ static int check_inode(struct btree_trans *trans,
 		      u.bi_inum))) {
 		bch_verbose(c, "truncating inode %llu", u.bi_inum);
 
-		bch2_trans_unlock(trans);
-		bch2_fs_lazy_rw(c);
-
 		/*
 		 * XXX: need to truncate partial blocks too here - or ideally
 		 * just switch units to bytes and that issue goes away
@@ -976,27 +961,22 @@ fsck_err:
 	return ret;
 }
 
-noinline_for_stack
 int bch2_check_inodes(struct bch_fs *c)
 {
 	bool full = c->opts.fsck;
-	struct btree_trans *trans = bch2_trans_get(c);
-	struct btree_iter iter;
 	struct bch_inode_unpacked prev = { 0 };
 	struct snapshots_seen s;
-	struct bkey_s_c k;
-	int ret;
 
 	snapshots_seen_init(&s);
 
-	ret = for_each_btree_key_commit(trans, iter, BTREE_ID_inodes,
-			POS_MIN,
-			BTREE_ITER_PREFETCH|BTREE_ITER_ALL_SNAPSHOTS, k,
-			NULL, NULL, BTREE_INSERT_LAZY_RW|BTREE_INSERT_NOFAIL,
-		check_inode(trans, &iter, k, &prev, &s, full));
+	int ret = bch2_trans_run(c,
+		for_each_btree_key_commit(trans, iter, BTREE_ID_inodes,
+				POS_MIN,
+				BTREE_ITER_PREFETCH|BTREE_ITER_ALL_SNAPSHOTS, k,
+				NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
+			check_inode(trans, &iter, k, &prev, &s, full)));
 
 	snapshots_seen_exit(&s);
-	bch2_trans_put(trans);
 	bch_err_fn(c, ret);
 	return ret;
 }
@@ -1023,29 +1003,9 @@ static bool dirent_points_to_inode(struct bkey_s_c_dirent d,
 		: le64_to_cpu(d.v->d_inum)		== inode->bi_inum;
 }
 
-static int inode_backpointer_exists(struct btree_trans *trans,
-				    struct bch_inode_unpacked *inode,
-				    u32 snapshot)
-{
-	struct btree_iter iter;
-	struct bkey_s_c_dirent d;
-	int ret;
-
-	d = dirent_get_by_pos(trans, &iter,
-			SPOS(inode->bi_dir, inode->bi_dir_offset, snapshot));
-	ret = bkey_err(d);
-	if (ret)
-		return bch2_err_matches(ret, ENOENT) ? 0 : ret;
-
-	ret = dirent_points_to_inode(d, inode);
-	bch2_trans_iter_exit(trans, &iter);
-	return ret;
-}
-
 static int check_i_sectors(struct btree_trans *trans, struct inode_walker *w)
 {
 	struct bch_fs *c = trans->c;
-	struct inode_walker_entry *i;
 	u32 restart_count = trans->restart_count;
 	int ret = 0;
 	s64 count2;
@@ -1094,11 +1054,8 @@ struct extent_ends {
 
 static void extent_ends_reset(struct extent_ends *extent_ends)
 {
-	struct extent_end *i;
-
 	darray_for_each(extent_ends->e, i)
 		snapshots_seen_exit(&i->seen);
-
 	extent_ends->e.nr = 0;
 }
 
@@ -1130,7 +1087,7 @@ static int extent_ends_at(struct bch_fs *c,
 	if (!n.seen.ids.data)
 		return -BCH_ERR_ENOMEM_fsck_extent_ends_at;
 
-	darray_for_each(extent_ends->e, i) {
+	__darray_for_each(extent_ends->e, i) {
 		if (i->snapshot == k.k->p.snapshot) {
 			snapshots_seen_exit(&i->seen);
 			*i = n;
@@ -1220,13 +1177,12 @@ static int overlapping_extents_found(struct btree_trans *trans,
 			swap(k1, k2);
 		}
 
-		trans->extra_journal_res += bch2_bkey_sectors_compressed(k2);
+		trans->extra_disk_res += bch2_bkey_sectors_compressed(k2);
 
 		ret =   bch2_trans_update_extent_overwrite(trans, old_iter,
 				BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE,
 				k1, k2) ?:
-			bch2_trans_commit(trans, &res, NULL,
-				BTREE_INSERT_LAZY_RW|BTREE_INSERT_NOFAIL);
+			bch2_trans_commit(trans, &res, NULL, BCH_TRANS_COMMIT_no_enospc);
 		bch2_disk_reservation_put(c, &res);
 
 		if (ret)
@@ -1270,7 +1226,6 @@ static int check_overlapping_extents(struct btree_trans *trans,
 			      bool *fixed)
 {
 	struct bch_fs *c = trans->c;
-	struct extent_end *i;
 	int ret = 0;
 
 	/* transaction restart, running again */
@@ -1451,32 +1406,28 @@ int bch2_check_extents(struct bch_fs *c)
 {
 	struct inode_walker w = inode_walker_init();
 	struct snapshots_seen s;
-	struct btree_trans *trans = bch2_trans_get(c);
-	struct btree_iter iter;
-	struct bkey_s_c k;
 	struct extent_ends extent_ends;
 	struct disk_reservation res = { 0 };
-	int ret = 0;
 
 	snapshots_seen_init(&s);
 	extent_ends_init(&extent_ends);
 
-	ret = for_each_btree_key_commit(trans, iter, BTREE_ID_extents,
-			POS(BCACHEFS_ROOT_INO, 0),
-			BTREE_ITER_PREFETCH|BTREE_ITER_ALL_SNAPSHOTS, k,
-			&res, NULL,
-			BTREE_INSERT_LAZY_RW|BTREE_INSERT_NOFAIL, ({
-		bch2_disk_reservation_put(c, &res);
-		check_extent(trans, &iter, k, &w, &s, &extent_ends) ?:
-		check_extent_overbig(trans, &iter, k);
-	})) ?:
-	check_i_sectors(trans, &w);
+	int ret = bch2_trans_run(c,
+		for_each_btree_key_commit(trans, iter, BTREE_ID_extents,
+				POS(BCACHEFS_ROOT_INO, 0),
+				BTREE_ITER_PREFETCH|BTREE_ITER_ALL_SNAPSHOTS, k,
+				&res, NULL,
+				BCH_TRANS_COMMIT_no_enospc, ({
+			bch2_disk_reservation_put(c, &res);
+			check_extent(trans, &iter, k, &w, &s, &extent_ends) ?:
+			check_extent_overbig(trans, &iter, k);
+		})) ?:
+		check_i_sectors(trans, &w));
 
 	bch2_disk_reservation_put(c, &res);
 	extent_ends_exit(&extent_ends);
 	inode_walker_exit(&w);
 	snapshots_seen_exit(&s);
-	bch2_trans_put(trans);
 
 	bch_err_fn(c, ret);
 	return ret;
@@ -1484,24 +1435,19 @@ int bch2_check_extents(struct bch_fs *c)
 
 int bch2_check_indirect_extents(struct bch_fs *c)
 {
-	struct btree_trans *trans = bch2_trans_get(c);
-	struct btree_iter iter;
-	struct bkey_s_c k;
 	struct disk_reservation res = { 0 };
-	int ret = 0;
 
-	ret = for_each_btree_key_commit(trans, iter, BTREE_ID_reflink,
-			POS_MIN,
-			BTREE_ITER_PREFETCH, k,
-			&res, NULL,
-			BTREE_INSERT_LAZY_RW|BTREE_INSERT_NOFAIL, ({
-		bch2_disk_reservation_put(c, &res);
-		check_extent_overbig(trans, &iter, k);
-	}));
+	int ret = bch2_trans_run(c,
+		for_each_btree_key_commit(trans, iter, BTREE_ID_reflink,
+				POS_MIN,
+				BTREE_ITER_PREFETCH, k,
+				&res, NULL,
+				BCH_TRANS_COMMIT_no_enospc, ({
+			bch2_disk_reservation_put(c, &res);
+			check_extent_overbig(trans, &iter, k);
+		})));
 
 	bch2_disk_reservation_put(c, &res);
-	bch2_trans_put(trans);
-
 	bch_err_fn(c, ret);
 	return ret;
 }
@@ -1509,7 +1455,6 @@ int bch2_check_indirect_extents(struct bch_fs *c)
 static int check_subdir_count(struct btree_trans *trans, struct inode_walker *w)
 {
 	struct bch_fs *c = trans->c;
-	struct inode_walker_entry *i;
 	u32 restart_count = trans->restart_count;
 	int ret = 0;
 	s64 count2;
@@ -1553,8 +1498,8 @@ static int check_dirent_target(struct btree_trans *trans,
 {
 	struct bch_fs *c = trans->c;
 	struct bkey_i_dirent *n;
-	bool backpointer_exists = true;
 	struct printbuf buf = PRINTBUF;
+	struct btree_iter bp_iter = { NULL };
 	int ret = 0;
 
 	if (!target->bi_dir &&
@@ -1568,25 +1513,37 @@ static int check_dirent_target(struct btree_trans *trans,
 	}
 
 	if (!inode_points_to_dirent(target, d)) {
-		ret = inode_backpointer_exists(trans, target, d.k->p.snapshot);
-		if (ret < 0)
+		struct bkey_s_c_dirent bp_dirent = dirent_get_by_pos(trans, &bp_iter,
+				      SPOS(target->bi_dir, target->bi_dir_offset, target_snapshot));
+		ret = bkey_err(bp_dirent);
+		if (ret && !bch2_err_matches(ret, ENOENT))
 			goto err;
 
-		backpointer_exists = ret;
+		bool backpointer_exists = !ret;
 		ret = 0;
 
+		bch2_bkey_val_to_text(&buf, c, d.s_c);
+		prt_newline(&buf);
+		if (backpointer_exists)
+			bch2_bkey_val_to_text(&buf, c, bp_dirent.s_c);
+
 		if (fsck_err_on(S_ISDIR(target->bi_mode) && backpointer_exists,
 				c, inode_dir_multiple_links,
-				"directory %llu with multiple links",
-				target->bi_inum)) {
+				"directory %llu:%u with multiple links\n%s",
+				target->bi_inum, target_snapshot, buf.buf)) {
 			ret = __remove_dirent(trans, d.k->p);
 			goto out;
 		}
 
+		/*
+		 * hardlinked file with nlink 0:
+		 * We're just adjusting nlink here so check_nlinks() will pick
+		 * it up, it ignores inodes with nlink 0
+		 */
 		if (fsck_err_on(backpointer_exists && !target->bi_nlink,
 				c, inode_multiple_links_but_nlink_0,
-				"inode %llu type %s has multiple links but i_nlink 0",
-				target->bi_inum, bch2_d_types[d.v->d_type])) {
+				"inode %llu:%u type %s has multiple links but i_nlink 0\n%s",
+				target->bi_inum, target_snapshot, bch2_d_types[d.v->d_type], buf.buf)) {
 			target->bi_nlink++;
 			target->bi_flags &= ~BCH_INODE_unlinked;
 
@@ -1636,13 +1593,12 @@ static int check_dirent_target(struct btree_trans *trans,
 		d = dirent_i_to_s_c(n);
 	}
 
-	if (d.v->d_type == DT_SUBVOL &&
-	    target->bi_parent_subvol != le32_to_cpu(d.v->d_parent_subvol) &&
-	    (c->sb.version < bcachefs_metadata_version_subvol_dirent ||
-	     fsck_err(c, dirent_d_parent_subvol_wrong,
-		      "dirent has wrong d_parent_subvol field: got %u, should be %u",
-		      le32_to_cpu(d.v->d_parent_subvol),
-		      target->bi_parent_subvol))) {
+	if (fsck_err_on(d.v->d_type == DT_SUBVOL &&
+			target->bi_parent_subvol != le32_to_cpu(d.v->d_parent_subvol),
+			c, dirent_d_parent_subvol_wrong,
+			"dirent has wrong d_parent_subvol field: got %u, should be %u",
+			le32_to_cpu(d.v->d_parent_subvol),
+			target->bi_parent_subvol)) {
 		n = bch2_trans_kmalloc(trans, bkey_bytes(d.k));
 		ret = PTR_ERR_OR_ZERO(n);
 		if (ret)
@@ -1660,6 +1616,7 @@ static int check_dirent_target(struct btree_trans *trans,
 out:
 err:
 fsck_err:
+	bch2_trans_iter_exit(trans, &bp_iter);
 	printbuf_exit(&buf);
 	bch_err_fn(c, ret);
 	return ret;
@@ -1701,7 +1658,7 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter,
 			goto err;
 	}
 
-	BUG_ON(!iter->path->should_be_locked);
+	BUG_ON(!btree_iter_path(trans, iter)->should_be_locked);
 
 	i = walk_inode(trans, dir, equiv, k.k->type == KEY_TYPE_whiteout);
 	ret = PTR_ERR_OR_ZERO(i);
@@ -1754,7 +1711,7 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter,
 		u32 target_snapshot;
 		u64 target_inum;
 
-		ret = __subvol_lookup(trans, target_subvol,
+		ret = subvol_lookup(trans, target_subvol,
 				      &target_snapshot, &target_inum);
 		if (ret && !bch2_err_matches(ret, ENOENT))
 			goto err;
@@ -1766,7 +1723,7 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter,
 			goto err;
 		}
 
-		ret = __lookup_inode(trans, target_inum,
+		ret = lookup_inode(trans, target_inum,
 				   &subvol_root, &target_snapshot);
 		if (ret && !bch2_err_matches(ret, ENOENT))
 			goto err;
@@ -1842,22 +1799,18 @@ int bch2_check_dirents(struct bch_fs *c)
 	struct inode_walker target = inode_walker_init();
 	struct snapshots_seen s;
 	struct bch_hash_info hash_info;
-	struct btree_trans *trans = bch2_trans_get(c);
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	int ret = 0;
 
 	snapshots_seen_init(&s);
 
-	ret = for_each_btree_key_commit(trans, iter, BTREE_ID_dirents,
-			POS(BCACHEFS_ROOT_INO, 0),
-			BTREE_ITER_PREFETCH|BTREE_ITER_ALL_SNAPSHOTS,
-			k,
-			NULL, NULL,
-			BTREE_INSERT_LAZY_RW|BTREE_INSERT_NOFAIL,
-		check_dirent(trans, &iter, k, &hash_info, &dir, &target, &s));
+	int ret = bch2_trans_run(c,
+		for_each_btree_key_commit(trans, iter, BTREE_ID_dirents,
+				POS(BCACHEFS_ROOT_INO, 0),
+				BTREE_ITER_PREFETCH|BTREE_ITER_ALL_SNAPSHOTS,
+				k,
+				NULL, NULL,
+				BCH_TRANS_COMMIT_no_enospc,
+			check_dirent(trans, &iter, k, &hash_info, &dir, &target, &s)));
 
-	bch2_trans_put(trans);
 	snapshots_seen_exit(&s);
 	inode_walker_exit(&dir);
 	inode_walker_exit(&target);
@@ -1908,8 +1861,6 @@ int bch2_check_xattrs(struct bch_fs *c)
 {
 	struct inode_walker inode = inode_walker_init();
 	struct bch_hash_info hash_info;
-	struct btree_iter iter;
-	struct bkey_s_c k;
 	int ret = 0;
 
 	ret = bch2_trans_run(c,
@@ -1918,7 +1869,7 @@ int bch2_check_xattrs(struct bch_fs *c)
 			BTREE_ITER_PREFETCH|BTREE_ITER_ALL_SNAPSHOTS,
 			k,
 			NULL, NULL,
-			BTREE_INSERT_LAZY_RW|BTREE_INSERT_NOFAIL,
+			BCH_TRANS_COMMIT_no_enospc,
 		check_xattr(trans, &iter, k, &hash_info, &inode)));
 	bch_err_fn(c, ret);
 	return ret;
@@ -1932,7 +1883,7 @@ static int check_root_trans(struct btree_trans *trans)
 	u64 inum;
 	int ret;
 
-	ret = __subvol_lookup(trans, BCACHEFS_ROOT_SUBVOL, &snapshot, &inum);
+	ret = subvol_lookup(trans, BCACHEFS_ROOT_SUBVOL, &snapshot, &inum);
 	if (ret && !bch2_err_matches(ret, ENOENT))
 		return ret;
 
@@ -1948,18 +1899,13 @@ static int check_root_trans(struct btree_trans *trans)
 		root_subvol.v.flags	= 0;
 		root_subvol.v.snapshot	= cpu_to_le32(snapshot);
 		root_subvol.v.inode	= cpu_to_le64(inum);
-		ret = commit_do(trans, NULL, NULL,
-				      BTREE_INSERT_NOFAIL|
-				      BTREE_INSERT_LAZY_RW,
-			bch2_btree_insert_trans(trans, BTREE_ID_subvolumes,
-					    &root_subvol.k_i, 0));
+		ret = bch2_btree_insert_trans(trans, BTREE_ID_subvolumes, &root_subvol.k_i, 0);
 		bch_err_msg(c, ret, "writing root subvol");
 		if (ret)
 			goto err;
-
 	}
 
-	ret = __lookup_inode(trans, BCACHEFS_ROOT_INO, &root_inode, &snapshot);
+	ret = lookup_inode(trans, BCACHEFS_ROOT_INO, &root_inode, &snapshot);
 	if (ret && !bch2_err_matches(ret, ENOENT))
 		return ret;
 
@@ -1983,11 +1929,7 @@ fsck_err:
 /* Get root directory, create if it doesn't exist: */
 int bch2_check_root(struct bch_fs *c)
 {
-	int ret;
-
-	ret = bch2_trans_do(c, NULL, NULL,
-			     BTREE_INSERT_NOFAIL|
-			     BTREE_INSERT_LAZY_RW,
+	int ret = bch2_trans_do(c, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 		check_root_trans(trans));
 	bch_err_fn(c, ret);
 	return ret;
@@ -2002,13 +1944,10 @@ typedef DARRAY(struct pathbuf_entry) pathbuf;
 
 static bool path_is_dup(pathbuf *p, u64 inum, u32 snapshot)
 {
-	struct pathbuf_entry *i;
-
 	darray_for_each(*p, i)
 		if (i->inum	== inum &&
 		    i->snapshot	== snapshot)
 			return true;
-
 	return false;
 }
 
@@ -2057,10 +1996,10 @@ static int check_path(struct btree_trans *trans,
 				break;
 		}
 
-		ret = lockrestart_do(trans,
-			PTR_ERR_OR_ZERO((d = dirent_get_by_pos(trans, &dirent_iter,
-					  SPOS(inode->bi_dir, inode->bi_dir_offset,
-					       parent_snapshot))).k));
+		d = dirent_get_by_pos(trans, &dirent_iter,
+				      SPOS(inode->bi_dir, inode->bi_dir_offset,
+					   parent_snapshot));
+		ret = bkey_err(d.s_c);
 		if (ret && !bch2_err_matches(ret, ENOENT))
 			break;
 
@@ -2097,13 +2036,12 @@ static int check_path(struct btree_trans *trans,
 		ret = lookup_inode(trans, inode->bi_dir, inode, &snapshot);
 		if (ret) {
 			/* Should have been caught in dirents pass */
-			bch_err(c, "error looking up parent directory: %i", ret);
+			if (!bch2_err_matches(ret, BCH_ERR_transaction_restart))
+				bch_err(c, "error looking up parent directory: %i", ret);
 			break;
 		}
 
 		if (path_is_dup(p, inode->bi_inum, snapshot)) {
-			struct pathbuf_entry *i;
-
 			/* XXX print path */
 			bch_err(c, "directory structure loop");
 
@@ -2111,20 +2049,19 @@ static int check_path(struct btree_trans *trans,
 				pr_err("%llu:%u", i->inum, i->snapshot);
 			pr_err("%llu:%u", inode->bi_inum, snapshot);
 
-			if (!fsck_err(c, dir_loop,
-				      "directory structure loop"))
+			if (!fsck_err(c, dir_loop, "directory structure loop"))
 				return 0;
 
-			ret = commit_do(trans, NULL, NULL,
-					      BTREE_INSERT_NOFAIL|
-					      BTREE_INSERT_LAZY_RW,
-					remove_backpointer(trans, inode));
-			if (ret) {
-				bch_err(c, "error removing dirent: %i", ret);
+			ret = remove_backpointer(trans, inode);
+			if (ret && !bch2_err_matches(ret, BCH_ERR_transaction_restart))
+				bch_err_msg(c, ret, "removing dirent");
+			if (ret)
 				break;
-			}
 
 			ret = reattach_inode(trans, inode, snapshot);
+			if (ret && !bch2_err_matches(ret, BCH_ERR_transaction_restart))
+				bch_err_msg(c, ret, "reattaching inode %llu", inode->bi_inum);
+			break;
 		}
 	}
 fsck_err:
@@ -2139,37 +2076,28 @@ fsck_err:
  */
 int bch2_check_directory_structure(struct bch_fs *c)
 {
-	struct btree_trans *trans = bch2_trans_get(c);
-	struct btree_iter iter;
-	struct bkey_s_c k;
 	struct bch_inode_unpacked u;
 	pathbuf path = { 0, };
 	int ret;
 
-	for_each_btree_key(trans, iter, BTREE_ID_inodes, POS_MIN,
-			   BTREE_ITER_INTENT|
-			   BTREE_ITER_PREFETCH|
-			   BTREE_ITER_ALL_SNAPSHOTS, k, ret) {
-		if (!bkey_is_inode(k.k))
-			continue;
+	ret = bch2_trans_run(c,
+		for_each_btree_key_commit(trans, iter, BTREE_ID_inodes, POS_MIN,
+					  BTREE_ITER_INTENT|
+					  BTREE_ITER_PREFETCH|
+					  BTREE_ITER_ALL_SNAPSHOTS, k,
+					  NULL, NULL, BCH_TRANS_COMMIT_no_enospc, ({
+			if (!bkey_is_inode(k.k))
+				continue;
 
-		ret = bch2_inode_unpack(k, &u);
-		if (ret) {
-			/* Should have been caught earlier in fsck: */
-			bch_err(c, "error unpacking inode %llu: %i", k.k->p.offset, ret);
-			break;
-		}
+			BUG_ON(bch2_inode_unpack(k, &u));
 
-		if (u.bi_flags & BCH_INODE_unlinked)
-			continue;
+			if (u.bi_flags & BCH_INODE_unlinked)
+				continue;
 
-		ret = check_path(trans, &path, &u, iter.pos.snapshot);
-		if (ret)
-			break;
-	}
-	bch2_trans_iter_exit(trans, &iter);
-	bch2_trans_put(trans);
+			check_path(trans, &path, &u, iter.pos.snapshot);
+		})));
 	darray_exit(&path);
+
 	bch_err_fn(c, ret);
 	return ret;
 }
@@ -2220,7 +2148,7 @@ static int nlink_cmp(const void *_l, const void *_r)
 	const struct nlink *l = _l;
 	const struct nlink *r = _r;
 
-	return cmp_int(l->inum, r->inum) ?: cmp_int(l->snapshot, r->snapshot);
+	return cmp_int(l->inum, r->inum);
 }
 
 static void inc_link(struct bch_fs *c, struct snapshots_seen *s,
@@ -2255,47 +2183,39 @@ static int check_nlinks_find_hardlinks(struct bch_fs *c,
 				       struct nlink_table *t,
 				       u64 start, u64 *end)
 {
-	struct btree_trans *trans = bch2_trans_get(c);
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	struct bch_inode_unpacked u;
-	int ret = 0;
-
-	for_each_btree_key(trans, iter, BTREE_ID_inodes,
-			   POS(0, start),
-			   BTREE_ITER_INTENT|
-			   BTREE_ITER_PREFETCH|
-			   BTREE_ITER_ALL_SNAPSHOTS, k, ret) {
-		if (!bkey_is_inode(k.k))
-			continue;
-
-		/* Should never fail, checked by bch2_inode_invalid: */
-		BUG_ON(bch2_inode_unpack(k, &u));
-
-		/*
-		 * Backpointer and directory structure checks are sufficient for
-		 * directories, since they can't have hardlinks:
-		 */
-		if (S_ISDIR(u.bi_mode))
-			continue;
+	int ret = bch2_trans_run(c,
+		for_each_btree_key(trans, iter, BTREE_ID_inodes,
+				   POS(0, start),
+				   BTREE_ITER_INTENT|
+				   BTREE_ITER_PREFETCH|
+				   BTREE_ITER_ALL_SNAPSHOTS, k, ({
+			if (!bkey_is_inode(k.k))
+				continue;
 
-		if (!u.bi_nlink)
-			continue;
+			/* Should never fail, checked by bch2_inode_invalid: */
+			struct bch_inode_unpacked u;
+			BUG_ON(bch2_inode_unpack(k, &u));
 
-		ret = add_nlink(c, t, k.k->p.offset, k.k->p.snapshot);
-		if (ret) {
-			*end = k.k->p.offset;
-			ret = 0;
-			break;
-		}
+			/*
+			 * Backpointer and directory structure checks are sufficient for
+			 * directories, since they can't have hardlinks:
+			 */
+			if (S_ISDIR(u.bi_mode))
+				continue;
 
-	}
-	bch2_trans_iter_exit(trans, &iter);
-	bch2_trans_put(trans);
+			if (!u.bi_nlink)
+				continue;
 
-	if (ret)
-		bch_err(c, "error in fsck: btree error %i while walking inodes", ret);
+			ret = add_nlink(c, t, k.k->p.offset, k.k->p.snapshot);
+			if (ret) {
+				*end = k.k->p.offset;
+				ret = 0;
+				break;
+			}
+			0;
+		})));
 
+	bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -2303,42 +2223,34 @@ noinline_for_stack
 static int check_nlinks_walk_dirents(struct bch_fs *c, struct nlink_table *links,
 				     u64 range_start, u64 range_end)
 {
-	struct btree_trans *trans = bch2_trans_get(c);
 	struct snapshots_seen s;
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	struct bkey_s_c_dirent d;
-	int ret;
 
 	snapshots_seen_init(&s);
 
-	for_each_btree_key(trans, iter, BTREE_ID_dirents, POS_MIN,
-			   BTREE_ITER_INTENT|
-			   BTREE_ITER_PREFETCH|
-			   BTREE_ITER_ALL_SNAPSHOTS, k, ret) {
-		ret = snapshots_seen_update(c, &s, iter.btree_id, k.k->p);
-		if (ret)
-			break;
-
-		switch (k.k->type) {
-		case KEY_TYPE_dirent:
-			d = bkey_s_c_to_dirent(k);
+	int ret = bch2_trans_run(c,
+		for_each_btree_key(trans, iter, BTREE_ID_dirents, POS_MIN,
+				   BTREE_ITER_INTENT|
+				   BTREE_ITER_PREFETCH|
+				   BTREE_ITER_ALL_SNAPSHOTS, k, ({
+			ret = snapshots_seen_update(c, &s, iter.btree_id, k.k->p);
+			if (ret)
+				break;
 
-			if (d.v->d_type != DT_DIR &&
-			    d.v->d_type != DT_SUBVOL)
-				inc_link(c, &s, links, range_start, range_end,
-					 le64_to_cpu(d.v->d_inum),
-					 bch2_snapshot_equiv(c, d.k->p.snapshot));
-			break;
-		}
-	}
-	bch2_trans_iter_exit(trans, &iter);
+			if (k.k->type == KEY_TYPE_dirent) {
+				struct bkey_s_c_dirent d = bkey_s_c_to_dirent(k);
 
-	if (ret)
-		bch_err(c, "error in fsck: btree error %i while walking dirents", ret);
+				if (d.v->d_type != DT_DIR &&
+				    d.v->d_type != DT_SUBVOL)
+					inc_link(c, &s, links, range_start, range_end,
+						 le64_to_cpu(d.v->d_inum),
+						 bch2_snapshot_equiv(c, d.k->p.snapshot));
+			}
+			0;
+		})));
 
-	bch2_trans_put(trans);
 	snapshots_seen_exit(&s);
+
+	bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -2389,19 +2301,16 @@ static int check_nlinks_update_hardlinks(struct bch_fs *c,
 			       struct nlink_table *links,
 			       u64 range_start, u64 range_end)
 {
-	struct btree_iter iter;
-	struct bkey_s_c k;
 	size_t idx = 0;
-	int ret = 0;
 
-	ret = bch2_trans_run(c,
+	int ret = bch2_trans_run(c,
 		for_each_btree_key_commit(trans, iter, BTREE_ID_inodes,
 				POS(0, range_start),
 				BTREE_ITER_INTENT|BTREE_ITER_PREFETCH|BTREE_ITER_ALL_SNAPSHOTS, k,
-				NULL, NULL, BTREE_INSERT_LAZY_RW|BTREE_INSERT_NOFAIL,
+				NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 			check_nlinks_update_inode(trans, &iter, k, links, &idx, range_end)));
 	if (ret < 0) {
-		bch_err(c, "error in fsck: btree error %i while walking inodes", ret);
+		bch_err(c, "error in fsck walking inodes: %s", bch2_err_str(ret));
 		return ret;
 	}
 
@@ -2447,7 +2356,6 @@ static int fix_reflink_p_key(struct btree_trans *trans, struct btree_iter *iter,
 {
 	struct bkey_s_c_reflink_p p;
 	struct bkey_i_reflink_p *u;
-	int ret;
 
 	if (k.k->type != KEY_TYPE_reflink_p)
 		return 0;
@@ -2458,7 +2366,7 @@ static int fix_reflink_p_key(struct btree_trans *trans, struct btree_iter *iter,
 		return 0;
 
 	u = bch2_trans_kmalloc(trans, sizeof(*u));
-	ret = PTR_ERR_OR_ZERO(u);
+	int ret = PTR_ERR_OR_ZERO(u);
 	if (ret)
 		return ret;
 
@@ -2471,19 +2379,15 @@ static int fix_reflink_p_key(struct btree_trans *trans, struct btree_iter *iter,
 
 int bch2_fix_reflink_p(struct bch_fs *c)
 {
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	int ret;
-
 	if (c->sb.version >= bcachefs_metadata_version_reflink_p_fix)
 		return 0;
 
-	ret = bch2_trans_run(c,
+	int ret = bch2_trans_run(c,
 		for_each_btree_key_commit(trans, iter,
 				BTREE_ID_extents, POS_MIN,
 				BTREE_ITER_INTENT|BTREE_ITER_PREFETCH|
 				BTREE_ITER_ALL_SNAPSHOTS, k,
-				NULL, NULL, BTREE_INSERT_NOFAIL|BTREE_INSERT_LAZY_RW,
+				NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 			fix_reflink_p_key(trans, &iter, k)));
 	bch_err_fn(c, ret);
 	return ret;
diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c
index def77f2d8802..37dce96f48ac 100644
--- a/fs/bcachefs/inode.c
+++ b/fs/bcachefs/inode.c
@@ -7,6 +7,7 @@
 #include "btree_update.h"
 #include "buckets.h"
 #include "compress.h"
+#include "dirent.h"
 #include "error.h"
 #include "extents.h"
 #include "extent_update.h"
@@ -560,64 +561,46 @@ static inline bool bkey_is_deleted_inode(struct bkey_s_c k)
 	return bkey_inode_flags(k) & BCH_INODE_unlinked;
 }
 
-int bch2_trans_mark_inode(struct btree_trans *trans,
-			  enum btree_id btree_id, unsigned level,
-			  struct bkey_s_c old,
-			  struct bkey_i *new,
-			  unsigned flags)
+int bch2_trigger_inode(struct btree_trans *trans,
+		       enum btree_id btree_id, unsigned level,
+		       struct bkey_s_c old,
+		       struct bkey_s new,
+		       unsigned flags)
 {
-	int nr = bkey_is_inode(&new->k) - bkey_is_inode(old.k);
-	bool old_deleted = bkey_is_deleted_inode(old);
-	bool new_deleted = bkey_is_deleted_inode(bkey_i_to_s_c(new));
+	s64 nr = bkey_is_inode(new.k) - bkey_is_inode(old.k);
 
-	if (nr) {
-		int ret = bch2_replicas_deltas_realloc(trans, 0);
-		struct replicas_delta_list *d = trans->fs_usage_deltas;
+	if (flags & BTREE_TRIGGER_TRANSACTIONAL) {
+		if (nr) {
+			int ret = bch2_replicas_deltas_realloc(trans, 0);
+			if (ret)
+				return ret;
 
-		if (ret)
-			return ret;
-
-		d->nr_inodes += nr;
-	}
+			trans->fs_usage_deltas->nr_inodes += nr;
+		}
 
-	if (old_deleted != new_deleted) {
-		int ret = bch2_btree_bit_mod(trans, BTREE_ID_deleted_inodes, new->k.p, new_deleted);
-		if (ret)
-			return ret;
+		bool old_deleted = bkey_is_deleted_inode(old);
+		bool new_deleted = bkey_is_deleted_inode(new.s_c);
+		if (old_deleted != new_deleted) {
+			int ret = bch2_btree_bit_mod(trans, BTREE_ID_deleted_inodes, new.k->p, new_deleted);
+			if (ret)
+				return ret;
+		}
 	}
 
-	return 0;
-}
-
-int bch2_mark_inode(struct btree_trans *trans,
-		    enum btree_id btree_id, unsigned level,
-		    struct bkey_s_c old, struct bkey_s_c new,
-		    unsigned flags)
-{
-	struct bch_fs *c = trans->c;
-	struct bch_fs_usage *fs_usage;
-	u64 journal_seq = trans->journal_res.seq;
+	if (!(flags & BTREE_TRIGGER_TRANSACTIONAL) && (flags & BTREE_TRIGGER_INSERT)) {
+		BUG_ON(!trans->journal_res.seq);
 
-	if (flags & BTREE_TRIGGER_INSERT) {
-		struct bch_inode_v3 *v = (struct bch_inode_v3 *) new.v;
-
-		BUG_ON(!journal_seq);
-		BUG_ON(new.k->type != KEY_TYPE_inode_v3);
-
-		v->bi_journal_seq = cpu_to_le64(journal_seq);
+		bkey_s_to_inode_v3(new).v->bi_journal_seq = cpu_to_le64(trans->journal_res.seq);
 	}
 
 	if (flags & BTREE_TRIGGER_GC) {
-		percpu_down_read(&c->mark_lock);
-		preempt_disable();
+		struct bch_fs *c = trans->c;
 
-		fs_usage = fs_usage_ptr(c, journal_seq, flags & BTREE_TRIGGER_GC);
-		fs_usage->nr_inodes += bkey_is_inode(new.k);
-		fs_usage->nr_inodes -= bkey_is_inode(old.k);
-
-		preempt_enable();
+		percpu_down_read(&c->mark_lock);
+		this_cpu_add(c->usage_gc->nr_inodes, nr);
 		percpu_up_read(&c->mark_lock);
 	}
+
 	return 0;
 }
 
@@ -830,7 +813,7 @@ static int bch2_inode_delete_keys(struct btree_trans *trans,
 
 		ret = bch2_trans_update(trans, &iter, &delete, 0) ?:
 		      bch2_trans_commit(trans, NULL, NULL,
-					BTREE_INSERT_NOFAIL);
+					BCH_TRANS_COMMIT_no_enospc);
 err:
 		if (ret && !bch2_err_matches(ret, BCH_ERR_transaction_restart))
 			break;
@@ -893,7 +876,7 @@ retry:
 
 	ret   = bch2_trans_update(trans, &iter, &delete.k_i, 0) ?:
 		bch2_trans_commit(trans, NULL, NULL,
-				BTREE_INSERT_NOFAIL);
+				BCH_TRANS_COMMIT_no_enospc);
 err:
 	bch2_trans_iter_exit(trans, &iter);
 	if (bch2_err_matches(ret, BCH_ERR_transaction_restart))
@@ -1057,7 +1040,7 @@ retry:
 
 	ret   = bch2_trans_update(trans, &iter, &delete.k_i, 0) ?:
 		bch2_trans_commit(trans, NULL, NULL,
-				BTREE_INSERT_NOFAIL);
+				BCH_TRANS_COMMIT_no_enospc);
 err:
 	bch2_trans_iter_exit(trans, &iter);
 	if (bch2_err_matches(ret, BCH_ERR_transaction_restart))
@@ -1093,11 +1076,15 @@ static int may_delete_deleted_inode(struct btree_trans *trans,
 	if (ret)
 		goto out;
 
-	if (fsck_err_on(S_ISDIR(inode.bi_mode), c,
-			deleted_inode_is_dir,
-			"directory %llu:%u in deleted_inodes btree",
-			pos.offset, pos.snapshot))
-		goto delete;
+	if (S_ISDIR(inode.bi_mode)) {
+		ret = bch2_empty_dir_snapshot(trans, pos.offset, pos.snapshot);
+		if (fsck_err_on(ret == -ENOTEMPTY, c, deleted_inode_is_dir,
+				"non empty directory %llu:%u in deleted_inodes btree",
+				pos.offset, pos.snapshot))
+			goto delete;
+		if (ret)
+			goto out;
+	}
 
 	if (fsck_err_on(!(inode.bi_flags & BCH_INODE_unlinked), c,
 			deleted_inode_not_unlinked,
@@ -1134,7 +1121,7 @@ static int may_delete_deleted_inode(struct btree_trans *trans,
 		 * unlinked inodes in the snapshot leaves:
 		 */
 		*need_another_pass = true;
-		return 0;
+		goto out;
 	}
 
 	ret = 1;
@@ -1150,49 +1137,48 @@ delete:
 int bch2_delete_dead_inodes(struct bch_fs *c)
 {
 	struct btree_trans *trans = bch2_trans_get(c);
-	struct btree_iter iter;
-	struct bkey_s_c k;
 	bool need_another_pass;
 	int ret;
 again:
 	need_another_pass = false;
 
-	ret = bch2_btree_write_buffer_flush_sync(trans);
-	if (ret)
-		goto err;
-
 	/*
 	 * Weird transaction restart handling here because on successful delete,
 	 * bch2_inode_rm_snapshot() will return a nested transaction restart,
 	 * but we can't retry because the btree write buffer won't have been
 	 * flushed and we'd spin:
 	 */
-	for_each_btree_key(trans, iter, BTREE_ID_deleted_inodes, POS_MIN,
-			   BTREE_ITER_PREFETCH|BTREE_ITER_ALL_SNAPSHOTS, k, ret) {
-		ret = lockrestart_do(trans, may_delete_deleted_inode(trans, &iter, k.k->p,
-								     &need_another_pass));
-		if (ret < 0)
-			break;
-
-		if (ret) {
-			if (!test_bit(BCH_FS_RW, &c->flags)) {
-				bch2_trans_unlock(trans);
-				bch2_fs_lazy_rw(c);
-			}
-
+	ret = for_each_btree_key_commit(trans, iter, BTREE_ID_deleted_inodes, POS_MIN,
+					BTREE_ITER_PREFETCH|BTREE_ITER_ALL_SNAPSHOTS, k,
+					NULL, NULL, BCH_TRANS_COMMIT_no_enospc, ({
+		ret = may_delete_deleted_inode(trans, &iter, k.k->p, &need_another_pass);
+		if (ret > 0) {
 			bch_verbose(c, "deleting unlinked inode %llu:%u", k.k->p.offset, k.k->p.snapshot);
 
 			ret = bch2_inode_rm_snapshot(trans, k.k->p.offset, k.k->p.snapshot);
-			if (ret && !bch2_err_matches(ret, BCH_ERR_transaction_restart))
-				break;
+			/*
+			 * We don't want to loop here: a transaction restart
+			 * error here means we handled a transaction restart and
+			 * we're actually done, but if we loop we'll retry the
+			 * same key because the write buffer hasn't been flushed
+			 * yet
+			 */
+			if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) {
+				ret = 0;
+				continue;
+			}
 		}
-	}
-	bch2_trans_iter_exit(trans, &iter);
 
-	if (!ret && need_another_pass)
+		ret;
+	}));
+
+	if (!ret && need_another_pass) {
+		ret = bch2_btree_write_buffer_flush_sync(trans);
+		if (ret)
+			goto err;
 		goto again;
+	}
 err:
 	bch2_trans_put(trans);
-
 	return ret;
 }
diff --git a/fs/bcachefs/inode.h b/fs/bcachefs/inode.h
index 88818a332b1e..b63f312581cf 100644
--- a/fs/bcachefs/inode.h
+++ b/fs/bcachefs/inode.h
@@ -17,32 +17,27 @@ int bch2_inode_v3_invalid(struct bch_fs *, struct bkey_s_c,
 			  enum bkey_invalid_flags, struct printbuf *);
 void bch2_inode_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
 
-int bch2_trans_mark_inode(struct btree_trans *, enum btree_id, unsigned,
-			  struct bkey_s_c, struct bkey_i *, unsigned);
-int bch2_mark_inode(struct btree_trans *, enum btree_id, unsigned,
-		    struct bkey_s_c, struct bkey_s_c, unsigned);
+int bch2_trigger_inode(struct btree_trans *, enum btree_id, unsigned,
+			  struct bkey_s_c, struct bkey_s, unsigned);
 
 #define bch2_bkey_ops_inode ((struct bkey_ops) {	\
 	.key_invalid	= bch2_inode_invalid,		\
 	.val_to_text	= bch2_inode_to_text,		\
-	.trans_trigger	= bch2_trans_mark_inode,	\
-	.atomic_trigger	= bch2_mark_inode,		\
+	.trigger	= bch2_trigger_inode,		\
 	.min_val_size	= 16,				\
 })
 
 #define bch2_bkey_ops_inode_v2 ((struct bkey_ops) {	\
 	.key_invalid	= bch2_inode_v2_invalid,	\
 	.val_to_text	= bch2_inode_to_text,		\
-	.trans_trigger	= bch2_trans_mark_inode,	\
-	.atomic_trigger	= bch2_mark_inode,		\
+	.trigger	= bch2_trigger_inode,		\
 	.min_val_size	= 32,				\
 })
 
 #define bch2_bkey_ops_inode_v3 ((struct bkey_ops) {	\
 	.key_invalid	= bch2_inode_v3_invalid,	\
 	.val_to_text	= bch2_inode_to_text,		\
-	.trans_trigger	= bch2_trans_mark_inode,	\
-	.atomic_trigger	= bch2_mark_inode,		\
+	.trigger	= bch2_trigger_inode,		\
 	.min_val_size	= 48,				\
 })
 
diff --git a/fs/bcachefs/io_misc.c b/fs/bcachefs/io_misc.c
index bebc11444ef5..ca6d5f516aa2 100644
--- a/fs/bcachefs/io_misc.c
+++ b/fs/bcachefs/io_misc.c
@@ -34,8 +34,7 @@ int bch2_extent_fallocate(struct btree_trans *trans,
 	struct open_buckets open_buckets = { 0 };
 	struct bkey_s_c k;
 	struct bkey_buf old, new;
-	unsigned sectors_allocated = 0;
-	bool have_reservation = false;
+	unsigned sectors_allocated = 0, new_replicas;
 	bool unwritten = opts.nocow &&
 	    c->sb.version >= bcachefs_metadata_version_unwritten_extents;
 	int ret;
@@ -50,28 +49,20 @@ int bch2_extent_fallocate(struct btree_trans *trans,
 		return ret;
 
 	sectors = min_t(u64, sectors, k.k->p.offset - iter->pos.offset);
+	new_replicas = max(0, (int) opts.data_replicas -
+			   (int) bch2_bkey_nr_ptrs_fully_allocated(k));
 
-	if (!have_reservation) {
-		unsigned new_replicas =
-			max(0, (int) opts.data_replicas -
-			    (int) bch2_bkey_nr_ptrs_fully_allocated(k));
-		/*
-		 * Get a disk reservation before (in the nocow case) calling
-		 * into the allocator:
-		 */
-		ret = bch2_disk_reservation_get(c, &disk_res, sectors, new_replicas, 0);
-		if (unlikely(ret))
-			goto err;
-
-		bch2_bkey_buf_reassemble(&old, c, k);
-	}
+	/*
+	 * Get a disk reservation before (in the nocow case) calling
+	 * into the allocator:
+	 */
+	ret = bch2_disk_reservation_get(c, &disk_res, sectors, new_replicas, 0);
+	if (unlikely(ret))
+		goto err_noprint;
 
-	if (have_reservation) {
-		if (!bch2_extents_match(k, bkey_i_to_s_c(old.k)))
-			goto err;
+	bch2_bkey_buf_reassemble(&old, c, k);
 
-		bch2_key_resize(&new.k->k, sectors);
-	} else if (!unwritten) {
+	if (!unwritten) {
 		struct bkey_i_reservation *reservation;
 
 		bch2_bkey_buf_realloc(&new, c, sizeof(*reservation) / sizeof(u64));
@@ -83,7 +74,6 @@ int bch2_extent_fallocate(struct btree_trans *trans,
 		struct bkey_i_extent *e;
 		struct bch_devs_list devs_have;
 		struct write_point *wp;
-		struct bch_extent_ptr *ptr;
 
 		devs_have.nr = 0;
 
@@ -118,14 +108,17 @@ int bch2_extent_fallocate(struct btree_trans *trans,
 			ptr->unwritten = true;
 	}
 
-	have_reservation = true;
-
 	ret = bch2_extent_update(trans, inum, iter, new.k, &disk_res,
 				 0, i_sectors_delta, true);
 err:
 	if (!ret && sectors_allocated)
 		bch2_increment_clock(c, sectors_allocated, WRITE);
-
+	if (should_print_err(ret))
+		bch_err_inum_offset_ratelimited(c,
+			inum.inum,
+			iter->pos.offset << 9,
+			"%s(): error: %s", __func__, bch2_err_str(ret));
+err_noprint:
 	bch2_open_buckets_put(c, &open_buckets);
 	bch2_disk_reservation_put(c, &disk_res);
 	bch2_bkey_buf_exit(&new, c);
@@ -256,7 +249,7 @@ static int __bch2_resume_logged_op_truncate(struct btree_trans *trans,
 	u64 new_i_size = le64_to_cpu(op->v.new_i_size);
 	int ret;
 
-	ret = commit_do(trans, NULL, NULL, BTREE_INSERT_NOFAIL,
+	ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 			truncate_set_isize(trans, inum, new_i_size));
 	if (ret)
 		goto err;
@@ -378,7 +371,7 @@ case LOGGED_OP_FINSERT_start:
 	op->v.state = LOGGED_OP_FINSERT_shift_extents;
 
 	if (insert) {
-		ret = commit_do(trans, NULL, NULL, BTREE_INSERT_NOFAIL,
+		ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 				adjust_i_size(trans, inum, src_offset, len) ?:
 				bch2_logged_op_update(trans, &op->k_i));
 		if (ret)
@@ -390,7 +383,7 @@ case LOGGED_OP_FINSERT_start:
 		if (ret && !bch2_err_matches(ret, BCH_ERR_transaction_restart))
 			goto err;
 
-		ret = commit_do(trans, NULL, NULL, BTREE_INSERT_NOFAIL,
+		ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 				bch2_logged_op_update(trans, &op->k_i));
 	}
 
@@ -455,7 +448,7 @@ case LOGGED_OP_FINSERT_shift_extents:
 			bch2_btree_insert_trans(trans, BTREE_ID_extents, &delete, 0) ?:
 			bch2_btree_insert_trans(trans, BTREE_ID_extents, copy, 0) ?:
 			bch2_logged_op_update(trans, &op->k_i) ?:
-			bch2_trans_commit(trans, &disk_res, NULL, BTREE_INSERT_NOFAIL);
+			bch2_trans_commit(trans, &disk_res, NULL, BCH_TRANS_COMMIT_no_enospc);
 btree_err:
 		bch2_disk_reservation_put(c, &disk_res);
 
@@ -470,12 +463,12 @@ btree_err:
 	op->v.state = LOGGED_OP_FINSERT_finish;
 
 	if (!insert) {
-		ret = commit_do(trans, NULL, NULL, BTREE_INSERT_NOFAIL,
+		ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 				adjust_i_size(trans, inum, src_offset, shift) ?:
 				bch2_logged_op_update(trans, &op->k_i));
 	} else {
 		/* We need an inode update to update bi_journal_seq for fsync: */
-		ret = commit_do(trans, NULL, NULL, BTREE_INSERT_NOFAIL,
+		ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 				adjust_i_size(trans, inum, 0, 0) ?:
 				bch2_logged_op_update(trans, &op->k_i));
 	}
diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c
index a56ed553dc15..3c574d8873a1 100644
--- a/fs/bcachefs/io_read.c
+++ b/fs/bcachefs/io_read.c
@@ -80,7 +80,7 @@ struct promote_op {
 	struct bpos		pos;
 
 	struct data_update	write;
-	struct bio_vec		bi_inline_vecs[0]; /* must be last */
+	struct bio_vec		bi_inline_vecs[]; /* must be last */
 };
 
 static const struct rhashtable_params bch_promote_params = {
@@ -172,11 +172,13 @@ static struct promote_op *__promote_alloc(struct btree_trans *trans,
 	int ret;
 
 	if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_promote))
-		return NULL;
+		return ERR_PTR(-BCH_ERR_nopromote_no_writes);
 
-	op = kzalloc(sizeof(*op) + sizeof(struct bio_vec) * pages, GFP_NOFS);
-	if (!op)
+	op = kzalloc(sizeof(*op) + sizeof(struct bio_vec) * pages, GFP_KERNEL);
+	if (!op) {
+		ret = -BCH_ERR_nopromote_enomem;
 		goto err;
+	}
 
 	op->start_time = local_clock();
 	op->pos = pos;
@@ -187,29 +189,34 @@ static struct promote_op *__promote_alloc(struct btree_trans *trans,
 	 */
 	*rbio = kzalloc(sizeof(struct bch_read_bio) +
 			sizeof(struct bio_vec) * pages,
-			GFP_NOFS);
-	if (!*rbio)
+			GFP_KERNEL);
+	if (!*rbio) {
+		ret = -BCH_ERR_nopromote_enomem;
 		goto err;
+	}
 
 	rbio_init(&(*rbio)->bio, opts);
 	bio_init(&(*rbio)->bio, NULL, (*rbio)->bio.bi_inline_vecs, pages, 0);
 
-	if (bch2_bio_alloc_pages(&(*rbio)->bio, sectors << 9,
-				 GFP_NOFS))
+	if (bch2_bio_alloc_pages(&(*rbio)->bio, sectors << 9, GFP_KERNEL)) {
+		ret = -BCH_ERR_nopromote_enomem;
 		goto err;
+	}
 
 	(*rbio)->bounce		= true;
 	(*rbio)->split		= true;
 	(*rbio)->kmalloc	= true;
 
 	if (rhashtable_lookup_insert_fast(&c->promote_table, &op->hash,
-					  bch_promote_params))
+					  bch_promote_params)) {
+		ret = -BCH_ERR_nopromote_in_flight;
 		goto err;
+	}
 
 	bio = &op->write.op.wbio.bio;
 	bio_init(bio, NULL, bio->bi_inline_vecs, pages, 0);
 
-	ret = bch2_data_update_init(trans, NULL, &op->write,
+	ret = bch2_data_update_init(trans, NULL, NULL, &op->write,
 			writepoint_hashed((unsigned long) current),
 			opts,
 			(struct data_update_opts) {
@@ -223,9 +230,8 @@ static struct promote_op *__promote_alloc(struct btree_trans *trans,
 	 * -BCH_ERR_ENOSPC_disk_reservation:
 	 */
 	if (ret) {
-		ret = rhashtable_remove_fast(&c->promote_table, &op->hash,
-					bch_promote_params);
-		BUG_ON(ret);
+		BUG_ON(rhashtable_remove_fast(&c->promote_table, &op->hash,
+					      bch_promote_params));
 		goto err;
 	}
 
@@ -239,7 +245,7 @@ err:
 	*rbio = NULL;
 	kfree(op);
 	bch2_write_ref_put(c, BCH_WRITE_REF_promote);
-	return NULL;
+	return ERR_PTR(ret);
 }
 
 noinline
@@ -274,10 +280,9 @@ static struct promote_op *promote_alloc(struct btree_trans *trans,
 				  ? BTREE_ID_reflink
 				  : BTREE_ID_extents,
 				  k, pos, pick, opts, sectors, rbio);
-	if (!promote) {
-		ret = -BCH_ERR_nopromote_enomem;
+	ret = PTR_ERR_OR_ZERO(promote);
+	if (ret)
 		goto nopromote;
-	}
 
 	*bounce		= true;
 	*read_full	= promote_full;
@@ -526,7 +531,7 @@ out:
 
 static noinline void bch2_rbio_narrow_crcs(struct bch_read_bio *rbio)
 {
-	bch2_trans_do(rbio->c, NULL, NULL, BTREE_INSERT_NOFAIL,
+	bch2_trans_do(rbio->c, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 		      __bch2_rbio_narrow_crcs(trans, rbio));
 }
 
@@ -637,12 +642,17 @@ csum_err:
 		goto out;
 	}
 
+	struct printbuf buf = PRINTBUF;
+	buf.atomic++;
+	prt_str(&buf, "data ");
+	bch2_csum_err_msg(&buf, crc.csum_type, rbio->pick.crc.csum, csum);
+
 	bch_err_inum_offset_ratelimited(ca,
 		rbio->read_pos.inode,
 		rbio->read_pos.offset << 9,
-		"data checksum error: expected %0llx:%0llx got %0llx:%0llx (type %s)",
-		rbio->pick.crc.csum.hi, rbio->pick.crc.csum.lo,
-		csum.hi, csum.lo, bch2_csum_types[crc.csum_type]);
+		"data %s", buf.buf);
+	printbuf_exit(&buf);
+
 	bch2_io_error(ca, BCH_MEMBER_ERROR_checksum);
 	bch2_rbio_error(rbio, READ_RETRY_AVOID, BLK_STS_IOERR);
 	goto out;
diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c
index f02b3f7d26a0..33c0e783d546 100644
--- a/fs/bcachefs/io_write.c
+++ b/fs/bcachefs/io_write.c
@@ -316,8 +316,8 @@ int bch2_extent_update(struct btree_trans *trans,
 						  i_sectors_delta) ?:
 		bch2_trans_update(trans, iter, k, 0) ?:
 		bch2_trans_commit(trans, disk_res, NULL,
-				BTREE_INSERT_NOCHECK_RW|
-				BTREE_INSERT_NOFAIL);
+				BCH_TRANS_COMMIT_no_check_rw|
+				BCH_TRANS_COMMIT_no_enospc);
 	if (unlikely(ret))
 		return ret;
 
@@ -396,17 +396,14 @@ void bch2_submit_wbio_replicas(struct bch_write_bio *wbio, struct bch_fs *c,
 			       bool nocow)
 {
 	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(bkey_i_to_s_c(k));
-	const struct bch_extent_ptr *ptr;
 	struct bch_write_bio *n;
-	struct bch_dev *ca;
 
 	BUG_ON(c->opts.nochanges);
 
 	bkey_for_each_ptr(ptrs, ptr) {
-		BUG_ON(ptr->dev >= BCH_SB_MEMBERS_MAX ||
-		       !c->devs[ptr->dev]);
+		BUG_ON(!bch2_dev_exists2(c, ptr->dev));
 
-		ca = bch_dev_bkey_exists(c, ptr->dev);
+		struct bch_dev *ca = bch_dev_bkey_exists(c, ptr->dev);
 
 		if (to_entry(ptr + 1) < ptrs.end) {
 			n = to_wbio(bio_alloc_clone(NULL, &wbio->bio,
@@ -580,9 +577,9 @@ static inline void wp_update_state(struct write_point *wp, bool running)
 	__wp_update_state(wp, state);
 }
 
-static void bch2_write_index(struct closure *cl)
+static CLOSURE_CALLBACK(bch2_write_index)
 {
-	struct bch_write_op *op = container_of(cl, struct bch_write_op, cl);
+	closure_type(op, struct bch_write_op, cl);
 	struct write_point *wp = op->wp;
 	struct workqueue_struct *wq = index_update_wq(op);
 	unsigned long flags;
@@ -795,7 +792,7 @@ static int bch2_write_decrypt(struct bch_write_op *op)
 	 * checksum:
 	 */
 	csum = bch2_checksum_bio(c, op->crc.csum_type, nonce, &op->wbio.bio);
-	if (bch2_crc_cmp(op->crc.csum, csum))
+	if (bch2_crc_cmp(op->crc.csum, csum) && !c->opts.no_data_io)
 		return -EIO;
 
 	ret = bch2_encrypt_bio(c, op->crc.csum_type, nonce, &op->wbio.bio);
@@ -1109,16 +1106,14 @@ static bool bch2_extent_is_writeable(struct bch_write_op *op,
 static inline void bch2_nocow_write_unlock(struct bch_write_op *op)
 {
 	struct bch_fs *c = op->c;
-	const struct bch_extent_ptr *ptr;
-	struct bkey_i *k;
 
 	for_each_keylist_key(&op->insert_keys, k) {
 		struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(bkey_i_to_s_c(k));
 
 		bkey_for_each_ptr(ptrs, ptr)
 			bch2_bucket_nocow_unlock(&c->nocow_locks,
-					       PTR_BUCKET_POS(c, ptr),
-					       BUCKET_NOCOW_LOCK_UPDATE);
+						 PTR_BUCKET_POS(c, ptr),
+						 BUCKET_NOCOW_LOCK_UPDATE);
 	}
 }
 
@@ -1128,25 +1123,20 @@ static int bch2_nocow_write_convert_one_unwritten(struct btree_trans *trans,
 						  struct bkey_s_c k,
 						  u64 new_i_size)
 {
-	struct bkey_i *new;
-	struct bkey_ptrs ptrs;
-	struct bch_extent_ptr *ptr;
-	int ret;
-
 	if (!bch2_extents_match(bkey_i_to_s_c(orig), k)) {
 		/* trace this */
 		return 0;
 	}
 
-	new = bch2_bkey_make_mut_noupdate(trans, k);
-	ret = PTR_ERR_OR_ZERO(new);
+	struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, k);
+	int ret = PTR_ERR_OR_ZERO(new);
 	if (ret)
 		return ret;
 
 	bch2_cut_front(bkey_start_pos(&orig->k), new);
 	bch2_cut_back(orig->k.p, new);
 
-	ptrs = bch2_bkey_ptrs(bkey_i_to_s(new));
+	struct bkey_ptrs ptrs = bch2_bkey_ptrs(bkey_i_to_s(new));
 	bkey_for_each_ptr(ptrs, ptr)
 		ptr->unwritten = 0;
 
@@ -1167,16 +1157,12 @@ static void bch2_nocow_write_convert_unwritten(struct bch_write_op *op)
 {
 	struct bch_fs *c = op->c;
 	struct btree_trans *trans = bch2_trans_get(c);
-	struct btree_iter iter;
-	struct bkey_i *orig;
-	struct bkey_s_c k;
-	int ret;
 
 	for_each_keylist_key(&op->insert_keys, orig) {
-		ret = for_each_btree_key_upto_commit(trans, iter, BTREE_ID_extents,
+		int ret = for_each_btree_key_upto_commit(trans, iter, BTREE_ID_extents,
 				     bkey_start_pos(&orig->k), orig->k.p,
 				     BTREE_ITER_INTENT, k,
-				     NULL, NULL, BTREE_INSERT_NOFAIL, ({
+				     NULL, NULL, BCH_TRANS_COMMIT_no_enospc, ({
 			bch2_nocow_write_convert_one_unwritten(trans, &iter, orig, k, op->new_i_size);
 		}));
 
@@ -1208,34 +1194,35 @@ static void __bch2_nocow_write_done(struct bch_write_op *op)
 		bch2_nocow_write_convert_unwritten(op);
 }
 
-static void bch2_nocow_write_done(struct closure *cl)
+static CLOSURE_CALLBACK(bch2_nocow_write_done)
 {
-	struct bch_write_op *op = container_of(cl, struct bch_write_op, cl);
+	closure_type(op, struct bch_write_op, cl);
 
 	__bch2_nocow_write_done(op);
 	bch2_write_done(cl);
 }
 
+struct bucket_to_lock {
+	struct bpos		b;
+	unsigned		gen;
+	struct nocow_lock_bucket *l;
+};
+
 static void bch2_nocow_write(struct bch_write_op *op)
 {
 	struct bch_fs *c = op->c;
 	struct btree_trans *trans;
 	struct btree_iter iter;
 	struct bkey_s_c k;
-	struct bkey_ptrs_c ptrs;
-	const struct bch_extent_ptr *ptr;
-	struct {
-		struct bpos	b;
-		unsigned	gen;
-		struct nocow_lock_bucket *l;
-	} buckets[BCH_REPLICAS_MAX];
-	unsigned nr_buckets = 0;
+	DARRAY_PREALLOCATED(struct bucket_to_lock, 3) buckets;
 	u32 snapshot;
-	int ret, i;
+	struct bucket_to_lock *stale_at;
+	int ret;
 
 	if (op->flags & BCH_WRITE_MOVE)
 		return;
 
+	darray_init(&buckets);
 	trans = bch2_trans_get(c);
 retry:
 	bch2_trans_begin(trans);
@@ -1250,7 +1237,7 @@ retry:
 	while (1) {
 		struct bio *bio = &op->wbio.bio;
 
-		nr_buckets = 0;
+		buckets.nr = 0;
 
 		k = bch2_btree_iter_peek_slot(&iter);
 		ret = bkey_err(k);
@@ -1263,26 +1250,26 @@ retry:
 			break;
 
 		if (bch2_keylist_realloc(&op->insert_keys,
-					op->inline_keys,
-					ARRAY_SIZE(op->inline_keys),
-					k.k->u64s))
+					 op->inline_keys,
+					 ARRAY_SIZE(op->inline_keys),
+					 k.k->u64s))
 			break;
 
 		/* Get iorefs before dropping btree locks: */
-		ptrs = bch2_bkey_ptrs_c(k);
+		struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
 		bkey_for_each_ptr(ptrs, ptr) {
-			buckets[nr_buckets].b = PTR_BUCKET_POS(c, ptr);
-			buckets[nr_buckets].gen = ptr->gen;
-			buckets[nr_buckets].l =
-				bucket_nocow_lock(&c->nocow_locks,
-						  bucket_to_u64(buckets[nr_buckets].b));
-
-			prefetch(buckets[nr_buckets].l);
+			struct bpos b = PTR_BUCKET_POS(c, ptr);
+			struct nocow_lock_bucket *l =
+				bucket_nocow_lock(&c->nocow_locks, bucket_to_u64(b));
+			prefetch(l);
 
 			if (unlikely(!bch2_dev_get_ioref(bch_dev_bkey_exists(c, ptr->dev), WRITE)))
 				goto err_get_ioref;
 
-			nr_buckets++;
+			/* XXX allocating memory with btree locks held - rare */
+			darray_push_gfp(&buckets, ((struct bucket_to_lock) {
+						   .b = b, .gen = ptr->gen, .l = l,
+						   }), GFP_KERNEL|__GFP_NOFAIL);
 
 			if (ptr->unwritten)
 				op->flags |= BCH_WRITE_CONVERT_UNWRITTEN;
@@ -1296,21 +1283,21 @@ retry:
 		if (op->flags & BCH_WRITE_CONVERT_UNWRITTEN)
 			bch2_cut_back(POS(op->pos.inode, op->pos.offset + bio_sectors(bio)), op->insert_keys.top);
 
-		for (i = 0; i < nr_buckets; i++) {
-			struct bch_dev *ca = bch_dev_bkey_exists(c, buckets[i].b.inode);
-			struct nocow_lock_bucket *l = buckets[i].l;
-			bool stale;
+		darray_for_each(buckets, i) {
+			struct bch_dev *ca = bch_dev_bkey_exists(c, i->b.inode);
 
-			__bch2_bucket_nocow_lock(&c->nocow_locks, l,
-						 bucket_to_u64(buckets[i].b),
+			__bch2_bucket_nocow_lock(&c->nocow_locks, i->l,
+						 bucket_to_u64(i->b),
 						 BUCKET_NOCOW_LOCK_UPDATE);
 
 			rcu_read_lock();
-			stale = gen_after(*bucket_gen(ca, buckets[i].b.offset), buckets[i].gen);
+			bool stale = gen_after(*bucket_gen(ca, i->b.offset), i->gen);
 			rcu_read_unlock();
 
-			if (unlikely(stale))
+			if (unlikely(stale)) {
+				stale_at = i;
 				goto err_bucket_stale;
+			}
 		}
 
 		bio = &op->wbio.bio;
@@ -1346,15 +1333,14 @@ err:
 
 	if (ret) {
 		bch_err_inum_offset_ratelimited(c,
-				op->pos.inode,
-				op->pos.offset << 9,
-				"%s: btree lookup error %s",
-				__func__, bch2_err_str(ret));
+			op->pos.inode, op->pos.offset << 9,
+			"%s: btree lookup error %s", __func__, bch2_err_str(ret));
 		op->error = ret;
 		op->flags |= BCH_WRITE_DONE;
 	}
 
 	bch2_trans_put(trans);
+	darray_exit(&buckets);
 
 	/* fallback to cow write path? */
 	if (!(op->flags & BCH_WRITE_DONE)) {
@@ -1363,7 +1349,7 @@ err:
 		op->insert_keys.top = op->insert_keys.keys;
 	} else if (op->flags & BCH_WRITE_SYNC) {
 		closure_sync(&op->cl);
-		bch2_nocow_write_done(&op->cl);
+		bch2_nocow_write_done(&op->cl.work);
 	} else {
 		/*
 		 * XXX
@@ -1374,24 +1360,21 @@ err:
 	}
 	return;
 err_get_ioref:
-	for (i = 0; i < nr_buckets; i++)
-		percpu_ref_put(&bch_dev_bkey_exists(c, buckets[i].b.inode)->io_ref);
+	darray_for_each(buckets, i)
+		percpu_ref_put(&bch_dev_bkey_exists(c, i->b.inode)->io_ref);
 
 	/* Fall back to COW path: */
 	goto out;
 err_bucket_stale:
-	while (i >= 0) {
-		bch2_bucket_nocow_unlock(&c->nocow_locks,
-					 buckets[i].b,
-					 BUCKET_NOCOW_LOCK_UPDATE);
-		--i;
+	darray_for_each(buckets, i) {
+		bch2_bucket_nocow_unlock(&c->nocow_locks, i->b, BUCKET_NOCOW_LOCK_UPDATE);
+		if (i == stale_at)
+			break;
 	}
-	for (i = 0; i < nr_buckets; i++)
-		percpu_ref_put(&bch_dev_bkey_exists(c, buckets[i].b.inode)->io_ref);
 
 	/* We can retry this: */
 	ret = -BCH_ERR_transaction_restart;
-	goto out;
+	goto err_get_ioref;
 }
 
 static void __bch2_write(struct bch_write_op *op)
@@ -1464,6 +1447,10 @@ err:
 			op->flags |= BCH_WRITE_DONE;
 
 			if (ret < 0) {
+				bch_err_inum_offset_ratelimited(c,
+					op->pos.inode,
+					op->pos.offset << 9,
+					"%s(): error: %s", __func__, bch2_err_str(ret));
 				op->error = ret;
 				break;
 			}
@@ -1566,9 +1553,9 @@ err:
  * If op->discard is true, instead of inserting the data it invalidates the
  * region of the cache represented by op->bio and op->inode.
  */
-void bch2_write(struct closure *cl)
+CLOSURE_CALLBACK(bch2_write)
 {
-	struct bch_write_op *op = container_of(cl, struct bch_write_op, cl);
+	closure_type(op, struct bch_write_op, cl);
 	struct bio *bio = &op->wbio.bio;
 	struct bch_fs *c = op->c;
 	unsigned data_len;
diff --git a/fs/bcachefs/io_write.h b/fs/bcachefs/io_write.h
index 9323167229ee..6c276a48f95d 100644
--- a/fs/bcachefs/io_write.h
+++ b/fs/bcachefs/io_write.h
@@ -90,8 +90,7 @@ static inline void bch2_write_op_init(struct bch_write_op *op, struct bch_fs *c,
 	op->devs_need_flush	= NULL;
 }
 
-void bch2_write(struct closure *);
-
+CLOSURE_CALLBACK(bch2_write);
 void bch2_write_point_do_index_updates(struct work_struct *);
 
 static inline struct bch_write_bio *wbio_init(struct bio *bio)
diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c
index 5b5d69f2316b..8538ef34f62b 100644
--- a/fs/bcachefs/journal.c
+++ b/fs/bcachefs/journal.c
@@ -10,6 +10,7 @@
 #include "bkey_methods.h"
 #include "btree_gc.h"
 #include "btree_update.h"
+#include "btree_write_buffer.h"
 #include "buckets.h"
 #include "error.h"
 #include "journal.h"
@@ -184,6 +185,8 @@ static void __journal_entry_close(struct journal *j, unsigned closed_val)
 	/* Close out old buffer: */
 	buf->data->u64s		= cpu_to_le32(old.cur_entry_offset);
 
+	trace_journal_entry_close(c, vstruct_bytes(buf->data));
+
 	sectors = vstruct_blocks_plus(buf->data, c->block_bits,
 				      buf->u64s_reserved) << c->block_bits;
 	BUG_ON(sectors > buf->sectors);
@@ -249,7 +252,7 @@ static bool journal_entry_want_write(struct journal *j)
 	return ret;
 }
 
-static bool journal_entry_close(struct journal *j)
+bool bch2_journal_entry_close(struct journal *j)
 {
 	bool ret;
 
@@ -321,6 +324,8 @@ static int journal_entry_open(struct journal *j)
 	atomic64_inc(&j->seq);
 	journal_pin_list_init(fifo_push_ref(&j->pin), 1);
 
+	BUG_ON(j->pin.back - 1 != atomic64_read(&j->seq));
+
 	BUG_ON(j->buf + (journal_cur_seq(j) & JOURNAL_BUF_MASK) != buf);
 
 	bkey_extent_init(&buf->key);
@@ -328,6 +333,7 @@ static int journal_entry_open(struct journal *j)
 	buf->must_flush	= false;
 	buf->separate_flush = false;
 	buf->flush_time	= 0;
+	buf->need_flush_to_write_buffer = true;
 
 	memset(buf->data, 0, sizeof(*buf->data));
 	buf->data->seq	= cpu_to_le64(journal_cur_seq(j));
@@ -361,11 +367,6 @@ static int journal_entry_open(struct journal *j)
 	} while ((v = atomic64_cmpxchg(&j->reservations.counter,
 				       old.v, new.v)) != old.v);
 
-	if (j->res_get_blocked_start)
-		bch2_time_stats_update(j->blocked_time,
-				       j->res_get_blocked_start);
-	j->res_get_blocked_start = 0;
-
 	mod_delayed_work(c->io_complete_wq,
 			 &j->write_work,
 			 msecs_to_jiffies(c->opts.journal_flush_delay));
@@ -381,7 +382,7 @@ static bool journal_quiesced(struct journal *j)
 	bool ret = atomic64_read(&j->seq) == j->seq_ondisk;
 
 	if (!ret)
-		journal_entry_close(j);
+		bch2_journal_entry_close(j);
 	return ret;
 }
 
@@ -434,7 +435,7 @@ retry:
 
 	/*
 	 * Recheck after taking the lock, so we don't race with another thread
-	 * that just did journal_entry_open() and call journal_entry_close()
+	 * that just did journal_entry_open() and call bch2_journal_entry_close()
 	 * unnecessarily
 	 */
 	if (journal_res_get_fast(j, res, flags)) {
@@ -465,15 +466,12 @@ retry:
 	__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL);
 	ret = journal_entry_open(j);
 
-	if (ret == JOURNAL_ERR_max_in_flight)
+	if (ret == JOURNAL_ERR_max_in_flight) {
+		track_event_change(&c->times[BCH_TIME_blocked_journal_max_in_flight],
+				   &j->max_in_flight_start, true);
 		trace_and_count(c, journal_entry_full, c);
-unlock:
-	if ((ret && ret != JOURNAL_ERR_insufficient_devices) &&
-	    !j->res_get_blocked_start) {
-		j->res_get_blocked_start = local_clock() ?: 1;
-		trace_and_count(c, journal_full, c);
 	}
-
+unlock:
 	can_discard = j->can_discard;
 	spin_unlock(&j->lock);
 
@@ -526,36 +524,6 @@ int bch2_journal_res_get_slowpath(struct journal *j, struct journal_res *res,
 	return ret;
 }
 
-/* journal_preres: */
-
-static bool journal_preres_available(struct journal *j,
-				     struct journal_preres *res,
-				     unsigned new_u64s,
-				     unsigned flags)
-{
-	bool ret = bch2_journal_preres_get_fast(j, res, new_u64s, flags, true);
-
-	if (!ret && mutex_trylock(&j->reclaim_lock)) {
-		bch2_journal_reclaim(j);
-		mutex_unlock(&j->reclaim_lock);
-	}
-
-	return ret;
-}
-
-int __bch2_journal_preres_get(struct journal *j,
-			      struct journal_preres *res,
-			      unsigned new_u64s,
-			      unsigned flags)
-{
-	int ret;
-
-	closure_wait_event(&j->preres_wait,
-		   (ret = bch2_journal_error(j)) ||
-		   journal_preres_available(j, res, new_u64s, flags));
-	return ret;
-}
-
 /* journal_entry_res: */
 
 void bch2_journal_entry_res_resize(struct journal *j,
@@ -802,6 +770,48 @@ void bch2_journal_block(struct journal *j)
 	journal_quiesce(j);
 }
 
+static struct journal_buf *__bch2_next_write_buffer_flush_journal_buf(struct journal *j, u64 max_seq)
+{
+	struct journal_buf *ret = NULL;
+
+	mutex_lock(&j->buf_lock);
+	spin_lock(&j->lock);
+	max_seq = min(max_seq, journal_cur_seq(j));
+
+	for (u64 seq = journal_last_unwritten_seq(j);
+	     seq <= max_seq;
+	     seq++) {
+		unsigned idx = seq & JOURNAL_BUF_MASK;
+		struct journal_buf *buf = j->buf + idx;
+
+		if (buf->need_flush_to_write_buffer) {
+			if (seq == journal_cur_seq(j))
+				__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL);
+
+			union journal_res_state s;
+			s.v = atomic64_read_acquire(&j->reservations.counter);
+
+			ret = journal_state_count(s, idx)
+				? ERR_PTR(-EAGAIN)
+				: buf;
+			break;
+		}
+	}
+
+	spin_unlock(&j->lock);
+	if (IS_ERR_OR_NULL(ret))
+		mutex_unlock(&j->buf_lock);
+	return ret;
+}
+
+struct journal_buf *bch2_next_write_buffer_flush_journal_buf(struct journal *j, u64 max_seq)
+{
+	struct journal_buf *ret;
+
+	wait_event(j->wait, (ret = __bch2_next_write_buffer_flush_journal_buf(j, max_seq)) != ERR_PTR(-EAGAIN));
+	return ret;
+}
+
 /* allocate journal on a device: */
 
 static int __bch2_set_nr_journal_buckets(struct bch_dev *ca, unsigned nr,
@@ -983,8 +993,7 @@ int bch2_set_nr_journal_buckets(struct bch_fs *c, struct bch_dev *ca,
 			break;
 	}
 
-	if (ret)
-		bch_err_fn(c, ret);
+	bch_err_fn(c, ret);
 unlock:
 	up_write(&c->state_lock);
 	return ret;
@@ -1014,17 +1023,13 @@ int bch2_dev_journal_alloc(struct bch_dev *ca)
 
 	ret = __bch2_set_nr_journal_buckets(ca, nr, true, NULL);
 err:
-	if (ret)
-		bch_err_fn(ca, ret);
+	bch_err_fn(ca, ret);
 	return ret;
 }
 
 int bch2_fs_journal_alloc(struct bch_fs *c)
 {
-	struct bch_dev *ca;
-	unsigned i;
-
-	for_each_online_member(ca, c, i) {
+	for_each_online_member(c, ca) {
 		if (ca->journal.nr)
 			continue;
 
@@ -1069,7 +1074,7 @@ void bch2_fs_journal_stop(struct journal *j)
 	bch2_journal_reclaim_stop(j);
 	bch2_journal_flush_all_pins(j);
 
-	wait_event(j->wait, journal_entry_close(j));
+	wait_event(j->wait, bch2_journal_entry_close(j));
 
 	/*
 	 * Always write a new journal entry, to make sure the clock hands are up
@@ -1253,6 +1258,7 @@ int bch2_fs_journal_init(struct journal *j)
 	static struct lock_class_key res_key;
 	unsigned i;
 
+	mutex_init(&j->buf_lock);
 	spin_lock_init(&j->lock);
 	spin_lock_init(&j->err_lock);
 	init_waitqueue_head(&j->wait);
@@ -1288,10 +1294,8 @@ void __bch2_journal_debug_to_text(struct printbuf *out, struct journal *j)
 {
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
 	union journal_res_state s;
-	struct bch_dev *ca;
 	unsigned long now = jiffies;
-	u64 seq;
-	unsigned i;
+	u64 nr_writes = j->nr_flush_writes + j->nr_noflush_writes;
 
 	if (!out->nr_tabstops)
 		printbuf_tabstop_push(out, 24);
@@ -1303,21 +1307,23 @@ void __bch2_journal_debug_to_text(struct printbuf *out, struct journal *j)
 	prt_printf(out, "dirty journal entries:\t%llu/%llu\n",	fifo_used(&j->pin), j->pin.size);
 	prt_printf(out, "seq:\t\t\t%llu\n",			journal_cur_seq(j));
 	prt_printf(out, "seq_ondisk:\t\t%llu\n",		j->seq_ondisk);
-	prt_printf(out, "last_seq:\t\t%llu\n",		journal_last_seq(j));
+	prt_printf(out, "last_seq:\t\t%llu\n",			journal_last_seq(j));
 	prt_printf(out, "last_seq_ondisk:\t%llu\n",		j->last_seq_ondisk);
-	prt_printf(out, "flushed_seq_ondisk:\t%llu\n",	j->flushed_seq_ondisk);
-	prt_printf(out, "prereserved:\t\t%u/%u\n",		j->prereserved.reserved, j->prereserved.remaining);
-	prt_printf(out, "watermark:\t\t%s\n",		bch2_watermarks[j->watermark]);
-	prt_printf(out, "each entry reserved:\t%u\n",	j->entry_u64s_reserved);
+	prt_printf(out, "flushed_seq_ondisk:\t%llu\n",		j->flushed_seq_ondisk);
+	prt_printf(out, "watermark:\t\t%s\n",			bch2_watermarks[j->watermark]);
+	prt_printf(out, "each entry reserved:\t%u\n",		j->entry_u64s_reserved);
 	prt_printf(out, "nr flush writes:\t%llu\n",		j->nr_flush_writes);
-	prt_printf(out, "nr noflush writes:\t%llu\n",	j->nr_noflush_writes);
-	prt_printf(out, "nr direct reclaim:\t%llu\n",	j->nr_direct_reclaim);
+	prt_printf(out, "nr noflush writes:\t%llu\n",		j->nr_noflush_writes);
+	prt_printf(out, "average write size:\t");
+	prt_human_readable_u64(out, nr_writes ? div64_u64(j->entry_bytes_written, nr_writes) : 0);
+	prt_newline(out);
+	prt_printf(out, "nr direct reclaim:\t%llu\n",		j->nr_direct_reclaim);
 	prt_printf(out, "nr background reclaim:\t%llu\n",	j->nr_background_reclaim);
 	prt_printf(out, "reclaim kicked:\t\t%u\n",		j->reclaim_kicked);
-	prt_printf(out, "reclaim runs in:\t%u ms\n",	time_after(j->next_reclaim, now)
+	prt_printf(out, "reclaim runs in:\t%u ms\n",		time_after(j->next_reclaim, now)
 	       ? jiffies_to_msecs(j->next_reclaim - jiffies) : 0);
-	prt_printf(out, "current entry sectors:\t%u\n",	j->cur_entry_sectors);
-	prt_printf(out, "current entry error:\t%s\n",	bch2_journal_errors[j->cur_entry_error]);
+	prt_printf(out, "current entry sectors:\t%u\n",		j->cur_entry_sectors);
+	prt_printf(out, "current entry error:\t%s\n",		bch2_journal_errors[j->cur_entry_error]);
 	prt_printf(out, "current entry:\t\t");
 
 	switch (s.cur_entry_offset) {
@@ -1334,10 +1340,10 @@ void __bch2_journal_debug_to_text(struct printbuf *out, struct journal *j)
 
 	prt_newline(out);
 
-	for (seq = journal_cur_seq(j);
+	for (u64 seq = journal_cur_seq(j);
 	     seq >= journal_last_unwritten_seq(j);
 	     --seq) {
-		i = seq & JOURNAL_BUF_MASK;
+		unsigned i = seq & JOURNAL_BUF_MASK;
 
 		prt_printf(out, "unwritten entry:");
 		prt_tab(out);
@@ -1381,8 +1387,7 @@ void __bch2_journal_debug_to_text(struct printbuf *out, struct journal *j)
 	       j->space[journal_space_total].next_entry,
 	       j->space[journal_space_total].total);
 
-	for_each_member_device_rcu(ca, c, i,
-				   &c->rw_devs[BCH_DATA_journal]) {
+	for_each_member_device_rcu(c, ca, &c->rw_devs[BCH_DATA_journal]) {
 		struct journal_device *ja = &ca->journal;
 
 		if (!test_bit(ca->dev_idx, c->rw_devs[BCH_DATA_journal].d))
@@ -1391,7 +1396,7 @@ void __bch2_journal_debug_to_text(struct printbuf *out, struct journal *j)
 		if (!ja->nr)
 			continue;
 
-		prt_printf(out, "dev %u:\n",		i);
+		prt_printf(out, "dev %u:\n",		ca->dev_idx);
 		prt_printf(out, "\tnr\t\t%u\n",		ja->nr);
 		prt_printf(out, "\tbucket size\t%u\n",	ca->mi.bucket_size);
 		prt_printf(out, "\tavailable\t%u:%u\n",	bch2_journal_dev_buckets_available(j, ja, journal_space_discarded), ja->sectors_free);
diff --git a/fs/bcachefs/journal.h b/fs/bcachefs/journal.h
index 011711e99c8d..4544ce24bb8a 100644
--- a/fs/bcachefs/journal.h
+++ b/fs/bcachefs/journal.h
@@ -119,7 +119,6 @@ static inline void journal_wake(struct journal *j)
 {
 	wake_up(&j->wait);
 	closure_wake_up(&j->async_wait);
-	closure_wake_up(&j->preres_wait);
 }
 
 static inline struct journal_buf *journal_cur_buf(struct journal *j)
@@ -136,9 +135,7 @@ static inline u64 journal_last_seq(struct journal *j)
 
 static inline u64 journal_cur_seq(struct journal *j)
 {
-	EBUG_ON(j->pin.back - 1 != atomic64_read(&j->seq));
-
-	return j->pin.back - 1;
+	return atomic64_read(&j->seq);
 }
 
 static inline u64 journal_last_unwritten_seq(struct journal *j)
@@ -241,8 +238,6 @@ bch2_journal_add_entry(struct journal *j, struct journal_res *res,
 
 static inline bool journal_entry_empty(struct jset *j)
 {
-	struct jset_entry *i;
-
 	if (j->seq != j->last_seq)
 		return false;
 
@@ -268,6 +263,7 @@ static inline union journal_res_state journal_state_buf_put(struct journal *j, u
 	return s;
 }
 
+bool bch2_journal_entry_close(struct journal *);
 void bch2_journal_buf_put_final(struct journal *, u64, bool);
 
 static inline void __bch2_journal_buf_put(struct journal *j, unsigned idx, u64 seq)
@@ -395,104 +391,6 @@ out:
 	return 0;
 }
 
-/* journal_preres: */
-
-static inline void journal_set_watermark(struct journal *j)
-{
-	union journal_preres_state s = READ_ONCE(j->prereserved);
-	unsigned watermark = BCH_WATERMARK_stripe;
-
-	if (fifo_free(&j->pin) < j->pin.size / 4)
-		watermark = max_t(unsigned, watermark, BCH_WATERMARK_copygc);
-	if (fifo_free(&j->pin) < j->pin.size / 8)
-		watermark = max_t(unsigned, watermark, BCH_WATERMARK_reclaim);
-
-	if (s.reserved > s.remaining)
-		watermark = max_t(unsigned, watermark, BCH_WATERMARK_copygc);
-	if (!s.remaining)
-		watermark = max_t(unsigned, watermark, BCH_WATERMARK_reclaim);
-
-	if (watermark == j->watermark)
-		return;
-
-	swap(watermark, j->watermark);
-	if (watermark > j->watermark)
-		journal_wake(j);
-}
-
-static inline void bch2_journal_preres_put(struct journal *j,
-					   struct journal_preres *res)
-{
-	union journal_preres_state s = { .reserved = res->u64s };
-
-	if (!res->u64s)
-		return;
-
-	s.v = atomic64_sub_return(s.v, &j->prereserved.counter);
-	res->u64s = 0;
-
-	if (unlikely(s.waiting)) {
-		clear_bit(ilog2((((union journal_preres_state) { .waiting = 1 }).v)),
-			  (unsigned long *) &j->prereserved.v);
-		closure_wake_up(&j->preres_wait);
-	}
-
-	if (s.reserved <= s.remaining && j->watermark)
-		journal_set_watermark(j);
-}
-
-int __bch2_journal_preres_get(struct journal *,
-			struct journal_preres *, unsigned, unsigned);
-
-static inline int bch2_journal_preres_get_fast(struct journal *j,
-					       struct journal_preres *res,
-					       unsigned new_u64s,
-					       unsigned flags,
-					       bool set_waiting)
-{
-	int d = new_u64s - res->u64s;
-	union journal_preres_state old, new;
-	u64 v = atomic64_read(&j->prereserved.counter);
-	enum bch_watermark watermark = flags & BCH_WATERMARK_MASK;
-	int ret;
-
-	do {
-		old.v = new.v = v;
-		ret = 0;
-
-		if (watermark == BCH_WATERMARK_reclaim ||
-		    new.reserved + d < new.remaining) {
-			new.reserved += d;
-			ret = 1;
-		} else if (set_waiting && !new.waiting)
-			new.waiting = true;
-		else
-			return 0;
-	} while ((v = atomic64_cmpxchg(&j->prereserved.counter,
-				       old.v, new.v)) != old.v);
-
-	if (ret)
-		res->u64s += d;
-	return ret;
-}
-
-static inline int bch2_journal_preres_get(struct journal *j,
-					  struct journal_preres *res,
-					  unsigned new_u64s,
-					  unsigned flags)
-{
-	if (new_u64s <= res->u64s)
-		return 0;
-
-	if (bch2_journal_preres_get_fast(j, res, new_u64s, flags, false))
-		return 0;
-
-	if (flags & JOURNAL_RES_GET_NONBLOCK)
-		return -BCH_ERR_journal_preres_get_blocked;
-
-	return __bch2_journal_preres_get(j, res, new_u64s, flags);
-}
-
 /* journal_entry_res: */
 
 void bch2_journal_entry_res_resize(struct journal *,
@@ -525,6 +423,7 @@ static inline void bch2_journal_set_replay_done(struct journal *j)
 
 void bch2_journal_unblock(struct journal *);
 void bch2_journal_block(struct journal *);
+struct journal_buf *bch2_next_write_buffer_flush_journal_buf(struct journal *j, u64 max_seq);
 
 void __bch2_journal_debug_to_text(struct printbuf *, struct journal *);
 void bch2_journal_debug_to_text(struct printbuf *, struct journal *);
diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c
index f4bc2cdbfdd7..b0f4dd491e12 100644
--- a/fs/bcachefs/journal_io.c
+++ b/fs/bcachefs/journal_io.c
@@ -4,6 +4,7 @@
 #include "alloc_foreground.h"
 #include "btree_io.h"
 #include "btree_update_interior.h"
+#include "btree_write_buffer.h"
 #include "buckets.h"
 #include "checksum.h"
 #include "disk_groups.h"
@@ -26,11 +27,15 @@ static struct nonce journal_nonce(const struct jset *jset)
 	}};
 }
 
-static bool jset_csum_good(struct bch_fs *c, struct jset *j)
+static bool jset_csum_good(struct bch_fs *c, struct jset *j, struct bch_csum *csum)
 {
-	return bch2_checksum_type_valid(c, JSET_CSUM_TYPE(j)) &&
-		!bch2_crc_cmp(j->csum,
-			      csum_vstruct(c, JSET_CSUM_TYPE(j), journal_nonce(j), j));
+	if (!bch2_checksum_type_valid(c, JSET_CSUM_TYPE(j))) {
+		*csum = (struct bch_csum) {};
+		return false;
+	}
+
+	*csum = csum_vstruct(c, JSET_CSUM_TYPE(j), journal_nonce(j), j);
+	return !bch2_crc_cmp(j->csum, *csum);
 }
 
 static inline u32 journal_entry_radix_idx(struct bch_fs *c, u64 seq)
@@ -408,8 +413,10 @@ static int journal_entry_btree_root_validate(struct bch_fs *c,
 		return 0;
 	}
 
-	return journal_validate_key(c, jset, entry, 1, entry->btree_id, k,
-				    version, big_endian, flags);
+	ret = journal_validate_key(c, jset, entry, 1, entry->btree_id, k,
+				   version, big_endian, flags);
+	if (ret == FSCK_DELETED_KEY)
+		ret = 0;
 fsck_err:
 	return ret;
 }
@@ -547,6 +554,7 @@ static int journal_entry_data_usage_validate(struct bch_fs *c,
 	struct jset_entry_data_usage *u =
 		container_of(entry, struct jset_entry_data_usage, entry);
 	unsigned bytes = jset_u64s(le16_to_cpu(entry->u64s)) * sizeof(u64);
+	struct printbuf err = PRINTBUF;
 	int ret = 0;
 
 	if (journal_entry_err_on(bytes < sizeof(*u) ||
@@ -555,10 +563,19 @@ static int journal_entry_data_usage_validate(struct bch_fs *c,
 				 journal_entry_data_usage_bad_size,
 				 "invalid journal entry usage: bad size")) {
 		journal_entry_null_range(entry, vstruct_next(entry));
-		return ret;
+		goto out;
 	}
 
+	if (journal_entry_err_on(bch2_replicas_entry_validate(&u->r, c->disk_sb.sb, &err),
+				 c, version, jset, entry,
+				 journal_entry_data_usage_bad_size,
+				 "invalid journal entry usage: %s", err.buf)) {
+		journal_entry_null_range(entry, vstruct_next(entry));
+		goto out;
+	}
+out:
 fsck_err:
+	printbuf_exit(&err);
 	return ret;
 }
 
@@ -675,8 +692,6 @@ static void journal_entry_dev_usage_to_text(struct printbuf *out, struct bch_fs
 		       le64_to_cpu(u->d[i].sectors),
 		       le64_to_cpu(u->d[i].fragmented));
 	}
-
-	prt_printf(out, " buckets_ec: %llu", le64_to_cpu(u->buckets_ec));
 }
 
 static int journal_entry_log_validate(struct bch_fs *c,
@@ -713,6 +728,22 @@ static void journal_entry_overwrite_to_text(struct printbuf *out, struct bch_fs
 	journal_entry_btree_keys_to_text(out, c, entry);
 }
 
+static int journal_entry_write_buffer_keys_validate(struct bch_fs *c,
+				struct jset *jset,
+				struct jset_entry *entry,
+				unsigned version, int big_endian,
+				enum bkey_invalid_flags flags)
+{
+	return journal_entry_btree_keys_validate(c, jset, entry,
+				version, big_endian, READ);
+}
+
+static void journal_entry_write_buffer_keys_to_text(struct printbuf *out, struct bch_fs *c,
+					    struct jset_entry *entry)
+{
+	journal_entry_btree_keys_to_text(out, c, entry);
+}
+
 struct jset_entry_ops {
 	int (*validate)(struct bch_fs *, struct jset *,
 			struct jset_entry *, unsigned, int,
@@ -756,7 +787,6 @@ void bch2_journal_entry_to_text(struct printbuf *out, struct bch_fs *c,
 static int jset_validate_entries(struct bch_fs *c, struct jset *jset,
 				 enum bkey_invalid_flags flags)
 {
-	struct jset_entry *entry;
 	unsigned version = le32_to_cpu(jset->version);
 	int ret = 0;
 
@@ -908,6 +938,7 @@ static int journal_read_bucket(struct bch_dev *ca,
 	u64 offset = bucket_to_sector(ca, ja->buckets[bucket]),
 	    end = offset + ca->mi.bucket_size;
 	bool saw_bad = false, csum_good;
+	struct printbuf err = PRINTBUF;
 	int ret = 0;
 
 	pr_debug("reading %u", bucket);
@@ -940,7 +971,7 @@ reread:
 				 * found on a different device, and missing or
 				 * no journal entries will be handled later
 				 */
-				return 0;
+				goto out;
 			}
 
 			j = buf->data;
@@ -957,12 +988,12 @@ reread:
 				ret = journal_read_buf_realloc(buf,
 							vstruct_bytes(j));
 				if (ret)
-					return ret;
+					goto err;
 			}
 			goto reread;
 		case JOURNAL_ENTRY_NONE:
 			if (!saw_bad)
-				return 0;
+				goto out;
 			/*
 			 * On checksum error we don't really trust the size
 			 * field of the journal entry we read, so try reading
@@ -971,7 +1002,7 @@ reread:
 			sectors = block_sectors(c);
 			goto next_block;
 		default:
-			return ret;
+			goto err;
 		}
 
 		/*
@@ -981,20 +1012,28 @@ reread:
 		 * bucket:
 		 */
 		if (le64_to_cpu(j->seq) < ja->bucket_seq[bucket])
-			return 0;
+			goto out;
 
 		ja->bucket_seq[bucket] = le64_to_cpu(j->seq);
 
-		csum_good = jset_csum_good(c, j);
+		enum bch_csum_type csum_type = JSET_CSUM_TYPE(j);
+		struct bch_csum csum;
+		csum_good = jset_csum_good(c, j, &csum);
+
 		if (bch2_dev_io_err_on(!csum_good, ca, BCH_MEMBER_ERROR_checksum,
-				       "journal checksum error"))
+				       "%s",
+				       (printbuf_reset(&err),
+					prt_str(&err, "journal "),
+					bch2_csum_err_msg(&err, csum_type, j->csum, csum),
+					err.buf)))
 			saw_bad = true;
 
 		ret = bch2_encrypt(c, JSET_CSUM_TYPE(j), journal_nonce(j),
 			     j->encrypted_start,
 			     vstruct_end(j) - (void *) j->encrypted_start);
 		bch2_fs_fatal_err_on(ret, c,
-				"error decrypting journal entry: %i", ret);
+				"error decrypting journal entry: %s",
+				bch2_err_str(ret));
 
 		mutex_lock(&jlist->lock);
 		ret = journal_entry_add(c, ca, (struct journal_ptr) {
@@ -1013,7 +1052,7 @@ reread:
 		case JOURNAL_ENTRY_ADD_OUT_OF_RANGE:
 			break;
 		default:
-			return ret;
+			goto err;
 		}
 next_block:
 		pr_debug("next");
@@ -1022,13 +1061,16 @@ next_block:
 		j = ((void *) j) + (sectors << 9);
 	}
 
-	return 0;
+out:
+	ret = 0;
+err:
+	printbuf_exit(&err);
+	return ret;
 }
 
-static void bch2_journal_read_device(struct closure *cl)
+static CLOSURE_CALLBACK(bch2_journal_read_device)
 {
-	struct journal_device *ja =
-		container_of(cl, struct journal_device, read);
+	closure_type(ja, struct journal_device, read);
 	struct bch_dev *ca = container_of(ja, struct bch_dev, journal);
 	struct bch_fs *c = ca->fs;
 	struct journal_list *jlist =
@@ -1079,6 +1121,12 @@ found:
 
 	if (ja->bucket_seq[ja->cur_idx] &&
 	    ja->sectors_free == ca->mi.bucket_size) {
+#if 0
+		/*
+		 * Debug code for ZNS support, where we (probably) want to be
+		 * correlated where we stopped in the journal to the zone write
+		 * points:
+		 */
 		bch_err(c, "ja->sectors_free == ca->mi.bucket_size");
 		bch_err(c, "cur_idx %u/%u", ja->cur_idx, ja->nr);
 		for (i = 0; i < 3; i++) {
@@ -1086,6 +1134,7 @@ found:
 
 			bch_err(c, "bucket_seq[%u] = %llu", idx, ja->bucket_seq[idx]);
 		}
+#endif
 		ja->sectors_free = 0;
 	}
 
@@ -1138,8 +1187,6 @@ int bch2_journal_read(struct bch_fs *c,
 	struct journal_list jlist;
 	struct journal_replay *i, **_i, *prev = NULL;
 	struct genradix_iter radix_iter;
-	struct bch_dev *ca;
-	unsigned iter;
 	struct printbuf buf = PRINTBUF;
 	bool degraded = false, last_write_torn = false;
 	u64 seq;
@@ -1150,7 +1197,7 @@ int bch2_journal_read(struct bch_fs *c,
 	jlist.last_seq = 0;
 	jlist.ret = 0;
 
-	for_each_member_device(ca, c, iter) {
+	for_each_member_device(c, ca) {
 		if (!c->opts.fsck &&
 		    !(bch2_dev_has_data(c, ca) & (1 << BCH_DATA_journal)))
 			continue;
@@ -1316,7 +1363,7 @@ int bch2_journal_read(struct bch_fs *c,
 			continue;
 
 		for (ptr = 0; ptr < i->nr_ptrs; ptr++) {
-			ca = bch_dev_bkey_exists(c, i->ptrs[ptr].dev);
+			struct bch_dev *ca = bch_dev_bkey_exists(c, i->ptrs[ptr].dev);
 
 			if (!i->ptrs[ptr].csum_good)
 				bch_err_dev_offset(ca, i->ptrs[ptr].sector,
@@ -1487,6 +1534,8 @@ done:
 
 static void journal_buf_realloc(struct journal *j, struct journal_buf *buf)
 {
+	struct bch_fs *c = container_of(j, struct bch_fs, journal);
+
 	/* we aren't holding j->lock: */
 	unsigned new_size = READ_ONCE(j->buf_size_want);
 	void *new_buf;
@@ -1494,6 +1543,11 @@ static void journal_buf_realloc(struct journal *j, struct journal_buf *buf)
 	if (buf->buf_size >= new_size)
 		return;
 
+	size_t btree_write_buffer_size = new_size / 64;
+
+	if (bch2_btree_write_buffer_resize(c, btree_write_buffer_size))
+		return;
+
 	new_buf = kvpmalloc(new_size, GFP_NOFS|__GFP_NOWARN);
 	if (!new_buf)
 		return;
@@ -1513,9 +1567,9 @@ static inline struct journal_buf *journal_last_unwritten_buf(struct journal *j)
 	return j->buf + (journal_last_unwritten_seq(j) & JOURNAL_BUF_MASK);
 }
 
-static void journal_write_done(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write_done)
 {
-	struct journal *j = container_of(cl, struct journal, io);
+	closure_type(j, struct journal, io);
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
 	struct journal_buf *w = journal_last_unwritten_buf(j);
 	struct bch_replicas_padded replicas;
@@ -1583,8 +1637,12 @@ static void journal_write_done(struct closure *cl)
 	} while ((v = atomic64_cmpxchg(&j->reservations.counter,
 				       old.v, new.v)) != old.v);
 
+	bch2_journal_reclaim_fast(j);
 	bch2_journal_space_available(j);
 
+	track_event_change(&c->times[BCH_TIME_blocked_journal_max_in_flight],
+			   &j->max_in_flight_start, false);
+
 	closure_wake_up(&w->wait);
 	journal_wake(j);
 
@@ -1631,13 +1689,12 @@ static void journal_write_endio(struct bio *bio)
 	percpu_ref_put(&ca->io_ref);
 }
 
-static void do_journal_write(struct closure *cl)
+static CLOSURE_CALLBACK(do_journal_write)
 {
-	struct journal *j = container_of(cl, struct journal, io);
+	closure_type(j, struct journal, io);
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
 	struct bch_dev *ca;
 	struct journal_buf *w = journal_last_unwritten_buf(j);
-	struct bch_extent_ptr *ptr;
 	struct bio *bio;
 	unsigned sectors = vstruct_sectors(w->data, c->block_bits);
 
@@ -1681,11 +1738,13 @@ static void do_journal_write(struct closure *cl)
 static int bch2_journal_write_prep(struct journal *j, struct journal_buf *w)
 {
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
-	struct jset_entry *start, *end, *i, *next, *prev = NULL;
+	struct jset_entry *start, *end;
 	struct jset *jset = w->data;
+	struct journal_keys_to_wb wb = { NULL };
 	unsigned sectors, bytes, u64s;
-	bool validate_before_checksum = false;
 	unsigned long btree_roots_have = 0;
+	bool validate_before_checksum = false;
+	u64 seq = le64_to_cpu(jset->seq);
 	int ret;
 
 	/*
@@ -1696,7 +1755,7 @@ static int bch2_journal_write_prep(struct journal *j, struct journal_buf *w)
 	 * If we wanted to be really fancy here, we could sort all the keys in
 	 * the jset and drop keys that were overwritten - probably not worth it:
 	 */
-	vstruct_for_each_safe(jset, i, next) {
+	vstruct_for_each(jset, i) {
 		unsigned u64s = le16_to_cpu(i->u64s);
 
 		/* Empty entry: */
@@ -1713,40 +1772,40 @@ static int bch2_journal_write_prep(struct journal *j, struct journal_buf *w)
 		 * to c->btree_roots we have to get any missing btree roots and
 		 * add them to this journal entry:
 		 */
-		if (i->type == BCH_JSET_ENTRY_btree_root) {
+		switch (i->type) {
+		case BCH_JSET_ENTRY_btree_root:
 			bch2_journal_entry_to_btree_root(c, i);
 			__set_bit(i->btree_id, &btree_roots_have);
+			break;
+		case BCH_JSET_ENTRY_write_buffer_keys:
+			EBUG_ON(!w->need_flush_to_write_buffer);
+
+			if (!wb.wb)
+				bch2_journal_keys_to_write_buffer_start(c, &wb, seq);
+
+			struct bkey_i *k;
+			jset_entry_for_each_key(i, k) {
+				ret = bch2_journal_key_to_wb(c, &wb, i->btree_id, k);
+				if (ret) {
+					bch2_fs_fatal_error(c, "-ENOMEM flushing journal keys to btree write buffer");
+					bch2_journal_keys_to_write_buffer_end(c, &wb);
+					return ret;
+				}
+			}
+			i->type = BCH_JSET_ENTRY_btree_keys;
+			break;
 		}
-
-		/* Can we merge with previous entry? */
-		if (prev &&
-		    i->btree_id == prev->btree_id &&
-		    i->level	== prev->level &&
-		    i->type	== prev->type &&
-		    i->type	== BCH_JSET_ENTRY_btree_keys &&
-		    le16_to_cpu(prev->u64s) + u64s <= U16_MAX) {
-			memmove_u64s_down(vstruct_next(prev),
-					  i->_data,
-					  u64s);
-			le16_add_cpu(&prev->u64s, u64s);
-			continue;
-		}
-
-		/* Couldn't merge, move i into new position (after prev): */
-		prev = prev ? vstruct_next(prev) : jset->start;
-		if (i != prev)
-			memmove_u64s_down(prev, i, jset_u64s(u64s));
 	}
 
-	prev = prev ? vstruct_next(prev) : jset->start;
-	jset->u64s = cpu_to_le32((u64 *) prev - jset->_data);
+	if (wb.wb)
+		bch2_journal_keys_to_write_buffer_end(c, &wb);
+	w->need_flush_to_write_buffer = false;
 
 	start = end = vstruct_last(jset);
 
 	end	= bch2_btree_roots_to_journal_entries(c, end, btree_roots_have);
 
-	bch2_journal_super_entries_add_common(c, &end,
-				le64_to_cpu(jset->seq));
+	bch2_journal_super_entries_add_common(c, &end, seq);
 	u64s	= (u64 *) end - (u64 *) start;
 	BUG_ON(u64s > j->entry_u64s_reserved);
 
@@ -1769,7 +1828,7 @@ static int bch2_journal_write_prep(struct journal *j, struct journal_buf *w)
 	SET_JSET_CSUM_TYPE(jset, bch2_meta_checksum_type(c));
 
 	if (!JSET_NO_FLUSH(jset) && journal_entry_empty(jset))
-		j->last_empty_seq = le64_to_cpu(jset->seq);
+		j->last_empty_seq = seq;
 
 	if (bch2_csum_type_is_encryption(JSET_CSUM_TYPE(jset)))
 		validate_before_checksum = true;
@@ -1828,7 +1887,7 @@ static int bch2_journal_write_pick_flush(struct journal *j, struct journal_buf *
 	    (!w->must_flush &&
 	     (jiffies - j->last_flush_write) < msecs_to_jiffies(c->opts.journal_flush_delay) &&
 	     test_bit(JOURNAL_MAY_SKIP_FLUSH, &j->flags))) {
-		     w->noflush = true;
+		w->noflush = true;
 		SET_JSET_NO_FLUSH(w->data, true);
 		w->data->last_seq	= 0;
 		w->last_seq		= 0;
@@ -1843,16 +1902,15 @@ static int bch2_journal_write_pick_flush(struct journal *j, struct journal_buf *
 	return 0;
 }
 
-void bch2_journal_write(struct closure *cl)
+CLOSURE_CALLBACK(bch2_journal_write)
 {
-	struct journal *j = container_of(cl, struct journal, io);
+	closure_type(j, struct journal, io);
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
-	struct bch_dev *ca;
 	struct journal_buf *w = journal_last_unwritten_buf(j);
 	struct bch_replicas_padded replicas;
 	struct bio *bio;
 	struct printbuf journal_debug_buf = PRINTBUF;
-	unsigned i, nr_rw_members = 0;
+	unsigned nr_rw_members = 0;
 	int ret;
 
 	BUG_ON(BCH_SB_CLEAN(c->disk_sb.sb));
@@ -1865,12 +1923,16 @@ void bch2_journal_write(struct closure *cl)
 	if (ret)
 		goto err;
 
+	mutex_lock(&j->buf_lock);
 	journal_buf_realloc(j, w);
 
 	ret = bch2_journal_write_prep(j, w);
+	mutex_unlock(&j->buf_lock);
 	if (ret)
 		goto err;
 
+	j->entry_bytes_written += vstruct_bytes(w->data);
+
 	while (1) {
 		spin_lock(&j->lock);
 		ret = journal_write_alloc(j, w);
@@ -1908,7 +1970,7 @@ void bch2_journal_write(struct closure *cl)
 	if (c->opts.nochanges)
 		goto no_io;
 
-	for_each_rw_member(ca, c, i)
+	for_each_rw_member(c, ca)
 		nr_rw_members++;
 
 	if (nr_rw_members > 1)
@@ -1925,7 +1987,7 @@ void bch2_journal_write(struct closure *cl)
 		goto err;
 
 	if (!JSET_NO_FLUSH(w->data) && w->separate_flush) {
-		for_each_rw_member(ca, c, i) {
+		for_each_rw_member(c, ca) {
 			percpu_ref_get(&ca->io_ref);
 
 			bio = ca->journal.bio;
diff --git a/fs/bcachefs/journal_io.h b/fs/bcachefs/journal_io.h
index a88d097b13f1..c035e7c108e1 100644
--- a/fs/bcachefs/journal_io.h
+++ b/fs/bcachefs/journal_io.h
@@ -60,6 +60,6 @@ void bch2_journal_ptrs_to_text(struct printbuf *, struct bch_fs *,
 
 int bch2_journal_read(struct bch_fs *, u64 *, u64 *, u64 *);
 
-void bch2_journal_write(struct closure *);
+CLOSURE_CALLBACK(bch2_journal_write);
 
 #endif /* _BCACHEFS_JOURNAL_IO_H */
diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c
index 9a584aaaa2eb..820d25e19e5f 100644
--- a/fs/bcachefs/journal_reclaim.c
+++ b/fs/bcachefs/journal_reclaim.c
@@ -3,6 +3,7 @@
 #include "bcachefs.h"
 #include "btree_key_cache.h"
 #include "btree_update.h"
+#include "btree_write_buffer.h"
 #include "buckets.h"
 #include "errcode.h"
 #include "error.h"
@@ -50,16 +51,28 @@ unsigned bch2_journal_dev_buckets_available(struct journal *j,
 	return available;
 }
 
-static void journal_set_remaining(struct journal *j, unsigned u64s_remaining)
+void bch2_journal_set_watermark(struct journal *j)
 {
-	union journal_preres_state old, new;
-	u64 v = atomic64_read(&j->prereserved.counter);
-
-	do {
-		old.v = new.v = v;
-		new.remaining = u64s_remaining;
-	} while ((v = atomic64_cmpxchg(&j->prereserved.counter,
-				       old.v, new.v)) != old.v);
+	struct bch_fs *c = container_of(j, struct bch_fs, journal);
+	bool low_on_space = j->space[journal_space_clean].total * 4 <=
+		j->space[journal_space_total].total;
+	bool low_on_pin = fifo_free(&j->pin) < j->pin.size / 4;
+	bool low_on_wb = bch2_btree_write_buffer_must_wait(c);
+	unsigned watermark = low_on_space || low_on_pin || low_on_wb
+		? BCH_WATERMARK_reclaim
+		: BCH_WATERMARK_stripe;
+
+	if (track_event_change(&c->times[BCH_TIME_blocked_journal_low_on_space],
+			       &j->low_on_space_start, low_on_space) ||
+	    track_event_change(&c->times[BCH_TIME_blocked_journal_low_on_pin],
+			       &j->low_on_pin_start, low_on_pin) ||
+	    track_event_change(&c->times[BCH_TIME_blocked_write_buffer_full],
+			       &j->write_buffer_full_start, low_on_wb))
+		trace_and_count(c, journal_full, c);
+
+	swap(watermark, j->watermark);
+	if (watermark > j->watermark)
+		journal_wake(j);
 }
 
 static struct journal_space
@@ -123,15 +136,13 @@ static struct journal_space __journal_space_available(struct journal *j, unsigne
 			    enum journal_space_from from)
 {
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
-	struct bch_dev *ca;
-	unsigned i, pos, nr_devs = 0;
+	unsigned pos, nr_devs = 0;
 	struct journal_space space, dev_space[BCH_SB_MEMBERS_MAX];
 
 	BUG_ON(nr_devs_want > ARRAY_SIZE(dev_space));
 
 	rcu_read_lock();
-	for_each_member_device_rcu(ca, c, i,
-				   &c->rw_devs[BCH_DATA_journal]) {
+	for_each_member_device_rcu(c, ca, &c->rw_devs[BCH_DATA_journal]) {
 		if (!ca->journal.nr)
 			continue;
 
@@ -160,20 +171,17 @@ static struct journal_space __journal_space_available(struct journal *j, unsigne
 void bch2_journal_space_available(struct journal *j)
 {
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
-	struct bch_dev *ca;
 	unsigned clean, clean_ondisk, total;
-	s64 u64s_remaining = 0;
 	unsigned max_entry_size	 = min(j->buf[0].buf_size >> 9,
 				       j->buf[1].buf_size >> 9);
-	unsigned i, nr_online = 0, nr_devs_want;
+	unsigned nr_online = 0, nr_devs_want;
 	bool can_discard = false;
 	int ret = 0;
 
 	lockdep_assert_held(&j->lock);
 
 	rcu_read_lock();
-	for_each_member_device_rcu(ca, c, i,
-				   &c->rw_devs[BCH_DATA_journal]) {
+	for_each_member_device_rcu(c, ca, &c->rw_devs[BCH_DATA_journal]) {
 		struct journal_device *ja = &ca->journal;
 
 		if (!ja->nr)
@@ -204,7 +212,7 @@ void bch2_journal_space_available(struct journal *j)
 
 	nr_devs_want = min_t(unsigned, nr_online, c->opts.metadata_replicas);
 
-	for (i = 0; i < journal_space_nr; i++)
+	for (unsigned i = 0; i < journal_space_nr; i++)
 		j->space[i] = __journal_space_available(j, nr_devs_want, i);
 
 	clean_ondisk	= j->space[journal_space_clean_ondisk].total;
@@ -222,16 +230,10 @@ void bch2_journal_space_available(struct journal *j)
 	else
 		clear_bit(JOURNAL_MAY_SKIP_FLUSH, &j->flags);
 
-	u64s_remaining  = (u64) clean << 6;
-	u64s_remaining -= (u64) total << 3;
-	u64s_remaining = max(0LL, u64s_remaining);
-	u64s_remaining /= 4;
-	u64s_remaining = min_t(u64, u64s_remaining, U32_MAX);
+	bch2_journal_set_watermark(j);
 out:
 	j->cur_entry_sectors	= !ret ? j->space[journal_space_discarded].next_entry : 0;
 	j->cur_entry_error	= ret;
-	journal_set_remaining(j, u64s_remaining);
-	journal_set_watermark(j);
 
 	if (!ret)
 		journal_wake(j);
@@ -257,12 +259,10 @@ static bool should_discard_bucket(struct journal *j, struct journal_device *ja)
 void bch2_journal_do_discards(struct journal *j)
 {
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
-	struct bch_dev *ca;
-	unsigned iter;
 
 	mutex_lock(&j->discard_lock);
 
-	for_each_rw_member(ca, c, iter) {
+	for_each_rw_member(c, ca) {
 		struct journal_device *ja = &ca->journal;
 
 		while (should_discard_bucket(j, ja)) {
@@ -301,6 +301,7 @@ void bch2_journal_reclaim_fast(struct journal *j)
 	 * all btree nodes got written out
 	 */
 	while (!fifo_empty(&j->pin) &&
+	       j->pin.front <= j->seq_ondisk &&
 	       !atomic_read(&fifo_peek_front(&j->pin).count)) {
 		j->pin.front++;
 		popped = true;
@@ -369,15 +370,36 @@ static enum journal_pin_type journal_pin_type(journal_pin_flush_fn fn)
 		return JOURNAL_PIN_other;
 }
 
-void bch2_journal_pin_set(struct journal *j, u64 seq,
+static inline void bch2_journal_pin_set_locked(struct journal *j, u64 seq,
 			  struct journal_entry_pin *pin,
-			  journal_pin_flush_fn flush_fn)
+			  journal_pin_flush_fn flush_fn,
+			  enum journal_pin_type type)
+{
+	struct journal_entry_pin_list *pin_list = journal_seq_pin(j, seq);
+
+	/*
+	 * flush_fn is how we identify journal pins in debugfs, so must always
+	 * exist, even if it doesn't do anything:
+	 */
+	BUG_ON(!flush_fn);
+
+	atomic_inc(&pin_list->count);
+	pin->seq	= seq;
+	pin->flush	= flush_fn;
+	list_add(&pin->list, &pin_list->list[type]);
+}
+
+void bch2_journal_pin_copy(struct journal *j,
+			   struct journal_entry_pin *dst,
+			   struct journal_entry_pin *src,
+			   journal_pin_flush_fn flush_fn)
 {
-	struct journal_entry_pin_list *pin_list;
 	bool reclaim;
 
 	spin_lock(&j->lock);
 
+	u64 seq = READ_ONCE(src->seq);
+
 	if (seq < journal_last_seq(j)) {
 		/*
 		 * bch2_journal_pin_copy() raced with bch2_journal_pin_drop() on
@@ -389,18 +411,34 @@ void bch2_journal_pin_set(struct journal *j, u64 seq,
 		return;
 	}
 
-	pin_list = journal_seq_pin(j, seq);
+	reclaim = __journal_pin_drop(j, dst);
 
-	reclaim = __journal_pin_drop(j, pin);
+	bch2_journal_pin_set_locked(j, seq, dst, flush_fn, journal_pin_type(flush_fn));
 
-	atomic_inc(&pin_list->count);
-	pin->seq	= seq;
-	pin->flush	= flush_fn;
+	if (reclaim)
+		bch2_journal_reclaim_fast(j);
+	spin_unlock(&j->lock);
 
-	if (flush_fn)
-		list_add(&pin->list, &pin_list->list[journal_pin_type(flush_fn)]);
-	else
-		list_add(&pin->list, &pin_list->flushed);
+	/*
+	 * If the journal is currently full,  we might want to call flush_fn
+	 * immediately:
+	 */
+	journal_wake(j);
+}
+
+void bch2_journal_pin_set(struct journal *j, u64 seq,
+			  struct journal_entry_pin *pin,
+			  journal_pin_flush_fn flush_fn)
+{
+	bool reclaim;
+
+	spin_lock(&j->lock);
+
+	BUG_ON(seq < journal_last_seq(j));
+
+	reclaim = __journal_pin_drop(j, pin);
+
+	bch2_journal_pin_set_locked(j, seq, pin, flush_fn, journal_pin_type(flush_fn));
 
 	if (reclaim)
 		bch2_journal_reclaim_fast(j);
@@ -539,13 +577,11 @@ static size_t journal_flush_pins(struct journal *j,
 static u64 journal_seq_to_flush(struct journal *j)
 {
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
-	struct bch_dev *ca;
 	u64 seq_to_flush = 0;
-	unsigned iter;
 
 	spin_lock(&j->lock);
 
-	for_each_rw_member(ca, c, iter) {
+	for_each_rw_member(c, ca) {
 		struct journal_device *ja = &ca->journal;
 		unsigned nr_buckets, bucket_to_flush;
 
@@ -555,11 +591,6 @@ static u64 journal_seq_to_flush(struct journal *j)
 		/* Try to keep the journal at most half full: */
 		nr_buckets = ja->nr / 2;
 
-		/* And include pre-reservations: */
-		nr_buckets += DIV_ROUND_UP(j->prereserved.reserved,
-					   (ca->mi.bucket_size << 6) -
-					   journal_entry_overhead(j));
-
 		nr_buckets = min(nr_buckets, ja->nr);
 
 		bucket_to_flush = (ja->cur_idx + nr_buckets) % ja->nr;
@@ -638,10 +669,7 @@ static int __bch2_journal_reclaim(struct journal *j, bool direct, bool kicked)
 			       msecs_to_jiffies(c->opts.journal_reclaim_delay)))
 			min_nr = 1;
 
-		if (j->prereserved.reserved * 4 > j->prereserved.remaining)
-			min_nr = 1;
-
-		if (fifo_free(&j->pin) <= 32)
+		if (j->watermark != BCH_WATERMARK_stripe)
 			min_nr = 1;
 
 		if (atomic_read(&c->btree_cache.dirty) * 2 > c->btree_cache.used)
@@ -652,8 +680,6 @@ static int __bch2_journal_reclaim(struct journal *j, bool direct, bool kicked)
 		trace_and_count(c, journal_reclaim_start, c,
 				direct, kicked,
 				min_nr, min_key_cache,
-				j->prereserved.reserved,
-				j->prereserved.remaining,
 				atomic_read(&c->btree_cache.dirty),
 				c->btree_cache.used,
 				atomic_long_read(&c->btree_key_cache.nr_dirty),
@@ -759,10 +785,9 @@ int bch2_journal_reclaim_start(struct journal *j)
 	p = kthread_create(bch2_journal_reclaim_thread, j,
 			   "bch-reclaim/%s", c->name);
 	ret = PTR_ERR_OR_ZERO(p);
-	if (ret) {
-		bch_err_msg(c, ret, "creating journal reclaim thread");
+	bch_err_msg(c, ret, "creating journal reclaim thread");
+	if (ret)
 		return ret;
-	}
 
 	get_task_struct(p);
 	j->reclaim_thread = p;
@@ -788,6 +813,9 @@ static int journal_flush_done(struct journal *j, u64 seq_to_flush,
 			       (1U << JOURNAL_PIN_btree), 0, 0, 0))
 		*did_work = true;
 
+	if (seq_to_flush > journal_cur_seq(j))
+		bch2_journal_entry_close(j);
+
 	spin_lock(&j->lock);
 	/*
 	 * If journal replay hasn't completed, the unreplayed journal entries
@@ -805,6 +833,7 @@ static int journal_flush_done(struct journal *j, u64 seq_to_flush,
 
 bool bch2_journal_flush_pins(struct journal *j, u64 seq_to_flush)
 {
+	/* time_stats this */
 	bool did_work = false;
 
 	if (!test_bit(JOURNAL_STARTED, &j->flags))
diff --git a/fs/bcachefs/journal_reclaim.h b/fs/bcachefs/journal_reclaim.h
index 494d1a6eddb0..ec84c3345281 100644
--- a/fs/bcachefs/journal_reclaim.h
+++ b/fs/bcachefs/journal_reclaim.h
@@ -16,6 +16,7 @@ static inline void journal_reclaim_kick(struct journal *j)
 unsigned bch2_journal_dev_buckets_available(struct journal *,
 					    struct journal_device *,
 					    enum journal_space_from);
+void bch2_journal_set_watermark(struct journal *);
 void bch2_journal_space_available(struct journal *);
 
 static inline bool journal_pin_active(struct journal_entry_pin *pin)
@@ -47,17 +48,10 @@ static inline void bch2_journal_pin_add(struct journal *j, u64 seq,
 		bch2_journal_pin_set(j, seq, pin, flush_fn);
 }
 
-static inline void bch2_journal_pin_copy(struct journal *j,
-					 struct journal_entry_pin *dst,
-					 struct journal_entry_pin *src,
-					 journal_pin_flush_fn flush_fn)
-{
-	/* Guard against racing with journal_pin_drop(src): */
-	u64 seq = READ_ONCE(src->seq);
-
-	if (seq)
-		bch2_journal_pin_add(j, seq, dst, flush_fn);
-}
+void bch2_journal_pin_copy(struct journal *,
+			   struct journal_entry_pin *,
+			   struct journal_entry_pin *,
+			   journal_pin_flush_fn);
 
 static inline void bch2_journal_pin_update(struct journal *j, u64 seq,
 					   struct journal_entry_pin *pin,
diff --git a/fs/bcachefs/journal_seq_blacklist.c b/fs/bcachefs/journal_seq_blacklist.c
index f9d9aa95bf3a..0200e299cfbb 100644
--- a/fs/bcachefs/journal_seq_blacklist.c
+++ b/fs/bcachefs/journal_seq_blacklist.c
@@ -267,7 +267,7 @@ retry:
 
 		while (!(ret = PTR_ERR_OR_ZERO(b)) &&
 		       b &&
-		       !test_bit(BCH_FS_STOPPING, &c->flags))
+		       !test_bit(BCH_FS_stopping, &c->flags))
 			b = bch2_btree_iter_next_node(&iter);
 
 		if (bch2_err_matches(ret, BCH_ERR_transaction_restart))
diff --git a/fs/bcachefs/journal_types.h b/fs/bcachefs/journal_types.h
index 42504e16acb6..38817c7a0851 100644
--- a/fs/bcachefs/journal_types.h
+++ b/fs/bcachefs/journal_types.h
@@ -36,6 +36,7 @@ struct journal_buf {
 	bool			noflush;	/* write has already been kicked off, and was noflush */
 	bool			must_flush;	/* something wants a flush */
 	bool			separate_flush;
+	bool			need_flush_to_write_buffer;
 };
 
 /*
@@ -76,14 +77,6 @@ struct journal_res {
 	u64			seq;
 };
 
-/*
- * For reserving space in the journal prior to getting a reservation on a
- * particular journal entry:
- */
-struct journal_preres {
-	unsigned		u64s;
-};
-
 union journal_res_state {
 	struct {
 		atomic64_t	counter;
@@ -104,22 +97,6 @@ union journal_res_state {
 	};
 };
 
-union journal_preres_state {
-	struct {
-		atomic64_t	counter;
-	};
-
-	struct {
-		u64		v;
-	};
-
-	struct {
-		u64		waiting:1,
-				reserved:31,
-				remaining:32;
-	};
-};
-
 /* bytes: */
 #define JOURNAL_ENTRY_SIZE_MIN		(64U << 10) /* 64k */
 #define JOURNAL_ENTRY_SIZE_MAX		(4U  << 20) /* 4M */
@@ -180,8 +157,6 @@ struct journal {
 	union journal_res_state reservations;
 	enum bch_watermark	watermark;
 
-	union journal_preres_state prereserved;
-
 	} __aligned(SMP_CACHE_BYTES);
 
 	unsigned long		flags;
@@ -208,6 +183,12 @@ struct journal {
 	darray_u64		early_journal_entries;
 
 	/*
+	 * Protects journal_buf->data, when accessing without a jorunal
+	 * reservation: for synchronization between the btree write buffer code
+	 * and the journal write path:
+	 */
+	struct mutex		buf_lock;
+	/*
 	 * Two journal entries -- one is currently open for new entries, the
 	 * other is possibly being written out.
 	 */
@@ -221,7 +202,6 @@ struct journal {
 	/* Used when waiting because the journal was full */
 	wait_queue_head_t	wait;
 	struct closure_waitlist	async_wait;
-	struct closure_waitlist	preres_wait;
 
 	struct closure		io;
 	struct delayed_work	write_work;
@@ -288,15 +268,19 @@ struct journal {
 
 	unsigned long		last_flush_write;
 
-	u64			res_get_blocked_start;
 	u64			write_start_time;
 
 	u64			nr_flush_writes;
 	u64			nr_noflush_writes;
+	u64			entry_bytes_written;
+
+	u64			low_on_space_start;
+	u64			low_on_pin_start;
+	u64			max_in_flight_start;
+	u64			write_buffer_full_start;
 
 	struct bch2_time_stats	*flush_write_time;
 	struct bch2_time_stats	*noflush_write_time;
-	struct bch2_time_stats	*blocked_time;
 	struct bch2_time_stats	*flush_seq_time;
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/fs/bcachefs/keylist.c b/fs/bcachefs/keylist.c
index 5699cd4873c8..1b828bddd11b 100644
--- a/fs/bcachefs/keylist.c
+++ b/fs/bcachefs/keylist.c
@@ -43,8 +43,6 @@ void bch2_keylist_pop_front(struct keylist *l)
 #ifdef CONFIG_BCACHEFS_DEBUG
 void bch2_verify_keylist_sorted(struct keylist *l)
 {
-	struct bkey_i *k;
-
 	for_each_keylist_key(l, k)
 		BUG_ON(bkey_next(k) != l->top &&
 		       bpos_ge(k->k.p, bkey_next(k)->k.p));
diff --git a/fs/bcachefs/keylist.h b/fs/bcachefs/keylist.h
index fe759c7031e0..e687e0e9aede 100644
--- a/fs/bcachefs/keylist.h
+++ b/fs/bcachefs/keylist.h
@@ -50,18 +50,16 @@ static inline struct bkey_i *bch2_keylist_front(struct keylist *l)
 }
 
 #define for_each_keylist_key(_keylist, _k)			\
-	for (_k = (_keylist)->keys;				\
+	for (struct bkey_i *_k = (_keylist)->keys;		\
 	     _k != (_keylist)->top;				\
 	     _k = bkey_next(_k))
 
 static inline u64 keylist_sectors(struct keylist *keys)
 {
-	struct bkey_i *k;
 	u64 ret = 0;
 
 	for_each_keylist_key(keys, k)
 		ret += k->k.size;
-
 	return ret;
 }
 
diff --git a/fs/bcachefs/logged_ops.c b/fs/bcachefs/logged_ops.c
index 8640f7dee0de..ad598105c587 100644
--- a/fs/bcachefs/logged_ops.c
+++ b/fs/bcachefs/logged_ops.c
@@ -54,16 +54,12 @@ static int resume_logged_op(struct btree_trans *trans, struct btree_iter *iter,
 
 int bch2_resume_logged_ops(struct bch_fs *c)
 {
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	int ret;
-
-	ret = bch2_trans_run(c,
-		for_each_btree_key2(trans, iter,
-				BTREE_ID_logged_ops, POS_MIN, BTREE_ITER_PREFETCH, k,
+	int ret = bch2_trans_run(c,
+		for_each_btree_key(trans, iter,
+				   BTREE_ID_logged_ops, POS_MIN,
+				   BTREE_ITER_PREFETCH, k,
 			resume_logged_op(trans, &iter, k)));
-	if (ret)
-		bch_err_fn(c, ret);
+	bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -85,13 +81,13 @@ static int __bch2_logged_op_start(struct btree_trans *trans, struct bkey_i *k)
 
 int bch2_logged_op_start(struct btree_trans *trans, struct bkey_i *k)
 {
-	return commit_do(trans, NULL, NULL, BTREE_INSERT_NOFAIL,
+	return commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 			 __bch2_logged_op_start(trans, k));
 }
 
 void bch2_logged_op_finish(struct btree_trans *trans, struct bkey_i *k)
 {
-	int ret = commit_do(trans, NULL, NULL, BTREE_INSERT_NOFAIL,
+	int ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 			    bch2_btree_delete(trans, BTREE_ID_logged_ops, k->k.p, 0));
 	/*
 	 * This needs to be a fatal error because we've left an unfinished
diff --git a/fs/bcachefs/lru.c b/fs/bcachefs/lru.c
index a5cc0ed195d6..7a4ca5a28b3e 100644
--- a/fs/bcachefs/lru.c
+++ b/fs/bcachefs/lru.c
@@ -147,18 +147,13 @@ fsck_err:
 
 int bch2_check_lrus(struct bch_fs *c)
 {
-	struct btree_iter iter;
-	struct bkey_s_c k;
 	struct bpos last_flushed_pos = POS_MIN;
-	int ret = 0;
-
-	ret = bch2_trans_run(c,
+	int ret = bch2_trans_run(c,
 		for_each_btree_key_commit(trans, iter,
 				BTREE_ID_lru, POS_MIN, BTREE_ITER_PREFETCH, k,
-				NULL, NULL, BTREE_INSERT_NOFAIL|BTREE_INSERT_LAZY_RW,
+				NULL, NULL, BCH_TRANS_COMMIT_no_enospc|BCH_TRANS_COMMIT_lazy_rw,
 			bch2_check_lru_key(trans, &iter, k, &last_flushed_pos)));
-	if (ret)
-		bch_err_fn(c, ret);
+	bch_err_fn(c, ret);
 	return ret;
 
 }
diff --git a/fs/bcachefs/mean_and_variance.c b/fs/bcachefs/mean_and_variance.c
index 1f0801e2e565..bf0ef668fd38 100644
--- a/fs/bcachefs/mean_and_variance.c
+++ b/fs/bcachefs/mean_and_variance.c
@@ -62,6 +62,7 @@ EXPORT_SYMBOL_GPL(u128_div);
 
 /**
  * mean_and_variance_get_mean() - get mean from @s
+ * @s: mean and variance number of samples and their sums
  */
 s64 mean_and_variance_get_mean(struct mean_and_variance s)
 {
@@ -71,6 +72,7 @@ EXPORT_SYMBOL_GPL(mean_and_variance_get_mean);
 
 /**
  * mean_and_variance_get_variance() -  get variance from @s1
+ * @s1: mean and variance number of samples and sums
  *
  * see linked pdf equation 12.
  */
@@ -89,6 +91,7 @@ EXPORT_SYMBOL_GPL(mean_and_variance_get_variance);
 
 /**
  * mean_and_variance_get_stddev() - get standard deviation from @s
+ * @s: mean and variance number of samples and their sums
  */
 u32 mean_and_variance_get_stddev(struct mean_and_variance s)
 {
@@ -98,8 +101,8 @@ EXPORT_SYMBOL_GPL(mean_and_variance_get_stddev);
 
 /**
  * mean_and_variance_weighted_update() - exponentially weighted variant of mean_and_variance_update()
- * @s1: ..
- * @s2: ..
+ * @s: mean and variance number of samples and their sums
+ * @x: new value to include in the &mean_and_variance_weighted
  *
  * see linked pdf: function derived from equations 140-143 where alpha = 2^w.
  * values are stored bitshifted for performance and added precision.
@@ -129,6 +132,7 @@ EXPORT_SYMBOL_GPL(mean_and_variance_weighted_update);
 
 /**
  * mean_and_variance_weighted_get_mean() - get mean from @s
+ * @s: mean and variance number of samples and their sums
  */
 s64 mean_and_variance_weighted_get_mean(struct mean_and_variance_weighted s)
 {
@@ -138,6 +142,7 @@ EXPORT_SYMBOL_GPL(mean_and_variance_weighted_get_mean);
 
 /**
  * mean_and_variance_weighted_get_variance() -- get variance from @s
+ * @s: mean and variance number of samples and their sums
  */
 u64 mean_and_variance_weighted_get_variance(struct mean_and_variance_weighted s)
 {
@@ -148,6 +153,7 @@ EXPORT_SYMBOL_GPL(mean_and_variance_weighted_get_variance);
 
 /**
  * mean_and_variance_weighted_get_stddev() - get standard deviation from @s
+ * @s: mean and variance number of samples and their sums
  */
 u32 mean_and_variance_weighted_get_stddev(struct mean_and_variance_weighted s)
 {
diff --git a/fs/bcachefs/mean_and_variance.h b/fs/bcachefs/mean_and_variance.h
index 647505010b39..b2be565bb8f2 100644
--- a/fs/bcachefs/mean_and_variance.h
+++ b/fs/bcachefs/mean_and_variance.h
@@ -12,9 +12,12 @@
 /*
  * u128_u: u128 user mode, because not all architectures support a real int128
  * type
+ *
+ * We don't use this version in userspace, because in userspace we link with
+ * Rust and rustc has issues with u128.
  */
 
-#ifdef __SIZEOF_INT128__
+#if defined(__SIZEOF_INT128__) && defined(__KERNEL__)
 
 typedef struct {
 	unsigned __int128 v;
diff --git a/fs/bcachefs/migrate.c b/fs/bcachefs/migrate.c
index e3a51f6d6c9b..5623cee3ef86 100644
--- a/fs/bcachefs/migrate.c
+++ b/fs/bcachefs/migrate.c
@@ -79,8 +79,6 @@ static int bch2_dev_usrdata_drop_key(struct btree_trans *trans,
 static int bch2_dev_usrdata_drop(struct bch_fs *c, unsigned dev_idx, int flags)
 {
 	struct btree_trans *trans = bch2_trans_get(c);
-	struct btree_iter iter;
-	struct bkey_s_c k;
 	enum btree_id id;
 	int ret = 0;
 
@@ -90,7 +88,7 @@ static int bch2_dev_usrdata_drop(struct bch_fs *c, unsigned dev_idx, int flags)
 
 		ret = for_each_btree_key_commit(trans, iter, id, POS_MIN,
 				BTREE_ITER_PREFETCH|BTREE_ITER_ALL_SNAPSHOTS, k,
-				NULL, NULL, BTREE_INSERT_NOFAIL,
+				NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 			bch2_dev_usrdata_drop_key(trans, &iter, k, dev_idx, flags));
 		if (ret)
 			break;
@@ -145,10 +143,9 @@ retry:
 				continue;
 			}
 
-			if (ret) {
-				bch_err_msg(c, ret, "updating btree node key");
+			bch_err_msg(c, ret, "updating btree node key");
+			if (ret)
 				break;
-			}
 next:
 			bch2_btree_iter_next_node(&iter);
 		}
diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c
index ab749bf2fcbc..7a33319dcd16 100644
--- a/fs/bcachefs/move.c
+++ b/fs/bcachefs/move.c
@@ -27,6 +27,13 @@
 #include <linux/ioprio.h>
 #include <linux/kthread.h>
 
+const char * const bch2_data_ops_strs[] = {
+#define x(t, n, ...) [n] = #t,
+	BCH_DATA_OPS()
+#undef x
+	NULL
+};
+
 static void trace_move_extent2(struct bch_fs *c, struct bkey_s_c k)
 {
 	if (trace_move_extent_enabled()) {
@@ -49,17 +56,6 @@ static void trace_move_extent_read2(struct bch_fs *c, struct bkey_s_c k)
 	}
 }
 
-static void trace_move_extent_alloc_mem_fail2(struct bch_fs *c, struct bkey_s_c k)
-{
-	if (trace_move_extent_alloc_mem_fail_enabled()) {
-		struct printbuf buf = PRINTBUF;
-
-		bch2_bkey_val_to_text(&buf, c, k);
-		trace_move_extent_alloc_mem_fail(c, buf.buf);
-		printbuf_exit(&buf);
-	}
-}
-
 struct moving_io {
 	struct list_head		read_list;
 	struct list_head		io_list;
@@ -74,7 +70,7 @@ struct moving_io {
 
 	struct data_update		write;
 	/* Must be last since it is variable size */
-	struct bio_vec			bi_inline_vecs[0];
+	struct bio_vec			bi_inline_vecs[];
 };
 
 static void move_free(struct moving_io *io)
@@ -163,12 +159,18 @@ void bch2_move_ctxt_wait_for_io(struct moving_context *ctxt)
 		atomic_read(&ctxt->write_sectors) != sectors_pending);
 }
 
+void bch2_moving_ctxt_flush_all(struct moving_context *ctxt)
+{
+	move_ctxt_wait_event(ctxt, list_empty(&ctxt->reads));
+	bch2_trans_unlock_long(ctxt->trans);
+	closure_sync(&ctxt->cl);
+}
+
 void bch2_moving_ctxt_exit(struct moving_context *ctxt)
 {
 	struct bch_fs *c = ctxt->trans->c;
 
-	move_ctxt_wait_event(ctxt, list_empty(&ctxt->reads));
-	closure_sync(&ctxt->cl);
+	bch2_moving_ctxt_flush_all(ctxt);
 
 	EBUG_ON(atomic_read(&ctxt->write_sectors));
 	EBUG_ON(atomic_read(&ctxt->write_ios));
@@ -216,56 +218,13 @@ void bch2_move_stats_exit(struct bch_move_stats *stats, struct bch_fs *c)
 	trace_move_data(c, stats);
 }
 
-void bch2_move_stats_init(struct bch_move_stats *stats, char *name)
+void bch2_move_stats_init(struct bch_move_stats *stats, const char *name)
 {
 	memset(stats, 0, sizeof(*stats));
 	stats->data_type = BCH_DATA_user;
 	scnprintf(stats->name, sizeof(stats->name), "%s", name);
 }
 
-static int bch2_extent_drop_ptrs(struct btree_trans *trans,
-				 struct btree_iter *iter,
-				 struct bkey_s_c k,
-				 struct data_update_opts data_opts)
-{
-	struct bch_fs *c = trans->c;
-	struct bkey_i *n;
-	int ret;
-
-	n = bch2_bkey_make_mut_noupdate(trans, k);
-	ret = PTR_ERR_OR_ZERO(n);
-	if (ret)
-		return ret;
-
-	while (data_opts.kill_ptrs) {
-		unsigned i = 0, drop = __fls(data_opts.kill_ptrs);
-		struct bch_extent_ptr *ptr;
-
-		bch2_bkey_drop_ptrs(bkey_i_to_s(n), ptr, i++ == drop);
-		data_opts.kill_ptrs ^= 1U << drop;
-	}
-
-	/*
-	 * If the new extent no longer has any pointers, bch2_extent_normalize()
-	 * will do the appropriate thing with it (turning it into a
-	 * KEY_TYPE_error key, or just a discard if it was a cached extent)
-	 */
-	bch2_extent_normalize(c, bkey_i_to_s(n));
-
-	/*
-	 * Since we're not inserting through an extent iterator
-	 * (BTREE_ITER_ALL_SNAPSHOTS iterators aren't extent iterators),
-	 * we aren't using the extent overwrite path to delete, we're
-	 * just using the normal key deletion path:
-	 */
-	if (bkey_deleted(&n->k))
-		n->k.size = 0;
-
-	return bch2_trans_relock(trans) ?:
-		bch2_trans_update(trans, iter, n, BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE) ?:
-		bch2_trans_commit(trans, NULL, NULL, BTREE_INSERT_NOFAIL);
-}
-
 int bch2_move_extent(struct moving_context *ctxt,
 		     struct move_bucket_in_flight *bucket_in_flight,
 		     struct btree_iter *iter,
@@ -335,19 +294,11 @@ int bch2_move_extent(struct moving_context *ctxt,
 	io->rbio.bio.bi_iter.bi_sector	= bkey_start_offset(k.k);
 	io->rbio.bio.bi_end_io		= move_read_endio;
 
-	ret = bch2_data_update_init(trans, ctxt, &io->write, ctxt->wp,
+	ret = bch2_data_update_init(trans, iter, ctxt, &io->write, ctxt->wp,
 				    io_opts, data_opts, iter->btree_id, k);
-	if (ret && ret != -BCH_ERR_unwritten_extent_update)
+	if (ret)
 		goto err_free_pages;
 
-	if (ret == -BCH_ERR_unwritten_extent_update) {
-		bch2_update_unwritten_extent(trans, &io->write);
-		move_free(io);
-		return 0;
-	}
-
-	BUG_ON(ret);
-
 	io->write.op.end_io = move_write_done;
 
 	if (ctxt->rate)
@@ -391,8 +342,24 @@ err_free_pages:
 err_free:
 	kfree(io);
 err:
-	this_cpu_inc(c->counters[BCH_COUNTER_move_extent_alloc_mem_fail]);
-	trace_move_extent_alloc_mem_fail2(c, k);
+	if (ret == -BCH_ERR_data_update_done)
+		return 0;
+
+	if (bch2_err_matches(ret, EROFS) ||
+	    bch2_err_matches(ret, BCH_ERR_transaction_restart))
+		return ret;
+
+	count_event(c, move_extent_start_fail);
+
+	if (trace_move_extent_start_fail_enabled()) {
+		struct printbuf buf = PRINTBUF;
+
+		bch2_bkey_val_to_text(&buf, c, k);
+		prt_str(&buf, ": ");
+		prt_str(&buf, bch2_err_str(ret));
+		trace_move_extent_start_fail(c, buf.buf);
+		printbuf_exit(&buf);
+	}
 	return ret;
 }
 
@@ -405,13 +372,10 @@ struct bch_io_opts *bch2_move_get_io_opts(struct btree_trans *trans,
 	int ret = 0;
 
 	if (io_opts->cur_inum != extent_k.k->p.inode) {
-		struct btree_iter iter;
-		struct bkey_s_c k;
-
 		io_opts->d.nr = 0;
 
-		for_each_btree_key(trans, iter, BTREE_ID_inodes, POS(0, extent_k.k->p.inode),
-				   BTREE_ITER_ALL_SNAPSHOTS, k, ret) {
+		ret = for_each_btree_key(trans, iter, BTREE_ID_inodes, POS(0, extent_k.k->p.inode),
+					 BTREE_ITER_ALL_SNAPSHOTS, k, ({
 			if (k.k->p.offset != extent_k.k->p.inode)
 				break;
 
@@ -424,11 +388,8 @@ struct bch_io_opts *bch2_move_get_io_opts(struct btree_trans *trans,
 			struct snapshot_io_opts_entry e = { .snapshot = k.k->p.snapshot };
 			bch2_inode_opts_get(&e.io_opts, trans->c, &inode);
 
-			ret = darray_push(&io_opts->d, e);
-			if (ret)
-				break;
-		}
-		bch2_trans_iter_exit(trans, &iter);
+			darray_push(&io_opts->d, e);
+		}));
 		io_opts->cur_inum = extent_k.k->p.inode;
 	}
 
@@ -436,12 +397,10 @@ struct bch_io_opts *bch2_move_get_io_opts(struct btree_trans *trans,
 	if (ret)
 		return ERR_PTR(ret);
 
-	if (extent_k.k->p.snapshot) {
-		struct snapshot_io_opts_entry *i;
+	if (extent_k.k->p.snapshot)
 		darray_for_each(io_opts->d, i)
 			if (bch2_snapshot_is_ancestor(c, extent_k.k->p.snapshot, i->snapshot))
 				return &i->io_opts;
-	}
 
 	return &io_opts->fs_io_opts;
 }
@@ -482,37 +441,30 @@ int bch2_move_get_io_opts_one(struct btree_trans *trans,
 int bch2_move_ratelimit(struct moving_context *ctxt)
 {
 	struct bch_fs *c = ctxt->trans->c;
+	bool is_kthread = current->flags & PF_KTHREAD;
 	u64 delay;
 
-	if (ctxt->wait_on_copygc && !c->copygc_running) {
-		bch2_trans_unlock_long(ctxt->trans);
+	if (ctxt->wait_on_copygc && c->copygc_running) {
+		bch2_moving_ctxt_flush_all(ctxt);
 		wait_event_killable(c->copygc_running_wq,
 				    !c->copygc_running ||
-				    kthread_should_stop());
+				    (is_kthread && kthread_should_stop()));
 	}
 
 	do {
 		delay = ctxt->rate ? bch2_ratelimit_delay(ctxt->rate) : 0;
 
-
-		if (delay) {
-			if (delay > HZ / 10)
-				bch2_trans_unlock_long(ctxt->trans);
-			else
-				bch2_trans_unlock(ctxt->trans);
-			set_current_state(TASK_INTERRUPTIBLE);
-		}
-
-		if ((current->flags & PF_KTHREAD) && kthread_should_stop()) {
-			__set_current_state(TASK_RUNNING);
+		if (is_kthread && kthread_should_stop())
 			return 1;
-		}
 
 		if (delay)
-			schedule_timeout(delay);
+			move_ctxt_wait_event_timeout(ctxt,
+					freezing(current) ||
+					(is_kthread && kthread_should_stop()),
+					delay);
 
 		if (unlikely(freezing(current))) {
-			move_ctxt_wait_event(ctxt, list_empty(&ctxt->reads));
+			bch2_moving_ctxt_flush_all(ctxt);
 			try_to_freeze();
 		}
 	} while (delay);
@@ -676,13 +628,14 @@ int bch2_move_data(struct bch_fs *c,
 	return ret;
 }
 
-int __bch2_evacuate_bucket(struct moving_context *ctxt,
+int bch2_evacuate_bucket(struct moving_context *ctxt,
 			   struct move_bucket_in_flight *bucket_in_flight,
 			   struct bpos bucket, int gen,
 			   struct data_update_opts _data_opts)
 {
 	struct btree_trans *trans = ctxt->trans;
 	struct bch_fs *c = trans->c;
+	bool is_kthread = current->flags & PF_KTHREAD;
 	struct bch_io_opts io_opts = bch2_opts_to_inode_opts(c->opts);
 	struct btree_iter iter;
 	struct bkey_buf sk;
@@ -711,23 +664,24 @@ int __bch2_evacuate_bucket(struct moving_context *ctxt,
 			bkey_err(k = bch2_btree_iter_peek_slot(&iter)));
 	bch2_trans_iter_exit(trans, &iter);
 
-	if (ret) {
-		bch_err_msg(c, ret, "looking up alloc key");
+	bch_err_msg(c, ret, "looking up alloc key");
+	if (ret)
 		goto err;
-	}
 
 	a = bch2_alloc_to_v4(k, &a_convert);
-	dirty_sectors = a->dirty_sectors;
+	dirty_sectors = bch2_bucket_sectors_dirty(*a);
 	bucket_size = bch_dev_bkey_exists(c, bucket.inode)->mi.bucket_size;
 	fragmentation = a->fragmentation_lru;
 
-	ret = bch2_btree_write_buffer_flush(trans);
-	if (ret) {
-		bch_err_msg(c, ret, "flushing btree write buffer");
+	ret = bch2_btree_write_buffer_tryflush(trans);
+	bch_err_msg(c, ret, "flushing btree write buffer");
+	if (ret)
 		goto err;
-	}
 
 	while (!(ret = bch2_move_ratelimit(ctxt))) {
+		if (is_kthread && kthread_should_stop())
+			break;
+
 		bch2_trans_begin(trans);
 
 		ret = bch2_get_next_backpointer(trans, bucket, gen,
@@ -741,9 +695,6 @@ int __bch2_evacuate_bucket(struct moving_context *ctxt,
 			break;
 
 		if (!bp.level) {
-			const struct bch_extent_ptr *ptr;
-			unsigned i = 0;
-
 			k = bch2_backpointer_get_key(trans, &iter, bp_pos, bp, 0);
 			ret = bkey_err(k);
 			if (bch2_err_matches(ret, BCH_ERR_transaction_restart))
@@ -766,6 +717,7 @@ int __bch2_evacuate_bucket(struct moving_context *ctxt,
 			data_opts.target	= io_opts.background_target;
 			data_opts.rewrite_ptrs = 0;
 
+			unsigned i = 0;
 			bkey_for_each_ptr(bch2_bkey_ptrs_c(k), ptr) {
 				if (ptr->dev == bucket.inode) {
 					data_opts.rewrite_ptrs |= 1U << i;
@@ -833,31 +785,13 @@ err:
 	return ret;
 }
 
-int bch2_evacuate_bucket(struct bch_fs *c,
-			 struct bpos bucket, int gen,
-			 struct data_update_opts data_opts,
-			 struct bch_ratelimit *rate,
-			 struct bch_move_stats *stats,
-			 struct write_point_specifier wp,
-			 bool wait_on_copygc)
-{
-	struct moving_context ctxt;
-	int ret;
-
-	bch2_moving_ctxt_init(&ctxt, c, rate, stats, wp, wait_on_copygc);
-	ret = __bch2_evacuate_bucket(&ctxt, NULL, bucket, gen, data_opts);
-	bch2_moving_ctxt_exit(&ctxt);
-
-	return ret;
-}
-
 typedef bool (*move_btree_pred)(struct bch_fs *, void *,
 				struct btree *, struct bch_io_opts *,
 				struct data_update_opts *);
 
 static int bch2_move_btree(struct bch_fs *c,
-			   enum btree_id start_btree_id, struct bpos start_pos,
-			   enum btree_id end_btree_id,   struct bpos end_pos,
+			   struct bbpos start,
+			   struct bbpos end,
 			   move_btree_pred pred, void *arg,
 			   struct bch_move_stats *stats)
 {
@@ -867,7 +801,7 @@ static int bch2_move_btree(struct bch_fs *c,
 	struct btree_trans *trans;
 	struct btree_iter iter;
 	struct btree *b;
-	enum btree_id id;
+	enum btree_id btree;
 	struct data_update_opts data_opts;
 	int ret = 0;
 
@@ -878,15 +812,15 @@ static int bch2_move_btree(struct bch_fs *c,
 
 	stats->data_type = BCH_DATA_btree;
 
-	for (id = start_btree_id;
-	     id <= min_t(unsigned, end_btree_id, btree_id_nr_alive(c) - 1);
-	     id++) {
-		stats->pos = BBPOS(id, POS_MIN);
+	for (btree = start.btree;
+	     btree <= min_t(unsigned, end.btree, btree_id_nr_alive(c) - 1);
+	     btree ++) {
+		stats->pos = BBPOS(btree, POS_MIN);
 
-		if (!bch2_btree_id_root(c, id)->b)
+		if (!bch2_btree_id_root(c, btree)->b)
 			continue;
 
-		bch2_trans_node_iter_init(trans, &iter, id, POS_MIN, 0, 0,
+		bch2_trans_node_iter_init(trans, &iter, btree, POS_MIN, 0, 0,
 					  BTREE_ITER_PREFETCH);
 retry:
 		ret = 0;
@@ -896,8 +830,8 @@ retry:
 			if (kthread && kthread_should_stop())
 				break;
 
-			if ((cmp_int(id, end_btree_id) ?:
-			     bpos_cmp(b->key.k.p, end_pos)) > 0)
+			if ((cmp_int(btree, end.btree) ?:
+			     bpos_cmp(b->key.k.p, end.pos)) > 0)
 				break;
 
 			stats->pos = BBPOS(iter.btree_id, iter.pos);
@@ -954,7 +888,6 @@ static bool migrate_pred(struct bch_fs *c, void *arg,
 			 struct data_update_opts *data_opts)
 {
 	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
-	const struct bch_extent_ptr *ptr;
 	struct bch_ioctl_data *op = arg;
 	unsigned i = 0;
 
@@ -1034,8 +967,8 @@ int bch2_scan_old_btree_nodes(struct bch_fs *c, struct bch_move_stats *stats)
 	int ret;
 
 	ret = bch2_move_btree(c,
-			      0,		POS_MIN,
-			      BTREE_ID_NR,	SPOS_MAX,
+			      BBPOS_MIN,
+			      BBPOS_MAX,
 			      rewrite_old_nodes_pred, c, stats);
 	if (!ret) {
 		mutex_lock(&c->sb_lock);
@@ -1050,71 +983,101 @@ int bch2_scan_old_btree_nodes(struct bch_fs *c, struct bch_move_stats *stats)
 	return ret;
 }
 
+static bool drop_extra_replicas_pred(struct bch_fs *c, void *arg,
+			     struct bkey_s_c k,
+			     struct bch_io_opts *io_opts,
+			     struct data_update_opts *data_opts)
+{
+	unsigned durability = bch2_bkey_durability(c, k);
+	unsigned replicas = bkey_is_btree_ptr(k.k)
+		? c->opts.metadata_replicas
+		: io_opts->data_replicas;
+	const union bch_extent_entry *entry;
+	struct extent_ptr_decoded p;
+	unsigned i = 0;
+
+	bkey_for_each_ptr_decode(k.k, bch2_bkey_ptrs_c(k), p, entry) {
+		unsigned d = bch2_extent_ptr_durability(c, &p);
+
+		if (d && durability - d >= replicas) {
+			data_opts->kill_ptrs |= BIT(i);
+			durability -= d;
+		}
+
+		i++;
+	}
+
+	return data_opts->kill_ptrs != 0;
+}
+
+static bool drop_extra_replicas_btree_pred(struct bch_fs *c, void *arg,
+				   struct btree *b,
+				   struct bch_io_opts *io_opts,
+				   struct data_update_opts *data_opts)
+{
+	return drop_extra_replicas_pred(c, arg, bkey_i_to_s_c(&b->key), io_opts, data_opts);
+}
+
 int bch2_data_job(struct bch_fs *c,
 		  struct bch_move_stats *stats,
 		  struct bch_ioctl_data op)
 {
+	struct bbpos start	= BBPOS(op.start_btree, op.start_pos);
+	struct bbpos end	= BBPOS(op.end_btree, op.end_pos);
 	int ret = 0;
 
+	if (op.op >= BCH_DATA_OP_NR)
+		return -EINVAL;
+
+	bch2_move_stats_init(stats, bch2_data_ops_strs[op.op]);
+
 	switch (op.op) {
-	case BCH_DATA_OP_REREPLICATE:
-		bch2_move_stats_init(stats, "rereplicate");
+	case BCH_DATA_OP_rereplicate:
 		stats->data_type = BCH_DATA_journal;
 		ret = bch2_journal_flush_device_pins(&c->journal, -1);
-
-		ret = bch2_move_btree(c,
-				      op.start_btree,	op.start_pos,
-				      op.end_btree,	op.end_pos,
+		ret = bch2_move_btree(c, start, end,
 				      rereplicate_btree_pred, c, stats) ?: ret;
-		ret = bch2_replicas_gc2(c) ?: ret;
-
-		ret = bch2_move_data(c,
-				     (struct bbpos) { op.start_btree,	op.start_pos },
-				     (struct bbpos) { op.end_btree,	op.end_pos },
+		ret = bch2_move_data(c, start, end,
 				     NULL,
 				     stats,
 				     writepoint_hashed((unsigned long) current),
 				     true,
 				     rereplicate_pred, c) ?: ret;
 		ret = bch2_replicas_gc2(c) ?: ret;
-
-		bch2_move_stats_exit(stats, c);
 		break;
-	case BCH_DATA_OP_MIGRATE:
+	case BCH_DATA_OP_migrate:
 		if (op.migrate.dev >= c->sb.nr_devices)
 			return -EINVAL;
 
-		bch2_move_stats_init(stats, "migrate");
 		stats->data_type = BCH_DATA_journal;
 		ret = bch2_journal_flush_device_pins(&c->journal, op.migrate.dev);
-
-		ret = bch2_move_btree(c,
-				      op.start_btree,	op.start_pos,
-				      op.end_btree,	op.end_pos,
+		ret = bch2_move_btree(c, start, end,
 				      migrate_btree_pred, &op, stats) ?: ret;
-		ret = bch2_replicas_gc2(c) ?: ret;
-
-		ret = bch2_move_data(c,
-				     (struct bbpos) { op.start_btree,	op.start_pos },
-				     (struct bbpos) { op.end_btree,	op.end_pos },
+		ret = bch2_move_data(c, start, end,
 				     NULL,
 				     stats,
 				     writepoint_hashed((unsigned long) current),
 				     true,
 				     migrate_pred, &op) ?: ret;
 		ret = bch2_replicas_gc2(c) ?: ret;
-
-		bch2_move_stats_exit(stats, c);
 		break;
-	case BCH_DATA_OP_REWRITE_OLD_NODES:
-		bch2_move_stats_init(stats, "rewrite_old_nodes");
+	case BCH_DATA_OP_rewrite_old_nodes:
 		ret = bch2_scan_old_btree_nodes(c, stats);
-		bch2_move_stats_exit(stats, c);
+		break;
+	case BCH_DATA_OP_drop_extra_replicas:
+		ret = bch2_move_btree(c, start, end,
+				drop_extra_replicas_btree_pred, c, stats) ?: ret;
+		ret = bch2_move_data(c, start, end, NULL, stats,
+				writepoint_hashed((unsigned long) current),
+				true,
+				drop_extra_replicas_pred, c) ?: ret;
+		ret = bch2_replicas_gc2(c) ?: ret;
 		break;
 	default:
 		ret = -EINVAL;
 	}
 
+	bch2_move_stats_exit(stats, c);
 	return ret;
 }
 
diff --git a/fs/bcachefs/move.h b/fs/bcachefs/move.h
index 07cf9d42643b..9baf3093a678 100644
--- a/fs/bcachefs/move.h
+++ b/fs/bcachefs/move.h
@@ -38,6 +38,25 @@ struct moving_context {
 	wait_queue_head_t	wait;
 };
 
+#define move_ctxt_wait_event_timeout(_ctxt, _cond, _timeout)			\
+({										\
+	int _ret = 0;								\
+	while (true) {								\
+		bool cond_finished = false;					\
+		bch2_moving_ctxt_do_pending_writes(_ctxt);			\
+										\
+		if (_cond)							\
+			break;							\
+		bch2_trans_unlock_long((_ctxt)->trans);				\
+		_ret = __wait_event_timeout((_ctxt)->wait,			\
+			     bch2_moving_ctxt_next_pending_write(_ctxt) ||	\
+			     (cond_finished = (_cond)), _timeout);		\
+		if (_ret || ( cond_finished))					\
+			break;							\
+	}									\
+	_ret;									\
+})
+
 #define move_ctxt_wait_event(_ctxt, _cond)				\
 do {									\
 	bool cond_finished = false;					\
@@ -56,12 +75,15 @@ do {									\
 typedef bool (*move_pred_fn)(struct bch_fs *, void *, struct bkey_s_c,
 			     struct bch_io_opts *, struct data_update_opts *);
 
+extern const char * const bch2_data_ops_strs[];
+
 void bch2_moving_ctxt_exit(struct moving_context *);
 void bch2_moving_ctxt_init(struct moving_context *, struct bch_fs *,
 			   struct bch_ratelimit *, struct bch_move_stats *,
 			   struct write_point_specifier, bool);
 struct moving_io *bch2_moving_ctxt_next_pending_write(struct moving_context *);
 void bch2_moving_ctxt_do_pending_writes(struct moving_context *);
+void bch2_moving_ctxt_flush_all(struct moving_context *);
 void bch2_move_ctxt_wait_for_io(struct moving_context *);
 int bch2_move_ratelimit(struct moving_context *);
 
@@ -114,23 +136,17 @@ int bch2_move_data(struct bch_fs *,
 		   bool,
 		   move_pred_fn, void *);
 
-int __bch2_evacuate_bucket(struct moving_context *,
+int bch2_evacuate_bucket(struct moving_context *,
 			   struct move_bucket_in_flight *,
 			   struct bpos, int,
 			   struct data_update_opts);
-int bch2_evacuate_bucket(struct bch_fs *, struct bpos, int,
-			 struct data_update_opts,
-			 struct bch_ratelimit *,
-			 struct bch_move_stats *,
-			 struct write_point_specifier,
-			 bool);
 int bch2_data_job(struct bch_fs *,
 		  struct bch_move_stats *,
 		  struct bch_ioctl_data);
 
 void bch2_move_stats_to_text(struct printbuf *, struct bch_move_stats *);
 void bch2_move_stats_exit(struct bch_move_stats *, struct bch_fs *);
-void bch2_move_stats_init(struct bch_move_stats *, char *);
+void bch2_move_stats_init(struct bch_move_stats *, const char *);
 
 void bch2_fs_moving_ctxts_to_text(struct printbuf *, struct bch_fs *);
 
diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c
index 0a0576326c5b..69e06a84dad4 100644
--- a/fs/bcachefs/movinggc.c
+++ b/fs/bcachefs/movinggc.c
@@ -91,7 +91,7 @@ static int bch2_bucket_is_movable(struct btree_trans *trans,
 
 	a = bch2_alloc_to_v4(k, &_a);
 	b->k.gen	= a->gen;
-	b->sectors	= a->dirty_sectors;
+	b->sectors	= bch2_bucket_sectors_dirty(*a);
 
 	ret = data_type_movable(a->data_type) &&
 		a->fragmentation_lru &&
@@ -145,20 +145,21 @@ static int bch2_copygc_get_buckets(struct moving_context *ctxt,
 {
 	struct btree_trans *trans = ctxt->trans;
 	struct bch_fs *c = trans->c;
-	struct btree_iter iter;
-	struct bkey_s_c k;
 	size_t nr_to_get = max_t(size_t, 16U, buckets_in_flight->nr / 4);
 	size_t saw = 0, in_flight = 0, not_movable = 0, sectors = 0;
 	int ret;
 
 	move_buckets_wait(ctxt, buckets_in_flight, false);
 
-	ret = bch2_btree_write_buffer_flush(trans);
-	if (bch2_fs_fatal_err_on(ret, c, "%s: error %s from bch2_btree_write_buffer_flush()",
+	ret = bch2_btree_write_buffer_tryflush(trans);
+	if (bch2_err_matches(ret, EROFS))
+		return ret;
+
+	if (bch2_fs_fatal_err_on(ret, c, "%s: error %s from bch2_btree_write_buffer_tryflush()",
 				 __func__, bch2_err_str(ret)))
 		return ret;
 
-	ret = for_each_btree_key2_upto(trans, iter, BTREE_ID_lru,
+	ret = for_each_btree_key_upto(trans, iter, BTREE_ID_lru,
 				  lru_pos(BCH_LRU_FRAGMENTATION_START, 0, 0),
 				  lru_pos(BCH_LRU_FRAGMENTATION_START, U64_MAX, LRU_TIME_MAX),
 				  0, k, ({
@@ -167,15 +168,23 @@ static int bch2_copygc_get_buckets(struct moving_context *ctxt,
 
 		saw++;
 
-		if (!bch2_bucket_is_movable(trans, &b, lru_pos_time(k.k->p)))
+		ret2 = bch2_bucket_is_movable(trans, &b, lru_pos_time(k.k->p));
+		if (ret2 < 0)
+			goto err;
+
+		if (!ret2)
 			not_movable++;
 		else if (bucket_in_flight(buckets_in_flight, b.k))
 			in_flight++;
 		else {
-			ret2 = darray_push(buckets, b) ?: buckets->nr >= nr_to_get;
-			if (ret2 >= 0)
-				sectors += b.sectors;
+			ret2 = darray_push(buckets, b);
+			if (ret2)
+				goto err;
+			sectors += b.sectors;
 		}
+
+		ret2 = buckets->nr >= nr_to_get;
+err:
 		ret2;
 	}));
 
@@ -198,7 +207,6 @@ static int bch2_copygc(struct moving_context *ctxt,
 	};
 	move_buckets buckets = { 0 };
 	struct move_bucket_in_flight *f;
-	struct move_bucket *i;
 	u64 moved = atomic64_read(&ctxt->stats->sectors_moved);
 	int ret = 0;
 
@@ -207,7 +215,7 @@ static int bch2_copygc(struct moving_context *ctxt,
 		goto err;
 
 	darray_for_each(buckets, i) {
-		if (unlikely(freezing(current)))
+		if (kthread_should_stop() || freezing(current))
 			break;
 
 		f = move_bucket_in_flight_add(buckets_in_flight, *i);
@@ -221,7 +229,7 @@ static int bch2_copygc(struct moving_context *ctxt,
 			break;
 		}
 
-		ret = __bch2_evacuate_bucket(ctxt, f, f->bucket.k.bucket,
+		ret = bch2_evacuate_bucket(ctxt, f, f->bucket.k.bucket,
 					     f->bucket.k.gen, data_opts);
 		if (ret)
 			goto err;
@@ -259,19 +267,16 @@ err:
  */
 unsigned long bch2_copygc_wait_amount(struct bch_fs *c)
 {
-	struct bch_dev *ca;
-	unsigned dev_idx;
 	s64 wait = S64_MAX, fragmented_allowed, fragmented;
-	unsigned i;
 
-	for_each_rw_member(ca, c, dev_idx) {
+	for_each_rw_member(c, ca) {
 		struct bch_dev_usage usage = bch2_dev_usage_read(ca);
 
 		fragmented_allowed = ((__dev_buckets_available(ca, usage, BCH_WATERMARK_stripe) *
 				       ca->mi.bucket_size) >> 1);
 		fragmented = 0;
 
-		for (i = 0; i < BCH_DATA_NR; i++)
+		for (unsigned i = 0; i < BCH_DATA_NR; i++)
 			if (data_type_movable(i))
 				fragmented += usage.d[i].fragmented;
 
@@ -313,9 +318,9 @@ static int bch2_copygc_thread(void *arg)
 	if (!buckets)
 		return -ENOMEM;
 	ret = rhashtable_init(&buckets->table, &bch_move_bucket_params);
+	bch_err_msg(c, ret, "allocating copygc buckets in flight");
 	if (ret) {
 		kfree(buckets);
-		bch_err_msg(c, ret, "allocating copygc buckets in flight");
 		return ret;
 	}
 
@@ -334,7 +339,8 @@ static int bch2_copygc_thread(void *arg)
 
 		if (!c->copy_gc_enabled) {
 			move_buckets_wait(&ctxt, buckets, true);
-			kthread_wait_freezable(c->copy_gc_enabled);
+			kthread_wait_freezable(c->copy_gc_enabled ||
+					       kthread_should_stop());
 		}
 
 		if (unlikely(freezing(current))) {
@@ -411,10 +417,9 @@ int bch2_copygc_start(struct bch_fs *c)
 
 	t = kthread_create(bch2_copygc_thread, c, "bch-copygc/%s", c->name);
 	ret = PTR_ERR_OR_ZERO(t);
-	if (ret) {
-		bch_err_msg(c, ret, "creating copygc thread");
+	bch_err_msg(c, ret, "creating copygc thread");
+	if (ret)
 		return ret;
-	}
 
 	get_task_struct(t);
 
diff --git a/fs/bcachefs/opts.c b/fs/bcachefs/opts.c
index 8dd4046cca41..8e6f230eac38 100644
--- a/fs/bcachefs/opts.c
+++ b/fs/bcachefs/opts.c
@@ -279,14 +279,14 @@ int bch2_opt_validate(const struct bch_option *opt, u64 v, struct printbuf *err)
 		if (err)
 			prt_printf(err, "%s: not a multiple of 512",
 			       opt->attr.name);
-		return -EINVAL;
+		return -BCH_ERR_opt_parse_error;
 	}
 
 	if ((opt->flags & OPT_MUST_BE_POW_2) && !is_power_of_2(v)) {
 		if (err)
 			prt_printf(err, "%s: must be a power of two",
 			       opt->attr.name);
-		return -EINVAL;
+		return -BCH_ERR_opt_parse_error;
 	}
 
 	if (opt->fn.validate)
diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h
index 8526f177450a..93a24fef4214 100644
--- a/fs/bcachefs/opts.h
+++ b/fs/bcachefs/opts.h
@@ -233,11 +233,6 @@ enum fsck_err_opts {
 	  OPT_BOOL(),							\
 	  BCH2_NO_SB_OPT,		true,				\
 	  NULL,		"Stash pointer to in memory btree node in btree ptr")\
-	x(btree_write_buffer_size, u32,					\
-	  OPT_FS|OPT_MOUNT,						\
-	  OPT_UINT(16, (1U << 20) - 1),					\
-	  BCH2_NO_SB_OPT,		1U << 13,			\
-	  NULL,		"Number of btree write buffer entries")		\
 	x(gc_reserve_percent,		u8,				\
 	  OPT_FS|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME,			\
 	  OPT_UINT(5, 21),						\
@@ -394,7 +389,7 @@ enum fsck_err_opts {
 	  BCH2_NO_SB_OPT,		BCH_SB_SECTOR,			\
 	  "offset",	"Sector offset of superblock")			\
 	x(read_only,			u8,				\
-	  OPT_FS,							\
+	  OPT_FS|OPT_MOUNT,						\
 	  OPT_BOOL(),							\
 	  BCH2_NO_SB_OPT,		false,				\
 	  NULL,		NULL)						\
@@ -419,6 +414,11 @@ enum fsck_err_opts {
 	  OPT_BOOL(),							\
 	  BCH2_NO_SB_OPT,		false,				\
 	  NULL,		"Allocate the buckets_nouse bitmap")		\
+	x(stdio,			u64,				\
+	  0,								\
+	  OPT_UINT(0, S64_MAX),						\
+	  BCH2_NO_SB_OPT,		false,				\
+	  NULL,		"Pointer to a struct stdio_redirect")		\
 	x(project,			u8,				\
 	  OPT_INODE,							\
 	  OPT_BOOL(),							\
@@ -458,7 +458,13 @@ enum fsck_err_opts {
 	  OPT_UINT(0, BCH_REPLICAS_MAX),				\
 	  BCH2_NO_SB_OPT,		1,				\
 	  "n",		"Data written to this device will be considered\n"\
-			"to have already been replicated n times")
+			"to have already been replicated n times")	\
+	x(btree_node_prefetch,		u8,				\
+	  OPT_FS|OPT_MOUNT|OPT_RUNTIME,					\
+	  OPT_BOOL(),							\
+	  BCH2_NO_SB_OPT,		true,				\
+	  NULL,		"BTREE_ITER_PREFETCH casuse btree nodes to be\n"\
+	  " prefetched sequentially")
 
 struct bch_opts {
 #define x(_name, _bits, ...)	unsigned _name##_defined:1;
diff --git a/fs/bcachefs/printbuf.c b/fs/bcachefs/printbuf.c
index 5e653eb81d54..accf246c3233 100644
--- a/fs/bcachefs/printbuf.c
+++ b/fs/bcachefs/printbuf.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: LGPL-2.1+
 /* Copyright (C) 2022 Kent Overstreet */
 
+#include <linux/bitmap.h>
 #include <linux/err.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
@@ -423,3 +424,24 @@ void bch2_prt_bitflags(struct printbuf *out,
 		flags ^= BIT_ULL(bit);
 	}
 }
+
+void bch2_prt_bitflags_vector(struct printbuf *out,
+			      const char * const list[],
+			      unsigned long *v, unsigned nr)
+{
+	bool first = true;
+	unsigned i;
+
+	for (i = 0; i < nr; i++)
+		if (!list[i]) {
+			nr = i - 1;
+			break;
+		}
+
+	for_each_set_bit(i, v, nr) {
+		if (!first)
+			bch2_prt_printf(out, ",");
+		first = false;
+		bch2_prt_printf(out, "%s", list[i]);
+	}
+}
diff --git a/fs/bcachefs/printbuf.h b/fs/bcachefs/printbuf.h
index 2191423d9f22..9a4a56c40937 100644
--- a/fs/bcachefs/printbuf.h
+++ b/fs/bcachefs/printbuf.h
@@ -124,6 +124,8 @@ void bch2_prt_units_u64(struct printbuf *, u64);
 void bch2_prt_units_s64(struct printbuf *, s64);
 void bch2_prt_string_option(struct printbuf *, const char * const[], size_t);
 void bch2_prt_bitflags(struct printbuf *, const char * const[], u64);
+void bch2_prt_bitflags_vector(struct printbuf *, const char * const[],
+			      unsigned long *, unsigned);
 
 /* Initializer for a heap allocated printbuf: */
 #define PRINTBUF ((struct printbuf) { .heap_allocated = true })
diff --git a/fs/bcachefs/quota.c b/fs/bcachefs/quota.c
index a54647c36b85..e68b34eab90a 100644
--- a/fs/bcachefs/quota.c
+++ b/fs/bcachefs/quota.c
@@ -599,14 +599,9 @@ advance:
 
 int bch2_fs_quota_read(struct bch_fs *c)
 {
-	struct bch_sb_field_quota *sb_quota;
-	struct btree_trans *trans;
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	int ret;
 
 	mutex_lock(&c->sb_lock);
-	sb_quota = bch2_sb_get_or_create_quota(&c->disk_sb);
+	struct bch_sb_field_quota *sb_quota = bch2_sb_get_or_create_quota(&c->disk_sb);
 	if (!sb_quota) {
 		mutex_unlock(&c->sb_lock);
 		return -BCH_ERR_ENOSPC_sb_quota;
@@ -615,19 +610,14 @@ int bch2_fs_quota_read(struct bch_fs *c)
 	bch2_sb_quota_read(c);
 	mutex_unlock(&c->sb_lock);
 
-	trans = bch2_trans_get(c);
-
-	ret = for_each_btree_key2(trans, iter, BTREE_ID_quotas,
-			POS_MIN, BTREE_ITER_PREFETCH, k,
-		__bch2_quota_set(c, k, NULL)) ?:
-	      for_each_btree_key2(trans, iter, BTREE_ID_inodes,
-			POS_MIN, BTREE_ITER_PREFETCH|BTREE_ITER_ALL_SNAPSHOTS, k,
-		bch2_fs_quota_read_inode(trans, &iter, k));
-
-	bch2_trans_put(trans);
-
-	if (ret)
-		bch_err_fn(c, ret);
+	int ret = bch2_trans_run(c,
+		for_each_btree_key(trans, iter, BTREE_ID_quotas, POS_MIN,
+				   BTREE_ITER_PREFETCH, k,
+			__bch2_quota_set(c, k, NULL)) ?:
+		for_each_btree_key(trans, iter, BTREE_ID_inodes, POS_MIN,
+				   BTREE_ITER_PREFETCH|BTREE_ITER_ALL_SNAPSHOTS, k,
+			bch2_fs_quota_read_inode(trans, &iter, k)));
+	bch_err_fn(c, ret);
 	return ret;
 }
 
diff --git a/fs/bcachefs/rebalance.c b/fs/bcachefs/rebalance.c
index 3319190b8d9c..95f46cb3b5bd 100644
--- a/fs/bcachefs/rebalance.c
+++ b/fs/bcachefs/rebalance.c
@@ -69,7 +69,7 @@ err:
 
 int bch2_set_rebalance_needs_scan(struct bch_fs *c, u64 inum)
 {
-	int ret = bch2_trans_do(c, NULL, NULL, BTREE_INSERT_NOFAIL|BTREE_INSERT_LAZY_RW,
+	int ret = bch2_trans_do(c, NULL, NULL, BCH_TRANS_COMMIT_no_enospc|BCH_TRANS_COMMIT_lazy_rw,
 			    __bch2_set_rebalance_needs_scan(trans, inum));
 	rebalance_wakeup(c);
 	return ret;
@@ -125,7 +125,7 @@ static int bch2_bkey_clear_needs_rebalance(struct btree_trans *trans,
 
 	extent_entry_drop(bkey_i_to_s(n),
 			  (void *) bch2_bkey_rebalance_opts(bkey_i_to_s_c(n)));
-	return bch2_trans_commit(trans, NULL, NULL, BTREE_INSERT_NOFAIL);
+	return bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc);
 }
 
 static struct bkey_s_c next_rebalance_extent(struct btree_trans *trans,
@@ -171,6 +171,21 @@ static struct bkey_s_c next_rebalance_extent(struct btree_trans *trans,
 		return bkey_s_c_null;
 	}
 
+	if (trace_rebalance_extent_enabled()) {
+		struct printbuf buf = PRINTBUF;
+
+		prt_str(&buf, "target=");
+		bch2_target_to_text(&buf, c, r->target);
+		prt_str(&buf, " compression=");
+		struct bch_compression_opt opt = __bch2_compression_decode(r->compression);
+		prt_str(&buf, bch2_compression_opts[opt.type]);
+		prt_str(&buf, " ");
+		bch2_bkey_val_to_text(&buf, c, k);
+
+		trace_rebalance_extent(c, buf.buf);
+		printbuf_exit(&buf);
+	}
+
 	return k;
 }
 
@@ -273,7 +288,7 @@ static int do_rebalance_scan(struct moving_context *ctxt, u64 inum, u64 cookie)
 	r->state = BCH_REBALANCE_scanning;
 
 	ret = __bch2_move_data(ctxt, r->scan_start, r->scan_end, rebalance_pred, NULL) ?:
-		commit_do(trans, NULL, NULL, BTREE_INSERT_NOFAIL,
+		commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 			  bch2_clear_rebalance_needs_scan(trans, inum, cookie));
 
 	bch2_move_stats_exit(&r->scan_stats, trans->c);
@@ -317,8 +332,16 @@ static int do_rebalance(struct moving_context *ctxt)
 			     BTREE_ID_rebalance_work, POS_MIN,
 			     BTREE_ITER_ALL_SNAPSHOTS);
 
-	while (!bch2_move_ratelimit(ctxt) &&
-	       !kthread_wait_freezable(r->enabled)) {
+	while (!bch2_move_ratelimit(ctxt)) {
+		if (!r->enabled) {
+			bch2_moving_ctxt_flush_all(ctxt);
+			kthread_wait_freezable(r->enabled ||
+					       kthread_should_stop());
+		}
+
+		if (kthread_should_stop())
+			break;
+
 		bch2_trans_begin(trans);
 
 		ret = bkey_err(k = next_rebalance_entry(trans, &rebalance_work_iter));
@@ -447,10 +470,9 @@ int bch2_rebalance_start(struct bch_fs *c)
 
 	p = kthread_create(bch2_rebalance_thread, c, "bch-rebalance/%s", c->name);
 	ret = PTR_ERR_OR_ZERO(p);
-	if (ret) {
-		bch_err_msg(c, ret, "creating rebalance thread");
+	bch_err_msg(c, ret, "creating rebalance thread");
+	if (ret)
 		return ret;
-	}
 
 	get_task_struct(p);
 	rcu_assign_pointer(c->rebalance.thread, p);
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 9c30500ce920..725214605a05 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -27,6 +27,7 @@
 #include "recovery.h"
 #include "replicas.h"
 #include "sb-clean.h"
+#include "sb-downgrade.h"
 #include "snapshot.h"
 #include "subvolume.h"
 #include "super-io.h"
@@ -98,6 +99,11 @@ static int bch2_journal_replay_key(struct btree_trans *trans,
 	unsigned update_flags = BTREE_TRIGGER_NORUN;
 	int ret;
 
+	if (k->overwritten)
+		return 0;
+
+	trans->journal_res.seq = k->journal_seq;
+
 	/*
 	 * BTREE_UPDATE_KEY_CACHE_RECLAIM disables key cache lookup/update to
 	 * keep the key cache coherent with the underlying btree. Nothing
@@ -139,26 +145,12 @@ static int journal_sort_seq_cmp(const void *_l, const void *_r)
 static int bch2_journal_replay(struct bch_fs *c)
 {
 	struct journal_keys *keys = &c->journal_keys;
-	struct journal_key **keys_sorted, *k;
+	DARRAY(struct journal_key *) keys_sorted = { 0 };
 	struct journal *j = &c->journal;
 	u64 start_seq	= c->journal_replay_seq_start;
 	u64 end_seq	= c->journal_replay_seq_start;
-	size_t i;
-	int ret;
-
-	move_gap(keys->d, keys->nr, keys->size, keys->gap, keys->nr);
-	keys->gap = keys->nr;
-
-	keys_sorted = kvmalloc_array(keys->nr, sizeof(*keys_sorted), GFP_KERNEL);
-	if (!keys_sorted)
-		return -BCH_ERR_ENOMEM_journal_replay;
-
-	for (i = 0; i < keys->nr; i++)
-		keys_sorted[i] = &keys->d[i];
-
-	sort(keys_sorted, keys->nr,
-	     sizeof(keys_sorted[0]),
-	     journal_sort_seq_cmp, NULL);
+	struct btree_trans *trans = bch2_trans_get(c);
+	int ret = 0;
 
 	if (keys->nr) {
 		ret = bch2_journal_log_msg(c, "Starting journal replay (%zu keys in entries %llu-%llu)",
@@ -167,41 +159,84 @@ static int bch2_journal_replay(struct bch_fs *c)
 			goto err;
 	}
 
-	for (i = 0; i < keys->nr; i++) {
-		k = keys_sorted[i];
+	BUG_ON(!atomic_read(&keys->ref));
 
+	/*
+	 * First, attempt to replay keys in sorted order. This is more
+	 * efficient - better locality of btree access -  but some might fail if
+	 * that would cause a journal deadlock.
+	 */
+	for (size_t i = 0; i < keys->nr; i++) {
 		cond_resched();
 
-		replay_now_at(j, k->journal_seq);
+		struct journal_key *k = keys->d + i;
 
-		ret = bch2_trans_do(c, NULL, NULL,
-				    BTREE_INSERT_LAZY_RW|
-				    BTREE_INSERT_NOFAIL|
-				    (!k->allocated
-				     ? BTREE_INSERT_JOURNAL_REPLAY|BCH_WATERMARK_reclaim
-				     : 0),
+		/* Skip fastpath if we're low on space in the journal */
+		ret = c->journal.watermark ? -1 :
+			commit_do(trans, NULL, NULL,
+				  BCH_TRANS_COMMIT_no_enospc|
+				  BCH_TRANS_COMMIT_journal_reclaim|
+				  (!k->allocated ? BCH_TRANS_COMMIT_no_journal_res : 0),
 			     bch2_journal_replay_key(trans, k));
+		BUG_ON(!ret && !k->overwritten);
 		if (ret) {
-			bch_err(c, "journal replay: error while replaying key at btree %s level %u: %s",
-				bch2_btree_id_str(k->btree_id), k->level, bch2_err_str(ret));
-			goto err;
+			ret = darray_push(&keys_sorted, k);
+			if (ret)
+				goto err;
 		}
 	}
 
+	/*
+	 * Now, replay any remaining keys in the order in which they appear in
+	 * the journal, unpinning those journal entries as we go:
+	 */
+	sort(keys_sorted.data, keys_sorted.nr,
+	     sizeof(keys_sorted.data[0]),
+	     journal_sort_seq_cmp, NULL);
+
+	darray_for_each(keys_sorted, kp) {
+		cond_resched();
+
+		struct journal_key *k = *kp;
+
+		replay_now_at(j, k->journal_seq);
+
+		ret = commit_do(trans, NULL, NULL,
+				BCH_TRANS_COMMIT_no_enospc|
+				(!k->allocated
+				 ? BCH_TRANS_COMMIT_no_journal_res|BCH_WATERMARK_reclaim
+				 : 0),
+			     bch2_journal_replay_key(trans, k));
+		bch_err_msg(c, ret, "while replaying key at btree %s level %u:",
+			    bch2_btree_id_str(k->btree_id), k->level);
+		if (ret)
+			goto err;
+
+		BUG_ON(!k->overwritten);
+	}
+
+	/*
+	 * We need to put our btree_trans before calling flush_all_pins(), since
+	 * that will use a btree_trans internally
+	 */
+	bch2_trans_put(trans);
+	trans = NULL;
+
+	if (!c->opts.keep_journal)
+		bch2_journal_keys_put_initial(c);
+
 	replay_now_at(j, j->replay_journal_seq_end);
 	j->replay_journal_seq = 0;
 
 	bch2_journal_set_replay_done(j);
-	bch2_journal_flush_all_pins(j);
-	ret = bch2_journal_error(j);
 
-	if (keys->nr && !ret)
+	if (keys->nr)
 		bch2_journal_log_msg(c, "journal replay finished");
 err:
-	kvfree(keys_sorted);
-
-	if (ret)
-		bch_err_fn(c, ret);
+	if (trans)
+		bch2_trans_put(trans);
+	darray_exit(&keys_sorted);
+	bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -269,8 +304,6 @@ static int journal_replay_entry_early(struct bch_fs *c,
 		struct bch_dev *ca = bch_dev_bkey_exists(c, le32_to_cpu(u->dev));
 		unsigned i, nr_types = jset_entry_dev_usage_nr_types(u);
 
-		ca->usage_base->buckets_ec		= le64_to_cpu(u->buckets_ec);
-
 		for (i = 0; i < min_t(unsigned, nr_types, BCH_DATA_NR); i++) {
 			ca->usage_base->d[i].buckets	= le64_to_cpu(u->d[i].buckets);
 			ca->usage_base->d[i].sectors	= le64_to_cpu(u->d[i].sectors);
@@ -311,14 +344,11 @@ static int journal_replay_entry_early(struct bch_fs *c,
 static int journal_replay_early(struct bch_fs *c,
 				struct bch_sb_field_clean *clean)
 {
-	struct jset_entry *entry;
-	int ret;
-
 	if (clean) {
-		for (entry = clean->start;
+		for (struct jset_entry *entry = clean->start;
 		     entry != vstruct_end(&clean->field);
 		     entry = vstruct_next(entry)) {
-			ret = journal_replay_entry_early(c, entry);
+			int ret = journal_replay_entry_early(c, entry);
 			if (ret)
 				return ret;
 		}
@@ -333,7 +363,7 @@ static int journal_replay_early(struct bch_fs *c,
 				continue;
 
 			vstruct_for_each(&i->j, entry) {
-				ret = journal_replay_entry_early(c, entry);
+				int ret = journal_replay_entry_early(c, entry);
 				if (ret)
 					return ret;
 			}
@@ -429,8 +459,7 @@ static int bch2_initialize_subvolumes(struct bch_fs *c)
 	ret =   bch2_btree_insert(c, BTREE_ID_snapshot_trees,	&root_tree.k_i, NULL, 0) ?:
 		bch2_btree_insert(c, BTREE_ID_snapshots,	&root_snapshot.k_i, NULL, 0) ?:
 		bch2_btree_insert(c, BTREE_ID_subvolumes,	&root_volume.k_i, NULL, 0);
-	if (ret)
-		bch_err_fn(c, ret);
+	bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -468,15 +497,14 @@ err:
 noinline_for_stack
 static int bch2_fs_upgrade_for_subvolumes(struct bch_fs *c)
 {
-	int ret = bch2_trans_do(c, NULL, NULL, BTREE_INSERT_LAZY_RW,
+	int ret = bch2_trans_do(c, NULL, NULL, BCH_TRANS_COMMIT_lazy_rw,
 				__bch2_fs_upgrade_for_subvolumes(trans));
-	if (ret)
-		bch_err_fn(c, ret);
+	bch_err_fn(c, ret);
 	return ret;
 }
 
 const char * const bch2_recovery_passes[] = {
-#define x(_fn, _when)	#_fn,
+#define x(_fn, ...)	#_fn,
 	BCH_RECOVERY_PASSES()
 #undef x
 	NULL
@@ -489,7 +517,20 @@ static int bch2_check_allocations(struct bch_fs *c)
 
 static int bch2_set_may_go_rw(struct bch_fs *c)
 {
-	set_bit(BCH_FS_MAY_GO_RW, &c->flags);
+	struct journal_keys *keys = &c->journal_keys;
+
+	/*
+	 * After we go RW, the journal keys buffer can't be modified (except for
+	 * setting journal_key->overwritten: it will be accessed by multiple
+	 * threads
+	 */
+	move_gap(keys->d, keys->nr, keys->size, keys->gap, keys->nr);
+	keys->gap = keys->nr;
+
+	set_bit(BCH_FS_may_go_rw, &c->flags);
+
+	if (keys->nr || c->opts.fsck || !c->sb.clean)
+		return bch2_fs_read_write_early(c);
 	return 0;
 }
 
@@ -499,18 +540,47 @@ struct recovery_pass_fn {
 };
 
 static struct recovery_pass_fn recovery_pass_fns[] = {
-#define x(_fn, _when)	{ .fn = bch2_##_fn, .when = _when },
+#define x(_fn, _id, _when)	{ .fn = bch2_##_fn, .when = _when },
 	BCH_RECOVERY_PASSES()
 #undef x
 };
 
-static void check_version_upgrade(struct bch_fs *c)
+u64 bch2_recovery_passes_to_stable(u64 v)
+{
+	static const u8 map[] = {
+#define x(n, id, ...)	[BCH_RECOVERY_PASS_##n] = BCH_RECOVERY_PASS_STABLE_##n,
+	BCH_RECOVERY_PASSES()
+#undef x
+	};
+
+	u64 ret = 0;
+	for (unsigned i = 0; i < ARRAY_SIZE(map); i++)
+		if (v & BIT_ULL(i))
+			ret |= BIT_ULL(map[i]);
+	return ret;
+}
+
+u64 bch2_recovery_passes_from_stable(u64 v)
+{
+	static const u8 map[] = {
+#define x(n, id, ...)	[BCH_RECOVERY_PASS_STABLE_##n] = BCH_RECOVERY_PASS_##n,
+	BCH_RECOVERY_PASSES()
+#undef x
+	};
+
+	u64 ret = 0;
+	for (unsigned i = 0; i < ARRAY_SIZE(map); i++)
+		if (v & BIT_ULL(i))
+			ret |= BIT_ULL(map[i]);
+	return ret;
+}
+
+static bool check_version_upgrade(struct bch_fs *c)
 {
 	unsigned latest_compatible = bch2_latest_compatible_version(c->sb.version);
 	unsigned latest_version	= bcachefs_metadata_version_current;
 	unsigned old_version = c->sb.version_upgrade_complete ?: c->sb.version;
 	unsigned new_version = 0;
-	u64 recovery_passes;
 
 	if (old_version < bcachefs_metadata_required_upgrade_below) {
 		if (c->opts.version_upgrade == BCH_VERSION_UPGRADE_incompatible ||
@@ -554,27 +624,26 @@ static void check_version_upgrade(struct bch_fs *c)
 		bch2_version_to_text(&buf, new_version);
 		prt_newline(&buf);
 
-		recovery_passes = bch2_upgrade_recovery_passes(c, old_version, new_version);
-		if (recovery_passes) {
-			if ((recovery_passes & RECOVERY_PASS_ALL_FSCK) == RECOVERY_PASS_ALL_FSCK)
-				prt_str(&buf, "fsck required");
-			else {
-				prt_str(&buf, "running recovery passes: ");
-				prt_bitflags(&buf, bch2_recovery_passes, recovery_passes);
-			}
+		struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
+		__le64 passes = ext->recovery_passes_required[0];
+		bch2_sb_set_upgrade(c, old_version, new_version);
+		passes = ext->recovery_passes_required[0] & ~passes;
 
-			c->recovery_passes_explicit |= recovery_passes;
-			c->opts.fix_errors = FSCK_FIX_yes;
+		if (passes) {
+			prt_str(&buf, "  running recovery passes: ");
+			prt_bitflags(&buf, bch2_recovery_passes,
+				     bch2_recovery_passes_from_stable(le64_to_cpu(passes)));
 		}
 
 		bch_info(c, "%s", buf.buf);
 
-		mutex_lock(&c->sb_lock);
 		bch2_sb_upgrade(c, new_version);
-		mutex_unlock(&c->sb_lock);
 
 		printbuf_exit(&buf);
+		return true;
 	}
+
+	return false;
 }
 
 u64 bch2_fsck_recovery_passes(void)
@@ -589,7 +658,7 @@ u64 bch2_fsck_recovery_passes(void)
 
 static bool should_run_recovery_pass(struct bch_fs *c, enum bch_recovery_pass pass)
 {
-	struct recovery_pass_fn *p = recovery_pass_fns + c->curr_recovery_pass;
+	struct recovery_pass_fn *p = recovery_pass_fns + pass;
 
 	if (c->opts.norecovery && pass > BCH_RECOVERY_PASS_snapshots_read)
 		return false;
@@ -606,39 +675,62 @@ static bool should_run_recovery_pass(struct bch_fs *c, enum bch_recovery_pass pa
 
 static int bch2_run_recovery_pass(struct bch_fs *c, enum bch_recovery_pass pass)
 {
+	struct recovery_pass_fn *p = recovery_pass_fns + pass;
 	int ret;
 
-	c->curr_recovery_pass = pass;
+	if (!(p->when & PASS_SILENT))
+		bch2_print(c, KERN_INFO bch2_log_msg(c, "%s..."),
+			   bch2_recovery_passes[pass]);
+	ret = p->fn(c);
+	if (ret)
+		return ret;
+	if (!(p->when & PASS_SILENT))
+		bch2_print(c, KERN_CONT " done\n");
+
+	return 0;
+}
 
-	if (should_run_recovery_pass(c, pass)) {
-		struct recovery_pass_fn *p = recovery_pass_fns + pass;
+static int bch2_run_recovery_passes(struct bch_fs *c)
+{
+	int ret = 0;
 
-		if (!(p->when & PASS_SILENT))
-			printk(KERN_INFO bch2_log_msg(c, "%s..."),
-			       bch2_recovery_passes[pass]);
-		ret = p->fn(c);
-		if (ret)
-			return ret;
-		if (!(p->when & PASS_SILENT))
-			printk(KERN_CONT " done\n");
+	while (c->curr_recovery_pass < ARRAY_SIZE(recovery_pass_fns)) {
+		if (should_run_recovery_pass(c, c->curr_recovery_pass)) {
+			unsigned pass = c->curr_recovery_pass;
 
-		c->recovery_passes_complete |= BIT_ULL(pass);
+			ret = bch2_run_recovery_pass(c, c->curr_recovery_pass);
+			if (bch2_err_matches(ret, BCH_ERR_restart_recovery) ||
+			    (ret && c->curr_recovery_pass < pass))
+				continue;
+			if (ret)
+				break;
+
+			c->recovery_passes_complete |= BIT_ULL(c->curr_recovery_pass);
+		}
+		c->curr_recovery_pass++;
+		c->recovery_pass_done = max(c->recovery_pass_done, c->curr_recovery_pass);
 	}
 
-	return 0;
+	return ret;
 }
 
-static int bch2_run_recovery_passes(struct bch_fs *c)
+int bch2_run_online_recovery_passes(struct bch_fs *c)
 {
 	int ret = 0;
 
-	while (c->curr_recovery_pass < ARRAY_SIZE(recovery_pass_fns)) {
-		ret = bch2_run_recovery_pass(c, c->curr_recovery_pass);
-		if (bch2_err_matches(ret, BCH_ERR_restart_recovery))
+	for (unsigned i = 0; i < ARRAY_SIZE(recovery_pass_fns); i++) {
+		struct recovery_pass_fn *p = recovery_pass_fns + i;
+
+		if (!(p->when & PASS_ONLINE))
+			continue;
+
+		ret = bch2_run_recovery_pass(c, i);
+		if (bch2_err_matches(ret, BCH_ERR_restart_recovery)) {
+			i = c->curr_recovery_pass;
 			continue;
+		}
 		if (ret)
 			break;
-		c->curr_recovery_pass++;
 	}
 
 	return ret;
@@ -649,7 +741,6 @@ int bch2_fs_recovery(struct bch_fs *c)
 	struct bch_sb_field_clean *clean = NULL;
 	struct jset *last_journal_entry = NULL;
 	u64 last_seq = 0, blacklist_seq, journal_seq;
-	bool write_sb = false;
 	int ret = 0;
 
 	if (c->sb.clean) {
@@ -677,15 +768,76 @@ int bch2_fs_recovery(struct bch_fs *c)
 		goto err;
 	}
 
-	if (c->opts.fsck || !(c->opts.nochanges && c->opts.norecovery))
-		check_version_upgrade(c);
-
 	if (c->opts.fsck && c->opts.norecovery) {
 		bch_err(c, "cannot select both norecovery and fsck");
 		ret = -EINVAL;
 		goto err;
 	}
 
+	if (!(c->opts.nochanges && c->opts.norecovery)) {
+		mutex_lock(&c->sb_lock);
+		bool write_sb = false;
+
+		struct bch_sb_field_ext *ext =
+			bch2_sb_field_get_minsize(&c->disk_sb, ext, sizeof(*ext) / sizeof(u64));
+		if (!ext) {
+			ret = -BCH_ERR_ENOSPC_sb;
+			mutex_unlock(&c->sb_lock);
+			goto err;
+		}
+
+		if (BCH_SB_HAS_TOPOLOGY_ERRORS(c->disk_sb.sb)) {
+			ext->recovery_passes_required[0] |=
+				cpu_to_le64(bch2_recovery_passes_to_stable(BIT_ULL(BCH_RECOVERY_PASS_check_topology)));
+			write_sb = true;
+		}
+
+		u64 sb_passes = bch2_recovery_passes_from_stable(le64_to_cpu(ext->recovery_passes_required[0]));
+		if (sb_passes) {
+			struct printbuf buf = PRINTBUF;
+			prt_str(&buf, "superblock requires following recovery passes to be run:\n  ");
+			prt_bitflags(&buf, bch2_recovery_passes, sb_passes);
+			bch_info(c, "%s", buf.buf);
+			printbuf_exit(&buf);
+		}
+
+		if (bch2_check_version_downgrade(c)) {
+			struct printbuf buf = PRINTBUF;
+
+			prt_str(&buf, "Version downgrade required:\n");
+
+			__le64 passes = ext->recovery_passes_required[0];
+			bch2_sb_set_downgrade(c,
+					BCH_VERSION_MINOR(bcachefs_metadata_version_current),
+					BCH_VERSION_MINOR(c->sb.version));
+			passes = ext->recovery_passes_required[0] & ~passes;
+			if (passes) {
+				prt_str(&buf, "  running recovery passes: ");
+				prt_bitflags(&buf, bch2_recovery_passes,
+					     bch2_recovery_passes_from_stable(le64_to_cpu(passes)));
+			}
+
+			bch_info(c, "%s", buf.buf);
+			printbuf_exit(&buf);
+			write_sb = true;
+		}
+
+		if (check_version_upgrade(c))
+			write_sb = true;
+
+		if (write_sb)
+			bch2_write_super(c);
+
+		c->recovery_passes_explicit |= bch2_recovery_passes_from_stable(le64_to_cpu(ext->recovery_passes_required[0]));
+		mutex_unlock(&c->sb_lock);
+	}
+
+	if (c->opts.fsck && IS_ENABLED(CONFIG_BCACHEFS_DEBUG))
+		c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_topology);
+
+	if (c->opts.fsck)
+		set_bit(BCH_FS_fsck_running, &c->flags);
+
 	ret = bch2_blacklist_table_initialize(c);
 	if (ret) {
 		bch_err(c, "error initializing blacklist table");
@@ -822,22 +974,21 @@ use_clean:
 	if (ret)
 		goto err;
 
-	if (c->opts.fsck &&
-	    (IS_ENABLED(CONFIG_BCACHEFS_DEBUG) ||
-	     BCH_SB_HAS_TOPOLOGY_ERRORS(c->disk_sb.sb)))
-		c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_topology);
-
 	ret = bch2_run_recovery_passes(c);
 	if (ret)
 		goto err;
 
+	clear_bit(BCH_FS_fsck_running, &c->flags);
+
 	/* If we fixed errors, verify that fs is actually clean now: */
 	if (IS_ENABLED(CONFIG_BCACHEFS_DEBUG) &&
-	    test_bit(BCH_FS_ERRORS_FIXED, &c->flags) &&
-	    !test_bit(BCH_FS_ERRORS_NOT_FIXED, &c->flags) &&
-	    !test_bit(BCH_FS_ERROR, &c->flags)) {
+	    test_bit(BCH_FS_errors_fixed, &c->flags) &&
+	    !test_bit(BCH_FS_errors_not_fixed, &c->flags) &&
+	    !test_bit(BCH_FS_error, &c->flags)) {
+		bch2_flush_fsck_errs(c);
+
 		bch_info(c, "Fixed errors, running fsck a second time to verify fs is clean");
-		clear_bit(BCH_FS_ERRORS_FIXED, &c->flags);
+		clear_bit(BCH_FS_errors_fixed, &c->flags);
 
 		c->curr_recovery_pass = BCH_RECOVERY_PASS_check_alloc_info;
 
@@ -845,13 +996,13 @@ use_clean:
 		if (ret)
 			goto err;
 
-		if (test_bit(BCH_FS_ERRORS_FIXED, &c->flags) ||
-		    test_bit(BCH_FS_ERRORS_NOT_FIXED, &c->flags)) {
+		if (test_bit(BCH_FS_errors_fixed, &c->flags) ||
+		    test_bit(BCH_FS_errors_not_fixed, &c->flags)) {
 			bch_err(c, "Second fsck run was not clean");
-			set_bit(BCH_FS_ERRORS_NOT_FIXED, &c->flags);
+			set_bit(BCH_FS_errors_not_fixed, &c->flags);
 		}
 
-		set_bit(BCH_FS_ERRORS_FIXED, &c->flags);
+		set_bit(BCH_FS_errors_fixed, &c->flags);
 	}
 
 	if (enabled_qtypes(c)) {
@@ -863,19 +1014,33 @@ use_clean:
 	}
 
 	mutex_lock(&c->sb_lock);
-	if (BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb) != c->sb.version) {
-		SET_BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb, c->sb.version);
+	bool write_sb = false;
+
+	if (BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb) != le16_to_cpu(c->disk_sb.sb->version)) {
+		SET_BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb, le16_to_cpu(c->disk_sb.sb->version));
 		write_sb = true;
 	}
 
-	if (!test_bit(BCH_FS_ERROR, &c->flags)) {
+	if (!test_bit(BCH_FS_error, &c->flags) &&
+	    !(c->disk_sb.sb->compat[0] & cpu_to_le64(1ULL << BCH_COMPAT_alloc_info))) {
 		c->disk_sb.sb->compat[0] |= cpu_to_le64(1ULL << BCH_COMPAT_alloc_info);
 		write_sb = true;
 	}
 
+	if (!test_bit(BCH_FS_error, &c->flags)) {
+		struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
+		if (ext &&
+		    (!bch2_is_zero(ext->recovery_passes_required, sizeof(ext->recovery_passes_required)) ||
+		     !bch2_is_zero(ext->errors_silent, sizeof(ext->errors_silent)))) {
+			memset(ext->recovery_passes_required, 0, sizeof(ext->recovery_passes_required));
+			memset(ext->errors_silent, 0, sizeof(ext->errors_silent));
+			write_sb = true;
+		}
+	}
+
 	if (c->opts.fsck &&
-	    !test_bit(BCH_FS_ERROR, &c->flags) &&
-	    !test_bit(BCH_FS_ERRORS_NOT_FIXED, &c->flags)) {
+	    !test_bit(BCH_FS_error, &c->flags) &&
+	    !test_bit(BCH_FS_errors_not_fixed, &c->flags)) {
 		SET_BCH_SB_HAS_ERRORS(c->disk_sb.sb, 0);
 		SET_BCH_SB_HAS_TOPOLOGY_ERRORS(c->disk_sb.sb, 0);
 		write_sb = true;
@@ -891,8 +1056,12 @@ use_clean:
 
 		bch2_move_stats_init(&stats, "recovery");
 
-		bch_info(c, "scanning for old btree nodes");
-		ret =   bch2_fs_read_write(c) ?:
+		struct printbuf buf = PRINTBUF;
+		bch2_version_to_text(&buf, c->sb.version_min);
+		bch_info(c, "scanning for old btree nodes: min_version %s", buf.buf);
+		printbuf_exit(&buf);
+
+		ret =   bch2_fs_read_write_early(c) ?:
 			bch2_scan_old_btree_nodes(c, &stats);
 		if (ret)
 			goto err;
@@ -905,23 +1074,21 @@ use_clean:
 
 	ret = 0;
 out:
-	set_bit(BCH_FS_FSCK_DONE, &c->flags);
 	bch2_flush_fsck_errs(c);
 
 	if (!c->opts.keep_journal &&
-	    test_bit(JOURNAL_REPLAY_DONE, &c->journal.flags)) {
-		bch2_journal_keys_free(&c->journal_keys);
-		bch2_journal_entries_free(c);
-	}
+	    test_bit(JOURNAL_REPLAY_DONE, &c->journal.flags))
+		bch2_journal_keys_put_initial(c);
 	kfree(clean);
 
-	if (!ret && test_bit(BCH_FS_NEED_DELETE_DEAD_SNAPSHOTS, &c->flags)) {
+	if (!ret &&
+	    test_bit(BCH_FS_need_delete_dead_snapshots, &c->flags) &&
+	    !c->opts.nochanges) {
 		bch2_fs_read_write_early(c);
 		bch2_delete_dead_snapshots_async(c);
 	}
 
-	if (ret)
-		bch_err_fn(c, ret);
+	bch_err_fn(c, ret);
 	return ret;
 err:
 fsck_err:
@@ -934,8 +1101,6 @@ int bch2_fs_initialize(struct bch_fs *c)
 	struct bch_inode_unpacked root_inode, lostfound_inode;
 	struct bkey_inode_buf packed_inode;
 	struct qstr lostfound = QSTR("lost+found");
-	struct bch_dev *ca;
-	unsigned i;
 	int ret;
 
 	bch_notice(c, "initializing new filesystem");
@@ -944,7 +1109,7 @@ int bch2_fs_initialize(struct bch_fs *c)
 	c->disk_sb.sb->compat[0] |= cpu_to_le64(1ULL << BCH_COMPAT_extents_above_btree_updates_done);
 	c->disk_sb.sb->compat[0] |= cpu_to_le64(1ULL << BCH_COMPAT_bformat_overflow_done);
 
-	bch2_sb_maybe_downgrade(c);
+	bch2_check_version_downgrade(c);
 
 	if (c->opts.version_upgrade != BCH_VERSION_UPGRADE_none) {
 		bch2_sb_upgrade(c, bcachefs_metadata_version_current);
@@ -954,13 +1119,12 @@ int bch2_fs_initialize(struct bch_fs *c)
 	mutex_unlock(&c->sb_lock);
 
 	c->curr_recovery_pass = ARRAY_SIZE(recovery_pass_fns);
-	set_bit(BCH_FS_MAY_GO_RW, &c->flags);
-	set_bit(BCH_FS_FSCK_DONE, &c->flags);
+	set_bit(BCH_FS_may_go_rw, &c->flags);
 
-	for (i = 0; i < BTREE_ID_NR; i++)
+	for (unsigned i = 0; i < BTREE_ID_NR; i++)
 		bch2_btree_root_alloc(c, i);
 
-	for_each_member_device(ca, c, i)
+	for_each_member_device(c, ca)
 		bch2_dev_usage_init(ca);
 
 	ret = bch2_fs_journal_alloc(c);
@@ -988,7 +1152,7 @@ int bch2_fs_initialize(struct bch_fs *c)
 	if (ret)
 		goto err;
 
-	for_each_online_member(ca, c, i)
+	for_each_online_member(c, ca)
 		ca->new_fs_bucket_idx = 0;
 
 	ret = bch2_fs_freespace_init(c);
@@ -1012,10 +1176,9 @@ int bch2_fs_initialize(struct bch_fs *c)
 	packed_inode.inode.k.p.snapshot = U32_MAX;
 
 	ret = bch2_btree_insert(c, BTREE_ID_inodes, &packed_inode.inode.k_i, NULL, 0);
-	if (ret) {
-		bch_err_msg(c, ret, "creating root directory");
+	bch_err_msg(c, ret, "creating root directory");
+	if (ret)
 		goto err;
-	}
 
 	bch2_inode_init_early(c, &lostfound_inode);
 
@@ -1026,10 +1189,11 @@ int bch2_fs_initialize(struct bch_fs *c)
 				  &lostfound,
 				  0, 0, S_IFDIR|0700, 0,
 				  NULL, NULL, (subvol_inum) { 0 }, 0));
-	if (ret) {
-		bch_err_msg(c, ret, "creating lost+found");
+	bch_err_msg(c, ret, "creating lost+found");
+	if (ret)
 		goto err;
-	}
+
+	c->recovery_pass_done = ARRAY_SIZE(recovery_pass_fns) - 1;
 
 	if (enabled_qtypes(c)) {
 		ret = bch2_fs_quota_read(c);
@@ -1038,10 +1202,9 @@ int bch2_fs_initialize(struct bch_fs *c)
 	}
 
 	ret = bch2_journal_flush(&c->journal);
-	if (ret) {
-		bch_err_msg(c, ret, "writing first journal entry");
+	bch_err_msg(c, ret, "writing first journal entry");
+	if (ret)
 		goto err;
-	}
 
 	mutex_lock(&c->sb_lock);
 	SET_BCH_SB_INITIALIZED(c->disk_sb.sb, true);
@@ -1052,6 +1215,6 @@ int bch2_fs_initialize(struct bch_fs *c)
 
 	return 0;
 err:
-	bch_err_fn(ca, ret);
+	bch_err_fn(c, ret);
 	return ret;
 }
diff --git a/fs/bcachefs/recovery.h b/fs/bcachefs/recovery.h
index 852d30567da9..4e9d24719b2e 100644
--- a/fs/bcachefs/recovery.h
+++ b/fs/bcachefs/recovery.h
@@ -4,12 +4,18 @@
 
 extern const char * const bch2_recovery_passes[];
 
+u64 bch2_recovery_passes_to_stable(u64 v);
+u64 bch2_recovery_passes_from_stable(u64 v);
+
 /*
  * For when we need to rewind recovery passes and run a pass we skipped:
  */
 static inline int bch2_run_explicit_recovery_pass(struct bch_fs *c,
 						  enum bch_recovery_pass pass)
 {
+	if (c->recovery_passes_explicit & BIT_ULL(pass))
+		return 0;
+
 	bch_info(c, "running explicit recovery pass %s (%u), currently at %s (%u)",
 		 bch2_recovery_passes[pass], pass,
 		 bch2_recovery_passes[c->curr_recovery_pass], c->curr_recovery_pass);
@@ -25,6 +31,7 @@ static inline int bch2_run_explicit_recovery_pass(struct bch_fs *c,
 	}
 }
 
+int bch2_run_online_recovery_passes(struct bch_fs *);
 u64 bch2_fsck_recovery_passes(void);
 
 int bch2_fs_recovery(struct bch_fs *);
diff --git a/fs/bcachefs/recovery_types.h b/fs/bcachefs/recovery_types.h
index 515e3d62c2ac..fa0c8efd2a1b 100644
--- a/fs/bcachefs/recovery_types.h
+++ b/fs/bcachefs/recovery_types.h
@@ -6,46 +6,59 @@
 #define PASS_FSCK		BIT(1)
 #define PASS_UNCLEAN		BIT(2)
 #define PASS_ALWAYS		BIT(3)
+#define PASS_ONLINE		BIT(4)
 
-#define BCH_RECOVERY_PASSES()									\
-	x(alloc_read,			PASS_ALWAYS)						\
-	x(stripes_read,			PASS_ALWAYS)						\
-	x(initialize_subvolumes,	0)							\
-	x(snapshots_read,		PASS_ALWAYS)						\
-	x(check_topology,		0)							\
-	x(check_allocations,		PASS_FSCK)						\
-	x(trans_mark_dev_sbs,		PASS_ALWAYS|PASS_SILENT)				\
-	x(fs_journal_alloc,		PASS_ALWAYS|PASS_SILENT)				\
-	x(set_may_go_rw,		PASS_ALWAYS|PASS_SILENT)				\
-	x(journal_replay,		PASS_ALWAYS)						\
-	x(check_alloc_info,		PASS_FSCK)						\
-	x(check_lrus,			PASS_FSCK)						\
-	x(check_btree_backpointers,	PASS_FSCK)						\
-	x(check_backpointers_to_extents,PASS_FSCK)						\
-	x(check_extents_to_backpointers,PASS_FSCK)						\
-	x(check_alloc_to_lru_refs,	PASS_FSCK)						\
-	x(fs_freespace_init,		PASS_ALWAYS|PASS_SILENT)				\
-	x(bucket_gens_init,		0)							\
-	x(check_snapshot_trees,		PASS_FSCK)						\
-	x(check_snapshots,		PASS_FSCK)						\
-	x(check_subvols,		PASS_FSCK)						\
-	x(delete_dead_snapshots,	PASS_FSCK)						\
-	x(fs_upgrade_for_subvolumes,	0)							\
-	x(resume_logged_ops,		PASS_ALWAYS)						\
-	x(check_inodes,			PASS_FSCK)						\
-	x(check_extents,		PASS_FSCK)						\
-	x(check_indirect_extents,	PASS_FSCK)						\
-	x(check_dirents,		PASS_FSCK)						\
-	x(check_xattrs,			PASS_FSCK)						\
-	x(check_root,			PASS_FSCK)						\
-	x(check_directory_structure,	PASS_FSCK)						\
-	x(check_nlinks,			PASS_FSCK)						\
-	x(delete_dead_inodes,		PASS_FSCK|PASS_UNCLEAN)					\
-	x(fix_reflink_p,		0)							\
-	x(set_fs_needs_rebalance,	0)							\
+/*
+ * Passes may be reordered, but the second field is a persistent identifier and
+ * must never change:
+ */
+#define BCH_RECOVERY_PASSES()							\
+	x(alloc_read,				 0, PASS_ALWAYS)		\
+	x(stripes_read,				 1, PASS_ALWAYS)		\
+	x(initialize_subvolumes,		 2, 0)				\
+	x(snapshots_read,			 3, PASS_ALWAYS)		\
+	x(check_topology,			 4, 0)				\
+	x(check_allocations,			 5, PASS_FSCK)			\
+	x(trans_mark_dev_sbs,			 6, PASS_ALWAYS|PASS_SILENT)	\
+	x(fs_journal_alloc,			 7, PASS_ALWAYS|PASS_SILENT)	\
+	x(set_may_go_rw,			 8, PASS_ALWAYS|PASS_SILENT)	\
+	x(journal_replay,			 9, PASS_ALWAYS)		\
+	x(check_alloc_info,			10, PASS_ONLINE|PASS_FSCK)	\
+	x(check_lrus,				11, PASS_ONLINE|PASS_FSCK)	\
+	x(check_btree_backpointers,		12, PASS_ONLINE|PASS_FSCK)	\
+	x(check_backpointers_to_extents,	13, PASS_ONLINE|PASS_FSCK)	\
+	x(check_extents_to_backpointers,	14, PASS_ONLINE|PASS_FSCK)	\
+	x(check_alloc_to_lru_refs,		15, PASS_ONLINE|PASS_FSCK)	\
+	x(fs_freespace_init,			16, PASS_ALWAYS|PASS_SILENT)	\
+	x(bucket_gens_init,			17, 0)				\
+	x(check_snapshot_trees,			18, PASS_ONLINE|PASS_FSCK)	\
+	x(check_snapshots,			19, PASS_ONLINE|PASS_FSCK)	\
+	x(check_subvols,			20, PASS_ONLINE|PASS_FSCK)	\
+	x(delete_dead_snapshots,		21, PASS_ONLINE|PASS_FSCK)	\
+	x(fs_upgrade_for_subvolumes,		22, 0)				\
+	x(resume_logged_ops,			23, PASS_ALWAYS)		\
+	x(check_inodes,				24, PASS_FSCK)			\
+	x(check_extents,			25, PASS_FSCK)			\
+	x(check_indirect_extents,		26, PASS_FSCK)			\
+	x(check_dirents,			27, PASS_FSCK)			\
+	x(check_xattrs,				28, PASS_FSCK)			\
+	x(check_root,				29, PASS_ONLINE|PASS_FSCK)	\
+	x(check_directory_structure,		30, PASS_ONLINE|PASS_FSCK)	\
+	x(check_nlinks,				31, PASS_FSCK)			\
+	x(delete_dead_inodes,			32, PASS_FSCK|PASS_UNCLEAN)	\
+	x(fix_reflink_p,			33, 0)				\
+	x(set_fs_needs_rebalance,		34, 0)				\
 
+/* We normally enumerate recovery passes in the order we run them: */
 enum bch_recovery_pass {
-#define x(n, when)	BCH_RECOVERY_PASS_##n,
+#define x(n, id, when)	BCH_RECOVERY_PASS_##n,
+	BCH_RECOVERY_PASSES()
+#undef x
+};
+
+/* But we also need stable identifiers that can be used in the superblock */
+enum bch_recovery_pass_stable {
+#define x(n, id, when)	BCH_RECOVERY_PASS_STABLE_##n = id,
 	BCH_RECOVERY_PASSES()
 #undef x
 };
diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c
index 6e1bfe9feb59..faa5d3670058 100644
--- a/fs/bcachefs/reflink.c
+++ b/fs/bcachefs/reflink.c
@@ -3,6 +3,7 @@
 #include "bkey_buf.h"
 #include "btree_update.h"
 #include "buckets.h"
+#include "error.h"
 #include "extents.h"
 #include "inode.h"
 #include "io_misc.h"
@@ -33,15 +34,14 @@ int bch2_reflink_p_invalid(struct bch_fs *c, struct bkey_s_c k,
 			   struct printbuf *err)
 {
 	struct bkey_s_c_reflink_p p = bkey_s_c_to_reflink_p(k);
+	int ret = 0;
 
-	if (c->sb.version >= bcachefs_metadata_version_reflink_p_fix &&
-	    le64_to_cpu(p.v->idx) < le32_to_cpu(p.v->front_pad)) {
-		prt_printf(err, "idx < front_pad (%llu < %u)",
-		       le64_to_cpu(p.v->idx), le32_to_cpu(p.v->front_pad));
-		return -EINVAL;
-	}
-
-	return 0;
+	bkey_fsck_err_on(le64_to_cpu(p.v->idx) < le32_to_cpu(p.v->front_pad),
+			 c, err, reflink_p_front_pad_bad,
+			 "idx < front_pad (%llu < %u)",
+			 le64_to_cpu(p.v->idx), le32_to_cpu(p.v->front_pad));
+fsck_err:
+	return ret;
 }
 
 void bch2_reflink_p_to_text(struct printbuf *out, struct bch_fs *c,
@@ -73,6 +73,184 @@ bool bch2_reflink_p_merge(struct bch_fs *c, struct bkey_s _l, struct bkey_s_c _r
 	return true;
 }
 
+static int trans_trigger_reflink_p_segment(struct btree_trans *trans,
+			struct bkey_s_c_reflink_p p,
+			u64 *idx, unsigned flags)
+{
+	struct bch_fs *c = trans->c;
+	struct btree_iter iter;
+	struct bkey_i *k;
+	__le64 *refcount;
+	int add = !(flags & BTREE_TRIGGER_OVERWRITE) ? 1 : -1;
+	struct printbuf buf = PRINTBUF;
+	int ret;
+
+	k = bch2_bkey_get_mut_noupdate(trans, &iter,
+			BTREE_ID_reflink, POS(0, *idx),
+			BTREE_ITER_WITH_UPDATES);
+	ret = PTR_ERR_OR_ZERO(k);
+	if (ret)
+		goto err;
+
+	refcount = bkey_refcount(bkey_i_to_s(k));
+	if (!refcount) {
+		bch2_bkey_val_to_text(&buf, c, p.s_c);
+		bch2_trans_inconsistent(trans,
+			"nonexistent indirect extent at %llu while marking\n  %s",
+			*idx, buf.buf);
+		ret = -EIO;
+		goto err;
+	}
+
+	if (!*refcount && (flags & BTREE_TRIGGER_OVERWRITE)) {
+		bch2_bkey_val_to_text(&buf, c, p.s_c);
+		bch2_trans_inconsistent(trans,
+			"indirect extent refcount underflow at %llu while marking\n  %s",
+			*idx, buf.buf);
+		ret = -EIO;
+		goto err;
+	}
+
+	if (flags & BTREE_TRIGGER_INSERT) {
+		struct bch_reflink_p *v = (struct bch_reflink_p *) p.v;
+		u64 pad;
+
+		pad = max_t(s64, le32_to_cpu(v->front_pad),
+			    le64_to_cpu(v->idx) - bkey_start_offset(&k->k));
+		BUG_ON(pad > U32_MAX);
+		v->front_pad = cpu_to_le32(pad);
+
+		pad = max_t(s64, le32_to_cpu(v->back_pad),
+			    k->k.p.offset - p.k->size - le64_to_cpu(v->idx));
+		BUG_ON(pad > U32_MAX);
+		v->back_pad = cpu_to_le32(pad);
+	}
+
+	le64_add_cpu(refcount, add);
+
+	bch2_btree_iter_set_pos_to_extent_start(&iter);
+	ret = bch2_trans_update(trans, &iter, k, 0);
+	if (ret)
+		goto err;
+
+	*idx = k->k.p.offset;
+err:
+	bch2_trans_iter_exit(trans, &iter);
+	printbuf_exit(&buf);
+	return ret;
+}
+
+static s64 gc_trigger_reflink_p_segment(struct btree_trans *trans,
+				struct bkey_s_c_reflink_p p,
+				u64 *idx, unsigned flags, size_t r_idx)
+{
+	struct bch_fs *c = trans->c;
+	struct reflink_gc *r;
+	int add = !(flags & BTREE_TRIGGER_OVERWRITE) ? 1 : -1;
+	u64 start = le64_to_cpu(p.v->idx);
+	u64 end = le64_to_cpu(p.v->idx) + p.k->size;
+	u64 next_idx = end + le32_to_cpu(p.v->back_pad);
+	s64 ret = 0;
+	struct printbuf buf = PRINTBUF;
+
+	if (r_idx >= c->reflink_gc_nr)
+		goto not_found;
+
+	r = genradix_ptr(&c->reflink_gc_table, r_idx);
+	next_idx = min(next_idx, r->offset - r->size);
+	if (*idx < next_idx)
+		goto not_found;
+
+	BUG_ON((s64) r->refcount + add < 0);
+
+	r->refcount += add;
+	*idx = r->offset;
+	return 0;
+not_found:
+	if (fsck_err(c, reflink_p_to_missing_reflink_v,
+		     "pointer to missing indirect extent\n"
+		     "  %s\n"
+		     "  missing range %llu-%llu",
+		     (bch2_bkey_val_to_text(&buf, c, p.s_c), buf.buf),
+		     *idx, next_idx)) {
+		struct bkey_i *update = bch2_bkey_make_mut_noupdate(trans, p.s_c);
+		ret = PTR_ERR_OR_ZERO(update);
+		if (ret)
+			goto err;
+
+		if (next_idx <= start) {
+			bkey_i_to_reflink_p(update)->v.front_pad = cpu_to_le32(start - next_idx);
+		} else if (*idx >= end) {
+			bkey_i_to_reflink_p(update)->v.back_pad = cpu_to_le32(*idx - end);
+		} else {
+			bkey_error_init(update);
+			update->k.p		= p.k->p;
+			update->k.p.offset	= next_idx;
+			update->k.size		= next_idx - *idx;
+			set_bkey_val_u64s(&update->k, 0);
+		}
+
+		ret = bch2_btree_insert_trans(trans, BTREE_ID_extents, update, BTREE_TRIGGER_NORUN);
+	}
+
+	*idx = next_idx;
+err:
+fsck_err:
+	printbuf_exit(&buf);
+	return ret;
+}
+
+static int __trigger_reflink_p(struct btree_trans *trans,
+			    enum btree_id btree_id, unsigned level,
+			    struct bkey_s_c k, unsigned flags)
+{
+	struct bch_fs *c = trans->c;
+	struct bkey_s_c_reflink_p p = bkey_s_c_to_reflink_p(k);
+	int ret = 0;
+
+	u64 idx = le64_to_cpu(p.v->idx) - le32_to_cpu(p.v->front_pad);
+	u64 end = le64_to_cpu(p.v->idx) + p.k->size + le32_to_cpu(p.v->back_pad);
+
+	if (flags & BTREE_TRIGGER_TRANSACTIONAL) {
+		while (idx < end && !ret)
+			ret = trans_trigger_reflink_p_segment(trans, p, &idx, flags);
+	}
+
+	if (flags & BTREE_TRIGGER_GC) {
+		size_t l = 0, r = c->reflink_gc_nr;
+
+		while (l < r) {
+			size_t m = l + (r - l) / 2;
+			struct reflink_gc *ref = genradix_ptr(&c->reflink_gc_table, m);
+			if (ref->offset <= idx)
+				l = m + 1;
+			else
+				r = m;
+		}
+
+		while (idx < end && !ret)
+			ret = gc_trigger_reflink_p_segment(trans, p, &idx, flags, l++);
+	}
+
+	return ret;
+}
+
+int bch2_trigger_reflink_p(struct btree_trans *trans,
+			   enum btree_id btree_id, unsigned level,
+			   struct bkey_s_c old,
+			   struct bkey_s new,
+			   unsigned flags)
+{
+	if ((flags & BTREE_TRIGGER_TRANSACTIONAL) &&
+	    (flags & BTREE_TRIGGER_INSERT)) {
+		struct bch_reflink_p *v = bkey_s_to_reflink_p(new).v;
+
+		v->front_pad = v->back_pad = 0;
+	}
+
+	return trigger_run_overwrite_then_insert(__trigger_reflink_p, trans, btree_id, level, old, new, flags);
+}
+
 /* indirect extents */
 
 int bch2_reflink_v_invalid(struct bch_fs *c, struct bkey_s_c k,
@@ -104,24 +282,26 @@ bool bch2_reflink_v_merge(struct bch_fs *c, struct bkey_s _l, struct bkey_s_c _r
 }
 #endif
 
-static inline void check_indirect_extent_deleting(struct bkey_i *new, unsigned *flags)
+static inline void check_indirect_extent_deleting(struct bkey_s new, unsigned *flags)
 {
 	if ((*flags & BTREE_TRIGGER_INSERT) && !*bkey_refcount(new)) {
-		new->k.type = KEY_TYPE_deleted;
-		new->k.size = 0;
-		set_bkey_val_u64s(&new->k, 0);;
+		new.k->type = KEY_TYPE_deleted;
+		new.k->size = 0;
+		set_bkey_val_u64s(new.k, 0);
 		*flags &= ~BTREE_TRIGGER_INSERT;
 	}
 }
 
 int bch2_trans_mark_reflink_v(struct btree_trans *trans,
 			      enum btree_id btree_id, unsigned level,
-			      struct bkey_s_c old, struct bkey_i *new,
+			      struct bkey_s_c old, struct bkey_s new,
 			      unsigned flags)
 {
-	check_indirect_extent_deleting(new, &flags);
+	if ((flags & BTREE_TRIGGER_TRANSACTIONAL) &&
+	    (flags & BTREE_TRIGGER_INSERT))
+		check_indirect_extent_deleting(new, &flags);
 
-	return bch2_trans_mark_extent(trans, btree_id, level, old, new, flags);
+	return bch2_trigger_extent(trans, btree_id, level, old, new, flags);
 }
 
 /* indirect inline data */
@@ -146,7 +326,7 @@ void bch2_indirect_inline_data_to_text(struct printbuf *out,
 
 int bch2_trans_mark_indirect_inline_data(struct btree_trans *trans,
 			      enum btree_id btree_id, unsigned level,
-			      struct bkey_s_c old, struct bkey_i *new,
+			      struct bkey_s_c old, struct bkey_s new,
 			      unsigned flags)
 {
 	check_indirect_extent_deleting(new, &flags);
@@ -189,7 +369,7 @@ static int bch2_make_extent_indirect(struct btree_trans *trans,
 
 	set_bkey_val_bytes(&r_v->k, sizeof(__le64) + bkey_val_bytes(&orig->k));
 
-	refcount	= bkey_refcount(r_v);
+	refcount	= bkey_refcount(bkey_i_to_s(r_v));
 	*refcount	= 0;
 	memcpy(refcount + 1, &orig->v, bkey_val_bytes(&orig->k));
 
@@ -390,7 +570,7 @@ s64 bch2_remap_range(struct bch_fs *c,
 			inode_u.bi_size = new_i_size;
 			ret2  = bch2_inode_write(trans, &inode_iter, &inode_u) ?:
 				bch2_trans_commit(trans, NULL, NULL,
-						  BTREE_INSERT_NOFAIL);
+						  BCH_TRANS_COMMIT_no_enospc);
 		}
 
 		bch2_trans_iter_exit(trans, &inode_iter);
diff --git a/fs/bcachefs/reflink.h b/fs/bcachefs/reflink.h
index 8ccf3f9c4939..8ee778ec0022 100644
--- a/fs/bcachefs/reflink.h
+++ b/fs/bcachefs/reflink.h
@@ -9,13 +9,14 @@ int bch2_reflink_p_invalid(struct bch_fs *, struct bkey_s_c,
 void bch2_reflink_p_to_text(struct printbuf *, struct bch_fs *,
 			    struct bkey_s_c);
 bool bch2_reflink_p_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c);
+int bch2_trigger_reflink_p(struct btree_trans *, enum btree_id, unsigned,
+			   struct bkey_s_c, struct bkey_s, unsigned);
 
 #define bch2_bkey_ops_reflink_p ((struct bkey_ops) {		\
 	.key_invalid	= bch2_reflink_p_invalid,		\
 	.val_to_text	= bch2_reflink_p_to_text,		\
 	.key_merge	= bch2_reflink_p_merge,			\
-	.trans_trigger	= bch2_trans_mark_reflink_p,		\
-	.atomic_trigger	= bch2_mark_reflink_p,			\
+	.trigger	= bch2_trigger_reflink_p,		\
 	.min_val_size	= 16,					\
 })
 
@@ -24,14 +25,13 @@ int bch2_reflink_v_invalid(struct bch_fs *, struct bkey_s_c,
 void bch2_reflink_v_to_text(struct printbuf *, struct bch_fs *,
 			    struct bkey_s_c);
 int bch2_trans_mark_reflink_v(struct btree_trans *, enum btree_id, unsigned,
-			      struct bkey_s_c, struct bkey_i *, unsigned);
+			      struct bkey_s_c, struct bkey_s, unsigned);
 
 #define bch2_bkey_ops_reflink_v ((struct bkey_ops) {		\
 	.key_invalid	= bch2_reflink_v_invalid,		\
 	.val_to_text	= bch2_reflink_v_to_text,		\
 	.swab		= bch2_ptr_swab,			\
-	.trans_trigger	= bch2_trans_mark_reflink_v,		\
-	.atomic_trigger	= bch2_mark_extent,			\
+	.trigger	= bch2_trans_mark_reflink_v,		\
 	.min_val_size	= 8,					\
 })
 
@@ -41,13 +41,13 @@ void bch2_indirect_inline_data_to_text(struct printbuf *,
 				struct bch_fs *, struct bkey_s_c);
 int bch2_trans_mark_indirect_inline_data(struct btree_trans *,
 					 enum btree_id, unsigned,
-			      struct bkey_s_c, struct bkey_i *,
+			      struct bkey_s_c, struct bkey_s,
 			      unsigned);
 
 #define bch2_bkey_ops_indirect_inline_data ((struct bkey_ops) {	\
 	.key_invalid	= bch2_indirect_inline_data_invalid,	\
 	.val_to_text	= bch2_indirect_inline_data_to_text,	\
-	.trans_trigger	= bch2_trans_mark_indirect_inline_data,	\
+	.trigger	= bch2_trans_mark_indirect_inline_data,	\
 	.min_val_size	= 8,					\
 })
 
@@ -63,13 +63,13 @@ static inline const __le64 *bkey_refcount_c(struct bkey_s_c k)
 	}
 }
 
-static inline __le64 *bkey_refcount(struct bkey_i *k)
+static inline __le64 *bkey_refcount(struct bkey_s k)
 {
-	switch (k->k.type) {
+	switch (k.k->type) {
 	case KEY_TYPE_reflink_v:
-		return &bkey_i_to_reflink_v(k)->v.refcount;
+		return &bkey_s_to_reflink_v(k).v->refcount;
 	case KEY_TYPE_indirect_inline_data:
-		return &bkey_i_to_indirect_inline_data(k)->v.refcount;
+		return &bkey_s_to_indirect_inline_data(k).v->refcount;
 	default:
 		return NULL;
 	}
diff --git a/fs/bcachefs/replicas.c b/fs/bcachefs/replicas.c
index 1c3ae13bfced..92ba56ef1fc8 100644
--- a/fs/bcachefs/replicas.c
+++ b/fs/bcachefs/replicas.c
@@ -11,7 +11,7 @@ static int bch2_cpu_replicas_to_sb_replicas(struct bch_fs *,
 
 /* Replicas tracking - in memory: */
 
-static void verify_replicas_entry(struct bch_replicas_entry *e)
+static void verify_replicas_entry(struct bch_replicas_entry_v1 *e)
 {
 #ifdef CONFIG_BCACHEFS_DEBUG
 	unsigned i;
@@ -26,7 +26,7 @@ static void verify_replicas_entry(struct bch_replicas_entry *e)
 #endif
 }
 
-void bch2_replicas_entry_sort(struct bch_replicas_entry *e)
+void bch2_replicas_entry_sort(struct bch_replicas_entry_v1 *e)
 {
 	bubble_sort(e->devs, e->nr_devs, u8_cmp);
 }
@@ -53,7 +53,7 @@ static void bch2_replicas_entry_v0_to_text(struct printbuf *out,
 }
 
 void bch2_replicas_entry_to_text(struct printbuf *out,
-				 struct bch_replicas_entry *e)
+				 struct bch_replicas_entry_v1 *e)
 {
 	unsigned i;
 
@@ -68,10 +68,37 @@ void bch2_replicas_entry_to_text(struct printbuf *out,
 	prt_printf(out, "]");
 }
 
+int bch2_replicas_entry_validate(struct bch_replicas_entry_v1 *r,
+				 struct bch_sb *sb,
+				 struct printbuf *err)
+{
+	if (!r->nr_devs) {
+		prt_printf(err, "no devices in entry ");
+		goto bad;
+	}
+
+	if (r->nr_required > 1 &&
+	    r->nr_required >= r->nr_devs) {
+		prt_printf(err, "bad nr_required in entry ");
+		goto bad;
+	}
+
+	for (unsigned i = 0; i < r->nr_devs; i++)
+		if (!bch2_dev_exists(sb, r->devs[i])) {
+			prt_printf(err, "invalid device %u in entry ", r->devs[i]);
+			goto bad;
+		}
+
+	return 0;
+bad:
+	bch2_replicas_entry_to_text(err, r);
+	return -BCH_ERR_invalid_replicas_entry;
+}
+
 void bch2_cpu_replicas_to_text(struct printbuf *out,
 			       struct bch_replicas_cpu *r)
 {
-	struct bch_replicas_entry *e;
+	struct bch_replicas_entry_v1 *e;
 	bool first = true;
 
 	for_each_cpu_replicas_entry(r, e) {
@@ -84,7 +111,7 @@ void bch2_cpu_replicas_to_text(struct printbuf *out,
 }
 
 static void extent_to_replicas(struct bkey_s_c k,
-			       struct bch_replicas_entry *r)
+			       struct bch_replicas_entry_v1 *r)
 {
 	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
 	const union bch_extent_entry *entry;
@@ -104,7 +131,7 @@ static void extent_to_replicas(struct bkey_s_c k,
 }
 
 static void stripe_to_replicas(struct bkey_s_c k,
-			       struct bch_replicas_entry *r)
+			       struct bch_replicas_entry_v1 *r)
 {
 	struct bkey_s_c_stripe s = bkey_s_c_to_stripe(k);
 	const struct bch_extent_ptr *ptr;
@@ -117,7 +144,7 @@ static void stripe_to_replicas(struct bkey_s_c k,
 		r->devs[r->nr_devs++] = ptr->dev;
 }
 
-void bch2_bkey_to_replicas(struct bch_replicas_entry *e,
+void bch2_bkey_to_replicas(struct bch_replicas_entry_v1 *e,
 			   struct bkey_s_c k)
 {
 	e->nr_devs = 0;
@@ -142,12 +169,10 @@ void bch2_bkey_to_replicas(struct bch_replicas_entry *e,
 	bch2_replicas_entry_sort(e);
 }
 
-void bch2_devlist_to_replicas(struct bch_replicas_entry *e,
+void bch2_devlist_to_replicas(struct bch_replicas_entry_v1 *e,
 			      enum bch_data_type data_type,
 			      struct bch_devs_list devs)
 {
-	unsigned i;
-
 	BUG_ON(!data_type ||
 	       data_type == BCH_DATA_sb ||
 	       data_type >= BCH_DATA_NR);
@@ -156,15 +181,16 @@ void bch2_devlist_to_replicas(struct bch_replicas_entry *e,
 	e->nr_devs	= 0;
 	e->nr_required	= 1;
 
-	for (i = 0; i < devs.nr; i++)
-		e->devs[e->nr_devs++] = devs.devs[i];
+	darray_for_each(devs, i)
+		e->devs[e->nr_devs++] = *i;
 
 	bch2_replicas_entry_sort(e);
 }
 
 static struct bch_replicas_cpu
-cpu_replicas_add_entry(struct bch_replicas_cpu *old,
-		       struct bch_replicas_entry *new_entry)
+cpu_replicas_add_entry(struct bch_fs *c,
+		       struct bch_replicas_cpu *old,
+		       struct bch_replicas_entry_v1 *new_entry)
 {
 	unsigned i;
 	struct bch_replicas_cpu new = {
@@ -173,6 +199,9 @@ cpu_replicas_add_entry(struct bch_replicas_cpu *old,
 					replicas_entry_bytes(new_entry)),
 	};
 
+	for (i = 0; i < new_entry->nr_devs; i++)
+		BUG_ON(!bch2_dev_exists2(c, new_entry->devs[i]));
+
 	BUG_ON(!new_entry->data_type);
 	verify_replicas_entry(new_entry);
 
@@ -194,7 +223,7 @@ cpu_replicas_add_entry(struct bch_replicas_cpu *old,
 }
 
 static inline int __replicas_entry_idx(struct bch_replicas_cpu *r,
-				       struct bch_replicas_entry *search)
+				       struct bch_replicas_entry_v1 *search)
 {
 	int idx, entry_size = replicas_entry_bytes(search);
 
@@ -212,7 +241,7 @@ static inline int __replicas_entry_idx(struct bch_replicas_cpu *r,
 }
 
 int bch2_replicas_entry_idx(struct bch_fs *c,
-			    struct bch_replicas_entry *search)
+			    struct bch_replicas_entry_v1 *search)
 {
 	bch2_replicas_entry_sort(search);
 
@@ -220,13 +249,13 @@ int bch2_replicas_entry_idx(struct bch_fs *c,
 }
 
 static bool __replicas_has_entry(struct bch_replicas_cpu *r,
-				 struct bch_replicas_entry *search)
+				 struct bch_replicas_entry_v1 *search)
 {
 	return __replicas_entry_idx(r, search) >= 0;
 }
 
 bool bch2_replicas_marked(struct bch_fs *c,
-			  struct bch_replicas_entry *search)
+			  struct bch_replicas_entry_v1 *search)
 {
 	bool marked;
 
@@ -343,7 +372,7 @@ err:
 static unsigned reserve_journal_replicas(struct bch_fs *c,
 				     struct bch_replicas_cpu *r)
 {
-	struct bch_replicas_entry *e;
+	struct bch_replicas_entry_v1 *e;
 	unsigned journal_res_u64s = 0;
 
 	/* nr_inodes: */
@@ -368,7 +397,7 @@ static unsigned reserve_journal_replicas(struct bch_fs *c,
 
 noinline
 static int bch2_mark_replicas_slowpath(struct bch_fs *c,
-				struct bch_replicas_entry *new_entry)
+				struct bch_replicas_entry_v1 *new_entry)
 {
 	struct bch_replicas_cpu new_r, new_gc;
 	int ret = 0;
@@ -382,7 +411,7 @@ static int bch2_mark_replicas_slowpath(struct bch_fs *c,
 
 	if (c->replicas_gc.entries &&
 	    !__replicas_has_entry(&c->replicas_gc, new_entry)) {
-		new_gc = cpu_replicas_add_entry(&c->replicas_gc, new_entry);
+		new_gc = cpu_replicas_add_entry(c, &c->replicas_gc, new_entry);
 		if (!new_gc.entries) {
 			ret = -BCH_ERR_ENOMEM_cpu_replicas;
 			goto err;
@@ -390,7 +419,7 @@ static int bch2_mark_replicas_slowpath(struct bch_fs *c,
 	}
 
 	if (!__replicas_has_entry(&c->replicas, new_entry)) {
-		new_r = cpu_replicas_add_entry(&c->replicas, new_entry);
+		new_r = cpu_replicas_add_entry(c, &c->replicas, new_entry);
 		if (!new_r.entries) {
 			ret = -BCH_ERR_ENOMEM_cpu_replicas;
 			goto err;
@@ -433,7 +462,7 @@ err:
 	goto out;
 }
 
-int bch2_mark_replicas(struct bch_fs *c, struct bch_replicas_entry *r)
+int bch2_mark_replicas(struct bch_fs *c, struct bch_replicas_entry_v1 *r)
 {
 	return likely(bch2_replicas_marked(c, r))
 		? 0 : bch2_mark_replicas_slowpath(c, r);
@@ -484,7 +513,7 @@ int bch2_replicas_gc_end(struct bch_fs *c, int ret)
 
 int bch2_replicas_gc_start(struct bch_fs *c, unsigned typemask)
 {
-	struct bch_replicas_entry *e;
+	struct bch_replicas_entry_v1 *e;
 	unsigned i = 0;
 
 	lockdep_assert_held(&c->replicas_gc_lock);
@@ -559,7 +588,7 @@ retry:
 	}
 
 	for (i = 0; i < c->replicas.nr; i++) {
-		struct bch_replicas_entry *e =
+		struct bch_replicas_entry_v1 *e =
 			cpu_replicas_entry(&c->replicas, i);
 
 		if (e->data_type == BCH_DATA_journal ||
@@ -590,7 +619,7 @@ retry:
 }
 
 int bch2_replicas_set_usage(struct bch_fs *c,
-			    struct bch_replicas_entry *r,
+			    struct bch_replicas_entry_v1 *r,
 			    u64 sectors)
 {
 	int ret, idx = bch2_replicas_entry_idx(c, r);
@@ -598,7 +627,7 @@ int bch2_replicas_set_usage(struct bch_fs *c,
 	if (idx < 0) {
 		struct bch_replicas_cpu n;
 
-		n = cpu_replicas_add_entry(&c->replicas, r);
+		n = cpu_replicas_add_entry(c, &c->replicas, r);
 		if (!n.entries)
 			return -BCH_ERR_ENOMEM_cpu_replicas;
 
@@ -623,7 +652,7 @@ static int
 __bch2_sb_replicas_to_cpu_replicas(struct bch_sb_field_replicas *sb_r,
 				   struct bch_replicas_cpu *cpu_r)
 {
-	struct bch_replicas_entry *e, *dst;
+	struct bch_replicas_entry_v1 *e, *dst;
 	unsigned nr = 0, entry_size = 0, idx = 0;
 
 	for_each_replicas_entry(sb_r, e) {
@@ -661,7 +690,7 @@ __bch2_sb_replicas_v0_to_cpu_replicas(struct bch_sb_field_replicas_v0 *sb_r,
 		nr++;
 	}
 
-	entry_size += sizeof(struct bch_replicas_entry) -
+	entry_size += sizeof(struct bch_replicas_entry_v1) -
 		sizeof(struct bch_replicas_entry_v0);
 
 	cpu_r->entries = kcalloc(nr, entry_size, GFP_KERNEL);
@@ -672,7 +701,7 @@ __bch2_sb_replicas_v0_to_cpu_replicas(struct bch_sb_field_replicas_v0 *sb_r,
 	cpu_r->entry_size	= entry_size;
 
 	for_each_replicas_entry(sb_r, e) {
-		struct bch_replicas_entry *dst =
+		struct bch_replicas_entry_v1 *dst =
 			cpu_replicas_entry(cpu_r, idx++);
 
 		dst->data_type	= e->data_type;
@@ -716,7 +745,7 @@ static int bch2_cpu_replicas_to_sb_replicas_v0(struct bch_fs *c,
 {
 	struct bch_sb_field_replicas_v0 *sb_r;
 	struct bch_replicas_entry_v0 *dst;
-	struct bch_replicas_entry *src;
+	struct bch_replicas_entry_v1 *src;
 	size_t bytes;
 
 	bytes = sizeof(struct bch_sb_field_replicas);
@@ -754,7 +783,7 @@ static int bch2_cpu_replicas_to_sb_replicas(struct bch_fs *c,
 					    struct bch_replicas_cpu *r)
 {
 	struct bch_sb_field_replicas *sb_r;
-	struct bch_replicas_entry *dst, *src;
+	struct bch_replicas_entry_v1 *dst, *src;
 	bool need_v1 = false;
 	size_t bytes;
 
@@ -797,7 +826,7 @@ static int bch2_cpu_replicas_validate(struct bch_replicas_cpu *cpu_r,
 				      struct bch_sb *sb,
 				      struct printbuf *err)
 {
-	unsigned i, j;
+	unsigned i;
 
 	sort_cmp_size(cpu_r->entries,
 		      cpu_r->nr,
@@ -805,37 +834,15 @@ static int bch2_cpu_replicas_validate(struct bch_replicas_cpu *cpu_r,
 		      memcmp, NULL);
 
 	for (i = 0; i < cpu_r->nr; i++) {
-		struct bch_replicas_entry *e =
+		struct bch_replicas_entry_v1 *e =
 			cpu_replicas_entry(cpu_r, i);
 
-		if (e->data_type >= BCH_DATA_NR) {
-			prt_printf(err, "invalid data type in entry ");
-			bch2_replicas_entry_to_text(err, e);
-			return -BCH_ERR_invalid_sb_replicas;
-		}
-
-		if (!e->nr_devs) {
-			prt_printf(err, "no devices in entry ");
-			bch2_replicas_entry_to_text(err, e);
-			return -BCH_ERR_invalid_sb_replicas;
-		}
-
-		if (e->nr_required > 1 &&
-		    e->nr_required >= e->nr_devs) {
-			prt_printf(err, "bad nr_required in entry ");
-			bch2_replicas_entry_to_text(err, e);
-			return -BCH_ERR_invalid_sb_replicas;
-		}
-
-		for (j = 0; j < e->nr_devs; j++)
-			if (!bch2_dev_exists(sb, e->devs[j])) {
-				prt_printf(err, "invalid device %u in entry ", e->devs[j]);
-				bch2_replicas_entry_to_text(err, e);
-				return -BCH_ERR_invalid_sb_replicas;
-			}
+		int ret = bch2_replicas_entry_validate(e, sb, err);
+		if (ret)
+			return ret;
 
 		if (i + 1 < cpu_r->nr) {
-			struct bch_replicas_entry *n =
+			struct bch_replicas_entry_v1 *n =
 				cpu_replicas_entry(cpu_r, i + 1);
 
 			BUG_ON(memcmp(e, n, cpu_r->entry_size) > 0);
@@ -872,7 +879,7 @@ static void bch2_sb_replicas_to_text(struct printbuf *out,
 				     struct bch_sb_field *f)
 {
 	struct bch_sb_field_replicas *r = field_to_type(f, replicas);
-	struct bch_replicas_entry *e;
+	struct bch_replicas_entry_v1 *e;
 	bool first = true;
 
 	for_each_replicas_entry(r, e) {
@@ -934,7 +941,7 @@ const struct bch_sb_field_ops bch_sb_field_ops_replicas_v0 = {
 bool bch2_have_enough_devs(struct bch_fs *c, struct bch_devs_mask devs,
 			   unsigned flags, bool print)
 {
-	struct bch_replicas_entry *e;
+	struct bch_replicas_entry_v1 *e;
 	bool ret = true;
 
 	percpu_down_read(&c->mark_lock);
@@ -994,7 +1001,7 @@ unsigned bch2_sb_dev_has_data(struct bch_sb *sb, unsigned dev)
 	replicas_v0 = bch2_sb_field_get(sb, replicas_v0);
 
 	if (replicas) {
-		struct bch_replicas_entry *r;
+		struct bch_replicas_entry_v1 *r;
 
 		for_each_replicas_entry(replicas, r)
 			for (i = 0; i < r->nr_devs; i++)
diff --git a/fs/bcachefs/replicas.h b/fs/bcachefs/replicas.h
index 4887675a86f0..654a4b26d3a3 100644
--- a/fs/bcachefs/replicas.h
+++ b/fs/bcachefs/replicas.h
@@ -6,26 +6,28 @@
 #include "eytzinger.h"
 #include "replicas_types.h"
 
-void bch2_replicas_entry_sort(struct bch_replicas_entry *);
+void bch2_replicas_entry_sort(struct bch_replicas_entry_v1 *);
 void bch2_replicas_entry_to_text(struct printbuf *,
-				 struct bch_replicas_entry *);
+				 struct bch_replicas_entry_v1 *);
+int bch2_replicas_entry_validate(struct bch_replicas_entry_v1 *,
+				 struct bch_sb *, struct printbuf *);
 void bch2_cpu_replicas_to_text(struct printbuf *, struct bch_replicas_cpu *);
 
-static inline struct bch_replicas_entry *
+static inline struct bch_replicas_entry_v1 *
 cpu_replicas_entry(struct bch_replicas_cpu *r, unsigned i)
 {
 	return (void *) r->entries + r->entry_size * i;
 }
 
 int bch2_replicas_entry_idx(struct bch_fs *,
-			    struct bch_replicas_entry *);
+			    struct bch_replicas_entry_v1 *);
 
-void bch2_devlist_to_replicas(struct bch_replicas_entry *,
+void bch2_devlist_to_replicas(struct bch_replicas_entry_v1 *,
 			      enum bch_data_type,
 			      struct bch_devs_list);
-bool bch2_replicas_marked(struct bch_fs *, struct bch_replicas_entry *);
+bool bch2_replicas_marked(struct bch_fs *, struct bch_replicas_entry_v1 *);
 int bch2_mark_replicas(struct bch_fs *,
-		       struct bch_replicas_entry *);
+		       struct bch_replicas_entry_v1 *);
 
 static inline struct replicas_delta *
 replicas_delta_next(struct replicas_delta *d)
@@ -35,9 +37,9 @@ replicas_delta_next(struct replicas_delta *d)
 
 int bch2_replicas_delta_list_mark(struct bch_fs *, struct replicas_delta_list *);
 
-void bch2_bkey_to_replicas(struct bch_replicas_entry *, struct bkey_s_c);
+void bch2_bkey_to_replicas(struct bch_replicas_entry_v1 *, struct bkey_s_c);
 
-static inline void bch2_replicas_entry_cached(struct bch_replicas_entry *e,
+static inline void bch2_replicas_entry_cached(struct bch_replicas_entry_v1 *e,
 					      unsigned dev)
 {
 	e->data_type	= BCH_DATA_cached;
@@ -57,7 +59,7 @@ int bch2_replicas_gc_start(struct bch_fs *, unsigned);
 int bch2_replicas_gc2(struct bch_fs *);
 
 int bch2_replicas_set_usage(struct bch_fs *,
-			    struct bch_replicas_entry *,
+			    struct bch_replicas_entry_v1 *,
 			    u64);
 
 #define for_each_cpu_replicas_entry(_r, _i)				\
diff --git a/fs/bcachefs/replicas_types.h b/fs/bcachefs/replicas_types.h
index 5cfff489bbc3..ac90d142c4e8 100644
--- a/fs/bcachefs/replicas_types.h
+++ b/fs/bcachefs/replicas_types.h
@@ -5,12 +5,12 @@
 struct bch_replicas_cpu {
 	unsigned		nr;
 	unsigned		entry_size;
-	struct bch_replicas_entry *entries;
+	struct bch_replicas_entry_v1 *entries;
 };
 
 struct replicas_delta {
 	s64			delta;
-	struct bch_replicas_entry r;
+	struct bch_replicas_entry_v1 r;
 } __packed;
 
 struct replicas_delta_list {
@@ -21,7 +21,7 @@ struct replicas_delta_list {
 	u64			nr_inodes;
 	u64			persistent_reserved[BCH_REPLICAS_MAX];
 	struct			{} memset_end;
-	struct replicas_delta	d[0];
+	struct replicas_delta	d[];
 };
 
 #endif /* _BCACHEFS_REPLICAS_TYPES_H */
diff --git a/fs/bcachefs/sb-clean.c b/fs/bcachefs/sb-clean.c
index e151ada1c8bd..9632f36f5f31 100644
--- a/fs/bcachefs/sb-clean.c
+++ b/fs/bcachefs/sb-clean.c
@@ -191,13 +191,10 @@ void bch2_journal_super_entries_add_common(struct bch_fs *c,
 					   struct jset_entry **end,
 					   u64 journal_seq)
 {
-	struct bch_dev *ca;
-	unsigned i, dev;
-
 	percpu_down_read(&c->mark_lock);
 
 	if (!journal_seq) {
-		for (i = 0; i < ARRAY_SIZE(c->usage); i++)
+		for (unsigned i = 0; i < ARRAY_SIZE(c->usage); i++)
 			bch2_fs_usage_acc_to_base(c, i);
 	} else {
 		bch2_fs_usage_acc_to_base(c, journal_seq & JOURNAL_BUF_MASK);
@@ -223,7 +220,7 @@ void bch2_journal_super_entries_add_common(struct bch_fs *c,
 		u->v		= cpu_to_le64(atomic64_read(&c->key_version));
 	}
 
-	for (i = 0; i < BCH_REPLICAS_MAX; i++) {
+	for (unsigned i = 0; i < BCH_REPLICAS_MAX; i++) {
 		struct jset_entry_usage *u =
 			container_of(jset_entry_init(end, sizeof(*u)),
 				     struct jset_entry_usage, entry);
@@ -234,8 +231,8 @@ void bch2_journal_super_entries_add_common(struct bch_fs *c,
 		u->v		= cpu_to_le64(c->usage_base->persistent_reserved[i]);
 	}
 
-	for (i = 0; i < c->replicas.nr; i++) {
-		struct bch_replicas_entry *e =
+	for (unsigned i = 0; i < c->replicas.nr; i++) {
+		struct bch_replicas_entry_v1 *e =
 			cpu_replicas_entry(&c->replicas, i);
 		struct jset_entry_data_usage *u =
 			container_of(jset_entry_init(end, sizeof(*u) + e->nr_devs),
@@ -247,7 +244,7 @@ void bch2_journal_super_entries_add_common(struct bch_fs *c,
 			      "embedded variable length struct");
 	}
 
-	for_each_member_device(ca, c, dev) {
+	for_each_member_device(c, ca) {
 		unsigned b = sizeof(struct jset_entry_dev_usage) +
 			sizeof(struct jset_entry_dev_usage_type) * BCH_DATA_NR;
 		struct jset_entry_dev_usage *u =
@@ -255,10 +252,9 @@ void bch2_journal_super_entries_add_common(struct bch_fs *c,
 				     struct jset_entry_dev_usage, entry);
 
 		u->entry.type = BCH_JSET_ENTRY_dev_usage;
-		u->dev = cpu_to_le32(dev);
-		u->buckets_ec		= cpu_to_le64(ca->usage_base->buckets_ec);
+		u->dev = cpu_to_le32(ca->dev_idx);
 
-		for (i = 0; i < BCH_DATA_NR; i++) {
+		for (unsigned i = 0; i < BCH_DATA_NR; i++) {
 			u->d[i].buckets = cpu_to_le64(ca->usage_base->d[i].buckets);
 			u->d[i].sectors	= cpu_to_le64(ca->usage_base->d[i].sectors);
 			u->d[i].fragmented = cpu_to_le64(ca->usage_base->d[i].fragmented);
@@ -267,7 +263,7 @@ void bch2_journal_super_entries_add_common(struct bch_fs *c,
 
 	percpu_up_read(&c->mark_lock);
 
-	for (i = 0; i < 2; i++) {
+	for (unsigned i = 0; i < 2; i++) {
 		struct jset_entry_clock *clock =
 			container_of(jset_entry_init(end, sizeof(*clock)),
 				     struct jset_entry_clock, entry);
@@ -332,8 +328,6 @@ int bch2_fs_mark_dirty(struct bch_fs *c)
 
 	mutex_lock(&c->sb_lock);
 	SET_BCH_SB_CLEAN(c->disk_sb.sb, false);
-
-	bch2_sb_maybe_downgrade(c);
 	c->disk_sb.sb->features[0] |= cpu_to_le64(BCH_SB_FEATURES_ALWAYS);
 
 	ret = bch2_write_super(c);
diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c
new file mode 100644
index 000000000000..441dcb1bf160
--- /dev/null
+++ b/fs/bcachefs/sb-downgrade.c
@@ -0,0 +1,260 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Superblock section that contains a list of recovery passes to run when
+ * downgrading past a given version
+ */
+
+#include "bcachefs.h"
+#include "darray.h"
+#include "recovery.h"
+#include "sb-downgrade.h"
+#include "sb-errors.h"
+#include "super-io.h"
+
+#define RECOVERY_PASS_ALL_FSCK		BIT_ULL(63)
+
+/*
+ * Upgrade, downgrade tables - run certain recovery passes, fix certain errors
+ *
+ * x(version, recovery_passes, errors...)
+ */
+#define UPGRADE_TABLE()						\
+	x(backpointers,						\
+	  RECOVERY_PASS_ALL_FSCK)				\
+	x(inode_v3,						\
+	  RECOVERY_PASS_ALL_FSCK)				\
+	x(unwritten_extents,					\
+	  RECOVERY_PASS_ALL_FSCK)				\
+	x(bucket_gens,						\
+	  BIT_ULL(BCH_RECOVERY_PASS_bucket_gens_init)|		\
+	  RECOVERY_PASS_ALL_FSCK)				\
+	x(lru_v2,						\
+	  RECOVERY_PASS_ALL_FSCK)				\
+	x(fragmentation_lru,					\
+	  RECOVERY_PASS_ALL_FSCK)				\
+	x(no_bps_in_alloc_keys,					\
+	  RECOVERY_PASS_ALL_FSCK)				\
+	x(snapshot_trees,					\
+	  RECOVERY_PASS_ALL_FSCK)				\
+	x(snapshot_skiplists,					\
+	  BIT_ULL(BCH_RECOVERY_PASS_check_snapshots),		\
+	  BCH_FSCK_ERR_snapshot_bad_depth,			\
+	  BCH_FSCK_ERR_snapshot_bad_skiplist)			\
+	x(deleted_inodes,					\
+	  BIT_ULL(BCH_RECOVERY_PASS_check_inodes),		\
+	  BCH_FSCK_ERR_unlinked_inode_not_on_deleted_list)	\
+	x(rebalance_work,					\
+	  BIT_ULL(BCH_RECOVERY_PASS_set_fs_needs_rebalance))
+
+#define DOWNGRADE_TABLE()
+
+struct upgrade_downgrade_entry {
+	u64		recovery_passes;
+	u16		version;
+	u16		nr_errors;
+	const u16	*errors;
+};
+
+#define x(ver, passes, ...) static const u16 upgrade_##ver##_errors[] = { __VA_ARGS__ };
+UPGRADE_TABLE()
+#undef x
+
+static const struct upgrade_downgrade_entry upgrade_table[] = {
+#define x(ver, passes, ...) {					\
+	.recovery_passes	= passes,			\
+	.version		= bcachefs_metadata_version_##ver,\
+	.nr_errors		= ARRAY_SIZE(upgrade_##ver##_errors),	\
+	.errors			= upgrade_##ver##_errors,	\
+},
+UPGRADE_TABLE()
+#undef x
+};
+
+void bch2_sb_set_upgrade(struct bch_fs *c,
+			 unsigned old_version,
+			 unsigned new_version)
+{
+	lockdep_assert_held(&c->sb_lock);
+
+	struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
+
+	for (const struct upgrade_downgrade_entry *i = upgrade_table;
+	     i < upgrade_table + ARRAY_SIZE(upgrade_table);
+	     i++)
+		if (i->version > old_version && i->version <= new_version) {
+			u64 passes = i->recovery_passes;
+
+			if (passes & RECOVERY_PASS_ALL_FSCK)
+				passes |= bch2_fsck_recovery_passes();
+			passes &= ~RECOVERY_PASS_ALL_FSCK;
+
+			ext->recovery_passes_required[0] |=
+				cpu_to_le64(bch2_recovery_passes_to_stable(passes));
+
+			for (const u16 *e = i->errors;
+			     e < i->errors + i->nr_errors;
+			     e++) {
+				__set_bit(*e, c->sb.errors_silent);
+				ext->errors_silent[*e / 64] |= cpu_to_le64(BIT_ULL(*e % 64));
+			}
+		}
+}
+
+#define x(ver, passes, ...) static const u16 downgrade_ver_##errors[] = { __VA_ARGS__ };
+DOWNGRADE_TABLE()
+#undef x
+
+static const struct upgrade_downgrade_entry downgrade_table[] = {
+#define x(ver, passes, ...) {					\
+	.recovery_passes	= passes,			\
+	.version		= bcachefs_metadata_version_##ver,\
+	.nr_errors		= ARRAY_SIZE(downgrade_##ver##_errors),	\
+	.errors			= downgrade_##ver##_errors,	\
+},
+DOWNGRADE_TABLE()
+#undef x
+};
+
+static inline const struct bch_sb_field_downgrade_entry *
+downgrade_entry_next_c(const struct bch_sb_field_downgrade_entry *e)
+{
+	return (void *) &e->errors[le16_to_cpu(e->nr_errors)];
+}
+
+#define for_each_downgrade_entry(_d, _i)						\
+	for (const struct bch_sb_field_downgrade_entry *_i = (_d)->entries;		\
+	     (void *) _i	< vstruct_end(&(_d)->field) &&				\
+	     (void *) &_i->errors[0] < vstruct_end(&(_d)->field);			\
+	     _i = downgrade_entry_next_c(_i))
+
+static int bch2_sb_downgrade_validate(struct bch_sb *sb, struct bch_sb_field *f,
+				      struct printbuf *err)
+{
+	struct bch_sb_field_downgrade *e = field_to_type(f, downgrade);
+
+	for_each_downgrade_entry(e, i) {
+		if (BCH_VERSION_MAJOR(le16_to_cpu(i->version)) !=
+		    BCH_VERSION_MAJOR(le16_to_cpu(sb->version))) {
+			prt_printf(err, "downgrade entry with mismatched major version (%u != %u)",
+				   BCH_VERSION_MAJOR(le16_to_cpu(i->version)),
+				   BCH_VERSION_MAJOR(le16_to_cpu(sb->version)));
+			return -BCH_ERR_invalid_sb_downgrade;
+		}
+	}
+
+	return 0;
+}
+
+static void bch2_sb_downgrade_to_text(struct printbuf *out, struct bch_sb *sb,
+				      struct bch_sb_field *f)
+{
+	struct bch_sb_field_downgrade *e = field_to_type(f, downgrade);
+
+	if (out->nr_tabstops <= 1)
+		printbuf_tabstop_push(out, 16);
+
+	for_each_downgrade_entry(e, i) {
+		prt_str(out, "version:");
+		prt_tab(out);
+		bch2_version_to_text(out, le16_to_cpu(i->version));
+		prt_newline(out);
+
+		prt_str(out, "recovery passes:");
+		prt_tab(out);
+		prt_bitflags(out, bch2_recovery_passes,
+			     bch2_recovery_passes_from_stable(le64_to_cpu(i->recovery_passes[0])));
+		prt_newline(out);
+
+		prt_str(out, "errors:");
+		prt_tab(out);
+		bool first = true;
+		for (unsigned j = 0; j < le16_to_cpu(i->nr_errors); j++) {
+			if (!first)
+				prt_char(out, ',');
+			first = false;
+			unsigned e = le16_to_cpu(i->errors[j]);
+			prt_str(out, e < BCH_SB_ERR_MAX ? bch2_sb_error_strs[e] : "(unknown)");
+		}
+		prt_newline(out);
+	}
+}
+
+const struct bch_sb_field_ops bch_sb_field_ops_downgrade = {
+	.validate	= bch2_sb_downgrade_validate,
+	.to_text	= bch2_sb_downgrade_to_text,
+};
+
+int bch2_sb_downgrade_update(struct bch_fs *c)
+{
+	darray_char table = {};
+	int ret = 0;
+
+	for (const struct upgrade_downgrade_entry *src = downgrade_table;
+	     src < downgrade_table + ARRAY_SIZE(downgrade_table);
+	     src++) {
+		if (BCH_VERSION_MAJOR(src->version) != BCH_VERSION_MAJOR(le16_to_cpu(c->disk_sb.sb->version)))
+			continue;
+
+		struct bch_sb_field_downgrade_entry *dst;
+		unsigned bytes = sizeof(*dst) + sizeof(dst->errors[0]) * src->nr_errors;
+
+		ret = darray_make_room(&table, bytes);
+		if (ret)
+			goto out;
+
+		dst = (void *) &darray_top(table);
+		dst->version = cpu_to_le16(src->version);
+		dst->recovery_passes[0]	= cpu_to_le64(src->recovery_passes);
+		dst->recovery_passes[1]	= 0;
+		dst->nr_errors		= cpu_to_le16(src->nr_errors);
+		for (unsigned i = 0; i < src->nr_errors; i++)
+			dst->errors[i] = cpu_to_le16(src->errors[i]);
+
+		table.nr += bytes;
+	}
+
+	struct bch_sb_field_downgrade *d = bch2_sb_field_get(c->disk_sb.sb, downgrade);
+
+	unsigned sb_u64s = DIV_ROUND_UP(sizeof(*d) + table.nr, sizeof(u64));
+
+	if (d && le32_to_cpu(d->field.u64s) > sb_u64s)
+		goto out;
+
+	d = bch2_sb_field_resize(&c->disk_sb, downgrade, sb_u64s);
+	if (!d) {
+		ret = -BCH_ERR_ENOSPC_sb_downgrade;
+		goto out;
+	}
+
+	memcpy(d->entries, table.data, table.nr);
+	memset_u64s_tail(d->entries, 0, table.nr);
+out:
+	darray_exit(&table);
+	return ret;
+}
+
+void bch2_sb_set_downgrade(struct bch_fs *c, unsigned new_minor, unsigned old_minor)
+{
+	struct bch_sb_field_downgrade *d = bch2_sb_field_get(c->disk_sb.sb, downgrade);
+	if (!d)
+		return;
+
+	struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
+
+	for_each_downgrade_entry(d, i) {
+		unsigned minor = BCH_VERSION_MINOR(le16_to_cpu(i->version));
+		if (new_minor < minor && minor <= old_minor) {
+			ext->recovery_passes_required[0] |= i->recovery_passes[0];
+			ext->recovery_passes_required[1] |= i->recovery_passes[1];
+
+			for (unsigned j = 0; j < le16_to_cpu(i->nr_errors); j++) {
+				unsigned e = le16_to_cpu(i->errors[j]);
+				if (e < BCH_SB_ERR_MAX)
+					__set_bit(e, c->sb.errors_silent);
+				if (e < sizeof(ext->errors_silent) * 8)
+					ext->errors_silent[e / 64] |= cpu_to_le64(BIT_ULL(e % 64));
+			}
+		}
+	}
+}
diff --git a/fs/bcachefs/sb-downgrade.h b/fs/bcachefs/sb-downgrade.h
new file mode 100644
index 000000000000..57e6c916fc73
--- /dev/null
+++ b/fs/bcachefs/sb-downgrade.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_SB_DOWNGRADE_H
+#define _BCACHEFS_SB_DOWNGRADE_H
+
+extern const struct bch_sb_field_ops bch_sb_field_ops_downgrade;
+
+int bch2_sb_downgrade_update(struct bch_fs *);
+void bch2_sb_set_upgrade(struct bch_fs *, unsigned, unsigned);
+void bch2_sb_set_downgrade(struct bch_fs *, unsigned, unsigned);
+
+#endif /* _BCACHEFS_SB_DOWNGRADE_H */
diff --git a/fs/bcachefs/sb-errors.c b/fs/bcachefs/sb-errors.c
index f0930ab7f036..5f5bcae391fb 100644
--- a/fs/bcachefs/sb-errors.c
+++ b/fs/bcachefs/sb-errors.c
@@ -4,7 +4,7 @@
 #include "sb-errors.h"
 #include "super-io.h"
 
-static const char * const bch2_sb_error_strs[] = {
+const char * const bch2_sb_error_strs[] = {
 #define x(t, n, ...) [n] = #t,
 	BCH_SB_ERRS()
 	NULL
@@ -20,9 +20,7 @@ static void bch2_sb_error_id_to_text(struct printbuf *out, enum bch_sb_error_id
 
 static inline unsigned bch2_sb_field_errors_nr_entries(struct bch_sb_field_errors *e)
 {
-	return e
-		? (bch2_sb_field_bytes(&e->field) - sizeof(*e)) / sizeof(e->entries[0])
-		: 0;
+	return bch2_sb_field_nr_entries(e);
 }
 
 static inline unsigned bch2_sb_field_errors_u64s(unsigned nr)
diff --git a/fs/bcachefs/sb-errors.h b/fs/bcachefs/sb-errors.h
index 5a09a53966be..8889001e7db4 100644
--- a/fs/bcachefs/sb-errors.h
+++ b/fs/bcachefs/sb-errors.h
@@ -4,258 +4,7 @@
 
 #include "sb-errors_types.h"
 
-#define BCH_SB_ERRS()							\
-	x(clean_but_journal_not_empty,				0)	\
-	x(dirty_but_no_journal_entries,				1)	\
-	x(dirty_but_no_journal_entries_post_drop_nonflushes,	2)	\
-	x(sb_clean_journal_seq_mismatch,			3)	\
-	x(sb_clean_btree_root_mismatch,				4)	\
-	x(sb_clean_missing,					5)	\
-	x(jset_unsupported_version,				6)	\
-	x(jset_unknown_csum,					7)	\
-	x(jset_last_seq_newer_than_seq,				8)	\
-	x(jset_past_bucket_end,					9)	\
-	x(jset_seq_blacklisted,					10)	\
-	x(journal_entries_missing,				11)	\
-	x(journal_entry_replicas_not_marked,			12)	\
-	x(journal_entry_past_jset_end,				13)	\
-	x(journal_entry_replicas_data_mismatch,			14)	\
-	x(journal_entry_bkey_u64s_0,				15)	\
-	x(journal_entry_bkey_past_end,				16)	\
-	x(journal_entry_bkey_bad_format,			17)	\
-	x(journal_entry_bkey_invalid,				18)	\
-	x(journal_entry_btree_root_bad_size,			19)	\
-	x(journal_entry_blacklist_bad_size,			20)	\
-	x(journal_entry_blacklist_v2_bad_size,			21)	\
-	x(journal_entry_blacklist_v2_start_past_end,		22)	\
-	x(journal_entry_usage_bad_size,				23)	\
-	x(journal_entry_data_usage_bad_size,			24)	\
-	x(journal_entry_clock_bad_size,				25)	\
-	x(journal_entry_clock_bad_rw,				26)	\
-	x(journal_entry_dev_usage_bad_size,			27)	\
-	x(journal_entry_dev_usage_bad_dev,			28)	\
-	x(journal_entry_dev_usage_bad_pad,			29)	\
-	x(btree_node_unreadable,				30)	\
-	x(btree_node_fault_injected,				31)	\
-	x(btree_node_bad_magic,					32)	\
-	x(btree_node_bad_seq,					33)	\
-	x(btree_node_unsupported_version,			34)	\
-	x(btree_node_bset_older_than_sb_min,			35)	\
-	x(btree_node_bset_newer_than_sb,			36)	\
-	x(btree_node_data_missing,				37)	\
-	x(btree_node_bset_after_end,				38)	\
-	x(btree_node_replicas_sectors_written_mismatch,		39)	\
-	x(btree_node_replicas_data_mismatch,			40)	\
-	x(bset_unknown_csum,					41)	\
-	x(bset_bad_csum,					42)	\
-	x(bset_past_end_of_btree_node,				43)	\
-	x(bset_wrong_sector_offset,				44)	\
-	x(bset_empty,						45)	\
-	x(bset_bad_seq,						46)	\
-	x(bset_blacklisted_journal_seq,				47)	\
-	x(first_bset_blacklisted_journal_seq,			48)	\
-	x(btree_node_bad_btree,					49)	\
-	x(btree_node_bad_level,					50)	\
-	x(btree_node_bad_min_key,				51)	\
-	x(btree_node_bad_max_key,				52)	\
-	x(btree_node_bad_format,				53)	\
-	x(btree_node_bkey_past_bset_end,			54)	\
-	x(btree_node_bkey_bad_format,				55)	\
-	x(btree_node_bad_bkey,					56)	\
-	x(btree_node_bkey_out_of_order,				57)	\
-	x(btree_root_bkey_invalid,				58)	\
-	x(btree_root_read_error,				59)	\
-	x(btree_root_bad_min_key,				50)	\
-	x(btree_root_bad_max_key,				61)	\
-	x(btree_node_read_error,				62)	\
-	x(btree_node_topology_bad_min_key,			63)	\
-	x(btree_node_topology_bad_max_key,			64)	\
-	x(btree_node_topology_overwritten_by_prev_node,		65)	\
-	x(btree_node_topology_overwritten_by_next_node,		66)	\
-	x(btree_node_topology_interior_node_empty,		67)	\
-	x(fs_usage_hidden_wrong,				68)	\
-	x(fs_usage_btree_wrong,					69)	\
-	x(fs_usage_data_wrong,					70)	\
-	x(fs_usage_cached_wrong,				71)	\
-	x(fs_usage_reserved_wrong,				72)	\
-	x(fs_usage_persistent_reserved_wrong,			73)	\
-	x(fs_usage_nr_inodes_wrong,				74)	\
-	x(fs_usage_replicas_wrong,				75)	\
-	x(dev_usage_buckets_wrong,				76)	\
-	x(dev_usage_sectors_wrong,				77)	\
-	x(dev_usage_fragmented_wrong,				78)	\
-	x(dev_usage_buckets_ec_wrong,				79)	\
-	x(bkey_version_in_future,				80)	\
-	x(bkey_u64s_too_small,					81)	\
-	x(bkey_invalid_type_for_btree,				82)	\
-	x(bkey_extent_size_zero,				83)	\
-	x(bkey_extent_size_greater_than_offset,			84)	\
-	x(bkey_size_nonzero,					85)	\
-	x(bkey_snapshot_nonzero,				86)	\
-	x(bkey_snapshot_zero,					87)	\
-	x(bkey_at_pos_max,					88)	\
-	x(bkey_before_start_of_btree_node,			89)	\
-	x(bkey_after_end_of_btree_node,				90)	\
-	x(bkey_val_size_nonzero,				91)	\
-	x(bkey_val_size_too_small,				92)	\
-	x(alloc_v1_val_size_bad,				93)	\
-	x(alloc_v2_unpack_error,				94)	\
-	x(alloc_v3_unpack_error,				95)	\
-	x(alloc_v4_val_size_bad,				96)	\
-	x(alloc_v4_backpointers_start_bad,			97)	\
-	x(alloc_key_data_type_bad,				98)	\
-	x(alloc_key_empty_but_have_data,			99)	\
-	x(alloc_key_dirty_sectors_0,				100)	\
-	x(alloc_key_data_type_inconsistency,			101)	\
-	x(alloc_key_to_missing_dev_bucket,			102)	\
-	x(alloc_key_cached_inconsistency,			103)	\
-	x(alloc_key_cached_but_read_time_zero,			104)	\
-	x(alloc_key_to_missing_lru_entry,			105)	\
-	x(alloc_key_data_type_wrong,				106)	\
-	x(alloc_key_gen_wrong,					107)	\
-	x(alloc_key_dirty_sectors_wrong,			108)	\
-	x(alloc_key_cached_sectors_wrong,			109)	\
-	x(alloc_key_stripe_wrong,				110)	\
-	x(alloc_key_stripe_redundancy_wrong,			111)	\
-	x(bucket_sector_count_overflow,				112)	\
-	x(bucket_metadata_type_mismatch,			113)	\
-	x(need_discard_key_wrong,				114)	\
-	x(freespace_key_wrong,					115)	\
-	x(freespace_hole_missing,				116)	\
-	x(bucket_gens_val_size_bad,				117)	\
-	x(bucket_gens_key_wrong,				118)	\
-	x(bucket_gens_hole_wrong,				119)	\
-	x(bucket_gens_to_invalid_dev,				120)	\
-	x(bucket_gens_to_invalid_buckets,			121)	\
-	x(bucket_gens_nonzero_for_invalid_buckets,		122)	\
-	x(need_discard_freespace_key_to_invalid_dev_bucket,	123)	\
-	x(need_discard_freespace_key_bad,			124)	\
-	x(backpointer_pos_wrong,				125)	\
-	x(backpointer_to_missing_device,			126)	\
-	x(backpointer_to_missing_alloc,				127)	\
-	x(backpointer_to_missing_ptr,				128)	\
-	x(lru_entry_at_time_0,					129)	\
-	x(lru_entry_to_invalid_bucket,				130)	\
-	x(lru_entry_bad,					131)	\
-	x(btree_ptr_val_too_big,				132)	\
-	x(btree_ptr_v2_val_too_big,				133)	\
-	x(btree_ptr_has_non_ptr,				134)	\
-	x(extent_ptrs_invalid_entry,				135)	\
-	x(extent_ptrs_no_ptrs,					136)	\
-	x(extent_ptrs_too_many_ptrs,				137)	\
-	x(extent_ptrs_redundant_crc,				138)	\
-	x(extent_ptrs_redundant_stripe,				139)	\
-	x(extent_ptrs_unwritten,				140)	\
-	x(extent_ptrs_written_and_unwritten,			141)	\
-	x(ptr_to_invalid_device,				142)	\
-	x(ptr_to_duplicate_device,				143)	\
-	x(ptr_after_last_bucket,				144)	\
-	x(ptr_before_first_bucket,				145)	\
-	x(ptr_spans_multiple_buckets,				146)	\
-	x(ptr_to_missing_backpointer,				147)	\
-	x(ptr_to_missing_alloc_key,				148)	\
-	x(ptr_to_missing_replicas_entry,			149)	\
-	x(ptr_to_missing_stripe,				150)	\
-	x(ptr_to_incorrect_stripe,				151)	\
-	x(ptr_gen_newer_than_bucket_gen,			152)	\
-	x(ptr_too_stale,					153)	\
-	x(stale_dirty_ptr,					154)	\
-	x(ptr_bucket_data_type_mismatch,			155)	\
-	x(ptr_cached_and_erasure_coded,				156)	\
-	x(ptr_crc_uncompressed_size_too_small,			157)	\
-	x(ptr_crc_csum_type_unknown,				158)	\
-	x(ptr_crc_compression_type_unknown,			159)	\
-	x(ptr_crc_redundant,					160)	\
-	x(ptr_crc_uncompressed_size_too_big,			161)	\
-	x(ptr_crc_nonce_mismatch,				162)	\
-	x(ptr_stripe_redundant,					163)	\
-	x(reservation_key_nr_replicas_invalid,			164)	\
-	x(reflink_v_refcount_wrong,				165)	\
-	x(reflink_p_to_missing_reflink_v,			166)	\
-	x(stripe_pos_bad,					167)	\
-	x(stripe_val_size_bad,					168)	\
-	x(stripe_sector_count_wrong,				169)	\
-	x(snapshot_tree_pos_bad,				170)	\
-	x(snapshot_tree_to_missing_snapshot,			171)	\
-	x(snapshot_tree_to_missing_subvol,			172)	\
-	x(snapshot_tree_to_wrong_subvol,			173)	\
-	x(snapshot_tree_to_snapshot_subvol,			174)	\
-	x(snapshot_pos_bad,					175)	\
-	x(snapshot_parent_bad,					176)	\
-	x(snapshot_children_not_normalized,			177)	\
-	x(snapshot_child_duplicate,				178)	\
-	x(snapshot_child_bad,					179)	\
-	x(snapshot_skiplist_not_normalized,			180)	\
-	x(snapshot_skiplist_bad,				181)	\
-	x(snapshot_should_not_have_subvol,			182)	\
-	x(snapshot_to_bad_snapshot_tree,			183)	\
-	x(snapshot_bad_depth,					184)	\
-	x(snapshot_bad_skiplist,				185)	\
-	x(subvol_pos_bad,					186)	\
-	x(subvol_not_master_and_not_snapshot,			187)	\
-	x(subvol_to_missing_root,				188)	\
-	x(subvol_root_wrong_bi_subvol,				189)	\
-	x(bkey_in_missing_snapshot,				190)	\
-	x(inode_pos_inode_nonzero,				191)	\
-	x(inode_pos_blockdev_range,				192)	\
-	x(inode_unpack_error,					193)	\
-	x(inode_str_hash_invalid,				194)	\
-	x(inode_v3_fields_start_bad,				195)	\
-	x(inode_snapshot_mismatch,				196)	\
-	x(inode_unlinked_but_clean,				197)	\
-	x(inode_unlinked_but_nlink_nonzero,			198)	\
-	x(inode_checksum_type_invalid,				199)	\
-	x(inode_compression_type_invalid,			200)	\
-	x(inode_subvol_root_but_not_dir,			201)	\
-	x(inode_i_size_dirty_but_clean,				202)	\
-	x(inode_i_sectors_dirty_but_clean,			203)	\
-	x(inode_i_sectors_wrong,				204)	\
-	x(inode_dir_wrong_nlink,				205)	\
-	x(inode_dir_multiple_links,				206)	\
-	x(inode_multiple_links_but_nlink_0,			207)	\
-	x(inode_wrong_backpointer,				208)	\
-	x(inode_wrong_nlink,					209)	\
-	x(inode_unreachable,					210)	\
-	x(deleted_inode_but_clean,				211)	\
-	x(deleted_inode_missing,				212)	\
-	x(deleted_inode_is_dir,					213)	\
-	x(deleted_inode_not_unlinked,				214)	\
-	x(extent_overlapping,					215)	\
-	x(extent_in_missing_inode,				216)	\
-	x(extent_in_non_reg_inode,				217)	\
-	x(extent_past_end_of_inode,				218)	\
-	x(dirent_empty_name,					219)	\
-	x(dirent_val_too_big,					220)	\
-	x(dirent_name_too_long,					221)	\
-	x(dirent_name_embedded_nul,				222)	\
-	x(dirent_name_dot_or_dotdot,				223)	\
-	x(dirent_name_has_slash,				224)	\
-	x(dirent_d_type_wrong,					225)	\
-	x(dirent_d_parent_subvol_wrong,				226)	\
-	x(dirent_in_missing_dir_inode,				227)	\
-	x(dirent_in_non_dir_inode,				228)	\
-	x(dirent_to_missing_inode,				229)	\
-	x(dirent_to_missing_subvol,				230)	\
-	x(dirent_to_itself,					231)	\
-	x(quota_type_invalid,					232)	\
-	x(xattr_val_size_too_small,				233)	\
-	x(xattr_val_size_too_big,				234)	\
-	x(xattr_invalid_type,					235)	\
-	x(xattr_name_invalid_chars,				236)	\
-	x(xattr_in_missing_inode,				237)	\
-	x(root_subvol_missing,					238)	\
-	x(root_dir_missing,					239)	\
-	x(root_inode_not_dir,					240)	\
-	x(dir_loop,						241)	\
-	x(hash_table_key_duplicate,				242)	\
-	x(hash_table_key_wrong_offset,				243)
-
-enum bch_sb_error_id {
-#define x(t, n) BCH_FSCK_ERR_##t = n,
-	BCH_SB_ERRS()
-#undef x
-	BCH_SB_ERR_MAX
-};
+extern const char * const bch2_sb_error_strs[];
 
 extern const struct bch_sb_field_ops bch_sb_field_ops_errors;
 
diff --git a/fs/bcachefs/sb-errors_types.h b/fs/bcachefs/sb-errors_types.h
index b1c099843a39..c08aacdfd073 100644
--- a/fs/bcachefs/sb-errors_types.h
+++ b/fs/bcachefs/sb-errors_types.h
@@ -4,6 +4,261 @@
 
 #include "darray.h"
 
+#define BCH_SB_ERRS()							\
+	x(clean_but_journal_not_empty,				0)	\
+	x(dirty_but_no_journal_entries,				1)	\
+	x(dirty_but_no_journal_entries_post_drop_nonflushes,	2)	\
+	x(sb_clean_journal_seq_mismatch,			3)	\
+	x(sb_clean_btree_root_mismatch,				4)	\
+	x(sb_clean_missing,					5)	\
+	x(jset_unsupported_version,				6)	\
+	x(jset_unknown_csum,					7)	\
+	x(jset_last_seq_newer_than_seq,				8)	\
+	x(jset_past_bucket_end,					9)	\
+	x(jset_seq_blacklisted,					10)	\
+	x(journal_entries_missing,				11)	\
+	x(journal_entry_replicas_not_marked,			12)	\
+	x(journal_entry_past_jset_end,				13)	\
+	x(journal_entry_replicas_data_mismatch,			14)	\
+	x(journal_entry_bkey_u64s_0,				15)	\
+	x(journal_entry_bkey_past_end,				16)	\
+	x(journal_entry_bkey_bad_format,			17)	\
+	x(journal_entry_bkey_invalid,				18)	\
+	x(journal_entry_btree_root_bad_size,			19)	\
+	x(journal_entry_blacklist_bad_size,			20)	\
+	x(journal_entry_blacklist_v2_bad_size,			21)	\
+	x(journal_entry_blacklist_v2_start_past_end,		22)	\
+	x(journal_entry_usage_bad_size,				23)	\
+	x(journal_entry_data_usage_bad_size,			24)	\
+	x(journal_entry_clock_bad_size,				25)	\
+	x(journal_entry_clock_bad_rw,				26)	\
+	x(journal_entry_dev_usage_bad_size,			27)	\
+	x(journal_entry_dev_usage_bad_dev,			28)	\
+	x(journal_entry_dev_usage_bad_pad,			29)	\
+	x(btree_node_unreadable,				30)	\
+	x(btree_node_fault_injected,				31)	\
+	x(btree_node_bad_magic,					32)	\
+	x(btree_node_bad_seq,					33)	\
+	x(btree_node_unsupported_version,			34)	\
+	x(btree_node_bset_older_than_sb_min,			35)	\
+	x(btree_node_bset_newer_than_sb,			36)	\
+	x(btree_node_data_missing,				37)	\
+	x(btree_node_bset_after_end,				38)	\
+	x(btree_node_replicas_sectors_written_mismatch,		39)	\
+	x(btree_node_replicas_data_mismatch,			40)	\
+	x(bset_unknown_csum,					41)	\
+	x(bset_bad_csum,					42)	\
+	x(bset_past_end_of_btree_node,				43)	\
+	x(bset_wrong_sector_offset,				44)	\
+	x(bset_empty,						45)	\
+	x(bset_bad_seq,						46)	\
+	x(bset_blacklisted_journal_seq,				47)	\
+	x(first_bset_blacklisted_journal_seq,			48)	\
+	x(btree_node_bad_btree,					49)	\
+	x(btree_node_bad_level,					50)	\
+	x(btree_node_bad_min_key,				51)	\
+	x(btree_node_bad_max_key,				52)	\
+	x(btree_node_bad_format,				53)	\
+	x(btree_node_bkey_past_bset_end,			54)	\
+	x(btree_node_bkey_bad_format,				55)	\
+	x(btree_node_bad_bkey,					56)	\
+	x(btree_node_bkey_out_of_order,				57)	\
+	x(btree_root_bkey_invalid,				58)	\
+	x(btree_root_read_error,				59)	\
+	x(btree_root_bad_min_key,				60)	\
+	x(btree_root_bad_max_key,				61)	\
+	x(btree_node_read_error,				62)	\
+	x(btree_node_topology_bad_min_key,			63)	\
+	x(btree_node_topology_bad_max_key,			64)	\
+	x(btree_node_topology_overwritten_by_prev_node,		65)	\
+	x(btree_node_topology_overwritten_by_next_node,		66)	\
+	x(btree_node_topology_interior_node_empty,		67)	\
+	x(fs_usage_hidden_wrong,				68)	\
+	x(fs_usage_btree_wrong,					69)	\
+	x(fs_usage_data_wrong,					70)	\
+	x(fs_usage_cached_wrong,				71)	\
+	x(fs_usage_reserved_wrong,				72)	\
+	x(fs_usage_persistent_reserved_wrong,			73)	\
+	x(fs_usage_nr_inodes_wrong,				74)	\
+	x(fs_usage_replicas_wrong,				75)	\
+	x(dev_usage_buckets_wrong,				76)	\
+	x(dev_usage_sectors_wrong,				77)	\
+	x(dev_usage_fragmented_wrong,				78)	\
+	x(dev_usage_buckets_ec_wrong,				79)	\
+	x(bkey_version_in_future,				80)	\
+	x(bkey_u64s_too_small,					81)	\
+	x(bkey_invalid_type_for_btree,				82)	\
+	x(bkey_extent_size_zero,				83)	\
+	x(bkey_extent_size_greater_than_offset,			84)	\
+	x(bkey_size_nonzero,					85)	\
+	x(bkey_snapshot_nonzero,				86)	\
+	x(bkey_snapshot_zero,					87)	\
+	x(bkey_at_pos_max,					88)	\
+	x(bkey_before_start_of_btree_node,			89)	\
+	x(bkey_after_end_of_btree_node,				90)	\
+	x(bkey_val_size_nonzero,				91)	\
+	x(bkey_val_size_too_small,				92)	\
+	x(alloc_v1_val_size_bad,				93)	\
+	x(alloc_v2_unpack_error,				94)	\
+	x(alloc_v3_unpack_error,				95)	\
+	x(alloc_v4_val_size_bad,				96)	\
+	x(alloc_v4_backpointers_start_bad,			97)	\
+	x(alloc_key_data_type_bad,				98)	\
+	x(alloc_key_empty_but_have_data,			99)	\
+	x(alloc_key_dirty_sectors_0,				100)	\
+	x(alloc_key_data_type_inconsistency,			101)	\
+	x(alloc_key_to_missing_dev_bucket,			102)	\
+	x(alloc_key_cached_inconsistency,			103)	\
+	x(alloc_key_cached_but_read_time_zero,			104)	\
+	x(alloc_key_to_missing_lru_entry,			105)	\
+	x(alloc_key_data_type_wrong,				106)	\
+	x(alloc_key_gen_wrong,					107)	\
+	x(alloc_key_dirty_sectors_wrong,			108)	\
+	x(alloc_key_cached_sectors_wrong,			109)	\
+	x(alloc_key_stripe_wrong,				110)	\
+	x(alloc_key_stripe_redundancy_wrong,			111)	\
+	x(bucket_sector_count_overflow,				112)	\
+	x(bucket_metadata_type_mismatch,			113)	\
+	x(need_discard_key_wrong,				114)	\
+	x(freespace_key_wrong,					115)	\
+	x(freespace_hole_missing,				116)	\
+	x(bucket_gens_val_size_bad,				117)	\
+	x(bucket_gens_key_wrong,				118)	\
+	x(bucket_gens_hole_wrong,				119)	\
+	x(bucket_gens_to_invalid_dev,				120)	\
+	x(bucket_gens_to_invalid_buckets,			121)	\
+	x(bucket_gens_nonzero_for_invalid_buckets,		122)	\
+	x(need_discard_freespace_key_to_invalid_dev_bucket,	123)	\
+	x(need_discard_freespace_key_bad,			124)	\
+	x(backpointer_pos_wrong,				125)	\
+	x(backpointer_to_missing_device,			126)	\
+	x(backpointer_to_missing_alloc,				127)	\
+	x(backpointer_to_missing_ptr,				128)	\
+	x(lru_entry_at_time_0,					129)	\
+	x(lru_entry_to_invalid_bucket,				130)	\
+	x(lru_entry_bad,					131)	\
+	x(btree_ptr_val_too_big,				132)	\
+	x(btree_ptr_v2_val_too_big,				133)	\
+	x(btree_ptr_has_non_ptr,				134)	\
+	x(extent_ptrs_invalid_entry,				135)	\
+	x(extent_ptrs_no_ptrs,					136)	\
+	x(extent_ptrs_too_many_ptrs,				137)	\
+	x(extent_ptrs_redundant_crc,				138)	\
+	x(extent_ptrs_redundant_stripe,				139)	\
+	x(extent_ptrs_unwritten,				140)	\
+	x(extent_ptrs_written_and_unwritten,			141)	\
+	x(ptr_to_invalid_device,				142)	\
+	x(ptr_to_duplicate_device,				143)	\
+	x(ptr_after_last_bucket,				144)	\
+	x(ptr_before_first_bucket,				145)	\
+	x(ptr_spans_multiple_buckets,				146)	\
+	x(ptr_to_missing_backpointer,				147)	\
+	x(ptr_to_missing_alloc_key,				148)	\
+	x(ptr_to_missing_replicas_entry,			149)	\
+	x(ptr_to_missing_stripe,				150)	\
+	x(ptr_to_incorrect_stripe,				151)	\
+	x(ptr_gen_newer_than_bucket_gen,			152)	\
+	x(ptr_too_stale,					153)	\
+	x(stale_dirty_ptr,					154)	\
+	x(ptr_bucket_data_type_mismatch,			155)	\
+	x(ptr_cached_and_erasure_coded,				156)	\
+	x(ptr_crc_uncompressed_size_too_small,			157)	\
+	x(ptr_crc_csum_type_unknown,				158)	\
+	x(ptr_crc_compression_type_unknown,			159)	\
+	x(ptr_crc_redundant,					160)	\
+	x(ptr_crc_uncompressed_size_too_big,			161)	\
+	x(ptr_crc_nonce_mismatch,				162)	\
+	x(ptr_stripe_redundant,					163)	\
+	x(reservation_key_nr_replicas_invalid,			164)	\
+	x(reflink_v_refcount_wrong,				165)	\
+	x(reflink_p_to_missing_reflink_v,			166)	\
+	x(stripe_pos_bad,					167)	\
+	x(stripe_val_size_bad,					168)	\
+	x(stripe_sector_count_wrong,				169)	\
+	x(snapshot_tree_pos_bad,				170)	\
+	x(snapshot_tree_to_missing_snapshot,			171)	\
+	x(snapshot_tree_to_missing_subvol,			172)	\
+	x(snapshot_tree_to_wrong_subvol,			173)	\
+	x(snapshot_tree_to_snapshot_subvol,			174)	\
+	x(snapshot_pos_bad,					175)	\
+	x(snapshot_parent_bad,					176)	\
+	x(snapshot_children_not_normalized,			177)	\
+	x(snapshot_child_duplicate,				178)	\
+	x(snapshot_child_bad,					179)	\
+	x(snapshot_skiplist_not_normalized,			180)	\
+	x(snapshot_skiplist_bad,				181)	\
+	x(snapshot_should_not_have_subvol,			182)	\
+	x(snapshot_to_bad_snapshot_tree,			183)	\
+	x(snapshot_bad_depth,					184)	\
+	x(snapshot_bad_skiplist,				185)	\
+	x(subvol_pos_bad,					186)	\
+	x(subvol_not_master_and_not_snapshot,			187)	\
+	x(subvol_to_missing_root,				188)	\
+	x(subvol_root_wrong_bi_subvol,				189)	\
+	x(bkey_in_missing_snapshot,				190)	\
+	x(inode_pos_inode_nonzero,				191)	\
+	x(inode_pos_blockdev_range,				192)	\
+	x(inode_unpack_error,					193)	\
+	x(inode_str_hash_invalid,				194)	\
+	x(inode_v3_fields_start_bad,				195)	\
+	x(inode_snapshot_mismatch,				196)	\
+	x(inode_unlinked_but_clean,				197)	\
+	x(inode_unlinked_but_nlink_nonzero,			198)	\
+	x(inode_checksum_type_invalid,				199)	\
+	x(inode_compression_type_invalid,			200)	\
+	x(inode_subvol_root_but_not_dir,			201)	\
+	x(inode_i_size_dirty_but_clean,				202)	\
+	x(inode_i_sectors_dirty_but_clean,			203)	\
+	x(inode_i_sectors_wrong,				204)	\
+	x(inode_dir_wrong_nlink,				205)	\
+	x(inode_dir_multiple_links,				206)	\
+	x(inode_multiple_links_but_nlink_0,			207)	\
+	x(inode_wrong_backpointer,				208)	\
+	x(inode_wrong_nlink,					209)	\
+	x(inode_unreachable,					210)	\
+	x(deleted_inode_but_clean,				211)	\
+	x(deleted_inode_missing,				212)	\
+	x(deleted_inode_is_dir,					213)	\
+	x(deleted_inode_not_unlinked,				214)	\
+	x(extent_overlapping,					215)	\
+	x(extent_in_missing_inode,				216)	\
+	x(extent_in_non_reg_inode,				217)	\
+	x(extent_past_end_of_inode,				218)	\
+	x(dirent_empty_name,					219)	\
+	x(dirent_val_too_big,					220)	\
+	x(dirent_name_too_long,					221)	\
+	x(dirent_name_embedded_nul,				222)	\
+	x(dirent_name_dot_or_dotdot,				223)	\
+	x(dirent_name_has_slash,				224)	\
+	x(dirent_d_type_wrong,					225)	\
+	x(dirent_d_parent_subvol_wrong,				226)	\
+	x(dirent_in_missing_dir_inode,				227)	\
+	x(dirent_in_non_dir_inode,				228)	\
+	x(dirent_to_missing_inode,				229)	\
+	x(dirent_to_missing_subvol,				230)	\
+	x(dirent_to_itself,					231)	\
+	x(quota_type_invalid,					232)	\
+	x(xattr_val_size_too_small,				233)	\
+	x(xattr_val_size_too_big,				234)	\
+	x(xattr_invalid_type,					235)	\
+	x(xattr_name_invalid_chars,				236)	\
+	x(xattr_in_missing_inode,				237)	\
+	x(root_subvol_missing,					238)	\
+	x(root_dir_missing,					239)	\
+	x(root_inode_not_dir,					240)	\
+	x(dir_loop,						241)	\
+	x(hash_table_key_duplicate,				242)	\
+	x(hash_table_key_wrong_offset,				243)	\
+	x(unlinked_inode_not_on_deleted_list,			244)	\
+	x(reflink_p_front_pad_bad,				245)
+
+enum bch_sb_error_id {
+#define x(t, n) BCH_FSCK_ERR_##t = n,
+	BCH_SB_ERRS()
+#undef x
+	BCH_SB_ERR_MAX
+};
+
 struct bch_sb_error_entry_cpu {
 	u64			id:16,
 				nr:48;
diff --git a/fs/bcachefs/sb-members.c b/fs/bcachefs/sb-members.c
index bed0f857fe5b..a44a238bf8b5 100644
--- a/fs/bcachefs/sb-members.c
+++ b/fs/bcachefs/sb-members.c
@@ -235,6 +235,11 @@ static void member_to_text(struct printbuf *out,
 		prt_printf(out, "(never)");
 	prt_newline(out);
 
+	prt_printf(out, "Last superblock write:");
+	prt_tab(out);
+	prt_u64(out, le64_to_cpu(m.seq));
+	prt_newline(out);
+
 	prt_printf(out, "State:");
 	prt_tab(out);
 	prt_printf(out, "%s",
@@ -259,6 +264,11 @@ static void member_to_text(struct printbuf *out,
 		prt_printf(out, "(none)");
 	prt_newline(out);
 
+	prt_str(out, "Durability:");
+	prt_tab(out);
+	prt_printf(out, "%llu", BCH_MEMBER_DURABILITY(&m) ? BCH_MEMBER_DURABILITY(&m) - 1 : 1);
+	prt_newline(out);
+
 	prt_printf(out, "Discard:");
 	prt_tab(out);
 	prt_printf(out, "%llu", BCH_MEMBER_DISCARD(&m));
@@ -353,14 +363,12 @@ const struct bch_sb_field_ops bch_sb_field_ops_members_v2 = {
 void bch2_sb_members_from_cpu(struct bch_fs *c)
 {
 	struct bch_sb_field_members_v2 *mi = bch2_sb_field_get(c->disk_sb.sb, members_v2);
-	struct bch_dev *ca;
-	unsigned i, e;
 
 	rcu_read_lock();
-	for_each_member_device_rcu(ca, c, i, NULL) {
-		struct bch_member *m = __bch2_members_v2_get_mut(mi, i);
+	for_each_member_device_rcu(c, ca, NULL) {
+		struct bch_member *m = __bch2_members_v2_get_mut(mi, ca->dev_idx);
 
-		for (e = 0; e < BCH_MEMBER_ERROR_NR; e++)
+		for (unsigned e = 0; e < BCH_MEMBER_ERROR_NR; e++)
 			m->errors[e] = cpu_to_le64(atomic64_read(&ca->errors[e]));
 	}
 	rcu_read_unlock();
diff --git a/fs/bcachefs/sb-members.h b/fs/bcachefs/sb-members.h
index 03613e3eb8e3..be0a94183271 100644
--- a/fs/bcachefs/sb-members.h
+++ b/fs/bcachefs/sb-members.h
@@ -2,6 +2,8 @@
 #ifndef _BCACHEFS_SB_MEMBERS_H
 #define _BCACHEFS_SB_MEMBERS_H
 
+#include "darray.h"
+
 extern char * const bch2_member_error_strs[];
 
 static inline struct bch_member *
@@ -47,23 +49,18 @@ static inline unsigned dev_mask_nr(const struct bch_devs_mask *devs)
 static inline bool bch2_dev_list_has_dev(struct bch_devs_list devs,
 					 unsigned dev)
 {
-	unsigned i;
-
-	for (i = 0; i < devs.nr; i++)
-		if (devs.devs[i] == dev)
+	darray_for_each(devs, i)
+		if (*i == dev)
 			return true;
-
 	return false;
 }
 
 static inline void bch2_dev_list_drop_dev(struct bch_devs_list *devs,
 					  unsigned dev)
 {
-	unsigned i;
-
-	for (i = 0; i < devs->nr; i++)
-		if (devs->devs[i] == dev) {
-			array_remove_item(devs->devs, devs->nr, i);
+	darray_for_each(*devs, i)
+		if (*i == dev) {
+			darray_remove_item(devs, i);
 			return;
 		}
 }
@@ -72,40 +69,48 @@ static inline void bch2_dev_list_add_dev(struct bch_devs_list *devs,
 					 unsigned dev)
 {
 	if (!bch2_dev_list_has_dev(*devs, dev)) {
-		BUG_ON(devs->nr >= ARRAY_SIZE(devs->devs));
-		devs->devs[devs->nr++] = dev;
+		BUG_ON(devs->nr >= ARRAY_SIZE(devs->data));
+		devs->data[devs->nr++] = dev;
 	}
 }
 
 static inline struct bch_devs_list bch2_dev_list_single(unsigned dev)
 {
-	return (struct bch_devs_list) { .nr = 1, .devs[0] = dev };
+	return (struct bch_devs_list) { .nr = 1, .data[0] = dev };
 }
 
-static inline struct bch_dev *__bch2_next_dev(struct bch_fs *c, unsigned *iter,
-					      const struct bch_devs_mask *mask)
+static inline struct bch_dev *__bch2_next_dev_idx(struct bch_fs *c, unsigned idx,
+						  const struct bch_devs_mask *mask)
 {
 	struct bch_dev *ca = NULL;
 
-	while ((*iter = mask
-		? find_next_bit(mask->d, c->sb.nr_devices, *iter)
-		: *iter) < c->sb.nr_devices &&
-	       !(ca = rcu_dereference_check(c->devs[*iter],
+	while ((idx = mask
+		? find_next_bit(mask->d, c->sb.nr_devices, idx)
+		: idx) < c->sb.nr_devices &&
+	       !(ca = rcu_dereference_check(c->devs[idx],
 					    lockdep_is_held(&c->state_lock))))
-		(*iter)++;
+		idx++;
 
 	return ca;
 }
 
-#define for_each_member_device_rcu(ca, c, iter, mask)			\
-	for ((iter) = 0; ((ca) = __bch2_next_dev((c), &(iter), mask)); (iter)++)
+static inline struct bch_dev *__bch2_next_dev(struct bch_fs *c, struct bch_dev *ca,
+					      const struct bch_devs_mask *mask)
+{
+	return __bch2_next_dev_idx(c, ca ? ca->dev_idx + 1 : 0, mask);
+}
 
-static inline struct bch_dev *bch2_get_next_dev(struct bch_fs *c, unsigned *iter)
+#define for_each_member_device_rcu(_c, _ca, _mask)			\
+	for (struct bch_dev *_ca = NULL;				\
+	     (_ca = __bch2_next_dev((_c), _ca, (_mask)));)
+
+static inline struct bch_dev *bch2_get_next_dev(struct bch_fs *c, struct bch_dev *ca)
 {
-	struct bch_dev *ca;
+	if (ca)
+		percpu_ref_put(&ca->ref);
 
 	rcu_read_lock();
-	if ((ca = __bch2_next_dev(c, iter, NULL)))
+	if ((ca = __bch2_next_dev(c, ca, NULL)))
 		percpu_ref_get(&ca->ref);
 	rcu_read_unlock();
 
@@ -115,41 +120,42 @@ static inline struct bch_dev *bch2_get_next_dev(struct bch_fs *c, unsigned *iter
 /*
  * If you break early, you must drop your ref on the current device
  */
-#define for_each_member_device(ca, c, iter)				\
-	for ((iter) = 0;						\
-	     (ca = bch2_get_next_dev(c, &(iter)));			\
-	     percpu_ref_put(&ca->ref), (iter)++)
+#define __for_each_member_device(_c, _ca)				\
+	for (;	(_ca = bch2_get_next_dev(_c, _ca));)
+
+#define for_each_member_device(_c, _ca)					\
+	for (struct bch_dev *_ca = NULL;				\
+	     (_ca = bch2_get_next_dev(_c, _ca));)
 
 static inline struct bch_dev *bch2_get_next_online_dev(struct bch_fs *c,
-						      unsigned *iter,
-						      int state_mask)
+						       struct bch_dev *ca,
+						       unsigned state_mask)
 {
-	struct bch_dev *ca;
+	if (ca)
+		percpu_ref_put(&ca->io_ref);
 
 	rcu_read_lock();
-	while ((ca = __bch2_next_dev(c, iter, NULL)) &&
+	while ((ca = __bch2_next_dev(c, ca, NULL)) &&
 	       (!((1 << ca->mi.state) & state_mask) ||
 		!percpu_ref_tryget(&ca->io_ref)))
-		(*iter)++;
+		;
 	rcu_read_unlock();
 
 	return ca;
 }
 
-#define __for_each_online_member(ca, c, iter, state_mask)		\
-	for ((iter) = 0;						\
-	     (ca = bch2_get_next_online_dev(c, &(iter), state_mask));	\
-	     percpu_ref_put(&ca->io_ref), (iter)++)
+#define __for_each_online_member(_c, _ca, state_mask)			\
+	for (struct bch_dev *_ca = NULL;				\
+	     (_ca = bch2_get_next_online_dev(_c, _ca, state_mask));)
 
-#define for_each_online_member(ca, c, iter)				\
-	__for_each_online_member(ca, c, iter, ~0)
+#define for_each_online_member(c, ca)					\
+	__for_each_online_member(c, ca, ~0)
 
-#define for_each_rw_member(ca, c, iter)					\
-	__for_each_online_member(ca, c, iter, 1 << BCH_MEMBER_STATE_rw)
+#define for_each_rw_member(c, ca)					\
+	__for_each_online_member(c, ca, BIT(BCH_MEMBER_STATE_rw))
 
-#define for_each_readable_member(ca, c, iter)				\
-	__for_each_online_member(ca, c, iter,				\
-		(1 << BCH_MEMBER_STATE_rw)|(1 << BCH_MEMBER_STATE_ro))
+#define for_each_readable_member(c, ca)				\
+	__for_each_online_member(c, ca,	BIT( BCH_MEMBER_STATE_rw)|BIT(BCH_MEMBER_STATE_ro))
 
 /*
  * If a key exists that references a device, the device won't be going away and
@@ -175,11 +181,9 @@ static inline struct bch_dev *bch_dev_locked(struct bch_fs *c, unsigned idx)
 static inline struct bch_devs_mask bch2_online_devs(struct bch_fs *c)
 {
 	struct bch_devs_mask devs;
-	struct bch_dev *ca;
-	unsigned i;
 
 	memset(&devs, 0, sizeof(devs));
-	for_each_online_member(ca, c, i)
+	for_each_online_member(c, ca)
 		__set_bit(ca->dev_idx, devs.d);
 	return devs;
 }
diff --git a/fs/bcachefs/six.c b/fs/bcachefs/six.c
index b775cf0fb7cb..3a494c5d1247 100644
--- a/fs/bcachefs/six.c
+++ b/fs/bcachefs/six.c
@@ -163,8 +163,11 @@ static int __do_six_trylock(struct six_lock *lock, enum six_lock_type type,
 		this_cpu_sub(*lock->readers, !ret);
 		preempt_enable();
 
-		if (!ret && (old & SIX_LOCK_WAITING_write))
-			ret = -1 - SIX_LOCK_write;
+		if (!ret) {
+			smp_mb();
+			if (atomic_read(&lock->state) & SIX_LOCK_WAITING_write)
+				ret = -1 - SIX_LOCK_write;
+		}
 	} else if (type == SIX_LOCK_write && lock->readers) {
 		if (try) {
 			atomic_add(SIX_LOCK_HELD_write, &lock->state);
@@ -321,101 +324,57 @@ bool six_relock_ip(struct six_lock *lock, enum six_lock_type type,
 }
 EXPORT_SYMBOL_GPL(six_relock_ip);
 
-#ifdef CONFIG_SIX_LOCK_SPIN_ON_OWNER
+#ifdef CONFIG_BCACHEFS_SIX_OPTIMISTIC_SPIN
 
-static inline bool six_can_spin_on_owner(struct six_lock *lock)
+static inline bool six_owner_running(struct six_lock *lock)
 {
-	struct task_struct *owner;
-	bool ret;
-
-	if (need_resched())
-		return false;
-
+	/*
+	 * When there's no owner, we might have preempted between the owner
+	 * acquiring the lock and setting the owner field. If we're an RT task
+	 * that will live-lock because we won't let the owner complete.
+	 */
 	rcu_read_lock();
-	owner = READ_ONCE(lock->owner);
-	ret = !owner || owner_on_cpu(owner);
+	struct task_struct *owner = READ_ONCE(lock->owner);
+	bool ret = owner ? owner_on_cpu(owner) : !rt_task(current);
 	rcu_read_unlock();
 
 	return ret;
 }
 
-static inline bool six_spin_on_owner(struct six_lock *lock,
-				     struct task_struct *owner,
-				     u64 end_time)
+static inline bool six_optimistic_spin(struct six_lock *lock,
+				       struct six_lock_waiter *wait,
+				       enum six_lock_type type)
 {
-	bool ret = true;
 	unsigned loop = 0;
-
-	rcu_read_lock();
-	while (lock->owner == owner) {
-		/*
-		 * Ensure we emit the owner->on_cpu, dereference _after_
-		 * checking lock->owner still matches owner. If that fails,
-		 * owner might point to freed memory. If it still matches,
-		 * the rcu_read_lock() ensures the memory stays valid.
-		 */
-		barrier();
-
-		if (!owner_on_cpu(owner) || need_resched()) {
-			ret = false;
-			break;
-		}
-
-		if (!(++loop & 0xf) && (time_after64(sched_clock(), end_time))) {
-			six_set_bitmask(lock, SIX_LOCK_NOSPIN);
-			ret = false;
-			break;
-		}
-
-		cpu_relax();
-	}
-	rcu_read_unlock();
-
-	return ret;
-}
-
-static inline bool six_optimistic_spin(struct six_lock *lock, enum six_lock_type type)
-{
-	struct task_struct *task = current;
 	u64 end_time;
 
 	if (type == SIX_LOCK_write)
 		return false;
 
-	preempt_disable();
-	if (!six_can_spin_on_owner(lock))
-		goto fail;
+	if (lock->wait_list.next != &wait->list)
+		return false;
 
-	if (!osq_lock(&lock->osq))
-		goto fail;
+	if (atomic_read(&lock->state) & SIX_LOCK_NOSPIN)
+		return false;
 
+	preempt_disable();
 	end_time = sched_clock() + 10 * NSEC_PER_USEC;
 
-	while (1) {
-		struct task_struct *owner;
-
+	while (!need_resched() && six_owner_running(lock)) {
 		/*
-		 * If there's an owner, wait for it to either
-		 * release the lock or go to sleep.
+		 * Ensures that writes to the waitlist entry happen after we see
+		 * wait->lock_acquired: pairs with the smp_store_release in
+		 * __six_lock_wakeup
 		 */
-		owner = READ_ONCE(lock->owner);
-		if (owner && !six_spin_on_owner(lock, owner, end_time))
-			break;
-
-		if (do_six_trylock(lock, type, false)) {
-			osq_unlock(&lock->osq);
+		if (smp_load_acquire(&wait->lock_acquired)) {
 			preempt_enable();
 			return true;
 		}
 
-		/*
-		 * When there's no owner, we might have preempted between the
-		 * owner acquiring the lock and setting the owner field. If
-		 * we're an RT task that will live-lock because we won't let
-		 * the owner complete.
-		 */
-		if (!owner && (need_resched() || rt_task(task)))
+		if (!(++loop & 0xf) && (time_after64(sched_clock(), end_time))) {
+			six_set_bitmask(lock, SIX_LOCK_NOSPIN);
 			break;
+		}
 
 		/*
 		 * The cpu_relax() call is a compiler barrier which forces
@@ -426,24 +385,15 @@ static inline bool six_optimistic_spin(struct six_lock *lock, enum six_lock_type
 		cpu_relax();
 	}
 
-	osq_unlock(&lock->osq);
-fail:
 	preempt_enable();
-
-	/*
-	 * If we fell out of the spin path because of need_resched(),
-	 * reschedule now, before we try-lock again. This avoids getting
-	 * scheduled out right after we obtained the lock.
-	 */
-	if (need_resched())
-		schedule();
-
 	return false;
 }
 
-#else /* CONFIG_SIX_LOCK_SPIN_ON_OWNER */
+#else /* CONFIG_LOCK_SPIN_ON_OWNER */
 
-static inline bool six_optimistic_spin(struct six_lock *lock, enum six_lock_type type)
+static inline bool six_optimistic_spin(struct six_lock *lock,
+				       struct six_lock_waiter *wait,
+				       enum six_lock_type type)
 {
 	return false;
 }
@@ -467,9 +417,6 @@ static int six_lock_slowpath(struct six_lock *lock, enum six_lock_type type,
 	trace_contention_begin(lock, 0);
 	lock_contended(&lock->dep_map, ip);
 
-	if (six_optimistic_spin(lock, type))
-		goto out;
-
 	wait->task		= current;
 	wait->lock_want		= type;
 	wait->lock_acquired	= false;
@@ -507,6 +454,9 @@ static int six_lock_slowpath(struct six_lock *lock, enum six_lock_type type,
 		ret = 0;
 	}
 
+	if (six_optimistic_spin(lock, wait, type))
+		goto out;
+
 	while (1) {
 		set_current_state(TASK_UNINTERRUPTIBLE);
 
diff --git a/fs/bcachefs/six.h b/fs/bcachefs/six.h
index 4c268b0b8316..68d46fd7f391 100644
--- a/fs/bcachefs/six.h
+++ b/fs/bcachefs/six.h
@@ -15,7 +15,7 @@
  * will have to take write locks for the full duration of the operation.
  *
  * But by adding an intent state, which is exclusive with other intent locks but
- * not with readers, we can take intent locks at thte start of the operation,
+ * not with readers, we can take intent locks at the start of the operation,
  * and then take write locks only for the actual update to each individual
  * nodes, without deadlocking.
  *
@@ -65,8 +65,8 @@
  *
  * Reentrancy:
  *
- *   Six locks are not by themselves reentrent, but have counters for both the
- *   read and intent states that can be used to provide reentrency by an upper
+ *   Six locks are not by themselves reentrant, but have counters for both the
+ *   read and intent states that can be used to provide reentrancy by an upper
  *   layer that tracks held locks. If a lock is known to already be held in the
  *   read or intent state, six_lock_increment() can be used to bump the "lock
  *   held in this state" counter, increasing the number of unlock calls that
@@ -127,10 +127,6 @@
 #include <linux/sched.h>
 #include <linux/types.h>
 
-#ifdef CONFIG_SIX_LOCK_SPIN_ON_OWNER
-#include <linux/osq_lock.h>
-#endif
-
 enum six_lock_type {
 	SIX_LOCK_read,
 	SIX_LOCK_intent,
@@ -143,9 +139,6 @@ struct six_lock {
 	unsigned		intent_lock_recurse;
 	struct task_struct	*owner;
 	unsigned __percpu	*readers;
-#ifdef CONFIG_SIX_LOCK_SPIN_ON_OWNER
-	struct optimistic_spin_queue osq;
-#endif
 	raw_spinlock_t		wait_lock;
 	struct list_head	wait_list;
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c
index e9af77b384c7..56af937523ff 100644
--- a/fs/bcachefs/snapshot.c
+++ b/fs/bcachefs/snapshot.c
@@ -123,7 +123,7 @@ bool __bch2_snapshot_is_ancestor(struct bch_fs *c, u32 id, u32 ancestor)
 	struct snapshot_table *t;
 	bool ret;
 
-	EBUG_ON(c->curr_recovery_pass <= BCH_RECOVERY_PASS_check_snapshots);
+	EBUG_ON(c->recovery_pass_done <= BCH_RECOVERY_PASS_check_snapshots);
 
 	rcu_read_lock();
 	t = rcu_dereference(c->snapshots);
@@ -276,7 +276,7 @@ static void set_is_ancestor_bitmap(struct bch_fs *c, u32 id)
 	mutex_unlock(&c->snapshot_table_lock);
 }
 
-int bch2_mark_snapshot(struct btree_trans *trans,
+static int __bch2_mark_snapshot(struct btree_trans *trans,
 		       enum btree_id btree, unsigned level,
 		       struct bkey_s_c old, struct bkey_s_c new,
 		       unsigned flags)
@@ -318,7 +318,7 @@ int bch2_mark_snapshot(struct btree_trans *trans,
 		__set_is_ancestor_bitmap(c, id);
 
 		if (BCH_SNAPSHOT_DELETED(s.v)) {
-			set_bit(BCH_FS_NEED_DELETE_DEAD_SNAPSHOTS, &c->flags);
+			set_bit(BCH_FS_need_delete_dead_snapshots, &c->flags);
 			if (c->curr_recovery_pass > BCH_RECOVERY_PASS_delete_dead_snapshots)
 				bch2_delete_dead_snapshots_async(c);
 		}
@@ -330,6 +330,14 @@ err:
 	return ret;
 }
 
+int bch2_mark_snapshot(struct btree_trans *trans,
+		       enum btree_id btree, unsigned level,
+		       struct bkey_s_c old, struct bkey_s new,
+		       unsigned flags)
+{
+	return __bch2_mark_snapshot(trans, btree, level, old, new.s_c, flags);
+}
+
 int bch2_snapshot_lookup(struct btree_trans *trans, u32 id,
 			 struct bch_snapshot *s)
 {
@@ -459,7 +467,6 @@ static int bch2_snapshot_tree_master_subvol(struct btree_trans *trans,
 	struct bch_fs *c = trans->c;
 	struct btree_iter iter;
 	struct bkey_s_c k;
-	struct bkey_s_c_subvolume s;
 	bool found = false;
 	int ret;
 
@@ -468,7 +475,7 @@ static int bch2_snapshot_tree_master_subvol(struct btree_trans *trans,
 		if (k.k->type != KEY_TYPE_subvolume)
 			continue;
 
-		s = bkey_s_c_to_subvolume(k);
+		struct bkey_s_c_subvolume s = bkey_s_c_to_subvolume(k);
 		if (!bch2_snapshot_is_ancestor(c, le32_to_cpu(s.v->snapshot), snapshot_root))
 			continue;
 		if (!BCH_SUBVOLUME_SNAP(s.v)) {
@@ -582,19 +589,13 @@ fsck_err:
  */
 int bch2_check_snapshot_trees(struct bch_fs *c)
 {
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	int ret;
-
-	ret = bch2_trans_run(c,
+	int ret = bch2_trans_run(c,
 		for_each_btree_key_commit(trans, iter,
 			BTREE_ID_snapshot_trees, POS_MIN,
 			BTREE_ITER_PREFETCH, k,
-			NULL, NULL, BTREE_INSERT_LAZY_RW|BTREE_INSERT_NOFAIL,
+			NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 		check_snapshot_tree(trans, &iter, k)));
-
-	if (ret)
-		bch_err(c, "error %i checking snapshot trees", ret);
+	bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -813,11 +814,10 @@ static int check_snapshot(struct btree_trans *trans,
 
 	real_depth = bch2_snapshot_depth(c, parent_id);
 
-	if (le32_to_cpu(s.depth) != real_depth &&
-	    (c->sb.version_upgrade_complete < bcachefs_metadata_version_snapshot_skiplists ||
-	     fsck_err(c, snapshot_bad_depth,
-		      "snapshot with incorrect depth field, should be %u:\n  %s",
-		      real_depth, (bch2_bkey_val_to_text(&buf, c, k), buf.buf)))) {
+	if (fsck_err_on(le32_to_cpu(s.depth) != real_depth,
+			c, snapshot_bad_depth,
+			"snapshot with incorrect depth field, should be %u:\n  %s",
+			real_depth, (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) {
 		u = bch2_bkey_make_mut_typed(trans, iter, &k, 0, snapshot);
 		ret = PTR_ERR_OR_ZERO(u);
 		if (ret)
@@ -831,11 +831,9 @@ static int check_snapshot(struct btree_trans *trans,
 	if (ret < 0)
 		goto err;
 
-	if (!ret &&
-	    (c->sb.version_upgrade_complete < bcachefs_metadata_version_snapshot_skiplists ||
-	     fsck_err(c, snapshot_bad_skiplist,
-		      "snapshot with bad skiplist field:\n  %s",
-		      (bch2_bkey_val_to_text(&buf, c, k), buf.buf)))) {
+	if (fsck_err_on(!ret, c, snapshot_bad_skiplist,
+			"snapshot with bad skiplist field:\n  %s",
+			(bch2_bkey_val_to_text(&buf, c, k), buf.buf))) {
 		u = bch2_bkey_make_mut_typed(trans, iter, &k, 0, snapshot);
 		ret = PTR_ERR_OR_ZERO(u);
 		if (ret)
@@ -856,22 +854,17 @@ fsck_err:
 
 int bch2_check_snapshots(struct bch_fs *c)
 {
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	int ret;
-
 	/*
 	 * We iterate backwards as checking/fixing the depth field requires that
 	 * the parent's depth already be correct:
 	 */
-	ret = bch2_trans_run(c,
+	int ret = bch2_trans_run(c,
 		for_each_btree_key_reverse_commit(trans, iter,
-			BTREE_ID_snapshots, POS_MAX,
-			BTREE_ITER_PREFETCH, k,
-			NULL, NULL, BTREE_INSERT_LAZY_RW|BTREE_INSERT_NOFAIL,
-		check_snapshot(trans, &iter, k)));
-	if (ret)
-		bch_err_fn(c, ret);
+				BTREE_ID_snapshots, POS_MAX,
+				BTREE_ITER_PREFETCH, k,
+				NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
+			check_snapshot(trans, &iter, k)));
+	bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -959,7 +952,7 @@ static int bch2_snapshot_node_delete(struct btree_trans *trans, u32 id)
 					parent_id, id))
 			goto err;
 
-		parent->v.children[i] = le32_to_cpu(child_id);
+		parent->v.children[i] = cpu_to_le32(child_id);
 
 		normalize_snapshot_child_pointers(&parent->v);
 	}
@@ -1067,7 +1060,7 @@ static int create_snapids(struct btree_trans *trans, u32 parent, u32 tree,
 		bubble_sort(n->v.skip, ARRAY_SIZE(n->v.skip), cmp_le32);
 		SET_BCH_SNAPSHOT_SUBVOL(&n->v, true);
 
-		ret = bch2_mark_snapshot(trans, BTREE_ID_snapshots, 0,
+		ret = __bch2_mark_snapshot(trans, BTREE_ID_snapshots, 0,
 					 bkey_s_c_null, bkey_i_to_s_c(&n->k_i), 0);
 		if (ret)
 			goto err;
@@ -1315,7 +1308,6 @@ static int bch2_fix_child_of_deleted_snapshot(struct btree_trans *trans,
 	struct bch_fs *c = trans->c;
 	u32 nr_deleted_ancestors = 0;
 	struct bkey_i_snapshot *s;
-	u32 *i;
 	int ret;
 
 	if (k.k->type != KEY_TYPE_snapshot)
@@ -1368,23 +1360,19 @@ static int bch2_fix_child_of_deleted_snapshot(struct btree_trans *trans,
 int bch2_delete_dead_snapshots(struct bch_fs *c)
 {
 	struct btree_trans *trans;
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	struct bkey_s_c_snapshot snap;
 	snapshot_id_list deleted = { 0 };
 	snapshot_id_list deleted_interior = { 0 };
-	u32 *i, id;
+	u32 id;
 	int ret = 0;
 
-	if (!test_and_clear_bit(BCH_FS_NEED_DELETE_DEAD_SNAPSHOTS, &c->flags))
+	if (!test_and_clear_bit(BCH_FS_need_delete_dead_snapshots, &c->flags))
 		return 0;
 
-	if (!test_bit(BCH_FS_STARTED, &c->flags)) {
+	if (!test_bit(BCH_FS_started, &c->flags)) {
 		ret = bch2_fs_read_write_early(c);
-		if (ret) {
-			bch_err_msg(c, ret, "deleting dead snapshots: error going rw");
+		bch_err_msg(c, ret, "deleting dead snapshots: error going rw");
+		if (ret)
 			return ret;
-		}
 	}
 
 	trans = bch2_trans_get(c);
@@ -1397,37 +1385,29 @@ int bch2_delete_dead_snapshots(struct bch_fs *c)
 			POS_MIN, 0, k,
 			NULL, NULL, 0,
 		bch2_delete_redundant_snapshot(trans, k));
-	if (ret) {
-		bch_err_msg(c, ret, "deleting redundant snapshots");
+	bch_err_msg(c, ret, "deleting redundant snapshots");
+	if (ret)
 		goto err;
-	}
 
-	ret = for_each_btree_key2(trans, iter, BTREE_ID_snapshots,
-				  POS_MIN, 0, k,
+	ret = for_each_btree_key(trans, iter, BTREE_ID_snapshots,
+				 POS_MIN, 0, k,
 		bch2_snapshot_set_equiv(trans, k));
-	if (ret) {
-		bch_err_msg(c, ret, "in bch2_snapshots_set_equiv");
+	bch_err_msg(c, ret, "in bch2_snapshots_set_equiv");
+	if (ret)
 		goto err;
-	}
 
-	for_each_btree_key(trans, iter, BTREE_ID_snapshots,
-			   POS_MIN, 0, k, ret) {
+	ret = for_each_btree_key(trans, iter, BTREE_ID_snapshots,
+				 POS_MIN, 0, k, ({
 		if (k.k->type != KEY_TYPE_snapshot)
 			continue;
 
-		snap = bkey_s_c_to_snapshot(k);
-		if (BCH_SNAPSHOT_DELETED(snap.v)) {
-			ret = snapshot_list_add(c, &deleted, k.k->p.offset);
-			if (ret)
-				break;
-		}
-	}
-	bch2_trans_iter_exit(trans, &iter);
-
-	if (ret) {
-		bch_err_msg(c, ret, "walking snapshots");
+		BCH_SNAPSHOT_DELETED(bkey_s_c_to_snapshot(k).v)
+			? snapshot_list_add(c, &deleted, k.k->p.offset)
+			: 0;
+	}));
+	bch_err_msg(c, ret, "walking snapshots");
+	if (ret)
 		goto err;
-	}
 
 	for (id = 0; id < BTREE_ID_NR; id++) {
 		struct bpos last_pos = POS_MIN;
@@ -1449,36 +1429,36 @@ int bch2_delete_dead_snapshots(struct bch_fs *c)
 		ret = for_each_btree_key_commit(trans, iter,
 				id, POS_MIN,
 				BTREE_ITER_PREFETCH|BTREE_ITER_ALL_SNAPSHOTS, k,
-				&res, NULL, BTREE_INSERT_NOFAIL,
+				&res, NULL, BCH_TRANS_COMMIT_no_enospc,
 			snapshot_delete_key(trans, &iter, k, &deleted, &equiv_seen, &last_pos)) ?:
 		      for_each_btree_key_commit(trans, iter,
 				id, POS_MIN,
 				BTREE_ITER_PREFETCH|BTREE_ITER_ALL_SNAPSHOTS, k,
-				&res, NULL, BTREE_INSERT_NOFAIL,
+				&res, NULL, BCH_TRANS_COMMIT_no_enospc,
 			move_key_to_correct_snapshot(trans, &iter, k));
 
 		bch2_disk_reservation_put(c, &res);
 		darray_exit(&equiv_seen);
 
-		if (ret) {
-			bch_err_msg(c, ret, "deleting keys from dying snapshots");
+		bch_err_msg(c, ret, "deleting keys from dying snapshots");
+		if (ret)
 			goto err;
-		}
 	}
 
 	bch2_trans_unlock(trans);
 	down_write(&c->snapshot_create_lock);
 
-	for_each_btree_key(trans, iter, BTREE_ID_snapshots,
-			   POS_MIN, 0, k, ret) {
+	ret = for_each_btree_key(trans, iter, BTREE_ID_snapshots,
+				 POS_MIN, 0, k, ({
 		u32 snapshot = k.k->p.offset;
 		u32 equiv = bch2_snapshot_equiv(c, snapshot);
 
-		if (equiv != snapshot)
-			snapshot_list_add(c, &deleted_interior, snapshot);
-	}
-	bch2_trans_iter_exit(trans, &iter);
+		equiv != snapshot
+			? snapshot_list_add(c, &deleted_interior, snapshot)
+			: 0;
+	}));
 
+	bch_err_msg(c, ret, "walking snapshots");
 	if (ret)
 		goto err_create_lock;
 
@@ -1489,7 +1469,7 @@ int bch2_delete_dead_snapshots(struct bch_fs *c)
 	 */
 	ret = for_each_btree_key_commit(trans, iter, BTREE_ID_snapshots, POS_MIN,
 				  BTREE_ITER_INTENT, k,
-				  NULL, NULL, BTREE_INSERT_NOFAIL,
+				  NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 		bch2_fix_child_of_deleted_snapshot(trans, &iter, k, &deleted_interior));
 	if (ret)
 		goto err_create_lock;
@@ -1497,19 +1477,17 @@ int bch2_delete_dead_snapshots(struct bch_fs *c)
 	darray_for_each(deleted, i) {
 		ret = commit_do(trans, NULL, NULL, 0,
 			bch2_snapshot_node_delete(trans, *i));
-		if (ret) {
-			bch_err_msg(c, ret, "deleting snapshot %u", *i);
+		bch_err_msg(c, ret, "deleting snapshot %u", *i);
+		if (ret)
 			goto err_create_lock;
-		}
 	}
 
 	darray_for_each(deleted_interior, i) {
 		ret = commit_do(trans, NULL, NULL, 0,
 			bch2_snapshot_node_delete(trans, *i));
-		if (ret) {
-			bch_err_msg(c, ret, "deleting snapshot %u", *i);
+		bch_err_msg(c, ret, "deleting snapshot %u", *i);
+		if (ret)
 			goto err_create_lock;
-		}
 	}
 err_create_lock:
 	up_write(&c->snapshot_create_lock);
@@ -1517,8 +1495,7 @@ err:
 	darray_exit(&deleted_interior);
 	darray_exit(&deleted);
 	bch2_trans_put(trans);
-	if (ret)
-		bch_err_fn(c, ret);
+	bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -1680,7 +1657,7 @@ static int bch2_check_snapshot_needs_deletion(struct btree_trans *trans, struct
 	if (BCH_SNAPSHOT_DELETED(snap.v) ||
 	    bch2_snapshot_equiv(c, k.k->p.offset) != k.k->p.offset ||
 	    (ret = bch2_snapshot_needs_delete(trans, k)) > 0) {
-		set_bit(BCH_FS_NEED_DELETE_DEAD_SNAPSHOTS, &c->flags);
+		set_bit(BCH_FS_need_delete_dead_snapshots, &c->flags);
 		return 0;
 	}
 
@@ -1689,21 +1666,16 @@ static int bch2_check_snapshot_needs_deletion(struct btree_trans *trans, struct
 
 int bch2_snapshots_read(struct bch_fs *c)
 {
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	int ret = 0;
-
-	ret = bch2_trans_run(c,
-		for_each_btree_key2(trans, iter, BTREE_ID_snapshots,
-			   POS_MIN, 0, k,
-			bch2_mark_snapshot(trans, BTREE_ID_snapshots, 0, bkey_s_c_null, k, 0) ?:
+	int ret = bch2_trans_run(c,
+		for_each_btree_key(trans, iter, BTREE_ID_snapshots,
+				   POS_MIN, 0, k,
+			__bch2_mark_snapshot(trans, BTREE_ID_snapshots, 0, bkey_s_c_null, k, 0) ?:
 			bch2_snapshot_set_equiv(trans, k) ?:
 			bch2_check_snapshot_needs_deletion(trans, k)) ?:
-		for_each_btree_key2(trans, iter, BTREE_ID_snapshots,
-			   POS_MIN, 0, k,
+		for_each_btree_key(trans, iter, BTREE_ID_snapshots,
+				   POS_MIN, 0, k,
 			   (set_is_ancestor_bitmap(c, k.k->p.offset), 0)));
-	if (ret)
-		bch_err_fn(c, ret);
+	bch_err_fn(c, ret);
 	return ret;
 }
 
diff --git a/fs/bcachefs/snapshot.h b/fs/bcachefs/snapshot.h
index f09a22f44239..7c66ffc06385 100644
--- a/fs/bcachefs/snapshot.h
+++ b/fs/bcachefs/snapshot.h
@@ -22,12 +22,12 @@ void bch2_snapshot_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
 int bch2_snapshot_invalid(struct bch_fs *, struct bkey_s_c,
 			  enum bkey_invalid_flags, struct printbuf *);
 int bch2_mark_snapshot(struct btree_trans *, enum btree_id, unsigned,
-		       struct bkey_s_c, struct bkey_s_c, unsigned);
+		       struct bkey_s_c, struct bkey_s, unsigned);
 
 #define bch2_bkey_ops_snapshot ((struct bkey_ops) {		\
 	.key_invalid	= bch2_snapshot_invalid,		\
 	.val_to_text	= bch2_snapshot_to_text,		\
-	.atomic_trigger	= bch2_mark_snapshot,			\
+	.trigger	= bch2_mark_snapshot,			\
 	.min_val_size	= 24,					\
 })
 
@@ -202,8 +202,6 @@ static inline bool bch2_snapshot_has_children(struct bch_fs *c, u32 id)
 
 static inline bool snapshot_list_has_id(snapshot_id_list *s, u32 id)
 {
-	u32 *i;
-
 	darray_for_each(*s, i)
 		if (*i == id)
 			return true;
@@ -212,8 +210,6 @@ static inline bool snapshot_list_has_id(snapshot_id_list *s, u32 id)
 
 static inline bool snapshot_list_has_ancestor(struct bch_fs *c, snapshot_id_list *s, u32 id)
 {
-	u32 *i;
-
 	darray_for_each(*s, i)
 		if (bch2_snapshot_is_ancestor(c, id, *i))
 			return true;
diff --git a/fs/bcachefs/str_hash.h b/fs/bcachefs/str_hash.h
index ae21a8cca1b4..89fdb7c21134 100644
--- a/fs/bcachefs/str_hash.h
+++ b/fs/bcachefs/str_hash.h
@@ -15,6 +15,16 @@
 #include <crypto/hash.h>
 #include <crypto/sha2.h>
 
+typedef unsigned __bitwise bch_str_hash_flags_t;
+
+enum bch_str_hash_flags {
+	__BCH_HASH_SET_MUST_CREATE,
+	__BCH_HASH_SET_MUST_REPLACE,
+};
+
+#define BCH_HASH_SET_MUST_CREATE	(__force bch_str_hash_flags_t) BIT(__BCH_HASH_SET_MUST_CREATE)
+#define BCH_HASH_SET_MUST_REPLACE	(__force bch_str_hash_flags_t) BIT(__BCH_HASH_SET_MUST_REPLACE)
+
 static inline enum bch_str_hash_type
 bch2_str_hash_opt_to_type(struct bch_fs *c, enum bch_str_hash_opts opt)
 {
@@ -246,7 +256,7 @@ int bch2_hash_set_snapshot(struct btree_trans *trans,
 			   const struct bch_hash_info *info,
 			   subvol_inum inum, u32 snapshot,
 			   struct bkey_i *insert,
-			   int flags,
+			   bch_str_hash_flags_t str_hash_flags,
 			   int update_flags)
 {
 	struct btree_iter iter, slot = { NULL };
@@ -269,7 +279,7 @@ int bch2_hash_set_snapshot(struct btree_trans *trans,
 		}
 
 		if (!slot.path &&
-		    !(flags & BCH_HASH_SET_MUST_REPLACE))
+		    !(str_hash_flags & BCH_HASH_SET_MUST_REPLACE))
 			bch2_trans_copy_iter(&slot, &iter);
 
 		if (k.k->type != KEY_TYPE_hash_whiteout)
@@ -287,16 +297,16 @@ found:
 	found = true;
 not_found:
 
-	if (!found && (flags & BCH_HASH_SET_MUST_REPLACE)) {
+	if (!found && (str_hash_flags & BCH_HASH_SET_MUST_REPLACE)) {
 		ret = -BCH_ERR_ENOENT_str_hash_set_must_replace;
-	} else if (found && (flags & BCH_HASH_SET_MUST_CREATE)) {
+	} else if (found && (str_hash_flags & BCH_HASH_SET_MUST_CREATE)) {
 		ret = -EEXIST;
 	} else {
 		if (!found && slot.path)
 			swap(iter, slot);
 
 		insert->k.p = iter.pos;
-		ret = bch2_trans_update(trans, &iter, insert, 0);
+		ret = bch2_trans_update(trans, &iter, insert, update_flags);
 	}
 
 	goto out;
@@ -307,7 +317,8 @@ int bch2_hash_set(struct btree_trans *trans,
 		  const struct bch_hash_desc desc,
 		  const struct bch_hash_info *info,
 		  subvol_inum inum,
-		  struct bkey_i *insert, int flags)
+		  struct bkey_i *insert,
+		  bch_str_hash_flags_t str_hash_flags)
 {
 	u32 snapshot;
 	int ret;
@@ -319,7 +330,7 @@ int bch2_hash_set(struct btree_trans *trans,
 	insert->k.p.inode = inum.inum;
 
 	return bch2_hash_set_snapshot(trans, desc, info, inum,
-				      snapshot, insert, flags, 0);
+				      snapshot, insert, str_hash_flags, 0);
 }
 
 static __always_inline
diff --git a/fs/bcachefs/subvolume.c b/fs/bcachefs/subvolume.c
index fccd25aa3242..7c67c28d3ef8 100644
--- a/fs/bcachefs/subvolume.c
+++ b/fs/bcachefs/subvolume.c
@@ -37,11 +37,8 @@ static int check_subvol(struct btree_trans *trans,
 		return ret;
 
 	if (BCH_SUBVOLUME_UNLINKED(subvol.v)) {
-		bch2_fs_lazy_rw(c);
-
 		ret = bch2_subvolume_delete(trans, iter->pos.offset);
-		if (ret)
-			bch_err_msg(c, ret, "deleting subvolume %llu", iter->pos.offset);
+		bch_err_msg(c, ret, "deleting subvolume %llu", iter->pos.offset);
 		return ret ?: -BCH_ERR_transaction_restart_nested;
 	}
 
@@ -82,17 +79,12 @@ fsck_err:
 
 int bch2_check_subvols(struct bch_fs *c)
 {
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	int ret;
-
-	ret = bch2_trans_run(c,
+	int ret = bch2_trans_run(c,
 		for_each_btree_key_commit(trans, iter,
-			BTREE_ID_subvolumes, POS_MIN, BTREE_ITER_PREFETCH, k,
-			NULL, NULL, BTREE_INSERT_LAZY_RW|BTREE_INSERT_NOFAIL,
-		check_subvol(trans, &iter, k)));
-	if (ret)
-		bch_err_fn(c, ret);
+				BTREE_ID_subvolumes, POS_MIN, BTREE_ITER_PREFETCH, k,
+				NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
+			check_subvol(trans, &iter, k)));
+	bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -146,6 +138,24 @@ int bch2_subvolume_get(struct btree_trans *trans, unsigned subvol,
 	return bch2_subvolume_get_inlined(trans, subvol, inconsistent_if_not_found, iter_flags, s);
 }
 
+int bch2_subvol_is_ro_trans(struct btree_trans *trans, u32 subvol)
+{
+	struct bch_subvolume s;
+	int ret = bch2_subvolume_get_inlined(trans, subvol, true, 0, &s);
+	if (ret)
+		return ret;
+
+	if (BCH_SUBVOLUME_RO(&s))
+		return -EROFS;
+	return 0;
+}
+
+int bch2_subvol_is_ro(struct bch_fs *c, u32 subvol)
+{
+	return bch2_trans_do(c, NULL, NULL, 0,
+		bch2_subvol_is_ro_trans(trans, subvol));
+}
+
 int bch2_snapshot_get_subvol(struct btree_trans *trans, u32 snapshot,
 			     struct bch_subvolume *subvol)
 {
@@ -210,8 +220,6 @@ static int bch2_subvolume_reparent(struct btree_trans *trans,
  */
 static int bch2_subvolumes_reparent(struct btree_trans *trans, u32 subvolid_to_delete)
 {
-	struct btree_iter iter;
-	struct bkey_s_c k;
 	struct bch_subvolume s;
 
 	return lockrestart_do(trans,
@@ -219,7 +227,7 @@ static int bch2_subvolumes_reparent(struct btree_trans *trans, u32 subvolid_to_d
 				   BTREE_ITER_CACHED, &s)) ?:
 		for_each_btree_key_commit(trans, iter,
 				BTREE_ID_subvolumes, POS_MIN, BTREE_ITER_PREFETCH, k,
-				NULL, NULL, BTREE_INSERT_NOFAIL,
+				NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 			bch2_subvolume_reparent(trans, &iter, k,
 					subvolid_to_delete, le32_to_cpu(s.parent)));
 }
@@ -256,7 +264,7 @@ static int __bch2_subvolume_delete(struct btree_trans *trans, u32 subvolid)
 static int bch2_subvolume_delete(struct btree_trans *trans, u32 subvolid)
 {
 	return bch2_subvolumes_reparent(trans, subvolid) ?:
-		commit_do(trans, NULL, NULL, BTREE_INSERT_NOFAIL,
+		commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 			  __bch2_subvolume_delete(trans, subvolid));
 }
 
@@ -281,10 +289,9 @@ static void bch2_subvolume_wait_for_pagecache_and_delete(struct work_struct *wor
 
 		for (id = s.data; id < s.data + s.nr; id++) {
 			ret = bch2_trans_run(c, bch2_subvolume_delete(trans, *id));
-			if (ret) {
-				bch_err_msg(c, ret, "deleting subvolume %u", *id);
+			bch_err_msg(c, ret, "deleting subvolume %u", *id);
+			if (ret)
 				break;
-			}
 		}
 
 		darray_exit(&s);
diff --git a/fs/bcachefs/subvolume.h b/fs/bcachefs/subvolume.h
index a1003d30ab0a..a6f56f66e27c 100644
--- a/fs/bcachefs/subvolume.h
+++ b/fs/bcachefs/subvolume.h
@@ -23,6 +23,9 @@ int bch2_subvolume_get(struct btree_trans *, unsigned,
 		       bool, int, struct bch_subvolume *);
 int bch2_subvolume_get_snapshot(struct btree_trans *, u32, u32 *);
 
+int bch2_subvol_is_ro_trans(struct btree_trans *, u32);
+int bch2_subvol_is_ro(struct bch_fs *, u32);
+
 int bch2_delete_dead_snapshots(struct bch_fs *);
 void bch2_delete_dead_snapshots_async(struct bch_fs *);
 
diff --git a/fs/bcachefs/subvolume_types.h b/fs/bcachefs/subvolume_types.h
index 86833445af20..ae644adfc391 100644
--- a/fs/bcachefs/subvolume_types.h
+++ b/fs/bcachefs/subvolume_types.h
@@ -20,7 +20,11 @@ struct snapshot_t {
 };
 
 struct snapshot_table {
+#ifndef RUST_BINDGEN
+	DECLARE_FLEX_ARRAY(struct snapshot_t, s);
+#else
 	struct snapshot_t	s[0];
+#endif
 };
 
 typedef struct {
diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c
index f4cad903f4d6..6d3db5cce5f6 100644
--- a/fs/bcachefs/super-io.c
+++ b/fs/bcachefs/super-io.c
@@ -13,6 +13,7 @@
 #include "replicas.h"
 #include "quota.h"
 #include "sb-clean.h"
+#include "sb-downgrade.h"
 #include "sb-errors.h"
 #include "sb-members.h"
 #include "super-io.h"
@@ -29,14 +30,12 @@ static const struct blk_holder_ops bch2_sb_handle_bdev_ops = {
 struct bch2_metadata_version {
 	u16		version;
 	const char	*name;
-	u64		recovery_passes;
 };
 
 static const struct bch2_metadata_version bch2_metadata_versions[] = {
-#define x(n, v, _recovery_passes) {		\
+#define x(n, v) {		\
 	.version = v,				\
 	.name = #n,				\
-	.recovery_passes = _recovery_passes,	\
 },
 	BCH_METADATA_VERSIONS()
 #undef x
@@ -69,24 +68,6 @@ unsigned bch2_latest_compatible_version(unsigned v)
 	return v;
 }
 
-u64 bch2_upgrade_recovery_passes(struct bch_fs *c,
-				 unsigned old_version,
-				 unsigned new_version)
-{
-	u64 ret = 0;
-
-	for (const struct bch2_metadata_version *i = bch2_metadata_versions;
-	     i < bch2_metadata_versions + ARRAY_SIZE(bch2_metadata_versions);
-	     i++)
-		if (i->version > old_version && i->version <= new_version) {
-			if (i->recovery_passes & RECOVERY_PASS_ALL_FSCK)
-				ret |= bch2_fsck_recovery_passes();
-			ret |= i->recovery_passes;
-		}
-
-	return ret &= ~RECOVERY_PASS_ALL_FSCK;
-}
-
 const char * const bch2_sb_fields[] = {
 #define x(name, nr)	#name,
 	BCH_SB_FIELDS()
@@ -100,8 +81,6 @@ static int bch2_sb_field_validate(struct bch_sb *, struct bch_sb_field *,
 struct bch_sb_field *bch2_sb_field_get_id(struct bch_sb *sb,
 				      enum bch_sb_field_type type)
 {
-	struct bch_sb_field *f;
-
 	/* XXX: need locking around superblock to access optional fields */
 
 	vstruct_for_each(sb, f)
@@ -163,9 +142,10 @@ void bch2_sb_field_delete(struct bch_sb_handle *sb,
 void bch2_free_super(struct bch_sb_handle *sb)
 {
 	kfree(sb->bio);
-	if (!IS_ERR_OR_NULL(sb->bdev))
-		blkdev_put(sb->bdev, sb->holder);
+	if (!IS_ERR_OR_NULL(sb->bdev_handle))
+		bdev_release(sb->bdev_handle);
 	kfree(sb->holder);
+	kfree(sb->sb_name);
 
 	kfree(sb->sb);
 	memset(sb, 0, sizeof(*sb));
@@ -190,8 +170,12 @@ int bch2_sb_realloc(struct bch_sb_handle *sb, unsigned u64s)
 		u64 max_bytes = 512 << sb->sb->layout.sb_max_size_bits;
 
 		if (new_bytes > max_bytes) {
-			pr_err("%pg: superblock too big: want %zu but have %llu",
-			       sb->bdev, new_bytes, max_bytes);
+			struct printbuf buf = PRINTBUF;
+
+			prt_bdevname(&buf, sb->bdev);
+			prt_printf(&buf, ": superblock too big: want %zu but have %llu", new_bytes, max_bytes);
+			pr_err("%s", buf.buf);
+			printbuf_exit(&buf);
 			return -BCH_ERR_ENOSPC_sb;
 		}
 	}
@@ -239,14 +223,12 @@ struct bch_sb_field *bch2_sb_field_resize_id(struct bch_sb_handle *sb,
 
 	if (sb->fs_sb) {
 		struct bch_fs *c = container_of(sb, struct bch_fs, disk_sb);
-		struct bch_dev *ca;
-		unsigned i;
 
 		lockdep_assert_held(&c->sb_lock);
 
 		/* XXX: we're not checking that offline device have enough space */
 
-		for_each_online_member(ca, c, i) {
+		for_each_online_member(c, ca) {
 			struct bch_sb_handle *dev_sb = &ca->disk_sb;
 
 			if (bch2_sb_realloc(dev_sb, le32_to_cpu(dev_sb->sb->u64s) + d)) {
@@ -263,6 +245,17 @@ struct bch_sb_field *bch2_sb_field_resize_id(struct bch_sb_handle *sb,
 	return f;
 }
 
+struct bch_sb_field *bch2_sb_field_get_minsize_id(struct bch_sb_handle *sb,
+						  enum bch_sb_field_type type,
+						  unsigned u64s)
+{
+	struct bch_sb_field *f = bch2_sb_field_get_id(sb->sb, type);
+
+	if (!f || le32_to_cpu(f->u64s) < u64s)
+		f = bch2_sb_field_resize_id(sb, type, u64s);
+	return f;
+}
+
 /* Superblock validate: */
 
 static int validate_sb_layout(struct bch_sb_layout *layout, struct printbuf *out)
@@ -355,7 +348,6 @@ static int bch2_sb_validate(struct bch_sb_handle *disk_sb, struct printbuf *out,
 			    int rw)
 {
 	struct bch_sb *sb = disk_sb->sb;
-	struct bch_sb_field *f;
 	struct bch_sb_field_members_v1 *mi;
 	enum bch_opt_id opt_id;
 	u16 block_size;
@@ -483,11 +475,24 @@ static int bch2_sb_validate(struct bch_sb_handle *disk_sb, struct printbuf *out,
 
 /* device open: */
 
+static unsigned long le_ulong_to_cpu(unsigned long v)
+{
+	return sizeof(unsigned long) == 8
+		? le64_to_cpu(v)
+		: le32_to_cpu(v);
+}
+
+static void le_bitvector_to_cpu(unsigned long *dst, unsigned long *src, unsigned nr)
+{
+	BUG_ON(nr & (BITS_PER_TYPE(long) - 1));
+
+	for (unsigned i = 0; i < BITS_TO_LONGS(nr); i++)
+		dst[i] = le_ulong_to_cpu(src[i]);
+}
+
 static void bch2_sb_update(struct bch_fs *c)
 {
 	struct bch_sb *src = c->disk_sb.sb;
-	struct bch_dev *ca;
-	unsigned i;
 
 	lockdep_assert_held(&c->sb_lock);
 
@@ -511,8 +516,15 @@ static void bch2_sb_update(struct bch_fs *c)
 	c->sb.features		= le64_to_cpu(src->features[0]);
 	c->sb.compat		= le64_to_cpu(src->compat[0]);
 
-	for_each_member_device(ca, c, i) {
-		struct bch_member m = bch2_sb_member_get(src, i);
+	memset(c->sb.errors_silent, 0, sizeof(c->sb.errors_silent));
+
+	struct bch_sb_field_ext *ext = bch2_sb_field_get(src, ext);
+	if (ext)
+		le_bitvector_to_cpu(c->sb.errors_silent, (void *) ext->errors_silent,
+				    sizeof(c->sb.errors_silent) * 8);
+
+	for_each_member_device(c, ca) {
+		struct bch_member m = bch2_sb_member_get(src, ca->dev_idx);
 		ca->mi = bch2_mi_to_cpu(&m);
 	}
 }
@@ -536,6 +548,7 @@ static int __copy_super(struct bch_sb_handle *dst_handle, struct bch_sb *src)
 	dst->time_base_lo	= src->time_base_lo;
 	dst->time_base_hi	= src->time_base_hi;
 	dst->time_precision	= src->time_precision;
+	dst->write_time		= src->write_time;
 
 	memcpy(dst->flags,	src->flags,	sizeof(dst->flags));
 	memcpy(dst->features,	src->features,	sizeof(dst->features));
@@ -599,7 +612,6 @@ int bch2_sb_from_fs(struct bch_fs *c, struct bch_dev *ca)
 
 static int read_one_super(struct bch_sb_handle *sb, u64 offset, struct printbuf *err)
 {
-	struct bch_csum csum;
 	size_t bytes;
 	int ret;
 reread:
@@ -615,7 +627,9 @@ reread:
 
 	if (!uuid_equal(&sb->sb->magic, &BCACHE_MAGIC) &&
 	    !uuid_equal(&sb->sb->magic, &BCHFS_MAGIC)) {
-		prt_printf(err, "Not a bcachefs superblock");
+		prt_str(err, "Not a bcachefs superblock (got magic ");
+		pr_uuid(err, sb->sb->magic.b);
+		prt_str(err, ")");
 		return -BCH_ERR_invalid_sb_magic;
 	}
 
@@ -638,17 +652,16 @@ reread:
 		goto reread;
 	}
 
-	if (BCH_SB_CSUM_TYPE(sb->sb) >= BCH_CSUM_NR) {
+	enum bch_csum_type csum_type = BCH_SB_CSUM_TYPE(sb->sb);
+	if (csum_type >= BCH_CSUM_NR) {
 		prt_printf(err, "unknown checksum type %llu", BCH_SB_CSUM_TYPE(sb->sb));
 		return -BCH_ERR_invalid_sb_csum_type;
 	}
 
 	/* XXX: verify MACs */
-	csum = csum_vstruct(NULL, BCH_SB_CSUM_TYPE(sb->sb),
-			    null_nonce(), sb->sb);
-
+	struct bch_csum csum = csum_vstruct(NULL, csum_type, null_nonce(), sb->sb);
 	if (bch2_crc_cmp(csum, sb->sb->csum)) {
-		prt_printf(err, "bad checksum");
+		bch2_csum_err_msg(err, csum_type, sb->sb->csum, csum);
 		return -BCH_ERR_invalid_sb_csum;
 	}
 
@@ -657,12 +670,13 @@ reread:
 	return 0;
 }
 
-int bch2_read_super(const char *path, struct bch_opts *opts,
-		    struct bch_sb_handle *sb)
+static int __bch2_read_super(const char *path, struct bch_opts *opts,
+		    struct bch_sb_handle *sb, bool ignore_notbchfs_msg)
 {
 	u64 offset = opt_get(*opts, sb);
 	struct bch_sb_layout layout;
 	struct printbuf err = PRINTBUF;
+	struct printbuf err2 = PRINTBUF;
 	__le64 *i;
 	int ret;
 #ifndef __KERNEL__
@@ -675,6 +689,10 @@ retry:
 	if (!sb->holder)
 		return -ENOMEM;
 
+	sb->sb_name = kstrdup(path, GFP_KERNEL);
+	if (!sb->sb_name)
+		return -ENOMEM;
+
 #ifndef __KERNEL__
 	if (opt_get(*opts, direct_io) == false)
 		sb->mode |= BLK_OPEN_BUFFERED;
@@ -686,21 +704,22 @@ retry:
 	if (!opt_get(*opts, nochanges))
 		sb->mode |= BLK_OPEN_WRITE;
 
-	sb->bdev = blkdev_get_by_path(path, sb->mode, sb->holder, &bch2_sb_handle_bdev_ops);
-	if (IS_ERR(sb->bdev) &&
-	    PTR_ERR(sb->bdev) == -EACCES &&
+	sb->bdev_handle = bdev_open_by_path(path, sb->mode, sb->holder, &bch2_sb_handle_bdev_ops);
+	if (IS_ERR(sb->bdev_handle) &&
+	    PTR_ERR(sb->bdev_handle) == -EACCES &&
 	    opt_get(*opts, read_only)) {
 		sb->mode &= ~BLK_OPEN_WRITE;
 
-		sb->bdev = blkdev_get_by_path(path, sb->mode, sb->holder, &bch2_sb_handle_bdev_ops);
-		if (!IS_ERR(sb->bdev))
+		sb->bdev_handle = bdev_open_by_path(path, sb->mode, sb->holder, &bch2_sb_handle_bdev_ops);
+		if (!IS_ERR(sb->bdev_handle))
 			opt_set(*opts, nochanges, true);
 	}
 
-	if (IS_ERR(sb->bdev)) {
-		ret = PTR_ERR(sb->bdev);
+	if (IS_ERR(sb->bdev_handle)) {
+		ret = PTR_ERR(sb->bdev_handle);
 		goto out;
 	}
+	sb->bdev = sb->bdev_handle->bdev;
 
 	ret = bch2_sb_realloc(sb, 0);
 	if (ret) {
@@ -721,8 +740,14 @@ retry:
 	if (opt_defined(*opts, sb))
 		goto err;
 
-	printk(KERN_ERR "bcachefs (%s): error reading default superblock: %s\n",
+	prt_printf(&err2, "bcachefs (%s): error reading default superblock: %s\n",
 	       path, err.buf);
+	if (ret == -BCH_ERR_invalid_sb_magic && ignore_notbchfs_msg)
+		printk(KERN_INFO "%s", err2.buf);
+	else
+		printk(KERN_ERR "%s", err2.buf);
+
+	printbuf_exit(&err2);
 	printbuf_reset(&err);
 
 	/*
@@ -798,6 +823,20 @@ err_no_print:
 	goto out;
 }
 
+int bch2_read_super(const char *path, struct bch_opts *opts,
+		    struct bch_sb_handle *sb)
+{
+	return __bch2_read_super(path, opts, sb, false);
+}
+
+/* provide a silenced version for mount.bcachefs */
+
+int bch2_read_super_silent(const char *path, struct bch_opts *opts,
+		    struct bch_sb_handle *sb)
+{
+	return __bch2_read_super(path, opts, sb, true);
+}
+
 /* write superblock: */
 
 static void write_super_endio(struct bio *bio)
@@ -866,9 +905,8 @@ static void write_one_super(struct bch_fs *c, struct bch_dev *ca, unsigned idx)
 int bch2_write_super(struct bch_fs *c)
 {
 	struct closure *cl = &c->sb_write;
-	struct bch_dev *ca;
 	struct printbuf err = PRINTBUF;
-	unsigned i, sb = 0, nr_wrote;
+	unsigned sb = 0, nr_wrote;
 	struct bch_devs_mask sb_written;
 	bool wrote, can_mount_without_written, can_mount_with_written;
 	unsigned degraded_flags = BCH_FORCE_IF_DEGRADED;
@@ -890,9 +928,14 @@ int bch2_write_super(struct bch_fs *c)
 
 	le64_add_cpu(&c->disk_sb.sb->seq, 1);
 
-	if (test_bit(BCH_FS_ERROR, &c->flags))
+	struct bch_sb_field_members_v2 *mi = bch2_sb_field_get(c->disk_sb.sb, members_v2);
+	for_each_online_member(c, ca)
+		__bch2_members_v2_get_mut(mi, ca->dev_idx)->seq = c->disk_sb.sb->seq;
+	c->disk_sb.sb->write_time = cpu_to_le64(ktime_get_real_seconds());
+
+	if (test_bit(BCH_FS_error, &c->flags))
 		SET_BCH_SB_HAS_ERRORS(c->disk_sb.sb, 1);
-	if (test_bit(BCH_FS_TOPOLOGY_ERROR, &c->flags))
+	if (test_bit(BCH_FS_topology_error, &c->flags))
 		SET_BCH_SB_HAS_TOPOLOGY_ERRORS(c->disk_sb.sb, 1);
 
 	SET_BCH_SB_BIG_ENDIAN(c->disk_sb.sb, CPU_BIG_ENDIAN);
@@ -901,11 +944,12 @@ int bch2_write_super(struct bch_fs *c)
 	bch2_sb_members_from_cpu(c);
 	bch2_sb_members_cpy_v2_v1(&c->disk_sb);
 	bch2_sb_errors_from_cpu(c);
+	bch2_sb_downgrade_update(c);
 
-	for_each_online_member(ca, c, i)
+	for_each_online_member(c, ca)
 		bch2_sb_from_fs(c, ca);
 
-	for_each_online_member(ca, c, i) {
+	for_each_online_member(c, ca) {
 		printbuf_reset(&err);
 
 		ret = bch2_sb_validate(&ca->disk_sb, &err, WRITE);
@@ -926,16 +970,28 @@ int bch2_write_super(struct bch_fs *c)
 	if (!BCH_SB_INITIALIZED(c->disk_sb.sb))
 		goto out;
 
-	for_each_online_member(ca, c, i) {
+	if (le16_to_cpu(c->disk_sb.sb->version) > bcachefs_metadata_version_current) {
+		struct printbuf buf = PRINTBUF;
+		prt_printf(&buf, "attempting to write superblock that wasn't version downgraded (");
+		bch2_version_to_text(&buf, le16_to_cpu(c->disk_sb.sb->version));
+		prt_str(&buf, " > ");
+		bch2_version_to_text(&buf, bcachefs_metadata_version_current);
+		prt_str(&buf, ")");
+		bch2_fs_fatal_error(c, "%s", buf.buf);
+		printbuf_exit(&buf);
+		return -BCH_ERR_sb_not_downgraded;
+	}
+
+	for_each_online_member(c, ca) {
 		__set_bit(ca->dev_idx, sb_written.d);
 		ca->sb_write_error = 0;
 	}
 
-	for_each_online_member(ca, c, i)
+	for_each_online_member(c, ca)
 		read_back_super(c, ca);
 	closure_sync(cl);
 
-	for_each_online_member(ca, c, i) {
+	for_each_online_member(c, ca) {
 		if (ca->sb_write_error)
 			continue;
 
@@ -962,7 +1018,7 @@ int bch2_write_super(struct bch_fs *c)
 
 	do {
 		wrote = false;
-		for_each_online_member(ca, c, i)
+		for_each_online_member(c, ca)
 			if (!ca->sb_write_error &&
 			    sb < ca->disk_sb.sb->layout.nr_superblocks) {
 				write_one_super(c, ca, sb);
@@ -972,7 +1028,7 @@ int bch2_write_super(struct bch_fs *c)
 		sb++;
 	} while (wrote);
 
-	for_each_online_member(ca, c, i) {
+	for_each_online_member(c, ca) {
 		if (ca->sb_write_error)
 			__clear_bit(ca->dev_idx, sb_written.d);
 		else
@@ -984,7 +1040,7 @@ int bch2_write_super(struct bch_fs *c)
 	can_mount_with_written =
 		bch2_have_enough_devs(c, sb_written, degraded_flags, false);
 
-	for (i = 0; i < ARRAY_SIZE(sb_written.d); i++)
+	for (unsigned i = 0; i < ARRAY_SIZE(sb_written.d); i++)
 		sb_written.d[i] = ~sb_written.d[i];
 
 	can_mount_without_written =
@@ -1024,31 +1080,87 @@ void __bch2_check_set_feature(struct bch_fs *c, unsigned feat)
 }
 
 /* Downgrade if superblock is at a higher version than currently supported: */
-void bch2_sb_maybe_downgrade(struct bch_fs *c)
+bool bch2_check_version_downgrade(struct bch_fs *c)
 {
+	bool ret = bcachefs_metadata_version_current < c->sb.version;
+
 	lockdep_assert_held(&c->sb_lock);
 
 	/*
 	 * Downgrade, if superblock is at a higher version than currently
 	 * supported:
+	 *
+	 * c->sb will be checked before we write the superblock, so update it as
+	 * well:
 	 */
-	if (BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb) > bcachefs_metadata_version_current)
+	if (BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb) > bcachefs_metadata_version_current) {
 		SET_BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb, bcachefs_metadata_version_current);
-	if (c->sb.version > bcachefs_metadata_version_current)
+		c->sb.version_upgrade_complete = bcachefs_metadata_version_current;
+	}
+	if (c->sb.version > bcachefs_metadata_version_current) {
 		c->disk_sb.sb->version = cpu_to_le16(bcachefs_metadata_version_current);
-	if (c->sb.version_min > bcachefs_metadata_version_current)
+		c->sb.version = bcachefs_metadata_version_current;
+	}
+	if (c->sb.version_min > bcachefs_metadata_version_current) {
 		c->disk_sb.sb->version_min = cpu_to_le16(bcachefs_metadata_version_current);
+		c->sb.version_min = bcachefs_metadata_version_current;
+	}
 	c->disk_sb.sb->compat[0] &= cpu_to_le64((1ULL << BCH_COMPAT_NR) - 1);
+	return ret;
 }
 
 void bch2_sb_upgrade(struct bch_fs *c, unsigned new_version)
 {
 	lockdep_assert_held(&c->sb_lock);
 
+	if (BCH_VERSION_MAJOR(new_version) >
+	    BCH_VERSION_MAJOR(le16_to_cpu(c->disk_sb.sb->version)))
+		bch2_sb_field_resize(&c->disk_sb, downgrade, 0);
+
 	c->disk_sb.sb->version = cpu_to_le16(new_version);
 	c->disk_sb.sb->features[0] |= cpu_to_le64(BCH_SB_FEATURES_ALL);
 }
 
+static int bch2_sb_ext_validate(struct bch_sb *sb, struct bch_sb_field *f,
+				struct printbuf *err)
+{
+	if (vstruct_bytes(f) < 88) {
+		prt_printf(err, "field too small (%zu < %u)", vstruct_bytes(f), 88);
+		return -BCH_ERR_invalid_sb_ext;
+	}
+
+	return 0;
+}
+
+static void bch2_sb_ext_to_text(struct printbuf *out, struct bch_sb *sb,
+				struct bch_sb_field *f)
+{
+	struct bch_sb_field_ext *e = field_to_type(f, ext);
+
+	prt_printf(out, "Recovery passes required:");
+	prt_tab(out);
+	prt_bitflags(out, bch2_recovery_passes,
+		     bch2_recovery_passes_from_stable(le64_to_cpu(e->recovery_passes_required[0])));
+	prt_newline(out);
+
+	unsigned long *errors_silent = kmalloc(sizeof(e->errors_silent), GFP_KERNEL);
+	if (errors_silent) {
+		le_bitvector_to_cpu(errors_silent, (void *) e->errors_silent, sizeof(e->errors_silent) * 8);
+
+		prt_printf(out, "Errors to silently fix:");
+		prt_tab(out);
+		prt_bitflags_vector(out, bch2_sb_error_strs, errors_silent, sizeof(e->errors_silent) * 8);
+		prt_newline(out);
+
+		kfree(errors_silent);
+	}
+}
+
+static const struct bch_sb_field_ops bch_sb_field_ops_ext = {
+	.validate	= bch2_sb_ext_validate,
+	.to_text	= bch2_sb_ext_to_text,
+};
+
 static const struct bch_sb_field_ops *bch2_sb_field_ops[] = {
 #define x(f, nr)					\
 	[BCH_SB_FIELD_##f] = &bch_sb_field_ops_##f,
@@ -1085,8 +1197,8 @@ static int bch2_sb_field_validate(struct bch_sb *sb, struct bch_sb_field *f,
 	return ret;
 }
 
-void bch2_sb_field_to_text(struct printbuf *out, struct bch_sb *sb,
-			   struct bch_sb_field *f)
+void __bch2_sb_field_to_text(struct printbuf *out, struct bch_sb *sb,
+			     struct bch_sb_field *f)
 {
 	unsigned type = le32_to_cpu(f->type);
 	const struct bch_sb_field_ops *ops = bch2_sb_field_type_ops(type);
@@ -1094,6 +1206,15 @@ void bch2_sb_field_to_text(struct printbuf *out, struct bch_sb *sb,
 	if (!out->nr_tabstops)
 		printbuf_tabstop_push(out, 32);
 
+	if (ops->to_text)
+		ops->to_text(out, sb, f);
+}
+
+void bch2_sb_field_to_text(struct printbuf *out, struct bch_sb *sb,
+			   struct bch_sb_field *f)
+{
+	unsigned type = le32_to_cpu(f->type);
+
 	if (type < BCH_SB_FIELD_NR)
 		prt_printf(out, "%s", bch2_sb_fields[type]);
 	else
@@ -1102,11 +1223,7 @@ void bch2_sb_field_to_text(struct printbuf *out, struct bch_sb *sb,
 	prt_printf(out, " (size %zu):", vstruct_bytes(f));
 	prt_newline(out);
 
-	if (ops->to_text) {
-		printbuf_indent_add(out, 2);
-		ops->to_text(out, sb, f);
-		printbuf_indent_sub(out, 2);
-	}
+	__bch2_sb_field_to_text(out, sb, f);
 }
 
 void bch2_sb_layout_to_text(struct printbuf *out, struct bch_sb_layout *l)
@@ -1135,7 +1252,6 @@ void bch2_sb_layout_to_text(struct printbuf *out, struct bch_sb_layout *l)
 void bch2_sb_to_text(struct printbuf *out, struct bch_sb *sb,
 		     bool print_layout, unsigned fields)
 {
-	struct bch_sb_field *f;
 	u64 fields_have = 0;
 	unsigned nr_devices = 0;
 
@@ -1155,6 +1271,11 @@ void bch2_sb_to_text(struct printbuf *out, struct bch_sb *sb,
 	pr_uuid(out, sb->uuid.b);
 	prt_newline(out);
 
+	prt_printf(out, "Magic number:");
+	prt_tab(out);
+	pr_uuid(out, sb->magic.b);
+	prt_newline(out);
+
 	prt_str(out, "Device index:");
 	prt_tab(out);
 	prt_printf(out, "%u", sb->dev_idx);
@@ -1193,6 +1314,11 @@ void bch2_sb_to_text(struct printbuf *out, struct bch_sb *sb,
 	prt_printf(out, "%llu", le64_to_cpu(sb->seq));
 	prt_newline(out);
 
+	prt_printf(out, "Time of last write:");
+	prt_tab(out);
+	bch2_prt_datetime(out, le64_to_cpu(sb->write_time));
+	prt_newline(out);
+
 	prt_printf(out, "Superblock size:");
 	prt_tab(out);
 	prt_printf(out, "%zu", vstruct_bytes(sb));
diff --git a/fs/bcachefs/super-io.h b/fs/bcachefs/super-io.h
index f5abd102bff7..95e80e06316b 100644
--- a/fs/bcachefs/super-io.h
+++ b/fs/bcachefs/super-io.h
@@ -19,10 +19,6 @@ static inline bool bch2_version_compatible(u16 version)
 void bch2_version_to_text(struct printbuf *, unsigned);
 unsigned bch2_latest_compatible_version(unsigned);
 
-u64 bch2_upgrade_recovery_passes(struct bch_fs *c,
-				 unsigned,
-				 unsigned);
-
 static inline size_t bch2_sb_field_bytes(struct bch_sb_field *f)
 {
 	return le32_to_cpu(f->u64s) * sizeof(u64);
@@ -40,6 +36,16 @@ struct bch_sb_field *bch2_sb_field_resize_id(struct bch_sb_handle *,
 #define bch2_sb_field_resize(_sb, _name, _u64s)				\
 	field_to_type(bch2_sb_field_resize_id(_sb, BCH_SB_FIELD_##_name, _u64s), _name)
 
+struct bch_sb_field *bch2_sb_field_get_minsize_id(struct bch_sb_handle *,
+					enum bch_sb_field_type, unsigned);
+#define bch2_sb_field_get_minsize(_sb, _name, _u64s)				\
+	field_to_type(bch2_sb_field_get_minsize_id(_sb, BCH_SB_FIELD_##_name, _u64s), _name)
+
+#define bch2_sb_field_nr_entries(_f)					\
+	(_f ? ((bch2_sb_field_bytes(&_f->field) - sizeof(*_f)) /	\
+	       sizeof(_f->entries[0]))					\
+	    : 0)
+
 void bch2_sb_field_delete(struct bch_sb_handle *, enum bch_sb_field_type);
 
 extern const char * const bch2_sb_fields[];
@@ -74,6 +80,7 @@ void bch2_free_super(struct bch_sb_handle *);
 int bch2_sb_realloc(struct bch_sb_handle *, unsigned);
 
 int bch2_read_super(const char *, struct bch_opts *, struct bch_sb_handle *);
+int bch2_read_super_silent(const char *, struct bch_opts *, struct bch_sb_handle *);
 int bch2_write_super(struct bch_fs *);
 void __bch2_check_set_feature(struct bch_fs *, unsigned);
 
@@ -83,9 +90,11 @@ static inline void bch2_check_set_feature(struct bch_fs *c, unsigned feat)
 		__bch2_check_set_feature(c, feat);
 }
 
-void bch2_sb_maybe_downgrade(struct bch_fs *);
+bool bch2_check_version_downgrade(struct bch_fs *);
 void bch2_sb_upgrade(struct bch_fs *, unsigned);
 
+void __bch2_sb_field_to_text(struct printbuf *, struct bch_sb *,
+			     struct bch_sb_field *);
 void bch2_sb_field_to_text(struct printbuf *, struct bch_sb *,
 			   struct bch_sb_field *);
 void bch2_sb_layout_to_text(struct printbuf *, struct bch_sb_layout *);
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index 24672bb31cbe..9dbc35940197 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -72,6 +72,42 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Kent Overstreet <kent.overstreet@gmail.com>");
 MODULE_DESCRIPTION("bcachefs filesystem");
+MODULE_SOFTDEP("pre: crc32c");
+MODULE_SOFTDEP("pre: crc64");
+MODULE_SOFTDEP("pre: sha256");
+MODULE_SOFTDEP("pre: chacha20");
+MODULE_SOFTDEP("pre: poly1305");
+MODULE_SOFTDEP("pre: xxhash");
+
+const char * const bch2_fs_flag_strs[] = {
+#define x(n)		#n,
+	BCH_FS_FLAGS()
+#undef x
+	NULL
+};
+
+void __bch2_print(struct bch_fs *c, const char *fmt, ...)
+{
+	struct stdio_redirect *stdio = bch2_fs_stdio_redirect(c);
+
+	va_list args;
+	va_start(args, fmt);
+	if (likely(!stdio)) {
+		vprintk(fmt, args);
+	} else {
+		unsigned long flags;
+
+		if (fmt[0] == KERN_SOH[0])
+			fmt += 2;
+
+		spin_lock_irqsave(&stdio->output_lock, flags);
+		prt_vprintf(&stdio->output_buf, fmt, args);
+		spin_unlock_irqrestore(&stdio->output_lock, flags);
+
+		wake_up(&stdio->output_wait);
+	}
+	va_end(args);
+}
 
 #define KTYPE(type)							\
 static const struct attribute_group type ## _group = {			\
@@ -128,14 +164,12 @@ static void __bch2_dev_read_only(struct bch_fs *, struct bch_dev *);
 struct bch_fs *bch2_dev_to_fs(dev_t dev)
 {
 	struct bch_fs *c;
-	struct bch_dev *ca;
-	unsigned i;
 
 	mutex_lock(&bch_fs_list_lock);
 	rcu_read_lock();
 
 	list_for_each_entry(c, &bch_fs_list, list)
-		for_each_member_device_rcu(ca, c, i, NULL)
+		for_each_member_device_rcu(c, ca, NULL)
 			if (ca->disk_sb.bdev && ca->disk_sb.bdev->bd_dev == dev) {
 				closure_get(&c->cl);
 				goto found;
@@ -176,14 +210,13 @@ struct bch_fs *bch2_uuid_to_fs(__uuid_t uuid)
 
 static void bch2_dev_usage_journal_reserve(struct bch_fs *c)
 {
-	struct bch_dev *ca;
-	unsigned i, nr = 0, u64s =
+	unsigned nr = 0, u64s =
 		((sizeof(struct jset_entry_dev_usage) +
 		  sizeof(struct jset_entry_dev_usage_type) * BCH_DATA_NR)) /
 		sizeof(u64);
 
 	rcu_read_lock();
-	for_each_member_device_rcu(ca, c, i, NULL)
+	for_each_member_device_rcu(c, ca, NULL)
 		nr++;
 	rcu_read_unlock();
 
@@ -210,8 +243,7 @@ static void bch2_dev_usage_journal_reserve(struct bch_fs *c)
 
 static void __bch2_fs_read_only(struct bch_fs *c)
 {
-	struct bch_dev *ca;
-	unsigned i, clean_passes = 0;
+	unsigned clean_passes = 0;
 	u64 seq = 0;
 
 	bch2_fs_ec_stop(c);
@@ -240,14 +272,14 @@ static void __bch2_fs_read_only(struct bch_fs *c)
 		    journal_cur_seq(&c->journal));
 
 	if (test_bit(JOURNAL_REPLAY_DONE, &c->journal.flags) &&
-	    !test_bit(BCH_FS_EMERGENCY_RO, &c->flags))
-		set_bit(BCH_FS_CLEAN_SHUTDOWN, &c->flags);
+	    !test_bit(BCH_FS_emergency_ro, &c->flags))
+		set_bit(BCH_FS_clean_shutdown, &c->flags);
 	bch2_fs_journal_stop(&c->journal);
 
 	/*
 	 * After stopping journal:
 	 */
-	for_each_member_device(ca, c, i)
+	for_each_member_device(c, ca)
 		bch2_dev_allocator_remove(c, ca);
 }
 
@@ -256,25 +288,27 @@ static void bch2_writes_disabled(struct percpu_ref *writes)
 {
 	struct bch_fs *c = container_of(writes, struct bch_fs, writes);
 
-	set_bit(BCH_FS_WRITE_DISABLE_COMPLETE, &c->flags);
+	set_bit(BCH_FS_write_disable_complete, &c->flags);
 	wake_up(&bch2_read_only_wait);
 }
 #endif
 
 void bch2_fs_read_only(struct bch_fs *c)
 {
-	if (!test_bit(BCH_FS_RW, &c->flags)) {
+	if (!test_bit(BCH_FS_rw, &c->flags)) {
 		bch2_journal_reclaim_stop(&c->journal);
 		return;
 	}
 
-	BUG_ON(test_bit(BCH_FS_WRITE_DISABLE_COMPLETE, &c->flags));
+	BUG_ON(test_bit(BCH_FS_write_disable_complete, &c->flags));
+
+	bch_verbose(c, "going read-only");
 
 	/*
 	 * Block new foreground-end write operations from starting - any new
 	 * writes will return -EROFS:
 	 */
-	set_bit(BCH_FS_GOING_RO, &c->flags);
+	set_bit(BCH_FS_going_ro, &c->flags);
 #ifndef BCH_WRITE_REF_DEBUG
 	percpu_ref_kill(&c->writes);
 #else
@@ -294,33 +328,42 @@ void bch2_fs_read_only(struct bch_fs *c)
 	 * that going RO is complete:
 	 */
 	wait_event(bch2_read_only_wait,
-		   test_bit(BCH_FS_WRITE_DISABLE_COMPLETE, &c->flags) ||
-		   test_bit(BCH_FS_EMERGENCY_RO, &c->flags));
+		   test_bit(BCH_FS_write_disable_complete, &c->flags) ||
+		   test_bit(BCH_FS_emergency_ro, &c->flags));
+
+	bool writes_disabled = test_bit(BCH_FS_write_disable_complete, &c->flags);
+	if (writes_disabled)
+		bch_verbose(c, "finished waiting for writes to stop");
 
 	__bch2_fs_read_only(c);
 
 	wait_event(bch2_read_only_wait,
-		   test_bit(BCH_FS_WRITE_DISABLE_COMPLETE, &c->flags));
+		   test_bit(BCH_FS_write_disable_complete, &c->flags));
 
-	clear_bit(BCH_FS_WRITE_DISABLE_COMPLETE, &c->flags);
-	clear_bit(BCH_FS_GOING_RO, &c->flags);
+	if (!writes_disabled)
+		bch_verbose(c, "finished waiting for writes to stop");
+
+	clear_bit(BCH_FS_write_disable_complete, &c->flags);
+	clear_bit(BCH_FS_going_ro, &c->flags);
+	clear_bit(BCH_FS_rw, &c->flags);
 
 	if (!bch2_journal_error(&c->journal) &&
-	    !test_bit(BCH_FS_ERROR, &c->flags) &&
-	    !test_bit(BCH_FS_EMERGENCY_RO, &c->flags) &&
-	    test_bit(BCH_FS_STARTED, &c->flags) &&
-	    test_bit(BCH_FS_CLEAN_SHUTDOWN, &c->flags) &&
+	    !test_bit(BCH_FS_error, &c->flags) &&
+	    !test_bit(BCH_FS_emergency_ro, &c->flags) &&
+	    test_bit(BCH_FS_started, &c->flags) &&
+	    test_bit(BCH_FS_clean_shutdown, &c->flags) &&
 	    !c->opts.norecovery) {
 		BUG_ON(c->journal.last_empty_seq != journal_cur_seq(&c->journal));
 		BUG_ON(atomic_read(&c->btree_cache.dirty));
 		BUG_ON(atomic_long_read(&c->btree_key_cache.nr_dirty));
-		BUG_ON(c->btree_write_buffer.state.nr);
+		BUG_ON(c->btree_write_buffer.inc.keys.nr);
+		BUG_ON(c->btree_write_buffer.flushing.keys.nr);
 
 		bch_verbose(c, "marking filesystem clean");
 		bch2_fs_mark_clean(c);
+	} else {
+		bch_verbose(c, "done going read-only, filesystem not clean");
 	}
-
-	clear_bit(BCH_FS_RW, &c->flags);
 }
 
 static void bch2_fs_read_only_work(struct work_struct *work)
@@ -340,7 +383,7 @@ static void bch2_fs_read_only_async(struct bch_fs *c)
 
 bool bch2_fs_emergency_read_only(struct bch_fs *c)
 {
-	bool ret = !test_and_set_bit(BCH_FS_EMERGENCY_RO, &c->flags);
+	bool ret = !test_and_set_bit(BCH_FS_emergency_ro, &c->flags);
 
 	bch2_journal_halt(&c->journal);
 	bch2_fs_read_only_async(c);
@@ -377,28 +420,16 @@ static int bch2_fs_read_write_late(struct bch_fs *c)
 
 static int __bch2_fs_read_write(struct bch_fs *c, bool early)
 {
-	struct bch_dev *ca;
-	unsigned i;
 	int ret;
 
-	if (test_bit(BCH_FS_INITIAL_GC_UNFIXED, &c->flags)) {
+	if (test_bit(BCH_FS_initial_gc_unfixed, &c->flags)) {
 		bch_err(c, "cannot go rw, unfixed btree errors");
 		return -BCH_ERR_erofs_unfixed_errors;
 	}
 
-	if (test_bit(BCH_FS_RW, &c->flags))
+	if (test_bit(BCH_FS_rw, &c->flags))
 		return 0;
 
-	if (c->opts.norecovery)
-		return -BCH_ERR_erofs_norecovery;
-
-	/*
-	 * nochanges is used for fsck -n mode - we have to allow going rw
-	 * during recovery for that to work:
-	 */
-	if (c->opts.nochanges && (!early || c->opts.read_only))
-		return -BCH_ERR_erofs_nochanges;
-
 	bch_info(c, "going read-write");
 
 	ret = bch2_sb_members_v2_init(c);
@@ -409,7 +440,7 @@ static int __bch2_fs_read_write(struct bch_fs *c, bool early)
 	if (ret)
 		goto err;
 
-	clear_bit(BCH_FS_CLEAN_SHUTDOWN, &c->flags);
+	clear_bit(BCH_FS_clean_shutdown, &c->flags);
 
 	/*
 	 * First journal write must be a flush write: after a clean shutdown we
@@ -419,10 +450,22 @@ static int __bch2_fs_read_write(struct bch_fs *c, bool early)
 	 */
 	set_bit(JOURNAL_NEED_FLUSH_WRITE, &c->journal.flags);
 
-	for_each_rw_member(ca, c, i)
+	for_each_rw_member(c, ca)
 		bch2_dev_allocator_add(c, ca);
 	bch2_recalc_capacity(c);
 
+	set_bit(BCH_FS_rw, &c->flags);
+	set_bit(BCH_FS_was_rw, &c->flags);
+
+#ifndef BCH_WRITE_REF_DEBUG
+	percpu_ref_reinit(&c->writes);
+#else
+	for (unsigned i = 0; i < BCH_WRITE_REF_NR; i++) {
+		BUG_ON(atomic_long_read(&c->writes[i]));
+		atomic_long_inc(&c->writes[i]);
+	}
+#endif
+
 	ret = bch2_gc_thread_start(c);
 	if (ret) {
 		bch_err(c, "error starting gc thread");
@@ -439,29 +482,27 @@ static int __bch2_fs_read_write(struct bch_fs *c, bool early)
 			goto err;
 	}
 
-#ifndef BCH_WRITE_REF_DEBUG
-	percpu_ref_reinit(&c->writes);
-#else
-	for (i = 0; i < BCH_WRITE_REF_NR; i++) {
-		BUG_ON(atomic_long_read(&c->writes[i]));
-		atomic_long_inc(&c->writes[i]);
-	}
-#endif
-	set_bit(BCH_FS_RW, &c->flags);
-	set_bit(BCH_FS_WAS_RW, &c->flags);
-
 	bch2_do_discards(c);
 	bch2_do_invalidates(c);
 	bch2_do_stripe_deletes(c);
 	bch2_do_pending_node_rewrites(c);
 	return 0;
 err:
-	__bch2_fs_read_only(c);
+	if (test_bit(BCH_FS_rw, &c->flags))
+		bch2_fs_read_only(c);
+	else
+		__bch2_fs_read_only(c);
 	return ret;
 }
 
 int bch2_fs_read_write(struct bch_fs *c)
 {
+	if (c->opts.norecovery)
+		return -BCH_ERR_erofs_norecovery;
+
+	if (c->opts.nochanges)
+		return -BCH_ERR_erofs_nochanges;
+
 	return __bch2_fs_read_write(c, false);
 }
 
@@ -504,8 +545,8 @@ static void __bch2_fs_free(struct bch_fs *c)
 	bch2_io_clock_exit(&c->io_clock[WRITE]);
 	bch2_io_clock_exit(&c->io_clock[READ]);
 	bch2_fs_compress_exit(c);
-	bch2_journal_keys_free(&c->journal_keys);
-	bch2_journal_entries_free(c);
+	bch2_journal_keys_put_initial(c);
+	BUG_ON(atomic_read(&c->journal_keys.ref));
 	bch2_fs_btree_write_buffer_exit(c);
 	percpu_free_rwsem(&c->mark_lock);
 	free_percpu(c->online_reserved);
@@ -548,12 +589,9 @@ static void bch2_fs_release(struct kobject *kobj)
 
 void __bch2_fs_stop(struct bch_fs *c)
 {
-	struct bch_dev *ca;
-	unsigned i;
-
 	bch_verbose(c, "shutting down");
 
-	set_bit(BCH_FS_STOPPING, &c->flags);
+	set_bit(BCH_FS_stopping, &c->flags);
 
 	cancel_work_sync(&c->journal_seq_blacklist_gc_work);
 
@@ -561,7 +599,7 @@ void __bch2_fs_stop(struct bch_fs *c)
 	bch2_fs_read_only(c);
 	up_write(&c->state_lock);
 
-	for_each_member_device(ca, c, i)
+	for_each_member_device(c, ca)
 		if (ca->kobj.state_in_sysfs &&
 		    ca->disk_sb.bdev)
 			sysfs_remove_link(bdev_kobj(ca->disk_sb.bdev), "bcachefs");
@@ -572,6 +610,9 @@ void __bch2_fs_stop(struct bch_fs *c)
 	bch2_fs_debug_exit(c);
 	bch2_fs_chardev_exit(c);
 
+	bch2_ro_ref_put(c);
+	wait_event(c->ro_ref_wait, !refcount_read(&c->ro_ref));
+
 	kobject_put(&c->counters_kobj);
 	kobject_put(&c->time_stats);
 	kobject_put(&c->opts_dir);
@@ -580,7 +621,7 @@ void __bch2_fs_stop(struct bch_fs *c)
 	/* btree prefetch might have kicked off reads in the background: */
 	bch2_btree_flush_all_reads(c);
 
-	for_each_member_device(ca, c, i)
+	for_each_member_device(c, ca)
 		cancel_work_sync(&ca->io_error_work);
 
 	cancel_work_sync(&c->read_only_work);
@@ -619,8 +660,6 @@ void bch2_fs_stop(struct bch_fs *c)
 
 static int bch2_fs_online(struct bch_fs *c)
 {
-	struct bch_dev *ca;
-	unsigned i;
 	int ret = 0;
 
 	lockdep_assert_held(&bch_fs_list_lock);
@@ -641,7 +680,9 @@ static int bch2_fs_online(struct bch_fs *c)
 	ret = kobject_add(&c->kobj, NULL, "%pU", c->sb.user_uuid.b) ?:
 	    kobject_add(&c->internal, &c->kobj, "internal") ?:
 	    kobject_add(&c->opts_dir, &c->kobj, "options") ?:
+#ifndef CONFIG_BCACHEFS_NO_LATENCY_ACCT
 	    kobject_add(&c->time_stats, &c->kobj, "time_stats") ?:
+#endif
 	    kobject_add(&c->counters_kobj, &c->kobj, "counters") ?:
 	    bch2_opts_create_sysfs_files(&c->opts_dir);
 	if (ret) {
@@ -651,7 +692,7 @@ static int bch2_fs_online(struct bch_fs *c)
 
 	down_write(&c->state_lock);
 
-	for_each_member_device(ca, c, i) {
+	for_each_member_device(c, ca) {
 		ret = bch2_dev_sysfs_online(c, ca);
 		if (ret) {
 			bch_err(c, "error creating sysfs objects");
@@ -680,6 +721,8 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts)
 		goto out;
 	}
 
+	c->stdio = (void *)(unsigned long) opts.stdio;
+
 	__module_get(THIS_MODULE);
 
 	closure_init(&c->cl, NULL);
@@ -700,14 +743,21 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts)
 	mutex_init(&c->btree_root_lock);
 	INIT_WORK(&c->read_only_work, bch2_fs_read_only_work);
 
+	refcount_set(&c->ro_ref, 1);
+	init_waitqueue_head(&c->ro_ref_wait);
+	sema_init(&c->online_fsck_mutex, 1);
+
 	init_rwsem(&c->gc_lock);
 	mutex_init(&c->gc_gens_lock);
+	atomic_set(&c->journal_keys.ref, 1);
+	c->journal_keys.initial_ref_held = true;
 
 	for (i = 0; i < BCH_TIME_STAT_NR; i++)
 		bch2_time_stats_init(&c->times[i]);
 
 	bch2_fs_copygc_init(c);
 	bch2_fs_btree_key_cache_init_early(&c->btree_key_cache);
+	bch2_fs_btree_iter_init_early(c);
 	bch2_fs_btree_interior_update_init_early(c);
 	bch2_fs_allocator_background_init(c);
 	bch2_fs_allocator_foreground_init(c);
@@ -750,7 +800,6 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts)
 
 	c->journal.flush_write_time	= &c->times[BCH_TIME_journal_flush_write];
 	c->journal.noflush_write_time	= &c->times[BCH_TIME_journal_noflush_write];
-	c->journal.blocked_time		= &c->times[BCH_TIME_blocked_journal];
 	c->journal.flush_seq_time	= &c->times[BCH_TIME_journal_flush_seq];
 
 	bch2_fs_btree_cache_init_early(&c->btree_cache);
@@ -819,7 +868,7 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts)
 	    !(c->copygc_wq = alloc_workqueue("bcachefs_copygc",
 				WQ_FREEZABLE|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 1)) ||
 	    !(c->io_complete_wq = alloc_workqueue("bcachefs_io",
-				WQ_FREEZABLE|WQ_HIGHPRI|WQ_MEM_RECLAIM, 1)) ||
+				WQ_FREEZABLE|WQ_HIGHPRI|WQ_MEM_RECLAIM, 512)) ||
 	    !(c->write_ref_wq = alloc_workqueue("bcachefs_write_ref",
 				WQ_FREEZABLE, 0)) ||
 #ifndef BCH_WRITE_REF_DEBUG
@@ -933,16 +982,14 @@ static void print_mount_opts(struct bch_fs *c)
 
 int bch2_fs_start(struct bch_fs *c)
 {
-	struct bch_dev *ca;
 	time64_t now = ktime_get_real_seconds();
-	unsigned i;
 	int ret;
 
 	print_mount_opts(c);
 
 	down_write(&c->state_lock);
 
-	BUG_ON(test_bit(BCH_FS_STARTED, &c->flags));
+	BUG_ON(test_bit(BCH_FS_started, &c->flags));
 
 	mutex_lock(&c->sb_lock);
 
@@ -952,12 +999,12 @@ int bch2_fs_start(struct bch_fs *c)
 		goto err;
 	}
 
-	for_each_online_member(ca, c, i)
-		bch2_members_v2_get_mut(c->disk_sb.sb, i)->last_mount = cpu_to_le64(now);
+	for_each_online_member(c, ca)
+		bch2_members_v2_get_mut(c->disk_sb.sb, ca->dev_idx)->last_mount = cpu_to_le64(now);
 
 	mutex_unlock(&c->sb_lock);
 
-	for_each_rw_member(ca, c, i)
+	for_each_rw_member(c, ca)
 		bch2_dev_allocator_add(c, ca);
 	bch2_recalc_capacity(c);
 
@@ -977,12 +1024,12 @@ int bch2_fs_start(struct bch_fs *c)
 		goto err;
 	}
 
-	set_bit(BCH_FS_STARTED, &c->flags);
+	set_bit(BCH_FS_started, &c->flags);
 
-	if (c->opts.read_only || c->opts.nochanges) {
+	if (c->opts.read_only) {
 		bch2_fs_read_only(c);
 	} else {
-		ret = !test_bit(BCH_FS_RW, &c->flags)
+		ret = !test_bit(BCH_FS_rw, &c->flags)
 			? bch2_fs_read_write(c)
 			: bch2_fs_read_write_late(c);
 		if (ret)
@@ -990,12 +1037,13 @@ int bch2_fs_start(struct bch_fs *c)
 	}
 
 	ret = 0;
-out:
+err:
+	if (ret)
+		bch_err_msg(c, ret, "starting filesystem");
+	else
+		bch_verbose(c, "done starting filesystem");
 	up_write(&c->state_lock);
 	return ret;
-err:
-	bch_err_msg(c, ret, "starting filesystem");
-	goto out;
 }
 
 static int bch2_dev_may_add(struct bch_sb *sb, struct bch_fs *c)
@@ -1012,20 +1060,83 @@ static int bch2_dev_may_add(struct bch_sb *sb, struct bch_fs *c)
 	return 0;
 }
 
-static int bch2_dev_in_fs(struct bch_sb *fs, struct bch_sb *sb)
+static int bch2_dev_in_fs(struct bch_sb_handle *fs,
+			  struct bch_sb_handle *sb)
 {
-	struct bch_sb *newest =
-		le64_to_cpu(fs->seq) > le64_to_cpu(sb->seq) ? fs : sb;
+	if (fs == sb)
+		return 0;
 
-	if (!uuid_equal(&fs->uuid, &sb->uuid))
+	if (!uuid_equal(&fs->sb->uuid, &sb->sb->uuid))
 		return -BCH_ERR_device_not_a_member_of_filesystem;
 
-	if (!bch2_dev_exists(newest, sb->dev_idx))
+	if (!bch2_dev_exists(fs->sb, sb->sb->dev_idx))
 		return -BCH_ERR_device_has_been_removed;
 
-	if (fs->block_size != sb->block_size)
+	if (fs->sb->block_size != sb->sb->block_size)
 		return -BCH_ERR_mismatched_block_size;
 
+	if (le16_to_cpu(fs->sb->version) < bcachefs_metadata_version_member_seq ||
+	    le16_to_cpu(sb->sb->version) < bcachefs_metadata_version_member_seq)
+		return 0;
+
+	if (fs->sb->seq == sb->sb->seq &&
+	    fs->sb->write_time != sb->sb->write_time) {
+		struct printbuf buf = PRINTBUF;
+
+		prt_str(&buf, "Split brain detected between ");
+		prt_bdevname(&buf, sb->bdev);
+		prt_str(&buf, " and ");
+		prt_bdevname(&buf, fs->bdev);
+		prt_char(&buf, ':');
+		prt_newline(&buf);
+		prt_printf(&buf, "seq=%llu but write_time different, got", le64_to_cpu(sb->sb->seq));
+		prt_newline(&buf);
+
+		prt_bdevname(&buf, fs->bdev);
+		prt_char(&buf, ' ');
+		bch2_prt_datetime(&buf, le64_to_cpu(fs->sb->write_time));;
+		prt_newline(&buf);
+
+		prt_bdevname(&buf, sb->bdev);
+		prt_char(&buf, ' ');
+		bch2_prt_datetime(&buf, le64_to_cpu(sb->sb->write_time));;
+		prt_newline(&buf);
+
+		prt_printf(&buf, "Not using older sb");
+
+		pr_err("%s", buf.buf);
+		printbuf_exit(&buf);
+		return -BCH_ERR_device_splitbrain;
+	}
+
+	struct bch_member m = bch2_sb_member_get(fs->sb, sb->sb->dev_idx);
+	u64 seq_from_fs		= le64_to_cpu(m.seq);
+	u64 seq_from_member	= le64_to_cpu(sb->sb->seq);
+
+	if (seq_from_fs && seq_from_fs < seq_from_member) {
+		struct printbuf buf = PRINTBUF;
+
+		prt_str(&buf, "Split brain detected between ");
+		prt_bdevname(&buf, sb->bdev);
+		prt_str(&buf, " and ");
+		prt_bdevname(&buf, fs->bdev);
+		prt_char(&buf, ':');
+		prt_newline(&buf);
+
+		prt_bdevname(&buf, fs->bdev);
+		prt_str(&buf, "believes seq of ");
+		prt_bdevname(&buf, sb->bdev);
+		prt_printf(&buf, " to be %llu, but ", seq_from_fs);
+		prt_bdevname(&buf, sb->bdev);
+		prt_printf(&buf, " has %llu\n", seq_from_member);
+		prt_str(&buf, "Not using ");
+		prt_bdevname(&buf, sb->bdev);
+
+		pr_err("%s", buf.buf);
+		printbuf_exit(&buf);
+		return -BCH_ERR_device_splitbrain;
+	}
+
 	return 0;
 }
 
@@ -1271,9 +1382,14 @@ static int bch2_dev_attach_bdev(struct bch_fs *c, struct bch_sb_handle *sb)
 
 	bch2_dev_sysfs_online(c, ca);
 
+	struct printbuf name = PRINTBUF;
+	prt_bdevname(&name, ca->disk_sb.bdev);
+
 	if (c->sb.nr_devices == 1)
-		snprintf(c->name, sizeof(c->name), "%pg", ca->disk_sb.bdev);
-	snprintf(ca->name, sizeof(ca->name), "%pg", ca->disk_sb.bdev);
+		strlcpy(c->name, name.buf, sizeof(c->name));
+	strlcpy(ca->name, name.buf, sizeof(ca->name));
+
+	printbuf_exit(&name);
 
 	rebalance_wakeup(c);
 	return 0;
@@ -1294,8 +1410,7 @@ bool bch2_dev_state_allowed(struct bch_fs *c, struct bch_dev *ca,
 			    enum bch_member_state new_state, int flags)
 {
 	struct bch_devs_mask new_online_devs;
-	struct bch_dev *ca2;
-	int i, nr_rw = 0, required;
+	int nr_rw = 0, required;
 
 	lockdep_assert_held(&c->state_lock);
 
@@ -1307,7 +1422,7 @@ bool bch2_dev_state_allowed(struct bch_fs *c, struct bch_dev *ca,
 			return true;
 
 		/* do we have enough devices to write to?  */
-		for_each_member_device(ca2, c, i)
+		for_each_member_device(c, ca2)
 			if (ca2 != ca)
 				nr_rw += ca2->mi.state == BCH_MEMBER_STATE_rw;
 
@@ -1455,9 +1570,7 @@ static int bch2_dev_remove_alloc(struct bch_fs *c, struct bch_dev *ca)
 					BTREE_TRIGGER_NORUN, NULL) ?:
 		bch2_btree_delete_range(c, BTREE_ID_bucket_gens, start, end,
 					BTREE_TRIGGER_NORUN, NULL);
-	if (ret)
-		bch_err_msg(c, ret, "removing dev alloc info");
-
+	bch_err_msg(c, ret, "removing dev alloc info");
 	return ret;
 }
 
@@ -1484,34 +1597,29 @@ int bch2_dev_remove(struct bch_fs *c, struct bch_dev *ca, int flags)
 	__bch2_dev_read_only(c, ca);
 
 	ret = bch2_dev_data_drop(c, ca->dev_idx, flags);
-	if (ret) {
-		bch_err_msg(ca, ret, "dropping data");
+	bch_err_msg(ca, ret, "dropping data");
+	if (ret)
 		goto err;
-	}
 
 	ret = bch2_dev_remove_alloc(c, ca);
-	if (ret) {
-		bch_err_msg(ca, ret, "deleting alloc info");
+	bch_err_msg(ca, ret, "deleting alloc info");
+	if (ret)
 		goto err;
-	}
 
 	ret = bch2_journal_flush_device_pins(&c->journal, ca->dev_idx);
-	if (ret) {
-		bch_err_msg(ca, ret, "flushing journal");
+	bch_err_msg(ca, ret, "flushing journal");
+	if (ret)
 		goto err;
-	}
 
 	ret = bch2_journal_flush(&c->journal);
-	if (ret) {
-		bch_err(ca, "journal error");
+	bch_err(ca, "journal error");
+	if (ret)
 		goto err;
-	}
 
 	ret = bch2_replicas_gc2(c);
-	if (ret) {
-		bch_err_msg(ca, ret, "in replicas_gc2()");
+	bch_err_msg(ca, ret, "in replicas_gc2()");
+	if (ret)
 		goto err;
-	}
 
 	data = bch2_dev_has_data(c, ca);
 	if (data) {
@@ -1583,10 +1691,9 @@ int bch2_dev_add(struct bch_fs *c, const char *path)
 	int ret;
 
 	ret = bch2_read_super(path, &opts, &sb);
-	if (ret) {
-		bch_err_msg(c, ret, "reading super");
+	bch_err_msg(c, ret, "reading super");
+	if (ret)
 		goto err;
-	}
 
 	dev_mi = bch2_sb_member_get(sb.sb, sb.sb->dev_idx);
 
@@ -1599,10 +1706,8 @@ int bch2_dev_add(struct bch_fs *c, const char *path)
 	}
 
 	ret = bch2_dev_may_add(sb.sb, c);
-	if (ret) {
-		bch_err_fn(c, ret);
+	if (ret)
 		goto err;
-	}
 
 	ca = __bch2_dev_alloc(c, &dev_mi);
 	if (!ca) {
@@ -1617,19 +1722,17 @@ int bch2_dev_add(struct bch_fs *c, const char *path)
 		goto err;
 
 	ret = bch2_dev_journal_alloc(ca);
-	if (ret) {
-		bch_err_msg(c, ret, "allocating journal");
+	bch_err_msg(c, ret, "allocating journal");
+	if (ret)
 		goto err;
-	}
 
 	down_write(&c->state_lock);
 	mutex_lock(&c->sb_lock);
 
 	ret = bch2_sb_from_fs(c, ca);
-	if (ret) {
-		bch_err_msg(c, ret, "setting up new superblock");
+	bch_err_msg(c, ret, "setting up new superblock");
+	if (ret)
 		goto err_unlock;
-	}
 
 	if (dynamic_fault("bcachefs:add:no_slot"))
 		goto no_slot;
@@ -1668,10 +1771,9 @@ have_slot:
 
 	if (BCH_MEMBER_GROUP(&dev_mi)) {
 		ret = __bch2_dev_group_set(c, ca, label.buf);
-		if (ret) {
-			bch_err_msg(c, ret, "creating new label");
+		bch_err_msg(c, ret, "creating new label");
+		if (ret)
 			goto err_unlock;
-		}
 	}
 
 	bch2_write_super(c);
@@ -1680,16 +1782,14 @@ have_slot:
 	bch2_dev_usage_journal_reserve(c);
 
 	ret = bch2_trans_mark_dev_sb(c, ca);
-	if (ret) {
-		bch_err_msg(ca, ret, "marking new superblock");
+	bch_err_msg(ca, ret, "marking new superblock");
+	if (ret)
 		goto err_late;
-	}
 
 	ret = bch2_fs_freespace_init(c);
-	if (ret) {
-		bch_err_msg(ca, ret, "initializing free space");
+	bch_err_msg(ca, ret, "initializing free space");
+	if (ret)
 		goto err_late;
-	}
 
 	ca->new_fs_bucket_idx = 0;
 
@@ -1708,6 +1808,7 @@ err:
 	bch2_free_super(&sb);
 	printbuf_exit(&label);
 	printbuf_exit(&errbuf);
+	bch_err_fn(c, ret);
 	return ret;
 err_late:
 	up_write(&c->state_lock);
@@ -1734,11 +1835,10 @@ int bch2_dev_online(struct bch_fs *c, const char *path)
 
 	dev_idx = sb.sb->dev_idx;
 
-	ret = bch2_dev_in_fs(c->disk_sb.sb, sb.sb);
-	if (ret) {
-		bch_err_msg(c, ret, "bringing %s online", path);
+	ret = bch2_dev_in_fs(&c->disk_sb, &sb);
+	bch_err_msg(c, ret, "bringing %s online", path);
+	if (ret)
 		goto err;
-	}
 
 	ret = bch2_dev_attach_bdev(c, &sb);
 	if (ret)
@@ -1747,10 +1847,9 @@ int bch2_dev_online(struct bch_fs *c, const char *path)
 	ca = bch_dev_locked(c, dev_idx);
 
 	ret = bch2_trans_mark_dev_sb(c, ca);
-	if (ret) {
-		bch_err_msg(c, ret, "bringing %s online: error from bch2_trans_mark_dev_sb", path);
+	bch_err_msg(c, ret, "bringing %s online: error from bch2_trans_mark_dev_sb", path);
+	if (ret)
 		goto err;
-	}
 
 	if (ca->mi.state == BCH_MEMBER_STATE_rw)
 		__bch2_dev_read_write(c, ca);
@@ -1829,10 +1928,9 @@ int bch2_dev_resize(struct bch_fs *c, struct bch_dev *ca, u64 nbuckets)
 	}
 
 	ret = bch2_dev_buckets_resize(c, ca, nbuckets);
-	if (ret) {
-		bch_err_msg(ca, ret, "resizing buckets");
+	bch_err_msg(ca, ret, "resizing buckets");
+	if (ret)
 		goto err;
-	}
 
 	ret = bch2_trans_mark_dev_sb(c, ca);
 	if (ret)
@@ -1866,28 +1964,30 @@ err:
 /* return with ref on ca->ref: */
 struct bch_dev *bch2_dev_lookup(struct bch_fs *c, const char *name)
 {
-	struct bch_dev *ca;
-	unsigned i;
-
 	rcu_read_lock();
-	for_each_member_device_rcu(ca, c, i, NULL)
-		if (!strcmp(name, ca->name))
-			goto found;
-	ca = ERR_PTR(-BCH_ERR_ENOENT_dev_not_found);
-found:
+	for_each_member_device_rcu(c, ca, NULL)
+		if (!strcmp(name, ca->name)) {
+			rcu_read_unlock();
+			return ca;
+		}
 	rcu_read_unlock();
-
-	return ca;
+	return ERR_PTR(-BCH_ERR_ENOENT_dev_not_found);
 }
 
 /* Filesystem open: */
 
+static inline int sb_cmp(struct bch_sb *l, struct bch_sb *r)
+{
+	return  cmp_int(le64_to_cpu(l->seq), le64_to_cpu(r->seq)) ?:
+		cmp_int(le64_to_cpu(l->write_time), le64_to_cpu(r->write_time));
+}
+
 struct bch_fs *bch2_fs_open(char * const *devices, unsigned nr_devices,
 			    struct bch_opts opts)
 {
 	DARRAY(struct bch_sb_handle) sbs = { 0 };
 	struct bch_fs *c = NULL;
-	struct bch_sb_handle *sb, *best = NULL;
+	struct bch_sb_handle *best = NULL;
 	struct printbuf errbuf = PRINTBUF;
 	int ret = 0;
 
@@ -1913,20 +2013,27 @@ struct bch_fs *bch2_fs_open(char * const *devices, unsigned nr_devices,
 		BUG_ON(darray_push(&sbs, sb));
 	}
 
+	if (opts.nochanges && !opts.read_only) {
+		ret = -BCH_ERR_erofs_nochanges;
+		goto err_print;
+	}
+
 	darray_for_each(sbs, sb)
-		if (!best || le64_to_cpu(sb->sb->seq) > le64_to_cpu(best->sb->seq))
+		if (!best || sb_cmp(sb->sb, best->sb) > 0)
 			best = sb;
 
 	darray_for_each_reverse(sbs, sb) {
-		if (sb != best && !bch2_dev_exists(best->sb, sb->sb->dev_idx)) {
-			pr_info("%pg has been removed, skipping", sb->bdev);
+		ret = bch2_dev_in_fs(best, sb);
+
+		if (ret == -BCH_ERR_device_has_been_removed ||
+		    ret == -BCH_ERR_device_splitbrain) {
 			bch2_free_super(sb);
 			darray_remove_item(&sbs, sb);
 			best -= best > sb;
+			ret = 0;
 			continue;
 		}
 
-		ret = bch2_dev_in_fs(best->sb, sb->sb);
 		if (ret)
 			goto err_print;
 	}
diff --git a/fs/bcachefs/super.h b/fs/bcachefs/super.h
index bf762df18012..dada09331d2e 100644
--- a/fs/bcachefs/super.h
+++ b/fs/bcachefs/super.h
@@ -8,6 +8,8 @@
 
 #include <linux/math64.h>
 
+extern const char * const bch2_fs_flag_strs[];
+
 struct bch_fs *bch2_dev_to_fs(dev_t);
 struct bch_fs *bch2_uuid_to_fs(__uuid_t);
 
@@ -37,8 +39,8 @@ int bch2_fs_read_write_early(struct bch_fs *);
  */
 static inline void bch2_fs_lazy_rw(struct bch_fs *c)
 {
-	if (!test_bit(BCH_FS_RW, &c->flags) &&
-	    !test_bit(BCH_FS_WAS_RW, &c->flags))
+	if (!test_bit(BCH_FS_rw, &c->flags) &&
+	    !test_bit(BCH_FS_was_rw, &c->flags))
 		bch2_fs_read_write_early(c);
 }
 
diff --git a/fs/bcachefs/super_types.h b/fs/bcachefs/super_types.h
index 7dda4985b99f..0e5a14fc8e7f 100644
--- a/fs/bcachefs/super_types.h
+++ b/fs/bcachefs/super_types.h
@@ -4,7 +4,9 @@
 
 struct bch_sb_handle {
 	struct bch_sb		*sb;
+	struct bdev_handle	*bdev_handle;
 	struct block_device	*bdev;
+	char			*sb_name;
 	struct bio		*bio;
 	void			*holder;
 	size_t			buffer_size;
@@ -21,7 +23,7 @@ struct bch_devs_mask {
 
 struct bch_devs_list {
 	u8			nr;
-	u8			devs[BCH_BKEY_PTRS_MAX];
+	u8			data[BCH_BKEY_PTRS_MAX];
 };
 
 struct bch_member_cpu {
diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c
index ab743115f169..8ed52319ff68 100644
--- a/fs/bcachefs/sysfs.c
+++ b/fs/bcachefs/sysfs.c
@@ -145,6 +145,7 @@ rw_attribute(gc_gens_pos);
 
 read_attribute(uuid);
 read_attribute(minor);
+read_attribute(flags);
 read_attribute(bucket_size);
 read_attribute(first_bucket);
 read_attribute(nbuckets);
@@ -255,19 +256,18 @@ static size_t bch2_btree_cache_size(struct bch_fs *c)
 static int bch2_compression_stats_to_text(struct printbuf *out, struct bch_fs *c)
 {
 	struct btree_trans *trans;
-	struct btree_iter iter;
-	struct bkey_s_c k;
 	enum btree_id id;
-	u64 nr_uncompressed_extents = 0,
-	    nr_compressed_extents = 0,
-	    nr_incompressible_extents = 0,
-	    uncompressed_sectors = 0,
-	    incompressible_sectors = 0,
-	    compressed_sectors_compressed = 0,
-	    compressed_sectors_uncompressed = 0;
+	struct compression_type_stats {
+		u64		nr_extents;
+		u64		sectors_compressed;
+		u64		sectors_uncompressed;
+	} s[BCH_COMPRESSION_TYPE_NR];
+	u64 compressed_incompressible = 0;
 	int ret = 0;
 
-	if (!test_bit(BCH_FS_STARTED, &c->flags))
+	memset(s, 0, sizeof(s));
+
+	if (!test_bit(BCH_FS_started, &c->flags))
 		return -EPERM;
 
 	trans = bch2_trans_get(c);
@@ -276,41 +276,35 @@ static int bch2_compression_stats_to_text(struct printbuf *out, struct bch_fs *c
 		if (!btree_type_has_ptrs(id))
 			continue;
 
-		for_each_btree_key(trans, iter, id, POS_MIN,
-				   BTREE_ITER_ALL_SNAPSHOTS, k, ret) {
+		ret = for_each_btree_key(trans, iter, id, POS_MIN,
+					 BTREE_ITER_ALL_SNAPSHOTS, k, ({
 			struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
+			struct bch_extent_crc_unpacked crc;
 			const union bch_extent_entry *entry;
-			struct extent_ptr_decoded p;
-			bool compressed = false, uncompressed = false, incompressible = false;
-
-			bkey_for_each_ptr_decode(k.k, ptrs, p, entry) {
-				switch (p.crc.compression_type) {
-				case BCH_COMPRESSION_TYPE_none:
-					uncompressed = true;
-					uncompressed_sectors += k.k->size;
-					break;
-				case BCH_COMPRESSION_TYPE_incompressible:
-					incompressible = true;
-					incompressible_sectors += k.k->size;
-					break;
-				default:
-					compressed_sectors_compressed +=
-						p.crc.compressed_size;
-					compressed_sectors_uncompressed +=
-						p.crc.uncompressed_size;
-					compressed = true;
-					break;
+			bool compressed = false, incompressible = false;
+
+			bkey_for_each_crc(k.k, ptrs, crc, entry) {
+				incompressible	|= crc.compression_type == BCH_COMPRESSION_TYPE_incompressible;
+				compressed	|= crc_is_compressed(crc);
+
+				if (crc_is_compressed(crc)) {
+					s[crc.compression_type].nr_extents++;
+					s[crc.compression_type].sectors_compressed += crc.compressed_size;
+					s[crc.compression_type].sectors_uncompressed += crc.uncompressed_size;
 				}
 			}
 
-			if (incompressible)
-				nr_incompressible_extents++;
-			else if (uncompressed)
-				nr_uncompressed_extents++;
-			else if (compressed)
-				nr_compressed_extents++;
-		}
-		bch2_trans_iter_exit(trans, &iter);
+			compressed_incompressible += compressed && incompressible;
+
+			if (!compressed) {
+				unsigned t = incompressible ? BCH_COMPRESSION_TYPE_incompressible : 0;
+
+				s[t].nr_extents++;
+				s[t].sectors_compressed += k.k->size;
+				s[t].sectors_uncompressed += k.k->size;
+			}
+			0;
+		}));
 	}
 
 	bch2_trans_put(trans);
@@ -318,26 +312,45 @@ static int bch2_compression_stats_to_text(struct printbuf *out, struct bch_fs *c
 	if (ret)
 		return ret;
 
-	prt_printf(out, "uncompressed:\n");
-	prt_printf(out, "	nr extents:		%llu\n", nr_uncompressed_extents);
-	prt_printf(out, "	size:			");
-	prt_human_readable_u64(out, uncompressed_sectors << 9);
-	prt_printf(out, "\n");
+	prt_str(out, "type");
+	printbuf_tabstop_push(out, 12);
+	prt_tab(out);
 
-	prt_printf(out, "compressed:\n");
-	prt_printf(out, "	nr extents:		%llu\n", nr_compressed_extents);
-	prt_printf(out, "	compressed size:	");
-	prt_human_readable_u64(out, compressed_sectors_compressed << 9);
-	prt_printf(out, "\n");
-	prt_printf(out, "	uncompressed size:	");
-	prt_human_readable_u64(out, compressed_sectors_uncompressed << 9);
-	prt_printf(out, "\n");
+	prt_str(out, "compressed");
+	printbuf_tabstop_push(out, 16);
+	prt_tab_rjust(out);
+
+	prt_str(out, "uncompressed");
+	printbuf_tabstop_push(out, 16);
+	prt_tab_rjust(out);
+
+	prt_str(out, "average extent size");
+	printbuf_tabstop_push(out, 24);
+	prt_tab_rjust(out);
+	prt_newline(out);
+
+	for (unsigned i = 0; i < ARRAY_SIZE(s); i++) {
+		prt_str(out, bch2_compression_types[i]);
+		prt_tab(out);
+
+		prt_human_readable_u64(out, s[i].sectors_compressed << 9);
+		prt_tab_rjust(out);
+
+		prt_human_readable_u64(out, s[i].sectors_uncompressed << 9);
+		prt_tab_rjust(out);
+
+		prt_human_readable_u64(out, s[i].nr_extents
+				       ? div_u64(s[i].sectors_uncompressed << 9, s[i].nr_extents)
+				       : 0);
+		prt_tab_rjust(out);
+		prt_newline(out);
+	}
+
+	if (compressed_incompressible) {
+		prt_printf(out, "%llu compressed & incompressible extents", compressed_incompressible);
+		prt_newline(out);
+	}
 
-	prt_printf(out, "incompressible:\n");
-	prt_printf(out, "	nr extents:		%llu\n", nr_incompressible_extents);
-	prt_printf(out, "	size:			");
-	prt_human_readable_u64(out, incompressible_sectors << 9);
-	prt_printf(out, "\n");
 	return 0;
 }
 
@@ -370,6 +383,9 @@ SHOW(bch2_fs)
 	sysfs_print(minor,			c->minor);
 	sysfs_printf(internal_uuid, "%pU",	c->sb.uuid.b);
 
+	if (attr == &sysfs_flags)
+		prt_bitflags(out, bch2_fs_flag_strs, c->flags);
+
 	sysfs_hprint(btree_cache_size,		bch2_btree_cache_size(c));
 
 	if (attr == &sysfs_btree_write_stats)
@@ -483,12 +499,12 @@ STORE(bch2_fs)
 
 	/* Debugging: */
 
-	if (!test_bit(BCH_FS_STARTED, &c->flags))
+	if (!test_bit(BCH_FS_started, &c->flags))
 		return -EPERM;
 
 	/* Debugging: */
 
-	if (!test_bit(BCH_FS_RW, &c->flags))
+	if (!test_bit(BCH_FS_rw, &c->flags))
 		return -EROFS;
 
 	if (attr == &sysfs_prune_cache) {
@@ -620,6 +636,7 @@ STORE(bch2_fs_internal)
 SYSFS_OPS(bch2_fs_internal);
 
 struct attribute *bch2_fs_internal_files[] = {
+	&sysfs_flags,
 	&sysfs_journal_debug,
 	&sysfs_btree_updates,
 	&sysfs_btree_cache,
@@ -786,32 +803,7 @@ static void dev_alloc_debug_to_text(struct printbuf *out, struct bch_dev *ca)
 	printbuf_tabstop_push(out, 16);
 	printbuf_tabstop_push(out, 16);
 
-	prt_tab(out);
-	prt_str(out, "buckets");
-	prt_tab_rjust(out);
-	prt_str(out, "sectors");
-	prt_tab_rjust(out);
-	prt_str(out, "fragmented");
-	prt_tab_rjust(out);
-	prt_newline(out);
-
-	for (i = 0; i < BCH_DATA_NR; i++) {
-		prt_str(out, bch2_data_types[i]);
-		prt_tab(out);
-		prt_u64(out, stats.d[i].buckets);
-		prt_tab_rjust(out);
-		prt_u64(out, stats.d[i].sectors);
-		prt_tab_rjust(out);
-		prt_u64(out, stats.d[i].fragmented);
-		prt_tab_rjust(out);
-		prt_newline(out);
-	}
-
-	prt_str(out, "ec");
-	prt_tab(out);
-	prt_u64(out, stats.buckets_ec);
-	prt_tab_rjust(out);
-	prt_newline(out);
+	bch2_dev_usage_to_text(out, &stats);
 
 	prt_newline(out);
 
diff --git a/fs/bcachefs/tests.c b/fs/bcachefs/tests.c
index 2fc9e60c754b..b3fe9fc57747 100644
--- a/fs/bcachefs/tests.c
+++ b/fs/bcachefs/tests.c
@@ -107,9 +107,6 @@ err:
 
 static int test_iterate(struct bch_fs *c, u64 nr)
 {
-	struct btree_trans *trans = bch2_trans_get(c);
-	struct btree_iter iter = { NULL };
-	struct bkey_s_c k;
 	u64 i;
 	int ret = 0;
 
@@ -127,49 +124,43 @@ static int test_iterate(struct bch_fs *c, u64 nr)
 		ret = bch2_btree_insert(c, BTREE_ID_xattrs, &ck.k_i, NULL, 0);
 		bch_err_msg(c, ret, "insert error");
 		if (ret)
-			goto err;
+			return ret;
 	}
 
 	pr_info("iterating forwards");
-
 	i = 0;
 
-	ret = for_each_btree_key2_upto(trans, iter, BTREE_ID_xattrs,
-				  SPOS(0, 0, U32_MAX), POS(0, U64_MAX),
-				  0, k, ({
-		BUG_ON(k.k->p.offset != i++);
-		0;
-	}));
+	ret = bch2_trans_run(c,
+		for_each_btree_key_upto(trans, iter, BTREE_ID_xattrs,
+					SPOS(0, 0, U32_MAX), POS(0, U64_MAX),
+					0, k, ({
+			BUG_ON(k.k->p.offset != i++);
+			0;
+		})));
 	bch_err_msg(c, ret, "error iterating forwards");
 	if (ret)
-		goto err;
+		return ret;
 
 	BUG_ON(i != nr);
 
 	pr_info("iterating backwards");
 
-	ret = for_each_btree_key_reverse(trans, iter, BTREE_ID_xattrs,
-					 SPOS(0, U64_MAX, U32_MAX), 0, k,
-		({
+	ret = bch2_trans_run(c,
+		for_each_btree_key_reverse(trans, iter, BTREE_ID_xattrs,
+				SPOS(0, U64_MAX, U32_MAX), 0, k, ({
 			BUG_ON(k.k->p.offset != --i);
 			0;
-		}));
+		})));
 	bch_err_msg(c, ret, "error iterating backwards");
 	if (ret)
-		goto err;
+		return ret;
 
 	BUG_ON(i);
-err:
-	bch2_trans_iter_exit(trans, &iter);
-	bch2_trans_put(trans);
-	return ret;
+	return 0;
 }
 
 static int test_iterate_extents(struct bch_fs *c, u64 nr)
 {
-	struct btree_trans *trans = bch2_trans_get(c);
-	struct btree_iter iter = { NULL };
-	struct bkey_s_c k;
 	u64 i;
 	int ret = 0;
 
@@ -188,51 +179,45 @@ static int test_iterate_extents(struct bch_fs *c, u64 nr)
 		ret = bch2_btree_insert(c, BTREE_ID_extents, &ck.k_i, NULL, 0);
 		bch_err_msg(c, ret, "insert error");
 		if (ret)
-			goto err;
+			return ret;
 	}
 
 	pr_info("iterating forwards");
-
 	i = 0;
 
-	ret = for_each_btree_key2_upto(trans, iter, BTREE_ID_extents,
-				  SPOS(0, 0, U32_MAX), POS(0, U64_MAX),
-				  0, k, ({
-		BUG_ON(bkey_start_offset(k.k) != i);
-		i = k.k->p.offset;
-		0;
-	}));
+	ret = bch2_trans_run(c,
+		for_each_btree_key_upto(trans, iter, BTREE_ID_extents,
+					SPOS(0, 0, U32_MAX), POS(0, U64_MAX),
+					0, k, ({
+			BUG_ON(bkey_start_offset(k.k) != i);
+			i = k.k->p.offset;
+			0;
+		})));
 	bch_err_msg(c, ret, "error iterating forwards");
 	if (ret)
-		goto err;
+		return ret;
 
 	BUG_ON(i != nr);
 
 	pr_info("iterating backwards");
 
-	ret = for_each_btree_key_reverse(trans, iter, BTREE_ID_extents,
-					 SPOS(0, U64_MAX, U32_MAX), 0, k,
-		({
+	ret = bch2_trans_run(c,
+		for_each_btree_key_reverse(trans, iter, BTREE_ID_extents,
+				SPOS(0, U64_MAX, U32_MAX), 0, k, ({
 			BUG_ON(k.k->p.offset != i);
 			i = bkey_start_offset(k.k);
 			0;
-		}));
+		})));
 	bch_err_msg(c, ret, "error iterating backwards");
 	if (ret)
-		goto err;
+		return ret;
 
 	BUG_ON(i);
-err:
-	bch2_trans_iter_exit(trans, &iter);
-	bch2_trans_put(trans);
-	return ret;
+	return 0;
 }
 
 static int test_iterate_slots(struct bch_fs *c, u64 nr)
 {
-	struct btree_trans *trans = bch2_trans_get(c);
-	struct btree_iter iter = { NULL };
-	struct bkey_s_c k;
 	u64 i;
 	int ret = 0;
 
@@ -250,57 +235,48 @@ static int test_iterate_slots(struct bch_fs *c, u64 nr)
 		ret = bch2_btree_insert(c, BTREE_ID_xattrs, &ck.k_i, NULL, 0);
 		bch_err_msg(c, ret, "insert error");
 		if (ret)
-			goto err;
+			return ret;
 	}
 
 	pr_info("iterating forwards");
-
 	i = 0;
 
-	ret = for_each_btree_key2_upto(trans, iter, BTREE_ID_xattrs,
-				  SPOS(0, 0, U32_MAX), POS(0, U64_MAX),
-				  0, k, ({
-		BUG_ON(k.k->p.offset != i);
-		i += 2;
-		0;
-	}));
+	ret = bch2_trans_run(c,
+		for_each_btree_key_upto(trans, iter, BTREE_ID_xattrs,
+					  SPOS(0, 0, U32_MAX), POS(0, U64_MAX),
+					  0, k, ({
+			BUG_ON(k.k->p.offset != i);
+			i += 2;
+			0;
+		})));
 	bch_err_msg(c, ret, "error iterating forwards");
 	if (ret)
-		goto err;
+		return ret;
 
 	BUG_ON(i != nr * 2);
 
 	pr_info("iterating forwards by slots");
-
 	i = 0;
 
-	ret = for_each_btree_key2_upto(trans, iter, BTREE_ID_xattrs,
-				  SPOS(0, 0, U32_MAX), POS(0, U64_MAX),
-				  BTREE_ITER_SLOTS, k, ({
-		if (i >= nr * 2)
-			break;
+	ret = bch2_trans_run(c,
+		for_each_btree_key_upto(trans, iter, BTREE_ID_xattrs,
+					SPOS(0, 0, U32_MAX), POS(0, U64_MAX),
+					BTREE_ITER_SLOTS, k, ({
+			if (i >= nr * 2)
+				break;
 
-		BUG_ON(k.k->p.offset != i);
-		BUG_ON(bkey_deleted(k.k) != (i & 1));
+			BUG_ON(k.k->p.offset != i);
+			BUG_ON(bkey_deleted(k.k) != (i & 1));
 
-		i++;
-		0;
-	}));
-	if (ret < 0) {
-		bch_err_msg(c, ret, "error iterating forwards by slots");
-		goto err;
-	}
-	ret = 0;
-err:
-	bch2_trans_put(trans);
+			i++;
+			0;
+		})));
+	bch_err_msg(c, ret, "error iterating forwards by slots");
 	return ret;
 }
 
 static int test_iterate_slots_extents(struct bch_fs *c, u64 nr)
 {
-	struct btree_trans *trans = bch2_trans_get(c);
-	struct btree_iter iter = { NULL };
-	struct bkey_s_c k;
 	u64 i;
 	int ret = 0;
 
@@ -319,50 +295,45 @@ static int test_iterate_slots_extents(struct bch_fs *c, u64 nr)
 		ret = bch2_btree_insert(c, BTREE_ID_extents, &ck.k_i, NULL, 0);
 		bch_err_msg(c, ret, "insert error");
 		if (ret)
-			goto err;
+			return ret;
 	}
 
 	pr_info("iterating forwards");
-
 	i = 0;
 
-	ret = for_each_btree_key2_upto(trans, iter, BTREE_ID_extents,
-				  SPOS(0, 0, U32_MAX), POS(0, U64_MAX),
-				  0, k, ({
-		BUG_ON(bkey_start_offset(k.k) != i + 8);
-		BUG_ON(k.k->size != 8);
-		i += 16;
-		0;
-	}));
+	ret = bch2_trans_run(c,
+		for_each_btree_key_upto(trans, iter, BTREE_ID_extents,
+					SPOS(0, 0, U32_MAX), POS(0, U64_MAX),
+					0, k, ({
+			BUG_ON(bkey_start_offset(k.k) != i + 8);
+			BUG_ON(k.k->size != 8);
+			i += 16;
+			0;
+		})));
 	bch_err_msg(c, ret, "error iterating forwards");
 	if (ret)
-		goto err;
+		return ret;
 
 	BUG_ON(i != nr);
 
 	pr_info("iterating forwards by slots");
-
 	i = 0;
 
-	ret = for_each_btree_key2_upto(trans, iter, BTREE_ID_extents,
-				 SPOS(0, 0, U32_MAX), POS(0, U64_MAX),
-				 BTREE_ITER_SLOTS, k, ({
-		if (i == nr)
-			break;
-		BUG_ON(bkey_deleted(k.k) != !(i % 16));
+	ret = bch2_trans_run(c,
+		for_each_btree_key_upto(trans, iter, BTREE_ID_extents,
+					SPOS(0, 0, U32_MAX), POS(0, U64_MAX),
+					BTREE_ITER_SLOTS, k, ({
+			if (i == nr)
+				break;
+			BUG_ON(bkey_deleted(k.k) != !(i % 16));
 
-		BUG_ON(bkey_start_offset(k.k) != i);
-		BUG_ON(k.k->size != 8);
-		i = k.k->p.offset;
-		0;
-	}));
+			BUG_ON(bkey_start_offset(k.k) != i);
+			BUG_ON(k.k->size != 8);
+			i = k.k->p.offset;
+			0;
+		})));
 	bch_err_msg(c, ret, "error iterating forwards by slots");
-	if (ret)
-		goto err;
-	ret = 0;
-err:
-	bch2_trans_put(trans);
-	return 0;
+	return ret;
 }
 
 /*
@@ -736,8 +707,6 @@ static int rand_delete(struct bch_fs *c, u64 nr)
 
 static int seq_insert(struct bch_fs *c, u64 nr)
 {
-	struct btree_iter iter;
-	struct bkey_s_c k;
 	struct bkey_i_cookie insert;
 
 	bkey_cookie_init(&insert.k_i);
@@ -756,11 +725,8 @@ static int seq_insert(struct bch_fs *c, u64 nr)
 
 static int seq_lookup(struct bch_fs *c, u64 nr)
 {
-	struct btree_iter iter;
-	struct bkey_s_c k;
-
 	return bch2_trans_run(c,
-		for_each_btree_key2_upto(trans, iter, BTREE_ID_xattrs,
+		for_each_btree_key_upto(trans, iter, BTREE_ID_xattrs,
 				  SPOS(0, 0, U32_MAX), POS(0, U64_MAX),
 				  0, k,
 		0));
@@ -768,9 +734,6 @@ static int seq_lookup(struct bch_fs *c, u64 nr)
 
 static int seq_overwrite(struct bch_fs *c, u64 nr)
 {
-	struct btree_iter iter;
-	struct bkey_s_c k;
-
 	return bch2_trans_run(c,
 		for_each_btree_key_commit(trans, iter, BTREE_ID_xattrs,
 					SPOS(0, 0, U32_MAX),
diff --git a/fs/bcachefs/thread_with_file.c b/fs/bcachefs/thread_with_file.c
new file mode 100644
index 000000000000..b1c867aa2b58
--- /dev/null
+++ b/fs/bcachefs/thread_with_file.c
@@ -0,0 +1,299 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef NO_BCACHEFS_FS
+
+#include "bcachefs.h"
+#include "printbuf.h"
+#include "thread_with_file.h"
+
+#include <linux/anon_inodes.h>
+#include <linux/file.h>
+#include <linux/kthread.h>
+#include <linux/pagemap.h>
+#include <linux/poll.h>
+
+void bch2_thread_with_file_exit(struct thread_with_file *thr)
+{
+	if (thr->task) {
+		kthread_stop(thr->task);
+		put_task_struct(thr->task);
+	}
+}
+
+int bch2_run_thread_with_file(struct thread_with_file *thr,
+			      const struct file_operations *fops,
+			      int (*fn)(void *))
+{
+	struct file *file = NULL;
+	int ret, fd = -1;
+	unsigned fd_flags = O_CLOEXEC;
+
+	if (fops->read && fops->write)
+		fd_flags |= O_RDWR;
+	else if (fops->read)
+		fd_flags |= O_RDONLY;
+	else if (fops->write)
+		fd_flags |= O_WRONLY;
+
+	char name[TASK_COMM_LEN];
+	get_task_comm(name, current);
+
+	thr->ret = 0;
+	thr->task = kthread_create(fn, thr, "%s", name);
+	ret = PTR_ERR_OR_ZERO(thr->task);
+	if (ret)
+		return ret;
+
+	ret = get_unused_fd_flags(fd_flags);
+	if (ret < 0)
+		goto err;
+	fd = ret;
+
+	file = anon_inode_getfile(name, fops, thr, fd_flags);
+	ret = PTR_ERR_OR_ZERO(file);
+	if (ret)
+		goto err;
+
+	fd_install(fd, file);
+	get_task_struct(thr->task);
+	wake_up_process(thr->task);
+	return fd;
+err:
+	if (fd >= 0)
+		put_unused_fd(fd);
+	if (thr->task)
+		kthread_stop(thr->task);
+	return ret;
+}
+
+static inline bool thread_with_stdio_has_output(struct thread_with_stdio *thr)
+{
+	return thr->stdio.output_buf.pos ||
+		thr->output2.nr ||
+		thr->thr.done;
+}
+
+static ssize_t thread_with_stdio_read(struct file *file, char __user *buf,
+				      size_t len, loff_t *ppos)
+{
+	struct thread_with_stdio *thr =
+		container_of(file->private_data, struct thread_with_stdio, thr);
+	size_t copied = 0, b;
+	int ret = 0;
+
+	if ((file->f_flags & O_NONBLOCK) &&
+	    !thread_with_stdio_has_output(thr))
+		return -EAGAIN;
+
+	ret = wait_event_interruptible(thr->stdio.output_wait,
+		thread_with_stdio_has_output(thr));
+	if (ret)
+		return ret;
+
+	if (thr->thr.done)
+		return 0;
+
+	while (len) {
+		ret = darray_make_room(&thr->output2, thr->stdio.output_buf.pos);
+		if (ret)
+			break;
+
+		spin_lock_irq(&thr->stdio.output_lock);
+		b = min_t(size_t, darray_room(thr->output2), thr->stdio.output_buf.pos);
+
+		memcpy(&darray_top(thr->output2), thr->stdio.output_buf.buf, b);
+		memmove(thr->stdio.output_buf.buf,
+			thr->stdio.output_buf.buf + b,
+			thr->stdio.output_buf.pos - b);
+
+		thr->output2.nr += b;
+		thr->stdio.output_buf.pos -= b;
+		spin_unlock_irq(&thr->stdio.output_lock);
+
+		b = min(len, thr->output2.nr);
+		if (!b)
+			break;
+
+		b -= copy_to_user(buf, thr->output2.data, b);
+		if (!b) {
+			ret = -EFAULT;
+			break;
+		}
+
+		copied	+= b;
+		buf	+= b;
+		len	-= b;
+
+		memmove(thr->output2.data,
+			thr->output2.data + b,
+			thr->output2.nr - b);
+		thr->output2.nr -= b;
+	}
+
+	return copied ?: ret;
+}
+
+static int thread_with_stdio_release(struct inode *inode, struct file *file)
+{
+	struct thread_with_stdio *thr =
+		container_of(file->private_data, struct thread_with_stdio, thr);
+
+	bch2_thread_with_file_exit(&thr->thr);
+	printbuf_exit(&thr->stdio.input_buf);
+	printbuf_exit(&thr->stdio.output_buf);
+	darray_exit(&thr->output2);
+	thr->exit(thr);
+	return 0;
+}
+
+#define WRITE_BUFFER		4096
+
+static inline bool thread_with_stdio_has_input_space(struct thread_with_stdio *thr)
+{
+	return thr->stdio.input_buf.pos < WRITE_BUFFER || thr->thr.done;
+}
+
+static ssize_t thread_with_stdio_write(struct file *file, const char __user *ubuf,
+				       size_t len, loff_t *ppos)
+{
+	struct thread_with_stdio *thr =
+		container_of(file->private_data, struct thread_with_stdio, thr);
+	struct printbuf *buf = &thr->stdio.input_buf;
+	size_t copied = 0;
+	ssize_t ret = 0;
+
+	while (len) {
+		if (thr->thr.done) {
+			ret = -EPIPE;
+			break;
+		}
+
+		size_t b = len - fault_in_readable(ubuf, len);
+		if (!b) {
+			ret = -EFAULT;
+			break;
+		}
+
+		spin_lock(&thr->stdio.input_lock);
+		if (buf->pos < WRITE_BUFFER)
+			bch2_printbuf_make_room(buf, min(b, WRITE_BUFFER - buf->pos));
+		b = min(len, printbuf_remaining_size(buf));
+
+		if (b && !copy_from_user_nofault(&buf->buf[buf->pos], ubuf, b)) {
+			ubuf += b;
+			len -= b;
+			copied += b;
+			buf->pos += b;
+		}
+		spin_unlock(&thr->stdio.input_lock);
+
+		if (b) {
+			wake_up(&thr->stdio.input_wait);
+		} else {
+			if ((file->f_flags & O_NONBLOCK)) {
+				ret = -EAGAIN;
+				break;
+			}
+
+			ret = wait_event_interruptible(thr->stdio.input_wait,
+					thread_with_stdio_has_input_space(thr));
+			if (ret)
+				break;
+		}
+	}
+
+	return copied ?: ret;
+}
+
+static __poll_t thread_with_stdio_poll(struct file *file, struct poll_table_struct *wait)
+{
+	struct thread_with_stdio *thr =
+		container_of(file->private_data, struct thread_with_stdio, thr);
+
+	poll_wait(file, &thr->stdio.output_wait, wait);
+	poll_wait(file, &thr->stdio.input_wait, wait);
+
+	__poll_t mask = 0;
+
+	if (thread_with_stdio_has_output(thr))
+		mask |= EPOLLIN;
+	if (thread_with_stdio_has_input_space(thr))
+		mask |= EPOLLOUT;
+	if (thr->thr.done)
+		mask |= EPOLLHUP|EPOLLERR;
+	return mask;
+}
+
+static const struct file_operations thread_with_stdio_fops = {
+	.release	= thread_with_stdio_release,
+	.read		= thread_with_stdio_read,
+	.write		= thread_with_stdio_write,
+	.poll		= thread_with_stdio_poll,
+	.llseek		= no_llseek,
+};
+
+int bch2_run_thread_with_stdio(struct thread_with_stdio *thr,
+			       void (*exit)(struct thread_with_stdio *),
+			       int (*fn)(void *))
+{
+	thr->stdio.input_buf = PRINTBUF;
+	thr->stdio.input_buf.atomic++;
+	spin_lock_init(&thr->stdio.input_lock);
+	init_waitqueue_head(&thr->stdio.input_wait);
+
+	thr->stdio.output_buf = PRINTBUF;
+	thr->stdio.output_buf.atomic++;
+	spin_lock_init(&thr->stdio.output_lock);
+	init_waitqueue_head(&thr->stdio.output_wait);
+
+	darray_init(&thr->output2);
+	thr->exit = exit;
+
+	return bch2_run_thread_with_file(&thr->thr, &thread_with_stdio_fops, fn);
+}
+
+int bch2_stdio_redirect_read(struct stdio_redirect *stdio, char *buf, size_t len)
+{
+	wait_event(stdio->input_wait,
+		   stdio->input_buf.pos || stdio->done);
+
+	if (stdio->done)
+		return -1;
+
+	spin_lock(&stdio->input_lock);
+	int ret = min(len, stdio->input_buf.pos);
+	stdio->input_buf.pos -= ret;
+	memcpy(buf, stdio->input_buf.buf, ret);
+	memmove(stdio->input_buf.buf,
+		stdio->input_buf.buf + ret,
+		stdio->input_buf.pos);
+	spin_unlock(&stdio->input_lock);
+
+	wake_up(&stdio->input_wait);
+	return ret;
+}
+
+int bch2_stdio_redirect_readline(struct stdio_redirect *stdio, char *buf, size_t len)
+{
+	wait_event(stdio->input_wait,
+		   stdio->input_buf.pos || stdio->done);
+
+	if (stdio->done)
+		return -1;
+
+	spin_lock(&stdio->input_lock);
+	int ret = min(len, stdio->input_buf.pos);
+	char *n = memchr(stdio->input_buf.buf, '\n', ret);
+	if (n)
+		ret = min(ret, n + 1 - stdio->input_buf.buf);
+	stdio->input_buf.pos -= ret;
+	memcpy(buf, stdio->input_buf.buf, ret);
+	memmove(stdio->input_buf.buf,
+		stdio->input_buf.buf + ret,
+		stdio->input_buf.pos);
+	spin_unlock(&stdio->input_lock);
+
+	wake_up(&stdio->input_wait);
+	return ret;
+}
+
+#endif /* NO_BCACHEFS_FS */
diff --git a/fs/bcachefs/thread_with_file.h b/fs/bcachefs/thread_with_file.h
new file mode 100644
index 000000000000..05879c5048c8
--- /dev/null
+++ b/fs/bcachefs/thread_with_file.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_THREAD_WITH_FILE_H
+#define _BCACHEFS_THREAD_WITH_FILE_H
+
+#include "thread_with_file_types.h"
+
+struct task_struct;
+
+struct thread_with_file {
+	struct task_struct	*task;
+	int			ret;
+	bool			done;
+};
+
+void bch2_thread_with_file_exit(struct thread_with_file *);
+int bch2_run_thread_with_file(struct thread_with_file *,
+			      const struct file_operations *,
+			      int (*fn)(void *));
+
+struct thread_with_stdio {
+	struct thread_with_file	thr;
+	struct stdio_redirect	stdio;
+	DARRAY(char)		output2;
+	void			(*exit)(struct thread_with_stdio *);
+};
+
+static inline void thread_with_stdio_done(struct thread_with_stdio *thr)
+{
+	thr->thr.done = true;
+	thr->stdio.done = true;
+	wake_up(&thr->stdio.input_wait);
+	wake_up(&thr->stdio.output_wait);
+}
+
+int bch2_run_thread_with_stdio(struct thread_with_stdio *,
+			       void (*exit)(struct thread_with_stdio *),
+			       int (*fn)(void *));
+int bch2_stdio_redirect_read(struct stdio_redirect *, char *, size_t);
+int bch2_stdio_redirect_readline(struct stdio_redirect *, char *, size_t);
+
+#endif /* _BCACHEFS_THREAD_WITH_FILE_H */
diff --git a/fs/bcachefs/thread_with_file_types.h b/fs/bcachefs/thread_with_file_types.h
new file mode 100644
index 000000000000..90b5e645e98c
--- /dev/null
+++ b/fs/bcachefs/thread_with_file_types.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_THREAD_WITH_FILE_TYPES_H
+#define _BCACHEFS_THREAD_WITH_FILE_TYPES_H
+
+struct stdio_redirect {
+	spinlock_t		output_lock;
+	wait_queue_head_t	output_wait;
+	struct printbuf		output_buf;
+
+	spinlock_t		input_lock;
+	wait_queue_head_t	input_wait;
+	struct printbuf		input_buf;
+	bool			done;
+};
+
+#endif /* _BCACHEFS_THREAD_WITH_FILE_TYPES_H */
diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h
index 893304a1f06e..c94876b3bb06 100644
--- a/fs/bcachefs/trace.h
+++ b/fs/bcachefs/trace.h
@@ -32,22 +32,68 @@ DECLARE_EVENT_CLASS(bpos,
 	TP_printk("%llu:%llu:%u", __entry->p_inode, __entry->p_offset, __entry->p_snapshot)
 );
 
-DECLARE_EVENT_CLASS(bkey,
-	TP_PROTO(struct bch_fs *c, const char *k),
-	TP_ARGS(c, k),
+DECLARE_EVENT_CLASS(fs_str,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str),
 
 	TP_STRUCT__entry(
-		__string(k,	k				)
+		__field(dev_t,		dev			)
+		__string(str,		str			)
 	),
 
 	TP_fast_assign(
-		__assign_str(k, k);
+		__entry->dev		= c->dev;
+		__assign_str(str, str);
 	),
 
-	TP_printk("%s", __get_str(k))
+	TP_printk("%d,%d %s", MAJOR(__entry->dev), MINOR(__entry->dev), __get_str(str))
 );
 
-DECLARE_EVENT_CLASS(btree_node,
+DECLARE_EVENT_CLASS(trans_str,
+	TP_PROTO(struct btree_trans *trans, unsigned long caller_ip, const char *str),
+	TP_ARGS(trans, caller_ip, str),
+
+	TP_STRUCT__entry(
+		__field(dev_t,		dev			)
+		__array(char,		trans_fn, 32		)
+		__field(unsigned long,	caller_ip		)
+		__string(str,		str			)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= trans->c->dev;
+		strscpy(__entry->trans_fn, trans->fn, sizeof(__entry->trans_fn));
+		__entry->caller_ip		= caller_ip;
+		__assign_str(str, str);
+	),
+
+	TP_printk("%d,%d %s %pS %s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->trans_fn, (void *) __entry->caller_ip, __get_str(str))
+);
+
+DECLARE_EVENT_CLASS(trans_str_nocaller,
+	TP_PROTO(struct btree_trans *trans, const char *str),
+	TP_ARGS(trans, str),
+
+	TP_STRUCT__entry(
+		__field(dev_t,		dev			)
+		__array(char,		trans_fn, 32		)
+		__string(str,		str			)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= trans->c->dev;
+		strscpy(__entry->trans_fn, trans->fn, sizeof(__entry->trans_fn));
+		__assign_str(str, str);
+	),
+
+	TP_printk("%d,%d %s %s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->trans_fn, __get_str(str))
+);
+
+DECLARE_EVENT_CLASS(btree_node_nofs,
 	TP_PROTO(struct bch_fs *c, struct btree *b),
 	TP_ARGS(c, b),
 
@@ -72,6 +118,33 @@ DECLARE_EVENT_CLASS(btree_node,
 		  __entry->pos_inode, __entry->pos_offset, __entry->pos_snapshot)
 );
 
+DECLARE_EVENT_CLASS(btree_node,
+	TP_PROTO(struct btree_trans *trans, struct btree *b),
+	TP_ARGS(trans, b),
+
+	TP_STRUCT__entry(
+		__field(dev_t,		dev			)
+		__array(char,		trans_fn, 32		)
+		__field(u8,		level			)
+		__field(u8,		btree_id		)
+		TRACE_BPOS_entries(pos)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= trans->c->dev;
+		strscpy(__entry->trans_fn, trans->fn, sizeof(__entry->trans_fn));
+		__entry->level		= b->c.level;
+		__entry->btree_id	= b->c.btree_id;
+		TRACE_BPOS_assign(pos, b->key.k.p);
+	),
+
+	TP_printk("%d,%d %s %u %s %llu:%llu:%u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->trans_fn,
+		  __entry->level,
+		  bch2_btree_id_str(__entry->btree_id),
+		  __entry->pos_inode, __entry->pos_offset, __entry->pos_snapshot)
+);
+
 DECLARE_EVENT_CLASS(bch_fs,
 	TP_PROTO(struct bch_fs *c),
 	TP_ARGS(c),
@@ -87,6 +160,23 @@ DECLARE_EVENT_CLASS(bch_fs,
 	TP_printk("%d,%d", MAJOR(__entry->dev), MINOR(__entry->dev))
 );
 
+DECLARE_EVENT_CLASS(btree_trans,
+	TP_PROTO(struct btree_trans *trans),
+	TP_ARGS(trans),
+
+	TP_STRUCT__entry(
+		__field(dev_t,		dev			)
+		__array(char,		trans_fn, 32		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= trans->c->dev;
+		strscpy(__entry->trans_fn, trans->fn, sizeof(__entry->trans_fn));
+	),
+
+	TP_printk("%d,%d %s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->trans_fn)
+);
+
 DECLARE_EVENT_CLASS(bio,
 	TP_PROTO(struct bio *bio),
 	TP_ARGS(bio),
@@ -188,6 +278,25 @@ DEFINE_EVENT(bch_fs, journal_entry_full,
 	TP_ARGS(c)
 );
 
+TRACE_EVENT(journal_entry_close,
+	TP_PROTO(struct bch_fs *c, unsigned bytes),
+	TP_ARGS(c, bytes),
+
+	TP_STRUCT__entry(
+		__field(dev_t,		dev			)
+		__field(u32,		bytes			)
+	),
+
+	TP_fast_assign(
+		__entry->dev			= c->dev;
+		__entry->bytes			= bytes;
+	),
+
+	TP_printk("%d,%d entry bytes %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->bytes)
+);
+
 DEFINE_EVENT(bio, journal_write,
 	TP_PROTO(struct bio *bio),
 	TP_ARGS(bio)
@@ -196,10 +305,9 @@ DEFINE_EVENT(bio, journal_write,
 TRACE_EVENT(journal_reclaim_start,
 	TP_PROTO(struct bch_fs *c, bool direct, bool kicked,
 		 u64 min_nr, u64 min_key_cache,
-		 u64 prereserved, u64 prereserved_total,
 		 u64 btree_cache_dirty, u64 btree_cache_total,
 		 u64 btree_key_cache_dirty, u64 btree_key_cache_total),
-	TP_ARGS(c, direct, kicked, min_nr, min_key_cache, prereserved, prereserved_total,
+	TP_ARGS(c, direct, kicked, min_nr, min_key_cache,
 		btree_cache_dirty, btree_cache_total,
 		btree_key_cache_dirty, btree_key_cache_total),
 
@@ -209,8 +317,6 @@ TRACE_EVENT(journal_reclaim_start,
 		__field(bool,		kicked			)
 		__field(u64,		min_nr			)
 		__field(u64,		min_key_cache		)
-		__field(u64,		prereserved		)
-		__field(u64,		prereserved_total	)
 		__field(u64,		btree_cache_dirty	)
 		__field(u64,		btree_cache_total	)
 		__field(u64,		btree_key_cache_dirty	)
@@ -223,22 +329,18 @@ TRACE_EVENT(journal_reclaim_start,
 		__entry->kicked			= kicked;
 		__entry->min_nr			= min_nr;
 		__entry->min_key_cache		= min_key_cache;
-		__entry->prereserved		= prereserved;
-		__entry->prereserved_total	= prereserved_total;
 		__entry->btree_cache_dirty	= btree_cache_dirty;
 		__entry->btree_cache_total	= btree_cache_total;
 		__entry->btree_key_cache_dirty	= btree_key_cache_dirty;
 		__entry->btree_key_cache_total	= btree_key_cache_total;
 	),
 
-	TP_printk("%d,%d direct %u kicked %u min %llu key cache %llu prereserved %llu/%llu btree cache %llu/%llu key cache %llu/%llu",
+	TP_printk("%d,%d direct %u kicked %u min %llu key cache %llu btree cache %llu/%llu key cache %llu/%llu",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->direct,
 		  __entry->kicked,
 		  __entry->min_nr,
 		  __entry->min_key_cache,
-		  __entry->prereserved,
-		  __entry->prereserved_total,
 		  __entry->btree_cache_dirty,
 		  __entry->btree_cache_total,
 		  __entry->btree_key_cache_dirty,
@@ -293,36 +395,36 @@ TRACE_EVENT(btree_cache_scan,
 		  __entry->nr_to_scan, __entry->can_free, __entry->ret)
 );
 
-DEFINE_EVENT(btree_node, btree_cache_reap,
+DEFINE_EVENT(btree_node_nofs, btree_cache_reap,
 	TP_PROTO(struct bch_fs *c, struct btree *b),
 	TP_ARGS(c, b)
 );
 
-DEFINE_EVENT(bch_fs, btree_cache_cannibalize_lock_fail,
-	TP_PROTO(struct bch_fs *c),
-	TP_ARGS(c)
+DEFINE_EVENT(btree_trans, btree_cache_cannibalize_lock_fail,
+	TP_PROTO(struct btree_trans *trans),
+	TP_ARGS(trans)
 );
 
-DEFINE_EVENT(bch_fs, btree_cache_cannibalize_lock,
-	TP_PROTO(struct bch_fs *c),
-	TP_ARGS(c)
+DEFINE_EVENT(btree_trans, btree_cache_cannibalize_lock,
+	TP_PROTO(struct btree_trans *trans),
+	TP_ARGS(trans)
 );
 
-DEFINE_EVENT(bch_fs, btree_cache_cannibalize,
-	TP_PROTO(struct bch_fs *c),
-	TP_ARGS(c)
+DEFINE_EVENT(btree_trans, btree_cache_cannibalize,
+	TP_PROTO(struct btree_trans *trans),
+	TP_ARGS(trans)
 );
 
-DEFINE_EVENT(bch_fs, btree_cache_cannibalize_unlock,
-	TP_PROTO(struct bch_fs *c),
-	TP_ARGS(c)
+DEFINE_EVENT(btree_trans, btree_cache_cannibalize_unlock,
+	TP_PROTO(struct btree_trans *trans),
+	TP_ARGS(trans)
 );
 
 /* Btree */
 
 DEFINE_EVENT(btree_node, btree_node_read,
-	TP_PROTO(struct bch_fs *c, struct btree *b),
-	TP_ARGS(c, b)
+	TP_PROTO(struct btree_trans *trans, struct btree *b),
+	TP_ARGS(trans, b)
 );
 
 TRACE_EVENT(btree_node_write,
@@ -346,13 +448,13 @@ TRACE_EVENT(btree_node_write,
 );
 
 DEFINE_EVENT(btree_node, btree_node_alloc,
-	TP_PROTO(struct bch_fs *c, struct btree *b),
-	TP_ARGS(c, b)
+	TP_PROTO(struct btree_trans *trans, struct btree *b),
+	TP_ARGS(trans, b)
 );
 
 DEFINE_EVENT(btree_node, btree_node_free,
-	TP_PROTO(struct bch_fs *c, struct btree *b),
-	TP_ARGS(c, b)
+	TP_PROTO(struct btree_trans *trans, struct btree *b),
+	TP_ARGS(trans, b)
 );
 
 TRACE_EVENT(btree_reserve_get_fail,
@@ -384,28 +486,28 @@ TRACE_EVENT(btree_reserve_get_fail,
 );
 
 DEFINE_EVENT(btree_node, btree_node_compact,
-	TP_PROTO(struct bch_fs *c, struct btree *b),
-	TP_ARGS(c, b)
+	TP_PROTO(struct btree_trans *trans, struct btree *b),
+	TP_ARGS(trans, b)
 );
 
 DEFINE_EVENT(btree_node, btree_node_merge,
-	TP_PROTO(struct bch_fs *c, struct btree *b),
-	TP_ARGS(c, b)
+	TP_PROTO(struct btree_trans *trans, struct btree *b),
+	TP_ARGS(trans, b)
 );
 
 DEFINE_EVENT(btree_node, btree_node_split,
-	TP_PROTO(struct bch_fs *c, struct btree *b),
-	TP_ARGS(c, b)
+	TP_PROTO(struct btree_trans *trans, struct btree *b),
+	TP_ARGS(trans, b)
 );
 
 DEFINE_EVENT(btree_node, btree_node_rewrite,
-	TP_PROTO(struct bch_fs *c, struct btree *b),
-	TP_ARGS(c, b)
+	TP_PROTO(struct btree_trans *trans, struct btree *b),
+	TP_ARGS(trans, b)
 );
 
 DEFINE_EVENT(btree_node, btree_node_set_root,
-	TP_PROTO(struct bch_fs *c, struct btree *b),
-	TP_ARGS(c, b)
+	TP_PROTO(struct btree_trans *trans, struct btree *b),
+	TP_ARGS(trans, b)
 );
 
 TRACE_EVENT(btree_path_relock_fail,
@@ -724,22 +826,22 @@ TRACE_EVENT(bucket_evacuate,
 		  __entry->dev_idx, __entry->bucket)
 );
 
-DEFINE_EVENT(bkey, move_extent,
+DEFINE_EVENT(fs_str, move_extent,
 	TP_PROTO(struct bch_fs *c, const char *k),
 	TP_ARGS(c, k)
 );
 
-DEFINE_EVENT(bkey, move_extent_read,
+DEFINE_EVENT(fs_str, move_extent_read,
 	TP_PROTO(struct bch_fs *c, const char *k),
 	TP_ARGS(c, k)
 );
 
-DEFINE_EVENT(bkey, move_extent_write,
+DEFINE_EVENT(fs_str, move_extent_write,
 	TP_PROTO(struct bch_fs *c, const char *k),
 	TP_ARGS(c, k)
 );
 
-DEFINE_EVENT(bkey, move_extent_finish,
+DEFINE_EVENT(fs_str, move_extent_finish,
 	TP_PROTO(struct bch_fs *c, const char *k),
 	TP_ARGS(c, k)
 );
@@ -761,9 +863,9 @@ TRACE_EVENT(move_extent_fail,
 	TP_printk("%d:%d %s", MAJOR(__entry->dev), MINOR(__entry->dev), __get_str(msg))
 );
 
-DEFINE_EVENT(bkey, move_extent_alloc_mem_fail,
-	TP_PROTO(struct bch_fs *c, const char *k),
-	TP_ARGS(c, k)
+DEFINE_EVENT(fs_str, move_extent_start_fail,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
 );
 
 TRACE_EVENT(move_data,
@@ -994,10 +1096,11 @@ DEFINE_EVENT(transaction_event,	trans_restart_key_cache_raced,
 	TP_ARGS(trans, caller_ip)
 );
 
-DEFINE_EVENT(transaction_event,	trans_restart_too_many_iters,
+DEFINE_EVENT(trans_str, trans_restart_too_many_iters,
 	TP_PROTO(struct btree_trans *trans,
-		 unsigned long caller_ip),
-	TP_ARGS(trans, caller_ip)
+		 unsigned long caller_ip,
+		 const char *paths),
+	TP_ARGS(trans, caller_ip, paths)
 );
 
 DECLARE_EVENT_CLASS(transaction_restart_iter,
@@ -1063,8 +1166,6 @@ TRACE_EVENT(trans_restart_upgrade,
 		__field(u8,			level		)
 		__field(u32,			path_seq	)
 		__field(u32,			node_seq	)
-		__field(u32,			path_alloc_seq	)
-		__field(u32,			downgrade_seq)
 		TRACE_BPOS_entries(pos)
 	),
 
@@ -1077,12 +1178,10 @@ TRACE_EVENT(trans_restart_upgrade,
 		__entry->level			= f->l;
 		__entry->path_seq		= path->l[f->l].lock_seq;
 		__entry->node_seq		= IS_ERR_OR_NULL(f->b) ? 0 : f->b->c.lock.seq;
-		__entry->path_alloc_seq		= path->alloc_seq;
-		__entry->downgrade_seq		= path->downgrade_seq;
 		TRACE_BPOS_assign(pos, path->pos)
 	),
 
-	TP_printk("%s %pS btree %s pos %llu:%llu:%u locks_want %u -> %u level %u path seq %u node seq %u alloc_seq %u downgrade_seq %u",
+	TP_printk("%s %pS btree %s pos %llu:%llu:%u locks_want %u -> %u level %u path seq %u node seq %u",
 		  __entry->trans_fn,
 		  (void *) __entry->caller_ip,
 		  bch2_btree_id_str(__entry->btree_id),
@@ -1093,9 +1192,7 @@ TRACE_EVENT(trans_restart_upgrade,
 		  __entry->new_locks_want,
 		  __entry->level,
 		  __entry->path_seq,
-		  __entry->node_seq,
-		  __entry->path_alloc_seq,
-		  __entry->downgrade_seq)
+		  __entry->node_seq)
 );
 
 DEFINE_EVENT(transaction_restart_iter,	trans_restart_relock,
@@ -1167,10 +1264,10 @@ DEFINE_EVENT(transaction_restart_iter,	trans_restart_memory_allocation_failure,
 	TP_ARGS(trans, caller_ip, path)
 );
 
-DEFINE_EVENT(transaction_event,	trans_restart_would_deadlock,
+DEFINE_EVENT(trans_str_nocaller, trans_restart_would_deadlock,
 	TP_PROTO(struct btree_trans *trans,
-		 unsigned long caller_ip),
-	TP_ARGS(trans, caller_ip)
+		 const char *cycle),
+	TP_ARGS(trans, cycle)
 );
 
 DEFINE_EVENT(transaction_event,	trans_restart_would_deadlock_recursion_limit,
@@ -1259,22 +1356,37 @@ TRACE_EVENT(trans_restart_key_cache_key_realloced,
 TRACE_EVENT(path_downgrade,
 	TP_PROTO(struct btree_trans *trans,
 		 unsigned long caller_ip,
-		 struct btree_path *path),
-	TP_ARGS(trans, caller_ip, path),
+		 struct btree_path *path,
+		 unsigned old_locks_want),
+	TP_ARGS(trans, caller_ip, path, old_locks_want),
 
 	TP_STRUCT__entry(
 		__array(char,			trans_fn, 32	)
 		__field(unsigned long,		caller_ip	)
+		__field(unsigned,		old_locks_want	)
+		__field(unsigned,		new_locks_want	)
+		__field(unsigned,		btree		)
+		TRACE_BPOS_entries(pos)
 	),
 
 	TP_fast_assign(
 		strscpy(__entry->trans_fn, trans->fn, sizeof(__entry->trans_fn));
 		__entry->caller_ip		= caller_ip;
+		__entry->old_locks_want		= old_locks_want;
+		__entry->new_locks_want		= path->locks_want;
+		__entry->btree			= path->btree_id;
+		TRACE_BPOS_assign(pos, path->pos);
 	),
 
-	TP_printk("%s %pS",
+	TP_printk("%s %pS locks_want %u -> %u %s %llu:%llu:%u",
 		  __entry->trans_fn,
-		  (void *) __entry->caller_ip)
+		  (void *) __entry->caller_ip,
+		  __entry->old_locks_want,
+		  __entry->new_locks_want,
+		  bch2_btree_id_str(__entry->btree),
+		  __entry->pos_inode,
+		  __entry->pos_offset,
+		  __entry->pos_snapshot)
 );
 
 DEFINE_EVENT(transaction_event,	trans_restart_write_buffer_flush,
@@ -1305,21 +1417,48 @@ TRACE_EVENT(write_buffer_flush,
 		  __entry->nr, __entry->size, __entry->skipped, __entry->fast)
 );
 
+TRACE_EVENT(write_buffer_flush_sync,
+	TP_PROTO(struct btree_trans *trans, unsigned long caller_ip),
+	TP_ARGS(trans, caller_ip),
+
+	TP_STRUCT__entry(
+		__array(char,			trans_fn, 32	)
+		__field(unsigned long,		caller_ip	)
+	),
+
+	TP_fast_assign(
+		strscpy(__entry->trans_fn, trans->fn, sizeof(__entry->trans_fn));
+		__entry->caller_ip		= caller_ip;
+	),
+
+	TP_printk("%s %pS", __entry->trans_fn, (void *) __entry->caller_ip)
+);
+
 TRACE_EVENT(write_buffer_flush_slowpath,
-	TP_PROTO(struct btree_trans *trans, size_t nr, size_t size),
-	TP_ARGS(trans, nr, size),
+	TP_PROTO(struct btree_trans *trans, size_t slowpath, size_t total),
+	TP_ARGS(trans, slowpath, total),
 
 	TP_STRUCT__entry(
-		__field(size_t,		nr		)
-		__field(size_t,		size		)
+		__field(size_t,		slowpath	)
+		__field(size_t,		total		)
 	),
 
 	TP_fast_assign(
-		__entry->nr	= nr;
-		__entry->size	= size;
+		__entry->slowpath	= slowpath;
+		__entry->total		= total;
 	),
 
-	TP_printk("%zu/%zu", __entry->nr, __entry->size)
+	TP_printk("%zu/%zu", __entry->slowpath, __entry->total)
+);
+
+DEFINE_EVENT(fs_str, rebalance_extent,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
+);
+
+DEFINE_EVENT(fs_str, data_update,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
 );
 
 #endif /* _TRACE_BCACHEFS_H */
diff --git a/fs/bcachefs/util.c b/fs/bcachefs/util.c
index 84b142fcc3df..c2ef7cddaa4f 100644
--- a/fs/bcachefs/util.c
+++ b/fs/bcachefs/util.c
@@ -267,7 +267,7 @@ void bch2_print_string_as_lines(const char *prefix, const char *lines)
 	console_unlock();
 }
 
-int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *task)
+int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *task, unsigned skipnr)
 {
 #ifdef CONFIG_STACKTRACE
 	unsigned nr_entries = 0;
@@ -282,7 +282,7 @@ int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *task)
 		return -1;
 
 	do {
-		nr_entries = stack_trace_save_tsk(task, stack->data, stack->size, 0);
+		nr_entries = stack_trace_save_tsk(task, stack->data, stack->size, skipnr + 1);
 	} while (nr_entries == stack->size &&
 		 !(ret = darray_make_room(stack, stack->size * 2)));
 
@@ -297,24 +297,74 @@ int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *task)
 
 void bch2_prt_backtrace(struct printbuf *out, bch_stacktrace *stack)
 {
-	unsigned long *i;
-
 	darray_for_each(*stack, i) {
 		prt_printf(out, "[<0>] %pB", (void *) *i);
 		prt_newline(out);
 	}
 }
 
-int bch2_prt_task_backtrace(struct printbuf *out, struct task_struct *task)
+int bch2_prt_task_backtrace(struct printbuf *out, struct task_struct *task, unsigned skipnr)
 {
 	bch_stacktrace stack = { 0 };
-	int ret = bch2_save_backtrace(&stack, task);
+	int ret = bch2_save_backtrace(&stack, task, skipnr + 1);
 
 	bch2_prt_backtrace(out, &stack);
 	darray_exit(&stack);
 	return ret;
 }
 
+#ifndef __KERNEL__
+#include <time.h>
+void bch2_prt_datetime(struct printbuf *out, time64_t sec)
+{
+	time_t t = sec;
+	char buf[64];
+	ctime_r(&t, buf);
+	strim(buf);
+	prt_str(out, buf);
+}
+#else
+void bch2_prt_datetime(struct printbuf *out, time64_t sec)
+{
+	char buf[64];
+	snprintf(buf, sizeof(buf), "%ptT", &sec);
+	prt_u64(out, sec);
+}
+#endif
+
+static const struct time_unit {
+	const char	*name;
+	u64		nsecs;
+} time_units[] = {
+	{ "ns",		1		 },
+	{ "us",		NSEC_PER_USEC	 },
+	{ "ms",		NSEC_PER_MSEC	 },
+	{ "s",		NSEC_PER_SEC	 },
+	{ "m",          (u64) NSEC_PER_SEC * 60},
+	{ "h",          (u64) NSEC_PER_SEC * 3600},
+	{ "eon",        U64_MAX          },
+};
+
+static const struct time_unit *pick_time_units(u64 ns)
+{
+	const struct time_unit *u;
+
+	for (u = time_units;
+	     u + 1 < time_units + ARRAY_SIZE(time_units) &&
+	     ns >= u[1].nsecs << 1;
+	     u++)
+		;
+
+	return u;
+}
+
+void bch2_pr_time_units(struct printbuf *out, u64 ns)
+{
+	const struct time_unit *u = pick_time_units(ns);
+
+	prt_printf(out, "%llu %s", div_u64(ns, u->nsecs), u->name);
+}
+
 /* time stats: */
 
 #ifndef CONFIG_BCACHEFS_NO_LATENCY_ACCT
@@ -359,6 +409,7 @@ static inline void bch2_time_stats_update_one(struct bch2_time_stats *stats,
 		mean_and_variance_weighted_update(&stats->duration_stats_weighted, duration);
 		stats->max_duration = max(stats->max_duration, duration);
 		stats->min_duration = min(stats->min_duration, duration);
+		stats->total_duration += duration;
 		bch2_quantiles_update(&stats->quantiles, duration);
 	}
 
@@ -372,29 +423,33 @@ static inline void bch2_time_stats_update_one(struct bch2_time_stats *stats,
 	}
 }
 
+static void __bch2_time_stats_clear_buffer(struct bch2_time_stats *stats,
+					   struct bch2_time_stat_buffer *b)
+{
+	for (struct bch2_time_stat_buffer_entry *i = b->entries;
+	     i < b->entries + ARRAY_SIZE(b->entries);
+	     i++)
+		bch2_time_stats_update_one(stats, i->start, i->end);
+	b->nr = 0;
+}
+
 static noinline void bch2_time_stats_clear_buffer(struct bch2_time_stats *stats,
 						  struct bch2_time_stat_buffer *b)
 {
-	struct bch2_time_stat_buffer_entry *i;
 	unsigned long flags;
 
 	spin_lock_irqsave(&stats->lock, flags);
-	for (i = b->entries;
-	     i < b->entries + ARRAY_SIZE(b->entries);
-	     i++)
-		bch2_time_stats_update_one(stats, i->start, i->end);
+	__bch2_time_stats_clear_buffer(stats, b);
 	spin_unlock_irqrestore(&stats->lock, flags);
-
-	b->nr = 0;
 }
 
 void __bch2_time_stats_update(struct bch2_time_stats *stats, u64 start, u64 end)
 {
 	unsigned long flags;
 
-	WARN_RATELIMIT(!stats->min_duration || !stats->min_freq,
-		       "time_stats: min_duration = %llu, min_freq = %llu",
-		       stats->min_duration, stats->min_freq);
+	WARN_ONCE(!stats->duration_stats_weighted.weight ||
+		  !stats->freq_stats_weighted.weight,
+		  "uninitialized time_stats");
 
 	if (!stats->buffer) {
 		spin_lock_irqsave(&stats->lock, flags);
@@ -423,40 +478,6 @@ void __bch2_time_stats_update(struct bch2_time_stats *stats, u64 start, u64 end)
 		preempt_enable();
 	}
 }
-#endif
-
-static const struct time_unit {
-	const char	*name;
-	u64		nsecs;
-} time_units[] = {
-	{ "ns",		1		 },
-	{ "us",		NSEC_PER_USEC	 },
-	{ "ms",		NSEC_PER_MSEC	 },
-	{ "s",		NSEC_PER_SEC	 },
-	{ "m",          (u64) NSEC_PER_SEC * 60},
-	{ "h",          (u64) NSEC_PER_SEC * 3600},
-	{ "eon",        U64_MAX          },
-};
-
-static const struct time_unit *pick_time_units(u64 ns)
-{
-	const struct time_unit *u;
-
-	for (u = time_units;
-	     u + 1 < time_units + ARRAY_SIZE(time_units) &&
-	     ns >= u[1].nsecs << 1;
-	     u++)
-		;
-
-	return u;
-}
-
-void bch2_pr_time_units(struct printbuf *out, u64 ns)
-{
-	const struct time_unit *u = pick_time_units(ns);
-
-	prt_printf(out, "%llu %s", div_u64(ns, u->nsecs), u->name);
-}
 
 static void bch2_pr_time_units_aligned(struct printbuf *out, u64 ns)
 {
@@ -467,26 +488,6 @@ static void bch2_pr_time_units_aligned(struct printbuf *out, u64 ns)
 	prt_printf(out, "%s", u->name);
 }
 
-#ifndef __KERNEL__
-#include <time.h>
-void bch2_prt_datetime(struct printbuf *out, time64_t sec)
-{
-	time_t t = sec;
-	char buf[64];
-	ctime_r(&t, buf);
-	prt_str(out, buf);
-}
-#else
-void bch2_prt_datetime(struct printbuf *out, time64_t sec)
-{
-	char buf[64];
-	snprintf(buf, sizeof(buf), "%ptT", &sec);
-	prt_u64(out, sec);
-}
-#endif
-
-#define TABSTOP_SIZE 12
-
 static inline void pr_name_and_units(struct printbuf *out, const char *name, u64 ns)
 {
 	prt_str(out, name);
@@ -495,12 +496,24 @@ static inline void pr_name_and_units(struct printbuf *out, const char *name, u64
 	prt_newline(out);
 }
 
+#define TABSTOP_SIZE 12
+
 void bch2_time_stats_to_text(struct printbuf *out, struct bch2_time_stats *stats)
 {
 	const struct time_unit *u;
 	s64 f_mean = 0, d_mean = 0;
 	u64 q, last_q = 0, f_stddev = 0, d_stddev = 0;
 	int i;
+
+	if (stats->buffer) {
+		int cpu;
+
+		spin_lock_irq(&stats->lock);
+		for_each_possible_cpu(cpu)
+			__bch2_time_stats_clear_buffer(stats, per_cpu_ptr(stats->buffer, cpu));
+		spin_unlock_irq(&stats->lock);
+	}
+
 	/*
 	 * avoid divide by zero
 	 */
@@ -546,6 +559,7 @@ void bch2_time_stats_to_text(struct printbuf *out, struct bch2_time_stats *stats
 
 	pr_name_and_units(out, "min:", stats->min_duration);
 	pr_name_and_units(out, "max:", stats->max_duration);
+	pr_name_and_units(out, "total:", stats->total_duration);
 
 	prt_printf(out, "mean:");
 	prt_tab(out);
@@ -603,6 +617,9 @@ void bch2_time_stats_to_text(struct printbuf *out, struct bch2_time_stats *stats
 		last_q = q;
 	}
 }
+#else
+void bch2_time_stats_to_text(struct printbuf *out, struct bch2_time_stats *stats) {}
+#endif
 
 void bch2_time_stats_exit(struct bch2_time_stats *stats)
 {
@@ -1157,3 +1174,37 @@ u64 *bch2_acc_percpu_u64s(u64 __percpu *p, unsigned nr)
 
 	return ret;
 }
+
+void bch2_darray_str_exit(darray_str *d)
+{
+	darray_for_each(*d, i)
+		kfree(*i);
+	darray_exit(d);
+}
+
+int bch2_split_devs(const char *_dev_name, darray_str *ret)
+{
+	darray_init(ret);
+
+	char *dev_name = kstrdup(_dev_name, GFP_KERNEL), *s = dev_name;
+	if (!dev_name)
+		return -ENOMEM;
+
+	while ((s = strsep(&dev_name, ":"))) {
+		char *p = kstrdup(s, GFP_KERNEL);
+		if (!p)
+			goto err;
+
+		if (darray_push(ret, p)) {
+			kfree(p);
+			goto err;
+		}
+	}
+
+	kfree(dev_name);
+	return 0;
+err:
+	bch2_darray_str_exit(ret);
+	kfree(dev_name);
+	return -ENOMEM;
+}
diff --git a/fs/bcachefs/util.h b/fs/bcachefs/util.h
index 2984b57b2958..c75fc31915d3 100644
--- a/fs/bcachefs/util.h
+++ b/fs/bcachefs/util.h
@@ -243,6 +243,7 @@ do {									\
 #define prt_units_s64(...)		bch2_prt_units_s64(__VA_ARGS__)
 #define prt_string_option(...)		bch2_prt_string_option(__VA_ARGS__)
 #define prt_bitflags(...)		bch2_prt_bitflags(__VA_ARGS__)
+#define prt_bitflags_vector(...)	bch2_prt_bitflags_vector(__VA_ARGS__)
 
 void bch2_pr_time_units(struct printbuf *, u64);
 void bch2_prt_datetime(struct printbuf *, time64_t);
@@ -346,9 +347,18 @@ void bch2_prt_u64_binary(struct printbuf *, u64, unsigned);
 void bch2_print_string_as_lines(const char *prefix, const char *lines);
 
 typedef DARRAY(unsigned long) bch_stacktrace;
-int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *);
+int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *, unsigned);
 void bch2_prt_backtrace(struct printbuf *, bch_stacktrace *);
-int bch2_prt_task_backtrace(struct printbuf *, struct task_struct *);
+int bch2_prt_task_backtrace(struct printbuf *, struct task_struct *, unsigned);
+
+static inline void prt_bdevname(struct printbuf *out, struct block_device *bdev)
+{
+#ifdef __KERNEL__
+	prt_printf(out, "%pg", bdev);
+#else
+	prt_str(out, bdev->name);
+#endif
+}
 
 #define NR_QUANTILES	15
 #define QUANTILE_IDX(i)	inorder_to_eytzinger0(i, NR_QUANTILES)
@@ -373,8 +383,9 @@ struct bch2_time_stat_buffer {
 struct bch2_time_stats {
 	spinlock_t	lock;
 	/* all fields are in nanoseconds */
-	u64		max_duration;
 	u64             min_duration;
+	u64		max_duration;
+	u64		total_duration;
 	u64             max_freq;
 	u64             min_freq;
 	u64		last_event;
@@ -389,15 +400,39 @@ struct bch2_time_stats {
 
 #ifndef CONFIG_BCACHEFS_NO_LATENCY_ACCT
 void __bch2_time_stats_update(struct bch2_time_stats *stats, u64, u64);
-#else
-static inline void __bch2_time_stats_update(struct bch2_time_stats *stats, u64 start, u64 end) {}
-#endif
 
 static inline void bch2_time_stats_update(struct bch2_time_stats *stats, u64 start)
 {
 	__bch2_time_stats_update(stats, start, local_clock());
 }
 
+static inline bool track_event_change(struct bch2_time_stats *stats,
+				      u64 *start, bool v)
+{
+	if (v != !!*start) {
+		if (!v) {
+			bch2_time_stats_update(stats, *start);
+			*start = 0;
+		} else {
+			*start = local_clock() ?: 1;
+			return true;
+		}
+	}
+
+	return false;
+}
+#else
+static inline void __bch2_time_stats_update(struct bch2_time_stats *stats, u64 start, u64 end) {}
+static inline void bch2_time_stats_update(struct bch2_time_stats *stats, u64 start) {}
+static inline bool track_event_change(struct bch2_time_stats *stats,
+				      u64 *start, bool v)
+{
+	bool ret = v && !*start;
+	*start = v;
+	return ret;
+}
+#endif
+
 void bch2_time_stats_to_text(struct printbuf *, struct bch2_time_stats *);
 
 void bch2_time_stats_exit(struct bch2_time_stats *);
@@ -830,4 +865,14 @@ static inline int cmp_le32(__le32 l, __le32 r)
 
 #include <linux/uuid.h>
 
+#define QSTR(n) { { { .len = strlen(n) } }, .name = n }
+
+static inline bool qstr_eq(const struct qstr l, const struct qstr r)
+{
+	return l.len == r.len && !memcmp(l.name, r.name, l.len);
+}
+
+void bch2_darray_str_exit(darray_str *);
+int bch2_split_devs(const char *, darray_str *);
+
 #endif /* _BCACHEFS_UTIL_H */
diff --git a/fs/bcachefs/vstructs.h b/fs/bcachefs/vstructs.h
index a6561b4b36a6..2ad338e282da 100644
--- a/fs/bcachefs/vstructs.h
+++ b/fs/bcachefs/vstructs.h
@@ -48,14 +48,14 @@
 	((void *)			((u64 *) (_s)->_data + __vstruct_u64s(_s)))
 
 #define vstruct_for_each(_s, _i)					\
-	for (_i = (_s)->start;						\
+	for (typeof(&(_s)->start[0]) _i = (_s)->start;			\
 	     _i < vstruct_last(_s);					\
 	     _i = vstruct_next(_i))
 
-#define vstruct_for_each_safe(_s, _i, _t)				\
-	for (_i = (_s)->start;						\
-	     _i < vstruct_last(_s) && (_t = vstruct_next(_i), true);	\
-	     _i = _t)
+#define vstruct_for_each_safe(_s, _i)					\
+	for (typeof(&(_s)->start[0]) _next, _i = (_s)->start;		\
+	     _i < vstruct_last(_s) && (_next = vstruct_next(_i), true);	\
+	     _i = _next)
 
 #define vstruct_idx(_s, _idx)						\
 	((typeof(&(_s)->start[0])) ((_s)->_data + (_idx)))
diff --git a/fs/bcachefs/xattr.c b/fs/bcachefs/xattr.c
index a39ff0c296ec..5a1858fb9879 100644
--- a/fs/bcachefs/xattr.c
+++ b/fs/bcachefs/xattr.c
@@ -176,7 +176,8 @@ int bch2_xattr_set(struct btree_trans *trans, subvol_inum inum,
 	struct btree_iter inode_iter = { NULL };
 	int ret;
 
-	ret = bch2_inode_peek(trans, &inode_iter, inode_u, inum, BTREE_ITER_INTENT);
+	ret   = bch2_subvol_is_ro_trans(trans, inum.subvol) ?:
+		bch2_inode_peek(trans, &inode_iter, inode_u, inum, BTREE_ITER_INTENT);
 	if (ret)
 		return ret;
 
@@ -552,6 +553,14 @@ static int bch2_xattr_bcachefs_set(const struct xattr_handler *handler,
 		s.v = v + 1;
 		s.defined = true;
 	} else {
+		/*
+		 * Check if this option was set on the parent - if so, switched
+		 * back to inheriting from the parent:
+		 *
+		 * rename() also has to deal with keeping inherited options up
+		 * to date - see bch2_reinherit_attrs()
+		 */
+		spin_lock(&dentry->d_lock);
 		if (!IS_ROOT(dentry)) {
 			struct bch_inode_info *dir =
 				to_bch_ei(d_inode(dentry->d_parent));
@@ -560,6 +569,7 @@ static int bch2_xattr_bcachefs_set(const struct xattr_handler *handler,
 		} else {
 			s.v = 0;
 		}
+		spin_unlock(&dentry->d_lock);
 
 		s.defined = false;
 	}
diff --git a/fs/bfs/file.c b/fs/bfs/file.c
index adc2230079c6..a778411574a9 100644
--- a/fs/bfs/file.c
+++ b/fs/bfs/file.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/fs.h>
+#include <linux/mpage.h>
 #include <linux/buffer_head.h>
 #include "bfs.h"
 
@@ -150,9 +151,10 @@ out:
 	return err;
 }
 
-static int bfs_writepage(struct page *page, struct writeback_control *wbc)
+static int bfs_writepages(struct address_space *mapping,
+		struct writeback_control *wbc)
 {
-	return block_write_full_page(page, bfs_get_block, wbc);
+	return mpage_writepages(mapping, wbc, bfs_get_block);
 }
 
 static int bfs_read_folio(struct file *file, struct folio *folio)
@@ -190,9 +192,10 @@ const struct address_space_operations bfs_aops = {
 	.dirty_folio	= block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
 	.read_folio	= bfs_read_folio,
-	.writepage	= bfs_writepage,
+	.writepages	= bfs_writepages,
 	.write_begin	= bfs_write_begin,
 	.write_end	= generic_write_end,
+	.migrate_folio	= buffer_migrate_folio,
 	.bmap		= bfs_bmap,
 };
 
diff --git a/fs/btrfs/accessors.c b/fs/btrfs/accessors.c
index 206cf1612c1d..1925a0919ca6 100644
--- a/fs/btrfs/accessors.c
+++ b/fs/btrfs/accessors.c
@@ -27,7 +27,7 @@ static bool check_setget_bounds(const struct extent_buffer *eb,
 void btrfs_init_map_token(struct btrfs_map_token *token, struct extent_buffer *eb)
 {
 	token->eb = eb;
-	token->kaddr = page_address(eb->pages[0]);
+	token->kaddr = folio_address(eb->folios[0]);
 	token->offset = 0;
 }
 
@@ -50,7 +50,7 @@ void btrfs_init_map_token(struct btrfs_map_token *token, struct extent_buffer *e
  * an offset into the extent buffer page array, cast to a specific type.  This
  * gives us all the type checking.
  *
- * The extent buffer pages stored in the array pages do not form a contiguous
+ * The extent buffer pages stored in the array folios may not form a contiguous
  * phyusical range, but the API functions assume the linear offset to the range
  * from 0 to metadata node size.
  */
@@ -60,28 +60,30 @@ u##bits btrfs_get_token_##bits(struct btrfs_map_token *token,		\
 			       const void *ptr, unsigned long off)	\
 {									\
 	const unsigned long member_offset = (unsigned long)ptr + off;	\
-	const unsigned long idx = get_eb_page_index(member_offset);	\
-	const unsigned long oip = get_eb_offset_in_page(token->eb,	\
-							member_offset);	\
+	const unsigned long idx = get_eb_folio_index(token->eb, member_offset); \
+	const unsigned long oil = get_eb_offset_in_folio(token->eb,	\
+							 member_offset);\
+	const int unit_size = folio_size(token->eb->folios[0]);		\
+	const int unit_shift = folio_shift(token->eb->folios[0]);	\
 	const int size = sizeof(u##bits);				\
 	u8 lebytes[sizeof(u##bits)];					\
-	const int part = PAGE_SIZE - oip;				\
+	const int part = unit_size - oil;				\
 									\
 	ASSERT(token);							\
 	ASSERT(token->kaddr);						\
 	ASSERT(check_setget_bounds(token->eb, ptr, off, size));		\
 	if (token->offset <= member_offset &&				\
-	    member_offset + size <= token->offset + PAGE_SIZE) {	\
-		return get_unaligned_le##bits(token->kaddr + oip);	\
+	    member_offset + size <= token->offset + unit_size) {	\
+		return get_unaligned_le##bits(token->kaddr + oil);	\
 	}								\
-	token->kaddr = page_address(token->eb->pages[idx]);		\
-	token->offset = idx << PAGE_SHIFT;				\
-	if (INLINE_EXTENT_BUFFER_PAGES == 1 || oip + size <= PAGE_SIZE ) \
-		return get_unaligned_le##bits(token->kaddr + oip);	\
+	token->kaddr = folio_address(token->eb->folios[idx]);		\
+	token->offset = idx << unit_shift;				\
+	if (INLINE_EXTENT_BUFFER_PAGES == 1 || oil + size <= unit_size) \
+		return get_unaligned_le##bits(token->kaddr + oil);	\
 									\
-	memcpy(lebytes, token->kaddr + oip, part);			\
-	token->kaddr = page_address(token->eb->pages[idx + 1]);		\
-	token->offset = (idx + 1) << PAGE_SHIFT;			\
+	memcpy(lebytes, token->kaddr + oil, part);			\
+	token->kaddr = folio_address(token->eb->folios[idx + 1]);	\
+	token->offset = (idx + 1) << unit_shift;			\
 	memcpy(lebytes + part, token->kaddr, size - part);		\
 	return get_unaligned_le##bits(lebytes);				\
 }									\
@@ -89,19 +91,21 @@ u##bits btrfs_get_##bits(const struct extent_buffer *eb,		\
 			 const void *ptr, unsigned long off)		\
 {									\
 	const unsigned long member_offset = (unsigned long)ptr + off;	\
-	const unsigned long oip = get_eb_offset_in_page(eb, member_offset); \
-	const unsigned long idx = get_eb_page_index(member_offset);	\
-	char *kaddr = page_address(eb->pages[idx]);			\
+	const unsigned long idx = get_eb_folio_index(eb, member_offset);\
+	const unsigned long oil = get_eb_offset_in_folio(eb,		\
+							 member_offset);\
+	const int unit_size = folio_size(eb->folios[0]);		\
+	char *kaddr = folio_address(eb->folios[idx]);			\
 	const int size = sizeof(u##bits);				\
-	const int part = PAGE_SIZE - oip;				\
+	const int part = unit_size - oil;				\
 	u8 lebytes[sizeof(u##bits)];					\
 									\
 	ASSERT(check_setget_bounds(eb, ptr, off, size));		\
-	if (INLINE_EXTENT_BUFFER_PAGES == 1 || oip + size <= PAGE_SIZE)	\
-		return get_unaligned_le##bits(kaddr + oip);		\
+	if (INLINE_EXTENT_BUFFER_PAGES == 1 || oil + size <= unit_size)	\
+		return get_unaligned_le##bits(kaddr + oil);		\
 									\
-	memcpy(lebytes, kaddr + oip, part);				\
-	kaddr = page_address(eb->pages[idx + 1]);			\
+	memcpy(lebytes, kaddr + oil, part);				\
+	kaddr = folio_address(eb->folios[idx + 1]);			\
 	memcpy(lebytes + part, kaddr, size - part);			\
 	return get_unaligned_le##bits(lebytes);				\
 }									\
@@ -110,53 +114,59 @@ void btrfs_set_token_##bits(struct btrfs_map_token *token,		\
 			    u##bits val)				\
 {									\
 	const unsigned long member_offset = (unsigned long)ptr + off;	\
-	const unsigned long idx = get_eb_page_index(member_offset);	\
-	const unsigned long oip = get_eb_offset_in_page(token->eb,	\
-							member_offset);	\
+	const unsigned long idx = get_eb_folio_index(token->eb, member_offset); \
+	const unsigned long oil = get_eb_offset_in_folio(token->eb,	\
+							 member_offset);\
+	const int unit_size = folio_size(token->eb->folios[0]);		\
+	const int unit_shift = folio_shift(token->eb->folios[0]);	\
 	const int size = sizeof(u##bits);				\
 	u8 lebytes[sizeof(u##bits)];					\
-	const int part = PAGE_SIZE - oip;				\
+	const int part = unit_size - oil;				\
 									\
 	ASSERT(token);							\
 	ASSERT(token->kaddr);						\
 	ASSERT(check_setget_bounds(token->eb, ptr, off, size));		\
 	if (token->offset <= member_offset &&				\
-	    member_offset + size <= token->offset + PAGE_SIZE) {	\
-		put_unaligned_le##bits(val, token->kaddr + oip);	\
+	    member_offset + size <= token->offset + unit_size) {	\
+		put_unaligned_le##bits(val, token->kaddr + oil);	\
 		return;							\
 	}								\
-	token->kaddr = page_address(token->eb->pages[idx]);		\
-	token->offset = idx << PAGE_SHIFT;				\
-	if (INLINE_EXTENT_BUFFER_PAGES == 1 || oip + size <= PAGE_SIZE) { \
-		put_unaligned_le##bits(val, token->kaddr + oip);	\
+	token->kaddr = folio_address(token->eb->folios[idx]);		\
+	token->offset = idx << unit_shift;				\
+	if (INLINE_EXTENT_BUFFER_PAGES == 1 ||				\
+	    oil + size <= unit_size) {					\
+		put_unaligned_le##bits(val, token->kaddr + oil);	\
 		return;							\
 	}								\
 	put_unaligned_le##bits(val, lebytes);				\
-	memcpy(token->kaddr + oip, lebytes, part);			\
-	token->kaddr = page_address(token->eb->pages[idx + 1]);		\
-	token->offset = (idx + 1) << PAGE_SHIFT;			\
+	memcpy(token->kaddr + oil, lebytes, part);			\
+	token->kaddr = folio_address(token->eb->folios[idx + 1]);	\
+	token->offset = (idx + 1) << unit_shift;			\
 	memcpy(token->kaddr, lebytes + part, size - part);		\
 }									\
 void btrfs_set_##bits(const struct extent_buffer *eb, void *ptr,	\
 		      unsigned long off, u##bits val)			\
 {									\
 	const unsigned long member_offset = (unsigned long)ptr + off;	\
-	const unsigned long oip = get_eb_offset_in_page(eb, member_offset); \
-	const unsigned long idx = get_eb_page_index(member_offset);	\
-	char *kaddr = page_address(eb->pages[idx]);			\
+	const unsigned long idx = get_eb_folio_index(eb, member_offset);\
+	const unsigned long oil = get_eb_offset_in_folio(eb,		\
+							 member_offset);\
+	const int unit_size = folio_size(eb->folios[0]);		\
+	char *kaddr = folio_address(eb->folios[idx]);			\
 	const int size = sizeof(u##bits);				\
-	const int part = PAGE_SIZE - oip;				\
+	const int part = unit_size - oil;				\
 	u8 lebytes[sizeof(u##bits)];					\
 									\
 	ASSERT(check_setget_bounds(eb, ptr, off, size));		\
-	if (INLINE_EXTENT_BUFFER_PAGES == 1 || oip + size <= PAGE_SIZE) { \
-		put_unaligned_le##bits(val, kaddr + oip);		\
+	if (INLINE_EXTENT_BUFFER_PAGES == 1 ||				\
+	    oil + size <= unit_size) {					\
+		put_unaligned_le##bits(val, kaddr + oil);		\
 		return;							\
 	}								\
 									\
 	put_unaligned_le##bits(val, lebytes);				\
-	memcpy(kaddr + oip, lebytes, part);				\
-	kaddr = page_address(eb->pages[idx + 1]);			\
+	memcpy(kaddr + oil, lebytes, part);				\
+	kaddr = folio_address(eb->folios[idx + 1]);			\
 	memcpy(kaddr, lebytes + part, size - part);			\
 }
 
diff --git a/fs/btrfs/accessors.h b/fs/btrfs/accessors.h
index aa0844535644..ed7aa32972ad 100644
--- a/fs/btrfs/accessors.h
+++ b/fs/btrfs/accessors.h
@@ -90,14 +90,14 @@ static inline void btrfs_set_token_##name(struct btrfs_map_token *token,\
 #define BTRFS_SETGET_HEADER_FUNCS(name, type, member, bits)		\
 static inline u##bits btrfs_##name(const struct extent_buffer *eb)	\
 {									\
-	const type *p = page_address(eb->pages[0]) +			\
+	const type *p = folio_address(eb->folios[0]) +			\
 			offset_in_page(eb->start);			\
 	return get_unaligned_le##bits(&p->member);			\
 }									\
 static inline void btrfs_set_##name(const struct extent_buffer *eb,	\
 				    u##bits val)			\
 {									\
-	type *p = page_address(eb->pages[0]) + offset_in_page(eb->start); \
+	type *p = folio_address(eb->folios[0]) + offset_in_page(eb->start); \
 	put_unaligned_le##bits(val, &p->member);			\
 }
 
diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index 4f3b693a16b1..928f512cdb4a 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -194,6 +194,12 @@ static void btrfs_end_repair_bio(struct btrfs_bio *repair_bbio,
 	struct bio_vec *bv = bio_first_bvec_all(&repair_bbio->bio);
 	int mirror = repair_bbio->mirror_num;
 
+	/*
+	 * We can only trigger this for data bio, which doesn't support larger
+	 * folios yet.
+	 */
+	ASSERT(folio_order(page_folio(bv->bv_page)) == 0);
+
 	if (repair_bbio->bio.bi_status ||
 	    !btrfs_data_csum_ok(repair_bbio, dev, 0, bv)) {
 		bio_reset(&repair_bbio->bio, NULL, REQ_OP_READ);
@@ -215,7 +221,7 @@ static void btrfs_end_repair_bio(struct btrfs_bio *repair_bbio,
 		btrfs_repair_io_failure(fs_info, btrfs_ino(inode),
 				  repair_bbio->file_offset, fs_info->sectorsize,
 				  repair_bbio->saved_iter.bi_sector << SECTOR_SHIFT,
-				  bv->bv_page, bv->bv_offset, mirror);
+				  page_folio(bv->bv_page), bv->bv_offset, mirror);
 	} while (mirror != fbio->bbio->mirror_num);
 
 done:
@@ -626,7 +632,7 @@ static bool should_async_write(struct btrfs_bio *bbio)
 /*
  * Submit bio to an async queue.
  *
- * Return true if the work has been succesfuly submitted, else false.
+ * Return true if the work has been successfully submitted, else false.
  */
 static bool btrfs_wq_submit_bio(struct btrfs_bio *bbio,
 				struct btrfs_io_context *bioc,
@@ -767,8 +773,8 @@ void btrfs_submit_bio(struct btrfs_bio *bbio, int mirror_num)
  * freeing the bio.
  */
 int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
-			    u64 length, u64 logical, struct page *page,
-			    unsigned int pg_offset, int mirror_num)
+			    u64 length, u64 logical, struct folio *folio,
+			    unsigned int folio_offset, int mirror_num)
 {
 	struct btrfs_io_stripe smap = { 0 };
 	struct bio_vec bvec;
@@ -799,7 +805,8 @@ int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
 
 	bio_init(&bio, smap.dev->bdev, &bvec, 1, REQ_OP_WRITE | REQ_SYNC);
 	bio.bi_iter.bi_sector = smap.physical >> SECTOR_SHIFT;
-	__bio_add_page(&bio, page, length, pg_offset);
+	ret = bio_add_folio(&bio, folio, length, folio_offset);
+	ASSERT(ret);
 	ret = submit_bio_wait(&bio);
 	if (ret) {
 		/* try to remap that extent elsewhere? */
diff --git a/fs/btrfs/bio.h b/fs/btrfs/bio.h
index ca79decee060..bbaed317161a 100644
--- a/fs/btrfs/bio.h
+++ b/fs/btrfs/bio.h
@@ -105,7 +105,7 @@ void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status);
 void btrfs_submit_bio(struct btrfs_bio *bbio, int mirror_num);
 void btrfs_submit_repair_write(struct btrfs_bio *bbio, int mirror_num, bool dev_replace);
 int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
-			    u64 length, u64 logical, struct page *page,
-			    unsigned int pg_offset, int mirror_num);
+			    u64 length, u64 logical, struct folio *folio,
+			    unsigned int folio_offset, int mirror_num);
 
 #endif
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 6e5dc68ff661..a9be9ac99222 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -168,7 +168,7 @@ void btrfs_put_block_group(struct btrfs_block_group *cache)
 						  cache);
 
 		kfree(cache->free_space_ctl);
-		kfree(cache->physical_map);
+		btrfs_free_chunk_map(cache->physical_map);
 		kfree(cache);
 	}
 }
@@ -1047,7 +1047,7 @@ static int remove_block_group_item(struct btrfs_trans_handle *trans,
 }
 
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
-			     u64 group_start, struct extent_map *em)
+			     struct btrfs_chunk_map *map)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_path *path;
@@ -1059,10 +1059,10 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	int index;
 	int factor;
 	struct btrfs_caching_control *caching_ctl = NULL;
-	bool remove_em;
+	bool remove_map;
 	bool remove_rsv = false;
 
-	block_group = btrfs_lookup_block_group(fs_info, group_start);
+	block_group = btrfs_lookup_block_group(fs_info, map->start);
 	BUG_ON(!block_group);
 	BUG_ON(!block_group->ro);
 
@@ -1252,7 +1252,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	 * entries because we already removed them all when we called
 	 * btrfs_remove_free_space_cache().
 	 *
-	 * And we must not remove the extent map from the fs_info->mapping_tree
+	 * And we must not remove the chunk map from the fs_info->mapping_tree
 	 * to prevent the same logical address range and physical device space
 	 * ranges from being reused for a new block group. This is needed to
 	 * avoid races with trimming and scrub.
@@ -1268,19 +1268,11 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	 * in place until the extents have been discarded completely when
 	 * the transaction commit has completed.
 	 */
-	remove_em = (atomic_read(&block_group->frozen) == 0);
+	remove_map = (atomic_read(&block_group->frozen) == 0);
 	spin_unlock(&block_group->lock);
 
-	if (remove_em) {
-		struct extent_map_tree *em_tree;
-
-		em_tree = &fs_info->mapping_tree;
-		write_lock(&em_tree->lock);
-		remove_extent_mapping(em_tree, em);
-		write_unlock(&em_tree->lock);
-		/* once for the tree */
-		free_extent_map(em);
-	}
+	if (remove_map)
+		btrfs_remove_chunk_map(fs_info, map);
 
 out:
 	/* Once for the lookup reference */
@@ -1295,15 +1287,12 @@ struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
 		struct btrfs_fs_info *fs_info, const u64 chunk_offset)
 {
 	struct btrfs_root *root = btrfs_block_group_root(fs_info);
-	struct extent_map_tree *em_tree = &fs_info->mapping_tree;
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	unsigned int num_items;
 
-	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, chunk_offset, 1);
-	read_unlock(&em_tree->lock);
-	ASSERT(em && em->start == chunk_offset);
+	map = btrfs_find_chunk_map(fs_info, chunk_offset, 1);
+	ASSERT(map != NULL);
+	ASSERT(map->start == chunk_offset);
 
 	/*
 	 * We need to reserve 3 + N units from the metadata space info in order
@@ -1324,9 +1313,8 @@ struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
 	 * more device items and remove one chunk item), but this is done at
 	 * btrfs_remove_chunk() through a call to check_system_chunk().
 	 */
-	map = em->map_lookup;
 	num_items = 3 + map->num_stripes;
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 
 	return btrfs_start_transaction_fallback_global_rsv(root, num_items);
 }
@@ -1927,8 +1915,7 @@ void btrfs_mark_bg_to_reclaim(struct btrfs_block_group *bg)
 static int read_bg_from_eb(struct btrfs_fs_info *fs_info, struct btrfs_key *key,
 			   struct btrfs_path *path)
 {
-	struct extent_map_tree *em_tree;
-	struct extent_map *em;
+	struct btrfs_chunk_map *map;
 	struct btrfs_block_group_item bg;
 	struct extent_buffer *leaf;
 	int slot;
@@ -1938,23 +1925,20 @@ static int read_bg_from_eb(struct btrfs_fs_info *fs_info, struct btrfs_key *key,
 	slot = path->slots[0];
 	leaf = path->nodes[0];
 
-	em_tree = &fs_info->mapping_tree;
-	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, key->objectid, key->offset);
-	read_unlock(&em_tree->lock);
-	if (!em) {
+	map = btrfs_find_chunk_map(fs_info, key->objectid, key->offset);
+	if (!map) {
 		btrfs_err(fs_info,
 			  "logical %llu len %llu found bg but no related chunk",
 			  key->objectid, key->offset);
 		return -ENOENT;
 	}
 
-	if (em->start != key->objectid || em->len != key->offset) {
+	if (map->start != key->objectid || map->chunk_len != key->offset) {
 		btrfs_err(fs_info,
 			"block group %llu len %llu mismatch with chunk %llu len %llu",
-			key->objectid, key->offset, em->start, em->len);
+			  key->objectid, key->offset, map->start, map->chunk_len);
 		ret = -EUCLEAN;
-		goto out_free_em;
+		goto out_free_map;
 	}
 
 	read_extent_buffer(leaf, &bg, btrfs_item_ptr_offset(leaf, slot),
@@ -1962,16 +1946,16 @@ static int read_bg_from_eb(struct btrfs_fs_info *fs_info, struct btrfs_key *key,
 	flags = btrfs_stack_block_group_flags(&bg) &
 		BTRFS_BLOCK_GROUP_TYPE_MASK;
 
-	if (flags != (em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
+	if (flags != (map->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
 		btrfs_err(fs_info,
 "block group %llu len %llu type flags 0x%llx mismatch with chunk type flags 0x%llx",
 			  key->objectid, key->offset, flags,
-			  (BTRFS_BLOCK_GROUP_TYPE_MASK & em->map_lookup->type));
+			  (BTRFS_BLOCK_GROUP_TYPE_MASK & map->type));
 		ret = -EUCLEAN;
 	}
 
-out_free_em:
-	free_extent_map(em);
+out_free_map:
+	btrfs_free_chunk_map(map);
 	return ret;
 }
 
@@ -2024,8 +2008,7 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
 int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
 		     u64 physical, u64 **logical, int *naddrs, int *stripe_len)
 {
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	u64 *buf;
 	u64 bytenr;
 	u64 data_stripe_length;
@@ -2033,14 +2016,13 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
 	int i, nr = 0;
 	int ret = 0;
 
-	em = btrfs_get_chunk_map(fs_info, chunk_start, 1);
-	if (IS_ERR(em))
+	map = btrfs_get_chunk_map(fs_info, chunk_start, 1);
+	if (IS_ERR(map))
 		return -EIO;
 
-	map = em->map_lookup;
-	data_stripe_length = em->orig_block_len;
+	data_stripe_length = map->stripe_size;
 	io_stripe_size = BTRFS_STRIPE_LEN;
-	chunk_start = em->start;
+	chunk_start = map->start;
 
 	/* For RAID5/6 adjust to a full IO stripe length */
 	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
@@ -2094,7 +2076,7 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
 	*naddrs = nr;
 	*stripe_len = io_stripe_size;
 out:
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 	return ret;
 }
 
@@ -2199,49 +2181,47 @@ static struct btrfs_block_group *btrfs_create_block_group_cache(
  */
 static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
 {
-	struct extent_map_tree *map_tree = &fs_info->mapping_tree;
-	struct extent_map *em;
-	struct btrfs_block_group *bg;
 	u64 start = 0;
 	int ret = 0;
 
 	while (1) {
-		read_lock(&map_tree->lock);
+		struct btrfs_chunk_map *map;
+		struct btrfs_block_group *bg;
+
 		/*
-		 * lookup_extent_mapping will return the first extent map
-		 * intersecting the range, so setting @len to 1 is enough to
+		 * btrfs_find_chunk_map() will return the first chunk map
+		 * intersecting the range, so setting @length to 1 is enough to
 		 * get the first chunk.
 		 */
-		em = lookup_extent_mapping(map_tree, start, 1);
-		read_unlock(&map_tree->lock);
-		if (!em)
+		map = btrfs_find_chunk_map(fs_info, start, 1);
+		if (!map)
 			break;
 
-		bg = btrfs_lookup_block_group(fs_info, em->start);
+		bg = btrfs_lookup_block_group(fs_info, map->start);
 		if (!bg) {
 			btrfs_err(fs_info,
 	"chunk start=%llu len=%llu doesn't have corresponding block group",
-				     em->start, em->len);
+				     map->start, map->chunk_len);
 			ret = -EUCLEAN;
-			free_extent_map(em);
+			btrfs_free_chunk_map(map);
 			break;
 		}
-		if (bg->start != em->start || bg->length != em->len ||
+		if (bg->start != map->start || bg->length != map->chunk_len ||
 		    (bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK) !=
-		    (em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
+		    (map->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
 			btrfs_err(fs_info,
 "chunk start=%llu len=%llu flags=0x%llx doesn't match block group start=%llu len=%llu flags=0x%llx",
-				em->start, em->len,
-				em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK,
+				map->start, map->chunk_len,
+				map->type & BTRFS_BLOCK_GROUP_TYPE_MASK,
 				bg->start, bg->length,
 				bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK);
 			ret = -EUCLEAN;
-			free_extent_map(em);
+			btrfs_free_chunk_map(map);
 			btrfs_put_block_group(bg);
 			break;
 		}
-		start = em->start + em->len;
-		free_extent_map(em);
+		start = map->start + map->chunk_len;
+		btrfs_free_chunk_map(map);
 		btrfs_put_block_group(bg);
 	}
 	return ret;
@@ -2369,28 +2349,25 @@ error:
 
 static int fill_dummy_bgs(struct btrfs_fs_info *fs_info)
 {
-	struct extent_map_tree *em_tree = &fs_info->mapping_tree;
 	struct rb_node *node;
 	int ret = 0;
 
-	for (node = rb_first_cached(&em_tree->map); node; node = rb_next(node)) {
-		struct extent_map *em;
-		struct map_lookup *map;
+	for (node = rb_first_cached(&fs_info->mapping_tree); node; node = rb_next(node)) {
+		struct btrfs_chunk_map *map;
 		struct btrfs_block_group *bg;
 
-		em = rb_entry(node, struct extent_map, rb_node);
-		map = em->map_lookup;
-		bg = btrfs_create_block_group_cache(fs_info, em->start);
+		map = rb_entry(node, struct btrfs_chunk_map, rb_node);
+		bg = btrfs_create_block_group_cache(fs_info, map->start);
 		if (!bg) {
 			ret = -ENOMEM;
 			break;
 		}
 
 		/* Fill dummy cache as FULL */
-		bg->length = em->len;
+		bg->length = map->chunk_len;
 		bg->flags = map->type;
 		bg->cached = BTRFS_CACHE_FINISHED;
-		bg->used = em->len;
+		bg->used = map->chunk_len;
 		bg->flags = map->type;
 		ret = btrfs_add_block_group_cache(fs_info, bg);
 		/*
@@ -2618,19 +2595,14 @@ static int insert_dev_extents(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_device *device;
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	u64 dev_offset;
-	u64 stripe_size;
 	int i;
 	int ret = 0;
 
-	em = btrfs_get_chunk_map(fs_info, chunk_offset, chunk_size);
-	if (IS_ERR(em))
-		return PTR_ERR(em);
-
-	map = em->map_lookup;
-	stripe_size = em->orig_block_len;
+	map = btrfs_get_chunk_map(fs_info, chunk_offset, chunk_size);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
 
 	/*
 	 * Take the device list mutex to prevent races with the final phase of
@@ -2647,13 +2619,13 @@ static int insert_dev_extents(struct btrfs_trans_handle *trans,
 		dev_offset = map->stripes[i].physical;
 
 		ret = insert_dev_extent(trans, device, chunk_offset, dev_offset,
-				       stripe_size);
+					map->stripe_size);
 		if (ret)
 			break;
 	}
 	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 	return ret;
 }
 
@@ -2910,7 +2882,7 @@ int btrfs_inc_block_group_ro(struct btrfs_block_group *cache,
 		goto unlock_out;
 
 	/*
-	 * Skip chunk alloction if the bg is SYSTEM, this is to avoid system
+	 * Skip chunk allocation if the bg is SYSTEM, this is to avoid system
 	 * chunk allocation storm to exhaust the system chunk array.  Otherwise
 	 * we still want to try our best to mark the block group read-only.
 	 */
@@ -4406,8 +4378,6 @@ void btrfs_freeze_block_group(struct btrfs_block_group *cache)
 void btrfs_unfreeze_block_group(struct btrfs_block_group *block_group)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
-	struct extent_map_tree *em_tree;
-	struct extent_map *em;
 	bool cleanup;
 
 	spin_lock(&block_group->lock);
@@ -4416,17 +4386,16 @@ void btrfs_unfreeze_block_group(struct btrfs_block_group *block_group)
 	spin_unlock(&block_group->lock);
 
 	if (cleanup) {
-		em_tree = &fs_info->mapping_tree;
-		write_lock(&em_tree->lock);
-		em = lookup_extent_mapping(em_tree, block_group->start,
-					   1);
-		BUG_ON(!em); /* logic error, can't happen */
-		remove_extent_mapping(em_tree, em);
-		write_unlock(&em_tree->lock);
-
-		/* once for us and once for the tree */
-		free_extent_map(em);
-		free_extent_map(em);
+		struct btrfs_chunk_map *map;
+
+		map = btrfs_find_chunk_map(fs_info, block_group->start, 1);
+		/* Logic error, can't happen. */
+		ASSERT(map);
+
+		btrfs_remove_chunk_map(fs_info, map);
+
+		/* Once for our lookup reference. */
+		btrfs_free_chunk_map(map);
 
 		/*
 		 * We may have left one free space entry and other possible
diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index 2bdbcb834f95..c4a1f01cc1c2 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -5,6 +5,8 @@
 
 #include "free-space-cache.h"
 
+struct btrfs_chunk_map;
+
 enum btrfs_disk_cache_state {
 	BTRFS_DC_WRITTEN,
 	BTRFS_DC_ERROR,
@@ -243,7 +245,7 @@ struct btrfs_block_group {
 	u64 zone_unusable;
 	u64 zone_capacity;
 	u64 meta_write_pointer;
-	struct map_lookup *physical_map;
+	struct btrfs_chunk_map *physical_map;
 	struct list_head active_bg_list;
 	struct work_struct zone_finish_work;
 	struct extent_buffer *last_eb;
@@ -297,7 +299,7 @@ struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
 				struct btrfs_fs_info *fs_info,
 				const u64 chunk_offset);
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
-			     u64 group_start, struct extent_map *em);
+			     struct btrfs_chunk_map *map);
 void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info);
 void btrfs_mark_bg_unused(struct btrfs_block_group *bg);
 void btrfs_reclaim_bgs_work(struct work_struct *work);
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 5572ae52444e..7f7c5a92d2b8 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -69,6 +69,8 @@ enum {
 	BTRFS_INODE_VERITY_IN_PROGRESS,
 	/* Set when this inode is a free space inode. */
 	BTRFS_INODE_FREE_SPACE_INODE,
+	/* Set when there are no capabilities in XATTs for the inode. */
+	BTRFS_INODE_NO_CAP_XATTR,
 };
 
 /* in memory btrfs inode */
@@ -107,9 +109,11 @@ struct btrfs_inode {
 
 	/*
 	 * Keep track of where the inode has extent items mapped in order to
-	 * make sure the i_size adjustments are accurate
+	 * make sure the i_size adjustments are accurate. Not required when the
+	 * filesystem is NO_HOLES, the status can't be set while mounted as
+	 * it's a mkfs-time feature.
 	 */
-	struct extent_io_tree file_extent_tree;
+	struct extent_io_tree *file_extent_tree;
 
 	/* held while logging the inode in tree-log.c */
 	struct mutex log_mutex;
@@ -487,7 +491,7 @@ struct inode *btrfs_iget_path(struct super_block *s, u64 ino,
 struct inode *btrfs_iget(struct super_block *s, u64 ino, struct btrfs_root *root);
 struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 				    struct page *page, size_t pg_offset,
-				    u64 start, u64 end);
+				    u64 start, u64 len);
 int btrfs_update_inode(struct btrfs_trans_handle *trans,
 		       struct btrfs_inode *inode);
 int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 19b22b4653c8..193168214eeb 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -20,6 +20,7 @@
 #include <linux/slab.h>
 #include <linux/sched/mm.h>
 #include <linux/log2.h>
+#include <linux/shrinker.h>
 #include <crypto/hash.h>
 #include "misc.h"
 #include "ctree.h"
@@ -163,13 +164,107 @@ static int compression_decompress(int type, struct list_head *ws,
 static void btrfs_free_compressed_pages(struct compressed_bio *cb)
 {
 	for (unsigned int i = 0; i < cb->nr_pages; i++)
-		put_page(cb->compressed_pages[i]);
+		btrfs_free_compr_page(cb->compressed_pages[i]);
 	kfree(cb->compressed_pages);
 }
 
 static int btrfs_decompress_bio(struct compressed_bio *cb);
 
-static void end_compressed_bio_read(struct btrfs_bio *bbio)
+/*
+ * Global cache of last unused pages for compression/decompression.
+ */
+static struct btrfs_compr_pool {
+	struct shrinker *shrinker;
+	spinlock_t lock;
+	struct list_head list;
+	int count;
+	int thresh;
+} compr_pool;
+
+static unsigned long btrfs_compr_pool_count(struct shrinker *sh, struct shrink_control *sc)
+{
+	int ret;
+
+	/*
+	 * We must not read the values more than once if 'ret' gets expanded in
+	 * the return statement so we don't accidentally return a negative
+	 * number, even if the first condition finds it positive.
+	 */
+	ret = READ_ONCE(compr_pool.count) - READ_ONCE(compr_pool.thresh);
+
+	return ret > 0 ? ret : 0;
+}
+
+static unsigned long btrfs_compr_pool_scan(struct shrinker *sh, struct shrink_control *sc)
+{
+	struct list_head remove;
+	struct list_head *tmp, *next;
+	int freed;
+
+	if (compr_pool.count == 0)
+		return SHRINK_STOP;
+
+	INIT_LIST_HEAD(&remove);
+
+	/* For now, just simply drain the whole list. */
+	spin_lock(&compr_pool.lock);
+	list_splice_init(&compr_pool.list, &remove);
+	freed = compr_pool.count;
+	compr_pool.count = 0;
+	spin_unlock(&compr_pool.lock);
+
+	list_for_each_safe(tmp, next, &remove) {
+		struct page *page = list_entry(tmp, struct page, lru);
+
+		ASSERT(page_ref_count(page) == 1);
+		put_page(page);
+	}
+
+	return freed;
+}
+
+/*
+ * Common wrappers for page allocation from compression wrappers
+ */
+struct page *btrfs_alloc_compr_page(void)
+{
+	struct page *page = NULL;
+
+	spin_lock(&compr_pool.lock);
+	if (compr_pool.count > 0) {
+		page = list_first_entry(&compr_pool.list, struct page, lru);
+		list_del_init(&page->lru);
+		compr_pool.count--;
+	}
+	spin_unlock(&compr_pool.lock);
+
+	if (page)
+		return page;
+
+	return alloc_page(GFP_NOFS);
+}
+
+void btrfs_free_compr_page(struct page *page)
+{
+	bool do_free = false;
+
+	spin_lock(&compr_pool.lock);
+	if (compr_pool.count > compr_pool.thresh) {
+		do_free = true;
+	} else {
+		list_add(&page->lru, &compr_pool.list);
+		compr_pool.count++;
+	}
+	spin_unlock(&compr_pool.lock);
+
+	if (!do_free)
+		return;
+
+	ASSERT(page_ref_count(page) == 1);
+	put_page(page);
+}
+
+static void end_bbio_comprssed_read(struct btrfs_bio *bbio)
 {
 	struct compressed_bio *cb = to_compressed_bio(bbio);
 	blk_status_t status = bbio->bio.bi_status;
@@ -211,8 +306,8 @@ static noinline void end_compressed_writeback(const struct compressed_bio *cb)
 		for (i = 0; i < ret; i++) {
 			struct folio *folio = fbatch.folios[i];
 
-			btrfs_page_clamp_clear_writeback(fs_info, &folio->page,
-							 cb->start, cb->len);
+			btrfs_folio_clamp_clear_writeback(fs_info, folio,
+							  cb->start, cb->len);
 		}
 		folio_batch_release(&fbatch);
 	}
@@ -242,7 +337,7 @@ static void btrfs_finish_compressed_write_work(struct work_struct *work)
  * This also calls the writeback end hooks for the file pages so that metadata
  * and checksums can be updated in the file.
  */
-static void end_compressed_bio_write(struct btrfs_bio *bbio)
+static void end_bbio_comprssed_write(struct btrfs_bio *bbio)
 {
 	struct compressed_bio *cb = to_compressed_bio(bbio);
 	struct btrfs_fs_info *fs_info = bbio->inode->root->fs_info;
@@ -289,7 +384,7 @@ void btrfs_submit_compressed_write(struct btrfs_ordered_extent *ordered,
 
 	cb = alloc_compressed_bio(inode, ordered->file_offset,
 				  REQ_OP_WRITE | write_flags,
-				  end_compressed_bio_write);
+				  end_bbio_comprssed_write);
 	cb->start = ordered->file_offset;
 	cb->len = ordered->num_bytes;
 	cb->compressed_pages = compressed_pages;
@@ -446,7 +541,8 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		 * subpage::readers and to unlock the page.
 		 */
 		if (fs_info->sectorsize < PAGE_SIZE)
-			btrfs_subpage_start_reader(fs_info, page, cur, add_size);
+			btrfs_subpage_start_reader(fs_info, page_folio(page),
+						   cur, add_size);
 		put_page(page);
 		cur += add_size;
 	}
@@ -489,11 +585,11 @@ void btrfs_submit_compressed_read(struct btrfs_bio *bbio)
 		goto out;
 	}
 
-	ASSERT(em->compress_type != BTRFS_COMPRESS_NONE);
+	ASSERT(extent_map_is_compressed(em));
 	compressed_len = em->block_len;
 
 	cb = alloc_compressed_bio(inode, file_offset, REQ_OP_READ,
-				  end_compressed_bio_read);
+				  end_bbio_comprssed_read);
 
 	cb->start = em->orig_start;
 	em_len = em->len;
@@ -501,7 +597,7 @@ void btrfs_submit_compressed_read(struct btrfs_bio *bbio)
 
 	cb->len = bbio->bio.bi_iter.bi_size;
 	cb->compressed_len = compressed_len;
-	cb->compress_type = em->compress_type;
+	cb->compress_type = extent_map_compression(em);
 	cb->orig_bbio = bbio;
 
 	free_extent_map(em);
@@ -513,7 +609,7 @@ void btrfs_submit_compressed_read(struct btrfs_bio *bbio)
 		goto out_free_bio;
 	}
 
-	ret2 = btrfs_alloc_page_array(cb->nr_pages, cb->compressed_pages);
+	ret2 = btrfs_alloc_page_array(cb->nr_pages, cb->compressed_pages, 0);
 	if (ret2) {
 		ret = BLK_STS_RESOURCE;
 		goto out_free_compressed_pages;
@@ -960,15 +1056,36 @@ int __init btrfs_init_compress(void)
 			offsetof(struct compressed_bio, bbio.bio),
 			BIOSET_NEED_BVECS))
 		return -ENOMEM;
+
+	compr_pool.shrinker = shrinker_alloc(SHRINKER_NONSLAB, "btrfs-compr-pages");
+	if (!compr_pool.shrinker)
+		return -ENOMEM;
+
 	btrfs_init_workspace_manager(BTRFS_COMPRESS_NONE);
 	btrfs_init_workspace_manager(BTRFS_COMPRESS_ZLIB);
 	btrfs_init_workspace_manager(BTRFS_COMPRESS_LZO);
 	zstd_init_workspace_manager();
+
+	spin_lock_init(&compr_pool.lock);
+	INIT_LIST_HEAD(&compr_pool.list);
+	compr_pool.count = 0;
+	/* 128K / 4K = 32, for 8 threads is 256 pages. */
+	compr_pool.thresh = BTRFS_MAX_COMPRESSED / PAGE_SIZE * 8;
+	compr_pool.shrinker->count_objects = btrfs_compr_pool_count;
+	compr_pool.shrinker->scan_objects = btrfs_compr_pool_scan;
+	compr_pool.shrinker->batch = 32;
+	compr_pool.shrinker->seeks = DEFAULT_SEEKS;
+	shrinker_register(compr_pool.shrinker);
+
 	return 0;
 }
 
 void __cold btrfs_exit_compress(void)
 {
+	/* For now scan drains all pages and does not touch the parameters. */
+	btrfs_compr_pool_scan(NULL, NULL);
+	shrinker_free(compr_pool.shrinker);
+
 	btrfs_cleanup_workspace_manager(BTRFS_COMPRESS_NONE);
 	btrfs_cleanup_workspace_manager(BTRFS_COMPRESS_ZLIB);
 	btrfs_cleanup_workspace_manager(BTRFS_COMPRESS_LZO);
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 03bb9d143fa7..93cc92974dee 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -32,6 +32,8 @@ static_assert((BTRFS_MAX_COMPRESSED % PAGE_SIZE) == 0);
 
 #define	BTRFS_ZLIB_DEFAULT_LEVEL		3
 
+struct page;
+
 struct compressed_bio {
 	/* Number of compressed pages in the array */
 	unsigned int nr_pages;
@@ -96,6 +98,9 @@ void btrfs_submit_compressed_read(struct btrfs_bio *bbio);
 
 unsigned int btrfs_compress_str2level(unsigned int type, const char *str);
 
+struct page *btrfs_alloc_compr_page(void);
+void btrfs_free_compr_page(struct page *page);
+
 enum btrfs_compression_type {
 	BTRFS_COMPRESS_NONE  = 0,
 	BTRFS_COMPRESS_ZLIB  = 1,
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 2a9344a3fcee..e65e012bac55 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -370,33 +370,41 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
 /*
  * check if the tree block can be shared by multiple trees
  */
-int btrfs_block_can_be_shared(struct btrfs_trans_handle *trans,
-			      struct btrfs_root *root,
-			      struct extent_buffer *buf)
+bool btrfs_block_can_be_shared(struct btrfs_trans_handle *trans,
+			       struct btrfs_root *root,
+			       struct extent_buffer *buf)
 {
+	const u64 buf_gen = btrfs_header_generation(buf);
+
 	/*
 	 * Tree blocks not in shareable trees and tree roots are never shared.
 	 * If a block was allocated after the last snapshot and the block was
 	 * not allocated by tree relocation, we know the block is not shared.
 	 */
-	if (test_bit(BTRFS_ROOT_SHAREABLE, &root->state) &&
-	    buf != root->node &&
-	    (btrfs_header_generation(buf) <=
-	     btrfs_root_last_snapshot(&root->root_item) ||
-	     btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC))) {
-		if (buf != root->commit_root)
-			return 1;
-		/*
-		 * An extent buffer that used to be the commit root may still be
-		 * shared because the tree height may have increased and it
-		 * became a child of a higher level root. This can happen when
-		 * snapshotting a subvolume created in the current transaction.
-		 */
-		if (btrfs_header_generation(buf) == trans->transid)
-			return 1;
-	}
 
-	return 0;
+	if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))
+		return false;
+
+	if (buf == root->node)
+		return false;
+
+	if (buf_gen > btrfs_root_last_snapshot(&root->root_item) &&
+	    !btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC))
+		return false;
+
+	if (buf != root->commit_root)
+		return true;
+
+	/*
+	 * An extent buffer that used to be the commit root may still be shared
+	 * because the tree height may have increased and it became a child of a
+	 * higher level root. This can happen when snapshotting a subvolume
+	 * created in the current transaction.
+	 */
+	if (buf_gen == trans->transid)
+		return true;
+
+	return false;
 }
 
 static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
@@ -432,7 +440,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 	if (btrfs_block_can_be_shared(trans, root, buf)) {
 		ret = btrfs_lookup_extent_info(trans, fs_info, buf->start,
 					       btrfs_header_level(buf), 1,
-					       &refs, &flags);
+					       &refs, &flags, NULL);
 		if (ret)
 			return ret;
 		if (unlikely(refs == 0)) {
@@ -812,7 +820,8 @@ int btrfs_bin_search(struct extent_buffer *eb, int first_slot,
 	}
 
 	while (low < high) {
-		unsigned long oip;
+		const int unit_size = folio_size(eb->folios[0]);
+		unsigned long oil;
 		unsigned long offset;
 		struct btrfs_disk_key *tmp;
 		struct btrfs_disk_key unaligned;
@@ -820,14 +829,14 @@ int btrfs_bin_search(struct extent_buffer *eb, int first_slot,
 
 		mid = (low + high) / 2;
 		offset = p + mid * item_size;
-		oip = offset_in_page(offset);
+		oil = get_eb_offset_in_folio(eb, offset);
 
-		if (oip + key_size <= PAGE_SIZE) {
-			const unsigned long idx = get_eb_page_index(offset);
-			char *kaddr = page_address(eb->pages[idx]);
+		if (oil + key_size <= unit_size) {
+			const unsigned long idx = get_eb_folio_index(eb, offset);
+			char *kaddr = folio_address(eb->folios[idx]);
 
-			oip = get_eb_offset_in_page(eb, offset);
-			tmp = (struct btrfs_disk_key *)(kaddr + oip);
+			oil = get_eb_offset_in_folio(eb, offset);
+			tmp = (struct btrfs_disk_key *)(kaddr + oil);
 		} else {
 			read_extent_buffer(eb, &unaligned, offset, key_size);
 			tmp = &unaligned;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 196c005c31f6..70e828d33177 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -212,8 +212,6 @@ struct btrfs_root {
 
 	u64 last_trans;
 
-	u32 type;
-
 	u64 free_objectid;
 
 	struct btrfs_key defrag_progress;
@@ -224,18 +222,15 @@ struct btrfs_root {
 
 	struct list_head root_list;
 
-	spinlock_t log_extents_lock[2];
-	struct list_head logged_list[2];
-
 	spinlock_t inode_lock;
 	/* red-black tree that keeps track of in-memory inodes */
 	struct rb_root inode_tree;
 
 	/*
-	 * radix tree that keeps track of delayed nodes of every inode,
-	 * protected by inode_lock
+	 * Xarray that keeps track of delayed nodes of every inode, protected
+	 * by @inode_lock.
 	 */
-	struct radix_tree_root delayed_nodes_tree;
+	struct xarray delayed_nodes;
 	/*
 	 * right now this just gets used so that a root has its own devid
 	 * for stat.  It may be used for more later
@@ -561,9 +556,9 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
 		      struct btrfs_root *root,
 		      struct extent_buffer *buf,
 		      struct extent_buffer **cow_ret, u64 new_root_objectid);
-int btrfs_block_can_be_shared(struct btrfs_trans_handle *trans,
-			      struct btrfs_root *root,
-			      struct extent_buffer *buf);
+bool btrfs_block_can_be_shared(struct btrfs_trans_handle *trans,
+			       struct btrfs_root *root,
+			       struct extent_buffer *buf);
 int btrfs_del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		  struct btrfs_path *path, int level, int slot);
 void btrfs_extend_item(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c
index 5244561e2016..c276b136ab63 100644
--- a/fs/btrfs/defrag.c
+++ b/fs/btrfs/defrag.c
@@ -775,7 +775,7 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start,
 	 * this em, as either we don't care about the generation, or the
 	 * merged extent map will be rejected anyway.
 	 */
-	if (em && test_bit(EXTENT_FLAG_MERGED, &em->flags) &&
+	if (em && (em->flags & EXTENT_FLAG_MERGED) &&
 	    newer_than && em->generation >= newer_than) {
 		free_extent_map(em);
 		em = NULL;
@@ -802,7 +802,7 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start,
 static u32 get_extent_max_capacity(const struct btrfs_fs_info *fs_info,
 				   const struct extent_map *em)
 {
-	if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
+	if (extent_map_is_compressed(em))
 		return BTRFS_MAX_COMPRESSED;
 	return fs_info->max_extent_size;
 }
@@ -828,7 +828,7 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em,
 	/* No more em or hole */
 	if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE)
 		goto out;
-	if (test_bit(EXTENT_FLAG_PREALLOC, &next->flags))
+	if (next->flags & EXTENT_FLAG_PREALLOC)
 		goto out;
 	/*
 	 * If the next extent is at its max capacity, defragging current extent
@@ -996,10 +996,9 @@ static int defrag_collect_targets(struct btrfs_inode *inode,
 		    em->len <= inode->root->fs_info->max_inline)
 			goto next;
 
-		/* Skip hole/delalloc/preallocated extents */
+		/* Skip holes and preallocated extents. */
 		if (em->block_start == EXTENT_MAP_HOLE ||
-		    em->block_start == EXTENT_MAP_DELALLOC ||
-		    test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+		    (em->flags & EXTENT_FLAG_PREALLOC))
 			goto next;
 
 		/* Skip older extent */
@@ -1190,7 +1189,7 @@ static int defrag_one_locked_target(struct btrfs_inode *inode,
 	/* Update the page status */
 	for (i = start_index - first_index; i <= last_index - first_index; i++) {
 		ClearPageChecked(pages[i]);
-		btrfs_page_clamp_set_dirty(fs_info, pages[i], start, len);
+		btrfs_folio_clamp_set_dirty(fs_info, page_folio(pages[i]), start, len);
 	}
 	btrfs_delalloc_release_extents(inode, len);
 	extent_changeset_free(data_reserved);
diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c
index 51453d4928fa..2833e8ef4c09 100644
--- a/fs/btrfs/delalloc-space.c
+++ b/fs/btrfs/delalloc-space.c
@@ -199,7 +199,7 @@ void btrfs_free_reserved_data_space(struct btrfs_inode *inode,
 	start = round_down(start, fs_info->sectorsize);
 
 	btrfs_free_reserved_data_space_noquota(fs_info, len);
-	btrfs_qgroup_free_data(inode, reserved, start, len);
+	btrfs_qgroup_free_data(inode, reserved, start, len, NULL);
 }
 
 /*
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 7381241334e8..08102883f560 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -71,7 +71,7 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(
 	}
 
 	spin_lock(&root->inode_lock);
-	node = radix_tree_lookup(&root->delayed_nodes_tree, ino);
+	node = xa_load(&root->delayed_nodes, ino);
 
 	if (node) {
 		if (btrfs_inode->delayed_node) {
@@ -83,9 +83,9 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(
 
 		/*
 		 * It's possible that we're racing into the middle of removing
-		 * this node from the radix tree.  In this case, the refcount
+		 * this node from the xarray.  In this case, the refcount
 		 * was zero and it should never go back to one.  Just return
-		 * NULL like it was never in the radix at all; our release
+		 * NULL like it was never in the xarray at all; our release
 		 * function is in the process of removing it.
 		 *
 		 * Some implementations of refcount_inc refuse to bump the
@@ -93,7 +93,7 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(
 		 * here, refcount_inc() may decide to just WARN_ONCE() instead
 		 * of actually bumping the refcount.
 		 *
-		 * If this node is properly in the radix, we want to bump the
+		 * If this node is properly in the xarray, we want to bump the
 		 * refcount twice, once for the inode and once for this get
 		 * operation.
 		 */
@@ -120,6 +120,7 @@ static struct btrfs_delayed_node *btrfs_get_or_create_delayed_node(
 	struct btrfs_root *root = btrfs_inode->root;
 	u64 ino = btrfs_ino(btrfs_inode);
 	int ret;
+	void *ptr;
 
 again:
 	node = btrfs_get_delayed_node(btrfs_inode);
@@ -131,26 +132,30 @@ again:
 		return ERR_PTR(-ENOMEM);
 	btrfs_init_delayed_node(node, root, ino);
 
-	/* cached in the btrfs inode and can be accessed */
+	/* Cached in the inode and can be accessed. */
 	refcount_set(&node->refs, 2);
 
-	ret = radix_tree_preload(GFP_NOFS);
-	if (ret) {
+	/* Allocate and reserve the slot, from now it can return a NULL from xa_load(). */
+	ret = xa_reserve(&root->delayed_nodes, ino, GFP_NOFS);
+	if (ret == -ENOMEM) {
 		kmem_cache_free(delayed_node_cache, node);
-		return ERR_PTR(ret);
+		return ERR_PTR(-ENOMEM);
 	}
-
 	spin_lock(&root->inode_lock);
-	ret = radix_tree_insert(&root->delayed_nodes_tree, ino, node);
-	if (ret == -EEXIST) {
+	ptr = xa_load(&root->delayed_nodes, ino);
+	if (ptr) {
+		/* Somebody inserted it, go back and read it. */
 		spin_unlock(&root->inode_lock);
 		kmem_cache_free(delayed_node_cache, node);
-		radix_tree_preload_end();
+		node = NULL;
 		goto again;
 	}
+	ptr = xa_store(&root->delayed_nodes, ino, node, GFP_ATOMIC);
+	ASSERT(xa_err(ptr) != -EINVAL);
+	ASSERT(xa_err(ptr) != -ENOMEM);
+	ASSERT(ptr == NULL);
 	btrfs_inode->delayed_node = node;
 	spin_unlock(&root->inode_lock);
-	radix_tree_preload_end();
 
 	return node;
 }
@@ -269,8 +274,7 @@ static void __btrfs_release_delayed_node(
 		 * back up.  We can delete it now.
 		 */
 		ASSERT(refcount_read(&delayed_node->refs) == 0);
-		radix_tree_delete(&root->delayed_nodes_tree,
-				  delayed_node->inode_id);
+		xa_erase(&root->delayed_nodes, delayed_node->inode_id);
 		spin_unlock(&root->inode_lock);
 		kmem_cache_free(delayed_node_cache, delayed_node);
 	}
@@ -1036,14 +1040,33 @@ static int __btrfs_update_delayed_inode(struct btrfs_trans_handle *trans,
 	if (!test_bit(BTRFS_DELAYED_NODE_DEL_IREF, &node->flags))
 		goto out;
 
-	path->slots[0]++;
-	if (path->slots[0] >= btrfs_header_nritems(leaf))
-		goto search;
-again:
+	/*
+	 * Now we're going to delete the INODE_REF/EXTREF, which should be the
+	 * only one ref left.  Check if the next item is an INODE_REF/EXTREF.
+	 *
+	 * But if we're the last item already, release and search for the last
+	 * INODE_REF/EXTREF.
+	 */
+	if (path->slots[0] + 1 >= btrfs_header_nritems(leaf)) {
+		key.objectid = node->inode_id;
+		key.type = BTRFS_INODE_EXTREF_KEY;
+		key.offset = (u64)-1;
+
+		btrfs_release_path(path);
+		ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+		if (ret < 0)
+			goto err_out;
+		ASSERT(ret > 0);
+		ASSERT(path->slots[0] > 0);
+		ret = 0;
+		path->slots[0]--;
+		leaf = path->nodes[0];
+	} else {
+		path->slots[0]++;
+	}
 	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
 	if (key.objectid != node->inode_id)
 		goto out;
-
 	if (key.type != BTRFS_INODE_REF_KEY &&
 	    key.type != BTRFS_INODE_EXTREF_KEY)
 		goto out;
@@ -1070,22 +1093,6 @@ err_out:
 		btrfs_abort_transaction(trans, ret);
 
 	return ret;
-
-search:
-	btrfs_release_path(path);
-
-	key.type = BTRFS_INODE_EXTREF_KEY;
-	key.offset = -1;
-
-	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
-	if (ret < 0)
-		goto err_out;
-	ASSERT(ret);
-
-	ret = 0;
-	leaf = path->nodes[0];
-	path->slots[0]--;
-	goto again;
 }
 
 static inline int btrfs_update_delayed_inode(struct btrfs_trans_handle *trans,
@@ -2035,34 +2042,36 @@ void btrfs_kill_delayed_inode_items(struct btrfs_inode *inode)
 
 void btrfs_kill_all_delayed_nodes(struct btrfs_root *root)
 {
-	u64 inode_id = 0;
+	unsigned long index = 0;
 	struct btrfs_delayed_node *delayed_nodes[8];
-	int i, n;
 
 	while (1) {
+		struct btrfs_delayed_node *node;
+		int count;
+
 		spin_lock(&root->inode_lock);
-		n = radix_tree_gang_lookup(&root->delayed_nodes_tree,
-					   (void **)delayed_nodes, inode_id,
-					   ARRAY_SIZE(delayed_nodes));
-		if (!n) {
+		if (xa_empty(&root->delayed_nodes)) {
 			spin_unlock(&root->inode_lock);
-			break;
+			return;
 		}
 
-		inode_id = delayed_nodes[n - 1]->inode_id + 1;
-		for (i = 0; i < n; i++) {
+		count = 0;
+		xa_for_each_start(&root->delayed_nodes, index, node, index) {
 			/*
 			 * Don't increase refs in case the node is dead and
 			 * about to be removed from the tree in the loop below
 			 */
-			if (!refcount_inc_not_zero(&delayed_nodes[i]->refs))
-				delayed_nodes[i] = NULL;
+			if (refcount_inc_not_zero(&node->refs)) {
+				delayed_nodes[count] = node;
+				count++;
+			}
+			if (count >= ARRAY_SIZE(delayed_nodes))
+				break;
 		}
 		spin_unlock(&root->inode_lock);
+		index++;
 
-		for (i = 0; i < n; i++) {
-			if (!delayed_nodes[i])
-				continue;
+		for (int i = 0; i < count; i++) {
 			__btrfs_kill_delayed_node(delayed_nodes[i]);
 			btrfs_release_delayed_node(delayed_nodes[i]);
 		}
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 9223934d95f4..891ea2fa263c 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -1041,7 +1041,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 	}
 
-	if (btrfs_qgroup_enabled(fs_info) && !generic_ref->skip_qgroup) {
+	if (btrfs_qgroup_full_accounting(fs_info) && !generic_ref->skip_qgroup) {
 		record = kzalloc(sizeof(*record), GFP_NOFS);
 		if (!record) {
 			kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
@@ -1144,7 +1144,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 	}
 
-	if (btrfs_qgroup_enabled(fs_info) && !generic_ref->skip_qgroup) {
+	if (btrfs_qgroup_full_accounting(fs_info) && !generic_ref->skip_qgroup) {
 		record = kzalloc(sizeof(*record), GFP_NOFS);
 		if (!record) {
 			kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index f9544fda38e9..1502d664c892 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -550,8 +550,7 @@ bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev,
 				      u64 physical)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	u64 chunk_offset = cache->start;
 	int num_extents, cur_extent;
 	int i;
@@ -567,9 +566,8 @@ bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev,
 	}
 	spin_unlock(&cache->lock);
 
-	em = btrfs_get_chunk_map(fs_info, chunk_offset, 1);
-	ASSERT(!IS_ERR(em));
-	map = em->map_lookup;
+	map = btrfs_get_chunk_map(fs_info, chunk_offset, 1);
+	ASSERT(!IS_ERR(map));
 
 	num_extents = 0;
 	cur_extent = 0;
@@ -583,7 +581,7 @@ bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev,
 			cur_extent = i;
 	}
 
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 
 	if (num_extents > 1 && cur_extent < num_extents - 1) {
 		/*
@@ -812,25 +810,23 @@ static void btrfs_dev_replace_update_device_in_mapping_tree(
 						struct btrfs_device *srcdev,
 						struct btrfs_device *tgtdev)
 {
-	struct extent_map_tree *em_tree = &fs_info->mapping_tree;
-	struct extent_map *em;
-	struct map_lookup *map;
 	u64 start = 0;
 	int i;
 
-	write_lock(&em_tree->lock);
+	write_lock(&fs_info->mapping_tree_lock);
 	do {
-		em = lookup_extent_mapping(em_tree, start, (u64)-1);
-		if (!em)
+		struct btrfs_chunk_map *map;
+
+		map = btrfs_find_chunk_map_nolock(fs_info, start, U64_MAX);
+		if (!map)
 			break;
-		map = em->map_lookup;
 		for (i = 0; i < map->num_stripes; i++)
 			if (srcdev == map->stripes[i].dev)
 				map->stripes[i].dev = tgtdev;
-		start = em->start + em->len;
-		free_extent_map(em);
+		start = map->start + map->chunk_len;
+		btrfs_free_chunk_map(map);
 	} while (start);
-	write_unlock(&em_tree->lock);
+	write_unlock(&fs_info->mapping_tree_lock);
 }
 
 static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 401ea09ae4b8..c6907d533fe8 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -74,20 +74,37 @@ static void btrfs_free_csum_hash(struct btrfs_fs_info *fs_info)
 static void csum_tree_block(struct extent_buffer *buf, u8 *result)
 {
 	struct btrfs_fs_info *fs_info = buf->fs_info;
-	const int num_pages = num_extent_pages(buf);
-	const int first_page_part = min_t(u32, PAGE_SIZE, fs_info->nodesize);
+	int num_pages;
+	u32 first_page_part;
 	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
 	char *kaddr;
 	int i;
 
 	shash->tfm = fs_info->csum_shash;
 	crypto_shash_init(shash);
-	kaddr = page_address(buf->pages[0]) + offset_in_page(buf->start);
+
+	if (buf->addr) {
+		/* Pages are contiguous, handle them as a big one. */
+		kaddr = buf->addr;
+		first_page_part = fs_info->nodesize;
+		num_pages = 1;
+	} else {
+		kaddr = folio_address(buf->folios[0]);
+		first_page_part = min_t(u32, PAGE_SIZE, fs_info->nodesize);
+		num_pages = num_extent_pages(buf);
+	}
+
 	crypto_shash_update(shash, kaddr + BTRFS_CSUM_SIZE,
 			    first_page_part - BTRFS_CSUM_SIZE);
 
+	/*
+	 * Multiple single-page folios case would reach here.
+	 *
+	 * nodesize <= PAGE_SIZE and large folio all handled by above
+	 * crypto_shash_update() already.
+	 */
 	for (i = 1; i < num_pages && INLINE_EXTENT_BUFFER_PAGES > 1; i++) {
-		kaddr = page_address(buf->pages[i]);
+		kaddr = folio_address(buf->folios[i]);
 		crypto_shash_update(shash, kaddr, PAGE_SIZE);
 	}
 	memset(result, 0, BTRFS_CSUM_SIZE);
@@ -166,20 +183,22 @@ static int btrfs_repair_eb_io_failure(const struct extent_buffer *eb,
 				      int mirror_num)
 {
 	struct btrfs_fs_info *fs_info = eb->fs_info;
-	int i, num_pages = num_extent_pages(eb);
+	int num_folios = num_extent_folios(eb);
 	int ret = 0;
 
 	if (sb_rdonly(fs_info->sb))
 		return -EROFS;
 
-	for (i = 0; i < num_pages; i++) {
-		struct page *p = eb->pages[i];
-		u64 start = max_t(u64, eb->start, page_offset(p));
-		u64 end = min_t(u64, eb->start + eb->len, page_offset(p) + PAGE_SIZE);
+	for (int i = 0; i < num_folios; i++) {
+		struct folio *folio = eb->folios[i];
+		u64 start = max_t(u64, eb->start, folio_pos(folio));
+		u64 end = min_t(u64, eb->start + eb->len,
+				folio_pos(folio) + folio_size(folio));
 		u32 len = end - start;
 
 		ret = btrfs_repair_io_failure(fs_info, 0, start, len,
-				start, p, offset_in_page(start), mirror_num);
+					      start, folio, offset_in_folio(folio, start),
+					      mirror_num);
 		if (ret)
 			break;
 	}
@@ -254,15 +273,20 @@ blk_status_t btree_csum_one_bio(struct btrfs_bio *bbio)
 	if (WARN_ON_ONCE(bbio->bio.bi_iter.bi_size != eb->len))
 		return BLK_STS_IOERR;
 
-	if (test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags)) {
-		WARN_ON_ONCE(found_start != 0);
+	/*
+	 * If an extent_buffer is marked as EXTENT_BUFFER_ZONED_ZEROOUT, don't
+	 * checksum it but zero-out its content. This is done to preserve
+	 * ordering of I/O without unnecessarily writing out data.
+	 */
+	if (test_bit(EXTENT_BUFFER_ZONED_ZEROOUT, &eb->bflags)) {
+		memzero_extent_buffer(eb, 0, eb->len);
 		return BLK_STS_OK;
 	}
 
 	if (WARN_ON_ONCE(found_start != eb->start))
 		return BLK_STS_IOERR;
-	if (WARN_ON(!btrfs_page_test_uptodate(fs_info, eb->pages[0], eb->start,
-					      eb->len)))
+	if (WARN_ON(!btrfs_folio_test_uptodate(fs_info, eb->folios[0],
+					       eb->start, eb->len)))
 		return BLK_STS_IOERR;
 
 	ASSERT(memcmp_extent_buffer(eb, fs_info->fs_devices->metadata_uuid,
@@ -371,8 +395,8 @@ int btrfs_validate_extent_buffer(struct extent_buffer *eb,
 	}
 
 	csum_tree_block(eb, result);
-	header_csum = page_address(eb->pages[0]) +
-		get_eb_offset_in_page(eb, offsetof(struct btrfs_header, csum));
+	header_csum = folio_address(eb->folios[0]) +
+		get_eb_offset_in_folio(eb, offsetof(struct btrfs_header, csum));
 
 	if (memcmp(result, header_csum, csum_size) != 0) {
 		btrfs_warn_rl(fs_info,
@@ -639,7 +663,8 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	root->nr_delalloc_inodes = 0;
 	root->nr_ordered_extents = 0;
 	root->inode_tree = RB_ROOT;
-	INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC);
+	/* GFP flags are compatible with XA_FLAGS_*. */
+	xa_init_flags(&root->delayed_nodes, GFP_ATOMIC);
 
 	btrfs_init_root_block_rsv(root);
 
@@ -650,14 +675,10 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	INIT_LIST_HEAD(&root->ordered_extents);
 	INIT_LIST_HEAD(&root->ordered_root);
 	INIT_LIST_HEAD(&root->reloc_dirty_list);
-	INIT_LIST_HEAD(&root->logged_list[0]);
-	INIT_LIST_HEAD(&root->logged_list[1]);
 	spin_lock_init(&root->inode_lock);
 	spin_lock_init(&root->delalloc_lock);
 	spin_lock_init(&root->ordered_extent_lock);
 	spin_lock_init(&root->accounting_lock);
-	spin_lock_init(&root->log_extents_lock[0]);
-	spin_lock_init(&root->log_extents_lock[1]);
 	spin_lock_init(&root->qgroup_meta_rsv_lock);
 	mutex_init(&root->objectid_mutex);
 	mutex_init(&root->log_mutex);
@@ -2618,9 +2639,6 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info)
 			 */
 			btrfs_set_super_log_root(sb, 0);
 
-			/* We can't trust the free space cache either */
-			btrfs_set_opt(fs_info->mount_opt, CLEAR_CACHE);
-
 			btrfs_warn(fs_info, "try to load backup roots slot %d", i);
 			ret = read_backup_root(fs_info, i);
 			backup_index = ret;
@@ -2724,7 +2742,8 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	INIT_LIST_HEAD(&fs_info->allocated_ebs);
 	spin_lock_init(&fs_info->eb_leak_lock);
 #endif
-	extent_map_tree_init(&fs_info->mapping_tree);
+	fs_info->mapping_tree = RB_ROOT_CACHED;
+	rwlock_init(&fs_info->mapping_tree_lock);
 	btrfs_init_block_rsv(&fs_info->global_block_rsv,
 			     BTRFS_BLOCK_RSV_GLOBAL);
 	btrfs_init_block_rsv(&fs_info->trans_block_rsv, BTRFS_BLOCK_RSV_TRANS);
@@ -2794,6 +2813,9 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	fs_info->sectorsize_bits = ilog2(4096);
 	fs_info->stripesize = 4096;
 
+	/* Default compress algorithm when user does -o compress */
+	fs_info->compress_type = BTRFS_COMPRESS_ZLIB;
+
 	fs_info->max_extent_size = BTRFS_MAX_EXTENT_SIZE;
 
 	spin_lock_init(&fs_info->swapfile_pins_lock);
@@ -2931,17 +2953,6 @@ out:
 }
 
 /*
- * Some options only have meaning at mount time and shouldn't persist across
- * remounts, or be displayed. Clear these at the end of mount and remount
- * code paths.
- */
-void btrfs_clear_oneshot_options(struct btrfs_fs_info *fs_info)
-{
-	btrfs_clear_opt(fs_info->mount_opt, USEBACKUPROOT);
-	btrfs_clear_opt(fs_info->mount_opt, CLEAR_CACHE);
-}
-
-/*
  * Mounting logic specific to read-write file systems. Shared by open_ctree
  * and btrfs_remount when remounting from read-only to read-write.
  */
@@ -2953,7 +2964,11 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
 
 	if (btrfs_test_opt(fs_info, CLEAR_CACHE) &&
 	    btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
-		rebuild_free_space_tree = true;
+		if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2))
+			btrfs_warn(fs_info,
+				   "'clear_cache' option is ignored with extent tree v2");
+		else
+			rebuild_free_space_tree = true;
 	} else if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) &&
 		   !btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID)) {
 		btrfs_warn(fs_info, "free space tree is invalid");
@@ -3213,6 +3228,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		goto fail_alloc;
 	}
 
+	btrfs_info(fs_info, "first mount of filesystem %pU", disk_super->fsid);
 	/*
 	 * Verify the type first, if that or the checksum value are
 	 * corrupted, we'll find out
@@ -3275,13 +3291,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 	if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_ERROR)
 		WRITE_ONCE(fs_info->fs_error, -EUCLEAN);
 
-	/*
-	 * In the long term, we'll store the compression type in the super
-	 * block, and it'll be used for per file compression control.
-	 */
-	fs_info->compress_type = BTRFS_COMPRESS_ZLIB;
-
-
 	/* Set up fs_info before parsing mount options */
 	nodesize = btrfs_super_nodesize(disk_super);
 	sectorsize = btrfs_super_sectorsize(disk_super);
@@ -3295,28 +3304,30 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 	fs_info->csums_per_leaf = BTRFS_MAX_ITEM_SIZE(fs_info) / fs_info->csum_size;
 	fs_info->stripesize = stripesize;
 
-	ret = btrfs_parse_options(fs_info, options, sb->s_flags);
-	if (ret)
+	/*
+	 * Handle the space caching options appropriately now that we have the
+	 * super block loaded and validated.
+	 */
+	btrfs_set_free_space_cache_settings(fs_info);
+
+	if (!btrfs_check_options(fs_info, &fs_info->mount_opt, sb->s_flags)) {
+		ret = -EINVAL;
 		goto fail_alloc;
+	}
 
 	ret = btrfs_check_features(fs_info, !sb_rdonly(sb));
 	if (ret < 0)
 		goto fail_alloc;
 
+	/*
+	 * At this point our mount options are validated, if we set ->max_inline
+	 * to something non-standard make sure we truncate it to sectorsize.
+	 */
+	fs_info->max_inline = min_t(u64, fs_info->max_inline, fs_info->sectorsize);
+
 	if (sectorsize < PAGE_SIZE) {
 		struct btrfs_subpage_info *subpage_info;
 
-		/*
-		 * V1 space cache has some hardcoded PAGE_SIZE usage, and is
-		 * going to be deprecated.
-		 *
-		 * Force to use v2 cache for subpage case.
-		 */
-		btrfs_clear_opt(fs_info->mount_opt, SPACE_CACHE);
-		btrfs_set_and_info(fs_info, FREE_SPACE_TREE,
-			"forcing free space tree for sector size %u with page size %lu",
-			sectorsize, PAGE_SIZE);
-
 		btrfs_warn(fs_info,
 		"read-write for sector size %u with page size %lu is experimental",
 			   sectorsize, PAGE_SIZE);
@@ -3493,29 +3504,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		goto fail_cleaner;
 	}
 
-	if (!btrfs_test_opt(fs_info, NOSSD) &&
-	    !fs_info->fs_devices->rotating) {
-		btrfs_set_and_info(fs_info, SSD, "enabling ssd optimizations");
-	}
-
-	/*
-	 * For devices supporting discard turn on discard=async automatically,
-	 * unless it's already set or disabled. This could be turned off by
-	 * nodiscard for the same mount.
-	 *
-	 * The zoned mode piggy backs on the discard functionality for
-	 * resetting a zone. There is no reason to delay the zone reset as it is
-	 * fast enough. So, do not enable async discard for zoned mode.
-	 */
-	if (!(btrfs_test_opt(fs_info, DISCARD_SYNC) ||
-	      btrfs_test_opt(fs_info, DISCARD_ASYNC) ||
-	      btrfs_test_opt(fs_info, NODISCARD)) &&
-	    fs_info->fs_devices->discardable &&
-	    !btrfs_is_zoned(fs_info)) {
-		btrfs_set_and_info(fs_info, DISCARD_ASYNC,
-				   "auto enabling async discard");
-	}
-
 	ret = btrfs_read_qgroup_config(fs_info);
 	if (ret)
 		goto fail_trans_kthread;
@@ -3541,7 +3529,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 	}
 
 	if (sb_rdonly(sb))
-		goto clear_oneshot;
+		return 0;
 
 	ret = btrfs_start_pre_rw_mount(fs_info);
 	if (ret) {
@@ -3569,8 +3557,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 	if (test_bit(BTRFS_FS_UNFINISHED_DROPS, &fs_info->flags))
 		wake_up_process(fs_info->cleaner_kthread);
 
-clear_oneshot:
-	btrfs_clear_oneshot_options(fs_info);
 	return 0;
 
 fail_qgroup:
@@ -3607,7 +3593,7 @@ fail_sb_buffer:
 	btrfs_stop_all_workers(fs_info);
 	btrfs_free_block_groups(fs_info);
 fail_alloc:
-	btrfs_mapping_tree_free(&fs_info->mapping_tree);
+	btrfs_mapping_tree_free(fs_info);
 
 	iput(fs_info->btree_inode);
 fail:
@@ -4390,7 +4376,7 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 
 	iput(fs_info->btree_inode);
 
-	btrfs_mapping_tree_free(&fs_info->mapping_tree);
+	btrfs_mapping_tree_free(fs_info);
 	btrfs_close_devices(fs_info->fs_devices);
 }
 
@@ -4798,6 +4784,32 @@ void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans,
 	}
 }
 
+static void btrfs_free_all_qgroup_pertrans(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_root *gang[8];
+	int i;
+	int ret;
+
+	spin_lock(&fs_info->fs_roots_radix_lock);
+	while (1) {
+		ret = radix_tree_gang_lookup_tag(&fs_info->fs_roots_radix,
+						 (void **)gang, 0,
+						 ARRAY_SIZE(gang),
+						 BTRFS_ROOT_TRANS_TAG);
+		if (ret == 0)
+			break;
+		for (i = 0; i < ret; i++) {
+			struct btrfs_root *root = gang[i];
+
+			btrfs_qgroup_free_meta_all_pertrans(root);
+			radix_tree_tag_clear(&fs_info->fs_roots_radix,
+					(unsigned long)root->root_key.objectid,
+					BTRFS_ROOT_TRANS_TAG);
+		}
+	}
+	spin_unlock(&fs_info->fs_roots_radix_lock);
+}
+
 void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
 				   struct btrfs_fs_info *fs_info)
 {
@@ -4826,6 +4838,8 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
 				     EXTENT_DIRTY);
 	btrfs_destroy_pinned_extent(fs_info, &cur_trans->pinned_extents);
 
+	btrfs_free_all_qgroup_pertrans(fs_info);
+
 	cur_trans->state =TRANS_STATE_COMPLETED;
 	wake_up(&cur_trans->commit_wait);
 }
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 50dab8f639dc..9413726b329b 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -37,9 +37,6 @@ struct extent_buffer *btrfs_find_create_tree_block(
 						struct btrfs_fs_info *fs_info,
 						u64 bytenr, u64 owner_root,
 						int level);
-void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans,
-			      struct extent_buffer *buf);
-void btrfs_clear_oneshot_options(struct btrfs_fs_info *fs_info);
 int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info);
 int btrfs_check_super_csum(struct btrfs_fs_info *fs_info,
 			   const struct btrfs_super_block *disk_sb);
diff --git a/fs/btrfs/extent-io-tree.c b/fs/btrfs/extent-io-tree.c
index ea149be28dff..e3ee5449cc4a 100644
--- a/fs/btrfs/extent-io-tree.c
+++ b/fs/btrfs/extent-io-tree.c
@@ -58,12 +58,13 @@ static inline void __btrfs_debug_check_extent_io_range(const char *caller,
 						       struct extent_io_tree *tree,
 						       u64 start, u64 end)
 {
-	struct btrfs_inode *inode = tree->inode;
+	const struct btrfs_inode *inode;
 	u64 isize;
 
-	if (!inode)
+	if (tree->owner != IO_TREE_INODE_IO)
 		return;
 
+	inode = extent_io_tree_to_inode_const(tree);
 	isize = i_size_read(&inode->vfs_inode);
 	if (end >= PAGE_SIZE && (end % 2) == 0 && end != isize - 1) {
 		btrfs_debug_rl(inode->root->fs_info,
@@ -78,31 +79,46 @@ static inline void __btrfs_debug_check_extent_io_range(const char *caller,
 #define btrfs_debug_check_extent_io_range(c, s, e)	do {} while (0)
 #endif
 
+
 /*
- * For the file_extent_tree, we want to hold the inode lock when we lookup and
- * update the disk_i_size, but lockdep will complain because our io_tree we hold
- * the tree lock and get the inode lock when setting delalloc.  These two things
- * are unrelated, so make a class for the file_extent_tree so we don't get the
- * two locking patterns mixed up.
+ * The only tree allowed to set the inode is IO_TREE_INODE_IO.
  */
-static struct lock_class_key file_extent_tree_class;
+static bool is_inode_io_tree(const struct extent_io_tree *tree)
+{
+	return tree->owner == IO_TREE_INODE_IO;
+}
+
+/* Return the inode if it's valid for the given tree, otherwise NULL. */
+struct btrfs_inode *extent_io_tree_to_inode(struct extent_io_tree *tree)
+{
+	if (tree->owner == IO_TREE_INODE_IO)
+		return tree->inode;
+	return NULL;
+}
+
+/* Read-only access to the inode. */
+const struct btrfs_inode *extent_io_tree_to_inode_const(const struct extent_io_tree *tree)
+{
+	if (tree->owner == IO_TREE_INODE_IO)
+		return tree->inode;
+	return NULL;
+}
 
-struct tree_entry {
-	u64 start;
-	u64 end;
-	struct rb_node rb_node;
-};
+/* For read-only access to fs_info. */
+const struct btrfs_fs_info *extent_io_tree_to_fs_info(const struct extent_io_tree *tree)
+{
+	if (tree->owner == IO_TREE_INODE_IO)
+		return tree->inode->root->fs_info;
+	return tree->fs_info;
+}
 
 void extent_io_tree_init(struct btrfs_fs_info *fs_info,
 			 struct extent_io_tree *tree, unsigned int owner)
 {
-	tree->fs_info = fs_info;
 	tree->state = RB_ROOT;
 	spin_lock_init(&tree->lock);
-	tree->inode = NULL;
+	tree->fs_info = fs_info;
 	tree->owner = owner;
-	if (owner == IO_TREE_INODE_FILE_EXTENT)
-		lockdep_set_class(&tree->lock, &file_extent_tree_class);
 }
 
 /*
@@ -329,10 +345,14 @@ static inline struct extent_state *tree_search(struct extent_io_tree *tree, u64
 	return tree_search_for_insert(tree, offset, NULL, NULL);
 }
 
-static void extent_io_tree_panic(struct extent_io_tree *tree, int err)
+static void extent_io_tree_panic(const struct extent_io_tree *tree,
+				 const struct extent_state *state,
+				 const char *opname,
+				 int err)
 {
-	btrfs_panic(tree->fs_info, err,
-	"locking error: extent tree was modified by another thread while locked");
+	btrfs_panic(extent_io_tree_to_fs_info(tree), err,
+		    "extent io tree error on %s state start %llu end %llu",
+		    opname, state->start, state->end);
 }
 
 static void merge_prev_state(struct extent_io_tree *tree, struct extent_state *state)
@@ -341,8 +361,9 @@ static void merge_prev_state(struct extent_io_tree *tree, struct extent_state *s
 
 	prev = prev_state(state);
 	if (prev && prev->end == state->start - 1 && prev->state == state->state) {
-		if (tree->inode)
-			btrfs_merge_delalloc_extent(tree->inode, state, prev);
+		if (is_inode_io_tree(tree))
+			btrfs_merge_delalloc_extent(extent_io_tree_to_inode(tree),
+						    state, prev);
 		state->start = prev->start;
 		rb_erase(&prev->rb_node, &tree->state);
 		RB_CLEAR_NODE(&prev->rb_node);
@@ -356,8 +377,9 @@ static void merge_next_state(struct extent_io_tree *tree, struct extent_state *s
 
 	next = next_state(state);
 	if (next && next->start == state->end + 1 && next->state == state->state) {
-		if (tree->inode)
-			btrfs_merge_delalloc_extent(tree->inode, state, next);
+		if (is_inode_io_tree(tree))
+			btrfs_merge_delalloc_extent(extent_io_tree_to_inode(tree),
+						    state, next);
 		state->end = next->end;
 		rb_erase(&next->rb_node, &tree->state);
 		RB_CLEAR_NODE(&next->rb_node);
@@ -390,8 +412,8 @@ static void set_state_bits(struct extent_io_tree *tree,
 	u32 bits_to_set = bits & ~EXTENT_CTLBITS;
 	int ret;
 
-	if (tree->inode)
-		btrfs_set_delalloc_extent(tree->inode, state, bits);
+	if (is_inode_io_tree(tree))
+		btrfs_set_delalloc_extent(extent_io_tree_to_inode(tree), state, bits);
 
 	ret = add_extent_changeset(state, bits_to_set, changeset, 1);
 	BUG_ON(ret < 0);
@@ -436,9 +458,10 @@ static struct extent_state *insert_state(struct extent_io_tree *tree,
 		if (state->end < entry->start) {
 			if (try_merge && end == entry->start &&
 			    state->state == entry->state) {
-				if (tree->inode)
-					btrfs_merge_delalloc_extent(tree->inode,
-								    state, entry);
+				if (is_inode_io_tree(tree))
+					btrfs_merge_delalloc_extent(
+							extent_io_tree_to_inode(tree),
+							state, entry);
 				entry->start = state->start;
 				merge_prev_state(tree, entry);
 				state->state = 0;
@@ -448,9 +471,10 @@ static struct extent_state *insert_state(struct extent_io_tree *tree,
 		} else if (state->end > entry->end) {
 			if (try_merge && entry->end == start &&
 			    state->state == entry->state) {
-				if (tree->inode)
-					btrfs_merge_delalloc_extent(tree->inode,
-								    state, entry);
+				if (is_inode_io_tree(tree))
+					btrfs_merge_delalloc_extent(
+							extent_io_tree_to_inode(tree),
+							state, entry);
 				entry->end = state->end;
 				merge_next_state(tree, entry);
 				state->state = 0;
@@ -458,9 +482,6 @@ static struct extent_state *insert_state(struct extent_io_tree *tree,
 			}
 			node = &(*node)->rb_right;
 		} else {
-			btrfs_err(tree->fs_info,
-			       "found node %llu %llu on insert of %llu %llu",
-			       entry->start, entry->end, state->start, state->end);
 			return ERR_PTR(-EEXIST);
 		}
 	}
@@ -505,8 +526,9 @@ static int split_state(struct extent_io_tree *tree, struct extent_state *orig,
 	struct rb_node *parent = NULL;
 	struct rb_node **node;
 
-	if (tree->inode)
-		btrfs_split_delalloc_extent(tree->inode, orig, split);
+	if (is_inode_io_tree(tree))
+		btrfs_split_delalloc_extent(extent_io_tree_to_inode(tree), orig,
+					    split);
 
 	prealloc->start = orig->start;
 	prealloc->end = split - 1;
@@ -553,8 +575,9 @@ static struct extent_state *clear_state_bit(struct extent_io_tree *tree,
 	u32 bits_to_clear = bits & ~EXTENT_CTLBITS;
 	int ret;
 
-	if (tree->inode)
-		btrfs_clear_delalloc_extent(tree->inode, state, bits);
+	if (is_inode_io_tree(tree))
+		btrfs_clear_delalloc_extent(extent_io_tree_to_inode(tree), state,
+					    bits);
 
 	ret = add_extent_changeset(state, bits_to_clear, changeset, 0);
 	BUG_ON(ret < 0);
@@ -695,7 +718,7 @@ hit_next:
 			goto search_again;
 		err = split_state(tree, state, prealloc, start);
 		if (err)
-			extent_io_tree_panic(tree, err);
+			extent_io_tree_panic(tree, state, "split", err);
 
 		prealloc = NULL;
 		if (err)
@@ -717,7 +740,7 @@ hit_next:
 			goto search_again;
 		err = split_state(tree, state, prealloc, end + 1);
 		if (err)
-			extent_io_tree_panic(tree, err);
+			extent_io_tree_panic(tree, state, "split", err);
 
 		if (wake)
 			wake_up(&state->wq);
@@ -939,6 +962,8 @@ int find_contiguous_extent_bit(struct extent_io_tree *tree, u64 start,
 	struct extent_state *state;
 	int ret = 1;
 
+	ASSERT(!btrfs_fs_incompat(extent_io_tree_to_fs_info(tree), NO_HOLES));
+
 	spin_lock(&tree->lock);
 	state = find_first_extent_bit_state(tree, start, bits);
 	if (state) {
@@ -1152,7 +1177,7 @@ hit_next:
 			goto search_again;
 		err = split_state(tree, state, prealloc, start);
 		if (err)
-			extent_io_tree_panic(tree, err);
+			extent_io_tree_panic(tree, state, "split", err);
 
 		prealloc = NULL;
 		if (err)
@@ -1200,7 +1225,7 @@ hit_next:
 		inserted_state = insert_state(tree, prealloc, bits, changeset);
 		if (IS_ERR(inserted_state)) {
 			err = PTR_ERR(inserted_state);
-			extent_io_tree_panic(tree, err);
+			extent_io_tree_panic(tree, prealloc, "insert", err);
 		}
 
 		cache_state(inserted_state, cached_state);
@@ -1228,7 +1253,7 @@ hit_next:
 			goto search_again;
 		err = split_state(tree, state, prealloc, end + 1);
 		if (err)
-			extent_io_tree_panic(tree, err);
+			extent_io_tree_panic(tree, state, "split", err);
 
 		set_state_bits(tree, prealloc, bits, changeset);
 		cache_state(prealloc, cached_state);
@@ -1382,7 +1407,7 @@ hit_next:
 		}
 		err = split_state(tree, state, prealloc, start);
 		if (err)
-			extent_io_tree_panic(tree, err);
+			extent_io_tree_panic(tree, state, "split", err);
 		prealloc = NULL;
 		if (err)
 			goto out;
@@ -1430,7 +1455,7 @@ hit_next:
 		inserted_state = insert_state(tree, prealloc, bits, NULL);
 		if (IS_ERR(inserted_state)) {
 			err = PTR_ERR(inserted_state);
-			extent_io_tree_panic(tree, err);
+			extent_io_tree_panic(tree, prealloc, "insert", err);
 		}
 		cache_state(inserted_state, cached_state);
 		if (inserted_state == prealloc)
@@ -1453,7 +1478,7 @@ hit_next:
 
 		err = split_state(tree, state, prealloc, end + 1);
 		if (err)
-			extent_io_tree_panic(tree, err);
+			extent_io_tree_panic(tree, state, "split", err);
 
 		set_state_bits(tree, prealloc, bits, NULL);
 		cache_state(prealloc, cached_state);
diff --git a/fs/btrfs/extent-io-tree.h b/fs/btrfs/extent-io-tree.h
index 5602b0137fcd..ebe6390d65e9 100644
--- a/fs/btrfs/extent-io-tree.h
+++ b/fs/btrfs/extent-io-tree.h
@@ -87,9 +87,17 @@ enum {
 
 struct extent_io_tree {
 	struct rb_root state;
-	struct btrfs_fs_info *fs_info;
-	/* Inode associated with this tree, or NULL. */
-	struct btrfs_inode *inode;
+	/*
+	 * The fs_info is needed for trace points, a tree attached to an inode
+	 * needs the inode.
+	 *
+	 * owner == IO_TREE_INODE_IO - then inode is valid and fs_info can be
+	 *                             accessed as inode->root->fs_info
+	 */
+	union {
+		struct btrfs_fs_info *fs_info;
+		struct btrfs_inode *inode;
+	};
 
 	/* Who owns this io tree, should be one of IO_TREE_* */
 	u8 owner;
@@ -112,6 +120,10 @@ struct extent_state {
 #endif
 };
 
+struct btrfs_inode *extent_io_tree_to_inode(struct extent_io_tree *tree);
+const struct btrfs_inode *extent_io_tree_to_inode_const(const struct extent_io_tree *tree);
+const struct btrfs_fs_info *extent_io_tree_to_fs_info(const struct extent_io_tree *tree);
+
 void extent_io_tree_init(struct btrfs_fs_info *fs_info,
 			 struct extent_io_tree *tree, unsigned int owner);
 void extent_io_tree_release(struct extent_io_tree *tree);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index c8e5b4715b49..f396aba92c57 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -102,7 +102,8 @@ int btrfs_lookup_data_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len)
  */
 int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
 			     struct btrfs_fs_info *fs_info, u64 bytenr,
-			     u64 offset, int metadata, u64 *refs, u64 *flags)
+			     u64 offset, int metadata, u64 *refs, u64 *flags,
+			     u64 *owning_root)
 {
 	struct btrfs_root *extent_root;
 	struct btrfs_delayed_ref_head *head;
@@ -114,6 +115,7 @@ int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
 	u32 item_size;
 	u64 num_refs;
 	u64 extent_flags;
+	u64 owner = 0;
 	int ret;
 
 	/*
@@ -167,6 +169,8 @@ search_again:
 					    struct btrfs_extent_item);
 			num_refs = btrfs_extent_refs(leaf, ei);
 			extent_flags = btrfs_extent_flags(leaf, ei);
+			owner = btrfs_get_extent_owner_root(fs_info, leaf,
+							    path->slots[0]);
 		} else {
 			ret = -EUCLEAN;
 			btrfs_err(fs_info,
@@ -226,6 +230,8 @@ out:
 		*refs = num_refs;
 	if (flags)
 		*flags = extent_flags;
+	if (owning_root)
+		*owning_root = owner;
 out_free:
 	btrfs_free_path(path);
 	return ret;
@@ -1541,6 +1547,23 @@ out:
 	return ret;
 }
 
+static void free_head_ref_squota_rsv(struct btrfs_fs_info *fs_info,
+				     struct btrfs_delayed_ref_head *href)
+{
+	u64 root = href->owning_root;
+
+	/*
+	 * Don't check must_insert_reserved, as this is called from contexts
+	 * where it has already been unset.
+	 */
+	if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_SIMPLE ||
+	    !href->is_data || !is_fstree(root))
+		return;
+
+	btrfs_qgroup_free_refroot(fs_info, root, href->reserved_bytes,
+				  BTRFS_QGROUP_RSV_DATA);
+}
+
 static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
 				struct btrfs_delayed_ref_head *href,
 				struct btrfs_delayed_ref_node *node,
@@ -1563,7 +1586,6 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
 		struct btrfs_squota_delta delta = {
 			.root = href->owning_root,
 			.num_bytes = node->num_bytes,
-			.rsv_bytes = href->reserved_bytes,
 			.is_data = true,
 			.is_inc	= true,
 			.generation = trans->transid,
@@ -1580,11 +1602,9 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
 						 flags, ref->objectid,
 						 ref->offset, &key,
 						 node->ref_mod, href->owning_root);
+		free_head_ref_squota_rsv(trans->fs_info, href);
 		if (!ret)
 			ret = btrfs_record_squota_delta(trans->fs_info, &delta);
-		else
-			btrfs_qgroup_free_refroot(trans->fs_info, delta.root,
-						  delta.rsv_bytes, BTRFS_QGROUP_RSV_DATA);
 	} else if (node->action == BTRFS_ADD_DELAYED_REF) {
 		ret = __btrfs_inc_extent_ref(trans, node, parent, ref->root,
 					     ref->objectid, ref->offset,
@@ -1736,7 +1756,6 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 		struct btrfs_squota_delta delta = {
 			.root = href->owning_root,
 			.num_bytes = fs_info->nodesize,
-			.rsv_bytes = 0,
 			.is_data = false,
 			.is_inc = true,
 			.generation = trans->transid,
@@ -1768,8 +1787,10 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans,
 	int ret = 0;
 
 	if (TRANS_ABORTED(trans)) {
-		if (insert_reserved)
+		if (insert_reserved) {
 			btrfs_pin_extent(trans, node->bytenr, node->num_bytes, 1);
+			free_head_ref_squota_rsv(trans->fs_info, href);
+		}
 		return 0;
 	}
 
@@ -1865,6 +1886,8 @@ u64 btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
 				  struct btrfs_delayed_ref_root *delayed_refs,
 				  struct btrfs_delayed_ref_head *head)
 {
+	u64 ret = 0;
+
 	/*
 	 * We had csum deletions accounted for in our delayed refs rsv, we need
 	 * to drop the csum leaves for this update from our delayed_refs_rsv.
@@ -1879,14 +1902,13 @@ u64 btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
 
 		btrfs_delayed_refs_rsv_release(fs_info, 0, nr_csums);
 
-		return btrfs_calc_delayed_ref_csum_bytes(fs_info, nr_csums);
+		ret = btrfs_calc_delayed_ref_csum_bytes(fs_info, nr_csums);
 	}
-	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE &&
-	    head->must_insert_reserved && head->is_data)
-		btrfs_qgroup_free_refroot(fs_info, head->owning_root,
-					  head->reserved_bytes, BTRFS_QGROUP_RSV_DATA);
+	/* must_insert_reserved can be set only if we didn't run the head ref. */
+	if (head->must_insert_reserved)
+		free_head_ref_squota_rsv(fs_info, head);
 
-	return 0;
+	return ret;
 }
 
 static int cleanup_ref_head(struct btrfs_trans_handle *trans,
@@ -2027,6 +2049,12 @@ static int btrfs_run_delayed_refs_for_head(struct btrfs_trans_handle *trans,
 		 * spin lock.
 		 */
 		must_insert_reserved = locked_ref->must_insert_reserved;
+		/*
+		 * Unsetting this on the head ref relinquishes ownership of
+		 * the rsv_bytes, so it is critical that every possible code
+		 * path from here forward frees all reserves including qgroup
+		 * reserve.
+		 */
 		locked_ref->must_insert_reserved = false;
 
 		extent_op = locked_ref->extent_op;
@@ -3286,7 +3314,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 		struct btrfs_squota_delta delta = {
 			.root = delayed_ref_root,
 			.num_bytes = num_bytes,
-			.rsv_bytes = 0,
 			.is_data = is_data,
 			.is_inc = false,
 			.generation = btrfs_extent_generation(leaf, ei),
@@ -3420,6 +3447,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_ref generic_ref = { 0 };
+	struct btrfs_block_group *bg;
 	int ret;
 
 	btrfs_init_generic_ref(&generic_ref, BTRFS_DROP_DELAYED_REF,
@@ -3433,67 +3461,64 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 		BUG_ON(ret); /* -ENOMEM */
 	}
 
-	if (last_ref && btrfs_header_generation(buf) == trans->transid) {
-		struct btrfs_block_group *cache;
-		bool must_pin = false;
-
-		if (root_id != BTRFS_TREE_LOG_OBJECTID) {
-			ret = check_ref_cleanup(trans, buf->start);
-			if (!ret) {
-				btrfs_redirty_list_add(trans->transaction, buf);
-				goto out;
-			}
-		}
+	if (!last_ref)
+		return;
 
-		cache = btrfs_lookup_block_group(fs_info, buf->start);
+	if (btrfs_header_generation(buf) != trans->transid)
+		goto out;
 
-		if (btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN)) {
-			pin_down_extent(trans, cache, buf->start, buf->len, 1);
-			btrfs_put_block_group(cache);
+	if (root_id != BTRFS_TREE_LOG_OBJECTID) {
+		ret = check_ref_cleanup(trans, buf->start);
+		if (!ret)
 			goto out;
-		}
+	}
 
-		/*
-		 * If there are tree mod log users we may have recorded mod log
-		 * operations for this node.  If we re-allocate this node we
-		 * could replay operations on this node that happened when it
-		 * existed in a completely different root.  For example if it
-		 * was part of root A, then was reallocated to root B, and we
-		 * are doing a btrfs_old_search_slot(root b), we could replay
-		 * operations that happened when the block was part of root A,
-		 * giving us an inconsistent view of the btree.
-		 *
-		 * We are safe from races here because at this point no other
-		 * node or root points to this extent buffer, so if after this
-		 * check a new tree mod log user joins we will not have an
-		 * existing log of operations on this node that we have to
-		 * contend with.
-		 */
-		if (test_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags))
-			must_pin = true;
+	bg = btrfs_lookup_block_group(fs_info, buf->start);
 
-		if (must_pin || btrfs_is_zoned(fs_info)) {
-			btrfs_redirty_list_add(trans->transaction, buf);
-			pin_down_extent(trans, cache, buf->start, buf->len, 1);
-			btrfs_put_block_group(cache);
-			goto out;
-		}
+	if (btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN)) {
+		pin_down_extent(trans, bg, buf->start, buf->len, 1);
+		btrfs_put_block_group(bg);
+		goto out;
+	}
 
-		WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags));
+	/*
+	 * If there are tree mod log users we may have recorded mod log
+	 * operations for this node.  If we re-allocate this node we
+	 * could replay operations on this node that happened when it
+	 * existed in a completely different root.  For example if it
+	 * was part of root A, then was reallocated to root B, and we
+	 * are doing a btrfs_old_search_slot(root b), we could replay
+	 * operations that happened when the block was part of root A,
+	 * giving us an inconsistent view of the btree.
+	 *
+	 * We are safe from races here because at this point no other
+	 * node or root points to this extent buffer, so if after this
+	 * check a new tree mod log user joins we will not have an
+	 * existing log of operations on this node that we have to
+	 * contend with.
+	 */
 
-		btrfs_add_free_space(cache, buf->start, buf->len);
-		btrfs_free_reserved_bytes(cache, buf->len, 0);
-		btrfs_put_block_group(cache);
-		trace_btrfs_reserved_extent_free(fs_info, buf->start, buf->len);
+	if (test_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags)
+		     || btrfs_is_zoned(fs_info)) {
+		pin_down_extent(trans, bg, buf->start, buf->len, 1);
+		btrfs_put_block_group(bg);
+		goto out;
 	}
+
+	WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags));
+
+	btrfs_add_free_space(bg, buf->start, buf->len);
+	btrfs_free_reserved_bytes(bg, buf->len, 0);
+	btrfs_put_block_group(bg);
+	trace_btrfs_reserved_extent_free(fs_info, buf->start, buf->len);
+
 out:
-	if (last_ref) {
-		/*
-		 * Deleting the buffer, clear the corrupt flag since it doesn't
-		 * matter anymore.
-		 */
-		clear_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags);
-	}
+
+	/*
+	 * Deleting the buffer, clear the corrupt flag since it doesn't
+	 * matter anymore.
+	 */
+	clear_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags);
 }
 
 /* Can return -ENOMEM */
@@ -4931,7 +4956,6 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
 		.root = root_objectid,
 		.num_bytes = ins->offset,
 		.generation = trans->transid,
-		.rsv_bytes = 0,
 		.is_data = true,
 		.is_inc = true,
 	};
@@ -5035,7 +5059,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	__btrfs_tree_lock(buf, nest);
 	btrfs_clear_buffer_dirty(trans, buf);
 	clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
-	clear_bit(EXTENT_BUFFER_NO_CHECK, &buf->bflags);
+	clear_bit(EXTENT_BUFFER_ZONED_ZEROOUT, &buf->bflags);
 
 	set_extent_buffer_uptodate(buf);
 
@@ -5234,7 +5258,7 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans,
 		/* We don't lock the tree block, it's OK to be racy here */
 		ret = btrfs_lookup_extent_info(trans, fs_info, bytenr,
 					       wc->level - 1, 1, &refs,
-					       &flags);
+					       &flags, NULL);
 		/* We don't care about errors in readahead. */
 		if (ret < 0)
 			continue;
@@ -5301,7 +5325,8 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans,
 		ret = btrfs_lookup_extent_info(trans, fs_info,
 					       eb->start, level, 1,
 					       &wc->refs[level],
-					       &wc->flags[level]);
+					       &wc->flags[level],
+					       NULL);
 		BUG_ON(ret == -ENOMEM);
 		if (ret)
 			return ret;
@@ -5391,6 +5416,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 	u64 bytenr;
 	u64 generation;
 	u64 parent;
+	u64 owner_root = 0;
 	struct btrfs_tree_parent_check check = { 0 };
 	struct btrfs_key key;
 	struct btrfs_ref ref = { 0 };
@@ -5434,7 +5460,8 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_lookup_extent_info(trans, fs_info, bytenr, level - 1, 1,
 				       &wc->refs[level - 1],
-				       &wc->flags[level - 1]);
+				       &wc->flags[level - 1],
+				       &owner_root);
 	if (ret < 0)
 		goto out_unlock;
 
@@ -5567,8 +5594,7 @@ skip:
 		find_next_key(path, level, &wc->drop_progress);
 
 		btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, bytenr,
-				       fs_info->nodesize, parent,
-				       btrfs_header_owner(next));
+				       fs_info->nodesize, parent, owner_root);
 		btrfs_init_tree_ref(&ref, level - 1, root->root_key.objectid,
 				    0, false);
 		ret = btrfs_free_extent(trans, &ref);
@@ -5635,7 +5661,8 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 			ret = btrfs_lookup_extent_info(trans, fs_info,
 						       eb->start, level, 1,
 						       &wc->refs[level],
-						       &wc->flags[level]);
+						       &wc->flags[level],
+						       NULL);
 			if (ret < 0) {
 				btrfs_tree_unlock_rw(eb, path->locks[level]);
 				path->locks[level] = 0;
@@ -5880,7 +5907,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
 			ret = btrfs_lookup_extent_info(trans, fs_info,
 						path->nodes[level]->start,
 						level, 1, &wc->refs[level],
-						&wc->flags[level]);
+						&wc->flags[level], NULL);
 			if (ret < 0) {
 				err = ret;
 				goto out_end_trans;
diff --git a/fs/btrfs/extent-tree.h b/fs/btrfs/extent-tree.h
index 0716f65d9753..2e066035ccee 100644
--- a/fs/btrfs/extent-tree.h
+++ b/fs/btrfs/extent-tree.h
@@ -99,7 +99,8 @@ u64 btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
 int btrfs_lookup_data_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len);
 int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
 			     struct btrfs_fs_info *fs_info, u64 bytenr,
-			     u64 offset, int metadata, u64 *refs, u64 *flags);
+			     u64 offset, int metadata, u64 *refs, u64 *flags,
+			     u64 *owner_root);
 int btrfs_pin_extent(struct btrfs_trans_handle *trans, u64 bytenr, u64 num,
 		     int reserved);
 int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 03cef28d9e37..cfd2967f04a2 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -184,22 +184,23 @@ static void process_one_page(struct btrfs_fs_info *fs_info,
 			     struct page *page, struct page *locked_page,
 			     unsigned long page_ops, u64 start, u64 end)
 {
+	struct folio *folio = page_folio(page);
 	u32 len;
 
 	ASSERT(end + 1 - start != 0 && end + 1 - start < U32_MAX);
 	len = end + 1 - start;
 
 	if (page_ops & PAGE_SET_ORDERED)
-		btrfs_page_clamp_set_ordered(fs_info, page, start, len);
+		btrfs_folio_clamp_set_ordered(fs_info, folio, start, len);
 	if (page_ops & PAGE_START_WRITEBACK) {
-		btrfs_page_clamp_clear_dirty(fs_info, page, start, len);
-		btrfs_page_clamp_set_writeback(fs_info, page, start, len);
+		btrfs_folio_clamp_clear_dirty(fs_info, folio, start, len);
+		btrfs_folio_clamp_set_writeback(fs_info, folio, start, len);
 	}
 	if (page_ops & PAGE_END_WRITEBACK)
-		btrfs_page_clamp_clear_writeback(fs_info, page, start, len);
+		btrfs_folio_clamp_clear_writeback(fs_info, folio, start, len);
 
 	if (page != locked_page && (page_ops & PAGE_UNLOCK))
-		btrfs_page_end_writer_lock(fs_info, page, start, len);
+		btrfs_folio_end_writer_lock(fs_info, folio, start, len);
 }
 
 static void __process_pages_contig(struct address_space *mapping,
@@ -271,19 +272,20 @@ static noinline int lock_delalloc_pages(struct inode *inode,
 			goto out;
 
 		for (i = 0; i < found_folios; i++) {
-			struct page *page = &fbatch.folios[i]->page;
+			struct folio *folio = fbatch.folios[i];
+			struct page *page = folio_page(folio, 0);
 			u32 len = end + 1 - start;
 
 			if (page == locked_page)
 				continue;
 
-			if (btrfs_page_start_writer_lock(fs_info, page, start,
-							 len))
+			if (btrfs_folio_start_writer_lock(fs_info, folio, start,
+							  len))
 				goto out;
 
 			if (!PageDirty(page) || page->mapping != mapping) {
-				btrfs_page_end_writer_lock(fs_info, page, start,
-							   len);
+				btrfs_folio_end_writer_lock(fs_info, folio, start,
+							    len);
 				goto out;
 			}
 
@@ -432,60 +434,65 @@ static bool btrfs_verify_page(struct page *page, u64 start)
 static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
+	struct folio *folio = page_folio(page);
 
 	ASSERT(page_offset(page) <= start &&
 	       start + len <= page_offset(page) + PAGE_SIZE);
 
 	if (uptodate && btrfs_verify_page(page, start))
-		btrfs_page_set_uptodate(fs_info, page, start, len);
+		btrfs_folio_set_uptodate(fs_info, folio, start, len);
 	else
-		btrfs_page_clear_uptodate(fs_info, page, start, len);
+		btrfs_folio_clear_uptodate(fs_info, folio, start, len);
 
-	if (!btrfs_is_subpage(fs_info, page))
+	if (!btrfs_is_subpage(fs_info, page->mapping))
 		unlock_page(page);
 	else
-		btrfs_subpage_end_reader(fs_info, page, start, len);
+		btrfs_subpage_end_reader(fs_info, folio, start, len);
 }
 
 /*
- * after a writepage IO is done, we need to:
- * clear the uptodate bits on error
- * clear the writeback bits in the extent tree for this IO
- * end_page_writeback if the page has no more pending IO
+ * After a write IO is done, we need to:
+ *
+ * - clear the uptodate bits on error
+ * - clear the writeback bits in the extent tree for the range
+ * - filio_end_writeback()  if there is no more pending io for the folio
  *
  * Scheduling is not allowed, so the extent state tree is expected
  * to have one and only one object corresponding to this IO.
  */
-static void end_bio_extent_writepage(struct btrfs_bio *bbio)
+static void end_bbio_data_write(struct btrfs_bio *bbio)
 {
 	struct bio *bio = &bbio->bio;
 	int error = blk_status_to_errno(bio->bi_status);
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
+	struct folio_iter fi;
 
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		struct page *page = bvec->bv_page;
-		struct inode *inode = page->mapping->host;
+	bio_for_each_folio_all(fi, bio) {
+		struct folio *folio = fi.folio;
+		struct inode *inode = folio->mapping->host;
 		struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 		const u32 sectorsize = fs_info->sectorsize;
-		u64 start = page_offset(page) + bvec->bv_offset;
-		u32 len = bvec->bv_len;
+		u64 start = folio_pos(folio) + fi.offset;
+		u32 len = fi.length;
+
+		/* Only order 0 (single page) folios are allowed for data. */
+		ASSERT(folio_order(folio) == 0);
 
 		/* Our read/write should always be sector aligned. */
-		if (!IS_ALIGNED(bvec->bv_offset, sectorsize))
+		if (!IS_ALIGNED(fi.offset, sectorsize))
 			btrfs_err(fs_info,
-		"partial page write in btrfs with offset %u and length %u",
-				  bvec->bv_offset, bvec->bv_len);
-		else if (!IS_ALIGNED(bvec->bv_len, sectorsize))
+		"partial page write in btrfs with offset %zu and length %zu",
+				  fi.offset, fi.length);
+		else if (!IS_ALIGNED(fi.length, sectorsize))
 			btrfs_info(fs_info,
-		"incomplete page write with offset %u and length %u",
-				   bvec->bv_offset, bvec->bv_len);
+		"incomplete page write with offset %zu and length %zu",
+				   fi.offset, fi.length);
 
-		btrfs_finish_ordered_extent(bbio->ordered, page, start, len, !error);
+		btrfs_finish_ordered_extent(bbio->ordered,
+				folio_page(folio, 0), start, len, !error);
 		if (error)
-			mapping_set_error(page->mapping, error);
-		btrfs_page_clear_writeback(fs_info, page, start, len);
+			mapping_set_error(folio->mapping, error);
+		btrfs_folio_clear_writeback(fs_info, folio, start, len);
 	}
 
 	bio_put(bio);
@@ -562,98 +569,102 @@ update:
 
 static void begin_page_read(struct btrfs_fs_info *fs_info, struct page *page)
 {
-	ASSERT(PageLocked(page));
-	if (!btrfs_is_subpage(fs_info, page))
+	struct folio *folio = page_folio(page);
+
+	ASSERT(folio_test_locked(folio));
+	if (!btrfs_is_subpage(fs_info, folio->mapping))
 		return;
 
-	ASSERT(PagePrivate(page));
-	btrfs_subpage_start_reader(fs_info, page, page_offset(page), PAGE_SIZE);
+	ASSERT(folio_test_private(folio));
+	btrfs_subpage_start_reader(fs_info, folio, page_offset(page), PAGE_SIZE);
 }
 
 /*
- * after a readpage IO is done, we need to:
- * clear the uptodate bits on error
- * set the uptodate bits if things worked
- * set the page up to date if all extents in the tree are uptodate
- * clear the lock bit in the extent tree
- * unlock the page if there are no other extents locked for it
+ * After a data read IO is done, we need to:
+ *
+ * - clear the uptodate bits on error
+ * - set the uptodate bits if things worked
+ * - set the folio up to date if all extents in the tree are uptodate
+ * - clear the lock bit in the extent tree
+ * - unlock the folio if there are no other extents locked for it
  *
  * Scheduling is not allowed, so the extent state tree is expected
  * to have one and only one object corresponding to this IO.
  */
-static void end_bio_extent_readpage(struct btrfs_bio *bbio)
+static void end_bbio_data_read(struct btrfs_bio *bbio)
 {
 	struct bio *bio = &bbio->bio;
-	struct bio_vec *bvec;
 	struct processed_extent processed = { 0 };
+	struct folio_iter fi;
 	/*
 	 * The offset to the beginning of a bio, since one bio can never be
 	 * larger than UINT_MAX, u32 here is enough.
 	 */
 	u32 bio_offset = 0;
-	struct bvec_iter_all iter_all;
 
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
-	bio_for_each_segment_all(bvec, bio, iter_all) {
+	bio_for_each_folio_all(fi, &bbio->bio) {
 		bool uptodate = !bio->bi_status;
-		struct page *page = bvec->bv_page;
-		struct inode *inode = page->mapping->host;
+		struct folio *folio = fi.folio;
+		struct inode *inode = folio->mapping->host;
 		struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 		const u32 sectorsize = fs_info->sectorsize;
 		u64 start;
 		u64 end;
 		u32 len;
 
+		/* For now only order 0 folios are supported for data. */
+		ASSERT(folio_order(folio) == 0);
 		btrfs_debug(fs_info,
-			"end_bio_extent_readpage: bi_sector=%llu, err=%d, mirror=%u",
-			bio->bi_iter.bi_sector, bio->bi_status,
+			"%s: bi_sector=%llu, err=%d, mirror=%u",
+			__func__, bio->bi_iter.bi_sector, bio->bi_status,
 			bbio->mirror_num);
 
 		/*
 		 * We always issue full-sector reads, but if some block in a
-		 * page fails to read, blk_update_request() will advance
+		 * folio fails to read, blk_update_request() will advance
 		 * bv_offset and adjust bv_len to compensate.  Print a warning
 		 * for unaligned offsets, and an error if they don't add up to
 		 * a full sector.
 		 */
-		if (!IS_ALIGNED(bvec->bv_offset, sectorsize))
+		if (!IS_ALIGNED(fi.offset, sectorsize))
 			btrfs_err(fs_info,
-		"partial page read in btrfs with offset %u and length %u",
-				  bvec->bv_offset, bvec->bv_len);
-		else if (!IS_ALIGNED(bvec->bv_offset + bvec->bv_len,
-				     sectorsize))
+		"partial page read in btrfs with offset %zu and length %zu",
+				  fi.offset, fi.length);
+		else if (!IS_ALIGNED(fi.offset + fi.length, sectorsize))
 			btrfs_info(fs_info,
-		"incomplete page read with offset %u and length %u",
-				   bvec->bv_offset, bvec->bv_len);
+		"incomplete page read with offset %zu and length %zu",
+				   fi.offset, fi.length);
 
-		start = page_offset(page) + bvec->bv_offset;
-		end = start + bvec->bv_len - 1;
-		len = bvec->bv_len;
+		start = folio_pos(folio) + fi.offset;
+		end = start + fi.length - 1;
+		len = fi.length;
 
 		if (likely(uptodate)) {
 			loff_t i_size = i_size_read(inode);
-			pgoff_t end_index = i_size >> PAGE_SHIFT;
+			pgoff_t end_index = i_size >> folio_shift(folio);
 
 			/*
 			 * Zero out the remaining part if this range straddles
 			 * i_size.
 			 *
-			 * Here we should only zero the range inside the bvec,
+			 * Here we should only zero the range inside the folio,
 			 * not touch anything else.
 			 *
 			 * NOTE: i_size is exclusive while end is inclusive.
 			 */
-			if (page->index == end_index && i_size <= end) {
-				u32 zero_start = max(offset_in_page(i_size),
-						     offset_in_page(start));
+			if (folio_index(folio) == end_index && i_size <= end) {
+				u32 zero_start = max(offset_in_folio(folio, i_size),
+						     offset_in_folio(folio, start));
+				u32 zero_len = offset_in_folio(folio, end) + 1 -
+					       zero_start;
 
-				zero_user_segment(page, zero_start,
-						  offset_in_page(end) + 1);
+				folio_zero_range(folio, zero_start, zero_len);
 			}
 		}
 
 		/* Update page status and unlock. */
-		end_page_read(page, uptodate, start, len);
+		end_page_read(folio_page(folio, 0), uptodate, start, len);
 		endio_readpage_release_extent(&processed, BTRFS_I(inode),
 					      start, end, uptodate);
 
@@ -672,19 +683,22 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio)
  * @nr_pages:   number of pages to allocate
  * @page_array: the array to fill with pages; any existing non-null entries in
  * 		the array will be skipped
+ * @extra_gfp:	the extra GFP flags for the allocation.
  *
  * Return: 0        if all pages were able to be allocated;
- *         -ENOMEM  otherwise, and the caller is responsible for freeing all
- *                  non-null page pointers in the array.
+ *         -ENOMEM  otherwise, the partially allocated pages would be freed and
+ *                  the array slots zeroed
  */
-int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array)
+int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array,
+			   gfp_t extra_gfp)
 {
 	unsigned int allocated;
 
 	for (allocated = 0; allocated < nr_pages;) {
 		unsigned int last = allocated;
 
-		allocated = alloc_pages_bulk_array(GFP_NOFS, nr_pages, page_array);
+		allocated = alloc_pages_bulk_array(GFP_NOFS | extra_gfp,
+						   nr_pages, page_array);
 
 		if (allocated == nr_pages)
 			return 0;
@@ -694,14 +708,39 @@ int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array)
 		 * though alloc_pages_bulk_array() falls back to alloc_page()
 		 * if  it could not bulk-allocate. So we must be out of memory.
 		 */
-		if (allocated == last)
+		if (allocated == last) {
+			for (int i = 0; i < allocated; i++) {
+				__free_page(page_array[i]);
+				page_array[i] = NULL;
+			}
 			return -ENOMEM;
+		}
 
 		memalloc_retry_wait(GFP_NOFS);
 	}
 	return 0;
 }
 
+/*
+ * Populate needed folios for the extent buffer.
+ *
+ * For now, the folios populated are always in order 0 (aka, single page).
+ */
+static int alloc_eb_folio_array(struct extent_buffer *eb, gfp_t extra_gfp)
+{
+	struct page *page_array[INLINE_EXTENT_BUFFER_PAGES] = { 0 };
+	int num_pages = num_extent_pages(eb);
+	int ret;
+
+	ret = btrfs_alloc_page_array(num_pages, page_array, extra_gfp);
+	if (ret < 0)
+		return ret;
+
+	for (int i = 0; i < num_pages; i++)
+		eb->folios[i] = page_folio(page_array[i]);
+	return 0;
+}
+
 static bool btrfs_bio_is_contig(struct btrfs_bio_ctrl *bio_ctrl,
 				struct page *page, u64 disk_bytenr,
 				unsigned int pg_offset)
@@ -856,9 +895,9 @@ static void submit_extent_page(struct btrfs_bio_ctrl *bio_ctrl,
 	} while (size);
 }
 
-static int attach_extent_buffer_page(struct extent_buffer *eb,
-				     struct page *page,
-				     struct btrfs_subpage *prealloc)
+static int attach_extent_buffer_folio(struct extent_buffer *eb,
+				      struct folio *folio,
+				      struct btrfs_subpage *prealloc)
 {
 	struct btrfs_fs_info *fs_info = eb->fs_info;
 	int ret = 0;
@@ -869,65 +908,66 @@ static int attach_extent_buffer_page(struct extent_buffer *eb,
 	 * For cloned or dummy extent buffers, their pages are not mapped and
 	 * will not race with any other ebs.
 	 */
-	if (page->mapping)
-		lockdep_assert_held(&page->mapping->private_lock);
+	if (folio->mapping)
+		lockdep_assert_held(&folio->mapping->i_private_lock);
 
 	if (fs_info->nodesize >= PAGE_SIZE) {
-		if (!PagePrivate(page))
-			attach_page_private(page, eb);
+		if (!folio_test_private(folio))
+			folio_attach_private(folio, eb);
 		else
-			WARN_ON(page->private != (unsigned long)eb);
+			WARN_ON(folio_get_private(folio) != eb);
 		return 0;
 	}
 
 	/* Already mapped, just free prealloc */
-	if (PagePrivate(page)) {
+	if (folio_test_private(folio)) {
 		btrfs_free_subpage(prealloc);
 		return 0;
 	}
 
 	if (prealloc)
 		/* Has preallocated memory for subpage */
-		attach_page_private(page, prealloc);
+		folio_attach_private(folio, prealloc);
 	else
 		/* Do new allocation to attach subpage */
-		ret = btrfs_attach_subpage(fs_info, page,
-					   BTRFS_SUBPAGE_METADATA);
+		ret = btrfs_attach_subpage(fs_info, folio, BTRFS_SUBPAGE_METADATA);
 	return ret;
 }
 
 int set_page_extent_mapped(struct page *page)
 {
+	struct folio *folio = page_folio(page);
 	struct btrfs_fs_info *fs_info;
 
 	ASSERT(page->mapping);
 
-	if (PagePrivate(page))
+	if (folio_test_private(folio))
 		return 0;
 
 	fs_info = btrfs_sb(page->mapping->host->i_sb);
 
-	if (btrfs_is_subpage(fs_info, page))
-		return btrfs_attach_subpage(fs_info, page, BTRFS_SUBPAGE_DATA);
+	if (btrfs_is_subpage(fs_info, page->mapping))
+		return btrfs_attach_subpage(fs_info, folio, BTRFS_SUBPAGE_DATA);
 
-	attach_page_private(page, (void *)EXTENT_PAGE_PRIVATE);
+	folio_attach_private(folio, (void *)EXTENT_FOLIO_PRIVATE);
 	return 0;
 }
 
 void clear_page_extent_mapped(struct page *page)
 {
+	struct folio *folio = page_folio(page);
 	struct btrfs_fs_info *fs_info;
 
 	ASSERT(page->mapping);
 
-	if (!PagePrivate(page))
+	if (!folio_test_private(folio))
 		return;
 
 	fs_info = btrfs_sb(page->mapping->host->i_sb);
-	if (btrfs_is_subpage(fs_info, page))
-		return btrfs_detach_subpage(fs_info, page);
+	if (btrfs_is_subpage(fs_info, page->mapping))
+		return btrfs_detach_subpage(fs_info, folio);
 
-	detach_page_private(page);
+	folio_detach_private(folio);
 }
 
 static struct extent_map *
@@ -996,7 +1036,7 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
 			memzero_page(page, zero_offset, iosize);
 		}
 	}
-	bio_ctrl->end_io_func = end_bio_extent_readpage;
+	bio_ctrl->end_io_func = end_bbio_data_read;
 	begin_page_read(fs_info, page);
 	while (cur <= end) {
 		enum btrfs_compression_type compress_type = BTRFS_COMPRESS_NONE;
@@ -1022,8 +1062,7 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
 		BUG_ON(extent_map_end(em) <= cur);
 		BUG_ON(end < cur);
 
-		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
-			compress_type = em->compress_type;
+		compress_type = extent_map_compression(em);
 
 		iosize = min(extent_map_end(em) - cur, end - cur + 1);
 		iosize = ALIGN(iosize, blocksize);
@@ -1032,7 +1071,7 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
 		else
 			disk_bytenr = em->block_start + extent_offset;
 		block_start = em->block_start;
-		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+		if (em->flags & EXTENT_FLAG_PREALLOC)
 			block_start = EXTENT_MAP_HOLE;
 
 		/*
@@ -1069,7 +1108,7 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
 		 * is a corner case so we prioritize correctness over
 		 * non-optimal behavior (submitting 2 bios for the same extent).
 		 */
-		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) &&
+		if (compress_type != BTRFS_COMPRESS_NONE &&
 		    prev_em_start && *prev_em_start != (u64)-1 &&
 		    *prev_em_start != em->start)
 			force_bio_submit = true;
@@ -1235,7 +1274,8 @@ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode,
 static void find_next_dirty_byte(struct btrfs_fs_info *fs_info,
 				 struct page *page, u64 *start, u64 *end)
 {
-	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
+	struct folio *folio = page_folio(page);
+	struct btrfs_subpage *subpage = folio_get_private(folio);
 	struct btrfs_subpage_info *spi = fs_info->subpage_info;
 	u64 orig_start = *start;
 	/* Declare as unsigned long so we can use bitmap ops */
@@ -1247,7 +1287,7 @@ static void find_next_dirty_byte(struct btrfs_fs_info *fs_info,
 	 * For regular sector size == page size case, since one page only
 	 * contains one sector, we return the page offset directly.
 	 */
-	if (!btrfs_is_subpage(fs_info, page)) {
+	if (!btrfs_is_subpage(fs_info, page->mapping)) {
 		*start = page_offset(page);
 		*end = page_offset(page) + PAGE_SIZE;
 		return;
@@ -1300,7 +1340,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
 		return 1;
 	}
 
-	bio_ctrl->end_io_func = end_bio_extent_writepage;
+	bio_ctrl->end_io_func = end_bbio_data_write;
 	while (cur <= end) {
 		u32 len = end - cur + 1;
 		u64 disk_bytenr;
@@ -1320,7 +1360,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
 			 * writeback the sectors with subpage dirty bits,
 			 * causing writeback without ordered extent.
 			 */
-			btrfs_page_clear_dirty(fs_info, page, cur, len);
+			btrfs_folio_clear_dirty(fs_info, page_folio(page), cur, len);
 			break;
 		}
 
@@ -1347,7 +1387,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
 		block_start = em->block_start;
 		disk_bytenr = em->block_start + extent_offset;
 
-		ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags));
+		ASSERT(!extent_map_is_compressed(em));
 		ASSERT(block_start != EXTENT_MAP_HOLE);
 		ASSERT(block_start != EXTENT_MAP_INLINE);
 
@@ -1372,7 +1412,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
 		 * So clear subpage dirty bit here so next time we won't submit
 		 * page for range already written to disk.
 		 */
-		btrfs_page_clear_dirty(fs_info, page, cur, iosize);
+		btrfs_folio_clear_dirty(fs_info, page_folio(page), cur, iosize);
 
 		submit_extent_page(bio_ctrl, disk_bytenr, page, iosize,
 				   cur - page_offset(page));
@@ -1380,7 +1420,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
 		nr++;
 	}
 
-	btrfs_page_assert_not_dirty(fs_info, page);
+	btrfs_folio_assert_not_dirty(fs_info, page_folio(page));
 	*nr_ret = nr;
 	return 0;
 
@@ -1602,24 +1642,23 @@ static struct extent_buffer *find_extent_buffer_nolock(
 	return NULL;
 }
 
-static void extent_buffer_write_end_io(struct btrfs_bio *bbio)
+static void end_bbio_meta_write(struct btrfs_bio *bbio)
 {
 	struct extent_buffer *eb = bbio->private;
 	struct btrfs_fs_info *fs_info = eb->fs_info;
 	bool uptodate = !bbio->bio.bi_status;
-	struct bvec_iter_all iter_all;
-	struct bio_vec *bvec;
+	struct folio_iter fi;
 	u32 bio_offset = 0;
 
 	if (!uptodate)
 		set_btree_ioerr(eb);
 
-	bio_for_each_segment_all(bvec, &bbio->bio, iter_all) {
+	bio_for_each_folio_all(fi, &bbio->bio) {
 		u64 start = eb->start + bio_offset;
-		struct page *page = bvec->bv_page;
-		u32 len = bvec->bv_len;
+		struct folio *folio = fi.folio;
+		u32 len = fi.length;
 
-		btrfs_page_clear_writeback(fs_info, page, start, len);
+		btrfs_folio_clear_writeback(fs_info, folio, start, len);
 		bio_offset += len;
 	}
 
@@ -1668,36 +1707,44 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb,
 
 	bbio = btrfs_bio_alloc(INLINE_EXTENT_BUFFER_PAGES,
 			       REQ_OP_WRITE | REQ_META | wbc_to_write_flags(wbc),
-			       eb->fs_info, extent_buffer_write_end_io, eb);
+			       eb->fs_info, end_bbio_meta_write, eb);
 	bbio->bio.bi_iter.bi_sector = eb->start >> SECTOR_SHIFT;
 	bio_set_dev(&bbio->bio, fs_info->fs_devices->latest_dev->bdev);
 	wbc_init_bio(wbc, &bbio->bio);
 	bbio->inode = BTRFS_I(eb->fs_info->btree_inode);
 	bbio->file_offset = eb->start;
 	if (fs_info->nodesize < PAGE_SIZE) {
-		struct page *p = eb->pages[0];
+		struct folio *folio = eb->folios[0];
+		bool ret;
 
-		lock_page(p);
-		btrfs_subpage_set_writeback(fs_info, p, eb->start, eb->len);
-		if (btrfs_subpage_clear_and_test_dirty(fs_info, p, eb->start,
+		folio_lock(folio);
+		btrfs_subpage_set_writeback(fs_info, folio, eb->start, eb->len);
+		if (btrfs_subpage_clear_and_test_dirty(fs_info, folio, eb->start,
 						       eb->len)) {
-			clear_page_dirty_for_io(p);
+			folio_clear_dirty_for_io(folio);
 			wbc->nr_to_write--;
 		}
-		__bio_add_page(&bbio->bio, p, eb->len, eb->start - page_offset(p));
-		wbc_account_cgroup_owner(wbc, p, eb->len);
-		unlock_page(p);
+		ret = bio_add_folio(&bbio->bio, folio, eb->len,
+				    eb->start - folio_pos(folio));
+		ASSERT(ret);
+		wbc_account_cgroup_owner(wbc, folio_page(folio, 0), eb->len);
+		folio_unlock(folio);
 	} else {
-		for (int i = 0; i < num_extent_pages(eb); i++) {
-			struct page *p = eb->pages[i];
-
-			lock_page(p);
-			clear_page_dirty_for_io(p);
-			set_page_writeback(p);
-			__bio_add_page(&bbio->bio, p, PAGE_SIZE, 0);
-			wbc_account_cgroup_owner(wbc, p, PAGE_SIZE);
-			wbc->nr_to_write--;
-			unlock_page(p);
+		int num_folios = num_extent_folios(eb);
+
+		for (int i = 0; i < num_folios; i++) {
+			struct folio *folio = eb->folios[i];
+			bool ret;
+
+			folio_lock(folio);
+			folio_clear_dirty_for_io(folio);
+			folio_start_writeback(folio);
+			ret = bio_add_folio(&bbio->bio, folio, folio_size(folio), 0);
+			ASSERT(ret);
+			wbc_account_cgroup_owner(wbc, folio_page(folio, 0),
+						 folio_size(folio));
+			wbc->nr_to_write -= folio_nr_pages(folio);
+			folio_unlock(folio);
 		}
 	}
 	btrfs_submit_bio(bbio, 0);
@@ -1720,6 +1767,7 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb,
 static int submit_eb_subpage(struct page *page, struct writeback_control *wbc)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
+	struct folio *folio = page_folio(page);
 	int submitted = 0;
 	u64 page_start = page_offset(page);
 	int bit_start = 0;
@@ -1727,7 +1775,7 @@ static int submit_eb_subpage(struct page *page, struct writeback_control *wbc)
 
 	/* Lock and write each dirty extent buffers in the range */
 	while (bit_start < fs_info->subpage_info->bitmap_nr_bits) {
-		struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
+		struct btrfs_subpage *subpage = folio_get_private(folio);
 		struct extent_buffer *eb;
 		unsigned long flags;
 		u64 start;
@@ -1736,16 +1784,16 @@ static int submit_eb_subpage(struct page *page, struct writeback_control *wbc)
 		 * Take private lock to ensure the subpage won't be detached
 		 * in the meantime.
 		 */
-		spin_lock(&page->mapping->private_lock);
-		if (!PagePrivate(page)) {
-			spin_unlock(&page->mapping->private_lock);
+		spin_lock(&page->mapping->i_private_lock);
+		if (!folio_test_private(folio)) {
+			spin_unlock(&page->mapping->i_private_lock);
 			break;
 		}
 		spin_lock_irqsave(&subpage->lock, flags);
 		if (!test_bit(bit_start + fs_info->subpage_info->dirty_offset,
 			      subpage->bitmaps)) {
 			spin_unlock_irqrestore(&subpage->lock, flags);
-			spin_unlock(&page->mapping->private_lock);
+			spin_unlock(&page->mapping->i_private_lock);
 			bit_start++;
 			continue;
 		}
@@ -1759,7 +1807,7 @@ static int submit_eb_subpage(struct page *page, struct writeback_control *wbc)
 		 */
 		eb = find_extent_buffer_nolock(fs_info, start);
 		spin_unlock_irqrestore(&subpage->lock, flags);
-		spin_unlock(&page->mapping->private_lock);
+		spin_unlock(&page->mapping->i_private_lock);
 
 		/*
 		 * The eb has already reached 0 refs thus find_extent_buffer()
@@ -1802,38 +1850,39 @@ static int submit_eb_page(struct page *page, struct btrfs_eb_write_context *ctx)
 {
 	struct writeback_control *wbc = ctx->wbc;
 	struct address_space *mapping = page->mapping;
+	struct folio *folio = page_folio(page);
 	struct extent_buffer *eb;
 	int ret;
 
-	if (!PagePrivate(page))
+	if (!folio_test_private(folio))
 		return 0;
 
 	if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE)
 		return submit_eb_subpage(page, wbc);
 
-	spin_lock(&mapping->private_lock);
-	if (!PagePrivate(page)) {
-		spin_unlock(&mapping->private_lock);
+	spin_lock(&mapping->i_private_lock);
+	if (!folio_test_private(folio)) {
+		spin_unlock(&mapping->i_private_lock);
 		return 0;
 	}
 
-	eb = (struct extent_buffer *)page->private;
+	eb = folio_get_private(folio);
 
 	/*
 	 * Shouldn't happen and normally this would be a BUG_ON but no point
 	 * crashing the machine for something we can survive anyway.
 	 */
 	if (WARN_ON(!eb)) {
-		spin_unlock(&mapping->private_lock);
+		spin_unlock(&mapping->i_private_lock);
 		return 0;
 	}
 
 	if (eb == ctx->eb) {
-		spin_unlock(&mapping->private_lock);
+		spin_unlock(&mapping->i_private_lock);
 		return 0;
 	}
 	ret = atomic_inc_not_zero(&eb->refs);
-	spin_unlock(&mapping->private_lock);
+	spin_unlock(&mapping->i_private_lock);
 	if (!ret)
 		return 0;
 
@@ -2196,7 +2245,7 @@ void extent_write_locked_range(struct inode *inode, struct page *locked_page,
 						       cur, cur_len, !ret);
 			mapping_set_error(page->mapping, ret);
 		}
-		btrfs_page_unlock_writer(fs_info, page, cur, cur_len);
+		btrfs_folio_unlock_writer(fs_info, page_folio(page), cur, cur_len);
 		if (ret < 0)
 			found_error = true;
 next_page:
@@ -2297,7 +2346,8 @@ static int try_release_extent_state(struct extent_io_tree *tree,
 		ret = 0;
 	} else {
 		u32 clear_bits = ~(EXTENT_LOCKED | EXTENT_NODATASUM |
-				   EXTENT_DELALLOC_NEW | EXTENT_CTLBITS);
+				   EXTENT_DELALLOC_NEW | EXTENT_CTLBITS |
+				   EXTENT_QGROUP_RESERVED);
 
 		/*
 		 * At this point we can safely clear everything except the
@@ -2346,7 +2396,7 @@ int try_release_extent_mapping(struct page *page, gfp_t mask)
 				write_unlock(&map->lock);
 				break;
 			}
-			if (test_bit(EXTENT_FLAG_PINNED, &em->flags) ||
+			if ((em->flags & EXTENT_FLAG_PINNED) ||
 			    em->start != start) {
 				write_unlock(&map->lock);
 				free_extent_map(em);
@@ -2363,7 +2413,7 @@ int try_release_extent_mapping(struct page *page, gfp_t mask)
 			 * extra reference on the em.
 			 */
 			if (list_empty(&em->list) ||
-			    test_bit(EXTENT_FLAG_LOGGING, &em->flags))
+			    (em->flags & EXTENT_FLAG_LOGGING))
 				goto remove_em;
 			/*
 			 * If it's in the list of modified extents, remove it
@@ -3052,14 +3102,14 @@ static int extent_buffer_under_io(const struct extent_buffer *eb)
 		test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
 }
 
-static bool page_range_has_eb(struct btrfs_fs_info *fs_info, struct page *page)
+static bool folio_range_has_eb(struct btrfs_fs_info *fs_info, struct folio *folio)
 {
 	struct btrfs_subpage *subpage;
 
-	lockdep_assert_held(&page->mapping->private_lock);
+	lockdep_assert_held(&folio->mapping->i_private_lock);
 
-	if (PagePrivate(page)) {
-		subpage = (struct btrfs_subpage *)page->private;
+	if (folio_test_private(folio)) {
+		subpage = folio_get_private(folio);
 		if (atomic_read(&subpage->eb_refs))
 			return true;
 		/*
@@ -3072,21 +3122,21 @@ static bool page_range_has_eb(struct btrfs_fs_info *fs_info, struct page *page)
 	return false;
 }
 
-static void detach_extent_buffer_page(struct extent_buffer *eb, struct page *page)
+static void detach_extent_buffer_folio(struct extent_buffer *eb, struct folio *folio)
 {
 	struct btrfs_fs_info *fs_info = eb->fs_info;
 	const bool mapped = !test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags);
 
 	/*
-	 * For mapped eb, we're going to change the page private, which should
-	 * be done under the private_lock.
+	 * For mapped eb, we're going to change the folio private, which should
+	 * be done under the i_private_lock.
 	 */
 	if (mapped)
-		spin_lock(&page->mapping->private_lock);
+		spin_lock(&folio->mapping->i_private_lock);
 
-	if (!PagePrivate(page)) {
+	if (!folio_test_private(folio)) {
 		if (mapped)
-			spin_unlock(&page->mapping->private_lock);
+			spin_unlock(&folio->mapping->i_private_lock);
 		return;
 	}
 
@@ -3095,66 +3145,58 @@ static void detach_extent_buffer_page(struct extent_buffer *eb, struct page *pag
 		 * We do this since we'll remove the pages after we've
 		 * removed the eb from the radix tree, so we could race
 		 * and have this page now attached to the new eb.  So
-		 * only clear page_private if it's still connected to
+		 * only clear folio if it's still connected to
 		 * this eb.
 		 */
-		if (PagePrivate(page) &&
-		    page->private == (unsigned long)eb) {
+		if (folio_test_private(folio) && folio_get_private(folio) == eb) {
 			BUG_ON(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
-			BUG_ON(PageDirty(page));
-			BUG_ON(PageWriteback(page));
-			/*
-			 * We need to make sure we haven't be attached
-			 * to a new eb.
-			 */
-			detach_page_private(page);
+			BUG_ON(folio_test_dirty(folio));
+			BUG_ON(folio_test_writeback(folio));
+			/* We need to make sure we haven't be attached to a new eb. */
+			folio_detach_private(folio);
 		}
 		if (mapped)
-			spin_unlock(&page->mapping->private_lock);
+			spin_unlock(&folio->mapping->i_private_lock);
 		return;
 	}
 
 	/*
-	 * For subpage, we can have dummy eb with page private.  In this case,
-	 * we can directly detach the private as such page is only attached to
-	 * one dummy eb, no sharing.
+	 * For subpage, we can have dummy eb with folio private attached.  In
+	 * this case, we can directly detach the private as such folio is only
+	 * attached to one dummy eb, no sharing.
 	 */
 	if (!mapped) {
-		btrfs_detach_subpage(fs_info, page);
+		btrfs_detach_subpage(fs_info, folio);
 		return;
 	}
 
-	btrfs_page_dec_eb_refs(fs_info, page);
+	btrfs_folio_dec_eb_refs(fs_info, folio);
 
 	/*
-	 * We can only detach the page private if there are no other ebs in the
+	 * We can only detach the folio private if there are no other ebs in the
 	 * page range and no unfinished IO.
 	 */
-	if (!page_range_has_eb(fs_info, page))
-		btrfs_detach_subpage(fs_info, page);
+	if (!folio_range_has_eb(fs_info, folio))
+		btrfs_detach_subpage(fs_info, folio);
 
-	spin_unlock(&page->mapping->private_lock);
+	spin_unlock(&folio->mapping->i_private_lock);
 }
 
 /* Release all pages attached to the extent buffer */
 static void btrfs_release_extent_buffer_pages(struct extent_buffer *eb)
 {
-	int i;
-	int num_pages;
-
 	ASSERT(!extent_buffer_under_io(eb));
 
-	num_pages = num_extent_pages(eb);
-	for (i = 0; i < num_pages; i++) {
-		struct page *page = eb->pages[i];
+	for (int i = 0; i < INLINE_EXTENT_BUFFER_PAGES; i++) {
+		struct folio *folio = eb->folios[i];
 
-		if (!page)
+		if (!folio)
 			continue;
 
-		detach_extent_buffer_page(eb, page);
+		detach_extent_buffer_folio(eb, folio);
 
-		/* One for when we allocated the page */
-		put_page(page);
+		/* One for when we allocated the folio. */
+		folio_put(folio);
 	}
 }
 
@@ -3192,9 +3234,8 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
 
 struct extent_buffer *btrfs_clone_extent_buffer(const struct extent_buffer *src)
 {
-	int i;
 	struct extent_buffer *new;
-	int num_pages = num_extent_pages(src);
+	int num_folios = num_extent_folios(src);
 	int ret;
 
 	new = __alloc_extent_buffer(src->fs_info, src->start, src->len);
@@ -3208,22 +3249,22 @@ struct extent_buffer *btrfs_clone_extent_buffer(const struct extent_buffer *src)
 	 */
 	set_bit(EXTENT_BUFFER_UNMAPPED, &new->bflags);
 
-	ret = btrfs_alloc_page_array(num_pages, new->pages);
+	ret = alloc_eb_folio_array(new, 0);
 	if (ret) {
 		btrfs_release_extent_buffer(new);
 		return NULL;
 	}
 
-	for (i = 0; i < num_pages; i++) {
+	for (int i = 0; i < num_folios; i++) {
+		struct folio *folio = new->folios[i];
 		int ret;
-		struct page *p = new->pages[i];
 
-		ret = attach_extent_buffer_page(new, p, NULL);
+		ret = attach_extent_buffer_folio(new, folio, NULL);
 		if (ret < 0) {
 			btrfs_release_extent_buffer(new);
 			return NULL;
 		}
-		WARN_ON(PageDirty(p));
+		WARN_ON(folio_test_dirty(folio));
 	}
 	copy_extent_buffer_full(new, src);
 	set_extent_buffer_uptodate(new);
@@ -3235,23 +3276,20 @@ struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
 						  u64 start, unsigned long len)
 {
 	struct extent_buffer *eb;
-	int num_pages;
-	int i;
+	int num_folios = 0;
 	int ret;
 
 	eb = __alloc_extent_buffer(fs_info, start, len);
 	if (!eb)
 		return NULL;
 
-	num_pages = num_extent_pages(eb);
-	ret = btrfs_alloc_page_array(num_pages, eb->pages);
+	ret = alloc_eb_folio_array(eb, 0);
 	if (ret)
 		goto err;
 
-	for (i = 0; i < num_pages; i++) {
-		struct page *p = eb->pages[i];
-
-		ret = attach_extent_buffer_page(eb, p, NULL);
+	num_folios = num_extent_folios(eb);
+	for (int i = 0; i < num_folios; i++) {
+		ret = attach_extent_buffer_folio(eb, eb->folios[i], NULL);
 		if (ret < 0)
 			goto err;
 	}
@@ -3262,10 +3300,10 @@ struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
 
 	return eb;
 err:
-	for (i = 0; i < num_pages; i++) {
-		if (eb->pages[i]) {
-			detach_extent_buffer_page(eb, eb->pages[i]);
-			__free_page(eb->pages[i]);
+	for (int i = 0; i < num_folios; i++) {
+		if (eb->folios[i]) {
+			detach_extent_buffer_folio(eb, eb->folios[i]);
+			__folio_put(eb->folios[i]);
 		}
 	}
 	__free_extent_buffer(eb);
@@ -3314,20 +3352,14 @@ static void check_buffer_tree_ref(struct extent_buffer *eb)
 	spin_unlock(&eb->refs_lock);
 }
 
-static void mark_extent_buffer_accessed(struct extent_buffer *eb,
-		struct page *accessed)
+static void mark_extent_buffer_accessed(struct extent_buffer *eb)
 {
-	int num_pages, i;
+	int num_folios= num_extent_folios(eb);
 
 	check_buffer_tree_ref(eb);
 
-	num_pages = num_extent_pages(eb);
-	for (i = 0; i < num_pages; i++) {
-		struct page *p = eb->pages[i];
-
-		if (p != accessed)
-			mark_page_accessed(p);
-	}
+	for (int i = 0; i < num_folios; i++)
+		folio_mark_accessed(eb->folios[i]);
 }
 
 struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
@@ -3355,7 +3387,7 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
 		spin_lock(&eb->refs_lock);
 		spin_unlock(&eb->refs_lock);
 	}
-	mark_extent_buffer_accessed(eb, NULL);
+	mark_extent_buffer_accessed(eb);
 	return eb;
 }
 
@@ -3404,6 +3436,7 @@ free_eb:
 static struct extent_buffer *grab_extent_buffer(
 		struct btrfs_fs_info *fs_info, struct page *page)
 {
+	struct folio *folio = page_folio(page);
 	struct extent_buffer *exists;
 
 	/*
@@ -3415,21 +3448,21 @@ static struct extent_buffer *grab_extent_buffer(
 		return NULL;
 
 	/* Page not yet attached to an extent buffer */
-	if (!PagePrivate(page))
+	if (!folio_test_private(folio))
 		return NULL;
 
 	/*
 	 * We could have already allocated an eb for this page and attached one
 	 * so lets see if we can get a ref on the existing eb, and if we can we
 	 * know it's good and we can just return that one, else we know we can
-	 * just overwrite page->private.
+	 * just overwrite folio private.
 	 */
-	exists = (struct extent_buffer *)page->private;
+	exists = folio_get_private(folio);
 	if (atomic_inc_not_zero(&exists->refs))
 		return exists;
 
 	WARN_ON(PageDirty(page));
-	detach_page_private(page);
+	folio_detach_private(folio);
 	return NULL;
 }
 
@@ -3463,19 +3496,88 @@ static int check_eb_alignment(struct btrfs_fs_info *fs_info, u64 start)
 	return 0;
 }
 
+
+/*
+ * Return 0 if eb->folios[i] is attached to btree inode successfully.
+ * Return >0 if there is already another extent buffer for the range,
+ * and @found_eb_ret would be updated.
+ * Return -EAGAIN if the filemap has an existing folio but with different size
+ * than @eb.
+ * The caller needs to free the existing folios and retry using the same order.
+ */
+static int attach_eb_folio_to_filemap(struct extent_buffer *eb, int i,
+				      struct extent_buffer **found_eb_ret)
+{
+
+	struct btrfs_fs_info *fs_info = eb->fs_info;
+	struct address_space *mapping = fs_info->btree_inode->i_mapping;
+	const unsigned long index = eb->start >> PAGE_SHIFT;
+	struct folio *existing_folio;
+	int ret;
+
+	ASSERT(found_eb_ret);
+
+	/* Caller should ensure the folio exists. */
+	ASSERT(eb->folios[i]);
+
+retry:
+	ret = filemap_add_folio(mapping, eb->folios[i], index + i,
+				GFP_NOFS | __GFP_NOFAIL);
+	if (!ret)
+		return 0;
+
+	existing_folio = filemap_lock_folio(mapping, index + i);
+	/* The page cache only exists for a very short time, just retry. */
+	if (IS_ERR(existing_folio))
+		goto retry;
+
+	/* For now, we should only have single-page folios for btree inode. */
+	ASSERT(folio_nr_pages(existing_folio) == 1);
+
+	if (folio_size(existing_folio) != folio_size(eb->folios[0])) {
+		folio_unlock(existing_folio);
+		folio_put(existing_folio);
+		return -EAGAIN;
+	}
+
+	if (fs_info->nodesize < PAGE_SIZE) {
+		/*
+		 * We're going to reuse the existing page, can drop our page
+		 * and subpage structure now.
+		 */
+		__free_page(folio_page(eb->folios[i], 0));
+		eb->folios[i] = existing_folio;
+	} else {
+		struct extent_buffer *existing_eb;
+
+		existing_eb = grab_extent_buffer(fs_info,
+						 folio_page(existing_folio, 0));
+		if (existing_eb) {
+			/* The extent buffer still exists, we can use it directly. */
+			*found_eb_ret = existing_eb;
+			folio_unlock(existing_folio);
+			folio_put(existing_folio);
+			return 1;
+		}
+		/* The extent buffer no longer exists, we can reuse the folio. */
+		__free_page(folio_page(eb->folios[i], 0));
+		eb->folios[i] = existing_folio;
+	}
+	return 0;
+}
+
 struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 					  u64 start, u64 owner_root, int level)
 {
 	unsigned long len = fs_info->nodesize;
-	int num_pages;
-	int i;
-	unsigned long index = start >> PAGE_SHIFT;
+	int num_folios;
+	int attached = 0;
 	struct extent_buffer *eb;
-	struct extent_buffer *exists = NULL;
-	struct page *p;
+	struct extent_buffer *existing_eb = NULL;
 	struct address_space *mapping = fs_info->btree_inode->i_mapping;
 	struct btrfs_subpage *prealloc = NULL;
 	u64 lockdep_owner = owner_root;
+	bool page_contig = true;
 	int uptodate = 1;
 	int ret;
 
@@ -3510,11 +3612,9 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 
 	btrfs_set_buffer_lockdep_class(lockdep_owner, eb, level);
 
-	num_pages = num_extent_pages(eb);
-
 	/*
-	 * Preallocate page->private for subpage case, so that we won't
-	 * allocate memory with private_lock nor page lock hold.
+	 * Preallocate folio private for subpage case, so that we won't
+	 * allocate memory with i_private_lock nor page lock hold.
 	 *
 	 * The memory will be freed by attach_extent_buffer_page() or freed
 	 * manually if we exit earlier.
@@ -3522,47 +3622,89 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	if (fs_info->nodesize < PAGE_SIZE) {
 		prealloc = btrfs_alloc_subpage(fs_info, BTRFS_SUBPAGE_METADATA);
 		if (IS_ERR(prealloc)) {
-			exists = ERR_CAST(prealloc);
-			goto free_eb;
+			ret = PTR_ERR(prealloc);
+			goto out;
 		}
 	}
 
-	for (i = 0; i < num_pages; i++, index++) {
-		p = find_or_create_page(mapping, index, GFP_NOFS|__GFP_NOFAIL);
-		if (!p) {
-			exists = ERR_PTR(-ENOMEM);
-			btrfs_free_subpage(prealloc);
-			goto free_eb;
+reallocate:
+	/* Allocate all pages first. */
+	ret = alloc_eb_folio_array(eb, __GFP_NOFAIL);
+	if (ret < 0) {
+		btrfs_free_subpage(prealloc);
+		goto out;
+	}
+
+	num_folios = num_extent_folios(eb);
+	/* Attach all pages to the filemap. */
+	for (int i = 0; i < num_folios; i++) {
+		struct folio *folio;
+
+		ret = attach_eb_folio_to_filemap(eb, i, &existing_eb);
+		if (ret > 0) {
+			ASSERT(existing_eb);
+			goto out;
 		}
 
-		spin_lock(&mapping->private_lock);
-		exists = grab_extent_buffer(fs_info, p);
-		if (exists) {
-			spin_unlock(&mapping->private_lock);
-			unlock_page(p);
-			put_page(p);
-			mark_extent_buffer_accessed(exists, p);
-			btrfs_free_subpage(prealloc);
-			goto free_eb;
+		/*
+		 * TODO: Special handling for a corner case where the order of
+		 * folios mismatch between the new eb and filemap.
+		 *
+		 * This happens when:
+		 *
+		 * - the new eb is using higher order folio
+		 *
+		 * - the filemap is still using 0-order folios for the range
+		 *   This can happen at the previous eb allocation, and we don't
+		 *   have higher order folio for the call.
+		 *
+		 * - the existing eb has already been freed
+		 *
+		 * In this case, we have to free the existing folios first, and
+		 * re-allocate using the same order.
+		 * Thankfully this is not going to happen yet, as we're still
+		 * using 0-order folios.
+		 */
+		if (unlikely(ret == -EAGAIN)) {
+			ASSERT(0);
+			goto reallocate;
 		}
+		attached++;
+
+		/*
+		 * Only after attach_eb_folio_to_filemap(), eb->folios[] is
+		 * reliable, as we may choose to reuse the existing page cache
+		 * and free the allocated page.
+		 */
+		folio = eb->folios[i];
+		spin_lock(&mapping->i_private_lock);
 		/* Should not fail, as we have preallocated the memory */
-		ret = attach_extent_buffer_page(eb, p, prealloc);
+		ret = attach_extent_buffer_folio(eb, folio, prealloc);
 		ASSERT(!ret);
 		/*
 		 * To inform we have extra eb under allocation, so that
-		 * detach_extent_buffer_page() won't release the page private
+		 * detach_extent_buffer_page() won't release the folio private
 		 * when the eb hasn't yet been inserted into radix tree.
 		 *
 		 * The ref will be decreased when the eb released the page, in
 		 * detach_extent_buffer_page().
 		 * Thus needs no special handling in error path.
 		 */
-		btrfs_page_inc_eb_refs(fs_info, p);
-		spin_unlock(&mapping->private_lock);
+		btrfs_folio_inc_eb_refs(fs_info, folio);
+		spin_unlock(&mapping->i_private_lock);
+
+		WARN_ON(btrfs_folio_test_dirty(fs_info, folio, eb->start, eb->len));
+
+		/*
+		 * Check if the current page is physically contiguous with previous eb
+		 * page.
+		 * At this stage, either we allocated a large folio, thus @i
+		 * would only be 0, or we fall back to per-page allocation.
+		 */
+		if (i && folio_page(eb->folios[i - 1], 0) + 1 != folio_page(folio, 0))
+			page_contig = false;
 
-		WARN_ON(btrfs_page_test_dirty(fs_info, p, eb->start, eb->len));
-		eb->pages[i] = p;
-		if (!btrfs_page_test_uptodate(fs_info, p, eb->start, eb->len))
+		if (!btrfs_folio_test_uptodate(fs_info, folio, eb->start, eb->len))
 			uptodate = 0;
 
 		/*
@@ -3575,12 +3717,13 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	}
 	if (uptodate)
 		set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
+	/* All pages are physically contiguous, can skip cross page handling. */
+	if (page_contig)
+		eb->addr = folio_address(eb->folios[0]) + offset_in_page(eb->start);
 again:
 	ret = radix_tree_preload(GFP_NOFS);
-	if (ret) {
-		exists = ERR_PTR(ret);
-		goto free_eb;
-	}
+	if (ret)
+		goto out;
 
 	spin_lock(&fs_info->buffer_lock);
 	ret = radix_tree_insert(&fs_info->buffer_radix,
@@ -3588,9 +3731,10 @@ again:
 	spin_unlock(&fs_info->buffer_lock);
 	radix_tree_preload_end();
 	if (ret == -EEXIST) {
-		exists = find_extent_buffer(fs_info, start);
-		if (exists)
-			goto free_eb;
+		ret = 0;
+		existing_eb = find_extent_buffer(fs_info, start);
+		if (existing_eb)
+			goto out;
 		else
 			goto again;
 	}
@@ -3603,19 +3747,46 @@ again:
 	 * btree_release_folio will correctly detect that a page belongs to a
 	 * live buffer and won't free them prematurely.
 	 */
-	for (i = 0; i < num_pages; i++)
-		unlock_page(eb->pages[i]);
+	for (int i = 0; i < num_folios; i++)
+		unlock_page(folio_page(eb->folios[i], 0));
 	return eb;
 
-free_eb:
+out:
 	WARN_ON(!atomic_dec_and_test(&eb->refs));
-	for (i = 0; i < num_pages; i++) {
-		if (eb->pages[i])
-			unlock_page(eb->pages[i]);
+
+	/*
+	 * Any attached folios need to be detached before we unlock them.  This
+	 * is because when we're inserting our new folios into the mapping, and
+	 * then attaching our eb to that folio.  If we fail to insert our folio
+	 * we'll lookup the folio for that index, and grab that EB.  We do not
+	 * want that to grab this eb, as we're getting ready to free it.  So we
+	 * have to detach it first and then unlock it.
+	 *
+	 * We have to drop our reference and NULL it out here because in the
+	 * subpage case detaching does a btrfs_folio_dec_eb_refs() for our eb.
+	 * Below when we call btrfs_release_extent_buffer() we will call
+	 * detach_extent_buffer_folio() on our remaining pages in the !subpage
+	 * case.  If we left eb->folios[i] populated in the subpage case we'd
+	 * double put our reference and be super sad.
+	 */
+	for (int i = 0; i < attached; i++) {
+		ASSERT(eb->folios[i]);
+		detach_extent_buffer_folio(eb, eb->folios[i]);
+		unlock_page(folio_page(eb->folios[i], 0));
+		folio_put(eb->folios[i]);
+		eb->folios[i] = NULL;
 	}
+	/*
+	 * Now all pages of that extent buffer is unmapped, set UNMAPPED flag,
+	 * so it can be cleaned up without utlizing page->mapping.
+	 */
+	set_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags);
 
 	btrfs_release_extent_buffer(eb);
-	return exists;
+	if (ret < 0)
+		return ERR_PTR(ret);
+	ASSERT(existing_eb);
+	return existing_eb;
 }
 
 static inline void btrfs_release_extent_buffer_rcu(struct rcu_head *head)
@@ -3707,31 +3878,30 @@ void free_extent_buffer_stale(struct extent_buffer *eb)
 	release_extent_buffer(eb);
 }
 
-static void btree_clear_page_dirty(struct page *page)
+static void btree_clear_folio_dirty(struct folio *folio)
 {
-	ASSERT(PageDirty(page));
-	ASSERT(PageLocked(page));
-	clear_page_dirty_for_io(page);
-	xa_lock_irq(&page->mapping->i_pages);
-	if (!PageDirty(page))
-		__xa_clear_mark(&page->mapping->i_pages,
-				page_index(page), PAGECACHE_TAG_DIRTY);
-	xa_unlock_irq(&page->mapping->i_pages);
+	ASSERT(folio_test_dirty(folio));
+	ASSERT(folio_test_locked(folio));
+	folio_clear_dirty_for_io(folio);
+	xa_lock_irq(&folio->mapping->i_pages);
+	if (!folio_test_dirty(folio))
+		__xa_clear_mark(&folio->mapping->i_pages,
+				folio_index(folio), PAGECACHE_TAG_DIRTY);
+	xa_unlock_irq(&folio->mapping->i_pages);
 }
 
 static void clear_subpage_extent_buffer_dirty(const struct extent_buffer *eb)
 {
 	struct btrfs_fs_info *fs_info = eb->fs_info;
-	struct page *page = eb->pages[0];
+	struct folio *folio = eb->folios[0];
 	bool last;
 
-	/* btree_clear_page_dirty() needs page locked */
-	lock_page(page);
-	last = btrfs_subpage_clear_and_test_dirty(fs_info, page, eb->start,
-						  eb->len);
+	/* btree_clear_folio_dirty() needs page locked. */
+	folio_lock(folio);
+	last = btrfs_subpage_clear_and_test_dirty(fs_info, folio, eb->start, eb->len);
 	if (last)
-		btree_clear_page_dirty(page);
-	unlock_page(page);
+		btree_clear_folio_dirty(folio);
+	folio_unlock(folio);
 	WARN_ON(atomic_read(&eb->refs) == 0);
 }
 
@@ -3739,15 +3909,27 @@ void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans,
 			      struct extent_buffer *eb)
 {
 	struct btrfs_fs_info *fs_info = eb->fs_info;
-	int i;
-	int num_pages;
-	struct page *page;
+	int num_folios;
 
 	btrfs_assert_tree_write_locked(eb);
 
 	if (trans && btrfs_header_generation(eb) != trans->transid)
 		return;
 
+	/*
+	 * Instead of clearing the dirty flag off of the buffer, mark it as
+	 * EXTENT_BUFFER_ZONED_ZEROOUT. This allows us to preserve
+	 * write-ordering in zoned mode, without the need to later re-dirty
+	 * the extent_buffer.
+	 *
+	 * The actual zeroout of the buffer will happen later in
+	 * btree_csum_one_bio.
+	 */
+	if (btrfs_is_zoned(fs_info)) {
+		set_bit(EXTENT_BUFFER_ZONED_ZEROOUT, &eb->bflags);
+		return;
+	}
+
 	if (!test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->bflags))
 		return;
 
@@ -3757,30 +3939,29 @@ void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans,
 	if (eb->fs_info->nodesize < PAGE_SIZE)
 		return clear_subpage_extent_buffer_dirty(eb);
 
-	num_pages = num_extent_pages(eb);
+	num_folios = num_extent_folios(eb);
+	for (int i = 0; i < num_folios; i++) {
+		struct folio *folio = eb->folios[i];
 
-	for (i = 0; i < num_pages; i++) {
-		page = eb->pages[i];
-		if (!PageDirty(page))
+		if (!folio_test_dirty(folio))
 			continue;
-		lock_page(page);
-		btree_clear_page_dirty(page);
-		unlock_page(page);
+		folio_lock(folio);
+		btree_clear_folio_dirty(folio);
+		folio_unlock(folio);
 	}
 	WARN_ON(atomic_read(&eb->refs) == 0);
 }
 
 void set_extent_buffer_dirty(struct extent_buffer *eb)
 {
-	int i;
-	int num_pages;
+	int num_folios;
 	bool was_dirty;
 
 	check_buffer_tree_ref(eb);
 
 	was_dirty = test_and_set_bit(EXTENT_BUFFER_DIRTY, &eb->bflags);
 
-	num_pages = num_extent_pages(eb);
+	num_folios = num_extent_folios(eb);
 	WARN_ON(atomic_read(&eb->refs) == 0);
 	WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags));
 
@@ -3799,34 +3980,32 @@ void set_extent_buffer_dirty(struct extent_buffer *eb)
 		 * the above race.
 		 */
 		if (subpage)
-			lock_page(eb->pages[0]);
-		for (i = 0; i < num_pages; i++)
-			btrfs_page_set_dirty(eb->fs_info, eb->pages[i],
-					     eb->start, eb->len);
+			lock_page(folio_page(eb->folios[0], 0));
+		for (int i = 0; i < num_folios; i++)
+			btrfs_folio_set_dirty(eb->fs_info, eb->folios[i],
+					      eb->start, eb->len);
 		if (subpage)
-			unlock_page(eb->pages[0]);
+			unlock_page(folio_page(eb->folios[0], 0));
 		percpu_counter_add_batch(&eb->fs_info->dirty_metadata_bytes,
 					 eb->len,
 					 eb->fs_info->dirty_metadata_batch);
 	}
 #ifdef CONFIG_BTRFS_DEBUG
-	for (i = 0; i < num_pages; i++)
-		ASSERT(PageDirty(eb->pages[i]));
+	for (int i = 0; i < num_folios; i++)
+		ASSERT(folio_test_dirty(eb->folios[i]));
 #endif
 }
 
 void clear_extent_buffer_uptodate(struct extent_buffer *eb)
 {
 	struct btrfs_fs_info *fs_info = eb->fs_info;
-	struct page *page;
-	int num_pages;
-	int i;
+	int num_folios = num_extent_folios(eb);
 
 	clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
-	num_pages = num_extent_pages(eb);
-	for (i = 0; i < num_pages; i++) {
-		page = eb->pages[i];
-		if (!page)
+	for (int i = 0; i < num_folios; i++) {
+		struct folio *folio = eb->folios[i];
+
+		if (!folio)
 			continue;
 
 		/*
@@ -3834,44 +4013,40 @@ void clear_extent_buffer_uptodate(struct extent_buffer *eb)
 		 * btrfs_is_subpage() can not handle cloned/dummy metadata.
 		 */
 		if (fs_info->nodesize >= PAGE_SIZE)
-			ClearPageUptodate(page);
+			folio_clear_uptodate(folio);
 		else
-			btrfs_subpage_clear_uptodate(fs_info, page, eb->start,
-						     eb->len);
+			btrfs_subpage_clear_uptodate(fs_info, folio,
+						     eb->start, eb->len);
 	}
 }
 
 void set_extent_buffer_uptodate(struct extent_buffer *eb)
 {
 	struct btrfs_fs_info *fs_info = eb->fs_info;
-	struct page *page;
-	int num_pages;
-	int i;
+	int num_folios = num_extent_folios(eb);
 
 	set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
-	num_pages = num_extent_pages(eb);
-	for (i = 0; i < num_pages; i++) {
-		page = eb->pages[i];
+	for (int i = 0; i < num_folios; i++) {
+		struct folio *folio = eb->folios[i];
 
 		/*
 		 * This is special handling for metadata subpage, as regular
 		 * btrfs_is_subpage() can not handle cloned/dummy metadata.
 		 */
 		if (fs_info->nodesize >= PAGE_SIZE)
-			SetPageUptodate(page);
+			folio_mark_uptodate(folio);
 		else
-			btrfs_subpage_set_uptodate(fs_info, page, eb->start,
-						   eb->len);
+			btrfs_subpage_set_uptodate(fs_info, folio,
+						   eb->start, eb->len);
 	}
 }
 
-static void extent_buffer_read_end_io(struct btrfs_bio *bbio)
+static void end_bbio_meta_read(struct btrfs_bio *bbio)
 {
 	struct extent_buffer *eb = bbio->private;
 	struct btrfs_fs_info *fs_info = eb->fs_info;
 	bool uptodate = !bbio->bio.bi_status;
-	struct bvec_iter_all iter_all;
-	struct bio_vec *bvec;
+	struct folio_iter fi;
 	u32 bio_offset = 0;
 
 	eb->read_mirror = bbio->mirror_num;
@@ -3887,15 +4062,15 @@ static void extent_buffer_read_end_io(struct btrfs_bio *bbio)
 		set_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
 	}
 
-	bio_for_each_segment_all(bvec, &bbio->bio, iter_all) {
+	bio_for_each_folio_all(fi, &bbio->bio) {
+		struct folio *folio = fi.folio;
 		u64 start = eb->start + bio_offset;
-		struct page *page = bvec->bv_page;
-		u32 len = bvec->bv_len;
+		u32 len = fi.length;
 
 		if (uptodate)
-			btrfs_page_set_uptodate(fs_info, page, start, len);
+			btrfs_folio_set_uptodate(fs_info, folio, start, len);
 		else
-			btrfs_page_clear_uptodate(fs_info, page, start, len);
+			btrfs_folio_clear_uptodate(fs_info, folio, start, len);
 
 		bio_offset += len;
 	}
@@ -3911,8 +4086,8 @@ static void extent_buffer_read_end_io(struct btrfs_bio *bbio)
 int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num,
 			     struct btrfs_tree_parent_check *check)
 {
-	int num_pages = num_extent_pages(eb), i;
 	struct btrfs_bio *bbio;
+	bool ret;
 
 	if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
 		return 0;
@@ -3936,17 +4111,24 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num,
 
 	bbio = btrfs_bio_alloc(INLINE_EXTENT_BUFFER_PAGES,
 			       REQ_OP_READ | REQ_META, eb->fs_info,
-			       extent_buffer_read_end_io, eb);
+			       end_bbio_meta_read, eb);
 	bbio->bio.bi_iter.bi_sector = eb->start >> SECTOR_SHIFT;
 	bbio->inode = BTRFS_I(eb->fs_info->btree_inode);
 	bbio->file_offset = eb->start;
 	memcpy(&bbio->parent_check, check, sizeof(*check));
 	if (eb->fs_info->nodesize < PAGE_SIZE) {
-		__bio_add_page(&bbio->bio, eb->pages[0], eb->len,
-			       eb->start - page_offset(eb->pages[0]));
+		ret = bio_add_folio(&bbio->bio, eb->folios[0], eb->len,
+				    eb->start - folio_pos(eb->folios[0]));
+		ASSERT(ret);
 	} else {
-		for (i = 0; i < num_pages; i++)
-			__bio_add_page(&bbio->bio, eb->pages[i], PAGE_SIZE, 0);
+		int num_folios = num_extent_folios(eb);
+
+		for (int i = 0; i < num_folios; i++) {
+			struct folio *folio = eb->folios[i];
+
+			ret = bio_add_folio(&bbio->bio, folio, folio_size(folio), 0);
+			ASSERT(ret);
+		}
 	}
 	btrfs_submit_bio(bbio, mirror_num);
 
@@ -3993,29 +4175,33 @@ static inline int check_eb_range(const struct extent_buffer *eb,
 void read_extent_buffer(const struct extent_buffer *eb, void *dstv,
 			unsigned long start, unsigned long len)
 {
+	const int unit_size = folio_size(eb->folios[0]);
 	size_t cur;
 	size_t offset;
-	struct page *page;
-	char *kaddr;
 	char *dst = (char *)dstv;
-	unsigned long i = get_eb_page_index(start);
+	unsigned long i = get_eb_folio_index(eb, start);
 
 	if (check_eb_range(eb, start, len)) {
 		/*
 		 * Invalid range hit, reset the memory, so callers won't get
-		 * some random garbage for their uninitialzed memory.
+		 * some random garbage for their uninitialized memory.
 		 */
 		memset(dstv, 0, len);
 		return;
 	}
 
-	offset = get_eb_offset_in_page(eb, start);
+	if (eb->addr) {
+		memcpy(dstv, eb->addr + start, len);
+		return;
+	}
+
+	offset = get_eb_offset_in_folio(eb, start);
 
 	while (len > 0) {
-		page = eb->pages[i];
+		char *kaddr;
 
-		cur = min(len, (PAGE_SIZE - offset));
-		kaddr = page_address(page);
+		cur = min(len, unit_size - offset);
+		kaddr = folio_address(eb->folios[i]);
 		memcpy(dst, kaddr + offset, cur);
 
 		dst += cur;
@@ -4029,24 +4215,29 @@ int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb,
 				       void __user *dstv,
 				       unsigned long start, unsigned long len)
 {
+	const int unit_size = folio_size(eb->folios[0]);
 	size_t cur;
 	size_t offset;
-	struct page *page;
-	char *kaddr;
 	char __user *dst = (char __user *)dstv;
-	unsigned long i = get_eb_page_index(start);
+	unsigned long i = get_eb_folio_index(eb, start);
 	int ret = 0;
 
 	WARN_ON(start > eb->len);
 	WARN_ON(start + len > eb->start + eb->len);
 
-	offset = get_eb_offset_in_page(eb, start);
+	if (eb->addr) {
+		if (copy_to_user_nofault(dstv, eb->addr + start, len))
+			ret = -EFAULT;
+		return ret;
+	}
+
+	offset = get_eb_offset_in_folio(eb, start);
 
 	while (len > 0) {
-		page = eb->pages[i];
+		char *kaddr;
 
-		cur = min(len, (PAGE_SIZE - offset));
-		kaddr = page_address(page);
+		cur = min(len, unit_size - offset);
+		kaddr = folio_address(eb->folios[i]);
 		if (copy_to_user_nofault(dst, kaddr + offset, cur)) {
 			ret = -EFAULT;
 			break;
@@ -4064,25 +4255,25 @@ int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb,
 int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv,
 			 unsigned long start, unsigned long len)
 {
+	const int unit_size = folio_size(eb->folios[0]);
 	size_t cur;
 	size_t offset;
-	struct page *page;
 	char *kaddr;
 	char *ptr = (char *)ptrv;
-	unsigned long i = get_eb_page_index(start);
+	unsigned long i = get_eb_folio_index(eb, start);
 	int ret = 0;
 
 	if (check_eb_range(eb, start, len))
 		return -EINVAL;
 
-	offset = get_eb_offset_in_page(eb, start);
-
-	while (len > 0) {
-		page = eb->pages[i];
+	if (eb->addr)
+		return memcmp(ptrv, eb->addr + start, len);
 
-		cur = min(len, (PAGE_SIZE - offset));
+	offset = get_eb_offset_in_folio(eb, start);
 
-		kaddr = page_address(page);
+	while (len > 0) {
+		cur = min(len, unit_size - offset);
+		kaddr = folio_address(eb->folios[i]);
 		ret = memcmp(ptr, kaddr + offset, cur);
 		if (ret)
 			break;
@@ -4101,10 +4292,12 @@ int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv,
  * For regular sector size == PAGE_SIZE case, check if @page is uptodate.
  * For subpage case, check if the range covered by the eb has EXTENT_UPTODATE.
  */
-static void assert_eb_page_uptodate(const struct extent_buffer *eb,
-				    struct page *page)
+static void assert_eb_folio_uptodate(const struct extent_buffer *eb, int i)
 {
 	struct btrfs_fs_info *fs_info = eb->fs_info;
+	struct folio *folio = eb->folios[i];
+
+	ASSERT(folio);
 
 	/*
 	 * If we are using the commit root we could potentially clear a page
@@ -4118,11 +4311,14 @@ static void assert_eb_page_uptodate(const struct extent_buffer *eb,
 		return;
 
 	if (fs_info->nodesize < PAGE_SIZE) {
-		if (WARN_ON(!btrfs_subpage_test_uptodate(fs_info, page,
+		struct folio *folio = eb->folios[0];
+
+		ASSERT(i == 0);
+		if (WARN_ON(!btrfs_subpage_test_uptodate(fs_info, folio,
 							 eb->start, eb->len)))
-			btrfs_subpage_dump_bitmap(fs_info, page, eb->start, eb->len);
+			btrfs_subpage_dump_bitmap(fs_info, folio, eb->start, eb->len);
 	} else {
-		WARN_ON(!PageUptodate(page));
+		WARN_ON(!folio_test_uptodate(folio));
 	}
 }
 
@@ -4130,29 +4326,34 @@ static void __write_extent_buffer(const struct extent_buffer *eb,
 				  const void *srcv, unsigned long start,
 				  unsigned long len, bool use_memmove)
 {
+	const int unit_size = folio_size(eb->folios[0]);
 	size_t cur;
 	size_t offset;
-	struct page *page;
 	char *kaddr;
 	char *src = (char *)srcv;
-	unsigned long i = get_eb_page_index(start);
+	unsigned long i = get_eb_folio_index(eb, start);
 	/* For unmapped (dummy) ebs, no need to check their uptodate status. */
 	const bool check_uptodate = !test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags);
 
-	WARN_ON(test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags));
-
 	if (check_eb_range(eb, start, len))
 		return;
 
-	offset = get_eb_offset_in_page(eb, start);
+	if (eb->addr) {
+		if (use_memmove)
+			memmove(eb->addr + start, srcv, len);
+		else
+			memcpy(eb->addr + start, srcv, len);
+		return;
+	}
+
+	offset = get_eb_offset_in_folio(eb, start);
 
 	while (len > 0) {
-		page = eb->pages[i];
 		if (check_uptodate)
-			assert_eb_page_uptodate(eb, page);
+			assert_eb_folio_uptodate(eb, i);
 
-		cur = min(len, PAGE_SIZE - offset);
-		kaddr = page_address(page);
+		cur = min(len, unit_size - offset);
+		kaddr = folio_address(eb->folios[i]);
 		if (use_memmove)
 			memmove(kaddr + offset, src, cur);
 		else
@@ -4174,16 +4375,21 @@ void write_extent_buffer(const struct extent_buffer *eb, const void *srcv,
 static void memset_extent_buffer(const struct extent_buffer *eb, int c,
 				 unsigned long start, unsigned long len)
 {
+	const int unit_size = folio_size(eb->folios[0]);
 	unsigned long cur = start;
 
+	if (eb->addr) {
+		memset(eb->addr + start, c, len);
+		return;
+	}
+
 	while (cur < start + len) {
-		unsigned long index = get_eb_page_index(cur);
-		unsigned int offset = get_eb_offset_in_page(eb, cur);
-		unsigned int cur_len = min(start + len - cur, PAGE_SIZE - offset);
-		struct page *page = eb->pages[index];
+		unsigned long index = get_eb_folio_index(eb, cur);
+		unsigned int offset = get_eb_offset_in_folio(eb, cur);
+		unsigned int cur_len = min(start + len - cur, unit_size - offset);
 
-		assert_eb_page_uptodate(eb, page);
-		memset(page_address(page) + offset, c, cur_len);
+		assert_eb_folio_uptodate(eb, index);
+		memset(folio_address(eb->folios[index]) + offset, c, cur_len);
 
 		cur += cur_len;
 	}
@@ -4200,15 +4406,16 @@ void memzero_extent_buffer(const struct extent_buffer *eb, unsigned long start,
 void copy_extent_buffer_full(const struct extent_buffer *dst,
 			     const struct extent_buffer *src)
 {
+	const int unit_size = folio_size(src->folios[0]);
 	unsigned long cur = 0;
 
 	ASSERT(dst->len == src->len);
 
 	while (cur < src->len) {
-		unsigned long index = get_eb_page_index(cur);
-		unsigned long offset = get_eb_offset_in_page(src, cur);
-		unsigned long cur_len = min(src->len, PAGE_SIZE - offset);
-		void *addr = page_address(src->pages[index]) + offset;
+		unsigned long index = get_eb_folio_index(src, cur);
+		unsigned long offset = get_eb_offset_in_folio(src, cur);
+		unsigned long cur_len = min(src->len, unit_size - offset);
+		void *addr = folio_address(src->folios[index]) + offset;
 
 		write_extent_buffer(dst, addr, cur, cur_len);
 
@@ -4221,12 +4428,12 @@ void copy_extent_buffer(const struct extent_buffer *dst,
 			unsigned long dst_offset, unsigned long src_offset,
 			unsigned long len)
 {
+	const int unit_size = folio_size(dst->folios[0]);
 	u64 dst_len = dst->len;
 	size_t cur;
 	size_t offset;
-	struct page *page;
 	char *kaddr;
-	unsigned long i = get_eb_page_index(dst_offset);
+	unsigned long i = get_eb_folio_index(dst, dst_offset);
 
 	if (check_eb_range(dst, dst_offset, len) ||
 	    check_eb_range(src, src_offset, len))
@@ -4234,15 +4441,14 @@ void copy_extent_buffer(const struct extent_buffer *dst,
 
 	WARN_ON(src->len != dst_len);
 
-	offset = get_eb_offset_in_page(dst, dst_offset);
+	offset = get_eb_offset_in_folio(dst, dst_offset);
 
 	while (len > 0) {
-		page = dst->pages[i];
-		assert_eb_page_uptodate(dst, page);
+		assert_eb_folio_uptodate(dst, i);
 
-		cur = min(len, (unsigned long)(PAGE_SIZE - offset));
+		cur = min(len, (unsigned long)(unit_size - offset));
 
-		kaddr = page_address(page);
+		kaddr = folio_address(dst->folios[i]);
 		read_extent_buffer(src, kaddr + offset, src_offset, cur);
 
 		src_offset += cur;
@@ -4253,22 +4459,22 @@ void copy_extent_buffer(const struct extent_buffer *dst,
 }
 
 /*
- * Calculate the page and offset of the byte containing the given bit number.
+ * Calculate the folio and offset of the byte containing the given bit number.
  *
  * @eb:           the extent buffer
  * @start:        offset of the bitmap item in the extent buffer
  * @nr:           bit number
- * @page_index:   return index of the page in the extent buffer that contains
+ * @folio_index:  return index of the folio in the extent buffer that contains
  *                the given bit number
- * @page_offset:  return offset into the page given by page_index
+ * @folio_offset: return offset into the folio given by folio_index
  *
  * This helper hides the ugliness of finding the byte in an extent buffer which
  * contains a given bit.
  */
 static inline void eb_bitmap_offset(const struct extent_buffer *eb,
 				    unsigned long start, unsigned long nr,
-				    unsigned long *page_index,
-				    size_t *page_offset)
+				    unsigned long *folio_index,
+				    size_t *folio_offset)
 {
 	size_t byte_offset = BIT_BYTE(nr);
 	size_t offset;
@@ -4278,10 +4484,10 @@ static inline void eb_bitmap_offset(const struct extent_buffer *eb,
 	 * the bitmap item in the extent buffer + the offset of the byte in the
 	 * bitmap item.
 	 */
-	offset = start + offset_in_page(eb->start) + byte_offset;
+	offset = start + offset_in_folio(eb->folios[0], eb->start) + byte_offset;
 
-	*page_index = offset >> PAGE_SHIFT;
-	*page_offset = offset_in_page(offset);
+	*folio_index = offset >> folio_shift(eb->folios[0]);
+	*folio_offset = offset_in_folio(eb->folios[0], offset);
 }
 
 /*
@@ -4294,25 +4500,23 @@ static inline void eb_bitmap_offset(const struct extent_buffer *eb,
 int extent_buffer_test_bit(const struct extent_buffer *eb, unsigned long start,
 			   unsigned long nr)
 {
-	u8 *kaddr;
-	struct page *page;
 	unsigned long i;
 	size_t offset;
+	u8 *kaddr;
 
 	eb_bitmap_offset(eb, start, nr, &i, &offset);
-	page = eb->pages[i];
-	assert_eb_page_uptodate(eb, page);
-	kaddr = page_address(page);
+	assert_eb_folio_uptodate(eb, i);
+	kaddr = folio_address(eb->folios[i]);
 	return 1U & (kaddr[offset] >> (nr & (BITS_PER_BYTE - 1)));
 }
 
 static u8 *extent_buffer_get_byte(const struct extent_buffer *eb, unsigned long bytenr)
 {
-	unsigned long index = get_eb_page_index(bytenr);
+	unsigned long index = get_eb_folio_index(eb, bytenr);
 
 	if (check_eb_range(eb, bytenr, 1))
 		return NULL;
-	return page_address(eb->pages[index]) + get_eb_offset_in_page(eb, bytenr);
+	return folio_address(eb->folios[index]) + get_eb_offset_in_folio(eb, bytenr);
 }
 
 /*
@@ -4397,19 +4601,30 @@ void memcpy_extent_buffer(const struct extent_buffer *dst,
 			  unsigned long dst_offset, unsigned long src_offset,
 			  unsigned long len)
 {
+	const int unit_size = folio_size(dst->folios[0]);
 	unsigned long cur_off = 0;
 
 	if (check_eb_range(dst, dst_offset, len) ||
 	    check_eb_range(dst, src_offset, len))
 		return;
 
+	if (dst->addr) {
+		const bool use_memmove = areas_overlap(src_offset, dst_offset, len);
+
+		if (use_memmove)
+			memmove(dst->addr + dst_offset, dst->addr + src_offset, len);
+		else
+			memcpy(dst->addr + dst_offset, dst->addr + src_offset, len);
+		return;
+	}
+
 	while (cur_off < len) {
 		unsigned long cur_src = cur_off + src_offset;
-		unsigned long pg_index = get_eb_page_index(cur_src);
-		unsigned long pg_off = get_eb_offset_in_page(dst, cur_src);
+		unsigned long folio_index = get_eb_folio_index(dst, cur_src);
+		unsigned long folio_off = get_eb_offset_in_folio(dst, cur_src);
 		unsigned long cur_len = min(src_offset + len - cur_src,
-					    PAGE_SIZE - pg_off);
-		void *src_addr = page_address(dst->pages[pg_index]) + pg_off;
+					    unit_size - folio_off);
+		void *src_addr = folio_address(dst->folios[folio_index]) + folio_off;
 		const bool use_memmove = areas_overlap(src_offset + cur_off,
 						       dst_offset + cur_off, cur_len);
 
@@ -4435,24 +4650,29 @@ void memmove_extent_buffer(const struct extent_buffer *dst,
 		return;
 	}
 
+	if (dst->addr) {
+		memmove(dst->addr + dst_offset, dst->addr + src_offset, len);
+		return;
+	}
+
 	while (len > 0) {
 		unsigned long src_i;
 		size_t cur;
-		size_t dst_off_in_page;
-		size_t src_off_in_page;
+		size_t dst_off_in_folio;
+		size_t src_off_in_folio;
 		void *src_addr;
 		bool use_memmove;
 
-		src_i = get_eb_page_index(src_end);
+		src_i = get_eb_folio_index(dst, src_end);
 
-		dst_off_in_page = get_eb_offset_in_page(dst, dst_end);
-		src_off_in_page = get_eb_offset_in_page(dst, src_end);
+		dst_off_in_folio = get_eb_offset_in_folio(dst, dst_end);
+		src_off_in_folio = get_eb_offset_in_folio(dst, src_end);
 
-		cur = min_t(unsigned long, len, src_off_in_page + 1);
-		cur = min(cur, dst_off_in_page + 1);
+		cur = min_t(unsigned long, len, src_off_in_folio + 1);
+		cur = min(cur, dst_off_in_folio + 1);
 
-		src_addr = page_address(dst->pages[src_i]) + src_off_in_page -
-					cur + 1;
+		src_addr = folio_address(dst->folios[src_i]) + src_off_in_folio -
+					 cur + 1;
 		use_memmove = areas_overlap(src_end - cur + 1, dst_end - cur + 1,
 					    cur);
 
@@ -4514,7 +4734,7 @@ static int try_release_subpage_extent_buffer(struct page *page)
 		struct extent_buffer *eb = NULL;
 
 		/*
-		 * Unlike try_release_extent_buffer() which uses page->private
+		 * Unlike try_release_extent_buffer() which uses folio private
 		 * to grab buffer, for subpage case we rely on radix tree, thus
 		 * we need to ensure radix tree consistency.
 		 *
@@ -4554,43 +4774,44 @@ static int try_release_subpage_extent_buffer(struct page *page)
 
 		/*
 		 * Here we don't care about the return value, we will always
-		 * check the page private at the end.  And
+		 * check the folio private at the end.  And
 		 * release_extent_buffer() will release the refs_lock.
 		 */
 		release_extent_buffer(eb);
 	}
 	/*
-	 * Finally to check if we have cleared page private, as if we have
-	 * released all ebs in the page, the page private should be cleared now.
+	 * Finally to check if we have cleared folio private, as if we have
+	 * released all ebs in the page, the folio private should be cleared now.
 	 */
-	spin_lock(&page->mapping->private_lock);
-	if (!PagePrivate(page))
+	spin_lock(&page->mapping->i_private_lock);
+	if (!folio_test_private(page_folio(page)))
 		ret = 1;
 	else
 		ret = 0;
-	spin_unlock(&page->mapping->private_lock);
+	spin_unlock(&page->mapping->i_private_lock);
 	return ret;
 
 }
 
 int try_release_extent_buffer(struct page *page)
 {
+	struct folio *folio = page_folio(page);
 	struct extent_buffer *eb;
 
 	if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE)
 		return try_release_subpage_extent_buffer(page);
 
 	/*
-	 * We need to make sure nobody is changing page->private, as we rely on
-	 * page->private as the pointer to extent buffer.
+	 * We need to make sure nobody is changing folio private, as we rely on
+	 * folio private as the pointer to extent buffer.
 	 */
-	spin_lock(&page->mapping->private_lock);
-	if (!PagePrivate(page)) {
-		spin_unlock(&page->mapping->private_lock);
+	spin_lock(&page->mapping->i_private_lock);
+	if (!folio_test_private(folio)) {
+		spin_unlock(&page->mapping->i_private_lock);
 		return 1;
 	}
 
-	eb = (struct extent_buffer *)page->private;
+	eb = folio_get_private(folio);
 	BUG_ON(!eb);
 
 	/*
@@ -4601,10 +4822,10 @@ int try_release_extent_buffer(struct page *page)
 	spin_lock(&eb->refs_lock);
 	if (atomic_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) {
 		spin_unlock(&eb->refs_lock);
-		spin_unlock(&page->mapping->private_lock);
+		spin_unlock(&page->mapping->i_private_lock);
 		return 0;
 	}
-	spin_unlock(&page->mapping->private_lock);
+	spin_unlock(&page->mapping->i_private_lock);
 
 	/*
 	 * If tree ref isn't set then we know the ref on this eb is a real ref,
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 2171057a4477..46050500529b 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -28,7 +28,8 @@ enum {
 	EXTENT_BUFFER_IN_TREE,
 	/* write IO error */
 	EXTENT_BUFFER_WRITE_ERR,
-	EXTENT_BUFFER_NO_CHECK,
+	/* Indicate the extent buffer is written zeroed out (for zoned) */
+	EXTENT_BUFFER_ZONED_ZEROOUT,
 	/* Indicate that extent buffer pages a being read */
 	EXTENT_BUFFER_READING,
 };
@@ -43,10 +44,10 @@ enum {
 };
 
 /*
- * page->private values.  Every page that is controlled by the extent
- * map has page->private set to one.
+ * Folio private values.  Every page that is controlled by the extent map has
+ * folio private set to this value.
  */
-#define EXTENT_PAGE_PRIVATE 1
+#define EXTENT_FOLIO_PRIVATE			1
 
 /*
  * The extent buffer bitmap operations are done with byte granularity instead of
@@ -77,6 +78,13 @@ struct extent_buffer {
 	unsigned long len;
 	unsigned long bflags;
 	struct btrfs_fs_info *fs_info;
+
+	/*
+	 * The address where the eb can be accessed without any cross-page handling.
+	 * This can be NULL if not possible.
+	 */
+	void *addr;
+
 	spinlock_t refs_lock;
 	atomic_t refs;
 	int read_mirror;
@@ -86,7 +94,12 @@ struct extent_buffer {
 
 	struct rw_semaphore lock;
 
-	struct page *pages[INLINE_EXTENT_BUFFER_PAGES];
+	/*
+	 * Pointers to all the folios of the extent buffer.
+	 *
+	 * For now the folio is always order 0 (aka, a single page).
+	 */
+	struct folio *folios[INLINE_EXTENT_BUFFER_PAGES];
 #ifdef CONFIG_BTRFS_DEBUG
 	struct list_head leak_list;
 	pid_t lock_owner;
@@ -108,29 +121,43 @@ struct btrfs_eb_write_context {
  *
  * Will handle both sectorsize == PAGE_SIZE and sectorsize < PAGE_SIZE cases.
  */
-static inline size_t get_eb_offset_in_page(const struct extent_buffer *eb,
-					   unsigned long offset)
+static inline size_t get_eb_offset_in_folio(const struct extent_buffer *eb,
+					    unsigned long offset)
 {
 	/*
-	 * For sectorsize == PAGE_SIZE case, eb->start will always be aligned
-	 * to PAGE_SIZE, thus adding it won't cause any difference.
+	 * 1) sectorsize == PAGE_SIZE and nodesize >= PAGE_SIZE case
+	 *    1.1) One large folio covering the whole eb
+	 *	   The eb->start is aligned to folio size, thus adding it
+	 *	   won't cause any difference.
+	 *    1.2) Several page sized folios
+	 *	   The eb->start is aligned to folio (page) size, thus
+	 *	   adding it won't cause any difference.
 	 *
-	 * For sectorsize < PAGE_SIZE, we must only read the data that belongs
-	 * to the eb, thus we have to take the eb->start into consideration.
+	 * 2) sectorsize < PAGE_SIZE and nodesize < PAGE_SIZE case
+	 *    In this case there would only be one page sized folio, and there
+	 *    may be several different extent buffers in the page/folio.
+	 *    We need to add eb->start to properly access the offset inside
+	 *    that eb.
 	 */
-	return offset_in_page(offset + eb->start);
+	return offset_in_folio(eb->folios[0], offset + eb->start);
 }
 
-static inline unsigned long get_eb_page_index(unsigned long offset)
+static inline unsigned long get_eb_folio_index(const struct extent_buffer *eb,
+					       unsigned long offset)
 {
 	/*
-	 * For sectorsize == PAGE_SIZE case, plain >> PAGE_SHIFT is enough.
+	 * 1) sectorsize == PAGE_SIZE and nodesize >= PAGE_SIZE case
+	 *    1.1) One large folio covering the whole eb.
+	 *	   the folio_shift would be large enough to always make us
+	 *	   return 0 as index.
+	 *    1.2) Several page sized folios
+	 *         The folio_shift() would be PAGE_SHIFT, giving us the correct
+	 *         index.
 	 *
-	 * For sectorsize < PAGE_SIZE case, we only support 64K PAGE_SIZE,
-	 * and have ensured that all tree blocks are contained in one page,
-	 * thus we always get index == 0.
+	 * 2) sectorsize < PAGE_SIZE and nodesize < PAGE_SIZE case
+	 *    The folio would only be page sized, and always give us 0 as index.
 	 */
-	return offset >> PAGE_SHIFT;
+	return offset >> folio_shift(eb->folios[0]);
 }
 
 /*
@@ -230,6 +257,20 @@ static inline int num_extent_pages(const struct extent_buffer *eb)
 	return (eb->len >> PAGE_SHIFT) ?: 1;
 }
 
+/*
+ * This can only be determined at runtime by checking eb::folios[0].
+ *
+ * As we can have either one large folio covering the whole eb
+ * (either nodesize <= PAGE_SIZE, or high order folio), or multiple
+ * single-paged folios.
+ */
+static inline int num_extent_folios(const struct extent_buffer *eb)
+{
+	if (folio_order(eb->folios[0]))
+		return 1;
+	return num_extent_pages(eb);
+}
+
 static inline int extent_buffer_uptodate(const struct extent_buffer *eb)
 {
 	return test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
@@ -294,7 +335,8 @@ int extent_invalidate_folio(struct extent_io_tree *tree,
 void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans,
 			      struct extent_buffer *buf);
 
-int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array);
+int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array,
+			   gfp_t extra_gfp);
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 bool find_lock_delalloc_range(struct inode *inode,
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index a6d8368ed0ed..b61099bf97a8 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -50,7 +50,6 @@ struct extent_map *alloc_extent_map(void)
 	if (!em)
 		return NULL;
 	RB_CLEAR_NODE(&em->rb_node);
-	em->compress_type = BTRFS_COMPRESS_NONE;
 	refcount_set(&em->refs, 1);
 	INIT_LIST_HEAD(&em->list);
 	return em;
@@ -67,8 +66,6 @@ void free_extent_map(struct extent_map *em)
 	if (refcount_dec_and_test(&em->refs)) {
 		WARN_ON(extent_map_in_tree(em));
 		WARN_ON(!list_empty(&em->list));
-		if (test_bit(EXTENT_FLAG_FS_MAPPING, &em->flags))
-			kfree(em->map_lookup);
 		kmem_cache_free(extent_map_cache, em);
 	}
 }
@@ -182,50 +179,50 @@ static struct rb_node *__tree_search(struct rb_root *root, u64 offset,
 	return NULL;
 }
 
-/* Check to see if two extent_map structs are adjacent and safe to merge. */
-static int mergable_maps(struct extent_map *prev, struct extent_map *next)
+static inline u64 extent_map_block_end(const struct extent_map *em)
 {
-	if (test_bit(EXTENT_FLAG_PINNED, &prev->flags))
-		return 0;
+	if (em->block_start + em->block_len < em->block_start)
+		return (u64)-1;
+	return em->block_start + em->block_len;
+}
 
-	/*
-	 * don't merge compressed extents, we need to know their
-	 * actual size
-	 */
-	if (test_bit(EXTENT_FLAG_COMPRESSED, &prev->flags))
-		return 0;
+static bool can_merge_extent_map(const struct extent_map *em)
+{
+	if (em->flags & EXTENT_FLAG_PINNED)
+		return false;
+
+	/* Don't merge compressed extents, we need to know their actual size. */
+	if (extent_map_is_compressed(em))
+		return false;
 
-	if (test_bit(EXTENT_FLAG_LOGGING, &prev->flags) ||
-	    test_bit(EXTENT_FLAG_LOGGING, &next->flags))
-		return 0;
+	if (em->flags & EXTENT_FLAG_LOGGING)
+		return false;
 
 	/*
 	 * We don't want to merge stuff that hasn't been written to the log yet
 	 * since it may not reflect exactly what is on disk, and that would be
 	 * bad.
 	 */
-	if (!list_empty(&prev->list) || !list_empty(&next->list))
-		return 0;
-
-	ASSERT(next->block_start != EXTENT_MAP_DELALLOC &&
-	       prev->block_start != EXTENT_MAP_DELALLOC);
-
-	if (prev->map_lookup || next->map_lookup)
-		ASSERT(test_bit(EXTENT_FLAG_FS_MAPPING, &prev->flags) &&
-		       test_bit(EXTENT_FLAG_FS_MAPPING, &next->flags));
-
-	if (extent_map_end(prev) == next->start &&
-	    prev->flags == next->flags &&
-	    prev->map_lookup == next->map_lookup &&
-	    ((next->block_start == EXTENT_MAP_HOLE &&
-	      prev->block_start == EXTENT_MAP_HOLE) ||
-	     (next->block_start == EXTENT_MAP_INLINE &&
-	      prev->block_start == EXTENT_MAP_INLINE) ||
-	     (next->block_start < EXTENT_MAP_LAST_BYTE - 1 &&
-	      next->block_start == extent_map_block_end(prev)))) {
-		return 1;
-	}
-	return 0;
+	if (!list_empty(&em->list))
+		return false;
+
+	return true;
+}
+
+/* Check to see if two extent_map structs are adjacent and safe to merge. */
+static bool mergeable_maps(const struct extent_map *prev, const struct extent_map *next)
+{
+	if (extent_map_end(prev) != next->start)
+		return false;
+
+	if (prev->flags != next->flags)
+		return false;
+
+	if (next->block_start < EXTENT_MAP_LAST_BYTE - 1)
+		return next->block_start == extent_map_block_end(prev);
+
+	/* HOLES and INLINE extents. */
+	return next->block_start == prev->block_start;
 }
 
 static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
@@ -244,11 +241,14 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
 	if (refcount_read(&em->refs) > 2)
 		return;
 
+	if (!can_merge_extent_map(em))
+		return;
+
 	if (em->start != 0) {
 		rb = rb_prev(&em->rb_node);
 		if (rb)
 			merge = rb_entry(rb, struct extent_map, rb_node);
-		if (rb && mergable_maps(merge, em)) {
+		if (rb && can_merge_extent_map(merge) && mergeable_maps(merge, em)) {
 			em->start = merge->start;
 			em->orig_start = merge->orig_start;
 			em->len += merge->len;
@@ -257,7 +257,7 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
 			em->mod_len = (em->mod_len + em->mod_start) - merge->mod_start;
 			em->mod_start = merge->mod_start;
 			em->generation = max(em->generation, merge->generation);
-			set_bit(EXTENT_FLAG_MERGED, &em->flags);
+			em->flags |= EXTENT_FLAG_MERGED;
 
 			rb_erase_cached(&merge->rb_node, &tree->map);
 			RB_CLEAR_NODE(&merge->rb_node);
@@ -268,14 +268,14 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
 	rb = rb_next(&em->rb_node);
 	if (rb)
 		merge = rb_entry(rb, struct extent_map, rb_node);
-	if (rb && mergable_maps(em, merge)) {
+	if (rb && can_merge_extent_map(merge) && mergeable_maps(em, merge)) {
 		em->len += merge->len;
 		em->block_len += merge->block_len;
 		rb_erase_cached(&merge->rb_node, &tree->map);
 		RB_CLEAR_NODE(&merge->rb_node);
 		em->mod_len = (merge->mod_start + merge->mod_len) - em->mod_start;
 		em->generation = max(em->generation, merge->generation);
-		set_bit(EXTENT_FLAG_MERGED, &em->flags);
+		em->flags |= EXTENT_FLAG_MERGED;
 		free_extent_map(merge);
 	}
 }
@@ -283,7 +283,7 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
 /*
  * Unpin an extent from the cache.
  *
- * @tree:	tree to unpin the extent in
+ * @inode:	the inode from which we are unpinning an extent range
  * @start:	logical offset in the file
  * @len:	length of the extent
  * @gen:	generation that this extent has been modified in
@@ -292,9 +292,10 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
  * to the generation that actually added the file item to the inode so we know
  * we need to sync this extent when we call fsync().
  */
-int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len,
-		       u64 gen)
+int unpin_extent_cache(struct btrfs_inode *inode, u64 start, u64 len, u64 gen)
 {
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
+	struct extent_map_tree *tree = &inode->extent_tree;
 	int ret = 0;
 	struct extent_map *em;
 	bool prealloc = false;
@@ -302,19 +303,28 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len,
 	write_lock(&tree->lock);
 	em = lookup_extent_mapping(tree, start, len);
 
-	WARN_ON(!em || em->start != start);
-
-	if (!em)
+	if (WARN_ON(!em)) {
+		btrfs_warn(fs_info,
+"no extent map found for inode %llu (root %lld) when unpinning extent range [%llu, %llu), generation %llu",
+			   btrfs_ino(inode), btrfs_root_id(inode->root),
+			   start, len, gen);
 		goto out;
+	}
+
+	if (WARN_ON(em->start != start))
+		btrfs_warn(fs_info,
+"found extent map for inode %llu (root %lld) with unexpected start offset %llu when unpinning extent range [%llu, %llu), generation %llu",
+			   btrfs_ino(inode), btrfs_root_id(inode->root),
+			   em->start, start, len, gen);
 
 	em->generation = gen;
-	clear_bit(EXTENT_FLAG_PINNED, &em->flags);
+	em->flags &= ~EXTENT_FLAG_PINNED;
 	em->mod_start = em->start;
 	em->mod_len = em->len;
 
-	if (test_bit(EXTENT_FLAG_FILLING, &em->flags)) {
+	if (em->flags & EXTENT_FLAG_FILLING) {
 		prealloc = true;
-		clear_bit(EXTENT_FLAG_FILLING, &em->flags);
+		em->flags &= ~EXTENT_FLAG_FILLING;
 	}
 
 	try_merge_map(tree, em);
@@ -335,7 +345,7 @@ void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em)
 {
 	lockdep_assert_held_write(&tree->lock);
 
-	clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
+	em->flags &= ~EXTENT_FLAG_LOGGING;
 	if (extent_map_in_tree(em))
 		try_merge_map(tree, em);
 }
@@ -348,45 +358,14 @@ static inline void setup_extent_mapping(struct extent_map_tree *tree,
 	em->mod_start = em->start;
 	em->mod_len = em->len;
 
+	ASSERT(list_empty(&em->list));
+
 	if (modified)
-		list_move(&em->list, &tree->modified_extents);
+		list_add(&em->list, &tree->modified_extents);
 	else
 		try_merge_map(tree, em);
 }
 
-static void extent_map_device_set_bits(struct extent_map *em, unsigned bits)
-{
-	struct map_lookup *map = em->map_lookup;
-	u64 stripe_size = em->orig_block_len;
-	int i;
-
-	for (i = 0; i < map->num_stripes; i++) {
-		struct btrfs_io_stripe *stripe = &map->stripes[i];
-		struct btrfs_device *device = stripe->dev;
-
-		set_extent_bit(&device->alloc_state, stripe->physical,
-			       stripe->physical + stripe_size - 1,
-			       bits | EXTENT_NOWAIT, NULL);
-	}
-}
-
-static void extent_map_device_clear_bits(struct extent_map *em, unsigned bits)
-{
-	struct map_lookup *map = em->map_lookup;
-	u64 stripe_size = em->orig_block_len;
-	int i;
-
-	for (i = 0; i < map->num_stripes; i++) {
-		struct btrfs_io_stripe *stripe = &map->stripes[i];
-		struct btrfs_device *device = stripe->dev;
-
-		__clear_extent_bit(&device->alloc_state, stripe->physical,
-				   stripe->physical + stripe_size - 1,
-				   bits | EXTENT_NOWAIT,
-				   NULL, NULL);
-	}
-}
-
 /*
  * Add new extent map to the extent tree
  *
@@ -400,8 +379,8 @@ static void extent_map_device_clear_bits(struct extent_map *em, unsigned bits)
  * into the tree directly, with an additional reference taken, or a
  * reference dropped if the merge attempt was successful.
  */
-int add_extent_mapping(struct extent_map_tree *tree,
-		       struct extent_map *em, int modified)
+static int add_extent_mapping(struct extent_map_tree *tree,
+			      struct extent_map *em, int modified)
 {
 	int ret = 0;
 
@@ -412,10 +391,6 @@ int add_extent_mapping(struct extent_map_tree *tree,
 		goto out;
 
 	setup_extent_mapping(tree, em, modified);
-	if (test_bit(EXTENT_FLAG_FS_MAPPING, &em->flags)) {
-		extent_map_device_set_bits(em, CHUNK_ALLOCATED);
-		extent_map_device_clear_bits(em, CHUNK_TRIMMED);
-	}
 out:
 	return ret;
 }
@@ -495,12 +470,10 @@ void remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em)
 {
 	lockdep_assert_held_write(&tree->lock);
 
-	WARN_ON(test_bit(EXTENT_FLAG_PINNED, &em->flags));
+	WARN_ON(em->flags & EXTENT_FLAG_PINNED);
 	rb_erase_cached(&em->rb_node, &tree->map);
-	if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags))
+	if (!(em->flags & EXTENT_FLAG_LOGGING))
 		list_del_init(&em->list);
-	if (test_bit(EXTENT_FLAG_FS_MAPPING, &em->flags))
-		extent_map_device_clear_bits(em, CHUNK_ALLOCATED);
 	RB_CLEAR_NODE(&em->rb_node);
 }
 
@@ -511,9 +484,9 @@ static void replace_extent_mapping(struct extent_map_tree *tree,
 {
 	lockdep_assert_held_write(&tree->lock);
 
-	WARN_ON(test_bit(EXTENT_FLAG_PINNED, &cur->flags));
+	WARN_ON(cur->flags & EXTENT_FLAG_PINNED);
 	ASSERT(extent_map_in_tree(cur));
-	if (!test_bit(EXTENT_FLAG_LOGGING, &cur->flags))
+	if (!(cur->flags & EXTENT_FLAG_LOGGING))
 		list_del_init(&cur->list);
 	rb_replace_node_cached(&cur->rb_node, &new->rb_node, &tree->map);
 	RB_CLEAR_NODE(&cur->rb_node);
@@ -576,7 +549,7 @@ static noinline int merge_extent_mapping(struct extent_map_tree *em_tree,
 	em->start = start;
 	em->len = end - start;
 	if (em->block_start < EXTENT_MAP_LAST_BYTE &&
-	    !test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
+	    !extent_map_is_compressed(em)) {
 		em->block_start += start_diff;
 		em->block_len = em->len;
 	}
@@ -626,8 +599,6 @@ int btrfs_add_extent_mapping(struct btrfs_fs_info *fs_info,
 	if (ret == -EEXIST) {
 		struct extent_map *existing;
 
-		ret = 0;
-
 		existing = search_extent_mapping(em_tree, start, len);
 
 		trace_btrfs_handle_em_exist(fs_info, existing, em, start, len);
@@ -681,8 +652,7 @@ static void drop_all_extent_maps_fast(struct extent_map_tree *tree)
 
 		node = rb_first_cached(&tree->map);
 		em = rb_entry(node, struct extent_map, rb_node);
-		clear_bit(EXTENT_FLAG_PINNED, &em->flags);
-		clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
+		em->flags &= ~(EXTENT_FLAG_PINNED | EXTENT_FLAG_LOGGING);
 		remove_extent_mapping(tree, em);
 		free_extent_map(em);
 		cond_resched_rwlock_write(&tree->lock);
@@ -758,19 +728,18 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end,
 			}
 		}
 
-		if (skip_pinned && test_bit(EXTENT_FLAG_PINNED, &em->flags)) {
+		if (skip_pinned && (em->flags & EXTENT_FLAG_PINNED)) {
 			start = em_end;
 			goto next;
 		}
 
 		flags = em->flags;
-		clear_bit(EXTENT_FLAG_PINNED, &em->flags);
 		/*
 		 * In case we split the extent map, we want to preserve the
 		 * EXTENT_FLAG_LOGGING flag on our extent map, but we don't want
 		 * it on the new extent maps.
 		 */
-		clear_bit(EXTENT_FLAG_LOGGING, &flags);
+		em->flags &= ~(EXTENT_FLAG_PINNED | EXTENT_FLAG_LOGGING);
 		modified = !list_empty(&em->list);
 
 		/*
@@ -781,7 +750,7 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end,
 			goto remove_em;
 
 		gen = em->generation;
-		compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
+		compressed = extent_map_is_compressed(em);
 
 		if (em->start < start) {
 			if (!split) {
@@ -814,7 +783,6 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end,
 
 			split->generation = gen;
 			split->flags = flags;
-			split->compress_type = em->compress_type;
 			replace_extent_mapping(em_tree, em, split, modified);
 			free_extent_map(split);
 			split = split2;
@@ -831,7 +799,6 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end,
 			split->len = em_end - end;
 			split->block_start = em->block_start;
 			split->flags = flags;
-			split->compress_type = em->compress_type;
 			split->generation = gen;
 
 			if (em->block_start < EXTENT_MAP_LAST_BYTE) {
@@ -997,14 +964,14 @@ int split_extent_map(struct btrfs_inode *inode, u64 start, u64 len, u64 pre,
 	}
 
 	ASSERT(em->len == len);
-	ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags));
+	ASSERT(!extent_map_is_compressed(em));
 	ASSERT(em->block_start < EXTENT_MAP_LAST_BYTE);
-	ASSERT(test_bit(EXTENT_FLAG_PINNED, &em->flags));
-	ASSERT(!test_bit(EXTENT_FLAG_LOGGING, &em->flags));
+	ASSERT(em->flags & EXTENT_FLAG_PINNED);
+	ASSERT(!(em->flags & EXTENT_FLAG_LOGGING));
 	ASSERT(!list_empty(&em->list));
 
 	flags = em->flags;
-	clear_bit(EXTENT_FLAG_PINNED, &em->flags);
+	em->flags &= ~EXTENT_FLAG_PINNED;
 
 	/* First, replace the em with a new extent_map starting from * em->start */
 	split_pre->start = em->start;
@@ -1015,7 +982,6 @@ int split_extent_map(struct btrfs_inode *inode, u64 start, u64 len, u64 pre,
 	split_pre->orig_block_len = split_pre->block_len;
 	split_pre->ram_bytes = split_pre->len;
 	split_pre->flags = flags;
-	split_pre->compress_type = em->compress_type;
 	split_pre->generation = em->generation;
 
 	replace_extent_mapping(em_tree, em, split_pre, 1);
@@ -1034,7 +1000,6 @@ int split_extent_map(struct btrfs_inode *inode, u64 start, u64 len, u64 pre,
 	split_mid->orig_block_len = split_mid->block_len;
 	split_mid->ram_bytes = split_mid->len;
 	split_mid->flags = flags;
-	split_mid->compress_type = em->compress_type;
 	split_mid->generation = em->generation;
 	add_extent_mapping(em_tree, split_mid, 1);
 
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index 35d27c756e08..e380fc08bbe4 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -5,30 +5,33 @@
 
 #include <linux/rbtree.h>
 #include <linux/refcount.h>
+#include "compression.h"
 
 #define EXTENT_MAP_LAST_BYTE ((u64)-4)
 #define EXTENT_MAP_HOLE ((u64)-3)
 #define EXTENT_MAP_INLINE ((u64)-2)
-/* used only during fiemap calls */
-#define EXTENT_MAP_DELALLOC ((u64)-1)
 
 /* bits for the extent_map::flags field */
 enum {
 	/* this entry not yet on disk, don't free it */
-	EXTENT_FLAG_PINNED,
-	EXTENT_FLAG_COMPRESSED,
+	ENUM_BIT(EXTENT_FLAG_PINNED),
+	ENUM_BIT(EXTENT_FLAG_COMPRESS_ZLIB),
+	ENUM_BIT(EXTENT_FLAG_COMPRESS_LZO),
+	ENUM_BIT(EXTENT_FLAG_COMPRESS_ZSTD),
 	/* pre-allocated extent */
-	EXTENT_FLAG_PREALLOC,
+	ENUM_BIT(EXTENT_FLAG_PREALLOC),
 	/* Logging this extent */
-	EXTENT_FLAG_LOGGING,
+	ENUM_BIT(EXTENT_FLAG_LOGGING),
 	/* Filling in a preallocated extent */
-	EXTENT_FLAG_FILLING,
-	/* filesystem extent mapping type */
-	EXTENT_FLAG_FS_MAPPING,
+	ENUM_BIT(EXTENT_FLAG_FILLING),
 	/* This em is merged from two or more physically adjacent ems */
-	EXTENT_FLAG_MERGED,
+	ENUM_BIT(EXTENT_FLAG_MERGED),
 };
 
+/*
+ * Keep this structure as compact as possible, as we can have really large
+ * amounts of allocated extent maps at any time.
+ */
 struct extent_map {
 	struct rb_node rb_node;
 
@@ -49,11 +52,8 @@ struct extent_map {
 	 * For non-merged extents, it's from btrfs_file_extent_item::generation.
 	 */
 	u64 generation;
-	unsigned long flags;
-	/* Used for chunk mappings, flag EXTENT_FLAG_FS_MAPPING must be set */
-	struct map_lookup *map_lookup;
+	u32 flags;
 	refcount_t refs;
-	unsigned int compress_type;
 	struct list_head list;
 };
 
@@ -65,30 +65,57 @@ struct extent_map_tree {
 
 struct btrfs_inode;
 
+static inline void extent_map_set_compression(struct extent_map *em,
+					      enum btrfs_compression_type type)
+{
+	if (type == BTRFS_COMPRESS_ZLIB)
+		em->flags |= EXTENT_FLAG_COMPRESS_ZLIB;
+	else if (type == BTRFS_COMPRESS_LZO)
+		em->flags |= EXTENT_FLAG_COMPRESS_LZO;
+	else if (type == BTRFS_COMPRESS_ZSTD)
+		em->flags |= EXTENT_FLAG_COMPRESS_ZSTD;
+}
+
+static inline enum btrfs_compression_type extent_map_compression(const struct extent_map *em)
+{
+	if (em->flags & EXTENT_FLAG_COMPRESS_ZLIB)
+		return BTRFS_COMPRESS_ZLIB;
+
+	if (em->flags & EXTENT_FLAG_COMPRESS_LZO)
+		return BTRFS_COMPRESS_LZO;
+
+	if (em->flags & EXTENT_FLAG_COMPRESS_ZSTD)
+		return BTRFS_COMPRESS_ZSTD;
+
+	return BTRFS_COMPRESS_NONE;
+}
+
+/*
+ * More efficient way to determine if extent is compressed, instead of using
+ * 'extent_map_compression() != BTRFS_COMPRESS_NONE'.
+ */
+static inline bool extent_map_is_compressed(const struct extent_map *em)
+{
+	return (em->flags & (EXTENT_FLAG_COMPRESS_ZLIB |
+			     EXTENT_FLAG_COMPRESS_LZO |
+			     EXTENT_FLAG_COMPRESS_ZSTD)) != 0;
+}
+
 static inline int extent_map_in_tree(const struct extent_map *em)
 {
 	return !RB_EMPTY_NODE(&em->rb_node);
 }
 
-static inline u64 extent_map_end(struct extent_map *em)
+static inline u64 extent_map_end(const struct extent_map *em)
 {
 	if (em->start + em->len < em->start)
 		return (u64)-1;
 	return em->start + em->len;
 }
 
-static inline u64 extent_map_block_end(struct extent_map *em)
-{
-	if (em->block_start + em->block_len < em->block_start)
-		return (u64)-1;
-	return em->block_start + em->block_len;
-}
-
 void extent_map_tree_init(struct extent_map_tree *tree);
 struct extent_map *lookup_extent_mapping(struct extent_map_tree *tree,
 					 u64 start, u64 len);
-int add_extent_mapping(struct extent_map_tree *tree,
-		       struct extent_map *em, int modified);
 void remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em);
 int split_extent_map(struct btrfs_inode *inode, u64 start, u64 len, u64 pre,
 		     u64 new_logical);
@@ -97,7 +124,7 @@ struct extent_map *alloc_extent_map(void);
 void free_extent_map(struct extent_map *em);
 int __init extent_map_init(void);
 void __cold extent_map_exit(void);
-int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len, u64 gen);
+int unpin_extent_cache(struct btrfs_inode *inode, u64 start, u64 len, u64 gen);
 void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em);
 struct extent_map *search_extent_mapping(struct extent_map_tree *tree,
 					 u64 start, u64 len);
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 45cae356e89b..81ac1d474bf1 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -59,7 +59,7 @@ void btrfs_inode_safe_disk_i_size_write(struct btrfs_inode *inode, u64 new_i_siz
 		goto out_unlock;
 	}
 
-	ret = find_contiguous_extent_bit(&inode->file_extent_tree, 0, &start,
+	ret = find_contiguous_extent_bit(inode->file_extent_tree, 0, &start,
 					 &end, EXTENT_DIRTY);
 	if (!ret && start == 0)
 		i_size = min(i_size, end + 1);
@@ -94,7 +94,7 @@ int btrfs_inode_set_file_extent_range(struct btrfs_inode *inode, u64 start,
 
 	if (btrfs_fs_incompat(inode->root->fs_info, NO_HOLES))
 		return 0;
-	return set_extent_bit(&inode->file_extent_tree, start, start + len - 1,
+	return set_extent_bit(inode->file_extent_tree, start, start + len - 1,
 			      EXTENT_DIRTY, NULL);
 }
 
@@ -123,7 +123,7 @@ int btrfs_inode_clear_file_extent_range(struct btrfs_inode *inode, u64 start,
 
 	if (btrfs_fs_incompat(inode->root->fs_info, NO_HOLES))
 		return 0;
-	return clear_extent_bit(&inode->file_extent_tree, start,
+	return clear_extent_bit(inode->file_extent_tree, start,
 				start + len - 1, EXTENT_DIRTY, NULL);
 }
 
@@ -1294,8 +1294,7 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 			return;
 		}
 		if (compress_type != BTRFS_COMPRESS_NONE) {
-			set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
-			em->compress_type = compress_type;
+			extent_map_set_compression(em, compress_type);
 			em->block_start = bytenr;
 			em->block_len = em->orig_block_len;
 		} else {
@@ -1303,7 +1302,7 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 			em->block_start = bytenr;
 			em->block_len = em->len;
 			if (type == BTRFS_FILE_EXTENT_PREALLOC)
-				set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
+				em->flags |= EXTENT_FLAG_PREALLOC;
 		}
 	} else if (type == BTRFS_FILE_EXTENT_INLINE) {
 		em->block_start = EXTENT_MAP_INLINE;
@@ -1315,9 +1314,7 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 		 */
 		em->orig_start = EXTENT_MAP_HOLE;
 		em->block_len = (u64)-1;
-		em->compress_type = compress_type;
-		if (compress_type != BTRFS_COMPRESS_NONE)
-			set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
+		extent_map_set_compression(em, compress_type);
 	} else {
 		btrfs_err(fs_info,
 			  "unknown file extent item type %d, inode %llu, offset %llu, "
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index f47731c45bb5..38dfcac47609 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -111,8 +111,8 @@ static void btrfs_drop_pages(struct btrfs_fs_info *fs_info,
 		 * accessed as prepare_pages should have marked them accessed
 		 * in prepare_pages via find_or_create_page()
 		 */
-		btrfs_page_clamp_clear_checked(fs_info, pages[i], block_start,
-					       block_len);
+		btrfs_folio_clamp_clear_checked(fs_info, page_folio(pages[i]),
+						block_start, block_len);
 		unlock_page(pages[i]);
 		put_page(pages[i]);
 	}
@@ -168,9 +168,12 @@ int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages,
 	for (i = 0; i < num_pages; i++) {
 		struct page *p = pages[i];
 
-		btrfs_page_clamp_set_uptodate(fs_info, p, start_pos, num_bytes);
-		btrfs_page_clamp_clear_checked(fs_info, p, start_pos, num_bytes);
-		btrfs_page_clamp_set_dirty(fs_info, p, start_pos, num_bytes);
+		btrfs_folio_clamp_set_uptodate(fs_info, page_folio(p),
+					       start_pos, num_bytes);
+		btrfs_folio_clamp_clear_checked(fs_info, page_folio(p),
+						start_pos, num_bytes);
+		btrfs_folio_clamp_set_dirty(fs_info, page_folio(p),
+					    start_pos, num_bytes);
 	}
 
 	/*
@@ -869,9 +872,9 @@ static int prepare_uptodate_page(struct inode *inode,
 		 * released.
 		 *
 		 * The private flag check is essential for subpage as we need
-		 * to store extra bitmap using page->private.
+		 * to store extra bitmap using folio private.
 		 */
-		if (page->mapping != inode->i_mapping || !PagePrivate(page)) {
+		if (page->mapping != inode->i_mapping || !folio_test_private(folio)) {
 			unlock_page(page);
 			return -EAGAIN;
 		}
@@ -2150,7 +2153,6 @@ out:
 		hole_em->block_start = EXTENT_MAP_HOLE;
 		hole_em->block_len = 0;
 		hole_em->orig_block_len = 0;
-		hole_em->compress_type = BTRFS_COMPRESS_NONE;
 		hole_em->generation = trans->transid;
 
 		ret = btrfs_replace_extent_map_range(inode, hole_em, true);
@@ -2839,7 +2841,7 @@ static int btrfs_zero_range_check_range_boundary(struct btrfs_inode *inode,
 
 	if (em->block_start == EXTENT_MAP_HOLE)
 		ret = RANGE_BOUNDARY_HOLE;
-	else if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+	else if (em->flags & EXTENT_FLAG_PREALLOC)
 		ret = RANGE_BOUNDARY_PREALLOC_EXTENT;
 	else
 		ret = RANGE_BOUNDARY_WRITTEN_EXTENT;
@@ -2879,8 +2881,7 @@ static int btrfs_zero_range(struct inode *inode,
 	 * extents and holes, we drop all the existing extents and allocate a
 	 * new prealloc extent, so that we get a larger contiguous disk extent.
 	 */
-	if (em->start <= alloc_start &&
-	    test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
+	if (em->start <= alloc_start && (em->flags & EXTENT_FLAG_PREALLOC)) {
 		const u64 em_end = em->start + em->len;
 
 		if (em_end >= offset + len) {
@@ -2915,7 +2916,7 @@ static int btrfs_zero_range(struct inode *inode,
 			goto out;
 		}
 
-		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
+		if (em->flags & EXTENT_FLAG_PREALLOC) {
 			free_extent_map(em);
 			ret = btrfs_fallocate_update_isize(inode, offset + len,
 							   mode);
@@ -3136,7 +3137,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 		last_byte = ALIGN(last_byte, blocksize);
 		if (em->block_start == EXTENT_MAP_HOLE ||
 		    (cur_offset >= inode->i_size &&
-		     !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) {
+		     !(em->flags & EXTENT_FLAG_PREALLOC))) {
 			const u64 range_len = last_byte - cur_offset;
 
 			ret = add_falloc_range(&reserve_list, cur_offset, range_len);
@@ -3192,7 +3193,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 			qgroup_reserved -= range->len;
 		} else if (qgroup_reserved > 0) {
 			btrfs_qgroup_free_data(BTRFS_I(inode), data_reserved,
-					       range->start, range->len);
+					       range->start, range->len, NULL);
 			qgroup_reserved -= range->len;
 		}
 		list_del(&range->list);
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 6f93c9a2c3e3..d372c7ce0e6b 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -439,8 +439,8 @@ static void io_ctl_drop_pages(struct btrfs_io_ctl *io_ctl)
 
 	for (i = 0; i < io_ctl->num_pages; i++) {
 		if (io_ctl->pages[i]) {
-			btrfs_page_clear_checked(io_ctl->fs_info,
-					io_ctl->pages[i],
+			btrfs_folio_clear_checked(io_ctl->fs_info,
+					page_folio(io_ctl->pages[i]),
 					page_offset(io_ctl->pages[i]),
 					PAGE_SIZE);
 			unlock_page(io_ctl->pages[i]);
diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h
index 318df6f9d9cb..f8bb73d6ab68 100644
--- a/fs/btrfs/fs.h
+++ b/fs/btrfs/fs.h
@@ -188,6 +188,7 @@ enum {
 	BTRFS_MOUNT_IGNOREBADROOTS		= (1UL << 27),
 	BTRFS_MOUNT_IGNOREDATACSUMS		= (1UL << 28),
 	BTRFS_MOUNT_NODISCARD			= (1UL << 29),
+	BTRFS_MOUNT_NOSPACECACHE		= (1UL << 30),
 };
 
 /*
@@ -398,7 +399,8 @@ struct btrfs_fs_info {
 	struct extent_io_tree excluded_extents;
 
 	/* logical->physical extent mapping */
-	struct extent_map_tree mapping_tree;
+	struct rb_root_cached mapping_tree;
+	rwlock_t mapping_tree_lock;
 
 	/*
 	 * Block reservation for extent, checksum, root tree and delayed dir
@@ -960,20 +962,6 @@ void __btrfs_clear_fs_compat_ro(struct btrfs_fs_info *fs_info, u64 flag,
 #define btrfs_test_opt(fs_info, opt)	((fs_info)->mount_opt & \
 					 BTRFS_MOUNT_##opt)
 
-#define btrfs_set_and_info(fs_info, opt, fmt, args...)			\
-do {									\
-	if (!btrfs_test_opt(fs_info, opt))				\
-		btrfs_info(fs_info, fmt, ##args);			\
-	btrfs_set_opt(fs_info->mount_opt, opt);				\
-} while (0)
-
-#define btrfs_clear_and_info(fs_info, opt, fmt, args...)		\
-do {									\
-	if (btrfs_test_opt(fs_info, opt))				\
-		btrfs_info(fs_info, fmt, ##args);			\
-	btrfs_clear_opt(fs_info->mount_opt, opt);			\
-} while (0)
-
 static inline int btrfs_fs_closing(struct btrfs_fs_info *fs_info)
 {
 	/* Do it this way so we only ever do one test_bit in the normal case. */
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5e3fccddde0c..809b11472a80 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -114,6 +114,15 @@ struct data_reloc_warn {
 	int mirror_num;
 };
 
+/*
+ * For the file_extent_tree, we want to hold the inode lock when we lookup and
+ * update the disk_i_size, but lockdep will complain because our io_tree we hold
+ * the tree lock and get the inode lock when setting delalloc. These two things
+ * are unrelated, so make a class for the file_extent_tree so we don't get the
+ * two locking patterns mixed up.
+ */
+static struct lock_class_key file_extent_tree_class;
+
 static const struct inode_operations btrfs_dir_inode_operations;
 static const struct inode_operations btrfs_symlink_inode_operations;
 static const struct inode_operations btrfs_special_inode_operations;
@@ -447,8 +456,8 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode,
 		 * range, then btrfs_mark_ordered_io_finished() will handle
 		 * the ordered extent accounting for the range.
 		 */
-		btrfs_page_clamp_clear_ordered(inode->root->fs_info, page,
-					       offset, bytes);
+		btrfs_folio_clamp_clear_ordered(inode->root->fs_info,
+						page_folio(page), offset, bytes);
 		put_page(page);
 	}
 
@@ -688,7 +697,7 @@ out:
 	 * And at reserve time, it's always aligned to page size, so
 	 * just free one page here.
 	 */
-	btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE);
+	btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE, NULL);
 	btrfs_free_path(path);
 	btrfs_end_transaction(trans);
 	return ret;
@@ -1037,7 +1046,7 @@ free_pages:
 	if (pages) {
 		for (i = 0; i < nr_pages; i++) {
 			WARN_ON(pages[i]->mapping);
-			put_page(pages[i]);
+			btrfs_free_compr_page(pages[i]);
 		}
 		kfree(pages);
 	}
@@ -1052,7 +1061,7 @@ static void free_async_extent_pages(struct async_extent *async_extent)
 
 	for (i = 0; i < async_extent->nr_pages; i++) {
 		WARN_ON(async_extent->pages[i]->mapping);
-		put_page(async_extent->pages[i]);
+		btrfs_free_compr_page(async_extent->pages[i]);
 	}
 	kfree(async_extent->pages);
 	async_extent->nr_pages = 0;
@@ -2793,7 +2802,7 @@ out_page:
 					       PAGE_SIZE, !ret);
 		clear_page_dirty_for_io(page);
 	}
-	btrfs_page_clear_checked(fs_info, page, page_start, PAGE_SIZE);
+	btrfs_folio_clear_checked(fs_info, page_folio(page), page_start, PAGE_SIZE);
 	unlock_page(page);
 	put_page(page);
 	kfree(fixup);
@@ -2848,7 +2857,7 @@ int btrfs_writepage_cow_fixup(struct page *page)
 	 * page->mapping outside of the page lock.
 	 */
 	ihold(inode);
-	btrfs_page_set_checked(fs_info, page, page_offset(page), PAGE_SIZE);
+	btrfs_folio_set_checked(fs_info, page_folio(page), page_offset(page), PAGE_SIZE);
 	get_page(page);
 	btrfs_init_work(&fixup->work, btrfs_writepage_fixup_worker, NULL);
 	fixup->page = page;
@@ -3118,7 +3127,7 @@ int btrfs_finish_one_ordered(struct btrfs_ordered_extent *ordered_extent)
 						ordered_extent->disk_num_bytes);
 		}
 	}
-	unpin_extent_cache(&inode->extent_tree, ordered_extent->file_offset,
+	unpin_extent_cache(inode, ordered_extent->file_offset,
 			   ordered_extent->num_bytes, trans->transid);
 	if (ret < 0) {
 		btrfs_abort_transaction(trans, ret);
@@ -3796,7 +3805,7 @@ cache_index:
 	 * cache.
 	 *
 	 * This is required for both inode re-read from disk and delayed inode
-	 * in delayed_nodes_tree.
+	 * in the delayed_nodes xarray.
 	 */
 	if (BTRFS_I(inode)->last_trans == btrfs_get_fs_generation(fs_info))
 		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
@@ -4725,7 +4734,7 @@ again:
 	/*
 	 * We unlock the page after the io is completed and then re-lock it
 	 * above.  release_folio() could have come in between that and cleared
-	 * PagePrivate(), but left the page in the mapping.  Set the page mapped
+	 * folio private, but left the page in the mapping.  Set the page mapped
 	 * here to make sure it's properly set for the subpage stuff.
 	 */
 	ret = set_page_extent_mapped(page);
@@ -4767,9 +4776,10 @@ again:
 			memzero_page(page, (block_start - page_offset(page)) + offset,
 				     len);
 	}
-	btrfs_page_clear_checked(fs_info, page, block_start,
-				 block_end + 1 - block_start);
-	btrfs_page_set_dirty(fs_info, page, block_start, block_end + 1 - block_start);
+	btrfs_folio_clear_checked(fs_info, page_folio(page), block_start,
+				  block_end + 1 - block_start);
+	btrfs_folio_set_dirty(fs_info, page_folio(page), block_start,
+			      block_end + 1 - block_start);
 	unlock_extent(io_tree, block_start, block_end, &cached_state);
 
 	if (only_release_metadata)
@@ -4889,7 +4899,7 @@ int btrfs_cont_expand(struct btrfs_inode *inode, loff_t oldsize, loff_t size)
 		last_byte = ALIGN(last_byte, fs_info->sectorsize);
 		hole_size = last_byte - cur_offset;
 
-		if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
+		if (!(em->flags & EXTENT_FLAG_PREALLOC)) {
 			struct extent_map *hole_em;
 
 			err = maybe_insert_hole(inode, cur_offset, hole_size);
@@ -4917,7 +4927,6 @@ int btrfs_cont_expand(struct btrfs_inode *inode, loff_t oldsize, loff_t size)
 			hole_em->block_len = 0;
 			hole_em->orig_block_len = 0;
 			hole_em->ram_bytes = hole_size;
-			hole_em->compress_type = BTRFS_COMPRESS_NONE;
 			hole_em->generation = btrfs_get_fs_generation(fs_info);
 
 			err = btrfs_replace_extent_map_range(inode, hole_em, true);
@@ -5132,7 +5141,7 @@ static void evict_inode_truncate_pages(struct inode *inode)
 		 */
 		if (state_flags & EXTENT_DELALLOC)
 			btrfs_qgroup_free_data(BTRFS_I(inode), NULL, start,
-					       end - start + 1);
+					       end - start + 1, NULL);
 
 		clear_extent_bit(io_tree, start, end,
 				 EXTENT_CLEAR_ALL_BITS | EXTENT_DO_ACCOUNTING,
@@ -6217,6 +6226,13 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
 	inode->i_generation = BTRFS_I(inode)->generation;
 
 	/*
+	 * We don't have any capability xattrs set here yet, shortcut any
+	 * queries for the xattrs here.  If we add them later via the inode
+	 * security init path or any other path this flag will be cleared.
+	 */
+	set_bit(BTRFS_INODE_NO_CAP_XATTR, &BTRFS_I(inode)->runtime_flags);
+
+	/*
 	 * Subvolumes don't inherit flags from their parent directory.
 	 * Originally this was probably by accident, but we probably can't
 	 * change it now without compatibility issues.
@@ -6983,8 +6999,15 @@ static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode,
 	int ret;
 
 	alloc_hint = get_extent_allocation_hint(inode, start, len);
+again:
 	ret = btrfs_reserve_extent(root, len, len, fs_info->sectorsize,
 				   0, alloc_hint, &ins, 1, 1);
+	if (ret == -EAGAIN) {
+		ASSERT(btrfs_is_zoned(fs_info));
+		wait_on_bit_io(&inode->root->fs_info->flags, BTRFS_FS_NEED_ZONE_FINISH,
+			       TASK_UNINTERRUPTIBLE);
+		goto again;
+	}
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -7251,13 +7274,11 @@ static struct extent_map *create_io_em(struct btrfs_inode *inode, u64 start,
 	em->orig_block_len = orig_block_len;
 	em->ram_bytes = ram_bytes;
 	em->generation = -1;
-	set_bit(EXTENT_FLAG_PINNED, &em->flags);
-	if (type == BTRFS_ORDERED_PREALLOC) {
-		set_bit(EXTENT_FLAG_FILLING, &em->flags);
-	} else if (type == BTRFS_ORDERED_COMPRESSED) {
-		set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
-		em->compress_type = compress_type;
-	}
+	em->flags |= EXTENT_FLAG_PINNED;
+	if (type == BTRFS_ORDERED_PREALLOC)
+		em->flags |= EXTENT_FLAG_FILLING;
+	else if (type == BTRFS_ORDERED_COMPRESSED)
+		extent_map_set_compression(em, compress_type);
 
 	ret = btrfs_replace_extent_map_range(inode, em, true);
 	if (ret) {
@@ -7297,10 +7318,10 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 	 * just use the extent.
 	 *
 	 */
-	if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) ||
+	if ((em->flags & EXTENT_FLAG_PREALLOC) ||
 	    ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
 	     em->block_start != EXTENT_MAP_HOLE)) {
-		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+		if (em->flags & EXTENT_FLAG_PREALLOC)
 			type = BTRFS_ORDERED_PREALLOC;
 		else
 			type = BTRFS_ORDERED_NOCOW;
@@ -7535,7 +7556,7 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 	 * to buffered IO.  Don't blame me, this is the price we pay for using
 	 * the generic code.
 	 */
-	if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) ||
+	if (extent_map_is_compressed(em) ||
 	    em->block_start == EXTENT_MAP_INLINE) {
 		free_extent_map(em);
 		/*
@@ -7631,7 +7652,7 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 	 * that, since we have locked only the parts we are performing I/O in.
 	 */
 	if ((em->block_start == EXTENT_MAP_HOLE) ||
-	    (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) && !write)) {
+	    ((em->flags & EXTENT_FLAG_PREALLOC) && !write)) {
 		iomap->addr = IOMAP_NULL_ADDR;
 		iomap->type = IOMAP_HOLE;
 	} else {
@@ -7844,13 +7865,14 @@ static void btrfs_readahead(struct readahead_control *rac)
 static void wait_subpage_spinlock(struct page *page)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
+	struct folio *folio = page_folio(page);
 	struct btrfs_subpage *subpage;
 
-	if (!btrfs_is_subpage(fs_info, page))
+	if (!btrfs_is_subpage(fs_info, page->mapping))
 		return;
 
-	ASSERT(PagePrivate(page) && page->private);
-	subpage = (struct btrfs_subpage *)page->private;
+	ASSERT(folio_test_private(folio) && folio_get_private(folio));
+	subpage = folio_get_private(folio);
 
 	/*
 	 * This may look insane as we just acquire the spinlock and release it,
@@ -7988,7 +8010,7 @@ static void btrfs_invalidate_folio(struct folio *folio, size_t offset,
 				page_end);
 		ASSERT(range_end + 1 - cur < U32_MAX);
 		range_len = range_end + 1 - cur;
-		if (!btrfs_page_test_ordered(fs_info, &folio->page, cur, range_len)) {
+		if (!btrfs_folio_test_ordered(fs_info, folio, cur, range_len)) {
 			/*
 			 * If Ordered (Private2) is cleared, it means endio has
 			 * already been executed for the range.
@@ -7997,7 +8019,7 @@ static void btrfs_invalidate_folio(struct folio *folio, size_t offset,
 			 */
 			goto next;
 		}
-		btrfs_page_clear_ordered(fs_info, &folio->page, cur, range_len);
+		btrfs_folio_clear_ordered(fs_info, folio, cur, range_len);
 
 		/*
 		 * IO on this page will never be started, so we need to account
@@ -8052,7 +8074,7 @@ next:
 		 *    reserved data space.
 		 *    Since the IO will never happen for this page.
 		 */
-		btrfs_qgroup_free_data(inode, NULL, cur, range_end + 1 - cur);
+		btrfs_qgroup_free_data(inode, NULL, cur, range_end + 1 - cur, NULL);
 		if (!inode_evicting) {
 			clear_extent_bit(tree, cur, range_end, EXTENT_LOCKED |
 				 EXTENT_DELALLOC | EXTENT_UPTODATE |
@@ -8067,7 +8089,7 @@ next:
 	 * did something wrong.
 	 */
 	ASSERT(!folio_test_ordered(folio));
-	btrfs_page_clear_checked(fs_info, &folio->page, folio_pos(folio), folio_size(folio));
+	btrfs_folio_clear_checked(fs_info, folio, folio_pos(folio), folio_size(folio));
 	if (!inode_evicting)
 		__btrfs_release_folio(folio, GFP_NOFS);
 	clear_page_extent_mapped(&folio->page);
@@ -8091,6 +8113,7 @@ next:
 vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
 {
 	struct page *page = vmf->page;
+	struct folio *folio = page_folio(page);
 	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
@@ -8107,6 +8130,8 @@ vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
 	u64 page_end;
 	u64 end;
 
+	ASSERT(folio_order(folio) == 0);
+
 	reserved_space = PAGE_SIZE;
 
 	sb_start_pagefault(inode->i_sb);
@@ -8210,9 +8235,9 @@ again:
 	if (zero_start != PAGE_SIZE)
 		memzero_page(page, zero_start, PAGE_SIZE - zero_start);
 
-	btrfs_page_clear_checked(fs_info, page, page_start, PAGE_SIZE);
-	btrfs_page_set_dirty(fs_info, page, page_start, end + 1 - page_start);
-	btrfs_page_set_uptodate(fs_info, page, page_start, end + 1 - page_start);
+	btrfs_folio_clear_checked(fs_info, folio, page_start, PAGE_SIZE);
+	btrfs_folio_set_dirty(fs_info, folio, page_start, end + 1 - page_start);
+	btrfs_folio_set_uptodate(fs_info, folio, page_start, end + 1 - page_start);
 
 	btrfs_set_inode_last_sub_trans(BTRFS_I(inode));
 
@@ -8455,10 +8480,20 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
 	struct btrfs_inode *ei;
 	struct inode *inode;
+	struct extent_io_tree *file_extent_tree = NULL;
+
+	/* Self tests may pass a NULL fs_info. */
+	if (fs_info && !btrfs_fs_incompat(fs_info, NO_HOLES)) {
+		file_extent_tree = kmalloc(sizeof(struct extent_io_tree), GFP_KERNEL);
+		if (!file_extent_tree)
+			return NULL;
+	}
 
 	ei = alloc_inode_sb(sb, btrfs_inode_cachep, GFP_KERNEL);
-	if (!ei)
+	if (!ei) {
+		kfree(file_extent_tree);
 		return NULL;
+	}
 
 	ei->root = NULL;
 	ei->generation = 0;
@@ -8494,10 +8529,18 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 
 	inode = &ei->vfs_inode;
 	extent_map_tree_init(&ei->extent_tree);
+
+	/* This io tree sets the valid inode. */
 	extent_io_tree_init(fs_info, &ei->io_tree, IO_TREE_INODE_IO);
 	ei->io_tree.inode = ei;
-	extent_io_tree_init(fs_info, &ei->file_extent_tree,
-			    IO_TREE_INODE_FILE_EXTENT);
+
+	ei->file_extent_tree = file_extent_tree;
+	if (file_extent_tree) {
+		extent_io_tree_init(fs_info, ei->file_extent_tree,
+				    IO_TREE_INODE_FILE_EXTENT);
+		/* Lockdep class is set only for the file extent tree. */
+		lockdep_set_class(&ei->file_extent_tree->lock, &file_extent_tree_class);
+	}
 	mutex_init(&ei->log_mutex);
 	spin_lock_init(&ei->ordered_tree_lock);
 	ei->ordered_tree = RB_ROOT;
@@ -8514,12 +8557,14 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 void btrfs_test_destroy_inode(struct inode *inode)
 {
 	btrfs_drop_extent_map_range(BTRFS_I(inode), 0, (u64)-1, false);
+	kfree(BTRFS_I(inode)->file_extent_tree);
 	kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode));
 }
 #endif
 
 void btrfs_free_inode(struct inode *inode)
 {
+	kfree(BTRFS_I(inode)->file_extent_tree);
 	kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode));
 }
 
@@ -9484,7 +9529,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
 	struct btrfs_path *path;
 	u64 start = ins->objectid;
 	u64 len = ins->offset;
-	int qgroup_released;
+	u64 qgroup_released = 0;
 	int ret;
 
 	memset(&stack_fi, 0, sizeof(stack_fi));
@@ -9497,9 +9542,9 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
 	btrfs_set_stack_file_extent_compression(&stack_fi, BTRFS_COMPRESS_NONE);
 	/* Encryption and other encoding is reserved and all 0 */
 
-	qgroup_released = btrfs_qgroup_release_data(inode, file_offset, len);
-	if (qgroup_released < 0)
-		return ERR_PTR(qgroup_released);
+	ret = btrfs_qgroup_release_data(inode, file_offset, len, &qgroup_released);
+	if (ret < 0)
+		return ERR_PTR(ret);
 
 	if (trans) {
 		ret = insert_reserved_file_extent(trans, inode,
@@ -9625,7 +9670,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 		em->block_len = ins.offset;
 		em->orig_block_len = ins.offset;
 		em->ram_bytes = ins.offset;
-		set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
+		em->flags |= EXTENT_FLAG_PREALLOC;
 		em->generation = trans->transid;
 
 		ret = btrfs_replace_extent_map_range(BTRFS_I(inode), em, true);
@@ -9778,7 +9823,9 @@ void btrfs_set_range_writeback(struct btrfs_inode *inode, u64 start, u64 end)
 		page = find_get_page(inode->vfs_inode.i_mapping, index);
 		ASSERT(page); /* Pages should be in the extent_io_tree */
 
-		btrfs_page_set_writeback(fs_info, page, start, len);
+		/* This is for data, which doesn't yet support larger folio. */
+		ASSERT(folio_order(page_folio(page)) == 0);
+		btrfs_folio_set_writeback(fs_info, page_folio(page), start, len);
 		put_page(page);
 		index++;
 	}
@@ -9987,7 +10034,7 @@ static ssize_t btrfs_encoded_read_regular(struct kiocb *iocb,
 	pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS);
 	if (!pages)
 		return -ENOMEM;
-	ret = btrfs_alloc_page_array(nr_pages, pages);
+	ret = btrfs_alloc_page_array(nr_pages, pages, 0);
 	if (ret) {
 		ret = -ENOMEM;
 		goto out;
@@ -10106,12 +10153,12 @@ ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter,
 	encoded->len = min_t(u64, extent_map_end(em),
 			     inode->vfs_inode.i_size) - iocb->ki_pos;
 	if (em->block_start == EXTENT_MAP_HOLE ||
-	    test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
+	    (em->flags & EXTENT_FLAG_PREALLOC)) {
 		disk_bytenr = EXTENT_MAP_HOLE;
 		count = min_t(u64, count, encoded->len);
 		encoded->len = count;
 		encoded->unencoded_len = count;
-	} else if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
+	} else if (extent_map_is_compressed(em)) {
 		disk_bytenr = em->block_start;
 		/*
 		 * Bail if the buffer isn't large enough to return the whole
@@ -10126,7 +10173,7 @@ ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter,
 		encoded->unencoded_len = em->ram_bytes;
 		encoded->unencoded_offset = iocb->ki_pos - em->orig_start;
 		ret = btrfs_encoded_io_compression_from_extent(fs_info,
-							     em->compress_type);
+							       extent_map_compression(em));
 		if (ret < 0)
 			goto out_em;
 		encoded->compression = ret;
@@ -10394,7 +10441,7 @@ out_delalloc_release:
 	btrfs_delalloc_release_metadata(inode, disk_num_bytes, ret < 0);
 out_qgroup_free_data:
 	if (ret < 0)
-		btrfs_qgroup_free_data(inode, data_reserved, start, num_bytes);
+		btrfs_qgroup_free_data(inode, data_reserved, start, num_bytes, NULL);
 out_free_data_space:
 	/*
 	 * If btrfs_reserve_extent() succeeded, then we already decremented
@@ -10557,6 +10604,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct extent_state *cached_state = NULL;
 	struct extent_map *em = NULL;
+	struct btrfs_chunk_map *map = NULL;
 	struct btrfs_device *device = NULL;
 	struct btrfs_swap_info bsi = {
 		.lowest_ppage = (sector_t)-1ULL,
@@ -10673,7 +10721,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 			ret = -EINVAL;
 			goto out;
 		}
-		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
+		if (extent_map_is_compressed(em)) {
 			btrfs_warn(fs_info, "swapfile must not be compressed");
 			ret = -EINVAL;
 			goto out;
@@ -10696,13 +10744,13 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 			goto out;
 		}
 
-		em = btrfs_get_chunk_map(fs_info, logical_block_start, len);
-		if (IS_ERR(em)) {
-			ret = PTR_ERR(em);
+		map = btrfs_get_chunk_map(fs_info, logical_block_start, len);
+		if (IS_ERR(map)) {
+			ret = PTR_ERR(map);
 			goto out;
 		}
 
-		if (em->map_lookup->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
+		if (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
 			btrfs_warn(fs_info,
 				   "swapfile must have single data profile");
 			ret = -EINVAL;
@@ -10710,23 +10758,23 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 		}
 
 		if (device == NULL) {
-			device = em->map_lookup->stripes[0].dev;
+			device = map->stripes[0].dev;
 			ret = btrfs_add_swapfile_pin(inode, device, false);
 			if (ret == 1)
 				ret = 0;
 			else if (ret)
 				goto out;
-		} else if (device != em->map_lookup->stripes[0].dev) {
+		} else if (device != map->stripes[0].dev) {
 			btrfs_warn(fs_info, "swapfile must be on one device");
 			ret = -EINVAL;
 			goto out;
 		}
 
-		physical_block_start = (em->map_lookup->stripes[0].physical +
-					(logical_block_start - em->start));
-		len = min(len, em->len - (logical_block_start - em->start));
-		free_extent_map(em);
-		em = NULL;
+		physical_block_start = (map->stripes[0].physical +
+					(logical_block_start - map->start));
+		len = min(len, map->chunk_len - (logical_block_start - map->start));
+		btrfs_free_chunk_map(map);
+		map = NULL;
 
 		bg = btrfs_lookup_block_group(fs_info, logical_block_start);
 		if (!bg) {
@@ -10779,6 +10827,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 out:
 	if (!IS_ERR_OR_NULL(em))
 		free_extent_map(em);
+	if (!IS_ERR_OR_NULL(map))
+		btrfs_free_chunk_map(map);
 
 	unlock_extent(io_tree, 0, isize - 1, &cached_state);
 
@@ -10923,7 +10973,7 @@ static const struct address_space_operations btrfs_aops = {
 	.release_folio	= btrfs_release_folio,
 	.migrate_folio	= btrfs_migrate_folio,
 	.dirty_folio	= filemap_dirty_folio,
-	.error_remove_page = generic_error_remove_page,
+	.error_remove_folio = generic_error_remove_folio,
 	.swap_activate	= btrfs_swap_activate,
 	.swap_deactivate = btrfs_swap_deactivate,
 };
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 752acff2c734..41b479861b3c 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1290,6 +1290,15 @@ static noinline int __btrfs_ioctl_snap_create(struct file *file,
 			 * are limited to own subvolumes only
 			 */
 			ret = -EPERM;
+		} else if (btrfs_ino(BTRFS_I(src_inode)) != BTRFS_FIRST_FREE_OBJECTID) {
+			/*
+			 * Snapshots must be made with the src_inode referring
+			 * to the subvolume inode, otherwise the permission
+			 * checking above is useless because we may have
+			 * permission on a lower directory but not the subvol
+			 * itself.
+			 */
+			ret = -EINVAL;
 		} else {
 			ret = btrfs_mksnapshot(&file->f_path, idmap,
 					       name, namelen,
@@ -1528,7 +1537,7 @@ static noinline int key_in_sk(struct btrfs_key *key,
 static noinline int copy_to_sk(struct btrfs_path *path,
 			       struct btrfs_key *key,
 			       struct btrfs_ioctl_search_key *sk,
-			       size_t *buf_size,
+			       u64 *buf_size,
 			       char __user *ubuf,
 			       unsigned long *sk_offset,
 			       int *num_found)
@@ -1660,7 +1669,7 @@ out:
 
 static noinline int search_ioctl(struct inode *inode,
 				 struct btrfs_ioctl_search_key *sk,
-				 size_t *buf_size,
+				 u64 *buf_size,
 				 char __user *ubuf)
 {
 	struct btrfs_fs_info *info = btrfs_sb(inode->i_sb);
@@ -1733,7 +1742,7 @@ static noinline int btrfs_ioctl_tree_search(struct inode *inode,
 	struct btrfs_ioctl_search_args __user *uargs = argp;
 	struct btrfs_ioctl_search_key sk;
 	int ret;
-	size_t buf_size;
+	u64 buf_size;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -1763,8 +1772,8 @@ static noinline int btrfs_ioctl_tree_search_v2(struct inode *inode,
 	struct btrfs_ioctl_search_args_v2 __user *uarg = argp;
 	struct btrfs_ioctl_search_args_v2 args;
 	int ret;
-	size_t buf_size;
-	const size_t buf_limit = SZ_16M;
+	u64 buf_size;
+	const u64 buf_limit = SZ_16M;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -4356,6 +4365,7 @@ static int _btrfs_ioctl_send(struct inode *inode, void __user *argp, bool compat
 		arg->clone_sources = compat_ptr(args32.clone_sources);
 		arg->parent_root = args32.parent_root;
 		arg->flags = args32.flags;
+		arg->version = args32.version;
 		memcpy(arg->reserved, args32.reserved,
 		       sizeof(args32.reserved));
 #else
@@ -4523,29 +4533,29 @@ static int btrfs_ioctl_encoded_write(struct file *file, void __user *argp, bool
 	if (ret < 0)
 		goto out_acct;
 
-	file_start_write(file);
-
 	if (iov_iter_count(&iter) == 0) {
 		ret = 0;
-		goto out_end_write;
+		goto out_iov;
 	}
 	pos = args.offset;
 	ret = rw_verify_area(WRITE, file, &pos, args.len);
 	if (ret < 0)
-		goto out_end_write;
+		goto out_iov;
 
 	init_sync_kiocb(&kiocb, file);
 	ret = kiocb_set_rw_flags(&kiocb, 0);
 	if (ret)
-		goto out_end_write;
+		goto out_iov;
 	kiocb.ki_pos = pos;
 
+	file_start_write(file);
+
 	ret = btrfs_do_write_iter(&kiocb, &iter, &args);
 	if (ret > 0)
 		fsnotify_modify(file);
 
-out_end_write:
 	file_end_write(file);
+out_iov:
 	kfree(iov);
 out_acct:
 	if (ret > 0)
diff --git a/fs/btrfs/lru_cache.c b/fs/btrfs/lru_cache.c
index 0fe0ae54ac67..fd88af17d8d9 100644
--- a/fs/btrfs/lru_cache.c
+++ b/fs/btrfs/lru_cache.c
@@ -9,7 +9,7 @@
  *
  * @cache:      The cache.
  * @max_size:   Maximum size (number of entries) for the cache.
- *              Use 0 for unlimited size, it's the user's responsability to
+ *              Use 0 for unlimited size, it's the user's responsibility to
  *              trim the cache in that case.
  */
 void btrfs_lru_cache_init(struct btrfs_lru_cache *cache, unsigned int max_size)
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index d3fcfc628a4f..1131d5a29d61 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -152,7 +152,7 @@ static int copy_compressed_data_to_page(char *compressed_data,
 	cur_page = out_pages[*cur_out / PAGE_SIZE];
 	/* Allocate a new page */
 	if (!cur_page) {
-		cur_page = alloc_page(GFP_NOFS);
+		cur_page = btrfs_alloc_compr_page();
 		if (!cur_page)
 			return -ENOMEM;
 		out_pages[*cur_out / PAGE_SIZE] = cur_page;
@@ -178,7 +178,7 @@ static int copy_compressed_data_to_page(char *compressed_data,
 		cur_page = out_pages[*cur_out / PAGE_SIZE];
 		/* Allocate a new page */
 		if (!cur_page) {
-			cur_page = alloc_page(GFP_NOFS);
+			cur_page = btrfs_alloc_compr_page();
 			if (!cur_page)
 				return -ENOMEM;
 			out_pages[*cur_out / PAGE_SIZE] = cur_page;
diff --git a/fs/btrfs/messages.c b/fs/btrfs/messages.c
index b8f9c9e56c8c..cdada4865837 100644
--- a/fs/btrfs/messages.c
+++ b/fs/btrfs/messages.c
@@ -287,7 +287,7 @@ void __cold btrfs_err_32bit_limit(struct btrfs_fs_info *fs_info)
  * panic or BUGs, depending on mount options.
  */
 __cold
-void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function,
+void __btrfs_panic(const struct btrfs_fs_info *fs_info, const char *function,
 		   unsigned int line, int error, const char *fmt, ...)
 {
 	char *s_id = "<unknown>";
diff --git a/fs/btrfs/messages.h b/fs/btrfs/messages.h
index 4d04c1fa5899..08a9272399d2 100644
--- a/fs/btrfs/messages.h
+++ b/fs/btrfs/messages.h
@@ -194,7 +194,7 @@ const char * __attribute_const__ btrfs_decode_error(int error);
 
 __printf(5, 6)
 __cold
-void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function,
+void __btrfs_panic(const struct btrfs_fs_info *fs_info, const char *function,
 		   unsigned int line, int error, const char *fmt, ...);
 /*
  * If BTRFS_MOUNT_PANIC_ON_FATAL_ERROR is in mount_opt, __btrfs_panic
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 574e8a55e24a..59850dc17b22 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -152,11 +152,12 @@ static struct btrfs_ordered_extent *alloc_ordered_extent(
 {
 	struct btrfs_ordered_extent *entry;
 	int ret;
+	u64 qgroup_rsv = 0;
 
 	if (flags &
 	    ((1 << BTRFS_ORDERED_NOCOW) | (1 << BTRFS_ORDERED_PREALLOC))) {
 		/* For nocow write, we can release the qgroup rsv right now */
-		ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes);
+		ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes, &qgroup_rsv);
 		if (ret < 0)
 			return ERR_PTR(ret);
 	} else {
@@ -164,7 +165,7 @@ static struct btrfs_ordered_extent *alloc_ordered_extent(
 		 * The ordered extent has reserved qgroup space, release now
 		 * and pass the reserved number for qgroup_record to free.
 		 */
-		ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes);
+		ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes, &qgroup_rsv);
 		if (ret < 0)
 			return ERR_PTR(ret);
 	}
@@ -182,7 +183,7 @@ static struct btrfs_ordered_extent *alloc_ordered_extent(
 	entry->inode = igrab(&inode->vfs_inode);
 	entry->compress_type = compress_type;
 	entry->truncated_len = (u64)-1;
-	entry->qgroup_rsv = ret;
+	entry->qgroup_rsv = qgroup_rsv;
 	entry->flags = flags;
 	refcount_set(&entry->refs, 1);
 	init_waitqueue_head(&entry->wait);
@@ -322,9 +323,10 @@ static bool can_finish_ordered_extent(struct btrfs_ordered_extent *ordered,
 		 *
 		 * If there's no such bit, we need to skip to next range.
 		 */
-		if (!btrfs_page_test_ordered(fs_info, page, file_offset, len))
+		if (!btrfs_folio_test_ordered(fs_info, page_folio(page),
+					      file_offset, len))
 			return false;
-		btrfs_page_clear_ordered(fs_info, page, file_offset, len);
+		btrfs_folio_clear_ordered(fs_info, page_folio(page), file_offset, len);
 	}
 
 	/* Now we're fine to update the accounting. */
@@ -599,7 +601,9 @@ void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode,
 			release = entry->disk_num_bytes;
 		else
 			release = entry->num_bytes;
-		btrfs_delalloc_release_metadata(btrfs_inode, release, false);
+		btrfs_delalloc_release_metadata(btrfs_inode, release,
+						test_bit(BTRFS_ORDERED_IOERR,
+							 &entry->flags));
 	}
 
 	percpu_counter_add_batch(&fs_info->ordered_bytes, -entry->num_bytes,
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 567a6d3d4712..127ef8bf0ffd 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -97,13 +97,6 @@ struct btrfs_ordered_extent {
 	u64 bytes_left;
 
 	/*
-	 * the end of the ordered extent which is behind it but
-	 * didn't update disk_i_size. Please see the comment of
-	 * btrfs_ordered_update_i_size();
-	 */
-	u64 outstanding_isize;
-
-	/*
 	 * If we get truncated we need to adjust the file extent we enter for
 	 * this ordered extent so that we do not expose stale data.
 	 */
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index edb84cc03237..63b426cc7798 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -194,7 +194,7 @@ static struct btrfs_qgroup *find_qgroup_rb(struct btrfs_fs_info *fs_info,
  *
  * Must be called with qgroup_lock held and @prealloc preallocated.
  *
- * The control on the lifespan of @prealloc would be transfered to this
+ * The control on the lifespan of @prealloc would be transferred to this
  * function, thus caller should no longer touch @prealloc.
  */
 static struct btrfs_qgroup *add_qgroup_rb(struct btrfs_fs_info *fs_info,
@@ -1888,7 +1888,7 @@ int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info,
 	u64 bytenr = record->bytenr;
 
 	if (!btrfs_qgroup_full_accounting(fs_info))
-		return 0;
+		return 1;
 
 	lockdep_assert_held(&delayed_refs->lock);
 	trace_btrfs_qgroup_trace_extent(fs_info, record);
@@ -2875,12 +2875,18 @@ int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr,
 			       num_bytes, seq);
 
 	/*
+	 * We're done using the iterator, release all its qgroups while holding
+	 * fs_info->qgroup_lock so that we don't race with btrfs_remove_qgroup()
+	 * and trigger use-after-free accesses to qgroups.
+	 */
+	qgroup_iterator_nested_clean(&qgroups);
+
+	/*
 	 * Bump qgroup_seq to avoid seq overlap
 	 */
 	fs_info->qgroup_seq += max(nr_old_roots, nr_new_roots) + 1;
 	spin_unlock(&fs_info->qgroup_lock);
 out_free:
-	qgroup_iterator_nested_clean(&qgroups);
 	ulist_free(old_roots);
 	ulist_free(new_roots);
 	return ret;
@@ -4051,13 +4057,14 @@ int btrfs_qgroup_reserve_data(struct btrfs_inode *inode,
 
 /* Free ranges specified by @reserved, normally in error path */
 static int qgroup_free_reserved_data(struct btrfs_inode *inode,
-			struct extent_changeset *reserved, u64 start, u64 len)
+				     struct extent_changeset *reserved,
+				     u64 start, u64 len, u64 *freed_ret)
 {
 	struct btrfs_root *root = inode->root;
 	struct ulist_node *unode;
 	struct ulist_iterator uiter;
 	struct extent_changeset changeset;
-	int freed = 0;
+	u64 freed = 0;
 	int ret;
 
 	extent_changeset_init(&changeset);
@@ -4098,7 +4105,9 @@ static int qgroup_free_reserved_data(struct btrfs_inode *inode,
 	}
 	btrfs_qgroup_free_refroot(root->fs_info, root->root_key.objectid, freed,
 				  BTRFS_QGROUP_RSV_DATA);
-	ret = freed;
+	if (freed_ret)
+		*freed_ret = freed;
+	ret = 0;
 out:
 	extent_changeset_release(&changeset);
 	return ret;
@@ -4106,7 +4115,7 @@ out:
 
 static int __btrfs_qgroup_release_data(struct btrfs_inode *inode,
 			struct extent_changeset *reserved, u64 start, u64 len,
-			int free)
+			u64 *released, int free)
 {
 	struct extent_changeset changeset;
 	int trace_op = QGROUP_RELEASE;
@@ -4122,7 +4131,7 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode,
 	/* In release case, we shouldn't have @reserved */
 	WARN_ON(!free && reserved);
 	if (free && reserved)
-		return qgroup_free_reserved_data(inode, reserved, start, len);
+		return qgroup_free_reserved_data(inode, reserved, start, len, released);
 	extent_changeset_init(&changeset);
 	ret = clear_record_extent_bits(&inode->io_tree, start, start + len -1,
 				       EXTENT_QGROUP_RESERVED, &changeset);
@@ -4137,7 +4146,8 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode,
 		btrfs_qgroup_free_refroot(inode->root->fs_info,
 				inode->root->root_key.objectid,
 				changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA);
-	ret = changeset.bytes_changed;
+	if (released)
+		*released = changeset.bytes_changed;
 out:
 	extent_changeset_release(&changeset);
 	return ret;
@@ -4156,9 +4166,10 @@ out:
  * NOTE: This function may sleep for memory allocation.
  */
 int btrfs_qgroup_free_data(struct btrfs_inode *inode,
-			struct extent_changeset *reserved, u64 start, u64 len)
+			   struct extent_changeset *reserved,
+			   u64 start, u64 len, u64 *freed)
 {
-	return __btrfs_qgroup_release_data(inode, reserved, start, len, 1);
+	return __btrfs_qgroup_release_data(inode, reserved, start, len, freed, 1);
 }
 
 /*
@@ -4176,9 +4187,9 @@ int btrfs_qgroup_free_data(struct btrfs_inode *inode,
  *
  * NOTE: This function may sleep for memory allocation.
  */
-int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len)
+int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len, u64 *released)
 {
-	return __btrfs_qgroup_release_data(inode, NULL, start, len, 0);
+	return __btrfs_qgroup_release_data(inode, NULL, start, len, released, 0);
 }
 
 static void add_root_meta_rsv(struct btrfs_root *root, int num_bytes,
@@ -4326,8 +4337,9 @@ static void qgroup_convert_meta(struct btrfs_fs_info *fs_info, u64 ref_root,
 
 		qgroup_rsv_release(fs_info, qgroup, num_bytes,
 				BTRFS_QGROUP_RSV_META_PREALLOC);
-		qgroup_rsv_add(fs_info, qgroup, num_bytes,
-				BTRFS_QGROUP_RSV_META_PERTRANS);
+		if (!sb_rdonly(fs_info->sb))
+			qgroup_rsv_add(fs_info, qgroup, num_bytes,
+				       BTRFS_QGROUP_RSV_META_PERTRANS);
 
 		list_for_each_entry(glist, &qgroup->groups, next_group)
 			qgroup_iterator_add(&qgroup_list, glist->group);
@@ -4649,6 +4661,17 @@ void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans)
 	*root = RB_ROOT;
 }
 
+void btrfs_free_squota_rsv(struct btrfs_fs_info *fs_info, u64 root, u64 rsv_bytes)
+{
+	if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_SIMPLE)
+		return;
+
+	if (!is_fstree(root))
+		return;
+
+	btrfs_qgroup_free_refroot(fs_info, root, rsv_bytes, BTRFS_QGROUP_RSV_DATA);
+}
+
 int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info,
 			      struct btrfs_squota_delta *delta)
 {
@@ -4693,8 +4716,5 @@ int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info,
 
 out:
 	spin_unlock(&fs_info->qgroup_lock);
-	if (!ret && delta->rsv_bytes)
-		btrfs_qgroup_free_refroot(fs_info, root, delta->rsv_bytes,
-					  BTRFS_QGROUP_RSV_DATA);
 	return ret;
 }
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 855a4f978761..be18c862e64e 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -274,8 +274,6 @@ struct btrfs_squota_delta {
 	u64 root;
 	/* The number of bytes in the extent being counted. */
 	u64 num_bytes;
-	/* The number of bytes reserved for this extent. */
-	u64 rsv_bytes;
 	/* The generation the extent was created in. */
 	u64 generation;
 	/* Whether we are using or freeing the extent. */
@@ -358,10 +356,10 @@ int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid,
 /* New io_tree based accurate qgroup reserve API */
 int btrfs_qgroup_reserve_data(struct btrfs_inode *inode,
 			struct extent_changeset **reserved, u64 start, u64 len);
-int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len);
+int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len, u64 *released);
 int btrfs_qgroup_free_data(struct btrfs_inode *inode,
 			   struct extent_changeset *reserved, u64 start,
-			   u64 len);
+			   u64 len, u64 *freed);
 int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
 			      enum btrfs_qgroup_rsv_type type, bool enforce);
 int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
@@ -422,6 +420,7 @@ int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans,
 		struct btrfs_root *root, struct extent_buffer *eb);
 void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans);
 bool btrfs_check_quota_leak(struct btrfs_fs_info *fs_info);
+void btrfs_free_squota_rsv(struct btrfs_fs_info *fs_info, u64 root, u64 rsv_bytes);
 int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info,
 			      struct btrfs_squota_delta *delta);
 
diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c
index 944e8f1862aa..9589362acfbf 100644
--- a/fs/btrfs/raid-stripe-tree.c
+++ b/fs/btrfs/raid-stripe-tree.c
@@ -145,7 +145,7 @@ int btrfs_insert_raid_extent(struct btrfs_trans_handle *trans,
 		btrfs_put_bioc(bioc);
 	}
 
-	return ret;
+	return 0;
 }
 
 int btrfs_get_raid_extent_offset(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 3e014b9370a3..792c8e17c31d 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -964,7 +964,7 @@ static int alloc_rbio_pages(struct btrfs_raid_bio *rbio)
 {
 	int ret;
 
-	ret = btrfs_alloc_page_array(rbio->nr_pages, rbio->stripe_pages);
+	ret = btrfs_alloc_page_array(rbio->nr_pages, rbio->stripe_pages, 0);
 	if (ret < 0)
 		return ret;
 	/* Mapping all sectors */
@@ -979,7 +979,7 @@ static int alloc_rbio_parity_pages(struct btrfs_raid_bio *rbio)
 	int ret;
 
 	ret = btrfs_alloc_page_array(rbio->nr_pages - data_pages,
-				     rbio->stripe_pages + data_pages);
+				     rbio->stripe_pages + data_pages, 0);
 	if (ret < 0)
 		return ret;
 
@@ -1530,7 +1530,7 @@ static int alloc_rbio_data_pages(struct btrfs_raid_bio *rbio)
 	const int data_pages = rbio->nr_data * rbio->stripe_npages;
 	int ret;
 
-	ret = btrfs_alloc_page_array(data_pages, rbio->stripe_pages);
+	ret = btrfs_alloc_page_array(data_pages, rbio->stripe_pages, 0);
 	if (ret < 0)
 		return ret;
 
@@ -1549,7 +1549,6 @@ struct btrfs_plug_cb {
 	struct blk_plug_cb cb;
 	struct btrfs_fs_info *info;
 	struct list_head rbio_list;
-	struct work_struct work;
 };
 
 /*
diff --git a/fs/btrfs/raid56.h b/fs/btrfs/raid56.h
index 45e6ff78316f..470213688872 100644
--- a/fs/btrfs/raid56.h
+++ b/fs/btrfs/raid56.h
@@ -164,7 +164,7 @@ struct raid56_bio_trace_info {
 	u8 stripe_nr;
 };
 
-static inline int nr_data_stripes(const struct map_lookup *map)
+static inline int nr_data_stripes(const struct btrfs_chunk_map *map)
 {
 	return map->num_stripes - btrfs_nr_parity_stripes(map->type);
 }
diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index 1f62976bee82..6486f0d7e993 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -794,6 +794,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
 			dump_ref_action(fs_info, ra);
 			kfree(ref);
 			kfree(ra);
+			kfree(re);
 			goto out_unlock;
 		} else if (be->num_refs == 0) {
 			btrfs_err(fs_info,
@@ -803,6 +804,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
 			dump_ref_action(fs_info, ra);
 			kfree(ref);
 			kfree(ra);
+			kfree(re);
 			goto out_unlock;
 		}
 
diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c
index f88b0c2ac3fe..ae90894dc7dc 100644
--- a/fs/btrfs/reflink.c
+++ b/fs/btrfs/reflink.c
@@ -141,9 +141,9 @@ static int copy_inline_to_page(struct btrfs_inode *inode,
 	if (datal < block_size)
 		memzero_page(page, datal, block_size - datal);
 
-	btrfs_page_set_uptodate(fs_info, page, file_offset, block_size);
-	btrfs_page_clear_checked(fs_info, page, file_offset, block_size);
-	btrfs_page_set_dirty(fs_info, page, file_offset, block_size);
+	btrfs_folio_set_uptodate(fs_info, page_folio(page), file_offset, block_size);
+	btrfs_folio_clear_checked(fs_info, page_folio(page), file_offset, block_size);
+	btrfs_folio_set_dirty(fs_info, page_folio(page), file_offset, block_size);
 out_unlock:
 	if (page) {
 		unlock_page(page);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index f5d9e5f74a52..abe594f77f99 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2895,7 +2895,7 @@ static noinline_for_stack int prealloc_file_extent_cluster(
 		 * will re-read the whole page anyway.
 		 */
 		if (page) {
-			btrfs_subpage_clear_uptodate(fs_info, page, i_size,
+			btrfs_subpage_clear_uptodate(fs_info, page_folio(page), i_size,
 					round_up(i_size, PAGE_SIZE) - i_size);
 			unlock_page(page);
 			put_page(page);
@@ -2951,7 +2951,7 @@ static noinline_for_stack int setup_relocation_extent_mapping(struct inode *inod
 	em->len = end + 1 - start;
 	em->block_len = em->len;
 	em->block_start = block_start;
-	set_bit(EXTENT_FLAG_PINNED, &em->flags);
+	em->flags |= EXTENT_FLAG_PINNED;
 
 	lock_extent(&BTRFS_I(inode)->io_tree, start, end, &cached_state);
 	ret = btrfs_replace_extent_map_range(BTRFS_I(inode), em, false);
@@ -3070,7 +3070,8 @@ static int relocate_one_page(struct inode *inode, struct file_ra_state *ra,
 						       clamped_len);
 			goto release_page;
 		}
-		btrfs_page_set_dirty(fs_info, page, clamped_start, clamped_len);
+		btrfs_folio_set_dirty(fs_info, page_folio(page),
+				      clamped_start, clamped_len);
 
 		/*
 		 * Set the boundary if it's inside the page.
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 9ce5be21b036..a01807cbd4d4 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -43,7 +43,7 @@ struct scrub_ctx;
 /*
  * The following value only influences the performance.
  *
- * This detemines how many stripes would be submitted in one go,
+ * This determines how many stripes would be submitted in one go,
  * which is 512KiB (BTRFS_STRIPE_LEN * SCRUB_STRIPES_PER_GROUP).
  */
 #define SCRUB_STRIPES_PER_GROUP		8
@@ -192,7 +192,6 @@ struct scrub_ctx {
 	int			cur_stripe;
 	atomic_t		cancel_req;
 	int			readonly;
-	int			sectors_per_bio;
 
 	/* State of IO submission throttling affecting the associated device */
 	ktime_t			throttle_deadline;
@@ -262,7 +261,7 @@ static int init_scrub_stripe(struct btrfs_fs_info *fs_info,
 	atomic_set(&stripe->pending_io, 0);
 	spin_lock_init(&stripe->write_error_lock);
 
-	ret = btrfs_alloc_page_array(SCRUB_STRIPE_PAGES, stripe->pages);
+	ret = btrfs_alloc_page_array(SCRUB_STRIPE_PAGES, stripe->pages, 0);
 	if (ret < 0)
 		goto error;
 
@@ -710,7 +709,7 @@ static void scrub_verify_one_sector(struct scrub_stripe *stripe, int sector_nr)
 	/* Metadata, verify the full tree block. */
 	if (sector->is_metadata) {
 		/*
-		 * Check if the tree block crosses the stripe boudary.  If
+		 * Check if the tree block crosses the stripe boundary.  If
 		 * crossed the boundary, we cannot verify it but only give a
 		 * warning.
 		 *
@@ -884,7 +883,7 @@ static void scrub_stripe_report_errors(struct scrub_ctx *sctx,
 	/*
 	 * Init needed infos for error reporting.
 	 *
-	 * Although our scrub_stripe infrastucture is mostly based on btrfs_submit_bio()
+	 * Although our scrub_stripe infrastructure is mostly based on btrfs_submit_bio()
 	 * thus no need for dev/physical, error reporting still needs dev and physical.
 	 */
 	if (!bitmap_empty(&stripe->init_error_bitmap, stripe->nr_sectors)) {
@@ -1280,7 +1279,7 @@ static void scrub_throttle_dev_io(struct scrub_ctx *sctx, struct btrfs_device *d
  * return 0 if it is a data stripe, 1 means parity stripe.
  */
 static int get_raid56_logic_offset(u64 physical, int num,
-				   struct map_lookup *map, u64 *offset,
+				   struct btrfs_chunk_map *map, u64 *offset,
 				   u64 *stripe_start)
 {
 	int i;
@@ -1409,14 +1408,11 @@ search_forward:
 		if (ret > 0)
 			break;
 next:
-		path->slots[0]++;
-		if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
-			ret = btrfs_next_leaf(extent_root, path);
-			if (ret) {
-				/* Either no more item or fatal error */
-				btrfs_release_path(path);
-				return ret;
-			}
+		ret = btrfs_next_item(extent_root, path);
+		if (ret) {
+			/* Either no more items or a fatal error. */
+			btrfs_release_path(path);
+			return ret;
 		}
 	}
 	btrfs_release_path(path);
@@ -1816,7 +1812,7 @@ static int flush_scrub_stripes(struct scrub_ctx *sctx)
 	if (sctx->is_dev_replace) {
 		/*
 		 * For dev-replace, if we know there is something wrong with
-		 * metadata, we should immedately abort.
+		 * metadata, we should immediately abort.
 		 */
 		for (int i = 0; i < nr_stripes; i++) {
 			if (stripe_has_metadata_error(&sctx->stripes[i])) {
@@ -1868,6 +1864,9 @@ static int queue_scrub_stripe(struct scrub_ctx *sctx, struct btrfs_block_group *
 	 */
 	ASSERT(sctx->cur_stripe < SCRUB_TOTAL_STRIPES);
 
+	/* @found_logical_ret must be specified. */
+	ASSERT(found_logical_ret);
+
 	stripe = &sctx->stripes[sctx->cur_stripe];
 	scrub_reset_stripe(stripe);
 	ret = scrub_find_fill_first_stripe(bg, &sctx->extent_path,
@@ -1876,8 +1875,7 @@ static int queue_scrub_stripe(struct scrub_ctx *sctx, struct btrfs_block_group *
 	/* Either >0 as no more extents or <0 for error. */
 	if (ret)
 		return ret;
-	if (found_logical_ret)
-		*found_logical_ret = stripe->logical;
+	*found_logical_ret = stripe->logical;
 	sctx->cur_stripe++;
 
 	/* We filled one group, submit it. */
@@ -1896,7 +1894,7 @@ static int queue_scrub_stripe(struct scrub_ctx *sctx, struct btrfs_block_group *
 static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx,
 				      struct btrfs_device *scrub_dev,
 				      struct btrfs_block_group *bg,
-				      struct map_lookup *map,
+				      struct btrfs_chunk_map *map,
 				      u64 full_stripe_start)
 {
 	DECLARE_COMPLETION_ONSTACK(io_done);
@@ -2065,7 +2063,7 @@ out:
  */
 static int scrub_simple_mirror(struct scrub_ctx *sctx,
 			       struct btrfs_block_group *bg,
-			       struct map_lookup *map,
+			       struct btrfs_chunk_map *map,
 			       u64 logical_start, u64 logical_length,
 			       struct btrfs_device *device,
 			       u64 physical, int mirror_num)
@@ -2080,7 +2078,7 @@ static int scrub_simple_mirror(struct scrub_ctx *sctx,
 
 	/* Go through each extent items inside the logical range */
 	while (cur_logical < logical_end) {
-		u64 found_logical;
+		u64 found_logical = U64_MAX;
 		u64 cur_physical = physical + cur_logical - logical_start;
 
 		/* Canceled? */
@@ -2115,6 +2113,8 @@ static int scrub_simple_mirror(struct scrub_ctx *sctx,
 		if (ret < 0)
 			break;
 
+		/* queue_scrub_stripe() returned 0, @found_logical must be updated. */
+		ASSERT(found_logical != U64_MAX);
 		cur_logical = found_logical + BTRFS_STRIPE_LEN;
 
 		/* Don't hold CPU for too long time */
@@ -2124,7 +2124,7 @@ static int scrub_simple_mirror(struct scrub_ctx *sctx,
 }
 
 /* Calculate the full stripe length for simple stripe based profiles */
-static u64 simple_stripe_full_stripe_len(const struct map_lookup *map)
+static u64 simple_stripe_full_stripe_len(const struct btrfs_chunk_map *map)
 {
 	ASSERT(map->type & (BTRFS_BLOCK_GROUP_RAID0 |
 			    BTRFS_BLOCK_GROUP_RAID10));
@@ -2133,7 +2133,7 @@ static u64 simple_stripe_full_stripe_len(const struct map_lookup *map)
 }
 
 /* Get the logical bytenr for the stripe */
-static u64 simple_stripe_get_logical(struct map_lookup *map,
+static u64 simple_stripe_get_logical(struct btrfs_chunk_map *map,
 				     struct btrfs_block_group *bg,
 				     int stripe_index)
 {
@@ -2150,7 +2150,7 @@ static u64 simple_stripe_get_logical(struct map_lookup *map,
 }
 
 /* Get the mirror number for the stripe */
-static int simple_stripe_mirror_num(struct map_lookup *map, int stripe_index)
+static int simple_stripe_mirror_num(struct btrfs_chunk_map *map, int stripe_index)
 {
 	ASSERT(map->type & (BTRFS_BLOCK_GROUP_RAID0 |
 			    BTRFS_BLOCK_GROUP_RAID10));
@@ -2162,7 +2162,7 @@ static int simple_stripe_mirror_num(struct map_lookup *map, int stripe_index)
 
 static int scrub_simple_stripe(struct scrub_ctx *sctx,
 			       struct btrfs_block_group *bg,
-			       struct map_lookup *map,
+			       struct btrfs_chunk_map *map,
 			       struct btrfs_device *device,
 			       int stripe_index)
 {
@@ -2195,18 +2195,17 @@ static int scrub_simple_stripe(struct scrub_ctx *sctx,
 
 static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 					   struct btrfs_block_group *bg,
-					   struct extent_map *em,
+					   struct btrfs_chunk_map *map,
 					   struct btrfs_device *scrub_dev,
 					   int stripe_index)
 {
 	struct btrfs_fs_info *fs_info = sctx->fs_info;
-	struct map_lookup *map = em->map_lookup;
 	const u64 profile = map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK;
 	const u64 chunk_logical = bg->start;
 	int ret;
 	int ret2;
 	u64 physical = map->stripes[stripe_index].physical;
-	const u64 dev_stripe_len = btrfs_calc_stripe_length(em);
+	const u64 dev_stripe_len = btrfs_calc_stripe_length(map);
 	const u64 physical_end = physical + dev_stripe_len;
 	u64 logical;
 	u64 logic_end;
@@ -2369,17 +2368,12 @@ static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx,
 					  u64 dev_extent_len)
 {
 	struct btrfs_fs_info *fs_info = sctx->fs_info;
-	struct extent_map_tree *map_tree = &fs_info->mapping_tree;
-	struct map_lookup *map;
-	struct extent_map *em;
+	struct btrfs_chunk_map *map;
 	int i;
 	int ret = 0;
 
-	read_lock(&map_tree->lock);
-	em = lookup_extent_mapping(map_tree, bg->start, bg->length);
-	read_unlock(&map_tree->lock);
-
-	if (!em) {
+	map = btrfs_find_chunk_map(fs_info, bg->start, bg->length);
+	if (!map) {
 		/*
 		 * Might have been an unused block group deleted by the cleaner
 		 * kthread or relocation.
@@ -2391,22 +2385,21 @@ static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx,
 
 		return ret;
 	}
-	if (em->start != bg->start)
+	if (map->start != bg->start)
 		goto out;
-	if (em->len < dev_extent_len)
+	if (map->chunk_len < dev_extent_len)
 		goto out;
 
-	map = em->map_lookup;
 	for (i = 0; i < map->num_stripes; ++i) {
 		if (map->stripes[i].dev->bdev == scrub_dev->bdev &&
 		    map->stripes[i].physical == dev_offset) {
-			ret = scrub_stripe(sctx, bg, em, scrub_dev, i);
+			ret = scrub_stripe(sctx, bg, map, scrub_dev, i);
 			if (ret)
 				goto out;
 		}
 	}
 out:
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 
 	return ret;
 }
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 3b929f0e8f04..4e36550618e5 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -8158,7 +8158,7 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg)
 	}
 
 	sctx->send_filp = fget(arg->send_fd);
-	if (!sctx->send_filp) {
+	if (!sctx->send_filp || !(sctx->send_filp->f_mode & FMODE_WRITE)) {
 		ret = -EBADF;
 		goto out;
 	}
diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c
index 1b999c6e4193..93511d54abf8 100644
--- a/fs/btrfs/subpage.c
+++ b/fs/btrfs/subpage.c
@@ -64,7 +64,7 @@
  *   This means a slightly higher tree locking latency.
  */
 
-bool btrfs_is_subpage(const struct btrfs_fs_info *fs_info, struct page *page)
+bool btrfs_is_subpage(const struct btrfs_fs_info *fs_info, struct address_space *mapping)
 {
 	if (fs_info->sectorsize >= PAGE_SIZE)
 		return false;
@@ -74,8 +74,7 @@ bool btrfs_is_subpage(const struct btrfs_fs_info *fs_info, struct page *page)
 	 * mapping. And if page->mapping->host is data inode, it's subpage.
 	 * As we have ruled our sectorsize >= PAGE_SIZE case already.
 	 */
-	if (!page->mapping || !page->mapping->host ||
-	    is_data_inode(page->mapping->host))
+	if (!mapping || !mapping->host || is_data_inode(mapping->host))
 		return true;
 
 	/*
@@ -116,7 +115,7 @@ void btrfs_init_subpage_info(struct btrfs_subpage_info *subpage_info, u32 sector
 }
 
 int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info,
-			 struct page *page, enum btrfs_subpage_type type)
+			 struct folio *folio, enum btrfs_subpage_type type)
 {
 	struct btrfs_subpage *subpage;
 
@@ -124,31 +123,30 @@ int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info,
 	 * We have cases like a dummy extent buffer page, which is not mapped
 	 * and doesn't need to be locked.
 	 */
-	if (page->mapping)
-		ASSERT(PageLocked(page));
+	if (folio->mapping)
+		ASSERT(folio_test_locked(folio));
 
-	/* Either not subpage, or the page already has private attached */
-	if (!btrfs_is_subpage(fs_info, page) || PagePrivate(page))
+	/* Either not subpage, or the folio already has private attached. */
+	if (!btrfs_is_subpage(fs_info, folio->mapping) || folio_test_private(folio))
 		return 0;
 
 	subpage = btrfs_alloc_subpage(fs_info, type);
 	if (IS_ERR(subpage))
 		return  PTR_ERR(subpage);
 
-	attach_page_private(page, subpage);
+	folio_attach_private(folio, subpage);
 	return 0;
 }
 
-void btrfs_detach_subpage(const struct btrfs_fs_info *fs_info,
-			  struct page *page)
+void btrfs_detach_subpage(const struct btrfs_fs_info *fs_info, struct folio *folio)
 {
 	struct btrfs_subpage *subpage;
 
-	/* Either not subpage, or already detached */
-	if (!btrfs_is_subpage(fs_info, page) || !PagePrivate(page))
+	/* Either not subpage, or the folio already has private attached. */
+	if (!btrfs_is_subpage(fs_info, folio->mapping) || !folio_test_private(folio))
 		return;
 
-	subpage = detach_page_private(page);
+	subpage = folio_detach_private(folio);
 	ASSERT(subpage);
 	btrfs_free_subpage(subpage);
 }
@@ -188,77 +186,78 @@ void btrfs_free_subpage(struct btrfs_subpage *subpage)
  * This is important for eb allocation, to prevent race with last eb freeing
  * of the same page.
  * With the eb_refs increased before the eb inserted into radix tree,
- * detach_extent_buffer_page() won't detach the page private while we're still
+ * detach_extent_buffer_page() won't detach the folio private while we're still
  * allocating the extent buffer.
  */
-void btrfs_page_inc_eb_refs(const struct btrfs_fs_info *fs_info,
-			    struct page *page)
+void btrfs_folio_inc_eb_refs(const struct btrfs_fs_info *fs_info, struct folio *folio)
 {
 	struct btrfs_subpage *subpage;
 
-	if (!btrfs_is_subpage(fs_info, page))
+	if (!btrfs_is_subpage(fs_info, folio->mapping))
 		return;
 
-	ASSERT(PagePrivate(page) && page->mapping);
-	lockdep_assert_held(&page->mapping->private_lock);
+	ASSERT(folio_test_private(folio) && folio->mapping);
+	lockdep_assert_held(&folio->mapping->i_private_lock);
 
-	subpage = (struct btrfs_subpage *)page->private;
+	subpage = folio_get_private(folio);
 	atomic_inc(&subpage->eb_refs);
 }
 
-void btrfs_page_dec_eb_refs(const struct btrfs_fs_info *fs_info,
-			    struct page *page)
+void btrfs_folio_dec_eb_refs(const struct btrfs_fs_info *fs_info, struct folio *folio)
 {
 	struct btrfs_subpage *subpage;
 
-	if (!btrfs_is_subpage(fs_info, page))
+	if (!btrfs_is_subpage(fs_info, folio->mapping))
 		return;
 
-	ASSERT(PagePrivate(page) && page->mapping);
-	lockdep_assert_held(&page->mapping->private_lock);
+	ASSERT(folio_test_private(folio) && folio->mapping);
+	lockdep_assert_held(&folio->mapping->i_private_lock);
 
-	subpage = (struct btrfs_subpage *)page->private;
+	subpage = folio_get_private(folio);
 	ASSERT(atomic_read(&subpage->eb_refs));
 	atomic_dec(&subpage->eb_refs);
 }
 
 static void btrfs_subpage_assert(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len)
+				 struct folio *folio, u64 start, u32 len)
 {
+	/* For subpage support, the folio must be single page. */
+	ASSERT(folio_order(folio) == 0);
+
 	/* Basic checks */
-	ASSERT(PagePrivate(page) && page->private);
+	ASSERT(folio_test_private(folio) && folio_get_private(folio));
 	ASSERT(IS_ALIGNED(start, fs_info->sectorsize) &&
 	       IS_ALIGNED(len, fs_info->sectorsize));
 	/*
 	 * The range check only works for mapped page, we can still have
 	 * unmapped page like dummy extent buffer pages.
 	 */
-	if (page->mapping)
-		ASSERT(page_offset(page) <= start &&
-		       start + len <= page_offset(page) + PAGE_SIZE);
+	if (folio->mapping)
+		ASSERT(folio_pos(folio) <= start &&
+		       start + len <= folio_pos(folio) + PAGE_SIZE);
 }
 
 void btrfs_subpage_start_reader(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len)
+				struct folio *folio, u64 start, u32 len)
 {
-	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
+	struct btrfs_subpage *subpage = folio_get_private(folio);
 	const int nbits = len >> fs_info->sectorsize_bits;
 
-	btrfs_subpage_assert(fs_info, page, start, len);
+	btrfs_subpage_assert(fs_info, folio, start, len);
 
 	atomic_add(nbits, &subpage->readers);
 }
 
 void btrfs_subpage_end_reader(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len)
+			      struct folio *folio, u64 start, u32 len)
 {
-	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
+	struct btrfs_subpage *subpage = folio_get_private(folio);
 	const int nbits = len >> fs_info->sectorsize_bits;
 	bool is_data;
 	bool last;
 
-	btrfs_subpage_assert(fs_info, page, start, len);
-	is_data = is_data_inode(page->mapping->host);
+	btrfs_subpage_assert(fs_info, folio, start, len);
+	is_data = is_data_inode(folio->mapping->host);
 	ASSERT(atomic_read(&subpage->readers) >= nbits);
 	last = atomic_sub_and_test(nbits, &subpage->readers);
 
@@ -270,35 +269,35 @@ void btrfs_subpage_end_reader(const struct btrfs_fs_info *fs_info,
 	 * As we want the atomic_sub_and_test() to be always executed.
 	 */
 	if (is_data && last)
-		unlock_page(page);
+		folio_unlock(folio);
 }
 
-static void btrfs_subpage_clamp_range(struct page *page, u64 *start, u32 *len)
+static void btrfs_subpage_clamp_range(struct folio *folio, u64 *start, u32 *len)
 {
 	u64 orig_start = *start;
 	u32 orig_len = *len;
 
-	*start = max_t(u64, page_offset(page), orig_start);
+	*start = max_t(u64, folio_pos(folio), orig_start);
 	/*
 	 * For certain call sites like btrfs_drop_pages(), we may have pages
 	 * beyond the target range. In that case, just set @len to 0, subpage
 	 * helpers can handle @len == 0 without any problem.
 	 */
-	if (page_offset(page) >= orig_start + orig_len)
+	if (folio_pos(folio) >= orig_start + orig_len)
 		*len = 0;
 	else
-		*len = min_t(u64, page_offset(page) + PAGE_SIZE,
+		*len = min_t(u64, folio_pos(folio) + PAGE_SIZE,
 			     orig_start + orig_len) - *start;
 }
 
 void btrfs_subpage_start_writer(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len)
+				struct folio *folio, u64 start, u32 len)
 {
-	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
+	struct btrfs_subpage *subpage = folio_get_private(folio);
 	const int nbits = (len >> fs_info->sectorsize_bits);
 	int ret;
 
-	btrfs_subpage_assert(fs_info, page, start, len);
+	btrfs_subpage_assert(fs_info, folio, start, len);
 
 	ASSERT(atomic_read(&subpage->readers) == 0);
 	ret = atomic_add_return(nbits, &subpage->writers);
@@ -306,12 +305,12 @@ void btrfs_subpage_start_writer(const struct btrfs_fs_info *fs_info,
 }
 
 bool btrfs_subpage_end_and_test_writer(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len)
+				       struct folio *folio, u64 start, u32 len)
 {
-	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
+	struct btrfs_subpage *subpage = folio_get_private(folio);
 	const int nbits = (len >> fs_info->sectorsize_bits);
 
-	btrfs_subpage_assert(fs_info, page, start, len);
+	btrfs_subpage_assert(fs_info, folio, start, len);
 
 	/*
 	 * We have call sites passing @lock_page into
@@ -328,7 +327,7 @@ bool btrfs_subpage_end_and_test_writer(const struct btrfs_fs_info *fs_info,
 }
 
 /*
- * Lock a page for delalloc page writeback.
+ * Lock a folio for delalloc page writeback.
  *
  * Return -EAGAIN if the page is not properly initialized.
  * Return 0 with the page locked, and writer counter updated.
@@ -337,38 +336,40 @@ bool btrfs_subpage_end_and_test_writer(const struct btrfs_fs_info *fs_info,
  * it's really the correct page, as the caller is using
  * filemap_get_folios_contig(), which can race with page invalidating.
  */
-int btrfs_page_start_writer_lock(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len)
+int btrfs_folio_start_writer_lock(const struct btrfs_fs_info *fs_info,
+				  struct folio *folio, u64 start, u32 len)
 {
-	if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page)) {
-		lock_page(page);
+	if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, folio->mapping)) {
+		folio_lock(folio);
 		return 0;
 	}
-	lock_page(page);
-	if (!PagePrivate(page) || !page->private) {
-		unlock_page(page);
+	folio_lock(folio);
+	if (!folio_test_private(folio) || !folio_get_private(folio)) {
+		folio_unlock(folio);
 		return -EAGAIN;
 	}
-	btrfs_subpage_clamp_range(page, &start, &len);
-	btrfs_subpage_start_writer(fs_info, page, start, len);
+	btrfs_subpage_clamp_range(folio, &start, &len);
+	btrfs_subpage_start_writer(fs_info, folio, start, len);
 	return 0;
 }
 
-void btrfs_page_end_writer_lock(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len)
+void btrfs_folio_end_writer_lock(const struct btrfs_fs_info *fs_info,
+				 struct folio *folio, u64 start, u32 len)
 {
-	if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page))
-		return unlock_page(page);
-	btrfs_subpage_clamp_range(page, &start, &len);
-	if (btrfs_subpage_end_and_test_writer(fs_info, page, start, len))
-		unlock_page(page);
+	if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, folio->mapping)) {
+		folio_unlock(folio);
+		return;
+	}
+	btrfs_subpage_clamp_range(folio, &start, &len);
+	if (btrfs_subpage_end_and_test_writer(fs_info, folio, start, len))
+		folio_unlock(folio);
 }
 
-#define subpage_calc_start_bit(fs_info, page, name, start, len)		\
+#define subpage_calc_start_bit(fs_info, folio, name, start, len)	\
 ({									\
 	unsigned int start_bit;						\
 									\
-	btrfs_subpage_assert(fs_info, page, start, len);		\
+	btrfs_subpage_assert(fs_info, folio, start, len);		\
 	start_bit = offset_in_page(start) >> fs_info->sectorsize_bits;	\
 	start_bit += fs_info->subpage_info->name##_offset;		\
 	start_bit;							\
@@ -385,46 +386,46 @@ void btrfs_page_end_writer_lock(const struct btrfs_fs_info *fs_info,
 			fs_info->subpage_info->bitmap_nr_bits)
 
 void btrfs_subpage_set_uptodate(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len)
+				struct folio *folio, u64 start, u32 len)
 {
-	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
-	unsigned int start_bit = subpage_calc_start_bit(fs_info, page,
+	struct btrfs_subpage *subpage = folio_get_private(folio);
+	unsigned int start_bit = subpage_calc_start_bit(fs_info, folio,
 							uptodate, start, len);
 	unsigned long flags;
 
 	spin_lock_irqsave(&subpage->lock, flags);
 	bitmap_set(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits);
 	if (subpage_test_bitmap_all_set(fs_info, subpage, uptodate))
-		SetPageUptodate(page);
+		folio_mark_uptodate(folio);
 	spin_unlock_irqrestore(&subpage->lock, flags);
 }
 
 void btrfs_subpage_clear_uptodate(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len)
+				  struct folio *folio, u64 start, u32 len)
 {
-	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
-	unsigned int start_bit = subpage_calc_start_bit(fs_info, page,
+	struct btrfs_subpage *subpage = folio_get_private(folio);
+	unsigned int start_bit = subpage_calc_start_bit(fs_info, folio,
 							uptodate, start, len);
 	unsigned long flags;
 
 	spin_lock_irqsave(&subpage->lock, flags);
 	bitmap_clear(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits);
-	ClearPageUptodate(page);
+	folio_clear_uptodate(folio);
 	spin_unlock_irqrestore(&subpage->lock, flags);
 }
 
 void btrfs_subpage_set_dirty(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len)
+			     struct folio *folio, u64 start, u32 len)
 {
-	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
-	unsigned int start_bit = subpage_calc_start_bit(fs_info, page,
+	struct btrfs_subpage *subpage = folio_get_private(folio);
+	unsigned int start_bit = subpage_calc_start_bit(fs_info, folio,
 							dirty, start, len);
 	unsigned long flags;
 
 	spin_lock_irqsave(&subpage->lock, flags);
 	bitmap_set(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits);
 	spin_unlock_irqrestore(&subpage->lock, flags);
-	set_page_dirty(page);
+	folio_mark_dirty(folio);
 }
 
 /*
@@ -438,10 +439,10 @@ void btrfs_subpage_set_dirty(const struct btrfs_fs_info *fs_info,
  * extra handling for tree blocks.
  */
 bool btrfs_subpage_clear_and_test_dirty(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len)
+					struct folio *folio, u64 start, u32 len)
 {
-	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
-	unsigned int start_bit = subpage_calc_start_bit(fs_info, page,
+	struct btrfs_subpage *subpage = folio_get_private(folio);
+	unsigned int start_bit = subpage_calc_start_bit(fs_info, folio,
 							dirty, start, len);
 	unsigned long flags;
 	bool last = false;
@@ -455,101 +456,101 @@ bool btrfs_subpage_clear_and_test_dirty(const struct btrfs_fs_info *fs_info,
 }
 
 void btrfs_subpage_clear_dirty(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len)
+			       struct folio *folio, u64 start, u32 len)
 {
 	bool last;
 
-	last = btrfs_subpage_clear_and_test_dirty(fs_info, page, start, len);
+	last = btrfs_subpage_clear_and_test_dirty(fs_info, folio, start, len);
 	if (last)
-		clear_page_dirty_for_io(page);
+		folio_clear_dirty_for_io(folio);
 }
 
 void btrfs_subpage_set_writeback(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len)
+				 struct folio *folio, u64 start, u32 len)
 {
-	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
-	unsigned int start_bit = subpage_calc_start_bit(fs_info, page,
+	struct btrfs_subpage *subpage = folio_get_private(folio);
+	unsigned int start_bit = subpage_calc_start_bit(fs_info, folio,
 							writeback, start, len);
 	unsigned long flags;
 
 	spin_lock_irqsave(&subpage->lock, flags);
 	bitmap_set(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits);
-	set_page_writeback(page);
+	folio_start_writeback(folio);
 	spin_unlock_irqrestore(&subpage->lock, flags);
 }
 
 void btrfs_subpage_clear_writeback(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len)
+				   struct folio *folio, u64 start, u32 len)
 {
-	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
-	unsigned int start_bit = subpage_calc_start_bit(fs_info, page,
+	struct btrfs_subpage *subpage = folio_get_private(folio);
+	unsigned int start_bit = subpage_calc_start_bit(fs_info, folio,
 							writeback, start, len);
 	unsigned long flags;
 
 	spin_lock_irqsave(&subpage->lock, flags);
 	bitmap_clear(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits);
 	if (subpage_test_bitmap_all_zero(fs_info, subpage, writeback)) {
-		ASSERT(PageWriteback(page));
-		end_page_writeback(page);
+		ASSERT(folio_test_writeback(folio));
+		folio_end_writeback(folio);
 	}
 	spin_unlock_irqrestore(&subpage->lock, flags);
 }
 
 void btrfs_subpage_set_ordered(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len)
+			       struct folio *folio, u64 start, u32 len)
 {
-	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
-	unsigned int start_bit = subpage_calc_start_bit(fs_info, page,
+	struct btrfs_subpage *subpage = folio_get_private(folio);
+	unsigned int start_bit = subpage_calc_start_bit(fs_info, folio,
 							ordered, start, len);
 	unsigned long flags;
 
 	spin_lock_irqsave(&subpage->lock, flags);
 	bitmap_set(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits);
-	SetPageOrdered(page);
+	folio_set_ordered(folio);
 	spin_unlock_irqrestore(&subpage->lock, flags);
 }
 
 void btrfs_subpage_clear_ordered(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len)
+				 struct folio *folio, u64 start, u32 len)
 {
-	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
-	unsigned int start_bit = subpage_calc_start_bit(fs_info, page,
+	struct btrfs_subpage *subpage = folio_get_private(folio);
+	unsigned int start_bit = subpage_calc_start_bit(fs_info, folio,
 							ordered, start, len);
 	unsigned long flags;
 
 	spin_lock_irqsave(&subpage->lock, flags);
 	bitmap_clear(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits);
 	if (subpage_test_bitmap_all_zero(fs_info, subpage, ordered))
-		ClearPageOrdered(page);
+		folio_clear_ordered(folio);
 	spin_unlock_irqrestore(&subpage->lock, flags);
 }
 
 void btrfs_subpage_set_checked(const struct btrfs_fs_info *fs_info,
-			       struct page *page, u64 start, u32 len)
+			       struct folio *folio, u64 start, u32 len)
 {
-	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
-	unsigned int start_bit = subpage_calc_start_bit(fs_info, page,
+	struct btrfs_subpage *subpage = folio_get_private(folio);
+	unsigned int start_bit = subpage_calc_start_bit(fs_info, folio,
 							checked, start, len);
 	unsigned long flags;
 
 	spin_lock_irqsave(&subpage->lock, flags);
 	bitmap_set(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits);
 	if (subpage_test_bitmap_all_set(fs_info, subpage, checked))
-		SetPageChecked(page);
+		folio_set_checked(folio);
 	spin_unlock_irqrestore(&subpage->lock, flags);
 }
 
 void btrfs_subpage_clear_checked(const struct btrfs_fs_info *fs_info,
-				 struct page *page, u64 start, u32 len)
+				 struct folio *folio, u64 start, u32 len)
 {
-	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
-	unsigned int start_bit = subpage_calc_start_bit(fs_info, page,
+	struct btrfs_subpage *subpage = folio_get_private(folio);
+	unsigned int start_bit = subpage_calc_start_bit(fs_info, folio,
 							checked, start, len);
 	unsigned long flags;
 
 	spin_lock_irqsave(&subpage->lock, flags);
 	bitmap_clear(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits);
-	ClearPageChecked(page);
+	folio_clear_checked(folio);
 	spin_unlock_irqrestore(&subpage->lock, flags);
 }
 
@@ -559,10 +560,10 @@ void btrfs_subpage_clear_checked(const struct btrfs_fs_info *fs_info,
  */
 #define IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(name)				\
 bool btrfs_subpage_test_##name(const struct btrfs_fs_info *fs_info,	\
-		struct page *page, u64 start, u32 len)			\
+			       struct folio *folio, u64 start, u32 len)	\
 {									\
-	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; \
-	unsigned int start_bit = subpage_calc_start_bit(fs_info, page,	\
+	struct btrfs_subpage *subpage = folio_get_private(folio);	\
+	unsigned int start_bit = subpage_calc_start_bit(fs_info, folio,	\
 						name, start, len);	\
 	unsigned long flags;						\
 	bool ret;							\
@@ -584,88 +585,94 @@ IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(checked);
  * in.  We only test sectorsize == PAGE_SIZE cases so far, thus we can fall
  * back to regular sectorsize branch.
  */
-#define IMPLEMENT_BTRFS_PAGE_OPS(name, set_page_func, clear_page_func,	\
-			       test_page_func)				\
-void btrfs_page_set_##name(const struct btrfs_fs_info *fs_info,		\
-		struct page *page, u64 start, u32 len)			\
+#define IMPLEMENT_BTRFS_PAGE_OPS(name, folio_set_func,			\
+				 folio_clear_func, folio_test_func)	\
+void btrfs_folio_set_##name(const struct btrfs_fs_info *fs_info,	\
+			    struct folio *folio, u64 start, u32 len)	\
 {									\
-	if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page)) {	\
-		set_page_func(page);					\
+	if (unlikely(!fs_info) ||					\
+	    !btrfs_is_subpage(fs_info, folio->mapping)) {		\
+		folio_set_func(folio);					\
 		return;							\
 	}								\
-	btrfs_subpage_set_##name(fs_info, page, start, len);		\
+	btrfs_subpage_set_##name(fs_info, folio, start, len);		\
 }									\
-void btrfs_page_clear_##name(const struct btrfs_fs_info *fs_info,	\
-		struct page *page, u64 start, u32 len)			\
+void btrfs_folio_clear_##name(const struct btrfs_fs_info *fs_info,	\
+			      struct folio *folio, u64 start, u32 len)	\
 {									\
-	if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page)) {	\
-		clear_page_func(page);					\
+	if (unlikely(!fs_info) ||					\
+	    !btrfs_is_subpage(fs_info, folio->mapping)) {		\
+		folio_clear_func(folio);				\
 		return;							\
 	}								\
-	btrfs_subpage_clear_##name(fs_info, page, start, len);		\
+	btrfs_subpage_clear_##name(fs_info, folio, start, len);		\
 }									\
-bool btrfs_page_test_##name(const struct btrfs_fs_info *fs_info,	\
-		struct page *page, u64 start, u32 len)			\
+bool btrfs_folio_test_##name(const struct btrfs_fs_info *fs_info,	\
+			     struct folio *folio, u64 start, u32 len)	\
 {									\
-	if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page))	\
-		return test_page_func(page);				\
-	return btrfs_subpage_test_##name(fs_info, page, start, len);	\
+	if (unlikely(!fs_info) ||					\
+	    !btrfs_is_subpage(fs_info, folio->mapping))			\
+		return folio_test_func(folio);				\
+	return btrfs_subpage_test_##name(fs_info, folio, start, len);	\
 }									\
-void btrfs_page_clamp_set_##name(const struct btrfs_fs_info *fs_info,	\
-		struct page *page, u64 start, u32 len)			\
+void btrfs_folio_clamp_set_##name(const struct btrfs_fs_info *fs_info,	\
+				  struct folio *folio, u64 start, u32 len) \
 {									\
-	if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page)) {	\
-		set_page_func(page);					\
+	if (unlikely(!fs_info) ||					\
+	    !btrfs_is_subpage(fs_info, folio->mapping)) {		\
+		folio_set_func(folio);					\
 		return;							\
 	}								\
-	btrfs_subpage_clamp_range(page, &start, &len);			\
-	btrfs_subpage_set_##name(fs_info, page, start, len);		\
+	btrfs_subpage_clamp_range(folio, &start, &len);			\
+	btrfs_subpage_set_##name(fs_info, folio, start, len);		\
 }									\
-void btrfs_page_clamp_clear_##name(const struct btrfs_fs_info *fs_info, \
-		struct page *page, u64 start, u32 len)			\
+void btrfs_folio_clamp_clear_##name(const struct btrfs_fs_info *fs_info, \
+				    struct folio *folio, u64 start, u32 len) \
 {									\
-	if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page)) {	\
-		clear_page_func(page);					\
+	if (unlikely(!fs_info) ||					\
+	    !btrfs_is_subpage(fs_info, folio->mapping)) {		\
+		folio_clear_func(folio);				\
 		return;							\
 	}								\
-	btrfs_subpage_clamp_range(page, &start, &len);			\
-	btrfs_subpage_clear_##name(fs_info, page, start, len);		\
+	btrfs_subpage_clamp_range(folio, &start, &len);			\
+	btrfs_subpage_clear_##name(fs_info, folio, start, len);		\
 }									\
-bool btrfs_page_clamp_test_##name(const struct btrfs_fs_info *fs_info,	\
-		struct page *page, u64 start, u32 len)			\
+bool btrfs_folio_clamp_test_##name(const struct btrfs_fs_info *fs_info,	\
+				   struct folio *folio, u64 start, u32 len) \
 {									\
-	if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page))	\
-		return test_page_func(page);				\
-	btrfs_subpage_clamp_range(page, &start, &len);			\
-	return btrfs_subpage_test_##name(fs_info, page, start, len);	\
-}
-IMPLEMENT_BTRFS_PAGE_OPS(uptodate, SetPageUptodate, ClearPageUptodate,
-			 PageUptodate);
-IMPLEMENT_BTRFS_PAGE_OPS(dirty, set_page_dirty, clear_page_dirty_for_io,
-			 PageDirty);
-IMPLEMENT_BTRFS_PAGE_OPS(writeback, set_page_writeback, end_page_writeback,
-			 PageWriteback);
-IMPLEMENT_BTRFS_PAGE_OPS(ordered, SetPageOrdered, ClearPageOrdered,
-			 PageOrdered);
-IMPLEMENT_BTRFS_PAGE_OPS(checked, SetPageChecked, ClearPageChecked, PageChecked);
+	if (unlikely(!fs_info) ||					\
+	    !btrfs_is_subpage(fs_info, folio->mapping))			\
+		return folio_test_func(folio);				\
+	btrfs_subpage_clamp_range(folio, &start, &len);			\
+	return btrfs_subpage_test_##name(fs_info, folio, start, len);	\
+}
+IMPLEMENT_BTRFS_PAGE_OPS(uptodate, folio_mark_uptodate, folio_clear_uptodate,
+			 folio_test_uptodate);
+IMPLEMENT_BTRFS_PAGE_OPS(dirty, folio_mark_dirty, folio_clear_dirty_for_io,
+			 folio_test_dirty);
+IMPLEMENT_BTRFS_PAGE_OPS(writeback, folio_start_writeback, folio_end_writeback,
+			 folio_test_writeback);
+IMPLEMENT_BTRFS_PAGE_OPS(ordered, folio_set_ordered, folio_clear_ordered,
+			 folio_test_ordered);
+IMPLEMENT_BTRFS_PAGE_OPS(checked, folio_set_checked, folio_clear_checked,
+			 folio_test_checked);
 
 /*
  * Make sure not only the page dirty bit is cleared, but also subpage dirty bit
  * is cleared.
  */
-void btrfs_page_assert_not_dirty(const struct btrfs_fs_info *fs_info,
-				 struct page *page)
+void btrfs_folio_assert_not_dirty(const struct btrfs_fs_info *fs_info, struct folio *folio)
 {
-	struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
+	struct btrfs_subpage *subpage = folio_get_private(folio);
 
 	if (!IS_ENABLED(CONFIG_BTRFS_ASSERT))
 		return;
 
-	ASSERT(!PageDirty(page));
-	if (!btrfs_is_subpage(fs_info, page))
+	ASSERT(!folio_test_dirty(folio));
+	if (!btrfs_is_subpage(fs_info, folio->mapping))
 		return;
 
-	ASSERT(PagePrivate(page) && page->private);
+	ASSERT(folio_test_private(folio) && folio_get_private(folio));
 	ASSERT(subpage_test_bitmap_all_zero(fs_info, subpage, dirty));
 }
 
@@ -684,18 +691,20 @@ void btrfs_page_assert_not_dirty(const struct btrfs_fs_info *fs_info,
  *   extent_write_locked_range().
  *   In this case, we have to call subpage helper to handle the case.
  */
-void btrfs_page_unlock_writer(struct btrfs_fs_info *fs_info, struct page *page,
-			      u64 start, u32 len)
+void btrfs_folio_unlock_writer(struct btrfs_fs_info *fs_info,
+			       struct folio *folio, u64 start, u32 len)
 {
 	struct btrfs_subpage *subpage;
 
-	ASSERT(PageLocked(page));
+	ASSERT(folio_test_locked(folio));
 	/* For non-subpage case, we just unlock the page */
-	if (!btrfs_is_subpage(fs_info, page))
-		return unlock_page(page);
+	if (!btrfs_is_subpage(fs_info, folio->mapping)) {
+		folio_unlock(folio);
+		return;
+	}
 
-	ASSERT(PagePrivate(page) && page->private);
-	subpage = (struct btrfs_subpage *)page->private;
+	ASSERT(folio_test_private(folio) && folio_get_private(folio));
+	subpage = folio_get_private(folio);
 
 	/*
 	 * For subpage case, there are two types of locked page.  With or
@@ -704,12 +713,14 @@ void btrfs_page_unlock_writer(struct btrfs_fs_info *fs_info, struct page *page,
 	 * Since we own the page lock, no one else could touch subpage::writers
 	 * and we are safe to do several atomic operations without spinlock.
 	 */
-	if (atomic_read(&subpage->writers) == 0)
+	if (atomic_read(&subpage->writers) == 0) {
 		/* No writers, locked by plain lock_page() */
-		return unlock_page(page);
+		folio_unlock(folio);
+		return;
+	}
 
 	/* Have writers, use proper subpage helper to end it */
-	btrfs_page_end_writer_lock(fs_info, page, start, len);
+	btrfs_folio_end_writer_lock(fs_info, folio, start, len);
 }
 
 #define GET_SUBPAGE_BITMAP(subpage, subpage_info, name, dst)		\
@@ -717,7 +728,7 @@ void btrfs_page_unlock_writer(struct btrfs_fs_info *fs_info, struct page *page,
 		   subpage_info->name##_offset, subpage_info->bitmap_nr_bits)
 
 void __cold btrfs_subpage_dump_bitmap(const struct btrfs_fs_info *fs_info,
-				      struct page *page, u64 start, u32 len)
+				      struct folio *folio, u64 start, u32 len)
 {
 	struct btrfs_subpage_info *subpage_info = fs_info->subpage_info;
 	struct btrfs_subpage *subpage;
@@ -729,9 +740,9 @@ void __cold btrfs_subpage_dump_bitmap(const struct btrfs_fs_info *fs_info,
 	unsigned long checked_bitmap;
 	unsigned long flags;
 
-	ASSERT(PagePrivate(page) && page->private);
+	ASSERT(folio_test_private(folio) && folio_get_private(folio));
 	ASSERT(subpage_info);
-	subpage = (struct btrfs_subpage *)page->private;
+	subpage = folio_get_private(folio);
 
 	spin_lock_irqsave(&subpage->lock, flags);
 	GET_SUBPAGE_BITMAP(subpage, subpage_info, uptodate, &uptodate_bitmap);
@@ -741,10 +752,10 @@ void __cold btrfs_subpage_dump_bitmap(const struct btrfs_fs_info *fs_info,
 	GET_SUBPAGE_BITMAP(subpage, subpage_info, checked, &checked_bitmap);
 	spin_unlock_irqrestore(&subpage->lock, flags);
 
-	dump_page(page, "btrfs subpage dump");
+	dump_page(folio_page(folio, 0), "btrfs subpage dump");
 	btrfs_warn(fs_info,
 "start=%llu len=%u page=%llu, bitmaps uptodate=%*pbl error=%*pbl dirty=%*pbl writeback=%*pbl ordered=%*pbl checked=%*pbl",
-		    start, len, page_offset(page),
+		    start, len, folio_pos(folio),
 		    subpage_info->bitmap_nr_bits, &uptodate_bitmap,
 		    subpage_info->bitmap_nr_bits, &error_bitmap,
 		    subpage_info->bitmap_nr_bits, &dirty_bitmap,
diff --git a/fs/btrfs/subpage.h b/fs/btrfs/subpage.h
index 5cbf67ccbdeb..793c2b314a58 100644
--- a/fs/btrfs/subpage.h
+++ b/fs/btrfs/subpage.h
@@ -73,71 +73,68 @@ enum btrfs_subpage_type {
 	BTRFS_SUBPAGE_DATA,
 };
 
-bool btrfs_is_subpage(const struct btrfs_fs_info *fs_info, struct page *page);
+bool btrfs_is_subpage(const struct btrfs_fs_info *fs_info, struct address_space *mapping);
 
 void btrfs_init_subpage_info(struct btrfs_subpage_info *subpage_info, u32 sectorsize);
 int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info,
-			 struct page *page, enum btrfs_subpage_type type);
-void btrfs_detach_subpage(const struct btrfs_fs_info *fs_info,
-			  struct page *page);
+			 struct folio *folio, enum btrfs_subpage_type type);
+void btrfs_detach_subpage(const struct btrfs_fs_info *fs_info, struct folio *folio);
 
 /* Allocate additional data where page represents more than one sector */
 struct btrfs_subpage *btrfs_alloc_subpage(const struct btrfs_fs_info *fs_info,
 					  enum btrfs_subpage_type type);
 void btrfs_free_subpage(struct btrfs_subpage *subpage);
 
-void btrfs_page_inc_eb_refs(const struct btrfs_fs_info *fs_info,
-			    struct page *page);
-void btrfs_page_dec_eb_refs(const struct btrfs_fs_info *fs_info,
-			    struct page *page);
+void btrfs_folio_inc_eb_refs(const struct btrfs_fs_info *fs_info, struct folio *folio);
+void btrfs_folio_dec_eb_refs(const struct btrfs_fs_info *fs_info, struct folio *folio);
 
 void btrfs_subpage_start_reader(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len);
+				struct folio *folio, u64 start, u32 len);
 void btrfs_subpage_end_reader(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len);
+			      struct folio *folio, u64 start, u32 len);
 
 void btrfs_subpage_start_writer(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len);
+				struct folio *folio, u64 start, u32 len);
 bool btrfs_subpage_end_and_test_writer(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len);
-int btrfs_page_start_writer_lock(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len);
-void btrfs_page_end_writer_lock(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len);
+				       struct folio *folio, u64 start, u32 len);
+int btrfs_folio_start_writer_lock(const struct btrfs_fs_info *fs_info,
+				  struct folio *folio, u64 start, u32 len);
+void btrfs_folio_end_writer_lock(const struct btrfs_fs_info *fs_info,
+				 struct folio *folio, u64 start, u32 len);
 
 /*
  * Template for subpage related operations.
  *
- * btrfs_subpage_*() are for call sites where the page has subpage attached and
- * the range is ensured to be inside the page.
+ * btrfs_subpage_*() are for call sites where the folio has subpage attached and
+ * the range is ensured to be inside the folio's single page.
  *
- * btrfs_page_*() are for call sites where the page can either be subpage
- * specific or regular page. The function will handle both cases.
- * But the range still needs to be inside the page.
+ * btrfs_folio_*() are for call sites where the page can either be subpage
+ * specific or regular folios. The function will handle both cases.
+ * But the range still needs to be inside one single page.
  *
- * btrfs_page_clamp_*() are similar to btrfs_page_*(), except the range doesn't
+ * btrfs_folio_clamp_*() are similar to btrfs_folio_*(), except the range doesn't
  * need to be inside the page. Those functions will truncate the range
  * automatically.
  */
 #define DECLARE_BTRFS_SUBPAGE_OPS(name)					\
 void btrfs_subpage_set_##name(const struct btrfs_fs_info *fs_info,	\
-		struct page *page, u64 start, u32 len);			\
+		struct folio *folio, u64 start, u32 len);			\
 void btrfs_subpage_clear_##name(const struct btrfs_fs_info *fs_info,	\
-		struct page *page, u64 start, u32 len);			\
+		struct folio *folio, u64 start, u32 len);			\
 bool btrfs_subpage_test_##name(const struct btrfs_fs_info *fs_info,	\
-		struct page *page, u64 start, u32 len);			\
-void btrfs_page_set_##name(const struct btrfs_fs_info *fs_info,		\
-		struct page *page, u64 start, u32 len);			\
-void btrfs_page_clear_##name(const struct btrfs_fs_info *fs_info,	\
-		struct page *page, u64 start, u32 len);			\
-bool btrfs_page_test_##name(const struct btrfs_fs_info *fs_info,	\
-		struct page *page, u64 start, u32 len);			\
-void btrfs_page_clamp_set_##name(const struct btrfs_fs_info *fs_info,	\
-		struct page *page, u64 start, u32 len);			\
-void btrfs_page_clamp_clear_##name(const struct btrfs_fs_info *fs_info,	\
-		struct page *page, u64 start, u32 len);			\
-bool btrfs_page_clamp_test_##name(const struct btrfs_fs_info *fs_info,	\
-		struct page *page, u64 start, u32 len);
+		struct folio *folio, u64 start, u32 len);			\
+void btrfs_folio_set_##name(const struct btrfs_fs_info *fs_info,	\
+		struct folio *folio, u64 start, u32 len);			\
+void btrfs_folio_clear_##name(const struct btrfs_fs_info *fs_info,	\
+		struct folio *folio, u64 start, u32 len);			\
+bool btrfs_folio_test_##name(const struct btrfs_fs_info *fs_info,	\
+		struct folio *folio, u64 start, u32 len);			\
+void btrfs_folio_clamp_set_##name(const struct btrfs_fs_info *fs_info,	\
+		struct folio *folio, u64 start, u32 len);			\
+void btrfs_folio_clamp_clear_##name(const struct btrfs_fs_info *fs_info,	\
+		struct folio *folio, u64 start, u32 len);			\
+bool btrfs_folio_clamp_test_##name(const struct btrfs_fs_info *fs_info,	\
+		struct folio *folio, u64 start, u32 len);
 
 DECLARE_BTRFS_SUBPAGE_OPS(uptodate);
 DECLARE_BTRFS_SUBPAGE_OPS(dirty);
@@ -146,13 +143,12 @@ DECLARE_BTRFS_SUBPAGE_OPS(ordered);
 DECLARE_BTRFS_SUBPAGE_OPS(checked);
 
 bool btrfs_subpage_clear_and_test_dirty(const struct btrfs_fs_info *fs_info,
-		struct page *page, u64 start, u32 len);
+					struct folio *folio, u64 start, u32 len);
 
-void btrfs_page_assert_not_dirty(const struct btrfs_fs_info *fs_info,
-				 struct page *page);
-void btrfs_page_unlock_writer(struct btrfs_fs_info *fs_info, struct page *page,
-			      u64 start, u32 len);
+void btrfs_folio_assert_not_dirty(const struct btrfs_fs_info *fs_info, struct folio *folio);
+void btrfs_folio_unlock_writer(struct btrfs_fs_info *fs_info,
+			       struct folio *folio, u64 start, u32 len);
 void __cold btrfs_subpage_dump_bitmap(const struct btrfs_fs_info *fs_info,
-				      struct page *page, u64 start, u32 len);
+				      struct folio *folio, u64 start, u32 len);
 
 #endif
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index f638dc339693..896acfda1789 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -27,6 +27,7 @@
 #include <linux/crc32c.h>
 #include <linux/btrfs.h>
 #include <linux/security.h>
+#include <linux/fs_parser.h>
 #include "messages.h"
 #include "delayed-inode.h"
 #include "ctree.h"
@@ -64,27 +65,32 @@
 #include <trace/events/btrfs.h>
 
 static const struct super_operations btrfs_super_ops;
-
-/*
- * Types for mounting the default subvolume and a subvolume explicitly
- * requested by subvol=/path. That way the callchain is straightforward and we
- * don't have to play tricks with the mount options and recursive calls to
- * btrfs_mount.
- *
- * The new btrfs_root_fs_type also servers as a tag for the bdev_holder.
- */
 static struct file_system_type btrfs_fs_type;
-static struct file_system_type btrfs_root_fs_type;
-
-static int btrfs_remount(struct super_block *sb, int *flags, char *data);
 
 static void btrfs_put_super(struct super_block *sb)
 {
-	close_ctree(btrfs_sb(sb));
+	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+
+	btrfs_info(fs_info, "last unmount of filesystem %pU", fs_info->fs_devices->fsid);
+	close_ctree(fs_info);
 }
 
+/* Store the mount options related information. */
+struct btrfs_fs_context {
+	char *subvol_name;
+	u64 subvol_objectid;
+	u64 max_inline;
+	u32 commit_interval;
+	u32 metadata_ratio;
+	u32 thread_pool_size;
+	unsigned long mount_opt;
+	unsigned long compress_type:4;
+	unsigned int compress_level;
+	refcount_t refs;
+};
+
 enum {
-	Opt_acl, Opt_noacl,
+	Opt_acl,
 	Opt_clear_cache,
 	Opt_commit_interval,
 	Opt_compress,
@@ -94,27 +100,26 @@ enum {
 	Opt_degraded,
 	Opt_device,
 	Opt_fatal_errors,
-	Opt_flushoncommit, Opt_noflushoncommit,
+	Opt_flushoncommit,
 	Opt_max_inline,
-	Opt_barrier, Opt_nobarrier,
-	Opt_datacow, Opt_nodatacow,
-	Opt_datasum, Opt_nodatasum,
-	Opt_defrag, Opt_nodefrag,
-	Opt_discard, Opt_nodiscard,
+	Opt_barrier,
+	Opt_datacow,
+	Opt_datasum,
+	Opt_defrag,
+	Opt_discard,
 	Opt_discard_mode,
-	Opt_norecovery,
 	Opt_ratio,
 	Opt_rescan_uuid_tree,
 	Opt_skip_balance,
-	Opt_space_cache, Opt_no_space_cache,
+	Opt_space_cache,
 	Opt_space_cache_version,
-	Opt_ssd, Opt_nossd,
-	Opt_ssd_spread, Opt_nossd_spread,
+	Opt_ssd,
+	Opt_ssd_spread,
 	Opt_subvol,
 	Opt_subvol_empty,
 	Opt_subvolid,
 	Opt_thread_pool,
-	Opt_treelog, Opt_notreelog,
+	Opt_treelog,
 	Opt_user_subvol_rm_allowed,
 
 	/* Rescue options */
@@ -125,14 +130,10 @@ enum {
 	Opt_ignoredatacsums,
 	Opt_rescue_all,
 
-	/* Deprecated options */
-	Opt_recovery,
-	Opt_inode_cache, Opt_noinode_cache,
-
 	/* Debugging options */
-	Opt_enospc_debug, Opt_noenospc_debug,
+	Opt_enospc_debug,
 #ifdef CONFIG_BTRFS_DEBUG
-	Opt_fragment_data, Opt_fragment_metadata, Opt_fragment_all,
+	Opt_fragment, Opt_fragment_data, Opt_fragment_metadata, Opt_fragment_all,
 #endif
 #ifdef CONFIG_BTRFS_FS_REF_VERIFY
 	Opt_ref_verify,
@@ -140,785 +141,611 @@ enum {
 	Opt_err,
 };
 
-static const match_table_t tokens = {
-	{Opt_acl, "acl"},
-	{Opt_noacl, "noacl"},
-	{Opt_clear_cache, "clear_cache"},
-	{Opt_commit_interval, "commit=%u"},
-	{Opt_compress, "compress"},
-	{Opt_compress_type, "compress=%s"},
-	{Opt_compress_force, "compress-force"},
-	{Opt_compress_force_type, "compress-force=%s"},
-	{Opt_degraded, "degraded"},
-	{Opt_device, "device=%s"},
-	{Opt_fatal_errors, "fatal_errors=%s"},
-	{Opt_flushoncommit, "flushoncommit"},
-	{Opt_noflushoncommit, "noflushoncommit"},
-	{Opt_inode_cache, "inode_cache"},
-	{Opt_noinode_cache, "noinode_cache"},
-	{Opt_max_inline, "max_inline=%s"},
-	{Opt_barrier, "barrier"},
-	{Opt_nobarrier, "nobarrier"},
-	{Opt_datacow, "datacow"},
-	{Opt_nodatacow, "nodatacow"},
-	{Opt_datasum, "datasum"},
-	{Opt_nodatasum, "nodatasum"},
-	{Opt_defrag, "autodefrag"},
-	{Opt_nodefrag, "noautodefrag"},
-	{Opt_discard, "discard"},
-	{Opt_discard_mode, "discard=%s"},
-	{Opt_nodiscard, "nodiscard"},
-	{Opt_norecovery, "norecovery"},
-	{Opt_ratio, "metadata_ratio=%u"},
-	{Opt_rescan_uuid_tree, "rescan_uuid_tree"},
-	{Opt_skip_balance, "skip_balance"},
-	{Opt_space_cache, "space_cache"},
-	{Opt_no_space_cache, "nospace_cache"},
-	{Opt_space_cache_version, "space_cache=%s"},
-	{Opt_ssd, "ssd"},
-	{Opt_nossd, "nossd"},
-	{Opt_ssd_spread, "ssd_spread"},
-	{Opt_nossd_spread, "nossd_spread"},
-	{Opt_subvol, "subvol=%s"},
-	{Opt_subvol_empty, "subvol="},
-	{Opt_subvolid, "subvolid=%s"},
-	{Opt_thread_pool, "thread_pool=%u"},
-	{Opt_treelog, "treelog"},
-	{Opt_notreelog, "notreelog"},
-	{Opt_user_subvol_rm_allowed, "user_subvol_rm_allowed"},
+enum {
+	Opt_fatal_errors_panic,
+	Opt_fatal_errors_bug,
+};
 
-	/* Rescue options */
-	{Opt_rescue, "rescue=%s"},
+static const struct constant_table btrfs_parameter_fatal_errors[] = {
+	{ "panic", Opt_fatal_errors_panic },
+	{ "bug", Opt_fatal_errors_bug },
+	{}
+};
+
+enum {
+	Opt_discard_sync,
+	Opt_discard_async,
+};
+
+static const struct constant_table btrfs_parameter_discard[] = {
+	{ "sync", Opt_discard_sync },
+	{ "async", Opt_discard_async },
+	{}
+};
+
+enum {
+	Opt_space_cache_v1,
+	Opt_space_cache_v2,
+};
+
+static const struct constant_table btrfs_parameter_space_cache[] = {
+	{ "v1", Opt_space_cache_v1 },
+	{ "v2", Opt_space_cache_v2 },
+	{}
+};
+
+enum {
+	Opt_rescue_usebackuproot,
+	Opt_rescue_nologreplay,
+	Opt_rescue_ignorebadroots,
+	Opt_rescue_ignoredatacsums,
+	Opt_rescue_parameter_all,
+};
+
+static const struct constant_table btrfs_parameter_rescue[] = {
+	{ "usebackuproot", Opt_rescue_usebackuproot },
+	{ "nologreplay", Opt_rescue_nologreplay },
+	{ "ignorebadroots", Opt_rescue_ignorebadroots },
+	{ "ibadroots", Opt_rescue_ignorebadroots },
+	{ "ignoredatacsums", Opt_rescue_ignoredatacsums },
+	{ "idatacsums", Opt_rescue_ignoredatacsums },
+	{ "all", Opt_rescue_parameter_all },
+	{}
+};
+
+#ifdef CONFIG_BTRFS_DEBUG
+enum {
+	Opt_fragment_parameter_data,
+	Opt_fragment_parameter_metadata,
+	Opt_fragment_parameter_all,
+};
+
+static const struct constant_table btrfs_parameter_fragment[] = {
+	{ "data", Opt_fragment_parameter_data },
+	{ "metadata", Opt_fragment_parameter_metadata },
+	{ "all", Opt_fragment_parameter_all },
+	{}
+};
+#endif
+
+static const struct fs_parameter_spec btrfs_fs_parameters[] = {
+	fsparam_flag_no("acl", Opt_acl),
+	fsparam_flag_no("autodefrag", Opt_defrag),
+	fsparam_flag_no("barrier", Opt_barrier),
+	fsparam_flag("clear_cache", Opt_clear_cache),
+	fsparam_u32("commit", Opt_commit_interval),
+	fsparam_flag("compress", Opt_compress),
+	fsparam_string("compress", Opt_compress_type),
+	fsparam_flag("compress-force", Opt_compress_force),
+	fsparam_string("compress-force", Opt_compress_force_type),
+	fsparam_flag_no("datacow", Opt_datacow),
+	fsparam_flag_no("datasum", Opt_datasum),
+	fsparam_flag("degraded", Opt_degraded),
+	fsparam_string("device", Opt_device),
+	fsparam_flag_no("discard", Opt_discard),
+	fsparam_enum("discard", Opt_discard_mode, btrfs_parameter_discard),
+	fsparam_enum("fatal_errors", Opt_fatal_errors, btrfs_parameter_fatal_errors),
+	fsparam_flag_no("flushoncommit", Opt_flushoncommit),
+	fsparam_string("max_inline", Opt_max_inline),
+	fsparam_u32("metadata_ratio", Opt_ratio),
+	fsparam_flag("rescan_uuid_tree", Opt_rescan_uuid_tree),
+	fsparam_flag("skip_balance", Opt_skip_balance),
+	fsparam_flag_no("space_cache", Opt_space_cache),
+	fsparam_enum("space_cache", Opt_space_cache_version, btrfs_parameter_space_cache),
+	fsparam_flag_no("ssd", Opt_ssd),
+	fsparam_flag_no("ssd_spread", Opt_ssd_spread),
+	fsparam_string("subvol", Opt_subvol),
+	fsparam_flag("subvol=", Opt_subvol_empty),
+	fsparam_u64("subvolid", Opt_subvolid),
+	fsparam_u32("thread_pool", Opt_thread_pool),
+	fsparam_flag_no("treelog", Opt_treelog),
+	fsparam_flag("user_subvol_rm_allowed", Opt_user_subvol_rm_allowed),
+
+	/* Rescue options. */
+	fsparam_enum("rescue", Opt_rescue, btrfs_parameter_rescue),
 	/* Deprecated, with alias rescue=nologreplay */
-	{Opt_nologreplay, "nologreplay"},
+	__fsparam(NULL, "nologreplay", Opt_nologreplay, fs_param_deprecated, NULL),
 	/* Deprecated, with alias rescue=usebackuproot */
-	{Opt_usebackuproot, "usebackuproot"},
-
-	/* Deprecated options */
-	{Opt_recovery, "recovery"},
+	__fsparam(NULL, "usebackuproot", Opt_usebackuproot, fs_param_deprecated, NULL),
 
-	/* Debugging options */
-	{Opt_enospc_debug, "enospc_debug"},
-	{Opt_noenospc_debug, "noenospc_debug"},
+	/* Debugging options. */
+	fsparam_flag_no("enospc_debug", Opt_enospc_debug),
 #ifdef CONFIG_BTRFS_DEBUG
-	{Opt_fragment_data, "fragment=data"},
-	{Opt_fragment_metadata, "fragment=metadata"},
-	{Opt_fragment_all, "fragment=all"},
+	fsparam_enum("fragment", Opt_fragment, btrfs_parameter_fragment),
 #endif
 #ifdef CONFIG_BTRFS_FS_REF_VERIFY
-	{Opt_ref_verify, "ref_verify"},
+	fsparam_flag("ref_verify", Opt_ref_verify),
 #endif
-	{Opt_err, NULL},
-};
-
-static const match_table_t rescue_tokens = {
-	{Opt_usebackuproot, "usebackuproot"},
-	{Opt_nologreplay, "nologreplay"},
-	{Opt_ignorebadroots, "ignorebadroots"},
-	{Opt_ignorebadroots, "ibadroots"},
-	{Opt_ignoredatacsums, "ignoredatacsums"},
-	{Opt_ignoredatacsums, "idatacsums"},
-	{Opt_rescue_all, "all"},
-	{Opt_err, NULL},
+	{}
 };
 
-static bool check_ro_option(struct btrfs_fs_info *fs_info, unsigned long opt,
-			    const char *opt_name)
+/* No support for restricting writes to btrfs devices yet... */
+static inline blk_mode_t btrfs_open_mode(struct fs_context *fc)
 {
-	if (fs_info->mount_opt & opt) {
-		btrfs_err(fs_info, "%s must be used with ro mount option",
-			  opt_name);
-		return true;
-	}
-	return false;
+	return sb_open_mode(fc->sb_flags) & ~BLK_OPEN_RESTRICT_WRITES;
 }
 
-static int parse_rescue_options(struct btrfs_fs_info *info, const char *options)
+static int btrfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
 {
-	char *opts;
-	char *orig;
-	char *p;
-	substring_t args[MAX_OPT_ARGS];
-	int ret = 0;
+	struct btrfs_fs_context *ctx = fc->fs_private;
+	struct fs_parse_result result;
+	int opt;
 
-	opts = kstrdup(options, GFP_KERNEL);
-	if (!opts)
-		return -ENOMEM;
-	orig = opts;
+	opt = fs_parse(fc, btrfs_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
 
-	while ((p = strsep(&opts, ":")) != NULL) {
-		int token;
+	switch (opt) {
+	case Opt_degraded:
+		btrfs_set_opt(ctx->mount_opt, DEGRADED);
+		break;
+	case Opt_subvol_empty:
+		/*
+		 * This exists because we used to allow it on accident, so we're
+		 * keeping it to maintain ABI.  See 37becec95ac3 ("Btrfs: allow
+		 * empty subvol= again").
+		 */
+		break;
+	case Opt_subvol:
+		kfree(ctx->subvol_name);
+		ctx->subvol_name = kstrdup(param->string, GFP_KERNEL);
+		if (!ctx->subvol_name)
+			return -ENOMEM;
+		break;
+	case Opt_subvolid:
+		ctx->subvol_objectid = result.uint_64;
 
-		if (!*p)
-			continue;
-		token = match_token(p, rescue_tokens, args);
-		switch (token){
-		case Opt_usebackuproot:
-			btrfs_info(info,
-				   "trying to use backup root at mount time");
-			btrfs_set_opt(info->mount_opt, USEBACKUPROOT);
-			break;
-		case Opt_nologreplay:
-			btrfs_set_and_info(info, NOLOGREPLAY,
-					   "disabling log replay at mount time");
-			break;
-		case Opt_ignorebadroots:
-			btrfs_set_and_info(info, IGNOREBADROOTS,
-					   "ignoring bad roots");
-			break;
-		case Opt_ignoredatacsums:
-			btrfs_set_and_info(info, IGNOREDATACSUMS,
-					   "ignoring data csums");
-			break;
-		case Opt_rescue_all:
-			btrfs_info(info, "enabling all of the rescue options");
-			btrfs_set_and_info(info, IGNOREDATACSUMS,
-					   "ignoring data csums");
-			btrfs_set_and_info(info, IGNOREBADROOTS,
-					   "ignoring bad roots");
-			btrfs_set_and_info(info, NOLOGREPLAY,
-					   "disabling log replay at mount time");
-			break;
-		case Opt_err:
-			btrfs_info(info, "unrecognized rescue option '%s'", p);
-			ret = -EINVAL;
-			goto out;
-		default:
-			break;
-		}
+		/* subvolid=0 means give me the original fs_tree. */
+		if (!ctx->subvol_objectid)
+			ctx->subvol_objectid = BTRFS_FS_TREE_OBJECTID;
+		break;
+	case Opt_device: {
+		struct btrfs_device *device;
+		blk_mode_t mode = btrfs_open_mode(fc);
 
+		mutex_lock(&uuid_mutex);
+		device = btrfs_scan_one_device(param->string, mode, false);
+		mutex_unlock(&uuid_mutex);
+		if (IS_ERR(device))
+			return PTR_ERR(device);
+		break;
 	}
-out:
-	kfree(orig);
-	return ret;
-}
-
-/*
- * Regular mount options parser.  Everything that is needed only when
- * reading in a new superblock is parsed here.
- * XXX JDM: This needs to be cleaned up for remount.
- */
-int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
-			unsigned long new_flags)
-{
-	substring_t args[MAX_OPT_ARGS];
-	char *p, *num;
-	int intarg;
-	int ret = 0;
-	char *compress_type;
-	bool compress_force = false;
-	enum btrfs_compression_type saved_compress_type;
-	int saved_compress_level;
-	bool saved_compress_force;
-	int no_compress = 0;
-	const bool remounting = test_bit(BTRFS_FS_STATE_REMOUNTING, &info->fs_state);
-
-	if (btrfs_fs_compat_ro(info, FREE_SPACE_TREE))
-		btrfs_set_opt(info->mount_opt, FREE_SPACE_TREE);
-	else if (btrfs_free_space_cache_v1_active(info)) {
-		if (btrfs_is_zoned(info)) {
-			btrfs_info(info,
-			"zoned: clearing existing space cache");
-			btrfs_set_super_cache_generation(info->super_copy, 0);
+	case Opt_datasum:
+		if (result.negated) {
+			btrfs_set_opt(ctx->mount_opt, NODATASUM);
 		} else {
-			btrfs_set_opt(info->mount_opt, SPACE_CACHE);
+			btrfs_clear_opt(ctx->mount_opt, NODATACOW);
+			btrfs_clear_opt(ctx->mount_opt, NODATASUM);
 		}
-	}
-
-	/*
-	 * Even the options are empty, we still need to do extra check
-	 * against new flags
-	 */
-	if (!options)
-		goto check;
-
-	while ((p = strsep(&options, ",")) != NULL) {
-		int token;
-		if (!*p)
-			continue;
-
-		token = match_token(p, tokens, args);
-		switch (token) {
-		case Opt_degraded:
-			btrfs_info(info, "allowing degraded mounts");
-			btrfs_set_opt(info->mount_opt, DEGRADED);
-			break;
-		case Opt_subvol:
-		case Opt_subvol_empty:
-		case Opt_subvolid:
-		case Opt_device:
-			/*
-			 * These are parsed by btrfs_parse_subvol_options or
-			 * btrfs_parse_device_options and can be ignored here.
-			 */
-			break;
-		case Opt_nodatasum:
-			btrfs_set_and_info(info, NODATASUM,
-					   "setting nodatasum");
-			break;
-		case Opt_datasum:
-			if (btrfs_test_opt(info, NODATASUM)) {
-				if (btrfs_test_opt(info, NODATACOW))
-					btrfs_info(info,
-						   "setting datasum, datacow enabled");
-				else
-					btrfs_info(info, "setting datasum");
-			}
-			btrfs_clear_opt(info->mount_opt, NODATACOW);
-			btrfs_clear_opt(info->mount_opt, NODATASUM);
-			break;
-		case Opt_nodatacow:
-			if (!btrfs_test_opt(info, NODATACOW)) {
-				if (!btrfs_test_opt(info, COMPRESS) ||
-				    !btrfs_test_opt(info, FORCE_COMPRESS)) {
-					btrfs_info(info,
-						   "setting nodatacow, compression disabled");
-				} else {
-					btrfs_info(info, "setting nodatacow");
-				}
-			}
-			btrfs_clear_opt(info->mount_opt, COMPRESS);
-			btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
-			btrfs_set_opt(info->mount_opt, NODATACOW);
-			btrfs_set_opt(info->mount_opt, NODATASUM);
-			break;
-		case Opt_datacow:
-			btrfs_clear_and_info(info, NODATACOW,
-					     "setting datacow");
-			break;
-		case Opt_compress_force:
-		case Opt_compress_force_type:
-			compress_force = true;
-			fallthrough;
-		case Opt_compress:
-		case Opt_compress_type:
-			saved_compress_type = btrfs_test_opt(info,
-							     COMPRESS) ?
-				info->compress_type : BTRFS_COMPRESS_NONE;
-			saved_compress_force =
-				btrfs_test_opt(info, FORCE_COMPRESS);
-			saved_compress_level = info->compress_level;
-			if (token == Opt_compress ||
-			    token == Opt_compress_force ||
-			    strncmp(args[0].from, "zlib", 4) == 0) {
-				compress_type = "zlib";
-
-				info->compress_type = BTRFS_COMPRESS_ZLIB;
-				info->compress_level = BTRFS_ZLIB_DEFAULT_LEVEL;
-				/*
-				 * args[0] contains uninitialized data since
-				 * for these tokens we don't expect any
-				 * parameter.
-				 */
-				if (token != Opt_compress &&
-				    token != Opt_compress_force)
-					info->compress_level =
-					  btrfs_compress_str2level(
-							BTRFS_COMPRESS_ZLIB,
-							args[0].from + 4);
-				btrfs_set_opt(info->mount_opt, COMPRESS);
-				btrfs_clear_opt(info->mount_opt, NODATACOW);
-				btrfs_clear_opt(info->mount_opt, NODATASUM);
-				no_compress = 0;
-			} else if (strncmp(args[0].from, "lzo", 3) == 0) {
-				compress_type = "lzo";
-				info->compress_type = BTRFS_COMPRESS_LZO;
-				info->compress_level = 0;
-				btrfs_set_opt(info->mount_opt, COMPRESS);
-				btrfs_clear_opt(info->mount_opt, NODATACOW);
-				btrfs_clear_opt(info->mount_opt, NODATASUM);
-				btrfs_set_fs_incompat(info, COMPRESS_LZO);
-				no_compress = 0;
-			} else if (strncmp(args[0].from, "zstd", 4) == 0) {
-				compress_type = "zstd";
-				info->compress_type = BTRFS_COMPRESS_ZSTD;
-				info->compress_level =
-					btrfs_compress_str2level(
-							 BTRFS_COMPRESS_ZSTD,
-							 args[0].from + 4);
-				btrfs_set_opt(info->mount_opt, COMPRESS);
-				btrfs_clear_opt(info->mount_opt, NODATACOW);
-				btrfs_clear_opt(info->mount_opt, NODATASUM);
-				btrfs_set_fs_incompat(info, COMPRESS_ZSTD);
-				no_compress = 0;
-			} else if (strncmp(args[0].from, "no", 2) == 0) {
-				compress_type = "no";
-				info->compress_level = 0;
-				info->compress_type = 0;
-				btrfs_clear_opt(info->mount_opt, COMPRESS);
-				btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
-				compress_force = false;
-				no_compress++;
-			} else {
-				btrfs_err(info, "unrecognized compression value %s",
-					  args[0].from);
-				ret = -EINVAL;
-				goto out;
-			}
-
-			if (compress_force) {
-				btrfs_set_opt(info->mount_opt, FORCE_COMPRESS);
-			} else {
-				/*
-				 * If we remount from compress-force=xxx to
-				 * compress=xxx, we need clear FORCE_COMPRESS
-				 * flag, otherwise, there is no way for users
-				 * to disable forcible compression separately.
-				 */
-				btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
-			}
-			if (no_compress == 1) {
-				btrfs_info(info, "use no compression");
-			} else if ((info->compress_type != saved_compress_type) ||
-				   (compress_force != saved_compress_force) ||
-				   (info->compress_level != saved_compress_level)) {
-				btrfs_info(info, "%s %s compression, level %d",
-					   (compress_force) ? "force" : "use",
-					   compress_type, info->compress_level);
-			}
-			compress_force = false;
-			break;
-		case Opt_ssd:
-			btrfs_set_and_info(info, SSD,
-					   "enabling ssd optimizations");
-			btrfs_clear_opt(info->mount_opt, NOSSD);
-			break;
-		case Opt_ssd_spread:
-			btrfs_set_and_info(info, SSD,
-					   "enabling ssd optimizations");
-			btrfs_set_and_info(info, SSD_SPREAD,
-					   "using spread ssd allocation scheme");
-			btrfs_clear_opt(info->mount_opt, NOSSD);
-			break;
-		case Opt_nossd:
-			btrfs_set_opt(info->mount_opt, NOSSD);
-			btrfs_clear_and_info(info, SSD,
-					     "not using ssd optimizations");
-			fallthrough;
-		case Opt_nossd_spread:
-			btrfs_clear_and_info(info, SSD_SPREAD,
-					     "not using spread ssd allocation scheme");
-			break;
-		case Opt_barrier:
-			btrfs_clear_and_info(info, NOBARRIER,
-					     "turning on barriers");
-			break;
-		case Opt_nobarrier:
-			btrfs_set_and_info(info, NOBARRIER,
-					   "turning off barriers");
-			break;
-		case Opt_thread_pool:
-			ret = match_int(&args[0], &intarg);
-			if (ret) {
-				btrfs_err(info, "unrecognized thread_pool value %s",
-					  args[0].from);
-				goto out;
-			} else if (intarg == 0) {
-				btrfs_err(info, "invalid value 0 for thread_pool");
-				ret = -EINVAL;
-				goto out;
-			}
-			info->thread_pool_size = intarg;
-			break;
-		case Opt_max_inline:
-			num = match_strdup(&args[0]);
-			if (num) {
-				info->max_inline = memparse(num, NULL);
-				kfree(num);
-
-				if (info->max_inline) {
-					info->max_inline = min_t(u64,
-						info->max_inline,
-						info->sectorsize);
-				}
-				btrfs_info(info, "max_inline at %llu",
-					   info->max_inline);
-			} else {
-				ret = -ENOMEM;
-				goto out;
-			}
-			break;
-		case Opt_acl:
+		break;
+	case Opt_datacow:
+		if (result.negated) {
+			btrfs_clear_opt(ctx->mount_opt, COMPRESS);
+			btrfs_clear_opt(ctx->mount_opt, FORCE_COMPRESS);
+			btrfs_set_opt(ctx->mount_opt, NODATACOW);
+			btrfs_set_opt(ctx->mount_opt, NODATASUM);
+		} else {
+			btrfs_clear_opt(ctx->mount_opt, NODATACOW);
+		}
+		break;
+	case Opt_compress_force:
+	case Opt_compress_force_type:
+		btrfs_set_opt(ctx->mount_opt, FORCE_COMPRESS);
+		fallthrough;
+	case Opt_compress:
+	case Opt_compress_type:
+		if (opt == Opt_compress || opt == Opt_compress_force) {
+			ctx->compress_type = BTRFS_COMPRESS_ZLIB;
+			ctx->compress_level = BTRFS_ZLIB_DEFAULT_LEVEL;
+			btrfs_set_opt(ctx->mount_opt, COMPRESS);
+			btrfs_clear_opt(ctx->mount_opt, NODATACOW);
+			btrfs_clear_opt(ctx->mount_opt, NODATASUM);
+		} else if (strncmp(param->string, "zlib", 4) == 0) {
+			ctx->compress_type = BTRFS_COMPRESS_ZLIB;
+			ctx->compress_level =
+				btrfs_compress_str2level(BTRFS_COMPRESS_ZLIB,
+							 param->string + 4);
+			btrfs_set_opt(ctx->mount_opt, COMPRESS);
+			btrfs_clear_opt(ctx->mount_opt, NODATACOW);
+			btrfs_clear_opt(ctx->mount_opt, NODATASUM);
+		} else if (strncmp(param->string, "lzo", 3) == 0) {
+			ctx->compress_type = BTRFS_COMPRESS_LZO;
+			ctx->compress_level = 0;
+			btrfs_set_opt(ctx->mount_opt, COMPRESS);
+			btrfs_clear_opt(ctx->mount_opt, NODATACOW);
+			btrfs_clear_opt(ctx->mount_opt, NODATASUM);
+		} else if (strncmp(param->string, "zstd", 4) == 0) {
+			ctx->compress_type = BTRFS_COMPRESS_ZSTD;
+			ctx->compress_level =
+				btrfs_compress_str2level(BTRFS_COMPRESS_ZSTD,
+							 param->string + 4);
+			btrfs_set_opt(ctx->mount_opt, COMPRESS);
+			btrfs_clear_opt(ctx->mount_opt, NODATACOW);
+			btrfs_clear_opt(ctx->mount_opt, NODATASUM);
+		} else if (strncmp(param->string, "no", 2) == 0) {
+			ctx->compress_level = 0;
+			ctx->compress_type = 0;
+			btrfs_clear_opt(ctx->mount_opt, COMPRESS);
+			btrfs_clear_opt(ctx->mount_opt, FORCE_COMPRESS);
+		} else {
+			btrfs_err(NULL, "unrecognized compression value %s",
+				  param->string);
+			return -EINVAL;
+		}
+		break;
+	case Opt_ssd:
+		if (result.negated) {
+			btrfs_set_opt(ctx->mount_opt, NOSSD);
+			btrfs_clear_opt(ctx->mount_opt, SSD);
+			btrfs_clear_opt(ctx->mount_opt, SSD_SPREAD);
+		} else {
+			btrfs_set_opt(ctx->mount_opt, SSD);
+			btrfs_clear_opt(ctx->mount_opt, NOSSD);
+		}
+		break;
+	case Opt_ssd_spread:
+		if (result.negated) {
+			btrfs_clear_opt(ctx->mount_opt, SSD_SPREAD);
+		} else {
+			btrfs_set_opt(ctx->mount_opt, SSD);
+			btrfs_set_opt(ctx->mount_opt, SSD_SPREAD);
+			btrfs_clear_opt(ctx->mount_opt, NOSSD);
+		}
+		break;
+	case Opt_barrier:
+		if (result.negated)
+			btrfs_set_opt(ctx->mount_opt, NOBARRIER);
+		else
+			btrfs_clear_opt(ctx->mount_opt, NOBARRIER);
+		break;
+	case Opt_thread_pool:
+		if (result.uint_32 == 0) {
+			btrfs_err(NULL, "invalid value 0 for thread_pool");
+			return -EINVAL;
+		}
+		ctx->thread_pool_size = result.uint_32;
+		break;
+	case Opt_max_inline:
+		ctx->max_inline = memparse(param->string, NULL);
+		break;
+	case Opt_acl:
+		if (result.negated) {
+			fc->sb_flags &= ~SB_POSIXACL;
+		} else {
 #ifdef CONFIG_BTRFS_FS_POSIX_ACL
-			info->sb->s_flags |= SB_POSIXACL;
-			break;
+			fc->sb_flags |= SB_POSIXACL;
 #else
-			btrfs_err(info, "support for ACL not compiled in!");
-			ret = -EINVAL;
-			goto out;
+			btrfs_err(NULL, "support for ACL not compiled in");
+			return -EINVAL;
 #endif
-		case Opt_noacl:
-			info->sb->s_flags &= ~SB_POSIXACL;
-			break;
-		case Opt_notreelog:
-			btrfs_set_and_info(info, NOTREELOG,
-					   "disabling tree log");
-			break;
-		case Opt_treelog:
-			btrfs_clear_and_info(info, NOTREELOG,
-					     "enabling tree log");
-			break;
-		case Opt_norecovery:
-		case Opt_nologreplay:
-			btrfs_warn(info,
+		}
+		/*
+		 * VFS limits the ability to toggle ACL on and off via remount,
+		 * despite every file system allowing this.  This seems to be
+		 * an oversight since we all do, but it'll fail if we're
+		 * remounting.  So don't set the mask here, we'll check it in
+		 * btrfs_reconfigure and do the toggling ourselves.
+		 */
+		if (fc->purpose != FS_CONTEXT_FOR_RECONFIGURE)
+			fc->sb_flags_mask |= SB_POSIXACL;
+		break;
+	case Opt_treelog:
+		if (result.negated)
+			btrfs_set_opt(ctx->mount_opt, NOTREELOG);
+		else
+			btrfs_clear_opt(ctx->mount_opt, NOTREELOG);
+		break;
+	case Opt_nologreplay:
+		btrfs_warn(NULL,
 		"'nologreplay' is deprecated, use 'rescue=nologreplay' instead");
-			btrfs_set_and_info(info, NOLOGREPLAY,
-					   "disabling log replay at mount time");
-			break;
-		case Opt_flushoncommit:
-			btrfs_set_and_info(info, FLUSHONCOMMIT,
-					   "turning on flush-on-commit");
-			break;
-		case Opt_noflushoncommit:
-			btrfs_clear_and_info(info, FLUSHONCOMMIT,
-					     "turning off flush-on-commit");
-			break;
-		case Opt_ratio:
-			ret = match_int(&args[0], &intarg);
-			if (ret) {
-				btrfs_err(info, "unrecognized metadata_ratio value %s",
-					  args[0].from);
-				goto out;
-			}
-			info->metadata_ratio = intarg;
-			btrfs_info(info, "metadata ratio %u",
-				   info->metadata_ratio);
-			break;
-		case Opt_discard:
-		case Opt_discard_mode:
-			if (token == Opt_discard ||
-			    strcmp(args[0].from, "sync") == 0) {
-				btrfs_clear_opt(info->mount_opt, DISCARD_ASYNC);
-				btrfs_set_and_info(info, DISCARD_SYNC,
-						   "turning on sync discard");
-			} else if (strcmp(args[0].from, "async") == 0) {
-				btrfs_clear_opt(info->mount_opt, DISCARD_SYNC);
-				btrfs_set_and_info(info, DISCARD_ASYNC,
-						   "turning on async discard");
-			} else {
-				btrfs_err(info, "unrecognized discard mode value %s",
-					  args[0].from);
-				ret = -EINVAL;
-				goto out;
-			}
-			btrfs_clear_opt(info->mount_opt, NODISCARD);
-			break;
-		case Opt_nodiscard:
-			btrfs_clear_and_info(info, DISCARD_SYNC,
-					     "turning off discard");
-			btrfs_clear_and_info(info, DISCARD_ASYNC,
-					     "turning off async discard");
-			btrfs_set_opt(info->mount_opt, NODISCARD);
-			break;
-		case Opt_space_cache:
-		case Opt_space_cache_version:
-			/*
-			 * We already set FREE_SPACE_TREE above because we have
-			 * compat_ro(FREE_SPACE_TREE) set, and we aren't going
-			 * to allow v1 to be set for extent tree v2, simply
-			 * ignore this setting if we're extent tree v2.
-			 */
-			if (btrfs_fs_incompat(info, EXTENT_TREE_V2))
-				break;
-			if (token == Opt_space_cache ||
-			    strcmp(args[0].from, "v1") == 0) {
-				btrfs_clear_opt(info->mount_opt,
-						FREE_SPACE_TREE);
-				btrfs_set_and_info(info, SPACE_CACHE,
-					   "enabling disk space caching");
-			} else if (strcmp(args[0].from, "v2") == 0) {
-				btrfs_clear_opt(info->mount_opt,
-						SPACE_CACHE);
-				btrfs_set_and_info(info, FREE_SPACE_TREE,
-						   "enabling free space tree");
-			} else {
-				btrfs_err(info, "unrecognized space_cache value %s",
-					  args[0].from);
-				ret = -EINVAL;
-				goto out;
-			}
-			break;
-		case Opt_rescan_uuid_tree:
-			btrfs_set_opt(info->mount_opt, RESCAN_UUID_TREE);
-			break;
-		case Opt_no_space_cache:
-			/*
-			 * We cannot operate without the free space tree with
-			 * extent tree v2, ignore this option.
-			 */
-			if (btrfs_fs_incompat(info, EXTENT_TREE_V2))
-				break;
-			if (btrfs_test_opt(info, SPACE_CACHE)) {
-				btrfs_clear_and_info(info, SPACE_CACHE,
-					     "disabling disk space caching");
-			}
-			if (btrfs_test_opt(info, FREE_SPACE_TREE)) {
-				btrfs_clear_and_info(info, FREE_SPACE_TREE,
-					     "disabling free space tree");
-			}
+		btrfs_set_opt(ctx->mount_opt, NOLOGREPLAY);
+		break;
+	case Opt_flushoncommit:
+		if (result.negated)
+			btrfs_clear_opt(ctx->mount_opt, FLUSHONCOMMIT);
+		else
+			btrfs_set_opt(ctx->mount_opt, FLUSHONCOMMIT);
+		break;
+	case Opt_ratio:
+		ctx->metadata_ratio = result.uint_32;
+		break;
+	case Opt_discard:
+		if (result.negated) {
+			btrfs_clear_opt(ctx->mount_opt, DISCARD_SYNC);
+			btrfs_clear_opt(ctx->mount_opt, DISCARD_ASYNC);
+			btrfs_set_opt(ctx->mount_opt, NODISCARD);
+		} else {
+			btrfs_set_opt(ctx->mount_opt, DISCARD_SYNC);
+			btrfs_clear_opt(ctx->mount_opt, DISCARD_ASYNC);
+		}
+		break;
+	case Opt_discard_mode:
+		switch (result.uint_32) {
+		case Opt_discard_sync:
+			btrfs_clear_opt(ctx->mount_opt, DISCARD_ASYNC);
+			btrfs_set_opt(ctx->mount_opt, DISCARD_SYNC);
 			break;
-		case Opt_inode_cache:
-		case Opt_noinode_cache:
-			btrfs_warn(info,
-	"the 'inode_cache' option is deprecated and has no effect since 5.11");
+		case Opt_discard_async:
+			btrfs_clear_opt(ctx->mount_opt, DISCARD_SYNC);
+			btrfs_set_opt(ctx->mount_opt, DISCARD_ASYNC);
 			break;
-		case Opt_clear_cache:
-			/*
-			 * We cannot clear the free space tree with extent tree
-			 * v2, ignore this option.
-			 */
-			if (btrfs_fs_incompat(info, EXTENT_TREE_V2))
-				break;
-			btrfs_set_and_info(info, CLEAR_CACHE,
-					   "force clearing of disk cache");
-			break;
-		case Opt_user_subvol_rm_allowed:
-			btrfs_set_opt(info->mount_opt, USER_SUBVOL_RM_ALLOWED);
+		default:
+			btrfs_err(NULL, "unrecognized discard mode value %s",
+				  param->key);
+			return -EINVAL;
+		}
+		btrfs_clear_opt(ctx->mount_opt, NODISCARD);
+		break;
+	case Opt_space_cache:
+		if (result.negated) {
+			btrfs_set_opt(ctx->mount_opt, NOSPACECACHE);
+			btrfs_clear_opt(ctx->mount_opt, SPACE_CACHE);
+			btrfs_clear_opt(ctx->mount_opt, FREE_SPACE_TREE);
+		} else {
+			btrfs_clear_opt(ctx->mount_opt, FREE_SPACE_TREE);
+			btrfs_set_opt(ctx->mount_opt, SPACE_CACHE);
+		}
+		break;
+	case Opt_space_cache_version:
+		switch (result.uint_32) {
+		case Opt_space_cache_v1:
+			btrfs_set_opt(ctx->mount_opt, SPACE_CACHE);
+			btrfs_clear_opt(ctx->mount_opt, FREE_SPACE_TREE);
 			break;
-		case Opt_enospc_debug:
-			btrfs_set_opt(info->mount_opt, ENOSPC_DEBUG);
+		case Opt_space_cache_v2:
+			btrfs_clear_opt(ctx->mount_opt, SPACE_CACHE);
+			btrfs_set_opt(ctx->mount_opt, FREE_SPACE_TREE);
 			break;
-		case Opt_noenospc_debug:
-			btrfs_clear_opt(info->mount_opt, ENOSPC_DEBUG);
+		default:
+			btrfs_err(NULL, "unrecognized space_cache value %s",
+				  param->key);
+			return -EINVAL;
+		}
+		break;
+	case Opt_rescan_uuid_tree:
+		btrfs_set_opt(ctx->mount_opt, RESCAN_UUID_TREE);
+		break;
+	case Opt_clear_cache:
+		btrfs_set_opt(ctx->mount_opt, CLEAR_CACHE);
+		break;
+	case Opt_user_subvol_rm_allowed:
+		btrfs_set_opt(ctx->mount_opt, USER_SUBVOL_RM_ALLOWED);
+		break;
+	case Opt_enospc_debug:
+		if (result.negated)
+			btrfs_clear_opt(ctx->mount_opt, ENOSPC_DEBUG);
+		else
+			btrfs_set_opt(ctx->mount_opt, ENOSPC_DEBUG);
+		break;
+	case Opt_defrag:
+		if (result.negated)
+			btrfs_clear_opt(ctx->mount_opt, AUTO_DEFRAG);
+		else
+			btrfs_set_opt(ctx->mount_opt, AUTO_DEFRAG);
+		break;
+	case Opt_usebackuproot:
+		btrfs_warn(NULL,
+			   "'usebackuproot' is deprecated, use 'rescue=usebackuproot' instead");
+		btrfs_set_opt(ctx->mount_opt, USEBACKUPROOT);
+
+		/* If we're loading the backup roots we can't trust the space cache. */
+		btrfs_set_opt(ctx->mount_opt, CLEAR_CACHE);
+		break;
+	case Opt_skip_balance:
+		btrfs_set_opt(ctx->mount_opt, SKIP_BALANCE);
+		break;
+	case Opt_fatal_errors:
+		switch (result.uint_32) {
+		case Opt_fatal_errors_panic:
+			btrfs_set_opt(ctx->mount_opt, PANIC_ON_FATAL_ERROR);
 			break;
-		case Opt_defrag:
-			btrfs_set_and_info(info, AUTO_DEFRAG,
-					   "enabling auto defrag");
+		case Opt_fatal_errors_bug:
+			btrfs_clear_opt(ctx->mount_opt, PANIC_ON_FATAL_ERROR);
 			break;
-		case Opt_nodefrag:
-			btrfs_clear_and_info(info, AUTO_DEFRAG,
-					     "disabling auto defrag");
+		default:
+			btrfs_err(NULL, "unrecognized fatal_errors value %s",
+				  param->key);
+			return -EINVAL;
+		}
+		break;
+	case Opt_commit_interval:
+		ctx->commit_interval = result.uint_32;
+		if (ctx->commit_interval == 0)
+			ctx->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
+		break;
+	case Opt_rescue:
+		switch (result.uint_32) {
+		case Opt_rescue_usebackuproot:
+			btrfs_set_opt(ctx->mount_opt, USEBACKUPROOT);
 			break;
-		case Opt_recovery:
-		case Opt_usebackuproot:
-			btrfs_warn(info,
-			"'%s' is deprecated, use 'rescue=usebackuproot' instead",
-				   token == Opt_recovery ? "recovery" :
-				   "usebackuproot");
-			btrfs_info(info,
-				   "trying to use backup root at mount time");
-			btrfs_set_opt(info->mount_opt, USEBACKUPROOT);
+		case Opt_rescue_nologreplay:
+			btrfs_set_opt(ctx->mount_opt, NOLOGREPLAY);
 			break;
-		case Opt_skip_balance:
-			btrfs_set_opt(info->mount_opt, SKIP_BALANCE);
+		case Opt_rescue_ignorebadroots:
+			btrfs_set_opt(ctx->mount_opt, IGNOREBADROOTS);
 			break;
-		case Opt_fatal_errors:
-			if (strcmp(args[0].from, "panic") == 0) {
-				btrfs_set_opt(info->mount_opt,
-					      PANIC_ON_FATAL_ERROR);
-			} else if (strcmp(args[0].from, "bug") == 0) {
-				btrfs_clear_opt(info->mount_opt,
-					      PANIC_ON_FATAL_ERROR);
-			} else {
-				btrfs_err(info, "unrecognized fatal_errors value %s",
-					  args[0].from);
-				ret = -EINVAL;
-				goto out;
-			}
+		case Opt_rescue_ignoredatacsums:
+			btrfs_set_opt(ctx->mount_opt, IGNOREDATACSUMS);
 			break;
-		case Opt_commit_interval:
-			intarg = 0;
-			ret = match_int(&args[0], &intarg);
-			if (ret) {
-				btrfs_err(info, "unrecognized commit_interval value %s",
-					  args[0].from);
-				ret = -EINVAL;
-				goto out;
-			}
-			if (intarg == 0) {
-				btrfs_info(info,
-					   "using default commit interval %us",
-					   BTRFS_DEFAULT_COMMIT_INTERVAL);
-				intarg = BTRFS_DEFAULT_COMMIT_INTERVAL;
-			} else if (intarg > 300) {
-				btrfs_warn(info, "excessive commit interval %d",
-					   intarg);
-			}
-			info->commit_interval = intarg;
-			break;
-		case Opt_rescue:
-			ret = parse_rescue_options(info, args[0].from);
-			if (ret < 0) {
-				btrfs_err(info, "unrecognized rescue value %s",
-					  args[0].from);
-				goto out;
-			}
+		case Opt_rescue_parameter_all:
+			btrfs_set_opt(ctx->mount_opt, IGNOREDATACSUMS);
+			btrfs_set_opt(ctx->mount_opt, IGNOREBADROOTS);
+			btrfs_set_opt(ctx->mount_opt, NOLOGREPLAY);
 			break;
+		default:
+			btrfs_info(NULL, "unrecognized rescue option '%s'",
+				   param->key);
+			return -EINVAL;
+		}
+		break;
 #ifdef CONFIG_BTRFS_DEBUG
-		case Opt_fragment_all:
-			btrfs_info(info, "fragmenting all space");
-			btrfs_set_opt(info->mount_opt, FRAGMENT_DATA);
-			btrfs_set_opt(info->mount_opt, FRAGMENT_METADATA);
+	case Opt_fragment:
+		switch (result.uint_32) {
+		case Opt_fragment_parameter_all:
+			btrfs_set_opt(ctx->mount_opt, FRAGMENT_DATA);
+			btrfs_set_opt(ctx->mount_opt, FRAGMENT_METADATA);
 			break;
-		case Opt_fragment_metadata:
-			btrfs_info(info, "fragmenting metadata");
-			btrfs_set_opt(info->mount_opt,
-				      FRAGMENT_METADATA);
+		case Opt_fragment_parameter_metadata:
+			btrfs_set_opt(ctx->mount_opt, FRAGMENT_METADATA);
 			break;
-		case Opt_fragment_data:
-			btrfs_info(info, "fragmenting data");
-			btrfs_set_opt(info->mount_opt, FRAGMENT_DATA);
+		case Opt_fragment_parameter_data:
+			btrfs_set_opt(ctx->mount_opt, FRAGMENT_DATA);
 			break;
+		default:
+			btrfs_info(NULL, "unrecognized fragment option '%s'",
+				   param->key);
+			return -EINVAL;
+		}
+		break;
 #endif
 #ifdef CONFIG_BTRFS_FS_REF_VERIFY
-		case Opt_ref_verify:
-			btrfs_info(info, "doing ref verification");
-			btrfs_set_opt(info->mount_opt, REF_VERIFY);
-			break;
+	case Opt_ref_verify:
+		btrfs_set_opt(ctx->mount_opt, REF_VERIFY);
+		break;
 #endif
-		case Opt_err:
-			btrfs_err(info, "unrecognized mount option '%s'", p);
-			ret = -EINVAL;
-			goto out;
-		default:
-			break;
-		}
+	default:
+		btrfs_err(NULL, "unrecognized mount option '%s'", param->key);
+		return -EINVAL;
 	}
-check:
-	/* We're read-only, don't have to check. */
-	if (new_flags & SB_RDONLY)
-		goto out;
 
-	if (check_ro_option(info, BTRFS_MOUNT_NOLOGREPLAY, "nologreplay") ||
-	    check_ro_option(info, BTRFS_MOUNT_IGNOREBADROOTS, "ignorebadroots") ||
-	    check_ro_option(info, BTRFS_MOUNT_IGNOREDATACSUMS, "ignoredatacsums"))
-		ret = -EINVAL;
-out:
-	if (btrfs_fs_compat_ro(info, FREE_SPACE_TREE) &&
-	    !btrfs_test_opt(info, FREE_SPACE_TREE) &&
-	    !btrfs_test_opt(info, CLEAR_CACHE)) {
-		btrfs_err(info, "cannot disable free space tree");
-		ret = -EINVAL;
-	}
-	if (btrfs_fs_compat_ro(info, BLOCK_GROUP_TREE) &&
-	     !btrfs_test_opt(info, FREE_SPACE_TREE)) {
-		btrfs_err(info, "cannot disable free space tree with block-group-tree feature");
-		ret = -EINVAL;
-	}
-	if (!ret)
-		ret = btrfs_check_mountopts_zoned(info);
-	if (!ret && !remounting) {
-		if (btrfs_test_opt(info, SPACE_CACHE))
-			btrfs_info(info, "disk space caching is enabled");
-		if (btrfs_test_opt(info, FREE_SPACE_TREE))
-			btrfs_info(info, "using free space tree");
-	}
-	return ret;
+	return 0;
 }
 
 /*
- * Parse mount options that are required early in the mount process.
- *
- * All other options will be parsed on much later in the mount process and
- * only when we need to allocate a new super block.
+ * Some options only have meaning at mount time and shouldn't persist across
+ * remounts, or be displayed. Clear these at the end of mount and remount code
+ * paths.
  */
-static int btrfs_parse_device_options(const char *options, blk_mode_t flags)
+static void btrfs_clear_oneshot_options(struct btrfs_fs_info *fs_info)
 {
-	substring_t args[MAX_OPT_ARGS];
-	char *device_name, *opts, *orig, *p;
-	struct btrfs_device *device = NULL;
-	int error = 0;
+	btrfs_clear_opt(fs_info->mount_opt, USEBACKUPROOT);
+	btrfs_clear_opt(fs_info->mount_opt, CLEAR_CACHE);
+	btrfs_clear_opt(fs_info->mount_opt, NOSPACECACHE);
+}
 
-	lockdep_assert_held(&uuid_mutex);
+static bool check_ro_option(struct btrfs_fs_info *fs_info,
+			    unsigned long mount_opt, unsigned long opt,
+			    const char *opt_name)
+{
+	if (mount_opt & opt) {
+		btrfs_err(fs_info, "%s must be used with ro mount option",
+			  opt_name);
+		return true;
+	}
+	return false;
+}
 
-	if (!options)
-		return 0;
+bool btrfs_check_options(struct btrfs_fs_info *info, unsigned long *mount_opt,
+			 unsigned long flags)
+{
+	bool ret = true;
 
-	/*
-	 * strsep changes the string, duplicate it because btrfs_parse_options
-	 * gets called later
-	 */
-	opts = kstrdup(options, GFP_KERNEL);
-	if (!opts)
-		return -ENOMEM;
-	orig = opts;
+	if (!(flags & SB_RDONLY) &&
+	    (check_ro_option(info, *mount_opt, BTRFS_MOUNT_NOLOGREPLAY, "nologreplay") ||
+	     check_ro_option(info, *mount_opt, BTRFS_MOUNT_IGNOREBADROOTS, "ignorebadroots") ||
+	     check_ro_option(info, *mount_opt, BTRFS_MOUNT_IGNOREDATACSUMS, "ignoredatacsums")))
+		ret = false;
 
-	while ((p = strsep(&opts, ",")) != NULL) {
-		int token;
+	if (btrfs_fs_compat_ro(info, FREE_SPACE_TREE) &&
+	    !btrfs_raw_test_opt(*mount_opt, FREE_SPACE_TREE) &&
+	    !btrfs_raw_test_opt(*mount_opt, CLEAR_CACHE)) {
+		btrfs_err(info, "cannot disable free-space-tree");
+		ret = false;
+	}
+	if (btrfs_fs_compat_ro(info, BLOCK_GROUP_TREE) &&
+	     !btrfs_raw_test_opt(*mount_opt, FREE_SPACE_TREE)) {
+		btrfs_err(info, "cannot disable free-space-tree with block-group-tree feature");
+		ret = false;
+	}
 
-		if (!*p)
-			continue;
+	if (btrfs_check_mountopts_zoned(info, mount_opt))
+		ret = false;
 
-		token = match_token(p, tokens, args);
-		if (token == Opt_device) {
-			device_name = match_strdup(&args[0]);
-			if (!device_name) {
-				error = -ENOMEM;
-				goto out;
-			}
-			device = btrfs_scan_one_device(device_name, flags, false);
-			kfree(device_name);
-			if (IS_ERR(device)) {
-				error = PTR_ERR(device);
-				goto out;
-			}
-		}
+	if (!test_bit(BTRFS_FS_STATE_REMOUNTING, &info->fs_state)) {
+		if (btrfs_raw_test_opt(*mount_opt, SPACE_CACHE))
+			btrfs_info(info, "disk space caching is enabled");
+		if (btrfs_raw_test_opt(*mount_opt, FREE_SPACE_TREE))
+			btrfs_info(info, "using free-space-tree");
 	}
 
-out:
-	kfree(orig);
-	return error;
+	return ret;
 }
 
 /*
- * Parse mount options that are related to subvolume id
+ * This is subtle, we only call this during open_ctree().  We need to pre-load
+ * the mount options with the on-disk settings.  Before the new mount API took
+ * effect we would do this on mount and remount.  With the new mount API we'll
+ * only do this on the initial mount.
  *
- * The value is later passed to mount_subvol()
+ * This isn't a change in behavior, because we're using the current state of the
+ * file system to set the current mount options.  If you mounted with special
+ * options to disable these features and then remounted we wouldn't revert the
+ * settings, because mounting without these features cleared the on-disk
+ * settings, so this being called on re-mount is not needed.
  */
-static int btrfs_parse_subvol_options(const char *options, char **subvol_name,
-		u64 *subvol_objectid)
+void btrfs_set_free_space_cache_settings(struct btrfs_fs_info *fs_info)
 {
-	substring_t args[MAX_OPT_ARGS];
-	char *opts, *orig, *p;
-	int error = 0;
-	u64 subvolid;
-
-	if (!options)
-		return 0;
+	if (fs_info->sectorsize < PAGE_SIZE) {
+		btrfs_clear_opt(fs_info->mount_opt, SPACE_CACHE);
+		if (!btrfs_test_opt(fs_info, FREE_SPACE_TREE)) {
+			btrfs_info(fs_info,
+				   "forcing free space tree for sector size %u with page size %lu",
+				   fs_info->sectorsize, PAGE_SIZE);
+			btrfs_set_opt(fs_info->mount_opt, FREE_SPACE_TREE);
+		}
+	}
 
 	/*
-	 * strsep changes the string, duplicate it because
-	 * btrfs_parse_device_options gets called later
+	 * At this point our mount options are populated, so we only mess with
+	 * these settings if we don't have any settings already.
 	 */
-	opts = kstrdup(options, GFP_KERNEL);
-	if (!opts)
-		return -ENOMEM;
-	orig = opts;
+	if (btrfs_test_opt(fs_info, FREE_SPACE_TREE))
+		return;
 
-	while ((p = strsep(&opts, ",")) != NULL) {
-		int token;
-		if (!*p)
-			continue;
+	if (btrfs_is_zoned(fs_info) &&
+	    btrfs_free_space_cache_v1_active(fs_info)) {
+		btrfs_info(fs_info, "zoned: clearing existing space cache");
+		btrfs_set_super_cache_generation(fs_info->super_copy, 0);
+		return;
+	}
 
-		token = match_token(p, tokens, args);
-		switch (token) {
-		case Opt_subvol:
-			kfree(*subvol_name);
-			*subvol_name = match_strdup(&args[0]);
-			if (!*subvol_name) {
-				error = -ENOMEM;
-				goto out;
-			}
-			break;
-		case Opt_subvolid:
-			error = match_u64(&args[0], &subvolid);
-			if (error)
-				goto out;
+	if (btrfs_test_opt(fs_info, SPACE_CACHE))
+		return;
 
-			/* we want the original fs_tree */
-			if (subvolid == 0)
-				subvolid = BTRFS_FS_TREE_OBJECTID;
+	if (btrfs_test_opt(fs_info, NOSPACECACHE))
+		return;
 
-			*subvol_objectid = subvolid;
-			break;
-		default:
-			break;
-		}
-	}
+	/*
+	 * At this point we don't have explicit options set by the user, set
+	 * them ourselves based on the state of the file system.
+	 */
+	if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
+		btrfs_set_opt(fs_info->mount_opt, FREE_SPACE_TREE);
+	else if (btrfs_free_space_cache_v1_active(fs_info))
+		btrfs_set_opt(fs_info->mount_opt, SPACE_CACHE);
+}
 
-out:
-	kfree(orig);
-	return error;
+static void set_device_specific_options(struct btrfs_fs_info *fs_info)
+{
+	if (!btrfs_test_opt(fs_info, NOSSD) &&
+	    !fs_info->fs_devices->rotating)
+		btrfs_set_opt(fs_info->mount_opt, SSD);
+
+	/*
+	 * For devices supporting discard turn on discard=async automatically,
+	 * unless it's already set or disabled. This could be turned off by
+	 * nodiscard for the same mount.
+	 *
+	 * The zoned mode piggy backs on the discard functionality for
+	 * resetting a zone. There is no reason to delay the zone reset as it is
+	 * fast enough. So, do not enable async discard for zoned mode.
+	 */
+	if (!(btrfs_test_opt(fs_info, DISCARD_SYNC) ||
+	      btrfs_test_opt(fs_info, DISCARD_ASYNC) ||
+	      btrfs_test_opt(fs_info, NODISCARD)) &&
+	    fs_info->fs_devices->discardable &&
+	    !btrfs_is_zoned(fs_info))
+		btrfs_set_opt(fs_info->mount_opt, DISCARD_ASYNC);
 }
 
 char *btrfs_get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info,
@@ -1102,10 +929,6 @@ static int btrfs_fill_super(struct super_block *sb,
 #endif
 	sb->s_xattr = btrfs_xattr_handlers;
 	sb->s_time_gran = 1;
-#ifdef CONFIG_BTRFS_FS_POSIX_ACL
-	sb->s_flags |= SB_POSIXACL;
-#endif
-	sb->s_flags |= SB_I_VERSION;
 	sb->s_iflags |= SB_I_CGROUPWB;
 
 	err = super_setup_bdi(sb);
@@ -1288,22 +1111,6 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 	return 0;
 }
 
-static int btrfs_test_super(struct super_block *s, void *data)
-{
-	struct btrfs_fs_info *p = data;
-	struct btrfs_fs_info *fs_info = btrfs_sb(s);
-
-	return fs_info->fs_devices == p->fs_devices;
-}
-
-static int btrfs_set_super(struct super_block *s, void *data)
-{
-	int err = set_anon_super(s, data);
-	if (!err)
-		s->s_fs_info = data;
-	return err;
-}
-
 /*
  * subvolumes are identified by ino 256
  */
@@ -1379,200 +1186,6 @@ out:
 	return root;
 }
 
-/*
- * Find a superblock for the given device / mount point.
- *
- * Note: This is based on mount_bdev from fs/super.c with a few additions
- *       for multiple device setup.  Make sure to keep it in sync.
- */
-static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
-		int flags, const char *device_name, void *data)
-{
-	struct block_device *bdev = NULL;
-	struct super_block *s;
-	struct btrfs_device *device = NULL;
-	struct btrfs_fs_devices *fs_devices = NULL;
-	struct btrfs_fs_info *fs_info = NULL;
-	void *new_sec_opts = NULL;
-	blk_mode_t mode = sb_open_mode(flags);
-	int error = 0;
-
-	if (data) {
-		error = security_sb_eat_lsm_opts(data, &new_sec_opts);
-		if (error)
-			return ERR_PTR(error);
-	}
-
-	/*
-	 * Setup a dummy root and fs_info for test/set super.  This is because
-	 * we don't actually fill this stuff out until open_ctree, but we need
-	 * then open_ctree will properly initialize the file system specific
-	 * settings later.  btrfs_init_fs_info initializes the static elements
-	 * of the fs_info (locks and such) to make cleanup easier if we find a
-	 * superblock with our given fs_devices later on at sget() time.
-	 */
-	fs_info = kvzalloc(sizeof(struct btrfs_fs_info), GFP_KERNEL);
-	if (!fs_info) {
-		error = -ENOMEM;
-		goto error_sec_opts;
-	}
-	btrfs_init_fs_info(fs_info);
-
-	fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL);
-	fs_info->super_for_commit = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL);
-	if (!fs_info->super_copy || !fs_info->super_for_commit) {
-		error = -ENOMEM;
-		goto error_fs_info;
-	}
-
-	mutex_lock(&uuid_mutex);
-	error = btrfs_parse_device_options(data, mode);
-	if (error) {
-		mutex_unlock(&uuid_mutex);
-		goto error_fs_info;
-	}
-
-	/*
-	 * With 'true' passed to btrfs_scan_one_device() (mount time) we expect
-	 * either a valid device or an error.
-	 */
-	device = btrfs_scan_one_device(device_name, mode, true);
-	ASSERT(device != NULL);
-	if (IS_ERR(device)) {
-		mutex_unlock(&uuid_mutex);
-		error = PTR_ERR(device);
-		goto error_fs_info;
-	}
-
-	fs_devices = device->fs_devices;
-	fs_info->fs_devices = fs_devices;
-
-	error = btrfs_open_devices(fs_devices, mode, fs_type);
-	mutex_unlock(&uuid_mutex);
-	if (error)
-		goto error_fs_info;
-
-	if (!(flags & SB_RDONLY) && fs_devices->rw_devices == 0) {
-		error = -EACCES;
-		goto error_close_devices;
-	}
-
-	bdev = fs_devices->latest_dev->bdev;
-	s = sget(fs_type, btrfs_test_super, btrfs_set_super, flags | SB_NOSEC,
-		 fs_info);
-	if (IS_ERR(s)) {
-		error = PTR_ERR(s);
-		goto error_close_devices;
-	}
-
-	if (s->s_root) {
-		btrfs_close_devices(fs_devices);
-		btrfs_free_fs_info(fs_info);
-		if ((flags ^ s->s_flags) & SB_RDONLY)
-			error = -EBUSY;
-	} else {
-		snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
-		shrinker_debugfs_rename(s->s_shrink, "sb-%s:%s", fs_type->name,
-					s->s_id);
-		btrfs_sb(s)->bdev_holder = fs_type;
-		error = btrfs_fill_super(s, fs_devices, data);
-	}
-	if (!error)
-		error = security_sb_set_mnt_opts(s, new_sec_opts, 0, NULL);
-	security_free_mnt_opts(&new_sec_opts);
-	if (error) {
-		deactivate_locked_super(s);
-		return ERR_PTR(error);
-	}
-
-	return dget(s->s_root);
-
-error_close_devices:
-	btrfs_close_devices(fs_devices);
-error_fs_info:
-	btrfs_free_fs_info(fs_info);
-error_sec_opts:
-	security_free_mnt_opts(&new_sec_opts);
-	return ERR_PTR(error);
-}
-
-/*
- * Mount function which is called by VFS layer.
- *
- * In order to allow mounting a subvolume directly, btrfs uses mount_subtree()
- * which needs vfsmount* of device's root (/).  This means device's root has to
- * be mounted internally in any case.
- *
- * Operation flow:
- *   1. Parse subvol id related options for later use in mount_subvol().
- *
- *   2. Mount device's root (/) by calling vfs_kern_mount().
- *
- *      NOTE: vfs_kern_mount() is used by VFS to call btrfs_mount() in the
- *      first place. In order to avoid calling btrfs_mount() again, we use
- *      different file_system_type which is not registered to VFS by
- *      register_filesystem() (btrfs_root_fs_type). As a result,
- *      btrfs_mount_root() is called. The return value will be used by
- *      mount_subtree() in mount_subvol().
- *
- *   3. Call mount_subvol() to get the dentry of subvolume. Since there is
- *      "btrfs subvolume set-default", mount_subvol() is called always.
- */
-static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
-		const char *device_name, void *data)
-{
-	struct vfsmount *mnt_root;
-	struct dentry *root;
-	char *subvol_name = NULL;
-	u64 subvol_objectid = 0;
-	int error = 0;
-
-	error = btrfs_parse_subvol_options(data, &subvol_name,
-					&subvol_objectid);
-	if (error) {
-		kfree(subvol_name);
-		return ERR_PTR(error);
-	}
-
-	/* mount device's root (/) */
-	mnt_root = vfs_kern_mount(&btrfs_root_fs_type, flags, device_name, data);
-	if (PTR_ERR_OR_ZERO(mnt_root) == -EBUSY) {
-		if (flags & SB_RDONLY) {
-			mnt_root = vfs_kern_mount(&btrfs_root_fs_type,
-				flags & ~SB_RDONLY, device_name, data);
-		} else {
-			mnt_root = vfs_kern_mount(&btrfs_root_fs_type,
-				flags | SB_RDONLY, device_name, data);
-			if (IS_ERR(mnt_root)) {
-				root = ERR_CAST(mnt_root);
-				kfree(subvol_name);
-				goto out;
-			}
-
-			down_write(&mnt_root->mnt_sb->s_umount);
-			error = btrfs_remount(mnt_root->mnt_sb, &flags, NULL);
-			up_write(&mnt_root->mnt_sb->s_umount);
-			if (error < 0) {
-				root = ERR_PTR(error);
-				mntput(mnt_root);
-				kfree(subvol_name);
-				goto out;
-			}
-		}
-	}
-	if (IS_ERR(mnt_root)) {
-		root = ERR_CAST(mnt_root);
-		kfree(subvol_name);
-		goto out;
-	}
-
-	/* mount_subvol() will free subvol_name and mnt_root */
-	root = mount_subvol(subvol_name, subvol_objectid, mnt_root);
-
-out:
-	return root;
-}
-
 static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info,
 				     u32 new_pool_size, u32 old_pool_size)
 {
@@ -1635,202 +1248,274 @@ static inline void btrfs_remount_cleanup(struct btrfs_fs_info *fs_info,
 		btrfs_set_free_space_cache_v1_active(fs_info, cache_opt);
 }
 
-static int btrfs_remount(struct super_block *sb, int *flags, char *data)
+static int btrfs_remount_rw(struct btrfs_fs_info *fs_info)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
-	unsigned old_flags = sb->s_flags;
-	unsigned long old_opts = fs_info->mount_opt;
-	unsigned long old_compress_type = fs_info->compress_type;
-	u64 old_max_inline = fs_info->max_inline;
-	u32 old_thread_pool_size = fs_info->thread_pool_size;
-	u32 old_metadata_ratio = fs_info->metadata_ratio;
 	int ret;
 
-	sync_filesystem(sb);
-	set_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
+	if (BTRFS_FS_ERROR(fs_info)) {
+		btrfs_err(fs_info,
+			  "remounting read-write after error is not allowed");
+		return -EINVAL;
+	}
 
-	if (data) {
-		void *new_sec_opts = NULL;
+	if (fs_info->fs_devices->rw_devices == 0)
+		return -EACCES;
 
-		ret = security_sb_eat_lsm_opts(data, &new_sec_opts);
-		if (!ret)
-			ret = security_sb_remount(sb, new_sec_opts);
-		security_free_mnt_opts(&new_sec_opts);
-		if (ret)
-			goto restore;
+	if (!btrfs_check_rw_degradable(fs_info, NULL)) {
+		btrfs_warn(fs_info,
+			   "too many missing devices, writable remount is not allowed");
+		return -EACCES;
 	}
 
-	ret = btrfs_parse_options(fs_info, data, *flags);
+	if (btrfs_super_log_root(fs_info->super_copy) != 0) {
+		btrfs_warn(fs_info,
+			   "mount required to replay tree-log, cannot remount read-write");
+		return -EINVAL;
+	}
+
+	/*
+	 * NOTE: when remounting with a change that does writes, don't put it
+	 * anywhere above this point, as we are not sure to be safe to write
+	 * until we pass the above checks.
+	 */
+	ret = btrfs_start_pre_rw_mount(fs_info);
 	if (ret)
-		goto restore;
+		return ret;
 
-	ret = btrfs_check_features(fs_info, !(*flags & SB_RDONLY));
-	if (ret < 0)
-		goto restore;
+	btrfs_clear_sb_rdonly(fs_info->sb);
 
-	btrfs_remount_begin(fs_info, old_opts, *flags);
-	btrfs_resize_thread_pool(fs_info,
-		fs_info->thread_pool_size, old_thread_pool_size);
+	set_bit(BTRFS_FS_OPEN, &fs_info->flags);
 
-	if ((bool)btrfs_test_opt(fs_info, FREE_SPACE_TREE) !=
-	    (bool)btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) &&
-	    (!sb_rdonly(sb) || (*flags & SB_RDONLY))) {
-		btrfs_warn(fs_info,
-		"remount supports changing free space tree only from ro to rw");
-		/* Make sure free space cache options match the state on disk */
-		if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
-			btrfs_set_opt(fs_info->mount_opt, FREE_SPACE_TREE);
-			btrfs_clear_opt(fs_info->mount_opt, SPACE_CACHE);
-		}
-		if (btrfs_free_space_cache_v1_active(fs_info)) {
-			btrfs_clear_opt(fs_info->mount_opt, FREE_SPACE_TREE);
-			btrfs_set_opt(fs_info->mount_opt, SPACE_CACHE);
-		}
-	}
+	/*
+	 * If we've gone from readonly -> read-write, we need to get our
+	 * sync/async discard lists in the right state.
+	 */
+	btrfs_discard_resume(fs_info);
 
-	if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb))
-		goto out;
+	return 0;
+}
 
-	if (*flags & SB_RDONLY) {
-		/*
-		 * this also happens on 'umount -rf' or on shutdown, when
-		 * the filesystem is busy.
-		 */
-		cancel_work_sync(&fs_info->async_reclaim_work);
-		cancel_work_sync(&fs_info->async_data_reclaim_work);
+static int btrfs_remount_ro(struct btrfs_fs_info *fs_info)
+{
+	/*
+	 * This also happens on 'umount -rf' or on shutdown, when the
+	 * filesystem is busy.
+	 */
+	cancel_work_sync(&fs_info->async_reclaim_work);
+	cancel_work_sync(&fs_info->async_data_reclaim_work);
 
-		btrfs_discard_cleanup(fs_info);
+	btrfs_discard_cleanup(fs_info);
 
-		/* wait for the uuid_scan task to finish */
-		down(&fs_info->uuid_tree_rescan_sem);
-		/* avoid complains from lockdep et al. */
-		up(&fs_info->uuid_tree_rescan_sem);
+	/* Wait for the uuid_scan task to finish */
+	down(&fs_info->uuid_tree_rescan_sem);
+	/* Avoid complains from lockdep et al. */
+	up(&fs_info->uuid_tree_rescan_sem);
 
-		btrfs_set_sb_rdonly(sb);
+	btrfs_set_sb_rdonly(fs_info->sb);
 
-		/*
-		 * Setting SB_RDONLY will put the cleaner thread to
-		 * sleep at the next loop if it's already active.
-		 * If it's already asleep, we'll leave unused block
-		 * groups on disk until we're mounted read-write again
-		 * unless we clean them up here.
-		 */
-		btrfs_delete_unused_bgs(fs_info);
+	/*
+	 * Setting SB_RDONLY will put the cleaner thread to sleep at the next
+	 * loop if it's already active.  If it's already asleep, we'll leave
+	 * unused block groups on disk until we're mounted read-write again
+	 * unless we clean them up here.
+	 */
+	btrfs_delete_unused_bgs(fs_info);
 
-		/*
-		 * The cleaner task could be already running before we set the
-		 * flag BTRFS_FS_STATE_RO (and SB_RDONLY in the superblock).
-		 * We must make sure that after we finish the remount, i.e. after
-		 * we call btrfs_commit_super(), the cleaner can no longer start
-		 * a transaction - either because it was dropping a dead root,
-		 * running delayed iputs or deleting an unused block group (the
-		 * cleaner picked a block group from the list of unused block
-		 * groups before we were able to in the previous call to
-		 * btrfs_delete_unused_bgs()).
-		 */
-		wait_on_bit(&fs_info->flags, BTRFS_FS_CLEANER_RUNNING,
-			    TASK_UNINTERRUPTIBLE);
+	/*
+	 * The cleaner task could be already running before we set the flag
+	 * BTRFS_FS_STATE_RO (and SB_RDONLY in the superblock).  We must make
+	 * sure that after we finish the remount, i.e. after we call
+	 * btrfs_commit_super(), the cleaner can no longer start a transaction
+	 * - either because it was dropping a dead root, running delayed iputs
+	 *   or deleting an unused block group (the cleaner picked a block
+	 *   group from the list of unused block groups before we were able to
+	 *   in the previous call to btrfs_delete_unused_bgs()).
+	 */
+	wait_on_bit(&fs_info->flags, BTRFS_FS_CLEANER_RUNNING, TASK_UNINTERRUPTIBLE);
 
-		/*
-		 * We've set the superblock to RO mode, so we might have made
-		 * the cleaner task sleep without running all pending delayed
-		 * iputs. Go through all the delayed iputs here, so that if an
-		 * unmount happens without remounting RW we don't end up at
-		 * finishing close_ctree() with a non-empty list of delayed
-		 * iputs.
-		 */
-		btrfs_run_delayed_iputs(fs_info);
+	/*
+	 * We've set the superblock to RO mode, so we might have made the
+	 * cleaner task sleep without running all pending delayed iputs. Go
+	 * through all the delayed iputs here, so that if an unmount happens
+	 * without remounting RW we don't end up at finishing close_ctree()
+	 * with a non-empty list of delayed iputs.
+	 */
+	btrfs_run_delayed_iputs(fs_info);
 
-		btrfs_dev_replace_suspend_for_unmount(fs_info);
-		btrfs_scrub_cancel(fs_info);
-		btrfs_pause_balance(fs_info);
+	btrfs_dev_replace_suspend_for_unmount(fs_info);
+	btrfs_scrub_cancel(fs_info);
+	btrfs_pause_balance(fs_info);
 
-		/*
-		 * Pause the qgroup rescan worker if it is running. We don't want
-		 * it to be still running after we are in RO mode, as after that,
-		 * by the time we unmount, it might have left a transaction open,
-		 * so we would leak the transaction and/or crash.
-		 */
-		btrfs_qgroup_wait_for_completion(fs_info, false);
+	/*
+	 * Pause the qgroup rescan worker if it is running. We don't want it to
+	 * be still running after we are in RO mode, as after that, by the time
+	 * we unmount, it might have left a transaction open, so we would leak
+	 * the transaction and/or crash.
+	 */
+	btrfs_qgroup_wait_for_completion(fs_info, false);
 
-		ret = btrfs_commit_super(fs_info);
-		if (ret)
-			goto restore;
-	} else {
-		if (BTRFS_FS_ERROR(fs_info)) {
-			btrfs_err(fs_info,
-				"Remounting read-write after error is not allowed");
-			ret = -EINVAL;
-			goto restore;
-		}
-		if (fs_info->fs_devices->rw_devices == 0) {
-			ret = -EACCES;
-			goto restore;
-		}
+	return btrfs_commit_super(fs_info);
+}
 
-		if (!btrfs_check_rw_degradable(fs_info, NULL)) {
-			btrfs_warn(fs_info,
-		"too many missing devices, writable remount is not allowed");
-			ret = -EACCES;
-			goto restore;
-		}
+static void btrfs_ctx_to_info(struct btrfs_fs_info *fs_info, struct btrfs_fs_context *ctx)
+{
+	fs_info->max_inline = ctx->max_inline;
+	fs_info->commit_interval = ctx->commit_interval;
+	fs_info->metadata_ratio = ctx->metadata_ratio;
+	fs_info->thread_pool_size = ctx->thread_pool_size;
+	fs_info->mount_opt = ctx->mount_opt;
+	fs_info->compress_type = ctx->compress_type;
+	fs_info->compress_level = ctx->compress_level;
+}
 
-		if (btrfs_super_log_root(fs_info->super_copy) != 0) {
-			btrfs_warn(fs_info,
-		"mount required to replay tree-log, cannot remount read-write");
-			ret = -EINVAL;
-			goto restore;
-		}
+static void btrfs_info_to_ctx(struct btrfs_fs_info *fs_info, struct btrfs_fs_context *ctx)
+{
+	ctx->max_inline = fs_info->max_inline;
+	ctx->commit_interval = fs_info->commit_interval;
+	ctx->metadata_ratio = fs_info->metadata_ratio;
+	ctx->thread_pool_size = fs_info->thread_pool_size;
+	ctx->mount_opt = fs_info->mount_opt;
+	ctx->compress_type = fs_info->compress_type;
+	ctx->compress_level = fs_info->compress_level;
+}
 
-		/*
-		 * NOTE: when remounting with a change that does writes, don't
-		 * put it anywhere above this point, as we are not sure to be
-		 * safe to write until we pass the above checks.
-		 */
-		ret = btrfs_start_pre_rw_mount(fs_info);
-		if (ret)
-			goto restore;
+#define btrfs_info_if_set(fs_info, old_ctx, opt, fmt, args...)			\
+do {										\
+	if ((!old_ctx || !btrfs_raw_test_opt(old_ctx->mount_opt, opt)) &&	\
+	    btrfs_raw_test_opt(fs_info->mount_opt, opt))			\
+		btrfs_info(fs_info, fmt, ##args);				\
+} while (0)
+
+#define btrfs_info_if_unset(fs_info, old_ctx, opt, fmt, args...)	\
+do {									\
+	if ((old_ctx && btrfs_raw_test_opt(old_ctx->mount_opt, opt)) &&	\
+	    !btrfs_raw_test_opt(fs_info->mount_opt, opt))		\
+		btrfs_info(fs_info, fmt, ##args);			\
+} while (0)
+
+static void btrfs_emit_options(struct btrfs_fs_info *info,
+			       struct btrfs_fs_context *old)
+{
+	btrfs_info_if_set(info, old, NODATASUM, "setting nodatasum");
+	btrfs_info_if_set(info, old, DEGRADED, "allowing degraded mounts");
+	btrfs_info_if_set(info, old, NODATASUM, "setting nodatasum");
+	btrfs_info_if_set(info, old, SSD, "enabling ssd optimizations");
+	btrfs_info_if_set(info, old, SSD_SPREAD, "using spread ssd allocation scheme");
+	btrfs_info_if_set(info, old, NOBARRIER, "turning off barriers");
+	btrfs_info_if_set(info, old, NOTREELOG, "disabling tree log");
+	btrfs_info_if_set(info, old, NOLOGREPLAY, "disabling log replay at mount time");
+	btrfs_info_if_set(info, old, FLUSHONCOMMIT, "turning on flush-on-commit");
+	btrfs_info_if_set(info, old, DISCARD_SYNC, "turning on sync discard");
+	btrfs_info_if_set(info, old, DISCARD_ASYNC, "turning on async discard");
+	btrfs_info_if_set(info, old, FREE_SPACE_TREE, "enabling free space tree");
+	btrfs_info_if_set(info, old, SPACE_CACHE, "enabling disk space caching");
+	btrfs_info_if_set(info, old, CLEAR_CACHE, "force clearing of disk cache");
+	btrfs_info_if_set(info, old, AUTO_DEFRAG, "enabling auto defrag");
+	btrfs_info_if_set(info, old, FRAGMENT_DATA, "fragmenting data");
+	btrfs_info_if_set(info, old, FRAGMENT_METADATA, "fragmenting metadata");
+	btrfs_info_if_set(info, old, REF_VERIFY, "doing ref verification");
+	btrfs_info_if_set(info, old, USEBACKUPROOT, "trying to use backup root at mount time");
+	btrfs_info_if_set(info, old, IGNOREBADROOTS, "ignoring bad roots");
+	btrfs_info_if_set(info, old, IGNOREDATACSUMS, "ignoring data csums");
+
+	btrfs_info_if_unset(info, old, NODATACOW, "setting datacow");
+	btrfs_info_if_unset(info, old, SSD, "not using ssd optimizations");
+	btrfs_info_if_unset(info, old, SSD_SPREAD, "not using spread ssd allocation scheme");
+	btrfs_info_if_unset(info, old, NOBARRIER, "turning off barriers");
+	btrfs_info_if_unset(info, old, NOTREELOG, "enabling tree log");
+	btrfs_info_if_unset(info, old, SPACE_CACHE, "disabling disk space caching");
+	btrfs_info_if_unset(info, old, FREE_SPACE_TREE, "disabling free space tree");
+	btrfs_info_if_unset(info, old, AUTO_DEFRAG, "disabling auto defrag");
+	btrfs_info_if_unset(info, old, COMPRESS, "use no compression");
+
+	/* Did the compression settings change? */
+	if (btrfs_test_opt(info, COMPRESS) &&
+	    (!old ||
+	     old->compress_type != info->compress_type ||
+	     old->compress_level != info->compress_level ||
+	     (!btrfs_raw_test_opt(old->mount_opt, FORCE_COMPRESS) &&
+	      btrfs_raw_test_opt(info->mount_opt, FORCE_COMPRESS)))) {
+		const char *compress_type = btrfs_compress_type2str(info->compress_type);
+
+		btrfs_info(info, "%s %s compression, level %d",
+			   btrfs_test_opt(info, FORCE_COMPRESS) ? "force" : "use",
+			   compress_type, info->compress_level);
+	}
 
-		btrfs_clear_sb_rdonly(sb);
+	if (info->max_inline != BTRFS_DEFAULT_MAX_INLINE)
+		btrfs_info(info, "max_inline set to %llu", info->max_inline);
+}
 
-		set_bit(BTRFS_FS_OPEN, &fs_info->flags);
+static int btrfs_reconfigure(struct fs_context *fc)
+{
+	struct super_block *sb = fc->root->d_sb;
+	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+	struct btrfs_fs_context *ctx = fc->fs_private;
+	struct btrfs_fs_context old_ctx;
+	int ret = 0;
+	bool mount_reconfigure = (fc->s_fs_info != NULL);
 
-		/*
-		 * If we've gone from readonly -> read/write, we need to get
-		 * our sync/async discard lists in the right state.
-		 */
-		btrfs_discard_resume(fs_info);
+	btrfs_info_to_ctx(fs_info, &old_ctx);
+
+	sync_filesystem(sb);
+	set_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
+
+	if (!mount_reconfigure &&
+	    !btrfs_check_options(fs_info, &ctx->mount_opt, fc->sb_flags))
+		return -EINVAL;
+
+	ret = btrfs_check_features(fs_info, !(fc->sb_flags & SB_RDONLY));
+	if (ret < 0)
+		return ret;
+
+	btrfs_ctx_to_info(fs_info, ctx);
+	btrfs_remount_begin(fs_info, old_ctx.mount_opt, fc->sb_flags);
+	btrfs_resize_thread_pool(fs_info, fs_info->thread_pool_size,
+				 old_ctx.thread_pool_size);
+
+	if ((bool)btrfs_test_opt(fs_info, FREE_SPACE_TREE) !=
+	    (bool)btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) &&
+	    (!sb_rdonly(sb) || (fc->sb_flags & SB_RDONLY))) {
+		btrfs_warn(fs_info,
+		"remount supports changing free space tree only from RO to RW");
+		/* Make sure free space cache options match the state on disk. */
+		if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
+			btrfs_set_opt(fs_info->mount_opt, FREE_SPACE_TREE);
+			btrfs_clear_opt(fs_info->mount_opt, SPACE_CACHE);
+		}
+		if (btrfs_free_space_cache_v1_active(fs_info)) {
+			btrfs_clear_opt(fs_info->mount_opt, FREE_SPACE_TREE);
+			btrfs_set_opt(fs_info->mount_opt, SPACE_CACHE);
+		}
 	}
-out:
+
+	ret = 0;
+	if (!sb_rdonly(sb) && (fc->sb_flags & SB_RDONLY))
+		ret = btrfs_remount_ro(fs_info);
+	else if (sb_rdonly(sb) && !(fc->sb_flags & SB_RDONLY))
+		ret = btrfs_remount_rw(fs_info);
+	if (ret)
+		goto restore;
+
 	/*
-	 * We need to set SB_I_VERSION here otherwise it'll get cleared by VFS,
-	 * since the absence of the flag means it can be toggled off by remount.
+	 * If we set the mask during the parameter parsing VFS would reject the
+	 * remount.  Here we can set the mask and the value will be updated
+	 * appropriately.
 	 */
-	*flags |= SB_I_VERSION;
+	if ((fc->sb_flags & SB_POSIXACL) != (sb->s_flags & SB_POSIXACL))
+		fc->sb_flags_mask |= SB_POSIXACL;
 
+	btrfs_emit_options(fs_info, &old_ctx);
 	wake_up_process(fs_info->transaction_kthread);
-	btrfs_remount_cleanup(fs_info, old_opts);
+	btrfs_remount_cleanup(fs_info, old_ctx.mount_opt);
 	btrfs_clear_oneshot_options(fs_info);
 	clear_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
 
 	return 0;
-
 restore:
-	/* We've hit an error - don't reset SB_RDONLY */
-	if (sb_rdonly(sb))
-		old_flags |= SB_RDONLY;
-	if (!(old_flags & SB_RDONLY))
-		clear_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state);
-	sb->s_flags = old_flags;
-	fs_info->mount_opt = old_opts;
-	fs_info->compress_type = old_compress_type;
-	fs_info->max_inline = old_max_inline;
-	btrfs_resize_thread_pool(fs_info,
-		old_thread_pool_size, fs_info->thread_pool_size);
-	fs_info->metadata_ratio = old_metadata_ratio;
-	btrfs_remount_cleanup(fs_info, old_opts);
+	btrfs_ctx_to_info(fs_info, &old_ctx);
+	btrfs_remount_cleanup(fs_info, old_ctx.mount_opt);
 	clear_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
-
 	return ret;
 }
 
@@ -2091,6 +1776,309 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	return 0;
 }
 
+static int btrfs_fc_test_super(struct super_block *sb, struct fs_context *fc)
+{
+	struct btrfs_fs_info *p = fc->s_fs_info;
+	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+
+	return fs_info->fs_devices == p->fs_devices;
+}
+
+static int btrfs_get_tree_super(struct fs_context *fc)
+{
+	struct btrfs_fs_info *fs_info = fc->s_fs_info;
+	struct btrfs_fs_context *ctx = fc->fs_private;
+	struct btrfs_fs_devices *fs_devices = NULL;
+	struct block_device *bdev;
+	struct btrfs_device *device;
+	struct super_block *sb;
+	blk_mode_t mode = btrfs_open_mode(fc);
+	int ret;
+
+	btrfs_ctx_to_info(fs_info, ctx);
+	mutex_lock(&uuid_mutex);
+
+	/*
+	 * With 'true' passed to btrfs_scan_one_device() (mount time) we expect
+	 * either a valid device or an error.
+	 */
+	device = btrfs_scan_one_device(fc->source, mode, true);
+	ASSERT(device != NULL);
+	if (IS_ERR(device)) {
+		mutex_unlock(&uuid_mutex);
+		return PTR_ERR(device);
+	}
+
+	fs_devices = device->fs_devices;
+	fs_info->fs_devices = fs_devices;
+
+	ret = btrfs_open_devices(fs_devices, mode, &btrfs_fs_type);
+	mutex_unlock(&uuid_mutex);
+	if (ret)
+		return ret;
+
+	if (!(fc->sb_flags & SB_RDONLY) && fs_devices->rw_devices == 0) {
+		ret = -EACCES;
+		goto error;
+	}
+
+	bdev = fs_devices->latest_dev->bdev;
+
+	/*
+	 * From now on the error handling is not straightforward.
+	 *
+	 * If successful, this will transfer the fs_info into the super block,
+	 * and fc->s_fs_info will be NULL.  However if there's an existing
+	 * super, we'll still have fc->s_fs_info populated.  If we error
+	 * completely out it'll be cleaned up when we drop the fs_context,
+	 * otherwise it's tied to the lifetime of the super_block.
+	 */
+	sb = sget_fc(fc, btrfs_fc_test_super, set_anon_super_fc);
+	if (IS_ERR(sb)) {
+		ret = PTR_ERR(sb);
+		goto error;
+	}
+
+	set_device_specific_options(fs_info);
+
+	if (sb->s_root) {
+		btrfs_close_devices(fs_devices);
+		if ((fc->sb_flags ^ sb->s_flags) & SB_RDONLY)
+			ret = -EBUSY;
+	} else {
+		snprintf(sb->s_id, sizeof(sb->s_id), "%pg", bdev);
+		shrinker_debugfs_rename(sb->s_shrink, "sb-btrfs:%s", sb->s_id);
+		btrfs_sb(sb)->bdev_holder = &btrfs_fs_type;
+		ret = btrfs_fill_super(sb, fs_devices, NULL);
+	}
+
+	if (ret) {
+		deactivate_locked_super(sb);
+		return ret;
+	}
+
+	btrfs_clear_oneshot_options(fs_info);
+
+	fc->root = dget(sb->s_root);
+	return 0;
+
+error:
+	btrfs_close_devices(fs_devices);
+	return ret;
+}
+
+/*
+ * Ever since commit 0723a0473fb4 ("btrfs: allow mounting btrfs subvolumes
+ * with different ro/rw options") the following works:
+ *
+ *        (i) mount /dev/sda3 -o subvol=foo,ro /mnt/foo
+ *       (ii) mount /dev/sda3 -o subvol=bar,rw /mnt/bar
+ *
+ * which looks nice and innocent but is actually pretty intricate and deserves
+ * a long comment.
+ *
+ * On another filesystem a subvolume mount is close to something like:
+ *
+ *	(iii) # create rw superblock + initial mount
+ *	      mount -t xfs /dev/sdb /opt/
+ *
+ *	      # create ro bind mount
+ *	      mount --bind -o ro /opt/foo /mnt/foo
+ *
+ *	      # unmount initial mount
+ *	      umount /opt
+ *
+ * Of course, there's some special subvolume sauce and there's the fact that the
+ * sb->s_root dentry is really swapped after mount_subtree(). But conceptually
+ * it's very close and will help us understand the issue.
+ *
+ * The old mount API didn't cleanly distinguish between a mount being made ro
+ * and a superblock being made ro.  The only way to change the ro state of
+ * either object was by passing ms_rdonly. If a new mount was created via
+ * mount(2) such as:
+ *
+ *      mount("/dev/sdb", "/mnt", "xfs", ms_rdonly, null);
+ *
+ * the MS_RDONLY flag being specified had two effects:
+ *
+ * (1) MNT_READONLY was raised -> the resulting mount got
+ *     @mnt->mnt_flags |= MNT_READONLY raised.
+ *
+ * (2) MS_RDONLY was passed to the filesystem's mount method and the filesystems
+ *     made the superblock ro. Note, how SB_RDONLY has the same value as
+ *     ms_rdonly and is raised whenever MS_RDONLY is passed through mount(2).
+ *
+ * Creating a subtree mount via (iii) ends up leaving a rw superblock with a
+ * subtree mounted ro.
+ *
+ * But consider the effect on the old mount API on btrfs subvolume mounting
+ * which combines the distinct step in (iii) into a single step.
+ *
+ * By issuing (i) both the mount and the superblock are turned ro. Now when (ii)
+ * is issued the superblock is ro and thus even if the mount created for (ii) is
+ * rw it wouldn't help. Hence, btrfs needed to transition the superblock from ro
+ * to rw for (ii) which it did using an internal remount call.
+ *
+ * IOW, subvolume mounting was inherently complicated due to the ambiguity of
+ * MS_RDONLY in mount(2). Note, this ambiguity has mount(8) always translate
+ * "ro" to MS_RDONLY. IOW, in both (i) and (ii) "ro" becomes MS_RDONLY when
+ * passed by mount(8) to mount(2).
+ *
+ * Enter the new mount API. The new mount API disambiguates making a mount ro
+ * and making a superblock ro.
+ *
+ * (3) To turn a mount ro the MOUNT_ATTR_ONLY flag can be used with either
+ *     fsmount() or mount_setattr() this is a pure VFS level change for a
+ *     specific mount or mount tree that is never seen by the filesystem itself.
+ *
+ * (4) To turn a superblock ro the "ro" flag must be used with
+ *     fsconfig(FSCONFIG_SET_FLAG, "ro"). This option is seen by the filesystem
+ *     in fc->sb_flags.
+ *
+ * This disambiguation has rather positive consequences.  Mounting a subvolume
+ * ro will not also turn the superblock ro. Only the mount for the subvolume
+ * will become ro.
+ *
+ * So, if the superblock creation request comes from the new mount API the
+ * caller must have explicitly done:
+ *
+ *      fsconfig(FSCONFIG_SET_FLAG, "ro")
+ *      fsmount/mount_setattr(MOUNT_ATTR_RDONLY)
+ *
+ * IOW, at some point the caller must have explicitly turned the whole
+ * superblock ro and we shouldn't just undo it like we did for the old mount
+ * API. In any case, it lets us avoid the hack in the new mount API.
+ *
+ * Consequently, the remounting hack must only be used for requests originating
+ * from the old mount API and should be marked for full deprecation so it can be
+ * turned off in a couple of years.
+ *
+ * The new mount API has no reason to support this hack.
+ */
+static struct vfsmount *btrfs_reconfigure_for_mount(struct fs_context *fc)
+{
+	struct vfsmount *mnt;
+	int ret;
+	const bool ro2rw = !(fc->sb_flags & SB_RDONLY);
+
+	/*
+	 * We got an EBUSY because our SB_RDONLY flag didn't match the existing
+	 * super block, so invert our setting here and retry the mount so we
+	 * can get our vfsmount.
+	 */
+	if (ro2rw)
+		fc->sb_flags |= SB_RDONLY;
+	else
+		fc->sb_flags &= ~SB_RDONLY;
+
+	mnt = fc_mount(fc);
+	if (IS_ERR(mnt))
+		return mnt;
+
+	if (!fc->oldapi || !ro2rw)
+		return mnt;
+
+	/* We need to convert to rw, call reconfigure. */
+	fc->sb_flags &= ~SB_RDONLY;
+	down_write(&mnt->mnt_sb->s_umount);
+	ret = btrfs_reconfigure(fc);
+	up_write(&mnt->mnt_sb->s_umount);
+	if (ret) {
+		mntput(mnt);
+		return ERR_PTR(ret);
+	}
+	return mnt;
+}
+
+static int btrfs_get_tree_subvol(struct fs_context *fc)
+{
+	struct btrfs_fs_info *fs_info = NULL;
+	struct btrfs_fs_context *ctx = fc->fs_private;
+	struct fs_context *dup_fc;
+	struct dentry *dentry;
+	struct vfsmount *mnt;
+
+	/*
+	 * Setup a dummy root and fs_info for test/set super.  This is because
+	 * we don't actually fill this stuff out until open_ctree, but we need
+	 * then open_ctree will properly initialize the file system specific
+	 * settings later.  btrfs_init_fs_info initializes the static elements
+	 * of the fs_info (locks and such) to make cleanup easier if we find a
+	 * superblock with our given fs_devices later on at sget() time.
+	 */
+	fs_info = kvzalloc(sizeof(struct btrfs_fs_info), GFP_KERNEL);
+	if (!fs_info)
+		return -ENOMEM;
+
+	fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL);
+	fs_info->super_for_commit = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL);
+	if (!fs_info->super_copy || !fs_info->super_for_commit) {
+		btrfs_free_fs_info(fs_info);
+		return -ENOMEM;
+	}
+	btrfs_init_fs_info(fs_info);
+
+	dup_fc = vfs_dup_fs_context(fc);
+	if (IS_ERR(dup_fc)) {
+		btrfs_free_fs_info(fs_info);
+		return PTR_ERR(dup_fc);
+	}
+
+	/*
+	 * When we do the sget_fc this gets transferred to the sb, so we only
+	 * need to set it on the dup_fc as this is what creates the super block.
+	 */
+	dup_fc->s_fs_info = fs_info;
+
+	/*
+	 * We'll do the security settings in our btrfs_get_tree_super() mount
+	 * loop, they were duplicated into dup_fc, we can drop the originals
+	 * here.
+	 */
+	security_free_mnt_opts(&fc->security);
+	fc->security = NULL;
+
+	mnt = fc_mount(dup_fc);
+	if (PTR_ERR_OR_ZERO(mnt) == -EBUSY)
+		mnt = btrfs_reconfigure_for_mount(dup_fc);
+	put_fs_context(dup_fc);
+	if (IS_ERR(mnt))
+		return PTR_ERR(mnt);
+
+	/*
+	 * This free's ->subvol_name, because if it isn't set we have to
+	 * allocate a buffer to hold the subvol_name, so we just drop our
+	 * reference to it here.
+	 */
+	dentry = mount_subvol(ctx->subvol_name, ctx->subvol_objectid, mnt);
+	ctx->subvol_name = NULL;
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	fc->root = dentry;
+	return 0;
+}
+
+static int btrfs_get_tree(struct fs_context *fc)
+{
+	/*
+	 * Since we use mount_subtree to mount the default/specified subvol, we
+	 * have to do mounts in two steps.
+	 *
+	 * First pass through we call btrfs_get_tree_subvol(), this is just a
+	 * wrapper around fc_mount() to call back into here again, and this time
+	 * we'll call btrfs_get_tree_super().  This will do the open_ctree() and
+	 * everything to open the devices and file system.  Then we return back
+	 * with a fully constructed vfsmount in btrfs_get_tree_subvol(), and
+	 * from there we can do our mount_subvol() call, which will lookup
+	 * whichever subvol we're mounting and setup this fc with the
+	 * appropriate dentry for the subvol.
+	 */
+	if (fc->s_fs_info)
+		return btrfs_get_tree_super(fc);
+	return btrfs_get_tree_subvol(fc);
+}
+
 static void btrfs_kill_super(struct super_block *sb)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
@@ -2098,22 +2086,85 @@ static void btrfs_kill_super(struct super_block *sb)
 	btrfs_free_fs_info(fs_info);
 }
 
-static struct file_system_type btrfs_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "btrfs",
-	.mount		= btrfs_mount,
-	.kill_sb	= btrfs_kill_super,
-	.fs_flags	= FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA,
-};
+static void btrfs_free_fs_context(struct fs_context *fc)
+{
+	struct btrfs_fs_context *ctx = fc->fs_private;
+	struct btrfs_fs_info *fs_info = fc->s_fs_info;
+
+	if (fs_info)
+		btrfs_free_fs_info(fs_info);
+
+	if (ctx && refcount_dec_and_test(&ctx->refs)) {
+		kfree(ctx->subvol_name);
+		kfree(ctx);
+	}
+}
+
+static int btrfs_dup_fs_context(struct fs_context *fc, struct fs_context *src_fc)
+{
+	struct btrfs_fs_context *ctx = src_fc->fs_private;
 
-static struct file_system_type btrfs_root_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "btrfs",
-	.mount		= btrfs_mount_root,
-	.kill_sb	= btrfs_kill_super,
-	.fs_flags	= FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA | FS_ALLOW_IDMAP,
+	/*
+	 * Give a ref to our ctx to this dup, as we want to keep it around for
+	 * our original fc so we can have the subvolume name or objectid.
+	 *
+	 * We unset ->source in the original fc because the dup needs it for
+	 * mounting, and then once we free the dup it'll free ->source, so we
+	 * need to make sure we're only pointing to it in one fc.
+	 */
+	refcount_inc(&ctx->refs);
+	fc->fs_private = ctx;
+	fc->source = src_fc->source;
+	src_fc->source = NULL;
+	return 0;
+}
+
+static const struct fs_context_operations btrfs_fs_context_ops = {
+	.parse_param	= btrfs_parse_param,
+	.reconfigure	= btrfs_reconfigure,
+	.get_tree	= btrfs_get_tree,
+	.dup		= btrfs_dup_fs_context,
+	.free		= btrfs_free_fs_context,
 };
 
+static int btrfs_init_fs_context(struct fs_context *fc)
+{
+	struct btrfs_fs_context *ctx;
+
+	ctx = kzalloc(sizeof(struct btrfs_fs_context), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	refcount_set(&ctx->refs, 1);
+	fc->fs_private = ctx;
+	fc->ops = &btrfs_fs_context_ops;
+
+	if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
+		btrfs_info_to_ctx(btrfs_sb(fc->root->d_sb), ctx);
+	} else {
+		ctx->thread_pool_size =
+			min_t(unsigned long, num_online_cpus() + 2, 8);
+		ctx->max_inline = BTRFS_DEFAULT_MAX_INLINE;
+		ctx->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
+	}
+
+#ifdef CONFIG_BTRFS_FS_POSIX_ACL
+	fc->sb_flags |= SB_POSIXACL;
+#endif
+	fc->sb_flags |= SB_I_VERSION;
+
+	return 0;
+}
+
+static struct file_system_type btrfs_fs_type = {
+	.owner			= THIS_MODULE,
+	.name			= "btrfs",
+	.init_fs_context	= btrfs_init_fs_context,
+	.parameters		= btrfs_fs_parameters,
+	.kill_sb		= btrfs_kill_super,
+	.fs_flags		= FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA | FS_ALLOW_IDMAP,
+ };
+
 MODULE_ALIAS_FS("btrfs");
 
 static int btrfs_control_open(struct inode *inode, struct file *file)
@@ -2325,7 +2376,6 @@ static const struct super_operations btrfs_super_ops = {
 	.destroy_inode	= btrfs_destroy_inode,
 	.free_inode	= btrfs_free_inode,
 	.statfs		= btrfs_statfs,
-	.remount_fs	= btrfs_remount,
 	.freeze_fs	= btrfs_freeze,
 	.unfreeze_fs	= btrfs_unfreeze,
 };
diff --git a/fs/btrfs/super.h b/fs/btrfs/super.h
index 8dbb909b364f..f18253ca280d 100644
--- a/fs/btrfs/super.h
+++ b/fs/btrfs/super.h
@@ -3,11 +3,12 @@
 #ifndef BTRFS_SUPER_H
 #define BTRFS_SUPER_H
 
-int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
-			unsigned long new_flags);
+bool btrfs_check_options(struct btrfs_fs_info *info, unsigned long *mount_opt,
+			 unsigned long flags);
 int btrfs_sync_fs(struct super_block *sb, int wait);
 char *btrfs_get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info,
 					  u64 subvol_objectid);
+void btrfs_set_free_space_cache_settings(struct btrfs_fs_info *fs_info);
 
 static inline struct btrfs_fs_info *btrfs_sb(struct super_block *sb)
 {
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index e6b51fb3ddc1..84c05246ffd8 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -1783,6 +1783,10 @@ static ssize_t btrfs_devinfo_scrub_speed_max_store(struct kobject *kobj,
 	unsigned long long limit;
 
 	limit = memparse(buf, &endptr);
+	/* There could be trailing '\n', also catch any typos after the value. */
+	endptr = skip_spaces(endptr);
+	if (*endptr != 0)
+		return -EINVAL;
 	WRITE_ONCE(device->scrub_speed_max, limit);
 	return len;
 }
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index ca09cf9afce8..709c6cc9706a 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -28,6 +28,7 @@ const char *test_error[] = {
 	[TEST_ALLOC_INODE]	     = "cannot allocate inode",
 	[TEST_ALLOC_BLOCK_GROUP]     = "cannot allocate block group",
 	[TEST_ALLOC_EXTENT_MAP]      = "cannot allocate extent map",
+	[TEST_ALLOC_CHUNK_MAP]       = "cannot allocate chunk map",
 };
 
 static const struct super_operations btrfs_test_super_ops = {
@@ -102,7 +103,7 @@ struct btrfs_device *btrfs_alloc_dummy_device(struct btrfs_fs_info *fs_info)
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
-	extent_io_tree_init(NULL, &dev->alloc_state, 0);
+	extent_io_tree_init(fs_info, &dev->alloc_state, 0);
 	INIT_LIST_HEAD(&dev->dev_list);
 	list_add(&dev->dev_list, &fs_info->fs_devices->devices);
 
@@ -185,7 +186,7 @@ void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info)
 	}
 	spin_unlock(&fs_info->buffer_lock);
 
-	btrfs_mapping_tree_free(&fs_info->mapping_tree);
+	btrfs_mapping_tree_free(fs_info);
 	list_for_each_entry_safe(dev, tmp, &fs_info->fs_devices->devices,
 				 dev_list) {
 		btrfs_free_dummy_device(dev);
diff --git a/fs/btrfs/tests/btrfs-tests.h b/fs/btrfs/tests/btrfs-tests.h
index 7a2d7ffbe30e..dc2f2ab15fa5 100644
--- a/fs/btrfs/tests/btrfs-tests.h
+++ b/fs/btrfs/tests/btrfs-tests.h
@@ -23,6 +23,7 @@ enum {
 	TEST_ALLOC_INODE,
 	TEST_ALLOC_BLOCK_GROUP,
 	TEST_ALLOC_EXTENT_MAP,
+	TEST_ALLOC_CHUNK_MAP,
 };
 
 extern const char *test_error[];
diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c
index 1cc86af97dc6..25b3349595e0 100644
--- a/fs/btrfs/tests/extent-io-tests.c
+++ b/fs/btrfs/tests/extent-io-tests.c
@@ -652,7 +652,7 @@ static void dump_eb_and_memory_contents(struct extent_buffer *eb, void *memory,
 					const char *test_name)
 {
 	for (int i = 0; i < eb->len; i++) {
-		struct page *page = eb->pages[i >> PAGE_SHIFT];
+		struct page *page = folio_page(eb->folios[i >> PAGE_SHIFT], 0);
 		void *addr = page_address(page) + offset_in_page(i);
 
 		if (memcmp(addr, memory + i, 1) != 0) {
@@ -668,7 +668,7 @@ static int verify_eb_and_memory(struct extent_buffer *eb, void *memory,
 				const char *test_name)
 {
 	for (int i = 0; i < (eb->len >> PAGE_SHIFT); i++) {
-		void *eb_addr = page_address(eb->pages[i]);
+		void *eb_addr = folio_address(eb->folios[i]);
 
 		if (memcmp(memory + (i << PAGE_SHIFT), eb_addr, PAGE_SIZE) != 0) {
 			dump_eb_and_memory_contents(eb, memory, test_name);
diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c
index 29bdd08b241f..253cce7ffecf 100644
--- a/fs/btrfs/tests/extent-map-tests.c
+++ b/fs/btrfs/tests/extent-map-tests.c
@@ -25,7 +25,7 @@ static void free_extent_map_tree(struct extent_map_tree *em_tree)
 #ifdef CONFIG_BTRFS_DEBUG
 		if (refcount_read(&em->refs) != 1) {
 			test_err(
-"em leak: em (start 0x%llx len 0x%llx block_start 0x%llx block_len 0x%llx) refs %d",
+"em leak: em (start %llu len %llu block_start %llu block_len %llu) refs %d",
 				 em->start, em->len, em->block_start,
 				 em->block_len, refcount_read(&em->refs));
 
@@ -73,7 +73,7 @@ static int test_case_1(struct btrfs_fs_info *fs_info,
 	em->block_start = 0;
 	em->block_len = SZ_16K;
 	write_lock(&em_tree->lock);
-	ret = add_extent_mapping(em_tree, em, 0);
+	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	if (ret < 0) {
 		test_err("cannot add extent range [0, 16K)");
@@ -94,7 +94,7 @@ static int test_case_1(struct btrfs_fs_info *fs_info,
 	em->block_start = SZ_32K; /* avoid merging */
 	em->block_len = SZ_4K;
 	write_lock(&em_tree->lock);
-	ret = add_extent_mapping(em_tree, em, 0);
+	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	if (ret < 0) {
 		test_err("cannot add extent range [16K, 20K)");
@@ -121,9 +121,14 @@ static int test_case_1(struct btrfs_fs_info *fs_info,
 		test_err("case1 [%llu %llu]: ret %d", start, start + len, ret);
 		goto out;
 	}
-	if (em &&
-	    (em->start != 0 || extent_map_end(em) != SZ_16K ||
-	     em->block_start != 0 || em->block_len != SZ_16K)) {
+	if (!em) {
+		test_err("case1 [%llu %llu]: no extent map returned",
+			 start, start + len);
+		ret = -ENOENT;
+		goto out;
+	}
+	if (em->start != 0 || extent_map_end(em) != SZ_16K ||
+	    em->block_start != 0 || em->block_len != SZ_16K) {
 		test_err(
 "case1 [%llu %llu]: ret %d return a wrong em (start %llu len %llu block_start %llu block_len %llu",
 			 start, start + len, ret, em->start, em->len,
@@ -161,7 +166,7 @@ static int test_case_2(struct btrfs_fs_info *fs_info,
 	em->block_start = EXTENT_MAP_INLINE;
 	em->block_len = (u64)-1;
 	write_lock(&em_tree->lock);
-	ret = add_extent_mapping(em_tree, em, 0);
+	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	if (ret < 0) {
 		test_err("cannot add extent range [0, 1K)");
@@ -182,7 +187,7 @@ static int test_case_2(struct btrfs_fs_info *fs_info,
 	em->block_start = SZ_4K;
 	em->block_len = SZ_4K;
 	write_lock(&em_tree->lock);
-	ret = add_extent_mapping(em_tree, em, 0);
+	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	if (ret < 0) {
 		test_err("cannot add extent range [4K, 8K)");
@@ -209,9 +214,13 @@ static int test_case_2(struct btrfs_fs_info *fs_info,
 		test_err("case2 [0 1K]: ret %d", ret);
 		goto out;
 	}
-	if (em &&
-	    (em->start != 0 || extent_map_end(em) != SZ_1K ||
-	     em->block_start != EXTENT_MAP_INLINE || em->block_len != (u64)-1)) {
+	if (!em) {
+		test_err("case2 [0 1K]: no extent map returned");
+		ret = -ENOENT;
+		goto out;
+	}
+	if (em->start != 0 || extent_map_end(em) != SZ_1K ||
+	    em->block_start != EXTENT_MAP_INLINE || em->block_len != (u64)-1) {
 		test_err(
 "case2 [0 1K]: ret %d return a wrong em (start %llu len %llu block_start %llu block_len %llu",
 			 ret, em->start, em->len, em->block_start,
@@ -244,7 +253,7 @@ static int __test_case_3(struct btrfs_fs_info *fs_info,
 	em->block_start = SZ_4K;
 	em->block_len = SZ_4K;
 	write_lock(&em_tree->lock);
-	ret = add_extent_mapping(em_tree, em, 0);
+	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	if (ret < 0) {
 		test_err("cannot add extent range [4K, 8K)");
@@ -268,19 +277,24 @@ static int __test_case_3(struct btrfs_fs_info *fs_info,
 	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, start, len);
 	write_unlock(&em_tree->lock);
 	if (ret) {
-		test_err("case3 [0x%llx 0x%llx): ret %d",
+		test_err("case3 [%llu %llu): ret %d",
 			 start, start + len, ret);
 		goto out;
 	}
+	if (!em) {
+		test_err("case3 [%llu %llu): no extent map returned",
+			 start, start + len);
+		ret = -ENOENT;
+		goto out;
+	}
 	/*
 	 * Since bytes within em are contiguous, em->block_start is identical to
 	 * em->start.
 	 */
-	if (em &&
-	    (start < em->start || start + len > extent_map_end(em) ||
-	     em->start != em->block_start || em->len != em->block_len)) {
+	if (start < em->start || start + len > extent_map_end(em) ||
+	    em->start != em->block_start || em->len != em->block_len) {
 		test_err(
-"case3 [0x%llx 0x%llx): ret %d em (start 0x%llx len 0x%llx block_start 0x%llx block_len 0x%llx)",
+"case3 [%llu %llu): ret %d em (start %llu len %llu block_start %llu block_len %llu)",
 			 start, start + len, ret, em->start, em->len,
 			 em->block_start, em->block_len);
 		ret = -EINVAL;
@@ -343,7 +357,7 @@ static int __test_case_4(struct btrfs_fs_info *fs_info,
 	em->block_start = 0;
 	em->block_len = SZ_8K;
 	write_lock(&em_tree->lock);
-	ret = add_extent_mapping(em_tree, em, 0);
+	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	if (ret < 0) {
 		test_err("cannot add extent range [0, 8K)");
@@ -364,7 +378,7 @@ static int __test_case_4(struct btrfs_fs_info *fs_info,
 	em->block_start = SZ_16K; /* avoid merging */
 	em->block_len = 24 * SZ_1K;
 	write_lock(&em_tree->lock);
-	ret = add_extent_mapping(em_tree, em, 0);
+	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	if (ret < 0) {
 		test_err("cannot add extent range [8K, 32K)");
@@ -387,14 +401,20 @@ static int __test_case_4(struct btrfs_fs_info *fs_info,
 	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, start, len);
 	write_unlock(&em_tree->lock);
 	if (ret) {
-		test_err("case4 [0x%llx 0x%llx): ret %d",
-			 start, len, ret);
+		test_err("case4 [%llu %llu): ret %d",
+			 start, start + len, ret);
 		goto out;
 	}
-	if (em && (start < em->start || start + len > extent_map_end(em))) {
+	if (!em) {
+		test_err("case4 [%llu %llu): no extent map returned",
+			 start, start + len);
+		ret = -ENOENT;
+		goto out;
+	}
+	if (start < em->start || start + len > extent_map_end(em)) {
 		test_err(
-"case4 [0x%llx 0x%llx): ret %d, added wrong em (start 0x%llx len 0x%llx block_start 0x%llx block_len 0x%llx)",
-			 start, len, ret, em->start, em->len, em->block_start,
+"case4 [%llu %llu): ret %d, added wrong em (start %llu len %llu block_start %llu block_len %llu)",
+			 start, start + len, ret, em->start, em->len, em->block_start,
 			 em->block_len);
 		ret = -EINVAL;
 	}
@@ -443,7 +463,8 @@ static int test_case_4(struct btrfs_fs_info *fs_info,
 	return ret;
 }
 
-static int add_compressed_extent(struct extent_map_tree *em_tree,
+static int add_compressed_extent(struct btrfs_fs_info *fs_info,
+				 struct extent_map_tree *em_tree,
 				 u64 start, u64 len, u64 block_start)
 {
 	struct extent_map *em;
@@ -459,9 +480,9 @@ static int add_compressed_extent(struct extent_map_tree *em_tree,
 	em->len = len;
 	em->block_start = block_start;
 	em->block_len = SZ_4K;
-	set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
+	em->flags |= EXTENT_FLAG_COMPRESS_ZLIB;
 	write_lock(&em_tree->lock);
-	ret = add_extent_mapping(em_tree, em, 0);
+	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	free_extent_map(em);
 	if (ret < 0) {
@@ -567,7 +588,7 @@ static int validate_range(struct extent_map_tree *em_tree, int index)
  * They'll have the EXTENT_FLAG_COMPRESSED flag set to keep the em tree from
  * merging the em's.
  */
-static int test_case_5(void)
+static int test_case_5(struct btrfs_fs_info *fs_info)
 {
 	struct extent_map_tree *em_tree;
 	struct inode *inode;
@@ -585,35 +606,35 @@ static int test_case_5(void)
 	em_tree = &BTRFS_I(inode)->extent_tree;
 
 	/* [0, 12k) */
-	ret = add_compressed_extent(em_tree, 0, SZ_4K * 3, 0);
+	ret = add_compressed_extent(fs_info, em_tree, 0, SZ_4K * 3, 0);
 	if (ret) {
 		test_err("cannot add extent range [0, 12K)");
 		goto out;
 	}
 
 	/* [12k, 24k) */
-	ret = add_compressed_extent(em_tree, SZ_4K * 3, SZ_4K * 3, SZ_4K);
+	ret = add_compressed_extent(fs_info, em_tree, SZ_4K * 3, SZ_4K * 3, SZ_4K);
 	if (ret) {
 		test_err("cannot add extent range [12k, 24k)");
 		goto out;
 	}
 
 	/* [24k, 36k) */
-	ret = add_compressed_extent(em_tree, SZ_4K * 6, SZ_4K * 3, SZ_8K);
+	ret = add_compressed_extent(fs_info, em_tree, SZ_4K * 6, SZ_4K * 3, SZ_8K);
 	if (ret) {
 		test_err("cannot add extent range [12k, 24k)");
 		goto out;
 	}
 
 	/* [36k, 40k) */
-	ret = add_compressed_extent(em_tree, SZ_32K + SZ_4K, SZ_4K, SZ_4K * 3);
+	ret = add_compressed_extent(fs_info, em_tree, SZ_32K + SZ_4K, SZ_4K, SZ_4K * 3);
 	if (ret) {
 		test_err("cannot add extent range [12k, 24k)");
 		goto out;
 	}
 
 	/* [40k, 64k) */
-	ret = add_compressed_extent(em_tree, SZ_4K * 10, SZ_4K * 6, SZ_16K);
+	ret = add_compressed_extent(fs_info, em_tree, SZ_4K * 10, SZ_4K * 6, SZ_16K);
 	if (ret) {
 		test_err("cannot add extent range [12k, 24k)");
 		goto out;
@@ -665,11 +686,11 @@ static int test_case_6(struct btrfs_fs_info *fs_info, struct extent_map_tree *em
 	struct extent_map *em = NULL;
 	int ret;
 
-	ret = add_compressed_extent(em_tree, 0, SZ_4K, 0);
+	ret = add_compressed_extent(fs_info, em_tree, 0, SZ_4K, 0);
 	if (ret)
 		goto out;
 
-	ret = add_compressed_extent(em_tree, SZ_4K, SZ_4K, 0);
+	ret = add_compressed_extent(fs_info, em_tree, SZ_4K, SZ_4K, 0);
 	if (ret)
 		goto out;
 
@@ -713,7 +734,7 @@ out:
  * true would mess up the start/end calculations and subsequent splits would be
  * incorrect.
  */
-static int test_case_7(void)
+static int test_case_7(struct btrfs_fs_info *fs_info)
 {
 	struct extent_map_tree *em_tree;
 	struct extent_map *em;
@@ -742,9 +763,9 @@ static int test_case_7(void)
 	em->len = SZ_16K;
 	em->block_start = 0;
 	em->block_len = SZ_4K;
-	set_bit(EXTENT_FLAG_PINNED, &em->flags);
+	em->flags |= EXTENT_FLAG_PINNED;
 	write_lock(&em_tree->lock);
-	ret = add_extent_mapping(em_tree, em, 0);
+	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	if (ret < 0) {
 		test_err("couldn't add extent map");
@@ -765,7 +786,7 @@ static int test_case_7(void)
 	em->block_start = SZ_32K;
 	em->block_len = SZ_16K;
 	write_lock(&em_tree->lock);
-	ret = add_extent_mapping(em_tree, em, 0);
+	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	if (ret < 0) {
 		test_err("couldn't add extent map");
@@ -859,33 +880,21 @@ struct rmap_test_vector {
 static int test_rmap_block(struct btrfs_fs_info *fs_info,
 			   struct rmap_test_vector *test)
 {
-	struct extent_map *em;
-	struct map_lookup *map = NULL;
+	struct btrfs_chunk_map *map;
 	u64 *logical = NULL;
 	int i, out_ndaddrs, out_stripe_len;
 	int ret;
 
-	em = alloc_extent_map();
-	if (!em) {
-		test_std_err(TEST_ALLOC_EXTENT_MAP);
-		return -ENOMEM;
-	}
-
-	map = kmalloc(map_lookup_size(test->num_stripes), GFP_KERNEL);
+	map = btrfs_alloc_chunk_map(test->num_stripes, GFP_KERNEL);
 	if (!map) {
-		kfree(em);
-		test_std_err(TEST_ALLOC_EXTENT_MAP);
+		test_std_err(TEST_ALLOC_CHUNK_MAP);
 		return -ENOMEM;
 	}
 
-	set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
 	/* Start at 4GiB logical address */
-	em->start = SZ_4G;
-	em->len = test->data_stripe_size * test->num_data_stripes;
-	em->block_len = em->len;
-	em->orig_block_len = test->data_stripe_size;
-	em->map_lookup = map;
-
+	map->start = SZ_4G;
+	map->chunk_len = test->data_stripe_size * test->num_data_stripes;
+	map->stripe_size = test->data_stripe_size;
 	map->num_stripes = test->num_stripes;
 	map->type = test->raid_type;
 
@@ -901,15 +910,13 @@ static int test_rmap_block(struct btrfs_fs_info *fs_info,
 		map->stripes[i].physical = test->data_stripe_phys_start[i];
 	}
 
-	write_lock(&fs_info->mapping_tree.lock);
-	ret = add_extent_mapping(&fs_info->mapping_tree, em, 0);
-	write_unlock(&fs_info->mapping_tree.lock);
+	ret = btrfs_add_chunk_map(fs_info, map);
 	if (ret) {
-		test_err("error adding block group mapping to mapping tree");
+		test_err("error adding chunk map to mapping tree");
 		goto out_free;
 	}
 
-	ret = btrfs_rmap_block(fs_info, em->start, btrfs_sb_offset(1),
+	ret = btrfs_rmap_block(fs_info, map->start, btrfs_sb_offset(1),
 			       &logical, &out_ndaddrs, &out_stripe_len);
 	if (ret || (out_ndaddrs == 0 && test->expected_mapped_addr)) {
 		test_err("didn't rmap anything but expected %d",
@@ -938,14 +945,8 @@ static int test_rmap_block(struct btrfs_fs_info *fs_info,
 
 	ret = 0;
 out:
-	write_lock(&fs_info->mapping_tree.lock);
-	remove_extent_mapping(&fs_info->mapping_tree, em);
-	write_unlock(&fs_info->mapping_tree.lock);
-	/* For us */
-	free_extent_map(em);
+	btrfs_remove_chunk_map(fs_info, map);
 out_free:
-	/* For the tree */
-	free_extent_map(em);
 	kfree(logical);
 	return ret;
 }
@@ -1022,13 +1023,13 @@ int btrfs_test_extent_map(void)
 	ret = test_case_4(fs_info, em_tree);
 	if (ret)
 		goto out;
-	ret = test_case_5();
+	ret = test_case_5(fs_info);
 	if (ret)
 		goto out;
 	ret = test_case_6(fs_info, em_tree);
 	if (ret)
 		goto out;
-	ret = test_case_7();
+	ret = test_case_7(fs_info);
 	if (ret)
 		goto out;
 
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index 492d69d2fa73..9957de9f7806 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -211,9 +211,9 @@ static void setup_file_extents(struct btrfs_root *root, u32 sectorsize)
 		      sectorsize, BTRFS_FILE_EXTENT_REG, 0, slot);
 }
 
-static unsigned long prealloc_only = 0;
-static unsigned long compressed_only = 0;
-static unsigned long vacancy_only = 0;
+static u32 prealloc_only = 0;
+static u32 compressed_only = 0;
+static u32 vacancy_only = 0;
 
 static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 {
@@ -305,7 +305,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, want 0 have %lu", em->flags);
+		test_err("unexpected flags set, want 0 have %u", em->flags);
 		goto out;
 	}
 	/*
@@ -332,7 +332,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, want 0 have %lu", em->flags);
+		test_err("unexpected flags set, want 0 have %u", em->flags);
 		goto out;
 	}
 	offset = em->start + em->len;
@@ -355,7 +355,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, want 0 have %lu", em->flags);
+		test_err("unexpected flags set, want 0 have %u", em->flags);
 		goto out;
 	}
 	if (em->orig_start != em->start) {
@@ -383,7 +383,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, want 0 have %lu", em->flags);
+		test_err("unexpected flags set, want 0 have %u", em->flags);
 		goto out;
 	}
 	if (em->orig_start != em->start) {
@@ -412,7 +412,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, want 0 have %lu", em->flags);
+		test_err("unexpected flags set, want 0 have %u", em->flags);
 		goto out;
 	}
 	offset = em->start + em->len;
@@ -434,7 +434,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, want 0 have %lu", em->flags);
+		test_err("unexpected flags set, want 0 have %u", em->flags);
 		goto out;
 	}
 	if (em->orig_start != orig_start) {
@@ -468,7 +468,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != prealloc_only) {
-		test_err("unexpected flags set, want %lu have %lu",
+		test_err("unexpected flags set, want %u have %u",
 			 prealloc_only, em->flags);
 		goto out;
 	}
@@ -497,7 +497,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != prealloc_only) {
-		test_err("unexpected flags set, want %lu have %lu",
+		test_err("unexpected flags set, want %u have %u",
 			 prealloc_only, em->flags);
 		goto out;
 	}
@@ -527,7 +527,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, want 0 have %lu", em->flags);
+		test_err("unexpected flags set, want 0 have %u", em->flags);
 		goto out;
 	}
 	if (em->orig_start != orig_start) {
@@ -560,7 +560,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != prealloc_only) {
-		test_err("unexpected flags set, want %lu have %lu",
+		test_err("unexpected flags set, want %u have %u",
 			 prealloc_only, em->flags);
 		goto out;
 	}
@@ -595,7 +595,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != compressed_only) {
-		test_err("unexpected flags set, want %lu have %lu",
+		test_err("unexpected flags set, want %u have %u",
 			 compressed_only, em->flags);
 		goto out;
 	}
@@ -604,9 +604,9 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 			 em->start, em->orig_start);
 		goto out;
 	}
-	if (em->compress_type != BTRFS_COMPRESS_ZLIB) {
+	if (extent_map_compression(em) != BTRFS_COMPRESS_ZLIB) {
 		test_err("unexpected compress type, wanted %d, got %d",
-			 BTRFS_COMPRESS_ZLIB, em->compress_type);
+			 BTRFS_COMPRESS_ZLIB, extent_map_compression(em));
 		goto out;
 	}
 	offset = em->start + em->len;
@@ -629,7 +629,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != compressed_only) {
-		test_err("unexpected flags set, want %lu have %lu",
+		test_err("unexpected flags set, want %u have %u",
 			 compressed_only, em->flags);
 		goto out;
 	}
@@ -638,9 +638,9 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 			 em->start, em->orig_start);
 		goto out;
 	}
-	if (em->compress_type != BTRFS_COMPRESS_ZLIB) {
+	if (extent_map_compression(em) != BTRFS_COMPRESS_ZLIB) {
 		test_err("unexpected compress type, wanted %d, got %d",
-			 BTRFS_COMPRESS_ZLIB, em->compress_type);
+			 BTRFS_COMPRESS_ZLIB, extent_map_compression(em));
 		goto out;
 	}
 	disk_bytenr = em->block_start;
@@ -664,7 +664,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, want 0 have %lu", em->flags);
+		test_err("unexpected flags set, want 0 have %u", em->flags);
 		goto out;
 	}
 	if (em->orig_start != em->start) {
@@ -692,7 +692,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != compressed_only) {
-		test_err("unexpected flags set, want %lu have %lu",
+		test_err("unexpected flags set, want %u have %u",
 			 compressed_only, em->flags);
 		goto out;
 	}
@@ -701,9 +701,9 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 			 em->start, orig_start);
 		goto out;
 	}
-	if (em->compress_type != BTRFS_COMPRESS_ZLIB) {
+	if (extent_map_compression(em) != BTRFS_COMPRESS_ZLIB) {
 		test_err("unexpected compress type, wanted %d, got %d",
-			 BTRFS_COMPRESS_ZLIB, em->compress_type);
+			 BTRFS_COMPRESS_ZLIB, extent_map_compression(em));
 		goto out;
 	}
 	offset = em->start + em->len;
@@ -726,7 +726,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, want 0 have %lu", em->flags);
+		test_err("unexpected flags set, want 0 have %u", em->flags);
 		goto out;
 	}
 	if (em->orig_start != em->start) {
@@ -758,7 +758,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != vacancy_only) {
-		test_err("unexpected flags set, want %lu have %lu",
+		test_err("unexpected flags set, want %u have %u",
 			 vacancy_only, em->flags);
 		goto out;
 	}
@@ -786,7 +786,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, want 0 have %lu", em->flags);
+		test_err("unexpected flags set, want 0 have %u", em->flags);
 		goto out;
 	}
 	if (em->orig_start != em->start) {
@@ -866,7 +866,7 @@ static int test_hole_first(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != vacancy_only) {
-		test_err("wrong flags, wanted %lu, have %lu", vacancy_only,
+		test_err("wrong flags, wanted %u, have %u", vacancy_only,
 			 em->flags);
 		goto out;
 	}
@@ -888,7 +888,7 @@ static int test_hole_first(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, wanted 0 got %lu",
+		test_err("unexpected flags set, wanted 0 got %u",
 			 em->flags);
 		goto out;
 	}
@@ -1095,8 +1095,8 @@ int btrfs_test_inodes(u32 sectorsize, u32 nodesize)
 
 	test_msg("running inode tests");
 
-	set_bit(EXTENT_FLAG_COMPRESSED, &compressed_only);
-	set_bit(EXTENT_FLAG_PREALLOC, &prealloc_only);
+	compressed_only |= EXTENT_FLAG_COMPRESS_ZLIB;
+	prealloc_only |= EXTENT_FLAG_PREALLOC;
 
 	ret = test_btrfs_get_extent(sectorsize, nodesize);
 	if (ret)
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 6e63816dddcb..5b3333ceef04 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -37,8 +37,6 @@
 
 static struct kmem_cache *btrfs_trans_handle_cachep;
 
-#define BTRFS_ROOT_TRANS_TAG 0
-
 /*
  * Transaction states and transitions
  *
@@ -1774,7 +1772,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	btrfs_release_path(path);
 
 	ret = btrfs_create_qgroup(trans, objectid);
-	if (ret) {
+	if (ret && ret != -EEXIST) {
 		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 18c4f6e83b78..2bf8bbdfd0b3 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -12,6 +12,9 @@
 #include "ctree.h"
 #include "misc.h"
 
+/* Radix-tree tag for roots that are part of the trasaction. */
+#define BTRFS_ROOT_TRANS_TAG			0
+
 enum btrfs_trans_state {
 	TRANS_STATE_RUNNING,
 	TRANS_STATE_COMMIT_PREP,
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index a416cbea75d1..50fdc69fdddf 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -31,6 +31,7 @@
 #include "inode-item.h"
 #include "dir-item.h"
 #include "raid-stripe-tree.h"
+#include "extent-tree.h"
 
 /*
  * Error message should follow the following format:
@@ -1276,6 +1277,8 @@ static int check_extent_item(struct extent_buffer *leaf,
 	unsigned long ptr;	/* Current pointer inside inline refs */
 	unsigned long end;	/* Extent item end */
 	const u32 item_size = btrfs_item_size(leaf, slot);
+	u8 last_type = 0;
+	u64 last_seq = U64_MAX;
 	u64 flags;
 	u64 generation;
 	u64 total_refs;		/* Total refs in btrfs_extent_item */
@@ -1322,6 +1325,18 @@ static int check_extent_item(struct extent_buffer *leaf,
 	 *    2.2) Ref type specific data
 	 *         Either using btrfs_extent_inline_ref::offset, or specific
 	 *         data structure.
+	 *
+	 *    All above inline items should follow the order:
+	 *
+	 *    - All btrfs_extent_inline_ref::type should be in an ascending
+	 *      order
+	 *
+	 *    - Within the same type, the items should follow a descending
+	 *      order by their sequence number. The sequence number is
+	 *      determined by:
+	 *      * btrfs_extent_inline_ref::offset for all types  other than
+	 *        EXTENT_DATA_REF
+	 *      * hash_extent_data_ref() for EXTENT_DATA_REF
 	 */
 	if (unlikely(item_size < sizeof(*ei))) {
 		extent_err(leaf, slot,
@@ -1403,6 +1418,7 @@ static int check_extent_item(struct extent_buffer *leaf,
 		struct btrfs_extent_inline_ref *iref;
 		struct btrfs_extent_data_ref *dref;
 		struct btrfs_shared_data_ref *sref;
+		u64 seq;
 		u64 dref_offset;
 		u64 inline_offset;
 		u8 inline_type;
@@ -1416,6 +1432,7 @@ static int check_extent_item(struct extent_buffer *leaf,
 		iref = (struct btrfs_extent_inline_ref *)ptr;
 		inline_type = btrfs_extent_inline_ref_type(leaf, iref);
 		inline_offset = btrfs_extent_inline_ref_offset(leaf, iref);
+		seq = inline_offset;
 		if (unlikely(ptr + btrfs_extent_inline_ref_size(inline_type) > end)) {
 			extent_err(leaf, slot,
 "inline ref item overflows extent item, ptr %lu iref size %u end %lu",
@@ -1446,6 +1463,10 @@ static int check_extent_item(struct extent_buffer *leaf,
 		case BTRFS_EXTENT_DATA_REF_KEY:
 			dref = (struct btrfs_extent_data_ref *)(&iref->offset);
 			dref_offset = btrfs_extent_data_ref_offset(leaf, dref);
+			seq = hash_extent_data_ref(
+					btrfs_extent_data_ref_root(leaf, dref),
+					btrfs_extent_data_ref_objectid(leaf, dref),
+					btrfs_extent_data_ref_offset(leaf, dref));
 			if (unlikely(!IS_ALIGNED(dref_offset,
 						 fs_info->sectorsize))) {
 				extent_err(leaf, slot,
@@ -1475,6 +1496,24 @@ static int check_extent_item(struct extent_buffer *leaf,
 				   inline_type);
 			return -EUCLEAN;
 		}
+		if (inline_type < last_type) {
+			extent_err(leaf, slot,
+				   "inline ref out-of-order: has type %u, prev type %u",
+				   inline_type, last_type);
+			return -EUCLEAN;
+		}
+		/* Type changed, allow the sequence starts from U64_MAX again. */
+		if (inline_type > last_type)
+			last_seq = U64_MAX;
+		if (seq > last_seq) {
+			extent_err(leaf, slot,
+"inline ref out-of-order: has type %u offset %llu seq 0x%llx, prev type %u seq 0x%llx",
+				   inline_type, inline_offset, seq,
+				   last_type, last_seq);
+			return -EUCLEAN;
+		}
+		last_type = inline_type;
+		last_seq = seq;
 		ptr += btrfs_extent_inline_ref_size(inline_type);
 	}
 	/* No padding is allowed */
diff --git a/fs/btrfs/tree-checker.h b/fs/btrfs/tree-checker.h
index 3c2a02a72f64..14b9fbe82da4 100644
--- a/fs/btrfs/tree-checker.h
+++ b/fs/btrfs/tree-checker.h
@@ -22,7 +22,7 @@ struct btrfs_tree_parent_check {
 
 	/*
 	 * Expected transid, can be 0 to skip the check, but such skip
-	 * should only be utlized for backref walk related code.
+	 * should only be utilized for backref walk related code.
 	 */
 	u64 transid;
 
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 7d6729d9fd2f..331fc7429952 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2575,7 +2575,6 @@ static int clean_log_buffer(struct btrfs_trans_handle *trans,
 		ret = btrfs_pin_reserved_extent(trans, eb);
 		if (ret)
 			return ret;
-		btrfs_redirty_list_add(trans->transaction, eb);
 	} else {
 		unaccount_log_buffer(eb->fs_info, eb->start);
 	}
@@ -4520,7 +4519,7 @@ static int log_extent_csums(struct btrfs_trans_handle *trans,
 	int ret = 0;
 
 	if (inode->flags & BTRFS_INODE_NODATASUM ||
-	    test_bit(EXTENT_FLAG_PREALLOC, &em->flags) ||
+	    (em->flags & EXTENT_FLAG_PREALLOC) ||
 	    em->block_start == EXTENT_MAP_HOLE)
 		return 0;
 
@@ -4583,7 +4582,7 @@ static int log_extent_csums(struct btrfs_trans_handle *trans,
 		return 0;
 
 	/* If we're compressed we have to save the entire range of csums. */
-	if (em->compress_type) {
+	if (extent_map_is_compressed(em)) {
 		csum_offset = 0;
 		csum_len = max(em->block_len, em->orig_block_len);
 	} else {
@@ -4623,18 +4622,20 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 	struct btrfs_file_extent_item fi = { 0 };
 	struct extent_buffer *leaf;
 	struct btrfs_key key;
+	enum btrfs_compression_type compress_type;
 	u64 extent_offset = em->start - em->orig_start;
 	u64 block_len;
 	int ret;
 
 	btrfs_set_stack_file_extent_generation(&fi, trans->transid);
-	if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+	if (em->flags & EXTENT_FLAG_PREALLOC)
 		btrfs_set_stack_file_extent_type(&fi, BTRFS_FILE_EXTENT_PREALLOC);
 	else
 		btrfs_set_stack_file_extent_type(&fi, BTRFS_FILE_EXTENT_REG);
 
 	block_len = max(em->block_len, em->orig_block_len);
-	if (em->compress_type != BTRFS_COMPRESS_NONE) {
+	compress_type = extent_map_compression(em);
+	if (compress_type != BTRFS_COMPRESS_NONE) {
 		btrfs_set_stack_file_extent_disk_bytenr(&fi, em->block_start);
 		btrfs_set_stack_file_extent_disk_num_bytes(&fi, block_len);
 	} else if (em->block_start < EXTENT_MAP_LAST_BYTE) {
@@ -4646,7 +4647,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 	btrfs_set_stack_file_extent_offset(&fi, extent_offset);
 	btrfs_set_stack_file_extent_num_bytes(&fi, em->len);
 	btrfs_set_stack_file_extent_ram_bytes(&fi, em->ram_bytes);
-	btrfs_set_stack_file_extent_compression(&fi, em->compress_type);
+	btrfs_set_stack_file_extent_compression(&fi, compress_type);
 
 	ret = log_extent_csums(trans, inode, log, em, ctx);
 	if (ret)
@@ -4859,13 +4860,13 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 			continue;
 
 		/* We log prealloc extents beyond eof later. */
-		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) &&
+		if ((em->flags & EXTENT_FLAG_PREALLOC) &&
 		    em->start >= i_size_read(&inode->vfs_inode))
 			continue;
 
 		/* Need a ref to keep it from getting evicted from cache */
 		refcount_inc(&em->refs);
-		set_bit(EXTENT_FLAG_LOGGING, &em->flags);
+		em->flags |= EXTENT_FLAG_LOGGING;
 		list_add_tail(&em->list, &extents);
 		num++;
 	}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index c87e18827a0a..4c32497311d2 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -41,6 +41,17 @@
 					 BTRFS_BLOCK_GROUP_RAID10 | \
 					 BTRFS_BLOCK_GROUP_RAID56_MASK)
 
+struct btrfs_io_geometry {
+	u32 stripe_index;
+	u32 stripe_nr;
+	int mirror_num;
+	int num_stripes;
+	u64 stripe_offset;
+	u64 raid56_full_stripe_start;
+	int max_errors;
+	enum btrfs_map_op op;
+};
+
 const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
 	[BTRFS_RAID_RAID10] = {
 		.sub_stripes	= 2,
@@ -748,13 +759,13 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 
 	if (!fs_devices) {
 		fs_devices = alloc_fs_devices(disk_super->fsid);
+		if (IS_ERR(fs_devices))
+			return ERR_CAST(fs_devices);
+
 		if (has_metadata_uuid)
 			memcpy(fs_devices->metadata_uuid,
 			       disk_super->metadata_uuid, BTRFS_FSID_SIZE);
 
-		if (IS_ERR(fs_devices))
-			return ERR_CAST(fs_devices);
-
 		if (same_fsid_diff_dev) {
 			generate_random_uuid(fs_devices->fsid);
 			fs_devices->temp_fsid = true;
@@ -1742,19 +1753,18 @@ out:
 
 static u64 find_next_chunk(struct btrfs_fs_info *fs_info)
 {
-	struct extent_map_tree *em_tree;
-	struct extent_map *em;
 	struct rb_node *n;
 	u64 ret = 0;
 
-	em_tree = &fs_info->mapping_tree;
-	read_lock(&em_tree->lock);
-	n = rb_last(&em_tree->map.rb_root);
+	read_lock(&fs_info->mapping_tree_lock);
+	n = rb_last(&fs_info->mapping_tree.rb_root);
 	if (n) {
-		em = rb_entry(n, struct extent_map, rb_node);
-		ret = em->start + em->len;
+		struct btrfs_chunk_map *map;
+
+		map = rb_entry(n, struct btrfs_chunk_map, rb_node);
+		ret = map->start + map->chunk_len;
 	}
-	read_unlock(&em_tree->lock);
+	read_unlock(&fs_info->mapping_tree_lock);
 
 	return ret;
 }
@@ -2986,6 +2996,81 @@ static int btrfs_del_sys_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset)
 	return ret;
 }
 
+struct btrfs_chunk_map *btrfs_find_chunk_map_nolock(struct btrfs_fs_info *fs_info,
+						    u64 logical, u64 length)
+{
+	struct rb_node *node = fs_info->mapping_tree.rb_root.rb_node;
+	struct rb_node *prev = NULL;
+	struct rb_node *orig_prev;
+	struct btrfs_chunk_map *map;
+	struct btrfs_chunk_map *prev_map = NULL;
+
+	while (node) {
+		map = rb_entry(node, struct btrfs_chunk_map, rb_node);
+		prev = node;
+		prev_map = map;
+
+		if (logical < map->start) {
+			node = node->rb_left;
+		} else if (logical >= map->start + map->chunk_len) {
+			node = node->rb_right;
+		} else {
+			refcount_inc(&map->refs);
+			return map;
+		}
+	}
+
+	if (!prev)
+		return NULL;
+
+	orig_prev = prev;
+	while (prev && logical >= prev_map->start + prev_map->chunk_len) {
+		prev = rb_next(prev);
+		prev_map = rb_entry(prev, struct btrfs_chunk_map, rb_node);
+	}
+
+	if (!prev) {
+		prev = orig_prev;
+		prev_map = rb_entry(prev, struct btrfs_chunk_map, rb_node);
+		while (prev && logical < prev_map->start) {
+			prev = rb_prev(prev);
+			prev_map = rb_entry(prev, struct btrfs_chunk_map, rb_node);
+		}
+	}
+
+	if (prev) {
+		u64 end = logical + length;
+
+		/*
+		 * Caller can pass a U64_MAX length when it wants to get any
+		 * chunk starting at an offset of 'logical' or higher, so deal
+		 * with underflow by resetting the end offset to U64_MAX.
+		 */
+		if (end < logical)
+			end = U64_MAX;
+
+		if (end > prev_map->start &&
+		    logical < prev_map->start + prev_map->chunk_len) {
+			refcount_inc(&prev_map->refs);
+			return prev_map;
+		}
+	}
+
+	return NULL;
+}
+
+struct btrfs_chunk_map *btrfs_find_chunk_map(struct btrfs_fs_info *fs_info,
+					     u64 logical, u64 length)
+{
+	struct btrfs_chunk_map *map;
+
+	read_lock(&fs_info->mapping_tree_lock);
+	map = btrfs_find_chunk_map_nolock(fs_info, logical, length);
+	read_unlock(&fs_info->mapping_tree_lock);
+
+	return map;
+}
+
 /*
  * Find the mapping containing the given logical extent.
  *
@@ -2994,37 +3079,37 @@ static int btrfs_del_sys_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset)
  *
  * Return: Chunk mapping or ERR_PTR.
  */
-struct extent_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
-				       u64 logical, u64 length)
+struct btrfs_chunk_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
+					    u64 logical, u64 length)
 {
-	struct extent_map_tree *em_tree;
-	struct extent_map *em;
+	struct btrfs_chunk_map *map;
 
-	em_tree = &fs_info->mapping_tree;
-	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, logical, length);
-	read_unlock(&em_tree->lock);
+	map = btrfs_find_chunk_map(fs_info, logical, length);
 
-	if (!em) {
-		btrfs_crit(fs_info, "unable to find logical %llu length %llu",
+	if (unlikely(!map)) {
+		read_unlock(&fs_info->mapping_tree_lock);
+		btrfs_crit(fs_info,
+			   "unable to find chunk map for logical %llu length %llu",
 			   logical, length);
 		return ERR_PTR(-EINVAL);
 	}
 
-	if (em->start > logical || em->start + em->len < logical) {
+	if (unlikely(map->start > logical || map->start + map->chunk_len <= logical)) {
+		read_unlock(&fs_info->mapping_tree_lock);
 		btrfs_crit(fs_info,
-			   "found a bad mapping, wanted %llu-%llu, found %llu-%llu",
-			   logical, length, em->start, em->start + em->len);
-		free_extent_map(em);
+			   "found a bad chunk map, wanted %llu-%llu, found %llu-%llu",
+			   logical, logical + length, map->start,
+			   map->start + map->chunk_len);
+		btrfs_free_chunk_map(map);
 		return ERR_PTR(-EINVAL);
 	}
 
-	/* callers are responsible for dropping em's ref. */
-	return em;
+	/* Callers are responsible for dropping the reference. */
+	return map;
 }
 
 static int remove_chunk_item(struct btrfs_trans_handle *trans,
-			     struct map_lookup *map, u64 chunk_offset)
+			     struct btrfs_chunk_map *map, u64 chunk_offset)
 {
 	int i;
 
@@ -3049,23 +3134,21 @@ static int remove_chunk_item(struct btrfs_trans_handle *trans,
 int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	u64 dev_extent_len = 0;
 	int i, ret = 0;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 
-	em = btrfs_get_chunk_map(fs_info, chunk_offset, 1);
-	if (IS_ERR(em)) {
+	map = btrfs_get_chunk_map(fs_info, chunk_offset, 1);
+	if (IS_ERR(map)) {
 		/*
 		 * This is a logic error, but we don't want to just rely on the
 		 * user having built with ASSERT enabled, so if ASSERT doesn't
 		 * do anything we still error out.
 		 */
 		ASSERT(0);
-		return PTR_ERR(em);
+		return PTR_ERR(map);
 	}
-	map = em->map_lookup;
 
 	/*
 	 * First delete the device extent items from the devices btree.
@@ -3168,7 +3251,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset)
 		goto out;
 	}
 
-	trace_btrfs_chunk_free(fs_info, map, chunk_offset, em->len);
+	trace_btrfs_chunk_free(fs_info, map, chunk_offset, map->chunk_len);
 
 	if (map->type & BTRFS_BLOCK_GROUP_SYSTEM) {
 		ret = btrfs_del_sys_chunk(fs_info, chunk_offset);
@@ -3187,7 +3270,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset)
 	 */
 	btrfs_trans_release_chunk_metadata(trans);
 
-	ret = btrfs_remove_block_group(trans, chunk_offset, em);
+	ret = btrfs_remove_block_group(trans, map);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto out;
@@ -3199,7 +3282,7 @@ out:
 		trans->removing_chunk = false;
 	}
 	/* once for us */
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 	return ret;
 }
 
@@ -5346,24 +5429,131 @@ static int decide_stripe_size(struct btrfs_fs_devices *fs_devices,
 	}
 }
 
+static void chunk_map_device_set_bits(struct btrfs_chunk_map *map, unsigned int bits)
+{
+	for (int i = 0; i < map->num_stripes; i++) {
+		struct btrfs_io_stripe *stripe = &map->stripes[i];
+		struct btrfs_device *device = stripe->dev;
+
+		set_extent_bit(&device->alloc_state, stripe->physical,
+			       stripe->physical + map->stripe_size - 1,
+			       bits | EXTENT_NOWAIT, NULL);
+	}
+}
+
+static void chunk_map_device_clear_bits(struct btrfs_chunk_map *map, unsigned int bits)
+{
+	for (int i = 0; i < map->num_stripes; i++) {
+		struct btrfs_io_stripe *stripe = &map->stripes[i];
+		struct btrfs_device *device = stripe->dev;
+
+		__clear_extent_bit(&device->alloc_state, stripe->physical,
+				   stripe->physical + map->stripe_size - 1,
+				   bits | EXTENT_NOWAIT,
+				   NULL, NULL);
+	}
+}
+
+void btrfs_remove_chunk_map(struct btrfs_fs_info *fs_info, struct btrfs_chunk_map *map)
+{
+	write_lock(&fs_info->mapping_tree_lock);
+	rb_erase_cached(&map->rb_node, &fs_info->mapping_tree);
+	RB_CLEAR_NODE(&map->rb_node);
+	chunk_map_device_clear_bits(map, CHUNK_ALLOCATED);
+	write_unlock(&fs_info->mapping_tree_lock);
+
+	/* Once for the tree reference. */
+	btrfs_free_chunk_map(map);
+}
+
+EXPORT_FOR_TESTS
+int btrfs_add_chunk_map(struct btrfs_fs_info *fs_info, struct btrfs_chunk_map *map)
+{
+	struct rb_node **p;
+	struct rb_node *parent = NULL;
+	bool leftmost = true;
+
+	write_lock(&fs_info->mapping_tree_lock);
+	p = &fs_info->mapping_tree.rb_root.rb_node;
+	while (*p) {
+		struct btrfs_chunk_map *entry;
+
+		parent = *p;
+		entry = rb_entry(parent, struct btrfs_chunk_map, rb_node);
+
+		if (map->start < entry->start) {
+			p = &(*p)->rb_left;
+		} else if (map->start > entry->start) {
+			p = &(*p)->rb_right;
+			leftmost = false;
+		} else {
+			write_unlock(&fs_info->mapping_tree_lock);
+			return -EEXIST;
+		}
+	}
+	rb_link_node(&map->rb_node, parent, p);
+	rb_insert_color_cached(&map->rb_node, &fs_info->mapping_tree, leftmost);
+	chunk_map_device_set_bits(map, CHUNK_ALLOCATED);
+	chunk_map_device_clear_bits(map, CHUNK_TRIMMED);
+	write_unlock(&fs_info->mapping_tree_lock);
+
+	return 0;
+}
+
+EXPORT_FOR_TESTS
+struct btrfs_chunk_map *btrfs_alloc_chunk_map(int num_stripes, gfp_t gfp)
+{
+	struct btrfs_chunk_map *map;
+
+	map = kmalloc(btrfs_chunk_map_size(num_stripes), gfp);
+	if (!map)
+		return NULL;
+
+	refcount_set(&map->refs, 1);
+	RB_CLEAR_NODE(&map->rb_node);
+
+	return map;
+}
+
+struct btrfs_chunk_map *btrfs_clone_chunk_map(struct btrfs_chunk_map *map, gfp_t gfp)
+{
+	const int size = btrfs_chunk_map_size(map->num_stripes);
+	struct btrfs_chunk_map *clone;
+
+	clone = kmemdup(map, size, gfp);
+	if (!clone)
+		return NULL;
+
+	refcount_set(&clone->refs, 1);
+	RB_CLEAR_NODE(&clone->rb_node);
+
+	return clone;
+}
+
 static struct btrfs_block_group *create_chunk(struct btrfs_trans_handle *trans,
 			struct alloc_chunk_ctl *ctl,
 			struct btrfs_device_info *devices_info)
 {
 	struct btrfs_fs_info *info = trans->fs_info;
-	struct map_lookup *map = NULL;
-	struct extent_map_tree *em_tree;
+	struct btrfs_chunk_map *map;
 	struct btrfs_block_group *block_group;
-	struct extent_map *em;
 	u64 start = ctl->start;
 	u64 type = ctl->type;
 	int ret;
 	int i;
 	int j;
 
-	map = kmalloc(map_lookup_size(ctl->num_stripes), GFP_NOFS);
+	map = btrfs_alloc_chunk_map(ctl->num_stripes, GFP_NOFS);
 	if (!map)
 		return ERR_PTR(-ENOMEM);
+
+	map->start = start;
+	map->chunk_len = ctl->chunk_size;
+	map->stripe_size = ctl->stripe_size;
+	map->type = type;
+	map->io_align = BTRFS_STRIPE_LEN;
+	map->io_width = BTRFS_STRIPE_LEN;
+	map->sub_stripes = ctl->sub_stripes;
 	map->num_stripes = ctl->num_stripes;
 
 	for (i = 0; i < ctl->ndevs; ++i) {
@@ -5374,41 +5564,22 @@ static struct btrfs_block_group *create_chunk(struct btrfs_trans_handle *trans,
 						   j * ctl->stripe_size;
 		}
 	}
-	map->io_align = BTRFS_STRIPE_LEN;
-	map->io_width = BTRFS_STRIPE_LEN;
-	map->type = type;
-	map->sub_stripes = ctl->sub_stripes;
 
 	trace_btrfs_chunk_alloc(info, map, start, ctl->chunk_size);
 
-	em = alloc_extent_map();
-	if (!em) {
-		kfree(map);
-		return ERR_PTR(-ENOMEM);
-	}
-	set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
-	em->map_lookup = map;
-	em->start = start;
-	em->len = ctl->chunk_size;
-	em->block_start = 0;
-	em->block_len = em->len;
-	em->orig_block_len = ctl->stripe_size;
-
-	em_tree = &info->mapping_tree;
-	write_lock(&em_tree->lock);
-	ret = add_extent_mapping(em_tree, em, 0);
+	ret = btrfs_add_chunk_map(info, map);
 	if (ret) {
-		write_unlock(&em_tree->lock);
-		free_extent_map(em);
+		btrfs_free_chunk_map(map);
 		return ERR_PTR(ret);
 	}
-	write_unlock(&em_tree->lock);
 
 	block_group = btrfs_make_block_group(trans, type, start, ctl->chunk_size);
-	if (IS_ERR(block_group))
-		goto error_del_extent;
+	if (IS_ERR(block_group)) {
+		btrfs_remove_chunk_map(info, map);
+		return block_group;
+	}
 
-	for (i = 0; i < map->num_stripes; i++) {
+	for (int i = 0; i < map->num_stripes; i++) {
 		struct btrfs_device *dev = map->stripes[i].dev;
 
 		btrfs_device_set_bytes_used(dev,
@@ -5421,23 +5592,10 @@ static struct btrfs_block_group *create_chunk(struct btrfs_trans_handle *trans,
 	atomic64_sub(ctl->stripe_size * map->num_stripes,
 		     &info->free_chunk_space);
 
-	free_extent_map(em);
 	check_raid56_incompat_flag(info, type);
 	check_raid1c34_incompat_flag(info, type);
 
 	return block_group;
-
-error_del_extent:
-	write_lock(&em_tree->lock);
-	remove_extent_mapping(em_tree, em);
-	write_unlock(&em_tree->lock);
-
-	/* One for our allocation */
-	free_extent_map(em);
-	/* One for the tree reference */
-	free_extent_map(em);
-
-	return block_group;
 }
 
 struct btrfs_block_group *btrfs_create_chunk(struct btrfs_trans_handle *trans,
@@ -5513,8 +5671,7 @@ int btrfs_chunk_alloc_add_chunk_item(struct btrfs_trans_handle *trans,
 	struct btrfs_key key;
 	struct btrfs_chunk *chunk;
 	struct btrfs_stripe *stripe;
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	size_t item_size;
 	int i;
 	int ret;
@@ -5543,14 +5700,13 @@ int btrfs_chunk_alloc_add_chunk_item(struct btrfs_trans_handle *trans,
 	 */
 	lockdep_assert_held(&fs_info->chunk_mutex);
 
-	em = btrfs_get_chunk_map(fs_info, bg->start, bg->length);
-	if (IS_ERR(em)) {
-		ret = PTR_ERR(em);
+	map = btrfs_get_chunk_map(fs_info, bg->start, bg->length);
+	if (IS_ERR(map)) {
+		ret = PTR_ERR(map);
 		btrfs_abort_transaction(trans, ret);
 		return ret;
 	}
 
-	map = em->map_lookup;
 	item_size = btrfs_chunk_item_size(map->num_stripes);
 
 	chunk = kzalloc(item_size, GFP_NOFS);
@@ -5607,7 +5763,7 @@ int btrfs_chunk_alloc_add_chunk_item(struct btrfs_trans_handle *trans,
 
 out:
 	kfree(chunk);
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 	return ret;
 }
 
@@ -5652,7 +5808,7 @@ static noinline int init_first_rw_device(struct btrfs_trans_handle *trans)
 	return 0;
 }
 
-static inline int btrfs_chunk_max_errors(struct map_lookup *map)
+static inline int btrfs_chunk_max_errors(struct btrfs_chunk_map *map)
 {
 	const int index = btrfs_bg_flags_to_raid_index(map->type);
 
@@ -5661,17 +5817,15 @@ static inline int btrfs_chunk_max_errors(struct map_lookup *map)
 
 bool btrfs_chunk_writeable(struct btrfs_fs_info *fs_info, u64 chunk_offset)
 {
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	int miss_ndevs = 0;
 	int i;
 	bool ret = true;
 
-	em = btrfs_get_chunk_map(fs_info, chunk_offset, 1);
-	if (IS_ERR(em))
+	map = btrfs_get_chunk_map(fs_info, chunk_offset, 1);
+	if (IS_ERR(map))
 		return false;
 
-	map = em->map_lookup;
 	for (i = 0; i < map->num_stripes; i++) {
 		if (test_bit(BTRFS_DEV_STATE_MISSING,
 					&map->stripes[i].dev->dev_state)) {
@@ -5692,38 +5846,37 @@ bool btrfs_chunk_writeable(struct btrfs_fs_info *fs_info, u64 chunk_offset)
 	if (miss_ndevs > btrfs_chunk_max_errors(map))
 		ret = false;
 end:
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 	return ret;
 }
 
-void btrfs_mapping_tree_free(struct extent_map_tree *tree)
+void btrfs_mapping_tree_free(struct btrfs_fs_info *fs_info)
 {
-	struct extent_map *em;
+	write_lock(&fs_info->mapping_tree_lock);
+	while (!RB_EMPTY_ROOT(&fs_info->mapping_tree.rb_root)) {
+		struct btrfs_chunk_map *map;
+		struct rb_node *node;
 
-	while (1) {
-		write_lock(&tree->lock);
-		em = lookup_extent_mapping(tree, 0, (u64)-1);
-		if (em)
-			remove_extent_mapping(tree, em);
-		write_unlock(&tree->lock);
-		if (!em)
-			break;
-		/* once for us */
-		free_extent_map(em);
-		/* once for the tree */
-		free_extent_map(em);
+		node = rb_first_cached(&fs_info->mapping_tree);
+		map = rb_entry(node, struct btrfs_chunk_map, rb_node);
+		rb_erase_cached(&map->rb_node, &fs_info->mapping_tree);
+		RB_CLEAR_NODE(&map->rb_node);
+		chunk_map_device_clear_bits(map, CHUNK_ALLOCATED);
+		/* Once for the tree ref. */
+		btrfs_free_chunk_map(map);
+		cond_resched_rwlock_write(&fs_info->mapping_tree_lock);
 	}
+	write_unlock(&fs_info->mapping_tree_lock);
 }
 
 int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 {
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	enum btrfs_raid_types index;
 	int ret = 1;
 
-	em = btrfs_get_chunk_map(fs_info, logical, len);
-	if (IS_ERR(em))
+	map = btrfs_get_chunk_map(fs_info, logical, len);
+	if (IS_ERR(map))
 		/*
 		 * We could return errors for these cases, but that could get
 		 * ugly and we'd probably do the same thing which is just not do
@@ -5732,7 +5885,6 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 		 */
 		return 1;
 
-	map = em->map_lookup;
 	index = btrfs_bg_flags_to_raid_index(map->type);
 
 	/* Non-RAID56, use their ncopies from btrfs_raid_array. */
@@ -5749,53 +5901,49 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 		 * stripe under reconstruction.
 		 */
 		ret = map->num_stripes;
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 	return ret;
 }
 
 unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info,
 				    u64 logical)
 {
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	unsigned long len = fs_info->sectorsize;
 
 	if (!btrfs_fs_incompat(fs_info, RAID56))
 		return len;
 
-	em = btrfs_get_chunk_map(fs_info, logical, len);
+	map = btrfs_get_chunk_map(fs_info, logical, len);
 
-	if (!WARN_ON(IS_ERR(em))) {
-		map = em->map_lookup;
+	if (!WARN_ON(IS_ERR(map))) {
 		if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
 			len = btrfs_stripe_nr_to_offset(nr_data_stripes(map));
-		free_extent_map(em);
+		btrfs_free_chunk_map(map);
 	}
 	return len;
 }
 
 int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 {
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	int ret = 0;
 
 	if (!btrfs_fs_incompat(fs_info, RAID56))
 		return 0;
 
-	em = btrfs_get_chunk_map(fs_info, logical, len);
+	map = btrfs_get_chunk_map(fs_info, logical, len);
 
-	if(!WARN_ON(IS_ERR(em))) {
-		map = em->map_lookup;
+	if (!WARN_ON(IS_ERR(map))) {
 		if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
 			ret = 1;
-		free_extent_map(em);
+		btrfs_free_chunk_map(map);
 	}
 	return ret;
 }
 
 static int find_live_mirror(struct btrfs_fs_info *fs_info,
-			    struct map_lookup *map, int first,
+			    struct btrfs_chunk_map *map, int first,
 			    int dev_replace_is_ongoing)
 {
 	int i;
@@ -5902,8 +6050,7 @@ struct btrfs_discard_stripe *btrfs_map_discard(struct btrfs_fs_info *fs_info,
 					       u64 logical, u64 *length_ret,
 					       u32 *num_stripes)
 {
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	struct btrfs_discard_stripe *stripes;
 	u64 length = *length_ret;
 	u64 offset;
@@ -5921,11 +6068,9 @@ struct btrfs_discard_stripe *btrfs_map_discard(struct btrfs_fs_info *fs_info,
 	int ret;
 	int i;
 
-	em = btrfs_get_chunk_map(fs_info, logical, length);
-	if (IS_ERR(em))
-		return ERR_CAST(em);
-
-	map = em->map_lookup;
+	map = btrfs_get_chunk_map(fs_info, logical, length);
+	if (IS_ERR(map))
+		return ERR_CAST(map);
 
 	/* we don't discard raid56 yet */
 	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
@@ -5933,8 +6078,8 @@ struct btrfs_discard_stripe *btrfs_map_discard(struct btrfs_fs_info *fs_info,
 		goto out_free_map;
 	}
 
-	offset = logical - em->start;
-	length = min_t(u64, em->start + em->len - logical, length);
+	offset = logical - map->start;
+	length = min_t(u64, map->start + map->chunk_len - logical, length);
 	*length_ret = length;
 
 	/*
@@ -6031,10 +6176,10 @@ struct btrfs_discard_stripe *btrfs_map_discard(struct btrfs_fs_info *fs_info,
 		}
 	}
 
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 	return stripes;
 out_free_map:
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 	return ERR_PTR(ret);
 }
 
@@ -6132,17 +6277,16 @@ static void handle_ops_on_dev_replace(enum btrfs_map_op op,
 	bioc->replace_nr_stripes = nr_extra_stripes;
 }
 
-static u64 btrfs_max_io_len(struct map_lookup *map, enum btrfs_map_op op,
-			    u64 offset, u32 *stripe_nr, u64 *stripe_offset,
-			    u64 *full_stripe_start)
+static u64 btrfs_max_io_len(struct btrfs_chunk_map *map, u64 offset,
+			    struct btrfs_io_geometry *io_geom)
 {
 	/*
 	 * Stripe_nr is the stripe where this block falls.  stripe_offset is
 	 * the offset of this block in its stripe.
 	 */
-	*stripe_offset = offset & BTRFS_STRIPE_LEN_MASK;
-	*stripe_nr = offset >> BTRFS_STRIPE_LEN_SHIFT;
-	ASSERT(*stripe_offset < U32_MAX);
+	io_geom->stripe_offset = offset & BTRFS_STRIPE_LEN_MASK;
+	io_geom->stripe_nr = offset >> BTRFS_STRIPE_LEN_SHIFT;
+	ASSERT(io_geom->stripe_offset < U32_MAX);
 
 	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
 		unsigned long full_stripe_len =
@@ -6157,18 +6301,17 @@ static u64 btrfs_max_io_len(struct map_lookup *map, enum btrfs_map_op op,
 		 * to go rounddown(), not round_down(), as nr_data_stripes is
 		 * not ensured to be power of 2.
 		 */
-		*full_stripe_start =
-			btrfs_stripe_nr_to_offset(
-				rounddown(*stripe_nr, nr_data_stripes(map)));
+		io_geom->raid56_full_stripe_start = btrfs_stripe_nr_to_offset(
+			rounddown(io_geom->stripe_nr, nr_data_stripes(map)));
 
-		ASSERT(*full_stripe_start + full_stripe_len > offset);
-		ASSERT(*full_stripe_start <= offset);
+		ASSERT(io_geom->raid56_full_stripe_start + full_stripe_len > offset);
+		ASSERT(io_geom->raid56_full_stripe_start <= offset);
 		/*
 		 * For writes to RAID56, allow to write a full stripe set, but
 		 * no straddling of stripe sets.
 		 */
-		if (op == BTRFS_MAP_WRITE)
-			return full_stripe_len - (offset - *full_stripe_start);
+		if (io_geom->op == BTRFS_MAP_WRITE)
+			return full_stripe_len - (offset - io_geom->raid56_full_stripe_start);
 	}
 
 	/*
@@ -6176,26 +6319,180 @@ static u64 btrfs_max_io_len(struct map_lookup *map, enum btrfs_map_op op,
 	 * a single disk).
 	 */
 	if (map->type & BTRFS_BLOCK_GROUP_STRIPE_MASK)
-		return BTRFS_STRIPE_LEN - *stripe_offset;
+		return BTRFS_STRIPE_LEN - io_geom->stripe_offset;
 	return U64_MAX;
 }
 
-static int set_io_stripe(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
-			 u64 logical, u64 *length, struct btrfs_io_stripe *dst,
-			 struct map_lookup *map, u32 stripe_index,
-			 u64 stripe_offset, u64 stripe_nr)
+static int set_io_stripe(struct btrfs_fs_info *fs_info, u64 logical,
+			 u64 *length, struct btrfs_io_stripe *dst,
+			 struct btrfs_chunk_map *map,
+			 struct btrfs_io_geometry *io_geom)
 {
-	dst->dev = map->stripes[stripe_index].dev;
+	dst->dev = map->stripes[io_geom->stripe_index].dev;
 
-	if (op == BTRFS_MAP_READ && btrfs_need_stripe_tree_update(fs_info, map->type))
+	if (io_geom->op == BTRFS_MAP_READ &&
+	    btrfs_need_stripe_tree_update(fs_info, map->type))
 		return btrfs_get_raid_extent_offset(fs_info, logical, length,
-						    map->type, stripe_index, dst);
+						    map->type,
+						    io_geom->stripe_index, dst);
 
-	dst->physical = map->stripes[stripe_index].physical +
-			stripe_offset + btrfs_stripe_nr_to_offset(stripe_nr);
+	dst->physical = map->stripes[io_geom->stripe_index].physical +
+			io_geom->stripe_offset +
+			btrfs_stripe_nr_to_offset(io_geom->stripe_nr);
 	return 0;
 }
 
+static bool is_single_device_io(struct btrfs_fs_info *fs_info,
+				const struct btrfs_io_stripe *smap,
+				const struct btrfs_chunk_map *map,
+				int num_alloc_stripes,
+				enum btrfs_map_op op, int mirror_num)
+{
+	if (!smap)
+		return false;
+
+	if (num_alloc_stripes != 1)
+		return false;
+
+	if (btrfs_need_stripe_tree_update(fs_info, map->type) && op != BTRFS_MAP_READ)
+		return false;
+
+	if ((map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) && mirror_num > 1)
+		return false;
+
+	return true;
+}
+
+static void map_blocks_raid0(const struct btrfs_chunk_map *map,
+			     struct btrfs_io_geometry *io_geom)
+{
+	io_geom->stripe_index = io_geom->stripe_nr % map->num_stripes;
+	io_geom->stripe_nr /= map->num_stripes;
+	if (io_geom->op == BTRFS_MAP_READ)
+		io_geom->mirror_num = 1;
+}
+
+static void map_blocks_raid1(struct btrfs_fs_info *fs_info,
+			     struct btrfs_chunk_map *map,
+			     struct btrfs_io_geometry *io_geom,
+			     bool dev_replace_is_ongoing)
+{
+	if (io_geom->op != BTRFS_MAP_READ) {
+		io_geom->num_stripes = map->num_stripes;
+		return;
+	}
+
+	if (io_geom->mirror_num) {
+		io_geom->stripe_index = io_geom->mirror_num - 1;
+		return;
+	}
+
+	io_geom->stripe_index = find_live_mirror(fs_info, map, 0,
+						 dev_replace_is_ongoing);
+	io_geom->mirror_num = io_geom->stripe_index + 1;
+}
+
+static void map_blocks_dup(const struct btrfs_chunk_map *map,
+			   struct btrfs_io_geometry *io_geom)
+{
+	if (io_geom->op != BTRFS_MAP_READ) {
+		io_geom->num_stripes = map->num_stripes;
+		return;
+	}
+
+	if (io_geom->mirror_num) {
+		io_geom->stripe_index = io_geom->mirror_num - 1;
+		return;
+	}
+
+	io_geom->mirror_num = 1;
+}
+
+static void map_blocks_raid10(struct btrfs_fs_info *fs_info,
+			      struct btrfs_chunk_map *map,
+			      struct btrfs_io_geometry *io_geom,
+			      bool dev_replace_is_ongoing)
+{
+	u32 factor = map->num_stripes / map->sub_stripes;
+	int old_stripe_index;
+
+	io_geom->stripe_index = (io_geom->stripe_nr % factor) * map->sub_stripes;
+	io_geom->stripe_nr /= factor;
+
+	if (io_geom->op != BTRFS_MAP_READ) {
+		io_geom->num_stripes = map->sub_stripes;
+		return;
+	}
+
+	if (io_geom->mirror_num) {
+		io_geom->stripe_index += io_geom->mirror_num - 1;
+		return;
+	}
+
+	old_stripe_index = io_geom->stripe_index;
+	io_geom->stripe_index = find_live_mirror(fs_info, map,
+						 io_geom->stripe_index,
+						 dev_replace_is_ongoing);
+	io_geom->mirror_num = io_geom->stripe_index - old_stripe_index + 1;
+}
+
+static void map_blocks_raid56_write(struct btrfs_chunk_map *map,
+				    struct btrfs_io_geometry *io_geom,
+				    u64 logical, u64 *length)
+{
+	int data_stripes = nr_data_stripes(map);
+
+	/*
+	 * Needs full stripe mapping.
+	 *
+	 * Push stripe_nr back to the start of the full stripe For those cases
+	 * needing a full stripe, @stripe_nr is the full stripe number.
+	 *
+	 * Originally we go raid56_full_stripe_start / full_stripe_len, but
+	 * that can be expensive.  Here we just divide @stripe_nr with
+	 * @data_stripes.
+	 */
+	io_geom->stripe_nr /= data_stripes;
+
+	/* RAID[56] write or recovery. Return all stripes */
+	io_geom->num_stripes = map->num_stripes;
+	io_geom->max_errors = btrfs_chunk_max_errors(map);
+
+	/* Return the length to the full stripe end. */
+	*length = min(logical + *length,
+		      io_geom->raid56_full_stripe_start + map->start +
+		      btrfs_stripe_nr_to_offset(data_stripes)) -
+		logical;
+	io_geom->stripe_index = 0;
+	io_geom->stripe_offset = 0;
+}
+
+static void map_blocks_raid56_read(struct btrfs_chunk_map *map,
+				   struct btrfs_io_geometry *io_geom)
+{
+	int data_stripes = nr_data_stripes(map);
+
+	ASSERT(io_geom->mirror_num <= 1);
+	/* Just grab the data stripe directly. */
+	io_geom->stripe_index = io_geom->stripe_nr % data_stripes;
+	io_geom->stripe_nr /= data_stripes;
+
+	/* We distribute the parity blocks across stripes. */
+	io_geom->stripe_index =
+		(io_geom->stripe_nr + io_geom->stripe_index) % map->num_stripes;
+
+	if (io_geom->op == BTRFS_MAP_READ && io_geom->mirror_num < 1)
+		io_geom->mirror_num = 1;
+}
+
+static void map_blocks_single(const struct btrfs_chunk_map *map,
+			      struct btrfs_io_geometry *io_geom)
+{
+	io_geom->stripe_index = io_geom->stripe_nr % map->num_stripes;
+	io_geom->stripe_nr /= map->num_stripes;
+	io_geom->mirror_num = io_geom->stripe_index + 1;
+}
+
 /*
  * Map one logical range to one or more physical ranges.
  *
@@ -6236,43 +6533,37 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 		    struct btrfs_io_context **bioc_ret,
 		    struct btrfs_io_stripe *smap, int *mirror_num_ret)
 {
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
+	struct btrfs_io_geometry io_geom = { 0 };
 	u64 map_offset;
-	u64 stripe_offset;
-	u32 stripe_nr;
-	u32 stripe_index;
-	int data_stripes;
 	int i;
 	int ret = 0;
-	int mirror_num = (mirror_num_ret ? *mirror_num_ret : 0);
-	int num_stripes;
 	int num_copies;
-	int max_errors = 0;
 	struct btrfs_io_context *bioc = NULL;
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
 	int dev_replace_is_ongoing = 0;
 	u16 num_alloc_stripes;
-	u64 raid56_full_stripe_start = (u64)-1;
 	u64 max_len;
 
 	ASSERT(bioc_ret);
 
+	io_geom.mirror_num = (mirror_num_ret ? *mirror_num_ret : 0);
+	io_geom.num_stripes = 1;
+	io_geom.stripe_index = 0;
+	io_geom.op = op;
+
 	num_copies = btrfs_num_copies(fs_info, logical, fs_info->sectorsize);
-	if (mirror_num > num_copies)
+	if (io_geom.mirror_num > num_copies)
 		return -EINVAL;
 
-	em = btrfs_get_chunk_map(fs_info, logical, *length);
-	if (IS_ERR(em))
-		return PTR_ERR(em);
+	map = btrfs_get_chunk_map(fs_info, logical, *length);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
 
-	map = em->map_lookup;
-	data_stripes = nr_data_stripes(map);
-
-	map_offset = logical - em->start;
-	max_len = btrfs_max_io_len(map, op, map_offset, &stripe_nr,
-				   &stripe_offset, &raid56_full_stripe_start);
-	*length = min_t(u64, em->len - map_offset, max_len);
+	map_offset = logical - map->start;
+	io_geom.raid56_full_stripe_start = (u64)-1;
+	max_len = btrfs_max_io_len(map, map_offset, &io_geom);
+	*length = min_t(u64, map->chunk_len - map_offset, max_len);
 
 	down_read(&dev_replace->rwsem);
 	dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(dev_replace);
@@ -6283,107 +6574,46 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 	if (!dev_replace_is_ongoing)
 		up_read(&dev_replace->rwsem);
 
-	num_stripes = 1;
-	stripe_index = 0;
-	if (map->type & BTRFS_BLOCK_GROUP_RAID0) {
-		stripe_index = stripe_nr % map->num_stripes;
-		stripe_nr /= map->num_stripes;
-		if (op == BTRFS_MAP_READ)
-			mirror_num = 1;
-	} else if (map->type & BTRFS_BLOCK_GROUP_RAID1_MASK) {
-		if (op != BTRFS_MAP_READ) {
-			num_stripes = map->num_stripes;
-		} else if (mirror_num) {
-			stripe_index = mirror_num - 1;
-		} else {
-			stripe_index = find_live_mirror(fs_info, map, 0,
-					    dev_replace_is_ongoing);
-			mirror_num = stripe_index + 1;
-		}
-
-	} else if (map->type & BTRFS_BLOCK_GROUP_DUP) {
-		if (op != BTRFS_MAP_READ) {
-			num_stripes = map->num_stripes;
-		} else if (mirror_num) {
-			stripe_index = mirror_num - 1;
-		} else {
-			mirror_num = 1;
-		}
-
-	} else if (map->type & BTRFS_BLOCK_GROUP_RAID10) {
-		u32 factor = map->num_stripes / map->sub_stripes;
-
-		stripe_index = (stripe_nr % factor) * map->sub_stripes;
-		stripe_nr /= factor;
-
-		if (op != BTRFS_MAP_READ)
-			num_stripes = map->sub_stripes;
-		else if (mirror_num)
-			stripe_index += mirror_num - 1;
-		else {
-			int old_stripe_index = stripe_index;
-			stripe_index = find_live_mirror(fs_info, map,
-					      stripe_index,
-					      dev_replace_is_ongoing);
-			mirror_num = stripe_index - old_stripe_index + 1;
-		}
-
-	} else if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
-		if (op != BTRFS_MAP_READ || mirror_num > 1) {
-			/*
-			 * Needs full stripe mapping.
-			 *
-			 * Push stripe_nr back to the start of the full stripe
-			 * For those cases needing a full stripe, @stripe_nr
-			 * is the full stripe number.
-			 *
-			 * Originally we go raid56_full_stripe_start / full_stripe_len,
-			 * but that can be expensive.  Here we just divide
-			 * @stripe_nr with @data_stripes.
-			 */
-			stripe_nr /= data_stripes;
-
-			/* RAID[56] write or recovery. Return all stripes */
-			num_stripes = map->num_stripes;
-			max_errors = btrfs_chunk_max_errors(map);
-
-			/* Return the length to the full stripe end */
-			*length = min(logical + *length,
-				      raid56_full_stripe_start + em->start +
-				      btrfs_stripe_nr_to_offset(data_stripes)) -
-				  logical;
-			stripe_index = 0;
-			stripe_offset = 0;
-		} else {
-			ASSERT(mirror_num <= 1);
-			/* Just grab the data stripe directly. */
-			stripe_index = stripe_nr % data_stripes;
-			stripe_nr /= data_stripes;
-
-			/* We distribute the parity blocks across stripes */
-			stripe_index = (stripe_nr + stripe_index) % map->num_stripes;
-			if (op == BTRFS_MAP_READ && mirror_num < 1)
-				mirror_num = 1;
-		}
-	} else {
+	switch (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
+	case BTRFS_BLOCK_GROUP_RAID0:
+		map_blocks_raid0(map, &io_geom);
+		break;
+	case BTRFS_BLOCK_GROUP_RAID1:
+	case BTRFS_BLOCK_GROUP_RAID1C3:
+	case BTRFS_BLOCK_GROUP_RAID1C4:
+		map_blocks_raid1(fs_info, map, &io_geom, dev_replace_is_ongoing);
+		break;
+	case BTRFS_BLOCK_GROUP_DUP:
+		map_blocks_dup(map, &io_geom);
+		break;
+	case BTRFS_BLOCK_GROUP_RAID10:
+		map_blocks_raid10(fs_info, map, &io_geom, dev_replace_is_ongoing);
+		break;
+	case BTRFS_BLOCK_GROUP_RAID5:
+	case BTRFS_BLOCK_GROUP_RAID6:
+		if (op != BTRFS_MAP_READ || io_geom.mirror_num > 1)
+			map_blocks_raid56_write(map, &io_geom, logical, length);
+		else
+			map_blocks_raid56_read(map, &io_geom);
+		break;
+	default:
 		/*
 		 * After this, stripe_nr is the number of stripes on this
 		 * device we have to walk to find the data, and stripe_index is
 		 * the number of our device in the stripe array
 		 */
-		stripe_index = stripe_nr % map->num_stripes;
-		stripe_nr /= map->num_stripes;
-		mirror_num = stripe_index + 1;
+		map_blocks_single(map, &io_geom);
+		break;
 	}
-	if (stripe_index >= map->num_stripes) {
+	if (io_geom.stripe_index >= map->num_stripes) {
 		btrfs_crit(fs_info,
 			   "stripe index math went horribly wrong, got stripe_index=%u, num_stripes=%u",
-			   stripe_index, map->num_stripes);
+			   io_geom.stripe_index, map->num_stripes);
 		ret = -EINVAL;
 		goto out;
 	}
 
-	num_alloc_stripes = num_stripes;
+	num_alloc_stripes = io_geom.num_stripes;
 	if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL &&
 	    op != BTRFS_MAP_READ)
 		/*
@@ -6400,14 +6630,11 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 	 * physical block information on the stack instead of allocating an
 	 * I/O context structure.
 	 */
-	if (smap && num_alloc_stripes == 1 &&
-	    !(btrfs_need_stripe_tree_update(fs_info, map->type) &&
-	      op != BTRFS_MAP_READ) &&
-	    !((map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) && mirror_num > 1)) {
-		ret = set_io_stripe(fs_info, op, logical, length, smap, map,
-				    stripe_index, stripe_offset, stripe_nr);
+	if (is_single_device_io(fs_info, smap, map, num_alloc_stripes, op,
+				io_geom.mirror_num)) {
+		ret = set_io_stripe(fs_info, logical, length, smap, map, &io_geom);
 		if (mirror_num_ret)
-			*mirror_num_ret = mirror_num;
+			*mirror_num_ret = io_geom.mirror_num;
 		*bioc_ret = NULL;
 		goto out;
 	}
@@ -6427,7 +6654,7 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 	 * It's still mostly the same as other profiles, just with extra rotation.
 	 */
 	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK &&
-	    (op != BTRFS_MAP_READ || mirror_num > 1)) {
+	    (op != BTRFS_MAP_READ || io_geom.mirror_num > 1)) {
 		/*
 		 * For RAID56 @stripe_nr is already the number of full stripes
 		 * before us, which is also the rotation value (needs to modulo
@@ -6436,28 +6663,31 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 		 * In this case, we just add @stripe_nr with @i, then do the
 		 * modulo, to reduce one modulo call.
 		 */
-		bioc->full_stripe_logical = em->start +
-			btrfs_stripe_nr_to_offset(stripe_nr * data_stripes);
-		for (int i = 0; i < num_stripes; i++) {
-			ret = set_io_stripe(fs_info, op, logical, length,
-					    &bioc->stripes[i], map,
-					    (i + stripe_nr) % num_stripes,
-					    stripe_offset, stripe_nr);
-			if (ret < 0)
-				break;
+		bioc->full_stripe_logical = map->start +
+			btrfs_stripe_nr_to_offset(io_geom.stripe_nr *
+						  nr_data_stripes(map));
+		for (int i = 0; i < io_geom.num_stripes; i++) {
+			struct btrfs_io_stripe *dst = &bioc->stripes[i];
+			u32 stripe_index;
+
+			stripe_index = (i + io_geom.stripe_nr) % io_geom.num_stripes;
+			dst->dev = map->stripes[stripe_index].dev;
+			dst->physical =
+				map->stripes[stripe_index].physical +
+				io_geom.stripe_offset +
+				btrfs_stripe_nr_to_offset(io_geom.stripe_nr);
 		}
 	} else {
 		/*
 		 * For all other non-RAID56 profiles, just copy the target
 		 * stripe into the bioc.
 		 */
-		for (i = 0; i < num_stripes; i++) {
-			ret = set_io_stripe(fs_info, op, logical, length,
-					    &bioc->stripes[i], map, stripe_index,
-					    stripe_offset, stripe_nr);
+		for (i = 0; i < io_geom.num_stripes; i++) {
+			ret = set_io_stripe(fs_info, logical, length,
+					    &bioc->stripes[i], map, &io_geom);
 			if (ret < 0)
 				break;
-			stripe_index++;
+			io_geom.stripe_index++;
 		}
 	}
 
@@ -6468,18 +6698,18 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 	}
 
 	if (op != BTRFS_MAP_READ)
-		max_errors = btrfs_chunk_max_errors(map);
+		io_geom.max_errors = btrfs_chunk_max_errors(map);
 
 	if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL &&
 	    op != BTRFS_MAP_READ) {
 		handle_ops_on_dev_replace(op, bioc, dev_replace, logical,
-					  &num_stripes, &max_errors);
+					  &io_geom.num_stripes, &io_geom.max_errors);
 	}
 
 	*bioc_ret = bioc;
-	bioc->num_stripes = num_stripes;
-	bioc->max_errors = max_errors;
-	bioc->mirror_num = mirror_num;
+	bioc->num_stripes = io_geom.num_stripes;
+	bioc->max_errors = io_geom.max_errors;
+	bioc->mirror_num = io_geom.mirror_num;
 
 out:
 	if (dev_replace_is_ongoing) {
@@ -6487,7 +6717,7 @@ out:
 		/* Unlock and let waiting writers proceed */
 		up_read(&dev_replace->rwsem);
 	}
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 	return ret;
 }
 
@@ -6659,12 +6889,11 @@ static void btrfs_report_missing_device(struct btrfs_fs_info *fs_info,
 			      devid, uuid);
 }
 
-u64 btrfs_calc_stripe_length(const struct extent_map *em)
+u64 btrfs_calc_stripe_length(const struct btrfs_chunk_map *map)
 {
-	const struct map_lookup *map = em->map_lookup;
 	const int data_stripes = calc_data_stripes(map->type, map->num_stripes);
 
-	return div_u64(em->len, data_stripes);
+	return div_u64(map->chunk_len, data_stripes);
 }
 
 #if BITS_PER_LONG == 32
@@ -6733,9 +6962,7 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
 {
 	BTRFS_DEV_LOOKUP_ARGS(args);
 	struct btrfs_fs_info *fs_info = leaf->fs_info;
-	struct extent_map_tree *map_tree = &fs_info->mapping_tree;
-	struct map_lookup *map;
-	struct extent_map *em;
+	struct btrfs_chunk_map *map;
 	u64 logical;
 	u64 length;
 	u64 devid;
@@ -6769,35 +6996,22 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
 			return ret;
 	}
 
-	read_lock(&map_tree->lock);
-	em = lookup_extent_mapping(map_tree, logical, 1);
-	read_unlock(&map_tree->lock);
+	map = btrfs_find_chunk_map(fs_info, logical, 1);
 
 	/* already mapped? */
-	if (em && em->start <= logical && em->start + em->len > logical) {
-		free_extent_map(em);
+	if (map && map->start <= logical && map->start + map->chunk_len > logical) {
+		btrfs_free_chunk_map(map);
 		return 0;
-	} else if (em) {
-		free_extent_map(em);
+	} else if (map) {
+		btrfs_free_chunk_map(map);
 	}
 
-	em = alloc_extent_map();
-	if (!em)
-		return -ENOMEM;
-	map = kmalloc(map_lookup_size(num_stripes), GFP_NOFS);
-	if (!map) {
-		free_extent_map(em);
+	map = btrfs_alloc_chunk_map(num_stripes, GFP_NOFS);
+	if (!map)
 		return -ENOMEM;
-	}
-
-	set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
-	em->map_lookup = map;
-	em->start = logical;
-	em->len = length;
-	em->orig_start = 0;
-	em->block_start = 0;
-	em->block_len = em->len;
 
+	map->start = logical;
+	map->chunk_len = length;
 	map->num_stripes = num_stripes;
 	map->io_width = btrfs_chunk_io_width(leaf, chunk);
 	map->io_align = btrfs_chunk_io_align(leaf, chunk);
@@ -6812,7 +7026,7 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
 	 */
 	map->sub_stripes = btrfs_raid_array[index].sub_stripes;
 	map->verified_stripes = 0;
-	em->orig_block_len = btrfs_calc_stripe_length(em);
+	map->stripe_size = btrfs_calc_stripe_length(map);
 	for (i = 0; i < num_stripes; i++) {
 		map->stripes[i].physical =
 			btrfs_stripe_offset_nr(leaf, chunk, i);
@@ -6828,7 +7042,7 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
 								    devid, uuid);
 			if (IS_ERR(map->stripes[i].dev)) {
 				ret = PTR_ERR(map->stripes[i].dev);
-				free_extent_map(em);
+				btrfs_free_chunk_map(map);
 				return ret;
 			}
 		}
@@ -6837,15 +7051,12 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
 				&(map->stripes[i].dev->dev_state));
 	}
 
-	write_lock(&map_tree->lock);
-	ret = add_extent_mapping(map_tree, em, 0);
-	write_unlock(&map_tree->lock);
+	ret = btrfs_add_chunk_map(fs_info, map);
 	if (ret < 0) {
 		btrfs_err(fs_info,
 			  "failed to add chunk map, start=%llu len=%llu: %d",
-			  em->start, em->len, ret);
+			  map->start, map->chunk_len, ret);
 	}
-	free_extent_map(em);
 
 	return ret;
 }
@@ -7155,26 +7366,21 @@ out_short_read:
 bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info,
 					struct btrfs_device *failing_dev)
 {
-	struct extent_map_tree *map_tree = &fs_info->mapping_tree;
-	struct extent_map *em;
-	u64 next_start = 0;
+	struct btrfs_chunk_map *map;
+	u64 next_start;
 	bool ret = true;
 
-	read_lock(&map_tree->lock);
-	em = lookup_extent_mapping(map_tree, 0, (u64)-1);
-	read_unlock(&map_tree->lock);
+	map = btrfs_find_chunk_map(fs_info, 0, U64_MAX);
 	/* No chunk at all? Return false anyway */
-	if (!em) {
+	if (!map) {
 		ret = false;
 		goto out;
 	}
-	while (em) {
-		struct map_lookup *map;
+	while (map) {
 		int missing = 0;
 		int max_tolerated;
 		int i;
 
-		map = em->map_lookup;
 		max_tolerated =
 			btrfs_get_num_tolerated_disk_barrier_failures(
 					map->type);
@@ -7192,18 +7398,15 @@ bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info,
 			if (!failing_dev)
 				btrfs_warn(fs_info,
 	"chunk %llu missing %d devices, max tolerance is %d for writable mount",
-				   em->start, missing, max_tolerated);
-			free_extent_map(em);
+				   map->start, missing, max_tolerated);
+			btrfs_free_chunk_map(map);
 			ret = false;
 			goto out;
 		}
-		next_start = extent_map_end(em);
-		free_extent_map(em);
+		next_start = map->start + map->chunk_len;
+		btrfs_free_chunk_map(map);
 
-		read_lock(&map_tree->lock);
-		em = lookup_extent_mapping(map_tree, next_start,
-					   (u64)(-1) - next_start);
-		read_unlock(&map_tree->lock);
+		map = btrfs_find_chunk_map(fs_info, next_start, U64_MAX - next_start);
 	}
 out:
 	return ret;
@@ -7696,20 +7899,15 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info,
 				 u64 physical_offset, u64 physical_len)
 {
 	struct btrfs_dev_lookup_args args = { .devid = devid };
-	struct extent_map_tree *em_tree = &fs_info->mapping_tree;
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	struct btrfs_device *dev;
 	u64 stripe_len;
 	bool found = false;
 	int ret = 0;
 	int i;
 
-	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, chunk_offset, 1);
-	read_unlock(&em_tree->lock);
-
-	if (!em) {
+	map = btrfs_find_chunk_map(fs_info, chunk_offset, 1);
+	if (!map) {
 		btrfs_err(fs_info,
 "dev extent physical offset %llu on devid %llu doesn't have corresponding chunk",
 			  physical_offset, devid);
@@ -7717,12 +7915,11 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info,
 		goto out;
 	}
 
-	map = em->map_lookup;
-	stripe_len = btrfs_calc_stripe_length(em);
+	stripe_len = btrfs_calc_stripe_length(map);
 	if (physical_len != stripe_len) {
 		btrfs_err(fs_info,
 "dev extent physical offset %llu on devid %llu length doesn't match chunk %llu, have %llu expect %llu",
-			  physical_offset, devid, em->start, physical_len,
+			  physical_offset, devid, map->start, physical_len,
 			  stripe_len);
 		ret = -EUCLEAN;
 		goto out;
@@ -7745,7 +7942,7 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info,
 			if (map->verified_stripes >= map->num_stripes) {
 				btrfs_err(fs_info,
 				"too many dev extents for chunk %llu found",
-					  em->start);
+					  map->start);
 				ret = -EUCLEAN;
 				goto out;
 			}
@@ -7791,32 +7988,30 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info,
 	}
 
 out:
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 	return ret;
 }
 
 static int verify_chunk_dev_extent_mapping(struct btrfs_fs_info *fs_info)
 {
-	struct extent_map_tree *em_tree = &fs_info->mapping_tree;
-	struct extent_map *em;
 	struct rb_node *node;
 	int ret = 0;
 
-	read_lock(&em_tree->lock);
-	for (node = rb_first_cached(&em_tree->map); node; node = rb_next(node)) {
-		em = rb_entry(node, struct extent_map, rb_node);
-		if (em->map_lookup->num_stripes !=
-		    em->map_lookup->verified_stripes) {
+	read_lock(&fs_info->mapping_tree_lock);
+	for (node = rb_first_cached(&fs_info->mapping_tree); node; node = rb_next(node)) {
+		struct btrfs_chunk_map *map;
+
+		map = rb_entry(node, struct btrfs_chunk_map, rb_node);
+		if (map->num_stripes != map->verified_stripes) {
 			btrfs_err(fs_info,
 			"chunk %llu has missing dev extent, have %d expect %d",
-				  em->start, em->map_lookup->verified_stripes,
-				  em->map_lookup->num_stripes);
+				  map->start, map->verified_stripes, map->num_stripes);
 			ret = -EUCLEAN;
 			goto out;
 		}
 	}
 out:
-	read_unlock(&em_tree->lock);
+	read_unlock(&fs_info->mapping_tree_lock);
 	return ret;
 }
 
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 9cc374864a79..53f87f398da7 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -426,7 +426,8 @@ struct btrfs_discard_stripe {
 struct btrfs_io_context {
 	refcount_t refs;
 	struct btrfs_fs_info *fs_info;
-	u64 map_type; /* get from map_lookup->type */
+	/* Taken from struct btrfs_chunk_map::type. */
+	u64 map_type;
 	struct bio *orig_bio;
 	atomic_t error;
 	u16 max_errors;
@@ -529,18 +530,32 @@ struct btrfs_raid_attr {
 
 extern const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES];
 
-struct map_lookup {
+struct btrfs_chunk_map {
+	struct rb_node rb_node;
+	/* For mount time dev extent verification. */
+	int verified_stripes;
+	refcount_t refs;
+	u64 start;
+	u64 chunk_len;
+	u64 stripe_size;
 	u64 type;
 	int io_align;
 	int io_width;
 	int num_stripes;
 	int sub_stripes;
-	int verified_stripes; /* For mount time dev extent verification */
 	struct btrfs_io_stripe stripes[];
 };
 
-#define map_lookup_size(n) (sizeof(struct map_lookup) + \
-			    (sizeof(struct btrfs_io_stripe) * (n)))
+#define btrfs_chunk_map_size(n) (sizeof(struct btrfs_chunk_map) + \
+				 (sizeof(struct btrfs_io_stripe) * (n)))
+
+static inline void btrfs_free_chunk_map(struct btrfs_chunk_map *map)
+{
+	if (map && refcount_dec_and_test(&map->refs)) {
+		ASSERT(RB_EMPTY_NODE(&map->rb_node));
+		kfree(map);
+	}
+}
 
 struct btrfs_balance_args;
 struct btrfs_balance_progress;
@@ -598,7 +613,7 @@ static inline unsigned long btrfs_chunk_item_size(int num_stripes)
 }
 
 /*
- * Do the type safe converstion from stripe_nr to offset inside the chunk.
+ * Do the type safe conversion from stripe_nr to offset inside the chunk.
  *
  * @stripe_nr is u32, with left shift it can overflow u32 for chunks larger
  * than 4G.  This does the proper type cast to avoid overflow.
@@ -624,7 +639,7 @@ int btrfs_read_sys_array(struct btrfs_fs_info *fs_info);
 int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info);
 struct btrfs_block_group *btrfs_create_chunk(struct btrfs_trans_handle *trans,
 					    u64 type);
-void btrfs_mapping_tree_free(struct extent_map_tree *tree);
+void btrfs_mapping_tree_free(struct btrfs_fs_info *fs_info);
 int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 		       blk_mode_t flags, void *holder);
 struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags,
@@ -680,13 +695,25 @@ int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info,
 			   u64 logical, u64 len);
 unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info,
 				    u64 logical);
-u64 btrfs_calc_stripe_length(const struct extent_map *em);
+u64 btrfs_calc_stripe_length(const struct btrfs_chunk_map *map);
 int btrfs_nr_parity_stripes(u64 type);
 int btrfs_chunk_alloc_add_chunk_item(struct btrfs_trans_handle *trans,
 				     struct btrfs_block_group *bg);
 int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset);
-struct extent_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
-				       u64 logical, u64 length);
+
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+struct btrfs_chunk_map *btrfs_alloc_chunk_map(int num_stripes, gfp_t gfp);
+int btrfs_add_chunk_map(struct btrfs_fs_info *fs_info, struct btrfs_chunk_map *map);
+#endif
+
+struct btrfs_chunk_map *btrfs_clone_chunk_map(struct btrfs_chunk_map *map, gfp_t gfp);
+struct btrfs_chunk_map *btrfs_find_chunk_map(struct btrfs_fs_info *fs_info,
+					     u64 logical, u64 length);
+struct btrfs_chunk_map *btrfs_find_chunk_map_nolock(struct btrfs_fs_info *fs_info,
+						    u64 logical, u64 length);
+struct btrfs_chunk_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
+					    u64 logical, u64 length);
+void btrfs_remove_chunk_map(struct btrfs_fs_info *fs_info, struct btrfs_chunk_map *map);
 void btrfs_release_disk_super(struct btrfs_super_block *super);
 
 static inline void btrfs_dev_stat_inc(struct btrfs_device *dev,
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 3cf236fb40a4..6287763fdccc 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -382,6 +382,53 @@ static int btrfs_xattr_handler_set(const struct xattr_handler *handler,
 	return btrfs_setxattr_trans(inode, name, buffer, size, flags);
 }
 
+static int btrfs_xattr_handler_get_security(const struct xattr_handler *handler,
+					    struct dentry *unused,
+					    struct inode *inode,
+					    const char *name, void *buffer,
+					    size_t size)
+{
+	int ret;
+	bool is_cap = false;
+
+	name = xattr_full_name(handler, name);
+
+	/*
+	 * security.capability doesn't cache the results, so calls into us
+	 * constantly to see if there's a capability xattr.  Cache the result
+	 * here in order to avoid wasting time doing lookups for xattrs we know
+	 * don't exist.
+	 */
+	if (strcmp(name, XATTR_NAME_CAPS) == 0) {
+		is_cap = true;
+		if (test_bit(BTRFS_INODE_NO_CAP_XATTR, &BTRFS_I(inode)->runtime_flags))
+			return -ENODATA;
+	}
+
+	ret = btrfs_getxattr(inode, name, buffer, size);
+	if (ret == -ENODATA && is_cap)
+		set_bit(BTRFS_INODE_NO_CAP_XATTR, &BTRFS_I(inode)->runtime_flags);
+	return ret;
+}
+
+static int btrfs_xattr_handler_set_security(const struct xattr_handler *handler,
+					    struct mnt_idmap *idmap,
+					    struct dentry *unused,
+					    struct inode *inode,
+					    const char *name,
+					    const void *buffer,
+					    size_t size, int flags)
+{
+	if (btrfs_root_readonly(BTRFS_I(inode)->root))
+		return -EROFS;
+
+	name = xattr_full_name(handler, name);
+	if (strcmp(name, XATTR_NAME_CAPS) == 0)
+		clear_bit(BTRFS_INODE_NO_CAP_XATTR, &BTRFS_I(inode)->runtime_flags);
+
+	return btrfs_setxattr_trans(inode, name, buffer, size, flags);
+}
+
 static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler,
 					struct mnt_idmap *idmap,
 					struct dentry *unused, struct inode *inode,
@@ -420,8 +467,8 @@ static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler,
 
 static const struct xattr_handler btrfs_security_xattr_handler = {
 	.prefix = XATTR_SECURITY_PREFIX,
-	.get = btrfs_xattr_handler_get,
-	.set = btrfs_xattr_handler_set,
+	.get = btrfs_xattr_handler_get_security,
+	.set = btrfs_xattr_handler_set_security,
 };
 
 static const struct xattr_handler btrfs_trusted_xattr_handler = {
@@ -473,6 +520,10 @@ static int btrfs_initxattrs(struct inode *inode,
 		}
 		strcpy(name, XATTR_SECURITY_PREFIX);
 		strcpy(name + XATTR_SECURITY_PREFIX_LEN, xattr->name);
+
+		if (strcmp(name, XATTR_NAME_CAPS) == 0)
+			clear_bit(BTRFS_INODE_NO_CAP_XATTR, &BTRFS_I(inode)->runtime_flags);
+
 		err = btrfs_setxattr(trans, inode, name, xattr->value,
 				     xattr->value_len, 0);
 		kfree(name);
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 6c231a116a29..36cf1f0e338e 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -121,7 +121,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
 	workspace->strm.total_in = 0;
 	workspace->strm.total_out = 0;
 
-	out_page = alloc_page(GFP_NOFS);
+	out_page = btrfs_alloc_compr_page();
 	if (out_page == NULL) {
 		ret = -ENOMEM;
 		goto out;
@@ -200,7 +200,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
 				ret = -E2BIG;
 				goto out;
 			}
-			out_page = alloc_page(GFP_NOFS);
+			out_page = btrfs_alloc_compr_page();
 			if (out_page == NULL) {
 				ret = -ENOMEM;
 				goto out;
@@ -236,7 +236,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
 				ret = -E2BIG;
 				goto out;
 			}
-			out_page = alloc_page(GFP_NOFS);
+			out_page = btrfs_alloc_compr_page();
 			if (out_page == NULL) {
 				ret = -ENOMEM;
 				goto out;
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 3504ade30cb0..5bd76813b23f 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -578,26 +578,12 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache)
 
 	kvfree(zones);
 
-	switch (bdev_zoned_model(bdev)) {
-	case BLK_ZONED_HM:
+	if (bdev_is_zoned(bdev)) {
 		model = "host-managed zoned";
 		emulated = "";
-		break;
-	case BLK_ZONED_HA:
-		model = "host-aware zoned";
-		emulated = "";
-		break;
-	case BLK_ZONED_NONE:
+	} else {
 		model = "regular";
 		emulated = "emulated ";
-		break;
-	default:
-		/* Just in case */
-		btrfs_err_in_rcu(fs_info, "zoned: unsupported model %d on %s",
-				 bdev_zoned_model(bdev),
-				 rcu_str_deref(device->name));
-		ret = -EOPNOTSUPP;
-		goto out_free_zone_info;
 	}
 
 	btrfs_info_in_rcu(fs_info,
@@ -609,9 +595,7 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache)
 
 out:
 	kvfree(zones);
-out_free_zone_info:
 	btrfs_destroy_dev_zone_info(device);
-
 	return ret;
 }
 
@@ -688,8 +672,7 @@ static int btrfs_check_for_zoned_device(struct btrfs_fs_info *fs_info)
 	struct btrfs_device *device;
 
 	list_for_each_entry(device, &fs_info->fs_devices->devices, dev_list) {
-		if (device->bdev &&
-		    bdev_zoned_model(device->bdev) == BLK_ZONED_HM) {
+		if (device->bdev && bdev_is_zoned(device->bdev)) {
 			btrfs_err(fs_info,
 				"zoned: mode not enabled but zoned device found: %pg",
 				device->bdev);
@@ -781,7 +764,7 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
 	 * Check mount options here, because we might change fs_info->zoned
 	 * from fs_info->zone_size.
 	 */
-	ret = btrfs_check_mountopts_zoned(fs_info);
+	ret = btrfs_check_mountopts_zoned(fs_info, &fs_info->mount_opt);
 	if (ret)
 		return ret;
 
@@ -789,7 +772,7 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
 	return 0;
 }
 
-int btrfs_check_mountopts_zoned(struct btrfs_fs_info *info)
+int btrfs_check_mountopts_zoned(struct btrfs_fs_info *info, unsigned long *mount_opt)
 {
 	if (!btrfs_is_zoned(info))
 		return 0;
@@ -798,18 +781,21 @@ int btrfs_check_mountopts_zoned(struct btrfs_fs_info *info)
 	 * Space cache writing is not COWed. Disable that to avoid write errors
 	 * in sequential zones.
 	 */
-	if (btrfs_test_opt(info, SPACE_CACHE)) {
+	if (btrfs_raw_test_opt(*mount_opt, SPACE_CACHE)) {
 		btrfs_err(info, "zoned: space cache v1 is not supported");
 		return -EINVAL;
 	}
 
-	if (btrfs_test_opt(info, NODATACOW)) {
+	if (btrfs_raw_test_opt(*mount_opt, NODATACOW)) {
 		btrfs_err(info, "zoned: NODATACOW not supported");
 		return -EINVAL;
 	}
 
-	btrfs_clear_and_info(info, DISCARD_ASYNC,
-			"zoned: async discard ignored and disabled for zoned mode");
+	if (btrfs_raw_test_opt(*mount_opt, DISCARD_ASYNC)) {
+		btrfs_info(info,
+			   "zoned: async discard ignored and disabled for zoned mode");
+		btrfs_clear_opt(*mount_opt, DISCARD_ASYNC);
+	}
 
 	return 0;
 }
@@ -1290,7 +1276,7 @@ struct zone_info {
 
 static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
 				struct zone_info *info, unsigned long *active,
-				struct map_lookup *map)
+				struct btrfs_chunk_map *map)
 {
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
 	struct btrfs_device *device = map->stripes[zone_idx].dev;
@@ -1393,7 +1379,7 @@ static int btrfs_load_block_group_single(struct btrfs_block_group *bg,
 }
 
 static int btrfs_load_block_group_dup(struct btrfs_block_group *bg,
-				      struct map_lookup *map,
+				      struct btrfs_chunk_map *map,
 				      struct zone_info *zone_info,
 				      unsigned long *active)
 {
@@ -1435,7 +1421,7 @@ static int btrfs_load_block_group_dup(struct btrfs_block_group *bg,
 }
 
 static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg,
-					struct map_lookup *map,
+					struct btrfs_chunk_map *map,
 					struct zone_info *zone_info,
 					unsigned long *active)
 {
@@ -1483,7 +1469,7 @@ static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg,
 }
 
 static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg,
-					struct map_lookup *map,
+					struct btrfs_chunk_map *map,
 					struct zone_info *zone_info,
 					unsigned long *active)
 {
@@ -1515,7 +1501,7 @@ static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg,
 }
 
 static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg,
-					 struct map_lookup *map,
+					 struct btrfs_chunk_map *map,
 					 struct zone_info *zone_info,
 					 unsigned long *active)
 {
@@ -1552,9 +1538,7 @@ static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg,
 int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
-	struct extent_map_tree *em_tree = &fs_info->mapping_tree;
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	u64 logical = cache->start;
 	u64 length = cache->length;
 	struct zone_info *zone_info = NULL;
@@ -1575,17 +1559,11 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 		return -EIO;
 	}
 
-	/* Get the chunk mapping */
-	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, logical, length);
-	read_unlock(&em_tree->lock);
-
-	if (!em)
+	map = btrfs_find_chunk_map(fs_info, logical, length);
+	if (!map)
 		return -EINVAL;
 
-	map = em->map_lookup;
-
-	cache->physical_map = kmemdup(map, map_lookup_size(map->num_stripes), GFP_NOFS);
+	cache->physical_map = btrfs_clone_chunk_map(map, GFP_NOFS);
 	if (!cache->physical_map) {
 		ret = -ENOMEM;
 		goto out;
@@ -1661,13 +1639,6 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 	}
 
 out:
-	if (cache->alloc_offset > fs_info->zone_size) {
-		btrfs_err(fs_info,
-			"zoned: invalid write pointer %llu in block group %llu",
-			cache->alloc_offset, cache->start);
-		ret = -EIO;
-	}
-
 	if (cache->alloc_offset > cache->zone_capacity) {
 		btrfs_err(fs_info,
 "zoned: invalid write pointer %llu (larger than zone capacity %llu) in block group %llu",
@@ -1694,12 +1665,11 @@ out:
 			spin_unlock(&fs_info->zone_active_bgs_lock);
 		}
 	} else {
-		kfree(cache->physical_map);
+		btrfs_free_chunk_map(cache->physical_map);
 		cache->physical_map = NULL;
 	}
 	bitmap_free(active);
 	kfree(zone_info);
-	free_extent_map(em);
 
 	return ret;
 }
@@ -1722,22 +1692,6 @@ void btrfs_calc_zone_unusable(struct btrfs_block_group *cache)
 	cache->zone_unusable = unusable;
 }
 
-void btrfs_redirty_list_add(struct btrfs_transaction *trans,
-			    struct extent_buffer *eb)
-{
-	if (!btrfs_is_zoned(eb->fs_info) ||
-	    btrfs_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN))
-		return;
-
-	ASSERT(!test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
-
-	memzero_extent_buffer(eb, 0, eb->len);
-	set_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags);
-	set_extent_buffer_dirty(eb);
-	set_extent_bit(&trans->dirty_pages, eb->start, eb->start + eb->len - 1,
-			EXTENT_DIRTY, NULL);
-}
-
 bool btrfs_use_zone_append(struct btrfs_bio *bbio)
 {
 	u64 start = (bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT);
@@ -2089,7 +2043,7 @@ int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev, u64 logical,
 bool btrfs_zone_activate(struct btrfs_block_group *block_group)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	struct btrfs_device *device;
 	u64 physical;
 	const bool is_data = (block_group->flags & BTRFS_BLOCK_GROUP_DATA);
@@ -2201,7 +2155,7 @@ static void wait_eb_writebacks(struct btrfs_block_group *block_group)
 static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_written)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	const bool is_metadata = (block_group->flags &
 			(BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM));
 	int ret = 0;
@@ -2650,7 +2604,7 @@ void btrfs_check_active_zone_reservation(struct btrfs_fs_info *fs_info)
 	/* Release reservation for currently active block groups. */
 	spin_lock(&fs_info->zone_active_bgs_lock);
 	list_for_each_entry(block_group, &fs_info->zone_active_bgs, active_bg_list) {
-		struct map_lookup *map = block_group->physical_map;
+		struct btrfs_chunk_map *map = block_group->physical_map;
 
 		if (!(block_group->flags &
 		      (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM)))
diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h
index b9cec523b778..f573bda496fb 100644
--- a/fs/btrfs/zoned.h
+++ b/fs/btrfs/zoned.h
@@ -45,7 +45,7 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache);
 void btrfs_destroy_dev_zone_info(struct btrfs_device *device);
 struct btrfs_zoned_device_info *btrfs_clone_dev_zone_info(struct btrfs_device *orig_dev);
 int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info);
-int btrfs_check_mountopts_zoned(struct btrfs_fs_info *info);
+int btrfs_check_mountopts_zoned(struct btrfs_fs_info *info, unsigned long *mount_opt);
 int btrfs_sb_log_location_bdev(struct block_device *bdev, int mirror, int rw,
 			       u64 *bytenr_ret);
 int btrfs_sb_log_location(struct btrfs_device *device, int mirror, int rw,
@@ -59,8 +59,6 @@ int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical,
 int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size);
 int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new);
 void btrfs_calc_zone_unusable(struct btrfs_block_group *cache);
-void btrfs_redirty_list_add(struct btrfs_transaction *trans,
-			    struct extent_buffer *eb);
 bool btrfs_use_zone_append(struct btrfs_bio *bbio);
 void btrfs_record_physical_zoned(struct btrfs_bio *bbio);
 int btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
@@ -123,7 +121,8 @@ static inline int btrfs_check_zoned_mode(const struct btrfs_fs_info *fs_info)
 	return -EOPNOTSUPP;
 }
 
-static inline int btrfs_check_mountopts_zoned(struct btrfs_fs_info *info)
+static inline int btrfs_check_mountopts_zoned(struct btrfs_fs_info *info,
+					      unsigned long *mount_opt)
 {
 	return 0;
 }
@@ -180,9 +179,6 @@ static inline int btrfs_load_block_group_zone_info(
 
 static inline void btrfs_calc_zone_unusable(struct btrfs_block_group *cache) { }
 
-static inline void btrfs_redirty_list_add(struct btrfs_transaction *trans,
-					  struct extent_buffer *eb) { }
-
 static inline bool btrfs_use_zone_append(struct btrfs_bio *bbio)
 {
 	return false;
@@ -323,8 +319,8 @@ static inline bool btrfs_check_device_zone_type(const struct btrfs_fs_info *fs_i
 			(bdev_zone_sectors(bdev) << SECTOR_SHIFT);
 	}
 
-	/* Do not allow Host Manged zoned device */
-	return bdev_zoned_model(bdev) != BLK_ZONED_HM;
+	/* Do not allow Host Managed zoned device. */
+	return !bdev_is_zoned(bdev);
 }
 
 static inline bool btrfs_check_super_location(struct btrfs_device *device, u64 pos)
diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c
index 5511766485cd..0d66db8bc1d4 100644
--- a/fs/btrfs/zstd.c
+++ b/fs/btrfs/zstd.c
@@ -410,9 +410,8 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
 	workspace->in_buf.pos = 0;
 	workspace->in_buf.size = min_t(size_t, len, PAGE_SIZE);
 
-
 	/* Allocate and map in the output buffer */
-	out_page = alloc_page(GFP_NOFS);
+	out_page = btrfs_alloc_compr_page();
 	if (out_page == NULL) {
 		ret = -ENOMEM;
 		goto out;
@@ -457,7 +456,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
 				ret = -E2BIG;
 				goto out;
 			}
-			out_page = alloc_page(GFP_NOFS);
+			out_page = btrfs_alloc_compr_page();
 			if (out_page == NULL) {
 				ret = -ENOMEM;
 				goto out;
@@ -514,7 +513,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
 			ret = -E2BIG;
 			goto out;
 		}
-		out_page = alloc_page(GFP_NOFS);
+		out_page = btrfs_alloc_compr_page();
 		if (out_page == NULL) {
 			ret = -ENOMEM;
 			goto out;
diff --git a/fs/buffer.c b/fs/buffer.c
index 967f34b70aa8..d3bcf601d3e5 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -180,11 +180,11 @@ EXPORT_SYMBOL(end_buffer_write_sync);
  * Various filesystems appear to want __find_get_block to be non-blocking.
  * But it's the page lock which protects the buffers.  To get around this,
  * we get exclusion from try_to_free_buffers with the blockdev mapping's
- * private_lock.
+ * i_private_lock.
  *
- * Hack idea: for the blockdev mapping, private_lock contention
+ * Hack idea: for the blockdev mapping, i_private_lock contention
  * may be quite high.  This code could TryLock the page, and if that
- * succeeds, there is no need to take private_lock.
+ * succeeds, there is no need to take i_private_lock.
  */
 static struct buffer_head *
 __find_get_block_slow(struct block_device *bdev, sector_t block)
@@ -199,12 +199,12 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
 	int all_mapped = 1;
 	static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1);
 
-	index = block >> (PAGE_SHIFT - bd_inode->i_blkbits);
+	index = ((loff_t)block << bd_inode->i_blkbits) / PAGE_SIZE;
 	folio = __filemap_get_folio(bd_mapping, index, FGP_ACCESSED, 0);
 	if (IS_ERR(folio))
 		goto out;
 
-	spin_lock(&bd_mapping->private_lock);
+	spin_lock(&bd_mapping->i_private_lock);
 	head = folio_buffers(folio);
 	if (!head)
 		goto out_unlock;
@@ -236,7 +236,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
 		       1 << bd_inode->i_blkbits);
 	}
 out_unlock:
-	spin_unlock(&bd_mapping->private_lock);
+	spin_unlock(&bd_mapping->i_private_lock);
 	folio_put(folio);
 out:
 	return ret;
@@ -372,10 +372,10 @@ static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate)
 }
 
 /*
- * Completion handler for block_write_full_page() - pages which are unlocked
- * during I/O, and which have PageWriteback cleared upon I/O completion.
+ * Completion handler for block_write_full_folio() - folios which are unlocked
+ * during I/O, and which have the writeback flag cleared upon I/O completion.
  */
-void end_buffer_async_write(struct buffer_head *bh, int uptodate)
+static void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 {
 	unsigned long flags;
 	struct buffer_head *first;
@@ -415,7 +415,6 @@ still_busy:
 	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
 	return;
 }
-EXPORT_SYMBOL(end_buffer_async_write);
 
 /*
  * If a page's buffers are under async readin (end_buffer_async_read
@@ -467,25 +466,25 @@ EXPORT_SYMBOL(mark_buffer_async_write);
  *
  * The functions mark_buffer_inode_dirty(), fsync_inode_buffers(),
  * inode_has_buffers() and invalidate_inode_buffers() are provided for the
- * management of a list of dependent buffers at ->i_mapping->private_list.
+ * management of a list of dependent buffers at ->i_mapping->i_private_list.
  *
  * Locking is a little subtle: try_to_free_buffers() will remove buffers
  * from their controlling inode's queue when they are being freed.  But
  * try_to_free_buffers() will be operating against the *blockdev* mapping
  * at the time, not against the S_ISREG file which depends on those buffers.
- * So the locking for private_list is via the private_lock in the address_space
+ * So the locking for i_private_list is via the i_private_lock in the address_space
  * which backs the buffers.  Which is different from the address_space 
  * against which the buffers are listed.  So for a particular address_space,
- * mapping->private_lock does *not* protect mapping->private_list!  In fact,
- * mapping->private_list will always be protected by the backing blockdev's
- * ->private_lock.
+ * mapping->i_private_lock does *not* protect mapping->i_private_list!  In fact,
+ * mapping->i_private_list will always be protected by the backing blockdev's
+ * ->i_private_lock.
  *
  * Which introduces a requirement: all buffers on an address_space's
- * ->private_list must be from the same address_space: the blockdev's.
+ * ->i_private_list must be from the same address_space: the blockdev's.
  *
- * address_spaces which do not place buffers at ->private_list via these
- * utility functions are free to use private_lock and private_list for
- * whatever they want.  The only requirement is that list_empty(private_list)
+ * address_spaces which do not place buffers at ->i_private_list via these
+ * utility functions are free to use i_private_lock and i_private_list for
+ * whatever they want.  The only requirement is that list_empty(i_private_list)
  * be true at clear_inode() time.
  *
  * FIXME: clear_inode should not call invalidate_inode_buffers().  The
@@ -508,7 +507,7 @@ EXPORT_SYMBOL(mark_buffer_async_write);
  */
 
 /*
- * The buffer's backing address_space's private_lock must be held
+ * The buffer's backing address_space's i_private_lock must be held
  */
 static void __remove_assoc_queue(struct buffer_head *bh)
 {
@@ -519,7 +518,7 @@ static void __remove_assoc_queue(struct buffer_head *bh)
 
 int inode_has_buffers(struct inode *inode)
 {
-	return !list_empty(&inode->i_data.private_list);
+	return !list_empty(&inode->i_data.i_private_list);
 }
 
 /*
@@ -561,7 +560,7 @@ repeat:
  * sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers
  * @mapping: the mapping which wants those buffers written
  *
- * Starts I/O against the buffers at mapping->private_list, and waits upon
+ * Starts I/O against the buffers at mapping->i_private_list, and waits upon
  * that I/O.
  *
  * Basically, this is a convenience function for fsync().
@@ -570,13 +569,13 @@ repeat:
  */
 int sync_mapping_buffers(struct address_space *mapping)
 {
-	struct address_space *buffer_mapping = mapping->private_data;
+	struct address_space *buffer_mapping = mapping->i_private_data;
 
-	if (buffer_mapping == NULL || list_empty(&mapping->private_list))
+	if (buffer_mapping == NULL || list_empty(&mapping->i_private_list))
 		return 0;
 
-	return fsync_buffers_list(&buffer_mapping->private_lock,
-					&mapping->private_list);
+	return fsync_buffers_list(&buffer_mapping->i_private_lock,
+					&mapping->i_private_list);
 }
 EXPORT_SYMBOL(sync_mapping_buffers);
 
@@ -673,17 +672,17 @@ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode)
 	struct address_space *buffer_mapping = bh->b_folio->mapping;
 
 	mark_buffer_dirty(bh);
-	if (!mapping->private_data) {
-		mapping->private_data = buffer_mapping;
+	if (!mapping->i_private_data) {
+		mapping->i_private_data = buffer_mapping;
 	} else {
-		BUG_ON(mapping->private_data != buffer_mapping);
+		BUG_ON(mapping->i_private_data != buffer_mapping);
 	}
 	if (!bh->b_assoc_map) {
-		spin_lock(&buffer_mapping->private_lock);
+		spin_lock(&buffer_mapping->i_private_lock);
 		list_move_tail(&bh->b_assoc_buffers,
-				&mapping->private_list);
+				&mapping->i_private_list);
 		bh->b_assoc_map = mapping;
-		spin_unlock(&buffer_mapping->private_lock);
+		spin_unlock(&buffer_mapping->i_private_lock);
 	}
 }
 EXPORT_SYMBOL(mark_buffer_dirty_inode);
@@ -706,7 +705,7 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode);
  * bit, see a bunch of clean buffers and we'd end up with dirty buffers/clean
  * page on the dirty page list.
  *
- * We use private_lock to lock against try_to_free_buffers while using the
+ * We use i_private_lock to lock against try_to_free_buffers while using the
  * page's buffer list.  Also use this to protect against clean buffers being
  * added to the page after it was set dirty.
  *
@@ -718,7 +717,7 @@ bool block_dirty_folio(struct address_space *mapping, struct folio *folio)
 	struct buffer_head *head;
 	bool newly_dirty;
 
-	spin_lock(&mapping->private_lock);
+	spin_lock(&mapping->i_private_lock);
 	head = folio_buffers(folio);
 	if (head) {
 		struct buffer_head *bh = head;
@@ -734,7 +733,7 @@ bool block_dirty_folio(struct address_space *mapping, struct folio *folio)
 	 */
 	folio_memcg_lock(folio);
 	newly_dirty = !folio_test_set_dirty(folio);
-	spin_unlock(&mapping->private_lock);
+	spin_unlock(&mapping->i_private_lock);
 
 	if (newly_dirty)
 		__folio_mark_dirty(folio, mapping, 1);
@@ -827,7 +826,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
 		smp_mb();
 		if (buffer_dirty(bh)) {
 			list_add(&bh->b_assoc_buffers,
-				 &mapping->private_list);
+				 &mapping->i_private_list);
 			bh->b_assoc_map = mapping;
 		}
 		spin_unlock(lock);
@@ -851,7 +850,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
  * probably unmounting the fs, but that doesn't mean we have already
  * done a sync().  Just drop the buffers from the inode list.
  *
- * NOTE: we take the inode's blockdev's mapping's private_lock.  Which
+ * NOTE: we take the inode's blockdev's mapping's i_private_lock.  Which
  * assumes that all the buffers are against the blockdev.  Not true
  * for reiserfs.
  */
@@ -859,13 +858,13 @@ void invalidate_inode_buffers(struct inode *inode)
 {
 	if (inode_has_buffers(inode)) {
 		struct address_space *mapping = &inode->i_data;
-		struct list_head *list = &mapping->private_list;
-		struct address_space *buffer_mapping = mapping->private_data;
+		struct list_head *list = &mapping->i_private_list;
+		struct address_space *buffer_mapping = mapping->i_private_data;
 
-		spin_lock(&buffer_mapping->private_lock);
+		spin_lock(&buffer_mapping->i_private_lock);
 		while (!list_empty(list))
 			__remove_assoc_queue(BH_ENTRY(list->next));
-		spin_unlock(&buffer_mapping->private_lock);
+		spin_unlock(&buffer_mapping->i_private_lock);
 	}
 }
 EXPORT_SYMBOL(invalidate_inode_buffers);
@@ -882,10 +881,10 @@ int remove_inode_buffers(struct inode *inode)
 
 	if (inode_has_buffers(inode)) {
 		struct address_space *mapping = &inode->i_data;
-		struct list_head *list = &mapping->private_list;
-		struct address_space *buffer_mapping = mapping->private_data;
+		struct list_head *list = &mapping->i_private_list;
+		struct address_space *buffer_mapping = mapping->i_private_data;
 
-		spin_lock(&buffer_mapping->private_lock);
+		spin_lock(&buffer_mapping->i_private_lock);
 		while (!list_empty(list)) {
 			struct buffer_head *bh = BH_ENTRY(list->next);
 			if (buffer_dirty(bh)) {
@@ -894,7 +893,7 @@ int remove_inode_buffers(struct inode *inode)
 			}
 			__remove_assoc_queue(bh);
 		}
-		spin_unlock(&buffer_mapping->private_lock);
+		spin_unlock(&buffer_mapping->i_private_lock);
 	}
 	return ret;
 }
@@ -995,11 +994,12 @@ static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size)
  * Initialise the state of a blockdev folio's buffers.
  */ 
 static sector_t folio_init_buffers(struct folio *folio,
-		struct block_device *bdev, sector_t block, int size)
+		struct block_device *bdev, unsigned size)
 {
 	struct buffer_head *head = folio_buffers(folio);
 	struct buffer_head *bh = head;
 	bool uptodate = folio_test_uptodate(folio);
+	sector_t block = div_u64(folio_pos(folio), size);
 	sector_t end_block = blkdev_max_block(bdev, size);
 
 	do {
@@ -1024,86 +1024,88 @@ static sector_t folio_init_buffers(struct folio *folio,
 }
 
 /*
- * Create the page-cache page that contains the requested block.
+ * Create the page-cache folio that contains the requested block.
  *
  * This is used purely for blockdev mappings.
+ *
+ * Returns false if we have a failure which cannot be cured by retrying
+ * without sleeping.  Returns true if we succeeded, or the caller should retry.
  */
-static int
-grow_dev_page(struct block_device *bdev, sector_t block,
-	      pgoff_t index, int size, int sizebits, gfp_t gfp)
+static bool grow_dev_folio(struct block_device *bdev, sector_t block,
+		pgoff_t index, unsigned size, gfp_t gfp)
 {
 	struct inode *inode = bdev->bd_inode;
 	struct folio *folio;
 	struct buffer_head *bh;
-	sector_t end_block;
-	int ret = 0;
+	sector_t end_block = 0;
 
 	folio = __filemap_get_folio(inode->i_mapping, index,
 			FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp);
 	if (IS_ERR(folio))
-		return PTR_ERR(folio);
+		return false;
 
 	bh = folio_buffers(folio);
 	if (bh) {
 		if (bh->b_size == size) {
-			end_block = folio_init_buffers(folio, bdev,
-					(sector_t)index << sizebits, size);
-			goto done;
+			end_block = folio_init_buffers(folio, bdev, size);
+			goto unlock;
+		}
+
+		/*
+		 * Retrying may succeed; for example the folio may finish
+		 * writeback, or buffers may be cleaned.  This should not
+		 * happen very often; maybe we have old buffers attached to
+		 * this blockdev's page cache and we're trying to change
+		 * the block size?
+		 */
+		if (!try_to_free_buffers(folio)) {
+			end_block = ~0ULL;
+			goto unlock;
 		}
-		if (!try_to_free_buffers(folio))
-			goto failed;
 	}
 
-	ret = -ENOMEM;
 	bh = folio_alloc_buffers(folio, size, gfp | __GFP_ACCOUNT);
 	if (!bh)
-		goto failed;
+		goto unlock;
 
 	/*
 	 * Link the folio to the buffers and initialise them.  Take the
 	 * lock to be atomic wrt __find_get_block(), which does not
 	 * run under the folio lock.
 	 */
-	spin_lock(&inode->i_mapping->private_lock);
+	spin_lock(&inode->i_mapping->i_private_lock);
 	link_dev_buffers(folio, bh);
-	end_block = folio_init_buffers(folio, bdev,
-			(sector_t)index << sizebits, size);
-	spin_unlock(&inode->i_mapping->private_lock);
-done:
-	ret = (block < end_block) ? 1 : -ENXIO;
-failed:
+	end_block = folio_init_buffers(folio, bdev, size);
+	spin_unlock(&inode->i_mapping->i_private_lock);
+unlock:
 	folio_unlock(folio);
 	folio_put(folio);
-	return ret;
+	return block < end_block;
 }
 
 /*
- * Create buffers for the specified block device block's page.  If
- * that page was dirty, the buffers are set dirty also.
+ * Create buffers for the specified block device block's folio.  If
+ * that folio was dirty, the buffers are set dirty also.  Returns false
+ * if we've hit a permanent error.
  */
-static int
-grow_buffers(struct block_device *bdev, sector_t block, int size, gfp_t gfp)
+static bool grow_buffers(struct block_device *bdev, sector_t block,
+		unsigned size, gfp_t gfp)
 {
-	pgoff_t index;
-	int sizebits;
-
-	sizebits = PAGE_SHIFT - __ffs(size);
-	index = block >> sizebits;
+	loff_t pos;
 
 	/*
-	 * Check for a block which wants to lie outside our maximum possible
-	 * pagecache index.  (this comparison is done using sector_t types).
+	 * Check for a block which lies outside our maximum possible
+	 * pagecache index.
 	 */
-	if (unlikely(index != block >> sizebits)) {
-		printk(KERN_ERR "%s: requested out-of-range block %llu for "
-			"device %pg\n",
+	if (check_mul_overflow(block, (sector_t)size, &pos) || pos > MAX_LFS_FILESIZE) {
+		printk(KERN_ERR "%s: requested out-of-range block %llu for device %pg\n",
 			__func__, (unsigned long long)block,
 			bdev);
-		return -EIO;
+		return false;
 	}
 
-	/* Create a page with the proper size buffers.. */
-	return grow_dev_page(bdev, block, index, size, sizebits, gfp);
+	/* Create a folio with the proper size buffers */
+	return grow_dev_folio(bdev, block, pos / PAGE_SIZE, size, gfp);
 }
 
 static struct buffer_head *
@@ -1124,14 +1126,12 @@ __getblk_slow(struct block_device *bdev, sector_t block,
 
 	for (;;) {
 		struct buffer_head *bh;
-		int ret;
 
 		bh = __find_get_block(bdev, block, size);
 		if (bh)
 			return bh;
 
-		ret = grow_buffers(bdev, block, size, gfp);
-		if (ret < 0)
+		if (!grow_buffers(bdev, block, size, gfp))
 			return NULL;
 	}
 }
@@ -1168,7 +1168,7 @@ __getblk_slow(struct block_device *bdev, sector_t block,
  * and then attach the address_space's inode to its superblock's dirty
  * inode list.
  *
- * mark_buffer_dirty() is atomic.  It takes bh->b_folio->mapping->private_lock,
+ * mark_buffer_dirty() is atomic.  It takes bh->b_folio->mapping->i_private_lock,
  * i_pages lock and mapping->host->i_lock.
  */
 void mark_buffer_dirty(struct buffer_head *bh)
@@ -1246,10 +1246,10 @@ void __bforget(struct buffer_head *bh)
 	if (bh->b_assoc_map) {
 		struct address_space *buffer_mapping = bh->b_folio->mapping;
 
-		spin_lock(&buffer_mapping->private_lock);
+		spin_lock(&buffer_mapping->i_private_lock);
 		list_del_init(&bh->b_assoc_buffers);
 		bh->b_assoc_map = NULL;
-		spin_unlock(&buffer_mapping->private_lock);
+		spin_unlock(&buffer_mapping->i_private_lock);
 	}
 	__brelse(bh);
 }
@@ -1638,7 +1638,7 @@ EXPORT_SYMBOL(block_invalidate_folio);
 
 /*
  * We attach and possibly dirty the buffers atomically wrt
- * block_dirty_folio() via private_lock.  try_to_free_buffers
+ * block_dirty_folio() via i_private_lock.  try_to_free_buffers
  * is already excluded via the folio lock.
  */
 struct buffer_head *create_empty_buffers(struct folio *folio,
@@ -1656,7 +1656,7 @@ struct buffer_head *create_empty_buffers(struct folio *folio,
 	} while (bh);
 	tail->b_this_page = head;
 
-	spin_lock(&folio->mapping->private_lock);
+	spin_lock(&folio->mapping->i_private_lock);
 	if (folio_test_uptodate(folio) || folio_test_dirty(folio)) {
 		bh = head;
 		do {
@@ -1668,7 +1668,7 @@ struct buffer_head *create_empty_buffers(struct folio *folio,
 		} while (bh != head);
 	}
 	folio_attach_private(folio, head);
-	spin_unlock(&folio->mapping->private_lock);
+	spin_unlock(&folio->mapping->i_private_lock);
 
 	return head;
 }
@@ -1699,13 +1699,13 @@ void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len)
 	struct inode *bd_inode = bdev->bd_inode;
 	struct address_space *bd_mapping = bd_inode->i_mapping;
 	struct folio_batch fbatch;
-	pgoff_t index = block >> (PAGE_SHIFT - bd_inode->i_blkbits);
+	pgoff_t index = ((loff_t)block << bd_inode->i_blkbits) / PAGE_SIZE;
 	pgoff_t end;
 	int i, count;
 	struct buffer_head *bh;
 	struct buffer_head *head;
 
-	end = (block + len - 1) >> (PAGE_SHIFT - bd_inode->i_blkbits);
+	end = ((loff_t)(block + len - 1) << bd_inode->i_blkbits) / PAGE_SIZE;
 	folio_batch_init(&fbatch);
 	while (filemap_get_folios(bd_mapping, &index, end, &fbatch)) {
 		count = folio_batch_count(&fbatch);
@@ -1715,7 +1715,7 @@ void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len)
 			if (!folio_buffers(folio))
 				continue;
 			/*
-			 * We use folio lock instead of bd_mapping->private_lock
+			 * We use folio lock instead of bd_mapping->i_private_lock
 			 * to pin buffers here since we can afford to sleep and
 			 * it scales better than a global spinlock lock.
 			 */
@@ -1748,19 +1748,6 @@ unlock_page:
 }
 EXPORT_SYMBOL(clean_bdev_aliases);
 
-/*
- * Size is a power-of-two in the range 512..PAGE_SIZE,
- * and the case we care about most is PAGE_SIZE.
- *
- * So this *could* possibly be written with those
- * constraints in mind (relevant mostly if some
- * architecture has a slow bit-scan instruction)
- */
-static inline int block_size_bits(unsigned int blocksize)
-{
-	return ilog2(blocksize);
-}
-
 static struct buffer_head *folio_create_buffers(struct folio *folio,
 						struct inode *inode,
 						unsigned int b_state)
@@ -1790,30 +1777,29 @@ static struct buffer_head *folio_create_buffers(struct folio *folio,
  */
 
 /*
- * While block_write_full_page is writing back the dirty buffers under
+ * While block_write_full_folio is writing back the dirty buffers under
  * the page lock, whoever dirtied the buffers may decide to clean them
  * again at any time.  We handle that by only looking at the buffer
  * state inside lock_buffer().
  *
- * If block_write_full_page() is called for regular writeback
+ * If block_write_full_folio() is called for regular writeback
  * (wbc->sync_mode == WB_SYNC_NONE) then it will redirty a page which has a
  * locked buffer.   This only can happen if someone has written the buffer
  * directly, with submit_bh().  At the address_space level PageWriteback
  * prevents this contention from occurring.
  *
- * If block_write_full_page() is called with wbc->sync_mode ==
+ * If block_write_full_folio() is called with wbc->sync_mode ==
  * WB_SYNC_ALL, the writes are posted using REQ_SYNC; this
  * causes the writes to be flagged as synchronous writes.
  */
 int __block_write_full_folio(struct inode *inode, struct folio *folio,
-			get_block_t *get_block, struct writeback_control *wbc,
-			bh_end_io_t *handler)
+			get_block_t *get_block, struct writeback_control *wbc)
 {
 	int err;
 	sector_t block;
 	sector_t last_block;
 	struct buffer_head *bh, *head;
-	unsigned int blocksize, bbits;
+	size_t blocksize;
 	int nr_underway = 0;
 	blk_opf_t write_flags = wbc_to_write_flags(wbc);
 
@@ -1832,10 +1818,9 @@ int __block_write_full_folio(struct inode *inode, struct folio *folio,
 
 	bh = head;
 	blocksize = bh->b_size;
-	bbits = block_size_bits(blocksize);
 
-	block = (sector_t)folio->index << (PAGE_SHIFT - bbits);
-	last_block = (i_size_read(inode) - 1) >> bbits;
+	block = div_u64(folio_pos(folio), blocksize);
+	last_block = div_u64(i_size_read(inode) - 1, blocksize);
 
 	/*
 	 * Get all the dirty buffers mapped to disk addresses and
@@ -1849,7 +1834,7 @@ int __block_write_full_folio(struct inode *inode, struct folio *folio,
 			 * truncate in progress.
 			 */
 			/*
-			 * The buffer was zeroed by block_write_full_page()
+			 * The buffer was zeroed by block_write_full_folio()
 			 */
 			clear_buffer_dirty(bh);
 			set_buffer_uptodate(bh);
@@ -1887,7 +1872,8 @@ int __block_write_full_folio(struct inode *inode, struct folio *folio,
 			continue;
 		}
 		if (test_clear_buffer_dirty(bh)) {
-			mark_buffer_async_write_endio(bh, handler);
+			mark_buffer_async_write_endio(bh,
+				end_buffer_async_write);
 		} else {
 			unlock_buffer(bh);
 		}
@@ -1940,7 +1926,8 @@ recover:
 		if (buffer_mapped(bh) && buffer_dirty(bh) &&
 		    !buffer_delay(bh)) {
 			lock_buffer(bh);
-			mark_buffer_async_write_endio(bh, handler);
+			mark_buffer_async_write_endio(bh,
+				end_buffer_async_write);
 		} else {
 			/*
 			 * The buffer may have been set dirty during
@@ -2014,7 +2001,7 @@ static int
 iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh,
 		const struct iomap *iomap)
 {
-	loff_t offset = block << inode->i_blkbits;
+	loff_t offset = (loff_t)block << inode->i_blkbits;
 
 	bh->b_bdev = iomap->bdev;
 
@@ -2081,27 +2068,24 @@ iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh,
 int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len,
 		get_block_t *get_block, const struct iomap *iomap)
 {
-	unsigned from = pos & (PAGE_SIZE - 1);
-	unsigned to = from + len;
+	size_t from = offset_in_folio(folio, pos);
+	size_t to = from + len;
 	struct inode *inode = folio->mapping->host;
-	unsigned block_start, block_end;
+	size_t block_start, block_end;
 	sector_t block;
 	int err = 0;
-	unsigned blocksize, bbits;
+	size_t blocksize;
 	struct buffer_head *bh, *head, *wait[2], **wait_bh=wait;
 
 	BUG_ON(!folio_test_locked(folio));
-	BUG_ON(from > PAGE_SIZE);
-	BUG_ON(to > PAGE_SIZE);
+	BUG_ON(to > folio_size(folio));
 	BUG_ON(from > to);
 
 	head = folio_create_buffers(folio, inode, 0);
 	blocksize = head->b_size;
-	bbits = block_size_bits(blocksize);
+	block = div_u64(folio_pos(folio), blocksize);
 
-	block = (sector_t)folio->index << (PAGE_SHIFT - bbits);
-
-	for(bh = head, block_start = 0; bh != head || !block_start;
+	for (bh = head, block_start = 0; bh != head || !block_start;
 	    block++, block_start=block_end, bh = bh->b_this_page) {
 		block_end = block_start + blocksize;
 		if (block_end <= from || block_start >= to) {
@@ -2364,7 +2348,7 @@ int block_read_full_folio(struct folio *folio, get_block_t *get_block)
 	struct inode *inode = folio->mapping->host;
 	sector_t iblock, lblock;
 	struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE];
-	unsigned int blocksize, bbits;
+	size_t blocksize;
 	int nr, i;
 	int fully_mapped = 1;
 	bool page_error = false;
@@ -2378,10 +2362,9 @@ int block_read_full_folio(struct folio *folio, get_block_t *get_block)
 
 	head = folio_create_buffers(folio, inode, 0);
 	blocksize = head->b_size;
-	bbits = block_size_bits(blocksize);
 
-	iblock = (sector_t)folio->index << (PAGE_SHIFT - bbits);
-	lblock = (limit+blocksize-1) >> bbits;
+	iblock = div_u64(folio_pos(folio), blocksize);
+	lblock = div_u64(limit + blocksize - 1, blocksize);
 	bh = head;
 	nr = 0;
 	i = 0;
@@ -2666,8 +2649,8 @@ int block_truncate_page(struct address_space *mapping,
 		return 0;
 
 	length = blocksize - length;
-	iblock = (sector_t)index << (PAGE_SHIFT - inode->i_blkbits);
-	
+	iblock = ((loff_t)index * PAGE_SIZE) >> inode->i_blkbits;
+
 	folio = filemap_grab_folio(mapping, index);
 	if (IS_ERR(folio))
 		return PTR_ERR(folio);
@@ -2720,17 +2703,15 @@ EXPORT_SYMBOL(block_truncate_page);
 /*
  * The generic ->writepage function for buffer-backed address_spaces
  */
-int block_write_full_page(struct page *page, get_block_t *get_block,
-			struct writeback_control *wbc)
+int block_write_full_folio(struct folio *folio, struct writeback_control *wbc,
+		void *get_block)
 {
-	struct folio *folio = page_folio(page);
 	struct inode * const inode = folio->mapping->host;
 	loff_t i_size = i_size_read(inode);
 
 	/* Is the folio fully inside i_size? */
 	if (folio_pos(folio) + folio_size(folio) <= i_size)
-		return __block_write_full_folio(inode, folio, get_block, wbc,
-					       end_buffer_async_write);
+		return __block_write_full_folio(inode, folio, get_block, wbc);
 
 	/* Is the folio fully outside i_size? (truncate in progress) */
 	if (folio_pos(folio) >= i_size) {
@@ -2747,10 +2728,8 @@ int block_write_full_page(struct page *page, get_block_t *get_block,
 	 */
 	folio_zero_segment(folio, offset_in_folio(folio, i_size),
 			folio_size(folio));
-	return __block_write_full_folio(inode, folio, get_block, wbc,
-			end_buffer_async_write);
+	return __block_write_full_folio(inode, folio, get_block, wbc);
 }
-EXPORT_SYMBOL(block_write_full_page);
 
 sector_t generic_block_bmap(struct address_space *mapping, sector_t block,
 			    get_block_t *get_block)
@@ -2883,7 +2862,7 @@ EXPORT_SYMBOL(sync_dirty_buffer);
  * are unused, and releases them if so.
  *
  * Exclusion against try_to_free_buffers may be obtained by either
- * locking the folio or by holding its mapping's private_lock.
+ * locking the folio or by holding its mapping's i_private_lock.
  *
  * If the folio is dirty but all the buffers are clean then we need to
  * be sure to mark the folio clean as well.  This is because the folio
@@ -2894,7 +2873,7 @@ EXPORT_SYMBOL(sync_dirty_buffer);
  * The same applies to regular filesystem folios: if all the buffers are
  * clean then we set the folio clean and proceed.  To do that, we require
  * total exclusion from block_dirty_folio().  That is obtained with
- * private_lock.
+ * i_private_lock.
  *
  * try_to_free_buffers() is non-blocking.
  */
@@ -2946,7 +2925,7 @@ bool try_to_free_buffers(struct folio *folio)
 		goto out;
 	}
 
-	spin_lock(&mapping->private_lock);
+	spin_lock(&mapping->i_private_lock);
 	ret = drop_buffers(folio, &buffers_to_free);
 
 	/*
@@ -2959,13 +2938,13 @@ bool try_to_free_buffers(struct folio *folio)
 	 * the folio's buffers clean.  We discover that here and clean
 	 * the folio also.
 	 *
-	 * private_lock must be held over this entire operation in order
+	 * i_private_lock must be held over this entire operation in order
 	 * to synchronise against block_dirty_folio and prevent the
 	 * dirty bit from being lost.
 	 */
 	if (ret)
 		folio_cancel_dirty(folio);
-	spin_unlock(&mapping->private_lock);
+	spin_unlock(&mapping->i_private_lock);
 out:
 	if (buffers_to_free) {
 		struct buffer_head *bh = buffers_to_free;
diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c
index aa4efcabb5e3..3f24905f4066 100644
--- a/fs/cachefiles/daemon.c
+++ b/fs/cachefiles/daemon.c
@@ -77,6 +77,7 @@ static const struct cachefiles_daemon_cmd cachefiles_daemon_cmds[] = {
 	{ "tag",	cachefiles_daemon_tag		},
 #ifdef CONFIG_CACHEFILES_ONDEMAND
 	{ "copen",	cachefiles_ondemand_copen	},
+	{ "restore",	cachefiles_ondemand_restore	},
 #endif
 	{ "",		NULL				}
 };
@@ -355,14 +356,24 @@ static __poll_t cachefiles_daemon_poll(struct file *file,
 					   struct poll_table_struct *poll)
 {
 	struct cachefiles_cache *cache = file->private_data;
+	XA_STATE(xas, &cache->reqs, 0);
+	struct cachefiles_req *req;
 	__poll_t mask;
 
 	poll_wait(file, &cache->daemon_pollwq, poll);
 	mask = 0;
 
 	if (cachefiles_in_ondemand_mode(cache)) {
-		if (!xa_empty(&cache->reqs))
-			mask |= EPOLLIN;
+		if (!xa_empty(&cache->reqs)) {
+			rcu_read_lock();
+			xas_for_each_marked(&xas, req, ULONG_MAX, CACHEFILES_REQ_NEW) {
+				if (!cachefiles_ondemand_is_reopening_read(req)) {
+					mask |= EPOLLIN;
+					break;
+				}
+			}
+			rcu_read_unlock();
+		}
 	} else {
 		if (test_bit(CACHEFILES_STATE_CHANGED, &cache->flags))
 			mask |= EPOLLIN;
diff --git a/fs/cachefiles/error_inject.c b/fs/cachefiles/error_inject.c
index 18de8a876b02..1715d5ca2b2d 100644
--- a/fs/cachefiles/error_inject.c
+++ b/fs/cachefiles/error_inject.c
@@ -19,7 +19,6 @@ static struct ctl_table cachefiles_sysctls[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_douintvec,
 	},
-	{}
 };
 
 int __init cachefiles_register_error_injection(void)
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 40052bdb3365..35ba2117a6f6 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -31,6 +31,11 @@ struct cachefiles_object *cachefiles_alloc_object(struct fscache_cookie *cookie)
 	if (!object)
 		return NULL;
 
+	if (cachefiles_ondemand_init_obj_info(object, volume)) {
+		kmem_cache_free(cachefiles_object_jar, object);
+		return NULL;
+	}
+
 	refcount_set(&object->ref, 1);
 
 	spin_lock_init(&object->lock);
@@ -88,7 +93,7 @@ void cachefiles_put_object(struct cachefiles_object *object,
 		ASSERTCMP(object->file, ==, NULL);
 
 		kfree(object->d_name);
-
+		cachefiles_ondemand_deinit_obj_info(object);
 		cache = object->volume->cache->cache;
 		fscache_put_cookie(object->cookie, fscache_cookie_put_object);
 		object->cookie = NULL;
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index 2ad58c465208..4a87c9d714a9 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -44,6 +44,19 @@ struct cachefiles_volume {
 	struct dentry			*fanout[256];	/* Fanout subdirs */
 };
 
+enum cachefiles_object_state {
+	CACHEFILES_ONDEMAND_OBJSTATE_CLOSE, /* Anonymous fd closed by daemon or initial state */
+	CACHEFILES_ONDEMAND_OBJSTATE_OPEN, /* Anonymous fd associated with object is available */
+	CACHEFILES_ONDEMAND_OBJSTATE_REOPENING, /* Object that was closed and is being reopened. */
+};
+
+struct cachefiles_ondemand_info {
+	struct work_struct		ondemand_work;
+	int				ondemand_id;
+	enum cachefiles_object_state	state;
+	struct cachefiles_object	*object;
+};
+
 /*
  * Backing file state.
  */
@@ -61,7 +74,7 @@ struct cachefiles_object {
 	unsigned long			flags;
 #define CACHEFILES_OBJECT_USING_TMPFILE	0		/* Have an unlinked tmpfile */
 #ifdef CONFIG_CACHEFILES_ONDEMAND
-	int				ondemand_id;
+	struct cachefiles_ondemand_info	*ondemand;
 #endif
 };
 
@@ -290,12 +303,42 @@ extern ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
 extern int cachefiles_ondemand_copen(struct cachefiles_cache *cache,
 				     char *args);
 
+extern int cachefiles_ondemand_restore(struct cachefiles_cache *cache,
+					char *args);
+
 extern int cachefiles_ondemand_init_object(struct cachefiles_object *object);
 extern void cachefiles_ondemand_clean_object(struct cachefiles_object *object);
 
 extern int cachefiles_ondemand_read(struct cachefiles_object *object,
 				    loff_t pos, size_t len);
 
+extern int cachefiles_ondemand_init_obj_info(struct cachefiles_object *obj,
+					struct cachefiles_volume *volume);
+extern void cachefiles_ondemand_deinit_obj_info(struct cachefiles_object *obj);
+
+#define CACHEFILES_OBJECT_STATE_FUNCS(_state, _STATE)	\
+static inline bool								\
+cachefiles_ondemand_object_is_##_state(const struct cachefiles_object *object) \
+{												\
+	return object->ondemand->state == CACHEFILES_ONDEMAND_OBJSTATE_##_STATE; \
+}												\
+												\
+static inline void								\
+cachefiles_ondemand_set_object_##_state(struct cachefiles_object *object) \
+{												\
+	object->ondemand->state = CACHEFILES_ONDEMAND_OBJSTATE_##_STATE; \
+}
+
+CACHEFILES_OBJECT_STATE_FUNCS(open, OPEN);
+CACHEFILES_OBJECT_STATE_FUNCS(close, CLOSE);
+CACHEFILES_OBJECT_STATE_FUNCS(reopening, REOPENING);
+
+static inline bool cachefiles_ondemand_is_reopening_read(struct cachefiles_req *req)
+{
+	return cachefiles_ondemand_object_is_reopening(req->object) &&
+			req->msg.opcode == CACHEFILES_OP_READ;
+}
+
 #else
 static inline ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
 					char __user *_buffer, size_t buflen)
@@ -317,6 +360,20 @@ static inline int cachefiles_ondemand_read(struct cachefiles_object *object,
 {
 	return -EOPNOTSUPP;
 }
+
+static inline int cachefiles_ondemand_init_obj_info(struct cachefiles_object *obj,
+						struct cachefiles_volume *volume)
+{
+	return 0;
+}
+static inline void cachefiles_ondemand_deinit_obj_info(struct cachefiles_object *obj)
+{
+}
+
+static inline bool cachefiles_ondemand_is_reopening_read(struct cachefiles_req *req)
+{
+	return false;
+}
 #endif
 
 /*
diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c
index 009d23cd435b..5857241c5918 100644
--- a/fs/cachefiles/io.c
+++ b/fs/cachefiles/io.c
@@ -259,7 +259,8 @@ static void cachefiles_write_complete(struct kiocb *iocb, long ret)
 
 	_enter("%ld", ret);
 
-	kiocb_end_write(iocb);
+	if (ki->was_async)
+		kiocb_end_write(iocb);
 
 	if (ret < 0)
 		trace_cachefiles_io_error(object, inode, ret,
@@ -319,8 +320,6 @@ int __cachefiles_write(struct cachefiles_object *object,
 		ki->iocb.ki_complete = cachefiles_write_complete;
 	atomic_long_add(ki->b_writing, &cache->b_writing);
 
-	kiocb_start_write(&ki->iocb);
-
 	get_file(ki->iocb.ki_filp);
 	cachefiles_grab_object(object, cachefiles_obj_get_ioreq);
 
diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c
index 0254ed39f68c..b8fbbb1961bb 100644
--- a/fs/cachefiles/ondemand.c
+++ b/fs/cachefiles/ondemand.c
@@ -9,21 +9,19 @@ static int cachefiles_ondemand_fd_release(struct inode *inode,
 {
 	struct cachefiles_object *object = file->private_data;
 	struct cachefiles_cache *cache = object->volume->cache;
-	int object_id = object->ondemand_id;
+	struct cachefiles_ondemand_info *info = object->ondemand;
+	int object_id = info->ondemand_id;
 	struct cachefiles_req *req;
 	XA_STATE(xas, &cache->reqs, 0);
 
 	xa_lock(&cache->reqs);
-	object->ondemand_id = CACHEFILES_ONDEMAND_ID_CLOSED;
+	info->ondemand_id = CACHEFILES_ONDEMAND_ID_CLOSED;
+	cachefiles_ondemand_set_object_close(object);
 
-	/*
-	 * Flush all pending READ requests since their completion depends on
-	 * anon_fd.
-	 */
-	xas_for_each(&xas, req, ULONG_MAX) {
+	/* Only flush CACHEFILES_REQ_NEW marked req to avoid race with daemon_read */
+	xas_for_each_marked(&xas, req, ULONG_MAX, CACHEFILES_REQ_NEW) {
 		if (req->msg.object_id == object_id &&
-		    req->msg.opcode == CACHEFILES_OP_READ) {
-			req->error = -EIO;
+		    req->msg.opcode == CACHEFILES_OP_CLOSE) {
 			complete(&req->done);
 			xas_store(&xas, NULL);
 		}
@@ -176,11 +174,37 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args)
 		set_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags);
 	trace_cachefiles_ondemand_copen(req->object, id, size);
 
+	cachefiles_ondemand_set_object_open(req->object);
+	wake_up_all(&cache->daemon_pollwq);
+
 out:
 	complete(&req->done);
 	return ret;
 }
 
+int cachefiles_ondemand_restore(struct cachefiles_cache *cache, char *args)
+{
+	struct cachefiles_req *req;
+
+	XA_STATE(xas, &cache->reqs, 0);
+
+	if (!test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags))
+		return -EOPNOTSUPP;
+
+	/*
+	 * Reset the requests to CACHEFILES_REQ_NEW state, so that the
+	 * requests have been processed halfway before the crash of the
+	 * user daemon could be reprocessed after the recovery.
+	 */
+	xas_lock(&xas);
+	xas_for_each(&xas, req, ULONG_MAX)
+		xas_set_mark(&xas, CACHEFILES_REQ_NEW);
+	xas_unlock(&xas);
+
+	wake_up_all(&cache->daemon_pollwq);
+	return 0;
+}
+
 static int cachefiles_ondemand_get_fd(struct cachefiles_req *req)
 {
 	struct cachefiles_object *object;
@@ -218,8 +242,7 @@ static int cachefiles_ondemand_get_fd(struct cachefiles_req *req)
 
 	load = (void *)req->msg.data;
 	load->fd = fd;
-	req->msg.object_id = object_id;
-	object->ondemand_id = object_id;
+	object->ondemand->ondemand_id = object_id;
 
 	cachefiles_get_unbind_pincount(cache);
 	trace_cachefiles_ondemand_open(object, &req->msg, load);
@@ -234,6 +257,43 @@ err:
 	return ret;
 }
 
+static void ondemand_object_worker(struct work_struct *work)
+{
+	struct cachefiles_ondemand_info *info =
+		container_of(work, struct cachefiles_ondemand_info, ondemand_work);
+
+	cachefiles_ondemand_init_object(info->object);
+}
+
+/*
+ * If there are any inflight or subsequent READ requests on the
+ * closed object, reopen it.
+ * Skip read requests whose related object is reopening.
+ */
+static struct cachefiles_req *cachefiles_ondemand_select_req(struct xa_state *xas,
+							      unsigned long xa_max)
+{
+	struct cachefiles_req *req;
+	struct cachefiles_object *object;
+	struct cachefiles_ondemand_info *info;
+
+	xas_for_each_marked(xas, req, xa_max, CACHEFILES_REQ_NEW) {
+		if (req->msg.opcode != CACHEFILES_OP_READ)
+			return req;
+		object = req->object;
+		info = object->ondemand;
+		if (cachefiles_ondemand_object_is_close(object)) {
+			cachefiles_ondemand_set_object_reopening(object);
+			queue_work(fscache_wq, &info->ondemand_work);
+			continue;
+		}
+		if (cachefiles_ondemand_object_is_reopening(object))
+			continue;
+		return req;
+	}
+	return NULL;
+}
+
 ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
 					char __user *_buffer, size_t buflen)
 {
@@ -244,16 +304,16 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
 	int ret = 0;
 	XA_STATE(xas, &cache->reqs, cache->req_id_next);
 
+	xa_lock(&cache->reqs);
 	/*
 	 * Cyclically search for a request that has not ever been processed,
 	 * to prevent requests from being processed repeatedly, and make
 	 * request distribution fair.
 	 */
-	xa_lock(&cache->reqs);
-	req = xas_find_marked(&xas, UINT_MAX, CACHEFILES_REQ_NEW);
+	req = cachefiles_ondemand_select_req(&xas, ULONG_MAX);
 	if (!req && cache->req_id_next > 0) {
 		xas_set(&xas, 0);
-		req = xas_find_marked(&xas, cache->req_id_next - 1, CACHEFILES_REQ_NEW);
+		req = cachefiles_ondemand_select_req(&xas, cache->req_id_next - 1);
 	}
 	if (!req) {
 		xa_unlock(&cache->reqs);
@@ -273,14 +333,18 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
 	xa_unlock(&cache->reqs);
 
 	id = xas.xa_index;
-	msg->msg_id = id;
 
 	if (msg->opcode == CACHEFILES_OP_OPEN) {
 		ret = cachefiles_ondemand_get_fd(req);
-		if (ret)
+		if (ret) {
+			cachefiles_ondemand_set_object_close(req->object);
 			goto error;
+		}
 	}
 
+	msg->msg_id = id;
+	msg->object_id = req->object->ondemand->ondemand_id;
+
 	if (copy_to_user(_buffer, msg, n) != 0) {
 		ret = -EFAULT;
 		goto err_put_fd;
@@ -313,19 +377,23 @@ static int cachefiles_ondemand_send_req(struct cachefiles_object *object,
 					void *private)
 {
 	struct cachefiles_cache *cache = object->volume->cache;
-	struct cachefiles_req *req;
+	struct cachefiles_req *req = NULL;
 	XA_STATE(xas, &cache->reqs, 0);
 	int ret;
 
 	if (!test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags))
 		return 0;
 
-	if (test_bit(CACHEFILES_DEAD, &cache->flags))
-		return -EIO;
+	if (test_bit(CACHEFILES_DEAD, &cache->flags)) {
+		ret = -EIO;
+		goto out;
+	}
 
 	req = kzalloc(sizeof(*req) + data_len, GFP_KERNEL);
-	if (!req)
-		return -ENOMEM;
+	if (!req) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
 	req->object = object;
 	init_completion(&req->done);
@@ -363,8 +431,9 @@ static int cachefiles_ondemand_send_req(struct cachefiles_object *object,
 		/* coupled with the barrier in cachefiles_flush_reqs() */
 		smp_mb();
 
-		if (opcode != CACHEFILES_OP_OPEN && object->ondemand_id <= 0) {
-			WARN_ON_ONCE(object->ondemand_id == 0);
+		if (opcode == CACHEFILES_OP_CLOSE &&
+			!cachefiles_ondemand_object_is_open(object)) {
+			WARN_ON_ONCE(object->ondemand->ondemand_id == 0);
 			xas_unlock(&xas);
 			ret = -EIO;
 			goto out;
@@ -387,7 +456,15 @@ static int cachefiles_ondemand_send_req(struct cachefiles_object *object,
 	wake_up_all(&cache->daemon_pollwq);
 	wait_for_completion(&req->done);
 	ret = req->error;
+	kfree(req);
+	return ret;
 out:
+	/* Reset the object to close state in error handling path.
+	 * If error occurs after creating the anonymous fd,
+	 * cachefiles_ondemand_fd_release() will set object to close.
+	 */
+	if (opcode == CACHEFILES_OP_OPEN)
+		cachefiles_ondemand_set_object_close(object);
 	kfree(req);
 	return ret;
 }
@@ -430,18 +507,10 @@ static int cachefiles_ondemand_init_close_req(struct cachefiles_req *req,
 					      void *private)
 {
 	struct cachefiles_object *object = req->object;
-	int object_id = object->ondemand_id;
 
-	/*
-	 * It's possible that object id is still 0 if the cookie looking up
-	 * phase failed before OPEN request has ever been sent. Also avoid
-	 * sending CLOSE request for CACHEFILES_ONDEMAND_ID_CLOSED, which means
-	 * anon_fd has already been closed.
-	 */
-	if (object_id <= 0)
+	if (!cachefiles_ondemand_object_is_open(object))
 		return -ENOENT;
 
-	req->msg.object_id = object_id;
 	trace_cachefiles_ondemand_close(object, &req->msg);
 	return 0;
 }
@@ -457,16 +526,7 @@ static int cachefiles_ondemand_init_read_req(struct cachefiles_req *req,
 	struct cachefiles_object *object = req->object;
 	struct cachefiles_read *load = (void *)req->msg.data;
 	struct cachefiles_read_ctx *read_ctx = private;
-	int object_id = object->ondemand_id;
-
-	/* Stop enqueuing requests when daemon has closed anon_fd. */
-	if (object_id <= 0) {
-		WARN_ON_ONCE(object_id == 0);
-		pr_info_once("READ: anonymous fd closed prematurely.\n");
-		return -EIO;
-	}
 
-	req->msg.object_id = object_id;
 	load->off = read_ctx->off;
 	load->len = read_ctx->len;
 	trace_cachefiles_ondemand_read(object, &req->msg, load);
@@ -485,7 +545,7 @@ int cachefiles_ondemand_init_object(struct cachefiles_object *object)
 	 * creating a new tmpfile as the cache file. Reuse the previously
 	 * allocated object ID if any.
 	 */
-	if (object->ondemand_id > 0)
+	if (cachefiles_ondemand_object_is_open(object))
 		return 0;
 
 	volume_key_size = volume->key[0] + 1;
@@ -503,6 +563,28 @@ void cachefiles_ondemand_clean_object(struct cachefiles_object *object)
 			cachefiles_ondemand_init_close_req, NULL);
 }
 
+int cachefiles_ondemand_init_obj_info(struct cachefiles_object *object,
+				struct cachefiles_volume *volume)
+{
+	if (!cachefiles_in_ondemand_mode(volume->cache))
+		return 0;
+
+	object->ondemand = kzalloc(sizeof(struct cachefiles_ondemand_info),
+					GFP_KERNEL);
+	if (!object->ondemand)
+		return -ENOMEM;
+
+	object->ondemand->object = object;
+	INIT_WORK(&object->ondemand->ondemand_work, ondemand_object_worker);
+	return 0;
+}
+
+void cachefiles_ondemand_deinit_obj_info(struct cachefiles_object *object)
+{
+	kfree(object->ondemand);
+	object->ondemand = NULL;
+}
+
 int cachefiles_ondemand_read(struct cachefiles_object *object,
 			     loff_t pos, size_t len)
 {
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 85be3bf18cdf..13af429ab030 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -907,8 +907,8 @@ static void writepages_finish(struct ceph_osd_request *req)
 			doutc(cl, "unlocking %p\n", page);
 
 			if (remove_page)
-				generic_error_remove_page(inode->i_mapping,
-							  page);
+				generic_error_remove_folio(inode->i_mapping,
+							  page_folio(page));
 
 			unlock_page(page);
 		}
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 3b5aae29e944..d380d9dad0e0 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -12,6 +12,7 @@
 #include <linux/falloc.h>
 #include <linux/iversion.h>
 #include <linux/ktime.h>
+#include <linux/splice.h>
 
 #include "super.h"
 #include "mds_client.h"
@@ -3010,8 +3011,8 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
 		 * {read,write}_iter, which will get caps again.
 		 */
 		put_rd_wr_caps(src_ci, src_got, dst_ci, dst_got);
-		ret = do_splice_direct(src_file, &src_off, dst_file,
-				       &dst_off, src_objlen, flags);
+		ret = splice_file_range(src_file, &src_off, dst_file, &dst_off,
+					src_objlen);
 		/* Abort on short copies or on error */
 		if (ret < (long)src_objlen) {
 			doutc(cl, "Failed partial copy (%zd)\n", ret);
@@ -3065,8 +3066,8 @@ out_caps:
 	 */
 	if (len && (len < src_ci->i_layout.object_size)) {
 		doutc(cl, "Final partial copy of %zu bytes\n", len);
-		bytes = do_splice_direct(src_file, &src_off, dst_file,
-					 &dst_off, len, flags);
+		bytes = splice_file_range(src_file, &src_off, dst_file,
+					  &dst_off, len);
 		if (bytes > 0)
 			ret += bytes;
 		else
@@ -3089,8 +3090,8 @@ static ssize_t ceph_copy_file_range(struct file *src_file, loff_t src_off,
 				     len, flags);
 
 	if (ret == -EOPNOTSUPP || ret == -EXDEV)
-		ret = generic_copy_file_range(src_file, src_off, dst_file,
-					      dst_off, len, flags);
+		ret = splice_copy_file_range(src_file, src_off, dst_file,
+					     dst_off, len);
 	return ret;
 }
 
diff --git a/fs/coda/file.c b/fs/coda/file.c
index 16acc58311ea..148856a582a9 100644
--- a/fs/coda/file.c
+++ b/fs/coda/file.c
@@ -79,14 +79,12 @@ coda_file_write_iter(struct kiocb *iocb, struct iov_iter *to)
 	if (ret)
 		goto finish_write;
 
-	file_start_write(host_file);
 	inode_lock(coda_inode);
 	ret = vfs_iter_write(cfi->cfi_container, to, &iocb->ki_pos, 0);
 	coda_inode->i_size = file_inode(host_file)->i_size;
 	coda_inode->i_blocks = (coda_inode->i_size + 511) >> 9;
 	inode_set_mtime_to_ts(coda_inode, inode_set_ctime_current(coda_inode));
 	inode_unlock(coda_inode);
-	file_end_write(host_file);
 
 finish_write:
 	venus_access_intent(coda_inode->i_sb, coda_i2f(coda_inode),
diff --git a/fs/coda/sysctl.c b/fs/coda/sysctl.c
index a247c14aaab7..9f2d5743e2c8 100644
--- a/fs/coda/sysctl.c
+++ b/fs/coda/sysctl.c
@@ -36,7 +36,6 @@ static struct ctl_table coda_table[] = {
 		.mode		= 0600,
 		.proc_handler	= proc_dointvec
 	},
-	{}
 };
 
 void coda_sysctl_init(void)
diff --git a/fs/coredump.c b/fs/coredump.c
index 9d235fa14ab9..f258c17c1841 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -981,7 +981,6 @@ static struct ctl_table coredump_sysctls[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-	{ }
 };
 
 static int __init init_fs_coredump_sysctls(void)
diff --git a/fs/crypto/Kconfig b/fs/crypto/Kconfig
index 2d0c8922f635..5aff5934baa1 100644
--- a/fs/crypto/Kconfig
+++ b/fs/crypto/Kconfig
@@ -11,7 +11,7 @@ config FS_ENCRYPTION
 	  feature is similar to ecryptfs, but it is more memory
 	  efficient since it avoids caching the encrypted and
 	  decrypted pages in the page cache.  Currently Ext4,
-	  F2FS and UBIFS make use of this feature.
+	  F2FS, UBIFS, and CephFS make use of this feature.
 
 # Filesystems supporting encryption must select this if FS_ENCRYPTION.  This
 # allows the algorithms to be built as modules when all the filesystems are,
diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c
index f34a9b0b9e92..0edf0b58daa7 100644
--- a/fs/crypto/keyring.c
+++ b/fs/crypto/keyring.c
@@ -1002,9 +1002,9 @@ static int try_to_lock_encrypted_files(struct super_block *sb,
  * FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS (all_users=true) always removes the
  * key itself.
  *
- * To "remove the key itself", first we wipe the actual master key secret, so
- * that no more inodes can be unlocked with it.  Then we try to evict all cached
- * inodes that had been unlocked with the key.
+ * To "remove the key itself", first we transition the key to the "incompletely
+ * removed" state, so that no more inodes can be unlocked with it.  Then we try
+ * to evict all cached inodes that had been unlocked with the key.
  *
  * If all inodes were evicted, then we unlink the fscrypt_master_key from the
  * keyring.  Otherwise it remains in the keyring in the "incompletely removed"
diff --git a/fs/dax.c b/fs/dax.c
index 3380b43cb6bb..423fc1607dfa 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1128,7 +1128,7 @@ static int dax_iomap_copy_around(loff_t pos, uint64_t length, size_t align_size,
 	/* zero the edges if srcmap is a HOLE or IOMAP_UNWRITTEN */
 	bool zero_edge = srcmap->flags & IOMAP_F_SHARED ||
 			 srcmap->type == IOMAP_UNWRITTEN;
-	void *saddr = 0;
+	void *saddr = NULL;
 	int ret = 0;
 
 	if (!zero_edge) {
diff --git a/fs/dcache.c b/fs/dcache.c
index c82ae731df9a..df49d29ca154 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -191,7 +191,6 @@ static struct ctl_table fs_dcache_sysctls[] = {
 		.mode		= 0444,
 		.proc_handler	= proc_nr_dentry,
 	},
-	{ }
 };
 
 static int __init init_fs_dcache_sysctls(void)
@@ -428,7 +427,8 @@ static void d_lru_add(struct dentry *dentry)
 	this_cpu_inc(nr_dentry_unused);
 	if (d_is_negative(dentry))
 		this_cpu_inc(nr_dentry_negative);
-	WARN_ON_ONCE(!list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
+	WARN_ON_ONCE(!list_lru_add_obj(
+			&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
 }
 
 static void d_lru_del(struct dentry *dentry)
@@ -438,7 +438,8 @@ static void d_lru_del(struct dentry *dentry)
 	this_cpu_dec(nr_dentry_unused);
 	if (d_is_negative(dentry))
 		this_cpu_dec(nr_dentry_negative);
-	WARN_ON_ONCE(!list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
+	WARN_ON_ONCE(!list_lru_del_obj(
+			&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
 }
 
 static void d_shrink_del(struct dentry *dentry)
@@ -1240,7 +1241,7 @@ static enum lru_status dentry_lru_isolate(struct list_head *item,
 		 *
 		 * This is guaranteed by the fact that all LRU management
 		 * functions are intermediated by the LRU API calls like
-		 * list_lru_add and list_lru_del. List movement in this file
+		 * list_lru_add_obj and list_lru_del_obj. List movement in this file
 		 * only ever occur through this functions or through callbacks
 		 * like this one, that are called from the LRU API.
 		 *
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index c45e8c2d62e1..c6f4a9a98b85 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -84,6 +84,14 @@ int debugfs_file_get(struct dentry *dentry)
 	struct debugfs_fsdata *fsd;
 	void *d_fsd;
 
+	/*
+	 * This could only happen if some debugfs user erroneously calls
+	 * debugfs_file_get() on a dentry that isn't even a file, let
+	 * them know about it.
+	 */
+	if (WARN_ON(!d_is_reg(dentry)))
+		return -EINVAL;
+
 	d_fsd = READ_ONCE(dentry->d_fsdata);
 	if (!((unsigned long)d_fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) {
 		fsd = d_fsd;
@@ -96,7 +104,11 @@ int debugfs_file_get(struct dentry *dentry)
 					~DEBUGFS_FSDATA_IS_REAL_FOPS_BIT);
 		refcount_set(&fsd->active_users, 1);
 		init_completion(&fsd->active_users_drained);
+		INIT_LIST_HEAD(&fsd->cancellations);
+		mutex_init(&fsd->cancellations_mtx);
+
 		if (cmpxchg(&dentry->d_fsdata, d_fsd, fsd) != d_fsd) {
+			mutex_destroy(&fsd->cancellations_mtx);
 			kfree(fsd);
 			fsd = READ_ONCE(dentry->d_fsdata);
 		}
@@ -138,6 +150,86 @@ void debugfs_file_put(struct dentry *dentry)
 }
 EXPORT_SYMBOL_GPL(debugfs_file_put);
 
+/**
+ * debugfs_enter_cancellation - enter a debugfs cancellation
+ * @file: the file being accessed
+ * @cancellation: the cancellation object, the cancel callback
+ *	inside of it must be initialized
+ *
+ * When a debugfs file is removed it needs to wait for all active
+ * operations to complete. However, the operation itself may need
+ * to wait for hardware or completion of some asynchronous process
+ * or similar. As such, it may need to be cancelled to avoid long
+ * waits or even deadlocks.
+ *
+ * This function can be used inside a debugfs handler that may
+ * need to be cancelled. As soon as this function is called, the
+ * cancellation's 'cancel' callback may be called, at which point
+ * the caller should proceed to call debugfs_leave_cancellation()
+ * and leave the debugfs handler function as soon as possible.
+ * Note that the 'cancel' callback is only ever called in the
+ * context of some kind of debugfs_remove().
+ *
+ * This function must be paired with debugfs_leave_cancellation().
+ */
+void debugfs_enter_cancellation(struct file *file,
+				struct debugfs_cancellation *cancellation)
+{
+	struct debugfs_fsdata *fsd;
+	struct dentry *dentry = F_DENTRY(file);
+
+	INIT_LIST_HEAD(&cancellation->list);
+
+	if (WARN_ON(!d_is_reg(dentry)))
+		return;
+
+	if (WARN_ON(!cancellation->cancel))
+		return;
+
+	fsd = READ_ONCE(dentry->d_fsdata);
+	if (WARN_ON(!fsd ||
+		    ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)))
+		return;
+
+	mutex_lock(&fsd->cancellations_mtx);
+	list_add(&cancellation->list, &fsd->cancellations);
+	mutex_unlock(&fsd->cancellations_mtx);
+
+	/* if we're already removing wake it up to cancel */
+	if (d_unlinked(dentry))
+		complete(&fsd->active_users_drained);
+}
+EXPORT_SYMBOL_GPL(debugfs_enter_cancellation);
+
+/**
+ * debugfs_leave_cancellation - leave cancellation section
+ * @file: the file being accessed
+ * @cancellation: the cancellation previously registered with
+ *	debugfs_enter_cancellation()
+ *
+ * See the documentation of debugfs_enter_cancellation().
+ */
+void debugfs_leave_cancellation(struct file *file,
+				struct debugfs_cancellation *cancellation)
+{
+	struct debugfs_fsdata *fsd;
+	struct dentry *dentry = F_DENTRY(file);
+
+	if (WARN_ON(!d_is_reg(dentry)))
+		return;
+
+	fsd = READ_ONCE(dentry->d_fsdata);
+	if (WARN_ON(!fsd ||
+		    ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)))
+		return;
+
+	mutex_lock(&fsd->cancellations_mtx);
+	if (!list_empty(&cancellation->list))
+		list_del(&cancellation->list);
+	mutex_unlock(&fsd->cancellations_mtx);
+}
+EXPORT_SYMBOL_GPL(debugfs_leave_cancellation);
+
 /*
  * Only permit access to world-readable files when the kernel is locked down.
  * We also need to exclude any file that has ways to write or alter it as root
@@ -1008,17 +1100,35 @@ static ssize_t read_file_blob(struct file *file, char __user *user_buf,
 	return r;
 }
 
+static ssize_t write_file_blob(struct file *file, const char __user *user_buf,
+			       size_t count, loff_t *ppos)
+{
+	struct debugfs_blob_wrapper *blob = file->private_data;
+	struct dentry *dentry = F_DENTRY(file);
+	ssize_t r;
+
+	r = debugfs_file_get(dentry);
+	if (unlikely(r))
+		return r;
+	r = simple_write_to_buffer(blob->data, blob->size, ppos, user_buf,
+				   count);
+
+	debugfs_file_put(dentry);
+	return r;
+}
+
 static const struct file_operations fops_blob = {
 	.read =		read_file_blob,
+	.write =	write_file_blob,
 	.open =		simple_open,
 	.llseek =	default_llseek,
 };
 
 /**
- * debugfs_create_blob - create a debugfs file that is used to read a binary blob
+ * debugfs_create_blob - create a debugfs file that is used to read and write
+ * a binary blob
  * @name: a pointer to a string containing the name of the file to create.
- * @mode: the read permission that the file should have (other permissions are
- *	  masked out)
+ * @mode: the permission that the file should have
  * @parent: a pointer to the parent dentry for this file.  This should be a
  *          directory dentry if set.  If this parameter is %NULL, then the
  *          file will be created in the root of the debugfs filesystem.
@@ -1027,7 +1137,7 @@ static const struct file_operations fops_blob = {
  *
  * This function creates a file in debugfs with the given name that exports
  * @blob->data as a binary blob. If the @mode variable is so set it can be
- * read from. Writing is not supported.
+ * read from and written to.
  *
  * This function will return a pointer to a dentry if it succeeds.  This
  * pointer must be passed to the debugfs_remove() function when the file is
@@ -1042,7 +1152,7 @@ struct dentry *debugfs_create_blob(const char *name, umode_t mode,
 				   struct dentry *parent,
 				   struct debugfs_blob_wrapper *blob)
 {
-	return debugfs_create_file_unsafe(name, mode & 0444, parent, blob, &fops_blob);
+	return debugfs_create_file_unsafe(name, mode & 0644, parent, blob, &fops_blob);
 }
 EXPORT_SYMBOL_GPL(debugfs_create_blob);
 
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 5d41765e0c77..034a617cb1a5 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -236,17 +236,25 @@ static const struct super_operations debugfs_super_operations = {
 
 static void debugfs_release_dentry(struct dentry *dentry)
 {
-	void *fsd = dentry->d_fsdata;
+	struct debugfs_fsdata *fsd = dentry->d_fsdata;
 
-	if (!((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))
-		kfree(dentry->d_fsdata);
+	if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)
+		return;
+
+	/* check it wasn't a dir (no fsdata) or automount (no real_fops) */
+	if (fsd && fsd->real_fops) {
+		WARN_ON(!list_empty(&fsd->cancellations));
+		mutex_destroy(&fsd->cancellations_mtx);
+	}
+
+	kfree(fsd);
 }
 
 static struct vfsmount *debugfs_automount(struct path *path)
 {
-	debugfs_automount_t f;
-	f = (debugfs_automount_t)path->dentry->d_fsdata;
-	return f(path->dentry, d_inode(path->dentry)->i_private);
+	struct debugfs_fsdata *fsd = path->dentry->d_fsdata;
+
+	return fsd->automount(path->dentry, d_inode(path->dentry)->i_private);
 }
 
 static const struct dentry_operations debugfs_dops = {
@@ -634,13 +642,23 @@ struct dentry *debugfs_create_automount(const char *name,
 					void *data)
 {
 	struct dentry *dentry = start_creating(name, parent);
+	struct debugfs_fsdata *fsd;
 	struct inode *inode;
 
 	if (IS_ERR(dentry))
 		return dentry;
 
+	fsd = kzalloc(sizeof(*fsd), GFP_KERNEL);
+	if (!fsd) {
+		failed_creating(dentry);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	fsd->automount = f;
+
 	if (!(debugfs_allow & DEBUGFS_ALLOW_API)) {
 		failed_creating(dentry);
+		kfree(fsd);
 		return ERR_PTR(-EPERM);
 	}
 
@@ -648,13 +666,14 @@ struct dentry *debugfs_create_automount(const char *name,
 	if (unlikely(!inode)) {
 		pr_err("out of free dentries, can not create automount '%s'\n",
 		       name);
+		kfree(fsd);
 		return failed_creating(dentry);
 	}
 
 	make_empty_dir_inode(inode);
 	inode->i_flags |= S_AUTOMOUNT;
 	inode->i_private = data;
-	dentry->d_fsdata = (void *)f;
+	dentry->d_fsdata = fsd;
 	/* directory inodes start off with i_nlink == 2 (for "." entry) */
 	inc_nlink(inode);
 	d_instantiate(dentry, inode);
@@ -731,8 +750,37 @@ static void __debugfs_file_removed(struct dentry *dentry)
 	fsd = READ_ONCE(dentry->d_fsdata);
 	if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)
 		return;
-	if (!refcount_dec_and_test(&fsd->active_users))
+
+	/* if we hit zero, just wait for all to finish */
+	if (!refcount_dec_and_test(&fsd->active_users)) {
 		wait_for_completion(&fsd->active_users_drained);
+		return;
+	}
+
+	/* if we didn't hit zero, try to cancel any we can */
+	while (refcount_read(&fsd->active_users)) {
+		struct debugfs_cancellation *c;
+
+		/*
+		 * Lock the cancellations. Note that the cancellations
+		 * structs are meant to be on the stack, so we need to
+		 * ensure we either use them here or don't touch them,
+		 * and debugfs_leave_cancellation() will wait for this
+		 * to be finished processing before exiting one. It may
+		 * of course win and remove the cancellation, but then
+		 * chances are we never even got into this bit, we only
+		 * do if the refcount isn't zero already.
+		 */
+		mutex_lock(&fsd->cancellations_mtx);
+		while ((c = list_first_entry_or_null(&fsd->cancellations,
+						     typeof(*c), list))) {
+			list_del_init(&c->list);
+			c->cancel(dentry, c->cancel_data);
+		}
+		mutex_unlock(&fsd->cancellations_mtx);
+
+		wait_for_completion(&fsd->active_users_drained);
+	}
 }
 
 static void remove_one(struct dentry *victim)
diff --git a/fs/debugfs/internal.h b/fs/debugfs/internal.h
index 92af8ae31313..dae80c2a469e 100644
--- a/fs/debugfs/internal.h
+++ b/fs/debugfs/internal.h
@@ -7,6 +7,7 @@
 
 #ifndef _DEBUGFS_INTERNAL_H_
 #define _DEBUGFS_INTERNAL_H_
+#include <linux/list.h>
 
 struct file_operations;
 
@@ -17,8 +18,18 @@ extern const struct file_operations debugfs_full_proxy_file_operations;
 
 struct debugfs_fsdata {
 	const struct file_operations *real_fops;
-	refcount_t active_users;
-	struct completion active_users_drained;
+	union {
+		/* automount_fn is used when real_fops is NULL */
+		debugfs_automount_t automount;
+		struct {
+			refcount_t active_users;
+			struct completion active_users_drained;
+
+			/* protect cancellations */
+			struct mutex cancellations_mtx;
+			struct list_head cancellations;
+		};
+	};
 };
 
 /*
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index c830261aa883..b20e565b9c5e 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -69,7 +69,6 @@ static struct ctl_table pty_table[] = {
 		.data		= &pty_count,
 		.proc_handler	= proc_dointvec,
 	},
-	{}
 };
 
 struct pts_mount_opts {
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 20533266ade6..60456263a338 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1114,7 +1114,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	loff_t offset = iocb->ki_pos;
 	const loff_t end = offset + count;
 	struct dio *dio;
-	struct dio_submit sdio = { 0, };
+	struct dio_submit sdio = { NULL, };
 	struct buffer_head map_bh = { 0, };
 	struct blk_plug plug;
 	unsigned long align = offset | iov_iter_alignment(iter);
diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c
index 42f332f46359..4fa11d9ddbb6 100644
--- a/fs/dlm/debug_fs.c
+++ b/fs/dlm/debug_fs.c
@@ -443,14 +443,14 @@ static int table_seq_show(struct seq_file *seq, void *iter_ptr)
 		break;
 	case 3:
 		if (ri->header) {
-			seq_puts(seq, "version rsb 1.1 lvb 1.1 lkb 1.1\n");
+			seq_puts(seq, "rsb ptr nodeid first_lkid flags !root_list_empty !recover_list_empty recover_locks_count len\n");
 			ri->header = 0;
 		}
 		print_format3(ri->rsb, seq);
 		break;
 	case 4:
 		if (ri->header) {
-			seq_puts(seq, "version 4 rsb 2\n");
+			seq_puts(seq, "rsb ptr nodeid master_nodeid dir_nodeid our_nodeid toss_time flags len str|hex name\n");
 			ri->header = 0;
 		}
 		print_format4(ri->rsb, seq);
@@ -748,7 +748,7 @@ static int table_open4(struct inode *inode, struct file *file)
 	struct seq_file *seq;
 	int ret;
 
-	ret = seq_open(file, &format5_seq_ops);
+	ret = seq_open(file, &format4_seq_ops);
 	if (ret)
 		return ret;
 
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 67f8dd8a05ef..6296c62c10fa 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -1817,8 +1817,8 @@ static int dlm_tcp_bind(struct socket *sock)
 	memcpy(&src_addr, &dlm_local_addr[0], sizeof(src_addr));
 	make_sockaddr(&src_addr, 0, &addr_len);
 
-	result = sock->ops->bind(sock, (struct sockaddr *)&src_addr,
-				 addr_len);
+	result = kernel_bind(sock, (struct sockaddr *)&src_addr,
+			     addr_len);
 	if (result < 0) {
 		/* This *may* not indicate a critical error */
 		log_print("could not bind for connect: %d", result);
@@ -1830,7 +1830,7 @@ static int dlm_tcp_bind(struct socket *sock)
 static int dlm_tcp_connect(struct connection *con, struct socket *sock,
 			   struct sockaddr *addr, int addr_len)
 {
-	return sock->ops->connect(sock, addr, addr_len, O_NONBLOCK);
+	return kernel_connect(sock, addr, addr_len, O_NONBLOCK);
 }
 
 static int dlm_tcp_listen_validate(void)
@@ -1862,8 +1862,8 @@ static int dlm_tcp_listen_bind(struct socket *sock)
 
 	/* Bind to our port */
 	make_sockaddr(&dlm_local_addr[0], dlm_config.ci_tcp_port, &addr_len);
-	return sock->ops->bind(sock, (struct sockaddr *)&dlm_local_addr[0],
-			       addr_len);
+	return kernel_bind(sock, (struct sockaddr *)&dlm_local_addr[0],
+			   addr_len);
 }
 
 static const struct dlm_proto_ops dlm_tcp_ops = {
@@ -1888,12 +1888,12 @@ static int dlm_sctp_connect(struct connection *con, struct socket *sock,
 	int ret;
 
 	/*
-	 * Make sock->ops->connect() function return in specified time,
+	 * Make kernel_connect() function return in specified time,
 	 * since O_NONBLOCK argument in connect() function does not work here,
 	 * then, we should restore the default value of this attribute.
 	 */
 	sock_set_sndtimeo(sock->sk, 5);
-	ret = sock->ops->connect(sock, addr, addr_len, 0);
+	ret = kernel_connect(sock, addr, addr_len, 0);
 	sock_set_sndtimeo(sock->sk, 0);
 	return ret;
 }
diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c
index e6b4c1a21446..d814c5121367 100644
--- a/fs/dlm/plock.c
+++ b/fs/dlm/plock.c
@@ -140,11 +140,12 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 	op->info.optype		= DLM_PLOCK_OP_LOCK;
 	op->info.pid		= fl->fl_pid;
 	op->info.ex		= (fl->fl_type == F_WRLCK);
-	op->info.wait		= IS_SETLKW(cmd);
+	op->info.wait		= !!(fl->fl_flags & FL_SLEEP);
 	op->info.fsid		= ls->ls_global_id;
 	op->info.number		= number;
 	op->info.start		= fl->fl_start;
 	op->info.end		= fl->fl_end;
+	op->info.owner = (__u64)(long)fl->fl_owner;
 	/* async handling */
 	if (fl->fl_lmops && fl->fl_lmops->lm_grant) {
 		op_data = kzalloc(sizeof(*op_data), GFP_NOFS);
@@ -154,9 +155,6 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 			goto out;
 		}
 
-		/* fl_owner is lockd which doesn't distinguish
-		   processes on the nfs client */
-		op->info.owner	= (__u64) fl->fl_pid;
 		op_data->callback = fl->fl_lmops->lm_grant;
 		locks_init_lock(&op_data->flc);
 		locks_copy_lock(&op_data->flc, fl);
@@ -168,8 +166,6 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 		send_op(op);
 		rv = FILE_LOCK_DEFERRED;
 		goto out;
-	} else {
-		op->info.owner	= (__u64)(long) fl->fl_owner;
 	}
 
 	send_op(op);
@@ -326,10 +322,7 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 	op->info.number		= number;
 	op->info.start		= fl->fl_start;
 	op->info.end		= fl->fl_end;
-	if (fl->fl_lmops && fl->fl_lmops->lm_grant)
-		op->info.owner	= (__u64) fl->fl_pid;
-	else
-		op->info.owner	= (__u64)(long) fl->fl_owner;
+	op->info.owner = (__u64)(long)fl->fl_owner;
 
 	if (fl->fl_flags & FL_CLOSE) {
 		op->info.flags |= DLM_PLOCK_FL_CLOSE;
@@ -389,7 +382,7 @@ int dlm_posix_cancel(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 	info.number = number;
 	info.start = fl->fl_start;
 	info.end = fl->fl_end;
-	info.owner = (__u64)fl->fl_pid;
+	info.owner = (__u64)(long)fl->fl_owner;
 
 	rv = do_lock_cancel(&info);
 	switch (rv) {
@@ -450,10 +443,7 @@ int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 	op->info.number		= number;
 	op->info.start		= fl->fl_start;
 	op->info.end		= fl->fl_end;
-	if (fl->fl_lmops && fl->fl_lmops->lm_grant)
-		op->info.owner	= (__u64) fl->fl_pid;
-	else
-		op->info.owner	= (__u64)(long) fl->fl_owner;
+	op->info.owner = (__u64)(long)fl->fl_owner;
 
 	send_op(op);
 	wait_event(recv_wq, (op->done != 0));
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index a25dd3d20008..d7193687b9b4 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -78,6 +78,14 @@ static struct inode *__ecryptfs_get_inode(struct inode *lower_inode,
 
 	if (lower_inode->i_sb != ecryptfs_superblock_to_lower(sb))
 		return ERR_PTR(-EXDEV);
+
+	/* Reject dealing with casefold directories. */
+	if (IS_CASEFOLDED(lower_inode)) {
+		pr_err_ratelimited("%s: Can't handle casefolded directory.\n",
+				   __func__);
+		return ERR_PTR(-EREMOTE);
+	}
+
 	if (!igrab(lower_inode))
 		return ERR_PTR(-ESTALE);
 	inode = iget5_locked(sb, (unsigned long)lower_inode,
@@ -998,6 +1006,14 @@ static int ecryptfs_getattr_link(struct mnt_idmap *idmap,
 	return rc;
 }
 
+static int ecryptfs_do_getattr(const struct path *path, struct kstat *stat,
+			       u32 request_mask, unsigned int flags)
+{
+	if (flags & AT_GETATTR_NOSEC)
+		return vfs_getattr_nosec(path, stat, request_mask, flags);
+	return vfs_getattr(path, stat, request_mask, flags);
+}
+
 static int ecryptfs_getattr(struct mnt_idmap *idmap,
 			    const struct path *path, struct kstat *stat,
 			    u32 request_mask, unsigned int flags)
@@ -1006,8 +1022,8 @@ static int ecryptfs_getattr(struct mnt_idmap *idmap,
 	struct kstat lower_stat;
 	int rc;
 
-	rc = vfs_getattr(ecryptfs_dentry_to_lower_path(dentry), &lower_stat,
-			 request_mask, flags);
+	rc = ecryptfs_do_getattr(ecryptfs_dentry_to_lower_path(dentry),
+				 &lower_stat, request_mask, flags);
 	if (!rc) {
 		fsstack_copy_attr_all(d_inode(dentry),
 				      ecryptfs_inode_to_lower(d_inode(dentry)));
diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c
index 91290fe4a70b..586446e02ef7 100644
--- a/fs/efivarfs/inode.c
+++ b/fs/efivarfs/inode.c
@@ -77,6 +77,7 @@ bool efivarfs_valid_name(const char *str, int len)
 static int efivarfs_create(struct mnt_idmap *idmap, struct inode *dir,
 			   struct dentry *dentry, umode_t mode, bool excl)
 {
+	struct efivarfs_fs_info *info = dir->i_sb->s_fs_info;
 	struct inode *inode = NULL;
 	struct efivar_entry *var;
 	int namelen, i = 0, err = 0;
@@ -118,7 +119,7 @@ static int efivarfs_create(struct mnt_idmap *idmap, struct inode *dir,
 	inode->i_private = var;
 	kmemleak_ignore(var);
 
-	err = efivar_entry_add(var, &efivarfs_list);
+	err = efivar_entry_add(var, &info->efivarfs_list);
 	if (err)
 		goto out;
 
diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h
index c66647f5c0bd..169252e6dc46 100644
--- a/fs/efivarfs/internal.h
+++ b/fs/efivarfs/internal.h
@@ -16,6 +16,9 @@ struct efivarfs_mount_opts {
 
 struct efivarfs_fs_info {
 	struct efivarfs_mount_opts mount_opts;
+	struct list_head efivarfs_list;
+	struct super_block *sb;
+	struct notifier_block nb;
 };
 
 struct efi_variable {
@@ -33,7 +36,8 @@ struct efivar_entry {
 	struct kobject kobj;
 };
 
-int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *),
+int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *,
+			    struct list_head *),
 		void *data, bool duplicates, struct list_head *head);
 
 int efivar_entry_add(struct efivar_entry *entry, struct list_head *head);
@@ -64,6 +68,4 @@ extern struct inode *efivarfs_get_inode(struct super_block *sb,
 			const struct inode *dir, int mode, dev_t dev,
 			bool is_removable);
 
-extern struct list_head efivarfs_list;
-
 #endif /* EFIVAR_FS_INTERNAL_H */
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index 77240953a92e..6038dd39367a 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -15,10 +15,29 @@
 #include <linux/slab.h>
 #include <linux/magic.h>
 #include <linux/statfs.h>
+#include <linux/notifier.h>
+#include <linux/printk.h>
 
 #include "internal.h"
 
-LIST_HEAD(efivarfs_list);
+static int efivarfs_ops_notifier(struct notifier_block *nb, unsigned long event,
+				 void *data)
+{
+	struct efivarfs_fs_info *sfi = container_of(nb, struct efivarfs_fs_info, nb);
+
+	switch (event) {
+	case EFIVAR_OPS_RDONLY:
+		sfi->sb->s_flags |= SB_RDONLY;
+		break;
+	case EFIVAR_OPS_RDWR:
+		sfi->sb->s_flags &= ~SB_RDONLY;
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
 
 static void efivarfs_evict_inode(struct inode *inode)
 {
@@ -166,7 +185,8 @@ static struct dentry *efivarfs_alloc_dentry(struct dentry *parent, char *name)
 }
 
 static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
-			     unsigned long name_size, void *data)
+			     unsigned long name_size, void *data,
+			     struct list_head *list)
 {
 	struct super_block *sb = (struct super_block *)data;
 	struct efivar_entry *entry;
@@ -221,7 +241,7 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 	}
 
 	__efivar_entry_get(entry, NULL, &size, NULL);
-	__efivar_entry_add(entry, &efivarfs_list);
+	__efivar_entry_add(entry, list);
 
 	/* copied by the above to local storage in the dentry. */
 	kfree(name);
@@ -291,13 +311,11 @@ static int efivarfs_parse_param(struct fs_context *fc, struct fs_parameter *para
 
 static int efivarfs_fill_super(struct super_block *sb, struct fs_context *fc)
 {
+	struct efivarfs_fs_info *sfi = sb->s_fs_info;
 	struct inode *inode = NULL;
 	struct dentry *root;
 	int err;
 
-	if (!efivar_is_available())
-		return -EOPNOTSUPP;
-
 	sb->s_maxbytes          = MAX_LFS_FILESIZE;
 	sb->s_blocksize         = PAGE_SIZE;
 	sb->s_blocksize_bits    = PAGE_SHIFT;
@@ -319,11 +337,16 @@ static int efivarfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	if (!root)
 		return -ENOMEM;
 
-	INIT_LIST_HEAD(&efivarfs_list);
+	sfi->sb = sb;
+	sfi->nb.notifier_call = efivarfs_ops_notifier;
+	err = blocking_notifier_chain_register(&efivar_ops_nh, &sfi->nb);
+	if (err)
+		return err;
 
-	err = efivar_init(efivarfs_callback, (void *)sb, true, &efivarfs_list);
+	err = efivar_init(efivarfs_callback, (void *)sb, true,
+			  &sfi->efivarfs_list);
 	if (err)
-		efivar_entry_iter(efivarfs_destroy, &efivarfs_list, NULL);
+		efivar_entry_iter(efivarfs_destroy, &sfi->efivarfs_list, NULL);
 
 	return err;
 }
@@ -333,19 +356,35 @@ static int efivarfs_get_tree(struct fs_context *fc)
 	return get_tree_single(fc, efivarfs_fill_super);
 }
 
+static int efivarfs_reconfigure(struct fs_context *fc)
+{
+	if (!efivar_supports_writes() && !(fc->sb_flags & SB_RDONLY)) {
+		pr_err("Firmware does not support SetVariableRT. Can not remount with rw\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct fs_context_operations efivarfs_context_ops = {
 	.get_tree	= efivarfs_get_tree,
 	.parse_param	= efivarfs_parse_param,
+	.reconfigure	= efivarfs_reconfigure,
 };
 
 static int efivarfs_init_fs_context(struct fs_context *fc)
 {
 	struct efivarfs_fs_info *sfi;
 
+	if (!efivar_is_available())
+		return -EOPNOTSUPP;
+
 	sfi = kzalloc(sizeof(*sfi), GFP_KERNEL);
 	if (!sfi)
 		return -ENOMEM;
 
+	INIT_LIST_HEAD(&sfi->efivarfs_list);
+
 	sfi->mount_opts.uid = GLOBAL_ROOT_UID;
 	sfi->mount_opts.gid = GLOBAL_ROOT_GID;
 
@@ -356,13 +395,14 @@ static int efivarfs_init_fs_context(struct fs_context *fc)
 
 static void efivarfs_kill_sb(struct super_block *sb)
 {
-	kill_litter_super(sb);
+	struct efivarfs_fs_info *sfi = sb->s_fs_info;
 
-	if (!efivar_is_available())
-		return;
+	blocking_notifier_chain_unregister(&efivar_ops_nh, &sfi->nb);
+	kill_litter_super(sb);
 
 	/* Remove all entries and destroy */
-	efivar_entry_iter(efivarfs_destroy, &efivarfs_list, NULL);
+	efivar_entry_iter(efivarfs_destroy, &sfi->efivarfs_list, NULL);
+	kfree(sfi);
 }
 
 static struct file_system_type efivarfs_type = {
diff --git a/fs/efivarfs/vars.c b/fs/efivarfs/vars.c
index 9e4f47808bd5..114ff0fd4e55 100644
--- a/fs/efivarfs/vars.c
+++ b/fs/efivarfs/vars.c
@@ -369,7 +369,8 @@ static void dup_variable_bug(efi_char16_t *str16, efi_guid_t *vendor_guid,
  *
  * Returns 0 on success, or a kernel error code on failure.
  */
-int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *),
+int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *,
+			    struct list_head *),
 		void *data, bool duplicates, struct list_head *head)
 {
 	unsigned long variable_name_size = 1024;
@@ -420,7 +421,7 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *),
 				status = EFI_NOT_FOUND;
 			} else {
 				err = func(variable_name, vendor_guid,
-					   variable_name_size, data);
+					   variable_name_size, data, head);
 				if (err)
 					status = EFI_NOT_FOUND;
 			}
diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig
index e540648dedc2..1d318f85232d 100644
--- a/fs/erofs/Kconfig
+++ b/fs/erofs/Kconfig
@@ -21,7 +21,7 @@ config EROFS_FS
 	  performance under extremely memory pressure without extra cost.
 
 	  See the documentation at <file:Documentation/filesystems/erofs.rst>
-	  for more details.
+	  and the web pages at <https://erofs.docs.kernel.org> for more details.
 
 	  If unsure, say N.
 
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 029c761670bf..c98aeda8abb2 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -220,7 +220,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 			up_read(&devs->rwsem);
 			return 0;
 		}
-		map->m_bdev = dif->bdev_handle->bdev;
+		map->m_bdev = dif->bdev_handle ? dif->bdev_handle->bdev : NULL;
 		map->m_daxdev = dif->dax_dev;
 		map->m_dax_part_off = dif->dax_part_off;
 		map->m_fscache = dif->fscache;
@@ -238,7 +238,8 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 			if (map->m_pa >= startoff &&
 			    map->m_pa < startoff + length) {
 				map->m_pa -= startoff;
-				map->m_bdev = dif->bdev_handle->bdev;
+				map->m_bdev = dif->bdev_handle ?
+					      dif->bdev_handle->bdev : NULL;
 				map->m_daxdev = dif->dax_dev;
 				map->m_dax_part_off = dif->dax_part_off;
 				map->m_fscache = dif->fscache;
diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c
index 021be5feb1bc..1d65b9f60a39 100644
--- a/fs/erofs/decompressor.c
+++ b/fs/erofs/decompressor.c
@@ -121,11 +121,11 @@ static int z_erofs_lz4_prepare_dstpages(struct z_erofs_lz4_decompress_ctx *ctx,
 }
 
 static void *z_erofs_lz4_handle_overlap(struct z_erofs_lz4_decompress_ctx *ctx,
-			void *inpage, unsigned int *inputmargin, int *maptype,
-			bool may_inplace)
+			void *inpage, void *out, unsigned int *inputmargin,
+			int *maptype, bool may_inplace)
 {
 	struct z_erofs_decompress_req *rq = ctx->rq;
-	unsigned int omargin, total, i, j;
+	unsigned int omargin, total, i;
 	struct page **in;
 	void *src, *tmp;
 
@@ -135,12 +135,13 @@ static void *z_erofs_lz4_handle_overlap(struct z_erofs_lz4_decompress_ctx *ctx,
 		    omargin < LZ4_DECOMPRESS_INPLACE_MARGIN(rq->inputsize))
 			goto docopy;
 
-		for (i = 0; i < ctx->inpages; ++i) {
-			DBG_BUGON(rq->in[i] == NULL);
-			for (j = 0; j < ctx->outpages - ctx->inpages + i; ++j)
-				if (rq->out[j] == rq->in[i])
-					goto docopy;
-		}
+		for (i = 0; i < ctx->inpages; ++i)
+			if (rq->out[ctx->outpages - ctx->inpages + i] !=
+			    rq->in[i])
+				goto docopy;
+		kunmap_local(inpage);
+		*maptype = 3;
+		return out + ((ctx->outpages - ctx->inpages) << PAGE_SHIFT);
 	}
 
 	if (ctx->inpages <= 1) {
@@ -148,7 +149,6 @@ static void *z_erofs_lz4_handle_overlap(struct z_erofs_lz4_decompress_ctx *ctx,
 		return inpage;
 	}
 	kunmap_local(inpage);
-	might_sleep();
 	src = erofs_vm_map_ram(rq->in, ctx->inpages);
 	if (!src)
 		return ERR_PTR(-ENOMEM);
@@ -204,12 +204,12 @@ int z_erofs_fixup_insize(struct z_erofs_decompress_req *rq, const char *padbuf,
 }
 
 static int z_erofs_lz4_decompress_mem(struct z_erofs_lz4_decompress_ctx *ctx,
-				      u8 *out)
+				      u8 *dst)
 {
 	struct z_erofs_decompress_req *rq = ctx->rq;
 	bool support_0padding = false, may_inplace = false;
 	unsigned int inputmargin;
-	u8 *headpage, *src;
+	u8 *out, *headpage, *src;
 	int ret, maptype;
 
 	DBG_BUGON(*rq->in == NULL);
@@ -230,11 +230,12 @@ static int z_erofs_lz4_decompress_mem(struct z_erofs_lz4_decompress_ctx *ctx,
 	}
 
 	inputmargin = rq->pageofs_in;
-	src = z_erofs_lz4_handle_overlap(ctx, headpage, &inputmargin,
+	src = z_erofs_lz4_handle_overlap(ctx, headpage, dst, &inputmargin,
 					 &maptype, may_inplace);
 	if (IS_ERR(src))
 		return PTR_ERR(src);
 
+	out = dst + rq->pageofs_out;
 	/* legacy format could compress extra data in a pcluster. */
 	if (rq->partial_decoding || !support_0padding)
 		ret = LZ4_decompress_safe_partial(src + inputmargin, out,
@@ -246,15 +247,9 @@ static int z_erofs_lz4_decompress_mem(struct z_erofs_lz4_decompress_ctx *ctx,
 	if (ret != rq->outputsize) {
 		erofs_err(rq->sb, "failed to decompress %d in[%u, %u] out[%u]",
 			  ret, rq->inputsize, inputmargin, rq->outputsize);
-
-		print_hex_dump(KERN_DEBUG, "[ in]: ", DUMP_PREFIX_OFFSET,
-			       16, 1, src + inputmargin, rq->inputsize, true);
-		print_hex_dump(KERN_DEBUG, "[out]: ", DUMP_PREFIX_OFFSET,
-			       16, 1, out, rq->outputsize, true);
-
 		if (ret >= 0)
 			memset(out + ret, 0, rq->outputsize - ret);
-		ret = -EIO;
+		ret = -EFSCORRUPTED;
 	} else {
 		ret = 0;
 	}
@@ -265,7 +260,7 @@ static int z_erofs_lz4_decompress_mem(struct z_erofs_lz4_decompress_ctx *ctx,
 		vm_unmap_ram(src, ctx->inpages);
 	} else if (maptype == 2) {
 		erofs_put_pcpubuf(src);
-	} else {
+	} else if (maptype != 3) {
 		DBG_BUGON(1);
 		return -EFAULT;
 	}
@@ -308,7 +303,7 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq,
 	}
 
 dstmap_out:
-	ret = z_erofs_lz4_decompress_mem(&ctx, dst + rq->pageofs_out);
+	ret = z_erofs_lz4_decompress_mem(&ctx, dst);
 	if (!dst_maptype)
 		kunmap_local(dst);
 	else if (dst_maptype == 2)
@@ -319,43 +314,58 @@ dstmap_out:
 static int z_erofs_transform_plain(struct z_erofs_decompress_req *rq,
 				   struct page **pagepool)
 {
-	const unsigned int inpages = PAGE_ALIGN(rq->inputsize) >> PAGE_SHIFT;
-	const unsigned int outpages =
+	const unsigned int nrpages_in =
+		PAGE_ALIGN(rq->pageofs_in + rq->inputsize) >> PAGE_SHIFT;
+	const unsigned int nrpages_out =
 		PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT;
-	const unsigned int righthalf = min_t(unsigned int, rq->outputsize,
-					     PAGE_SIZE - rq->pageofs_out);
-	const unsigned int lefthalf = rq->outputsize - righthalf;
-	const unsigned int interlaced_offset =
-		rq->alg == Z_EROFS_COMPRESSION_SHIFTED ? 0 : rq->pageofs_out;
-	u8 *src;
-
-	if (outpages > 2 && rq->alg == Z_EROFS_COMPRESSION_SHIFTED) {
-		DBG_BUGON(1);
-		return -EFSCORRUPTED;
-	}
-
-	if (rq->out[0] == *rq->in) {
-		DBG_BUGON(rq->pageofs_out);
-		return 0;
+	const unsigned int bs = rq->sb->s_blocksize;
+	unsigned int cur = 0, ni = 0, no, pi, po, insz, cnt;
+	u8 *kin;
+
+	DBG_BUGON(rq->outputsize > rq->inputsize);
+	if (rq->alg == Z_EROFS_COMPRESSION_INTERLACED) {
+		cur = bs - (rq->pageofs_out & (bs - 1));
+		pi = (rq->pageofs_in + rq->inputsize - cur) & ~PAGE_MASK;
+		cur = min(cur, rq->outputsize);
+		if (cur && rq->out[0]) {
+			kin = kmap_local_page(rq->in[nrpages_in - 1]);
+			if (rq->out[0] == rq->in[nrpages_in - 1]) {
+				memmove(kin + rq->pageofs_out, kin + pi, cur);
+				flush_dcache_page(rq->out[0]);
+			} else {
+				memcpy_to_page(rq->out[0], rq->pageofs_out,
+					       kin + pi, cur);
+			}
+			kunmap_local(kin);
+		}
+		rq->outputsize -= cur;
 	}
 
-	src = kmap_local_page(rq->in[inpages - 1]) + rq->pageofs_in;
-	if (rq->out[0])
-		memcpy_to_page(rq->out[0], rq->pageofs_out,
-			       src + interlaced_offset, righthalf);
-
-	if (outpages > inpages) {
-		DBG_BUGON(!rq->out[outpages - 1]);
-		if (rq->out[outpages - 1] != rq->in[inpages - 1]) {
-			memcpy_to_page(rq->out[outpages - 1], 0, src +
-					(interlaced_offset ? 0 : righthalf),
-				       lefthalf);
-		} else if (!interlaced_offset) {
-			memmove(src, src + righthalf, lefthalf);
-			flush_dcache_page(rq->in[inpages - 1]);
-		}
+	for (; rq->outputsize; rq->pageofs_in = 0, cur += PAGE_SIZE, ni++) {
+		insz = min(PAGE_SIZE - rq->pageofs_in, rq->outputsize);
+		rq->outputsize -= insz;
+		if (!rq->in[ni])
+			continue;
+		kin = kmap_local_page(rq->in[ni]);
+		pi = 0;
+		do {
+			no = (rq->pageofs_out + cur + pi) >> PAGE_SHIFT;
+			po = (rq->pageofs_out + cur + pi) & ~PAGE_MASK;
+			DBG_BUGON(no >= nrpages_out);
+			cnt = min(insz - pi, PAGE_SIZE - po);
+			if (rq->out[no] == rq->in[ni]) {
+				memmove(kin + po,
+					kin + rq->pageofs_in + pi, cnt);
+				flush_dcache_page(rq->out[no]);
+			} else if (rq->out[no]) {
+				memcpy_to_page(rq->out[no], po,
+					       kin + rq->pageofs_in + pi, cnt);
+			}
+			pi += cnt;
+		} while (pi < insz);
+		kunmap_local(kin);
 	}
-	kunmap_local(src);
+	DBG_BUGON(ni > nrpages_in);
 	return 0;
 }
 
diff --git a/fs/erofs/decompressor_deflate.c b/fs/erofs/decompressor_deflate.c
index daf3c1bdeab8..4a64a9c91dd3 100644
--- a/fs/erofs/decompressor_deflate.c
+++ b/fs/erofs/decompressor_deflate.c
@@ -70,7 +70,7 @@ int __init z_erofs_deflate_init(void)
 	return 0;
 
 out_failed:
-	pr_err("failed to allocate zlib workspace\n");
+	erofs_err(NULL, "failed to allocate zlib workspace");
 	z_erofs_deflate_exit();
 	return -ENOMEM;
 }
diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
index b8ad05b4509d..3d616dea55dc 100644
--- a/fs/erofs/inode.c
+++ b/fs/erofs/inode.c
@@ -15,11 +15,11 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 	struct erofs_sb_info *sbi = EROFS_SB(sb);
 	struct erofs_inode *vi = EROFS_I(inode);
 	const erofs_off_t inode_loc = erofs_iloc(inode);
-
 	erofs_blk_t blkaddr, nblks = 0;
 	void *kaddr;
 	struct erofs_inode_compact *dic;
 	struct erofs_inode_extended *die, *copied = NULL;
+	union erofs_inode_i_u iu;
 	unsigned int ifmt;
 	int err;
 
@@ -35,9 +35,8 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 
 	dic = kaddr + *ofs;
 	ifmt = le16_to_cpu(dic->i_format);
-
 	if (ifmt & ~EROFS_I_ALL) {
-		erofs_err(inode->i_sb, "unsupported i_format %u of nid %llu",
+		erofs_err(sb, "unsupported i_format %u of nid %llu",
 			  ifmt, vi->nid);
 		err = -EOPNOTSUPP;
 		goto err_out;
@@ -45,7 +44,7 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 
 	vi->datalayout = erofs_inode_datalayout(ifmt);
 	if (vi->datalayout >= EROFS_INODE_DATALAYOUT_MAX) {
-		erofs_err(inode->i_sb, "unsupported datalayout %u of nid %llu",
+		erofs_err(sb, "unsupported datalayout %u of nid %llu",
 			  vi->datalayout, vi->nid);
 		err = -EOPNOTSUPP;
 		goto err_out;
@@ -82,40 +81,15 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 		vi->xattr_isize = erofs_xattr_ibody_size(die->i_xattr_icount);
 
 		inode->i_mode = le16_to_cpu(die->i_mode);
-		switch (inode->i_mode & S_IFMT) {
-		case S_IFREG:
-		case S_IFDIR:
-		case S_IFLNK:
-			vi->raw_blkaddr = le32_to_cpu(die->i_u.raw_blkaddr);
-			break;
-		case S_IFCHR:
-		case S_IFBLK:
-			inode->i_rdev =
-				new_decode_dev(le32_to_cpu(die->i_u.rdev));
-			break;
-		case S_IFIFO:
-		case S_IFSOCK:
-			inode->i_rdev = 0;
-			break;
-		default:
-			goto bogusimode;
-		}
+		iu = die->i_u;
 		i_uid_write(inode, le32_to_cpu(die->i_uid));
 		i_gid_write(inode, le32_to_cpu(die->i_gid));
 		set_nlink(inode, le32_to_cpu(die->i_nlink));
-
-		/* extended inode has its own timestamp */
+		/* each extended inode has its own timestamp */
 		inode_set_ctime(inode, le64_to_cpu(die->i_mtime),
 				le32_to_cpu(die->i_mtime_nsec));
 
 		inode->i_size = le64_to_cpu(die->i_size);
-
-		/* total blocks for compressed files */
-		if (erofs_inode_is_data_compressed(vi->datalayout))
-			nblks = le32_to_cpu(die->i_u.compressed_blocks);
-		else if (vi->datalayout == EROFS_INODE_CHUNK_BASED)
-			/* fill chunked inode summary info */
-			vi->chunkformat = le16_to_cpu(die->i_u.c.format);
 		kfree(copied);
 		copied = NULL;
 		break;
@@ -125,49 +99,51 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 		vi->xattr_isize = erofs_xattr_ibody_size(dic->i_xattr_icount);
 
 		inode->i_mode = le16_to_cpu(dic->i_mode);
-		switch (inode->i_mode & S_IFMT) {
-		case S_IFREG:
-		case S_IFDIR:
-		case S_IFLNK:
-			vi->raw_blkaddr = le32_to_cpu(dic->i_u.raw_blkaddr);
-			break;
-		case S_IFCHR:
-		case S_IFBLK:
-			inode->i_rdev =
-				new_decode_dev(le32_to_cpu(dic->i_u.rdev));
-			break;
-		case S_IFIFO:
-		case S_IFSOCK:
-			inode->i_rdev = 0;
-			break;
-		default:
-			goto bogusimode;
-		}
+		iu = dic->i_u;
 		i_uid_write(inode, le16_to_cpu(dic->i_uid));
 		i_gid_write(inode, le16_to_cpu(dic->i_gid));
 		set_nlink(inode, le16_to_cpu(dic->i_nlink));
-
 		/* use build time for compact inodes */
 		inode_set_ctime(inode, sbi->build_time, sbi->build_time_nsec);
 
 		inode->i_size = le32_to_cpu(dic->i_size);
-		if (erofs_inode_is_data_compressed(vi->datalayout))
-			nblks = le32_to_cpu(dic->i_u.compressed_blocks);
-		else if (vi->datalayout == EROFS_INODE_CHUNK_BASED)
-			vi->chunkformat = le16_to_cpu(dic->i_u.c.format);
 		break;
 	default:
-		erofs_err(inode->i_sb,
-			  "unsupported on-disk inode version %u of nid %llu",
+		erofs_err(sb, "unsupported on-disk inode version %u of nid %llu",
 			  erofs_inode_version(ifmt), vi->nid);
 		err = -EOPNOTSUPP;
 		goto err_out;
 	}
 
-	if (vi->datalayout == EROFS_INODE_CHUNK_BASED) {
+	switch (inode->i_mode & S_IFMT) {
+	case S_IFREG:
+	case S_IFDIR:
+	case S_IFLNK:
+		vi->raw_blkaddr = le32_to_cpu(iu.raw_blkaddr);
+		break;
+	case S_IFCHR:
+	case S_IFBLK:
+		inode->i_rdev = new_decode_dev(le32_to_cpu(iu.rdev));
+		break;
+	case S_IFIFO:
+	case S_IFSOCK:
+		inode->i_rdev = 0;
+		break;
+	default:
+		erofs_err(sb, "bogus i_mode (%o) @ nid %llu", inode->i_mode,
+			  vi->nid);
+		err = -EFSCORRUPTED;
+		goto err_out;
+	}
+
+	/* total blocks for compressed files */
+	if (erofs_inode_is_data_compressed(vi->datalayout)) {
+		nblks = le32_to_cpu(iu.compressed_blocks);
+	} else if (vi->datalayout == EROFS_INODE_CHUNK_BASED) {
+		/* fill chunked inode summary info */
+		vi->chunkformat = le16_to_cpu(iu.c.format);
 		if (vi->chunkformat & ~EROFS_CHUNK_FORMAT_ALL) {
-			erofs_err(inode->i_sb,
-				  "unsupported chunk format %x of nid %llu",
+			erofs_err(sb, "unsupported chunk format %x of nid %llu",
 				  vi->chunkformat, vi->nid);
 			err = -EOPNOTSUPP;
 			goto err_out;
@@ -191,10 +167,6 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 		inode->i_blocks = nblks << (sb->s_blocksize_bits - 9);
 	return kaddr;
 
-bogusimode:
-	erofs_err(inode->i_sb, "bogus i_mode (%o) @ nid %llu",
-		  inode->i_mode, vi->nid);
-	err = -EFSCORRUPTED;
 err_out:
 	DBG_BUGON(1);
 	kfree(copied);
@@ -287,8 +259,10 @@ static int erofs_fill_inode(struct inode *inode)
 
 	if (erofs_inode_is_data_compressed(vi->datalayout)) {
 #ifdef CONFIG_EROFS_FS_ZIP
-		if (!erofs_is_fscache_mode(inode->i_sb) &&
-		    inode->i_sb->s_blocksize_bits == PAGE_SHIFT) {
+		if (!erofs_is_fscache_mode(inode->i_sb)) {
+			DO_ONCE_LITE_IF(inode->i_sb->s_blocksize != PAGE_SIZE,
+				  erofs_info, inode->i_sb,
+				  "EXPERIMENTAL EROFS subpage compressed block support in use. Use at your own risk!");
 			inode->i_mapping->a_ops = &z_erofs_aops;
 			err = 0;
 			goto out_unlock;
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 3789d6224513..5f60f163bd56 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -27,7 +27,10 @@ void _erofs_err(struct super_block *sb, const char *func, const char *fmt, ...)
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
-	pr_err("(device %s): %s: %pV", sb->s_id, func, &vaf);
+	if (sb)
+		pr_err("(device %s): %s: %pV", sb->s_id, func, &vaf);
+	else
+		pr_err("%s: %pV", func, &vaf);
 	va_end(args);
 }
 
@@ -41,7 +44,10 @@ void _erofs_info(struct super_block *sb, const char *func, const char *fmt, ...)
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
-	pr_info("(device %s): %pV", sb->s_id, &vaf);
+	if (sb)
+		pr_info("(device %s): %pV", sb->s_id, &vaf);
+	else
+		pr_info("%pV", &vaf);
 	va_end(args);
 }
 
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index a7e6847f6f8f..692c0c39be63 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -56,6 +56,9 @@ struct z_erofs_pcluster {
 	/* L: total number of bvecs */
 	unsigned int vcnt;
 
+	/* I: pcluster size (compressed size) in bytes */
+	unsigned int pclustersize;
+
 	/* I: page offset of start position of decompression */
 	unsigned short pageofs_out;
 
@@ -70,14 +73,6 @@ struct z_erofs_pcluster {
 		struct rcu_head rcu;
 	};
 
-	union {
-		/* I: physical cluster size in pages */
-		unsigned short pclusterpages;
-
-		/* I: tailpacking inline compressed size */
-		unsigned short tailpacking_size;
-	};
-
 	/* I: compression algorithm format */
 	unsigned char algorithmformat;
 
@@ -115,9 +110,7 @@ static inline bool z_erofs_is_inline_pcluster(struct z_erofs_pcluster *pcl)
 
 static inline unsigned int z_erofs_pclusterpages(struct z_erofs_pcluster *pcl)
 {
-	if (z_erofs_is_inline_pcluster(pcl))
-		return 1;
-	return pcl->pclusterpages;
+	return PAGE_ALIGN(pcl->pclustersize) >> PAGE_SHIFT;
 }
 
 /*
@@ -298,12 +291,12 @@ static int z_erofs_create_pcluster_pool(void)
 	return 0;
 }
 
-static struct z_erofs_pcluster *z_erofs_alloc_pcluster(unsigned int nrpages)
+static struct z_erofs_pcluster *z_erofs_alloc_pcluster(unsigned int size)
 {
-	int i;
+	unsigned int nrpages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	struct z_erofs_pcluster_slab *pcs = pcluster_pool;
 
-	for (i = 0; i < ARRAY_SIZE(pcluster_pool); ++i) {
-		struct z_erofs_pcluster_slab *pcs = pcluster_pool + i;
+	for (; pcs < pcluster_pool + ARRAY_SIZE(pcluster_pool); ++pcs) {
 		struct z_erofs_pcluster *pcl;
 
 		if (nrpages > pcs->maxpages)
@@ -312,7 +305,7 @@ static struct z_erofs_pcluster *z_erofs_alloc_pcluster(unsigned int nrpages)
 		pcl = kmem_cache_zalloc(pcs->slab, GFP_NOFS);
 		if (!pcl)
 			return ERR_PTR(-ENOMEM);
-		pcl->pclusterpages = nrpages;
+		pcl->pclustersize = size;
 		return pcl;
 	}
 	return ERR_PTR(-EINVAL);
@@ -559,6 +552,7 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe)
 {
 	struct address_space *mc = MNGD_MAPPING(EROFS_I_SB(fe->inode));
 	struct z_erofs_pcluster *pcl = fe->pcl;
+	unsigned int pclusterpages = z_erofs_pclusterpages(pcl);
 	bool shouldalloc = z_erofs_should_alloc_cache(fe);
 	bool standalone = true;
 	/*
@@ -569,13 +563,14 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe)
 			__GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN;
 	unsigned int i;
 
+	if (i_blocksize(fe->inode) != PAGE_SIZE)
+		return;
 	if (fe->mode < Z_EROFS_PCLUSTER_FOLLOWED)
 		return;
 
-	for (i = 0; i < pcl->pclusterpages; ++i) {
-		struct page *page;
+	for (i = 0; i < pclusterpages; ++i) {
+		struct page *page, *newpage;
 		void *t;	/* mark pages just found for debugging */
-		struct page *newpage = NULL;
 
 		/* the compressed page was loaded before */
 		if (READ_ONCE(pcl->compressed_bvecs[i].page))
@@ -585,6 +580,7 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe)
 
 		if (page) {
 			t = (void *)((unsigned long)page | 1);
+			newpage = NULL;
 		} else {
 			/* I/O is needed, no possible to decompress directly */
 			standalone = false;
@@ -592,9 +588,8 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe)
 				continue;
 
 			/*
-			 * try to use cached I/O if page allocation
-			 * succeeds or fallback to in-place I/O instead
-			 * to avoid any direct reclaim.
+			 * Try cached I/O if allocation succeeds or fallback to
+			 * in-place I/O instead to avoid any direct reclaim.
 			 */
 			newpage = erofs_allocpage(&fe->pagepool, gfp);
 			if (!newpage)
@@ -626,6 +621,7 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
 {
 	struct z_erofs_pcluster *const pcl =
 		container_of(grp, struct z_erofs_pcluster, obj);
+	unsigned int pclusterpages = z_erofs_pclusterpages(pcl);
 	int i;
 
 	DBG_BUGON(z_erofs_is_inline_pcluster(pcl));
@@ -633,7 +629,7 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
 	 * refcount of workgroup is now freezed as 0,
 	 * therefore no need to worry about available decompression users.
 	 */
-	for (i = 0; i < pcl->pclusterpages; ++i) {
+	for (i = 0; i < pclusterpages; ++i) {
 		struct page *page = pcl->compressed_bvecs[i].page;
 
 		if (!page)
@@ -657,6 +653,7 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
 static bool z_erofs_cache_release_folio(struct folio *folio, gfp_t gfp)
 {
 	struct z_erofs_pcluster *pcl = folio_get_private(folio);
+	unsigned int pclusterpages = z_erofs_pclusterpages(pcl);
 	bool ret;
 	int i;
 
@@ -669,7 +666,7 @@ static bool z_erofs_cache_release_folio(struct folio *folio, gfp_t gfp)
 		goto out;
 
 	DBG_BUGON(z_erofs_is_inline_pcluster(pcl));
-	for (i = 0; i < pcl->pclusterpages; ++i) {
+	for (i = 0; i < pclusterpages; ++i) {
 		if (pcl->compressed_bvecs[i].page == &folio->page) {
 			WRITE_ONCE(pcl->compressed_bvecs[i].page, NULL);
 			ret = true;
@@ -778,20 +775,20 @@ static void z_erofs_try_to_claim_pcluster(struct z_erofs_decompress_frontend *f)
 static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe)
 {
 	struct erofs_map_blocks *map = &fe->map;
+	struct super_block *sb = fe->inode->i_sb;
 	bool ztailpacking = map->m_flags & EROFS_MAP_META;
 	struct z_erofs_pcluster *pcl;
 	struct erofs_workgroup *grp;
 	int err;
 
 	if (!(map->m_flags & EROFS_MAP_ENCODED) ||
-	    (!ztailpacking && !(map->m_pa >> PAGE_SHIFT))) {
+	    (!ztailpacking && !erofs_blknr(sb, map->m_pa))) {
 		DBG_BUGON(1);
 		return -EFSCORRUPTED;
 	}
 
 	/* no available pcluster, let's allocate one */
-	pcl = z_erofs_alloc_pcluster(ztailpacking ? 1 :
-				     map->m_plen >> PAGE_SHIFT);
+	pcl = z_erofs_alloc_pcluster(map->m_plen);
 	if (IS_ERR(pcl))
 		return PTR_ERR(pcl);
 
@@ -815,10 +812,8 @@ static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe)
 
 	if (ztailpacking) {
 		pcl->obj.index = 0;	/* which indicates ztailpacking */
-		pcl->pageofs_in = erofs_blkoff(fe->inode->i_sb, map->m_pa);
-		pcl->tailpacking_size = map->m_plen;
 	} else {
-		pcl->obj.index = map->m_pa >> PAGE_SHIFT;
+		pcl->obj.index = erofs_blknr(sb, map->m_pa);
 
 		grp = erofs_insert_workgroup(fe->inode->i_sb, &pcl->obj);
 		if (IS_ERR(grp)) {
@@ -893,6 +888,7 @@ static int z_erofs_pcluster_begin(struct z_erofs_decompress_frontend *fe)
 		}
 		get_page(map->buf.page);
 		WRITE_ONCE(fe->pcl->compressed_bvecs[0].page, map->buf.page);
+		fe->pcl->pageofs_in = map->m_pa & ~PAGE_MASK;
 		fe->mode = Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE;
 	}
 	/* file-backed inplace I/O pages are traversed in reverse order */
@@ -973,12 +969,12 @@ static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe,
 	struct inode *const inode = fe->inode;
 	struct erofs_map_blocks *const map = &fe->map;
 	const loff_t offset = page_offset(page);
+	const unsigned int bs = i_blocksize(inode);
 	bool tight = true, exclusive;
 	unsigned int cur, end, len, split;
 	int err = 0;
 
 	z_erofs_onlinepage_init(page);
-
 	split = 0;
 	end = PAGE_SIZE;
 repeat:
@@ -1027,7 +1023,7 @@ repeat:
 	 * for inplace I/O or bvpage (should be processed in a strict order.)
 	 */
 	tight &= (fe->mode > Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE);
-	exclusive = (!cur && ((split <= 1) || tight));
+	exclusive = (!cur && ((split <= 1) || (tight && bs == PAGE_SIZE)));
 	if (cur)
 		tight &= (fe->mode >= Z_EROFS_PCLUSTER_FOLLOWED);
 
@@ -1206,34 +1202,27 @@ static int z_erofs_parse_in_bvecs(struct z_erofs_decompress_backend *be,
 		struct z_erofs_bvec *bvec = &pcl->compressed_bvecs[i];
 		struct page *page = bvec->page;
 
-		/* compressed pages ought to be present before decompressing */
+		/* compressed data ought to be valid before decompressing */
 		if (!page) {
-			DBG_BUGON(1);
+			err = -EIO;
 			continue;
 		}
 		be->compressed_pages[i] = page;
 
-		if (z_erofs_is_inline_pcluster(pcl)) {
+		if (z_erofs_is_inline_pcluster(pcl) ||
+		    erofs_page_is_managed(EROFS_SB(be->sb), page)) {
 			if (!PageUptodate(page))
 				err = -EIO;
 			continue;
 		}
 
 		DBG_BUGON(z_erofs_page_is_invalidated(page));
-		if (!z_erofs_is_shortlived_page(page)) {
-			if (erofs_page_is_managed(EROFS_SB(be->sb), page)) {
-				if (!PageUptodate(page))
-					err = -EIO;
-				continue;
-			}
-			z_erofs_do_decompressed_bvec(be, bvec);
-			*overlapped = true;
-		}
+		if (z_erofs_is_shortlived_page(page))
+			continue;
+		z_erofs_do_decompressed_bvec(be, bvec);
+		*overlapped = true;
 	}
-
-	if (err)
-		return err;
-	return 0;
+	return err;
 }
 
 static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
@@ -1242,10 +1231,9 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
 	struct erofs_sb_info *const sbi = EROFS_SB(be->sb);
 	struct z_erofs_pcluster *pcl = be->pcl;
 	unsigned int pclusterpages = z_erofs_pclusterpages(pcl);
-	const struct z_erofs_decompressor *decompressor =
+	const struct z_erofs_decompressor *decomp =
 				&erofs_decompressors[pcl->algorithmformat];
-	unsigned int i, inputsize;
-	int err2;
+	int i, err2;
 	struct page *page;
 	bool overlapped;
 
@@ -1279,21 +1267,14 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
 	err2 = z_erofs_parse_in_bvecs(be, &overlapped);
 	if (err2)
 		err = err2;
-	if (err)
-		goto out;
-
-	if (z_erofs_is_inline_pcluster(pcl))
-		inputsize = pcl->tailpacking_size;
-	else
-		inputsize = pclusterpages * PAGE_SIZE;
-
-	err = decompressor->decompress(&(struct z_erofs_decompress_req) {
+	if (!err)
+		err = decomp->decompress(&(struct z_erofs_decompress_req) {
 					.sb = be->sb,
 					.in = be->compressed_pages,
 					.out = be->decompressed_pages,
 					.pageofs_in = pcl->pageofs_in,
 					.pageofs_out = pcl->pageofs_out,
-					.inputsize = inputsize,
+					.inputsize = pcl->pclustersize,
 					.outputsize = pcl->length,
 					.alg = pcl->algorithmformat,
 					.inplace_io = overlapped,
@@ -1301,7 +1282,6 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
 					.fillgaps = pcl->multibases,
 				 }, be->pagepool);
 
-out:
 	/* must handle all compressed pages before actual file pages */
 	if (z_erofs_is_inline_pcluster(pcl)) {
 		page = pcl->compressed_bvecs[0].page;
@@ -1309,12 +1289,11 @@ out:
 		put_page(page);
 	} else {
 		for (i = 0; i < pclusterpages; ++i) {
-			page = pcl->compressed_bvecs[i].page;
+			/* consider shortlived pages added when decompressing */
+			page = be->compressed_pages[i];
 
-			if (erofs_page_is_managed(sbi, page))
+			if (!page || erofs_page_is_managed(sbi, page))
 				continue;
-
-			/* recycle all individual short-lived pages */
 			(void)z_erofs_put_shortlivedpage(be->pagepool, page);
 			WRITE_ONCE(pcl->compressed_bvecs[i].page, NULL);
 		}
@@ -1436,86 +1415,85 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io,
 	z_erofs_decompressqueue_work(&io->u.work);
 }
 
-static struct page *pickup_page_for_submission(struct z_erofs_pcluster *pcl,
-					       unsigned int nr,
-					       struct page **pagepool,
-					       struct address_space *mc)
+static void z_erofs_fill_bio_vec(struct bio_vec *bvec,
+				 struct z_erofs_decompress_frontend *f,
+				 struct z_erofs_pcluster *pcl,
+				 unsigned int nr,
+				 struct address_space *mc)
 {
-	const pgoff_t index = pcl->obj.index;
 	gfp_t gfp = mapping_gfp_mask(mc);
 	bool tocache = false;
-
+	struct z_erofs_bvec *zbv = pcl->compressed_bvecs + nr;
 	struct address_space *mapping;
-	struct page *oldpage, *page;
-	int justfound;
+	struct page *page, *oldpage;
+	int justfound, bs = i_blocksize(f->inode);
 
+	/* Except for inplace pages, the entire page can be used for I/Os */
+	bvec->bv_offset = 0;
+	bvec->bv_len = PAGE_SIZE;
 repeat:
-	page = READ_ONCE(pcl->compressed_bvecs[nr].page);
-	oldpage = page;
-
-	if (!page)
+	oldpage = READ_ONCE(zbv->page);
+	if (!oldpage)
 		goto out_allocpage;
 
-	justfound = (unsigned long)page & 1UL;
-	page = (struct page *)((unsigned long)page & ~1UL);
+	justfound = (unsigned long)oldpage & 1UL;
+	page = (struct page *)((unsigned long)oldpage & ~1UL);
+	bvec->bv_page = page;
 
+	DBG_BUGON(z_erofs_is_shortlived_page(page));
 	/*
-	 * preallocated cached pages, which is used to avoid direct reclaim
-	 * otherwise, it will go inplace I/O path instead.
+	 * Handle preallocated cached pages.  We tried to allocate such pages
+	 * without triggering direct reclaim.  If allocation failed, inplace
+	 * file-backed pages will be used instead.
 	 */
 	if (page->private == Z_EROFS_PREALLOCATED_PAGE) {
-		WRITE_ONCE(pcl->compressed_bvecs[nr].page, page);
 		set_page_private(page, 0);
+		WRITE_ONCE(zbv->page, page);
 		tocache = true;
 		goto out_tocache;
 	}
-	mapping = READ_ONCE(page->mapping);
 
+	mapping = READ_ONCE(page->mapping);
 	/*
-	 * file-backed online pages in plcuster are all locked steady,
-	 * therefore it is impossible for `mapping' to be NULL.
+	 * File-backed pages for inplace I/Os are all locked steady,
+	 * therefore it is impossible for `mapping` to be NULL.
 	 */
-	if (mapping && mapping != mc)
-		/* ought to be unmanaged pages */
-		goto out;
-
-	/* directly return for shortlived page as well */
-	if (z_erofs_is_shortlived_page(page))
-		goto out;
+	if (mapping && mapping != mc) {
+		if (zbv->offset < 0)
+			bvec->bv_offset = round_up(-zbv->offset, bs);
+		bvec->bv_len = round_up(zbv->end, bs) - bvec->bv_offset;
+		return;
+	}
 
 	lock_page(page);
-
 	/* only true if page reclaim goes wrong, should never happen */
 	DBG_BUGON(justfound && PagePrivate(page));
 
-	/* the page is still in manage cache */
+	/* the cached page is still in managed cache */
 	if (page->mapping == mc) {
-		WRITE_ONCE(pcl->compressed_bvecs[nr].page, page);
-
+		WRITE_ONCE(zbv->page, page);
+		/*
+		 * The cached page is still available but without a valid
+		 * `->private` pcluster hint.  Let's reconnect them.
+		 */
 		if (!PagePrivate(page)) {
-			/*
-			 * impossible to be !PagePrivate(page) for
-			 * the current restriction as well if
-			 * the page is already in compressed_bvecs[].
-			 */
 			DBG_BUGON(!justfound);
-
-			justfound = 0;
-			set_page_private(page, (unsigned long)pcl);
-			SetPagePrivate(page);
+			/* compressed_bvecs[] already takes a ref */
+			attach_page_private(page, pcl);
+			put_page(page);
 		}
 
-		/* no need to submit io if it is already up-to-date */
+		/* no need to submit if it is already up-to-date */
 		if (PageUptodate(page)) {
 			unlock_page(page);
-			page = NULL;
+			bvec->bv_page = NULL;
 		}
-		goto out;
+		return;
 	}
 
 	/*
-	 * the managed page has been truncated, it's unsafe to
-	 * reuse this one, let's allocate a new cache-managed page.
+	 * It has been truncated, so it's unsafe to reuse this one. Let's
+	 * allocate a new page for compressed data.
 	 */
 	DBG_BUGON(page->mapping);
 	DBG_BUGON(!justfound);
@@ -1524,25 +1502,23 @@ repeat:
 	unlock_page(page);
 	put_page(page);
 out_allocpage:
-	page = erofs_allocpage(pagepool, gfp | __GFP_NOFAIL);
-	if (oldpage != cmpxchg(&pcl->compressed_bvecs[nr].page,
-			       oldpage, page)) {
-		erofs_pagepool_add(pagepool, page);
+	page = erofs_allocpage(&f->pagepool, gfp | __GFP_NOFAIL);
+	if (oldpage != cmpxchg(&zbv->page, oldpage, page)) {
+		erofs_pagepool_add(&f->pagepool, page);
 		cond_resched();
 		goto repeat;
 	}
+	bvec->bv_page = page;
 out_tocache:
-	if (!tocache || add_to_page_cache_lru(page, mc, index + nr, gfp)) {
-		/* turn into temporary page if fails (1 ref) */
+	if (!tocache || bs != PAGE_SIZE ||
+	    add_to_page_cache_lru(page, mc, pcl->obj.index + nr, gfp)) {
+		/* turn into a temporary shortlived page (1 ref) */
 		set_page_private(page, Z_EROFS_SHORTLIVED_PAGE);
-		goto out;
+		return;
 	}
 	attach_page_private(page, pcl);
-	/* drop a refcount added by allocpage (then we have 2 refs here) */
+	/* drop a refcount added by allocpage (then 2 refs in total here) */
 	put_page(page);
-
-out:	/* the only exit (for tracing and debugging) */
-	return page;
 }
 
 static struct z_erofs_decompressqueue *jobqueue_init(struct super_block *sb,
@@ -1597,7 +1573,7 @@ static void move_to_bypass_jobqueue(struct z_erofs_pcluster *pcl,
 	qtail[JQ_BYPASS] = &pcl->next;
 }
 
-static void z_erofs_decompressqueue_endio(struct bio *bio)
+static void z_erofs_submissionqueue_endio(struct bio *bio)
 {
 	struct z_erofs_decompressqueue *q = bio->bi_private;
 	blk_status_t err = bio->bi_status;
@@ -1609,7 +1585,6 @@ static void z_erofs_decompressqueue_endio(struct bio *bio)
 
 		DBG_BUGON(PageUptodate(page));
 		DBG_BUGON(z_erofs_page_is_invalidated(page));
-
 		if (erofs_page_is_managed(EROFS_SB(q->sb), page)) {
 			if (!err)
 				SetPageUptodate(page);
@@ -1632,17 +1607,14 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 	struct z_erofs_decompressqueue *q[NR_JOBQUEUES];
 	z_erofs_next_pcluster_t owned_head = f->owned_head;
 	/* bio is NULL initially, so no need to initialize last_{index,bdev} */
-	pgoff_t last_index;
+	erofs_off_t last_pa;
 	struct block_device *last_bdev;
 	unsigned int nr_bios = 0;
 	struct bio *bio = NULL;
 	unsigned long pflags;
 	int memstall = 0;
 
-	/*
-	 * if managed cache is enabled, bypass jobqueue is needed,
-	 * no need to read from device for all pclusters in this queue.
-	 */
+	/* No need to read from device for pclusters in the bypass queue. */
 	q[JQ_BYPASS] = jobqueue_init(sb, fgq + JQ_BYPASS, NULL);
 	q[JQ_SUBMIT] = jobqueue_init(sb, fgq + JQ_SUBMIT, force_fg);
 
@@ -1655,7 +1627,8 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 	do {
 		struct erofs_map_dev mdev;
 		struct z_erofs_pcluster *pcl;
-		pgoff_t cur, end;
+		erofs_off_t cur, end;
+		struct bio_vec bvec;
 		unsigned int i = 0;
 		bool bypass = true;
 
@@ -1674,18 +1647,14 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 		};
 		(void)erofs_map_dev(sb, &mdev);
 
-		cur = erofs_blknr(sb, mdev.m_pa);
-		end = cur + pcl->pclusterpages;
-
+		cur = mdev.m_pa;
+		end = cur + pcl->pclustersize;
 		do {
-			struct page *page;
-
-			page = pickup_page_for_submission(pcl, i++,
-					&f->pagepool, mc);
-			if (!page)
+			z_erofs_fill_bio_vec(&bvec, f, pcl, i++, mc);
+			if (!bvec.bv_page)
 				continue;
 
-			if (bio && (cur != last_index + 1 ||
+			if (bio && (cur != last_pa ||
 				    last_bdev != mdev.m_bdev)) {
 submit_bio_retry:
 				submit_bio(bio);
@@ -1696,7 +1665,8 @@ submit_bio_retry:
 				bio = NULL;
 			}
 
-			if (unlikely(PageWorkingset(page)) && !memstall) {
+			if (unlikely(PageWorkingset(bvec.bv_page)) &&
+			    !memstall) {
 				psi_memstall_enter(&pflags);
 				memstall = 1;
 			}
@@ -1704,23 +1674,24 @@ submit_bio_retry:
 			if (!bio) {
 				bio = bio_alloc(mdev.m_bdev, BIO_MAX_VECS,
 						REQ_OP_READ, GFP_NOIO);
-				bio->bi_end_io = z_erofs_decompressqueue_endio;
-
-				last_bdev = mdev.m_bdev;
-				bio->bi_iter.bi_sector = (sector_t)cur <<
-					(sb->s_blocksize_bits - 9);
+				bio->bi_end_io = z_erofs_submissionqueue_endio;
+				bio->bi_iter.bi_sector = cur >> 9;
 				bio->bi_private = q[JQ_SUBMIT];
 				if (readahead)
 					bio->bi_opf |= REQ_RAHEAD;
 				++nr_bios;
+				last_bdev = mdev.m_bdev;
 			}
 
-			if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE)
+			if (cur + bvec.bv_len > end)
+				bvec.bv_len = end - cur;
+			if (!bio_add_page(bio, bvec.bv_page, bvec.bv_len,
+					  bvec.bv_offset))
 				goto submit_bio_retry;
 
-			last_index = cur;
+			last_pa = cur + bvec.bv_len;
 			bypass = false;
-		} while (++cur < end);
+		} while ((cur += bvec.bv_len) < end);
 
 		if (!bypass)
 			qtail[JQ_SUBMIT] = &pcl->next;
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 7b55111fd533..9753875e41cb 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -82,29 +82,26 @@ static int z_erofs_load_full_lcluster(struct z_erofs_maprecorder *m,
 }
 
 static unsigned int decode_compactedbits(unsigned int lobits,
-					 unsigned int lomask,
 					 u8 *in, unsigned int pos, u8 *type)
 {
 	const unsigned int v = get_unaligned_le32(in + pos / 8) >> (pos & 7);
-	const unsigned int lo = v & lomask;
+	const unsigned int lo = v & ((1 << lobits) - 1);
 
 	*type = (v >> lobits) & 3;
 	return lo;
 }
 
-static int get_compacted_la_distance(unsigned int lclusterbits,
+static int get_compacted_la_distance(unsigned int lobits,
 				     unsigned int encodebits,
 				     unsigned int vcnt, u8 *in, int i)
 {
-	const unsigned int lomask = (1 << lclusterbits) - 1;
 	unsigned int lo, d1 = 0;
 	u8 type;
 
 	DBG_BUGON(i >= vcnt);
 
 	do {
-		lo = decode_compactedbits(lclusterbits, lomask,
-					  in, encodebits * i, &type);
+		lo = decode_compactedbits(lobits, in, encodebits * i, &type);
 
 		if (type != Z_EROFS_LCLUSTER_TYPE_NONHEAD)
 			return d1;
@@ -123,15 +120,14 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 {
 	struct erofs_inode *const vi = EROFS_I(m->inode);
 	const unsigned int lclusterbits = vi->z_logical_clusterbits;
-	const unsigned int lomask = (1 << lclusterbits) - 1;
-	unsigned int vcnt, base, lo, encodebits, nblk, eofs;
+	unsigned int vcnt, base, lo, lobits, encodebits, nblk, eofs;
 	int i;
 	u8 *in, type;
 	bool big_pcluster;
 
 	if (1 << amortizedshift == 4 && lclusterbits <= 14)
 		vcnt = 2;
-	else if (1 << amortizedshift == 2 && lclusterbits == 12)
+	else if (1 << amortizedshift == 2 && lclusterbits <= 12)
 		vcnt = 16;
 	else
 		return -EOPNOTSUPP;
@@ -140,6 +136,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 	m->nextpackoff = round_down(pos, vcnt << amortizedshift) +
 			 (vcnt << amortizedshift);
 	big_pcluster = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1;
+	lobits = max(lclusterbits, ilog2(Z_EROFS_LI_D0_CBLKCNT) + 1U);
 	encodebits = ((vcnt << amortizedshift) - sizeof(__le32)) * 8 / vcnt;
 	eofs = erofs_blkoff(m->inode->i_sb, pos);
 	base = round_down(eofs, vcnt << amortizedshift);
@@ -147,15 +144,14 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 
 	i = (eofs - base) >> amortizedshift;
 
-	lo = decode_compactedbits(lclusterbits, lomask,
-				  in, encodebits * i, &type);
+	lo = decode_compactedbits(lobits, in, encodebits * i, &type);
 	m->type = type;
 	if (type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) {
 		m->clusterofs = 1 << lclusterbits;
 
 		/* figure out lookahead_distance: delta[1] if needed */
 		if (lookahead)
-			m->delta[1] = get_compacted_la_distance(lclusterbits,
+			m->delta[1] = get_compacted_la_distance(lobits,
 						encodebits, vcnt, in, i);
 		if (lo & Z_EROFS_LI_D0_CBLKCNT) {
 			if (!big_pcluster) {
@@ -174,8 +170,8 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 		 * of which lo saves delta[1] rather than delta[0].
 		 * Hence, get delta[0] by the previous lcluster indirectly.
 		 */
-		lo = decode_compactedbits(lclusterbits, lomask,
-					  in, encodebits * (i - 1), &type);
+		lo = decode_compactedbits(lobits, in,
+					  encodebits * (i - 1), &type);
 		if (type != Z_EROFS_LCLUSTER_TYPE_NONHEAD)
 			lo = 0;
 		else if (lo & Z_EROFS_LI_D0_CBLKCNT)
@@ -190,8 +186,8 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 		nblk = 1;
 		while (i > 0) {
 			--i;
-			lo = decode_compactedbits(lclusterbits, lomask,
-						  in, encodebits * i, &type);
+			lo = decode_compactedbits(lobits, in,
+						  encodebits * i, &type);
 			if (type == Z_EROFS_LCLUSTER_TYPE_NONHEAD)
 				i -= lo;
 
@@ -202,8 +198,8 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 		nblk = 0;
 		while (i > 0) {
 			--i;
-			lo = decode_compactedbits(lclusterbits, lomask,
-						  in, encodebits * i, &type);
+			lo = decode_compactedbits(lobits, in,
+						  encodebits * i, &type);
 			if (type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) {
 				if (lo & Z_EROFS_LI_D0_CBLKCNT) {
 					--i;
diff --git a/fs/eventfd.c b/fs/eventfd.c
index 33a918f9566c..ad8186d47ba7 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -43,7 +43,17 @@ struct eventfd_ctx {
 	int id;
 };
 
-__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask)
+/**
+ * eventfd_signal_mask - Increment the event counter
+ * @ctx: [in] Pointer to the eventfd context.
+ * @mask: [in] poll mask
+ *
+ * This function is supposed to be called by the kernel in paths that do not
+ * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX
+ * value, and we signal this as overflow condition by returning a EPOLLERR
+ * to poll(2).
+ */
+void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask)
 {
 	unsigned long flags;
 
@@ -56,45 +66,23 @@ __u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask)
 	 * safe context.
 	 */
 	if (WARN_ON_ONCE(current->in_eventfd))
-		return 0;
+		return;
 
 	spin_lock_irqsave(&ctx->wqh.lock, flags);
 	current->in_eventfd = 1;
-	if (ULLONG_MAX - ctx->count < n)
-		n = ULLONG_MAX - ctx->count;
-	ctx->count += n;
+	if (ctx->count < ULLONG_MAX)
+		ctx->count++;
 	if (waitqueue_active(&ctx->wqh))
 		wake_up_locked_poll(&ctx->wqh, EPOLLIN | mask);
 	current->in_eventfd = 0;
 	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
-
-	return n;
-}
-
-/**
- * eventfd_signal - Adds @n to the eventfd counter.
- * @ctx: [in] Pointer to the eventfd context.
- * @n: [in] Value of the counter to be added to the eventfd internal counter.
- *          The value cannot be negative.
- *
- * This function is supposed to be called by the kernel in paths that do not
- * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX
- * value, and we signal this as overflow condition by returning a EPOLLERR
- * to poll(2).
- *
- * Returns the amount by which the counter was incremented.  This will be less
- * than @n if the counter has overflowed.
- */
-__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n)
-{
-	return eventfd_signal_mask(ctx, n, 0);
 }
-EXPORT_SYMBOL_GPL(eventfd_signal);
+EXPORT_SYMBOL_GPL(eventfd_signal_mask);
 
 static void eventfd_free_ctx(struct eventfd_ctx *ctx)
 {
 	if (ctx->id >= 0)
-		ida_simple_remove(&eventfd_ida, ctx->id);
+		ida_free(&eventfd_ida, ctx->id);
 	kfree(ctx);
 }
 
@@ -407,7 +395,7 @@ static int do_eventfd(unsigned int count, int flags)
 	init_waitqueue_head(&ctx->wqh);
 	ctx->count = count;
 	ctx->flags = flags;
-	ctx->id = ida_simple_get(&eventfd_ida, 0, 0, GFP_KERNEL);
+	ctx->id = ida_alloc(&eventfd_ida, GFP_KERNEL);
 
 	flags &= EFD_SHARED_FCNTL_FLAGS;
 	flags |= O_RDWR;
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 2877cc01cff1..3534d36a1474 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -322,7 +322,6 @@ static struct ctl_table epoll_table[] = {
 		.extra1		= &long_zero,
 		.extra2		= &long_max,
 	},
-	{ }
 };
 
 static void __init epoll_sysctls_init(void)
diff --git a/fs/exec.c b/fs/exec.c
index 4aa19b24f281..73e4045df271 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -66,6 +66,7 @@
 #include <linux/coredump.h>
 #include <linux/time_namespace.h>
 #include <linux/user_events.h>
+#include <linux/rseq.h>
 
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>
@@ -1578,11 +1579,10 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
 	 * will be able to manipulate the current directory, etc.
 	 * It would be nice to force an unshare instead...
 	 */
-	t = p;
 	n_fs = 1;
 	spin_lock(&p->fs->lock);
 	rcu_read_lock();
-	while_each_thread(p, t) {
+	for_other_threads(p, t) {
 		if (t->fs == p->fs)
 			n_fs++;
 	}
@@ -2165,7 +2165,6 @@ static struct ctl_table fs_exec_sysctls[] = {
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_TWO,
 	},
-	{ }
 };
 
 static int __init init_fs_exec_sysctls(void)
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 1039e5bf90af..4ddc36f4dbd4 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -258,7 +258,6 @@ static ssize_t ext2_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 			goto out_unlock;
 		}
 
-		iocb->ki_pos += status;
 		ret += status;
 		endbyte = pos + status - 1;
 		ret2 = filemap_write_and_wait_range(inode->i_mapping, pos,
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 464faf6c217e..5a4272b2c6b0 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -969,7 +969,7 @@ const struct address_space_operations ext2_aops = {
 	.writepages		= ext2_writepages,
 	.migrate_folio		= buffer_migrate_folio,
 	.is_partially_uptodate	= block_is_partially_uptodate,
-	.error_remove_page	= generic_error_remove_page,
+	.error_remove_folio	= generic_error_remove_folio,
 };
 
 static const struct address_space_operations ext2_dax_aops = {
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index d1a2e6624401..5d8055161acd 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -235,8 +235,6 @@ int __ext4_journal_get_write_access(const char *where, unsigned int line,
 
 	might_sleep();
 
-	ext4_check_bdev_write_error(sb);
-
 	if (ext4_handle_valid(handle)) {
 		err = jbd2_journal_get_write_access(handle, bh);
 		if (err) {
@@ -244,7 +242,8 @@ int __ext4_journal_get_write_access(const char *where, unsigned int line,
 						  handle, err);
 			return err;
 		}
-	}
+	} else
+		ext4_check_bdev_write_error(sb);
 	if (trigger_type == EXT4_JTR_NONE || !ext4_has_metadata_csum(sb))
 		return 0;
 	BUG_ON(trigger_type >= EXT4_JOURNAL_TRIGGER_COUNT);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index d5efe076d3d3..01299b55a567 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4523,7 +4523,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	 * Round up offset. This is not fallocate, we need to zero out
 	 * blocks, so convert interior block aligned part of the range to
 	 * unwritten and possibly manually zero out unaligned parts of the
-	 * range.
+	 * range. Here, start and partial_begin are inclusive, end and
+	 * partial_end are exclusive.
 	 */
 	start = round_up(offset, 1 << blkbits);
 	end = round_down((offset + len), 1 << blkbits);
@@ -4609,7 +4610,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		 * disk in case of crash before zeroing trans is committed.
 		 */
 		if (ext4_should_journal_data(inode)) {
-			ret = filemap_write_and_wait_range(mapping, start, end);
+			ret = filemap_write_and_wait_range(mapping, start,
+							   end - 1);
 			if (ret) {
 				filemap_invalidate_unlock(mapping);
 				goto out_mutex;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 0166bb9ca160..6aa15dafc677 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -349,9 +349,10 @@ static void ext4_inode_extension_cleanup(struct inode *inode, ssize_t count)
 		return;
 	}
 	/*
-	 * If i_disksize got extended due to writeback of delalloc blocks while
-	 * the DIO was running we could fail to cleanup the orphan list in
-	 * ext4_handle_inode_extension(). Do it now.
+	 * If i_disksize got extended either due to writeback of delalloc
+	 * blocks or extending truncate while the DIO was running we could fail
+	 * to cleanup the orphan list in ext4_handle_inode_extension(). Do it
+	 * now.
 	 */
 	if (!list_empty(&EXT4_I(inode)->i_orphan) && inode->i_nlink) {
 		handle_t *handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
@@ -386,10 +387,11 @@ static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size,
 	 * blocks. But the code in ext4_iomap_alloc() is careful to use
 	 * zeroed/unwritten extents if this is possible; thus we won't leave
 	 * uninitialized blocks in a file even if we didn't succeed in writing
-	 * as much as we intended.
+	 * as much as we intended. Also we can race with truncate or write
+	 * expanding the file so we have to be a bit careful here.
 	 */
-	WARN_ON_ONCE(i_size_read(inode) < READ_ONCE(EXT4_I(inode)->i_disksize));
-	if (pos + size <= READ_ONCE(EXT4_I(inode)->i_disksize))
+	if (pos + size <= READ_ONCE(EXT4_I(inode)->i_disksize) &&
+	    pos + size <= i_size_read(inode))
 		return size;
 	return ext4_handle_inode_extension(inode, pos, size);
 }
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 9a84a5f9fef4..d5bd1e3a5d36 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -502,9 +502,8 @@ static int ext4_read_inline_folio(struct inode *inode, struct folio *folio)
 	BUG_ON(len > PAGE_SIZE);
 	kaddr = kmap_local_folio(folio, 0);
 	ret = ext4_read_inline_data(inode, kaddr, len, &iloc);
-	flush_dcache_folio(folio);
+	kaddr = folio_zero_tail(folio, len, kaddr + len);
 	kunmap_local(kaddr);
-	folio_zero_segment(folio, len, folio_size(folio));
 	folio_mark_uptodate(folio);
 	brelse(iloc.bh);
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 61277f7f8722..5af1b0b8680e 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1261,7 +1261,7 @@ static int write_end_fn(handle_t *handle, struct inode *inode,
  * We need to pick up the new inode size which generic_commit_write gave us
  * `file' can be NULL - eg, when called from page_symlink().
  *
- * ext4 never places buffers on inode->i_mapping->private_list.  metadata
+ * ext4 never places buffers on inode->i_mapping->i_private_list.  metadata
  * buffers are managed internally.
  */
 static int ext4_write_end(struct file *file,
@@ -2947,7 +2947,7 @@ static int ext4_da_should_update_i_disksize(struct folio *folio,
 
 static int ext4_da_do_write_end(struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
-			struct page *page)
+			struct folio *folio)
 {
 	struct inode *inode = mapping->host;
 	loff_t old_size = inode->i_size;
@@ -2958,12 +2958,13 @@ static int ext4_da_do_write_end(struct address_space *mapping,
 	 * block_write_end() will mark the inode as dirty with I_DIRTY_PAGES
 	 * flag, which all that's needed to trigger page writeback.
 	 */
-	copied = block_write_end(NULL, mapping, pos, len, copied, page, NULL);
+	copied = block_write_end(NULL, mapping, pos, len, copied,
+			&folio->page, NULL);
 	new_i_size = pos + copied;
 
 	/*
-	 * It's important to update i_size while still holding page lock,
-	 * because page writeout could otherwise come in and zero beyond
+	 * It's important to update i_size while still holding folio lock,
+	 * because folio writeout could otherwise come in and zero beyond
 	 * i_size.
 	 *
 	 * Since we are holding inode lock, we are sure i_disksize <=
@@ -2981,14 +2982,14 @@ static int ext4_da_do_write_end(struct address_space *mapping,
 
 		i_size_write(inode, new_i_size);
 		end = (new_i_size - 1) & (PAGE_SIZE - 1);
-		if (copied && ext4_da_should_update_i_disksize(page_folio(page), end)) {
+		if (copied && ext4_da_should_update_i_disksize(folio, end)) {
 			ext4_update_i_disksize(inode, new_i_size);
 			disksize_changed = true;
 		}
 	}
 
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 
 	if (old_size < pos)
 		pagecache_isize_extended(inode, old_size, pos);
@@ -3027,10 +3028,10 @@ static int ext4_da_write_end(struct file *file,
 		return ext4_write_inline_data_end(inode, pos, len, copied,
 						  folio);
 
-	if (unlikely(copied < len) && !PageUptodate(page))
+	if (unlikely(copied < len) && !folio_test_uptodate(folio))
 		copied = 0;
 
-	return ext4_da_do_write_end(mapping, pos, len, copied, &folio->page);
+	return ext4_da_do_write_end(mapping, pos, len, copied, folio);
 }
 
 /*
@@ -3213,7 +3214,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode)
 	}
 
 	/* Any metadata buffers to write? */
-	if (!list_empty(&inode->i_mapping->private_list))
+	if (!list_empty(&inode->i_mapping->i_private_list))
 		return true;
 	return inode->i_state & I_DIRTY_DATASYNC;
 }
@@ -3564,7 +3565,7 @@ static const struct address_space_operations ext4_aops = {
 	.direct_IO		= noop_direct_IO,
 	.migrate_folio		= buffer_migrate_folio,
 	.is_partially_uptodate  = block_is_partially_uptodate,
-	.error_remove_page	= generic_error_remove_page,
+	.error_remove_folio	= generic_error_remove_folio,
 	.swap_activate		= ext4_iomap_swap_activate,
 };
 
@@ -3581,7 +3582,7 @@ static const struct address_space_operations ext4_journalled_aops = {
 	.direct_IO		= noop_direct_IO,
 	.migrate_folio		= buffer_migrate_folio_norefs,
 	.is_partially_uptodate  = block_is_partially_uptodate,
-	.error_remove_page	= generic_error_remove_page,
+	.error_remove_folio	= generic_error_remove_folio,
 	.swap_activate		= ext4_iomap_swap_activate,
 };
 
@@ -3598,7 +3599,7 @@ static const struct address_space_operations ext4_da_aops = {
 	.direct_IO		= noop_direct_IO,
 	.migrate_folio		= buffer_migrate_folio,
 	.is_partially_uptodate  = block_is_partially_uptodate,
-	.error_remove_page	= generic_error_remove_page,
+	.error_remove_folio	= generic_error_remove_folio,
 	.swap_activate		= ext4_iomap_swap_activate,
 };
 
@@ -3630,6 +3631,12 @@ void ext4_set_aops(struct inode *inode)
 		inode->i_mapping->a_ops = &ext4_aops;
 }
 
+/*
+ * Here we can't skip an unwritten buffer even though it usually reads zero
+ * because it might have data in pagecache (eg, if called from ext4_zero_range,
+ * ext4_punch_hole, etc) which needs to be properly zeroed out. Otherwise a
+ * racing writeback can come later and flush the stale pagecache to disk.
+ */
 static int __ext4_block_zero_page_range(handle_t *handle,
 		struct address_space *mapping, loff_t from, loff_t length)
 {
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 4f931f80cb34..aa6be510eb8f 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -819,11 +819,11 @@ int ext4_force_shutdown(struct super_block *sb, u32 flags)
 
 	switch (flags) {
 	case EXT4_GOING_FLAGS_DEFAULT:
-		ret = freeze_bdev(sb->s_bdev);
+		ret = bdev_freeze(sb->s_bdev);
 		if (ret)
 			return ret;
 		set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
-		thaw_bdev(sb->s_bdev);
+		bdev_thaw(sb->s_bdev);
 		break;
 	case EXT4_GOING_FLAGS_LOGFLUSH:
 		set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 454d5612641e..f44f668e407f 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1456,9 +1456,8 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
 		return 0;
 	}
 
-	block++;
-	pnum = block / blocks_per_page;
-	page = find_or_create_page(inode->i_mapping, pnum, gfp);
+	/* blocks_per_page == 1, hence we need another page for the buddy */
+	page = find_or_create_page(inode->i_mapping, block + 1, gfp);
 	if (!page)
 		return -ENOMEM;
 	BUG_ON(page->mapping != inode->i_mapping);
@@ -1958,8 +1957,7 @@ done:
 static int mb_find_extent(struct ext4_buddy *e4b, int block,
 				int needed, struct ext4_free_extent *ex)
 {
-	int next = block;
-	int max, order;
+	int max, order, next;
 	void *buddy;
 
 	assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group));
@@ -1977,16 +1975,12 @@ static int mb_find_extent(struct ext4_buddy *e4b, int block,
 
 	/* find actual order */
 	order = mb_find_order_for_block(e4b, block);
-	block = block >> order;
 
-	ex->fe_len = 1 << order;
-	ex->fe_start = block << order;
+	ex->fe_len = (1 << order) - (block & ((1 << order) - 1));
+	ex->fe_start = block;
 	ex->fe_group = e4b->bd_group;
 
-	/* calc difference from given start */
-	next = next - ex->fe_start;
-	ex->fe_len -= next;
-	ex->fe_start += next;
+	block = block >> order;
 
 	while (needed > ex->fe_len &&
 	       mb_find_buddy(e4b, order, &max)) {
@@ -2895,14 +2889,19 @@ repeat:
 			ac->ac_groups_scanned++;
 			if (cr == CR_POWER2_ALIGNED)
 				ext4_mb_simple_scan_group(ac, &e4b);
-			else if ((cr == CR_GOAL_LEN_FAST ||
-				 cr == CR_BEST_AVAIL_LEN) &&
-				 sbi->s_stripe &&
-				 !(ac->ac_g_ex.fe_len %
-				 EXT4_B2C(sbi, sbi->s_stripe)))
-				ext4_mb_scan_aligned(ac, &e4b);
-			else
-				ext4_mb_complex_scan_group(ac, &e4b);
+			else {
+				bool is_stripe_aligned = sbi->s_stripe &&
+					!(ac->ac_g_ex.fe_len %
+					  EXT4_B2C(sbi, sbi->s_stripe));
+
+				if ((cr == CR_GOAL_LEN_FAST ||
+				     cr == CR_BEST_AVAIL_LEN) &&
+				    is_stripe_aligned)
+					ext4_mb_scan_aligned(ac, &e4b);
+
+				if (ac->ac_status == AC_STATUS_CONTINUE)
+					ext4_mb_complex_scan_group(ac, &e4b);
+			}
 
 			ext4_unlock_group(sb, group);
 			ext4_mb_unload_buddy(&e4b);
@@ -4478,6 +4477,10 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	start = max(start, rounddown(ac->ac_o_ex.fe_logical,
 			(ext4_lblk_t)EXT4_BLOCKS_PER_GROUP(ac->ac_sb)));
 
+	/* avoid unnecessary preallocation that may trigger assertions */
+	if (start + size > EXT_MAX_BLOCKS)
+		size = EXT_MAX_BLOCKS - start;
+
 	/* don't cover already allocated blocks in selected range */
 	if (ar->pleft && start <= ar->lleft) {
 		size -= ar->lleft + 1 - start;
@@ -6731,11 +6734,16 @@ __acquires(bitlock)
 static ext4_grpblk_t ext4_last_grp_cluster(struct super_block *sb,
 					   ext4_group_t grp)
 {
-	if (grp < ext4_get_groups_count(sb))
-		return EXT4_CLUSTERS_PER_GROUP(sb) - 1;
-	return (ext4_blocks_count(EXT4_SB(sb)->s_es) -
-		ext4_group_first_block_no(sb, grp) - 1) >>
-					EXT4_CLUSTER_BITS(sb);
+	unsigned long nr_clusters_in_group;
+
+	if (grp < (ext4_get_groups_count(sb) - 1))
+		nr_clusters_in_group = EXT4_CLUSTERS_PER_GROUP(sb);
+	else
+		nr_clusters_in_group = (ext4_blocks_count(EXT4_SB(sb)->s_es) -
+					ext4_group_first_block_no(sb, grp))
+				       >> EXT4_CLUSTER_BITS(sb);
+
+	return nr_clusters_in_group - 1;
 }
 
 static bool ext4_trim_interrupted(void)
@@ -6749,13 +6757,15 @@ static int ext4_try_to_trim_range(struct super_block *sb,
 __acquires(ext4_group_lock_ptr(sb, e4b->bd_group))
 __releases(ext4_group_lock_ptr(sb, e4b->bd_group))
 {
-	ext4_grpblk_t next, count, free_count;
+	ext4_grpblk_t next, count, free_count, last, origin_start;
 	bool set_trimmed = false;
 	void *bitmap;
 
+	last = ext4_last_grp_cluster(sb, e4b->bd_group);
 	bitmap = e4b->bd_bitmap;
-	if (start == 0 && max >= ext4_last_grp_cluster(sb, e4b->bd_group))
+	if (start == 0 && max >= last)
 		set_trimmed = true;
+	origin_start = start;
 	start = max(e4b->bd_info->bb_first_free, start);
 	count = 0;
 	free_count = 0;
@@ -6764,7 +6774,10 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group))
 		start = mb_find_next_zero_bit(bitmap, max + 1, start);
 		if (start > max)
 			break;
-		next = mb_find_next_bit(bitmap, max + 1, start);
+
+		next = mb_find_next_bit(bitmap, last + 1, start);
+		if (origin_start == 0 && next >= last)
+			set_trimmed = true;
 
 		if ((next - start) >= minblocks) {
 			int ret = ext4_trim_extent(sb, start, next - start, e4b);
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index dfdd7e5cf038..312bc6813357 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -444,7 +444,7 @@ int ext4_bio_write_folio(struct ext4_io_submit *io, struct folio *folio,
 	folio_clear_error(folio);
 
 	/*
-	 * Comments copied from block_write_full_page:
+	 * Comments copied from block_write_full_folio:
 	 *
 	 * The folio straddles i_size.  It must be zeroed out on each and every
 	 * writepage invocation because it may be mmapped.  "A file is mapped
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 4fe061edefdd..4d4a5a32e310 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -218,35 +218,53 @@ struct ext4_new_flex_group_data {
 						   in the flex group */
 	__u16 *bg_flags;			/* block group flags of groups
 						   in @groups */
+	ext4_group_t resize_bg;			/* number of allocated
+						   new_group_data */
 	ext4_group_t count;			/* number of groups in @groups
 						 */
 };
 
 /*
+ * Avoiding memory allocation failures due to too many groups added each time.
+ */
+#define MAX_RESIZE_BG				16384
+
+/*
  * alloc_flex_gd() allocates a ext4_new_flex_group_data with size of
  * @flexbg_size.
  *
  * Returns NULL on failure otherwise address of the allocated structure.
  */
-static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size)
+static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned int flexbg_size,
+				ext4_group_t o_group, ext4_group_t n_group)
 {
+	ext4_group_t last_group;
 	struct ext4_new_flex_group_data *flex_gd;
 
 	flex_gd = kmalloc(sizeof(*flex_gd), GFP_NOFS);
 	if (flex_gd == NULL)
 		goto out3;
 
-	if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data))
-		goto out2;
-	flex_gd->count = flexbg_size;
+	if (unlikely(flexbg_size > MAX_RESIZE_BG))
+		flex_gd->resize_bg = MAX_RESIZE_BG;
+	else
+		flex_gd->resize_bg = flexbg_size;
+
+	/* Avoid allocating large 'groups' array if not needed */
+	last_group = o_group | (flex_gd->resize_bg - 1);
+	if (n_group <= last_group)
+		flex_gd->resize_bg = 1 << fls(n_group - o_group + 1);
+	else if (n_group - last_group < flex_gd->resize_bg)
+		flex_gd->resize_bg = 1 << max(fls(last_group - o_group + 1),
+					      fls(n_group - last_group));
 
-	flex_gd->groups = kmalloc_array(flexbg_size,
+	flex_gd->groups = kmalloc_array(flex_gd->resize_bg,
 					sizeof(struct ext4_new_group_data),
 					GFP_NOFS);
 	if (flex_gd->groups == NULL)
 		goto out2;
 
-	flex_gd->bg_flags = kmalloc_array(flexbg_size, sizeof(__u16),
+	flex_gd->bg_flags = kmalloc_array(flex_gd->resize_bg, sizeof(__u16),
 					  GFP_NOFS);
 	if (flex_gd->bg_flags == NULL)
 		goto out1;
@@ -283,7 +301,7 @@ static void free_flex_gd(struct ext4_new_flex_group_data *flex_gd)
  */
 static int ext4_alloc_group_tables(struct super_block *sb,
 				struct ext4_new_flex_group_data *flex_gd,
-				int flexbg_size)
+				unsigned int flexbg_size)
 {
 	struct ext4_new_group_data *group_data = flex_gd->groups;
 	ext4_fsblk_t start_blk;
@@ -384,12 +402,12 @@ next_group:
 		group = group_data[0].group;
 
 		printk(KERN_DEBUG "EXT4-fs: adding a flex group with "
-		       "%d groups, flexbg size is %d:\n", flex_gd->count,
+		       "%u groups, flexbg size is %u:\n", flex_gd->count,
 		       flexbg_size);
 
 		for (i = 0; i < flex_gd->count; i++) {
 			ext4_debug(
-			       "adding %s group %u: %u blocks (%d free, %d mdata blocks)\n",
+			       "adding %s group %u: %u blocks (%u free, %u mdata blocks)\n",
 			       ext4_bg_has_super(sb, group + i) ? "normal" :
 			       "no-super", group + i,
 			       group_data[i].blocks_count,
@@ -1605,8 +1623,7 @@ exit:
 
 static int ext4_setup_next_flex_gd(struct super_block *sb,
 				    struct ext4_new_flex_group_data *flex_gd,
-				    ext4_fsblk_t n_blocks_count,
-				    unsigned long flexbg_size)
+				    ext4_fsblk_t n_blocks_count)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_super_block *es = sbi->s_es;
@@ -1630,7 +1647,7 @@ static int ext4_setup_next_flex_gd(struct super_block *sb,
 	BUG_ON(last);
 	ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &last);
 
-	last_group = group | (flexbg_size - 1);
+	last_group = group | (flex_gd->resize_bg - 1);
 	if (last_group > n_group)
 		last_group = n_group;
 
@@ -1990,8 +2007,9 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
 	ext4_fsblk_t o_blocks_count;
 	ext4_fsblk_t n_blocks_count_retry = 0;
 	unsigned long last_update_time = 0;
-	int err = 0, flexbg_size = 1 << sbi->s_log_groups_per_flex;
+	int err = 0;
 	int meta_bg;
+	unsigned int flexbg_size = ext4_flex_bg_size(sbi);
 
 	/* See if the device is actually as big as what was requested */
 	bh = ext4_sb_bread(sb, n_blocks_count - 1, 0);
@@ -2123,7 +2141,7 @@ retry:
 	if (err)
 		goto out;
 
-	flex_gd = alloc_flex_gd(flexbg_size);
+	flex_gd = alloc_flex_gd(flexbg_size, o_group, n_group);
 	if (flex_gd == NULL) {
 		err = -ENOMEM;
 		goto out;
@@ -2132,8 +2150,7 @@ retry:
 	/* Add flex groups. Note that a regular group is a
 	 * flex group with 1 group.
 	 */
-	while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count,
-					      flexbg_size)) {
+	while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count)) {
 		if (time_is_before_jiffies(last_update_time + HZ * 10)) {
 			if (last_update_time)
 				ext4_msg(sb, KERN_INFO,
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index c5fcf377ab1f..dcba0f85dfe2 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2793,15 +2793,6 @@ static int ext4_check_opt_consistency(struct fs_context *fc,
 		return -EINVAL;
 	}
 
-	if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DIOREAD_NOLOCK)) {
-		int blocksize =
-			BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
-		if (blocksize < PAGE_SIZE)
-			ext4_msg(NULL, KERN_WARNING, "Warning: mounting with an "
-				 "experimental mount option 'dioread_nolock' "
-				 "for blocksize < PAGE_SIZE");
-	}
-
 	err = ext4_check_test_dummy_encryption(fc, sb);
 	if (err)
 		return err;
@@ -4410,7 +4401,7 @@ static void ext4_set_def_opts(struct super_block *sb,
 	    ((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0))
 		set_opt(sb, DELALLOC);
 
-	if (sb->s_blocksize == PAGE_SIZE)
+	if (sb->s_blocksize <= PAGE_SIZE)
 		set_opt(sb, DIOREAD_NOLOCK);
 }
 
@@ -5864,11 +5855,9 @@ static struct bdev_handle *ext4_get_journal_blkdev(struct super_block *sb,
 	struct ext4_super_block *es;
 	int errno;
 
-	/* see get_tree_bdev why this is needed and safe */
-	up_write(&sb->s_umount);
-	bdev_handle = bdev_open_by_dev(j_dev, BLK_OPEN_READ | BLK_OPEN_WRITE,
-				       sb, &fs_holder_ops);
-	down_write(&sb->s_umount);
+	bdev_handle = bdev_open_by_dev(j_dev,
+		BLK_OPEN_READ | BLK_OPEN_WRITE | BLK_OPEN_RESTRICT_WRITES,
+		sb, &fs_holder_ops);
 	if (IS_ERR(bdev_handle)) {
 		ext4_msg(sb, KERN_ERR,
 			 "failed to open journal device unknown-block(%u,%u) %ld",
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index 36e5dab6baae..6b2af514660d 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -1944,7 +1944,7 @@ void f2fs_invalidate_compress_pages(struct f2fs_sb_info *sbi, nid_t ino)
 				continue;
 			}
 
-			generic_error_remove_page(mapping, &folio->page);
+			generic_error_remove_folio(mapping, folio);
 			folio_unlock(folio);
 		}
 		folio_batch_release(&fbatch);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 4e42b5f24deb..9b62549a29ce 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -995,7 +995,7 @@ static bool is_end_zone_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr)
 		}
 		blkaddr -= FDEV(devi).start_blk;
 	}
-	return bdev_zoned_model(FDEV(devi).bdev) == BLK_ZONED_HM &&
+	return bdev_is_zoned(FDEV(devi).bdev) &&
 		f2fs_blkz_is_seq(sbi, devi, blkaddr) &&
 		(blkaddr % sbi->blocks_per_blkz == sbi->blocks_per_blkz - 1);
 }
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index e50363583f01..4580dfefd5e9 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -2239,11 +2239,11 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
 
 	switch (in) {
 	case F2FS_GOING_DOWN_FULLSYNC:
-		ret = freeze_bdev(sb->s_bdev);
+		ret = bdev_freeze(sb->s_bdev);
 		if (ret)
 			goto out;
 		f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN);
-		thaw_bdev(sb->s_bdev);
+		bdev_thaw(sb->s_bdev);
 		break;
 	case F2FS_GOING_DOWN_METASYNC:
 		/* do checkpoint only */
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 560bfcad1af2..a9eb3891f417 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -600,7 +600,7 @@ make_now:
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 		inode->i_mapping->a_ops = &f2fs_compress_aops;
 		/*
-		 * generic_error_remove_page only truncates pages of regular
+		 * generic_error_remove_folio only truncates pages of regular
 		 * inode
 		 */
 		inode->i_mode |= S_IFREG;
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 033af907c3b1..e965b4ec366c 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1717,12 +1717,10 @@ static void f2fs_put_super(struct super_block *sb)
 
 	kvfree(sbi->ckpt);
 
-	sb->s_fs_info = NULL;
 	if (sbi->s_chksum_driver)
 		crypto_free_shash(sbi->s_chksum_driver);
 	kfree(sbi->raw_super);
 
-	destroy_device_list(sbi);
 	f2fs_destroy_page_array_cache(sbi);
 	f2fs_destroy_xattr_caches(sbi);
 	mempool_destroy(sbi->write_io_dummy);
@@ -1738,7 +1736,6 @@ static void f2fs_put_super(struct super_block *sb)
 #if IS_ENABLED(CONFIG_UNICODE)
 	utf8_unload(sb->s_encoding);
 #endif
-	kfree(sbi);
 }
 
 int f2fs_sync_fs(struct super_block *sb, int sync)
@@ -4282,24 +4279,21 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 			sbi->aligned_blksize = false;
 
 #ifdef CONFIG_BLK_DEV_ZONED
-		if (bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HM &&
-				!f2fs_sb_has_blkzoned(sbi)) {
-			f2fs_err(sbi, "Zoned block device feature not enabled");
-			return -EINVAL;
-		}
-		if (bdev_zoned_model(FDEV(i).bdev) != BLK_ZONED_NONE) {
+		if (bdev_is_zoned(FDEV(i).bdev)) {
+			if (!f2fs_sb_has_blkzoned(sbi)) {
+				f2fs_err(sbi, "Zoned block device feature not enabled");
+				return -EINVAL;
+			}
 			if (init_blkz_info(sbi, i)) {
 				f2fs_err(sbi, "Failed to initialize F2FS blkzone information");
 				return -EINVAL;
 			}
 			if (max_devices == 1)
 				break;
-			f2fs_info(sbi, "Mount Device [%2d]: %20s, %8u, %8x - %8x (zone: %s)",
+			f2fs_info(sbi, "Mount Device [%2d]: %20s, %8u, %8x - %8x (zone: Host-managed)",
 				  i, FDEV(i).path,
 				  FDEV(i).total_segments,
-				  FDEV(i).start_blk, FDEV(i).end_blk,
-				  bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HA ?
-				  "Host-aware" : "Host-managed");
+				  FDEV(i).start_blk, FDEV(i).end_blk);
 			continue;
 		}
 #endif
@@ -4902,9 +4896,9 @@ static struct dentry *f2fs_mount(struct file_system_type *fs_type, int flags,
 
 static void kill_f2fs_super(struct super_block *sb)
 {
-	if (sb->s_root) {
-		struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 
+	if (sb->s_root) {
 		set_sbi_flag(sbi, SBI_IS_CLOSE);
 		f2fs_stop_gc_thread(sbi);
 		f2fs_stop_discard_thread(sbi);
@@ -4931,6 +4925,12 @@ static void kill_f2fs_super(struct super_block *sb)
 			sb->s_flags &= ~SB_RDONLY;
 	}
 	kill_block_super(sb);
+	/* Release block devices last, after fscrypt_destroy_keyring(). */
+	if (sbi) {
+		destroy_device_list(sbi);
+		kfree(sbi);
+		sb->s_fs_info = NULL;
+	}
 }
 
 static struct file_system_type f2fs_fs_type = {
diff --git a/fs/file.c b/fs/file.c
index 5fb0b146e79e..3b683b9101d8 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -629,19 +629,23 @@ void fd_install(unsigned int fd, struct file *file)
 EXPORT_SYMBOL(fd_install);
 
 /**
- * pick_file - return file associatd with fd
+ * file_close_fd_locked - return file associated with fd
  * @files: file struct to retrieve file from
  * @fd: file descriptor to retrieve file for
  *
+ * Doesn't take a separate reference count.
+ *
  * Context: files_lock must be held.
  *
  * Returns: The file associated with @fd (NULL if @fd is not open)
  */
-static struct file *pick_file(struct files_struct *files, unsigned fd)
+struct file *file_close_fd_locked(struct files_struct *files, unsigned fd)
 {
 	struct fdtable *fdt = files_fdtable(files);
 	struct file *file;
 
+	lockdep_assert_held(&files->file_lock);
+
 	if (fd >= fdt->max_fds)
 		return NULL;
 
@@ -660,7 +664,7 @@ int close_fd(unsigned fd)
 	struct file *file;
 
 	spin_lock(&files->file_lock);
-	file = pick_file(files, fd);
+	file = file_close_fd_locked(files, fd);
 	spin_unlock(&files->file_lock);
 	if (!file)
 		return -EBADF;
@@ -707,7 +711,7 @@ static inline void __range_close(struct files_struct *files, unsigned int fd,
 	max_fd = min(max_fd, n);
 
 	for (; fd <= max_fd; fd++) {
-		file = pick_file(files, fd);
+		file = file_close_fd_locked(files, fd);
 		if (file) {
 			spin_unlock(&files->file_lock);
 			filp_close(file, files);
@@ -795,26 +799,21 @@ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags)
 	return 0;
 }
 
-/*
- * See close_fd_get_file() below, this variant assumes current->files->file_lock
- * is held.
- */
-struct file *__close_fd_get_file(unsigned int fd)
-{
-	return pick_file(current->files, fd);
-}
-
-/*
- * variant of close_fd that gets a ref on the file for later fput.
- * The caller must ensure that filp_close() called on the file.
+/**
+ * file_close_fd - return file associated with fd
+ * @fd: file descriptor to retrieve file for
+ *
+ * Doesn't take a separate reference count.
+ *
+ * Returns: The file associated with @fd (NULL if @fd is not open)
  */
-struct file *close_fd_get_file(unsigned int fd)
+struct file *file_close_fd(unsigned int fd)
 {
 	struct files_struct *files = current->files;
 	struct file *file;
 
 	spin_lock(&files->file_lock);
-	file = pick_file(files, fd);
+	file = file_close_fd_locked(files, fd);
 	spin_unlock(&files->file_lock);
 
 	return file;
@@ -959,31 +958,45 @@ static inline struct file *__fget_files_rcu(struct files_struct *files,
 		struct file *file;
 		struct fdtable *fdt = rcu_dereference_raw(files->fdt);
 		struct file __rcu **fdentry;
+		unsigned long nospec_mask;
 
-		if (unlikely(fd >= fdt->max_fds))
-			return NULL;
-
-		fdentry = fdt->fd + array_index_nospec(fd, fdt->max_fds);
+		/* Mask is a 0 for invalid fd's, ~0 for valid ones */
+		nospec_mask = array_index_mask_nospec(fd, fdt->max_fds);
 
 		/*
-		 * Ok, we have a file pointer. However, because we do
-		 * this all locklessly under RCU, we may be racing with
-		 * that file being closed.
-		 *
-		 * Such a race can take two forms:
-		 *
-		 *  (a) the file ref already went down to zero and the
-		 *      file hasn't been reused yet or the file count
-		 *      isn't zero but the file has already been reused.
+		 * fdentry points to the 'fd' offset, or fdt->fd[0].
+		 * Loading from fdt->fd[0] is always safe, because the
+		 * array always exists.
 		 */
-		file = __get_file_rcu(fdentry);
+		fdentry = fdt->fd + (fd & nospec_mask);
+
+		/* Do the load, then mask any invalid result */
+		file = rcu_dereference_raw(*fdentry);
+		file = (void *)(nospec_mask & (unsigned long)file);
 		if (unlikely(!file))
 			return NULL;
 
-		if (unlikely(IS_ERR(file)))
+		/*
+		 * Ok, we have a file pointer that was valid at
+		 * some point, but it might have become stale since.
+		 *
+		 * We need to confirm it by incrementing the refcount
+		 * and then check the lookup again.
+		 *
+		 * atomic_long_inc_not_zero() gives us a full memory
+		 * barrier. We only really need an 'acquire' one to
+		 * protect the loads below, but we don't have that.
+		 */
+		if (unlikely(!atomic_long_inc_not_zero(&file->f_count)))
 			continue;
 
 		/*
+		 * Such a race can take two forms:
+		 *
+		 *  (a) the file ref already went down to zero and the
+		 *      file hasn't been reused yet or the file count
+		 *      isn't zero but the file has already been reused.
+		 *
 		 *  (b) the file table entry has changed under us.
 		 *       Note that we don't need to re-check the 'fdt->fd'
 		 *       pointer having changed, because it always goes
@@ -991,7 +1004,8 @@ static inline struct file *__fget_files_rcu(struct files_struct *files,
 		 *
 		 * If so, we need to put our ref and try again.
 		 */
-		if (unlikely(rcu_dereference_raw(files->fdt) != fdt)) {
+		if (unlikely(file != rcu_dereference_raw(*fdentry)) ||
+		    unlikely(rcu_dereference_raw(files->fdt) != fdt)) {
 			fput(file);
 			continue;
 		}
@@ -1128,13 +1142,13 @@ static unsigned long __fget_light(unsigned int fd, fmode_t mask)
 	 * atomic_read_acquire() pairs with atomic_dec_and_test() in
 	 * put_files_struct().
 	 */
-	if (atomic_read_acquire(&files->count) == 1) {
+	if (likely(atomic_read_acquire(&files->count) == 1)) {
 		file = files_lookup_fd_raw(files, fd);
 		if (!file || unlikely(file->f_mode & mask))
 			return 0;
 		return (unsigned long)file;
 	} else {
-		file = __fget(fd, mask);
+		file = __fget_files(files, fd, mask);
 		if (!file)
 			return 0;
 		return FDPUT_FPUT | (unsigned long)file;
@@ -1282,7 +1296,7 @@ out_unlock:
 }
 
 /**
- * __receive_fd() - Install received file into file descriptor table
+ * receive_fd() - Install received file into file descriptor table
  * @file: struct file that was received from another process
  * @ufd: __user pointer to write new fd number to
  * @o_flags: the O_* flags to apply to the new fd entry
@@ -1296,7 +1310,7 @@ out_unlock:
  *
  * Returns newly install fd or -ve on error.
  */
-int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags)
+int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags)
 {
 	int new_fd;
 	int error;
@@ -1321,6 +1335,7 @@ int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags)
 	__receive_sock(file);
 	return new_fd;
 }
+EXPORT_SYMBOL_GPL(receive_fd);
 
 int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags)
 {
@@ -1336,12 +1351,6 @@ int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags)
 	return new_fd;
 }
 
-int receive_fd(struct file *file, unsigned int o_flags)
-{
-	return __receive_fd(file, NULL, o_flags);
-}
-EXPORT_SYMBOL_GPL(receive_fd);
-
 static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags)
 {
 	int err = -EBADF;
diff --git a/fs/file_table.c b/fs/file_table.c
index de4a2915bfd4..c5ac2cc05135 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -75,18 +75,6 @@ static inline void file_free(struct file *f)
 	}
 }
 
-void release_empty_file(struct file *f)
-{
-	WARN_ON_ONCE(f->f_mode & (FMODE_BACKING | FMODE_OPENED));
-	if (atomic_long_dec_and_test(&f->f_count)) {
-		security_file_free(f);
-		put_cred(f->f_cred);
-		if (likely(!(f->f_mode & FMODE_NOACCOUNT)))
-			percpu_counter_dec(&nr_files);
-		kmem_cache_free(filp_cachep, f);
-	}
-}
-
 /*
  * Return the total number of open files in the system
  */
@@ -142,7 +130,6 @@ static struct ctl_table fs_stat_sysctls[] = {
 		.extra1		= &sysctl_nr_open_min,
 		.extra2		= &sysctl_nr_open_max,
 	},
-	{ }
 };
 
 static int __init init_fs_stat_sysctls(void)
@@ -419,7 +406,7 @@ static void delayed_fput(struct work_struct *unused)
 
 static void ____fput(struct callback_head *work)
 {
-	__fput(container_of(work, struct file, f_rcuhead));
+	__fput(container_of(work, struct file, f_task_work));
 }
 
 /*
@@ -445,9 +432,13 @@ void fput(struct file *file)
 	if (atomic_long_dec_and_test(&file->f_count)) {
 		struct task_struct *task = current;
 
+		if (unlikely(!(file->f_mode & (FMODE_BACKING | FMODE_OPENED)))) {
+			file_free(file);
+			return;
+		}
 		if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
-			init_task_work(&file->f_rcuhead, ____fput);
-			if (!task_work_add(task, &file->f_rcuhead, TWA_RESUME))
+			init_task_work(&file->f_task_work, ____fput);
+			if (!task_work_add(task, &file->f_task_work, TWA_RESUME))
 				return;
 			/*
 			 * After this task has run exit_task_work(),
diff --git a/fs/freevxfs/vxfs_bmap.c b/fs/freevxfs/vxfs_bmap.c
index de2a5bccb930..26d367e3668d 100644
--- a/fs/freevxfs/vxfs_bmap.c
+++ b/fs/freevxfs/vxfs_bmap.c
@@ -29,7 +29,7 @@ vxfs_typdump(struct vxfs_typed *typ)
 /**
  * vxfs_bmap_ext4 - do bmap for ext4 extents
  * @ip:		pointer to the inode we do bmap for
- * @iblock:	logical block.
+ * @bn:		logical block.
  *
  * Description:
  *   vxfs_bmap_ext4 performs the bmap operation for inodes with
@@ -97,7 +97,7 @@ fail_buf:
  *   vxfs_bmap_indir reads a &struct vxfs_typed at @indir
  *   and performs the type-defined action.
  *
- * Return Value:
+ * Returns:
  *   The physical block number on success, else Zero.
  *
  * Note:
@@ -179,7 +179,7 @@ out:
  * Description:
  *   Performs the bmap operation for typed extents.
  *
- * Return Value:
+ * Returns:
  *   The physical block number on success, else Zero.
  */
 static daddr_t
@@ -243,7 +243,7 @@ vxfs_bmap_typed(struct inode *ip, long iblock)
  *   vxfs_bmap1 perfoms a logical to physical block mapping
  *   for vxfs-internal purposes.
  *
- * Return Value:
+ * Returns:
  *   The physical block number on success, else Zero.
  */
 daddr_t
diff --git a/fs/freevxfs/vxfs_immed.c b/fs/freevxfs/vxfs_immed.c
index 9b49ec36e667..ed51fcd34757 100644
--- a/fs/freevxfs/vxfs_immed.c
+++ b/fs/freevxfs/vxfs_immed.c
@@ -15,7 +15,7 @@
 
 /**
  * vxfs_immed_read_folio - read part of an immed inode into pagecache
- * @file:	file context (unused)
+ * @fp:		file context (unused)
  * @folio:	folio to fill in.
  *
  * Description:
diff --git a/fs/freevxfs/vxfs_lookup.c b/fs/freevxfs/vxfs_lookup.c
index f04ba2ed1e1a..1b0bca8b4cc6 100644
--- a/fs/freevxfs/vxfs_lookup.c
+++ b/fs/freevxfs/vxfs_lookup.c
@@ -177,8 +177,7 @@ vxfs_lookup(struct inode *dip, struct dentry *dp, unsigned int flags)
 /**
  * vxfs_readdir - read a directory
  * @fp:		the directory to read
- * @retp:	return buffer
- * @filler:	filldir callback
+ * @ctx:	dir_context for filldir/readdir
  *
  * Description:
  *   vxfs_readdir fills @retp with directory entries from @fp
diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c
index 23904a6a9a96..12ef91d170bb 100644
--- a/fs/fuse/dax.c
+++ b/fs/fuse/dax.c
@@ -1222,6 +1222,7 @@ void fuse_dax_conn_free(struct fuse_conn *fc)
 	if (fc->dax) {
 		fuse_free_dax_mem_ranges(&fc->dax->free_ranges);
 		kfree(fc->dax);
+		fc->dax = NULL;
 	}
 }
 
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 1cdb6327511e..148a71b8b4d0 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -19,6 +19,7 @@
 #include <linux/uio.h>
 #include <linux/fs.h>
 #include <linux/filelock.h>
+#include <linux/splice.h>
 
 static int fuse_send_open(struct fuse_mount *fm, u64 nodeid,
 			  unsigned int open_flags, int opcode,
@@ -1448,7 +1449,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 	if (!ia)
 		return -ENOMEM;
 
-	if (fopen_direct_io && fc->direct_io_relax) {
+	if (fopen_direct_io && fc->direct_io_allow_mmap) {
 		res = filemap_write_and_wait_range(mapping, pos, pos + count - 1);
 		if (res) {
 			fuse_io_free(ia);
@@ -1574,6 +1575,7 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	ssize_t res;
 	bool exclusive_lock =
 		!(ff->open_flags & FOPEN_PARALLEL_DIRECT_WRITES) ||
+		get_fuse_conn(inode)->direct_io_allow_mmap ||
 		iocb->ki_flags & IOCB_APPEND ||
 		fuse_direct_write_extending_i_size(iocb, from);
 
@@ -1581,6 +1583,7 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	 * Take exclusive lock if
 	 * - Parallel direct writes are disabled - a user space decision
 	 * - Parallel direct writes are enabled and i_size is being extended.
+	 * - Shared mmap on direct_io file is supported (FUSE_DIRECT_IO_ALLOW_MMAP).
 	 *   This might not be needed at all, but needs further investigation.
 	 */
 	if (exclusive_lock)
@@ -2466,9 +2469,9 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 	if (ff->open_flags & FOPEN_DIRECT_IO) {
 		/* Can't provide the coherency needed for MAP_SHARED
-		 * if FUSE_DIRECT_IO_RELAX isn't set.
+		 * if FUSE_DIRECT_IO_ALLOW_MMAP isn't set.
 		 */
-		if ((vma->vm_flags & VM_MAYSHARE) && !fc->direct_io_relax)
+		if ((vma->vm_flags & VM_MAYSHARE) && !fc->direct_io_allow_mmap)
 			return -ENODEV;
 
 		invalidate_inode_pages2(file->f_mapping);
@@ -3193,8 +3196,8 @@ static ssize_t fuse_copy_file_range(struct file *src_file, loff_t src_off,
 				     len, flags);
 
 	if (ret == -EOPNOTSUPP || ret == -EXDEV)
-		ret = generic_copy_file_range(src_file, src_off, dst_file,
-					      dst_off, len, flags);
+		ret = splice_copy_file_range(src_file, src_off, dst_file,
+					     dst_off, len);
 	return ret;
 }
 
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 6e6e721f421b..1df83eebda92 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -63,6 +63,19 @@ struct fuse_forget_link {
 	struct fuse_forget_link *next;
 };
 
+/* Submount lookup tracking */
+struct fuse_submount_lookup {
+	/** Refcount */
+	refcount_t count;
+
+	/** Unique ID, which identifies the inode between userspace
+	 * and kernel */
+	u64 nodeid;
+
+	/** The request used for sending the FORGET message */
+	struct fuse_forget_link *forget;
+};
+
 /** FUSE inode */
 struct fuse_inode {
 	/** Inode data */
@@ -158,6 +171,8 @@ struct fuse_inode {
 	 */
 	struct fuse_inode_dax *dax;
 #endif
+	/** Submount specific lookup tracking */
+	struct fuse_submount_lookup *submount_lookup;
 };
 
 /** FUSE inode state bits */
@@ -797,8 +812,8 @@ struct fuse_conn {
 	/* Is tmpfile not implemented by fs? */
 	unsigned int no_tmpfile:1;
 
-	/* relax restrictions in FOPEN_DIRECT_IO mode */
-	unsigned int direct_io_relax:1;
+	/* Relax restrictions to allow shared mmap in FOPEN_DIRECT_IO mode */
+	unsigned int direct_io_allow_mmap:1;
 
 	/* Is statx not implemented by fs? */
 	unsigned int no_statx:1;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 74d4f09d5827..2a6d44f91729 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -68,6 +68,24 @@ struct fuse_forget_link *fuse_alloc_forget(void)
 	return kzalloc(sizeof(struct fuse_forget_link), GFP_KERNEL_ACCOUNT);
 }
 
+static struct fuse_submount_lookup *fuse_alloc_submount_lookup(void)
+{
+	struct fuse_submount_lookup *sl;
+
+	sl = kzalloc(sizeof(struct fuse_submount_lookup), GFP_KERNEL_ACCOUNT);
+	if (!sl)
+		return NULL;
+	sl->forget = fuse_alloc_forget();
+	if (!sl->forget)
+		goto out_free;
+
+	return sl;
+
+out_free:
+	kfree(sl);
+	return NULL;
+}
+
 static struct inode *fuse_alloc_inode(struct super_block *sb)
 {
 	struct fuse_inode *fi;
@@ -83,6 +101,7 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
 	fi->attr_version = 0;
 	fi->orig_ino = 0;
 	fi->state = 0;
+	fi->submount_lookup = NULL;
 	mutex_init(&fi->mutex);
 	spin_lock_init(&fi->lock);
 	fi->forget = fuse_alloc_forget();
@@ -113,6 +132,17 @@ static void fuse_free_inode(struct inode *inode)
 	kmem_cache_free(fuse_inode_cachep, fi);
 }
 
+static void fuse_cleanup_submount_lookup(struct fuse_conn *fc,
+					 struct fuse_submount_lookup *sl)
+{
+	if (!refcount_dec_and_test(&sl->count))
+		return;
+
+	fuse_queue_forget(fc, sl->forget, sl->nodeid, 1);
+	sl->forget = NULL;
+	kfree(sl);
+}
+
 static void fuse_evict_inode(struct inode *inode)
 {
 	struct fuse_inode *fi = get_fuse_inode(inode);
@@ -132,6 +162,11 @@ static void fuse_evict_inode(struct inode *inode)
 					  fi->nlookup);
 			fi->forget = NULL;
 		}
+
+		if (fi->submount_lookup) {
+			fuse_cleanup_submount_lookup(fc, fi->submount_lookup);
+			fi->submount_lookup = NULL;
+		}
 	}
 	if (S_ISREG(inode->i_mode) && !fuse_is_bad(inode)) {
 		WARN_ON(!list_empty(&fi->write_files));
@@ -330,6 +365,13 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
 		fuse_dax_dontcache(inode, attr->flags);
 }
 
+static void fuse_init_submount_lookup(struct fuse_submount_lookup *sl,
+				      u64 nodeid)
+{
+	sl->nodeid = nodeid;
+	refcount_set(&sl->count, 1);
+}
+
 static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr,
 			    struct fuse_conn *fc)
 {
@@ -392,12 +434,22 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
 	 */
 	if (fc->auto_submounts && (attr->flags & FUSE_ATTR_SUBMOUNT) &&
 	    S_ISDIR(attr->mode)) {
+		struct fuse_inode *fi;
+
 		inode = new_inode(sb);
 		if (!inode)
 			return NULL;
 
 		fuse_init_inode(inode, attr, fc);
-		get_fuse_inode(inode)->nodeid = nodeid;
+		fi = get_fuse_inode(inode);
+		fi->nodeid = nodeid;
+		fi->submount_lookup = fuse_alloc_submount_lookup();
+		if (!fi->submount_lookup) {
+			iput(inode);
+			return NULL;
+		}
+		/* Sets nlookup = 1 on fi->submount_lookup->nlookup */
+		fuse_init_submount_lookup(fi->submount_lookup, nodeid);
 		inode->i_flags |= S_AUTOMOUNT;
 		goto done;
 	}
@@ -420,11 +472,11 @@ retry:
 		iput(inode);
 		goto retry;
 	}
-done:
 	fi = get_fuse_inode(inode);
 	spin_lock(&fi->lock);
 	fi->nlookup++;
 	spin_unlock(&fi->lock);
+done:
 	fuse_change_attributes(inode, attr, NULL, attr_valid, attr_version);
 
 	return inode;
@@ -1230,8 +1282,8 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
 				fc->init_security = 1;
 			if (flags & FUSE_CREATE_SUPP_GROUP)
 				fc->create_supp_group = 1;
-			if (flags & FUSE_DIRECT_IO_RELAX)
-				fc->direct_io_relax = 1;
+			if (flags & FUSE_DIRECT_IO_ALLOW_MMAP)
+				fc->direct_io_allow_mmap = 1;
 		} else {
 			ra_pages = fc->max_read / PAGE_SIZE;
 			fc->no_lock = 1;
@@ -1278,7 +1330,7 @@ void fuse_send_init(struct fuse_mount *fm)
 		FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA |
 		FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT |
 		FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP |
-		FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_RELAX;
+		FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP;
 #ifdef CONFIG_FUSE_DAX
 	if (fm->fc->dax)
 		flags |= FUSE_MAP_ALIGNMENT;
@@ -1465,6 +1517,8 @@ static int fuse_fill_super_submount(struct super_block *sb,
 	struct super_block *parent_sb = parent_fi->inode.i_sb;
 	struct fuse_attr root_attr;
 	struct inode *root;
+	struct fuse_submount_lookup *sl;
+	struct fuse_inode *fi;
 
 	fuse_sb_defaults(sb);
 	fm->sb = sb;
@@ -1487,12 +1541,27 @@ static int fuse_fill_super_submount(struct super_block *sb,
 	 * its nlookup should not be incremented.  fuse_iget() does
 	 * that, though, so undo it here.
 	 */
-	get_fuse_inode(root)->nlookup--;
+	fi = get_fuse_inode(root);
+	fi->nlookup--;
+
 	sb->s_d_op = &fuse_dentry_operations;
 	sb->s_root = d_make_root(root);
 	if (!sb->s_root)
 		return -ENOMEM;
 
+	/*
+	 * Grab the parent's submount_lookup pointer and take a
+	 * reference on the shared nlookup from the parent.  This is to
+	 * prevent the last forget for this nodeid from getting
+	 * triggered until all users have finished with it.
+	 */
+	sl = parent_fi->submount_lookup;
+	WARN_ON(!sl);
+	if (sl) {
+		refcount_inc(&sl->count);
+		fi->submount_lookup = sl;
+	}
+
 	return 0;
 }
 
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 9611bfceda4b..974aca9c8ea8 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -82,11 +82,11 @@ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock,
 }
 
 /**
- * gfs2_write_jdata_folio - gfs2 jdata-specific version of block_write_full_page
+ * gfs2_write_jdata_folio - gfs2 jdata-specific version of block_write_full_folio
  * @folio: The folio to write
  * @wbc: The writeback control
  *
- * This is the same as calling block_write_full_page, but it also
+ * This is the same as calling block_write_full_folio, but it also
  * writes pages outside of i_size
  */
 static int gfs2_write_jdata_folio(struct folio *folio,
@@ -108,7 +108,7 @@ static int gfs2_write_jdata_folio(struct folio *folio,
 				folio_size(folio));
 
 	return __block_write_full_folio(inode, folio, gfs2_get_block_noalloc,
-			wbc, end_buffer_async_write);
+			wbc);
 }
 
 /**
@@ -403,18 +403,18 @@ static int gfs2_jdata_writepages(struct address_space *mapping,
 }
 
 /**
- * stuffed_readpage - Fill in a Linux folio with stuffed file data
+ * stuffed_read_folio - Fill in a Linux folio with stuffed file data
  * @ip: the inode
  * @folio: the folio
  *
  * Returns: errno
  */
-static int stuffed_readpage(struct gfs2_inode *ip, struct folio *folio)
+static int stuffed_read_folio(struct gfs2_inode *ip, struct folio *folio)
 {
-	struct buffer_head *dibh;
-	size_t i_size = i_size_read(&ip->i_inode);
-	void *data;
-	int error;
+	struct buffer_head *dibh = NULL;
+	size_t dsize = i_size_read(&ip->i_inode);
+	void *from = NULL;
+	int error = 0;
 
 	/*
 	 * Due to the order of unstuffing files and ->fault(), we can be
@@ -422,22 +422,20 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct folio *folio)
 	 * so we need to supply one here. It doesn't happen often.
 	 */
 	if (unlikely(folio->index)) {
-		folio_zero_range(folio, 0, folio_size(folio));
-		folio_mark_uptodate(folio);
-		return 0;
+		dsize = 0;
+	} else {
+		error = gfs2_meta_inode_buffer(ip, &dibh);
+		if (error)
+			goto out;
+		from = dibh->b_data + sizeof(struct gfs2_dinode);
 	}
 
-	error = gfs2_meta_inode_buffer(ip, &dibh);
-	if (error)
-		return error;
-
-	data = dibh->b_data + sizeof(struct gfs2_dinode);
-	memcpy_to_folio(folio, 0, data, i_size);
-	folio_zero_range(folio, i_size, folio_size(folio) - i_size);
+	folio_fill_tail(folio, 0, from, dsize);
 	brelse(dibh);
-	folio_mark_uptodate(folio);
+out:
+	folio_end_read(folio, error == 0);
 
-	return 0;
+	return error;
 }
 
 /**
@@ -456,13 +454,12 @@ static int gfs2_read_folio(struct file *file, struct folio *folio)
 	    (i_blocksize(inode) == PAGE_SIZE && !folio_buffers(folio))) {
 		error = iomap_read_folio(folio, &gfs2_iomap_ops);
 	} else if (gfs2_is_stuffed(ip)) {
-		error = stuffed_readpage(ip, folio);
-		folio_unlock(folio);
+		error = stuffed_read_folio(ip, folio);
 	} else {
 		error = mpage_read_folio(folio, gfs2_block_map);
 	}
 
-	if (unlikely(gfs2_withdrawn(sdp)))
+	if (gfs2_withdrawing_or_withdrawn(sdp))
 		return -EIO;
 
 	return error;
@@ -748,7 +745,7 @@ static const struct address_space_operations gfs2_aops = {
 	.bmap = gfs2_bmap,
 	.migrate_folio = filemap_migrate_folio,
 	.is_partially_uptodate = iomap_is_partially_uptodate,
-	.error_remove_page = generic_error_remove_page,
+	.error_remove_folio = generic_error_remove_folio,
 };
 
 static const struct address_space_operations gfs2_jdata_aops = {
@@ -761,7 +758,7 @@ static const struct address_space_operations gfs2_jdata_aops = {
 	.invalidate_folio = gfs2_invalidate_folio,
 	.release_folio = gfs2_release_folio,
 	.is_partially_uptodate = block_is_partially_uptodate,
-	.error_remove_page = generic_error_remove_page,
+	.error_remove_folio = generic_error_remove_folio,
 };
 
 void gfs2_set_aops(struct inode *inode)
diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c
index 2e215e8c3c88..177f1f41f225 100644
--- a/fs/gfs2/dentry.c
+++ b/fs/gfs2/dentry.c
@@ -32,21 +32,25 @@
 
 static int gfs2_drevalidate(struct dentry *dentry, unsigned int flags)
 {
-	struct dentry *parent;
+	struct dentry *parent = NULL;
 	struct gfs2_sbd *sdp;
 	struct gfs2_inode *dip;
-	struct inode *inode;
+	struct inode *dinode, *inode;
 	struct gfs2_holder d_gh;
 	struct gfs2_inode *ip = NULL;
 	int error, valid = 0;
 	int had_lock = 0;
 
-	if (flags & LOOKUP_RCU)
-		return -ECHILD;
-
-	parent = dget_parent(dentry);
-	sdp = GFS2_SB(d_inode(parent));
-	dip = GFS2_I(d_inode(parent));
+	if (flags & LOOKUP_RCU) {
+		dinode = d_inode_rcu(READ_ONCE(dentry->d_parent));
+		if (!dinode)
+			return -ECHILD;
+	} else {
+		parent = dget_parent(dentry);
+		dinode = d_inode(parent);
+	}
+	sdp = GFS2_SB(dinode);
+	dip = GFS2_I(dinode);
 	inode = d_inode(dentry);
 
 	if (inode) {
@@ -62,7 +66,8 @@ static int gfs2_drevalidate(struct dentry *dentry, unsigned int flags)
 
 	had_lock = (gfs2_glock_is_locked_by_me(dip->i_gl) != NULL);
 	if (!had_lock) {
-		error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
+		error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED,
+					   flags & LOOKUP_RCU ? GL_NOBLOCK : 0, &d_gh);
 		if (error)
 			goto out;
 	}
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index cf40895233f5..d418d8b5367f 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -138,8 +138,6 @@ static struct dentry *gfs2_get_dentry(struct super_block *sb,
 		return ERR_PTR(-ESTALE);
 	inode = gfs2_lookup_by_inum(sdp, inum->no_addr, inum->no_formal_ino,
 				    GFS2_BLKST_DINODE);
-	if (IS_ERR(inode))
-		return ERR_CAST(inode);
 	return d_obtain_alias(inode);
 }
 
@@ -192,5 +190,6 @@ const struct export_operations gfs2_export_ops = {
 	.fh_to_parent = gfs2_fh_to_parent,
 	.get_name = gfs2_get_name,
 	.get_parent = gfs2_get_parent,
+	.flags = EXPORT_OP_ASYNC_LOCK,
 };
 
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 4b66efc1a82a..992ca4effb50 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -1442,7 +1442,7 @@ static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl)
 
 	if (!(fl->fl_flags & FL_POSIX))
 		return -ENOLCK;
-	if (unlikely(gfs2_withdrawn(sdp))) {
+	if (gfs2_withdrawing_or_withdrawn(sdp)) {
 		if (fl->fl_type == F_UNLCK)
 			locks_lock_file_wait(file, fl);
 		return -EIO;
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index d6bf1f8c25dc..34540f9d011c 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -156,7 +156,7 @@ static bool glock_blocked_by_withdraw(struct gfs2_glock *gl)
 {
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 
-	if (likely(!gfs2_withdrawn(sdp)))
+	if (!gfs2_withdrawing_or_withdrawn(sdp))
 		return false;
 	if (gl->gl_ops->go_flags & GLOF_NONDISK)
 		return false;
@@ -278,7 +278,7 @@ static void __gfs2_glock_put(struct gfs2_glock *gl)
 	GLOCK_BUG_ON(gl, !list_empty(&gl->gl_holders));
 	if (mapping) {
 		truncate_inode_pages_final(mapping);
-		if (!gfs2_withdrawn(sdp))
+		if (!gfs2_withdrawing_or_withdrawn(sdp))
 			GLOCK_BUG_ON(gl, !mapping_empty(mapping));
 	}
 	trace_gfs2_glock_put(gl);
@@ -517,6 +517,23 @@ static inline struct gfs2_holder *find_first_waiter(const struct gfs2_glock *gl)
 }
 
 /**
+ * find_last_waiter - find the last gh that's waiting for the glock
+ * @gl: the glock
+ *
+ * This also is a fast way of finding out if there are any waiters.
+ */
+
+static inline struct gfs2_holder *find_last_waiter(const struct gfs2_glock *gl)
+{
+	struct gfs2_holder *gh;
+
+	if (list_empty(&gl->gl_holders))
+		return NULL;
+	gh = list_last_entry(&gl->gl_holders, struct gfs2_holder, gh_list);
+	return test_bit(HIF_HOLDER, &gh->gh_iflags) ? NULL : gh;
+}
+
+/**
  * state_change - record that the glock is now in a different state
  * @gl: the glock
  * @new_state: the new state
@@ -757,7 +774,7 @@ skip_inval:
 	 * gfs2_gl_hash_clear calls clear_glock) and recovery is complete
 	 * then it's okay to tell dlm to unlock it.
 	 */
-	if (unlikely(sdp->sd_log_error && !gfs2_withdrawn(sdp)))
+	if (unlikely(sdp->sd_log_error) && !gfs2_withdrawing_or_withdrawn(sdp))
 		gfs2_withdraw_delayed(sdp);
 	if (glock_blocked_by_withdraw(gl) &&
 	    (target != LM_ST_UNLOCKED ||
@@ -794,7 +811,7 @@ skip_inval:
 			gfs2_glock_queue_work(gl, 0);
 		} else if (ret) {
 			fs_err(sdp, "lm_lock ret %d\n", ret);
-			GLOCK_BUG_ON(gl, !gfs2_withdrawn(sdp));
+			GLOCK_BUG_ON(gl, !gfs2_withdrawing_or_withdrawn(sdp));
 		}
 	} else { /* lock_nolock */
 		finish_xmote(gl, target);
@@ -1213,7 +1230,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 		mapping->host = s->s_bdev->bd_inode;
 		mapping->flags = 0;
 		mapping_set_gfp_mask(mapping, GFP_NOFS);
-		mapping->private_data = NULL;
+		mapping->i_private_data = NULL;
 		mapping->writeback_index = 0;
 	}
 
@@ -1555,11 +1572,30 @@ trap_recursive:
 int gfs2_glock_nq(struct gfs2_holder *gh)
 {
 	struct gfs2_glock *gl = gh->gh_gl;
-	int error = 0;
+	int error;
 
 	if (glock_blocked_by_withdraw(gl) && !(gh->gh_flags & LM_FLAG_NOEXP))
 		return -EIO;
 
+	if (gh->gh_flags & GL_NOBLOCK) {
+		struct gfs2_holder *current_gh;
+
+		error = -ECHILD;
+		spin_lock(&gl->gl_lockref.lock);
+		if (find_last_waiter(gl))
+			goto unlock;
+		current_gh = find_first_holder(gl);
+		if (!may_grant(gl, current_gh, gh))
+			goto unlock;
+		set_bit(HIF_HOLDER, &gh->gh_iflags);
+		list_add_tail(&gh->gh_list, &gl->gl_holders);
+		trace_gfs2_promote(gh);
+		error = 0;
+unlock:
+		spin_unlock(&gl->gl_lockref.lock);
+		return error;
+	}
+
 	if (test_bit(GLF_LRU, &gl->gl_flags))
 		gfs2_glock_remove_from_lru(gl);
 
@@ -1575,6 +1611,7 @@ int gfs2_glock_nq(struct gfs2_holder *gh)
 	run_queue(gl, 1);
 	spin_unlock(&gl->gl_lockref.lock);
 
+	error = 0;
 	if (!(gh->gh_flags & GL_ASYNC))
 		error = gfs2_glock_wait(gh);
 
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index 61197598abfd..0114f3e0ebe0 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -84,6 +84,7 @@ enum {
 #define GL_SKIP			0x0100
 #define GL_NOPID		0x0200
 #define GL_NOCACHE		0x0400
+#define GL_NOBLOCK		0x0800
   
 /*
  * lm_async_cb return flags
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index b41c78bd2cc0..45653cbc8a87 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -174,7 +174,7 @@ static int gfs2_rgrp_metasync(struct gfs2_glock *gl)
 
 	filemap_fdatawrite_range(metamapping, start, end);
 	error = filemap_fdatawait_range(metamapping, start, end);
-	WARN_ON_ONCE(error && !gfs2_withdrawn(sdp));
+	WARN_ON_ONCE(error && !gfs2_withdrawing_or_withdrawn(sdp));
 	mapping_set_error(metamapping, error);
 	if (error)
 		gfs2_io_error(sdp);
@@ -494,7 +494,7 @@ int gfs2_inode_refresh(struct gfs2_inode *ip)
 
 /**
  * inode_go_instantiate - read in an inode if necessary
- * @gh: The glock holder
+ * @gl: The glock
  *
  * Returns: errno
  */
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 1b95db2c3aac..6bfc9383b7b8 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1882,10 +1882,10 @@ int gfs2_permission(struct mnt_idmap *idmap, struct inode *inode,
 		WARN_ON_ONCE(!may_not_block);
 		return -ECHILD;
         }
-	if (gfs2_glock_is_locked_by_me(gl) == NULL) {
-		if (may_not_block)
-			return -ECHILD;
-		error = gfs2_glock_nq_init(gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
+	if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) {
+		int noblock = may_not_block ? GL_NOBLOCK : 0;
+		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
+					   LM_FLAG_ANY | noblock, &i_gh);
 		if (error)
 			return error;
 	}
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 59ab18c79889..d1ac5d0679ea 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -1122,7 +1122,7 @@ static void gdlm_recover_prep(void *arg)
 	struct gfs2_sbd *sdp = arg;
 	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
 
-	if (gfs2_withdrawn(sdp)) {
+	if (gfs2_withdrawing_or_withdrawn(sdp)) {
 		fs_err(sdp, "recover_prep ignored due to withdraw.\n");
 		return;
 	}
@@ -1148,7 +1148,7 @@ static void gdlm_recover_slot(void *arg, struct dlm_slot *slot)
 	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
 	int jid = slot->slot - 1;
 
-	if (gfs2_withdrawn(sdp)) {
+	if (gfs2_withdrawing_or_withdrawn(sdp)) {
 		fs_err(sdp, "recover_slot jid %d ignored due to withdraw.\n",
 		       jid);
 		return;
@@ -1177,7 +1177,7 @@ static void gdlm_recover_done(void *arg, struct dlm_slot *slots, int num_slots,
 	struct gfs2_sbd *sdp = arg;
 	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
 
-	if (gfs2_withdrawn(sdp)) {
+	if (gfs2_withdrawing_or_withdrawn(sdp)) {
 		fs_err(sdp, "recover_done ignored due to withdraw.\n");
 		return;
 	}
@@ -1208,7 +1208,7 @@ static void gdlm_recovery_result(struct gfs2_sbd *sdp, unsigned int jid,
 {
 	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
 
-	if (gfs2_withdrawn(sdp)) {
+	if (gfs2_withdrawing_or_withdrawn(sdp)) {
 		fs_err(sdp, "recovery_result jid %d ignored due to withdraw.\n",
 		       jid);
 		return;
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index e5271ae87d1c..8cddf955ebc0 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -126,7 +126,7 @@ __acquires(&sdp->sd_ail_lock)
 			}
 		}
 
-		if (gfs2_withdrawn(sdp)) {
+		if (gfs2_withdrawing_or_withdrawn(sdp)) {
 			gfs2_remove_from_ail(bd);
 			continue;
 		}
@@ -352,14 +352,15 @@ static int gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr,
  * @sdp: The superblock
  * @max_revokes: If non-zero, add revokes where appropriate
  *
- * Tries to empty the ail1 lists, starting with the oldest first
+ * Tries to empty the ail1 lists, starting with the oldest first.
+ * Returns %true if the ail1 list is now empty.
  */
 
-static int gfs2_ail1_empty(struct gfs2_sbd *sdp, int max_revokes)
+static bool gfs2_ail1_empty(struct gfs2_sbd *sdp, int max_revokes)
 {
 	struct gfs2_trans *tr, *s;
 	int oldest_tr = 1;
-	int ret;
+	bool empty;
 
 	spin_lock(&sdp->sd_ail_lock);
 	list_for_each_entry_safe_reverse(tr, s, &sdp->sd_ail1_list, tr_list) {
@@ -369,15 +370,10 @@ static int gfs2_ail1_empty(struct gfs2_sbd *sdp, int max_revokes)
 			oldest_tr = 0;
 	}
 	gfs2_log_update_flush_tail(sdp);
-	ret = list_empty(&sdp->sd_ail1_list);
+	empty = list_empty(&sdp->sd_ail1_list);
 	spin_unlock(&sdp->sd_ail_lock);
 
-	if (test_bit(SDF_WITHDRAWING, &sdp->sd_flags)) {
-		gfs2_lm(sdp, "fatal: I/O error(s)\n");
-		gfs2_withdraw(sdp);
-	}
-
-	return ret;
+	return empty;
 }
 
 static void gfs2_ail1_wait(struct gfs2_sbd *sdp)
@@ -814,6 +810,9 @@ void gfs2_flush_revokes(struct gfs2_sbd *sdp)
 	gfs2_log_lock(sdp);
 	gfs2_ail1_empty(sdp, max_revokes);
 	gfs2_log_unlock(sdp);
+
+	if (gfs2_withdrawing(sdp))
+		gfs2_withdraw(sdp);
 }
 
 /**
@@ -841,7 +840,7 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
 	struct super_block *sb = sdp->sd_vfs;
 	u64 dblock;
 
-	if (gfs2_withdrawn(sdp))
+	if (gfs2_withdrawing_or_withdrawn(sdp))
 		return;
 
 	page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
@@ -914,8 +913,9 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
 static void log_write_header(struct gfs2_sbd *sdp, u32 flags)
 {
 	blk_opf_t op_flags = REQ_PREFLUSH | REQ_FUA | REQ_META | REQ_SYNC;
+	struct super_block *sb = sdp->sd_vfs;
 
-	gfs2_assert_withdraw(sdp, !test_bit(SDF_FROZEN, &sdp->sd_flags));
+	gfs2_assert_withdraw(sdp, sb->s_writers.frozen != SB_FREEZE_COMPLETE);
 
 	if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags)) {
 		gfs2_ordered_wait(sdp);
@@ -974,8 +974,9 @@ void gfs2_ail_drain(struct gfs2_sbd *sdp)
 static void empty_ail1_list(struct gfs2_sbd *sdp)
 {
 	unsigned long start = jiffies;
+	bool empty = false;
 
-	for (;;) {
+	while (!empty) {
 		if (time_after(jiffies, start + (HZ * 600))) {
 			fs_err(sdp, "Error: In %s for 10 minutes! t=%d\n",
 			       __func__, current->journal_info ? 1 : 0);
@@ -984,9 +985,14 @@ static void empty_ail1_list(struct gfs2_sbd *sdp)
 		}
 		gfs2_ail1_start(sdp);
 		gfs2_ail1_wait(sdp);
-		if (gfs2_ail1_empty(sdp, 0))
-			return;
+		empty = gfs2_ail1_empty(sdp, 0);
+
+		if (gfs2_withdrawing_or_withdrawn(sdp))
+			break;
 	}
+
+	if (gfs2_withdrawing(sdp))
+		gfs2_withdraw(sdp);
 }
 
 /**
@@ -1047,7 +1053,8 @@ repeat:
 	 * Do this check while holding the log_flush_lock to prevent new
 	 * buffers from being added to the ail via gfs2_pin()
 	 */
-	if (gfs2_withdrawn(sdp) || !test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
+	if (gfs2_withdrawing_or_withdrawn(sdp) ||
+	    !test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
 		goto out;
 
 	/* Log might have been flushed while we waited for the flush lock */
@@ -1096,13 +1103,13 @@ repeat:
 			goto out_withdraw;
 
 	gfs2_ordered_write(sdp);
-	if (gfs2_withdrawn(sdp))
+	if (gfs2_withdrawing_or_withdrawn(sdp))
 		goto out_withdraw;
 	lops_before_commit(sdp, tr);
-	if (gfs2_withdrawn(sdp))
+	if (gfs2_withdrawing_or_withdrawn(sdp))
 		goto out_withdraw;
 	gfs2_log_submit_bio(&sdp->sd_jdesc->jd_log_bio, REQ_OP_WRITE);
-	if (gfs2_withdrawn(sdp))
+	if (gfs2_withdrawing_or_withdrawn(sdp))
 		goto out_withdraw;
 
 	if (sdp->sd_log_head != sdp->sd_log_flush_head) {
@@ -1110,7 +1117,7 @@ repeat:
 	} else if (sdp->sd_log_tail != sdp->sd_log_flush_tail && !sdp->sd_log_idle) {
 		log_write_header(sdp, flags);
 	}
-	if (gfs2_withdrawn(sdp))
+	if (gfs2_withdrawing_or_withdrawn(sdp))
 		goto out_withdraw;
 	lops_after_commit(sdp, tr);
 
@@ -1128,7 +1135,7 @@ repeat:
 	if (!(flags & GFS2_LOG_HEAD_FLUSH_NORMAL)) {
 		if (!sdp->sd_log_idle) {
 			empty_ail1_list(sdp);
-			if (gfs2_withdrawn(sdp))
+			if (gfs2_withdrawing_or_withdrawn(sdp))
 				goto out_withdraw;
 			log_write_header(sdp, flags);
 		}
@@ -1297,8 +1304,9 @@ int gfs2_logd(void *data)
 	struct gfs2_sbd *sdp = data;
 	unsigned long t = 1;
 
+	set_freezable();
 	while (!kthread_should_stop()) {
-		if (gfs2_withdrawn(sdp))
+		if (gfs2_withdrawing_or_withdrawn(sdp))
 			break;
 
 		/* Check for errors writing to the journal */
@@ -1330,18 +1338,19 @@ int gfs2_logd(void *data)
 
 		t = gfs2_tune_get(sdp, gt_logd_secs) * HZ;
 
-		try_to_freeze();
-
-		t = wait_event_interruptible_timeout(sdp->sd_logd_waitq,
+		t = wait_event_freezable_timeout(sdp->sd_logd_waitq,
 				test_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags) ||
 				gfs2_ail_flush_reqd(sdp) ||
 				gfs2_jrnl_flush_reqd(sdp) ||
 				sdp->sd_log_error ||
-				gfs2_withdrawn(sdp) ||
+				gfs2_withdrawing_or_withdrawn(sdp) ||
 				kthread_should_stop(),
 				t);
 	}
 
+	if (gfs2_withdrawing(sdp))
+		gfs2_withdraw(sdp);
+
 	return 0;
 }
 
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 483f69807062..314ec2a70167 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -391,22 +391,15 @@ static void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page)
  * Simply unlock the pages in the bio. The main thread will wait on them and
  * process them in order as necessary.
  */
-
 static void gfs2_end_log_read(struct bio *bio)
 {
-	struct page *page;
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
+	int error = blk_status_to_errno(bio->bi_status);
+	struct folio_iter fi;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		page = bvec->bv_page;
-		if (bio->bi_status) {
-			int err = blk_status_to_errno(bio->bi_status);
-
-			SetPageError(page);
-			mapping_set_error(page->mapping, err);
-		}
-		unlock_page(page);
+	bio_for_each_folio_all(fi, bio) {
+		/* We're abusing wb_err to get the error to gfs2_find_jhead */
+		filemap_set_wb_err(fi.folio->mapping, error);
+		folio_end_read(fi.folio, !error);
 	}
 
 	bio_put(bio);
@@ -475,7 +468,7 @@ static void gfs2_jhead_process_page(struct gfs2_jdesc *jd, unsigned long index,
 	folio = filemap_get_folio(jd->jd_inode->i_mapping, index);
 
 	folio_wait_locked(folio);
-	if (folio_test_error(folio))
+	if (!folio_test_uptodate(folio))
 		*done = true;
 
 	if (!*done)
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 25ceb0805df2..f814054c8cd0 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -252,7 +252,8 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
 	struct buffer_head *bh, *bhs[2];
 	int num = 0;
 
-	if (unlikely(gfs2_withdrawn(sdp)) && !gfs2_withdraw_in_prog(sdp)) {
+	if (gfs2_withdrawing_or_withdrawn(sdp) &&
+	    !gfs2_withdraw_in_prog(sdp)) {
 		*bhp = NULL;
 		return -EIO;
 	}
@@ -310,7 +311,8 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
 
 int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh)
 {
-	if (unlikely(gfs2_withdrawn(sdp)) && !gfs2_withdraw_in_prog(sdp))
+	if (gfs2_withdrawing_or_withdrawn(sdp) &&
+	    !gfs2_withdraw_in_prog(sdp))
 		return -EIO;
 
 	wait_on_buffer(bh);
@@ -321,7 +323,8 @@ int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh)
 			gfs2_io_error_bh_wd(sdp, bh);
 		return -EIO;
 	}
-	if (unlikely(gfs2_withdrawn(sdp)) && !gfs2_withdraw_in_prog(sdp))
+	if (gfs2_withdrawing_or_withdrawn(sdp) &&
+	    !gfs2_withdraw_in_prog(sdp))
 		return -EIO;
 
 	return 0;
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index b108c5d26839..1281e60be639 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -117,7 +117,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 	mapping->host = sb->s_bdev->bd_inode;
 	mapping->flags = 0;
 	mapping_set_gfp_mask(mapping, GFP_NOFS);
-	mapping->private_data = NULL;
+	mapping->i_private_data = NULL;
 	mapping->writeback_index = 0;
 
 	spin_lock_init(&sdp->sd_log_lock);
@@ -1073,7 +1073,7 @@ hostdata_error:
 void gfs2_lm_unmount(struct gfs2_sbd *sdp)
 {
 	const struct lm_lockops *lm = sdp->sd_lockstruct.ls_ops;
-	if (likely(!gfs2_withdrawn(sdp)) && lm->lm_unmount)
+	if (!gfs2_withdrawing_or_withdrawn(sdp) && lm->lm_unmount)
 		lm->lm_unmount(sdp);
 }
 
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 95dae7838b4e..aa9cf0102848 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -128,7 +128,7 @@ static void gfs2_qd_dispose(struct gfs2_quota_data *qd)
 	hlist_bl_del_rcu(&qd->qd_hlist);
 	spin_unlock_bucket(qd->qd_hash);
 
-	if (!gfs2_withdrawn(sdp)) {
+	if (!gfs2_withdrawing_or_withdrawn(sdp)) {
 		gfs2_assert_warn(sdp, !qd->qd_change);
 		gfs2_assert_warn(sdp, !qd->qd_slot_ref);
 		gfs2_assert_warn(sdp, !qd->qd_bh_count);
@@ -271,7 +271,7 @@ static struct gfs2_quota_data *gfs2_qd_search_bucket(unsigned int hash,
 		if (qd->qd_sbd != sdp)
 			continue;
 		if (lockref_get_not_dead(&qd->qd_lockref)) {
-			list_lru_del(&gfs2_qd_lru, &qd->qd_lru);
+			list_lru_del_obj(&gfs2_qd_lru, &qd->qd_lru);
 			return qd;
 		}
 	}
@@ -344,7 +344,7 @@ static void qd_put(struct gfs2_quota_data *qd)
 	}
 
 	qd->qd_lockref.count = 0;
-	list_lru_add(&gfs2_qd_lru, &qd->qd_lru);
+	list_lru_add_obj(&gfs2_qd_lru, &qd->qd_lru);
 	spin_unlock(&qd->qd_lockref.lock);
 }
 
@@ -1505,7 +1505,8 @@ void gfs2_quota_cleanup(struct gfs2_sbd *sdp)
 	LIST_HEAD(dispose);
 	int count;
 
-	BUG_ON(test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags));
+	BUG_ON(!test_bit(SDF_NORECOVERY, &sdp->sd_flags) &&
+		test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags));
 
 	spin_lock(&qd_lock);
 	list_for_each_entry(qd, &sdp->sd_quota_list, qd_list) {
@@ -1517,7 +1518,7 @@ void gfs2_quota_cleanup(struct gfs2_sbd *sdp)
 		lockref_mark_dead(&qd->qd_lockref);
 		spin_unlock(&qd->qd_lockref.lock);
 
-		list_lru_del(&gfs2_qd_lru, &qd->qd_lru);
+		list_lru_del_obj(&gfs2_qd_lru, &qd->qd_lru);
 		list_add(&qd->qd_lru, &dispose);
 	}
 	spin_unlock(&qd_lock);
@@ -1539,7 +1540,7 @@ static void quotad_error(struct gfs2_sbd *sdp, const char *msg, int error)
 {
 	if (error == 0 || error == -EROFS)
 		return;
-	if (!gfs2_withdrawn(sdp)) {
+	if (!gfs2_withdrawing_or_withdrawn(sdp)) {
 		if (!cmpxchg(&sdp->sd_log_error, 0, error))
 			fs_err(sdp, "gfs2_quotad: %s error %d\n", msg, error);
 		wake_up(&sdp->sd_logd_waitq);
@@ -1582,8 +1583,9 @@ int gfs2_quotad(void *data)
 	unsigned long quotad_timeo = 0;
 	unsigned long t = 0;
 
+	set_freezable();
 	while (!kthread_should_stop()) {
-		if (gfs2_withdrawn(sdp))
+		if (gfs2_withdrawing_or_withdrawn(sdp))
 			break;
 
 		/* Update the master statfs file */
@@ -1601,13 +1603,11 @@ int gfs2_quotad(void *data)
 		quotad_check_timeo(sdp, "sync", gfs2_quota_sync, t,
 				   &quotad_timeo, &tune->gt_quota_quantum);
 
-		try_to_freeze();
-
 		t = min(quotad_timeo, statfs_timeo);
 
-		t = wait_event_interruptible_timeout(sdp->sd_quota_wait,
+		t = wait_event_freezable_timeout(sdp->sd_quota_wait,
 				sdp->sd_statfs_force_sync ||
-				gfs2_withdrawn(sdp) ||
+				gfs2_withdrawing_or_withdrawn(sdp) ||
 				kthread_should_stop(),
 				t);
 
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index 5aae02669a40..f4fe7039f725 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -411,7 +411,7 @@ void gfs2_recover_func(struct work_struct *work)
 	int error = 0;
 	int jlocked = 0;
 
-	if (gfs2_withdrawn(sdp)) {
+	if (gfs2_withdrawing_or_withdrawn(sdp)) {
 		fs_err(sdp, "jid=%u: Recovery not attempted due to withdraw.\n",
 		       jd->jd_jid);
 		goto fail;
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index c2060203b98a..26d6c1eea559 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -159,13 +159,13 @@ static inline u8 gfs2_testbit(const struct gfs2_rbm *rbm, bool use_clone)
 }
 
 /**
- * gfs2_bit_search
+ * gfs2_bit_search - search bitmap for a state
  * @ptr: Pointer to bitmap data
  * @mask: Mask to use (normally 0x55555.... but adjusted for search start)
  * @state: The state we are searching for
  *
- * We xor the bitmap data with a patter which is the bitwise opposite
- * of what we are looking for, this gives rise to a pattern of ones
+ * We xor the bitmap data with a pattern which is the bitwise opposite
+ * of what we are looking for. This gives rise to a pattern of ones
  * wherever there is a match. Since we have two bits per entry, we
  * take this pattern, shift it down by one place and then and it with
  * the original. All the even bit positions (0,2,4, etc) then represent
@@ -1188,7 +1188,7 @@ static void rgrp_set_bitmap_flags(struct gfs2_rgrpd *rgd)
 
 /**
  * gfs2_rgrp_go_instantiate - Read in a RG's header and bitmaps
- * @gh: the glock holder representing the rgrpd to read in
+ * @gl: the glock representing the rgrpd to read in
  *
  * Read in all of a Resource Group's header and bitmap blocks.
  * Caller must eventually call gfs2_rgrp_brelse() to free the bitmaps.
@@ -1967,7 +1967,7 @@ static bool gfs2_rgrp_congested(const struct gfs2_rgrpd *rgd, int loops)
 }
 
 /**
- * gfs2_rgrp_used_recently
+ * gfs2_rgrp_used_recently - test if an rgrp has been used recently
  * @rs: The block reservation with the rgrp to test
  * @msecs: The time limit in milliseconds
  *
@@ -2306,7 +2306,7 @@ void gfs2_rgrp_dump(struct seq_file *seq, struct gfs2_rgrpd *rgd,
 		       (unsigned long long)rgd->rd_addr, rgd->rd_flags,
 		       rgd->rd_free, rgd->rd_free_clone, rgd->rd_dinodes,
 		       rgd->rd_requested, rgd->rd_reserved, rgd->rd_extfail_pt);
-	if (rgd->rd_sbd->sd_args.ar_rgrplvb) {
+	if (rgd->rd_sbd->sd_args.ar_rgrplvb && rgd->rd_rgl) {
 		struct gfs2_rgrp_lvb *rgl = rgd->rd_rgl;
 
 		gfs2_print_dbg(seq, "%s  L: f:%02x b:%u i:%u\n", fs_id_buf,
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index d21c04a22d73..e5f79466340d 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -134,7 +134,7 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp)
 	int error;
 
 	j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
-	if (gfs2_withdrawn(sdp))
+	if (gfs2_withdrawing_or_withdrawn(sdp))
 		return -EIO;
 
 	error = gfs2_find_jhead(sdp->sd_jdesc, &head, false);
@@ -153,7 +153,7 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp)
 	gfs2_log_pointers_init(sdp, head.lh_blkno);
 
 	error = gfs2_quota_init(sdp);
-	if (!error && gfs2_withdrawn(sdp))
+	if (!error && gfs2_withdrawing_or_withdrawn(sdp))
 		error = -EIO;
 	if (!error)
 		set_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
@@ -499,7 +499,7 @@ static void gfs2_dirty_inode(struct inode *inode, int flags)
 		return;
 	}
 
-	if (unlikely(gfs2_withdrawn(sdp)))
+	if (gfs2_withdrawing_or_withdrawn(sdp))
 		return;
 	if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
 		ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
@@ -605,7 +605,7 @@ restart:
 	if (!sb_rdonly(sb))
 		gfs2_make_fs_ro(sdp);
 	else {
-		if (gfs2_withdrawn(sdp))
+		if (gfs2_withdrawing_or_withdrawn(sdp))
 			gfs2_destroy_threads(sdp);
 
 		gfs2_quota_cleanup(sdp);
@@ -673,28 +673,6 @@ static int gfs2_sync_fs(struct super_block *sb, int wait)
 	return sdp->sd_log_error;
 }
 
-static int gfs2_freeze_locally(struct gfs2_sbd *sdp)
-{
-	struct super_block *sb = sdp->sd_vfs;
-	int error;
-
-	error = freeze_super(sb, FREEZE_HOLDER_USERSPACE);
-	if (error)
-		return error;
-
-	if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
-		gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_FREEZE |
-			       GFS2_LFC_FREEZE_GO_SYNC);
-		if (gfs2_withdrawn(sdp)) {
-			error = thaw_super(sb, FREEZE_HOLDER_USERSPACE);
-			if (error)
-				return error;
-			return -EIO;
-		}
-	}
-	return 0;
-}
-
 static int gfs2_do_thaw(struct gfs2_sbd *sdp)
 {
 	struct super_block *sb = sdp->sd_vfs;
@@ -724,7 +702,7 @@ void gfs2_freeze_func(struct work_struct *work)
 	if (test_bit(SDF_FROZEN, &sdp->sd_flags))
 		goto freeze_failed;
 
-	error = gfs2_freeze_locally(sdp);
+	error = freeze_super(sb, FREEZE_HOLDER_USERSPACE);
 	if (error)
 		goto freeze_failed;
 
@@ -759,12 +737,13 @@ static int gfs2_freeze_super(struct super_block *sb, enum freeze_holder who)
 
 	if (!mutex_trylock(&sdp->sd_freeze_mutex))
 		return -EBUSY;
-	error = -EBUSY;
-	if (test_bit(SDF_FROZEN, &sdp->sd_flags))
-		goto out;
+	if (test_bit(SDF_FROZEN, &sdp->sd_flags)) {
+		mutex_unlock(&sdp->sd_freeze_mutex);
+		return -EBUSY;
+	}
 
 	for (;;) {
-		error = gfs2_freeze_locally(sdp);
+		error = freeze_super(sb, FREEZE_HOLDER_USERSPACE);
 		if (error) {
 			fs_info(sdp, "GFS2: couldn't freeze filesystem: %d\n",
 				error);
@@ -772,8 +751,11 @@ static int gfs2_freeze_super(struct super_block *sb, enum freeze_holder who)
 		}
 
 		error = gfs2_lock_fs_check_clean(sdp);
-		if (!error)
-			break;  /* success */
+		if (!error) {
+			set_bit(SDF_FREEZE_INITIATOR, &sdp->sd_flags);
+			set_bit(SDF_FROZEN, &sdp->sd_flags);
+			break;
+		}
 
 		error = gfs2_do_thaw(sdp);
 		if (error)
@@ -793,14 +775,23 @@ static int gfs2_freeze_super(struct super_block *sb, enum freeze_holder who)
 	}
 
 out:
-	if (!error) {
-		set_bit(SDF_FREEZE_INITIATOR, &sdp->sd_flags);
-		set_bit(SDF_FROZEN, &sdp->sd_flags);
-	}
 	mutex_unlock(&sdp->sd_freeze_mutex);
 	return error;
 }
 
+static int gfs2_freeze_fs(struct super_block *sb)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+
+	if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
+		gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_FREEZE |
+			       GFS2_LFC_FREEZE_GO_SYNC);
+		if (gfs2_withdrawing_or_withdrawn(sdp))
+			return -EIO;
+	}
+	return 0;
+}
+
 /**
  * gfs2_thaw_super - reallow writes to the filesystem
  * @sb: the VFS structure for the filesystem
@@ -814,10 +805,12 @@ static int gfs2_thaw_super(struct super_block *sb, enum freeze_holder who)
 
 	if (!mutex_trylock(&sdp->sd_freeze_mutex))
 		return -EBUSY;
-	error = -EINVAL;
-	if (!test_bit(SDF_FREEZE_INITIATOR, &sdp->sd_flags))
-		goto out;
+	if (!test_bit(SDF_FREEZE_INITIATOR, &sdp->sd_flags)) {
+		mutex_unlock(&sdp->sd_freeze_mutex);
+		return -EINVAL;
+	}
 
+	atomic_inc(&sb->s_active);
 	gfs2_freeze_unlock(&sdp->sd_freeze_gh);
 
 	error = gfs2_do_thaw(sdp);
@@ -826,8 +819,8 @@ static int gfs2_thaw_super(struct super_block *sb, enum freeze_holder who)
 		clear_bit(SDF_FREEZE_INITIATOR, &sdp->sd_flags);
 		clear_bit(SDF_FROZEN, &sdp->sd_flags);
 	}
-out:
 	mutex_unlock(&sdp->sd_freeze_mutex);
+	deactivate_super(sb);
 	return error;
 }
 
@@ -1065,16 +1058,6 @@ static int gfs2_drop_inode(struct inode *inode)
 	return generic_drop_inode(inode);
 }
 
-static int is_ancestor(const struct dentry *d1, const struct dentry *d2)
-{
-	do {
-		if (d1 == d2)
-			return 1;
-		d1 = d1->d_parent;
-	} while (!IS_ROOT(d1));
-	return 0;
-}
-
 /**
  * gfs2_show_options - Show mount options for /proc/mounts
  * @s: seq_file structure
@@ -1096,7 +1079,7 @@ static int gfs2_show_options(struct seq_file *s, struct dentry *root)
 	statfs_slow = sdp->sd_tune.gt_statfs_slow;
 	spin_unlock(&sdp->sd_tune.gt_spin);
 
-	if (is_ancestor(root, sdp->sd_master_dir))
+	if (is_subdir(root, sdp->sd_master_dir))
 		seq_puts(s, ",meta");
 	if (args->ar_lockproto[0])
 		seq_show_option(s, "lockproto", args->ar_lockproto);
@@ -1607,6 +1590,7 @@ const struct super_operations gfs2_super_ops = {
 	.put_super		= gfs2_put_super,
 	.sync_fs		= gfs2_sync_fs,
 	.freeze_super		= gfs2_freeze_super,
+	.freeze_fs		= gfs2_freeze_fs,
 	.thaw_super		= gfs2_thaw_super,
 	.statfs			= gfs2_statfs,
 	.drop_inode		= gfs2_drop_inode,
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index 60a0206890c5..250f340cb44d 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -193,7 +193,7 @@ static ssize_t freeze_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
 
 static ssize_t withdraw_show(struct gfs2_sbd *sdp, char *buf)
 {
-	unsigned int b = gfs2_withdrawn(sdp);
+	unsigned int b = gfs2_withdrawing_or_withdrawn(sdp);
 	return snprintf(buf, PAGE_SIZE, "%u\n", b);
 }
 
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index 7e835be7032d..192213c7359a 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -268,7 +268,7 @@ void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh)
 		       (unsigned long long)bd->bd_bh->b_blocknr);
 		BUG();
 	}
-	if (unlikely(gfs2_withdrawn(sdp))) {
+	if (gfs2_withdrawing_or_withdrawn(sdp)) {
 		fs_info(sdp, "GFS2:adding buf while withdrawn! 0x%llx\n",
 			(unsigned long long)bd->bd_bh->b_blocknr);
 		goto out_unlock;
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index da29fafb6272..f52141ce9485 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -372,7 +372,7 @@ void gfs2_assert_withdraw_i(struct gfs2_sbd *sdp, char *assertion,
 			    const char *function, char *file, unsigned int line,
 			    bool delayed)
 {
-	if (gfs2_withdrawn(sdp))
+	if (gfs2_withdrawing_or_withdrawn(sdp))
 		return;
 
 	fs_err(sdp,
@@ -548,7 +548,7 @@ void gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh,
 			const char *function, char *file, unsigned int line,
 			bool withdraw)
 {
-	if (gfs2_withdrawn(sdp))
+	if (gfs2_withdrawing_or_withdrawn(sdp))
 		return;
 
 	fs_err(sdp, "fatal: I/O error\n"
diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h
index 11c9d59b6889..ba071998461f 100644
--- a/fs/gfs2/util.h
+++ b/fs/gfs2/util.h
@@ -198,13 +198,14 @@ static inline void gfs2_withdraw_delayed(struct gfs2_sbd *sdp)
 }
 
 /**
- * gfs2_withdrawn - test whether the file system is withdrawing or withdrawn
+ * gfs2_withdrawing_or_withdrawn - test whether the file system is withdrawing
+ *                                 or withdrawn
  * @sdp: the superblock
  */
-static inline bool gfs2_withdrawn(struct gfs2_sbd *sdp)
+static inline bool gfs2_withdrawing_or_withdrawn(struct gfs2_sbd *sdp)
 {
-	return test_bit(SDF_WITHDRAWN, &sdp->sd_flags) ||
-		test_bit(SDF_WITHDRAWING, &sdp->sd_flags);
+	return unlikely(test_bit(SDF_WITHDRAWN, &sdp->sd_flags) ||
+			test_bit(SDF_WITHDRAWING, &sdp->sd_flags));
 }
 
 /**
@@ -213,13 +214,13 @@ static inline bool gfs2_withdrawn(struct gfs2_sbd *sdp)
  */
 static inline bool gfs2_withdrawing(struct gfs2_sbd *sdp)
 {
-	return test_bit(SDF_WITHDRAWING, &sdp->sd_flags) &&
-	       !test_bit(SDF_WITHDRAWN, &sdp->sd_flags);
+	return unlikely(test_bit(SDF_WITHDRAWING, &sdp->sd_flags) &&
+			!test_bit(SDF_WITHDRAWN, &sdp->sd_flags));
 }
 
 static inline bool gfs2_withdraw_in_prog(struct gfs2_sbd *sdp)
 {
-	return test_bit(SDF_WITHDRAW_IN_PROG, &sdp->sd_flags);
+	return unlikely(test_bit(SDF_WITHDRAW_IN_PROG, &sdp->sd_flags));
 }
 
 #define gfs2_tune_get(sdp, field) \
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index a7bc4690a780..8c34798a0715 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -29,11 +29,6 @@ static const struct inode_operations hfs_file_inode_operations;
 
 #define HFS_VALID_MODE_BITS  (S_IFREG | S_IFDIR | S_IRWXUGO)
 
-static int hfs_writepage(struct page *page, struct writeback_control *wbc)
-{
-	return block_write_full_page(page, hfs_get_block, wbc);
-}
-
 static int hfs_read_folio(struct file *file, struct folio *folio)
 {
 	return block_read_full_folio(folio, hfs_get_block);
@@ -162,9 +157,10 @@ const struct address_space_operations hfs_btree_aops = {
 	.dirty_folio	= block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
 	.read_folio	= hfs_read_folio,
-	.writepage	= hfs_writepage,
+	.writepages	= hfs_writepages,
 	.write_begin	= hfs_write_begin,
 	.write_end	= generic_write_end,
+	.migrate_folio	= buffer_migrate_folio,
 	.bmap		= hfs_bmap,
 	.release_folio	= hfs_release_folio,
 };
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 702a0663b1d8..3d326926c195 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -28,11 +28,6 @@ static int hfsplus_read_folio(struct file *file, struct folio *folio)
 	return block_read_full_folio(folio, hfsplus_get_block);
 }
 
-static int hfsplus_writepage(struct page *page, struct writeback_control *wbc)
-{
-	return block_write_full_page(page, hfsplus_get_block, wbc);
-}
-
 static void hfsplus_write_failed(struct address_space *mapping, loff_t to)
 {
 	struct inode *inode = mapping->host;
@@ -159,9 +154,10 @@ const struct address_space_operations hfsplus_btree_aops = {
 	.dirty_folio	= block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
 	.read_folio	= hfsplus_read_folio,
-	.writepage	= hfsplus_writepage,
+	.writepages	= hfsplus_writepages,
 	.write_begin	= hfsplus_write_begin,
 	.write_end	= generic_write_end,
+	.migrate_folio	= buffer_migrate_folio,
 	.bmap		= hfsplus_bmap,
 	.release_folio	= hfsplus_release_folio,
 };
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index 0b791adf02e5..b0cb70400996 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -30,8 +30,7 @@ struct hfsplus_wd {
  * @sector: block to read or write, for blocks of HFSPLUS_SECTOR_SIZE bytes
  * @buf: buffer for I/O
  * @data: output pointer for location of requested data
- * @op: direction of I/O
- * @op_flags: request op flags
+ * @opf: request op flags
  *
  * The unit of I/O is hfsplus_min_io_size(sb), which may be bigger than
  * HFSPLUS_SECTOR_SIZE, and @buf must be sized accordingly. On reads
@@ -43,6 +42,8 @@ struct hfsplus_wd {
  * that starts at the rounded-down address. As long as the data was
  * read using hfsplus_submit_bio() and the same buffer is used things
  * will work correctly.
+ *
+ * Returns: %0 on success else -errno code
  */
 int hfsplus_submit_bio(struct super_block *sb, sector_t sector,
 		       void *buf, void **data, blk_opf_t opf)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index f757d4f7ad98..ea5b8e57d904 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -686,7 +686,7 @@ static void hugetlbfs_evict_inode(struct inode *inode)
 	 * at inode creation time.  If this is a device special inode,
 	 * i_mapping may not point to the original address space.
 	 */
-	resv_map = (struct resv_map *)(&inode->i_data)->private_data;
+	resv_map = (struct resv_map *)(&inode->i_data)->i_private_data;
 	/* Only regular and link inodes have associated reserve maps */
 	if (resv_map)
 		resv_map_release(&resv_map->refs);
@@ -1000,7 +1000,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 				&hugetlbfs_i_mmap_rwsem_key);
 		inode->i_mapping->a_ops = &hugetlbfs_aops;
 		simple_inode_init_ts(inode);
-		inode->i_mapping->private_data = resv_map;
+		inode->i_mapping->i_private_data = resv_map;
 		info->seals = F_SEAL_SEAL;
 		switch (mode & S_IFMT) {
 		default:
@@ -1129,8 +1129,8 @@ static int hugetlbfs_migrate_folio(struct address_space *mapping,
 #define hugetlbfs_migrate_folio NULL
 #endif
 
-static int hugetlbfs_error_remove_page(struct address_space *mapping,
-				struct page *page)
+static int hugetlbfs_error_remove_folio(struct address_space *mapping,
+				struct folio *folio)
 {
 	return 0;
 }
@@ -1277,7 +1277,7 @@ static const struct address_space_operations hugetlbfs_aops = {
 	.write_end	= hugetlbfs_write_end,
 	.dirty_folio	= noop_dirty_folio,
 	.migrate_folio  = hugetlbfs_migrate_folio,
-	.error_remove_page	= hugetlbfs_error_remove_page,
+	.error_remove_folio	= hugetlbfs_error_remove_folio,
 };
 
 
diff --git a/fs/inode.c b/fs/inode.c
index edcd8a61975f..d23362a671dd 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -129,7 +129,6 @@ static struct ctl_table inodes_sysctls[] = {
 		.mode		= 0444,
 		.proc_handler	= proc_nr_inodes,
 	},
-	{ }
 };
 
 static int __init init_fs_inode_sysctls(void)
@@ -209,12 +208,14 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	atomic_set(&mapping->nr_thps, 0);
 #endif
 	mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
-	mapping->private_data = NULL;
+	mapping->i_private_data = NULL;
 	mapping->writeback_index = 0;
 	init_rwsem(&mapping->invalidate_lock);
 	lockdep_set_class_and_name(&mapping->invalidate_lock,
 				   &sb->s_type->invalidate_lock_key,
 				   "mapping.invalidate_lock");
+	if (sb->s_iflags & SB_I_STABLE_WRITES)
+		mapping_set_stable_writes(mapping);
 	inode->i_private = NULL;
 	inode->i_mapping = mapping;
 	INIT_HLIST_HEAD(&inode->i_dentry);	/* buggered by rcu freeing */
@@ -396,8 +397,8 @@ static void __address_space_init_once(struct address_space *mapping)
 {
 	xa_init_flags(&mapping->i_pages, XA_FLAGS_LOCK_IRQ | XA_FLAGS_ACCOUNT);
 	init_rwsem(&mapping->i_mmap_rwsem);
-	INIT_LIST_HEAD(&mapping->private_list);
-	spin_lock_init(&mapping->private_lock);
+	INIT_LIST_HEAD(&mapping->i_private_list);
+	spin_lock_init(&mapping->i_private_lock);
 	mapping->i_mmap = RB_ROOT_CACHED;
 }
 
@@ -462,7 +463,7 @@ static void __inode_add_lru(struct inode *inode, bool rotate)
 	if (!mapping_shrinkable(&inode->i_data))
 		return;
 
-	if (list_lru_add(&inode->i_sb->s_inode_lru, &inode->i_lru))
+	if (list_lru_add_obj(&inode->i_sb->s_inode_lru, &inode->i_lru))
 		this_cpu_inc(nr_unused);
 	else if (rotate)
 		inode->i_state |= I_REFERENCED;
@@ -480,7 +481,7 @@ void inode_add_lru(struct inode *inode)
 
 static void inode_lru_list_del(struct inode *inode)
 {
-	if (list_lru_del(&inode->i_sb->s_inode_lru, &inode->i_lru))
+	if (list_lru_del_obj(&inode->i_sb->s_inode_lru, &inode->i_lru))
 		this_cpu_dec(nr_unused);
 }
 
@@ -618,7 +619,7 @@ void clear_inode(struct inode *inode)
 	 * nor even WARN_ON(!mapping_empty).
 	 */
 	xa_unlock_irq(&inode->i_data.i_pages);
-	BUG_ON(!list_empty(&inode->i_data.private_list));
+	BUG_ON(!list_empty(&inode->i_data.i_private_list));
 	BUG_ON(!(inode->i_state & I_FREEING));
 	BUG_ON(inode->i_state & I_CLEAR);
 	BUG_ON(!list_empty(&inode->i_wb_list));
@@ -1834,37 +1835,37 @@ EXPORT_SYMBOL(bmap);
  * earlier than or equal to either the ctime or mtime,
  * or if at least a day has passed since the last atime update.
  */
-static int relatime_need_update(struct vfsmount *mnt, struct inode *inode,
+static bool relatime_need_update(struct vfsmount *mnt, struct inode *inode,
 			     struct timespec64 now)
 {
 	struct timespec64 atime, mtime, ctime;
 
 	if (!(mnt->mnt_flags & MNT_RELATIME))
-		return 1;
+		return true;
 	/*
 	 * Is mtime younger than or equal to atime? If yes, update atime:
 	 */
 	atime = inode_get_atime(inode);
 	mtime = inode_get_mtime(inode);
 	if (timespec64_compare(&mtime, &atime) >= 0)
-		return 1;
+		return true;
 	/*
 	 * Is ctime younger than or equal to atime? If yes, update atime:
 	 */
 	ctime = inode_get_ctime(inode);
 	if (timespec64_compare(&ctime, &atime) >= 0)
-		return 1;
+		return true;
 
 	/*
 	 * Is the previous atime value older than a day? If yes,
 	 * update atime:
 	 */
 	if ((long)(now.tv_sec - atime.tv_sec) >= 24*60*60)
-		return 1;
+		return true;
 	/*
 	 * Good, we can skip the atime update:
 	 */
-	return 0;
+	return false;
 }
 
 /**
@@ -2402,7 +2403,7 @@ EXPORT_SYMBOL(inode_init_owner);
  * the vfsmount must be passed through @idmap. This function will then take
  * care to map the inode according to @idmap before checking permissions.
  * On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
  */
 bool inode_owner_or_capable(struct mnt_idmap *idmap,
 			    const struct inode *inode)
diff --git a/fs/internal.h b/fs/internal.h
index 58e43341aebf..bf2ee2e0d45d 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -83,6 +83,8 @@ int path_mount(const char *dev_name, struct path *path,
 		const char *type_page, unsigned long flags, void *data_page);
 int path_umount(struct path *path, int flags);
 
+int show_path(struct seq_file *m, struct dentry *root);
+
 /*
  * fs_struct.c
  */
@@ -94,7 +96,6 @@ extern void chroot_fs_refs(const struct path *, const struct path *);
 struct file *alloc_empty_file(int flags, const struct cred *cred);
 struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred);
 struct file *alloc_empty_backing_file(int flags, const struct cred *cred);
-void release_empty_file(struct file *f);
 
 static inline void file_put_write_access(struct file *file)
 {
@@ -180,7 +181,7 @@ extern struct file *do_file_open_root(const struct path *,
 		const char *, const struct open_flags *);
 extern struct open_how build_open_how(int flags, umode_t mode);
 extern int build_open_flags(const struct open_how *how, struct open_flags *op);
-extern struct file *__close_fd_get_file(unsigned int fd);
+struct file *file_close_fd_locked(struct files_struct *files, unsigned fd);
 
 long do_sys_ftruncate(unsigned int fd, loff_t length, int small);
 int chmod_common(const struct path *path, umode_t mode);
@@ -243,10 +244,10 @@ int do_statx(int dfd, struct filename *filename, unsigned int flags,
 /*
  * fs/splice.c:
  */
-long splice_file_to_pipe(struct file *in,
-			 struct pipe_inode_info *opipe,
-			 loff_t *offset,
-			 size_t len, unsigned int flags);
+ssize_t splice_file_to_pipe(struct file *in,
+			    struct pipe_inode_info *opipe,
+			    loff_t *offset,
+			    size_t len, unsigned int flags);
 
 /*
  * fs/xattr.c:
diff --git a/fs/ioctl.c b/fs/ioctl.c
index f5fd99d6b0d4..76cf22ac97d7 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -920,8 +920,7 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd,
 	if (!f.file)
 		return -EBADF;
 
-	/* RED-PEN how should LSM module know it's handling 32bit? */
-	error = security_file_ioctl(f.file, cmd, arg);
+	error = security_file_ioctl_compat(f.file, cmd, arg);
 	if (error)
 		goto out;
 
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index f72df2babe56..093c4515b22a 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -305,28 +305,18 @@ static int iomap_read_inline_data(const struct iomap_iter *iter,
 {
 	const struct iomap *iomap = iomap_iter_srcmap(iter);
 	size_t size = i_size_read(iter->inode) - iomap->offset;
-	size_t poff = offset_in_page(iomap->offset);
 	size_t offset = offset_in_folio(folio, iomap->offset);
-	void *addr;
 
 	if (folio_test_uptodate(folio))
 		return 0;
 
-	if (WARN_ON_ONCE(size > PAGE_SIZE - poff))
-		return -EIO;
-	if (WARN_ON_ONCE(size > PAGE_SIZE -
-			 offset_in_page(iomap->inline_data)))
-		return -EIO;
 	if (WARN_ON_ONCE(size > iomap->length))
 		return -EIO;
 	if (offset > 0)
 		ifs_alloc(iter->inode, folio, iter->flags);
 
-	addr = kmap_local_folio(folio, offset);
-	memcpy(addr, iomap->inline_data, size);
-	memset(addr + size, 0, PAGE_SIZE - poff - size);
-	kunmap_local(addr);
-	iomap_set_range_uptodate(folio, offset, PAGE_SIZE - poff);
+	folio_fill_tail(folio, offset, iomap->inline_data, size);
+	iomap_set_range_uptodate(folio, offset, folio_size(folio) - offset);
 	return 0;
 }
 
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 118699fff2f9..1c97e64c4784 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -556,7 +556,6 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
 	struct transaction_chp_stats_s *stats;
 	transaction_t *transaction;
 	journal_t *journal;
-	struct buffer_head *bh = jh2bh(jh);
 
 	JBUFFER_TRACE(jh, "entry");
 
@@ -569,16 +568,6 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
 
 	JBUFFER_TRACE(jh, "removing from transaction");
 
-	/*
-	 * If we have failed to write the buffer out to disk, the filesystem
-	 * may become inconsistent. We cannot abort the journal here since
-	 * we hold j_list_lock and we have to be careful about races with
-	 * jbd2_journal_destroy(). So mark the writeback IO error in the
-	 * journal here and we abort the journal later from a better context.
-	 */
-	if (buffer_write_io_error(bh))
-		set_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags);
-
 	__buffer_unlink(jh);
 	jh->b_cp_transaction = NULL;
 	percpu_counter_dec(&journal->j_checkpoint_jh_count);
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 8d6f934c3d95..5e122586e06e 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -119,7 +119,7 @@ static int journal_submit_commit_record(journal_t *journal,
 	struct commit_header *tmp;
 	struct buffer_head *bh;
 	struct timespec64 now;
-	blk_opf_t write_flags = REQ_OP_WRITE | REQ_SYNC;
+	blk_opf_t write_flags = REQ_OP_WRITE | JBD2_JOURNAL_REQ_FLAGS;
 
 	*cbh = NULL;
 
@@ -270,6 +270,7 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 			if (!ret)
 				ret = err;
 		}
+		cond_resched();
 		spin_lock(&journal->j_list_lock);
 		jinode->i_flags &= ~JI_COMMIT_RUNNING;
 		smp_mb();
@@ -395,8 +396,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		 */
 		jbd2_journal_update_sb_log_tail(journal,
 						journal->j_tail_sequence,
-						journal->j_tail,
-						REQ_SYNC);
+						journal->j_tail, 0);
 		mutex_unlock(&journal->j_checkpoint_mutex);
 	} else {
 		jbd2_debug(3, "superblock not updated\n");
@@ -715,6 +715,7 @@ start_journal_io:
 
 			for (i = 0; i < bufs; i++) {
 				struct buffer_head *bh = wbuf[i];
+
 				/*
 				 * Compute checksum.
 				 */
@@ -727,7 +728,8 @@ start_journal_io:
 				clear_buffer_dirty(bh);
 				set_buffer_uptodate(bh);
 				bh->b_end_io = journal_end_buffer_io_sync;
-				submit_bh(REQ_OP_WRITE | REQ_SYNC, bh);
+				submit_bh(REQ_OP_WRITE | JBD2_JOURNAL_REQ_FLAGS,
+					  bh);
 			}
 			cond_resched();
 
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index ed53188472f9..b6c114c11b97 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1100,8 +1100,7 @@ int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
 	 * space and if we lose sb update during power failure we'd replay
 	 * old transaction with possibly newly overwritten data.
 	 */
-	ret = jbd2_journal_update_sb_log_tail(journal, tid, block,
-					      REQ_SYNC | REQ_FUA);
+	ret = jbd2_journal_update_sb_log_tail(journal, tid, block, REQ_FUA);
 	if (ret)
 		goto out;
 
@@ -1535,6 +1534,7 @@ static journal_t *journal_init_common(struct block_device *bdev,
 	journal->j_fs_dev = fs_dev;
 	journal->j_blk_offset = start;
 	journal->j_total_len = len;
+	jbd2_init_fs_dev_write_error(journal);
 
 	err = journal_load_superblock(journal);
 	if (err)
@@ -1775,8 +1775,7 @@ static int journal_reset(journal_t *journal)
 		 */
 		jbd2_journal_update_sb_log_tail(journal,
 						journal->j_tail_sequence,
-						journal->j_tail,
-						REQ_SYNC | REQ_FUA);
+						journal->j_tail, REQ_FUA);
 		mutex_unlock(&journal->j_checkpoint_mutex);
 	}
 	return jbd2_journal_start_thread(journal);
@@ -1798,9 +1797,16 @@ static int jbd2_write_superblock(journal_t *journal, blk_opf_t write_flags)
 		return -EIO;
 	}
 
-	trace_jbd2_write_superblock(journal, write_flags);
+	/*
+	 * Always set high priority flags to exempt from block layer's
+	 * QOS policies, e.g. writeback throttle.
+	 */
+	write_flags |= JBD2_JOURNAL_REQ_FLAGS;
 	if (!(journal->j_flags & JBD2_BARRIER))
 		write_flags &= ~(REQ_FUA | REQ_PREFLUSH);
+
+	trace_jbd2_write_superblock(journal, write_flags);
+
 	if (buffer_write_io_error(bh)) {
 		/*
 		 * Oh, dear.  A previous attempt to write the journal
@@ -1856,7 +1862,7 @@ int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid,
 
 	if (is_journal_aborted(journal))
 		return -EIO;
-	if (test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags)) {
+	if (jbd2_check_fs_dev_write_error(journal)) {
 		jbd2_journal_abort(journal, -EIO);
 		return -EIO;
 	}
@@ -2050,7 +2056,7 @@ void jbd2_journal_update_sb_errno(journal_t *journal)
 	jbd2_debug(1, "JBD2: updating superblock error (errno %d)\n", errcode);
 	sb->s_errno    = cpu_to_be32(errcode);
 
-	jbd2_write_superblock(journal, REQ_SYNC | REQ_FUA);
+	jbd2_write_superblock(journal, REQ_FUA);
 }
 EXPORT_SYMBOL(jbd2_journal_update_sb_errno);
 
@@ -2154,12 +2160,12 @@ int jbd2_journal_destroy(journal_t *journal)
 
 	/*
 	 * OK, all checkpoint transactions have been checked, now check the
-	 * write out io error flag and abort the journal if some buffer failed
-	 * to write back to the original location, otherwise the filesystem
-	 * may become inconsistent.
+	 * writeback errseq of fs dev and abort the journal if some buffer
+	 * failed to write back to the original location, otherwise the
+	 * filesystem may become inconsistent.
 	 */
 	if (!is_journal_aborted(journal) &&
-	    test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags))
+	    jbd2_check_fs_dev_write_error(journal))
 		jbd2_journal_abort(journal, -EIO);
 
 	if (journal->j_sb_buffer) {
@@ -2171,8 +2177,7 @@ int jbd2_journal_destroy(journal_t *journal)
 				++journal->j_transaction_sequence;
 			write_unlock(&journal->j_state_lock);
 
-			jbd2_mark_journal_empty(journal,
-					REQ_SYNC | REQ_PREFLUSH | REQ_FUA);
+			jbd2_mark_journal_empty(journal, REQ_PREFLUSH | REQ_FUA);
 			mutex_unlock(&journal->j_checkpoint_mutex);
 		} else
 			err = -EIO;
@@ -2473,7 +2478,7 @@ int jbd2_journal_flush(journal_t *journal, unsigned int flags)
 	 * the magic code for a fully-recovered superblock.  Any future
 	 * commits of data to the journal will restore the current
 	 * s_start value. */
-	jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA);
+	jbd2_mark_journal_empty(journal, REQ_FUA);
 
 	if (flags)
 		err = __jbd2_journal_erase(journal, flags);
@@ -2519,7 +2524,7 @@ int jbd2_journal_wipe(journal_t *journal, int write)
 	if (write) {
 		/* Lock to make assertions happy... */
 		mutex_lock_io(&journal->j_checkpoint_mutex);
-		jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA);
+		jbd2_mark_journal_empty(journal, REQ_FUA);
 		mutex_unlock(&journal->j_checkpoint_mutex);
 	}
 
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 01f744cb97a4..1f7664984d6e 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -289,8 +289,6 @@ int jbd2_journal_recover(journal_t *journal)
 	journal_superblock_t *	sb;
 
 	struct recovery_info	info;
-	errseq_t		wb_err;
-	struct address_space	*mapping;
 
 	memset(&info, 0, sizeof(info));
 	sb = journal->j_superblock;
@@ -308,9 +306,6 @@ int jbd2_journal_recover(journal_t *journal)
 		return 0;
 	}
 
-	wb_err = 0;
-	mapping = journal->j_fs_dev->bd_inode->i_mapping;
-	errseq_check_and_advance(&mapping->wb_err, &wb_err);
 	err = do_one_pass(journal, &info, PASS_SCAN);
 	if (!err)
 		err = do_one_pass(journal, &info, PASS_REVOKE);
@@ -334,7 +329,7 @@ int jbd2_journal_recover(journal_t *journal)
 	err2 = sync_blockdev(journal->j_fs_dev);
 	if (!err)
 		err = err2;
-	err2 = errseq_check_and_advance(&mapping->wb_err, &wb_err);
+	err2 = jbd2_check_fs_dev_write_error(journal);
 	if (!err)
 		err = err2;
 	/* Make sure all replayed data is on permanent storage */
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 5f08b5fd105a..cb0b8d6fc0c6 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1231,11 +1231,25 @@ out:
 int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh)
 {
 	struct journal_head *jh;
+	journal_t *journal;
 	int rc;
 
 	if (is_handle_aborted(handle))
 		return -EROFS;
 
+	journal = handle->h_transaction->t_journal;
+	if (jbd2_check_fs_dev_write_error(journal)) {
+		/*
+		 * If the fs dev has writeback errors, it may have failed
+		 * to async write out metadata buffers in the background.
+		 * In this case, we could read old data from disk and write
+		 * it out again, which may lead to on-disk filesystem
+		 * inconsistency. Aborting journal can avoid it happen.
+		 */
+		jbd2_journal_abort(journal, -EIO);
+		return -EIO;
+	}
+
 	if (jbd2_write_access_granted(handle, bh, false))
 		return 0;
 
diff --git a/fs/jffs2/debug.c b/fs/jffs2/debug.c
index 9d26b1b9fc01..0925caab23c4 100644
--- a/fs/jffs2/debug.c
+++ b/fs/jffs2/debug.c
@@ -157,7 +157,7 @@ __jffs2_dbg_prewrite_paranoia_check(struct jffs2_sb_info *c,
 	kfree(buf);
 }
 
-void __jffs2_dbg_superblock_counts(struct jffs2_sb_info *c)
+static void __jffs2_dbg_superblock_counts(struct jffs2_sb_info *c)
 {
 	struct jffs2_eraseblock *jeb;
 	uint32_t free = 0, dirty = 0, used = 0, wasted = 0,
diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c
index 11c77757ead9..8eec84c651bf 100644
--- a/fs/jfs/jfs_dmap.c
+++ b/fs/jfs/jfs_dmap.c
@@ -63,10 +63,10 @@
  */
 static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno,
 			int nblocks);
-static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval);
-static int dbBackSplit(dmtree_t * tp, int leafno);
-static int dbJoin(dmtree_t * tp, int leafno, int newval);
-static void dbAdjTree(dmtree_t * tp, int leafno, int newval);
+static void dbSplit(dmtree_t *tp, int leafno, int splitsz, int newval, bool is_ctl);
+static int dbBackSplit(dmtree_t *tp, int leafno, bool is_ctl);
+static int dbJoin(dmtree_t *tp, int leafno, int newval, bool is_ctl);
+static void dbAdjTree(dmtree_t *tp, int leafno, int newval, bool is_ctl);
 static int dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc,
 		    int level);
 static int dbAllocAny(struct bmap * bmp, s64 nblocks, int l2nb, s64 * results);
@@ -2103,7 +2103,7 @@ static int dbFreeDmap(struct bmap * bmp, struct dmap * dp, s64 blkno,
 		 * system.
 		 */
 		if (dp->tree.stree[word] == NOFREE)
-			dbBackSplit((dmtree_t *) & dp->tree, word);
+			dbBackSplit((dmtree_t *)&dp->tree, word, false);
 
 		dbAllocBits(bmp, dp, blkno, nblocks);
 	}
@@ -2189,7 +2189,7 @@ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno,
 			 * the binary system of the leaves if need be.
 			 */
 			dbSplit(tp, word, BUDMIN,
-				dbMaxBud((u8 *) & dp->wmap[word]));
+				dbMaxBud((u8 *)&dp->wmap[word]), false);
 
 			word += 1;
 		} else {
@@ -2229,7 +2229,7 @@ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno,
 				 * system of the leaves to reflect the current
 				 * allocation (size).
 				 */
-				dbSplit(tp, word, size, NOFREE);
+				dbSplit(tp, word, size, NOFREE, false);
 
 				/* get the number of dmap words handled */
 				nw = BUDSIZE(size, BUDMIN);
@@ -2336,7 +2336,7 @@ static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno,
 			/* update the leaf for this dmap word.
 			 */
 			rc = dbJoin(tp, word,
-				    dbMaxBud((u8 *) & dp->wmap[word]));
+				    dbMaxBud((u8 *)&dp->wmap[word]), false);
 			if (rc)
 				return rc;
 
@@ -2369,7 +2369,7 @@ static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno,
 
 				/* update the leaf.
 				 */
-				rc = dbJoin(tp, word, size);
+				rc = dbJoin(tp, word, size, false);
 				if (rc)
 					return rc;
 
@@ -2521,16 +2521,16 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level)
 		 * that it is at the front of a binary buddy system.
 		 */
 		if (oldval == NOFREE) {
-			rc = dbBackSplit((dmtree_t *) dcp, leafno);
+			rc = dbBackSplit((dmtree_t *)dcp, leafno, true);
 			if (rc) {
 				release_metapage(mp);
 				return rc;
 			}
 			oldval = dcp->stree[ti];
 		}
-		dbSplit((dmtree_t *) dcp, leafno, dcp->budmin, newval);
+		dbSplit((dmtree_t *) dcp, leafno, dcp->budmin, newval, true);
 	} else {
-		rc = dbJoin((dmtree_t *) dcp, leafno, newval);
+		rc = dbJoin((dmtree_t *) dcp, leafno, newval, true);
 		if (rc) {
 			release_metapage(mp);
 			return rc;
@@ -2561,7 +2561,7 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level)
 				 */
 				if (alloc) {
 					dbJoin((dmtree_t *) dcp, leafno,
-					       oldval);
+					       oldval, true);
 				} else {
 					/* the dbJoin() above might have
 					 * caused a larger binary buddy system
@@ -2571,9 +2571,9 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level)
 					 */
 					if (dcp->stree[ti] == NOFREE)
 						dbBackSplit((dmtree_t *)
-							    dcp, leafno);
+							    dcp, leafno, true);
 					dbSplit((dmtree_t *) dcp, leafno,
-						dcp->budmin, oldval);
+						dcp->budmin, oldval, true);
 				}
 
 				/* release the buffer and return the error.
@@ -2621,7 +2621,7 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level)
  *
  * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit;
  */
-static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval)
+static void dbSplit(dmtree_t *tp, int leafno, int splitsz, int newval, bool is_ctl)
 {
 	int budsz;
 	int cursz;
@@ -2643,7 +2643,7 @@ static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval)
 		while (cursz >= splitsz) {
 			/* update the buddy's leaf with its new value.
 			 */
-			dbAdjTree(tp, leafno ^ budsz, cursz);
+			dbAdjTree(tp, leafno ^ budsz, cursz, is_ctl);
 
 			/* on to the next size and buddy.
 			 */
@@ -2655,7 +2655,7 @@ static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval)
 	/* adjust the dmap tree to reflect the specified leaf's new
 	 * value.
 	 */
-	dbAdjTree(tp, leafno, newval);
+	dbAdjTree(tp, leafno, newval, is_ctl);
 }
 
 
@@ -2686,7 +2686,7 @@ static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval)
  *
  * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit;
  */
-static int dbBackSplit(dmtree_t * tp, int leafno)
+static int dbBackSplit(dmtree_t *tp, int leafno, bool is_ctl)
 {
 	int budsz, bud, w, bsz, size;
 	int cursz;
@@ -2737,7 +2737,7 @@ static int dbBackSplit(dmtree_t * tp, int leafno)
 				 * system in two.
 				 */
 				cursz = leaf[bud] - 1;
-				dbSplit(tp, bud, cursz, cursz);
+				dbSplit(tp, bud, cursz, cursz, is_ctl);
 				break;
 			}
 		}
@@ -2763,9 +2763,11 @@ static int dbBackSplit(dmtree_t * tp, int leafno)
  *	leafno	- the number of the leaf to be updated.
  *	newval	- the new value for the leaf.
  *
- * RETURN VALUES: none
+ * RETURN VALUES:
+ *  0		- success
+ *	-EIO	- i/o error
  */
-static int dbJoin(dmtree_t * tp, int leafno, int newval)
+static int dbJoin(dmtree_t *tp, int leafno, int newval, bool is_ctl)
 {
 	int budsz, buddy;
 	s8 *leaf;
@@ -2790,6 +2792,10 @@ static int dbJoin(dmtree_t * tp, int leafno, int newval)
 		 * get the buddy size (number of words covered) of
 		 * the new value.
 		 */
+
+		if ((newval - tp->dmt_budmin) > BUDMIN)
+			return -EIO;
+
 		budsz = BUDSIZE(newval, tp->dmt_budmin);
 
 		/* try to join.
@@ -2820,12 +2826,12 @@ static int dbJoin(dmtree_t * tp, int leafno, int newval)
 			if (leafno < buddy) {
 				/* leafno is the left buddy.
 				 */
-				dbAdjTree(tp, buddy, NOFREE);
+				dbAdjTree(tp, buddy, NOFREE, is_ctl);
 			} else {
 				/* buddy is the left buddy and becomes
 				 * leafno.
 				 */
-				dbAdjTree(tp, leafno, NOFREE);
+				dbAdjTree(tp, leafno, NOFREE, is_ctl);
 				leafno = buddy;
 			}
 
@@ -2838,7 +2844,7 @@ static int dbJoin(dmtree_t * tp, int leafno, int newval)
 
 	/* update the leaf value.
 	 */
-	dbAdjTree(tp, leafno, newval);
+	dbAdjTree(tp, leafno, newval, is_ctl);
 
 	return 0;
 }
@@ -2859,15 +2865,20 @@ static int dbJoin(dmtree_t * tp, int leafno, int newval)
  *
  * RETURN VALUES: none
  */
-static void dbAdjTree(dmtree_t * tp, int leafno, int newval)
+static void dbAdjTree(dmtree_t *tp, int leafno, int newval, bool is_ctl)
 {
 	int lp, pp, k;
-	int max;
+	int max, size;
+
+	size = is_ctl ? CTLTREESIZE : TREESIZE;
 
 	/* pick up the index of the leaf for this leafno.
 	 */
 	lp = leafno + le32_to_cpu(tp->dmt_leafidx);
 
+	if (WARN_ON_ONCE(lp >= size || lp < 0))
+		return;
+
 	/* is the current value the same as the old value ?  if so,
 	 * there is nothing to do.
 	 */
diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c
index 92b7c533407c..031d8f570f58 100644
--- a/fs/jfs/jfs_dtree.c
+++ b/fs/jfs/jfs_dtree.c
@@ -633,6 +633,11 @@ int dtSearch(struct inode *ip, struct component_name * key, ino_t * data,
 		for (base = 0, lim = p->header.nextindex; lim; lim >>= 1) {
 			index = base + (lim >> 1);
 
+			if (stbl[index] < 0) {
+				rc = -EIO;
+				goto out;
+			}
+
 			if (p->header.flag & BT_LEAF) {
 				/* uppercase leaf name to compare */
 				cmp =
@@ -1970,7 +1975,7 @@ static int dtSplitRoot(tid_t tid,
 		do {
 			f = &rp->slot[fsi];
 			fsi = f->next;
-		} while (fsi != -1);
+		} while (fsi >= 0);
 
 		f->next = n;
 	}
diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c
index a037ee59e398..2ec35889ad24 100644
--- a/fs/jfs/jfs_imap.c
+++ b/fs/jfs/jfs_imap.c
@@ -2179,6 +2179,9 @@ static int diNewExt(struct inomap * imap, struct iag * iagp, int extno)
 	/* get the ag and iag numbers for this iag.
 	 */
 	agno = BLKTOAG(le64_to_cpu(iagp->agstart), sbi);
+	if (agno >= MAXAG || agno < 0)
+		return -EIO;
+
 	iagno = le32_to_cpu(iagp->iagnum);
 
 	/* check if this is the last free extent within the
diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c
index 415eb65a36ff..9b5c6a20b30c 100644
--- a/fs/jfs/jfs_mount.c
+++ b/fs/jfs/jfs_mount.c
@@ -172,15 +172,15 @@ int jfs_mount(struct super_block *sb)
 	}
 	jfs_info("jfs_mount: ipimap:0x%p", ipimap);
 
-	/* map further access of per fileset inodes by the fileset inode */
-	sbi->ipimap = ipimap;
-
 	/* initialize fileset inode allocation map */
 	if ((rc = diMount(ipimap))) {
 		jfs_err("jfs_mount: diMount failed w/rc = %d", rc);
 		goto err_ipimap;
 	}
 
+	/* map further access of per fileset inodes by the fileset inode */
+	sbi->ipimap = ipimap;
+
 	return rc;
 
 	/*
diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c
index dccc8b3f1045..be17e3c43582 100644
--- a/fs/jfs/jfs_txnmgr.c
+++ b/fs/jfs/jfs_txnmgr.c
@@ -2702,6 +2702,7 @@ int jfs_lazycommit(void *arg)
 	unsigned long flags;
 	struct jfs_sb_info *sbi;
 
+	set_freezable();
 	do {
 		LAZY_LOCK(flags);
 		jfs_commit_thread_waking = 0;	/* OK to wake another thread */
@@ -2884,6 +2885,7 @@ int jfs_sync(void *arg)
 	struct jfs_inode_info *jfs_ip;
 	tid_t tid;
 
+	set_freezable();
 	do {
 		/*
 		 * write each inode on the anonymous inode list
diff --git a/fs/libfs.c b/fs/libfs.c
index e9440d55073c..c2aa6fd4795c 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -399,6 +399,8 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence)
 		return -EINVAL;
 	}
 
+	/* In this case, ->private_data is protected by f_pos_lock */
+	file->private_data = NULL;
 	return vfs_setpos(file, offset, U32_MAX);
 }
 
@@ -428,7 +430,7 @@ static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry)
 			  inode->i_ino, fs_umode_to_dtype(inode->i_mode));
 }
 
-static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
+static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
 {
 	struct offset_ctx *so_ctx = inode->i_op->get_offset_ctx(inode);
 	XA_STATE(xas, &so_ctx->xa, ctx->pos);
@@ -437,7 +439,7 @@ static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
 	while (true) {
 		dentry = offset_find_next(&xas);
 		if (!dentry)
-			break;
+			return ERR_PTR(-ENOENT);
 
 		if (!offset_dir_emit(ctx, dentry)) {
 			dput(dentry);
@@ -447,6 +449,7 @@ static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
 		dput(dentry);
 		ctx->pos = xas.xa_index + 1;
 	}
+	return NULL;
 }
 
 /**
@@ -479,7 +482,12 @@ static int offset_readdir(struct file *file, struct dir_context *ctx)
 	if (!dir_emit_dots(file, ctx))
 		return 0;
 
-	offset_iterate_dir(d_inode(dir), ctx);
+	/* In this case, ->private_data is protected by f_pos_lock */
+	if (ctx->pos == 2)
+		file->private_data = NULL;
+	else if (file->private_data == ERR_PTR(-ENOENT))
+		return 0;
+	file->private_data = offset_iterate_dir(d_inode(dir), ctx);
 	return 0;
 }
 
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 81be07c1d3d1..ce5862482097 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -345,10 +345,10 @@ static int lockd_get(void)
 
 	serv->sv_maxconn = nlm_max_connections;
 	error = svc_set_num_threads(serv, NULL, 1);
-	/* The thread now holds the only reference */
-	svc_put(serv);
-	if (error < 0)
+	if (error < 0) {
+		svc_destroy(&serv);
 		return error;
+	}
 
 	nlmsvc_serv = serv;
 	register_inetaddr_notifier(&lockd_inetaddr_notifier);
@@ -372,11 +372,9 @@ static void lockd_put(void)
 	unregister_inet6addr_notifier(&lockd_inet6addr_notifier);
 #endif
 
-	svc_get(nlmsvc_serv);
 	svc_set_num_threads(nlmsvc_serv, NULL, 0);
-	svc_put(nlmsvc_serv);
 	timer_delete_sync(&nlmsvc_retry);
-	nlmsvc_serv = NULL;
+	svc_destroy(&nlmsvc_serv);
 	dprintk("lockd_down: service destroyed\n");
 }
 
@@ -475,7 +473,6 @@ static struct ctl_table nlm_sysctls[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-	{ }
 };
 
 #endif	/* CONFIG_SYSCTL */
diff --git a/fs/locks.c b/fs/locks.c
index 46d88b9e222c..cc7c117ee192 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -111,7 +111,6 @@ static struct ctl_table locks_sysctls[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif /* CONFIG_MMU */
-	{}
 };
 
 static int __init init_fs_locks_sysctls(void)
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index f8af6c3ae336..73f37f298087 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -17,6 +17,7 @@
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/highuid.h>
+#include <linux/mpage.h>
 #include <linux/vfs.h>
 #include <linux/writeback.h>
 
@@ -397,9 +398,10 @@ static int minix_get_block(struct inode *inode, sector_t block,
 		return V2_minix_get_block(inode, block, bh_result, create);
 }
 
-static int minix_writepage(struct page *page, struct writeback_control *wbc)
+static int minix_writepages(struct address_space *mapping,
+		struct writeback_control *wbc)
 {
-	return block_write_full_page(page, minix_get_block, wbc);
+	return mpage_writepages(mapping, wbc, minix_get_block);
 }
 
 static int minix_read_folio(struct file *file, struct folio *folio)
@@ -444,9 +446,10 @@ static const struct address_space_operations minix_aops = {
 	.dirty_folio	= block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
 	.read_folio = minix_read_folio,
-	.writepage = minix_writepage,
+	.writepages = minix_writepages,
 	.write_begin = minix_write_begin,
 	.write_end = generic_write_end,
+	.migrate_folio = buffer_migrate_folio,
 	.bmap = minix_bmap,
 	.direct_IO = noop_direct_IO
 };
diff --git a/fs/mnt_idmapping.c b/fs/mnt_idmapping.c
index 57d1dedf3f8f..64c5205e2b5e 100644
--- a/fs/mnt_idmapping.c
+++ b/fs/mnt_idmapping.c
@@ -9,8 +9,16 @@
 
 #include "internal.h"
 
+/*
+ * Outside of this file vfs{g,u}id_t are always created from k{g,u}id_t,
+ * never from raw values. These are just internal helpers.
+ */
+#define VFSUIDT_INIT_RAW(val) (vfsuid_t){ val }
+#define VFSGIDT_INIT_RAW(val) (vfsgid_t){ val }
+
 struct mnt_idmap {
-	struct user_namespace *owner;
+	struct uid_gid_map uid_map;
+	struct uid_gid_map gid_map;
 	refcount_t count;
 };
 
@@ -20,25 +28,11 @@ struct mnt_idmap {
  * mapped to {g,u}id 1, [...], {g,u}id 1000 to {g,u}id 1000, [...].
  */
 struct mnt_idmap nop_mnt_idmap = {
-	.owner	= &init_user_ns,
 	.count	= REFCOUNT_INIT(1),
 };
 EXPORT_SYMBOL_GPL(nop_mnt_idmap);
 
 /**
- * check_fsmapping - check whether an mount idmapping is allowed
- * @idmap: idmap of the relevent mount
- * @sb:    super block of the filesystem
- *
- * Return: true if @idmap is allowed, false if not.
- */
-bool check_fsmapping(const struct mnt_idmap *idmap,
-		     const struct super_block *sb)
-{
-	return idmap->owner != sb->s_user_ns;
-}
-
-/**
  * initial_idmapping - check whether this is the initial mapping
  * @ns: idmapping to check
  *
@@ -53,26 +47,6 @@ static inline bool initial_idmapping(const struct user_namespace *ns)
 }
 
 /**
- * no_idmapping - check whether we can skip remapping a kuid/gid
- * @mnt_userns: the mount's idmapping
- * @fs_userns: the filesystem's idmapping
- *
- * This function can be used to check whether a remapping between two
- * idmappings is required.
- * An idmapped mount is a mount that has an idmapping attached to it that
- * is different from the filsystem's idmapping and the initial idmapping.
- * If the initial mapping is used or the idmapping of the mount and the
- * filesystem are identical no remapping is required.
- *
- * Return: true if remapping can be skipped, false if not.
- */
-static inline bool no_idmapping(const struct user_namespace *mnt_userns,
-				const struct user_namespace *fs_userns)
-{
-	return initial_idmapping(mnt_userns) || mnt_userns == fs_userns;
-}
-
-/**
  * make_vfsuid - map a filesystem kuid according to an idmapping
  * @idmap: the mount's idmapping
  * @fs_userns: the filesystem's idmapping
@@ -81,8 +55,8 @@ static inline bool no_idmapping(const struct user_namespace *mnt_userns,
  * Take a @kuid and remap it from @fs_userns into @idmap. Use this
  * function when preparing a @kuid to be reported to userspace.
  *
- * If no_idmapping() determines that this is not an idmapped mount we can
- * simply return @kuid unchanged.
+ * If initial_idmapping() determines that this is not an idmapped mount
+ * we can simply return @kuid unchanged.
  * If initial_idmapping() tells us that the filesystem is not mounted with an
  * idmapping we know the value of @kuid won't change when calling
  * from_kuid() so we can simply retrieve the value via __kuid_val()
@@ -94,13 +68,12 @@ static inline bool no_idmapping(const struct user_namespace *mnt_userns,
  */
 
 vfsuid_t make_vfsuid(struct mnt_idmap *idmap,
-				   struct user_namespace *fs_userns,
-				   kuid_t kuid)
+		     struct user_namespace *fs_userns,
+		     kuid_t kuid)
 {
 	uid_t uid;
-	struct user_namespace *mnt_userns = idmap->owner;
 
-	if (no_idmapping(mnt_userns, fs_userns))
+	if (idmap == &nop_mnt_idmap)
 		return VFSUIDT_INIT(kuid);
 	if (initial_idmapping(fs_userns))
 		uid = __kuid_val(kuid);
@@ -108,7 +81,7 @@ vfsuid_t make_vfsuid(struct mnt_idmap *idmap,
 		uid = from_kuid(fs_userns, kuid);
 	if (uid == (uid_t)-1)
 		return INVALID_VFSUID;
-	return VFSUIDT_INIT(make_kuid(mnt_userns, uid));
+	return VFSUIDT_INIT_RAW(map_id_down(&idmap->uid_map, uid));
 }
 EXPORT_SYMBOL_GPL(make_vfsuid);
 
@@ -121,8 +94,8 @@ EXPORT_SYMBOL_GPL(make_vfsuid);
  * Take a @kgid and remap it from @fs_userns into @idmap. Use this
  * function when preparing a @kgid to be reported to userspace.
  *
- * If no_idmapping() determines that this is not an idmapped mount we can
- * simply return @kgid unchanged.
+ * If initial_idmapping() determines that this is not an idmapped mount
+ * we can simply return @kgid unchanged.
  * If initial_idmapping() tells us that the filesystem is not mounted with an
  * idmapping we know the value of @kgid won't change when calling
  * from_kgid() so we can simply retrieve the value via __kgid_val()
@@ -136,9 +109,8 @@ vfsgid_t make_vfsgid(struct mnt_idmap *idmap,
 		     struct user_namespace *fs_userns, kgid_t kgid)
 {
 	gid_t gid;
-	struct user_namespace *mnt_userns = idmap->owner;
 
-	if (no_idmapping(mnt_userns, fs_userns))
+	if (idmap == &nop_mnt_idmap)
 		return VFSGIDT_INIT(kgid);
 	if (initial_idmapping(fs_userns))
 		gid = __kgid_val(kgid);
@@ -146,7 +118,7 @@ vfsgid_t make_vfsgid(struct mnt_idmap *idmap,
 		gid = from_kgid(fs_userns, kgid);
 	if (gid == (gid_t)-1)
 		return INVALID_VFSGID;
-	return VFSGIDT_INIT(make_kgid(mnt_userns, gid));
+	return VFSGIDT_INIT_RAW(map_id_down(&idmap->gid_map, gid));
 }
 EXPORT_SYMBOL_GPL(make_vfsgid);
 
@@ -165,11 +137,10 @@ kuid_t from_vfsuid(struct mnt_idmap *idmap,
 		   struct user_namespace *fs_userns, vfsuid_t vfsuid)
 {
 	uid_t uid;
-	struct user_namespace *mnt_userns = idmap->owner;
 
-	if (no_idmapping(mnt_userns, fs_userns))
+	if (idmap == &nop_mnt_idmap)
 		return AS_KUIDT(vfsuid);
-	uid = from_kuid(mnt_userns, AS_KUIDT(vfsuid));
+	uid = map_id_up(&idmap->uid_map, __vfsuid_val(vfsuid));
 	if (uid == (uid_t)-1)
 		return INVALID_UID;
 	if (initial_idmapping(fs_userns))
@@ -193,11 +164,10 @@ kgid_t from_vfsgid(struct mnt_idmap *idmap,
 		   struct user_namespace *fs_userns, vfsgid_t vfsgid)
 {
 	gid_t gid;
-	struct user_namespace *mnt_userns = idmap->owner;
 
-	if (no_idmapping(mnt_userns, fs_userns))
+	if (idmap == &nop_mnt_idmap)
 		return AS_KGIDT(vfsgid);
-	gid = from_kgid(mnt_userns, AS_KGIDT(vfsgid));
+	gid = map_id_up(&idmap->gid_map, __vfsgid_val(vfsgid));
 	if (gid == (gid_t)-1)
 		return INVALID_GID;
 	if (initial_idmapping(fs_userns))
@@ -228,16 +198,91 @@ int vfsgid_in_group_p(vfsgid_t vfsgid)
 #endif
 EXPORT_SYMBOL_GPL(vfsgid_in_group_p);
 
+static int copy_mnt_idmap(struct uid_gid_map *map_from,
+			  struct uid_gid_map *map_to)
+{
+	struct uid_gid_extent *forward, *reverse;
+	u32 nr_extents = READ_ONCE(map_from->nr_extents);
+	/* Pairs with smp_wmb() when writing the idmapping. */
+	smp_rmb();
+
+	/*
+	 * Don't blindly copy @map_to into @map_from if nr_extents is
+	 * smaller or equal to UID_GID_MAP_MAX_BASE_EXTENTS. Since we
+	 * read @nr_extents someone could have written an idmapping and
+	 * then we might end up with inconsistent data. So just don't do
+	 * anything at all.
+	 */
+	if (nr_extents == 0)
+		return 0;
+
+	/*
+	 * Here we know that nr_extents is greater than zero which means
+	 * a map has been written. Since idmappings can't be changed
+	 * once they have been written we know that we can safely copy
+	 * from @map_to into @map_from.
+	 */
+
+	if (nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) {
+		*map_to = *map_from;
+		return 0;
+	}
+
+	forward = kmemdup(map_from->forward,
+			  nr_extents * sizeof(struct uid_gid_extent),
+			  GFP_KERNEL_ACCOUNT);
+	if (!forward)
+		return -ENOMEM;
+
+	reverse = kmemdup(map_from->reverse,
+			  nr_extents * sizeof(struct uid_gid_extent),
+			  GFP_KERNEL_ACCOUNT);
+	if (!reverse) {
+		kfree(forward);
+		return -ENOMEM;
+	}
+
+	/*
+	 * The idmapping isn't exposed anywhere so we don't need to care
+	 * about ordering between extent pointers and @nr_extents
+	 * initialization.
+	 */
+	map_to->forward = forward;
+	map_to->reverse = reverse;
+	map_to->nr_extents = nr_extents;
+	return 0;
+}
+
+static void free_mnt_idmap(struct mnt_idmap *idmap)
+{
+	if (idmap->uid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) {
+		kfree(idmap->uid_map.forward);
+		kfree(idmap->uid_map.reverse);
+	}
+	if (idmap->gid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) {
+		kfree(idmap->gid_map.forward);
+		kfree(idmap->gid_map.reverse);
+	}
+	kfree(idmap);
+}
+
 struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns)
 {
 	struct mnt_idmap *idmap;
+	int ret;
 
 	idmap = kzalloc(sizeof(struct mnt_idmap), GFP_KERNEL_ACCOUNT);
 	if (!idmap)
 		return ERR_PTR(-ENOMEM);
 
-	idmap->owner = get_user_ns(mnt_userns);
 	refcount_set(&idmap->count, 1);
+	ret = copy_mnt_idmap(&mnt_userns->uid_map, &idmap->uid_map);
+	if (!ret)
+		ret = copy_mnt_idmap(&mnt_userns->gid_map, &idmap->gid_map);
+	if (ret) {
+		free_mnt_idmap(idmap);
+		idmap = ERR_PTR(ret);
+	}
 	return idmap;
 }
 
@@ -267,9 +312,7 @@ EXPORT_SYMBOL_GPL(mnt_idmap_get);
  */
 void mnt_idmap_put(struct mnt_idmap *idmap)
 {
-	if (idmap != &nop_mnt_idmap && refcount_dec_and_test(&idmap->count)) {
-		put_user_ns(idmap->owner);
-		kfree(idmap);
-	}
+	if (idmap != &nop_mnt_idmap && refcount_dec_and_test(&idmap->count))
+		free_mnt_idmap(idmap);
 }
 EXPORT_SYMBOL_GPL(mnt_idmap_put);
diff --git a/fs/mount.h b/fs/mount.h
index 130c07c2f8d2..4a42fc68f4cc 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -8,19 +8,13 @@
 struct mnt_namespace {
 	struct ns_common	ns;
 	struct mount *	root;
-	/*
-	 * Traversal and modification of .list is protected by either
-	 * - taking namespace_sem for write, OR
-	 * - taking namespace_sem for read AND taking .ns_lock.
-	 */
-	struct list_head	list;
-	spinlock_t		ns_lock;
+	struct rb_root		mounts; /* Protected by namespace_sem */
 	struct user_namespace	*user_ns;
 	struct ucounts		*ucounts;
 	u64			seq;	/* Sequence number to prevent loops */
 	wait_queue_head_t poll;
 	u64 event;
-	unsigned int		mounts; /* # of mounts in the namespace */
+	unsigned int		nr_mounts; /* # of mounts in the namespace */
 	unsigned int		pending_mounts;
 } __randomize_layout;
 
@@ -55,7 +49,10 @@ struct mount {
 	struct list_head mnt_child;	/* and going through their mnt_child */
 	struct list_head mnt_instance;	/* mount instance on sb->s_mounts */
 	const char *mnt_devname;	/* Name of device e.g. /dev/dsk/hda1 */
-	struct list_head mnt_list;
+	union {
+		struct rb_node mnt_node;	/* Under ns->mounts */
+		struct list_head mnt_list;
+	};
 	struct list_head mnt_expire;	/* link in fs-specific expiry list */
 	struct list_head mnt_share;	/* circular list of shared mounts */
 	struct list_head mnt_slave_list;/* list of slave mounts */
@@ -72,7 +69,8 @@ struct mount {
 	struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks;
 	__u32 mnt_fsnotify_mask;
 #endif
-	int mnt_id;			/* mount identifier */
+	int mnt_id;			/* mount identifier, reused */
+	u64 mnt_id_unique;		/* mount ID unique until reboot */
 	int mnt_group_id;		/* peer group identifier */
 	int mnt_expiry_mark;		/* true if marked for expiry */
 	struct hlist_head mnt_pins;
@@ -127,7 +125,6 @@ struct proc_mounts {
 	struct mnt_namespace *ns;
 	struct path root;
 	int (*show)(struct seq_file *, struct vfsmount *);
-	struct mount cursor;
 };
 
 extern const struct seq_operations mounts_op;
@@ -146,4 +143,12 @@ static inline bool is_anon_ns(struct mnt_namespace *ns)
 	return ns->seq == 0;
 }
 
+static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list)
+{
+	WARN_ON(!(mnt->mnt.mnt_flags & MNT_ONRB));
+	mnt->mnt.mnt_flags &= ~MNT_ONRB;
+	rb_erase(&mnt->mnt_node, &mnt->mnt_ns->mounts);
+	list_add_tail(&mnt->mnt_list, dt_list);
+}
+
 extern void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor);
diff --git a/fs/mpage.c b/fs/mpage.c
index ffb064ed9d04..738882e0766d 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -166,7 +166,7 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
 	sector_t block_in_file;
 	sector_t last_block;
 	sector_t last_block_in_file;
-	sector_t blocks[MAX_BUF_PER_PAGE];
+	sector_t first_block;
 	unsigned page_block;
 	unsigned first_hole = blocks_per_page;
 	struct block_device *bdev = NULL;
@@ -205,6 +205,7 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
 		unsigned map_offset = block_in_file - args->first_logical_block;
 		unsigned last = nblocks - map_offset;
 
+		first_block = map_bh->b_blocknr + map_offset;
 		for (relative_block = 0; ; relative_block++) {
 			if (relative_block == last) {
 				clear_buffer_mapped(map_bh);
@@ -212,8 +213,6 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
 			}
 			if (page_block == blocks_per_page)
 				break;
-			blocks[page_block] = map_bh->b_blocknr + map_offset +
-						relative_block;
 			page_block++;
 			block_in_file++;
 		}
@@ -259,7 +258,9 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
 			goto confused;		/* hole -> non-hole */
 
 		/* Contiguous blocks? */
-		if (page_block && blocks[page_block-1] != map_bh->b_blocknr-1)
+		if (!page_block)
+			first_block = map_bh->b_blocknr;
+		else if (first_block + page_block != map_bh->b_blocknr)
 			goto confused;
 		nblocks = map_bh->b_size >> blkbits;
 		for (relative_block = 0; ; relative_block++) {
@@ -268,7 +269,6 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
 				break;
 			} else if (page_block == blocks_per_page)
 				break;
-			blocks[page_block] = map_bh->b_blocknr+relative_block;
 			page_block++;
 			block_in_file++;
 		}
@@ -289,7 +289,7 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
 	/*
 	 * This folio will go to BIO.  Do we need to send this BIO off first?
 	 */
-	if (args->bio && (args->last_block_in_bio != blocks[0] - 1))
+	if (args->bio && (args->last_block_in_bio != first_block - 1))
 		args->bio = mpage_bio_submit_read(args->bio);
 
 alloc_new:
@@ -298,7 +298,7 @@ alloc_new:
 				      gfp);
 		if (args->bio == NULL)
 			goto confused;
-		args->bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9);
+		args->bio->bi_iter.bi_sector = first_block << (blkbits - 9);
 	}
 
 	length = first_hole << blkbits;
@@ -313,7 +313,7 @@ alloc_new:
 	    (first_hole != blocks_per_page))
 		args->bio = mpage_bio_submit_read(args->bio);
 	else
-		args->last_block_in_bio = blocks[blocks_per_page - 1];
+		args->last_block_in_bio = first_block + blocks_per_page - 1;
 out:
 	return args->bio;
 
@@ -430,13 +430,13 @@ struct mpage_data {
  * We have our BIO, so we can now mark the buffers clean.  Make
  * sure to only clean buffers which we know we'll be writing.
  */
-static void clean_buffers(struct page *page, unsigned first_unmapped)
+static void clean_buffers(struct folio *folio, unsigned first_unmapped)
 {
 	unsigned buffer_counter = 0;
-	struct buffer_head *bh, *head;
-	if (!page_has_buffers(page))
+	struct buffer_head *bh, *head = folio_buffers(folio);
+
+	if (!head)
 		return;
-	head = page_buffers(page);
 	bh = head;
 
 	do {
@@ -451,18 +451,8 @@ static void clean_buffers(struct page *page, unsigned first_unmapped)
 	 * read_folio would fail to serialize with the bh and it would read from
 	 * disk before we reach the platter.
 	 */
-	if (buffer_heads_over_limit && PageUptodate(page))
-		try_to_free_buffers(page_folio(page));
-}
-
-/*
- * For situations where we want to clean all buffers attached to a page.
- * We don't need to calculate how many buffers are attached to the page,
- * we just need to specify a number larger than the maximum number of buffers.
- */
-void clean_page_buffers(struct page *page)
-{
-	clean_buffers(page, ~0U);
+	if (buffer_heads_over_limit && folio_test_uptodate(folio))
+		try_to_free_buffers(folio);
 }
 
 static int __mpage_writepage(struct folio *folio, struct writeback_control *wbc,
@@ -476,7 +466,7 @@ static int __mpage_writepage(struct folio *folio, struct writeback_control *wbc,
 	const unsigned blocks_per_page = PAGE_SIZE >> blkbits;
 	sector_t last_block;
 	sector_t block_in_file;
-	sector_t blocks[MAX_BUF_PER_PAGE];
+	sector_t first_block;
 	unsigned page_block;
 	unsigned first_unmapped = blocks_per_page;
 	struct block_device *bdev = NULL;
@@ -514,10 +504,12 @@ static int __mpage_writepage(struct folio *folio, struct writeback_control *wbc,
 			if (!buffer_dirty(bh) || !buffer_uptodate(bh))
 				goto confused;
 			if (page_block) {
-				if (bh->b_blocknr != blocks[page_block-1] + 1)
+				if (bh->b_blocknr != first_block + page_block)
 					goto confused;
+			} else {
+				first_block = bh->b_blocknr;
 			}
-			blocks[page_block++] = bh->b_blocknr;
+			page_block++;
 			boundary = buffer_boundary(bh);
 			if (boundary) {
 				boundary_block = bh->b_blocknr;
@@ -566,10 +558,12 @@ static int __mpage_writepage(struct folio *folio, struct writeback_control *wbc,
 			boundary_bdev = map_bh.b_bdev;
 		}
 		if (page_block) {
-			if (map_bh.b_blocknr != blocks[page_block-1] + 1)
+			if (map_bh.b_blocknr != first_block + page_block)
 				goto confused;
+		} else {
+			first_block = map_bh.b_blocknr;
 		}
-		blocks[page_block++] = map_bh.b_blocknr;
+		page_block++;
 		boundary = buffer_boundary(&map_bh);
 		bdev = map_bh.b_bdev;
 		if (block_in_file == last_block)
@@ -601,7 +595,7 @@ page_is_mapped:
 	/*
 	 * This page will go to BIO.  Do we need to send this BIO off first?
 	 */
-	if (bio && mpd->last_block_in_bio != blocks[0] - 1)
+	if (bio && mpd->last_block_in_bio != first_block - 1)
 		bio = mpage_bio_submit_write(bio);
 
 alloc_new:
@@ -609,7 +603,7 @@ alloc_new:
 		bio = bio_alloc(bdev, BIO_MAX_VECS,
 				REQ_OP_WRITE | wbc_to_write_flags(wbc),
 				GFP_NOFS);
-		bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9);
+		bio->bi_iter.bi_sector = first_block << (blkbits - 9);
 		wbc_init_bio(wbc, bio);
 	}
 
@@ -625,7 +619,7 @@ alloc_new:
 		goto alloc_new;
 	}
 
-	clean_buffers(&folio->page, first_unmapped);
+	clean_buffers(folio, first_unmapped);
 
 	BUG_ON(folio_test_writeback(folio));
 	folio_start_writeback(folio);
@@ -637,7 +631,7 @@ alloc_new:
 					boundary_block, 1 << blkbits);
 		}
 	} else {
-		mpd->last_block_in_bio = blocks[blocks_per_page - 1];
+		mpd->last_block_in_bio = first_block + blocks_per_page - 1;
 	}
 	goto out;
 
@@ -648,7 +642,7 @@ confused:
 	/*
 	 * The caller has a ref on the inode, so *mapping is stable
 	 */
-	ret = block_write_full_page(&folio->page, mpd->get_block, wbc);
+	ret = block_write_full_folio(folio, wbc, mpd->get_block);
 	mapping_set_error(mapping, ret);
 out:
 	mpd->bio = bio;
diff --git a/fs/namei.c b/fs/namei.c
index 71c13b2990b4..963576e67f62 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -289,7 +289,7 @@ EXPORT_SYMBOL(putname);
  * the vfsmount must be passed through @idmap. This function will then take
  * care to map the inode according to @idmap before checking permissions.
  * On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
  */
 static int check_acl(struct mnt_idmap *idmap,
 		     struct inode *inode, int mask)
@@ -334,7 +334,7 @@ static int check_acl(struct mnt_idmap *idmap,
  * the vfsmount must be passed through @idmap. This function will then take
  * care to map the inode according to @idmap before checking permissions.
  * On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
  */
 static int acl_permission_check(struct mnt_idmap *idmap,
 				struct inode *inode, int mask)
@@ -395,7 +395,7 @@ static int acl_permission_check(struct mnt_idmap *idmap,
  * the vfsmount must be passed through @idmap. This function will then take
  * care to map the inode according to @idmap before checking permissions.
  * On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
  */
 int generic_permission(struct mnt_idmap *idmap, struct inode *inode,
 		       int mask)
@@ -1071,7 +1071,6 @@ static struct ctl_table namei_sysctls[] = {
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_TWO,
 	},
-	{ }
 };
 
 static int __init init_fs_namei_sysctls(void)
@@ -2467,7 +2466,7 @@ static int handle_lookup_down(struct nameidata *nd)
 	return PTR_ERR(step_into(nd, WALK_NOFOLLOW, nd->path.dentry));
 }
 
-/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
+/* Returns 0 and nd will be valid on success; Returns error, otherwise. */
 static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path)
 {
 	const char *s = path_init(nd, flags);
@@ -2522,7 +2521,7 @@ int filename_lookup(int dfd, struct filename *name, unsigned flags,
 	return retval;
 }
 
-/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
+/* Returns 0 and nd will be valid on success; Returns error, otherwise. */
 static int path_parentat(struct nameidata *nd, unsigned flags,
 				struct path *parent)
 {
@@ -3158,7 +3157,7 @@ static inline umode_t vfs_prepare_mode(struct mnt_idmap *idmap,
  * the vfsmount must be passed through @idmap. This function will then take
  * care to map the inode according to @idmap before checking permissions.
  * On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
  */
 int vfs_create(struct mnt_idmap *idmap, struct inode *dir,
 	       struct dentry *dentry, umode_t mode, bool want_excl)
@@ -3646,7 +3645,7 @@ static int do_open(struct nameidata *nd,
  * the vfsmount must be passed through @idmap. This function will then take
  * care to map the inode according to @idmap before checking permissions.
  * On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
  */
 static int vfs_tmpfile(struct mnt_idmap *idmap,
 		       const struct path *parentpath,
@@ -3785,10 +3784,7 @@ static struct file *path_openat(struct nameidata *nd,
 		WARN_ON(1);
 		error = -EINVAL;
 	}
-	if (unlikely(file->f_mode & FMODE_OPENED))
-		fput(file);
-	else
-		release_empty_file(file);
+	fput(file);
 	if (error == -EOPENSTALE) {
 		if (flags & LOOKUP_RCU)
 			error = -ECHILD;
@@ -3954,7 +3950,7 @@ EXPORT_SYMBOL(user_path_create);
  * the vfsmount must be passed through @idmap. This function will then take
  * care to map the inode according to @idmap before checking permissions.
  * On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
  */
 int vfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 	      struct dentry *dentry, umode_t mode, dev_t dev)
@@ -4080,7 +4076,7 @@ SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, d
  * the vfsmount must be passed through @idmap. This function will then take
  * care to map the inode according to @idmap before checking permissions.
  * On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
  */
 int vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	      struct dentry *dentry, umode_t mode)
@@ -4161,7 +4157,7 @@ SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode)
  * the vfsmount must be passed through @idmap. This function will then take
  * care to map the inode according to @idmap before checking permissions.
  * On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
  */
 int vfs_rmdir(struct mnt_idmap *idmap, struct inode *dir,
 		     struct dentry *dentry)
@@ -4290,7 +4286,7 @@ SYSCALL_DEFINE1(rmdir, const char __user *, pathname)
  * the vfsmount must be passed through @idmap. This function will then take
  * care to map the inode according to @idmap before checking permissions.
  * On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
  */
 int vfs_unlink(struct mnt_idmap *idmap, struct inode *dir,
 	       struct dentry *dentry, struct inode **delegated_inode)
@@ -4443,7 +4439,7 @@ SYSCALL_DEFINE1(unlink, const char __user *, pathname)
  * the vfsmount must be passed through @idmap. This function will then take
  * care to map the inode according to @idmap before checking permissions.
  * On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
  */
 int vfs_symlink(struct mnt_idmap *idmap, struct inode *dir,
 		struct dentry *dentry, const char *oldname)
@@ -4535,7 +4531,7 @@ SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newn
  * the vfsmount must be passed through @idmap. This function will then take
  * care to map the inode according to @idmap before checking permissions.
  * On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
  */
 int vfs_link(struct dentry *old_dentry, struct mnt_idmap *idmap,
 	     struct inode *dir, struct dentry *new_dentry,
diff --git a/fs/namespace.c b/fs/namespace.c
index fbf0e596fcd3..ef1fd6829814 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -32,6 +32,7 @@
 #include <linux/fs_context.h>
 #include <linux/shmem_fs.h>
 #include <linux/mnt_idmapping.h>
+#include <linux/nospec.h>
 
 #include "pnode.h"
 #include "internal.h"
@@ -68,6 +69,9 @@ static u64 event;
 static DEFINE_IDA(mnt_id_ida);
 static DEFINE_IDA(mnt_group_ida);
 
+/* Don't allow confusion with old 32bit mount ID */
+static atomic64_t mnt_id_ctr = ATOMIC64_INIT(1ULL << 32);
+
 static struct hlist_head *mount_hashtable __ro_after_init;
 static struct hlist_head *mountpoint_hashtable __ro_after_init;
 static struct kmem_cache *mnt_cache __ro_after_init;
@@ -131,6 +135,7 @@ static int mnt_alloc_id(struct mount *mnt)
 	if (res < 0)
 		return res;
 	mnt->mnt_id = res;
+	mnt->mnt_id_unique = atomic64_inc_return(&mnt_id_ctr);
 	return 0;
 }
 
@@ -730,21 +735,6 @@ struct vfsmount *lookup_mnt(const struct path *path)
 	return m;
 }
 
-static inline void lock_ns_list(struct mnt_namespace *ns)
-{
-	spin_lock(&ns->ns_lock);
-}
-
-static inline void unlock_ns_list(struct mnt_namespace *ns)
-{
-	spin_unlock(&ns->ns_lock);
-}
-
-static inline bool mnt_is_cursor(struct mount *mnt)
-{
-	return mnt->mnt.mnt_flags & MNT_CURSOR;
-}
-
 /*
  * __is_local_mountpoint - Test to see if dentry is a mountpoint in the
  *                         current mount namespace.
@@ -763,19 +753,15 @@ static inline bool mnt_is_cursor(struct mount *mnt)
 bool __is_local_mountpoint(struct dentry *dentry)
 {
 	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
-	struct mount *mnt;
+	struct mount *mnt, *n;
 	bool is_covered = false;
 
 	down_read(&namespace_sem);
-	lock_ns_list(ns);
-	list_for_each_entry(mnt, &ns->list, mnt_list) {
-		if (mnt_is_cursor(mnt))
-			continue;
+	rbtree_postorder_for_each_entry_safe(mnt, n, &ns->mounts, mnt_node) {
 		is_covered = (mnt->mnt_mountpoint == dentry);
 		if (is_covered)
 			break;
 	}
-	unlock_ns_list(ns);
 	up_read(&namespace_sem);
 
 	return is_covered;
@@ -1022,6 +1008,30 @@ void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct m
 	mnt_add_count(old_parent, -1);
 }
 
+static inline struct mount *node_to_mount(struct rb_node *node)
+{
+	return node ? rb_entry(node, struct mount, mnt_node) : NULL;
+}
+
+static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt)
+{
+	struct rb_node **link = &ns->mounts.rb_node;
+	struct rb_node *parent = NULL;
+
+	WARN_ON(mnt->mnt.mnt_flags & MNT_ONRB);
+	mnt->mnt_ns = ns;
+	while (*link) {
+		parent = *link;
+		if (mnt->mnt_id_unique < node_to_mount(parent)->mnt_id_unique)
+			link = &parent->rb_left;
+		else
+			link = &parent->rb_right;
+	}
+	rb_link_node(&mnt->mnt_node, parent, link);
+	rb_insert_color(&mnt->mnt_node, &ns->mounts);
+	mnt->mnt.mnt_flags |= MNT_ONRB;
+}
+
 /*
  * vfsmount lock must be held for write
  */
@@ -1035,12 +1045,13 @@ static void commit_tree(struct mount *mnt)
 	BUG_ON(parent == mnt);
 
 	list_add_tail(&head, &mnt->mnt_list);
-	list_for_each_entry(m, &head, mnt_list)
-		m->mnt_ns = n;
+	while (!list_empty(&head)) {
+		m = list_first_entry(&head, typeof(*m), mnt_list);
+		list_del(&m->mnt_list);
 
-	list_splice(&head, n->list.prev);
-
-	n->mounts += n->pending_mounts;
+		mnt_add_to_ns(n, m);
+	}
+	n->nr_mounts += n->pending_mounts;
 	n->pending_mounts = 0;
 
 	__attach_mnt(mnt, parent);
@@ -1188,7 +1199,7 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 	}
 
 	mnt->mnt.mnt_flags = old->mnt.mnt_flags;
-	mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL);
+	mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL|MNT_ONRB);
 
 	atomic_inc(&sb->s_active);
 	mnt->mnt.mnt_idmap = mnt_idmap_get(mnt_idmap(&old->mnt));
@@ -1413,65 +1424,57 @@ struct vfsmount *mnt_clone_internal(const struct path *path)
 	return &p->mnt;
 }
 
-#ifdef CONFIG_PROC_FS
-static struct mount *mnt_list_next(struct mnt_namespace *ns,
-				   struct list_head *p)
+/*
+ * Returns the mount which either has the specified mnt_id, or has the next
+ * smallest id afer the specified one.
+ */
+static struct mount *mnt_find_id_at(struct mnt_namespace *ns, u64 mnt_id)
 {
-	struct mount *mnt, *ret = NULL;
+	struct rb_node *node = ns->mounts.rb_node;
+	struct mount *ret = NULL;
 
-	lock_ns_list(ns);
-	list_for_each_continue(p, &ns->list) {
-		mnt = list_entry(p, typeof(*mnt), mnt_list);
-		if (!mnt_is_cursor(mnt)) {
-			ret = mnt;
-			break;
+	while (node) {
+		struct mount *m = node_to_mount(node);
+
+		if (mnt_id <= m->mnt_id_unique) {
+			ret = node_to_mount(node);
+			if (mnt_id == m->mnt_id_unique)
+				break;
+			node = node->rb_left;
+		} else {
+			node = node->rb_right;
 		}
 	}
-	unlock_ns_list(ns);
-
 	return ret;
 }
 
+#ifdef CONFIG_PROC_FS
+
 /* iterator; we want it to have access to namespace_sem, thus here... */
 static void *m_start(struct seq_file *m, loff_t *pos)
 {
 	struct proc_mounts *p = m->private;
-	struct list_head *prev;
 
 	down_read(&namespace_sem);
-	if (!*pos) {
-		prev = &p->ns->list;
-	} else {
-		prev = &p->cursor.mnt_list;
-
-		/* Read after we'd reached the end? */
-		if (list_empty(prev))
-			return NULL;
-	}
 
-	return mnt_list_next(p->ns, prev);
+	return mnt_find_id_at(p->ns, *pos);
 }
 
 static void *m_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct proc_mounts *p = m->private;
-	struct mount *mnt = v;
+	struct mount *next = NULL, *mnt = v;
+	struct rb_node *node = rb_next(&mnt->mnt_node);
 
 	++*pos;
-	return mnt_list_next(p->ns, &mnt->mnt_list);
+	if (node) {
+		next = node_to_mount(node);
+		*pos = next->mnt_id_unique;
+	}
+	return next;
 }
 
 static void m_stop(struct seq_file *m, void *v)
 {
-	struct proc_mounts *p = m->private;
-	struct mount *mnt = v;
-
-	lock_ns_list(p->ns);
-	if (mnt)
-		list_move_tail(&p->cursor.mnt_list, &mnt->mnt_list);
-	else
-		list_del_init(&p->cursor.mnt_list);
-	unlock_ns_list(p->ns);
 	up_read(&namespace_sem);
 }
 
@@ -1489,14 +1492,6 @@ const struct seq_operations mounts_op = {
 	.show	= m_show,
 };
 
-void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor)
-{
-	down_read(&namespace_sem);
-	lock_ns_list(ns);
-	list_del(&cursor->mnt_list);
-	unlock_ns_list(ns);
-	up_read(&namespace_sem);
-}
 #endif  /* CONFIG_PROC_FS */
 
 /**
@@ -1638,7 +1633,10 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
 	/* Gather the mounts to umount */
 	for (p = mnt; p; p = next_mnt(p, mnt)) {
 		p->mnt.mnt_flags |= MNT_UMOUNT;
-		list_move(&p->mnt_list, &tmp_list);
+		if (p->mnt.mnt_flags & MNT_ONRB)
+			move_from_ns(p, &tmp_list);
+		else
+			list_move(&p->mnt_list, &tmp_list);
 	}
 
 	/* Hide the mounts from mnt_mounts */
@@ -1658,7 +1656,7 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
 		list_del_init(&p->mnt_list);
 		ns = p->mnt_ns;
 		if (ns) {
-			ns->mounts--;
+			ns->nr_mounts--;
 			__touch_mnt_namespace(ns);
 		}
 		p->mnt_ns = NULL;
@@ -1784,14 +1782,16 @@ static int do_umount(struct mount *mnt, int flags)
 
 	event++;
 	if (flags & MNT_DETACH) {
-		if (!list_empty(&mnt->mnt_list))
+		if (mnt->mnt.mnt_flags & MNT_ONRB ||
+		    !list_empty(&mnt->mnt_list))
 			umount_tree(mnt, UMOUNT_PROPAGATE);
 		retval = 0;
 	} else {
 		shrink_submounts(mnt);
 		retval = -EBUSY;
 		if (!propagate_mount_busy(mnt, 2)) {
-			if (!list_empty(&mnt->mnt_list))
+			if (mnt->mnt.mnt_flags & MNT_ONRB ||
+			    !list_empty(&mnt->mnt_list))
 				umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC);
 			retval = 0;
 		}
@@ -2209,9 +2209,9 @@ int count_mounts(struct mnt_namespace *ns, struct mount *mnt)
 	unsigned int mounts = 0;
 	struct mount *p;
 
-	if (ns->mounts >= max)
+	if (ns->nr_mounts >= max)
 		return -ENOSPC;
-	max -= ns->mounts;
+	max -= ns->nr_mounts;
 	if (ns->pending_mounts >= max)
 		return -ENOSPC;
 	max -= ns->pending_mounts;
@@ -2355,8 +2355,12 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 		touch_mnt_namespace(source_mnt->mnt_ns);
 	} else {
 		if (source_mnt->mnt_ns) {
+			LIST_HEAD(head);
+
 			/* move from anon - the caller will destroy */
-			list_del_init(&source_mnt->mnt_ns->list);
+			for (p = source_mnt; p; p = next_mnt(p, source_mnt))
+				move_from_ns(p, &head);
+			list_del_init(&head);
 		}
 		if (beneath)
 			mnt_set_mountpoint_beneath(source_mnt, top_mnt, smp);
@@ -2667,11 +2671,10 @@ static struct file *open_detached_copy(struct path *path, bool recursive)
 
 	lock_mount_hash();
 	for (p = mnt; p; p = next_mnt(p, mnt)) {
-		p->mnt_ns = ns;
-		ns->mounts++;
+		mnt_add_to_ns(ns, p);
+		ns->nr_mounts++;
 	}
 	ns->root = mnt;
-	list_add_tail(&ns->list, &mnt->mnt_list);
 	mntget(&mnt->mnt);
 	unlock_mount_hash();
 	namespace_unlock();
@@ -2875,7 +2878,12 @@ static int do_remount(struct path *path, int ms_flags, int sb_flags,
 	if (IS_ERR(fc))
 		return PTR_ERR(fc);
 
+	/*
+	 * Indicate to the filesystem that the remount request is coming
+	 * from the legacy mount system call.
+	 */
 	fc->oldapi = true;
+
 	err = parse_monolithic_mount_data(fc, data);
 	if (!err) {
 		down_write(&sb->s_umount);
@@ -3026,6 +3034,7 @@ static inline bool path_overmounted(const struct path *path)
  * can_move_mount_beneath - check that we can mount beneath the top mount
  * @from: mount to mount beneath
  * @to:   mount under which to mount
+ * @mp:   mountpoint of @to
  *
  * - Make sure that @to->dentry is actually the root of a mount under
  *   which we can mount another mount.
@@ -3324,6 +3333,12 @@ static int do_new_mount(struct path *path, const char *fstype, int sb_flags,
 	if (IS_ERR(fc))
 		return PTR_ERR(fc);
 
+	/*
+	 * Indicate to the filesystem that the mount request is coming
+	 * from the legacy mount system call.
+	 */
+	fc->oldapi = true;
+
 	if (subtype)
 		err = vfs_parse_fs_string(fc, "subtype",
 					  subtype, strlen(subtype));
@@ -3734,9 +3749,8 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool a
 	if (!anon)
 		new_ns->seq = atomic64_add_return(1, &mnt_ns_seq);
 	refcount_set(&new_ns->ns.count, 1);
-	INIT_LIST_HEAD(&new_ns->list);
+	new_ns->mounts = RB_ROOT;
 	init_waitqueue_head(&new_ns->poll);
-	spin_lock_init(&new_ns->ns_lock);
 	new_ns->user_ns = get_user_ns(user_ns);
 	new_ns->ucounts = ucounts;
 	return new_ns;
@@ -3783,7 +3797,6 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
 		unlock_mount_hash();
 	}
 	new_ns->root = new;
-	list_add_tail(&new_ns->list, &new->mnt_list);
 
 	/*
 	 * Second pass: switch the tsk->fs->* elements and mark new vfsmounts
@@ -3793,8 +3806,8 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
 	p = old;
 	q = new;
 	while (p) {
-		q->mnt_ns = new_ns;
-		new_ns->mounts++;
+		mnt_add_to_ns(new_ns, q);
+		new_ns->nr_mounts++;
 		if (new_fs) {
 			if (&p->mnt == new_fs->root.mnt) {
 				new_fs->root.mnt = mntget(&q->mnt);
@@ -3836,10 +3849,9 @@ struct dentry *mount_subtree(struct vfsmount *m, const char *name)
 		mntput(m);
 		return ERR_CAST(ns);
 	}
-	mnt->mnt_ns = ns;
 	ns->root = mnt;
-	ns->mounts++;
-	list_add(&mnt->mnt_list, &ns->list);
+	ns->nr_mounts++;
+	mnt_add_to_ns(ns, mnt);
 
 	err = vfs_path_lookup(m->mnt_root, m,
 			name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path);
@@ -4017,10 +4029,9 @@ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags,
 		goto err_path;
 	}
 	mnt = real_mount(newmount.mnt);
-	mnt->mnt_ns = ns;
 	ns->root = mnt;
-	ns->mounts = 1;
-	list_add(&mnt->mnt_list, &ns->list);
+	ns->nr_mounts = 1;
+	mnt_add_to_ns(ns, mnt);
 	mntget(newmount.mnt);
 
 	/* Attach to an apparent O_PATH fd with a note that we need to unmount
@@ -4288,7 +4299,7 @@ static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt)
 	 * Creating an idmapped mount with the filesystem wide idmapping
 	 * doesn't make sense so block that. We don't allow mushy semantics.
 	 */
-	if (!check_fsmapping(kattr->mnt_idmap, m->mnt_sb))
+	if (kattr->mnt_userns == m->mnt_sb->s_user_ns)
 		return -EINVAL;
 
 	/*
@@ -4676,6 +4687,438 @@ SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path,
 	return err;
 }
 
+int show_path(struct seq_file *m, struct dentry *root)
+{
+	if (root->d_sb->s_op->show_path)
+		return root->d_sb->s_op->show_path(m, root);
+
+	seq_dentry(m, root, " \t\n\\");
+	return 0;
+}
+
+static struct vfsmount *lookup_mnt_in_ns(u64 id, struct mnt_namespace *ns)
+{
+	struct mount *mnt = mnt_find_id_at(ns, id);
+
+	if (!mnt || mnt->mnt_id_unique != id)
+		return NULL;
+
+	return &mnt->mnt;
+}
+
+struct kstatmount {
+	struct statmount __user *buf;
+	size_t bufsize;
+	struct vfsmount *mnt;
+	u64 mask;
+	struct path root;
+	struct statmount sm;
+	struct seq_file seq;
+};
+
+static u64 mnt_to_attr_flags(struct vfsmount *mnt)
+{
+	unsigned int mnt_flags = READ_ONCE(mnt->mnt_flags);
+	u64 attr_flags = 0;
+
+	if (mnt_flags & MNT_READONLY)
+		attr_flags |= MOUNT_ATTR_RDONLY;
+	if (mnt_flags & MNT_NOSUID)
+		attr_flags |= MOUNT_ATTR_NOSUID;
+	if (mnt_flags & MNT_NODEV)
+		attr_flags |= MOUNT_ATTR_NODEV;
+	if (mnt_flags & MNT_NOEXEC)
+		attr_flags |= MOUNT_ATTR_NOEXEC;
+	if (mnt_flags & MNT_NODIRATIME)
+		attr_flags |= MOUNT_ATTR_NODIRATIME;
+	if (mnt_flags & MNT_NOSYMFOLLOW)
+		attr_flags |= MOUNT_ATTR_NOSYMFOLLOW;
+
+	if (mnt_flags & MNT_NOATIME)
+		attr_flags |= MOUNT_ATTR_NOATIME;
+	else if (mnt_flags & MNT_RELATIME)
+		attr_flags |= MOUNT_ATTR_RELATIME;
+	else
+		attr_flags |= MOUNT_ATTR_STRICTATIME;
+
+	if (is_idmapped_mnt(mnt))
+		attr_flags |= MOUNT_ATTR_IDMAP;
+
+	return attr_flags;
+}
+
+static u64 mnt_to_propagation_flags(struct mount *m)
+{
+	u64 propagation = 0;
+
+	if (IS_MNT_SHARED(m))
+		propagation |= MS_SHARED;
+	if (IS_MNT_SLAVE(m))
+		propagation |= MS_SLAVE;
+	if (IS_MNT_UNBINDABLE(m))
+		propagation |= MS_UNBINDABLE;
+	if (!propagation)
+		propagation |= MS_PRIVATE;
+
+	return propagation;
+}
+
+static void statmount_sb_basic(struct kstatmount *s)
+{
+	struct super_block *sb = s->mnt->mnt_sb;
+
+	s->sm.mask |= STATMOUNT_SB_BASIC;
+	s->sm.sb_dev_major = MAJOR(sb->s_dev);
+	s->sm.sb_dev_minor = MINOR(sb->s_dev);
+	s->sm.sb_magic = sb->s_magic;
+	s->sm.sb_flags = sb->s_flags & (SB_RDONLY|SB_SYNCHRONOUS|SB_DIRSYNC|SB_LAZYTIME);
+}
+
+static void statmount_mnt_basic(struct kstatmount *s)
+{
+	struct mount *m = real_mount(s->mnt);
+
+	s->sm.mask |= STATMOUNT_MNT_BASIC;
+	s->sm.mnt_id = m->mnt_id_unique;
+	s->sm.mnt_parent_id = m->mnt_parent->mnt_id_unique;
+	s->sm.mnt_id_old = m->mnt_id;
+	s->sm.mnt_parent_id_old = m->mnt_parent->mnt_id;
+	s->sm.mnt_attr = mnt_to_attr_flags(&m->mnt);
+	s->sm.mnt_propagation = mnt_to_propagation_flags(m);
+	s->sm.mnt_peer_group = IS_MNT_SHARED(m) ? m->mnt_group_id : 0;
+	s->sm.mnt_master = IS_MNT_SLAVE(m) ? m->mnt_master->mnt_group_id : 0;
+}
+
+static void statmount_propagate_from(struct kstatmount *s)
+{
+	struct mount *m = real_mount(s->mnt);
+
+	s->sm.mask |= STATMOUNT_PROPAGATE_FROM;
+	if (IS_MNT_SLAVE(m))
+		s->sm.propagate_from = get_dominating_id(m, &current->fs->root);
+}
+
+static int statmount_mnt_root(struct kstatmount *s, struct seq_file *seq)
+{
+	int ret;
+	size_t start = seq->count;
+
+	ret = show_path(seq, s->mnt->mnt_root);
+	if (ret)
+		return ret;
+
+	if (unlikely(seq_has_overflowed(seq)))
+		return -EAGAIN;
+
+	/*
+         * Unescape the result. It would be better if supplied string was not
+         * escaped in the first place, but that's a pretty invasive change.
+         */
+	seq->buf[seq->count] = '\0';
+	seq->count = start;
+	seq_commit(seq, string_unescape_inplace(seq->buf + start, UNESCAPE_OCTAL));
+	return 0;
+}
+
+static int statmount_mnt_point(struct kstatmount *s, struct seq_file *seq)
+{
+	struct vfsmount *mnt = s->mnt;
+	struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
+	int err;
+
+	err = seq_path_root(seq, &mnt_path, &s->root, "");
+	return err == SEQ_SKIP ? 0 : err;
+}
+
+static int statmount_fs_type(struct kstatmount *s, struct seq_file *seq)
+{
+	struct super_block *sb = s->mnt->mnt_sb;
+
+	seq_puts(seq, sb->s_type->name);
+	return 0;
+}
+
+static int statmount_string(struct kstatmount *s, u64 flag)
+{
+	int ret;
+	size_t kbufsize;
+	struct seq_file *seq = &s->seq;
+	struct statmount *sm = &s->sm;
+
+	switch (flag) {
+	case STATMOUNT_FS_TYPE:
+		sm->fs_type = seq->count;
+		ret = statmount_fs_type(s, seq);
+		break;
+	case STATMOUNT_MNT_ROOT:
+		sm->mnt_root = seq->count;
+		ret = statmount_mnt_root(s, seq);
+		break;
+	case STATMOUNT_MNT_POINT:
+		sm->mnt_point = seq->count;
+		ret = statmount_mnt_point(s, seq);
+		break;
+	default:
+		WARN_ON_ONCE(true);
+		return -EINVAL;
+	}
+
+	if (unlikely(check_add_overflow(sizeof(*sm), seq->count, &kbufsize)))
+		return -EOVERFLOW;
+	if (kbufsize >= s->bufsize)
+		return -EOVERFLOW;
+
+	/* signal a retry */
+	if (unlikely(seq_has_overflowed(seq)))
+		return -EAGAIN;
+
+	if (ret)
+		return ret;
+
+	seq->buf[seq->count++] = '\0';
+	sm->mask |= flag;
+	return 0;
+}
+
+static int copy_statmount_to_user(struct kstatmount *s)
+{
+	struct statmount *sm = &s->sm;
+	struct seq_file *seq = &s->seq;
+	char __user *str = ((char __user *)s->buf) + sizeof(*sm);
+	size_t copysize = min_t(size_t, s->bufsize, sizeof(*sm));
+
+	if (seq->count && copy_to_user(str, seq->buf, seq->count))
+		return -EFAULT;
+
+	/* Return the number of bytes copied to the buffer */
+	sm->size = copysize + seq->count;
+	if (copy_to_user(s->buf, sm, copysize))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int do_statmount(struct kstatmount *s)
+{
+	struct mount *m = real_mount(s->mnt);
+	int err;
+
+	/*
+	 * Don't trigger audit denials. We just want to determine what
+	 * mounts to show users.
+	 */
+	if (!is_path_reachable(m, m->mnt.mnt_root, &s->root) &&
+	    !ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	err = security_sb_statfs(s->mnt->mnt_root);
+	if (err)
+		return err;
+
+	if (s->mask & STATMOUNT_SB_BASIC)
+		statmount_sb_basic(s);
+
+	if (s->mask & STATMOUNT_MNT_BASIC)
+		statmount_mnt_basic(s);
+
+	if (s->mask & STATMOUNT_PROPAGATE_FROM)
+		statmount_propagate_from(s);
+
+	if (s->mask & STATMOUNT_FS_TYPE)
+		err = statmount_string(s, STATMOUNT_FS_TYPE);
+
+	if (!err && s->mask & STATMOUNT_MNT_ROOT)
+		err = statmount_string(s, STATMOUNT_MNT_ROOT);
+
+	if (!err && s->mask & STATMOUNT_MNT_POINT)
+		err = statmount_string(s, STATMOUNT_MNT_POINT);
+
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static inline bool retry_statmount(const long ret, size_t *seq_size)
+{
+	if (likely(ret != -EAGAIN))
+		return false;
+	if (unlikely(check_mul_overflow(*seq_size, 2, seq_size)))
+		return false;
+	if (unlikely(*seq_size > MAX_RW_COUNT))
+		return false;
+	return true;
+}
+
+static int prepare_kstatmount(struct kstatmount *ks, struct mnt_id_req *kreq,
+			      struct statmount __user *buf, size_t bufsize,
+			      size_t seq_size)
+{
+	if (!access_ok(buf, bufsize))
+		return -EFAULT;
+
+	memset(ks, 0, sizeof(*ks));
+	ks->mask = kreq->param;
+	ks->buf = buf;
+	ks->bufsize = bufsize;
+	ks->seq.size = seq_size;
+	ks->seq.buf = kvmalloc(seq_size, GFP_KERNEL_ACCOUNT);
+	if (!ks->seq.buf)
+		return -ENOMEM;
+	return 0;
+}
+
+static int copy_mnt_id_req(const struct mnt_id_req __user *req,
+			   struct mnt_id_req *kreq)
+{
+	int ret;
+	size_t usize;
+
+	BUILD_BUG_ON(sizeof(struct mnt_id_req) != MNT_ID_REQ_SIZE_VER0);
+
+	ret = get_user(usize, &req->size);
+	if (ret)
+		return -EFAULT;
+	if (unlikely(usize > PAGE_SIZE))
+		return -E2BIG;
+	if (unlikely(usize < MNT_ID_REQ_SIZE_VER0))
+		return -EINVAL;
+	memset(kreq, 0, sizeof(*kreq));
+	ret = copy_struct_from_user(kreq, sizeof(*kreq), req, usize);
+	if (ret)
+		return ret;
+	if (kreq->spare != 0)
+		return -EINVAL;
+	return 0;
+}
+
+SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req,
+		struct statmount __user *, buf, size_t, bufsize,
+		unsigned int, flags)
+{
+	struct vfsmount *mnt;
+	struct mnt_id_req kreq;
+	struct kstatmount ks;
+	/* We currently support retrieval of 3 strings. */
+	size_t seq_size = 3 * PATH_MAX;
+	int ret;
+
+	if (flags)
+		return -EINVAL;
+
+	ret = copy_mnt_id_req(req, &kreq);
+	if (ret)
+		return ret;
+
+retry:
+	ret = prepare_kstatmount(&ks, &kreq, buf, bufsize, seq_size);
+	if (ret)
+		return ret;
+
+	down_read(&namespace_sem);
+	mnt = lookup_mnt_in_ns(kreq.mnt_id, current->nsproxy->mnt_ns);
+	if (!mnt) {
+		up_read(&namespace_sem);
+		kvfree(ks.seq.buf);
+		return -ENOENT;
+	}
+
+	ks.mnt = mnt;
+	get_fs_root(current->fs, &ks.root);
+	ret = do_statmount(&ks);
+	path_put(&ks.root);
+	up_read(&namespace_sem);
+
+	if (!ret)
+		ret = copy_statmount_to_user(&ks);
+	kvfree(ks.seq.buf);
+	if (retry_statmount(ret, &seq_size))
+		goto retry;
+	return ret;
+}
+
+static struct mount *listmnt_next(struct mount *curr)
+{
+	return node_to_mount(rb_next(&curr->mnt_node));
+}
+
+static ssize_t do_listmount(struct mount *first, struct path *orig, u64 mnt_id,
+			    u64 __user *buf, size_t bufsize,
+			    const struct path *root)
+{
+	struct mount *r;
+	ssize_t ctr;
+	int err;
+
+	/*
+	 * Don't trigger audit denials. We just want to determine what
+	 * mounts to show users.
+	 */
+	if (!is_path_reachable(real_mount(orig->mnt), orig->dentry, root) &&
+	    !ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	err = security_sb_statfs(orig->dentry);
+	if (err)
+		return err;
+
+	for (ctr = 0, r = first; r && ctr < bufsize; r = listmnt_next(r)) {
+		if (r->mnt_id_unique == mnt_id)
+			continue;
+		if (!is_path_reachable(r, r->mnt.mnt_root, orig))
+			continue;
+		ctr = array_index_nospec(ctr, bufsize);
+		if (put_user(r->mnt_id_unique, buf + ctr))
+			return -EFAULT;
+		if (check_add_overflow(ctr, 1, &ctr))
+			return -ERANGE;
+	}
+	return ctr;
+}
+
+SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req,
+		u64 __user *, buf, size_t, bufsize, unsigned int, flags)
+{
+	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
+	struct mnt_id_req kreq;
+	struct mount *first;
+	struct path root, orig;
+	u64 mnt_id, last_mnt_id;
+	ssize_t ret;
+
+	if (flags)
+		return -EINVAL;
+
+	ret = copy_mnt_id_req(req, &kreq);
+	if (ret)
+		return ret;
+	mnt_id = kreq.mnt_id;
+	last_mnt_id = kreq.param;
+
+	down_read(&namespace_sem);
+	get_fs_root(current->fs, &root);
+	if (mnt_id == LSMT_ROOT) {
+		orig = root;
+	} else {
+		ret = -ENOENT;
+		orig.mnt  = lookup_mnt_in_ns(mnt_id, ns);
+		if (!orig.mnt)
+			goto err;
+		orig.dentry = orig.mnt->mnt_root;
+	}
+	if (!last_mnt_id)
+		first = node_to_mount(rb_first(&ns->mounts));
+	else
+		first = mnt_find_id_at(ns, last_mnt_id + 1);
+
+	ret = do_listmount(first, &orig, mnt_id, buf, bufsize, &root);
+err:
+	path_put(&root);
+	up_read(&namespace_sem);
+	return ret;
+}
+
+
 static void __init init_mount_tree(void)
 {
 	struct vfsmount *mnt;
@@ -4691,10 +5134,9 @@ static void __init init_mount_tree(void)
 	if (IS_ERR(ns))
 		panic("Can't allocate initial namespace");
 	m = real_mount(mnt);
-	m->mnt_ns = ns;
 	ns->root = m;
-	ns->mounts = 1;
-	list_add(&m->mnt_list, &ns->list);
+	ns->nr_mounts = 1;
+	mnt_add_to_ns(ns, m);
 	init_task.nsproxy->mnt_ns = ns;
 	get_mnt_ns(ns);
 
@@ -4821,18 +5263,14 @@ static bool mnt_already_visible(struct mnt_namespace *ns,
 				int *new_mnt_flags)
 {
 	int new_flags = *new_mnt_flags;
-	struct mount *mnt;
+	struct mount *mnt, *n;
 	bool visible = false;
 
 	down_read(&namespace_sem);
-	lock_ns_list(ns);
-	list_for_each_entry(mnt, &ns->list, mnt_list) {
+	rbtree_postorder_for_each_entry_safe(mnt, n, &ns->mounts, mnt_node) {
 		struct mount *child;
 		int mnt_flags;
 
-		if (mnt_is_cursor(mnt))
-			continue;
-
 		if (mnt->mnt.mnt_sb->s_type != sb->s_type)
 			continue;
 
@@ -4880,7 +5318,6 @@ static bool mnt_already_visible(struct mnt_namespace *ns,
 	next:	;
 	}
 found:
-	unlock_ns_list(ns);
 	up_read(&namespace_sem);
 	return visible;
 }
@@ -5010,7 +5447,6 @@ static struct ctl_table fs_namespace_sysctls[] = {
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ONE,
 	},
-	{ }
 };
 
 static int __init init_fs_namespace_sysctls(void)
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 943aeea1eb16..6be13e0ec170 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -580,6 +580,8 @@ retry:
 		nfs4_delete_deviceid(node->ld, node->nfs_client, id);
 		goto retry;
 	}
+
+	nfs4_put_deviceid_node(node);
 	return ERR_PTR(-ENODEV);
 }
 
@@ -893,10 +895,9 @@ bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 	}
 
 	if (pgio->pg_dreq == NULL)
-		wb_size = pnfs_num_cont_bytes(pgio->pg_inode,
-					      req->wb_index);
+		wb_size = pnfs_num_cont_bytes(pgio->pg_inode, req->wb_index);
 	else
-		wb_size = nfs_dreq_bytes_left(pgio->pg_dreq);
+		wb_size = nfs_dreq_bytes_left(pgio->pg_dreq, req_offset(req));
 
 	pnfs_generic_pg_init_write(pgio, req, wb_size);
 
diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c
index f318a05a80e1..c97ebc42ec0f 100644
--- a/fs/nfs/blocklayout/dev.c
+++ b/fs/nfs/blocklayout/dev.c
@@ -351,6 +351,9 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
 	d->map = bl_map_simple;
 	d->pr_key = v->scsi.pr_key;
 
+	if (d->len == 0)
+		return -ENODEV;
+
 	pr_info("pNFS: using block device %s (reservation key 0x%llx)\n",
 		d->bdev_handle->bdev->bd_disk->disk_name, d->pr_key);
 
diff --git a/fs/nfs/blocklayout/rpc_pipefs.c b/fs/nfs/blocklayout/rpc_pipefs.c
index 6c977288cc28..d8d50a88de04 100644
--- a/fs/nfs/blocklayout/rpc_pipefs.c
+++ b/fs/nfs/blocklayout/rpc_pipefs.c
@@ -75,7 +75,7 @@ bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b,
 	msg->len = sizeof(*bl_msg) + b->simple.len;
 	msg->data = kzalloc(msg->len, gfp_mask);
 	if (!msg->data)
-		goto out_free_data;
+		goto out_unlock;
 
 	bl_msg = msg->data;
 	bl_msg->type = BL_DEVICE_MOUNT;
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 4ffa1f469e90..760d27dd7225 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -187,7 +187,7 @@ static struct svc_serv *nfs_callback_create_svc(int minorversion)
 	 * Check whether we're already up and running.
 	 */
 	if (cb_info->serv)
-		return svc_get(cb_info->serv);
+		return cb_info->serv;
 
 	/*
 	 * Sanity check: if there's no task,
@@ -245,9 +245,10 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt)
 
 	cb_info->users++;
 err_net:
-	if (!cb_info->users)
-		cb_info->serv = NULL;
-	svc_put(serv);
+	if (!cb_info->users) {
+		svc_set_num_threads(cb_info->serv, NULL, 0);
+		svc_destroy(&cb_info->serv);
+	}
 err_create:
 	mutex_unlock(&nfs_callback_mutex);
 	return ret;
@@ -271,11 +272,9 @@ void nfs_callback_down(int minorversion, struct net *net)
 	nfs_callback_down_net(minorversion, serv, net);
 	cb_info->users--;
 	if (cb_info->users == 0) {
-		svc_get(serv);
 		svc_set_num_threads(serv, NULL, 0);
-		svc_put(serv);
 		dprintk("nfs_callback_down: service destroyed\n");
-		cb_info->serv = NULL;
+		svc_destroy(&cb_info->serv);
 	}
 	mutex_unlock(&nfs_callback_mutex);
 }
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index ccd4f245cae2..650758ee0d5f 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -19,32 +19,14 @@ enum nfs4_callback_procnum {
 	CB_COMPOUND = 1,
 };
 
-enum nfs4_callback_opnum {
-	OP_CB_GETATTR = 3,
-	OP_CB_RECALL  = 4,
-/* Callback operations new to NFSv4.1 */
-	OP_CB_LAYOUTRECALL  = 5,
-	OP_CB_NOTIFY        = 6,
-	OP_CB_PUSH_DELEG    = 7,
-	OP_CB_RECALL_ANY    = 8,
-	OP_CB_RECALLABLE_OBJ_AVAIL = 9,
-	OP_CB_RECALL_SLOT   = 10,
-	OP_CB_SEQUENCE      = 11,
-	OP_CB_WANTS_CANCELLED = 12,
-	OP_CB_NOTIFY_LOCK   = 13,
-	OP_CB_NOTIFY_DEVICEID = 14,
-/* Callback operations new to NFSv4.2 */
-	OP_CB_OFFLOAD = 15,
-	OP_CB_ILLEGAL = 10044,
-};
-
 struct nfs4_slot;
 struct cb_process_state {
-	__be32			drc_status;
 	struct nfs_client	*clp;
 	struct nfs4_slot	*slot;
-	u32			minorversion;
 	struct net		*net;
+	u32			minorversion;
+	__be32			drc_status;
+	unsigned int		referring_calls;
 };
 
 struct cb_compound_hdr_arg {
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 96a4923080ae..76cea34477ae 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -207,7 +207,8 @@ static struct inode *nfs_layout_find_inode(struct nfs_client *clp,
  * Enforce RFC5661 section 12.5.5.2.1. (Layout Recall and Return Sequencing)
  */
 static u32 pnfs_check_callback_stateid(struct pnfs_layout_hdr *lo,
-					const nfs4_stateid *new)
+					const nfs4_stateid *new,
+					struct cb_process_state *cps)
 {
 	u32 oldseq, newseq;
 
@@ -221,28 +222,29 @@ static u32 pnfs_check_callback_stateid(struct pnfs_layout_hdr *lo,
 
 	newseq = be32_to_cpu(new->seqid);
 	/* Are we already in a layout recall situation? */
-	if (test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags) &&
-	    lo->plh_return_seq != 0) {
-		if (newseq < lo->plh_return_seq)
-			return NFS4ERR_OLD_STATEID;
-		if (newseq > lo->plh_return_seq)
-			return NFS4ERR_DELAY;
-		goto out;
-	}
+	if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
+		return NFS4ERR_DELAY;
 
-	/* Check that the stateid matches what we think it should be. */
+	/*
+	 * Check that the stateid matches what we think it should be.
+	 * Note that if the server sent us a list of referring calls,
+	 * and we know that those have completed, then we trust the
+	 * stateid argument is correct.
+	 */
 	oldseq = be32_to_cpu(lo->plh_stateid.seqid);
-	if (newseq > oldseq + 1)
+	if (newseq > oldseq + 1 && !cps->referring_calls)
 		return NFS4ERR_DELAY;
+
 	/* Crazy server! */
 	if (newseq <= oldseq)
 		return NFS4ERR_OLD_STATEID;
-out:
+
 	return NFS_OK;
 }
 
 static u32 initiate_file_draining(struct nfs_client *clp,
-				  struct cb_layoutrecallargs *args)
+				  struct cb_layoutrecallargs *args,
+				  struct cb_process_state *cps)
 {
 	struct inode *ino;
 	struct pnfs_layout_hdr *lo;
@@ -266,7 +268,7 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 		goto out;
 	}
 	pnfs_get_layout_hdr(lo);
-	rv = pnfs_check_callback_stateid(lo, &args->cbl_stateid);
+	rv = pnfs_check_callback_stateid(lo, &args->cbl_stateid, cps);
 	if (rv != NFS_OK)
 		goto unlock;
 
@@ -326,10 +328,11 @@ static u32 initiate_bulk_draining(struct nfs_client *clp,
 }
 
 static u32 do_callback_layoutrecall(struct nfs_client *clp,
-				    struct cb_layoutrecallargs *args)
+				    struct cb_layoutrecallargs *args,
+				    struct cb_process_state *cps)
 {
 	if (args->cbl_recall_type == RETURN_FILE)
-		return initiate_file_draining(clp, args);
+		return initiate_file_draining(clp, args, cps);
 	return initiate_bulk_draining(clp, args);
 }
 
@@ -340,11 +343,12 @@ __be32 nfs4_callback_layoutrecall(void *argp, void *resp,
 	u32 res = NFS4ERR_OP_NOT_IN_SESSION;
 
 	if (cps->clp)
-		res = do_callback_layoutrecall(cps->clp, args);
+		res = do_callback_layoutrecall(cps->clp, args, cps);
 	return cpu_to_be32(res);
 }
 
-static void pnfs_recall_all_layouts(struct nfs_client *clp)
+static void pnfs_recall_all_layouts(struct nfs_client *clp,
+				    struct cb_process_state *cps)
 {
 	struct cb_layoutrecallargs args;
 
@@ -352,7 +356,7 @@ static void pnfs_recall_all_layouts(struct nfs_client *clp)
 	memset(&args, 0, sizeof(args));
 	args.cbl_recall_type = RETURN_ALL;
 	/* FIXME we ignore errors, what should we do? */
-	do_callback_layoutrecall(clp, &args);
+	do_callback_layoutrecall(clp, &args, cps);
 }
 
 __be32 nfs4_callback_devicenotify(void *argp, void *resp,
@@ -450,6 +454,7 @@ static int referring_call_exists(struct nfs_client *clp,
 	__acquires(lock)
 {
 	int status = 0;
+	int found = 0;
 	int i, j;
 	struct nfs4_session *session;
 	struct nfs4_slot_table *tbl;
@@ -478,11 +483,12 @@ static int referring_call_exists(struct nfs_client *clp,
 			spin_lock(lock);
 			if (status)
 				goto out;
+			found++;
 		}
 	}
 
 out:
-	return status;
+	return status < 0 ? status : found;
 }
 
 __be32 nfs4_callback_sequence(void *argp, void *resp,
@@ -493,6 +499,7 @@ __be32 nfs4_callback_sequence(void *argp, void *resp,
 	struct nfs4_slot_table *tbl;
 	struct nfs4_slot *slot;
 	struct nfs_client *clp;
+	int ret;
 	int i;
 	__be32 status = htonl(NFS4ERR_BADSESSION);
 
@@ -552,11 +559,13 @@ __be32 nfs4_callback_sequence(void *argp, void *resp,
 	 * related callback was received before the response to the original
 	 * call.
 	 */
-	if (referring_call_exists(clp, args->csa_nrclists, args->csa_rclists,
-				&tbl->slot_tbl_lock) < 0) {
+	ret = referring_call_exists(clp, args->csa_nrclists, args->csa_rclists,
+				    &tbl->slot_tbl_lock);
+	if (ret < 0) {
 		status = htonl(NFS4ERR_DELAY);
 		goto out_unlock;
 	}
+	cps->referring_calls = ret;
 
 	/*
 	 * RFC5661 20.9.3
@@ -617,7 +626,7 @@ __be32 nfs4_callback_recallany(void *argp, void *resp,
 		nfs_expire_unused_delegation_types(cps->clp, flags);
 
 	if (args->craa_type_mask & BIT(RCA4_TYPE_MASK_FILE_LAYOUT))
-		pnfs_recall_all_layouts(cps->clp);
+		pnfs_recall_all_layouts(cps->clp, cps);
 
 	if (args->craa_type_mask & BIT(PNFS_FF_RCA4_TYPE_MASK_READ)) {
 		set_bit(NFS4CLNT_RECALL_ANY_LAYOUT_READ, &cps->clp->cl_state);
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 321af81c456e..9369488f2ed4 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -967,6 +967,11 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp)
 		nops--;
 	}
 
+	if (svc_is_backchannel(rqstp) && cps.clp) {
+		rqstp->bc_to_initval = cps.clp->cl_rpcclient->cl_timeout->to_initval;
+		rqstp->bc_to_retries = cps.clp->cl_rpcclient->cl_timeout->to_retries;
+	}
+
 	*hdr_res.status = status;
 	*hdr_res.nops = htonl(nops);
 	nfs4_cb_free_slot(&cps);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 13dffe4201e6..c8ecbe999059 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2194,6 +2194,8 @@ nfs4_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
 {
 	struct inode *inode;
 
+	trace_nfs_lookup_revalidate_enter(dir, dentry, flags);
+
 	if (!(flags & LOOKUP_OPEN) || (flags & LOOKUP_DIRECTORY))
 		goto full_reval;
 	if (d_mountpoint(dentry))
@@ -2963,7 +2965,7 @@ static u64 nfs_access_login_time(const struct task_struct *task,
 	rcu_read_lock();
 	for (;;) {
 		parent = rcu_dereference(task->real_parent);
-		pcred = rcu_dereference(parent->cred);
+		pcred = __task_cred(parent);
 		if (parent == task || cred_fscmp(pcred, cred) != 0)
 			break;
 		task = parent;
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index f6c74f424691..c03926a1cc73 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -205,9 +205,10 @@ static void nfs_direct_req_release(struct nfs_direct_req *dreq)
 	kref_put(&dreq->kref, nfs_direct_req_free);
 }
 
-ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq)
+ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq, loff_t offset)
 {
-	return dreq->bytes_left;
+	loff_t start = offset - dreq->io_start;
+	return dreq->max_count - start;
 }
 EXPORT_SYMBOL_GPL(nfs_dreq_bytes_left);
 
@@ -368,7 +369,6 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 			bytes -= req_len;
 			requested_bytes += req_len;
 			pos += req_len;
-			dreq->bytes_left -= req_len;
 		}
 		nfs_direct_release_pages(pagevec, npages);
 		kvfree(pagevec);
@@ -440,7 +440,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
 		goto out;
 
 	dreq->inode = inode;
-	dreq->bytes_left = dreq->max_count = count;
+	dreq->max_count = count;
 	dreq->io_start = iocb->ki_pos;
 	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
 	l_ctx = nfs_get_lock_context(dreq->ctx);
@@ -873,7 +873,6 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 			bytes -= req_len;
 			requested_bytes += req_len;
 			pos += req_len;
-			dreq->bytes_left -= req_len;
 
 			if (defer) {
 				nfs_mark_request_commit(req, NULL, &cinfo, 0);
@@ -980,7 +979,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter,
 		goto out;
 
 	dreq->inode = inode;
-	dreq->bytes_left = dreq->max_count = count;
+	dreq->max_count = count;
 	dreq->io_start = pos;
 	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
 	l_ctx = nfs_get_lock_context(dreq->ctx);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 3f9768810427..8577ccf621f5 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -558,7 +558,6 @@ const struct address_space_operations nfs_file_aops = {
 	.read_folio = nfs_read_folio,
 	.readahead = nfs_readahead,
 	.dirty_folio = filemap_dirty_folio,
-	.writepage = nfs_writepage,
 	.writepages = nfs_writepages,
 	.write_begin = nfs_write_begin,
 	.write_end = nfs_write_end,
@@ -567,7 +566,7 @@ const struct address_space_operations nfs_file_aops = {
 	.migrate_folio = nfs_migrate_folio,
 	.launder_folio = nfs_launder_folio,
 	.is_dirty_writeback = nfs_check_dirty_writeback,
-	.error_remove_page = generic_error_remove_page,
+	.error_remove_folio = generic_error_remove_folio,
 	.swap_activate = nfs_swap_activate,
 	.swap_deactivate = nfs_swap_deactivate,
 	.swap_rw = nfs_swap_rw,
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 9c9cf764f600..e3722ce6722e 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -655,7 +655,7 @@ extern int nfs_sillyrename(struct inode *dir, struct dentry *dentry);
 /* direct.c */
 void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo,
 			      struct nfs_direct_req *dreq);
-extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq);
+extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq, loff_t offset);
 
 /* nfs4proc.c */
 extern struct nfs_client *nfs4_init_client(struct nfs_client *clp,
@@ -936,7 +936,6 @@ struct nfs_direct_req {
 	loff_t			io_start;	/* Start offset for I/O */
 	ssize_t			count,		/* bytes actually processed */
 				max_count,	/* max expected count */
-				bytes_left,	/* bytes left to be sent */
 				error;		/* any reported error */
 	struct completion	completion;	/* wait for i/o completion */
 
diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c
index 2ad66a8922f4..49aaf28a6950 100644
--- a/fs/nfs/nfs42xattr.c
+++ b/fs/nfs/nfs42xattr.c
@@ -132,7 +132,7 @@ nfs4_xattr_entry_lru_add(struct nfs4_xattr_entry *entry)
 	lru = (entry->flags & NFS4_XATTR_ENTRY_EXTVAL) ?
 	    &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru;
 
-	return list_lru_add(lru, &entry->lru);
+	return list_lru_add_obj(lru, &entry->lru);
 }
 
 static bool
@@ -143,7 +143,7 @@ nfs4_xattr_entry_lru_del(struct nfs4_xattr_entry *entry)
 	lru = (entry->flags & NFS4_XATTR_ENTRY_EXTVAL) ?
 	    &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru;
 
-	return list_lru_del(lru, &entry->lru);
+	return list_lru_del_obj(lru, &entry->lru);
 }
 
 /*
@@ -349,7 +349,7 @@ nfs4_xattr_cache_unlink(struct inode *inode)
 
 	oldcache = nfsi->xattr_cache;
 	if (oldcache != NULL) {
-		list_lru_del(&nfs4_xattr_cache_lru, &oldcache->lru);
+		list_lru_del_obj(&nfs4_xattr_cache_lru, &oldcache->lru);
 		oldcache->inode = NULL;
 	}
 	nfsi->xattr_cache = NULL;
@@ -474,7 +474,7 @@ nfs4_xattr_get_cache(struct inode *inode, int add)
 			kref_get(&cache->ref);
 			nfsi->xattr_cache = cache;
 			cache->inode = inode;
-			list_lru_add(&nfs4_xattr_cache_lru, &cache->lru);
+			list_lru_add_obj(&nfs4_xattr_cache_lru, &cache->lru);
 		}
 
 		spin_unlock(&inode->i_lock);
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 02788c3c85e5..e238abc78a13 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -10,6 +10,7 @@
 #include <linux/mount.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs_ssc.h>
+#include <linux/splice.h>
 #include "delegation.h"
 #include "internal.h"
 #include "iostat.h"
@@ -195,8 +196,8 @@ static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
 	ret = __nfs4_copy_file_range(file_in, pos_in, file_out, pos_out, count,
 				     flags);
 	if (ret == -EOPNOTSUPP || ret == -EXDEV)
-		ret = generic_copy_file_range(file_in, pos_in, file_out,
-					      pos_out, count, flags);
+		ret = splice_copy_file_range(file_in, pos_in, file_out,
+					     pos_out, count);
 	return ret;
 }
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 8a943fffaad5..23819a756508 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -170,6 +170,7 @@ static int nfs4_map_errors(int err)
 	case -NFS4ERR_RESOURCE:
 	case -NFS4ERR_LAYOUTTRYLATER:
 	case -NFS4ERR_RECALLCONFLICT:
+	case -NFS4ERR_RETURNCONFLICT:
 		return -EREMOTEIO;
 	case -NFS4ERR_WRONGSEC:
 	case -NFS4ERR_WRONG_CRED:
@@ -558,6 +559,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server,
 		case -NFS4ERR_GRACE:
 		case -NFS4ERR_LAYOUTTRYLATER:
 		case -NFS4ERR_RECALLCONFLICT:
+		case -NFS4ERR_RETURNCONFLICT:
 			exception->delay = 1;
 			return 0;
 
@@ -9691,6 +9693,7 @@ nfs4_layoutget_handle_exception(struct rpc_task *task,
 		status = -EBUSY;
 		break;
 	case -NFS4ERR_RECALLCONFLICT:
+	case -NFS4ERR_RETURNCONFLICT:
 		status = -ERECALLCONFLICT;
 		break;
 	case -NFS4ERR_DELEG_REVOKED:
diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c
index e776200e9a11..886a7c4c60b3 100644
--- a/fs/nfs/nfs4sysctl.c
+++ b/fs/nfs/nfs4sysctl.c
@@ -34,7 +34,6 @@ static struct ctl_table nfs4_cb_sysctls[] = {
 		.mode = 0644,
 		.proc_handler = proc_dointvec,
 	},
-	{ }
 };
 
 int nfs4_register_sysctl(void)
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index deec76cf5afe..69406e60f391 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1602,7 +1602,8 @@ static void encode_read(struct xdr_stream *xdr, const struct nfs_pgio_args *args
 static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg *readdir, struct rpc_rqst *req, struct compound_hdr *hdr)
 {
 	uint32_t attrs[3] = {
-		FATTR4_WORD0_RDATTR_ERROR,
+		FATTR4_WORD0_TYPE
+		| FATTR4_WORD0_RDATTR_ERROR,
 		FATTR4_WORD1_MOUNTED_ON_FILEID,
 	};
 	uint32_t dircount = readdir->count;
@@ -1612,12 +1613,20 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg
 	unsigned int i;
 
 	if (readdir->plus) {
-		attrs[0] |= FATTR4_WORD0_TYPE|FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE|
-			FATTR4_WORD0_FSID|FATTR4_WORD0_FILEHANDLE|FATTR4_WORD0_FILEID;
-		attrs[1] |= FATTR4_WORD1_MODE|FATTR4_WORD1_NUMLINKS|FATTR4_WORD1_OWNER|
-			FATTR4_WORD1_OWNER_GROUP|FATTR4_WORD1_RAWDEV|
-			FATTR4_WORD1_SPACE_USED|FATTR4_WORD1_TIME_ACCESS|
-			FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY;
+		attrs[0] |= FATTR4_WORD0_CHANGE
+			| FATTR4_WORD0_SIZE
+			| FATTR4_WORD0_FSID
+			| FATTR4_WORD0_FILEHANDLE
+			| FATTR4_WORD0_FILEID;
+		attrs[1] |= FATTR4_WORD1_MODE
+			| FATTR4_WORD1_NUMLINKS
+			| FATTR4_WORD1_OWNER
+			| FATTR4_WORD1_OWNER_GROUP
+			| FATTR4_WORD1_RAWDEV
+			| FATTR4_WORD1_SPACE_USED
+			| FATTR4_WORD1_TIME_ACCESS
+			| FATTR4_WORD1_TIME_METADATA
+			| FATTR4_WORD1_TIME_MODIFY;
 		attrs[2] |= FATTR4_WORD2_SECURITY_LABEL;
 	}
 	/* Use mounted_on_fileid only if the server supports it */
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 4e90ca531176..afedb449b54f 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -400,6 +400,7 @@ DECLARE_EVENT_CLASS(nfs_lookup_event,
 			__field(unsigned long, flags)
 			__field(dev_t, dev)
 			__field(u64, dir)
+			__field(u64, fileid)
 			__string(name, dentry->d_name.name)
 		),
 
@@ -407,16 +408,18 @@ DECLARE_EVENT_CLASS(nfs_lookup_event,
 			__entry->dev = dir->i_sb->s_dev;
 			__entry->dir = NFS_FILEID(dir);
 			__entry->flags = flags;
+			__entry->fileid = d_is_negative(dentry) ? 0 : NFS_FILEID(d_inode(dentry));
 			__assign_str(name, dentry->d_name.name);
 		),
 
 		TP_printk(
-			"flags=0x%lx (%s) name=%02x:%02x:%llu/%s",
+			"flags=0x%lx (%s) name=%02x:%02x:%llu/%s fileid=%llu",
 			__entry->flags,
 			show_fs_lookup_flags(__entry->flags),
 			MAJOR(__entry->dev), MINOR(__entry->dev),
 			(unsigned long long)__entry->dir,
-			__get_str(name)
+			__get_str(name),
+			__entry->fileid
 		)
 );
 
@@ -444,6 +447,7 @@ DECLARE_EVENT_CLASS(nfs_lookup_event_done,
 			__field(unsigned long, flags)
 			__field(dev_t, dev)
 			__field(u64, dir)
+			__field(u64, fileid)
 			__string(name, dentry->d_name.name)
 		),
 
@@ -452,17 +456,19 @@ DECLARE_EVENT_CLASS(nfs_lookup_event_done,
 			__entry->dir = NFS_FILEID(dir);
 			__entry->error = error < 0 ? -error : 0;
 			__entry->flags = flags;
+			__entry->fileid = d_is_negative(dentry) ? 0 : NFS_FILEID(d_inode(dentry));
 			__assign_str(name, dentry->d_name.name);
 		),
 
 		TP_printk(
-			"error=%ld (%s) flags=0x%lx (%s) name=%02x:%02x:%llu/%s",
+			"error=%ld (%s) flags=0x%lx (%s) name=%02x:%02x:%llu/%s fileid=%llu",
 			-__entry->error, show_nfs_status(__entry->error),
 			__entry->flags,
 			show_fs_lookup_flags(__entry->flags),
 			MAJOR(__entry->dev), MINOR(__entry->dev),
 			(unsigned long long)__entry->dir,
-			__get_str(name)
+			__get_str(name),
+			__entry->fileid
 		)
 );
 
@@ -893,7 +899,7 @@ DECLARE_EVENT_CLASS(nfs_rename_event_done,
 DEFINE_NFS_RENAME_EVENT(nfs_rename_enter);
 DEFINE_NFS_RENAME_EVENT_DONE(nfs_rename_exit);
 
-DEFINE_NFS_RENAME_EVENT_DONE(nfs_sillyrename_rename);
+DEFINE_NFS_RENAME_EVENT_DONE(nfs_async_rename_done);
 
 TRACE_EVENT(nfs_sillyrename_unlink,
 		TP_PROTO(
@@ -1539,7 +1545,6 @@ DECLARE_EVENT_CLASS(nfs_direct_req_class,
 			__field(u32, fhandle)
 			__field(loff_t, offset)
 			__field(ssize_t, count)
-			__field(ssize_t, bytes_left)
 			__field(ssize_t, error)
 			__field(int, flags)
 		),
@@ -1554,19 +1559,18 @@ DECLARE_EVENT_CLASS(nfs_direct_req_class,
 			__entry->fhandle = nfs_fhandle_hash(fh);
 			__entry->offset = dreq->io_start;
 			__entry->count = dreq->count;
-			__entry->bytes_left = dreq->bytes_left;
 			__entry->error = dreq->error;
 			__entry->flags = dreq->flags;
 		),
 
 		TP_printk(
 			"error=%zd fileid=%02x:%02x:%llu fhandle=0x%08x "
-			"offset=%lld count=%zd bytes_left=%zd flags=%s",
+			"offset=%lld count=%zd flags=%s",
 			__entry->error, MAJOR(__entry->dev),
 			MINOR(__entry->dev),
 			(unsigned long long)__entry->fileid,
 			__entry->fhandle, __entry->offset,
-			__entry->count, __entry->bytes_left,
+			__entry->count,
 			nfs_show_direct_req_flags(__entry->flags)
 		)
 );
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 21a365357629..0c0fed1ecd0b 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -2733,7 +2733,8 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r
 		if (pgio->pg_dreq == NULL)
 			rd_size = i_size_read(pgio->pg_inode) - req_offset(req);
 		else
-			rd_size = nfs_dreq_bytes_left(pgio->pg_dreq);
+			rd_size = nfs_dreq_bytes_left(pgio->pg_dreq,
+						      req_offset(req));
 
 		pgio->pg_lseg =
 			pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req),
diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c
index f39e2089bc4c..e645be1a3381 100644
--- a/fs/nfs/sysctl.c
+++ b/fs/nfs/sysctl.c
@@ -29,7 +29,6 @@ static struct ctl_table nfs_cb_sysctls[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-	{ }
 };
 
 int nfs_register_sysctl(void)
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 150a953a8be9..0110299643a2 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -267,7 +267,7 @@ static void nfs_async_rename_done(struct rpc_task *task, void *calldata)
 	struct inode *new_dir = data->new_dir;
 	struct dentry *old_dentry = data->old_dentry;
 
-	trace_nfs_sillyrename_rename(old_dir, old_dentry,
+	trace_nfs_async_rename_done(old_dir, old_dentry,
 			new_dir, data->new_dentry, task->tk_status);
 	if (!NFS_PROTO(old_dir)->rename_done(task, old_dir, new_dir)) {
 		rpc_restart_call_prepare(task);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index b664caea8b4e..bb79d3a886ae 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -192,13 +192,13 @@ static struct nfs_page *nfs_folio_find_private_request(struct folio *folio)
 
 	if (!folio_test_private(folio))
 		return NULL;
-	spin_lock(&mapping->private_lock);
+	spin_lock(&mapping->i_private_lock);
 	req = nfs_folio_private_request(folio);
 	if (req) {
 		WARN_ON_ONCE(req->wb_head != req);
 		kref_get(&req->wb_kref);
 	}
-	spin_unlock(&mapping->private_lock);
+	spin_unlock(&mapping->i_private_lock);
 	return req;
 }
 
@@ -680,17 +680,6 @@ static int nfs_writepage_locked(struct folio *folio,
 	return err;
 }
 
-int nfs_writepage(struct page *page, struct writeback_control *wbc)
-{
-	struct folio *folio = page_folio(page);
-	int ret;
-
-	ret = nfs_writepage_locked(folio, wbc);
-	if (ret != AOP_WRITEPAGE_ACTIVATE)
-		unlock_page(page);
-	return ret;
-}
-
 static int nfs_writepages_callback(struct folio *folio,
 				   struct writeback_control *wbc, void *data)
 {
@@ -769,13 +758,13 @@ static void nfs_inode_add_request(struct nfs_page *req)
 	 * Swap-space should not get truncated. Hence no need to plug the race
 	 * with invalidate/truncate.
 	 */
-	spin_lock(&mapping->private_lock);
+	spin_lock(&mapping->i_private_lock);
 	if (likely(!folio_test_swapcache(folio))) {
 		set_bit(PG_MAPPED, &req->wb_flags);
 		folio_set_private(folio);
 		folio->private = req;
 	}
-	spin_unlock(&mapping->private_lock);
+	spin_unlock(&mapping->i_private_lock);
 	atomic_long_inc(&nfsi->nrequests);
 	/* this a head request for a page group - mark it as having an
 	 * extra reference so sub groups can follow suit.
@@ -796,13 +785,13 @@ static void nfs_inode_remove_request(struct nfs_page *req)
 		struct folio *folio = nfs_page_to_folio(req->wb_head);
 		struct address_space *mapping = folio_file_mapping(folio);
 
-		spin_lock(&mapping->private_lock);
+		spin_lock(&mapping->i_private_lock);
 		if (likely(folio && !folio_test_swapcache(folio))) {
 			folio->private = NULL;
 			folio_clear_private(folio);
 			clear_bit(PG_MAPPED, &req->wb_head->wb_flags);
 		}
-		spin_unlock(&mapping->private_lock);
+		spin_unlock(&mapping->i_private_lock);
 	}
 
 	if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) {
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 43b88eaf0673..272ab8d5c4d7 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -158,3 +158,19 @@ config NFSD_V4_SECURITY_LABEL
 
 	If you do not wish to enable fine-grained security labels SELinux or
 	Smack policies on NFSv4 files, say N.
+
+config NFSD_LEGACY_CLIENT_TRACKING
+	bool "Support legacy NFSv4 client tracking methods (DEPRECATED)"
+	depends on NFSD_V4
+	default n
+	help
+	  The NFSv4 server needs to store a small amount of information on
+	  stable storage in order to handle state recovery after reboot. Most
+	  modern deployments upcall to a userland daemon for this (nfsdcld),
+	  but older NFS servers may store information directly in a
+	  recoverydir, or spawn a process directly using a usermodehelper
+	  upcall.
+
+	  These legacy client tracking methods have proven to be probelmatic
+	  and will be removed in the future. Say Y here if you need support
+	  for them in the interim.
diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c
index fdf2aad73470..e6beaaf4f170 100644
--- a/fs/nfsd/auth.c
+++ b/fs/nfsd/auth.c
@@ -26,8 +26,6 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
 	int i;
 	int flags = nfsexp_flags(rqstp, exp);
 
-	validate_process_creds();
-
 	/* discard any old override before preparing the new set */
 	revert_creds(get_cred(current_real_cred()));
 	new = prepare_creds();
@@ -81,10 +79,8 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
 	else
 		new->cap_effective = cap_raise_nfsd_set(new->cap_effective,
 							new->cap_permitted);
-	validate_process_creds();
 	put_cred(override_creds(new));
 	put_cred(new);
-	validate_process_creds();
 	return 0;
 
 oom:
diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h
index 929248c6ca84..4cbe0434cbb8 100644
--- a/fs/nfsd/cache.h
+++ b/fs/nfsd/cache.h
@@ -84,8 +84,8 @@ int	nfsd_net_reply_cache_init(struct nfsd_net *nn);
 void	nfsd_net_reply_cache_destroy(struct nfsd_net *nn);
 int	nfsd_reply_cache_init(struct nfsd_net *);
 void	nfsd_reply_cache_shutdown(struct nfsd_net *);
-int	nfsd_cache_lookup(struct svc_rqst *rqstp,
-			  struct nfsd_cacherep **cacherep);
+int	nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start,
+			  unsigned int len, struct nfsd_cacherep **cacherep);
 void	nfsd_cache_update(struct svc_rqst *rqstp, struct nfsd_cacherep *rp,
 			  int cachetype, __be32 *statp);
 int	nfsd_reply_cache_stats_show(struct seq_file *m, void *v);
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index ef063f93fde9..9cb7f0c33df5 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -322,7 +322,7 @@ nfsd_file_check_writeback(struct nfsd_file *nf)
 static bool nfsd_file_lru_add(struct nfsd_file *nf)
 {
 	set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags);
-	if (list_lru_add(&nfsd_file_lru, &nf->nf_lru)) {
+	if (list_lru_add_obj(&nfsd_file_lru, &nf->nf_lru)) {
 		trace_nfsd_file_lru_add(nf);
 		return true;
 	}
@@ -331,7 +331,7 @@ static bool nfsd_file_lru_add(struct nfsd_file *nf)
 
 static bool nfsd_file_lru_remove(struct nfsd_file *nf)
 {
-	if (list_lru_del(&nfsd_file_lru, &nf->nf_lru)) {
+	if (list_lru_del_obj(&nfsd_file_lru, &nf->nf_lru)) {
 		trace_nfsd_file_lru_del(nf);
 		return true;
 	}
@@ -717,7 +717,7 @@ nfsd_file_cache_init(void)
 		return ret;
 
 	ret = -ENOMEM;
-	nfsd_filecache_wq = alloc_workqueue("nfsd_filecache", 0, 0);
+	nfsd_filecache_wq = alloc_workqueue("nfsd_filecache", WQ_UNBOUND, 0);
 	if (!nfsd_filecache_wq)
 		goto out;
 
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index ab303a8b77d5..74b4360779a1 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -123,14 +123,9 @@ struct nfsd_net {
 	u32 clientid_counter;
 	u32 clverifier_counter;
 
-	struct svc_serv *nfsd_serv;
-	/* When a listening socket is added to nfsd, keep_active is set
-	 * and this justifies a reference on nfsd_serv.  This stops
-	 * nfsd_serv from being freed.  When the number of threads is
-	 * set, keep_active is cleared and the reference is dropped.  So
-	 * when the last thread exits, the service will be destroyed.
-	 */
-	int keep_active;
+	struct svc_info nfsd_info;
+#define nfsd_serv nfsd_info.serv
+
 
 	/*
 	 * clientid and stateid data for construction of net unique COPY
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 92bc109dabe6..926c29879c6a 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -31,6 +31,7 @@
  *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
+#include <linux/nfs4.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/xprt.h>
 #include <linux/sunrpc/svc_xprt.h>
@@ -84,48 +85,9 @@ static void encode_uint32(struct xdr_stream *xdr, u32 n)
 static void encode_bitmap4(struct xdr_stream *xdr, const __u32 *bitmap,
 			   size_t len)
 {
-	xdr_stream_encode_uint32_array(xdr, bitmap, len);
+	WARN_ON_ONCE(xdr_stream_encode_uint32_array(xdr, bitmap, len) < 0);
 }
 
-static int decode_cb_fattr4(struct xdr_stream *xdr, uint32_t *bitmap,
-				struct nfs4_cb_fattr *fattr)
-{
-	fattr->ncf_cb_change = 0;
-	fattr->ncf_cb_fsize = 0;
-	if (bitmap[0] & FATTR4_WORD0_CHANGE)
-		if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_change) < 0)
-			return -NFSERR_BAD_XDR;
-	if (bitmap[0] & FATTR4_WORD0_SIZE)
-		if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_fsize) < 0)
-			return -NFSERR_BAD_XDR;
-	return 0;
-}
-
-/*
- *	nfs_cb_opnum4
- *
- *	enum nfs_cb_opnum4 {
- *		OP_CB_GETATTR		= 3,
- *		  ...
- *	};
- */
-enum nfs_cb_opnum4 {
-	OP_CB_GETATTR			= 3,
-	OP_CB_RECALL			= 4,
-	OP_CB_LAYOUTRECALL		= 5,
-	OP_CB_NOTIFY			= 6,
-	OP_CB_PUSH_DELEG		= 7,
-	OP_CB_RECALL_ANY		= 8,
-	OP_CB_RECALLABLE_OBJ_AVAIL	= 9,
-	OP_CB_RECALL_SLOT		= 10,
-	OP_CB_SEQUENCE			= 11,
-	OP_CB_WANTS_CANCELLED		= 12,
-	OP_CB_NOTIFY_LOCK		= 13,
-	OP_CB_NOTIFY_DEVICEID		= 14,
-	OP_CB_OFFLOAD			= 15,
-	OP_CB_ILLEGAL			= 10044
-};
-
 static void encode_nfs_cb_opnum4(struct xdr_stream *xdr, enum nfs_cb_opnum4 op)
 {
 	__be32 *p;
@@ -372,30 +334,6 @@ encode_cb_recallany4args(struct xdr_stream *xdr,
 }
 
 /*
- * CB_GETATTR4args
- *	struct CB_GETATTR4args {
- *	   nfs_fh4 fh;
- *	   bitmap4 attr_request;
- *	};
- *
- * The size and change attributes are the only one
- * guaranteed to be serviced by the client.
- */
-static void
-encode_cb_getattr4args(struct xdr_stream *xdr, struct nfs4_cb_compound_hdr *hdr,
-			struct nfs4_cb_fattr *fattr)
-{
-	struct nfs4_delegation *dp =
-		container_of(fattr, struct nfs4_delegation, dl_cb_fattr);
-	struct knfsd_fh *fh = &dp->dl_stid.sc_file->fi_fhandle;
-
-	encode_nfs_cb_opnum4(xdr, OP_CB_GETATTR);
-	encode_nfs_fh4(xdr, fh);
-	encode_bitmap4(xdr, fattr->ncf_cb_bmap, ARRAY_SIZE(fattr->ncf_cb_bmap));
-	hdr->nops++;
-}
-
-/*
  * CB_SEQUENCE4args
  *
  *	struct CB_SEQUENCE4args {
@@ -531,26 +469,6 @@ static void nfs4_xdr_enc_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr,
 }
 
 /*
- * 20.1.  Operation 3: CB_GETATTR - Get Attributes
- */
-static void nfs4_xdr_enc_cb_getattr(struct rpc_rqst *req,
-		struct xdr_stream *xdr, const void *data)
-{
-	const struct nfsd4_callback *cb = data;
-	struct nfs4_cb_fattr *ncf =
-		container_of(cb, struct nfs4_cb_fattr, ncf_getattr);
-	struct nfs4_cb_compound_hdr hdr = {
-		.ident = cb->cb_clp->cl_cb_ident,
-		.minorversion = cb->cb_clp->cl_minorversion,
-	};
-
-	encode_cb_compound4args(xdr, &hdr);
-	encode_cb_sequence4args(xdr, cb, &hdr);
-	encode_cb_getattr4args(xdr, &hdr, ncf);
-	encode_cb_nops(&hdr);
-}
-
-/*
  * 20.2. Operation 4: CB_RECALL - Recall a Delegation
  */
 static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr,
@@ -606,42 +524,6 @@ static int nfs4_xdr_dec_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr,
 }
 
 /*
- * 20.1.  Operation 3: CB_GETATTR - Get Attributes
- */
-static int nfs4_xdr_dec_cb_getattr(struct rpc_rqst *rqstp,
-				  struct xdr_stream *xdr,
-				  void *data)
-{
-	struct nfsd4_callback *cb = data;
-	struct nfs4_cb_compound_hdr hdr;
-	int status;
-	u32 bitmap[3] = {0};
-	u32 attrlen;
-	struct nfs4_cb_fattr *ncf =
-		container_of(cb, struct nfs4_cb_fattr, ncf_getattr);
-
-	status = decode_cb_compound4res(xdr, &hdr);
-	if (unlikely(status))
-		return status;
-
-	status = decode_cb_sequence4res(xdr, cb);
-	if (unlikely(status || cb->cb_seq_status))
-		return status;
-
-	status = decode_cb_op_status(xdr, OP_CB_GETATTR, &cb->cb_status);
-	if (status)
-		return status;
-	if (xdr_stream_decode_uint32_array(xdr, bitmap, 3) < 0)
-		return -NFSERR_BAD_XDR;
-	if (xdr_stream_decode_u32(xdr, &attrlen) < 0)
-		return -NFSERR_BAD_XDR;
-	if (attrlen > (sizeof(ncf->ncf_cb_change) + sizeof(ncf->ncf_cb_fsize)))
-		return -NFSERR_BAD_XDR;
-	status = decode_cb_fattr4(xdr, bitmap, ncf);
-	return status;
-}
-
-/*
  * 20.2. Operation 4: CB_RECALL - Recall a Delegation
  */
 static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp,
@@ -949,7 +831,6 @@ static const struct rpc_procinfo nfs4_cb_procedures[] = {
 	PROC(CB_NOTIFY_LOCK,	COMPOUND,	cb_notify_lock,	cb_notify_lock),
 	PROC(CB_OFFLOAD,	COMPOUND,	cb_offload,	cb_offload),
 	PROC(CB_RECALL_ANY,	COMPOUND,	cb_recall_any,	cb_recall_any),
-	PROC(CB_GETATTR,	COMPOUND,	cb_getattr,	cb_getattr),
 };
 
 static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)];
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 6f2d4aa4970d..14712fa08f76 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -970,8 +970,11 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	 * To ensure proper ordering, we therefore turn off zero copy if
 	 * the client wants us to do more in this compound:
 	 */
-	if (!nfsd4_last_compound_op(rqstp))
-		clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
+	if (!nfsd4_last_compound_op(rqstp)) {
+		struct nfsd4_compoundargs *argp = rqstp->rq_argp;
+
+		argp->splice_ok = false;
+	}
 
 	/* check stateid */
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 3509e73abe1f..2c060e0b1604 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -66,6 +66,7 @@ struct nfsd4_client_tracking_ops {
 static const struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops;
 static const struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops_v2;
 
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
 /* Globals */
 static char user_recovery_dirname[PATH_MAX] = "/var/lib/nfs/v4recovery";
 
@@ -720,6 +721,7 @@ static const struct nfsd4_client_tracking_ops nfsd4_legacy_tracking_ops = {
 	.version	= 1,
 	.msglen		= 0,
 };
+#endif /* CONFIG_NFSD_LEGACY_CLIENT_TRACKING */
 
 /* Globals */
 #define NFSD_PIPE_DIR		"nfsd"
@@ -731,8 +733,10 @@ struct cld_net {
 	spinlock_t		 cn_lock;
 	struct list_head	 cn_list;
 	unsigned int		 cn_xid;
-	bool			 cn_has_legacy;
 	struct crypto_shash	*cn_tfm;
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
+	bool			 cn_has_legacy;
+#endif
 };
 
 struct cld_upcall {
@@ -793,7 +797,6 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg,
 	uint8_t cmd, princhashlen;
 	struct xdr_netobj name, princhash = { .len = 0, .data = NULL };
 	uint16_t namelen;
-	struct cld_net *cn = nn->cld_net;
 
 	if (get_user(cmd, &cmsg->cm_cmd)) {
 		dprintk("%s: error when copying cmd from userspace", __func__);
@@ -833,11 +836,15 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg,
 				return PTR_ERR(name.data);
 			name.len = namelen;
 		}
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
 		if (name.len > 5 && memcmp(name.data, "hash:", 5) == 0) {
+			struct cld_net *cn = nn->cld_net;
+
 			name.len = name.len - 5;
 			memmove(name.data, name.data + 5, name.len);
 			cn->cn_has_legacy = true;
 		}
+#endif
 		if (!nfs4_client_to_reclaim(name, princhash, nn)) {
 			kfree(name.data);
 			kfree(princhash.data);
@@ -1010,7 +1017,9 @@ __nfsd4_init_cld_pipe(struct net *net)
 	}
 
 	cn->cn_pipe->dentry = dentry;
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
 	cn->cn_has_legacy = false;
+#endif
 	nn->cld_net = cn;
 	return 0;
 
@@ -1282,10 +1291,6 @@ nfsd4_cld_check(struct nfs4_client *clp)
 {
 	struct nfs4_client_reclaim *crp;
 	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
-	struct cld_net *cn = nn->cld_net;
-	int status;
-	char dname[HEXDIR_LEN];
-	struct xdr_netobj name;
 
 	/* did we already find that this client is stable? */
 	if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
@@ -1296,7 +1301,12 @@ nfsd4_cld_check(struct nfs4_client *clp)
 	if (crp)
 		goto found;
 
-	if (cn->cn_has_legacy) {
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
+	if (nn->cld_net->cn_has_legacy) {
+		int status;
+		char dname[HEXDIR_LEN];
+		struct xdr_netobj name;
+
 		status = nfs4_make_rec_clidname(dname, &clp->cl_name);
 		if (status)
 			return -ENOENT;
@@ -1314,6 +1324,7 @@ nfsd4_cld_check(struct nfs4_client *clp)
 			goto found;
 
 	}
+#endif
 	return -ENOENT;
 found:
 	crp->cr_clp = clp;
@@ -1327,8 +1338,6 @@ nfsd4_cld_check_v2(struct nfs4_client *clp)
 	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
 	struct cld_net *cn = nn->cld_net;
 	int status;
-	char dname[HEXDIR_LEN];
-	struct xdr_netobj name;
 	struct crypto_shash *tfm = cn->cn_tfm;
 	struct xdr_netobj cksum;
 	char *principal = NULL;
@@ -1342,7 +1351,11 @@ nfsd4_cld_check_v2(struct nfs4_client *clp)
 	if (crp)
 		goto found;
 
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
 	if (cn->cn_has_legacy) {
+		struct xdr_netobj name;
+		char dname[HEXDIR_LEN];
+
 		status = nfs4_make_rec_clidname(dname, &clp->cl_name);
 		if (status)
 			return -ENOENT;
@@ -1360,6 +1373,7 @@ nfsd4_cld_check_v2(struct nfs4_client *clp)
 			goto found;
 
 	}
+#endif
 	return -ENOENT;
 found:
 	if (crp->cr_princhash.len) {
@@ -1663,6 +1677,7 @@ static const struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops_v2 = {
 	.msglen		= sizeof(struct cld_msg_v2),
 };
 
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
 /* upcall via usermodehelper */
 static char cltrack_prog[PATH_MAX] = "/sbin/nfsdcltrack";
 module_param_string(cltrack_prog, cltrack_prog, sizeof(cltrack_prog),
@@ -2007,28 +2022,10 @@ static const struct nfsd4_client_tracking_ops nfsd4_umh_tracking_ops = {
 	.msglen		= 0,
 };
 
-int
-nfsd4_client_tracking_init(struct net *net)
+static inline int check_for_legacy_methods(int status, struct net *net)
 {
-	int status;
-	struct path path;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
-
-	/* just run the init if it the method is already decided */
-	if (nn->client_tracking_ops)
-		goto do_init;
-
-	/* First, try to use nfsdcld */
-	nn->client_tracking_ops = &nfsd4_cld_tracking_ops;
-	status = nn->client_tracking_ops->init(net);
-	if (!status)
-		return status;
-	if (status != -ETIMEDOUT) {
-		nn->client_tracking_ops = &nfsd4_cld_tracking_ops_v0;
-		status = nn->client_tracking_ops->init(net);
-		if (!status)
-			return status;
-	}
+	struct path path;
 
 	/*
 	 * Next, try the UMH upcall.
@@ -2045,14 +2042,46 @@ nfsd4_client_tracking_init(struct net *net)
 	nn->client_tracking_ops = &nfsd4_legacy_tracking_ops;
 	status = kern_path(nfs4_recoverydir(), LOOKUP_FOLLOW, &path);
 	if (!status) {
-		status = d_is_dir(path.dentry);
+		status = !d_is_dir(path.dentry);
 		path_put(&path);
-		if (!status) {
-			status = -EINVAL;
-			goto out;
-		}
+		if (status)
+			return -ENOTDIR;
+		status = nn->client_tracking_ops->init(net);
+	}
+	return status;
+}
+#else
+static inline int check_for_legacy_methods(int status, struct net *net)
+{
+	return status;
+}
+#endif /* CONFIG_LEGACY_NFSD_CLIENT_TRACKING */
+
+int
+nfsd4_client_tracking_init(struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	int status;
+
+	/* just run the init if it the method is already decided */
+	if (nn->client_tracking_ops)
+		goto do_init;
+
+	/* First, try to use nfsdcld */
+	nn->client_tracking_ops = &nfsd4_cld_tracking_ops;
+	status = nn->client_tracking_ops->init(net);
+	if (!status)
+		return status;
+	if (status != -ETIMEDOUT) {
+		nn->client_tracking_ops = &nfsd4_cld_tracking_ops_v0;
+		status = nn->client_tracking_ops->init(net);
+		if (!status)
+			return status;
 	}
 
+	status = check_for_legacy_methods(status, net);
+	if (status)
+		goto out;
 do_init:
 	status = nn->client_tracking_ops->init(net);
 out:
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 4045c852a450..2fa54cfd4882 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -127,7 +127,6 @@ static void free_session(struct nfsd4_session *);
 
 static const struct nfsd4_callback_ops nfsd4_cb_recall_ops;
 static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops;
-static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops;
 
 static struct workqueue_struct *laundry_wq;
 
@@ -1190,10 +1189,6 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
 	dp->dl_recalled = false;
 	nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client,
 		      &nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL);
-	nfsd4_init_cb(&dp->dl_cb_fattr.ncf_getattr, dp->dl_stid.sc_client,
-			&nfsd4_cb_getattr_ops, NFSPROC4_CLNT_CB_GETATTR);
-	dp->dl_cb_fattr.ncf_file_modified = false;
-	dp->dl_cb_fattr.ncf_cb_bmap[0] = FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE;
 	get_nfs4_file(fp);
 	dp->dl_stid.sc_file = fp;
 	return dp;
@@ -2804,7 +2799,7 @@ static int client_opens_release(struct inode *inode, struct file *file)
 
 	/* XXX: alternatively, we could get/drop in seq start/stop */
 	drop_client(clp);
-	return 0;
+	return seq_release(inode, file);
 }
 
 static const struct file_operations client_states_fops = {
@@ -2901,56 +2896,11 @@ nfsd4_cb_recall_any_release(struct nfsd4_callback *cb)
 	spin_unlock(&nn->client_lock);
 }
 
-static int
-nfsd4_cb_getattr_done(struct nfsd4_callback *cb, struct rpc_task *task)
-{
-	struct nfs4_cb_fattr *ncf =
-			container_of(cb, struct nfs4_cb_fattr, ncf_getattr);
-
-	ncf->ncf_cb_status = task->tk_status;
-	switch (task->tk_status) {
-	case -NFS4ERR_DELAY:
-		rpc_delay(task, 2 * HZ);
-		return 0;
-	default:
-		return 1;
-	}
-}
-
-static void
-nfsd4_cb_getattr_release(struct nfsd4_callback *cb)
-{
-	struct nfs4_cb_fattr *ncf =
-			container_of(cb, struct nfs4_cb_fattr, ncf_getattr);
-	struct nfs4_delegation *dp =
-			container_of(ncf, struct nfs4_delegation, dl_cb_fattr);
-
-	nfs4_put_stid(&dp->dl_stid);
-	clear_bit(CB_GETATTR_BUSY, &ncf->ncf_cb_flags);
-	wake_up_bit(&ncf->ncf_cb_flags, CB_GETATTR_BUSY);
-}
-
 static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = {
 	.done		= nfsd4_cb_recall_any_done,
 	.release	= nfsd4_cb_recall_any_release,
 };
 
-static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops = {
-	.done		= nfsd4_cb_getattr_done,
-	.release	= nfsd4_cb_getattr_release,
-};
-
-void nfs4_cb_getattr(struct nfs4_cb_fattr *ncf)
-{
-	struct nfs4_delegation *dp =
-			container_of(ncf, struct nfs4_delegation, dl_cb_fattr);
-
-	if (test_and_set_bit(CB_GETATTR_BUSY, &ncf->ncf_cb_flags))
-		return;
-	refcount_inc(&dp->dl_stid.sc_count);
-	nfsd4_run_cb(&ncf->ncf_getattr);
-}
-
 static struct nfs4_client *create_client(struct xdr_netobj name,
 		struct svc_rqst *rqstp, nfs4_verifier *verf)
 {
@@ -5685,8 +5635,6 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	struct svc_fh *parent = NULL;
 	int cb_up;
 	int status = 0;
-	struct kstat stat;
-	struct path path;
 
 	cb_up = nfsd4_cb_channel_good(oo->oo_owner.so_client);
 	open->op_recall = false;
@@ -5724,18 +5672,6 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) {
 		open->op_delegate_type = NFS4_OPEN_DELEGATE_WRITE;
 		trace_nfsd_deleg_write(&dp->dl_stid.sc_stateid);
-		path.mnt = currentfh->fh_export->ex_path.mnt;
-		path.dentry = currentfh->fh_dentry;
-		if (vfs_getattr(&path, &stat,
-				(STATX_SIZE | STATX_CTIME | STATX_CHANGE_COOKIE),
-				AT_STATX_SYNC_AS_STAT)) {
-			nfs4_put_stid(&dp->dl_stid);
-			destroy_delegation(dp);
-			goto out_no_deleg;
-		}
-		dp->dl_cb_fattr.ncf_cur_fsize = stat.size;
-		dp->dl_cb_fattr.ncf_initial_cinfo =
-			nfsd4_change_attribute(&stat, d_inode(currentfh->fh_dentry));
 	} else {
 		open->op_delegate_type = NFS4_OPEN_DELEGATE_READ;
 		trace_nfsd_deleg_read(&dp->dl_stid.sc_stateid);
@@ -6639,7 +6575,7 @@ unlock:
 	spin_unlock(&nn->s2s_cp_lock);
 	if (!state)
 		return nfserr_bad_stateid;
-	if (!clp && state)
+	if (!clp)
 		*cps = state;
 	return 0;
 }
@@ -8492,8 +8428,6 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate,
  * nfsd4_deleg_getattr_conflict - Recall if GETATTR causes conflict
  * @rqstp: RPC transaction context
  * @inode: file to be checked for a conflict
- * @modified: return true if file was modified
- * @size: new size of file if modified is true
  *
  * This function is called when there is a conflict between a write
  * delegation and a change/size GETATTR from another client. The server
@@ -8502,23 +8436,21 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate,
  * delegation before replying to the GETATTR. See RFC 8881 section
  * 18.7.4.
  *
+ * The current implementation does not support CB_GETATTR yet. However
+ * this can avoid recalling the delegation could be added in follow up
+ * work.
+ *
  * Returns 0 if there is no conflict; otherwise an nfs_stat
  * code is returned.
  */
 __be32
-nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode,
-			     bool *modified, u64 *size)
+nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode)
 {
+	__be32 status;
 	struct file_lock_context *ctx;
-	struct nfs4_delegation *dp;
-	struct nfs4_cb_fattr *ncf;
 	struct file_lock *fl;
-	struct iattr attrs;
-	__be32 status;
-
-	might_sleep();
+	struct nfs4_delegation *dp;
 
-	*modified = false;
 	ctx = locks_inode_context(inode);
 	if (!ctx)
 		return 0;
@@ -8545,34 +8477,10 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode,
 break_lease:
 			spin_unlock(&ctx->flc_lock);
 			nfsd_stats_wdeleg_getattr_inc();
-
-			dp = fl->fl_owner;
-			ncf = &dp->dl_cb_fattr;
-			nfs4_cb_getattr(&dp->dl_cb_fattr);
-			wait_on_bit(&ncf->ncf_cb_flags, CB_GETATTR_BUSY, TASK_INTERRUPTIBLE);
-			if (ncf->ncf_cb_status) {
-				status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ));
-				if (status != nfserr_jukebox ||
-						!nfsd_wait_for_delegreturn(rqstp, inode))
-					return status;
-			}
-			if (!ncf->ncf_file_modified &&
-					(ncf->ncf_initial_cinfo != ncf->ncf_cb_change ||
-					ncf->ncf_cur_fsize != ncf->ncf_cb_fsize))
-				ncf->ncf_file_modified = true;
-			if (ncf->ncf_file_modified) {
-				/*
-				 * The server would not update the file's metadata
-				 * with the client's modified size.
-				 */
-				attrs.ia_mtime = attrs.ia_ctime = current_time(inode);
-				attrs.ia_valid = ATTR_MTIME | ATTR_CTIME;
-				setattr_copy(&nop_mnt_idmap, inode, &attrs);
-				mark_inode_dirty(inode);
-				ncf->ncf_cur_fsize = ncf->ncf_cb_fsize;
-				*size = ncf->ncf_cur_fsize;
-				*modified = true;
-			}
+			status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ));
+			if (status != nfserr_jukebox ||
+					!nfsd_wait_for_delegreturn(rqstp, inode))
+				return status;
 			return 0;
 		}
 		break;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index ec4ed6206df1..c719c475a068 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2524,8 +2524,9 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
 	svc_reserve(argp->rqstp, max_reply + readbytes);
 	argp->rqstp->rq_cachetype = cachethis ? RC_REPLBUFF : RC_NOCACHE;
 
+	argp->splice_ok = nfsd_read_splice_ok(argp->rqstp);
 	if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack)
-		clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags);
+		argp->splice_ok = false;
 
 	return true;
 }
@@ -3505,9 +3506,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 		u32		attrmask[3];
 		unsigned long	mask[2];
 	} u;
-	bool file_modified;
 	unsigned long bit;
-	u64 size = 0;
 
 	WARN_ON_ONCE(bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1);
 	WARN_ON_ONCE(!nfsd_attrs_supported(minorversion, bmval));
@@ -3534,8 +3533,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 	}
 	args.size = 0;
 	if (u.attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) {
-		status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry),
-						      &file_modified, &size);
+		status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry));
 		if (status)
 			goto out;
 	}
@@ -3545,7 +3543,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 			  AT_STATX_SYNC_AS_STAT);
 	if (err)
 		goto out_nfserr;
-	args.size = file_modified ? size : args.stat.size;
+	args.size = args.stat.size;
 
 	if (!(args.stat.result_mask & STATX_BTIME))
 		/* underlying FS does not offer btime so we can't share it */
@@ -4378,12 +4376,13 @@ static __be32
 nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
 		  union nfsd4_op_u *u)
 {
+	struct nfsd4_compoundargs *argp = resp->rqstp->rq_argp;
 	struct nfsd4_read *read = &u->read;
-	bool splice_ok = test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags);
-	unsigned long maxcount;
 	struct xdr_stream *xdr = resp->xdr;
-	struct file *file;
 	int starting_len = xdr->buf->len;
+	bool splice_ok = argp->splice_ok;
+	unsigned long maxcount;
+	struct file *file;
 	__be32 *p;
 
 	if (nfserr)
@@ -5204,9 +5203,10 @@ static __be32
 nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp,
 			    struct nfsd4_read *read)
 {
-	bool splice_ok = test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags);
+	struct nfsd4_compoundargs *argp = resp->rqstp->rq_argp;
 	struct file *file = read->rd_nf->nf_file;
 	struct xdr_stream *xdr = resp->xdr;
+	bool splice_ok = argp->splice_ok;
 	unsigned long maxcount;
 	__be32 nfserr, *p;
 
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index fd56a52aa5fb..5c1a4a0aa605 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -364,38 +364,55 @@ nfsd_reply_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
 		if (freed > sc->nr_to_scan)
 			break;
 	}
-
-	trace_nfsd_drc_gc(nn, freed);
 	return freed;
 }
 
-/*
- * Walk an xdr_buf and get a CRC for at most the first RC_CSUMLEN bytes
+/**
+ * nfsd_cache_csum - Checksum incoming NFS Call arguments
+ * @buf: buffer containing a whole RPC Call message
+ * @start: starting byte of the NFS Call header
+ * @remaining: size of the NFS Call header, in bytes
+ *
+ * Compute a weak checksum of the leading bytes of an NFS procedure
+ * call header to help verify that a retransmitted Call matches an
+ * entry in the duplicate reply cache.
+ *
+ * To avoid assumptions about how the RPC message is laid out in
+ * @buf and what else it might contain (eg, a GSS MIC suffix), the
+ * caller passes us the exact location and length of the NFS Call
+ * header.
+ *
+ * Returns a 32-bit checksum value, as defined in RFC 793.
  */
-static __wsum
-nfsd_cache_csum(struct svc_rqst *rqstp)
+static __wsum nfsd_cache_csum(struct xdr_buf *buf, unsigned int start,
+			      unsigned int remaining)
 {
+	unsigned int base, len;
+	struct xdr_buf subbuf;
+	__wsum csum = 0;
+	void *p;
 	int idx;
-	unsigned int base;
-	__wsum csum;
-	struct xdr_buf *buf = &rqstp->rq_arg;
-	const unsigned char *p = buf->head[0].iov_base;
-	size_t csum_len = min_t(size_t, buf->head[0].iov_len + buf->page_len,
-				RC_CSUMLEN);
-	size_t len = min(buf->head[0].iov_len, csum_len);
+
+	if (remaining > RC_CSUMLEN)
+		remaining = RC_CSUMLEN;
+	if (xdr_buf_subsegment(buf, &subbuf, start, remaining))
+		return csum;
 
 	/* rq_arg.head first */
-	csum = csum_partial(p, len, 0);
-	csum_len -= len;
+	if (subbuf.head[0].iov_len) {
+		len = min_t(unsigned int, subbuf.head[0].iov_len, remaining);
+		csum = csum_partial(subbuf.head[0].iov_base, len, csum);
+		remaining -= len;
+	}
 
 	/* Continue into page array */
-	idx = buf->page_base / PAGE_SIZE;
-	base = buf->page_base & ~PAGE_MASK;
-	while (csum_len) {
-		p = page_address(buf->pages[idx]) + base;
-		len = min_t(size_t, PAGE_SIZE - base, csum_len);
+	idx = subbuf.page_base / PAGE_SIZE;
+	base = subbuf.page_base & ~PAGE_MASK;
+	while (remaining) {
+		p = page_address(subbuf.pages[idx]) + base;
+		len = min_t(unsigned int, PAGE_SIZE - base, remaining);
 		csum = csum_partial(p, len, csum);
-		csum_len -= len;
+		remaining -= len;
 		base = 0;
 		++idx;
 	}
@@ -466,6 +483,8 @@ out:
 /**
  * nfsd_cache_lookup - Find an entry in the duplicate reply cache
  * @rqstp: Incoming Call to find
+ * @start: starting byte in @rqstp->rq_arg of the NFS Call header
+ * @len: size of the NFS Call header, in bytes
  * @cacherep: OUT: DRC entry for this request
  *
  * Try to find an entry matching the current call in the cache. When none
@@ -479,14 +498,14 @@ out:
  *   %RC_REPLY: Reply from cache
  *   %RC_DROPIT: Do not process the request further
  */
-int nfsd_cache_lookup(struct svc_rqst *rqstp, struct nfsd_cacherep **cacherep)
+int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start,
+		      unsigned int len, struct nfsd_cacherep **cacherep)
 {
 	struct nfsd_net		*nn;
 	struct nfsd_cacherep	*rp, *found;
 	__wsum			csum;
 	struct nfsd_drc_bucket	*b;
 	int type = rqstp->rq_cachetype;
-	unsigned long freed;
 	LIST_HEAD(dispose);
 	int rtn = RC_DOIT;
 
@@ -495,7 +514,7 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp, struct nfsd_cacherep **cacherep)
 		goto out;
 	}
 
-	csum = nfsd_cache_csum(rqstp);
+	csum = nfsd_cache_csum(&rqstp->rq_arg, start, len);
 
 	/*
 	 * Since the common case is a cache miss followed by an insert,
@@ -516,8 +535,7 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp, struct nfsd_cacherep **cacherep)
 	nfsd_prune_bucket_locked(nn, b, 3, &dispose);
 	spin_unlock(&b->cache_lock);
 
-	freed = nfsd_cacherep_dispose(&dispose);
-	trace_nfsd_drc_gc(nn, freed);
+	nfsd_cacherep_dispose(&dispose);
 
 	nfsd_stats_rc_misses_inc();
 	atomic_inc(&nn->num_drc_entries);
@@ -641,24 +659,17 @@ void nfsd_cache_update(struct svc_rqst *rqstp, struct nfsd_cacherep *rp,
 	return;
 }
 
-/*
- * Copy cached reply to current reply buffer. Should always fit.
- * FIXME as reply is in a page, we should just attach the page, and
- * keep a refcount....
- */
 static int
 nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *data)
 {
-	struct kvec	*vec = &rqstp->rq_res.head[0];
-
-	if (vec->iov_len + data->iov_len > PAGE_SIZE) {
-		printk(KERN_WARNING "nfsd: cached reply too large (%zd).\n",
-				data->iov_len);
-		return 0;
-	}
-	memcpy((char*)vec->iov_base + vec->iov_len, data->iov_base, data->iov_len);
-	vec->iov_len += data->iov_len;
-	return 1;
+	__be32 *p;
+
+	p = xdr_reserve_space(&rqstp->rq_res_stream, data->iov_len);
+	if (unlikely(!p))
+		return false;
+	memcpy(p, data->iov_base, data->iov_len);
+	xdr_commit_encode(&rqstp->rq_res_stream);
+	return true;
 }
 
 /*
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 3e15b72f421d..8e6dbe9e0b65 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -76,7 +76,9 @@ static ssize_t write_maxconn(struct file *file, char *buf, size_t size);
 #ifdef CONFIG_NFSD_V4
 static ssize_t write_leasetime(struct file *file, char *buf, size_t size);
 static ssize_t write_gracetime(struct file *file, char *buf, size_t size);
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
 static ssize_t write_recoverydir(struct file *file, char *buf, size_t size);
+#endif
 static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size);
 #endif
 
@@ -93,7 +95,9 @@ static ssize_t (*const write_op[])(struct file *, char *, size_t) = {
 #ifdef CONFIG_NFSD_V4
 	[NFSD_Leasetime] = write_leasetime,
 	[NFSD_Gracetime] = write_gracetime,
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
 	[NFSD_RecoveryDir] = write_recoverydir,
+#endif
 	[NFSD_V4EndGrace] = write_v4_end_grace,
 #endif
 };
@@ -179,7 +183,7 @@ static const struct file_operations pool_stats_operations = {
 	.open		= nfsd_pool_stats_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= nfsd_pool_stats_release,
+	.release	= seq_release,
 };
 
 DEFINE_SHOW_ATTRIBUTE(nfsd_reply_cache_stats);
@@ -693,6 +697,7 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred
 	char *mesg = buf;
 	int fd, err;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct svc_serv *serv;
 
 	err = get_int(&mesg, &fd);
 	if (err != 0 || fd < 0)
@@ -703,13 +708,12 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred
 	if (err != 0)
 		return err;
 
-	err = svc_addsock(nn->nfsd_serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred);
+	serv = nn->nfsd_serv;
+	err = svc_addsock(serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred);
 
-	if (err >= 0 &&
-	    !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
-		svc_get(nn->nfsd_serv);
+	if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks))
+		nfsd_destroy_serv(net);
 
-	nfsd_put(net);
 	return err;
 }
 
@@ -723,6 +727,7 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr
 	struct svc_xprt *xprt;
 	int port, err;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct svc_serv *serv;
 
 	if (sscanf(buf, "%15s %5u", transport, &port) != 2)
 		return -EINVAL;
@@ -735,29 +740,28 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr
 	if (err != 0)
 		return err;
 
-	err = svc_xprt_create(nn->nfsd_serv, transport, net,
+	serv = nn->nfsd_serv;
+	err = svc_xprt_create(serv, transport, net,
 			      PF_INET, port, SVC_SOCK_ANONYMOUS, cred);
 	if (err < 0)
 		goto out_err;
 
-	err = svc_xprt_create(nn->nfsd_serv, transport, net,
+	err = svc_xprt_create(serv, transport, net,
 			      PF_INET6, port, SVC_SOCK_ANONYMOUS, cred);
 	if (err < 0 && err != -EAFNOSUPPORT)
 		goto out_close;
 
-	if (!nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
-		svc_get(nn->nfsd_serv);
-
-	nfsd_put(net);
 	return 0;
 out_close:
-	xprt = svc_find_xprt(nn->nfsd_serv, transport, net, PF_INET, port);
+	xprt = svc_find_xprt(serv, transport, net, PF_INET, port);
 	if (xprt != NULL) {
 		svc_xprt_close(xprt);
 		svc_xprt_put(xprt);
 	}
 out_err:
-	nfsd_put(net);
+	if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks))
+		nfsd_destroy_serv(net);
+
 	return err;
 }
 
@@ -1013,6 +1017,7 @@ static ssize_t write_gracetime(struct file *file, char *buf, size_t size)
 	return nfsd4_write_time(file, buf, size, &nn->nfsd4_grace, nn);
 }
 
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
 static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size,
 				   struct nfsd_net *nn)
 {
@@ -1073,6 +1078,7 @@ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size)
 	mutex_unlock(&nfsd_mutex);
 	return rv;
 }
+#endif
 
 /*
  * write_v4_end_grace - release grace period for nfsd's v4.x lock manager
@@ -1510,11 +1516,10 @@ int nfsd_nl_rpc_status_get_start(struct netlink_callback *cb)
 	int ret = -ENODEV;
 
 	mutex_lock(&nfsd_mutex);
-	if (nn->nfsd_serv) {
-		svc_get(nn->nfsd_serv);
+	if (nn->nfsd_serv)
 		ret = 0;
-	}
-	mutex_unlock(&nfsd_mutex);
+	else
+		mutex_unlock(&nfsd_mutex);
 
 	return ret;
 }
@@ -1686,8 +1691,6 @@ out:
  */
 int nfsd_nl_rpc_status_get_done(struct netlink_callback *cb)
 {
-	mutex_lock(&nfsd_mutex);
-	nfsd_put(sock_net(cb->skb->sk));
 	mutex_unlock(&nfsd_mutex);
 
 	return 0;
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index f5ff42f41ee7..304e9728b929 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -113,13 +113,6 @@ int		nfsd_pool_stats_open(struct inode *, struct file *);
 int		nfsd_pool_stats_release(struct inode *, struct file *);
 void		nfsd_shutdown_threads(struct net *net);
 
-static inline void nfsd_put(struct net *net)
-{
-	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
-
-	svc_put(nn->nfsd_serv);
-}
-
 bool		i_am_nfsd(void);
 
 struct nfsdfs_client {
@@ -155,6 +148,7 @@ int nfsd_vers(struct nfsd_net *nn, int vers, enum vers_op change);
 int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change);
 void nfsd_reset_versions(struct nfsd_net *nn);
 int nfsd_create_serv(struct net *net);
+void nfsd_destroy_serv(struct net *net);
 
 extern int nfsd_max_blksize;
 
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index d6122bb2d167..a667802e08e7 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -59,15 +59,6 @@ static __be32			nfsd_init_request(struct svc_rqst *,
  * nfsd_mutex protects nn->nfsd_serv -- both the pointer itself and some members
  * of the svc_serv struct such as ->sv_temp_socks and ->sv_permsocks.
  *
- * If (out side the lock) nn->nfsd_serv is non-NULL, then it must point to a
- * properly initialised 'struct svc_serv' with ->sv_nrthreads > 0 (unless
- * nn->keep_active is set).  That number of nfsd threads must
- * exist and each must be listed in ->sp_all_threads in some entry of
- * ->sv_pools[].
- *
- * Each active thread holds a counted reference on nn->nfsd_serv, as does
- * the nn->keep_active flag and various transient calls to svc_get().
- *
  * Finally, the nfsd_mutex also protects some of the global variables that are
  * accessed when nfsd starts and that are settable via the write_* routines in
  * nfsctl.c. In particular:
@@ -359,13 +350,12 @@ static bool nfsd_needs_lockd(struct nfsd_net *nn)
  */
 void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn)
 {
-	int seq = 0;
+	unsigned int seq;
 
 	do {
-		read_seqbegin_or_lock(&nn->writeverf_lock, &seq);
+		seq = read_seqbegin(&nn->writeverf_lock);
 		memcpy(verf, nn->writeverf, sizeof(nn->writeverf));
-	} while (need_seqretry(&nn->writeverf_lock, seq));
-	done_seqretry(&nn->writeverf_lock, seq);
+	} while (read_seqretry(&nn->writeverf_lock, seq));
 }
 
 static void nfsd_reset_write_verifier_locked(struct nfsd_net *nn)
@@ -542,7 +532,11 @@ static struct notifier_block nfsd_inet6addr_notifier = {
 /* Only used under nfsd_mutex, so this atomic may be overkill: */
 static atomic_t nfsd_notifier_refcount = ATOMIC_INIT(0);
 
-static void nfsd_last_thread(struct net *net)
+/**
+ * nfsd_destroy_serv - tear down NFSD's svc_serv for a namespace
+ * @net: network namespace the NFS service is associated with
+ */
+void nfsd_destroy_serv(struct net *net)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 	struct svc_serv *serv = nn->nfsd_serv;
@@ -564,7 +558,7 @@ static void nfsd_last_thread(struct net *net)
 	/*
 	 * write_ports can create the server without actually starting
 	 * any threads--if we get shut down before any threads are
-	 * started, then nfsd_last_thread will be run before any of this
+	 * started, then nfsd_destroy_serv will be run before any of this
 	 * other initialization has been done except the rpcb information.
 	 */
 	svc_rpcb_cleanup(serv, net);
@@ -573,6 +567,7 @@ static void nfsd_last_thread(struct net *net)
 
 	nfsd_shutdown_net(net);
 	nfsd_export_flush(net);
+	svc_destroy(&serv);
 }
 
 void nfsd_reset_versions(struct nfsd_net *nn)
@@ -647,11 +642,9 @@ void nfsd_shutdown_threads(struct net *net)
 		return;
 	}
 
-	svc_get(serv);
 	/* Kill outstanding nfsd threads */
 	svc_set_num_threads(serv, NULL, 0);
-	nfsd_last_thread(net);
-	svc_put(serv);
+	nfsd_destroy_serv(net);
 	mutex_unlock(&nfsd_mutex);
 }
 
@@ -667,10 +660,9 @@ int nfsd_create_serv(struct net *net)
 	struct svc_serv *serv;
 
 	WARN_ON(!mutex_is_locked(&nfsd_mutex));
-	if (nn->nfsd_serv) {
-		svc_get(nn->nfsd_serv);
+	if (nn->nfsd_serv)
 		return 0;
-	}
+
 	if (nfsd_max_blksize == 0)
 		nfsd_max_blksize = nfsd_get_default_max_blksize();
 	nfsd_reset_versions(nn);
@@ -681,10 +673,11 @@ int nfsd_create_serv(struct net *net)
 	serv->sv_maxconn = nn->max_connections;
 	error = svc_bind(serv, net);
 	if (error < 0) {
-		svc_put(serv);
+		svc_destroy(&serv);
 		return error;
 	}
 	spin_lock(&nfsd_notifier_lock);
+	nn->nfsd_info.mutex = &nfsd_mutex;
 	nn->nfsd_serv = serv;
 	spin_unlock(&nfsd_notifier_lock);
 
@@ -764,7 +757,6 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
 		nthreads[0] = 1;
 
 	/* apply the new numbers */
-	svc_get(nn->nfsd_serv);
 	for (i = 0; i < n; i++) {
 		err = svc_set_num_threads(nn->nfsd_serv,
 					  &nn->nfsd_serv->sv_pools[i],
@@ -772,7 +764,6 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
 		if (err)
 			break;
 	}
-	svc_put(nn->nfsd_serv);
 	return err;
 }
 
@@ -814,13 +805,8 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred)
 		goto out_put;
 	error = serv->sv_nrthreads;
 out_put:
-	/* Threads now hold service active */
-	if (xchg(&nn->keep_active, 0))
-		svc_put(serv);
-
 	if (serv->sv_nrthreads == 0)
-		nfsd_last_thread(net);
-	svc_put(serv);
+		nfsd_destroy_serv(net);
 out:
 	mutex_unlock(&nfsd_mutex);
 	return error;
@@ -955,7 +941,6 @@ nfsd(void *vrqstp)
 		rqstp->rq_server->sv_maxconn = nn->max_connections;
 
 		svc_recv(rqstp);
-		validate_process_creds();
 	}
 
 	atomic_dec(&nfsdstats.th_cnt);
@@ -981,6 +966,8 @@ int nfsd_dispatch(struct svc_rqst *rqstp)
 	const struct svc_procedure *proc = rqstp->rq_procinfo;
 	__be32 *statp = rqstp->rq_accept_statp;
 	struct nfsd_cacherep *rp;
+	unsigned int start, len;
+	__be32 *nfs_reply;
 
 	/*
 	 * Give the xdr decoder a chance to change this if it wants
@@ -988,6 +975,13 @@ int nfsd_dispatch(struct svc_rqst *rqstp)
 	 */
 	rqstp->rq_cachetype = proc->pc_cachetype;
 
+	/*
+	 * ->pc_decode advances the argument stream past the NFS
+	 * Call header, so grab the header's starting location and
+	 * size now for the call to nfsd_cache_lookup().
+	 */
+	start = xdr_stream_pos(&rqstp->rq_arg_stream);
+	len = xdr_stream_remaining(&rqstp->rq_arg_stream);
 	if (!proc->pc_decode(rqstp, &rqstp->rq_arg_stream))
 		goto out_decode_err;
 
@@ -1001,7 +995,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp)
 	smp_store_release(&rqstp->rq_status_counter, rqstp->rq_status_counter | 1);
 
 	rp = NULL;
-	switch (nfsd_cache_lookup(rqstp, &rp)) {
+	switch (nfsd_cache_lookup(rqstp, start, len, &rp)) {
 	case RC_DOIT:
 		break;
 	case RC_REPLY:
@@ -1010,6 +1004,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp)
 		goto out_dropit;
 	}
 
+	nfs_reply = xdr_inline_decode(&rqstp->rq_res_stream, 0);
 	*statp = proc->pc_func(rqstp);
 	if (test_bit(RQ_DROPME, &rqstp->rq_flags))
 		goto out_update_drop;
@@ -1023,7 +1018,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp)
 	 */
 	smp_store_release(&rqstp->rq_status_counter, rqstp->rq_status_counter + 1);
 
-	nfsd_cache_update(rqstp, rp, rqstp->rq_cachetype, statp + 1);
+	nfsd_cache_update(rqstp, rp, rqstp->rq_cachetype, nfs_reply);
 out_cached_reply:
 	return 1;
 
@@ -1074,28 +1069,7 @@ bool nfssvc_encode_voidres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 
 int nfsd_pool_stats_open(struct inode *inode, struct file *file)
 {
-	int ret;
 	struct nfsd_net *nn = net_generic(inode->i_sb->s_fs_info, nfsd_net_id);
 
-	mutex_lock(&nfsd_mutex);
-	if (nn->nfsd_serv == NULL) {
-		mutex_unlock(&nfsd_mutex);
-		return -ENODEV;
-	}
-	svc_get(nn->nfsd_serv);
-	ret = svc_pool_stats_open(nn->nfsd_serv, file);
-	mutex_unlock(&nfsd_mutex);
-	return ret;
-}
-
-int nfsd_pool_stats_release(struct inode *inode, struct file *file)
-{
-	struct seq_file *seq = file->private_data;
-	struct svc_serv *serv = seq->private;
-	int ret = seq_release(inode, file);
-
-	mutex_lock(&nfsd_mutex);
-	svc_put(serv);
-	mutex_unlock(&nfsd_mutex);
-	return ret;
+	return svc_pool_stats_open(&nn->nfsd_info, file);
 }
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index f96eaa8e9413..41bdc913fa71 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -117,24 +117,6 @@ struct nfs4_cpntf_state {
 	time64_t		cpntf_time;	/* last time stateid used */
 };
 
-struct nfs4_cb_fattr {
-	struct nfsd4_callback ncf_getattr;
-	u32 ncf_cb_status;
-	u32 ncf_cb_bmap[1];
-
-	/* from CB_GETATTR reply */
-	u64 ncf_cb_change;
-	u64 ncf_cb_fsize;
-
-	unsigned long ncf_cb_flags;
-	bool ncf_file_modified;
-	u64 ncf_initial_cinfo;
-	u64 ncf_cur_fsize;
-};
-
-/* bits for ncf_cb_flags */
-#define	CB_GETATTR_BUSY		0
-
 /*
  * Represents a delegation stateid. The nfs4_client holds references to these
  * and they are put when it is being destroyed or when the delegation is
@@ -168,9 +150,6 @@ struct nfs4_delegation {
 	int			dl_retries;
 	struct nfsd4_callback	dl_recall;
 	bool			dl_recalled;
-
-	/* for CB_GETATTR */
-	struct nfs4_cb_fattr    dl_cb_fattr;
 };
 
 #define cb_to_delegation(cb) \
@@ -661,7 +640,6 @@ enum nfsd4_cb_op {
 	NFSPROC4_CLNT_CB_SEQUENCE,
 	NFSPROC4_CLNT_CB_NOTIFY_LOCK,
 	NFSPROC4_CLNT_CB_RECALL_ANY,
-	NFSPROC4_CLNT_CB_GETATTR,
 };
 
 /* Returns true iff a is later than b: */
@@ -754,6 +732,5 @@ static inline bool try_to_expire_client(struct nfs4_client *clp)
 }
 
 extern __be32 nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp,
-		struct inode *inode, bool *file_modified, u64 *size);
-extern void nfs4_cb_getattr(struct nfs4_cb_fattr *ncf);
+				struct inode *inode);
 #endif   /* NFSD4_STATE_H */
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index fbc0ccb40424..d1e8cf079b0f 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -1262,28 +1262,6 @@ TRACE_EVENT(nfsd_drc_mismatch,
 		__entry->ingress)
 );
 
-TRACE_EVENT_CONDITION(nfsd_drc_gc,
-	TP_PROTO(
-		const struct nfsd_net *nn,
-		unsigned long freed
-	),
-	TP_ARGS(nn, freed),
-	TP_CONDITION(freed > 0),
-	TP_STRUCT__entry(
-		__field(unsigned long long, boot_time)
-		__field(unsigned long, freed)
-		__field(int, total)
-	),
-	TP_fast_assign(
-		__entry->boot_time = nn->boot_time;
-		__entry->freed = freed;
-		__entry->total = atomic_read(&nn->num_drc_entries);
-	),
-	TP_printk("boot_time=%16llx total=%d freed=%lu",
-		__entry->boot_time, __entry->total, __entry->freed
-	)
-);
-
 TRACE_EVENT(nfsd_cb_args,
 	TP_PROTO(
 		const struct nfs4_client *clp,
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index fbbea7498f02..6e7e37192461 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -901,7 +901,6 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
 	int host_err;
 	bool retried = false;
 
-	validate_process_creds();
 	/*
 	 * If we get here, then the client has already done an "open",
 	 * and (hopefully) checked permission - so allow OWNER_OVERRIDE
@@ -926,7 +925,6 @@ retry:
 		}
 		err = nfserrno(host_err);
 	}
-	validate_process_creds();
 	return err;
 }
 
@@ -943,12 +941,7 @@ int
 nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp, int may_flags,
 		   struct file **filp)
 {
-	int err;
-
-	validate_process_creds();
-	err = __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp);
-	validate_process_creds();
-	return err;
+	return __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp);
 }
 
 /*
@@ -1046,7 +1039,10 @@ __be32 nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	ssize_t host_err;
 
 	trace_nfsd_read_splice(rqstp, fhp, offset, *count);
-	host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor);
+	host_err = rw_verify_area(READ, file, &offset, *count);
+	if (!host_err)
+		host_err = splice_direct_to_actor(file, &sd,
+						  nfsd_direct_splice_actor);
 	return nfsd_finish_read(rqstp, fhp, file, offset, count, eof, host_err);
 }
 
@@ -1183,9 +1179,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
 	since = READ_ONCE(file->f_wb_err);
 	if (verf)
 		nfsd_copy_write_verifier(verf, nn);
-	file_start_write(file);
 	host_err = vfs_iter_write(file, &iter, &pos, flags);
-	file_end_write(file);
 	if (host_err < 0) {
 		commit_reset_write_verifier(nn, rqstp, host_err);
 		goto out_nfserr;
@@ -1217,6 +1211,30 @@ out_nfserr:
 }
 
 /**
+ * nfsd_read_splice_ok - check if spliced reading is supported
+ * @rqstp: RPC transaction context
+ *
+ * Return values:
+ *   %true: nfsd_splice_read() may be used
+ *   %false: nfsd_splice_read() must not be used
+ *
+ * NFS READ normally uses splice to send data in-place. However the
+ * data in cache can change after the reply's MIC is computed but
+ * before the RPC reply is sent. To prevent the client from
+ * rejecting the server-computed MIC in this somewhat rare case, do
+ * not use splice with the GSS integrity and privacy services.
+ */
+bool nfsd_read_splice_ok(struct svc_rqst *rqstp)
+{
+	switch (svc_auth_flavor(rqstp)) {
+	case RPC_AUTH_GSS_KRB5I:
+	case RPC_AUTH_GSS_KRB5P:
+		return false;
+	}
+	return true;
+}
+
+/**
  * nfsd_read - Read data from a file
  * @rqstp: RPC transaction context
  * @fhp: file handle of file to be read
@@ -1245,7 +1263,7 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		return err;
 
 	file = nf->nf_file;
-	if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &rqstp->rq_flags))
+	if (file->f_op->splice_read && nfsd_read_splice_ok(rqstp))
 		err = nfsd_splice_read(rqstp, fhp, file, offset, count, eof);
 	else
 		err = nfsd_iter_read(rqstp, fhp, file, offset, count, 0, eof);
@@ -2109,9 +2127,23 @@ static __be32 nfsd_buffered_readdir(struct file *file, struct svc_fh *fhp,
 	return cdp->err;
 }
 
-/*
- * Read entries from a directory.
- * The  NFSv3/4 verifier we ignore for now.
+/**
+ * nfsd_readdir - Read entries from a directory
+ * @rqstp: RPC transaction context
+ * @fhp: NFS file handle of directory to be read
+ * @offsetp: OUT: seek offset of final entry that was read
+ * @cdp: OUT: an eof error value
+ * @func: entry filler actor
+ *
+ * This implementation ignores the NFSv3/4 verifier cookie.
+ *
+ * NB: normal system calls hold file->f_pos_lock when calling
+ * ->iterate_shared and ->llseek, but nfsd_readdir() does not.
+ * Because the struct file acquired here is not visible to other
+ * threads, it's internal state does not need mutex protection.
+ *
+ * Returns nfs_ok on success, otherwise an nfsstat code is
+ * returned.
  */
 __be32
 nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, 
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index e3c29596f4df..702fbc4483bf 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -114,6 +114,7 @@ __be32		nfsd_iter_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
 				struct file *file, loff_t offset,
 				unsigned long *count, unsigned int base,
 				u32 *eof);
+bool		nfsd_read_splice_ok(struct svc_rqst *rqstp);
 __be32		nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
 				loff_t offset, unsigned long *count,
 				u32 *eof);
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 80e859dc84d8..415516c1b27e 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -840,6 +840,7 @@ struct nfsd4_compoundargs {
 	u32				minorversion;
 	u32				client_opcnt;
 	u32				opcnt;
+	bool				splice_ok;
 	struct nfsd4_op			*ops;
 	struct nfsd4_op			iops[8];
 };
diff --git a/fs/nfsd/xdr4cb.h b/fs/nfsd/xdr4cb.h
index e8b00309c449..0d39af1b00a0 100644
--- a/fs/nfsd/xdr4cb.h
+++ b/fs/nfsd/xdr4cb.h
@@ -54,21 +54,3 @@
 #define NFS4_dec_cb_recall_any_sz	(cb_compound_dec_hdr_sz  +      \
 					cb_sequence_dec_sz +            \
 					op_dec_sz)
-
-/*
- * 1: CB_GETATTR opcode (32-bit)
- * N: file_handle
- * 1: number of entry in attribute array (32-bit)
- * 1: entry 0 in attribute array (32-bit)
- */
-#define NFS4_enc_cb_getattr_sz		(cb_compound_enc_hdr_sz +       \
-					cb_sequence_enc_sz +            \
-					1 + enc_nfs4_fh_sz + 1 + 1)
-/*
- * 4: fattr_bitmap_maxsz
- * 1: attribute array len
- * 2: change attr (64-bit)
- * 2: size (64-bit)
- */
-#define NFS4_dec_cb_getattr_sz		(cb_compound_dec_hdr_sz  +      \
-			cb_sequence_dec_sz + 4 + 1 + 2 + 2 + op_dec_sz)
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index 5710833ac1cc..0131d83b912d 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -64,8 +64,8 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr)
 	set_buffer_mapped(bh);
 	set_buffer_uptodate(bh);
 
-	unlock_page(bh->b_page);
-	put_page(bh->b_page);
+	folio_unlock(bh->b_folio);
+	folio_put(bh->b_folio);
 	return bh;
 }
 
@@ -75,7 +75,7 @@ int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr,
 {
 	struct buffer_head *bh;
 	struct inode *inode = btnc->host;
-	struct page *page;
+	struct folio *folio;
 	int err;
 
 	bh = nilfs_grab_buffer(inode, btnc, blocknr, BIT(BH_NILFS_Node));
@@ -83,7 +83,7 @@ int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr,
 		return -ENOMEM;
 
 	err = -EEXIST; /* internal code */
-	page = bh->b_page;
+	folio = bh->b_folio;
 
 	if (buffer_uptodate(bh) || buffer_dirty(bh))
 		goto found;
@@ -130,8 +130,8 @@ found:
 	*pbh = bh;
 
 out_locked:
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 	return err;
 }
 
@@ -145,19 +145,19 @@ out_locked:
 void nilfs_btnode_delete(struct buffer_head *bh)
 {
 	struct address_space *mapping;
-	struct page *page = bh->b_page;
-	pgoff_t index = page_index(page);
+	struct folio *folio = bh->b_folio;
+	pgoff_t index = folio->index;
 	int still_dirty;
 
-	get_page(page);
-	lock_page(page);
-	wait_on_page_writeback(page);
+	folio_get(folio);
+	folio_lock(folio);
+	folio_wait_writeback(folio);
 
 	nilfs_forget_buffer(bh);
-	still_dirty = PageDirty(page);
-	mapping = page->mapping;
-	unlock_page(page);
-	put_page(page);
+	still_dirty = folio_test_dirty(folio);
+	mapping = folio->mapping;
+	folio_unlock(folio);
+	folio_put(folio);
 
 	if (!still_dirty && mapping)
 		invalidate_inode_pages2_range(mapping, index, index);
@@ -185,23 +185,23 @@ int nilfs_btnode_prepare_change_key(struct address_space *btnc,
 	ctxt->newbh = NULL;
 
 	if (inode->i_blkbits == PAGE_SHIFT) {
-		struct page *opage = obh->b_page;
-		lock_page(opage);
+		struct folio *ofolio = obh->b_folio;
+		folio_lock(ofolio);
 retry:
 		/* BUG_ON(oldkey != obh->b_folio->index); */
-		if (unlikely(oldkey != opage->index))
-			NILFS_PAGE_BUG(opage,
+		if (unlikely(oldkey != ofolio->index))
+			NILFS_FOLIO_BUG(ofolio,
 				       "invalid oldkey %lld (newkey=%lld)",
 				       (unsigned long long)oldkey,
 				       (unsigned long long)newkey);
 
 		xa_lock_irq(&btnc->i_pages);
-		err = __xa_insert(&btnc->i_pages, newkey, opage, GFP_NOFS);
+		err = __xa_insert(&btnc->i_pages, newkey, ofolio, GFP_NOFS);
 		xa_unlock_irq(&btnc->i_pages);
 		/*
-		 * Note: page->index will not change to newkey until
+		 * Note: folio->index will not change to newkey until
 		 * nilfs_btnode_commit_change_key() will be called.
-		 * To protect the page in intermediate state, the page lock
+		 * To protect the folio in intermediate state, the folio lock
 		 * is held.
 		 */
 		if (!err)
@@ -213,7 +213,7 @@ retry:
 		if (!err)
 			goto retry;
 		/* fallback to copy mode */
-		unlock_page(opage);
+		folio_unlock(ofolio);
 	}
 
 	nbh = nilfs_btnode_create_block(btnc, newkey);
@@ -225,7 +225,7 @@ retry:
 	return 0;
 
  failed_unlock:
-	unlock_page(obh->b_page);
+	folio_unlock(obh->b_folio);
 	return err;
 }
 
@@ -238,15 +238,15 @@ void nilfs_btnode_commit_change_key(struct address_space *btnc,
 {
 	struct buffer_head *obh = ctxt->bh, *nbh = ctxt->newbh;
 	__u64 oldkey = ctxt->oldkey, newkey = ctxt->newkey;
-	struct page *opage;
+	struct folio *ofolio;
 
 	if (oldkey == newkey)
 		return;
 
 	if (nbh == NULL) {	/* blocksize == pagesize */
-		opage = obh->b_page;
-		if (unlikely(oldkey != opage->index))
-			NILFS_PAGE_BUG(opage,
+		ofolio = obh->b_folio;
+		if (unlikely(oldkey != ofolio->index))
+			NILFS_FOLIO_BUG(ofolio,
 				       "invalid oldkey %lld (newkey=%lld)",
 				       (unsigned long long)oldkey,
 				       (unsigned long long)newkey);
@@ -257,8 +257,8 @@ void nilfs_btnode_commit_change_key(struct address_space *btnc,
 		__xa_set_mark(&btnc->i_pages, newkey, PAGECACHE_TAG_DIRTY);
 		xa_unlock_irq(&btnc->i_pages);
 
-		opage->index = obh->b_blocknr = newkey;
-		unlock_page(opage);
+		ofolio->index = obh->b_blocknr = newkey;
+		folio_unlock(ofolio);
 	} else {
 		nilfs_copy_buffer(nbh, obh);
 		mark_buffer_dirty(nbh);
@@ -284,7 +284,7 @@ void nilfs_btnode_abort_change_key(struct address_space *btnc,
 
 	if (nbh == NULL) {	/* blocksize == pagesize */
 		xa_erase_irq(&btnc->i_pages, newkey);
-		unlock_page(ctxt->bh->b_page);
+		folio_unlock(ctxt->bh->b_folio);
 	} else {
 		/*
 		 * When canceling a buffer that a prepare operation has
diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c
index 9ebefb3acb0e..39136637f715 100644
--- a/fs/nilfs2/cpfile.c
+++ b/fs/nilfs2/cpfile.c
@@ -552,11 +552,29 @@ static ssize_t nilfs_cpfile_do_get_ssinfo(struct inode *cpfile, __u64 *cnop,
 }
 
 /**
- * nilfs_cpfile_get_cpinfo -
- * @cpfile:
- * @cno:
- * @ci:
- * @nci:
+ * nilfs_cpfile_get_cpinfo - get information on checkpoints
+ * @cpfile: checkpoint file inode
+ * @cnop:   place to pass a starting checkpoint number and receive a
+ *          checkpoint number to continue the search
+ * @mode:   mode of checkpoints that the caller wants to retrieve
+ * @buf:    buffer for storing checkpoints' information
+ * @cisz:   byte size of one checkpoint info item in array
+ * @nci:    number of checkpoint info items to retrieve
+ *
+ * nilfs_cpfile_get_cpinfo() searches for checkpoints in @mode state
+ * starting from the checkpoint number stored in @cnop, and stores
+ * information about found checkpoints in @buf.
+ * The buffer pointed to by @buf must be large enough to store information
+ * for @nci checkpoints.  If at least one checkpoint information is
+ * successfully retrieved, @cnop is updated to point to the checkpoint
+ * number to continue searching.
+ *
+ * Return: Count of checkpoint info items stored in the output buffer on
+ * success, or the following negative error code on failure.
+ * * %-EINVAL	- Invalid checkpoint mode.
+ * * %-ENOMEM	- Insufficient memory available.
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOENT	- Invalid checkpoint number specified.
  */
 
 ssize_t nilfs_cpfile_get_cpinfo(struct inode *cpfile, __u64 *cnop, int mode,
diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index de2073c47651..bc846b904b68 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -64,12 +64,6 @@ static inline unsigned int nilfs_chunk_size(struct inode *inode)
 	return inode->i_sb->s_blocksize;
 }
 
-static inline void nilfs_put_page(struct page *page)
-{
-	kunmap(page);
-	put_page(page);
-}
-
 /*
  * Return the offset into page `page_nr' of the last valid
  * byte in that page, plus one.
@@ -84,48 +78,46 @@ static unsigned int nilfs_last_byte(struct inode *inode, unsigned long page_nr)
 	return last_byte;
 }
 
-static int nilfs_prepare_chunk(struct page *page, unsigned int from,
+static int nilfs_prepare_chunk(struct folio *folio, unsigned int from,
 			       unsigned int to)
 {
-	loff_t pos = page_offset(page) + from;
+	loff_t pos = folio_pos(folio) + from;
 
-	return __block_write_begin(page, pos, to - from, nilfs_get_block);
+	return __block_write_begin(&folio->page, pos, to - from, nilfs_get_block);
 }
 
-static void nilfs_commit_chunk(struct page *page,
-			       struct address_space *mapping,
-			       unsigned int from, unsigned int to)
+static void nilfs_commit_chunk(struct folio *folio,
+		struct address_space *mapping, size_t from, size_t to)
 {
 	struct inode *dir = mapping->host;
-	loff_t pos = page_offset(page) + from;
-	unsigned int len = to - from;
-	unsigned int nr_dirty, copied;
+	loff_t pos = folio_pos(folio) + from;
+	size_t copied, len = to - from;
+	unsigned int nr_dirty;
 	int err;
 
-	nr_dirty = nilfs_page_count_clean_buffers(page, from, to);
-	copied = block_write_end(NULL, mapping, pos, len, len, page, NULL);
+	nr_dirty = nilfs_page_count_clean_buffers(&folio->page, from, to);
+	copied = block_write_end(NULL, mapping, pos, len, len, &folio->page, NULL);
 	if (pos + copied > dir->i_size)
 		i_size_write(dir, pos + copied);
 	if (IS_DIRSYNC(dir))
 		nilfs_set_transaction_flag(NILFS_TI_SYNC);
 	err = nilfs_set_file_dirty(dir, nr_dirty);
 	WARN_ON(err); /* do not happen */
-	unlock_page(page);
+	folio_unlock(folio);
 }
 
-static bool nilfs_check_page(struct page *page)
+static bool nilfs_check_folio(struct folio *folio, char *kaddr)
 {
-	struct inode *dir = page->mapping->host;
+	struct inode *dir = folio->mapping->host;
 	struct super_block *sb = dir->i_sb;
 	unsigned int chunk_size = nilfs_chunk_size(dir);
-	char *kaddr = page_address(page);
-	unsigned int offs, rec_len;
-	unsigned int limit = PAGE_SIZE;
+	size_t offs, rec_len;
+	size_t limit = folio_size(folio);
 	struct nilfs_dir_entry *p;
 	char *error;
 
-	if ((dir->i_size >> PAGE_SHIFT) == page->index) {
-		limit = dir->i_size & ~PAGE_MASK;
+	if (dir->i_size < folio_pos(folio) + limit) {
+		limit = dir->i_size - folio_pos(folio);
 		if (limit & (chunk_size - 1))
 			goto Ebadsize;
 		if (!limit)
@@ -147,7 +139,7 @@ static bool nilfs_check_page(struct page *page)
 	if (offs != limit)
 		goto Eend;
 out:
-	SetPageChecked(page);
+	folio_set_checked(folio);
 	return true;
 
 	/* Too bad, we had an error */
@@ -170,8 +162,8 @@ Espan:
 	error = "directory entry across blocks";
 bad_entry:
 	nilfs_error(sb,
-		    "bad entry in directory #%lu: %s - offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
-		    dir->i_ino, error, (page->index << PAGE_SHIFT) + offs,
+		    "bad entry in directory #%lu: %s - offset=%lu, inode=%lu, rec_len=%zd, name_len=%d",
+		    dir->i_ino, error, (folio->index << PAGE_SHIFT) + offs,
 		    (unsigned long)le64_to_cpu(p->inode),
 		    rec_len, p->name_len);
 	goto fail;
@@ -179,29 +171,34 @@ Eend:
 	p = (struct nilfs_dir_entry *)(kaddr + offs);
 	nilfs_error(sb,
 		    "entry in directory #%lu spans the page boundary offset=%lu, inode=%lu",
-		    dir->i_ino, (page->index << PAGE_SHIFT) + offs,
+		    dir->i_ino, (folio->index << PAGE_SHIFT) + offs,
 		    (unsigned long)le64_to_cpu(p->inode));
 fail:
-	SetPageError(page);
+	folio_set_error(folio);
 	return false;
 }
 
-static struct page *nilfs_get_page(struct inode *dir, unsigned long n)
+static void *nilfs_get_folio(struct inode *dir, unsigned long n,
+		struct folio **foliop)
 {
 	struct address_space *mapping = dir->i_mapping;
-	struct page *page = read_mapping_page(mapping, n, NULL);
+	struct folio *folio = read_mapping_folio(mapping, n, NULL);
+	void *kaddr;
 
-	if (!IS_ERR(page)) {
-		kmap(page);
-		if (unlikely(!PageChecked(page))) {
-			if (!nilfs_check_page(page))
-				goto fail;
-		}
+	if (IS_ERR(folio))
+		return folio;
+
+	kaddr = kmap_local_folio(folio, 0);
+	if (unlikely(!folio_test_checked(folio))) {
+		if (!nilfs_check_folio(folio, kaddr))
+			goto fail;
 	}
-	return page;
+
+	*foliop = folio;
+	return kaddr;
 
 fail:
-	nilfs_put_page(page);
+	folio_release_kmap(folio, kaddr);
 	return ERR_PTR(-EIO);
 }
 
@@ -275,21 +272,21 @@ static int nilfs_readdir(struct file *file, struct dir_context *ctx)
 	for ( ; n < npages; n++, offset = 0) {
 		char *kaddr, *limit;
 		struct nilfs_dir_entry *de;
-		struct page *page = nilfs_get_page(inode, n);
+		struct folio *folio;
 
-		if (IS_ERR(page)) {
+		kaddr = nilfs_get_folio(inode, n, &folio);
+		if (IS_ERR(kaddr)) {
 			nilfs_error(sb, "bad page in #%lu", inode->i_ino);
 			ctx->pos += PAGE_SIZE - offset;
 			return -EIO;
 		}
-		kaddr = page_address(page);
 		de = (struct nilfs_dir_entry *)(kaddr + offset);
 		limit = kaddr + nilfs_last_byte(inode, n) -
 			NILFS_DIR_REC_LEN(1);
 		for ( ; (char *)de <= limit; de = nilfs_next_entry(de)) {
 			if (de->rec_len == 0) {
 				nilfs_error(sb, "zero-length directory entry");
-				nilfs_put_page(page);
+				folio_release_kmap(folio, kaddr);
 				return -EIO;
 			}
 			if (de->inode) {
@@ -302,72 +299,67 @@ static int nilfs_readdir(struct file *file, struct dir_context *ctx)
 
 				if (!dir_emit(ctx, de->name, de->name_len,
 						le64_to_cpu(de->inode), t)) {
-					nilfs_put_page(page);
+					folio_release_kmap(folio, kaddr);
 					return 0;
 				}
 			}
 			ctx->pos += nilfs_rec_len_from_disk(de->rec_len);
 		}
-		nilfs_put_page(page);
+		folio_release_kmap(folio, kaddr);
 	}
 	return 0;
 }
 
 /*
- *	nilfs_find_entry()
+ * nilfs_find_entry()
+ *
+ * Finds an entry in the specified directory with the wanted name. It
+ * returns the folio in which the entry was found, and the entry itself.
+ * The folio is mapped and unlocked.  When the caller is finished with
+ * the entry, it should call folio_release_kmap().
  *
- * finds an entry in the specified directory with the wanted name. It
- * returns the page in which the entry was found, and the entry itself
- * (as a parameter - res_dir). Page is returned mapped and unlocked.
- * Entry is guaranteed to be valid.
+ * On failure, returns NULL and the caller should ignore foliop.
  */
-struct nilfs_dir_entry *
-nilfs_find_entry(struct inode *dir, const struct qstr *qstr,
-		 struct page **res_page)
+struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir,
+		const struct qstr *qstr, struct folio **foliop)
 {
 	const unsigned char *name = qstr->name;
 	int namelen = qstr->len;
 	unsigned int reclen = NILFS_DIR_REC_LEN(namelen);
 	unsigned long start, n;
 	unsigned long npages = dir_pages(dir);
-	struct page *page = NULL;
 	struct nilfs_inode_info *ei = NILFS_I(dir);
 	struct nilfs_dir_entry *de;
 
 	if (npages == 0)
 		goto out;
 
-	/* OFFSET_CACHE */
-	*res_page = NULL;
-
 	start = ei->i_dir_start_lookup;
 	if (start >= npages)
 		start = 0;
 	n = start;
 	do {
-		char *kaddr;
+		char *kaddr = nilfs_get_folio(dir, n, foliop);
 
-		page = nilfs_get_page(dir, n);
-		if (!IS_ERR(page)) {
-			kaddr = page_address(page);
+		if (!IS_ERR(kaddr)) {
 			de = (struct nilfs_dir_entry *)kaddr;
 			kaddr += nilfs_last_byte(dir, n) - reclen;
 			while ((char *) de <= kaddr) {
 				if (de->rec_len == 0) {
 					nilfs_error(dir->i_sb,
 						"zero-length directory entry");
-					nilfs_put_page(page);
+					folio_release_kmap(*foliop, kaddr);
 					goto out;
 				}
 				if (nilfs_match(namelen, name, de))
 					goto found;
 				de = nilfs_next_entry(de);
 			}
-			nilfs_put_page(page);
+			folio_release_kmap(*foliop, kaddr);
 		}
 		if (++n >= npages)
 			n = 0;
-		/* next page is past the blocks we've got */
+		/* next folio is past the blocks we've got */
 		if (unlikely(n > (dir->i_blocks >> (PAGE_SHIFT - 9)))) {
 			nilfs_error(dir->i_sb,
 			       "dir %lu size %lld exceeds block count %llu",
@@ -380,55 +372,47 @@ out:
 	return NULL;
 
 found:
-	*res_page = page;
 	ei->i_dir_start_lookup = n;
 	return de;
 }
 
-struct nilfs_dir_entry *nilfs_dotdot(struct inode *dir, struct page **p)
+struct nilfs_dir_entry *nilfs_dotdot(struct inode *dir, struct folio **foliop)
 {
-	struct page *page = nilfs_get_page(dir, 0);
-	struct nilfs_dir_entry *de = NULL;
+	struct nilfs_dir_entry *de = nilfs_get_folio(dir, 0, foliop);
 
-	if (!IS_ERR(page)) {
-		de = nilfs_next_entry(
-			(struct nilfs_dir_entry *)page_address(page));
-		*p = page;
-	}
-	return de;
+	if (IS_ERR(de))
+		return NULL;
+	return nilfs_next_entry(de);
 }
 
 ino_t nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr)
 {
 	ino_t res = 0;
 	struct nilfs_dir_entry *de;
-	struct page *page;
+	struct folio *folio;
 
-	de = nilfs_find_entry(dir, qstr, &page);
+	de = nilfs_find_entry(dir, qstr, &folio);
 	if (de) {
 		res = le64_to_cpu(de->inode);
-		kunmap(page);
-		put_page(page);
+		folio_release_kmap(folio, de);
 	}
 	return res;
 }
 
-/* Releases the page */
 void nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de,
-		    struct page *page, struct inode *inode)
+		    struct folio *folio, struct inode *inode)
 {
-	unsigned int from = (char *)de - (char *)page_address(page);
-	unsigned int to = from + nilfs_rec_len_from_disk(de->rec_len);
-	struct address_space *mapping = page->mapping;
+	size_t from = offset_in_folio(folio, de);
+	size_t to = from + nilfs_rec_len_from_disk(de->rec_len);
+	struct address_space *mapping = folio->mapping;
 	int err;
 
-	lock_page(page);
-	err = nilfs_prepare_chunk(page, from, to);
+	folio_lock(folio);
+	err = nilfs_prepare_chunk(folio, from, to);
 	BUG_ON(err);
 	de->inode = cpu_to_le64(inode->i_ino);
 	nilfs_set_de_type(de, inode);
-	nilfs_commit_chunk(page, mapping, from, to);
-	nilfs_put_page(page);
+	nilfs_commit_chunk(folio, mapping, from, to);
 	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
 }
 
@@ -443,31 +427,28 @@ int nilfs_add_link(struct dentry *dentry, struct inode *inode)
 	unsigned int chunk_size = nilfs_chunk_size(dir);
 	unsigned int reclen = NILFS_DIR_REC_LEN(namelen);
 	unsigned short rec_len, name_len;
-	struct page *page = NULL;
+	struct folio *folio = NULL;
 	struct nilfs_dir_entry *de;
 	unsigned long npages = dir_pages(dir);
 	unsigned long n;
-	char *kaddr;
-	unsigned int from, to;
+	size_t from, to;
 	int err;
 
 	/*
 	 * We take care of directory expansion in the same loop.
-	 * This code plays outside i_size, so it locks the page
+	 * This code plays outside i_size, so it locks the folio
 	 * to protect that region.
 	 */
 	for (n = 0; n <= npages; n++) {
+		char *kaddr = nilfs_get_folio(dir, n, &folio);
 		char *dir_end;
 
-		page = nilfs_get_page(dir, n);
-		err = PTR_ERR(page);
-		if (IS_ERR(page))
-			goto out;
-		lock_page(page);
-		kaddr = page_address(page);
+		if (IS_ERR(kaddr))
+			return PTR_ERR(kaddr);
+		folio_lock(folio);
 		dir_end = kaddr + nilfs_last_byte(dir, n);
 		de = (struct nilfs_dir_entry *)kaddr;
-		kaddr += PAGE_SIZE - reclen;
+		kaddr += folio_size(folio) - reclen;
 		while ((char *)de <= kaddr) {
 			if ((char *)de == dir_end) {
 				/* We hit i_size */
@@ -494,16 +475,16 @@ int nilfs_add_link(struct dentry *dentry, struct inode *inode)
 				goto got_it;
 			de = (struct nilfs_dir_entry *)((char *)de + rec_len);
 		}
-		unlock_page(page);
-		nilfs_put_page(page);
+		folio_unlock(folio);
+		folio_release_kmap(folio, kaddr);
 	}
 	BUG();
 	return -EINVAL;
 
 got_it:
-	from = (char *)de - (char *)page_address(page);
+	from = offset_in_folio(folio, de);
 	to = from + rec_len;
-	err = nilfs_prepare_chunk(page, from, to);
+	err = nilfs_prepare_chunk(folio, from, to);
 	if (err)
 		goto out_unlock;
 	if (de->inode) {
@@ -518,29 +499,28 @@ got_it:
 	memcpy(de->name, name, namelen);
 	de->inode = cpu_to_le64(inode->i_ino);
 	nilfs_set_de_type(de, inode);
-	nilfs_commit_chunk(page, page->mapping, from, to);
+	nilfs_commit_chunk(folio, folio->mapping, from, to);
 	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
 	nilfs_mark_inode_dirty(dir);
 	/* OFFSET_CACHE */
 out_put:
-	nilfs_put_page(page);
-out:
+	folio_release_kmap(folio, de);
 	return err;
 out_unlock:
-	unlock_page(page);
+	folio_unlock(folio);
 	goto out_put;
 }
 
 /*
  * nilfs_delete_entry deletes a directory entry by merging it with the
- * previous entry. Page is up-to-date. Releases the page.
+ * previous entry. Folio is up-to-date.
  */
-int nilfs_delete_entry(struct nilfs_dir_entry *dir, struct page *page)
+int nilfs_delete_entry(struct nilfs_dir_entry *dir, struct folio *folio)
 {
-	struct address_space *mapping = page->mapping;
+	struct address_space *mapping = folio->mapping;
 	struct inode *inode = mapping->host;
-	char *kaddr = page_address(page);
-	unsigned int from, to;
+	char *kaddr = (char *)((unsigned long)dir & ~(folio_size(folio) - 1));
+	size_t from, to;
 	struct nilfs_dir_entry *de, *pde = NULL;
 	int err;
 
@@ -559,17 +539,16 @@ int nilfs_delete_entry(struct nilfs_dir_entry *dir, struct page *page)
 		de = nilfs_next_entry(de);
 	}
 	if (pde)
-		from = (char *)pde - (char *)page_address(page);
-	lock_page(page);
-	err = nilfs_prepare_chunk(page, from, to);
+		from = (char *)pde - kaddr;
+	folio_lock(folio);
+	err = nilfs_prepare_chunk(folio, from, to);
 	BUG_ON(err);
 	if (pde)
 		pde->rec_len = nilfs_rec_len_to_disk(to - from);
 	dir->inode = 0;
-	nilfs_commit_chunk(page, mapping, from, to);
+	nilfs_commit_chunk(folio, mapping, from, to);
 	inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
 out:
-	nilfs_put_page(page);
 	return err;
 }
 
@@ -579,21 +558,21 @@ out:
 int nilfs_make_empty(struct inode *inode, struct inode *parent)
 {
 	struct address_space *mapping = inode->i_mapping;
-	struct page *page = grab_cache_page(mapping, 0);
+	struct folio *folio = filemap_grab_folio(mapping, 0);
 	unsigned int chunk_size = nilfs_chunk_size(inode);
 	struct nilfs_dir_entry *de;
 	int err;
 	void *kaddr;
 
-	if (!page)
-		return -ENOMEM;
+	if (IS_ERR(folio))
+		return PTR_ERR(folio);
 
-	err = nilfs_prepare_chunk(page, 0, chunk_size);
+	err = nilfs_prepare_chunk(folio, 0, chunk_size);
 	if (unlikely(err)) {
-		unlock_page(page);
+		folio_unlock(folio);
 		goto fail;
 	}
-	kaddr = kmap_atomic(page);
+	kaddr = kmap_local_folio(folio, 0);
 	memset(kaddr, 0, chunk_size);
 	de = (struct nilfs_dir_entry *)kaddr;
 	de->name_len = 1;
@@ -608,10 +587,10 @@ int nilfs_make_empty(struct inode *inode, struct inode *parent)
 	de->inode = cpu_to_le64(parent->i_ino);
 	memcpy(de->name, "..\0", 4);
 	nilfs_set_de_type(de, inode);
-	kunmap_atomic(kaddr);
-	nilfs_commit_chunk(page, mapping, 0, chunk_size);
+	kunmap_local(kaddr);
+	nilfs_commit_chunk(folio, mapping, 0, chunk_size);
 fail:
-	put_page(page);
+	folio_put(folio);
 	return err;
 }
 
@@ -620,18 +599,17 @@ fail:
  */
 int nilfs_empty_dir(struct inode *inode)
 {
-	struct page *page = NULL;
+	struct folio *folio = NULL;
+	char *kaddr;
 	unsigned long i, npages = dir_pages(inode);
 
 	for (i = 0; i < npages; i++) {
-		char *kaddr;
 		struct nilfs_dir_entry *de;
 
-		page = nilfs_get_page(inode, i);
-		if (IS_ERR(page))
+		kaddr = nilfs_get_folio(inode, i, &folio);
+		if (IS_ERR(kaddr))
 			continue;
 
-		kaddr = page_address(page);
 		de = (struct nilfs_dir_entry *)kaddr;
 		kaddr += nilfs_last_byte(inode, i) - NILFS_DIR_REC_LEN(1);
 
@@ -657,12 +635,12 @@ int nilfs_empty_dir(struct inode *inode)
 			}
 			de = nilfs_next_entry(de);
 		}
-		nilfs_put_page(page);
+		folio_release_kmap(folio, kaddr);
 	}
 	return 1;
 
 not_empty:
-	nilfs_put_page(page);
+	folio_release_kmap(folio, kaddr);
 	return 0;
 }
 
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index 740ce26d1e76..bec33b89a075 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -45,34 +45,36 @@ int nilfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 static vm_fault_t nilfs_page_mkwrite(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
-	struct page *page = vmf->page;
+	struct folio *folio = page_folio(vmf->page);
 	struct inode *inode = file_inode(vma->vm_file);
 	struct nilfs_transaction_info ti;
+	struct buffer_head *bh, *head;
 	int ret = 0;
 
 	if (unlikely(nilfs_near_disk_full(inode->i_sb->s_fs_info)))
 		return VM_FAULT_SIGBUS; /* -ENOSPC */
 
 	sb_start_pagefault(inode->i_sb);
-	lock_page(page);
-	if (page->mapping != inode->i_mapping ||
-	    page_offset(page) >= i_size_read(inode) || !PageUptodate(page)) {
-		unlock_page(page);
+	folio_lock(folio);
+	if (folio->mapping != inode->i_mapping ||
+	    folio_pos(folio) >= i_size_read(inode) ||
+	    !folio_test_uptodate(folio)) {
+		folio_unlock(folio);
 		ret = -EFAULT;	/* make the VM retry the fault */
 		goto out;
 	}
 
 	/*
-	 * check to see if the page is mapped already (no holes)
+	 * check to see if the folio is mapped already (no holes)
 	 */
-	if (PageMappedToDisk(page))
+	if (folio_test_mappedtodisk(folio))
 		goto mapped;
 
-	if (page_has_buffers(page)) {
-		struct buffer_head *bh, *head;
+	head = folio_buffers(folio);
+	if (head) {
 		int fully_mapped = 1;
 
-		bh = head = page_buffers(page);
+		bh = head;
 		do {
 			if (!buffer_mapped(bh)) {
 				fully_mapped = 0;
@@ -81,11 +83,11 @@ static vm_fault_t nilfs_page_mkwrite(struct vm_fault *vmf)
 		} while (bh = bh->b_this_page, bh != head);
 
 		if (fully_mapped) {
-			SetPageMappedToDisk(page);
+			folio_set_mappedtodisk(folio);
 			goto mapped;
 		}
 	}
-	unlock_page(page);
+	folio_unlock(folio);
 
 	/*
 	 * fill hole blocks
@@ -105,7 +107,7 @@ static vm_fault_t nilfs_page_mkwrite(struct vm_fault *vmf)
 	nilfs_transaction_commit(inode->i_sb);
 
  mapped:
-	wait_for_stable_page(page);
+	folio_wait_stable(folio);
  out:
 	sb_end_pagefault(inode->i_sb);
 	return vmf_fs_error(ret);
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index 8beb2730929d..bf9a11d58817 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -98,8 +98,8 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff,
 	*out_bh = bh;
 
  failed:
-	unlock_page(bh->b_page);
-	put_page(bh->b_page);
+	folio_unlock(bh->b_folio);
+	folio_put(bh->b_folio);
 	if (unlikely(err))
 		brelse(bh);
 	return err;
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index f861f3a0bf5c..9c334c722fc1 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -175,7 +175,8 @@ static int nilfs_writepages(struct address_space *mapping,
 
 static int nilfs_writepage(struct page *page, struct writeback_control *wbc)
 {
-	struct inode *inode = page->mapping->host;
+	struct folio *folio = page_folio(page);
+	struct inode *inode = folio->mapping->host;
 	int err;
 
 	if (sb_rdonly(inode->i_sb)) {
@@ -185,13 +186,13 @@ static int nilfs_writepage(struct page *page, struct writeback_control *wbc)
 		 * have dirty pages that try to be flushed in background.
 		 * So, here we simply discard this dirty page.
 		 */
-		nilfs_clear_dirty_page(page, false);
-		unlock_page(page);
+		nilfs_clear_folio_dirty(folio, false);
+		folio_unlock(folio);
 		return -EROFS;
 	}
 
-	redirty_page_for_writepage(wbc, page);
-	unlock_page(page);
+	folio_redirty_for_writepage(wbc, folio);
+	folio_unlock(folio);
 
 	if (wbc->sync_mode == WB_SYNC_ALL) {
 		err = nilfs_construct_segment(inode->i_sb);
@@ -214,7 +215,7 @@ static bool nilfs_dirty_folio(struct address_space *mapping,
 	/*
 	 * The page may not be locked, eg if called from try_to_unmap_one()
 	 */
-	spin_lock(&mapping->private_lock);
+	spin_lock(&mapping->i_private_lock);
 	head = folio_buffers(folio);
 	if (head) {
 		struct buffer_head *bh = head;
@@ -230,7 +231,7 @@ static bool nilfs_dirty_folio(struct address_space *mapping,
 	} else if (ret) {
 		nr_dirty = 1 << (folio_shift(folio) - inode->i_blkbits);
 	}
-	spin_unlock(&mapping->private_lock);
+	spin_unlock(&mapping->i_private_lock);
 
 	if (nr_dirty)
 		nilfs_set_file_dirty(inode, nr_dirty);
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 40ffade49f38..cfb6aca5ec38 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -872,16 +872,14 @@ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp,
 	nsegs = argv[4].v_nmembs;
 	if (argv[4].v_size != argsz[4])
 		goto out;
-	if (nsegs > UINT_MAX / sizeof(__u64))
-		goto out;
 
 	/*
 	 * argv[4] points to segment numbers this ioctl cleans.  We
-	 * use kmalloc() for its buffer because memory used for the
-	 * segment numbers is enough small.
+	 * use kmalloc() for its buffer because the memory used for the
+	 * segment numbers is small enough.
 	 */
-	kbufs[4] = memdup_user((void __user *)(unsigned long)argv[4].v_base,
-			       nsegs * sizeof(__u64));
+	kbufs[4] = memdup_array_user((void __user *)(unsigned long)argv[4].v_base,
+				     nsegs, sizeof(__u64));
 	if (IS_ERR(kbufs[4])) {
 		ret = PTR_ERR(kbufs[4]);
 		goto out;
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index c97c77a39668..e45c01a559c0 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -97,8 +97,8 @@ static int nilfs_mdt_create_block(struct inode *inode, unsigned long block,
 	}
 
  failed_bh:
-	unlock_page(bh->b_page);
-	put_page(bh->b_page);
+	folio_unlock(bh->b_folio);
+	folio_put(bh->b_folio);
 	brelse(bh);
 
  failed_unlock:
@@ -158,8 +158,8 @@ nilfs_mdt_submit_block(struct inode *inode, unsigned long blkoff, blk_opf_t opf,
 	*out_bh = bh;
 
  failed_bh:
-	unlock_page(bh->b_page);
-	put_page(bh->b_page);
+	folio_unlock(bh->b_folio);
+	folio_put(bh->b_folio);
 	brelse(bh);
  failed:
 	return ret;
@@ -399,7 +399,8 @@ int nilfs_mdt_fetch_dirty(struct inode *inode)
 static int
 nilfs_mdt_write_page(struct page *page, struct writeback_control *wbc)
 {
-	struct inode *inode = page->mapping->host;
+	struct folio *folio = page_folio(page);
+	struct inode *inode = folio->mapping->host;
 	struct super_block *sb;
 	int err = 0;
 
@@ -407,16 +408,16 @@ nilfs_mdt_write_page(struct page *page, struct writeback_control *wbc)
 		/*
 		 * It means that filesystem was remounted in read-only
 		 * mode because of error or metadata corruption. But we
-		 * have dirty pages that try to be flushed in background.
-		 * So, here we simply discard this dirty page.
+		 * have dirty folios that try to be flushed in background.
+		 * So, here we simply discard this dirty folio.
 		 */
-		nilfs_clear_dirty_page(page, false);
-		unlock_page(page);
+		nilfs_clear_folio_dirty(folio, false);
+		folio_unlock(folio);
 		return -EROFS;
 	}
 
-	redirty_page_for_writepage(wbc, page);
-	unlock_page(page);
+	folio_redirty_for_writepage(wbc, folio);
+	folio_unlock(folio);
 
 	if (!inode)
 		return 0;
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 2a4e7f4a8102..959bd9fb3d81 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -260,11 +260,11 @@ static int nilfs_do_unlink(struct inode *dir, struct dentry *dentry)
 {
 	struct inode *inode;
 	struct nilfs_dir_entry *de;
-	struct page *page;
+	struct folio *folio;
 	int err;
 
 	err = -ENOENT;
-	de = nilfs_find_entry(dir, &dentry->d_name, &page);
+	de = nilfs_find_entry(dir, &dentry->d_name, &folio);
 	if (!de)
 		goto out;
 
@@ -279,7 +279,8 @@ static int nilfs_do_unlink(struct inode *dir, struct dentry *dentry)
 			   inode->i_ino, inode->i_nlink);
 		set_nlink(inode, 1);
 	}
-	err = nilfs_delete_entry(de, page);
+	err = nilfs_delete_entry(de, folio);
+	folio_release_kmap(folio, de);
 	if (err)
 		goto out;
 
@@ -347,9 +348,9 @@ static int nilfs_rename(struct mnt_idmap *idmap,
 {
 	struct inode *old_inode = d_inode(old_dentry);
 	struct inode *new_inode = d_inode(new_dentry);
-	struct page *dir_page = NULL;
+	struct folio *dir_folio = NULL;
 	struct nilfs_dir_entry *dir_de = NULL;
-	struct page *old_page;
+	struct folio *old_folio;
 	struct nilfs_dir_entry *old_de;
 	struct nilfs_transaction_info ti;
 	int err;
@@ -362,19 +363,19 @@ static int nilfs_rename(struct mnt_idmap *idmap,
 		return err;
 
 	err = -ENOENT;
-	old_de = nilfs_find_entry(old_dir, &old_dentry->d_name, &old_page);
+	old_de = nilfs_find_entry(old_dir, &old_dentry->d_name, &old_folio);
 	if (!old_de)
 		goto out;
 
 	if (S_ISDIR(old_inode->i_mode)) {
 		err = -EIO;
-		dir_de = nilfs_dotdot(old_inode, &dir_page);
+		dir_de = nilfs_dotdot(old_inode, &dir_folio);
 		if (!dir_de)
 			goto out_old;
 	}
 
 	if (new_inode) {
-		struct page *new_page;
+		struct folio *new_folio;
 		struct nilfs_dir_entry *new_de;
 
 		err = -ENOTEMPTY;
@@ -382,10 +383,11 @@ static int nilfs_rename(struct mnt_idmap *idmap,
 			goto out_dir;
 
 		err = -ENOENT;
-		new_de = nilfs_find_entry(new_dir, &new_dentry->d_name, &new_page);
+		new_de = nilfs_find_entry(new_dir, &new_dentry->d_name, &new_folio);
 		if (!new_de)
 			goto out_dir;
-		nilfs_set_link(new_dir, new_de, new_page, old_inode);
+		nilfs_set_link(new_dir, new_de, new_folio, old_inode);
+		folio_release_kmap(new_folio, new_de);
 		nilfs_mark_inode_dirty(new_dir);
 		inode_set_ctime_current(new_inode);
 		if (dir_de)
@@ -408,12 +410,15 @@ static int nilfs_rename(struct mnt_idmap *idmap,
 	 */
 	inode_set_ctime_current(old_inode);
 
-	nilfs_delete_entry(old_de, old_page);
+	nilfs_delete_entry(old_de, old_folio);
 
 	if (dir_de) {
-		nilfs_set_link(old_inode, dir_de, dir_page, new_dir);
+		nilfs_set_link(old_inode, dir_de, dir_folio, new_dir);
+		folio_release_kmap(dir_folio, dir_de);
 		drop_nlink(old_dir);
 	}
+	folio_release_kmap(old_folio, old_de);
+
 	nilfs_mark_inode_dirty(old_dir);
 	nilfs_mark_inode_dirty(old_inode);
 
@@ -421,13 +426,10 @@ static int nilfs_rename(struct mnt_idmap *idmap,
 	return err;
 
 out_dir:
-	if (dir_de) {
-		kunmap(dir_page);
-		put_page(dir_page);
-	}
+	if (dir_de)
+		folio_release_kmap(dir_folio, dir_de);
 out_old:
-	kunmap(old_page);
-	put_page(old_page);
+	folio_release_kmap(old_folio, old_de);
 out:
 	nilfs_transaction_abort(old_dir->i_sb);
 	return err;
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index 8046490cd7fe..98cffaf0ac12 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -226,16 +226,16 @@ static inline __u32 nilfs_mask_flags(umode_t mode, __u32 flags)
 }
 
 /* dir.c */
-extern int nilfs_add_link(struct dentry *, struct inode *);
-extern ino_t nilfs_inode_by_name(struct inode *, const struct qstr *);
-extern int nilfs_make_empty(struct inode *, struct inode *);
-extern struct nilfs_dir_entry *
-nilfs_find_entry(struct inode *, const struct qstr *, struct page **);
-extern int nilfs_delete_entry(struct nilfs_dir_entry *, struct page *);
-extern int nilfs_empty_dir(struct inode *);
-extern struct nilfs_dir_entry *nilfs_dotdot(struct inode *, struct page **);
-extern void nilfs_set_link(struct inode *, struct nilfs_dir_entry *,
-			   struct page *, struct inode *);
+int nilfs_add_link(struct dentry *, struct inode *);
+ino_t nilfs_inode_by_name(struct inode *, const struct qstr *);
+int nilfs_make_empty(struct inode *, struct inode *);
+struct nilfs_dir_entry *nilfs_find_entry(struct inode *, const struct qstr *,
+		struct folio **);
+int nilfs_delete_entry(struct nilfs_dir_entry *, struct folio *);
+int nilfs_empty_dir(struct inode *);
+struct nilfs_dir_entry *nilfs_dotdot(struct inode *, struct folio **);
+void nilfs_set_link(struct inode *, struct nilfs_dir_entry *,
+			   struct folio *, struct inode *);
 
 /* file.c */
 extern int nilfs_sync_file(struct file *, loff_t, loff_t, int);
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 06b04758f289..5c2eba1987bd 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -73,7 +73,7 @@ struct buffer_head *nilfs_grab_buffer(struct inode *inode,
  */
 void nilfs_forget_buffer(struct buffer_head *bh)
 {
-	struct page *page = bh->b_page;
+	struct folio *folio = bh->b_folio;
 	const unsigned long clear_bits =
 		(BIT(BH_Uptodate) | BIT(BH_Dirty) | BIT(BH_Mapped) |
 		 BIT(BH_Async_Write) | BIT(BH_NILFS_Volatile) |
@@ -81,12 +81,12 @@ void nilfs_forget_buffer(struct buffer_head *bh)
 
 	lock_buffer(bh);
 	set_mask_bits(&bh->b_state, clear_bits, 0);
-	if (nilfs_page_buffers_clean(page))
-		__nilfs_clear_page_dirty(page);
+	if (nilfs_folio_buffers_clean(folio))
+		__nilfs_clear_folio_dirty(folio);
 
 	bh->b_blocknr = -1;
-	ClearPageUptodate(page);
-	ClearPageMappedToDisk(page);
+	folio_clear_uptodate(folio);
+	folio_clear_mappedtodisk(folio);
 	unlock_buffer(bh);
 	brelse(bh);
 }
@@ -131,48 +131,49 @@ void nilfs_copy_buffer(struct buffer_head *dbh, struct buffer_head *sbh)
 }
 
 /**
- * nilfs_page_buffers_clean - check if a page has dirty buffers or not.
- * @page: page to be checked
+ * nilfs_folio_buffers_clean - Check if a folio has dirty buffers or not.
+ * @folio: Folio to be checked.
  *
- * nilfs_page_buffers_clean() returns zero if the page has dirty buffers.
- * Otherwise, it returns non-zero value.
+ * nilfs_folio_buffers_clean() returns false if the folio has dirty buffers.
+ * Otherwise, it returns true.
  */
-int nilfs_page_buffers_clean(struct page *page)
+bool nilfs_folio_buffers_clean(struct folio *folio)
 {
 	struct buffer_head *bh, *head;
 
-	bh = head = page_buffers(page);
+	bh = head = folio_buffers(folio);
 	do {
 		if (buffer_dirty(bh))
-			return 0;
+			return false;
 		bh = bh->b_this_page;
 	} while (bh != head);
-	return 1;
+	return true;
 }
 
-void nilfs_page_bug(struct page *page)
+void nilfs_folio_bug(struct folio *folio)
 {
+	struct buffer_head *bh, *head;
 	struct address_space *m;
 	unsigned long ino;
 
-	if (unlikely(!page)) {
-		printk(KERN_CRIT "NILFS_PAGE_BUG(NULL)\n");
+	if (unlikely(!folio)) {
+		printk(KERN_CRIT "NILFS_FOLIO_BUG(NULL)\n");
 		return;
 	}
 
-	m = page->mapping;
+	m = folio->mapping;
 	ino = m ? m->host->i_ino : 0;
 
-	printk(KERN_CRIT "NILFS_PAGE_BUG(%p): cnt=%d index#=%llu flags=0x%lx "
+	printk(KERN_CRIT "NILFS_FOLIO_BUG(%p): cnt=%d index#=%llu flags=0x%lx "
 	       "mapping=%p ino=%lu\n",
-	       page, page_ref_count(page),
-	       (unsigned long long)page->index, page->flags, m, ino);
+	       folio, folio_ref_count(folio),
+	       (unsigned long long)folio->index, folio->flags, m, ino);
 
-	if (page_has_buffers(page)) {
-		struct buffer_head *bh, *head;
+	head = folio_buffers(folio);
+	if (head) {
 		int i = 0;
 
-		bh = head = page_buffers(page);
+		bh = head;
 		do {
 			printk(KERN_CRIT
 			       " BH[%d] %p: cnt=%d block#=%llu state=0x%lx\n",
@@ -258,7 +259,7 @@ repeat:
 
 		folio_lock(folio);
 		if (unlikely(!folio_test_dirty(folio)))
-			NILFS_PAGE_BUG(&folio->page, "inconsistent dirty state");
+			NILFS_FOLIO_BUG(folio, "inconsistent dirty state");
 
 		dfolio = filemap_grab_folio(dmap, folio->index);
 		if (unlikely(IS_ERR(dfolio))) {
@@ -268,7 +269,7 @@ repeat:
 			break;
 		}
 		if (unlikely(!folio_buffers(folio)))
-			NILFS_PAGE_BUG(&folio->page,
+			NILFS_FOLIO_BUG(folio,
 				       "found empty page in dat page cache");
 
 		nilfs_copy_folio(dfolio, folio, true);
@@ -379,7 +380,7 @@ void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent)
 			 * was acquired.  Skip processing in that case.
 			 */
 			if (likely(folio->mapping == mapping))
-				nilfs_clear_dirty_page(&folio->page, silent);
+				nilfs_clear_folio_dirty(folio, silent);
 
 			folio_unlock(folio);
 		}
@@ -389,32 +390,33 @@ void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent)
 }
 
 /**
- * nilfs_clear_dirty_page - discard dirty page
- * @page: dirty page that will be discarded
+ * nilfs_clear_folio_dirty - discard dirty folio
+ * @folio: dirty folio that will be discarded
  * @silent: suppress [true] or print [false] warning messages
  */
-void nilfs_clear_dirty_page(struct page *page, bool silent)
+void nilfs_clear_folio_dirty(struct folio *folio, bool silent)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = folio->mapping->host;
 	struct super_block *sb = inode->i_sb;
+	struct buffer_head *bh, *head;
 
-	BUG_ON(!PageLocked(page));
+	BUG_ON(!folio_test_locked(folio));
 
 	if (!silent)
 		nilfs_warn(sb, "discard dirty page: offset=%lld, ino=%lu",
-			   page_offset(page), inode->i_ino);
+			   folio_pos(folio), inode->i_ino);
 
-	ClearPageUptodate(page);
-	ClearPageMappedToDisk(page);
+	folio_clear_uptodate(folio);
+	folio_clear_mappedtodisk(folio);
 
-	if (page_has_buffers(page)) {
-		struct buffer_head *bh, *head;
+	head = folio_buffers(folio);
+	if (head) {
 		const unsigned long clear_bits =
 			(BIT(BH_Uptodate) | BIT(BH_Dirty) | BIT(BH_Mapped) |
 			 BIT(BH_Async_Write) | BIT(BH_NILFS_Volatile) |
 			 BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected));
 
-		bh = head = page_buffers(page);
+		bh = head;
 		do {
 			lock_buffer(bh);
 			if (!silent)
@@ -427,7 +429,7 @@ void nilfs_clear_dirty_page(struct page *page, bool silent)
 		} while (bh = bh->b_this_page, bh != head);
 	}
 
-	__nilfs_clear_page_dirty(page);
+	__nilfs_clear_folio_dirty(folio);
 }
 
 unsigned int nilfs_page_count_clean_buffers(struct page *page,
@@ -457,22 +459,23 @@ unsigned int nilfs_page_count_clean_buffers(struct page *page,
  * 2) Some B-tree operations like insertion or deletion may dispose buffers
  *    in dirty state, and this needs to cancel the dirty state of their pages.
  */
-int __nilfs_clear_page_dirty(struct page *page)
+void __nilfs_clear_folio_dirty(struct folio *folio)
 {
-	struct address_space *mapping = page->mapping;
+	struct address_space *mapping = folio->mapping;
 
 	if (mapping) {
 		xa_lock_irq(&mapping->i_pages);
-		if (test_bit(PG_dirty, &page->flags)) {
-			__xa_clear_mark(&mapping->i_pages, page_index(page),
+		if (folio_test_dirty(folio)) {
+			__xa_clear_mark(&mapping->i_pages, folio->index,
 					     PAGECACHE_TAG_DIRTY);
 			xa_unlock_irq(&mapping->i_pages);
-			return clear_page_dirty_for_io(page);
+			folio_clear_dirty_for_io(folio);
+			return;
 		}
 		xa_unlock_irq(&mapping->i_pages);
-		return 0;
+		return;
 	}
-	return TestClearPageDirty(page);
+	folio_clear_dirty(folio);
 }
 
 /**
diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h
index d249ea1cefff..7e1a2c455a10 100644
--- a/fs/nilfs2/page.h
+++ b/fs/nilfs2/page.h
@@ -30,18 +30,18 @@ BUFFER_FNS(NILFS_Checked, nilfs_checked)	/* buffer is verified */
 BUFFER_FNS(NILFS_Redirected, nilfs_redirected)	/* redirected to a copy */
 
 
-int __nilfs_clear_page_dirty(struct page *);
+void __nilfs_clear_folio_dirty(struct folio *);
 
 struct buffer_head *nilfs_grab_buffer(struct inode *, struct address_space *,
 				      unsigned long, unsigned long);
 void nilfs_forget_buffer(struct buffer_head *);
 void nilfs_copy_buffer(struct buffer_head *, struct buffer_head *);
-int nilfs_page_buffers_clean(struct page *);
-void nilfs_page_bug(struct page *);
+bool nilfs_folio_buffers_clean(struct folio *);
+void nilfs_folio_bug(struct folio *);
 
 int nilfs_copy_dirty_pages(struct address_space *, struct address_space *);
 void nilfs_copy_back_pages(struct address_space *, struct address_space *);
-void nilfs_clear_dirty_page(struct page *, bool);
+void nilfs_clear_folio_dirty(struct folio *, bool);
 void nilfs_clear_dirty_pages(struct address_space *, bool);
 unsigned int nilfs_page_count_clean_buffers(struct page *, unsigned int,
 					    unsigned int);
@@ -49,7 +49,7 @@ unsigned long nilfs_find_uncommitted_extent(struct inode *inode,
 					    sector_t start_blk,
 					    sector_t *blkoff);
 
-#define NILFS_PAGE_BUG(page, m, a...) \
-	do { nilfs_page_bug(page); BUG(); } while (0)
+#define NILFS_FOLIO_BUG(folio, m, a...) \
+	do { nilfs_folio_bug(folio); BUG(); } while (0)
 
 #endif /* _NILFS_PAGE_H */
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 55e31cc903d1..2590a0860eab 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -1665,39 +1665,39 @@ static int nilfs_segctor_assign(struct nilfs_sc_info *sci, int mode)
 	return 0;
 }
 
-static void nilfs_begin_page_io(struct page *page)
+static void nilfs_begin_folio_io(struct folio *folio)
 {
-	if (!page || PageWriteback(page))
+	if (!folio || folio_test_writeback(folio))
 		/*
 		 * For split b-tree node pages, this function may be called
 		 * twice.  We ignore the 2nd or later calls by this check.
 		 */
 		return;
 
-	lock_page(page);
-	clear_page_dirty_for_io(page);
-	set_page_writeback(page);
-	unlock_page(page);
+	folio_lock(folio);
+	folio_clear_dirty_for_io(folio);
+	folio_start_writeback(folio);
+	folio_unlock(folio);
 }
 
 static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
 {
 	struct nilfs_segment_buffer *segbuf;
-	struct page *bd_page = NULL, *fs_page = NULL;
+	struct folio *bd_folio = NULL, *fs_folio = NULL;
 
 	list_for_each_entry(segbuf, &sci->sc_segbufs, sb_list) {
 		struct buffer_head *bh;
 
 		list_for_each_entry(bh, &segbuf->sb_segsum_buffers,
 				    b_assoc_buffers) {
-			if (bh->b_page != bd_page) {
-				if (bd_page) {
-					lock_page(bd_page);
-					clear_page_dirty_for_io(bd_page);
-					set_page_writeback(bd_page);
-					unlock_page(bd_page);
+			if (bh->b_folio != bd_folio) {
+				if (bd_folio) {
+					folio_lock(bd_folio);
+					folio_clear_dirty_for_io(bd_folio);
+					folio_start_writeback(bd_folio);
+					folio_unlock(bd_folio);
 				}
-				bd_page = bh->b_page;
+				bd_folio = bh->b_folio;
 			}
 		}
 
@@ -1705,28 +1705,28 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
 				    b_assoc_buffers) {
 			set_buffer_async_write(bh);
 			if (bh == segbuf->sb_super_root) {
-				if (bh->b_page != bd_page) {
-					lock_page(bd_page);
-					clear_page_dirty_for_io(bd_page);
-					set_page_writeback(bd_page);
-					unlock_page(bd_page);
-					bd_page = bh->b_page;
+				if (bh->b_folio != bd_folio) {
+					folio_lock(bd_folio);
+					folio_clear_dirty_for_io(bd_folio);
+					folio_start_writeback(bd_folio);
+					folio_unlock(bd_folio);
+					bd_folio = bh->b_folio;
 				}
 				break;
 			}
-			if (bh->b_page != fs_page) {
-				nilfs_begin_page_io(fs_page);
-				fs_page = bh->b_page;
+			if (bh->b_folio != fs_folio) {
+				nilfs_begin_folio_io(fs_folio);
+				fs_folio = bh->b_folio;
 			}
 		}
 	}
-	if (bd_page) {
-		lock_page(bd_page);
-		clear_page_dirty_for_io(bd_page);
-		set_page_writeback(bd_page);
-		unlock_page(bd_page);
+	if (bd_folio) {
+		folio_lock(bd_folio);
+		folio_clear_dirty_for_io(bd_folio);
+		folio_start_writeback(bd_folio);
+		folio_unlock(bd_folio);
 	}
-	nilfs_begin_page_io(fs_page);
+	nilfs_begin_folio_io(fs_folio);
 }
 
 static int nilfs_segctor_write(struct nilfs_sc_info *sci,
@@ -1739,17 +1739,18 @@ static int nilfs_segctor_write(struct nilfs_sc_info *sci,
 	return ret;
 }
 
-static void nilfs_end_page_io(struct page *page, int err)
+static void nilfs_end_folio_io(struct folio *folio, int err)
 {
-	if (!page)
+	if (!folio)
 		return;
 
-	if (buffer_nilfs_node(page_buffers(page)) && !PageWriteback(page)) {
+	if (buffer_nilfs_node(folio_buffers(folio)) &&
+			!folio_test_writeback(folio)) {
 		/*
 		 * For b-tree node pages, this function may be called twice
 		 * or more because they might be split in a segment.
 		 */
-		if (PageDirty(page)) {
+		if (folio_test_dirty(folio)) {
 			/*
 			 * For pages holding split b-tree node buffers, dirty
 			 * flag on the buffers may be cleared discretely.
@@ -1757,30 +1758,30 @@ static void nilfs_end_page_io(struct page *page, int err)
 			 * remaining buffers, and it must be cancelled if
 			 * all the buffers get cleaned later.
 			 */
-			lock_page(page);
-			if (nilfs_page_buffers_clean(page))
-				__nilfs_clear_page_dirty(page);
-			unlock_page(page);
+			folio_lock(folio);
+			if (nilfs_folio_buffers_clean(folio))
+				__nilfs_clear_folio_dirty(folio);
+			folio_unlock(folio);
 		}
 		return;
 	}
 
 	if (!err) {
-		if (!nilfs_page_buffers_clean(page))
-			__set_page_dirty_nobuffers(page);
-		ClearPageError(page);
+		if (!nilfs_folio_buffers_clean(folio))
+			filemap_dirty_folio(folio->mapping, folio);
+		folio_clear_error(folio);
 	} else {
-		__set_page_dirty_nobuffers(page);
-		SetPageError(page);
+		filemap_dirty_folio(folio->mapping, folio);
+		folio_set_error(folio);
 	}
 
-	end_page_writeback(page);
+	folio_end_writeback(folio);
 }
 
 static void nilfs_abort_logs(struct list_head *logs, int err)
 {
 	struct nilfs_segment_buffer *segbuf;
-	struct page *bd_page = NULL, *fs_page = NULL;
+	struct folio *bd_folio = NULL, *fs_folio = NULL;
 	struct buffer_head *bh;
 
 	if (list_empty(logs))
@@ -1790,10 +1791,10 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
 		list_for_each_entry(bh, &segbuf->sb_segsum_buffers,
 				    b_assoc_buffers) {
 			clear_buffer_uptodate(bh);
-			if (bh->b_page != bd_page) {
-				if (bd_page)
-					end_page_writeback(bd_page);
-				bd_page = bh->b_page;
+			if (bh->b_folio != bd_folio) {
+				if (bd_folio)
+					folio_end_writeback(bd_folio);
+				bd_folio = bh->b_folio;
 			}
 		}
 
@@ -1802,22 +1803,22 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
 			clear_buffer_async_write(bh);
 			if (bh == segbuf->sb_super_root) {
 				clear_buffer_uptodate(bh);
-				if (bh->b_page != bd_page) {
-					end_page_writeback(bd_page);
-					bd_page = bh->b_page;
+				if (bh->b_folio != bd_folio) {
+					folio_end_writeback(bd_folio);
+					bd_folio = bh->b_folio;
 				}
 				break;
 			}
-			if (bh->b_page != fs_page) {
-				nilfs_end_page_io(fs_page, err);
-				fs_page = bh->b_page;
+			if (bh->b_folio != fs_folio) {
+				nilfs_end_folio_io(fs_folio, err);
+				fs_folio = bh->b_folio;
 			}
 		}
 	}
-	if (bd_page)
-		end_page_writeback(bd_page);
+	if (bd_folio)
+		folio_end_writeback(bd_folio);
 
-	nilfs_end_page_io(fs_page, err);
+	nilfs_end_folio_io(fs_folio, err);
 }
 
 static void nilfs_segctor_abort_construction(struct nilfs_sc_info *sci,
@@ -1859,7 +1860,7 @@ static void nilfs_set_next_segment(struct the_nilfs *nilfs,
 static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
 {
 	struct nilfs_segment_buffer *segbuf;
-	struct page *bd_page = NULL, *fs_page = NULL;
+	struct folio *bd_folio = NULL, *fs_folio = NULL;
 	struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
 	int update_sr = false;
 
@@ -1870,21 +1871,21 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
 				    b_assoc_buffers) {
 			set_buffer_uptodate(bh);
 			clear_buffer_dirty(bh);
-			if (bh->b_page != bd_page) {
-				if (bd_page)
-					end_page_writeback(bd_page);
-				bd_page = bh->b_page;
+			if (bh->b_folio != bd_folio) {
+				if (bd_folio)
+					folio_end_writeback(bd_folio);
+				bd_folio = bh->b_folio;
 			}
 		}
 		/*
-		 * We assume that the buffers which belong to the same page
+		 * We assume that the buffers which belong to the same folio
 		 * continue over the buffer list.
-		 * Under this assumption, the last BHs of pages is
-		 * identifiable by the discontinuity of bh->b_page
-		 * (page != fs_page).
+		 * Under this assumption, the last BHs of folios is
+		 * identifiable by the discontinuity of bh->b_folio
+		 * (folio != fs_folio).
 		 *
 		 * For B-tree node blocks, however, this assumption is not
-		 * guaranteed.  The cleanup code of B-tree node pages needs
+		 * guaranteed.  The cleanup code of B-tree node folios needs
 		 * special care.
 		 */
 		list_for_each_entry(bh, &segbuf->sb_payload_buffers,
@@ -1897,16 +1898,16 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
 
 			set_mask_bits(&bh->b_state, clear_bits, set_bits);
 			if (bh == segbuf->sb_super_root) {
-				if (bh->b_page != bd_page) {
-					end_page_writeback(bd_page);
-					bd_page = bh->b_page;
+				if (bh->b_folio != bd_folio) {
+					folio_end_writeback(bd_folio);
+					bd_folio = bh->b_folio;
 				}
 				update_sr = true;
 				break;
 			}
-			if (bh->b_page != fs_page) {
-				nilfs_end_page_io(fs_page, 0);
-				fs_page = bh->b_page;
+			if (bh->b_folio != fs_folio) {
+				nilfs_end_folio_io(fs_folio, 0);
+				fs_folio = bh->b_folio;
 			}
 		}
 
@@ -1920,13 +1921,13 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
 		}
 	}
 	/*
-	 * Since pages may continue over multiple segment buffers,
-	 * end of the last page must be checked outside of the loop.
+	 * Since folios may continue over multiple segment buffers,
+	 * end of the last folio must be checked outside of the loop.
 	 */
-	if (bd_page)
-		end_page_writeback(bd_page);
+	if (bd_folio)
+		folio_end_writeback(bd_folio);
 
-	nilfs_end_page_io(fs_page, 0);
+	nilfs_end_folio_io(fs_folio, 0);
 
 	nilfs_drop_collected_inodes(&sci->sc_dirty_files);
 
@@ -2587,6 +2588,7 @@ static int nilfs_segctor_thread(void *arg)
 		   "segctord starting. Construction interval = %lu seconds, CP frequency < %lu seconds",
 		   sci->sc_interval / HZ, sci->sc_mjcp_freq / HZ);
 
+	set_freezable();
 	spin_lock(&sci->sc_state_lock);
  loop:
 	for (;;) {
diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index 2c6078a6b8ec..0a8119456c21 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -471,10 +471,15 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum,
 		kunmap_atomic(kaddr);
 		return;
 	}
-	WARN_ON(nilfs_segment_usage_error(su));
-	WARN_ON(!nilfs_segment_usage_dirty(su));
+	if (unlikely(nilfs_segment_usage_error(su)))
+		nilfs_warn(sufile->i_sb, "free segment %llu marked in error",
+			   (unsigned long long)segnum);
 
 	sudirty = nilfs_segment_usage_dirty(su);
+	if (unlikely(!sudirty))
+		nilfs_warn(sufile->i_sb, "free unallocated segment %llu",
+			   (unsigned long long)segnum);
+
 	nilfs_segment_usage_set_clean(su);
 	kunmap_atomic(kaddr);
 	mark_buffer_dirty(su_bh);
@@ -501,15 +506,38 @@ int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum)
 
 	down_write(&NILFS_MDT(sufile)->mi_sem);
 	ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0, &bh);
-	if (!ret) {
-		mark_buffer_dirty(bh);
-		nilfs_mdt_mark_dirty(sufile);
-		kaddr = kmap_atomic(bh->b_page);
-		su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr);
+	if (ret)
+		goto out_sem;
+
+	kaddr = kmap_atomic(bh->b_page);
+	su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr);
+	if (unlikely(nilfs_segment_usage_error(su))) {
+		struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
+
+		kunmap_atomic(kaddr);
+		brelse(bh);
+		if (nilfs_segment_is_active(nilfs, segnum)) {
+			nilfs_error(sufile->i_sb,
+				    "active segment %llu is erroneous",
+				    (unsigned long long)segnum);
+		} else {
+			/*
+			 * Segments marked erroneous are never allocated by
+			 * nilfs_sufile_alloc(); only active segments, ie,
+			 * the segments indexed by ns_segnum or ns_nextnum,
+			 * can be erroneous here.
+			 */
+			WARN_ON_ONCE(1);
+		}
+		ret = -EIO;
+	} else {
 		nilfs_segment_usage_set_dirty(su);
 		kunmap_atomic(kaddr);
+		mark_buffer_dirty(bh);
+		nilfs_mdt_mark_dirty(sufile);
 		brelse(bh);
 	}
+out_sem:
 	up_write(&NILFS_MDT(sufile)->mi_sem);
 	return ret;
 }
@@ -536,9 +564,14 @@ int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum,
 
 	kaddr = kmap_atomic(bh->b_page);
 	su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr);
-	WARN_ON(nilfs_segment_usage_error(su));
-	if (modtime)
+	if (modtime) {
+		/*
+		 * Check segusage error and set su_lastmod only when updating
+		 * this entry with a valid timestamp, not for cancellation.
+		 */
+		WARN_ON_ONCE(nilfs_segment_usage_error(su));
 		su->su_lastmod = cpu_to_le64(modtime);
+	}
 	su->su_nblocks = cpu_to_le32(nblocks);
 	kunmap_atomic(kaddr);
 
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index a5d1fa4e7552..df8674173b22 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1314,15 +1314,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
 		return ERR_CAST(s);
 
 	if (!s->s_root) {
-		/*
-		 * We drop s_umount here because we need to open the bdev and
-		 * bdev->open_mutex ranks above s_umount (blkdev_put() ->
-		 * __invalidate_device()). It is safe because we have active sb
-		 * reference and SB_BORN is not set yet.
-		 */
-		up_write(&s->s_umount);
 		err = setup_bdev_super(s, flags, NULL);
-		down_write(&s->s_umount);
 		if (!err)
 			err = nilfs_fill_super(s, data,
 					       flags & SB_SILENT ? 1 : 0);
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 0f0667957c81..71400496ed36 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -716,7 +716,11 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data)
 			goto failed_sbh;
 		}
 		nilfs_release_super_block(nilfs);
-		sb_set_blocksize(sb, blocksize);
+		if (!sb_set_blocksize(sb, blocksize)) {
+			nilfs_err(sb, "bad blocksize %d", blocksize);
+			err = -EINVAL;
+			goto out;
+		}
 
 		err = nilfs_load_super_block(nilfs, sb, blocksize, &sbp);
 		if (err)
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 1cb9ad7e884e..3464fa7e8538 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -29,7 +29,6 @@ static struct ctl_table dnotify_sysctls[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-	{}
 };
 static void __init dnotify_sysctl_init(void)
 {
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 9dac7f6e72d2..1e4def21811e 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -29,12 +29,6 @@ static unsigned int fanotify_hash_path(const struct path *path)
 		hash_ptr(path->mnt, FANOTIFY_EVENT_HASH_BITS);
 }
 
-static inline bool fanotify_fsid_equal(__kernel_fsid_t *fsid1,
-				       __kernel_fsid_t *fsid2)
-{
-	return fsid1->val[0] == fsid2->val[0] && fsid1->val[1] == fsid2->val[1];
-}
-
 static unsigned int fanotify_hash_fsid(__kernel_fsid_t *fsid)
 {
 	return hash_32(fsid->val[0], FANOTIFY_EVENT_HASH_BITS) ^
@@ -838,9 +832,8 @@ out:
 }
 
 /*
- * Get cached fsid of the filesystem containing the object from any connector.
- * All connectors are supposed to have the same fsid, but we do not verify that
- * here.
+ * Get cached fsid of the filesystem containing the object from any mark.
+ * All marks are supposed to have the same fsid, but we do not verify that here.
  */
 static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info)
 {
@@ -849,18 +842,11 @@ static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info)
 	__kernel_fsid_t fsid = {};
 
 	fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
-		struct fsnotify_mark_connector *conn;
-
-		conn = READ_ONCE(mark->connector);
-		/* Mark is just getting destroyed or created? */
-		if (!conn)
+		if (!(mark->flags & FSNOTIFY_MARK_FLAG_HAS_FSID))
 			continue;
-		if (!(conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID))
-			continue;
-		/* Pairs with smp_wmb() in fsnotify_add_mark_list() */
-		smp_rmb();
-		fsid = conn->fsid;
-		if (WARN_ON_ONCE(!fsid.val[0] && !fsid.val[1]))
+		fsid = FANOTIFY_MARK(mark)->fsid;
+		if (!(mark->flags & FSNOTIFY_MARK_FLAG_WEAK_FSID) &&
+		    WARN_ON_ONCE(!fsid.val[0] && !fsid.val[1]))
 			continue;
 		return fsid;
 	}
@@ -942,12 +928,8 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
 			return 0;
 	}
 
-	if (FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS)) {
+	if (FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS))
 		fsid = fanotify_get_fsid(iter_info);
-		/* Racing with mark destruction or creation? */
-		if (!fsid.val[0] && !fsid.val[1])
-			return 0;
-	}
 
 	event = fanotify_alloc_event(group, mask, data, data_type, dir,
 				     file_name, &fsid, match_mask);
@@ -1068,7 +1050,7 @@ static void fanotify_freeing_mark(struct fsnotify_mark *mark,
 
 static void fanotify_free_mark(struct fsnotify_mark *fsn_mark)
 {
-	kmem_cache_free(fanotify_mark_cache, fsn_mark);
+	kmem_cache_free(fanotify_mark_cache, FANOTIFY_MARK(fsn_mark));
 }
 
 const struct fsnotify_ops fanotify_fsnotify_ops = {
diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h
index 6936671e148d..e5ab33cae6a7 100644
--- a/fs/notify/fanotify/fanotify.h
+++ b/fs/notify/fanotify/fanotify.h
@@ -489,6 +489,22 @@ static inline unsigned int fanotify_event_hash_bucket(
 	return event->hash & FANOTIFY_HTABLE_MASK;
 }
 
+struct fanotify_mark {
+	struct fsnotify_mark fsn_mark;
+	__kernel_fsid_t fsid;
+};
+
+static inline struct fanotify_mark *FANOTIFY_MARK(struct fsnotify_mark *mark)
+{
+	return container_of(mark, struct fanotify_mark, fsn_mark);
+}
+
+static inline bool fanotify_fsid_equal(__kernel_fsid_t *fsid1,
+				       __kernel_fsid_t *fsid2)
+{
+	return fsid1->val[0] == fsid2->val[0] && fsid1->val[1] == fsid2->val[1];
+}
+
 static inline unsigned int fanotify_mark_user_flags(struct fsnotify_mark *mark)
 {
 	unsigned int mflags = 0;
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 4d765c72496f..fbdc63cc10d9 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -23,7 +23,7 @@
 
 #include <asm/ioctls.h>
 
-#include "../../mount.h"
+#include "../fsnotify.h"
 #include "../fdinfo.h"
 #include "fanotify.h"
 
@@ -86,7 +86,6 @@ static struct ctl_table fanotify_table[] = {
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO
 	},
-	{ }
 };
 
 static void __init fanotify_sysctls_init(void)
@@ -1192,13 +1191,71 @@ static bool fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark,
 	return recalc;
 }
 
+struct fan_fsid {
+	struct super_block *sb;
+	__kernel_fsid_t id;
+	bool weak;
+};
+
+static int fanotify_set_mark_fsid(struct fsnotify_group *group,
+				  struct fsnotify_mark *mark,
+				  struct fan_fsid *fsid)
+{
+	struct fsnotify_mark_connector *conn;
+	struct fsnotify_mark *old;
+	struct super_block *old_sb = NULL;
+
+	FANOTIFY_MARK(mark)->fsid = fsid->id;
+	mark->flags |= FSNOTIFY_MARK_FLAG_HAS_FSID;
+	if (fsid->weak)
+		mark->flags |= FSNOTIFY_MARK_FLAG_WEAK_FSID;
+
+	/* First mark added will determine if group is single or multi fsid */
+	if (list_empty(&group->marks_list))
+		return 0;
+
+	/* Find sb of an existing mark */
+	list_for_each_entry(old, &group->marks_list, g_list) {
+		conn = READ_ONCE(old->connector);
+		if (!conn)
+			continue;
+		old_sb = fsnotify_connector_sb(conn);
+		if (old_sb)
+			break;
+	}
+
+	/* Only detached marks left? */
+	if (!old_sb)
+		return 0;
+
+	/* Do not allow mixing of marks with weak and strong fsid */
+	if ((mark->flags ^ old->flags) & FSNOTIFY_MARK_FLAG_WEAK_FSID)
+		return -EXDEV;
+
+	/* Allow mixing of marks with strong fsid from different fs */
+	if (!fsid->weak)
+		return 0;
+
+	/* Do not allow mixing marks with weak fsid from different fs */
+	if (old_sb != fsid->sb)
+		return -EXDEV;
+
+	/* Do not allow mixing marks from different btrfs sub-volumes */
+	if (!fanotify_fsid_equal(&FANOTIFY_MARK(old)->fsid,
+				 &FANOTIFY_MARK(mark)->fsid))
+		return -EXDEV;
+
+	return 0;
+}
+
 static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
 						   fsnotify_connp_t *connp,
 						   unsigned int obj_type,
 						   unsigned int fan_flags,
-						   __kernel_fsid_t *fsid)
+						   struct fan_fsid *fsid)
 {
 	struct ucounts *ucounts = group->fanotify_data.ucounts;
+	struct fanotify_mark *fan_mark;
 	struct fsnotify_mark *mark;
 	int ret;
 
@@ -1211,24 +1268,34 @@ static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
 	    !inc_ucount(ucounts->ns, ucounts->uid, UCOUNT_FANOTIFY_MARKS))
 		return ERR_PTR(-ENOSPC);
 
-	mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
-	if (!mark) {
+	fan_mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
+	if (!fan_mark) {
 		ret = -ENOMEM;
 		goto out_dec_ucounts;
 	}
 
+	mark = &fan_mark->fsn_mark;
 	fsnotify_init_mark(mark, group);
 	if (fan_flags & FAN_MARK_EVICTABLE)
 		mark->flags |= FSNOTIFY_MARK_FLAG_NO_IREF;
 
-	ret = fsnotify_add_mark_locked(mark, connp, obj_type, 0, fsid);
-	if (ret) {
-		fsnotify_put_mark(mark);
-		goto out_dec_ucounts;
+	/* Cache fsid of filesystem containing the marked object */
+	if (fsid) {
+		ret = fanotify_set_mark_fsid(group, mark, fsid);
+		if (ret)
+			goto out_put_mark;
+	} else {
+		fan_mark->fsid.val[0] = fan_mark->fsid.val[1] = 0;
 	}
 
+	ret = fsnotify_add_mark_locked(mark, connp, obj_type, 0);
+	if (ret)
+		goto out_put_mark;
+
 	return mark;
 
+out_put_mark:
+	fsnotify_put_mark(mark);
 out_dec_ucounts:
 	if (!FAN_GROUP_FLAG(group, FAN_UNLIMITED_MARKS))
 		dec_ucount(ucounts, UCOUNT_FANOTIFY_MARKS);
@@ -1279,7 +1346,7 @@ static int fanotify_may_update_existing_mark(struct fsnotify_mark *fsn_mark,
 static int fanotify_add_mark(struct fsnotify_group *group,
 			     fsnotify_connp_t *connp, unsigned int obj_type,
 			     __u32 mask, unsigned int fan_flags,
-			     __kernel_fsid_t *fsid)
+			     struct fan_fsid *fsid)
 {
 	struct fsnotify_mark *fsn_mark;
 	bool recalc;
@@ -1327,7 +1394,7 @@ out:
 
 static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
 				      struct vfsmount *mnt, __u32 mask,
-				      unsigned int flags, __kernel_fsid_t *fsid)
+				      unsigned int flags, struct fan_fsid *fsid)
 {
 	return fanotify_add_mark(group, &real_mount(mnt)->mnt_fsnotify_marks,
 				 FSNOTIFY_OBJ_TYPE_VFSMOUNT, mask, flags, fsid);
@@ -1335,7 +1402,7 @@ static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
 
 static int fanotify_add_sb_mark(struct fsnotify_group *group,
 				struct super_block *sb, __u32 mask,
-				unsigned int flags, __kernel_fsid_t *fsid)
+				unsigned int flags, struct fan_fsid *fsid)
 {
 	return fanotify_add_mark(group, &sb->s_fsnotify_marks,
 				 FSNOTIFY_OBJ_TYPE_SB, mask, flags, fsid);
@@ -1343,7 +1410,7 @@ static int fanotify_add_sb_mark(struct fsnotify_group *group,
 
 static int fanotify_add_inode_mark(struct fsnotify_group *group,
 				   struct inode *inode, __u32 mask,
-				   unsigned int flags, __kernel_fsid_t *fsid)
+				   unsigned int flags, struct fan_fsid *fsid)
 {
 	pr_debug("%s: group=%p inode=%p\n", __func__, group, inode);
 
@@ -1554,20 +1621,25 @@ out_destroy_group:
 	return fd;
 }
 
-static int fanotify_test_fsid(struct dentry *dentry, __kernel_fsid_t *fsid)
+static int fanotify_test_fsid(struct dentry *dentry, unsigned int flags,
+			      struct fan_fsid *fsid)
 {
+	unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
 	__kernel_fsid_t root_fsid;
 	int err;
 
 	/*
 	 * Make sure dentry is not of a filesystem with zero fsid (e.g. fuse).
 	 */
-	err = vfs_get_fsid(dentry, fsid);
+	err = vfs_get_fsid(dentry, &fsid->id);
 	if (err)
 		return err;
 
-	if (!fsid->val[0] && !fsid->val[1])
-		return -ENODEV;
+	fsid->sb = dentry->d_sb;
+	if (!fsid->id.val[0] && !fsid->id.val[1]) {
+		err = -ENODEV;
+		goto weak;
+	}
 
 	/*
 	 * Make sure dentry is not of a filesystem subvolume (e.g. btrfs)
@@ -1577,11 +1649,18 @@ static int fanotify_test_fsid(struct dentry *dentry, __kernel_fsid_t *fsid)
 	if (err)
 		return err;
 
-	if (root_fsid.val[0] != fsid->val[0] ||
-	    root_fsid.val[1] != fsid->val[1])
-		return -EXDEV;
+	if (!fanotify_fsid_equal(&root_fsid, &fsid->id)) {
+		err = -EXDEV;
+		goto weak;
+	}
 
+	fsid->weak = false;
 	return 0;
+
+weak:
+	/* Allow weak fsid when marking inodes */
+	fsid->weak = true;
+	return (mark_type == FAN_MARK_INODE) ? 0 : err;
 }
 
 /* Check if filesystem can encode a unique fid */
@@ -1665,7 +1744,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 	struct fsnotify_group *group;
 	struct fd f;
 	struct path path;
-	__kernel_fsid_t __fsid, *fsid = NULL;
+	struct fan_fsid __fsid, *fsid = NULL;
 	u32 valid_mask = FANOTIFY_EVENTS | FANOTIFY_EVENT_FLAGS;
 	unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
 	unsigned int mark_cmd = flags & FANOTIFY_MARK_CMD_BITS;
@@ -1817,7 +1896,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 	}
 
 	if (fid_mode) {
-		ret = fanotify_test_fsid(path.dentry, &__fsid);
+		ret = fanotify_test_fsid(path.dentry, flags, &__fsid);
 		if (ret)
 			goto path_put_and_out;
 
@@ -1935,7 +2014,7 @@ static int __init fanotify_user_setup(void)
 	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 12);
 	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 11);
 
-	fanotify_mark_cache = KMEM_CACHE(fsnotify_mark,
+	fanotify_mark_cache = KMEM_CACHE(fanotify_mark,
 					 SLAB_PANIC|SLAB_ACCOUNT);
 	fanotify_fid_event_cachep = KMEM_CACHE(fanotify_fid_event,
 					       SLAB_PANIC);
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index a3809ae92170..85d8fdd55329 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -85,7 +85,6 @@ static struct ctl_table inotify_table[] = {
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO
 	},
-	{ }
 };
 
 static void __init inotify_sysctls_init(void)
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index c74ef947447d..d6944ff86ffa 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -537,8 +537,7 @@ int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b)
 }
 
 static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp,
-					       unsigned int obj_type,
-					       __kernel_fsid_t *fsid)
+					       unsigned int obj_type)
 {
 	struct fsnotify_mark_connector *conn;
 
@@ -550,14 +549,7 @@ static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp,
 	conn->flags = 0;
 	conn->type = obj_type;
 	conn->obj = connp;
-	/* Cache fsid of filesystem containing the object */
-	if (fsid) {
-		conn->fsid = *fsid;
-		conn->flags = FSNOTIFY_CONN_FLAG_HAS_FSID;
-	} else {
-		conn->fsid.val[0] = conn->fsid.val[1] = 0;
-		conn->flags = 0;
-	}
+	conn->flags = 0;
 	fsnotify_get_sb_connectors(conn);
 
 	/*
@@ -608,8 +600,7 @@ out:
  */
 static int fsnotify_add_mark_list(struct fsnotify_mark *mark,
 				  fsnotify_connp_t *connp,
-				  unsigned int obj_type,
-				  int add_flags, __kernel_fsid_t *fsid)
+				  unsigned int obj_type, int add_flags)
 {
 	struct fsnotify_mark *lmark, *last = NULL;
 	struct fsnotify_mark_connector *conn;
@@ -619,41 +610,15 @@ static int fsnotify_add_mark_list(struct fsnotify_mark *mark,
 	if (WARN_ON(!fsnotify_valid_obj_type(obj_type)))
 		return -EINVAL;
 
-	/* Backend is expected to check for zero fsid (e.g. tmpfs) */
-	if (fsid && WARN_ON_ONCE(!fsid->val[0] && !fsid->val[1]))
-		return -ENODEV;
-
 restart:
 	spin_lock(&mark->lock);
 	conn = fsnotify_grab_connector(connp);
 	if (!conn) {
 		spin_unlock(&mark->lock);
-		err = fsnotify_attach_connector_to_object(connp, obj_type,
-							  fsid);
+		err = fsnotify_attach_connector_to_object(connp, obj_type);
 		if (err)
 			return err;
 		goto restart;
-	} else if (fsid && !(conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID)) {
-		conn->fsid = *fsid;
-		/* Pairs with smp_rmb() in fanotify_get_fsid() */
-		smp_wmb();
-		conn->flags |= FSNOTIFY_CONN_FLAG_HAS_FSID;
-	} else if (fsid && (conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID) &&
-		   (fsid->val[0] != conn->fsid.val[0] ||
-		    fsid->val[1] != conn->fsid.val[1])) {
-		/*
-		 * Backend is expected to check for non uniform fsid
-		 * (e.g. btrfs), but maybe we missed something?
-		 * Only allow setting conn->fsid once to non zero fsid.
-		 * inotify and non-fid fanotify groups do not set nor test
-		 * conn->fsid.
-		 */
-		pr_warn_ratelimited("%s: fsid mismatch on object of type %u: "
-				    "%x.%x != %x.%x\n", __func__, conn->type,
-				    fsid->val[0], fsid->val[1],
-				    conn->fsid.val[0], conn->fsid.val[1]);
-		err = -EXDEV;
-		goto out_err;
 	}
 
 	/* is mark the first mark? */
@@ -703,7 +668,7 @@ out_err:
  */
 int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
 			     fsnotify_connp_t *connp, unsigned int obj_type,
-			     int add_flags, __kernel_fsid_t *fsid)
+			     int add_flags)
 {
 	struct fsnotify_group *group = mark->group;
 	int ret = 0;
@@ -723,7 +688,7 @@ int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
 	fsnotify_get_mark(mark); /* for g_list */
 	spin_unlock(&mark->lock);
 
-	ret = fsnotify_add_mark_list(mark, connp, obj_type, add_flags, fsid);
+	ret = fsnotify_add_mark_list(mark, connp, obj_type, add_flags);
 	if (ret)
 		goto err;
 
@@ -742,14 +707,13 @@ err:
 }
 
 int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp,
-		      unsigned int obj_type, int add_flags,
-		      __kernel_fsid_t *fsid)
+		      unsigned int obj_type, int add_flags)
 {
 	int ret;
 	struct fsnotify_group *group = mark->group;
 
 	fsnotify_group_lock(group);
-	ret = fsnotify_add_mark_locked(mark, connp, obj_type, add_flags, fsid);
+	ret = fsnotify_add_mark_locked(mark, connp, obj_type, add_flags);
 	fsnotify_group_unlock(group);
 	return ret;
 }
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 71e31e789b29..2d01517a2d59 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -1304,7 +1304,7 @@ done:
  * page cleaned.  The VM has already locked the page and marked it clean.
  *
  * For non-resident attributes, ntfs_writepage() writes the @page by calling
- * the ntfs version of the generic block_write_full_page() function,
+ * the ntfs version of the generic block_write_full_folio() function,
  * ntfs_write_block(), which in turn if necessary creates and writes the
  * buffers associated with the page asynchronously.
  *
@@ -1314,7 +1314,7 @@ done:
  * vfs inode dirty code path for the inode the mft record belongs to or via the
  * vm page dirty code path for the page the mft record is in.
  *
- * Based on ntfs_read_folio() and fs/buffer.c::block_write_full_page().
+ * Based on ntfs_read_folio() and fs/buffer.c::block_write_full_folio().
  *
  * Return 0 on success and -errno on error.
  */
@@ -1644,7 +1644,7 @@ const struct address_space_operations ntfs_normal_aops = {
 	.bmap		= ntfs_bmap,
 	.migrate_folio	= buffer_migrate_folio,
 	.is_partially_uptodate = block_is_partially_uptodate,
-	.error_remove_page = generic_error_remove_page,
+	.error_remove_folio = generic_error_remove_folio,
 };
 
 /*
@@ -1658,7 +1658,7 @@ const struct address_space_operations ntfs_compressed_aops = {
 #endif /* NTFS_RW */
 	.migrate_folio	= buffer_migrate_folio,
 	.is_partially_uptodate = block_is_partially_uptodate,
-	.error_remove_page = generic_error_remove_page,
+	.error_remove_folio = generic_error_remove_folio,
 };
 
 /*
@@ -1673,7 +1673,7 @@ const struct address_space_operations ntfs_mst_aops = {
 #endif /* NTFS_RW */
 	.migrate_folio	= buffer_migrate_folio,
 	.is_partially_uptodate	= block_is_partially_uptodate,
-	.error_remove_page = generic_error_remove_page,
+	.error_remove_folio = generic_error_remove_folio,
 };
 
 #ifdef NTFS_RW
@@ -1690,7 +1690,7 @@ const struct address_space_operations ntfs_mst_aops = {
  *
  * If the page does not have buffers, we create them and set them uptodate.
  * The page may not be locked which is why we need to handle the buffers under
- * the mapping->private_lock.  Once the buffers are marked dirty we no longer
+ * the mapping->i_private_lock.  Once the buffers are marked dirty we no longer
  * need the lock since try_to_free_buffers() does not free dirty buffers.
  */
 void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) {
@@ -1702,11 +1702,11 @@ void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) {
 	BUG_ON(!PageUptodate(page));
 	end = ofs + ni->itype.index.block_size;
 	bh_size = VFS_I(ni)->i_sb->s_blocksize;
-	spin_lock(&mapping->private_lock);
+	spin_lock(&mapping->i_private_lock);
 	if (unlikely(!page_has_buffers(page))) {
-		spin_unlock(&mapping->private_lock);
+		spin_unlock(&mapping->i_private_lock);
 		bh = head = alloc_page_buffers(page, bh_size, true);
-		spin_lock(&mapping->private_lock);
+		spin_lock(&mapping->i_private_lock);
 		if (likely(!page_has_buffers(page))) {
 			struct buffer_head *tail;
 
@@ -1730,7 +1730,7 @@ void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) {
 			break;
 		set_buffer_dirty(bh);
 	} while ((bh = bh->b_this_page) != head);
-	spin_unlock(&mapping->private_lock);
+	spin_unlock(&mapping->i_private_lock);
 	filemap_dirty_folio(mapping, page_folio(page));
 	if (unlikely(buffers_to_free)) {
 		do {
diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c
index 4596c90e7b7c..629723a8d712 100644
--- a/fs/ntfs/dir.c
+++ b/fs/ntfs/dir.c
@@ -1462,7 +1462,8 @@ static int ntfs_dir_open(struct inode *vi, struct file *filp)
 /**
  * ntfs_dir_fsync - sync a directory to disk
  * @filp:	directory to be synced
- * @dentry:	dentry describing the directory to sync
+ * @start:	offset in bytes of the beginning of data range to sync
+ * @end:	offset in bytes of the end of data range (inclusive)
  * @datasync:	if non-zero only flush user data and not metadata
  *
  * Data integrity sync of a directory to disk.  Used for fsync, fdatasync, and
diff --git a/fs/ntfs/sysctl.c b/fs/ntfs/sysctl.c
index 174fe536a1c0..4e980170d86a 100644
--- a/fs/ntfs/sysctl.c
+++ b/fs/ntfs/sysctl.c
@@ -28,7 +28,6 @@ static struct ctl_table ntfs_sysctls[] = {
 		.mode		= 0644,			/* Mode, proc handler. */
 		.proc_handler	= proc_dointvec
 	},
-	{}
 };
 
 /* Storage for the sysctls header. */
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 91b32b2377ac..ea9127ba3208 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -6934,7 +6934,7 @@ static int ocfs2_grab_eof_pages(struct inode *inode, loff_t start, loff_t end,
  * nonzero data on subsequent file extends.
  *
  * We need to call this before i_size is updated on the inode because
- * otherwise block_write_full_page() will skip writeout of pages past
+ * otherwise block_write_full_folio() will skip writeout of pages past
  * i_size.
  */
 int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index ba790219d528..b82185075de7 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -389,21 +389,18 @@ out_unlock:
 /* Note: Because we don't support holes, our allocation has
  * already happened (allocation writes zeros to the file data)
  * so we don't have to worry about ordered writes in
- * ocfs2_writepage.
+ * ocfs2_writepages.
  *
- * ->writepage is called during the process of invalidating the page cache
+ * ->writepages is called during the process of invalidating the page cache
  * during blocked lock processing.  It can't block on any cluster locks
  * to during block mapping.  It's relying on the fact that the block
  * mapping can't have disappeared under the dirty pages that it is
  * being asked to write back.
  */
-static int ocfs2_writepage(struct page *page, struct writeback_control *wbc)
+static int ocfs2_writepages(struct address_space *mapping,
+		struct writeback_control *wbc)
 {
-	trace_ocfs2_writepage(
-		(unsigned long long)OCFS2_I(page->mapping->host)->ip_blkno,
-		page->index);
-
-	return block_write_full_page(page, ocfs2_get_block, wbc);
+	return mpage_writepages(mapping, wbc, ocfs2_get_block);
 }
 
 /* Taken from ext3. We don't necessarily need the full blown
@@ -2471,7 +2468,7 @@ const struct address_space_operations ocfs2_aops = {
 	.dirty_folio		= block_dirty_folio,
 	.read_folio		= ocfs2_read_folio,
 	.readahead		= ocfs2_readahead,
-	.writepage		= ocfs2_writepage,
+	.writepages		= ocfs2_writepages,
 	.write_begin		= ocfs2_write_begin,
 	.write_end		= ocfs2_write_end,
 	.bmap			= ocfs2_bmap,
@@ -2480,5 +2477,5 @@ const struct address_space_operations ocfs2_aops = {
 	.release_folio		= ocfs2_release_folio,
 	.migrate_folio		= buffer_migrate_folio,
 	.is_partially_uptodate	= block_is_partially_uptodate,
-	.error_remove_page	= generic_error_remove_page,
+	.error_remove_folio	= generic_error_remove_folio,
 };
diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c
index eaa8c80ace3c..b8b6a191b5cb 100644
--- a/fs/ocfs2/export.c
+++ b/fs/ocfs2/export.c
@@ -280,4 +280,5 @@ const struct export_operations ocfs2_export_ops = {
 	.fh_to_dentry	= ocfs2_fh_to_dentry,
 	.fh_to_parent	= ocfs2_fh_to_parent,
 	.get_parent	= ocfs2_get_parent,
+	.flags		= EXPORT_OP_ASYNC_LOCK,
 };
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 94e2a1244442..8b6d15010703 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -818,7 +818,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
 	/*
 	 * fs-writeback will release the dirty pages without page lock
 	 * whose offset are over inode size, the release happens at
-	 * block_write_full_page().
+	 * block_write_full_folio().
 	 */
 	i_size_write(inode, abs_to);
 	inode->i_blocks = ocfs2_inode_sector_count(inode);
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index ac4fd1d5b128..9898c11bdfa1 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -1157,8 +1157,6 @@ DEFINE_OCFS2_ULL_ULL_EVENT(ocfs2_get_block_end);
 
 DEFINE_OCFS2_ULL_ULL_EVENT(ocfs2_readpage);
 
-DEFINE_OCFS2_ULL_ULL_EVENT(ocfs2_writepage);
-
 DEFINE_OCFS2_ULL_ULL_EVENT(ocfs2_bmap);
 
 TRACE_EVENT(ocfs2_try_to_write_inline_data,
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index a8d5ca98fa57..20aa37b67cfb 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -658,7 +658,6 @@ static struct ctl_table ocfs2_nm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dostring,
 	},
-	{ }
 };
 
 static struct ctl_table_header *ocfs2_table_header;
diff --git a/fs/open.c b/fs/open.c
index 02dc608d40d8..a84d21e55c39 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -304,6 +304,10 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (ret)
 		return ret;
 
+	ret = fsnotify_file_area_perm(file, MAY_WRITE, &offset, len);
+	if (ret)
+		return ret;
+
 	if (S_ISFIFO(inode->i_mode))
 		return -ESPIPE;
 
@@ -442,7 +446,8 @@ static const struct cred *access_override_creds(void)
 	 * 'get_current_cred()' function), that will clear the
 	 * non_rcu field, because now that other user may be
 	 * expecting RCU freeing. But normal thread-synchronous
-	 * cred accesses will keep things non-RCY.
+	 * cred accesses will keep things non-racy to avoid RCU
+	 * freeing.
 	 */
 	override_cred->non_rcu = 1;
 
@@ -1088,8 +1093,6 @@ struct file *dentry_open(const struct path *path, int flags,
 	int error;
 	struct file *f;
 
-	validate_creds(cred);
-
 	/* We must always pass in a valid mount pointer. */
 	BUG_ON(!path->mnt);
 
@@ -1128,7 +1131,6 @@ struct file *dentry_create(const struct path *path, int flags, umode_t mode,
 	struct file *f;
 	int error;
 
-	validate_creds(cred);
 	f = alloc_empty_file(flags, cred);
 	if (IS_ERR(f))
 		return f;
@@ -1180,44 +1182,6 @@ struct file *kernel_file_open(const struct path *path, int flags,
 }
 EXPORT_SYMBOL_GPL(kernel_file_open);
 
-/**
- * backing_file_open - open a backing file for kernel internal use
- * @user_path:	path that the user reuqested to open
- * @flags:	open flags
- * @real_path:	path of the backing file
- * @cred:	credentials for open
- *
- * Open a backing file for a stackable filesystem (e.g., overlayfs).
- * @user_path may be on the stackable filesystem and @real_path on the
- * underlying filesystem.  In this case, we want to be able to return the
- * @user_path of the stackable filesystem. This is done by embedding the
- * returned file into a container structure that also stores the stacked
- * file's path, which can be retrieved using backing_file_user_path().
- */
-struct file *backing_file_open(const struct path *user_path, int flags,
-			       const struct path *real_path,
-			       const struct cred *cred)
-{
-	struct file *f;
-	int error;
-
-	f = alloc_empty_backing_file(flags, cred);
-	if (IS_ERR(f))
-		return f;
-
-	path_get(user_path);
-	*backing_file_user_path(f) = *user_path;
-	f->f_path = *real_path;
-	error = do_dentry_open(f, d_inode(real_path->dentry), NULL);
-	if (error) {
-		fput(f);
-		f = ERR_PTR(error);
-	}
-
-	return f;
-}
-EXPORT_SYMBOL_GPL(backing_file_open);
-
 #define WILL_CREATE(flags)	(flags & (O_CREAT | __O_TMPFILE))
 #define O_PATH_FLAGS		(O_DIRECTORY | O_NOFOLLOW | O_PATH | O_CLOEXEC)
 
@@ -1577,7 +1541,7 @@ SYSCALL_DEFINE1(close, unsigned int, fd)
 	int retval;
 	struct file *file;
 
-	file = close_fd_get_file(fd);
+	file = file_close_fd(fd);
 	if (!file)
 		return -EBADF;
 
diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig
index fec5020c3495..2ac67e04a6fb 100644
--- a/fs/overlayfs/Kconfig
+++ b/fs/overlayfs/Kconfig
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config OVERLAY_FS
 	tristate "Overlay filesystem support"
+	select FS_STACK
 	select EXPORTFS
 	help
 	  An overlay filesystem combines two filesystems - an 'upper' filesystem
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 4382881b0709..696478f09cc1 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -230,6 +230,19 @@ static int ovl_copy_fileattr(struct inode *inode, const struct path *old,
 	return ovl_real_fileattr_set(new, &newfa);
 }
 
+static int ovl_verify_area(loff_t pos, loff_t pos2, loff_t len, loff_t totlen)
+{
+	loff_t tmp;
+
+	if (WARN_ON_ONCE(pos != pos2))
+		return -EIO;
+	if (WARN_ON_ONCE(pos < 0 || len < 0 || totlen < 0))
+		return -EIO;
+	if (WARN_ON_ONCE(check_add_overflow(pos, len, &tmp)))
+		return -EIO;
+	return 0;
+}
+
 static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry,
 			    struct file *new_file, loff_t len)
 {
@@ -244,13 +257,20 @@ static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry,
 	int error = 0;
 
 	ovl_path_lowerdata(dentry, &datapath);
-	if (WARN_ON(datapath.dentry == NULL))
+	if (WARN_ON_ONCE(datapath.dentry == NULL) ||
+	    WARN_ON_ONCE(len < 0))
 		return -EIO;
 
 	old_file = ovl_path_open(&datapath, O_LARGEFILE | O_RDONLY);
 	if (IS_ERR(old_file))
 		return PTR_ERR(old_file);
 
+	error = rw_verify_area(READ, old_file, &old_pos, len);
+	if (!error)
+		error = rw_verify_area(WRITE, new_file, &new_pos, len);
+	if (error)
+		goto out_fput;
+
 	/* Try to use clone_file_range to clone up within the same fs */
 	ovl_start_write(dentry);
 	cloned = do_clone_file_range(old_file, 0, new_file, 0, len, 0);
@@ -265,7 +285,7 @@ static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry,
 
 	while (len) {
 		size_t this_len = OVL_COPY_UP_CHUNK_SIZE;
-		long bytes;
+		ssize_t bytes;
 
 		if (len < this_len)
 			this_len = len;
@@ -309,11 +329,13 @@ static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry,
 			}
 		}
 
-		ovl_start_write(dentry);
+		error = ovl_verify_area(old_pos, new_pos, this_len, len);
+		if (error)
+			break;
+
 		bytes = do_splice_direct(old_file, &old_pos,
 					 new_file, &new_pos,
 					 this_len, SPLICE_F_MOVE);
-		ovl_end_write(dentry);
 		if (bytes <= 0) {
 			error = bytes;
 			break;
@@ -753,15 +775,16 @@ static int ovl_copy_up_workdir(struct ovl_copy_up_ctx *c)
 	path.dentry = temp;
 	err = ovl_copy_up_data(c, &path);
 	/*
-	 * We cannot hold lock_rename() throughout this helper, because or
+	 * We cannot hold lock_rename() throughout this helper, because of
 	 * lock ordering with sb_writers, which shouldn't be held when calling
 	 * ovl_copy_up_data(), so lock workdir and destdir and make sure that
 	 * temp wasn't moved before copy up completion or cleanup.
-	 * If temp was moved, abort without the cleanup.
 	 */
 	ovl_start_write(c->dentry);
 	if (lock_rename(c->workdir, c->destdir) != NULL ||
 	    temp->d_parent != c->workdir) {
+		/* temp or workdir moved underneath us? abort without cleanup */
+		dput(temp);
 		err = -EIO;
 		goto unlock;
 	} else if (err) {
@@ -930,6 +953,13 @@ static int ovl_do_copy_up(struct ovl_copy_up_ctx *c)
 		goto out_free_fh;
 	} else {
 		/*
+		 * c->dentry->d_name is stabilzed by ovl_copy_up_start(),
+		 * because if we got here, it means that c->dentry has no upper
+		 * alias and changing ->d_name means going through ovl_rename()
+		 * that will call ovl_copy_up() on source and target dentry.
+		 */
+		c->destname = c->dentry->d_name;
+		/*
 		 * Mark parent "impure" because it may now contain non-pure
 		 * upper
 		 */
@@ -1109,7 +1139,6 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	if (parent) {
 		ovl_path_upper(parent, &parentpath);
 		ctx.destdir = parentpath.dentry;
-		ctx.destname = dentry->d_name;
 
 		err = vfs_getattr(&parentpath, &ctx.pstat,
 				  STATX_ATIME | STATX_MTIME,
diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c
index 7e16bbcad95e..6909c4a5da56 100644
--- a/fs/overlayfs/export.c
+++ b/fs/overlayfs/export.c
@@ -460,7 +460,7 @@ static struct dentry *ovl_lookup_real_inode(struct super_block *sb,
 	 * For decoded lower dir file handle, lookup index by origin to check
 	 * if lower dir was copied up and and/or removed.
 	 */
-	if (!this && layer->idx && ofs->indexdir && !WARN_ON(!d_is_dir(real))) {
+	if (!this && layer->idx && ovl_indexdir(sb) && !WARN_ON(!d_is_dir(real))) {
 		index = ovl_lookup_index(ofs, NULL, real, false);
 		if (IS_ERR(index))
 			return index;
@@ -733,7 +733,7 @@ static struct dentry *ovl_lower_fh_to_d(struct super_block *sb,
 	}
 
 	/* Then lookup indexed upper/whiteout by origin fh */
-	if (ofs->indexdir) {
+	if (ovl_indexdir(sb)) {
 		index = ovl_get_index_fh(ofs, fh);
 		err = PTR_ERR(index);
 		if (IS_ERR(index)) {
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 131621daeb13..05536964d37f 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -9,25 +9,11 @@
 #include <linux/xattr.h>
 #include <linux/uio.h>
 #include <linux/uaccess.h>
-#include <linux/splice.h>
 #include <linux/security.h>
-#include <linux/mm.h>
 #include <linux/fs.h>
+#include <linux/backing-file.h>
 #include "overlayfs.h"
 
-#include "../internal.h"	/* for sb_init_dio_done_wq */
-
-struct ovl_aio_req {
-	struct kiocb iocb;
-	refcount_t ref;
-	struct kiocb *orig_iocb;
-	/* used for aio completion */
-	struct work_struct work;
-	long res;
-};
-
-static struct kmem_cache *ovl_aio_request_cachep;
-
 static char ovl_whatisit(struct inode *inode, struct inode *realinode)
 {
 	if (realinode != ovl_inode_upper(inode))
@@ -274,83 +260,16 @@ static void ovl_file_accessed(struct file *file)
 	touch_atime(&file->f_path);
 }
 
-#define OVL_IOCB_MASK \
-	(IOCB_NOWAIT | IOCB_HIPRI | IOCB_DSYNC | IOCB_SYNC | IOCB_APPEND)
-
-static rwf_t iocb_to_rw_flags(int flags)
-{
-	return (__force rwf_t)(flags & OVL_IOCB_MASK);
-}
-
-static inline void ovl_aio_put(struct ovl_aio_req *aio_req)
-{
-	if (refcount_dec_and_test(&aio_req->ref)) {
-		fput(aio_req->iocb.ki_filp);
-		kmem_cache_free(ovl_aio_request_cachep, aio_req);
-	}
-}
-
-static void ovl_aio_cleanup_handler(struct ovl_aio_req *aio_req)
-{
-	struct kiocb *iocb = &aio_req->iocb;
-	struct kiocb *orig_iocb = aio_req->orig_iocb;
-
-	if (iocb->ki_flags & IOCB_WRITE) {
-		kiocb_end_write(iocb);
-		ovl_file_modified(orig_iocb->ki_filp);
-	}
-
-	orig_iocb->ki_pos = iocb->ki_pos;
-	ovl_aio_put(aio_req);
-}
-
-static void ovl_aio_rw_complete(struct kiocb *iocb, long res)
-{
-	struct ovl_aio_req *aio_req = container_of(iocb,
-						   struct ovl_aio_req, iocb);
-	struct kiocb *orig_iocb = aio_req->orig_iocb;
-
-	ovl_aio_cleanup_handler(aio_req);
-	orig_iocb->ki_complete(orig_iocb, res);
-}
-
-static void ovl_aio_complete_work(struct work_struct *work)
-{
-	struct ovl_aio_req *aio_req = container_of(work,
-						   struct ovl_aio_req, work);
-
-	ovl_aio_rw_complete(&aio_req->iocb, aio_req->res);
-}
-
-static void ovl_aio_queue_completion(struct kiocb *iocb, long res)
-{
-	struct ovl_aio_req *aio_req = container_of(iocb,
-						   struct ovl_aio_req, iocb);
-	struct kiocb *orig_iocb = aio_req->orig_iocb;
-
-	/*
-	 * Punt to a work queue to serialize updates of mtime/size.
-	 */
-	aio_req->res = res;
-	INIT_WORK(&aio_req->work, ovl_aio_complete_work);
-	queue_work(file_inode(orig_iocb->ki_filp)->i_sb->s_dio_done_wq,
-		   &aio_req->work);
-}
-
-static int ovl_init_aio_done_wq(struct super_block *sb)
-{
-	if (sb->s_dio_done_wq)
-		return 0;
-
-	return sb_init_dio_done_wq(sb);
-}
-
 static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct file *file = iocb->ki_filp;
 	struct fd real;
-	const struct cred *old_cred;
 	ssize_t ret;
+	struct backing_file_ctx ctx = {
+		.cred = ovl_creds(file_inode(file)->i_sb),
+		.user_file = file,
+		.accessed = ovl_file_accessed,
+	};
 
 	if (!iov_iter_count(iter))
 		return 0;
@@ -359,37 +278,8 @@ static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 	if (ret)
 		return ret;
 
-	ret = -EINVAL;
-	if (iocb->ki_flags & IOCB_DIRECT &&
-	    !(real.file->f_mode & FMODE_CAN_ODIRECT))
-		goto out_fdput;
-
-	old_cred = ovl_override_creds(file_inode(file)->i_sb);
-	if (is_sync_kiocb(iocb)) {
-		rwf_t rwf = iocb_to_rw_flags(iocb->ki_flags);
-
-		ret = vfs_iter_read(real.file, iter, &iocb->ki_pos, rwf);
-	} else {
-		struct ovl_aio_req *aio_req;
-
-		ret = -ENOMEM;
-		aio_req = kmem_cache_zalloc(ovl_aio_request_cachep, GFP_KERNEL);
-		if (!aio_req)
-			goto out;
-
-		aio_req->orig_iocb = iocb;
-		kiocb_clone(&aio_req->iocb, iocb, get_file(real.file));
-		aio_req->iocb.ki_complete = ovl_aio_rw_complete;
-		refcount_set(&aio_req->ref, 2);
-		ret = vfs_iocb_iter_read(real.file, &aio_req->iocb, iter);
-		ovl_aio_put(aio_req);
-		if (ret != -EIOCBQUEUED)
-			ovl_aio_cleanup_handler(aio_req);
-	}
-out:
-	revert_creds(old_cred);
-	ovl_file_accessed(file);
-out_fdput:
+	ret = backing_file_read_iter(real.file, iter, iocb, iocb->ki_flags,
+				     &ctx);
 	fdput(real);
 
 	return ret;
@@ -400,9 +290,13 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	struct fd real;
-	const struct cred *old_cred;
 	ssize_t ret;
 	int ifl = iocb->ki_flags;
+	struct backing_file_ctx ctx = {
+		.cred = ovl_creds(inode->i_sb),
+		.user_file = file,
+		.end_write = ovl_file_modified,
+	};
 
 	if (!iov_iter_count(iter))
 		return 0;
@@ -410,19 +304,11 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 	inode_lock(inode);
 	/* Update mode */
 	ovl_copyattr(inode);
-	ret = file_remove_privs(file);
-	if (ret)
-		goto out_unlock;
 
 	ret = ovl_real_fdget(file, &real);
 	if (ret)
 		goto out_unlock;
 
-	ret = -EINVAL;
-	if (iocb->ki_flags & IOCB_DIRECT &&
-	    !(real.file->f_mode & FMODE_CAN_ODIRECT))
-		goto out_fdput;
-
 	if (!ovl_should_sync(OVL_FS(inode->i_sb)))
 		ifl &= ~(IOCB_DSYNC | IOCB_SYNC);
 
@@ -431,42 +317,7 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 	 * this property in case it is set by the issuer.
 	 */
 	ifl &= ~IOCB_DIO_CALLER_COMP;
-
-	old_cred = ovl_override_creds(file_inode(file)->i_sb);
-	if (is_sync_kiocb(iocb)) {
-		rwf_t rwf = iocb_to_rw_flags(ifl);
-
-		file_start_write(real.file);
-		ret = vfs_iter_write(real.file, iter, &iocb->ki_pos, rwf);
-		file_end_write(real.file);
-		/* Update size */
-		ovl_file_modified(file);
-	} else {
-		struct ovl_aio_req *aio_req;
-
-		ret = ovl_init_aio_done_wq(inode->i_sb);
-		if (ret)
-			goto out;
-
-		ret = -ENOMEM;
-		aio_req = kmem_cache_zalloc(ovl_aio_request_cachep, GFP_KERNEL);
-		if (!aio_req)
-			goto out;
-
-		aio_req->orig_iocb = iocb;
-		kiocb_clone(&aio_req->iocb, iocb, get_file(real.file));
-		aio_req->iocb.ki_flags = ifl;
-		aio_req->iocb.ki_complete = ovl_aio_queue_completion;
-		refcount_set(&aio_req->ref, 2);
-		kiocb_start_write(&aio_req->iocb);
-		ret = vfs_iocb_iter_write(real.file, &aio_req->iocb, iter);
-		ovl_aio_put(aio_req);
-		if (ret != -EIOCBQUEUED)
-			ovl_aio_cleanup_handler(aio_req);
-	}
-out:
-	revert_creds(old_cred);
-out_fdput:
+	ret = backing_file_write_iter(real.file, iter, iocb, ifl, &ctx);
 	fdput(real);
 
 out_unlock:
@@ -479,20 +330,21 @@ static ssize_t ovl_splice_read(struct file *in, loff_t *ppos,
 			       struct pipe_inode_info *pipe, size_t len,
 			       unsigned int flags)
 {
-	const struct cred *old_cred;
 	struct fd real;
 	ssize_t ret;
+	struct backing_file_ctx ctx = {
+		.cred = ovl_creds(file_inode(in)->i_sb),
+		.user_file = in,
+		.accessed = ovl_file_accessed,
+	};
 
 	ret = ovl_real_fdget(in, &real);
 	if (ret)
 		return ret;
 
-	old_cred = ovl_override_creds(file_inode(in)->i_sb);
-	ret = vfs_splice_read(real.file, ppos, pipe, len, flags);
-	revert_creds(old_cred);
-	ovl_file_accessed(in);
-
+	ret = backing_file_splice_read(real.file, ppos, pipe, len, flags, &ctx);
 	fdput(real);
+
 	return ret;
 }
 
@@ -508,30 +360,23 @@ static ssize_t ovl_splice_write(struct pipe_inode_info *pipe, struct file *out,
 				loff_t *ppos, size_t len, unsigned int flags)
 {
 	struct fd real;
-	const struct cred *old_cred;
 	struct inode *inode = file_inode(out);
 	ssize_t ret;
+	struct backing_file_ctx ctx = {
+		.cred = ovl_creds(inode->i_sb),
+		.user_file = out,
+		.end_write = ovl_file_modified,
+	};
 
 	inode_lock(inode);
 	/* Update mode */
 	ovl_copyattr(inode);
-	ret = file_remove_privs(out);
-	if (ret)
-		goto out_unlock;
 
 	ret = ovl_real_fdget(out, &real);
 	if (ret)
 		goto out_unlock;
 
-	old_cred = ovl_override_creds(inode->i_sb);
-	file_start_write(real.file);
-
-	ret = iter_file_splice_write(pipe, real.file, ppos, len, flags);
-
-	file_end_write(real.file);
-	/* Update size */
-	ovl_file_modified(out);
-	revert_creds(old_cred);
+	ret = backing_file_splice_write(pipe, real.file, ppos, len, flags, &ctx);
 	fdput(real);
 
 out_unlock:
@@ -569,23 +414,13 @@ static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 static int ovl_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct file *realfile = file->private_data;
-	const struct cred *old_cred;
-	int ret;
-
-	if (!realfile->f_op->mmap)
-		return -ENODEV;
+	struct backing_file_ctx ctx = {
+		.cred = ovl_creds(file_inode(file)->i_sb),
+		.user_file = file,
+		.accessed = ovl_file_accessed,
+	};
 
-	if (WARN_ON(file != vma->vm_file))
-		return -EIO;
-
-	vma_set_file(vma, realfile);
-
-	old_cred = ovl_override_creds(file_inode(file)->i_sb);
-	ret = call_mmap(vma->vm_file, vma);
-	revert_creds(old_cred);
-	ovl_file_accessed(file);
-
-	return ret;
+	return backing_file_mmap(realfile, vma, &ctx);
 }
 
 static long ovl_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
@@ -778,19 +613,3 @@ const struct file_operations ovl_file_operations = {
 	.copy_file_range	= ovl_copy_file_range,
 	.remap_file_range	= ovl_remap_file_range,
 };
-
-int __init ovl_aio_request_cache_init(void)
-{
-	ovl_aio_request_cachep = kmem_cache_create("ovl_aio_req",
-						   sizeof(struct ovl_aio_req),
-						   0, SLAB_HWCACHE_ALIGN, NULL);
-	if (!ovl_aio_request_cachep)
-		return -ENOMEM;
-
-	return 0;
-}
-
-void ovl_aio_request_cache_destroy(void)
-{
-	kmem_cache_destroy(ovl_aio_request_cachep);
-}
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 345b8f161ca4..c63b31a460be 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -171,7 +171,7 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path,
 
 	type = ovl_path_real(dentry, &realpath);
 	old_cred = ovl_override_creds(dentry->d_sb);
-	err = vfs_getattr(&realpath, stat, request_mask, flags);
+	err = ovl_do_getattr(&realpath, stat, request_mask, flags);
 	if (err)
 		goto out;
 
@@ -196,8 +196,8 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path,
 					(!is_dir ? STATX_NLINK : 0);
 
 			ovl_path_lower(dentry, &realpath);
-			err = vfs_getattr(&realpath, &lowerstat,
-					  lowermask, flags);
+			err = ovl_do_getattr(&realpath, &lowerstat, lowermask,
+					     flags);
 			if (err)
 				goto out;
 
@@ -249,8 +249,8 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path,
 
 			ovl_path_lowerdata(dentry, &realpath);
 			if (realpath.dentry) {
-				err = vfs_getattr(&realpath, &lowerdatastat,
-						  lowermask, flags);
+				err = ovl_do_getattr(&realpath, &lowerdatastat,
+						     lowermask, flags);
 				if (err)
 					goto out;
 			} else {
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index 03bc8d5dfa31..984ffdaeed6c 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -754,7 +754,7 @@ struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh)
 	if (err)
 		return ERR_PTR(err);
 
-	index = lookup_positive_unlocked(name.name, ofs->indexdir, name.len);
+	index = lookup_positive_unlocked(name.name, ofs->workdir, name.len);
 	kfree(name.name);
 	if (IS_ERR(index)) {
 		if (PTR_ERR(index) == -ENOENT)
@@ -787,7 +787,7 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper,
 		return ERR_PTR(err);
 
 	index = lookup_one_positive_unlocked(ovl_upper_mnt_idmap(ofs), name.name,
-					     ofs->indexdir, name.len);
+					     ofs->workdir, name.len);
 	if (IS_ERR(index)) {
 		err = PTR_ERR(index);
 		if (err == -ENOENT) {
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index ca88b2636a57..5ba11eb43767 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -408,6 +408,14 @@ static inline bool ovl_open_flags_need_copy_up(int flags)
 	return ((OPEN_FMODE(flags) & FMODE_WRITE) || (flags & O_TRUNC));
 }
 
+static inline int ovl_do_getattr(const struct path *path, struct kstat *stat,
+				 u32 request_mask, unsigned int flags)
+{
+	if (flags & AT_GETATTR_NOSEC)
+		return vfs_getattr_nosec(path, stat, request_mask, flags);
+	return vfs_getattr(path, stat, request_mask, flags);
+}
+
 /* util.c */
 int ovl_get_write_access(struct dentry *dentry);
 void ovl_put_write_access(struct dentry *dentry);
@@ -417,6 +425,12 @@ int ovl_want_write(struct dentry *dentry);
 void ovl_drop_write(struct dentry *dentry);
 struct dentry *ovl_workdir(struct dentry *dentry);
 const struct cred *ovl_override_creds(struct super_block *sb);
+
+static inline const struct cred *ovl_creds(struct super_block *sb)
+{
+	return OVL_FS(sb)->creator_cred;
+}
+
 int ovl_can_decode_fh(struct super_block *sb);
 struct dentry *ovl_indexdir(struct super_block *sb);
 bool ovl_index_all(struct super_block *sb);
@@ -829,8 +843,6 @@ struct dentry *ovl_create_temp(struct ovl_fs *ofs, struct dentry *workdir,
 
 /* file.c */
 extern const struct file_operations ovl_file_operations;
-int __init ovl_aio_request_cache_init(void);
-void ovl_aio_request_cache_destroy(void);
 int ovl_real_fileattr_get(const struct path *realpath, struct fileattr *fa);
 int ovl_real_fileattr_set(const struct path *realpath, struct fileattr *fa);
 int ovl_fileattr_get(struct dentry *dentry, struct fileattr *fa);
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index d82d2a043da2..5fa9c58af65f 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -63,10 +63,8 @@ struct ovl_fs {
 	struct ovl_sb *fs;
 	/* workbasedir is the path at workdir= mount option */
 	struct dentry *workbasedir;
-	/* workdir is the 'work' directory under workbasedir */
+	/* workdir is the 'work' or 'index' directory under workbasedir */
 	struct dentry *workdir;
-	/* index directory listing overlay inodes by origin file handle */
-	struct dentry *indexdir;
 	long namelen;
 	/* pathnames of lower and upper dirs, for show_options */
 	struct ovl_config config;
@@ -81,7 +79,6 @@ struct ovl_fs {
 	/* Traps in ovl inode cache */
 	struct inode *workbasedir_trap;
 	struct inode *workdir_trap;
-	struct inode *indexdir_trap;
 	/* -1: disabled, 0: same fs, 1..32: number of unused ino bits */
 	int xino_mode;
 	/* For allocation of non-persistent inode numbers */
diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c
index ddab9ea267d1..112b4b12f825 100644
--- a/fs/overlayfs/params.c
+++ b/fs/overlayfs/params.c
@@ -430,7 +430,7 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
 	struct ovl_fs_context *ctx = fc->fs_private;
 	struct ovl_fs_context_layer *l;
 	char *dup = NULL, *iter;
-	ssize_t nr_lower = 0, nr = 0, nr_data = 0;
+	ssize_t nr_lower, nr;
 	bool data_layer = false;
 
 	/*
@@ -482,6 +482,7 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
 	iter = dup;
 	l = ctx->lower;
 	for (nr = 0; nr < nr_lower; nr++, l++) {
+		ctx->nr++;
 		memset(l, 0, sizeof(*l));
 
 		err = ovl_mount_dir(iter, &l->path);
@@ -498,10 +499,10 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
 			goto out_put;
 
 		if (data_layer)
-			nr_data++;
+			ctx->nr_data++;
 
 		/* Calling strchr() again would overrun. */
-		if ((nr + 1) == nr_lower)
+		if (ctx->nr == nr_lower)
 			break;
 
 		err = -EINVAL;
@@ -511,7 +512,7 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
 			 * This is a regular layer so we require that
 			 * there are no data layers.
 			 */
-			if ((ctx->nr_data + nr_data) > 0) {
+			if (ctx->nr_data > 0) {
 				pr_err("regular lower layers cannot follow data lower layers");
 				goto out_put;
 			}
@@ -524,8 +525,6 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
 		data_layer = true;
 		iter++;
 	}
-	ctx->nr = nr_lower;
-	ctx->nr_data += nr_data;
 	kfree(dup);
 	return 0;
 
@@ -744,10 +743,8 @@ void ovl_free_fs(struct ovl_fs *ofs)
 	unsigned i;
 
 	iput(ofs->workbasedir_trap);
-	iput(ofs->indexdir_trap);
 	iput(ofs->workdir_trap);
 	dput(ofs->whiteout);
-	dput(ofs->indexdir);
 	dput(ofs->workdir);
 	if (ofs->workdir_locked)
 		ovl_inuse_unlock(ofs->workbasedir);
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index a490fc47c3e7..e71156baa7bc 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -1169,7 +1169,7 @@ int ovl_workdir_cleanup(struct ovl_fs *ofs, struct inode *dir,
 int ovl_indexdir_cleanup(struct ovl_fs *ofs)
 {
 	int err;
-	struct dentry *indexdir = ofs->indexdir;
+	struct dentry *indexdir = ofs->workdir;
 	struct dentry *index = NULL;
 	struct inode *dir = indexdir->d_inode;
 	struct path path = { .mnt = ovl_upper_mnt(ofs), .dentry = indexdir };
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index a0967bb25003..0bbbe4818f67 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -853,10 +853,8 @@ static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs,
 	if (IS_ERR(indexdir)) {
 		err = PTR_ERR(indexdir);
 	} else if (indexdir) {
-		ofs->indexdir = indexdir;
-		ofs->workdir = dget(indexdir);
-
-		err = ovl_setup_trap(sb, ofs->indexdir, &ofs->indexdir_trap,
+		ofs->workdir = indexdir;
+		err = ovl_setup_trap(sb, indexdir, &ofs->workdir_trap,
 				     "indexdir");
 		if (err)
 			goto out;
@@ -869,16 +867,15 @@ static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs,
 		 * ".overlay.upper" to indicate that index may have
 		 * directory entries.
 		 */
-		if (ovl_check_origin_xattr(ofs, ofs->indexdir)) {
-			err = ovl_verify_origin_xattr(ofs, ofs->indexdir,
+		if (ovl_check_origin_xattr(ofs, indexdir)) {
+			err = ovl_verify_origin_xattr(ofs, indexdir,
 						      OVL_XATTR_ORIGIN,
 						      upperpath->dentry, true,
 						      false);
 			if (err)
 				pr_err("failed to verify index dir 'origin' xattr\n");
 		}
-		err = ovl_verify_upper(ofs, ofs->indexdir, upperpath->dentry,
-				       true);
+		err = ovl_verify_upper(ofs, indexdir, upperpath->dentry, true);
 		if (err)
 			pr_err("failed to verify index dir 'upper' xattr\n");
 
@@ -886,7 +883,7 @@ static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs,
 		if (!err)
 			err = ovl_indexdir_cleanup(ofs);
 	}
-	if (err || !ofs->indexdir)
+	if (err || !indexdir)
 		pr_warn("try deleting index dir or mounting with '-o index=off' to disable inodes index.\n");
 
 out:
@@ -1406,7 +1403,7 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc)
 			goto out_free_oe;
 
 		/* Force r/o mount with no index dir */
-		if (!ofs->indexdir)
+		if (!ofs->workdir)
 			sb->s_flags |= SB_RDONLY;
 	}
 
@@ -1415,7 +1412,7 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc)
 		goto out_free_oe;
 
 	/* Show index=off in /proc/mounts for forced r/o mount */
-	if (!ofs->indexdir) {
+	if (!ofs->workdir) {
 		ofs->config.index = false;
 		if (ovl_upper_mnt(ofs) && ofs->config.nfs_export) {
 			pr_warn("NFS export requires an index dir, falling back to nfs_export=off.\n");
@@ -1454,6 +1451,7 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc)
 	 * lead to unexpected results.
 	 */
 	sb->s_iflags |= SB_I_NOUMASK;
+	sb->s_iflags |= SB_I_EVM_UNSUPPORTED;
 
 	err = -ENOMEM;
 	root_dentry = ovl_get_root(sb, ctx->upper.dentry, oe);
@@ -1501,14 +1499,10 @@ static int __init ovl_init(void)
 	if (ovl_inode_cachep == NULL)
 		return -ENOMEM;
 
-	err = ovl_aio_request_cache_init();
-	if (!err) {
-		err = register_filesystem(&ovl_fs_type);
-		if (!err)
-			return 0;
+	err = register_filesystem(&ovl_fs_type);
+	if (!err)
+		return 0;
 
-		ovl_aio_request_cache_destroy();
-	}
 	kmem_cache_destroy(ovl_inode_cachep);
 
 	return err;
@@ -1524,7 +1518,6 @@ static void __exit ovl_exit(void)
 	 */
 	rcu_barrier();
 	kmem_cache_destroy(ovl_inode_cachep);
-	ovl_aio_request_cache_destroy();
 }
 
 module_init(ovl_init);
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 50a201e9cd39..22b519763267 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -91,7 +91,7 @@ struct dentry *ovl_indexdir(struct super_block *sb)
 {
 	struct ovl_fs *ofs = OVL_FS(sb);
 
-	return ofs->indexdir;
+	return ofs->config.index ? ofs->workdir : NULL;
 }
 
 /* Index all files on copy up. For now only enabled for NFS export */
@@ -978,7 +978,7 @@ int ovl_set_protattr(struct inode *inode, struct dentry *upper,
 	return 0;
 }
 
-/**
+/*
  * Caller must hold a reference to inode to prevent it from being freed while
  * it is marked inuse.
  */
diff --git a/fs/pipe.c b/fs/pipe.c
index 804a7d789452..f1adbfe743d4 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -446,6 +446,18 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
 	bool was_empty = false;
 	bool wake_next_writer = false;
 
+	/*
+	 * Reject writing to watch queue pipes before the point where we lock
+	 * the pipe.
+	 * Otherwise, lockdep would be unhappy if the caller already has another
+	 * pipe locked.
+	 * If we had to support locking a normal pipe and a notification pipe at
+	 * the same time, we could set up lockdep annotations for that, but
+	 * since we don't actually need that, it's simpler to just bail here.
+	 */
+	if (pipe_has_watch_queue(pipe))
+		return -EXDEV;
+
 	/* Null write succeeds. */
 	if (unlikely(total_len == 0))
 		return 0;
@@ -458,11 +470,6 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
 		goto out;
 	}
 
-	if (pipe_has_watch_queue(pipe)) {
-		ret = -EXDEV;
-		goto out;
-	}
-
 	/*
 	 * If it wasn't empty we try to merge new data into
 	 * the last buffer.
@@ -1317,6 +1324,11 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots)
 	pipe->tail = tail;
 	pipe->head = head;
 
+	if (!pipe_has_watch_queue(pipe)) {
+		pipe->max_usage = nr_slots;
+		pipe->nr_accounted = nr_slots;
+	}
+
 	spin_unlock_irq(&pipe->rd_wait.lock);
 
 	/* This might have made more room for writers */
@@ -1368,8 +1380,6 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned int arg)
 	if (ret < 0)
 		goto out_revert_acct;
 
-	pipe->max_usage = nr_slots;
-	pipe->nr_accounted = nr_slots;
 	return pipe->max_usage * PAGE_SIZE;
 
 out_revert_acct:
@@ -1497,7 +1507,6 @@ static struct ctl_table fs_pipe_sysctls[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_doulongvec_minmax,
 	},
-	{ }
 };
 #endif
 
diff --git a/fs/pnode.c b/fs/pnode.c
index e4d0340393d5..a799e0315cc9 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -468,7 +468,7 @@ static void umount_one(struct mount *mnt, struct list_head *to_umount)
 	mnt->mnt.mnt_flags |= MNT_UMOUNT;
 	list_del_init(&mnt->mnt_child);
 	list_del_init(&mnt->mnt_umounting);
-	list_move_tail(&mnt->mnt_list, to_umount);
+	move_from_ns(mnt, to_umount);
 }
 
 /*
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index a05fe94970ce..e1af20893ebe 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -600,7 +600,7 @@ EXPORT_SYMBOL(__posix_acl_chmod);
  * the vfsmount must be passed through @idmap. This function will then
  * take care to map the inode according to @idmap before checking
  * permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs @nop_mnt_idmap.
+ * performed on the raw inode simply pass @nop_mnt_idmap.
  */
 int
  posix_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry,
@@ -700,7 +700,7 @@ EXPORT_SYMBOL_GPL(posix_acl_create);
  * the vfsmount must be passed through @idmap. This function will then
  * take care to map the inode according to @idmap before checking
  * permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs @nop_mnt_idmap.
+ * performed on the raw inode simply pass @nop_mnt_idmap.
  *
  * Called from set_acl inode operations.
  */
diff --git a/fs/proc/base.c b/fs/proc/base.c
index dd31e3b6bf77..98a031ac2648 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -97,6 +97,7 @@
 #include <linux/resctrl.h>
 #include <linux/cn_proc.h>
 #include <linux/ksm.h>
+#include <uapi/linux/lsm.h>
 #include <trace/events/oom.h>
 #include "internal.h"
 #include "fd.h"
@@ -146,10 +147,10 @@ struct pid_entry {
 	NOD(NAME, (S_IFREG|(MODE)),			\
 		NULL, &proc_single_file_operations,	\
 		{ .proc_show = show } )
-#define ATTR(LSM, NAME, MODE)				\
+#define ATTR(LSMID, NAME, MODE)				\
 	NOD(NAME, (S_IFREG|(MODE)),			\
 		NULL, &proc_pid_attr_operations,	\
-		{ .lsm = LSM })
+		{ .lsmid = LSMID })
 
 /*
  * Count the number of hardlinks for the pid_entry table, excluding the .
@@ -2726,7 +2727,7 @@ static ssize_t proc_pid_attr_read(struct file * file, char __user * buf,
 	if (!task)
 		return -ESRCH;
 
-	length = security_getprocattr(task, PROC_I(inode)->op.lsm,
+	length = security_getprocattr(task, PROC_I(inode)->op.lsmid,
 				      file->f_path.dentry->d_name.name,
 				      &p);
 	put_task_struct(task);
@@ -2784,7 +2785,7 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
 	if (rv < 0)
 		goto out_free;
 
-	rv = security_setprocattr(PROC_I(inode)->op.lsm,
+	rv = security_setprocattr(PROC_I(inode)->op.lsmid,
 				  file->f_path.dentry->d_name.name, page,
 				  count);
 	mutex_unlock(&current->signal->cred_guard_mutex);
@@ -2833,27 +2834,27 @@ static const struct inode_operations proc_##LSM##_attr_dir_inode_ops = { \
 
 #ifdef CONFIG_SECURITY_SMACK
 static const struct pid_entry smack_attr_dir_stuff[] = {
-	ATTR("smack", "current",	0666),
+	ATTR(LSM_ID_SMACK, "current",	0666),
 };
 LSM_DIR_OPS(smack);
 #endif
 
 #ifdef CONFIG_SECURITY_APPARMOR
 static const struct pid_entry apparmor_attr_dir_stuff[] = {
-	ATTR("apparmor", "current",	0666),
-	ATTR("apparmor", "prev",	0444),
-	ATTR("apparmor", "exec",	0666),
+	ATTR(LSM_ID_APPARMOR, "current",	0666),
+	ATTR(LSM_ID_APPARMOR, "prev",		0444),
+	ATTR(LSM_ID_APPARMOR, "exec",		0666),
 };
 LSM_DIR_OPS(apparmor);
 #endif
 
 static const struct pid_entry attr_dir_stuff[] = {
-	ATTR(NULL, "current",		0666),
-	ATTR(NULL, "prev",		0444),
-	ATTR(NULL, "exec",		0666),
-	ATTR(NULL, "fscreate",		0666),
-	ATTR(NULL, "keycreate",		0666),
-	ATTR(NULL, "sockcreate",	0666),
+	ATTR(LSM_ID_UNDEF, "current",	0666),
+	ATTR(LSM_ID_UNDEF, "prev",		0444),
+	ATTR(LSM_ID_UNDEF, "exec",		0666),
+	ATTR(LSM_ID_UNDEF, "fscreate",	0666),
+	ATTR(LSM_ID_UNDEF, "keycreate",	0666),
+	ATTR(LSM_ID_UNDEF, "sockcreate",	0666),
 #ifdef CONFIG_SECURITY_SMACK
 	DIR("smack",			0555,
 	    proc_smack_attr_dir_inode_ops, proc_smack_attr_dir_ops),
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 9a8f32f21ff5..a71ac5379584 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -92,7 +92,7 @@ union proc_op {
 	int (*proc_show)(struct seq_file *m,
 		struct pid_namespace *ns, struct pid *pid,
 		struct task_struct *task);
-	const char *lsm;
+	int lsmid;
 };
 
 struct proc_inode {
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 8064ea76f80b..7e16ce3ccbae 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -44,7 +44,7 @@ static struct ctl_table sysctl_mount_point[] = {
  */
 struct ctl_table_header *register_sysctl_mount_point(const char *path)
 {
-	return register_sysctl_sz(path, sysctl_mount_point, 0);
+	return register_sysctl(path, sysctl_mount_point);
 }
 EXPORT_SYMBOL(register_sysctl_mount_point);
 
@@ -71,7 +71,6 @@ static struct ctl_table root_table[] = {
 		.procname = "",
 		.mode = S_IFDIR|S_IRUGO|S_IXUGO,
 	},
-	{ }
 };
 static struct ctl_table_root sysctl_table_root = {
 	.default_set.dir.header = {
@@ -233,7 +232,8 @@ static int insert_header(struct ctl_dir *dir, struct ctl_table_header *header)
 		return -EROFS;
 
 	/* Am I creating a permanently empty directory? */
-	if (sysctl_is_perm_empty_ctl_table(header->ctl_table)) {
+	if (header->ctl_table_size > 0 &&
+	    sysctl_is_perm_empty_ctl_table(header->ctl_table)) {
 		if (!RB_EMPTY_ROOT(&dir->root))
 			return -EINVAL;
 		sysctl_set_perm_empty_ctl_header(dir_h);
@@ -1213,6 +1213,10 @@ static bool get_links(struct ctl_dir *dir,
 	struct ctl_table_header *tmp_head;
 	struct ctl_table *entry, *link;
 
+	if (header->ctl_table_size == 0 ||
+	    sysctl_is_perm_empty_ctl_table(header->ctl_table))
+		return true;
+
 	/* Are there links available for every entry in table? */
 	list_for_each_table_entry(entry, header) {
 		const char *procname = entry->procname;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index ef2eb12906da..62b16f42d5d2 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -273,7 +273,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
 	const char *name = NULL;
 
 	if (file) {
-		struct inode *inode = file_inode(vma->vm_file);
+		const struct inode *inode = file_user_inode(vma->vm_file);
+
 		dev = inode->i_sb->s_dev;
 		ino = inode->i_ino;
 		pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT;
@@ -865,7 +866,8 @@ static int show_smap(struct seq_file *m, void *v)
 	__show_smap(m, &mss, false);
 
 	seq_printf(m, "THPeligible:    %8u\n",
-		   hugepage_vma_check(vma, vma->vm_flags, true, false, true));
+		   !!thp_vma_allowable_orders(vma, vma->vm_flags, true, false,
+					      true, THP_ORDERS_ALL));
 
 	if (arch_pkeys_enabled())
 		seq_printf(m, "ProtectionKey:  %8u\n", vma_pkey(vma));
@@ -1761,7 +1763,7 @@ static int pagemap_release(struct inode *inode, struct file *file)
 #define PM_SCAN_CATEGORIES	(PAGE_IS_WPALLOWED | PAGE_IS_WRITTEN |	\
 				 PAGE_IS_FILE |	PAGE_IS_PRESENT |	\
 				 PAGE_IS_SWAPPED | PAGE_IS_PFNZERO |	\
-				 PAGE_IS_HUGE)
+				 PAGE_IS_HUGE | PAGE_IS_SOFT_DIRTY)
 #define PM_SCAN_FLAGS		(PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC)
 
 struct pagemap_scan_private {
@@ -1793,6 +1795,8 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p,
 
 		if (is_zero_pfn(pte_pfn(pte)))
 			categories |= PAGE_IS_PFNZERO;
+		if (pte_soft_dirty(pte))
+			categories |= PAGE_IS_SOFT_DIRTY;
 	} else if (is_swap_pte(pte)) {
 		swp_entry_t swp;
 
@@ -1806,6 +1810,8 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p,
 			    !PageAnon(pfn_swap_entry_to_page(swp)))
 				categories |= PAGE_IS_FILE;
 		}
+		if (pte_swp_soft_dirty(pte))
+			categories |= PAGE_IS_SOFT_DIRTY;
 	}
 
 	return categories;
@@ -1853,12 +1859,16 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p,
 
 		if (is_zero_pfn(pmd_pfn(pmd)))
 			categories |= PAGE_IS_PFNZERO;
+		if (pmd_soft_dirty(pmd))
+			categories |= PAGE_IS_SOFT_DIRTY;
 	} else if (is_swap_pmd(pmd)) {
 		swp_entry_t swp;
 
 		categories |= PAGE_IS_SWAPPED;
 		if (!pmd_swp_uffd_wp(pmd))
 			categories |= PAGE_IS_WRITTEN;
+		if (pmd_swp_soft_dirty(pmd))
+			categories |= PAGE_IS_SOFT_DIRTY;
 
 		if (p->masks_of_interest & PAGE_IS_FILE) {
 			swp = pmd_to_swp_entry(pmd);
@@ -1905,10 +1915,14 @@ static unsigned long pagemap_hugetlb_category(pte_t pte)
 			categories |= PAGE_IS_FILE;
 		if (is_zero_pfn(pte_pfn(pte)))
 			categories |= PAGE_IS_PFNZERO;
+		if (pte_soft_dirty(pte))
+			categories |= PAGE_IS_SOFT_DIRTY;
 	} else if (is_swap_pte(pte)) {
 		categories |= PAGE_IS_SWAPPED;
 		if (!pte_swp_uffd_wp_any(pte))
 			categories |= PAGE_IS_WRITTEN;
+		if (pte_swp_soft_dirty(pte))
+			categories |= PAGE_IS_SOFT_DIRTY;
 	}
 
 	return categories;
@@ -1982,15 +1996,34 @@ static int pagemap_scan_test_walk(unsigned long start, unsigned long end,
 	struct pagemap_scan_private *p = walk->private;
 	struct vm_area_struct *vma = walk->vma;
 	unsigned long vma_category = 0;
+	bool wp_allowed = userfaultfd_wp_async(vma) &&
+	    userfaultfd_wp_use_markers(vma);
 
-	if (userfaultfd_wp_async(vma) && userfaultfd_wp_use_markers(vma))
-		vma_category |= PAGE_IS_WPALLOWED;
-	else if (p->arg.flags & PM_SCAN_CHECK_WPASYNC)
-		return -EPERM;
+	if (!wp_allowed) {
+		/* User requested explicit failure over wp-async capability */
+		if (p->arg.flags & PM_SCAN_CHECK_WPASYNC)
+			return -EPERM;
+		/*
+		 * User requires wr-protect, and allows silently skipping
+		 * unsupported vmas.
+		 */
+		if (p->arg.flags & PM_SCAN_WP_MATCHING)
+			return 1;
+		/*
+		 * Then the request doesn't involve wr-protects at all,
+		 * fall through to the rest checks, and allow vma walk.
+		 */
+	}
 
 	if (vma->vm_flags & VM_PFNMAP)
 		return 1;
 
+	if (wp_allowed)
+		vma_category |= PAGE_IS_WPALLOWED;
+
+	if (vma->vm_flags & VM_SOFTDIRTY)
+		vma_category |= PAGE_IS_SOFT_DIRTY;
+
 	if (!pagemap_scan_is_interesting_vma(vma_category, p))
 		return 1;
 
@@ -2140,7 +2173,7 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start,
 		return 0;
 	}
 
-	if (!p->vec_out) {
+	if ((p->arg.flags & PM_SCAN_WP_MATCHING) && !p->vec_out) {
 		/* Fast path for performing exclusive WP */
 		for (addr = start; addr != end; pte++, addr += PAGE_SIZE) {
 			if (pte_uffd_wp(ptep_get(pte)))
diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c
index 250eb5bf7b52..0a808951b7d3 100644
--- a/fs/proc_namespace.c
+++ b/fs/proc_namespace.c
@@ -142,13 +142,9 @@ static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt)
 
 	seq_printf(m, "%i %i %u:%u ", r->mnt_id, r->mnt_parent->mnt_id,
 		   MAJOR(sb->s_dev), MINOR(sb->s_dev));
-	if (sb->s_op->show_path) {
-		err = sb->s_op->show_path(m, mnt->mnt_root);
-		if (err)
-			goto out;
-	} else {
-		seq_dentry(m, mnt->mnt_root, " \t\n\\");
-	}
+	err = show_path(m, mnt->mnt_root);
+	if (err)
+		goto out;
 	seq_putc(m, ' ');
 
 	/* mountpoints outside of chroot jail will give SEQ_SKIP on this */
@@ -283,8 +279,6 @@ static int mounts_open_common(struct inode *inode, struct file *file,
 	p->ns = ns;
 	p->root = root;
 	p->show = show;
-	INIT_LIST_HEAD(&p->cursor.mnt_list);
-	p->cursor.mnt.mnt_flags = MNT_CURSOR;
 
 	return 0;
 
@@ -301,7 +295,6 @@ static int mounts_release(struct inode *inode, struct file *file)
 	struct seq_file *m = file->private_data;
 	struct proc_mounts *p = m->private;
 	path_put(&p->root);
-	mnt_cursor_del(p->ns, &p->cursor);
 	put_mnt_ns(p->ns);
 	return seq_release_private(inode, file);
 }
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index d41c20d1b5e8..d0d9bfdad30c 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -23,6 +23,7 @@
 #include <linux/pstore.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/cleanup.h>
 
 #include "internal.h"
 
@@ -34,6 +35,8 @@ static LIST_HEAD(records_list);
 static DEFINE_MUTEX(pstore_sb_lock);
 static struct super_block *pstore_sb;
 
+DEFINE_FREE(pstore_iput, struct inode *, if (_T) iput(_T))
+
 struct pstore_private {
 	struct list_head list;
 	struct dentry *dentry;
@@ -60,11 +63,12 @@ static void free_pstore_private(struct pstore_private *private)
 	}
 	kfree(private);
 }
+DEFINE_FREE(pstore_private, struct pstore_private *, free_pstore_private(_T));
 
 static void *pstore_ftrace_seq_start(struct seq_file *s, loff_t *pos)
 {
 	struct pstore_private *ps = s->private;
-	struct pstore_ftrace_seq_data *data;
+	struct pstore_ftrace_seq_data *data __free(kfree) = NULL;
 
 	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
@@ -72,13 +76,10 @@ static void *pstore_ftrace_seq_start(struct seq_file *s, loff_t *pos)
 
 	data->off = ps->total_size % REC_SIZE;
 	data->off += *pos * REC_SIZE;
-	if (data->off + REC_SIZE > ps->total_size) {
-		kfree(data);
+	if (data->off + REC_SIZE > ps->total_size)
 		return NULL;
-	}
-
-	return data;
 
+	return_ptr(data);
 }
 
 static void pstore_ftrace_seq_stop(struct seq_file *s, void *v)
@@ -182,25 +183,21 @@ static int pstore_unlink(struct inode *dir, struct dentry *dentry)
 {
 	struct pstore_private *p = d_inode(dentry)->i_private;
 	struct pstore_record *record = p->record;
-	int rc = 0;
 
 	if (!record->psi->erase)
 		return -EPERM;
 
 	/* Make sure we can't race while removing this file. */
-	mutex_lock(&records_list_lock);
-	if (!list_empty(&p->list))
-		list_del_init(&p->list);
-	else
-		rc = -ENOENT;
-	p->dentry = NULL;
-	mutex_unlock(&records_list_lock);
-	if (rc)
-		return rc;
-
-	mutex_lock(&record->psi->read_mutex);
-	record->psi->erase(record);
-	mutex_unlock(&record->psi->read_mutex);
+	scoped_guard(mutex, &records_list_lock) {
+		if (!list_empty(&p->list))
+			list_del_init(&p->list);
+		else
+			return -ENOENT;
+		p->dentry = NULL;
+	}
+
+	scoped_guard(mutex, &record->psi->read_mutex)
+		record->psi->erase(record);
 
 	return simple_unlink(dir, dentry);
 }
@@ -292,19 +289,16 @@ static struct dentry *psinfo_lock_root(void)
 {
 	struct dentry *root;
 
-	mutex_lock(&pstore_sb_lock);
+	guard(mutex)(&pstore_sb_lock);
 	/*
 	 * Having no backend is fine -- no records appear.
 	 * Not being mounted is fine -- nothing to do.
 	 */
-	if (!psinfo || !pstore_sb) {
-		mutex_unlock(&pstore_sb_lock);
+	if (!psinfo || !pstore_sb)
 		return NULL;
-	}
 
 	root = pstore_sb->s_root;
 	inode_lock(d_inode(root));
-	mutex_unlock(&pstore_sb_lock);
 
 	return root;
 }
@@ -319,19 +313,19 @@ int pstore_put_backend_records(struct pstore_info *psi)
 	if (!root)
 		return 0;
 
-	mutex_lock(&records_list_lock);
-	list_for_each_entry_safe(pos, tmp, &records_list, list) {
-		if (pos->record->psi == psi) {
-			list_del_init(&pos->list);
-			rc = simple_unlink(d_inode(root), pos->dentry);
-			if (WARN_ON(rc))
-				break;
-			d_drop(pos->dentry);
-			dput(pos->dentry);
-			pos->dentry = NULL;
+	scoped_guard(mutex, &records_list_lock) {
+		list_for_each_entry_safe(pos, tmp, &records_list, list) {
+			if (pos->record->psi == psi) {
+				list_del_init(&pos->list);
+				rc = simple_unlink(d_inode(root), pos->dentry);
+				if (WARN_ON(rc))
+					break;
+				d_drop(pos->dentry);
+				dput(pos->dentry);
+				pos->dentry = NULL;
+			}
 		}
 	}
-	mutex_unlock(&records_list_lock);
 
 	inode_unlock(d_inode(root));
 
@@ -346,29 +340,27 @@ int pstore_put_backend_records(struct pstore_info *psi)
 int pstore_mkfile(struct dentry *root, struct pstore_record *record)
 {
 	struct dentry		*dentry;
-	struct inode		*inode;
-	int			rc = 0;
+	struct inode		*inode __free(pstore_iput) = NULL;
 	char			name[PSTORE_NAMELEN];
-	struct pstore_private	*private, *pos;
+	struct pstore_private	*private __free(pstore_private) = NULL, *pos;
 	size_t			size = record->size + record->ecc_notice_size;
 
 	if (WARN_ON(!inode_is_locked(d_inode(root))))
 		return -EINVAL;
 
-	rc = -EEXIST;
+	guard(mutex)(&records_list_lock);
+
 	/* Skip records that are already present in the filesystem. */
-	mutex_lock(&records_list_lock);
 	list_for_each_entry(pos, &records_list, list) {
 		if (pos->record->type == record->type &&
 		    pos->record->id == record->id &&
 		    pos->record->psi == record->psi)
-			goto fail;
+			return -EEXIST;
 	}
 
-	rc = -ENOMEM;
 	inode = pstore_get_inode(root->d_sb);
 	if (!inode)
-		goto fail;
+		return -ENOMEM;
 	inode->i_mode = S_IFREG | 0444;
 	inode->i_fop = &pstore_file_operations;
 	scnprintf(name, sizeof(name), "%s-%s-%llu%s",
@@ -378,11 +370,11 @@ int pstore_mkfile(struct dentry *root, struct pstore_record *record)
 
 	private = kzalloc(sizeof(*private), GFP_KERNEL);
 	if (!private)
-		goto fail_inode;
+		return -ENOMEM;
 
 	dentry = d_alloc_name(root, name);
 	if (!dentry)
-		goto fail_private;
+		return -ENOMEM;
 
 	private->dentry = dentry;
 	private->record = record;
@@ -393,20 +385,11 @@ int pstore_mkfile(struct dentry *root, struct pstore_record *record)
 		inode_set_mtime_to_ts(inode,
 				      inode_set_ctime_to_ts(inode, record->time));
 
-	d_add(dentry, inode);
+	d_add(dentry, no_free_ptr(inode));
 
-	list_add(&private->list, &records_list);
-	mutex_unlock(&records_list_lock);
+	list_add(&(no_free_ptr(private))->list, &records_list);
 
 	return 0;
-
-fail_private:
-	free_pstore_private(private);
-fail_inode:
-	iput(inode);
-fail:
-	mutex_unlock(&records_list_lock);
-	return rc;
 }
 
 /*
@@ -451,9 +434,8 @@ static int pstore_fill_super(struct super_block *sb, void *data, int silent)
 	if (!sb->s_root)
 		return -ENOMEM;
 
-	mutex_lock(&pstore_sb_lock);
-	pstore_sb = sb;
-	mutex_unlock(&pstore_sb_lock);
+	scoped_guard(mutex, &pstore_sb_lock)
+		pstore_sb = sb;
 
 	pstore_get_records(0);
 
@@ -468,17 +450,14 @@ static struct dentry *pstore_mount(struct file_system_type *fs_type,
 
 static void pstore_kill_sb(struct super_block *sb)
 {
-	mutex_lock(&pstore_sb_lock);
+	guard(mutex)(&pstore_sb_lock);
 	WARN_ON(pstore_sb && pstore_sb != sb);
 
 	kill_litter_super(sb);
 	pstore_sb = NULL;
 
-	mutex_lock(&records_list_lock);
+	guard(mutex)(&records_list_lock);
 	INIT_LIST_HEAD(&records_list);
-	mutex_unlock(&records_list_lock);
-
-	mutex_unlock(&pstore_sb_lock);
 }
 
 static struct file_system_type pstore_fs_type = {
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index d36702c7ab3c..88b34fdbf759 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -529,6 +529,7 @@ static int ramoops_init_przs(const char *name,
 	}
 
 	zone_sz = mem_sz / *cnt;
+	zone_sz = ALIGN_DOWN(zone_sz, 2);
 	if (!zone_sz) {
 		dev_err(dev, "%s zone size == 0\n", name);
 		goto fail;
diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c
index 650e437b55e6..f1848cdd6d34 100644
--- a/fs/pstore/ram_core.c
+++ b/fs/pstore/ram_core.c
@@ -190,7 +190,7 @@ static int persistent_ram_init_ecc(struct persistent_ram_zone *prz,
 {
 	int numerr;
 	struct persistent_ram_buffer *buffer = prz->buffer;
-	int ecc_blocks;
+	size_t ecc_blocks;
 	size_t ecc_total;
 
 	if (!ecc_info || !ecc_info->ecc_size)
diff --git a/fs/qnx4/dir.c b/fs/qnx4/dir.c
index 66645a5a35f3..42a529e26bd6 100644
--- a/fs/qnx4/dir.c
+++ b/fs/qnx4/dir.c
@@ -15,43 +15,6 @@
 #include <linux/buffer_head.h>
 #include "qnx4.h"
 
-/*
- * A qnx4 directory entry is an inode entry or link info
- * depending on the status field in the last byte. The
- * first byte is where the name start either way, and a
- * zero means it's empty.
- *
- * Also, due to a bug in gcc, we don't want to use the
- * real (differently sized) name arrays in the inode and
- * link entries, but always the 'de_name[]' one in the
- * fake struct entry.
- *
- * See
- *
- *   https://gcc.gnu.org/bugzilla/show_bug.cgi?id=99578#c6
- *
- * for details, but basically gcc will take the size of the
- * 'name' array from one of the used union entries randomly.
- *
- * This use of 'de_name[]' (48 bytes) avoids the false positive
- * warnings that would happen if gcc decides to use 'inode.di_name'
- * (16 bytes) even when the pointer and size were to come from
- * 'link.dl_name' (48 bytes).
- *
- * In all cases the actual name pointer itself is the same, it's
- * only the gcc internal 'what is the size of this field' logic
- * that can get confused.
- */
-union qnx4_directory_entry {
-	struct {
-		const char de_name[48];
-		u8 de_pad[15];
-		u8 de_status;
-	};
-	struct qnx4_inode_entry inode;
-	struct qnx4_link_info link;
-};
-
 static int qnx4_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct inode *inode = file_inode(file);
@@ -74,26 +37,25 @@ static int qnx4_readdir(struct file *file, struct dir_context *ctx)
 		ix = (ctx->pos >> QNX4_DIR_ENTRY_SIZE_BITS) % QNX4_INODES_PER_BLOCK;
 		for (; ix < QNX4_INODES_PER_BLOCK; ix++, ctx->pos += QNX4_DIR_ENTRY_SIZE) {
 			union qnx4_directory_entry *de;
+			const char *fname;
 
 			offset = ix * QNX4_DIR_ENTRY_SIZE;
 			de = (union qnx4_directory_entry *) (bh->b_data + offset);
 
-			if (!de->de_name[0])
-				continue;
-			if (!(de->de_status & (QNX4_FILE_USED|QNX4_FILE_LINK)))
+			fname = get_entry_fname(de, &size);
+			if (!fname)
 				continue;
+
 			if (!(de->de_status & QNX4_FILE_LINK)) {
-				size = sizeof(de->inode.di_fname);
 				ino = blknum * QNX4_INODES_PER_BLOCK + ix - 1;
 			} else {
-				size = sizeof(de->link.dl_fname);
 				ino = ( le32_to_cpu(de->link.dl_inode_blk) - 1 ) *
 					QNX4_INODES_PER_BLOCK +
 					de->link.dl_inode_ndx;
 			}
-			size = strnlen(de->de_name, size);
-			QNX4DEBUG((KERN_INFO "qnx4_readdir:%.*s\n", size, name));
-			if (!dir_emit(ctx, de->de_name, size, ino, DT_UNKNOWN)) {
+
+			QNX4DEBUG((KERN_INFO "qnx4_readdir:%.*s\n", size, fname));
+			if (!dir_emit(ctx, fname, size, ino, DT_UNKNOWN)) {
 				brelse(bh);
 				return 0;
 			}
diff --git a/fs/qnx4/namei.c b/fs/qnx4/namei.c
index 8d72221735d7..bb8db6550ca5 100644
--- a/fs/qnx4/namei.c
+++ b/fs/qnx4/namei.c
@@ -26,31 +26,24 @@
 static int qnx4_match(int len, const char *name,
 		      struct buffer_head *bh, unsigned long *offset)
 {
-	struct qnx4_inode_entry *de;
-	int namelen, thislen;
+	union qnx4_directory_entry *de;
+	const char *fname;
+	int fnamelen;
 
 	if (bh == NULL) {
 		printk(KERN_WARNING "qnx4: matching unassigned buffer !\n");
 		return 0;
 	}
-	de = (struct qnx4_inode_entry *) (bh->b_data + *offset);
+	de = (union qnx4_directory_entry *) (bh->b_data + *offset);
 	*offset += QNX4_DIR_ENTRY_SIZE;
-	if ((de->di_status & QNX4_FILE_LINK) != 0) {
-		namelen = QNX4_NAME_MAX;
-	} else {
-		namelen = QNX4_SHORT_NAME_MAX;
-	}
-	thislen = strlen( de->di_fname );
-	if ( thislen > namelen )
-		thislen = namelen;
-	if (len != thislen) {
+
+	fname = get_entry_fname(de, &fnamelen);
+	if (!fname || len != fnamelen)
 		return 0;
-	}
-	if (strncmp(name, de->di_fname, len) == 0) {
-		if ((de->di_status & (QNX4_FILE_USED|QNX4_FILE_LINK)) != 0) {
-			return 1;
-		}
-	}
+
+	if (strncmp(name, fname, len) == 0)
+		return 1;
+
 	return 0;
 }
 
diff --git a/fs/qnx4/qnx4.h b/fs/qnx4/qnx4.h
index 6283705466a4..5c2b1fb6b952 100644
--- a/fs/qnx4/qnx4.h
+++ b/fs/qnx4/qnx4.h
@@ -44,3 +44,63 @@ static inline struct qnx4_inode_entry *qnx4_raw_inode(struct inode *inode)
 {
 	return &qnx4_i(inode)->raw;
 }
+
+/*
+ * A qnx4 directory entry is an inode entry or link info
+ * depending on the status field in the last byte. The
+ * first byte is where the name start either way, and a
+ * zero means it's empty.
+ *
+ * Also, due to a bug in gcc, we don't want to use the
+ * real (differently sized) name arrays in the inode and
+ * link entries, but always the 'de_name[]' one in the
+ * fake struct entry.
+ *
+ * See
+ *
+ *   https://gcc.gnu.org/bugzilla/show_bug.cgi?id=99578#c6
+ *
+ * for details, but basically gcc will take the size of the
+ * 'name' array from one of the used union entries randomly.
+ *
+ * This use of 'de_name[]' (48 bytes) avoids the false positive
+ * warnings that would happen if gcc decides to use 'inode.di_name'
+ * (16 bytes) even when the pointer and size were to come from
+ * 'link.dl_name' (48 bytes).
+ *
+ * In all cases the actual name pointer itself is the same, it's
+ * only the gcc internal 'what is the size of this field' logic
+ * that can get confused.
+ */
+union qnx4_directory_entry {
+	struct {
+		const char de_name[48];
+		u8 de_pad[15];
+		u8 de_status;
+	};
+	struct qnx4_inode_entry inode;
+	struct qnx4_link_info link;
+};
+
+static inline const char *get_entry_fname(union qnx4_directory_entry *de,
+					  int *size)
+{
+	/* Make sure the status byte is in the same place for all structs. */
+	BUILD_BUG_ON(offsetof(struct qnx4_inode_entry, di_status) !=
+			offsetof(struct qnx4_link_info, dl_status));
+	BUILD_BUG_ON(offsetof(struct qnx4_inode_entry, di_status) !=
+			offsetof(union qnx4_directory_entry, de_status));
+
+	if (!de->de_name[0])
+		return NULL;
+	if (!(de->de_status & (QNX4_FILE_USED|QNX4_FILE_LINK)))
+		return NULL;
+	if (!(de->de_status & QNX4_FILE_LINK))
+		*size = sizeof(de->inode.di_fname);
+	else
+		*size = sizeof(de->link.dl_fname);
+
+	*size = strnlen(de->de_name, *size);
+
+	return de->de_name;
+}
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 58b5de081b57..1f0c754416b6 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -1787,7 +1787,7 @@ EXPORT_SYMBOL(dquot_alloc_inode);
 /*
  * Convert in-memory reserved quotas to real consumed quotas
  */
-int dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
+void dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
 {
 	struct dquot **dquots;
 	int cnt, index;
@@ -1797,7 +1797,7 @@ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
 		*inode_reserved_space(inode) -= number;
 		__inode_add_bytes(inode, number);
 		spin_unlock(&inode->i_lock);
-		return 0;
+		return;
 	}
 
 	dquots = i_dquot(inode);
@@ -1822,7 +1822,7 @@ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
 	spin_unlock(&inode->i_lock);
 	mark_all_dquot_dirty(dquots);
 	srcu_read_unlock(&dquot_srcu, index);
-	return 0;
+	return;
 }
 EXPORT_SYMBOL(dquot_claim_space_nodirty);
 
@@ -2969,7 +2969,6 @@ static struct ctl_table fs_dqstats_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
-	{ },
 };
 
 static int __init dquot_init(void)
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index efb1b4c1a0a4..7a6d980e614d 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -70,7 +70,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize)
 
 	/* make various checks */
 	order = get_order(newsize);
-	if (unlikely(order > MAX_ORDER))
+	if (unlikely(order > MAX_PAGE_ORDER))
 		return -EFBIG;
 
 	ret = inode_newsize_ok(inode, newsize);
diff --git a/fs/read_write.c b/fs/read_write.c
index 4771701c896b..d4c036e82b6c 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -354,6 +354,9 @@ out_putf:
 
 int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count)
 {
+	int mask = read_write == READ ? MAY_READ : MAY_WRITE;
+	int ret;
+
 	if (unlikely((ssize_t) count < 0))
 		return -EINVAL;
 
@@ -371,8 +374,11 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t
 		}
 	}
 
-	return security_file_permission(file,
-				read_write == READ ? MAY_READ : MAY_WRITE);
+	ret = security_file_permission(file, mask);
+	if (ret)
+		return ret;
+
+	return fsnotify_file_area_perm(file, mask, ppos, count);
 }
 EXPORT_SYMBOL(rw_verify_area);
 
@@ -773,12 +779,14 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
 	return ret;
 }
 
-static ssize_t do_iter_read(struct file *file, struct iov_iter *iter,
-		loff_t *pos, rwf_t flags)
+ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb,
+			   struct iov_iter *iter)
 {
 	size_t tot_len;
 	ssize_t ret = 0;
 
+	if (!file->f_op->read_iter)
+		return -EINVAL;
 	if (!(file->f_mode & FMODE_READ))
 		return -EBADF;
 	if (!(file->f_mode & FMODE_CAN_READ))
@@ -787,22 +795,20 @@ static ssize_t do_iter_read(struct file *file, struct iov_iter *iter,
 	tot_len = iov_iter_count(iter);
 	if (!tot_len)
 		goto out;
-	ret = rw_verify_area(READ, file, pos, tot_len);
+	ret = rw_verify_area(READ, file, &iocb->ki_pos, tot_len);
 	if (ret < 0)
 		return ret;
 
-	if (file->f_op->read_iter)
-		ret = do_iter_readv_writev(file, iter, pos, READ, flags);
-	else
-		ret = do_loop_readv_writev(file, iter, pos, READ, flags);
+	ret = call_read_iter(file, iocb, iter);
 out:
 	if (ret >= 0)
 		fsnotify_access(file);
 	return ret;
 }
+EXPORT_SYMBOL(vfs_iocb_iter_read);
 
-ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb,
-			   struct iov_iter *iter)
+ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos,
+		      rwf_t flags)
 {
 	size_t tot_len;
 	ssize_t ret = 0;
@@ -817,33 +823,30 @@ ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb,
 	tot_len = iov_iter_count(iter);
 	if (!tot_len)
 		goto out;
-	ret = rw_verify_area(READ, file, &iocb->ki_pos, tot_len);
+	ret = rw_verify_area(READ, file, ppos, tot_len);
 	if (ret < 0)
 		return ret;
 
-	ret = call_read_iter(file, iocb, iter);
+	ret = do_iter_readv_writev(file, iter, ppos, READ, flags);
 out:
 	if (ret >= 0)
 		fsnotify_access(file);
 	return ret;
 }
-EXPORT_SYMBOL(vfs_iocb_iter_read);
-
-ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos,
-		rwf_t flags)
-{
-	if (!file->f_op->read_iter)
-		return -EINVAL;
-	return do_iter_read(file, iter, ppos, flags);
-}
 EXPORT_SYMBOL(vfs_iter_read);
 
-static ssize_t do_iter_write(struct file *file, struct iov_iter *iter,
-		loff_t *pos, rwf_t flags)
+/*
+ * Caller is responsible for calling kiocb_end_write() on completion
+ * if async iocb was queued.
+ */
+ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb,
+			    struct iov_iter *iter)
 {
 	size_t tot_len;
 	ssize_t ret = 0;
 
+	if (!file->f_op->write_iter)
+		return -EINVAL;
 	if (!(file->f_mode & FMODE_WRITE))
 		return -EBADF;
 	if (!(file->f_mode & FMODE_CAN_WRITE))
@@ -852,88 +855,127 @@ static ssize_t do_iter_write(struct file *file, struct iov_iter *iter,
 	tot_len = iov_iter_count(iter);
 	if (!tot_len)
 		return 0;
-	ret = rw_verify_area(WRITE, file, pos, tot_len);
+	ret = rw_verify_area(WRITE, file, &iocb->ki_pos, tot_len);
 	if (ret < 0)
 		return ret;
 
-	if (file->f_op->write_iter)
-		ret = do_iter_readv_writev(file, iter, pos, WRITE, flags);
-	else
-		ret = do_loop_readv_writev(file, iter, pos, WRITE, flags);
+	kiocb_start_write(iocb);
+	ret = call_write_iter(file, iocb, iter);
+	if (ret != -EIOCBQUEUED)
+		kiocb_end_write(iocb);
 	if (ret > 0)
 		fsnotify_modify(file);
+
 	return ret;
 }
+EXPORT_SYMBOL(vfs_iocb_iter_write);
 
-ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb,
-			    struct iov_iter *iter)
+ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
+		       rwf_t flags)
 {
 	size_t tot_len;
-	ssize_t ret = 0;
+	ssize_t ret;
 
-	if (!file->f_op->write_iter)
-		return -EINVAL;
 	if (!(file->f_mode & FMODE_WRITE))
 		return -EBADF;
 	if (!(file->f_mode & FMODE_CAN_WRITE))
 		return -EINVAL;
+	if (!file->f_op->write_iter)
+		return -EINVAL;
 
 	tot_len = iov_iter_count(iter);
 	if (!tot_len)
 		return 0;
-	ret = rw_verify_area(WRITE, file, &iocb->ki_pos, tot_len);
+
+	ret = rw_verify_area(WRITE, file, ppos, tot_len);
 	if (ret < 0)
 		return ret;
 
-	ret = call_write_iter(file, iocb, iter);
+	file_start_write(file);
+	ret = do_iter_readv_writev(file, iter, ppos, WRITE, flags);
 	if (ret > 0)
 		fsnotify_modify(file);
+	file_end_write(file);
 
 	return ret;
 }
-EXPORT_SYMBOL(vfs_iocb_iter_write);
-
-ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
-		rwf_t flags)
-{
-	if (!file->f_op->write_iter)
-		return -EINVAL;
-	return do_iter_write(file, iter, ppos, flags);
-}
 EXPORT_SYMBOL(vfs_iter_write);
 
 static ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
-		  unsigned long vlen, loff_t *pos, rwf_t flags)
+			 unsigned long vlen, loff_t *pos, rwf_t flags)
 {
 	struct iovec iovstack[UIO_FASTIOV];
 	struct iovec *iov = iovstack;
 	struct iov_iter iter;
-	ssize_t ret;
+	size_t tot_len;
+	ssize_t ret = 0;
 
-	ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
-	if (ret >= 0) {
-		ret = do_iter_read(file, &iter, pos, flags);
-		kfree(iov);
-	}
+	if (!(file->f_mode & FMODE_READ))
+		return -EBADF;
+	if (!(file->f_mode & FMODE_CAN_READ))
+		return -EINVAL;
+
+	ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov,
+			   &iter);
+	if (ret < 0)
+		return ret;
+
+	tot_len = iov_iter_count(&iter);
+	if (!tot_len)
+		goto out;
 
+	ret = rw_verify_area(READ, file, pos, tot_len);
+	if (ret < 0)
+		goto out;
+
+	if (file->f_op->read_iter)
+		ret = do_iter_readv_writev(file, &iter, pos, READ, flags);
+	else
+		ret = do_loop_readv_writev(file, &iter, pos, READ, flags);
+out:
+	if (ret >= 0)
+		fsnotify_access(file);
+	kfree(iov);
 	return ret;
 }
 
 static ssize_t vfs_writev(struct file *file, const struct iovec __user *vec,
-		   unsigned long vlen, loff_t *pos, rwf_t flags)
+			  unsigned long vlen, loff_t *pos, rwf_t flags)
 {
 	struct iovec iovstack[UIO_FASTIOV];
 	struct iovec *iov = iovstack;
 	struct iov_iter iter;
-	ssize_t ret;
+	size_t tot_len;
+	ssize_t ret = 0;
 
-	ret = import_iovec(ITER_SOURCE, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
-	if (ret >= 0) {
-		file_start_write(file);
-		ret = do_iter_write(file, &iter, pos, flags);
-		file_end_write(file);
-		kfree(iov);
-	}
+	if (!(file->f_mode & FMODE_WRITE))
+		return -EBADF;
+	if (!(file->f_mode & FMODE_CAN_WRITE))
+		return -EINVAL;
+
+	ret = import_iovec(ITER_SOURCE, vec, vlen, ARRAY_SIZE(iovstack), &iov,
+			   &iter);
+	if (ret < 0)
+		return ret;
+
+	tot_len = iov_iter_count(&iter);
+	if (!tot_len)
+		goto out;
+
+	ret = rw_verify_area(WRITE, file, pos, tot_len);
+	if (ret < 0)
+		goto out;
+
+	file_start_write(file);
+	if (file->f_op->write_iter)
+		ret = do_iter_readv_writev(file, &iter, pos, WRITE, flags);
+	else
+		ret = do_loop_readv_writev(file, &iter, pos, WRITE, flags);
+	if (ret > 0)
+		fsnotify_modify(file);
+	file_end_write(file);
+out:
+	kfree(iov);
 	return ret;
 }
 
@@ -1178,7 +1220,7 @@ COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd,
 #endif /* CONFIG_COMPAT */
 
 static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
-		  	   size_t count, loff_t max)
+			   size_t count, loff_t max)
 {
 	struct fd in, out;
 	struct inode *in_inode, *out_inode;
@@ -1250,10 +1292,8 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 		retval = rw_verify_area(WRITE, out.file, &out_pos, count);
 		if (retval < 0)
 			goto fput_out;
-		file_start_write(out.file);
 		retval = do_splice_direct(in.file, &pos, out.file, &out_pos,
 					  count, fl);
-		file_end_write(out.file);
 	} else {
 		if (out.file->f_flags & O_NONBLOCK)
 			fl |= SPLICE_F_NONBLOCK;
@@ -1362,38 +1402,6 @@ COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd,
 }
 #endif
 
-/**
- * generic_copy_file_range - copy data between two files
- * @file_in:	file structure to read from
- * @pos_in:	file offset to read from
- * @file_out:	file structure to write data to
- * @pos_out:	file offset to write data to
- * @len:	amount of data to copy
- * @flags:	copy flags
- *
- * This is a generic filesystem helper to copy data from one file to another.
- * It has no constraints on the source or destination file owners - the files
- * can belong to different superblocks and different filesystem types. Short
- * copies are allowed.
- *
- * This should be called from the @file_out filesystem, as per the
- * ->copy_file_range() method.
- *
- * Returns the number of bytes copied or a negative error indicating the
- * failure.
- */
-
-ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,
-				struct file *file_out, loff_t pos_out,
-				size_t len, unsigned int flags)
-{
-	lockdep_assert(sb_write_started(file_inode(file_out)->i_sb));
-
-	return do_splice_direct(file_in, &pos_in, file_out, &pos_out,
-				len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0);
-}
-EXPORT_SYMBOL(generic_copy_file_range);
-
 /*
  * Performs necessary checks before doing a file copy
  *
@@ -1478,6 +1486,7 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 {
 	ssize_t ret;
 	bool splice = flags & COPY_FILE_SPLICE;
+	bool samesb = file_inode(file_in)->i_sb == file_inode(file_out)->i_sb;
 
 	if (flags & ~COPY_FILE_SPLICE)
 		return -EINVAL;
@@ -1509,19 +1518,24 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 		ret = file_out->f_op->copy_file_range(file_in, pos_in,
 						      file_out, pos_out,
 						      len, flags);
-		goto done;
-	}
-
-	if (!splice && file_in->f_op->remap_file_range &&
-	    file_inode(file_in)->i_sb == file_inode(file_out)->i_sb) {
+	} else if (!splice && file_in->f_op->remap_file_range && samesb) {
 		ret = file_in->f_op->remap_file_range(file_in, pos_in,
 				file_out, pos_out,
 				min_t(loff_t, MAX_RW_COUNT, len),
 				REMAP_FILE_CAN_SHORTEN);
-		if (ret > 0)
-			goto done;
+		/* fallback to splice */
+		if (ret <= 0)
+			splice = true;
+	} else if (samesb) {
+		/* Fallback to splice for same sb copy for backward compat */
+		splice = true;
 	}
 
+	file_end_write(file_out);
+
+	if (!splice)
+		goto done;
+
 	/*
 	 * We can get here for same sb copy of filesystems that do not implement
 	 * ->copy_file_range() in case filesystem does not support clone or in
@@ -1533,11 +1547,16 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	 * and which filesystems do not, that will allow userspace tools to
 	 * make consistent desicions w.r.t using copy_file_range().
 	 *
-	 * We also get here if caller (e.g. nfsd) requested COPY_FILE_SPLICE.
+	 * We also get here if caller (e.g. nfsd) requested COPY_FILE_SPLICE
+	 * for server-side-copy between any two sb.
+	 *
+	 * In any case, we call do_splice_direct() and not splice_file_range(),
+	 * without file_start_write() held, to avoid possible deadlocks related
+	 * to splicing from input file, while file_start_write() is held on
+	 * the output file on a different sb.
 	 */
-	ret = generic_copy_file_range(file_in, pos_in, file_out, pos_out, len,
-				      flags);
-
+	ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out,
+			       min_t(size_t, len, MAX_RW_COUNT), 0);
 done:
 	if (ret > 0) {
 		fsnotify_access(file_in);
@@ -1549,8 +1568,6 @@ done:
 	inc_syscr(current);
 	inc_syscw(current);
 
-	file_end_write(file_out);
-
 	return ret;
 }
 EXPORT_SYMBOL(vfs_copy_file_range);
diff --git a/fs/readdir.c b/fs/readdir.c
index c8c46e294431..278bc0254732 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -96,6 +96,10 @@ int iterate_dir(struct file *file, struct dir_context *ctx)
 	if (res)
 		goto out;
 
+	res = fsnotify_file_perm(file, MAY_READ);
+	if (res)
+		goto out;
+
 	res = down_read_killable(&inode->i_rwsem);
 	if (res)
 		goto out;
diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c
index 2138ee7d271d..5faf702f8d15 100644
--- a/fs/reiserfs/stree.c
+++ b/fs/reiserfs/stree.c
@@ -1407,7 +1407,7 @@ void reiserfs_delete_solid_item(struct reiserfs_transaction_handle *th,
 	INITIALIZE_PATH(path);
 	int item_len = 0;
 	int tb_init = 0;
-	struct cpu_key cpu_key;
+	struct cpu_key cpu_key = {};
 	int retval;
 	int quota_cut_bytes = 0;
 
diff --git a/fs/remap_range.c b/fs/remap_range.c
index 87ae4f0dc3aa..f8c1120b8311 100644
--- a/fs/remap_range.c
+++ b/fs/remap_range.c
@@ -102,7 +102,9 @@ static int generic_remap_checks(struct file *file_in, loff_t pos_in,
 static int remap_verify_area(struct file *file, loff_t pos, loff_t len,
 			     bool write)
 {
+	int mask = write ? MAY_WRITE : MAY_READ;
 	loff_t tmp;
+	int ret;
 
 	if (unlikely(pos < 0 || len < 0))
 		return -EINVAL;
@@ -110,7 +112,11 @@ static int remap_verify_area(struct file *file, loff_t pos, loff_t len,
 	if (unlikely(check_add_overflow(pos, len, &tmp)))
 		return -EINVAL;
 
-	return security_file_permission(file, write ? MAY_WRITE : MAY_READ);
+	ret = security_file_permission(file, mask);
+	if (ret)
+		return ret;
+
+	return fsnotify_file_area_perm(file, mask, &pos, len);
 }
 
 /*
@@ -385,14 +391,6 @@ loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
 	if (!file_in->f_op->remap_file_range)
 		return -EOPNOTSUPP;
 
-	ret = remap_verify_area(file_in, pos_in, len, false);
-	if (ret)
-		return ret;
-
-	ret = remap_verify_area(file_out, pos_out, len, true);
-	if (ret)
-		return ret;
-
 	ret = file_in->f_op->remap_file_range(file_in, pos_in,
 			file_out, pos_out, len, remap_flags);
 	if (ret < 0)
@@ -410,6 +408,14 @@ loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
 {
 	loff_t ret;
 
+	ret = remap_verify_area(file_in, pos_in, len, false);
+	if (ret)
+		return ret;
+
+	ret = remap_verify_area(file_out, pos_out, len, true);
+	if (ret)
+		return ret;
+
 	file_start_write(file_out);
 	ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len,
 				  remap_flags);
@@ -420,7 +426,7 @@ loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
 EXPORT_SYMBOL(vfs_clone_file_range);
 
 /* Check whether we are allowed to dedupe the destination file */
-static bool allow_file_dedupe(struct file *file)
+static bool may_dedupe_file(struct file *file)
 {
 	struct mnt_idmap *idmap = file_mnt_idmap(file);
 	struct inode *inode = file_inode(file);
@@ -445,24 +451,29 @@ loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
 	WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP |
 				     REMAP_FILE_CAN_SHORTEN));
 
-	ret = mnt_want_write_file(dst_file);
-	if (ret)
-		return ret;
-
 	/*
 	 * This is redundant if called from vfs_dedupe_file_range(), but other
 	 * callers need it and it's not performance sesitive...
 	 */
 	ret = remap_verify_area(src_file, src_pos, len, false);
 	if (ret)
-		goto out_drop_write;
+		return ret;
 
 	ret = remap_verify_area(dst_file, dst_pos, len, true);
 	if (ret)
-		goto out_drop_write;
+		return ret;
+
+	/*
+	 * This needs to be called after remap_verify_area() because of
+	 * sb_start_write() and before may_dedupe_file() because the mount's
+	 * MAY_WRITE need to be checked with mnt_get_write_access_file() held.
+	 */
+	ret = mnt_want_write_file(dst_file);
+	if (ret)
+		return ret;
 
 	ret = -EPERM;
-	if (!allow_file_dedupe(dst_file))
+	if (!may_dedupe_file(dst_file))
 		goto out_drop_write;
 
 	ret = -EXDEV;
diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index 59f6b8e32cc9..d64a306a414b 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -291,16 +291,23 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
 	oparms.fid->mid = le64_to_cpu(o_rsp->hdr.MessageId);
 #endif /* CIFS_DEBUG2 */
 
-	rc = -EINVAL;
+
 	if (o_rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) {
 		spin_unlock(&cfids->cfid_list_lock);
+		rc = -EINVAL;
+		goto oshr_free;
+	}
+
+	rc = smb2_parse_contexts(server, rsp_iov,
+				 &oparms.fid->epoch,
+				 oparms.fid->lease_key,
+				 &oplock, NULL, NULL);
+	if (rc) {
+		spin_unlock(&cfids->cfid_list_lock);
 		goto oshr_free;
 	}
 
-	smb2_parse_contexts(server, o_rsp,
-			    &oparms.fid->epoch,
-			    oparms.fid->lease_key, &oplock,
-			    NULL, NULL);
+	rc = -EINVAL;
 	if (!(oplock & SMB2_LEASE_READ_CACHING_HE)) {
 		spin_unlock(&cfids->cfid_list_lock);
 		goto oshr_free;
diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c
index 5596c9f30ccb..60027f5aebe8 100644
--- a/fs/smb/client/cifs_debug.c
+++ b/fs/smb/client/cifs_debug.c
@@ -40,11 +40,13 @@ void cifs_dump_detail(void *buf, struct TCP_Server_Info *server)
 #ifdef CONFIG_CIFS_DEBUG2
 	struct smb_hdr *smb = buf;
 
-	cifs_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Flgs2: 0x%x Mid: %d Pid: %d\n",
-		 smb->Command, smb->Status.CifsError,
-		 smb->Flags, smb->Flags2, smb->Mid, smb->Pid);
-	cifs_dbg(VFS, "smb buf %p len %u\n", smb,
-		 server->ops->calc_smb_size(smb));
+	cifs_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Flgs2: 0x%x Mid: %d Pid: %d Wct: %d\n",
+		 smb->Command, smb->Status.CifsError, smb->Flags,
+		 smb->Flags2, smb->Mid, smb->Pid, smb->WordCount);
+	if (!server->ops->check_message(buf, server->total_read, server)) {
+		cifs_dbg(VFS, "smb buf %p len %u\n", smb,
+			 server->ops->calc_smb_size(smb));
+	}
 #endif /* CONFIG_CIFS_DEBUG2 */
 }
 
diff --git a/fs/smb/client/cifs_spnego.c b/fs/smb/client/cifs_spnego.c
index 6f3285f1dfee..af7849e5974f 100644
--- a/fs/smb/client/cifs_spnego.c
+++ b/fs/smb/client/cifs_spnego.c
@@ -64,8 +64,8 @@ struct key_type cifs_spnego_key_type = {
  * strlen(";sec=ntlmsspi") */
 #define MAX_MECH_STR_LEN	13
 
-/* strlen of "host=" */
-#define HOST_KEY_LEN		5
+/* strlen of ";host=" */
+#define HOST_KEY_LEN		6
 
 /* strlen of ";ip4=" or ";ip6=" */
 #define IP_KEY_LEN		5
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index ea3a7a668b45..99b0ade833aa 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -25,6 +25,7 @@
 #include <linux/freezer.h>
 #include <linux/namei.h>
 #include <linux/random.h>
+#include <linux/splice.h>
 #include <linux/uuid.h>
 #include <linux/xattr.h>
 #include <uapi/linux/magic.h>
@@ -1196,32 +1197,103 @@ const struct inode_operations cifs_symlink_inode_ops = {
 	.listxattr = cifs_listxattr,
 };
 
+/*
+ * Advance the EOF marker to after the source range.
+ */
+static int cifs_precopy_set_eof(struct inode *src_inode, struct cifsInodeInfo *src_cifsi,
+				struct cifs_tcon *src_tcon,
+				unsigned int xid, loff_t src_end)
+{
+	struct cifsFileInfo *writeable_srcfile;
+	int rc = -EINVAL;
+
+	writeable_srcfile = find_writable_file(src_cifsi, FIND_WR_FSUID_ONLY);
+	if (writeable_srcfile) {
+		if (src_tcon->ses->server->ops->set_file_size)
+			rc = src_tcon->ses->server->ops->set_file_size(
+				xid, src_tcon, writeable_srcfile,
+				src_inode->i_size, true /* no need to set sparse */);
+		else
+			rc = -ENOSYS;
+		cifsFileInfo_put(writeable_srcfile);
+		cifs_dbg(FYI, "SetFSize for copychunk rc = %d\n", rc);
+	}
+
+	if (rc < 0)
+		goto set_failed;
+
+	netfs_resize_file(&src_cifsi->netfs, src_end);
+	fscache_resize_cookie(cifs_inode_cookie(src_inode), src_end);
+	return 0;
+
+set_failed:
+	return filemap_write_and_wait(src_inode->i_mapping);
+}
+
+/*
+ * Flush out either the folio that overlaps the beginning of a range in which
+ * pos resides or the folio that overlaps the end of a range unless that folio
+ * is entirely within the range we're going to invalidate.  We extend the flush
+ * bounds to encompass the folio.
+ */
+static int cifs_flush_folio(struct inode *inode, loff_t pos, loff_t *_fstart, loff_t *_fend,
+			    bool first)
+{
+	struct folio *folio;
+	unsigned long long fpos, fend;
+	pgoff_t index = pos / PAGE_SIZE;
+	size_t size;
+	int rc = 0;
+
+	folio = filemap_get_folio(inode->i_mapping, index);
+	if (IS_ERR(folio))
+		return 0;
+
+	size = folio_size(folio);
+	fpos = folio_pos(folio);
+	fend = fpos + size - 1;
+	*_fstart = min_t(unsigned long long, *_fstart, fpos);
+	*_fend   = max_t(unsigned long long, *_fend, fend);
+	if ((first && pos == fpos) || (!first && pos == fend))
+		goto out;
+
+	rc = filemap_write_and_wait_range(inode->i_mapping, fpos, fend);
+out:
+	folio_put(folio);
+	return rc;
+}
+
 static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
 		struct file *dst_file, loff_t destoff, loff_t len,
 		unsigned int remap_flags)
 {
 	struct inode *src_inode = file_inode(src_file);
 	struct inode *target_inode = file_inode(dst_file);
+	struct cifsInodeInfo *src_cifsi = CIFS_I(src_inode);
+	struct cifsInodeInfo *target_cifsi = CIFS_I(target_inode);
 	struct cifsFileInfo *smb_file_src = src_file->private_data;
-	struct cifsFileInfo *smb_file_target;
-	struct cifs_tcon *target_tcon;
+	struct cifsFileInfo *smb_file_target = dst_file->private_data;
+	struct cifs_tcon *target_tcon, *src_tcon;
+	unsigned long long destend, fstart, fend, new_size;
 	unsigned int xid;
 	int rc;
 
-	if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY))
+	if (remap_flags & REMAP_FILE_DEDUP)
+		return -EOPNOTSUPP;
+	if (remap_flags & ~REMAP_FILE_ADVISORY)
 		return -EINVAL;
 
 	cifs_dbg(FYI, "clone range\n");
 
 	xid = get_xid();
 
-	if (!src_file->private_data || !dst_file->private_data) {
+	if (!smb_file_src || !smb_file_target) {
 		rc = -EBADF;
 		cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
 		goto out;
 	}
 
-	smb_file_target = dst_file->private_data;
+	src_tcon = tlink_tcon(smb_file_src->tlink);
 	target_tcon = tlink_tcon(smb_file_target->tlink);
 
 	/*
@@ -1234,20 +1306,63 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
 	if (len == 0)
 		len = src_inode->i_size - off;
 
-	cifs_dbg(FYI, "about to flush pages\n");
-	/* should we flush first and last page first */
-	truncate_inode_pages_range(&target_inode->i_data, destoff,
-				   PAGE_ALIGN(destoff + len)-1);
+	cifs_dbg(FYI, "clone range\n");
 
-	if (target_tcon->ses->server->ops->duplicate_extents)
+	/* Flush the source buffer */
+	rc = filemap_write_and_wait_range(src_inode->i_mapping, off,
+					  off + len - 1);
+	if (rc)
+		goto unlock;
+
+	/* The server-side copy will fail if the source crosses the EOF marker.
+	 * Advance the EOF marker after the flush above to the end of the range
+	 * if it's short of that.
+	 */
+	if (src_cifsi->netfs.remote_i_size < off + len) {
+		rc = cifs_precopy_set_eof(src_inode, src_cifsi, src_tcon, xid, off + len);
+		if (rc < 0)
+			goto unlock;
+	}
+
+	new_size = destoff + len;
+	destend = destoff + len - 1;
+
+	/* Flush the folios at either end of the destination range to prevent
+	 * accidental loss of dirty data outside of the range.
+	 */
+	fstart = destoff;
+	fend = destend;
+
+	rc = cifs_flush_folio(target_inode, destoff, &fstart, &fend, true);
+	if (rc)
+		goto unlock;
+	rc = cifs_flush_folio(target_inode, destend, &fstart, &fend, false);
+	if (rc)
+		goto unlock;
+
+	/* Discard all the folios that overlap the destination region. */
+	cifs_dbg(FYI, "about to discard pages %llx-%llx\n", fstart, fend);
+	truncate_inode_pages_range(&target_inode->i_data, fstart, fend);
+
+	fscache_invalidate(cifs_inode_cookie(target_inode), NULL,
+			   i_size_read(target_inode), 0);
+
+	rc = -EOPNOTSUPP;
+	if (target_tcon->ses->server->ops->duplicate_extents) {
 		rc = target_tcon->ses->server->ops->duplicate_extents(xid,
 			smb_file_src, smb_file_target, off, len, destoff);
-	else
-		rc = -EOPNOTSUPP;
+		if (rc == 0 && new_size > i_size_read(target_inode)) {
+			truncate_setsize(target_inode, new_size);
+			netfs_resize_file(&target_cifsi->netfs, new_size);
+			fscache_resize_cookie(cifs_inode_cookie(target_inode),
+					      new_size);
+		}
+	}
 
 	/* force revalidate of size and timestamps of target file now
 	   that target is updated on the server */
 	CIFS_I(target_inode)->time = 0;
+unlock:
 	/* although unlocking in the reverse order from locking is not
 	   strictly necessary here it is a little cleaner to be consistent */
 	unlock_two_nondirectories(src_inode, target_inode);
@@ -1263,10 +1378,12 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
 {
 	struct inode *src_inode = file_inode(src_file);
 	struct inode *target_inode = file_inode(dst_file);
+	struct cifsInodeInfo *src_cifsi = CIFS_I(src_inode);
 	struct cifsFileInfo *smb_file_src;
 	struct cifsFileInfo *smb_file_target;
 	struct cifs_tcon *src_tcon;
 	struct cifs_tcon *target_tcon;
+	unsigned long long destend, fstart, fend;
 	ssize_t rc;
 
 	cifs_dbg(FYI, "copychunk range\n");
@@ -1306,13 +1423,41 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
 	if (rc)
 		goto unlock;
 
-	/* should we flush first and last page first */
-	truncate_inode_pages(&target_inode->i_data, 0);
+	/* The server-side copy will fail if the source crosses the EOF marker.
+	 * Advance the EOF marker after the flush above to the end of the range
+	 * if it's short of that.
+	 */
+	if (src_cifsi->server_eof < off + len) {
+		rc = cifs_precopy_set_eof(src_inode, src_cifsi, src_tcon, xid, off + len);
+		if (rc < 0)
+			goto unlock;
+	}
+
+	destend = destoff + len - 1;
+
+	/* Flush the folios at either end of the destination range to prevent
+	 * accidental loss of dirty data outside of the range.
+	 */
+	fstart = destoff;
+	fend = destend;
+
+	rc = cifs_flush_folio(target_inode, destoff, &fstart, &fend, true);
+	if (rc)
+		goto unlock;
+	rc = cifs_flush_folio(target_inode, destend, &fstart, &fend, false);
+	if (rc)
+		goto unlock;
+
+	/* Discard all the folios that overlap the destination region. */
+	truncate_inode_pages_range(&target_inode->i_data, fstart, fend);
 
 	rc = file_modified(dst_file);
-	if (!rc)
+	if (!rc) {
 		rc = target_tcon->ses->server->ops->copychunk_range(xid,
 			smb_file_src, smb_file_target, off, len, destoff);
+		if (rc > 0 && destoff + rc > i_size_read(target_inode))
+			truncate_setsize(target_inode, destoff + rc);
+	}
 
 	file_accessed(src_file);
 
@@ -1362,8 +1507,8 @@ static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off,
 	free_xid(xid);
 
 	if (rc == -EOPNOTSUPP || rc == -EXDEV)
-		rc = generic_copy_file_range(src_file, off, dst_file,
-					     destoff, len, flags);
+		rc = splice_copy_file_range(src_file, off, dst_file,
+					    destoff, len);
 	return rc;
 }
 
diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h
index 3adea10aa9da..685f7d1139c6 100644
--- a/fs/smb/client/cifsfs.h
+++ b/fs/smb/client/cifsfs.h
@@ -152,6 +152,6 @@ extern const struct export_operations cifs_export_ops;
 #endif /* CONFIG_CIFS_NFSD_EXPORT */
 
 /* when changing internal version - update following two lines at same time */
-#define SMB3_PRODUCT_BUILD 46
-#define CIFS_VERSION   "2.46"
+#define SMB3_PRODUCT_BUILD 47
+#define CIFS_VERSION   "2.47"
 #endif				/* _CIFSFS_H */
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 6ffbd81bd109..879d5ef8a66e 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -191,7 +191,18 @@ struct cifs_open_info_data {
 		bool reparse_point;
 		bool symlink;
 	};
-	__u32 reparse_tag;
+	struct {
+		/* ioctl response buffer */
+		struct {
+			int buftype;
+			struct kvec iov;
+		} io;
+		__u32 tag;
+		union {
+			struct reparse_data_buffer *buf;
+			struct reparse_posix_data *posix;
+		};
+	} reparse;
 	char *symlink_target;
 	union {
 		struct smb2_file_all_info fi;
@@ -199,13 +210,17 @@ struct cifs_open_info_data {
 	};
 };
 
-#define cifs_open_data_reparse(d) \
-	((d)->reparse_point || \
-	 (le32_to_cpu((d)->fi.Attributes) & ATTR_REPARSE))
-
-static inline void cifs_free_open_info(struct cifs_open_info_data *data)
+static inline bool cifs_open_data_reparse(struct cifs_open_info_data *data)
 {
-	kfree(data->symlink_target);
+	struct smb2_file_all_info *fi = &data->fi;
+	u32 attrs = le32_to_cpu(fi->Attributes);
+	bool ret;
+
+	ret = data->reparse_point || (attrs & ATTR_REPARSE);
+	if (ret)
+		attrs |= ATTR_REPARSE;
+	fi->Attributes = cpu_to_le32(attrs);
+	return ret;
 }
 
 /*
@@ -384,19 +399,23 @@ struct smb_version_operations {
 	int (*rename_pending_delete)(const char *, struct dentry *,
 				     const unsigned int);
 	/* send rename request */
-	int (*rename)(const unsigned int, struct cifs_tcon *, const char *,
-		      const char *, struct cifs_sb_info *);
+	int (*rename)(const unsigned int xid,
+		      struct cifs_tcon *tcon,
+		      struct dentry *source_dentry,
+		      const char *from_name, const char *to_name,
+		      struct cifs_sb_info *cifs_sb);
 	/* send create hardlink request */
-	int (*create_hardlink)(const unsigned int, struct cifs_tcon *,
-			       const char *, const char *,
-			       struct cifs_sb_info *);
+	int (*create_hardlink)(const unsigned int xid,
+			       struct cifs_tcon *tcon,
+			       struct dentry *source_dentry,
+			       const char *from_name, const char *to_name,
+			       struct cifs_sb_info *cifs_sb);
 	/* query symlink target */
 	int (*query_symlink)(const unsigned int xid,
 			     struct cifs_tcon *tcon,
 			     struct cifs_sb_info *cifs_sb,
 			     const char *full_path,
-			     char **target_path,
-			     struct kvec *rsp_iov);
+			     char **target_path);
 	/* open a file for non-posix mounts */
 	int (*open)(const unsigned int xid, struct cifs_open_parms *oparms, __u32 *oplock,
 		    void *buf);
@@ -527,7 +546,8 @@ struct smb_version_operations {
 				 struct mid_q_entry **, char **, int *);
 	enum securityEnum (*select_sectype)(struct TCP_Server_Info *,
 			    enum securityEnum);
-	int (*next_header)(char *);
+	int (*next_header)(struct TCP_Server_Info *server, char *buf,
+			   unsigned int *noff);
 	/* ioctl passthrough for query_info */
 	int (*ioctl_query_info)(const unsigned int xid,
 				struct cifs_tcon *tcon,
@@ -551,6 +571,15 @@ struct smb_version_operations {
 	bool (*is_status_io_timeout)(char *buf);
 	/* Check for STATUS_NETWORK_NAME_DELETED */
 	bool (*is_network_name_deleted)(char *buf, struct TCP_Server_Info *srv);
+	int (*parse_reparse_point)(struct cifs_sb_info *cifs_sb,
+				   struct kvec *rsp_iov,
+				   struct cifs_open_info_data *data);
+	int (*create_reparse_symlink)(const unsigned int xid,
+				      struct inode *inode,
+				      struct dentry *dentry,
+				      struct cifs_tcon *tcon,
+				      const char *full_path,
+				      const char *symname);
 };
 
 struct smb_version_values {
@@ -985,7 +1014,6 @@ release_iface(struct kref *ref)
 	struct cifs_server_iface *iface = container_of(ref,
 						       struct cifs_server_iface,
 						       refcount);
-	list_del_init(&iface->iface_head);
 	kfree(iface);
 }
 
@@ -1537,6 +1565,7 @@ struct cifsInodeInfo {
 	spinlock_t deferred_lock; /* protection on deferred list */
 	bool lease_granted; /* Flag to indicate whether lease or oplock is granted. */
 	char *symlink_target;
+	__u32 reparse_tag;
 };
 
 static inline struct cifsInodeInfo *
@@ -2230,8 +2259,8 @@ static inline void cifs_sg_set_buf(struct sg_table *sgtable,
 
 struct smb2_compound_vars {
 	struct cifs_open_parms oparms;
-	struct kvec rsp_iov[3];
-	struct smb_rqst rqst[3];
+	struct kvec rsp_iov[MAX_COMPOUND];
+	struct smb_rqst rqst[MAX_COMPOUND];
 	struct kvec open_iov[SMB2_CREATE_IOV_SIZE];
 	struct kvec qi_iov;
 	struct kvec io_iov[SMB2_IOCTL_IOV_SIZE];
diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h
index a75220db5c1e..c0513fbb8a59 100644
--- a/fs/smb/client/cifspdu.h
+++ b/fs/smb/client/cifspdu.h
@@ -882,11 +882,13 @@ typedef struct smb_com_open_rsp {
 	__u8 OplockLevel;
 	__u16 Fid;
 	__le32 CreateAction;
-	__le64 CreationTime;
-	__le64 LastAccessTime;
-	__le64 LastWriteTime;
-	__le64 ChangeTime;
-	__le32 FileAttributes;
+	struct_group(common_attributes,
+		__le64 CreationTime;
+		__le64 LastAccessTime;
+		__le64 LastWriteTime;
+		__le64 ChangeTime;
+		__le32 FileAttributes;
+	);
 	__le64 AllocationSize;
 	__le64 EndOfFile;
 	__le16 FileType;
@@ -1356,7 +1358,7 @@ typedef struct smb_com_transaction_ioctl_rsp {
 	__le32 DataDisplacement;
 	__u8 SetupCount;	/* 1 */
 	__le16 ReturnedDataLen;
-	__u16 ByteCount;
+	__le16 ByteCount;
 } __attribute__((packed)) TRANSACT_IOCTL_RSP;
 
 #define CIFS_ACL_OWNER 1
@@ -1509,7 +1511,7 @@ struct reparse_posix_data {
 	__le16	ReparseDataLength;
 	__u16	Reserved;
 	__le64	InodeType; /* LNK, FIFO, CHR etc. */
-	char	PathBuffer[];
+	__u8	DataBuffer[];
 } __attribute__((packed));
 
 struct cifs_quota_data {
@@ -2264,11 +2266,13 @@ typedef struct {
 /* QueryFileInfo/QueryPathinfo (also for SetPath/SetFile) data buffer formats */
 /******************************************************************************/
 typedef struct { /* data block encoding of response to level 263 QPathInfo */
-	__le64 CreationTime;
-	__le64 LastAccessTime;
-	__le64 LastWriteTime;
-	__le64 ChangeTime;
-	__le32 Attributes;
+	struct_group(common_attributes,
+		__le64 CreationTime;
+		__le64 LastAccessTime;
+		__le64 LastWriteTime;
+		__le64 ChangeTime;
+		__le32 Attributes;
+	);
 	__u32 Pad1;
 	__le64 AllocationSize;
 	__le64 EndOfFile;	/* size ie offset to first free byte in file */
diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h
index d87e2c26cce2..a841bf4967fa 100644
--- a/fs/smb/client/cifsproto.h
+++ b/fs/smb/client/cifsproto.h
@@ -210,9 +210,13 @@ int cifs_get_inode_info(struct inode **inode, const char *full_path,
 			const struct cifs_fid *fid);
 bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb,
 				 struct cifs_fattr *fattr,
-				 u32 tag);
-extern int smb311_posix_get_inode_info(struct inode **pinode, const char *search_path,
-			struct super_block *sb, unsigned int xid);
+				 struct cifs_open_info_data *data);
+
+extern int smb311_posix_get_inode_info(struct inode **inode,
+				       const char *full_path,
+				       struct cifs_open_info_data *data,
+				       struct super_block *sb,
+				       const unsigned int xid);
 extern int cifs_get_inode_info_unix(struct inode **pinode,
 			const unsigned char *search_path,
 			struct super_block *sb, unsigned int xid);
@@ -435,16 +439,19 @@ extern int CIFSPOSIXDelFile(const unsigned int xid, struct cifs_tcon *tcon,
 			int remap_special_chars);
 extern int CIFSSMBDelFile(const unsigned int xid, struct cifs_tcon *tcon,
 			  const char *name, struct cifs_sb_info *cifs_sb);
-extern int CIFSSMBRename(const unsigned int xid, struct cifs_tcon *tcon,
-			 const char *from_name, const char *to_name,
-			 struct cifs_sb_info *cifs_sb);
+int CIFSSMBRename(const unsigned int xid, struct cifs_tcon *tcon,
+		  struct dentry *source_dentry,
+		  const char *from_name, const char *to_name,
+		  struct cifs_sb_info *cifs_sb);
 extern int CIFSSMBRenameOpenFile(const unsigned int xid, struct cifs_tcon *tcon,
 				 int netfid, const char *target_name,
 				 const struct nls_table *nls_codepage,
 				 int remap_special_chars);
-extern int CIFSCreateHardLink(const unsigned int xid, struct cifs_tcon *tcon,
-			      const char *from_name, const char *to_name,
-			      struct cifs_sb_info *cifs_sb);
+int CIFSCreateHardLink(const unsigned int xid,
+		       struct cifs_tcon *tcon,
+		       struct dentry *source_dentry,
+		       const char *from_name, const char *to_name,
+		       struct cifs_sb_info *cifs_sb);
 extern int CIFSUnixCreateHardLink(const unsigned int xid,
 			struct cifs_tcon *tcon,
 			const char *fromName, const char *toName,
@@ -458,6 +465,12 @@ extern int CIFSSMBUnixQuerySymLink(const unsigned int xid,
 			struct cifs_tcon *tcon,
 			const unsigned char *searchName, char **syminfo,
 			const struct nls_table *nls_codepage, int remap);
+extern int cifs_query_reparse_point(const unsigned int xid,
+				    struct cifs_tcon *tcon,
+				    struct cifs_sb_info *cifs_sb,
+				    const char *full_path,
+				    u32 *tag, struct kvec *rsp,
+				    int *rsp_buftype);
 extern int CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon,
 			       __u16 fid, char **symlinkinfo,
 			       const struct nls_table *nls_codepage);
@@ -643,7 +656,7 @@ cifs_chan_is_iface_active(struct cifs_ses *ses,
 			  struct TCP_Server_Info *server);
 void
 cifs_disable_secondary_channels(struct cifs_ses *ses);
-int
+void
 cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server);
 int
 SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon, bool in_mount);
@@ -659,6 +672,12 @@ void cifs_put_tcp_super(struct super_block *sb);
 int cifs_update_super_prepath(struct cifs_sb_info *cifs_sb, char *prefix);
 char *extract_hostname(const char *unc);
 char *extract_sharename(const char *unc);
+int parse_reparse_point(struct reparse_data_buffer *buf,
+			u32 plen, struct cifs_sb_info *cifs_sb,
+			bool unicode, struct cifs_open_info_data *data);
+int cifs_sfu_make_node(unsigned int xid, struct inode *inode,
+		       struct dentry *dentry, struct cifs_tcon *tcon,
+		       const char *full_path, umode_t mode, dev_t dev);
 
 #ifdef CONFIG_CIFS_DFS_UPCALL
 static inline int get_dfs_path(const unsigned int xid, struct cifs_ses *ses,
@@ -748,4 +767,11 @@ static inline void release_mid(struct mid_q_entry *mid)
 	kref_put(&mid->refcount, __release_mid);
 }
 
+static inline void cifs_free_open_info(struct cifs_open_info_data *data)
+{
+	kfree(data->symlink_target);
+	free_rsp_buf(data->reparse.io.buftype, data->reparse.io.iov.iov_base);
+	memset(data, 0, sizeof(*data));
+}
+
 #endif			/* _CIFSPROTO_H */
diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index 25503f1a4fd2..01e89070df5a 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -1244,8 +1244,10 @@ openRetry:
 		*oplock |= CIFS_CREATE_ACTION;
 
 	if (buf) {
-		/* copy from CreationTime to Attributes */
-		memcpy((char *)buf, (char *)&rsp->CreationTime, 36);
+		/* copy commonly used attributes */
+		memcpy(&buf->common_attributes,
+		       &rsp->common_attributes,
+		       sizeof(buf->common_attributes));
 		/* the file_info buf is endian converted by caller */
 		buf->AllocationSize = rsp->AllocationSize;
 		buf->EndOfFile = rsp->EndOfFile;
@@ -2147,10 +2149,10 @@ CIFSSMBFlush(const unsigned int xid, struct cifs_tcon *tcon, int smb_file_id)
 	return rc;
 }
 
-int
-CIFSSMBRename(const unsigned int xid, struct cifs_tcon *tcon,
-	      const char *from_name, const char *to_name,
-	      struct cifs_sb_info *cifs_sb)
+int CIFSSMBRename(const unsigned int xid, struct cifs_tcon *tcon,
+		  struct dentry *source_dentry,
+		  const char *from_name, const char *to_name,
+		  struct cifs_sb_info *cifs_sb)
 {
 	int rc = 0;
 	RENAME_REQ *pSMB = NULL;
@@ -2528,10 +2530,11 @@ createHardLinkRetry:
 	return rc;
 }
 
-int
-CIFSCreateHardLink(const unsigned int xid, struct cifs_tcon *tcon,
-		   const char *from_name, const char *to_name,
-		   struct cifs_sb_info *cifs_sb)
+int CIFSCreateHardLink(const unsigned int xid,
+		       struct cifs_tcon *tcon,
+		       struct dentry *source_dentry,
+		       const char *from_name, const char *to_name,
+		       struct cifs_sb_info *cifs_sb)
 {
 	int rc = 0;
 	NT_RENAME_REQ *pSMB = NULL;
@@ -2690,136 +2693,107 @@ querySymLinkRetry:
 	return rc;
 }
 
-/*
- *	Recent Windows versions now create symlinks more frequently
- *	and they use the "reparse point" mechanism below.  We can of course
- *	do symlinks nicely to Samba and other servers which support the
- *	CIFS Unix Extensions and we can also do SFU symlinks and "client only"
- *	"MF" symlinks optionally, but for recent Windows we really need to
- *	reenable the code below and fix the cifs_symlink callers to handle this.
- *	In the interim this code has been moved to its own config option so
- *	it is not compiled in by default until callers fixed up and more tested.
- */
-int
-CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon,
-		    __u16 fid, char **symlinkinfo,
-		    const struct nls_table *nls_codepage)
+int cifs_query_reparse_point(const unsigned int xid,
+			     struct cifs_tcon *tcon,
+			     struct cifs_sb_info *cifs_sb,
+			     const char *full_path,
+			     u32 *tag, struct kvec *rsp,
+			     int *rsp_buftype)
 {
-	int rc = 0;
-	int bytes_returned;
-	struct smb_com_transaction_ioctl_req *pSMB;
-	struct smb_com_transaction_ioctl_rsp *pSMBr;
-	bool is_unicode;
-	unsigned int sub_len;
-	char *sub_start;
-	struct reparse_symlink_data *reparse_buf;
-	struct reparse_posix_data *posix_buf;
-	__u32 data_offset, data_count;
-	char *end_of_smb;
+	struct reparse_data_buffer *buf;
+	struct cifs_open_parms oparms;
+	TRANSACT_IOCTL_REQ *io_req = NULL;
+	TRANSACT_IOCTL_RSP *io_rsp = NULL;
+	struct cifs_fid fid;
+	__u32 data_offset, data_count, len;
+	__u8 *start, *end;
+	int io_rsp_len;
+	int oplock = 0;
+	int rc;
 
-	cifs_dbg(FYI, "In Windows reparse style QueryLink for fid %u\n", fid);
-	rc = smb_init(SMB_COM_NT_TRANSACT, 23, tcon, (void **) &pSMB,
-		      (void **) &pSMBr);
+	cifs_tcon_dbg(FYI, "%s: path=%s\n", __func__, full_path);
+
+	if (cap_unix(tcon->ses))
+		return -EOPNOTSUPP;
+
+	oparms = (struct cifs_open_parms) {
+		.tcon = tcon,
+		.cifs_sb = cifs_sb,
+		.desired_access = FILE_READ_ATTRIBUTES,
+		.create_options = cifs_create_options(cifs_sb,
+						      OPEN_REPARSE_POINT),
+		.disposition = FILE_OPEN,
+		.path = full_path,
+		.fid = &fid,
+	};
+
+	rc = CIFS_open(xid, &oparms, &oplock, NULL);
 	if (rc)
 		return rc;
 
-	pSMB->TotalParameterCount = 0 ;
-	pSMB->TotalDataCount = 0;
-	pSMB->MaxParameterCount = cpu_to_le32(2);
-	/* BB find exact data count max from sess structure BB */
-	pSMB->MaxDataCount = cpu_to_le32(CIFSMaxBufSize & 0xFFFFFF00);
-	pSMB->MaxSetupCount = 4;
-	pSMB->Reserved = 0;
-	pSMB->ParameterOffset = 0;
-	pSMB->DataCount = 0;
-	pSMB->DataOffset = 0;
-	pSMB->SetupCount = 4;
-	pSMB->SubCommand = cpu_to_le16(NT_TRANSACT_IOCTL);
-	pSMB->ParameterCount = pSMB->TotalParameterCount;
-	pSMB->FunctionCode = cpu_to_le32(FSCTL_GET_REPARSE_POINT);
-	pSMB->IsFsctl = 1; /* FSCTL */
-	pSMB->IsRootFlag = 0;
-	pSMB->Fid = fid; /* file handle always le */
-	pSMB->ByteCount = 0;
+	rc = smb_init(SMB_COM_NT_TRANSACT, 23, tcon,
+		      (void **)&io_req, (void **)&io_rsp);
+	if (rc)
+		goto error;
 
-	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
-			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
-	if (rc) {
-		cifs_dbg(FYI, "Send error in QueryReparseLinkInfo = %d\n", rc);
-		goto qreparse_out;
-	}
+	io_req->TotalParameterCount = 0;
+	io_req->TotalDataCount = 0;
+	io_req->MaxParameterCount = cpu_to_le32(2);
+	/* BB find exact data count max from sess structure BB */
+	io_req->MaxDataCount = cpu_to_le32(CIFSMaxBufSize & 0xFFFFFF00);
+	io_req->MaxSetupCount = 4;
+	io_req->Reserved = 0;
+	io_req->ParameterOffset = 0;
+	io_req->DataCount = 0;
+	io_req->DataOffset = 0;
+	io_req->SetupCount = 4;
+	io_req->SubCommand = cpu_to_le16(NT_TRANSACT_IOCTL);
+	io_req->ParameterCount = io_req->TotalParameterCount;
+	io_req->FunctionCode = cpu_to_le32(FSCTL_GET_REPARSE_POINT);
+	io_req->IsFsctl = 1;
+	io_req->IsRootFlag = 0;
+	io_req->Fid = fid.netfid;
+	io_req->ByteCount = 0;
+
+	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *)io_req,
+			 (struct smb_hdr *)io_rsp, &io_rsp_len, 0);
+	if (rc)
+		goto error;
 
-	data_offset = le32_to_cpu(pSMBr->DataOffset);
-	data_count = le32_to_cpu(pSMBr->DataCount);
-	if (get_bcc(&pSMBr->hdr) < 2 || data_offset > 512) {
-		/* BB also check enough total bytes returned */
-		rc = -EIO;	/* bad smb */
-		goto qreparse_out;
-	}
-	if (!data_count || (data_count > 2048)) {
+	data_offset = le32_to_cpu(io_rsp->DataOffset);
+	data_count = le32_to_cpu(io_rsp->DataCount);
+	if (get_bcc(&io_rsp->hdr) < 2 || data_offset > 512 ||
+	    !data_count || data_count > 2048) {
 		rc = -EIO;
-		cifs_dbg(FYI, "Invalid return data count on get reparse info ioctl\n");
-		goto qreparse_out;
+		goto error;
 	}
-	end_of_smb = 2 + get_bcc(&pSMBr->hdr) + (char *)&pSMBr->ByteCount;
-	reparse_buf = (struct reparse_symlink_data *)
-				((char *)&pSMBr->hdr.Protocol + data_offset);
-	if ((char *)reparse_buf >= end_of_smb) {
+
+	end = 2 + get_bcc(&io_rsp->hdr) + (__u8 *)&io_rsp->ByteCount;
+	start = (__u8 *)&io_rsp->hdr.Protocol + data_offset;
+	if (start >= end) {
 		rc = -EIO;
-		goto qreparse_out;
-	}
-	if (reparse_buf->ReparseTag == cpu_to_le32(IO_REPARSE_TAG_NFS)) {
-		cifs_dbg(FYI, "NFS style reparse tag\n");
-		posix_buf =  (struct reparse_posix_data *)reparse_buf;
-
-		if (posix_buf->InodeType != cpu_to_le64(NFS_SPECFILE_LNK)) {
-			cifs_dbg(FYI, "unsupported file type 0x%llx\n",
-				 le64_to_cpu(posix_buf->InodeType));
-			rc = -EOPNOTSUPP;
-			goto qreparse_out;
-		}
-		is_unicode = true;
-		sub_len = le16_to_cpu(reparse_buf->ReparseDataLength);
-		if (posix_buf->PathBuffer + sub_len > end_of_smb) {
-			cifs_dbg(FYI, "reparse buf beyond SMB\n");
-			rc = -EIO;
-			goto qreparse_out;
-		}
-		*symlinkinfo = cifs_strndup_from_utf16(posix_buf->PathBuffer,
-				sub_len, is_unicode, nls_codepage);
-		goto qreparse_out;
-	} else if (reparse_buf->ReparseTag !=
-			cpu_to_le32(IO_REPARSE_TAG_SYMLINK)) {
-		rc = -EOPNOTSUPP;
-		goto qreparse_out;
+		goto error;
 	}
 
-	/* Reparse tag is NTFS symlink */
-	sub_start = le16_to_cpu(reparse_buf->SubstituteNameOffset) +
-				reparse_buf->PathBuffer;
-	sub_len = le16_to_cpu(reparse_buf->SubstituteNameLength);
-	if (sub_start + sub_len > end_of_smb) {
-		cifs_dbg(FYI, "reparse buf beyond SMB\n");
+	data_count = le16_to_cpu(io_rsp->ByteCount);
+	buf = (struct reparse_data_buffer *)start;
+	len = sizeof(*buf);
+	if (data_count < len ||
+	    data_count < le16_to_cpu(buf->ReparseDataLength) + len) {
 		rc = -EIO;
-		goto qreparse_out;
+		goto error;
 	}
-	if (pSMBr->hdr.Flags2 & SMBFLG2_UNICODE)
-		is_unicode = true;
-	else
-		is_unicode = false;
-
-	/* BB FIXME investigate remapping reserved chars here */
-	*symlinkinfo = cifs_strndup_from_utf16(sub_start, sub_len, is_unicode,
-					       nls_codepage);
-	if (!*symlinkinfo)
-		rc = -ENOMEM;
-qreparse_out:
-	cifs_buf_release(pSMB);
 
-	/*
-	 * Note: On -EAGAIN error only caller can retry on handle based calls
-	 * since file handle passed in no longer valid.
-	 */
+	*tag = le32_to_cpu(buf->ReparseTag);
+	rsp->iov_base = io_rsp;
+	rsp->iov_len = io_rsp_len;
+	*rsp_buftype = CIFS_LARGE_BUFFER;
+	CIFSSMBClose(xid, tcon, fid.netfid);
+	return 0;
+
+error:
+	cifs_buf_release(io_req);
+	CIFSSMBClose(xid, tcon, fid.netfid);
 	return rc;
 }
 
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 57c2a7df3457..3052a208c6ca 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -216,22 +216,29 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server,
 	/* If server is a channel, select the primary channel */
 	pserver = SERVER_IS_CHAN(server) ? server->primary_server : server;
 
+	/*
+	 * if the server has been marked for termination, there is a
+	 * chance that the remaining channels all need reconnect. To be
+	 * on the safer side, mark the session and trees for reconnect
+	 * for this scenario. This might cause a few redundant session
+	 * setup and tree connect requests, but it is better than not doing
+	 * a tree connect when needed, and all following requests failing
+	 */
+	if (server->terminate) {
+		mark_smb_session = true;
+		server = pserver;
+	}
 
 	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each_entry_safe(ses, nses, &pserver->smb_ses_list, smb_ses_list) {
-		/*
-		 * if channel has been marked for termination, nothing to do
-		 * for the channel. in fact, we cannot find the channel for the
-		 * server. So safe to exit here
-		 */
-		if (server->terminate)
-			break;
-
 		/* check if iface is still active */
-		if (!cifs_chan_is_iface_active(ses, server))
+		spin_lock(&ses->chan_lock);
+		if (!cifs_chan_is_iface_active(ses, server)) {
+			spin_unlock(&ses->chan_lock);
 			cifs_chan_update_iface(ses, server);
+			spin_lock(&ses->chan_lock);
+		}
 
-		spin_lock(&ses->chan_lock);
 		if (!mark_smb_session && cifs_chan_needs_reconnect(ses, server)) {
 			spin_unlock(&ses->chan_lock);
 			continue;
@@ -402,13 +409,7 @@ static int __cifs_reconnect(struct TCP_Server_Info *server,
 			spin_unlock(&server->srv_lock);
 			cifs_swn_reset_server_dstaddr(server);
 			cifs_server_unlock(server);
-
-			/* increase ref count which reconnect work will drop */
-			spin_lock(&cifs_tcp_ses_lock);
-			server->srv_count++;
-			spin_unlock(&cifs_tcp_ses_lock);
-			if (mod_delayed_work(cifsiod_wq, &server->reconnect, 0))
-				cifs_put_tcp_session(server, false);
+			mod_delayed_work(cifsiod_wq, &server->reconnect, 0);
 		}
 	} while (server->tcpStatus == CifsNeedReconnect);
 
@@ -482,6 +483,7 @@ static int reconnect_target_unlocked(struct TCP_Server_Info *server, struct dfs_
 static int reconnect_dfs_server(struct TCP_Server_Info *server)
 {
 	struct dfs_cache_tgt_iterator *target_hint = NULL;
+
 	DFS_CACHE_TGT_LIST(tl);
 	int num_targets = 0;
 	int rc = 0;
@@ -538,13 +540,7 @@ static int reconnect_dfs_server(struct TCP_Server_Info *server)
 		spin_unlock(&server->srv_lock);
 		cifs_swn_reset_server_dstaddr(server);
 		cifs_server_unlock(server);
-
-		/* increase ref count which reconnect work will drop */
-		spin_lock(&cifs_tcp_ses_lock);
-		server->srv_count++;
-		spin_unlock(&cifs_tcp_ses_lock);
-		if (mod_delayed_work(cifsiod_wq, &server->reconnect, 0))
-			cifs_put_tcp_session(server, false);
+		mod_delayed_work(cifsiod_wq, &server->reconnect, 0);
 	} while (server->tcpStatus == CifsNeedReconnect);
 
 	mutex_lock(&server->refpath_lock);
@@ -750,6 +746,7 @@ cifs_read_from_socket(struct TCP_Server_Info *server, char *buf,
 {
 	struct msghdr smb_msg = {};
 	struct kvec iov = {.iov_base = buf, .iov_len = to_read};
+
 	iov_iter_kvec(&smb_msg.msg_iter, ITER_DEST, &iov, 1, to_read);
 
 	return cifs_readv_from_socket(server, &smb_msg);
@@ -1213,7 +1210,12 @@ next_pdu:
 		server->total_read += length;
 
 		if (server->ops->next_header) {
-			next_offset = server->ops->next_header(buf);
+			if (server->ops->next_header(server, buf, &next_offset)) {
+				cifs_dbg(VFS, "%s: malformed response (next_offset=%u)\n",
+					 __func__, next_offset);
+				cifs_reconnect(server, true);
+				continue;
+			}
 			if (next_offset)
 				server->pdu_size = next_offset;
 		}
@@ -1400,11 +1402,13 @@ cifs_match_ipaddr(struct sockaddr *srcaddr, struct sockaddr *rhs)
 	case AF_INET: {
 		struct sockaddr_in *saddr4 = (struct sockaddr_in *)srcaddr;
 		struct sockaddr_in *vaddr4 = (struct sockaddr_in *)rhs;
+
 		return (saddr4->sin_addr.s_addr == vaddr4->sin_addr.s_addr);
 	}
 	case AF_INET6: {
 		struct sockaddr_in6 *saddr6 = (struct sockaddr_in6 *)srcaddr;
 		struct sockaddr_in6 *vaddr6 = (struct sockaddr_in6 *)rhs;
+
 		return (ipv6_addr_equal(&saddr6->sin6_addr, &vaddr6->sin6_addr)
 			&& saddr6->sin6_scope_id == vaddr6->sin6_scope_id);
 	}
@@ -1620,25 +1624,22 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect)
 	list_del_init(&server->tcp_ses_list);
 	spin_unlock(&cifs_tcp_ses_lock);
 
-	/* For secondary channels, we pick up ref-count on the primary server */
-	if (SERVER_IS_CHAN(server))
-		cifs_put_tcp_session(server->primary_server, from_reconnect);
-
 	cancel_delayed_work_sync(&server->echo);
 
-	if (from_reconnect) {
+	if (from_reconnect)
 		/*
 		 * Avoid deadlock here: reconnect work calls
 		 * cifs_put_tcp_session() at its end. Need to be sure
 		 * that reconnect work does nothing with server pointer after
 		 * that step.
 		 */
-		if (cancel_delayed_work(&server->reconnect))
-			cifs_put_tcp_session(server, from_reconnect);
-	} else {
-		if (cancel_delayed_work_sync(&server->reconnect))
-			cifs_put_tcp_session(server, from_reconnect);
-	}
+		cancel_delayed_work(&server->reconnect);
+	else
+		cancel_delayed_work_sync(&server->reconnect);
+
+	/* For secondary channels, we pick up ref-count on the primary server */
+	if (SERVER_IS_CHAN(server))
+		cifs_put_tcp_session(server->primary_server, from_reconnect);
 
 	spin_lock(&server->srv_lock);
 	server->tcpStatus = CifsExiting;
@@ -2065,6 +2066,12 @@ void __cifs_put_smb_ses(struct cifs_ses *ses)
 		ses->chans[i].server = NULL;
 	}
 
+	/* we now account for primary channel in iface->refcount */
+	if (ses->chans[0].iface) {
+		kref_put(&ses->chans[0].iface->refcount, release_iface);
+		ses->chans[0].server = NULL;
+	}
+
 	sesInfoFree(ses);
 	cifs_put_tcp_session(server, 0);
 }
@@ -2596,8 +2603,8 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx)
 			rc = -EOPNOTSUPP;
 			goto out_fail;
 		} else {
-			cifs_dbg(VFS, "Check vers= mount option. SMB3.11 "
-				"disabled but required for POSIX extensions\n");
+			cifs_dbg(VFS,
+				"Check vers= mount option. SMB3.11 disabled but required for POSIX extensions\n");
 			rc = -EOPNOTSUPP;
 			goto out_fail;
 		}
@@ -2740,7 +2747,6 @@ cifs_put_tlink(struct tcon_link *tlink)
 	if (!IS_ERR(tlink_tcon(tlink)))
 		cifs_put_tcon(tlink_tcon(tlink));
 	kfree(tlink);
-	return;
 }
 
 static int
@@ -2881,6 +2887,7 @@ static inline void
 cifs_reclassify_socket4(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
+
 	BUG_ON(!sock_allow_reclassification(sk));
 	sock_lock_init_class_and_name(sk, "slock-AF_INET-CIFS",
 		&cifs_slock_key[0], "sk_lock-AF_INET-CIFS", &cifs_key[0]);
@@ -2890,6 +2897,7 @@ static inline void
 cifs_reclassify_socket6(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
+
 	BUG_ON(!sock_allow_reclassification(sk));
 	sock_lock_init_class_and_name(sk, "slock-AF_INET6-CIFS",
 		&cifs_slock_key[1], "sk_lock-AF_INET6-CIFS", &cifs_key[1]);
@@ -2924,15 +2932,18 @@ static int
 bind_socket(struct TCP_Server_Info *server)
 {
 	int rc = 0;
+
 	if (server->srcaddr.ss_family != AF_UNSPEC) {
 		/* Bind to the specified local IP address */
 		struct socket *socket = server->ssocket;
+
 		rc = kernel_bind(socket,
 				 (struct sockaddr *) &server->srcaddr,
 				 sizeof(server->srcaddr));
 		if (rc < 0) {
 			struct sockaddr_in *saddr4;
 			struct sockaddr_in6 *saddr6;
+
 			saddr4 = (struct sockaddr_in *)&server->srcaddr;
 			saddr6 = (struct sockaddr_in6 *)&server->srcaddr;
 			if (saddr6->sin6_family == AF_INET6)
@@ -3162,6 +3173,7 @@ void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon,
 
 	if (!CIFSSMBQFSUnixInfo(xid, tcon)) {
 		__u64 cap = le64_to_cpu(tcon->fsUnixInfo.Capability);
+
 		cifs_dbg(FYI, "unix caps which server supports %lld\n", cap);
 		/*
 		 * check for reconnect case in which we do not
@@ -3665,7 +3677,7 @@ CIFSTCon(const unsigned int xid, struct cifs_ses *ses,
 	smb_buffer_response = smb_buffer;
 
 	header_assemble(smb_buffer, SMB_COM_TREE_CONNECT_ANDX,
-			NULL /*no tid */ , 4 /*wct */ );
+			NULL /*no tid */, 4 /*wct */);
 
 	smb_buffer->Mid = get_next_mid(ses->server);
 	smb_buffer->Uid = ses->Suid;
@@ -3684,12 +3696,12 @@ CIFSTCon(const unsigned int xid, struct cifs_ses *ses,
 	if (ses->server->sign)
 		smb_buffer->Flags2 |= SMBFLG2_SECURITY_SIGNATURE;
 
-	if (ses->capabilities & CAP_STATUS32) {
+	if (ses->capabilities & CAP_STATUS32)
 		smb_buffer->Flags2 |= SMBFLG2_ERR_STATUS;
-	}
-	if (ses->capabilities & CAP_DFS) {
+
+	if (ses->capabilities & CAP_DFS)
 		smb_buffer->Flags2 |= SMBFLG2_DFS;
-	}
+
 	if (ses->capabilities & CAP_UNICODE) {
 		smb_buffer->Flags2 |= SMBFLG2_UNICODE;
 		length =
diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c
index 580a27a3a7e6..89333d9bce36 100644
--- a/fs/smb/client/dir.c
+++ b/fs/smb/client/dir.c
@@ -680,9 +680,10 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
 		 full_path, d_inode(direntry));
 
 again:
-	if (pTcon->posix_extensions)
-		rc = smb311_posix_get_inode_info(&newInode, full_path, parent_dir_inode->i_sb, xid);
-	else if (pTcon->unix_ext) {
+	if (pTcon->posix_extensions) {
+		rc = smb311_posix_get_inode_info(&newInode, full_path, NULL,
+						 parent_dir_inode->i_sb, xid);
+	} else if (pTcon->unix_ext) {
 		rc = cifs_get_inode_info_unix(&newInode, full_path,
 					      parent_dir_inode->i_sb, xid);
 	} else {
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index cf17e3dd703e..1b4262aff8fa 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -1020,14 +1020,16 @@ reopen_success:
 		if (!is_interrupt_error(rc))
 			mapping_set_error(inode->i_mapping, rc);
 
-		if (tcon->posix_extensions)
-			rc = smb311_posix_get_inode_info(&inode, full_path, inode->i_sb, xid);
-		else if (tcon->unix_ext)
+		if (tcon->posix_extensions) {
+			rc = smb311_posix_get_inode_info(&inode, full_path,
+							 NULL, inode->i_sb, xid);
+		} else if (tcon->unix_ext) {
 			rc = cifs_get_inode_info_unix(&inode, full_path,
 						      inode->i_sb, xid);
-		else
+		} else {
 			rc = cifs_get_inode_info(&inode, full_path, NULL,
 						 inode->i_sb, xid, NULL);
+		}
 	}
 	/*
 	 * Else we are writing out data to server already and could deadlock if
@@ -2706,8 +2708,7 @@ static void cifs_extend_writeback(struct address_space *mapping,
 			 */
 			if (!folio_clear_dirty_for_io(folio))
 				WARN_ON(1);
-			if (folio_start_writeback(folio))
-				WARN_ON(1);
+			folio_start_writeback(folio);
 
 			*_count -= folio_nr_pages(folio);
 			folio_unlock(folio);
@@ -2742,8 +2743,7 @@ static ssize_t cifs_write_back_from_locked_folio(struct address_space *mapping,
 	int rc;
 
 	/* The folio should be locked, dirty and not undergoing writeback. */
-	if (folio_start_writeback(folio))
-		WARN_ON(1);
+	folio_start_writeback(folio);
 
 	count -= folio_nr_pages(folio);
 	len = folio_size(folio);
@@ -4671,7 +4671,7 @@ static int cifs_readpage_worker(struct file *file, struct page *page,
 	/* we do not want atime to be less than mtime, it broke some apps */
 	atime = inode_set_atime_to_ts(inode, current_time(inode));
 	mtime = inode_get_mtime(inode);
-	if (timespec64_compare(&atime, &mtime))
+	if (timespec64_compare(&atime, &mtime) < 0)
 		inode_set_atime_to_ts(inode, inode_get_mtime(inode));
 
 	if (PAGE_SIZE > rc)
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index 86fbd3f847d6..9f37c1758f73 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -182,6 +182,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
 		inode->i_mode = fattr->cf_mode;
 
 	cifs_i->cifsAttrs = fattr->cf_cifsattrs;
+	cifs_i->reparse_tag = fattr->cf_cifstag;
 
 	if (fattr->cf_flags & CIFS_FATTR_NEED_REVAL)
 		cifs_i->time = 0;
@@ -209,7 +210,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
 		inode->i_blocks = (512 - 1 + fattr->cf_bytes) >> 9;
 	}
 
-	if (S_ISLNK(fattr->cf_mode)) {
+	if (S_ISLNK(fattr->cf_mode) && fattr->cf_symlink_target) {
 		kfree(cifs_i->symlink_target);
 		cifs_i->symlink_target = fattr->cf_symlink_target;
 		fattr->cf_symlink_target = NULL;
@@ -459,8 +460,7 @@ static int cifs_get_unix_fattr(const unsigned char *full_path,
 			return -EOPNOTSUPP;
 		rc = server->ops->query_symlink(xid, tcon,
 						cifs_sb, full_path,
-						&fattr->cf_symlink_target,
-						NULL);
+						&fattr->cf_symlink_target);
 		cifs_dbg(FYI, "%s: query_symlink: %d\n", __func__, rc);
 	}
 	return rc;
@@ -692,29 +692,36 @@ static void smb311_posix_info_to_fattr(struct cifs_fattr *fattr,
 		fattr->cf_mtime.tv_sec += tcon->ses->server->timeAdj;
 	}
 
+	/*
+	 * The srv fs device id is overridden on network mount so setting
+	 * @fattr->cf_rdev isn't needed here.
+	 */
 	fattr->cf_eof = le64_to_cpu(info->EndOfFile);
 	fattr->cf_bytes = le64_to_cpu(info->AllocationSize);
 	fattr->cf_createtime = le64_to_cpu(info->CreationTime);
-
 	fattr->cf_nlink = le32_to_cpu(info->HardLinks);
 	fattr->cf_mode = (umode_t) le32_to_cpu(info->Mode);
-	/* The srv fs device id is overridden on network mount so setting rdev isn't needed here */
-	/* fattr->cf_rdev = le32_to_cpu(info->DeviceId); */
 
-	if (data->symlink) {
-		fattr->cf_mode |= S_IFLNK;
-		fattr->cf_dtype = DT_LNK;
-		fattr->cf_symlink_target = data->symlink_target;
-		data->symlink_target = NULL;
-	} else if (fattr->cf_cifsattrs & ATTR_DIRECTORY) {
+	if (cifs_open_data_reparse(data) &&
+	    cifs_reparse_point_to_fattr(cifs_sb, fattr, data))
+		goto out_reparse;
+
+	fattr->cf_mode &= ~S_IFMT;
+	if (fattr->cf_cifsattrs & ATTR_DIRECTORY) {
 		fattr->cf_mode |= S_IFDIR;
 		fattr->cf_dtype = DT_DIR;
 	} else { /* file */
 		fattr->cf_mode |= S_IFREG;
 		fattr->cf_dtype = DT_REG;
 	}
-	/* else if reparse point ... TODO: add support for FIFO and blk dev; special file types */
 
+out_reparse:
+	if (S_ISLNK(fattr->cf_mode)) {
+		if (likely(data->symlink_target))
+			fattr->cf_eof = strnlen(data->symlink_target, PATH_MAX);
+		fattr->cf_symlink_target = data->symlink_target;
+		data->symlink_target = NULL;
+	}
 	sid_to_id(cifs_sb, owner, fattr, SIDOWNER);
 	sid_to_id(cifs_sb, group, fattr, SIDGROUP);
 
@@ -722,35 +729,76 @@ static void smb311_posix_info_to_fattr(struct cifs_fattr *fattr,
 		fattr->cf_mode, fattr->cf_uniqueid, fattr->cf_nlink);
 }
 
+static inline dev_t nfs_mkdev(struct reparse_posix_data *buf)
+{
+	u64 v = le64_to_cpu(*(__le64 *)buf->DataBuffer);
+
+	return MKDEV(v >> 32, v & 0xffffffff);
+}
+
 bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb,
 				 struct cifs_fattr *fattr,
-				 u32 tag)
+				 struct cifs_open_info_data *data)
 {
+	struct reparse_posix_data *buf = data->reparse.posix;
+	u32 tag = data->reparse.tag;
+
+	if (tag == IO_REPARSE_TAG_NFS && buf) {
+		switch (le64_to_cpu(buf->InodeType)) {
+		case NFS_SPECFILE_CHR:
+			fattr->cf_mode |= S_IFCHR;
+			fattr->cf_dtype = DT_CHR;
+			fattr->cf_rdev = nfs_mkdev(buf);
+			break;
+		case NFS_SPECFILE_BLK:
+			fattr->cf_mode |= S_IFBLK;
+			fattr->cf_dtype = DT_BLK;
+			fattr->cf_rdev = nfs_mkdev(buf);
+			break;
+		case NFS_SPECFILE_FIFO:
+			fattr->cf_mode |= S_IFIFO;
+			fattr->cf_dtype = DT_FIFO;
+			break;
+		case NFS_SPECFILE_SOCK:
+			fattr->cf_mode |= S_IFSOCK;
+			fattr->cf_dtype = DT_SOCK;
+			break;
+		case NFS_SPECFILE_LNK:
+			fattr->cf_mode |= S_IFLNK;
+			fattr->cf_dtype = DT_LNK;
+			break;
+		default:
+			WARN_ON_ONCE(1);
+			return false;
+		}
+		return true;
+	}
+
 	switch (tag) {
 	case IO_REPARSE_TAG_LX_SYMLINK:
-		fattr->cf_mode |= S_IFLNK | cifs_sb->ctx->file_mode;
+		fattr->cf_mode |= S_IFLNK;
 		fattr->cf_dtype = DT_LNK;
 		break;
 	case IO_REPARSE_TAG_LX_FIFO:
-		fattr->cf_mode |= S_IFIFO | cifs_sb->ctx->file_mode;
+		fattr->cf_mode |= S_IFIFO;
 		fattr->cf_dtype = DT_FIFO;
 		break;
 	case IO_REPARSE_TAG_AF_UNIX:
-		fattr->cf_mode |= S_IFSOCK | cifs_sb->ctx->file_mode;
+		fattr->cf_mode |= S_IFSOCK;
 		fattr->cf_dtype = DT_SOCK;
 		break;
 	case IO_REPARSE_TAG_LX_CHR:
-		fattr->cf_mode |= S_IFCHR | cifs_sb->ctx->file_mode;
+		fattr->cf_mode |= S_IFCHR;
 		fattr->cf_dtype = DT_CHR;
 		break;
 	case IO_REPARSE_TAG_LX_BLK:
-		fattr->cf_mode |= S_IFBLK | cifs_sb->ctx->file_mode;
+		fattr->cf_mode |= S_IFBLK;
 		fattr->cf_dtype = DT_BLK;
 		break;
 	case 0: /* SMB1 symlink */
 	case IO_REPARSE_TAG_SYMLINK:
 	case IO_REPARSE_TAG_NFS:
-		fattr->cf_mode = S_IFLNK;
+		fattr->cf_mode |= S_IFLNK;
 		fattr->cf_dtype = DT_LNK;
 		break;
 	default:
@@ -790,8 +838,9 @@ static void cifs_open_info_to_fattr(struct cifs_fattr *fattr,
 	fattr->cf_createtime = le64_to_cpu(info->CreationTime);
 	fattr->cf_nlink = le32_to_cpu(info->NumberOfLinks);
 
+	fattr->cf_mode = cifs_sb->ctx->file_mode;
 	if (cifs_open_data_reparse(data) &&
-	    cifs_reparse_point_to_fattr(cifs_sb, fattr, data->reparse_tag))
+	    cifs_reparse_point_to_fattr(cifs_sb, fattr, data))
 		goto out_reparse;
 
 	if (fattr->cf_cifsattrs & ATTR_DIRECTORY) {
@@ -825,6 +874,8 @@ static void cifs_open_info_to_fattr(struct cifs_fattr *fattr,
 
 out_reparse:
 	if (S_ISLNK(fattr->cf_mode)) {
+		if (likely(data->symlink_target))
+			fattr->cf_eof = strnlen(data->symlink_target, PATH_MAX);
 		fattr->cf_symlink_target = data->symlink_target;
 		data->symlink_target = NULL;
 	}
@@ -856,7 +907,7 @@ cifs_get_file_info(struct file *filp)
 		data.adjust_tz = false;
 		if (data.symlink_target) {
 			data.symlink = true;
-			data.reparse_tag = IO_REPARSE_TAG_SYMLINK;
+			data.reparse.tag = IO_REPARSE_TAG_SYMLINK;
 		}
 		cifs_open_info_to_fattr(&fattr, &data, inode->i_sb);
 		break;
@@ -1019,13 +1070,15 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data,
 				 const unsigned int xid,
 				 struct cifs_tcon *tcon,
 				 const char *full_path,
-				 struct cifs_fattr *fattr)
+				 struct cifs_fattr *fattr,
+				 struct cifs_sid *owner,
+				 struct cifs_sid *group)
 {
 	struct TCP_Server_Info *server = tcon->ses->server;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 	struct kvec rsp_iov, *iov = NULL;
 	int rsp_buftype = CIFS_NO_BUFFER;
-	u32 tag = data->reparse_tag;
+	u32 tag = data->reparse.tag;
 	int rc = 0;
 
 	if (!tag && server->ops->query_reparse_point) {
@@ -1034,27 +1087,41 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data,
 						      &rsp_iov, &rsp_buftype);
 		if (!rc)
 			iov = &rsp_iov;
+	} else if (data->reparse.io.buftype != CIFS_NO_BUFFER &&
+		   data->reparse.io.iov.iov_base) {
+		iov = &data->reparse.io.iov;
 	}
-	switch ((data->reparse_tag = tag)) {
+
+	rc = -EOPNOTSUPP;
+	switch ((data->reparse.tag = tag)) {
 	case 0: /* SMB1 symlink */
-		iov = NULL;
-		fallthrough;
-	case IO_REPARSE_TAG_NFS:
-	case IO_REPARSE_TAG_SYMLINK:
-		if (!data->symlink_target && server->ops->query_symlink) {
+		if (server->ops->query_symlink) {
 			rc = server->ops->query_symlink(xid, tcon,
 							cifs_sb, full_path,
-							&data->symlink_target,
-							iov);
+							&data->symlink_target);
 		}
 		break;
 	case IO_REPARSE_TAG_MOUNT_POINT:
 		cifs_create_junction_fattr(fattr, sb);
+		rc = 0;
 		goto out;
+	default:
+		/* Check for cached reparse point data */
+		if (data->symlink_target || data->reparse.buf) {
+			rc = 0;
+		} else if (iov && server->ops->parse_reparse_point) {
+			rc = server->ops->parse_reparse_point(cifs_sb,
+							      iov, data);
+		}
+		break;
 	}
 
-	cifs_open_info_to_fattr(fattr, data, sb);
+	if (tcon->posix_extensions)
+		smb311_posix_info_to_fattr(fattr, data, owner, group, sb);
+	else
+		cifs_open_info_to_fattr(fattr, data, sb);
 out:
+	fattr->cf_cifstag = data->reparse.tag;
 	free_rsp_buf(rsp_buftype, rsp_iov.iov_base);
 	return rc;
 }
@@ -1104,7 +1171,8 @@ static int cifs_get_fattr(struct cifs_open_info_data *data,
 		 */
 		if (cifs_open_data_reparse(data)) {
 			rc = reparse_info_to_fattr(data, sb, xid, tcon,
-						   full_path, fattr);
+						   full_path, fattr,
+						   NULL, NULL);
 		} else {
 			cifs_open_info_to_fattr(fattr, data, sb);
 		}
@@ -1242,18 +1310,19 @@ out:
 	return rc;
 }
 
-static int smb311_posix_get_fattr(struct cifs_fattr *fattr,
+static int smb311_posix_get_fattr(struct cifs_open_info_data *data,
+				  struct cifs_fattr *fattr,
 				  const char *full_path,
 				  struct super_block *sb,
 				  const unsigned int xid)
 {
-	struct cifs_open_info_data data = {};
+	struct cifs_open_info_data tmp_data = {};
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 	struct cifs_tcon *tcon;
 	struct tcon_link *tlink;
 	struct cifs_sid owner, group;
 	int tmprc;
-	int rc;
+	int rc = 0;
 
 	tlink = cifs_sb_tlink(cifs_sb);
 	if (IS_ERR(tlink))
@@ -1261,12 +1330,14 @@ static int smb311_posix_get_fattr(struct cifs_fattr *fattr,
 	tcon = tlink_tcon(tlink);
 
 	/*
-	 * 1. Fetch file metadata
+	 * 1. Fetch file metadata if not provided (data)
 	 */
-
-	rc = smb311_posix_query_path_info(xid, tcon, cifs_sb,
-					  full_path, &data,
-					  &owner, &group);
+	if (!data) {
+		rc = smb311_posix_query_path_info(xid, tcon, cifs_sb,
+						  full_path, &tmp_data,
+						  &owner, &group);
+		data = &tmp_data;
+	}
 
 	/*
 	 * 2. Convert it to internal cifs metadata (fattr)
@@ -1274,7 +1345,14 @@ static int smb311_posix_get_fattr(struct cifs_fattr *fattr,
 
 	switch (rc) {
 	case 0:
-		smb311_posix_info_to_fattr(fattr, &data, &owner, &group, sb);
+		if (cifs_open_data_reparse(data)) {
+			rc = reparse_info_to_fattr(data, sb, xid, tcon,
+						   full_path, fattr,
+						   &owner, &group);
+		} else {
+			smb311_posix_info_to_fattr(fattr, data,
+						   &owner, &group, sb);
+		}
 		break;
 	case -EREMOTE:
 		/* DFS link, no metadata available on this server */
@@ -1305,12 +1383,15 @@ static int smb311_posix_get_fattr(struct cifs_fattr *fattr,
 
 out:
 	cifs_put_tlink(tlink);
-	cifs_free_open_info(&data);
+	cifs_free_open_info(data);
 	return rc;
 }
 
-int smb311_posix_get_inode_info(struct inode **inode, const char *full_path,
-				struct super_block *sb, const unsigned int xid)
+int smb311_posix_get_inode_info(struct inode **inode,
+				const char *full_path,
+				struct cifs_open_info_data *data,
+				struct super_block *sb,
+				const unsigned int xid)
 {
 	struct cifs_fattr fattr = {};
 	int rc;
@@ -1320,7 +1401,7 @@ int smb311_posix_get_inode_info(struct inode **inode, const char *full_path,
 		return 0;
 	}
 
-	rc = smb311_posix_get_fattr(&fattr, full_path, sb, xid);
+	rc = smb311_posix_get_fattr(data, &fattr, full_path, sb, xid);
 	if (rc)
 		goto out;
 
@@ -1468,7 +1549,7 @@ struct inode *cifs_root_iget(struct super_block *sb)
 
 	convert_delimiter(path, CIFS_DIR_SEP(cifs_sb));
 	if (tcon->posix_extensions)
-		rc = smb311_posix_get_fattr(&fattr, path, sb, xid);
+		rc = smb311_posix_get_fattr(NULL, &fattr, path, sb, xid);
 	else
 		rc = cifs_get_fattr(NULL, sb, xid, NULL, &fattr, &inode, path);
 
@@ -1841,16 +1922,18 @@ cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode,
 	int rc = 0;
 	struct inode *inode = NULL;
 
-	if (tcon->posix_extensions)
-		rc = smb311_posix_get_inode_info(&inode, full_path, parent->i_sb, xid);
+	if (tcon->posix_extensions) {
+		rc = smb311_posix_get_inode_info(&inode, full_path,
+						 NULL, parent->i_sb, xid);
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
-	else if (tcon->unix_ext)
+	} else if (tcon->unix_ext) {
 		rc = cifs_get_inode_info_unix(&inode, full_path, parent->i_sb,
 					      xid);
 #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
-	else
+	} else {
 		rc = cifs_get_inode_info(&inode, full_path, NULL, parent->i_sb,
 					 xid, NULL);
+	}
 
 	if (rc)
 		return rc;
@@ -2171,7 +2254,8 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry,
 		return -ENOSYS;
 
 	/* try path-based rename first */
-	rc = server->ops->rename(xid, tcon, from_path, to_path, cifs_sb);
+	rc = server->ops->rename(xid, tcon, from_dentry,
+				 from_path, to_path, cifs_sb);
 
 	/*
 	 * Don't bother with rename by filehandle unless file is busy and
@@ -2531,13 +2615,15 @@ int cifs_revalidate_dentry_attr(struct dentry *dentry)
 		 dentry, cifs_get_time(dentry), jiffies);
 
 again:
-	if (cifs_sb_master_tcon(CIFS_SB(sb))->posix_extensions)
-		rc = smb311_posix_get_inode_info(&inode, full_path, sb, xid);
-	else if (cifs_sb_master_tcon(CIFS_SB(sb))->unix_ext)
+	if (cifs_sb_master_tcon(CIFS_SB(sb))->posix_extensions) {
+		rc = smb311_posix_get_inode_info(&inode, full_path,
+						 NULL, sb, xid);
+	} else if (cifs_sb_master_tcon(CIFS_SB(sb))->unix_ext) {
 		rc = cifs_get_inode_info_unix(&inode, full_path, sb, xid);
-	else
+	} else {
 		rc = cifs_get_inode_info(&inode, full_path, NULL, sb,
 					 xid, NULL);
+	}
 	if (rc == -EAGAIN && count++ < 10)
 		goto again;
 out:
diff --git a/fs/smb/client/link.c b/fs/smb/client/link.c
index a1da50e66fbb..d86da949a919 100644
--- a/fs/smb/client/link.c
+++ b/fs/smb/client/link.c
@@ -510,8 +510,8 @@ cifs_hardlink(struct dentry *old_file, struct inode *inode,
 			rc = -ENOSYS;
 			goto cifs_hl_exit;
 		}
-		rc = server->ops->create_hardlink(xid, tcon, from_name, to_name,
-						  cifs_sb);
+		rc = server->ops->create_hardlink(xid, tcon, old_file,
+						  from_name, to_name, cifs_sb);
 		if ((rc == -EIO) || (rc == -EINVAL))
 			rc = -EOPNOTSUPP;
 	}
@@ -569,6 +569,7 @@ cifs_symlink(struct mnt_idmap *idmap, struct inode *inode,
 	int rc = -EOPNOTSUPP;
 	unsigned int xid;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct TCP_Server_Info *server;
 	struct tcon_link *tlink;
 	struct cifs_tcon *pTcon;
 	const char *full_path;
@@ -590,6 +591,7 @@ cifs_symlink(struct mnt_idmap *idmap, struct inode *inode,
 		goto symlink_exit;
 	}
 	pTcon = tlink_tcon(tlink);
+	server = cifs_pick_channel(pTcon->ses);
 
 	full_path = build_path_from_dentry(direntry, page);
 	if (IS_ERR(full_path)) {
@@ -601,27 +603,32 @@ cifs_symlink(struct mnt_idmap *idmap, struct inode *inode,
 	cifs_dbg(FYI, "symname is %s\n", symname);
 
 	/* BB what if DFS and this volume is on different share? BB */
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS)
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) {
 		rc = create_mf_symlink(xid, pTcon, cifs_sb, full_path, symname);
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
-	else if (pTcon->unix_ext)
+	} else if (pTcon->unix_ext) {
 		rc = CIFSUnixCreateSymLink(xid, pTcon, full_path, symname,
 					   cifs_sb->local_nls,
 					   cifs_remap(cifs_sb));
 #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
-	/* else
-	   rc = CIFSCreateReparseSymLink(xid, pTcon, fromName, toName,
-					cifs_sb_target->local_nls); */
+	} else if (server->ops->create_reparse_symlink) {
+		rc =  server->ops->create_reparse_symlink(xid, inode, direntry,
+							  pTcon, full_path,
+							  symname);
+		goto symlink_exit;
+	}
 
 	if (rc == 0) {
-		if (pTcon->posix_extensions)
-			rc = smb311_posix_get_inode_info(&newinode, full_path, inode->i_sb, xid);
-		else if (pTcon->unix_ext)
+		if (pTcon->posix_extensions) {
+			rc = smb311_posix_get_inode_info(&newinode, full_path,
+							 NULL, inode->i_sb, xid);
+		} else if (pTcon->unix_ext) {
 			rc = cifs_get_inode_info_unix(&newinode, full_path,
 						      inode->i_sb, xid);
-		else
+		} else {
 			rc = cifs_get_inode_info(&newinode, full_path, NULL,
 						 inode->i_sb, xid, NULL);
+		}
 
 		if (rc != 0) {
 			cifs_dbg(FYI, "Create symlink ok, getinodeinfo fail rc = %d\n",
diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c
index 35b176457bbe..c2137ea3c253 100644
--- a/fs/smb/client/misc.c
+++ b/fs/smb/client/misc.c
@@ -363,6 +363,10 @@ checkSMB(char *buf, unsigned int total_read, struct TCP_Server_Info *server)
 			cifs_dbg(VFS, "Length less than smb header size\n");
 		}
 		return -EIO;
+	} else if (total_read < sizeof(*smb) + 2 * smb->WordCount) {
+		cifs_dbg(VFS, "%s: can't read BCC due to invalid WordCount(%u)\n",
+			 __func__, smb->WordCount);
+		return -EIO;
 	}
 
 	/* otherwise, there is enough to get to the BCC */
diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c
index 47fc22de8d20..056cae1ddcce 100644
--- a/fs/smb/client/readdir.c
+++ b/fs/smb/client/readdir.c
@@ -56,6 +56,23 @@ static inline void dump_cifs_file_struct(struct file *file, char *label)
 #endif /* DEBUG2 */
 
 /*
+ * Match a reparse point inode if reparse tag and ctime haven't changed.
+ *
+ * Windows Server updates ctime of reparse points when their data have changed.
+ * The server doesn't allow changing reparse tags from existing reparse points,
+ * though it's worth checking.
+ */
+static inline bool reparse_inode_match(struct inode *inode,
+				       struct cifs_fattr *fattr)
+{
+	struct timespec64 ctime = inode_get_ctime(inode);
+
+	return (CIFS_I(inode)->cifsAttrs & ATTR_REPARSE) &&
+		CIFS_I(inode)->reparse_tag == fattr->cf_cifstag &&
+		timespec64_equal(&ctime, &fattr->cf_ctime);
+}
+
+/*
  * Attempt to preload the dcache with the results from the FIND_FIRST/NEXT
  *
  * Find the dentry that matches "name". If there isn't one, create one. If it's
@@ -71,6 +88,7 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name,
 	struct super_block *sb = parent->d_sb;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+	int rc;
 
 	cifs_dbg(FYI, "%s: for %s\n", __func__, name->name);
 
@@ -82,9 +100,11 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name,
 		 * We'll end up doing an on the wire call either way and
 		 * this spares us an invalidation.
 		 */
-		if (fattr->cf_flags & CIFS_FATTR_NEED_REVAL)
-			return;
 retry:
+		if ((fattr->cf_cifsattrs & ATTR_REPARSE) ||
+		    (fattr->cf_flags & CIFS_FATTR_NEED_REVAL))
+			return;
+
 		dentry = d_alloc_parallel(parent, name, &wq);
 	}
 	if (IS_ERR(dentry))
@@ -104,12 +124,34 @@ retry:
 			if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM))
 				fattr->cf_uniqueid = CIFS_I(inode)->uniqueid;
 
-			/* update inode in place
-			 * if both i_ino and i_mode didn't change */
-			if (CIFS_I(inode)->uniqueid == fattr->cf_uniqueid &&
-			    cifs_fattr_to_inode(inode, fattr) == 0) {
-				dput(dentry);
-				return;
+			/*
+			 * Update inode in place if both i_ino and i_mode didn't
+			 * change.
+			 */
+			if (CIFS_I(inode)->uniqueid == fattr->cf_uniqueid) {
+				/*
+				 * Query dir responses don't provide enough
+				 * information about reparse points other than
+				 * their reparse tags.  Save an invalidation by
+				 * not clobbering the existing mode, size and
+				 * symlink target (if any) when reparse tag and
+				 * ctime haven't changed.
+				 */
+				rc = 0;
+				if (fattr->cf_cifsattrs & ATTR_REPARSE) {
+					if (likely(reparse_inode_match(inode, fattr))) {
+						fattr->cf_mode = inode->i_mode;
+						fattr->cf_eof = CIFS_I(inode)->server_eof;
+						fattr->cf_symlink_target = NULL;
+					} else {
+						CIFS_I(inode)->time = 0;
+						rc = -ESTALE;
+					}
+				}
+				if (!rc && !cifs_fattr_to_inode(inode, fattr)) {
+					dput(dentry);
+					return;
+				}
 			}
 		}
 		d_invalidate(dentry);
@@ -127,32 +169,13 @@ retry:
 	dput(dentry);
 }
 
-static bool reparse_file_needs_reval(const struct cifs_fattr *fattr)
-{
-	if (!(fattr->cf_cifsattrs & ATTR_REPARSE))
-		return false;
-	/*
-	 * The DFS tags should be only intepreted by server side as per
-	 * MS-FSCC 2.1.2.1, but let's include them anyway.
-	 *
-	 * Besides, if cf_cifstag is unset (0), then we still need it to be
-	 * revalidated to know exactly what reparse point it is.
-	 */
-	switch (fattr->cf_cifstag) {
-	case IO_REPARSE_TAG_DFS:
-	case IO_REPARSE_TAG_DFSR:
-	case IO_REPARSE_TAG_SYMLINK:
-	case IO_REPARSE_TAG_NFS:
-	case IO_REPARSE_TAG_MOUNT_POINT:
-	case 0:
-		return true;
-	}
-	return false;
-}
-
 static void
 cifs_fill_common_info(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb)
 {
+	struct cifs_open_info_data data = {
+		.reparse = { .tag = fattr->cf_cifstag, },
+	};
+
 	fattr->cf_uid = cifs_sb->ctx->linux_uid;
 	fattr->cf_gid = cifs_sb->ctx->linux_gid;
 
@@ -165,7 +188,7 @@ cifs_fill_common_info(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb)
 	 * reasonably map some of them to directories vs. files vs. symlinks
 	 */
 	if ((fattr->cf_cifsattrs & ATTR_REPARSE) &&
-	    cifs_reparse_point_to_fattr(cifs_sb, fattr, fattr->cf_cifstag))
+	    cifs_reparse_point_to_fattr(cifs_sb, fattr, &data))
 		goto out_reparse;
 
 	if (fattr->cf_cifsattrs & ATTR_DIRECTORY) {
@@ -177,14 +200,6 @@ cifs_fill_common_info(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb)
 	}
 
 out_reparse:
-	/*
-	 * We need to revalidate it further to make a decision about whether it
-	 * is a symbolic link, DFS referral or a reparse point with a direct
-	 * access like junctions, deduplicated files, NFS symlinks.
-	 */
-	if (reparse_file_needs_reval(fattr))
-		fattr->cf_flags |= CIFS_FATTR_NEED_REVAL;
-
 	/* non-unix readdir doesn't provide nlink */
 	fattr->cf_flags |= CIFS_FATTR_UNKNOWN_NLINK;
 
@@ -265,9 +280,6 @@ cifs_posix_to_fattr(struct cifs_fattr *fattr, struct smb2_posix_info *info,
 		fattr->cf_dtype = DT_REG;
 	}
 
-	if (reparse_file_needs_reval(fattr))
-		fattr->cf_flags |= CIFS_FATTR_NEED_REVAL;
-
 	sid_to_id(cifs_sb, &parsed.owner, fattr, SIDOWNER);
 	sid_to_id(cifs_sb, &parsed.group, fattr, SIDGROUP);
 }
@@ -327,38 +339,6 @@ cifs_std_info_to_fattr(struct cifs_fattr *fattr, FIND_FILE_STANDARD_INFO *info,
 	cifs_fill_common_info(fattr, cifs_sb);
 }
 
-/* BB eventually need to add the following helper function to
-      resolve NT_STATUS_STOPPED_ON_SYMLINK return code when
-      we try to do FindFirst on (NTFS) directory symlinks */
-/*
-int get_symlink_reparse_path(char *full_path, struct cifs_sb_info *cifs_sb,
-			     unsigned int xid)
-{
-	__u16 fid;
-	int len;
-	int oplock = 0;
-	int rc;
-	struct cifs_tcon *ptcon = cifs_sb_tcon(cifs_sb);
-	char *tmpbuffer;
-
-	rc = CIFSSMBOpen(xid, ptcon, full_path, FILE_OPEN, GENERIC_READ,
-			OPEN_REPARSE_POINT, &fid, &oplock, NULL,
-			cifs_sb->local_nls,
-			cifs_remap(cifs_sb);
-	if (!rc) {
-		tmpbuffer = kmalloc(maxpath);
-		rc = CIFSSMBQueryReparseLinkInfo(xid, ptcon, full_path,
-				tmpbuffer,
-				maxpath -1,
-				fid,
-				cifs_sb->local_nls);
-		if (CIFSSMBClose(xid, ptcon, fid)) {
-			cifs_dbg(FYI, "Error closing temporary reparsepoint open\n");
-		}
-	}
-}
- */
-
 static int
 _initiate_cifs_search(const unsigned int xid, struct file *file,
 		     const char *full_path)
@@ -427,13 +407,10 @@ ffirst_retry:
 					  &cifsFile->fid, search_flags,
 					  &cifsFile->srch_inf);
 
-	if (rc == 0)
+	if (rc == 0) {
 		cifsFile->invalidHandle = false;
-	/* BB add following call to handle readdir on new NTFS symlink errors
-	else if STATUS_STOPPED_ON_SYMLINK
-		call get_symlink_reparse_path and retry with new path */
-	else if ((rc == -EOPNOTSUPP) &&
-		(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)) {
+	} else if ((rc == -EOPNOTSUPP) &&
+		   (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)) {
 		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SERVER_INUM;
 		goto ffirst_retry;
 	}
diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c
index 0bb2ac929061..cde81042bebd 100644
--- a/fs/smb/client/sess.c
+++ b/fs/smb/client/sess.c
@@ -322,28 +322,32 @@ cifs_disable_secondary_channels(struct cifs_ses *ses)
 		iface = ses->chans[i].iface;
 		server = ses->chans[i].server;
 
+		/*
+		 * remove these references first, since we need to unlock
+		 * the chan_lock here, since iface_lock is a higher lock
+		 */
+		ses->chans[i].iface = NULL;
+		ses->chans[i].server = NULL;
+		spin_unlock(&ses->chan_lock);
+
 		if (iface) {
 			spin_lock(&ses->iface_lock);
-			kref_put(&iface->refcount, release_iface);
-			ses->chans[i].iface = NULL;
 			iface->num_channels--;
 			if (iface->weight_fulfilled)
 				iface->weight_fulfilled--;
+			kref_put(&iface->refcount, release_iface);
 			spin_unlock(&ses->iface_lock);
 		}
 
-		spin_unlock(&ses->chan_lock);
-		if (server && !server->terminate) {
-			server->terminate = true;
-			cifs_signal_cifsd_for_reconnect(server, false);
-		}
-		spin_lock(&ses->chan_lock);
-
 		if (server) {
-			ses->chans[i].server = NULL;
+			if (!server->terminate) {
+				server->terminate = true;
+				cifs_signal_cifsd_for_reconnect(server, false);
+			}
 			cifs_put_tcp_session(server, false);
 		}
 
+		spin_lock(&ses->chan_lock);
 	}
 
 done:
@@ -352,10 +356,9 @@ done:
 
 /*
  * update the iface for the channel if necessary.
- * will return 0 when iface is updated, 1 if removed, 2 otherwise
  * Must be called with chan_lock held.
  */
-int
+void
 cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server)
 {
 	unsigned int chan_index;
@@ -364,20 +367,19 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server)
 	struct cifs_server_iface *old_iface = NULL;
 	struct cifs_server_iface *last_iface = NULL;
 	struct sockaddr_storage ss;
-	int rc = 0;
 
 	spin_lock(&ses->chan_lock);
 	chan_index = cifs_ses_get_chan_index(ses, server);
 	if (chan_index == CIFS_INVAL_CHAN_INDEX) {
 		spin_unlock(&ses->chan_lock);
-		return 0;
+		return;
 	}
 
 	if (ses->chans[chan_index].iface) {
 		old_iface = ses->chans[chan_index].iface;
 		if (old_iface->is_active) {
 			spin_unlock(&ses->chan_lock);
-			return 1;
+			return;
 		}
 	}
 	spin_unlock(&ses->chan_lock);
@@ -390,7 +392,7 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server)
 	if (!ses->iface_count) {
 		spin_unlock(&ses->iface_lock);
 		cifs_dbg(VFS, "server %s does not advertise interfaces\n", ses->server->hostname);
-		return 0;
+		return;
 	}
 
 	last_iface = list_last_entry(&ses->iface_list, struct cifs_server_iface,
@@ -430,20 +432,25 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server)
 	}
 
 	if (list_entry_is_head(iface, &ses->iface_list, iface_head)) {
-		rc = 1;
 		iface = NULL;
 		cifs_dbg(FYI, "unable to find a suitable iface\n");
 	}
 
-	if (!chan_index && !iface) {
-		cifs_dbg(FYI, "unable to get the interface matching: %pIS\n",
-			 &ss);
+	if (!iface) {
+		if (!chan_index)
+			cifs_dbg(FYI, "unable to get the interface matching: %pIS\n",
+				 &ss);
+		else {
+			cifs_dbg(FYI, "unable to find another interface to replace: %pIS\n",
+				 &old_iface->sockaddr);
+		}
+
 		spin_unlock(&ses->iface_lock);
-		return 0;
+		return;
 	}
 
 	/* now drop the ref to the current iface */
-	if (old_iface && iface) {
+	if (old_iface) {
 		cifs_dbg(FYI, "replacing iface: %pIS with %pIS\n",
 			 &old_iface->sockaddr,
 			 &iface->sockaddr);
@@ -455,24 +462,12 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server)
 		iface->weight_fulfilled++;
 
 		kref_put(&old_iface->refcount, release_iface);
-	} else if (old_iface) {
-		cifs_dbg(FYI, "releasing ref to iface: %pIS\n",
-			 &old_iface->sockaddr);
-
-		old_iface->num_channels--;
-		if (old_iface->weight_fulfilled)
-			old_iface->weight_fulfilled--;
-
-		kref_put(&old_iface->refcount, release_iface);
 	} else if (!chan_index) {
 		/* special case: update interface for primary channel */
 		cifs_dbg(FYI, "referencing primary channel iface: %pIS\n",
 			 &iface->sockaddr);
 		iface->num_channels++;
 		iface->weight_fulfilled++;
-	} else {
-		WARN_ON(!iface);
-		cifs_dbg(FYI, "adding new iface: %pIS\n", &iface->sockaddr);
 	}
 	spin_unlock(&ses->iface_lock);
 
@@ -480,21 +475,11 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server)
 	chan_index = cifs_ses_get_chan_index(ses, server);
 	if (chan_index == CIFS_INVAL_CHAN_INDEX) {
 		spin_unlock(&ses->chan_lock);
-		return 0;
+		return;
 	}
 
 	ses->chans[chan_index].iface = iface;
-
-	/* No iface is found. if secondary chan, drop connection */
-	if (!iface && SERVER_IS_CHAN(server))
-		ses->chans[chan_index].server = NULL;
-
 	spin_unlock(&ses->chan_lock);
-
-	if (!iface && SERVER_IS_CHAN(server))
-		cifs_put_tcp_session(server, false);
-
-	return rc;
 }
 
 /*
diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c
index 9bf8735cdd1e..a9eaba8083b0 100644
--- a/fs/smb/client/smb1ops.c
+++ b/fs/smb/client/smb1ops.c
@@ -976,64 +976,37 @@ static int cifs_query_symlink(const unsigned int xid,
 			      struct cifs_tcon *tcon,
 			      struct cifs_sb_info *cifs_sb,
 			      const char *full_path,
-			      char **target_path,
-			      struct kvec *rsp_iov)
+			      char **target_path)
 {
 	int rc;
-	int oplock = 0;
-	bool is_reparse_point = !!rsp_iov;
-	struct cifs_fid fid;
-	struct cifs_open_parms oparms;
 
-	cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path);
+	cifs_tcon_dbg(FYI, "%s: path=%s\n", __func__, full_path);
 
-	if (is_reparse_point) {
-		cifs_dbg(VFS, "reparse points not handled for SMB1 symlinks\n");
+	if (!cap_unix(tcon->ses))
 		return -EOPNOTSUPP;
-	}
-
-	/* Check for unix extensions */
-	if (cap_unix(tcon->ses)) {
-		rc = CIFSSMBUnixQuerySymLink(xid, tcon, full_path, target_path,
-					     cifs_sb->local_nls,
-					     cifs_remap(cifs_sb));
-		if (rc == -EREMOTE)
-			rc = cifs_unix_dfs_readlink(xid, tcon, full_path,
-						    target_path,
-						    cifs_sb->local_nls);
-
-		goto out;
-	}
-
-	oparms = (struct cifs_open_parms) {
-		.tcon = tcon,
-		.cifs_sb = cifs_sb,
-		.desired_access = FILE_READ_ATTRIBUTES,
-		.create_options = cifs_create_options(cifs_sb,
-						      OPEN_REPARSE_POINT),
-		.disposition = FILE_OPEN,
-		.path = full_path,
-		.fid = &fid,
-	};
-
-	rc = CIFS_open(xid, &oparms, &oplock, NULL);
-	if (rc)
-		goto out;
-
-	rc = CIFSSMBQuerySymLink(xid, tcon, fid.netfid, target_path,
-				 cifs_sb->local_nls);
-	if (rc)
-		goto out_close;
 
-	convert_delimiter(*target_path, '/');
-out_close:
-	CIFSSMBClose(xid, tcon, fid.netfid);
-out:
-	if (!rc)
-		cifs_dbg(FYI, "%s: target path: %s\n", __func__, *target_path);
+	rc = CIFSSMBUnixQuerySymLink(xid, tcon, full_path, target_path,
+				     cifs_sb->local_nls, cifs_remap(cifs_sb));
+	if (rc == -EREMOTE)
+		rc = cifs_unix_dfs_readlink(xid, tcon, full_path,
+					    target_path, cifs_sb->local_nls);
 	return rc;
 }
 
+static int cifs_parse_reparse_point(struct cifs_sb_info *cifs_sb,
+				    struct kvec *rsp_iov,
+				    struct cifs_open_info_data *data)
+{
+	struct reparse_data_buffer *buf;
+	TRANSACT_IOCTL_RSP *io = rsp_iov->iov_base;
+	bool unicode = !!(io->hdr.Flags2 & SMBFLG2_UNICODE);
+	u32 plen = le16_to_cpu(io->ByteCount);
+
+	buf = (struct reparse_data_buffer *)((__u8 *)&io->hdr.Protocol +
+					     le32_to_cpu(io->DataOffset));
+	return parse_reparse_point(buf, plen, cifs_sb, unicode, data);
+}
+
 static bool
 cifs_is_read_op(__u32 oplock)
 {
@@ -1068,15 +1041,7 @@ cifs_make_node(unsigned int xid, struct inode *inode,
 {
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct inode *newinode = NULL;
-	int rc = -EPERM;
-	struct cifs_open_info_data buf = {};
-	struct cifs_io_parms io_parms;
-	__u32 oplock = 0;
-	struct cifs_fid fid;
-	struct cifs_open_parms oparms;
-	unsigned int bytes_written;
-	struct win_dev *pdev;
-	struct kvec iov[2];
+	int rc;
 
 	if (tcon->unix_ext) {
 		/*
@@ -1110,74 +1075,18 @@ cifs_make_node(unsigned int xid, struct inode *inode,
 			d_instantiate(dentry, newinode);
 		return rc;
 	}
-
 	/*
-	 * SMB1 SFU emulation: should work with all servers, but only
-	 * support block and char device (no socket & fifo)
+	 * Check if mounted with mount parm 'sfu' mount parm.
+	 * SFU emulation should work with all servers, but only
+	 * supports block and char device (no socket & fifo),
+	 * and was used by default in earlier versions of Windows
 	 */
 	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL))
-		return rc;
-
-	if (!S_ISCHR(mode) && !S_ISBLK(mode))
-		return rc;
-
-	cifs_dbg(FYI, "sfu compat create special file\n");
-
-	oparms = (struct cifs_open_parms) {
-		.tcon = tcon,
-		.cifs_sb = cifs_sb,
-		.desired_access = GENERIC_WRITE,
-		.create_options = cifs_create_options(cifs_sb, CREATE_NOT_DIR |
-						      CREATE_OPTION_SPECIAL),
-		.disposition = FILE_CREATE,
-		.path = full_path,
-		.fid = &fid,
-	};
-
-	if (tcon->ses->server->oplocks)
-		oplock = REQ_OPLOCK;
-	else
-		oplock = 0;
-	rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, &buf);
-	if (rc)
-		return rc;
-
-	/*
-	 * BB Do not bother to decode buf since no local inode yet to put
-	 * timestamps in, but we can reuse it safely.
-	 */
-
-	pdev = (struct win_dev *)&buf.fi;
-	io_parms.pid = current->tgid;
-	io_parms.tcon = tcon;
-	io_parms.offset = 0;
-	io_parms.length = sizeof(struct win_dev);
-	iov[1].iov_base = &buf.fi;
-	iov[1].iov_len = sizeof(struct win_dev);
-	if (S_ISCHR(mode)) {
-		memcpy(pdev->type, "IntxCHR", 8);
-		pdev->major = cpu_to_le64(MAJOR(dev));
-		pdev->minor = cpu_to_le64(MINOR(dev));
-		rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms,
-							&bytes_written, iov, 1);
-	} else if (S_ISBLK(mode)) {
-		memcpy(pdev->type, "IntxBLK", 8);
-		pdev->major = cpu_to_le64(MAJOR(dev));
-		pdev->minor = cpu_to_le64(MINOR(dev));
-		rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms,
-							&bytes_written, iov, 1);
-	}
-	tcon->ses->server->ops->close(xid, tcon, &fid);
-	d_drop(dentry);
-
-	/* FIXME: add code here to set EAs */
-
-	cifs_free_open_info(&buf);
-	return rc;
+		return -EPERM;
+	return cifs_sfu_make_node(xid, inode, dentry, tcon,
+				  full_path, mode, dev);
 }
 
-
-
 struct smb_version_operations smb1_operations = {
 	.send_cancel = send_nt_cancel,
 	.compare_fids = cifs_compare_fids,
@@ -1214,6 +1123,7 @@ struct smb_version_operations smb1_operations = {
 	.is_path_accessible = cifs_is_path_accessible,
 	.can_echo = cifs_can_echo,
 	.query_path_info = cifs_query_path_info,
+	.query_reparse_point = cifs_query_reparse_point,
 	.query_file_info = cifs_query_file_info,
 	.get_srv_inum = cifs_get_srv_inum,
 	.set_path_size = CIFSSMBSetEOF,
@@ -1229,6 +1139,7 @@ struct smb_version_operations smb1_operations = {
 	.rename = CIFSSMBRename,
 	.create_hardlink = CIFSCreateHardLink,
 	.query_symlink = cifs_query_symlink,
+	.parse_reparse_point = cifs_parse_reparse_point,
 	.open = cifs_open_file,
 	.set_fid = cifs_set_fid,
 	.close = cifs_close_file,
diff --git a/fs/smb/client/smb2glob.h b/fs/smb/client/smb2glob.h
index 82e916ad167c..a0c156996fc5 100644
--- a/fs/smb/client/smb2glob.h
+++ b/fs/smb/client/smb2glob.h
@@ -23,17 +23,21 @@
  * Identifiers for functions that use the open, operation, close pattern
  * in smb2inode.c:smb2_compound_op()
  */
-#define SMB2_OP_SET_DELETE 1
-#define SMB2_OP_SET_INFO 2
-#define SMB2_OP_QUERY_INFO 3
-#define SMB2_OP_QUERY_DIR 4
-#define SMB2_OP_MKDIR 5
-#define SMB2_OP_RENAME 6
-#define SMB2_OP_DELETE 7
-#define SMB2_OP_HARDLINK 8
-#define SMB2_OP_SET_EOF 9
-#define SMB2_OP_RMDIR 10
-#define SMB2_OP_POSIX_QUERY_INFO 11
+enum smb2_compound_ops {
+	SMB2_OP_SET_DELETE = 1,
+	SMB2_OP_SET_INFO,
+	SMB2_OP_QUERY_INFO,
+	SMB2_OP_QUERY_DIR,
+	SMB2_OP_MKDIR,
+	SMB2_OP_RENAME,
+	SMB2_OP_DELETE,
+	SMB2_OP_HARDLINK,
+	SMB2_OP_SET_EOF,
+	SMB2_OP_RMDIR,
+	SMB2_OP_POSIX_QUERY_INFO,
+	SMB2_OP_SET_REPARSE,
+	SMB2_OP_GET_REPARSE
+};
 
 /* Used when constructing chained read requests. */
 #define CHAINED_REQUEST 1
diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 0b89f7008ac0..5053a5550abe 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -26,13 +26,34 @@
 #include "cached_dir.h"
 #include "smb2status.h"
 
-static void
-free_set_inf_compound(struct smb_rqst *rqst)
+static struct reparse_data_buffer *reparse_buf_ptr(struct kvec *iov)
 {
-	if (rqst[1].rq_iov)
-		SMB2_set_info_free(&rqst[1]);
-	if (rqst[2].rq_iov)
-		SMB2_close_free(&rqst[2]);
+	struct reparse_data_buffer *buf;
+	struct smb2_ioctl_rsp *io = iov->iov_base;
+	u32 off, count, len;
+
+	count = le32_to_cpu(io->OutputCount);
+	off = le32_to_cpu(io->OutputOffset);
+	if (check_add_overflow(off, count, &len) || len > iov->iov_len)
+		return ERR_PTR(-EIO);
+
+	buf = (struct reparse_data_buffer *)((u8 *)io + off);
+	len = sizeof(*buf);
+	if (count < len || count < le16_to_cpu(buf->ReparseDataLength) + len)
+		return ERR_PTR(-EIO);
+	return buf;
+}
+
+static inline __u32 file_create_options(struct dentry *dentry)
+{
+	struct cifsInodeInfo *ci;
+
+	if (dentry) {
+		ci = CIFS_I(d_inode(dentry));
+		if (ci->cifsAttrs & ATTR_REPARSE)
+			return OPEN_REPARSE_POINT;
+	}
+	return 0;
 }
 
 /*
@@ -45,13 +66,16 @@ free_set_inf_compound(struct smb_rqst *rqst)
  */
 static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
 			    struct cifs_sb_info *cifs_sb, const char *full_path,
-			    __u32 desired_access, __u32 create_disposition, __u32 create_options,
-			    umode_t mode, void *ptr, int command, struct cifsFileInfo *cfile,
+			    __u32 desired_access, __u32 create_disposition,
+			    __u32 create_options, umode_t mode, struct kvec *in_iov,
+			    int *cmds, int num_cmds, struct cifsFileInfo *cfile,
 			    __u8 **extbuf, size_t *extbuflen,
 			    struct kvec *out_iov, int *out_buftype)
 {
+
+	struct reparse_data_buffer *rbuf;
 	struct smb2_compound_vars *vars = NULL;
-	struct kvec *rsp_iov;
+	struct kvec *rsp_iov, *iov;
 	struct smb_rqst *rqst;
 	int rc;
 	__le16 *utf16_path = NULL;
@@ -59,8 +83,8 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
 	struct cifs_fid fid;
 	struct cifs_ses *ses = tcon->ses;
 	struct TCP_Server_Info *server;
-	int num_rqst = 0;
-	int resp_buftype[3];
+	int num_rqst = 0, i;
+	int resp_buftype[MAX_COMPOUND];
 	struct smb2_query_info_rsp *qi_rsp = NULL;
 	struct cifs_open_info_data *idata;
 	int flags = 0;
@@ -80,7 +104,8 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
 	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
-	resp_buftype[0] = resp_buftype[1] = resp_buftype[2] = CIFS_NO_BUFFER;
+	for (i = 0; i < ARRAY_SIZE(resp_buftype); i++)
+		resp_buftype[i] = CIFS_NO_BUFFER;
 
 	/* We already have a handle so we can skip the open */
 	if (cfile)
@@ -118,242 +143,277 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
 	num_rqst++;
 	rc = 0;
 
-	/* Operation */
-	switch (command) {
-	case SMB2_OP_QUERY_INFO:
-		rqst[num_rqst].rq_iov = &vars->qi_iov;
-		rqst[num_rqst].rq_nvec = 1;
-
-		if (cfile)
-			rc = SMB2_query_info_init(tcon, server,
-				&rqst[num_rqst],
-				cfile->fid.persistent_fid,
-				cfile->fid.volatile_fid,
-				FILE_ALL_INFORMATION,
-				SMB2_O_INFO_FILE, 0,
-				sizeof(struct smb2_file_all_info) +
-					  PATH_MAX * 2, 0, NULL);
-		else {
-			rc = SMB2_query_info_init(tcon, server,
-				&rqst[num_rqst],
-				COMPOUND_FID,
-				COMPOUND_FID,
-				FILE_ALL_INFORMATION,
-				SMB2_O_INFO_FILE, 0,
-				sizeof(struct smb2_file_all_info) +
-					  PATH_MAX * 2, 0, NULL);
-			if (!rc) {
-				smb2_set_next_command(tcon, &rqst[num_rqst]);
-				smb2_set_related(&rqst[num_rqst]);
+	for (i = 0; i < num_cmds; i++) {
+		/* Operation */
+		switch (cmds[i]) {
+		case SMB2_OP_QUERY_INFO:
+			rqst[num_rqst].rq_iov = &vars->qi_iov;
+			rqst[num_rqst].rq_nvec = 1;
+
+			if (cfile) {
+				rc = SMB2_query_info_init(tcon, server,
+							  &rqst[num_rqst],
+							  cfile->fid.persistent_fid,
+							  cfile->fid.volatile_fid,
+							  FILE_ALL_INFORMATION,
+							  SMB2_O_INFO_FILE, 0,
+							  sizeof(struct smb2_file_all_info) +
+							  PATH_MAX * 2, 0, NULL);
+			} else {
+				rc = SMB2_query_info_init(tcon, server,
+							  &rqst[num_rqst],
+							  COMPOUND_FID,
+							  COMPOUND_FID,
+							  FILE_ALL_INFORMATION,
+							  SMB2_O_INFO_FILE, 0,
+							  sizeof(struct smb2_file_all_info) +
+							  PATH_MAX * 2, 0, NULL);
+				if (!rc) {
+					smb2_set_next_command(tcon, &rqst[num_rqst]);
+					smb2_set_related(&rqst[num_rqst]);
+				}
 			}
-		}
 
-		if (rc)
-			goto finished;
-		num_rqst++;
-		trace_smb3_query_info_compound_enter(xid, ses->Suid, tcon->tid,
-						     full_path);
-		break;
-	case SMB2_OP_POSIX_QUERY_INFO:
-		rqst[num_rqst].rq_iov = &vars->qi_iov;
-		rqst[num_rqst].rq_nvec = 1;
-
-		if (cfile)
-			rc = SMB2_query_info_init(tcon, server,
-				&rqst[num_rqst],
-				cfile->fid.persistent_fid,
-				cfile->fid.volatile_fid,
-				SMB_FIND_FILE_POSIX_INFO,
-				SMB2_O_INFO_FILE, 0,
+			if (rc)
+				goto finished;
+			num_rqst++;
+			trace_smb3_query_info_compound_enter(xid, ses->Suid,
+							     tcon->tid, full_path);
+			break;
+		case SMB2_OP_POSIX_QUERY_INFO:
+			rqst[num_rqst].rq_iov = &vars->qi_iov;
+			rqst[num_rqst].rq_nvec = 1;
+
+			if (cfile) {
 				/* TBD: fix following to allow for longer SIDs */
-				sizeof(struct smb311_posix_qinfo *) + (PATH_MAX * 2) +
-				(sizeof(struct cifs_sid) * 2), 0, NULL);
-		else {
-			rc = SMB2_query_info_init(tcon, server,
-				&rqst[num_rqst],
-				COMPOUND_FID,
-				COMPOUND_FID,
-				SMB_FIND_FILE_POSIX_INFO,
-				SMB2_O_INFO_FILE, 0,
-				sizeof(struct smb311_posix_qinfo *) + (PATH_MAX * 2) +
-				(sizeof(struct cifs_sid) * 2), 0, NULL);
-			if (!rc) {
-				smb2_set_next_command(tcon, &rqst[num_rqst]);
-				smb2_set_related(&rqst[num_rqst]);
+				rc = SMB2_query_info_init(tcon, server,
+							  &rqst[num_rqst],
+							  cfile->fid.persistent_fid,
+							  cfile->fid.volatile_fid,
+							  SMB_FIND_FILE_POSIX_INFO,
+							  SMB2_O_INFO_FILE, 0,
+							  sizeof(struct smb311_posix_qinfo *) +
+							  (PATH_MAX * 2) +
+							  (sizeof(struct cifs_sid) * 2), 0, NULL);
+			} else {
+				rc = SMB2_query_info_init(tcon, server,
+							  &rqst[num_rqst],
+							  COMPOUND_FID,
+							  COMPOUND_FID,
+							  SMB_FIND_FILE_POSIX_INFO,
+							  SMB2_O_INFO_FILE, 0,
+							  sizeof(struct smb311_posix_qinfo *) +
+							  (PATH_MAX * 2) +
+							  (sizeof(struct cifs_sid) * 2), 0, NULL);
+				if (!rc) {
+					smb2_set_next_command(tcon, &rqst[num_rqst]);
+					smb2_set_related(&rqst[num_rqst]);
+				}
 			}
-		}
 
-		if (rc)
-			goto finished;
-		num_rqst++;
-		trace_smb3_posix_query_info_compound_enter(xid, ses->Suid, tcon->tid, full_path);
-		break;
-	case SMB2_OP_DELETE:
-		trace_smb3_delete_enter(xid, ses->Suid, tcon->tid, full_path);
-		break;
-	case SMB2_OP_MKDIR:
-		/*
-		 * Directories are created through parameters in the
-		 * SMB2_open() call.
-		 */
-		trace_smb3_mkdir_enter(xid, ses->Suid, tcon->tid, full_path);
-		break;
-	case SMB2_OP_RMDIR:
-		rqst[num_rqst].rq_iov = &vars->si_iov[0];
-		rqst[num_rqst].rq_nvec = 1;
-
-		size[0] = 1; /* sizeof __u8 See MS-FSCC section 2.4.11 */
-		data[0] = &delete_pending[0];
-
-		rc = SMB2_set_info_init(tcon, server,
-					&rqst[num_rqst], COMPOUND_FID,
-					COMPOUND_FID, current->tgid,
-					FILE_DISPOSITION_INFORMATION,
-					SMB2_O_INFO_FILE, 0, data, size);
-		if (rc)
-			goto finished;
-		smb2_set_next_command(tcon, &rqst[num_rqst]);
-		smb2_set_related(&rqst[num_rqst++]);
-		trace_smb3_rmdir_enter(xid, ses->Suid, tcon->tid, full_path);
-		break;
-	case SMB2_OP_SET_EOF:
-		rqst[num_rqst].rq_iov = &vars->si_iov[0];
-		rqst[num_rqst].rq_nvec = 1;
+			if (rc)
+				goto finished;
+			num_rqst++;
+			trace_smb3_posix_query_info_compound_enter(xid, ses->Suid,
+								   tcon->tid, full_path);
+			break;
+		case SMB2_OP_DELETE:
+			trace_smb3_delete_enter(xid, ses->Suid, tcon->tid, full_path);
+			break;
+		case SMB2_OP_MKDIR:
+			/*
+			 * Directories are created through parameters in the
+			 * SMB2_open() call.
+			 */
+			trace_smb3_mkdir_enter(xid, ses->Suid, tcon->tid, full_path);
+			break;
+		case SMB2_OP_RMDIR:
+			rqst[num_rqst].rq_iov = &vars->si_iov[0];
+			rqst[num_rqst].rq_nvec = 1;
 
-		size[0] = 8; /* sizeof __le64 */
-		data[0] = ptr;
+			size[0] = 1; /* sizeof __u8 See MS-FSCC section 2.4.11 */
+			data[0] = &delete_pending[0];
 
-		if (cfile) {
 			rc = SMB2_set_info_init(tcon, server,
-						&rqst[num_rqst],
-						cfile->fid.persistent_fid,
-						cfile->fid.volatile_fid,
-						current->tgid,
-						FILE_END_OF_FILE_INFORMATION,
-						SMB2_O_INFO_FILE, 0,
-						data, size);
-		} else {
-			rc = SMB2_set_info_init(tcon, server,
-						&rqst[num_rqst],
-						COMPOUND_FID,
-						COMPOUND_FID,
-						current->tgid,
-						FILE_END_OF_FILE_INFORMATION,
-						SMB2_O_INFO_FILE, 0,
-						data, size);
-			if (!rc) {
-				smb2_set_next_command(tcon, &rqst[num_rqst]);
-				smb2_set_related(&rqst[num_rqst]);
+						&rqst[num_rqst], COMPOUND_FID,
+						COMPOUND_FID, current->tgid,
+						FILE_DISPOSITION_INFORMATION,
+						SMB2_O_INFO_FILE, 0, data, size);
+			if (rc)
+				goto finished;
+			smb2_set_next_command(tcon, &rqst[num_rqst]);
+			smb2_set_related(&rqst[num_rqst++]);
+			trace_smb3_rmdir_enter(xid, ses->Suid, tcon->tid, full_path);
+			break;
+		case SMB2_OP_SET_EOF:
+			rqst[num_rqst].rq_iov = &vars->si_iov[0];
+			rqst[num_rqst].rq_nvec = 1;
+
+			size[0] = in_iov[i].iov_len;
+			data[0] = in_iov[i].iov_base;
+
+			if (cfile) {
+				rc = SMB2_set_info_init(tcon, server,
+							&rqst[num_rqst],
+							cfile->fid.persistent_fid,
+							cfile->fid.volatile_fid,
+							current->tgid,
+							FILE_END_OF_FILE_INFORMATION,
+							SMB2_O_INFO_FILE, 0,
+							data, size);
+			} else {
+				rc = SMB2_set_info_init(tcon, server,
+							&rqst[num_rqst],
+							COMPOUND_FID,
+							COMPOUND_FID,
+							current->tgid,
+							FILE_END_OF_FILE_INFORMATION,
+							SMB2_O_INFO_FILE, 0,
+							data, size);
+				if (!rc) {
+					smb2_set_next_command(tcon, &rqst[num_rqst]);
+					smb2_set_related(&rqst[num_rqst]);
+				}
 			}
-		}
-		if (rc)
-			goto finished;
-		num_rqst++;
-		trace_smb3_set_eof_enter(xid, ses->Suid, tcon->tid, full_path);
-		break;
-	case SMB2_OP_SET_INFO:
-		rqst[num_rqst].rq_iov = &vars->si_iov[0];
-		rqst[num_rqst].rq_nvec = 1;
-
-
-		size[0] = sizeof(FILE_BASIC_INFO);
-		data[0] = ptr;
-
-		if (cfile)
-			rc = SMB2_set_info_init(tcon, server,
-				&rqst[num_rqst],
-				cfile->fid.persistent_fid,
-				cfile->fid.volatile_fid, current->tgid,
-				FILE_BASIC_INFORMATION,
-				SMB2_O_INFO_FILE, 0, data, size);
-		else {
-			rc = SMB2_set_info_init(tcon, server,
-				&rqst[num_rqst],
-				COMPOUND_FID,
-				COMPOUND_FID, current->tgid,
-				FILE_BASIC_INFORMATION,
-				SMB2_O_INFO_FILE, 0, data, size);
-			if (!rc) {
-				smb2_set_next_command(tcon, &rqst[num_rqst]);
-				smb2_set_related(&rqst[num_rqst]);
+			if (rc)
+				goto finished;
+			num_rqst++;
+			trace_smb3_set_eof_enter(xid, ses->Suid, tcon->tid, full_path);
+			break;
+		case SMB2_OP_SET_INFO:
+			rqst[num_rqst].rq_iov = &vars->si_iov[0];
+			rqst[num_rqst].rq_nvec = 1;
+
+			size[0] = in_iov[i].iov_len;
+			data[0] = in_iov[i].iov_base;
+
+			if (cfile) {
+				rc = SMB2_set_info_init(tcon, server,
+							&rqst[num_rqst],
+							cfile->fid.persistent_fid,
+							cfile->fid.volatile_fid, current->tgid,
+							FILE_BASIC_INFORMATION,
+							SMB2_O_INFO_FILE, 0, data, size);
+			} else {
+				rc = SMB2_set_info_init(tcon, server,
+							&rqst[num_rqst],
+							COMPOUND_FID,
+							COMPOUND_FID, current->tgid,
+							FILE_BASIC_INFORMATION,
+							SMB2_O_INFO_FILE, 0, data, size);
+				if (!rc) {
+					smb2_set_next_command(tcon, &rqst[num_rqst]);
+					smb2_set_related(&rqst[num_rqst]);
+				}
 			}
-		}
 
-		if (rc)
-			goto finished;
-		num_rqst++;
-		trace_smb3_set_info_compound_enter(xid, ses->Suid, tcon->tid,
-						   full_path);
-		break;
-	case SMB2_OP_RENAME:
-		rqst[num_rqst].rq_iov = &vars->si_iov[0];
-		rqst[num_rqst].rq_nvec = 2;
+			if (rc)
+				goto finished;
+			num_rqst++;
+			trace_smb3_set_info_compound_enter(xid, ses->Suid,
+							   tcon->tid, full_path);
+			break;
+		case SMB2_OP_RENAME:
+			rqst[num_rqst].rq_iov = &vars->si_iov[0];
+			rqst[num_rqst].rq_nvec = 2;
 
-		len = (2 * UniStrnlen((wchar_t *)ptr, PATH_MAX));
+			len = in_iov[i].iov_len;
 
-		vars->rename_info.ReplaceIfExists = 1;
-		vars->rename_info.RootDirectory = 0;
-		vars->rename_info.FileNameLength = cpu_to_le32(len);
+			vars->rename_info.ReplaceIfExists = 1;
+			vars->rename_info.RootDirectory = 0;
+			vars->rename_info.FileNameLength = cpu_to_le32(len);
 
-		size[0] = sizeof(struct smb2_file_rename_info);
-		data[0] = &vars->rename_info;
+			size[0] = sizeof(struct smb2_file_rename_info);
+			data[0] = &vars->rename_info;
 
-		size[1] = len + 2 /* null */;
-		data[1] = (__le16 *)ptr;
+			size[1] = len + 2 /* null */;
+			data[1] = in_iov[i].iov_base;
 
-		if (cfile)
-			rc = SMB2_set_info_init(tcon, server,
-						&rqst[num_rqst],
-						cfile->fid.persistent_fid,
-						cfile->fid.volatile_fid,
-					current->tgid, FILE_RENAME_INFORMATION,
-					SMB2_O_INFO_FILE, 0, data, size);
-		else {
-			rc = SMB2_set_info_init(tcon, server,
-					&rqst[num_rqst],
-					COMPOUND_FID, COMPOUND_FID,
-					current->tgid, FILE_RENAME_INFORMATION,
-					SMB2_O_INFO_FILE, 0, data, size);
-			if (!rc) {
-				smb2_set_next_command(tcon, &rqst[num_rqst]);
-				smb2_set_related(&rqst[num_rqst]);
+			if (cfile) {
+				rc = SMB2_set_info_init(tcon, server,
+							&rqst[num_rqst],
+							cfile->fid.persistent_fid,
+							cfile->fid.volatile_fid,
+							current->tgid, FILE_RENAME_INFORMATION,
+							SMB2_O_INFO_FILE, 0, data, size);
+			} else {
+				rc = SMB2_set_info_init(tcon, server,
+							&rqst[num_rqst],
+							COMPOUND_FID, COMPOUND_FID,
+							current->tgid, FILE_RENAME_INFORMATION,
+							SMB2_O_INFO_FILE, 0, data, size);
+				if (!rc) {
+					smb2_set_next_command(tcon, &rqst[num_rqst]);
+					smb2_set_related(&rqst[num_rqst]);
+				}
 			}
-		}
-		if (rc)
-			goto finished;
-		num_rqst++;
-		trace_smb3_rename_enter(xid, ses->Suid, tcon->tid, full_path);
-		break;
-	case SMB2_OP_HARDLINK:
-		rqst[num_rqst].rq_iov = &vars->si_iov[0];
-		rqst[num_rqst].rq_nvec = 2;
+			if (rc)
+				goto finished;
+			num_rqst++;
+			trace_smb3_rename_enter(xid, ses->Suid, tcon->tid, full_path);
+			break;
+		case SMB2_OP_HARDLINK:
+			rqst[num_rqst].rq_iov = &vars->si_iov[0];
+			rqst[num_rqst].rq_nvec = 2;
 
-		len = (2 * UniStrnlen((wchar_t *)ptr, PATH_MAX));
+			len = in_iov[i].iov_len;
 
-		vars->link_info.ReplaceIfExists = 0;
-		vars->link_info.RootDirectory = 0;
-		vars->link_info.FileNameLength = cpu_to_le32(len);
+			vars->link_info.ReplaceIfExists = 0;
+			vars->link_info.RootDirectory = 0;
+			vars->link_info.FileNameLength = cpu_to_le32(len);
 
-		size[0] = sizeof(struct smb2_file_link_info);
-		data[0] = &vars->link_info;
+			size[0] = sizeof(struct smb2_file_link_info);
+			data[0] = &vars->link_info;
 
-		size[1] = len + 2 /* null */;
-		data[1] = (__le16 *)ptr;
+			size[1] = len + 2 /* null */;
+			data[1] = in_iov[i].iov_base;
 
-		rc = SMB2_set_info_init(tcon, server,
-					&rqst[num_rqst], COMPOUND_FID,
-					COMPOUND_FID, current->tgid,
-					FILE_LINK_INFORMATION,
-					SMB2_O_INFO_FILE, 0, data, size);
-		if (rc)
-			goto finished;
-		smb2_set_next_command(tcon, &rqst[num_rqst]);
-		smb2_set_related(&rqst[num_rqst++]);
-		trace_smb3_hardlink_enter(xid, ses->Suid, tcon->tid, full_path);
-		break;
-	default:
-		cifs_dbg(VFS, "Invalid command\n");
-		rc = -EINVAL;
+			rc = SMB2_set_info_init(tcon, server,
+						&rqst[num_rqst], COMPOUND_FID,
+						COMPOUND_FID, current->tgid,
+						FILE_LINK_INFORMATION,
+						SMB2_O_INFO_FILE, 0, data, size);
+			if (rc)
+				goto finished;
+			smb2_set_next_command(tcon, &rqst[num_rqst]);
+			smb2_set_related(&rqst[num_rqst++]);
+			trace_smb3_hardlink_enter(xid, ses->Suid, tcon->tid, full_path);
+			break;
+		case SMB2_OP_SET_REPARSE:
+			rqst[num_rqst].rq_iov = vars->io_iov;
+			rqst[num_rqst].rq_nvec = ARRAY_SIZE(vars->io_iov);
+
+			rc = SMB2_ioctl_init(tcon, server, &rqst[num_rqst],
+					     COMPOUND_FID, COMPOUND_FID,
+					     FSCTL_SET_REPARSE_POINT,
+					     in_iov[i].iov_base,
+					     in_iov[i].iov_len, 0);
+			if (rc)
+				goto finished;
+			smb2_set_next_command(tcon, &rqst[num_rqst]);
+			smb2_set_related(&rqst[num_rqst++]);
+			trace_smb3_set_reparse_compound_enter(xid, ses->Suid,
+							      tcon->tid, full_path);
+			break;
+		case SMB2_OP_GET_REPARSE:
+			rqst[num_rqst].rq_iov = vars->io_iov;
+			rqst[num_rqst].rq_nvec = ARRAY_SIZE(vars->io_iov);
+
+			rc = SMB2_ioctl_init(tcon, server, &rqst[num_rqst],
+					     COMPOUND_FID, COMPOUND_FID,
+					     FSCTL_GET_REPARSE_POINT,
+					     NULL, 0, CIFSMaxBufSize);
+			if (rc)
+				goto finished;
+			smb2_set_next_command(tcon, &rqst[num_rqst]);
+			smb2_set_related(&rqst[num_rqst++]);
+			trace_smb3_get_reparse_compound_enter(xid, ses->Suid,
+							      tcon->tid, full_path);
+			break;
+		default:
+			cifs_dbg(VFS, "Invalid command\n");
+			rc = -EINVAL;
+		}
 	}
 	if (rc)
 		goto finished;
@@ -385,145 +445,176 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
 					rqst, resp_buftype,
 					rsp_iov);
 
- finished:
-	SMB2_open_free(&rqst[0]);
+finished:
+	num_rqst = 0;
+	SMB2_open_free(&rqst[num_rqst++]);
 	if (rc == -EREMCHG) {
 		pr_warn_once("server share %s deleted\n", tcon->tree_name);
 		tcon->need_reconnect = true;
 	}
 
-	switch (command) {
-	case SMB2_OP_QUERY_INFO:
-		idata = ptr;
-		if (rc == 0 && cfile && cfile->symlink_target) {
-			idata->symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL);
-			if (!idata->symlink_target)
-				rc = -ENOMEM;
-		}
-		if (rc == 0) {
-			qi_rsp = (struct smb2_query_info_rsp *)
-				rsp_iov[1].iov_base;
-			rc = smb2_validate_and_copy_iov(
-				le16_to_cpu(qi_rsp->OutputBufferOffset),
-				le32_to_cpu(qi_rsp->OutputBufferLength),
-				&rsp_iov[1], sizeof(idata->fi), (char *)&idata->fi);
-		}
-		if (rqst[1].rq_iov)
-			SMB2_query_info_free(&rqst[1]);
-		if (rqst[2].rq_iov)
-			SMB2_close_free(&rqst[2]);
-		if (rc)
-			trace_smb3_query_info_compound_err(xid,  ses->Suid,
-						tcon->tid, rc);
-		else
-			trace_smb3_query_info_compound_done(xid, ses->Suid,
-						tcon->tid);
-		break;
-	case SMB2_OP_POSIX_QUERY_INFO:
-		idata = ptr;
-		if (rc == 0 && cfile && cfile->symlink_target) {
-			idata->symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL);
-			if (!idata->symlink_target)
-				rc = -ENOMEM;
-		}
-		if (rc == 0) {
-			qi_rsp = (struct smb2_query_info_rsp *)
-				rsp_iov[1].iov_base;
-			rc = smb2_validate_and_copy_iov(
-				le16_to_cpu(qi_rsp->OutputBufferOffset),
-				le32_to_cpu(qi_rsp->OutputBufferLength),
-				&rsp_iov[1], sizeof(idata->posix_fi) /* add SIDs */,
-				(char *)&idata->posix_fi);
-		}
-		if (rc == 0) {
-			unsigned int length = le32_to_cpu(qi_rsp->OutputBufferLength);
-
-			if (length > sizeof(idata->posix_fi)) {
-				char *base = (char *)rsp_iov[1].iov_base +
-					le16_to_cpu(qi_rsp->OutputBufferOffset) +
-					sizeof(idata->posix_fi);
-				*extbuflen = length - sizeof(idata->posix_fi);
-				*extbuf = kmemdup(base, *extbuflen, GFP_KERNEL);
-				if (!*extbuf)
+	for (i = 0; i < num_cmds; i++) {
+		switch (cmds[i]) {
+		case SMB2_OP_QUERY_INFO:
+			idata = in_iov[i].iov_base;
+			if (rc == 0 && cfile && cfile->symlink_target) {
+				idata->symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL);
+				if (!idata->symlink_target)
 					rc = -ENOMEM;
+			}
+			if (rc == 0) {
+				qi_rsp = (struct smb2_query_info_rsp *)
+					rsp_iov[i + 1].iov_base;
+				rc = smb2_validate_and_copy_iov(
+					le16_to_cpu(qi_rsp->OutputBufferOffset),
+					le32_to_cpu(qi_rsp->OutputBufferLength),
+					&rsp_iov[i + 1], sizeof(idata->fi), (char *)&idata->fi);
+			}
+			SMB2_query_info_free(&rqst[num_rqst++]);
+			if (rc)
+				trace_smb3_query_info_compound_err(xid,  ses->Suid,
+								   tcon->tid, rc);
+			else
+				trace_smb3_query_info_compound_done(xid, ses->Suid,
+								    tcon->tid);
+			break;
+		case SMB2_OP_POSIX_QUERY_INFO:
+			idata = in_iov[i].iov_base;
+			if (rc == 0 && cfile && cfile->symlink_target) {
+				idata->symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL);
+				if (!idata->symlink_target)
+					rc = -ENOMEM;
+			}
+			if (rc == 0) {
+				qi_rsp = (struct smb2_query_info_rsp *)
+					rsp_iov[i + 1].iov_base;
+				rc = smb2_validate_and_copy_iov(
+					le16_to_cpu(qi_rsp->OutputBufferOffset),
+					le32_to_cpu(qi_rsp->OutputBufferLength),
+					&rsp_iov[i + 1], sizeof(idata->posix_fi) /* add SIDs */,
+					(char *)&idata->posix_fi);
+			}
+			if (rc == 0) {
+				unsigned int length = le32_to_cpu(qi_rsp->OutputBufferLength);
+
+				if (length > sizeof(idata->posix_fi)) {
+					char *base = (char *)rsp_iov[i + 1].iov_base +
+						le16_to_cpu(qi_rsp->OutputBufferOffset) +
+						sizeof(idata->posix_fi);
+					*extbuflen = length - sizeof(idata->posix_fi);
+					*extbuf = kmemdup(base, *extbuflen, GFP_KERNEL);
+					if (!*extbuf)
+						rc = -ENOMEM;
+				} else {
+					rc = -EINVAL;
+				}
+			}
+			SMB2_query_info_free(&rqst[num_rqst++]);
+			if (rc)
+				trace_smb3_posix_query_info_compound_err(xid,  ses->Suid,
+									 tcon->tid, rc);
+			else
+				trace_smb3_posix_query_info_compound_done(xid, ses->Suid,
+									  tcon->tid);
+			break;
+		case SMB2_OP_DELETE:
+			if (rc)
+				trace_smb3_delete_err(xid,  ses->Suid, tcon->tid, rc);
+			else
+				trace_smb3_delete_done(xid, ses->Suid, tcon->tid);
+			break;
+		case SMB2_OP_MKDIR:
+			if (rc)
+				trace_smb3_mkdir_err(xid,  ses->Suid, tcon->tid, rc);
+			else
+				trace_smb3_mkdir_done(xid, ses->Suid, tcon->tid);
+			break;
+		case SMB2_OP_HARDLINK:
+			if (rc)
+				trace_smb3_hardlink_err(xid,  ses->Suid, tcon->tid, rc);
+			else
+				trace_smb3_hardlink_done(xid, ses->Suid, tcon->tid);
+			SMB2_set_info_free(&rqst[num_rqst++]);
+			break;
+		case SMB2_OP_RENAME:
+			if (rc)
+				trace_smb3_rename_err(xid,  ses->Suid, tcon->tid, rc);
+			else
+				trace_smb3_rename_done(xid, ses->Suid, tcon->tid);
+			SMB2_set_info_free(&rqst[num_rqst++]);
+			break;
+		case SMB2_OP_RMDIR:
+			if (rc)
+				trace_smb3_rmdir_err(xid,  ses->Suid, tcon->tid, rc);
+			else
+				trace_smb3_rmdir_done(xid, ses->Suid, tcon->tid);
+			SMB2_set_info_free(&rqst[num_rqst++]);
+			break;
+		case SMB2_OP_SET_EOF:
+			if (rc)
+				trace_smb3_set_eof_err(xid,  ses->Suid, tcon->tid, rc);
+			else
+				trace_smb3_set_eof_done(xid, ses->Suid, tcon->tid);
+			SMB2_set_info_free(&rqst[num_rqst++]);
+			break;
+		case SMB2_OP_SET_INFO:
+			if (rc)
+				trace_smb3_set_info_compound_err(xid,  ses->Suid,
+								 tcon->tid, rc);
+			else
+				trace_smb3_set_info_compound_done(xid, ses->Suid,
+								  tcon->tid);
+			SMB2_set_info_free(&rqst[num_rqst++]);
+			break;
+		case SMB2_OP_SET_REPARSE:
+			if (rc) {
+				trace_smb3_set_reparse_compound_err(xid,  ses->Suid,
+								    tcon->tid, rc);
+			} else {
+				trace_smb3_set_reparse_compound_done(xid, ses->Suid,
+								     tcon->tid);
+			}
+			SMB2_ioctl_free(&rqst[num_rqst++]);
+			break;
+		case SMB2_OP_GET_REPARSE:
+			if (!rc) {
+				iov = &rsp_iov[i + 1];
+				idata = in_iov[i].iov_base;
+				idata->reparse.io.iov = *iov;
+				idata->reparse.io.buftype = resp_buftype[i + 1];
+				rbuf = reparse_buf_ptr(iov);
+				if (IS_ERR(rbuf)) {
+					rc = PTR_ERR(rbuf);
+					trace_smb3_set_reparse_compound_err(xid,  ses->Suid,
+									    tcon->tid, rc);
+				} else {
+					idata->reparse.tag = le32_to_cpu(rbuf->ReparseTag);
+					trace_smb3_set_reparse_compound_done(xid, ses->Suid,
+									     tcon->tid);
+				}
+				memset(iov, 0, sizeof(*iov));
+				resp_buftype[i + 1] = CIFS_NO_BUFFER;
 			} else {
-				rc = -EINVAL;
+				trace_smb3_set_reparse_compound_err(xid,  ses->Suid,
+								    tcon->tid, rc);
 			}
+			SMB2_ioctl_free(&rqst[num_rqst++]);
+			break;
 		}
-		if (rqst[1].rq_iov)
-			SMB2_query_info_free(&rqst[1]);
-		if (rqst[2].rq_iov)
-			SMB2_close_free(&rqst[2]);
-		if (rc)
-			trace_smb3_posix_query_info_compound_err(xid,  ses->Suid, tcon->tid, rc);
-		else
-			trace_smb3_posix_query_info_compound_done(xid, ses->Suid, tcon->tid);
-		break;
-	case SMB2_OP_DELETE:
-		if (rc)
-			trace_smb3_delete_err(xid,  ses->Suid, tcon->tid, rc);
-		else
-			trace_smb3_delete_done(xid, ses->Suid, tcon->tid);
-		if (rqst[1].rq_iov)
-			SMB2_close_free(&rqst[1]);
-		break;
-	case SMB2_OP_MKDIR:
-		if (rc)
-			trace_smb3_mkdir_err(xid,  ses->Suid, tcon->tid, rc);
-		else
-			trace_smb3_mkdir_done(xid, ses->Suid, tcon->tid);
-		if (rqst[1].rq_iov)
-			SMB2_close_free(&rqst[1]);
-		break;
-	case SMB2_OP_HARDLINK:
-		if (rc)
-			trace_smb3_hardlink_err(xid,  ses->Suid, tcon->tid, rc);
-		else
-			trace_smb3_hardlink_done(xid, ses->Suid, tcon->tid);
-		free_set_inf_compound(rqst);
-		break;
-	case SMB2_OP_RENAME:
-		if (rc)
-			trace_smb3_rename_err(xid,  ses->Suid, tcon->tid, rc);
-		else
-			trace_smb3_rename_done(xid, ses->Suid, tcon->tid);
-		free_set_inf_compound(rqst);
-		break;
-	case SMB2_OP_RMDIR:
-		if (rc)
-			trace_smb3_rmdir_err(xid,  ses->Suid, tcon->tid, rc);
-		else
-			trace_smb3_rmdir_done(xid, ses->Suid, tcon->tid);
-		free_set_inf_compound(rqst);
-		break;
-	case SMB2_OP_SET_EOF:
-		if (rc)
-			trace_smb3_set_eof_err(xid,  ses->Suid, tcon->tid, rc);
-		else
-			trace_smb3_set_eof_done(xid, ses->Suid, tcon->tid);
-		free_set_inf_compound(rqst);
-		break;
-	case SMB2_OP_SET_INFO:
-		if (rc)
-			trace_smb3_set_info_compound_err(xid,  ses->Suid,
-						tcon->tid, rc);
-		else
-			trace_smb3_set_info_compound_done(xid, ses->Suid,
-						tcon->tid);
-		free_set_inf_compound(rqst);
-		break;
 	}
+	SMB2_close_free(&rqst[num_rqst]);
 
 	if (cfile)
 		cifsFileInfo_put(cfile);
 
+	num_cmds += 2;
 	if (out_iov && out_buftype) {
-		memcpy(out_iov, rsp_iov, 3 * sizeof(*out_iov));
-		memcpy(out_buftype, resp_buftype, 3 * sizeof(*out_buftype));
+		memcpy(out_iov, rsp_iov, num_cmds * sizeof(*out_iov));
+		memcpy(out_buftype, resp_buftype,
+		       num_cmds * sizeof(*out_buftype));
 	} else {
-		free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base);
-		free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base);
-		free_rsp_buf(resp_buftype[2], rsp_iov[2].iov_base);
+		for (i = 0; i < num_cmds; i++)
+			free_rsp_buf(resp_buftype[i], rsp_iov[i].iov_base);
 	}
 	kfree(vars);
 	return rc;
@@ -555,7 +646,7 @@ static int parse_create_response(struct cifs_open_info_data *data,
 		break;
 	}
 	data->reparse_point = reparse_point;
-	data->reparse_tag = tag;
+	data->reparse.tag = tag;
 	return rc;
 }
 
@@ -569,9 +660,11 @@ int smb2_query_path_info(const unsigned int xid,
 	struct cifsFileInfo *cfile;
 	struct cached_fid *cfid = NULL;
 	struct smb2_hdr *hdr;
-	struct kvec out_iov[3] = {};
+	struct kvec in_iov[2], out_iov[3] = {};
 	int out_buftype[3] = {};
+	int cmds[2] = { SMB2_OP_QUERY_INFO,  };
 	bool islink;
+	int i, num_cmds;
 	int rc, rc2;
 
 	data->adjust_tz = false;
@@ -593,9 +686,15 @@ int smb2_query_path_info(const unsigned int xid,
 		return rc;
 	}
 
+	in_iov[0].iov_base = data;
+	in_iov[0].iov_len = sizeof(*data);
+	in_iov[1] = in_iov[0];
+
 	cifs_get_readable_path(tcon, full_path, &cfile);
-	rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_READ_ATTRIBUTES, FILE_OPEN,
-			      create_options, ACL_NO_MODE, data, SMB2_OP_QUERY_INFO, cfile,
+	rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
+			      FILE_READ_ATTRIBUTES, FILE_OPEN,
+			      create_options, ACL_NO_MODE,
+			      in_iov, cmds, 1, cfile,
 			      NULL, NULL, out_iov, out_buftype);
 	hdr = out_iov[0].iov_base;
 	/*
@@ -612,14 +711,19 @@ int smb2_query_path_info(const unsigned int xid,
 		if (rc || !data->reparse_point)
 			goto out;
 
+		if (data->reparse.tag == IO_REPARSE_TAG_SYMLINK) {
+			/* symlink already parsed in create response */
+			num_cmds = 1;
+		} else {
+			cmds[1] = SMB2_OP_GET_REPARSE;
+			num_cmds = 2;
+		}
 		create_options |= OPEN_REPARSE_POINT;
-		/* Failed on a symbolic link - query a reparse point info */
 		cifs_get_readable_path(tcon, full_path, &cfile);
 		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
 				      FILE_READ_ATTRIBUTES, FILE_OPEN,
-				      create_options, ACL_NO_MODE, data,
-				      SMB2_OP_QUERY_INFO, cfile, NULL, NULL,
-				      NULL, NULL);
+				      create_options, ACL_NO_MODE, in_iov, cmds,
+				      num_cmds, cfile, NULL, NULL, NULL, NULL);
 		break;
 	case -EREMOTE:
 		break;
@@ -637,9 +741,8 @@ int smb2_query_path_info(const unsigned int xid,
 	}
 
 out:
-	free_rsp_buf(out_buftype[0], out_iov[0].iov_base);
-	free_rsp_buf(out_buftype[1], out_iov[1].iov_base);
-	free_rsp_buf(out_buftype[2], out_iov[2].iov_base);
+	for (i = 0; i < ARRAY_SIZE(out_buftype); i++)
+		free_rsp_buf(out_buftype[i], out_iov[i].iov_base);
 	return rc;
 }
 
@@ -654,12 +757,14 @@ int smb311_posix_query_path_info(const unsigned int xid,
 	int rc;
 	__u32 create_options = 0;
 	struct cifsFileInfo *cfile;
-	struct kvec out_iov[3] = {};
+	struct kvec in_iov[2], out_iov[3] = {};
 	int out_buftype[3] = {};
 	__u8 *sidsbuf = NULL;
 	__u8 *sidsbuf_end = NULL;
 	size_t sidsbuflen = 0;
 	size_t owner_len, group_len;
+	int cmds[2] = { SMB2_OP_POSIX_QUERY_INFO,  };
+	int i, num_cmds;
 
 	data->adjust_tz = false;
 	data->reparse_point = false;
@@ -670,11 +775,15 @@ int smb311_posix_query_path_info(const unsigned int xid,
 	 * when we already have an open file handle for this. For now this is fast enough
 	 * (always using the compounded version).
 	 */
+	in_iov[0].iov_base = data;
+	in_iov[0].iov_len = sizeof(*data);
+	in_iov[1] = in_iov[0];
 
 	cifs_get_readable_path(tcon, full_path, &cfile);
-	rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_READ_ATTRIBUTES, FILE_OPEN,
-			      create_options, ACL_NO_MODE, data, SMB2_OP_POSIX_QUERY_INFO, cfile,
-			      &sidsbuf, &sidsbuflen, out_iov, out_buftype);
+	rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
+			      FILE_READ_ATTRIBUTES, FILE_OPEN,
+			      create_options, ACL_NO_MODE, in_iov, cmds, 1,
+			      cfile, &sidsbuf, &sidsbuflen, out_iov, out_buftype);
 	/*
 	 * If first iov is unset, then SMB session was dropped or we've got a
 	 * cached open file (@cfile).
@@ -690,13 +799,19 @@ int smb311_posix_query_path_info(const unsigned int xid,
 		if (rc || !data->reparse_point)
 			goto out;
 
+		if (data->reparse.tag == IO_REPARSE_TAG_SYMLINK) {
+			/* symlink already parsed in create response */
+			num_cmds = 1;
+		} else {
+			cmds[1] = SMB2_OP_GET_REPARSE;
+			num_cmds = 2;
+		}
 		create_options |= OPEN_REPARSE_POINT;
-		/* Failed on a symbolic link - query a reparse point info */
 		cifs_get_readable_path(tcon, full_path, &cfile);
-		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_READ_ATTRIBUTES,
-				      FILE_OPEN, create_options, ACL_NO_MODE, data,
-				      SMB2_OP_POSIX_QUERY_INFO, cfile,
-				      &sidsbuf, &sidsbuflen, NULL, NULL);
+		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
+				      FILE_READ_ATTRIBUTES, FILE_OPEN,
+				      create_options, ACL_NO_MODE, in_iov, cmds,
+				      num_cmds, cfile, &sidsbuf, &sidsbuflen, NULL, NULL);
 		break;
 	}
 
@@ -721,9 +836,8 @@ out:
 	}
 
 	kfree(sidsbuf);
-	free_rsp_buf(out_buftype[0], out_iov[0].iov_base);
-	free_rsp_buf(out_buftype[1], out_iov[1].iov_base);
-	free_rsp_buf(out_buftype[2], out_iov[2].iov_base);
+	for (i = 0; i < ARRAY_SIZE(out_buftype); i++)
+		free_rsp_buf(out_buftype[i], out_iov[i].iov_base);
 	return rc;
 }
 
@@ -734,7 +848,8 @@ smb2_mkdir(const unsigned int xid, struct inode *parent_inode, umode_t mode,
 {
 	return smb2_compound_op(xid, tcon, cifs_sb, name,
 				FILE_WRITE_ATTRIBUTES, FILE_CREATE,
-				CREATE_NOT_FILE, mode, NULL, SMB2_OP_MKDIR,
+				CREATE_NOT_FILE, mode, NULL,
+				&(int){SMB2_OP_MKDIR}, 1,
 				NULL, NULL, NULL, NULL, NULL);
 }
 
@@ -743,21 +858,24 @@ smb2_mkdir_setinfo(struct inode *inode, const char *name,
 		   struct cifs_sb_info *cifs_sb, struct cifs_tcon *tcon,
 		   const unsigned int xid)
 {
-	FILE_BASIC_INFO data;
+	FILE_BASIC_INFO data = {};
 	struct cifsInodeInfo *cifs_i;
 	struct cifsFileInfo *cfile;
+	struct kvec in_iov;
 	u32 dosattrs;
 	int tmprc;
 
-	memset(&data, 0, sizeof(data));
+	in_iov.iov_base = &data;
+	in_iov.iov_len = sizeof(data);
 	cifs_i = CIFS_I(inode);
 	dosattrs = cifs_i->cifsAttrs | ATTR_READONLY;
 	data.Attributes = cpu_to_le32(dosattrs);
 	cifs_get_writable_path(tcon, name, FIND_WR_ANY, &cfile);
 	tmprc = smb2_compound_op(xid, tcon, cifs_sb, name,
 				 FILE_WRITE_ATTRIBUTES, FILE_CREATE,
-				 CREATE_NOT_FILE, ACL_NO_MODE,
-				 &data, SMB2_OP_SET_INFO, cfile, NULL, NULL, NULL, NULL);
+				 CREATE_NOT_FILE, ACL_NO_MODE, &in_iov,
+				 &(int){SMB2_OP_SET_INFO}, 1,
+				 cfile, NULL, NULL, NULL, NULL);
 	if (tmprc == 0)
 		cifs_i->cifsAttrs = dosattrs;
 }
@@ -767,9 +885,10 @@ smb2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, const char *name,
 	   struct cifs_sb_info *cifs_sb)
 {
 	drop_cached_dir_by_name(xid, tcon, name, cifs_sb);
-	return smb2_compound_op(xid, tcon, cifs_sb, name, DELETE, FILE_OPEN,
-				CREATE_NOT_FILE, ACL_NO_MODE,
-				NULL, SMB2_OP_RMDIR, NULL, NULL, NULL, NULL, NULL);
+	return smb2_compound_op(xid, tcon, cifs_sb, name,
+				DELETE, FILE_OPEN, CREATE_NOT_FILE,
+				ACL_NO_MODE, NULL, &(int){SMB2_OP_RMDIR}, 1,
+				NULL, NULL, NULL, NULL, NULL);
 }
 
 int
@@ -778,15 +897,17 @@ smb2_unlink(const unsigned int xid, struct cifs_tcon *tcon, const char *name,
 {
 	return smb2_compound_op(xid, tcon, cifs_sb, name, DELETE, FILE_OPEN,
 				CREATE_DELETE_ON_CLOSE | OPEN_REPARSE_POINT,
-				ACL_NO_MODE, NULL, SMB2_OP_DELETE, NULL, NULL, NULL, NULL, NULL);
+				ACL_NO_MODE, NULL, &(int){SMB2_OP_DELETE}, 1,
+				NULL, NULL, NULL, NULL, NULL);
 }
 
-static int
-smb2_set_path_attr(const unsigned int xid, struct cifs_tcon *tcon,
-		   const char *from_name, const char *to_name,
-		   struct cifs_sb_info *cifs_sb, __u32 access, int command,
-		   struct cifsFileInfo *cfile)
+static int smb2_set_path_attr(const unsigned int xid, struct cifs_tcon *tcon,
+			      const char *from_name, const char *to_name,
+			      struct cifs_sb_info *cifs_sb,
+			      __u32 create_options, __u32 access,
+			      int command, struct cifsFileInfo *cfile)
 {
+	struct kvec in_iov;
 	__le16 *smb2_to_name = NULL;
 	int rc;
 
@@ -795,36 +916,43 @@ smb2_set_path_attr(const unsigned int xid, struct cifs_tcon *tcon,
 		rc = -ENOMEM;
 		goto smb2_rename_path;
 	}
+	in_iov.iov_base = smb2_to_name;
+	in_iov.iov_len = 2 * UniStrnlen((wchar_t *)smb2_to_name, PATH_MAX);
 	rc = smb2_compound_op(xid, tcon, cifs_sb, from_name, access,
-			      FILE_OPEN, 0, ACL_NO_MODE, smb2_to_name,
-			      command, cfile, NULL, NULL, NULL, NULL);
+			      FILE_OPEN, create_options, ACL_NO_MODE, &in_iov,
+			      &command, 1, cfile, NULL, NULL, NULL, NULL);
 smb2_rename_path:
 	kfree(smb2_to_name);
 	return rc;
 }
 
-int
-smb2_rename_path(const unsigned int xid, struct cifs_tcon *tcon,
-		 const char *from_name, const char *to_name,
-		 struct cifs_sb_info *cifs_sb)
+int smb2_rename_path(const unsigned int xid,
+		     struct cifs_tcon *tcon,
+		     struct dentry *source_dentry,
+		     const char *from_name, const char *to_name,
+		     struct cifs_sb_info *cifs_sb)
 {
 	struct cifsFileInfo *cfile;
+	__u32 co = file_create_options(source_dentry);
 
 	drop_cached_dir_by_name(xid, tcon, from_name, cifs_sb);
 	cifs_get_writable_path(tcon, from_name, FIND_WR_WITH_DELETE, &cfile);
 
-	return smb2_set_path_attr(xid, tcon, from_name, to_name,
-				  cifs_sb, DELETE, SMB2_OP_RENAME, cfile);
+	return smb2_set_path_attr(xid, tcon, from_name, to_name, cifs_sb,
+				  co, DELETE, SMB2_OP_RENAME, cfile);
 }
 
-int
-smb2_create_hardlink(const unsigned int xid, struct cifs_tcon *tcon,
-		     const char *from_name, const char *to_name,
-		     struct cifs_sb_info *cifs_sb)
+int smb2_create_hardlink(const unsigned int xid,
+			 struct cifs_tcon *tcon,
+			 struct dentry *source_dentry,
+			 const char *from_name, const char *to_name,
+			 struct cifs_sb_info *cifs_sb)
 {
-	return smb2_set_path_attr(xid, tcon, from_name, to_name, cifs_sb,
-				  FILE_READ_ATTRIBUTES, SMB2_OP_HARDLINK,
-				  NULL);
+	__u32 co = file_create_options(source_dentry);
+
+	return smb2_set_path_attr(xid, tcon, from_name, to_name,
+				  cifs_sb, co, FILE_READ_ATTRIBUTES,
+				  SMB2_OP_HARDLINK, NULL);
 }
 
 int
@@ -832,13 +960,18 @@ smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon,
 		   const char *full_path, __u64 size,
 		   struct cifs_sb_info *cifs_sb, bool set_alloc)
 {
-	__le64 eof = cpu_to_le64(size);
 	struct cifsFileInfo *cfile;
+	struct kvec in_iov;
+	__le64 eof = cpu_to_le64(size);
 
+	in_iov.iov_base = &eof;
+	in_iov.iov_len = sizeof(eof);
 	cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
 	return smb2_compound_op(xid, tcon, cifs_sb, full_path,
-				FILE_WRITE_DATA, FILE_OPEN, 0, ACL_NO_MODE,
-				&eof, SMB2_OP_SET_EOF, cfile, NULL, NULL, NULL, NULL);
+				FILE_WRITE_DATA, FILE_OPEN,
+				0, ACL_NO_MODE, &in_iov,
+				&(int){SMB2_OP_SET_EOF}, 1,
+				cfile, NULL, NULL, NULL, NULL);
 }
 
 int
@@ -849,6 +982,7 @@ smb2_set_file_info(struct inode *inode, const char *full_path,
 	struct tcon_link *tlink;
 	struct cifs_tcon *tcon;
 	struct cifsFileInfo *cfile;
+	struct kvec in_iov = { .iov_base = buf, .iov_len = sizeof(*buf), };
 	int rc;
 
 	if ((buf->CreationTime == 0) && (buf->LastAccessTime == 0) &&
@@ -864,8 +998,91 @@ smb2_set_file_info(struct inode *inode, const char *full_path,
 	cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
 	rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
 			      FILE_WRITE_ATTRIBUTES, FILE_OPEN,
-			      0, ACL_NO_MODE, buf, SMB2_OP_SET_INFO, cfile,
+			      0, ACL_NO_MODE, &in_iov,
+			      &(int){SMB2_OP_SET_INFO}, 1, cfile,
 			      NULL, NULL, NULL, NULL);
 	cifs_put_tlink(tlink);
 	return rc;
 }
+
+struct inode *smb2_get_reparse_inode(struct cifs_open_info_data *data,
+				     struct super_block *sb,
+				     const unsigned int xid,
+				     struct cifs_tcon *tcon,
+				     const char *full_path,
+				     struct kvec *iov)
+{
+	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
+	struct cifsFileInfo *cfile;
+	struct inode *new = NULL;
+	struct kvec in_iov[2];
+	int cmds[2];
+	int da, co, cd;
+	int rc;
+
+	da = SYNCHRONIZE | DELETE |
+		FILE_READ_ATTRIBUTES |
+		FILE_WRITE_ATTRIBUTES;
+	co = CREATE_NOT_DIR | OPEN_REPARSE_POINT;
+	cd = FILE_CREATE;
+	cmds[0] = SMB2_OP_SET_REPARSE;
+	in_iov[0] = *iov;
+	in_iov[1].iov_base = data;
+	in_iov[1].iov_len = sizeof(*data);
+
+	if (tcon->posix_extensions) {
+		cmds[1] = SMB2_OP_POSIX_QUERY_INFO;
+		cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
+		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
+				      da, cd, co, ACL_NO_MODE, in_iov,
+				      cmds, 2, cfile, NULL, NULL, NULL, NULL);
+		if (!rc) {
+			rc = smb311_posix_get_inode_info(&new, full_path,
+							 data, sb, xid);
+		}
+	} else {
+		cmds[1] = SMB2_OP_QUERY_INFO;
+		cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
+		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
+				      da, cd, co, ACL_NO_MODE, in_iov,
+				      cmds, 2, cfile, NULL, NULL, NULL, NULL);
+		if (!rc) {
+			rc = cifs_get_inode_info(&new, full_path,
+						 data, sb, xid, NULL);
+		}
+	}
+	return rc ? ERR_PTR(rc) : new;
+}
+
+int smb2_query_reparse_point(const unsigned int xid,
+			     struct cifs_tcon *tcon,
+			     struct cifs_sb_info *cifs_sb,
+			     const char *full_path,
+			     u32 *tag, struct kvec *rsp,
+			     int *rsp_buftype)
+{
+	struct cifs_open_info_data data = {};
+	struct cifsFileInfo *cfile;
+	struct kvec in_iov = { .iov_base = &data, .iov_len = sizeof(data), };
+	int rc;
+
+	cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path);
+
+	cifs_get_readable_path(tcon, full_path, &cfile);
+	rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
+			      FILE_READ_ATTRIBUTES, FILE_OPEN,
+			      OPEN_REPARSE_POINT, ACL_NO_MODE, &in_iov,
+			      &(int){SMB2_OP_GET_REPARSE}, 1, cfile,
+			      NULL, NULL, NULL, NULL);
+	if (rc)
+		goto out;
+
+	*tag = data.reparse.tag;
+	*rsp = data.reparse.io.iov;
+	*rsp_buftype = data.reparse.io.buftype;
+	memset(&data.reparse.io.iov, 0, sizeof(data.reparse.io.iov));
+	data.reparse.io.buftype = CIFS_NO_BUFFER;
+out:
+	cifs_free_open_info(&data);
+	return rc;
+}
diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c
index 32dfa0f7a78c..82b84a4941dd 100644
--- a/fs/smb/client/smb2misc.c
+++ b/fs/smb/client/smb2misc.c
@@ -173,6 +173,21 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server)
 	}
 
 	mid = le64_to_cpu(shdr->MessageId);
+	if (check_smb2_hdr(shdr, mid))
+		return 1;
+
+	if (shdr->StructureSize != SMB2_HEADER_STRUCTURE_SIZE) {
+		cifs_dbg(VFS, "Invalid structure size %u\n",
+			 le16_to_cpu(shdr->StructureSize));
+		return 1;
+	}
+
+	command = le16_to_cpu(shdr->Command);
+	if (command >= NUMBER_OF_SMB2_COMMANDS) {
+		cifs_dbg(VFS, "Invalid SMB2 command %d\n", command);
+		return 1;
+	}
+
 	if (len < pdu_size) {
 		if ((len >= hdr_size)
 		    && (shdr->Status != 0)) {
@@ -193,21 +208,6 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server)
 		return 1;
 	}
 
-	if (check_smb2_hdr(shdr, mid))
-		return 1;
-
-	if (shdr->StructureSize != SMB2_HEADER_STRUCTURE_SIZE) {
-		cifs_dbg(VFS, "Invalid structure size %u\n",
-			 le16_to_cpu(shdr->StructureSize));
-		return 1;
-	}
-
-	command = le16_to_cpu(shdr->Command);
-	if (command >= NUMBER_OF_SMB2_COMMANDS) {
-		cifs_dbg(VFS, "Invalid SMB2 command %d\n", command);
-		return 1;
-	}
-
 	if (smb2_rsp_struct_sizes[command] != pdu->StructureSize2) {
 		if (command != SMB2_OPLOCK_BREAK_HE && (shdr->Status == 0 ||
 		    pdu->StructureSize2 != SMB2_ERROR_STRUCTURE_SIZE2_LE)) {
@@ -313,6 +313,9 @@ static const bool has_smb2_data_area[NUMBER_OF_SMB2_COMMANDS] = {
 char *
 smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *shdr)
 {
+	const int max_off = 4096;
+	const int max_len = 128 * 1024;
+
 	*off = 0;
 	*len = 0;
 
@@ -384,29 +387,20 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *shdr)
 	 * Invalid length or offset probably means data area is invalid, but
 	 * we have little choice but to ignore the data area in this case.
 	 */
-	if (*off > 4096) {
-		cifs_dbg(VFS, "offset %d too large, data area ignored\n", *off);
-		*len = 0;
+	if (unlikely(*off < 0 || *off > max_off ||
+		     *len < 0 || *len > max_len)) {
+		cifs_dbg(VFS, "%s: invalid data area (off=%d len=%d)\n",
+			 __func__, *off, *len);
 		*off = 0;
-	} else if (*off < 0) {
-		cifs_dbg(VFS, "negative offset %d to data invalid ignore data area\n",
-			 *off);
-		*off = 0;
-		*len = 0;
-	} else if (*len < 0) {
-		cifs_dbg(VFS, "negative data length %d invalid, data area ignored\n",
-			 *len);
 		*len = 0;
-	} else if (*len > 128 * 1024) {
-		cifs_dbg(VFS, "data area larger than 128K: %d\n", *len);
+	} else if (*off == 0) {
 		*len = 0;
 	}
 
 	/* return pointer to beginning of data area, ie offset from SMB start */
-	if ((*off != 0) && (*len != 0))
+	if (*off > 0 && *len > 0)
 		return (char *)shdr + *off;
-	else
-		return NULL;
+	return NULL;
 }
 
 /*
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index a959ed2c9b22..01a5bd7e6a30 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -403,8 +403,10 @@ smb2_dump_detail(void *buf, struct TCP_Server_Info *server)
 	cifs_server_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Mid: %llu Pid: %d\n",
 		 shdr->Command, shdr->Status, shdr->Flags, shdr->MessageId,
 		 shdr->Id.SyncId.ProcessId);
-	cifs_server_dbg(VFS, "smb buf %p len %u\n", buf,
-		 server->ops->calc_smb_size(buf));
+	if (!server->ops->check_message(buf, server->total_read, server)) {
+		cifs_server_dbg(VFS, "smb buf %p len %u\n", buf,
+				server->ops->calc_smb_size(buf));
+	}
 #endif
 }
 
@@ -593,16 +595,12 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
 	}
 
 	/*
-	 * Go through iface_list and do kref_put to remove
-	 * any unused ifaces. ifaces in use will be removed
-	 * when the last user calls a kref_put on it
+	 * Go through iface_list and mark them as inactive
 	 */
 	list_for_each_entry_safe(iface, niface, &ses->iface_list,
-				 iface_head) {
+				 iface_head)
 		iface->is_active = 0;
-		kref_put(&iface->refcount, release_iface);
-		ses->iface_count--;
-	}
+
 	spin_unlock(&ses->iface_lock);
 
 	/*
@@ -676,10 +674,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
 					 iface_head) {
 			ret = iface_cmp(iface, &tmp_iface);
 			if (!ret) {
-				/* just get a ref so that it doesn't get picked/freed */
 				iface->is_active = 1;
-				kref_get(&iface->refcount);
-				ses->iface_count++;
 				spin_unlock(&ses->iface_lock);
 				goto next_iface;
 			} else if (ret < 0) {
@@ -746,6 +741,20 @@ next_iface:
 	}
 
 out:
+	/*
+	 * Go through the list again and put the inactive entries
+	 */
+	spin_lock(&ses->iface_lock);
+	list_for_each_entry_safe(iface, niface, &ses->iface_list,
+				 iface_head) {
+		if (!iface->is_active) {
+			list_del(&iface->iface_head);
+			kref_put(&iface->refcount, release_iface);
+			ses->iface_count--;
+		}
+	}
+	spin_unlock(&ses->iface_lock);
+
 	return rc;
 }
 
@@ -782,9 +791,14 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon, bool in_
 		goto out;
 
 	/* check if iface is still active */
+	spin_lock(&ses->chan_lock);
 	pserver = ses->chans[0].server;
-	if (pserver && !cifs_chan_is_iface_active(ses, pserver))
+	if (pserver && !cifs_chan_is_iface_active(ses, pserver)) {
+		spin_unlock(&ses->chan_lock);
 		cifs_chan_update_iface(ses, pserver);
+		spin_lock(&ses->chan_lock);
+	}
+	spin_unlock(&ses->chan_lock);
 
 out:
 	kfree(out_buf);
@@ -1921,7 +1935,6 @@ static int
 smb2_set_file_size(const unsigned int xid, struct cifs_tcon *tcon,
 		   struct cifsFileInfo *cfile, __u64 size, bool set_alloc)
 {
-	__le64 eof = cpu_to_le64(size);
 	struct inode *inode;
 
 	/*
@@ -1938,7 +1951,7 @@ smb2_set_file_size(const unsigned int xid, struct cifs_tcon *tcon,
 	}
 
 	return SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
-			    cfile->fid.volatile_fid, cfile->pid, &eof);
+			    cfile->fid.volatile_fid, cfile->pid, size);
 }
 
 static int
@@ -2836,6 +2849,8 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses,
 		usleep_range(512, 2048);
 	} while (++retry_count < 5);
 
+	if (!rc && !dfs_rsp)
+		rc = -EIO;
 	if (rc) {
 		if (!is_retryable_error(rc) && rc != -ENOENT && rc != -EOPNOTSUPP)
 			cifs_tcon_dbg(VFS, "%s: ioctl error: rc=%d\n", __func__, rc);
@@ -2866,248 +2881,107 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses,
 	return rc;
 }
 
-static int
-parse_reparse_posix(struct reparse_posix_data *symlink_buf,
-		      u32 plen, char **target_path,
-		      struct cifs_sb_info *cifs_sb)
+/* See MS-FSCC 2.1.2.6 for the 'NFS' style reparse tags */
+static int parse_reparse_posix(struct reparse_posix_data *buf,
+			       struct cifs_sb_info *cifs_sb,
+			       struct cifs_open_info_data *data)
 {
 	unsigned int len;
-
-	/* See MS-FSCC 2.1.2.6 for the 'NFS' style reparse tags */
-	len = le16_to_cpu(symlink_buf->ReparseDataLength);
-
-	if (le64_to_cpu(symlink_buf->InodeType) != NFS_SPECFILE_LNK) {
-		cifs_dbg(VFS, "%lld not a supported symlink type\n",
-			le64_to_cpu(symlink_buf->InodeType));
+	u64 type;
+
+	switch ((type = le64_to_cpu(buf->InodeType))) {
+	case NFS_SPECFILE_LNK:
+		len = le16_to_cpu(buf->ReparseDataLength);
+		data->symlink_target = cifs_strndup_from_utf16(buf->DataBuffer,
+							       len, true,
+							       cifs_sb->local_nls);
+		if (!data->symlink_target)
+			return -ENOMEM;
+		convert_delimiter(data->symlink_target, '/');
+		cifs_dbg(FYI, "%s: target path: %s\n",
+			 __func__, data->symlink_target);
+		break;
+	case NFS_SPECFILE_CHR:
+	case NFS_SPECFILE_BLK:
+	case NFS_SPECFILE_FIFO:
+	case NFS_SPECFILE_SOCK:
+		break;
+	default:
+		cifs_dbg(VFS, "%s: unhandled inode type: 0x%llx\n",
+			 __func__, type);
 		return -EOPNOTSUPP;
 	}
-
-	*target_path = cifs_strndup_from_utf16(
-				symlink_buf->PathBuffer,
-				len, true, cifs_sb->local_nls);
-	if (!(*target_path))
-		return -ENOMEM;
-
-	convert_delimiter(*target_path, '/');
-	cifs_dbg(FYI, "%s: target path: %s\n", __func__, *target_path);
-
 	return 0;
 }
 
-static int
-parse_reparse_symlink(struct reparse_symlink_data_buffer *symlink_buf,
-		      u32 plen, char **target_path,
-		      struct cifs_sb_info *cifs_sb)
+static int parse_reparse_symlink(struct reparse_symlink_data_buffer *sym,
+				 u32 plen, bool unicode,
+				 struct cifs_sb_info *cifs_sb,
+				 struct cifs_open_info_data *data)
 {
-	unsigned int sub_len;
-	unsigned int sub_offset;
+	unsigned int len;
+	unsigned int offs;
 
 	/* We handle Symbolic Link reparse tag here. See: MS-FSCC 2.1.2.4 */
 
-	sub_offset = le16_to_cpu(symlink_buf->SubstituteNameOffset);
-	sub_len = le16_to_cpu(symlink_buf->SubstituteNameLength);
-	if (sub_offset + 20 > plen ||
-	    sub_offset + sub_len + 20 > plen) {
+	offs = le16_to_cpu(sym->SubstituteNameOffset);
+	len = le16_to_cpu(sym->SubstituteNameLength);
+	if (offs + 20 > plen || offs + len + 20 > plen) {
 		cifs_dbg(VFS, "srv returned malformed symlink buffer\n");
 		return -EIO;
 	}
 
-	*target_path = cifs_strndup_from_utf16(
-				symlink_buf->PathBuffer + sub_offset,
-				sub_len, true, cifs_sb->local_nls);
-	if (!(*target_path))
+	data->symlink_target = cifs_strndup_from_utf16(sym->PathBuffer + offs,
+						       len, unicode,
+						       cifs_sb->local_nls);
+	if (!data->symlink_target)
 		return -ENOMEM;
 
-	convert_delimiter(*target_path, '/');
-	cifs_dbg(FYI, "%s: target path: %s\n", __func__, *target_path);
+	convert_delimiter(data->symlink_target, '/');
+	cifs_dbg(FYI, "%s: target path: %s\n", __func__, data->symlink_target);
 
 	return 0;
 }
 
-static int
-parse_reparse_point(struct reparse_data_buffer *buf,
-		    u32 plen, char **target_path,
-		    struct cifs_sb_info *cifs_sb)
+int parse_reparse_point(struct reparse_data_buffer *buf,
+			u32 plen, struct cifs_sb_info *cifs_sb,
+			bool unicode, struct cifs_open_info_data *data)
 {
-	if (plen < sizeof(struct reparse_data_buffer)) {
-		cifs_dbg(VFS, "reparse buffer is too small. Must be at least 8 bytes but was %d\n",
-			 plen);
-		return -EIO;
-	}
-
-	if (plen < le16_to_cpu(buf->ReparseDataLength) +
-	    sizeof(struct reparse_data_buffer)) {
-		cifs_dbg(VFS, "srv returned invalid reparse buf length: %d\n",
-			 plen);
-		return -EIO;
-	}
+	data->reparse.buf = buf;
 
 	/* See MS-FSCC 2.1.2 */
 	switch (le32_to_cpu(buf->ReparseTag)) {
 	case IO_REPARSE_TAG_NFS:
-		return parse_reparse_posix(
-			(struct reparse_posix_data *)buf,
-			plen, target_path, cifs_sb);
+		return parse_reparse_posix((struct reparse_posix_data *)buf,
+					   cifs_sb, data);
 	case IO_REPARSE_TAG_SYMLINK:
 		return parse_reparse_symlink(
 			(struct reparse_symlink_data_buffer *)buf,
-			plen, target_path, cifs_sb);
+			plen, unicode, cifs_sb, data);
+	case IO_REPARSE_TAG_LX_SYMLINK:
+	case IO_REPARSE_TAG_AF_UNIX:
+	case IO_REPARSE_TAG_LX_FIFO:
+	case IO_REPARSE_TAG_LX_CHR:
+	case IO_REPARSE_TAG_LX_BLK:
+		return 0;
 	default:
-		cifs_dbg(VFS, "srv returned unknown symlink buffer tag:0x%08x\n",
-			 le32_to_cpu(buf->ReparseTag));
+		cifs_dbg(VFS, "%s: unhandled reparse tag: 0x%08x\n",
+			 __func__, le32_to_cpu(buf->ReparseTag));
 		return -EOPNOTSUPP;
 	}
 }
 
-static int smb2_query_symlink(const unsigned int xid,
-			      struct cifs_tcon *tcon,
-			      struct cifs_sb_info *cifs_sb,
-			      const char *full_path,
-			      char **target_path,
-			      struct kvec *rsp_iov)
+static int smb2_parse_reparse_point(struct cifs_sb_info *cifs_sb,
+				    struct kvec *rsp_iov,
+				    struct cifs_open_info_data *data)
 {
 	struct reparse_data_buffer *buf;
 	struct smb2_ioctl_rsp *io = rsp_iov->iov_base;
 	u32 plen = le32_to_cpu(io->OutputCount);
 
-	cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path);
-
 	buf = (struct reparse_data_buffer *)((u8 *)io +
 					     le32_to_cpu(io->OutputOffset));
-	return parse_reparse_point(buf, plen, target_path, cifs_sb);
-}
-
-static int smb2_query_reparse_point(const unsigned int xid,
-				    struct cifs_tcon *tcon,
-				    struct cifs_sb_info *cifs_sb,
-				    const char *full_path,
-				    u32 *tag, struct kvec *rsp,
-				    int *rsp_buftype)
-{
-	struct smb2_compound_vars *vars;
-	int rc;
-	__le16 *utf16_path = NULL;
-	__u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
-	struct cifs_open_parms oparms;
-	struct cifs_fid fid;
-	struct TCP_Server_Info *server = cifs_pick_channel(tcon->ses);
-	int flags = CIFS_CP_CREATE_CLOSE_OP;
-	struct smb_rqst *rqst;
-	int resp_buftype[3];
-	struct kvec *rsp_iov;
-	struct smb2_ioctl_rsp *ioctl_rsp;
-	struct reparse_data_buffer *reparse_buf;
-	u32 plen;
-
-	cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path);
-
-	if (smb3_encryption_required(tcon))
-		flags |= CIFS_TRANSFORM_REQ;
-
-	utf16_path = cifs_convert_path_to_utf16(full_path, cifs_sb);
-	if (!utf16_path)
-		return -ENOMEM;
-
-	resp_buftype[0] = resp_buftype[1] = resp_buftype[2] = CIFS_NO_BUFFER;
-	vars = kzalloc(sizeof(*vars), GFP_KERNEL);
-	if (!vars) {
-		rc = -ENOMEM;
-		goto out_free_path;
-	}
-	rqst = vars->rqst;
-	rsp_iov = vars->rsp_iov;
-
-	/*
-	 * setup smb2open - TODO add optimization to call cifs_get_readable_path
-	 * to see if there is a handle already open that we can use
-	 */
-	rqst[0].rq_iov = vars->open_iov;
-	rqst[0].rq_nvec = SMB2_CREATE_IOV_SIZE;
-
-	oparms = (struct cifs_open_parms) {
-		.tcon = tcon,
-		.path = full_path,
-		.desired_access = FILE_READ_ATTRIBUTES,
-		.disposition = FILE_OPEN,
-		.create_options = cifs_create_options(cifs_sb, OPEN_REPARSE_POINT),
-		.fid = &fid,
-	};
-
-	rc = SMB2_open_init(tcon, server,
-			    &rqst[0], &oplock, &oparms, utf16_path);
-	if (rc)
-		goto query_rp_exit;
-	smb2_set_next_command(tcon, &rqst[0]);
-
-
-	/* IOCTL */
-	rqst[1].rq_iov = vars->io_iov;
-	rqst[1].rq_nvec = SMB2_IOCTL_IOV_SIZE;
-
-	rc = SMB2_ioctl_init(tcon, server,
-			     &rqst[1], COMPOUND_FID,
-			     COMPOUND_FID, FSCTL_GET_REPARSE_POINT, NULL, 0,
-			     CIFSMaxBufSize -
-			     MAX_SMB2_CREATE_RESPONSE_SIZE -
-			     MAX_SMB2_CLOSE_RESPONSE_SIZE);
-	if (rc)
-		goto query_rp_exit;
-
-	smb2_set_next_command(tcon, &rqst[1]);
-	smb2_set_related(&rqst[1]);
-
-	/* Close */
-	rqst[2].rq_iov = &vars->close_iov;
-	rqst[2].rq_nvec = 1;
-
-	rc = SMB2_close_init(tcon, server,
-			     &rqst[2], COMPOUND_FID, COMPOUND_FID, false);
-	if (rc)
-		goto query_rp_exit;
-
-	smb2_set_related(&rqst[2]);
-
-	rc = compound_send_recv(xid, tcon->ses, server,
-				flags, 3, rqst,
-				resp_buftype, rsp_iov);
-
-	ioctl_rsp = rsp_iov[1].iov_base;
-
-	/*
-	 * Open was successful and we got an ioctl response.
-	 */
-	if (rc == 0) {
-		/* See MS-FSCC 2.3.23 */
-
-		reparse_buf = (struct reparse_data_buffer *)
-			((char *)ioctl_rsp +
-			 le32_to_cpu(ioctl_rsp->OutputOffset));
-		plen = le32_to_cpu(ioctl_rsp->OutputCount);
-
-		if (plen + le32_to_cpu(ioctl_rsp->OutputOffset) >
-		    rsp_iov[1].iov_len) {
-			cifs_tcon_dbg(FYI, "srv returned invalid ioctl len: %d\n",
-				 plen);
-			rc = -EIO;
-			goto query_rp_exit;
-		}
-		*tag = le32_to_cpu(reparse_buf->ReparseTag);
-		*rsp = rsp_iov[1];
-		*rsp_buftype = resp_buftype[1];
-		resp_buftype[1] = CIFS_NO_BUFFER;
-	}
-
- query_rp_exit:
-	SMB2_open_free(&rqst[0]);
-	SMB2_ioctl_free(&rqst[1]);
-	SMB2_close_free(&rqst[2]);
-	free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base);
-	free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base);
-	free_rsp_buf(resp_buftype[2], rsp_iov[2].iov_base);
-	kfree(vars);
-out_free_path:
-	kfree(utf16_path);
-	return rc;
+	return parse_reparse_point(buf, plen, cifs_sb, true, data);
 }
 
 static struct cifs_ntsd *
@@ -3307,9 +3181,9 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 	struct inode *inode = file_inode(file);
 	struct cifsInodeInfo *cifsi = CIFS_I(inode);
 	struct cifsFileInfo *cfile = file->private_data;
+	unsigned long long new_size;
 	long rc;
 	unsigned int xid;
-	__le64 eof;
 
 	xid = get_xid();
 
@@ -3337,10 +3211,14 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 	/*
 	 * do we also need to change the size of the file?
 	 */
-	if (keep_size == false && i_size_read(inode) < offset + len) {
-		eof = cpu_to_le64(offset + len);
+	new_size = offset + len;
+	if (keep_size == false && (unsigned long long)i_size_read(inode) < new_size) {
 		rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
-				  cfile->fid.volatile_fid, cfile->pid, &eof);
+				  cfile->fid.volatile_fid, cfile->pid, new_size);
+		if (rc >= 0) {
+			truncate_setsize(inode, new_size);
+			fscache_resize_cookie(cifs_inode_cookie(inode), new_size);
+		}
 	}
 
  zero_range_exit:
@@ -3529,7 +3407,7 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
 	struct cifsFileInfo *cfile = file->private_data;
 	long rc = -EOPNOTSUPP;
 	unsigned int xid;
-	__le64 eof;
+	loff_t new_eof;
 
 	xid = get_xid();
 
@@ -3558,14 +3436,14 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
 		if (cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE)
 			smb2_set_sparse(xid, tcon, cfile, inode, false);
 
-		eof = cpu_to_le64(off + len);
+		new_eof = off + len;
 		rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
-				  cfile->fid.volatile_fid, cfile->pid, &eof);
+				  cfile->fid.volatile_fid, cfile->pid, new_eof);
 		if (rc == 0) {
-			cifsi->server_eof = off + len;
-			cifs_setsize(inode, off + len);
+			cifsi->server_eof = new_eof;
+			cifs_setsize(inode, new_eof);
 			cifs_truncate_page(inode->i_mapping, inode->i_size);
-			truncate_setsize(inode, off + len);
+			truncate_setsize(inode, new_eof);
 		}
 		goto out;
 	}
@@ -3656,8 +3534,7 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon,
 	struct inode *inode = file_inode(file);
 	struct cifsFileInfo *cfile = file->private_data;
 	struct cifsInodeInfo *cifsi = CIFS_I(inode);
-	__le64 eof;
-	loff_t old_eof;
+	loff_t old_eof, new_eof;
 
 	xid = get_xid();
 
@@ -3682,9 +3559,9 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon,
 	if (rc < 0)
 		goto out_2;
 
-	eof = cpu_to_le64(old_eof - len);
+	new_eof = old_eof - len;
 	rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
-			  cfile->fid.volatile_fid, cfile->pid, &eof);
+			  cfile->fid.volatile_fid, cfile->pid, new_eof);
 	if (rc < 0)
 		goto out_2;
 
@@ -3708,8 +3585,7 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon,
 	unsigned int xid;
 	struct cifsFileInfo *cfile = file->private_data;
 	struct inode *inode = file_inode(file);
-	__le64 eof;
-	__u64  count, old_eof;
+	__u64 count, old_eof, new_eof;
 
 	xid = get_xid();
 
@@ -3722,19 +3598,22 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon,
 	}
 
 	count = old_eof - off;
-	eof = cpu_to_le64(old_eof + len);
+	new_eof = old_eof + len;
 
 	filemap_invalidate_lock(inode->i_mapping);
-	rc = filemap_write_and_wait_range(inode->i_mapping, off, old_eof + len - 1);
+	rc = filemap_write_and_wait_range(inode->i_mapping, off, new_eof - 1);
 	if (rc < 0)
 		goto out_2;
 	truncate_pagecache_range(inode, off, old_eof);
 
 	rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
-			  cfile->fid.volatile_fid, cfile->pid, &eof);
+			  cfile->fid.volatile_fid, cfile->pid, new_eof);
 	if (rc < 0)
 		goto out_2;
 
+	truncate_setsize(inode, new_eof);
+	fscache_resize_cookie(cifs_inode_cookie(inode), i_size_read(inode));
+
 	rc = smb2_copychunk_range(xid, cfile, cfile, off, count, off + len);
 	if (rc < 0)
 		goto out_2;
@@ -4928,6 +4807,7 @@ receive_encrypted_standard(struct TCP_Server_Info *server,
 	struct smb2_hdr *shdr;
 	unsigned int pdu_length = server->pdu_size;
 	unsigned int buf_size;
+	unsigned int next_cmd;
 	struct mid_q_entry *mid_entry;
 	int next_is_large;
 	char *next_buffer = NULL;
@@ -4956,14 +4836,15 @@ receive_encrypted_standard(struct TCP_Server_Info *server,
 	next_is_large = server->large_buf;
 one_more:
 	shdr = (struct smb2_hdr *)buf;
-	if (shdr->NextCommand) {
+	next_cmd = le32_to_cpu(shdr->NextCommand);
+	if (next_cmd) {
+		if (WARN_ON_ONCE(next_cmd > pdu_length))
+			return -1;
 		if (next_is_large)
 			next_buffer = (char *)cifs_buf_get();
 		else
 			next_buffer = (char *)cifs_small_buf_get();
-		memcpy(next_buffer,
-		       buf + le32_to_cpu(shdr->NextCommand),
-		       pdu_length - le32_to_cpu(shdr->NextCommand));
+		memcpy(next_buffer, buf + next_cmd, pdu_length - next_cmd);
 	}
 
 	mid_entry = smb2_find_mid(server, buf);
@@ -4987,8 +4868,8 @@ one_more:
 	else
 		ret = cifs_handle_standard(server, mid_entry);
 
-	if (ret == 0 && shdr->NextCommand) {
-		pdu_length -= le32_to_cpu(shdr->NextCommand);
+	if (ret == 0 && next_cmd) {
+		pdu_length -= next_cmd;
 		server->large_buf = next_is_large;
 		if (next_is_large)
 			server->bigbuf = buf = next_buffer;
@@ -5051,54 +4932,42 @@ smb3_handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 				NULL, 0, false);
 }
 
-static int
-smb2_next_header(char *buf)
+static int smb2_next_header(struct TCP_Server_Info *server, char *buf,
+			    unsigned int *noff)
 {
 	struct smb2_hdr *hdr = (struct smb2_hdr *)buf;
 	struct smb2_transform_hdr *t_hdr = (struct smb2_transform_hdr *)buf;
 
-	if (hdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM)
-		return sizeof(struct smb2_transform_hdr) +
-		  le32_to_cpu(t_hdr->OriginalMessageSize);
-
-	return le32_to_cpu(hdr->NextCommand);
+	if (hdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) {
+		*noff = le32_to_cpu(t_hdr->OriginalMessageSize);
+		if (unlikely(check_add_overflow(*noff, sizeof(*t_hdr), noff)))
+			return -EINVAL;
+	} else {
+		*noff = le32_to_cpu(hdr->NextCommand);
+	}
+	if (unlikely(*noff && *noff < MID_HEADER_SIZE(server)))
+		return -EINVAL;
+	return 0;
 }
 
-static int
-smb2_make_node(unsigned int xid, struct inode *inode,
-	       struct dentry *dentry, struct cifs_tcon *tcon,
-	       const char *full_path, umode_t mode, dev_t dev)
+int cifs_sfu_make_node(unsigned int xid, struct inode *inode,
+		       struct dentry *dentry, struct cifs_tcon *tcon,
+		       const char *full_path, umode_t mode, dev_t dev)
 {
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
-	int rc = -EPERM;
 	struct cifs_open_info_data buf = {};
-	struct cifs_io_parms io_parms = {0};
-	__u32 oplock = 0;
-	struct cifs_fid fid;
+	struct TCP_Server_Info *server = tcon->ses->server;
 	struct cifs_open_parms oparms;
+	struct cifs_io_parms io_parms = {};
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_fid fid;
 	unsigned int bytes_written;
 	struct win_dev *pdev;
 	struct kvec iov[2];
-
-	/*
-	 * Check if mounted with mount parm 'sfu' mount parm.
-	 * SFU emulation should work with all servers, but only
-	 * supports block and char device (no socket & fifo),
-	 * and was used by default in earlier versions of Windows
-	 */
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL))
-		return rc;
-
-	/*
-	 * TODO: Add ability to create instead via reparse point. Windows (e.g.
-	 * their current NFS server) uses this approach to expose special files
-	 * over SMB2/SMB3 and Samba will do this with SMB3.1.1 POSIX Extensions
-	 */
+	__u32 oplock = server->oplocks ? REQ_OPLOCK : 0;
+	int rc;
 
 	if (!S_ISCHR(mode) && !S_ISBLK(mode) && !S_ISFIFO(mode))
-		return rc;
-
-	cifs_dbg(FYI, "sfu compat create special file\n");
+		return -EPERM;
 
 	oparms = (struct cifs_open_parms) {
 		.tcon = tcon,
@@ -5111,11 +4980,7 @@ smb2_make_node(unsigned int xid, struct inode *inode,
 		.fid = &fid,
 	};
 
-	if (tcon->ses->server->oplocks)
-		oplock = REQ_OPLOCK;
-	else
-		oplock = 0;
-	rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, &buf);
+	rc = server->ops->open(xid, &oparms, &oplock, &buf);
 	if (rc)
 		return rc;
 
@@ -5123,42 +4988,198 @@ smb2_make_node(unsigned int xid, struct inode *inode,
 	 * BB Do not bother to decode buf since no local inode yet to put
 	 * timestamps in, but we can reuse it safely.
 	 */
-
 	pdev = (struct win_dev *)&buf.fi;
 	io_parms.pid = current->tgid;
 	io_parms.tcon = tcon;
-	io_parms.offset = 0;
-	io_parms.length = sizeof(struct win_dev);
-	iov[1].iov_base = &buf.fi;
-	iov[1].iov_len = sizeof(struct win_dev);
+	io_parms.length = sizeof(*pdev);
+	iov[1].iov_base = pdev;
+	iov[1].iov_len = sizeof(*pdev);
 	if (S_ISCHR(mode)) {
 		memcpy(pdev->type, "IntxCHR", 8);
 		pdev->major = cpu_to_le64(MAJOR(dev));
 		pdev->minor = cpu_to_le64(MINOR(dev));
-		rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms,
-							&bytes_written, iov, 1);
 	} else if (S_ISBLK(mode)) {
 		memcpy(pdev->type, "IntxBLK", 8);
 		pdev->major = cpu_to_le64(MAJOR(dev));
 		pdev->minor = cpu_to_le64(MINOR(dev));
-		rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms,
-							&bytes_written, iov, 1);
 	} else if (S_ISFIFO(mode)) {
 		memcpy(pdev->type, "LnxFIFO", 8);
-		pdev->major = 0;
-		pdev->minor = 0;
-		rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms,
-							&bytes_written, iov, 1);
 	}
-	tcon->ses->server->ops->close(xid, tcon, &fid);
-	d_drop(dentry);
 
+	rc = server->ops->sync_write(xid, &fid, &io_parms,
+				     &bytes_written, iov, 1);
+	server->ops->close(xid, tcon, &fid);
+	d_drop(dentry);
 	/* FIXME: add code here to set EAs */
-
 	cifs_free_open_info(&buf);
 	return rc;
 }
 
+static inline u64 mode_nfs_type(mode_t mode)
+{
+	switch (mode & S_IFMT) {
+	case S_IFBLK: return NFS_SPECFILE_BLK;
+	case S_IFCHR: return NFS_SPECFILE_CHR;
+	case S_IFIFO: return NFS_SPECFILE_FIFO;
+	case S_IFSOCK: return NFS_SPECFILE_SOCK;
+	}
+	return 0;
+}
+
+static int nfs_set_reparse_buf(struct reparse_posix_data *buf,
+			       mode_t mode, dev_t dev,
+			       struct kvec *iov)
+{
+	u64 type;
+	u16 len, dlen;
+
+	len = sizeof(*buf);
+
+	switch ((type = mode_nfs_type(mode))) {
+	case NFS_SPECFILE_BLK:
+	case NFS_SPECFILE_CHR:
+		dlen = sizeof(__le64);
+		break;
+	case NFS_SPECFILE_FIFO:
+	case NFS_SPECFILE_SOCK:
+		dlen = 0;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	buf->ReparseTag = cpu_to_le32(IO_REPARSE_TAG_NFS);
+	buf->Reserved = 0;
+	buf->InodeType = cpu_to_le64(type);
+	buf->ReparseDataLength = cpu_to_le16(len + dlen -
+					     sizeof(struct reparse_data_buffer));
+	*(__le64 *)buf->DataBuffer = cpu_to_le64(((u64)MAJOR(dev) << 32) |
+						 MINOR(dev));
+	iov->iov_base = buf;
+	iov->iov_len = len + dlen;
+	return 0;
+}
+
+static int nfs_make_node(unsigned int xid, struct inode *inode,
+			 struct dentry *dentry, struct cifs_tcon *tcon,
+			 const char *full_path, umode_t mode, dev_t dev)
+{
+	struct cifs_open_info_data data;
+	struct reparse_posix_data *p;
+	struct inode *new;
+	struct kvec iov;
+	__u8 buf[sizeof(*p) + sizeof(__le64)];
+	int rc;
+
+	p = (struct reparse_posix_data *)buf;
+	rc = nfs_set_reparse_buf(p, mode, dev, &iov);
+	if (rc)
+		return rc;
+
+	data = (struct cifs_open_info_data) {
+		.reparse_point = true,
+		.reparse = { .tag = IO_REPARSE_TAG_NFS, .posix = p, },
+	};
+
+	new = smb2_get_reparse_inode(&data, inode->i_sb, xid,
+				     tcon, full_path, &iov);
+	if (!IS_ERR(new))
+		d_instantiate(dentry, new);
+	else
+		rc = PTR_ERR(new);
+	cifs_free_open_info(&data);
+	return rc;
+}
+
+static int smb2_create_reparse_symlink(const unsigned int xid,
+				       struct inode *inode,
+				       struct dentry *dentry,
+				       struct cifs_tcon *tcon,
+				       const char *full_path,
+				       const char *symname)
+{
+	struct reparse_symlink_data_buffer *buf = NULL;
+	struct cifs_open_info_data data;
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct inode *new;
+	struct kvec iov;
+	__le16 *path;
+	char *sym;
+	u16 len, plen;
+	int rc = 0;
+
+	sym = kstrdup(symname, GFP_KERNEL);
+	if (!sym)
+		return -ENOMEM;
+
+	data = (struct cifs_open_info_data) {
+		.reparse_point = true,
+		.reparse = { .tag = IO_REPARSE_TAG_SYMLINK, },
+		.symlink_target = sym,
+	};
+
+	path = cifs_convert_path_to_utf16(symname, cifs_sb);
+	if (!path) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	plen = 2 * UniStrnlen((wchar_t *)path, PATH_MAX);
+	len = sizeof(*buf) + plen * 2;
+	buf = kzalloc(len, GFP_KERNEL);
+	if (!buf) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	buf->ReparseTag = cpu_to_le32(IO_REPARSE_TAG_SYMLINK);
+	buf->ReparseDataLength = cpu_to_le16(len - sizeof(struct reparse_data_buffer));
+	buf->SubstituteNameOffset = cpu_to_le16(plen);
+	buf->SubstituteNameLength = cpu_to_le16(plen);
+	memcpy(&buf->PathBuffer[plen], path, plen);
+	buf->PrintNameOffset = 0;
+	buf->PrintNameLength = cpu_to_le16(plen);
+	memcpy(buf->PathBuffer, path, plen);
+	buf->Flags = cpu_to_le32(*symname != '/' ? SYMLINK_FLAG_RELATIVE : 0);
+
+	iov.iov_base = buf;
+	iov.iov_len = len;
+	new = smb2_get_reparse_inode(&data, inode->i_sb, xid,
+				     tcon, full_path, &iov);
+	if (!IS_ERR(new))
+		d_instantiate(dentry, new);
+	else
+		rc = PTR_ERR(new);
+out:
+	kfree(path);
+	cifs_free_open_info(&data);
+	kfree(buf);
+	return rc;
+}
+
+static int smb2_make_node(unsigned int xid, struct inode *inode,
+			  struct dentry *dentry, struct cifs_tcon *tcon,
+			  const char *full_path, umode_t mode, dev_t dev)
+{
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	int rc;
+
+	/*
+	 * Check if mounted with mount parm 'sfu' mount parm.
+	 * SFU emulation should work with all servers, but only
+	 * supports block and char device (no socket & fifo),
+	 * and was used by default in earlier versions of Windows
+	 */
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) {
+		rc = cifs_sfu_make_node(xid, inode, dentry, tcon,
+					full_path, mode, dev);
+	} else {
+		rc = nfs_make_node(xid, inode, dentry, tcon,
+				   full_path, mode, dev);
+	}
+	return rc;
+}
+
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 struct smb_version_operations smb20_operations = {
 	.compare_fids = smb2_compare_fids,
@@ -5209,9 +5230,10 @@ struct smb_version_operations smb20_operations = {
 	.unlink = smb2_unlink,
 	.rename = smb2_rename_path,
 	.create_hardlink = smb2_create_hardlink,
-	.query_symlink = smb2_query_symlink,
+	.parse_reparse_point = smb2_parse_reparse_point,
 	.query_mf_symlink = smb3_query_mf_symlink,
 	.create_mf_symlink = smb3_create_mf_symlink,
+	.create_reparse_symlink = smb2_create_reparse_symlink,
 	.open = smb2_open_file,
 	.set_fid = smb2_set_fid,
 	.close = smb2_close_file,
@@ -5311,9 +5333,10 @@ struct smb_version_operations smb21_operations = {
 	.unlink = smb2_unlink,
 	.rename = smb2_rename_path,
 	.create_hardlink = smb2_create_hardlink,
-	.query_symlink = smb2_query_symlink,
+	.parse_reparse_point = smb2_parse_reparse_point,
 	.query_mf_symlink = smb3_query_mf_symlink,
 	.create_mf_symlink = smb3_create_mf_symlink,
+	.create_reparse_symlink = smb2_create_reparse_symlink,
 	.open = smb2_open_file,
 	.set_fid = smb2_set_fid,
 	.close = smb2_close_file,
@@ -5416,9 +5439,10 @@ struct smb_version_operations smb30_operations = {
 	.unlink = smb2_unlink,
 	.rename = smb2_rename_path,
 	.create_hardlink = smb2_create_hardlink,
-	.query_symlink = smb2_query_symlink,
+	.parse_reparse_point = smb2_parse_reparse_point,
 	.query_mf_symlink = smb3_query_mf_symlink,
 	.create_mf_symlink = smb3_create_mf_symlink,
+	.create_reparse_symlink = smb2_create_reparse_symlink,
 	.open = smb2_open_file,
 	.set_fid = smb2_set_fid,
 	.close = smb2_close_file,
@@ -5530,9 +5554,10 @@ struct smb_version_operations smb311_operations = {
 	.unlink = smb2_unlink,
 	.rename = smb2_rename_path,
 	.create_hardlink = smb2_create_hardlink,
-	.query_symlink = smb2_query_symlink,
+	.parse_reparse_point = smb2_parse_reparse_point,
 	.query_mf_symlink = smb3_query_mf_symlink,
 	.create_mf_symlink = smb3_create_mf_symlink,
+	.create_reparse_symlink = smb2_create_reparse_symlink,
 	.open = smb2_open_file,
 	.set_fid = smb2_set_fid,
 	.close = smb2_close_file,
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 2eb29fa278c3..bd25c34dc398 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -158,7 +158,7 @@ out:
 
 static int
 smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon,
-	       struct TCP_Server_Info *server)
+	       struct TCP_Server_Info *server, bool from_reconnect)
 {
 	int rc = 0;
 	struct nls_table *nls_codepage = NULL;
@@ -331,7 +331,7 @@ again:
 				 * as cifs_put_tcp_session takes a higher lock
 				 * i.e. cifs_tcp_ses_lock
 				 */
-				cifs_put_tcp_session(server, 1);
+				cifs_put_tcp_session(server, from_reconnect);
 
 				server->terminate = true;
 				cifs_signal_cifsd_for_reconnect(server, false);
@@ -411,8 +411,7 @@ skip_sess_setup:
 	}
 
 	if (smb2_command != SMB2_INTERNAL_CMD)
-		if (mod_delayed_work(cifsiod_wq, &server->reconnect, 0))
-			cifs_put_tcp_session(server, false);
+		mod_delayed_work(cifsiod_wq, &server->reconnect, 0);
 
 	atomic_inc(&tconInfoReconnectCount);
 out:
@@ -471,10 +470,15 @@ static int __smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
 				 void **request_buf, unsigned int *total_len)
 {
 	/* BB eventually switch this to SMB2 specific small buf size */
-	if (smb2_command == SMB2_SET_INFO)
+	switch (smb2_command) {
+	case SMB2_SET_INFO:
+	case SMB2_QUERY_INFO:
 		*request_buf = cifs_buf_get();
-	else
+		break;
+	default:
 		*request_buf = cifs_small_buf_get();
+		break;
+	}
 	if (*request_buf == NULL) {
 		/* BB should we add a retry in here if not a writepage? */
 		return -ENOMEM;
@@ -499,7 +503,7 @@ static int smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
 {
 	int rc;
 
-	rc = smb2_reconnect(smb2_command, tcon, server);
+	rc = smb2_reconnect(smb2_command, tcon, server, false);
 	if (rc)
 		return rc;
 
@@ -2236,17 +2240,18 @@ parse_posix_ctxt(struct create_context *cc, struct smb2_file_all_info *info,
 		 posix->nlink, posix->mode, posix->reparse_tag);
 }
 
-void
-smb2_parse_contexts(struct TCP_Server_Info *server,
-		    struct smb2_create_rsp *rsp,
-		    unsigned int *epoch, char *lease_key, __u8 *oplock,
-		    struct smb2_file_all_info *buf,
-		    struct create_posix_rsp *posix)
+int smb2_parse_contexts(struct TCP_Server_Info *server,
+			struct kvec *rsp_iov,
+			unsigned int *epoch,
+			char *lease_key, __u8 *oplock,
+			struct smb2_file_all_info *buf,
+			struct create_posix_rsp *posix)
 {
-	char *data_offset;
+	struct smb2_create_rsp *rsp = rsp_iov->iov_base;
 	struct create_context *cc;
-	unsigned int next;
-	unsigned int remaining;
+	size_t rem, off, len;
+	size_t doff, dlen;
+	size_t noff, nlen;
 	char *name;
 	static const char smb3_create_tag_posix[] = {
 		0x93, 0xAD, 0x25, 0x50, 0x9C,
@@ -2255,45 +2260,63 @@ smb2_parse_contexts(struct TCP_Server_Info *server,
 	};
 
 	*oplock = 0;
-	data_offset = (char *)rsp + le32_to_cpu(rsp->CreateContextsOffset);
-	remaining = le32_to_cpu(rsp->CreateContextsLength);
-	cc = (struct create_context *)data_offset;
+
+	off = le32_to_cpu(rsp->CreateContextsOffset);
+	rem = le32_to_cpu(rsp->CreateContextsLength);
+	if (check_add_overflow(off, rem, &len) || len > rsp_iov->iov_len)
+		return -EINVAL;
+	cc = (struct create_context *)((u8 *)rsp + off);
 
 	/* Initialize inode number to 0 in case no valid data in qfid context */
 	if (buf)
 		buf->IndexNumber = 0;
 
-	while (remaining >= sizeof(struct create_context)) {
-		name = le16_to_cpu(cc->NameOffset) + (char *)cc;
-		if (le16_to_cpu(cc->NameLength) == 4 &&
-		    strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4) == 0)
-			*oplock = server->ops->parse_lease_buf(cc, epoch,
-							   lease_key);
-		else if (buf && (le16_to_cpu(cc->NameLength) == 4) &&
-		    strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4) == 0)
-			parse_query_id_ctxt(cc, buf);
-		else if ((le16_to_cpu(cc->NameLength) == 16)) {
-			if (posix &&
-			    memcmp(name, smb3_create_tag_posix, 16) == 0)
+	while (rem >= sizeof(*cc)) {
+		doff = le16_to_cpu(cc->DataOffset);
+		dlen = le32_to_cpu(cc->DataLength);
+		if (check_add_overflow(doff, dlen, &len) || len > rem)
+			return -EINVAL;
+
+		noff = le16_to_cpu(cc->NameOffset);
+		nlen = le16_to_cpu(cc->NameLength);
+		if (noff + nlen >= doff)
+			return -EINVAL;
+
+		name = (char *)cc + noff;
+		switch (nlen) {
+		case 4:
+			if (!strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4)) {
+				*oplock = server->ops->parse_lease_buf(cc, epoch,
+								       lease_key);
+			} else if (buf &&
+				   !strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4)) {
+				parse_query_id_ctxt(cc, buf);
+			}
+			break;
+		case 16:
+			if (posix && !memcmp(name, smb3_create_tag_posix, 16))
 				parse_posix_ctxt(cc, buf, posix);
+			break;
+		default:
+			cifs_dbg(FYI, "%s: unhandled context (nlen=%zu dlen=%zu)\n",
+				 __func__, nlen, dlen);
+			if (IS_ENABLED(CONFIG_CIFS_DEBUG2))
+				cifs_dump_mem("context data: ", cc, dlen);
+			break;
 		}
-		/* else {
-			cifs_dbg(FYI, "Context not matched with len %d\n",
-				le16_to_cpu(cc->NameLength));
-			cifs_dump_mem("Cctxt name: ", name, 4);
-		} */
-
-		next = le32_to_cpu(cc->Next);
-		if (!next)
+
+		off = le32_to_cpu(cc->Next);
+		if (!off)
 			break;
-		remaining -= next;
-		cc = (struct create_context *)((char *)cc + next);
+		if (check_sub_overflow(rem, off, &rem))
+			return -EINVAL;
+		cc = (struct create_context *)((u8 *)cc + off);
 	}
 
 	if (rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE)
 		*oplock = rsp->OplockLevel;
 
-	return;
+	return 0;
 }
 
 static int
@@ -3124,8 +3147,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	}
 
 
-	smb2_parse_contexts(server, rsp, &oparms->fid->epoch,
-			    oparms->fid->lease_key, oplock, buf, posix);
+	rc = smb2_parse_contexts(server, &rsp_iov, &oparms->fid->epoch,
+				 oparms->fid->lease_key, oplock, buf, posix);
 creat_exit:
 	SMB2_open_free(&rqst);
 	free_rsp_buf(resp_buftype, rsp);
@@ -3472,12 +3495,10 @@ __SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 	} else {
 		trace_smb3_close_done(xid, persistent_fid, tcon->tid,
 				      ses->Suid);
-		/*
-		 * Note that have to subtract 4 since struct network_open_info
-		 * has a final 4 byte pad that close response does not have
-		 */
 		if (pbuf)
-			memcpy(pbuf, (char *)&rsp->CreationTime, sizeof(*pbuf) - 4);
+			memcpy(&pbuf->network_open_info,
+			       &rsp->network_open_info,
+			       sizeof(pbuf->network_open_info));
 	}
 
 	atomic_dec(&tcon->num_remote_opens);
@@ -3570,8 +3591,13 @@ SMB2_query_info_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server,
 	struct smb2_query_info_req *req;
 	struct kvec *iov = rqst->rq_iov;
 	unsigned int total_len;
+	size_t len;
 	int rc;
 
+	if (unlikely(check_add_overflow(input_len, sizeof(*req), &len) ||
+		     len > CIFSMaxBufSize))
+		return -EINVAL;
+
 	rc = smb2_plain_req_init(SMB2_QUERY_INFO, tcon, server,
 				 (void **) &req, &total_len);
 	if (rc)
@@ -3593,7 +3619,7 @@ SMB2_query_info_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server,
 
 	iov[0].iov_base = (char *)req;
 	/* 1 for Buffer */
-	iov[0].iov_len = total_len - 1 + input_len;
+	iov[0].iov_len = len;
 	return 0;
 }
 
@@ -3601,7 +3627,7 @@ void
 SMB2_query_info_free(struct smb_rqst *rqst)
 {
 	if (rqst && rqst->rq_iov)
-		cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */
+		cifs_buf_release(rqst->rq_iov[0].iov_base); /* request */
 }
 
 static int
@@ -3897,6 +3923,15 @@ void smb2_reconnect_server(struct work_struct *work)
 	int rc;
 	bool resched = false;
 
+	/* first check if ref count has reached 0, if not inc ref count */
+	spin_lock(&cifs_tcp_ses_lock);
+	if (!server->srv_count) {
+		spin_unlock(&cifs_tcp_ses_lock);
+		return;
+	}
+	server->srv_count++;
+	spin_unlock(&cifs_tcp_ses_lock);
+
 	/* If server is a channel, select the primary channel */
 	pserver = SERVER_IS_CHAN(server) ? server->primary_server : server;
 
@@ -3954,11 +3989,10 @@ void smb2_reconnect_server(struct work_struct *work)
 		}
 		spin_unlock(&ses->chan_lock);
 	}
-
 	spin_unlock(&cifs_tcp_ses_lock);
 
 	list_for_each_entry_safe(tcon, tcon2, &tmp_list, rlist) {
-		rc = smb2_reconnect(SMB2_INTERNAL_CMD, tcon, server);
+		rc = smb2_reconnect(SMB2_INTERNAL_CMD, tcon, server, true);
 		if (!rc)
 			cifs_reopen_persistent_handles(tcon);
 		else
@@ -3991,7 +4025,7 @@ void smb2_reconnect_server(struct work_struct *work)
 	/* now reconnect sessions for necessary channels */
 	list_for_each_entry_safe(ses, ses2, &tmp_ses_list, rlist) {
 		tcon->ses = ses;
-		rc = smb2_reconnect(SMB2_INTERNAL_CMD, tcon, server);
+		rc = smb2_reconnect(SMB2_INTERNAL_CMD, tcon, server, true);
 		if (rc)
 			resched = true;
 		list_del_init(&ses->rlist);
@@ -4001,13 +4035,8 @@ void smb2_reconnect_server(struct work_struct *work)
 
 done:
 	cifs_dbg(FYI, "Reconnecting tcons and channels finished\n");
-	if (resched) {
+	if (resched)
 		queue_delayed_work(cifsiod_wq, &server->reconnect, 2 * HZ);
-		mutex_unlock(&pserver->reconnect_mutex);
-
-		/* no need to put tcp session as we're retrying */
-		return;
-	}
 	mutex_unlock(&pserver->reconnect_mutex);
 
 	/* now we can safely release srv struct */
@@ -4031,12 +4060,7 @@ SMB2_echo(struct TCP_Server_Info *server)
 	    server->ops->need_neg(server)) {
 		spin_unlock(&server->srv_lock);
 		/* No need to send echo on newly established connections */
-		spin_lock(&cifs_tcp_ses_lock);
-		server->srv_count++;
-		spin_unlock(&cifs_tcp_ses_lock);
-		if (mod_delayed_work(cifsiod_wq, &server->reconnect, 0))
-			cifs_put_tcp_session(server, false);
-
+		mod_delayed_work(cifsiod_wq, &server->reconnect, 0);
 		return rc;
 	}
 	spin_unlock(&server->srv_lock);
@@ -5323,18 +5347,18 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon,
 
 int
 SMB2_set_eof(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
-	     u64 volatile_fid, u32 pid, __le64 *eof)
+	     u64 volatile_fid, u32 pid, loff_t new_eof)
 {
 	struct smb2_file_eof_info info;
 	void *data;
 	unsigned int size;
 
-	info.EndOfFile = *eof;
+	info.EndOfFile = cpu_to_le64(new_eof);
 
 	data = &info;
 	size = sizeof(struct smb2_file_eof_info);
 
-	trace_smb3_set_eof(xid, persistent_fid, tcon->tid, tcon->ses->Suid, le64_to_cpu(*eof));
+	trace_smb3_set_eof(xid, persistent_fid, tcon->tid, tcon->ses->Suid, new_eof);
 
 	return send_set_info(xid, tcon, persistent_fid, volatile_fid,
 			pid, FILE_END_OF_FILE_INFORMATION, SMB2_O_INFO_FILE,
@@ -5478,6 +5502,11 @@ build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon,
 	return 0;
 }
 
+static inline void free_qfs_info_req(struct kvec *iov)
+{
+	cifs_buf_release(iov->iov_base);
+}
+
 int
 SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon,
 	      u64 persistent_fid, u64 volatile_fid, struct kstatfs *fsdata)
@@ -5509,7 +5538,7 @@ SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
-	cifs_small_buf_release(iov.iov_base);
+	free_qfs_info_req(&iov);
 	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
 		goto posix_qfsinf_exit;
@@ -5560,7 +5589,7 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
-	cifs_small_buf_release(iov.iov_base);
+	free_qfs_info_req(&iov);
 	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
 		goto qfsinf_exit;
@@ -5627,7 +5656,7 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
-	cifs_small_buf_release(iov.iov_base);
+	free_qfs_info_req(&iov);
 	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
 		goto qfsattr_exit;
diff --git a/fs/smb/client/smb2pdu.h b/fs/smb/client/smb2pdu.h
index 220994d0a0f7..db08194484e0 100644
--- a/fs/smb/client/smb2pdu.h
+++ b/fs/smb/client/smb2pdu.h
@@ -319,13 +319,15 @@ struct smb2_file_reparse_point_info {
 } __packed;
 
 struct smb2_file_network_open_info {
-	__le64 CreationTime;
-	__le64 LastAccessTime;
-	__le64 LastWriteTime;
-	__le64 ChangeTime;
-	__le64 AllocationSize;
-	__le64 EndOfFile;
-	__le32 Attributes;
+	struct_group(network_open_info,
+		__le64 CreationTime;
+		__le64 LastAccessTime;
+		__le64 LastWriteTime;
+		__le64 ChangeTime;
+		__le64 AllocationSize;
+		__le64 EndOfFile;
+		__le32 Attributes;
+	);
 	__le32 Reserved;
 } __packed; /* level 34 Query also similar returned in close rsp and open rsp */
 
diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h
index 46eff9ec302a..343ada691e76 100644
--- a/fs/smb/client/smb2proto.h
+++ b/fs/smb/client/smb2proto.h
@@ -56,6 +56,18 @@ extern int smb3_handle_read_data(struct TCP_Server_Info *server,
 extern int smb2_query_reparse_tag(const unsigned int xid, struct cifs_tcon *tcon,
 				struct cifs_sb_info *cifs_sb, const char *path,
 				__u32 *reparse_tag);
+struct inode *smb2_get_reparse_inode(struct cifs_open_info_data *data,
+				     struct super_block *sb,
+				     const unsigned int xid,
+				     struct cifs_tcon *tcon,
+				     const char *full_path,
+				     struct kvec *iov);
+int smb2_query_reparse_point(const unsigned int xid,
+			     struct cifs_tcon *tcon,
+			     struct cifs_sb_info *cifs_sb,
+			     const char *full_path,
+			     u32 *tag, struct kvec *rsp,
+			     int *rsp_buftype);
 int smb2_query_path_info(const unsigned int xid,
 			 struct cifs_tcon *tcon,
 			 struct cifs_sb_info *cifs_sb,
@@ -80,12 +92,16 @@ extern int smb2_rmdir(const unsigned int xid, struct cifs_tcon *tcon,
 		      const char *name, struct cifs_sb_info *cifs_sb);
 extern int smb2_unlink(const unsigned int xid, struct cifs_tcon *tcon,
 		       const char *name, struct cifs_sb_info *cifs_sb);
-extern int smb2_rename_path(const unsigned int xid, struct cifs_tcon *tcon,
-			    const char *from_name, const char *to_name,
-			    struct cifs_sb_info *cifs_sb);
-extern int smb2_create_hardlink(const unsigned int xid, struct cifs_tcon *tcon,
-				const char *from_name, const char *to_name,
-				struct cifs_sb_info *cifs_sb);
+int smb2_rename_path(const unsigned int xid,
+		     struct cifs_tcon *tcon,
+		     struct dentry *source_dentry,
+		     const char *from_name, const char *to_name,
+		     struct cifs_sb_info *cifs_sb);
+int smb2_create_hardlink(const unsigned int xid,
+			 struct cifs_tcon *tcon,
+			 struct dentry *source_dentry,
+			 const char *from_name, const char *to_name,
+			 struct cifs_sb_info *cifs_sb);
 extern int smb3_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
 			struct cifs_sb_info *cifs_sb, const unsigned char *path,
 			char *pbuf, unsigned int *pbytes_written);
@@ -205,7 +221,7 @@ extern int SMB2_query_directory_init(unsigned int xid, struct cifs_tcon *tcon,
 extern void SMB2_query_directory_free(struct smb_rqst *rqst);
 extern int SMB2_set_eof(const unsigned int xid, struct cifs_tcon *tcon,
 			u64 persistent_fid, u64 volatile_fid, u32 pid,
-			__le64 *eof);
+			loff_t new_eof);
 extern int SMB2_set_info_init(struct cifs_tcon *tcon,
 			      struct TCP_Server_Info *server,
 			      struct smb_rqst *rqst,
@@ -251,11 +267,13 @@ extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *);
 
 extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *,
 					enum securityEnum);
-extern void smb2_parse_contexts(struct TCP_Server_Info *server,
-				struct smb2_create_rsp *rsp,
-				unsigned int *epoch, char *lease_key,
-				__u8 *oplock, struct smb2_file_all_info *buf,
-				struct create_posix_rsp *posix);
+int smb2_parse_contexts(struct TCP_Server_Info *server,
+			struct kvec *rsp_iov,
+			unsigned int *epoch,
+			char *lease_key, __u8 *oplock,
+			struct smb2_file_all_info *buf,
+			struct create_posix_rsp *posix);
+
 extern int smb3_encryption_required(const struct cifs_tcon *tcon);
 extern int smb2_validate_iov(unsigned int offset, unsigned int buffer_length,
 			     struct kvec *iov, unsigned int min_buf_size);
@@ -287,4 +305,5 @@ int smb311_posix_query_path_info(const unsigned int xid,
 int posix_info_parse(const void *beg, const void *end,
 		     struct smb2_posix_info_parsed *out);
 int posix_info_sid_size(const void *beg, const void *end);
+
 #endif			/* _SMB2PROTO_H */
diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c
index 84ea67301303..5a3ca62d2f07 100644
--- a/fs/smb/client/smb2transport.c
+++ b/fs/smb/client/smb2transport.c
@@ -458,6 +458,8 @@ generate_smb3signingkey(struct cifs_ses *ses,
 				  ptriplet->encryption.context,
 				  ses->smb3encryptionkey,
 				  SMB3_ENC_DEC_KEY_SIZE);
+		if (rc)
+			return rc;
 		rc = generate_key(ses, ptriplet->decryption.label,
 				  ptriplet->decryption.context,
 				  ses->smb3decryptionkey,
@@ -466,9 +468,6 @@ generate_smb3signingkey(struct cifs_ses *ses,
 			return rc;
 	}
 
-	if (rc)
-		return rc;
-
 #ifdef CONFIG_CIFS_DEBUG_DUMP_KEYS
 	cifs_dbg(VFS, "%s: dumping generated AES session keys\n", __func__);
 	/*
diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c
index 94df9eec3d8d..d74e829de51c 100644
--- a/fs/smb/client/smbdirect.c
+++ b/fs/smb/client/smbdirect.c
@@ -2136,7 +2136,7 @@ static int allocate_mr_list(struct smbd_connection *info)
 	for (i = 0; i < info->responder_resources * 2; i++) {
 		smbdirect_mr = kzalloc(sizeof(*smbdirect_mr), GFP_KERNEL);
 		if (!smbdirect_mr)
-			goto out;
+			goto cleanup_entries;
 		smbdirect_mr->mr = ib_alloc_mr(info->pd, info->mr_type,
 					info->max_frmr_depth);
 		if (IS_ERR(smbdirect_mr->mr)) {
@@ -2162,7 +2162,7 @@ static int allocate_mr_list(struct smbd_connection *info)
 
 out:
 	kfree(smbdirect_mr);
-
+cleanup_entries:
 	list_for_each_entry_safe(smbdirect_mr, tmp, &info->mr_list, list) {
 		list_del(&smbdirect_mr->list);
 		ib_dereg_mr(smbdirect_mr->mr);
diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h
index de199ec9f726..522fa387fcfd 100644
--- a/fs/smb/client/trace.h
+++ b/fs/smb/client/trace.h
@@ -370,11 +370,12 @@ DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(rename_enter);
 DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(rmdir_enter);
 DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_eof_enter);
 DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_info_compound_enter);
+DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_reparse_compound_enter);
+DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(get_reparse_compound_enter);
 DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(delete_enter);
 DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(mkdir_enter);
 DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(tdis_enter);
 
-
 DECLARE_EVENT_CLASS(smb3_inf_compound_done_class,
 	TP_PROTO(unsigned int xid,
 		__u32	tid,
@@ -408,6 +409,8 @@ DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(rename_done);
 DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(rmdir_done);
 DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_eof_done);
 DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_info_compound_done);
+DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_reparse_compound_done);
+DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(get_reparse_compound_done);
 DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(delete_done);
 DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(mkdir_done);
 DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(tdis_done);
@@ -451,6 +454,8 @@ DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(rename_err);
 DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(rmdir_err);
 DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_eof_err);
 DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_info_compound_err);
+DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_reparse_compound_err);
+DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(get_reparse_compound_err);
 DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(mkdir_err);
 DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(delete_err);
 DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(tdis_err);
diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h
index 8983f45f8430..57f2343164a3 100644
--- a/fs/smb/common/smb2pdu.h
+++ b/fs/smb/common/smb2pdu.h
@@ -702,13 +702,16 @@ struct smb2_close_rsp {
 	__le16 StructureSize; /* 60 */
 	__le16 Flags;
 	__le32 Reserved;
-	__le64 CreationTime;
-	__le64 LastAccessTime;
-	__le64 LastWriteTime;
-	__le64 ChangeTime;
-	__le64 AllocationSize;	/* Beginning of FILE_STANDARD_INFO equivalent */
-	__le64 EndOfFile;
-	__le32 Attributes;
+	struct_group(network_open_info,
+		__le64 CreationTime;
+		__le64 LastAccessTime;
+		__le64 LastWriteTime;
+		__le64 ChangeTime;
+		/* Beginning of FILE_STANDARD_INFO equivalent */
+		__le64 AllocationSize;
+		__le64 EndOfFile;
+		__le32 Attributes;
+	);
 } __packed;
 
 
@@ -1142,7 +1145,7 @@ struct smb2_server_client_notification {
 #define SMB2_CREATE_SD_BUFFER			"SecD" /* security descriptor */
 #define SMB2_CREATE_DURABLE_HANDLE_REQUEST	"DHnQ"
 #define SMB2_CREATE_DURABLE_HANDLE_RECONNECT	"DHnC"
-#define SMB2_CREATE_ALLOCATION_SIZE		"AISi"
+#define SMB2_CREATE_ALLOCATION_SIZE		"AlSi"
 #define SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST "MxAc"
 #define SMB2_CREATE_TIMEWARP_REQUEST		"TWrp"
 #define SMB2_CREATE_QUERY_ON_DISK_ID		"QFid"
@@ -1250,6 +1253,7 @@ struct create_mxac_rsp {
 #define SMB2_LEASE_WRITE_CACHING_LE		cpu_to_le32(0x04)
 
 #define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE	cpu_to_le32(0x02)
+#define SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE	cpu_to_le32(0x04)
 
 #define SMB2_LEASE_KEY_SIZE			16
 
diff --git a/fs/smb/server/ksmbd_work.c b/fs/smb/server/ksmbd_work.c
index a2ed441e837a..d7c676c151e2 100644
--- a/fs/smb/server/ksmbd_work.c
+++ b/fs/smb/server/ksmbd_work.c
@@ -56,6 +56,9 @@ void ksmbd_free_work_struct(struct ksmbd_work *work)
 	kfree(work->tr_buf);
 	kvfree(work->request_buf);
 	kfree(work->iov);
+	if (!list_empty(&work->interim_entry))
+		list_del(&work->interim_entry);
+
 	if (work->async_id)
 		ksmbd_release_id(&work->conn->async_ida, work->async_id);
 	kmem_cache_free(work_cache, work);
@@ -106,7 +109,7 @@ static inline void __ksmbd_iov_pin(struct ksmbd_work *work, void *ib,
 static int __ksmbd_iov_pin_rsp(struct ksmbd_work *work, void *ib, int len,
 			       void *aux_buf, unsigned int aux_size)
 {
-	struct aux_read *ar;
+	struct aux_read *ar = NULL;
 	int need_iov_cnt = 1;
 
 	if (aux_size) {
@@ -123,8 +126,11 @@ static int __ksmbd_iov_pin_rsp(struct ksmbd_work *work, void *ib, int len,
 		new = krealloc(work->iov,
 			       sizeof(struct kvec) * work->iov_alloc_cnt,
 			       GFP_KERNEL | __GFP_ZERO);
-		if (!new)
+		if (!new) {
+			kfree(ar);
+			work->iov_alloc_cnt -= 4;
 			return -ENOMEM;
+		}
 		work->iov = new;
 	}
 
diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c
index 9bc0103720f5..562b180459a1 100644
--- a/fs/smb/server/oplock.c
+++ b/fs/smb/server/oplock.c
@@ -102,9 +102,10 @@ static int alloc_lease(struct oplock_info *opinfo, struct lease_ctx_info *lctx)
 	lease->new_state = 0;
 	lease->flags = lctx->flags;
 	lease->duration = lctx->duration;
+	lease->is_dir = lctx->is_dir;
 	memcpy(lease->parent_lease_key, lctx->parent_lease_key, SMB2_LEASE_KEY_SIZE);
 	lease->version = lctx->version;
-	lease->epoch = 0;
+	lease->epoch = le16_to_cpu(lctx->epoch);
 	INIT_LIST_HEAD(&opinfo->lease_entry);
 	opinfo->o_lease = lease;
 
@@ -395,8 +396,8 @@ void close_id_del_oplock(struct ksmbd_file *fp)
 {
 	struct oplock_info *opinfo;
 
-	if (S_ISDIR(file_inode(fp->filp)->i_mode))
-		return;
+	if (fp->reserve_lease_break)
+		smb_lazy_parent_lease_break_close(fp);
 
 	opinfo = opinfo_get(fp);
 	if (!opinfo)
@@ -543,12 +544,13 @@ static struct oplock_info *same_client_has_lease(struct ksmbd_inode *ci,
 			/* upgrading lease */
 			if ((atomic_read(&ci->op_count) +
 			     atomic_read(&ci->sop_count)) == 1) {
-				if (lease->state ==
-				    (lctx->req_state & lease->state)) {
+				if (lease->state != SMB2_LEASE_NONE_LE &&
+				    lease->state == (lctx->req_state & lease->state)) {
 					lease->state |= lctx->req_state;
 					if (lctx->req_state &
 						SMB2_LEASE_WRITE_CACHING_LE)
 						lease_read_to_write(opinfo);
+
 				}
 			} else if ((atomic_read(&ci->op_count) +
 				    atomic_read(&ci->sop_count)) > 1) {
@@ -833,7 +835,8 @@ static int smb2_lease_break_noti(struct oplock_info *opinfo)
 					     interim_entry);
 			setup_async_work(in_work, NULL, NULL);
 			smb2_send_interim_resp(in_work, STATUS_PENDING);
-			list_del(&in_work->interim_entry);
+			list_del_init(&in_work->interim_entry);
+			release_async_work(in_work);
 		}
 		INIT_WORK(&work->work, __smb2_lease_break_noti);
 		ksmbd_queue_work(work);
@@ -899,7 +902,8 @@ static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level)
 					lease->new_state =
 						SMB2_LEASE_READ_CACHING_LE;
 			} else {
-				if (lease->state & SMB2_LEASE_HANDLE_CACHING_LE)
+				if (lease->state & SMB2_LEASE_HANDLE_CACHING_LE &&
+						!lease->is_dir)
 					lease->new_state =
 						SMB2_LEASE_READ_CACHING_LE;
 				else
@@ -1031,6 +1035,7 @@ static void copy_lease(struct oplock_info *op1, struct oplock_info *op2)
 	       SMB2_LEASE_KEY_SIZE);
 	lease2->duration = lease1->duration;
 	lease2->flags = lease1->flags;
+	lease2->epoch = lease1->epoch++;
 }
 
 static int add_lease_global_list(struct oplock_info *opinfo)
@@ -1080,6 +1085,89 @@ static void set_oplock_level(struct oplock_info *opinfo, int level,
 	}
 }
 
+void smb_send_parent_lease_break_noti(struct ksmbd_file *fp,
+				      struct lease_ctx_info *lctx)
+{
+	struct oplock_info *opinfo;
+	struct ksmbd_inode *p_ci = NULL;
+
+	if (lctx->version != 2)
+		return;
+
+	p_ci = ksmbd_inode_lookup_lock(fp->filp->f_path.dentry->d_parent);
+	if (!p_ci)
+		return;
+
+	read_lock(&p_ci->m_lock);
+	list_for_each_entry(opinfo, &p_ci->m_op_list, op_entry) {
+		if (!opinfo->is_lease)
+			continue;
+
+		if (opinfo->o_lease->state != SMB2_OPLOCK_LEVEL_NONE &&
+		    (!(lctx->flags & SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE) ||
+		     !compare_guid_key(opinfo, fp->conn->ClientGUID,
+				      lctx->parent_lease_key))) {
+			if (!atomic_inc_not_zero(&opinfo->refcount))
+				continue;
+
+			atomic_inc(&opinfo->conn->r_count);
+			if (ksmbd_conn_releasing(opinfo->conn)) {
+				atomic_dec(&opinfo->conn->r_count);
+				continue;
+			}
+
+			read_unlock(&p_ci->m_lock);
+			oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE);
+			opinfo_conn_put(opinfo);
+			read_lock(&p_ci->m_lock);
+		}
+	}
+	read_unlock(&p_ci->m_lock);
+
+	ksmbd_inode_put(p_ci);
+}
+
+void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp)
+{
+	struct oplock_info *opinfo;
+	struct ksmbd_inode *p_ci = NULL;
+
+	rcu_read_lock();
+	opinfo = rcu_dereference(fp->f_opinfo);
+	rcu_read_unlock();
+
+	if (!opinfo->is_lease || opinfo->o_lease->version != 2)
+		return;
+
+	p_ci = ksmbd_inode_lookup_lock(fp->filp->f_path.dentry->d_parent);
+	if (!p_ci)
+		return;
+
+	read_lock(&p_ci->m_lock);
+	list_for_each_entry(opinfo, &p_ci->m_op_list, op_entry) {
+		if (!opinfo->is_lease)
+			continue;
+
+		if (opinfo->o_lease->state != SMB2_OPLOCK_LEVEL_NONE) {
+			if (!atomic_inc_not_zero(&opinfo->refcount))
+				continue;
+
+			atomic_inc(&opinfo->conn->r_count);
+			if (ksmbd_conn_releasing(opinfo->conn)) {
+				atomic_dec(&opinfo->conn->r_count);
+				continue;
+			}
+			read_unlock(&p_ci->m_lock);
+			oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE);
+			opinfo_conn_put(opinfo);
+			read_lock(&p_ci->m_lock);
+		}
+	}
+	read_unlock(&p_ci->m_lock);
+
+	ksmbd_inode_put(p_ci);
+}
+
 /**
  * smb_grant_oplock() - handle oplock/lease request on file open
  * @work:		smb work
@@ -1103,10 +1191,6 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid,
 	bool prev_op_has_lease;
 	__le32 prev_op_state = 0;
 
-	/* not support directory lease */
-	if (S_ISDIR(file_inode(fp->filp)->i_mode))
-		return 0;
-
 	opinfo = alloc_opinfo(work, pid, tid);
 	if (!opinfo)
 		return -ENOMEM;
@@ -1363,6 +1447,7 @@ void create_lease_buf(u8 *rbuf, struct lease *lease)
 		memcpy(buf->lcontext.LeaseKey, lease->lease_key,
 		       SMB2_LEASE_KEY_SIZE);
 		buf->lcontext.LeaseFlags = lease->flags;
+		buf->lcontext.Epoch = cpu_to_le16(++lease->epoch);
 		buf->lcontext.LeaseState = lease->state;
 		memcpy(buf->lcontext.ParentLeaseKey, lease->parent_lease_key,
 		       SMB2_LEASE_KEY_SIZE);
@@ -1399,10 +1484,11 @@ void create_lease_buf(u8 *rbuf, struct lease *lease)
 /**
  * parse_lease_state() - parse lease context containted in file open request
  * @open_req:	buffer containing smb2 file open(create) request
+ * @is_dir:	whether leasing file is directory
  *
  * Return:  oplock state, -ENOENT if create lease context not found
  */
-struct lease_ctx_info *parse_lease_state(void *open_req)
+struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir)
 {
 	struct create_context *cc;
 	struct smb2_create_req *req = (struct smb2_create_req *)open_req;
@@ -1420,8 +1506,14 @@ struct lease_ctx_info *parse_lease_state(void *open_req)
 		struct create_lease_v2 *lc = (struct create_lease_v2 *)cc;
 
 		memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE);
-		lreq->req_state = lc->lcontext.LeaseState;
+		if (is_dir) {
+			lreq->req_state = lc->lcontext.LeaseState &
+				~SMB2_LEASE_WRITE_CACHING_LE;
+			lreq->is_dir = true;
+		} else
+			lreq->req_state = lc->lcontext.LeaseState;
 		lreq->flags = lc->lcontext.LeaseFlags;
+		lreq->epoch = lc->lcontext.Epoch;
 		lreq->duration = lc->lcontext.LeaseDuration;
 		memcpy(lreq->parent_lease_key, lc->lcontext.ParentLeaseKey,
 				SMB2_LEASE_KEY_SIZE);
diff --git a/fs/smb/server/oplock.h b/fs/smb/server/oplock.h
index 4b0fe6da7694..5b93ea9196c0 100644
--- a/fs/smb/server/oplock.h
+++ b/fs/smb/server/oplock.h
@@ -34,7 +34,9 @@ struct lease_ctx_info {
 	__le32			flags;
 	__le64			duration;
 	__u8			parent_lease_key[SMB2_LEASE_KEY_SIZE];
+	__le16			epoch;
 	int			version;
+	bool			is_dir;
 };
 
 struct lease_table {
@@ -53,6 +55,7 @@ struct lease {
 	__u8			parent_lease_key[SMB2_LEASE_KEY_SIZE];
 	int			version;
 	unsigned short		epoch;
+	bool			is_dir;
 	struct lease_table	*l_lb;
 };
 
@@ -108,7 +111,7 @@ void opinfo_put(struct oplock_info *opinfo);
 
 /* Lease related functions */
 void create_lease_buf(u8 *rbuf, struct lease *lease);
-struct lease_ctx_info *parse_lease_state(void *open_req);
+struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir);
 __u8 smb2_map_lease_to_oplock(__le32 lease_state);
 int lease_read_to_write(struct oplock_info *opinfo);
 
@@ -124,4 +127,7 @@ struct oplock_info *lookup_lease_in_table(struct ksmbd_conn *conn,
 int find_same_lease_key(struct ksmbd_session *sess, struct ksmbd_inode *ci,
 			struct lease_ctx_info *lctx);
 void destroy_lease_table(struct ksmbd_conn *conn);
+void smb_send_parent_lease_break_noti(struct ksmbd_file *fp,
+				      struct lease_ctx_info *lctx);
+void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp);
 #endif /* __KSMBD_OPLOCK_H */
diff --git a/fs/smb/server/smb2misc.c b/fs/smb/server/smb2misc.c
index 23bd3d1209df..03dded29a980 100644
--- a/fs/smb/server/smb2misc.c
+++ b/fs/smb/server/smb2misc.c
@@ -106,16 +106,25 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len,
 		break;
 	case SMB2_CREATE:
 	{
+		unsigned short int name_off =
+			le16_to_cpu(((struct smb2_create_req *)hdr)->NameOffset);
+		unsigned short int name_len =
+			le16_to_cpu(((struct smb2_create_req *)hdr)->NameLength);
+
 		if (((struct smb2_create_req *)hdr)->CreateContextsLength) {
 			*off = le32_to_cpu(((struct smb2_create_req *)
 				hdr)->CreateContextsOffset);
 			*len = le32_to_cpu(((struct smb2_create_req *)
 				hdr)->CreateContextsLength);
-			break;
+			if (!name_len)
+				break;
+
+			if (name_off + name_len < (u64)*off + *len)
+				break;
 		}
 
-		*off = le16_to_cpu(((struct smb2_create_req *)hdr)->NameOffset);
-		*len = le16_to_cpu(((struct smb2_create_req *)hdr)->NameLength);
+		*off = name_off;
+		*len = name_len;
 		break;
 	}
 	case SMB2_QUERY_INFO:
diff --git a/fs/smb/server/smb2ops.c b/fs/smb/server/smb2ops.c
index aed7704a0672..27a9dce3e03a 100644
--- a/fs/smb/server/smb2ops.c
+++ b/fs/smb/server/smb2ops.c
@@ -221,7 +221,8 @@ void init_smb3_0_server(struct ksmbd_conn *conn)
 	conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE;
 
 	if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES)
-		conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING;
+		conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING |
+			SMB2_GLOBAL_CAP_DIRECTORY_LEASING;
 
 	if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION &&
 	    conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION)
@@ -245,7 +246,8 @@ void init_smb3_02_server(struct ksmbd_conn *conn)
 	conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE;
 
 	if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES)
-		conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING;
+		conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING |
+			SMB2_GLOBAL_CAP_DIRECTORY_LEASING;
 
 	if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION ||
 	    (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) &&
@@ -270,7 +272,8 @@ int init_smb3_11_server(struct ksmbd_conn *conn)
 	conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE;
 
 	if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES)
-		conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING;
+		conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING |
+			SMB2_GLOBAL_CAP_DIRECTORY_LEASING;
 
 	if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION ||
 	    (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) &&
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 658209839729..652ab429bf2e 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -657,13 +657,9 @@ smb2_get_name(const char *src, const int maxlen, struct nls_table *local_nls)
 
 int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg)
 {
-	struct smb2_hdr *rsp_hdr;
 	struct ksmbd_conn *conn = work->conn;
 	int id;
 
-	rsp_hdr = ksmbd_resp_buf_next(work);
-	rsp_hdr->Flags |= SMB2_FLAGS_ASYNC_COMMAND;
-
 	id = ksmbd_acquire_async_msg_id(&conn->async_ida);
 	if (id < 0) {
 		pr_err("Failed to alloc async message id\n");
@@ -671,7 +667,6 @@ int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg)
 	}
 	work->asynchronous = true;
 	work->async_id = id;
-	rsp_hdr->Id.AsyncId = cpu_to_le64(id);
 
 	ksmbd_debug(SMB,
 		    "Send interim Response to inform async request id : %d\n",
@@ -723,6 +718,8 @@ void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status)
 	       __SMB2_HEADER_STRUCTURE_SIZE);
 
 	rsp_hdr = smb2_get_msg(in_work->response_buf);
+	rsp_hdr->Flags |= SMB2_FLAGS_ASYNC_COMMAND;
+	rsp_hdr->Id.AsyncId = cpu_to_le64(work->async_id);
 	smb2_set_err_rsp(in_work);
 	rsp_hdr->Status = status;
 
@@ -2380,7 +2377,8 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len,
 			rc = 0;
 		} else {
 			rc = ksmbd_vfs_setxattr(idmap, path, attr_name, value,
-						le16_to_cpu(eabuf->EaValueLength), 0);
+						le16_to_cpu(eabuf->EaValueLength),
+						0, true);
 			if (rc < 0) {
 				ksmbd_debug(SMB,
 					    "ksmbd_vfs_setxattr is failed(%d)\n",
@@ -2443,7 +2441,7 @@ static noinline int smb2_set_stream_name_xattr(const struct path *path,
 		return -EBADF;
 	}
 
-	rc = ksmbd_vfs_setxattr(idmap, path, xattr_stream_name, NULL, 0, 0);
+	rc = ksmbd_vfs_setxattr(idmap, path, xattr_stream_name, NULL, 0, 0, false);
 	if (rc < 0)
 		pr_err("Failed to store XATTR stream name :%d\n", rc);
 	return 0;
@@ -2518,7 +2516,7 @@ static void smb2_new_xattrs(struct ksmbd_tree_connect *tcon, const struct path *
 	da.flags = XATTR_DOSINFO_ATTRIB | XATTR_DOSINFO_CREATE_TIME |
 		XATTR_DOSINFO_ITIME;
 
-	rc = ksmbd_vfs_set_dos_attrib_xattr(mnt_idmap(path->mnt), path, &da);
+	rc = ksmbd_vfs_set_dos_attrib_xattr(mnt_idmap(path->mnt), path, &da, true);
 	if (rc)
 		ksmbd_debug(SMB, "failed to store file attribute into xattr\n");
 }
@@ -2608,7 +2606,7 @@ static int smb2_create_sd_buffer(struct ksmbd_work *work,
 	    sizeof(struct create_sd_buf_req))
 		return -EINVAL;
 	return set_info_sec(work->conn, work->tcon, path, &sd_buf->ntsd,
-			    le32_to_cpu(sd_buf->ccontext.DataLength), true);
+			    le32_to_cpu(sd_buf->ccontext.DataLength), true, false);
 }
 
 static void ksmbd_acls_fattr(struct smb_fattr *fattr,
@@ -2690,7 +2688,7 @@ int smb2_open(struct ksmbd_work *work)
 		    *(char *)req->Buffer == '\\') {
 			pr_err("not allow directory name included leading slash\n");
 			rc = -EINVAL;
-			goto err_out1;
+			goto err_out2;
 		}
 
 		name = smb2_get_name(req->Buffer,
@@ -2701,7 +2699,7 @@ int smb2_open(struct ksmbd_work *work)
 			if (rc != -ENOMEM)
 				rc = -ENOENT;
 			name = NULL;
-			goto err_out1;
+			goto err_out2;
 		}
 
 		ksmbd_debug(SMB, "converted name = %s\n", name);
@@ -2709,48 +2707,44 @@ int smb2_open(struct ksmbd_work *work)
 			if (!test_share_config_flag(work->tcon->share_conf,
 						    KSMBD_SHARE_FLAG_STREAMS)) {
 				rc = -EBADF;
-				goto err_out1;
+				goto err_out2;
 			}
 			rc = parse_stream_name(name, &stream_name, &s_type);
 			if (rc < 0)
-				goto err_out1;
+				goto err_out2;
 		}
 
 		rc = ksmbd_validate_filename(name);
 		if (rc < 0)
-			goto err_out1;
+			goto err_out2;
 
 		if (ksmbd_share_veto_filename(share, name)) {
 			rc = -ENOENT;
 			ksmbd_debug(SMB, "Reject open(), vetoed file: %s\n",
 				    name);
-			goto err_out1;
+			goto err_out2;
 		}
 	} else {
 		name = kstrdup("", GFP_KERNEL);
 		if (!name) {
 			rc = -ENOMEM;
-			goto err_out1;
+			goto err_out2;
 		}
 	}
 
-	req_op_level = req->RequestedOplockLevel;
-	if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE)
-		lc = parse_lease_state(req);
-
 	if (le32_to_cpu(req->ImpersonationLevel) > le32_to_cpu(IL_DELEGATE)) {
 		pr_err("Invalid impersonationlevel : 0x%x\n",
 		       le32_to_cpu(req->ImpersonationLevel));
 		rc = -EIO;
 		rsp->hdr.Status = STATUS_BAD_IMPERSONATION_LEVEL;
-		goto err_out1;
+		goto err_out2;
 	}
 
 	if (req->CreateOptions && !(req->CreateOptions & CREATE_OPTIONS_MASK_LE)) {
 		pr_err("Invalid create options : 0x%x\n",
 		       le32_to_cpu(req->CreateOptions));
 		rc = -EINVAL;
-		goto err_out1;
+		goto err_out2;
 	} else {
 		if (req->CreateOptions & FILE_SEQUENTIAL_ONLY_LE &&
 		    req->CreateOptions & FILE_RANDOM_ACCESS_LE)
@@ -2760,13 +2754,13 @@ int smb2_open(struct ksmbd_work *work)
 		    (FILE_OPEN_BY_FILE_ID_LE | CREATE_TREE_CONNECTION |
 		     FILE_RESERVE_OPFILTER_LE)) {
 			rc = -EOPNOTSUPP;
-			goto err_out1;
+			goto err_out2;
 		}
 
 		if (req->CreateOptions & FILE_DIRECTORY_FILE_LE) {
 			if (req->CreateOptions & FILE_NON_DIRECTORY_FILE_LE) {
 				rc = -EINVAL;
-				goto err_out1;
+				goto err_out2;
 			} else if (req->CreateOptions & FILE_NO_COMPRESSION_LE) {
 				req->CreateOptions = ~(FILE_NO_COMPRESSION_LE);
 			}
@@ -2778,21 +2772,21 @@ int smb2_open(struct ksmbd_work *work)
 		pr_err("Invalid create disposition : 0x%x\n",
 		       le32_to_cpu(req->CreateDisposition));
 		rc = -EINVAL;
-		goto err_out1;
+		goto err_out2;
 	}
 
 	if (!(req->DesiredAccess & DESIRED_ACCESS_MASK)) {
 		pr_err("Invalid desired access : 0x%x\n",
 		       le32_to_cpu(req->DesiredAccess));
 		rc = -EACCES;
-		goto err_out1;
+		goto err_out2;
 	}
 
 	if (req->FileAttributes && !(req->FileAttributes & FILE_ATTRIBUTE_MASK_LE)) {
 		pr_err("Invalid file attribute : 0x%x\n",
 		       le32_to_cpu(req->FileAttributes));
 		rc = -EINVAL;
-		goto err_out1;
+		goto err_out2;
 	}
 
 	if (req->CreateContextsOffset) {
@@ -2800,19 +2794,19 @@ int smb2_open(struct ksmbd_work *work)
 		context = smb2_find_context_vals(req, SMB2_CREATE_EA_BUFFER, 4);
 		if (IS_ERR(context)) {
 			rc = PTR_ERR(context);
-			goto err_out1;
+			goto err_out2;
 		} else if (context) {
 			ea_buf = (struct create_ea_buf_req *)context;
 			if (le16_to_cpu(context->DataOffset) +
 			    le32_to_cpu(context->DataLength) <
 			    sizeof(struct create_ea_buf_req)) {
 				rc = -EINVAL;
-				goto err_out1;
+				goto err_out2;
 			}
 			if (req->CreateOptions & FILE_NO_EA_KNOWLEDGE_LE) {
 				rsp->hdr.Status = STATUS_ACCESS_DENIED;
 				rc = -EACCES;
-				goto err_out1;
+				goto err_out2;
 			}
 		}
 
@@ -2820,7 +2814,7 @@ int smb2_open(struct ksmbd_work *work)
 						 SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST, 4);
 		if (IS_ERR(context)) {
 			rc = PTR_ERR(context);
-			goto err_out1;
+			goto err_out2;
 		} else if (context) {
 			ksmbd_debug(SMB,
 				    "get query maximal access context\n");
@@ -2831,11 +2825,11 @@ int smb2_open(struct ksmbd_work *work)
 						 SMB2_CREATE_TIMEWARP_REQUEST, 4);
 		if (IS_ERR(context)) {
 			rc = PTR_ERR(context);
-			goto err_out1;
+			goto err_out2;
 		} else if (context) {
 			ksmbd_debug(SMB, "get timewarp context\n");
 			rc = -EBADF;
-			goto err_out1;
+			goto err_out2;
 		}
 
 		if (tcon->posix_extensions) {
@@ -2843,7 +2837,7 @@ int smb2_open(struct ksmbd_work *work)
 							 SMB2_CREATE_TAG_POSIX, 16);
 			if (IS_ERR(context)) {
 				rc = PTR_ERR(context);
-				goto err_out1;
+				goto err_out2;
 			} else if (context) {
 				struct create_posix *posix =
 					(struct create_posix *)context;
@@ -2851,7 +2845,7 @@ int smb2_open(struct ksmbd_work *work)
 				    le32_to_cpu(context->DataLength) <
 				    sizeof(struct create_posix) - 4) {
 					rc = -EINVAL;
-					goto err_out1;
+					goto err_out2;
 				}
 				ksmbd_debug(SMB, "get posix context\n");
 
@@ -2863,7 +2857,7 @@ int smb2_open(struct ksmbd_work *work)
 
 	if (ksmbd_override_fsids(work)) {
 		rc = -ENOMEM;
-		goto err_out1;
+		goto err_out2;
 	}
 
 	rc = ksmbd_vfs_kern_path_locked(work, name, LOOKUP_NO_SYMLINKS,
@@ -3038,7 +3032,7 @@ int smb2_open(struct ksmbd_work *work)
 		}
 	}
 
-	rc = ksmbd_query_inode_status(d_inode(path.dentry->d_parent));
+	rc = ksmbd_query_inode_status(path.dentry->d_parent);
 	if (rc == KSMBD_INODE_STATUS_PENDING_DELETE) {
 		rc = -EBUSY;
 		goto err_out;
@@ -3152,7 +3146,8 @@ int smb2_open(struct ksmbd_work *work)
 								    idmap,
 								    &path,
 								    pntsd,
-								    pntsd_size);
+								    pntsd_size,
+								    false);
 					kfree(pntsd);
 					if (rc)
 						pr_err("failed to store ntacl in xattr : %d\n",
@@ -3175,11 +3170,6 @@ int smb2_open(struct ksmbd_work *work)
 
 	fp->attrib_only = !(req->DesiredAccess & ~(FILE_READ_ATTRIBUTES_LE |
 			FILE_WRITE_ATTRIBUTES_LE | FILE_SYNCHRONIZE_LE));
-	if (!S_ISDIR(file_inode(filp)->i_mode) && open_flags & O_TRUNC &&
-	    !fp->attrib_only && !stream_name) {
-		smb_break_all_oplock(work, fp);
-		need_truncate = 1;
-	}
 
 	/* fp should be searchable through ksmbd_inode.m_fp_list
 	 * after daccess, saccess, attrib_only, and stream are
@@ -3195,23 +3185,43 @@ int smb2_open(struct ksmbd_work *work)
 		goto err_out;
 	}
 
+	if (file_present || created)
+		ksmbd_vfs_kern_path_unlock(&parent_path, &path);
+
+	if (!S_ISDIR(file_inode(filp)->i_mode) && open_flags & O_TRUNC &&
+	    !fp->attrib_only && !stream_name) {
+		smb_break_all_oplock(work, fp);
+		need_truncate = 1;
+	}
+
+	req_op_level = req->RequestedOplockLevel;
+	if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE)
+		lc = parse_lease_state(req, S_ISDIR(file_inode(filp)->i_mode));
+
 	share_ret = ksmbd_smb_check_shared_mode(fp->filp, fp);
 	if (!test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_OPLOCKS) ||
 	    (req_op_level == SMB2_OPLOCK_LEVEL_LEASE &&
 	     !(conn->vals->capabilities & SMB2_GLOBAL_CAP_LEASING))) {
 		if (share_ret < 0 && !S_ISDIR(file_inode(fp->filp)->i_mode)) {
 			rc = share_ret;
-			goto err_out;
+			goto err_out1;
 		}
 	} else {
 		if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) {
+			/*
+			 * Compare parent lease using parent key. If there is no
+			 * a lease that has same parent key, Send lease break
+			 * notification.
+			 */
+			smb_send_parent_lease_break_noti(fp, lc);
+
 			req_op_level = smb2_map_lease_to_oplock(lc->req_state);
 			ksmbd_debug(SMB,
 				    "lease req for(%s) req oplock state 0x%x, lease state 0x%x\n",
 				    name, req_op_level, lc->req_state);
 			rc = find_same_lease_key(sess, fp->f_ci, lc);
 			if (rc)
-				goto err_out;
+				goto err_out1;
 		} else if (open_flags == O_RDONLY &&
 			   (req_op_level == SMB2_OPLOCK_LEVEL_BATCH ||
 			    req_op_level == SMB2_OPLOCK_LEVEL_EXCLUSIVE))
@@ -3222,16 +3232,16 @@ int smb2_open(struct ksmbd_work *work)
 				      le32_to_cpu(req->hdr.Id.SyncId.TreeId),
 				      lc, share_ret);
 		if (rc < 0)
-			goto err_out;
+			goto err_out1;
 	}
 
 	if (req->CreateOptions & FILE_DELETE_ON_CLOSE_LE)
 		ksmbd_fd_set_delete_on_close(fp, file_info);
 
 	if (need_truncate) {
-		rc = smb2_create_truncate(&path);
+		rc = smb2_create_truncate(&fp->filp->f_path);
 		if (rc)
-			goto err_out;
+			goto err_out1;
 	}
 
 	if (req->CreateContextsOffset) {
@@ -3241,7 +3251,7 @@ int smb2_open(struct ksmbd_work *work)
 					SMB2_CREATE_ALLOCATION_SIZE, 4);
 		if (IS_ERR(az_req)) {
 			rc = PTR_ERR(az_req);
-			goto err_out;
+			goto err_out1;
 		} else if (az_req) {
 			loff_t alloc_size;
 			int err;
@@ -3250,7 +3260,7 @@ int smb2_open(struct ksmbd_work *work)
 			    le32_to_cpu(az_req->ccontext.DataLength) <
 			    sizeof(struct create_alloc_size_req)) {
 				rc = -EINVAL;
-				goto err_out;
+				goto err_out1;
 			}
 			alloc_size = le64_to_cpu(az_req->AllocationSize);
 			ksmbd_debug(SMB,
@@ -3268,7 +3278,7 @@ int smb2_open(struct ksmbd_work *work)
 		context = smb2_find_context_vals(req, SMB2_CREATE_QUERY_ON_DISK_ID, 4);
 		if (IS_ERR(context)) {
 			rc = PTR_ERR(context);
-			goto err_out;
+			goto err_out1;
 		} else if (context) {
 			ksmbd_debug(SMB, "get query on disk id context\n");
 			query_disk_id = 1;
@@ -3277,7 +3287,7 @@ int smb2_open(struct ksmbd_work *work)
 
 	rc = ksmbd_vfs_getattr(&path, &stat);
 	if (rc)
-		goto err_out;
+		goto err_out1;
 
 	if (stat.result_mask & STATX_BTIME)
 		fp->create_time = ksmbd_UnixTimeToNT(stat.btime);
@@ -3398,13 +3408,13 @@ int smb2_open(struct ksmbd_work *work)
 	}
 
 err_out:
-	if (file_present || created) {
-		inode_unlock(d_inode(parent_path.dentry));
-		path_put(&path);
-		path_put(&parent_path);
-	}
-	ksmbd_revert_fsids(work);
+	if (rc && (file_present || created))
+		ksmbd_vfs_kern_path_unlock(&parent_path, &path);
+
 err_out1:
+	ksmbd_revert_fsids(work);
+
+err_out2:
 	if (!rc) {
 		ksmbd_update_fstate(&work->sess->file_table, fp, FP_INITED);
 		rc = ksmbd_iov_pin_rsp(work, (void *)rsp, iov_len);
@@ -5537,7 +5547,7 @@ static int smb2_rename(struct ksmbd_work *work,
 		rc = ksmbd_vfs_setxattr(file_mnt_idmap(fp->filp),
 					&fp->filp->f_path,
 					xattr_stream_name,
-					NULL, 0, 0);
+					NULL, 0, 0, true);
 		if (rc < 0) {
 			pr_err("failed to store stream name in xattr: %d\n",
 			       rc);
@@ -5630,11 +5640,9 @@ static int smb2_create_link(struct ksmbd_work *work,
 	if (rc)
 		rc = -EINVAL;
 out:
-	if (file_present) {
-		inode_unlock(d_inode(parent_path.dentry));
-		path_put(&path);
-		path_put(&parent_path);
-	}
+	if (file_present)
+		ksmbd_vfs_kern_path_unlock(&parent_path, &path);
+
 	if (!IS_ERR(link_name))
 		kfree(link_name);
 	kfree(pathname);
@@ -5701,7 +5709,8 @@ static int set_file_basic_info(struct ksmbd_file *fp,
 		da.flags = XATTR_DOSINFO_ATTRIB | XATTR_DOSINFO_CREATE_TIME |
 			XATTR_DOSINFO_ITIME;
 
-		rc = ksmbd_vfs_set_dos_attrib_xattr(idmap, &filp->f_path, &da);
+		rc = ksmbd_vfs_set_dos_attrib_xattr(idmap, &filp->f_path, &da,
+				true);
 		if (rc)
 			ksmbd_debug(SMB,
 				    "failed to restore file attribute in EA\n");
@@ -6013,7 +6022,7 @@ static int smb2_set_info_sec(struct ksmbd_file *fp, int addition_info,
 	fp->saccess |= FILE_SHARE_DELETE_LE;
 
 	return set_info_sec(fp->conn, fp->tcon, &fp->filp->f_path, pntsd,
-			buf_len, false);
+			buf_len, false, true);
 }
 
 /**
@@ -7078,6 +7087,7 @@ skip:
 						      smb2_remove_blocked_lock,
 						      argv);
 				if (rc) {
+					kfree(argv);
 					err = -ENOMEM;
 					goto out;
 				}
@@ -7582,7 +7592,8 @@ static inline int fsctl_set_sparse(struct ksmbd_work *work, u64 id,
 
 		da.attr = le32_to_cpu(fp->f_ci->m_fattr);
 		ret = ksmbd_vfs_set_dos_attrib_xattr(idmap,
-						     &fp->filp->f_path, &da);
+						     &fp->filp->f_path,
+						     &da, true);
 		if (ret)
 			fp->f_ci->m_fattr = old_fattr;
 	}
@@ -8208,6 +8219,11 @@ static void smb21_lease_break_ack(struct ksmbd_work *work)
 			    le32_to_cpu(req->LeaseState));
 	}
 
+	if (ret < 0) {
+		rsp->hdr.Status = err;
+		goto err_out;
+	}
+
 	lease_state = lease->state;
 	opinfo->op_state = OPLOCK_STATE_NONE;
 	wake_up_interruptible_all(&opinfo->oplock_q);
@@ -8215,11 +8231,6 @@ static void smb21_lease_break_ack(struct ksmbd_work *work)
 	wake_up_interruptible_all(&opinfo->oplock_brk);
 	opinfo_put(opinfo);
 
-	if (ret < 0) {
-		rsp->hdr.Status = err;
-		goto err_out;
-	}
-
 	rsp->StructureSize = cpu_to_le16(36);
 	rsp->Reserved = 0;
 	rsp->Flags = 0;
@@ -8231,7 +8242,6 @@ static void smb21_lease_break_ack(struct ksmbd_work *work)
 		return;
 
 err_out:
-	opinfo->op_state = OPLOCK_STATE_NONE;
 	wake_up_interruptible_all(&opinfo->oplock_q);
 	atomic_dec(&opinfo->breaking_cnt);
 	wake_up_interruptible_all(&opinfo->oplock_brk);
diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c
index 51b8bfab7481..1164365533f0 100644
--- a/fs/smb/server/smbacl.c
+++ b/fs/smb/server/smbacl.c
@@ -1185,7 +1185,7 @@ pass:
 			pntsd_size += sizeof(struct smb_acl) + nt_size;
 		}
 
-		ksmbd_vfs_set_sd_xattr(conn, idmap, path, pntsd, pntsd_size);
+		ksmbd_vfs_set_sd_xattr(conn, idmap, path, pntsd, pntsd_size, false);
 		kfree(pntsd);
 	}
 
@@ -1377,7 +1377,7 @@ err_out:
 
 int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon,
 		 const struct path *path, struct smb_ntsd *pntsd, int ntsd_len,
-		 bool type_check)
+		 bool type_check, bool get_write)
 {
 	int rc;
 	struct smb_fattr fattr = {{0}};
@@ -1437,7 +1437,8 @@ int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon,
 	if (test_share_config_flag(tcon->share_conf, KSMBD_SHARE_FLAG_ACL_XATTR)) {
 		/* Update WinACL in xattr */
 		ksmbd_vfs_remove_sd_xattrs(idmap, path);
-		ksmbd_vfs_set_sd_xattr(conn, idmap, path, pntsd, ntsd_len);
+		ksmbd_vfs_set_sd_xattr(conn, idmap, path, pntsd, ntsd_len,
+				get_write);
 	}
 
 out:
diff --git a/fs/smb/server/smbacl.h b/fs/smb/server/smbacl.h
index 49a8c292bd2e..2b52861707d8 100644
--- a/fs/smb/server/smbacl.h
+++ b/fs/smb/server/smbacl.h
@@ -207,7 +207,7 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, const struct path *path,
 			__le32 *pdaccess, int uid);
 int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon,
 		 const struct path *path, struct smb_ntsd *pntsd, int ntsd_len,
-		 bool type_check);
+		 bool type_check, bool get_write);
 void id_to_sid(unsigned int cid, uint sidtype, struct smb_sid *ssid);
 void ksmbd_init_domain(u32 *sub_auth);
 
diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c
index c53dea5598fc..4277750a6da1 100644
--- a/fs/smb/server/vfs.c
+++ b/fs/smb/server/vfs.c
@@ -97,6 +97,13 @@ static int ksmbd_vfs_path_lookup_locked(struct ksmbd_share_config *share_conf,
 		return -ENOENT;
 	}
 
+	err = mnt_want_write(parent_path->mnt);
+	if (err) {
+		path_put(parent_path);
+		putname(filename);
+		return -ENOENT;
+	}
+
 	inode_lock_nested(parent_path->dentry->d_inode, I_MUTEX_PARENT);
 	d = lookup_one_qstr_excl(&last, parent_path->dentry, 0);
 	if (IS_ERR(d))
@@ -123,6 +130,7 @@ static int ksmbd_vfs_path_lookup_locked(struct ksmbd_share_config *share_conf,
 
 err_out:
 	inode_unlock(d_inode(parent_path->dentry));
+	mnt_drop_write(parent_path->mnt);
 	path_put(parent_path);
 	putname(filename);
 	return -ENOENT;
@@ -451,7 +459,8 @@ static int ksmbd_vfs_stream_write(struct ksmbd_file *fp, char *buf, loff_t *pos,
 				 fp->stream.name,
 				 (void *)stream_buf,
 				 size,
-				 0);
+				 0,
+				 true);
 	if (err < 0)
 		goto out;
 
@@ -508,6 +517,9 @@ int ksmbd_vfs_write(struct ksmbd_work *work, struct ksmbd_file *fp,
 		}
 	}
 
+	/* Reserve lease break for parent dir at closing time */
+	fp->reserve_lease_break = true;
+
 	/* Do we need to break any of a levelII oplock? */
 	smb_break_all_levII_oplock(work, fp, 1);
 
@@ -593,10 +605,6 @@ int ksmbd_vfs_remove_file(struct ksmbd_work *work, const struct path *path)
 		goto out_err;
 	}
 
-	err = mnt_want_write(path->mnt);
-	if (err)
-		goto out_err;
-
 	idmap = mnt_idmap(path->mnt);
 	if (S_ISDIR(d_inode(path->dentry)->i_mode)) {
 		err = vfs_rmdir(idmap, d_inode(parent), path->dentry);
@@ -607,7 +615,6 @@ int ksmbd_vfs_remove_file(struct ksmbd_work *work, const struct path *path)
 		if (err)
 			ksmbd_debug(VFS, "unlink failed, err %d\n", err);
 	}
-	mnt_drop_write(path->mnt);
 
 out_err:
 	ksmbd_revert_fsids(work);
@@ -715,7 +722,7 @@ retry:
 		goto out3;
 	}
 
-	parent_fp = ksmbd_lookup_fd_inode(d_inode(old_child->d_parent));
+	parent_fp = ksmbd_lookup_fd_inode(old_child->d_parent);
 	if (parent_fp) {
 		if (parent_fp->daccess & FILE_DELETE_LE) {
 			pr_err("parent dir is opened with delete access\n");
@@ -907,18 +914,22 @@ ssize_t ksmbd_vfs_getxattr(struct mnt_idmap *idmap,
  * @attr_value:	xattr value to set
  * @attr_size:	size of xattr value
  * @flags:	destination buffer length
+ * @get_write:	get write access to a mount
  *
  * Return:	0 on success, otherwise error
  */
 int ksmbd_vfs_setxattr(struct mnt_idmap *idmap,
 		       const struct path *path, const char *attr_name,
-		       void *attr_value, size_t attr_size, int flags)
+		       void *attr_value, size_t attr_size, int flags,
+		       bool get_write)
 {
 	int err;
 
-	err = mnt_want_write(path->mnt);
-	if (err)
-		return err;
+	if (get_write == true) {
+		err = mnt_want_write(path->mnt);
+		if (err)
+			return err;
+	}
 
 	err = vfs_setxattr(idmap,
 			   path->dentry,
@@ -928,7 +939,8 @@ int ksmbd_vfs_setxattr(struct mnt_idmap *idmap,
 			   flags);
 	if (err)
 		ksmbd_debug(VFS, "setxattr failed, err %d\n", err);
-	mnt_drop_write(path->mnt);
+	if (get_write == true)
+		mnt_drop_write(path->mnt);
 	return err;
 }
 
@@ -1252,6 +1264,13 @@ out1:
 	}
 
 	if (!err) {
+		err = mnt_want_write(parent_path->mnt);
+		if (err) {
+			path_put(path);
+			path_put(parent_path);
+			return err;
+		}
+
 		err = ksmbd_vfs_lock_parent(parent_path->dentry, path->dentry);
 		if (err) {
 			path_put(path);
@@ -1261,6 +1280,14 @@ out1:
 	return err;
 }
 
+void ksmbd_vfs_kern_path_unlock(struct path *parent_path, struct path *path)
+{
+	inode_unlock(d_inode(parent_path->dentry));
+	mnt_drop_write(parent_path->mnt);
+	path_put(path);
+	path_put(parent_path);
+}
+
 struct dentry *ksmbd_vfs_kern_path_create(struct ksmbd_work *work,
 					  const char *name,
 					  unsigned int flags,
@@ -1415,7 +1442,8 @@ out:
 int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn,
 			   struct mnt_idmap *idmap,
 			   const struct path *path,
-			   struct smb_ntsd *pntsd, int len)
+			   struct smb_ntsd *pntsd, int len,
+			   bool get_write)
 {
 	int rc;
 	struct ndr sd_ndr = {0}, acl_ndr = {0};
@@ -1475,7 +1503,7 @@ int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn,
 
 	rc = ksmbd_vfs_setxattr(idmap, path,
 				XATTR_NAME_SD, sd_ndr.data,
-				sd_ndr.offset, 0);
+				sd_ndr.offset, 0, get_write);
 	if (rc < 0)
 		pr_err("Failed to store XATTR ntacl :%d\n", rc);
 
@@ -1564,7 +1592,8 @@ free_n_data:
 
 int ksmbd_vfs_set_dos_attrib_xattr(struct mnt_idmap *idmap,
 				   const struct path *path,
-				   struct xattr_dos_attrib *da)
+				   struct xattr_dos_attrib *da,
+				   bool get_write)
 {
 	struct ndr n;
 	int err;
@@ -1574,7 +1603,7 @@ int ksmbd_vfs_set_dos_attrib_xattr(struct mnt_idmap *idmap,
 		return err;
 
 	err = ksmbd_vfs_setxattr(idmap, path, XATTR_NAME_DOS_ATTRIBUTE,
-				 (void *)n.data, n.offset, 0);
+				 (void *)n.data, n.offset, 0, get_write);
 	if (err)
 		ksmbd_debug(SMB, "failed to store dos attribute in xattr\n");
 	kfree(n.data);
@@ -1846,10 +1875,6 @@ int ksmbd_vfs_set_init_posix_acl(struct mnt_idmap *idmap,
 	}
 	posix_state_to_acl(&acl_state, acls->a_entries);
 
-	rc = mnt_want_write(path->mnt);
-	if (rc)
-		goto out_err;
-
 	rc = set_posix_acl(idmap, dentry, ACL_TYPE_ACCESS, acls);
 	if (rc < 0)
 		ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_ACCESS) failed, rc : %d\n",
@@ -1861,9 +1886,7 @@ int ksmbd_vfs_set_init_posix_acl(struct mnt_idmap *idmap,
 			ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_DEFAULT) failed, rc : %d\n",
 				    rc);
 	}
-	mnt_drop_write(path->mnt);
 
-out_err:
 	free_acl_state(&acl_state);
 	posix_acl_release(acls);
 	return rc;
@@ -1893,10 +1916,6 @@ int ksmbd_vfs_inherit_posix_acl(struct mnt_idmap *idmap,
 		}
 	}
 
-	rc = mnt_want_write(path->mnt);
-	if (rc)
-		goto out_err;
-
 	rc = set_posix_acl(idmap, dentry, ACL_TYPE_ACCESS, acls);
 	if (rc < 0)
 		ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_ACCESS) failed, rc : %d\n",
@@ -1908,9 +1927,7 @@ int ksmbd_vfs_inherit_posix_acl(struct mnt_idmap *idmap,
 			ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_DEFAULT) failed, rc : %d\n",
 				    rc);
 	}
-	mnt_drop_write(path->mnt);
 
-out_err:
 	posix_acl_release(acls);
 	return rc;
 }
diff --git a/fs/smb/server/vfs.h b/fs/smb/server/vfs.h
index 00968081856e..cfe1c8092f23 100644
--- a/fs/smb/server/vfs.h
+++ b/fs/smb/server/vfs.h
@@ -109,7 +109,8 @@ ssize_t ksmbd_vfs_casexattr_len(struct mnt_idmap *idmap,
 				int attr_name_len);
 int ksmbd_vfs_setxattr(struct mnt_idmap *idmap,
 		       const struct path *path, const char *attr_name,
-		       void *attr_value, size_t attr_size, int flags);
+		       void *attr_value, size_t attr_size, int flags,
+		       bool get_write);
 int ksmbd_vfs_xattr_stream_name(char *stream_name, char **xattr_stream_name,
 				size_t *xattr_stream_name_size, int s_type);
 int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap,
@@ -117,6 +118,7 @@ int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap,
 int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name,
 			       unsigned int flags, struct path *parent_path,
 			       struct path *path, bool caseless);
+void ksmbd_vfs_kern_path_unlock(struct path *parent_path, struct path *path);
 struct dentry *ksmbd_vfs_kern_path_create(struct ksmbd_work *work,
 					  const char *name,
 					  unsigned int flags,
@@ -144,14 +146,16 @@ int ksmbd_vfs_remove_sd_xattrs(struct mnt_idmap *idmap, const struct path *path)
 int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn,
 			   struct mnt_idmap *idmap,
 			   const struct path *path,
-			   struct smb_ntsd *pntsd, int len);
+			   struct smb_ntsd *pntsd, int len,
+			   bool get_write);
 int ksmbd_vfs_get_sd_xattr(struct ksmbd_conn *conn,
 			   struct mnt_idmap *idmap,
 			   struct dentry *dentry,
 			   struct smb_ntsd **pntsd);
 int ksmbd_vfs_set_dos_attrib_xattr(struct mnt_idmap *idmap,
 				   const struct path *path,
-				   struct xattr_dos_attrib *da);
+				   struct xattr_dos_attrib *da,
+				   bool get_write);
 int ksmbd_vfs_get_dos_attrib_xattr(struct mnt_idmap *idmap,
 				   struct dentry *dentry,
 				   struct xattr_dos_attrib *da);
diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c
index c91eac6514dd..4e82ff627d12 100644
--- a/fs/smb/server/vfs_cache.c
+++ b/fs/smb/server/vfs_cache.c
@@ -66,14 +66,14 @@ static unsigned long inode_hash(struct super_block *sb, unsigned long hashval)
 	return tmp & inode_hash_mask;
 }
 
-static struct ksmbd_inode *__ksmbd_inode_lookup(struct inode *inode)
+static struct ksmbd_inode *__ksmbd_inode_lookup(struct dentry *de)
 {
 	struct hlist_head *head = inode_hashtable +
-		inode_hash(inode->i_sb, inode->i_ino);
+		inode_hash(d_inode(de)->i_sb, (unsigned long)de);
 	struct ksmbd_inode *ci = NULL, *ret_ci = NULL;
 
 	hlist_for_each_entry(ci, head, m_hash) {
-		if (ci->m_inode == inode) {
+		if (ci->m_de == de) {
 			if (atomic_inc_not_zero(&ci->m_count))
 				ret_ci = ci;
 			break;
@@ -84,26 +84,27 @@ static struct ksmbd_inode *__ksmbd_inode_lookup(struct inode *inode)
 
 static struct ksmbd_inode *ksmbd_inode_lookup(struct ksmbd_file *fp)
 {
-	return __ksmbd_inode_lookup(file_inode(fp->filp));
+	return __ksmbd_inode_lookup(fp->filp->f_path.dentry);
 }
 
-static struct ksmbd_inode *ksmbd_inode_lookup_by_vfsinode(struct inode *inode)
+struct ksmbd_inode *ksmbd_inode_lookup_lock(struct dentry *d)
 {
 	struct ksmbd_inode *ci;
 
 	read_lock(&inode_hash_lock);
-	ci = __ksmbd_inode_lookup(inode);
+	ci = __ksmbd_inode_lookup(d);
 	read_unlock(&inode_hash_lock);
+
 	return ci;
 }
 
-int ksmbd_query_inode_status(struct inode *inode)
+int ksmbd_query_inode_status(struct dentry *dentry)
 {
 	struct ksmbd_inode *ci;
 	int ret = KSMBD_INODE_STATUS_UNKNOWN;
 
 	read_lock(&inode_hash_lock);
-	ci = __ksmbd_inode_lookup(inode);
+	ci = __ksmbd_inode_lookup(dentry);
 	if (ci) {
 		ret = KSMBD_INODE_STATUS_OK;
 		if (ci->m_flags & (S_DEL_PENDING | S_DEL_ON_CLS))
@@ -143,7 +144,7 @@ void ksmbd_fd_set_delete_on_close(struct ksmbd_file *fp,
 static void ksmbd_inode_hash(struct ksmbd_inode *ci)
 {
 	struct hlist_head *b = inode_hashtable +
-		inode_hash(ci->m_inode->i_sb, ci->m_inode->i_ino);
+		inode_hash(d_inode(ci->m_de)->i_sb, (unsigned long)ci->m_de);
 
 	hlist_add_head(&ci->m_hash, b);
 }
@@ -157,7 +158,6 @@ static void ksmbd_inode_unhash(struct ksmbd_inode *ci)
 
 static int ksmbd_inode_init(struct ksmbd_inode *ci, struct ksmbd_file *fp)
 {
-	ci->m_inode = file_inode(fp->filp);
 	atomic_set(&ci->m_count, 1);
 	atomic_set(&ci->op_count, 0);
 	atomic_set(&ci->sop_count, 0);
@@ -166,6 +166,7 @@ static int ksmbd_inode_init(struct ksmbd_inode *ci, struct ksmbd_file *fp)
 	INIT_LIST_HEAD(&ci->m_fp_list);
 	INIT_LIST_HEAD(&ci->m_op_list);
 	rwlock_init(&ci->m_lock);
+	ci->m_de = fp->filp->f_path.dentry;
 	return 0;
 }
 
@@ -209,7 +210,7 @@ static void ksmbd_inode_free(struct ksmbd_inode *ci)
 	kfree(ci);
 }
 
-static void ksmbd_inode_put(struct ksmbd_inode *ci)
+void ksmbd_inode_put(struct ksmbd_inode *ci)
 {
 	if (atomic_dec_and_test(&ci->m_count))
 		ksmbd_inode_free(ci);
@@ -488,12 +489,15 @@ struct ksmbd_file *ksmbd_lookup_fd_cguid(char *cguid)
 	return fp;
 }
 
-struct ksmbd_file *ksmbd_lookup_fd_inode(struct inode *inode)
+struct ksmbd_file *ksmbd_lookup_fd_inode(struct dentry *dentry)
 {
 	struct ksmbd_file	*lfp;
 	struct ksmbd_inode	*ci;
+	struct inode		*inode = d_inode(dentry);
 
-	ci = ksmbd_inode_lookup_by_vfsinode(inode);
+	read_lock(&inode_hash_lock);
+	ci = __ksmbd_inode_lookup(dentry);
+	read_unlock(&inode_hash_lock);
 	if (!ci)
 		return NULL;
 
diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h
index 03d0bf941216..a528f0cc775a 100644
--- a/fs/smb/server/vfs_cache.h
+++ b/fs/smb/server/vfs_cache.h
@@ -51,7 +51,7 @@ struct ksmbd_inode {
 	atomic_t			op_count;
 	/* opinfo count for streams */
 	atomic_t			sop_count;
-	struct inode			*m_inode;
+	struct dentry			*m_de;
 	unsigned int			m_flags;
 	struct hlist_node		m_hash;
 	struct list_head		m_fp_list;
@@ -105,6 +105,7 @@ struct ksmbd_file {
 	struct ksmbd_readdir_data	readdir_data;
 	int				dot_dotdot[2];
 	unsigned int			f_state;
+	bool				reserve_lease_break;
 };
 
 static inline void set_ctx_actor(struct dir_context *ctx,
@@ -138,9 +139,11 @@ struct ksmbd_file *ksmbd_lookup_foreign_fd(struct ksmbd_work *work, u64 id);
 struct ksmbd_file *ksmbd_lookup_fd_slow(struct ksmbd_work *work, u64 id,
 					u64 pid);
 void ksmbd_fd_put(struct ksmbd_work *work, struct ksmbd_file *fp);
+struct ksmbd_inode *ksmbd_inode_lookup_lock(struct dentry *d);
+void ksmbd_inode_put(struct ksmbd_inode *ci);
 struct ksmbd_file *ksmbd_lookup_durable_fd(unsigned long long id);
 struct ksmbd_file *ksmbd_lookup_fd_cguid(char *cguid);
-struct ksmbd_file *ksmbd_lookup_fd_inode(struct inode *inode);
+struct ksmbd_file *ksmbd_lookup_fd_inode(struct dentry *dentry);
 unsigned int ksmbd_open_durable_fd(struct ksmbd_file *fp);
 struct ksmbd_file *ksmbd_open_fd(struct ksmbd_work *work, struct file *filp);
 void ksmbd_close_tree_conn_fds(struct ksmbd_work *work);
@@ -164,7 +167,7 @@ enum KSMBD_INODE_STATUS {
 	KSMBD_INODE_STATUS_PENDING_DELETE,
 };
 
-int ksmbd_query_inode_status(struct inode *inode);
+int ksmbd_query_inode_status(struct dentry *dentry);
 bool ksmbd_inode_pending_delete(struct ksmbd_file *fp);
 void ksmbd_set_inode_pending_delete(struct ksmbd_file *fp);
 void ksmbd_clear_inode_pending_delete(struct ksmbd_file *fp);
diff --git a/fs/splice.c b/fs/splice.c
index d983d375ff11..218e24b1ac40 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -201,7 +201,8 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
 	unsigned int tail = pipe->tail;
 	unsigned int head = pipe->head;
 	unsigned int mask = pipe->ring_size - 1;
-	int ret = 0, page_nr = 0;
+	ssize_t ret = 0;
+	int page_nr = 0;
 
 	if (!spd_pages)
 		return 0;
@@ -673,10 +674,13 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 		.u.file = out,
 	};
 	int nbufs = pipe->max_usage;
-	struct bio_vec *array = kcalloc(nbufs, sizeof(struct bio_vec),
-					GFP_KERNEL);
+	struct bio_vec *array;
 	ssize_t ret;
 
+	if (!out->f_op->write_iter)
+		return -EINVAL;
+
+	array = kcalloc(nbufs, sizeof(struct bio_vec), GFP_KERNEL);
 	if (unlikely(!array))
 		return -ENOMEM;
 
@@ -684,6 +688,7 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 
 	splice_from_pipe_begin(&sd);
 	while (sd.total_len) {
+		struct kiocb kiocb;
 		struct iov_iter from;
 		unsigned int head, tail, mask;
 		size_t left;
@@ -733,7 +738,10 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 		}
 
 		iov_iter_bvec(&from, ITER_SOURCE, array, n, sd.total_len - left);
-		ret = vfs_iter_write(out, &from, &sd.pos, 0);
+		init_sync_kiocb(&kiocb, out);
+		kiocb.ki_pos = sd.pos;
+		ret = call_write_iter(out, &kiocb, &from);
+		sd.pos = kiocb.ki_pos;
 		if (ret <= 0)
 			break;
 
@@ -925,8 +933,8 @@ static int warn_unsupported(struct file *file, const char *op)
 /*
  * Attempt to initiate a splice from pipe to file.
  */
-static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
-			   loff_t *ppos, size_t len, unsigned int flags)
+static ssize_t do_splice_from(struct pipe_inode_info *pipe, struct file *out,
+			      loff_t *ppos, size_t len, unsigned int flags)
 {
 	if (unlikely(!out->f_op->splice_write))
 		return warn_unsupported(out, "write");
@@ -944,27 +952,15 @@ static void do_splice_eof(struct splice_desc *sd)
 		sd->splice_eof(sd);
 }
 
-/**
- * vfs_splice_read - Read data from a file and splice it into a pipe
- * @in:		File to splice from
- * @ppos:	Input file offset
- * @pipe:	Pipe to splice to
- * @len:	Number of bytes to splice
- * @flags:	Splice modifier flags (SPLICE_F_*)
- *
- * Splice the requested amount of data from the input file to the pipe.  This
- * is synchronous as the caller must hold the pipe lock across the entire
- * operation.
- *
- * If successful, it returns the amount of data spliced, 0 if it hit the EOF or
- * a hole and a negative error code otherwise.
+/*
+ * Callers already called rw_verify_area() on the entire range.
+ * No need to call it for sub ranges.
  */
-long vfs_splice_read(struct file *in, loff_t *ppos,
-		     struct pipe_inode_info *pipe, size_t len,
-		     unsigned int flags)
+static ssize_t do_splice_read(struct file *in, loff_t *ppos,
+			      struct pipe_inode_info *pipe, size_t len,
+			      unsigned int flags)
 {
 	unsigned int p_space;
-	int ret;
 
 	if (unlikely(!(in->f_mode & FMODE_READ)))
 		return -EBADF;
@@ -975,10 +971,6 @@ long vfs_splice_read(struct file *in, loff_t *ppos,
 	p_space = pipe->max_usage - pipe_occupancy(pipe->head, pipe->tail);
 	len = min_t(size_t, len, p_space << PAGE_SHIFT);
 
-	ret = rw_verify_area(READ, in, ppos, len);
-	if (unlikely(ret < 0))
-		return ret;
-
 	if (unlikely(len > MAX_RW_COUNT))
 		len = MAX_RW_COUNT;
 
@@ -992,6 +984,34 @@ long vfs_splice_read(struct file *in, loff_t *ppos,
 		return copy_splice_read(in, ppos, pipe, len, flags);
 	return in->f_op->splice_read(in, ppos, pipe, len, flags);
 }
+
+/**
+ * vfs_splice_read - Read data from a file and splice it into a pipe
+ * @in:		File to splice from
+ * @ppos:	Input file offset
+ * @pipe:	Pipe to splice to
+ * @len:	Number of bytes to splice
+ * @flags:	Splice modifier flags (SPLICE_F_*)
+ *
+ * Splice the requested amount of data from the input file to the pipe.  This
+ * is synchronous as the caller must hold the pipe lock across the entire
+ * operation.
+ *
+ * If successful, it returns the amount of data spliced, 0 if it hit the EOF or
+ * a hole and a negative error code otherwise.
+ */
+ssize_t vfs_splice_read(struct file *in, loff_t *ppos,
+			struct pipe_inode_info *pipe, size_t len,
+			unsigned int flags)
+{
+	ssize_t ret;
+
+	ret = rw_verify_area(READ, in, ppos, len);
+	if (unlikely(ret < 0))
+		return ret;
+
+	return do_splice_read(in, ppos, pipe, len, flags);
+}
 EXPORT_SYMBOL_GPL(vfs_splice_read);
 
 /**
@@ -1011,7 +1031,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
 			       splice_direct_actor *actor)
 {
 	struct pipe_inode_info *pipe;
-	long ret, bytes;
+	ssize_t ret, bytes;
 	size_t len;
 	int i, flags, more;
 
@@ -1066,7 +1086,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
 		size_t read_len;
 		loff_t pos = sd->pos, prev_pos = pos;
 
-		ret = vfs_splice_read(in, &pos, pipe, len, flags);
+		ret = do_splice_read(in, &pos, pipe, len, flags);
 		if (unlikely(ret <= 0))
 			goto read_failure;
 
@@ -1138,9 +1158,20 @@ static int direct_splice_actor(struct pipe_inode_info *pipe,
 			       struct splice_desc *sd)
 {
 	struct file *file = sd->u.file;
+	long ret;
+
+	file_start_write(file);
+	ret = do_splice_from(pipe, file, sd->opos, sd->total_len, sd->flags);
+	file_end_write(file);
+	return ret;
+}
+
+static int splice_file_range_actor(struct pipe_inode_info *pipe,
+					struct splice_desc *sd)
+{
+	struct file *file = sd->u.file;
 
-	return do_splice_from(pipe, file, sd->opos, sd->total_len,
-			      sd->flags);
+	return do_splice_from(pipe, file, sd->opos, sd->total_len, sd->flags);
 }
 
 static void direct_file_splice_eof(struct splice_desc *sd)
@@ -1151,24 +1182,10 @@ static void direct_file_splice_eof(struct splice_desc *sd)
 		file->f_op->splice_eof(file);
 }
 
-/**
- * do_splice_direct - splices data directly between two files
- * @in:		file to splice from
- * @ppos:	input file offset
- * @out:	file to splice to
- * @opos:	output file offset
- * @len:	number of bytes to splice
- * @flags:	splice modifier flags
- *
- * Description:
- *    For use by do_sendfile(). splice can easily emulate sendfile, but
- *    doing it in the application would incur an extra system call
- *    (splice in + splice out, as compared to just sendfile()). So this helper
- *    can splice directly through a process-private pipe.
- *
- */
-long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
-		      loff_t *opos, size_t len, unsigned int flags)
+static ssize_t do_splice_direct_actor(struct file *in, loff_t *ppos,
+				      struct file *out, loff_t *opos,
+				      size_t len, unsigned int flags,
+				      splice_direct_actor *actor)
 {
 	struct splice_desc sd = {
 		.len		= len,
@@ -1179,7 +1196,7 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
 		.splice_eof	= direct_file_splice_eof,
 		.opos		= opos,
 	};
-	long ret;
+	ssize_t ret;
 
 	if (unlikely(!(out->f_mode & FMODE_WRITE)))
 		return -EBADF;
@@ -1187,18 +1204,63 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
 	if (unlikely(out->f_flags & O_APPEND))
 		return -EINVAL;
 
-	ret = rw_verify_area(WRITE, out, opos, len);
-	if (unlikely(ret < 0))
-		return ret;
-
-	ret = splice_direct_to_actor(in, &sd, direct_splice_actor);
+	ret = splice_direct_to_actor(in, &sd, actor);
 	if (ret > 0)
 		*ppos = sd.pos;
 
 	return ret;
 }
+/**
+ * do_splice_direct - splices data directly between two files
+ * @in:		file to splice from
+ * @ppos:	input file offset
+ * @out:	file to splice to
+ * @opos:	output file offset
+ * @len:	number of bytes to splice
+ * @flags:	splice modifier flags
+ *
+ * Description:
+ *    For use by do_sendfile(). splice can easily emulate sendfile, but
+ *    doing it in the application would incur an extra system call
+ *    (splice in + splice out, as compared to just sendfile()). So this helper
+ *    can splice directly through a process-private pipe.
+ *
+ * Callers already called rw_verify_area() on the entire range.
+ */
+ssize_t do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
+			 loff_t *opos, size_t len, unsigned int flags)
+{
+	return do_splice_direct_actor(in, ppos, out, opos, len, flags,
+				      direct_splice_actor);
+}
 EXPORT_SYMBOL(do_splice_direct);
 
+/**
+ * splice_file_range - splices data between two files for copy_file_range()
+ * @in:		file to splice from
+ * @ppos:	input file offset
+ * @out:	file to splice to
+ * @opos:	output file offset
+ * @len:	number of bytes to splice
+ *
+ * Description:
+ *    For use by ->copy_file_range() methods.
+ *    Like do_splice_direct(), but vfs_copy_file_range() already holds
+ *    start_file_write() on @out file.
+ *
+ * Callers already called rw_verify_area() on the entire range.
+ */
+ssize_t splice_file_range(struct file *in, loff_t *ppos, struct file *out,
+			  loff_t *opos, size_t len)
+{
+	lockdep_assert(file_write_started(out));
+
+	return do_splice_direct_actor(in, ppos, out, opos,
+				      min_t(size_t, len, MAX_RW_COUNT),
+				      0, splice_file_range_actor);
+}
+EXPORT_SYMBOL(splice_file_range);
+
 static int wait_for_space(struct pipe_inode_info *pipe, unsigned flags)
 {
 	for (;;) {
@@ -1220,17 +1282,17 @@ static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
 			       struct pipe_inode_info *opipe,
 			       size_t len, unsigned int flags);
 
-long splice_file_to_pipe(struct file *in,
-			 struct pipe_inode_info *opipe,
-			 loff_t *offset,
-			 size_t len, unsigned int flags)
+ssize_t splice_file_to_pipe(struct file *in,
+			    struct pipe_inode_info *opipe,
+			    loff_t *offset,
+			    size_t len, unsigned int flags)
 {
-	long ret;
+	ssize_t ret;
 
 	pipe_lock(opipe);
 	ret = wait_for_space(opipe, flags);
 	if (!ret)
-		ret = vfs_splice_read(in, offset, opipe, len, flags);
+		ret = do_splice_read(in, offset, opipe, len, flags);
 	pipe_unlock(opipe);
 	if (ret > 0)
 		wakeup_pipe_readers(opipe);
@@ -1240,13 +1302,13 @@ long splice_file_to_pipe(struct file *in,
 /*
  * Determine where to splice to/from.
  */
-long do_splice(struct file *in, loff_t *off_in, struct file *out,
-	       loff_t *off_out, size_t len, unsigned int flags)
+ssize_t do_splice(struct file *in, loff_t *off_in, struct file *out,
+		  loff_t *off_out, size_t len, unsigned int flags)
 {
 	struct pipe_inode_info *ipipe;
 	struct pipe_inode_info *opipe;
 	loff_t offset;
-	long ret;
+	ssize_t ret;
 
 	if (unlikely(!(in->f_mode & FMODE_READ) ||
 		     !(out->f_mode & FMODE_WRITE)))
@@ -1307,6 +1369,10 @@ long do_splice(struct file *in, loff_t *off_in, struct file *out,
 			offset = in->f_pos;
 		}
 
+		ret = rw_verify_area(READ, in, &offset, len);
+		if (unlikely(ret < 0))
+			return ret;
+
 		if (out->f_flags & O_NONBLOCK)
 			flags |= SPLICE_F_NONBLOCK;
 
@@ -1333,14 +1399,14 @@ long do_splice(struct file *in, loff_t *off_in, struct file *out,
 	return ret;
 }
 
-static long __do_splice(struct file *in, loff_t __user *off_in,
-			struct file *out, loff_t __user *off_out,
-			size_t len, unsigned int flags)
+static ssize_t __do_splice(struct file *in, loff_t __user *off_in,
+			   struct file *out, loff_t __user *off_out,
+			   size_t len, unsigned int flags)
 {
 	struct pipe_inode_info *ipipe;
 	struct pipe_inode_info *opipe;
 	loff_t offset, *__off_in = NULL, *__off_out = NULL;
-	long ret;
+	ssize_t ret;
 
 	ipipe = get_pipe_info(in, true);
 	opipe = get_pipe_info(out, true);
@@ -1379,16 +1445,16 @@ static long __do_splice(struct file *in, loff_t __user *off_in,
 	return ret;
 }
 
-static int iter_to_pipe(struct iov_iter *from,
-			struct pipe_inode_info *pipe,
-			unsigned flags)
+static ssize_t iter_to_pipe(struct iov_iter *from,
+			    struct pipe_inode_info *pipe,
+			    unsigned int flags)
 {
 	struct pipe_buffer buf = {
 		.ops = &user_page_pipe_buf_ops,
 		.flags = flags
 	};
 	size_t total = 0;
-	int ret = 0;
+	ssize_t ret = 0;
 
 	while (iov_iter_count(from)) {
 		struct page *pages[16];
@@ -1437,8 +1503,8 @@ static int pipe_to_user(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
  * For lack of a better implementation, implement vmsplice() to userspace
  * as a simple copy of the pipes pages to the user iov.
  */
-static long vmsplice_to_user(struct file *file, struct iov_iter *iter,
-			     unsigned int flags)
+static ssize_t vmsplice_to_user(struct file *file, struct iov_iter *iter,
+				unsigned int flags)
 {
 	struct pipe_inode_info *pipe = get_pipe_info(file, true);
 	struct splice_desc sd = {
@@ -1446,7 +1512,7 @@ static long vmsplice_to_user(struct file *file, struct iov_iter *iter,
 		.flags = flags,
 		.u.data = iter
 	};
-	long ret = 0;
+	ssize_t ret = 0;
 
 	if (!pipe)
 		return -EBADF;
@@ -1470,11 +1536,11 @@ static long vmsplice_to_user(struct file *file, struct iov_iter *iter,
  * as splice-from-memory, where the regular splice is splice-from-file (or
  * to file). In both cases the output is a pipe, naturally.
  */
-static long vmsplice_to_pipe(struct file *file, struct iov_iter *iter,
-			     unsigned int flags)
+static ssize_t vmsplice_to_pipe(struct file *file, struct iov_iter *iter,
+				unsigned int flags)
 {
 	struct pipe_inode_info *pipe;
-	long ret = 0;
+	ssize_t ret = 0;
 	unsigned buf_flag = 0;
 
 	if (flags & SPLICE_F_GIFT)
@@ -1570,7 +1636,7 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
 		size_t, len, unsigned int, flags)
 {
 	struct fd in, out;
-	long error;
+	ssize_t error;
 
 	if (unlikely(!len))
 		return 0;
@@ -1584,7 +1650,7 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
 		out = fdget(fd_out);
 		if (out.file) {
 			error = __do_splice(in.file, off_in, out.file, off_out,
-						len, flags);
+					    len, flags);
 			fdput(out);
 		}
 		fdput(in);
@@ -1807,15 +1873,15 @@ retry:
 /*
  * Link contents of ipipe to opipe.
  */
-static int link_pipe(struct pipe_inode_info *ipipe,
-		     struct pipe_inode_info *opipe,
-		     size_t len, unsigned int flags)
+static ssize_t link_pipe(struct pipe_inode_info *ipipe,
+			 struct pipe_inode_info *opipe,
+			 size_t len, unsigned int flags)
 {
 	struct pipe_buffer *ibuf, *obuf;
 	unsigned int i_head, o_head;
 	unsigned int i_tail, o_tail;
 	unsigned int i_mask, o_mask;
-	int ret = 0;
+	ssize_t ret = 0;
 
 	/*
 	 * Potential ABBA deadlock, work around it by ordering lock
@@ -1898,11 +1964,12 @@ static int link_pipe(struct pipe_inode_info *ipipe,
  * The 'flags' used are the SPLICE_F_* variants, currently the only
  * applicable one is SPLICE_F_NONBLOCK.
  */
-long do_tee(struct file *in, struct file *out, size_t len, unsigned int flags)
+ssize_t do_tee(struct file *in, struct file *out, size_t len,
+	       unsigned int flags)
 {
 	struct pipe_inode_info *ipipe = get_pipe_info(in, true);
 	struct pipe_inode_info *opipe = get_pipe_info(out, true);
-	int ret = -EINVAL;
+	ssize_t ret = -EINVAL;
 
 	if (unlikely(!(in->f_mode & FMODE_READ) ||
 		     !(out->f_mode & FMODE_WRITE)))
@@ -1939,7 +2006,7 @@ long do_tee(struct file *in, struct file *out, size_t len, unsigned int flags)
 SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags)
 {
 	struct fd in, out;
-	int error;
+	ssize_t error;
 
 	if (unlikely(flags & ~SPLICE_F_ALL))
 		return -EINVAL;
diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index 581ce9519339..2dc730800f44 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -321,7 +321,7 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length,
 		TRACE("Block @ 0x%llx, %scompressed size %d\n", index - 2,
 		      compressed ? "" : "un", length);
 	}
-	if (length < 0 || length > output->length ||
+	if (length <= 0 || length > output->length ||
 			(index + length) > msblk->bytes_used) {
 		res = -EIO;
 		goto out;
diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
index 8ba8c4c50770..e8df6430444b 100644
--- a/fs/squashfs/file.c
+++ b/fs/squashfs/file.c
@@ -544,7 +544,8 @@ static void squashfs_readahead(struct readahead_control *ractl)
 	struct squashfs_page_actor *actor;
 	unsigned int nr_pages = 0;
 	struct page **pages;
-	int i, file_end = i_size_read(inode) >> msblk->block_log;
+	int i;
+	loff_t file_end = i_size_read(inode) >> msblk->block_log;
 	unsigned int max_pages = 1UL << shift;
 
 	readahead_expand(ractl, start, (len | mask) + 1);
diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c
index f1ccad519e28..763a3f7a75f6 100644
--- a/fs/squashfs/file_direct.c
+++ b/fs/squashfs/file_direct.c
@@ -26,10 +26,10 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize,
 	struct inode *inode = target_page->mapping->host;
 	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
 
-	int file_end = (i_size_read(inode) - 1) >> PAGE_SHIFT;
+	loff_t file_end = (i_size_read(inode) - 1) >> PAGE_SHIFT;
 	int mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1;
-	int start_index = target_page->index & ~mask;
-	int end_index = start_index | mask;
+	loff_t start_index = target_page->index & ~mask;
+	loff_t end_index = start_index | mask;
 	int i, n, pages, bytes, res = -ENOMEM;
 	struct page **page;
 	struct squashfs_page_actor *actor;
diff --git a/fs/stat.c b/fs/stat.c
index 24bb0209e459..77cdc69eb422 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -41,7 +41,7 @@
  * the vfsmount must be passed through @idmap. This function will then
  * take care to map the inode according to @idmap before filling in the
  * uid and gid filds. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs @nop_mnt_idmap.
+ * performed on the raw inode simply pass @nop_mnt_idmap.
  */
 void generic_fillattr(struct mnt_idmap *idmap, u32 request_mask,
 		      struct inode *inode, struct kstat *stat)
@@ -133,7 +133,8 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat,
 	idmap = mnt_idmap(path->mnt);
 	if (inode->i_op->getattr)
 		return inode->i_op->getattr(idmap, path, stat,
-					    request_mask, query_flags);
+					    request_mask,
+					    query_flags | AT_GETATTR_NOSEC);
 
 	generic_fillattr(idmap, request_mask, inode, stat);
 	return 0;
@@ -166,6 +167,9 @@ int vfs_getattr(const struct path *path, struct kstat *stat,
 {
 	int retval;
 
+	if (WARN_ON_ONCE(query_flags & AT_GETATTR_NOSEC))
+		return -EPERM;
+
 	retval = security_inode_getattr(path);
 	if (retval)
 		return retval;
@@ -243,8 +247,13 @@ retry:
 
 	error = vfs_getattr(&path, stat, request_mask, flags);
 
-	stat->mnt_id = real_mount(path.mnt)->mnt_id;
-	stat->result_mask |= STATX_MNT_ID;
+	if (request_mask & STATX_MNT_ID_UNIQUE) {
+		stat->mnt_id = real_mount(path.mnt)->mnt_id_unique;
+		stat->result_mask |= STATX_MNT_ID_UNIQUE;
+	} else {
+		stat->mnt_id = real_mount(path.mnt)->mnt_id;
+		stat->result_mask |= STATX_MNT_ID;
+	}
 
 	if (path.mnt->mnt_root == path.dentry)
 		stat->attributes |= STATX_ATTR_MOUNT_ROOT;
diff --git a/fs/super.c b/fs/super.c
index 076392396e72..d35e85295489 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -81,16 +81,13 @@ static inline void super_unlock_shared(struct super_block *sb)
 	super_unlock(sb, false);
 }
 
-static inline bool wait_born(struct super_block *sb)
+static bool super_flags(const struct super_block *sb, unsigned int flags)
 {
-	unsigned int flags;
-
 	/*
 	 * Pairs with smp_store_release() in super_wake() and ensures
-	 * that we see SB_BORN or SB_DYING after we're woken.
+	 * that we see @flags after we're woken.
 	 */
-	flags = smp_load_acquire(&sb->s_flags);
-	return flags & (SB_BORN | SB_DYING);
+	return smp_load_acquire(&sb->s_flags) & flags;
 }
 
 /**
@@ -105,15 +102,21 @@ static inline bool wait_born(struct super_block *sb)
  *
  * The caller must have acquired a temporary reference on @sb->s_count.
  *
- * Return: This returns true if SB_BORN was set, false if SB_DYING was
- *         set. The function acquires s_umount and returns with it held.
+ * Return: The function returns true if SB_BORN was set and with
+ *         s_umount held. The function returns false if SB_DYING was
+ *         set and without s_umount held.
  */
 static __must_check bool super_lock(struct super_block *sb, bool excl)
 {
-
 	lockdep_assert_not_held(&sb->s_umount);
 
-relock:
+	/* wait until the superblock is ready or dying */
+	wait_var_event(&sb->s_flags, super_flags(sb, SB_BORN | SB_DYING));
+
+	/* Don't pointlessly acquire s_umount. */
+	if (super_flags(sb, SB_DYING))
+		return false;
+
 	__super_lock(sb, excl);
 
 	/*
@@ -121,32 +124,22 @@ relock:
 	 * @sb->s_root is NULL and @sb->s_active is 0. No one needs to
 	 * grab a reference to this. Tell them so.
 	 */
-	if (sb->s_flags & SB_DYING)
+	if (sb->s_flags & SB_DYING) {
+		super_unlock(sb, excl);
 		return false;
+	}
 
-	/* Has called ->get_tree() successfully. */
-	if (sb->s_flags & SB_BORN)
-		return true;
-
-	super_unlock(sb, excl);
-
-	/* wait until the superblock is ready or dying */
-	wait_var_event(&sb->s_flags, wait_born(sb));
-
-	/*
-	 * Neither SB_BORN nor SB_DYING are ever unset so we never loop.
-	 * Just reacquire @sb->s_umount for the caller.
-	 */
-	goto relock;
+	WARN_ON_ONCE(!(sb->s_flags & SB_BORN));
+	return true;
 }
 
-/* wait and acquire read-side of @sb->s_umount */
+/* wait and try to acquire read-side of @sb->s_umount */
 static inline bool super_lock_shared(struct super_block *sb)
 {
 	return super_lock(sb, false);
 }
 
-/* wait and acquire write-side of @sb->s_umount */
+/* wait and try to acquire write-side of @sb->s_umount */
 static inline bool super_lock_excl(struct super_block *sb)
 {
 	return super_lock(sb, true);
@@ -323,7 +316,7 @@ static void destroy_unused_super(struct super_block *s)
 static struct super_block *alloc_super(struct file_system_type *type, int flags,
 				       struct user_namespace *user_ns)
 {
-	struct super_block *s = kzalloc(sizeof(struct super_block),  GFP_USER);
+	struct super_block *s = kzalloc(sizeof(struct super_block), GFP_KERNEL);
 	static const struct super_operations default_op;
 	int i;
 
@@ -521,48 +514,7 @@ void deactivate_super(struct super_block *s)
 EXPORT_SYMBOL(deactivate_super);
 
 /**
- *	grab_super - acquire an active reference
- *	@s: reference we are trying to make active
- *
- *	Tries to acquire an active reference.  grab_super() is used when we
- * 	had just found a superblock in super_blocks or fs_type->fs_supers
- *	and want to turn it into a full-blown active reference.  grab_super()
- *	is called with sb_lock held and drops it.  Returns 1 in case of
- *	success, 0 if we had failed (superblock contents was already dead or
- *	dying when grab_super() had been called).  Note that this is only
- *	called for superblocks not in rundown mode (== ones still on ->fs_supers
- *	of their type), so increment of ->s_count is OK here.
- */
-static int grab_super(struct super_block *s) __releases(sb_lock)
-{
-	bool born;
-
-	s->s_count++;
-	spin_unlock(&sb_lock);
-	born = super_lock_excl(s);
-	if (born && atomic_inc_not_zero(&s->s_active)) {
-		put_super(s);
-		return 1;
-	}
-	super_unlock_excl(s);
-	put_super(s);
-	return 0;
-}
-
-static inline bool wait_dead(struct super_block *sb)
-{
-	unsigned int flags;
-
-	/*
-	 * Pairs with memory barrier in super_wake() and ensures
-	 * that we see SB_DEAD after we're woken.
-	 */
-	flags = smp_load_acquire(&sb->s_flags);
-	return flags & SB_DEAD;
-}
-
-/**
- * grab_super_dead - acquire an active reference to a superblock
+ * grab_super - acquire an active reference to a superblock
  * @sb: superblock to acquire
  *
  * Acquire a temporary reference on a superblock and try to trade it for
@@ -573,17 +525,21 @@ static inline bool wait_dead(struct super_block *sb)
  * Return: This returns true if an active reference could be acquired,
  *         false if not.
  */
-static bool grab_super_dead(struct super_block *sb)
+static bool grab_super(struct super_block *sb)
 {
+	bool locked;
 
 	sb->s_count++;
-	if (grab_super(sb)) {
-		put_super(sb);
-		lockdep_assert_held(&sb->s_umount);
-		return true;
+	spin_unlock(&sb_lock);
+	locked = super_lock_excl(sb);
+	if (locked) {
+		if (atomic_inc_not_zero(&sb->s_active)) {
+			put_super(sb);
+			return true;
+		}
+		super_unlock_excl(sb);
 	}
-	wait_var_event(&sb->s_flags, wait_dead(sb));
-	lockdep_assert_not_held(&sb->s_umount);
+	wait_var_event(&sb->s_flags, super_flags(sb, SB_DEAD));
 	put_super(sb);
 	return false;
 }
@@ -681,12 +637,6 @@ void generic_shutdown_super(struct super_block *sb)
 		fsnotify_sb_delete(sb);
 		security_sb_delete(sb);
 
-		/*
-		 * Now that all potentially-encrypted inodes have been evicted,
-		 * the fscrypt keyring can be destroyed.
-		 */
-		fscrypt_destroy_keyring(sb);
-
 		if (sb->s_dio_done_wq) {
 			destroy_workqueue(sb->s_dio_done_wq);
 			sb->s_dio_done_wq = NULL;
@@ -695,6 +645,12 @@ void generic_shutdown_super(struct super_block *sb)
 		if (sop->put_super)
 			sop->put_super(sb);
 
+		/*
+		 * Now that all potentially-encrypted inodes have been evicted,
+		 * the fscrypt keyring can be destroyed.
+		 */
+		fscrypt_destroy_keyring(sb);
+
 		if (CHECK_DATA_CORRUPTION(!list_empty(&sb->s_inodes),
 				"VFS: Busy inodes after unmount of %s (%s)",
 				sb->s_id, sb->s_type->name)) {
@@ -834,7 +790,7 @@ share_extant_sb:
 			warnfc(fc, "reusing existing filesystem in another namespace not allowed");
 		return ERR_PTR(-EBUSY);
 	}
-	if (!grab_super_dead(old))
+	if (!grab_super(old))
 		goto retry;
 	destroy_unused_super(s);
 	return old;
@@ -878,7 +834,7 @@ retry:
 				destroy_unused_super(s);
 				return ERR_PTR(-EBUSY);
 			}
-			if (!grab_super_dead(old))
+			if (!grab_super(old))
 				goto retry;
 			destroy_unused_super(s);
 			return old;
@@ -930,8 +886,7 @@ static void __iterate_supers(void (*f)(struct super_block *))
 
 	spin_lock(&sb_lock);
 	list_for_each_entry(sb, &super_blocks, s_list) {
-		/* Pairs with memory marrier in super_wake(). */
-		if (smp_load_acquire(&sb->s_flags) & SB_DYING)
+		if (super_flags(sb, SB_DYING))
 			continue;
 		sb->s_count++;
 		spin_unlock(&sb_lock);
@@ -961,15 +916,17 @@ void iterate_supers(void (*f)(struct super_block *, void *), void *arg)
 
 	spin_lock(&sb_lock);
 	list_for_each_entry(sb, &super_blocks, s_list) {
-		bool born;
+		bool locked;
 
 		sb->s_count++;
 		spin_unlock(&sb_lock);
 
-		born = super_lock_shared(sb);
-		if (born && sb->s_root)
-			f(sb, arg);
-		super_unlock_shared(sb);
+		locked = super_lock_shared(sb);
+		if (locked) {
+			if (sb->s_root)
+				f(sb, arg);
+			super_unlock_shared(sb);
+		}
 
 		spin_lock(&sb_lock);
 		if (p)
@@ -997,15 +954,17 @@ void iterate_supers_type(struct file_system_type *type,
 
 	spin_lock(&sb_lock);
 	hlist_for_each_entry(sb, &type->fs_supers, s_instances) {
-		bool born;
+		bool locked;
 
 		sb->s_count++;
 		spin_unlock(&sb_lock);
 
-		born = super_lock_shared(sb);
-		if (born && sb->s_root)
-			f(sb, arg);
-		super_unlock_shared(sb);
+		locked = super_lock_shared(sb);
+		if (locked) {
+			if (sb->s_root)
+				f(sb, arg);
+			super_unlock_shared(sb);
+		}
 
 		spin_lock(&sb_lock);
 		if (p)
@@ -1019,34 +978,6 @@ void iterate_supers_type(struct file_system_type *type,
 
 EXPORT_SYMBOL(iterate_supers_type);
 
-/**
- * get_active_super - get an active reference to the superblock of a device
- * @bdev: device to get the superblock for
- *
- * Scans the superblock list and finds the superblock of the file system
- * mounted on the device given.  Returns the superblock with an active
- * reference or %NULL if none was found.
- */
-struct super_block *get_active_super(struct block_device *bdev)
-{
-	struct super_block *sb;
-
-	if (!bdev)
-		return NULL;
-
-	spin_lock(&sb_lock);
-	list_for_each_entry(sb, &super_blocks, s_list) {
-		if (sb->s_bdev == bdev) {
-			if (!grab_super(sb))
-				return NULL;
-			super_unlock_excl(sb);
-			return sb;
-		}
-	}
-	spin_unlock(&sb_lock);
-	return NULL;
-}
-
 struct super_block *user_get_super(dev_t dev, bool excl)
 {
 	struct super_block *sb;
@@ -1054,15 +985,17 @@ struct super_block *user_get_super(dev_t dev, bool excl)
 	spin_lock(&sb_lock);
 	list_for_each_entry(sb, &super_blocks, s_list) {
 		if (sb->s_dev ==  dev) {
-			bool born;
+			bool locked;
 
 			sb->s_count++;
 			spin_unlock(&sb_lock);
 			/* still alive? */
-			born = super_lock(sb, excl);
-			if (born && sb->s_root)
-				return sb;
-			super_unlock(sb, excl);
+			locked = super_lock(sb, excl);
+			if (locked) {
+				if (sb->s_root)
+					return sb;
+				super_unlock(sb, excl);
+			}
 			/* nope, got unmounted */
 			spin_lock(&sb_lock);
 			__put_super(sb);
@@ -1173,9 +1106,9 @@ cancel_readonly:
 
 static void do_emergency_remount_callback(struct super_block *sb)
 {
-	bool born = super_lock_excl(sb);
+	bool locked = super_lock_excl(sb);
 
-	if (born && sb->s_root && sb->s_bdev && !sb_rdonly(sb)) {
+	if (locked && sb->s_root && sb->s_bdev && !sb_rdonly(sb)) {
 		struct fs_context *fc;
 
 		fc = fs_context_for_reconfigure(sb->s_root,
@@ -1186,7 +1119,8 @@ static void do_emergency_remount_callback(struct super_block *sb)
 			put_fs_context(fc);
 		}
 	}
-	super_unlock_excl(sb);
+	if (locked)
+		super_unlock_excl(sb);
 }
 
 static void do_emergency_remount(struct work_struct *work)
@@ -1209,16 +1143,17 @@ void emergency_remount(void)
 
 static void do_thaw_all_callback(struct super_block *sb)
 {
-	bool born = super_lock_excl(sb);
+	bool locked = super_lock_excl(sb);
 
-	if (born && sb->s_root) {
+	if (locked && sb->s_root) {
 		if (IS_ENABLED(CONFIG_BLOCK))
-			while (sb->s_bdev && !thaw_bdev(sb->s_bdev))
+			while (sb->s_bdev && !bdev_thaw(sb->s_bdev))
 				pr_warn("Emergency Thaw on %pg\n", sb->s_bdev);
 		thaw_super_locked(sb, FREEZE_HOLDER_USERSPACE);
-	} else {
-		super_unlock_excl(sb);
+		return;
 	}
+	if (locked)
+		super_unlock_excl(sb);
 }
 
 static void do_thaw_all(struct work_struct *work)
@@ -1428,11 +1363,11 @@ EXPORT_SYMBOL(sget_dev);
  *
  * The function must be called with bdev->bd_holder_lock and releases it.
  */
-static struct super_block *bdev_super_lock_shared(struct block_device *bdev)
+static struct super_block *bdev_super_lock(struct block_device *bdev, bool excl)
 	__releases(&bdev->bd_holder_lock)
 {
 	struct super_block *sb = bdev->bd_holder;
-	bool born;
+	bool locked;
 
 	lockdep_assert_held(&bdev->bd_holder_lock);
 	lockdep_assert_not_held(&sb->s_umount);
@@ -1442,19 +1377,25 @@ static struct super_block *bdev_super_lock_shared(struct block_device *bdev)
 	spin_lock(&sb_lock);
 	sb->s_count++;
 	spin_unlock(&sb_lock);
+
 	mutex_unlock(&bdev->bd_holder_lock);
 
-	born = super_lock_shared(sb);
-	if (!born || !sb->s_root || !(sb->s_flags & SB_ACTIVE)) {
-		super_unlock_shared(sb);
-		put_super(sb);
-		return NULL;
-	}
+	locked = super_lock(sb, excl);
+
 	/*
-	 * The superblock is active and we hold s_umount, we can drop our
-	 * temporary reference now.
-	 */
+	 * If the superblock wasn't already SB_DYING then we hold
+	 * s_umount and can safely drop our temporary reference.
+         */
 	put_super(sb);
+
+	if (!locked)
+		return NULL;
+
+	if (!sb->s_root || !(sb->s_flags & SB_ACTIVE)) {
+		super_unlock(sb, excl);
+		return NULL;
+	}
+
 	return sb;
 }
 
@@ -1462,7 +1403,7 @@ static void fs_bdev_mark_dead(struct block_device *bdev, bool surprise)
 {
 	struct super_block *sb;
 
-	sb = bdev_super_lock_shared(bdev);
+	sb = bdev_super_lock(bdev, false);
 	if (!sb)
 		return;
 
@@ -1480,16 +1421,110 @@ static void fs_bdev_sync(struct block_device *bdev)
 {
 	struct super_block *sb;
 
-	sb = bdev_super_lock_shared(bdev);
+	sb = bdev_super_lock(bdev, false);
 	if (!sb)
 		return;
+
 	sync_filesystem(sb);
 	super_unlock_shared(sb);
 }
 
+static struct super_block *get_bdev_super(struct block_device *bdev)
+{
+	bool active = false;
+	struct super_block *sb;
+
+	sb = bdev_super_lock(bdev, true);
+	if (sb) {
+		active = atomic_inc_not_zero(&sb->s_active);
+		super_unlock_excl(sb);
+	}
+	if (!active)
+		return NULL;
+	return sb;
+}
+
+/**
+ * fs_bdev_freeze - freeze owning filesystem of block device
+ * @bdev: block device
+ *
+ * Freeze the filesystem that owns this block device if it is still
+ * active.
+ *
+ * A filesystem that owns multiple block devices may be frozen from each
+ * block device and won't be unfrozen until all block devices are
+ * unfrozen. Each block device can only freeze the filesystem once as we
+ * nest freezes for block devices in the block layer.
+ *
+ * Return: If the freeze was successful zero is returned. If the freeze
+ *         failed a negative error code is returned.
+ */
+static int fs_bdev_freeze(struct block_device *bdev)
+{
+	struct super_block *sb;
+	int error = 0;
+
+	lockdep_assert_held(&bdev->bd_fsfreeze_mutex);
+
+	sb = get_bdev_super(bdev);
+	if (!sb)
+		return -EINVAL;
+
+	if (sb->s_op->freeze_super)
+		error = sb->s_op->freeze_super(sb,
+				FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE);
+	else
+		error = freeze_super(sb,
+				FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE);
+	if (!error)
+		error = sync_blockdev(bdev);
+	deactivate_super(sb);
+	return error;
+}
+
+/**
+ * fs_bdev_thaw - thaw owning filesystem of block device
+ * @bdev: block device
+ *
+ * Thaw the filesystem that owns this block device.
+ *
+ * A filesystem that owns multiple block devices may be frozen from each
+ * block device and won't be unfrozen until all block devices are
+ * unfrozen. Each block device can only freeze the filesystem once as we
+ * nest freezes for block devices in the block layer.
+ *
+ * Return: If the thaw was successful zero is returned. If the thaw
+ *         failed a negative error code is returned. If this function
+ *         returns zero it doesn't mean that the filesystem is unfrozen
+ *         as it may have been frozen multiple times (kernel may hold a
+ *         freeze or might be frozen from other block devices).
+ */
+static int fs_bdev_thaw(struct block_device *bdev)
+{
+	struct super_block *sb;
+	int error;
+
+	lockdep_assert_held(&bdev->bd_fsfreeze_mutex);
+
+	sb = get_bdev_super(bdev);
+	if (WARN_ON_ONCE(!sb))
+		return -EINVAL;
+
+	if (sb->s_op->thaw_super)
+		error = sb->s_op->thaw_super(sb,
+				FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE);
+	else
+		error = thaw_super(sb,
+				FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE);
+	deactivate_super(sb);
+	return error;
+}
+
 const struct blk_holder_ops fs_holder_ops = {
 	.mark_dead		= fs_bdev_mark_dead,
 	.sync			= fs_bdev_sync,
+	.freeze			= fs_bdev_freeze,
+	.thaw			= fs_bdev_thaw,
 };
 EXPORT_SYMBOL_GPL(fs_holder_ops);
 
@@ -1519,15 +1554,10 @@ int setup_bdev_super(struct super_block *sb, int sb_flags,
 	}
 
 	/*
-	 * Until SB_BORN flag is set, there can be no active superblock
-	 * references and thus no filesystem freezing. get_active_super() will
-	 * just loop waiting for SB_BORN so even freeze_bdev() cannot proceed.
-	 *
-	 * It is enough to check bdev was not frozen before we set s_bdev.
+	 * It is enough to check bdev was not frozen before we set
+	 * s_bdev as freezing will wait until SB_BORN is set.
 	 */
-	mutex_lock(&bdev->bd_fsfreeze_mutex);
-	if (bdev->bd_fsfreeze_count > 0) {
-		mutex_unlock(&bdev->bd_fsfreeze_mutex);
+	if (atomic_read(&bdev->bd_fsfreeze_count) > 0) {
 		if (fc)
 			warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev);
 		bdev_release(bdev_handle);
@@ -1540,7 +1570,6 @@ int setup_bdev_super(struct super_block *sb, int sb_flags,
 	if (bdev_stable_writes(bdev))
 		sb->s_iflags |= SB_I_STABLE_WRITES;
 	spin_unlock(&sb_lock);
-	mutex_unlock(&bdev->bd_fsfreeze_mutex);
 
 	snprintf(sb->s_id, sizeof(sb->s_id), "%pg", bdev);
 	shrinker_debugfs_rename(sb->s_shrink, "sb-%s:%s", sb->s_type->name,
@@ -1585,15 +1614,7 @@ int get_tree_bdev(struct fs_context *fc,
 			return -EBUSY;
 		}
 	} else {
-		/*
-		 * We drop s_umount here because we need to open the bdev and
-		 * bdev->open_mutex ranks above s_umount (blkdev_put() ->
-		 * bdev_mark_dead()). It is safe because we have active sb
-		 * reference and SB_BORN is not set yet.
-		 */
-		super_unlock_excl(s);
 		error = setup_bdev_super(s, fc->sb_flags, fc);
-		__super_lock_excl(s);
 		if (!error)
 			error = fill_super(s, fc);
 		if (error) {
@@ -1637,15 +1658,7 @@ struct dentry *mount_bdev(struct file_system_type *fs_type,
 			return ERR_PTR(-EBUSY);
 		}
 	} else {
-		/*
-		 * We drop s_umount here because we need to open the bdev and
-		 * bdev->open_mutex ranks above s_umount (blkdev_put() ->
-		 * bdev_mark_dead()). It is safe because we have active sb
-		 * reference and SB_BORN is not set yet.
-		 */
-		super_unlock_excl(s);
 		error = setup_bdev_super(s, flags, NULL);
-		__super_lock_excl(s);
 		if (!error)
 			error = fill_super(s, data, flags & SB_SILENT ? 1 : 0);
 		if (error) {
@@ -1914,6 +1927,47 @@ static int wait_for_partially_frozen(struct super_block *sb)
 	return ret;
 }
 
+#define FREEZE_HOLDERS (FREEZE_HOLDER_KERNEL | FREEZE_HOLDER_USERSPACE)
+#define FREEZE_FLAGS (FREEZE_HOLDERS | FREEZE_MAY_NEST)
+
+static inline int freeze_inc(struct super_block *sb, enum freeze_holder who)
+{
+	WARN_ON_ONCE((who & ~FREEZE_FLAGS));
+	WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1);
+
+	if (who & FREEZE_HOLDER_KERNEL)
+		++sb->s_writers.freeze_kcount;
+	if (who & FREEZE_HOLDER_USERSPACE)
+		++sb->s_writers.freeze_ucount;
+	return sb->s_writers.freeze_kcount + sb->s_writers.freeze_ucount;
+}
+
+static inline int freeze_dec(struct super_block *sb, enum freeze_holder who)
+{
+	WARN_ON_ONCE((who & ~FREEZE_FLAGS));
+	WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1);
+
+	if ((who & FREEZE_HOLDER_KERNEL) && sb->s_writers.freeze_kcount)
+		--sb->s_writers.freeze_kcount;
+	if ((who & FREEZE_HOLDER_USERSPACE) && sb->s_writers.freeze_ucount)
+		--sb->s_writers.freeze_ucount;
+	return sb->s_writers.freeze_kcount + sb->s_writers.freeze_ucount;
+}
+
+static inline bool may_freeze(struct super_block *sb, enum freeze_holder who)
+{
+	WARN_ON_ONCE((who & ~FREEZE_FLAGS));
+	WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1);
+
+	if (who & FREEZE_HOLDER_KERNEL)
+		return (who & FREEZE_MAY_NEST) ||
+		       sb->s_writers.freeze_kcount == 0;
+	if (who & FREEZE_HOLDER_USERSPACE)
+		return (who & FREEZE_MAY_NEST) ||
+		       sb->s_writers.freeze_ucount == 0;
+	return false;
+}
+
 /**
  * freeze_super - lock the filesystem and force it into a consistent state
  * @sb: the super to lock
@@ -1926,6 +1980,7 @@ static int wait_for_partially_frozen(struct super_block *sb)
  * @who should be:
  * * %FREEZE_HOLDER_USERSPACE if userspace wants to freeze the fs;
  * * %FREEZE_HOLDER_KERNEL if the kernel wants to freeze the fs.
+ * * %FREEZE_MAY_NEST whether nesting freeze and thaw requests is allowed.
  *
  * The @who argument distinguishes between the kernel and userspace trying to
  * freeze the filesystem.  Although there cannot be multiple kernel freezes or
@@ -1933,6 +1988,13 @@ static int wait_for_partially_frozen(struct super_block *sb)
  * userspace can both hold a filesystem frozen.  The filesystem remains frozen
  * until there are no kernel or userspace freezes in effect.
  *
+ * A filesystem may hold multiple devices and thus a filesystems may be
+ * frozen through the block layer via multiple block devices. In this
+ * case the request is marked as being allowed to nest by passing
+ * FREEZE_MAY_NEST. The filesystem remains frozen until all block
+ * devices are unfrozen. If multiple freezes are attempted without
+ * FREEZE_MAY_NEST -EBUSY will be returned.
+ *
  * During this function, sb->s_writers.frozen goes through these values:
  *
  * SB_UNFROZEN: File system is normal, all writes progress as usual.
@@ -1957,31 +2019,29 @@ static int wait_for_partially_frozen(struct super_block *sb)
  * mostly auxiliary for filesystems to verify they do not modify frozen fs.
  *
  * sb->s_writers.frozen is protected by sb->s_umount.
+ *
+ * Return: If the freeze was successful zero is returned. If the freeze
+ *         failed a negative error code is returned.
  */
 int freeze_super(struct super_block *sb, enum freeze_holder who)
 {
 	int ret;
 
+	if (!super_lock_excl(sb)) {
+		WARN_ON_ONCE("Dying superblock while freezing!");
+		return -EINVAL;
+	}
 	atomic_inc(&sb->s_active);
-	if (!super_lock_excl(sb))
-		WARN(1, "Dying superblock while freezing!");
 
 retry:
 	if (sb->s_writers.frozen == SB_FREEZE_COMPLETE) {
-		if (sb->s_writers.freeze_holders & who) {
-			deactivate_locked_super(sb);
-			return -EBUSY;
-		}
-
-		WARN_ON(sb->s_writers.freeze_holders == 0);
-
-		/*
-		 * Someone else already holds this type of freeze; share the
-		 * freeze and assign the active ref to the freeze.
-		 */
-		sb->s_writers.freeze_holders |= who;
-		super_unlock_excl(sb);
-		return 0;
+		if (may_freeze(sb, who))
+			ret = !!WARN_ON_ONCE(freeze_inc(sb, who) == 1);
+		else
+			ret = -EBUSY;
+		/* All freezers share a single active reference. */
+		deactivate_locked_super(sb);
+		return ret;
 	}
 
 	if (sb->s_writers.frozen != SB_UNFROZEN) {
@@ -1994,14 +2054,9 @@ retry:
 		goto retry;
 	}
 
-	if (!(sb->s_flags & SB_BORN)) {
-		super_unlock_excl(sb);
-		return 0;	/* sic - it's "nothing to do" */
-	}
-
 	if (sb_rdonly(sb)) {
 		/* Nothing to do really... */
-		sb->s_writers.freeze_holders |= who;
+		WARN_ON_ONCE(freeze_inc(sb, who) > 1);
 		sb->s_writers.frozen = SB_FREEZE_COMPLETE;
 		wake_up_var(&sb->s_writers.frozen);
 		super_unlock_excl(sb);
@@ -2012,8 +2067,7 @@ retry:
 	/* Release s_umount to preserve sb_start_write -> s_umount ordering */
 	super_unlock_excl(sb);
 	sb_wait_write(sb, SB_FREEZE_WRITE);
-	if (!super_lock_excl(sb))
-		WARN(1, "Dying superblock while freezing!");
+	__super_lock_excl(sb);
 
 	/* Now we go and block page faults... */
 	sb->s_writers.frozen = SB_FREEZE_PAGEFAULT;
@@ -2049,7 +2103,7 @@ retry:
 	 * For debugging purposes so that fs can warn if it sees write activity
 	 * when frozen is set to SB_FREEZE_COMPLETE, and for thaw_super().
 	 */
-	sb->s_writers.freeze_holders |= who;
+	WARN_ON_ONCE(freeze_inc(sb, who) > 1);
 	sb->s_writers.frozen = SB_FREEZE_COMPLETE;
 	wake_up_var(&sb->s_writers.frozen);
 	lockdep_sb_freeze_release(sb);
@@ -2066,34 +2120,22 @@ EXPORT_SYMBOL(freeze_super);
  */
 static int thaw_super_locked(struct super_block *sb, enum freeze_holder who)
 {
-	int error;
+	int error = -EINVAL;
 
-	if (sb->s_writers.frozen == SB_FREEZE_COMPLETE) {
-		if (!(sb->s_writers.freeze_holders & who)) {
-			super_unlock_excl(sb);
-			return -EINVAL;
-		}
+	if (sb->s_writers.frozen != SB_FREEZE_COMPLETE)
+		goto out_unlock;
 
-		/*
-		 * Freeze is shared with someone else.  Release our hold and
-		 * drop the active ref that freeze_super assigned to the
-		 * freezer.
-		 */
-		if (sb->s_writers.freeze_holders & ~who) {
-			sb->s_writers.freeze_holders &= ~who;
-			deactivate_locked_super(sb);
-			return 0;
-		}
-	} else {
-		super_unlock_excl(sb);
-		return -EINVAL;
-	}
+	/*
+	 * All freezers share a single active reference.
+	 * So just unlock in case there are any left.
+	 */
+	if (freeze_dec(sb, who))
+		goto out_unlock;
 
 	if (sb_rdonly(sb)) {
-		sb->s_writers.freeze_holders &= ~who;
 		sb->s_writers.frozen = SB_UNFROZEN;
 		wake_up_var(&sb->s_writers.frozen);
-		goto out;
+		goto out_deactivate;
 	}
 
 	lockdep_sb_freeze_acquire(sb);
@@ -2101,20 +2143,23 @@ static int thaw_super_locked(struct super_block *sb, enum freeze_holder who)
 	if (sb->s_op->unfreeze_fs) {
 		error = sb->s_op->unfreeze_fs(sb);
 		if (error) {
-			printk(KERN_ERR "VFS:Filesystem thaw failed\n");
+			pr_err("VFS: Filesystem thaw failed\n");
+			freeze_inc(sb, who);
 			lockdep_sb_freeze_release(sb);
-			super_unlock_excl(sb);
-			return error;
+			goto out_unlock;
 		}
 	}
 
-	sb->s_writers.freeze_holders &= ~who;
 	sb->s_writers.frozen = SB_UNFROZEN;
 	wake_up_var(&sb->s_writers.frozen);
 	sb_freeze_unlock(sb, SB_FREEZE_FS);
-out:
+out_deactivate:
 	deactivate_locked_super(sb);
 	return 0;
+
+out_unlock:
+	super_unlock_excl(sb);
+	return error;
 }
 
 /**
@@ -2128,11 +2173,18 @@ out:
  * @who should be:
  * * %FREEZE_HOLDER_USERSPACE if userspace wants to thaw the fs;
  * * %FREEZE_HOLDER_KERNEL if the kernel wants to thaw the fs.
+ * * %FREEZE_MAY_NEST whether nesting freeze and thaw requests is allowed
+ *
+ * A filesystem may hold multiple devices and thus a filesystems may
+ * have been frozen through the block layer via multiple block devices.
+ * The filesystem remains frozen until all block devices are unfrozen.
  */
 int thaw_super(struct super_block *sb, enum freeze_holder who)
 {
-	if (!super_lock_excl(sb))
-		WARN(1, "Dying superblock while thawing!");
+	if (!super_lock_excl(sb)) {
+		WARN_ON_ONCE("Dying superblock while thawing!");
+		return -EINVAL;
+	}
 	return thaw_super_locked(sb, who);
 }
 EXPORT_SYMBOL(thaw_super);
diff --git a/fs/sysctls.c b/fs/sysctls.c
index 76a0aee8c229..8dbde9a802fa 100644
--- a/fs/sysctls.c
+++ b/fs/sysctls.c
@@ -26,7 +26,6 @@ static struct ctl_table fs_shared_sysctls[] = {
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_MAXOLDUID,
 	},
-	{ }
 };
 
 static int __init init_fs_sysctls(void)
diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c
index 725981474e5f..410ab2a44d2f 100644
--- a/fs/sysv/itree.c
+++ b/fs/sysv/itree.c
@@ -8,6 +8,7 @@
 
 #include <linux/buffer_head.h>
 #include <linux/mount.h>
+#include <linux/mpage.h>
 #include <linux/string.h>
 #include "sysv.h"
 
@@ -456,9 +457,10 @@ int sysv_getattr(struct mnt_idmap *idmap, const struct path *path,
 	return 0;
 }
 
-static int sysv_writepage(struct page *page, struct writeback_control *wbc)
+static int sysv_writepages(struct address_space *mapping,
+		struct writeback_control *wbc)
 {
-	return block_write_full_page(page,get_block,wbc);
+	return mpage_writepages(mapping, wbc, get_block);
 }
 
 static int sysv_read_folio(struct file *file, struct folio *folio)
@@ -503,8 +505,9 @@ const struct address_space_operations sysv_aops = {
 	.dirty_folio = block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
 	.read_folio = sysv_read_folio,
-	.writepage = sysv_writepage,
+	.writepages = sysv_writepages,
 	.write_begin = sysv_write_begin,
 	.write_end = generic_write_end,
+	.migrate_folio = buffer_migrate_folio,
 	.bmap = sysv_bmap
 };
diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index f8a594a50ae6..f0677ea0ec24 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -27,16 +27,16 @@
 /*
  * eventfs_mutex protects the eventfs_inode (ei) dentry. Any access
  * to the ei->dentry must be done under this mutex and after checking
- * if ei->is_freed is not set. The ei->dentry is released under the
- * mutex at the same time ei->is_freed is set. If ei->is_freed is set
- * then the ei->dentry is invalid.
+ * if ei->is_freed is not set. When ei->is_freed is set, the dentry
+ * is on its way to being freed after the last dput() is made on it.
  */
 static DEFINE_MUTEX(eventfs_mutex);
 
 /*
  * The eventfs_inode (ei) itself is protected by SRCU. It is released from
  * its parent's list and will have is_freed set (under eventfs_mutex).
- * After the SRCU grace period is over, the ei may be freed.
+ * After the SRCU grace period is over and the last dput() is called
+ * the ei is freed.
  */
 DEFINE_STATIC_SRCU(eventfs_srcu);
 
@@ -95,7 +95,7 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry,
 	if (!(dentry->d_inode->i_mode & S_IFDIR)) {
 		if (!ei->entry_attrs) {
 			ei->entry_attrs = kzalloc(sizeof(*ei->entry_attrs) * ei->nr_entries,
-						  GFP_KERNEL);
+						  GFP_NOFS);
 			if (!ei->entry_attrs) {
 				ret = -ENOMEM;
 				goto out;
@@ -113,7 +113,14 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry,
 	 * determined by the parent directory.
 	 */
 	if (dentry->d_inode->i_mode & S_IFDIR) {
-		update_attr(&ei->attr, iattr);
+		/*
+		 * The events directory dentry is never freed, unless its
+		 * part of an instance that is deleted. It's attr is the
+		 * default for its child files and directories.
+		 * Do not update it. It's not used for its own mode or ownership
+		 */
+		if (!ei->is_events)
+			update_attr(&ei->attr, iattr);
 
 	} else {
 		name = dentry->d_name.name;
@@ -148,17 +155,49 @@ static const struct file_operations eventfs_file_operations = {
 	.release	= eventfs_release,
 };
 
-static void update_inode_attr(struct inode *inode, struct eventfs_attr *attr, umode_t mode)
+/* Return the evenfs_inode of the "events" directory */
+static struct eventfs_inode *eventfs_find_events(struct dentry *dentry)
+{
+	struct eventfs_inode *ei;
+
+	mutex_lock(&eventfs_mutex);
+	do {
+		/* The parent always has an ei, except for events itself */
+		ei = dentry->d_parent->d_fsdata;
+
+		/*
+		 * If the ei is being freed, the ownership of the children
+		 * doesn't matter.
+		 */
+		if (ei->is_freed) {
+			ei = NULL;
+			break;
+		}
+
+		dentry = ei->dentry;
+	} while (!ei->is_events);
+	mutex_unlock(&eventfs_mutex);
+
+	return ei;
+}
+
+static void update_inode_attr(struct dentry *dentry, struct inode *inode,
+			      struct eventfs_attr *attr, umode_t mode)
 {
-	if (!attr) {
-		inode->i_mode = mode;
+	struct eventfs_inode *events_ei = eventfs_find_events(dentry);
+
+	if (!events_ei)
+		return;
+
+	inode->i_mode = mode;
+	inode->i_uid = events_ei->attr.uid;
+	inode->i_gid = events_ei->attr.gid;
+
+	if (!attr)
 		return;
-	}
 
 	if (attr->mode & EVENTFS_SAVE_MODE)
 		inode->i_mode = attr->mode & EVENTFS_MODE_MASK;
-	else
-		inode->i_mode = mode;
 
 	if (attr->mode & EVENTFS_SAVE_UID)
 		inode->i_uid = attr->uid;
@@ -167,6 +206,44 @@ static void update_inode_attr(struct inode *inode, struct eventfs_attr *attr, um
 		inode->i_gid = attr->gid;
 }
 
+static void update_gid(struct eventfs_inode *ei, kgid_t gid, int level)
+{
+	struct eventfs_inode *ei_child;
+
+	/* at most we have events/system/event */
+	if (WARN_ON_ONCE(level > 3))
+		return;
+
+	ei->attr.gid = gid;
+
+	if (ei->entry_attrs) {
+		for (int i = 0; i < ei->nr_entries; i++) {
+			ei->entry_attrs[i].gid = gid;
+		}
+	}
+
+	/*
+	 * Only eventfs_inode with dentries are updated, make sure
+	 * all eventfs_inodes are updated. If one of the children
+	 * do not have a dentry, this function must traverse it.
+	 */
+	list_for_each_entry_srcu(ei_child, &ei->children, list,
+				 srcu_read_lock_held(&eventfs_srcu)) {
+		if (!ei_child->dentry)
+			update_gid(ei_child, gid, level + 1);
+	}
+}
+
+void eventfs_update_gid(struct dentry *dentry, kgid_t gid)
+{
+	struct eventfs_inode *ei = dentry->d_fsdata;
+	int idx;
+
+	idx = srcu_read_lock(&eventfs_srcu);
+	update_gid(ei, gid, 0);
+	srcu_read_unlock(&eventfs_srcu, idx);
+}
+
 /**
  * create_file - create a file in the tracefs filesystem
  * @name: the name of the file to create.
@@ -206,7 +283,7 @@ static struct dentry *create_file(const char *name, umode_t mode,
 		return eventfs_failed_creating(dentry);
 
 	/* If the user updated the directory's attributes, use them */
-	update_inode_attr(inode, attr, mode);
+	update_inode_attr(dentry, inode, attr, mode);
 
 	inode->i_op = &eventfs_file_inode_operations;
 	inode->i_fop = fop;
@@ -242,7 +319,8 @@ static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent
 		return eventfs_failed_creating(dentry);
 
 	/* If the user updated the directory's attributes, use them */
-	update_inode_attr(inode, &ei->attr, S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO);
+	update_inode_attr(dentry, inode, &ei->attr,
+			  S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO);
 
 	inode->i_op = &eventfs_root_dir_inode_operations;
 	inode->i_fop = &eventfs_file_operations;
@@ -326,7 +404,8 @@ create_file_dentry(struct eventfs_inode *ei, int idx,
 	struct eventfs_attr *attr = NULL;
 	struct dentry **e_dentry = &ei->d_children[idx];
 	struct dentry *dentry;
-	bool invalidate = false;
+
+	WARN_ON_ONCE(!inode_is_locked(parent->d_inode));
 
 	mutex_lock(&eventfs_mutex);
 	if (ei->is_freed) {
@@ -348,15 +427,8 @@ create_file_dentry(struct eventfs_inode *ei, int idx,
 
 	mutex_unlock(&eventfs_mutex);
 
-	/* The lookup already has the parent->d_inode locked */
-	if (!lookup)
-		inode_lock(parent->d_inode);
-
 	dentry = create_file(name, mode, attr, parent, data, fops);
 
-	if (!lookup)
-		inode_unlock(parent->d_inode);
-
 	mutex_lock(&eventfs_mutex);
 
 	if (IS_ERR_OR_NULL(dentry)) {
@@ -365,12 +437,14 @@ create_file_dentry(struct eventfs_inode *ei, int idx,
 		 * created the dentry for this e_dentry. In which case
 		 * use that one.
 		 *
-		 * Note, with the mutex held, the e_dentry cannot have content
-		 * and the ei->is_freed be true at the same time.
+		 * If ei->is_freed is set, the e_dentry is currently on its
+		 * way to being freed, don't return it. If e_dentry is NULL
+		 * it means it was already freed.
 		 */
-		dentry = *e_dentry;
-		if (WARN_ON_ONCE(dentry && ei->is_freed))
+		if (ei->is_freed)
 			dentry = NULL;
+		else
+			dentry = *e_dentry;
 		/* The lookup does not need to up the dentry refcount */
 		if (dentry && !lookup)
 			dget(dentry);
@@ -387,17 +461,14 @@ create_file_dentry(struct eventfs_inode *ei, int idx,
 		 * Otherwise it means two dentries exist with the same name.
 		 */
 		WARN_ON_ONCE(!ei->is_freed);
-		invalidate = true;
+		dentry = NULL;
 	}
 	mutex_unlock(&eventfs_mutex);
 
-	if (invalidate)
-		d_invalidate(dentry);
-
-	if (lookup || invalidate)
+	if (lookup)
 		dput(dentry);
 
-	return invalidate ? NULL : dentry;
+	return dentry;
 }
 
 /**
@@ -437,9 +508,10 @@ static struct dentry *
 create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei,
 		  struct dentry *parent, bool lookup)
 {
-	bool invalidate = false;
 	struct dentry *dentry = NULL;
 
+	WARN_ON_ONCE(!inode_is_locked(parent->d_inode));
+
 	mutex_lock(&eventfs_mutex);
 	if (pei->is_freed || ei->is_freed) {
 		mutex_unlock(&eventfs_mutex);
@@ -456,15 +528,8 @@ create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei,
 	}
 	mutex_unlock(&eventfs_mutex);
 
-	/* The lookup already has the parent->d_inode locked */
-	if (!lookup)
-		inode_lock(parent->d_inode);
-
 	dentry = create_dir(ei, parent);
 
-	if (!lookup)
-		inode_unlock(parent->d_inode);
-
 	mutex_lock(&eventfs_mutex);
 
 	if (IS_ERR_OR_NULL(dentry) && !ei->is_freed) {
@@ -473,8 +538,8 @@ create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei,
 		 * created the dentry for this e_dentry. In which case
 		 * use that one.
 		 *
-		 * Note, with the mutex held, the e_dentry cannot have content
-		 * and the ei->is_freed be true at the same time.
+		 * If ei->is_freed is set, the e_dentry is currently on its
+		 * way to being freed.
 		 */
 		dentry = ei->dentry;
 		if (dentry && !lookup)
@@ -493,16 +558,14 @@ create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei,
 		 * Otherwise it means two dentries exist with the same name.
 		 */
 		WARN_ON_ONCE(!ei->is_freed);
-		invalidate = true;
+		dentry = NULL;
 	}
 	mutex_unlock(&eventfs_mutex);
-	if (invalidate)
-		d_invalidate(dentry);
 
-	if (lookup || invalidate)
+	if (lookup)
 		dput(dentry);
 
-	return invalidate ? NULL : dentry;
+	return dentry;
 }
 
 /**
@@ -561,6 +624,8 @@ static struct dentry *eventfs_root_lookup(struct inode *dir,
 		if (strcmp(ei_child->name, name) != 0)
 			continue;
 		ret = simple_lookup(dir, dentry, flags);
+		if (IS_ERR(ret))
+			goto out;
 		create_dir_dentry(ei, ei_child, ei_dentry, true);
 		created = true;
 		break;
@@ -583,6 +648,8 @@ static struct dentry *eventfs_root_lookup(struct inode *dir,
 			if (r <= 0)
 				continue;
 			ret = simple_lookup(dir, dentry, flags);
+			if (IS_ERR(ret))
+				goto out;
 			create_file_dentry(ei, i, ei_dentry, name, mode, cdata,
 					   fops, true);
 			break;
@@ -632,7 +699,7 @@ static int add_dentries(struct dentry ***dentries, struct dentry *d, int cnt)
 {
 	struct dentry **tmp;
 
-	tmp = krealloc(*dentries, sizeof(d) * (cnt + 2), GFP_KERNEL);
+	tmp = krealloc(*dentries, sizeof(d) * (cnt + 2), GFP_NOFS);
 	if (!tmp)
 		return -1;
 	tmp[cnt] = d;
@@ -698,6 +765,7 @@ static int dcache_dir_open_wrapper(struct inode *inode, struct file *file)
 		return -ENOMEM;
 	}
 
+	inode_lock(parent->d_inode);
 	list_for_each_entry_srcu(ei_child, &ei->children, list,
 				 srcu_read_lock_held(&eventfs_srcu)) {
 		d = create_dir_dentry(ei, ei_child, parent, false);
@@ -730,6 +798,7 @@ static int dcache_dir_open_wrapper(struct inode *inode, struct file *file)
 			cnt++;
 		}
 	}
+	inode_unlock(parent->d_inode);
 	srcu_read_unlock(&eventfs_srcu, idx);
 	ret = dcache_dir_open(inode, file);
 
@@ -863,6 +932,8 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 	struct eventfs_inode *ei;
 	struct tracefs_inode *ti;
 	struct inode *inode;
+	kuid_t uid;
+	kgid_t gid;
 
 	if (security_locked_down(LOCKDOWN_TRACEFS))
 		return NULL;
@@ -887,11 +958,20 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 	ei->dentry = dentry;
 	ei->entries = entries;
 	ei->nr_entries = size;
+	ei->is_events = 1;
 	ei->data = data;
 	ei->name = kstrdup_const(name, GFP_KERNEL);
 	if (!ei->name)
 		goto fail;
 
+	/* Save the ownership of this directory */
+	uid = d_inode(dentry->d_parent)->i_uid;
+	gid = d_inode(dentry->d_parent)->i_gid;
+
+	/* This is used as the default ownership of the files and directories */
+	ei->attr.uid = uid;
+	ei->attr.gid = gid;
+
 	INIT_LIST_HEAD(&ei->children);
 	INIT_LIST_HEAD(&ei->list);
 
@@ -900,6 +980,8 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 	ti->private = ei;
 
 	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
+	inode->i_uid = uid;
+	inode->i_gid = gid;
 	inode->i_op = &eventfs_root_dir_inode_operations;
 	inode->i_fop = &eventfs_file_operations;
 
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 5b54948514fe..bc86ffdb103b 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -210,14 +210,24 @@ repeat:
 	next = this_parent->d_subdirs.next;
 resume:
 	while (next != &this_parent->d_subdirs) {
+		struct tracefs_inode *ti;
 		struct list_head *tmp = next;
 		struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
 		next = tmp->next;
 
+		/* Note, getdents() can add a cursor dentry with no inode */
+		if (!dentry->d_inode)
+			continue;
+
 		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
 
 		change_gid(dentry, gid);
 
+		/* If this is the events directory, update that too */
+		ti = get_tracefs(dentry->d_inode);
+		if (ti && (ti->flags & TRACEFS_EVENT_INODE))
+			eventfs_update_gid(dentry, gid);
+
 		if (!list_empty(&dentry->d_subdirs)) {
 			spin_unlock(&this_parent->d_lock);
 			spin_release(&dentry->d_lock.dep_map, _RET_IP_);
@@ -509,20 +519,15 @@ struct dentry *eventfs_start_creating(const char *name, struct dentry *parent)
 	struct dentry *dentry;
 	int error;
 
+	/* Must always have a parent. */
+	if (WARN_ON_ONCE(!parent))
+		return ERR_PTR(-EINVAL);
+
 	error = simple_pin_fs(&trace_fs_type, &tracefs_mount,
 			      &tracefs_mount_count);
 	if (error)
 		return ERR_PTR(error);
 
-	/*
-	 * If the parent is not specified, we create it in the root.
-	 * We need the root dentry to do this, which is in the super
-	 * block. A pointer to that is in the struct vfsmount that we
-	 * have around.
-	 */
-	if (!parent)
-		parent = tracefs_mount->mnt_root;
-
 	if (unlikely(IS_DEADDIR(parent->d_inode)))
 		dentry = ERR_PTR(-ENOENT);
 	else
diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
index ccee18ca66c7..42bdeb471a07 100644
--- a/fs/tracefs/internal.h
+++ b/fs/tracefs/internal.h
@@ -62,7 +62,8 @@ struct eventfs_inode {
 		struct rcu_head		rcu;
 	};
 	unsigned int			is_freed:1;
-	unsigned int			nr_entries:31;
+	unsigned int			is_events:1;
+	unsigned int			nr_entries:30;
 };
 
 static inline struct tracefs_inode *get_tracefs(const struct inode *inode)
@@ -77,6 +78,7 @@ struct inode *tracefs_get_inode(struct super_block *sb);
 struct dentry *eventfs_start_creating(const char *name, struct dentry *parent);
 struct dentry *eventfs_failed_creating(struct dentry *dentry);
 struct dentry *eventfs_end_creating(struct dentry *dentry);
+void eventfs_update_gid(struct dentry *dentry, kgid_t gid);
 void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry);
 
 #endif /* _TRACEFS_INTERNAL_H */
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index ebce93b08281..a7bb2e63cdde 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -35,6 +35,7 @@
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/buffer_head.h>
+#include <linux/mpage.h>
 #include <linux/writeback.h>
 #include <linux/iversion.h>
 
@@ -390,7 +391,7 @@ out:
 
 /**
  * ufs_getfrag_block() - `get_block_t' function, interface between UFS and
- * read_folio, writepage and so on
+ * read_folio, writepages and so on
  */
 
 static int ufs_getfrag_block(struct inode *inode, sector_t fragment, struct buffer_head *bh_result, int create)
@@ -467,9 +468,10 @@ done:
 	return 0;
 }
 
-static int ufs_writepage(struct page *page, struct writeback_control *wbc)
+static int ufs_writepages(struct address_space *mapping,
+		struct writeback_control *wbc)
 {
-	return block_write_full_page(page,ufs_getfrag_block,wbc);
+	return mpage_writepages(mapping, wbc, ufs_getfrag_block);
 }
 
 static int ufs_read_folio(struct file *file, struct folio *folio)
@@ -528,9 +530,10 @@ const struct address_space_operations ufs_aops = {
 	.dirty_folio = block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
 	.read_folio = ufs_read_folio,
-	.writepage = ufs_writepage,
+	.writepages = ufs_writepages,
 	.write_begin = ufs_write_begin,
 	.write_end = ufs_write_end,
+	.migrate_folio = buffer_migrate_folio,
 	.bmap = ufs_bmap
 };
 
diff --git a/fs/ufs/util.c b/fs/ufs/util.c
index 13ba34e6d64f..2acf191eb89e 100644
--- a/fs/ufs/util.c
+++ b/fs/ufs/util.c
@@ -245,7 +245,7 @@ struct folio *ufs_get_locked_folio(struct address_space *mapping,
 {
 	struct inode *inode = mapping->host;
 	struct folio *folio = filemap_lock_folio(mapping, index);
-	if (!folio) {
+	if (IS_ERR(folio)) {
 		folio = read_mapping_folio(mapping, index, NULL);
 
 		if (IS_ERR(folio)) {
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index e8af40b05549..4fcefe5ef7cb 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -45,7 +45,6 @@ static struct ctl_table vm_userfaultfd_table[] = {
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_ONE,
 	},
-	{ }
 };
 #endif
 
@@ -2005,6 +2004,75 @@ static inline unsigned int uffd_ctx_features(__u64 user_features)
 	return (unsigned int)user_features | UFFD_FEATURE_INITIALIZED;
 }
 
+static int userfaultfd_move(struct userfaultfd_ctx *ctx,
+			    unsigned long arg)
+{
+	__s64 ret;
+	struct uffdio_move uffdio_move;
+	struct uffdio_move __user *user_uffdio_move;
+	struct userfaultfd_wake_range range;
+	struct mm_struct *mm = ctx->mm;
+
+	user_uffdio_move = (struct uffdio_move __user *) arg;
+
+	if (atomic_read(&ctx->mmap_changing))
+		return -EAGAIN;
+
+	if (copy_from_user(&uffdio_move, user_uffdio_move,
+			   /* don't copy "move" last field */
+			   sizeof(uffdio_move)-sizeof(__s64)))
+		return -EFAULT;
+
+	/* Do not allow cross-mm moves. */
+	if (mm != current->mm)
+		return -EINVAL;
+
+	ret = validate_range(mm, uffdio_move.dst, uffdio_move.len);
+	if (ret)
+		return ret;
+
+	ret = validate_range(mm, uffdio_move.src, uffdio_move.len);
+	if (ret)
+		return ret;
+
+	if (uffdio_move.mode & ~(UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES|
+				  UFFDIO_MOVE_MODE_DONTWAKE))
+		return -EINVAL;
+
+	if (mmget_not_zero(mm)) {
+		mmap_read_lock(mm);
+
+		/* Re-check after taking mmap_lock */
+		if (likely(!atomic_read(&ctx->mmap_changing)))
+			ret = move_pages(ctx, mm, uffdio_move.dst, uffdio_move.src,
+					 uffdio_move.len, uffdio_move.mode);
+		else
+			ret = -EINVAL;
+
+		mmap_read_unlock(mm);
+		mmput(mm);
+	} else {
+		return -ESRCH;
+	}
+
+	if (unlikely(put_user(ret, &user_uffdio_move->move)))
+		return -EFAULT;
+	if (ret < 0)
+		goto out;
+
+	/* len == 0 would wake all */
+	VM_WARN_ON(!ret);
+	range.len = ret;
+	if (!(uffdio_move.mode & UFFDIO_MOVE_MODE_DONTWAKE)) {
+		range.start = uffdio_move.dst;
+		wake_userfault(ctx, &range);
+	}
+	ret = range.len == uffdio_move.len ? 0 : -EAGAIN;
+
+out:
+	return ret;
+}
+
 /*
  * userland asks for a certain API version and we return which bits
  * and ioctl commands are implemented in this kernel for such API
@@ -2097,6 +2165,9 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd,
 	case UFFDIO_ZEROPAGE:
 		ret = userfaultfd_zeropage(ctx, arg);
 		break;
+	case UFFDIO_MOVE:
+		ret = userfaultfd_move(ctx, arg);
+		break;
 	case UFFDIO_WRITEPROTECT:
 		ret = userfaultfd_writeprotect(ctx, arg);
 		break;
diff --git a/fs/verity/fsverity_private.h b/fs/verity/fsverity_private.h
index d071a6e32581..a6a6b2749241 100644
--- a/fs/verity/fsverity_private.h
+++ b/fs/verity/fsverity_private.h
@@ -100,6 +100,16 @@ fsverity_msg(const struct inode *inode, const char *level,
 #define fsverity_err(inode, fmt, ...)		\
 	fsverity_msg((inode), KERN_ERR, fmt, ##__VA_ARGS__)
 
+/* measure.c */
+
+#ifdef CONFIG_BPF_SYSCALL
+void __init fsverity_init_bpf(void);
+#else
+static inline void fsverity_init_bpf(void)
+{
+}
+#endif
+
 /* open.c */
 
 int fsverity_init_merkle_tree_params(struct merkle_tree_params *params,
diff --git a/fs/verity/init.c b/fs/verity/init.c
index a29f062f6047..cb2c9aac61ed 100644
--- a/fs/verity/init.c
+++ b/fs/verity/init.c
@@ -24,7 +24,6 @@ static struct ctl_table fsverity_sysctl_table[] = {
 		.extra2         = SYSCTL_ONE,
 	},
 #endif
-	{ }
 };
 
 static void __init fsverity_init_sysctl(void)
@@ -69,6 +68,7 @@ static int __init fsverity_init(void)
 	fsverity_init_workqueue();
 	fsverity_init_sysctl();
 	fsverity_init_signature();
+	fsverity_init_bpf();
 	return 0;
 }
 late_initcall(fsverity_init)
diff --git a/fs/verity/measure.c b/fs/verity/measure.c
index eec5956141da..bf7a5f4cccaf 100644
--- a/fs/verity/measure.c
+++ b/fs/verity/measure.c
@@ -7,6 +7,8 @@
 
 #include "fsverity_private.h"
 
+#include <linux/bpf.h>
+#include <linux/btf.h>
 #include <linux/uaccess.h>
 
 /**
@@ -100,3 +102,85 @@ int fsverity_get_digest(struct inode *inode,
 	return hash_alg->digest_size;
 }
 EXPORT_SYMBOL_GPL(fsverity_get_digest);
+
+#ifdef CONFIG_BPF_SYSCALL
+
+/* bpf kfuncs */
+__bpf_kfunc_start_defs();
+
+/**
+ * bpf_get_fsverity_digest: read fsverity digest of file
+ * @file: file to get digest from
+ * @digest_ptr: (out) dynptr for struct fsverity_digest
+ *
+ * Read fsverity_digest of *file* into *digest_ptr*.
+ *
+ * Return: 0 on success, a negative value on error.
+ */
+__bpf_kfunc int bpf_get_fsverity_digest(struct file *file, struct bpf_dynptr_kern *digest_ptr)
+{
+	const struct inode *inode = file_inode(file);
+	u32 dynptr_sz = __bpf_dynptr_size(digest_ptr);
+	struct fsverity_digest *arg;
+	const struct fsverity_info *vi;
+	const struct fsverity_hash_alg *hash_alg;
+	int out_digest_sz;
+
+	if (dynptr_sz < sizeof(struct fsverity_digest))
+		return -EINVAL;
+
+	arg = __bpf_dynptr_data_rw(digest_ptr, dynptr_sz);
+	if (!arg)
+		return -EINVAL;
+
+	if (!IS_ALIGNED((uintptr_t)arg, __alignof__(*arg)))
+		return -EINVAL;
+
+	vi = fsverity_get_info(inode);
+	if (!vi)
+		return -ENODATA; /* not a verity file */
+
+	hash_alg = vi->tree_params.hash_alg;
+
+	arg->digest_algorithm = hash_alg - fsverity_hash_algs;
+	arg->digest_size = hash_alg->digest_size;
+
+	out_digest_sz = dynptr_sz - sizeof(struct fsverity_digest);
+
+	/* copy digest */
+	memcpy(arg->digest, vi->file_digest,  min_t(int, hash_alg->digest_size, out_digest_sz));
+
+	/* fill the extra buffer with zeros */
+	if (out_digest_sz > hash_alg->digest_size)
+		memset(arg->digest + arg->digest_size, 0, out_digest_sz - hash_alg->digest_size);
+
+	return 0;
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_SET8_START(fsverity_set_ids)
+BTF_ID_FLAGS(func, bpf_get_fsverity_digest, KF_TRUSTED_ARGS)
+BTF_SET8_END(fsverity_set_ids)
+
+static int bpf_get_fsverity_digest_filter(const struct bpf_prog *prog, u32 kfunc_id)
+{
+	if (!btf_id_set8_contains(&fsverity_set_ids, kfunc_id))
+		return 0;
+
+	/* Only allow to attach from LSM hooks, to avoid recursion */
+	return prog->type != BPF_PROG_TYPE_LSM ? -EACCES : 0;
+}
+
+static const struct btf_kfunc_id_set bpf_fsverity_set = {
+	.owner = THIS_MODULE,
+	.set = &fsverity_set_ids,
+	.filter = bpf_get_fsverity_digest_filter,
+};
+
+void __init fsverity_init_bpf(void)
+{
+	register_btf_kfunc_id_set(BPF_PROG_TYPE_LSM, &bpf_fsverity_set);
+}
+
+#endif /* CONFIG_BPF_SYSCALL */
diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index ed0bc8cbc703..567fb37274d3 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -147,7 +147,7 @@ config XFS_ONLINE_SCRUB_STATS
 	bool "XFS online metadata check usage data collection"
 	default y
 	depends on XFS_ONLINE_SCRUB
-	select XFS_DEBUG
+	select DEBUG_FS
 	help
 	  If you say Y here, the kernel will gather usage data about
 	  the online metadata check subsystem.  This includes the number
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 7762c01a85cf..fbe3cdc79036 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -145,6 +145,7 @@ ifeq ($(CONFIG_XFS_ONLINE_SCRUB),y)
 
 xfs-y				+= $(addprefix scrub/, \
 				   trace.o \
+				   agb_bitmap.o \
 				   agheader.o \
 				   alloc.o \
 				   attr.o \
@@ -175,14 +176,32 @@ xfs-$(CONFIG_XFS_RT)		+= $(addprefix scrub/, \
 				   rtsummary.o \
 				   )
 
-xfs-$(CONFIG_XFS_QUOTA)		+= scrub/quota.o
+xfs-$(CONFIG_XFS_QUOTA)		+= $(addprefix scrub/, \
+				   dqiterate.o \
+				   quota.o \
+				   )
 
 # online repair
 ifeq ($(CONFIG_XFS_ONLINE_REPAIR),y)
 xfs-y				+= $(addprefix scrub/, \
 				   agheader_repair.o \
+				   alloc_repair.o \
+				   bmap_repair.o \
+				   cow_repair.o \
+				   ialloc_repair.o \
+				   inode_repair.o \
+				   newbt.o \
 				   reap.o \
+				   refcount_repair.o \
 				   repair.o \
 				   )
+
+xfs-$(CONFIG_XFS_RT)		+= $(addprefix scrub/, \
+				   rtbitmap_repair.o \
+				   )
+
+xfs-$(CONFIG_XFS_QUOTA)		+= $(addprefix scrub/, \
+				   quota_repair.o \
+				   )
 endif
 endif
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index f9f4d694640d..39d9525270b7 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -332,6 +332,31 @@ xfs_agino_range(
 	return __xfs_agino_range(mp, xfs_ag_block_count(mp, agno), first, last);
 }
 
+/*
+ * Free perag within the specified AG range, it is only used to free unused
+ * perags under the error handling path.
+ */
+void
+xfs_free_unused_perag_range(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agstart,
+	xfs_agnumber_t		agend)
+{
+	struct xfs_perag	*pag;
+	xfs_agnumber_t		index;
+
+	for (index = agstart; index < agend; index++) {
+		spin_lock(&mp->m_perag_lock);
+		pag = radix_tree_delete(&mp->m_perag_tree, index);
+		spin_unlock(&mp->m_perag_lock);
+		if (!pag)
+			break;
+		xfs_buf_hash_destroy(pag);
+		xfs_defer_drain_free(&pag->pag_intents_drain);
+		kmem_free(pag);
+	}
+}
+
 int
 xfs_initialize_perag(
 	struct xfs_mount	*mp,
@@ -424,19 +449,14 @@ xfs_initialize_perag(
 
 out_remove_pag:
 	xfs_defer_drain_free(&pag->pag_intents_drain);
+	spin_lock(&mp->m_perag_lock);
 	radix_tree_delete(&mp->m_perag_tree, index);
+	spin_unlock(&mp->m_perag_lock);
 out_free_pag:
 	kmem_free(pag);
 out_unwind_new_pags:
 	/* unwind any prior newly initialized pags */
-	for (index = first_initialised; index < agcount; index++) {
-		pag = radix_tree_delete(&mp->m_perag_tree, index);
-		if (!pag)
-			break;
-		xfs_buf_hash_destroy(pag);
-		xfs_defer_drain_free(&pag->pag_intents_drain);
-		kmem_free(pag);
-	}
+	xfs_free_unused_perag_range(mp, first_initialised, agcount);
 	return error;
 }
 
@@ -984,7 +1004,7 @@ xfs_ag_shrink_space(
 		if (err2 != -ENOSPC)
 			goto resv_err;
 
-		err2 = __xfs_free_extent_later(*tpp, args.fsbno, delta, NULL,
+		err2 = xfs_free_extent_later(*tpp, args.fsbno, delta, NULL,
 				XFS_AG_RESV_NONE, true);
 		if (err2)
 			goto resv_err;
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 2e0aef87d633..4b343c4fac28 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -80,6 +80,16 @@ struct xfs_perag {
 	 */
 	uint16_t	pag_checked;
 	uint16_t	pag_sick;
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+	/*
+	 * Alternate btree heights so that online repair won't trip the write
+	 * verifiers while rebuilding the AG btrees.
+	 */
+	uint8_t		pagf_repair_levels[XFS_BTNUM_AGF];
+	uint8_t		pagf_repair_refcount_level;
+#endif
+
 	spinlock_t	pag_state_lock;
 
 	spinlock_t	pagb_lock;	/* lock for pagb_tree */
@@ -133,6 +143,8 @@ __XFS_AG_OPSTATE(prefers_metadata, PREFERS_METADATA)
 __XFS_AG_OPSTATE(allows_inodes, ALLOWS_INODES)
 __XFS_AG_OPSTATE(agfl_needs_reset, AGFL_NEEDS_RESET)
 
+void xfs_free_unused_perag_range(struct xfs_mount *mp, xfs_agnumber_t agstart,
+			xfs_agnumber_t agend);
 int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t agcount,
 			xfs_rfsblock_t dcount, xfs_agnumber_t *maxagi);
 int xfs_initialize_perag_data(struct xfs_mount *mp, xfs_agnumber_t agno);
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index 7fd1fea95552..da1057bd0e60 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -411,6 +411,8 @@ xfs_ag_resv_free_extent(
 		fallthrough;
 	case XFS_AG_RESV_NONE:
 		xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, (int64_t)len);
+		fallthrough;
+	case XFS_AG_RESV_IGNORE:
 		return;
 	}
 
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 3069194527dd..3bd0a33fee0a 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -246,11 +246,9 @@ xfs_alloc_btrec_to_irec(
 /* Simple checks for free space records. */
 xfs_failaddr_t
 xfs_alloc_check_irec(
-	struct xfs_btree_cur		*cur,
-	const struct xfs_alloc_rec_incore *irec)
+	struct xfs_perag			*pag,
+	const struct xfs_alloc_rec_incore	*irec)
 {
-	struct xfs_perag		*pag = cur->bc_ag.pag;
-
 	if (irec->ar_blockcount == 0)
 		return __this_address;
 
@@ -299,7 +297,7 @@ xfs_alloc_get_rec(
 		return error;
 
 	xfs_alloc_btrec_to_irec(rec, &irec);
-	fa = xfs_alloc_check_irec(cur, &irec);
+	fa = xfs_alloc_check_irec(cur->bc_ag.pag, &irec);
 	if (fa)
 		return xfs_alloc_complain_bad_rec(cur, fa, &irec);
 
@@ -2275,16 +2273,37 @@ xfs_alloc_min_freelist(
 
 	ASSERT(mp->m_alloc_maxlevels > 0);
 
+	/*
+	 * For a btree shorter than the maximum height, the worst case is that
+	 * every level gets split and a new level is added, then while inserting
+	 * another entry to refill the AGFL, every level under the old root gets
+	 * split again. This is:
+	 *
+	 *   (full height split reservation) + (AGFL refill split height)
+	 * = (current height + 1) + (current height - 1)
+	 * = (new height) + (new height - 2)
+	 * = 2 * new height - 2
+	 *
+	 * For a btree of maximum height, the worst case is that every level
+	 * under the root gets split, then while inserting another entry to
+	 * refill the AGFL, every level under the root gets split again. This is
+	 * also:
+	 *
+	 *   2 * (current height - 1)
+	 * = 2 * (new height - 1)
+	 * = 2 * new height - 2
+	 */
+
 	/* space needed by-bno freespace btree */
 	min_free = min_t(unsigned int, levels[XFS_BTNUM_BNOi] + 1,
-				       mp->m_alloc_maxlevels);
+				       mp->m_alloc_maxlevels) * 2 - 2;
 	/* space needed by-size freespace btree */
 	min_free += min_t(unsigned int, levels[XFS_BTNUM_CNTi] + 1,
-				       mp->m_alloc_maxlevels);
+				       mp->m_alloc_maxlevels) * 2 - 2;
 	/* space needed reverse mapping used space btree */
 	if (xfs_has_rmapbt(mp))
 		min_free += min_t(unsigned int, levels[XFS_BTNUM_RMAPi] + 1,
-						mp->m_rmap_maxlevels);
+						mp->m_rmap_maxlevels) * 2 - 2;
 
 	return min_free;
 }
@@ -2493,7 +2512,7 @@ xfs_defer_agfl_block(
 	trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);
 
 	xfs_extent_free_get_group(mp, xefi);
-	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_AGFL_FREE, &xefi->xefi_list);
+	xfs_defer_add(tp, &xefi->xefi_list, &xfs_agfl_free_defer_type);
 	return 0;
 }
 
@@ -2501,14 +2520,15 @@ xfs_defer_agfl_block(
  * Add the extent to the list of extents to be free at transaction end.
  * The list is maintained sorted (by block number).
  */
-int
-__xfs_free_extent_later(
+static int
+xfs_defer_extent_free(
 	struct xfs_trans		*tp,
 	xfs_fsblock_t			bno,
 	xfs_filblks_t			len,
 	const struct xfs_owner_info	*oinfo,
 	enum xfs_ag_resv_type		type,
-	bool				skip_discard)
+	bool				skip_discard,
+	struct xfs_defer_pending	**dfpp)
 {
 	struct xfs_extent_free_item	*xefi;
 	struct xfs_mount		*mp = tp->t_mountp;
@@ -2556,10 +2576,105 @@ __xfs_free_extent_later(
 			XFS_FSB_TO_AGBNO(tp->t_mountp, bno), len);
 
 	xfs_extent_free_get_group(mp, xefi);
-	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &xefi->xefi_list);
+	*dfpp = xfs_defer_add(tp, &xefi->xefi_list, &xfs_extent_free_defer_type);
 	return 0;
 }
 
+int
+xfs_free_extent_later(
+	struct xfs_trans		*tp,
+	xfs_fsblock_t			bno,
+	xfs_filblks_t			len,
+	const struct xfs_owner_info	*oinfo,
+	enum xfs_ag_resv_type		type,
+	bool				skip_discard)
+{
+	struct xfs_defer_pending	*dontcare = NULL;
+
+	return xfs_defer_extent_free(tp, bno, len, oinfo, type, skip_discard,
+			&dontcare);
+}
+
+/*
+ * Set up automatic freeing of unwritten space in the filesystem.
+ *
+ * This function attached a paused deferred extent free item to the
+ * transaction.  Pausing means that the EFI will be logged in the next
+ * transaction commit, but the pending EFI will not be finished until the
+ * pending item is unpaused.
+ *
+ * If the system goes down after the EFI has been persisted to the log but
+ * before the pending item is unpaused, log recovery will find the EFI, fail to
+ * find the EFD, and free the space.
+ *
+ * If the pending item is unpaused, the next transaction commit will log an EFD
+ * without freeing the space.
+ *
+ * Caller must ensure that the tp, fsbno, len, oinfo, and resv flags of the
+ * @args structure are set to the relevant values.
+ */
+int
+xfs_alloc_schedule_autoreap(
+	const struct xfs_alloc_arg	*args,
+	bool				skip_discard,
+	struct xfs_alloc_autoreap	*aarp)
+{
+	int				error;
+
+	error = xfs_defer_extent_free(args->tp, args->fsbno, args->len,
+			&args->oinfo, args->resv, skip_discard, &aarp->dfp);
+	if (error)
+		return error;
+
+	xfs_defer_item_pause(args->tp, aarp->dfp);
+	return 0;
+}
+
+/*
+ * Cancel automatic freeing of unwritten space in the filesystem.
+ *
+ * Earlier, we created a paused deferred extent free item and attached it to
+ * this transaction so that we could automatically roll back a new space
+ * allocation if the system went down.  Now we want to cancel the paused work
+ * item by marking the EFI stale so we don't actually free the space, unpausing
+ * the pending item and logging an EFD.
+ *
+ * The caller generally should have already mapped the space into the ondisk
+ * filesystem.  If the reserved space was partially used, the caller must call
+ * xfs_free_extent_later to create a new EFI to free the unused space.
+ */
+void
+xfs_alloc_cancel_autoreap(
+	struct xfs_trans		*tp,
+	struct xfs_alloc_autoreap	*aarp)
+{
+	struct xfs_defer_pending	*dfp = aarp->dfp;
+	struct xfs_extent_free_item	*xefi;
+
+	if (!dfp)
+		return;
+
+	list_for_each_entry(xefi, &dfp->dfp_work, xefi_list)
+		xefi->xefi_flags |= XFS_EFI_CANCELLED;
+
+	xfs_defer_item_unpause(tp, dfp);
+}
+
+/*
+ * Commit automatic freeing of unwritten space in the filesystem.
+ *
+ * This unpauses an earlier _schedule_autoreap and commits to freeing the
+ * allocated space.  Call this if none of the reserved space was used.
+ */
+void
+xfs_alloc_commit_autoreap(
+	struct xfs_trans		*tp,
+	struct xfs_alloc_autoreap	*aarp)
+{
+	if (aarp->dfp)
+		xfs_defer_item_unpause(tp, aarp->dfp);
+}
+
 #ifdef DEBUG
 /*
  * Check if an AGF has a free extent record whose length is equal to
@@ -3827,7 +3942,7 @@ xfs_alloc_query_range_helper(
 	xfs_failaddr_t				fa;
 
 	xfs_alloc_btrec_to_irec(rec, &irec);
-	fa = xfs_alloc_check_irec(cur, &irec);
+	fa = xfs_alloc_check_irec(cur->bc_ag.pag, &irec);
 	if (fa)
 		return xfs_alloc_complain_bad_rec(cur, fa, &irec);
 
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index 6bb8d295c321..0b956f8b9d5a 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -185,7 +185,7 @@ xfs_alloc_get_rec(
 union xfs_btree_rec;
 void xfs_alloc_btrec_to_irec(const union xfs_btree_rec *rec,
 		struct xfs_alloc_rec_incore *irec);
-xfs_failaddr_t xfs_alloc_check_irec(struct xfs_btree_cur *cur,
+xfs_failaddr_t xfs_alloc_check_irec(struct xfs_perag *pag,
 		const struct xfs_alloc_rec_incore *irec);
 
 int xfs_read_agf(struct xfs_perag *pag, struct xfs_trans *tp, int flags,
@@ -231,7 +231,7 @@ xfs_buf_to_agfl_bno(
 	return bp->b_addr;
 }
 
-int __xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno,
+int xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno,
 		xfs_filblks_t len, const struct xfs_owner_info *oinfo,
 		enum xfs_ag_resv_type type, bool skip_discard);
 
@@ -255,18 +255,18 @@ void xfs_extent_free_get_group(struct xfs_mount *mp,
 #define XFS_EFI_SKIP_DISCARD	(1U << 0) /* don't issue discard */
 #define XFS_EFI_ATTR_FORK	(1U << 1) /* freeing attr fork block */
 #define XFS_EFI_BMBT_BLOCK	(1U << 2) /* freeing bmap btree block */
+#define XFS_EFI_CANCELLED	(1U << 3) /* dont actually free the space */
 
-static inline int
-xfs_free_extent_later(
-	struct xfs_trans		*tp,
-	xfs_fsblock_t			bno,
-	xfs_filblks_t			len,
-	const struct xfs_owner_info	*oinfo,
-	enum xfs_ag_resv_type		type)
-{
-	return __xfs_free_extent_later(tp, bno, len, oinfo, type, false);
-}
+struct xfs_alloc_autoreap {
+	struct xfs_defer_pending	*dfp;
+};
 
+int xfs_alloc_schedule_autoreap(const struct xfs_alloc_arg *args,
+		bool skip_discard, struct xfs_alloc_autoreap *aarp);
+void xfs_alloc_cancel_autoreap(struct xfs_trans *tp,
+		struct xfs_alloc_autoreap *aarp);
+void xfs_alloc_commit_autoreap(struct xfs_trans *tp,
+		struct xfs_alloc_autoreap *aarp);
 
 extern struct kmem_cache	*xfs_extfree_item_cache;
 
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index c65228efed4a..a7032bf0cd37 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -323,7 +323,18 @@ xfs_allocbt_verify(
 	if (bp->b_ops->magic[0] == cpu_to_be32(XFS_ABTC_MAGIC))
 		btnum = XFS_BTNUM_CNTi;
 	if (pag && xfs_perag_initialised_agf(pag)) {
-		if (level >= pag->pagf_levels[btnum])
+		unsigned int	maxlevel = pag->pagf_levels[btnum];
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+		/*
+		 * Online repair could be rewriting the free space btrees, so
+		 * we'll validate against the larger of either tree while this
+		 * is going on.
+		 */
+		maxlevel = max_t(unsigned int, maxlevel,
+				 pag->pagf_repair_levels[btnum]);
+#endif
+		if (level >= maxlevel)
 			return __this_address;
 	} else if (level >= mp->m_alloc_maxlevels)
 		return __this_address;
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index e28d93d232de..9976a00a73f9 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -862,8 +862,11 @@ xfs_attr_lookup(
 	if (!xfs_inode_hasattr(dp))
 		return -ENOATTR;
 
-	if (dp->i_af.if_format == XFS_DINODE_FMT_LOCAL)
-		return xfs_attr_sf_findname(args, NULL, NULL);
+	if (dp->i_af.if_format == XFS_DINODE_FMT_LOCAL) {
+		if (xfs_attr_sf_findname(args))
+			return -EEXIST;
+		return -ENOATTR;
+	}
 
 	if (xfs_attr_is_leaf(dp)) {
 		error = xfs_attr_leaf_hasname(args, &bp);
@@ -880,11 +883,10 @@ xfs_attr_lookup(
 	return error;
 }
 
-static int
-xfs_attr_intent_init(
+static void
+xfs_attr_defer_add(
 	struct xfs_da_args	*args,
-	unsigned int		op_flags,	/* op flag (set or remove) */
-	struct xfs_attr_intent	**attr)		/* new xfs_attr_intent */
+	unsigned int		op_flags)
 {
 
 	struct xfs_attr_intent	*new;
@@ -893,66 +895,22 @@ xfs_attr_intent_init(
 	new->xattri_op_flags = op_flags;
 	new->xattri_da_args = args;
 
-	*attr = new;
-	return 0;
-}
-
-/* Sets an attribute for an inode as a deferred operation */
-static int
-xfs_attr_defer_add(
-	struct xfs_da_args	*args)
-{
-	struct xfs_attr_intent	*new;
-	int			error = 0;
-
-	error = xfs_attr_intent_init(args, XFS_ATTRI_OP_FLAGS_SET, &new);
-	if (error)
-		return error;
+	switch (op_flags) {
+	case XFS_ATTRI_OP_FLAGS_SET:
+		new->xattri_dela_state = xfs_attr_init_add_state(args);
+		break;
+	case XFS_ATTRI_OP_FLAGS_REPLACE:
+		new->xattri_dela_state = xfs_attr_init_replace_state(args);
+		break;
+	case XFS_ATTRI_OP_FLAGS_REMOVE:
+		new->xattri_dela_state = xfs_attr_init_remove_state(args);
+		break;
+	default:
+		ASSERT(0);
+	}
 
-	new->xattri_dela_state = xfs_attr_init_add_state(args);
-	xfs_defer_add(args->trans, XFS_DEFER_OPS_TYPE_ATTR, &new->xattri_list);
+	xfs_defer_add(args->trans, &new->xattri_list, &xfs_attr_defer_type);
 	trace_xfs_attr_defer_add(new->xattri_dela_state, args->dp);
-
-	return 0;
-}
-
-/* Sets an attribute for an inode as a deferred operation */
-static int
-xfs_attr_defer_replace(
-	struct xfs_da_args	*args)
-{
-	struct xfs_attr_intent	*new;
-	int			error = 0;
-
-	error = xfs_attr_intent_init(args, XFS_ATTRI_OP_FLAGS_REPLACE, &new);
-	if (error)
-		return error;
-
-	new->xattri_dela_state = xfs_attr_init_replace_state(args);
-	xfs_defer_add(args->trans, XFS_DEFER_OPS_TYPE_ATTR, &new->xattri_list);
-	trace_xfs_attr_defer_replace(new->xattri_dela_state, args->dp);
-
-	return 0;
-}
-
-/* Removes an attribute for an inode as a deferred operation */
-static int
-xfs_attr_defer_remove(
-	struct xfs_da_args	*args)
-{
-
-	struct xfs_attr_intent	*new;
-	int			error;
-
-	error  = xfs_attr_intent_init(args, XFS_ATTRI_OP_FLAGS_REMOVE, &new);
-	if (error)
-		return error;
-
-	new->xattri_dela_state = xfs_attr_init_remove_state(args);
-	xfs_defer_add(args->trans, XFS_DEFER_OPS_TYPE_ATTR, &new->xattri_list);
-	trace_xfs_attr_defer_remove(new->xattri_dela_state, args->dp);
-
-	return 0;
 }
 
 /*
@@ -1038,16 +996,16 @@ xfs_attr_set(
 	error = xfs_attr_lookup(args);
 	switch (error) {
 	case -EEXIST:
-		/* if no value, we are performing a remove operation */
 		if (!args->value) {
-			error = xfs_attr_defer_remove(args);
+			/* if no value, we are performing a remove operation */
+			xfs_attr_defer_add(args, XFS_ATTRI_OP_FLAGS_REMOVE);
 			break;
 		}
+
 		/* Pure create fails if the attr already exists */
 		if (args->attr_flags & XATTR_CREATE)
 			goto out_trans_cancel;
-
-		error = xfs_attr_defer_replace(args);
+		xfs_attr_defer_add(args, XFS_ATTRI_OP_FLAGS_REPLACE);
 		break;
 	case -ENOATTR:
 		/* Can't remove what isn't there. */
@@ -1057,14 +1015,11 @@ xfs_attr_set(
 		/* Pure replace fails if no existing attr to replace. */
 		if (args->attr_flags & XATTR_REPLACE)
 			goto out_trans_cancel;
-
-		error = xfs_attr_defer_add(args);
+		xfs_attr_defer_add(args, XFS_ATTRI_OP_FLAGS_SET);
 		break;
 	default:
 		goto out_trans_cancel;
 	}
-	if (error)
-		goto out_trans_cancel;
 
 	/*
 	 * If this is a synchronous mount, make sure that the
@@ -1097,10 +1052,9 @@ out_trans_cancel:
 
 static inline int xfs_attr_sf_totsize(struct xfs_inode *dp)
 {
-	struct xfs_attr_shortform *sf;
+	struct xfs_attr_sf_hdr *sf = dp->i_af.if_data;
 
-	sf = (struct xfs_attr_shortform *)dp->i_af.if_u1.if_data;
-	return be16_to_cpu(sf->hdr.totsize);
+	return be16_to_cpu(sf->totsize);
 }
 
 /*
@@ -1112,19 +1066,13 @@ xfs_attr_shortform_addname(
 	struct xfs_da_args	*args)
 {
 	int			newsize, forkoff;
-	int			error;
 
 	trace_xfs_attr_sf_addname(args);
 
-	error = xfs_attr_shortform_lookup(args);
-	switch (error) {
-	case -ENOATTR:
-		if (args->op_flags & XFS_DA_OP_REPLACE)
-			return error;
-		break;
-	case -EEXIST:
-		if (!(args->op_flags & XFS_DA_OP_REPLACE))
-			return error;
+	if (xfs_attr_sf_findname(args)) {
+		int		error;
+
+		ASSERT(args->op_flags & XFS_DA_OP_REPLACE);
 
 		error = xfs_attr_sf_removename(args);
 		if (error)
@@ -1137,11 +1085,8 @@ xfs_attr_shortform_addname(
 		 * around.
 		 */
 		args->op_flags &= ~XFS_DA_OP_REPLACE;
-		break;
-	case 0:
-		break;
-	default:
-		return error;
+	} else {
+		ASSERT(!(args->op_flags & XFS_DA_OP_REPLACE));
 	}
 
 	if (args->namelen >= XFS_ATTR_SF_ENTSIZE_MAX ||
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 2580ae47209a..6374bf107242 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -690,56 +690,32 @@ xfs_attr_shortform_create(
 	ASSERT(ifp->if_bytes == 0);
 	if (ifp->if_format == XFS_DINODE_FMT_EXTENTS)
 		ifp->if_format = XFS_DINODE_FMT_LOCAL;
-	xfs_idata_realloc(dp, sizeof(*hdr), XFS_ATTR_FORK);
-	hdr = (struct xfs_attr_sf_hdr *)ifp->if_u1.if_data;
+
+	hdr = xfs_idata_realloc(dp, sizeof(*hdr), XFS_ATTR_FORK);
 	memset(hdr, 0, sizeof(*hdr));
 	hdr->totsize = cpu_to_be16(sizeof(*hdr));
 	xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_ADATA);
 }
 
 /*
- * Return -EEXIST if attr is found, or -ENOATTR if not
- * args:  args containing attribute name and namelen
- * sfep:  If not null, pointer will be set to the last attr entry found on
-	  -EEXIST.  On -ENOATTR pointer is left at the last entry in the list
- * basep: If not null, pointer is set to the byte offset of the entry in the
- *	  list on -EEXIST.  On -ENOATTR, pointer is left at the byte offset of
- *	  the last entry in the list
+ * Return the entry if the attr in args is found, or NULL if not.
  */
-int
+struct xfs_attr_sf_entry *
 xfs_attr_sf_findname(
-	struct xfs_da_args	 *args,
-	struct xfs_attr_sf_entry **sfep,
-	unsigned int		 *basep)
+	struct xfs_da_args		*args)
 {
-	struct xfs_attr_shortform *sf;
-	struct xfs_attr_sf_entry *sfe;
-	unsigned int		base = sizeof(struct xfs_attr_sf_hdr);
-	int			size = 0;
-	int			end;
-	int			i;
+	struct xfs_attr_sf_hdr		*sf = args->dp->i_af.if_data;
+	struct xfs_attr_sf_entry	*sfe;
 
-	sf = (struct xfs_attr_shortform *)args->dp->i_af.if_u1.if_data;
-	sfe = &sf->list[0];
-	end = sf->hdr.count;
-	for (i = 0; i < end; sfe = xfs_attr_sf_nextentry(sfe),
-			     base += size, i++) {
-		size = xfs_attr_sf_entsize(sfe);
-		if (!xfs_attr_match(args, sfe->namelen, sfe->nameval,
-				    sfe->flags))
-			continue;
-		break;
+	for (sfe = xfs_attr_sf_firstentry(sf);
+	     sfe < xfs_attr_sf_endptr(sf);
+	     sfe = xfs_attr_sf_nextentry(sfe)) {
+		if (xfs_attr_match(args, sfe->namelen, sfe->nameval,
+				sfe->flags))
+			return sfe;
 	}
 
-	if (sfep != NULL)
-		*sfep = sfe;
-
-	if (basep != NULL)
-		*basep = base;
-
-	if (i == end)
-		return -ENOATTR;
-	return -EEXIST;
+	return NULL;
 }
 
 /*
@@ -751,38 +727,31 @@ xfs_attr_shortform_add(
 	struct xfs_da_args		*args,
 	int				forkoff)
 {
-	struct xfs_attr_shortform	*sf;
+	struct xfs_inode		*dp = args->dp;
+	struct xfs_mount		*mp = dp->i_mount;
+	struct xfs_ifork		*ifp = &dp->i_af;
+	struct xfs_attr_sf_hdr		*sf = ifp->if_data;
 	struct xfs_attr_sf_entry	*sfe;
-	int				offset, size;
-	struct xfs_mount		*mp;
-	struct xfs_inode		*dp;
-	struct xfs_ifork		*ifp;
+	int				size;
 
 	trace_xfs_attr_sf_add(args);
 
-	dp = args->dp;
-	mp = dp->i_mount;
 	dp->i_forkoff = forkoff;
 
-	ifp = &dp->i_af;
 	ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
-	sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
-	if (xfs_attr_sf_findname(args, &sfe, NULL) == -EEXIST)
-		ASSERT(0);
+	ASSERT(!xfs_attr_sf_findname(args));
 
-	offset = (char *)sfe - (char *)sf;
 	size = xfs_attr_sf_entsize_byname(args->namelen, args->valuelen);
-	xfs_idata_realloc(dp, size, XFS_ATTR_FORK);
-	sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
-	sfe = (struct xfs_attr_sf_entry *)((char *)sf + offset);
+	sf = xfs_idata_realloc(dp, size, XFS_ATTR_FORK);
 
+	sfe = xfs_attr_sf_endptr(sf);
 	sfe->namelen = args->namelen;
 	sfe->valuelen = args->valuelen;
 	sfe->flags = args->attr_filter;
 	memcpy(sfe->nameval, args->name, args->namelen);
 	memcpy(&sfe->nameval[args->namelen], args->value, args->valuelen);
-	sf->hdr.count++;
-	be16_add_cpu(&sf->hdr.totsize, size);
+	sf->count++;
+	be16_add_cpu(&sf->totsize, size);
 	xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_ADATA);
 
 	xfs_sbversion_add_attr2(mp, args->trans);
@@ -811,48 +780,43 @@ int
 xfs_attr_sf_removename(
 	struct xfs_da_args		*args)
 {
-	struct xfs_attr_shortform	*sf;
+	struct xfs_inode		*dp = args->dp;
+	struct xfs_mount		*mp = dp->i_mount;
+	struct xfs_attr_sf_hdr		*sf = dp->i_af.if_data;
 	struct xfs_attr_sf_entry	*sfe;
-	int				size = 0, end, totsize;
-	unsigned int			base;
-	struct xfs_mount		*mp;
-	struct xfs_inode		*dp;
-	int				error;
+	uint16_t			totsize = be16_to_cpu(sf->totsize);
+	void				*next, *end;
+	int				size = 0;
 
 	trace_xfs_attr_sf_remove(args);
 
-	dp = args->dp;
-	mp = dp->i_mount;
-	sf = (struct xfs_attr_shortform *)dp->i_af.if_u1.if_data;
-
-	error = xfs_attr_sf_findname(args, &sfe, &base);
-
-	/*
-	 * If we are recovering an operation, finding nothing to
-	 * remove is not an error - it just means there was nothing
-	 * to clean up.
-	 */
-	if (error == -ENOATTR && (args->op_flags & XFS_DA_OP_RECOVERY))
-		return 0;
-	if (error != -EEXIST)
-		return error;
-	size = xfs_attr_sf_entsize(sfe);
+	sfe = xfs_attr_sf_findname(args);
+	if (!sfe) {
+		/*
+		 * If we are recovering an operation, finding nothing to remove
+		 * is not an error, it just means there was nothing to clean up.
+		 */
+		if (args->op_flags & XFS_DA_OP_RECOVERY)
+			return 0;
+		return -ENOATTR;
+	}
 
 	/*
 	 * Fix up the attribute fork data, covering the hole
 	 */
-	end = base + size;
-	totsize = be16_to_cpu(sf->hdr.totsize);
-	if (end != totsize)
-		memmove(&((char *)sf)[base], &((char *)sf)[end], totsize - end);
-	sf->hdr.count--;
-	be16_add_cpu(&sf->hdr.totsize, -size);
+	size = xfs_attr_sf_entsize(sfe);
+	next = xfs_attr_sf_nextentry(sfe);
+	end = xfs_attr_sf_endptr(sf);
+	if (next < end)
+		memmove(sfe, next, end - next);
+	sf->count--;
+	totsize -= size;
+	sf->totsize = cpu_to_be16(totsize);
 
 	/*
 	 * Fix up the start offset of the attribute fork
 	 */
-	totsize -= size;
-	if (totsize == sizeof(xfs_attr_sf_hdr_t) && xfs_has_attr2(mp) &&
+	if (totsize == sizeof(struct xfs_attr_sf_hdr) && xfs_has_attr2(mp) &&
 	    (dp->i_df.if_format != XFS_DINODE_FMT_BTREE) &&
 	    !(args->op_flags & (XFS_DA_OP_ADDNAME | XFS_DA_OP_REPLACE))) {
 		xfs_attr_fork_remove(dp, args->trans);
@@ -860,7 +824,7 @@ xfs_attr_sf_removename(
 		xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
 		dp->i_forkoff = xfs_attr_shortform_bytesfit(dp, totsize);
 		ASSERT(dp->i_forkoff);
-		ASSERT(totsize > sizeof(xfs_attr_sf_hdr_t) ||
+		ASSERT(totsize > sizeof(struct xfs_attr_sf_hdr) ||
 				(args->op_flags & XFS_DA_OP_ADDNAME) ||
 				!xfs_has_attr2(mp) ||
 				dp->i_df.if_format == XFS_DINODE_FMT_BTREE);
@@ -874,33 +838,6 @@ xfs_attr_sf_removename(
 }
 
 /*
- * Look up a name in a shortform attribute list structure.
- */
-/*ARGSUSED*/
-int
-xfs_attr_shortform_lookup(xfs_da_args_t *args)
-{
-	struct xfs_attr_shortform *sf;
-	struct xfs_attr_sf_entry *sfe;
-	int i;
-	struct xfs_ifork *ifp;
-
-	trace_xfs_attr_sf_lookup(args);
-
-	ifp = &args->dp->i_af;
-	ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
-	sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
-	sfe = &sf->list[0];
-	for (i = 0; i < sf->hdr.count;
-				sfe = xfs_attr_sf_nextentry(sfe), i++) {
-		if (xfs_attr_match(args, sfe->namelen, sfe->nameval,
-				sfe->flags))
-			return -EEXIST;
-	}
-	return -ENOATTR;
-}
-
-/*
  * Retrieve the attribute value and length.
  *
  * If args->valuelen is zero, only the length needs to be returned.  Unlike a
@@ -909,23 +846,19 @@ xfs_attr_shortform_lookup(xfs_da_args_t *args)
  */
 int
 xfs_attr_shortform_getvalue(
-	struct xfs_da_args	*args)
+	struct xfs_da_args		*args)
 {
-	struct xfs_attr_shortform *sf;
-	struct xfs_attr_sf_entry *sfe;
-	int			i;
+	struct xfs_attr_sf_entry	*sfe;
 
 	ASSERT(args->dp->i_af.if_format == XFS_DINODE_FMT_LOCAL);
-	sf = (struct xfs_attr_shortform *)args->dp->i_af.if_u1.if_data;
-	sfe = &sf->list[0];
-	for (i = 0; i < sf->hdr.count;
-				sfe = xfs_attr_sf_nextentry(sfe), i++) {
-		if (xfs_attr_match(args, sfe->namelen, sfe->nameval,
-				sfe->flags))
-			return xfs_attr_copy_value(args,
-				&sfe->nameval[args->namelen], sfe->valuelen);
-	}
-	return -ENOATTR;
+
+	trace_xfs_attr_sf_lookup(args);
+
+	sfe = xfs_attr_sf_findname(args);
+	if (!sfe)
+		return -ENOATTR;
+	return xfs_attr_copy_value(args, &sfe->nameval[args->namelen],
+			sfe->valuelen);
 }
 
 /* Convert from using the shortform to the leaf format. */
@@ -933,26 +866,23 @@ int
 xfs_attr_shortform_to_leaf(
 	struct xfs_da_args		*args)
 {
-	struct xfs_inode		*dp;
-	struct xfs_attr_shortform	*sf;
+	struct xfs_inode		*dp = args->dp;
+	struct xfs_ifork		*ifp = &dp->i_af;
+	struct xfs_attr_sf_hdr		*sf = ifp->if_data;
 	struct xfs_attr_sf_entry	*sfe;
+	int				size = be16_to_cpu(sf->totsize);
 	struct xfs_da_args		nargs;
 	char				*tmpbuffer;
-	int				error, i, size;
+	int				error, i;
 	xfs_dablk_t			blkno;
 	struct xfs_buf			*bp;
-	struct xfs_ifork		*ifp;
 
 	trace_xfs_attr_sf_to_leaf(args);
 
-	dp = args->dp;
-	ifp = &dp->i_af;
-	sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
-	size = be16_to_cpu(sf->hdr.totsize);
 	tmpbuffer = kmem_alloc(size, 0);
 	ASSERT(tmpbuffer != NULL);
-	memcpy(tmpbuffer, ifp->if_u1.if_data, size);
-	sf = (struct xfs_attr_shortform *)tmpbuffer;
+	memcpy(tmpbuffer, ifp->if_data, size);
+	sf = (struct xfs_attr_sf_hdr *)tmpbuffer;
 
 	xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
 	xfs_bmap_local_to_extents_empty(args->trans, dp, XFS_ATTR_FORK);
@@ -975,8 +905,8 @@ xfs_attr_shortform_to_leaf(
 	nargs.trans = args->trans;
 	nargs.op_flags = XFS_DA_OP_OKNOENT;
 
-	sfe = &sf->list[0];
-	for (i = 0; i < sf->hdr.count; i++) {
+	sfe = xfs_attr_sf_firstentry(sf);
+	for (i = 0; i < sf->count; i++) {
 		nargs.name = sfe->nameval;
 		nargs.namelen = sfe->namelen;
 		nargs.value = &sfe->nameval[nargs.namelen];
@@ -1040,23 +970,16 @@ xfs_attr_shortform_allfit(
 	return xfs_attr_shortform_bytesfit(dp, bytes);
 }
 
-/* Verify the consistency of an inline attribute fork. */
+/* Verify the consistency of a raw inline attribute fork. */
 xfs_failaddr_t
 xfs_attr_shortform_verify(
-	struct xfs_inode		*ip)
+	struct xfs_attr_sf_hdr		*sfp,
+	size_t				size)
 {
-	struct xfs_attr_shortform	*sfp;
-	struct xfs_attr_sf_entry	*sfep;
+	struct xfs_attr_sf_entry	*sfep = xfs_attr_sf_firstentry(sfp);
 	struct xfs_attr_sf_entry	*next_sfep;
 	char				*endp;
-	struct xfs_ifork		*ifp;
 	int				i;
-	int64_t				size;
-
-	ASSERT(ip->i_af.if_format == XFS_DINODE_FMT_LOCAL);
-	ifp = xfs_ifork_ptr(ip, XFS_ATTR_FORK);
-	sfp = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
-	size = ifp->if_bytes;
 
 	/*
 	 * Give up if the attribute is way too short.
@@ -1067,8 +990,7 @@ xfs_attr_shortform_verify(
 	endp = (char *)sfp + size;
 
 	/* Check all reported entries */
-	sfep = &sfp->list[0];
-	for (i = 0; i < sfp->hdr.count; i++) {
+	for (i = 0; i < sfp->count; i++) {
 		/*
 		 * struct xfs_attr_sf_entry has a variable length.
 		 * Check the fixed-offset parts of the structure are
@@ -1244,14 +1166,10 @@ xfs_attr3_leaf_to_node(
 	if (error)
 		goto out;
 
-	/* copy leaf to new buffer, update identifiers */
-	xfs_trans_buf_set_type(args->trans, bp2, XFS_BLFT_ATTR_LEAF_BUF);
-	bp2->b_ops = bp1->b_ops;
-	memcpy(bp2->b_addr, bp1->b_addr, args->geo->blksize);
-	if (xfs_has_crc(mp)) {
-		struct xfs_da3_blkinfo *hdr3 = bp2->b_addr;
-		hdr3->blkno = cpu_to_be64(xfs_buf_daddr(bp2));
-	}
+	/*
+	 * Copy leaf to new buffer and log it.
+	 */
+	xfs_da_buf_copy(bp2, bp1, args->geo->blksize);
 	xfs_trans_log_buf(args->trans, bp2, 0, args->geo->blksize - 1);
 
 	/*
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h
index 368f4d9fa1d5..9b9948639c0f 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.h
+++ b/fs/xfs/libxfs/xfs_attr_leaf.h
@@ -47,16 +47,14 @@ struct xfs_attr3_icleaf_hdr {
  */
 void	xfs_attr_shortform_create(struct xfs_da_args *args);
 void	xfs_attr_shortform_add(struct xfs_da_args *args, int forkoff);
-int	xfs_attr_shortform_lookup(struct xfs_da_args *args);
 int	xfs_attr_shortform_getvalue(struct xfs_da_args *args);
 int	xfs_attr_shortform_to_leaf(struct xfs_da_args *args);
 int	xfs_attr_sf_removename(struct xfs_da_args *args);
-int	xfs_attr_sf_findname(struct xfs_da_args *args,
-			     struct xfs_attr_sf_entry **sfep,
-			     unsigned int *basep);
+struct xfs_attr_sf_entry *xfs_attr_sf_findname(struct xfs_da_args *args);
 int	xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp);
 int	xfs_attr_shortform_bytesfit(struct xfs_inode *dp, int bytes);
-xfs_failaddr_t xfs_attr_shortform_verify(struct xfs_inode *ip);
+xfs_failaddr_t xfs_attr_shortform_verify(struct xfs_attr_sf_hdr *sfp,
+		size_t size);
 void	xfs_attr_fork_remove(struct xfs_inode *ip, struct xfs_trans *tp);
 
 /*
diff --git a/fs/xfs/libxfs/xfs_attr_sf.h b/fs/xfs/libxfs/xfs_attr_sf.h
index 37578b369d9b..bc4422223024 100644
--- a/fs/xfs/libxfs/xfs_attr_sf.h
+++ b/fs/xfs/libxfs/xfs_attr_sf.h
@@ -7,14 +7,6 @@
 #define	__XFS_ATTR_SF_H__
 
 /*
- * Attribute storage when stored inside the inode.
- *
- * Small attribute lists are packed as tightly as possible so as
- * to fit into the literal area of the inode.
- */
-typedef struct xfs_attr_sf_hdr xfs_attr_sf_hdr_t;
-
-/*
  * We generate this then sort it, attr_list() must return things in hash-order.
  */
 typedef struct xfs_attr_sf_sort {
@@ -41,11 +33,25 @@ static inline int xfs_attr_sf_entsize(struct xfs_attr_sf_entry *sfep)
 	return struct_size(sfep, nameval, sfep->namelen + sfep->valuelen);
 }
 
-/* next entry in struct */
+/* first entry in the SF attr fork */
+static inline struct xfs_attr_sf_entry *
+xfs_attr_sf_firstentry(struct xfs_attr_sf_hdr *hdr)
+{
+	return (struct xfs_attr_sf_entry *)(hdr + 1);
+}
+
+/* next entry after sfep */
 static inline struct xfs_attr_sf_entry *
 xfs_attr_sf_nextentry(struct xfs_attr_sf_entry *sfep)
 {
 	return (void *)sfep + xfs_attr_sf_entsize(sfep);
 }
 
+/* pointer to the space after the last entry, e.g. for adding a new one */
+static inline struct xfs_attr_sf_entry *
+xfs_attr_sf_endptr(struct xfs_attr_sf_hdr *sf)
+{
+	return (void *)sf + be16_to_cpu(sf->totsize);
+}
+
 #endif	/* __XFS_ATTR_SF_H__ */
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index be62acffad6c..98aaca933bdd 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -575,7 +575,7 @@ xfs_bmap_btree_to_extents(
 
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
 	error = xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo,
-			XFS_AG_RESV_NONE);
+			XFS_AG_RESV_NONE, false);
 	if (error)
 		return error;
 
@@ -747,7 +747,7 @@ xfs_bmap_local_to_extents_empty(
 	ASSERT(ifp->if_nextents == 0);
 
 	xfs_bmap_forkoff_reset(ip, whichfork);
-	ifp->if_u1.if_root = NULL;
+	ifp->if_data = NULL;
 	ifp->if_height = 0;
 	ifp->if_format = XFS_DINODE_FMT_EXTENTS;
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
@@ -832,7 +832,7 @@ xfs_bmap_local_to_extents(
 	xfs_bmap_local_to_extents_empty(tp, ip, whichfork);
 	flags |= XFS_ILOG_CORE;
 
-	ifp->if_u1.if_root = NULL;
+	ifp->if_data = NULL;
 	ifp->if_height = 0;
 
 	rec.br_startoff = 0;
@@ -3044,7 +3044,8 @@ xfs_bmap_extsize_align(
 
 #define XFS_ALLOC_GAP_UNITS	4
 
-void
+/* returns true if ap->blkno was modified */
+bool
 xfs_bmap_adjacent(
 	struct xfs_bmalloca	*ap)	/* bmap alloc argument struct */
 {
@@ -3079,13 +3080,14 @@ xfs_bmap_adjacent(
 		if (adjust &&
 		    ISVALID(ap->blkno + adjust, ap->prev.br_startblock))
 			ap->blkno += adjust;
+		return true;
 	}
 	/*
 	 * If not at eof, then compare the two neighbor blocks.
 	 * Figure out whether either one gives us a good starting point,
 	 * and pick the better one.
 	 */
-	else if (!ap->eof) {
+	if (!ap->eof) {
 		xfs_fsblock_t	gotbno;		/* right side block number */
 		xfs_fsblock_t	gotdiff=0;	/* right side difference */
 		xfs_fsblock_t	prevbno;	/* left side block number */
@@ -3165,14 +3167,21 @@ xfs_bmap_adjacent(
 		 * If both valid, pick the better one, else the only good
 		 * one, else ap->blkno is already set (to 0 or the inode block).
 		 */
-		if (prevbno != NULLFSBLOCK && gotbno != NULLFSBLOCK)
+		if (prevbno != NULLFSBLOCK && gotbno != NULLFSBLOCK) {
 			ap->blkno = prevdiff <= gotdiff ? prevbno : gotbno;
-		else if (prevbno != NULLFSBLOCK)
+			return true;
+		}
+		if (prevbno != NULLFSBLOCK) {
 			ap->blkno = prevbno;
-		else if (gotbno != NULLFSBLOCK)
+			return true;
+		}
+		if (gotbno != NULLFSBLOCK) {
 			ap->blkno = gotbno;
+			return true;
+		}
 	}
 #undef ISVALID
+	return false;
 }
 
 int
@@ -3263,11 +3272,14 @@ xfs_bmap_btalloc_select_lengths(
 }
 
 /* Update all inode and quota accounting for the allocation we just did. */
-static void
-xfs_bmap_btalloc_accounting(
-	struct xfs_bmalloca	*ap,
-	struct xfs_alloc_arg	*args)
+void
+xfs_bmap_alloc_account(
+	struct xfs_bmalloca	*ap)
 {
+	bool			isrt = XFS_IS_REALTIME_INODE(ap->ip) &&
+					(ap->flags & XFS_BMAPI_ATTRFORK);
+	uint			fld;
+
 	if (ap->flags & XFS_BMAPI_COWFORK) {
 		/*
 		 * COW fork blocks are in-core only and thus are treated as
@@ -3279,7 +3291,7 @@ xfs_bmap_btalloc_accounting(
 		 * yet.
 		 */
 		if (ap->wasdel) {
-			xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)args->len);
+			xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)ap->length);
 			return;
 		}
 
@@ -3291,22 +3303,25 @@ xfs_bmap_btalloc_accounting(
 		 * This essentially transfers the transaction quota reservation
 		 * to that of a delalloc extent.
 		 */
-		ap->ip->i_delayed_blks += args->len;
-		xfs_trans_mod_dquot_byino(ap->tp, ap->ip, XFS_TRANS_DQ_RES_BLKS,
-				-(long)args->len);
+		ap->ip->i_delayed_blks += ap->length;
+		xfs_trans_mod_dquot_byino(ap->tp, ap->ip, isrt ?
+				XFS_TRANS_DQ_RES_RTBLKS : XFS_TRANS_DQ_RES_BLKS,
+				-(long)ap->length);
 		return;
 	}
 
 	/* data/attr fork only */
-	ap->ip->i_nblocks += args->len;
+	ap->ip->i_nblocks += ap->length;
 	xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE);
 	if (ap->wasdel) {
-		ap->ip->i_delayed_blks -= args->len;
-		xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)args->len);
+		ap->ip->i_delayed_blks -= ap->length;
+		xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)ap->length);
+		fld = isrt ? XFS_TRANS_DQ_DELRTBCOUNT : XFS_TRANS_DQ_DELBCOUNT;
+	} else {
+		fld = isrt ? XFS_TRANS_DQ_RTBCOUNT : XFS_TRANS_DQ_BCOUNT;
 	}
-	xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
-		ap->wasdel ? XFS_TRANS_DQ_DELBCOUNT : XFS_TRANS_DQ_BCOUNT,
-		args->len);
+
+	xfs_trans_mod_dquot_byino(ap->tp, ap->ip, fld, ap->length);
 }
 
 static int
@@ -3380,7 +3395,7 @@ xfs_bmap_process_allocated_extent(
 		ap->offset = orig_offset;
 	else if (ap->offset + ap->length < orig_offset + orig_length)
 		ap->offset = orig_offset + orig_length - ap->length;
-	xfs_bmap_btalloc_accounting(ap, args);
+	xfs_bmap_alloc_account(ap);
 }
 
 #ifdef DEBUG
@@ -5010,7 +5025,6 @@ xfs_bmap_del_extent_real(
 	xfs_fileoff_t		del_endoff;	/* first offset past del */
 	int			do_fx;	/* free extent at end of routine */
 	int			error;	/* error return value */
-	int			flags = 0;/* inode logging flags */
 	struct xfs_bmbt_irec	got;	/* current extent entry */
 	xfs_fileoff_t		got_endoff;	/* first offset past got */
 	int			i;	/* temp state */
@@ -5023,6 +5037,8 @@ xfs_bmap_del_extent_real(
 	uint32_t		state = xfs_bmap_fork_to_state(whichfork);
 	struct xfs_bmbt_irec	old;
 
+	*logflagsp = 0;
+
 	mp = ip->i_mount;
 	XFS_STATS_INC(mp, xs_del_exlist);
 
@@ -5035,7 +5051,6 @@ xfs_bmap_del_extent_real(
 	ASSERT(got_endoff >= del_endoff);
 	ASSERT(!isnullstartblock(got.br_startblock));
 	qfield = 0;
-	error = 0;
 
 	/*
 	 * If it's the case where the directory code is running with no block
@@ -5051,13 +5066,13 @@ xfs_bmap_del_extent_real(
 	    del->br_startoff > got.br_startoff && del_endoff < got_endoff)
 		return -ENOSPC;
 
-	flags = XFS_ILOG_CORE;
+	*logflagsp = XFS_ILOG_CORE;
 	if (whichfork == XFS_DATA_FORK && XFS_IS_REALTIME_INODE(ip)) {
 		if (!(bflags & XFS_BMAPI_REMAP)) {
 			error = xfs_rtfree_blocks(tp, del->br_startblock,
 					del->br_blockcount);
 			if (error)
-				goto done;
+				return error;
 		}
 
 		do_fx = 0;
@@ -5072,11 +5087,9 @@ xfs_bmap_del_extent_real(
 	if (cur) {
 		error = xfs_bmbt_lookup_eq(cur, &got, &i);
 		if (error)
-			goto done;
-		if (XFS_IS_CORRUPT(mp, i != 1)) {
-			error = -EFSCORRUPTED;
-			goto done;
-		}
+			return error;
+		if (XFS_IS_CORRUPT(mp, i != 1))
+			return -EFSCORRUPTED;
 	}
 
 	if (got.br_startoff == del->br_startoff)
@@ -5093,17 +5106,15 @@ xfs_bmap_del_extent_real(
 		xfs_iext_prev(ifp, icur);
 		ifp->if_nextents--;
 
-		flags |= XFS_ILOG_CORE;
+		*logflagsp |= XFS_ILOG_CORE;
 		if (!cur) {
-			flags |= xfs_ilog_fext(whichfork);
+			*logflagsp |= xfs_ilog_fext(whichfork);
 			break;
 		}
 		if ((error = xfs_btree_delete(cur, &i)))
-			goto done;
-		if (XFS_IS_CORRUPT(mp, i != 1)) {
-			error = -EFSCORRUPTED;
-			goto done;
-		}
+			return error;
+		if (XFS_IS_CORRUPT(mp, i != 1))
+			return -EFSCORRUPTED;
 		break;
 	case BMAP_LEFT_FILLING:
 		/*
@@ -5114,12 +5125,12 @@ xfs_bmap_del_extent_real(
 		got.br_blockcount -= del->br_blockcount;
 		xfs_iext_update_extent(ip, state, icur, &got);
 		if (!cur) {
-			flags |= xfs_ilog_fext(whichfork);
+			*logflagsp |= xfs_ilog_fext(whichfork);
 			break;
 		}
 		error = xfs_bmbt_update(cur, &got);
 		if (error)
-			goto done;
+			return error;
 		break;
 	case BMAP_RIGHT_FILLING:
 		/*
@@ -5128,12 +5139,12 @@ xfs_bmap_del_extent_real(
 		got.br_blockcount -= del->br_blockcount;
 		xfs_iext_update_extent(ip, state, icur, &got);
 		if (!cur) {
-			flags |= xfs_ilog_fext(whichfork);
+			*logflagsp |= xfs_ilog_fext(whichfork);
 			break;
 		}
 		error = xfs_bmbt_update(cur, &got);
 		if (error)
-			goto done;
+			return error;
 		break;
 	case 0:
 		/*
@@ -5150,18 +5161,18 @@ xfs_bmap_del_extent_real(
 		new.br_state = got.br_state;
 		new.br_startblock = del_endblock;
 
-		flags |= XFS_ILOG_CORE;
+		*logflagsp |= XFS_ILOG_CORE;
 		if (cur) {
 			error = xfs_bmbt_update(cur, &got);
 			if (error)
-				goto done;
+				return error;
 			error = xfs_btree_increment(cur, 0, &i);
 			if (error)
-				goto done;
+				return error;
 			cur->bc_rec.b = new;
 			error = xfs_btree_insert(cur, &i);
 			if (error && error != -ENOSPC)
-				goto done;
+				return error;
 			/*
 			 * If get no-space back from btree insert, it tried a
 			 * split, and we have a zero block reservation.  Fix up
@@ -5174,33 +5185,28 @@ xfs_bmap_del_extent_real(
 				 */
 				error = xfs_bmbt_lookup_eq(cur, &got, &i);
 				if (error)
-					goto done;
-				if (XFS_IS_CORRUPT(mp, i != 1)) {
-					error = -EFSCORRUPTED;
-					goto done;
-				}
+					return error;
+				if (XFS_IS_CORRUPT(mp, i != 1))
+					return -EFSCORRUPTED;
 				/*
 				 * Update the btree record back
 				 * to the original value.
 				 */
 				error = xfs_bmbt_update(cur, &old);
 				if (error)
-					goto done;
+					return error;
 				/*
 				 * Reset the extent record back
 				 * to the original value.
 				 */
 				xfs_iext_update_extent(ip, state, icur, &old);
-				flags = 0;
-				error = -ENOSPC;
-				goto done;
-			}
-			if (XFS_IS_CORRUPT(mp, i != 1)) {
-				error = -EFSCORRUPTED;
-				goto done;
+				*logflagsp = 0;
+				return -ENOSPC;
 			}
+			if (XFS_IS_CORRUPT(mp, i != 1))
+				return -EFSCORRUPTED;
 		} else
-			flags |= xfs_ilog_fext(whichfork);
+			*logflagsp |= xfs_ilog_fext(whichfork);
 
 		ifp->if_nextents++;
 		xfs_iext_next(ifp, icur);
@@ -5218,13 +5224,13 @@ xfs_bmap_del_extent_real(
 		if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) {
 			xfs_refcount_decrease_extent(tp, del);
 		} else {
-			error = __xfs_free_extent_later(tp, del->br_startblock,
+			error = xfs_free_extent_later(tp, del->br_startblock,
 					del->br_blockcount, NULL,
 					XFS_AG_RESV_NONE,
 					((bflags & XFS_BMAPI_NODISCARD) ||
 					del->br_state == XFS_EXT_UNWRITTEN));
 			if (error)
-				goto done;
+				return error;
 		}
 	}
 
@@ -5239,9 +5245,7 @@ xfs_bmap_del_extent_real(
 	if (qfield && !(bflags & XFS_BMAPI_REMAP))
 		xfs_trans_mod_dquot_byino(tp, ip, qfield, (long)-nblks);
 
-done:
-	*logflagsp = flags;
-	return error;
+	return 0;
 }
 
 /*
@@ -5250,7 +5254,7 @@ done:
  * that value.  If not all extents in the block range can be removed then
  * *done is set.
  */
-int						/* error */
+static int
 __xfs_bunmapi(
 	struct xfs_trans	*tp,		/* transaction pointer */
 	struct xfs_inode	*ip,		/* incore inode */
@@ -6102,7 +6106,7 @@ __xfs_bmap_add(
 	bi->bi_bmap = *bmap;
 
 	xfs_bmap_update_get_group(tp->t_mountp, bi);
-	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_BMAP, &bi->bi_list);
+	xfs_defer_add(tp, &bi->bi_list, &xfs_bmap_update_defer_type);
 	return 0;
 }
 
@@ -6179,19 +6183,18 @@ xfs_bmap_finish_one(
 	return error;
 }
 
-/* Check that an inode's extent does not have invalid flags or bad ranges. */
+/* Check that an extent does not have invalid flags or bad ranges. */
 xfs_failaddr_t
-xfs_bmap_validate_extent(
-	struct xfs_inode	*ip,
+xfs_bmap_validate_extent_raw(
+	struct xfs_mount	*mp,
+	bool			rtfile,
 	int			whichfork,
 	struct xfs_bmbt_irec	*irec)
 {
-	struct xfs_mount	*mp = ip->i_mount;
-
 	if (!xfs_verify_fileext(mp, irec->br_startoff, irec->br_blockcount))
 		return __this_address;
 
-	if (XFS_IS_REALTIME_INODE(ip) && whichfork == XFS_DATA_FORK) {
+	if (rtfile && whichfork == XFS_DATA_FORK) {
 		if (!xfs_verify_rtbext(mp, irec->br_startblock,
 					   irec->br_blockcount))
 			return __this_address;
@@ -6221,3 +6224,53 @@ xfs_bmap_intent_destroy_cache(void)
 	kmem_cache_destroy(xfs_bmap_intent_cache);
 	xfs_bmap_intent_cache = NULL;
 }
+
+/* Check that an inode's extent does not have invalid flags or bad ranges. */
+xfs_failaddr_t
+xfs_bmap_validate_extent(
+	struct xfs_inode	*ip,
+	int			whichfork,
+	struct xfs_bmbt_irec	*irec)
+{
+	return xfs_bmap_validate_extent_raw(ip->i_mount,
+			XFS_IS_REALTIME_INODE(ip), whichfork, irec);
+}
+
+/*
+ * Used in xfs_itruncate_extents().  This is the maximum number of extents
+ * freed from a file in a single transaction.
+ */
+#define	XFS_ITRUNC_MAX_EXTENTS	2
+
+/*
+ * Unmap every extent in part of an inode's fork.  We don't do any higher level
+ * invalidation work at all.
+ */
+int
+xfs_bunmapi_range(
+	struct xfs_trans	**tpp,
+	struct xfs_inode	*ip,
+	uint32_t		flags,
+	xfs_fileoff_t		startoff,
+	xfs_fileoff_t		endoff)
+{
+	xfs_filblks_t		unmap_len = endoff - startoff + 1;
+	int			error = 0;
+
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+
+	while (unmap_len > 0) {
+		ASSERT((*tpp)->t_highest_agno == NULLAGNUMBER);
+		error = __xfs_bunmapi(*tpp, ip, startoff, &unmap_len, flags,
+				XFS_ITRUNC_MAX_EXTENTS);
+		if (error)
+			goto out;
+
+		/* free the just unmapped extents */
+		error = xfs_defer_finish(tpp);
+		if (error)
+			goto out;
+	}
+out:
+	return error;
+}
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index e33470e39728..f6b73f1bad5f 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -116,6 +116,8 @@ static inline int xfs_bmapi_whichfork(uint32_t bmapi_flags)
 	return XFS_DATA_FORK;
 }
 
+void xfs_bmap_alloc_account(struct xfs_bmalloca *ap);
+
 /*
  * Special values for xfs_bmbt_irec_t br_startblock field.
  */
@@ -190,9 +192,6 @@ int	xfs_bmapi_read(struct xfs_inode *ip, xfs_fileoff_t bno,
 int	xfs_bmapi_write(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, uint32_t flags,
 		xfs_extlen_t total, struct xfs_bmbt_irec *mval, int *nmap);
-int	__xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
-		xfs_fileoff_t bno, xfs_filblks_t *rlen, uint32_t flags,
-		xfs_extnum_t nexts);
 int	xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, uint32_t flags,
 		xfs_extnum_t nexts, int *done);
@@ -263,6 +262,8 @@ static inline uint32_t xfs_bmap_fork_to_state(int whichfork)
 	}
 }
 
+xfs_failaddr_t xfs_bmap_validate_extent_raw(struct xfs_mount *mp, bool rtfile,
+		int whichfork, struct xfs_bmbt_irec *irec);
 xfs_failaddr_t xfs_bmap_validate_extent(struct xfs_inode *ip, int whichfork,
 		struct xfs_bmbt_irec *irec);
 int xfs_bmap_complain_bad_rec(struct xfs_inode *ip, int whichfork,
@@ -271,6 +272,8 @@ int xfs_bmap_complain_bad_rec(struct xfs_inode *ip, int whichfork,
 int	xfs_bmapi_remap(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, xfs_fsblock_t startblock,
 		uint32_t flags);
+int	xfs_bunmapi_range(struct xfs_trans **tpp, struct xfs_inode *ip,
+		uint32_t flags, xfs_fileoff_t startoff, xfs_fileoff_t endoff);
 
 extern struct kmem_cache	*xfs_bmap_intent_cache;
 
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index bf3f1b36fdd2..71f2d50f7823 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -15,6 +15,7 @@
 #include "xfs_trans.h"
 #include "xfs_alloc.h"
 #include "xfs_btree.h"
+#include "xfs_btree_staging.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_bmap.h"
 #include "xfs_error.h"
@@ -272,7 +273,7 @@ xfs_bmbt_free_block(
 
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork);
 	error = xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo,
-			XFS_AG_RESV_NONE);
+			XFS_AG_RESV_NONE, false);
 	if (error)
 		return error;
 
@@ -288,10 +289,7 @@ xfs_bmbt_get_minrecs(
 	int			level)
 {
 	if (level == cur->bc_nlevels - 1) {
-		struct xfs_ifork	*ifp;
-
-		ifp = xfs_ifork_ptr(cur->bc_ino.ip,
-				    cur->bc_ino.whichfork);
+		struct xfs_ifork	*ifp = xfs_btree_ifork_ptr(cur);
 
 		return xfs_bmbt_maxrecs(cur->bc_mp,
 					ifp->if_broot_bytes, level == 0) / 2;
@@ -306,10 +304,7 @@ xfs_bmbt_get_maxrecs(
 	int			level)
 {
 	if (level == cur->bc_nlevels - 1) {
-		struct xfs_ifork	*ifp;
-
-		ifp = xfs_ifork_ptr(cur->bc_ino.ip,
-				    cur->bc_ino.whichfork);
+		struct xfs_ifork	*ifp = xfs_btree_ifork_ptr(cur);
 
 		return xfs_bmbt_maxrecs(cur->bc_mp,
 					ifp->if_broot_bytes, level == 0);
@@ -543,23 +538,19 @@ static const struct xfs_btree_ops xfs_bmbt_ops = {
 	.keys_contiguous	= xfs_bmbt_keys_contiguous,
 };
 
-/*
- * Allocate a new bmap btree cursor.
- */
-struct xfs_btree_cur *				/* new bmap btree cursor */
-xfs_bmbt_init_cursor(
-	struct xfs_mount	*mp,		/* file system mount point */
-	struct xfs_trans	*tp,		/* transaction pointer */
-	struct xfs_inode	*ip,		/* inode owning the btree */
-	int			whichfork)	/* data or attr fork */
+static struct xfs_btree_cur *
+xfs_bmbt_init_common(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	int			whichfork)
 {
-	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);
 	struct xfs_btree_cur	*cur;
+
 	ASSERT(whichfork != XFS_COW_FORK);
 
 	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_BMAP,
 			mp->m_bm_maxlevels[whichfork], xfs_bmbt_cur_cache);
-	cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1;
 	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_bmbt_2);
 
 	cur->bc_ops = &xfs_bmbt_ops;
@@ -567,10 +558,30 @@ xfs_bmbt_init_cursor(
 	if (xfs_has_crc(mp))
 		cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
 
-	cur->bc_ino.forksize = xfs_inode_fork_size(ip, whichfork);
 	cur->bc_ino.ip = ip;
 	cur->bc_ino.allocated = 0;
 	cur->bc_ino.flags = 0;
+
+	return cur;
+}
+
+/*
+ * Allocate a new bmap btree cursor.
+ */
+struct xfs_btree_cur *
+xfs_bmbt_init_cursor(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	int			whichfork)
+{
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);
+	struct xfs_btree_cur	*cur;
+
+	cur = xfs_bmbt_init_common(mp, tp, ip, whichfork);
+
+	cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1;
+	cur->bc_ino.forksize = xfs_inode_fork_size(ip, whichfork);
 	cur->bc_ino.whichfork = whichfork;
 
 	return cur;
@@ -588,6 +599,76 @@ xfs_bmbt_block_maxrecs(
 }
 
 /*
+ * Allocate a new bmap btree cursor for reloading an inode block mapping data
+ * structure.  Note that callers can use the staged cursor to reload extents
+ * format inode forks if they rebuild the iext tree and commit the staged
+ * cursor immediately.
+ */
+struct xfs_btree_cur *
+xfs_bmbt_stage_cursor(
+	struct xfs_mount	*mp,
+	struct xfs_inode	*ip,
+	struct xbtree_ifakeroot	*ifake)
+{
+	struct xfs_btree_cur	*cur;
+	struct xfs_btree_ops	*ops;
+
+	/* data fork always has larger maxheight */
+	cur = xfs_bmbt_init_common(mp, NULL, ip, XFS_DATA_FORK);
+	cur->bc_nlevels = ifake->if_levels;
+	cur->bc_ino.forksize = ifake->if_fork_size;
+
+	/* Don't let anyone think we're attached to the real fork yet. */
+	cur->bc_ino.whichfork = -1;
+	xfs_btree_stage_ifakeroot(cur, ifake, &ops);
+	ops->update_cursor = NULL;
+	return cur;
+}
+
+/*
+ * Swap in the new inode fork root.  Once we pass this point the newly rebuilt
+ * mappings are in place and we have to kill off any old btree blocks.
+ */
+void
+xfs_bmbt_commit_staged_btree(
+	struct xfs_btree_cur	*cur,
+	struct xfs_trans	*tp,
+	int			whichfork)
+{
+	struct xbtree_ifakeroot	*ifake = cur->bc_ino.ifake;
+	struct xfs_ifork	*ifp;
+	static const short	brootflag[2] = {XFS_ILOG_DBROOT, XFS_ILOG_ABROOT};
+	static const short	extflag[2] = {XFS_ILOG_DEXT, XFS_ILOG_AEXT};
+	int			flags = XFS_ILOG_CORE;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_STAGING);
+	ASSERT(whichfork != XFS_COW_FORK);
+
+	/*
+	 * Free any resources hanging off the real fork, then shallow-copy the
+	 * staging fork's contents into the real fork to transfer everything
+	 * we just built.
+	 */
+	ifp = xfs_ifork_ptr(cur->bc_ino.ip, whichfork);
+	xfs_idestroy_fork(ifp);
+	memcpy(ifp, ifake->if_fork, sizeof(struct xfs_ifork));
+
+	switch (ifp->if_format) {
+	case XFS_DINODE_FMT_EXTENTS:
+		flags |= extflag[whichfork];
+		break;
+	case XFS_DINODE_FMT_BTREE:
+		flags |= brootflag[whichfork];
+		break;
+	default:
+		ASSERT(0);
+		break;
+	}
+	xfs_trans_log_inode(tp, cur->bc_ino.ip, flags);
+	xfs_btree_commit_ifakeroot(cur, tp, whichfork, &xfs_bmbt_ops);
+}
+
+/*
  * Calculate number of records in a bmap btree block.
  */
 int
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.h b/fs/xfs/libxfs/xfs_bmap_btree.h
index 3e7a40a83835..151b8491f60e 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.h
+++ b/fs/xfs/libxfs/xfs_bmap_btree.h
@@ -11,6 +11,7 @@ struct xfs_btree_block;
 struct xfs_mount;
 struct xfs_inode;
 struct xfs_trans;
+struct xbtree_ifakeroot;
 
 /*
  * Btree block header size depends on a superblock flag.
@@ -106,6 +107,10 @@ extern int xfs_bmbt_change_owner(struct xfs_trans *tp, struct xfs_inode *ip,
 
 extern struct xfs_btree_cur *xfs_bmbt_init_cursor(struct xfs_mount *,
 		struct xfs_trans *, struct xfs_inode *, int);
+struct xfs_btree_cur *xfs_bmbt_stage_cursor(struct xfs_mount *mp,
+		struct xfs_inode *ip, struct xbtree_ifakeroot *ifake);
+void xfs_bmbt_commit_staged_btree(struct xfs_btree_cur *cur,
+		struct xfs_trans *tp, int whichfork);
 
 extern unsigned long long xfs_bmbt_calc_size(struct xfs_mount *mp,
 		unsigned long long len);
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 6a6503ab0cd7..ea8d3659df20 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -1330,7 +1330,7 @@ xfs_btree_get_buf_block(
  * Read in the buffer at the given ptr and return the buffer and
  * the block pointer within the buffer.
  */
-STATIC int
+int
 xfs_btree_read_buf_block(
 	struct xfs_btree_cur		*cur,
 	const union xfs_btree_ptr	*ptr,
@@ -5212,3 +5212,29 @@ xfs_btree_destroy_cur_caches(void)
 	xfs_rmapbt_destroy_cur_cache();
 	xfs_refcountbt_destroy_cur_cache();
 }
+
+/* Move the btree cursor before the first record. */
+int
+xfs_btree_goto_left_edge(
+	struct xfs_btree_cur	*cur)
+{
+	int			stat = 0;
+	int			error;
+
+	memset(&cur->bc_rec, 0, sizeof(cur->bc_rec));
+	error = xfs_btree_lookup(cur, XFS_LOOKUP_LE, &stat);
+	if (error)
+		return error;
+	if (!stat)
+		return 0;
+
+	error = xfs_btree_decrement(cur, 0, &stat);
+	if (error)
+		return error;
+	if (stat != 0) {
+		ASSERT(0);
+		return -EFSCORRUPTED;
+	}
+
+	return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 4d68a58be160..d906324e25c8 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -700,6 +700,9 @@ void xfs_btree_set_ptr_null(struct xfs_btree_cur *cur,
 int xfs_btree_get_buf_block(struct xfs_btree_cur *cur,
 		const union xfs_btree_ptr *ptr, struct xfs_btree_block **block,
 		struct xfs_buf **bpp);
+int xfs_btree_read_buf_block(struct xfs_btree_cur *cur,
+		const union xfs_btree_ptr *ptr, int flags,
+		struct xfs_btree_block **block, struct xfs_buf **bpp);
 void xfs_btree_set_sibling(struct xfs_btree_cur *cur,
 		struct xfs_btree_block *block, const union xfs_btree_ptr *ptr,
 		int lr);
@@ -735,4 +738,6 @@ xfs_btree_alloc_cursor(
 int __init xfs_btree_init_cur_caches(void);
 void xfs_btree_destroy_cur_caches(void);
 
+int xfs_btree_goto_left_edge(struct xfs_btree_cur *cur);
+
 #endif	/* __XFS_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_btree_staging.c b/fs/xfs/libxfs/xfs_btree_staging.c
index dd75e208b543..e276eba87cb1 100644
--- a/fs/xfs/libxfs/xfs_btree_staging.c
+++ b/fs/xfs/libxfs/xfs_btree_staging.c
@@ -333,20 +333,41 @@ xfs_btree_commit_ifakeroot(
 /*
  * Put a btree block that we're loading onto the ordered list and release it.
  * The btree blocks will be written to disk when bulk loading is finished.
+ * If we reach the dirty buffer threshold, flush them to disk before
+ * continuing.
  */
-static void
+static int
 xfs_btree_bload_drop_buf(
-	struct list_head	*buffers_list,
-	struct xfs_buf		**bpp)
+	struct xfs_btree_bload		*bbl,
+	struct list_head		*buffers_list,
+	struct xfs_buf			**bpp)
 {
-	if (*bpp == NULL)
-		return;
+	struct xfs_buf			*bp = *bpp;
+	int				error;
+
+	if (!bp)
+		return 0;
 
-	if (!xfs_buf_delwri_queue(*bpp, buffers_list))
-		ASSERT(0);
+	/*
+	 * Mark this buffer XBF_DONE (i.e. uptodate) so that a subsequent
+	 * xfs_buf_read will not pointlessly reread the contents from the disk.
+	 */
+	bp->b_flags |= XBF_DONE;
 
-	xfs_buf_relse(*bpp);
+	xfs_buf_delwri_queue_here(bp, buffers_list);
+	xfs_buf_relse(bp);
 	*bpp = NULL;
+	bbl->nr_dirty++;
+
+	if (!bbl->max_dirty || bbl->nr_dirty < bbl->max_dirty)
+		return 0;
+
+	error = xfs_buf_delwri_submit(buffers_list);
+	if (error)
+		return error;
+
+	bbl->nr_dirty = 0;
+	return 0;
 }
 
 /*
@@ -384,7 +405,7 @@ xfs_btree_bload_prep_block(
 		ASSERT(*bpp == NULL);
 
 		/* Allocate a new incore btree root block. */
-		new_size = bbl->iroot_size(cur, nr_this_block, priv);
+		new_size = bbl->iroot_size(cur, level, nr_this_block, priv);
 		ifp->if_broot = kmem_zalloc(new_size, 0);
 		ifp->if_broot_bytes = (int)new_size;
 
@@ -418,7 +439,10 @@ xfs_btree_bload_prep_block(
 	 */
 	if (*blockp)
 		xfs_btree_set_sibling(cur, *blockp, &new_ptr, XFS_BB_RIGHTSIB);
-	xfs_btree_bload_drop_buf(buffers_list, bpp);
+
+	ret = xfs_btree_bload_drop_buf(bbl, buffers_list, bpp);
+	if (ret)
+		return ret;
 
 	/* Initialize the new btree block. */
 	xfs_btree_init_block_cur(cur, new_bp, level, nr_this_block);
@@ -436,22 +460,19 @@ STATIC int
 xfs_btree_bload_leaf(
 	struct xfs_btree_cur		*cur,
 	unsigned int			recs_this_block,
-	xfs_btree_bload_get_record_fn	get_record,
+	xfs_btree_bload_get_records_fn	get_records,
 	struct xfs_btree_block		*block,
 	void				*priv)
 {
-	unsigned int			j;
+	unsigned int			j = 1;
 	int				ret;
 
 	/* Fill the leaf block with records. */
-	for (j = 1; j <= recs_this_block; j++) {
-		union xfs_btree_rec	*block_rec;
-
-		ret = get_record(cur, priv);
-		if (ret)
+	while (j <= recs_this_block) {
+		ret = get_records(cur, j, block, recs_this_block - j + 1, priv);
+		if (ret < 0)
 			return ret;
-		block_rec = xfs_btree_rec_addr(cur, j, block);
-		cur->bc_ops->init_rec_from_cur(cur, block_rec);
+		j += ret;
 	}
 
 	return 0;
@@ -485,7 +506,12 @@ xfs_btree_bload_node(
 
 		ASSERT(!xfs_btree_ptr_is_null(cur, child_ptr));
 
-		ret = xfs_btree_get_buf_block(cur, child_ptr, &child_block,
+		/*
+		 * Read the lower-level block in case the buffer for it has
+		 * been reclaimed.  LRU refs will be set on the block, which is
+		 * desirable if the new btree commits.
+		 */
+		ret = xfs_btree_read_buf_block(cur, child_ptr, 0, &child_block,
 				&child_bp);
 		if (ret)
 			return ret;
@@ -570,7 +596,14 @@ xfs_btree_bload_level_geometry(
 	unsigned int		desired_npb;
 	unsigned int		maxnr;
 
-	maxnr = cur->bc_ops->get_maxrecs(cur, level);
+	/*
+	 * Compute the absolute maximum number of records that we can store in
+	 * the ondisk block or inode root.
+	 */
+	if (cur->bc_ops->get_dmaxrecs)
+		maxnr = cur->bc_ops->get_dmaxrecs(cur, level);
+	else
+		maxnr = cur->bc_ops->get_maxrecs(cur, level);
 
 	/*
 	 * Compute the number of blocks we need to fill each block with the
@@ -764,6 +797,7 @@ xfs_btree_bload(
 	cur->bc_nlevels = bbl->btree_height;
 	xfs_btree_set_ptr_null(cur, &child_ptr);
 	xfs_btree_set_ptr_null(cur, &ptr);
+	bbl->nr_dirty = 0;
 
 	xfs_btree_bload_level_geometry(cur, bbl, level, nr_this_level,
 			&avg_per_block, &blocks, &blocks_with_extra);
@@ -789,7 +823,7 @@ xfs_btree_bload(
 		trace_xfs_btree_bload_block(cur, level, i, blocks, &ptr,
 				nr_this_block);
 
-		ret = xfs_btree_bload_leaf(cur, nr_this_block, bbl->get_record,
+		ret = xfs_btree_bload_leaf(cur, nr_this_block, bbl->get_records,
 				block, priv);
 		if (ret)
 			goto out;
@@ -802,7 +836,10 @@ xfs_btree_bload(
 			xfs_btree_copy_ptrs(cur, &child_ptr, &ptr, 1);
 	}
 	total_blocks += blocks;
-	xfs_btree_bload_drop_buf(&buffers_list, &bp);
+
+	ret = xfs_btree_bload_drop_buf(bbl, &buffers_list, &bp);
+	if (ret)
+		goto out;
 
 	/* Populate the internal btree nodes. */
 	for (level = 1; level < cur->bc_nlevels; level++) {
@@ -844,7 +881,11 @@ xfs_btree_bload(
 				xfs_btree_copy_ptrs(cur, &first_ptr, &ptr, 1);
 		}
 		total_blocks += blocks;
-		xfs_btree_bload_drop_buf(&buffers_list, &bp);
+
+		ret = xfs_btree_bload_drop_buf(bbl, &buffers_list, &bp);
+		if (ret)
+			goto out;
+
 		xfs_btree_copy_ptrs(cur, &child_ptr, &first_ptr, 1);
 	}
 
diff --git a/fs/xfs/libxfs/xfs_btree_staging.h b/fs/xfs/libxfs/xfs_btree_staging.h
index f0d2976050ae..055ea43b1e18 100644
--- a/fs/xfs/libxfs/xfs_btree_staging.h
+++ b/fs/xfs/libxfs/xfs_btree_staging.h
@@ -37,12 +37,6 @@ struct xbtree_ifakeroot {
 
 	/* Number of bytes available for this fork in the inode. */
 	unsigned int		if_fork_size;
-
-	/* Fork format. */
-	unsigned int		if_format;
-
-	/* Number of records. */
-	unsigned int		if_extents;
 };
 
 /* Cursor interactions with fake roots for inode-rooted btrees. */
@@ -53,19 +47,24 @@ void xfs_btree_commit_ifakeroot(struct xfs_btree_cur *cur, struct xfs_trans *tp,
 		int whichfork, const struct xfs_btree_ops *ops);
 
 /* Bulk loading of staged btrees. */
-typedef int (*xfs_btree_bload_get_record_fn)(struct xfs_btree_cur *cur, void *priv);
+typedef int (*xfs_btree_bload_get_records_fn)(struct xfs_btree_cur *cur,
+		unsigned int idx, struct xfs_btree_block *block,
+		unsigned int nr_wanted, void *priv);
 typedef int (*xfs_btree_bload_claim_block_fn)(struct xfs_btree_cur *cur,
 		union xfs_btree_ptr *ptr, void *priv);
 typedef size_t (*xfs_btree_bload_iroot_size_fn)(struct xfs_btree_cur *cur,
-		unsigned int nr_this_level, void *priv);
+		unsigned int level, unsigned int nr_this_level, void *priv);
 
 struct xfs_btree_bload {
 	/*
-	 * This function will be called nr_records times to load records into
-	 * the btree.  The function does this by setting the cursor's bc_rec
-	 * field in in-core format.  Records must be returned in sort order.
+	 * This function will be called to load @nr_wanted records into the
+	 * btree.  The implementation does this by setting the cursor's bc_rec
+	 * field in in-core format and using init_rec_from_cur to set the
+	 * records in the btree block.  Records must be returned in sort order.
+	 * The function must return the number of records loaded or the usual
+	 * negative errno.
 	 */
-	xfs_btree_bload_get_record_fn	get_record;
+	xfs_btree_bload_get_records_fn	get_records;
 
 	/*
 	 * This function will be called nr_blocks times to obtain a pointer
@@ -113,6 +112,16 @@ struct xfs_btree_bload {
 	 * height of the new btree.
 	 */
 	unsigned int			btree_height;
+
+	/*
+	 * Flush the new btree block buffer list to disk after this many blocks
+	 * have been formatted.  Zero prohibits writing any buffers until all
+	 * blocks have been formatted.
+	 */
+	uint16_t			max_dirty;
+
+	/* Number of dirty buffers. */
+	uint16_t			nr_dirty;
 };
 
 int xfs_btree_bload_compute_geometry(struct xfs_btree_cur *cur,
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index e576560b46e9..5457188bb4de 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -421,6 +421,25 @@ xfs_da3_node_read_mapped(
 	return xfs_da3_node_set_type(tp, *bpp);
 }
 
+/*
+ * Copy src directory/attr leaf/node buffer to the dst.
+ * For v5 file systems make sure the right blkno is stamped in.
+ */
+void
+xfs_da_buf_copy(
+	struct xfs_buf *dst,
+	struct xfs_buf *src,
+	size_t size)
+{
+	struct xfs_da3_blkinfo *da3 = dst->b_addr;
+
+	memcpy(dst->b_addr, src->b_addr, size);
+	dst->b_ops = src->b_ops;
+	xfs_trans_buf_copy_type(dst, src);
+	if (xfs_has_crc(dst->b_mount))
+		da3->blkno = cpu_to_be64(xfs_buf_daddr(dst));
+}
+
 /*========================================================================
  * Routines used for growing the Btree.
  *========================================================================*/
@@ -690,12 +709,6 @@ xfs_da3_root_split(
 		btree = icnodehdr.btree;
 		size = (int)((char *)&btree[icnodehdr.count] - (char *)oldroot);
 		level = icnodehdr.level;
-
-		/*
-		 * we are about to copy oldroot to bp, so set up the type
-		 * of bp while we know exactly what it will be.
-		 */
-		xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DA_NODE_BUF);
 	} else {
 		struct xfs_dir3_icleaf_hdr leafhdr;
 
@@ -707,31 +720,17 @@ xfs_da3_root_split(
 		size = (int)((char *)&leafhdr.ents[leafhdr.count] -
 			(char *)leaf);
 		level = 0;
-
-		/*
-		 * we are about to copy oldroot to bp, so set up the type
-		 * of bp while we know exactly what it will be.
-		 */
-		xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DIR_LEAFN_BUF);
 	}
 
 	/*
-	 * we can copy most of the information in the node from one block to
-	 * another, but for CRC enabled headers we have to make sure that the
-	 * block specific identifiers are kept intact. We update the buffer
-	 * directly for this.
+	 * Copy old root to new buffer and log it.
 	 */
-	memcpy(node, oldroot, size);
-	if (oldroot->hdr.info.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC) ||
-	    oldroot->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC)) {
-		struct xfs_da3_intnode *node3 = (struct xfs_da3_intnode *)node;
-
-		node3->hdr.info.blkno = cpu_to_be64(xfs_buf_daddr(bp));
-	}
+	xfs_da_buf_copy(bp, blk1->bp, size);
 	xfs_trans_log_buf(tp, bp, 0, size - 1);
 
-	bp->b_ops = blk1->bp->b_ops;
-	xfs_trans_buf_copy_type(bp, blk1->bp);
+	/*
+	 * Update blk1 to point to new buffer.
+	 */
 	blk1->bp = bp;
 	blk1->blkno = blkno;
 
@@ -1220,21 +1219,14 @@ xfs_da3_root_join(
 	xfs_da_blkinfo_onlychild_validate(bp->b_addr, oldroothdr.level);
 
 	/*
-	 * This could be copying a leaf back into the root block in the case of
-	 * there only being a single leaf block left in the tree. Hence we have
-	 * to update the b_ops pointer as well to match the buffer type change
-	 * that could occur. For dir3 blocks we also need to update the block
-	 * number in the buffer header.
+	 * Copy child to root buffer and log it.
 	 */
-	memcpy(root_blk->bp->b_addr, bp->b_addr, args->geo->blksize);
-	root_blk->bp->b_ops = bp->b_ops;
-	xfs_trans_buf_copy_type(root_blk->bp, bp);
-	if (oldroothdr.magic == XFS_DA3_NODE_MAGIC) {
-		struct xfs_da3_blkinfo *da3 = root_blk->bp->b_addr;
-		da3->blkno = cpu_to_be64(xfs_buf_daddr(root_blk->bp));
-	}
+	xfs_da_buf_copy(root_blk->bp, bp, args->geo->blksize);
 	xfs_trans_log_buf(args->trans, root_blk->bp, 0,
 			  args->geo->blksize - 1);
+	/*
+	 * Now we can drop the child buffer.
+	 */
 	error = xfs_da_shrink_inode(args, child, bp);
 	return error;
 }
@@ -2317,9 +2309,10 @@ xfs_da3_swap_lastblock(
 	/*
 	 * Copy the last block into the dead buffer and log it.
 	 */
-	memcpy(dead_buf->b_addr, last_buf->b_addr, args->geo->blksize);
+	xfs_da_buf_copy(dead_buf, last_buf, args->geo->blksize);
 	xfs_trans_log_buf(tp, dead_buf, 0, args->geo->blksize - 1);
 	dead_info = dead_buf->b_addr;
+
 	/*
 	 * Get values from the moved block.
 	 */
diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h
index ffa3df5b2893..706baf36e175 100644
--- a/fs/xfs/libxfs/xfs_da_btree.h
+++ b/fs/xfs/libxfs/xfs_da_btree.h
@@ -219,6 +219,8 @@ int	xfs_da_reada_buf(struct xfs_inode *dp, xfs_dablk_t bno,
 		const struct xfs_buf_ops *ops);
 int	xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
 					  struct xfs_buf *dead_buf);
+void	xfs_da_buf_copy(struct xfs_buf *dst, struct xfs_buf *src,
+			size_t size);
 
 uint xfs_da_hashname(const uint8_t *name_string, int name_length);
 enum xfs_dacmp xfs_da_compname(struct xfs_da_args *args,
diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h
index f9015f88eca7..24f9d1461f9a 100644
--- a/fs/xfs/libxfs/xfs_da_format.h
+++ b/fs/xfs/libxfs/xfs_da_format.h
@@ -578,20 +578,25 @@ xfs_dir2_block_leaf_p(struct xfs_dir2_block_tail *btp)
 #define XFS_ATTR_LEAF_MAPSIZE	3	/* how many freespace slots */
 
 /*
- * Entries are packed toward the top as tight as possible.
- */
-struct xfs_attr_shortform {
-	struct xfs_attr_sf_hdr {	/* constant-structure header block */
-		__be16	totsize;	/* total bytes in shortform list */
-		__u8	count;	/* count of active entries */
-		__u8	padding;
-	} hdr;
-	struct xfs_attr_sf_entry {
-		uint8_t namelen;	/* actual length of name (no NULL) */
-		uint8_t valuelen;	/* actual length of value (no NULL) */
-		uint8_t flags;	/* flags bits (see xfs_attr_leaf.h) */
-		uint8_t nameval[];	/* name & value bytes concatenated */
-	} list[];			/* variable sized array */
+ * Attribute storage when stored inside the inode.
+ *
+ * Small attribute lists are packed as tightly as possible so as to fit into the
+ * literal area of the inode.
+ *
+ * These "shortform" attribute forks consist of a single xfs_attr_sf_hdr header
+ * followed by zero or more xfs_attr_sf_entry structures.
+ */
+struct xfs_attr_sf_hdr {	/* constant-structure header block */
+	__be16	totsize;	/* total bytes in shortform list */
+	__u8	count;		/* count of active entries */
+	__u8	padding;
+};
+
+struct xfs_attr_sf_entry {
+	__u8	namelen;	/* actual length of name (no NULL) */
+	__u8	valuelen;	/* actual length of value (no NULL) */
+	__u8	flags;		/* flags bits (XFS_ATTR_*) */
+	__u8	nameval[];	/* name & value bytes concatenated */
 };
 
 typedef struct xfs_attr_leaf_map {	/* RLE map of free bytes */
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index bcfb6a4203cd..66a17910d021 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -26,6 +26,7 @@
 #include "xfs_da_format.h"
 #include "xfs_da_btree.h"
 #include "xfs_attr.h"
+#include "xfs_trans_priv.h"
 
 static struct kmem_cache	*xfs_defer_pending_cache;
 
@@ -181,16 +182,89 @@ static struct kmem_cache	*xfs_defer_pending_cache;
  * Note that the continuation requested between t2 and t3 is likely to
  * reoccur.
  */
+STATIC struct xfs_log_item *
+xfs_defer_barrier_create_intent(
+	struct xfs_trans		*tp,
+	struct list_head		*items,
+	unsigned int			count,
+	bool				sort)
+{
+	return NULL;
+}
+
+STATIC void
+xfs_defer_barrier_abort_intent(
+	struct xfs_log_item		*intent)
+{
+	/* empty */
+}
 
-static const struct xfs_defer_op_type *defer_op_types[] = {
-	[XFS_DEFER_OPS_TYPE_BMAP]	= &xfs_bmap_update_defer_type,
-	[XFS_DEFER_OPS_TYPE_REFCOUNT]	= &xfs_refcount_update_defer_type,
-	[XFS_DEFER_OPS_TYPE_RMAP]	= &xfs_rmap_update_defer_type,
-	[XFS_DEFER_OPS_TYPE_FREE]	= &xfs_extent_free_defer_type,
-	[XFS_DEFER_OPS_TYPE_AGFL_FREE]	= &xfs_agfl_free_defer_type,
-	[XFS_DEFER_OPS_TYPE_ATTR]	= &xfs_attr_defer_type,
+STATIC struct xfs_log_item *
+xfs_defer_barrier_create_done(
+	struct xfs_trans		*tp,
+	struct xfs_log_item		*intent,
+	unsigned int			count)
+{
+	return NULL;
+}
+
+STATIC int
+xfs_defer_barrier_finish_item(
+	struct xfs_trans		*tp,
+	struct xfs_log_item		*done,
+	struct list_head		*item,
+	struct xfs_btree_cur		**state)
+{
+	ASSERT(0);
+	return -EFSCORRUPTED;
+}
+
+STATIC void
+xfs_defer_barrier_cancel_item(
+	struct list_head		*item)
+{
+	ASSERT(0);
+}
+
+static const struct xfs_defer_op_type xfs_barrier_defer_type = {
+	.max_items	= 1,
+	.create_intent	= xfs_defer_barrier_create_intent,
+	.abort_intent	= xfs_defer_barrier_abort_intent,
+	.create_done	= xfs_defer_barrier_create_done,
+	.finish_item	= xfs_defer_barrier_finish_item,
+	.cancel_item	= xfs_defer_barrier_cancel_item,
 };
 
+/* Create a log intent done item for a log intent item. */
+static inline void
+xfs_defer_create_done(
+	struct xfs_trans		*tp,
+	struct xfs_defer_pending	*dfp)
+{
+	struct xfs_log_item		*lip;
+
+	/* If there is no log intent item, there can be no log done item. */
+	if (!dfp->dfp_intent)
+		return;
+
+	/*
+	 * Mark the transaction dirty, even on error. This ensures the
+	 * transaction is aborted, which:
+	 *
+	 * 1.) releases the log intent item and frees the log done item
+	 * 2.) shuts down the filesystem
+	 */
+	tp->t_flags |= XFS_TRANS_DIRTY;
+	lip = dfp->dfp_ops->create_done(tp, dfp->dfp_intent, dfp->dfp_count);
+	if (!lip)
+		return;
+
+	tp->t_flags |= XFS_TRANS_HAS_INTENT_DONE;
+	xfs_trans_add_item(tp, lip);
+	set_bit(XFS_LI_DIRTY, &lip->li_flags);
+	dfp->dfp_done = lip;
+}
+
 /*
  * Ensure there's a log intent item associated with this deferred work item if
  * the operation must be restarted on crash.  Returns 1 if there's a log item;
@@ -202,18 +276,21 @@ xfs_defer_create_intent(
 	struct xfs_defer_pending	*dfp,
 	bool				sort)
 {
-	const struct xfs_defer_op_type	*ops = defer_op_types[dfp->dfp_type];
 	struct xfs_log_item		*lip;
 
 	if (dfp->dfp_intent)
 		return 1;
 
-	lip = ops->create_intent(tp, &dfp->dfp_work, dfp->dfp_count, sort);
+	lip = dfp->dfp_ops->create_intent(tp, &dfp->dfp_work, dfp->dfp_count,
+			sort);
 	if (!lip)
 		return 0;
 	if (IS_ERR(lip))
 		return PTR_ERR(lip);
 
+	tp->t_flags |= XFS_TRANS_DIRTY;
+	xfs_trans_add_item(tp, lip);
+	set_bit(XFS_LI_DIRTY, &lip->li_flags);
 	dfp->dfp_intent = lip;
 	return 1;
 }
@@ -245,26 +322,60 @@ xfs_defer_create_intents(
 	return ret;
 }
 
+static inline void
+xfs_defer_pending_abort(
+	struct xfs_mount		*mp,
+	struct xfs_defer_pending	*dfp)
+{
+	trace_xfs_defer_pending_abort(mp, dfp);
+
+	if (dfp->dfp_intent && !dfp->dfp_done) {
+		dfp->dfp_ops->abort_intent(dfp->dfp_intent);
+		dfp->dfp_intent = NULL;
+	}
+}
+
+static inline void
+xfs_defer_pending_cancel_work(
+	struct xfs_mount		*mp,
+	struct xfs_defer_pending	*dfp)
+{
+	struct list_head		*pwi;
+	struct list_head		*n;
+
+	trace_xfs_defer_cancel_list(mp, dfp);
+
+	list_del(&dfp->dfp_list);
+	list_for_each_safe(pwi, n, &dfp->dfp_work) {
+		list_del(pwi);
+		dfp->dfp_count--;
+		trace_xfs_defer_cancel_item(mp, dfp, pwi);
+		dfp->dfp_ops->cancel_item(pwi);
+	}
+	ASSERT(dfp->dfp_count == 0);
+	kmem_cache_free(xfs_defer_pending_cache, dfp);
+}
+
+STATIC void
+xfs_defer_pending_abort_list(
+	struct xfs_mount		*mp,
+	struct list_head		*dop_list)
+{
+	struct xfs_defer_pending	*dfp;
+
+	/* Abort intent items that don't have a done item. */
+	list_for_each_entry(dfp, dop_list, dfp_list)
+		xfs_defer_pending_abort(mp, dfp);
+}
+
 /* Abort all the intents that were committed. */
 STATIC void
 xfs_defer_trans_abort(
 	struct xfs_trans		*tp,
 	struct list_head		*dop_pending)
 {
-	struct xfs_defer_pending	*dfp;
-	const struct xfs_defer_op_type	*ops;
-
 	trace_xfs_defer_trans_abort(tp, _RET_IP_);
-
-	/* Abort intent items that don't have a done item. */
-	list_for_each_entry(dfp, dop_pending, dfp_list) {
-		ops = defer_op_types[dfp->dfp_type];
-		trace_xfs_defer_pending_abort(tp->t_mountp, dfp);
-		if (dfp->dfp_intent && !dfp->dfp_done) {
-			ops->abort_intent(dfp->dfp_intent);
-			dfp->dfp_intent = NULL;
-		}
-	}
+	xfs_defer_pending_abort_list(tp->t_mountp, dop_pending);
 }
 
 /*
@@ -382,27 +493,31 @@ xfs_defer_cancel_list(
 {
 	struct xfs_defer_pending	*dfp;
 	struct xfs_defer_pending	*pli;
-	struct list_head		*pwi;
-	struct list_head		*n;
-	const struct xfs_defer_op_type	*ops;
 
 	/*
 	 * Free the pending items.  Caller should already have arranged
 	 * for the intent items to be released.
 	 */
-	list_for_each_entry_safe(dfp, pli, dop_list, dfp_list) {
-		ops = defer_op_types[dfp->dfp_type];
-		trace_xfs_defer_cancel_list(mp, dfp);
-		list_del(&dfp->dfp_list);
-		list_for_each_safe(pwi, n, &dfp->dfp_work) {
-			list_del(pwi);
-			dfp->dfp_count--;
-			trace_xfs_defer_cancel_item(mp, dfp, pwi);
-			ops->cancel_item(pwi);
-		}
-		ASSERT(dfp->dfp_count == 0);
-		kmem_cache_free(xfs_defer_pending_cache, dfp);
+	list_for_each_entry_safe(dfp, pli, dop_list, dfp_list)
+		xfs_defer_pending_cancel_work(mp, dfp);
+}
+
+static inline void
+xfs_defer_relog_intent(
+	struct xfs_trans		*tp,
+	struct xfs_defer_pending	*dfp)
+{
+	struct xfs_log_item		*lip;
+
+	xfs_defer_create_done(tp, dfp);
+
+	lip = dfp->dfp_ops->relog_intent(tp, dfp->dfp_intent, dfp->dfp_done);
+	if (lip) {
+		xfs_trans_add_item(tp, lip);
+		set_bit(XFS_LI_DIRTY, &lip->li_flags);
 	}
+	dfp->dfp_done = NULL;
+	dfp->dfp_intent = lip;
 }
 
 /*
@@ -410,7 +525,7 @@ xfs_defer_cancel_list(
  * done item to release the intent item; and then log a new intent item.
  * The caller should provide a fresh transaction and roll it after we're done.
  */
-static int
+static void
 xfs_defer_relog(
 	struct xfs_trans		**tpp,
 	struct list_head		*dfops)
@@ -449,31 +564,28 @@ xfs_defer_relog(
 
 		trace_xfs_defer_relog_intent((*tpp)->t_mountp, dfp);
 		XFS_STATS_INC((*tpp)->t_mountp, defer_relog);
-		dfp->dfp_intent = xfs_trans_item_relog(dfp->dfp_intent, *tpp);
-	}
 
-	if ((*tpp)->t_flags & XFS_TRANS_DIRTY)
-		return xfs_defer_trans_roll(tpp);
-	return 0;
+		xfs_defer_relog_intent(*tpp, dfp);
+	}
 }
 
 /*
  * Log an intent-done item for the first pending intent, and finish the work
  * items.
  */
-static int
+int
 xfs_defer_finish_one(
 	struct xfs_trans		*tp,
 	struct xfs_defer_pending	*dfp)
 {
-	const struct xfs_defer_op_type	*ops = defer_op_types[dfp->dfp_type];
+	const struct xfs_defer_op_type	*ops = dfp->dfp_ops;
 	struct xfs_btree_cur		*state = NULL;
 	struct list_head		*li, *n;
 	int				error;
 
 	trace_xfs_defer_pending_finish(tp->t_mountp, dfp);
 
-	dfp->dfp_done = ops->create_done(tp, dfp->dfp_intent, dfp->dfp_count);
+	xfs_defer_create_done(tp, dfp);
 	list_for_each_safe(li, n, &dfp->dfp_work) {
 		list_del(li);
 		dfp->dfp_count--;
@@ -510,6 +622,24 @@ out:
 	return error;
 }
 
+/* Move all paused deferred work from @tp to @paused_list. */
+static void
+xfs_defer_isolate_paused(
+	struct xfs_trans		*tp,
+	struct list_head		*paused_list)
+{
+	struct xfs_defer_pending	*dfp;
+	struct xfs_defer_pending	*pli;
+
+	list_for_each_entry_safe(dfp, pli, &tp->t_dfops, dfp_list) {
+		if (!(dfp->dfp_flags & XFS_DEFER_PAUSED))
+			continue;
+
+		list_move_tail(&dfp->dfp_list, paused_list);
+		trace_xfs_defer_isolate_paused(tp->t_mountp, dfp);
+	}
+}
+
 /*
  * Finish all the pending work.  This involves logging intent items for
  * any work items that wandered in since the last transaction roll (if
@@ -525,6 +655,7 @@ xfs_defer_finish_noroll(
 	struct xfs_defer_pending	*dfp = NULL;
 	int				error = 0;
 	LIST_HEAD(dop_pending);
+	LIST_HEAD(dop_paused);
 
 	ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
 
@@ -543,6 +674,8 @@ xfs_defer_finish_noroll(
 		 */
 		int has_intents = xfs_defer_create_intents(*tp);
 
+		xfs_defer_isolate_paused(*tp, &dop_paused);
+
 		list_splice_init(&(*tp)->t_dfops, &dop_pending);
 
 		if (has_intents < 0) {
@@ -555,22 +688,33 @@ xfs_defer_finish_noroll(
 				goto out_shutdown;
 
 			/* Relog intent items to keep the log moving. */
-			error = xfs_defer_relog(tp, &dop_pending);
-			if (error)
-				goto out_shutdown;
+			xfs_defer_relog(tp, &dop_pending);
+			xfs_defer_relog(tp, &dop_paused);
+
+			if ((*tp)->t_flags & XFS_TRANS_DIRTY) {
+				error = xfs_defer_trans_roll(tp);
+				if (error)
+					goto out_shutdown;
+			}
 		}
 
-		dfp = list_first_entry(&dop_pending, struct xfs_defer_pending,
-				       dfp_list);
+		dfp = list_first_entry_or_null(&dop_pending,
+				struct xfs_defer_pending, dfp_list);
+		if (!dfp)
+			break;
 		error = xfs_defer_finish_one(*tp, dfp);
 		if (error && error != -EAGAIN)
 			goto out_shutdown;
 	}
 
+	/* Requeue the paused items in the outgoing transaction. */
+	list_splice_tail_init(&dop_paused, &(*tp)->t_dfops);
+
 	trace_xfs_defer_finish_done(*tp, _RET_IP_);
 	return 0;
 
 out_shutdown:
+	list_splice_tail_init(&dop_paused, &dop_pending);
 	xfs_defer_trans_abort(*tp, &dop_pending);
 	xfs_force_shutdown((*tp)->t_mountp, SHUTDOWN_CORRUPT_INCORE);
 	trace_xfs_defer_finish_error(*tp, error);
@@ -583,6 +727,9 @@ int
 xfs_defer_finish(
 	struct xfs_trans	**tp)
 {
+#ifdef DEBUG
+	struct xfs_defer_pending *dfp;
+#endif
 	int			error;
 
 	/*
@@ -602,7 +749,10 @@ xfs_defer_finish(
 	}
 
 	/* Reset LOWMODE now that we've finished all the dfops. */
-	ASSERT(list_empty(&(*tp)->t_dfops));
+#ifdef DEBUG
+	list_for_each_entry(dfp, &(*tp)->t_dfops, dfp_list)
+		ASSERT(dfp->dfp_flags & XFS_DEFER_PAUSED);
+#endif
 	(*tp)->t_flags &= ~XFS_TRANS_LOWMODE;
 	return 0;
 }
@@ -614,48 +764,165 @@ xfs_defer_cancel(
 	struct xfs_mount	*mp = tp->t_mountp;
 
 	trace_xfs_defer_cancel(tp, _RET_IP_);
+	xfs_defer_trans_abort(tp, &tp->t_dfops);
 	xfs_defer_cancel_list(mp, &tp->t_dfops);
 }
 
+/*
+ * Return the last pending work item attached to this transaction if it matches
+ * the deferred op type.
+ */
+static inline struct xfs_defer_pending *
+xfs_defer_find_last(
+	struct xfs_trans		*tp,
+	const struct xfs_defer_op_type	*ops)
+{
+	struct xfs_defer_pending	*dfp = NULL;
+
+	/* No dfops at all? */
+	if (list_empty(&tp->t_dfops))
+		return NULL;
+
+	dfp = list_last_entry(&tp->t_dfops, struct xfs_defer_pending,
+			dfp_list);
+
+	/* Wrong type? */
+	if (dfp->dfp_ops != ops)
+		return NULL;
+	return dfp;
+}
+
+/*
+ * Decide if we can add a deferred work item to the last dfops item attached
+ * to the transaction.
+ */
+static inline bool
+xfs_defer_can_append(
+	struct xfs_defer_pending	*dfp,
+	const struct xfs_defer_op_type	*ops)
+{
+	/* Already logged? */
+	if (dfp->dfp_intent)
+		return false;
+
+	/* Paused items cannot absorb more work */
+	if (dfp->dfp_flags & XFS_DEFER_PAUSED)
+		return NULL;
+
+	/* Already full? */
+	if (ops->max_items && dfp->dfp_count >= ops->max_items)
+		return false;
+
+	return true;
+}
+
+/* Create a new pending item at the end of the transaction list. */
+static inline struct xfs_defer_pending *
+xfs_defer_alloc(
+	struct xfs_trans		*tp,
+	const struct xfs_defer_op_type	*ops)
+{
+	struct xfs_defer_pending	*dfp;
+
+	dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
+			GFP_NOFS | __GFP_NOFAIL);
+	dfp->dfp_ops = ops;
+	INIT_LIST_HEAD(&dfp->dfp_work);
+	list_add_tail(&dfp->dfp_list, &tp->t_dfops);
+
+	return dfp;
+}
+
 /* Add an item for later deferred processing. */
-void
+struct xfs_defer_pending *
 xfs_defer_add(
 	struct xfs_trans		*tp,
-	enum xfs_defer_ops_type		type,
-	struct list_head		*li)
+	struct list_head		*li,
+	const struct xfs_defer_op_type	*ops)
 {
 	struct xfs_defer_pending	*dfp = NULL;
-	const struct xfs_defer_op_type	*ops = defer_op_types[type];
 
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
-	BUILD_BUG_ON(ARRAY_SIZE(defer_op_types) != XFS_DEFER_OPS_TYPE_MAX);
 
-	/*
-	 * Add the item to a pending item at the end of the intake list.
-	 * If the last pending item has the same type, reuse it.  Else,
-	 * create a new pending item at the end of the intake list.
-	 */
-	if (!list_empty(&tp->t_dfops)) {
-		dfp = list_last_entry(&tp->t_dfops,
-				struct xfs_defer_pending, dfp_list);
-		if (dfp->dfp_type != type ||
-		    (ops->max_items && dfp->dfp_count >= ops->max_items))
-			dfp = NULL;
-	}
-	if (!dfp) {
-		dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
-				GFP_NOFS | __GFP_NOFAIL);
-		dfp->dfp_type = type;
-		dfp->dfp_intent = NULL;
-		dfp->dfp_done = NULL;
-		dfp->dfp_count = 0;
-		INIT_LIST_HEAD(&dfp->dfp_work);
-		list_add_tail(&dfp->dfp_list, &tp->t_dfops);
-	}
+	dfp = xfs_defer_find_last(tp, ops);
+	if (!dfp || !xfs_defer_can_append(dfp, ops))
+		dfp = xfs_defer_alloc(tp, ops);
 
-	list_add_tail(li, &dfp->dfp_work);
+	xfs_defer_add_item(dfp, li);
 	trace_xfs_defer_add_item(tp->t_mountp, dfp, li);
-	dfp->dfp_count++;
+	return dfp;
+}
+
+/*
+ * Add a defer ops barrier to force two otherwise adjacent deferred work items
+ * to be tracked separately and have separate log items.
+ */
+void
+xfs_defer_add_barrier(
+	struct xfs_trans		*tp)
+{
+	struct xfs_defer_pending	*dfp;
+
+	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
+
+	/* If the last defer op added was a barrier, we're done. */
+	dfp = xfs_defer_find_last(tp, &xfs_barrier_defer_type);
+	if (dfp)
+		return;
+
+	xfs_defer_alloc(tp, &xfs_barrier_defer_type);
+
+	trace_xfs_defer_add_item(tp->t_mountp, dfp, NULL);
+}
+
+/*
+ * Create a pending deferred work item to replay the recovered intent item
+ * and add it to the list.
+ */
+void
+xfs_defer_start_recovery(
+	struct xfs_log_item		*lip,
+	struct list_head		*r_dfops,
+	const struct xfs_defer_op_type	*ops)
+{
+	struct xfs_defer_pending	*dfp;
+
+	dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
+			GFP_NOFS | __GFP_NOFAIL);
+	dfp->dfp_ops = ops;
+	dfp->dfp_intent = lip;
+	INIT_LIST_HEAD(&dfp->dfp_work);
+	list_add_tail(&dfp->dfp_list, r_dfops);
+}
+
+/*
+ * Cancel a deferred work item created to recover a log intent item.  @dfp
+ * will be freed after this function returns.
+ */
+void
+xfs_defer_cancel_recovery(
+	struct xfs_mount		*mp,
+	struct xfs_defer_pending	*dfp)
+{
+	xfs_defer_pending_abort(mp, dfp);
+	xfs_defer_pending_cancel_work(mp, dfp);
+}
+
+/* Replay the deferred work item created from a recovered log intent item. */
+int
+xfs_defer_finish_recovery(
+	struct xfs_mount		*mp,
+	struct xfs_defer_pending	*dfp,
+	struct list_head		*capture_list)
+{
+	const struct xfs_defer_op_type	*ops = dfp->dfp_ops;
+	int				error;
+
+	/* dfp is freed by recover_work and must not be accessed afterwards */
+	error = ops->recover_work(dfp, capture_list);
+	if (error)
+		trace_xlog_intent_recovery_failed(mp, ops, error);
+	return error;
 }
 
 /*
@@ -756,12 +1023,13 @@ xfs_defer_ops_capture(
 
 /* Release all resources that we used to capture deferred ops. */
 void
-xfs_defer_ops_capture_free(
+xfs_defer_ops_capture_abort(
 	struct xfs_mount		*mp,
 	struct xfs_defer_capture	*dfc)
 {
 	unsigned short			i;
 
+	xfs_defer_pending_abort_list(mp, &dfc->dfc_dfops);
 	xfs_defer_cancel_list(mp, &dfc->dfc_dfops);
 
 	for (i = 0; i < dfc->dfc_held.dr_bufs; i++)
@@ -802,7 +1070,7 @@ xfs_defer_ops_capture_and_commit(
 	/* Commit the transaction and add the capture structure to the list. */
 	error = xfs_trans_commit(tp);
 	if (error) {
-		xfs_defer_ops_capture_free(mp, dfc);
+		xfs_defer_ops_capture_abort(mp, dfc);
 		return error;
 	}
 
@@ -930,3 +1198,36 @@ xfs_defer_destroy_item_caches(void)
 	xfs_rmap_intent_destroy_cache();
 	xfs_defer_destroy_cache();
 }
+
+/*
+ * Mark a deferred work item so that it will be requeued indefinitely without
+ * being finished.  Caller must ensure there are no data dependencies on this
+ * work item in the meantime.
+ */
+void
+xfs_defer_item_pause(
+	struct xfs_trans		*tp,
+	struct xfs_defer_pending	*dfp)
+{
+	ASSERT(!(dfp->dfp_flags & XFS_DEFER_PAUSED));
+
+	dfp->dfp_flags |= XFS_DEFER_PAUSED;
+
+	trace_xfs_defer_item_pause(tp->t_mountp, dfp);
+}
+
+/*
+ * Release a paused deferred work item so that it will be finished during the
+ * next transaction roll.
+ */
+void
+xfs_defer_item_unpause(
+	struct xfs_trans		*tp,
+	struct xfs_defer_pending	*dfp)
+{
+	ASSERT(dfp->dfp_flags & XFS_DEFER_PAUSED);
+
+	dfp->dfp_flags &= ~XFS_DEFER_PAUSED;
+
+	trace_xfs_defer_item_unpause(tp->t_mountp, dfp);
+}
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 114a3a4930a3..18a9fb92dde8 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -11,19 +11,6 @@ struct xfs_defer_op_type;
 struct xfs_defer_capture;
 
 /*
- * Header for deferred operation list.
- */
-enum xfs_defer_ops_type {
-	XFS_DEFER_OPS_TYPE_BMAP,
-	XFS_DEFER_OPS_TYPE_REFCOUNT,
-	XFS_DEFER_OPS_TYPE_RMAP,
-	XFS_DEFER_OPS_TYPE_FREE,
-	XFS_DEFER_OPS_TYPE_AGFL_FREE,
-	XFS_DEFER_OPS_TYPE_ATTR,
-	XFS_DEFER_OPS_TYPE_MAX,
-};
-
-/*
  * Save a log intent item and a list of extents, so that we can replay
  * whatever action had to happen to the extent list and file the log done
  * item.
@@ -33,19 +20,35 @@ struct xfs_defer_pending {
 	struct list_head		dfp_work;	/* work items */
 	struct xfs_log_item		*dfp_intent;	/* log intent item */
 	struct xfs_log_item		*dfp_done;	/* log done item */
+	const struct xfs_defer_op_type	*dfp_ops;
 	unsigned int			dfp_count;	/* # extent items */
-	enum xfs_defer_ops_type		dfp_type;
+	unsigned int			dfp_flags;
 };
 
-void xfs_defer_add(struct xfs_trans *tp, enum xfs_defer_ops_type type,
-		struct list_head *h);
+/*
+ * Create a log intent item for this deferred item, but don't actually finish
+ * the work.  Caller must clear this before the final transaction commit.
+ */
+#define XFS_DEFER_PAUSED	(1U << 0)
+
+#define XFS_DEFER_PENDING_STRINGS \
+	{ XFS_DEFER_PAUSED,	"paused" }
+
+void xfs_defer_item_pause(struct xfs_trans *tp, struct xfs_defer_pending *dfp);
+void xfs_defer_item_unpause(struct xfs_trans *tp, struct xfs_defer_pending *dfp);
+
+struct xfs_defer_pending *xfs_defer_add(struct xfs_trans *tp, struct list_head *h,
+		const struct xfs_defer_op_type *ops);
 int xfs_defer_finish_noroll(struct xfs_trans **tp);
 int xfs_defer_finish(struct xfs_trans **tp);
+int xfs_defer_finish_one(struct xfs_trans *tp, struct xfs_defer_pending *dfp);
 void xfs_defer_cancel(struct xfs_trans *);
 void xfs_defer_move(struct xfs_trans *dtp, struct xfs_trans *stp);
 
 /* Description of a deferred type. */
 struct xfs_defer_op_type {
+	const char		*name;
+	unsigned int		max_items;
 	struct xfs_log_item *(*create_intent)(struct xfs_trans *tp,
 			struct list_head *items, unsigned int count, bool sort);
 	void (*abort_intent)(struct xfs_log_item *intent);
@@ -56,7 +59,11 @@ struct xfs_defer_op_type {
 	void (*finish_cleanup)(struct xfs_trans *tp,
 			struct xfs_btree_cur *state, int error);
 	void (*cancel_item)(struct list_head *item);
-	unsigned int		max_items;
+	int (*recover_work)(struct xfs_defer_pending *dfp,
+			    struct list_head *capture_list);
+	struct xfs_log_item *(*relog_intent)(struct xfs_trans *tp,
+			struct xfs_log_item *intent,
+			struct xfs_log_item *done_item);
 };
 
 extern const struct xfs_defer_op_type xfs_bmap_update_defer_type;
@@ -121,11 +128,29 @@ int xfs_defer_ops_capture_and_commit(struct xfs_trans *tp,
 		struct list_head *capture_list);
 void xfs_defer_ops_continue(struct xfs_defer_capture *d, struct xfs_trans *tp,
 		struct xfs_defer_resources *dres);
-void xfs_defer_ops_capture_free(struct xfs_mount *mp,
+void xfs_defer_ops_capture_abort(struct xfs_mount *mp,
 		struct xfs_defer_capture *d);
 void xfs_defer_resources_rele(struct xfs_defer_resources *dres);
 
+void xfs_defer_start_recovery(struct xfs_log_item *lip,
+		struct list_head *r_dfops, const struct xfs_defer_op_type *ops);
+void xfs_defer_cancel_recovery(struct xfs_mount *mp,
+		struct xfs_defer_pending *dfp);
+int xfs_defer_finish_recovery(struct xfs_mount *mp,
+		struct xfs_defer_pending *dfp, struct list_head *capture_list);
+
+static inline void
+xfs_defer_add_item(
+	struct xfs_defer_pending	*dfp,
+	struct list_head		*work)
+{
+	list_add_tail(work, &dfp->dfp_work);
+	dfp->dfp_count++;
+}
+
 int __init xfs_defer_init_item_caches(void);
 void xfs_defer_destroy_item_caches(void);
 
+void xfs_defer_add_barrier(struct xfs_trans *tp);
+
 #endif /* __XFS_DEFER_H__ */
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index f5462fd582d5..a76673281514 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -196,7 +196,7 @@ xfs_dir_isempty(
 		return 1;
 	if (dp->i_disk_size > xfs_inode_data_fork_size(dp))
 		return 0;
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	sfp = dp->i_df.if_data;
 	return !sfp->count;
 }
 
diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c
index 00f960a703b2..3c256d4cc40b 100644
--- a/fs/xfs/libxfs/xfs_dir2_block.c
+++ b/fs/xfs/libxfs/xfs_dir2_block.c
@@ -1089,7 +1089,7 @@ xfs_dir2_sf_to_block(
 	int			newoffset;	/* offset from current entry */
 	unsigned int		offset = geo->data_entry_offset;
 	xfs_dir2_sf_entry_t	*sfep;		/* sf entry pointer */
-	xfs_dir2_sf_hdr_t	*oldsfp;	/* old shortform header  */
+	struct xfs_dir2_sf_hdr	*oldsfp = ifp->if_data;
 	xfs_dir2_sf_hdr_t	*sfp;		/* shortform header  */
 	__be16			*tagp;		/* end of data entry */
 	struct xfs_name		name;
@@ -1099,10 +1099,8 @@ xfs_dir2_sf_to_block(
 	ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
 	ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
 
-	oldsfp = (xfs_dir2_sf_hdr_t *)ifp->if_u1.if_data;
-
 	ASSERT(ifp->if_bytes == dp->i_disk_size);
-	ASSERT(ifp->if_u1.if_data != NULL);
+	ASSERT(oldsfp != NULL);
 	ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(oldsfp->i8count));
 	ASSERT(dp->i_df.if_nextents == 0);
 
diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h
index 7404a9ff1a92..1db2e60ba827 100644
--- a/fs/xfs/libxfs/xfs_dir2_priv.h
+++ b/fs/xfs/libxfs/xfs_dir2_priv.h
@@ -175,7 +175,8 @@ extern int xfs_dir2_sf_create(struct xfs_da_args *args, xfs_ino_t pino);
 extern int xfs_dir2_sf_lookup(struct xfs_da_args *args);
 extern int xfs_dir2_sf_removename(struct xfs_da_args *args);
 extern int xfs_dir2_sf_replace(struct xfs_da_args *args);
-extern xfs_failaddr_t xfs_dir2_sf_verify(struct xfs_inode *ip);
+xfs_failaddr_t xfs_dir2_sf_verify(struct xfs_mount *mp,
+		struct xfs_dir2_sf_hdr *sfp, int64_t size);
 int xfs_dir2_sf_entsize(struct xfs_mount *mp,
 		struct xfs_dir2_sf_hdr *hdr, int len);
 void xfs_dir2_sf_put_ino(struct xfs_mount *mp, struct xfs_dir2_sf_hdr *hdr,
diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c
index 8cd37e6e9d38..e1f83fc7b6ad 100644
--- a/fs/xfs/libxfs/xfs_dir2_sf.c
+++ b/fs/xfs/libxfs/xfs_dir2_sf.c
@@ -364,25 +364,23 @@ int						/* error */
 xfs_dir2_sf_addname(
 	xfs_da_args_t		*args)		/* operation arguments */
 {
-	xfs_inode_t		*dp;		/* incore directory inode */
+	struct xfs_inode	*dp = args->dp;
+	struct xfs_dir2_sf_hdr	*sfp = dp->i_df.if_data;
 	int			error;		/* error return value */
 	int			incr_isize;	/* total change in size */
 	int			new_isize;	/* size after adding name */
 	int			objchange;	/* changing to 8-byte inodes */
 	xfs_dir2_data_aoff_t	offset = 0;	/* offset for new entry */
 	int			pick;		/* which algorithm to use */
-	xfs_dir2_sf_hdr_t	*sfp;		/* shortform structure */
 	xfs_dir2_sf_entry_t	*sfep = NULL;	/* shortform entry */
 
 	trace_xfs_dir2_sf_addname(args);
 
 	ASSERT(xfs_dir2_sf_lookup(args) == -ENOENT);
-	dp = args->dp;
 	ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
 	ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
 	ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
-	ASSERT(dp->i_df.if_u1.if_data != NULL);
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	ASSERT(sfp != NULL);
 	ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(sfp->i8count));
 	/*
 	 * Compute entry (and change in) size.
@@ -462,20 +460,17 @@ xfs_dir2_sf_addname_easy(
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_mount	*mp = dp->i_mount;
-	int			byteoff;	/* byte offset in sf dir */
-	xfs_dir2_sf_hdr_t	*sfp;		/* shortform structure */
+	struct xfs_dir2_sf_hdr	*sfp = dp->i_df.if_data;
+	int			byteoff = (int)((char *)sfep - (char *)sfp);
 
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
-	byteoff = (int)((char *)sfep - (char *)sfp);
 	/*
 	 * Grow the in-inode space.
 	 */
-	xfs_idata_realloc(dp, xfs_dir2_sf_entsize(mp, sfp, args->namelen),
+	sfp = xfs_idata_realloc(dp, xfs_dir2_sf_entsize(mp, sfp, args->namelen),
 			  XFS_DATA_FORK);
 	/*
 	 * Need to set up again due to realloc of the inode data.
 	 */
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
 	sfep = (xfs_dir2_sf_entry_t *)((char *)sfp + byteoff);
 	/*
 	 * Fill in the new entry.
@@ -528,11 +523,10 @@ xfs_dir2_sf_addname_hard(
 	/*
 	 * Copy the old directory to the stack buffer.
 	 */
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
 	old_isize = (int)dp->i_disk_size;
 	buf = kmem_alloc(old_isize, 0);
 	oldsfp = (xfs_dir2_sf_hdr_t *)buf;
-	memcpy(oldsfp, sfp, old_isize);
+	memcpy(oldsfp, dp->i_df.if_data, old_isize);
 	/*
 	 * Loop over the old directory finding the place we're going
 	 * to insert the new entry.
@@ -556,11 +550,8 @@ xfs_dir2_sf_addname_hard(
 	 * the data.
 	 */
 	xfs_idata_realloc(dp, -old_isize, XFS_DATA_FORK);
-	xfs_idata_realloc(dp, new_isize, XFS_DATA_FORK);
-	/*
-	 * Reset the pointer since the buffer was reallocated.
-	 */
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	sfp = xfs_idata_realloc(dp, new_isize, XFS_DATA_FORK);
+
 	/*
 	 * Copy the first part of the directory, including the header.
 	 */
@@ -610,11 +601,10 @@ xfs_dir2_sf_addname_pick(
 	int			i;		/* entry number */
 	xfs_dir2_data_aoff_t	offset;		/* data block offset */
 	xfs_dir2_sf_entry_t	*sfep;		/* shortform entry */
-	xfs_dir2_sf_hdr_t	*sfp;		/* shortform structure */
+	struct xfs_dir2_sf_hdr	*sfp = dp->i_df.if_data;
 	int			size;		/* entry's data size */
 	int			used;		/* data bytes used */
 
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
 	size = xfs_dir2_data_entsize(mp, args->namelen);
 	offset = args->geo->data_first_offset;
 	sfep = xfs_dir2_sf_firstentry(sfp);
@@ -673,14 +663,13 @@ xfs_dir2_sf_check(
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_dir2_sf_hdr	*sfp = dp->i_df.if_data;
 	int			i;		/* entry number */
 	int			i8count;	/* number of big inode#s */
 	xfs_ino_t		ino;		/* entry inode number */
 	int			offset;		/* data offset */
 	xfs_dir2_sf_entry_t	*sfep;		/* shortform dir entry */
-	xfs_dir2_sf_hdr_t	*sfp;		/* shortform structure */
 
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
 	offset = args->geo->data_first_offset;
 	ino = xfs_dir2_sf_get_parent_ino(sfp);
 	i8count = ino > XFS_DIR2_MAX_SHORT_INUM;
@@ -707,11 +696,10 @@ xfs_dir2_sf_check(
 /* Verify the consistency of an inline directory. */
 xfs_failaddr_t
 xfs_dir2_sf_verify(
-	struct xfs_inode		*ip)
+	struct xfs_mount		*mp,
+	struct xfs_dir2_sf_hdr		*sfp,
+	int64_t				size)
 {
-	struct xfs_mount		*mp = ip->i_mount;
-	struct xfs_ifork		*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
-	struct xfs_dir2_sf_hdr		*sfp;
 	struct xfs_dir2_sf_entry	*sfep;
 	struct xfs_dir2_sf_entry	*next_sfep;
 	char				*endp;
@@ -719,15 +707,9 @@ xfs_dir2_sf_verify(
 	int				i;
 	int				i8count;
 	int				offset;
-	int64_t				size;
 	int				error;
 	uint8_t				filetype;
 
-	ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
-
-	sfp = (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data;
-	size = ifp->if_bytes;
-
 	/*
 	 * Give up if the directory is way too short.
 	 */
@@ -834,15 +816,13 @@ xfs_dir2_sf_create(
 	ASSERT(dp->i_df.if_bytes == 0);
 	i8count = pino > XFS_DIR2_MAX_SHORT_INUM;
 	size = xfs_dir2_sf_hdr_size(i8count);
+
 	/*
-	 * Make a buffer for the data.
-	 */
-	xfs_idata_realloc(dp, size, XFS_DATA_FORK);
-	/*
-	 * Fill in the header,
+	 * Make a buffer for the data and fill in the header.
 	 */
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	sfp = xfs_idata_realloc(dp, size, XFS_DATA_FORK);
 	sfp->i8count = i8count;
+
 	/*
 	 * Now can put in the inode number, since i8count is set.
 	 */
@@ -864,9 +844,9 @@ xfs_dir2_sf_lookup(
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_dir2_sf_hdr	*sfp = dp->i_df.if_data;
 	int			i;		/* entry index */
 	xfs_dir2_sf_entry_t	*sfep;		/* shortform directory entry */
-	xfs_dir2_sf_hdr_t	*sfp;		/* shortform structure */
 	enum xfs_dacmp		cmp;		/* comparison result */
 	xfs_dir2_sf_entry_t	*ci_sfep;	/* case-insens. entry */
 
@@ -877,8 +857,7 @@ xfs_dir2_sf_lookup(
 	ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
 	ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
 	ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
-	ASSERT(dp->i_df.if_u1.if_data != NULL);
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	ASSERT(sfp != NULL);
 	ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(sfp->i8count));
 	/*
 	 * Special case for .
@@ -940,13 +919,13 @@ xfs_dir2_sf_removename(
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_dir2_sf_hdr	*sfp = dp->i_df.if_data;
 	int			byteoff;	/* offset of removed entry */
 	int			entsize;	/* this entry's size */
 	int			i;		/* shortform entry index */
 	int			newsize;	/* new inode size */
 	int			oldsize;	/* old inode size */
 	xfs_dir2_sf_entry_t	*sfep;		/* shortform directory entry */
-	xfs_dir2_sf_hdr_t	*sfp;		/* shortform structure */
 
 	trace_xfs_dir2_sf_removename(args);
 
@@ -954,8 +933,7 @@ xfs_dir2_sf_removename(
 	oldsize = (int)dp->i_disk_size;
 	ASSERT(oldsize >= offsetof(struct xfs_dir2_sf_hdr, parent));
 	ASSERT(dp->i_df.if_bytes == oldsize);
-	ASSERT(dp->i_df.if_u1.if_data != NULL);
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	ASSERT(sfp != NULL);
 	ASSERT(oldsize >= xfs_dir2_sf_hdr_size(sfp->i8count));
 	/*
 	 * Loop over the old directory entries.
@@ -992,11 +970,12 @@ xfs_dir2_sf_removename(
 	 */
 	sfp->count--;
 	dp->i_disk_size = newsize;
+
 	/*
 	 * Reallocate, making it smaller.
 	 */
-	xfs_idata_realloc(dp, newsize - oldsize, XFS_DATA_FORK);
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	sfp = xfs_idata_realloc(dp, newsize - oldsize, XFS_DATA_FORK);
+
 	/*
 	 * Are we changing inode number size?
 	 */
@@ -1019,13 +998,12 @@ xfs_dir2_sf_replace_needblock(
 	struct xfs_inode	*dp,
 	xfs_ino_t		inum)
 {
+	struct xfs_dir2_sf_hdr	*sfp = dp->i_df.if_data;
 	int			newsize;
-	struct xfs_dir2_sf_hdr	*sfp;
 
 	if (dp->i_df.if_format != XFS_DINODE_FMT_LOCAL)
 		return false;
 
-	sfp = (struct xfs_dir2_sf_hdr *)dp->i_df.if_u1.if_data;
 	newsize = dp->i_df.if_bytes + (sfp->count + 1) * XFS_INO64_DIFF;
 
 	return inum > XFS_DIR2_MAX_SHORT_INUM &&
@@ -1041,19 +1019,18 @@ xfs_dir2_sf_replace(
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_dir2_sf_hdr	*sfp = dp->i_df.if_data;
 	int			i;		/* entry index */
 	xfs_ino_t		ino=0;		/* entry old inode number */
 	int			i8elevated;	/* sf_toino8 set i8count=1 */
 	xfs_dir2_sf_entry_t	*sfep;		/* shortform directory entry */
-	xfs_dir2_sf_hdr_t	*sfp;		/* shortform structure */
 
 	trace_xfs_dir2_sf_replace(args);
 
 	ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
 	ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
 	ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
-	ASSERT(dp->i_df.if_u1.if_data != NULL);
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	ASSERT(sfp != NULL);
 	ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(sfp->i8count));
 
 	/*
@@ -1076,7 +1053,7 @@ xfs_dir2_sf_replace(
 		 */
 		xfs_dir2_sf_toino8(args);
 		i8elevated = 1;
-		sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+		sfp = dp->i_df.if_data;
 	} else
 		i8elevated = 0;
 
@@ -1157,11 +1134,11 @@ xfs_dir2_sf_toino4(
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_dir2_sf_hdr	*oldsfp = dp->i_df.if_data;
 	char			*buf;		/* old dir's buffer */
 	int			i;		/* entry index */
 	int			newsize;	/* new inode size */
 	xfs_dir2_sf_entry_t	*oldsfep;	/* old sf entry */
-	xfs_dir2_sf_hdr_t	*oldsfp;	/* old sf directory */
 	int			oldsize;	/* old inode size */
 	xfs_dir2_sf_entry_t	*sfep;		/* new sf entry */
 	xfs_dir2_sf_hdr_t	*sfp;		/* new sf directory */
@@ -1175,7 +1152,6 @@ xfs_dir2_sf_toino4(
 	 */
 	oldsize = dp->i_df.if_bytes;
 	buf = kmem_alloc(oldsize, 0);
-	oldsfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
 	ASSERT(oldsfp->i8count == 1);
 	memcpy(buf, oldsfp, oldsize);
 	/*
@@ -1188,7 +1164,7 @@ xfs_dir2_sf_toino4(
 	 * Reset our pointers, the data has moved.
 	 */
 	oldsfp = (xfs_dir2_sf_hdr_t *)buf;
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	sfp = dp->i_df.if_data;
 	/*
 	 * Fill in the new header.
 	 */
@@ -1230,11 +1206,11 @@ xfs_dir2_sf_toino8(
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_dir2_sf_hdr	*oldsfp = dp->i_df.if_data;
 	char			*buf;		/* old dir's buffer */
 	int			i;		/* entry index */
 	int			newsize;	/* new inode size */
 	xfs_dir2_sf_entry_t	*oldsfep;	/* old sf entry */
-	xfs_dir2_sf_hdr_t	*oldsfp;	/* old sf directory */
 	int			oldsize;	/* old inode size */
 	xfs_dir2_sf_entry_t	*sfep;		/* new sf entry */
 	xfs_dir2_sf_hdr_t	*sfp;		/* new sf directory */
@@ -1248,7 +1224,6 @@ xfs_dir2_sf_toino8(
 	 */
 	oldsize = dp->i_df.if_bytes;
 	buf = kmem_alloc(oldsize, 0);
-	oldsfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
 	ASSERT(oldsfp->i8count == 0);
 	memcpy(buf, oldsfp, oldsize);
 	/*
@@ -1261,7 +1236,7 @@ xfs_dir2_sf_toino8(
 	 * Reset our pointers, the data has moved.
 	 */
 	oldsfp = (xfs_dir2_sf_hdr_t *)buf;
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	sfp = dp->i_df.if_data;
 	/*
 	 * Fill in the new header.
 	 */
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 9a88aba1589f..382ab1e71c0b 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -1008,7 +1008,7 @@ enum xfs_dinode_fmt {
  * Return pointers to the data or attribute forks.
  */
 #define XFS_DFORK_DPTR(dip) \
-	((char *)dip + xfs_dinode_size(dip->di_version))
+	((void *)dip + xfs_dinode_size(dip->di_version))
 #define XFS_DFORK_APTR(dip)	\
 	(XFS_DFORK_DPTR(dip) + XFS_DFORK_BOFF(dip))
 #define XFS_DFORK_PTR(dip,w)	\
@@ -1156,20 +1156,6 @@ static inline bool xfs_dinode_has_large_extent_counts(
 #define	XFS_DFL_RTEXTSIZE	(64 * 1024)	        /* 64kB */
 #define	XFS_MIN_RTEXTSIZE	(4 * 1024)		/* 4kB */
 
-#define	XFS_BLOCKSIZE(mp)	((mp)->m_sb.sb_blocksize)
-#define	XFS_BLOCKMASK(mp)	((mp)->m_blockmask)
-
-/*
- * RT bit manipulation macros.
- */
-#define	XFS_RTMIN(a,b)	((a) < (b) ? (a) : (b))
-#define	XFS_RTMAX(a,b)	((a) > (b) ? (a) : (b))
-
-#define	XFS_RTLOBIT(w)	xfs_lowbit32(w)
-#define	XFS_RTHIBIT(w)	xfs_highbit32(w)
-
-#define	XFS_RTBLOCKLOG(b)	xfs_highbit64(b)
-
 /*
  * Dquot and dquot block format definitions
  */
@@ -1272,6 +1258,9 @@ static inline time64_t xfs_dq_bigtime_to_unix(uint32_t ondisk_seconds)
 #define XFS_DQ_GRACE_MIN		((int64_t)0)
 #define XFS_DQ_GRACE_MAX		((int64_t)U32_MAX)
 
+/* Maximum id value for a quota record */
+#define XFS_DQ_ID_MAX			(U32_MAX)
+
 /*
  * This is the main portion of the on-disk representation of quota information
  * for a user.  We pad this with some more expansion room to construct the on
diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index 99e796256c5d..6296993ff8f3 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -68,6 +68,11 @@ struct xfs_fsop_geom;
 #define XFS_SICK_INO_SYMLINK	(1 << 6)  /* symbolic link remote target */
 #define XFS_SICK_INO_PARENT	(1 << 7)  /* parent pointers */
 
+#define XFS_SICK_INO_BMBTD_ZAPPED	(1 << 8)  /* data fork erased */
+#define XFS_SICK_INO_BMBTA_ZAPPED	(1 << 9)  /* attr fork erased */
+#define XFS_SICK_INO_DIR_ZAPPED		(1 << 10) /* directory erased */
+#define XFS_SICK_INO_SYMLINK_ZAPPED	(1 << 11) /* symlink erased */
+
 /* Primary evidence of health problems in a given group. */
 #define XFS_SICK_FS_PRIMARY	(XFS_SICK_FS_COUNTERS | \
 				 XFS_SICK_FS_UQUOTA | \
@@ -97,6 +102,11 @@ struct xfs_fsop_geom;
 				 XFS_SICK_INO_SYMLINK | \
 				 XFS_SICK_INO_PARENT)
 
+#define XFS_SICK_INO_ZAPPED	(XFS_SICK_INO_BMBTD_ZAPPED | \
+				 XFS_SICK_INO_BMBTA_ZAPPED | \
+				 XFS_SICK_INO_DIR_ZAPPED | \
+				 XFS_SICK_INO_SYMLINK_ZAPPED)
+
 /* These functions must be provided by the xfs implementation. */
 
 void xfs_fs_mark_sick(struct xfs_mount *mp, unsigned int mask);
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index b83e54c70906..2361a22035b0 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -95,18 +95,28 @@ xfs_inobt_btrec_to_irec(
 	irec->ir_free = be64_to_cpu(rec->inobt.ir_free);
 }
 
+/* Compute the freecount of an incore inode record. */
+uint8_t
+xfs_inobt_rec_freecount(
+	const struct xfs_inobt_rec_incore	*irec)
+{
+	uint64_t				realfree = irec->ir_free;
+
+	if (xfs_inobt_issparse(irec->ir_holemask))
+		realfree &= xfs_inobt_irec_to_allocmask(irec);
+	return hweight64(realfree);
+}
+
 /* Simple checks for inode records. */
 xfs_failaddr_t
 xfs_inobt_check_irec(
-	struct xfs_btree_cur			*cur,
+	struct xfs_perag			*pag,
 	const struct xfs_inobt_rec_incore	*irec)
 {
-	uint64_t			realfree;
-
 	/* Record has to be properly aligned within the AG. */
-	if (!xfs_verify_agino(cur->bc_ag.pag, irec->ir_startino))
+	if (!xfs_verify_agino(pag, irec->ir_startino))
 		return __this_address;
-	if (!xfs_verify_agino(cur->bc_ag.pag,
+	if (!xfs_verify_agino(pag,
 				irec->ir_startino + XFS_INODES_PER_CHUNK - 1))
 		return __this_address;
 	if (irec->ir_count < XFS_INODES_PER_HOLEMASK_BIT ||
@@ -115,12 +125,7 @@ xfs_inobt_check_irec(
 	if (irec->ir_freecount > XFS_INODES_PER_CHUNK)
 		return __this_address;
 
-	/* if there are no holes, return the first available offset */
-	if (!xfs_inobt_issparse(irec->ir_holemask))
-		realfree = irec->ir_free;
-	else
-		realfree = irec->ir_free & xfs_inobt_irec_to_allocmask(irec);
-	if (hweight64(realfree) != irec->ir_freecount)
+	if (xfs_inobt_rec_freecount(irec) != irec->ir_freecount)
 		return __this_address;
 
 	return NULL;
@@ -164,7 +169,7 @@ xfs_inobt_get_rec(
 		return error;
 
 	xfs_inobt_btrec_to_irec(mp, rec, irec);
-	fa = xfs_inobt_check_irec(cur, irec);
+	fa = xfs_inobt_check_irec(cur->bc_ag.pag, irec);
 	if (fa)
 		return xfs_inobt_complain_bad_rec(cur, fa, irec);
 
@@ -1854,7 +1859,7 @@ xfs_difree_inode_chunk(
 		return xfs_free_extent_later(tp,
 				XFS_AGB_TO_FSB(mp, agno, sagbno),
 				M_IGEO(mp)->ialloc_blks, &XFS_RMAP_OINFO_INODES,
-				XFS_AG_RESV_NONE);
+				XFS_AG_RESV_NONE, false);
 	}
 
 	/* holemask is only 16-bits (fits in an unsigned long) */
@@ -1900,7 +1905,8 @@ xfs_difree_inode_chunk(
 		ASSERT(contigblk % mp->m_sb.sb_spino_align == 0);
 		error = xfs_free_extent_later(tp,
 				XFS_AGB_TO_FSB(mp, agno, agbno), contigblk,
-				&XFS_RMAP_OINFO_INODES, XFS_AG_RESV_NONE);
+				&XFS_RMAP_OINFO_INODES, XFS_AG_RESV_NONE,
+				false);
 		if (error)
 			return error;
 
@@ -2739,7 +2745,7 @@ xfs_ialloc_count_inodes_rec(
 	xfs_failaddr_t			fa;
 
 	xfs_inobt_btrec_to_irec(cur->bc_mp, rec, &irec);
-	fa = xfs_inobt_check_irec(cur, &irec);
+	fa = xfs_inobt_check_irec(cur->bc_ag.pag, &irec);
 	if (fa)
 		return xfs_inobt_complain_bad_rec(cur, fa, &irec);
 
diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h
index fe824bb04a09..f1412183bb44 100644
--- a/fs/xfs/libxfs/xfs_ialloc.h
+++ b/fs/xfs/libxfs/xfs_ialloc.h
@@ -79,6 +79,7 @@ int xfs_inobt_lookup(struct xfs_btree_cur *cur, xfs_agino_t ino,
  */
 int xfs_inobt_get_rec(struct xfs_btree_cur *cur,
 		xfs_inobt_rec_incore_t *rec, int *stat);
+uint8_t xfs_inobt_rec_freecount(const struct xfs_inobt_rec_incore *irec);
 
 /*
  * Inode chunk initialisation routine
@@ -93,7 +94,7 @@ union xfs_btree_rec;
 void xfs_inobt_btrec_to_irec(struct xfs_mount *mp,
 		const union xfs_btree_rec *rec,
 		struct xfs_inobt_rec_incore *irec);
-xfs_failaddr_t xfs_inobt_check_irec(struct xfs_btree_cur *cur,
+xfs_failaddr_t xfs_inobt_check_irec(struct xfs_perag *pag,
 		const struct xfs_inobt_rec_incore *irec);
 int xfs_ialloc_has_inodes_at_extent(struct xfs_btree_cur *cur,
 		xfs_agblock_t bno, xfs_extlen_t len,
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 9258f01c0015..42a5e1f227a0 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -161,7 +161,7 @@ __xfs_inobt_free_block(
 	xfs_inobt_mod_blockcount(cur, -1);
 	fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp));
 	return xfs_free_extent_later(cur->bc_tp, fsbno, 1,
-			&XFS_RMAP_OINFO_INOBT, resv);
+			&XFS_RMAP_OINFO_INOBT, resv, false);
 }
 
 STATIC int
diff --git a/fs/xfs/libxfs/xfs_iext_tree.c b/fs/xfs/libxfs/xfs_iext_tree.c
index 773cf4349428..f4e6b200cdf8 100644
--- a/fs/xfs/libxfs/xfs_iext_tree.c
+++ b/fs/xfs/libxfs/xfs_iext_tree.c
@@ -158,7 +158,7 @@ static void *
 xfs_iext_find_first_leaf(
 	struct xfs_ifork	*ifp)
 {
-	struct xfs_iext_node	*node = ifp->if_u1.if_root;
+	struct xfs_iext_node	*node = ifp->if_data;
 	int			height;
 
 	if (!ifp->if_height)
@@ -176,7 +176,7 @@ static void *
 xfs_iext_find_last_leaf(
 	struct xfs_ifork	*ifp)
 {
-	struct xfs_iext_node	*node = ifp->if_u1.if_root;
+	struct xfs_iext_node	*node = ifp->if_data;
 	int			height, i;
 
 	if (!ifp->if_height)
@@ -306,7 +306,7 @@ xfs_iext_find_level(
 	xfs_fileoff_t		offset,
 	int			level)
 {
-	struct xfs_iext_node	*node = ifp->if_u1.if_root;
+	struct xfs_iext_node	*node = ifp->if_data;
 	int			height, i;
 
 	if (!ifp->if_height)
@@ -402,12 +402,12 @@ xfs_iext_grow(
 	int			i;
 
 	if (ifp->if_height == 1) {
-		struct xfs_iext_leaf *prev = ifp->if_u1.if_root;
+		struct xfs_iext_leaf *prev = ifp->if_data;
 
 		node->keys[0] = xfs_iext_leaf_key(prev, 0);
 		node->ptrs[0] = prev;
 	} else  {
-		struct xfs_iext_node *prev = ifp->if_u1.if_root;
+		struct xfs_iext_node *prev = ifp->if_data;
 
 		ASSERT(ifp->if_height > 1);
 
@@ -418,7 +418,7 @@ xfs_iext_grow(
 	for (i = 1; i < KEYS_PER_NODE; i++)
 		node->keys[i] = XFS_IEXT_KEY_INVALID;
 
-	ifp->if_u1.if_root = node;
+	ifp->if_data = node;
 	ifp->if_height++;
 }
 
@@ -430,7 +430,7 @@ xfs_iext_update_node(
 	int			level,
 	void			*ptr)
 {
-	struct xfs_iext_node	*node = ifp->if_u1.if_root;
+	struct xfs_iext_node	*node = ifp->if_data;
 	int			height, i;
 
 	for (height = ifp->if_height; height > level; height--) {
@@ -583,11 +583,11 @@ xfs_iext_alloc_root(
 {
 	ASSERT(ifp->if_bytes == 0);
 
-	ifp->if_u1.if_root = kmem_zalloc(sizeof(struct xfs_iext_rec), KM_NOFS);
+	ifp->if_data = kmem_zalloc(sizeof(struct xfs_iext_rec), KM_NOFS);
 	ifp->if_height = 1;
 
 	/* now that we have a node step into it */
-	cur->leaf = ifp->if_u1.if_root;
+	cur->leaf = ifp->if_data;
 	cur->pos = 0;
 }
 
@@ -603,9 +603,9 @@ xfs_iext_realloc_root(
 	if (new_size / sizeof(struct xfs_iext_rec) == RECS_PER_LEAF)
 		new_size = NODE_SIZE;
 
-	new = krealloc(ifp->if_u1.if_root, new_size, GFP_NOFS | __GFP_NOFAIL);
+	new = krealloc(ifp->if_data, new_size, GFP_NOFS | __GFP_NOFAIL);
 	memset(new + ifp->if_bytes, 0, new_size - ifp->if_bytes);
-	ifp->if_u1.if_root = new;
+	ifp->if_data = new;
 	cur->leaf = new;
 }
 
@@ -622,13 +622,11 @@ static inline void xfs_iext_inc_seq(struct xfs_ifork *ifp)
 }
 
 void
-xfs_iext_insert(
-	struct xfs_inode	*ip,
+xfs_iext_insert_raw(
+	struct xfs_ifork	*ifp,
 	struct xfs_iext_cursor	*cur,
-	struct xfs_bmbt_irec	*irec,
-	int			state)
+	struct xfs_bmbt_irec	*irec)
 {
-	struct xfs_ifork	*ifp = xfs_iext_state_to_fork(ip, state);
 	xfs_fileoff_t		offset = irec->br_startoff;
 	struct xfs_iext_leaf	*new = NULL;
 	int			nr_entries, i;
@@ -662,12 +660,23 @@ xfs_iext_insert(
 	xfs_iext_set(cur_rec(cur), irec);
 	ifp->if_bytes += sizeof(struct xfs_iext_rec);
 
-	trace_xfs_iext_insert(ip, cur, state, _RET_IP_);
-
 	if (new)
 		xfs_iext_insert_node(ifp, xfs_iext_leaf_key(new, 0), new, 2);
 }
 
+void
+xfs_iext_insert(
+	struct xfs_inode	*ip,
+	struct xfs_iext_cursor	*cur,
+	struct xfs_bmbt_irec	*irec,
+	int			state)
+{
+	struct xfs_ifork	*ifp = xfs_iext_state_to_fork(ip, state);
+
+	xfs_iext_insert_raw(ifp, cur, irec);
+	trace_xfs_iext_insert(ip, cur, state, _RET_IP_);
+}
+
 static struct xfs_iext_node *
 xfs_iext_rebalance_node(
 	struct xfs_iext_node	*parent,
@@ -777,8 +786,8 @@ again:
 		 * If we are at the root and only one entry is left we can just
 		 * free this node and update the root pointer.
 		 */
-		ASSERT(node == ifp->if_u1.if_root);
-		ifp->if_u1.if_root = node->ptrs[0];
+		ASSERT(node == ifp->if_data);
+		ifp->if_data = node->ptrs[0];
 		ifp->if_height--;
 		kmem_free(node);
 	}
@@ -854,8 +863,8 @@ xfs_iext_free_last_leaf(
 	struct xfs_ifork	*ifp)
 {
 	ifp->if_height--;
-	kmem_free(ifp->if_u1.if_root);
-	ifp->if_u1.if_root = NULL;
+	kmem_free(ifp->if_data);
+	ifp->if_data = NULL;
 }
 
 void
@@ -872,7 +881,7 @@ xfs_iext_remove(
 	trace_xfs_iext_remove(ip, cur, state, _RET_IP_);
 
 	ASSERT(ifp->if_height > 0);
-	ASSERT(ifp->if_u1.if_root != NULL);
+	ASSERT(ifp->if_data != NULL);
 	ASSERT(xfs_iext_valid(ifp, cur));
 
 	xfs_iext_inc_seq(ifp);
@@ -1042,9 +1051,9 @@ void
 xfs_iext_destroy(
 	struct xfs_ifork	*ifp)
 {
-	xfs_iext_destroy_node(ifp->if_u1.if_root, ifp->if_height);
+	xfs_iext_destroy_node(ifp->if_data, ifp->if_height);
 
 	ifp->if_bytes = 0;
 	ifp->if_height = 0;
-	ifp->if_u1.if_root = NULL;
+	ifp->if_data = NULL;
 }
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 543f3748c2a3..137a65bda95d 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -510,6 +510,9 @@ xfs_dinode_verify(
 	if (mode && nextents + naextents > nblocks)
 		return __this_address;
 
+	if (nextents + naextents == 0 && nblocks != 0)
+		return __this_address;
+
 	if (S_ISDIR(mode) && nextents > mp->m_dir_geo->max_extents)
 		return __this_address;
 
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index 5a2e7ddfa76d..f4569e18a8d0 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -50,12 +50,15 @@ xfs_init_local_fork(
 		mem_size++;
 
 	if (size) {
-		ifp->if_u1.if_data = kmem_alloc(mem_size, KM_NOFS);
-		memcpy(ifp->if_u1.if_data, data, size);
+		char *new_data = kmem_alloc(mem_size, KM_NOFS);
+
+		memcpy(new_data, data, size);
 		if (zero_terminate)
-			ifp->if_u1.if_data[size] = '\0';
+			new_data[size] = '\0';
+
+		ifp->if_data = new_data;
 	} else {
-		ifp->if_u1.if_data = NULL;
+		ifp->if_data = NULL;
 	}
 
 	ifp->if_bytes = size;
@@ -125,7 +128,7 @@ xfs_iformat_extents(
 	}
 
 	ifp->if_bytes = 0;
-	ifp->if_u1.if_root = NULL;
+	ifp->if_data = NULL;
 	ifp->if_height = 0;
 	if (size) {
 		dp = (xfs_bmbt_rec_t *) XFS_DFORK_PTR(dip, whichfork);
@@ -212,7 +215,7 @@ xfs_iformat_btree(
 			 ifp->if_broot, size);
 
 	ifp->if_bytes = 0;
-	ifp->if_u1.if_root = NULL;
+	ifp->if_data = NULL;
 	ifp->if_height = 0;
 	return 0;
 }
@@ -276,10 +279,9 @@ static uint16_t
 xfs_dfork_attr_shortform_size(
 	struct xfs_dinode		*dip)
 {
-	struct xfs_attr_shortform	*atp =
-		(struct xfs_attr_shortform *)XFS_DFORK_APTR(dip);
+	struct xfs_attr_sf_hdr		*sf = XFS_DFORK_APTR(dip);
 
-	return be16_to_cpu(atp->hdr.totsize);
+	return be16_to_cpu(sf->totsize);
 }
 
 void
@@ -493,7 +495,7 @@ xfs_iroot_realloc(
  * byte_diff -- the change in the number of bytes, positive or negative,
  *	 requested for the if_data array.
  */
-void
+void *
 xfs_idata_realloc(
 	struct xfs_inode	*ip,
 	int64_t			byte_diff,
@@ -505,21 +507,18 @@ xfs_idata_realloc(
 	ASSERT(new_size >= 0);
 	ASSERT(new_size <= xfs_inode_fork_size(ip, whichfork));
 
-	if (byte_diff == 0)
-		return;
-
-	if (new_size == 0) {
-		kmem_free(ifp->if_u1.if_data);
-		ifp->if_u1.if_data = NULL;
-		ifp->if_bytes = 0;
-		return;
+	if (byte_diff) {
+		ifp->if_data = krealloc(ifp->if_data, new_size,
+					GFP_NOFS | __GFP_NOFAIL);
+		if (new_size == 0)
+			ifp->if_data = NULL;
+		ifp->if_bytes = new_size;
 	}
 
-	ifp->if_u1.if_data = krealloc(ifp->if_u1.if_data, new_size,
-				      GFP_NOFS | __GFP_NOFAIL);
-	ifp->if_bytes = new_size;
+	return ifp->if_data;
 }
 
+/* Free all memory and reset a fork back to its initial state. */
 void
 xfs_idestroy_fork(
 	struct xfs_ifork	*ifp)
@@ -531,8 +530,8 @@ xfs_idestroy_fork(
 
 	switch (ifp->if_format) {
 	case XFS_DINODE_FMT_LOCAL:
-		kmem_free(ifp->if_u1.if_data);
-		ifp->if_u1.if_data = NULL;
+		kmem_free(ifp->if_data);
+		ifp->if_data = NULL;
 		break;
 	case XFS_DINODE_FMT_EXTENTS:
 	case XFS_DINODE_FMT_BTREE:
@@ -625,9 +624,9 @@ xfs_iflush_fork(
 	case XFS_DINODE_FMT_LOCAL:
 		if ((iip->ili_fields & dataflag[whichfork]) &&
 		    (ifp->if_bytes > 0)) {
-			ASSERT(ifp->if_u1.if_data != NULL);
+			ASSERT(ifp->if_data != NULL);
 			ASSERT(ifp->if_bytes <= xfs_inode_fork_size(ip, whichfork));
-			memcpy(cp, ifp->if_u1.if_data, ifp->if_bytes);
+			memcpy(cp, ifp->if_data, ifp->if_bytes);
 		}
 		break;
 
@@ -702,19 +701,27 @@ xfs_ifork_verify_local_data(
 	xfs_failaddr_t		fa = NULL;
 
 	switch (VFS_I(ip)->i_mode & S_IFMT) {
-	case S_IFDIR:
-		fa = xfs_dir2_sf_verify(ip);
+	case S_IFDIR: {
+		struct xfs_mount	*mp = ip->i_mount;
+		struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
+		struct xfs_dir2_sf_hdr	*sfp = ifp->if_data;
+
+		fa = xfs_dir2_sf_verify(mp, sfp, ifp->if_bytes);
 		break;
-	case S_IFLNK:
-		fa = xfs_symlink_shortform_verify(ip);
+	}
+	case S_IFLNK: {
+		struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
+
+		fa = xfs_symlink_shortform_verify(ifp->if_data, ifp->if_bytes);
 		break;
+	}
 	default:
 		break;
 	}
 
 	if (fa) {
 		xfs_inode_verifier_error(ip, -EFSCORRUPTED, "data fork",
-				ip->i_df.if_u1.if_data, ip->i_df.if_bytes, fa);
+				ip->i_df.if_data, ip->i_df.if_bytes, fa);
 		return -EFSCORRUPTED;
 	}
 
@@ -729,14 +736,17 @@ xfs_ifork_verify_local_attr(
 	struct xfs_ifork	*ifp = &ip->i_af;
 	xfs_failaddr_t		fa;
 
-	if (!xfs_inode_has_attr_fork(ip))
+	if (!xfs_inode_has_attr_fork(ip)) {
 		fa = __this_address;
-	else
-		fa = xfs_attr_shortform_verify(ip);
+	} else {
+		struct xfs_ifork		*ifp = &ip->i_af;
 
+		ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
+		fa = xfs_attr_shortform_verify(ifp->if_data, ifp->if_bytes);
+	}
 	if (fa) {
 		xfs_inode_verifier_error(ip, -EFSCORRUPTED, "attr fork",
-				ifp->if_u1.if_data, ifp->if_bytes, fa);
+				ifp->if_data, ifp->if_bytes, fa);
 		return -EFSCORRUPTED;
 	}
 
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index 96d307784c85..96303249d28a 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -13,14 +13,12 @@ struct xfs_dinode;
  * File incore extent information, present for each of data & attr forks.
  */
 struct xfs_ifork {
-	int64_t			if_bytes;	/* bytes in if_u1 */
+	int64_t			if_bytes;	/* bytes in if_data */
 	struct xfs_btree_block	*if_broot;	/* file's incore btree root */
 	unsigned int		if_seq;		/* fork mod counter */
 	int			if_height;	/* height of the extent tree */
-	union {
-		void		*if_root;	/* extent tree root */
-		char		*if_data;	/* inline file data */
-	} if_u1;
+	void			*if_data;	/* extent tree root or
+						   inline data */
 	xfs_extnum_t		if_nextents;	/* # of extents in this fork */
 	short			if_broot_bytes;	/* bytes allocated for root */
 	int8_t			if_format;	/* format of this fork */
@@ -170,7 +168,7 @@ int		xfs_iformat_attr_fork(struct xfs_inode *, struct xfs_dinode *);
 void		xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *,
 				struct xfs_inode_log_item *, int);
 void		xfs_idestroy_fork(struct xfs_ifork *ifp);
-void		xfs_idata_realloc(struct xfs_inode *ip, int64_t byte_diff,
+void *		xfs_idata_realloc(struct xfs_inode *ip, int64_t byte_diff,
 				int whichfork);
 void		xfs_iroot_realloc(struct xfs_inode *, int, int);
 int		xfs_iread_extents(struct xfs_trans *, struct xfs_inode *, int);
@@ -180,6 +178,9 @@ void		xfs_init_local_fork(struct xfs_inode *ip, int whichfork,
 				const void *data, int64_t size);
 
 xfs_extnum_t	xfs_iext_count(struct xfs_ifork *ifp);
+void		xfs_iext_insert_raw(struct xfs_ifork *ifp,
+			struct xfs_iext_cursor *cur,
+			struct xfs_bmbt_irec *irec);
 void		xfs_iext_insert(struct xfs_inode *, struct xfs_iext_cursor *cur,
 			struct xfs_bmbt_irec *, int);
 void		xfs_iext_remove(struct xfs_inode *, struct xfs_iext_cursor *,
diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h
index a5100a11faf9..9fe7a9564bca 100644
--- a/fs/xfs/libxfs/xfs_log_recover.h
+++ b/fs/xfs/libxfs/xfs_log_recover.h
@@ -11,6 +11,7 @@
  * define how recovery should work for that type of log item.
  */
 struct xlog_recover_item;
+struct xfs_defer_op_type;
 
 /* Sorting hat for log items as they're read in. */
 enum xlog_recover_reorder {
@@ -153,4 +154,11 @@ xlog_recover_resv(const struct xfs_trans_res *r)
 	return ret;
 }
 
+struct xfs_defer_pending;
+
+void xlog_recover_intent_item(struct xlog *log, struct xfs_log_item *lip,
+		xfs_lsn_t lsn, const struct xfs_defer_op_type *ops);
+int xlog_recover_finish_intent(struct xfs_trans *tp,
+		struct xfs_defer_pending *dfp);
+
 #endif	/* __XFS_LOG_RECOVER_H__ */
diff --git a/fs/xfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h
index 21a7e350b4c5..81885a6a028e 100644
--- a/fs/xfs/xfs_ondisk.h
+++ b/fs/xfs/libxfs/xfs_ondisk.h
@@ -7,16 +7,16 @@
 #define __XFS_ONDISK_H
 
 #define XFS_CHECK_STRUCT_SIZE(structname, size) \
-	BUILD_BUG_ON_MSG(sizeof(structname) != (size), "XFS: sizeof(" \
-		#structname ") is wrong, expected " #size)
+	static_assert(sizeof(structname) == (size), \
+		"XFS: sizeof(" #structname ") is wrong, expected " #size)
 
 #define XFS_CHECK_OFFSET(structname, member, off) \
-	BUILD_BUG_ON_MSG(offsetof(structname, member) != (off), \
+	static_assert(offsetof(structname, member) == (off), \
 		"XFS: offsetof(" #structname ", " #member ") is wrong, " \
 		"expected " #off)
 
 #define XFS_CHECK_VALUE(value, expected) \
-	BUILD_BUG_ON_MSG((value) != (expected), \
+	static_assert((value) == (expected), \
 		"XFS: value of " #value " is wrong, expected " #expected)
 
 static inline void __init
@@ -93,13 +93,13 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, namelen,	8);
 	XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, name,	9);
 	XFS_CHECK_STRUCT_SIZE(xfs_attr_leafblock_t,		32);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_shortform,	4);
-	XFS_CHECK_OFFSET(struct xfs_attr_shortform, hdr.totsize, 0);
-	XFS_CHECK_OFFSET(struct xfs_attr_shortform, hdr.count,	 2);
-	XFS_CHECK_OFFSET(struct xfs_attr_shortform, list[0].namelen,	4);
-	XFS_CHECK_OFFSET(struct xfs_attr_shortform, list[0].valuelen,	5);
-	XFS_CHECK_OFFSET(struct xfs_attr_shortform, list[0].flags,	6);
-	XFS_CHECK_OFFSET(struct xfs_attr_shortform, list[0].nameval,	7);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_sf_hdr,		4);
+	XFS_CHECK_OFFSET(struct xfs_attr_sf_hdr, totsize,	0);
+	XFS_CHECK_OFFSET(struct xfs_attr_sf_hdr, count,		2);
+	XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, namelen,	0);
+	XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, valuelen,	1);
+	XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, flags,	2);
+	XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, nameval,	3);
 	XFS_CHECK_STRUCT_SIZE(xfs_da_blkinfo_t,			12);
 	XFS_CHECK_STRUCT_SIZE(xfs_da_intnode_t,			16);
 	XFS_CHECK_STRUCT_SIZE(xfs_da_node_entry_t,		8);
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 646b3fa362ad..6709a7f8bad5 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -123,11 +123,9 @@ xfs_refcount_btrec_to_irec(
 /* Simple checks for refcount records. */
 xfs_failaddr_t
 xfs_refcount_check_irec(
-	struct xfs_btree_cur		*cur,
+	struct xfs_perag		*pag,
 	const struct xfs_refcount_irec	*irec)
 {
-	struct xfs_perag		*pag = cur->bc_ag.pag;
-
 	if (irec->rc_blockcount == 0 || irec->rc_blockcount > MAXREFCEXTLEN)
 		return __this_address;
 
@@ -179,7 +177,7 @@ xfs_refcount_get_rec(
 		return error;
 
 	xfs_refcount_btrec_to_irec(rec, irec);
-	fa = xfs_refcount_check_irec(cur, irec);
+	fa = xfs_refcount_check_irec(cur->bc_ag.pag, irec);
 	if (fa)
 		return xfs_refcount_complain_bad_rec(cur, fa, irec);
 
@@ -1153,7 +1151,7 @@ xfs_refcount_adjust_extents(
 						tmp.rc_startblock);
 				error = xfs_free_extent_later(cur->bc_tp, fsbno,
 						  tmp.rc_blockcount, NULL,
-						  XFS_AG_RESV_NONE);
+						  XFS_AG_RESV_NONE, false);
 				if (error)
 					goto out_error;
 			}
@@ -1215,7 +1213,7 @@ xfs_refcount_adjust_extents(
 					ext.rc_startblock);
 			error = xfs_free_extent_later(cur->bc_tp, fsbno,
 					ext.rc_blockcount, NULL,
-					XFS_AG_RESV_NONE);
+					XFS_AG_RESV_NONE, false);
 			if (error)
 				goto out_error;
 		}
@@ -1458,7 +1456,7 @@ __xfs_refcount_add(
 	ri->ri_blockcount = blockcount;
 
 	xfs_refcount_update_get_group(tp->t_mountp, ri);
-	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_REFCOUNT, &ri->ri_list);
+	xfs_defer_add(tp, &ri->ri_list, &xfs_refcount_update_defer_type);
 }
 
 /*
@@ -1899,7 +1897,7 @@ xfs_refcount_recover_extent(
 	INIT_LIST_HEAD(&rr->rr_list);
 	xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec);
 
-	if (xfs_refcount_check_irec(cur, &rr->rr_rrec) != NULL ||
+	if (xfs_refcount_check_irec(cur->bc_ag.pag, &rr->rr_rrec) != NULL ||
 	    XFS_IS_CORRUPT(cur->bc_mp,
 			   rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) {
 		kfree(rr);
@@ -1985,7 +1983,7 @@ xfs_refcount_recover_cow_leftovers(
 		/* Free the block. */
 		error = xfs_free_extent_later(tp, fsb,
 				rr->rr_rrec.rc_blockcount, NULL,
-				XFS_AG_RESV_NONE);
+				XFS_AG_RESV_NONE, false);
 		if (error)
 			goto out_trans;
 
@@ -2033,6 +2031,47 @@ xfs_refcount_has_records(
 	return xfs_btree_has_records(cur, &low, &high, NULL, outcome);
 }
 
+struct xfs_refcount_query_range_info {
+	xfs_refcount_query_range_fn	fn;
+	void				*priv;
+};
+
+/* Format btree record and pass to our callback. */
+STATIC int
+xfs_refcount_query_range_helper(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_rec	*rec,
+	void				*priv)
+{
+	struct xfs_refcount_query_range_info	*query = priv;
+	struct xfs_refcount_irec	irec;
+	xfs_failaddr_t			fa;
+
+	xfs_refcount_btrec_to_irec(rec, &irec);
+	fa = xfs_refcount_check_irec(cur->bc_ag.pag, &irec);
+	if (fa)
+		return xfs_refcount_complain_bad_rec(cur, fa, &irec);
+
+	return query->fn(cur, &irec, query->priv);
+}
+
+/* Find all refcount records between two keys. */
+int
+xfs_refcount_query_range(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_refcount_irec	*low_rec,
+	const struct xfs_refcount_irec	*high_rec,
+	xfs_refcount_query_range_fn	fn,
+	void				*priv)
+{
+	union xfs_btree_irec		low_brec = { .rc = *low_rec };
+	union xfs_btree_irec		high_brec = { .rc = *high_rec };
+	struct xfs_refcount_query_range_info query = { .priv = priv, .fn = fn };
+
+	return xfs_btree_query_range(cur, &low_brec, &high_brec,
+			xfs_refcount_query_range_helper, &query);
+}
+
 int __init
 xfs_refcount_intent_init_cache(void)
 {
diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h
index 783cd89ca195..9b56768a590c 100644
--- a/fs/xfs/libxfs/xfs_refcount.h
+++ b/fs/xfs/libxfs/xfs_refcount.h
@@ -117,7 +117,7 @@ extern int xfs_refcount_has_records(struct xfs_btree_cur *cur,
 union xfs_btree_rec;
 extern void xfs_refcount_btrec_to_irec(const union xfs_btree_rec *rec,
 		struct xfs_refcount_irec *irec);
-xfs_failaddr_t xfs_refcount_check_irec(struct xfs_btree_cur *cur,
+xfs_failaddr_t xfs_refcount_check_irec(struct xfs_perag *pag,
 		const struct xfs_refcount_irec *irec);
 extern int xfs_refcount_insert(struct xfs_btree_cur *cur,
 		struct xfs_refcount_irec *irec, int *stat);
@@ -127,4 +127,14 @@ extern struct kmem_cache	*xfs_refcount_intent_cache;
 int __init xfs_refcount_intent_init_cache(void);
 void xfs_refcount_intent_destroy_cache(void);
 
+typedef int (*xfs_refcount_query_range_fn)(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_refcount_irec	*rec,
+	void				*priv);
+
+int xfs_refcount_query_range(struct xfs_btree_cur *cur,
+		const struct xfs_refcount_irec *low_rec,
+		const struct xfs_refcount_irec *high_rec,
+		xfs_refcount_query_range_fn fn, void *priv);
+
 #endif	/* __XFS_REFCOUNT_H__ */
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 5c3987d8dc24..0d80bd99147c 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -112,7 +112,7 @@ xfs_refcountbt_free_block(
 	be32_add_cpu(&agf->agf_refcount_blocks, -1);
 	xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_REFCOUNT_BLOCKS);
 	return xfs_free_extent_later(cur->bc_tp, fsbno, 1,
-			&XFS_RMAP_OINFO_REFC, XFS_AG_RESV_METADATA);
+			&XFS_RMAP_OINFO_REFC, XFS_AG_RESV_METADATA, false);
 }
 
 STATIC int
@@ -226,7 +226,18 @@ xfs_refcountbt_verify(
 
 	level = be16_to_cpu(block->bb_level);
 	if (pag && xfs_perag_initialised_agf(pag)) {
-		if (level >= pag->pagf_refcount_level)
+		unsigned int	maxlevel = pag->pagf_refcount_level;
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+		/*
+		 * Online repair could be rewriting the refcount btree, so
+		 * we'll validate against the larger of either tree while this
+		 * is going on.
+		 */
+		maxlevel = max_t(unsigned int, maxlevel,
+				pag->pagf_repair_refcount_level);
+#endif
+		if (level >= maxlevel)
 			return __this_address;
 	} else if (level >= mp->m_refc_maxlevels)
 		return __this_address;
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index fbb0b2637463..76bf7f48cb5a 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -2567,7 +2567,7 @@ __xfs_rmap_add(
 	ri->ri_bmap = *bmap;
 
 	xfs_rmap_update_get_group(tp->t_mountp, ri);
-	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_RMAP, &ri->ri_list);
+	xfs_defer_add(tp, &ri->ri_list, &xfs_rmap_update_defer_type);
 }
 
 /* Map an extent into a file. */
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index c269d704314d..31100120b2c5 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -184,7 +184,7 @@ xfs_rtfind_back(
 		 * Calculate first (leftmost) bit number to look at,
 		 * and mask for all the relevant bits in this word.
 		 */
-		firstbit = XFS_RTMAX((xfs_srtblock_t)(bit - len + 1), 0);
+		firstbit = max_t(xfs_srtblock_t, bit - len + 1, 0);
 		mask = (((xfs_rtword_t)1 << (bit - firstbit + 1)) - 1) <<
 			firstbit;
 		/*
@@ -195,7 +195,7 @@ xfs_rtfind_back(
 			/*
 			 * Different.  Mark where we are and return.
 			 */
-			i = bit - XFS_RTHIBIT(wdiff);
+			i = bit - xfs_highbit32(wdiff);
 			*rtx = start - i + 1;
 			return 0;
 		}
@@ -233,7 +233,7 @@ xfs_rtfind_back(
 			/*
 			 * Different, mark where we are and return.
 			 */
-			i += XFS_NBWORD - 1 - XFS_RTHIBIT(wdiff);
+			i += XFS_NBWORD - 1 - xfs_highbit32(wdiff);
 			*rtx = start - i + 1;
 			return 0;
 		}
@@ -272,7 +272,7 @@ xfs_rtfind_back(
 			/*
 			 * Different, mark where we are and return.
 			 */
-			i += XFS_NBWORD - 1 - XFS_RTHIBIT(wdiff);
+			i += XFS_NBWORD - 1 - xfs_highbit32(wdiff);
 			*rtx = start - i + 1;
 			return 0;
 		} else
@@ -338,7 +338,7 @@ xfs_rtfind_forw(
 		 * Calculate last (rightmost) bit number to look at,
 		 * and mask for all the relevant bits in this word.
 		 */
-		lastbit = XFS_RTMIN(bit + len, XFS_NBWORD);
+		lastbit = min(bit + len, XFS_NBWORD);
 		mask = (((xfs_rtword_t)1 << (lastbit - bit)) - 1) << bit;
 		/*
 		 * Calculate the difference between the value there
@@ -348,7 +348,7 @@ xfs_rtfind_forw(
 			/*
 			 * Different.  Mark where we are and return.
 			 */
-			i = XFS_RTLOBIT(wdiff) - bit;
+			i = xfs_lowbit32(wdiff) - bit;
 			*rtx = start + i - 1;
 			return 0;
 		}
@@ -386,7 +386,7 @@ xfs_rtfind_forw(
 			/*
 			 * Different, mark where we are and return.
 			 */
-			i += XFS_RTLOBIT(wdiff);
+			i += xfs_lowbit32(wdiff);
 			*rtx = start + i - 1;
 			return 0;
 		}
@@ -423,7 +423,7 @@ xfs_rtfind_forw(
 			/*
 			 * Different, mark where we are and return.
 			 */
-			i += XFS_RTLOBIT(wdiff);
+			i += xfs_lowbit32(wdiff);
 			*rtx = start + i - 1;
 			return 0;
 		} else
@@ -452,71 +452,59 @@ xfs_trans_log_rtsummary(
 }
 
 /*
- * Read and/or modify the summary information for a given extent size,
- * bitmap block combination.
- * Keeps track of a current summary block, so we don't keep reading
- * it from the buffer cache.
- *
- * Summary information is returned in *sum if specified.
- * If no delta is specified, returns summary only.
+ * Modify the summary information for a given extent size, bitmap block
+ * combination.
  */
 int
-xfs_rtmodify_summary_int(
+xfs_rtmodify_summary(
 	struct xfs_rtalloc_args	*args,
 	int			log,	/* log2 of extent size */
 	xfs_fileoff_t		bbno,	/* bitmap block number */
-	int			delta,	/* change to make to summary info */
-	xfs_suminfo_t		*sum)	/* out: summary info for this block */
+	int			delta)	/* in/out: summary block number */
 {
 	struct xfs_mount	*mp = args->mp;
-	int			error;
-	xfs_fileoff_t		sb;	/* summary fsblock */
-	xfs_rtsumoff_t		so;	/* index into the summary file */
+	xfs_rtsumoff_t		so = xfs_rtsumoffs(mp, log, bbno);
 	unsigned int		infoword;
+	xfs_suminfo_t		val;
+	int			error;
 
-	/*
-	 * Compute entry number in the summary file.
-	 */
-	so = xfs_rtsumoffs(mp, log, bbno);
-	/*
-	 * Compute the block number in the summary file.
-	 */
-	sb = xfs_rtsumoffs_to_block(mp, so);
-
-	error = xfs_rtsummary_read_buf(args, sb);
+	error = xfs_rtsummary_read_buf(args, xfs_rtsumoffs_to_block(mp, so));
 	if (error)
 		return error;
 
-	/*
-	 * Point to the summary information, modify/log it, and/or copy it out.
-	 */
 	infoword = xfs_rtsumoffs_to_infoword(mp, so);
-	if (delta) {
-		xfs_suminfo_t	val = xfs_suminfo_add(args, infoword, delta);
-
-		if (mp->m_rsum_cache) {
-			if (val == 0 && log + 1 == mp->m_rsum_cache[bbno])
-				mp->m_rsum_cache[bbno] = log;
-			if (val != 0 && log >= mp->m_rsum_cache[bbno])
-				mp->m_rsum_cache[bbno] = log + 1;
-		}
-		xfs_trans_log_rtsummary(args, infoword);
-		if (sum)
-			*sum = val;
-	} else if (sum) {
-		*sum = xfs_suminfo_get(args, infoword);
+	val = xfs_suminfo_add(args, infoword, delta);
+
+	if (mp->m_rsum_cache) {
+		if (val == 0 && log + 1 == mp->m_rsum_cache[bbno])
+			mp->m_rsum_cache[bbno] = log;
+		if (val != 0 && log >= mp->m_rsum_cache[bbno])
+			mp->m_rsum_cache[bbno] = log + 1;
 	}
+
+	xfs_trans_log_rtsummary(args, infoword);
 	return 0;
 }
 
+/*
+ * Read and return the summary information for a given extent size, bitmap block
+ * combination.
+ */
 int
-xfs_rtmodify_summary(
+xfs_rtget_summary(
 	struct xfs_rtalloc_args	*args,
 	int			log,	/* log2 of extent size */
 	xfs_fileoff_t		bbno,	/* bitmap block number */
-	int			delta)	/* in/out: summary block number */
+	xfs_suminfo_t		*sum)	/* out: summary info for this block */
 {
-	return xfs_rtmodify_summary_int(args, log, bbno, delta, NULL);
+	struct xfs_mount	*mp = args->mp;
+	xfs_rtsumoff_t		so = xfs_rtsumoffs(mp, log, bbno);
+	int			error;
+
+	error = xfs_rtsummary_read_buf(args, xfs_rtsumoffs_to_block(mp, so));
+	if (!error)
+		*sum = xfs_suminfo_get(args, xfs_rtsumoffs_to_infoword(mp, so));
+	return error;
 }
 
 /* Log rtbitmap block from the word @from to the byte before @next. */
@@ -585,7 +573,7 @@ xfs_rtmodify_range(
 		/*
 		 * Compute first bit not changed and mask of relevant bits.
 		 */
-		lastbit = XFS_RTMIN(bit + len, XFS_NBWORD);
+		lastbit = min(bit + len, XFS_NBWORD);
 		mask = (((xfs_rtword_t)1 << (lastbit - bit)) - 1) << bit;
 		/*
 		 * Set/clear the active bits.
@@ -720,7 +708,7 @@ xfs_rtfree_range(
 	 */
 	if (preblock < start) {
 		error = xfs_rtmodify_summary(args,
-				XFS_RTBLOCKLOG(start - preblock),
+				xfs_highbit64(start - preblock),
 				xfs_rtx_to_rbmblock(mp, preblock), -1);
 		if (error) {
 			return error;
@@ -732,7 +720,7 @@ xfs_rtfree_range(
 	 */
 	if (postblock > end) {
 		error = xfs_rtmodify_summary(args,
-				XFS_RTBLOCKLOG(postblock - end),
+				xfs_highbit64(postblock - end),
 				xfs_rtx_to_rbmblock(mp, end + 1), -1);
 		if (error) {
 			return error;
@@ -743,7 +731,7 @@ xfs_rtfree_range(
 	 * (new) free extent.
 	 */
 	return xfs_rtmodify_summary(args,
-			XFS_RTBLOCKLOG(postblock + 1 - preblock),
+			xfs_highbit64(postblock + 1 - preblock),
 			xfs_rtx_to_rbmblock(mp, preblock), 1);
 }
 
@@ -799,7 +787,7 @@ xfs_rtcheck_range(
 		/*
 		 * Compute first bit not examined.
 		 */
-		lastbit = XFS_RTMIN(bit + len, XFS_NBWORD);
+		lastbit = min(bit + len, XFS_NBWORD);
 		/*
 		 * Mask of relevant bits.
 		 */
@@ -812,7 +800,7 @@ xfs_rtcheck_range(
 			/*
 			 * Different, compute first wrong bit and return.
 			 */
-			i = XFS_RTLOBIT(wdiff) - bit;
+			i = xfs_lowbit32(wdiff) - bit;
 			*new = start + i;
 			*stat = 0;
 			return 0;
@@ -851,7 +839,7 @@ xfs_rtcheck_range(
 			/*
 			 * Different, compute first wrong bit and return.
 			 */
-			i += XFS_RTLOBIT(wdiff);
+			i += xfs_lowbit32(wdiff);
 			*new = start + i;
 			*stat = 0;
 			return 0;
@@ -889,7 +877,7 @@ xfs_rtcheck_range(
 			/*
 			 * Different, compute first wrong bit and return.
 			 */
-			i += XFS_RTLOBIT(wdiff);
+			i += xfs_lowbit32(wdiff);
 			*new = start + i;
 			*stat = 0;
 			return 0;
@@ -1131,6 +1119,20 @@ xfs_rtbitmap_blockcount(
 }
 
 /*
+ * Compute the maximum level number of the realtime summary file, as defined by
+ * mkfs.  The historic use of highbit32 on a 64-bit quantity prohibited correct
+ * use of rt volumes with more than 2^32 extents.
+ */
+uint8_t
+xfs_compute_rextslog(
+	xfs_rtbxlen_t		rtextents)
+{
+	if (!rtextents)
+		return 0;
+	return xfs_highbit64(rtextents);
+}
+
+/*
  * Compute the number of rtbitmap words needed to populate every block of a
  * bitmap that is large enough to track the given number of rt extents.
  */
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h
index c0637057d69c..274dc7dae1fa 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.h
+++ b/fs/xfs/libxfs/xfs_rtbitmap.h
@@ -321,8 +321,8 @@ int xfs_rtfind_forw(struct xfs_rtalloc_args *args, xfs_rtxnum_t start,
 		xfs_rtxnum_t limit, xfs_rtxnum_t *rtblock);
 int xfs_rtmodify_range(struct xfs_rtalloc_args *args, xfs_rtxnum_t start,
 		xfs_rtxlen_t len, int val);
-int xfs_rtmodify_summary_int(struct xfs_rtalloc_args *args, int log,
-		xfs_fileoff_t bbno, int delta, xfs_suminfo_t *sum);
+int xfs_rtget_summary(struct xfs_rtalloc_args *args, int log,
+		xfs_fileoff_t bbno, xfs_suminfo_t *sum);
 int xfs_rtmodify_summary(struct xfs_rtalloc_args *args, int log,
 		xfs_fileoff_t bbno, int delta);
 int xfs_rtfree_range(struct xfs_rtalloc_args *args, xfs_rtxnum_t start,
@@ -351,6 +351,20 @@ xfs_rtfree_extent(
 int xfs_rtfree_blocks(struct xfs_trans *tp, xfs_fsblock_t rtbno,
 		xfs_filblks_t rtlen);
 
+uint8_t xfs_compute_rextslog(xfs_rtbxlen_t rtextents);
+
+/* Do we support an rt volume having this number of rtextents? */
+static inline bool
+xfs_validate_rtextents(
+	xfs_rtbxlen_t		rtextents)
+{
+	/* No runt rt volumes */
+	if (rtextents == 0)
+		return false;
+
+	return true;
+}
+
 xfs_filblks_t xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t
 		rtextents);
 unsigned long long xfs_rtbitmap_wordcount(struct xfs_mount *mp,
@@ -369,6 +383,8 @@ unsigned long long xfs_rtsummary_wordcount(struct xfs_mount *mp,
 # define xfs_rtsummary_read_buf(a,b)			(-ENOSYS)
 # define xfs_rtbuf_cache_relse(a)			(0)
 # define xfs_rtalloc_extent_is_free(m,t,s,l,i)		(-ENOSYS)
+# define xfs_compute_rextslog(rtx)			(0)
+# define xfs_validate_rtextents(rtx)			(false)
 static inline xfs_filblks_t
 xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t rtextents)
 {
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 1f74d0cd1618..4a9e8588f4c9 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -25,6 +25,7 @@
 #include "xfs_da_format.h"
 #include "xfs_health.h"
 #include "xfs_ag.h"
+#include "xfs_rtbitmap.h"
 
 /*
  * Physical superblock buffer manipulations. Shared with libxfs in userspace.
@@ -508,8 +509,9 @@ xfs_validate_sb_common(
 		rbmblocks = howmany_64(sbp->sb_rextents,
 				       NBBY * sbp->sb_blocksize);
 
-		if (sbp->sb_rextents != rexts ||
-		    sbp->sb_rextslog != xfs_highbit32(sbp->sb_rextents) ||
+		if (!xfs_validate_rtextents(rexts) ||
+		    sbp->sb_rextents != rexts ||
+		    sbp->sb_rextslog != xfs_compute_rextslog(rexts) ||
 		    sbp->sb_rbmblocks != rbmblocks) {
 			xfs_notice(mp,
 				"realtime geometry sanity check failed");
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index c4381388c0c1..4220d3584c1b 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -139,7 +139,7 @@ bool xfs_symlink_hdr_ok(xfs_ino_t ino, uint32_t offset,
 			uint32_t size, struct xfs_buf *bp);
 void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
 				 struct xfs_inode *ip, struct xfs_ifork *ifp);
-xfs_failaddr_t xfs_symlink_shortform_verify(struct xfs_inode *ip);
+xfs_failaddr_t xfs_symlink_shortform_verify(void *sfp, int64_t size);
 
 /* Computed inode geometry for the filesystem. */
 struct xfs_ino_geometry {
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c
index bdc777b9ec4a..160aa20aa441 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.c
+++ b/fs/xfs/libxfs/xfs_symlink_remote.c
@@ -175,7 +175,7 @@ xfs_symlink_local_to_remote(
 
 	if (!xfs_has_crc(mp)) {
 		bp->b_ops = NULL;
-		memcpy(bp->b_addr, ifp->if_u1.if_data, ifp->if_bytes);
+		memcpy(bp->b_addr, ifp->if_data, ifp->if_bytes);
 		xfs_trans_log_buf(tp, bp, 0, ifp->if_bytes - 1);
 		return;
 	}
@@ -191,7 +191,7 @@ xfs_symlink_local_to_remote(
 
 	buf = bp->b_addr;
 	buf += xfs_symlink_hdr_set(mp, ip->i_ino, 0, ifp->if_bytes, bp);
-	memcpy(buf, ifp->if_u1.if_data, ifp->if_bytes);
+	memcpy(buf, ifp->if_data, ifp->if_bytes);
 	xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsymlink_hdr) +
 					ifp->if_bytes - 1);
 }
@@ -202,15 +202,11 @@ xfs_symlink_local_to_remote(
  */
 xfs_failaddr_t
 xfs_symlink_shortform_verify(
-	struct xfs_inode	*ip)
+	void			*sfp,
+	int64_t			size)
 {
-	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
-	char			*sfp = (char *)ifp->if_u1.if_data;
-	int			size = ifp->if_bytes;
 	char			*endp = sfp + size;
 
-	ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
-
 	/*
 	 * Zero length symlinks should never occur in memory as they are
 	 * never allowed to exist on disk.
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index 533200c4ccc2..20b5375f2d9c 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -51,7 +51,6 @@ typedef void *		xfs_failaddr_t;
 #define	NULLRFSBLOCK	((xfs_rfsblock_t)-1)
 #define	NULLRTBLOCK	((xfs_rtblock_t)-1)
 #define	NULLFILEOFF	((xfs_fileoff_t)-1)
-#define	NULLRTEXTNO	((xfs_rtxnum_t)-1)
 
 #define	NULLAGBLOCK	((xfs_agblock_t)-1)
 #define	NULLAGNUMBER	((xfs_agnumber_t)-1)
@@ -208,6 +207,13 @@ enum xfs_ag_resv_type {
 	XFS_AG_RESV_AGFL,
 	XFS_AG_RESV_METADATA,
 	XFS_AG_RESV_RMAPBT,
+
+	/*
+	 * Don't increase fdblocks when freeing extent.  This is a pony for
+	 * the bnobt repair functions to re-free the free space without
+	 * altering fdblocks.  If you think you need this you're wrong.
+	 */
+	XFS_AG_RESV_IGNORE,
 };
 
 /* Results of scanning a btree keyspace to check occupancy. */
diff --git a/fs/xfs/scrub/agb_bitmap.c b/fs/xfs/scrub/agb_bitmap.c
new file mode 100644
index 000000000000..573e4e062754
--- /dev/null
+++ b/fs/xfs/scrub/agb_bitmap.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_shared.h"
+#include "xfs_bit.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_btree.h"
+#include "bitmap.h"
+#include "scrub/agb_bitmap.h"
+
+/*
+ * Record all btree blocks seen while iterating all records of a btree.
+ *
+ * We know that the btree query_all function starts at the left edge and walks
+ * towards the right edge of the tree.  Therefore, we know that we can walk up
+ * the btree cursor towards the root; if the pointer for a given level points
+ * to the first record/key in that block, we haven't seen this block before;
+ * and therefore we need to remember that we saw this block in the btree.
+ *
+ * So if our btree is:
+ *
+ *    4
+ *  / | \
+ * 1  2  3
+ *
+ * Pretend for this example that each leaf block has 100 btree records.  For
+ * the first btree record, we'll observe that bc_levels[0].ptr == 1, so we
+ * record that we saw block 1.  Then we observe that bc_levels[1].ptr == 1, so
+ * we record block 4.  The list is [1, 4].
+ *
+ * For the second btree record, we see that bc_levels[0].ptr == 2, so we exit
+ * the loop.  The list remains [1, 4].
+ *
+ * For the 101st btree record, we've moved onto leaf block 2.  Now
+ * bc_levels[0].ptr == 1 again, so we record that we saw block 2.  We see that
+ * bc_levels[1].ptr == 2, so we exit the loop.  The list is now [1, 4, 2].
+ *
+ * For the 102nd record, bc_levels[0].ptr == 2, so we continue.
+ *
+ * For the 201st record, we've moved on to leaf block 3.
+ * bc_levels[0].ptr == 1, so we add 3 to the list.  Now it is [1, 4, 2, 3].
+ *
+ * For the 300th record we just exit, with the list being [1, 4, 2, 3].
+ */
+
+/* Mark a btree block to the agblock bitmap. */
+STATIC int
+xagb_bitmap_visit_btblock(
+	struct xfs_btree_cur	*cur,
+	int			level,
+	void			*priv)
+{
+	struct xagb_bitmap	*bitmap = priv;
+	struct xfs_buf		*bp;
+	xfs_fsblock_t		fsbno;
+	xfs_agblock_t		agbno;
+
+	xfs_btree_get_block(cur, level, &bp);
+	if (!bp)
+		return 0;
+
+	fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp));
+	agbno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno);
+
+	return xagb_bitmap_set(bitmap, agbno, 1);
+}
+
+/* Mark all (per-AG) btree blocks in the agblock bitmap. */
+int
+xagb_bitmap_set_btblocks(
+	struct xagb_bitmap	*bitmap,
+	struct xfs_btree_cur	*cur)
+{
+	return xfs_btree_visit_blocks(cur, xagb_bitmap_visit_btblock,
+			XFS_BTREE_VISIT_ALL, bitmap);
+}
+
+/*
+ * Record all the buffers pointed to by the btree cursor.  Callers already
+ * engaged in a btree walk should call this function to capture the list of
+ * blocks going from the leaf towards the root.
+ */
+int
+xagb_bitmap_set_btcur_path(
+	struct xagb_bitmap	*bitmap,
+	struct xfs_btree_cur	*cur)
+{
+	int			i;
+	int			error;
+
+	for (i = 0; i < cur->bc_nlevels && cur->bc_levels[i].ptr == 1; i++) {
+		error = xagb_bitmap_visit_btblock(cur, i, bitmap);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
diff --git a/fs/xfs/scrub/agb_bitmap.h b/fs/xfs/scrub/agb_bitmap.h
new file mode 100644
index 000000000000..ed08f76ff4f3
--- /dev/null
+++ b/fs/xfs/scrub/agb_bitmap.h
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_AGB_BITMAP_H__
+#define __XFS_SCRUB_AGB_BITMAP_H__
+
+/* Bitmaps, but for type-checked for xfs_agblock_t */
+
+struct xagb_bitmap {
+	struct xbitmap32	agbitmap;
+};
+
+static inline void xagb_bitmap_init(struct xagb_bitmap *bitmap)
+{
+	xbitmap32_init(&bitmap->agbitmap);
+}
+
+static inline void xagb_bitmap_destroy(struct xagb_bitmap *bitmap)
+{
+	xbitmap32_destroy(&bitmap->agbitmap);
+}
+
+static inline int xagb_bitmap_clear(struct xagb_bitmap *bitmap,
+		xfs_agblock_t start, xfs_extlen_t len)
+{
+	return xbitmap32_clear(&bitmap->agbitmap, start, len);
+}
+static inline int xagb_bitmap_set(struct xagb_bitmap *bitmap,
+		xfs_agblock_t start, xfs_extlen_t len)
+{
+	return xbitmap32_set(&bitmap->agbitmap, start, len);
+}
+
+static inline bool xagb_bitmap_test(struct xagb_bitmap *bitmap,
+		xfs_agblock_t start, xfs_extlen_t *len)
+{
+	return xbitmap32_test(&bitmap->agbitmap, start, len);
+}
+
+static inline int xagb_bitmap_disunion(struct xagb_bitmap *bitmap,
+		struct xagb_bitmap *sub)
+{
+	return xbitmap32_disunion(&bitmap->agbitmap, &sub->agbitmap);
+}
+
+static inline uint32_t xagb_bitmap_hweight(struct xagb_bitmap *bitmap)
+{
+	return xbitmap32_hweight(&bitmap->agbitmap);
+}
+static inline bool xagb_bitmap_empty(struct xagb_bitmap *bitmap)
+{
+	return xbitmap32_empty(&bitmap->agbitmap);
+}
+
+static inline int xagb_bitmap_walk(struct xagb_bitmap *bitmap,
+		xbitmap32_walk_fn fn, void *priv)
+{
+	return xbitmap32_walk(&bitmap->agbitmap, fn, priv);
+}
+
+int xagb_bitmap_set_btblocks(struct xagb_bitmap *bitmap,
+		struct xfs_btree_cur *cur);
+int xagb_bitmap_set_btcur_path(struct xagb_bitmap *bitmap,
+		struct xfs_btree_cur *cur);
+
+#endif	/* __XFS_SCRUB_AGB_BITMAP_H__ */
diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
index 876a2f41b063..26bd1ff68f1b 100644
--- a/fs/xfs/scrub/agheader_repair.c
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -26,6 +26,7 @@
 #include "scrub/trace.h"
 #include "scrub/repair.h"
 #include "scrub/bitmap.h"
+#include "scrub/agb_bitmap.h"
 #include "scrub/reap.h"
 
 /* Superblock */
@@ -72,7 +73,7 @@ xrep_superblock(
 	/* Write this to disk. */
 	xfs_trans_buf_set_type(sc->tp, bp, XFS_BLFT_SB_BUF);
 	xfs_trans_log_buf(sc->tp, bp, 0, BBTOB(bp->b_length) - 1);
-	return error;
+	return 0;
 }
 
 /* AGF */
@@ -341,7 +342,7 @@ xrep_agf_commit_new(
 	pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level);
 	set_bit(XFS_AGSTATE_AGF_INIT, &pag->pag_opstate);
 
-	return 0;
+	return xrep_roll_ag_trans(sc);
 }
 
 /* Repair the AGF. v5 filesystems only. */
@@ -494,12 +495,11 @@ xrep_agfl_walk_rmap(
 /* Strike out the blocks that are cross-linked according to the rmapbt. */
 STATIC int
 xrep_agfl_check_extent(
-	uint64_t		start,
-	uint64_t		len,
+	uint32_t		agbno,
+	uint32_t		len,
 	void			*priv)
 {
 	struct xrep_agfl	*ra = priv;
-	xfs_agblock_t		agbno = start;
 	xfs_agblock_t		last_agbno = agbno + len - 1;
 	int			error;
 
@@ -647,8 +647,8 @@ struct xrep_agfl_fill {
 /* Fill the AGFL with whatever blocks are in this extent. */
 static int
 xrep_agfl_fill(
-	uint64_t		start,
-	uint64_t		len,
+	uint32_t		start,
+	uint32_t		len,
 	void			*priv)
 {
 	struct xrep_agfl_fill	*af = priv;
@@ -789,6 +789,9 @@ xrep_agfl(
 	/* Dump any AGFL overflow. */
 	error = xrep_reap_agblocks(sc, &agfl_extents, &XFS_RMAP_OINFO_AG,
 			XFS_AG_RESV_AGFL);
+	if (error)
+		goto err;
+
 err:
 	xagb_bitmap_destroy(&agfl_extents);
 	return error;
@@ -962,7 +965,7 @@ xrep_agi_commit_new(
 	pag->pagi_freecount = be32_to_cpu(agi->agi_freecount);
 	set_bit(XFS_AGSTATE_AGI_INIT, &pag->pag_opstate);
 
-	return 0;
+	return xrep_roll_ag_trans(sc);
 }
 
 /* Repair the AGI. */
diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
index 279af72b1671..d1b8a4997dd2 100644
--- a/fs/xfs/scrub/alloc.c
+++ b/fs/xfs/scrub/alloc.c
@@ -9,13 +9,16 @@
 #include "xfs_format.h"
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
 #include "xfs_btree.h"
 #include "xfs_alloc.h"
 #include "xfs_rmap.h"
+#include "xfs_ag.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/btree.h"
-#include "xfs_ag.h"
+#include "scrub/repair.h"
 
 /*
  * Set us up to scrub free space btrees.
@@ -24,10 +27,19 @@ int
 xchk_setup_ag_allocbt(
 	struct xfs_scrub	*sc)
 {
+	int			error;
+
 	if (xchk_need_intent_drain(sc))
 		xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN);
 
-	return xchk_setup_ag_btree(sc, false);
+	error = xchk_setup_ag_btree(sc, false);
+	if (error)
+		return error;
+
+	if (xchk_could_repair(sc))
+		return xrep_setup_ag_allocbt(sc);
+
+	return 0;
 }
 
 /* Free space btree scrubber. */
@@ -127,7 +139,7 @@ xchk_allocbt_rec(
 	struct xchk_alloc	*ca = bs->private;
 
 	xfs_alloc_btrec_to_irec(rec, &irec);
-	if (xfs_alloc_check_irec(bs->cur, &irec) != NULL) {
+	if (xfs_alloc_check_irec(bs->cur->bc_ag.pag, &irec) != NULL) {
 		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 		return 0;
 	}
@@ -138,31 +150,27 @@ xchk_allocbt_rec(
 	return 0;
 }
 
-/* Scrub the freespace btrees for some AG. */
-STATIC int
+/* Scrub one of the freespace btrees for some AG. */
+int
 xchk_allocbt(
-	struct xfs_scrub	*sc,
-	xfs_btnum_t		which)
+	struct xfs_scrub	*sc)
 {
 	struct xchk_alloc	ca = { };
 	struct xfs_btree_cur	*cur;
 
-	cur = which == XFS_BTNUM_BNO ? sc->sa.bno_cur : sc->sa.cnt_cur;
-	return xchk_btree(sc, cur, xchk_allocbt_rec, &XFS_RMAP_OINFO_AG, &ca);
-}
-
-int
-xchk_bnobt(
-	struct xfs_scrub	*sc)
-{
-	return xchk_allocbt(sc, XFS_BTNUM_BNO);
-}
+	switch (sc->sm->sm_type) {
+	case XFS_SCRUB_TYPE_BNOBT:
+		cur = sc->sa.bno_cur;
+		break;
+	case XFS_SCRUB_TYPE_CNTBT:
+		cur = sc->sa.cnt_cur;
+		break;
+	default:
+		ASSERT(0);
+		return -EIO;
+	}
 
-int
-xchk_cntbt(
-	struct xfs_scrub	*sc)
-{
-	return xchk_allocbt(sc, XFS_BTNUM_CNT);
+	return xchk_btree(sc, cur, xchk_allocbt_rec, &XFS_RMAP_OINFO_AG, &ca);
 }
 
 /* xref check that the extent is not free */
diff --git a/fs/xfs/scrub/alloc_repair.c b/fs/xfs/scrub/alloc_repair.c
new file mode 100644
index 000000000000..45edda096869
--- /dev/null
+++ b/fs/xfs/scrub/alloc_repair.c
@@ -0,0 +1,934 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_btree_staging.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_alloc.h"
+#include "xfs_alloc_btree.h"
+#include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_inode.h"
+#include "xfs_refcount.h"
+#include "xfs_extent_busy.h"
+#include "xfs_health.h"
+#include "xfs_bmap.h"
+#include "xfs_ialloc.h"
+#include "xfs_ag.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/btree.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/bitmap.h"
+#include "scrub/agb_bitmap.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/newbt.h"
+#include "scrub/reap.h"
+
+/*
+ * Free Space Btree Repair
+ * =======================
+ *
+ * The reverse mappings are supposed to record all space usage for the entire
+ * AG.  Therefore, we can recreate the free extent records in an AG by looking
+ * for gaps in the physical extents recorded in the rmapbt.  These records are
+ * staged in @free_records.  Identifying the gaps is more difficult on a
+ * reflink filesystem because rmap records are allowed to overlap.
+ *
+ * Because the final step of building a new index is to free the space used by
+ * the old index, repair needs to find that space.  Unfortunately, all
+ * structures that live in the free space (bnobt, cntbt, rmapbt, agfl) share
+ * the same rmapbt owner code (OWN_AG), so this is not straightforward.
+ *
+ * The scan of the reverse mapping information records the space used by OWN_AG
+ * in @old_allocbt_blocks, which (at this stage) is somewhat misnamed.  While
+ * walking the rmapbt records, we create a second bitmap @not_allocbt_blocks to
+ * record all visited rmap btree blocks and all blocks owned by the AGFL.
+ *
+ * After that is where the definitions of old_allocbt_blocks shifts.  This
+ * expression identifies possible former bnobt/cntbt blocks:
+ *
+ *	(OWN_AG blocks) & ~(rmapbt blocks | agfl blocks);
+ *
+ * Substituting from above definitions, that becomes:
+ *
+ *	old_allocbt_blocks & ~not_allocbt_blocks
+ *
+ * The OWN_AG bitmap itself isn't needed after this point, so what we really do
+ * instead is:
+ *
+ *	old_allocbt_blocks &= ~not_allocbt_blocks;
+ *
+ * After this point, @old_allocbt_blocks is a bitmap of alleged former
+ * bnobt/cntbt blocks.  The xagb_bitmap_disunion operation modifies its first
+ * parameter in place to avoid copying records around.
+ *
+ * Next, some of the space described by @free_records are diverted to the newbt
+ * reservation and used to format new btree blocks.  The remaining records are
+ * written to the new btree indices.  We reconstruct both bnobt and cntbt at
+ * the same time since we've already done all the work.
+ *
+ * We use the prefix 'xrep_abt' here because we regenerate both free space
+ * allocation btrees at the same time.
+ */
+
+struct xrep_abt {
+	/* Blocks owned by the rmapbt or the agfl. */
+	struct xagb_bitmap	not_allocbt_blocks;
+
+	/* All OWN_AG blocks. */
+	struct xagb_bitmap	old_allocbt_blocks;
+
+	/*
+	 * New bnobt information.  All btree block reservations are added to
+	 * the reservation list in new_bnobt.
+	 */
+	struct xrep_newbt	new_bnobt;
+
+	/* new cntbt information */
+	struct xrep_newbt	new_cntbt;
+
+	/* Free space extents. */
+	struct xfarray		*free_records;
+
+	struct xfs_scrub	*sc;
+
+	/* Number of non-null records in @free_records. */
+	uint64_t		nr_real_records;
+
+	/* get_records()'s position in the free space record array. */
+	xfarray_idx_t		array_cur;
+
+	/*
+	 * Next block we anticipate seeing in the rmap records.  If the next
+	 * rmap record is greater than next_agbno, we have found unused space.
+	 */
+	xfs_agblock_t		next_agbno;
+
+	/* Number of free blocks in this AG. */
+	xfs_agblock_t		nr_blocks;
+
+	/* Longest free extent we found in the AG. */
+	xfs_agblock_t		longest;
+};
+
+/* Set up to repair AG free space btrees. */
+int
+xrep_setup_ag_allocbt(
+	struct xfs_scrub	*sc)
+{
+	unsigned int		busy_gen;
+
+	/*
+	 * Make sure the busy extent list is clear because we can't put extents
+	 * on there twice.
+	 */
+	busy_gen = READ_ONCE(sc->sa.pag->pagb_gen);
+	if (xfs_extent_busy_list_empty(sc->sa.pag))
+		return 0;
+
+	return xfs_extent_busy_flush(sc->tp, sc->sa.pag, busy_gen, 0);
+}
+
+/* Check for any obvious conflicts in the free extent. */
+STATIC int
+xrep_abt_check_free_ext(
+	struct xfs_scrub	*sc,
+	const struct xfs_alloc_rec_incore *rec)
+{
+	enum xbtree_recpacking	outcome;
+	int			error;
+
+	if (xfs_alloc_check_irec(sc->sa.pag, rec) != NULL)
+		return -EFSCORRUPTED;
+
+	/* Must not be an inode chunk. */
+	error = xfs_ialloc_has_inodes_at_extent(sc->sa.ino_cur,
+			rec->ar_startblock, rec->ar_blockcount, &outcome);
+	if (error)
+		return error;
+	if (outcome != XBTREE_RECPACKING_EMPTY)
+		return -EFSCORRUPTED;
+
+	/* Must not be shared or CoW staging. */
+	if (sc->sa.refc_cur) {
+		error = xfs_refcount_has_records(sc->sa.refc_cur,
+				XFS_REFC_DOMAIN_SHARED, rec->ar_startblock,
+				rec->ar_blockcount, &outcome);
+		if (error)
+			return error;
+		if (outcome != XBTREE_RECPACKING_EMPTY)
+			return -EFSCORRUPTED;
+
+		error = xfs_refcount_has_records(sc->sa.refc_cur,
+				XFS_REFC_DOMAIN_COW, rec->ar_startblock,
+				rec->ar_blockcount, &outcome);
+		if (error)
+			return error;
+		if (outcome != XBTREE_RECPACKING_EMPTY)
+			return -EFSCORRUPTED;
+	}
+
+	return 0;
+}
+
+/*
+ * Stash a free space record for all the space since the last bno we found
+ * all the way up to @end.
+ */
+static int
+xrep_abt_stash(
+	struct xrep_abt		*ra,
+	xfs_agblock_t		end)
+{
+	struct xfs_alloc_rec_incore arec = {
+		.ar_startblock	= ra->next_agbno,
+		.ar_blockcount	= end - ra->next_agbno,
+	};
+	struct xfs_scrub	*sc = ra->sc;
+	int			error = 0;
+
+	if (xchk_should_terminate(sc, &error))
+		return error;
+
+	error = xrep_abt_check_free_ext(ra->sc, &arec);
+	if (error)
+		return error;
+
+	trace_xrep_abt_found(sc->mp, sc->sa.pag->pag_agno, &arec);
+
+	error = xfarray_append(ra->free_records, &arec);
+	if (error)
+		return error;
+
+	ra->nr_blocks += arec.ar_blockcount;
+	return 0;
+}
+
+/* Record extents that aren't in use from gaps in the rmap records. */
+STATIC int
+xrep_abt_walk_rmap(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*rec,
+	void				*priv)
+{
+	struct xrep_abt			*ra = priv;
+	int				error;
+
+	/* Record all the OWN_AG blocks... */
+	if (rec->rm_owner == XFS_RMAP_OWN_AG) {
+		error = xagb_bitmap_set(&ra->old_allocbt_blocks,
+				rec->rm_startblock, rec->rm_blockcount);
+		if (error)
+			return error;
+	}
+
+	/* ...and all the rmapbt blocks... */
+	error = xagb_bitmap_set_btcur_path(&ra->not_allocbt_blocks, cur);
+	if (error)
+		return error;
+
+	/* ...and all the free space. */
+	if (rec->rm_startblock > ra->next_agbno) {
+		error = xrep_abt_stash(ra, rec->rm_startblock);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * rmap records can overlap on reflink filesystems, so project
+	 * next_agbno as far out into the AG space as we currently know about.
+	 */
+	ra->next_agbno = max_t(xfs_agblock_t, ra->next_agbno,
+			rec->rm_startblock + rec->rm_blockcount);
+	return 0;
+}
+
+/* Collect an AGFL block for the not-to-release list. */
+static int
+xrep_abt_walk_agfl(
+	struct xfs_mount	*mp,
+	xfs_agblock_t		agbno,
+	void			*priv)
+{
+	struct xrep_abt		*ra = priv;
+
+	return xagb_bitmap_set(&ra->not_allocbt_blocks, agbno, 1);
+}
+
+/*
+ * Compare two free space extents by block number.  We want to sort in order of
+ * increasing block number.
+ */
+static int
+xrep_bnobt_extent_cmp(
+	const void		*a,
+	const void		*b)
+{
+	const struct xfs_alloc_rec_incore *ap = a;
+	const struct xfs_alloc_rec_incore *bp = b;
+
+	if (ap->ar_startblock > bp->ar_startblock)
+		return 1;
+	else if (ap->ar_startblock < bp->ar_startblock)
+		return -1;
+	return 0;
+}
+
+/*
+ * Re-sort the free extents by block number so that we can put the records into
+ * the bnobt in the correct order.  Make sure the records do not overlap in
+ * physical space.
+ */
+STATIC int
+xrep_bnobt_sort_records(
+	struct xrep_abt			*ra)
+{
+	struct xfs_alloc_rec_incore	arec;
+	xfarray_idx_t			cur = XFARRAY_CURSOR_INIT;
+	xfs_agblock_t			next_agbno = 0;
+	int				error;
+
+	error = xfarray_sort(ra->free_records, xrep_bnobt_extent_cmp, 0);
+	if (error)
+		return error;
+
+	while ((error = xfarray_iter(ra->free_records, &cur, &arec)) == 1) {
+		if (arec.ar_startblock < next_agbno)
+			return -EFSCORRUPTED;
+
+		next_agbno = arec.ar_startblock + arec.ar_blockcount;
+	}
+
+	return error;
+}
+
+/*
+ * Compare two free space extents by length and then block number.  We want
+ * to sort first in order of increasing length and then in order of increasing
+ * block number.
+ */
+static int
+xrep_cntbt_extent_cmp(
+	const void			*a,
+	const void			*b)
+{
+	const struct xfs_alloc_rec_incore *ap = a;
+	const struct xfs_alloc_rec_incore *bp = b;
+
+	if (ap->ar_blockcount > bp->ar_blockcount)
+		return 1;
+	else if (ap->ar_blockcount < bp->ar_blockcount)
+		return -1;
+	return xrep_bnobt_extent_cmp(a, b);
+}
+
+/*
+ * Sort the free extents by length so so that we can put the records into the
+ * cntbt in the correct order.  Don't let userspace kill us if we're resorting
+ * after allocating btree blocks.
+ */
+STATIC int
+xrep_cntbt_sort_records(
+	struct xrep_abt			*ra,
+	bool				is_resort)
+{
+	return xfarray_sort(ra->free_records, xrep_cntbt_extent_cmp,
+			is_resort ? 0 : XFARRAY_SORT_KILLABLE);
+}
+
+/*
+ * Iterate all reverse mappings to find (1) the gaps between rmap records (all
+ * unowned space), (2) the OWN_AG extents (which encompass the free space
+ * btrees, the rmapbt, and the agfl), (3) the rmapbt blocks, and (4) the AGFL
+ * blocks.  The free space is (1) + (2) - (3) - (4).
+ */
+STATIC int
+xrep_abt_find_freespace(
+	struct xrep_abt		*ra)
+{
+	struct xfs_scrub	*sc = ra->sc;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_agf		*agf = sc->sa.agf_bp->b_addr;
+	struct xfs_buf		*agfl_bp;
+	xfs_agblock_t		agend;
+	int			error;
+
+	xagb_bitmap_init(&ra->not_allocbt_blocks);
+
+	xrep_ag_btcur_init(sc, &sc->sa);
+
+	/*
+	 * Iterate all the reverse mappings to find gaps in the physical
+	 * mappings, all the OWN_AG blocks, and all the rmapbt extents.
+	 */
+	error = xfs_rmap_query_all(sc->sa.rmap_cur, xrep_abt_walk_rmap, ra);
+	if (error)
+		goto err;
+
+	/* Insert a record for space between the last rmap and EOAG. */
+	agend = be32_to_cpu(agf->agf_length);
+	if (ra->next_agbno < agend) {
+		error = xrep_abt_stash(ra, agend);
+		if (error)
+			goto err;
+	}
+
+	/* Collect all the AGFL blocks. */
+	error = xfs_alloc_read_agfl(sc->sa.pag, sc->tp, &agfl_bp);
+	if (error)
+		goto err;
+
+	error = xfs_agfl_walk(mp, agf, agfl_bp, xrep_abt_walk_agfl, ra);
+	if (error)
+		goto err_agfl;
+
+	/* Compute the old bnobt/cntbt blocks. */
+	error = xagb_bitmap_disunion(&ra->old_allocbt_blocks,
+			&ra->not_allocbt_blocks);
+	if (error)
+		goto err_agfl;
+
+	ra->nr_real_records = xfarray_length(ra->free_records);
+err_agfl:
+	xfs_trans_brelse(sc->tp, agfl_bp);
+err:
+	xchk_ag_btcur_free(&sc->sa);
+	xagb_bitmap_destroy(&ra->not_allocbt_blocks);
+	return error;
+}
+
+/*
+ * We're going to use the observed free space records to reserve blocks for the
+ * new free space btrees, so we play an iterative game where we try to converge
+ * on the number of blocks we need:
+ *
+ * 1. Estimate how many blocks we'll need to store the records.
+ * 2. If the first free record has more blocks than we need, we're done.
+ *    We will have to re-sort the records prior to building the cntbt.
+ * 3. If that record has exactly the number of blocks we need, null out the
+ *    record.  We're done.
+ * 4. Otherwise, we still need more blocks.  Null out the record, subtract its
+ *    length from the number of blocks we need, and go back to step 1.
+ *
+ * Fortunately, we don't have to do any transaction work to play this game, so
+ * we don't have to tear down the staging cursors.
+ */
+STATIC int
+xrep_abt_reserve_space(
+	struct xrep_abt		*ra,
+	struct xfs_btree_cur	*bno_cur,
+	struct xfs_btree_cur	*cnt_cur,
+	bool			*needs_resort)
+{
+	struct xfs_scrub	*sc = ra->sc;
+	xfarray_idx_t		record_nr;
+	unsigned int		allocated = 0;
+	int			error = 0;
+
+	record_nr = xfarray_length(ra->free_records) - 1;
+	do {
+		struct xfs_alloc_rec_incore arec;
+		uint64_t		required;
+		unsigned int		desired;
+		unsigned int		len;
+
+		/* Compute how many blocks we'll need. */
+		error = xfs_btree_bload_compute_geometry(cnt_cur,
+				&ra->new_cntbt.bload, ra->nr_real_records);
+		if (error)
+			break;
+
+		error = xfs_btree_bload_compute_geometry(bno_cur,
+				&ra->new_bnobt.bload, ra->nr_real_records);
+		if (error)
+			break;
+
+		/* How many btree blocks do we need to store all records? */
+		required = ra->new_bnobt.bload.nr_blocks +
+			   ra->new_cntbt.bload.nr_blocks;
+		ASSERT(required < INT_MAX);
+
+		/* If we've reserved enough blocks, we're done. */
+		if (allocated >= required)
+			break;
+
+		desired = required - allocated;
+
+		/* We need space but there's none left; bye! */
+		if (ra->nr_real_records == 0) {
+			error = -ENOSPC;
+			break;
+		}
+
+		/* Grab the first record from the list. */
+		error = xfarray_load(ra->free_records, record_nr, &arec);
+		if (error)
+			break;
+
+		ASSERT(arec.ar_blockcount <= UINT_MAX);
+		len = min_t(unsigned int, arec.ar_blockcount, desired);
+
+		trace_xrep_newbt_alloc_ag_blocks(sc->mp, sc->sa.pag->pag_agno,
+				arec.ar_startblock, len, XFS_RMAP_OWN_AG);
+
+		error = xrep_newbt_add_extent(&ra->new_bnobt, sc->sa.pag,
+				arec.ar_startblock, len);
+		if (error)
+			break;
+		allocated += len;
+		ra->nr_blocks -= len;
+
+		if (arec.ar_blockcount > desired) {
+			/*
+			 * Record has more space than we need.  The number of
+			 * free records doesn't change, so shrink the free
+			 * record, inform the caller that the records are no
+			 * longer sorted by length, and exit.
+			 */
+			arec.ar_startblock += desired;
+			arec.ar_blockcount -= desired;
+			error = xfarray_store(ra->free_records, record_nr,
+					&arec);
+			if (error)
+				break;
+
+			*needs_resort = true;
+			return 0;
+		}
+
+		/*
+		 * We're going to use up the entire record, so unset it and
+		 * move on to the next one.  This changes the number of free
+		 * records (but doesn't break the sorting order), so we must
+		 * go around the loop once more to re-run _bload_init.
+		 */
+		error = xfarray_unset(ra->free_records, record_nr);
+		if (error)
+			break;
+		ra->nr_real_records--;
+		record_nr--;
+	} while (1);
+
+	return error;
+}
+
+STATIC int
+xrep_abt_dispose_one(
+	struct xrep_abt		*ra,
+	struct xrep_newbt_resv	*resv)
+{
+	struct xfs_scrub	*sc = ra->sc;
+	struct xfs_perag	*pag = sc->sa.pag;
+	xfs_agblock_t		free_agbno = resv->agbno + resv->used;
+	xfs_extlen_t		free_aglen = resv->len - resv->used;
+	int			error;
+
+	ASSERT(pag == resv->pag);
+
+	/* Add a deferred rmap for each extent we used. */
+	if (resv->used > 0)
+		xfs_rmap_alloc_extent(sc->tp, pag->pag_agno, resv->agbno,
+				resv->used, XFS_RMAP_OWN_AG);
+
+	/*
+	 * For each reserved btree block we didn't use, add it to the free
+	 * space btree.  We didn't touch fdblocks when we reserved them, so
+	 * we don't touch it now.
+	 */
+	if (free_aglen == 0)
+		return 0;
+
+	trace_xrep_newbt_free_blocks(sc->mp, resv->pag->pag_agno, free_agbno,
+			free_aglen, ra->new_bnobt.oinfo.oi_owner);
+
+	error = __xfs_free_extent(sc->tp, resv->pag, free_agbno, free_aglen,
+			&ra->new_bnobt.oinfo, XFS_AG_RESV_IGNORE, true);
+	if (error)
+		return error;
+
+	return xrep_defer_finish(sc);
+}
+
+/*
+ * Deal with all the space we reserved.  Blocks that were allocated for the
+ * free space btrees need to have a (deferred) rmap added for the OWN_AG
+ * allocation, and blocks that didn't get used can be freed via the usual
+ * (deferred) means.
+ */
+STATIC void
+xrep_abt_dispose_reservations(
+	struct xrep_abt		*ra,
+	int			error)
+{
+	struct xrep_newbt_resv	*resv, *n;
+
+	if (error)
+		goto junkit;
+
+	list_for_each_entry_safe(resv, n, &ra->new_bnobt.resv_list, list) {
+		error = xrep_abt_dispose_one(ra, resv);
+		if (error)
+			goto junkit;
+	}
+
+junkit:
+	list_for_each_entry_safe(resv, n, &ra->new_bnobt.resv_list, list) {
+		xfs_perag_put(resv->pag);
+		list_del(&resv->list);
+		kfree(resv);
+	}
+
+	xrep_newbt_cancel(&ra->new_bnobt);
+	xrep_newbt_cancel(&ra->new_cntbt);
+}
+
+/* Retrieve free space data for bulk load. */
+STATIC int
+xrep_abt_get_records(
+	struct xfs_btree_cur		*cur,
+	unsigned int			idx,
+	struct xfs_btree_block		*block,
+	unsigned int			nr_wanted,
+	void				*priv)
+{
+	struct xfs_alloc_rec_incore	*arec = &cur->bc_rec.a;
+	struct xrep_abt			*ra = priv;
+	union xfs_btree_rec		*block_rec;
+	unsigned int			loaded;
+	int				error;
+
+	for (loaded = 0; loaded < nr_wanted; loaded++, idx++) {
+		error = xfarray_load_next(ra->free_records, &ra->array_cur,
+				arec);
+		if (error)
+			return error;
+
+		ra->longest = max(ra->longest, arec->ar_blockcount);
+
+		block_rec = xfs_btree_rec_addr(cur, idx, block);
+		cur->bc_ops->init_rec_from_cur(cur, block_rec);
+	}
+
+	return loaded;
+}
+
+/* Feed one of the new btree blocks to the bulk loader. */
+STATIC int
+xrep_abt_claim_block(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr,
+	void			*priv)
+{
+	struct xrep_abt		*ra = priv;
+
+	return xrep_newbt_claim_block(cur, &ra->new_bnobt, ptr);
+}
+
+/*
+ * Reset the AGF counters to reflect the free space btrees that we just
+ * rebuilt, then reinitialize the per-AG data.
+ */
+STATIC int
+xrep_abt_reset_counters(
+	struct xrep_abt		*ra)
+{
+	struct xfs_scrub	*sc = ra->sc;
+	struct xfs_perag	*pag = sc->sa.pag;
+	struct xfs_agf		*agf = sc->sa.agf_bp->b_addr;
+	unsigned int		freesp_btreeblks = 0;
+
+	/*
+	 * Compute the contribution to agf_btreeblks for the new free space
+	 * btrees.  This is the computed btree size minus anything we didn't
+	 * use.
+	 */
+	freesp_btreeblks += ra->new_bnobt.bload.nr_blocks - 1;
+	freesp_btreeblks += ra->new_cntbt.bload.nr_blocks - 1;
+
+	freesp_btreeblks -= xrep_newbt_unused_blocks(&ra->new_bnobt);
+	freesp_btreeblks -= xrep_newbt_unused_blocks(&ra->new_cntbt);
+
+	/*
+	 * The AGF header contains extra information related to the free space
+	 * btrees, so we must update those fields here.
+	 */
+	agf->agf_btreeblks = cpu_to_be32(freesp_btreeblks +
+				(be32_to_cpu(agf->agf_rmap_blocks) - 1));
+	agf->agf_freeblks = cpu_to_be32(ra->nr_blocks);
+	agf->agf_longest = cpu_to_be32(ra->longest);
+	xfs_alloc_log_agf(sc->tp, sc->sa.agf_bp, XFS_AGF_BTREEBLKS |
+						 XFS_AGF_LONGEST |
+						 XFS_AGF_FREEBLKS);
+
+	/*
+	 * After we commit the new btree to disk, it is possible that the
+	 * process to reap the old btree blocks will race with the AIL trying
+	 * to checkpoint the old btree blocks into the filesystem.  If the new
+	 * tree is shorter than the old one, the allocbt write verifier will
+	 * fail and the AIL will shut down the filesystem.
+	 *
+	 * To avoid this, save the old incore btree height values as the alt
+	 * height values before re-initializing the perag info from the updated
+	 * AGF to capture all the new values.
+	 */
+	pag->pagf_repair_levels[XFS_BTNUM_BNOi] = pag->pagf_levels[XFS_BTNUM_BNOi];
+	pag->pagf_repair_levels[XFS_BTNUM_CNTi] = pag->pagf_levels[XFS_BTNUM_CNTi];
+
+	/* Reinitialize with the values we just logged. */
+	return xrep_reinit_pagf(sc);
+}
+
+/*
+ * Use the collected free space information to stage new free space btrees.
+ * If this is successful we'll return with the new btree root
+ * information logged to the repair transaction but not yet committed.
+ */
+STATIC int
+xrep_abt_build_new_trees(
+	struct xrep_abt		*ra)
+{
+	struct xfs_scrub	*sc = ra->sc;
+	struct xfs_btree_cur	*bno_cur;
+	struct xfs_btree_cur	*cnt_cur;
+	struct xfs_perag	*pag = sc->sa.pag;
+	bool			needs_resort = false;
+	int			error;
+
+	/*
+	 * Sort the free extents by length so that we can set up the free space
+	 * btrees in as few extents as possible.  This reduces the amount of
+	 * deferred rmap / free work we have to do at the end.
+	 */
+	error = xrep_cntbt_sort_records(ra, false);
+	if (error)
+		return error;
+
+	/*
+	 * Prepare to construct the new btree by reserving disk space for the
+	 * new btree and setting up all the accounting information we'll need
+	 * to root the new btree while it's under construction and before we
+	 * attach it to the AG header.
+	 */
+	xrep_newbt_init_bare(&ra->new_bnobt, sc);
+	xrep_newbt_init_bare(&ra->new_cntbt, sc);
+
+	ra->new_bnobt.bload.get_records = xrep_abt_get_records;
+	ra->new_cntbt.bload.get_records = xrep_abt_get_records;
+
+	ra->new_bnobt.bload.claim_block = xrep_abt_claim_block;
+	ra->new_cntbt.bload.claim_block = xrep_abt_claim_block;
+
+	/* Allocate cursors for the staged btrees. */
+	bno_cur = xfs_allocbt_stage_cursor(sc->mp, &ra->new_bnobt.afake,
+			pag, XFS_BTNUM_BNO);
+	cnt_cur = xfs_allocbt_stage_cursor(sc->mp, &ra->new_cntbt.afake,
+			pag, XFS_BTNUM_CNT);
+
+	/* Last chance to abort before we start committing fixes. */
+	if (xchk_should_terminate(sc, &error))
+		goto err_cur;
+
+	/* Reserve the space we'll need for the new btrees. */
+	error = xrep_abt_reserve_space(ra, bno_cur, cnt_cur, &needs_resort);
+	if (error)
+		goto err_cur;
+
+	/*
+	 * If we need to re-sort the free extents by length, do so so that we
+	 * can put the records into the cntbt in the correct order.
+	 */
+	if (needs_resort) {
+		error = xrep_cntbt_sort_records(ra, needs_resort);
+		if (error)
+			goto err_cur;
+	}
+
+	/*
+	 * Due to btree slack factors, it's possible for a new btree to be one
+	 * level taller than the old btree.  Update the alternate incore btree
+	 * height so that we don't trip the verifiers when writing the new
+	 * btree blocks to disk.
+	 */
+	pag->pagf_repair_levels[XFS_BTNUM_BNOi] =
+					ra->new_bnobt.bload.btree_height;
+	pag->pagf_repair_levels[XFS_BTNUM_CNTi] =
+					ra->new_cntbt.bload.btree_height;
+
+	/* Load the free space by length tree. */
+	ra->array_cur = XFARRAY_CURSOR_INIT;
+	ra->longest = 0;
+	error = xfs_btree_bload(cnt_cur, &ra->new_cntbt.bload, ra);
+	if (error)
+		goto err_levels;
+
+	error = xrep_bnobt_sort_records(ra);
+	if (error)
+		return error;
+
+	/* Load the free space by block number tree. */
+	ra->array_cur = XFARRAY_CURSOR_INIT;
+	error = xfs_btree_bload(bno_cur, &ra->new_bnobt.bload, ra);
+	if (error)
+		goto err_levels;
+
+	/*
+	 * Install the new btrees in the AG header.  After this point the old
+	 * btrees are no longer accessible and the new trees are live.
+	 */
+	xfs_allocbt_commit_staged_btree(bno_cur, sc->tp, sc->sa.agf_bp);
+	xfs_btree_del_cursor(bno_cur, 0);
+	xfs_allocbt_commit_staged_btree(cnt_cur, sc->tp, sc->sa.agf_bp);
+	xfs_btree_del_cursor(cnt_cur, 0);
+
+	/* Reset the AGF counters now that we've changed the btree shape. */
+	error = xrep_abt_reset_counters(ra);
+	if (error)
+		goto err_newbt;
+
+	/* Dispose of any unused blocks and the accounting information. */
+	xrep_abt_dispose_reservations(ra, error);
+
+	return xrep_roll_ag_trans(sc);
+
+err_levels:
+	pag->pagf_repair_levels[XFS_BTNUM_BNOi] = 0;
+	pag->pagf_repair_levels[XFS_BTNUM_CNTi] = 0;
+err_cur:
+	xfs_btree_del_cursor(cnt_cur, error);
+	xfs_btree_del_cursor(bno_cur, error);
+err_newbt:
+	xrep_abt_dispose_reservations(ra, error);
+	return error;
+}
+
+/*
+ * Now that we've logged the roots of the new btrees, invalidate all of the
+ * old blocks and free them.
+ */
+STATIC int
+xrep_abt_remove_old_trees(
+	struct xrep_abt		*ra)
+{
+	struct xfs_perag	*pag = ra->sc->sa.pag;
+	int			error;
+
+	/* Free the old btree blocks if they're not in use. */
+	error = xrep_reap_agblocks(ra->sc, &ra->old_allocbt_blocks,
+			&XFS_RMAP_OINFO_AG, XFS_AG_RESV_IGNORE);
+	if (error)
+		return error;
+
+	/*
+	 * Now that we've zapped all the old allocbt blocks we can turn off
+	 * the alternate height mechanism.
+	 */
+	pag->pagf_repair_levels[XFS_BTNUM_BNOi] = 0;
+	pag->pagf_repair_levels[XFS_BTNUM_CNTi] = 0;
+	return 0;
+}
+
+/* Repair the freespace btrees for some AG. */
+int
+xrep_allocbt(
+	struct xfs_scrub	*sc)
+{
+	struct xrep_abt		*ra;
+	struct xfs_mount	*mp = sc->mp;
+	char			*descr;
+	int			error;
+
+	/* We require the rmapbt to rebuild anything. */
+	if (!xfs_has_rmapbt(mp))
+		return -EOPNOTSUPP;
+
+	ra = kzalloc(sizeof(struct xrep_abt), XCHK_GFP_FLAGS);
+	if (!ra)
+		return -ENOMEM;
+	ra->sc = sc;
+
+	/* We rebuild both data structures. */
+	sc->sick_mask = XFS_SICK_AG_BNOBT | XFS_SICK_AG_CNTBT;
+
+	/*
+	 * Make sure the busy extent list is clear because we can't put extents
+	 * on there twice.  In theory we cleared this before we started, but
+	 * let's not risk the filesystem.
+	 */
+	if (!xfs_extent_busy_list_empty(sc->sa.pag)) {
+		error = -EDEADLOCK;
+		goto out_ra;
+	}
+
+	/* Set up enough storage to handle maximally fragmented free space. */
+	descr = xchk_xfile_ag_descr(sc, "free space records");
+	error = xfarray_create(descr, mp->m_sb.sb_agblocks / 2,
+			sizeof(struct xfs_alloc_rec_incore),
+			&ra->free_records);
+	kfree(descr);
+	if (error)
+		goto out_ra;
+
+	/* Collect the free space data and find the old btree blocks. */
+	xagb_bitmap_init(&ra->old_allocbt_blocks);
+	error = xrep_abt_find_freespace(ra);
+	if (error)
+		goto out_bitmap;
+
+	/* Rebuild the free space information. */
+	error = xrep_abt_build_new_trees(ra);
+	if (error)
+		goto out_bitmap;
+
+	/* Kill the old trees. */
+	error = xrep_abt_remove_old_trees(ra);
+	if (error)
+		goto out_bitmap;
+
+out_bitmap:
+	xagb_bitmap_destroy(&ra->old_allocbt_blocks);
+	xfarray_destroy(ra->free_records);
+out_ra:
+	kfree(ra);
+	return error;
+}
+
+/* Make sure both btrees are ok after we've rebuilt them. */
+int
+xrep_revalidate_allocbt(
+	struct xfs_scrub	*sc)
+{
+	__u32			old_type = sc->sm->sm_type;
+	int			error;
+
+	/*
+	 * We must update sm_type temporarily so that the tree-to-tree cross
+	 * reference checks will work in the correct direction, and also so
+	 * that tracing will report correctly if there are more errors.
+	 */
+	sc->sm->sm_type = XFS_SCRUB_TYPE_BNOBT;
+	error = xchk_allocbt(sc);
+	if (error)
+		goto out;
+
+	sc->sm->sm_type = XFS_SCRUB_TYPE_CNTBT;
+	error = xchk_allocbt(sc);
+out:
+	sc->sm->sm_type = old_type;
+	return error;
+}
diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index 6c16d9530cca..83c7feb38714 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -527,28 +527,23 @@ xchk_xattr_check_sf(
 	struct xfs_scrub		*sc)
 {
 	struct xchk_xattr_buf		*ab = sc->buf;
-	struct xfs_attr_shortform	*sf;
-	struct xfs_attr_sf_entry	*sfe;
+	struct xfs_ifork		*ifp = &sc->ip->i_af;
+	struct xfs_attr_sf_hdr		*sf = ifp->if_data;
+	struct xfs_attr_sf_entry	*sfe = xfs_attr_sf_firstentry(sf);
 	struct xfs_attr_sf_entry	*next;
-	struct xfs_ifork		*ifp;
-	unsigned char			*end;
+	unsigned char			*end = ifp->if_data + ifp->if_bytes;
 	int				i;
 	int				error = 0;
 
-	ifp = xfs_ifork_ptr(sc->ip, XFS_ATTR_FORK);
-
 	bitmap_zero(ab->usedmap, ifp->if_bytes);
-	sf = (struct xfs_attr_shortform *)sc->ip->i_af.if_u1.if_data;
-	end = (unsigned char *)ifp->if_u1.if_data + ifp->if_bytes;
-	xchk_xattr_set_map(sc, ab->usedmap, 0, sizeof(sf->hdr));
+	xchk_xattr_set_map(sc, ab->usedmap, 0, sizeof(*sf));
 
-	sfe = &sf->list[0];
 	if ((unsigned char *)sfe > end) {
 		xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, 0);
 		return 0;
 	}
 
-	for (i = 0; i < sf->hdr.count; i++) {
+	for (i = 0; i < sf->count; i++) {
 		unsigned char		*name = sfe->nameval;
 		unsigned char		*value = &sfe->nameval[sfe->namelen];
 
diff --git a/fs/xfs/scrub/bitmap.c b/fs/xfs/scrub/bitmap.c
index e0c89a9a0ca0..1449bb5262d9 100644
--- a/fs/xfs/scrub/bitmap.c
+++ b/fs/xfs/scrub/bitmap.c
@@ -16,7 +16,9 @@
 
 #include <linux/interval_tree_generic.h>
 
-struct xbitmap_node {
+/* u64 bitmap */
+
+struct xbitmap64_node {
 	struct rb_node	bn_rbnode;
 
 	/* First set bit of this interval and subtree. */
@@ -39,72 +41,72 @@ struct xbitmap_node {
  * forward-declare them anyway for clarity.
  */
 static inline void
-xbitmap_tree_insert(struct xbitmap_node *node, struct rb_root_cached *root);
+xbitmap64_tree_insert(struct xbitmap64_node *node, struct rb_root_cached *root);
 
 static inline void
-xbitmap_tree_remove(struct xbitmap_node *node, struct rb_root_cached *root);
+xbitmap64_tree_remove(struct xbitmap64_node *node, struct rb_root_cached *root);
 
-static inline struct xbitmap_node *
-xbitmap_tree_iter_first(struct rb_root_cached *root, uint64_t start,
+static inline struct xbitmap64_node *
+xbitmap64_tree_iter_first(struct rb_root_cached *root, uint64_t start,
 			uint64_t last);
 
-static inline struct xbitmap_node *
-xbitmap_tree_iter_next(struct xbitmap_node *node, uint64_t start,
+static inline struct xbitmap64_node *
+xbitmap64_tree_iter_next(struct xbitmap64_node *node, uint64_t start,
 		       uint64_t last);
 
-INTERVAL_TREE_DEFINE(struct xbitmap_node, bn_rbnode, uint64_t,
-		__bn_subtree_last, START, LAST, static inline, xbitmap_tree)
+INTERVAL_TREE_DEFINE(struct xbitmap64_node, bn_rbnode, uint64_t,
+		__bn_subtree_last, START, LAST, static inline, xbitmap64_tree)
 
 /* Iterate each interval of a bitmap.  Do not change the bitmap. */
-#define for_each_xbitmap_extent(bn, bitmap) \
+#define for_each_xbitmap64_extent(bn, bitmap) \
 	for ((bn) = rb_entry_safe(rb_first(&(bitmap)->xb_root.rb_root), \
-				   struct xbitmap_node, bn_rbnode); \
+				   struct xbitmap64_node, bn_rbnode); \
 	     (bn) != NULL; \
 	     (bn) = rb_entry_safe(rb_next(&(bn)->bn_rbnode), \
-				   struct xbitmap_node, bn_rbnode))
+				   struct xbitmap64_node, bn_rbnode))
 
 /* Clear a range of this bitmap. */
 int
-xbitmap_clear(
-	struct xbitmap		*bitmap,
+xbitmap64_clear(
+	struct xbitmap64	*bitmap,
 	uint64_t		start,
 	uint64_t		len)
 {
-	struct xbitmap_node	*bn;
-	struct xbitmap_node	*new_bn;
+	struct xbitmap64_node	*bn;
+	struct xbitmap64_node	*new_bn;
 	uint64_t		last = start + len - 1;
 
-	while ((bn = xbitmap_tree_iter_first(&bitmap->xb_root, start, last))) {
+	while ((bn = xbitmap64_tree_iter_first(&bitmap->xb_root, start, last))) {
 		if (bn->bn_start < start && bn->bn_last > last) {
 			uint64_t	old_last = bn->bn_last;
 
 			/* overlaps with the entire clearing range */
-			xbitmap_tree_remove(bn, &bitmap->xb_root);
+			xbitmap64_tree_remove(bn, &bitmap->xb_root);
 			bn->bn_last = start - 1;
-			xbitmap_tree_insert(bn, &bitmap->xb_root);
+			xbitmap64_tree_insert(bn, &bitmap->xb_root);
 
 			/* add an extent */
-			new_bn = kmalloc(sizeof(struct xbitmap_node),
+			new_bn = kmalloc(sizeof(struct xbitmap64_node),
 					XCHK_GFP_FLAGS);
 			if (!new_bn)
 				return -ENOMEM;
 			new_bn->bn_start = last + 1;
 			new_bn->bn_last = old_last;
-			xbitmap_tree_insert(new_bn, &bitmap->xb_root);
+			xbitmap64_tree_insert(new_bn, &bitmap->xb_root);
 		} else if (bn->bn_start < start) {
 			/* overlaps with the left side of the clearing range */
-			xbitmap_tree_remove(bn, &bitmap->xb_root);
+			xbitmap64_tree_remove(bn, &bitmap->xb_root);
 			bn->bn_last = start - 1;
-			xbitmap_tree_insert(bn, &bitmap->xb_root);
+			xbitmap64_tree_insert(bn, &bitmap->xb_root);
 		} else if (bn->bn_last > last) {
 			/* overlaps with the right side of the clearing range */
-			xbitmap_tree_remove(bn, &bitmap->xb_root);
+			xbitmap64_tree_remove(bn, &bitmap->xb_root);
 			bn->bn_start = last + 1;
-			xbitmap_tree_insert(bn, &bitmap->xb_root);
+			xbitmap64_tree_insert(bn, &bitmap->xb_root);
 			break;
 		} else {
 			/* in the middle of the clearing range */
-			xbitmap_tree_remove(bn, &bitmap->xb_root);
+			xbitmap64_tree_remove(bn, &bitmap->xb_root);
 			kfree(bn);
 		}
 	}
@@ -114,59 +116,59 @@ xbitmap_clear(
 
 /* Set a range of this bitmap. */
 int
-xbitmap_set(
-	struct xbitmap		*bitmap,
+xbitmap64_set(
+	struct xbitmap64	*bitmap,
 	uint64_t		start,
 	uint64_t		len)
 {
-	struct xbitmap_node	*left;
-	struct xbitmap_node	*right;
+	struct xbitmap64_node	*left;
+	struct xbitmap64_node	*right;
 	uint64_t		last = start + len - 1;
 	int			error;
 
 	/* Is this whole range already set? */
-	left = xbitmap_tree_iter_first(&bitmap->xb_root, start, last);
+	left = xbitmap64_tree_iter_first(&bitmap->xb_root, start, last);
 	if (left && left->bn_start <= start && left->bn_last >= last)
 		return 0;
 
 	/* Clear out everything in the range we want to set. */
-	error = xbitmap_clear(bitmap, start, len);
+	error = xbitmap64_clear(bitmap, start, len);
 	if (error)
 		return error;
 
 	/* Do we have a left-adjacent extent? */
-	left = xbitmap_tree_iter_first(&bitmap->xb_root, start - 1, start - 1);
+	left = xbitmap64_tree_iter_first(&bitmap->xb_root, start - 1, start - 1);
 	ASSERT(!left || left->bn_last + 1 == start);
 
 	/* Do we have a right-adjacent extent? */
-	right = xbitmap_tree_iter_first(&bitmap->xb_root, last + 1, last + 1);
+	right = xbitmap64_tree_iter_first(&bitmap->xb_root, last + 1, last + 1);
 	ASSERT(!right || right->bn_start == last + 1);
 
 	if (left && right) {
 		/* combine left and right adjacent extent */
-		xbitmap_tree_remove(left, &bitmap->xb_root);
-		xbitmap_tree_remove(right, &bitmap->xb_root);
+		xbitmap64_tree_remove(left, &bitmap->xb_root);
+		xbitmap64_tree_remove(right, &bitmap->xb_root);
 		left->bn_last = right->bn_last;
-		xbitmap_tree_insert(left, &bitmap->xb_root);
+		xbitmap64_tree_insert(left, &bitmap->xb_root);
 		kfree(right);
 	} else if (left) {
 		/* combine with left extent */
-		xbitmap_tree_remove(left, &bitmap->xb_root);
+		xbitmap64_tree_remove(left, &bitmap->xb_root);
 		left->bn_last = last;
-		xbitmap_tree_insert(left, &bitmap->xb_root);
+		xbitmap64_tree_insert(left, &bitmap->xb_root);
 	} else if (right) {
 		/* combine with right extent */
-		xbitmap_tree_remove(right, &bitmap->xb_root);
+		xbitmap64_tree_remove(right, &bitmap->xb_root);
 		right->bn_start = start;
-		xbitmap_tree_insert(right, &bitmap->xb_root);
+		xbitmap64_tree_insert(right, &bitmap->xb_root);
 	} else {
 		/* add an extent */
-		left = kmalloc(sizeof(struct xbitmap_node), XCHK_GFP_FLAGS);
+		left = kmalloc(sizeof(struct xbitmap64_node), XCHK_GFP_FLAGS);
 		if (!left)
 			return -ENOMEM;
 		left->bn_start = start;
 		left->bn_last = last;
-		xbitmap_tree_insert(left, &bitmap->xb_root);
+		xbitmap64_tree_insert(left, &bitmap->xb_root);
 	}
 
 	return 0;
@@ -174,21 +176,21 @@ xbitmap_set(
 
 /* Free everything related to this bitmap. */
 void
-xbitmap_destroy(
-	struct xbitmap		*bitmap)
+xbitmap64_destroy(
+	struct xbitmap64	*bitmap)
 {
-	struct xbitmap_node	*bn;
+	struct xbitmap64_node	*bn;
 
-	while ((bn = xbitmap_tree_iter_first(&bitmap->xb_root, 0, -1ULL))) {
-		xbitmap_tree_remove(bn, &bitmap->xb_root);
+	while ((bn = xbitmap64_tree_iter_first(&bitmap->xb_root, 0, -1ULL))) {
+		xbitmap64_tree_remove(bn, &bitmap->xb_root);
 		kfree(bn);
 	}
 }
 
 /* Set up a per-AG block bitmap. */
 void
-xbitmap_init(
-	struct xbitmap		*bitmap)
+xbitmap64_init(
+	struct xbitmap64	*bitmap)
 {
 	bitmap->xb_root = RB_ROOT_CACHED;
 }
@@ -208,18 +210,18 @@ xbitmap_init(
  * This is the logical equivalent of bitmap &= ~sub.
  */
 int
-xbitmap_disunion(
-	struct xbitmap		*bitmap,
-	struct xbitmap		*sub)
+xbitmap64_disunion(
+	struct xbitmap64	*bitmap,
+	struct xbitmap64	*sub)
 {
-	struct xbitmap_node	*bn;
+	struct xbitmap64_node	*bn;
 	int			error;
 
-	if (xbitmap_empty(bitmap) || xbitmap_empty(sub))
+	if (xbitmap64_empty(bitmap) || xbitmap64_empty(sub))
 		return 0;
 
-	for_each_xbitmap_extent(bn, sub) {
-		error = xbitmap_clear(bitmap, bn->bn_start,
+	for_each_xbitmap64_extent(bn, sub) {
+		error = xbitmap64_clear(bitmap, bn->bn_start,
 				bn->bn_last - bn->bn_start + 1);
 		if (error)
 			return error;
@@ -228,88 +230,273 @@ xbitmap_disunion(
 	return 0;
 }
 
+/* How many bits are set in this bitmap? */
+uint64_t
+xbitmap64_hweight(
+	struct xbitmap64	*bitmap)
+{
+	struct xbitmap64_node	*bn;
+	uint64_t		ret = 0;
+
+	for_each_xbitmap64_extent(bn, bitmap)
+		ret += bn->bn_last - bn->bn_start + 1;
+
+	return ret;
+}
+
+/* Call a function for every run of set bits in this bitmap. */
+int
+xbitmap64_walk(
+	struct xbitmap64	*bitmap,
+	xbitmap64_walk_fn		fn,
+	void			*priv)
+{
+	struct xbitmap64_node	*bn;
+	int			error = 0;
+
+	for_each_xbitmap64_extent(bn, bitmap) {
+		error = fn(bn->bn_start, bn->bn_last - bn->bn_start + 1, priv);
+		if (error)
+			break;
+	}
+
+	return error;
+}
+
+/* Does this bitmap have no bits set at all? */
+bool
+xbitmap64_empty(
+	struct xbitmap64	*bitmap)
+{
+	return bitmap->xb_root.rb_root.rb_node == NULL;
+}
+
+/* Is the start of the range set or clear?  And for how long? */
+bool
+xbitmap64_test(
+	struct xbitmap64	*bitmap,
+	uint64_t		start,
+	uint64_t		*len)
+{
+	struct xbitmap64_node	*bn;
+	uint64_t		last = start + *len - 1;
+
+	bn = xbitmap64_tree_iter_first(&bitmap->xb_root, start, last);
+	if (!bn)
+		return false;
+	if (bn->bn_start <= start) {
+		if (bn->bn_last < last)
+			*len = bn->bn_last - start + 1;
+		return true;
+	}
+	*len = bn->bn_start - start;
+	return false;
+}
+
+/* u32 bitmap */
+
+struct xbitmap32_node {
+	struct rb_node	bn_rbnode;
+
+	/* First set bit of this interval and subtree. */
+	uint32_t	bn_start;
+
+	/* Last set bit of this interval. */
+	uint32_t	bn_last;
+
+	/* Last set bit of this subtree.  Do not touch this. */
+	uint32_t	__bn_subtree_last;
+};
+
+/* Define our own interval tree type with uint32_t parameters. */
+
 /*
- * Record all btree blocks seen while iterating all records of a btree.
- *
- * We know that the btree query_all function starts at the left edge and walks
- * towards the right edge of the tree.  Therefore, we know that we can walk up
- * the btree cursor towards the root; if the pointer for a given level points
- * to the first record/key in that block, we haven't seen this block before;
- * and therefore we need to remember that we saw this block in the btree.
- *
- * So if our btree is:
- *
- *    4
- *  / | \
- * 1  2  3
- *
- * Pretend for this example that each leaf block has 100 btree records.  For
- * the first btree record, we'll observe that bc_levels[0].ptr == 1, so we
- * record that we saw block 1.  Then we observe that bc_levels[1].ptr == 1, so
- * we record block 4.  The list is [1, 4].
- *
- * For the second btree record, we see that bc_levels[0].ptr == 2, so we exit
- * the loop.  The list remains [1, 4].
- *
- * For the 101st btree record, we've moved onto leaf block 2.  Now
- * bc_levels[0].ptr == 1 again, so we record that we saw block 2.  We see that
- * bc_levels[1].ptr == 2, so we exit the loop.  The list is now [1, 4, 2].
- *
- * For the 102nd record, bc_levels[0].ptr == 2, so we continue.
- *
- * For the 201st record, we've moved on to leaf block 3.
- * bc_levels[0].ptr == 1, so we add 3 to the list.  Now it is [1, 4, 2, 3].
- *
- * For the 300th record we just exit, with the list being [1, 4, 2, 3].
+ * These functions are defined by the INTERVAL_TREE_DEFINE macro, but we'll
+ * forward-declare them anyway for clarity.
  */
+static inline void
+xbitmap32_tree_insert(struct xbitmap32_node *node, struct rb_root_cached *root);
 
-/* Mark a btree block to the agblock bitmap. */
-STATIC int
-xagb_bitmap_visit_btblock(
-	struct xfs_btree_cur	*cur,
-	int			level,
-	void			*priv)
+static inline void
+xbitmap32_tree_remove(struct xbitmap32_node *node, struct rb_root_cached *root);
+
+static inline struct xbitmap32_node *
+xbitmap32_tree_iter_first(struct rb_root_cached *root, uint32_t start,
+			  uint32_t last);
+
+static inline struct xbitmap32_node *
+xbitmap32_tree_iter_next(struct xbitmap32_node *node, uint32_t start,
+			 uint32_t last);
+
+INTERVAL_TREE_DEFINE(struct xbitmap32_node, bn_rbnode, uint32_t,
+		__bn_subtree_last, START, LAST, static inline, xbitmap32_tree)
+
+/* Iterate each interval of a bitmap.  Do not change the bitmap. */
+#define for_each_xbitmap32_extent(bn, bitmap) \
+	for ((bn) = rb_entry_safe(rb_first(&(bitmap)->xb_root.rb_root), \
+				   struct xbitmap32_node, bn_rbnode); \
+	     (bn) != NULL; \
+	     (bn) = rb_entry_safe(rb_next(&(bn)->bn_rbnode), \
+				   struct xbitmap32_node, bn_rbnode))
+
+/* Clear a range of this bitmap. */
+int
+xbitmap32_clear(
+	struct xbitmap32	*bitmap,
+	uint32_t		start,
+	uint32_t		len)
 {
-	struct xagb_bitmap	*bitmap = priv;
-	struct xfs_buf		*bp;
-	xfs_fsblock_t		fsbno;
-	xfs_agblock_t		agbno;
+	struct xbitmap32_node	*bn;
+	struct xbitmap32_node	*new_bn;
+	uint32_t		last = start + len - 1;
 
-	xfs_btree_get_block(cur, level, &bp);
-	if (!bp)
-		return 0;
+	while ((bn = xbitmap32_tree_iter_first(&bitmap->xb_root, start, last))) {
+		if (bn->bn_start < start && bn->bn_last > last) {
+			uint32_t	old_last = bn->bn_last;
 
-	fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp));
-	agbno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno);
+			/* overlaps with the entire clearing range */
+			xbitmap32_tree_remove(bn, &bitmap->xb_root);
+			bn->bn_last = start - 1;
+			xbitmap32_tree_insert(bn, &bitmap->xb_root);
 
-	return xagb_bitmap_set(bitmap, agbno, 1);
+			/* add an extent */
+			new_bn = kmalloc(sizeof(struct xbitmap32_node),
+					XCHK_GFP_FLAGS);
+			if (!new_bn)
+				return -ENOMEM;
+			new_bn->bn_start = last + 1;
+			new_bn->bn_last = old_last;
+			xbitmap32_tree_insert(new_bn, &bitmap->xb_root);
+		} else if (bn->bn_start < start) {
+			/* overlaps with the left side of the clearing range */
+			xbitmap32_tree_remove(bn, &bitmap->xb_root);
+			bn->bn_last = start - 1;
+			xbitmap32_tree_insert(bn, &bitmap->xb_root);
+		} else if (bn->bn_last > last) {
+			/* overlaps with the right side of the clearing range */
+			xbitmap32_tree_remove(bn, &bitmap->xb_root);
+			bn->bn_start = last + 1;
+			xbitmap32_tree_insert(bn, &bitmap->xb_root);
+			break;
+		} else {
+			/* in the middle of the clearing range */
+			xbitmap32_tree_remove(bn, &bitmap->xb_root);
+			kfree(bn);
+		}
+	}
+
+	return 0;
 }
 
-/* Mark all (per-AG) btree blocks in the agblock bitmap. */
+/* Set a range of this bitmap. */
 int
-xagb_bitmap_set_btblocks(
-	struct xagb_bitmap	*bitmap,
-	struct xfs_btree_cur	*cur)
+xbitmap32_set(
+	struct xbitmap32	*bitmap,
+	uint32_t		start,
+	uint32_t		len)
 {
-	return xfs_btree_visit_blocks(cur, xagb_bitmap_visit_btblock,
-			XFS_BTREE_VISIT_ALL, bitmap);
+	struct xbitmap32_node	*left;
+	struct xbitmap32_node	*right;
+	uint32_t		last = start + len - 1;
+	int			error;
+
+	/* Is this whole range already set? */
+	left = xbitmap32_tree_iter_first(&bitmap->xb_root, start, last);
+	if (left && left->bn_start <= start && left->bn_last >= last)
+		return 0;
+
+	/* Clear out everything in the range we want to set. */
+	error = xbitmap32_clear(bitmap, start, len);
+	if (error)
+		return error;
+
+	/* Do we have a left-adjacent extent? */
+	left = xbitmap32_tree_iter_first(&bitmap->xb_root, start - 1, start - 1);
+	ASSERT(!left || left->bn_last + 1 == start);
+
+	/* Do we have a right-adjacent extent? */
+	right = xbitmap32_tree_iter_first(&bitmap->xb_root, last + 1, last + 1);
+	ASSERT(!right || right->bn_start == last + 1);
+
+	if (left && right) {
+		/* combine left and right adjacent extent */
+		xbitmap32_tree_remove(left, &bitmap->xb_root);
+		xbitmap32_tree_remove(right, &bitmap->xb_root);
+		left->bn_last = right->bn_last;
+		xbitmap32_tree_insert(left, &bitmap->xb_root);
+		kfree(right);
+	} else if (left) {
+		/* combine with left extent */
+		xbitmap32_tree_remove(left, &bitmap->xb_root);
+		left->bn_last = last;
+		xbitmap32_tree_insert(left, &bitmap->xb_root);
+	} else if (right) {
+		/* combine with right extent */
+		xbitmap32_tree_remove(right, &bitmap->xb_root);
+		right->bn_start = start;
+		xbitmap32_tree_insert(right, &bitmap->xb_root);
+	} else {
+		/* add an extent */
+		left = kmalloc(sizeof(struct xbitmap32_node), XCHK_GFP_FLAGS);
+		if (!left)
+			return -ENOMEM;
+		left->bn_start = start;
+		left->bn_last = last;
+		xbitmap32_tree_insert(left, &bitmap->xb_root);
+	}
+
+	return 0;
+}
+
+/* Free everything related to this bitmap. */
+void
+xbitmap32_destroy(
+	struct xbitmap32	*bitmap)
+{
+	struct xbitmap32_node	*bn;
+
+	while ((bn = xbitmap32_tree_iter_first(&bitmap->xb_root, 0, -1U))) {
+		xbitmap32_tree_remove(bn, &bitmap->xb_root);
+		kfree(bn);
+	}
+}
+
+/* Set up a per-AG block bitmap. */
+void
+xbitmap32_init(
+	struct xbitmap32	*bitmap)
+{
+	bitmap->xb_root = RB_ROOT_CACHED;
 }
 
 /*
- * Record all the buffers pointed to by the btree cursor.  Callers already
- * engaged in a btree walk should call this function to capture the list of
- * blocks going from the leaf towards the root.
+ * Remove all the blocks mentioned in @sub from the extents in @bitmap.
+ *
+ * The intent is that callers will iterate the rmapbt for all of its records
+ * for a given owner to generate @bitmap; and iterate all the blocks of the
+ * metadata structures that are not being rebuilt and have the same rmapbt
+ * owner to generate @sub.  This routine subtracts all the extents
+ * mentioned in sub from all the extents linked in @bitmap, which leaves
+ * @bitmap as the list of blocks that are not accounted for, which we assume
+ * are the dead blocks of the old metadata structure.  The blocks mentioned in
+ * @bitmap can be reaped.
+ *
+ * This is the logical equivalent of bitmap &= ~sub.
  */
 int
-xagb_bitmap_set_btcur_path(
-	struct xagb_bitmap	*bitmap,
-	struct xfs_btree_cur	*cur)
+xbitmap32_disunion(
+	struct xbitmap32	*bitmap,
+	struct xbitmap32	*sub)
 {
-	int			i;
+	struct xbitmap32_node	*bn;
 	int			error;
 
-	for (i = 0; i < cur->bc_nlevels && cur->bc_levels[i].ptr == 1; i++) {
-		error = xagb_bitmap_visit_btblock(cur, i, bitmap);
+	if (xbitmap32_empty(bitmap) || xbitmap32_empty(sub))
+		return 0;
+
+	for_each_xbitmap32_extent(bn, sub) {
+		error = xbitmap32_clear(bitmap, bn->bn_start,
+				bn->bn_last - bn->bn_start + 1);
 		if (error)
 			return error;
 	}
@@ -318,14 +505,14 @@ xagb_bitmap_set_btcur_path(
 }
 
 /* How many bits are set in this bitmap? */
-uint64_t
-xbitmap_hweight(
-	struct xbitmap		*bitmap)
+uint32_t
+xbitmap32_hweight(
+	struct xbitmap32	*bitmap)
 {
-	struct xbitmap_node	*bn;
-	uint64_t		ret = 0;
+	struct xbitmap32_node	*bn;
+	uint32_t		ret = 0;
 
-	for_each_xbitmap_extent(bn, bitmap)
+	for_each_xbitmap32_extent(bn, bitmap)
 		ret += bn->bn_last - bn->bn_start + 1;
 
 	return ret;
@@ -333,15 +520,15 @@ xbitmap_hweight(
 
 /* Call a function for every run of set bits in this bitmap. */
 int
-xbitmap_walk(
-	struct xbitmap		*bitmap,
-	xbitmap_walk_fn		fn,
+xbitmap32_walk(
+	struct xbitmap32	*bitmap,
+	xbitmap32_walk_fn	fn,
 	void			*priv)
 {
-	struct xbitmap_node	*bn;
+	struct xbitmap32_node	*bn;
 	int			error = 0;
 
-	for_each_xbitmap_extent(bn, bitmap) {
+	for_each_xbitmap32_extent(bn, bitmap) {
 		error = fn(bn->bn_start, bn->bn_last - bn->bn_start + 1, priv);
 		if (error)
 			break;
@@ -352,23 +539,23 @@ xbitmap_walk(
 
 /* Does this bitmap have no bits set at all? */
 bool
-xbitmap_empty(
-	struct xbitmap		*bitmap)
+xbitmap32_empty(
+	struct xbitmap32	*bitmap)
 {
 	return bitmap->xb_root.rb_root.rb_node == NULL;
 }
 
 /* Is the start of the range set or clear?  And for how long? */
 bool
-xbitmap_test(
-	struct xbitmap		*bitmap,
-	uint64_t		start,
-	uint64_t		*len)
+xbitmap32_test(
+	struct xbitmap32	*bitmap,
+	uint32_t		start,
+	uint32_t		*len)
 {
-	struct xbitmap_node	*bn;
-	uint64_t		last = start + *len - 1;
+	struct xbitmap32_node	*bn;
+	uint32_t		last = start + *len - 1;
 
-	bn = xbitmap_tree_iter_first(&bitmap->xb_root, start, last);
+	bn = xbitmap32_tree_iter_first(&bitmap->xb_root, start, last);
 	if (!bn)
 		return false;
 	if (bn->bn_start <= start) {
diff --git a/fs/xfs/scrub/bitmap.h b/fs/xfs/scrub/bitmap.h
index 4fe58bad6734..2df8911606d6 100644
--- a/fs/xfs/scrub/bitmap.h
+++ b/fs/xfs/scrub/bitmap.h
@@ -6,17 +6,19 @@
 #ifndef __XFS_SCRUB_BITMAP_H__
 #define __XFS_SCRUB_BITMAP_H__
 
-struct xbitmap {
+/* u64 bitmap */
+
+struct xbitmap64 {
 	struct rb_root_cached	xb_root;
 };
 
-void xbitmap_init(struct xbitmap *bitmap);
-void xbitmap_destroy(struct xbitmap *bitmap);
+void xbitmap64_init(struct xbitmap64 *bitmap);
+void xbitmap64_destroy(struct xbitmap64 *bitmap);
 
-int xbitmap_clear(struct xbitmap *bitmap, uint64_t start, uint64_t len);
-int xbitmap_set(struct xbitmap *bitmap, uint64_t start, uint64_t len);
-int xbitmap_disunion(struct xbitmap *bitmap, struct xbitmap *sub);
-uint64_t xbitmap_hweight(struct xbitmap *bitmap);
+int xbitmap64_clear(struct xbitmap64 *bitmap, uint64_t start, uint64_t len);
+int xbitmap64_set(struct xbitmap64 *bitmap, uint64_t start, uint64_t len);
+int xbitmap64_disunion(struct xbitmap64 *bitmap, struct xbitmap64 *sub);
+uint64_t xbitmap64_hweight(struct xbitmap64 *bitmap);
 
 /*
  * Return codes for the bitmap iterator functions are 0 to continue iterating,
@@ -25,84 +27,39 @@ uint64_t xbitmap_hweight(struct xbitmap *bitmap);
  * iteration, because neither bitmap iterator ever generates that error code on
  * its own.  Callers must not modify the bitmap while walking it.
  */
-typedef int (*xbitmap_walk_fn)(uint64_t start, uint64_t len, void *priv);
-int xbitmap_walk(struct xbitmap *bitmap, xbitmap_walk_fn fn,
+typedef int (*xbitmap64_walk_fn)(uint64_t start, uint64_t len, void *priv);
+int xbitmap64_walk(struct xbitmap64 *bitmap, xbitmap64_walk_fn fn,
 		void *priv);
 
-bool xbitmap_empty(struct xbitmap *bitmap);
-bool xbitmap_test(struct xbitmap *bitmap, uint64_t start, uint64_t *len);
+bool xbitmap64_empty(struct xbitmap64 *bitmap);
+bool xbitmap64_test(struct xbitmap64 *bitmap, uint64_t start, uint64_t *len);
 
-/* Bitmaps, but for type-checked for xfs_agblock_t */
+/* u32 bitmap */
 
-struct xagb_bitmap {
-	struct xbitmap	agbitmap;
+struct xbitmap32 {
+	struct rb_root_cached	xb_root;
 };
 
-static inline void xagb_bitmap_init(struct xagb_bitmap *bitmap)
-{
-	xbitmap_init(&bitmap->agbitmap);
-}
-
-static inline void xagb_bitmap_destroy(struct xagb_bitmap *bitmap)
-{
-	xbitmap_destroy(&bitmap->agbitmap);
-}
-
-static inline int xagb_bitmap_clear(struct xagb_bitmap *bitmap,
-		xfs_agblock_t start, xfs_extlen_t len)
-{
-	return xbitmap_clear(&bitmap->agbitmap, start, len);
-}
-static inline int xagb_bitmap_set(struct xagb_bitmap *bitmap,
-		xfs_agblock_t start, xfs_extlen_t len)
-{
-	return xbitmap_set(&bitmap->agbitmap, start, len);
-}
-
-static inline bool
-xagb_bitmap_test(
-	struct xagb_bitmap	*bitmap,
-	xfs_agblock_t		start,
-	xfs_extlen_t		*len)
-{
-	uint64_t		biglen = *len;
-	bool			ret;
-
-	ret = xbitmap_test(&bitmap->agbitmap, start, &biglen);
-
-	if (start + biglen >= UINT_MAX) {
-		ASSERT(0);
-		biglen = UINT_MAX - start;
-	}
-
-	*len = biglen;
-	return ret;
-}
-
-static inline int xagb_bitmap_disunion(struct xagb_bitmap *bitmap,
-		struct xagb_bitmap *sub)
-{
-	return xbitmap_disunion(&bitmap->agbitmap, &sub->agbitmap);
-}
+void xbitmap32_init(struct xbitmap32 *bitmap);
+void xbitmap32_destroy(struct xbitmap32 *bitmap);
 
-static inline uint32_t xagb_bitmap_hweight(struct xagb_bitmap *bitmap)
-{
-	return xbitmap_hweight(&bitmap->agbitmap);
-}
-static inline bool xagb_bitmap_empty(struct xagb_bitmap *bitmap)
-{
-	return xbitmap_empty(&bitmap->agbitmap);
-}
+int xbitmap32_clear(struct xbitmap32 *bitmap, uint32_t start, uint32_t len);
+int xbitmap32_set(struct xbitmap32 *bitmap, uint32_t start, uint32_t len);
+int xbitmap32_disunion(struct xbitmap32 *bitmap, struct xbitmap32 *sub);
+uint32_t xbitmap32_hweight(struct xbitmap32 *bitmap);
 
-static inline int xagb_bitmap_walk(struct xagb_bitmap *bitmap,
-		xbitmap_walk_fn fn, void *priv)
-{
-	return xbitmap_walk(&bitmap->agbitmap, fn, priv);
-}
+/*
+ * Return codes for the bitmap iterator functions are 0 to continue iterating,
+ * and non-zero to stop iterating.  Any non-zero value will be passed up to the
+ * iteration caller.  The special value -ECANCELED can be used to stop
+ * iteration, because neither bitmap iterator ever generates that error code on
+ * its own.  Callers must not modify the bitmap while walking it.
+ */
+typedef int (*xbitmap32_walk_fn)(uint32_t start, uint32_t len, void *priv);
+int xbitmap32_walk(struct xbitmap32 *bitmap, xbitmap32_walk_fn fn,
+		void *priv);
 
-int xagb_bitmap_set_btblocks(struct xagb_bitmap *bitmap,
-		struct xfs_btree_cur *cur);
-int xagb_bitmap_set_btcur_path(struct xagb_bitmap *bitmap,
-		struct xfs_btree_cur *cur);
+bool xbitmap32_empty(struct xbitmap32 *bitmap);
+bool xbitmap32_test(struct xbitmap32 *bitmap, uint32_t start, uint32_t *len);
 
 #endif	/* __XFS_SCRUB_BITMAP_H__ */
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 06d8c1996a33..b169cddde6da 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -19,9 +19,11 @@
 #include "xfs_bmap_btree.h"
 #include "xfs_rmap.h"
 #include "xfs_rmap_btree.h"
+#include "xfs_health.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/btree.h"
+#include "scrub/health.h"
 #include "xfs_ag.h"
 
 /* Set us up with an inode's bmap. */
@@ -48,9 +50,18 @@ xchk_setup_inode_bmap(
 	if (S_ISREG(VFS_I(sc->ip)->i_mode) &&
 	    sc->sm->sm_type != XFS_SCRUB_TYPE_BMBTA) {
 		struct address_space	*mapping = VFS_I(sc->ip)->i_mapping;
+		bool			is_repair = xchk_could_repair(sc);
 
 		xchk_ilock(sc, XFS_MMAPLOCK_EXCL);
 
+		/* Break all our leases, we're going to mess with things. */
+		if (is_repair) {
+			error = xfs_break_layouts(VFS_I(sc->ip),
+					&sc->ilock_flags, BREAK_WRITE);
+			if (error)
+				goto out;
+		}
+
 		inode_dio_wait(VFS_I(sc->ip));
 
 		/*
@@ -71,6 +82,15 @@ xchk_setup_inode_bmap(
 			error = filemap_fdatawait_keep_errors(mapping);
 		if (error && (error != -ENOSPC && error != -EIO))
 			goto out;
+
+		/* Drop the page cache if we're repairing block mappings. */
+		if (is_repair) {
+			error = invalidate_inode_pages2(
+					VFS_I(sc->ip)->i_mapping);
+			if (error)
+				goto out;
+		}
+
 	}
 
 	/* Got the inode, lock it and we're ready to go. */
@@ -78,6 +98,10 @@ xchk_setup_inode_bmap(
 	if (error)
 		goto out;
 
+	error = xchk_ino_dqattach(sc);
+	if (error)
+		goto out;
+
 	xchk_ilock(sc, XFS_ILOCK_EXCL);
 out:
 	/* scrub teardown will unlock and release the inode */
@@ -633,6 +657,82 @@ xchk_bmap_check_ag_rmaps(
 }
 
 /*
+ * Decide if we want to scan the reverse mappings to determine if the attr
+ * fork /really/ has zero space mappings.
+ */
+STATIC bool
+xchk_bmap_check_empty_attrfork(
+	struct xfs_inode	*ip)
+{
+	struct xfs_ifork	*ifp = &ip->i_af;
+
+	/*
+	 * If the dinode repair found a bad attr fork, it will reset the fork
+	 * to extents format with zero records and wait for the this scrubber
+	 * to reconstruct the block mappings.  If the fork is not in this
+	 * state, then the fork cannot have been zapped.
+	 */
+	if (ifp->if_format != XFS_DINODE_FMT_EXTENTS || ifp->if_nextents != 0)
+		return false;
+
+	/*
+	 * Files can have an attr fork in EXTENTS format with zero records for
+	 * several reasons:
+	 *
+	 * a) an attr set created a fork but ran out of space
+	 * b) attr replace deleted an old attr but failed during the set step
+	 * c) the data fork was in btree format when all attrs were deleted, so
+	 *    the fork was left in place
+	 * d) the inode repair code zapped the fork
+	 *
+	 * Only in case (d) do we want to scan the rmapbt to see if we need to
+	 * rebuild the attr fork.  The fork zap code clears all DAC permission
+	 * bits and zeroes the uid and gid, so avoid the scan if any of those
+	 * three conditions are not met.
+	 */
+	if ((VFS_I(ip)->i_mode & 0777) != 0)
+		return false;
+	if (!uid_eq(VFS_I(ip)->i_uid, GLOBAL_ROOT_UID))
+		return false;
+	if (!gid_eq(VFS_I(ip)->i_gid, GLOBAL_ROOT_GID))
+		return false;
+
+	return true;
+}
+
+/*
+ * Decide if we want to scan the reverse mappings to determine if the data
+ * fork /really/ has zero space mappings.
+ */
+STATIC bool
+xchk_bmap_check_empty_datafork(
+	struct xfs_inode	*ip)
+{
+	struct xfs_ifork	*ifp = &ip->i_df;
+
+	/* Don't support realtime rmap checks yet. */
+	if (XFS_IS_REALTIME_INODE(ip))
+		return false;
+
+	/*
+	 * If the dinode repair found a bad data fork, it will reset the fork
+	 * to extents format with zero records and wait for the this scrubber
+	 * to reconstruct the block mappings.  If the fork is not in this
+	 * state, then the fork cannot have been zapped.
+	 */
+	if (ifp->if_format != XFS_DINODE_FMT_EXTENTS || ifp->if_nextents != 0)
+		return false;
+
+	/*
+	 * If we encounter an empty data fork along with evidence that the fork
+	 * might not really be empty, we need to scan the reverse mappings to
+	 * decide if we're going to rebuild the fork.  Data forks with nonzero
+	 * file size are scanned.
+	 */
+	return i_size_read(VFS_I(ip)) != 0;
+}
+
+/*
  * Decide if we want to walk every rmap btree in the fs to make sure that each
  * rmap for this file fork has corresponding bmbt entries.
  */
@@ -641,7 +741,6 @@ xchk_bmap_want_check_rmaps(
 	struct xchk_bmap_info	*info)
 {
 	struct xfs_scrub	*sc = info->sc;
-	struct xfs_ifork	*ifp;
 
 	if (!xfs_has_rmapbt(sc->mp))
 		return false;
@@ -650,28 +749,10 @@ xchk_bmap_want_check_rmaps(
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return false;
 
-	/* Don't support realtime rmap checks yet. */
-	if (info->is_rt)
-		return false;
-
-	/*
-	 * The inode repair code zaps broken inode forks by resetting them back
-	 * to EXTENTS format and zero extent records.  If we encounter a fork
-	 * in this state along with evidence that the fork isn't supposed to be
-	 * empty, we need to scan the reverse mappings to decide if we're going
-	 * to rebuild the fork.  Data forks with nonzero file size are scanned.
-	 * xattr forks are never empty of content, so they are always scanned.
-	 */
-	ifp = xfs_ifork_ptr(sc->ip, info->whichfork);
-	if (ifp->if_format == XFS_DINODE_FMT_EXTENTS && ifp->if_nextents == 0) {
-		if (info->whichfork == XFS_DATA_FORK &&
-		    i_size_read(VFS_I(sc->ip)) == 0)
-			return false;
-
-		return true;
-	}
+	if (info->whichfork == XFS_ATTR_FORK)
+		return xchk_bmap_check_empty_attrfork(sc->ip);
 
-	return false;
+	return xchk_bmap_check_empty_datafork(sc->ip);
 }
 
 /* Make sure each rmap has a corresponding bmbt entry. */
@@ -939,7 +1020,20 @@ int
 xchk_bmap_data(
 	struct xfs_scrub	*sc)
 {
-	return xchk_bmap(sc, XFS_DATA_FORK);
+	int			error;
+
+	if (xchk_file_looks_zapped(sc, XFS_SICK_INO_BMBTD_ZAPPED)) {
+		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
+		return 0;
+	}
+
+	error = xchk_bmap(sc, XFS_DATA_FORK);
+	if (error)
+		return error;
+
+	/* If the data fork is clean, it is clearly not zapped. */
+	xchk_mark_healthy_if_clean(sc, XFS_SICK_INO_BMBTD_ZAPPED);
+	return 0;
 }
 
 /* Scrub an inode's attr fork. */
@@ -947,7 +1041,27 @@ int
 xchk_bmap_attr(
 	struct xfs_scrub	*sc)
 {
-	return xchk_bmap(sc, XFS_ATTR_FORK);
+	int			error;
+
+	/*
+	 * If the attr fork has been zapped, it's possible that forkoff was
+	 * reset to zero and hence sc->ip->i_afp is NULL.  We don't want the
+	 * NULL ifp check in xchk_bmap to conclude that the attr fork is ok,
+	 * so short circuit that logic by setting the corruption flag and
+	 * returning immediately.
+	 */
+	if (xchk_file_looks_zapped(sc, XFS_SICK_INO_BMBTA_ZAPPED)) {
+		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
+		return 0;
+	}
+
+	error = xchk_bmap(sc, XFS_ATTR_FORK);
+	if (error)
+		return error;
+
+	/* If the attr fork is clean, it is clearly not zapped. */
+	xchk_mark_healthy_if_clean(sc, XFS_SICK_INO_BMBTA_ZAPPED);
+	return 0;
 }
 
 /* Scrub an inode's CoW fork. */
diff --git a/fs/xfs/scrub/bmap_repair.c b/fs/xfs/scrub/bmap_repair.c
new file mode 100644
index 000000000000..a4bb89fdd510
--- /dev/null
+++ b/fs/xfs/scrub/bmap_repair.c
@@ -0,0 +1,867 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_btree_staging.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_inode_fork.h"
+#include "xfs_alloc.h"
+#include "xfs_rtalloc.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_refcount.h"
+#include "xfs_quota.h"
+#include "xfs_ialloc.h"
+#include "xfs_ag.h"
+#include "xfs_reflink.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/btree.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/bitmap.h"
+#include "scrub/fsb_bitmap.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/newbt.h"
+#include "scrub/reap.h"
+
+/*
+ * Inode Fork Block Mapping (BMBT) Repair
+ * ======================================
+ *
+ * Gather all the rmap records for the inode and fork we're fixing, reset the
+ * incore fork, then recreate the btree.
+ */
+
+enum reflink_scan_state {
+	RLS_IRRELEVANT = -1,	/* not applicable to this file */
+	RLS_UNKNOWN,		/* shared extent scans required */
+	RLS_SET_IFLAG,		/* iflag must be set */
+};
+
+struct xrep_bmap {
+	/* Old bmbt blocks */
+	struct xfsb_bitmap	old_bmbt_blocks;
+
+	/* New fork. */
+	struct xrep_newbt	new_bmapbt;
+
+	/* List of new bmap records. */
+	struct xfarray		*bmap_records;
+
+	struct xfs_scrub	*sc;
+
+	/* How many blocks did we find allocated to this file? */
+	xfs_rfsblock_t		nblocks;
+
+	/* How many bmbt blocks did we find for this fork? */
+	xfs_rfsblock_t		old_bmbt_block_count;
+
+	/* get_records()'s position in the free space record array. */
+	xfarray_idx_t		array_cur;
+
+	/* How many real (non-hole, non-delalloc) mappings do we have? */
+	uint64_t		real_mappings;
+
+	/* Which fork are we fixing? */
+	int			whichfork;
+
+	/* What d the REFLINK flag be set when the repair is over? */
+	enum reflink_scan_state	reflink_scan;
+
+	/* Do we allow unwritten extents? */
+	bool			allow_unwritten;
+};
+
+/* Is this space extent shared?  Flag the inode if it is. */
+STATIC int
+xrep_bmap_discover_shared(
+	struct xrep_bmap	*rb,
+	xfs_fsblock_t		startblock,
+	xfs_filblks_t		blockcount)
+{
+	struct xfs_scrub	*sc = rb->sc;
+	xfs_agblock_t		agbno;
+	xfs_agblock_t		fbno;
+	xfs_extlen_t		flen;
+	int			error;
+
+	agbno = XFS_FSB_TO_AGBNO(sc->mp, startblock);
+	error = xfs_refcount_find_shared(sc->sa.refc_cur, agbno, blockcount,
+			&fbno, &flen, false);
+	if (error)
+		return error;
+
+	if (fbno != NULLAGBLOCK)
+		rb->reflink_scan = RLS_SET_IFLAG;
+
+	return 0;
+}
+
+/* Remember this reverse-mapping as a series of bmap records. */
+STATIC int
+xrep_bmap_from_rmap(
+	struct xrep_bmap	*rb,
+	xfs_fileoff_t		startoff,
+	xfs_fsblock_t		startblock,
+	xfs_filblks_t		blockcount,
+	bool			unwritten)
+{
+	struct xfs_bmbt_irec	irec = {
+		.br_startoff	= startoff,
+		.br_startblock	= startblock,
+		.br_state	= unwritten ? XFS_EXT_UNWRITTEN : XFS_EXT_NORM,
+	};
+	struct xfs_bmbt_rec	rbe;
+	struct xfs_scrub	*sc = rb->sc;
+	int			error = 0;
+
+	/*
+	 * If we're repairing the data fork of a non-reflinked regular file on
+	 * a reflink filesystem, we need to figure out if this space extent is
+	 * shared.
+	 */
+	if (rb->reflink_scan == RLS_UNKNOWN && !unwritten) {
+		error = xrep_bmap_discover_shared(rb, startblock, blockcount);
+		if (error)
+			return error;
+	}
+
+	do {
+		xfs_failaddr_t	fa;
+
+		irec.br_blockcount = min_t(xfs_filblks_t, blockcount,
+				XFS_MAX_BMBT_EXTLEN);
+
+		fa = xfs_bmap_validate_extent(sc->ip, rb->whichfork, &irec);
+		if (fa)
+			return -EFSCORRUPTED;
+
+		xfs_bmbt_disk_set_all(&rbe, &irec);
+
+		trace_xrep_bmap_found(sc->ip, rb->whichfork, &irec);
+
+		if (xchk_should_terminate(sc, &error))
+			return error;
+
+		error = xfarray_append(rb->bmap_records, &rbe);
+		if (error)
+			return error;
+
+		rb->real_mappings++;
+
+		irec.br_startblock += irec.br_blockcount;
+		irec.br_startoff += irec.br_blockcount;
+		blockcount -= irec.br_blockcount;
+	} while (blockcount > 0);
+
+	return 0;
+}
+
+/* Check for any obvious errors or conflicts in the file mapping. */
+STATIC int
+xrep_bmap_check_fork_rmap(
+	struct xrep_bmap		*rb,
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*rec)
+{
+	struct xfs_scrub		*sc = rb->sc;
+	enum xbtree_recpacking		outcome;
+	int				error;
+
+	/*
+	 * Data extents for rt files are never stored on the data device, but
+	 * everything else (xattrs, bmbt blocks) can be.
+	 */
+	if (XFS_IS_REALTIME_INODE(sc->ip) &&
+	    !(rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK)))
+		return -EFSCORRUPTED;
+
+	/* Check that this is within the AG. */
+	if (!xfs_verify_agbext(cur->bc_ag.pag, rec->rm_startblock,
+				rec->rm_blockcount))
+		return -EFSCORRUPTED;
+
+	/* Check the file offset range. */
+	if (!(rec->rm_flags & XFS_RMAP_BMBT_BLOCK) &&
+	    !xfs_verify_fileext(sc->mp, rec->rm_offset, rec->rm_blockcount))
+		return -EFSCORRUPTED;
+
+	/* No contradictory flags. */
+	if ((rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK)) &&
+	    (rec->rm_flags & XFS_RMAP_UNWRITTEN))
+		return -EFSCORRUPTED;
+
+	/* Make sure this isn't free space. */
+	error = xfs_alloc_has_records(sc->sa.bno_cur, rec->rm_startblock,
+			rec->rm_blockcount, &outcome);
+	if (error)
+		return error;
+	if (outcome != XBTREE_RECPACKING_EMPTY)
+		return -EFSCORRUPTED;
+
+	/* Must not be an inode chunk. */
+	error = xfs_ialloc_has_inodes_at_extent(sc->sa.ino_cur,
+			rec->rm_startblock, rec->rm_blockcount, &outcome);
+	if (error)
+		return error;
+	if (outcome != XBTREE_RECPACKING_EMPTY)
+		return -EFSCORRUPTED;
+
+	return 0;
+}
+
+/* Record extents that belong to this inode's fork. */
+STATIC int
+xrep_bmap_walk_rmap(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*rec,
+	void				*priv)
+{
+	struct xrep_bmap		*rb = priv;
+	struct xfs_mount		*mp = cur->bc_mp;
+	xfs_fsblock_t			fsbno;
+	int				error = 0;
+
+	if (xchk_should_terminate(rb->sc, &error))
+		return error;
+
+	if (rec->rm_owner != rb->sc->ip->i_ino)
+		return 0;
+
+	error = xrep_bmap_check_fork_rmap(rb, cur, rec);
+	if (error)
+		return error;
+
+	/*
+	 * Record all blocks allocated to this file even if the extent isn't
+	 * for the fork we're rebuilding so that we can reset di_nblocks later.
+	 */
+	rb->nblocks += rec->rm_blockcount;
+
+	/* If this rmap isn't for the fork we want, we're done. */
+	if (rb->whichfork == XFS_DATA_FORK &&
+	    (rec->rm_flags & XFS_RMAP_ATTR_FORK))
+		return 0;
+	if (rb->whichfork == XFS_ATTR_FORK &&
+	    !(rec->rm_flags & XFS_RMAP_ATTR_FORK))
+		return 0;
+
+	/* Reject unwritten extents if we don't allow those. */
+	if ((rec->rm_flags & XFS_RMAP_UNWRITTEN) && !rb->allow_unwritten)
+		return -EFSCORRUPTED;
+
+	fsbno = XFS_AGB_TO_FSB(mp, cur->bc_ag.pag->pag_agno,
+			rec->rm_startblock);
+
+	if (rec->rm_flags & XFS_RMAP_BMBT_BLOCK) {
+		rb->old_bmbt_block_count += rec->rm_blockcount;
+		return xfsb_bitmap_set(&rb->old_bmbt_blocks, fsbno,
+				rec->rm_blockcount);
+	}
+
+	return xrep_bmap_from_rmap(rb, rec->rm_offset, fsbno,
+			rec->rm_blockcount,
+			rec->rm_flags & XFS_RMAP_UNWRITTEN);
+}
+
+/*
+ * Compare two block mapping records.  We want to sort in order of increasing
+ * file offset.
+ */
+static int
+xrep_bmap_extent_cmp(
+	const void			*a,
+	const void			*b)
+{
+	const struct xfs_bmbt_rec	*ba = a;
+	const struct xfs_bmbt_rec	*bb = b;
+	xfs_fileoff_t			ao = xfs_bmbt_disk_get_startoff(ba);
+	xfs_fileoff_t			bo = xfs_bmbt_disk_get_startoff(bb);
+
+	if (ao > bo)
+		return 1;
+	else if (ao < bo)
+		return -1;
+	return 0;
+}
+
+/*
+ * Sort the bmap extents by fork offset or else the records will be in the
+ * wrong order.  Ensure there are no overlaps in the file offset ranges.
+ */
+STATIC int
+xrep_bmap_sort_records(
+	struct xrep_bmap	*rb)
+{
+	struct xfs_bmbt_irec	irec;
+	xfs_fileoff_t		next_off = 0;
+	xfarray_idx_t		array_cur;
+	int			error;
+
+	error = xfarray_sort(rb->bmap_records, xrep_bmap_extent_cmp,
+			XFARRAY_SORT_KILLABLE);
+	if (error)
+		return error;
+
+	foreach_xfarray_idx(rb->bmap_records, array_cur) {
+		struct xfs_bmbt_rec	rec;
+
+		if (xchk_should_terminate(rb->sc, &error))
+			return error;
+
+		error = xfarray_load(rb->bmap_records, array_cur, &rec);
+		if (error)
+			return error;
+
+		xfs_bmbt_disk_get_all(&rec, &irec);
+
+		if (irec.br_startoff < next_off)
+			return -EFSCORRUPTED;
+
+		next_off = irec.br_startoff + irec.br_blockcount;
+	}
+
+	return 0;
+}
+
+/* Scan one AG for reverse mappings that we can turn into extent maps. */
+STATIC int
+xrep_bmap_scan_ag(
+	struct xrep_bmap	*rb,
+	struct xfs_perag	*pag)
+{
+	struct xfs_scrub	*sc = rb->sc;
+	int			error;
+
+	error = xrep_ag_init(sc, pag, &sc->sa);
+	if (error)
+		return error;
+
+	error = xfs_rmap_query_all(sc->sa.rmap_cur, xrep_bmap_walk_rmap, rb);
+	xchk_ag_free(sc, &sc->sa);
+	return error;
+}
+
+/* Find the delalloc extents from the old incore extent tree. */
+STATIC int
+xrep_bmap_find_delalloc(
+	struct xrep_bmap	*rb)
+{
+	struct xfs_bmbt_irec	irec;
+	struct xfs_iext_cursor	icur;
+	struct xfs_bmbt_rec	rbe;
+	struct xfs_inode	*ip = rb->sc->ip;
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, rb->whichfork);
+	int			error = 0;
+
+	/*
+	 * Skip this scan if we don't expect to find delayed allocation
+	 * reservations in this fork.
+	 */
+	if (rb->whichfork == XFS_ATTR_FORK || ip->i_delayed_blks == 0)
+		return 0;
+
+	for_each_xfs_iext(ifp, &icur, &irec) {
+		if (!isnullstartblock(irec.br_startblock))
+			continue;
+
+		xfs_bmbt_disk_set_all(&rbe, &irec);
+
+		trace_xrep_bmap_found(ip, rb->whichfork, &irec);
+
+		if (xchk_should_terminate(rb->sc, &error))
+			return error;
+
+		error = xfarray_append(rb->bmap_records, &rbe);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+/*
+ * Collect block mappings for this fork of this inode and decide if we have
+ * enough space to rebuild.  Caller is responsible for cleaning up the list if
+ * anything goes wrong.
+ */
+STATIC int
+xrep_bmap_find_mappings(
+	struct xrep_bmap	*rb)
+{
+	struct xfs_scrub	*sc = rb->sc;
+	struct xfs_perag	*pag;
+	xfs_agnumber_t		agno;
+	int			error = 0;
+
+	/* Iterate the rmaps for extents. */
+	for_each_perag(sc->mp, agno, pag) {
+		error = xrep_bmap_scan_ag(rb, pag);
+		if (error) {
+			xfs_perag_rele(pag);
+			return error;
+		}
+	}
+
+	return xrep_bmap_find_delalloc(rb);
+}
+
+/* Retrieve real extent mappings for bulk loading the bmap btree. */
+STATIC int
+xrep_bmap_get_records(
+	struct xfs_btree_cur	*cur,
+	unsigned int		idx,
+	struct xfs_btree_block	*block,
+	unsigned int		nr_wanted,
+	void			*priv)
+{
+	struct xfs_bmbt_rec	rec;
+	struct xfs_bmbt_irec	*irec = &cur->bc_rec.b;
+	struct xrep_bmap	*rb = priv;
+	union xfs_btree_rec	*block_rec;
+	unsigned int		loaded;
+	int			error;
+
+	for (loaded = 0; loaded < nr_wanted; loaded++, idx++) {
+		do {
+			error = xfarray_load(rb->bmap_records, rb->array_cur++,
+					&rec);
+			if (error)
+				return error;
+
+			xfs_bmbt_disk_get_all(&rec, irec);
+		} while (isnullstartblock(irec->br_startblock));
+
+		block_rec = xfs_btree_rec_addr(cur, idx, block);
+		cur->bc_ops->init_rec_from_cur(cur, block_rec);
+	}
+
+	return loaded;
+}
+
+/* Feed one of the new btree blocks to the bulk loader. */
+STATIC int
+xrep_bmap_claim_block(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr,
+	void			*priv)
+{
+	struct xrep_bmap        *rb = priv;
+
+	return xrep_newbt_claim_block(cur, &rb->new_bmapbt, ptr);
+}
+
+/* Figure out how much space we need to create the incore btree root block. */
+STATIC size_t
+xrep_bmap_iroot_size(
+	struct xfs_btree_cur	*cur,
+	unsigned int		level,
+	unsigned int		nr_this_level,
+	void			*priv)
+{
+	ASSERT(level > 0);
+
+	return XFS_BMAP_BROOT_SPACE_CALC(cur->bc_mp, nr_this_level);
+}
+
+/* Update the inode counters. */
+STATIC int
+xrep_bmap_reset_counters(
+	struct xrep_bmap	*rb)
+{
+	struct xfs_scrub	*sc = rb->sc;
+	struct xbtree_ifakeroot	*ifake = &rb->new_bmapbt.ifake;
+	int64_t			delta;
+
+	if (rb->reflink_scan == RLS_SET_IFLAG)
+		sc->ip->i_diflags2 |= XFS_DIFLAG2_REFLINK;
+
+	/*
+	 * Update the inode block counts to reflect the extents we found in the
+	 * rmapbt.
+	 */
+	delta = ifake->if_blocks - rb->old_bmbt_block_count;
+	sc->ip->i_nblocks = rb->nblocks + delta;
+	xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE);
+
+	/*
+	 * Adjust the quota counts by the difference in size between the old
+	 * and new bmbt.
+	 */
+	xfs_trans_mod_dquot_byino(sc->tp, sc->ip, XFS_TRANS_DQ_BCOUNT, delta);
+	return 0;
+}
+
+/*
+ * Create a new iext tree and load it with block mappings.  If the inode is
+ * in extents format, that's all we need to do to commit the new mappings.
+ * If it is in btree format, this takes care of preloading the incore tree.
+ */
+STATIC int
+xrep_bmap_extents_load(
+	struct xrep_bmap	*rb)
+{
+	struct xfs_iext_cursor	icur;
+	struct xfs_bmbt_irec	irec;
+	struct xfs_ifork	*ifp = rb->new_bmapbt.ifake.if_fork;
+	xfarray_idx_t		array_cur;
+	int			error;
+
+	ASSERT(ifp->if_bytes == 0);
+
+	/* Add all the mappings (incl. delalloc) to the incore extent tree. */
+	xfs_iext_first(ifp, &icur);
+	foreach_xfarray_idx(rb->bmap_records, array_cur) {
+		struct xfs_bmbt_rec	rec;
+
+		error = xfarray_load(rb->bmap_records, array_cur, &rec);
+		if (error)
+			return error;
+
+		xfs_bmbt_disk_get_all(&rec, &irec);
+
+		xfs_iext_insert_raw(ifp, &icur, &irec);
+		if (!isnullstartblock(irec.br_startblock))
+			ifp->if_nextents++;
+
+		xfs_iext_next(ifp, &icur);
+	}
+
+	return xrep_ino_ensure_extent_count(rb->sc, rb->whichfork,
+			ifp->if_nextents);
+}
+
+/*
+ * Reserve new btree blocks, bulk load the bmap records into the ondisk btree,
+ * and load the incore extent tree.
+ */
+STATIC int
+xrep_bmap_btree_load(
+	struct xrep_bmap	*rb,
+	struct xfs_btree_cur	*bmap_cur)
+{
+	struct xfs_scrub	*sc = rb->sc;
+	int			error;
+
+	/* Compute how many blocks we'll need. */
+	error = xfs_btree_bload_compute_geometry(bmap_cur,
+			&rb->new_bmapbt.bload, rb->real_mappings);
+	if (error)
+		return error;
+
+	/* Last chance to abort before we start committing fixes. */
+	if (xchk_should_terminate(sc, &error))
+		return error;
+
+	/*
+	 * Guess how many blocks we're going to need to rebuild an entire bmap
+	 * from the number of extents we found, and pump up our transaction to
+	 * have sufficient block reservation.  We're allowed to exceed file
+	 * quota to repair inconsistent metadata.
+	 */
+	error = xfs_trans_reserve_more_inode(sc->tp, sc->ip,
+			rb->new_bmapbt.bload.nr_blocks, 0, true);
+	if (error)
+		return error;
+
+	/* Reserve the space we'll need for the new btree. */
+	error = xrep_newbt_alloc_blocks(&rb->new_bmapbt,
+			rb->new_bmapbt.bload.nr_blocks);
+	if (error)
+		return error;
+
+	/* Add all observed bmap records. */
+	rb->array_cur = XFARRAY_CURSOR_INIT;
+	error = xfs_btree_bload(bmap_cur, &rb->new_bmapbt.bload, rb);
+	if (error)
+		return error;
+
+	/*
+	 * Load the new bmap records into the new incore extent tree to
+	 * preserve delalloc reservations for regular files.  The directory
+	 * code loads the extent tree during xfs_dir_open and assumes
+	 * thereafter that it remains loaded, so we must not violate that
+	 * assumption.
+	 */
+	return xrep_bmap_extents_load(rb);
+}
+
+/*
+ * Use the collected bmap information to stage a new bmap fork.  If this is
+ * successful we'll return with the new fork information logged to the repair
+ * transaction but not yet committed.  The caller must ensure that the inode
+ * is joined to the transaction; the inode will be joined to a clean
+ * transaction when the function returns.
+ */
+STATIC int
+xrep_bmap_build_new_fork(
+	struct xrep_bmap	*rb)
+{
+	struct xfs_owner_info	oinfo;
+	struct xfs_scrub	*sc = rb->sc;
+	struct xfs_btree_cur	*bmap_cur;
+	struct xbtree_ifakeroot	*ifake = &rb->new_bmapbt.ifake;
+	int			error;
+
+	error = xrep_bmap_sort_records(rb);
+	if (error)
+		return error;
+
+	/*
+	 * Prepare to construct the new fork by initializing the new btree
+	 * structure and creating a fake ifork in the ifakeroot structure.
+	 */
+	xfs_rmap_ino_bmbt_owner(&oinfo, sc->ip->i_ino, rb->whichfork);
+	error = xrep_newbt_init_inode(&rb->new_bmapbt, sc, rb->whichfork,
+			&oinfo);
+	if (error)
+		return error;
+
+	rb->new_bmapbt.bload.get_records = xrep_bmap_get_records;
+	rb->new_bmapbt.bload.claim_block = xrep_bmap_claim_block;
+	rb->new_bmapbt.bload.iroot_size = xrep_bmap_iroot_size;
+	bmap_cur = xfs_bmbt_stage_cursor(sc->mp, sc->ip, ifake);
+
+	/*
+	 * Figure out the size and format of the new fork, then fill it with
+	 * all the bmap records we've found.  Join the inode to the transaction
+	 * so that we can roll the transaction while holding the inode locked.
+	 */
+	if (rb->real_mappings <= XFS_IFORK_MAXEXT(sc->ip, rb->whichfork)) {
+		ifake->if_fork->if_format = XFS_DINODE_FMT_EXTENTS;
+		error = xrep_bmap_extents_load(rb);
+	} else {
+		ifake->if_fork->if_format = XFS_DINODE_FMT_BTREE;
+		error = xrep_bmap_btree_load(rb, bmap_cur);
+	}
+	if (error)
+		goto err_cur;
+
+	/*
+	 * Install the new fork in the inode.  After this point the old mapping
+	 * data are no longer accessible and the new tree is live.  We delete
+	 * the cursor immediately after committing the staged root because the
+	 * staged fork might be in extents format.
+	 */
+	xfs_bmbt_commit_staged_btree(bmap_cur, sc->tp, rb->whichfork);
+	xfs_btree_del_cursor(bmap_cur, 0);
+
+	/* Reset the inode counters now that we've changed the fork. */
+	error = xrep_bmap_reset_counters(rb);
+	if (error)
+		goto err_newbt;
+
+	/* Dispose of any unused blocks and the accounting information. */
+	error = xrep_newbt_commit(&rb->new_bmapbt);
+	if (error)
+		return error;
+
+	return xrep_roll_trans(sc);
+
+err_cur:
+	if (bmap_cur)
+		xfs_btree_del_cursor(bmap_cur, error);
+err_newbt:
+	xrep_newbt_cancel(&rb->new_bmapbt);
+	return error;
+}
+
+/*
+ * Now that we've logged the new inode btree, invalidate all of the old blocks
+ * and free them, if there were any.
+ */
+STATIC int
+xrep_bmap_remove_old_tree(
+	struct xrep_bmap	*rb)
+{
+	struct xfs_scrub	*sc = rb->sc;
+	struct xfs_owner_info	oinfo;
+
+	/* Free the old bmbt blocks if they're not in use. */
+	xfs_rmap_ino_bmbt_owner(&oinfo, sc->ip->i_ino, rb->whichfork);
+	return xrep_reap_fsblocks(sc, &rb->old_bmbt_blocks, &oinfo);
+}
+
+/* Check for garbage inputs.  Returns -ECANCELED if there's nothing to do. */
+STATIC int
+xrep_bmap_check_inputs(
+	struct xfs_scrub	*sc,
+	int			whichfork)
+{
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(sc->ip, whichfork);
+
+	ASSERT(whichfork == XFS_DATA_FORK || whichfork == XFS_ATTR_FORK);
+
+	if (!xfs_has_rmapbt(sc->mp))
+		return -EOPNOTSUPP;
+
+	/* No fork means nothing to rebuild. */
+	if (!ifp)
+		return -ECANCELED;
+
+	/*
+	 * We only know how to repair extent mappings, which is to say that we
+	 * only support extents and btree fork format.  Repairs to a local
+	 * format fork require a higher level repair function, so we do not
+	 * have any work to do here.
+	 */
+	switch (ifp->if_format) {
+	case XFS_DINODE_FMT_DEV:
+	case XFS_DINODE_FMT_LOCAL:
+	case XFS_DINODE_FMT_UUID:
+		return -ECANCELED;
+	case XFS_DINODE_FMT_EXTENTS:
+	case XFS_DINODE_FMT_BTREE:
+		break;
+	default:
+		return -EFSCORRUPTED;
+	}
+
+	if (whichfork == XFS_ATTR_FORK)
+		return 0;
+
+	/* Only files, symlinks, and directories get to have data forks. */
+	switch (VFS_I(sc->ip)->i_mode & S_IFMT) {
+	case S_IFREG:
+	case S_IFDIR:
+	case S_IFLNK:
+		/* ok */
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Don't know how to rebuild realtime data forks. */
+	if (XFS_IS_REALTIME_INODE(sc->ip))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+/* Set up the initial state of the reflink scan. */
+static inline enum reflink_scan_state
+xrep_bmap_init_reflink_scan(
+	struct xfs_scrub	*sc,
+	int			whichfork)
+{
+	/* cannot share on non-reflink filesystem */
+	if (!xfs_has_reflink(sc->mp))
+		return RLS_IRRELEVANT;
+
+	/* preserve flag if it's already set */
+	if (xfs_is_reflink_inode(sc->ip))
+		return RLS_SET_IFLAG;
+
+	/* can only share regular files */
+	if (!S_ISREG(VFS_I(sc->ip)->i_mode))
+		return RLS_IRRELEVANT;
+
+	/* cannot share attr fork extents */
+	if (whichfork != XFS_DATA_FORK)
+		return RLS_IRRELEVANT;
+
+	/* cannot share realtime extents */
+	if (XFS_IS_REALTIME_INODE(sc->ip))
+		return RLS_IRRELEVANT;
+
+	return RLS_UNKNOWN;
+}
+
+/* Repair an inode fork. */
+int
+xrep_bmap(
+	struct xfs_scrub	*sc,
+	int			whichfork,
+	bool			allow_unwritten)
+{
+	struct xrep_bmap	*rb;
+	char			*descr;
+	unsigned int		max_bmbt_recs;
+	bool			large_extcount;
+	int			error = 0;
+
+	error = xrep_bmap_check_inputs(sc, whichfork);
+	if (error == -ECANCELED)
+		return 0;
+	if (error)
+		return error;
+
+	rb = kzalloc(sizeof(struct xrep_bmap), XCHK_GFP_FLAGS);
+	if (!rb)
+		return -ENOMEM;
+	rb->sc = sc;
+	rb->whichfork = whichfork;
+	rb->reflink_scan = xrep_bmap_init_reflink_scan(sc, whichfork);
+	rb->allow_unwritten = allow_unwritten;
+
+	/* Set up enough storage to handle the max records for this fork. */
+	large_extcount = xfs_has_large_extent_counts(sc->mp);
+	max_bmbt_recs = xfs_iext_max_nextents(large_extcount, whichfork);
+	descr = xchk_xfile_ino_descr(sc, "%s fork mapping records",
+			whichfork == XFS_DATA_FORK ? "data" : "attr");
+	error = xfarray_create(descr, max_bmbt_recs,
+			sizeof(struct xfs_bmbt_rec), &rb->bmap_records);
+	kfree(descr);
+	if (error)
+		goto out_rb;
+
+	/* Collect all reverse mappings for this fork's extents. */
+	xfsb_bitmap_init(&rb->old_bmbt_blocks);
+	error = xrep_bmap_find_mappings(rb);
+	if (error)
+		goto out_bitmap;
+
+	xfs_trans_ijoin(sc->tp, sc->ip, 0);
+
+	/* Rebuild the bmap information. */
+	error = xrep_bmap_build_new_fork(rb);
+	if (error)
+		goto out_bitmap;
+
+	/* Kill the old tree. */
+	error = xrep_bmap_remove_old_tree(rb);
+	if (error)
+		goto out_bitmap;
+
+out_bitmap:
+	xfsb_bitmap_destroy(&rb->old_bmbt_blocks);
+	xfarray_destroy(rb->bmap_records);
+out_rb:
+	kfree(rb);
+	return error;
+}
+
+/* Repair an inode's data fork. */
+int
+xrep_bmap_data(
+	struct xfs_scrub	*sc)
+{
+	return xrep_bmap(sc, XFS_DATA_FORK, true);
+}
+
+/* Repair an inode's attr fork. */
+int
+xrep_bmap_attr(
+	struct xfs_scrub	*sc)
+{
+	return xrep_bmap(sc, XFS_ATTR_FORK, false);
+}
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index de24532fe083..81f2b96bb5a7 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -25,6 +25,7 @@
 #include "xfs_trans_priv.h"
 #include "xfs_da_format.h"
 #include "xfs_da_btree.h"
+#include "xfs_dir2_priv.h"
 #include "xfs_attr.h"
 #include "xfs_reflink.h"
 #include "xfs_ag.h"
@@ -604,6 +605,7 @@ xchk_ag_free(
 	struct xchk_ag		*sa)
 {
 	xchk_ag_btcur_free(sa);
+	xrep_reset_perag_resv(sc);
 	if (sa->agf_bp) {
 		xfs_trans_brelse(sc->tp, sa->agf_bp);
 		sa->agf_bp = NULL;
@@ -733,6 +735,8 @@ xchk_iget(
 	xfs_ino_t		inum,
 	struct xfs_inode	**ipp)
 {
+	ASSERT(sc->tp != NULL);
+
 	return xfs_iget(sc->mp, sc->tp, inum, XFS_IGET_UNTRUSTED, 0, ipp);
 }
 
@@ -816,6 +820,26 @@ again:
 	return 0;
 }
 
+#ifdef CONFIG_XFS_QUOTA
+/*
+ * Try to attach dquots to this inode if we think we might want to repair it.
+ * Callers must not hold any ILOCKs.  If the dquots are broken and cannot be
+ * attached, a quotacheck will be scheduled.
+ */
+int
+xchk_ino_dqattach(
+	struct xfs_scrub	*sc)
+{
+	ASSERT(sc->tp != NULL);
+	ASSERT(sc->ip != NULL);
+
+	if (!xchk_could_repair(sc))
+		return 0;
+
+	return xrep_ino_dqattach(sc);
+}
+#endif
+
 /* Install an inode that we opened by handle for scrubbing. */
 int
 xchk_install_handle_inode(
@@ -882,8 +906,8 @@ xchk_iget_for_scrubbing(
 	if (!xfs_verify_ino(sc->mp, sc->sm->sm_ino))
 		return -ENOENT;
 
-	/* Try a regular untrusted iget. */
-	error = xchk_iget(sc, sc->sm->sm_ino, &ip);
+	/* Try a safe untrusted iget. */
+	error = xchk_iget_safe(sc, sc->sm->sm_ino, &ip);
 	if (!error)
 		return xchk_install_handle_inode(sc, ip);
 	if (error == -ENOENT)
@@ -1027,6 +1051,11 @@ xchk_setup_inode_contents(
 	error = xchk_trans_alloc(sc, resblks);
 	if (error)
 		goto out;
+
+	error = xchk_ino_dqattach(sc);
+	if (error)
+		goto out;
+
 	xchk_ilock(sc, XFS_ILOCK_EXCL);
 out:
 	/* scrub teardown will unlock and release the inode for us */
@@ -1132,6 +1161,7 @@ xchk_metadata_inode_subtype(
 	unsigned int		scrub_type)
 {
 	__u32			smtype = sc->sm->sm_type;
+	unsigned int		sick_mask = sc->sick_mask;
 	int			error;
 
 	sc->sm->sm_type = scrub_type;
@@ -1149,6 +1179,7 @@ xchk_metadata_inode_subtype(
 		break;
 	}
 
+	sc->sick_mask = sick_mask;
 	sc->sm->sm_type = smtype;
 	return error;
 }
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index cabdc0e16838..da09580b454a 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -103,9 +103,15 @@ xchk_setup_rtsummary(struct xfs_scrub *sc)
 }
 #endif
 #ifdef CONFIG_XFS_QUOTA
+int xchk_ino_dqattach(struct xfs_scrub *sc);
 int xchk_setup_quota(struct xfs_scrub *sc);
 #else
 static inline int
+xchk_ino_dqattach(struct xfs_scrub *sc)
+{
+	return 0;
+}
+static inline int
 xchk_setup_quota(struct xfs_scrub *sc)
 {
 	return -ENOENT;
@@ -151,6 +157,11 @@ void xchk_iunlock(struct xfs_scrub *sc, unsigned int ilock_flags);
 
 void xchk_buffer_recheck(struct xfs_scrub *sc, struct xfs_buf *bp);
 
+/*
+ * Grab the inode at @inum.  The caller must have created a scrub transaction
+ * so that we can confirm the inumber by walking the inobt and not deadlock on
+ * a loop in the inobt.
+ */
 int xchk_iget(struct xfs_scrub *sc, xfs_ino_t inum, struct xfs_inode **ipp);
 int xchk_iget_agi(struct xfs_scrub *sc, xfs_ino_t inum,
 		struct xfs_buf **agi_bpp, struct xfs_inode **ipp);
@@ -158,6 +169,26 @@ void xchk_irele(struct xfs_scrub *sc, struct xfs_inode *ip);
 int xchk_install_handle_inode(struct xfs_scrub *sc, struct xfs_inode *ip);
 
 /*
+ * Safe version of (untrusted) xchk_iget that uses an empty transaction to
+ * avoid deadlocking on loops in the inobt.  This should only be used in a
+ * scrub or repair setup routine, and only prior to grabbing a transaction.
+ */
+static inline int
+xchk_iget_safe(struct xfs_scrub *sc, xfs_ino_t inum, struct xfs_inode **ipp)
+{
+	int	error;
+
+	ASSERT(sc->tp == NULL);
+
+	error = xchk_trans_alloc(sc, 0);
+	if (error)
+		return error;
+	error = xchk_iget(sc, inum, ipp);
+	xchk_trans_cancel(sc);
+	return error;
+}
+
+/*
  * Don't bother cross-referencing if we already found corruption or cross
  * referencing discrepancies.
  */
@@ -167,6 +198,8 @@ static inline bool xchk_skip_xref(struct xfs_scrub_metadata *sm)
 			       XFS_SCRUB_OFLAG_XCORRUPT);
 }
 
+bool xchk_dir_looks_zapped(struct xfs_inode *dp);
+
 #ifdef CONFIG_XFS_ONLINE_REPAIR
 /* Decide if a repair is required. */
 static inline bool xchk_needs_repair(const struct xfs_scrub_metadata *sm)
@@ -175,8 +208,21 @@ static inline bool xchk_needs_repair(const struct xfs_scrub_metadata *sm)
 			       XFS_SCRUB_OFLAG_XCORRUPT |
 			       XFS_SCRUB_OFLAG_PREEN);
 }
+
+/*
+ * "Should we prepare for a repair?"
+ *
+ * Return true if the caller permits us to repair metadata and we're not
+ * setting up for a post-repair evaluation.
+ */
+static inline bool xchk_could_repair(const struct xfs_scrub *sc)
+{
+	return (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) &&
+		!(sc->flags & XREP_ALREADY_FIXED);
+}
 #else
 # define xchk_needs_repair(sc)		(false)
+# define xchk_could_repair(sc)		(false)
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
 int xchk_metadata_inode_forks(struct xfs_scrub *sc);
@@ -188,6 +234,16 @@ int xchk_metadata_inode_forks(struct xfs_scrub *sc);
 #define xchk_xfile_descr(sc, fmt, ...) \
 	kasprintf(XCHK_GFP_FLAGS, "XFS (%s): " fmt, \
 			(sc)->mp->m_super->s_id, ##__VA_ARGS__)
+#define xchk_xfile_ag_descr(sc, fmt, ...) \
+	kasprintf(XCHK_GFP_FLAGS, "XFS (%s): AG 0x%x " fmt, \
+			(sc)->mp->m_super->s_id, \
+			(sc)->sa.pag ? (sc)->sa.pag->pag_agno : (sc)->sm->sm_agno, \
+			##__VA_ARGS__)
+#define xchk_xfile_ino_descr(sc, fmt, ...) \
+	kasprintf(XCHK_GFP_FLAGS, "XFS (%s): inode 0x%llx " fmt, \
+			(sc)->mp->m_super->s_id, \
+			(sc)->ip ? (sc)->ip->i_ino : (sc)->sm->sm_ino, \
+			##__VA_ARGS__)
 
 /*
  * Setting up a hook to wait for intents to drain is costly -- we have to take
diff --git a/fs/xfs/scrub/cow_repair.c b/fs/xfs/scrub/cow_repair.c
new file mode 100644
index 000000000000..1e82c727af8e
--- /dev/null
+++ b/fs/xfs/scrub/cow_repair.c
@@ -0,0 +1,614 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2022-2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_inode.h"
+#include "xfs_inode_fork.h"
+#include "xfs_alloc.h"
+#include "xfs_bmap.h"
+#include "xfs_rmap.h"
+#include "xfs_refcount.h"
+#include "xfs_quota.h"
+#include "xfs_ialloc.h"
+#include "xfs_ag.h"
+#include "xfs_error.h"
+#include "xfs_errortag.h"
+#include "xfs_icache.h"
+#include "xfs_refcount_btree.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/bitmap.h"
+#include "scrub/off_bitmap.h"
+#include "scrub/fsb_bitmap.h"
+#include "scrub/reap.h"
+
+/*
+ * CoW Fork Mapping Repair
+ * =======================
+ *
+ * Although CoW staging extents are owned by incore CoW inode forks, on disk
+ * they are owned by the refcount btree.  The ondisk metadata does not record
+ * any ownership information, which limits what we can do to repair the
+ * mappings in the CoW fork.  At most, we can replace ifork mappings that lack
+ * an entry in the refcount btree or are described by a reverse mapping record
+ * whose owner is not OWN_COW.
+ *
+ * Replacing extents is also tricky -- we can't touch written CoW fork extents
+ * since they are undergoing writeback, and delalloc extents do not require
+ * repair since they only exist incore.  Hence the most we can do is find the
+ * bad parts of unwritten mappings, allocate a replacement set of blocks, and
+ * replace the incore mapping.  We use the regular reaping process to unmap
+ * or free the discarded blocks, as appropriate.
+ */
+struct xrep_cow {
+	struct xfs_scrub	*sc;
+
+	/* Bitmap of file offset ranges that need replacing. */
+	struct xoff_bitmap	bad_fileoffs;
+
+	/* Bitmap of fsblocks that were removed from the CoW fork. */
+	struct xfsb_bitmap	old_cowfork_fsblocks;
+
+	/* CoW fork mappings used to scan for bad CoW staging extents. */
+	struct xfs_bmbt_irec	irec;
+
+	/* refcount btree block number of irec.br_startblock */
+	unsigned int		irec_startbno;
+
+	/* refcount btree block number of the next refcount record we expect */
+	unsigned int		next_bno;
+};
+
+/* CoW staging extent. */
+struct xrep_cow_extent {
+	xfs_fsblock_t		fsbno;
+	xfs_extlen_t		len;
+};
+
+/*
+ * Mark the part of the file range that corresponds to the given physical
+ * space.  Caller must ensure that the physical range is within xc->irec.
+ */
+STATIC int
+xrep_cow_mark_file_range(
+	struct xrep_cow		*xc,
+	xfs_fsblock_t		startblock,
+	xfs_filblks_t		blockcount)
+{
+	xfs_fileoff_t		startoff;
+
+	startoff = xc->irec.br_startoff +
+				(startblock - xc->irec.br_startblock);
+
+	trace_xrep_cow_mark_file_range(xc->sc->ip, startblock, startoff,
+			blockcount);
+
+	return xoff_bitmap_set(&xc->bad_fileoffs, startoff, blockcount);
+}
+
+/*
+ * Trim @src to fit within the CoW fork mapping being examined, and put the
+ * result in @dst.
+ */
+static inline void
+xrep_cow_trim_refcount(
+	struct xrep_cow			*xc,
+	struct xfs_refcount_irec	*dst,
+	const struct xfs_refcount_irec	*src)
+{
+	unsigned int			adj;
+
+	memcpy(dst, src, sizeof(*dst));
+
+	if (dst->rc_startblock < xc->irec_startbno) {
+		adj = xc->irec_startbno - dst->rc_startblock;
+		dst->rc_blockcount -= adj;
+		dst->rc_startblock += adj;
+	}
+
+	if (dst->rc_startblock + dst->rc_blockcount >
+	    xc->irec_startbno + xc->irec.br_blockcount) {
+		adj = (dst->rc_startblock + dst->rc_blockcount) -
+		      (xc->irec_startbno + xc->irec.br_blockcount);
+		dst->rc_blockcount -= adj;
+	}
+}
+
+/* Mark any shared CoW staging extents. */
+STATIC int
+xrep_cow_mark_shared_staging(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_refcount_irec	*rec,
+	void				*priv)
+{
+	struct xrep_cow			*xc = priv;
+	struct xfs_refcount_irec	rrec;
+	xfs_fsblock_t			fsbno;
+
+	if (!xfs_refcount_check_domain(rec) ||
+	    rec->rc_domain != XFS_REFC_DOMAIN_SHARED)
+		return -EFSCORRUPTED;
+
+	xrep_cow_trim_refcount(xc, &rrec, rec);
+
+	fsbno = XFS_AGB_TO_FSB(xc->sc->mp, cur->bc_ag.pag->pag_agno,
+			rrec.rc_startblock);
+	return xrep_cow_mark_file_range(xc, fsbno, rrec.rc_blockcount);
+}
+
+/*
+ * Mark any portion of the CoW fork file offset range where there is not a CoW
+ * staging extent record in the refcountbt, and keep a record of where we did
+ * find correct refcountbt records.  Staging records are always cleaned out at
+ * mount time, so any two inodes trying to map the same staging area would have
+ * already taken the fs down due to refcount btree verifier errors.  Hence this
+ * inode should be the sole creator of the staging extent records ondisk.
+ */
+STATIC int
+xrep_cow_mark_missing_staging(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_refcount_irec	*rec,
+	void				*priv)
+{
+	struct xrep_cow			*xc = priv;
+	struct xfs_refcount_irec	rrec;
+	int				error;
+
+	if (!xfs_refcount_check_domain(rec) ||
+	    rec->rc_domain != XFS_REFC_DOMAIN_COW)
+		return -EFSCORRUPTED;
+
+	xrep_cow_trim_refcount(xc, &rrec, rec);
+
+	if (xc->next_bno >= rrec.rc_startblock)
+		goto next;
+
+	error = xrep_cow_mark_file_range(xc,
+			XFS_AGB_TO_FSB(xc->sc->mp, cur->bc_ag.pag->pag_agno,
+				       xc->next_bno),
+			rrec.rc_startblock - xc->next_bno);
+	if (error)
+		return error;
+
+next:
+	xc->next_bno = rrec.rc_startblock + rrec.rc_blockcount;
+	return 0;
+}
+
+/*
+ * Mark any area that does not correspond to a CoW staging rmap.  These are
+ * cross-linked areas that must be avoided.
+ */
+STATIC int
+xrep_cow_mark_missing_staging_rmap(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*rec,
+	void				*priv)
+{
+	struct xrep_cow			*xc = priv;
+	xfs_fsblock_t			fsbno;
+	xfs_agblock_t			rec_bno;
+	xfs_extlen_t			rec_len;
+	unsigned int			adj;
+
+	if (rec->rm_owner == XFS_RMAP_OWN_COW)
+		return 0;
+
+	rec_bno = rec->rm_startblock;
+	rec_len = rec->rm_blockcount;
+	if (rec_bno < xc->irec_startbno) {
+		adj = xc->irec_startbno - rec_bno;
+		rec_len -= adj;
+		rec_bno += adj;
+	}
+
+	if (rec_bno + rec_len > xc->irec_startbno + xc->irec.br_blockcount) {
+		adj = (rec_bno + rec_len) -
+		      (xc->irec_startbno + xc->irec.br_blockcount);
+		rec_len -= adj;
+	}
+
+	fsbno = XFS_AGB_TO_FSB(xc->sc->mp, cur->bc_ag.pag->pag_agno, rec_bno);
+	return xrep_cow_mark_file_range(xc, fsbno, rec_len);
+}
+
+/*
+ * Find any part of the CoW fork mapping that isn't a single-owner CoW staging
+ * extent and mark the corresponding part of the file range in the bitmap.
+ */
+STATIC int
+xrep_cow_find_bad(
+	struct xrep_cow			*xc)
+{
+	struct xfs_refcount_irec	rc_low = { 0 };
+	struct xfs_refcount_irec	rc_high = { 0 };
+	struct xfs_rmap_irec		rm_low = { 0 };
+	struct xfs_rmap_irec		rm_high = { 0 };
+	struct xfs_perag		*pag;
+	struct xfs_scrub		*sc = xc->sc;
+	xfs_agnumber_t			agno;
+	int				error;
+
+	agno = XFS_FSB_TO_AGNO(sc->mp, xc->irec.br_startblock);
+	xc->irec_startbno = XFS_FSB_TO_AGBNO(sc->mp, xc->irec.br_startblock);
+
+	pag = xfs_perag_get(sc->mp, agno);
+	if (!pag)
+		return -EFSCORRUPTED;
+
+	error = xrep_ag_init(sc, pag, &sc->sa);
+	if (error)
+		goto out_pag;
+
+	/* Mark any CoW fork extents that are shared. */
+	rc_low.rc_startblock = xc->irec_startbno;
+	rc_high.rc_startblock = xc->irec_startbno + xc->irec.br_blockcount - 1;
+	rc_low.rc_domain = rc_high.rc_domain = XFS_REFC_DOMAIN_SHARED;
+	error = xfs_refcount_query_range(sc->sa.refc_cur, &rc_low, &rc_high,
+			xrep_cow_mark_shared_staging, xc);
+	if (error)
+		goto out_sa;
+
+	/* Make sure there are CoW staging extents for the whole mapping. */
+	rc_low.rc_startblock = xc->irec_startbno;
+	rc_high.rc_startblock = xc->irec_startbno + xc->irec.br_blockcount - 1;
+	rc_low.rc_domain = rc_high.rc_domain = XFS_REFC_DOMAIN_COW;
+	xc->next_bno = xc->irec_startbno;
+	error = xfs_refcount_query_range(sc->sa.refc_cur, &rc_low, &rc_high,
+			xrep_cow_mark_missing_staging, xc);
+	if (error)
+		goto out_sa;
+
+	if (xc->next_bno < xc->irec_startbno + xc->irec.br_blockcount) {
+		error = xrep_cow_mark_file_range(xc,
+				XFS_AGB_TO_FSB(sc->mp, pag->pag_agno,
+					       xc->next_bno),
+				xc->irec_startbno + xc->irec.br_blockcount -
+				xc->next_bno);
+		if (error)
+			goto out_sa;
+	}
+
+	/* Mark any area has an rmap that isn't a COW staging extent. */
+	rm_low.rm_startblock = xc->irec_startbno;
+	memset(&rm_high, 0xFF, sizeof(rm_high));
+	rm_high.rm_startblock = xc->irec_startbno + xc->irec.br_blockcount - 1;
+	error = xfs_rmap_query_range(sc->sa.rmap_cur, &rm_low, &rm_high,
+			xrep_cow_mark_missing_staging_rmap, xc);
+	if (error)
+		goto out_sa;
+
+	/*
+	 * If userspace is forcing us to rebuild the CoW fork or someone turned
+	 * on the debugging knob, replace everything in the CoW fork.
+	 */
+	if ((sc->sm->sm_flags & XFS_SCRUB_IFLAG_FORCE_REBUILD) ||
+	    XFS_TEST_ERROR(false, sc->mp, XFS_ERRTAG_FORCE_SCRUB_REPAIR)) {
+		error = xrep_cow_mark_file_range(xc, xc->irec.br_startblock,
+				xc->irec.br_blockcount);
+		if (error)
+			return error;
+	}
+
+out_sa:
+	xchk_ag_free(sc, &sc->sa);
+out_pag:
+	xfs_perag_put(pag);
+	return 0;
+}
+
+/*
+ * Allocate a replacement CoW staging extent of up to the given number of
+ * blocks, and fill out the mapping.
+ */
+STATIC int
+xrep_cow_alloc(
+	struct xfs_scrub	*sc,
+	xfs_extlen_t		maxlen,
+	struct xrep_cow_extent	*repl)
+{
+	struct xfs_alloc_arg	args = {
+		.tp		= sc->tp,
+		.mp		= sc->mp,
+		.oinfo		= XFS_RMAP_OINFO_SKIP_UPDATE,
+		.minlen		= 1,
+		.maxlen		= maxlen,
+		.prod		= 1,
+		.resv		= XFS_AG_RESV_NONE,
+		.datatype	= XFS_ALLOC_USERDATA,
+	};
+	int			error;
+
+	error = xfs_trans_reserve_more(sc->tp, maxlen, 0);
+	if (error)
+		return error;
+
+	error = xfs_alloc_vextent_start_ag(&args,
+			XFS_INO_TO_FSB(sc->mp, sc->ip->i_ino));
+	if (error)
+		return error;
+	if (args.fsbno == NULLFSBLOCK)
+		return -ENOSPC;
+
+	xfs_refcount_alloc_cow_extent(sc->tp, args.fsbno, args.len);
+
+	repl->fsbno = args.fsbno;
+	repl->len = args.len;
+	return 0;
+}
+
+/*
+ * Look up the current CoW fork mapping so that we only allocate enough to
+ * replace a single mapping.  If we don't find a mapping that covers the start
+ * of the file range, or we find a delalloc or written extent, something is
+ * seriously wrong, since we didn't drop the ILOCK.
+ */
+static inline int
+xrep_cow_find_mapping(
+	struct xrep_cow		*xc,
+	struct xfs_iext_cursor	*icur,
+	xfs_fileoff_t		startoff,
+	struct xfs_bmbt_irec	*got)
+{
+	struct xfs_inode	*ip = xc->sc->ip;
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, XFS_COW_FORK);
+
+	if (!xfs_iext_lookup_extent(ip, ifp, startoff, icur, got))
+		goto bad;
+
+	if (got->br_startoff > startoff)
+		goto bad;
+
+	if (got->br_blockcount == 0)
+		goto bad;
+
+	if (isnullstartblock(got->br_startblock))
+		goto bad;
+
+	if (xfs_bmap_is_written_extent(got))
+		goto bad;
+
+	return 0;
+bad:
+	ASSERT(0);
+	return -EFSCORRUPTED;
+}
+
+#define REPLACE_LEFT_SIDE	(1U << 0)
+#define REPLACE_RIGHT_SIDE	(1U << 1)
+
+/*
+ * Given a CoW fork mapping @got and a replacement mapping @repl, remap the
+ * beginning of @got with the space described by @rep.
+ */
+static inline void
+xrep_cow_replace_mapping(
+	struct xfs_inode		*ip,
+	struct xfs_iext_cursor		*icur,
+	const struct xfs_bmbt_irec	*got,
+	const struct xrep_cow_extent	*repl)
+{
+	struct xfs_bmbt_irec		new = *got; /* struct copy */
+
+	ASSERT(repl->len > 0);
+	ASSERT(!isnullstartblock(got->br_startblock));
+
+	trace_xrep_cow_replace_mapping(ip, got, repl->fsbno, repl->len);
+
+	if (got->br_blockcount == repl->len) {
+		/*
+		 * The new extent is a complete replacement for the existing
+		 * extent.  Update the COW fork record.
+		 */
+		new.br_startblock = repl->fsbno;
+		xfs_iext_update_extent(ip, BMAP_COWFORK, icur, &new);
+		return;
+	}
+
+	/*
+	 * The new extent can replace the beginning of the COW fork record.
+	 * Move the left side of @got upwards, then insert the new record.
+	 */
+	new.br_startoff += repl->len;
+	new.br_startblock += repl->len;
+	new.br_blockcount -= repl->len;
+	xfs_iext_update_extent(ip, BMAP_COWFORK, icur, &new);
+
+	new.br_startoff = got->br_startoff;
+	new.br_startblock = repl->fsbno;
+	new.br_blockcount = repl->len;
+	xfs_iext_insert(ip, icur, &new, BMAP_COWFORK);
+}
+
+/*
+ * Replace the unwritten CoW staging extent backing the given file range with a
+ * new space extent that isn't as problematic.
+ */
+STATIC int
+xrep_cow_replace_range(
+	struct xrep_cow		*xc,
+	xfs_fileoff_t		startoff,
+	xfs_extlen_t		*blockcount)
+{
+	struct xfs_iext_cursor	icur;
+	struct xrep_cow_extent	repl;
+	struct xfs_bmbt_irec	got;
+	struct xfs_scrub	*sc = xc->sc;
+	xfs_fileoff_t		nextoff;
+	xfs_extlen_t		alloc_len;
+	int			error;
+
+	/*
+	 * Put the existing CoW fork mapping in @got.  If @got ends before
+	 * @rep, truncate @rep so we only replace one extent mapping at a time.
+	 */
+	error = xrep_cow_find_mapping(xc, &icur, startoff, &got);
+	if (error)
+		return error;
+	nextoff = min(startoff + *blockcount,
+		      got.br_startoff + got.br_blockcount);
+
+	/*
+	 * Allocate a replacement extent.  If we don't fill all the blocks,
+	 * shorten the quantity that will be deleted in this step.
+	 */
+	alloc_len = min_t(xfs_fileoff_t, XFS_MAX_BMBT_EXTLEN,
+			  nextoff - startoff);
+	error = xrep_cow_alloc(sc, alloc_len, &repl);
+	if (error)
+		return error;
+
+	/*
+	 * Replace the old mapping with the new one, and commit the metadata
+	 * changes made so far.
+	 */
+	xrep_cow_replace_mapping(sc->ip, &icur, &got, &repl);
+
+	xfs_inode_set_cowblocks_tag(sc->ip);
+	error = xfs_defer_finish(&sc->tp);
+	if (error)
+		return error;
+
+	/* Note the old CoW staging extents; we'll reap them all later. */
+	error = xfsb_bitmap_set(&xc->old_cowfork_fsblocks, got.br_startblock,
+			repl.len);
+	if (error)
+		return error;
+
+	*blockcount = repl.len;
+	return 0;
+}
+
+/*
+ * Replace a bad part of an unwritten CoW staging extent with a fresh delalloc
+ * reservation.
+ */
+STATIC int
+xrep_cow_replace(
+	uint64_t		startoff,
+	uint64_t		blockcount,
+	void			*priv)
+{
+	struct xrep_cow		*xc = priv;
+	int			error = 0;
+
+	while (blockcount > 0) {
+		xfs_extlen_t	len = min_t(xfs_filblks_t, blockcount,
+					    XFS_MAX_BMBT_EXTLEN);
+
+		error = xrep_cow_replace_range(xc, startoff, &len);
+		if (error)
+			break;
+
+		blockcount -= len;
+		startoff += len;
+	}
+
+	return error;
+}
+
+/*
+ * Repair an inode's CoW fork.  The CoW fork is an in-core structure, so
+ * there's no btree to rebuid.  Instead, we replace any mappings that are
+ * cross-linked or lack ondisk CoW fork records in the refcount btree.
+ */
+int
+xrep_bmap_cow(
+	struct xfs_scrub	*sc)
+{
+	struct xrep_cow		*xc;
+	struct xfs_iext_cursor	icur;
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(sc->ip, XFS_COW_FORK);
+	int			error;
+
+	if (!xfs_has_rmapbt(sc->mp) || !xfs_has_reflink(sc->mp))
+		return -EOPNOTSUPP;
+
+	if (!ifp)
+		return 0;
+
+	/* realtime files aren't supported yet */
+	if (XFS_IS_REALTIME_INODE(sc->ip))
+		return -EOPNOTSUPP;
+
+	/*
+	 * If we're somehow not in extents format, then reinitialize it to
+	 * an empty extent mapping fork and exit.
+	 */
+	if (ifp->if_format != XFS_DINODE_FMT_EXTENTS) {
+		ifp->if_format = XFS_DINODE_FMT_EXTENTS;
+		ifp->if_nextents = 0;
+		return 0;
+	}
+
+	xc = kzalloc(sizeof(struct xrep_cow), XCHK_GFP_FLAGS);
+	if (!xc)
+		return -ENOMEM;
+
+	xfs_trans_ijoin(sc->tp, sc->ip, 0);
+
+	xc->sc = sc;
+	xoff_bitmap_init(&xc->bad_fileoffs);
+	xfsb_bitmap_init(&xc->old_cowfork_fsblocks);
+
+	for_each_xfs_iext(ifp, &icur, &xc->irec) {
+		if (xchk_should_terminate(sc, &error))
+			goto out_bitmap;
+
+		/*
+		 * delalloc reservations only exist incore, so there is no
+		 * ondisk metadata that we can examine.  Hence we leave them
+		 * alone.
+		 */
+		if (isnullstartblock(xc->irec.br_startblock))
+			continue;
+
+		/*
+		 * COW fork extents are only in the written state if writeback
+		 * is actively writing to disk.  We cannot restart the write
+		 * at a different disk address since we've already issued the
+		 * IO, so we leave these alone and hope for the best.
+		 */
+		if (xfs_bmap_is_written_extent(&xc->irec))
+			continue;
+
+		error = xrep_cow_find_bad(xc);
+		if (error)
+			goto out_bitmap;
+	}
+
+	/* Replace any bad unwritten mappings with fresh reservations. */
+	error = xoff_bitmap_walk(&xc->bad_fileoffs, xrep_cow_replace, xc);
+	if (error)
+		goto out_bitmap;
+
+	/*
+	 * Reap as many of the old CoW blocks as we can.  They are owned ondisk
+	 * by the refcount btree, not the inode, so it is correct to treat them
+	 * like inode metadata.
+	 */
+	error = xrep_reap_fsblocks(sc, &xc->old_cowfork_fsblocks,
+			&XFS_RMAP_OINFO_COW);
+	if (error)
+		goto out_bitmap;
+
+out_bitmap:
+	xfsb_bitmap_destroy(&xc->old_cowfork_fsblocks);
+	xoff_bitmap_destroy(&xc->bad_fileoffs);
+	kmem_free(xc);
+	return error;
+}
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index 0b491784b759..d86ab51af928 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -15,10 +15,12 @@
 #include "xfs_icache.h"
 #include "xfs_dir2.h"
 #include "xfs_dir2_priv.h"
+#include "xfs_health.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/dabtree.h"
 #include "scrub/readdir.h"
+#include "scrub/health.h"
 
 /* Set us up to scrub directories. */
 int
@@ -760,6 +762,11 @@ xchk_directory(
 	if (!S_ISDIR(VFS_I(sc->ip)->i_mode))
 		return -ENOENT;
 
+	if (xchk_file_looks_zapped(sc, XFS_SICK_INO_DIR_ZAPPED)) {
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		return 0;
+	}
+
 	/* Plausible size? */
 	if (sc->ip->i_disk_size < xfs_dir2_sf_hdr_size(0)) {
 		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
@@ -784,7 +791,36 @@ xchk_directory(
 
 	/* Look up every name in this directory by hash. */
 	error = xchk_dir_walk(sc, sc->ip, xchk_dir_actor, NULL);
-	if (error == -ECANCELED)
-		error = 0;
-	return error;
+	if (error && error != -ECANCELED)
+		return error;
+
+	/* If the dir is clean, it is clearly not zapped. */
+	xchk_mark_healthy_if_clean(sc, XFS_SICK_INO_DIR_ZAPPED);
+	return 0;
+}
+
+/*
+ * Decide if this directory has been zapped to satisfy the inode and ifork
+ * verifiers.  Checking and repairing should be postponed until the directory
+ * is fixed.
+ */
+bool
+xchk_dir_looks_zapped(
+	struct xfs_inode	*dp)
+{
+	/* Repair zapped this dir's data fork a short time ago */
+	if (xfs_ifork_zapped(dp, XFS_DATA_FORK))
+		return true;
+
+	/*
+	 * If the dinode repair found a bad data fork, it will reset the fork
+	 * to extents format with zero records and wait for the bmapbtd
+	 * scrubber to reconstruct the block mappings.  Directories always
+	 * contain some content, so this is a clear sign of a zapped directory.
+	 * The state checked by xfs_ifork_zapped is not persisted, so this is
+	 * the secondary strategy if repairs are interrupted by a crash or an
+	 * unmount.
+	 */
+	return dp->i_df.if_format == XFS_DINODE_FMT_EXTENTS &&
+	       dp->i_df.if_nextents == 0;
 }
diff --git a/fs/xfs/scrub/dqiterate.c b/fs/xfs/scrub/dqiterate.c
new file mode 100644
index 000000000000..20c4daedd48d
--- /dev/null
+++ b/fs/xfs/scrub/dqiterate.c
@@ -0,0 +1,211 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_bit.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_inode.h"
+#include "xfs_quota.h"
+#include "xfs_qm.h"
+#include "xfs_bmap.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/quota.h"
+#include "scrub/trace.h"
+
+/* Initialize a dquot iteration cursor. */
+void
+xchk_dqiter_init(
+	struct xchk_dqiter	*cursor,
+	struct xfs_scrub	*sc,
+	xfs_dqtype_t		dqtype)
+{
+	cursor->sc = sc;
+	cursor->bmap.br_startoff = NULLFILEOFF;
+	cursor->dqtype = dqtype & XFS_DQTYPE_REC_MASK;
+	cursor->quota_ip = xfs_quota_inode(sc->mp, cursor->dqtype);
+	cursor->id = 0;
+}
+
+/*
+ * Ensure that the cached data fork mapping for the dqiter cursor is fresh and
+ * covers the dquot pointed to by the scan cursor.
+ */
+STATIC int
+xchk_dquot_iter_revalidate_bmap(
+	struct xchk_dqiter	*cursor)
+{
+	struct xfs_quotainfo	*qi = cursor->sc->mp->m_quotainfo;
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(cursor->quota_ip,
+								XFS_DATA_FORK);
+	xfs_fileoff_t		fileoff;
+	xfs_dqid_t		this_id = cursor->id;
+	int			nmaps = 1;
+	int			error;
+
+	fileoff = this_id / qi->qi_dqperchunk;
+
+	/*
+	 * If we have a mapping for cursor->id and it's still fresh, there's
+	 * no need to reread the bmbt.
+	 */
+	if (cursor->bmap.br_startoff != NULLFILEOFF &&
+	    cursor->if_seq == ifp->if_seq &&
+	    cursor->bmap.br_startoff + cursor->bmap.br_blockcount > fileoff)
+		return 0;
+
+	/* Look up the data fork mapping for the dquot id of interest. */
+	error = xfs_bmapi_read(cursor->quota_ip, fileoff,
+			XFS_MAX_FILEOFF - fileoff, &cursor->bmap, &nmaps, 0);
+	if (error)
+		return error;
+	if (!nmaps) {
+		ASSERT(nmaps > 0);
+		return -EFSCORRUPTED;
+	}
+	if (cursor->bmap.br_startoff > fileoff) {
+		ASSERT(cursor->bmap.br_startoff == fileoff);
+		return -EFSCORRUPTED;
+	}
+
+	cursor->if_seq = ifp->if_seq;
+	trace_xchk_dquot_iter_revalidate_bmap(cursor, cursor->id);
+	return 0;
+}
+
+/* Advance the dqiter cursor to the next non-sparse region of the quota file. */
+STATIC int
+xchk_dquot_iter_advance_bmap(
+	struct xchk_dqiter	*cursor,
+	uint64_t		*next_ondisk_id)
+{
+	struct xfs_quotainfo	*qi = cursor->sc->mp->m_quotainfo;
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(cursor->quota_ip,
+								XFS_DATA_FORK);
+	xfs_fileoff_t		fileoff;
+	uint64_t		next_id;
+	int			nmaps = 1;
+	int			error;
+
+	/* Find the dquot id for the next non-hole mapping. */
+	do {
+		fileoff = cursor->bmap.br_startoff + cursor->bmap.br_blockcount;
+		if (fileoff > XFS_DQ_ID_MAX / qi->qi_dqperchunk) {
+			/* The hole goes beyond the max dquot id, we're done */
+			*next_ondisk_id = -1ULL;
+			return 0;
+		}
+
+		error = xfs_bmapi_read(cursor->quota_ip, fileoff,
+				XFS_MAX_FILEOFF - fileoff, &cursor->bmap,
+				&nmaps, 0);
+		if (error)
+			return error;
+		if (!nmaps) {
+			/* Must have reached the end of the mappings. */
+			*next_ondisk_id = -1ULL;
+			return 0;
+		}
+		if (cursor->bmap.br_startoff > fileoff) {
+			ASSERT(cursor->bmap.br_startoff == fileoff);
+			return -EFSCORRUPTED;
+		}
+	} while (!xfs_bmap_is_real_extent(&cursor->bmap));
+
+	next_id = cursor->bmap.br_startoff * qi->qi_dqperchunk;
+	if (next_id > XFS_DQ_ID_MAX) {
+		/* The hole goes beyond the max dquot id, we're done */
+		*next_ondisk_id = -1ULL;
+		return 0;
+	}
+
+	/* Propose jumping forward to the dquot in the next allocated block. */
+	*next_ondisk_id = next_id;
+	cursor->if_seq = ifp->if_seq;
+	trace_xchk_dquot_iter_advance_bmap(cursor, *next_ondisk_id);
+	return 0;
+}
+
+/*
+ * Find the id of the next highest incore dquot.  Normally this will correspond
+ * exactly with the quota file block mappings, but repair might have erased a
+ * mapping because it was crosslinked; in that case, we need to re-allocate the
+ * space so that we can reset q_blkno.
+ */
+STATIC void
+xchk_dquot_iter_advance_incore(
+	struct xchk_dqiter	*cursor,
+	uint64_t		*next_incore_id)
+{
+	struct xfs_quotainfo	*qi = cursor->sc->mp->m_quotainfo;
+	struct radix_tree_root	*tree = xfs_dquot_tree(qi, cursor->dqtype);
+	struct xfs_dquot	*dq;
+	unsigned int		nr_found;
+
+	*next_incore_id = -1ULL;
+
+	mutex_lock(&qi->qi_tree_lock);
+	nr_found = radix_tree_gang_lookup(tree, (void **)&dq, cursor->id, 1);
+	if (nr_found)
+		*next_incore_id = dq->q_id;
+	mutex_unlock(&qi->qi_tree_lock);
+
+	trace_xchk_dquot_iter_advance_incore(cursor, *next_incore_id);
+}
+
+/*
+ * Walk all incore dquots of this filesystem.  Caller must set *@cursorp to
+ * zero before the first call, and must not hold the quota file ILOCK.
+ * Returns 1 and a valid *@dqpp; 0 and *@dqpp == NULL when there are no more
+ * dquots to iterate; or a negative errno.
+ */
+int
+xchk_dquot_iter(
+	struct xchk_dqiter	*cursor,
+	struct xfs_dquot	**dqpp)
+{
+	struct xfs_mount	*mp = cursor->sc->mp;
+	struct xfs_dquot	*dq = NULL;
+	uint64_t		next_ondisk, next_incore = -1ULL;
+	unsigned int		lock_mode;
+	int			error = 0;
+
+	if (cursor->id > XFS_DQ_ID_MAX)
+		return 0;
+	next_ondisk = cursor->id;
+
+	/* Revalidate and/or advance the cursor. */
+	lock_mode = xfs_ilock_data_map_shared(cursor->quota_ip);
+	error = xchk_dquot_iter_revalidate_bmap(cursor);
+	if (!error && !xfs_bmap_is_real_extent(&cursor->bmap))
+		error = xchk_dquot_iter_advance_bmap(cursor, &next_ondisk);
+	xfs_iunlock(cursor->quota_ip, lock_mode);
+	if (error)
+		return error;
+
+	if (next_ondisk > cursor->id)
+		xchk_dquot_iter_advance_incore(cursor, &next_incore);
+
+	/* Pick the next dquot in the sequence and return it. */
+	cursor->id = min(next_ondisk, next_incore);
+	if (cursor->id > XFS_DQ_ID_MAX)
+		return 0;
+
+	trace_xchk_dquot_iter(cursor, cursor->id);
+
+	error = xfs_qm_dqget(mp, cursor->id, cursor->dqtype, false, &dq);
+	if (error)
+		return error;
+
+	cursor->id = dq->q_id + 1;
+	*dqpp = dq;
+	return 1;
+}
diff --git a/fs/xfs/scrub/fsb_bitmap.h b/fs/xfs/scrub/fsb_bitmap.h
new file mode 100644
index 000000000000..40b462c1dd0d
--- /dev/null
+++ b/fs/xfs/scrub/fsb_bitmap.h
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_FSB_BITMAP_H__
+#define __XFS_SCRUB_FSB_BITMAP_H__
+
+/* Bitmaps, but for type-checked for xfs_fsblock_t */
+
+struct xfsb_bitmap {
+	struct xbitmap64	fsbitmap;
+};
+
+static inline void xfsb_bitmap_init(struct xfsb_bitmap *bitmap)
+{
+	xbitmap64_init(&bitmap->fsbitmap);
+}
+
+static inline void xfsb_bitmap_destroy(struct xfsb_bitmap *bitmap)
+{
+	xbitmap64_destroy(&bitmap->fsbitmap);
+}
+
+static inline int xfsb_bitmap_set(struct xfsb_bitmap *bitmap,
+		xfs_fsblock_t start, xfs_filblks_t len)
+{
+	return xbitmap64_set(&bitmap->fsbitmap, start, len);
+}
+
+static inline int xfsb_bitmap_walk(struct xfsb_bitmap *bitmap,
+		xbitmap64_walk_fn fn, void *priv)
+{
+	return xbitmap64_walk(&bitmap->fsbitmap, fn, priv);
+}
+
+#endif	/* __XFS_SCRUB_FSB_BITMAP_H__ */
diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c
index 5e2b09ed6e29..531006910ca9 100644
--- a/fs/xfs/scrub/health.c
+++ b/fs/xfs/scrub/health.c
@@ -10,8 +10,6 @@
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"
 #include "xfs_btree.h"
-#include "xfs_trans_resv.h"
-#include "xfs_mount.h"
 #include "xfs_ag.h"
 #include "xfs_health.h"
 #include "scrub/scrub.h"
@@ -118,6 +116,38 @@ xchk_health_mask_for_scrub_type(
 }
 
 /*
+ * If the scrub state is clean, add @mask to the scrub sick mask to clear
+ * additional sick flags from the metadata object's sick state.
+ */
+void
+xchk_mark_healthy_if_clean(
+	struct xfs_scrub	*sc,
+	unsigned int		mask)
+{
+	if (!(sc->sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
+				  XFS_SCRUB_OFLAG_XCORRUPT)))
+		sc->sick_mask |= mask;
+}
+
+/*
+ * If we're scrubbing a piece of file metadata for the first time, does it look
+ * like it has been zapped?  Skip the check if we just repaired the metadata
+ * and are revalidating it.
+ */
+bool
+xchk_file_looks_zapped(
+	struct xfs_scrub	*sc,
+	unsigned int		mask)
+{
+	ASSERT((mask & ~XFS_SICK_INO_ZAPPED) == 0);
+
+	if (sc->flags & XREP_ALREADY_FIXED)
+		return false;
+
+	return xfs_inode_has_sickness(sc->ip, mask);
+}
+
+/*
  * Update filesystem health assessments based on what we found and did.
  *
  * If the scrubber finds errors, we mark sick whatever's mentioned in
diff --git a/fs/xfs/scrub/health.h b/fs/xfs/scrub/health.h
index 66a273f8585b..a731b2467399 100644
--- a/fs/xfs/scrub/health.h
+++ b/fs/xfs/scrub/health.h
@@ -10,5 +10,7 @@ unsigned int xchk_health_mask_for_scrub_type(__u32 scrub_type);
 void xchk_update_health(struct xfs_scrub *sc);
 bool xchk_ag_btree_healthy_enough(struct xfs_scrub *sc, struct xfs_perag *pag,
 		xfs_btnum_t btnum);
+void xchk_mark_healthy_if_clean(struct xfs_scrub *sc, unsigned int mask);
+bool xchk_file_looks_zapped(struct xfs_scrub *sc, unsigned int mask);
 
 #endif /* __XFS_SCRUB_HEALTH_H__ */
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index fb7bbf47ae5d..a720fc62262a 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -585,7 +585,7 @@ xchk_iallocbt_rec(
 	uint16_t			holemask;
 
 	xfs_inobt_btrec_to_irec(mp, rec, &irec);
-	if (xfs_inobt_check_irec(bs->cur, &irec) != NULL) {
+	if (xfs_inobt_check_irec(bs->cur->bc_ag.pag, &irec) != NULL) {
 		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 		return 0;
 	}
@@ -708,11 +708,10 @@ xchk_iallocbt_xref_rmap_inodes(
 		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 }
 
-/* Scrub the inode btrees for some AG. */
-STATIC int
+/* Scrub one of the inode btrees for some AG. */
+int
 xchk_iallocbt(
-	struct xfs_scrub	*sc,
-	xfs_btnum_t		which)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_btree_cur	*cur;
 	struct xchk_iallocbt	iabt = {
@@ -720,9 +719,23 @@ xchk_iallocbt(
 		.next_startino	= NULLAGINO,
 		.next_cluster_ino = NULLAGINO,
 	};
+	xfs_btnum_t		which;
 	int			error;
 
-	cur = which == XFS_BTNUM_INO ? sc->sa.ino_cur : sc->sa.fino_cur;
+	switch (sc->sm->sm_type) {
+	case XFS_SCRUB_TYPE_INOBT:
+		cur = sc->sa.ino_cur;
+		which = XFS_BTNUM_INO;
+		break;
+	case XFS_SCRUB_TYPE_FINOBT:
+		cur = sc->sa.fino_cur;
+		which = XFS_BTNUM_FINO;
+		break;
+	default:
+		ASSERT(0);
+		return -EIO;
+	}
+
 	error = xchk_btree(sc, cur, xchk_iallocbt_rec, &XFS_RMAP_OINFO_INOBT,
 			&iabt);
 	if (error)
@@ -743,20 +756,6 @@ xchk_iallocbt(
 	return error;
 }
 
-int
-xchk_inobt(
-	struct xfs_scrub	*sc)
-{
-	return xchk_iallocbt(sc, XFS_BTNUM_INO);
-}
-
-int
-xchk_finobt(
-	struct xfs_scrub	*sc)
-{
-	return xchk_iallocbt(sc, XFS_BTNUM_FINO);
-}
-
 /* See if an inode btree has (or doesn't have) an inode chunk record. */
 static inline void
 xchk_xref_inode_check(
diff --git a/fs/xfs/scrub/ialloc_repair.c b/fs/xfs/scrub/ialloc_repair.c
new file mode 100644
index 000000000000..b3f7182dd2f5
--- /dev/null
+++ b/fs/xfs/scrub/ialloc_repair.c
@@ -0,0 +1,884 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_btree_staging.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_alloc.h"
+#include "xfs_ialloc.h"
+#include "xfs_ialloc_btree.h"
+#include "xfs_icache.h"
+#include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_log.h"
+#include "xfs_trans_priv.h"
+#include "xfs_error.h"
+#include "xfs_health.h"
+#include "xfs_ag.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/btree.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/bitmap.h"
+#include "scrub/agb_bitmap.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/newbt.h"
+#include "scrub/reap.h"
+
+/*
+ * Inode Btree Repair
+ * ==================
+ *
+ * A quick refresher of inode btrees on a v5 filesystem:
+ *
+ * - Inode records are read into memory in units of 'inode clusters'.  However
+ *   many inodes fit in a cluster buffer is the smallest number of inodes that
+ *   can be allocated or freed.  Clusters are never smaller than one fs block
+ *   though they can span multiple blocks.  The size (in fs blocks) is
+ *   computed with xfs_icluster_size_fsb().  The fs block alignment of a
+ *   cluster is computed with xfs_ialloc_cluster_alignment().
+ *
+ * - Each inode btree record can describe a single 'inode chunk'.  The chunk
+ *   size is defined to be 64 inodes.  If sparse inodes are enabled, every
+ *   inobt record must be aligned to the chunk size; if not, every record must
+ *   be aligned to the start of a cluster.  It is possible to construct an XFS
+ *   geometry where one inobt record maps to multiple inode clusters; it is
+ *   also possible to construct a geometry where multiple inobt records map to
+ *   different parts of one inode cluster.
+ *
+ * - If sparse inodes are not enabled, the smallest unit of allocation for
+ *   inode records is enough to contain one inode chunk's worth of inodes.
+ *
+ * - If sparse inodes are enabled, the holemask field will be active.  Each
+ *   bit of the holemask represents 4 potential inodes; if set, the
+ *   corresponding space does *not* contain inodes and must be left alone.
+ *   Clusters cannot be smaller than 4 inodes.  The smallest unit of allocation
+ *   of inode records is one inode cluster.
+ *
+ * So what's the rebuild algorithm?
+ *
+ * Iterate the reverse mapping records looking for OWN_INODES and OWN_INOBT
+ * records.  The OWN_INOBT records are the old inode btree blocks and will be
+ * cleared out after we've rebuilt the tree.  Each possible inode cluster
+ * within an OWN_INODES record will be read in; for each possible inobt record
+ * associated with that cluster, compute the freemask calculated from the
+ * i_mode data in the inode chunk.  For sparse inodes the holemask will be
+ * calculated by creating the properly aligned inobt record and punching out
+ * any chunk that's missing.  Inode allocations and frees grab the AGI first,
+ * so repair protects itself from concurrent access by locking the AGI.
+ *
+ * Once we've reconstructed all the inode records, we can create new inode
+ * btree roots and reload the btrees.  We rebuild both inode trees at the same
+ * time because they have the same rmap owner and it would be more complex to
+ * figure out if the other tree isn't in need of a rebuild and which OWN_INOBT
+ * blocks it owns.  We have all the data we need to build both, so dump
+ * everything and start over.
+ *
+ * We use the prefix 'xrep_ibt' because we rebuild both inode btrees at once.
+ */
+
+struct xrep_ibt {
+	/* Record under construction. */
+	struct xfs_inobt_rec_incore	rie;
+
+	/* new inobt information */
+	struct xrep_newbt	new_inobt;
+
+	/* new finobt information */
+	struct xrep_newbt	new_finobt;
+
+	/* Old inode btree blocks we found in the rmap. */
+	struct xagb_bitmap	old_iallocbt_blocks;
+
+	/* Reconstructed inode records. */
+	struct xfarray		*inode_records;
+
+	struct xfs_scrub	*sc;
+
+	/* Number of inodes assigned disk space. */
+	unsigned int		icount;
+
+	/* Number of inodes in use. */
+	unsigned int		iused;
+
+	/* Number of finobt records needed. */
+	unsigned int		finobt_recs;
+
+	/* get_records()'s position in the inode record array. */
+	xfarray_idx_t		array_cur;
+};
+
+/*
+ * Is this inode in use?  If the inode is in memory we can tell from i_mode,
+ * otherwise we have to check di_mode in the on-disk buffer.  We only care
+ * that the high (i.e. non-permission) bits of _mode are zero.  This should be
+ * safe because repair keeps all AG headers locked until the end, and process
+ * trying to perform an inode allocation/free must lock the AGI.
+ *
+ * @cluster_ag_base is the inode offset of the cluster within the AG.
+ * @cluster_bp is the cluster buffer.
+ * @cluster_index is the inode offset within the inode cluster.
+ */
+STATIC int
+xrep_ibt_check_ifree(
+	struct xrep_ibt		*ri,
+	xfs_agino_t		cluster_ag_base,
+	struct xfs_buf		*cluster_bp,
+	unsigned int		cluster_index,
+	bool			*inuse)
+{
+	struct xfs_scrub	*sc = ri->sc;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_dinode	*dip;
+	xfs_ino_t		fsino;
+	xfs_agino_t		agino;
+	xfs_agnumber_t		agno = ri->sc->sa.pag->pag_agno;
+	unsigned int		cluster_buf_base;
+	unsigned int		offset;
+	int			error;
+
+	agino = cluster_ag_base + cluster_index;
+	fsino = XFS_AGINO_TO_INO(mp, agno, agino);
+
+	/* Inode uncached or half assembled, read disk buffer */
+	cluster_buf_base = XFS_INO_TO_OFFSET(mp, cluster_ag_base);
+	offset = (cluster_buf_base + cluster_index) * mp->m_sb.sb_inodesize;
+	if (offset >= BBTOB(cluster_bp->b_length))
+		return -EFSCORRUPTED;
+	dip = xfs_buf_offset(cluster_bp, offset);
+	if (be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC)
+		return -EFSCORRUPTED;
+
+	if (dip->di_version >= 3 && be64_to_cpu(dip->di_ino) != fsino)
+		return -EFSCORRUPTED;
+
+	/* Will the in-core inode tell us if it's in use? */
+	error = xchk_inode_is_allocated(sc, agino, inuse);
+	if (!error)
+		return 0;
+
+	*inuse = dip->di_mode != 0;
+	return 0;
+}
+
+/* Stash the accumulated inobt record for rebuilding. */
+STATIC int
+xrep_ibt_stash(
+	struct xrep_ibt		*ri)
+{
+	int			error = 0;
+
+	if (xchk_should_terminate(ri->sc, &error))
+		return error;
+
+	ri->rie.ir_freecount = xfs_inobt_rec_freecount(&ri->rie);
+	if (xfs_inobt_check_irec(ri->sc->sa.pag, &ri->rie) != NULL)
+		return -EFSCORRUPTED;
+
+	if (ri->rie.ir_freecount > 0)
+		ri->finobt_recs++;
+
+	trace_xrep_ibt_found(ri->sc->mp, ri->sc->sa.pag->pag_agno, &ri->rie);
+
+	error = xfarray_append(ri->inode_records, &ri->rie);
+	if (error)
+		return error;
+
+	ri->rie.ir_startino = NULLAGINO;
+	return 0;
+}
+
+/*
+ * Given an extent of inodes and an inode cluster buffer, calculate the
+ * location of the corresponding inobt record (creating it if necessary),
+ * then update the parts of the holemask and freemask of that record that
+ * correspond to the inode extent we were given.
+ *
+ * @cluster_ir_startino is the AG inode number of an inobt record that we're
+ * proposing to create for this inode cluster.  If sparse inodes are enabled,
+ * we must round down to a chunk boundary to find the actual sparse record.
+ * @cluster_bp is the buffer of the inode cluster.
+ * @nr_inodes is the number of inodes to check from the cluster.
+ */
+STATIC int
+xrep_ibt_cluster_record(
+	struct xrep_ibt		*ri,
+	xfs_agino_t		cluster_ir_startino,
+	struct xfs_buf		*cluster_bp,
+	unsigned int		nr_inodes)
+{
+	struct xfs_scrub	*sc = ri->sc;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agino_t		ir_startino;
+	unsigned int		cluster_base;
+	unsigned int		cluster_index;
+	int			error = 0;
+
+	ir_startino = cluster_ir_startino;
+	if (xfs_has_sparseinodes(mp))
+		ir_startino = rounddown(ir_startino, XFS_INODES_PER_CHUNK);
+	cluster_base = cluster_ir_startino - ir_startino;
+
+	/*
+	 * If the accumulated inobt record doesn't map this cluster, add it to
+	 * the list and reset it.
+	 */
+	if (ri->rie.ir_startino != NULLAGINO &&
+	    ri->rie.ir_startino + XFS_INODES_PER_CHUNK <= ir_startino) {
+		error = xrep_ibt_stash(ri);
+		if (error)
+			return error;
+	}
+
+	if (ri->rie.ir_startino == NULLAGINO) {
+		ri->rie.ir_startino = ir_startino;
+		ri->rie.ir_free = XFS_INOBT_ALL_FREE;
+		ri->rie.ir_holemask = 0xFFFF;
+		ri->rie.ir_count = 0;
+	}
+
+	/* Record the whole cluster. */
+	ri->icount += nr_inodes;
+	ri->rie.ir_count += nr_inodes;
+	ri->rie.ir_holemask &= ~xfs_inobt_maskn(
+				cluster_base / XFS_INODES_PER_HOLEMASK_BIT,
+				nr_inodes / XFS_INODES_PER_HOLEMASK_BIT);
+
+	/* Which inodes within this cluster are free? */
+	for (cluster_index = 0; cluster_index < nr_inodes; cluster_index++) {
+		bool		inuse = false;
+
+		error = xrep_ibt_check_ifree(ri, cluster_ir_startino,
+				cluster_bp, cluster_index, &inuse);
+		if (error)
+			return error;
+		if (!inuse)
+			continue;
+		ri->iused++;
+		ri->rie.ir_free &= ~XFS_INOBT_MASK(cluster_base +
+						   cluster_index);
+	}
+	return 0;
+}
+
+/*
+ * For each inode cluster covering the physical extent recorded by the rmapbt,
+ * we must calculate the properly aligned startino of that cluster, then
+ * iterate each cluster to fill in used and filled masks appropriately.  We
+ * then use the (startino, used, filled) information to construct the
+ * appropriate inode records.
+ */
+STATIC int
+xrep_ibt_process_cluster(
+	struct xrep_ibt		*ri,
+	xfs_agblock_t		cluster_bno)
+{
+	struct xfs_imap		imap;
+	struct xfs_buf		*cluster_bp;
+	struct xfs_scrub	*sc = ri->sc;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_ino_geometry	*igeo = M_IGEO(mp);
+	xfs_agino_t		cluster_ag_base;
+	xfs_agino_t		irec_index;
+	unsigned int		nr_inodes;
+	int			error;
+
+	nr_inodes = min_t(unsigned int, igeo->inodes_per_cluster,
+			XFS_INODES_PER_CHUNK);
+
+	/*
+	 * Grab the inode cluster buffer.  This is safe to do with a broken
+	 * inobt because imap_to_bp directly maps the buffer without touching
+	 * either inode btree.
+	 */
+	imap.im_blkno = XFS_AGB_TO_DADDR(mp, sc->sa.pag->pag_agno, cluster_bno);
+	imap.im_len = XFS_FSB_TO_BB(mp, igeo->blocks_per_cluster);
+	imap.im_boffset = 0;
+	error = xfs_imap_to_bp(mp, sc->tp, &imap, &cluster_bp);
+	if (error)
+		return error;
+
+	/*
+	 * Record the contents of each possible inobt record mapping this
+	 * cluster.
+	 */
+	cluster_ag_base = XFS_AGB_TO_AGINO(mp, cluster_bno);
+	for (irec_index = 0;
+	     irec_index < igeo->inodes_per_cluster;
+	     irec_index += XFS_INODES_PER_CHUNK) {
+		error = xrep_ibt_cluster_record(ri,
+				cluster_ag_base + irec_index, cluster_bp,
+				nr_inodes);
+		if (error)
+			break;
+
+	}
+
+	xfs_trans_brelse(sc->tp, cluster_bp);
+	return error;
+}
+
+/* Check for any obvious conflicts in the inode chunk extent. */
+STATIC int
+xrep_ibt_check_inode_ext(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
+{
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_ino_geometry	*igeo = M_IGEO(mp);
+	xfs_agino_t		agino;
+	enum xbtree_recpacking	outcome;
+	int			error;
+
+	/* Inode records must be within the AG. */
+	if (!xfs_verify_agbext(sc->sa.pag, agbno, len))
+		return -EFSCORRUPTED;
+
+	/* The entire record must align to the inode cluster size. */
+	if (!IS_ALIGNED(agbno, igeo->blocks_per_cluster) ||
+	    !IS_ALIGNED(agbno + len, igeo->blocks_per_cluster))
+		return -EFSCORRUPTED;
+
+	/*
+	 * The entire record must also adhere to the inode cluster alignment
+	 * size if sparse inodes are not enabled.
+	 */
+	if (!xfs_has_sparseinodes(mp) &&
+	    (!IS_ALIGNED(agbno, igeo->cluster_align) ||
+	     !IS_ALIGNED(agbno + len, igeo->cluster_align)))
+		return -EFSCORRUPTED;
+
+	/*
+	 * On a sparse inode fs, this cluster could be part of a sparse chunk.
+	 * Sparse clusters must be aligned to sparse chunk alignment.
+	 */
+	if (xfs_has_sparseinodes(mp) &&
+	    (!IS_ALIGNED(agbno, mp->m_sb.sb_spino_align) ||
+	     !IS_ALIGNED(agbno + len, mp->m_sb.sb_spino_align)))
+		return -EFSCORRUPTED;
+
+	/* Make sure the entire range of blocks are valid AG inodes. */
+	agino = XFS_AGB_TO_AGINO(mp, agbno);
+	if (!xfs_verify_agino(sc->sa.pag, agino))
+		return -EFSCORRUPTED;
+
+	agino = XFS_AGB_TO_AGINO(mp, agbno + len) - 1;
+	if (!xfs_verify_agino(sc->sa.pag, agino))
+		return -EFSCORRUPTED;
+
+	/* Make sure this isn't free space. */
+	error = xfs_alloc_has_records(sc->sa.bno_cur, agbno, len, &outcome);
+	if (error)
+		return error;
+	if (outcome != XBTREE_RECPACKING_EMPTY)
+		return -EFSCORRUPTED;
+
+	return 0;
+}
+
+/* Found a fragment of the old inode btrees; dispose of them later. */
+STATIC int
+xrep_ibt_record_old_btree_blocks(
+	struct xrep_ibt			*ri,
+	const struct xfs_rmap_irec	*rec)
+{
+	if (!xfs_verify_agbext(ri->sc->sa.pag, rec->rm_startblock,
+				rec->rm_blockcount))
+		return -EFSCORRUPTED;
+
+	return xagb_bitmap_set(&ri->old_iallocbt_blocks, rec->rm_startblock,
+			rec->rm_blockcount);
+}
+
+/* Record extents that belong to inode cluster blocks. */
+STATIC int
+xrep_ibt_record_inode_blocks(
+	struct xrep_ibt			*ri,
+	const struct xfs_rmap_irec	*rec)
+{
+	struct xfs_mount		*mp = ri->sc->mp;
+	struct xfs_ino_geometry		*igeo = M_IGEO(mp);
+	xfs_agblock_t			cluster_base;
+	int				error;
+
+	error = xrep_ibt_check_inode_ext(ri->sc, rec->rm_startblock,
+			rec->rm_blockcount);
+	if (error)
+		return error;
+
+	trace_xrep_ibt_walk_rmap(mp, ri->sc->sa.pag->pag_agno,
+			rec->rm_startblock, rec->rm_blockcount, rec->rm_owner,
+			rec->rm_offset, rec->rm_flags);
+
+	/*
+	 * Record the free/hole masks for each inode cluster that could be
+	 * mapped by this rmap record.
+	 */
+	for (cluster_base = 0;
+	     cluster_base < rec->rm_blockcount;
+	     cluster_base += igeo->blocks_per_cluster) {
+		error = xrep_ibt_process_cluster(ri,
+				rec->rm_startblock + cluster_base);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+STATIC int
+xrep_ibt_walk_rmap(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*rec,
+	void				*priv)
+{
+	struct xrep_ibt			*ri = priv;
+	int				error = 0;
+
+	if (xchk_should_terminate(ri->sc, &error))
+		return error;
+
+	switch (rec->rm_owner) {
+	case XFS_RMAP_OWN_INOBT:
+		return xrep_ibt_record_old_btree_blocks(ri, rec);
+	case XFS_RMAP_OWN_INODES:
+		return xrep_ibt_record_inode_blocks(ri, rec);
+	}
+	return 0;
+}
+
+/*
+ * Iterate all reverse mappings to find the inodes (OWN_INODES) and the inode
+ * btrees (OWN_INOBT).  Figure out if we have enough free space to reconstruct
+ * the inode btrees.  The caller must clean up the lists if anything goes
+ * wrong.
+ */
+STATIC int
+xrep_ibt_find_inodes(
+	struct xrep_ibt		*ri)
+{
+	struct xfs_scrub	*sc = ri->sc;
+	int			error;
+
+	ri->rie.ir_startino = NULLAGINO;
+
+	/* Collect all reverse mappings for inode blocks. */
+	xrep_ag_btcur_init(sc, &sc->sa);
+	error = xfs_rmap_query_all(sc->sa.rmap_cur, xrep_ibt_walk_rmap, ri);
+	xchk_ag_btcur_free(&sc->sa);
+	if (error)
+		return error;
+
+	/* If we have a record ready to go, add it to the array. */
+	if (ri->rie.ir_startino != NULLAGINO)
+		return xrep_ibt_stash(ri);
+
+	return 0;
+}
+
+/* Update the AGI counters. */
+STATIC int
+xrep_ibt_reset_counters(
+	struct xrep_ibt		*ri)
+{
+	struct xfs_scrub	*sc = ri->sc;
+	struct xfs_agi		*agi = sc->sa.agi_bp->b_addr;
+	unsigned int		freecount = ri->icount - ri->iused;
+
+	/* Trigger inode count recalculation */
+	xfs_force_summary_recalc(sc->mp);
+
+	/*
+	 * The AGI header contains extra information related to the inode
+	 * btrees, so we must update those fields here.
+	 */
+	agi->agi_count = cpu_to_be32(ri->icount);
+	agi->agi_freecount = cpu_to_be32(freecount);
+	xfs_ialloc_log_agi(sc->tp, sc->sa.agi_bp,
+			   XFS_AGI_COUNT | XFS_AGI_FREECOUNT);
+
+	/* Reinitialize with the values we just logged. */
+	return xrep_reinit_pagi(sc);
+}
+
+/* Retrieve finobt data for bulk load. */
+STATIC int
+xrep_fibt_get_records(
+	struct xfs_btree_cur		*cur,
+	unsigned int			idx,
+	struct xfs_btree_block		*block,
+	unsigned int			nr_wanted,
+	void				*priv)
+{
+	struct xfs_inobt_rec_incore	*irec = &cur->bc_rec.i;
+	struct xrep_ibt			*ri = priv;
+	union xfs_btree_rec		*block_rec;
+	unsigned int			loaded;
+	int				error;
+
+	for (loaded = 0; loaded < nr_wanted; loaded++, idx++) {
+		do {
+			error = xfarray_load(ri->inode_records,
+					ri->array_cur++, irec);
+		} while (error == 0 && xfs_inobt_rec_freecount(irec) == 0);
+		if (error)
+			return error;
+
+		block_rec = xfs_btree_rec_addr(cur, idx, block);
+		cur->bc_ops->init_rec_from_cur(cur, block_rec);
+	}
+
+	return loaded;
+}
+
+/* Retrieve inobt data for bulk load. */
+STATIC int
+xrep_ibt_get_records(
+	struct xfs_btree_cur		*cur,
+	unsigned int			idx,
+	struct xfs_btree_block		*block,
+	unsigned int			nr_wanted,
+	void				*priv)
+{
+	struct xfs_inobt_rec_incore	*irec = &cur->bc_rec.i;
+	struct xrep_ibt			*ri = priv;
+	union xfs_btree_rec		*block_rec;
+	unsigned int			loaded;
+	int				error;
+
+	for (loaded = 0; loaded < nr_wanted; loaded++, idx++) {
+		error = xfarray_load(ri->inode_records, ri->array_cur++, irec);
+		if (error)
+			return error;
+
+		block_rec = xfs_btree_rec_addr(cur, idx, block);
+		cur->bc_ops->init_rec_from_cur(cur, block_rec);
+	}
+
+	return loaded;
+}
+
+/* Feed one of the new inobt blocks to the bulk loader. */
+STATIC int
+xrep_ibt_claim_block(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr,
+	void			*priv)
+{
+	struct xrep_ibt		*ri = priv;
+
+	return xrep_newbt_claim_block(cur, &ri->new_inobt, ptr);
+}
+
+/* Feed one of the new finobt blocks to the bulk loader. */
+STATIC int
+xrep_fibt_claim_block(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr,
+	void			*priv)
+{
+	struct xrep_ibt		*ri = priv;
+
+	return xrep_newbt_claim_block(cur, &ri->new_finobt, ptr);
+}
+
+/* Make sure the records do not overlap in inumber address space. */
+STATIC int
+xrep_ibt_check_overlap(
+	struct xrep_ibt			*ri)
+{
+	struct xfs_inobt_rec_incore	irec;
+	xfarray_idx_t			cur;
+	xfs_agino_t			next_agino = 0;
+	int				error = 0;
+
+	foreach_xfarray_idx(ri->inode_records, cur) {
+		if (xchk_should_terminate(ri->sc, &error))
+			return error;
+
+		error = xfarray_load(ri->inode_records, cur, &irec);
+		if (error)
+			return error;
+
+		if (irec.ir_startino < next_agino)
+			return -EFSCORRUPTED;
+
+		next_agino = irec.ir_startino + XFS_INODES_PER_CHUNK;
+	}
+
+	return error;
+}
+
+/* Build new inode btrees and dispose of the old one. */
+STATIC int
+xrep_ibt_build_new_trees(
+	struct xrep_ibt		*ri)
+{
+	struct xfs_scrub	*sc = ri->sc;
+	struct xfs_btree_cur	*ino_cur;
+	struct xfs_btree_cur	*fino_cur = NULL;
+	xfs_fsblock_t		fsbno;
+	bool			need_finobt;
+	int			error;
+
+	need_finobt = xfs_has_finobt(sc->mp);
+
+	/*
+	 * Create new btrees for staging all the inobt records we collected
+	 * earlier.  The records were collected in order of increasing agino,
+	 * so we do not have to sort them.  Ensure there are no overlapping
+	 * records.
+	 */
+	error = xrep_ibt_check_overlap(ri);
+	if (error)
+		return error;
+
+	/*
+	 * The new inode btrees will not be rooted in the AGI until we've
+	 * successfully rebuilt the tree.
+	 *
+	 * Start by setting up the inobt staging cursor.
+	 */
+	fsbno = XFS_AGB_TO_FSB(sc->mp, sc->sa.pag->pag_agno,
+			XFS_IBT_BLOCK(sc->mp)),
+	xrep_newbt_init_ag(&ri->new_inobt, sc, &XFS_RMAP_OINFO_INOBT, fsbno,
+			XFS_AG_RESV_NONE);
+	ri->new_inobt.bload.claim_block = xrep_ibt_claim_block;
+	ri->new_inobt.bload.get_records = xrep_ibt_get_records;
+
+	ino_cur = xfs_inobt_stage_cursor(sc->sa.pag, &ri->new_inobt.afake,
+			XFS_BTNUM_INO);
+	error = xfs_btree_bload_compute_geometry(ino_cur, &ri->new_inobt.bload,
+			xfarray_length(ri->inode_records));
+	if (error)
+		goto err_inocur;
+
+	/* Set up finobt staging cursor. */
+	if (need_finobt) {
+		enum xfs_ag_resv_type	resv = XFS_AG_RESV_METADATA;
+
+		if (sc->mp->m_finobt_nores)
+			resv = XFS_AG_RESV_NONE;
+
+		fsbno = XFS_AGB_TO_FSB(sc->mp, sc->sa.pag->pag_agno,
+				XFS_FIBT_BLOCK(sc->mp)),
+		xrep_newbt_init_ag(&ri->new_finobt, sc, &XFS_RMAP_OINFO_INOBT,
+				fsbno, resv);
+		ri->new_finobt.bload.claim_block = xrep_fibt_claim_block;
+		ri->new_finobt.bload.get_records = xrep_fibt_get_records;
+
+		fino_cur = xfs_inobt_stage_cursor(sc->sa.pag,
+				&ri->new_finobt.afake, XFS_BTNUM_FINO);
+		error = xfs_btree_bload_compute_geometry(fino_cur,
+				&ri->new_finobt.bload, ri->finobt_recs);
+		if (error)
+			goto err_finocur;
+	}
+
+	/* Last chance to abort before we start committing fixes. */
+	if (xchk_should_terminate(sc, &error))
+		goto err_finocur;
+
+	/* Reserve all the space we need to build the new btrees. */
+	error = xrep_newbt_alloc_blocks(&ri->new_inobt,
+			ri->new_inobt.bload.nr_blocks);
+	if (error)
+		goto err_finocur;
+
+	if (need_finobt) {
+		error = xrep_newbt_alloc_blocks(&ri->new_finobt,
+				ri->new_finobt.bload.nr_blocks);
+		if (error)
+			goto err_finocur;
+	}
+
+	/* Add all inobt records. */
+	ri->array_cur = XFARRAY_CURSOR_INIT;
+	error = xfs_btree_bload(ino_cur, &ri->new_inobt.bload, ri);
+	if (error)
+		goto err_finocur;
+
+	/* Add all finobt records. */
+	if (need_finobt) {
+		ri->array_cur = XFARRAY_CURSOR_INIT;
+		error = xfs_btree_bload(fino_cur, &ri->new_finobt.bload, ri);
+		if (error)
+			goto err_finocur;
+	}
+
+	/*
+	 * Install the new btrees in the AG header.  After this point the old
+	 * btrees are no longer accessible and the new trees are live.
+	 */
+	xfs_inobt_commit_staged_btree(ino_cur, sc->tp, sc->sa.agi_bp);
+	xfs_btree_del_cursor(ino_cur, 0);
+
+	if (fino_cur) {
+		xfs_inobt_commit_staged_btree(fino_cur, sc->tp, sc->sa.agi_bp);
+		xfs_btree_del_cursor(fino_cur, 0);
+	}
+
+	/* Reset the AGI counters now that we've changed the inode roots. */
+	error = xrep_ibt_reset_counters(ri);
+	if (error)
+		goto err_finobt;
+
+	/* Free unused blocks and bitmap. */
+	if (need_finobt) {
+		error = xrep_newbt_commit(&ri->new_finobt);
+		if (error)
+			goto err_inobt;
+	}
+	error = xrep_newbt_commit(&ri->new_inobt);
+	if (error)
+		return error;
+
+	return xrep_roll_ag_trans(sc);
+
+err_finocur:
+	if (need_finobt)
+		xfs_btree_del_cursor(fino_cur, error);
+err_inocur:
+	xfs_btree_del_cursor(ino_cur, error);
+err_finobt:
+	if (need_finobt)
+		xrep_newbt_cancel(&ri->new_finobt);
+err_inobt:
+	xrep_newbt_cancel(&ri->new_inobt);
+	return error;
+}
+
+/*
+ * Now that we've logged the roots of the new btrees, invalidate all of the
+ * old blocks and free them.
+ */
+STATIC int
+xrep_ibt_remove_old_trees(
+	struct xrep_ibt		*ri)
+{
+	struct xfs_scrub	*sc = ri->sc;
+	int			error;
+
+	/*
+	 * Free the old inode btree blocks if they're not in use.  It's ok to
+	 * reap with XFS_AG_RESV_NONE even if the finobt had a per-AG
+	 * reservation because we reset the reservation before releasing the
+	 * AGI and AGF header buffer locks.
+	 */
+	error = xrep_reap_agblocks(sc, &ri->old_iallocbt_blocks,
+			&XFS_RMAP_OINFO_INOBT, XFS_AG_RESV_NONE);
+	if (error)
+		return error;
+
+	/*
+	 * If the finobt is enabled and has a per-AG reservation, make sure we
+	 * reinitialize the per-AG reservations.
+	 */
+	if (xfs_has_finobt(sc->mp) && !sc->mp->m_finobt_nores)
+		sc->flags |= XREP_RESET_PERAG_RESV;
+
+	return 0;
+}
+
+/* Repair both inode btrees. */
+int
+xrep_iallocbt(
+	struct xfs_scrub	*sc)
+{
+	struct xrep_ibt		*ri;
+	struct xfs_mount	*mp = sc->mp;
+	char			*descr;
+	xfs_agino_t		first_agino, last_agino;
+	int			error = 0;
+
+	/* We require the rmapbt to rebuild anything. */
+	if (!xfs_has_rmapbt(mp))
+		return -EOPNOTSUPP;
+
+	ri = kzalloc(sizeof(struct xrep_ibt), XCHK_GFP_FLAGS);
+	if (!ri)
+		return -ENOMEM;
+	ri->sc = sc;
+
+	/* We rebuild both inode btrees. */
+	sc->sick_mask = XFS_SICK_AG_INOBT | XFS_SICK_AG_FINOBT;
+
+	/* Set up enough storage to handle an AG with nothing but inodes. */
+	xfs_agino_range(mp, sc->sa.pag->pag_agno, &first_agino, &last_agino);
+	last_agino /= XFS_INODES_PER_CHUNK;
+	descr = xchk_xfile_ag_descr(sc, "inode index records");
+	error = xfarray_create(descr, last_agino,
+			sizeof(struct xfs_inobt_rec_incore),
+			&ri->inode_records);
+	kfree(descr);
+	if (error)
+		goto out_ri;
+
+	/* Collect the inode data and find the old btree blocks. */
+	xagb_bitmap_init(&ri->old_iallocbt_blocks);
+	error = xrep_ibt_find_inodes(ri);
+	if (error)
+		goto out_bitmap;
+
+	/* Rebuild the inode indexes. */
+	error = xrep_ibt_build_new_trees(ri);
+	if (error)
+		goto out_bitmap;
+
+	/* Kill the old tree. */
+	error = xrep_ibt_remove_old_trees(ri);
+	if (error)
+		goto out_bitmap;
+
+out_bitmap:
+	xagb_bitmap_destroy(&ri->old_iallocbt_blocks);
+	xfarray_destroy(ri->inode_records);
+out_ri:
+	kfree(ri);
+	return error;
+}
+
+/* Make sure both btrees are ok after we've rebuilt them. */
+int
+xrep_revalidate_iallocbt(
+	struct xfs_scrub	*sc)
+{
+	__u32			old_type = sc->sm->sm_type;
+	int			error;
+
+	/*
+	 * We must update sm_type temporarily so that the tree-to-tree cross
+	 * reference checks will work in the correct direction, and also so
+	 * that tracing will report correctly if there are more errors.
+	 */
+	sc->sm->sm_type = XFS_SCRUB_TYPE_INOBT;
+	error = xchk_iallocbt(sc);
+	if (error)
+		goto out;
+
+	if (xfs_has_finobt(sc->mp)) {
+		sc->sm->sm_type = XFS_SCRUB_TYPE_FINOBT;
+		error = xchk_iallocbt(sc);
+	}
+
+out:
+	sc->sm->sm_type = old_type;
+	return error;
+}
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index 889f556bc98f..6e2fe2d6250b 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -25,6 +25,7 @@
 #include "scrub/common.h"
 #include "scrub/btree.h"
 #include "scrub/trace.h"
+#include "scrub/repair.h"
 
 /* Prepare the attached inode for scrubbing. */
 static inline int
@@ -39,6 +40,10 @@ xchk_prepare_iscrub(
 	if (error)
 		return error;
 
+	error = xchk_ino_dqattach(sc);
+	if (error)
+		return error;
+
 	xchk_ilock(sc, XFS_ILOCK_EXCL);
 	return 0;
 }
@@ -95,8 +100,8 @@ xchk_setup_inode(
 	if (!xfs_verify_ino(sc->mp, sc->sm->sm_ino))
 		return -ENOENT;
 
-	/* Try a regular untrusted iget. */
-	error = xchk_iget(sc, sc->sm->sm_ino, &ip);
+	/* Try a safe untrusted iget. */
+	error = xchk_iget_safe(sc, sc->sm->sm_ino, &ip);
 	if (!error)
 		return xchk_install_handle_iscrub(sc, ip);
 	if (error == -ENOENT)
@@ -181,8 +186,11 @@ xchk_setup_inode(
 	 * saying the inode is allocated and the icache being unable to load
 	 * the inode until we can flag the corruption in xchk_inode.  The
 	 * scrub function has to note the corruption, since we're not really
-	 * supposed to do that from the setup function.
+	 * supposed to do that from the setup function.  Save the mapping to
+	 * make repairs to the ondisk inode buffer.
 	 */
+	if (xchk_could_repair(sc))
+		xrep_setup_inode(sc, &imap);
 	return 0;
 
 out_cancel:
@@ -338,6 +346,10 @@ xchk_inode_flags2(
 	if (xfs_dinode_has_bigtime(dip) && !xfs_has_bigtime(mp))
 		goto bad;
 
+	/* no large extent counts without the filesystem feature */
+	if ((flags2 & XFS_DIFLAG2_NREXT64) && !xfs_has_large_extent_counts(mp))
+		goto bad;
+
 	return;
 bad:
 	xchk_ino_set_corrupt(sc, ino);
@@ -548,7 +560,7 @@ xchk_dinode(
 	}
 
 	/* di_forkoff */
-	if (XFS_DFORK_APTR(dip) >= (char *)dip + mp->m_sb.sb_inodesize)
+	if (XFS_DFORK_BOFF(dip) >= mp->m_sb.sb_inodesize)
 		xchk_ino_set_corrupt(sc, ino);
 	if (naextents != 0 && dip->di_forkoff == 0)
 		xchk_ino_set_corrupt(sc, ino);
diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c
new file mode 100644
index 000000000000..0ca62d59f84a
--- /dev/null
+++ b/fs/xfs/scrub/inode_repair.c
@@ -0,0 +1,1525 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_inode_buf.h"
+#include "xfs_inode_fork.h"
+#include "xfs_ialloc.h"
+#include "xfs_da_format.h"
+#include "xfs_reflink.h"
+#include "xfs_alloc.h"
+#include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_bmap_util.h"
+#include "xfs_dir2.h"
+#include "xfs_dir2_priv.h"
+#include "xfs_quota_defs.h"
+#include "xfs_quota.h"
+#include "xfs_ag.h"
+#include "xfs_rtbitmap.h"
+#include "xfs_attr_leaf.h"
+#include "xfs_log_priv.h"
+#include "xfs_health.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/btree.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+
+/*
+ * Inode Record Repair
+ * ===================
+ *
+ * Roughly speaking, inode problems can be classified based on whether or not
+ * they trip the dinode verifiers.  If those trip, then we won't be able to
+ * xfs_iget ourselves the inode.
+ *
+ * Therefore, the xrep_dinode_* functions fix anything that will cause the
+ * inode buffer verifier or the dinode verifier.  The xrep_inode_* functions
+ * fix things on live incore inodes.  The inode repair functions make decisions
+ * with security and usability implications when reviving a file:
+ *
+ * - Files with zero di_mode or a garbage di_mode are converted to regular file
+ *   that only root can read.  This file may not actually contain user data,
+ *   if the file was not previously a regular file.  Setuid and setgid bits
+ *   are cleared.
+ *
+ * - Zero-size directories can be truncated to look empty.  It is necessary to
+ *   run the bmapbtd and directory repair functions to fully rebuild the
+ *   directory.
+ *
+ * - Zero-size symbolic link targets can be truncated to '?'.  It is necessary
+ *   to run the bmapbtd and symlink repair functions to salvage the symlink.
+ *
+ * - Invalid extent size hints will be removed.
+ *
+ * - Quotacheck will be scheduled if we repaired an inode that was so badly
+ *   damaged that the ondisk inode had to be rebuilt.
+ *
+ * - Invalid user, group, or project IDs (aka -1U) will be reset to zero.
+ *   Setuid and setgid bits are cleared.
+ *
+ * - Data and attr forks are reset to extents format with zero extents if the
+ *   fork data is inconsistent.  It is necessary to run the bmapbtd or bmapbta
+ *   repair functions to recover the space mapping.
+ *
+ * - ACLs will not be recovered if the attr fork is zapped or the extended
+ *   attribute structure itself requires salvaging.
+ *
+ * - If the attr fork is zapped, the user and group ids are reset to root and
+ *   the setuid and setgid bits are removed.
+ */
+
+/*
+ * All the information we need to repair the ondisk inode if we can't iget the
+ * incore inode.  We don't allocate this buffer unless we're going to perform
+ * a repair to the ondisk inode cluster buffer.
+ */
+struct xrep_inode {
+	/* Inode mapping that we saved from the initial lookup attempt. */
+	struct xfs_imap		imap;
+
+	struct xfs_scrub	*sc;
+
+	/* Blocks in use on the data device by data extents or bmbt blocks. */
+	xfs_rfsblock_t		data_blocks;
+
+	/* Blocks in use on the rt device. */
+	xfs_rfsblock_t		rt_blocks;
+
+	/* Blocks in use by the attr fork. */
+	xfs_rfsblock_t		attr_blocks;
+
+	/* Number of data device extents for the data fork. */
+	xfs_extnum_t		data_extents;
+
+	/*
+	 * Number of realtime device extents for the data fork.  If
+	 * data_extents and rt_extents indicate that the data fork has extents
+	 * on both devices, we'll just back away slowly.
+	 */
+	xfs_extnum_t		rt_extents;
+
+	/* Number of (data device) extents for the attr fork. */
+	xfs_aextnum_t		attr_extents;
+
+	/* Sick state to set after zapping parts of the inode. */
+	unsigned int		ino_sick_mask;
+
+	/* Must we remove all access from this file? */
+	bool			zap_acls;
+};
+
+/*
+ * Setup function for inode repair.  @imap contains the ondisk inode mapping
+ * information so that we can correct the ondisk inode cluster buffer if
+ * necessary to make iget work.
+ */
+int
+xrep_setup_inode(
+	struct xfs_scrub	*sc,
+	const struct xfs_imap	*imap)
+{
+	struct xrep_inode	*ri;
+
+	sc->buf = kzalloc(sizeof(struct xrep_inode), XCHK_GFP_FLAGS);
+	if (!sc->buf)
+		return -ENOMEM;
+
+	ri = sc->buf;
+	memcpy(&ri->imap, imap, sizeof(struct xfs_imap));
+	ri->sc = sc;
+	return 0;
+}
+
+/*
+ * Make sure this ondisk inode can pass the inode buffer verifier.  This is
+ * not the same as the dinode verifier.
+ */
+STATIC void
+xrep_dinode_buf_core(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*bp,
+	unsigned int		ioffset)
+{
+	struct xfs_dinode	*dip = xfs_buf_offset(bp, ioffset);
+	struct xfs_trans	*tp = sc->tp;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agino_t		agino;
+	bool			crc_ok = false;
+	bool			magic_ok = false;
+	bool			unlinked_ok = false;
+
+	agino = be32_to_cpu(dip->di_next_unlinked);
+
+	if (xfs_verify_agino_or_null(bp->b_pag, agino))
+		unlinked_ok = true;
+
+	if (dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
+	    xfs_dinode_good_version(mp, dip->di_version))
+		magic_ok = true;
+
+	if (xfs_verify_cksum((char *)dip, mp->m_sb.sb_inodesize,
+			XFS_DINODE_CRC_OFF))
+		crc_ok = true;
+
+	if (magic_ok && unlinked_ok && crc_ok)
+		return;
+
+	if (!magic_ok) {
+		dip->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
+		dip->di_version = 3;
+	}
+	if (!unlinked_ok)
+		dip->di_next_unlinked = cpu_to_be32(NULLAGINO);
+	xfs_dinode_calc_crc(mp, dip);
+	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF);
+	xfs_trans_log_buf(tp, bp, ioffset,
+				  ioffset + sizeof(struct xfs_dinode) - 1);
+}
+
+/* Make sure this inode cluster buffer can pass the inode buffer verifier. */
+STATIC void
+xrep_dinode_buf(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*bp)
+{
+	struct xfs_mount	*mp = sc->mp;
+	int			i;
+	int			ni;
+
+	ni = XFS_BB_TO_FSB(mp, bp->b_length) * mp->m_sb.sb_inopblock;
+	for (i = 0; i < ni; i++)
+		xrep_dinode_buf_core(sc, bp, i << mp->m_sb.sb_inodelog);
+}
+
+/* Reinitialize things that never change in an inode. */
+STATIC void
+xrep_dinode_header(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip)
+{
+	trace_xrep_dinode_header(sc, dip);
+
+	dip->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
+	if (!xfs_dinode_good_version(sc->mp, dip->di_version))
+		dip->di_version = 3;
+	dip->di_ino = cpu_to_be64(sc->sm->sm_ino);
+	uuid_copy(&dip->di_uuid, &sc->mp->m_sb.sb_meta_uuid);
+	dip->di_gen = cpu_to_be32(sc->sm->sm_gen);
+}
+
+/* Turn di_mode into /something/ recognizable. */
+STATIC void
+xrep_dinode_mode(
+	struct xrep_inode	*ri,
+	struct xfs_dinode	*dip)
+{
+	struct xfs_scrub	*sc = ri->sc;
+	uint16_t		mode = be16_to_cpu(dip->di_mode);
+
+	trace_xrep_dinode_mode(sc, dip);
+
+	if (mode == 0 || xfs_mode_to_ftype(mode) != XFS_DIR3_FT_UNKNOWN)
+		return;
+
+	/* bad mode, so we set it to a file that only root can read */
+	mode = S_IFREG;
+	dip->di_mode = cpu_to_be16(mode);
+	dip->di_uid = 0;
+	dip->di_gid = 0;
+	ri->zap_acls = true;
+}
+
+/* Fix any conflicting flags that the verifiers complain about. */
+STATIC void
+xrep_dinode_flags(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip,
+	bool			isrt)
+{
+	struct xfs_mount	*mp = sc->mp;
+	uint64_t		flags2 = be64_to_cpu(dip->di_flags2);
+	uint16_t		flags = be16_to_cpu(dip->di_flags);
+	uint16_t		mode = be16_to_cpu(dip->di_mode);
+
+	trace_xrep_dinode_flags(sc, dip);
+
+	if (isrt)
+		flags |= XFS_DIFLAG_REALTIME;
+	else
+		flags &= ~XFS_DIFLAG_REALTIME;
+
+	/*
+	 * For regular files on a reflink filesystem, set the REFLINK flag to
+	 * protect shared extents.  A later stage will actually check those
+	 * extents and clear the flag if possible.
+	 */
+	if (xfs_has_reflink(mp) && S_ISREG(mode))
+		flags2 |= XFS_DIFLAG2_REFLINK;
+	else
+		flags2 &= ~(XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE);
+	if (flags & XFS_DIFLAG_REALTIME)
+		flags2 &= ~XFS_DIFLAG2_REFLINK;
+	if (!xfs_has_bigtime(mp))
+		flags2 &= ~XFS_DIFLAG2_BIGTIME;
+	if (!xfs_has_large_extent_counts(mp))
+		flags2 &= ~XFS_DIFLAG2_NREXT64;
+	if (flags2 & XFS_DIFLAG2_NREXT64)
+		dip->di_nrext64_pad = 0;
+	else if (dip->di_version >= 3)
+		dip->di_v3_pad = 0;
+	dip->di_flags = cpu_to_be16(flags);
+	dip->di_flags2 = cpu_to_be64(flags2);
+}
+
+/*
+ * Blow out symlink; now it points nowhere.  We don't have to worry about
+ * incore state because this inode is failing the verifiers.
+ */
+STATIC void
+xrep_dinode_zap_symlink(
+	struct xrep_inode	*ri,
+	struct xfs_dinode	*dip)
+{
+	struct xfs_scrub	*sc = ri->sc;
+	char			*p;
+
+	trace_xrep_dinode_zap_symlink(sc, dip);
+
+	dip->di_format = XFS_DINODE_FMT_LOCAL;
+	dip->di_size = cpu_to_be64(1);
+	p = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
+	*p = '?';
+	ri->ino_sick_mask |= XFS_SICK_INO_SYMLINK_ZAPPED;
+}
+
+/*
+ * Blow out dir, make the parent point to the root.  In the future repair will
+ * reconstruct this directory for us.  Note that there's no in-core directory
+ * inode because the sf verifier tripped, so we don't have to worry about the
+ * dentry cache.
+ */
+STATIC void
+xrep_dinode_zap_dir(
+	struct xrep_inode	*ri,
+	struct xfs_dinode	*dip)
+{
+	struct xfs_scrub	*sc = ri->sc;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_dir2_sf_hdr	*sfp;
+	int			i8count;
+
+	trace_xrep_dinode_zap_dir(sc, dip);
+
+	dip->di_format = XFS_DINODE_FMT_LOCAL;
+	i8count = mp->m_sb.sb_rootino > XFS_DIR2_MAX_SHORT_INUM;
+	sfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
+	sfp->count = 0;
+	sfp->i8count = i8count;
+	xfs_dir2_sf_put_parent_ino(sfp, mp->m_sb.sb_rootino);
+	dip->di_size = cpu_to_be64(xfs_dir2_sf_hdr_size(i8count));
+	ri->ino_sick_mask |= XFS_SICK_INO_DIR_ZAPPED;
+}
+
+/* Make sure we don't have a garbage file size. */
+STATIC void
+xrep_dinode_size(
+	struct xrep_inode	*ri,
+	struct xfs_dinode	*dip)
+{
+	struct xfs_scrub	*sc = ri->sc;
+	uint64_t		size = be64_to_cpu(dip->di_size);
+	uint16_t		mode = be16_to_cpu(dip->di_mode);
+
+	trace_xrep_dinode_size(sc, dip);
+
+	switch (mode & S_IFMT) {
+	case S_IFIFO:
+	case S_IFCHR:
+	case S_IFBLK:
+	case S_IFSOCK:
+		/* di_size can't be nonzero for special files */
+		dip->di_size = 0;
+		break;
+	case S_IFREG:
+		/* Regular files can't be larger than 2^63-1 bytes. */
+		dip->di_size = cpu_to_be64(size & ~(1ULL << 63));
+		break;
+	case S_IFLNK:
+		/*
+		 * Truncate ridiculously oversized symlinks.  If the size is
+		 * zero, reset it to point to the current directory.  Both of
+		 * these conditions trigger dinode verifier errors, so there
+		 * is no in-core state to reset.
+		 */
+		if (size > XFS_SYMLINK_MAXLEN)
+			dip->di_size = cpu_to_be64(XFS_SYMLINK_MAXLEN);
+		else if (size == 0)
+			xrep_dinode_zap_symlink(ri, dip);
+		break;
+	case S_IFDIR:
+		/*
+		 * Directories can't have a size larger than 32G.  If the size
+		 * is zero, reset it to an empty directory.  Both of these
+		 * conditions trigger dinode verifier errors, so there is no
+		 * in-core state to reset.
+		 */
+		if (size > XFS_DIR2_SPACE_SIZE)
+			dip->di_size = cpu_to_be64(XFS_DIR2_SPACE_SIZE);
+		else if (size == 0)
+			xrep_dinode_zap_dir(ri, dip);
+		break;
+	}
+}
+
+/* Fix extent size hints. */
+STATIC void
+xrep_dinode_extsize_hints(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip)
+{
+	struct xfs_mount	*mp = sc->mp;
+	uint64_t		flags2 = be64_to_cpu(dip->di_flags2);
+	uint16_t		flags = be16_to_cpu(dip->di_flags);
+	uint16_t		mode = be16_to_cpu(dip->di_mode);
+
+	xfs_failaddr_t		fa;
+
+	trace_xrep_dinode_extsize_hints(sc, dip);
+
+	fa = xfs_inode_validate_extsize(mp, be32_to_cpu(dip->di_extsize),
+			mode, flags);
+	if (fa) {
+		dip->di_extsize = 0;
+		dip->di_flags &= ~cpu_to_be16(XFS_DIFLAG_EXTSIZE |
+					      XFS_DIFLAG_EXTSZINHERIT);
+	}
+
+	if (dip->di_version < 3)
+		return;
+
+	fa = xfs_inode_validate_cowextsize(mp, be32_to_cpu(dip->di_cowextsize),
+			mode, flags, flags2);
+	if (fa) {
+		dip->di_cowextsize = 0;
+		dip->di_flags2 &= ~cpu_to_be64(XFS_DIFLAG2_COWEXTSIZE);
+	}
+}
+
+/* Count extents and blocks for an inode given an rmap. */
+STATIC int
+xrep_dinode_walk_rmap(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*rec,
+	void				*priv)
+{
+	struct xrep_inode		*ri = priv;
+	int				error = 0;
+
+	if (xchk_should_terminate(ri->sc, &error))
+		return error;
+
+	/* We only care about this inode. */
+	if (rec->rm_owner != ri->sc->sm->sm_ino)
+		return 0;
+
+	if (rec->rm_flags & XFS_RMAP_ATTR_FORK) {
+		ri->attr_blocks += rec->rm_blockcount;
+		if (!(rec->rm_flags & XFS_RMAP_BMBT_BLOCK))
+			ri->attr_extents++;
+
+		return 0;
+	}
+
+	ri->data_blocks += rec->rm_blockcount;
+	if (!(rec->rm_flags & XFS_RMAP_BMBT_BLOCK))
+		ri->data_extents++;
+
+	return 0;
+}
+
+/* Count extents and blocks for an inode from all AG rmap data. */
+STATIC int
+xrep_dinode_count_ag_rmaps(
+	struct xrep_inode	*ri,
+	struct xfs_perag	*pag)
+{
+	struct xfs_btree_cur	*cur;
+	struct xfs_buf		*agf;
+	int			error;
+
+	error = xfs_alloc_read_agf(pag, ri->sc->tp, 0, &agf);
+	if (error)
+		return error;
+
+	cur = xfs_rmapbt_init_cursor(ri->sc->mp, ri->sc->tp, agf, pag);
+	error = xfs_rmap_query_all(cur, xrep_dinode_walk_rmap, ri);
+	xfs_btree_del_cursor(cur, error);
+	xfs_trans_brelse(ri->sc->tp, agf);
+	return error;
+}
+
+/* Count extents and blocks for a given inode from all rmap data. */
+STATIC int
+xrep_dinode_count_rmaps(
+	struct xrep_inode	*ri)
+{
+	struct xfs_perag	*pag;
+	xfs_agnumber_t		agno;
+	int			error;
+
+	if (!xfs_has_rmapbt(ri->sc->mp) || xfs_has_realtime(ri->sc->mp))
+		return -EOPNOTSUPP;
+
+	for_each_perag(ri->sc->mp, agno, pag) {
+		error = xrep_dinode_count_ag_rmaps(ri, pag);
+		if (error) {
+			xfs_perag_rele(pag);
+			return error;
+		}
+	}
+
+	/* Can't have extents on both the rt and the data device. */
+	if (ri->data_extents && ri->rt_extents)
+		return -EFSCORRUPTED;
+
+	trace_xrep_dinode_count_rmaps(ri->sc,
+			ri->data_blocks, ri->rt_blocks, ri->attr_blocks,
+			ri->data_extents, ri->rt_extents, ri->attr_extents);
+	return 0;
+}
+
+/* Return true if this extents-format ifork looks like garbage. */
+STATIC bool
+xrep_dinode_bad_extents_fork(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip,
+	unsigned int		dfork_size,
+	int			whichfork)
+{
+	struct xfs_bmbt_irec	new;
+	struct xfs_bmbt_rec	*dp;
+	xfs_extnum_t		nex;
+	bool			isrt;
+	unsigned int		i;
+
+	nex = xfs_dfork_nextents(dip, whichfork);
+	if (nex > dfork_size / sizeof(struct xfs_bmbt_rec))
+		return true;
+
+	dp = XFS_DFORK_PTR(dip, whichfork);
+
+	isrt = dip->di_flags & cpu_to_be16(XFS_DIFLAG_REALTIME);
+	for (i = 0; i < nex; i++, dp++) {
+		xfs_failaddr_t	fa;
+
+		xfs_bmbt_disk_get_all(dp, &new);
+		fa = xfs_bmap_validate_extent_raw(sc->mp, isrt, whichfork,
+				&new);
+		if (fa)
+			return true;
+	}
+
+	return false;
+}
+
+/* Return true if this btree-format ifork looks like garbage. */
+STATIC bool
+xrep_dinode_bad_bmbt_fork(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip,
+	unsigned int		dfork_size,
+	int			whichfork)
+{
+	struct xfs_bmdr_block	*dfp;
+	xfs_extnum_t		nex;
+	unsigned int		i;
+	unsigned int		dmxr;
+	unsigned int		nrecs;
+	unsigned int		level;
+
+	nex = xfs_dfork_nextents(dip, whichfork);
+	if (nex <= dfork_size / sizeof(struct xfs_bmbt_rec))
+		return true;
+
+	if (dfork_size < sizeof(struct xfs_bmdr_block))
+		return true;
+
+	dfp = XFS_DFORK_PTR(dip, whichfork);
+	nrecs = be16_to_cpu(dfp->bb_numrecs);
+	level = be16_to_cpu(dfp->bb_level);
+
+	if (nrecs == 0 || XFS_BMDR_SPACE_CALC(nrecs) > dfork_size)
+		return true;
+	if (level == 0 || level >= XFS_BM_MAXLEVELS(sc->mp, whichfork))
+		return true;
+
+	dmxr = xfs_bmdr_maxrecs(dfork_size, 0);
+	for (i = 1; i <= nrecs; i++) {
+		struct xfs_bmbt_key	*fkp;
+		xfs_bmbt_ptr_t		*fpp;
+		xfs_fileoff_t		fileoff;
+		xfs_fsblock_t		fsbno;
+
+		fkp = XFS_BMDR_KEY_ADDR(dfp, i);
+		fileoff = be64_to_cpu(fkp->br_startoff);
+		if (!xfs_verify_fileoff(sc->mp, fileoff))
+			return true;
+
+		fpp = XFS_BMDR_PTR_ADDR(dfp, i, dmxr);
+		fsbno = be64_to_cpu(*fpp);
+		if (!xfs_verify_fsbno(sc->mp, fsbno))
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * Check the data fork for things that will fail the ifork verifiers or the
+ * ifork formatters.
+ */
+STATIC bool
+xrep_dinode_check_dfork(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip,
+	uint16_t		mode)
+{
+	void			*dfork_ptr;
+	int64_t			data_size;
+	unsigned int		fmt;
+	unsigned int		dfork_size;
+
+	/*
+	 * Verifier functions take signed int64_t, so check for bogus negative
+	 * values first.
+	 */
+	data_size = be64_to_cpu(dip->di_size);
+	if (data_size < 0)
+		return true;
+
+	fmt = XFS_DFORK_FORMAT(dip, XFS_DATA_FORK);
+	switch (mode & S_IFMT) {
+	case S_IFIFO:
+	case S_IFCHR:
+	case S_IFBLK:
+	case S_IFSOCK:
+		if (fmt != XFS_DINODE_FMT_DEV)
+			return true;
+		break;
+	case S_IFREG:
+		if (fmt == XFS_DINODE_FMT_LOCAL)
+			return true;
+		fallthrough;
+	case S_IFLNK:
+	case S_IFDIR:
+		switch (fmt) {
+		case XFS_DINODE_FMT_LOCAL:
+		case XFS_DINODE_FMT_EXTENTS:
+		case XFS_DINODE_FMT_BTREE:
+			break;
+		default:
+			return true;
+		}
+		break;
+	default:
+		return true;
+	}
+
+	dfork_size = XFS_DFORK_SIZE(dip, sc->mp, XFS_DATA_FORK);
+	dfork_ptr = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
+
+	switch (fmt) {
+	case XFS_DINODE_FMT_DEV:
+		break;
+	case XFS_DINODE_FMT_LOCAL:
+		/* dir/symlink structure cannot be larger than the fork */
+		if (data_size > dfork_size)
+			return true;
+		/* directory structure must pass verification. */
+		if (S_ISDIR(mode) &&
+		    xfs_dir2_sf_verify(sc->mp, dfork_ptr, data_size) != NULL)
+			return true;
+		/* symlink structure must pass verification. */
+		if (S_ISLNK(mode) &&
+		    xfs_symlink_shortform_verify(dfork_ptr, data_size) != NULL)
+			return true;
+		break;
+	case XFS_DINODE_FMT_EXTENTS:
+		if (xrep_dinode_bad_extents_fork(sc, dip, dfork_size,
+				XFS_DATA_FORK))
+			return true;
+		break;
+	case XFS_DINODE_FMT_BTREE:
+		if (xrep_dinode_bad_bmbt_fork(sc, dip, dfork_size,
+				XFS_DATA_FORK))
+			return true;
+		break;
+	default:
+		return true;
+	}
+
+	return false;
+}
+
+static void
+xrep_dinode_set_data_nextents(
+	struct xfs_dinode	*dip,
+	xfs_extnum_t		nextents)
+{
+	if (xfs_dinode_has_large_extent_counts(dip))
+		dip->di_big_nextents = cpu_to_be64(nextents);
+	else
+		dip->di_nextents = cpu_to_be32(nextents);
+}
+
+static void
+xrep_dinode_set_attr_nextents(
+	struct xfs_dinode	*dip,
+	xfs_extnum_t		nextents)
+{
+	if (xfs_dinode_has_large_extent_counts(dip))
+		dip->di_big_anextents = cpu_to_be32(nextents);
+	else
+		dip->di_anextents = cpu_to_be16(nextents);
+}
+
+/* Reset the data fork to something sane. */
+STATIC void
+xrep_dinode_zap_dfork(
+	struct xrep_inode	*ri,
+	struct xfs_dinode	*dip,
+	uint16_t		mode)
+{
+	struct xfs_scrub	*sc = ri->sc;
+
+	trace_xrep_dinode_zap_dfork(sc, dip);
+
+	ri->ino_sick_mask |= XFS_SICK_INO_BMBTD_ZAPPED;
+
+	xrep_dinode_set_data_nextents(dip, 0);
+	ri->data_blocks = 0;
+	ri->rt_blocks = 0;
+
+	/* Special files always get reset to DEV */
+	switch (mode & S_IFMT) {
+	case S_IFIFO:
+	case S_IFCHR:
+	case S_IFBLK:
+	case S_IFSOCK:
+		dip->di_format = XFS_DINODE_FMT_DEV;
+		dip->di_size = 0;
+		return;
+	}
+
+	/*
+	 * If we have data extents, reset to an empty map and hope the user
+	 * will run the bmapbtd checker next.
+	 */
+	if (ri->data_extents || ri->rt_extents || S_ISREG(mode)) {
+		dip->di_format = XFS_DINODE_FMT_EXTENTS;
+		return;
+	}
+
+	/* Otherwise, reset the local format to the minimum. */
+	switch (mode & S_IFMT) {
+	case S_IFLNK:
+		xrep_dinode_zap_symlink(ri, dip);
+		break;
+	case S_IFDIR:
+		xrep_dinode_zap_dir(ri, dip);
+		break;
+	}
+}
+
+/*
+ * Check the attr fork for things that will fail the ifork verifiers or the
+ * ifork formatters.
+ */
+STATIC bool
+xrep_dinode_check_afork(
+	struct xfs_scrub		*sc,
+	struct xfs_dinode		*dip)
+{
+	struct xfs_attr_sf_hdr		*afork_ptr;
+	size_t				attr_size;
+	unsigned int			afork_size;
+
+	if (XFS_DFORK_BOFF(dip) == 0)
+		return dip->di_aformat != XFS_DINODE_FMT_EXTENTS ||
+		       xfs_dfork_attr_extents(dip) != 0;
+
+	afork_size = XFS_DFORK_SIZE(dip, sc->mp, XFS_ATTR_FORK);
+	afork_ptr = XFS_DFORK_PTR(dip, XFS_ATTR_FORK);
+
+	switch (XFS_DFORK_FORMAT(dip, XFS_ATTR_FORK)) {
+	case XFS_DINODE_FMT_LOCAL:
+		/* Fork has to be large enough to extract the xattr size. */
+		if (afork_size < sizeof(struct xfs_attr_sf_hdr))
+			return true;
+
+		/* xattr structure cannot be larger than the fork */
+		attr_size = be16_to_cpu(afork_ptr->totsize);
+		if (attr_size > afork_size)
+			return true;
+
+		/* xattr structure must pass verification. */
+		return xfs_attr_shortform_verify(afork_ptr, attr_size) != NULL;
+	case XFS_DINODE_FMT_EXTENTS:
+		if (xrep_dinode_bad_extents_fork(sc, dip, afork_size,
+					XFS_ATTR_FORK))
+			return true;
+		break;
+	case XFS_DINODE_FMT_BTREE:
+		if (xrep_dinode_bad_bmbt_fork(sc, dip, afork_size,
+					XFS_ATTR_FORK))
+			return true;
+		break;
+	default:
+		return true;
+	}
+
+	return false;
+}
+
+/*
+ * Reset the attr fork to empty.  Since the attr fork could have contained
+ * ACLs, make the file readable only by root.
+ */
+STATIC void
+xrep_dinode_zap_afork(
+	struct xrep_inode	*ri,
+	struct xfs_dinode	*dip,
+	uint16_t		mode)
+{
+	struct xfs_scrub	*sc = ri->sc;
+
+	trace_xrep_dinode_zap_afork(sc, dip);
+
+	ri->ino_sick_mask |= XFS_SICK_INO_BMBTA_ZAPPED;
+
+	dip->di_aformat = XFS_DINODE_FMT_EXTENTS;
+	xrep_dinode_set_attr_nextents(dip, 0);
+	ri->attr_blocks = 0;
+
+	/*
+	 * If the data fork is in btree format, removing the attr fork entirely
+	 * might cause verifier failures if the next level down in the bmbt
+	 * could now fit in the data fork area.
+	 */
+	if (dip->di_format != XFS_DINODE_FMT_BTREE)
+		dip->di_forkoff = 0;
+	dip->di_mode = cpu_to_be16(mode & ~0777);
+	dip->di_uid = 0;
+	dip->di_gid = 0;
+}
+
+/* Make sure the fork offset is a sensible value. */
+STATIC void
+xrep_dinode_ensure_forkoff(
+	struct xrep_inode	*ri,
+	struct xfs_dinode	*dip,
+	uint16_t		mode)
+{
+	struct xfs_bmdr_block	*bmdr;
+	struct xfs_scrub	*sc = ri->sc;
+	xfs_extnum_t		attr_extents, data_extents;
+	size_t			bmdr_minsz = XFS_BMDR_SPACE_CALC(1);
+	unsigned int		lit_sz = XFS_LITINO(sc->mp);
+	unsigned int		afork_min, dfork_min;
+
+	trace_xrep_dinode_ensure_forkoff(sc, dip);
+
+	/*
+	 * Before calling this function, xrep_dinode_core ensured that both
+	 * forks actually fit inside their respective literal areas.  If this
+	 * was not the case, the fork was reset to FMT_EXTENTS with zero
+	 * records.  If the rmapbt scan found attr or data fork blocks, this
+	 * will be noted in the dinode_stats, and we must leave enough room
+	 * for the bmap repair code to reconstruct the mapping structure.
+	 *
+	 * First, compute the minimum space required for the attr fork.
+	 */
+	switch (dip->di_aformat) {
+	case XFS_DINODE_FMT_LOCAL:
+		/*
+		 * If we still have a shortform xattr structure at all, that
+		 * means the attr fork area was exactly large enough to fit
+		 * the sf structure.
+		 */
+		afork_min = XFS_DFORK_SIZE(dip, sc->mp, XFS_ATTR_FORK);
+		break;
+	case XFS_DINODE_FMT_EXTENTS:
+		attr_extents = xfs_dfork_attr_extents(dip);
+		if (attr_extents) {
+			/*
+			 * We must maintain sufficient space to hold the entire
+			 * extent map array in the data fork.  Note that we
+			 * previously zapped the fork if it had no chance of
+			 * fitting in the inode.
+			 */
+			afork_min = sizeof(struct xfs_bmbt_rec) * attr_extents;
+		} else if (ri->attr_extents > 0) {
+			/*
+			 * The attr fork thinks it has zero extents, but we
+			 * found some xattr extents.  We need to leave enough
+			 * empty space here so that the incore attr fork will
+			 * get created (and hence trigger the attr fork bmap
+			 * repairer).
+			 */
+			afork_min = bmdr_minsz;
+		} else {
+			/* No extents on disk or found in rmapbt. */
+			afork_min = 0;
+		}
+		break;
+	case XFS_DINODE_FMT_BTREE:
+		/* Must have space for btree header and key/pointers. */
+		bmdr = XFS_DFORK_PTR(dip, XFS_ATTR_FORK);
+		afork_min = XFS_BMAP_BROOT_SPACE(sc->mp, bmdr);
+		break;
+	default:
+		/* We should never see any other formats. */
+		afork_min = 0;
+		break;
+	}
+
+	/* Compute the minimum space required for the data fork. */
+	switch (dip->di_format) {
+	case XFS_DINODE_FMT_DEV:
+		dfork_min = sizeof(__be32);
+		break;
+	case XFS_DINODE_FMT_UUID:
+		dfork_min = sizeof(uuid_t);
+		break;
+	case XFS_DINODE_FMT_LOCAL:
+		/*
+		 * If we still have a shortform data fork at all, that means
+		 * the data fork area was large enough to fit whatever was in
+		 * there.
+		 */
+		dfork_min = be64_to_cpu(dip->di_size);
+		break;
+	case XFS_DINODE_FMT_EXTENTS:
+		data_extents = xfs_dfork_data_extents(dip);
+		if (data_extents) {
+			/*
+			 * We must maintain sufficient space to hold the entire
+			 * extent map array in the data fork.  Note that we
+			 * previously zapped the fork if it had no chance of
+			 * fitting in the inode.
+			 */
+			dfork_min = sizeof(struct xfs_bmbt_rec) * data_extents;
+		} else if (ri->data_extents > 0 || ri->rt_extents > 0) {
+			/*
+			 * The data fork thinks it has zero extents, but we
+			 * found some data extents.  We need to leave enough
+			 * empty space here so that the data fork bmap repair
+			 * will recover the mappings.
+			 */
+			dfork_min = bmdr_minsz;
+		} else {
+			/* No extents on disk or found in rmapbt. */
+			dfork_min = 0;
+		}
+		break;
+	case XFS_DINODE_FMT_BTREE:
+		/* Must have space for btree header and key/pointers. */
+		bmdr = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
+		dfork_min = XFS_BMAP_BROOT_SPACE(sc->mp, bmdr);
+		break;
+	default:
+		dfork_min = 0;
+		break;
+	}
+
+	/*
+	 * Round all values up to the nearest 8 bytes, because that is the
+	 * precision of di_forkoff.
+	 */
+	afork_min = roundup(afork_min, 8);
+	dfork_min = roundup(dfork_min, 8);
+	bmdr_minsz = roundup(bmdr_minsz, 8);
+
+	ASSERT(dfork_min <= lit_sz);
+	ASSERT(afork_min <= lit_sz);
+
+	/*
+	 * If the data fork was zapped and we don't have enough space for the
+	 * recovery fork, move the attr fork up.
+	 */
+	if (dip->di_format == XFS_DINODE_FMT_EXTENTS &&
+	    xfs_dfork_data_extents(dip) == 0 &&
+	    (ri->data_extents > 0 || ri->rt_extents > 0) &&
+	    bmdr_minsz > XFS_DFORK_DSIZE(dip, sc->mp)) {
+		if (bmdr_minsz + afork_min > lit_sz) {
+			/*
+			 * The attr for and the stub fork we need to recover
+			 * the data fork won't both fit.  Zap the attr fork.
+			 */
+			xrep_dinode_zap_afork(ri, dip, mode);
+			afork_min = bmdr_minsz;
+		} else {
+			void	*before, *after;
+
+			/* Otherwise, just slide the attr fork up. */
+			before = XFS_DFORK_APTR(dip);
+			dip->di_forkoff = bmdr_minsz >> 3;
+			after = XFS_DFORK_APTR(dip);
+			memmove(after, before, XFS_DFORK_ASIZE(dip, sc->mp));
+		}
+	}
+
+	/*
+	 * If the attr fork was zapped and we don't have enough space for the
+	 * recovery fork, move the attr fork down.
+	 */
+	if (dip->di_aformat == XFS_DINODE_FMT_EXTENTS &&
+	    xfs_dfork_attr_extents(dip) == 0 &&
+	    ri->attr_extents > 0 &&
+	    bmdr_minsz > XFS_DFORK_ASIZE(dip, sc->mp)) {
+		if (dip->di_format == XFS_DINODE_FMT_BTREE) {
+			/*
+			 * If the data fork is in btree format then we can't
+			 * adjust forkoff because that runs the risk of
+			 * violating the extents/btree format transition rules.
+			 */
+		} else if (bmdr_minsz + dfork_min > lit_sz) {
+			/*
+			 * If we can't move the attr fork, too bad, we lose the
+			 * attr fork and leak its blocks.
+			 */
+			xrep_dinode_zap_afork(ri, dip, mode);
+		} else {
+			/*
+			 * Otherwise, just slide the attr fork down.  The attr
+			 * fork is empty, so we don't have any old contents to
+			 * move here.
+			 */
+			dip->di_forkoff = (lit_sz - bmdr_minsz) >> 3;
+		}
+	}
+}
+
+/*
+ * Zap the data/attr forks if we spot anything that isn't going to pass the
+ * ifork verifiers or the ifork formatters, because we need to get the inode
+ * into good enough shape that the higher level repair functions can run.
+ */
+STATIC void
+xrep_dinode_zap_forks(
+	struct xrep_inode	*ri,
+	struct xfs_dinode	*dip)
+{
+	struct xfs_scrub	*sc = ri->sc;
+	xfs_extnum_t		data_extents;
+	xfs_extnum_t		attr_extents;
+	xfs_filblks_t		nblocks;
+	uint16_t		mode;
+	bool			zap_datafork = false;
+	bool			zap_attrfork = ri->zap_acls;
+
+	trace_xrep_dinode_zap_forks(sc, dip);
+
+	mode = be16_to_cpu(dip->di_mode);
+
+	data_extents = xfs_dfork_data_extents(dip);
+	attr_extents = xfs_dfork_attr_extents(dip);
+	nblocks = be64_to_cpu(dip->di_nblocks);
+
+	/* Inode counters don't make sense? */
+	if (data_extents > nblocks)
+		zap_datafork = true;
+	if (attr_extents > nblocks)
+		zap_attrfork = true;
+	if (data_extents + attr_extents > nblocks)
+		zap_datafork = zap_attrfork = true;
+
+	if (!zap_datafork)
+		zap_datafork = xrep_dinode_check_dfork(sc, dip, mode);
+	if (!zap_attrfork)
+		zap_attrfork = xrep_dinode_check_afork(sc, dip);
+
+	/* Zap whatever's bad. */
+	if (zap_attrfork)
+		xrep_dinode_zap_afork(ri, dip, mode);
+	if (zap_datafork)
+		xrep_dinode_zap_dfork(ri, dip, mode);
+	xrep_dinode_ensure_forkoff(ri, dip, mode);
+
+	/*
+	 * Zero di_nblocks if we don't have any extents at all to satisfy the
+	 * buffer verifier.
+	 */
+	data_extents = xfs_dfork_data_extents(dip);
+	attr_extents = xfs_dfork_attr_extents(dip);
+	if (data_extents + attr_extents == 0)
+		dip->di_nblocks = 0;
+}
+
+/* Inode didn't pass dinode verifiers, so fix the raw buffer and retry iget. */
+STATIC int
+xrep_dinode_core(
+	struct xrep_inode	*ri)
+{
+	struct xfs_scrub	*sc = ri->sc;
+	struct xfs_buf		*bp;
+	struct xfs_dinode	*dip;
+	xfs_ino_t		ino = sc->sm->sm_ino;
+	int			error;
+	int			iget_error;
+
+	/* Figure out what this inode had mapped in both forks. */
+	error = xrep_dinode_count_rmaps(ri);
+	if (error)
+		return error;
+
+	/* Read the inode cluster buffer. */
+	error = xfs_trans_read_buf(sc->mp, sc->tp, sc->mp->m_ddev_targp,
+			ri->imap.im_blkno, ri->imap.im_len, XBF_UNMAPPED, &bp,
+			NULL);
+	if (error)
+		return error;
+
+	/* Make sure we can pass the inode buffer verifier. */
+	xrep_dinode_buf(sc, bp);
+	bp->b_ops = &xfs_inode_buf_ops;
+
+	/* Fix everything the verifier will complain about. */
+	dip = xfs_buf_offset(bp, ri->imap.im_boffset);
+	xrep_dinode_header(sc, dip);
+	xrep_dinode_mode(ri, dip);
+	xrep_dinode_flags(sc, dip, ri->rt_extents > 0);
+	xrep_dinode_size(ri, dip);
+	xrep_dinode_extsize_hints(sc, dip);
+	xrep_dinode_zap_forks(ri, dip);
+
+	/* Write out the inode. */
+	trace_xrep_dinode_fixed(sc, dip);
+	xfs_dinode_calc_crc(sc->mp, dip);
+	xfs_trans_buf_set_type(sc->tp, bp, XFS_BLFT_DINO_BUF);
+	xfs_trans_log_buf(sc->tp, bp, ri->imap.im_boffset,
+			ri->imap.im_boffset + sc->mp->m_sb.sb_inodesize - 1);
+
+	/*
+	 * In theory, we've fixed the ondisk inode record enough that we should
+	 * be able to load the inode into the cache.  Try to iget that inode
+	 * now while we hold the AGI and the inode cluster buffer and take the
+	 * IOLOCK so that we can continue with repairs without anyone else
+	 * accessing the inode.  If iget fails, we still need to commit the
+	 * changes.
+	 */
+	iget_error = xchk_iget(sc, ino, &sc->ip);
+	if (!iget_error)
+		xchk_ilock(sc, XFS_IOLOCK_EXCL);
+
+	/*
+	 * Commit the inode cluster buffer updates and drop the AGI buffer that
+	 * we've been holding since scrub setup.  From here on out, repairs
+	 * deal only with the cached inode.
+	 */
+	error = xrep_trans_commit(sc);
+	if (error)
+		return error;
+
+	if (iget_error)
+		return iget_error;
+
+	error = xchk_trans_alloc(sc, 0);
+	if (error)
+		return error;
+
+	error = xrep_ino_dqattach(sc);
+	if (error)
+		return error;
+
+	xchk_ilock(sc, XFS_ILOCK_EXCL);
+	if (ri->ino_sick_mask)
+		xfs_inode_mark_sick(sc->ip, ri->ino_sick_mask);
+	return 0;
+}
+
+/* Fix everything xfs_dinode_verify cares about. */
+STATIC int
+xrep_dinode_problems(
+	struct xrep_inode	*ri)
+{
+	struct xfs_scrub	*sc = ri->sc;
+	int			error;
+
+	error = xrep_dinode_core(ri);
+	if (error)
+		return error;
+
+	/* We had to fix a totally busted inode, schedule quotacheck. */
+	if (XFS_IS_UQUOTA_ON(sc->mp))
+		xrep_force_quotacheck(sc, XFS_DQTYPE_USER);
+	if (XFS_IS_GQUOTA_ON(sc->mp))
+		xrep_force_quotacheck(sc, XFS_DQTYPE_GROUP);
+	if (XFS_IS_PQUOTA_ON(sc->mp))
+		xrep_force_quotacheck(sc, XFS_DQTYPE_PROJ);
+
+	return 0;
+}
+
+/*
+ * Fix problems that the verifiers don't care about.  In general these are
+ * errors that don't cause problems elsewhere in the kernel that we can easily
+ * detect, so we don't check them all that rigorously.
+ */
+
+/* Make sure block and extent counts are ok. */
+STATIC int
+xrep_inode_blockcounts(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_ifork	*ifp;
+	xfs_filblks_t		count;
+	xfs_filblks_t		acount;
+	xfs_extnum_t		nextents;
+	int			error;
+
+	trace_xrep_inode_blockcounts(sc);
+
+	/* Set data fork counters from the data fork mappings. */
+	error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_DATA_FORK,
+			&nextents, &count);
+	if (error)
+		return error;
+	if (xfs_is_reflink_inode(sc->ip)) {
+		/*
+		 * data fork blockcount can exceed physical storage if a user
+		 * reflinks the same block over and over again.
+		 */
+		;
+	} else if (XFS_IS_REALTIME_INODE(sc->ip)) {
+		if (count >= sc->mp->m_sb.sb_rblocks)
+			return -EFSCORRUPTED;
+	} else {
+		if (count >= sc->mp->m_sb.sb_dblocks)
+			return -EFSCORRUPTED;
+	}
+	error = xrep_ino_ensure_extent_count(sc, XFS_DATA_FORK, nextents);
+	if (error)
+		return error;
+	sc->ip->i_df.if_nextents = nextents;
+
+	/* Set attr fork counters from the attr fork mappings. */
+	ifp = xfs_ifork_ptr(sc->ip, XFS_ATTR_FORK);
+	if (ifp) {
+		error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_ATTR_FORK,
+				&nextents, &acount);
+		if (error)
+			return error;
+		if (count >= sc->mp->m_sb.sb_dblocks)
+			return -EFSCORRUPTED;
+		error = xrep_ino_ensure_extent_count(sc, XFS_ATTR_FORK,
+				nextents);
+		if (error)
+			return error;
+		ifp->if_nextents = nextents;
+	} else {
+		acount = 0;
+	}
+
+	sc->ip->i_nblocks = count + acount;
+	return 0;
+}
+
+/* Check for invalid uid/gid/prid. */
+STATIC void
+xrep_inode_ids(
+	struct xfs_scrub	*sc)
+{
+	bool			dirty = false;
+
+	trace_xrep_inode_ids(sc);
+
+	if (!uid_valid(VFS_I(sc->ip)->i_uid)) {
+		i_uid_write(VFS_I(sc->ip), 0);
+		dirty = true;
+		if (XFS_IS_UQUOTA_ON(sc->mp))
+			xrep_force_quotacheck(sc, XFS_DQTYPE_USER);
+	}
+
+	if (!gid_valid(VFS_I(sc->ip)->i_gid)) {
+		i_gid_write(VFS_I(sc->ip), 0);
+		dirty = true;
+		if (XFS_IS_GQUOTA_ON(sc->mp))
+			xrep_force_quotacheck(sc, XFS_DQTYPE_GROUP);
+	}
+
+	if (sc->ip->i_projid == -1U) {
+		sc->ip->i_projid = 0;
+		dirty = true;
+		if (XFS_IS_PQUOTA_ON(sc->mp))
+			xrep_force_quotacheck(sc, XFS_DQTYPE_PROJ);
+	}
+
+	/* strip setuid/setgid if we touched any of the ids */
+	if (dirty)
+		VFS_I(sc->ip)->i_mode &= ~(S_ISUID | S_ISGID);
+}
+
+static inline void
+xrep_clamp_timestamp(
+	struct xfs_inode	*ip,
+	struct timespec64	*ts)
+{
+	ts->tv_nsec = clamp_t(long, ts->tv_nsec, 0, NSEC_PER_SEC);
+	*ts = timestamp_truncate(*ts, VFS_I(ip));
+}
+
+/* Nanosecond counters can't have more than 1 billion. */
+STATIC void
+xrep_inode_timestamps(
+	struct xfs_inode	*ip)
+{
+	struct timespec64	tstamp;
+	struct inode		*inode = VFS_I(ip);
+
+	tstamp = inode_get_atime(inode);
+	xrep_clamp_timestamp(ip, &tstamp);
+	inode_set_atime_to_ts(inode, tstamp);
+
+	tstamp = inode_get_mtime(inode);
+	xrep_clamp_timestamp(ip, &tstamp);
+	inode_set_mtime_to_ts(inode, tstamp);
+
+	tstamp = inode_get_ctime(inode);
+	xrep_clamp_timestamp(ip, &tstamp);
+	inode_set_ctime_to_ts(inode, tstamp);
+
+	xrep_clamp_timestamp(ip, &ip->i_crtime);
+}
+
+/* Fix inode flags that don't make sense together. */
+STATIC void
+xrep_inode_flags(
+	struct xfs_scrub	*sc)
+{
+	uint16_t		mode;
+
+	trace_xrep_inode_flags(sc);
+
+	mode = VFS_I(sc->ip)->i_mode;
+
+	/* Clear junk flags */
+	if (sc->ip->i_diflags & ~XFS_DIFLAG_ANY)
+		sc->ip->i_diflags &= ~XFS_DIFLAG_ANY;
+
+	/* NEWRTBM only applies to realtime bitmaps */
+	if (sc->ip->i_ino == sc->mp->m_sb.sb_rbmino)
+		sc->ip->i_diflags |= XFS_DIFLAG_NEWRTBM;
+	else
+		sc->ip->i_diflags &= ~XFS_DIFLAG_NEWRTBM;
+
+	/* These only make sense for directories. */
+	if (!S_ISDIR(mode))
+		sc->ip->i_diflags &= ~(XFS_DIFLAG_RTINHERIT |
+					  XFS_DIFLAG_EXTSZINHERIT |
+					  XFS_DIFLAG_PROJINHERIT |
+					  XFS_DIFLAG_NOSYMLINKS);
+
+	/* These only make sense for files. */
+	if (!S_ISREG(mode))
+		sc->ip->i_diflags &= ~(XFS_DIFLAG_REALTIME |
+					  XFS_DIFLAG_EXTSIZE);
+
+	/* These only make sense for non-rt files. */
+	if (sc->ip->i_diflags & XFS_DIFLAG_REALTIME)
+		sc->ip->i_diflags &= ~XFS_DIFLAG_FILESTREAM;
+
+	/* Immutable and append only?  Drop the append. */
+	if ((sc->ip->i_diflags & XFS_DIFLAG_IMMUTABLE) &&
+	    (sc->ip->i_diflags & XFS_DIFLAG_APPEND))
+		sc->ip->i_diflags &= ~XFS_DIFLAG_APPEND;
+
+	/* Clear junk flags. */
+	if (sc->ip->i_diflags2 & ~XFS_DIFLAG2_ANY)
+		sc->ip->i_diflags2 &= ~XFS_DIFLAG2_ANY;
+
+	/* No reflink flag unless we support it and it's a file. */
+	if (!xfs_has_reflink(sc->mp) || !S_ISREG(mode))
+		sc->ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+
+	/* DAX only applies to files and dirs. */
+	if (!(S_ISREG(mode) || S_ISDIR(mode)))
+		sc->ip->i_diflags2 &= ~XFS_DIFLAG2_DAX;
+
+	/* No reflink files on the realtime device. */
+	if (sc->ip->i_diflags & XFS_DIFLAG_REALTIME)
+		sc->ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+}
+
+/*
+ * Fix size problems with block/node format directories.  If we fail to find
+ * the extent list, just bail out and let the bmapbtd repair functions clean
+ * up that mess.
+ */
+STATIC void
+xrep_inode_blockdir_size(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_iext_cursor	icur;
+	struct xfs_bmbt_irec	got;
+	struct xfs_ifork	*ifp;
+	xfs_fileoff_t		off;
+	int			error;
+
+	trace_xrep_inode_blockdir_size(sc);
+
+	error = xfs_iread_extents(sc->tp, sc->ip, XFS_DATA_FORK);
+	if (error)
+		return;
+
+	/* Find the last block before 32G; this is the dir size. */
+	ifp = xfs_ifork_ptr(sc->ip, XFS_DATA_FORK);
+	off = XFS_B_TO_FSB(sc->mp, XFS_DIR2_SPACE_SIZE);
+	if (!xfs_iext_lookup_extent_before(sc->ip, ifp, &off, &icur, &got)) {
+		/* zero-extents directory? */
+		return;
+	}
+
+	off = got.br_startoff + got.br_blockcount;
+	sc->ip->i_disk_size = min_t(loff_t, XFS_DIR2_SPACE_SIZE,
+			XFS_FSB_TO_B(sc->mp, off));
+}
+
+/* Fix size problems with short format directories. */
+STATIC void
+xrep_inode_sfdir_size(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_ifork	*ifp;
+
+	trace_xrep_inode_sfdir_size(sc);
+
+	ifp = xfs_ifork_ptr(sc->ip, XFS_DATA_FORK);
+	sc->ip->i_disk_size = ifp->if_bytes;
+}
+
+/*
+ * Fix any irregularities in a directory inode's size now that we can iterate
+ * extent maps and access other regular inode data.
+ */
+STATIC void
+xrep_inode_dir_size(
+	struct xfs_scrub	*sc)
+{
+	trace_xrep_inode_dir_size(sc);
+
+	switch (sc->ip->i_df.if_format) {
+	case XFS_DINODE_FMT_EXTENTS:
+	case XFS_DINODE_FMT_BTREE:
+		xrep_inode_blockdir_size(sc);
+		break;
+	case XFS_DINODE_FMT_LOCAL:
+		xrep_inode_sfdir_size(sc);
+		break;
+	}
+}
+
+/* Fix extent size hint problems. */
+STATIC void
+xrep_inode_extsize(
+	struct xfs_scrub	*sc)
+{
+	/* Fix misaligned extent size hints on a directory. */
+	if ((sc->ip->i_diflags & XFS_DIFLAG_RTINHERIT) &&
+	    (sc->ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) &&
+	    xfs_extlen_to_rtxmod(sc->mp, sc->ip->i_extsize) > 0) {
+		sc->ip->i_extsize = 0;
+		sc->ip->i_diflags &= ~XFS_DIFLAG_EXTSZINHERIT;
+	}
+}
+
+/* Fix any irregularities in an inode that the verifiers don't catch. */
+STATIC int
+xrep_inode_problems(
+	struct xfs_scrub	*sc)
+{
+	int			error;
+
+	error = xrep_inode_blockcounts(sc);
+	if (error)
+		return error;
+	xrep_inode_timestamps(sc->ip);
+	xrep_inode_flags(sc);
+	xrep_inode_ids(sc);
+	/*
+	 * We can now do a better job fixing the size of a directory now that
+	 * we can scan the data fork extents than we could in xrep_dinode_size.
+	 */
+	if (S_ISDIR(VFS_I(sc->ip)->i_mode))
+		xrep_inode_dir_size(sc);
+	xrep_inode_extsize(sc);
+
+	trace_xrep_inode_fixed(sc);
+	xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE);
+	return xrep_roll_trans(sc);
+}
+
+/* Repair an inode's fields. */
+int
+xrep_inode(
+	struct xfs_scrub	*sc)
+{
+	int			error = 0;
+
+	/*
+	 * No inode?  That means we failed the _iget verifiers.  Repair all
+	 * the things that the inode verifiers care about, then retry _iget.
+	 */
+	if (!sc->ip) {
+		struct xrep_inode	*ri = sc->buf;
+
+		ASSERT(ri != NULL);
+
+		error = xrep_dinode_problems(ri);
+		if (error)
+			return error;
+
+		/* By this point we had better have a working incore inode. */
+		if (!sc->ip)
+			return -EFSCORRUPTED;
+	}
+
+	xfs_trans_ijoin(sc->tp, sc->ip, 0);
+
+	/* If we found corruption of any kind, try to fix it. */
+	if ((sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) ||
+	    (sc->sm->sm_flags & XFS_SCRUB_OFLAG_XCORRUPT)) {
+		error = xrep_inode_problems(sc);
+		if (error)
+			return error;
+	}
+
+	/* See if we can clear the reflink flag. */
+	if (xfs_is_reflink_inode(sc->ip)) {
+		error = xfs_reflink_clear_inode_flag(sc->ip, &sc->tp);
+		if (error)
+			return error;
+	}
+
+	return xrep_defer_finish(sc);
+}
diff --git a/fs/xfs/scrub/newbt.c b/fs/xfs/scrub/newbt.c
new file mode 100644
index 000000000000..bb6d980b4fcd
--- /dev/null
+++ b/fs/xfs/scrub/newbt.c
@@ -0,0 +1,559 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2022-2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_btree.h"
+#include "xfs_btree_staging.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_alloc.h"
+#include "xfs_rmap.h"
+#include "xfs_ag.h"
+#include "xfs_defer.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/newbt.h"
+
+/*
+ * Estimate proper slack values for a btree that's being reloaded.
+ *
+ * Under most circumstances, we'll take whatever default loading value the
+ * btree bulk loading code calculates for us.  However, there are some
+ * exceptions to this rule:
+ *
+ * (0) If someone turned one of the debug knobs.
+ * (1) If this is a per-AG btree and the AG has less than 10% space free.
+ * (2) If this is an inode btree and the FS has less than 10% space free.
+
+ * In either case, format the new btree blocks almost completely full to
+ * minimize space usage.
+ */
+static void
+xrep_newbt_estimate_slack(
+	struct xrep_newbt	*xnr)
+{
+	struct xfs_scrub	*sc = xnr->sc;
+	struct xfs_btree_bload	*bload = &xnr->bload;
+	uint64_t		free;
+	uint64_t		sz;
+
+	/*
+	 * The xfs_globals values are set to -1 (i.e. take the bload defaults)
+	 * unless someone has set them otherwise, so we just pull the values
+	 * here.
+	 */
+	bload->leaf_slack = xfs_globals.bload_leaf_slack;
+	bload->node_slack = xfs_globals.bload_node_slack;
+
+	if (sc->ops->type == ST_PERAG) {
+		free = sc->sa.pag->pagf_freeblks;
+		sz = xfs_ag_block_count(sc->mp, sc->sa.pag->pag_agno);
+	} else {
+		free = percpu_counter_sum(&sc->mp->m_fdblocks);
+		sz = sc->mp->m_sb.sb_dblocks;
+	}
+
+	/* No further changes if there's more than 10% free space left. */
+	if (free >= div_u64(sz, 10))
+		return;
+
+	/*
+	 * We're low on space; load the btrees as tightly as possible.  Leave
+	 * a couple of open slots in each btree block so that we don't end up
+	 * splitting the btrees like crazy after a mount.
+	 */
+	if (bload->leaf_slack < 0)
+		bload->leaf_slack = 2;
+	if (bload->node_slack < 0)
+		bload->node_slack = 2;
+}
+
+/* Initialize accounting resources for staging a new AG btree. */
+void
+xrep_newbt_init_ag(
+	struct xrep_newbt		*xnr,
+	struct xfs_scrub		*sc,
+	const struct xfs_owner_info	*oinfo,
+	xfs_fsblock_t			alloc_hint,
+	enum xfs_ag_resv_type		resv)
+{
+	memset(xnr, 0, sizeof(struct xrep_newbt));
+	xnr->sc = sc;
+	xnr->oinfo = *oinfo; /* structure copy */
+	xnr->alloc_hint = alloc_hint;
+	xnr->resv = resv;
+	INIT_LIST_HEAD(&xnr->resv_list);
+	xnr->bload.max_dirty = XFS_B_TO_FSBT(sc->mp, 256U << 10); /* 256K */
+	xrep_newbt_estimate_slack(xnr);
+}
+
+/* Initialize accounting resources for staging a new inode fork btree. */
+int
+xrep_newbt_init_inode(
+	struct xrep_newbt		*xnr,
+	struct xfs_scrub		*sc,
+	int				whichfork,
+	const struct xfs_owner_info	*oinfo)
+{
+	struct xfs_ifork		*ifp;
+
+	ifp = kmem_cache_zalloc(xfs_ifork_cache, XCHK_GFP_FLAGS);
+	if (!ifp)
+		return -ENOMEM;
+
+	xrep_newbt_init_ag(xnr, sc, oinfo,
+			XFS_INO_TO_FSB(sc->mp, sc->ip->i_ino),
+			XFS_AG_RESV_NONE);
+	xnr->ifake.if_fork = ifp;
+	xnr->ifake.if_fork_size = xfs_inode_fork_size(sc->ip, whichfork);
+	return 0;
+}
+
+/*
+ * Initialize accounting resources for staging a new btree.  Callers are
+ * expected to add their own reservations (and clean them up) manually.
+ */
+void
+xrep_newbt_init_bare(
+	struct xrep_newbt		*xnr,
+	struct xfs_scrub		*sc)
+{
+	xrep_newbt_init_ag(xnr, sc, &XFS_RMAP_OINFO_ANY_OWNER, NULLFSBLOCK,
+			XFS_AG_RESV_NONE);
+}
+
+/*
+ * Designate specific blocks to be used to build our new btree.  @pag must be
+ * a passive reference.
+ */
+STATIC int
+xrep_newbt_add_blocks(
+	struct xrep_newbt		*xnr,
+	struct xfs_perag		*pag,
+	const struct xfs_alloc_arg	*args)
+{
+	struct xfs_mount		*mp = xnr->sc->mp;
+	struct xrep_newbt_resv		*resv;
+	int				error;
+
+	resv = kmalloc(sizeof(struct xrep_newbt_resv), XCHK_GFP_FLAGS);
+	if (!resv)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&resv->list);
+	resv->agbno = XFS_FSB_TO_AGBNO(mp, args->fsbno);
+	resv->len = args->len;
+	resv->used = 0;
+	resv->pag = xfs_perag_hold(pag);
+
+	if (args->tp) {
+		ASSERT(xnr->oinfo.oi_offset == 0);
+
+		error = xfs_alloc_schedule_autoreap(args, true, &resv->autoreap);
+		if (error)
+			goto out_pag;
+	}
+
+	list_add_tail(&resv->list, &xnr->resv_list);
+	return 0;
+out_pag:
+	xfs_perag_put(resv->pag);
+	kfree(resv);
+	return error;
+}
+
+/*
+ * Add an extent to the new btree reservation pool.  Callers are required to
+ * reap this reservation manually if the repair is cancelled.  @pag must be a
+ * passive reference.
+ */
+int
+xrep_newbt_add_extent(
+	struct xrep_newbt	*xnr,
+	struct xfs_perag	*pag,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
+{
+	struct xfs_mount	*mp = xnr->sc->mp;
+	struct xfs_alloc_arg	args = {
+		.tp		= NULL, /* no autoreap */
+		.oinfo		= xnr->oinfo,
+		.fsbno		= XFS_AGB_TO_FSB(mp, pag->pag_agno, agbno),
+		.len		= len,
+		.resv		= xnr->resv,
+	};
+
+	return xrep_newbt_add_blocks(xnr, pag, &args);
+}
+
+/* Don't let our allocation hint take us beyond this AG */
+static inline void
+xrep_newbt_validate_ag_alloc_hint(
+	struct xrep_newbt	*xnr)
+{
+	struct xfs_scrub	*sc = xnr->sc;
+	xfs_agnumber_t		agno = XFS_FSB_TO_AGNO(sc->mp, xnr->alloc_hint);
+
+	if (agno == sc->sa.pag->pag_agno &&
+	    xfs_verify_fsbno(sc->mp, xnr->alloc_hint))
+		return;
+
+	xnr->alloc_hint = XFS_AGB_TO_FSB(sc->mp, sc->sa.pag->pag_agno,
+					 XFS_AGFL_BLOCK(sc->mp) + 1);
+}
+
+/* Allocate disk space for a new per-AG btree. */
+STATIC int
+xrep_newbt_alloc_ag_blocks(
+	struct xrep_newbt	*xnr,
+	uint64_t		nr_blocks)
+{
+	struct xfs_scrub	*sc = xnr->sc;
+	struct xfs_mount	*mp = sc->mp;
+	int			error = 0;
+
+	ASSERT(sc->sa.pag != NULL);
+
+	while (nr_blocks > 0) {
+		struct xfs_alloc_arg	args = {
+			.tp		= sc->tp,
+			.mp		= mp,
+			.oinfo		= xnr->oinfo,
+			.minlen		= 1,
+			.maxlen		= nr_blocks,
+			.prod		= 1,
+			.resv		= xnr->resv,
+		};
+		xfs_agnumber_t		agno;
+
+		xrep_newbt_validate_ag_alloc_hint(xnr);
+
+		error = xfs_alloc_vextent_near_bno(&args, xnr->alloc_hint);
+		if (error)
+			return error;
+		if (args.fsbno == NULLFSBLOCK)
+			return -ENOSPC;
+
+		agno = XFS_FSB_TO_AGNO(mp, args.fsbno);
+
+		trace_xrep_newbt_alloc_ag_blocks(mp, agno,
+				XFS_FSB_TO_AGBNO(mp, args.fsbno), args.len,
+				xnr->oinfo.oi_owner);
+
+		if (agno != sc->sa.pag->pag_agno) {
+			ASSERT(agno == sc->sa.pag->pag_agno);
+			return -EFSCORRUPTED;
+		}
+
+		error = xrep_newbt_add_blocks(xnr, sc->sa.pag, &args);
+		if (error)
+			return error;
+
+		nr_blocks -= args.len;
+		xnr->alloc_hint = args.fsbno + args.len;
+
+		error = xrep_defer_finish(sc);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+/* Don't let our allocation hint take us beyond EOFS */
+static inline void
+xrep_newbt_validate_file_alloc_hint(
+	struct xrep_newbt	*xnr)
+{
+	struct xfs_scrub	*sc = xnr->sc;
+
+	if (xfs_verify_fsbno(sc->mp, xnr->alloc_hint))
+		return;
+
+	xnr->alloc_hint = XFS_AGB_TO_FSB(sc->mp, 0, XFS_AGFL_BLOCK(sc->mp) + 1);
+}
+
+/* Allocate disk space for our new file-based btree. */
+STATIC int
+xrep_newbt_alloc_file_blocks(
+	struct xrep_newbt	*xnr,
+	uint64_t		nr_blocks)
+{
+	struct xfs_scrub	*sc = xnr->sc;
+	struct xfs_mount	*mp = sc->mp;
+	int			error = 0;
+
+	while (nr_blocks > 0) {
+		struct xfs_alloc_arg	args = {
+			.tp		= sc->tp,
+			.mp		= mp,
+			.oinfo		= xnr->oinfo,
+			.minlen		= 1,
+			.maxlen		= nr_blocks,
+			.prod		= 1,
+			.resv		= xnr->resv,
+		};
+		struct xfs_perag	*pag;
+		xfs_agnumber_t		agno;
+
+		xrep_newbt_validate_file_alloc_hint(xnr);
+
+		error = xfs_alloc_vextent_start_ag(&args, xnr->alloc_hint);
+		if (error)
+			return error;
+		if (args.fsbno == NULLFSBLOCK)
+			return -ENOSPC;
+
+		agno = XFS_FSB_TO_AGNO(mp, args.fsbno);
+
+		trace_xrep_newbt_alloc_file_blocks(mp, agno,
+				XFS_FSB_TO_AGBNO(mp, args.fsbno), args.len,
+				xnr->oinfo.oi_owner);
+
+		pag = xfs_perag_get(mp, agno);
+		if (!pag) {
+			ASSERT(0);
+			return -EFSCORRUPTED;
+		}
+
+		error = xrep_newbt_add_blocks(xnr, pag, &args);
+		xfs_perag_put(pag);
+		if (error)
+			return error;
+
+		nr_blocks -= args.len;
+		xnr->alloc_hint = args.fsbno + args.len;
+
+		error = xrep_defer_finish(sc);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+/* Allocate disk space for our new btree. */
+int
+xrep_newbt_alloc_blocks(
+	struct xrep_newbt	*xnr,
+	uint64_t		nr_blocks)
+{
+	if (xnr->sc->ip)
+		return xrep_newbt_alloc_file_blocks(xnr, nr_blocks);
+	return xrep_newbt_alloc_ag_blocks(xnr, nr_blocks);
+}
+
+/*
+ * Free the unused part of a space extent that was reserved for a new ondisk
+ * structure.  Returns the number of EFIs logged or a negative errno.
+ */
+STATIC int
+xrep_newbt_free_extent(
+	struct xrep_newbt	*xnr,
+	struct xrep_newbt_resv	*resv,
+	bool			btree_committed)
+{
+	struct xfs_scrub	*sc = xnr->sc;
+	xfs_agblock_t		free_agbno = resv->agbno;
+	xfs_extlen_t		free_aglen = resv->len;
+	xfs_fsblock_t		fsbno;
+	int			error;
+
+	if (!btree_committed || resv->used == 0) {
+		/*
+		 * If we're not committing a new btree or we didn't use the
+		 * space reservation, let the existing EFI free the entire
+		 * space extent.
+		 */
+		trace_xrep_newbt_free_blocks(sc->mp, resv->pag->pag_agno,
+				free_agbno, free_aglen, xnr->oinfo.oi_owner);
+		xfs_alloc_commit_autoreap(sc->tp, &resv->autoreap);
+		return 1;
+	}
+
+	/*
+	 * We used space and committed the btree.  Cancel the autoreap, remove
+	 * the written blocks from the reservation, and possibly log a new EFI
+	 * to free any unused reservation space.
+	 */
+	xfs_alloc_cancel_autoreap(sc->tp, &resv->autoreap);
+	free_agbno += resv->used;
+	free_aglen -= resv->used;
+
+	if (free_aglen == 0)
+		return 0;
+
+	trace_xrep_newbt_free_blocks(sc->mp, resv->pag->pag_agno, free_agbno,
+			free_aglen, xnr->oinfo.oi_owner);
+
+	ASSERT(xnr->resv != XFS_AG_RESV_AGFL);
+	ASSERT(xnr->resv != XFS_AG_RESV_IGNORE);
+
+	/*
+	 * Use EFIs to free the reservations.  This reduces the chance
+	 * that we leak blocks if the system goes down.
+	 */
+	fsbno = XFS_AGB_TO_FSB(sc->mp, resv->pag->pag_agno, free_agbno);
+	error = xfs_free_extent_later(sc->tp, fsbno, free_aglen, &xnr->oinfo,
+			xnr->resv, true);
+	if (error)
+		return error;
+
+	return 1;
+}
+
+/* Free all the accounting info and disk space we reserved for a new btree. */
+STATIC int
+xrep_newbt_free(
+	struct xrep_newbt	*xnr,
+	bool			btree_committed)
+{
+	struct xfs_scrub	*sc = xnr->sc;
+	struct xrep_newbt_resv	*resv, *n;
+	unsigned int		freed = 0;
+	int			error = 0;
+
+	/*
+	 * If the filesystem already went down, we can't free the blocks.  Skip
+	 * ahead to freeing the incore metadata because we can't fix anything.
+	 */
+	if (xfs_is_shutdown(sc->mp))
+		goto junkit;
+
+	list_for_each_entry_safe(resv, n, &xnr->resv_list, list) {
+		int		ret;
+
+		ret = xrep_newbt_free_extent(xnr, resv, btree_committed);
+		list_del(&resv->list);
+		xfs_perag_put(resv->pag);
+		kfree(resv);
+		if (ret < 0) {
+			error = ret;
+			goto junkit;
+		}
+
+		freed += ret;
+		if (freed >= XREP_MAX_ITRUNCATE_EFIS) {
+			error = xrep_defer_finish(sc);
+			if (error)
+				goto junkit;
+			freed = 0;
+		}
+	}
+
+	if (freed)
+		error = xrep_defer_finish(sc);
+
+junkit:
+	/*
+	 * If we still have reservations attached to @newbt, cleanup must have
+	 * failed and the filesystem is about to go down.  Clean up the incore
+	 * reservations and try to commit to freeing the space we used.
+	 */
+	list_for_each_entry_safe(resv, n, &xnr->resv_list, list) {
+		xfs_alloc_commit_autoreap(sc->tp, &resv->autoreap);
+		list_del(&resv->list);
+		xfs_perag_put(resv->pag);
+		kfree(resv);
+	}
+
+	if (sc->ip) {
+		kmem_cache_free(xfs_ifork_cache, xnr->ifake.if_fork);
+		xnr->ifake.if_fork = NULL;
+	}
+
+	return error;
+}
+
+/*
+ * Free all the accounting info and unused disk space allocations after
+ * committing a new btree.
+ */
+int
+xrep_newbt_commit(
+	struct xrep_newbt	*xnr)
+{
+	return xrep_newbt_free(xnr, true);
+}
+
+/*
+ * Free all the accounting info and all of the disk space we reserved for a new
+ * btree that we're not going to commit.  We want to try to roll things back
+ * cleanly for things like ENOSPC midway through allocation.
+ */
+void
+xrep_newbt_cancel(
+	struct xrep_newbt	*xnr)
+{
+	xrep_newbt_free(xnr, false);
+}
+
+/* Feed one of the reserved btree blocks to the bulk loader. */
+int
+xrep_newbt_claim_block(
+	struct xfs_btree_cur	*cur,
+	struct xrep_newbt	*xnr,
+	union xfs_btree_ptr	*ptr)
+{
+	struct xrep_newbt_resv	*resv;
+	struct xfs_mount	*mp = cur->bc_mp;
+	xfs_agblock_t		agbno;
+
+	/*
+	 * The first item in the list should always have a free block unless
+	 * we're completely out.
+	 */
+	resv = list_first_entry(&xnr->resv_list, struct xrep_newbt_resv, list);
+	if (resv->used == resv->len)
+		return -ENOSPC;
+
+	/*
+	 * Peel off a block from the start of the reservation.  We allocate
+	 * blocks in order to place blocks on disk in increasing record or key
+	 * order.  The block reservations tend to end up on the list in
+	 * decreasing order, which hopefully results in leaf blocks ending up
+	 * together.
+	 */
+	agbno = resv->agbno + resv->used;
+	resv->used++;
+
+	/* If we used all the blocks in this reservation, move it to the end. */
+	if (resv->used == resv->len)
+		list_move_tail(&resv->list, &xnr->resv_list);
+
+	trace_xrep_newbt_claim_block(mp, resv->pag->pag_agno, agbno, 1,
+			xnr->oinfo.oi_owner);
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+		ptr->l = cpu_to_be64(XFS_AGB_TO_FSB(mp, resv->pag->pag_agno,
+								agbno));
+	else
+		ptr->s = cpu_to_be32(agbno);
+
+	/* Relog all the EFIs. */
+	return xrep_defer_finish(xnr->sc);
+}
+
+/* How many reserved blocks are unused? */
+unsigned int
+xrep_newbt_unused_blocks(
+	struct xrep_newbt	*xnr)
+{
+	struct xrep_newbt_resv	*resv;
+	unsigned int		unused = 0;
+
+	list_for_each_entry(resv, &xnr->resv_list, list)
+		unused += resv->len - resv->used;
+	return unused;
+}
diff --git a/fs/xfs/scrub/newbt.h b/fs/xfs/scrub/newbt.h
new file mode 100644
index 000000000000..89f8e3970b1f
--- /dev/null
+++ b/fs/xfs/scrub/newbt.h
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2022-2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_NEWBT_H__
+#define __XFS_SCRUB_NEWBT_H__
+
+struct xrep_newbt_resv {
+	/* Link to list of extents that we've reserved. */
+	struct list_head	list;
+
+	struct xfs_perag	*pag;
+
+	/* Auto-freeing this reservation if we don't commit. */
+	struct xfs_alloc_autoreap autoreap;
+
+	/* AG block of the extent we reserved. */
+	xfs_agblock_t		agbno;
+
+	/* Length of the reservation. */
+	xfs_extlen_t		len;
+
+	/* How much of this reservation has been used. */
+	xfs_extlen_t		used;
+};
+
+struct xrep_newbt {
+	struct xfs_scrub	*sc;
+
+	/* List of extents that we've reserved. */
+	struct list_head	resv_list;
+
+	/* Fake root for new btree. */
+	union {
+		struct xbtree_afakeroot	afake;
+		struct xbtree_ifakeroot	ifake;
+	};
+
+	/* rmap owner of these blocks */
+	struct xfs_owner_info	oinfo;
+
+	/* btree geometry for the bulk loader */
+	struct xfs_btree_bload	bload;
+
+	/* Allocation hint */
+	xfs_fsblock_t		alloc_hint;
+
+	/* per-ag reservation type */
+	enum xfs_ag_resv_type	resv;
+};
+
+void xrep_newbt_init_bare(struct xrep_newbt *xnr, struct xfs_scrub *sc);
+void xrep_newbt_init_ag(struct xrep_newbt *xnr, struct xfs_scrub *sc,
+		const struct xfs_owner_info *oinfo, xfs_fsblock_t alloc_hint,
+		enum xfs_ag_resv_type resv);
+int xrep_newbt_init_inode(struct xrep_newbt *xnr, struct xfs_scrub *sc,
+		int whichfork, const struct xfs_owner_info *oinfo);
+int xrep_newbt_alloc_blocks(struct xrep_newbt *xnr, uint64_t nr_blocks);
+int xrep_newbt_add_extent(struct xrep_newbt *xnr, struct xfs_perag *pag,
+		xfs_agblock_t agbno, xfs_extlen_t len);
+void xrep_newbt_cancel(struct xrep_newbt *xnr);
+int xrep_newbt_commit(struct xrep_newbt *xnr);
+int xrep_newbt_claim_block(struct xfs_btree_cur *cur, struct xrep_newbt *xnr,
+		union xfs_btree_ptr *ptr);
+unsigned int xrep_newbt_unused_blocks(struct xrep_newbt *xnr);
+
+#endif /* __XFS_SCRUB_NEWBT_H__ */
diff --git a/fs/xfs/scrub/off_bitmap.h b/fs/xfs/scrub/off_bitmap.h
new file mode 100644
index 000000000000..0d3f9e6c1aad
--- /dev/null
+++ b/fs/xfs/scrub/off_bitmap.h
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2022-2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_OFF_BITMAP_H__
+#define __XFS_SCRUB_OFF_BITMAP_H__
+
+/* Bitmaps, but for type-checked for xfs_fileoff_t */
+
+struct xoff_bitmap {
+	struct xbitmap64	offbitmap;
+};
+
+static inline void xoff_bitmap_init(struct xoff_bitmap *bitmap)
+{
+	xbitmap64_init(&bitmap->offbitmap);
+}
+
+static inline void xoff_bitmap_destroy(struct xoff_bitmap *bitmap)
+{
+	xbitmap64_destroy(&bitmap->offbitmap);
+}
+
+static inline int xoff_bitmap_set(struct xoff_bitmap *bitmap,
+		xfs_fileoff_t off, xfs_filblks_t len)
+{
+	return xbitmap64_set(&bitmap->offbitmap, off, len);
+}
+
+static inline int xoff_bitmap_walk(struct xoff_bitmap *bitmap,
+		xbitmap64_walk_fn fn, void *priv)
+{
+	return xbitmap64_walk(&bitmap->offbitmap, fn, priv);
+}
+
+#endif	/* __XFS_SCRUB_OFF_BITMAP_H__ */
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index e6155d86f791..7db873672146 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -156,6 +156,16 @@ xchk_parent_validate(
 		goto out_rele;
 	}
 
+	/*
+	 * We cannot yet validate this parent pointer if the directory looks as
+	 * though it has been zapped by the inode record repair code.
+	 */
+	if (xchk_dir_looks_zapped(dp)) {
+		error = -EBUSY;
+		xchk_set_incomplete(sc);
+		goto out_unlock;
+	}
+
 	/* Look for a directory entry in the parent pointing to the child. */
 	error = xchk_dir_walk(sc, dp, xchk_parent_actor, &spc);
 	if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
@@ -217,6 +227,13 @@ xchk_parent(
 		 */
 		error = xchk_parent_validate(sc, parent_ino);
 	} while (error == -EAGAIN);
+	if (error == -EBUSY) {
+		/*
+		 * We could not scan a directory, so we marked the check
+		 * incomplete.  No further error return is necessary.
+		 */
+		return 0;
+	}
 
 	return error;
 }
diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c
index 5671c8153433..183d531875ea 100644
--- a/fs/xfs/scrub/quota.c
+++ b/fs/xfs/scrub/quota.c
@@ -6,6 +6,7 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_shared.h"
+#include "xfs_bit.h"
 #include "xfs_format.h"
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"
@@ -17,9 +18,10 @@
 #include "xfs_bmap.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
+#include "scrub/quota.h"
 
 /* Convert a scrub type code to a DQ flag, or return 0 if error. */
-static inline xfs_dqtype_t
+xfs_dqtype_t
 xchk_quota_to_dqtype(
 	struct xfs_scrub	*sc)
 {
@@ -75,14 +77,70 @@ struct xchk_quota_info {
 	xfs_dqid_t		last_id;
 };
 
+/* There's a written block backing this dquot, right? */
+STATIC int
+xchk_quota_item_bmap(
+	struct xfs_scrub	*sc,
+	struct xfs_dquot	*dq,
+	xfs_fileoff_t		offset)
+{
+	struct xfs_bmbt_irec	irec;
+	struct xfs_mount	*mp = sc->mp;
+	int			nmaps = 1;
+	int			error;
+
+	if (!xfs_verify_fileoff(mp, offset)) {
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		return 0;
+	}
+
+	if (dq->q_fileoffset != offset) {
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		return 0;
+	}
+
+	error = xfs_bmapi_read(sc->ip, offset, 1, &irec, &nmaps, 0);
+	if (error)
+		return error;
+
+	if (nmaps != 1) {
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		return 0;
+	}
+
+	if (!xfs_verify_fsbno(mp, irec.br_startblock))
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+	if (XFS_FSB_TO_DADDR(mp, irec.br_startblock) != dq->q_blkno)
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+	if (!xfs_bmap_is_written_extent(&irec))
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+
+	return 0;
+}
+
+/* Complain if a quota timer is incorrectly set. */
+static inline void
+xchk_quota_item_timer(
+	struct xfs_scrub		*sc,
+	xfs_fileoff_t			offset,
+	const struct xfs_dquot_res	*res)
+{
+	if ((res->softlimit && res->count > res->softlimit) ||
+	    (res->hardlimit && res->count > res->hardlimit)) {
+		if (!res->timer)
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+	} else {
+		if (res->timer)
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+	}
+}
+
 /* Scrub the fields in an individual quota item. */
 STATIC int
 xchk_quota_item(
-	struct xfs_dquot	*dq,
-	xfs_dqtype_t		dqtype,
-	void			*priv)
+	struct xchk_quota_info	*sqi,
+	struct xfs_dquot	*dq)
 {
-	struct xchk_quota_info	*sqi = priv;
 	struct xfs_scrub	*sc = sqi->sc;
 	struct xfs_mount	*mp = sc->mp;
 	struct xfs_quotainfo	*qi = mp->m_quotainfo;
@@ -94,6 +152,17 @@ xchk_quota_item(
 		return error;
 
 	/*
+	 * We want to validate the bmap record for the storage backing this
+	 * dquot, so we need to lock the dquot and the quota file.  For quota
+	 * operations, the locking order is first the ILOCK and then the dquot.
+	 * However, dqiterate gave us a locked dquot, so drop the dquot lock to
+	 * get the ILOCK.
+	 */
+	xfs_dqunlock(dq);
+	xchk_ilock(sc, XFS_ILOCK_SHARED);
+	xfs_dqlock(dq);
+
+	/*
 	 * Except for the root dquot, the actual dquot we got must either have
 	 * the same or higher id as we saw before.
 	 */
@@ -103,6 +172,11 @@ xchk_quota_item(
 
 	sqi->last_id = dq->q_id;
 
+	error = xchk_quota_item_bmap(sc, dq, offset);
+	xchk_iunlock(sc, XFS_ILOCK_SHARED);
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, offset, &error))
+		return error;
+
 	/*
 	 * Warn if the hard limits are larger than the fs.
 	 * Administrators can do this, though in production this seems
@@ -166,6 +240,10 @@ xchk_quota_item(
 	    dq->q_rtb.count > dq->q_rtb.hardlimit)
 		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
 
+	xchk_quota_item_timer(sc, offset, &dq->q_blk);
+	xchk_quota_item_timer(sc, offset, &dq->q_ino);
+	xchk_quota_item_timer(sc, offset, &dq->q_rtb);
+
 out:
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return -ECANCELED;
@@ -191,7 +269,7 @@ xchk_quota_data_fork(
 		return error;
 
 	/* Check for data fork problems that apply only to quota files. */
-	max_dqid_off = ((xfs_dqid_t)-1) / qi->qi_dqperchunk;
+	max_dqid_off = XFS_DQ_ID_MAX / qi->qi_dqperchunk;
 	ifp = xfs_ifork_ptr(sc->ip, XFS_DATA_FORK);
 	for_each_xfs_iext(ifp, &icur, &irec) {
 		if (xchk_should_terminate(sc, &error))
@@ -218,9 +296,11 @@ int
 xchk_quota(
 	struct xfs_scrub	*sc)
 {
-	struct xchk_quota_info	sqi;
+	struct xchk_dqiter	cursor = { };
+	struct xchk_quota_info	sqi = { .sc = sc };
 	struct xfs_mount	*mp = sc->mp;
 	struct xfs_quotainfo	*qi = mp->m_quotainfo;
+	struct xfs_dquot	*dq;
 	xfs_dqtype_t		dqtype;
 	int			error = 0;
 
@@ -239,10 +319,15 @@ xchk_quota(
 	 * functions.
 	 */
 	xchk_iunlock(sc, sc->ilock_flags);
-	sqi.sc = sc;
-	sqi.last_id = 0;
-	error = xfs_qm_dqiterate(mp, dqtype, xchk_quota_item, &sqi);
-	xchk_ilock(sc, XFS_ILOCK_EXCL);
+
+	/* Now look for things that the quota verifiers won't complain about. */
+	xchk_dqiter_init(&cursor, sc, dqtype);
+	while ((error = xchk_dquot_iter(&cursor, &dq)) == 1) {
+		error = xchk_quota_item(&sqi, dq);
+		xfs_qm_dqput(dq);
+		if (error)
+			break;
+	}
 	if (error == -ECANCELED)
 		error = 0;
 	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK,
diff --git a/fs/xfs/scrub/quota.h b/fs/xfs/scrub/quota.h
new file mode 100644
index 000000000000..6c7134ce2385
--- /dev/null
+++ b/fs/xfs/scrub/quota.h
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_QUOTA_H__
+#define __XFS_SCRUB_QUOTA_H__
+
+xfs_dqtype_t xchk_quota_to_dqtype(struct xfs_scrub *sc);
+
+/* dquot iteration code */
+
+struct xchk_dqiter {
+	struct xfs_scrub	*sc;
+
+	/* Quota file that we're walking. */
+	struct xfs_inode	*quota_ip;
+
+	/* Cached data fork mapping for the dquot. */
+	struct xfs_bmbt_irec	bmap;
+
+	/* The next dquot to scan. */
+	uint64_t		id;
+
+	/* Quota type (user/group/project). */
+	xfs_dqtype_t		dqtype;
+
+	/* Data fork sequence number to detect stale mappings. */
+	unsigned int		if_seq;
+};
+
+void xchk_dqiter_init(struct xchk_dqiter *cursor, struct xfs_scrub *sc,
+		xfs_dqtype_t dqtype);
+int xchk_dquot_iter(struct xchk_dqiter *cursor, struct xfs_dquot **dqpp);
+
+#endif /* __XFS_SCRUB_QUOTA_H__ */
diff --git a/fs/xfs/scrub/quota_repair.c b/fs/xfs/scrub/quota_repair.c
new file mode 100644
index 000000000000..0bab4c30cb85
--- /dev/null
+++ b/fs/xfs/scrub/quota_repair.c
@@ -0,0 +1,575 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_bit.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_inode_fork.h"
+#include "xfs_alloc.h"
+#include "xfs_bmap.h"
+#include "xfs_quota.h"
+#include "xfs_qm.h"
+#include "xfs_dquot.h"
+#include "xfs_dquot_item.h"
+#include "xfs_reflink.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans_space.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/quota.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+
+/*
+ * Quota Repair
+ * ============
+ *
+ * Quota repairs are fairly simplistic; we fix everything that the dquot
+ * verifiers complain about, cap any counters or limits that make no sense,
+ * and schedule a quotacheck if we had to fix anything.  We also repair any
+ * data fork extent records that don't apply to metadata files.
+ */
+
+struct xrep_quota_info {
+	struct xfs_scrub	*sc;
+	bool			need_quotacheck;
+};
+
+/*
+ * Allocate a new block into a sparse hole in the quota file backing this
+ * dquot, initialize the block, and commit the whole mess.
+ */
+STATIC int
+xrep_quota_item_fill_bmap_hole(
+	struct xfs_scrub	*sc,
+	struct xfs_dquot	*dq,
+	struct xfs_bmbt_irec	*irec)
+{
+	struct xfs_buf		*bp;
+	struct xfs_mount	*mp = sc->mp;
+	int			nmaps = 1;
+	int			error;
+
+	xfs_trans_ijoin(sc->tp, sc->ip, 0);
+
+	/* Map a block into the file. */
+	error = xfs_trans_reserve_more(sc->tp, XFS_QM_DQALLOC_SPACE_RES(mp),
+			0);
+	if (error)
+		return error;
+
+	error = xfs_bmapi_write(sc->tp, sc->ip, dq->q_fileoffset,
+			XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA, 0,
+			irec, &nmaps);
+	if (error)
+		return error;
+	if (nmaps != 1)
+		return -ENOSPC;
+
+	dq->q_blkno = XFS_FSB_TO_DADDR(mp, irec->br_startblock);
+
+	trace_xrep_dquot_item_fill_bmap_hole(sc->mp, dq->q_type, dq->q_id);
+
+	/* Initialize the new block. */
+	error = xfs_trans_get_buf(sc->tp, mp->m_ddev_targp, dq->q_blkno,
+			mp->m_quotainfo->qi_dqchunklen, 0, &bp);
+	if (error)
+		return error;
+	bp->b_ops = &xfs_dquot_buf_ops;
+
+	xfs_qm_init_dquot_blk(sc->tp, dq->q_id, dq->q_type, bp);
+	xfs_buf_set_ref(bp, XFS_DQUOT_REF);
+
+	/*
+	 * Finish the mapping transactions and roll one more time to
+	 * disconnect sc->ip from sc->tp.
+	 */
+	error = xrep_defer_finish(sc);
+	if (error)
+		return error;
+	return xfs_trans_roll(&sc->tp);
+}
+
+/* Make sure there's a written block backing this dquot */
+STATIC int
+xrep_quota_item_bmap(
+	struct xfs_scrub	*sc,
+	struct xfs_dquot	*dq,
+	bool			*dirty)
+{
+	struct xfs_bmbt_irec	irec;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_quotainfo	*qi = mp->m_quotainfo;
+	xfs_fileoff_t		offset = dq->q_id / qi->qi_dqperchunk;
+	int			nmaps = 1;
+	int			error;
+
+	/* The computed file offset should always be valid. */
+	if (!xfs_verify_fileoff(mp, offset)) {
+		ASSERT(xfs_verify_fileoff(mp, offset));
+		return -EFSCORRUPTED;
+	}
+	dq->q_fileoffset = offset;
+
+	error = xfs_bmapi_read(sc->ip, offset, 1, &irec, &nmaps, 0);
+	if (error)
+		return error;
+
+	if (nmaps < 1 || !xfs_bmap_is_real_extent(&irec)) {
+		/* Hole/delalloc extent; allocate a real block. */
+		error = xrep_quota_item_fill_bmap_hole(sc, dq, &irec);
+		if (error)
+			return error;
+	} else if (irec.br_state != XFS_EXT_NORM) {
+		/* Unwritten extent, which we already took care of? */
+		ASSERT(irec.br_state == XFS_EXT_NORM);
+		return -EFSCORRUPTED;
+	} else if (dq->q_blkno != XFS_FSB_TO_DADDR(mp, irec.br_startblock)) {
+		/*
+		 * If the cached daddr is incorrect, repair probably punched a
+		 * hole out of the quota file and filled it back in with a new
+		 * block.  Update the block mapping in the dquot.
+		 */
+		dq->q_blkno = XFS_FSB_TO_DADDR(mp, irec.br_startblock);
+	}
+
+	*dirty = true;
+	return 0;
+}
+
+/* Reset quota timers if incorrectly set. */
+static inline void
+xrep_quota_item_timer(
+	struct xfs_scrub		*sc,
+	const struct xfs_dquot_res	*res,
+	bool				*dirty)
+{
+	if ((res->softlimit && res->count > res->softlimit) ||
+	    (res->hardlimit && res->count > res->hardlimit)) {
+		if (!res->timer)
+			*dirty = true;
+	} else {
+		if (res->timer)
+			*dirty = true;
+	}
+}
+
+/* Scrub the fields in an individual quota item. */
+STATIC int
+xrep_quota_item(
+	struct xrep_quota_info	*rqi,
+	struct xfs_dquot	*dq)
+{
+	struct xfs_scrub	*sc = rqi->sc;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_ino_t		fs_icount;
+	bool			dirty = false;
+	int			error = 0;
+
+	/* Last chance to abort before we start committing fixes. */
+	if (xchk_should_terminate(sc, &error))
+		return error;
+
+	/*
+	 * We might need to fix holes in the bmap record for the storage
+	 * backing this dquot, so we need to lock the dquot and the quota file.
+	 * dqiterate gave us a locked dquot, so drop the dquot lock to get the
+	 * ILOCK_EXCL.
+	 */
+	xfs_dqunlock(dq);
+	xchk_ilock(sc, XFS_ILOCK_EXCL);
+	xfs_dqlock(dq);
+
+	error = xrep_quota_item_bmap(sc, dq, &dirty);
+	xchk_iunlock(sc, XFS_ILOCK_EXCL);
+	if (error)
+		return error;
+
+	/* Check the limits. */
+	if (dq->q_blk.softlimit > dq->q_blk.hardlimit) {
+		dq->q_blk.softlimit = dq->q_blk.hardlimit;
+		dirty = true;
+	}
+
+	if (dq->q_ino.softlimit > dq->q_ino.hardlimit) {
+		dq->q_ino.softlimit = dq->q_ino.hardlimit;
+		dirty = true;
+	}
+
+	if (dq->q_rtb.softlimit > dq->q_rtb.hardlimit) {
+		dq->q_rtb.softlimit = dq->q_rtb.hardlimit;
+		dirty = true;
+	}
+
+	/*
+	 * Check that usage doesn't exceed physical limits.  However, on
+	 * a reflink filesystem we're allowed to exceed physical space
+	 * if there are no quota limits.  We don't know what the real number
+	 * is, but we can make quotacheck find out for us.
+	 */
+	if (!xfs_has_reflink(mp) && dq->q_blk.count > mp->m_sb.sb_dblocks) {
+		dq->q_blk.reserved -= dq->q_blk.count;
+		dq->q_blk.reserved += mp->m_sb.sb_dblocks;
+		dq->q_blk.count = mp->m_sb.sb_dblocks;
+		rqi->need_quotacheck = true;
+		dirty = true;
+	}
+	fs_icount = percpu_counter_sum(&mp->m_icount);
+	if (dq->q_ino.count > fs_icount) {
+		dq->q_ino.reserved -= dq->q_ino.count;
+		dq->q_ino.reserved += fs_icount;
+		dq->q_ino.count = fs_icount;
+		rqi->need_quotacheck = true;
+		dirty = true;
+	}
+	if (dq->q_rtb.count > mp->m_sb.sb_rblocks) {
+		dq->q_rtb.reserved -= dq->q_rtb.count;
+		dq->q_rtb.reserved += mp->m_sb.sb_rblocks;
+		dq->q_rtb.count = mp->m_sb.sb_rblocks;
+		rqi->need_quotacheck = true;
+		dirty = true;
+	}
+
+	xrep_quota_item_timer(sc, &dq->q_blk, &dirty);
+	xrep_quota_item_timer(sc, &dq->q_ino, &dirty);
+	xrep_quota_item_timer(sc, &dq->q_rtb, &dirty);
+
+	if (!dirty)
+		return 0;
+
+	trace_xrep_dquot_item(sc->mp, dq->q_type, dq->q_id);
+
+	dq->q_flags |= XFS_DQFLAG_DIRTY;
+	xfs_trans_dqjoin(sc->tp, dq);
+	if (dq->q_id) {
+		xfs_qm_adjust_dqlimits(dq);
+		xfs_qm_adjust_dqtimers(dq);
+	}
+	xfs_trans_log_dquot(sc->tp, dq);
+	error = xfs_trans_roll(&sc->tp);
+	xfs_dqlock(dq);
+	return error;
+}
+
+/* Fix a quota timer so that we can pass the verifier. */
+STATIC void
+xrep_quota_fix_timer(
+	struct xfs_mount	*mp,
+	const struct xfs_disk_dquot *ddq,
+	__be64			softlimit,
+	__be64			countnow,
+	__be32			*timer,
+	time64_t		timelimit)
+{
+	uint64_t		soft = be64_to_cpu(softlimit);
+	uint64_t		count = be64_to_cpu(countnow);
+	time64_t		new_timer;
+	uint32_t		t;
+
+	if (!soft || count <= soft || *timer != 0)
+		return;
+
+	new_timer = xfs_dquot_set_timeout(mp,
+				ktime_get_real_seconds() + timelimit);
+	if (ddq->d_type & XFS_DQTYPE_BIGTIME)
+		t = xfs_dq_unix_to_bigtime(new_timer);
+	else
+		t = new_timer;
+
+	*timer = cpu_to_be32(t);
+}
+
+/* Fix anything the verifiers complain about. */
+STATIC int
+xrep_quota_block(
+	struct xfs_scrub	*sc,
+	xfs_daddr_t		daddr,
+	xfs_dqtype_t		dqtype,
+	xfs_dqid_t		id)
+{
+	struct xfs_dqblk	*dqblk;
+	struct xfs_disk_dquot	*ddq;
+	struct xfs_quotainfo	*qi = sc->mp->m_quotainfo;
+	struct xfs_def_quota	*defq = xfs_get_defquota(qi, dqtype);
+	struct xfs_buf		*bp = NULL;
+	enum xfs_blft		buftype = 0;
+	int			i;
+	int			error;
+
+	error = xfs_trans_read_buf(sc->mp, sc->tp, sc->mp->m_ddev_targp, daddr,
+			qi->qi_dqchunklen, 0, &bp, &xfs_dquot_buf_ops);
+	switch (error) {
+	case -EFSBADCRC:
+	case -EFSCORRUPTED:
+		/* Failed verifier, retry read with no ops. */
+		error = xfs_trans_read_buf(sc->mp, sc->tp,
+				sc->mp->m_ddev_targp, daddr, qi->qi_dqchunklen,
+				0, &bp, NULL);
+		if (error)
+			return error;
+		break;
+	case 0:
+		dqblk = bp->b_addr;
+		ddq = &dqblk[0].dd_diskdq;
+
+		/*
+		 * If there's nothing that would impede a dqiterate, we're
+		 * done.
+		 */
+		if ((ddq->d_type & XFS_DQTYPE_REC_MASK) != dqtype ||
+		    id == be32_to_cpu(ddq->d_id)) {
+			xfs_trans_brelse(sc->tp, bp);
+			return 0;
+		}
+		break;
+	default:
+		return error;
+	}
+
+	/* Something's wrong with the block, fix the whole thing. */
+	dqblk = bp->b_addr;
+	bp->b_ops = &xfs_dquot_buf_ops;
+	for (i = 0; i < qi->qi_dqperchunk; i++, dqblk++) {
+		ddq = &dqblk->dd_diskdq;
+
+		trace_xrep_disk_dquot(sc->mp, dqtype, id + i);
+
+		ddq->d_magic = cpu_to_be16(XFS_DQUOT_MAGIC);
+		ddq->d_version = XFS_DQUOT_VERSION;
+		ddq->d_type = dqtype;
+		ddq->d_id = cpu_to_be32(id + i);
+
+		if (xfs_has_bigtime(sc->mp) && ddq->d_id)
+			ddq->d_type |= XFS_DQTYPE_BIGTIME;
+
+		xrep_quota_fix_timer(sc->mp, ddq, ddq->d_blk_softlimit,
+				ddq->d_bcount, &ddq->d_btimer,
+				defq->blk.time);
+
+		xrep_quota_fix_timer(sc->mp, ddq, ddq->d_ino_softlimit,
+				ddq->d_icount, &ddq->d_itimer,
+				defq->ino.time);
+
+		xrep_quota_fix_timer(sc->mp, ddq, ddq->d_rtb_softlimit,
+				ddq->d_rtbcount, &ddq->d_rtbtimer,
+				defq->rtb.time);
+
+		/* We only support v5 filesystems so always set these. */
+		uuid_copy(&dqblk->dd_uuid, &sc->mp->m_sb.sb_meta_uuid);
+		xfs_update_cksum((char *)dqblk, sizeof(struct xfs_dqblk),
+				 XFS_DQUOT_CRC_OFF);
+		dqblk->dd_lsn = 0;
+	}
+	switch (dqtype) {
+	case XFS_DQTYPE_USER:
+		buftype = XFS_BLFT_UDQUOT_BUF;
+		break;
+	case XFS_DQTYPE_GROUP:
+		buftype = XFS_BLFT_GDQUOT_BUF;
+		break;
+	case XFS_DQTYPE_PROJ:
+		buftype = XFS_BLFT_PDQUOT_BUF;
+		break;
+	}
+	xfs_trans_buf_set_type(sc->tp, bp, buftype);
+	xfs_trans_log_buf(sc->tp, bp, 0, BBTOB(bp->b_length) - 1);
+	return xrep_roll_trans(sc);
+}
+
+/*
+ * Repair a quota file's data fork.  The function returns with the inode
+ * joined.
+ */
+STATIC int
+xrep_quota_data_fork(
+	struct xfs_scrub	*sc,
+	xfs_dqtype_t		dqtype)
+{
+	struct xfs_bmbt_irec	irec = { 0 };
+	struct xfs_iext_cursor	icur;
+	struct xfs_quotainfo	*qi = sc->mp->m_quotainfo;
+	struct xfs_ifork	*ifp;
+	xfs_fileoff_t		max_dqid_off;
+	xfs_fileoff_t		off;
+	xfs_fsblock_t		fsbno;
+	bool			truncate = false;
+	bool			joined = false;
+	int			error = 0;
+
+	error = xrep_metadata_inode_forks(sc);
+	if (error)
+		goto out;
+
+	/* Check for data fork problems that apply only to quota files. */
+	max_dqid_off = XFS_DQ_ID_MAX / qi->qi_dqperchunk;
+	ifp = xfs_ifork_ptr(sc->ip, XFS_DATA_FORK);
+	for_each_xfs_iext(ifp, &icur, &irec) {
+		if (isnullstartblock(irec.br_startblock)) {
+			error = -EFSCORRUPTED;
+			goto out;
+		}
+
+		if (irec.br_startoff > max_dqid_off ||
+		    irec.br_startoff + irec.br_blockcount - 1 > max_dqid_off) {
+			truncate = true;
+			break;
+		}
+
+		/* Convert unwritten extents to real ones. */
+		if (irec.br_state == XFS_EXT_UNWRITTEN) {
+			struct xfs_bmbt_irec	nrec;
+			int			nmap = 1;
+
+			if (!joined) {
+				xfs_trans_ijoin(sc->tp, sc->ip, 0);
+				joined = true;
+			}
+
+			error = xfs_bmapi_write(sc->tp, sc->ip,
+					irec.br_startoff, irec.br_blockcount,
+					XFS_BMAPI_CONVERT, 0, &nrec, &nmap);
+			if (error)
+				goto out;
+			if (nmap != 1) {
+				error = -ENOSPC;
+				goto out;
+			}
+			ASSERT(nrec.br_startoff == irec.br_startoff);
+			ASSERT(nrec.br_blockcount == irec.br_blockcount);
+
+			error = xfs_defer_finish(&sc->tp);
+			if (error)
+				goto out;
+		}
+	}
+
+	if (!joined) {
+		xfs_trans_ijoin(sc->tp, sc->ip, 0);
+		joined = true;
+	}
+
+	if (truncate) {
+		/* Erase everything after the block containing the max dquot */
+		error = xfs_bunmapi_range(&sc->tp, sc->ip, 0,
+				max_dqid_off * sc->mp->m_sb.sb_blocksize,
+				XFS_MAX_FILEOFF);
+		if (error)
+			goto out;
+
+		/* Remove all CoW reservations. */
+		error = xfs_reflink_cancel_cow_blocks(sc->ip, &sc->tp, 0,
+				XFS_MAX_FILEOFF, true);
+		if (error)
+			goto out;
+		sc->ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+
+		/*
+		 * Always re-log the inode so that our permanent transaction
+		 * can keep on rolling it forward in the log.
+		 */
+		xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE);
+	}
+
+	/* Now go fix anything that fails the verifiers. */
+	for_each_xfs_iext(ifp, &icur, &irec) {
+		for (fsbno = irec.br_startblock, off = irec.br_startoff;
+		     fsbno < irec.br_startblock + irec.br_blockcount;
+		     fsbno += XFS_DQUOT_CLUSTER_SIZE_FSB,
+				off += XFS_DQUOT_CLUSTER_SIZE_FSB) {
+			error = xrep_quota_block(sc,
+					XFS_FSB_TO_DADDR(sc->mp, fsbno),
+					dqtype, off * qi->qi_dqperchunk);
+			if (error)
+				goto out;
+		}
+	}
+
+out:
+	return error;
+}
+
+/*
+ * Go fix anything in the quota items that we could have been mad about.  Now
+ * that we've checked the quota inode data fork we have to drop ILOCK_EXCL to
+ * use the regular dquot functions.
+ */
+STATIC int
+xrep_quota_problems(
+	struct xfs_scrub	*sc,
+	xfs_dqtype_t		dqtype)
+{
+	struct xchk_dqiter	cursor = { };
+	struct xrep_quota_info	rqi = { .sc = sc };
+	struct xfs_dquot	*dq;
+	int			error;
+
+	xchk_dqiter_init(&cursor, sc, dqtype);
+	while ((error = xchk_dquot_iter(&cursor, &dq)) == 1) {
+		error = xrep_quota_item(&rqi, dq);
+		xfs_qm_dqput(dq);
+		if (error)
+			break;
+	}
+	if (error)
+		return error;
+
+	/* Make a quotacheck happen. */
+	if (rqi.need_quotacheck)
+		xrep_force_quotacheck(sc, dqtype);
+	return 0;
+}
+
+/* Repair all of a quota type's items. */
+int
+xrep_quota(
+	struct xfs_scrub	*sc)
+{
+	xfs_dqtype_t		dqtype;
+	int			error;
+
+	dqtype = xchk_quota_to_dqtype(sc);
+
+	/*
+	 * Re-take the ILOCK so that we can fix any problems that we found
+	 * with the data fork mappings, or with the dquot bufs themselves.
+	 */
+	if (!(sc->ilock_flags & XFS_ILOCK_EXCL))
+		xchk_ilock(sc, XFS_ILOCK_EXCL);
+	error = xrep_quota_data_fork(sc, dqtype);
+	if (error)
+		return error;
+
+	/*
+	 * Finish deferred items and roll the transaction to unjoin the quota
+	 * inode from transaction so that we can unlock the quota inode; we
+	 * play only with dquots from now on.
+	 */
+	error = xrep_defer_finish(sc);
+	if (error)
+		return error;
+	error = xfs_trans_roll(&sc->tp);
+	if (error)
+		return error;
+	xchk_iunlock(sc, sc->ilock_flags);
+
+	/* Fix anything the dquot verifiers don't complain about. */
+	error = xrep_quota_problems(sc, dqtype);
+	if (error)
+		return error;
+
+	return xrep_trans_commit(sc);
+}
diff --git a/fs/xfs/scrub/readdir.c b/fs/xfs/scrub/readdir.c
index e51c1544be63..16462332c897 100644
--- a/fs/xfs/scrub/readdir.c
+++ b/fs/xfs/scrub/readdir.c
@@ -36,16 +36,14 @@ xchk_dir_walk_sf(
 	struct xfs_mount	*mp = dp->i_mount;
 	struct xfs_da_geometry	*geo = mp->m_dir_geo;
 	struct xfs_dir2_sf_entry *sfep;
-	struct xfs_dir2_sf_hdr	*sfp;
+	struct xfs_dir2_sf_hdr	*sfp = dp->i_df.if_data;
 	xfs_ino_t		ino;
 	xfs_dir2_dataptr_t	dapos;
 	unsigned int		i;
 	int			error;
 
 	ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
-	ASSERT(dp->i_df.if_u1.if_data != NULL);
-
-	sfp = (struct xfs_dir2_sf_hdr *)dp->i_df.if_u1.if_data;
+	ASSERT(sfp != NULL);
 
 	/* dot entry */
 	dapos = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
diff --git a/fs/xfs/scrub/reap.c b/fs/xfs/scrub/reap.c
index 86a62420e02c..f99eca799809 100644
--- a/fs/xfs/scrub/reap.c
+++ b/fs/xfs/scrub/reap.c
@@ -20,6 +20,7 @@
 #include "xfs_ialloc_btree.h"
 #include "xfs_rmap.h"
 #include "xfs_rmap_btree.h"
+#include "xfs_refcount.h"
 #include "xfs_refcount_btree.h"
 #include "xfs_extent_busy.h"
 #include "xfs_ag.h"
@@ -31,11 +32,14 @@
 #include "xfs_da_btree.h"
 #include "xfs_attr.h"
 #include "xfs_attr_remote.h"
+#include "xfs_defer.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
 #include "scrub/repair.h"
 #include "scrub/bitmap.h"
+#include "scrub/agb_bitmap.h"
+#include "scrub/fsb_bitmap.h"
 #include "scrub/reap.h"
 
 /*
@@ -73,10 +77,10 @@
  * with only the same rmap owner but the block is not owned by something with
  * the same rmap owner, the block will be freed.
  *
- * The caller is responsible for locking the AG headers for the entire rebuild
- * operation so that nothing else can sneak in and change the AG state while
- * we're not looking.  We must also invalidate any buffers associated with
- * @bitmap.
+ * The caller is responsible for locking the AG headers/inode for the entire
+ * rebuild operation so that nothing else can sneak in and change the incore
+ * state while we're not looking.  We must also invalidate any buffers
+ * associated with @bitmap.
  */
 
 /* Information about reaping extents after a repair. */
@@ -247,7 +251,7 @@ xreap_agextent_binval(
 		max_fsbs = min_t(xfs_agblock_t, agbno_next - bno,
 				xfs_attr3_rmt_blocks(mp, XFS_XATTR_SIZE_MAX));
 
-		for (fsbcount = 1; fsbcount < max_fsbs; fsbcount++) {
+		for (fsbcount = 1; fsbcount <= max_fsbs; fsbcount++) {
 			struct xfs_buf	*bp = NULL;
 			xfs_daddr_t	daddr;
 			int		error;
@@ -377,6 +381,17 @@ xreap_agextent_iter(
 		trace_xreap_dispose_unmap_extent(sc->sa.pag, agbno, *aglenp);
 
 		rs->force_roll = true;
+
+		if (rs->oinfo == &XFS_RMAP_OINFO_COW) {
+			/*
+			 * If we're unmapping CoW staging extents, remove the
+			 * records from the refcountbt, which will remove the
+			 * rmap record as well.
+			 */
+			xfs_refcount_free_cow_extent(sc->tp, fsbno, *aglenp);
+			return 0;
+		}
+
 		return xfs_rmap_free(sc->tp, sc->sa.agf_bp, sc->sa.pag, agbno,
 				*aglenp, rs->oinfo);
 	}
@@ -395,6 +410,26 @@ xreap_agextent_iter(
 		return 0;
 	}
 
+	/*
+	 * If we're getting rid of CoW staging extents, use deferred work items
+	 * to remove the refcountbt records (which removes the rmap records)
+	 * and free the extent.  We're not worried about the system going down
+	 * here because log recovery walks the refcount btree to clean out the
+	 * CoW staging extents.
+	 */
+	if (rs->oinfo == &XFS_RMAP_OINFO_COW) {
+		ASSERT(rs->resv == XFS_AG_RESV_NONE);
+
+		xfs_refcount_free_cow_extent(sc->tp, fsbno, *aglenp);
+		error = xfs_free_extent_later(sc->tp, fsbno, *aglenp, NULL,
+				rs->resv, true);
+		if (error)
+			return error;
+
+		rs->force_roll = true;
+		return 0;
+	}
+
 	/* Put blocks back on the AGFL one at a time. */
 	if (rs->resv == XFS_AG_RESV_AGFL) {
 		ASSERT(*aglenp == 1);
@@ -409,13 +444,17 @@ xreap_agextent_iter(
 	/*
 	 * Use deferred frees to get rid of the old btree blocks to try to
 	 * minimize the window in which we could crash and lose the old blocks.
+	 * Add a defer ops barrier every other extent to avoid stressing the
+	 * system with large EFIs.
 	 */
-	error = __xfs_free_extent_later(sc->tp, fsbno, *aglenp, rs->oinfo,
+	error = xfs_free_extent_later(sc->tp, fsbno, *aglenp, rs->oinfo,
 			rs->resv, true);
 	if (error)
 		return error;
 
 	rs->deferred++;
+	if (rs->deferred % 2 == 0)
+		xfs_defer_add_barrier(sc->tp);
 	return 0;
 }
 
@@ -425,13 +464,12 @@ xreap_agextent_iter(
  */
 STATIC int
 xreap_agmeta_extent(
-	uint64_t		fsbno,
-	uint64_t		len,
+	uint32_t		agbno,
+	uint32_t		len,
 	void			*priv)
 {
 	struct xreap_state	*rs = priv;
 	struct xfs_scrub	*sc = rs->sc;
-	xfs_agblock_t		agbno = fsbno;
 	xfs_agblock_t		agbno_next = agbno + len;
 	int			error = 0;
 
@@ -496,3 +534,115 @@ xrep_reap_agblocks(
 
 	return 0;
 }
+
+/*
+ * Break a file metadata extent into sub-extents by fate (crosslinked, not
+ * crosslinked), and dispose of each sub-extent separately.  The extent must
+ * not cross an AG boundary.
+ */
+STATIC int
+xreap_fsmeta_extent(
+	uint64_t		fsbno,
+	uint64_t		len,
+	void			*priv)
+{
+	struct xreap_state	*rs = priv;
+	struct xfs_scrub	*sc = rs->sc;
+	xfs_agnumber_t		agno = XFS_FSB_TO_AGNO(sc->mp, fsbno);
+	xfs_agblock_t		agbno = XFS_FSB_TO_AGBNO(sc->mp, fsbno);
+	xfs_agblock_t		agbno_next = agbno + len;
+	int			error = 0;
+
+	ASSERT(len <= XFS_MAX_BMBT_EXTLEN);
+	ASSERT(sc->ip != NULL);
+	ASSERT(!sc->sa.pag);
+
+	/*
+	 * We're reaping blocks after repairing file metadata, which means that
+	 * we have to init the xchk_ag structure ourselves.
+	 */
+	sc->sa.pag = xfs_perag_get(sc->mp, agno);
+	if (!sc->sa.pag)
+		return -EFSCORRUPTED;
+
+	error = xfs_alloc_read_agf(sc->sa.pag, sc->tp, 0, &sc->sa.agf_bp);
+	if (error)
+		goto out_pag;
+
+	while (agbno < agbno_next) {
+		xfs_extlen_t	aglen;
+		bool		crosslinked;
+
+		error = xreap_agextent_select(rs, agbno, agbno_next,
+				&crosslinked, &aglen);
+		if (error)
+			goto out_agf;
+
+		error = xreap_agextent_iter(rs, agbno, &aglen, crosslinked);
+		if (error)
+			goto out_agf;
+
+		if (xreap_want_defer_finish(rs)) {
+			/*
+			 * Holds the AGF buffer across the deferred chain
+			 * processing.
+			 */
+			error = xrep_defer_finish(sc);
+			if (error)
+				goto out_agf;
+			xreap_defer_finish_reset(rs);
+		} else if (xreap_want_roll(rs)) {
+			/*
+			 * Hold the AGF buffer across the transaction roll so
+			 * that we don't have to reattach it to the scrub
+			 * context.
+			 */
+			xfs_trans_bhold(sc->tp, sc->sa.agf_bp);
+			error = xfs_trans_roll_inode(&sc->tp, sc->ip);
+			xfs_trans_bjoin(sc->tp, sc->sa.agf_bp);
+			if (error)
+				goto out_agf;
+			xreap_reset(rs);
+		}
+
+		agbno += aglen;
+	}
+
+out_agf:
+	xfs_trans_brelse(sc->tp, sc->sa.agf_bp);
+	sc->sa.agf_bp = NULL;
+out_pag:
+	xfs_perag_put(sc->sa.pag);
+	sc->sa.pag = NULL;
+	return error;
+}
+
+/*
+ * Dispose of every block of every fs metadata extent in the bitmap.
+ * Do not use this to dispose of the mappings in an ondisk inode fork.
+ */
+int
+xrep_reap_fsblocks(
+	struct xfs_scrub		*sc,
+	struct xfsb_bitmap		*bitmap,
+	const struct xfs_owner_info	*oinfo)
+{
+	struct xreap_state		rs = {
+		.sc			= sc,
+		.oinfo			= oinfo,
+		.resv			= XFS_AG_RESV_NONE,
+	};
+	int				error;
+
+	ASSERT(xfs_has_rmapbt(sc->mp));
+	ASSERT(sc->ip != NULL);
+
+	error = xfsb_bitmap_walk(bitmap, xreap_fsmeta_extent, &rs);
+	if (error)
+		return error;
+
+	if (xreap_dirty(&rs))
+		return xrep_defer_finish(sc);
+
+	return 0;
+}
diff --git a/fs/xfs/scrub/reap.h b/fs/xfs/scrub/reap.h
index fe24626af164..0b69f16dd98f 100644
--- a/fs/xfs/scrub/reap.h
+++ b/fs/xfs/scrub/reap.h
@@ -6,7 +6,12 @@
 #ifndef __XFS_SCRUB_REAP_H__
 #define __XFS_SCRUB_REAP_H__
 
+struct xagb_bitmap;
+struct xfsb_bitmap;
+
 int xrep_reap_agblocks(struct xfs_scrub *sc, struct xagb_bitmap *bitmap,
 		const struct xfs_owner_info *oinfo, enum xfs_ag_resv_type type);
+int xrep_reap_fsblocks(struct xfs_scrub *sc, struct xfsb_bitmap *bitmap,
+		const struct xfs_owner_info *oinfo);
 
 #endif /* __XFS_SCRUB_REAP_H__ */
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index 304ea1e1bfb0..bf22f245bbfa 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -441,7 +441,7 @@ xchk_refcountbt_rec(
 	struct xchk_refcbt_records *rrc = bs->private;
 
 	xfs_refcount_btrec_to_irec(rec, &irec);
-	if (xfs_refcount_check_irec(bs->cur, &irec) != NULL) {
+	if (xfs_refcount_check_irec(bs->cur->bc_ag.pag, &irec) != NULL) {
 		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 		return 0;
 	}
diff --git a/fs/xfs/scrub/refcount_repair.c b/fs/xfs/scrub/refcount_repair.c
new file mode 100644
index 000000000000..f38fccc42a20
--- /dev/null
+++ b/fs/xfs/scrub/refcount_repair.c
@@ -0,0 +1,794 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_btree_staging.h"
+#include "xfs_inode.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_alloc.h"
+#include "xfs_ialloc.h"
+#include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_refcount.h"
+#include "xfs_refcount_btree.h"
+#include "xfs_error.h"
+#include "xfs_ag.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/btree.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/bitmap.h"
+#include "scrub/agb_bitmap.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/newbt.h"
+#include "scrub/reap.h"
+
+/*
+ * Rebuilding the Reference Count Btree
+ * ====================================
+ *
+ * This algorithm is "borrowed" from xfs_repair.  Imagine the rmap
+ * entries as rectangles representing extents of physical blocks, and
+ * that the rectangles can be laid down to allow them to overlap each
+ * other; then we know that we must emit a refcnt btree entry wherever
+ * the amount of overlap changes, i.e. the emission stimulus is
+ * level-triggered:
+ *
+ *                 -    ---
+ *       --      ----- ----   ---        ------
+ * --   ----     ----------- ----     ---------
+ * -------------------------------- -----------
+ * ^ ^  ^^ ^^    ^ ^^ ^^^  ^^^^  ^ ^^ ^  ^     ^
+ * 2 1  23 21    3 43 234  2123  1 01 2  3     0
+ *
+ * For our purposes, a rmap is a tuple (startblock, len, fileoff, owner).
+ *
+ * Note that in the actual refcnt btree we don't store the refcount < 2
+ * cases because the bnobt tells us which blocks are free; single-use
+ * blocks aren't recorded in the bnobt or the refcntbt.  If the rmapbt
+ * supports storing multiple entries covering a given block we could
+ * theoretically dispense with the refcntbt and simply count rmaps, but
+ * that's inefficient in the (hot) write path, so we'll take the cost of
+ * the extra tree to save time.  Also there's no guarantee that rmap
+ * will be enabled.
+ *
+ * Given an array of rmaps sorted by physical block number, a starting
+ * physical block (sp), a bag to hold rmaps that cover sp, and the next
+ * physical block where the level changes (np), we can reconstruct the
+ * refcount btree as follows:
+ *
+ * While there are still unprocessed rmaps in the array,
+ *  - Set sp to the physical block (pblk) of the next unprocessed rmap.
+ *  - Add to the bag all rmaps in the array where startblock == sp.
+ *  - Set np to the physical block where the bag size will change.  This
+ *    is the minimum of (the pblk of the next unprocessed rmap) and
+ *    (startblock + len of each rmap in the bag).
+ *  - Record the bag size as old_bag_size.
+ *
+ *  - While the bag isn't empty,
+ *     - Remove from the bag all rmaps where startblock + len == np.
+ *     - Add to the bag all rmaps in the array where startblock == np.
+ *     - If the bag size isn't old_bag_size, store the refcount entry
+ *       (sp, np - sp, bag_size) in the refcnt btree.
+ *     - If the bag is empty, break out of the inner loop.
+ *     - Set old_bag_size to the bag size
+ *     - Set sp = np.
+ *     - Set np to the physical block where the bag size will change.
+ *       This is the minimum of (the pblk of the next unprocessed rmap)
+ *       and (startblock + len of each rmap in the bag).
+ *
+ * Like all the other repairers, we make a list of all the refcount
+ * records we need, then reinitialize the refcount btree root and
+ * insert all the records.
+ */
+
+/* The only parts of the rmap that we care about for computing refcounts. */
+struct xrep_refc_rmap {
+	xfs_agblock_t		startblock;
+	xfs_extlen_t		blockcount;
+} __packed;
+
+struct xrep_refc {
+	/* refcount extents */
+	struct xfarray		*refcount_records;
+
+	/* new refcountbt information */
+	struct xrep_newbt	new_btree;
+
+	/* old refcountbt blocks */
+	struct xagb_bitmap	old_refcountbt_blocks;
+
+	struct xfs_scrub	*sc;
+
+	/* get_records()'s position in the refcount record array. */
+	xfarray_idx_t		array_cur;
+
+	/* # of refcountbt blocks */
+	xfs_extlen_t		btblocks;
+};
+
+/* Check for any obvious conflicts with this shared/CoW staging extent. */
+STATIC int
+xrep_refc_check_ext(
+	struct xfs_scrub		*sc,
+	const struct xfs_refcount_irec	*rec)
+{
+	enum xbtree_recpacking		outcome;
+	int				error;
+
+	if (xfs_refcount_check_irec(sc->sa.pag, rec) != NULL)
+		return -EFSCORRUPTED;
+
+	/* Make sure this isn't free space. */
+	error = xfs_alloc_has_records(sc->sa.bno_cur, rec->rc_startblock,
+			rec->rc_blockcount, &outcome);
+	if (error)
+		return error;
+	if (outcome != XBTREE_RECPACKING_EMPTY)
+		return -EFSCORRUPTED;
+
+	/* Must not be an inode chunk. */
+	error = xfs_ialloc_has_inodes_at_extent(sc->sa.ino_cur,
+			rec->rc_startblock, rec->rc_blockcount, &outcome);
+	if (error)
+		return error;
+	if (outcome != XBTREE_RECPACKING_EMPTY)
+		return -EFSCORRUPTED;
+
+	return 0;
+}
+
+/* Record a reference count extent. */
+STATIC int
+xrep_refc_stash(
+	struct xrep_refc		*rr,
+	enum xfs_refc_domain		domain,
+	xfs_agblock_t			agbno,
+	xfs_extlen_t			len,
+	uint64_t			refcount)
+{
+	struct xfs_refcount_irec	irec = {
+		.rc_startblock		= agbno,
+		.rc_blockcount		= len,
+		.rc_domain		= domain,
+	};
+	struct xfs_scrub		*sc = rr->sc;
+	int				error = 0;
+
+	if (xchk_should_terminate(sc, &error))
+		return error;
+
+	irec.rc_refcount = min_t(uint64_t, MAXREFCOUNT, refcount);
+
+	error = xrep_refc_check_ext(rr->sc, &irec);
+	if (error)
+		return error;
+
+	trace_xrep_refc_found(sc->sa.pag, &irec);
+
+	return xfarray_append(rr->refcount_records, &irec);
+}
+
+/* Record a CoW staging extent. */
+STATIC int
+xrep_refc_stash_cow(
+	struct xrep_refc		*rr,
+	xfs_agblock_t			agbno,
+	xfs_extlen_t			len)
+{
+	return xrep_refc_stash(rr, XFS_REFC_DOMAIN_COW, agbno, len, 1);
+}
+
+/* Decide if an rmap could describe a shared extent. */
+static inline bool
+xrep_refc_rmap_shareable(
+	struct xfs_mount		*mp,
+	const struct xfs_rmap_irec	*rmap)
+{
+	/* AG metadata are never sharable */
+	if (XFS_RMAP_NON_INODE_OWNER(rmap->rm_owner))
+		return false;
+
+	/* Metadata in files are never shareable */
+	if (xfs_internal_inum(mp, rmap->rm_owner))
+		return false;
+
+	/* Metadata and unwritten file blocks are not shareable. */
+	if (rmap->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK |
+			      XFS_RMAP_UNWRITTEN))
+		return false;
+
+	return true;
+}
+
+/*
+ * Walk along the reverse mapping records until we find one that could describe
+ * a shared extent.
+ */
+STATIC int
+xrep_refc_walk_rmaps(
+	struct xrep_refc	*rr,
+	struct xrep_refc_rmap	*rrm,
+	bool			*have_rec)
+{
+	struct xfs_rmap_irec	rmap;
+	struct xfs_btree_cur	*cur = rr->sc->sa.rmap_cur;
+	struct xfs_mount	*mp = cur->bc_mp;
+	int			have_gt;
+	int			error = 0;
+
+	*have_rec = false;
+
+	/*
+	 * Loop through the remaining rmaps.  Remember CoW staging
+	 * extents and the refcountbt blocks from the old tree for later
+	 * disposal.  We can only share written data fork extents, so
+	 * keep looping until we find an rmap for one.
+	 */
+	do {
+		if (xchk_should_terminate(rr->sc, &error))
+			return error;
+
+		error = xfs_btree_increment(cur, 0, &have_gt);
+		if (error)
+			return error;
+		if (!have_gt)
+			return 0;
+
+		error = xfs_rmap_get_rec(cur, &rmap, &have_gt);
+		if (error)
+			return error;
+		if (XFS_IS_CORRUPT(mp, !have_gt))
+			return -EFSCORRUPTED;
+
+		if (rmap.rm_owner == XFS_RMAP_OWN_COW) {
+			error = xrep_refc_stash_cow(rr, rmap.rm_startblock,
+					rmap.rm_blockcount);
+			if (error)
+				return error;
+		} else if (rmap.rm_owner == XFS_RMAP_OWN_REFC) {
+			/* refcountbt block, dump it when we're done. */
+			rr->btblocks += rmap.rm_blockcount;
+			error = xagb_bitmap_set(&rr->old_refcountbt_blocks,
+					rmap.rm_startblock, rmap.rm_blockcount);
+			if (error)
+				return error;
+		}
+	} while (!xrep_refc_rmap_shareable(mp, &rmap));
+
+	rrm->startblock = rmap.rm_startblock;
+	rrm->blockcount = rmap.rm_blockcount;
+	*have_rec = true;
+	return 0;
+}
+
+static inline uint32_t
+xrep_refc_encode_startblock(
+	const struct xfs_refcount_irec	*irec)
+{
+	uint32_t			start;
+
+	start = irec->rc_startblock & ~XFS_REFC_COWFLAG;
+	if (irec->rc_domain == XFS_REFC_DOMAIN_COW)
+		start |= XFS_REFC_COWFLAG;
+
+	return start;
+}
+
+/* Sort in the same order as the ondisk records. */
+static int
+xrep_refc_extent_cmp(
+	const void			*a,
+	const void			*b)
+{
+	const struct xfs_refcount_irec	*ap = a;
+	const struct xfs_refcount_irec	*bp = b;
+	uint32_t			sa, sb;
+
+	sa = xrep_refc_encode_startblock(ap);
+	sb = xrep_refc_encode_startblock(bp);
+
+	if (sa > sb)
+		return 1;
+	if (sa < sb)
+		return -1;
+	return 0;
+}
+
+/*
+ * Sort the refcount extents by startblock or else the btree records will be in
+ * the wrong order.  Make sure the records do not overlap in physical space.
+ */
+STATIC int
+xrep_refc_sort_records(
+	struct xrep_refc		*rr)
+{
+	struct xfs_refcount_irec	irec;
+	xfarray_idx_t			cur;
+	enum xfs_refc_domain		dom = XFS_REFC_DOMAIN_SHARED;
+	xfs_agblock_t			next_agbno = 0;
+	int				error;
+
+	error = xfarray_sort(rr->refcount_records, xrep_refc_extent_cmp,
+			XFARRAY_SORT_KILLABLE);
+	if (error)
+		return error;
+
+	foreach_xfarray_idx(rr->refcount_records, cur) {
+		if (xchk_should_terminate(rr->sc, &error))
+			return error;
+
+		error = xfarray_load(rr->refcount_records, cur, &irec);
+		if (error)
+			return error;
+
+		if (dom == XFS_REFC_DOMAIN_SHARED &&
+		    irec.rc_domain == XFS_REFC_DOMAIN_COW) {
+			dom = irec.rc_domain;
+			next_agbno = 0;
+		}
+
+		if (dom != irec.rc_domain)
+			return -EFSCORRUPTED;
+		if (irec.rc_startblock < next_agbno)
+			return -EFSCORRUPTED;
+
+		next_agbno = irec.rc_startblock + irec.rc_blockcount;
+	}
+
+	return error;
+}
+
+#define RRM_NEXT(r)	((r).startblock + (r).blockcount)
+/*
+ * Find the next block where the refcount changes, given the next rmap we
+ * looked at and the ones we're already tracking.
+ */
+static inline int
+xrep_refc_next_edge(
+	struct xfarray		*rmap_bag,
+	struct xrep_refc_rmap	*next_rrm,
+	bool			next_valid,
+	xfs_agblock_t		*nbnop)
+{
+	struct xrep_refc_rmap	rrm;
+	xfarray_idx_t		array_cur = XFARRAY_CURSOR_INIT;
+	xfs_agblock_t		nbno = NULLAGBLOCK;
+	int			error;
+
+	if (next_valid)
+		nbno = next_rrm->startblock;
+
+	while ((error = xfarray_iter(rmap_bag, &array_cur, &rrm)) == 1)
+		nbno = min_t(xfs_agblock_t, nbno, RRM_NEXT(rrm));
+
+	if (error)
+		return error;
+
+	/*
+	 * We should have found /something/ because either next_rrm is the next
+	 * interesting rmap to look at after emitting this refcount extent, or
+	 * there are other rmaps in rmap_bag contributing to the current
+	 * sharing count.  But if something is seriously wrong, bail out.
+	 */
+	if (nbno == NULLAGBLOCK)
+		return -EFSCORRUPTED;
+
+	*nbnop = nbno;
+	return 0;
+}
+
+/*
+ * Walk forward through the rmap btree to collect all rmaps starting at
+ * @bno in @rmap_bag.  These represent the file(s) that share ownership of
+ * the current block.  Upon return, the rmap cursor points to the last record
+ * satisfying the startblock constraint.
+ */
+static int
+xrep_refc_push_rmaps_at(
+	struct xrep_refc	*rr,
+	struct xfarray		*rmap_bag,
+	xfs_agblock_t		bno,
+	struct xrep_refc_rmap	*rrm,
+	bool			*have,
+	uint64_t		*stack_sz)
+{
+	struct xfs_scrub	*sc = rr->sc;
+	int			have_gt;
+	int			error;
+
+	while (*have && rrm->startblock == bno) {
+		error = xfarray_store_anywhere(rmap_bag, rrm);
+		if (error)
+			return error;
+		(*stack_sz)++;
+		error = xrep_refc_walk_rmaps(rr, rrm, have);
+		if (error)
+			return error;
+	}
+
+	error = xfs_btree_decrement(sc->sa.rmap_cur, 0, &have_gt);
+	if (error)
+		return error;
+	if (XFS_IS_CORRUPT(sc->mp, !have_gt))
+		return -EFSCORRUPTED;
+
+	return 0;
+}
+
+/* Iterate all the rmap records to generate reference count data. */
+STATIC int
+xrep_refc_find_refcounts(
+	struct xrep_refc	*rr)
+{
+	struct xrep_refc_rmap	rrm;
+	struct xfs_scrub	*sc = rr->sc;
+	struct xfarray		*rmap_bag;
+	char			*descr;
+	uint64_t		old_stack_sz;
+	uint64_t		stack_sz = 0;
+	xfs_agblock_t		sbno;
+	xfs_agblock_t		cbno;
+	xfs_agblock_t		nbno;
+	bool			have;
+	int			error;
+
+	xrep_ag_btcur_init(sc, &sc->sa);
+
+	/*
+	 * Set up a sparse array to store all the rmap records that we're
+	 * tracking to generate a reference count record.  If this exceeds
+	 * MAXREFCOUNT, we clamp rc_refcount.
+	 */
+	descr = xchk_xfile_ag_descr(sc, "rmap record bag");
+	error = xfarray_create(descr, 0, sizeof(struct xrep_refc_rmap),
+			&rmap_bag);
+	kfree(descr);
+	if (error)
+		goto out_cur;
+
+	/* Start the rmapbt cursor to the left of all records. */
+	error = xfs_btree_goto_left_edge(sc->sa.rmap_cur);
+	if (error)
+		goto out_bag;
+
+	/* Process reverse mappings into refcount data. */
+	while (xfs_btree_has_more_records(sc->sa.rmap_cur)) {
+		/* Push all rmaps with pblk == sbno onto the stack */
+		error = xrep_refc_walk_rmaps(rr, &rrm, &have);
+		if (error)
+			goto out_bag;
+		if (!have)
+			break;
+		sbno = cbno = rrm.startblock;
+		error = xrep_refc_push_rmaps_at(rr, rmap_bag, sbno,
+					&rrm, &have, &stack_sz);
+		if (error)
+			goto out_bag;
+
+		/* Set nbno to the bno of the next refcount change */
+		error = xrep_refc_next_edge(rmap_bag, &rrm, have, &nbno);
+		if (error)
+			goto out_bag;
+
+		ASSERT(nbno > sbno);
+		old_stack_sz = stack_sz;
+
+		/* While stack isn't empty... */
+		while (stack_sz) {
+			xfarray_idx_t	array_cur = XFARRAY_CURSOR_INIT;
+
+			/* Pop all rmaps that end at nbno */
+			while ((error = xfarray_iter(rmap_bag, &array_cur,
+								&rrm)) == 1) {
+				if (RRM_NEXT(rrm) != nbno)
+					continue;
+				error = xfarray_unset(rmap_bag, array_cur - 1);
+				if (error)
+					goto out_bag;
+				stack_sz--;
+			}
+			if (error)
+				goto out_bag;
+
+			/* Push array items that start at nbno */
+			error = xrep_refc_walk_rmaps(rr, &rrm, &have);
+			if (error)
+				goto out_bag;
+			if (have) {
+				error = xrep_refc_push_rmaps_at(rr, rmap_bag,
+						nbno, &rrm, &have, &stack_sz);
+				if (error)
+					goto out_bag;
+			}
+
+			/* Emit refcount if necessary */
+			ASSERT(nbno > cbno);
+			if (stack_sz != old_stack_sz) {
+				if (old_stack_sz > 1) {
+					error = xrep_refc_stash(rr,
+							XFS_REFC_DOMAIN_SHARED,
+							cbno, nbno - cbno,
+							old_stack_sz);
+					if (error)
+						goto out_bag;
+				}
+				cbno = nbno;
+			}
+
+			/* Stack empty, go find the next rmap */
+			if (stack_sz == 0)
+				break;
+			old_stack_sz = stack_sz;
+			sbno = nbno;
+
+			/* Set nbno to the bno of the next refcount change */
+			error = xrep_refc_next_edge(rmap_bag, &rrm, have,
+					&nbno);
+			if (error)
+				goto out_bag;
+
+			ASSERT(nbno > sbno);
+		}
+	}
+
+	ASSERT(stack_sz == 0);
+out_bag:
+	xfarray_destroy(rmap_bag);
+out_cur:
+	xchk_ag_btcur_free(&sc->sa);
+	return error;
+}
+#undef RRM_NEXT
+
+/* Retrieve refcountbt data for bulk load. */
+STATIC int
+xrep_refc_get_records(
+	struct xfs_btree_cur		*cur,
+	unsigned int			idx,
+	struct xfs_btree_block		*block,
+	unsigned int			nr_wanted,
+	void				*priv)
+{
+	struct xfs_refcount_irec	*irec = &cur->bc_rec.rc;
+	struct xrep_refc		*rr = priv;
+	union xfs_btree_rec		*block_rec;
+	unsigned int			loaded;
+	int				error;
+
+	for (loaded = 0; loaded < nr_wanted; loaded++, idx++) {
+		error = xfarray_load(rr->refcount_records, rr->array_cur++,
+				irec);
+		if (error)
+			return error;
+
+		block_rec = xfs_btree_rec_addr(cur, idx, block);
+		cur->bc_ops->init_rec_from_cur(cur, block_rec);
+	}
+
+	return loaded;
+}
+
+/* Feed one of the new btree blocks to the bulk loader. */
+STATIC int
+xrep_refc_claim_block(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr,
+	void			*priv)
+{
+	struct xrep_refc        *rr = priv;
+
+	return xrep_newbt_claim_block(cur, &rr->new_btree, ptr);
+}
+
+/* Update the AGF counters. */
+STATIC int
+xrep_refc_reset_counters(
+	struct xrep_refc	*rr)
+{
+	struct xfs_scrub	*sc = rr->sc;
+	struct xfs_perag	*pag = sc->sa.pag;
+
+	/*
+	 * After we commit the new btree to disk, it is possible that the
+	 * process to reap the old btree blocks will race with the AIL trying
+	 * to checkpoint the old btree blocks into the filesystem.  If the new
+	 * tree is shorter than the old one, the refcountbt write verifier will
+	 * fail and the AIL will shut down the filesystem.
+	 *
+	 * To avoid this, save the old incore btree height values as the alt
+	 * height values before re-initializing the perag info from the updated
+	 * AGF to capture all the new values.
+	 */
+	pag->pagf_repair_refcount_level = pag->pagf_refcount_level;
+
+	/* Reinitialize with the values we just logged. */
+	return xrep_reinit_pagf(sc);
+}
+
+/*
+ * Use the collected refcount information to stage a new refcount btree.  If
+ * this is successful we'll return with the new btree root information logged
+ * to the repair transaction but not yet committed.
+ */
+STATIC int
+xrep_refc_build_new_tree(
+	struct xrep_refc	*rr)
+{
+	struct xfs_scrub	*sc = rr->sc;
+	struct xfs_btree_cur	*refc_cur;
+	struct xfs_perag	*pag = sc->sa.pag;
+	xfs_fsblock_t		fsbno;
+	int			error;
+
+	error = xrep_refc_sort_records(rr);
+	if (error)
+		return error;
+
+	/*
+	 * Prepare to construct the new btree by reserving disk space for the
+	 * new btree and setting up all the accounting information we'll need
+	 * to root the new btree while it's under construction and before we
+	 * attach it to the AG header.
+	 */
+	fsbno = XFS_AGB_TO_FSB(sc->mp, pag->pag_agno, xfs_refc_block(sc->mp));
+	xrep_newbt_init_ag(&rr->new_btree, sc, &XFS_RMAP_OINFO_REFC, fsbno,
+			XFS_AG_RESV_METADATA);
+	rr->new_btree.bload.get_records = xrep_refc_get_records;
+	rr->new_btree.bload.claim_block = xrep_refc_claim_block;
+
+	/* Compute how many blocks we'll need. */
+	refc_cur = xfs_refcountbt_stage_cursor(sc->mp, &rr->new_btree.afake,
+			pag);
+	error = xfs_btree_bload_compute_geometry(refc_cur,
+			&rr->new_btree.bload,
+			xfarray_length(rr->refcount_records));
+	if (error)
+		goto err_cur;
+
+	/* Last chance to abort before we start committing fixes. */
+	if (xchk_should_terminate(sc, &error))
+		goto err_cur;
+
+	/* Reserve the space we'll need for the new btree. */
+	error = xrep_newbt_alloc_blocks(&rr->new_btree,
+			rr->new_btree.bload.nr_blocks);
+	if (error)
+		goto err_cur;
+
+	/*
+	 * Due to btree slack factors, it's possible for a new btree to be one
+	 * level taller than the old btree.  Update the incore btree height so
+	 * that we don't trip the verifiers when writing the new btree blocks
+	 * to disk.
+	 */
+	pag->pagf_repair_refcount_level = rr->new_btree.bload.btree_height;
+
+	/* Add all observed refcount records. */
+	rr->array_cur = XFARRAY_CURSOR_INIT;
+	error = xfs_btree_bload(refc_cur, &rr->new_btree.bload, rr);
+	if (error)
+		goto err_level;
+
+	/*
+	 * Install the new btree in the AG header.  After this point the old
+	 * btree is no longer accessible and the new tree is live.
+	 */
+	xfs_refcountbt_commit_staged_btree(refc_cur, sc->tp, sc->sa.agf_bp);
+	xfs_btree_del_cursor(refc_cur, 0);
+
+	/* Reset the AGF counters now that we've changed the btree shape. */
+	error = xrep_refc_reset_counters(rr);
+	if (error)
+		goto err_newbt;
+
+	/* Dispose of any unused blocks and the accounting information. */
+	error = xrep_newbt_commit(&rr->new_btree);
+	if (error)
+		return error;
+
+	return xrep_roll_ag_trans(sc);
+
+err_level:
+	pag->pagf_repair_refcount_level = 0;
+err_cur:
+	xfs_btree_del_cursor(refc_cur, error);
+err_newbt:
+	xrep_newbt_cancel(&rr->new_btree);
+	return error;
+}
+
+/*
+ * Now that we've logged the roots of the new btrees, invalidate all of the
+ * old blocks and free them.
+ */
+STATIC int
+xrep_refc_remove_old_tree(
+	struct xrep_refc	*rr)
+{
+	struct xfs_scrub	*sc = rr->sc;
+	struct xfs_perag	*pag = sc->sa.pag;
+	int			error;
+
+	/* Free the old refcountbt blocks if they're not in use. */
+	error = xrep_reap_agblocks(sc, &rr->old_refcountbt_blocks,
+			&XFS_RMAP_OINFO_REFC, XFS_AG_RESV_METADATA);
+	if (error)
+		return error;
+
+	/*
+	 * Now that we've zapped all the old refcountbt blocks we can turn off
+	 * the alternate height mechanism and reset the per-AG space
+	 * reservations.
+	 */
+	pag->pagf_repair_refcount_level = 0;
+	sc->flags |= XREP_RESET_PERAG_RESV;
+	return 0;
+}
+
+/* Rebuild the refcount btree. */
+int
+xrep_refcountbt(
+	struct xfs_scrub	*sc)
+{
+	struct xrep_refc	*rr;
+	struct xfs_mount	*mp = sc->mp;
+	char			*descr;
+	int			error;
+
+	/* We require the rmapbt to rebuild anything. */
+	if (!xfs_has_rmapbt(mp))
+		return -EOPNOTSUPP;
+
+	rr = kzalloc(sizeof(struct xrep_refc), XCHK_GFP_FLAGS);
+	if (!rr)
+		return -ENOMEM;
+	rr->sc = sc;
+
+	/* Set up enough storage to handle one refcount record per block. */
+	descr = xchk_xfile_ag_descr(sc, "reference count records");
+	error = xfarray_create(descr, mp->m_sb.sb_agblocks,
+			sizeof(struct xfs_refcount_irec),
+			&rr->refcount_records);
+	kfree(descr);
+	if (error)
+		goto out_rr;
+
+	/* Collect all reference counts. */
+	xagb_bitmap_init(&rr->old_refcountbt_blocks);
+	error = xrep_refc_find_refcounts(rr);
+	if (error)
+		goto out_bitmap;
+
+	/* Rebuild the refcount information. */
+	error = xrep_refc_build_new_tree(rr);
+	if (error)
+		goto out_bitmap;
+
+	/* Kill the old tree. */
+	error = xrep_refc_remove_old_tree(rr);
+	if (error)
+		goto out_bitmap;
+
+out_bitmap:
+	xagb_bitmap_destroy(&rr->old_refcountbt_blocks);
+	xfarray_destroy(rr->refcount_records);
+out_rr:
+	kfree(rr);
+	return error;
+}
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 1b8b5439f2d7..745d5b8f405a 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -27,6 +27,9 @@
 #include "xfs_quota.h"
 #include "xfs_qm.h"
 #include "xfs_defer.h"
+#include "xfs_errortag.h"
+#include "xfs_error.h"
+#include "xfs_reflink.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
@@ -176,6 +179,16 @@ xrep_roll_ag_trans(
 	return 0;
 }
 
+/* Roll the scrub transaction, holding the primary metadata locked. */
+int
+xrep_roll_trans(
+	struct xfs_scrub	*sc)
+{
+	if (!sc->ip)
+		return xrep_roll_ag_trans(sc);
+	return xfs_trans_roll_inode(&sc->tp, sc->ip);
+}
+
 /* Finish all deferred work attached to the repair transaction. */
 int
 xrep_defer_finish(
@@ -673,6 +686,7 @@ xrep_find_ag_btree_roots(
 	return error;
 }
 
+#ifdef CONFIG_XFS_QUOTA
 /* Force a quotacheck the next time we mount. */
 void
 xrep_force_quotacheck(
@@ -699,10 +713,10 @@ xrep_force_quotacheck(
  *
  * This function ensures that the appropriate dquots are attached to an inode.
  * We cannot allow the dquot code to allocate an on-disk dquot block here
- * because we're already in transaction context with the inode locked.  The
- * on-disk dquot should already exist anyway.  If the quota code signals
- * corruption or missing quota information, schedule quotacheck, which will
- * repair corruptions in the quota metadata.
+ * because we're already in transaction context.  The on-disk dquot should
+ * already exist anyway.  If the quota code signals corruption or missing quota
+ * information, schedule quotacheck, which will repair corruptions in the quota
+ * metadata.
  */
 int
 xrep_ino_dqattach(
@@ -710,7 +724,10 @@ xrep_ino_dqattach(
 {
 	int			error;
 
-	error = xfs_qm_dqattach_locked(sc->ip, false);
+	ASSERT(sc->tp != NULL);
+	ASSERT(sc->ip != NULL);
+
+	error = xfs_qm_dqattach(sc->ip);
 	switch (error) {
 	case -EFSBADCRC:
 	case -EFSCORRUPTED:
@@ -734,3 +751,367 @@ xrep_ino_dqattach(
 
 	return error;
 }
+#endif /* CONFIG_XFS_QUOTA */
+
+/*
+ * Ensure that the inode being repaired is ready to handle a certain number of
+ * extents, or return EFSCORRUPTED.  Caller must hold the ILOCK of the inode
+ * being repaired and have joined it to the scrub transaction.
+ */
+int
+xrep_ino_ensure_extent_count(
+	struct xfs_scrub	*sc,
+	int			whichfork,
+	xfs_extnum_t		nextents)
+{
+	xfs_extnum_t		max_extents;
+	bool			inode_has_nrext64;
+
+	inode_has_nrext64 = xfs_inode_has_large_extent_counts(sc->ip);
+	max_extents = xfs_iext_max_nextents(inode_has_nrext64, whichfork);
+	if (nextents <= max_extents)
+		return 0;
+	if (inode_has_nrext64)
+		return -EFSCORRUPTED;
+	if (!xfs_has_large_extent_counts(sc->mp))
+		return -EFSCORRUPTED;
+
+	max_extents = xfs_iext_max_nextents(true, whichfork);
+	if (nextents > max_extents)
+		return -EFSCORRUPTED;
+
+	sc->ip->i_diflags2 |= XFS_DIFLAG2_NREXT64;
+	xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE);
+	return 0;
+}
+
+/*
+ * Initialize all the btree cursors for an AG repair except for the btree that
+ * we're rebuilding.
+ */
+void
+xrep_ag_btcur_init(
+	struct xfs_scrub	*sc,
+	struct xchk_ag		*sa)
+{
+	struct xfs_mount	*mp = sc->mp;
+
+	/* Set up a bnobt cursor for cross-referencing. */
+	if (sc->sm->sm_type != XFS_SCRUB_TYPE_BNOBT &&
+	    sc->sm->sm_type != XFS_SCRUB_TYPE_CNTBT) {
+		sa->bno_cur = xfs_allocbt_init_cursor(mp, sc->tp, sa->agf_bp,
+				sc->sa.pag, XFS_BTNUM_BNO);
+		sa->cnt_cur = xfs_allocbt_init_cursor(mp, sc->tp, sa->agf_bp,
+				sc->sa.pag, XFS_BTNUM_CNT);
+	}
+
+	/* Set up a inobt cursor for cross-referencing. */
+	if (sc->sm->sm_type != XFS_SCRUB_TYPE_INOBT &&
+	    sc->sm->sm_type != XFS_SCRUB_TYPE_FINOBT) {
+		sa->ino_cur = xfs_inobt_init_cursor(sc->sa.pag, sc->tp,
+				sa->agi_bp, XFS_BTNUM_INO);
+		if (xfs_has_finobt(mp))
+			sa->fino_cur = xfs_inobt_init_cursor(sc->sa.pag,
+					sc->tp, sa->agi_bp, XFS_BTNUM_FINO);
+	}
+
+	/* Set up a rmapbt cursor for cross-referencing. */
+	if (sc->sm->sm_type != XFS_SCRUB_TYPE_RMAPBT &&
+	    xfs_has_rmapbt(mp))
+		sa->rmap_cur = xfs_rmapbt_init_cursor(mp, sc->tp, sa->agf_bp,
+				sc->sa.pag);
+
+	/* Set up a refcountbt cursor for cross-referencing. */
+	if (sc->sm->sm_type != XFS_SCRUB_TYPE_REFCNTBT &&
+	    xfs_has_reflink(mp))
+		sa->refc_cur = xfs_refcountbt_init_cursor(mp, sc->tp,
+				sa->agf_bp, sc->sa.pag);
+}
+
+/*
+ * Reinitialize the in-core AG state after a repair by rereading the AGF
+ * buffer.  We had better get the same AGF buffer as the one that's attached
+ * to the scrub context.
+ */
+int
+xrep_reinit_pagf(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_perag	*pag = sc->sa.pag;
+	struct xfs_buf		*bp;
+	int			error;
+
+	ASSERT(pag);
+	ASSERT(xfs_perag_initialised_agf(pag));
+
+	clear_bit(XFS_AGSTATE_AGF_INIT, &pag->pag_opstate);
+	error = xfs_alloc_read_agf(pag, sc->tp, 0, &bp);
+	if (error)
+		return error;
+
+	if (bp != sc->sa.agf_bp) {
+		ASSERT(bp == sc->sa.agf_bp);
+		return -EFSCORRUPTED;
+	}
+
+	return 0;
+}
+
+/*
+ * Reinitialize the in-core AG state after a repair by rereading the AGI
+ * buffer.  We had better get the same AGI buffer as the one that's attached
+ * to the scrub context.
+ */
+int
+xrep_reinit_pagi(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_perag	*pag = sc->sa.pag;
+	struct xfs_buf		*bp;
+	int			error;
+
+	ASSERT(pag);
+	ASSERT(xfs_perag_initialised_agi(pag));
+
+	clear_bit(XFS_AGSTATE_AGI_INIT, &pag->pag_opstate);
+	error = xfs_ialloc_read_agi(pag, sc->tp, &bp);
+	if (error)
+		return error;
+
+	if (bp != sc->sa.agi_bp) {
+		ASSERT(bp == sc->sa.agi_bp);
+		return -EFSCORRUPTED;
+	}
+
+	return 0;
+}
+
+/*
+ * Given an active reference to a perag structure, load AG headers and cursors.
+ * This should only be called to scan an AG while repairing file-based metadata.
+ */
+int
+xrep_ag_init(
+	struct xfs_scrub	*sc,
+	struct xfs_perag	*pag,
+	struct xchk_ag		*sa)
+{
+	int			error;
+
+	ASSERT(!sa->pag);
+
+	error = xfs_ialloc_read_agi(pag, sc->tp, &sa->agi_bp);
+	if (error)
+		return error;
+
+	error = xfs_alloc_read_agf(pag, sc->tp, 0, &sa->agf_bp);
+	if (error)
+		return error;
+
+	/* Grab our own passive reference from the caller's ref. */
+	sa->pag = xfs_perag_hold(pag);
+	xrep_ag_btcur_init(sc, sa);
+	return 0;
+}
+
+/* Reinitialize the per-AG block reservation for the AG we just fixed. */
+int
+xrep_reset_perag_resv(
+	struct xfs_scrub	*sc)
+{
+	int			error;
+
+	if (!(sc->flags & XREP_RESET_PERAG_RESV))
+		return 0;
+
+	ASSERT(sc->sa.pag != NULL);
+	ASSERT(sc->ops->type == ST_PERAG);
+	ASSERT(sc->tp);
+
+	sc->flags &= ~XREP_RESET_PERAG_RESV;
+	error = xfs_ag_resv_free(sc->sa.pag);
+	if (error)
+		goto out;
+	error = xfs_ag_resv_init(sc->sa.pag, sc->tp);
+	if (error == -ENOSPC) {
+		xfs_err(sc->mp,
+"Insufficient free space to reset per-AG reservation for AG %u after repair.",
+				sc->sa.pag->pag_agno);
+		error = 0;
+	}
+
+out:
+	return error;
+}
+
+/* Decide if we are going to call the repair function for a scrub type. */
+bool
+xrep_will_attempt(
+	struct xfs_scrub	*sc)
+{
+	/* Userspace asked us to rebuild the structure regardless. */
+	if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_FORCE_REBUILD)
+		return true;
+
+	/* Let debug users force us into the repair routines. */
+	if (XFS_TEST_ERROR(false, sc->mp, XFS_ERRTAG_FORCE_SCRUB_REPAIR))
+		return true;
+
+	/* Metadata is corrupt or failed cross-referencing. */
+	if (xchk_needs_repair(sc->sm))
+		return true;
+
+	return false;
+}
+
+/* Try to fix some part of a metadata inode by calling another scrubber. */
+STATIC int
+xrep_metadata_inode_subtype(
+	struct xfs_scrub	*sc,
+	unsigned int		scrub_type)
+{
+	__u32			smtype = sc->sm->sm_type;
+	__u32			smflags = sc->sm->sm_flags;
+	unsigned int		sick_mask = sc->sick_mask;
+	int			error;
+
+	/*
+	 * Let's see if the inode needs repair.  We're going to open-code calls
+	 * to the scrub and repair functions so that we can hang on to the
+	 * resources that we already acquired instead of using the standard
+	 * setup/teardown routines.
+	 */
+	sc->sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT;
+	sc->sm->sm_type = scrub_type;
+
+	switch (scrub_type) {
+	case XFS_SCRUB_TYPE_INODE:
+		error = xchk_inode(sc);
+		break;
+	case XFS_SCRUB_TYPE_BMBTD:
+		error = xchk_bmap_data(sc);
+		break;
+	case XFS_SCRUB_TYPE_BMBTA:
+		error = xchk_bmap_attr(sc);
+		break;
+	default:
+		ASSERT(0);
+		error = -EFSCORRUPTED;
+	}
+	if (error)
+		goto out;
+
+	if (!xrep_will_attempt(sc))
+		goto out;
+
+	/*
+	 * Repair some part of the inode.  This will potentially join the inode
+	 * to the transaction.
+	 */
+	switch (scrub_type) {
+	case XFS_SCRUB_TYPE_INODE:
+		error = xrep_inode(sc);
+		break;
+	case XFS_SCRUB_TYPE_BMBTD:
+		error = xrep_bmap(sc, XFS_DATA_FORK, false);
+		break;
+	case XFS_SCRUB_TYPE_BMBTA:
+		error = xrep_bmap(sc, XFS_ATTR_FORK, false);
+		break;
+	}
+	if (error)
+		goto out;
+
+	/*
+	 * Finish all deferred intent items and then roll the transaction so
+	 * that the inode will not be joined to the transaction when we exit
+	 * the function.
+	 */
+	error = xfs_defer_finish(&sc->tp);
+	if (error)
+		goto out;
+	error = xfs_trans_roll(&sc->tp);
+	if (error)
+		goto out;
+
+	/*
+	 * Clear the corruption flags and re-check the metadata that we just
+	 * repaired.
+	 */
+	sc->sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT;
+
+	switch (scrub_type) {
+	case XFS_SCRUB_TYPE_INODE:
+		error = xchk_inode(sc);
+		break;
+	case XFS_SCRUB_TYPE_BMBTD:
+		error = xchk_bmap_data(sc);
+		break;
+	case XFS_SCRUB_TYPE_BMBTA:
+		error = xchk_bmap_attr(sc);
+		break;
+	}
+	if (error)
+		goto out;
+
+	/* If corruption persists, the repair has failed. */
+	if (xchk_needs_repair(sc->sm)) {
+		error = -EFSCORRUPTED;
+		goto out;
+	}
+out:
+	sc->sick_mask = sick_mask;
+	sc->sm->sm_type = smtype;
+	sc->sm->sm_flags = smflags;
+	return error;
+}
+
+/*
+ * Repair the ondisk forks of a metadata inode.  The caller must ensure that
+ * sc->ip points to the metadata inode and the ILOCK is held on that inode.
+ * The inode must not be joined to the transaction before the call, and will
+ * not be afterwards.
+ */
+int
+xrep_metadata_inode_forks(
+	struct xfs_scrub	*sc)
+{
+	bool			dirty = false;
+	int			error;
+
+	/* Repair the inode record and the data fork. */
+	error = xrep_metadata_inode_subtype(sc, XFS_SCRUB_TYPE_INODE);
+	if (error)
+		return error;
+
+	error = xrep_metadata_inode_subtype(sc, XFS_SCRUB_TYPE_BMBTD);
+	if (error)
+		return error;
+
+	/* Make sure the attr fork looks ok before we delete it. */
+	error = xrep_metadata_inode_subtype(sc, XFS_SCRUB_TYPE_BMBTA);
+	if (error)
+		return error;
+
+	/* Clear the reflink flag since metadata never shares. */
+	if (xfs_is_reflink_inode(sc->ip)) {
+		dirty = true;
+		xfs_trans_ijoin(sc->tp, sc->ip, 0);
+		error = xfs_reflink_clear_inode_flag(sc->ip, &sc->tp);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * If we modified the inode, roll the transaction but don't rejoin the
+	 * inode to the new transaction because xrep_bmap_data can do that.
+	 */
+	if (dirty) {
+		error = xfs_trans_roll(&sc->tp);
+		if (error)
+			return error;
+		dirty = false;
+	}
+
+	return 0;
+}
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 60d2a9ae5f2e..17114327e6fa 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -28,15 +28,28 @@ static inline int xrep_notsupported(struct xfs_scrub *sc)
 /* Repair helpers */
 
 int xrep_attempt(struct xfs_scrub *sc, struct xchk_stats_run *run);
+bool xrep_will_attempt(struct xfs_scrub *sc);
 void xrep_failure(struct xfs_mount *mp);
 int xrep_roll_ag_trans(struct xfs_scrub *sc);
+int xrep_roll_trans(struct xfs_scrub *sc);
 int xrep_defer_finish(struct xfs_scrub *sc);
 bool xrep_ag_has_space(struct xfs_perag *pag, xfs_extlen_t nr_blocks,
 		enum xfs_ag_resv_type type);
 xfs_extlen_t xrep_calc_ag_resblks(struct xfs_scrub *sc);
 
+static inline int
+xrep_trans_commit(
+	struct xfs_scrub	*sc)
+{
+	int error = xfs_trans_commit(sc->tp);
+
+	sc->tp = NULL;
+	return error;
+}
+
 struct xbitmap;
 struct xagb_bitmap;
+struct xfsb_bitmap;
 
 int xrep_fix_freelist(struct xfs_scrub *sc, bool can_shrink);
 
@@ -57,8 +70,35 @@ struct xrep_find_ag_btree {
 
 int xrep_find_ag_btree_roots(struct xfs_scrub *sc, struct xfs_buf *agf_bp,
 		struct xrep_find_ag_btree *btree_info, struct xfs_buf *agfl_bp);
+
+#ifdef CONFIG_XFS_QUOTA
 void xrep_force_quotacheck(struct xfs_scrub *sc, xfs_dqtype_t type);
 int xrep_ino_dqattach(struct xfs_scrub *sc);
+#else
+# define xrep_force_quotacheck(sc, type)	((void)0)
+# define xrep_ino_dqattach(sc)			(0)
+#endif /* CONFIG_XFS_QUOTA */
+
+int xrep_ino_ensure_extent_count(struct xfs_scrub *sc, int whichfork,
+		xfs_extnum_t nextents);
+int xrep_reset_perag_resv(struct xfs_scrub *sc);
+int xrep_bmap(struct xfs_scrub *sc, int whichfork, bool allow_unwritten);
+int xrep_metadata_inode_forks(struct xfs_scrub *sc);
+
+/* Repair setup functions */
+int xrep_setup_ag_allocbt(struct xfs_scrub *sc);
+
+struct xfs_imap;
+int xrep_setup_inode(struct xfs_scrub *sc, const struct xfs_imap *imap);
+
+void xrep_ag_btcur_init(struct xfs_scrub *sc, struct xchk_ag *sa);
+int xrep_ag_init(struct xfs_scrub *sc, struct xfs_perag *pag,
+		struct xchk_ag *sa);
+
+/* Metadata revalidators */
+
+int xrep_revalidate_allocbt(struct xfs_scrub *sc);
+int xrep_revalidate_iallocbt(struct xfs_scrub *sc);
 
 /* Metadata repairers */
 
@@ -67,9 +107,34 @@ int xrep_superblock(struct xfs_scrub *sc);
 int xrep_agf(struct xfs_scrub *sc);
 int xrep_agfl(struct xfs_scrub *sc);
 int xrep_agi(struct xfs_scrub *sc);
+int xrep_allocbt(struct xfs_scrub *sc);
+int xrep_iallocbt(struct xfs_scrub *sc);
+int xrep_refcountbt(struct xfs_scrub *sc);
+int xrep_inode(struct xfs_scrub *sc);
+int xrep_bmap_data(struct xfs_scrub *sc);
+int xrep_bmap_attr(struct xfs_scrub *sc);
+int xrep_bmap_cow(struct xfs_scrub *sc);
+
+#ifdef CONFIG_XFS_RT
+int xrep_rtbitmap(struct xfs_scrub *sc);
+#else
+# define xrep_rtbitmap			xrep_notsupported
+#endif /* CONFIG_XFS_RT */
+
+#ifdef CONFIG_XFS_QUOTA
+int xrep_quota(struct xfs_scrub *sc);
+#else
+# define xrep_quota			xrep_notsupported
+#endif /* CONFIG_XFS_QUOTA */
+
+int xrep_reinit_pagf(struct xfs_scrub *sc);
+int xrep_reinit_pagi(struct xfs_scrub *sc);
 
 #else
 
+#define xrep_ino_dqattach(sc)	(0)
+#define xrep_will_attempt(sc)	(false)
+
 static inline int
 xrep_attempt(
 	struct xfs_scrub	*sc,
@@ -87,11 +152,45 @@ xrep_calc_ag_resblks(
 	return 0;
 }
 
+static inline int
+xrep_reset_perag_resv(
+	struct xfs_scrub	*sc)
+{
+	if (!(sc->flags & XREP_RESET_PERAG_RESV))
+		return 0;
+
+	ASSERT(0);
+	return -EOPNOTSUPP;
+}
+
+/* repair setup functions for no-repair */
+static inline int
+xrep_setup_nothing(
+	struct xfs_scrub	*sc)
+{
+	return 0;
+}
+#define xrep_setup_ag_allocbt		xrep_setup_nothing
+
+#define xrep_setup_inode(sc, imap)	((void)0)
+
+#define xrep_revalidate_allocbt		(NULL)
+#define xrep_revalidate_iallocbt	(NULL)
+
 #define xrep_probe			xrep_notsupported
 #define xrep_superblock			xrep_notsupported
 #define xrep_agf			xrep_notsupported
 #define xrep_agfl			xrep_notsupported
 #define xrep_agi			xrep_notsupported
+#define xrep_allocbt			xrep_notsupported
+#define xrep_iallocbt			xrep_notsupported
+#define xrep_refcountbt			xrep_notsupported
+#define xrep_inode			xrep_notsupported
+#define xrep_bmap_data			xrep_notsupported
+#define xrep_bmap_attr			xrep_notsupported
+#define xrep_bmap_cow			xrep_notsupported
+#define xrep_rtbitmap			xrep_notsupported
+#define xrep_quota			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index d29a26ecddd6..c99d1714f283 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -24,6 +24,7 @@
 #include "scrub/common.h"
 #include "scrub/btree.h"
 #include "scrub/bitmap.h"
+#include "scrub/agb_bitmap.h"
 
 /*
  * Set us up to scrub reverse mapping btrees.
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index 41a1d89ae8e6..441ca9977652 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -14,17 +14,33 @@
 #include "xfs_rtbitmap.h"
 #include "xfs_inode.h"
 #include "xfs_bmap.h"
+#include "xfs_bit.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
+#include "scrub/repair.h"
+#include "scrub/rtbitmap.h"
 
 /* Set us up with the realtime metadata locked. */
 int
 xchk_setup_rtbitmap(
 	struct xfs_scrub	*sc)
 {
+	struct xfs_mount	*mp = sc->mp;
+	struct xchk_rtbitmap	*rtb;
 	int			error;
 
-	error = xchk_trans_alloc(sc, 0);
+	rtb = kzalloc(sizeof(struct xchk_rtbitmap), XCHK_GFP_FLAGS);
+	if (!rtb)
+		return -ENOMEM;
+	sc->buf = rtb;
+
+	if (xchk_could_repair(sc)) {
+		error = xrep_setup_rtbitmap(sc, rtb);
+		if (error)
+			return error;
+	}
+
+	error = xchk_trans_alloc(sc, rtb->resblks);
 	if (error)
 		return error;
 
@@ -32,7 +48,22 @@ xchk_setup_rtbitmap(
 	if (error)
 		return error;
 
+	error = xchk_ino_dqattach(sc);
+	if (error)
+		return error;
+
 	xchk_ilock(sc, XFS_ILOCK_EXCL | XFS_ILOCK_RTBITMAP);
+
+	/*
+	 * Now that we've locked the rtbitmap, we can't race with growfsrt
+	 * trying to expand the bitmap or change the size of the rt volume.
+	 * Hence it is safe to compute and check the geometry values.
+	 */
+	if (mp->m_sb.sb_rblocks) {
+		rtb->rextents = xfs_rtb_to_rtx(mp, mp->m_sb.sb_rblocks);
+		rtb->rextslog = xfs_compute_rextslog(rtb->rextents);
+		rtb->rbmblocks = xfs_rtbitmap_blockcount(mp, rtb->rextents);
+	}
 	return 0;
 }
 
@@ -63,21 +94,30 @@ STATIC int
 xchk_rtbitmap_check_extents(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_mount	*mp = sc->mp;
 	struct xfs_bmbt_irec	map;
-	xfs_rtblock_t		off;
-	int			nmap;
+	struct xfs_iext_cursor	icur;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_inode	*ip = sc->ip;
+	xfs_fileoff_t		off = 0;
+	xfs_fileoff_t		endoff;
 	int			error = 0;
 
-	for (off = 0; off < mp->m_sb.sb_rbmblocks;) {
+	/* Mappings may not cross or lie beyond EOF. */
+	endoff = XFS_B_TO_FSB(mp, ip->i_disk_size);
+	if (xfs_iext_lookup_extent(ip, &ip->i_df, endoff, &icur, &map)) {
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, endoff);
+		return 0;
+	}
+
+	while (off < endoff) {
+		int		nmap = 1;
+
 		if (xchk_should_terminate(sc, &error) ||
 		    (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 			break;
 
 		/* Make sure we have a written extent. */
-		nmap = 1;
-		error = xfs_bmapi_read(mp->m_rbmip, off,
-				mp->m_sb.sb_rbmblocks - off, &map, &nmap,
+		error = xfs_bmapi_read(ip, off, endoff - off, &map, &nmap,
 				XFS_DATA_FORK);
 		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, off, &error))
 			break;
@@ -98,12 +138,48 @@ int
 xchk_rtbitmap(
 	struct xfs_scrub	*sc)
 {
+	struct xfs_mount	*mp = sc->mp;
+	struct xchk_rtbitmap	*rtb = sc->buf;
 	int			error;
 
-	/* Is the size of the rtbitmap correct? */
-	if (sc->mp->m_rbmip->i_disk_size !=
-	    XFS_FSB_TO_B(sc->mp, sc->mp->m_sb.sb_rbmblocks)) {
-		xchk_ino_set_corrupt(sc, sc->mp->m_rbmip->i_ino);
+	/* Is sb_rextents correct? */
+	if (mp->m_sb.sb_rextents != rtb->rextents) {
+		xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
+		return 0;
+	}
+
+	/* Is sb_rextslog correct? */
+	if (mp->m_sb.sb_rextslog != rtb->rextslog) {
+		xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
+		return 0;
+	}
+
+	/*
+	 * Is sb_rbmblocks large enough to handle the current rt volume?  In no
+	 * case can we exceed 4bn bitmap blocks since the super field is a u32.
+	 */
+	if (rtb->rbmblocks > U32_MAX) {
+		xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
+		return 0;
+	}
+	if (mp->m_sb.sb_rbmblocks != rtb->rbmblocks) {
+		xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
+		return 0;
+	}
+
+	/* The bitmap file length must be aligned to an fsblock. */
+	if (mp->m_rbmip->i_disk_size & mp->m_blockmask) {
+		xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
+		return 0;
+	}
+
+	/*
+	 * Is the bitmap file itself large enough to handle the rt volume?
+	 * growfsrt expands the bitmap file before updating sb_rextents, so the
+	 * file can be larger than sb_rbmblocks.
+	 */
+	if (mp->m_rbmip->i_disk_size < XFS_FSB_TO_B(mp, rtb->rbmblocks)) {
+		xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
 		return 0;
 	}
 
@@ -116,12 +192,11 @@ xchk_rtbitmap(
 	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 		return error;
 
-	error = xfs_rtalloc_query_all(sc->mp, sc->tp, xchk_rtbitmap_rec, sc);
+	error = xfs_rtalloc_query_all(mp, sc->tp, xchk_rtbitmap_rec, sc);
 	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
-		goto out;
+		return error;
 
-out:
-	return error;
+	return 0;
 }
 
 /* xref check that the extent is not free in the rtbitmap */
diff --git a/fs/xfs/scrub/rtbitmap.h b/fs/xfs/scrub/rtbitmap.h
new file mode 100644
index 000000000000..85304ff019e1
--- /dev/null
+++ b/fs/xfs/scrub/rtbitmap.h
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_RTBITMAP_H__
+#define __XFS_SCRUB_RTBITMAP_H__
+
+struct xchk_rtbitmap {
+	uint64_t		rextents;
+	uint64_t		rbmblocks;
+	unsigned int		rextslog;
+	unsigned int		resblks;
+};
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+int xrep_setup_rtbitmap(struct xfs_scrub *sc, struct xchk_rtbitmap *rtb);
+#else
+# define xrep_setup_rtbitmap(sc, rtb)	(0)
+#endif /* CONFIG_XFS_ONLINE_REPAIR */
+
+#endif /* __XFS_SCRUB_RTBITMAP_H__ */
diff --git a/fs/xfs/scrub/rtbitmap_repair.c b/fs/xfs/scrub/rtbitmap_repair.c
new file mode 100644
index 000000000000..46f5d5f605c9
--- /dev/null
+++ b/fs/xfs/scrub/rtbitmap_repair.c
@@ -0,0 +1,202 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2020-2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_btree.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_inode.h"
+#include "xfs_bit.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_btree.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/xfile.h"
+#include "scrub/rtbitmap.h"
+
+/* Set up to repair the realtime bitmap file metadata. */
+int
+xrep_setup_rtbitmap(
+	struct xfs_scrub	*sc,
+	struct xchk_rtbitmap	*rtb)
+{
+	struct xfs_mount	*mp = sc->mp;
+	unsigned long long	blocks = 0;
+
+	/*
+	 * Reserve enough blocks to write out a completely new bmbt for a
+	 * maximally fragmented bitmap file.  We do not hold the rtbitmap
+	 * ILOCK yet, so this is entirely speculative.
+	 */
+	blocks = xfs_bmbt_calc_size(mp, mp->m_sb.sb_rbmblocks);
+	if (blocks > UINT_MAX)
+		return -EOPNOTSUPP;
+
+	rtb->resblks += blocks;
+	return 0;
+}
+
+/*
+ * Make sure that the given range of the data fork of the realtime file is
+ * mapped to written blocks.  The caller must ensure that the inode is joined
+ * to the transaction.
+ */
+STATIC int
+xrep_rtbitmap_data_mappings(
+	struct xfs_scrub	*sc,
+	xfs_filblks_t		len)
+{
+	struct xfs_bmbt_irec	map;
+	xfs_fileoff_t		off = 0;
+	int			error;
+
+	ASSERT(sc->ip != NULL);
+
+	while (off < len) {
+		int		nmaps = 1;
+
+		/*
+		 * If we have a real extent mapping this block then we're
+		 * in ok shape.
+		 */
+		error = xfs_bmapi_read(sc->ip, off, len - off, &map, &nmaps,
+				XFS_DATA_FORK);
+		if (error)
+			return error;
+		if (nmaps == 0) {
+			ASSERT(nmaps != 0);
+			return -EFSCORRUPTED;
+		}
+
+		/*
+		 * Written extents are ok.  Holes are not filled because we
+		 * do not know the freespace information.
+		 */
+		if (xfs_bmap_is_written_extent(&map) ||
+		    map.br_startblock == HOLESTARTBLOCK) {
+			off = map.br_startoff + map.br_blockcount;
+			continue;
+		}
+
+		/*
+		 * If we find a delalloc reservation then something is very
+		 * very wrong.  Bail out.
+		 */
+		if (map.br_startblock == DELAYSTARTBLOCK)
+			return -EFSCORRUPTED;
+
+		/* Make sure we're really converting an unwritten extent. */
+		if (map.br_state != XFS_EXT_UNWRITTEN) {
+			ASSERT(map.br_state == XFS_EXT_UNWRITTEN);
+			return -EFSCORRUPTED;
+		}
+
+		/* Make sure this block has a real zeroed extent mapped. */
+		nmaps = 1;
+		error = xfs_bmapi_write(sc->tp, sc->ip, map.br_startoff,
+				map.br_blockcount,
+				XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO,
+				0, &map, &nmaps);
+		if (error)
+			return error;
+		if (nmaps != 1)
+			return -EFSCORRUPTED;
+
+		/* Commit new extent and all deferred work. */
+		error = xrep_defer_finish(sc);
+		if (error)
+			return error;
+
+		off = map.br_startoff + map.br_blockcount;
+	}
+
+	return 0;
+}
+
+/* Fix broken rt volume geometry. */
+STATIC int
+xrep_rtbitmap_geometry(
+	struct xfs_scrub	*sc,
+	struct xchk_rtbitmap	*rtb)
+{
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_trans	*tp = sc->tp;
+
+	/* Superblock fields */
+	if (mp->m_sb.sb_rextents != rtb->rextents)
+		xfs_trans_mod_sb(sc->tp, XFS_TRANS_SB_REXTENTS,
+				rtb->rextents - mp->m_sb.sb_rextents);
+
+	if (mp->m_sb.sb_rbmblocks != rtb->rbmblocks)
+		xfs_trans_mod_sb(tp, XFS_TRANS_SB_RBMBLOCKS,
+				rtb->rbmblocks - mp->m_sb.sb_rbmblocks);
+
+	if (mp->m_sb.sb_rextslog != rtb->rextslog)
+		xfs_trans_mod_sb(tp, XFS_TRANS_SB_REXTSLOG,
+				rtb->rextslog - mp->m_sb.sb_rextslog);
+
+	/* Fix broken isize */
+	sc->ip->i_disk_size = roundup_64(sc->ip->i_disk_size,
+					 mp->m_sb.sb_blocksize);
+
+	if (sc->ip->i_disk_size < XFS_FSB_TO_B(mp, rtb->rbmblocks))
+		sc->ip->i_disk_size = XFS_FSB_TO_B(mp, rtb->rbmblocks);
+
+	xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE);
+	return xrep_roll_trans(sc);
+}
+
+/* Repair the realtime bitmap file metadata. */
+int
+xrep_rtbitmap(
+	struct xfs_scrub	*sc)
+{
+	struct xchk_rtbitmap	*rtb = sc->buf;
+	struct xfs_mount	*mp = sc->mp;
+	unsigned long long	blocks = 0;
+	int			error;
+
+	/* Impossibly large rtbitmap means we can't touch the filesystem. */
+	if (rtb->rbmblocks > U32_MAX)
+		return 0;
+
+	/*
+	 * If the size of the rt bitmap file is larger than what we reserved,
+	 * figure out if we need to adjust the block reservation in the
+	 * transaction.
+	 */
+	blocks = xfs_bmbt_calc_size(mp, rtb->rbmblocks);
+	if (blocks > UINT_MAX)
+		return -EOPNOTSUPP;
+	if (blocks > rtb->resblks) {
+		error = xfs_trans_reserve_more(sc->tp, blocks, 0);
+		if (error)
+			return error;
+
+		rtb->resblks += blocks;
+	}
+
+	/* Fix inode core and forks. */
+	error = xrep_metadata_inode_forks(sc);
+	if (error)
+		return error;
+
+	xfs_trans_ijoin(sc->tp, sc->ip, 0);
+
+	/* Ensure no unwritten extents. */
+	error = xrep_rtbitmap_data_mappings(sc, rtb->rbmblocks);
+	if (error)
+		return error;
+
+	/* Fix inconsistent bitmap geometry */
+	return xrep_rtbitmap_geometry(sc, rtb);
+}
diff --git a/fs/xfs/scrub/rtsummary.c b/fs/xfs/scrub/rtsummary.c
index 8b15c47408d0..fabd0ed9dfa6 100644
--- a/fs/xfs/scrub/rtsummary.c
+++ b/fs/xfs/scrub/rtsummary.c
@@ -31,6 +31,18 @@
  * (potentially large) amount of data in pageable memory.
  */
 
+struct xchk_rtsummary {
+	struct xfs_rtalloc_args	args;
+
+	uint64_t		rextents;
+	uint64_t		rbmblocks;
+	uint64_t		rsumsize;
+	unsigned int		rsumlevels;
+
+	/* Memory buffer for the summary comparison. */
+	union xfs_suminfo_raw	words[];
+};
+
 /* Set us up to check the rtsummary file. */
 int
 xchk_setup_rtsummary(
@@ -38,8 +50,15 @@ xchk_setup_rtsummary(
 {
 	struct xfs_mount	*mp = sc->mp;
 	char			*descr;
+	struct xchk_rtsummary	*rts;
 	int			error;
 
+	rts = kvzalloc(struct_size(rts, words, mp->m_blockwsize),
+			XCHK_GFP_FLAGS);
+	if (!rts)
+		return -ENOMEM;
+	sc->buf = rts;
+
 	/*
 	 * Create an xfile to construct a new rtsummary file.  The xfile allows
 	 * us to avoid pinning kernel memory for this purpose.
@@ -54,15 +73,14 @@ xchk_setup_rtsummary(
 	if (error)
 		return error;
 
-	/* Allocate a memory buffer for the summary comparison. */
-	sc->buf = kvmalloc(mp->m_sb.sb_blocksize, XCHK_GFP_FLAGS);
-	if (!sc->buf)
-		return -ENOMEM;
-
 	error = xchk_install_live_inode(sc, mp->m_rsumip);
 	if (error)
 		return error;
 
+	error = xchk_ino_dqattach(sc);
+	if (error)
+		return error;
+
 	/*
 	 * Locking order requires us to take the rtbitmap first.  We must be
 	 * careful to unlock it ourselves when we are done with the rtbitmap
@@ -71,13 +89,29 @@ xchk_setup_rtsummary(
 	 */
 	xfs_ilock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
 	xchk_ilock(sc, XFS_ILOCK_EXCL | XFS_ILOCK_RTSUM);
+
+	/*
+	 * Now that we've locked the rtbitmap and rtsummary, we can't race with
+	 * growfsrt trying to expand the summary or change the size of the rt
+	 * volume.  Hence it is safe to compute and check the geometry values.
+	 */
+	if (mp->m_sb.sb_rblocks) {
+		xfs_filblks_t	rsumblocks;
+		int		rextslog;
+
+		rts->rextents = xfs_rtb_to_rtx(mp, mp->m_sb.sb_rblocks);
+		rextslog = xfs_compute_rextslog(rts->rextents);
+		rts->rsumlevels = rextslog + 1;
+		rts->rbmblocks = xfs_rtbitmap_blockcount(mp, rts->rextents);
+		rsumblocks = xfs_rtsummary_blockcount(mp, rts->rsumlevels,
+				rts->rbmblocks);
+		rts->rsumsize = XFS_FSB_TO_B(mp, rsumblocks);
+	}
 	return 0;
 }
 
 /* Helper functions to record suminfo words in an xfile. */
 
-typedef unsigned int xchk_rtsumoff_t;
-
 static inline int
 xfsum_load(
 	struct xfs_scrub	*sc,
@@ -143,7 +177,7 @@ xchk_rtsum_record_free(
 
 	/* Compute the relevant location in the rtsum file. */
 	rbmoff = xfs_rtx_to_rbmblock(mp, rec->ar_startext);
-	lenlog = XFS_RTBLOCKLOG(rec->ar_extcount);
+	lenlog = xfs_highbit64(rec->ar_extcount);
 	offs = xfs_rtsumoffs(mp, lenlog, rbmoff);
 
 	rtbno = xfs_rtx_to_rtb(mp, rec->ar_startext);
@@ -188,19 +222,29 @@ STATIC int
 xchk_rtsum_compare(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_rtalloc_args args = {
-		.mp		= sc->mp,
-		.tp		= sc->tp,
-	};
-	struct xfs_mount	*mp = sc->mp;
 	struct xfs_bmbt_irec	map;
-	xfs_fileoff_t		off;
-	xchk_rtsumoff_t		sumoff = 0;
-	int			nmap;
+	struct xfs_iext_cursor	icur;
+
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_inode	*ip = sc->ip;
+	struct xchk_rtsummary	*rts = sc->buf;
+	xfs_fileoff_t		off = 0;
+	xfs_fileoff_t		endoff;
+	xfs_rtsumoff_t		sumoff = 0;
+	int			error = 0;
+
+	rts->args.mp = sc->mp;
+	rts->args.tp = sc->tp;
+
+	/* Mappings may not cross or lie beyond EOF. */
+	endoff = XFS_B_TO_FSB(mp, ip->i_disk_size);
+	if (xfs_iext_lookup_extent(ip, &ip->i_df, endoff, &icur, &map)) {
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, endoff);
+		return 0;
+	}
 
-	for (off = 0; off < XFS_B_TO_FSB(mp, mp->m_rsumsize); off++) {
-		union xfs_suminfo_raw *ondisk_info;
-		int		error = 0;
+	while (off < endoff) {
+		int		nmap = 1;
 
 		if (xchk_should_terminate(sc, &error))
 			return error;
@@ -208,8 +252,7 @@ xchk_rtsum_compare(
 			return 0;
 
 		/* Make sure we have a written extent. */
-		nmap = 1;
-		error = xfs_bmapi_read(mp->m_rsumip, off, 1, &map, &nmap,
+		error = xfs_bmapi_read(ip, off, endoff - off, &map, &nmap,
 				XFS_DATA_FORK);
 		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, off, &error))
 			return error;
@@ -219,24 +262,33 @@ xchk_rtsum_compare(
 			return 0;
 		}
 
+		off += map.br_blockcount;
+	}
+
+	for (off = 0; off < endoff; off++) {
+		union xfs_suminfo_raw	*ondisk_info;
+
 		/* Read a block's worth of ondisk rtsummary file. */
-		error = xfs_rtsummary_read_buf(&args, off);
+		error = xfs_rtsummary_read_buf(&rts->args, off);
 		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, off, &error))
 			return error;
 
 		/* Read a block's worth of computed rtsummary file. */
-		error = xfsum_copyout(sc, sumoff, sc->buf, mp->m_blockwsize);
+		error = xfsum_copyout(sc, sumoff, rts->words, mp->m_blockwsize);
 		if (error) {
-			xfs_rtbuf_cache_relse(&args);
+			xfs_rtbuf_cache_relse(&rts->args);
 			return error;
 		}
 
-		ondisk_info = xfs_rsumblock_infoptr(&args, 0);
-		if (memcmp(ondisk_info, sc->buf,
-					mp->m_blockwsize << XFS_WORDLOG) != 0)
+		ondisk_info = xfs_rsumblock_infoptr(&rts->args, 0);
+		if (memcmp(ondisk_info, rts->words,
+					mp->m_blockwsize << XFS_WORDLOG) != 0) {
 			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, off);
+			xfs_rtbuf_cache_relse(&rts->args);
+			return error;
+		}
 
-		xfs_rtbuf_cache_relse(&args);
+		xfs_rtbuf_cache_relse(&rts->args);
 		sumoff += mp->m_blockwsize;
 	}
 
@@ -249,8 +301,43 @@ xchk_rtsummary(
 	struct xfs_scrub	*sc)
 {
 	struct xfs_mount	*mp = sc->mp;
+	struct xchk_rtsummary	*rts = sc->buf;
 	int			error = 0;
 
+	/* Is sb_rextents correct? */
+	if (mp->m_sb.sb_rextents != rts->rextents) {
+		xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
+		goto out_rbm;
+	}
+
+	/* Is m_rsumlevels correct? */
+	if (mp->m_rsumlevels != rts->rsumlevels) {
+		xchk_ino_set_corrupt(sc, mp->m_rsumip->i_ino);
+		goto out_rbm;
+	}
+
+	/* Is m_rsumsize correct? */
+	if (mp->m_rsumsize != rts->rsumsize) {
+		xchk_ino_set_corrupt(sc, mp->m_rsumip->i_ino);
+		goto out_rbm;
+	}
+
+	/* The summary file length must be aligned to an fsblock. */
+	if (mp->m_rsumip->i_disk_size & mp->m_blockmask) {
+		xchk_ino_set_corrupt(sc, mp->m_rsumip->i_ino);
+		goto out_rbm;
+	}
+
+	/*
+	 * Is the summary file itself large enough to handle the rt volume?
+	 * growfsrt expands the summary file before updating sb_rextents, so
+	 * the file can be larger than rsumsize.
+	 */
+	if (mp->m_rsumip->i_disk_size < rts->rsumsize) {
+		xchk_ino_set_corrupt(sc, mp->m_rsumip->i_ino);
+		goto out_rbm;
+	}
+
 	/* Invoke the fork scrubber. */
 	error = xchk_metadata_inode_forks(sc);
 	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 4849efcaa33a..caf324c2b991 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -14,8 +14,6 @@
 #include "xfs_inode.h"
 #include "xfs_quota.h"
 #include "xfs_qm.h"
-#include "xfs_errortag.h"
-#include "xfs_error.h"
 #include "xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
@@ -238,27 +236,31 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 	[XFS_SCRUB_TYPE_BNOBT] = {	/* bnobt */
 		.type	= ST_PERAG,
 		.setup	= xchk_setup_ag_allocbt,
-		.scrub	= xchk_bnobt,
-		.repair	= xrep_notsupported,
+		.scrub	= xchk_allocbt,
+		.repair	= xrep_allocbt,
+		.repair_eval = xrep_revalidate_allocbt,
 	},
 	[XFS_SCRUB_TYPE_CNTBT] = {	/* cntbt */
 		.type	= ST_PERAG,
 		.setup	= xchk_setup_ag_allocbt,
-		.scrub	= xchk_cntbt,
-		.repair	= xrep_notsupported,
+		.scrub	= xchk_allocbt,
+		.repair	= xrep_allocbt,
+		.repair_eval = xrep_revalidate_allocbt,
 	},
 	[XFS_SCRUB_TYPE_INOBT] = {	/* inobt */
 		.type	= ST_PERAG,
 		.setup	= xchk_setup_ag_iallocbt,
-		.scrub	= xchk_inobt,
-		.repair	= xrep_notsupported,
+		.scrub	= xchk_iallocbt,
+		.repair	= xrep_iallocbt,
+		.repair_eval = xrep_revalidate_iallocbt,
 	},
 	[XFS_SCRUB_TYPE_FINOBT] = {	/* finobt */
 		.type	= ST_PERAG,
 		.setup	= xchk_setup_ag_iallocbt,
-		.scrub	= xchk_finobt,
+		.scrub	= xchk_iallocbt,
 		.has	= xfs_has_finobt,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_iallocbt,
+		.repair_eval = xrep_revalidate_iallocbt,
 	},
 	[XFS_SCRUB_TYPE_RMAPBT] = {	/* rmapbt */
 		.type	= ST_PERAG,
@@ -272,31 +274,31 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.setup	= xchk_setup_ag_refcountbt,
 		.scrub	= xchk_refcountbt,
 		.has	= xfs_has_reflink,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_refcountbt,
 	},
 	[XFS_SCRUB_TYPE_INODE] = {	/* inode record */
 		.type	= ST_INODE,
 		.setup	= xchk_setup_inode,
 		.scrub	= xchk_inode,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_inode,
 	},
 	[XFS_SCRUB_TYPE_BMBTD] = {	/* inode data fork */
 		.type	= ST_INODE,
 		.setup	= xchk_setup_inode_bmap,
 		.scrub	= xchk_bmap_data,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_bmap_data,
 	},
 	[XFS_SCRUB_TYPE_BMBTA] = {	/* inode attr fork */
 		.type	= ST_INODE,
 		.setup	= xchk_setup_inode_bmap,
 		.scrub	= xchk_bmap_attr,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_bmap_attr,
 	},
 	[XFS_SCRUB_TYPE_BMBTC] = {	/* inode CoW fork */
 		.type	= ST_INODE,
 		.setup	= xchk_setup_inode_bmap,
 		.scrub	= xchk_bmap_cow,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_bmap_cow,
 	},
 	[XFS_SCRUB_TYPE_DIR] = {	/* directory */
 		.type	= ST_INODE,
@@ -326,33 +328,31 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.type	= ST_FS,
 		.setup	= xchk_setup_rtbitmap,
 		.scrub	= xchk_rtbitmap,
-		.has	= xfs_has_realtime,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_rtbitmap,
 	},
 	[XFS_SCRUB_TYPE_RTSUM] = {	/* realtime summary */
 		.type	= ST_FS,
 		.setup	= xchk_setup_rtsummary,
 		.scrub	= xchk_rtsummary,
-		.has	= xfs_has_realtime,
 		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_UQUOTA] = {	/* user quota */
 		.type	= ST_FS,
 		.setup	= xchk_setup_quota,
 		.scrub	= xchk_quota,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_quota,
 	},
 	[XFS_SCRUB_TYPE_GQUOTA] = {	/* group quota */
 		.type	= ST_FS,
 		.setup	= xchk_setup_quota,
 		.scrub	= xchk_quota,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_quota,
 	},
 	[XFS_SCRUB_TYPE_PQUOTA] = {	/* project quota */
 		.type	= ST_FS,
 		.setup	= xchk_setup_quota,
 		.scrub	= xchk_quota,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_quota,
 	},
 	[XFS_SCRUB_TYPE_FSCOUNTERS] = {	/* fs summary counters */
 		.type	= ST_FS,
@@ -531,7 +531,10 @@ retry_op:
 
 	/* Scrub for errors. */
 	check_start = xchk_stats_now();
-	error = sc->ops->scrub(sc);
+	if ((sc->flags & XREP_ALREADY_FIXED) && sc->ops->repair_eval != NULL)
+		error = sc->ops->repair_eval(sc);
+	else
+		error = sc->ops->scrub(sc);
 	run.scrub_ns += xchk_stats_elapsed_ns(check_start);
 	if (error == -EDEADLOCK && !(sc->flags & XCHK_TRY_HARDER))
 		goto try_harder;
@@ -542,23 +545,12 @@ retry_op:
 
 	xchk_update_health(sc);
 
-	if ((sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) &&
-	    !(sc->flags & XREP_ALREADY_FIXED)) {
-		bool needs_fix = xchk_needs_repair(sc->sm);
-
-		/* Userspace asked us to rebuild the structure regardless. */
-		if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_FORCE_REBUILD)
-			needs_fix = true;
-
-		/* Let debug users force us into the repair routines. */
-		if (XFS_TEST_ERROR(needs_fix, mp, XFS_ERRTAG_FORCE_SCRUB_REPAIR))
-			needs_fix = true;
-
+	if (xchk_could_repair(sc)) {
 		/*
 		 * If userspace asked for a repair but it wasn't necessary,
 		 * report that back to userspace.
 		 */
-		if (!needs_fix) {
+		if (!xrep_will_attempt(sc)) {
 			sc->sm->sm_flags |= XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED;
 			goto out_nofix;
 		}
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 1ef9c6b4842a..7fc50654c4fe 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -35,6 +35,14 @@ struct xchk_meta_ops {
 	/* Repair or optimize the metadata. */
 	int		(*repair)(struct xfs_scrub *);
 
+	/*
+	 * Re-scrub the metadata we repaired, in case there's extra work that
+	 * we need to do to check our repair work.  If this is NULL, we'll use
+	 * the ->scrub function pointer, assuming that the regular scrub is
+	 * sufficient.
+	 */
+	int		(*repair_eval)(struct xfs_scrub *sc);
+
 	/* Decide if we even have this piece of metadata. */
 	bool		(*has)(struct xfs_mount *);
 
@@ -113,6 +121,7 @@ struct xfs_scrub {
 #define XCHK_HAVE_FREEZE_PROT	(1U << 1)  /* do we have freeze protection? */
 #define XCHK_FSGATES_DRAIN	(1U << 2)  /* defer ops draining enabled */
 #define XCHK_NEED_DRAIN		(1U << 3)  /* scrub needs to drain defer ops */
+#define XREP_RESET_PERAG_RESV	(1U << 30) /* must reset AG space reservation */
 #define XREP_ALREADY_FIXED	(1U << 31) /* checking our repair work */
 
 /*
@@ -129,10 +138,8 @@ int xchk_superblock(struct xfs_scrub *sc);
 int xchk_agf(struct xfs_scrub *sc);
 int xchk_agfl(struct xfs_scrub *sc);
 int xchk_agi(struct xfs_scrub *sc);
-int xchk_bnobt(struct xfs_scrub *sc);
-int xchk_cntbt(struct xfs_scrub *sc);
-int xchk_inobt(struct xfs_scrub *sc);
-int xchk_finobt(struct xfs_scrub *sc);
+int xchk_allocbt(struct xfs_scrub *sc);
+int xchk_iallocbt(struct xfs_scrub *sc);
 int xchk_rmapbt(struct xfs_scrub *sc);
 int xchk_refcountbt(struct xfs_scrub *sc);
 int xchk_inode(struct xfs_scrub *sc);
diff --git a/fs/xfs/scrub/symlink.c b/fs/xfs/scrub/symlink.c
index 38708fb9a5d7..ddff86713df3 100644
--- a/fs/xfs/scrub/symlink.c
+++ b/fs/xfs/scrub/symlink.c
@@ -12,8 +12,10 @@
 #include "xfs_log_format.h"
 #include "xfs_inode.h"
 #include "xfs_symlink.h"
+#include "xfs_health.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
+#include "scrub/health.h"
 
 /* Set us up to scrub a symbolic link. */
 int
@@ -41,29 +43,37 @@ xchk_symlink(
 
 	if (!S_ISLNK(VFS_I(ip)->i_mode))
 		return -ENOENT;
+
+	if (xchk_file_looks_zapped(sc, XFS_SICK_INO_SYMLINK_ZAPPED)) {
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		return 0;
+	}
+
 	ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
 	len = ip->i_disk_size;
 
 	/* Plausible size? */
 	if (len > XFS_SYMLINK_MAXLEN || len <= 0) {
 		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
-		goto out;
+		return 0;
 	}
 
 	/* Inline symlink? */
 	if (ifp->if_format == XFS_DINODE_FMT_LOCAL) {
 		if (len > xfs_inode_data_fork_size(ip) ||
-		    len > strnlen(ifp->if_u1.if_data, xfs_inode_data_fork_size(ip)))
+		    len > strnlen(ifp->if_data, xfs_inode_data_fork_size(ip)))
 			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
-		goto out;
+		return 0;
 	}
 
 	/* Remote symlink; must read the contents. */
 	error = xfs_readlink_bmap_ilocked(sc->ip, sc->buf);
 	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
-		goto out;
+		return error;
 	if (strnlen(sc->buf, XFS_SYMLINK_MAXLEN) < len)
 		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
-out:
-	return error;
+
+	/* If a remote symlink is clean, it is clearly not zapped. */
+	xchk_mark_healthy_if_clean(sc, XFS_SICK_INO_SYMLINK_ZAPPED);
+	return 0;
 }
diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c
index 29afa4851235..d0e24ffaf754 100644
--- a/fs/xfs/scrub/trace.c
+++ b/fs/xfs/scrub/trace.c
@@ -14,9 +14,12 @@
 #include "xfs_btree.h"
 #include "xfs_ag.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_quota.h"
+#include "xfs_quota_defs.h"
 #include "scrub/scrub.h"
 #include "scrub/xfile.h"
 #include "scrub/xfarray.h"
+#include "scrub/quota.h"
 
 /* Figure out which block the btree cursor was pointing to. */
 static inline xfs_fsblock_t
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 4a8bc6f3c8f2..6bbb4e8639dc 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -19,6 +19,7 @@
 struct xfile;
 struct xfarray;
 struct xfarray_sortinfo;
+struct xchk_dqiter;
 
 /*
  * ftrace's __print_symbolic requires that all enum values be wrapped in the
@@ -106,6 +107,7 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_FSCOUNTERS);
 	{ XCHK_HAVE_FREEZE_PROT,		"nofreeze" }, \
 	{ XCHK_FSGATES_DRAIN,			"fsgates_drain" }, \
 	{ XCHK_NEED_DRAIN,			"need_drain" }, \
+	{ XREP_RESET_PERAG_RESV,		"reset_perag_resv" }, \
 	{ XREP_ALREADY_FIXED,			"already_fixed" }
 
 DECLARE_EVENT_CLASS(xchk_class,
@@ -347,6 +349,54 @@ DEFINE_EVENT(xchk_fblock_error_class, name, \
 DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xchk_fblock_error);
 DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xchk_fblock_warning);
 
+#ifdef CONFIG_XFS_QUOTA
+DECLARE_EVENT_CLASS(xchk_dqiter_class,
+	TP_PROTO(struct xchk_dqiter *cursor, uint64_t id),
+	TP_ARGS(cursor, id),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_dqtype_t, dqtype)
+		__field(xfs_ino_t, ino)
+		__field(unsigned long long, cur_id)
+		__field(unsigned long long, id)
+		__field(xfs_fileoff_t, startoff)
+		__field(xfs_fsblock_t, startblock)
+		__field(xfs_filblks_t, blockcount)
+		__field(xfs_exntst_t, state)
+	),
+	TP_fast_assign(
+		__entry->dev = cursor->sc->ip->i_mount->m_super->s_dev;
+		__entry->dqtype = cursor->dqtype;
+		__entry->ino = cursor->quota_ip->i_ino;
+		__entry->cur_id = cursor->id;
+		__entry->startoff = cursor->bmap.br_startoff;
+		__entry->startblock = cursor->bmap.br_startblock;
+		__entry->blockcount = cursor->bmap.br_blockcount;
+		__entry->state = cursor->bmap.br_state;
+		__entry->id = id;
+	),
+	TP_printk("dev %d:%d dquot type %s ino 0x%llx cursor_id 0x%llx startoff 0x%llx startblock 0x%llx blockcount 0x%llx state %u id 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __print_symbolic(__entry->dqtype, XFS_DQTYPE_STRINGS),
+		  __entry->ino,
+		  __entry->cur_id,
+		  __entry->startoff,
+		  __entry->startblock,
+		  __entry->blockcount,
+		  __entry->state,
+		  __entry->id)
+);
+
+#define DEFINE_SCRUB_DQITER_EVENT(name) \
+DEFINE_EVENT(xchk_dqiter_class, name, \
+	TP_PROTO(struct xchk_dqiter *cursor, uint64_t id), \
+	TP_ARGS(cursor, id))
+DEFINE_SCRUB_DQITER_EVENT(xchk_dquot_iter_revalidate_bmap);
+DEFINE_SCRUB_DQITER_EVENT(xchk_dquot_iter_advance_bmap);
+DEFINE_SCRUB_DQITER_EVENT(xchk_dquot_iter_advance_incore);
+DEFINE_SCRUB_DQITER_EVENT(xchk_dquot_iter);
+#endif /* CONFIG_XFS_QUOTA */
+
 TRACE_EVENT(xchk_incomplete,
 	TP_PROTO(struct xfs_scrub *sc, void *ret_ip),
 	TP_ARGS(sc, ret_ip),
@@ -1172,37 +1222,125 @@ DEFINE_EVENT(xrep_rmap_class, name, \
 		 xfs_agblock_t agbno, xfs_extlen_t len, \
 		 uint64_t owner, uint64_t offset, unsigned int flags), \
 	TP_ARGS(mp, agno, agbno, len, owner, offset, flags))
-DEFINE_REPAIR_RMAP_EVENT(xrep_alloc_extent_fn);
-DEFINE_REPAIR_RMAP_EVENT(xrep_ialloc_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xrep_ibt_walk_rmap);
 DEFINE_REPAIR_RMAP_EVENT(xrep_rmap_extent_fn);
-DEFINE_REPAIR_RMAP_EVENT(xrep_bmap_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xrep_bmap_walk_rmap);
 
-TRACE_EVENT(xrep_refcount_extent_fn,
+TRACE_EVENT(xrep_abt_found,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
-		 struct xfs_refcount_irec *irec),
-	TP_ARGS(mp, agno, irec),
+		 const struct xfs_alloc_rec_incore *rec),
+	TP_ARGS(mp, agno, rec),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
 		__field(xfs_agblock_t, startblock)
 		__field(xfs_extlen_t, blockcount)
-		__field(xfs_nlink_t, refcount)
 	),
 	TP_fast_assign(
 		__entry->dev = mp->m_super->s_dev;
 		__entry->agno = agno;
-		__entry->startblock = irec->rc_startblock;
-		__entry->blockcount = irec->rc_blockcount;
-		__entry->refcount = irec->rc_refcount;
+		__entry->startblock = rec->ar_startblock;
+		__entry->blockcount = rec->ar_blockcount;
+	),
+	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->startblock,
+		  __entry->blockcount)
+)
+
+TRACE_EVENT(xrep_ibt_found,
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+		 const struct xfs_inobt_rec_incore *rec),
+	TP_ARGS(mp, agno, rec),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agino_t, startino)
+		__field(uint16_t, holemask)
+		__field(uint8_t, count)
+		__field(uint8_t, freecount)
+		__field(uint64_t, freemask)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->agno = agno;
+		__entry->startino = rec->ir_startino;
+		__entry->holemask = rec->ir_holemask;
+		__entry->count = rec->ir_count;
+		__entry->freecount = rec->ir_freecount;
+		__entry->freemask = rec->ir_free;
+	),
+	TP_printk("dev %d:%d agno 0x%x agino 0x%x holemask 0x%x count 0x%x freecount 0x%x freemask 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->startino,
+		  __entry->holemask,
+		  __entry->count,
+		  __entry->freecount,
+		  __entry->freemask)
+)
+
+TRACE_EVENT(xrep_refc_found,
+	TP_PROTO(struct xfs_perag *pag, const struct xfs_refcount_irec *rec),
+	TP_ARGS(pag, rec),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(enum xfs_refc_domain, domain)
+		__field(xfs_agblock_t, startblock)
+		__field(xfs_extlen_t, blockcount)
+		__field(xfs_nlink_t, refcount)
+	),
+	TP_fast_assign(
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
+		__entry->domain = rec->rc_domain;
+		__entry->startblock = rec->rc_startblock;
+		__entry->blockcount = rec->rc_blockcount;
+		__entry->refcount = rec->rc_refcount;
 	),
-	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u",
+	TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
+		  __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS),
 		  __entry->startblock,
 		  __entry->blockcount,
 		  __entry->refcount)
 )
 
+TRACE_EVENT(xrep_bmap_found,
+	TP_PROTO(struct xfs_inode *ip, int whichfork,
+		 struct xfs_bmbt_irec *irec),
+	TP_ARGS(ip, whichfork, irec),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(int, whichfork)
+		__field(xfs_fileoff_t, lblk)
+		__field(xfs_filblks_t, len)
+		__field(xfs_fsblock_t, pblk)
+		__field(int, state)
+	),
+	TP_fast_assign(
+		__entry->dev = VFS_I(ip)->i_sb->s_dev;
+		__entry->ino = ip->i_ino;
+		__entry->whichfork = whichfork;
+		__entry->lblk = irec->br_startoff;
+		__entry->len = irec->br_blockcount;
+		__entry->pblk = irec->br_startblock;
+		__entry->state = irec->br_state;
+	),
+	TP_printk("dev %d:%d ino 0x%llx whichfork %s fileoff 0x%llx fsbcount 0x%llx startblock 0x%llx state %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __print_symbolic(__entry->whichfork, XFS_WHICHFORK_STRINGS),
+		  __entry->lblk,
+		  __entry->len,
+		  __entry->pblk,
+		  __entry->state)
+);
+
 TRACE_EVENT(xrep_findroot_block,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,
 		 uint32_t magic, uint16_t level),
@@ -1299,39 +1437,327 @@ TRACE_EVENT(xrep_reset_counters,
 		  MAJOR(__entry->dev), MINOR(__entry->dev))
 )
 
-TRACE_EVENT(xrep_ialloc_insert,
+DECLARE_EVENT_CLASS(xrep_newbt_extent_class,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
-		 xfs_agino_t startino, uint16_t holemask, uint8_t count,
-		 uint8_t freecount, uint64_t freemask),
-	TP_ARGS(mp, agno, startino, holemask, count, freecount, freemask),
+		 xfs_agblock_t agbno, xfs_extlen_t len,
+		 int64_t owner),
+	TP_ARGS(mp, agno, agbno, len, owner),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
-		__field(xfs_agino_t, startino)
-		__field(uint16_t, holemask)
-		__field(uint8_t, count)
-		__field(uint8_t, freecount)
-		__field(uint64_t, freemask)
+		__field(xfs_agblock_t, agbno)
+		__field(xfs_extlen_t, len)
+		__field(int64_t, owner)
 	),
 	TP_fast_assign(
 		__entry->dev = mp->m_super->s_dev;
 		__entry->agno = agno;
-		__entry->startino = startino;
-		__entry->holemask = holemask;
-		__entry->count = count;
-		__entry->freecount = freecount;
-		__entry->freemask = freemask;
+		__entry->agbno = agbno;
+		__entry->len = len;
+		__entry->owner = owner;
 	),
-	TP_printk("dev %d:%d agno 0x%x startino 0x%x holemask 0x%x count %u freecount %u freemask 0x%llx",
+	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x owner 0x%llx",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
-		  __entry->startino,
-		  __entry->holemask,
-		  __entry->count,
-		  __entry->freecount,
-		  __entry->freemask)
+		  __entry->agbno,
+		  __entry->len,
+		  __entry->owner)
+);
+#define DEFINE_NEWBT_EXTENT_EVENT(name) \
+DEFINE_EVENT(xrep_newbt_extent_class, name, \
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
+		 xfs_agblock_t agbno, xfs_extlen_t len, \
+		 int64_t owner), \
+	TP_ARGS(mp, agno, agbno, len, owner))
+DEFINE_NEWBT_EXTENT_EVENT(xrep_newbt_alloc_ag_blocks);
+DEFINE_NEWBT_EXTENT_EVENT(xrep_newbt_alloc_file_blocks);
+DEFINE_NEWBT_EXTENT_EVENT(xrep_newbt_free_blocks);
+DEFINE_NEWBT_EXTENT_EVENT(xrep_newbt_claim_block);
+
+DECLARE_EVENT_CLASS(xrep_dinode_class,
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_dinode *dip),
+	TP_ARGS(sc, dip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(uint16_t, mode)
+		__field(uint8_t, version)
+		__field(uint8_t, format)
+		__field(uint32_t, uid)
+		__field(uint32_t, gid)
+		__field(uint64_t, size)
+		__field(uint64_t, nblocks)
+		__field(uint32_t, extsize)
+		__field(uint32_t, nextents)
+		__field(uint16_t, anextents)
+		__field(uint8_t, forkoff)
+		__field(uint8_t, aformat)
+		__field(uint16_t, flags)
+		__field(uint32_t, gen)
+		__field(uint64_t, flags2)
+		__field(uint32_t, cowextsize)
+	),
+	TP_fast_assign(
+		__entry->dev = sc->mp->m_super->s_dev;
+		__entry->ino = sc->sm->sm_ino;
+		__entry->mode = be16_to_cpu(dip->di_mode);
+		__entry->version = dip->di_version;
+		__entry->format = dip->di_format;
+		__entry->uid = be32_to_cpu(dip->di_uid);
+		__entry->gid = be32_to_cpu(dip->di_gid);
+		__entry->size = be64_to_cpu(dip->di_size);
+		__entry->nblocks = be64_to_cpu(dip->di_nblocks);
+		__entry->extsize = be32_to_cpu(dip->di_extsize);
+		__entry->nextents = be32_to_cpu(dip->di_nextents);
+		__entry->anextents = be16_to_cpu(dip->di_anextents);
+		__entry->forkoff = dip->di_forkoff;
+		__entry->aformat = dip->di_aformat;
+		__entry->flags = be16_to_cpu(dip->di_flags);
+		__entry->gen = be32_to_cpu(dip->di_gen);
+		__entry->flags2 = be64_to_cpu(dip->di_flags2);
+		__entry->cowextsize = be32_to_cpu(dip->di_cowextsize);
+	),
+	TP_printk("dev %d:%d ino 0x%llx mode 0x%x version %u format %u uid %u gid %u disize 0x%llx nblocks 0x%llx extsize %u nextents %u anextents %u forkoff 0x%x aformat %u flags 0x%x gen 0x%x flags2 0x%llx cowextsize %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->mode,
+		  __entry->version,
+		  __entry->format,
+		  __entry->uid,
+		  __entry->gid,
+		  __entry->size,
+		  __entry->nblocks,
+		  __entry->extsize,
+		  __entry->nextents,
+		  __entry->anextents,
+		  __entry->forkoff,
+		  __entry->aformat,
+		  __entry->flags,
+		  __entry->gen,
+		  __entry->flags2,
+		  __entry->cowextsize)
 )
 
+#define DEFINE_REPAIR_DINODE_EVENT(name) \
+DEFINE_EVENT(xrep_dinode_class, name, \
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_dinode *dip), \
+	TP_ARGS(sc, dip))
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_header);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_mode);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_flags);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_size);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_extsize_hints);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_zap_symlink);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_zap_dir);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_fixed);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_zap_forks);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_zap_dfork);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_zap_afork);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_ensure_forkoff);
+
+DECLARE_EVENT_CLASS(xrep_inode_class,
+	TP_PROTO(struct xfs_scrub *sc),
+	TP_ARGS(sc),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(xfs_fsize_t, size)
+		__field(xfs_rfsblock_t, nblocks)
+		__field(uint16_t, flags)
+		__field(uint64_t, flags2)
+		__field(uint32_t, nextents)
+		__field(uint8_t, format)
+		__field(uint32_t, anextents)
+		__field(uint8_t, aformat)
+	),
+	TP_fast_assign(
+		__entry->dev = sc->mp->m_super->s_dev;
+		__entry->ino = sc->sm->sm_ino;
+		__entry->size = sc->ip->i_disk_size;
+		__entry->nblocks = sc->ip->i_nblocks;
+		__entry->flags = sc->ip->i_diflags;
+		__entry->flags2 = sc->ip->i_diflags2;
+		__entry->nextents = sc->ip->i_df.if_nextents;
+		__entry->format = sc->ip->i_df.if_format;
+		__entry->anextents = sc->ip->i_af.if_nextents;
+		__entry->aformat = sc->ip->i_af.if_format;
+	),
+	TP_printk("dev %d:%d ino 0x%llx disize 0x%llx nblocks 0x%llx flags 0x%x flags2 0x%llx nextents %u format %u anextents %u aformat %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->size,
+		  __entry->nblocks,
+		  __entry->flags,
+		  __entry->flags2,
+		  __entry->nextents,
+		  __entry->format,
+		  __entry->anextents,
+		  __entry->aformat)
+)
+
+#define DEFINE_REPAIR_INODE_EVENT(name) \
+DEFINE_EVENT(xrep_inode_class, name, \
+	TP_PROTO(struct xfs_scrub *sc), \
+	TP_ARGS(sc))
+DEFINE_REPAIR_INODE_EVENT(xrep_inode_blockcounts);
+DEFINE_REPAIR_INODE_EVENT(xrep_inode_ids);
+DEFINE_REPAIR_INODE_EVENT(xrep_inode_flags);
+DEFINE_REPAIR_INODE_EVENT(xrep_inode_blockdir_size);
+DEFINE_REPAIR_INODE_EVENT(xrep_inode_sfdir_size);
+DEFINE_REPAIR_INODE_EVENT(xrep_inode_dir_size);
+DEFINE_REPAIR_INODE_EVENT(xrep_inode_fixed);
+
+TRACE_EVENT(xrep_dinode_count_rmaps,
+	TP_PROTO(struct xfs_scrub *sc, xfs_rfsblock_t data_blocks,
+		xfs_rfsblock_t rt_blocks, xfs_rfsblock_t attr_blocks,
+		xfs_extnum_t data_extents, xfs_extnum_t rt_extents,
+		xfs_aextnum_t attr_extents),
+	TP_ARGS(sc, data_blocks, rt_blocks, attr_blocks, data_extents,
+		rt_extents, attr_extents),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(xfs_rfsblock_t, data_blocks)
+		__field(xfs_rfsblock_t, rt_blocks)
+		__field(xfs_rfsblock_t, attr_blocks)
+		__field(xfs_extnum_t, data_extents)
+		__field(xfs_extnum_t, rt_extents)
+		__field(xfs_aextnum_t, attr_extents)
+	),
+	TP_fast_assign(
+		__entry->dev = sc->mp->m_super->s_dev;
+		__entry->ino = sc->sm->sm_ino;
+		__entry->data_blocks = data_blocks;
+		__entry->rt_blocks = rt_blocks;
+		__entry->attr_blocks = attr_blocks;
+		__entry->data_extents = data_extents;
+		__entry->rt_extents = rt_extents;
+		__entry->attr_extents = attr_extents;
+	),
+	TP_printk("dev %d:%d ino 0x%llx dblocks 0x%llx rtblocks 0x%llx ablocks 0x%llx dextents %llu rtextents %llu aextents %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->data_blocks,
+		  __entry->rt_blocks,
+		  __entry->attr_blocks,
+		  __entry->data_extents,
+		  __entry->rt_extents,
+		  __entry->attr_extents)
+);
+
+TRACE_EVENT(xrep_cow_mark_file_range,
+	TP_PROTO(struct xfs_inode *ip, xfs_fsblock_t startblock,
+		 xfs_fileoff_t startoff, xfs_filblks_t blockcount),
+	TP_ARGS(ip, startblock, startoff, blockcount),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(xfs_fsblock_t, startblock)
+		__field(xfs_fileoff_t, startoff)
+		__field(xfs_filblks_t, blockcount)
+	),
+	TP_fast_assign(
+		__entry->dev = ip->i_mount->m_super->s_dev;
+		__entry->ino = ip->i_ino;
+		__entry->startoff = startoff;
+		__entry->startblock = startblock;
+		__entry->blockcount = blockcount;
+	),
+	TP_printk("dev %d:%d ino 0x%llx fileoff 0x%llx startblock 0x%llx fsbcount 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->startoff,
+		  __entry->startblock,
+		  __entry->blockcount)
+);
+
+TRACE_EVENT(xrep_cow_replace_mapping,
+	TP_PROTO(struct xfs_inode *ip, const struct xfs_bmbt_irec *irec,
+		 xfs_fsblock_t new_startblock, xfs_extlen_t new_blockcount),
+	TP_ARGS(ip, irec, new_startblock, new_blockcount),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(xfs_fsblock_t, startblock)
+		__field(xfs_fileoff_t, startoff)
+		__field(xfs_filblks_t, blockcount)
+		__field(xfs_exntst_t, state)
+		__field(xfs_fsblock_t, new_startblock)
+		__field(xfs_extlen_t, new_blockcount)
+	),
+	TP_fast_assign(
+		__entry->dev = ip->i_mount->m_super->s_dev;
+		__entry->ino = ip->i_ino;
+		__entry->startoff = irec->br_startoff;
+		__entry->startblock = irec->br_startblock;
+		__entry->blockcount = irec->br_blockcount;
+		__entry->state = irec->br_state;
+		__entry->new_startblock = new_startblock;
+		__entry->new_blockcount = new_blockcount;
+	),
+	TP_printk("dev %d:%d ino 0x%llx startoff 0x%llx startblock 0x%llx fsbcount 0x%llx state 0x%x new_startblock 0x%llx new_fsbcount 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->startoff,
+		  __entry->startblock,
+		  __entry->blockcount,
+		  __entry->state,
+		  __entry->new_startblock,
+		  __entry->new_blockcount)
+);
+
+TRACE_EVENT(xrep_cow_free_staging,
+	TP_PROTO(struct xfs_perag *pag, xfs_agblock_t agbno,
+		 xfs_extlen_t blockcount),
+	TP_ARGS(pag, agbno, blockcount),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agblock_t, agbno)
+		__field(xfs_extlen_t, blockcount)
+	),
+	TP_fast_assign(
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
+		__entry->agbno = agbno;
+		__entry->blockcount = blockcount;
+	),
+	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->agbno,
+		  __entry->blockcount)
+);
+
+#ifdef CONFIG_XFS_QUOTA
+DECLARE_EVENT_CLASS(xrep_dquot_class,
+	TP_PROTO(struct xfs_mount *mp, uint8_t type, uint32_t id),
+	TP_ARGS(mp, type, id),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(uint8_t, type)
+		__field(uint32_t, id)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->id = id;
+		__entry->type = type;
+	),
+	TP_printk("dev %d:%d type %s id 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __print_flags(__entry->type, "|", XFS_DQTYPE_STRINGS),
+		  __entry->id)
+);
+
+#define DEFINE_XREP_DQUOT_EVENT(name) \
+DEFINE_EVENT(xrep_dquot_class, name, \
+	TP_PROTO(struct xfs_mount *mp, uint8_t type, uint32_t id), \
+	TP_ARGS(mp, type, id))
+DEFINE_XREP_DQUOT_EVENT(xrep_dquot_item);
+DEFINE_XREP_DQUOT_EVENT(xrep_disk_dquot);
+DEFINE_XREP_DQUOT_EVENT(xrep_dquot_item_fill_bmap_hole);
+#endif /* CONFIG_XFS_QUOTA */
+
 #endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
 
 #endif /* _TRACE_XFS_SCRUB_TRACE_H */
diff --git a/fs/xfs/scrub/xfarray.h b/fs/xfs/scrub/xfarray.h
index 4ecac01363d9..62b9c506fdd1 100644
--- a/fs/xfs/scrub/xfarray.h
+++ b/fs/xfs/scrub/xfarray.h
@@ -54,6 +54,28 @@ static inline int xfarray_append(struct xfarray *array, const void *ptr)
 uint64_t xfarray_length(struct xfarray *array);
 int xfarray_load_next(struct xfarray *array, xfarray_idx_t *idx, void *rec);
 
+/*
+ * Iterate the non-null elements in a sparse xfarray.  Callers should
+ * initialize *idx to XFARRAY_CURSOR_INIT before the first call; on return, it
+ * will be set to one more than the index of the record that was retrieved.
+ * Returns 1 if a record was retrieved, 0 if there weren't any more records, or
+ * a negative errno.
+ */
+static inline int
+xfarray_iter(
+	struct xfarray	*array,
+	xfarray_idx_t	*idx,
+	void		*rec)
+{
+	int ret = xfarray_load_next(array, idx, rec);
+
+	if (ret == -ENODATA)
+		return 0;
+	if (ret == 0)
+		return 1;
+	return ret;
+}
+
 /* Declarations for xfile array sort functionality. */
 
 typedef cmp_func_t xfarray_cmp_fn;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 465d7630bb21..813f85156b0c 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -584,7 +584,7 @@ const struct address_space_operations xfs_address_space_operations = {
 	.bmap			= xfs_vm_bmap,
 	.migrate_folio		= filemap_migrate_folio,
 	.is_partially_uptodate  = iomap_is_partially_uptodate,
-	.error_remove_page	= generic_error_remove_page,
+	.error_remove_folio	= generic_error_remove_folio,
 	.swap_activate		= xfs_iomap_swapfile_activate,
 };
 
diff --git a/fs/xfs/xfs_attr_item.c b/fs/xfs/xfs_attr_item.c
index 36fe2abb16e6..9e02111bd890 100644
--- a/fs/xfs/xfs_attr_item.c
+++ b/fs/xfs/xfs_attr_item.c
@@ -33,8 +33,6 @@ struct kmem_cache		*xfs_attrd_cache;
 
 static const struct xfs_item_ops xfs_attri_item_ops;
 static const struct xfs_item_ops xfs_attrd_item_ops;
-static struct xfs_attrd_log_item *xfs_trans_get_attrd(struct xfs_trans *tp,
-					struct xfs_attri_log_item *attrip);
 
 static inline struct xfs_attri_log_item *ATTRI_ITEM(struct xfs_log_item *lip)
 {
@@ -310,47 +308,6 @@ xfs_attrd_item_intent(
 	return &ATTRD_ITEM(lip)->attrd_attrip->attri_item;
 }
 
-/*
- * Performs one step of an attribute update intent and marks the attrd item
- * dirty..  An attr operation may be a set or a remove.  Note that the
- * transaction is marked dirty regardless of whether the operation succeeds or
- * fails to support the ATTRI/ATTRD lifecycle rules.
- */
-STATIC int
-xfs_xattri_finish_update(
-	struct xfs_attr_intent		*attr,
-	struct xfs_attrd_log_item	*attrdp)
-{
-	struct xfs_da_args		*args = attr->xattri_da_args;
-	int				error;
-
-	if (XFS_TEST_ERROR(false, args->dp->i_mount, XFS_ERRTAG_LARP)) {
-		error = -EIO;
-		goto out;
-	}
-
-	error = xfs_attr_set_iter(attr);
-	if (!error && attr->xattri_dela_state != XFS_DAS_DONE)
-		error = -EAGAIN;
-out:
-	/*
-	 * Mark the transaction dirty, even on error. This ensures the
-	 * transaction is aborted, which:
-	 *
-	 * 1.) releases the ATTRI and frees the ATTRD
-	 * 2.) shuts down the filesystem
-	 */
-	args->trans->t_flags |= XFS_TRANS_DIRTY | XFS_TRANS_HAS_INTENT_DONE;
-
-	/*
-	 * attr intent/done items are null when logged attributes are disabled
-	 */
-	if (attrdp)
-		set_bit(XFS_LI_DIRTY, &attrdp->attrd_item.li_flags);
-
-	return error;
-}
-
 /* Log an attr to the intent item. */
 STATIC void
 xfs_attr_log_item(
@@ -360,9 +317,6 @@ xfs_attr_log_item(
 {
 	struct xfs_attri_log_format	*attrp;
 
-	tp->t_flags |= XFS_TRANS_DIRTY;
-	set_bit(XFS_LI_DIRTY, &attrip->attri_item.li_flags);
-
 	/*
 	 * At this point the xfs_attr_intent has been constructed, and we've
 	 * created the log intent. Fill in the attri log item and log format
@@ -419,7 +373,6 @@ xfs_attr_create_intent(
 	}
 
 	attrip = xfs_attri_init(mp, attr->xattri_nameval);
-	xfs_trans_add_item(tp, &attrip->attri_item);
 	xfs_attr_log_item(tp, attrip, attr);
 
 	return &attrip->attri_item;
@@ -447,23 +400,33 @@ xfs_attr_finish_item(
 	struct xfs_btree_cur		**state)
 {
 	struct xfs_attr_intent		*attr;
-	struct xfs_attrd_log_item	*done_item = NULL;
+	struct xfs_da_args		*args;
 	int				error;
 
 	attr = container_of(item, struct xfs_attr_intent, xattri_list);
-	if (done)
-		done_item = ATTRD_ITEM(done);
+	args = attr->xattri_da_args;
 
-	/*
-	 * Always reset trans after EAGAIN cycle
-	 * since the transaction is new
-	 */
-	attr->xattri_da_args->trans = tp;
+	/* Reset trans after EAGAIN cycle since the transaction is new */
+	args->trans = tp;
 
-	error = xfs_xattri_finish_update(attr, done_item);
-	if (error != -EAGAIN)
-		xfs_attr_free_item(attr);
+	if (XFS_TEST_ERROR(false, args->dp->i_mount, XFS_ERRTAG_LARP)) {
+		error = -EIO;
+		goto out;
+	}
 
+	/* If an attr removal is trivially complete, we're done. */
+	if (attr->xattri_op_flags == XFS_ATTRI_OP_FLAGS_REMOVE &&
+	    !xfs_inode_hasattr(args->dp)) {
+		error = 0;
+		goto out;
+	}
+
+	error = xfs_attr_set_iter(attr);
+	if (!error && attr->xattri_dela_state != XFS_DAS_DONE)
+		return -EAGAIN;
+
+out:
+	xfs_attr_free_item(attr);
 	return error;
 }
 
@@ -532,41 +495,22 @@ xfs_attri_validate(
 	return xfs_verify_ino(mp, attrp->alfi_ino);
 }
 
-/*
- * Process an attr intent item that was recovered from the log.  We need to
- * delete the attr that it describes.
- */
-STATIC int
-xfs_attri_item_recover(
-	struct xfs_log_item		*lip,
-	struct list_head		*capture_list)
+static inline struct xfs_attr_intent *
+xfs_attri_recover_work(
+	struct xfs_mount		*mp,
+	struct xfs_defer_pending	*dfp,
+	struct xfs_attri_log_format	*attrp,
+	struct xfs_inode		**ipp,
+	struct xfs_attri_log_nameval	*nv)
 {
-	struct xfs_attri_log_item	*attrip = ATTRI_ITEM(lip);
 	struct xfs_attr_intent		*attr;
-	struct xfs_mount		*mp = lip->li_log->l_mp;
-	struct xfs_inode		*ip;
 	struct xfs_da_args		*args;
-	struct xfs_trans		*tp;
-	struct xfs_trans_res		resv;
-	struct xfs_attri_log_format	*attrp;
-	struct xfs_attri_log_nameval	*nv = attrip->attri_nameval;
-	int				error;
-	int				total;
 	int				local;
-	struct xfs_attrd_log_item	*done_item = NULL;
-
-	/*
-	 * First check the validity of the attr described by the ATTRI.  If any
-	 * are bad, then assume that all are bad and just toss the ATTRI.
-	 */
-	attrp = &attrip->attri_format;
-	if (!xfs_attri_validate(mp, attrp) ||
-	    !xfs_attr_namecheck(nv->name.i_addr, nv->name.i_len))
-		return -EFSCORRUPTED;
+	int				error;
 
-	error = xlog_recover_iget(mp,  attrp->alfi_ino, &ip);
+	error = xlog_recover_iget(mp,  attrp->alfi_ino, ipp);
 	if (error)
-		return error;
+		return ERR_PTR(error);
 
 	attr = kmem_zalloc(sizeof(struct xfs_attr_intent) +
 			   sizeof(struct xfs_da_args), KM_NOFS);
@@ -584,7 +528,7 @@ xfs_attri_item_recover(
 	attr->xattri_nameval = xfs_attri_log_nameval_get(nv);
 	ASSERT(attr->xattri_nameval);
 
-	args->dp = ip;
+	args->dp = *ipp;
 	args->geo = mp->m_attr_geo;
 	args->whichfork = XFS_ATTR_FORK;
 	args->name = nv->name.i_addr;
@@ -608,43 +552,65 @@ xfs_attri_item_recover(
 			attr->xattri_dela_state = xfs_attr_init_add_state(args);
 		break;
 	case XFS_ATTRI_OP_FLAGS_REMOVE:
-		if (!xfs_inode_hasattr(args->dp))
-			goto out;
 		attr->xattri_dela_state = xfs_attr_init_remove_state(args);
 		break;
-	default:
-		ASSERT(0);
-		error = -EFSCORRUPTED;
-		goto out;
 	}
 
+	xfs_defer_add_item(dfp, &attr->xattri_list);
+	return attr;
+}
+
+/*
+ * Process an attr intent item that was recovered from the log.  We need to
+ * delete the attr that it describes.
+ */
+STATIC int
+xfs_attr_recover_work(
+	struct xfs_defer_pending	*dfp,
+	struct list_head		*capture_list)
+{
+	struct xfs_log_item		*lip = dfp->dfp_intent;
+	struct xfs_attri_log_item	*attrip = ATTRI_ITEM(lip);
+	struct xfs_attr_intent		*attr;
+	struct xfs_mount		*mp = lip->li_log->l_mp;
+	struct xfs_inode		*ip;
+	struct xfs_da_args		*args;
+	struct xfs_trans		*tp;
+	struct xfs_trans_res		resv;
+	struct xfs_attri_log_format	*attrp;
+	struct xfs_attri_log_nameval	*nv = attrip->attri_nameval;
+	int				error;
+	int				total;
+
+	/*
+	 * First check the validity of the attr described by the ATTRI.  If any
+	 * are bad, then assume that all are bad and just toss the ATTRI.
+	 */
+	attrp = &attrip->attri_format;
+	if (!xfs_attri_validate(mp, attrp) ||
+	    !xfs_attr_namecheck(nv->name.i_addr, nv->name.i_len))
+		return -EFSCORRUPTED;
+
+	attr = xfs_attri_recover_work(mp, dfp, attrp, &ip, nv);
+	if (IS_ERR(attr))
+		return PTR_ERR(attr);
+	args = attr->xattri_da_args;
+
 	xfs_init_attr_trans(args, &resv, &total);
 	resv = xlog_recover_resv(&resv);
 	error = xfs_trans_alloc(mp, &resv, total, 0, XFS_TRANS_RESERVE, &tp);
 	if (error)
-		goto out;
-
+		return error;
 	args->trans = tp;
-	done_item = xfs_trans_get_attrd(tp, attrip);
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
-	error = xfs_xattri_finish_update(attr, done_item);
-	if (error == -EAGAIN) {
-		/*
-		 * There's more work to do, so add the intent item to this
-		 * transaction so that we can continue it later.
-		 */
-		xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_ATTR, &attr->xattri_list);
-		error = xfs_defer_ops_capture_and_commit(tp, capture_list);
-		if (error)
-			goto out_unlock;
-
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		xfs_irele(ip);
-		return 0;
-	}
+	error = xlog_recover_finish_intent(tp, dfp);
+	if (error == -EFSCORRUPTED)
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				&attrip->attri_format,
+				sizeof(attrip->attri_format));
 	if (error) {
 		xfs_trans_cancel(tp);
 		goto out_unlock;
@@ -654,18 +620,16 @@ xfs_attri_item_recover(
 out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	xfs_irele(ip);
-out:
-	xfs_attr_free_item(attr);
 	return error;
 }
 
 /* Re-log an intent item to push the log tail forward. */
 static struct xfs_log_item *
-xfs_attri_item_relog(
+xfs_attr_relog_intent(
+	struct xfs_trans		*tp,
 	struct xfs_log_item		*intent,
-	struct xfs_trans		*tp)
+	struct xfs_log_item		*done_item)
 {
-	struct xfs_attrd_log_item	*attrdp;
 	struct xfs_attri_log_item	*old_attrip;
 	struct xfs_attri_log_item	*new_attrip;
 	struct xfs_attri_log_format	*new_attrp;
@@ -674,10 +638,6 @@ xfs_attri_item_relog(
 	old_attrip = ATTRI_ITEM(intent);
 	old_attrp = &old_attrip->attri_format;
 
-	tp->t_flags |= XFS_TRANS_DIRTY;
-	attrdp = xfs_trans_get_attrd(tp, old_attrip);
-	set_bit(XFS_LI_DIRTY, &attrdp->attrd_item.li_flags);
-
 	/*
 	 * Create a new log item that shares the same name/value buffer as the
 	 * old log item.
@@ -691,12 +651,43 @@ xfs_attri_item_relog(
 	new_attrp->alfi_name_len = old_attrp->alfi_name_len;
 	new_attrp->alfi_attr_filter = old_attrp->alfi_attr_filter;
 
-	xfs_trans_add_item(tp, &new_attrip->attri_item);
-	set_bit(XFS_LI_DIRTY, &new_attrip->attri_item.li_flags);
-
 	return &new_attrip->attri_item;
 }
 
+/* Get an ATTRD so we can process all the attrs. */
+static struct xfs_log_item *
+xfs_attr_create_done(
+	struct xfs_trans		*tp,
+	struct xfs_log_item		*intent,
+	unsigned int			count)
+{
+	struct xfs_attri_log_item	*attrip;
+	struct xfs_attrd_log_item	*attrdp;
+
+	attrip = ATTRI_ITEM(intent);
+
+	attrdp = kmem_cache_zalloc(xfs_attrd_cache, GFP_NOFS | __GFP_NOFAIL);
+
+	xfs_log_item_init(tp->t_mountp, &attrdp->attrd_item, XFS_LI_ATTRD,
+			  &xfs_attrd_item_ops);
+	attrdp->attrd_attrip = attrip;
+	attrdp->attrd_format.alfd_alf_id = attrip->attri_format.alfi_id;
+
+	return &attrdp->attrd_item;
+}
+
+const struct xfs_defer_op_type xfs_attr_defer_type = {
+	.name		= "attr",
+	.max_items	= 1,
+	.create_intent	= xfs_attr_create_intent,
+	.abort_intent	= xfs_attr_abort_intent,
+	.create_done	= xfs_attr_create_done,
+	.finish_item	= xfs_attr_finish_item,
+	.cancel_item	= xfs_attr_cancel_item,
+	.recover_work	= xfs_attr_recover_work,
+	.relog_intent	= xfs_attr_relog_intent,
+};
+
 STATIC int
 xlog_recover_attri_commit_pass2(
 	struct xlog                     *log,
@@ -767,63 +758,13 @@ xlog_recover_attri_commit_pass2(
 	attrip = xfs_attri_init(mp, nv);
 	memcpy(&attrip->attri_format, attri_formatp, len);
 
-	/*
-	 * The ATTRI has two references. One for the ATTRD and one for ATTRI to
-	 * ensure it makes it into the AIL. Insert the ATTRI into the AIL
-	 * directly and drop the ATTRI reference. Note that
-	 * xfs_trans_ail_update() drops the AIL lock.
-	 */
-	xfs_trans_ail_insert(log->l_ailp, &attrip->attri_item, lsn);
-	xfs_attri_release(attrip);
+	xlog_recover_intent_item(log, &attrip->attri_item, lsn,
+			&xfs_attr_defer_type);
 	xfs_attri_log_nameval_put(nv);
 	return 0;
 }
 
 /*
- * This routine is called to allocate an "attr free done" log item.
- */
-static struct xfs_attrd_log_item *
-xfs_trans_get_attrd(struct xfs_trans		*tp,
-		  struct xfs_attri_log_item	*attrip)
-{
-	struct xfs_attrd_log_item		*attrdp;
-
-	ASSERT(tp != NULL);
-
-	attrdp = kmem_cache_zalloc(xfs_attrd_cache, GFP_NOFS | __GFP_NOFAIL);
-
-	xfs_log_item_init(tp->t_mountp, &attrdp->attrd_item, XFS_LI_ATTRD,
-			  &xfs_attrd_item_ops);
-	attrdp->attrd_attrip = attrip;
-	attrdp->attrd_format.alfd_alf_id = attrip->attri_format.alfi_id;
-
-	xfs_trans_add_item(tp, &attrdp->attrd_item);
-	return attrdp;
-}
-
-/* Get an ATTRD so we can process all the attrs. */
-static struct xfs_log_item *
-xfs_attr_create_done(
-	struct xfs_trans		*tp,
-	struct xfs_log_item		*intent,
-	unsigned int			count)
-{
-	if (!intent)
-		return NULL;
-
-	return &xfs_trans_get_attrd(tp, ATTRI_ITEM(intent))->attrd_item;
-}
-
-const struct xfs_defer_op_type xfs_attr_defer_type = {
-	.max_items	= 1,
-	.create_intent	= xfs_attr_create_intent,
-	.abort_intent	= xfs_attr_abort_intent,
-	.create_done	= xfs_attr_create_done,
-	.finish_item	= xfs_attr_finish_item,
-	.cancel_item	= xfs_attr_cancel_item,
-};
-
-/*
  * This routine is called when an ATTRD format structure is found in a committed
  * transaction in the log. Its purpose is to cancel the corresponding ATTRI if
  * it was still in the log. To do this it searches the AIL for the ATTRI with
@@ -857,9 +798,7 @@ static const struct xfs_item_ops xfs_attri_item_ops = {
 	.iop_format	= xfs_attri_item_format,
 	.iop_unpin	= xfs_attri_item_unpin,
 	.iop_release    = xfs_attri_item_release,
-	.iop_recover	= xfs_attri_item_recover,
 	.iop_match	= xfs_attri_item_match,
-	.iop_relog	= xfs_attri_item_relog,
 };
 
 const struct xlog_recover_item_ops xlog_attri_item_ops = {
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 99bbbe1a0e44..e368ad671e26 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -56,14 +56,13 @@ xfs_attr_shortform_list(
 	struct xfs_attrlist_cursor_kern	*cursor = &context->cursor;
 	struct xfs_inode		*dp = context->dp;
 	struct xfs_attr_sf_sort		*sbuf, *sbp;
-	struct xfs_attr_shortform	*sf;
+	struct xfs_attr_sf_hdr		*sf = dp->i_af.if_data;
 	struct xfs_attr_sf_entry	*sfe;
 	int				sbsize, nsbuf, count, i;
 	int				error = 0;
 
-	sf = (struct xfs_attr_shortform *)dp->i_af.if_u1.if_data;
 	ASSERT(sf != NULL);
-	if (!sf->hdr.count)
+	if (!sf->count)
 		return 0;
 
 	trace_xfs_attr_list_sf(context);
@@ -79,8 +78,8 @@ xfs_attr_shortform_list(
 	 */
 	if (context->bufsize == 0 ||
 	    (XFS_ISRESET_CURSOR(cursor) &&
-	     (dp->i_af.if_bytes + sf->hdr.count * 16) < context->bufsize)) {
-		for (i = 0, sfe = &sf->list[0]; i < sf->hdr.count; i++) {
+	     (dp->i_af.if_bytes + sf->count * 16) < context->bufsize)) {
+		for (i = 0, sfe = xfs_attr_sf_firstentry(sf); i < sf->count; i++) {
 			if (XFS_IS_CORRUPT(context->dp->i_mount,
 					   !xfs_attr_namecheck(sfe->nameval,
 							       sfe->namelen)))
@@ -109,7 +108,7 @@ xfs_attr_shortform_list(
 	/*
 	 * It didn't all fit, so we have to sort everything on hashval.
 	 */
-	sbsize = sf->hdr.count * sizeof(*sbuf);
+	sbsize = sf->count * sizeof(*sbuf);
 	sbp = sbuf = kmem_alloc(sbsize, KM_NOFS);
 
 	/*
@@ -117,7 +116,7 @@ xfs_attr_shortform_list(
 	 * the relevant info from only those that match into a buffer.
 	 */
 	nsbuf = 0;
-	for (i = 0, sfe = &sf->list[0]; i < sf->hdr.count; i++) {
+	for (i = 0, sfe = xfs_attr_sf_firstentry(sf); i < sf->count; i++) {
 		if (unlikely(
 		    ((char *)sfe < (char *)sf) ||
 		    ((char *)sfe >= ((char *)sf + dp->i_af.if_bytes)))) {
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index e736a0844c89..52fb8a148b7d 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -221,51 +221,6 @@ static const struct xfs_item_ops xfs_bud_item_ops = {
 	.iop_intent	= xfs_bud_item_intent,
 };
 
-static struct xfs_bud_log_item *
-xfs_trans_get_bud(
-	struct xfs_trans		*tp,
-	struct xfs_bui_log_item		*buip)
-{
-	struct xfs_bud_log_item		*budp;
-
-	budp = kmem_cache_zalloc(xfs_bud_cache, GFP_KERNEL | __GFP_NOFAIL);
-	xfs_log_item_init(tp->t_mountp, &budp->bud_item, XFS_LI_BUD,
-			  &xfs_bud_item_ops);
-	budp->bud_buip = buip;
-	budp->bud_format.bud_bui_id = buip->bui_format.bui_id;
-
-	xfs_trans_add_item(tp, &budp->bud_item);
-	return budp;
-}
-
-/*
- * Finish an bmap update and log it to the BUD. Note that the
- * transaction is marked dirty regardless of whether the bmap update
- * succeeds or fails to support the BUI/BUD lifecycle rules.
- */
-static int
-xfs_trans_log_finish_bmap_update(
-	struct xfs_trans		*tp,
-	struct xfs_bud_log_item		*budp,
-	struct xfs_bmap_intent		*bi)
-{
-	int				error;
-
-	error = xfs_bmap_finish_one(tp, bi);
-
-	/*
-	 * Mark the transaction dirty, even on error. This ensures the
-	 * transaction is aborted, which:
-	 *
-	 * 1.) releases the BUI and frees the BUD
-	 * 2.) shuts down the filesystem
-	 */
-	tp->t_flags |= XFS_TRANS_DIRTY | XFS_TRANS_HAS_INTENT_DONE;
-	set_bit(XFS_LI_DIRTY, &budp->bud_item.li_flags);
-
-	return error;
-}
-
 /* Sort bmap intents by inode. */
 static int
 xfs_bmap_update_diff_items(
@@ -314,9 +269,6 @@ xfs_bmap_update_log_item(
 	uint				next_extent;
 	struct xfs_map_extent		*map;
 
-	tp->t_flags |= XFS_TRANS_DIRTY;
-	set_bit(XFS_LI_DIRTY, &buip->bui_item.li_flags);
-
 	/*
 	 * atomic_inc_return gives us the value after the increment;
 	 * we want to use it as an array index so we need to subtract 1 from
@@ -346,7 +298,6 @@ xfs_bmap_update_create_intent(
 
 	ASSERT(count == XFS_BUI_MAX_FAST_EXTENTS);
 
-	xfs_trans_add_item(tp, &buip->bui_item);
 	if (sort)
 		list_sort(mp, items, xfs_bmap_update_diff_items);
 	list_for_each_entry(bi, items, bi_list)
@@ -354,14 +305,23 @@ xfs_bmap_update_create_intent(
 	return &buip->bui_item;
 }
 
-/* Get an BUD so we can process all the deferred rmap updates. */
+/* Get an BUD so we can process all the deferred bmap updates. */
 static struct xfs_log_item *
 xfs_bmap_update_create_done(
 	struct xfs_trans		*tp,
 	struct xfs_log_item		*intent,
 	unsigned int			count)
 {
-	return &xfs_trans_get_bud(tp, BUI_ITEM(intent))->bud_item;
+	struct xfs_bui_log_item		*buip = BUI_ITEM(intent);
+	struct xfs_bud_log_item		*budp;
+
+	budp = kmem_cache_zalloc(xfs_bud_cache, GFP_KERNEL | __GFP_NOFAIL);
+	xfs_log_item_init(tp->t_mountp, &budp->bud_item, XFS_LI_BUD,
+			  &xfs_bud_item_ops);
+	budp->bud_buip = buip;
+	budp->bud_format.bud_bui_id = buip->bui_format.bui_id;
+
+	return &budp->bud_item;
 }
 
 /* Take a passive ref to the AG containing the space we're mapping. */
@@ -392,7 +352,7 @@ xfs_bmap_update_put_group(
 	xfs_perag_intent_put(bi->bi_pag);
 }
 
-/* Process a deferred rmap update. */
+/* Process a deferred bmap update. */
 STATIC int
 xfs_bmap_update_finish_item(
 	struct xfs_trans		*tp,
@@ -405,7 +365,7 @@ xfs_bmap_update_finish_item(
 
 	bi = container_of(item, struct xfs_bmap_intent, bi_list);
 
-	error = xfs_trans_log_finish_bmap_update(tp, BUD_ITEM(done), bi);
+	error = xfs_bmap_finish_one(tp, bi);
 	if (!error && bi->bi_bmap.br_blockcount > 0) {
 		ASSERT(bi->bi_type == XFS_BMAP_UNMAP);
 		return -EAGAIN;
@@ -437,15 +397,6 @@ xfs_bmap_update_cancel_item(
 	kmem_cache_free(xfs_bmap_intent_cache, bi);
 }
 
-const struct xfs_defer_op_type xfs_bmap_update_defer_type = {
-	.max_items	= XFS_BUI_MAX_FAST_EXTENTS,
-	.create_intent	= xfs_bmap_update_create_intent,
-	.abort_intent	= xfs_bmap_update_abort_intent,
-	.create_done	= xfs_bmap_update_create_done,
-	.finish_item	= xfs_bmap_update_finish_item,
-	.cancel_item	= xfs_bmap_update_cancel_item,
-};
-
 /* Is this recovered BUI ok? */
 static inline bool
 xfs_bui_validate(
@@ -480,23 +431,53 @@ xfs_bui_validate(
 	return xfs_verify_fsbext(mp, map->me_startblock, map->me_len);
 }
 
+static inline struct xfs_bmap_intent *
+xfs_bui_recover_work(
+	struct xfs_mount		*mp,
+	struct xfs_defer_pending	*dfp,
+	struct xfs_inode		**ipp,
+	struct xfs_map_extent		*map)
+{
+	struct xfs_bmap_intent		*bi;
+	int				error;
+
+	error = xlog_recover_iget(mp, map->me_owner, ipp);
+	if (error)
+		return ERR_PTR(error);
+
+	bi = kmem_cache_zalloc(xfs_bmap_intent_cache, GFP_NOFS | __GFP_NOFAIL);
+	bi->bi_whichfork = (map->me_flags & XFS_BMAP_EXTENT_ATTR_FORK) ?
+			XFS_ATTR_FORK : XFS_DATA_FORK;
+	bi->bi_type = map->me_flags & XFS_BMAP_EXTENT_TYPE_MASK;
+	bi->bi_bmap.br_startblock = map->me_startblock;
+	bi->bi_bmap.br_startoff = map->me_startoff;
+	bi->bi_bmap.br_blockcount = map->me_len;
+	bi->bi_bmap.br_state = (map->me_flags & XFS_BMAP_EXTENT_UNWRITTEN) ?
+			XFS_EXT_UNWRITTEN : XFS_EXT_NORM;
+	bi->bi_owner = *ipp;
+	xfs_bmap_update_get_group(mp, bi);
+
+	xfs_defer_add_item(dfp, &bi->bi_list);
+	return bi;
+}
+
 /*
  * Process a bmap update intent item that was recovered from the log.
  * We need to update some inode's bmbt.
  */
 STATIC int
-xfs_bui_item_recover(
-	struct xfs_log_item		*lip,
+xfs_bmap_recover_work(
+	struct xfs_defer_pending	*dfp,
 	struct list_head		*capture_list)
 {
-	struct xfs_bmap_intent		fake = { };
 	struct xfs_trans_res		resv;
+	struct xfs_log_item		*lip = dfp->dfp_intent;
 	struct xfs_bui_log_item		*buip = BUI_ITEM(lip);
 	struct xfs_trans		*tp;
 	struct xfs_inode		*ip = NULL;
 	struct xfs_mount		*mp = lip->li_log->l_mp;
 	struct xfs_map_extent		*map;
-	struct xfs_bud_log_item		*budp;
+	struct xfs_bmap_intent		*work;
 	int				iext_delta;
 	int				error = 0;
 
@@ -507,13 +488,9 @@ xfs_bui_item_recover(
 	}
 
 	map = &buip->bui_format.bui_extents[0];
-	fake.bi_whichfork = (map->me_flags & XFS_BMAP_EXTENT_ATTR_FORK) ?
-			XFS_ATTR_FORK : XFS_DATA_FORK;
-	fake.bi_type = map->me_flags & XFS_BMAP_EXTENT_TYPE_MASK;
-
-	error = xlog_recover_iget(mp, map->me_owner, &ip);
-	if (error)
-		return error;
+	work = xfs_bui_recover_work(mp, dfp, &ip, map);
+	if (IS_ERR(work))
+		return PTR_ERR(work);
 
 	/* Allocate transaction and do the work. */
 	resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate);
@@ -522,42 +499,27 @@ xfs_bui_item_recover(
 	if (error)
 		goto err_rele;
 
-	budp = xfs_trans_get_bud(tp, buip);
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
-	if (fake.bi_type == XFS_BMAP_MAP)
+	if (work->bi_type == XFS_BMAP_MAP)
 		iext_delta = XFS_IEXT_ADD_NOSPLIT_CNT;
 	else
 		iext_delta = XFS_IEXT_PUNCH_HOLE_CNT;
 
-	error = xfs_iext_count_may_overflow(ip, fake.bi_whichfork, iext_delta);
+	error = xfs_iext_count_may_overflow(ip, work->bi_whichfork, iext_delta);
 	if (error == -EFBIG)
 		error = xfs_iext_count_upgrade(tp, ip, iext_delta);
 	if (error)
 		goto err_cancel;
 
-	fake.bi_owner = ip;
-	fake.bi_bmap.br_startblock = map->me_startblock;
-	fake.bi_bmap.br_startoff = map->me_startoff;
-	fake.bi_bmap.br_blockcount = map->me_len;
-	fake.bi_bmap.br_state = (map->me_flags & XFS_BMAP_EXTENT_UNWRITTEN) ?
-			XFS_EXT_UNWRITTEN : XFS_EXT_NORM;
-
-	xfs_bmap_update_get_group(mp, &fake);
-	error = xfs_trans_log_finish_bmap_update(tp, budp, &fake);
+	error = xlog_recover_finish_intent(tp, dfp);
 	if (error == -EFSCORRUPTED)
-		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, map,
-				sizeof(*map));
-	xfs_bmap_update_put_group(&fake);
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				&buip->bui_format, sizeof(buip->bui_format));
 	if (error)
 		goto err_cancel;
 
-	if (fake.bi_bmap.br_blockcount > 0) {
-		ASSERT(fake.bi_type == XFS_BMAP_UNMAP);
-		xfs_bmap_unmap_extent(tp, ip, &fake.bi_bmap);
-	}
-
 	/*
 	 * Commit transaction, which frees the transaction and saves the inode
 	 * for later replay activities.
@@ -579,21 +541,13 @@ err_rele:
 	return error;
 }
 
-STATIC bool
-xfs_bui_item_match(
-	struct xfs_log_item	*lip,
-	uint64_t		intent_id)
-{
-	return BUI_ITEM(lip)->bui_format.bui_id == intent_id;
-}
-
 /* Relog an intent item to push the log tail forward. */
 static struct xfs_log_item *
-xfs_bui_item_relog(
+xfs_bmap_relog_intent(
+	struct xfs_trans		*tp,
 	struct xfs_log_item		*intent,
-	struct xfs_trans		*tp)
+	struct xfs_log_item		*done_item)
 {
-	struct xfs_bud_log_item		*budp;
 	struct xfs_bui_log_item		*buip;
 	struct xfs_map_extent		*map;
 	unsigned int			count;
@@ -601,27 +555,40 @@ xfs_bui_item_relog(
 	count = BUI_ITEM(intent)->bui_format.bui_nextents;
 	map = BUI_ITEM(intent)->bui_format.bui_extents;
 
-	tp->t_flags |= XFS_TRANS_DIRTY;
-	budp = xfs_trans_get_bud(tp, BUI_ITEM(intent));
-	set_bit(XFS_LI_DIRTY, &budp->bud_item.li_flags);
-
 	buip = xfs_bui_init(tp->t_mountp);
 	memcpy(buip->bui_format.bui_extents, map, count * sizeof(*map));
 	atomic_set(&buip->bui_next_extent, count);
-	xfs_trans_add_item(tp, &buip->bui_item);
-	set_bit(XFS_LI_DIRTY, &buip->bui_item.li_flags);
+
 	return &buip->bui_item;
 }
 
+const struct xfs_defer_op_type xfs_bmap_update_defer_type = {
+	.name		= "bmap",
+	.max_items	= XFS_BUI_MAX_FAST_EXTENTS,
+	.create_intent	= xfs_bmap_update_create_intent,
+	.abort_intent	= xfs_bmap_update_abort_intent,
+	.create_done	= xfs_bmap_update_create_done,
+	.finish_item	= xfs_bmap_update_finish_item,
+	.cancel_item	= xfs_bmap_update_cancel_item,
+	.recover_work	= xfs_bmap_recover_work,
+	.relog_intent	= xfs_bmap_relog_intent,
+};
+
+STATIC bool
+xfs_bui_item_match(
+	struct xfs_log_item	*lip,
+	uint64_t		intent_id)
+{
+	return BUI_ITEM(lip)->bui_format.bui_id == intent_id;
+}
+
 static const struct xfs_item_ops xfs_bui_item_ops = {
 	.flags		= XFS_ITEM_INTENT,
 	.iop_size	= xfs_bui_item_size,
 	.iop_format	= xfs_bui_item_format,
 	.iop_unpin	= xfs_bui_item_unpin,
 	.iop_release	= xfs_bui_item_release,
-	.iop_recover	= xfs_bui_item_recover,
 	.iop_match	= xfs_bui_item_match,
-	.iop_relog	= xfs_bui_item_relog,
 };
 
 static inline void
@@ -681,12 +648,9 @@ xlog_recover_bui_commit_pass2(
 	buip = xfs_bui_init(mp);
 	xfs_bui_copy_format(&buip->bui_format, bui_formatp);
 	atomic_set(&buip->bui_next_extent, bui_formatp->bui_nextents);
-	/*
-	 * Insert the intent into the AIL directly and drop one reference so
-	 * that finishing or canceling the work will drop the other.
-	 */
-	xfs_trans_ail_insert(log->l_ailp, &buip->bui_item, lsn);
-	xfs_bui_release(buip);
+
+	xlog_recover_intent_item(log, &buip->bui_item, lsn,
+			&xfs_bmap_update_defer_type);
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 731260a5af6d..c2531c28905c 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -69,147 +69,6 @@ xfs_zero_extent(
 		GFP_NOFS, 0);
 }
 
-#ifdef CONFIG_XFS_RT
-int
-xfs_bmap_rtalloc(
-	struct xfs_bmalloca	*ap)
-{
-	struct xfs_mount	*mp = ap->ip->i_mount;
-	xfs_fileoff_t		orig_offset = ap->offset;
-	xfs_rtxnum_t		rtx;
-	xfs_rtxlen_t		prod = 0;  /* product factor for allocators */
-	xfs_extlen_t		mod = 0;   /* product factor for allocators */
-	xfs_rtxlen_t		ralen = 0; /* realtime allocation length */
-	xfs_extlen_t		align;     /* minimum allocation alignment */
-	xfs_extlen_t		orig_length = ap->length;
-	xfs_extlen_t		minlen = mp->m_sb.sb_rextsize;
-	xfs_rtxlen_t		raminlen;
-	bool			rtlocked = false;
-	bool			ignore_locality = false;
-	int			error;
-
-	align = xfs_get_extsz_hint(ap->ip);
-retry:
-	prod = xfs_extlen_to_rtxlen(mp, align);
-	error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
-					align, 1, ap->eof, 0,
-					ap->conv, &ap->offset, &ap->length);
-	if (error)
-		return error;
-	ASSERT(ap->length);
-	ASSERT(xfs_extlen_to_rtxmod(mp, ap->length) == 0);
-
-	/*
-	 * If we shifted the file offset downward to satisfy an extent size
-	 * hint, increase minlen by that amount so that the allocator won't
-	 * give us an allocation that's too short to cover at least one of the
-	 * blocks that the caller asked for.
-	 */
-	if (ap->offset != orig_offset)
-		minlen += orig_offset - ap->offset;
-
-	/*
-	 * If the offset & length are not perfectly aligned
-	 * then kill prod, it will just get us in trouble.
-	 */
-	div_u64_rem(ap->offset, align, &mod);
-	if (mod || ap->length % align)
-		prod = 1;
-	/*
-	 * Set ralen to be the actual requested length in rtextents.
-	 *
-	 * If the old value was close enough to XFS_BMBT_MAX_EXTLEN that
-	 * we rounded up to it, cut it back so it's valid again.
-	 * Note that if it's a really large request (bigger than
-	 * XFS_BMBT_MAX_EXTLEN), we don't hear about that number, and can't
-	 * adjust the starting point to match it.
-	 */
-	ralen = xfs_extlen_to_rtxlen(mp, min(ap->length, XFS_MAX_BMBT_EXTLEN));
-
-	/*
-	 * Lock out modifications to both the RT bitmap and summary inodes
-	 */
-	if (!rtlocked) {
-		xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL|XFS_ILOCK_RTBITMAP);
-		xfs_trans_ijoin(ap->tp, mp->m_rbmip, XFS_ILOCK_EXCL);
-		xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL|XFS_ILOCK_RTSUM);
-		xfs_trans_ijoin(ap->tp, mp->m_rsumip, XFS_ILOCK_EXCL);
-		rtlocked = true;
-	}
-
-	/*
-	 * If it's an allocation to an empty file at offset 0,
-	 * pick an extent that will space things out in the rt area.
-	 */
-	if (ap->eof && ap->offset == 0) {
-		error = xfs_rtpick_extent(mp, ap->tp, ralen, &rtx);
-		if (error)
-			return error;
-		ap->blkno = xfs_rtx_to_rtb(mp, rtx);
-	} else {
-		ap->blkno = 0;
-	}
-
-	xfs_bmap_adjacent(ap);
-
-	/*
-	 * Realtime allocation, done through xfs_rtallocate_extent.
-	 */
-	if (ignore_locality)
-		rtx = 0;
-	else
-		rtx = xfs_rtb_to_rtx(mp, ap->blkno);
-	raminlen = max_t(xfs_rtxlen_t, 1, xfs_extlen_to_rtxlen(mp, minlen));
-	error = xfs_rtallocate_extent(ap->tp, rtx, raminlen, ralen, &ralen,
-			ap->wasdel, prod, &rtx);
-	if (error)
-		return error;
-
-	if (rtx != NULLRTEXTNO) {
-		ap->blkno = xfs_rtx_to_rtb(mp, rtx);
-		ap->length = xfs_rtxlen_to_extlen(mp, ralen);
-		ap->ip->i_nblocks += ap->length;
-		xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE);
-		if (ap->wasdel)
-			ap->ip->i_delayed_blks -= ap->length;
-		/*
-		 * Adjust the disk quota also. This was reserved
-		 * earlier.
-		 */
-		xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
-			ap->wasdel ? XFS_TRANS_DQ_DELRTBCOUNT :
-					XFS_TRANS_DQ_RTBCOUNT, ap->length);
-		return 0;
-	}
-
-	if (align > mp->m_sb.sb_rextsize) {
-		/*
-		 * We previously enlarged the request length to try to satisfy
-		 * an extent size hint.  The allocator didn't return anything,
-		 * so reset the parameters to the original values and try again
-		 * without alignment criteria.
-		 */
-		ap->offset = orig_offset;
-		ap->length = orig_length;
-		minlen = align = mp->m_sb.sb_rextsize;
-		goto retry;
-	}
-
-	if (!ignore_locality && ap->blkno != 0) {
-		/*
-		 * If we can't allocate near a specific rt extent, try again
-		 * without locality criteria.
-		 */
-		ignore_locality = true;
-		goto retry;
-	}
-
-	ap->blkno = NULLFSBLOCK;
-	ap->length = 0;
-	return 0;
-}
-#endif /* CONFIG_XFS_RT */
-
 /*
  * Extent tree block counting routines.
  */
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 6888078f5c31..77ecbb753ef2 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -47,7 +47,7 @@ int	xfs_bmap_extsize_align(struct xfs_mount *mp, struct xfs_bmbt_irec *gotp,
 			       struct xfs_bmbt_irec *prevp, xfs_extlen_t extsz,
 			       int rt, int eof, int delay, int convert,
 			       xfs_fileoff_t *offp, xfs_extlen_t *lenp);
-void	xfs_bmap_adjacent(struct xfs_bmalloca *ap);
+bool	xfs_bmap_adjacent(struct xfs_bmalloca *ap);
 int	xfs_bmap_last_extent(struct xfs_trans *tp, struct xfs_inode *ip,
 			     int whichfork, struct xfs_bmbt_irec *rec,
 			     int *is_empty);
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 545c7991b9b5..8e5bd50d29fe 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -169,7 +169,7 @@ xfs_buf_stale(
 
 	atomic_set(&bp->b_lru_ref, 0);
 	if (!(bp->b_state & XFS_BSTATE_DISPOSE) &&
-	    (list_lru_del(&bp->b_target->bt_lru, &bp->b_lru)))
+	    (list_lru_del_obj(&bp->b_target->bt_lru, &bp->b_lru)))
 		atomic_dec(&bp->b_hold);
 
 	ASSERT(atomic_read(&bp->b_hold) >= 1);
@@ -1047,7 +1047,7 @@ xfs_buf_rele(
 		 * buffer for the LRU and clear the (now stale) dispose list
 		 * state flag
 		 */
-		if (list_lru_add(&bp->b_target->bt_lru, &bp->b_lru)) {
+		if (list_lru_add_obj(&bp->b_target->bt_lru, &bp->b_lru)) {
 			bp->b_state &= ~XFS_BSTATE_DISPOSE;
 			atomic_inc(&bp->b_hold);
 		}
@@ -1060,7 +1060,7 @@ xfs_buf_rele(
 		 * was on was the disposal list
 		 */
 		if (!(bp->b_state & XFS_BSTATE_DISPOSE)) {
-			list_lru_del(&bp->b_target->bt_lru, &bp->b_lru);
+			list_lru_del_obj(&bp->b_target->bt_lru, &bp->b_lru);
 		} else {
 			ASSERT(list_empty(&bp->b_lru));
 		}
@@ -2049,6 +2049,14 @@ error_free:
 	return NULL;
 }
 
+static inline void
+xfs_buf_list_del(
+	struct xfs_buf		*bp)
+{
+	list_del_init(&bp->b_list);
+	wake_up_var(&bp->b_list);
+}
+
 /*
  * Cancel a delayed write list.
  *
@@ -2066,7 +2074,7 @@ xfs_buf_delwri_cancel(
 
 		xfs_buf_lock(bp);
 		bp->b_flags &= ~_XBF_DELWRI_Q;
-		list_del_init(&bp->b_list);
+		xfs_buf_list_del(bp);
 		xfs_buf_relse(bp);
 	}
 }
@@ -2120,6 +2128,34 @@ xfs_buf_delwri_queue(
 }
 
 /*
+ * Queue a buffer to this delwri list as part of a data integrity operation.
+ * If the buffer is on any other delwri list, we'll wait for that to clear
+ * so that the caller can submit the buffer for IO and wait for the result.
+ * Callers must ensure the buffer is not already on the list.
+ */
+void
+xfs_buf_delwri_queue_here(
+	struct xfs_buf		*bp,
+	struct list_head	*buffer_list)
+{
+	/*
+	 * We need this buffer to end up on the /caller's/ delwri list, not any
+	 * old list.  This can happen if the buffer is marked stale (which
+	 * clears DELWRI_Q) after the AIL queues the buffer to its list but
+	 * before the AIL has a chance to submit the list.
+	 */
+	while (!list_empty(&bp->b_list)) {
+		xfs_buf_unlock(bp);
+		wait_var_event(&bp->b_list, list_empty(&bp->b_list));
+		xfs_buf_lock(bp);
+	}
+
+	ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
+
+	xfs_buf_delwri_queue(bp, buffer_list);
+}
+
+/*
  * Compare function is more complex than it needs to be because
  * the return value is only 32 bits and we are doing comparisons
  * on 64 bit values
@@ -2181,7 +2217,7 @@ xfs_buf_delwri_submit_buffers(
 		 * reference and remove it from the list here.
 		 */
 		if (!(bp->b_flags & _XBF_DELWRI_Q)) {
-			list_del_init(&bp->b_list);
+			xfs_buf_list_del(bp);
 			xfs_buf_relse(bp);
 			continue;
 		}
@@ -2201,7 +2237,7 @@ xfs_buf_delwri_submit_buffers(
 			list_move_tail(&bp->b_list, wait_list);
 		} else {
 			bp->b_flags |= XBF_ASYNC;
-			list_del_init(&bp->b_list);
+			xfs_buf_list_del(bp);
 		}
 		__xfs_buf_submit(bp, false);
 	}
@@ -2255,7 +2291,7 @@ xfs_buf_delwri_submit(
 	while (!list_empty(&wait_list)) {
 		bp = list_first_entry(&wait_list, struct xfs_buf, b_list);
 
-		list_del_init(&bp->b_list);
+		xfs_buf_list_del(bp);
 
 		/*
 		 * Wait on the locked buffer, check for errors and unlock and
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index c86e16419656..b470de08a46c 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -319,6 +319,7 @@ extern void xfs_buf_stale(struct xfs_buf *bp);
 /* Delayed Write Buffer Routines */
 extern void xfs_buf_delwri_cancel(struct list_head *);
 extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *);
+void xfs_buf_delwri_queue_here(struct xfs_buf *bp, struct list_head *bl);
 extern int xfs_buf_delwri_submit(struct list_head *);
 extern int xfs_buf_delwri_submit_nowait(struct list_head *);
 extern int xfs_buf_delwri_pushbuf(struct xfs_buf *, struct list_head *);
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index 9f3ceb461515..cc6dc56f455d 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -18,6 +18,7 @@
 #include "xfs_bmap.h"
 #include "xfs_trans.h"
 #include "xfs_error.h"
+#include "xfs_health.h"
 
 /*
  * Directory file type support functions
@@ -51,7 +52,7 @@ xfs_dir2_sf_getdents(
 	struct xfs_mount	*mp = dp->i_mount;
 	xfs_dir2_dataptr_t	off;		/* current entry's offset */
 	xfs_dir2_sf_entry_t	*sfep;		/* shortform directory entry */
-	xfs_dir2_sf_hdr_t	*sfp;		/* shortform structure */
+	struct xfs_dir2_sf_hdr	*sfp = dp->i_df.if_data;
 	xfs_dir2_dataptr_t	dot_offset;
 	xfs_dir2_dataptr_t	dotdot_offset;
 	xfs_ino_t		ino;
@@ -59,9 +60,7 @@ xfs_dir2_sf_getdents(
 
 	ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
 	ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
-	ASSERT(dp->i_df.if_u1.if_data != NULL);
-
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	ASSERT(sfp != NULL);
 
 	/*
 	 * If the block number in the offset is out of range, we're done.
@@ -519,6 +518,8 @@ xfs_readdir(
 
 	if (xfs_is_shutdown(dp->i_mount))
 		return -EIO;
+	if (xfs_ifork_zapped(dp, XFS_DATA_FORK))
+		return -EIO;
 
 	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
 	ASSERT(xfs_isilocked(dp, XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index ac6ba646624d..b4f20d9c8f98 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -172,14 +172,14 @@ xfs_qm_adjust_dqtimers(
 /*
  * initialize a buffer full of dquots and log the whole thing
  */
-STATIC void
+void
 xfs_qm_init_dquot_blk(
 	struct xfs_trans	*tp,
-	struct xfs_mount	*mp,
 	xfs_dqid_t		id,
 	xfs_dqtype_t		type,
 	struct xfs_buf		*bp)
 {
+	struct xfs_mount	*mp = tp->t_mountp;
 	struct xfs_quotainfo	*q = mp->m_quotainfo;
 	struct xfs_dqblk	*d;
 	xfs_dqid_t		curid;
@@ -353,7 +353,7 @@ xfs_dquot_disk_alloc(
 	 * Make a chunk of dquots out of this buffer and log
 	 * the entire thing.
 	 */
-	xfs_qm_init_dquot_blk(tp, mp, dqp->q_id, qtype, bp);
+	xfs_qm_init_dquot_blk(tp, dqp->q_id, qtype, bp);
 	xfs_buf_set_ref(bp, XFS_DQUOT_REF);
 
 	/*
@@ -562,7 +562,8 @@ xfs_dquot_from_disk(
 	struct xfs_dquot	*dqp,
 	struct xfs_buf		*bp)
 {
-	struct xfs_disk_dquot	*ddqp = bp->b_addr + dqp->q_bufoffset;
+	struct xfs_dqblk	*dqb = xfs_buf_offset(bp, dqp->q_bufoffset);
+	struct xfs_disk_dquot	*ddqp = &dqb->dd_diskdq;
 
 	/*
 	 * Ensure that we got the type and ID we were looking for.
@@ -1064,7 +1065,7 @@ xfs_qm_dqput(
 		struct xfs_quotainfo	*qi = dqp->q_mount->m_quotainfo;
 		trace_xfs_dqput_free(dqp);
 
-		if (list_lru_add(&qi->qi_lru, &dqp->q_lru))
+		if (list_lru_add_obj(&qi->qi_lru, &dqp->q_lru))
 			XFS_STATS_INC(dqp->q_mount, xs_qm_dquot_unused);
 	}
 	xfs_dqunlock(dqp);
@@ -1250,7 +1251,7 @@ xfs_qm_dqflush(
 	}
 
 	/* Flush the incore dquot to the ondisk buffer. */
-	dqblk = bp->b_addr + dqp->q_bufoffset;
+	dqblk = xfs_buf_offset(bp, dqp->q_bufoffset);
 	xfs_dquot_to_disk(&dqblk->dd_diskdq, dqp);
 
 	/*
@@ -1361,34 +1362,3 @@ xfs_qm_exit(void)
 	kmem_cache_destroy(xfs_dqtrx_cache);
 	kmem_cache_destroy(xfs_dquot_cache);
 }
-
-/*
- * Iterate every dquot of a particular type.  The caller must ensure that the
- * particular quota type is active.  iter_fn can return negative error codes,
- * or -ECANCELED to indicate that it wants to stop iterating.
- */
-int
-xfs_qm_dqiterate(
-	struct xfs_mount	*mp,
-	xfs_dqtype_t		type,
-	xfs_qm_dqiterate_fn	iter_fn,
-	void			*priv)
-{
-	struct xfs_dquot	*dq;
-	xfs_dqid_t		id = 0;
-	int			error;
-
-	do {
-		error = xfs_qm_dqget_next(mp, id, type, &dq);
-		if (error == -ENOENT)
-			return 0;
-		if (error)
-			return error;
-
-		error = iter_fn(dq, type, priv);
-		id = dq->q_id + 1;
-		xfs_qm_dqput(dq);
-	} while (error == 0 && id != 0);
-
-	return error;
-}
diff --git a/fs/xfs/xfs_dquot.h b/fs/xfs/xfs_dquot.h
index 80c8f851a2f3..956272d9b302 100644
--- a/fs/xfs/xfs_dquot.h
+++ b/fs/xfs/xfs_dquot.h
@@ -234,12 +234,10 @@ static inline struct xfs_dquot *xfs_qm_dqhold(struct xfs_dquot *dqp)
 	return dqp;
 }
 
-typedef int (*xfs_qm_dqiterate_fn)(struct xfs_dquot *dq,
-		xfs_dqtype_t type, void *priv);
-int xfs_qm_dqiterate(struct xfs_mount *mp, xfs_dqtype_t type,
-		xfs_qm_dqiterate_fn iter_fn, void *priv);
-
 time64_t xfs_dquot_set_timeout(struct xfs_mount *mp, time64_t timeout);
 time64_t xfs_dquot_set_grace_period(time64_t grace);
 
+void xfs_qm_init_dquot_blk(struct xfs_trans *tp, xfs_dqid_t id, xfs_dqtype_t
+		type, struct xfs_buf *bp);
+
 #endif /* __XFS_DQUOT_H__ */
diff --git a/fs/xfs/xfs_dquot_item_recover.c b/fs/xfs/xfs_dquot_item_recover.c
index 8966ba842395..2c2720ce6923 100644
--- a/fs/xfs/xfs_dquot_item_recover.c
+++ b/fs/xfs/xfs_dquot_item_recover.c
@@ -19,6 +19,7 @@
 #include "xfs_log.h"
 #include "xfs_log_priv.h"
 #include "xfs_log_recover.h"
+#include "xfs_error.h"
 
 STATIC void
 xlog_recover_dquot_ra_pass2(
@@ -65,6 +66,7 @@ xlog_recover_dquot_commit_pass2(
 {
 	struct xfs_mount		*mp = log->l_mp;
 	struct xfs_buf			*bp;
+	struct xfs_dqblk		*dqb;
 	struct xfs_disk_dquot		*ddq, *recddq;
 	struct xfs_dq_logformat		*dq_f;
 	xfs_failaddr_t			fa;
@@ -130,14 +132,14 @@ xlog_recover_dquot_commit_pass2(
 		return error;
 
 	ASSERT(bp);
-	ddq = xfs_buf_offset(bp, dq_f->qlf_boffset);
+	dqb = xfs_buf_offset(bp, dq_f->qlf_boffset);
+	ddq = &dqb->dd_diskdq;
 
 	/*
 	 * If the dquot has an LSN in it, recover the dquot only if it's less
 	 * than the lsn of the transaction we are replaying.
 	 */
 	if (xfs_has_crc(mp)) {
-		struct xfs_dqblk *dqb = (struct xfs_dqblk *)ddq;
 		xfs_lsn_t	lsn = be64_to_cpu(dqb->dd_lsn);
 
 		if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) {
@@ -147,10 +149,23 @@ xlog_recover_dquot_commit_pass2(
 
 	memcpy(ddq, recddq, item->ri_buf[1].i_len);
 	if (xfs_has_crc(mp)) {
-		xfs_update_cksum((char *)ddq, sizeof(struct xfs_dqblk),
+		xfs_update_cksum((char *)dqb, sizeof(struct xfs_dqblk),
 				 XFS_DQUOT_CRC_OFF);
 	}
 
+	/* Validate the recovered dquot. */
+	fa = xfs_dqblk_verify(log->l_mp, dqb, dq_f->qlf_id);
+	if (fa) {
+		XFS_CORRUPTION_ERROR("Bad dquot after recovery",
+				XFS_ERRLEVEL_LOW, mp, dqb,
+				sizeof(struct xfs_dqblk));
+		xfs_alert(mp,
+ "Metadata corruption detected at %pS, dquot 0x%x",
+				fa, dq_f->qlf_id);
+		error = -EFSCORRUPTED;
+		goto out_release;
+	}
+
 	ASSERT(dq_f->qlf_size == 2);
 	ASSERT(bp->b_mount == mp);
 	bp->b_flags |= _XBF_LOGRECOVERY;
diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c
index 9ecfdcdc752f..2ccde32c9a9e 100644
--- a/fs/xfs/xfs_extent_busy.c
+++ b/fs/xfs/xfs_extent_busy.c
@@ -678,3 +678,16 @@ xfs_extent_busy_ag_cmp(
 		diff = b1->bno - b2->bno;
 	return diff;
 }
+
+/* Are there any busy extents in this AG? */
+bool
+xfs_extent_busy_list_empty(
+	struct xfs_perag	*pag)
+{
+	bool			res;
+
+	spin_lock(&pag->pagb_lock);
+	res = RB_EMPTY_ROOT(&pag->pagb_tree);
+	spin_unlock(&pag->pagb_lock);
+	return res;
+}
diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h
index 0639aab336f3..470032de3139 100644
--- a/fs/xfs/xfs_extent_busy.h
+++ b/fs/xfs/xfs_extent_busy.h
@@ -85,4 +85,6 @@ static inline void xfs_extent_busy_sort(struct list_head *list)
 	list_sort(NULL, list, xfs_extent_busy_ag_cmp);
 }
 
+bool xfs_extent_busy_list_empty(struct xfs_perag *pag);
+
 #endif /* __XFS_EXTENT_BUSY_H__ */
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index 3fa8789820ad..1d1185fca6a5 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -304,39 +304,6 @@ static const struct xfs_item_ops xfs_efd_item_ops = {
 };
 
 /*
- * Allocate an "extent free done" log item that will hold nextents worth of
- * extents.  The caller must use all nextents extents, because we are not
- * flexible about this at all.
- */
-static struct xfs_efd_log_item *
-xfs_trans_get_efd(
-	struct xfs_trans		*tp,
-	struct xfs_efi_log_item		*efip,
-	unsigned int			nextents)
-{
-	struct xfs_efd_log_item		*efdp;
-
-	ASSERT(nextents > 0);
-
-	if (nextents > XFS_EFD_MAX_FAST_EXTENTS) {
-		efdp = kzalloc(xfs_efd_log_item_sizeof(nextents),
-				GFP_KERNEL | __GFP_NOFAIL);
-	} else {
-		efdp = kmem_cache_zalloc(xfs_efd_cache,
-					GFP_KERNEL | __GFP_NOFAIL);
-	}
-
-	xfs_log_item_init(tp->t_mountp, &efdp->efd_item, XFS_LI_EFD,
-			  &xfs_efd_item_ops);
-	efdp->efd_efip = efip;
-	efdp->efd_format.efd_nextents = nextents;
-	efdp->efd_format.efd_efi_id = efip->efi_format.efi_id;
-
-	xfs_trans_add_item(tp, &efdp->efd_item);
-	return efdp;
-}
-
-/*
  * Fill the EFD with all extents from the EFI when we need to roll the
  * transaction and continue with a new EFI.
  *
@@ -364,69 +331,6 @@ xfs_efd_from_efi(
 	efdp->efd_next_extent = efip->efi_format.efi_nextents;
 }
 
-/*
- * Free an extent and log it to the EFD. Note that the transaction is marked
- * dirty regardless of whether the extent free succeeds or fails to support the
- * EFI/EFD lifecycle rules.
- */
-static int
-xfs_trans_free_extent(
-	struct xfs_trans		*tp,
-	struct xfs_efd_log_item		*efdp,
-	struct xfs_extent_free_item	*xefi)
-{
-	struct xfs_owner_info		oinfo = { };
-	struct xfs_mount		*mp = tp->t_mountp;
-	struct xfs_extent		*extp;
-	uint				next_extent;
-	xfs_agblock_t			agbno = XFS_FSB_TO_AGBNO(mp,
-							xefi->xefi_startblock);
-	int				error;
-
-	oinfo.oi_owner = xefi->xefi_owner;
-	if (xefi->xefi_flags & XFS_EFI_ATTR_FORK)
-		oinfo.oi_flags |= XFS_OWNER_INFO_ATTR_FORK;
-	if (xefi->xefi_flags & XFS_EFI_BMBT_BLOCK)
-		oinfo.oi_flags |= XFS_OWNER_INFO_BMBT_BLOCK;
-
-	trace_xfs_bmap_free_deferred(tp->t_mountp, xefi->xefi_pag->pag_agno, 0,
-			agbno, xefi->xefi_blockcount);
-
-	error = __xfs_free_extent(tp, xefi->xefi_pag, agbno,
-			xefi->xefi_blockcount, &oinfo, xefi->xefi_agresv,
-			xefi->xefi_flags & XFS_EFI_SKIP_DISCARD);
-
-	/*
-	 * Mark the transaction dirty, even on error. This ensures the
-	 * transaction is aborted, which:
-	 *
-	 * 1.) releases the EFI and frees the EFD
-	 * 2.) shuts down the filesystem
-	 */
-	tp->t_flags |= XFS_TRANS_DIRTY | XFS_TRANS_HAS_INTENT_DONE;
-	set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags);
-
-	/*
-	 * If we need a new transaction to make progress, the caller will log a
-	 * new EFI with the current contents. It will also log an EFD to cancel
-	 * the existing EFI, and so we need to copy all the unprocessed extents
-	 * in this EFI to the EFD so this works correctly.
-	 */
-	if (error == -EAGAIN) {
-		xfs_efd_from_efi(efdp);
-		return error;
-	}
-
-	next_extent = efdp->efd_next_extent;
-	ASSERT(next_extent < efdp->efd_format.efd_nextents);
-	extp = &(efdp->efd_format.efd_extents[next_extent]);
-	extp->ext_start = xefi->xefi_startblock;
-	extp->ext_len = xefi->xefi_blockcount;
-	efdp->efd_next_extent++;
-
-	return error;
-}
-
 /* Sort bmap items by AG. */
 static int
 xfs_extent_free_diff_items(
@@ -453,9 +357,6 @@ xfs_extent_free_log_item(
 	uint				next_extent;
 	struct xfs_extent		*extp;
 
-	tp->t_flags |= XFS_TRANS_DIRTY;
-	set_bit(XFS_LI_DIRTY, &efip->efi_item.li_flags);
-
 	/*
 	 * atomic_inc_return gives us the value after the increment;
 	 * we want to use it as an array index so we need to subtract 1 from
@@ -481,7 +382,6 @@ xfs_extent_free_create_intent(
 
 	ASSERT(count > 0);
 
-	xfs_trans_add_item(tp, &efip->efi_item);
 	if (sort)
 		list_sort(mp, items, xfs_extent_free_diff_items);
 	list_for_each_entry(xefi, items, xefi_list)
@@ -496,7 +396,26 @@ xfs_extent_free_create_done(
 	struct xfs_log_item		*intent,
 	unsigned int			count)
 {
-	return &xfs_trans_get_efd(tp, EFI_ITEM(intent), count)->efd_item;
+	struct xfs_efi_log_item		*efip = EFI_ITEM(intent);
+	struct xfs_efd_log_item		*efdp;
+
+	ASSERT(count > 0);
+
+	if (count > XFS_EFD_MAX_FAST_EXTENTS) {
+		efdp = kzalloc(xfs_efd_log_item_sizeof(count),
+				GFP_KERNEL | __GFP_NOFAIL);
+	} else {
+		efdp = kmem_cache_zalloc(xfs_efd_cache,
+					GFP_KERNEL | __GFP_NOFAIL);
+	}
+
+	xfs_log_item_init(tp->t_mountp, &efdp->efd_item, XFS_LI_EFD,
+			  &xfs_efd_item_ops);
+	efdp->efd_efip = efip;
+	efdp->efd_format.efd_nextents = count;
+	efdp->efd_format.efd_efi_id = efip->efi_format.efi_id;
+
+	return &efdp->efd_item;
 }
 
 /* Take a passive ref to the AG containing the space we're freeing. */
@@ -527,19 +446,49 @@ xfs_extent_free_finish_item(
 	struct list_head		*item,
 	struct xfs_btree_cur		**state)
 {
+	struct xfs_owner_info		oinfo = { };
 	struct xfs_extent_free_item	*xefi;
-	int				error;
+	struct xfs_efd_log_item		*efdp = EFD_ITEM(done);
+	struct xfs_mount		*mp = tp->t_mountp;
+	struct xfs_extent		*extp;
+	uint				next_extent;
+	xfs_agblock_t			agbno;
+	int				error = 0;
 
 	xefi = container_of(item, struct xfs_extent_free_item, xefi_list);
+	agbno = XFS_FSB_TO_AGBNO(mp, xefi->xefi_startblock);
+
+	oinfo.oi_owner = xefi->xefi_owner;
+	if (xefi->xefi_flags & XFS_EFI_ATTR_FORK)
+		oinfo.oi_flags |= XFS_OWNER_INFO_ATTR_FORK;
+	if (xefi->xefi_flags & XFS_EFI_BMBT_BLOCK)
+		oinfo.oi_flags |= XFS_OWNER_INFO_BMBT_BLOCK;
 
-	error = xfs_trans_free_extent(tp, EFD_ITEM(done), xefi);
+	trace_xfs_bmap_free_deferred(tp->t_mountp, xefi->xefi_pag->pag_agno, 0,
+			agbno, xefi->xefi_blockcount);
 
 	/*
-	 * Don't free the XEFI if we need a new transaction to complete
-	 * processing of it.
+	 * If we need a new transaction to make progress, the caller will log a
+	 * new EFI with the current contents. It will also log an EFD to cancel
+	 * the existing EFI, and so we need to copy all the unprocessed extents
+	 * in this EFI to the EFD so this works correctly.
 	 */
-	if (error == -EAGAIN)
+	if (!(xefi->xefi_flags & XFS_EFI_CANCELLED))
+		error = __xfs_free_extent(tp, xefi->xefi_pag, agbno,
+				xefi->xefi_blockcount, &oinfo, xefi->xefi_agresv,
+				xefi->xefi_flags & XFS_EFI_SKIP_DISCARD);
+	if (error == -EAGAIN) {
+		xfs_efd_from_efi(efdp);
 		return error;
+	}
+
+	/* Add the work we finished to the EFD, even though nobody uses that */
+	next_extent = efdp->efd_next_extent;
+	ASSERT(next_extent < efdp->efd_format.efd_nextents);
+	extp = &(efdp->efd_format.efd_extents[next_extent]);
+	extp->ext_start = xefi->xefi_startblock;
+	extp->ext_len = xefi->xefi_blockcount;
+	efdp->efd_next_extent++;
 
 	xfs_extent_free_put_group(xefi);
 	kmem_cache_free(xfs_extfree_item_cache, xefi);
@@ -567,15 +516,6 @@ xfs_extent_free_cancel_item(
 	kmem_cache_free(xfs_extfree_item_cache, xefi);
 }
 
-const struct xfs_defer_op_type xfs_extent_free_defer_type = {
-	.max_items	= XFS_EFI_MAX_FAST_EXTENTS,
-	.create_intent	= xfs_extent_free_create_intent,
-	.abort_intent	= xfs_extent_free_abort_intent,
-	.create_done	= xfs_extent_free_create_done,
-	.finish_item	= xfs_extent_free_finish_item,
-	.cancel_item	= xfs_extent_free_cancel_item,
-};
-
 /*
  * AGFL blocks are accounted differently in the reserve pools and are not
  * inserted into the busy extent list.
@@ -610,16 +550,6 @@ xfs_agfl_free_finish_item(
 		error = xfs_free_agfl_block(tp, xefi->xefi_pag->pag_agno,
 				agbno, agbp, &oinfo);
 
-	/*
-	 * Mark the transaction dirty, even on error. This ensures the
-	 * transaction is aborted, which:
-	 *
-	 * 1.) releases the EFI and frees the EFD
-	 * 2.) shuts down the filesystem
-	 */
-	tp->t_flags |= XFS_TRANS_DIRTY;
-	set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags);
-
 	next_extent = efdp->efd_next_extent;
 	ASSERT(next_extent < efdp->efd_format.efd_nextents);
 	extp = &(efdp->efd_format.efd_extents[next_extent]);
@@ -632,16 +562,6 @@ xfs_agfl_free_finish_item(
 	return error;
 }
 
-/* sub-type with special handling for AGFL deferred frees */
-const struct xfs_defer_op_type xfs_agfl_free_defer_type = {
-	.max_items	= XFS_EFI_MAX_FAST_EXTENTS,
-	.create_intent	= xfs_extent_free_create_intent,
-	.abort_intent	= xfs_extent_free_abort_intent,
-	.create_done	= xfs_extent_free_create_done,
-	.finish_item	= xfs_agfl_free_finish_item,
-	.cancel_item	= xfs_extent_free_cancel_item,
-};
-
 /* Is this recovered EFI ok? */
 static inline bool
 xfs_efi_validate_ext(
@@ -651,23 +571,41 @@ xfs_efi_validate_ext(
 	return xfs_verify_fsbext(mp, extp->ext_start, extp->ext_len);
 }
 
+static inline void
+xfs_efi_recover_work(
+	struct xfs_mount		*mp,
+	struct xfs_defer_pending	*dfp,
+	struct xfs_extent		*extp)
+{
+	struct xfs_extent_free_item	*xefi;
+
+	xefi = kmem_cache_zalloc(xfs_extfree_item_cache,
+			       GFP_KERNEL | __GFP_NOFAIL);
+	xefi->xefi_startblock = extp->ext_start;
+	xefi->xefi_blockcount = extp->ext_len;
+	xefi->xefi_agresv = XFS_AG_RESV_NONE;
+	xefi->xefi_owner = XFS_RMAP_OWN_UNKNOWN;
+	xfs_extent_free_get_group(mp, xefi);
+
+	xfs_defer_add_item(dfp, &xefi->xefi_list);
+}
+
 /*
  * Process an extent free intent item that was recovered from
  * the log.  We need to free the extents that it describes.
  */
 STATIC int
-xfs_efi_item_recover(
-	struct xfs_log_item		*lip,
+xfs_extent_free_recover_work(
+	struct xfs_defer_pending	*dfp,
 	struct list_head		*capture_list)
 {
 	struct xfs_trans_res		resv;
+	struct xfs_log_item		*lip = dfp->dfp_intent;
 	struct xfs_efi_log_item		*efip = EFI_ITEM(lip);
 	struct xfs_mount		*mp = lip->li_log->l_mp;
-	struct xfs_efd_log_item		*efdp;
 	struct xfs_trans		*tp;
 	int				i;
 	int				error = 0;
-	bool				requeue_only = false;
 
 	/*
 	 * First check the validity of the extents described by the
@@ -682,55 +620,22 @@ xfs_efi_item_recover(
 					sizeof(efip->efi_format));
 			return -EFSCORRUPTED;
 		}
+
+		xfs_efi_recover_work(mp, dfp, &efip->efi_format.efi_extents[i]);
 	}
 
 	resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate);
 	error = xfs_trans_alloc(mp, &resv, 0, 0, 0, &tp);
 	if (error)
 		return error;
-	efdp = xfs_trans_get_efd(tp, efip, efip->efi_format.efi_nextents);
-
-	for (i = 0; i < efip->efi_format.efi_nextents; i++) {
-		struct xfs_extent_free_item	fake = {
-			.xefi_owner		= XFS_RMAP_OWN_UNKNOWN,
-			.xefi_agresv		= XFS_AG_RESV_NONE,
-		};
-		struct xfs_extent		*extp;
 
-		extp = &efip->efi_format.efi_extents[i];
-
-		fake.xefi_startblock = extp->ext_start;
-		fake.xefi_blockcount = extp->ext_len;
-
-		if (!requeue_only) {
-			xfs_extent_free_get_group(mp, &fake);
-			error = xfs_trans_free_extent(tp, efdp, &fake);
-			xfs_extent_free_put_group(&fake);
-		}
-
-		/*
-		 * If we can't free the extent without potentially deadlocking,
-		 * requeue the rest of the extents to a new so that they get
-		 * run again later with a new transaction context.
-		 */
-		if (error == -EAGAIN || requeue_only) {
-			error = xfs_free_extent_later(tp, fake.xefi_startblock,
-					fake.xefi_blockcount,
-					&XFS_RMAP_OINFO_ANY_OWNER,
-					fake.xefi_agresv);
-			if (!error) {
-				requeue_only = true;
-				continue;
-			}
-		}
-
-		if (error == -EFSCORRUPTED)
-			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
-					extp, sizeof(*extp));
-		if (error)
-			goto abort_error;
-
-	}
+	error = xlog_recover_finish_intent(tp, dfp);
+	if (error == -EFSCORRUPTED)
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				&efip->efi_format,
+				sizeof(efip->efi_format));
+	if (error)
+		goto abort_error;
 
 	return xfs_defer_ops_capture_and_commit(tp, capture_list);
 
@@ -739,21 +644,14 @@ abort_error:
 	return error;
 }
 
-STATIC bool
-xfs_efi_item_match(
-	struct xfs_log_item	*lip,
-	uint64_t		intent_id)
-{
-	return EFI_ITEM(lip)->efi_format.efi_id == intent_id;
-}
-
 /* Relog an intent item to push the log tail forward. */
 static struct xfs_log_item *
-xfs_efi_item_relog(
+xfs_extent_free_relog_intent(
+	struct xfs_trans		*tp,
 	struct xfs_log_item		*intent,
-	struct xfs_trans		*tp)
+	struct xfs_log_item		*done_item)
 {
-	struct xfs_efd_log_item		*efdp;
+	struct xfs_efd_log_item		*efdp = EFD_ITEM(done_item);
 	struct xfs_efi_log_item		*efip;
 	struct xfs_extent		*extp;
 	unsigned int			count;
@@ -761,29 +659,56 @@ xfs_efi_item_relog(
 	count = EFI_ITEM(intent)->efi_format.efi_nextents;
 	extp = EFI_ITEM(intent)->efi_format.efi_extents;
 
-	tp->t_flags |= XFS_TRANS_DIRTY;
-	efdp = xfs_trans_get_efd(tp, EFI_ITEM(intent), count);
 	efdp->efd_next_extent = count;
 	memcpy(efdp->efd_format.efd_extents, extp, count * sizeof(*extp));
-	set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags);
 
 	efip = xfs_efi_init(tp->t_mountp, count);
 	memcpy(efip->efi_format.efi_extents, extp, count * sizeof(*extp));
 	atomic_set(&efip->efi_next_extent, count);
-	xfs_trans_add_item(tp, &efip->efi_item);
-	set_bit(XFS_LI_DIRTY, &efip->efi_item.li_flags);
+
 	return &efip->efi_item;
 }
 
+const struct xfs_defer_op_type xfs_extent_free_defer_type = {
+	.name		= "extent_free",
+	.max_items	= XFS_EFI_MAX_FAST_EXTENTS,
+	.create_intent	= xfs_extent_free_create_intent,
+	.abort_intent	= xfs_extent_free_abort_intent,
+	.create_done	= xfs_extent_free_create_done,
+	.finish_item	= xfs_extent_free_finish_item,
+	.cancel_item	= xfs_extent_free_cancel_item,
+	.recover_work	= xfs_extent_free_recover_work,
+	.relog_intent	= xfs_extent_free_relog_intent,
+};
+
+/* sub-type with special handling for AGFL deferred frees */
+const struct xfs_defer_op_type xfs_agfl_free_defer_type = {
+	.name		= "agfl_free",
+	.max_items	= XFS_EFI_MAX_FAST_EXTENTS,
+	.create_intent	= xfs_extent_free_create_intent,
+	.abort_intent	= xfs_extent_free_abort_intent,
+	.create_done	= xfs_extent_free_create_done,
+	.finish_item	= xfs_agfl_free_finish_item,
+	.cancel_item	= xfs_extent_free_cancel_item,
+	.recover_work	= xfs_extent_free_recover_work,
+	.relog_intent	= xfs_extent_free_relog_intent,
+};
+
+STATIC bool
+xfs_efi_item_match(
+	struct xfs_log_item	*lip,
+	uint64_t		intent_id)
+{
+	return EFI_ITEM(lip)->efi_format.efi_id == intent_id;
+}
+
 static const struct xfs_item_ops xfs_efi_item_ops = {
 	.flags		= XFS_ITEM_INTENT,
 	.iop_size	= xfs_efi_item_size,
 	.iop_format	= xfs_efi_item_format,
 	.iop_unpin	= xfs_efi_item_unpin,
 	.iop_release	= xfs_efi_item_release,
-	.iop_recover	= xfs_efi_item_recover,
 	.iop_match	= xfs_efi_item_match,
-	.iop_relog	= xfs_efi_item_relog,
 };
 
 /*
@@ -820,12 +745,9 @@ xlog_recover_efi_commit_pass2(
 		return error;
 	}
 	atomic_set(&efip->efi_next_extent, efi_formatp->efi_nextents);
-	/*
-	 * Insert the intent into the AIL directly and drop one reference so
-	 * that finishing or canceling the work will drop the other.
-	 */
-	xfs_trans_ail_insert(log->l_ailp, &efip->efi_item, lsn);
-	xfs_efi_release(efip);
+
+	xlog_recover_intent_item(log, &efip->efi_item, lsn,
+			&xfs_extent_free_defer_type);
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 7cb75cb6b8e9..83f708f62ed9 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -134,6 +134,10 @@ xfs_growfs_data_private(
 	if (delta < 0 && nagcount < 2)
 		return -EINVAL;
 
+	/* No work to do */
+	if (delta == 0)
+		return 0;
+
 	oagcount = mp->m_sb.sb_agcount;
 	/* allocate the new per-ag structures */
 	if (nagcount > oagcount) {
@@ -153,7 +157,7 @@ xfs_growfs_data_private(
 		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growdata, -delta, 0,
 				0, &tp);
 	if (error)
-		return error;
+		goto out_free_unused_perag;
 
 	last_pag = xfs_perag_get(mp, oagcount - 1);
 	if (delta > 0) {
@@ -227,6 +231,9 @@ xfs_growfs_data_private(
 
 out_trans_cancel:
 	xfs_trans_cancel(tp);
+out_free_unused_perag:
+	if (nagcount > oagcount)
+		xfs_free_unused_perag_range(mp, oagcount, nagcount);
 	return error;
 }
 
@@ -344,59 +351,20 @@ xfs_growfs_log(
 }
 
 /*
- * exported through ioctl XFS_IOC_FSCOUNTS
- */
-
-void
-xfs_fs_counts(
-	xfs_mount_t		*mp,
-	xfs_fsop_counts_t	*cnt)
-{
-	cnt->allocino = percpu_counter_read_positive(&mp->m_icount);
-	cnt->freeino = percpu_counter_read_positive(&mp->m_ifree);
-	cnt->freedata = percpu_counter_read_positive(&mp->m_fdblocks) -
-						xfs_fdblocks_unavailable(mp);
-	cnt->freertx = percpu_counter_read_positive(&mp->m_frextents);
-}
-
-/*
- * exported through ioctl XFS_IOC_SET_RESBLKS & XFS_IOC_GET_RESBLKS
- *
- * xfs_reserve_blocks is called to set m_resblks
- * in the in-core mount table. The number of unused reserved blocks
- * is kept in m_resblks_avail.
- *
  * Reserve the requested number of blocks if available. Otherwise return
  * as many as possible to satisfy the request. The actual number
- * reserved are returned in outval
- *
- * A null inval pointer indicates that only the current reserved blocks
- * available  should  be returned no settings are changed.
+ * reserved are returned in outval.
  */
-
 int
 xfs_reserve_blocks(
-	xfs_mount_t             *mp,
-	uint64_t              *inval,
-	xfs_fsop_resblks_t      *outval)
+	struct xfs_mount	*mp,
+	uint64_t		request)
 {
 	int64_t			lcounter, delta;
 	int64_t			fdblks_delta = 0;
-	uint64_t		request;
 	int64_t			free;
 	int			error = 0;
 
-	/* If inval is null, report current values and return */
-	if (inval == (uint64_t *)NULL) {
-		if (!outval)
-			return -EINVAL;
-		outval->resblks = mp->m_resblks;
-		outval->resblks_avail = mp->m_resblks_avail;
-		return 0;
-	}
-
-	request = *inval;
-
 	/*
 	 * With per-cpu counters, this becomes an interesting problem. we need
 	 * to work out if we are freeing or allocation blocks first, then we can
@@ -466,11 +434,6 @@ xfs_reserve_blocks(
 		spin_lock(&mp->m_sb_lock);
 	}
 out:
-	if (outval) {
-		outval->resblks = mp->m_resblks;
-		outval->resblks_avail = mp->m_resblks_avail;
-	}
-
 	spin_unlock(&mp->m_sb_lock);
 	return error;
 }
@@ -482,9 +445,9 @@ xfs_fs_goingdown(
 {
 	switch (inflags) {
 	case XFS_FSOP_GOING_FLAGS_DEFAULT: {
-		if (!freeze_bdev(mp->m_super->s_bdev)) {
+		if (!bdev_freeze(mp->m_super->s_bdev)) {
 			xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT);
-			thaw_bdev(mp->m_super->s_bdev);
+			bdev_thaw(mp->m_super->s_bdev);
 		}
 		break;
 	}
diff --git a/fs/xfs/xfs_fsops.h b/fs/xfs/xfs_fsops.h
index 2cffe51a31e8..44457b0a0593 100644
--- a/fs/xfs/xfs_fsops.h
+++ b/fs/xfs/xfs_fsops.h
@@ -6,14 +6,12 @@
 #ifndef __XFS_FSOPS_H__
 #define	__XFS_FSOPS_H__
 
-extern int xfs_growfs_data(struct xfs_mount *mp, struct xfs_growfs_data *in);
-extern int xfs_growfs_log(struct xfs_mount *mp, struct xfs_growfs_log *in);
-extern void xfs_fs_counts(xfs_mount_t *mp, xfs_fsop_counts_t *cnt);
-extern int xfs_reserve_blocks(xfs_mount_t *mp, uint64_t *inval,
-				xfs_fsop_resblks_t *outval);
-extern int xfs_fs_goingdown(xfs_mount_t *mp, uint32_t inflags);
+int xfs_growfs_data(struct xfs_mount *mp, struct xfs_growfs_data *in);
+int xfs_growfs_log(struct xfs_mount *mp, struct xfs_growfs_log *in);
+int xfs_reserve_blocks(struct xfs_mount *mp, uint64_t request);
+int xfs_fs_goingdown(struct xfs_mount *mp, uint32_t inflags);
 
-extern int xfs_fs_reserve_ag_blocks(struct xfs_mount *mp);
-extern int xfs_fs_unreserve_ag_blocks(struct xfs_mount *mp);
+int xfs_fs_reserve_ag_blocks(struct xfs_mount *mp);
+int xfs_fs_unreserve_ag_blocks(struct xfs_mount *mp);
 
 #endif	/* __XFS_FSOPS_H__ */
diff --git a/fs/xfs/xfs_globals.c b/fs/xfs/xfs_globals.c
index 9edc1f2bc939..f18fec0adf66 100644
--- a/fs/xfs/xfs_globals.c
+++ b/fs/xfs/xfs_globals.c
@@ -44,4 +44,16 @@ struct xfs_globals xfs_globals = {
 	.pwork_threads		=	-1,	/* automatic thread detection */
 	.larp			=	false,	/* log attribute replay */
 #endif
+
+	/*
+	 * Leave this many record slots empty when bulk loading btrees.  By
+	 * default we load new btree leaf blocks 75% full.
+	 */
+	.bload_leaf_slack	=	-1,
+
+	/*
+	 * Leave this many key/ptr slots empty when bulk loading btrees.  By
+	 * default we load new btree node blocks 75% full.
+	 */
+	.bload_node_slack	=	-1,
 };
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 72a075bb2c10..9a57afee9338 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -222,7 +222,7 @@ xfs_inode_mark_sick(
 	struct xfs_inode	*ip,
 	unsigned int		mask)
 {
-	ASSERT(!(mask & ~XFS_SICK_INO_PRIMARY));
+	ASSERT(!(mask & ~(XFS_SICK_INO_PRIMARY | XFS_SICK_INO_ZAPPED)));
 	trace_xfs_inode_mark_sick(ip, mask);
 
 	spin_lock(&ip->i_flags_lock);
@@ -246,7 +246,7 @@ xfs_inode_mark_healthy(
 	struct xfs_inode	*ip,
 	unsigned int		mask)
 {
-	ASSERT(!(mask & ~XFS_SICK_INO_PRIMARY));
+	ASSERT(!(mask & ~(XFS_SICK_INO_PRIMARY | XFS_SICK_INO_ZAPPED)));
 	trace_xfs_inode_mark_healthy(ip, mask);
 
 	spin_lock(&ip->i_flags_lock);
@@ -369,6 +369,10 @@ static const struct ioctl_sick_map ino_map[] = {
 	{ XFS_SICK_INO_XATTR,	XFS_BS_SICK_XATTR },
 	{ XFS_SICK_INO_SYMLINK,	XFS_BS_SICK_SYMLINK },
 	{ XFS_SICK_INO_PARENT,	XFS_BS_SICK_PARENT },
+	{ XFS_SICK_INO_BMBTD_ZAPPED,	XFS_BS_SICK_BMBTD },
+	{ XFS_SICK_INO_BMBTA_ZAPPED,	XFS_BS_SICK_BMBTA },
+	{ XFS_SICK_INO_DIR_ZAPPED,	XFS_BS_SICK_DIR },
+	{ XFS_SICK_INO_SYMLINK_ZAPPED,	XFS_BS_SICK_SYMLINK },
 	{ 0, 0 },
 };
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index c0f1c89786c2..1fd94958aa97 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -37,15 +37,10 @@
 #include "xfs_reflink.h"
 #include "xfs_ag.h"
 #include "xfs_log_priv.h"
+#include "xfs_health.h"
 
 struct kmem_cache *xfs_inode_cache;
 
-/*
- * Used in xfs_itruncate_extents().  This is the maximum number of extents
- * freed from a file in a single transaction.
- */
-#define	XFS_ITRUNC_MAX_EXTENTS	2
-
 STATIC int xfs_iunlink(struct xfs_trans *, struct xfs_inode *);
 STATIC int xfs_iunlink_remove(struct xfs_trans *tp, struct xfs_perag *pag,
 	struct xfs_inode *);
@@ -661,6 +656,8 @@ xfs_lookup(
 
 	if (xfs_is_shutdown(dp->i_mount))
 		return -EIO;
+	if (xfs_ifork_zapped(dp, XFS_DATA_FORK))
+		return -EIO;
 
 	error = xfs_dir_lookup(NULL, dp, name, &inum, ci_name);
 	if (error)
@@ -875,7 +872,7 @@ xfs_init_new_inode(
 	case S_IFLNK:
 		ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
 		ip->i_df.if_bytes = 0;
-		ip->i_df.if_u1.if_root = NULL;
+		ip->i_df.if_data = NULL;
 		break;
 	default:
 		ASSERT(0);
@@ -978,6 +975,8 @@ xfs_create(
 
 	if (xfs_is_shutdown(mp))
 		return -EIO;
+	if (xfs_ifork_zapped(dp, XFS_DATA_FORK))
+		return -EIO;
 
 	prid = xfs_get_initial_prid(dp);
 
@@ -1217,6 +1216,8 @@ xfs_link(
 
 	if (xfs_is_shutdown(mp))
 		return -EIO;
+	if (xfs_ifork_zapped(tdp, XFS_DATA_FORK))
+		return -EIO;
 
 	error = xfs_qm_dqattach(sip);
 	if (error)
@@ -1339,7 +1340,6 @@ xfs_itruncate_extents_flags(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp = *tpp;
 	xfs_fileoff_t		first_unmap_block;
-	xfs_filblks_t		unmap_len;
 	int			error = 0;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
@@ -1371,19 +1371,10 @@ xfs_itruncate_extents_flags(
 		return 0;
 	}
 
-	unmap_len = XFS_MAX_FILEOFF - first_unmap_block + 1;
-	while (unmap_len > 0) {
-		ASSERT(tp->t_highest_agno == NULLAGNUMBER);
-		error = __xfs_bunmapi(tp, ip, first_unmap_block, &unmap_len,
-				flags, XFS_ITRUNC_MAX_EXTENTS);
-		if (error)
-			goto out;
-
-		/* free the just unmapped extents */
-		error = xfs_defer_finish(&tp);
-		if (error)
-			goto out;
-	}
+	error = xfs_bunmapi_range(&tp, ip, flags, first_unmap_block,
+			XFS_MAX_FILEOFF);
+	if (error)
+		goto out;
 
 	if (whichfork == XFS_DATA_FORK) {
 		/* Remove all pending CoW reservations. */
@@ -2387,8 +2378,8 @@ xfs_ifree(
 	 * already been freed by xfs_attr_inactive.
 	 */
 	if (ip->i_df.if_format == XFS_DINODE_FMT_LOCAL) {
-		kmem_free(ip->i_df.if_u1.if_data);
-		ip->i_df.if_u1.if_data = NULL;
+		kmem_free(ip->i_df.if_data);
+		ip->i_df.if_data = NULL;
 		ip->i_df.if_bytes = 0;
 	}
 
@@ -2506,6 +2497,8 @@ xfs_remove(
 
 	if (xfs_is_shutdown(mp))
 		return -EIO;
+	if (xfs_ifork_zapped(dp, XFS_DATA_FORK))
+		return -EIO;
 
 	error = xfs_qm_dqattach(dp);
 	if (error)
@@ -3758,3 +3751,29 @@ xfs_inode_reload_unlinked(
 
 	return error;
 }
+
+/* Has this inode fork been zapped by repair? */
+bool
+xfs_ifork_zapped(
+	const struct xfs_inode	*ip,
+	int			whichfork)
+{
+	unsigned int		datamask = 0;
+
+	switch (whichfork) {
+	case XFS_DATA_FORK:
+		switch (ip->i_vnode.i_mode & S_IFMT) {
+		case S_IFDIR:
+			datamask = XFS_SICK_INO_DIR_ZAPPED;
+			break;
+		case S_IFLNK:
+			datamask = XFS_SICK_INO_SYMLINK_ZAPPED;
+			break;
+		}
+		return ip->i_sick & (XFS_SICK_INO_BMBTD_ZAPPED | datamask);
+	case XFS_ATTR_FORK:
+		return ip->i_sick & XFS_SICK_INO_BMBTA_ZAPPED;
+	default:
+		return false;
+	}
+}
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 3dc47937da5d..97f63bacd4c2 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -569,6 +569,14 @@ extern void xfs_setup_inode(struct xfs_inode *ip);
 extern void xfs_setup_iops(struct xfs_inode *ip);
 extern void xfs_diflags_to_iflags(struct xfs_inode *ip, bool init);
 
+static inline void xfs_update_stable_writes(struct xfs_inode *ip)
+{
+	if (bdev_stable_writes(xfs_inode_buftarg(ip)->bt_bdev))
+		mapping_set_stable_writes(VFS_I(ip)->i_mapping);
+	else
+		mapping_clear_stable_writes(VFS_I(ip)->i_mapping);
+}
+
 /*
  * When setting up a newly allocated inode, we need to call
  * xfs_finish_inode_setup() once the inode is fully instantiated at
@@ -614,4 +622,6 @@ xfs_inode_unlinked_incomplete(
 int xfs_inode_reload_unlinked_bucket(struct xfs_trans *tp, struct xfs_inode *ip);
 int xfs_inode_reload_unlinked(struct xfs_inode *ip);
 
+bool xfs_ifork_zapped(const struct xfs_inode *ip, int whichfork);
+
 #endif	/* __XFS_INODE_H__ */
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index cd7803fda8b1..0aee97ba0be8 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -352,11 +352,10 @@ xfs_inode_item_format_data_fork(
 			~(XFS_ILOG_DEXT | XFS_ILOG_DBROOT | XFS_ILOG_DEV);
 		if ((iip->ili_fields & XFS_ILOG_DDATA) &&
 		    ip->i_df.if_bytes > 0) {
-			ASSERT(ip->i_df.if_u1.if_data != NULL);
+			ASSERT(ip->i_df.if_data != NULL);
 			ASSERT(ip->i_disk_size > 0);
 			xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_ILOCAL,
-					ip->i_df.if_u1.if_data,
-					ip->i_df.if_bytes);
+					ip->i_df.if_data, ip->i_df.if_bytes);
 			ilf->ilf_dsize = (unsigned)ip->i_df.if_bytes;
 			ilf->ilf_size++;
 		} else {
@@ -431,10 +430,9 @@ xfs_inode_item_format_attr_fork(
 
 		if ((iip->ili_fields & XFS_ILOG_ADATA) &&
 		    ip->i_af.if_bytes > 0) {
-			ASSERT(ip->i_af.if_u1.if_data != NULL);
+			ASSERT(ip->i_af.if_data != NULL);
 			xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_LOCAL,
-					ip->i_af.if_u1.if_data,
-					ip->i_af.if_bytes);
+					ip->i_af.if_data, ip->i_af.if_bytes);
 			ilf->ilf_asize = (unsigned)ip->i_af.if_bytes;
 			ilf->ilf_size++;
 		} else {
@@ -557,6 +555,9 @@ xfs_inode_to_log_dinode(
 		memset(to->di_pad2, 0, sizeof(to->di_pad2));
 		uuid_copy(&to->di_uuid, &ip->i_mount->m_sb.sb_meta_uuid);
 		to->di_v3_pad = 0;
+
+		/* dummy value for initialisation */
+		to->di_crc = 0;
 	} else {
 		to->di_version = 2;
 		to->di_flushiter = ip->i_flushiter;
diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c
index 0e5dba2343ea..144198a6b270 100644
--- a/fs/xfs/xfs_inode_item_recover.c
+++ b/fs/xfs/xfs_inode_item_recover.c
@@ -286,6 +286,7 @@ xlog_recover_inode_commit_pass2(
 	struct xfs_log_dinode		*ldip;
 	uint				isize;
 	int				need_free = 0;
+	xfs_failaddr_t			fa;
 
 	if (item->ri_buf[0].i_len == sizeof(struct xfs_inode_log_format)) {
 		in_f = item->ri_buf[0].i_addr;
@@ -369,24 +370,26 @@ xlog_recover_inode_commit_pass2(
 	 * superblock flag to determine whether we need to look at di_flushiter
 	 * to skip replay when the on disk inode is newer than the log one
 	 */
-	if (!xfs_has_v3inodes(mp) &&
-	    ldip->di_flushiter < be16_to_cpu(dip->di_flushiter)) {
-		/*
-		 * Deal with the wrap case, DI_MAX_FLUSH is less
-		 * than smaller numbers
-		 */
-		if (be16_to_cpu(dip->di_flushiter) == DI_MAX_FLUSH &&
-		    ldip->di_flushiter < (DI_MAX_FLUSH >> 1)) {
-			/* do nothing */
-		} else {
-			trace_xfs_log_recover_inode_skip(log, in_f);
-			error = 0;
-			goto out_release;
+	if (!xfs_has_v3inodes(mp)) {
+		if (ldip->di_flushiter < be16_to_cpu(dip->di_flushiter)) {
+			/*
+			 * Deal with the wrap case, DI_MAX_FLUSH is less
+			 * than smaller numbers
+			 */
+			if (be16_to_cpu(dip->di_flushiter) == DI_MAX_FLUSH &&
+			    ldip->di_flushiter < (DI_MAX_FLUSH >> 1)) {
+				/* do nothing */
+			} else {
+				trace_xfs_log_recover_inode_skip(log, in_f);
+				error = 0;
+				goto out_release;
+			}
 		}
+
+		/* Take the opportunity to reset the flush iteration count */
+		ldip->di_flushiter = 0;
 	}
 
-	/* Take the opportunity to reset the flush iteration count */
-	ldip->di_flushiter = 0;
 
 	if (unlikely(S_ISREG(ldip->di_mode))) {
 		if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) &&
@@ -528,8 +531,19 @@ out_owner_change:
 	    (dip->di_mode != 0))
 		error = xfs_recover_inode_owner_change(mp, dip, in_f,
 						       buffer_list);
-	/* re-generate the checksum. */
+	/* re-generate the checksum and validate the recovered inode. */
 	xfs_dinode_calc_crc(log->l_mp, dip);
+	fa = xfs_dinode_verify(log->l_mp, in_f->ilf_ino, dip);
+	if (fa) {
+		XFS_CORRUPTION_ERROR(
+			"Bad dinode after recovery",
+				XFS_ERRLEVEL_LOW, mp, dip, sizeof(*dip));
+		xfs_alert(mp,
+			"Metadata corruption detected at %pS, inode 0x%llx",
+			fa, in_f->ilf_ino);
+		error = -EFSCORRUPTED;
+		goto out_release;
+	}
 
 	ASSERT(bp->b_mount == mp);
 	bp->b_flags |= _XBF_LOGRECOVERY;
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index a82470e027f7..f02b6e558af5 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1121,23 +1121,25 @@ xfs_ioctl_setattr_xflags(
 	struct fileattr		*fa)
 {
 	struct xfs_mount	*mp = ip->i_mount;
+	bool			rtflag = (fa->fsx_xflags & FS_XFLAG_REALTIME);
 	uint64_t		i_flags2;
 
-	/* Can't change realtime flag if any extents are allocated. */
-	if ((ip->i_df.if_nextents || ip->i_delayed_blks) &&
-	    XFS_IS_REALTIME_INODE(ip) != (fa->fsx_xflags & FS_XFLAG_REALTIME))
-		return -EINVAL;
+	if (rtflag != XFS_IS_REALTIME_INODE(ip)) {
+		/* Can't change realtime flag if any extents are allocated. */
+		if (ip->i_df.if_nextents || ip->i_delayed_blks)
+			return -EINVAL;
+	}
 
-	/* If realtime flag is set then must have realtime device */
-	if (fa->fsx_xflags & FS_XFLAG_REALTIME) {
+	if (rtflag) {
+		/* If realtime flag is set then must have realtime device */
 		if (mp->m_sb.sb_rblocks == 0 || mp->m_sb.sb_rextsize == 0 ||
 		    xfs_extlen_to_rtxmod(mp, ip->i_extsize))
 			return -EINVAL;
-	}
 
-	/* Clear reflink if we are actually able to set the rt flag. */
-	if ((fa->fsx_xflags & FS_XFLAG_REALTIME) && xfs_is_reflink_inode(ip))
-		ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+		/* Clear reflink if we are actually able to set the rt flag. */
+		if (xfs_is_reflink_inode(ip))
+			ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+	}
 
 	/* diflags2 only valid for v3 inodes. */
 	i_flags2 = xfs_flags2diflags2(ip, fa->fsx_xflags);
@@ -1148,6 +1150,14 @@ xfs_ioctl_setattr_xflags(
 	ip->i_diflags2 = i_flags2;
 
 	xfs_diflags_to_iflags(ip, false);
+
+	/*
+	 * Make the stable writes flag match that of the device the inode
+	 * resides on when flipping the RT flag.
+	 */
+	if (rtflag != XFS_IS_REALTIME_INODE(ip) && S_ISREG(VFS_I(ip)->i_mode))
+		xfs_update_stable_writes(ip);
+
 	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 	XFS_STATS_INC(mp, xs_ig_attrchg);
@@ -1862,6 +1872,63 @@ xfs_fs_eofblocks_from_user(
 	return 0;
 }
 
+static int
+xfs_ioctl_getset_resblocks(
+	struct file		*filp,
+	unsigned int		cmd,
+	void __user		*arg)
+{
+	struct xfs_mount	*mp = XFS_I(file_inode(filp))->i_mount;
+	struct xfs_fsop_resblks	fsop = { };
+	int			error;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (cmd == XFS_IOC_SET_RESBLKS) {
+		if (xfs_is_readonly(mp))
+			return -EROFS;
+
+		if (copy_from_user(&fsop, arg, sizeof(fsop)))
+			return -EFAULT;
+
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
+		error = xfs_reserve_blocks(mp, fsop.resblks);
+		mnt_drop_write_file(filp);
+		if (error)
+			return error;
+	}
+
+	spin_lock(&mp->m_sb_lock);
+	fsop.resblks = mp->m_resblks;
+	fsop.resblks_avail = mp->m_resblks_avail;
+	spin_unlock(&mp->m_sb_lock);
+
+	if (copy_to_user(arg, &fsop, sizeof(fsop)))
+		return -EFAULT;
+	return 0;
+}
+
+static int
+xfs_ioctl_fs_counts(
+	struct xfs_mount	*mp,
+	struct xfs_fsop_counts __user	*uarg)
+{
+	struct xfs_fsop_counts	out = {
+		.allocino = percpu_counter_read_positive(&mp->m_icount),
+		.freeino  = percpu_counter_read_positive(&mp->m_ifree),
+		.freedata = percpu_counter_read_positive(&mp->m_fdblocks) -
+				xfs_fdblocks_unavailable(mp),
+		.freertx  = percpu_counter_read_positive(&mp->m_frextents),
+	};
+
+	if (copy_to_user(uarg, &out, sizeof(out)))
+		return -EFAULT;
+	return 0;
+}
+
 /*
  * These long-unused ioctls were removed from the official ioctl API in 5.17,
  * but retain these definitions so that we can log warnings about them.
@@ -1998,60 +2065,12 @@ xfs_file_ioctl(
 		return error;
 	}
 
-	case XFS_IOC_FSCOUNTS: {
-		xfs_fsop_counts_t out;
-
-		xfs_fs_counts(mp, &out);
-
-		if (copy_to_user(arg, &out, sizeof(out)))
-			return -EFAULT;
-		return 0;
-	}
-
-	case XFS_IOC_SET_RESBLKS: {
-		xfs_fsop_resblks_t inout;
-		uint64_t	   in;
-
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
-
-		if (xfs_is_readonly(mp))
-			return -EROFS;
-
-		if (copy_from_user(&inout, arg, sizeof(inout)))
-			return -EFAULT;
-
-		error = mnt_want_write_file(filp);
-		if (error)
-			return error;
-
-		/* input parameter is passed in resblks field of structure */
-		in = inout.resblks;
-		error = xfs_reserve_blocks(mp, &in, &inout);
-		mnt_drop_write_file(filp);
-		if (error)
-			return error;
-
-		if (copy_to_user(arg, &inout, sizeof(inout)))
-			return -EFAULT;
-		return 0;
-	}
-
-	case XFS_IOC_GET_RESBLKS: {
-		xfs_fsop_resblks_t out;
+	case XFS_IOC_FSCOUNTS:
+		return xfs_ioctl_fs_counts(mp, arg);
 
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
-
-		error = xfs_reserve_blocks(mp, NULL, &out);
-		if (error)
-			return error;
-
-		if (copy_to_user(arg, &out, sizeof(out)))
-			return -EFAULT;
-
-		return 0;
-	}
+	case XFS_IOC_SET_RESBLKS:
+	case XFS_IOC_GET_RESBLKS:
+		return xfs_ioctl_getset_resblocks(filp, cmd, arg);
 
 	case XFS_IOC_FSGROWFSDATA: {
 		struct xfs_growfs_data in;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index fdfda4fba12b..a0d77f5f512e 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -1299,6 +1299,13 @@ xfs_setup_inode(
 	mapping_set_gfp_mask(inode->i_mapping, (gfp_mask & ~(__GFP_FS)));
 
 	/*
+	 * For real-time inodes update the stable write flags to that of the RT
+	 * device instead of the data device.
+	 */
+	if (S_ISREG(inode->i_mode) && XFS_IS_REALTIME_INODE(ip))
+		xfs_update_stable_writes(ip);
+
+	/*
 	 * If there is no attribute fork no ACL can exist on this inode,
 	 * and it can't have any file capabilities attached to it either.
 	 */
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 51c100c86177..a1650fc81382 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1542,6 +1542,7 @@ xlog_alloc_log(
 	log->l_covered_state = XLOG_STATE_COVER_IDLE;
 	set_bit(XLOG_ACTIVE_RECOVERY, &log->l_opstate);
 	INIT_DELAYED_WORK(&log->l_work, xfs_log_worker);
+	INIT_LIST_HEAD(&log->r_dfops);
 
 	log->l_prev_block  = -1;
 	/* log->l_tail_lsn = 0x100000000LL; cycle = 1; current block = 0 */
@@ -1893,9 +1894,7 @@ xlog_write_iclog(
 		 * the buffer manually, the code needs to be kept in sync
 		 * with the I/O completion path.
 		 */
-		xlog_state_done_syncing(iclog);
-		up(&iclog->ic_sema);
-		return;
+		goto sync;
 	}
 
 	/*
@@ -1925,20 +1924,17 @@ xlog_write_iclog(
 		 * avoid shutdown re-entering this path and erroring out again.
 		 */
 		if (log->l_targ != log->l_mp->m_ddev_targp &&
-		    blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev)) {
-			xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR);
-			return;
-		}
+		    blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev))
+			goto shutdown;
 	}
 	if (iclog->ic_flags & XLOG_ICL_NEED_FUA)
 		iclog->ic_bio.bi_opf |= REQ_FUA;
 
 	iclog->ic_flags &= ~(XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA);
 
-	if (xlog_map_iclog_data(&iclog->ic_bio, iclog->ic_data, count)) {
-		xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR);
-		return;
-	}
+	if (xlog_map_iclog_data(&iclog->ic_bio, iclog->ic_data, count))
+		goto shutdown;
+
 	if (is_vmalloc_addr(iclog->ic_data))
 		flush_kernel_vmap_range(iclog->ic_data, count);
 
@@ -1959,6 +1955,12 @@ xlog_write_iclog(
 	}
 
 	submit_bio(&iclog->ic_bio);
+	return;
+shutdown:
+	xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR);
+sync:
+	xlog_state_done_syncing(iclog);
+	up(&iclog->ic_sema);
 }
 
 /*
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index fa3ad1d7b31c..e30c06ec20e3 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -407,6 +407,7 @@ struct xlog {
 	long			l_opstate;	/* operational state */
 	uint			l_quotaoffs_flag; /* XFS_DQ_*, for QUOTAOFFs */
 	struct list_head	*l_buf_cancel_table;
+	struct list_head	r_dfops;	/* recovered log intent items */
 	int			l_iclog_hsize;  /* size of iclog header */
 	int			l_iclog_heads;  /* # of iclog header sectors */
 	uint			l_sectBBsize;   /* sector size in BBs (2^n) */
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 13b94d2e605b..1251c81e55f9 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1723,30 +1723,24 @@ xlog_clear_stale_blocks(
  */
 void
 xlog_recover_release_intent(
-	struct xlog		*log,
-	unsigned short		intent_type,
-	uint64_t		intent_id)
+	struct xlog			*log,
+	unsigned short			intent_type,
+	uint64_t			intent_id)
 {
-	struct xfs_ail_cursor	cur;
-	struct xfs_log_item	*lip;
-	struct xfs_ail		*ailp = log->l_ailp;
+	struct xfs_defer_pending	*dfp, *n;
+
+	list_for_each_entry_safe(dfp, n, &log->r_dfops, dfp_list) {
+		struct xfs_log_item	*lip = dfp->dfp_intent;
 
-	spin_lock(&ailp->ail_lock);
-	for (lip = xfs_trans_ail_cursor_first(ailp, &cur, 0); lip != NULL;
-	     lip = xfs_trans_ail_cursor_next(ailp, &cur)) {
 		if (lip->li_type != intent_type)
 			continue;
 		if (!lip->li_ops->iop_match(lip, intent_id))
 			continue;
 
-		spin_unlock(&ailp->ail_lock);
-		lip->li_ops->iop_release(lip);
-		spin_lock(&ailp->ail_lock);
-		break;
-	}
+		ASSERT(xlog_item_is_intent(lip));
 
-	xfs_trans_ail_cursor_done(&cur);
-	spin_unlock(&ailp->ail_lock);
+		xfs_defer_cancel_recovery(log->l_mp, dfp);
+	}
 }
 
 int
@@ -1939,6 +1933,29 @@ xlog_buf_readahead(
 		xfs_buf_readahead(log->l_mp->m_ddev_targp, blkno, len, ops);
 }
 
+/*
+ * Create a deferred work structure for resuming and tracking the progress of a
+ * log intent item that was found during recovery.
+ */
+void
+xlog_recover_intent_item(
+	struct xlog			*log,
+	struct xfs_log_item		*lip,
+	xfs_lsn_t			lsn,
+	const struct xfs_defer_op_type	*ops)
+{
+	ASSERT(xlog_item_is_intent(lip));
+
+	xfs_defer_start_recovery(lip, &log->r_dfops, ops);
+
+	/*
+	 * Insert the intent into the AIL directly and drop one reference so
+	 * that finishing or canceling the work will drop the other.
+	 */
+	xfs_trans_ail_insert(log->l_ailp, lip, lsn);
+	lip->li_ops->iop_unpin(lip, 0);
+}
+
 STATIC int
 xlog_recover_items_pass2(
 	struct xlog                     *log,
@@ -2511,7 +2528,7 @@ xlog_abort_defer_ops(
 
 	list_for_each_entry_safe(dfc, next, capture_list, dfc_list) {
 		list_del_init(&dfc->dfc_list);
-		xfs_defer_ops_capture_free(mp, dfc);
+		xfs_defer_ops_capture_abort(mp, dfc);
 	}
 }
 
@@ -2533,36 +2550,26 @@ xlog_abort_defer_ops(
  */
 STATIC int
 xlog_recover_process_intents(
-	struct xlog		*log)
+	struct xlog			*log)
 {
 	LIST_HEAD(capture_list);
-	struct xfs_ail_cursor	cur;
-	struct xfs_log_item	*lip;
-	struct xfs_ail		*ailp;
-	int			error = 0;
+	struct xfs_defer_pending	*dfp, *n;
+	int				error = 0;
 #if defined(DEBUG) || defined(XFS_WARN)
-	xfs_lsn_t		last_lsn;
-#endif
+	xfs_lsn_t			last_lsn;
 
-	ailp = log->l_ailp;
-	spin_lock(&ailp->ail_lock);
-#if defined(DEBUG) || defined(XFS_WARN)
 	last_lsn = xlog_assign_lsn(log->l_curr_cycle, log->l_curr_block);
 #endif
-	for (lip = xfs_trans_ail_cursor_first(ailp, &cur, 0);
-	     lip != NULL;
-	     lip = xfs_trans_ail_cursor_next(ailp, &cur)) {
-		const struct xfs_item_ops	*ops;
 
-		if (!xlog_item_is_intent(lip))
-			break;
+	list_for_each_entry_safe(dfp, n, &log->r_dfops, dfp_list) {
+		ASSERT(xlog_item_is_intent(dfp->dfp_intent));
 
 		/*
 		 * We should never see a redo item with a LSN higher than
 		 * the last transaction we found in the log at the start
 		 * of recovery.
 		 */
-		ASSERT(XFS_LSN_CMP(last_lsn, lip->li_lsn) >= 0);
+		ASSERT(XFS_LSN_CMP(last_lsn, dfp->dfp_intent->li_lsn) >= 0);
 
 		/*
 		 * NOTE: If your intent processing routine can create more
@@ -2571,21 +2578,14 @@ xlog_recover_process_intents(
 		 * replayed in the wrong order!
 		 *
 		 * The recovery function can free the log item, so we must not
-		 * access lip after it returns.
+		 * access dfp->dfp_intent after it returns.  It must dispose of
+		 * @dfp if it returns 0.
 		 */
-		spin_unlock(&ailp->ail_lock);
-		ops = lip->li_ops;
-		error = ops->iop_recover(lip, &capture_list);
-		spin_lock(&ailp->ail_lock);
-		if (error) {
-			trace_xlog_intent_recovery_failed(log->l_mp, error,
-					ops->iop_recover);
+		error = xfs_defer_finish_recovery(log->l_mp, dfp,
+				&capture_list);
+		if (error)
 			break;
-		}
 	}
-
-	xfs_trans_ail_cursor_done(&cur);
-	spin_unlock(&ailp->ail_lock);
 	if (error)
 		goto err;
 
@@ -2606,27 +2606,34 @@ err:
  */
 STATIC void
 xlog_recover_cancel_intents(
-	struct xlog		*log)
+	struct xlog			*log)
 {
-	struct xfs_log_item	*lip;
-	struct xfs_ail_cursor	cur;
-	struct xfs_ail		*ailp;
-
-	ailp = log->l_ailp;
-	spin_lock(&ailp->ail_lock);
-	lip = xfs_trans_ail_cursor_first(ailp, &cur, 0);
-	while (lip != NULL) {
-		if (!xlog_item_is_intent(lip))
-			break;
+	struct xfs_defer_pending	*dfp, *n;
 
-		spin_unlock(&ailp->ail_lock);
-		lip->li_ops->iop_release(lip);
-		spin_lock(&ailp->ail_lock);
-		lip = xfs_trans_ail_cursor_next(ailp, &cur);
+	list_for_each_entry_safe(dfp, n, &log->r_dfops, dfp_list) {
+		ASSERT(xlog_item_is_intent(dfp->dfp_intent));
+
+		xfs_defer_cancel_recovery(log->l_mp, dfp);
 	}
+}
 
-	xfs_trans_ail_cursor_done(&cur);
-	spin_unlock(&ailp->ail_lock);
+/*
+ * Transfer ownership of the recovered pending work to the recovery transaction
+ * and try to finish the work.  If there is more work to be done, the dfp will
+ * remain attached to the transaction.  If not, the dfp is freed.
+ */
+int
+xlog_recover_finish_intent(
+	struct xfs_trans		*tp,
+	struct xfs_defer_pending	*dfp)
+{
+	int				error;
+
+	list_move(&dfp->dfp_list, &tp->t_dfops);
+	error = xfs_defer_finish_one(tp, dfp);
+	if (error == -EAGAIN)
+		return 0;
+	return error;
 }
 
 /*
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index aed5be5508fe..aabb25dc3efa 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -637,7 +637,6 @@ xfs_mountfs(
 	struct xfs_sb		*sbp = &(mp->m_sb);
 	struct xfs_inode	*rip;
 	struct xfs_ino_geometry	*igeo = M_IGEO(mp);
-	uint64_t		resblks;
 	uint			quotamount = 0;
 	uint			quotaflags = 0;
 	int			error = 0;
@@ -974,8 +973,7 @@ xfs_mountfs(
 	 * we were already there on the last unmount. Warn if this occurs.
 	 */
 	if (!xfs_is_readonly(mp)) {
-		resblks = xfs_default_resblks(mp);
-		error = xfs_reserve_blocks(mp, &resblks, NULL);
+		error = xfs_reserve_blocks(mp, xfs_default_resblks(mp));
 		if (error)
 			xfs_warn(mp,
 	"Unable to allocate reserve blocks. Continuing without reserve pool.");
@@ -1053,7 +1051,6 @@ void
 xfs_unmountfs(
 	struct xfs_mount	*mp)
 {
-	uint64_t		resblks;
 	int			error;
 
 	/*
@@ -1090,8 +1087,7 @@ xfs_unmountfs(
 	 * we only every apply deltas to the superblock and hence the incore
 	 * value does not matter....
 	 */
-	resblks = 0;
-	error = xfs_reserve_blocks(mp, &resblks, NULL);
+	error = xfs_reserve_blocks(mp, 0);
 	if (error)
 		xfs_warn(mp, "Unable to free reserved block pool. "
 				"Freespace may not be correct on next mount.");
diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c
index a7daa522e00f..fa50e5308292 100644
--- a/fs/xfs/xfs_notify_failure.c
+++ b/fs/xfs/xfs_notify_failure.c
@@ -22,6 +22,7 @@
 
 #include <linux/mm.h>
 #include <linux/dax.h>
+#include <linux/fs.h>
 
 struct xfs_failure_info {
 	xfs_agblock_t		startblock;
@@ -73,10 +74,16 @@ xfs_dax_failure_fn(
 	struct xfs_mount		*mp = cur->bc_mp;
 	struct xfs_inode		*ip;
 	struct xfs_failure_info		*notify = data;
+	struct address_space		*mapping;
+	pgoff_t				pgoff;
+	unsigned long			pgcnt;
 	int				error = 0;
 
 	if (XFS_RMAP_NON_INODE_OWNER(rec->rm_owner) ||
 	    (rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK))) {
+		/* Continue the query because this isn't a failure. */
+		if (notify->mf_flags & MF_MEM_PRE_REMOVE)
+			return 0;
 		notify->want_shutdown = true;
 		return 0;
 	}
@@ -92,15 +99,61 @@ xfs_dax_failure_fn(
 		return 0;
 	}
 
-	error = mf_dax_kill_procs(VFS_I(ip)->i_mapping,
-				  xfs_failure_pgoff(mp, rec, notify),
-				  xfs_failure_pgcnt(mp, rec, notify),
-				  notify->mf_flags);
+	mapping = VFS_I(ip)->i_mapping;
+	pgoff = xfs_failure_pgoff(mp, rec, notify);
+	pgcnt = xfs_failure_pgcnt(mp, rec, notify);
+
+	/* Continue the rmap query if the inode isn't a dax file. */
+	if (dax_mapping(mapping))
+		error = mf_dax_kill_procs(mapping, pgoff, pgcnt,
+					  notify->mf_flags);
+
+	/* Invalidate the cache in dax pages. */
+	if (notify->mf_flags & MF_MEM_PRE_REMOVE)
+		invalidate_inode_pages2_range(mapping, pgoff,
+					      pgoff + pgcnt - 1);
+
 	xfs_irele(ip);
 	return error;
 }
 
 static int
+xfs_dax_notify_failure_freeze(
+	struct xfs_mount	*mp)
+{
+	struct super_block	*sb = mp->m_super;
+	int			error;
+
+	error = freeze_super(sb, FREEZE_HOLDER_KERNEL);
+	if (error)
+		xfs_emerg(mp, "already frozen by kernel, err=%d", error);
+
+	return error;
+}
+
+static void
+xfs_dax_notify_failure_thaw(
+	struct xfs_mount	*mp,
+	bool			kernel_frozen)
+{
+	struct super_block	*sb = mp->m_super;
+	int			error;
+
+	if (kernel_frozen) {
+		error = thaw_super(sb, FREEZE_HOLDER_KERNEL);
+		if (error)
+			xfs_emerg(mp, "still frozen after notify failure, err=%d",
+				error);
+	}
+
+	/*
+	 * Also thaw userspace call anyway because the device is about to be
+	 * removed immediately.
+	 */
+	thaw_super(sb, FREEZE_HOLDER_USERSPACE);
+}
+
+static int
 xfs_dax_notify_ddev_failure(
 	struct xfs_mount	*mp,
 	xfs_daddr_t		daddr,
@@ -112,15 +165,29 @@ xfs_dax_notify_ddev_failure(
 	struct xfs_btree_cur	*cur = NULL;
 	struct xfs_buf		*agf_bp = NULL;
 	int			error = 0;
+	bool			kernel_frozen = false;
 	xfs_fsblock_t		fsbno = XFS_DADDR_TO_FSB(mp, daddr);
 	xfs_agnumber_t		agno = XFS_FSB_TO_AGNO(mp, fsbno);
 	xfs_fsblock_t		end_fsbno = XFS_DADDR_TO_FSB(mp,
 							     daddr + bblen - 1);
 	xfs_agnumber_t		end_agno = XFS_FSB_TO_AGNO(mp, end_fsbno);
 
+	if (mf_flags & MF_MEM_PRE_REMOVE) {
+		xfs_info(mp, "Device is about to be removed!");
+		/*
+		 * Freeze fs to prevent new mappings from being created.
+		 * - Keep going on if others already hold the kernel forzen.
+		 * - Keep going on if other errors too because this device is
+		 *   starting to fail.
+		 * - If kernel frozen state is hold successfully here, thaw it
+		 *   here as well at the end.
+		 */
+		kernel_frozen = xfs_dax_notify_failure_freeze(mp) == 0;
+	}
+
 	error = xfs_trans_alloc_empty(mp, &tp);
 	if (error)
-		return error;
+		goto out;
 
 	for (; agno <= end_agno; agno++) {
 		struct xfs_rmap_irec	ri_low = { };
@@ -165,11 +232,26 @@ xfs_dax_notify_ddev_failure(
 	}
 
 	xfs_trans_cancel(tp);
-	if (error || notify.want_shutdown) {
+
+	/*
+	 * Shutdown fs from a force umount in pre-remove case which won't fail,
+	 * so errors can be ignored.  Otherwise, shutdown the filesystem with
+	 * CORRUPT flag if error occured or notify.want_shutdown was set during
+	 * RMAP querying.
+	 */
+	if (mf_flags & MF_MEM_PRE_REMOVE)
+		xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT);
+	else if (error || notify.want_shutdown) {
 		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK);
 		if (!error)
 			error = -EFSCORRUPTED;
 	}
+
+out:
+	/* Thaw the fs if it has been frozen before. */
+	if (mf_flags & MF_MEM_PRE_REMOVE)
+		xfs_dax_notify_failure_thaw(mp, kernel_frozen);
+
 	return error;
 }
 
@@ -197,6 +279,14 @@ xfs_dax_notify_failure(
 
 	if (mp->m_logdev_targp && mp->m_logdev_targp->bt_daxdev == dax_dev &&
 	    mp->m_logdev_targp != mp->m_ddev_targp) {
+		/*
+		 * In the pre-remove case the failure notification is attempting
+		 * to trigger a force unmount.  The expectation is that the
+		 * device is still present, but its removal is in progress and
+		 * can not be cancelled, proceed with accessing the log device.
+		 */
+		if (mf_flags & MF_MEM_PRE_REMOVE)
+			return 0;
 		xfs_err(mp, "ondisk log corrupt, shutting down fs!");
 		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK);
 		return -EFSCORRUPTED;
@@ -210,6 +300,12 @@ xfs_dax_notify_failure(
 	ddev_start = mp->m_ddev_targp->bt_dax_part_off;
 	ddev_end = ddev_start + bdev_nr_bytes(mp->m_ddev_targp->bt_bdev) - 1;
 
+	/* Notify failure on the whole device. */
+	if (offset == 0 && len == U64_MAX) {
+		offset = ddev_start;
+		len = bdev_nr_bytes(mp->m_ddev_targp->bt_bdev);
+	}
+
 	/* Ignore the range out of filesystem area */
 	if (offset + len - 1 < ddev_start)
 		return -ENXIO;
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 94a7932ac570..67d0a8564ff3 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -171,7 +171,7 @@ xfs_qm_dqpurge(
 	 * hits zero, so it really should be on the freelist here.
 	 */
 	ASSERT(!list_empty(&dqp->q_lru));
-	list_lru_del(&qi->qi_lru, &dqp->q_lru);
+	list_lru_del_obj(&qi->qi_lru, &dqp->q_lru);
 	XFS_STATS_DEC(dqp->q_mount, xs_qm_dquot_unused);
 
 	xfs_qm_dqdestroy(dqp);
diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h
index dcc785fdd345..e0d56489f3b2 100644
--- a/fs/xfs/xfs_quota.h
+++ b/fs/xfs/xfs_quota.h
@@ -127,7 +127,10 @@ xfs_qm_vop_dqalloc(struct xfs_inode *ip, kuid_t kuid, kgid_t kgid,
 }
 #define xfs_trans_dup_dqinfo(tp, tp2)
 #define xfs_trans_free_dqinfo(tp)
-#define xfs_trans_mod_dquot_byino(tp, ip, fields, delta) do { } while (0)
+static inline void xfs_trans_mod_dquot_byino(struct xfs_trans *tp,
+		struct xfs_inode *ip, uint field, int64_t delta)
+{
+}
 #define xfs_trans_apply_dquot_deltas(tp)
 #define xfs_trans_unreserve_and_mod_dquots(tp)
 static inline int xfs_trans_reserve_quota_nblks(struct xfs_trans *tp,
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index 2d4444d61e98..20ad8086da60 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -227,52 +227,6 @@ static const struct xfs_item_ops xfs_cud_item_ops = {
 	.iop_intent	= xfs_cud_item_intent,
 };
 
-static struct xfs_cud_log_item *
-xfs_trans_get_cud(
-	struct xfs_trans		*tp,
-	struct xfs_cui_log_item		*cuip)
-{
-	struct xfs_cud_log_item		*cudp;
-
-	cudp = kmem_cache_zalloc(xfs_cud_cache, GFP_KERNEL | __GFP_NOFAIL);
-	xfs_log_item_init(tp->t_mountp, &cudp->cud_item, XFS_LI_CUD,
-			  &xfs_cud_item_ops);
-	cudp->cud_cuip = cuip;
-	cudp->cud_format.cud_cui_id = cuip->cui_format.cui_id;
-
-	xfs_trans_add_item(tp, &cudp->cud_item);
-	return cudp;
-}
-
-/*
- * Finish an refcount update and log it to the CUD. Note that the
- * transaction is marked dirty regardless of whether the refcount
- * update succeeds or fails to support the CUI/CUD lifecycle rules.
- */
-static int
-xfs_trans_log_finish_refcount_update(
-	struct xfs_trans		*tp,
-	struct xfs_cud_log_item		*cudp,
-	struct xfs_refcount_intent	*ri,
-	struct xfs_btree_cur		**pcur)
-{
-	int				error;
-
-	error = xfs_refcount_finish_one(tp, ri, pcur);
-
-	/*
-	 * Mark the transaction dirty, even on error. This ensures the
-	 * transaction is aborted, which:
-	 *
-	 * 1.) releases the CUI and frees the CUD
-	 * 2.) shuts down the filesystem
-	 */
-	tp->t_flags |= XFS_TRANS_DIRTY | XFS_TRANS_HAS_INTENT_DONE;
-	set_bit(XFS_LI_DIRTY, &cudp->cud_item.li_flags);
-
-	return error;
-}
-
 /* Sort refcount intents by AG. */
 static int
 xfs_refcount_update_diff_items(
@@ -318,9 +272,6 @@ xfs_refcount_update_log_item(
 	uint				next_extent;
 	struct xfs_phys_extent		*pmap;
 
-	tp->t_flags |= XFS_TRANS_DIRTY;
-	set_bit(XFS_LI_DIRTY, &cuip->cui_item.li_flags);
-
 	/*
 	 * atomic_inc_return gives us the value after the increment;
 	 * we want to use it as an array index so we need to subtract 1 from
@@ -347,7 +298,6 @@ xfs_refcount_update_create_intent(
 
 	ASSERT(count > 0);
 
-	xfs_trans_add_item(tp, &cuip->cui_item);
 	if (sort)
 		list_sort(mp, items, xfs_refcount_update_diff_items);
 	list_for_each_entry(ri, items, ri_list)
@@ -362,7 +312,16 @@ xfs_refcount_update_create_done(
 	struct xfs_log_item		*intent,
 	unsigned int			count)
 {
-	return &xfs_trans_get_cud(tp, CUI_ITEM(intent))->cud_item;
+	struct xfs_cui_log_item		*cuip = CUI_ITEM(intent);
+	struct xfs_cud_log_item		*cudp;
+
+	cudp = kmem_cache_zalloc(xfs_cud_cache, GFP_KERNEL | __GFP_NOFAIL);
+	xfs_log_item_init(tp->t_mountp, &cudp->cud_item, XFS_LI_CUD,
+			  &xfs_cud_item_ops);
+	cudp->cud_cuip = cuip;
+	cudp->cud_format.cud_cui_id = cuip->cui_format.cui_id;
+
+	return &cudp->cud_item;
 }
 
 /* Take a passive ref to the AG containing the space we're refcounting. */
@@ -397,10 +356,9 @@ xfs_refcount_update_finish_item(
 	int				error;
 
 	ri = container_of(item, struct xfs_refcount_intent, ri_list);
-	error = xfs_trans_log_finish_refcount_update(tp, CUD_ITEM(done), ri,
-			state);
 
 	/* Did we run out of reservation?  Requeue what we didn't finish. */
+	error = xfs_refcount_finish_one(tp, ri, state);
 	if (!error && ri->ri_blockcount > 0) {
 		ASSERT(ri->ri_type == XFS_REFCOUNT_INCREASE ||
 		       ri->ri_type == XFS_REFCOUNT_DECREASE);
@@ -433,16 +391,6 @@ xfs_refcount_update_cancel_item(
 	kmem_cache_free(xfs_refcount_intent_cache, ri);
 }
 
-const struct xfs_defer_op_type xfs_refcount_update_defer_type = {
-	.max_items	= XFS_CUI_MAX_FAST_EXTENTS,
-	.create_intent	= xfs_refcount_update_create_intent,
-	.abort_intent	= xfs_refcount_update_abort_intent,
-	.create_done	= xfs_refcount_update_create_done,
-	.finish_item	= xfs_refcount_update_finish_item,
-	.finish_cleanup = xfs_refcount_finish_one_cleanup,
-	.cancel_item	= xfs_refcount_update_cancel_item,
-};
-
 /* Is this recovered CUI ok? */
 static inline bool
 xfs_cui_validate_phys(
@@ -468,23 +416,38 @@ xfs_cui_validate_phys(
 	return xfs_verify_fsbext(mp, pmap->pe_startblock, pmap->pe_len);
 }
 
+static inline void
+xfs_cui_recover_work(
+	struct xfs_mount		*mp,
+	struct xfs_defer_pending	*dfp,
+	struct xfs_phys_extent		*pmap)
+{
+	struct xfs_refcount_intent	*ri;
+
+	ri = kmem_cache_alloc(xfs_refcount_intent_cache,
+			GFP_NOFS | __GFP_NOFAIL);
+	ri->ri_type = pmap->pe_flags & XFS_REFCOUNT_EXTENT_TYPE_MASK;
+	ri->ri_startblock = pmap->pe_startblock;
+	ri->ri_blockcount = pmap->pe_len;
+	xfs_refcount_update_get_group(mp, ri);
+
+	xfs_defer_add_item(dfp, &ri->ri_list);
+}
+
 /*
  * Process a refcount update intent item that was recovered from the log.
  * We need to update the refcountbt.
  */
 STATIC int
-xfs_cui_item_recover(
-	struct xfs_log_item		*lip,
+xfs_refcount_recover_work(
+	struct xfs_defer_pending	*dfp,
 	struct list_head		*capture_list)
 {
 	struct xfs_trans_res		resv;
+	struct xfs_log_item		*lip = dfp->dfp_intent;
 	struct xfs_cui_log_item		*cuip = CUI_ITEM(lip);
-	struct xfs_cud_log_item		*cudp;
 	struct xfs_trans		*tp;
-	struct xfs_btree_cur		*rcur = NULL;
 	struct xfs_mount		*mp = lip->li_log->l_mp;
-	unsigned int			refc_type;
-	bool				requeue_only = false;
 	int				i;
 	int				error = 0;
 
@@ -501,6 +464,8 @@ xfs_cui_item_recover(
 					sizeof(cuip->cui_format));
 			return -EFSCORRUPTED;
 		}
+
+		xfs_cui_recover_work(mp, dfp, &cuip->cui_format.cui_extents[i]);
 	}
 
 	/*
@@ -521,100 +486,28 @@ xfs_cui_item_recover(
 	if (error)
 		return error;
 
-	cudp = xfs_trans_get_cud(tp, cuip);
-
-	for (i = 0; i < cuip->cui_format.cui_nextents; i++) {
-		struct xfs_refcount_intent	fake = { };
-		struct xfs_phys_extent		*pmap;
-
-		pmap = &cuip->cui_format.cui_extents[i];
-		refc_type = pmap->pe_flags & XFS_REFCOUNT_EXTENT_TYPE_MASK;
-		switch (refc_type) {
-		case XFS_REFCOUNT_INCREASE:
-		case XFS_REFCOUNT_DECREASE:
-		case XFS_REFCOUNT_ALLOC_COW:
-		case XFS_REFCOUNT_FREE_COW:
-			fake.ri_type = refc_type;
-			break;
-		default:
-			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
-					&cuip->cui_format,
-					sizeof(cuip->cui_format));
-			error = -EFSCORRUPTED;
-			goto abort_error;
-		}
-
-		fake.ri_startblock = pmap->pe_startblock;
-		fake.ri_blockcount = pmap->pe_len;
-
-		if (!requeue_only) {
-			xfs_refcount_update_get_group(mp, &fake);
-			error = xfs_trans_log_finish_refcount_update(tp, cudp,
-					&fake, &rcur);
-			xfs_refcount_update_put_group(&fake);
-		}
-		if (error == -EFSCORRUPTED)
-			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
-					&cuip->cui_format,
-					sizeof(cuip->cui_format));
-		if (error)
-			goto abort_error;
-
-		/* Requeue what we didn't finish. */
-		if (fake.ri_blockcount > 0) {
-			struct xfs_bmbt_irec	irec = {
-				.br_startblock	= fake.ri_startblock,
-				.br_blockcount	= fake.ri_blockcount,
-			};
-
-			switch (fake.ri_type) {
-			case XFS_REFCOUNT_INCREASE:
-				xfs_refcount_increase_extent(tp, &irec);
-				break;
-			case XFS_REFCOUNT_DECREASE:
-				xfs_refcount_decrease_extent(tp, &irec);
-				break;
-			case XFS_REFCOUNT_ALLOC_COW:
-				xfs_refcount_alloc_cow_extent(tp,
-						irec.br_startblock,
-						irec.br_blockcount);
-				break;
-			case XFS_REFCOUNT_FREE_COW:
-				xfs_refcount_free_cow_extent(tp,
-						irec.br_startblock,
-						irec.br_blockcount);
-				break;
-			default:
-				ASSERT(0);
-			}
-			requeue_only = true;
-		}
-	}
+	error = xlog_recover_finish_intent(tp, dfp);
+	if (error == -EFSCORRUPTED)
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				&cuip->cui_format,
+				sizeof(cuip->cui_format));
+	if (error)
+		goto abort_error;
 
-	xfs_refcount_finish_one_cleanup(tp, rcur, error);
 	return xfs_defer_ops_capture_and_commit(tp, capture_list);
 
 abort_error:
-	xfs_refcount_finish_one_cleanup(tp, rcur, error);
 	xfs_trans_cancel(tp);
 	return error;
 }
 
-STATIC bool
-xfs_cui_item_match(
-	struct xfs_log_item	*lip,
-	uint64_t		intent_id)
-{
-	return CUI_ITEM(lip)->cui_format.cui_id == intent_id;
-}
-
 /* Relog an intent item to push the log tail forward. */
 static struct xfs_log_item *
-xfs_cui_item_relog(
+xfs_refcount_relog_intent(
+	struct xfs_trans		*tp,
 	struct xfs_log_item		*intent,
-	struct xfs_trans		*tp)
+	struct xfs_log_item		*done_item)
 {
-	struct xfs_cud_log_item		*cudp;
 	struct xfs_cui_log_item		*cuip;
 	struct xfs_phys_extent		*pmap;
 	unsigned int			count;
@@ -622,27 +515,41 @@ xfs_cui_item_relog(
 	count = CUI_ITEM(intent)->cui_format.cui_nextents;
 	pmap = CUI_ITEM(intent)->cui_format.cui_extents;
 
-	tp->t_flags |= XFS_TRANS_DIRTY;
-	cudp = xfs_trans_get_cud(tp, CUI_ITEM(intent));
-	set_bit(XFS_LI_DIRTY, &cudp->cud_item.li_flags);
-
 	cuip = xfs_cui_init(tp->t_mountp, count);
 	memcpy(cuip->cui_format.cui_extents, pmap, count * sizeof(*pmap));
 	atomic_set(&cuip->cui_next_extent, count);
-	xfs_trans_add_item(tp, &cuip->cui_item);
-	set_bit(XFS_LI_DIRTY, &cuip->cui_item.li_flags);
+
 	return &cuip->cui_item;
 }
 
+const struct xfs_defer_op_type xfs_refcount_update_defer_type = {
+	.name		= "refcount",
+	.max_items	= XFS_CUI_MAX_FAST_EXTENTS,
+	.create_intent	= xfs_refcount_update_create_intent,
+	.abort_intent	= xfs_refcount_update_abort_intent,
+	.create_done	= xfs_refcount_update_create_done,
+	.finish_item	= xfs_refcount_update_finish_item,
+	.finish_cleanup = xfs_refcount_finish_one_cleanup,
+	.cancel_item	= xfs_refcount_update_cancel_item,
+	.recover_work	= xfs_refcount_recover_work,
+	.relog_intent	= xfs_refcount_relog_intent,
+};
+
+STATIC bool
+xfs_cui_item_match(
+	struct xfs_log_item	*lip,
+	uint64_t		intent_id)
+{
+	return CUI_ITEM(lip)->cui_format.cui_id == intent_id;
+}
+
 static const struct xfs_item_ops xfs_cui_item_ops = {
 	.flags		= XFS_ITEM_INTENT,
 	.iop_size	= xfs_cui_item_size,
 	.iop_format	= xfs_cui_item_format,
 	.iop_unpin	= xfs_cui_item_unpin,
 	.iop_release	= xfs_cui_item_release,
-	.iop_recover	= xfs_cui_item_recover,
 	.iop_match	= xfs_cui_item_match,
-	.iop_relog	= xfs_cui_item_relog,
 };
 
 static inline void
@@ -696,12 +603,9 @@ xlog_recover_cui_commit_pass2(
 	cuip = xfs_cui_init(mp, cui_formatp->cui_nextents);
 	xfs_cui_copy_format(&cuip->cui_format, cui_formatp);
 	atomic_set(&cuip->cui_next_extent, cui_formatp->cui_nextents);
-	/*
-	 * Insert the intent into the AIL directly and drop one reference so
-	 * that finishing or canceling the work will drop the other.
-	 */
-	xfs_trans_ail_insert(log->l_ailp, &cuip->cui_item, lsn);
-	xfs_cui_release(cuip);
+
+	xlog_recover_intent_item(log, &cuip->cui_item, lsn,
+			&xfs_refcount_update_defer_type);
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 658edee8381d..d5ca8bcae65b 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -618,7 +618,7 @@ xfs_reflink_cancel_cow_blocks(
 
 			error = xfs_free_extent_later(*tpp, del.br_startblock,
 					del.br_blockcount, NULL,
-					XFS_AG_RESV_NONE);
+					XFS_AG_RESV_NONE, false);
 			if (error)
 				break;
 
@@ -784,6 +784,7 @@ xfs_reflink_end_cow_extent(
 		}
 	}
 	del = got;
+	xfs_trim_extent(&del, *offset_fsb, end_fsb - *offset_fsb);
 
 	/* Grab the corresponding mapping in the data fork. */
 	nmaps = 1;
diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c
index 0e0e747028da..79ad0087aeca 100644
--- a/fs/xfs/xfs_rmap_item.c
+++ b/fs/xfs/xfs_rmap_item.c
@@ -225,23 +225,6 @@ static const struct xfs_item_ops xfs_rud_item_ops = {
 	.iop_intent	= xfs_rud_item_intent,
 };
 
-static struct xfs_rud_log_item *
-xfs_trans_get_rud(
-	struct xfs_trans		*tp,
-	struct xfs_rui_log_item		*ruip)
-{
-	struct xfs_rud_log_item		*rudp;
-
-	rudp = kmem_cache_zalloc(xfs_rud_cache, GFP_KERNEL | __GFP_NOFAIL);
-	xfs_log_item_init(tp->t_mountp, &rudp->rud_item, XFS_LI_RUD,
-			  &xfs_rud_item_ops);
-	rudp->rud_ruip = ruip;
-	rudp->rud_format.rud_rui_id = ruip->rui_format.rui_id;
-
-	xfs_trans_add_item(tp, &rudp->rud_item);
-	return rudp;
-}
-
 /* Set the map extent flags for this reverse mapping. */
 static void
 xfs_trans_set_rmap_flags(
@@ -285,35 +268,6 @@ xfs_trans_set_rmap_flags(
 	}
 }
 
-/*
- * Finish an rmap update and log it to the RUD. Note that the transaction is
- * marked dirty regardless of whether the rmap update succeeds or fails to
- * support the RUI/RUD lifecycle rules.
- */
-static int
-xfs_trans_log_finish_rmap_update(
-	struct xfs_trans		*tp,
-	struct xfs_rud_log_item		*rudp,
-	struct xfs_rmap_intent		*ri,
-	struct xfs_btree_cur		**pcur)
-{
-	int				error;
-
-	error = xfs_rmap_finish_one(tp, ri, pcur);
-
-	/*
-	 * Mark the transaction dirty, even on error. This ensures the
-	 * transaction is aborted, which:
-	 *
-	 * 1.) releases the RUI and frees the RUD
-	 * 2.) shuts down the filesystem
-	 */
-	tp->t_flags |= XFS_TRANS_DIRTY | XFS_TRANS_HAS_INTENT_DONE;
-	set_bit(XFS_LI_DIRTY, &rudp->rud_item.li_flags);
-
-	return error;
-}
-
 /* Sort rmap intents by AG. */
 static int
 xfs_rmap_update_diff_items(
@@ -340,9 +294,6 @@ xfs_rmap_update_log_item(
 	uint				next_extent;
 	struct xfs_map_extent		*map;
 
-	tp->t_flags |= XFS_TRANS_DIRTY;
-	set_bit(XFS_LI_DIRTY, &ruip->rui_item.li_flags);
-
 	/*
 	 * atomic_inc_return gives us the value after the increment;
 	 * we want to use it as an array index so we need to subtract 1 from
@@ -372,7 +323,6 @@ xfs_rmap_update_create_intent(
 
 	ASSERT(count > 0);
 
-	xfs_trans_add_item(tp, &ruip->rui_item);
 	if (sort)
 		list_sort(mp, items, xfs_rmap_update_diff_items);
 	list_for_each_entry(ri, items, ri_list)
@@ -387,7 +337,16 @@ xfs_rmap_update_create_done(
 	struct xfs_log_item		*intent,
 	unsigned int			count)
 {
-	return &xfs_trans_get_rud(tp, RUI_ITEM(intent))->rud_item;
+	struct xfs_rui_log_item		*ruip = RUI_ITEM(intent);
+	struct xfs_rud_log_item		*rudp;
+
+	rudp = kmem_cache_zalloc(xfs_rud_cache, GFP_KERNEL | __GFP_NOFAIL);
+	xfs_log_item_init(tp->t_mountp, &rudp->rud_item, XFS_LI_RUD,
+			  &xfs_rud_item_ops);
+	rudp->rud_ruip = ruip;
+	rudp->rud_format.rud_rui_id = ruip->rui_format.rui_id;
+
+	return &rudp->rud_item;
 }
 
 /* Take a passive ref to the AG containing the space we're rmapping. */
@@ -423,8 +382,7 @@ xfs_rmap_update_finish_item(
 
 	ri = container_of(item, struct xfs_rmap_intent, ri_list);
 
-	error = xfs_trans_log_finish_rmap_update(tp, RUD_ITEM(done), ri,
-			state);
+	error = xfs_rmap_finish_one(tp, ri, state);
 
 	xfs_rmap_update_put_group(ri);
 	kmem_cache_free(xfs_rmap_intent_cache, ri);
@@ -452,16 +410,6 @@ xfs_rmap_update_cancel_item(
 	kmem_cache_free(xfs_rmap_intent_cache, ri);
 }
 
-const struct xfs_defer_op_type xfs_rmap_update_defer_type = {
-	.max_items	= XFS_RUI_MAX_FAST_EXTENTS,
-	.create_intent	= xfs_rmap_update_create_intent,
-	.abort_intent	= xfs_rmap_update_abort_intent,
-	.create_done	= xfs_rmap_update_create_done,
-	.finish_item	= xfs_rmap_update_finish_item,
-	.finish_cleanup = xfs_rmap_finish_one_cleanup,
-	.cancel_item	= xfs_rmap_update_cancel_item,
-};
-
 /* Is this recovered RUI ok? */
 static inline bool
 xfs_rui_validate_map(
@@ -498,20 +446,72 @@ xfs_rui_validate_map(
 	return xfs_verify_fsbext(mp, map->me_startblock, map->me_len);
 }
 
+static inline void
+xfs_rui_recover_work(
+	struct xfs_mount		*mp,
+	struct xfs_defer_pending	*dfp,
+	const struct xfs_map_extent	*map)
+{
+	struct xfs_rmap_intent		*ri;
+
+	ri = kmem_cache_alloc(xfs_rmap_intent_cache, GFP_NOFS | __GFP_NOFAIL);
+
+	switch (map->me_flags & XFS_RMAP_EXTENT_TYPE_MASK) {
+	case XFS_RMAP_EXTENT_MAP:
+		ri->ri_type = XFS_RMAP_MAP;
+		break;
+	case XFS_RMAP_EXTENT_MAP_SHARED:
+		ri->ri_type = XFS_RMAP_MAP_SHARED;
+		break;
+	case XFS_RMAP_EXTENT_UNMAP:
+		ri->ri_type = XFS_RMAP_UNMAP;
+		break;
+	case XFS_RMAP_EXTENT_UNMAP_SHARED:
+		ri->ri_type = XFS_RMAP_UNMAP_SHARED;
+		break;
+	case XFS_RMAP_EXTENT_CONVERT:
+		ri->ri_type = XFS_RMAP_CONVERT;
+		break;
+	case XFS_RMAP_EXTENT_CONVERT_SHARED:
+		ri->ri_type = XFS_RMAP_CONVERT_SHARED;
+		break;
+	case XFS_RMAP_EXTENT_ALLOC:
+		ri->ri_type = XFS_RMAP_ALLOC;
+		break;
+	case XFS_RMAP_EXTENT_FREE:
+		ri->ri_type = XFS_RMAP_FREE;
+		break;
+	default:
+		ASSERT(0);
+		return;
+	}
+
+	ri->ri_owner = map->me_owner;
+	ri->ri_whichfork = (map->me_flags & XFS_RMAP_EXTENT_ATTR_FORK) ?
+			XFS_ATTR_FORK : XFS_DATA_FORK;
+	ri->ri_bmap.br_startblock = map->me_startblock;
+	ri->ri_bmap.br_startoff = map->me_startoff;
+	ri->ri_bmap.br_blockcount = map->me_len;
+	ri->ri_bmap.br_state = (map->me_flags & XFS_RMAP_EXTENT_UNWRITTEN) ?
+			XFS_EXT_UNWRITTEN : XFS_EXT_NORM;
+	xfs_rmap_update_get_group(mp, ri);
+
+	xfs_defer_add_item(dfp, &ri->ri_list);
+}
+
 /*
  * Process an rmap update intent item that was recovered from the log.
  * We need to update the rmapbt.
  */
 STATIC int
-xfs_rui_item_recover(
-	struct xfs_log_item		*lip,
+xfs_rmap_recover_work(
+	struct xfs_defer_pending	*dfp,
 	struct list_head		*capture_list)
 {
 	struct xfs_trans_res		resv;
+	struct xfs_log_item		*lip = dfp->dfp_intent;
 	struct xfs_rui_log_item		*ruip = RUI_ITEM(lip);
-	struct xfs_rud_log_item		*rudp;
 	struct xfs_trans		*tp;
-	struct xfs_btree_cur		*rcur = NULL;
 	struct xfs_mount		*mp = lip->li_log->l_mp;
 	int				i;
 	int				error = 0;
@@ -529,6 +529,8 @@ xfs_rui_item_recover(
 					sizeof(ruip->rui_format));
 			return -EFSCORRUPTED;
 		}
+
+		xfs_rui_recover_work(mp, dfp, &ruip->rui_format.rui_extents[i]);
 	}
 
 	resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate);
@@ -536,91 +538,29 @@ xfs_rui_item_recover(
 			XFS_TRANS_RESERVE, &tp);
 	if (error)
 		return error;
-	rudp = xfs_trans_get_rud(tp, ruip);
 
-	for (i = 0; i < ruip->rui_format.rui_nextents; i++) {
-		struct xfs_rmap_intent	fake = { };
-		struct xfs_map_extent	*map;
-
-		map = &ruip->rui_format.rui_extents[i];
-		switch (map->me_flags & XFS_RMAP_EXTENT_TYPE_MASK) {
-		case XFS_RMAP_EXTENT_MAP:
-			fake.ri_type = XFS_RMAP_MAP;
-			break;
-		case XFS_RMAP_EXTENT_MAP_SHARED:
-			fake.ri_type = XFS_RMAP_MAP_SHARED;
-			break;
-		case XFS_RMAP_EXTENT_UNMAP:
-			fake.ri_type = XFS_RMAP_UNMAP;
-			break;
-		case XFS_RMAP_EXTENT_UNMAP_SHARED:
-			fake.ri_type = XFS_RMAP_UNMAP_SHARED;
-			break;
-		case XFS_RMAP_EXTENT_CONVERT:
-			fake.ri_type = XFS_RMAP_CONVERT;
-			break;
-		case XFS_RMAP_EXTENT_CONVERT_SHARED:
-			fake.ri_type = XFS_RMAP_CONVERT_SHARED;
-			break;
-		case XFS_RMAP_EXTENT_ALLOC:
-			fake.ri_type = XFS_RMAP_ALLOC;
-			break;
-		case XFS_RMAP_EXTENT_FREE:
-			fake.ri_type = XFS_RMAP_FREE;
-			break;
-		default:
-			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
-					&ruip->rui_format,
-					sizeof(ruip->rui_format));
-			error = -EFSCORRUPTED;
-			goto abort_error;
-		}
-
-		fake.ri_owner = map->me_owner;
-		fake.ri_whichfork = (map->me_flags & XFS_RMAP_EXTENT_ATTR_FORK) ?
-				XFS_ATTR_FORK : XFS_DATA_FORK;
-		fake.ri_bmap.br_startblock = map->me_startblock;
-		fake.ri_bmap.br_startoff = map->me_startoff;
-		fake.ri_bmap.br_blockcount = map->me_len;
-		fake.ri_bmap.br_state = (map->me_flags & XFS_RMAP_EXTENT_UNWRITTEN) ?
-				XFS_EXT_UNWRITTEN : XFS_EXT_NORM;
-
-		xfs_rmap_update_get_group(mp, &fake);
-		error = xfs_trans_log_finish_rmap_update(tp, rudp, &fake,
-				&rcur);
-		if (error == -EFSCORRUPTED)
-			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
-					map, sizeof(*map));
-		xfs_rmap_update_put_group(&fake);
-		if (error)
-			goto abort_error;
-
-	}
+	error = xlog_recover_finish_intent(tp, dfp);
+	if (error == -EFSCORRUPTED)
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				&ruip->rui_format,
+				sizeof(ruip->rui_format));
+	if (error)
+		goto abort_error;
 
-	xfs_rmap_finish_one_cleanup(tp, rcur, error);
 	return xfs_defer_ops_capture_and_commit(tp, capture_list);
 
 abort_error:
-	xfs_rmap_finish_one_cleanup(tp, rcur, error);
 	xfs_trans_cancel(tp);
 	return error;
 }
 
-STATIC bool
-xfs_rui_item_match(
-	struct xfs_log_item	*lip,
-	uint64_t		intent_id)
-{
-	return RUI_ITEM(lip)->rui_format.rui_id == intent_id;
-}
-
 /* Relog an intent item to push the log tail forward. */
 static struct xfs_log_item *
-xfs_rui_item_relog(
+xfs_rmap_relog_intent(
+	struct xfs_trans		*tp,
 	struct xfs_log_item		*intent,
-	struct xfs_trans		*tp)
+	struct xfs_log_item		*done_item)
 {
-	struct xfs_rud_log_item		*rudp;
 	struct xfs_rui_log_item		*ruip;
 	struct xfs_map_extent		*map;
 	unsigned int			count;
@@ -628,27 +568,41 @@ xfs_rui_item_relog(
 	count = RUI_ITEM(intent)->rui_format.rui_nextents;
 	map = RUI_ITEM(intent)->rui_format.rui_extents;
 
-	tp->t_flags |= XFS_TRANS_DIRTY;
-	rudp = xfs_trans_get_rud(tp, RUI_ITEM(intent));
-	set_bit(XFS_LI_DIRTY, &rudp->rud_item.li_flags);
-
 	ruip = xfs_rui_init(tp->t_mountp, count);
 	memcpy(ruip->rui_format.rui_extents, map, count * sizeof(*map));
 	atomic_set(&ruip->rui_next_extent, count);
-	xfs_trans_add_item(tp, &ruip->rui_item);
-	set_bit(XFS_LI_DIRTY, &ruip->rui_item.li_flags);
+
 	return &ruip->rui_item;
 }
 
+const struct xfs_defer_op_type xfs_rmap_update_defer_type = {
+	.name		= "rmap",
+	.max_items	= XFS_RUI_MAX_FAST_EXTENTS,
+	.create_intent	= xfs_rmap_update_create_intent,
+	.abort_intent	= xfs_rmap_update_abort_intent,
+	.create_done	= xfs_rmap_update_create_done,
+	.finish_item	= xfs_rmap_update_finish_item,
+	.finish_cleanup = xfs_rmap_finish_one_cleanup,
+	.cancel_item	= xfs_rmap_update_cancel_item,
+	.recover_work	= xfs_rmap_recover_work,
+	.relog_intent	= xfs_rmap_relog_intent,
+};
+
+STATIC bool
+xfs_rui_item_match(
+	struct xfs_log_item	*lip,
+	uint64_t		intent_id)
+{
+	return RUI_ITEM(lip)->rui_format.rui_id == intent_id;
+}
+
 static const struct xfs_item_ops xfs_rui_item_ops = {
 	.flags		= XFS_ITEM_INTENT,
 	.iop_size	= xfs_rui_item_size,
 	.iop_format	= xfs_rui_item_format,
 	.iop_unpin	= xfs_rui_item_unpin,
 	.iop_release	= xfs_rui_item_release,
-	.iop_recover	= xfs_rui_item_recover,
 	.iop_match	= xfs_rui_item_match,
-	.iop_relog	= xfs_rui_item_relog,
 };
 
 static inline void
@@ -702,12 +656,9 @@ xlog_recover_rui_commit_pass2(
 	ruip = xfs_rui_init(mp, rui_formatp->rui_nextents);
 	xfs_rui_copy_format(&ruip->rui_format, rui_formatp);
 	atomic_set(&ruip->rui_next_extent, rui_formatp->rui_nextents);
-	/*
-	 * Insert the intent into the AIL directly and drop one reference so
-	 * that finishing or canceling the work will drop the other.
-	 */
-	xfs_trans_ail_insert(log->l_ailp, &ruip->rui_item, lsn);
-	xfs_rui_release(ruip);
+
+	xlog_recover_intent_item(log, &ruip->rui_item, lsn,
+			&xfs_rmap_update_defer_type);
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 88c48de5c9c8..8649d981a097 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -14,28 +14,14 @@
 #include "xfs_inode.h"
 #include "xfs_bmap.h"
 #include "xfs_bmap_btree.h"
+#include "xfs_bmap_util.h"
 #include "xfs_trans.h"
 #include "xfs_trans_space.h"
 #include "xfs_icache.h"
 #include "xfs_rtalloc.h"
 #include "xfs_sb.h"
 #include "xfs_rtbitmap.h"
-
-/*
- * Read and return the summary information for a given extent size,
- * bitmap block combination.
- * Keeps track of a current summary block, so we don't keep reading
- * it from the buffer cache.
- */
-static int
-xfs_rtget_summary(
-	struct xfs_rtalloc_args	*args,
-	int			log,	/* log2 of extent size */
-	xfs_fileoff_t		bbno,	/* bitmap block number */
-	xfs_suminfo_t		*sum)	/* out: summary info for this block */
-{
-	return xfs_rtmodify_summary_int(args, log, bbno, 0, sum);
-}
+#include "xfs_quota.h"
 
 /*
  * Return whether there are any free extents in the size range given
@@ -154,56 +140,55 @@ xfs_rtallocate_range(
 	 * properly update the summary.
 	 */
 	error = xfs_rtfind_back(args, start, 0, &preblock);
-	if (error) {
+	if (error)
 		return error;
-	}
+
 	/*
 	 * Find the next allocated block (end of free extent).
 	 */
 	error = xfs_rtfind_forw(args, end, mp->m_sb.sb_rextents - 1,
 			&postblock);
-	if (error) {
+	if (error)
 		return error;
-	}
+
 	/*
 	 * Decrement the summary information corresponding to the entire
 	 * (old) free extent.
 	 */
 	error = xfs_rtmodify_summary(args,
-			XFS_RTBLOCKLOG(postblock + 1 - preblock),
+			xfs_highbit64(postblock + 1 - preblock),
 			xfs_rtx_to_rbmblock(mp, preblock), -1);
-	if (error) {
+	if (error)
 		return error;
-	}
+
 	/*
 	 * If there are blocks not being allocated at the front of the
 	 * old extent, add summary data for them to be free.
 	 */
 	if (preblock < start) {
 		error = xfs_rtmodify_summary(args,
-				XFS_RTBLOCKLOG(start - preblock),
+				xfs_highbit64(start - preblock),
 				xfs_rtx_to_rbmblock(mp, preblock), 1);
-		if (error) {
+		if (error)
 			return error;
-		}
 	}
+
 	/*
 	 * If there are blocks not being allocated at the end of the
 	 * old extent, add summary data for them to be free.
 	 */
 	if (postblock > end) {
 		error = xfs_rtmodify_summary(args,
-				XFS_RTBLOCKLOG(postblock - end),
+				xfs_highbit64(postblock - end),
 				xfs_rtx_to_rbmblock(mp, end + 1), 1);
-		if (error) {
+		if (error)
 			return error;
-		}
 	}
+
 	/*
 	 * Modify the bitmap to mark this extent allocated.
 	 */
-	error = xfs_rtmodify_range(args, start, len, 0);
-	return error;
+	return xfs_rtmodify_range(args, start, len, 0);
 }
 
 /*
@@ -265,21 +250,17 @@ xfs_rtallocate_extent_block(
 		 * If it's not so then next will contain the first non-free.
 		 */
 		error = xfs_rtcheck_range(args, i, maxlen, 1, &next, &stat);
-		if (error) {
+		if (error)
 			return error;
-		}
 		if (stat) {
 			/*
 			 * i for maxlen is all free, allocate and return that.
 			 */
-			error = xfs_rtallocate_range(args, i, maxlen);
-			if (error) {
-				return error;
-			}
-			*len = maxlen;
-			*rtx = i;
-			return 0;
+			bestlen = maxlen;
+			besti = i;
+			goto allocate;
 		}
+
 		/*
 		 * In the case where we have a variable-sized allocation
 		 * request, figure out how big this free piece is,
@@ -298,45 +279,44 @@ xfs_rtallocate_extent_block(
 		/*
 		 * If not done yet, find the start of the next free space.
 		 */
-		if (next < end) {
-			error = xfs_rtfind_forw(args, next, end, &i);
-			if (error) {
-				return error;
-			}
-		} else
+		if (next >= end)
 			break;
+		error = xfs_rtfind_forw(args, next, end, &i);
+		if (error)
+			return error;
 	}
+
 	/*
 	 * Searched the whole thing & didn't find a maxlen free extent.
 	 */
-	if (minlen < maxlen && besti != -1) {
-		xfs_rtxlen_t	p;	/* amount to trim length by */
-
+	if (minlen > maxlen || besti == -1) {
 		/*
-		 * If size should be a multiple of prod, make that so.
+		 * Allocation failed.  Set *nextp to the next block to try.
 		 */
-		if (prod > 1) {
-			div_u64_rem(bestlen, prod, &p);
-			if (p)
-				bestlen -= p;
-		}
+		*nextp = next;
+		return -ENOSPC;
+	}
 
-		/*
-		 * Allocate besti for bestlen & return that.
-		 */
-		error = xfs_rtallocate_range(args, besti, bestlen);
-		if (error) {
-			return error;
-		}
-		*len = bestlen;
-		*rtx = besti;
-		return 0;
+	/*
+	 * If size should be a multiple of prod, make that so.
+	 */
+	if (prod > 1) {
+		xfs_rtxlen_t	p;	/* amount to trim length by */
+
+		div_u64_rem(bestlen, prod, &p);
+		if (p)
+			bestlen -= p;
 	}
+
 	/*
-	 * Allocation failed.  Set *nextp to the next block to try.
+	 * Allocate besti for bestlen & return that.
 	 */
-	*nextp = next;
-	*rtx = NULLRTEXTNO;
+allocate:
+	error = xfs_rtallocate_range(args, besti, bestlen);
+	if (error)
+		return error;
+	*len = bestlen;
+	*rtx = besti;
 	return 0;
 }
 
@@ -367,52 +347,33 @@ xfs_rtallocate_extent_exact(
 	 * Check if the range in question (for maxlen) is free.
 	 */
 	error = xfs_rtcheck_range(args, start, maxlen, 1, &next, &isfree);
-	if (error) {
+	if (error)
 		return error;
-	}
-	if (isfree) {
+
+	if (!isfree) {
 		/*
-		 * If it is, allocate it and return success.
+		 * If not, allocate what there is, if it's at least minlen.
 		 */
-		error = xfs_rtallocate_range(args, start, maxlen);
-		if (error) {
-			return error;
-		}
-		*len = maxlen;
-		*rtx = start;
-		return 0;
-	}
-	/*
-	 * If not, allocate what there is, if it's at least minlen.
-	 */
-	maxlen = next - start;
-	if (maxlen < minlen) {
+		maxlen = next - start;
+		if (maxlen < minlen)
+			return -ENOSPC;
+
 		/*
-		 * Failed, return failure status.
+		 * Trim off tail of extent, if prod is specified.
 		 */
-		*rtx = NULLRTEXTNO;
-		return 0;
-	}
-	/*
-	 * Trim off tail of extent, if prod is specified.
-	 */
-	if (prod > 1 && (i = maxlen % prod)) {
-		maxlen -= i;
-		if (maxlen < minlen) {
-			/*
-			 * Now we can't do it, return failure status.
-			 */
-			*rtx = NULLRTEXTNO;
-			return 0;
+		if (prod > 1 && (i = maxlen % prod)) {
+			maxlen -= i;
+			if (maxlen < minlen)
+				return -ENOSPC;
 		}
 	}
+
 	/*
 	 * Allocate what we can and return it.
 	 */
 	error = xfs_rtallocate_range(args, start, maxlen);
-	if (error) {
+	if (error)
 		return error;
-	}
 	*len = maxlen;
 	*rtx = start;
 	return 0;
@@ -441,7 +402,6 @@ xfs_rtallocate_extent_near(
 	int			j;	/* secondary loop control */
 	int			log2len; /* log2 of minlen */
 	xfs_rtxnum_t		n;	/* next rtext to try */
-	xfs_rtxnum_t		r;	/* result rtext */
 
 	ASSERT(minlen % prod == 0);
 	ASSERT(maxlen % prod == 0);
@@ -455,26 +415,18 @@ xfs_rtallocate_extent_near(
 
 	/* Make sure we don't run off the end of the rt volume. */
 	maxlen = xfs_rtallocate_clamp_len(mp, start, maxlen, prod);
-	if (maxlen < minlen) {
-		*rtx = NULLRTEXTNO;
-		return 0;
-	}
+	if (maxlen < minlen)
+		return -ENOSPC;
 
 	/*
 	 * Try the exact allocation first.
 	 */
 	error = xfs_rtallocate_extent_exact(args, start, minlen, maxlen, len,
-			prod, &r);
-	if (error) {
+			prod, rtx);
+	if (error != -ENOSPC)
 		return error;
-	}
-	/*
-	 * If the exact allocation worked, return that.
-	 */
-	if (r != NULLRTEXTNO) {
-		*rtx = r;
-		return 0;
-	}
+
+
 	bbno = xfs_rtx_to_rbmblock(mp, start);
 	i = 0;
 	j = -1;
@@ -490,9 +442,9 @@ xfs_rtallocate_extent_near(
 		 */
 		error = xfs_rtany_summary(args, log2len, mp->m_rsumlevels - 1,
 				bbno + i, &maxlog);
-		if (error) {
+		if (error)
 			return error;
-		}
+
 		/*
 		 * If there are any useful extents starting here, try
 		 * allocating one.
@@ -511,17 +463,9 @@ xfs_rtallocate_extent_near(
 				 */
 				error = xfs_rtallocate_extent_block(args,
 						bbno + i, minlen, maxavail, len,
-						&n, prod, &r);
-				if (error) {
+						&n, prod, rtx);
+				if (error != -ENOSPC)
 					return error;
-				}
-				/*
-				 * If it worked, return it.
-				 */
-				if (r != NULLRTEXTNO) {
-					*rtx = r;
-					return 0;
-				}
 			}
 			/*
 			 * On the negative side of the starting location.
@@ -555,17 +499,9 @@ xfs_rtallocate_extent_near(
 					error = xfs_rtallocate_extent_block(args,
 							bbno + j, minlen,
 							maxavail, len, &n, prod,
-							&r);
-					if (error) {
+							rtx);
+					if (error != -ENOSPC)
 						return error;
-					}
-					/*
-					 * If it works, return the extent.
-					 */
-					if (r != NULLRTEXTNO) {
-						*rtx = r;
-						return 0;
-					}
 				}
 			}
 		}
@@ -599,8 +535,53 @@ xfs_rtallocate_extent_near(
 		else
 			break;
 	}
-	*rtx = NULLRTEXTNO;
-	return 0;
+	return -ENOSPC;
+}
+
+static int
+xfs_rtalloc_sumlevel(
+	struct xfs_rtalloc_args	*args,
+	int			l,	/* level number */
+	xfs_rtxlen_t		minlen,	/* minimum length to allocate */
+	xfs_rtxlen_t		maxlen,	/* maximum length to allocate */
+	xfs_rtxlen_t		prod,	/* extent product factor */
+	xfs_rtxlen_t		*len,	/* out: actual length allocated */
+	xfs_rtxnum_t		*rtx)	/* out: start rtext allocated */
+{
+	xfs_fileoff_t		i;	/* bitmap block number */
+
+	for (i = 0; i < args->mp->m_sb.sb_rbmblocks; i++) {
+		xfs_suminfo_t	sum;	/* summary information for extents */
+		xfs_rtxnum_t	n;	/* next rtext to be tried */
+		int		error;
+
+		error = xfs_rtget_summary(args, l, i, &sum);
+		if (error)
+			return error;
+
+		/*
+		 * Nothing there, on to the next block.
+		 */
+		if (!sum)
+			continue;
+
+		/*
+		 * Try allocating the extent.
+		 */
+		error = xfs_rtallocate_extent_block(args, i, minlen, maxlen,
+				len, &n, prod, rtx);
+		if (error != -ENOSPC)
+			return error;
+
+		/*
+		 * If the "next block to try" returned from the allocator is
+		 * beyond the next bitmap block, skip to that bitmap block.
+		 */
+		if (xfs_rtx_to_rbmblock(args->mp, n) > i + 1)
+			i = xfs_rtx_to_rbmblock(args->mp, n) - 1;
+	}
+
+	return -ENOSPC;
 }
 
 /*
@@ -617,13 +598,8 @@ xfs_rtallocate_extent_size(
 	xfs_rtxlen_t		prod,	/* extent product factor */
 	xfs_rtxnum_t		*rtx)	/* out: start rtext allocated */
 {
-	struct xfs_mount	*mp = args->mp;
 	int			error;
-	xfs_fileoff_t		i;	/* bitmap block number */
 	int			l;	/* level number (loop control) */
-	xfs_rtxnum_t		n;	/* next rtext to be tried */
-	xfs_rtxnum_t		r;	/* result rtext number */
-	xfs_suminfo_t		sum;	/* summary information for extents */
 
 	ASSERT(minlen % prod == 0);
 	ASSERT(maxlen % prod == 0);
@@ -631,119 +607,46 @@ xfs_rtallocate_extent_size(
 
 	/*
 	 * Loop over all the levels starting with maxlen.
-	 * At each level, look at all the bitmap blocks, to see if there
-	 * are extents starting there that are long enough (>= maxlen).
-	 * Note, only on the initial level can the allocation fail if
-	 * the summary says there's an extent.
+	 *
+	 * At each level, look at all the bitmap blocks, to see if there are
+	 * extents starting there that are long enough (>= maxlen).
+	 *
+	 * Note, only on the initial level can the allocation fail if the
+	 * summary says there's an extent.
 	 */
-	for (l = xfs_highbit32(maxlen); l < mp->m_rsumlevels; l++) {
-		/*
-		 * Loop over all the bitmap blocks.
-		 */
-		for (i = 0; i < mp->m_sb.sb_rbmblocks; i++) {
-			/*
-			 * Get the summary for this level/block.
-			 */
-			error = xfs_rtget_summary(args, l, i, &sum);
-			if (error) {
-				return error;
-			}
-			/*
-			 * Nothing there, on to the next block.
-			 */
-			if (!sum)
-				continue;
-			/*
-			 * Try allocating the extent.
-			 */
-			error = xfs_rtallocate_extent_block(args, i, maxlen,
-					maxlen, len, &n, prod, &r);
-			if (error) {
-				return error;
-			}
-			/*
-			 * If it worked, return that.
-			 */
-			if (r != NULLRTEXTNO) {
-				*rtx = r;
-				return 0;
-			}
-			/*
-			 * If the "next block to try" returned from the
-			 * allocator is beyond the next bitmap block,
-			 * skip to that bitmap block.
-			 */
-			if (xfs_rtx_to_rbmblock(mp, n) > i + 1)
-				i = xfs_rtx_to_rbmblock(mp, n) - 1;
-		}
+	for (l = xfs_highbit32(maxlen); l < args->mp->m_rsumlevels; l++) {
+		error = xfs_rtalloc_sumlevel(args, l, minlen, maxlen, prod, len,
+				rtx);
+		if (error != -ENOSPC)
+			return error;
 	}
+
 	/*
-	 * Didn't find any maxlen blocks.  Try smaller ones, unless
-	 * we're asking for a fixed size extent.
+	 * Didn't find any maxlen blocks.  Try smaller ones, unless we are
+	 * looking for a fixed size extent.
 	 */
-	if (minlen > --maxlen) {
-		*rtx = NULLRTEXTNO;
-		return 0;
-	}
+	if (minlen > --maxlen)
+		return -ENOSPC;
 	ASSERT(minlen != 0);
 	ASSERT(maxlen != 0);
 
 	/*
 	 * Loop over sizes, from maxlen down to minlen.
-	 * This time, when we do the allocations, allow smaller ones
-	 * to succeed.
+	 *
+	 * This time, when we do the allocations, allow smaller ones to succeed,
+	 * but make sure the specified minlen/maxlen are in the possible range
+	 * for this summary level.
 	 */
 	for (l = xfs_highbit32(maxlen); l >= xfs_highbit32(minlen); l--) {
-		/*
-		 * Loop over all the bitmap blocks, try an allocation
-		 * starting in that block.
-		 */
-		for (i = 0; i < mp->m_sb.sb_rbmblocks; i++) {
-			/*
-			 * Get the summary information for this level/block.
-			 */
-			error =	xfs_rtget_summary(args, l, i, &sum);
-			if (error) {
-				return error;
-			}
-			/*
-			 * If nothing there, go on to next.
-			 */
-			if (!sum)
-				continue;
-			/*
-			 * Try the allocation.  Make sure the specified
-			 * minlen/maxlen are in the possible range for
-			 * this summary level.
-			 */
-			error = xfs_rtallocate_extent_block(args, i,
-					XFS_RTMAX(minlen, 1 << l),
-					XFS_RTMIN(maxlen, (1 << (l + 1)) - 1),
-					len, &n, prod, &r);
-			if (error) {
-				return error;
-			}
-			/*
-			 * If it worked, return that extent.
-			 */
-			if (r != NULLRTEXTNO) {
-				*rtx = r;
-				return 0;
-			}
-			/*
-			 * If the "next block to try" returned from the
-			 * allocator is beyond the next bitmap block,
-			 * skip to that bitmap block.
-			 */
-			if (xfs_rtx_to_rbmblock(mp, n) > i + 1)
-				i = xfs_rtx_to_rbmblock(mp, n) - 1;
-		}
+		error = xfs_rtalloc_sumlevel(args, l,
+				max_t(xfs_rtxlen_t, minlen, 1 << l),
+				min_t(xfs_rtxlen_t, maxlen, (1 << (l + 1)) - 1),
+				prod, len, rtx);
+		if (error != -ENOSPC)
+			return error;
 	}
-	/*
-	 * Got nothing, return failure.
-	 */
-	*rtx = NULLRTEXTNO;
-	return 0;
+
+	return -ENOSPC;
 }
 
 /*
@@ -963,8 +866,10 @@ xfs_growfs_rt(
 	 */
 	nrextents = nrblocks;
 	do_div(nrextents, in->extsize);
+	if (!xfs_validate_rtextents(nrextents))
+		return -EINVAL;
 	nrbmblocks = xfs_rtbitmap_blockcount(mp, nrextents);
-	nrextslog = xfs_highbit32(nrextents);
+	nrextslog = xfs_compute_rextslog(nrextents);
 	nrsumlevels = nrextslog + 1;
 	nrsumblocks = xfs_rtsummary_blockcount(mp, nrsumlevels, nrbmblocks);
 	nrsumsize = XFS_FSB_TO_B(mp, nrsumblocks);
@@ -1031,11 +936,14 @@ xfs_growfs_rt(
 		nsbp->sb_rblocks = min(nrblocks, nrblocks_step);
 		nsbp->sb_rextents = xfs_rtb_to_rtx(nmp, nsbp->sb_rblocks);
 		ASSERT(nsbp->sb_rextents != 0);
-		nsbp->sb_rextslog = xfs_highbit32(nsbp->sb_rextents);
+		nsbp->sb_rextslog = xfs_compute_rextslog(nsbp->sb_rextents);
 		nrsumlevels = nmp->m_rsumlevels = nsbp->sb_rextslog + 1;
 		nrsumblocks = xfs_rtsummary_blockcount(mp, nrsumlevels,
 				nsbp->sb_rbmblocks);
 		nmp->m_rsumsize = nrsumsize = XFS_FSB_TO_B(mp, nrsumblocks);
+		/* recompute growfsrt reservation from new rsumsize */
+		xfs_trans_resv_calc(nmp, &nmp->m_resv);
+
 		/*
 		 * Start a transaction, get the log reservation.
 		 */
@@ -1122,6 +1030,8 @@ error_cancel:
 		 */
 		mp->m_rsumlevels = nrsumlevels;
 		mp->m_rsumsize = nrsumsize;
+		/* recompute growfsrt reservation from new rsumsize */
+		xfs_trans_resv_calc(mp, &mp->m_resv);
 
 		error = xfs_trans_commit(tp);
 		if (error)
@@ -1160,81 +1070,6 @@ out_free:
 }
 
 /*
- * Allocate an extent in the realtime subvolume, with the usual allocation
- * parameters.  The length units are all in realtime extents, as is the
- * result block number.
- */
-int
-xfs_rtallocate_extent(
-	struct xfs_trans	*tp,
-	xfs_rtxnum_t		start,	/* starting rtext number to allocate */
-	xfs_rtxlen_t		minlen,	/* minimum length to allocate */
-	xfs_rtxlen_t		maxlen,	/* maximum length to allocate */
-	xfs_rtxlen_t		*len,	/* out: actual length allocated */
-	int			wasdel,	/* was a delayed allocation extent */
-	xfs_rtxlen_t		prod,	/* extent product factor */
-	xfs_rtxnum_t		*rtblock) /* out: start rtext allocated */
-{
-	struct xfs_rtalloc_args	args = {
-		.mp		= tp->t_mountp,
-		.tp		= tp,
-	};
-	int			error;	/* error value */
-	xfs_rtxnum_t		r;	/* result allocated rtext */
-
-	ASSERT(xfs_isilocked(args.mp->m_rbmip, XFS_ILOCK_EXCL));
-	ASSERT(minlen > 0 && minlen <= maxlen);
-
-	/*
-	 * If prod is set then figure out what to do to minlen and maxlen.
-	 */
-	if (prod > 1) {
-		xfs_rtxlen_t	i;
-
-		if ((i = maxlen % prod))
-			maxlen -= i;
-		if ((i = minlen % prod))
-			minlen += prod - i;
-		if (maxlen < minlen) {
-			*rtblock = NULLRTEXTNO;
-			return 0;
-		}
-	}
-
-retry:
-	if (start == 0) {
-		error = xfs_rtallocate_extent_size(&args, minlen,
-				maxlen, len, prod, &r);
-	} else {
-		error = xfs_rtallocate_extent_near(&args, start, minlen,
-				maxlen, len, prod, &r);
-	}
-
-	xfs_rtbuf_cache_relse(&args);
-	if (error)
-		return error;
-
-	/*
-	 * If it worked, update the superblock.
-	 */
-	if (r != NULLRTEXTNO) {
-		long	slen = (long)*len;
-
-		ASSERT(*len >= minlen && *len <= maxlen);
-		if (wasdel)
-			xfs_trans_mod_sb(tp, XFS_TRANS_SB_RES_FREXTENTS, -slen);
-		else
-			xfs_trans_mod_sb(tp, XFS_TRANS_SB_FREXTENTS, -slen);
-	} else if (prod > 1) {
-		prod = 1;
-		goto retry;
-	}
-
-	*rtblock = r;
-	return 0;
-}
-
-/*
  * Initialize realtime fields in the mount structure.
  */
 int				/* error */
@@ -1412,7 +1247,7 @@ xfs_rtunmount_inodes(
  * of rtextents and the fraction.
  * The fraction sequence is 0, 1/2, 1/4, 3/4, 1/8, ..., 7/8, 1/16, ...
  */
-int						/* error */
+static int
 xfs_rtpick_extent(
 	xfs_mount_t		*mp,		/* file system mount point */
 	xfs_trans_t		*tp,		/* transaction pointer */
@@ -1451,3 +1286,177 @@ xfs_rtpick_extent(
 	*pick = b;
 	return 0;
 }
+
+static void
+xfs_rtalloc_align_minmax(
+	xfs_rtxlen_t		*raminlen,
+	xfs_rtxlen_t		*ramaxlen,
+	xfs_rtxlen_t		*prod)
+{
+	xfs_rtxlen_t		newmaxlen = *ramaxlen;
+	xfs_rtxlen_t		newminlen = *raminlen;
+	xfs_rtxlen_t		slack;
+
+	slack = newmaxlen % *prod;
+	if (slack)
+		newmaxlen -= slack;
+	slack = newminlen % *prod;
+	if (slack)
+		newminlen += *prod - slack;
+
+	/*
+	 * If adjusting for extent size hint alignment produces an invalid
+	 * min/max len combination, go ahead without it.
+	 */
+	if (newmaxlen < newminlen) {
+		*prod = 1;
+		return;
+	}
+	*ramaxlen = newmaxlen;
+	*raminlen = newminlen;
+}
+
+int
+xfs_bmap_rtalloc(
+	struct xfs_bmalloca	*ap)
+{
+	struct xfs_mount	*mp = ap->ip->i_mount;
+	xfs_fileoff_t		orig_offset = ap->offset;
+	xfs_rtxnum_t		start;	   /* allocation hint rtextent no */
+	xfs_rtxnum_t		rtx;	   /* actually allocated rtextent no */
+	xfs_rtxlen_t		prod = 0;  /* product factor for allocators */
+	xfs_extlen_t		mod = 0;   /* product factor for allocators */
+	xfs_rtxlen_t		ralen = 0; /* realtime allocation length */
+	xfs_extlen_t		align;     /* minimum allocation alignment */
+	xfs_extlen_t		orig_length = ap->length;
+	xfs_extlen_t		minlen = mp->m_sb.sb_rextsize;
+	xfs_rtxlen_t		raminlen;
+	bool			rtlocked = false;
+	bool			ignore_locality = false;
+	struct xfs_rtalloc_args	args = {
+		.mp		= mp,
+		.tp		= ap->tp,
+	};
+	int			error;
+
+	align = xfs_get_extsz_hint(ap->ip);
+retry:
+	error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
+					align, 1, ap->eof, 0,
+					ap->conv, &ap->offset, &ap->length);
+	if (error)
+		return error;
+	ASSERT(ap->length);
+	ASSERT(xfs_extlen_to_rtxmod(mp, ap->length) == 0);
+
+	/*
+	 * If we shifted the file offset downward to satisfy an extent size
+	 * hint, increase minlen by that amount so that the allocator won't
+	 * give us an allocation that's too short to cover at least one of the
+	 * blocks that the caller asked for.
+	 */
+	if (ap->offset != orig_offset)
+		minlen += orig_offset - ap->offset;
+
+	/*
+	 * Set ralen to be the actual requested length in rtextents.
+	 *
+	 * If the old value was close enough to XFS_BMBT_MAX_EXTLEN that
+	 * we rounded up to it, cut it back so it's valid again.
+	 * Note that if it's a really large request (bigger than
+	 * XFS_BMBT_MAX_EXTLEN), we don't hear about that number, and can't
+	 * adjust the starting point to match it.
+	 */
+	ralen = xfs_extlen_to_rtxlen(mp, min(ap->length, XFS_MAX_BMBT_EXTLEN));
+	raminlen = max_t(xfs_rtxlen_t, 1, xfs_extlen_to_rtxlen(mp, minlen));
+	ASSERT(raminlen > 0);
+	ASSERT(raminlen <= ralen);
+
+	/*
+	 * Lock out modifications to both the RT bitmap and summary inodes
+	 */
+	if (!rtlocked) {
+		xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL|XFS_ILOCK_RTBITMAP);
+		xfs_trans_ijoin(ap->tp, mp->m_rbmip, XFS_ILOCK_EXCL);
+		xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL|XFS_ILOCK_RTSUM);
+		xfs_trans_ijoin(ap->tp, mp->m_rsumip, XFS_ILOCK_EXCL);
+		rtlocked = true;
+	}
+
+	if (ignore_locality) {
+		start = 0;
+	} else if (xfs_bmap_adjacent(ap)) {
+		start = xfs_rtb_to_rtx(mp, ap->blkno);
+	} else if (ap->eof && ap->offset == 0) {
+		/*
+		 * If it's an allocation to an empty file at offset 0, pick an
+		 * extent that will space things out in the rt area.
+		 */
+		error = xfs_rtpick_extent(mp, ap->tp, ralen, &start);
+		if (error)
+			return error;
+	} else {
+		start = 0;
+	}
+
+	/*
+	 * Only bother calculating a real prod factor if offset & length are
+	 * perfectly aligned, otherwise it will just get us in trouble.
+	 */
+	div_u64_rem(ap->offset, align, &mod);
+	if (mod || ap->length % align) {
+		prod = 1;
+	} else {
+		prod = xfs_extlen_to_rtxlen(mp, align);
+		if (prod > 1)
+			xfs_rtalloc_align_minmax(&raminlen, &ralen, &prod);
+	}
+
+	if (start) {
+		error = xfs_rtallocate_extent_near(&args, start, raminlen,
+				ralen, &ralen, prod, &rtx);
+	} else {
+		error = xfs_rtallocate_extent_size(&args, raminlen,
+				ralen, &ralen, prod, &rtx);
+	}
+	xfs_rtbuf_cache_relse(&args);
+
+	if (error == -ENOSPC) {
+		if (align > mp->m_sb.sb_rextsize) {
+			/*
+			 * We previously enlarged the request length to try to
+			 * satisfy an extent size hint.  The allocator didn't
+			 * return anything, so reset the parameters to the
+			 * original values and try again without alignment
+			 * criteria.
+			 */
+			ap->offset = orig_offset;
+			ap->length = orig_length;
+			minlen = align = mp->m_sb.sb_rextsize;
+			goto retry;
+		}
+
+		if (!ignore_locality && start != 0) {
+			/*
+			 * If we can't allocate near a specific rt extent, try
+			 * again without locality criteria.
+			 */
+			ignore_locality = true;
+			goto retry;
+		}
+
+		ap->blkno = NULLFSBLOCK;
+		ap->length = 0;
+		return 0;
+	}
+	if (error)
+		return error;
+
+	xfs_trans_mod_sb(ap->tp, ap->wasdel ?
+			XFS_TRANS_SB_RES_FREXTENTS : XFS_TRANS_SB_FREXTENTS,
+			-(long)ralen);
+	ap->blkno = xfs_rtx_to_rtb(mp, rtx);
+	ap->length = xfs_rtxlen_to_extlen(mp, ralen);
+	xfs_bmap_alloc_account(ap);
+	return 0;
+}
diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h
index f7cb9ffe51ca..a6836da9bebe 100644
--- a/fs/xfs/xfs_rtalloc.h
+++ b/fs/xfs/xfs_rtalloc.h
@@ -13,27 +13,6 @@ struct xfs_trans;
 
 #ifdef CONFIG_XFS_RT
 /*
- * Function prototypes for exported functions.
- */
-
-/*
- * Allocate an extent in the realtime subvolume, with the usual allocation
- * parameters.  The length units are all in realtime extents, as is the
- * result block number.
- */
-int					/* error */
-xfs_rtallocate_extent(
-	struct xfs_trans	*tp,	/* transaction pointer */
-	xfs_rtxnum_t		start,	/* starting rtext number to allocate */
-	xfs_rtxlen_t		minlen,	/* minimum length to allocate */
-	xfs_rtxlen_t		maxlen,	/* maximum length to allocate */
-	xfs_rtxlen_t		*len,	/* out: actual length allocated */
-	int			wasdel,	/* was a delayed allocation extent */
-	xfs_rtxlen_t		prod,	/* extent product factor */
-	xfs_rtxnum_t		*rtblock); /* out: start rtext allocated */
-
-
-/*
  * Initialize realtime fields in the mount structure.
  */
 int					/* error */
@@ -52,20 +31,6 @@ xfs_rtmount_inodes(
 	struct xfs_mount	*mp);	/* file system mount structure */
 
 /*
- * Pick an extent for allocation at the start of a new realtime file.
- * Use the sequence number stored in the atime field of the bitmap inode.
- * Translate this to a fraction of the rtextents, and return the product
- * of rtextents and the fraction.
- * The fraction sequence is 0, 1/2, 1/4, 3/4, 1/8, ..., 7/8, 1/16, ...
- */
-int					/* error */
-xfs_rtpick_extent(
-	struct xfs_mount	*mp,	/* file system mount point */
-	struct xfs_trans	*tp,	/* transaction pointer */
-	xfs_rtxlen_t		len,	/* allocation length (rtextents) */
-	xfs_rtxnum_t		*pick);	/* result rt extent */
-
-/*
  * Grow the realtime area of the filesystem.
  */
 int
@@ -75,8 +40,6 @@ xfs_growfs_rt(
 
 int xfs_rtalloc_reinit_frextents(struct xfs_mount *mp);
 #else
-# define xfs_rtallocate_extent(t,b,min,max,l,f,p,rb)	(-ENOSYS)
-# define xfs_rtpick_extent(m,t,l,rb)			(-ENOSYS)
 # define xfs_growfs_rt(mp,in)				(-ENOSYS)
 # define xfs_rtalloc_reinit_frextents(m)		(0)
 static inline int		/* error */
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 764304595e8b..aff20ddd4a9f 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -366,8 +366,9 @@ xfs_blkdev_get(
 {
 	int			error = 0;
 
-	*handlep = bdev_open_by_path(name, BLK_OPEN_READ | BLK_OPEN_WRITE,
-				     mp->m_super, &fs_holder_ops);
+	*handlep = bdev_open_by_path(name,
+		BLK_OPEN_READ | BLK_OPEN_WRITE | BLK_OPEN_RESTRICT_WRITES,
+		mp->m_super, &fs_holder_ops);
 	if (IS_ERR(*handlep)) {
 		error = PTR_ERR(*handlep);
 		*handlep = NULL;
@@ -439,18 +440,12 @@ xfs_open_devices(
 	int			error;
 
 	/*
-	 * blkdev_put() can't be called under s_umount, see the comment
-	 * in get_tree_bdev() for more details
-	 */
-	up_write(&sb->s_umount);
-
-	/*
 	 * Open real time and log devices - order is important.
 	 */
 	if (mp->m_logname) {
 		error = xfs_blkdev_get(mp, mp->m_logname, &logdev_handle);
 		if (error)
-			goto out_relock;
+			return error;
 	}
 
 	if (mp->m_rtname) {
@@ -493,10 +488,7 @@ xfs_open_devices(
 			bdev_release(logdev_handle);
 	}
 
-	error = 0;
-out_relock:
-	down_write(&sb->s_umount);
-	return error;
+	return 0;
 
  out_free_rtdev_targ:
 	if (mp->m_rtdev_targp)
@@ -509,7 +501,7 @@ out_relock:
  out_close_logdev:
 	if (logdev_handle)
 		bdev_release(logdev_handle);
-	goto out_relock;
+	return error;
 }
 
 /*
@@ -759,10 +751,6 @@ static void
 xfs_mount_free(
 	struct xfs_mount	*mp)
 {
-	/*
-	 * Free the buftargs here because blkdev_put needs to be called outside
-	 * of sb->s_umount, which is held around the call to ->put_super.
-	 */
 	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
 		xfs_free_buftarg(mp->m_logdev_targp);
 	if (mp->m_rtdev_targp)
@@ -906,10 +894,8 @@ xfs_fs_statfs(
 STATIC void
 xfs_save_resvblks(struct xfs_mount *mp)
 {
-	uint64_t resblks = 0;
-
 	mp->m_resblks_save = mp->m_resblks;
-	xfs_reserve_blocks(mp, &resblks, NULL);
+	xfs_reserve_blocks(mp, 0);
 }
 
 STATIC void
@@ -923,7 +909,7 @@ xfs_restore_resvblks(struct xfs_mount *mp)
 	} else
 		resblks = xfs_default_resblks(mp);
 
-	xfs_reserve_blocks(mp, &resblks, NULL);
+	xfs_reserve_blocks(mp, resblks);
 }
 
 /*
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 85e433df6a3f..92974a4414c8 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -23,6 +23,7 @@
 #include "xfs_trans.h"
 #include "xfs_ialloc.h"
 #include "xfs_error.h"
+#include "xfs_health.h"
 
 /* ----- Kernel only functions below ----- */
 int
@@ -108,6 +109,8 @@ xfs_readlink(
 
 	if (xfs_is_shutdown(mp))
 		return -EIO;
+	if (xfs_ifork_zapped(ip, XFS_DATA_FORK))
+		return -EIO;
 
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 
@@ -128,10 +131,10 @@ xfs_readlink(
 		 * The VFS crashes on a NULL pointer, so return -EFSCORRUPTED
 		 * if if_data is junk.
 		 */
-		if (XFS_IS_CORRUPT(ip->i_mount, !ip->i_df.if_u1.if_data))
+		if (XFS_IS_CORRUPT(ip->i_mount, !ip->i_df.if_data))
 			goto out;
 
-		memcpy(link, ip->i_df.if_u1.if_data, pathlen + 1);
+		memcpy(link, ip->i_df.if_data, pathlen + 1);
 		error = 0;
 	} else {
 		error = xfs_readlink_bmap_ilocked(ip, link);
diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c
index fade33735393..a191f6560f98 100644
--- a/fs/xfs/xfs_sysctl.c
+++ b/fs/xfs/xfs_sysctl.c
@@ -206,8 +206,6 @@ static struct ctl_table xfs_table[] = {
 		.extra2		= &xfs_params.stats_clear.max
 	},
 #endif /* CONFIG_PROC_FS */
-
-	{}
 };
 
 int
diff --git a/fs/xfs/xfs_sysctl.h b/fs/xfs/xfs_sysctl.h
index f78ad6b10ea5..276696a07040 100644
--- a/fs/xfs/xfs_sysctl.h
+++ b/fs/xfs/xfs_sysctl.h
@@ -85,6 +85,8 @@ struct xfs_globals {
 	int	pwork_threads;		/* parallel workqueue threads */
 	bool	larp;			/* log attribute replay */
 #endif
+	int	bload_leaf_slack;	/* btree bulk load leaf slack */
+	int	bload_node_slack;	/* btree bulk load node slack */
 	int	log_recovery_delay;	/* log recovery delay (secs) */
 	int	mount_delay;		/* mount setup delay (secs) */
 	bool	bug_on_assert;		/* BUG() the kernel on assert failure */
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index a3c6b1548723..17485666b672 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -229,6 +229,15 @@ pwork_threads_show(
 }
 XFS_SYSFS_ATTR_RW(pwork_threads);
 
+/*
+ * The "LARP" (Logged extended Attribute Recovery Persistence) debugging knob
+ * sets the XFS_DA_OP_LOGGED flag on all xfs_attr_set operations performed on
+ * V5 filesystems.  As a result, the intermediate progress of all setxattr and
+ * removexattr operations are tracked via the log and can be restarted during
+ * recovery.  This is useful for testing xattr recovery prior to merging of the
+ * parent pointer feature which requires it to maintain consistency, and may be
+ * enabled for userspace xattrs in the future.
+ */
 static ssize_t
 larp_store(
 	struct kobject	*kobject,
@@ -253,6 +262,58 @@ larp_show(
 XFS_SYSFS_ATTR_RW(larp);
 #endif /* DEBUG */
 
+STATIC ssize_t
+bload_leaf_slack_store(
+	struct kobject	*kobject,
+	const char	*buf,
+	size_t		count)
+{
+	int		ret;
+	int		val;
+
+	ret = kstrtoint(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	xfs_globals.bload_leaf_slack = val;
+	return count;
+}
+
+STATIC ssize_t
+bload_leaf_slack_show(
+	struct kobject	*kobject,
+	char		*buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n", xfs_globals.bload_leaf_slack);
+}
+XFS_SYSFS_ATTR_RW(bload_leaf_slack);
+
+STATIC ssize_t
+bload_node_slack_store(
+	struct kobject	*kobject,
+	const char	*buf,
+	size_t		count)
+{
+	int		ret;
+	int		val;
+
+	ret = kstrtoint(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	xfs_globals.bload_node_slack = val;
+	return count;
+}
+
+STATIC ssize_t
+bload_node_slack_show(
+	struct kobject	*kobject,
+	char		*buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n", xfs_globals.bload_node_slack);
+}
+XFS_SYSFS_ATTR_RW(bload_node_slack);
+
 static struct attribute *xfs_dbg_attrs[] = {
 	ATTR_LIST(bug_on_assert),
 	ATTR_LIST(log_recovery_delay),
@@ -262,6 +323,8 @@ static struct attribute *xfs_dbg_attrs[] = {
 	ATTR_LIST(pwork_threads),
 	ATTR_LIST(larp),
 #endif
+	ATTR_LIST(bload_leaf_slack),
+	ATTR_LIST(bload_node_slack),
 	NULL,
 };
 ATTRIBUTE_GROUPS(xfs_dbg);
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 3926cf7f2a6e..0984a1c884c7 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -67,6 +67,7 @@ struct xfs_buf_log_format;
 struct xfs_inode_log_format;
 struct xfs_bmbt_irec;
 struct xfs_btree_cur;
+struct xfs_defer_op_type;
 struct xfs_refcount_irec;
 struct xfs_fsmap;
 struct xfs_rmap_irec;
@@ -145,21 +146,23 @@ DEFINE_ATTR_LIST_EVENT(xfs_attr_leaf_list);
 DEFINE_ATTR_LIST_EVENT(xfs_attr_node_list);
 
 TRACE_EVENT(xlog_intent_recovery_failed,
-	TP_PROTO(struct xfs_mount *mp, int error, void *function),
-	TP_ARGS(mp, error, function),
+	TP_PROTO(struct xfs_mount *mp, const struct xfs_defer_op_type *ops,
+		 int error),
+	TP_ARGS(mp, ops, error),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
+		__string(name, ops->name)
 		__field(int, error)
-		__field(void *, function)
 	),
 	TP_fast_assign(
 		__entry->dev = mp->m_super->s_dev;
+		__assign_str(name, ops->name);
 		__entry->error = error;
-		__entry->function = function;
 	),
-	TP_printk("dev %d:%d error %d function %pS",
+	TP_printk("dev %d:%d optype %s error %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->error, __entry->function)
+		  __get_str(name),
+		  __entry->error)
 );
 
 DECLARE_EVENT_CLASS(xfs_perag_class,
@@ -2549,22 +2552,25 @@ DECLARE_EVENT_CLASS(xfs_defer_pending_class,
 	TP_ARGS(mp, dfp),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
-		__field(int, type)
+		__string(name, dfp->dfp_ops->name)
 		__field(void *, intent)
+		__field(unsigned int, flags)
 		__field(char, committed)
 		__field(int, nr)
 	),
 	TP_fast_assign(
 		__entry->dev = mp ? mp->m_super->s_dev : 0;
-		__entry->type = dfp->dfp_type;
+		__assign_str(name, dfp->dfp_ops->name);
 		__entry->intent = dfp->dfp_intent;
+		__entry->flags = dfp->dfp_flags;
 		__entry->committed = dfp->dfp_done != NULL;
 		__entry->nr = dfp->dfp_count;
 	),
-	TP_printk("dev %d:%d optype %d intent %p committed %d nr %d",
+	TP_printk("dev %d:%d optype %s intent %p flags %s committed %d nr %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->type,
+		  __get_str(name),
 		  __entry->intent,
+		  __print_flags(__entry->flags, "|", XFS_DEFER_PENDING_STRINGS),
 		  __entry->committed,
 		  __entry->nr)
 )
@@ -2675,6 +2681,9 @@ DEFINE_DEFER_PENDING_EVENT(xfs_defer_cancel_list);
 DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_finish);
 DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_abort);
 DEFINE_DEFER_PENDING_EVENT(xfs_defer_relog_intent);
+DEFINE_DEFER_PENDING_EVENT(xfs_defer_isolate_paused);
+DEFINE_DEFER_PENDING_EVENT(xfs_defer_item_pause);
+DEFINE_DEFER_PENDING_EVENT(xfs_defer_item_unpause);
 
 #define DEFINE_BMAP_FREE_DEFERRED_EVENT DEFINE_PHYS_EXTENT_DEFERRED_EVENT
 DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_bmap_free_defer);
@@ -2688,25 +2697,28 @@ DECLARE_EVENT_CLASS(xfs_defer_pending_item_class,
 	TP_ARGS(mp, dfp, item),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
-		__field(int, type)
+		__string(name, dfp->dfp_ops->name)
 		__field(void *, intent)
 		__field(void *, item)
 		__field(char, committed)
+		__field(unsigned int, flags)
 		__field(int, nr)
 	),
 	TP_fast_assign(
 		__entry->dev = mp ? mp->m_super->s_dev : 0;
-		__entry->type = dfp->dfp_type;
+		__assign_str(name, dfp->dfp_ops->name);
 		__entry->intent = dfp->dfp_intent;
 		__entry->item = item;
 		__entry->committed = dfp->dfp_done != NULL;
+		__entry->flags = dfp->dfp_flags;
 		__entry->nr = dfp->dfp_count;
 	),
-	TP_printk("dev %d:%d optype %d intent %p item %p committed %d nr %d",
+	TP_printk("dev %d:%d optype %s intent %p item %p flags %s committed %d nr %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->type,
+		  __get_str(name),
 		  __entry->intent,
 		  __entry->item,
+		  __print_flags(__entry->flags, "|", XFS_DEFER_PENDING_STRINGS),
 		  __entry->committed,
 		  __entry->nr)
 )
@@ -4399,8 +4411,6 @@ DEFINE_DAS_STATE_EVENT(xfs_attr_remove_iter_return);
 DEFINE_DAS_STATE_EVENT(xfs_attr_rmtval_alloc);
 DEFINE_DAS_STATE_EVENT(xfs_attr_rmtval_remove_return);
 DEFINE_DAS_STATE_EVENT(xfs_attr_defer_add);
-DEFINE_DAS_STATE_EVENT(xfs_attr_defer_replace);
-DEFINE_DAS_STATE_EVENT(xfs_attr_defer_remove);
 
 
 TRACE_EVENT(xfs_force_shutdown,
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 305c9d07bf1b..12d45e93f07d 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -1237,6 +1237,68 @@ out_cancel:
 }
 
 /*
+ * Try to reserve more blocks for a transaction.
+ *
+ * This is for callers that need to attach resources to a transaction, scan
+ * those resources to determine the space reservation requirements, and then
+ * modify the attached resources.  In other words, online repair.  This can
+ * fail due to ENOSPC, so the caller must be able to cancel the transaction
+ * without shutting down the fs.
+ */
+int
+xfs_trans_reserve_more(
+	struct xfs_trans	*tp,
+	unsigned int		blocks,
+	unsigned int		rtextents)
+{
+	struct xfs_trans_res	resv = { };
+
+	return xfs_trans_reserve(tp, &resv, blocks, rtextents);
+}
+
+/*
+ * Try to reserve more blocks and file quota for a transaction.  Same
+ * conditions of usage as xfs_trans_reserve_more.
+ */
+int
+xfs_trans_reserve_more_inode(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	unsigned int		dblocks,
+	unsigned int		rblocks,
+	bool			force_quota)
+{
+	struct xfs_trans_res	resv = { };
+	struct xfs_mount	*mp = ip->i_mount;
+	unsigned int		rtx = xfs_extlen_to_rtxlen(mp, rblocks);
+	int			error;
+
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+
+	error = xfs_trans_reserve(tp, &resv, dblocks, rtx);
+	if (error)
+		return error;
+
+	if (!XFS_IS_QUOTA_ON(mp) || xfs_is_quota_inode(&mp->m_sb, ip->i_ino))
+		return 0;
+
+	if (tp->t_flags & XFS_TRANS_RESERVE)
+		force_quota = true;
+
+	error = xfs_trans_reserve_quota_nblks(tp, ip, dblocks, rblocks,
+			force_quota);
+	if (!error)
+		return 0;
+
+	/* Quota failed, give back the new reservation. */
+	xfs_mod_fdblocks(mp, dblocks, tp->t_flags & XFS_TRANS_RESERVE);
+	tp->t_blk_res -= dblocks;
+	xfs_mod_frextents(mp, rtx);
+	tp->t_rtx_res -= rtx;
+	return error;
+}
+
+/*
  * Allocate an transaction in preparation for inode creation by reserving quota
  * against the given dquots.  Callers are not required to hold any inode locks.
  */
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 6e3646d524ce..08ce757c7454 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -78,11 +78,7 @@ struct xfs_item_ops {
 	xfs_lsn_t (*iop_committed)(struct xfs_log_item *, xfs_lsn_t);
 	uint (*iop_push)(struct xfs_log_item *, struct list_head *);
 	void (*iop_release)(struct xfs_log_item *);
-	int (*iop_recover)(struct xfs_log_item *lip,
-			   struct list_head *capture_list);
 	bool (*iop_match)(struct xfs_log_item *item, uint64_t id);
-	struct xfs_log_item *(*iop_relog)(struct xfs_log_item *intent,
-			struct xfs_trans *tp);
 	struct xfs_log_item *(*iop_intent)(struct xfs_log_item *intent_done);
 };
 
@@ -168,6 +164,8 @@ typedef struct xfs_trans {
 int		xfs_trans_alloc(struct xfs_mount *mp, struct xfs_trans_res *resp,
 			uint blocks, uint rtextents, uint flags,
 			struct xfs_trans **tpp);
+int		xfs_trans_reserve_more(struct xfs_trans *tp,
+			unsigned int blocks, unsigned int rtextents);
 int		xfs_trans_alloc_empty(struct xfs_mount *mp,
 			struct xfs_trans **tpp);
 void		xfs_trans_mod_sb(xfs_trans_t *, uint, int64_t);
@@ -247,19 +245,13 @@ void		xfs_trans_buf_copy_type(struct xfs_buf *dst_bp,
 
 extern struct kmem_cache	*xfs_trans_cache;
 
-static inline struct xfs_log_item *
-xfs_trans_item_relog(
-	struct xfs_log_item	*lip,
-	struct xfs_trans	*tp)
-{
-	return lip->li_ops->iop_relog(lip, tp);
-}
-
 struct xfs_dquot;
 
 int xfs_trans_alloc_inode(struct xfs_inode *ip, struct xfs_trans_res *resv,
 		unsigned int dblocks, unsigned int rblocks, bool force,
 		struct xfs_trans **tpp);
+int xfs_trans_reserve_more_inode(struct xfs_trans *tp, struct xfs_inode *ip,
+		unsigned int dblocks, unsigned int rblocks, bool force_quota);
 int xfs_trans_alloc_icreate(struct xfs_mount *mp, struct xfs_trans_res *resv,
 		struct xfs_dquot *udqp, struct xfs_dquot *gdqp,
 		struct xfs_dquot *pdqp, unsigned int dblocks,
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index 987843f84d03..364104e1b38a 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -136,6 +136,9 @@ xfs_xattr_get(const struct xattr_handler *handler, struct dentry *unused,
 	};
 	int			error;
 
+	if (xfs_ifork_zapped(XFS_I(inode), XFS_ATTR_FORK))
+		return -EIO;
+
 	error = xfs_attr_get(&args);
 	if (error)
 		return error;
@@ -294,6 +297,9 @@ xfs_vn_listxattr(
 	struct inode	*inode = d_inode(dentry);
 	int		error;
 
+	if (xfs_ifork_zapped(XFS_I(inode), XFS_ATTR_FORK))
+		return -EIO;
+
 	/*
 	 * First read the regular on-disk attributes.
 	 */
diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c
index b2c9b35df8f7..6ab2318a9c8e 100644
--- a/fs/zonefs/file.c
+++ b/fs/zonefs/file.c
@@ -180,7 +180,7 @@ const struct address_space_operations zonefs_file_aops = {
 	.invalidate_folio	= iomap_invalidate_folio,
 	.migrate_folio		= filemap_migrate_folio,
 	.is_partially_uptodate	= iomap_is_partially_uptodate,
-	.error_remove_page	= generic_error_remove_page,
+	.error_remove_folio	= generic_error_remove_folio,
 	.swap_activate		= zonefs_swap_activate,
 };
 
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index afeed6e72049..2b3ae51f950d 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -14,7 +14,7 @@
 
 struct acpi_handle_list {
 	u32 count;
-	acpi_handle* handles;
+	acpi_handle *handles;
 };
 
 /* acpi_utils.h */
@@ -25,16 +25,15 @@ acpi_status
 acpi_evaluate_integer(acpi_handle handle,
 		      acpi_string pathname,
 		      struct acpi_object_list *arguments, unsigned long long *data);
-acpi_status
-acpi_evaluate_reference(acpi_handle handle,
-			acpi_string pathname,
-			struct acpi_object_list *arguments,
-			struct acpi_handle_list *list);
+bool acpi_evaluate_reference(acpi_handle handle, acpi_string pathname,
+			     struct acpi_object_list *arguments,
+			     struct acpi_handle_list *list);
 bool acpi_handle_list_equal(struct acpi_handle_list *list1,
 			    struct acpi_handle_list *list2);
 void acpi_handle_list_replace(struct acpi_handle_list *dst,
 			      struct acpi_handle_list *src);
 void acpi_handle_list_free(struct acpi_handle_list *list);
+bool acpi_device_dep(acpi_handle target, acpi_handle match);
 acpi_status
 acpi_evaluate_ost(acpi_handle handle, u32 source_event, u32 status_code,
 		  struct acpi_buffer *status_buf);
@@ -366,6 +365,98 @@ struct acpi_device_data {
 
 struct acpi_gpio_mapping;
 
+#define ACPI_DEVICE_SWNODE_ROOT			0
+
+/*
+ * The maximum expected number of CSI-2 data lanes.
+ *
+ * This number is not expected to ever have to be equal to or greater than the
+ * number of bits in an unsigned long variable, but if it needs to be increased
+ * above that limit, code will need to be adjusted accordingly.
+ */
+#define ACPI_DEVICE_CSI2_DATA_LANES		8
+
+#define ACPI_DEVICE_SWNODE_PORT_NAME_LENGTH	8
+
+enum acpi_device_swnode_dev_props {
+	ACPI_DEVICE_SWNODE_DEV_ROTATION,
+	ACPI_DEVICE_SWNODE_DEV_CLOCK_FREQUENCY,
+	ACPI_DEVICE_SWNODE_DEV_LED_MAX_MICROAMP,
+	ACPI_DEVICE_SWNODE_DEV_FLASH_MAX_MICROAMP,
+	ACPI_DEVICE_SWNODE_DEV_FLASH_MAX_TIMEOUT_US,
+	ACPI_DEVICE_SWNODE_DEV_NUM_OF,
+	ACPI_DEVICE_SWNODE_DEV_NUM_ENTRIES
+};
+
+enum acpi_device_swnode_port_props {
+	ACPI_DEVICE_SWNODE_PORT_REG,
+	ACPI_DEVICE_SWNODE_PORT_NUM_OF,
+	ACPI_DEVICE_SWNODE_PORT_NUM_ENTRIES
+};
+
+enum acpi_device_swnode_ep_props {
+	ACPI_DEVICE_SWNODE_EP_REMOTE_EP,
+	ACPI_DEVICE_SWNODE_EP_BUS_TYPE,
+	ACPI_DEVICE_SWNODE_EP_REG,
+	ACPI_DEVICE_SWNODE_EP_CLOCK_LANES,
+	ACPI_DEVICE_SWNODE_EP_DATA_LANES,
+	ACPI_DEVICE_SWNODE_EP_LANE_POLARITIES,
+	/* TX only */
+	ACPI_DEVICE_SWNODE_EP_LINK_FREQUENCIES,
+	ACPI_DEVICE_SWNODE_EP_NUM_OF,
+	ACPI_DEVICE_SWNODE_EP_NUM_ENTRIES
+};
+
+/*
+ * Each device has a root software node plus two times as many nodes as the
+ * number of CSI-2 ports.
+ */
+#define ACPI_DEVICE_SWNODE_PORT(port)	(2 * (port) + 1)
+#define ACPI_DEVICE_SWNODE_EP(endpoint)	\
+		(ACPI_DEVICE_SWNODE_PORT(endpoint) + 1)
+
+/**
+ * struct acpi_device_software_node_port - MIPI DisCo for Imaging CSI-2 port
+ * @port_name: Port name.
+ * @data_lanes: "data-lanes" property values.
+ * @lane_polarities: "lane-polarities" property values.
+ * @link_frequencies: "link_frequencies" property values.
+ * @port_nr: Port number.
+ * @crs_crs2_local: _CRS CSI2 record present (i.e. this is a transmitter one).
+ * @port_props: Port properties.
+ * @ep_props: Endpoint properties.
+ * @remote_ep: Reference to the remote endpoint.
+ */
+struct acpi_device_software_node_port {
+	char port_name[ACPI_DEVICE_SWNODE_PORT_NAME_LENGTH + 1];
+	u32 data_lanes[ACPI_DEVICE_CSI2_DATA_LANES];
+	u32 lane_polarities[ACPI_DEVICE_CSI2_DATA_LANES + 1 /* clock lane */];
+	u64 link_frequencies[ACPI_DEVICE_CSI2_DATA_LANES];
+	unsigned int port_nr;
+	bool crs_csi2_local;
+
+	struct property_entry port_props[ACPI_DEVICE_SWNODE_PORT_NUM_ENTRIES];
+	struct property_entry ep_props[ACPI_DEVICE_SWNODE_EP_NUM_ENTRIES];
+
+	struct software_node_ref_args remote_ep[1];
+};
+
+/**
+ * struct acpi_device_software_nodes - Software nodes for an ACPI device
+ * @dev_props: Device properties.
+ * @nodes: Software nodes for root as well as ports and endpoints.
+ * @nodeprts: Array of software node pointers, for (un)registering them.
+ * @ports: Information related to each port and endpoint within a port.
+ * @num_ports: The number of ports.
+ */
+struct acpi_device_software_nodes {
+	struct property_entry dev_props[ACPI_DEVICE_SWNODE_DEV_NUM_ENTRIES];
+	struct software_node *nodes;
+	const struct software_node **nodeptrs;
+	struct acpi_device_software_node_port *ports;
+	unsigned int num_ports;
+};
+
 /* Device */
 struct acpi_device {
 	u32 pld_crc;
@@ -384,6 +475,7 @@ struct acpi_device {
 	struct acpi_device_data data;
 	struct acpi_scan_handler *handler;
 	struct acpi_hotplug_context *hp;
+	struct acpi_device_software_nodes *swnodes;
 	const struct acpi_gpio_mapping *driver_gpios;
 	void *driver_data;
 	struct device dev;
@@ -542,6 +634,7 @@ int acpi_device_set_power(struct acpi_device *device, int state);
 int acpi_bus_init_power(struct acpi_device *device);
 int acpi_device_fix_up_power(struct acpi_device *device);
 void acpi_device_fix_up_power_extended(struct acpi_device *adev);
+void acpi_device_fix_up_power_children(struct acpi_device *adev);
 int acpi_bus_update_power(acpi_handle handle, int *state_p);
 int acpi_device_update_power(struct acpi_device *device, int *state_p);
 bool acpi_bus_power_manageable(acpi_handle handle);
@@ -763,10 +856,71 @@ static inline bool acpi_device_can_poweroff(struct acpi_device *adev)
 		adev->power.states[ACPI_STATE_D3_HOT].flags.explicit_set);
 }
 
-bool acpi_dev_uid_match(struct acpi_device *adev, const char *uid2);
-bool acpi_dev_hid_uid_match(struct acpi_device *adev, const char *hid2, const char *uid2);
 int acpi_dev_uid_to_integer(struct acpi_device *adev, u64 *integer);
 
+static inline bool acpi_dev_hid_match(struct acpi_device *adev, const char *hid2)
+{
+	const char *hid1 = acpi_device_hid(adev);
+
+	return hid1 && hid2 && !strcmp(hid1, hid2);
+}
+
+static inline bool acpi_str_uid_match(struct acpi_device *adev, const char *uid2)
+{
+	const char *uid1 = acpi_device_uid(adev);
+
+	return uid1 && uid2 && !strcmp(uid1, uid2);
+}
+
+static inline bool acpi_int_uid_match(struct acpi_device *adev, u64 uid2)
+{
+	u64 uid1;
+
+	return !acpi_dev_uid_to_integer(adev, &uid1) && uid1 == uid2;
+}
+
+#define TYPE_ENTRY(type, x)			\
+	const type: x,				\
+	type: x
+
+#define ACPI_STR_TYPES(match)			\
+	TYPE_ENTRY(unsigned char *, match),	\
+	TYPE_ENTRY(signed char *, match),		\
+	TYPE_ENTRY(char *, match),		\
+	TYPE_ENTRY(void *, match)
+
+/**
+ * acpi_dev_uid_match - Match device by supplied UID
+ * @adev: ACPI device to match.
+ * @uid2: Unique ID of the device.
+ *
+ * Matches UID in @adev with given @uid2.
+ *
+ * Returns: %true if matches, %false otherwise.
+ */
+#define acpi_dev_uid_match(adev, uid2)					\
+	_Generic(uid2,							\
+		 /* Treat @uid2 as a string for acpi string types */	\
+		 ACPI_STR_TYPES(acpi_str_uid_match),			\
+		 /* Treat as an integer otherwise */			\
+		 default: acpi_int_uid_match)(adev, uid2)
+
+/**
+ * acpi_dev_hid_uid_match - Match device by supplied HID and UID
+ * @adev: ACPI device to match.
+ * @hid2: Hardware ID of the device.
+ * @uid2: Unique ID of the device, pass 0 or NULL to not check _UID.
+ *
+ * Matches HID and UID in @adev with given @hid2 and @uid2. Absence of @uid2
+ * will be treated as a match. If user wants to validate @uid2, it should be
+ * done before calling this function.
+ *
+ * Returns: %true if matches or @uid2 is 0 or NULL, %false otherwise.
+ */
+#define acpi_dev_hid_uid_match(adev, hid2, uid2)			\
+	(acpi_dev_hid_match(adev, hid2) &&				\
+		(!(uid2) || acpi_dev_uid_match(adev, uid2)))
+
 void acpi_dev_clear_dependencies(struct acpi_device *supplier);
 bool acpi_dev_ready_for_enumeration(const struct acpi_device *device);
 struct acpi_device *acpi_dev_get_next_consumer_dev(struct acpi_device *supplier,
diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index 6126c977ece0..3a0995f8bce8 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -144,6 +144,8 @@ extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls);
 extern int cppc_set_enable(int cpu, bool enable);
 extern int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps);
 extern bool cppc_perf_ctrs_in_pcc(void);
+extern unsigned int cppc_perf_to_khz(struct cppc_perf_caps *caps, unsigned int perf);
+extern unsigned int cppc_khz_to_perf(struct cppc_perf_caps *caps, unsigned int freq);
 extern bool acpi_cpc_valid(void);
 extern bool cppc_allow_fast_switch(void);
 extern int acpi_get_psd_map(unsigned int cpu, struct cppc_cpudata *cpu_data);
diff --git a/include/acpi/video.h b/include/acpi/video.h
index 4230392b5b0b..3d538d4178ab 100644
--- a/include/acpi/video.h
+++ b/include/acpi/video.h
@@ -75,6 +75,15 @@ static inline enum acpi_backlight_type acpi_video_get_backlight_type(void)
 	return __acpi_video_get_backlight_type(false, NULL);
 }
 
+/*
+ * This function MUST only be called by GPU drivers to check if the driver
+ * should register a backlight class device. This function not only checks
+ * if a GPU native backlight device should be registered it *also* tells
+ * the ACPI video-detect code that native GPU backlight control is available.
+ * Therefor calling this from any place other then the GPU driver is wrong!
+ * To check if GPU native backlight control is used in other places instead use:
+ *   if (acpi_video_get_backlight_type() == acpi_backlight_native) { ... }
+ */
 static inline bool acpi_video_backlight_use_native(void)
 {
 	return __acpi_video_get_backlight_type(true, NULL) == acpi_backlight_native;
diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild
index def242528b1d..d436bee4d129 100644
--- a/include/asm-generic/Kbuild
+++ b/include/asm-generic/Kbuild
@@ -11,6 +11,7 @@ mandatory-y += bitops.h
 mandatory-y += bug.h
 mandatory-y += bugs.h
 mandatory-y += cacheflush.h
+mandatory-y += cfi.h
 mandatory-y += checksum.h
 mandatory-y += compat.h
 mandatory-y += current.h
diff --git a/include/asm-generic/cfi.h b/include/asm-generic/cfi.h
new file mode 100644
index 000000000000..41fac3537bf9
--- /dev/null
+++ b/include/asm-generic/cfi.h
@@ -0,0 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_GENERIC_CFI_H
+#define __ASM_GENERIC_CFI_H
+
+#endif /* __ASM_GENERIC_CFI_H */
diff --git a/include/asm-generic/cmpxchg-local.h b/include/asm-generic/cmpxchg-local.h
index 3df9f59a544e..f27d66fdc00a 100644
--- a/include/asm-generic/cmpxchg-local.h
+++ b/include/asm-generic/cmpxchg-local.h
@@ -34,7 +34,7 @@ static inline unsigned long __generic_cmpxchg_local(volatile void *ptr,
 			*(u16 *)ptr = (new & 0xffffu);
 		break;
 	case 4: prev = *(u32 *)ptr;
-		if (prev == (old & 0xffffffffffu))
+		if (prev == (old & 0xffffffffu))
 			*(u32 *)ptr = (new & 0xffffffffu);
 		break;
 	case 8: prev = *(u64 *)ptr;
diff --git a/include/asm-generic/numa.h b/include/asm-generic/numa.h
index 1a3ad6d29833..c32e0cf23c90 100644
--- a/include/asm-generic/numa.h
+++ b/include/asm-generic/numa.h
@@ -35,6 +35,7 @@ int __init numa_add_memblk(int nodeid, u64 start, u64 end);
 void __init numa_set_distance(int from, int to, int distance);
 void __init numa_free_distance(void);
 void __init early_map_cpu_to_node(unsigned int cpu, int nid);
+int __init early_cpu_to_node(int cpu);
 void numa_store_cpu_info(unsigned int cpu);
 void numa_add_cpu(unsigned int cpu);
 void numa_remove_cpu(unsigned int cpu);
@@ -46,6 +47,7 @@ static inline void numa_add_cpu(unsigned int cpu) { }
 static inline void numa_remove_cpu(unsigned int cpu) { }
 static inline void arch_numa_init(void) { }
 static inline void early_map_cpu_to_node(unsigned int cpu, int nid) { }
+static inline int early_cpu_to_node(int cpu) { return 0; }
 
 #endif	/* CONFIG_NUMA */
 
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index 995513fa2690..0655aa5b57b2 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -70,7 +70,7 @@ static __always_inline int queued_spin_is_locked(struct qspinlock *lock)
  */
 static __always_inline int queued_spin_value_unlocked(struct qspinlock lock)
 {
-	return !atomic_read(&lock.val);
+	return !lock.val.counter;
 }
 
 /**
diff --git a/include/asm-generic/unaligned.h b/include/asm-generic/unaligned.h
index 699650f81970..a84c64e5f11e 100644
--- a/include/asm-generic/unaligned.h
+++ b/include/asm-generic/unaligned.h
@@ -104,9 +104,9 @@ static inline u32 get_unaligned_le24(const void *p)
 
 static inline void __put_unaligned_be24(const u32 val, u8 *p)
 {
-	*p++ = val >> 16;
-	*p++ = val >> 8;
-	*p++ = val;
+	*p++ = (val >> 16) & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = val & 0xff;
 }
 
 static inline void put_unaligned_be24(const u32 val, void *p)
@@ -116,9 +116,9 @@ static inline void put_unaligned_be24(const u32 val, void *p)
 
 static inline void __put_unaligned_le24(const u32 val, u8 *p)
 {
-	*p++ = val;
-	*p++ = val >> 8;
-	*p++ = val >> 16;
+	*p++ = val & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = (val >> 16) & 0xff;
 }
 
 static inline void put_unaligned_le24(const u32 val, void *p)
@@ -128,12 +128,12 @@ static inline void put_unaligned_le24(const u32 val, void *p)
 
 static inline void __put_unaligned_be48(const u64 val, u8 *p)
 {
-	*p++ = val >> 40;
-	*p++ = val >> 32;
-	*p++ = val >> 24;
-	*p++ = val >> 16;
-	*p++ = val >> 8;
-	*p++ = val;
+	*p++ = (val >> 40) & 0xff;
+	*p++ = (val >> 32) & 0xff;
+	*p++ = (val >> 24) & 0xff;
+	*p++ = (val >> 16) & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = val & 0xff;
 }
 
 static inline void put_unaligned_be48(const u64 val, void *p)
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index bae0fe4d499b..5dd3a61d673d 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -370,7 +370,8 @@
 	BRANCH_PROFILE()						\
 	TRACE_PRINTKS()							\
 	BPF_RAW_TP()							\
-	TRACEPOINT_STR()
+	TRACEPOINT_STR()						\
+	KUNIT_TABLE()
 
 /*
  * Data section helpers
@@ -700,7 +701,7 @@
 	EARLYCON_TABLE()						\
 	LSM_TABLE()							\
 	EARLY_LSM_TABLE()						\
-	KUNIT_TABLE()
+	KUNIT_INIT_TABLE()
 
 #define INIT_TEXT							\
 	*(.init.text .init.text.*)					\
@@ -926,6 +927,12 @@
 		. = ALIGN(8);						\
 		BOUNDED_SECTION_POST_LABEL(.kunit_test_suites, __kunit_suites, _start, _end)
 
+/* Alignment must be consistent with (kunit_suite *) in include/kunit/test.h */
+#define KUNIT_INIT_TABLE()						\
+		. = ALIGN(8);						\
+		BOUNDED_SECTION_POST_LABEL(.kunit_init_test_suites, \
+				__kunit_init_suites, _start, _end)
+
 #ifdef CONFIG_BLK_DEV_INITRD
 #define INIT_RAM_FS							\
 	. = ALIGN(4);							\
diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index c7bdbece27cc..5d61f576cfc8 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -212,13 +212,9 @@ struct shash_desc {
  *	      This is a counterpart to @init_tfm, used to remove
  *	      various changes set in @init_tfm.
  * @clone_tfm: Copy transform into new object, may allocate memory.
- * @digestsize: see struct ahash_alg
- * @statesize: see struct ahash_alg
  * @descsize: Size of the operational state for the message digest. This state
  * 	      size is the memory size that needs to be allocated for
  *	      shash_desc.__ctx
- * @stat: Statistics for hash algorithm.
- * @base: internally used
  * @halg: see struct hash_alg_common
  * @HASH_ALG_COMMON: see struct hash_alg_common
  */
diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h
index ef8ce86b1f78..78ecaf5db04c 100644
--- a/include/crypto/if_alg.h
+++ b/include/crypto/if_alg.h
@@ -121,6 +121,7 @@ struct af_alg_async_req {
  *
  * @tsgl_list:		Link to TX SGL
  * @iv:			IV for cipher operation
+ * @state:		Existing state for continuing operation
  * @aead_assoclen:	Length of AAD for AEAD cipher operations
  * @completion:		Work queue for synchronous operation
  * @used:		TX bytes sent to kernel. This variable is used to
@@ -136,11 +137,13 @@ struct af_alg_async_req {
  *			recvmsg is invoked.
  * @init:		True if metadata has been sent.
  * @len:		Length of memory allocated for this data structure.
+ * @inflight:		Non-zero when AIO requests are in flight.
  */
 struct af_alg_ctx {
 	struct list_head tsgl_list;
 
 	void *iv;
+	void *state;
 	size_t aead_assoclen;
 
 	struct crypto_wait wait;
@@ -154,6 +157,8 @@ struct af_alg_ctx {
 	bool init;
 
 	unsigned int len;
+
+	unsigned int inflight;
 };
 
 int af_alg_register_type(const struct af_alg_type *type);
diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h
index ea18af48346b..c8857d7bdb37 100644
--- a/include/crypto/skcipher.h
+++ b/include/crypto/skcipher.h
@@ -15,6 +15,17 @@
 #include <linux/string.h>
 #include <linux/types.h>
 
+/* Set this bit if the lskcipher operation is a continuation. */
+#define CRYPTO_LSKCIPHER_FLAG_CONT	0x00000001
+/* Set this bit if the lskcipher operation is final. */
+#define CRYPTO_LSKCIPHER_FLAG_FINAL	0x00000002
+/* The bit CRYPTO_TFM_REQ_MAY_SLEEP can also be set if needed. */
+
+/* Set this bit if the skcipher operation is a continuation. */
+#define CRYPTO_SKCIPHER_REQ_CONT	0x00000001
+/* Set this bit if the skcipher operation is not final. */
+#define CRYPTO_SKCIPHER_REQ_NOTFINAL	0x00000002
+
 struct scatterlist;
 
 /**
@@ -91,6 +102,7 @@ struct crypto_istat_cipher {
  *	    IV of exactly that size to perform the encrypt or decrypt operation.
  * @chunksize: Equal to the block size except for stream ciphers such as
  *	       CTR where it is set to the underlying block size.
+ * @statesize: Size of the internal state for the algorithm.
  * @stat: Statistics for cipher algorithm
  * @base: Definition of a generic crypto algorithm.
  */
@@ -99,6 +111,7 @@ struct crypto_istat_cipher {
 	unsigned int max_keysize;	\
 	unsigned int ivsize;		\
 	unsigned int chunksize;		\
+	unsigned int statesize;		\
 					\
 	SKCIPHER_ALG_COMMON_STAT	\
 					\
@@ -108,16 +121,6 @@ struct skcipher_alg_common SKCIPHER_ALG_COMMON;
 
 /**
  * struct skcipher_alg - symmetric key cipher definition
- * @min_keysize: Minimum key size supported by the transformation. This is the
- *		 smallest key length supported by this transformation algorithm.
- *		 This must be set to one of the pre-defined values as this is
- *		 not hardware specific. Possible values for this field can be
- *		 found via git grep "_MIN_KEY_SIZE" include/crypto/
- * @max_keysize: Maximum key size supported by the transformation. This is the
- *		 largest key length supported by this transformation algorithm.
- *		 This must be set to one of the pre-defined values as this is
- *		 not hardware specific. Possible values for this field can be
- *		 found via git grep "_MAX_KEY_SIZE" include/crypto/
  * @setkey: Set key for the transformation. This function is used to either
  *	    program a supplied key into the hardware or store the key in the
  *	    transformation context for programming it later. Note that this
@@ -141,6 +144,17 @@ struct skcipher_alg_common SKCIPHER_ALG_COMMON;
  *	     be called in parallel with the same transformation object.
  * @decrypt: Decrypt a single block. This is a reverse counterpart to @encrypt
  *	     and the conditions are exactly the same.
+ * @export: Export partial state of the transformation. This function dumps the
+ *	    entire state of the ongoing transformation into a provided block of
+ *	    data so it can be @import 'ed back later on. This is useful in case
+ *	    you want to save partial result of the transformation after
+ *	    processing certain amount of data and reload this partial result
+ *	    multiple times later on for multiple re-use. No data processing
+ *	    happens at this point.
+ * @import: Import partial state of the transformation. This function loads the
+ *	    entire state of the ongoing transformation from a provided block of
+ *	    data so the transformation can continue from this point onward. No
+ *	    data processing happens at this point.
  * @init: Initialize the cryptographic transformation object. This function
  *	  is used to initialize the cryptographic transformation object.
  *	  This function is called only once at the instantiation time, right
@@ -152,15 +166,9 @@ struct skcipher_alg_common SKCIPHER_ALG_COMMON;
  * @exit: Deinitialize the cryptographic transformation object. This is a
  *	  counterpart to @init, used to remove various changes set in
  *	  @init.
- * @ivsize: IV size applicable for transformation. The consumer must provide an
- *	    IV of exactly that size to perform the encrypt or decrypt operation.
- * @chunksize: Equal to the block size except for stream ciphers such as
- *	       CTR where it is set to the underlying block size.
  * @walksize: Equal to the chunk size except in cases where the algorithm is
  * 	      considerably more efficient if it can operate on multiple chunks
  * 	      in parallel. Should be a multiple of chunksize.
- * @stat: Statistics for cipher algorithm
- * @base: Definition of a generic crypto algorithm.
  * @co: see struct skcipher_alg_common
  *
  * All fields except @ivsize are mandatory and must be filled.
@@ -170,6 +178,8 @@ struct skcipher_alg {
 	              unsigned int keylen);
 	int (*encrypt)(struct skcipher_request *req);
 	int (*decrypt)(struct skcipher_request *req);
+	int (*export)(struct skcipher_request *req, void *out);
+	int (*import)(struct skcipher_request *req, const void *in);
 	int (*init)(struct crypto_skcipher *tfm);
 	void (*exit)(struct crypto_skcipher *tfm);
 
@@ -200,6 +210,9 @@ struct skcipher_alg {
  *	     may be left over if length is not a multiple of blocks
  *	     and there is more to come (final == false).  The number of
  *	     left-over bytes should be returned in case of success.
+ *	     The siv field shall be as long as ivsize + statesize with
+ *	     the IV placed at the front.  The state will be used by the
+ *	     algorithm internally.
  * @decrypt: Decrypt a number of bytes. This is a reverse counterpart to
  *	     @encrypt and the conditions are exactly the same.
  * @init: Initialize the cryptographic transformation object. This function
@@ -215,9 +228,9 @@ struct lskcipher_alg {
 	int (*setkey)(struct crypto_lskcipher *tfm, const u8 *key,
 	              unsigned int keylen);
 	int (*encrypt)(struct crypto_lskcipher *tfm, const u8 *src,
-		       u8 *dst, unsigned len, u8 *iv, bool final);
+		       u8 *dst, unsigned len, u8 *siv, u32 flags);
 	int (*decrypt)(struct crypto_lskcipher *tfm, const u8 *src,
-		       u8 *dst, unsigned len, u8 *iv, bool final);
+		       u8 *dst, unsigned len, u8 *siv, u32 flags);
 	int (*init)(struct crypto_lskcipher *tfm);
 	void (*exit)(struct crypto_lskcipher *tfm);
 
@@ -496,6 +509,40 @@ static inline unsigned int crypto_lskcipher_chunksize(
 	return crypto_lskcipher_alg(tfm)->co.chunksize;
 }
 
+/**
+ * crypto_skcipher_statesize() - obtain state size
+ * @tfm: cipher handle
+ *
+ * Some algorithms cannot be chained with the IV alone.  They carry
+ * internal state which must be replicated if data is to be processed
+ * incrementally.  The size of that state can be obtained with this
+ * function.
+ *
+ * Return: state size in bytes
+ */
+static inline unsigned int crypto_skcipher_statesize(
+	struct crypto_skcipher *tfm)
+{
+	return crypto_skcipher_alg_common(tfm)->statesize;
+}
+
+/**
+ * crypto_lskcipher_statesize() - obtain state size
+ * @tfm: cipher handle
+ *
+ * Some algorithms cannot be chained with the IV alone.  They carry
+ * internal state which must be replicated if data is to be processed
+ * incrementally.  The size of that state can be obtained with this
+ * function.
+ *
+ * Return: state size in bytes
+ */
+static inline unsigned int crypto_lskcipher_statesize(
+	struct crypto_lskcipher *tfm)
+{
+	return crypto_lskcipher_alg(tfm)->co.statesize;
+}
+
 static inline unsigned int crypto_sync_skcipher_blocksize(
 	struct crypto_sync_skcipher *tfm)
 {
@@ -684,14 +731,48 @@ int crypto_skcipher_encrypt(struct skcipher_request *req);
 int crypto_skcipher_decrypt(struct skcipher_request *req);
 
 /**
+ * crypto_skcipher_export() - export partial state
+ * @req: reference to the skcipher_request handle that holds all information
+ *	 needed to perform the operation
+ * @out: output buffer of sufficient size that can hold the state
+ *
+ * Export partial state of the transformation. This function dumps the
+ * entire state of the ongoing transformation into a provided block of
+ * data so it can be @import 'ed back later on. This is useful in case
+ * you want to save partial result of the transformation after
+ * processing certain amount of data and reload this partial result
+ * multiple times later on for multiple re-use. No data processing
+ * happens at this point.
+ *
+ * Return: 0 if the cipher operation was successful; < 0 if an error occurred
+ */
+int crypto_skcipher_export(struct skcipher_request *req, void *out);
+
+/**
+ * crypto_skcipher_import() - import partial state
+ * @req: reference to the skcipher_request handle that holds all information
+ *	 needed to perform the operation
+ * @in: buffer holding the state
+ *
+ * Import partial state of the transformation. This function loads the
+ * entire state of the ongoing transformation from a provided block of
+ * data so the transformation can continue from this point onward. No
+ * data processing happens at this point.
+ *
+ * Return: 0 if the cipher operation was successful; < 0 if an error occurred
+ */
+int crypto_skcipher_import(struct skcipher_request *req, const void *in);
+
+/**
  * crypto_lskcipher_encrypt() - encrypt plaintext
  * @tfm: lskcipher handle
  * @src: source buffer
  * @dst: destination buffer
  * @len: number of bytes to process
- * @iv: IV for the cipher operation which must comply with the IV size defined
- *      by crypto_lskcipher_ivsize
- *
+ * @siv: IV + state for the cipher operation.  The length of the IV must
+ *	 comply with the IV size defined by crypto_lskcipher_ivsize.  The
+ *	 IV is then followed with a buffer with the length as specified by
+ *	 crypto_lskcipher_statesize.
  * Encrypt plaintext data using the lskcipher handle.
  *
  * Return: >=0 if the cipher operation was successful, if positive
@@ -699,7 +780,7 @@ int crypto_skcipher_decrypt(struct skcipher_request *req);
  *	   < 0 if an error occurred
  */
 int crypto_lskcipher_encrypt(struct crypto_lskcipher *tfm, const u8 *src,
-			     u8 *dst, unsigned len, u8 *iv);
+			     u8 *dst, unsigned len, u8 *siv);
 
 /**
  * crypto_lskcipher_decrypt() - decrypt ciphertext
@@ -707,8 +788,10 @@ int crypto_lskcipher_encrypt(struct crypto_lskcipher *tfm, const u8 *src,
  * @src: source buffer
  * @dst: destination buffer
  * @len: number of bytes to process
- * @iv: IV for the cipher operation which must comply with the IV size defined
- *      by crypto_lskcipher_ivsize
+ * @siv: IV + state for the cipher operation.  The length of the IV must
+ *	 comply with the IV size defined by crypto_lskcipher_ivsize.  The
+ *	 IV is then followed with a buffer with the length as specified by
+ *	 crypto_lskcipher_statesize.
  *
  * Decrypt ciphertext data using the lskcipher handle.
  *
@@ -717,7 +800,7 @@ int crypto_lskcipher_encrypt(struct crypto_lskcipher *tfm, const u8 *src,
  *	   < 0 if an error occurred
  */
 int crypto_lskcipher_decrypt(struct crypto_lskcipher *tfm, const u8 *src,
-			     u8 *dst, unsigned len, u8 *iv);
+			     u8 *dst, unsigned len, u8 *siv);
 
 /**
  * DOC: Symmetric Key Cipher Request Handle
diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h
index 536a0b0091c3..006b5c977ad7 100644
--- a/include/drm/drm_atomic_helper.h
+++ b/include/drm/drm_atomic_helper.h
@@ -97,6 +97,8 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev,
 
 int drm_atomic_helper_prepare_planes(struct drm_device *dev,
 				     struct drm_atomic_state *state);
+void drm_atomic_helper_unprepare_planes(struct drm_device *dev,
+					struct drm_atomic_state *state);
 
 #define DRM_PLANE_COMMIT_ACTIVE_ONLY			BIT(0)
 #define DRM_PLANE_COMMIT_NO_DISABLE_AFTER_MODESET	BIT(1)
diff --git a/include/drm/drm_gpuvm.h b/include/drm/drm_gpuvm.h
index bdfafc4a7705..c7a0594bdab1 100644
--- a/include/drm/drm_gpuvm.h
+++ b/include/drm/drm_gpuvm.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/* SPDX-License-Identifier: GPL-2.0-only OR MIT */
 
 #ifndef __DRM_GPUVM_H__
 #define __DRM_GPUVM_H__
diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h
index a7abf9f3e697..2a1d01e5b56b 100644
--- a/include/drm/drm_prime.h
+++ b/include/drm/drm_prime.h
@@ -60,12 +60,19 @@ enum dma_data_direction;
 
 struct drm_device;
 struct drm_gem_object;
+struct drm_file;
 
 /* core prime functions */
 struct dma_buf *drm_gem_dmabuf_export(struct drm_device *dev,
 				      struct dma_buf_export_info *exp_info);
 void drm_gem_dmabuf_release(struct dma_buf *dma_buf);
 
+int drm_gem_prime_fd_to_handle(struct drm_device *dev,
+			       struct drm_file *file_priv, int prime_fd, uint32_t *handle);
+int drm_gem_prime_handle_to_fd(struct drm_device *dev,
+			       struct drm_file *file_priv, uint32_t handle, uint32_t flags,
+			       int *prime_fd);
+
 /* helper functions for exporting */
 int drm_gem_map_attach(struct dma_buf *dma_buf,
 		       struct dma_buf_attachment *attach);
diff --git a/include/drm/ttm/ttm_pool.h b/include/drm/ttm/ttm_pool.h
index 30a347e5aa11..4490d43c63e3 100644
--- a/include/drm/ttm/ttm_pool.h
+++ b/include/drm/ttm/ttm_pool.h
@@ -74,7 +74,7 @@ struct ttm_pool {
 	bool use_dma32;
 
 	struct {
-		struct ttm_pool_type orders[MAX_ORDER + 1];
+		struct ttm_pool_type orders[NR_PAGE_ORDERS];
 	} caching[TTM_NUM_CACHING_TYPES];
 };
 
diff --git a/include/dt-bindings/arm/qcom,ids.h b/include/dt-bindings/arm/qcom,ids.h
index f7248348a459..51e0f6059410 100644
--- a/include/dt-bindings/arm/qcom,ids.h
+++ b/include/dt-bindings/arm/qcom,ids.h
@@ -255,6 +255,7 @@
 #define QCOM_ID_SA8775P			534
 #define QCOM_ID_QRU1000			539
 #define QCOM_ID_QDU1000			545
+#define QCOM_ID_SM8650			557
 #define QCOM_ID_SM4450			568
 #define QCOM_ID_QDU1010			587
 #define QCOM_ID_QRU1032			588
diff --git a/include/dt-bindings/clock/google,gs101.h b/include/dt-bindings/clock/google,gs101.h
new file mode 100644
index 000000000000..21adec22387c
--- /dev/null
+++ b/include/dt-bindings/clock/google,gs101.h
@@ -0,0 +1,392 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (C) 2023 Linaro Ltd.
+ * Author: Peter Griffin <peter.griffin@linaro.org>
+ *
+ * Device Tree binding constants for Google gs101 clock controller.
+ */
+
+#ifndef _DT_BINDINGS_CLOCK_GOOGLE_GS101_H
+#define _DT_BINDINGS_CLOCK_GOOGLE_GS101_H
+
+/* CMU_TOP PLL */
+#define CLK_FOUT_SHARED0_PLL		1
+#define CLK_FOUT_SHARED1_PLL		2
+#define CLK_FOUT_SHARED2_PLL		3
+#define CLK_FOUT_SHARED3_PLL		4
+#define CLK_FOUT_SPARE_PLL		5
+
+/* CMU_TOP MUX */
+#define CLK_MOUT_PLL_SHARED0		6
+#define CLK_MOUT_PLL_SHARED1		7
+#define CLK_MOUT_PLL_SHARED2		8
+#define CLK_MOUT_PLL_SHARED3		9
+#define CLK_MOUT_PLL_SPARE		10
+#define CLK_MOUT_CMU_BO_BUS		11
+#define CLK_MOUT_CMU_BUS0_BUS		12
+#define CLK_MOUT_CMU_BUS1_BUS		13
+#define CLK_MOUT_CMU_BUS2_BUS		14
+#define CLK_MOUT_CMU_CIS_CLK0		15
+#define CLK_MOUT_CMU_CIS_CLK1		16
+#define CLK_MOUT_CMU_CIS_CLK2		17
+#define CLK_MOUT_CMU_CIS_CLK3		18
+#define CLK_MOUT_CMU_CIS_CLK4		19
+#define CLK_MOUT_CMU_CIS_CLK5		20
+#define CLK_MOUT_CMU_CIS_CLK6		21
+#define CLK_MOUT_CMU_CIS_CLK7		22
+#define CLK_MOUT_CMU_CMU_BOOST		23
+#define CLK_MOUT_CMU_BOOST_OPTION1	24
+#define CLK_MOUT_CMU_CORE_BUS		25
+#define CLK_MOUT_CMU_CPUCL0_DBG		26
+#define CLK_MOUT_CMU_CPUCL0_SWITCH	27
+#define CLK_MOUT_CMU_CPUCL1_SWITCH	28
+#define CLK_MOUT_CMU_CPUCL2_SWITCH	29
+#define CLK_MOUT_CMU_CSIS_BUS		30
+#define CLK_MOUT_CMU_DISP_BUS		31
+#define CLK_MOUT_CMU_DNS_BUS		32
+#define CLK_MOUT_CMU_DPU_BUS		33
+#define CLK_MOUT_CMU_EH_BUS		34
+#define CLK_MOUT_CMU_G2D_G2D		35
+#define CLK_MOUT_CMU_G2D_MSCL		36
+#define CLK_MOUT_CMU_G3AA_G3AA		37
+#define CLK_MOUT_CMU_G3D_BUSD		38
+#define CLK_MOUT_CMU_G3D_GLB		39
+#define CLK_MOUT_CMU_G3D_SWITCH		40
+#define CLK_MOUT_CMU_GDC_GDC0		41
+#define CLK_MOUT_CMU_GDC_GDC1		42
+#define CLK_MOUT_CMU_GDC_SCSC		43
+#define CLK_MOUT_CMU_HPM		44
+#define CLK_MOUT_CMU_HSI0_BUS		45
+#define CLK_MOUT_CMU_HSI0_DPGTC		46
+#define CLK_MOUT_CMU_HSI0_USB31DRD	47
+#define CLK_MOUT_CMU_HSI0_USBDPDBG	48
+#define CLK_MOUT_CMU_HSI1_BUS		49
+#define CLK_MOUT_CMU_HSI1_PCIE		50
+#define CLK_MOUT_CMU_HSI2_BUS		51
+#define CLK_MOUT_CMU_HSI2_MMC_CARD	52
+#define CLK_MOUT_CMU_HSI2_PCIE		53
+#define CLK_MOUT_CMU_HSI2_UFS_EMBD	54
+#define CLK_MOUT_CMU_IPP_BUS		55
+#define CLK_MOUT_CMU_ITP_BUS		56
+#define CLK_MOUT_CMU_MCSC_ITSC		57
+#define CLK_MOUT_CMU_MCSC_MCSC		58
+#define CLK_MOUT_CMU_MFC_MFC		59
+#define CLK_MOUT_CMU_MIF_BUSP		60
+#define CLK_MOUT_CMU_MIF_SWITCH		61
+#define CLK_MOUT_CMU_MISC_BUS		62
+#define CLK_MOUT_CMU_MISC_SSS		63
+#define CLK_MOUT_CMU_PDP_BUS		64
+#define CLK_MOUT_CMU_PDP_VRA		65
+#define CLK_MOUT_CMU_PERIC0_BUS		66
+#define CLK_MOUT_CMU_PERIC0_IP		67
+#define CLK_MOUT_CMU_PERIC1_BUS		68
+#define CLK_MOUT_CMU_PERIC1_IP		69
+#define CLK_MOUT_CMU_TNR_BUS		70
+#define CLK_MOUT_CMU_TOP_BOOST_OPTION1	71
+#define CLK_MOUT_CMU_TOP_CMUREF		72
+#define CLK_MOUT_CMU_TPU_BUS		73
+#define CLK_MOUT_CMU_TPU_TPU		74
+#define CLK_MOUT_CMU_TPU_TPUCTL		75
+#define CLK_MOUT_CMU_TPU_UART		76
+#define CLK_MOUT_CMU_CMUREF		77
+
+/* CMU_TOP Dividers */
+#define CLK_DOUT_CMU_BO_BUS		78
+#define CLK_DOUT_CMU_BUS0_BUS		79
+#define CLK_DOUT_CMU_BUS1_BUS		80
+#define CLK_DOUT_CMU_BUS2_BUS		81
+#define CLK_DOUT_CMU_CIS_CLK0		82
+#define CLK_DOUT_CMU_CIS_CLK1		83
+#define CLK_DOUT_CMU_CIS_CLK2		84
+#define CLK_DOUT_CMU_CIS_CLK3		85
+#define CLK_DOUT_CMU_CIS_CLK4		86
+#define CLK_DOUT_CMU_CIS_CLK5		87
+#define CLK_DOUT_CMU_CIS_CLK6		88
+#define CLK_DOUT_CMU_CIS_CLK7		89
+#define CLK_DOUT_CMU_CORE_BUS		90
+#define CLK_DOUT_CMU_CPUCL0_DBG		91
+#define CLK_DOUT_CMU_CPUCL0_SWITCH	92
+#define CLK_DOUT_CMU_CPUCL1_SWITCH	93
+#define CLK_DOUT_CMU_CPUCL2_SWITCH	94
+#define CLK_DOUT_CMU_CSIS_BUS		95
+#define CLK_DOUT_CMU_DISP_BUS		96
+#define CLK_DOUT_CMU_DNS_BUS		97
+#define CLK_DOUT_CMU_DPU_BUS		98
+#define CLK_DOUT_CMU_EH_BUS		99
+#define CLK_DOUT_CMU_G2D_G2D		100
+#define CLK_DOUT_CMU_G2D_MSCL		101
+#define CLK_DOUT_CMU_G3AA_G3AA		102
+#define CLK_DOUT_CMU_G3D_BUSD		103
+#define CLK_DOUT_CMU_G3D_GLB		104
+#define CLK_DOUT_CMU_G3D_SWITCH		105
+#define CLK_DOUT_CMU_GDC_GDC0		106
+#define CLK_DOUT_CMU_GDC_GDC1		107
+#define CLK_DOUT_CMU_GDC_SCSC		108
+#define CLK_DOUT_CMU_CMU_HPM		109
+#define CLK_DOUT_CMU_HSI0_BUS		110
+#define CLK_DOUT_CMU_HSI0_DPGTC		111
+#define CLK_DOUT_CMU_HSI0_USB31DRD	112
+#define CLK_DOUT_CMU_HSI0_USBDPDBG	113
+#define CLK_DOUT_CMU_HSI1_BUS		114
+#define CLK_DOUT_CMU_HSI1_PCIE		115
+#define CLK_DOUT_CMU_HSI2_BUS		116
+#define CLK_DOUT_CMU_HSI2_MMC_CARD	117
+#define CLK_DOUT_CMU_HSI2_PCIE		118
+#define CLK_DOUT_CMU_HSI2_UFS_EMBD	119
+#define CLK_DOUT_CMU_IPP_BUS		120
+#define CLK_DOUT_CMU_ITP_BUS		121
+#define CLK_DOUT_CMU_MCSC_ITSC		122
+#define CLK_DOUT_CMU_MCSC_MCSC		123
+#define CLK_DOUT_CMU_MFC_MFC		124
+#define CLK_DOUT_CMU_MIF_BUSP		125
+#define CLK_DOUT_CMU_MISC_BUS		126
+#define CLK_DOUT_CMU_MISC_SSS		127
+#define CLK_DOUT_CMU_OTP		128
+#define CLK_DOUT_CMU_PDP_BUS		129
+#define CLK_DOUT_CMU_PDP_VRA		130
+#define CLK_DOUT_CMU_PERIC0_BUS		131
+#define CLK_DOUT_CMU_PERIC0_IP		132
+#define CLK_DOUT_CMU_PERIC1_BUS		133
+#define CLK_DOUT_CMU_PERIC1_IP		134
+#define CLK_DOUT_CMU_TNR_BUS		135
+#define CLK_DOUT_CMU_TPU_BUS		136
+#define CLK_DOUT_CMU_TPU_TPU		137
+#define CLK_DOUT_CMU_TPU_TPUCTL		138
+#define CLK_DOUT_CMU_TPU_UART		139
+#define CLK_DOUT_CMU_CMU_BOOST		140
+#define CLK_DOUT_CMU_CMU_CMUREF		141
+#define CLK_DOUT_CMU_SHARED0_DIV2	142
+#define CLK_DOUT_CMU_SHARED0_DIV3	143
+#define CLK_DOUT_CMU_SHARED0_DIV4	144
+#define CLK_DOUT_CMU_SHARED0_DIV5	145
+#define CLK_DOUT_CMU_SHARED1_DIV2	146
+#define CLK_DOUT_CMU_SHARED1_DIV3	147
+#define CLK_DOUT_CMU_SHARED1_DIV4	148
+#define CLK_DOUT_CMU_SHARED2_DIV2	149
+#define CLK_DOUT_CMU_SHARED3_DIV2	150
+
+/* CMU_TOP Gates */
+#define CLK_GOUT_CMU_BUS0_BOOST		151
+#define CLK_GOUT_CMU_BUS1_BOOST		152
+#define CLK_GOUT_CMU_BUS2_BOOST		153
+#define CLK_GOUT_CMU_CORE_BOOST		154
+#define CLK_GOUT_CMU_CPUCL0_BOOST	155
+#define CLK_GOUT_CMU_CPUCL1_BOOST	156
+#define CLK_GOUT_CMU_CPUCL2_BOOST	157
+#define CLK_GOUT_CMU_MIF_BOOST		158
+#define CLK_GOUT_CMU_MIF_SWITCH		159
+#define CLK_GOUT_CMU_BO_BUS		160
+#define CLK_GOUT_CMU_BUS0_BUS		161
+#define CLK_GOUT_CMU_BUS1_BUS		162
+#define CLK_GOUT_CMU_BUS2_BUS		163
+#define CLK_GOUT_CMU_CIS_CLK0		164
+#define CLK_GOUT_CMU_CIS_CLK1		165
+#define CLK_GOUT_CMU_CIS_CLK2		166
+#define CLK_GOUT_CMU_CIS_CLK3		167
+#define CLK_GOUT_CMU_CIS_CLK4		168
+#define CLK_GOUT_CMU_CIS_CLK5		169
+#define CLK_GOUT_CMU_CIS_CLK6		170
+#define CLK_GOUT_CMU_CIS_CLK7		171
+#define CLK_GOUT_CMU_CMU_BOOST		172
+#define CLK_GOUT_CMU_CORE_BUS		173
+#define CLK_GOUT_CMU_CPUCL0_DBG		174
+#define CLK_GOUT_CMU_CPUCL0_SWITCH	175
+#define CLK_GOUT_CMU_CPUCL1_SWITCH	176
+#define CLK_GOUT_CMU_CPUCL2_SWITCH	177
+#define CLK_GOUT_CMU_CSIS_BUS		178
+#define CLK_GOUT_CMU_DISP_BUS		179
+#define CLK_GOUT_CMU_DNS_BUS		180
+#define CLK_GOUT_CMU_DPU_BUS		181
+#define CLK_GOUT_CMU_EH_BUS		182
+#define CLK_GOUT_CMU_G2D_G2D		183
+#define CLK_GOUT_CMU_G2D_MSCL		184
+#define CLK_GOUT_CMU_G3AA_G3AA		185
+#define CLK_GOUT_CMU_G3D_BUSD		186
+#define CLK_GOUT_CMU_G3D_GLB		187
+#define CLK_GOUT_CMU_G3D_SWITCH		188
+#define CLK_GOUT_CMU_GDC_GDC0		189
+#define CLK_GOUT_CMU_GDC_GDC1		190
+#define CLK_GOUT_CMU_GDC_SCSC		191
+#define CLK_GOUT_CMU_HPM		192
+#define CLK_GOUT_CMU_HSI0_BUS		193
+#define CLK_GOUT_CMU_HSI0_DPGTC		194
+#define CLK_GOUT_CMU_HSI0_USB31DRD	195
+#define CLK_GOUT_CMU_HSI0_USBDPDBG	196
+#define CLK_GOUT_CMU_HSI1_BUS		197
+#define CLK_GOUT_CMU_HSI1_PCIE		198
+#define CLK_GOUT_CMU_HSI2_BUS		199
+#define CLK_GOUT_CMU_HSI2_MMC_CARD	200
+#define CLK_GOUT_CMU_HSI2_PCIE		201
+#define CLK_GOUT_CMU_HSI2_UFS_EMBD	202
+#define CLK_GOUT_CMU_IPP_BUS		203
+#define CLK_GOUT_CMU_ITP_BUS		204
+#define CLK_GOUT_CMU_MCSC_ITSC		205
+#define CLK_GOUT_CMU_MCSC_MCSC		206
+#define CLK_GOUT_CMU_MFC_MFC		207
+#define CLK_GOUT_CMU_MIF_BUSP		208
+#define CLK_GOUT_CMU_MISC_BUS		209
+#define CLK_GOUT_CMU_MISC_SSS		210
+#define CLK_GOUT_CMU_PDP_BUS		211
+#define CLK_GOUT_CMU_PDP_VRA		212
+#define CLK_GOUT_CMU_G3AA		213
+#define CLK_GOUT_CMU_PERIC0_BUS		214
+#define CLK_GOUT_CMU_PERIC0_IP		215
+#define CLK_GOUT_CMU_PERIC1_BUS		216
+#define CLK_GOUT_CMU_PERIC1_IP		217
+#define CLK_GOUT_CMU_TNR_BUS		218
+#define CLK_GOUT_CMU_TOP_CMUREF		219
+#define CLK_GOUT_CMU_TPU_BUS		220
+#define CLK_GOUT_CMU_TPU_TPU		221
+#define CLK_GOUT_CMU_TPU_TPUCTL		222
+#define CLK_GOUT_CMU_TPU_UART		223
+
+/* CMU_APM */
+#define CLK_MOUT_APM_FUNC				1
+#define CLK_MOUT_APM_FUNCSRC				2
+#define CLK_DOUT_APM_BOOST				3
+#define CLK_DOUT_APM_USI0_UART				4
+#define CLK_DOUT_APM_USI0_USI				5
+#define CLK_DOUT_APM_USI1_UART				6
+#define CLK_GOUT_APM_APM_CMU_APM_PCLK			7
+#define CLK_GOUT_BUS0_BOOST_OPTION1			8
+#define CLK_GOUT_CMU_BOOST_OPTION1			9
+#define CLK_GOUT_CORE_BOOST_OPTION1			10
+#define CLK_GOUT_APM_FUNC				11
+#define CLK_GOUT_APM_APBIF_GPIO_ALIVE_PCLK		12
+#define CLK_GOUT_APM_APBIF_GPIO_FAR_ALIVE_PCLK		13
+#define CLK_GOUT_APM_APBIF_PMU_ALIVE_PCLK		14
+#define CLK_GOUT_APM_APBIF_RTC_PCLK			15
+#define CLK_GOUT_APM_APBIF_TRTC_PCLK			16
+#define CLK_GOUT_APM_APM_USI0_UART_IPCLK		17
+#define CLK_GOUT_APM_APM_USI0_UART_PCLK			18
+#define CLK_GOUT_APM_APM_USI0_USI_IPCLK			19
+#define CLK_GOUT_APM_APM_USI0_USI_PCLK			20
+#define CLK_GOUT_APM_APM_USI1_UART_IPCLK		21
+#define CLK_GOUT_APM_APM_USI1_UART_PCLK			22
+#define CLK_GOUT_APM_D_TZPC_APM_PCLK			23
+#define CLK_GOUT_APM_GPC_APM_PCLK			24
+#define CLK_GOUT_APM_GREBEINTEGRATION_HCLK		25
+#define CLK_GOUT_APM_INTMEM_ACLK			26
+#define CLK_GOUT_APM_INTMEM_PCLK			27
+#define CLK_GOUT_APM_LHM_AXI_G_SWD_I_CLK		28
+#define CLK_GOUT_APM_LHM_AXI_P_AOCAPM_I_CLK		29
+#define CLK_GOUT_APM_LHM_AXI_P_APM_I_CLK		30
+#define CLK_GOUT_APM_LHS_AXI_D_APM_I_CLK		31
+#define CLK_GOUT_APM_LHS_AXI_G_DBGCORE_I_CLK		32
+#define CLK_GOUT_APM_LHS_AXI_G_SCAN2DRAM_I_CLK		33
+#define CLK_GOUT_APM_MAILBOX_APM_AOC_PCLK		34
+#define CLK_GOUT_APM_MAILBOX_APM_AP_PCLK		35
+#define CLK_GOUT_APM_MAILBOX_APM_GSA_PCLK		36
+#define CLK_GOUT_APM_MAILBOX_APM_SWD_PCLK		37
+#define CLK_GOUT_APM_MAILBOX_APM_TPU_PCLK		38
+#define CLK_GOUT_APM_MAILBOX_AP_AOC_PCLK		39
+#define CLK_GOUT_APM_MAILBOX_AP_DBGCORE_PCLK		40
+#define CLK_GOUT_APM_PMU_INTR_GEN_PCLK			41
+#define CLK_GOUT_APM_ROM_CRC32_HOST_ACLK		42
+#define CLK_GOUT_APM_ROM_CRC32_HOST_PCLK		43
+#define CLK_GOUT_APM_CLK_APM_BUS_CLK			44
+#define CLK_GOUT_APM_CLK_APM_USI0_UART_CLK		45
+#define CLK_GOUT_APM_CLK_APM_USI0_USI_CLK		46
+#define CLK_GOUT_APM_CLK_APM_USI1_UART_CLK		47
+#define CLK_GOUT_APM_SPEEDY_APM_PCLK			48
+#define CLK_GOUT_APM_SPEEDY_SUB_APM_PCLK		49
+#define CLK_GOUT_APM_SSMT_D_APM_ACLK			50
+#define CLK_GOUT_APM_SSMT_D_APM_PCLK			51
+#define CLK_GOUT_APM_SSMT_G_DBGCORE_ACLK		52
+#define CLK_GOUT_APM_SSMT_G_DBGCORE_PCLK		53
+#define CLK_GOUT_APM_SS_DBGCORE_SS_DBGCORE_HCLK		54
+#define CLK_GOUT_APM_SYSMMU_D_APM_CLK_S2		55
+#define CLK_GOUT_APM_SYSREG_APM_PCLK			56
+#define CLK_GOUT_APM_UASC_APM_ACLK			57
+#define CLK_GOUT_APM_UASC_APM_PCLK			58
+#define CLK_GOUT_APM_UASC_DBGCORE_ACLK			59
+#define CLK_GOUT_APM_UASC_DBGCORE_PCLK			60
+#define CLK_GOUT_APM_UASC_G_SWD_ACLK			61
+#define CLK_GOUT_APM_UASC_G_SWD_PCLK			62
+#define CLK_GOUT_APM_UASC_P_AOCAPM_ACLK			63
+#define CLK_GOUT_APM_UASC_P_AOCAPM_PCLK			64
+#define CLK_GOUT_APM_UASC_P_APM_ACLK			65
+#define CLK_GOUT_APM_UASC_P_APM_PCLK			66
+#define CLK_GOUT_APM_WDT_APM_PCLK			67
+#define CLK_GOUT_APM_XIU_DP_APM_ACLK			68
+#define CLK_APM_PLL_DIV2_APM				69
+#define CLK_APM_PLL_DIV4_APM				70
+#define CLK_APM_PLL_DIV16_APM				71
+
+/* CMU_MISC */
+#define CLK_MOUT_MISC_BUS_USER				1
+#define CLK_MOUT_MISC_SSS_USER				2
+#define CLK_MOUT_MISC_GIC				3
+#define CLK_DOUT_MISC_BUSP				4
+#define CLK_DOUT_MISC_GIC				5
+#define CLK_GOUT_MISC_MISC_CMU_MISC_PCLK		6
+#define CLK_GOUT_MISC_OTP_CON_BIRA_I_OSCCLK		7
+#define CLK_GOUT_MISC_OTP_CON_BISR_I_OSCCLK		8
+#define CLK_GOUT_MISC_OTP_CON_TOP_I_OSCCLK		9
+#define CLK_GOUT_MISC_CLK_MISC_OSCCLK_CLK		10
+#define CLK_GOUT_MISC_ADM_AHB_SSS_HCLKM			11
+#define CLK_GOUT_MISC_AD_APB_DIT_PCLKM			12
+#define CLK_GOUT_MISC_AD_APB_PUF_PCLKM			13
+#define CLK_GOUT_MISC_DIT_ICLKL2A			14
+#define CLK_GOUT_MISC_D_TZPC_MISC_PCLK			15
+#define CLK_GOUT_MISC_GIC_GICCLK			16
+#define CLK_GOUT_MISC_GPC_MISC_PCLK			17
+#define CLK_GOUT_MISC_LHM_AST_ICC_CPUGIC_I_CLK		18
+#define CLK_GOUT_MISC_LHM_AXI_D_SSS_I_CLK		19
+#define CLK_GOUT_MISC_LHM_AXI_P_GIC_I_CLK		20
+#define CLK_GOUT_MISC_LHM_AXI_P_MISC_I_CLK		21
+#define CLK_GOUT_MISC_LHS_ACEL_D_MISC_I_CLK		22
+#define CLK_GOUT_MISC_LHS_AST_IRI_GICCPU_I_CLK		23
+#define CLK_GOUT_MISC_LHS_AXI_D_SSS_I_CLK		24
+#define CLK_GOUT_MISC_MCT_PCLK				25
+#define CLK_GOUT_MISC_OTP_CON_BIRA_PCLK			26
+#define CLK_GOUT_MISC_OTP_CON_BISR_PCLK			27
+#define CLK_GOUT_MISC_OTP_CON_TOP_PCLK			28
+#define CLK_GOUT_MISC_PDMA_ACLK				29
+#define CLK_GOUT_MISC_PPMU_DMA_ACLK			30
+#define CLK_GOUT_MISC_PPMU_MISC_ACLK			31
+#define CLK_GOUT_MISC_PPMU_MISC_PCLK			32
+#define CLK_GOUT_MISC_PUF_I_CLK				33
+#define CLK_GOUT_MISC_QE_DIT_ACLK			34
+#define CLK_GOUT_MISC_QE_DIT_PCLK			35
+#define CLK_GOUT_MISC_QE_PDMA_ACLK			36
+#define CLK_GOUT_MISC_QE_PDMA_PCLK			37
+#define CLK_GOUT_MISC_QE_PPMU_DMA_ACLK			38
+#define CLK_GOUT_MISC_QE_PPMU_DMA_PCLK			39
+#define CLK_GOUT_MISC_QE_RTIC_ACLK			40
+#define CLK_GOUT_MISC_QE_RTIC_PCLK			41
+#define CLK_GOUT_MISC_QE_SPDMA_ACLK			42
+#define CLK_GOUT_MISC_QE_SPDMA_PCLK			43
+#define CLK_GOUT_MISC_QE_SSS_ACLK			44
+#define CLK_GOUT_MISC_QE_SSS_PCLK			45
+#define CLK_GOUT_MISC_CLK_MISC_BUSD_CLK			46
+#define CLK_GOUT_MISC_CLK_MISC_BUSP_CLK			47
+#define CLK_GOUT_MISC_CLK_MISC_GIC_CLK			48
+#define CLK_GOUT_MISC_CLK_MISC_SSS_CLK			49
+#define CLK_GOUT_MISC_RTIC_I_ACLK			50
+#define CLK_GOUT_MISC_RTIC_I_PCLK			51
+#define CLK_GOUT_MISC_SPDMA_ACLK			52
+#define CLK_GOUT_MISC_SSMT_DIT_ACLK			53
+#define CLK_GOUT_MISC_SSMT_DIT_PCLK			54
+#define CLK_GOUT_MISC_SSMT_PDMA_ACLK			55
+#define CLK_GOUT_MISC_SSMT_PDMA_PCLK			56
+#define CLK_GOUT_MISC_SSMT_PPMU_DMA_ACLK		57
+#define CLK_GOUT_MISC_SSMT_PPMU_DMA_PCLK		58
+#define CLK_GOUT_MISC_SSMT_RTIC_ACLK			59
+#define CLK_GOUT_MISC_SSMT_RTIC_PCLK			60
+#define CLK_GOUT_MISC_SSMT_SPDMA_ACLK			61
+#define CLK_GOUT_MISC_SSMT_SPDMA_PCLK			62
+#define CLK_GOUT_MISC_SSMT_SSS_ACLK			63
+#define CLK_GOUT_MISC_SSMT_SSS_PCLK			64
+#define CLK_GOUT_MISC_SSS_I_ACLK			65
+#define CLK_GOUT_MISC_SSS_I_PCLK			66
+#define CLK_GOUT_MISC_SYSMMU_MISC_CLK_S2		67
+#define CLK_GOUT_MISC_SYSMMU_SSS_CLK_S1			68
+#define CLK_GOUT_MISC_SYSREG_MISC_PCLK			69
+#define CLK_GOUT_MISC_TMU_SUB_PCLK			70
+#define CLK_GOUT_MISC_TMU_TOP_PCLK			71
+#define CLK_GOUT_MISC_WDT_CLUSTER0_PCLK			72
+#define CLK_GOUT_MISC_WDT_CLUSTER1_PCLK			73
+#define CLK_GOUT_MISC_XIU_D_MISC_ACLK			74
+
+#endif /* _DT_BINDINGS_CLOCK_GOOGLE_GS101_H */
diff --git a/include/dt-bindings/clock/qcom,sc8280xp-camcc.h b/include/dt-bindings/clock/qcom,sc8280xp-camcc.h
new file mode 100644
index 000000000000..ea5ec73c8c6a
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,sc8280xp-camcc.h
@@ -0,0 +1,179 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2021, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2023, Linaro Ltd.
+ */
+
+#ifndef __DT_BINDINGS_CLK_QCOM_CAMCC_SC8280XP_H__
+#define __DT_BINDINGS_CLK_QCOM_CAMCC_SC8280XP_H__
+
+/* CAMCC clocks */
+#define CAMCC_PLL0					0
+#define CAMCC_PLL0_OUT_EVEN				1
+#define CAMCC_PLL0_OUT_ODD				2
+#define CAMCC_PLL1					3
+#define CAMCC_PLL1_OUT_EVEN				4
+#define CAMCC_PLL2					5
+#define CAMCC_PLL3					6
+#define CAMCC_PLL3_OUT_EVEN				7
+#define CAMCC_PLL4					8
+#define CAMCC_PLL4_OUT_EVEN				9
+#define CAMCC_PLL5					10
+#define CAMCC_PLL5_OUT_EVEN				11
+#define CAMCC_PLL6					12
+#define CAMCC_PLL6_OUT_EVEN				13
+#define CAMCC_PLL7					14
+#define CAMCC_PLL7_OUT_EVEN				15
+#define CAMCC_PLL7_OUT_ODD				16
+#define CAMCC_BPS_AHB_CLK				17
+#define CAMCC_BPS_AREG_CLK				18
+#define CAMCC_BPS_AXI_CLK				19
+#define CAMCC_BPS_CLK					20
+#define CAMCC_BPS_CLK_SRC				21
+#define CAMCC_CAMNOC_AXI_CLK				22
+#define CAMCC_CAMNOC_AXI_CLK_SRC			23
+#define CAMCC_CAMNOC_DCD_XO_CLK				24
+#define CAMCC_CCI_0_CLK					25
+#define CAMCC_CCI_0_CLK_SRC				26
+#define CAMCC_CCI_1_CLK					27
+#define CAMCC_CCI_1_CLK_SRC				28
+#define CAMCC_CCI_2_CLK					29
+#define CAMCC_CCI_2_CLK_SRC				30
+#define CAMCC_CCI_3_CLK					31
+#define CAMCC_CCI_3_CLK_SRC				32
+#define CAMCC_CORE_AHB_CLK				33
+#define CAMCC_CPAS_AHB_CLK				34
+#define CAMCC_CPHY_RX_CLK_SRC				35
+#define CAMCC_CSI0PHYTIMER_CLK				36
+#define CAMCC_CSI0PHYTIMER_CLK_SRC			37
+#define CAMCC_CSI1PHYTIMER_CLK				38
+#define CAMCC_CSI1PHYTIMER_CLK_SRC			39
+#define CAMCC_CSI2PHYTIMER_CLK				40
+#define CAMCC_CSI2PHYTIMER_CLK_SRC			41
+#define CAMCC_CSI3PHYTIMER_CLK				42
+#define CAMCC_CSI3PHYTIMER_CLK_SRC			43
+#define CAMCC_CSIPHY0_CLK				44
+#define CAMCC_CSIPHY1_CLK				45
+#define CAMCC_CSIPHY2_CLK				46
+#define CAMCC_CSIPHY3_CLK				47
+#define CAMCC_FAST_AHB_CLK_SRC				48
+#define CAMCC_GDSC_CLK					49
+#define CAMCC_ICP_AHB_CLK				50
+#define CAMCC_ICP_CLK					51
+#define CAMCC_ICP_CLK_SRC				52
+#define CAMCC_IFE_0_AXI_CLK				53
+#define CAMCC_IFE_0_CLK					54
+#define CAMCC_IFE_0_CLK_SRC				55
+#define CAMCC_IFE_0_CPHY_RX_CLK				56
+#define CAMCC_IFE_0_CSID_CLK				57
+#define CAMCC_IFE_0_CSID_CLK_SRC			58
+#define CAMCC_IFE_0_DSP_CLK				59
+#define CAMCC_IFE_1_AXI_CLK				60
+#define CAMCC_IFE_1_CLK					61
+#define CAMCC_IFE_1_CLK_SRC				62
+#define CAMCC_IFE_1_CPHY_RX_CLK				63
+#define CAMCC_IFE_1_CSID_CLK				64
+#define CAMCC_IFE_1_CSID_CLK_SRC			65
+#define CAMCC_IFE_1_DSP_CLK				66
+#define CAMCC_IFE_2_AXI_CLK				67
+#define CAMCC_IFE_2_CLK					68
+#define CAMCC_IFE_2_CLK_SRC				69
+#define CAMCC_IFE_2_CPHY_RX_CLK				70
+#define CAMCC_IFE_2_CSID_CLK				71
+#define CAMCC_IFE_2_CSID_CLK_SRC			72
+#define CAMCC_IFE_2_DSP_CLK				73
+#define CAMCC_IFE_3_AXI_CLK				74
+#define CAMCC_IFE_3_CLK					75
+#define CAMCC_IFE_3_CLK_SRC				76
+#define CAMCC_IFE_3_CPHY_RX_CLK				77
+#define CAMCC_IFE_3_CSID_CLK				78
+#define CAMCC_IFE_3_CSID_CLK_SRC			79
+#define CAMCC_IFE_3_DSP_CLK				80
+#define CAMCC_IFE_LITE_0_CLK				81
+#define CAMCC_IFE_LITE_0_CLK_SRC			82
+#define CAMCC_IFE_LITE_0_CPHY_RX_CLK			83
+#define CAMCC_IFE_LITE_0_CSID_CLK			84
+#define CAMCC_IFE_LITE_0_CSID_CLK_SRC			85
+#define CAMCC_IFE_LITE_1_CLK				86
+#define CAMCC_IFE_LITE_1_CLK_SRC			87
+#define CAMCC_IFE_LITE_1_CPHY_RX_CLK			88
+#define CAMCC_IFE_LITE_1_CSID_CLK			89
+#define CAMCC_IFE_LITE_1_CSID_CLK_SRC			90
+#define CAMCC_IFE_LITE_2_CLK				91
+#define CAMCC_IFE_LITE_2_CLK_SRC			92
+#define CAMCC_IFE_LITE_2_CPHY_RX_CLK			93
+#define CAMCC_IFE_LITE_2_CSID_CLK			94
+#define CAMCC_IFE_LITE_2_CSID_CLK_SRC			95
+#define CAMCC_IFE_LITE_3_CLK				96
+#define CAMCC_IFE_LITE_3_CLK_SRC			97
+#define CAMCC_IFE_LITE_3_CPHY_RX_CLK			98
+#define CAMCC_IFE_LITE_3_CSID_CLK			99
+#define CAMCC_IFE_LITE_3_CSID_CLK_SRC			100
+#define CAMCC_IPE_0_AHB_CLK				101
+#define CAMCC_IPE_0_AREG_CLK				102
+#define CAMCC_IPE_0_AXI_CLK				103
+#define CAMCC_IPE_0_CLK					104
+#define CAMCC_IPE_0_CLK_SRC				105
+#define CAMCC_IPE_1_AHB_CLK				106
+#define CAMCC_IPE_1_AREG_CLK				107
+#define CAMCC_IPE_1_AXI_CLK				108
+#define CAMCC_IPE_1_CLK					109
+#define CAMCC_JPEG_CLK					110
+#define CAMCC_JPEG_CLK_SRC				111
+#define CAMCC_LRME_CLK					112
+#define CAMCC_LRME_CLK_SRC				113
+#define CAMCC_MCLK0_CLK					114
+#define CAMCC_MCLK0_CLK_SRC				115
+#define CAMCC_MCLK1_CLK					116
+#define CAMCC_MCLK1_CLK_SRC				117
+#define CAMCC_MCLK2_CLK					118
+#define CAMCC_MCLK2_CLK_SRC				119
+#define CAMCC_MCLK3_CLK					120
+#define CAMCC_MCLK3_CLK_SRC				121
+#define CAMCC_MCLK4_CLK					122
+#define CAMCC_MCLK4_CLK_SRC				123
+#define CAMCC_MCLK5_CLK					124
+#define CAMCC_MCLK5_CLK_SRC				125
+#define CAMCC_MCLK6_CLK					126
+#define CAMCC_MCLK6_CLK_SRC				127
+#define CAMCC_MCLK7_CLK					128
+#define CAMCC_MCLK7_CLK_SRC				129
+#define CAMCC_SLEEP_CLK					130
+#define CAMCC_SLEEP_CLK_SRC				131
+#define CAMCC_SLOW_AHB_CLK_SRC				132
+#define CAMCC_XO_CLK_SRC				133
+
+/* CAMCC resets */
+#define CAMCC_BPS_BCR					0
+#define CAMCC_CAMNOC_BCR				1
+#define CAMCC_CCI_BCR					2
+#define CAMCC_CPAS_BCR					3
+#define CAMCC_CSI0PHY_BCR				4
+#define CAMCC_CSI1PHY_BCR				5
+#define CAMCC_CSI2PHY_BCR				6
+#define CAMCC_CSI3PHY_BCR				7
+#define CAMCC_ICP_BCR					8
+#define CAMCC_IFE_0_BCR					9
+#define CAMCC_IFE_1_BCR					10
+#define CAMCC_IFE_2_BCR					11
+#define CAMCC_IFE_3_BCR					12
+#define CAMCC_IFE_LITE_0_BCR				13
+#define CAMCC_IFE_LITE_1_BCR				14
+#define CAMCC_IFE_LITE_2_BCR				15
+#define CAMCC_IFE_LITE_3_BCR				16
+#define CAMCC_IPE_0_BCR					17
+#define CAMCC_IPE_1_BCR					18
+#define CAMCC_JPEG_BCR					19
+#define CAMCC_LRME_BCR					20
+
+/* CAMCC GDSCRs */
+#define BPS_GDSC					0
+#define IFE_0_GDSC					1
+#define IFE_1_GDSC					2
+#define IFE_2_GDSC					3
+#define IFE_3_GDSC					4
+#define IPE_0_GDSC					5
+#define IPE_1_GDSC					6
+#define TITAN_TOP_GDSC					7
+
+#endif /* __DT_BINDINGS_CLK_QCOM_CAMCC_SC8280XP_H__ */
diff --git a/include/dt-bindings/clock/qcom,sm8650-dispcc.h b/include/dt-bindings/clock/qcom,sm8650-dispcc.h
new file mode 100644
index 000000000000..b0a668b395a5
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,sm8650-dispcc.h
@@ -0,0 +1,102 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved
+ * Copyright (c) 2023, Linaro Ltd.
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_SM8650_DISP_CC_H
+#define _DT_BINDINGS_CLK_QCOM_SM8650_DISP_CC_H
+
+/* DISP_CC clocks */
+#define DISP_CC_MDSS_ACCU_CLK					0
+#define DISP_CC_MDSS_AHB1_CLK					1
+#define DISP_CC_MDSS_AHB_CLK					2
+#define DISP_CC_MDSS_AHB_CLK_SRC				3
+#define DISP_CC_MDSS_BYTE0_CLK					4
+#define DISP_CC_MDSS_BYTE0_CLK_SRC				5
+#define DISP_CC_MDSS_BYTE0_DIV_CLK_SRC				6
+#define DISP_CC_MDSS_BYTE0_INTF_CLK				7
+#define DISP_CC_MDSS_BYTE1_CLK					8
+#define DISP_CC_MDSS_BYTE1_CLK_SRC				9
+#define DISP_CC_MDSS_BYTE1_DIV_CLK_SRC				10
+#define DISP_CC_MDSS_BYTE1_INTF_CLK				11
+#define DISP_CC_MDSS_DPTX0_AUX_CLK				12
+#define DISP_CC_MDSS_DPTX0_AUX_CLK_SRC				13
+#define DISP_CC_MDSS_DPTX0_CRYPTO_CLK				14
+#define DISP_CC_MDSS_DPTX0_LINK_CLK				15
+#define DISP_CC_MDSS_DPTX0_LINK_CLK_SRC				16
+#define DISP_CC_MDSS_DPTX0_LINK_DIV_CLK_SRC			17
+#define DISP_CC_MDSS_DPTX0_LINK_INTF_CLK			18
+#define DISP_CC_MDSS_DPTX0_PIXEL0_CLK				19
+#define DISP_CC_MDSS_DPTX0_PIXEL0_CLK_SRC			20
+#define DISP_CC_MDSS_DPTX0_PIXEL1_CLK				21
+#define DISP_CC_MDSS_DPTX0_PIXEL1_CLK_SRC			22
+#define DISP_CC_MDSS_DPTX0_USB_ROUTER_LINK_INTF_CLK		23
+#define DISP_CC_MDSS_DPTX1_AUX_CLK				24
+#define DISP_CC_MDSS_DPTX1_AUX_CLK_SRC				25
+#define DISP_CC_MDSS_DPTX1_CRYPTO_CLK				26
+#define DISP_CC_MDSS_DPTX1_LINK_CLK				27
+#define DISP_CC_MDSS_DPTX1_LINK_CLK_SRC				28
+#define DISP_CC_MDSS_DPTX1_LINK_DIV_CLK_SRC			29
+#define DISP_CC_MDSS_DPTX1_LINK_INTF_CLK			30
+#define DISP_CC_MDSS_DPTX1_PIXEL0_CLK				31
+#define DISP_CC_MDSS_DPTX1_PIXEL0_CLK_SRC			32
+#define DISP_CC_MDSS_DPTX1_PIXEL1_CLK				33
+#define DISP_CC_MDSS_DPTX1_PIXEL1_CLK_SRC			34
+#define DISP_CC_MDSS_DPTX1_USB_ROUTER_LINK_INTF_CLK		35
+#define DISP_CC_MDSS_DPTX2_AUX_CLK				36
+#define DISP_CC_MDSS_DPTX2_AUX_CLK_SRC				37
+#define DISP_CC_MDSS_DPTX2_CRYPTO_CLK				38
+#define DISP_CC_MDSS_DPTX2_LINK_CLK				39
+#define DISP_CC_MDSS_DPTX2_LINK_CLK_SRC				40
+#define DISP_CC_MDSS_DPTX2_LINK_DIV_CLK_SRC			41
+#define DISP_CC_MDSS_DPTX2_LINK_INTF_CLK			42
+#define DISP_CC_MDSS_DPTX2_PIXEL0_CLK				43
+#define DISP_CC_MDSS_DPTX2_PIXEL0_CLK_SRC			44
+#define DISP_CC_MDSS_DPTX2_PIXEL1_CLK				45
+#define DISP_CC_MDSS_DPTX2_PIXEL1_CLK_SRC			46
+#define DISP_CC_MDSS_DPTX3_AUX_CLK				47
+#define DISP_CC_MDSS_DPTX3_AUX_CLK_SRC				48
+#define DISP_CC_MDSS_DPTX3_CRYPTO_CLK				49
+#define DISP_CC_MDSS_DPTX3_LINK_CLK				50
+#define DISP_CC_MDSS_DPTX3_LINK_CLK_SRC				51
+#define DISP_CC_MDSS_DPTX3_LINK_DIV_CLK_SRC			52
+#define DISP_CC_MDSS_DPTX3_LINK_INTF_CLK			53
+#define DISP_CC_MDSS_DPTX3_PIXEL0_CLK				54
+#define DISP_CC_MDSS_DPTX3_PIXEL0_CLK_SRC			55
+#define DISP_CC_MDSS_ESC0_CLK					56
+#define DISP_CC_MDSS_ESC0_CLK_SRC				57
+#define DISP_CC_MDSS_ESC1_CLK					58
+#define DISP_CC_MDSS_ESC1_CLK_SRC				59
+#define DISP_CC_MDSS_MDP1_CLK					60
+#define DISP_CC_MDSS_MDP_CLK					61
+#define DISP_CC_MDSS_MDP_CLK_SRC				62
+#define DISP_CC_MDSS_MDP_LUT1_CLK				63
+#define DISP_CC_MDSS_MDP_LUT_CLK				64
+#define DISP_CC_MDSS_NON_GDSC_AHB_CLK				65
+#define DISP_CC_MDSS_PCLK0_CLK					66
+#define DISP_CC_MDSS_PCLK0_CLK_SRC				67
+#define DISP_CC_MDSS_PCLK1_CLK					68
+#define DISP_CC_MDSS_PCLK1_CLK_SRC				69
+#define DISP_CC_MDSS_RSCC_AHB_CLK				70
+#define DISP_CC_MDSS_RSCC_VSYNC_CLK				71
+#define DISP_CC_MDSS_VSYNC1_CLK					72
+#define DISP_CC_MDSS_VSYNC_CLK					73
+#define DISP_CC_MDSS_VSYNC_CLK_SRC				74
+#define DISP_CC_PLL0						75
+#define DISP_CC_PLL1						76
+#define DISP_CC_SLEEP_CLK					77
+#define DISP_CC_SLEEP_CLK_SRC					78
+#define DISP_CC_XO_CLK						79
+#define DISP_CC_XO_CLK_SRC					80
+
+/* DISP_CC resets */
+#define DISP_CC_MDSS_CORE_BCR					0
+#define DISP_CC_MDSS_CORE_INT2_BCR				1
+#define DISP_CC_MDSS_RSCC_BCR					2
+
+/* DISP_CC GDSCR */
+#define MDSS_GDSC						0
+#define MDSS_INT2_GDSC						1
+
+#endif
diff --git a/include/dt-bindings/clock/qcom,sm8650-gcc.h b/include/dt-bindings/clock/qcom,sm8650-gcc.h
new file mode 100644
index 000000000000..0c543ba46079
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,sm8650-gcc.h
@@ -0,0 +1,254 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_GCC_SM8650_H
+#define _DT_BINDINGS_CLK_QCOM_GCC_SM8650_H
+
+/* GCC clocks */
+#define GCC_AGGRE_NOC_PCIE_AXI_CLK				0
+#define GCC_AGGRE_UFS_PHY_AXI_CLK				1
+#define GCC_AGGRE_UFS_PHY_AXI_HW_CTL_CLK			2
+#define GCC_AGGRE_USB3_PRIM_AXI_CLK				3
+#define GCC_BOOT_ROM_AHB_CLK					4
+#define GCC_CAMERA_AHB_CLK					5
+#define GCC_CAMERA_HF_AXI_CLK					6
+#define GCC_CAMERA_SF_AXI_CLK					7
+#define GCC_CAMERA_XO_CLK					8
+#define GCC_CFG_NOC_PCIE_ANOC_AHB_CLK				9
+#define GCC_CFG_NOC_USB3_PRIM_AXI_CLK				10
+#define GCC_CNOC_PCIE_SF_AXI_CLK				11
+#define GCC_DDRSS_GPU_AXI_CLK					12
+#define GCC_DDRSS_PCIE_SF_QTB_CLK				13
+#define GCC_DISP_AHB_CLK					14
+#define GCC_DISP_HF_AXI_CLK					15
+#define GCC_DISP_XO_CLK						16
+#define GCC_GP1_CLK						17
+#define GCC_GP1_CLK_SRC						18
+#define GCC_GP2_CLK						19
+#define GCC_GP2_CLK_SRC						20
+#define GCC_GP3_CLK						21
+#define GCC_GP3_CLK_SRC						22
+#define GCC_GPLL0						23
+#define GCC_GPLL0_OUT_EVEN					24
+#define GCC_GPLL1						25
+#define GCC_GPLL3						26
+#define GCC_GPLL4						27
+#define GCC_GPLL6						28
+#define GCC_GPLL7						29
+#define GCC_GPLL9						30
+#define GCC_GPU_CFG_AHB_CLK					31
+#define GCC_GPU_GPLL0_CLK_SRC					32
+#define GCC_GPU_GPLL0_DIV_CLK_SRC				33
+#define GCC_GPU_MEMNOC_GFX_CLK					34
+#define GCC_GPU_SNOC_DVM_GFX_CLK				35
+#define GCC_PCIE_0_AUX_CLK					36
+#define GCC_PCIE_0_AUX_CLK_SRC					37
+#define GCC_PCIE_0_CFG_AHB_CLK					38
+#define GCC_PCIE_0_MSTR_AXI_CLK					39
+#define GCC_PCIE_0_PHY_RCHNG_CLK				40
+#define GCC_PCIE_0_PHY_RCHNG_CLK_SRC				41
+#define GCC_PCIE_0_PIPE_CLK					42
+#define GCC_PCIE_0_PIPE_CLK_SRC					43
+#define GCC_PCIE_0_SLV_AXI_CLK					44
+#define GCC_PCIE_0_SLV_Q2A_AXI_CLK				45
+#define GCC_PCIE_1_AUX_CLK					46
+#define GCC_PCIE_1_AUX_CLK_SRC					47
+#define GCC_PCIE_1_CFG_AHB_CLK					48
+#define GCC_PCIE_1_MSTR_AXI_CLK					49
+#define GCC_PCIE_1_PHY_AUX_CLK					50
+#define GCC_PCIE_1_PHY_AUX_CLK_SRC				51
+#define GCC_PCIE_1_PHY_RCHNG_CLK				52
+#define GCC_PCIE_1_PHY_RCHNG_CLK_SRC				53
+#define GCC_PCIE_1_PIPE_CLK					54
+#define GCC_PCIE_1_PIPE_CLK_SRC					55
+#define GCC_PCIE_1_SLV_AXI_CLK					56
+#define GCC_PCIE_1_SLV_Q2A_AXI_CLK				57
+#define GCC_PDM2_CLK						58
+#define GCC_PDM2_CLK_SRC					59
+#define GCC_PDM_AHB_CLK						60
+#define GCC_PDM_XO4_CLK						61
+#define GCC_QMIP_CAMERA_NRT_AHB_CLK				62
+#define GCC_QMIP_CAMERA_RT_AHB_CLK				63
+#define GCC_QMIP_DISP_AHB_CLK					64
+#define GCC_QMIP_GPU_AHB_CLK					65
+#define GCC_QMIP_PCIE_AHB_CLK					66
+#define GCC_QMIP_VIDEO_CV_CPU_AHB_CLK				67
+#define GCC_QMIP_VIDEO_CVP_AHB_CLK				68
+#define GCC_QMIP_VIDEO_V_CPU_AHB_CLK				69
+#define GCC_QMIP_VIDEO_VCODEC_AHB_CLK				70
+#define GCC_QUPV3_I2C_CORE_CLK					71
+#define GCC_QUPV3_I2C_S0_CLK					72
+#define GCC_QUPV3_I2C_S0_CLK_SRC				73
+#define GCC_QUPV3_I2C_S1_CLK					74
+#define GCC_QUPV3_I2C_S1_CLK_SRC				75
+#define GCC_QUPV3_I2C_S2_CLK					76
+#define GCC_QUPV3_I2C_S2_CLK_SRC				77
+#define GCC_QUPV3_I2C_S3_CLK					78
+#define GCC_QUPV3_I2C_S3_CLK_SRC				79
+#define GCC_QUPV3_I2C_S4_CLK					80
+#define GCC_QUPV3_I2C_S4_CLK_SRC				81
+#define GCC_QUPV3_I2C_S5_CLK					82
+#define GCC_QUPV3_I2C_S5_CLK_SRC				83
+#define GCC_QUPV3_I2C_S6_CLK					84
+#define GCC_QUPV3_I2C_S6_CLK_SRC				85
+#define GCC_QUPV3_I2C_S7_CLK					86
+#define GCC_QUPV3_I2C_S7_CLK_SRC				87
+#define GCC_QUPV3_I2C_S8_CLK					88
+#define GCC_QUPV3_I2C_S8_CLK_SRC				89
+#define GCC_QUPV3_I2C_S9_CLK					90
+#define GCC_QUPV3_I2C_S9_CLK_SRC				91
+#define GCC_QUPV3_I2C_S_AHB_CLK					92
+#define GCC_QUPV3_WRAP1_CORE_2X_CLK				93
+#define GCC_QUPV3_WRAP1_CORE_CLK				94
+#define GCC_QUPV3_WRAP1_QSPI_REF_CLK				95
+#define GCC_QUPV3_WRAP1_QSPI_REF_CLK_SRC			96
+#define GCC_QUPV3_WRAP1_S0_CLK					97
+#define GCC_QUPV3_WRAP1_S0_CLK_SRC				98
+#define GCC_QUPV3_WRAP1_S1_CLK					99
+#define GCC_QUPV3_WRAP1_S1_CLK_SRC				100
+#define GCC_QUPV3_WRAP1_S2_CLK					101
+#define GCC_QUPV3_WRAP1_S2_CLK_SRC				102
+#define GCC_QUPV3_WRAP1_S3_CLK					103
+#define GCC_QUPV3_WRAP1_S3_CLK_SRC				104
+#define GCC_QUPV3_WRAP1_S4_CLK					105
+#define GCC_QUPV3_WRAP1_S4_CLK_SRC				106
+#define GCC_QUPV3_WRAP1_S5_CLK					107
+#define GCC_QUPV3_WRAP1_S5_CLK_SRC				108
+#define GCC_QUPV3_WRAP1_S6_CLK					109
+#define GCC_QUPV3_WRAP1_S6_CLK_SRC				110
+#define GCC_QUPV3_WRAP1_S7_CLK					111
+#define GCC_QUPV3_WRAP1_S7_CLK_SRC				112
+#define GCC_QUPV3_WRAP2_CORE_2X_CLK				113
+#define GCC_QUPV3_WRAP2_CORE_CLK				114
+#define GCC_QUPV3_WRAP2_IBI_CTRL_0_CLK_SRC			115
+#define GCC_QUPV3_WRAP2_IBI_CTRL_2_CLK				116
+#define GCC_QUPV3_WRAP2_IBI_CTRL_3_CLK				117
+#define GCC_QUPV3_WRAP2_S0_CLK					118
+#define GCC_QUPV3_WRAP2_S0_CLK_SRC				119
+#define GCC_QUPV3_WRAP2_S1_CLK					120
+#define GCC_QUPV3_WRAP2_S1_CLK_SRC				121
+#define GCC_QUPV3_WRAP2_S2_CLK					122
+#define GCC_QUPV3_WRAP2_S2_CLK_SRC				123
+#define GCC_QUPV3_WRAP2_S3_CLK					124
+#define GCC_QUPV3_WRAP2_S3_CLK_SRC				125
+#define GCC_QUPV3_WRAP2_S4_CLK					126
+#define GCC_QUPV3_WRAP2_S4_CLK_SRC				127
+#define GCC_QUPV3_WRAP2_S5_CLK					128
+#define GCC_QUPV3_WRAP2_S5_CLK_SRC				129
+#define GCC_QUPV3_WRAP2_S6_CLK					130
+#define GCC_QUPV3_WRAP2_S6_CLK_SRC				131
+#define GCC_QUPV3_WRAP2_S7_CLK					132
+#define GCC_QUPV3_WRAP2_S7_CLK_SRC				133
+#define GCC_QUPV3_WRAP3_CORE_2X_CLK				134
+#define GCC_QUPV3_WRAP3_CORE_CLK				135
+#define GCC_QUPV3_WRAP3_QSPI_REF_CLK				136
+#define GCC_QUPV3_WRAP3_QSPI_REF_CLK_SRC			137
+#define GCC_QUPV3_WRAP3_S0_CLK					138
+#define GCC_QUPV3_WRAP3_S0_CLK_SRC				139
+#define GCC_QUPV3_WRAP_1_M_AHB_CLK				140
+#define GCC_QUPV3_WRAP_1_S_AHB_CLK				141
+#define GCC_QUPV3_WRAP_2_IBI_2_AHB_CLK				142
+#define GCC_QUPV3_WRAP_2_IBI_3_AHB_CLK				143
+#define GCC_QUPV3_WRAP_2_M_AHB_CLK				144
+#define GCC_QUPV3_WRAP_2_S_AHB_CLK				145
+#define GCC_QUPV3_WRAP_3_M_AHB_CLK				146
+#define GCC_QUPV3_WRAP_3_S_AHB_CLK				147
+#define GCC_SDCC2_AHB_CLK					148
+#define GCC_SDCC2_APPS_CLK					149
+#define GCC_SDCC2_APPS_CLK_SRC					150
+#define GCC_SDCC4_AHB_CLK					151
+#define GCC_SDCC4_APPS_CLK					152
+#define GCC_SDCC4_APPS_CLK_SRC					153
+#define GCC_UFS_PHY_AHB_CLK					154
+#define GCC_UFS_PHY_AXI_CLK					155
+#define GCC_UFS_PHY_AXI_CLK_SRC					156
+#define GCC_UFS_PHY_AXI_HW_CTL_CLK				157
+#define GCC_UFS_PHY_ICE_CORE_CLK				158
+#define GCC_UFS_PHY_ICE_CORE_CLK_SRC				159
+#define GCC_UFS_PHY_ICE_CORE_HW_CTL_CLK				160
+#define GCC_UFS_PHY_PHY_AUX_CLK					161
+#define GCC_UFS_PHY_PHY_AUX_CLK_SRC				162
+#define GCC_UFS_PHY_PHY_AUX_HW_CTL_CLK				163
+#define GCC_UFS_PHY_RX_SYMBOL_0_CLK				164
+#define GCC_UFS_PHY_RX_SYMBOL_0_CLK_SRC				165
+#define GCC_UFS_PHY_RX_SYMBOL_1_CLK				166
+#define GCC_UFS_PHY_RX_SYMBOL_1_CLK_SRC				167
+#define GCC_UFS_PHY_TX_SYMBOL_0_CLK				168
+#define GCC_UFS_PHY_TX_SYMBOL_0_CLK_SRC				169
+#define GCC_UFS_PHY_UNIPRO_CORE_CLK				170
+#define GCC_UFS_PHY_UNIPRO_CORE_CLK_SRC				171
+#define GCC_UFS_PHY_UNIPRO_CORE_HW_CTL_CLK			172
+#define GCC_USB30_PRIM_MASTER_CLK				173
+#define GCC_USB30_PRIM_MASTER_CLK_SRC				174
+#define GCC_USB30_PRIM_MOCK_UTMI_CLK				175
+#define GCC_USB30_PRIM_MOCK_UTMI_CLK_SRC			176
+#define GCC_USB30_PRIM_MOCK_UTMI_POSTDIV_CLK_SRC		177
+#define GCC_USB30_PRIM_SLEEP_CLK				178
+#define GCC_USB3_PRIM_PHY_AUX_CLK				179
+#define GCC_USB3_PRIM_PHY_AUX_CLK_SRC				180
+#define GCC_USB3_PRIM_PHY_COM_AUX_CLK				181
+#define GCC_USB3_PRIM_PHY_PIPE_CLK				182
+#define GCC_USB3_PRIM_PHY_PIPE_CLK_SRC				183
+#define GCC_VIDEO_AHB_CLK					184
+#define GCC_VIDEO_AXI0_CLK					185
+#define GCC_VIDEO_AXI1_CLK					186
+#define GCC_VIDEO_XO_CLK					187
+#define GCC_GPLL0_AO						188
+#define GCC_GPLL0_OUT_EVEN_AO					189
+#define GCC_GPLL1_AO						190
+#define GCC_GPLL3_AO						191
+#define GCC_GPLL4_AO						192
+#define GCC_GPLL6_AO						193
+
+/* GCC resets */
+#define GCC_CAMERA_BCR						0
+#define GCC_DISPLAY_BCR						1
+#define GCC_GPU_BCR						2
+#define GCC_PCIE_0_BCR						3
+#define GCC_PCIE_0_LINK_DOWN_BCR				4
+#define GCC_PCIE_0_NOCSR_COM_PHY_BCR				5
+#define GCC_PCIE_0_PHY_BCR					6
+#define GCC_PCIE_0_PHY_NOCSR_COM_PHY_BCR			7
+#define GCC_PCIE_1_BCR						8
+#define GCC_PCIE_1_LINK_DOWN_BCR				9
+#define GCC_PCIE_1_NOCSR_COM_PHY_BCR				10
+#define GCC_PCIE_1_PHY_BCR					11
+#define GCC_PCIE_1_PHY_NOCSR_COM_PHY_BCR			12
+#define GCC_PCIE_PHY_BCR					13
+#define GCC_PCIE_PHY_CFG_AHB_BCR				14
+#define GCC_PCIE_PHY_COM_BCR					15
+#define GCC_PDM_BCR						16
+#define GCC_QUPV3_WRAPPER_1_BCR					17
+#define GCC_QUPV3_WRAPPER_2_BCR					18
+#define GCC_QUPV3_WRAPPER_3_BCR					19
+#define GCC_QUPV3_WRAPPER_I2C_BCR				20
+#define GCC_QUSB2PHY_PRIM_BCR					21
+#define GCC_QUSB2PHY_SEC_BCR					22
+#define GCC_SDCC2_BCR						23
+#define GCC_SDCC4_BCR						24
+#define GCC_UFS_PHY_BCR						25
+#define GCC_USB30_PRIM_BCR					26
+#define GCC_USB3_DP_PHY_PRIM_BCR				27
+#define GCC_USB3_DP_PHY_SEC_BCR					28
+#define GCC_USB3_PHY_PRIM_BCR					29
+#define GCC_USB3_PHY_SEC_BCR					30
+#define GCC_USB3PHY_PHY_PRIM_BCR				31
+#define GCC_USB3PHY_PHY_SEC_BCR					32
+#define GCC_VIDEO_AXI0_CLK_ARES					33
+#define GCC_VIDEO_AXI1_CLK_ARES					34
+#define GCC_VIDEO_BCR						35
+
+/* GCC power domains */
+#define PCIE_0_GDSC						0
+#define PCIE_0_PHY_GDSC						1
+#define PCIE_1_GDSC						2
+#define PCIE_1_PHY_GDSC						3
+#define UFS_PHY_GDSC						4
+#define UFS_MEM_PHY_GDSC					5
+#define USB30_PRIM_GDSC						6
+#define USB3_PHY_GDSC						7
+
+#endif
diff --git a/include/dt-bindings/clock/qcom,sm8650-gpucc.h b/include/dt-bindings/clock/qcom,sm8650-gpucc.h
new file mode 100644
index 000000000000..d0dc457cfe75
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,sm8650-gpucc.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_GPU_CC_SM8650_H
+#define _DT_BINDINGS_CLK_QCOM_GPU_CC_SM8650_H
+
+/* GPU_CC clocks */
+#define GPU_CC_AHB_CLK				0
+#define GPU_CC_CRC_AHB_CLK			1
+#define GPU_CC_CX_ACCU_SHIFT_CLK		2
+#define GPU_CC_CX_FF_CLK			3
+#define GPU_CC_CX_GMU_CLK			4
+#define GPU_CC_CXO_AON_CLK			5
+#define GPU_CC_CXO_CLK				6
+#define GPU_CC_DEMET_CLK			7
+#define GPU_CC_DPM_CLK				8
+#define GPU_CC_FF_CLK_SRC			9
+#define GPU_CC_FREQ_MEASURE_CLK			10
+#define GPU_CC_GMU_CLK_SRC			11
+#define GPU_CC_GX_ACCU_SHIFT_CLK		12
+#define GPU_CC_GX_FF_CLK			13
+#define GPU_CC_GX_GFX3D_CLK			14
+#define GPU_CC_GX_GFX3D_RDVM_CLK		15
+#define GPU_CC_GX_GMU_CLK			16
+#define GPU_CC_GX_VSENSE_CLK			17
+#define GPU_CC_HLOS1_VOTE_GPU_SMMU_CLK		18
+#define GPU_CC_HUB_AON_CLK			19
+#define GPU_CC_HUB_CLK_SRC			20
+#define GPU_CC_HUB_CX_INT_CLK			21
+#define GPU_CC_HUB_DIV_CLK_SRC			22
+#define GPU_CC_MEMNOC_GFX_CLK			23
+#define GPU_CC_PLL0				24
+#define GPU_CC_PLL1				25
+#define GPU_CC_SLEEP_CLK			26
+
+/* GDSCs */
+#define GPU_GX_GDSC				0
+#define GPU_CX_GDSC				1
+
+#endif
diff --git a/include/dt-bindings/clock/qcom,sm8650-tcsr.h b/include/dt-bindings/clock/qcom,sm8650-tcsr.h
new file mode 100644
index 000000000000..b2c72d492f1f
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,sm8650-tcsr.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_TCSR_CC_SM8650_H
+#define _DT_BINDINGS_CLK_QCOM_TCSR_CC_SM8650_H
+
+/* TCSR CC clocks */
+#define TCSR_PCIE_0_CLKREF_EN					0
+#define TCSR_PCIE_1_CLKREF_EN					1
+#define TCSR_UFS_CLKREF_EN					2
+#define TCSR_UFS_PAD_CLKREF_EN					3
+#define TCSR_USB2_CLKREF_EN					4
+#define TCSR_USB3_CLKREF_EN					5
+
+#endif
diff --git a/include/dt-bindings/clock/qcom,x1e80100-gcc.h b/include/dt-bindings/clock/qcom,x1e80100-gcc.h
new file mode 100644
index 000000000000..24ba9e2a5cf6
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,x1e80100-gcc.h
@@ -0,0 +1,485 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2023, Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_GCC_X1E80100_H
+#define _DT_BINDINGS_CLK_QCOM_GCC_X1E80100_H
+
+/* GCC clocks */
+#define GCC_AGGRE_NOC_USB_NORTH_AXI_CLK				0
+#define GCC_AGGRE_NOC_USB_SOUTH_AXI_CLK				1
+#define GCC_AGGRE_UFS_PHY_AXI_CLK				2
+#define GCC_AGGRE_USB2_PRIM_AXI_CLK				3
+#define GCC_AGGRE_USB3_MP_AXI_CLK				4
+#define GCC_AGGRE_USB3_PRIM_AXI_CLK				5
+#define GCC_AGGRE_USB3_SEC_AXI_CLK				6
+#define GCC_AGGRE_USB3_TERT_AXI_CLK				7
+#define GCC_AGGRE_USB4_0_AXI_CLK				8
+#define GCC_AGGRE_USB4_1_AXI_CLK				9
+#define GCC_AGGRE_USB4_2_AXI_CLK				10
+#define GCC_AGGRE_USB_NOC_AXI_CLK				11
+#define GCC_AV1E_AHB_CLK					12
+#define GCC_AV1E_AXI_CLK					13
+#define GCC_AV1E_XO_CLK						14
+#define GCC_BOOT_ROM_AHB_CLK					15
+#define GCC_CAMERA_AHB_CLK					16
+#define GCC_CAMERA_HF_AXI_CLK					17
+#define GCC_CAMERA_SF_AXI_CLK					18
+#define GCC_CAMERA_XO_CLK					19
+#define GCC_CFG_NOC_PCIE_ANOC_AHB_CLK				20
+#define GCC_CFG_NOC_PCIE_ANOC_NORTH_AHB_CLK			21
+#define GCC_CFG_NOC_PCIE_ANOC_SOUTH_AHB_CLK			22
+#define GCC_CFG_NOC_USB2_PRIM_AXI_CLK				23
+#define GCC_CFG_NOC_USB3_MP_AXI_CLK				24
+#define GCC_CFG_NOC_USB3_PRIM_AXI_CLK				25
+#define GCC_CFG_NOC_USB3_SEC_AXI_CLK				26
+#define GCC_CFG_NOC_USB3_TERT_AXI_CLK				27
+#define GCC_CFG_NOC_USB_ANOC_AHB_CLK				28
+#define GCC_CFG_NOC_USB_ANOC_NORTH_AHB_CLK			29
+#define GCC_CFG_NOC_USB_ANOC_SOUTH_AHB_CLK			30
+#define GCC_CNOC_PCIE1_TUNNEL_CLK				31
+#define GCC_CNOC_PCIE2_TUNNEL_CLK				32
+#define GCC_CNOC_PCIE_NORTH_SF_AXI_CLK				33
+#define GCC_CNOC_PCIE_SOUTH_SF_AXI_CLK				34
+#define GCC_CNOC_PCIE_TUNNEL_CLK				35
+#define GCC_DDRSS_GPU_AXI_CLK					36
+#define GCC_DISP_AHB_CLK					37
+#define GCC_DISP_HF_AXI_CLK					38
+#define GCC_DISP_XO_CLK						39
+#define GCC_GP1_CLK						40
+#define GCC_GP1_CLK_SRC						41
+#define GCC_GP2_CLK						42
+#define GCC_GP2_CLK_SRC						43
+#define GCC_GP3_CLK						44
+#define GCC_GP3_CLK_SRC						45
+#define GCC_GPLL0						46
+#define GCC_GPLL0_OUT_EVEN					47
+#define GCC_GPLL4						48
+#define GCC_GPLL7						49
+#define GCC_GPLL8						50
+#define GCC_GPLL9						51
+#define GCC_GPU_CFG_AHB_CLK					52
+#define GCC_GPU_GPLL0_CPH_CLK_SRC				53
+#define GCC_GPU_GPLL0_DIV_CPH_CLK_SRC				54
+#define GCC_GPU_MEMNOC_GFX_CLK					55
+#define GCC_GPU_SNOC_DVM_GFX_CLK				56
+#define GCC_PCIE0_PHY_RCHNG_CLK					57
+#define GCC_PCIE1_PHY_RCHNG_CLK					58
+#define GCC_PCIE2_PHY_RCHNG_CLK					59
+#define GCC_PCIE_0_AUX_CLK					60
+#define GCC_PCIE_0_AUX_CLK_SRC					61
+#define GCC_PCIE_0_CFG_AHB_CLK					62
+#define GCC_PCIE_0_MSTR_AXI_CLK					63
+#define GCC_PCIE_0_PHY_RCHNG_CLK_SRC				64
+#define GCC_PCIE_0_PIPE_CLK					65
+#define GCC_PCIE_0_SLV_AXI_CLK					66
+#define GCC_PCIE_0_SLV_Q2A_AXI_CLK				67
+#define GCC_PCIE_1_AUX_CLK					68
+#define GCC_PCIE_1_AUX_CLK_SRC					69
+#define GCC_PCIE_1_CFG_AHB_CLK					70
+#define GCC_PCIE_1_MSTR_AXI_CLK					71
+#define GCC_PCIE_1_PHY_RCHNG_CLK_SRC				72
+#define GCC_PCIE_1_PIPE_CLK					73
+#define GCC_PCIE_1_SLV_AXI_CLK					74
+#define GCC_PCIE_1_SLV_Q2A_AXI_CLK				75
+#define GCC_PCIE_2_AUX_CLK					76
+#define GCC_PCIE_2_AUX_CLK_SRC					77
+#define GCC_PCIE_2_CFG_AHB_CLK					78
+#define GCC_PCIE_2_MSTR_AXI_CLK					79
+#define GCC_PCIE_2_PHY_RCHNG_CLK_SRC				80
+#define GCC_PCIE_2_PIPE_CLK					81
+#define GCC_PCIE_2_SLV_AXI_CLK					82
+#define GCC_PCIE_2_SLV_Q2A_AXI_CLK				83
+#define GCC_PCIE_3_AUX_CLK					84
+#define GCC_PCIE_3_AUX_CLK_SRC					85
+#define GCC_PCIE_3_CFG_AHB_CLK					86
+#define GCC_PCIE_3_MSTR_AXI_CLK					87
+#define GCC_PCIE_3_PHY_AUX_CLK					88
+#define GCC_PCIE_3_PHY_RCHNG_CLK				89
+#define GCC_PCIE_3_PHY_RCHNG_CLK_SRC				90
+#define GCC_PCIE_3_PIPE_CLK					91
+#define GCC_PCIE_3_PIPE_DIV_CLK_SRC				92
+#define GCC_PCIE_3_PIPEDIV2_CLK					93
+#define GCC_PCIE_3_SLV_AXI_CLK					94
+#define GCC_PCIE_3_SLV_Q2A_AXI_CLK				95
+#define GCC_PCIE_4_AUX_CLK					96
+#define GCC_PCIE_4_AUX_CLK_SRC					97
+#define GCC_PCIE_4_CFG_AHB_CLK					98
+#define GCC_PCIE_4_MSTR_AXI_CLK					99
+#define GCC_PCIE_4_PHY_RCHNG_CLK				100
+#define GCC_PCIE_4_PHY_RCHNG_CLK_SRC				101
+#define GCC_PCIE_4_PIPE_CLK					102
+#define GCC_PCIE_4_PIPE_DIV_CLK_SRC				103
+#define GCC_PCIE_4_PIPEDIV2_CLK					104
+#define GCC_PCIE_4_SLV_AXI_CLK					105
+#define GCC_PCIE_4_SLV_Q2A_AXI_CLK				106
+#define GCC_PCIE_5_AUX_CLK					107
+#define GCC_PCIE_5_AUX_CLK_SRC					108
+#define GCC_PCIE_5_CFG_AHB_CLK					109
+#define GCC_PCIE_5_MSTR_AXI_CLK					110
+#define GCC_PCIE_5_PHY_RCHNG_CLK				111
+#define GCC_PCIE_5_PHY_RCHNG_CLK_SRC				112
+#define GCC_PCIE_5_PIPE_CLK					113
+#define GCC_PCIE_5_PIPE_DIV_CLK_SRC				114
+#define GCC_PCIE_5_PIPEDIV2_CLK					115
+#define GCC_PCIE_5_SLV_AXI_CLK					116
+#define GCC_PCIE_5_SLV_Q2A_AXI_CLK				117
+#define GCC_PCIE_6A_AUX_CLK					118
+#define GCC_PCIE_6A_AUX_CLK_SRC					119
+#define GCC_PCIE_6A_CFG_AHB_CLK					120
+#define GCC_PCIE_6A_MSTR_AXI_CLK				121
+#define GCC_PCIE_6A_PHY_AUX_CLK					122
+#define GCC_PCIE_6A_PHY_RCHNG_CLK				123
+#define GCC_PCIE_6A_PHY_RCHNG_CLK_SRC				124
+#define GCC_PCIE_6A_PIPE_CLK					125
+#define GCC_PCIE_6A_PIPE_DIV_CLK_SRC				126
+#define GCC_PCIE_6A_PIPEDIV2_CLK				127
+#define GCC_PCIE_6A_SLV_AXI_CLK					128
+#define GCC_PCIE_6A_SLV_Q2A_AXI_CLK				129
+#define GCC_PCIE_6B_AUX_CLK					130
+#define GCC_PCIE_6B_AUX_CLK_SRC					131
+#define GCC_PCIE_6B_CFG_AHB_CLK					132
+#define GCC_PCIE_6B_MSTR_AXI_CLK				133
+#define GCC_PCIE_6B_PHY_AUX_CLK					134
+#define GCC_PCIE_6B_PHY_RCHNG_CLK				135
+#define GCC_PCIE_6B_PHY_RCHNG_CLK_SRC				136
+#define GCC_PCIE_6B_PIPE_CLK					137
+#define GCC_PCIE_6B_PIPE_DIV_CLK_SRC				138
+#define GCC_PCIE_6B_PIPEDIV2_CLK				139
+#define GCC_PCIE_6B_SLV_AXI_CLK					140
+#define GCC_PCIE_6B_SLV_Q2A_AXI_CLK				141
+#define GCC_PCIE_RSCC_AHB_CLK					142
+#define GCC_PCIE_RSCC_XO_CLK					143
+#define GCC_PCIE_RSCC_XO_CLK_SRC				144
+#define GCC_PDM2_CLK						145
+#define GCC_PDM2_CLK_SRC					146
+#define GCC_PDM_AHB_CLK						147
+#define GCC_PDM_XO4_CLK						148
+#define GCC_QMIP_AV1E_AHB_CLK					149
+#define GCC_QMIP_CAMERA_NRT_AHB_CLK				150
+#define GCC_QMIP_CAMERA_RT_AHB_CLK				151
+#define GCC_QMIP_DISP_AHB_CLK					152
+#define GCC_QMIP_GPU_AHB_CLK					153
+#define GCC_QMIP_VIDEO_CV_CPU_AHB_CLK				154
+#define GCC_QMIP_VIDEO_CVP_AHB_CLK				155
+#define GCC_QMIP_VIDEO_V_CPU_AHB_CLK				156
+#define GCC_QMIP_VIDEO_VCODEC_AHB_CLK				157
+#define GCC_QUPV3_WRAP0_CORE_2X_CLK				158
+#define GCC_QUPV3_WRAP0_CORE_CLK				159
+#define GCC_QUPV3_WRAP0_QSPI_S2_CLK				160
+#define GCC_QUPV3_WRAP0_QSPI_S3_CLK				161
+#define GCC_QUPV3_WRAP0_S0_CLK					162
+#define GCC_QUPV3_WRAP0_S0_CLK_SRC				163
+#define GCC_QUPV3_WRAP0_S1_CLK					164
+#define GCC_QUPV3_WRAP0_S1_CLK_SRC				165
+#define GCC_QUPV3_WRAP0_S2_CLK					166
+#define GCC_QUPV3_WRAP0_S2_CLK_SRC				167
+#define GCC_QUPV3_WRAP0_S2_DIV_CLK_SRC				168
+#define GCC_QUPV3_WRAP0_S3_CLK					169
+#define GCC_QUPV3_WRAP0_S3_CLK_SRC				170
+#define GCC_QUPV3_WRAP0_S3_DIV_CLK_SRC				171
+#define GCC_QUPV3_WRAP0_S4_CLK					172
+#define GCC_QUPV3_WRAP0_S4_CLK_SRC				173
+#define GCC_QUPV3_WRAP0_S5_CLK					174
+#define GCC_QUPV3_WRAP0_S5_CLK_SRC				175
+#define GCC_QUPV3_WRAP0_S6_CLK					176
+#define GCC_QUPV3_WRAP0_S6_CLK_SRC				177
+#define GCC_QUPV3_WRAP0_S7_CLK					178
+#define GCC_QUPV3_WRAP0_S7_CLK_SRC				179
+#define GCC_QUPV3_WRAP1_CORE_2X_CLK				180
+#define GCC_QUPV3_WRAP1_CORE_CLK				181
+#define GCC_QUPV3_WRAP1_QSPI_S2_CLK				182
+#define GCC_QUPV3_WRAP1_QSPI_S3_CLK				183
+#define GCC_QUPV3_WRAP1_S0_CLK					184
+#define GCC_QUPV3_WRAP1_S0_CLK_SRC				185
+#define GCC_QUPV3_WRAP1_S1_CLK					186
+#define GCC_QUPV3_WRAP1_S1_CLK_SRC				187
+#define GCC_QUPV3_WRAP1_S2_CLK					188
+#define GCC_QUPV3_WRAP1_S2_CLK_SRC				189
+#define GCC_QUPV3_WRAP1_S2_DIV_CLK_SRC				190
+#define GCC_QUPV3_WRAP1_S3_CLK					191
+#define GCC_QUPV3_WRAP1_S3_CLK_SRC				192
+#define GCC_QUPV3_WRAP1_S3_DIV_CLK_SRC				193
+#define GCC_QUPV3_WRAP1_S4_CLK					194
+#define GCC_QUPV3_WRAP1_S4_CLK_SRC				195
+#define GCC_QUPV3_WRAP1_S5_CLK					196
+#define GCC_QUPV3_WRAP1_S5_CLK_SRC				197
+#define GCC_QUPV3_WRAP1_S6_CLK					198
+#define GCC_QUPV3_WRAP1_S6_CLK_SRC				199
+#define GCC_QUPV3_WRAP1_S7_CLK					200
+#define GCC_QUPV3_WRAP1_S7_CLK_SRC				201
+#define GCC_QUPV3_WRAP2_CORE_2X_CLK				202
+#define GCC_QUPV3_WRAP2_CORE_CLK				203
+#define GCC_QUPV3_WRAP2_QSPI_S2_CLK				204
+#define GCC_QUPV3_WRAP2_QSPI_S3_CLK				205
+#define GCC_QUPV3_WRAP2_S0_CLK					206
+#define GCC_QUPV3_WRAP2_S0_CLK_SRC				207
+#define GCC_QUPV3_WRAP2_S1_CLK					208
+#define GCC_QUPV3_WRAP2_S1_CLK_SRC				209
+#define GCC_QUPV3_WRAP2_S2_CLK					210
+#define GCC_QUPV3_WRAP2_S2_CLK_SRC				211
+#define GCC_QUPV3_WRAP2_S2_DIV_CLK_SRC				212
+#define GCC_QUPV3_WRAP2_S3_CLK					213
+#define GCC_QUPV3_WRAP2_S3_CLK_SRC				214
+#define GCC_QUPV3_WRAP2_S3_DIV_CLK_SRC				215
+#define GCC_QUPV3_WRAP2_S4_CLK					216
+#define GCC_QUPV3_WRAP2_S4_CLK_SRC				217
+#define GCC_QUPV3_WRAP2_S5_CLK					218
+#define GCC_QUPV3_WRAP2_S5_CLK_SRC				219
+#define GCC_QUPV3_WRAP2_S6_CLK					220
+#define GCC_QUPV3_WRAP2_S6_CLK_SRC				221
+#define GCC_QUPV3_WRAP2_S7_CLK					222
+#define GCC_QUPV3_WRAP2_S7_CLK_SRC				223
+#define GCC_QUPV3_WRAP_0_M_AHB_CLK				224
+#define GCC_QUPV3_WRAP_0_S_AHB_CLK				225
+#define GCC_QUPV3_WRAP_1_M_AHB_CLK				226
+#define GCC_QUPV3_WRAP_1_S_AHB_CLK				227
+#define GCC_QUPV3_WRAP_2_M_AHB_CLK				228
+#define GCC_QUPV3_WRAP_2_S_AHB_CLK				229
+#define GCC_SDCC2_AHB_CLK					230
+#define GCC_SDCC2_APPS_CLK					231
+#define GCC_SDCC2_APPS_CLK_SRC					232
+#define GCC_SDCC4_AHB_CLK					233
+#define GCC_SDCC4_APPS_CLK					234
+#define GCC_SDCC4_APPS_CLK_SRC					235
+#define GCC_SYS_NOC_USB_AXI_CLK					236
+#define GCC_UFS_PHY_AHB_CLK					237
+#define GCC_UFS_PHY_AXI_CLK					238
+#define GCC_UFS_PHY_AXI_CLK_SRC					239
+#define GCC_UFS_PHY_ICE_CORE_CLK				240
+#define GCC_UFS_PHY_ICE_CORE_CLK_SRC				241
+#define GCC_UFS_PHY_PHY_AUX_CLK					242
+#define GCC_UFS_PHY_PHY_AUX_CLK_SRC				243
+#define GCC_UFS_PHY_RX_SYMBOL_0_CLK				244
+#define GCC_UFS_PHY_RX_SYMBOL_1_CLK				245
+#define GCC_UFS_PHY_TX_SYMBOL_0_CLK				246
+#define GCC_UFS_PHY_UNIPRO_CORE_CLK				247
+#define GCC_UFS_PHY_UNIPRO_CORE_CLK_SRC				248
+#define GCC_USB20_MASTER_CLK					249
+#define GCC_USB20_MASTER_CLK_SRC				250
+#define GCC_USB20_MOCK_UTMI_CLK					251
+#define GCC_USB20_MOCK_UTMI_CLK_SRC				252
+#define GCC_USB20_MOCK_UTMI_POSTDIV_CLK_SRC			253
+#define GCC_USB20_SLEEP_CLK					254
+#define GCC_USB30_MP_MASTER_CLK					255
+#define GCC_USB30_MP_MASTER_CLK_SRC				256
+#define GCC_USB30_MP_MOCK_UTMI_CLK				257
+#define GCC_USB30_MP_MOCK_UTMI_CLK_SRC				258
+#define GCC_USB30_MP_MOCK_UTMI_POSTDIV_CLK_SRC			259
+#define GCC_USB30_MP_SLEEP_CLK					260
+#define GCC_USB30_PRIM_MASTER_CLK				261
+#define GCC_USB30_PRIM_MASTER_CLK_SRC				262
+#define GCC_USB30_PRIM_MOCK_UTMI_CLK				263
+#define GCC_USB30_PRIM_MOCK_UTMI_CLK_SRC			264
+#define GCC_USB30_PRIM_MOCK_UTMI_POSTDIV_CLK_SRC		265
+#define GCC_USB30_PRIM_SLEEP_CLK				266
+#define GCC_USB30_SEC_MASTER_CLK				267
+#define GCC_USB30_SEC_MASTER_CLK_SRC				268
+#define GCC_USB30_SEC_MOCK_UTMI_CLK				269
+#define GCC_USB30_SEC_MOCK_UTMI_CLK_SRC				270
+#define GCC_USB30_SEC_MOCK_UTMI_POSTDIV_CLK_SRC			271
+#define GCC_USB30_SEC_SLEEP_CLK					272
+#define GCC_USB30_TERT_MASTER_CLK				273
+#define GCC_USB30_TERT_MASTER_CLK_SRC				274
+#define GCC_USB30_TERT_MOCK_UTMI_CLK				275
+#define GCC_USB30_TERT_MOCK_UTMI_CLK_SRC			276
+#define GCC_USB30_TERT_MOCK_UTMI_POSTDIV_CLK_SRC		277
+#define GCC_USB30_TERT_SLEEP_CLK				278
+#define GCC_USB3_MP_PHY_AUX_CLK					279
+#define GCC_USB3_MP_PHY_AUX_CLK_SRC				280
+#define GCC_USB3_MP_PHY_COM_AUX_CLK				281
+#define GCC_USB3_MP_PHY_PIPE_0_CLK				282
+#define GCC_USB3_MP_PHY_PIPE_1_CLK				283
+#define GCC_USB3_PRIM_PHY_AUX_CLK				284
+#define GCC_USB3_PRIM_PHY_AUX_CLK_SRC				285
+#define GCC_USB3_PRIM_PHY_COM_AUX_CLK				286
+#define GCC_USB3_PRIM_PHY_PIPE_CLK				287
+#define GCC_USB3_SEC_PHY_AUX_CLK				288
+#define GCC_USB3_SEC_PHY_AUX_CLK_SRC				289
+#define GCC_USB3_SEC_PHY_COM_AUX_CLK				290
+#define GCC_USB3_SEC_PHY_PIPE_CLK				291
+#define GCC_USB3_TERT_PHY_AUX_CLK				292
+#define GCC_USB3_TERT_PHY_AUX_CLK_SRC				293
+#define GCC_USB3_TERT_PHY_COM_AUX_CLK				294
+#define GCC_USB3_TERT_PHY_PIPE_CLK				295
+#define GCC_USB4_0_CFG_AHB_CLK					296
+#define GCC_USB4_0_DP0_CLK					297
+#define GCC_USB4_0_DP1_CLK					298
+#define GCC_USB4_0_MASTER_CLK					299
+#define GCC_USB4_0_MASTER_CLK_SRC				300
+#define GCC_USB4_0_PHY_P2RR2P_PIPE_CLK				301
+#define GCC_USB4_0_PHY_PCIE_PIPE_CLK				302
+#define GCC_USB4_0_PHY_PCIE_PIPE_CLK_SRC			303
+#define GCC_USB4_0_PHY_RX0_CLK					304
+#define GCC_USB4_0_PHY_RX1_CLK					305
+#define GCC_USB4_0_PHY_USB_PIPE_CLK				306
+#define GCC_USB4_0_SB_IF_CLK					307
+#define GCC_USB4_0_SB_IF_CLK_SRC				308
+#define GCC_USB4_0_SYS_CLK					309
+#define GCC_USB4_0_TMU_CLK					310
+#define GCC_USB4_0_TMU_CLK_SRC					311
+#define GCC_USB4_1_CFG_AHB_CLK					312
+#define GCC_USB4_1_DP0_CLK					313
+#define GCC_USB4_1_DP1_CLK					314
+#define GCC_USB4_1_MASTER_CLK					315
+#define GCC_USB4_1_MASTER_CLK_SRC				316
+#define GCC_USB4_1_PHY_P2RR2P_PIPE_CLK				317
+#define GCC_USB4_1_PHY_PCIE_PIPE_CLK				318
+#define GCC_USB4_1_PHY_PCIE_PIPE_CLK_SRC			319
+#define GCC_USB4_1_PHY_RX0_CLK					320
+#define GCC_USB4_1_PHY_RX1_CLK					321
+#define GCC_USB4_1_PHY_USB_PIPE_CLK				322
+#define GCC_USB4_1_SB_IF_CLK					323
+#define GCC_USB4_1_SB_IF_CLK_SRC				324
+#define GCC_USB4_1_SYS_CLK					325
+#define GCC_USB4_1_TMU_CLK					326
+#define GCC_USB4_1_TMU_CLK_SRC					327
+#define GCC_USB4_2_CFG_AHB_CLK					328
+#define GCC_USB4_2_DP0_CLK					329
+#define GCC_USB4_2_DP1_CLK					330
+#define GCC_USB4_2_MASTER_CLK					331
+#define GCC_USB4_2_MASTER_CLK_SRC				332
+#define GCC_USB4_2_PHY_P2RR2P_PIPE_CLK				333
+#define GCC_USB4_2_PHY_PCIE_PIPE_CLK				334
+#define GCC_USB4_2_PHY_PCIE_PIPE_CLK_SRC			335
+#define GCC_USB4_2_PHY_RX0_CLK					336
+#define GCC_USB4_2_PHY_RX1_CLK					337
+#define GCC_USB4_2_PHY_USB_PIPE_CLK				338
+#define GCC_USB4_2_SB_IF_CLK					339
+#define GCC_USB4_2_SB_IF_CLK_SRC				340
+#define GCC_USB4_2_SYS_CLK					341
+#define GCC_USB4_2_TMU_CLK					342
+#define GCC_USB4_2_TMU_CLK_SRC					343
+#define GCC_VIDEO_AHB_CLK					344
+#define GCC_VIDEO_AXI0_CLK					345
+#define GCC_VIDEO_AXI1_CLK					346
+#define GCC_VIDEO_XO_CLK					347
+#define GCC_PCIE_3_PIPE_CLK_SRC					348
+#define GCC_PCIE_4_PIPE_CLK_SRC					349
+#define GCC_PCIE_5_PIPE_CLK_SRC					350
+#define GCC_PCIE_6A_PIPE_CLK_SRC				351
+#define GCC_PCIE_6B_PIPE_CLK_SRC				352
+#define GCC_USB3_PRIM_PHY_PIPE_CLK_SRC				353
+#define GCC_USB3_SEC_PHY_PIPE_CLK_SRC				354
+#define GCC_USB3_TERT_PHY_PIPE_CLK_SRC				355
+
+/* GCC power domains */
+#define GCC_PCIE_0_TUNNEL_GDSC					0
+#define GCC_PCIE_1_TUNNEL_GDSC					1
+#define GCC_PCIE_2_TUNNEL_GDSC					2
+#define GCC_PCIE_3_GDSC						3
+#define GCC_PCIE_3_PHY_GDSC					4
+#define GCC_PCIE_4_GDSC						5
+#define GCC_PCIE_4_PHY_GDSC					6
+#define GCC_PCIE_5_GDSC						7
+#define GCC_PCIE_5_PHY_GDSC					8
+#define GCC_PCIE_6_PHY_GDSC					9
+#define GCC_PCIE_6A_GDSC					10
+#define GCC_PCIE_6B_GDSC					11
+#define GCC_UFS_MEM_PHY_GDSC					12
+#define GCC_UFS_PHY_GDSC					13
+#define GCC_USB20_PRIM_GDSC					14
+#define GCC_USB30_MP_GDSC					15
+#define GCC_USB30_PRIM_GDSC					16
+#define GCC_USB30_SEC_GDSC					17
+#define GCC_USB30_TERT_GDSC					18
+#define GCC_USB3_MP_SS0_PHY_GDSC				19
+#define GCC_USB3_MP_SS1_PHY_GDSC				20
+#define GCC_USB4_0_GDSC						21
+#define GCC_USB4_1_GDSC						22
+#define GCC_USB4_2_GDSC						23
+#define GCC_USB_0_PHY_GDSC					24
+#define GCC_USB_1_PHY_GDSC					25
+#define GCC_USB_2_PHY_GDSC					26
+
+/* GCC resets */
+#define GCC_AV1E_BCR						0
+#define GCC_CAMERA_BCR						1
+#define GCC_DISPLAY_BCR						2
+#define GCC_GPU_BCR						3
+#define GCC_PCIE_0_LINK_DOWN_BCR				4
+#define GCC_PCIE_0_NOCSR_COM_PHY_BCR				5
+#define GCC_PCIE_0_PHY_BCR					6
+#define GCC_PCIE_0_PHY_NOCSR_COM_PHY_BCR			7
+#define GCC_PCIE_0_TUNNEL_BCR					8
+#define GCC_PCIE_1_LINK_DOWN_BCR				9
+#define GCC_PCIE_1_NOCSR_COM_PHY_BCR				10
+#define GCC_PCIE_1_PHY_BCR					11
+#define GCC_PCIE_1_PHY_NOCSR_COM_PHY_BCR			12
+#define GCC_PCIE_1_TUNNEL_BCR					13
+#define GCC_PCIE_2_LINK_DOWN_BCR				14
+#define GCC_PCIE_2_NOCSR_COM_PHY_BCR				15
+#define GCC_PCIE_2_PHY_BCR					16
+#define GCC_PCIE_2_PHY_NOCSR_COM_PHY_BCR			17
+#define GCC_PCIE_2_TUNNEL_BCR					18
+#define GCC_PCIE_3_BCR						19
+#define GCC_PCIE_3_LINK_DOWN_BCR				20
+#define GCC_PCIE_3_NOCSR_COM_PHY_BCR				21
+#define GCC_PCIE_3_PHY_BCR					22
+#define GCC_PCIE_3_PHY_NOCSR_COM_PHY_BCR			23
+#define GCC_PCIE_4_BCR						24
+#define GCC_PCIE_4_LINK_DOWN_BCR				25
+#define GCC_PCIE_4_NOCSR_COM_PHY_BCR				26
+#define GCC_PCIE_4_PHY_BCR					27
+#define GCC_PCIE_4_PHY_NOCSR_COM_PHY_BCR			28
+#define GCC_PCIE_5_BCR						29
+#define GCC_PCIE_5_LINK_DOWN_BCR				30
+#define GCC_PCIE_5_NOCSR_COM_PHY_BCR				31
+#define GCC_PCIE_5_PHY_BCR					32
+#define GCC_PCIE_5_PHY_NOCSR_COM_PHY_BCR			33
+#define GCC_PCIE_6A_BCR						34
+#define GCC_PCIE_6A_LINK_DOWN_BCR				35
+#define GCC_PCIE_6A_NOCSR_COM_PHY_BCR				36
+#define GCC_PCIE_6A_PHY_BCR					37
+#define GCC_PCIE_6A_PHY_NOCSR_COM_PHY_BCR			38
+#define GCC_PCIE_6B_BCR						39
+#define GCC_PCIE_6B_LINK_DOWN_BCR				40
+#define GCC_PCIE_6B_NOCSR_COM_PHY_BCR				41
+#define GCC_PCIE_6B_PHY_BCR					42
+#define GCC_PCIE_6B_PHY_NOCSR_COM_PHY_BCR			43
+#define GCC_PCIE_PHY_BCR					44
+#define GCC_PCIE_PHY_CFG_AHB_BCR				45
+#define GCC_PCIE_PHY_COM_BCR					46
+#define GCC_PCIE_RSCC_BCR					47
+#define GCC_PDM_BCR						48
+#define GCC_QUPV3_WRAPPER_0_BCR					49
+#define GCC_QUPV3_WRAPPER_1_BCR					50
+#define GCC_QUPV3_WRAPPER_2_BCR					51
+#define GCC_QUSB2PHY_HS0_MP_BCR					52
+#define GCC_QUSB2PHY_HS1_MP_BCR					53
+#define GCC_QUSB2PHY_PRIM_BCR					54
+#define GCC_QUSB2PHY_SEC_BCR					55
+#define GCC_QUSB2PHY_TERT_BCR					56
+#define GCC_QUSB2PHY_USB20_HS_BCR				57
+#define GCC_SDCC2_BCR						58
+#define GCC_SDCC4_BCR						59
+#define GCC_UFS_PHY_BCR						60
+#define GCC_USB20_PRIM_BCR					61
+#define GCC_USB30_MP_BCR					62
+#define GCC_USB30_PRIM_BCR					63
+#define GCC_USB30_SEC_BCR					64
+#define GCC_USB30_TERT_BCR					65
+#define GCC_USB3_MP_SS0_PHY_BCR					66
+#define GCC_USB3_MP_SS1_PHY_BCR					67
+#define GCC_USB3_PHY_PRIM_BCR					68
+#define GCC_USB3_PHY_SEC_BCR					69
+#define GCC_USB3_PHY_TERT_BCR					70
+#define GCC_USB3_UNIPHY_MP0_BCR					71
+#define GCC_USB3_UNIPHY_MP1_BCR					72
+#define GCC_USB3PHY_PHY_PRIM_BCR				73
+#define GCC_USB3PHY_PHY_SEC_BCR					74
+#define GCC_USB3PHY_PHY_TERT_BCR				75
+#define GCC_USB3UNIPHY_PHY_MP0_BCR				76
+#define GCC_USB3UNIPHY_PHY_MP1_BCR				77
+#define GCC_USB4_0_BCR						78
+#define GCC_USB4_0_DP0_PHY_PRIM_BCR				79
+#define GCC_USB4_1_DP0_PHY_SEC_BCR				80
+#define GCC_USB4_2_DP0_PHY_TERT_BCR				81
+#define GCC_USB4_1_BCR						82
+#define GCC_USB4_2_BCR						83
+#define GCC_USB_0_PHY_BCR					84
+#define GCC_USB_1_PHY_BCR					85
+#define GCC_USB_2_PHY_BCR					86
+#define GCC_VIDEO_BCR						87
+#endif
diff --git a/include/dt-bindings/iio/qcom,spmi-adc7-pm7325.h b/include/dt-bindings/iio/qcom,spmi-adc7-pm7325.h
new file mode 100644
index 000000000000..96908014e09e
--- /dev/null
+++ b/include/dt-bindings/iio/qcom,spmi-adc7-pm7325.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2020 The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_QCOM_SPMI_VADC_PM7325_H
+#define _DT_BINDINGS_QCOM_SPMI_VADC_PM7325_H
+
+#ifndef PM7325_SID
+#define PM7325_SID					1
+#endif
+
+#include <dt-bindings/iio/qcom,spmi-vadc.h>
+
+/* ADC channels for PM7325_ADC for PMIC7 */
+#define PM7325_ADC7_REF_GND			(PM7325_SID << 8 | ADC7_REF_GND)
+#define PM7325_ADC7_1P25VREF			(PM7325_SID << 8 | ADC7_1P25VREF)
+#define PM7325_ADC7_VREF_VADC			(PM7325_SID << 8 | ADC7_VREF_VADC)
+#define PM7325_ADC7_DIE_TEMP			(PM7325_SID << 8 | ADC7_DIE_TEMP)
+
+#define PM7325_ADC7_AMUX_THM1			(PM7325_SID << 8 | ADC7_AMUX_THM1)
+#define PM7325_ADC7_AMUX_THM2			(PM7325_SID << 8 | ADC7_AMUX_THM2)
+#define PM7325_ADC7_AMUX_THM3			(PM7325_SID << 8 | ADC7_AMUX_THM3)
+#define PM7325_ADC7_AMUX_THM4			(PM7325_SID << 8 | ADC7_AMUX_THM4)
+#define PM7325_ADC7_AMUX_THM5			(PM7325_SID << 8 | ADC7_AMUX_THM5)
+#define PM7325_ADC7_GPIO1			(PM7325_SID << 8 | ADC7_GPIO1)
+#define PM7325_ADC7_GPIO2			(PM7325_SID << 8 | ADC7_GPIO2)
+#define PM7325_ADC7_GPIO3			(PM7325_SID << 8 | ADC7_GPIO3)
+#define PM7325_ADC7_GPIO4			(PM7325_SID << 8 | ADC7_GPIO4)
+
+/* 30k pull-up1 */
+#define PM7325_ADC7_AMUX_THM1_30K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM1_30K_PU)
+#define PM7325_ADC7_AMUX_THM2_30K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM2_30K_PU)
+#define PM7325_ADC7_AMUX_THM3_30K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM3_30K_PU)
+#define PM7325_ADC7_AMUX_THM4_30K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM4_30K_PU)
+#define PM7325_ADC7_AMUX_THM5_30K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM5_30K_PU)
+#define PM7325_ADC7_GPIO1_30K_PU		(PM7325_SID << 8 | ADC7_GPIO1_30K_PU)
+#define PM7325_ADC7_GPIO2_30K_PU		(PM7325_SID << 8 | ADC7_GPIO2_30K_PU)
+#define PM7325_ADC7_GPIO3_30K_PU		(PM7325_SID << 8 | ADC7_GPIO3_30K_PU)
+#define PM7325_ADC7_GPIO4_30K_PU		(PM7325_SID << 8 | ADC7_GPIO4_30K_PU)
+
+/* 100k pull-up2 */
+#define PM7325_ADC7_AMUX_THM1_100K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM1_100K_PU)
+#define PM7325_ADC7_AMUX_THM2_100K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM2_100K_PU)
+#define PM7325_ADC7_AMUX_THM3_100K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM3_100K_PU)
+#define PM7325_ADC7_AMUX_THM4_100K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM4_100K_PU)
+#define PM7325_ADC7_AMUX_THM5_100K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM5_100K_PU)
+#define PM7325_ADC7_GPIO1_100K_PU		(PM7325_SID << 8 | ADC7_GPIO1_100K_PU)
+#define PM7325_ADC7_GPIO2_100K_PU		(PM7325_SID << 8 | ADC7_GPIO2_100K_PU)
+#define PM7325_ADC7_GPIO3_100K_PU		(PM7325_SID << 8 | ADC7_GPIO3_100K_PU)
+#define PM7325_ADC7_GPIO4_100K_PU		(PM7325_SID << 8 | ADC7_GPIO4_100K_PU)
+
+/* 400k pull-up3 */
+#define PM7325_ADC7_AMUX_THM1_400K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM1_400K_PU)
+#define PM7325_ADC7_AMUX_THM2_400K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM2_400K_PU)
+#define PM7325_ADC7_AMUX_THM3_400K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM3_400K_PU)
+#define PM7325_ADC7_AMUX_THM4_400K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM4_400K_PU)
+#define PM7325_ADC7_AMUX_THM5_400K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM5_400K_PU)
+#define PM7325_ADC7_GPIO1_400K_PU		(PM7325_SID << 8 | ADC7_GPIO1_400K_PU)
+#define PM7325_ADC7_GPIO2_400K_PU		(PM7325_SID << 8 | ADC7_GPIO2_400K_PU)
+#define PM7325_ADC7_GPIO3_400K_PU		(PM7325_SID << 8 | ADC7_GPIO3_400K_PU)
+#define PM7325_ADC7_GPIO4_400K_PU		(PM7325_SID << 8 | ADC7_GPIO4_400K_PU)
+
+/* 1/3 Divider */
+#define PM7325_ADC7_GPIO4_DIV3			(PM7325_SID << 8 | ADC7_GPIO4_DIV3)
+
+#define PM7325_ADC7_VPH_PWR			(PM7325_SID << 8 | ADC7_VPH_PWR)
+
+#endif /* _DT_BINDINGS_QCOM_SPMI_VADC_PM7325_H */
diff --git a/include/dt-bindings/iio/qcom,spmi-adc7-smb139x.h b/include/dt-bindings/iio/qcom,spmi-adc7-smb139x.h
new file mode 100644
index 000000000000..c0680d1285cf
--- /dev/null
+++ b/include/dt-bindings/iio/qcom,spmi-adc7-smb139x.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-only OR BSD-3-Clause */
+/*
+ * Copyright (c) 2020 The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_QCOM_SPMI_VADC_SMB139X_H
+#define _DT_BINDINGS_QCOM_SPMI_VADC_SMB139X_H
+
+#include <dt-bindings/iio/qcom,spmi-vadc.h>
+
+#define SMB139x_1_ADC7_SMB_TEMP			(SMB139x_1_SID << 8 | ADC7_SMB_TEMP)
+#define SMB139x_1_ADC7_ICHG_SMB			(SMB139x_1_SID << 8 | ADC7_ICHG_SMB)
+#define SMB139x_1_ADC7_IIN_SMB			(SMB139x_1_SID << 8 | ADC7_IIN_SMB)
+
+#define SMB139x_2_ADC7_SMB_TEMP			(SMB139x_2_SID << 8 | ADC7_SMB_TEMP)
+#define SMB139x_2_ADC7_ICHG_SMB			(SMB139x_2_SID << 8 | ADC7_ICHG_SMB)
+#define SMB139x_2_ADC7_IIN_SMB			(SMB139x_2_SID << 8 | ADC7_IIN_SMB)
+
+#endif
diff --git a/include/dt-bindings/iio/qcom,spmi-vadc.h b/include/dt-bindings/iio/qcom,spmi-vadc.h
index 08adfe25964c..ef07ecd4d585 100644
--- a/include/dt-bindings/iio/qcom,spmi-vadc.h
+++ b/include/dt-bindings/iio/qcom,spmi-vadc.h
@@ -239,12 +239,15 @@
 #define ADC7_GPIO3				0x0c
 #define ADC7_GPIO4				0x0d
 
+#define ADC7_SMB_TEMP				0x06
 #define ADC7_CHG_TEMP				0x10
 #define ADC7_USB_IN_V_16			0x11
 #define ADC7_VDC_16				0x12
 #define ADC7_CC1_ID				0x13
 #define ADC7_VREF_BAT_THERM			0x15
 #define ADC7_IIN_FB				0x17
+#define ADC7_ICHG_SMB				0x18
+#define ADC7_IIN_SMB				0x19
 
 /* 30k pull-up1 */
 #define ADC7_AMUX_THM1_30K_PU			0x24
diff --git a/include/dt-bindings/interconnect/qcom,sm6115.h b/include/dt-bindings/interconnect/qcom,sm6115.h
new file mode 100644
index 000000000000..21090e585f05
--- /dev/null
+++ b/include/dt-bindings/interconnect/qcom,sm6115.h
@@ -0,0 +1,111 @@
+/* SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause */
+/*
+ * Copyright (c) 2020, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef __DT_BINDINGS_INTERCONNECT_QCOM_SM6115_H
+#define __DT_BINDINGS_INTERCONNECT_QCOM_SM6115_H
+
+/* BIMC */
+#define MASTER_AMPSS_M0				0
+#define MASTER_SNOC_BIMC_RT			1
+#define MASTER_SNOC_BIMC_NRT			2
+#define SNOC_BIMC_MAS				3
+#define MASTER_GRAPHICS_3D			4
+#define MASTER_TCU_0				5
+#define SLAVE_EBI_CH0				6
+#define BIMC_SNOC_SLV				7
+
+/* CNOC */
+#define SNOC_CNOC_MAS				0
+#define MASTER_QDSS_DAP				1
+#define SLAVE_AHB2PHY_USB			2
+#define SLAVE_APSS_THROTTLE_CFG			3
+#define SLAVE_BIMC_CFG				4
+#define SLAVE_BOOT_ROM				5
+#define SLAVE_CAMERA_NRT_THROTTLE_CFG		6
+#define SLAVE_CAMERA_RT_THROTTLE_CFG		7
+#define SLAVE_CAMERA_CFG			8
+#define SLAVE_CLK_CTL				9
+#define SLAVE_RBCPR_CX_CFG			10
+#define SLAVE_RBCPR_MX_CFG			11
+#define SLAVE_CRYPTO_0_CFG			12
+#define SLAVE_DCC_CFG				13
+#define SLAVE_DDR_PHY_CFG			14
+#define SLAVE_DDR_SS_CFG			15
+#define SLAVE_DISPLAY_CFG			16
+#define SLAVE_DISPLAY_THROTTLE_CFG		17
+#define SLAVE_GPU_CFG				18
+#define SLAVE_GPU_THROTTLE_CFG			19
+#define SLAVE_HWKM_CORE				20
+#define SLAVE_IMEM_CFG				21
+#define SLAVE_IPA_CFG				22
+#define SLAVE_LPASS				23
+#define SLAVE_MAPSS				24
+#define SLAVE_MDSP_MPU_CFG			25
+#define SLAVE_MESSAGE_RAM			26
+#define SLAVE_CNOC_MSS				27
+#define SLAVE_PDM				28
+#define SLAVE_PIMEM_CFG				29
+#define SLAVE_PKA_CORE				30
+#define SLAVE_PMIC_ARB				31
+#define SLAVE_QDSS_CFG				32
+#define SLAVE_QM_CFG				33
+#define SLAVE_QM_MPU_CFG			34
+#define SLAVE_QPIC				35
+#define SLAVE_QUP_0				36
+#define SLAVE_RPM				37
+#define SLAVE_SDCC_1				38
+#define SLAVE_SDCC_2				39
+#define SLAVE_SECURITY				40
+#define SLAVE_SNOC_CFG				41
+#define SLAVE_TCSR				42
+#define SLAVE_TLMM				43
+#define SLAVE_USB3				44
+#define SLAVE_VENUS_CFG				45
+#define SLAVE_VENUS_THROTTLE_CFG		46
+#define SLAVE_VSENSE_CTRL_CFG			47
+#define SLAVE_SERVICE_CNOC			48
+
+/* SNOC */
+#define MASTER_CRYPTO_CORE0			0
+#define MASTER_SNOC_CFG				1
+#define MASTER_TIC				2
+#define MASTER_ANOC_SNOC			3
+#define BIMC_SNOC_MAS				4
+#define MASTER_PIMEM				5
+#define MASTER_QDSS_BAM				6
+#define MASTER_QPIC				7
+#define MASTER_QUP_0				8
+#define MASTER_IPA				9
+#define MASTER_QDSS_ETR				10
+#define MASTER_SDCC_1				11
+#define MASTER_SDCC_2				12
+#define MASTER_USB3				13
+#define SLAVE_APPSS				14
+#define SNOC_CNOC_SLV				15
+#define SLAVE_OCIMEM				16
+#define SLAVE_PIMEM				17
+#define SNOC_BIMC_SLV				18
+#define SLAVE_SERVICE_SNOC			19
+#define SLAVE_QDSS_STM				20
+#define SLAVE_TCU				21
+#define SLAVE_ANOC_SNOC				22
+
+/* CLK Virtual */
+#define MASTER_QUP_CORE_0			0
+#define SLAVE_QUP_CORE_0			1
+
+/* MMRT Virtual */
+#define MASTER_CAMNOC_HF			0
+#define MASTER_MDP_PORT0			1
+#define SLAVE_SNOC_BIMC_RT			2
+
+/* MMNRT Virtual */
+#define MASTER_CAMNOC_SF			0
+#define MASTER_VIDEO_P0				1
+#define MASTER_VIDEO_PROC			2
+#define SLAVE_SNOC_BIMC_NRT			3
+
+#endif
diff --git a/include/dt-bindings/interconnect/qcom,sm8650-rpmh.h b/include/dt-bindings/interconnect/qcom,sm8650-rpmh.h
new file mode 100644
index 000000000000..6c1eaf04e241
--- /dev/null
+++ b/include/dt-bindings/interconnect/qcom,sm8650-rpmh.h
@@ -0,0 +1,154 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2021, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef __DT_BINDINGS_INTERCONNECT_QCOM_SM8650_H
+#define __DT_BINDINGS_INTERCONNECT_QCOM_SM8650_H
+
+#define MASTER_QSPI_0				0
+#define MASTER_QUP_1				1
+#define MASTER_QUP_3				2
+#define MASTER_SDCC_4				3
+#define MASTER_UFS_MEM				4
+#define MASTER_USB3_0				5
+#define SLAVE_A1NOC_SNOC			6
+
+#define MASTER_QDSS_BAM				0
+#define MASTER_QUP_2				1
+#define MASTER_CRYPTO				2
+#define MASTER_IPA				3
+#define MASTER_SP				4
+#define MASTER_QDSS_ETR				5
+#define MASTER_QDSS_ETR_1			6
+#define MASTER_SDCC_2				7
+#define SLAVE_A2NOC_SNOC			8
+
+#define MASTER_QUP_CORE_0			0
+#define MASTER_QUP_CORE_1			1
+#define MASTER_QUP_CORE_2			2
+#define SLAVE_QUP_CORE_0			3
+#define SLAVE_QUP_CORE_1			4
+#define SLAVE_QUP_CORE_2			5
+
+#define MASTER_CNOC_CFG				0
+#define SLAVE_AHB2PHY_SOUTH			1
+#define SLAVE_AHB2PHY_NORTH			2
+#define SLAVE_CAMERA_CFG			3
+#define SLAVE_CLK_CTL				4
+#define SLAVE_RBCPR_CX_CFG			5
+#define SLAVE_CPR_HMX				6
+#define SLAVE_RBCPR_MMCX_CFG			7
+#define SLAVE_RBCPR_MXA_CFG			8
+#define SLAVE_RBCPR_MXC_CFG			9
+#define SLAVE_CPR_NSPCX				10
+#define SLAVE_CRYPTO_0_CFG			11
+#define SLAVE_CX_RDPM				12
+#define SLAVE_DISPLAY_CFG			13
+#define SLAVE_GFX3D_CFG				14
+#define SLAVE_I2C				15
+#define SLAVE_I3C_IBI0_CFG			16
+#define SLAVE_I3C_IBI1_CFG			17
+#define SLAVE_IMEM_CFG				18
+#define SLAVE_CNOC_MSS				19
+#define SLAVE_MX_2_RDPM				20
+#define SLAVE_MX_RDPM				21
+#define SLAVE_PCIE_0_CFG			22
+#define SLAVE_PCIE_1_CFG			23
+#define SLAVE_PCIE_RSCC				24
+#define SLAVE_PDM				25
+#define SLAVE_PRNG				26
+#define SLAVE_QDSS_CFG				27
+#define SLAVE_QSPI_0				28
+#define SLAVE_QUP_3				29
+#define SLAVE_QUP_1				30
+#define SLAVE_QUP_2				31
+#define SLAVE_SDCC_2				32
+#define SLAVE_SDCC_4				33
+#define SLAVE_SPSS_CFG				34
+#define SLAVE_TCSR				35
+#define SLAVE_TLMM				36
+#define SLAVE_UFS_MEM_CFG			37
+#define SLAVE_USB3_0				38
+#define SLAVE_VENUS_CFG				39
+#define SLAVE_VSENSE_CTRL_CFG			40
+#define SLAVE_CNOC_MNOC_CFG			41
+#define SLAVE_NSP_QTB_CFG			42
+#define SLAVE_PCIE_ANOC_CFG			43
+#define SLAVE_SERVICE_CNOC_CFG			44
+#define SLAVE_QDSS_STM				45
+#define SLAVE_TCU				46
+
+#define MASTER_GEM_NOC_CNOC			0
+#define MASTER_GEM_NOC_PCIE_SNOC		1
+#define SLAVE_AOSS				2
+#define SLAVE_IPA_CFG				3
+#define SLAVE_IPC_ROUTER_CFG			4
+#define SLAVE_TME_CFG				5
+#define SLAVE_APPSS				6
+#define SLAVE_CNOC_CFG				7
+#define SLAVE_DDRSS_CFG				8
+#define SLAVE_IMEM				9
+#define SLAVE_SERVICE_CNOC			10
+#define SLAVE_PCIE_0				11
+#define SLAVE_PCIE_1				12
+
+#define MASTER_GPU_TCU				0
+#define MASTER_SYS_TCU				1
+#define MASTER_UBWC_P_TCU			2
+#define MASTER_APPSS_PROC			3
+#define MASTER_GFX3D				4
+#define MASTER_LPASS_GEM_NOC			5
+#define MASTER_MSS_PROC				6
+#define MASTER_MNOC_HF_MEM_NOC			7
+#define MASTER_MNOC_SF_MEM_NOC			8
+#define MASTER_COMPUTE_NOC			9
+#define MASTER_ANOC_PCIE_GEM_NOC		10
+#define MASTER_SNOC_SF_MEM_NOC			11
+#define MASTER_UBWC_P				12
+#define MASTER_GIC				13
+#define SLAVE_GEM_NOC_CNOC			14
+#define SLAVE_LLCC				15
+#define SLAVE_MEM_NOC_PCIE_SNOC			16
+
+#define MASTER_LPIAON_NOC			0
+#define SLAVE_LPASS_GEM_NOC			1
+
+#define MASTER_LPASS_LPINOC			0
+#define SLAVE_LPIAON_NOC_LPASS_AG_NOC		1
+
+#define MASTER_LPASS_PROC			0
+#define SLAVE_LPICX_NOC_LPIAON_NOC		1
+
+#define MASTER_LLCC				0
+#define SLAVE_EBI1				1
+
+#define MASTER_CAMNOC_HF			0
+#define MASTER_CAMNOC_ICP			1
+#define MASTER_CAMNOC_SF			2
+#define MASTER_MDP				3
+#define MASTER_CDSP_HCP				4
+#define MASTER_VIDEO				5
+#define MASTER_VIDEO_CV_PROC			6
+#define MASTER_VIDEO_PROC			7
+#define MASTER_VIDEO_V_PROC			8
+#define MASTER_CNOC_MNOC_CFG			9
+#define SLAVE_MNOC_HF_MEM_NOC			10
+#define SLAVE_MNOC_SF_MEM_NOC			11
+#define SLAVE_SERVICE_MNOC			12
+
+#define MASTER_CDSP_PROC			0
+#define SLAVE_CDSP_MEM_NOC			1
+
+#define MASTER_PCIE_ANOC_CFG			0
+#define MASTER_PCIE_0				1
+#define MASTER_PCIE_1				2
+#define SLAVE_ANOC_PCIE_GEM_NOC			3
+#define SLAVE_SERVICE_PCIE_ANOC			4
+
+#define MASTER_A1NOC_SNOC			0
+#define MASTER_A2NOC_SNOC			1
+#define SLAVE_SNOC_GEM_NOC_SF			2
+
+#endif
diff --git a/include/dt-bindings/interconnect/qcom,x1e80100-rpmh.h b/include/dt-bindings/interconnect/qcom,x1e80100-rpmh.h
new file mode 100644
index 000000000000..a38c3472698a
--- /dev/null
+++ b/include/dt-bindings/interconnect/qcom,x1e80100-rpmh.h
@@ -0,0 +1,207 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef __DT_BINDINGS_INTERCONNECT_QCOM_X1E80100_H
+#define __DT_BINDINGS_INTERCONNECT_QCOM_X1E80100_H
+
+#define MASTER_QSPI_0				0
+#define MASTER_QUP_1				1
+#define MASTER_SDCC_4				2
+#define MASTER_UFS_MEM				3
+#define SLAVE_A1NOC_SNOC			4
+
+#define MASTER_QUP_0				0
+#define MASTER_QUP_2				1
+#define MASTER_CRYPTO				2
+#define MASTER_SP				3
+#define MASTER_QDSS_ETR				4
+#define MASTER_QDSS_ETR_1			5
+#define MASTER_SDCC_2				6
+#define SLAVE_A2NOC_SNOC			7
+
+#define MASTER_DDR_PERF_MODE			0
+#define MASTER_QUP_CORE_0			1
+#define MASTER_QUP_CORE_1			2
+#define MASTER_QUP_CORE_2			3
+#define SLAVE_DDR_PERF_MODE			4
+#define SLAVE_QUP_CORE_0			5
+#define SLAVE_QUP_CORE_1			6
+#define SLAVE_QUP_CORE_2			7
+
+#define MASTER_CNOC_CFG				0
+#define SLAVE_AHB2PHY_SOUTH			1
+#define SLAVE_AHB2PHY_NORTH			2
+#define SLAVE_AHB2PHY_2				3
+#define SLAVE_AV1_ENC_CFG			4
+#define SLAVE_CAMERA_CFG			5
+#define SLAVE_CLK_CTL				6
+#define SLAVE_CRYPTO_0_CFG			7
+#define SLAVE_DISPLAY_CFG			8
+#define SLAVE_GFX3D_CFG				9
+#define SLAVE_IMEM_CFG				10
+#define SLAVE_IPC_ROUTER_CFG			11
+#define SLAVE_PCIE_0_CFG			12
+#define SLAVE_PCIE_1_CFG			13
+#define SLAVE_PCIE_2_CFG			14
+#define SLAVE_PCIE_3_CFG			15
+#define SLAVE_PCIE_4_CFG			16
+#define SLAVE_PCIE_5_CFG			17
+#define SLAVE_PCIE_6A_CFG			18
+#define SLAVE_PCIE_6B_CFG			19
+#define SLAVE_PCIE_RSC_CFG			20
+#define SLAVE_PDM				21
+#define SLAVE_PRNG				22
+#define SLAVE_QDSS_CFG				23
+#define SLAVE_QSPI_0				24
+#define SLAVE_QUP_0				25
+#define SLAVE_QUP_1				26
+#define SLAVE_QUP_2				27
+#define SLAVE_SDCC_2				28
+#define SLAVE_SDCC_4				29
+#define SLAVE_SMMUV3_CFG			30
+#define SLAVE_TCSR				31
+#define SLAVE_TLMM				32
+#define SLAVE_UFS_MEM_CFG			33
+#define SLAVE_USB2				34
+#define SLAVE_USB3_0				35
+#define SLAVE_USB3_1				36
+#define SLAVE_USB3_2				37
+#define SLAVE_USB3_MP				38
+#define SLAVE_USB4_0				39
+#define SLAVE_USB4_1				40
+#define SLAVE_USB4_2				41
+#define SLAVE_VENUS_CFG				42
+#define SLAVE_LPASS_QTB_CFG			43
+#define SLAVE_CNOC_MNOC_CFG			44
+#define SLAVE_NSP_QTB_CFG			45
+#define SLAVE_QDSS_STM				46
+#define SLAVE_TCU				47
+
+#define MASTER_GEM_NOC_CNOC			0
+#define MASTER_GEM_NOC_PCIE_SNOC		1
+#define SLAVE_AOSS				2
+#define SLAVE_TME_CFG				3
+#define SLAVE_APPSS				4
+#define SLAVE_CNOC_CFG				5
+#define SLAVE_BOOT_IMEM				6
+#define SLAVE_IMEM				7
+#define SLAVE_PCIE_0				8
+#define SLAVE_PCIE_1				9
+#define SLAVE_PCIE_2				10
+#define SLAVE_PCIE_3				11
+#define SLAVE_PCIE_4				12
+#define SLAVE_PCIE_5				13
+#define SLAVE_PCIE_6A				14
+#define SLAVE_PCIE_6B				15
+
+#define MASTER_GPU_TCU				0
+#define MASTER_PCIE_TCU				1
+#define MASTER_SYS_TCU				2
+#define MASTER_APPSS_PROC			3
+#define MASTER_GFX3D				4
+#define MASTER_LPASS_GEM_NOC			5
+#define MASTER_MNOC_HF_MEM_NOC			6
+#define MASTER_MNOC_SF_MEM_NOC			7
+#define MASTER_COMPUTE_NOC			8
+#define MASTER_ANOC_PCIE_GEM_NOC		9
+#define MASTER_SNOC_SF_MEM_NOC			10
+#define MASTER_GIC2				11
+#define SLAVE_GEM_NOC_CNOC			12
+#define SLAVE_LLCC				13
+#define SLAVE_MEM_NOC_PCIE_SNOC			14
+#define MASTER_MNOC_HF_MEM_NOC_DISP		15
+#define MASTER_ANOC_PCIE_GEM_NOC_DISP		16
+#define SLAVE_LLCC_DISP				17
+#define MASTER_ANOC_PCIE_GEM_NOC_PCIE		18
+#define SLAVE_LLCC_PCIE				19
+
+#define MASTER_LPIAON_NOC			0
+#define SLAVE_LPASS_GEM_NOC			1
+
+#define MASTER_LPASS_LPINOC			0
+#define SLAVE_LPIAON_NOC_LPASS_AG_NOC		1
+
+#define MASTER_LPASS_PROC			0
+#define SLAVE_LPICX_NOC_LPIAON_NOC		1
+
+#define MASTER_LLCC				0
+#define SLAVE_EBI1				1
+#define MASTER_LLCC_DISP			2
+#define SLAVE_EBI1_DISP				3
+#define MASTER_LLCC_PCIE			4
+#define SLAVE_EBI1_PCIE				5
+
+#define MASTER_AV1_ENC				0
+#define MASTER_CAMNOC_HF			1
+#define MASTER_CAMNOC_ICP			2
+#define MASTER_CAMNOC_SF			3
+#define MASTER_EVA				4
+#define MASTER_MDP				5
+#define MASTER_VIDEO				6
+#define MASTER_VIDEO_CV_PROC			7
+#define MASTER_VIDEO_V_PROC			8
+#define MASTER_CNOC_MNOC_CFG			9
+#define SLAVE_MNOC_HF_MEM_NOC			10
+#define SLAVE_MNOC_SF_MEM_NOC			11
+#define SLAVE_SERVICE_MNOC			12
+#define MASTER_MDP_DISP				13
+#define SLAVE_MNOC_HF_MEM_NOC_DISP		14
+
+#define MASTER_CDSP_PROC			0
+#define SLAVE_CDSP_MEM_NOC			1
+
+#define MASTER_PCIE_NORTH			0
+#define MASTER_PCIE_SOUTH			1
+#define SLAVE_ANOC_PCIE_GEM_NOC			2
+#define MASTER_PCIE_NORTH_PCIE			3
+#define MASTER_PCIE_SOUTH_PCIE			4
+#define SLAVE_ANOC_PCIE_GEM_NOC_PCIE		5
+
+#define MASTER_PCIE_3				0
+#define MASTER_PCIE_4				1
+#define MASTER_PCIE_5				2
+#define SLAVE_PCIE_NORTH			3
+#define MASTER_PCIE_3_PCIE			4
+#define MASTER_PCIE_4_PCIE			5
+#define MASTER_PCIE_5_PCIE			6
+#define SLAVE_PCIE_NORTH_PCIE			7
+
+#define MASTER_PCIE_0				0
+#define MASTER_PCIE_1				1
+#define MASTER_PCIE_2				2
+#define MASTER_PCIE_6A				3
+#define MASTER_PCIE_6B				4
+#define SLAVE_PCIE_SOUTH			5
+#define MASTER_PCIE_0_PCIE			6
+#define MASTER_PCIE_1_PCIE			7
+#define MASTER_PCIE_2_PCIE			8
+#define MASTER_PCIE_6A_PCIE			9
+#define MASTER_PCIE_6B_PCIE			10
+#define SLAVE_PCIE_SOUTH_PCIE			11
+
+#define MASTER_A1NOC_SNOC			0
+#define MASTER_A2NOC_SNOC			1
+#define MASTER_GIC1				2
+#define MASTER_USB_NOC_SNOC			3
+#define SLAVE_SNOC_GEM_NOC_SF			4
+
+#define MASTER_AGGRE_USB_NORTH			0
+#define MASTER_AGGRE_USB_SOUTH			1
+#define SLAVE_USB_NOC_SNOC			2
+
+#define MASTER_USB2				0
+#define MASTER_USB3_MP				1
+#define SLAVE_AGGRE_USB_NORTH			2
+
+#define MASTER_USB3_0				0
+#define MASTER_USB3_1				1
+#define MASTER_USB3_2				2
+#define MASTER_USB4_0				3
+#define MASTER_USB4_1				4
+#define MASTER_USB4_2				5
+#define SLAVE_AGGRE_USB_SOUTH			6
+
+#endif
diff --git a/include/dt-bindings/reset/amlogic,c3-reset.h b/include/dt-bindings/reset/amlogic,c3-reset.h
new file mode 100644
index 000000000000..d9127863f603
--- /dev/null
+++ b/include/dt-bindings/reset/amlogic,c3-reset.h
@@ -0,0 +1,119 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR MIT) */
+/*
+ * Copyright (c) 2023 Amlogic, Inc. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_AMLOGIC_C3_RESET_H
+#define _DT_BINDINGS_AMLOGIC_C3_RESET_H
+
+/* RESET0 */
+/*						0-3 */
+#define RESET_USBCTRL				4
+/*						5-7 */
+#define RESET_USBPHY20				8
+/*						9 */
+#define RESET_USB2DRD				10
+#define RESET_MIPI_DSI_HOST			11
+#define RESET_MIPI_DSI_PHY			12
+/*						13-20 */
+#define RESET_GE2D				21
+#define RESET_DWAP				22
+/*						23-31 */
+
+/* RESET1 */
+#define RESET_AUDIO				32
+/*						33-34 */
+#define RESET_DDRAPB				35
+#define RESET_DDR				36
+#define RESET_DOS_CAPB3				37
+#define RESET_DOS				38
+/*						39-46 */
+#define RESET_NNA				47
+#define RESET_ETHERNET				48
+#define RESET_ISP				49
+#define RESET_VC9000E_APB			50
+#define RESET_VC9000E_A				51
+/*						52 */
+#define RESET_VC9000E_CORE			53
+/*						54-63 */
+
+/* RESET2 */
+#define RESET_ABUS_ARB				64
+#define RESET_IRCTRL				65
+/*						66 */
+#define RESET_TEMP_PII				67
+/*						68-72 */
+#define RESET_SPICC_0				73
+#define RESET_SPICC_1				74
+#define RESET_RSA				75
+
+/*						76-79 */
+#define RESET_MSR_CLK				80
+#define RESET_SPIFC				81
+#define RESET_SAR_ADC				82
+/*						83-87 */
+#define RESET_ACODEC				88
+/*						89-90 */
+#define RESET_WATCHDOG				91
+/*						92-95 */
+
+/* RESET3 */
+#define RESET_ISP_NIC_GPV			96
+#define RESET_ISP_NIC_MAIN			97
+#define RESET_ISP_NIC_VCLK			98
+#define RESET_ISP_NIC_VOUT			99
+#define RESET_ISP_NIC_ALL			100
+#define RESET_VOUT				101
+#define RESET_VOUT_VENC				102
+/*						103 */
+#define RESET_CVE_NIC_GPV			104
+#define RESET_CVE_NIC_MAIN			105
+#define RESET_CVE_NIC_GE2D			106
+#define RESET_CVE_NIC_DW			106
+#define RESET_CVE_NIC_CVE			108
+#define RESET_CVE_NIC_ALL			109
+#define RESET_CVE				110
+/*						112-127 */
+
+/* RESET4 */
+#define RESET_RTC				128
+#define RESET_PWM_AB				129
+#define RESET_PWM_CD				130
+#define RESET_PWM_EF				131
+#define RESET_PWM_GH				132
+#define RESET_PWM_IJ				133
+#define RESET_PWM_KL				134
+#define RESET_PWM_MN				135
+/*						136-137 */
+#define RESET_UART_A				138
+#define RESET_UART_B				139
+#define RESET_UART_C				140
+#define RESET_UART_D				141
+#define RESET_UART_E				142
+#define RESET_UART_F				143
+#define RESET_I2C_S_A				144
+#define RESET_I2C_M_A				145
+#define RESET_I2C_M_B				146
+#define RESET_I2C_M_C				147
+#define RESET_I2C_M_D				148
+/*						149-151 */
+#define RESET_SD_EMMC_A				152
+#define RESET_SD_EMMC_B				153
+#define RESET_SD_EMMC_C				154
+
+/* RESET5 */
+/*						160-172 */
+#define RESET_BRG_NIC_NNA			173
+#define RESET_BRG_MUX_NIC_MAIN			174
+#define RESET_BRG_AO_NIC_ALL			175
+/*						176-183 */
+#define RESET_BRG_NIC_VAPB			184
+#define RESET_BRG_NIC_SDIO_B			185
+#define RESET_BRG_NIC_SDIO_A			186
+#define RESET_BRG_NIC_EMMC			187
+#define RESET_BRG_NIC_DSU			188
+#define RESET_BRG_NIC_SYSCLK			189
+#define RESET_BRG_NIC_MAIN			190
+#define RESET_BRG_NIC_ALL			191
+
+#endif
diff --git a/include/dt-bindings/reset/mt8188-resets.h b/include/dt-bindings/reset/mt8188-resets.h
index ba9a5e9b8899..5a58c54e7d20 100644
--- a/include/dt-bindings/reset/mt8188-resets.h
+++ b/include/dt-bindings/reset/mt8188-resets.h
@@ -38,4 +38,79 @@
 #define MT8188_INFRA_RST1_THERMAL_CTRL_RST         1
 #define MT8188_INFRA_RST3_PTP_CTRL_RST             2
 
+#define MT8188_VDO0_RST_DISP_OVL0		0
+#define MT8188_VDO0_RST_FAKE_ENG0		1
+#define MT8188_VDO0_RST_DISP_CCORR0		2
+#define MT8188_VDO0_RST_DISP_MUTEX0		3
+#define MT8188_VDO0_RST_DISP_GAMMA0		4
+#define MT8188_VDO0_RST_DISP_DITHER0		5
+#define MT8188_VDO0_RST_DISP_WDMA0		6
+#define MT8188_VDO0_RST_DISP_RDMA0		7
+#define MT8188_VDO0_RST_DSI0			8
+#define MT8188_VDO0_RST_DSI1			9
+#define MT8188_VDO0_RST_DSC_WRAP0		10
+#define MT8188_VDO0_RST_VPP_MERGE0		11
+#define MT8188_VDO0_RST_DP_INTF0		12
+#define MT8188_VDO0_RST_DISP_AAL0		13
+#define MT8188_VDO0_RST_INLINEROT0		14
+#define MT8188_VDO0_RST_APB_BUS			15
+#define MT8188_VDO0_RST_DISP_COLOR0		16
+#define MT8188_VDO0_RST_MDP_WROT0		17
+#define MT8188_VDO0_RST_DISP_RSZ0		18
+
+#define MT8188_VDO1_RST_SMI_LARB2		0
+#define MT8188_VDO1_RST_SMI_LARB3		1
+#define MT8188_VDO1_RST_GALS			2
+#define MT8188_VDO1_RST_FAKE_ENG0		3
+#define MT8188_VDO1_RST_FAKE_ENG1		4
+#define MT8188_VDO1_RST_MDP_RDMA0		5
+#define MT8188_VDO1_RST_MDP_RDMA1		6
+#define MT8188_VDO1_RST_MDP_RDMA2		7
+#define MT8188_VDO1_RST_MDP_RDMA3		8
+#define MT8188_VDO1_RST_VPP_MERGE0		9
+#define MT8188_VDO1_RST_VPP_MERGE1		10
+#define MT8188_VDO1_RST_VPP_MERGE2		11
+#define MT8188_VDO1_RST_VPP_MERGE3		12
+#define MT8188_VDO1_RST_VPP_MERGE4		13
+#define MT8188_VDO1_RST_VPP2_TO_VDO1_DL_ASYNC	14
+#define MT8188_VDO1_RST_VPP3_TO_VDO1_DL_ASYNC	15
+#define MT8188_VDO1_RST_DISP_MUTEX		16
+#define MT8188_VDO1_RST_MDP_RDMA4		17
+#define MT8188_VDO1_RST_MDP_RDMA5		18
+#define MT8188_VDO1_RST_MDP_RDMA6		19
+#define MT8188_VDO1_RST_MDP_RDMA7		20
+#define MT8188_VDO1_RST_DP_INTF1_MMCK		21
+#define MT8188_VDO1_RST_DPI0_MM_CK		22
+#define MT8188_VDO1_RST_DPI1_MM_CK		23
+#define MT8188_VDO1_RST_MERGE0_DL_ASYNC		24
+#define MT8188_VDO1_RST_MERGE1_DL_ASYNC		25
+#define MT8188_VDO1_RST_MERGE2_DL_ASYNC		26
+#define MT8188_VDO1_RST_MERGE3_DL_ASYNC		27
+#define MT8188_VDO1_RST_MERGE4_DL_ASYNC		28
+#define MT8188_VDO1_RST_VDO0_DSC_TO_VDO1_DL_ASYNC	29
+#define MT8188_VDO1_RST_VDO0_MERGE_TO_VDO1_DL_ASYNC	30
+#define MT8188_VDO1_RST_PADDING0		31
+#define MT8188_VDO1_RST_PADDING1		32
+#define MT8188_VDO1_RST_PADDING2		33
+#define MT8188_VDO1_RST_PADDING3		34
+#define MT8188_VDO1_RST_PADDING4		35
+#define MT8188_VDO1_RST_PADDING5		36
+#define MT8188_VDO1_RST_PADDING6		37
+#define MT8188_VDO1_RST_PADDING7		38
+#define MT8188_VDO1_RST_DISP_RSZ0		39
+#define MT8188_VDO1_RST_DISP_RSZ1		40
+#define MT8188_VDO1_RST_DISP_RSZ2		41
+#define MT8188_VDO1_RST_DISP_RSZ3		42
+#define MT8188_VDO1_RST_HDR_VDO_FE0		43
+#define MT8188_VDO1_RST_HDR_GFX_FE0		44
+#define MT8188_VDO1_RST_HDR_VDO_BE		45
+#define MT8188_VDO1_RST_HDR_VDO_FE1		46
+#define MT8188_VDO1_RST_HDR_GFX_FE1		47
+#define MT8188_VDO1_RST_DISP_MIXER		48
+#define MT8188_VDO1_RST_HDR_VDO_FE0_DL_ASYNC	49
+#define MT8188_VDO1_RST_HDR_VDO_FE1_DL_ASYNC	50
+#define MT8188_VDO1_RST_HDR_GFX_FE0_DL_ASYNC	51
+#define MT8188_VDO1_RST_HDR_GFX_FE1_DL_ASYNC	52
+#define MT8188_VDO1_RST_HDR_VDO_BE_DL_ASYNC	53
+
 #endif  /* _DT_BINDINGS_RESET_CONTROLLER_MT8188 */
diff --git a/include/dt-bindings/reset/qcom,sm8650-gpucc.h b/include/dt-bindings/reset/qcom,sm8650-gpucc.h
new file mode 100644
index 000000000000..f021a6cccc66
--- /dev/null
+++ b/include/dt-bindings/reset/qcom,sm8650-gpucc.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2019, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef _DT_BINDINGS_RESET_QCOM_GPU_CC_SM8650_H
+#define _DT_BINDINGS_RESET_QCOM_GPU_CC_SM8650_H
+
+#define GPUCC_GPU_CC_ACD_BCR			0
+#define GPUCC_GPU_CC_CX_BCR			1
+#define GPUCC_GPU_CC_FAST_HUB_BCR		2
+#define GPUCC_GPU_CC_FF_BCR			3
+#define GPUCC_GPU_CC_GFX3D_AON_BCR		4
+#define GPUCC_GPU_CC_GMU_BCR			5
+#define GPUCC_GPU_CC_GX_BCR			6
+#define GPUCC_GPU_CC_XO_BCR			7
+#define GPUCC_GPU_CC_GX_ACD_IROOT_BCR		8
+
+#endif
diff --git a/include/kunit/device.h b/include/kunit/device.h
new file mode 100644
index 000000000000..2450110ad64e
--- /dev/null
+++ b/include/kunit/device.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * KUnit basic device implementation
+ *
+ * Helpers for creating and managing fake devices for KUnit tests.
+ *
+ * Copyright (C) 2023, Google LLC.
+ * Author: David Gow <davidgow@google.com>
+ */
+
+#ifndef _KUNIT_DEVICE_H
+#define _KUNIT_DEVICE_H
+
+#if IS_ENABLED(CONFIG_KUNIT)
+
+#include <kunit/test.h>
+
+struct device;
+struct device_driver;
+
+/**
+ * kunit_driver_create() - Create a struct device_driver attached to the kunit_bus
+ * @test: The test context object.
+ * @name: The name to give the created driver.
+ *
+ * Creates a struct device_driver attached to the kunit_bus, with the name @name.
+ * This driver will automatically be cleaned up on test exit.
+ *
+ * Return: a stub struct device_driver, managed by KUnit, with the name @name.
+ */
+struct device_driver *kunit_driver_create(struct kunit *test, const char *name);
+
+/**
+ * kunit_device_register() - Create a struct device for use in KUnit tests
+ * @test: The test context object.
+ * @name: The name to give the created device.
+ *
+ * Creates a struct kunit_device (which is a struct device) with the given name,
+ * and a corresponding driver. The device and driver will be cleaned up on test
+ * exit, or when kunit_device_unregister is called. See also
+ * kunit_device_register_with_driver, if you wish to provide your own
+ * struct device_driver.
+ *
+ * Return: a pointer to a struct device which will be cleaned up when the test
+ * exits, or an error pointer if the device could not be allocated or registered.
+ */
+struct device *kunit_device_register(struct kunit *test, const char *name);
+
+/**
+ * kunit_device_register_with_driver() - Create a struct device for use in KUnit tests
+ * @test: The test context object.
+ * @name: The name to give the created device.
+ * @drv: The struct device_driver to associate with the device.
+ *
+ * Creates a struct kunit_device (which is a struct device) with the given
+ * name, and driver. The device will be cleaned up on test exit, or when
+ * kunit_device_unregister is called. See also kunit_device_register, if you
+ * wish KUnit to create and manage a driver for you.
+ *
+ * Return: a pointer to a struct device which will be cleaned up when the test
+ * exits, or an error pointer if the device could not be allocated or registered.
+ */
+struct device *kunit_device_register_with_driver(struct kunit *test,
+						 const char *name,
+						 const struct device_driver *drv);
+
+/**
+ * kunit_device_unregister() - Unregister a KUnit-managed device
+ * @test: The test context object which created the device
+ * @dev: The device.
+ *
+ * Unregisters and destroys a struct device which was created with
+ * kunit_device_register or kunit_device_register_with_driver. If KUnit created
+ * a driver, cleans it up as well.
+ */
+void kunit_device_unregister(struct kunit *test, struct device *dev);
+
+#endif
+
+#endif
diff --git a/include/kunit/resource.h b/include/kunit/resource.h
index c7383e90f5c9..4ad69a2642a5 100644
--- a/include/kunit/resource.h
+++ b/include/kunit/resource.h
@@ -391,6 +391,27 @@ void kunit_remove_resource(struct kunit *test, struct kunit_resource *res);
 typedef void (kunit_action_t)(void *);
 
 /**
+ * KUNIT_DEFINE_ACTION_WRAPPER() - Wrap a function for use as a deferred action.
+ *
+ * @wrapper: The name of the new wrapper function define.
+ * @orig: The original function to wrap.
+ * @arg_type: The type of the argument accepted by @orig.
+ *
+ * Defines a wrapper for a function which accepts a single, pointer-sized
+ * argument. This wrapper can then be passed to kunit_add_action() and
+ * similar. This should be used in preference to casting a function
+ * directly to kunit_action_t, as casting function pointers will break
+ * control flow integrity (CFI), leading to crashes.
+ */
+#define KUNIT_DEFINE_ACTION_WRAPPER(wrapper, orig, arg_type)	\
+	static void wrapper(void *in)				\
+	{							\
+		arg_type arg = (arg_type)in;			\
+		orig(arg);					\
+	}
+
+
+/**
  * kunit_add_action() - Call a function when the test ends.
  * @test: Test case to associate the action with.
  * @action: The function to run on test exit
diff --git a/include/kunit/skbuff.h b/include/kunit/skbuff.h
new file mode 100644
index 000000000000..44d12370939a
--- /dev/null
+++ b/include/kunit/skbuff.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * KUnit resource management helpers for SKBs (skbuff).
+ *
+ * Copyright (C) 2023 Intel Corporation
+ */
+
+#ifndef _KUNIT_SKBUFF_H
+#define _KUNIT_SKBUFF_H
+
+#include <kunit/resource.h>
+#include <linux/skbuff.h>
+
+static void kunit_action_kfree_skb(void *p)
+{
+	kfree_skb((struct sk_buff *)p);
+}
+
+/**
+ * kunit_zalloc_skb() - Allocate and initialize a resource managed skb.
+ * @test: The test case to which the skb belongs
+ * @len: size to allocate
+ *
+ * Allocate a new struct sk_buff with GFP_KERNEL, zero fill the give length
+ * and add it as a resource to the kunit test for automatic cleanup.
+ *
+ * Returns: newly allocated SKB, or %NULL on error
+ */
+static inline struct sk_buff *kunit_zalloc_skb(struct kunit *test, int len,
+					       gfp_t gfp)
+{
+	struct sk_buff *res = alloc_skb(len, GFP_KERNEL);
+
+	if (!res || skb_pad(res, len))
+		return NULL;
+
+	if (kunit_add_action_or_reset(test, kunit_action_kfree_skb, res))
+		return NULL;
+
+	return res;
+}
+
+/**
+ * kunit_kfree_skb() - Like kfree_skb except for allocations managed by KUnit.
+ * @test: The test case to which the resource belongs.
+ * @skb: The SKB to free.
+ */
+static inline void kunit_kfree_skb(struct kunit *test, struct sk_buff *skb)
+{
+	if (!skb)
+		return;
+
+	kunit_release_action(test, kunit_action_kfree_skb, (void *)skb);
+}
+
+#endif /* _KUNIT_SKBUFF_H */
diff --git a/include/kunit/static_stub.h b/include/kunit/static_stub.h
index 85315c80b303..bf940322dfc0 100644
--- a/include/kunit/static_stub.h
+++ b/include/kunit/static_stub.h
@@ -93,7 +93,7 @@ void __kunit_activate_static_stub(struct kunit *test,
  * The redirection can be disabled again with kunit_deactivate_static_stub().
  */
 #define kunit_activate_static_stub(test, real_fn_addr, replacement_addr) do {	\
-	typecheck_fn(typeof(&real_fn_addr), replacement_addr);			\
+	typecheck_fn(typeof(&replacement_addr), real_fn_addr);			\
 	__kunit_activate_static_stub(test, real_fn_addr, replacement_addr);	\
 } while (0)
 
diff --git a/include/kunit/test.h b/include/kunit/test.h
index 20ed9f9275c9..fcb4a4940ace 100644
--- a/include/kunit/test.h
+++ b/include/kunit/test.h
@@ -253,6 +253,7 @@ struct kunit_suite {
 	struct dentry *debugfs;
 	struct string_stream *log;
 	int suite_init_err;
+	bool is_init;
 };
 
 /* Stores an array of suites, end points one past the end */
@@ -337,6 +338,9 @@ void __kunit_test_suites_exit(struct kunit_suite **suites, int num_suites);
 void kunit_exec_run_tests(struct kunit_suite_set *suite_set, bool builtin);
 void kunit_exec_list_tests(struct kunit_suite_set *suite_set, bool include_attr);
 
+struct kunit_suite_set kunit_merge_suite_sets(struct kunit_suite_set init_suite_set,
+		struct kunit_suite_set suite_set);
+
 #if IS_BUILTIN(CONFIG_KUNIT)
 int kunit_run_all_tests(void);
 #else
@@ -371,6 +375,11 @@ static inline int kunit_run_all_tests(void)
 
 #define kunit_test_suite(suite)	kunit_test_suites(&suite)
 
+#define __kunit_init_test_suites(unique_array, ...)			       \
+	static struct kunit_suite *unique_array[]			       \
+	__aligned(sizeof(struct kunit_suite *))				       \
+	__used __section(".kunit_init_test_suites") = { __VA_ARGS__ }
+
 /**
  * kunit_test_init_section_suites() - used to register one or more &struct
  *				      kunit_suite containing init functions or
@@ -378,21 +387,21 @@ static inline int kunit_run_all_tests(void)
  *
  * @__suites: a statically allocated list of &struct kunit_suite.
  *
- * This functions identically as kunit_test_suites() except that it suppresses
- * modpost warnings for referencing functions marked __init or data marked
- * __initdata; this is OK because currently KUnit only runs tests upon boot
- * during the init phase or upon loading a module during the init phase.
+ * This functions similar to kunit_test_suites() except that it compiles the
+ * list of suites during init phase.
+ *
+ * This macro also suffixes the array and suite declarations it makes with
+ * _probe; so that modpost suppresses warnings about referencing init data
+ * for symbols named in this manner.
  *
- * NOTE TO KUNIT DEVS: If we ever allow KUnit tests to be run after boot, these
- * tests must be excluded.
+ * Note: these init tests are not able to be run after boot so there is no
+ * "run" debugfs file generated for these tests.
  *
- * The only thing this macro does that's different from kunit_test_suites is
- * that it suffixes the array and suite declarations it makes with _probe;
- * modpost suppresses warnings about referencing init data for symbols named in
- * this manner.
+ * Also, do not mark the suite or test case structs with __initdata because
+ * they will be used after the init phase with debugfs.
  */
 #define kunit_test_init_section_suites(__suites...)			\
-	__kunit_test_suites(CONCATENATE(__UNIQUE_ID(array), _probe),	\
+	__kunit_init_test_suites(CONCATENATE(__UNIQUE_ID(array), _probe), \
 			    ##__suites)
 
 #define kunit_test_init_section_suite(suite)	\
@@ -749,7 +758,7 @@ do {									       \
 		.right_text = #right,					       \
 	};								       \
 									       \
-	if (likely(strcmp(__left, __right) op 0))			       \
+	if (likely((__left) && (__right) && (strcmp(__left, __right) op 0)))   \
 		break;							       \
 									       \
 									       \
@@ -1514,6 +1523,25 @@ do {									       \
 		return NULL;									\
 	}
 
+/**
+ * KUNIT_ARRAY_PARAM_DESC() - Define test parameter generator from an array.
+ * @name:  prefix for the test parameter generator function.
+ * @array: array of test parameters.
+ * @desc_member: structure member from array element to use as description
+ *
+ * Define function @name_gen_params which uses @array to generate parameters.
+ */
+#define KUNIT_ARRAY_PARAM_DESC(name, array, desc_member)					\
+	static const void *name##_gen_params(const void *prev, char *desc)			\
+	{											\
+		typeof((array)[0]) *__next = prev ? ((typeof(__next)) prev) + 1 : (array);	\
+		if (__next - (array) < ARRAY_SIZE((array))) {					\
+			strscpy(desc, __next->desc_member, KUNIT_PARAM_DESC_SIZE);		\
+			return __next;								\
+		}										\
+		return NULL;									\
+	}
+
 // TODO(dlatypov@google.com): consider eventually migrating users to explicitly
 // include resource.h themselves if they need it.
 #include <kunit/resource.h>
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 54189e0e5f41..118a18b7ff84 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -15,7 +15,6 @@
 #include <linux/mod_devicetable.h>
 #include <linux/property.h>
 #include <linux/uuid.h>
-#include <linux/fw_table.h>
 
 struct irq_domain;
 struct irq_domain_ops;
@@ -25,22 +24,13 @@ struct irq_domain_ops;
 #endif
 #include <acpi/acpi.h>
 
-#ifdef CONFIG_ACPI_TABLE_LIB
-#define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, ACPI)
-#define __init_or_acpilib
-#define __initdata_or_acpilib
-#else
-#define EXPORT_SYMBOL_ACPI_LIB(x)
-#define __init_or_acpilib __init
-#define __initdata_or_acpilib __initdata
-#endif
-
 #ifdef	CONFIG_ACPI
 
 #include <linux/list.h>
 #include <linux/dynamic_debug.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/fw_table.h>
 
 #include <acpi/acpi_bus.h>
 #include <acpi/acpi_drivers.h>
@@ -48,6 +38,16 @@ struct irq_domain_ops;
 #include <acpi/acpi_io.h>
 #include <asm/acpi.h>
 
+#ifdef CONFIG_ACPI_TABLE_LIB
+#define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, ACPI)
+#define __init_or_acpilib
+#define __initdata_or_acpilib
+#else
+#define EXPORT_SYMBOL_ACPI_LIB(x)
+#define __init_or_acpilib __init
+#define __initdata_or_acpilib __initdata
+#endif
+
 static inline acpi_handle acpi_device_handle(struct acpi_device *adev)
 {
 	return adev ? adev->handle : NULL;
@@ -424,6 +424,13 @@ extern int acpi_blacklisted(void);
 extern void acpi_osi_setup(char *str);
 extern bool acpi_osi_is_win8(void);
 
+#ifdef CONFIG_ACPI_THERMAL_LIB
+int thermal_acpi_active_trip_temp(struct acpi_device *adev, int id, int *ret_temp);
+int thermal_acpi_passive_trip_temp(struct acpi_device *adev, int *ret_temp);
+int thermal_acpi_hot_trip_temp(struct acpi_device *adev, int *ret_temp);
+int thermal_acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp);
+#endif
+
 #ifdef CONFIG_ACPI_NUMA
 int acpi_map_pxm_to_node(int pxm);
 int acpi_get_node(acpi_handle handle);
@@ -756,6 +763,10 @@ const char *acpi_get_subsystem_id(acpi_handle handle);
 #define ACPI_HANDLE(dev)		(NULL)
 #define ACPI_HANDLE_FWNODE(fwnode)	(NULL)
 
+/* Get rid of the -Wunused-variable for adev */
+#define acpi_dev_uid_match(adev, uid2)			(adev && false)
+#define acpi_dev_hid_uid_match(adev, hid2, uid2)	(adev && false)
+
 #include <acpi/acpi_numa.h>
 
 struct fwnode_handle;
@@ -772,17 +783,6 @@ static inline bool acpi_dev_present(const char *hid, const char *uid, s64 hrv)
 
 struct acpi_device;
 
-static inline bool acpi_dev_uid_match(struct acpi_device *adev, const char *uid2)
-{
-	return false;
-}
-
-static inline bool
-acpi_dev_hid_uid_match(struct acpi_device *adev, const char *hid2, const char *uid2)
-{
-	return false;
-}
-
 static inline int acpi_dev_uid_to_integer(struct acpi_device *adev, u64 *integer)
 {
 	return -ENODEV;
diff --git a/include/linux/acpi_amd_wbrf.h b/include/linux/acpi_amd_wbrf.h
new file mode 100644
index 000000000000..898f31d536d4
--- /dev/null
+++ b/include/linux/acpi_amd_wbrf.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Wifi Band Exclusion Interface (AMD ACPI Implementation)
+ * Copyright (C) 2023 Advanced Micro Devices
+ */
+
+#ifndef _ACPI_AMD_WBRF_H
+#define _ACPI_AMD_WBRF_H
+
+#include <linux/device.h>
+#include <linux/notifier.h>
+
+/* The maximum number of frequency band ranges */
+#define MAX_NUM_OF_WBRF_RANGES		11
+
+/* Record actions */
+#define WBRF_RECORD_ADD		0x0
+#define WBRF_RECORD_REMOVE	0x1
+
+/**
+ * struct freq_band_range - Wifi frequency band range definition
+ * @start: start frequency point (in Hz)
+ * @end: end frequency point (in Hz)
+ */
+struct freq_band_range {
+	u64		start;
+	u64		end;
+};
+
+/**
+ * struct wbrf_ranges_in_out - wbrf ranges info
+ * @num_of_ranges: total number of band ranges in this struct
+ * @band_list: array of Wifi band ranges
+ */
+struct wbrf_ranges_in_out {
+	u64			num_of_ranges;
+	struct freq_band_range	band_list[MAX_NUM_OF_WBRF_RANGES];
+};
+
+/**
+ * enum wbrf_notifier_actions - wbrf notifier actions index
+ * @WBRF_CHANGED: there was some frequency band updates. The consumers
+ *               should retrieve the latest active frequency bands.
+ */
+enum wbrf_notifier_actions {
+	WBRF_CHANGED,
+};
+
+#if IS_ENABLED(CONFIG_AMD_WBRF)
+bool acpi_amd_wbrf_supported_producer(struct device *dev);
+int acpi_amd_wbrf_add_remove(struct device *dev, uint8_t action, struct wbrf_ranges_in_out *in);
+bool acpi_amd_wbrf_supported_consumer(struct device *dev);
+int amd_wbrf_retrieve_freq_band(struct device *dev, struct wbrf_ranges_in_out *out);
+int amd_wbrf_register_notifier(struct notifier_block *nb);
+int amd_wbrf_unregister_notifier(struct notifier_block *nb);
+#else
+static inline
+bool acpi_amd_wbrf_supported_consumer(struct device *dev)
+{
+	return false;
+}
+
+static inline
+int acpi_amd_wbrf_add_remove(struct device *dev, uint8_t action, struct wbrf_ranges_in_out *in)
+{
+	return -ENODEV;
+}
+
+static inline
+bool acpi_amd_wbrf_supported_producer(struct device *dev)
+{
+	return false;
+}
+static inline
+int amd_wbrf_retrieve_freq_band(struct device *dev, struct wbrf_ranges_in_out *out)
+{
+	return -ENODEV;
+}
+static inline
+int amd_wbrf_register_notifier(struct notifier_block *nb)
+{
+	return -ENODEV;
+}
+static inline
+int amd_wbrf_unregister_notifier(struct notifier_block *nb)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_AMD_WBRF */
+
+#endif /* _ACPI_AMD_WBRF_H */
diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h
index 446394f84606..6ad02ad9c7b4 100644
--- a/include/linux/amd-pstate.h
+++ b/include/linux/amd-pstate.h
@@ -70,6 +70,10 @@ struct amd_cpudata {
 	u32	nominal_perf;
 	u32	lowest_nonlinear_perf;
 	u32	lowest_perf;
+	u32     min_limit_perf;
+	u32     max_limit_perf;
+	u32     min_limit_freq;
+	u32     max_limit_freq;
 
 	u32	max_freq;
 	u32	min_freq;
diff --git a/include/linux/apple-mailbox.h b/include/linux/apple-mailbox.h
deleted file mode 100644
index 720fbb70294a..000000000000
--- a/include/linux/apple-mailbox.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only OR MIT */
-/*
- * Apple mailbox message format
- *
- * Copyright (C) 2021 The Asahi Linux Contributors
- */
-
-#ifndef _LINUX_APPLE_MAILBOX_H_
-#define _LINUX_APPLE_MAILBOX_H_
-
-#include <linux/types.h>
-
-/* encodes a single 96bit message sent over the single channel */
-struct apple_mbox_msg {
-	u64 msg0;
-	u32 msg1;
-};
-
-#endif
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index a07b510e7dc5..a63d61ca55af 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -27,6 +27,13 @@ static inline unsigned long topology_get_cpu_scale(int cpu)
 
 void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity);
 
+DECLARE_PER_CPU(unsigned long, capacity_freq_ref);
+
+static inline unsigned long topology_get_freq_ref(int cpu)
+{
+	return per_cpu(capacity_freq_ref, cpu);
+}
+
 DECLARE_PER_CPU(unsigned long, arch_freq_scale);
 
 static inline unsigned long topology_get_freq_scale(int cpu)
@@ -92,6 +99,7 @@ void update_siblings_masks(unsigned int cpu);
 void remove_cpu_topology(unsigned int cpuid);
 void reset_cpu_topology(void);
 int parse_acpi_topology(void);
+void freq_inv_set_max_ratio(int cpu, u64 max_rate);
 #endif
 
 #endif /* _LINUX_ARCH_TOPOLOGY_H_ */
diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h
index 1abedb5b2e48..3d0fde57ba90 100644
--- a/include/linux/arm_ffa.h
+++ b/include/linux/arm_ffa.h
@@ -209,6 +209,8 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev) { return false; }
 #define module_ffa_driver(__ffa_driver)	\
 	module_driver(__ffa_driver, ffa_register, ffa_unregister)
 
+extern struct bus_type ffa_bus_type;
+
 /* FFA transport related */
 struct ffa_partition_info {
 	u16 id;
diff --git a/include/linux/async.h b/include/linux/async.h
index cce4ad31e8fc..33c9ff4afb49 100644
--- a/include/linux/async.h
+++ b/include/linux/async.h
@@ -90,6 +90,8 @@ async_schedule_dev(async_func_t func, struct device *dev)
 	return async_schedule_node(func, dev, dev_to_node(dev));
 }
 
+bool async_schedule_dev_nocall(async_func_t func, struct device *dev);
+
 /**
  * async_schedule_dev_domain - A device specific version of async_schedule_domain
  * @func: function to execute asynchronously
diff --git a/include/linux/audit.h b/include/linux/audit.h
index 51b1b7054a23..0050ef288ab3 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -36,6 +36,7 @@ struct mqstat;
 struct audit_watch;
 struct audit_tree;
 struct sk_buff;
+struct kern_ipc_perm;
 
 struct audit_krule {
 	u32			pflags;
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index 6b3acf15be5c..8e177b67e82f 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -5,6 +5,7 @@
 #define _VIRTCHNL_H_
 
 #include <linux/bitops.h>
+#include <linux/bits.h>
 #include <linux/overflow.h>
 #include <uapi/linux/if_ether.h>
 
@@ -118,6 +119,7 @@ enum virtchnl_ops {
 	VIRTCHNL_OP_GET_STATS = 15,
 	VIRTCHNL_OP_RSVD = 16,
 	VIRTCHNL_OP_EVENT = 17, /* must ALWAYS be 17 */
+	VIRTCHNL_OP_CONFIG_RSS_HFUNC = 18,
 	/* opcode 19 is reserved */
 	VIRTCHNL_OP_IWARP = 20, /* advanced opcode */
 	VIRTCHNL_OP_RDMA = VIRTCHNL_OP_IWARP,
@@ -911,6 +913,29 @@ struct virtchnl_rss_hena {
 
 VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_rss_hena);
 
+/* Type of RSS algorithm */
+enum virtchnl_rss_algorithm {
+	VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC	= 0,
+	VIRTCHNL_RSS_ALG_R_ASYMMETRIC		= 1,
+	VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC	= 2,
+	VIRTCHNL_RSS_ALG_XOR_SYMMETRIC		= 3,
+};
+
+/* VIRTCHNL_OP_CONFIG_RSS_HFUNC
+ * VF sends this message to configure the RSS hash function. Only supported
+ * if both PF and VF drivers set the VIRTCHNL_VF_OFFLOAD_RSS_PF bit during
+ * configuration negotiation.
+ * The hash function is initialized to VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC
+ * by the PF.
+ */
+struct virtchnl_rss_hfunc {
+	u16 vsi_id;
+	u16 rss_algorithm; /* enum virtchnl_rss_algorithm */
+	u32 reserved;
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_rss_hfunc);
+
 /* VIRTCHNL_OP_ENABLE_CHANNELS
  * VIRTCHNL_OP_DISABLE_CHANNELS
  * VF sends these messages to enable or disable channels based on
@@ -1095,14 +1120,6 @@ enum virtchnl_vfr_states {
 	VIRTCHNL_VFR_VFACTIVE,
 };
 
-/* Type of RSS algorithm */
-enum virtchnl_rss_algorithm {
-	VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC	= 0,
-	VIRTCHNL_RSS_ALG_R_ASYMMETRIC		= 1,
-	VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC	= 2,
-	VIRTCHNL_RSS_ALG_XOR_SYMMETRIC		= 3,
-};
-
 #define VIRTCHNL_MAX_NUM_PROTO_HDRS	32
 #define PROTO_HDR_SHIFT			5
 #define PROTO_HDR_FIELD_START(proto_hdr_type) ((proto_hdr_type) << PROTO_HDR_SHIFT)
@@ -1542,6 +1559,9 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
 							 vrl->lut_entries);
 		}
 		break;
+	case VIRTCHNL_OP_CONFIG_RSS_HFUNC:
+		valid_len = sizeof(struct virtchnl_rss_hfunc);
+		break;
 	case VIRTCHNL_OP_GET_RSS_HENA_CAPS:
 		break;
 	case VIRTCHNL_OP_SET_RSS_HENA:
diff --git a/include/linux/backing-file.h b/include/linux/backing-file.h
new file mode 100644
index 000000000000..3f1fe1774f1b
--- /dev/null
+++ b/include/linux/backing-file.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Common helpers for stackable filesystems and backing files.
+ *
+ * Copyright (C) 2023 CTERA Networks.
+ */
+
+#ifndef _LINUX_BACKING_FILE_H
+#define _LINUX_BACKING_FILE_H
+
+#include <linux/file.h>
+#include <linux/uio.h>
+#include <linux/fs.h>
+
+struct backing_file_ctx {
+	const struct cred *cred;
+	struct file *user_file;
+	void (*accessed)(struct file *);
+	void (*end_write)(struct file *);
+};
+
+struct file *backing_file_open(const struct path *user_path, int flags,
+			       const struct path *real_path,
+			       const struct cred *cred);
+ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter,
+			       struct kiocb *iocb, int flags,
+			       struct backing_file_ctx *ctx);
+ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter,
+				struct kiocb *iocb, int flags,
+				struct backing_file_ctx *ctx);
+ssize_t backing_file_splice_read(struct file *in, loff_t *ppos,
+				 struct pipe_inode_info *pipe, size_t len,
+				 unsigned int flags,
+				 struct backing_file_ctx *ctx);
+ssize_t backing_file_splice_write(struct pipe_inode_info *pipe,
+				  struct file *out, loff_t *ppos, size_t len,
+				  unsigned int flags,
+				  struct backing_file_ctx *ctx);
+int backing_file_mmap(struct file *file, struct vm_area_struct *vma,
+		      struct backing_file_ctx *ctx);
+
+#endif /* _LINUX_BACKING_FILE_H */
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 41d417ee1349..ec4db73e5f4e 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -324,6 +324,8 @@ enum bip_flags {
 	BIP_CTRL_NOCHECK	= 1 << 2, /* disable HBA integrity checking */
 	BIP_DISK_NOCHECK	= 1 << 3, /* disable disk integrity checking */
 	BIP_IP_CHECKSUM		= 1 << 4, /* IP checksum */
+	BIP_INTEGRITY_USER	= 1 << 5, /* Integrity payload is user address */
+	BIP_COPY_USER		= 1 << 6, /* Kernel bounce buffer in use */
 };
 
 /*
@@ -718,6 +720,7 @@ static inline bool bioset_initialized(struct bio_set *bs)
 	for_each_bio(_bio)						\
 		bip_for_each_vec(_bvl, _bio->bi_integrity, _iter)
 
+int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t len, u32 seed);
 extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int);
 extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int);
 extern bool bio_integrity_prep(struct bio *);
@@ -789,6 +792,12 @@ static inline int bio_integrity_add_page(struct bio *bio, struct page *page,
 	return 0;
 }
 
+static inline int bio_integrity_map_user(struct bio *bio, void __user *ubuf,
+					 ssize_t len, u32 seed)
+{
+	return -EINVAL;
+}
+
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
 /*
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 1ab3081c82ed..a676e116085f 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -830,6 +830,12 @@ void blk_mq_end_request_batch(struct io_comp_batch *ib);
  */
 static inline bool blk_mq_need_time_stamp(struct request *rq)
 {
+	/*
+	 * passthrough io doesn't use iostat accounting, cgroup stats
+	 * and io scheduler functionalities.
+	 */
+	if (blk_rq_is_passthrough(rq))
+		return false;
 	return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_USE_SCHED));
 }
 
diff --git a/include/linux/blk-pm.h b/include/linux/blk-pm.h
index 2580e05a8ab6..004b38a538ff 100644
--- a/include/linux/blk-pm.h
+++ b/include/linux/blk-pm.h
@@ -15,7 +15,6 @@ extern int blk_pre_runtime_suspend(struct request_queue *q);
 extern void blk_post_runtime_suspend(struct request_queue *q, int err);
 extern void blk_pre_runtime_resume(struct request_queue *q);
 extern void blk_post_runtime_resume(struct request_queue *q);
-extern void blk_set_runtime_active(struct request_queue *q);
 #else
 static inline void blk_pm_runtime_init(struct request_queue *q,
 				       struct device *dev) {}
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index d5c5e59ddbd2..f288c94374b3 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -49,26 +49,26 @@ struct block_device {
 	bool			bd_write_holder;
 	bool			bd_has_submit_bio;
 	dev_t			bd_dev;
+	struct inode		*bd_inode;	/* will die */
+
 	atomic_t		bd_openers;
 	spinlock_t		bd_size_lock; /* for bd_inode->i_size updates */
-	struct inode *		bd_inode;	/* will die */
 	void *			bd_claiming;
 	void *			bd_holder;
 	const struct blk_holder_ops *bd_holder_ops;
 	struct mutex		bd_holder_lock;
-	/* The counter of freeze processes */
-	int			bd_fsfreeze_count;
 	int			bd_holders;
 	struct kobject		*bd_holder_dir;
 
-	/* Mutex for freeze */
-	struct mutex		bd_fsfreeze_mutex;
-	struct super_block	*bd_fsfreeze_sb;
+	atomic_t		bd_fsfreeze_count; /* number of freeze requests */
+	struct mutex		bd_fsfreeze_mutex; /* serialize freeze/thaw */
 
 	struct partition_meta_info *bd_meta_info;
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	bool			bd_make_it_fail;
 #endif
+	bool			bd_ro_warned;
+	int			bd_writers;
 	/*
 	 * keep this out-of-line as it's both big and not needed in the fast
 	 * path
@@ -378,6 +378,8 @@ enum req_op {
 	REQ_OP_DISCARD		= (__force blk_opf_t)3,
 	/* securely erase sectors */
 	REQ_OP_SECURE_ERASE	= (__force blk_opf_t)5,
+	/* write data at the current zone write pointer */
+	REQ_OP_ZONE_APPEND	= (__force blk_opf_t)7,
 	/* write the zero filled sector many times */
 	REQ_OP_WRITE_ZEROES	= (__force blk_opf_t)9,
 	/* Open a zone */
@@ -386,12 +388,10 @@ enum req_op {
 	REQ_OP_ZONE_CLOSE	= (__force blk_opf_t)11,
 	/* Transition a zone to full */
 	REQ_OP_ZONE_FINISH	= (__force blk_opf_t)12,
-	/* write data at the current zone write pointer */
-	REQ_OP_ZONE_APPEND	= (__force blk_opf_t)13,
 	/* reset a zone write pointer */
-	REQ_OP_ZONE_RESET	= (__force blk_opf_t)15,
+	REQ_OP_ZONE_RESET	= (__force blk_opf_t)13,
 	/* reset all the zone present on the device */
-	REQ_OP_ZONE_RESET_ALL	= (__force blk_opf_t)17,
+	REQ_OP_ZONE_RESET_ALL	= (__force blk_opf_t)15,
 
 	/* Driver private requests */
 	REQ_OP_DRV_IN		= (__force blk_opf_t)34,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 51fa7ffdee83..99e4f5e72213 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -124,6 +124,8 @@ typedef unsigned int __bitwise blk_mode_t;
 #define BLK_OPEN_NDELAY		((__force blk_mode_t)(1 << 3))
 /* open for "writes" only for ioctls (specialy hack for floppy.c) */
 #define BLK_OPEN_WRITE_IOCTL	((__force blk_mode_t)(1 << 4))
+/* open is exclusive wrt all other BLK_OPEN_WRITE opens to the device */
+#define BLK_OPEN_RESTRICT_WRITES	((__force blk_mode_t)(1 << 5))
 
 struct gendisk {
 	/*
@@ -264,18 +266,6 @@ static inline bool blk_op_is_passthrough(blk_opf_t op)
 }
 
 /*
- * Zoned block device models (zoned limit).
- *
- * Note: This needs to be ordered from the least to the most severe
- * restrictions for the inheritance in blk_stack_limits() to work.
- */
-enum blk_zoned_model {
-	BLK_ZONED_NONE = 0,	/* Regular block device */
-	BLK_ZONED_HA,		/* Host-aware zoned block device */
-	BLK_ZONED_HM,		/* Host-managed zoned block device */
-};
-
-/*
  * BLK_BOUNCE_NONE:	never bounce (default)
  * BLK_BOUNCE_HIGH:	bounce all highmem pages
  */
@@ -316,7 +306,7 @@ struct queue_limits {
 	unsigned char		misaligned;
 	unsigned char		discard_misaligned;
 	unsigned char		raid_partial_stripes_expensive;
-	enum blk_zoned_model	zoned;
+	bool			zoned;
 
 	/*
 	 * Drivers that set dma_alignment to less than 511 must be prepared to
@@ -329,24 +319,15 @@ struct queue_limits {
 typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx,
 			       void *data);
 
-void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model);
+void disk_set_zoned(struct gendisk *disk);
 
-#ifdef CONFIG_BLK_DEV_ZONED
 #define BLK_ALL_ZONES  ((unsigned int)-1)
 int blkdev_report_zones(struct block_device *bdev, sector_t sector,
-			unsigned int nr_zones, report_zones_cb cb, void *data);
-unsigned int bdev_nr_zones(struct block_device *bdev);
-extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
-			    sector_t sectors, sector_t nr_sectors,
-			    gfp_t gfp_mask);
+		unsigned int nr_zones, report_zones_cb cb, void *data);
+int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
+		sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask);
 int blk_revalidate_disk_zones(struct gendisk *disk,
-			      void (*update_driver_data)(struct gendisk *disk));
-#else /* CONFIG_BLK_DEV_ZONED */
-static inline unsigned int bdev_nr_zones(struct block_device *bdev)
-{
-	return 0;
-}
-#endif /* CONFIG_BLK_DEV_ZONED */
+		void (*update_driver_data)(struct gendisk *disk));
 
 /*
  * Independent access ranges: struct blk_independent_access_range describes
@@ -376,59 +357,51 @@ struct blk_independent_access_ranges {
 };
 
 struct request_queue {
-	struct request		*last_merge;
-	struct elevator_queue	*elevator;
-
-	struct percpu_ref	q_usage_counter;
+	/*
+	 * The queue owner gets to use this for whatever they like.
+	 * ll_rw_blk doesn't touch it.
+	 */
+	void			*queuedata;
 
-	struct blk_queue_stats	*stats;
-	struct rq_qos		*rq_qos;
-	struct mutex		rq_qos_mutex;
+	struct elevator_queue	*elevator;
 
 	const struct blk_mq_ops	*mq_ops;
 
 	/* sw queues */
 	struct blk_mq_ctx __percpu	*queue_ctx;
 
+	/*
+	 * various queue flags, see QUEUE_* below
+	 */
+	unsigned long		queue_flags;
+
+	unsigned int		rq_timeout;
+
 	unsigned int		queue_depth;
 
+	refcount_t		refs;
+
 	/* hw dispatch queues */
-	struct xarray		hctx_table;
 	unsigned int		nr_hw_queues;
+	struct xarray		hctx_table;
 
-	/*
-	 * The queue owner gets to use this for whatever they like.
-	 * ll_rw_blk doesn't touch it.
-	 */
-	void			*queuedata;
-
-	/*
-	 * various queue flags, see QUEUE_* below
-	 */
-	unsigned long		queue_flags;
-	/*
-	 * Number of contexts that have called blk_set_pm_only(). If this
-	 * counter is above zero then only RQF_PM requests are processed.
-	 */
-	atomic_t		pm_only;
+	struct percpu_ref	q_usage_counter;
 
-	/*
-	 * ida allocated id for this queue.  Used to index queues from
-	 * ioctx.
-	 */
-	int			id;
+	struct request		*last_merge;
 
 	spinlock_t		queue_lock;
 
-	struct gendisk		*disk;
+	int			quiesce_depth;
 
-	refcount_t		refs;
+	struct gendisk		*disk;
 
 	/*
 	 * mq queue kobject
 	 */
 	struct kobject *mq_kobj;
 
+	struct queue_limits	limits;
+
 #ifdef  CONFIG_BLK_DEV_INTEGRITY
 	struct blk_integrity integrity;
 #endif	/* CONFIG_BLK_DEV_INTEGRITY */
@@ -439,24 +412,40 @@ struct request_queue {
 #endif
 
 	/*
-	 * queue settings
+	 * Number of contexts that have called blk_set_pm_only(). If this
+	 * counter is above zero then only RQF_PM requests are processed.
 	 */
-	unsigned long		nr_requests;	/* Max # of requests */
+	atomic_t		pm_only;
+
+	struct blk_queue_stats	*stats;
+	struct rq_qos		*rq_qos;
+	struct mutex		rq_qos_mutex;
+
+	/*
+	 * ida allocated id for this queue.  Used to index queues from
+	 * ioctx.
+	 */
+	int			id;
 
 	unsigned int		dma_pad_mask;
 
+	/*
+	 * queue settings
+	 */
+	unsigned long		nr_requests;	/* Max # of requests */
+
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
 	struct blk_crypto_profile *crypto_profile;
 	struct kobject *crypto_kobject;
 #endif
 
-	unsigned int		rq_timeout;
-
 	struct timer_list	timeout;
 	struct work_struct	timeout_work;
 
 	atomic_t		nr_active_requests_shared_tags;
 
+	unsigned int		required_elevator_features;
+
 	struct blk_mq_tags	*sched_shared_tags;
 
 	struct list_head	icq_list;
@@ -467,11 +456,12 @@ struct request_queue {
 	struct mutex		blkcg_mutex;
 #endif
 
-	struct queue_limits	limits;
+	int			node;
 
-	unsigned int		required_elevator_features;
+	spinlock_t		requeue_lock;
+	struct list_head	requeue_list;
+	struct delayed_work	requeue_work;
 
-	int			node;
 #ifdef CONFIG_BLK_DEV_IO_TRACE
 	struct blk_trace __rcu	*blk_trace;
 #endif
@@ -481,10 +471,6 @@ struct request_queue {
 	struct blk_flush_queue	*fq;
 	struct list_head	flush_list;
 
-	struct list_head	requeue_list;
-	spinlock_t		requeue_lock;
-	struct delayed_work	requeue_work;
-
 	struct mutex		sysfs_lock;
 	struct mutex		sysfs_dir_lock;
 
@@ -509,8 +495,6 @@ struct request_queue {
 	 */
 	struct mutex		mq_freeze_lock;
 
-	int			quiesce_depth;
-
 	struct blk_mq_tag_set	*tag_set;
 	struct list_head	tag_set_list;
 
@@ -538,7 +522,7 @@ struct request_queue {
 #define QUEUE_FLAG_ADD_RANDOM	10	/* Contributes to random pool */
 #define QUEUE_FLAG_SYNCHRONOUS	11	/* always completes in submit context */
 #define QUEUE_FLAG_SAME_FORCE	12	/* force complete on same CPU */
-#define QUEUE_FLAG_HW_WC	18	/* Write back caching supported */
+#define QUEUE_FLAG_HW_WC	13	/* Write back caching supported */
 #define QUEUE_FLAG_INIT_DONE	14	/* queue is initialized */
 #define QUEUE_FLAG_STABLE_WRITES 15	/* don't modify blks until WB is done */
 #define QUEUE_FLAG_POLL		16	/* IO polling enabled if set */
@@ -623,26 +607,14 @@ static inline enum rpm_status queue_rpm_status(struct request_queue *q)
 }
 #endif
 
-static inline enum blk_zoned_model
-blk_queue_zoned_model(struct request_queue *q)
-{
-	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED))
-		return q->limits.zoned;
-	return BLK_ZONED_NONE;
-}
-
 static inline bool blk_queue_is_zoned(struct request_queue *q)
 {
-	switch (blk_queue_zoned_model(q)) {
-	case BLK_ZONED_HA:
-	case BLK_ZONED_HM:
-		return true;
-	default:
-		return false;
-	}
+	return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && q->limits.zoned;
 }
 
 #ifdef CONFIG_BLK_DEV_ZONED
+unsigned int bdev_nr_zones(struct block_device *bdev);
+
 static inline unsigned int disk_nr_zones(struct gendisk *disk)
 {
 	return blk_queue_is_zoned(disk->queue) ? disk->nr_zones : 0;
@@ -687,6 +659,11 @@ static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
 }
 
 #else /* CONFIG_BLK_DEV_ZONED */
+static inline unsigned int bdev_nr_zones(struct block_device *bdev)
+{
+	return 0;
+}
+
 static inline unsigned int disk_nr_zones(struct gendisk *disk)
 {
 	return 0;
@@ -1080,7 +1057,14 @@ enum blk_default_limits {
 	BLK_SEG_BOUNDARY_MASK	= 0xFFFFFFFFUL,
 };
 
-#define BLK_DEF_MAX_SECTORS 2560u
+/*
+ * Default upper limit for the software max_sectors limit used for
+ * regular file system I/O.  This can be increased through sysfs.
+ *
+ * Not to be confused with the max_hw_sector limit that is entirely
+ * controlled by the driver, usually based on hardware limits.
+ */
+#define BLK_DEF_MAX_SECTORS_CAP	2560u
 
 static inline unsigned long queue_segment_boundary(const struct request_queue *q)
 {
@@ -1259,11 +1243,6 @@ static inline bool bdev_nowait(struct block_device *bdev)
 	return test_bit(QUEUE_FLAG_NOWAIT, &bdev_get_queue(bdev)->queue_flags);
 }
 
-static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev)
-{
-	return blk_queue_zoned_model(bdev_get_queue(bdev));
-}
-
 static inline bool bdev_is_zoned(struct block_device *bdev)
 {
 	return blk_queue_is_zoned(bdev_get_queue(bdev));
@@ -1468,8 +1447,23 @@ struct blk_holder_ops {
 	 * Sync the file system mounted on the block device.
 	 */
 	void (*sync)(struct block_device *bdev);
+
+	/*
+	 * Freeze the file system mounted on the block device.
+	 */
+	int (*freeze)(struct block_device *bdev);
+
+	/*
+	 * Thaw the file system mounted on the block device.
+	 */
+	int (*thaw)(struct block_device *bdev);
 };
 
+/*
+ * For filesystems using @fs_holder_ops, the @holder argument passed to
+ * helpers used to open and claim block devices via
+ * bd_prepare_to_claim() must point to a superblock.
+ */
 extern const struct blk_holder_ops fs_holder_ops;
 
 /*
@@ -1477,7 +1471,8 @@ extern const struct blk_holder_ops fs_holder_ops;
  * as stored in sb->s_flags.
  */
 #define sb_open_mode(flags) \
-	(BLK_OPEN_READ | (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE))
+	(BLK_OPEN_READ | BLK_OPEN_RESTRICT_WRITES | \
+	 (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE))
 
 struct bdev_handle {
 	struct block_device *bdev;
@@ -1485,10 +1480,6 @@ struct bdev_handle {
 	blk_mode_t mode;
 };
 
-struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder,
-		const struct blk_holder_ops *hops);
-struct block_device *blkdev_get_by_path(const char *path, blk_mode_t mode,
-		void *holder, const struct blk_holder_ops *hops);
 struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
 		const struct blk_holder_ops *hops);
 struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode,
@@ -1496,7 +1487,6 @@ struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode,
 int bd_prepare_to_claim(struct block_device *bdev, void *holder,
 		const struct blk_holder_ops *hops);
 void bd_abort_claiming(struct block_device *bdev, void *holder);
-void blkdev_put(struct block_device *bdev, void *holder);
 void bdev_release(struct bdev_handle *handle);
 
 /* just for blk-cgroup, don't use elsewhere */
@@ -1541,8 +1531,8 @@ static inline int early_lookup_bdev(const char *pathname, dev_t *dev)
 }
 #endif /* CONFIG_BLOCK */
 
-int freeze_bdev(struct block_device *bdev);
-int thaw_bdev(struct block_device *bdev);
+int bdev_freeze(struct block_device *bdev);
+int bdev_thaw(struct block_device *bdev);
 
 struct io_comp_batch {
 	struct request *req_list;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b4825d3cdb29..e30100597d0a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -29,6 +29,7 @@
 #include <linux/rcupdate_trace.h>
 #include <linux/static_call.h>
 #include <linux/memcontrol.h>
+#include <linux/cfi.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -56,7 +57,7 @@ extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
 extern struct kobject *btf_kobj;
 extern struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma;
-extern bool bpf_global_ma_set, bpf_global_percpu_ma_set;
+extern bool bpf_global_ma_set;
 
 typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64);
 typedef int (*bpf_iter_init_seq_priv_t)(void *private_data,
@@ -106,7 +107,11 @@ struct bpf_map_ops {
 	/* funcs called by prog_array and perf_event_array map */
 	void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file,
 				int fd);
-	void (*map_fd_put_ptr)(void *ptr);
+	/* If need_defer is true, the implementation should guarantee that
+	 * the to-be-put element is still alive before the bpf program, which
+	 * may manipulate it, exists.
+	 */
+	void (*map_fd_put_ptr)(struct bpf_map *map, void *ptr, bool need_defer);
 	int (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf);
 	u32 (*map_fd_sys_lookup_elem)(void *ptr);
 	void (*map_seq_show_elem)(struct bpf_map *map, void *key,
@@ -186,8 +191,8 @@ enum btf_field_type {
 	BPF_LIST_NODE  = (1 << 6),
 	BPF_RB_ROOT    = (1 << 7),
 	BPF_RB_NODE    = (1 << 8),
-	BPF_GRAPH_NODE_OR_ROOT = BPF_LIST_NODE | BPF_LIST_HEAD |
-				 BPF_RB_NODE | BPF_RB_ROOT,
+	BPF_GRAPH_NODE = BPF_RB_NODE | BPF_LIST_NODE,
+	BPF_GRAPH_ROOT = BPF_RB_ROOT | BPF_LIST_HEAD,
 	BPF_REFCOUNT   = (1 << 9),
 };
 
@@ -272,7 +277,11 @@ struct bpf_map {
 	 */
 	atomic64_t refcnt ____cacheline_aligned;
 	atomic64_t usercnt;
-	struct work_struct work;
+	/* rcu is used before freeing and work is only used during freeing */
+	union {
+		struct work_struct work;
+		struct rcu_head rcu;
+	};
 	struct mutex freeze_mutex;
 	atomic64_t writecnt;
 	/* 'Ownership' of program-containing map is claimed by the first program
@@ -288,6 +297,9 @@ struct bpf_map {
 	} owner;
 	bool bypass_spec_v1;
 	bool frozen; /* write-once; write-protected by freeze_mutex */
+	bool free_after_mult_rcu_gp;
+	bool free_after_rcu_gp;
+	atomic64_t sleepable_refcnt;
 	s64 __percpu *elem_count;
 };
 
@@ -909,10 +921,14 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size)
 	aux->ctx_field_size = size;
 }
 
+static bool bpf_is_ldimm64(const struct bpf_insn *insn)
+{
+	return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
+}
+
 static inline bool bpf_pseudo_func(const struct bpf_insn *insn)
 {
-	return insn->code == (BPF_LD | BPF_IMM | BPF_DW) &&
-	       insn->src_reg == BPF_PSEUDO_FUNC;
+	return bpf_is_ldimm64(insn) && insn->src_reg == BPF_PSEUDO_FUNC;
 }
 
 struct bpf_prog_ops {
@@ -1040,6 +1056,17 @@ struct btf_func_model {
  */
 #define BPF_TRAMP_F_TAIL_CALL_CTX	BIT(7)
 
+/*
+ * Indicate the trampoline should be suitable to receive indirect calls;
+ * without this indirectly calling the generated code can result in #UD/#CP,
+ * depending on the CFI options.
+ *
+ * Used by bpf_struct_ops.
+ *
+ * Incompatible with FENTRY usage, overloads @func_addr argument.
+ */
+#define BPF_TRAMP_F_INDIRECT		BIT(8)
+
 /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
  * bytes on x86.
  */
@@ -1079,10 +1106,17 @@ struct bpf_tramp_run_ctx;
  *      fexit = a set of program to run after original function
  */
 struct bpf_tramp_image;
-int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end,
+int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
 				const struct btf_func_model *m, u32 flags,
 				struct bpf_tramp_links *tlinks,
-				void *orig_call);
+				void *func_addr);
+void *arch_alloc_bpf_trampoline(unsigned int size);
+void arch_free_bpf_trampoline(void *image, unsigned int size);
+void arch_protect_bpf_trampoline(void *image, unsigned int size);
+void arch_unprotect_bpf_trampoline(void *image, unsigned int size);
+int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
+			     struct bpf_tramp_links *tlinks, void *func_addr);
+
 u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog,
 					     struct bpf_tramp_run_ctx *run_ctx);
 void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start,
@@ -1115,6 +1149,7 @@ enum bpf_tramp_prog_type {
 
 struct bpf_tramp_image {
 	void *image;
+	int size;
 	struct bpf_ksym ksym;
 	struct percpu_ref pcref;
 	void *ip_after_call;
@@ -1184,7 +1219,11 @@ struct bpf_dispatcher {
 #endif
 };
 
-static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func(
+#ifndef __bpfcall
+#define __bpfcall __nocfi
+#endif
+
+static __always_inline __bpfcall unsigned int bpf_dispatcher_nop_func(
 	const void *ctx,
 	const struct bpf_insn *insnsi,
 	bpf_func_t bpf_func)
@@ -1222,6 +1261,8 @@ enum bpf_dynptr_type {
 
 int bpf_dynptr_check_size(u32 size);
 u32 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr);
+const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u32 len);
+void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u32 len);
 
 #ifdef CONFIG_BPF_JIT
 int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr);
@@ -1274,7 +1315,7 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func
 
 #define DEFINE_BPF_DISPATCHER(name)					\
 	__BPF_DISPATCHER_SC(name);					\
-	noinline __nocfi unsigned int bpf_dispatcher_##name##_func(	\
+	noinline __bpfcall unsigned int bpf_dispatcher_##name##_func(	\
 		const void *ctx,					\
 		const struct bpf_insn *insnsi,				\
 		bpf_func_t bpf_func)					\
@@ -1297,7 +1338,7 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func
 void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,
 				struct bpf_prog *to);
 /* Called only from JIT-enabled code, so there's no need for stubs. */
-void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym);
+void bpf_image_ksym_add(void *data, unsigned int size, struct bpf_ksym *ksym);
 void bpf_image_ksym_del(struct bpf_ksym *ksym);
 void bpf_ksym_add(struct bpf_ksym *ksym);
 void bpf_ksym_del(struct bpf_ksym *ksym);
@@ -1341,6 +1382,8 @@ static inline bool bpf_prog_has_trampoline(const struct bpf_prog *prog)
 struct bpf_func_info_aux {
 	u16 linkage;
 	bool unreliable;
+	bool called : 1;
+	bool verified : 1;
 };
 
 enum bpf_jit_poke_reason {
@@ -1406,6 +1449,7 @@ struct bpf_prog_aux {
 	bool dev_bound; /* Program is bound to the netdev. */
 	bool offload_requested; /* Program is bound and offloaded to the netdev. */
 	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
+	bool attach_tracing_prog; /* true if tracing another tracing program */
 	bool func_proto_unreliable;
 	bool sleepable;
 	bool tail_call_reachable;
@@ -1422,6 +1466,9 @@ struct bpf_prog_aux {
 	struct bpf_kfunc_desc_tab *kfunc_tab;
 	struct bpf_kfunc_btf_tab *kfunc_btf_tab;
 	u32 size_poke_tab;
+#ifdef CONFIG_FINEIBT
+	struct bpf_ksym ksym_prefix;
+#endif
 	struct bpf_ksym ksym;
 	const struct bpf_prog_ops *ops;
 	struct bpf_map **used_maps;
@@ -1434,7 +1481,7 @@ struct bpf_prog_aux {
 	int cgroup_atype; /* enum cgroup_bpf_attach_type */
 	struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE];
 	char name[BPF_OBJ_NAME_LEN];
-	unsigned int (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp);
+	u64 (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp, u64, u64);
 #ifdef CONFIG_SECURITY
 	void *security;
 #endif
@@ -1632,6 +1679,7 @@ struct bpf_struct_ops {
 	struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS];
 	u32 type_id;
 	u32 value_id;
+	void *cfi_stubs;
 };
 
 #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL)
@@ -1645,6 +1693,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key,
 int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
 				      struct bpf_tramp_link *link,
 				      const struct btf_func_model *model,
+				      void *stub_func,
 				      void *image, void *image_end);
 static inline bool bpf_try_module_get(const void *data, struct module *owner)
 {
@@ -2418,12 +2467,7 @@ int btf_distill_func_proto(struct bpf_verifier_log *log,
 			   struct btf_func_model *m);
 
 struct bpf_reg_state;
-int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog,
-				struct bpf_reg_state *regs);
-int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
-			   struct bpf_reg_state *regs);
-int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
-			  struct bpf_reg_state *reg, bool is_ex_cb);
+int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog);
 int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog,
 			 struct btf *btf, const struct btf_type *t);
 const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt,
@@ -3171,6 +3215,9 @@ enum bpf_text_poke_type {
 int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 		       void *addr1, void *addr2);
 
+void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
+			       struct bpf_prog *new, struct bpf_prog *old);
+
 void *bpf_arch_text_copy(void *dst, void *src, size_t len);
 int bpf_arch_text_invalidate(void *dst, size_t len);
 
diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h
index bb1223b21308..aaf004d94322 100644
--- a/include/linux/bpf_mem_alloc.h
+++ b/include/linux/bpf_mem_alloc.h
@@ -11,6 +11,7 @@ struct bpf_mem_caches;
 struct bpf_mem_alloc {
 	struct bpf_mem_caches __percpu *caches;
 	struct bpf_mem_cache __percpu *cache;
+	struct obj_cgroup *objcg;
 	bool percpu;
 	struct work_struct work;
 };
@@ -21,8 +22,15 @@ struct bpf_mem_alloc {
  * 'size = 0' is for bpf_mem_alloc which manages many fixed-size objects.
  * Alloc and free are done with bpf_mem_{alloc,free}() and the size of
  * the returned object is given by the size argument of bpf_mem_alloc().
+ * If percpu equals true, error will be returned in order to avoid
+ * large memory consumption and the below bpf_mem_alloc_percpu_unit_init()
+ * should be used to do on-demand per-cpu allocation for each size.
  */
 int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu);
+/* Initialize a non-fix-size percpu memory allocator */
+int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg);
+/* The percpu allocation with a specific unit size. */
+int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size);
 void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma);
 
 /* kmalloc/kfree equivalent: */
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index fc0d6f32c687..94baced5a1ad 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -142,9 +142,13 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter)
 #ifdef CONFIG_NET
 BPF_LINK_TYPE(BPF_LINK_TYPE_NETNS, netns)
 BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp)
+BPF_LINK_TYPE(BPF_LINK_TYPE_NETFILTER, netfilter)
+BPF_LINK_TYPE(BPF_LINK_TYPE_TCX, tcx)
+BPF_LINK_TYPE(BPF_LINK_TYPE_NETKIT, netkit)
 #endif
 #ifdef CONFIG_PERF_EVENTS
 BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf)
 #endif
 BPF_LINK_TYPE(BPF_LINK_TYPE_KPROBE_MULTI, kprobe_multi)
 BPF_LINK_TYPE(BPF_LINK_TYPE_STRUCT_OPS, struct_ops)
+BPF_LINK_TYPE(BPF_LINK_TYPE_UPROBE_MULTI, uprobe_multi)
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 24213a99cc79..d07d857ca67f 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -275,6 +275,11 @@ struct bpf_reference_state {
 	int callback_ref;
 };
 
+struct bpf_retval_range {
+	s32 minval;
+	s32 maxval;
+};
+
 /* state of the program:
  * type of all registers and stack info
  */
@@ -297,24 +302,67 @@ struct bpf_func_state {
 	 * void foo(void) { bpf_timer_set_callback(,foo); }
 	 */
 	u32 async_entry_cnt;
+	struct bpf_retval_range callback_ret_range;
 	bool in_callback_fn;
-	struct tnum callback_ret_range;
 	bool in_async_callback_fn;
 	bool in_exception_callback_fn;
+	/* For callback calling functions that limit number of possible
+	 * callback executions (e.g. bpf_loop) keeps track of current
+	 * simulated iteration number.
+	 * Value in frame N refers to number of times callback with frame
+	 * N+1 was simulated, e.g. for the following call:
+	 *
+	 *   bpf_loop(..., fn, ...); | suppose current frame is N
+	 *                           | fn would be simulated in frame N+1
+	 *                           | number of simulations is tracked in frame N
+	 */
+	u32 callback_depth;
 
 	/* The following fields should be last. See copy_func_state() */
 	int acquired_refs;
 	struct bpf_reference_state *refs;
-	int allocated_stack;
+	/* The state of the stack. Each element of the array describes BPF_REG_SIZE
+	 * (i.e. 8) bytes worth of stack memory.
+	 * stack[0] represents bytes [*(r10-8)..*(r10-1)]
+	 * stack[1] represents bytes [*(r10-16)..*(r10-9)]
+	 * ...
+	 * stack[allocated_stack/8 - 1] represents [*(r10-allocated_stack)..*(r10-allocated_stack+7)]
+	 */
 	struct bpf_stack_state *stack;
+	/* Size of the current stack, in bytes. The stack state is tracked below, in
+	 * `stack`. allocated_stack is always a multiple of BPF_REG_SIZE.
+	 */
+	int allocated_stack;
 };
 
-struct bpf_idx_pair {
-	u32 prev_idx;
+#define MAX_CALL_FRAMES 8
+
+/* instruction history flags, used in bpf_jmp_history_entry.flags field */
+enum {
+	/* instruction references stack slot through PTR_TO_STACK register;
+	 * we also store stack's frame number in lower 3 bits (MAX_CALL_FRAMES is 8)
+	 * and accessed stack slot's index in next 6 bits (MAX_BPF_STACK is 512,
+	 * 8 bytes per slot, so slot index (spi) is [0, 63])
+	 */
+	INSN_F_FRAMENO_MASK = 0x7, /* 3 bits */
+
+	INSN_F_SPI_MASK = 0x3f, /* 6 bits */
+	INSN_F_SPI_SHIFT = 3, /* shifted 3 bits to the left */
+
+	INSN_F_STACK_ACCESS = BIT(9), /* we need 10 bits total */
+};
+
+static_assert(INSN_F_FRAMENO_MASK + 1 >= MAX_CALL_FRAMES);
+static_assert(INSN_F_SPI_MASK + 1 >= MAX_BPF_STACK / 8);
+
+struct bpf_jmp_history_entry {
 	u32 idx;
+	/* insn idx can't be bigger than 1 million */
+	u32 prev_idx : 22;
+	/* special flags, e.g., whether insn is doing register stack spill/load */
+	u32 flags : 10;
 };
 
-#define MAX_CALL_FRAMES 8
 /* Maximum number of register states that can exist at once */
 #define BPF_ID_MAP_SIZE ((MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE) * MAX_CALL_FRAMES)
 struct bpf_verifier_state {
@@ -397,9 +445,10 @@ struct bpf_verifier_state {
 	 * For most states jmp_history_cnt is [0-3].
 	 * For loops can go up to ~40.
 	 */
-	struct bpf_idx_pair *jmp_history;
+	struct bpf_jmp_history_entry *jmp_history;
 	u32 jmp_history_cnt;
 	u32 dfs_depth;
+	u32 callback_unroll_depth;
 };
 
 #define bpf_get_spilled_reg(slot, frame, mask)				\
@@ -511,6 +560,10 @@ struct bpf_insn_aux_data {
 	 * this instruction, regardless of any heuristics
 	 */
 	bool force_checkpoint;
+	/* true if instruction is a call to a helper function that
+	 * accepts callback function as a parameter.
+	 */
+	bool calls_callback;
 };
 
 #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
@@ -553,17 +606,28 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
 
 #define BPF_MAX_SUBPROGS 256
 
+struct bpf_subprog_arg_info {
+	enum bpf_arg_type arg_type;
+	union {
+		u32 mem_size;
+	};
+};
+
 struct bpf_subprog_info {
 	/* 'start' has to be the first field otherwise find_subprog() won't work */
 	u32 start; /* insn idx of function entry point */
 	u32 linfo_idx; /* The idx to the main_prog->aux->linfo */
 	u16 stack_depth; /* max. stack depth used by this function */
-	bool has_tail_call;
-	bool tail_call_reachable;
-	bool has_ld_abs;
-	bool is_cb;
-	bool is_async_cb;
-	bool is_exception_cb;
+	bool has_tail_call: 1;
+	bool tail_call_reachable: 1;
+	bool has_ld_abs: 1;
+	bool is_cb: 1;
+	bool is_async_cb: 1;
+	bool is_exception_cb: 1;
+	bool args_cached: 1;
+
+	u8 arg_cnt;
+	struct bpf_subprog_arg_info args[MAX_BPF_FUNC_REG_ARGS];
 };
 
 struct bpf_verifier_env;
@@ -602,6 +666,7 @@ struct bpf_verifier_env {
 	int stack_size;			/* number of states to be processed */
 	bool strict_alignment;		/* perform strict pointer alignment checks */
 	bool test_state_freq;		/* test verifier with different pruning frequency */
+	bool test_reg_invariants;	/* fail verification on register invariants violations */
 	struct bpf_verifier_state *cur_state; /* current verifier state */
 	struct bpf_verifier_state_list **explored_states; /* search pruning optimization */
 	struct bpf_verifier_state_list *free_list;
@@ -614,6 +679,10 @@ struct bpf_verifier_env {
 	int exception_callback_subprog;
 	bool explore_alu_limits;
 	bool allow_ptr_leaks;
+	/* Allow access to uninitialized stack memory. Writes with fixed offset are
+	 * always allowed, so this refers to reads (with fixed or variable offset),
+	 * to writes with variable offset and to indirect (helper) accesses.
+	 */
 	bool allow_uninit_stack;
 	bool bpf_capable;
 	bool bypass_spec_v1;
@@ -634,6 +703,7 @@ struct bpf_verifier_env {
 		int cur_stack;
 	} cfg;
 	struct backtrack_state bt;
+	struct bpf_jmp_history_entry *cur_hist_ent;
 	u32 pass_cnt; /* number of times do_check() was called */
 	u32 subprog_cnt;
 	/* number of instructions analyzed by the verifier */
@@ -668,6 +738,16 @@ struct bpf_verifier_env {
 	char tmp_str_buf[TMP_STR_BUF_LEN];
 };
 
+static inline struct bpf_func_info_aux *subprog_aux(struct bpf_verifier_env *env, int subprog)
+{
+	return &env->prog->aux->func_info_aux[subprog];
+}
+
+static inline struct bpf_subprog_info *subprog_info(struct bpf_verifier_env *env, int subprog)
+{
+	return &env->subprog_info[subprog];
+}
+
 __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log,
 				      const char *fmt, va_list args);
 __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env,
@@ -679,6 +759,10 @@ int bpf_vlog_init(struct bpf_verifier_log *log, u32 log_level,
 void bpf_vlog_reset(struct bpf_verifier_log *log, u64 new_pos);
 int bpf_vlog_finalize(struct bpf_verifier_log *log, u32 *log_size_actual);
 
+__printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env,
+				  u32 insn_off,
+				  const char *prefix_fmt, ...);
+
 static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env)
 {
 	struct bpf_verifier_state *cur = env->cur_state;
@@ -701,14 +785,6 @@ bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off,
 void
 bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt);
 
-int check_ptr_off_reg(struct bpf_verifier_env *env,
-		      const struct bpf_reg_state *reg, int regno);
-int check_func_arg_reg_off(struct bpf_verifier_env *env,
-			   const struct bpf_reg_state *reg, int regno,
-			   enum bpf_arg_type arg_type);
-int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
-		   u32 regno, u32 mem_size);
-
 /* this lives here instead of in bpf.h because it needs to dereference tgt_prog */
 static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog,
 					     struct btf *btf, u32 btf_id)
@@ -778,4 +854,76 @@ static inline bool bpf_type_has_unsafe_modifiers(u32 type)
 	return type_flag(type) & ~BPF_REG_TRUSTED_MODIFIERS;
 }
 
+static inline bool type_is_ptr_alloc_obj(u32 type)
+{
+	return base_type(type) == PTR_TO_BTF_ID && type_flag(type) & MEM_ALLOC;
+}
+
+static inline bool type_is_non_owning_ref(u32 type)
+{
+	return type_is_ptr_alloc_obj(type) && type_flag(type) & NON_OWN_REF;
+}
+
+static inline bool type_is_pkt_pointer(enum bpf_reg_type type)
+{
+	type = base_type(type);
+	return type == PTR_TO_PACKET ||
+	       type == PTR_TO_PACKET_META;
+}
+
+static inline bool type_is_sk_pointer(enum bpf_reg_type type)
+{
+	return type == PTR_TO_SOCKET ||
+		type == PTR_TO_SOCK_COMMON ||
+		type == PTR_TO_TCP_SOCK ||
+		type == PTR_TO_XDP_SOCK;
+}
+
+static inline void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno)
+{
+	env->scratched_regs |= 1U << regno;
+}
+
+static inline void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi)
+{
+	env->scratched_stack_slots |= 1ULL << spi;
+}
+
+static inline bool reg_scratched(const struct bpf_verifier_env *env, u32 regno)
+{
+	return (env->scratched_regs >> regno) & 1;
+}
+
+static inline bool stack_slot_scratched(const struct bpf_verifier_env *env, u64 regno)
+{
+	return (env->scratched_stack_slots >> regno) & 1;
+}
+
+static inline bool verifier_state_scratched(const struct bpf_verifier_env *env)
+{
+	return env->scratched_regs || env->scratched_stack_slots;
+}
+
+static inline void mark_verifier_state_clean(struct bpf_verifier_env *env)
+{
+	env->scratched_regs = 0U;
+	env->scratched_stack_slots = 0ULL;
+}
+
+/* Used for printing the entire verifier state. */
+static inline void mark_verifier_state_scratched(struct bpf_verifier_env *env)
+{
+	env->scratched_regs = ~0U;
+	env->scratched_stack_slots = ~0ULL;
+}
+
+const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type);
+const char *dynptr_type_str(enum bpf_dynptr_type type);
+const char *iter_type_str(const struct btf *btf, u32 btf_id);
+const char *iter_state_str(enum bpf_iter_state state);
+
+void print_verifier_state(struct bpf_verifier_env *env,
+			  const struct bpf_func_state *state, bool print_all);
+void print_insn_state(struct bpf_verifier_env *env, const struct bpf_func_state *state);
+
 #endif /* _LINUX_BPF_VERIFIER_H */
diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h
deleted file mode 100644
index 736ded4905e0..000000000000
--- a/include/linux/bpfilter.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_BPFILTER_H
-#define _LINUX_BPFILTER_H
-
-#include <uapi/linux/bpfilter.h>
-#include <linux/usermode_driver.h>
-#include <linux/sockptr.h>
-
-struct sock;
-int bpfilter_ip_set_sockopt(struct sock *sk, int optname, sockptr_t optval,
-			    unsigned int optlen);
-int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval,
-			    int __user *optlen);
-
-struct bpfilter_umh_ops {
-	struct umd_info info;
-	/* since ip_getsockopt() can run in parallel, serialize access to umh */
-	struct mutex lock;
-	int (*sockopt)(struct sock *sk, int optname, sockptr_t optval,
-		       unsigned int optlen, bool is_set);
-	int (*start)(void);
-};
-extern struct bpfilter_umh_ops bpfilter_ops;
-#endif
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 5f23ee599889..d78454a4dd1f 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -205,7 +205,6 @@ struct buffer_head *create_empty_buffers(struct folio *folio,
 		unsigned long blocksize, unsigned long b_state);
 void end_buffer_read_sync(struct buffer_head *bh, int uptodate);
 void end_buffer_write_sync(struct buffer_head *bh, int uptodate);
-void end_buffer_async_write(struct buffer_head *bh, int uptodate);
 
 /* Things to do with buffers at mapping->private_list */
 void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode);
@@ -252,11 +251,10 @@ void __bh_read_batch(int nr, struct buffer_head *bhs[],
  * address_spaces.
  */
 void block_invalidate_folio(struct folio *folio, size_t offset, size_t length);
-int block_write_full_page(struct page *page, get_block_t *get_block,
-				struct writeback_control *wbc);
+int block_write_full_folio(struct folio *folio, struct writeback_control *wbc,
+		void *get_block);
 int __block_write_full_folio(struct inode *inode, struct folio *folio,
-			get_block_t *get_block, struct writeback_control *wbc,
-			bh_end_io_t *handler);
+		get_block_t *get_block, struct writeback_control *wbc);
 int block_read_full_folio(struct folio *, get_block_t *);
 bool block_is_partially_uptodate(struct folio *, size_t from, size_t count);
 int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
@@ -270,7 +268,6 @@ int generic_write_end(struct file *, struct address_space *,
 				loff_t, unsigned, unsigned,
 				struct page *, void *);
 void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to);
-void clean_page_buffers(struct page *page);
 int cont_write_begin(struct file *, struct address_space *, loff_t,
 			unsigned, struct page **, void **,
 			get_block_t *, loff_t *);
diff --git a/include/linux/cache.h b/include/linux/cache.h
index 9900d20b76c2..0ecb17bb6883 100644
--- a/include/linux/cache.h
+++ b/include/linux/cache.h
@@ -85,6 +85,31 @@
 #define cache_line_size()	L1_CACHE_BYTES
 #endif
 
+#ifndef __cacheline_group_begin
+#define __cacheline_group_begin(GROUP) \
+	__u8 __cacheline_group_begin__##GROUP[0]
+#endif
+
+#ifndef __cacheline_group_end
+#define __cacheline_group_end(GROUP) \
+	__u8 __cacheline_group_end__##GROUP[0]
+#endif
+
+#ifndef CACHELINE_ASSERT_GROUP_MEMBER
+#define CACHELINE_ASSERT_GROUP_MEMBER(TYPE, GROUP, MEMBER) \
+	BUILD_BUG_ON(!(offsetof(TYPE, MEMBER) >= \
+		       offsetofend(TYPE, __cacheline_group_begin__##GROUP) && \
+		       offsetofend(TYPE, MEMBER) <= \
+		       offsetof(TYPE, __cacheline_group_end__##GROUP)))
+#endif
+
+#ifndef CACHELINE_ASSERT_GROUP_SIZE
+#define CACHELINE_ASSERT_GROUP_SIZE(TYPE, GROUP, SIZE) \
+	BUILD_BUG_ON(offsetof(TYPE, __cacheline_group_end__##GROUP) - \
+		     offsetofend(TYPE, __cacheline_group_begin__##GROUP) > \
+		     SIZE)
+#endif
+
 /*
  * Helper to add padding within a struct to ensure data fall into separate
  * cachelines.
diff --git a/include/linux/cfi.h b/include/linux/cfi.h
index 3552ec82b725..f0df518e11dd 100644
--- a/include/linux/cfi.h
+++ b/include/linux/cfi.h
@@ -9,6 +9,14 @@
 
 #include <linux/bug.h>
 #include <linux/module.h>
+#include <asm/cfi.h>
+
+#ifndef cfi_get_offset
+static inline int cfi_get_offset(void)
+{
+	return 0;
+}
+#endif
 
 #ifdef CONFIG_CFI_CLANG
 enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr,
@@ -38,4 +46,8 @@ static inline void module_cfi_finalize(const Elf_Ehdr *hdr,
 #endif /* CONFIG_ARCH_USES_CFI_TRAPS */
 #endif /* CONFIG_MODULES */
 
+#ifndef CFI_NOSEAL
+#define CFI_NOSEAL(x)
+#endif
+
 #endif /* _LINUX_CFI_H */
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 4a6b6b77ccb6..ea48c861cd36 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -496,6 +496,20 @@ struct cgroup {
 	struct cgroup_rstat_cpu __percpu *rstat_cpu;
 	struct list_head rstat_css_list;
 
+	/*
+	 * Add padding to separate the read mostly rstat_cpu and
+	 * rstat_css_list into a different cacheline from the following
+	 * rstat_flush_next and *bstat fields which can have frequent updates.
+	 */
+	CACHELINE_PADDING(_pad_);
+
+	/*
+	 * A singly-linked list of cgroup structures to be rstat flushed.
+	 * This is a scratch field to be used exclusively by
+	 * cgroup_rstat_flush_locked() and protected by cgroup_rstat_lock.
+	 */
+	struct cgroup	*rstat_flush_next;
+
 	/* cgroup basic resource statistics */
 	struct cgroup_base_stat last_bstat;
 	struct cgroup_base_stat bstat;
@@ -548,6 +562,10 @@ struct cgroup_root {
 	/* Unique id for this hierarchy. */
 	int hierarchy_id;
 
+	/* A list running through the active hierarchies */
+	struct list_head root_list;
+	struct rcu_head rcu;	/* Must be near the top */
+
 	/*
 	 * The root cgroup. The containing cgroup_root will be destroyed on its
 	 * release. cgrp->ancestors[0] will be used overflowing into the
@@ -561,9 +579,6 @@ struct cgroup_root {
 	/* Number of cgroups in the hierarchy, used only for /proc/cgroups */
 	atomic_t nr_cgrps;
 
-	/* A list running through the active hierarchies */
-	struct list_head root_list;
-
 	/* Hierarchy-specific flags */
 	unsigned int flags;
 
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 0ef0af66080e..34aaf0e87def 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -69,6 +69,7 @@ struct css_task_iter {
 extern struct file_system_type cgroup_fs_type;
 extern struct cgroup_root cgrp_dfl_root;
 extern struct css_set init_css_set;
+extern spinlock_t css_set_lock;
 
 #define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys;
 #include <linux/cgroup_subsys.h>
@@ -386,7 +387,6 @@ static inline void cgroup_unlock(void)
  * as locks used during the cgroup_subsys::attach() methods.
  */
 #ifdef CONFIG_PROVE_RCU
-extern spinlock_t css_set_lock;
 #define task_css_set_check(task, __c)					\
 	rcu_dereference_check((task)->cgroups,				\
 		rcu_read_lock_sched_held() ||				\
@@ -853,4 +853,6 @@ static inline void cgroup_bpf_put(struct cgroup *cgrp) {}
 
 #endif /* CONFIG_CGROUP_BPF */
 
+struct cgroup *task_get_cgroup1(struct task_struct *tsk, int hierarchy_id);
+
 #endif /* _LINUX_CGROUP_H */
diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h
index 9f1a9c455b68..c2d09bc4f976 100644
--- a/include/linux/cleanup.h
+++ b/include/linux/cleanup.h
@@ -125,25 +125,55 @@ static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \
  *	trivial wrapper around DEFINE_CLASS() above specifically
  *	for locks.
  *
+ * DEFINE_GUARD_COND(name, ext, condlock)
+ *	wrapper around EXTEND_CLASS above to add conditional lock
+ *	variants to a base class, eg. mutex_trylock() or
+ *	mutex_lock_interruptible().
+ *
  * guard(name):
- *	an anonymous instance of the (guard) class
+ *	an anonymous instance of the (guard) class, not recommended for
+ *	conditional locks.
  *
  * scoped_guard (name, args...) { }:
  *	similar to CLASS(name, scope)(args), except the variable (with the
  *	explicit name 'scope') is declard in a for-loop such that its scope is
  *	bound to the next (compound) statement.
  *
+ *	for conditional locks the loop body is skipped when the lock is not
+ *	acquired.
+ *
+ * scoped_cond_guard (name, fail, args...) { }:
+ *      similar to scoped_guard(), except it does fail when the lock
+ *      acquire fails.
+ *
  */
 
 #define DEFINE_GUARD(_name, _type, _lock, _unlock) \
-	DEFINE_CLASS(_name, _type, _unlock, ({ _lock; _T; }), _type _T)
+	DEFINE_CLASS(_name, _type, if (_T) { _unlock; }, ({ _lock; _T; }), _type _T); \
+	static inline void * class_##_name##_lock_ptr(class_##_name##_t *_T) \
+	{ return *_T; }
+
+#define DEFINE_GUARD_COND(_name, _ext, _condlock) \
+	EXTEND_CLASS(_name, _ext, \
+		     ({ void *_t = _T; if (_T && !(_condlock)) _t = NULL; _t; }), \
+		     class_##_name##_t _T) \
+	static inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \
+	{ return class_##_name##_lock_ptr(_T); }
 
 #define guard(_name) \
 	CLASS(_name, __UNIQUE_ID(guard))
 
+#define __guard_ptr(_name) class_##_name##_lock_ptr
+
 #define scoped_guard(_name, args...)					\
 	for (CLASS(_name, scope)(args),					\
-	     *done = NULL; !done; done = (void *)1)
+	     *done = NULL; __guard_ptr(_name)(&scope) && !done; done = (void *)1)
+
+#define scoped_cond_guard(_name, _fail, args...) \
+	for (CLASS(_name, scope)(args), \
+	     *done = NULL; !done; done = (void *)1) \
+		if (!__guard_ptr(_name)(&scope)) _fail; \
+		else
 
 /*
  * Additional helper macros for generating lock guards with types, either for
@@ -152,6 +182,7 @@ static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \
  *
  * DEFINE_LOCK_GUARD_0(name, lock, unlock, ...)
  * DEFINE_LOCK_GUARD_1(name, type, lock, unlock, ...)
+ * DEFINE_LOCK_GUARD_1_COND(name, ext, condlock)
  *
  * will result in the following type:
  *
@@ -173,6 +204,11 @@ typedef struct {							\
 static inline void class_##_name##_destructor(class_##_name##_t *_T)	\
 {									\
 	if (_T->lock) { _unlock; }					\
+}									\
+									\
+static inline void *class_##_name##_lock_ptr(class_##_name##_t *_T)	\
+{									\
+	return _T->lock;						\
 }
 
 
@@ -201,4 +237,14 @@ __DEFINE_LOCK_GUARD_1(_name, _type, _lock)
 __DEFINE_UNLOCK_GUARD(_name, void, _unlock, __VA_ARGS__)		\
 __DEFINE_LOCK_GUARD_0(_name, _lock)
 
+#define DEFINE_LOCK_GUARD_1_COND(_name, _ext, _condlock)		\
+	EXTEND_CLASS(_name, _ext,					\
+		     ({ class_##_name##_t _t = { .lock = l }, *_T = &_t;\
+		        if (_T->lock && !(_condlock)) _T->lock = NULL;	\
+			_t; }),						\
+		     typeof_member(class_##_name##_t, lock) l)		\
+	static inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \
+	{ return class_##_name##_lock_ptr(_T); }
+
+
 #endif /* __LINUX_GUARDS_H */
diff --git a/include/linux/closure.h b/include/linux/closure.h
index de7bb47d8a46..c554c6a08768 100644
--- a/include/linux/closure.h
+++ b/include/linux/closure.h
@@ -104,7 +104,7 @@
 
 struct closure;
 struct closure_syncer;
-typedef void (closure_fn) (struct closure *);
+typedef void (closure_fn) (struct work_struct *);
 extern struct dentry *bcache_debug;
 
 struct closure_waitlist {
@@ -254,7 +254,7 @@ static inline void closure_queue(struct closure *cl)
 		INIT_WORK(&cl->work, cl->work.func);
 		BUG_ON(!queue_work(wq, &cl->work));
 	} else
-		cl->fn(cl);
+		cl->fn(&cl->work);
 }
 
 /**
@@ -309,6 +309,11 @@ static inline void closure_wake_up(struct closure_waitlist *list)
 	__closure_wake_up(list);
 }
 
+#define CLOSURE_CALLBACK(name)	void name(struct work_struct *ws)
+#define closure_type(name, type, member)				\
+	struct closure *cl = container_of(ws, struct closure, work);	\
+	type *name = container_of(cl, type, member)
+
 /**
  * continue_at - jump to another function with barrier
  *
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 2ceba3fe4ec1..aebb65bf95a7 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -136,7 +136,7 @@
 #endif
 
 #define __diag_ignore_all(option, comment) \
-	__diag_GCC(8, ignore, option)
+	__diag(__diag_GCC_ignore option)
 
 /*
  * Prior to 9.1, -Wno-alloc-size-larger-than (and therefore the "alloc_size"
diff --git a/include/linux/connector.h b/include/linux/connector.h
index cec2d99ae902..70bc1160f3d8 100644
--- a/include/linux/connector.h
+++ b/include/linux/connector.h
@@ -100,8 +100,7 @@ void cn_del_callback(const struct cb_id *id);
  */
 int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid,
 			 u32 group, gfp_t gfp_mask,
-			 int (*filter)(struct sock *dsk, struct sk_buff *skb,
-				       void *data),
+			 netlink_filter_fn filter,
 			 void *filter_data);
 
 /**
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 1c5ca92a0555..afda5f24d3dd 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -1203,6 +1203,7 @@ void arch_set_freq_scale(const struct cpumask *cpus,
 {
 }
 #endif
+
 /* the following are really really optional */
 extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs;
 extern struct freq_attr cpufreq_freq_attr_scaling_boost_freqs;
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index d305db70674b..172d0a743e5d 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -66,15 +66,12 @@ enum cpuhp_state {
 	CPUHP_PERF_POWER,
 	CPUHP_PERF_SUPERH,
 	CPUHP_X86_HPET_DEAD,
-	CPUHP_X86_APB_DEAD,
 	CPUHP_X86_MCE_DEAD,
 	CPUHP_VIRT_NET_DEAD,
 	CPUHP_IBMVNIC_DEAD,
 	CPUHP_SLUB_DEAD,
 	CPUHP_DEBUG_OBJ_DEAD,
 	CPUHP_MM_WRITEBACK_DEAD,
-	/* Must be after CPUHP_MM_VMSTAT_DEAD */
-	CPUHP_MM_DEMOTION_DEAD,
 	CPUHP_MM_VMSTAT_DEAD,
 	CPUHP_SOFTIRQ_DEAD,
 	CPUHP_NET_MVNETA_DEAD,
@@ -96,7 +93,6 @@ enum cpuhp_state {
 	CPUHP_NET_DEV_DEAD,
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_IOVA_DEAD,
-	CPUHP_LUSTRE_CFS_DEAD,
 	CPUHP_AP_ARM_CACHE_B15_RAC_DEAD,
 	CPUHP_PADATA_DEAD,
 	CPUHP_AP_DTPM_CPU_DEAD,
@@ -108,7 +104,6 @@ enum cpuhp_state {
 	CPUHP_X2APIC_PREPARE,
 	CPUHP_SMPCFD_PREPARE,
 	CPUHP_RELAY_PREPARE,
-	CPUHP_SLAB_PREPARE,
 	CPUHP_MD_RAID5_PREPARE,
 	CPUHP_RCUTREE_PREP,
 	CPUHP_CPUIDLE_COUPLED_PREPARE,
@@ -118,13 +113,11 @@ enum cpuhp_state {
 	CPUHP_XEN_EVTCHN_PREPARE,
 	CPUHP_ARM_SHMOBILE_SCU_PREPARE,
 	CPUHP_SH_SH3X_PREPARE,
-	CPUHP_NET_FLOW_PREPARE,
 	CPUHP_TOPOLOGY_PREPARE,
 	CPUHP_NET_IUCV_PREPARE,
 	CPUHP_ARM_BL_PREPARE,
 	CPUHP_TRACE_RB_PREPARE,
 	CPUHP_MM_ZS_PREPARE,
-	CPUHP_MM_ZSWP_MEM_PREPARE,
 	CPUHP_MM_ZSWP_POOL_PREPARE,
 	CPUHP_KVM_PPC_BOOK3S_PREPARE,
 	CPUHP_ZCOMP_PREPARE,
@@ -151,18 +144,14 @@ enum cpuhp_state {
 	CPUHP_AP_IRQ_ARMADA_XP_STARTING,
 	CPUHP_AP_IRQ_BCM2836_STARTING,
 	CPUHP_AP_IRQ_MIPS_GIC_STARTING,
-	CPUHP_AP_IRQ_RISCV_STARTING,
 	CPUHP_AP_IRQ_LOONGARCH_STARTING,
 	CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING,
 	CPUHP_AP_ARM_MVEBU_COHERENCY,
-	CPUHP_AP_MICROCODE_LOADER,
 	CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
 	CPUHP_AP_PERF_X86_STARTING,
 	CPUHP_AP_PERF_X86_AMD_IBS_STARTING,
-	CPUHP_AP_PERF_X86_CQM_STARTING,
 	CPUHP_AP_PERF_X86_CSTATE_STARTING,
 	CPUHP_AP_PERF_XTENSA_STARTING,
-	CPUHP_AP_MIPS_OP_LOONGSON3_STARTING,
 	CPUHP_AP_ARM_VFP_STARTING,
 	CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING,
 	CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING,
@@ -179,7 +168,6 @@ enum cpuhp_state {
 	CPUHP_AP_QCOM_TIMER_STARTING,
 	CPUHP_AP_TEGRA_TIMER_STARTING,
 	CPUHP_AP_ARMADA_TIMER_STARTING,
-	CPUHP_AP_MARCO_TIMER_STARTING,
 	CPUHP_AP_MIPS_GIC_TIMER_STARTING,
 	CPUHP_AP_ARC_TIMER_STARTING,
 	CPUHP_AP_RISCV_TIMER_STARTING,
@@ -195,6 +183,7 @@ enum cpuhp_state {
 	CPUHP_AP_ARM_CORESIGHT_CTI_STARTING,
 	CPUHP_AP_ARM64_ISNDEP_STARTING,
 	CPUHP_AP_SMPCFD_DYING,
+	CPUHP_AP_HRTIMERS_DYING,
 	CPUHP_AP_X86_TBOOT_DYING,
 	CPUHP_AP_ARM_CACHE_B15_RAC_DYING,
 	CPUHP_AP_ONLINE,
@@ -216,9 +205,7 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE,
 	CPUHP_AP_PERF_X86_AMD_POWER_ONLINE,
 	CPUHP_AP_PERF_X86_RAPL_ONLINE,
-	CPUHP_AP_PERF_X86_CQM_ONLINE,
 	CPUHP_AP_PERF_X86_CSTATE_ONLINE,
-	CPUHP_AP_PERF_X86_IDXD_ONLINE,
 	CPUHP_AP_PERF_S390_CF_ONLINE,
 	CPUHP_AP_PERF_S390_SF_ONLINE,
 	CPUHP_AP_PERF_ARM_CCI_ONLINE,
@@ -250,9 +237,7 @@ enum cpuhp_state {
 	CPUHP_AP_RCUTREE_ONLINE,
 	CPUHP_AP_BASE_CACHEINFO_ONLINE,
 	CPUHP_AP_ONLINE_DYN,
-	CPUHP_AP_ONLINE_DYN_END		= CPUHP_AP_ONLINE_DYN + 30,
-	/* Must be after CPUHP_AP_ONLINE_DYN for node_states[N_CPU] update */
-	CPUHP_AP_MM_DEMOTION_ONLINE,
+	CPUHP_AP_ONLINE_DYN_END		= CPUHP_AP_ONLINE_DYN + 40,
 	CPUHP_AP_X86_HPET_ONLINE,
 	CPUHP_AP_X86_KVM_CLK_ONLINE,
 	CPUHP_AP_ACTIVE,
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index d629094fac6e..875d12598bd2 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -77,6 +77,7 @@ extern void cpuset_lock(void);
 extern void cpuset_unlock(void);
 extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
 extern bool cpuset_cpus_allowed_fallback(struct task_struct *p);
+extern bool cpuset_cpu_is_isolated(int cpu);
 extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
 #define cpuset_current_mems_allowed (current->mems_allowed)
 void cpuset_init_current_mems_allowed(void);
@@ -207,6 +208,11 @@ static inline bool cpuset_cpus_allowed_fallback(struct task_struct *p)
 	return false;
 }
 
+static inline bool cpuset_cpu_is_isolated(int cpu)
+{
+	return false;
+}
+
 static inline nodemask_t cpuset_mems_allowed(struct task_struct *p)
 {
 	return node_possible_map;
diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h
index 5126a4fecb44..9eaeaafe0cad 100644
--- a/include/linux/crash_core.h
+++ b/include/linux/crash_core.h
@@ -87,12 +87,6 @@ Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
 			  void *data, size_t data_len);
 void final_note(Elf_Word *buf);
 
-#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
-#ifndef DEFAULT_CRASH_KERNEL_LOW_SIZE
-#define DEFAULT_CRASH_KERNEL_LOW_SIZE  (128UL << 20)
-#endif
-#endif
-
 int __init parse_crashkernel(char *cmdline, unsigned long long system_ram,
 		unsigned long long *crash_size, unsigned long long *crash_base,
 		unsigned long long *low_size, bool *high);
diff --git a/include/linux/crc-ccitt.h b/include/linux/crc-ccitt.h
index 72c92c396bb8..cd4f420231ba 100644
--- a/include/linux/crc-ccitt.h
+++ b/include/linux/crc-ccitt.h
@@ -5,19 +5,12 @@
 #include <linux/types.h>
 
 extern u16 const crc_ccitt_table[256];
-extern u16 const crc_ccitt_false_table[256];
 
 extern u16 crc_ccitt(u16 crc, const u8 *buffer, size_t len);
-extern u16 crc_ccitt_false(u16 crc, const u8 *buffer, size_t len);
 
 static inline u16 crc_ccitt_byte(u16 crc, const u8 c)
 {
 	return (crc >> 8) ^ crc_ccitt_table[(crc ^ c) & 0xff];
 }
 
-static inline u16 crc_ccitt_false_byte(u16 crc, const u8 c)
-{
-    return (crc << 8) ^ crc_ccitt_false_table[(crc >> 8) ^ c];
-}
-
 #endif /* _LINUX_CRC_CCITT_H */
diff --git a/include/linux/cred.h b/include/linux/cred.h
index af8d353a4b86..2976f534a7a3 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -109,14 +109,7 @@ static inline int groups_search(const struct group_info *group_info, kgid_t grp)
  * same context as task->real_cred.
  */
 struct cred {
-	atomic_t	usage;
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	atomic_t	subscribers;	/* number of processes subscribed */
-	void		*put_addr;
-	unsigned	magic;
-#define CRED_MAGIC	0x43736564
-#define CRED_MAGIC_DEAD	0x44656144
-#endif
+	atomic_long_t	usage;
 	kuid_t		uid;		/* real UID of the task */
 	kgid_t		gid;		/* real GID of the task */
 	kuid_t		suid;		/* saved UID of the task */
@@ -172,46 +165,6 @@ extern int cred_fscmp(const struct cred *, const struct cred *);
 extern void __init cred_init(void);
 extern int set_cred_ucounts(struct cred *);
 
-/*
- * check for validity of credentials
- */
-#ifdef CONFIG_DEBUG_CREDENTIALS
-extern void __noreturn __invalid_creds(const struct cred *, const char *, unsigned);
-extern void __validate_process_creds(struct task_struct *,
-				     const char *, unsigned);
-
-extern bool creds_are_invalid(const struct cred *cred);
-
-static inline void __validate_creds(const struct cred *cred,
-				    const char *file, unsigned line)
-{
-	if (unlikely(creds_are_invalid(cred)))
-		__invalid_creds(cred, file, line);
-}
-
-#define validate_creds(cred)				\
-do {							\
-	__validate_creds((cred), __FILE__, __LINE__);	\
-} while(0)
-
-#define validate_process_creds()				\
-do {								\
-	__validate_process_creds(current, __FILE__, __LINE__);	\
-} while(0)
-
-extern void validate_creds_for_do_exit(struct task_struct *);
-#else
-static inline void validate_creds(const struct cred *cred)
-{
-}
-static inline void validate_creds_for_do_exit(struct task_struct *tsk)
-{
-}
-static inline void validate_process_creds(void)
-{
-}
-#endif
-
 static inline bool cap_ambient_invariant_ok(const struct cred *cred)
 {
 	return cap_issubset(cred->cap_ambient,
@@ -229,7 +182,7 @@ static inline bool cap_ambient_invariant_ok(const struct cred *cred)
  */
 static inline struct cred *get_new_cred_many(struct cred *cred, int nr)
 {
-	atomic_add(nr, &cred->usage);
+	atomic_long_add(nr, &cred->usage);
 	return cred;
 }
 
@@ -264,7 +217,6 @@ static inline const struct cred *get_cred_many(const struct cred *cred, int nr)
 	struct cred *nonconst_cred = (struct cred *) cred;
 	if (!cred)
 		return cred;
-	validate_creds(cred);
 	nonconst_cred->non_rcu = 0;
 	return get_new_cred_many(nonconst_cred, nr);
 }
@@ -288,9 +240,8 @@ static inline const struct cred *get_cred_rcu(const struct cred *cred)
 	struct cred *nonconst_cred = (struct cred *) cred;
 	if (!cred)
 		return NULL;
-	if (!atomic_inc_not_zero(&nonconst_cred->usage))
+	if (!atomic_long_inc_not_zero(&nonconst_cred->usage))
 		return NULL;
-	validate_creds(cred);
 	nonconst_cred->non_rcu = 0;
 	return cred;
 }
@@ -312,8 +263,7 @@ static inline void put_cred_many(const struct cred *_cred, int nr)
 	struct cred *cred = (struct cred *) _cred;
 
 	if (cred) {
-		validate_creds(cred);
-		if (atomic_sub_and_test(nr, &cred->usage))
+		if (atomic_long_sub_and_test(nr, &cred->usage))
 			__put_cred(cred);
 	}
 }
diff --git a/include/linux/damon.h b/include/linux/damon.h
index ab2f17d9926b..5881e4ac30be 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -2,7 +2,7 @@
 /*
  * DAMON api
  *
- * Author: SeongJae Park <sjpark@amazon.de>
+ * Author: SeongJae Park <sj@kernel.org>
  */
 
 #ifndef _DAMON_H_
@@ -136,6 +136,9 @@ enum damos_action {
  * @weight_nr_accesses:	Weight of the region's nr_accesses for prioritization.
  * @weight_age:		Weight of the region's age for prioritization.
  *
+ * @get_score:		Feedback function for self-tuning quota.
+ * @get_score_arg:	Parameter for @get_score
+ *
  * To avoid consuming too much CPU time or IO resources for applying the
  * &struct damos->action to large memory, DAMON allows users to set time and/or
  * size quotas.  The quotas can be set by writing non-zero values to &ms and
@@ -153,6 +156,17 @@ enum damos_action {
  * You could customize the prioritization logic by setting &weight_sz,
  * &weight_nr_accesses, and &weight_age, because monitoring operations are
  * encouraged to respect those.
+ *
+ * If @get_score function pointer is set, DAMON calls it back with
+ * @get_score_arg and get the return value of it for every @reset_interval.
+ * Then, DAMON adjusts the effective quota using the return value as a feedback
+ * score to the current quota, using its internal feedback loop algorithm.
+ *
+ * The feedback loop algorithem assumes the quota input and the feedback score
+ * output are in a positive proportional relationship, and the goal of the
+ * tuning is getting the feedback screo value of 10,000.  If @ms and/or @sz are
+ * set together, those work as a hard limit quota.  If neither @ms nor @sz are
+ * set, the mechanism starts from the quota of one byte.
  */
 struct damos_quota {
 	unsigned long ms;
@@ -163,6 +177,9 @@ struct damos_quota {
 	unsigned int weight_nr_accesses;
 	unsigned int weight_age;
 
+	unsigned long (*get_score)(void *arg);
+	void *get_score_arg;
+
 /* private: */
 	/* For throughput estimation */
 	unsigned long total_charged_sz;
@@ -179,6 +196,9 @@ struct damos_quota {
 	/* For prioritization */
 	unsigned long histogram[DAMOS_MAX_SCORE + 1];
 	unsigned int min_score;
+
+	/* For feedback loop */
+	unsigned long esz_bp;
 };
 
 /**
@@ -559,6 +579,8 @@ struct damon_ctx {
 	 * update
 	 */
 	unsigned long next_ops_update_sis;
+	/* for waiting until the execution of the kdamond_fn is started */
+	struct completion kdamond_started;
 
 /* public: */
 	struct task_struct *kdamond;
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index ea2d919fd9c7..c9c65b132c0f 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -171,6 +171,25 @@ ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf,
 ssize_t debugfs_read_file_str(struct file *file, char __user *user_buf,
 			      size_t count, loff_t *ppos);
 
+/**
+ * struct debugfs_cancellation - cancellation data
+ * @list: internal, for keeping track
+ * @cancel: callback to call
+ * @cancel_data: extra data for the callback to call
+ */
+struct debugfs_cancellation {
+	struct list_head list;
+	void (*cancel)(struct dentry *, void *);
+	void *cancel_data;
+};
+
+void __acquires(cancellation)
+debugfs_enter_cancellation(struct file *file,
+			   struct debugfs_cancellation *cancellation);
+void __releases(cancellation)
+debugfs_leave_cancellation(struct file *file,
+			   struct debugfs_cancellation *cancellation);
+
 #else
 
 #include <linux/err.h>
diff --git a/include/linux/device.h b/include/linux/device.h
index d7a72a8749ea..6c83294395ac 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1007,6 +1007,8 @@ static inline void device_unlock(struct device *dev)
 	mutex_unlock(&dev->mutex);
 }
 
+DEFINE_GUARD(device, struct device *, device_lock(_T), device_unlock(_T))
+
 static inline void device_lock_assert(struct device *dev)
 {
 	lockdep_assert_held(&dev->mutex);
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 18aade195884..3eb3589ff43e 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -21,7 +21,6 @@ struct bus_dma_region {
 	phys_addr_t	cpu_start;
 	dma_addr_t	dma_start;
 	u64		size;
-	u64		offset;
 };
 
 static inline dma_addr_t translate_phys_to_dma(struct device *dev,
@@ -29,9 +28,12 @@ static inline dma_addr_t translate_phys_to_dma(struct device *dev,
 {
 	const struct bus_dma_region *m;
 
-	for (m = dev->dma_range_map; m->size; m++)
-		if (paddr >= m->cpu_start && paddr - m->cpu_start < m->size)
-			return (dma_addr_t)paddr - m->offset;
+	for (m = dev->dma_range_map; m->size; m++) {
+		u64 offset = paddr - m->cpu_start;
+
+		if (paddr >= m->cpu_start && offset < m->size)
+			return m->dma_start + offset;
+	}
 
 	/* make sure dma_capable fails when no translation is available */
 	return DMA_MAPPING_ERROR;
@@ -42,9 +44,12 @@ static inline phys_addr_t translate_dma_to_phys(struct device *dev,
 {
 	const struct bus_dma_region *m;
 
-	for (m = dev->dma_range_map; m->size; m++)
-		if (dma_addr >= m->dma_start && dma_addr - m->dma_start < m->size)
-			return (phys_addr_t)dma_addr + m->offset;
+	for (m = dev->dma_range_map; m->size; m++) {
+		u64 offset = dma_addr - m->dma_start;
+
+		if (dma_addr >= m->dma_start && offset < m->size)
+			return m->cpu_start + offset;
+	}
 
 	return (phys_addr_t)-1;
 }
diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
index ebe78bd3d121..e06bad467f55 100644
--- a/include/linux/dma-fence.h
+++ b/include/linux/dma-fence.h
@@ -21,6 +21,7 @@
 #include <linux/sched.h>
 #include <linux/printk.h>
 #include <linux/rcupdate.h>
+#include <linux/timekeeping.h>
 
 struct dma_fence;
 struct dma_fence_ops;
@@ -499,6 +500,21 @@ static inline bool dma_fence_is_later(struct dma_fence *f1,
 }
 
 /**
+ * dma_fence_is_later_or_same - return true if f1 is later or same as f2
+ * @f1: the first fence from the same context
+ * @f2: the second fence from the same context
+ *
+ * Returns true if f1 is chronologically later than f2 or the same fence. Both
+ * fences must be from the same context, since a seqno is not re-used across
+ * contexts.
+ */
+static inline bool dma_fence_is_later_or_same(struct dma_fence *f1,
+					      struct dma_fence *f2)
+{
+	return f1 == f2 || dma_fence_is_later(f1, f2);
+}
+
+/**
  * dma_fence_later - return the chronologically later fence
  * @f1:	the first fence from the same context
  * @f2:	the second fence from the same context
diff --git a/include/linux/dpll.h b/include/linux/dpll.h
index 578fc5fa3750..9cf896ea1d41 100644
--- a/include/linux/dpll.h
+++ b/include/linux/dpll.h
@@ -17,9 +17,6 @@ struct dpll_pin;
 struct dpll_device_ops {
 	int (*mode_get)(const struct dpll_device *dpll, void *dpll_priv,
 			enum dpll_mode *mode, struct netlink_ext_ack *extack);
-	bool (*mode_supported)(const struct dpll_device *dpll, void *dpll_priv,
-			       const enum dpll_mode mode,
-			       struct netlink_ext_ack *extack);
 	int (*lock_status_get)(const struct dpll_device *dpll, void *dpll_priv,
 			       enum dpll_lock_status *status,
 			       struct netlink_ext_ack *extack);
@@ -80,6 +77,9 @@ struct dpll_pin_ops {
 				const struct dpll_device *dpll, void *dpll_priv,
 				const s32 phase_adjust,
 				struct netlink_ext_ack *extack);
+	int (*ffo_get)(const struct dpll_pin *pin, void *pin_priv,
+		       const struct dpll_device *dpll, void *dpll_priv,
+		       s64 *ffo, struct netlink_ext_ack *extack);
 };
 
 struct dpll_pin_frequency {
diff --git a/include/linux/edac.h b/include/linux/edac.h
index fa4bda2a70f6..1174beb94ab6 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -187,6 +187,7 @@ static inline char *mc_event_error_type(const unsigned int err_type)
  * @MEM_NVDIMM:		Non-volatile RAM
  * @MEM_WIO2:		Wide I/O 2.
  * @MEM_HBM2:		High bandwidth Memory Gen 2.
+ * @MEM_HBM3:		High bandwidth Memory Gen 3.
  */
 enum mem_type {
 	MEM_EMPTY = 0,
@@ -218,6 +219,7 @@ enum mem_type {
 	MEM_NVDIMM,
 	MEM_WIO2,
 	MEM_HBM2,
+	MEM_HBM3,
 };
 
 #define MEM_FLAG_EMPTY		BIT(MEM_EMPTY)
@@ -248,6 +250,7 @@ enum mem_type {
 #define MEM_FLAG_NVDIMM		BIT(MEM_NVDIMM)
 #define MEM_FLAG_WIO2		BIT(MEM_WIO2)
 #define MEM_FLAG_HBM2		BIT(MEM_HBM2)
+#define MEM_FLAG_HBM3		BIT(MEM_HBM3)
 
 /**
  * enum edac_type - Error Detection and Correction capabilities and mode
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 9cc5bf32f6f2..c74f47711f0b 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -40,6 +40,7 @@ struct screen_info;
 #define EFI_WRITE_PROTECTED	( 8 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_OUT_OF_RESOURCES	( 9 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_NOT_FOUND		(14 | (1UL << (BITS_PER_LONG-1)))
+#define EFI_ACCESS_DENIED	(15 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_TIMEOUT		(18 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_ABORTED		(21 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_SECURITY_VIOLATION	(26 | (1UL << (BITS_PER_LONG-1)))
@@ -1348,4 +1349,15 @@ bool efi_config_table_is_usable(const efi_guid_t *guid, unsigned long table)
 
 umode_t efi_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n);
 
+/*
+ * efivar ops event type
+ */
+#define EFIVAR_OPS_RDONLY 0
+#define EFIVAR_OPS_RDWR 1
+
+extern struct blocking_notifier_head efivar_ops_nh;
+
+void efivars_generic_ops_register(void);
+void efivars_generic_ops_unregister(void);
+
 #endif /* _LINUX_EFI_H */
diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index b9caa01dfac4..88d91e087471 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -224,7 +224,7 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
 				unsigned long max_util, unsigned long sum_util,
 				unsigned long allowed_cpu_cap)
 {
-	unsigned long freq, scale_cpu;
+	unsigned long freq, ref_freq, scale_cpu;
 	struct em_perf_state *ps;
 	int cpu;
 
@@ -241,11 +241,10 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
 	 */
 	cpu = cpumask_first(to_cpumask(pd->cpus));
 	scale_cpu = arch_scale_cpu_capacity(cpu);
-	ps = &pd->table[pd->nr_perf_states - 1];
+	ref_freq = arch_scale_freq_ref(cpu);
 
-	max_util = map_util_perf(max_util);
 	max_util = min(max_util, allowed_cpu_cap);
-	freq = map_util_freq(max_util, ps->frequency, scale_cpu);
+	freq = map_util_freq(max_util, ref_freq, scale_cpu);
 
 	/*
 	 * Find the lowest performance state of the Energy Model above the
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index d95ab85f96ba..b0fb775a600d 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -7,6 +7,11 @@
 #include <linux/syscalls.h>
 #include <linux/seccomp.h>
 #include <linux/sched.h>
+#include <linux/context_tracking.h>
+#include <linux/livepatch.h>
+#include <linux/resume_user_mode.h>
+#include <linux/tick.h>
+#include <linux/kmsan.h>
 
 #include <asm/entry-common.h>
 
@@ -98,7 +103,19 @@ static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) {}
  * done between establishing state and enabling interrupts. The caller must
  * enable interrupts before invoking syscall_enter_from_user_mode_work().
  */
-void enter_from_user_mode(struct pt_regs *regs);
+static __always_inline void enter_from_user_mode(struct pt_regs *regs)
+{
+	arch_enter_from_user_mode(regs);
+	lockdep_hardirqs_off(CALLER_ADDR0);
+
+	CT_WARN_ON(__ct_state() != CONTEXT_USER);
+	user_exit_irqoff();
+
+	instrumentation_begin();
+	kmsan_unpoison_entry_regs(regs);
+	trace_hardirqs_off_finish();
+	instrumentation_end();
+}
 
 /**
  * syscall_enter_from_user_mode_prepare - Establish state and enable interrupts
@@ -117,6 +134,9 @@ void enter_from_user_mode(struct pt_regs *regs);
  */
 void syscall_enter_from_user_mode_prepare(struct pt_regs *regs);
 
+long syscall_trace_enter(struct pt_regs *regs, long syscall,
+			 unsigned long work);
+
 /**
  * syscall_enter_from_user_mode_work - Check and handle work before invoking
  *				       a syscall
@@ -140,7 +160,15 @@ void syscall_enter_from_user_mode_prepare(struct pt_regs *regs);
  *     ptrace_report_syscall_entry(), __secure_computing(), trace_sys_enter()
  *  2) Invocation of audit_syscall_entry()
  */
-long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall);
+static __always_inline long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall)
+{
+	unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
+
+	if (work & SYSCALL_WORK_ENTER)
+		syscall = syscall_trace_enter(regs, syscall, work);
+
+	return syscall;
+}
 
 /**
  * syscall_enter_from_user_mode - Establish state and check and handle work
@@ -159,7 +187,19 @@ long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall);
  * Returns: The original or a modified syscall number. See
  * syscall_enter_from_user_mode_work() for further explanation.
  */
-long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall);
+static __always_inline long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
+{
+	long ret;
+
+	enter_from_user_mode(regs);
+
+	instrumentation_begin();
+	local_irq_enable();
+	ret = syscall_enter_from_user_mode_work(regs, syscall);
+	instrumentation_end();
+
+	return ret;
+}
 
 /**
  * local_irq_enable_exit_to_user - Exit to user variant of local_irq_enable()
@@ -259,6 +299,43 @@ static __always_inline void arch_exit_to_user_mode(void) { }
 void arch_do_signal_or_restart(struct pt_regs *regs);
 
 /**
+ * exit_to_user_mode_loop - do any pending work before leaving to user space
+ */
+unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
+				     unsigned long ti_work);
+
+/**
+ * exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required
+ * @regs:	Pointer to pt_regs on entry stack
+ *
+ * 1) check that interrupts are disabled
+ * 2) call tick_nohz_user_enter_prepare()
+ * 3) call exit_to_user_mode_loop() if any flags from
+ *    EXIT_TO_USER_MODE_WORK are set
+ * 4) check that interrupts are still disabled
+ */
+static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs)
+{
+	unsigned long ti_work;
+
+	lockdep_assert_irqs_disabled();
+
+	/* Flush pending rcuog wakeup before the last need_resched() check */
+	tick_nohz_user_enter_prepare();
+
+	ti_work = read_thread_flags();
+	if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
+		ti_work = exit_to_user_mode_loop(regs, ti_work);
+
+	arch_exit_to_user_mode_prepare(regs, ti_work);
+
+	/* Ensure that kernel state is sane for a return to userspace */
+	kmap_assert_nomap();
+	lockdep_assert_irqs_disabled();
+	lockdep_sys_exit();
+}
+
+/**
  * exit_to_user_mode - Fixup state when exiting to user mode
  *
  * Syscall/interrupt exit enables interrupts, but the kernel state is
@@ -276,7 +353,17 @@ void arch_do_signal_or_restart(struct pt_regs *regs);
  * non-instrumentable.
  * The caller has to invoke syscall_exit_to_user_mode_work() before this.
  */
-void exit_to_user_mode(void);
+static __always_inline void exit_to_user_mode(void)
+{
+	instrumentation_begin();
+	trace_hardirqs_on_prepare();
+	lockdep_hardirqs_on_prepare();
+	instrumentation_end();
+
+	user_enter_irqoff();
+	arch_exit_to_user_mode();
+	lockdep_hardirqs_on(CALLER_ADDR0);
+}
 
 /**
  * syscall_exit_to_user_mode_work - Handle work before returning to user mode
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 689028257fcc..325e0778e937 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -95,6 +95,7 @@ struct kernel_ethtool_ringparam {
  * @ETHTOOL_RING_USE_TX_PUSH: capture for setting tx_push
  * @ETHTOOL_RING_USE_RX_PUSH: capture for setting rx_push
  * @ETHTOOL_RING_USE_TX_PUSH_BUF_LEN: capture for setting tx_push_buf_len
+ * @ETHTOOL_RING_USE_TCP_DATA_SPLIT: capture for setting tcp_data_split
  */
 enum ethtool_supported_ring_param {
 	ETHTOOL_RING_USE_RX_BUF_LEN		= BIT(0),
@@ -102,6 +103,7 @@ enum ethtool_supported_ring_param {
 	ETHTOOL_RING_USE_TX_PUSH		= BIT(2),
 	ETHTOOL_RING_USE_RX_PUSH		= BIT(3),
 	ETHTOOL_RING_USE_TX_PUSH_BUF_LEN	= BIT(4),
+	ETHTOOL_RING_USE_TCP_DATA_SPLIT		= BIT(5),
 };
 
 #define __ETH_RSS_HASH_BIT(bit)	((u32)1 << (bit))
@@ -409,8 +411,10 @@ struct ethtool_pause_stats {
  *	not entire FEC data blocks. This is a non-standard statistic.
  *	Reported to user space as %ETHTOOL_A_FEC_STAT_CORR_BITS.
  *
- * @lane: per-lane/PCS-instance counts as defined by the standard
- * @total: error counts for the entire port, for drivers incapable of reporting
+ * For each of the above fields, the two substructure members are:
+ *
+ * - @lanes: per-lane/PCS-instance counts as defined by the standard
+ * - @total: error counts for the entire port, for drivers incapable of reporting
  *	per-lane stats
  *
  * Drivers should fill in either only total or per-lane statistics, core
@@ -595,9 +599,46 @@ struct ethtool_mm_stats {
 };
 
 /**
+ * struct ethtool_rxfh_param - RXFH (RSS) parameters
+ * @hfunc: Defines the current RSS hash function used by HW (or to be set to).
+ *	Valid values are one of the %ETH_RSS_HASH_*.
+ * @indir_size: On SET, the array size of the user buffer for the
+ *	indirection table, which may be zero, or
+ *	%ETH_RXFH_INDIR_NO_CHANGE.  On GET (read from the driver),
+ *	the array size of the hardware indirection table.
+ * @indir: The indirection table of size @indir_size entries.
+ * @key_size: On SET, the array size of the user buffer for the hash key,
+ *	which may be zero.  On GET (read from the driver), the size of the
+ *	hardware hash key.
+ * @key: The hash key of size @key_size bytes.
+ * @rss_context: RSS context identifier.  Context 0 is the default for normal
+ *	traffic; other contexts can be referenced as the destination for RX flow
+ *	classification rules.  On SET, %ETH_RXFH_CONTEXT_ALLOC is used
+ *	to allocate a new RSS context; on return this field will
+ *	contain the ID of the newly allocated context.
+ * @rss_delete: Set to non-ZERO to remove the @rss_context context.
+ * @input_xfrm: Defines how the input data is transformed. Valid values are one
+ *	of %RXH_XFRM_*.
+ */
+struct ethtool_rxfh_param {
+	u8	hfunc;
+	u32	indir_size;
+	u32	*indir;
+	u32	key_size;
+	u8	*key;
+	u32	rss_context;
+	u8	rss_delete;
+	u8	input_xfrm;
+};
+
+/**
  * struct ethtool_ops - optional netdev operations
  * @cap_link_lanes_supported: indicates if the driver supports lanes
  *	parameter.
+ * @cap_rss_ctx_supported: indicates if the driver supports RSS
+ *	contexts.
+ * @cap_rss_sym_xor_supported: indicates if the driver supports symmetric-xor
+ *	RSS.
  * @supported_coalesce_params: supported types of interrupt coalescing.
  * @supported_ring_params: supported ring params.
  * @get_drvinfo: Report driver/device information. Modern drivers no
@@ -694,15 +735,6 @@ struct ethtool_mm_stats {
  *	will remain unchanged.
  *	Returns a negative error code or zero. An error code must be returned
  *	if at least one unsupported change was requested.
- * @get_rxfh_context: Get the contents of the RX flow hash indirection table,
- *	hash key, and/or hash function assiciated to the given rss context.
- *	Returns a negative error code or zero.
- * @set_rxfh_context: Create, remove and configure RSS contexts. Allows setting
- *	the contents of the RX flow hash indirection table, hash key, and/or
- *	hash function associated to the given context. Arguments which are set
- *	to %NULL or zero will remain unchanged.
- *	Returns a negative error code or zero. An error code must be returned
- *	if at least one unsupported change was requested.
  * @get_channels: Get number of channels.
  * @set_channels: Set number of channels.  Returns a negative error code or
  *	zero.
@@ -785,6 +817,8 @@ struct ethtool_mm_stats {
  */
 struct ethtool_ops {
 	u32     cap_link_lanes_supported:1;
+	u32     cap_rss_ctx_supported:1;
+	u32	cap_rss_sym_xor_supported:1;
 	u32	supported_coalesce_params;
 	u32	supported_ring_params;
 	void	(*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *);
@@ -844,15 +878,9 @@ struct ethtool_ops {
 	int	(*reset)(struct net_device *, u32 *);
 	u32	(*get_rxfh_key_size)(struct net_device *);
 	u32	(*get_rxfh_indir_size)(struct net_device *);
-	int	(*get_rxfh)(struct net_device *, u32 *indir, u8 *key,
-			    u8 *hfunc);
-	int	(*set_rxfh)(struct net_device *, const u32 *indir,
-			    const u8 *key, const u8 hfunc);
-	int	(*get_rxfh_context)(struct net_device *, u32 *indir, u8 *key,
-				    u8 *hfunc, u32 rss_context);
-	int	(*set_rxfh_context)(struct net_device *, const u32 *indir,
-				    const u8 *key, const u8 hfunc,
-				    u32 *rss_context, bool delete);
+	int	(*get_rxfh)(struct net_device *, struct ethtool_rxfh_param *);
+	int	(*set_rxfh)(struct net_device *, struct ethtool_rxfh_param *,
+			    struct netlink_ext_ack *extack);
 	void	(*get_channels)(struct net_device *, struct ethtool_channels *);
 	int	(*set_channels)(struct net_device *, struct ethtool_channels *);
 	int	(*get_dump_flag)(struct net_device *, struct ethtool_dump *);
@@ -1044,6 +1072,14 @@ static inline int ethtool_mm_frag_size_min_to_add(u32 val_min, u32 *val_add,
 }
 
 /**
+ * ethtool_get_ts_info_by_layer - Obtains time stamping capabilities from the MAC or PHY layer.
+ * @dev: pointer to net_device structure
+ * @info: buffer to hold the result
+ * Returns zero on success, non-zero otherwise.
+ */
+int ethtool_get_ts_info_by_layer(struct net_device *dev, struct ethtool_ts_info *info);
+
+/**
  * ethtool_sprintf - Write formatted string to ethtool string data
  * @data: Pointer to a pointer to the start of string to update
  * @fmt: Format of string to write
@@ -1053,6 +1089,19 @@ static inline int ethtool_mm_frag_size_min_to_add(u32 val_min, u32 *val_add,
  */
 extern __printf(2, 3) void ethtool_sprintf(u8 **data, const char *fmt, ...);
 
+/**
+ * ethtool_puts - Write string to ethtool string data
+ * @data: Pointer to a pointer to the start of string to update
+ * @str: String to write
+ *
+ * Write string to *data without a trailing newline. Update *data
+ * to point at start of next string.
+ *
+ * Prefer this function to ethtool_sprintf() when given only
+ * two arguments or if @fmt is just "%s".
+ */
+extern void ethtool_puts(u8 **data, const char *str);
+
 /* Link mode to forced speed capabilities maps */
 struct ethtool_forced_speed_map {
 	u32		speed;
diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
index b9d83652c097..e32bee4345fb 100644
--- a/include/linux/eventfd.h
+++ b/include/linux/eventfd.h
@@ -35,8 +35,7 @@ void eventfd_ctx_put(struct eventfd_ctx *ctx);
 struct file *eventfd_fget(int fd);
 struct eventfd_ctx *eventfd_ctx_fdget(int fd);
 struct eventfd_ctx *eventfd_ctx_fileget(struct file *file);
-__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n);
-__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask);
+void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask);
 int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait,
 				  __u64 *cnt);
 void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt);
@@ -58,15 +57,8 @@ static inline struct eventfd_ctx *eventfd_ctx_fdget(int fd)
 	return ERR_PTR(-ENOSYS);
 }
 
-static inline int eventfd_signal(struct eventfd_ctx *ctx, __u64 n)
+static inline void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask)
 {
-	return -ENOSYS;
-}
-
-static inline int eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n,
-				      unsigned mask)
-{
-	return -ENOSYS;
 }
 
 static inline void eventfd_ctx_put(struct eventfd_ctx *ctx)
@@ -92,5 +84,10 @@ static inline void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
 
 #endif
 
+static inline void eventfd_signal(struct eventfd_ctx *ctx)
+{
+	eventfd_signal_mask(ctx, 0);
+}
+
 #endif /* _LINUX_EVENTFD_H */
 
diff --git a/include/linux/evm.h b/include/linux/evm.h
index 01fc495a83e2..36ec884320d9 100644
--- a/include/linux/evm.h
+++ b/include/linux/evm.h
@@ -31,6 +31,7 @@ extern void evm_inode_post_setxattr(struct dentry *dentry,
 				    const char *xattr_name,
 				    const void *xattr_value,
 				    size_t xattr_value_len);
+extern int evm_inode_copy_up_xattr(const char *name);
 extern int evm_inode_removexattr(struct mnt_idmap *idmap,
 				 struct dentry *dentry, const char *xattr_name);
 extern void evm_inode_post_removexattr(struct dentry *dentry,
@@ -117,6 +118,11 @@ static inline void evm_inode_post_setxattr(struct dentry *dentry,
 	return;
 }
 
+static inline int  evm_inode_copy_up_xattr(const char *name)
+{
+	return 0;
+}
+
 static inline int evm_inode_removexattr(struct mnt_idmap *idmap,
 					struct dentry *dentry,
 					const char *xattr_name)
diff --git a/include/linux/export-internal.h b/include/linux/export-internal.h
index 45fca09b2319..d445705ac13c 100644
--- a/include/linux/export-internal.h
+++ b/include/linux/export-internal.h
@@ -16,10 +16,13 @@
  * and eliminates the need for absolute relocations that require runtime
  * processing on relocatable kernels.
  */
+#define __KSYM_ALIGN		".balign 4"
 #define __KSYM_REF(sym)		".long " #sym "- ."
 #elif defined(CONFIG_64BIT)
+#define __KSYM_ALIGN		".balign 8"
 #define __KSYM_REF(sym)		".quad " #sym
 #else
+#define __KSYM_ALIGN		".balign 4"
 #define __KSYM_REF(sym)		".long " #sym
 #endif
 
@@ -42,7 +45,7 @@
 	    "	.asciz \"" ns "\""					"\n"	\
 	    "	.previous"						"\n"	\
 	    "	.section \"___ksymtab" sec "+" #name "\", \"a\""	"\n"	\
-	    "	.balign	4"						"\n"	\
+		__KSYM_ALIGN						"\n"	\
 	    "__ksymtab_" #name ":"					"\n"	\
 		__KSYM_REF(sym)						"\n"	\
 		__KSYM_REF(__kstrtab_ ##name)				"\n"	\
@@ -50,9 +53,7 @@
 	    "	.previous"						"\n"	\
 	)
 
-#ifdef CONFIG_IA64
-#define KSYM_FUNC(name)		@fptr(name)
-#elif defined(CONFIG_PARISC) && defined(CONFIG_64BIT)
+#if defined(CONFIG_PARISC) && defined(CONFIG_64BIT)
 #define KSYM_FUNC(name)		P%name
 #else
 #define KSYM_FUNC(name)		name
@@ -63,6 +64,7 @@
 
 #define SYMBOL_CRC(sym, crc, sec)   \
 	asm(".section \"___kcrctab" sec "+" #sym "\",\"a\""	"\n" \
+	    ".balign 4"						"\n" \
 	    "__crc_" #sym ":"					"\n" \
 	    ".long " #crc					"\n" \
 	    ".previous"						"\n")
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index bc4c3287a65e..78c8326d74ae 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -83,12 +83,17 @@ struct dentry;
 static inline struct file *files_lookup_fd_raw(struct files_struct *files, unsigned int fd)
 {
 	struct fdtable *fdt = rcu_dereference_raw(files->fdt);
-
-	if (fd < fdt->max_fds) {
-		fd = array_index_nospec(fd, fdt->max_fds);
-		return rcu_dereference_raw(fdt->fd[fd]);
-	}
-	return NULL;
+	unsigned long mask = array_index_mask_nospec(fd, fdt->max_fds);
+	struct file *needs_masking;
+
+	/*
+	 * 'mask' is zero for an out-of-bounds fd, all ones for ok.
+	 * 'fd&mask' is 'fd' for ok, or 0 for out of bounds.
+	 *
+	 * Accessing fdt->fd[0] is ok, but needs masking of the result.
+	 */
+	needs_masking = rcu_dereference_raw(fdt->fd[fd&mask]);
+	return (struct file *)(mask & (unsigned long)needs_masking);
 }
 
 static inline struct file *files_lookup_fd_locked(struct files_struct *files, unsigned int fd)
@@ -114,7 +119,7 @@ int iterate_fd(struct files_struct *, unsigned,
 
 extern int close_fd(unsigned int fd);
 extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags);
-extern struct file *close_fd_get_file(unsigned int fd);
+extern struct file *file_close_fd(unsigned int fd);
 extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
 		      struct files_struct **new_fdp);
 
diff --git a/include/linux/file.h b/include/linux/file.h
index 6e9099d29343..6834a29338c4 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -96,18 +96,8 @@ DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T),
 
 extern void fd_install(unsigned int fd, struct file *file);
 
-extern int __receive_fd(struct file *file, int __user *ufd,
-			unsigned int o_flags);
+int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags);
 
-extern int receive_fd(struct file *file, unsigned int o_flags);
-
-static inline int receive_fd_user(struct file *file, int __user *ufd,
-				  unsigned int o_flags)
-{
-	if (ufd == NULL)
-		return -EFAULT;
-	return __receive_fd(file, ufd, o_flags);
-}
 int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags);
 
 extern void flush_delayed_fput(void);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index a4953fafc8cb..68fb6c8142fe 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1067,7 +1067,7 @@ struct bpf_binary_header *
 bpf_jit_binary_pack_hdr(const struct bpf_prog *fp);
 
 void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns);
-void bpf_prog_pack_free(struct bpf_binary_header *hdr);
+void bpf_prog_pack_free(void *ptr, u32 size);
 
 static inline bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp)
 {
diff --git a/include/linux/firmware.h b/include/linux/firmware.h
index de7fea3bca51..0311858b46ce 100644
--- a/include/linux/firmware.h
+++ b/include/linux/firmware.h
@@ -27,6 +27,7 @@ struct firmware {
  * @FW_UPLOAD_ERR_INVALID_SIZE: invalid firmware image size
  * @FW_UPLOAD_ERR_RW_ERROR: read or write to HW failed, see kernel log
  * @FW_UPLOAD_ERR_WEAROUT: FLASH device is approaching wear-out, wait & retry
+ * @FW_UPLOAD_ERR_FW_INVALID: invalid firmware file
  * @FW_UPLOAD_ERR_MAX: Maximum error code marker
  */
 enum fw_upload_err {
@@ -38,6 +39,7 @@ enum fw_upload_err {
 	FW_UPLOAD_ERR_INVALID_SIZE,
 	FW_UPLOAD_ERR_RW_ERROR,
 	FW_UPLOAD_ERR_WEAROUT,
+	FW_UPLOAD_ERR_FW_INVALID,
 	FW_UPLOAD_ERR_MAX
 };
 
diff --git a/include/linux/framer/framer-provider.h b/include/linux/framer/framer-provider.h
new file mode 100644
index 000000000000..782cd5fc83d5
--- /dev/null
+++ b/include/linux/framer/framer-provider.h
@@ -0,0 +1,194 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Generic framer profider header file
+ *
+ * Copyright 2023 CS GROUP France
+ *
+ * Author: Herve Codina <herve.codina@bootlin.com>
+ */
+
+#ifndef __DRIVERS_PROVIDER_FRAMER_H
+#define __DRIVERS_PROVIDER_FRAMER_H
+
+#include <linux/export.h>
+#include <linux/framer/framer.h>
+#include <linux/types.h>
+
+#define FRAMER_FLAG_POLL_STATUS  BIT(0)
+
+/**
+ * struct framer_ops - set of function pointers for performing framer operations
+ * @init: operation to be performed for initializing the framer
+ * @exit: operation to be performed while exiting
+ * @power_on: powering on the framer
+ * @power_off: powering off the framer
+ * @flags: OR-ed flags (FRAMER_FLAG_*) to ask for core functionality
+ *          - @FRAMER_FLAG_POLL_STATUS:
+ *            Ask the core to perform a polling to get the framer status and
+ *            notify consumers on change.
+ *            The framer should call @framer_notify_status_change() when it
+ *            detects a status change. This is usually done using interrupts.
+ *            If the framer cannot detect this change, it can ask the core for
+ *            a status polling. The core will call @get_status() periodically
+ *            and, on change detected, it will notify the consumer.
+ *            the @get_status()
+ * @owner: the module owner containing the ops
+ */
+struct framer_ops {
+	int	(*init)(struct framer *framer);
+	void	(*exit)(struct framer *framer);
+	int	(*power_on)(struct framer *framer);
+	int	(*power_off)(struct framer *framer);
+
+	/**
+	 * @get_status:
+	 *
+	 * Optional.
+	 *
+	 * Used to get the framer status. framer_init() must have
+	 * been called on the framer.
+	 *
+	 * Returns: 0 if successful, an negative error code otherwise
+	 */
+	int	(*get_status)(struct framer *framer, struct framer_status *status);
+
+	/**
+	 * @set_config:
+	 *
+	 * Optional.
+	 *
+	 * Used to set the framer configuration. framer_init() must have
+	 * been called on the framer.
+	 *
+	 * Returns: 0 if successful, an negative error code otherwise
+	 */
+	int	(*set_config)(struct framer *framer, const struct framer_config *config);
+
+	/**
+	 * @get_config:
+	 *
+	 * Optional.
+	 *
+	 * Used to get the framer configuration. framer_init() must have
+	 * been called on the framer.
+	 *
+	 * Returns: 0 if successful, an negative error code otherwise
+	 */
+	int	(*get_config)(struct framer *framer, struct framer_config *config);
+
+	u32 flags;
+	struct module *owner;
+};
+
+/**
+ * struct framer_provider - represents the framer provider
+ * @dev: framer provider device
+ * @children: can be used to override the default (dev->of_node) child node
+ * @owner: the module owner having of_xlate
+ * @list: to maintain a linked list of framer providers
+ * @of_xlate: function pointer to obtain framer instance from framer pointer
+ */
+struct framer_provider {
+	struct device		*dev;
+	struct module		*owner;
+	struct list_head	list;
+	struct framer * (*of_xlate)(struct device *dev,
+				    struct of_phandle_args *args);
+};
+
+static inline void framer_set_drvdata(struct framer *framer, void *data)
+{
+	dev_set_drvdata(&framer->dev, data);
+}
+
+static inline void *framer_get_drvdata(struct framer *framer)
+{
+	return dev_get_drvdata(&framer->dev);
+}
+
+#if IS_ENABLED(CONFIG_GENERIC_FRAMER)
+
+/* Create and destroy a framer */
+struct framer *framer_create(struct device *dev, struct device_node *node,
+			     const struct framer_ops *ops);
+void framer_destroy(struct framer *framer);
+
+/* devm version */
+struct framer *devm_framer_create(struct device *dev, struct device_node *node,
+				  const struct framer_ops *ops);
+
+struct framer *framer_provider_simple_of_xlate(struct device *dev,
+					       struct of_phandle_args *args);
+
+struct framer_provider *
+__framer_provider_of_register(struct device *dev, struct module *owner,
+			      struct framer *(*of_xlate)(struct device *dev,
+							 struct of_phandle_args *args));
+
+void framer_provider_of_unregister(struct framer_provider *framer_provider);
+
+struct framer_provider *
+__devm_framer_provider_of_register(struct device *dev, struct module *owner,
+				   struct framer *(*of_xlate)(struct device *dev,
+							      struct of_phandle_args *args));
+
+void framer_notify_status_change(struct framer *framer);
+
+#else /* IS_ENABLED(CONFIG_GENERIC_FRAMER) */
+
+static inline struct framer *framer_create(struct device *dev, struct device_node *node,
+					   const struct framer_ops *ops)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline void framer_destroy(struct framer *framer)
+{
+}
+
+/* devm version */
+static inline struct framer *devm_framer_create(struct device *dev, struct device_node *node,
+						const struct framer_ops *ops)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline struct framer *framer_provider_simple_of_xlate(struct device *dev,
+							     struct of_phandle_args *args)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline struct framer_provider *
+__framer_provider_of_register(struct device *dev, struct module *owner,
+			      struct framer *(*of_xlate)(struct device *dev,
+							 struct of_phandle_args *args))
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+void framer_provider_of_unregister(struct framer_provider *framer_provider)
+{
+}
+
+static inline struct framer_provider *
+__devm_framer_provider_of_register(struct device *dev, struct module *owner,
+				   struct framer *(*of_xlate)(struct device *dev,
+							      struct of_phandle_args *args))
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+void framer_notify_status_change(struct framer *framer)
+{
+}
+
+#endif /* IS_ENABLED(CONFIG_GENERIC_FRAMER) */
+
+#define framer_provider_of_register(dev, xlate)		\
+	__framer_provider_of_register((dev), THIS_MODULE, (xlate))
+
+#define devm_framer_provider_of_register(dev, xlate)	\
+	__devm_framer_provider_of_register((dev), THIS_MODULE, (xlate))
+
+#endif /* __DRIVERS_PROVIDER_FRAMER_H */
diff --git a/include/linux/framer/framer.h b/include/linux/framer/framer.h
new file mode 100644
index 000000000000..9a9b88962c29
--- /dev/null
+++ b/include/linux/framer/framer.h
@@ -0,0 +1,205 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Generic framer header file
+ *
+ * Copyright 2023 CS GROUP France
+ *
+ * Author: Herve Codina <herve.codina@bootlin.com>
+ */
+
+#ifndef __DRIVERS_FRAMER_H
+#define __DRIVERS_FRAMER_H
+
+#include <linux/err.h>
+#include <linux/mutex.h>
+#include <linux/notifier.h>
+#include <linux/of.h>
+#include <linux/device.h>
+#include <linux/workqueue.h>
+
+/**
+ * enum framer_iface - Framer interface
+ * @FRAMER_IFACE_E1: E1 interface
+ * @FRAMER_IFACE_T1: T1 interface
+ */
+enum framer_iface {
+	FRAMER_IFACE_E1,
+	FRAMER_IFACE_T1,
+};
+
+/**
+ * enum framer_clock_type - Framer clock type
+ * @FRAMER_CLOCK_EXT: External clock
+ * @FRAMER_CLOCK_INT: Internal clock
+ */
+enum framer_clock_type {
+	FRAMER_CLOCK_EXT,
+	FRAMER_CLOCK_INT,
+};
+
+/**
+ * struct framer_config - Framer configuration
+ * @iface: Framer line interface
+ * @clock_type: Framer clock type
+ * @line_clock_rate: Framer line clock rate
+ */
+struct framer_config {
+	enum framer_iface iface;
+	enum framer_clock_type clock_type;
+	unsigned long line_clock_rate;
+};
+
+/**
+ * struct framer_status - Framer status
+ * @link_is_on: Framer link state. true, the link is on, false, the link is off.
+ */
+struct framer_status {
+	bool link_is_on;
+};
+
+/**
+ * enum framer_event - Event available for notification
+ * @FRAMER_EVENT_STATUS: Event notified on framer_status changes
+ */
+enum framer_event {
+	FRAMER_EVENT_STATUS,
+};
+
+/**
+ * struct framer - represents the framer device
+ * @dev: framer device
+ * @id: id of the framer device
+ * @ops: function pointers for performing framer operations
+ * @mutex: mutex to protect framer_ops
+ * @init_count: used to protect when the framer is used by multiple consumers
+ * @power_count: used to protect when the framer is used by multiple consumers
+ * @pwr: power regulator associated with the framer
+ * @notify_status_work: work structure used for status notifications
+ * @notifier_list: notifier list used for notifications
+ * @polling_work: delayed work structure used for the polling task
+ * @prev_status: previous read status used by the polling task to detect changes
+ */
+struct framer {
+	struct device			dev;
+	int				id;
+	const struct framer_ops		*ops;
+	struct mutex			mutex;	/* Protect framer */
+	int				init_count;
+	int				power_count;
+	struct regulator		*pwr;
+	struct work_struct		notify_status_work;
+	struct blocking_notifier_head	notifier_list;
+	struct delayed_work		polling_work;
+	struct framer_status		prev_status;
+};
+
+#if IS_ENABLED(CONFIG_GENERIC_FRAMER)
+int framer_pm_runtime_get(struct framer *framer);
+int framer_pm_runtime_get_sync(struct framer *framer);
+int framer_pm_runtime_put(struct framer *framer);
+int framer_pm_runtime_put_sync(struct framer *framer);
+int framer_init(struct framer *framer);
+int framer_exit(struct framer *framer);
+int framer_power_on(struct framer *framer);
+int framer_power_off(struct framer *framer);
+int framer_get_status(struct framer *framer, struct framer_status *status);
+int framer_get_config(struct framer *framer, struct framer_config *config);
+int framer_set_config(struct framer *framer, const struct framer_config *config);
+int framer_notifier_register(struct framer *framer, struct notifier_block *nb);
+int framer_notifier_unregister(struct framer *framer, struct notifier_block *nb);
+
+struct framer *framer_get(struct device *dev, const char *con_id);
+void framer_put(struct device *dev, struct framer *framer);
+
+struct framer *devm_framer_get(struct device *dev, const char *con_id);
+struct framer *devm_framer_optional_get(struct device *dev, const char *con_id);
+#else
+static inline int framer_pm_runtime_get(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_pm_runtime_get_sync(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_pm_runtime_put(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_pm_runtime_put_sync(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_init(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_exit(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_power_on(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_power_off(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_get_status(struct framer *framer, struct framer_status *status)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_get_config(struct framer *framer, struct framer_config *config)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_set_config(struct framer *framer, const struct framer_config *config)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_notifier_register(struct framer *framer,
+					   struct notifier_block *nb)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_notifier_unregister(struct framer *framer,
+					     struct notifier_block *nb)
+{
+	return -ENOSYS;
+}
+
+struct framer *framer_get(struct device *dev, const char *con_id)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+void framer_put(struct device *dev, struct framer *framer)
+{
+}
+
+static inline struct framer *devm_framer_get(struct device *dev, const char *con_id)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline struct framer *devm_framer_optional_get(struct device *dev, const char *con_id)
+{
+	return NULL;
+}
+
+#endif
+
+#endif /* __DRIVERS_FRAMER_H */
diff --git a/include/linux/framer/pef2256.h b/include/linux/framer/pef2256.h
new file mode 100644
index 000000000000..71d80af58c40
--- /dev/null
+++ b/include/linux/framer/pef2256.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * PEF2256 consumer API
+ *
+ * Copyright 2023 CS GROUP France
+ *
+ * Author: Herve Codina <herve.codina@bootlin.com>
+ */
+#ifndef __PEF2256_H__
+#define __PEF2256_H__
+
+#include <linux/types.h>
+
+struct pef2256;
+struct regmap;
+
+/* Retrieve the PEF2256 regmap */
+struct regmap *pef2256_get_regmap(struct pef2256 *pef2256);
+
+/* PEF2256 hardware versions */
+enum pef2256_version {
+	PEF2256_VERSION_UNKNOWN,
+	PEF2256_VERSION_1_2,
+	PEF2256_VERSION_2_1,
+	PEF2256_VERSION_2_2,
+};
+
+/* Get the PEF2256 hardware version */
+enum pef2256_version pef2256_get_version(struct pef2256 *pef2256);
+
+#endif /* __PEF2256_H__ */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 98b7a7a8c42e..e6ba0cc6f2ee 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -434,7 +434,7 @@ struct address_space_operations {
 	bool (*is_partially_uptodate) (struct folio *, size_t from,
 			size_t count);
 	void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb);
-	int (*error_remove_page)(struct address_space *, struct page *);
+	int (*error_remove_folio)(struct address_space *, struct folio *);
 
 	/* swapfile support */
 	int (*swap_activate)(struct swap_info_struct *sis, struct file *file,
@@ -463,9 +463,9 @@ extern const struct address_space_operations empty_aops;
  * @a_ops: Methods.
  * @flags: Error bits and flags (AS_*).
  * @wb_err: The most recent error which has occurred.
- * @private_lock: For use by the owner of the address_space.
- * @private_list: For use by the owner of the address_space.
- * @private_data: For use by the owner of the address_space.
+ * @i_private_lock: For use by the owner of the address_space.
+ * @i_private_list: For use by the owner of the address_space.
+ * @i_private_data: For use by the owner of the address_space.
  */
 struct address_space {
 	struct inode		*host;
@@ -484,9 +484,9 @@ struct address_space {
 	unsigned long		flags;
 	struct rw_semaphore	i_mmap_rwsem;
 	errseq_t		wb_err;
-	spinlock_t		private_lock;
-	struct list_head	private_list;
-	void			*private_data;
+	spinlock_t		i_private_lock;
+	struct list_head	i_private_list;
+	void *			i_private_data;
 } __attribute__((aligned(sizeof(long)))) __randomize_layout;
 	/*
 	 * On most architectures that alignment is already the case; but
@@ -991,8 +991,10 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
  */
 struct file {
 	union {
+		/* fput() uses task work when closing and freeing file (default). */
+		struct callback_head 	f_task_work;
+		/* fput() must use workqueue (most kernel threads). */
 		struct llist_node	f_llist;
-		struct rcu_head 	f_rcuhead;
 		unsigned int 		f_iocb_flags;
 	};
 
@@ -1164,6 +1166,7 @@ extern int send_sigurg(struct fown_struct *fown);
 #define SB_I_USERNS_VISIBLE		0x00000010 /* fstype already mounted */
 #define SB_I_IMA_UNVERIFIABLE_SIGNATURE	0x00000020
 #define SB_I_UNTRUSTED_MOUNTER		0x00000040
+#define SB_I_EVM_UNSUPPORTED		0x00000080
 
 #define SB_I_SKIP_SYNC	0x00000100	/* Skip superblock at global sync */
 #define SB_I_PERSB_BDI	0x00000200	/* has a per-sb bdi */
@@ -1185,7 +1188,8 @@ enum {
 
 struct sb_writers {
 	unsigned short			frozen;		/* Is sb frozen? */
-	unsigned short			freeze_holders;	/* Who froze fs? */
+	int				freeze_kcount;	/* How many kernel freeze requests? */
+	int				freeze_ucount;	/* How many userspace freeze requests? */
 	struct percpu_rw_semaphore	rw_sem[SB_FREEZE_LEVELS];
 };
 
@@ -1645,9 +1649,70 @@ static inline bool __sb_start_write_trylock(struct super_block *sb, int level)
 #define __sb_writers_release(sb, lev)	\
 	percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
 
+/**
+ * __sb_write_started - check if sb freeze level is held
+ * @sb: the super we write to
+ * @level: the freeze level
+ *
+ * * > 0 - sb freeze level is held
+ * *   0 - sb freeze level is not held
+ * * < 0 - !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN
+ */
+static inline int __sb_write_started(const struct super_block *sb, int level)
+{
+	return lockdep_is_held_type(sb->s_writers.rw_sem + level - 1, 1);
+}
+
+/**
+ * sb_write_started - check if SB_FREEZE_WRITE is held
+ * @sb: the super we write to
+ *
+ * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
+ */
 static inline bool sb_write_started(const struct super_block *sb)
 {
-	return lockdep_is_held_type(sb->s_writers.rw_sem + SB_FREEZE_WRITE - 1, 1);
+	return __sb_write_started(sb, SB_FREEZE_WRITE);
+}
+
+/**
+ * sb_write_not_started - check if SB_FREEZE_WRITE is not held
+ * @sb: the super we write to
+ *
+ * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
+ */
+static inline bool sb_write_not_started(const struct super_block *sb)
+{
+	return __sb_write_started(sb, SB_FREEZE_WRITE) <= 0;
+}
+
+/**
+ * file_write_started - check if SB_FREEZE_WRITE is held
+ * @file: the file we write to
+ *
+ * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
+ * May be false positive with !S_ISREG, because file_start_write() has
+ * no effect on !S_ISREG.
+ */
+static inline bool file_write_started(const struct file *file)
+{
+	if (!S_ISREG(file_inode(file)->i_mode))
+		return true;
+	return sb_write_started(file_inode(file)->i_sb);
+}
+
+/**
+ * file_write_not_started - check if SB_FREEZE_WRITE is not held
+ * @file: the file we write to
+ *
+ * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
+ * May be false positive with !S_ISREG, because file_start_write() has
+ * no effect on !S_ISREG.
+ */
+static inline bool file_write_not_started(const struct file *file)
+{
+	if (!S_ISREG(file_inode(file)->i_mode))
+		return true;
+	return sb_write_not_started(file_inode(file)->i_sb);
 }
 
 /**
@@ -2029,9 +2094,6 @@ extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
 				   loff_t, size_t, unsigned int);
-extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,
-				       struct file *file_out, loff_t pos_out,
-				       size_t len, unsigned int flags);
 int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 				    struct file *file_out, loff_t pos_out,
 				    loff_t *len, unsigned int remap_flags,
@@ -2051,9 +2113,24 @@ extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
 					struct file *dst_file, loff_t dst_pos,
 					loff_t len, unsigned int remap_flags);
 
+/**
+ * enum freeze_holder - holder of the freeze
+ * @FREEZE_HOLDER_KERNEL: kernel wants to freeze or thaw filesystem
+ * @FREEZE_HOLDER_USERSPACE: userspace wants to freeze or thaw filesystem
+ * @FREEZE_MAY_NEST: whether nesting freeze and thaw requests is allowed
+ *
+ * Indicate who the owner of the freeze or thaw request is and whether
+ * the freeze needs to be exclusive or can nest.
+ * Without @FREEZE_MAY_NEST, multiple freeze and thaw requests from the
+ * same holder aren't allowed. It is however allowed to hold a single
+ * @FREEZE_HOLDER_USERSPACE and a single @FREEZE_HOLDER_KERNEL freeze at
+ * the same time. This is relied upon by some filesystems during online
+ * repair or similar.
+ */
 enum freeze_holder {
 	FREEZE_HOLDER_KERNEL	= (1U << 0),
 	FREEZE_HOLDER_USERSPACE	= (1U << 1),
+	FREEZE_MAY_NEST		= (1U << 2),
 };
 
 struct super_operations {
@@ -2517,26 +2594,31 @@ struct file *dentry_open(const struct path *path, int flags,
 			 const struct cred *creds);
 struct file *dentry_create(const struct path *path, int flags, umode_t mode,
 			   const struct cred *cred);
-struct file *backing_file_open(const struct path *user_path, int flags,
-			       const struct path *real_path,
-			       const struct cred *cred);
 struct path *backing_file_user_path(struct file *f);
 
 /*
- * file_user_path - get the path to display for memory mapped file
- *
  * When mmapping a file on a stackable filesystem (e.g., overlayfs), the file
  * stored in ->vm_file is a backing file whose f_inode is on the underlying
- * filesystem.  When the mapped file path is displayed to user (e.g. via
- * /proc/<pid>/maps), this helper should be used to get the path to display
- * to the user, which is the path of the fd that user has requested to map.
+ * filesystem.  When the mapped file path and inode number are displayed to
+ * user (e.g. via /proc/<pid>/maps), these helpers should be used to get the
+ * path and inode number to display to the user, which is the path of the fd
+ * that user has requested to map and the inode number that would be returned
+ * by fstat() on that same fd.
  */
+/* Get the path to display in /proc/<pid>/maps */
 static inline const struct path *file_user_path(struct file *f)
 {
 	if (unlikely(f->f_mode & FMODE_BACKING))
 		return backing_file_user_path(f);
 	return &f->f_path;
 }
+/* Get the inode whose inode number to display in /proc/<pid>/maps */
+static inline const struct inode *file_user_inode(struct file *f)
+{
+	if (unlikely(f->f_mode & FMODE_BACKING))
+		return d_inode(backing_file_user_path(f)->dentry);
+	return file_inode(f);
+}
 
 static inline struct file *file_clone_open(struct file *file)
 {
@@ -2991,8 +3073,6 @@ ssize_t copy_splice_read(struct file *in, loff_t *ppos,
 			 size_t len, unsigned int flags);
 extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
 		struct file *, loff_t *, size_t, unsigned int);
-extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
-		loff_t *opos, size_t len, unsigned int flags);
 
 
 extern void
@@ -3121,7 +3201,6 @@ extern int vfs_readlink(struct dentry *, char __user *, int);
 extern struct file_system_type *get_filesystem(struct file_system_type *fs);
 extern void put_filesystem(struct file_system_type *fs);
 extern struct file_system_type *get_fs_type(const char *name);
-extern struct super_block *get_active_super(struct block_device *bdev);
 extern void drop_super(struct super_block *sb);
 extern void drop_super_exclusive(struct super_block *sb);
 extern void iterate_supers(void (*)(struct super_block *, void *), void *);
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index bcb6609b54b3..11e6434b8e71 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -100,29 +100,49 @@ static inline int fsnotify_file(struct file *file, __u32 mask)
 	return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH);
 }
 
-/* Simple call site for access decisions */
-static inline int fsnotify_perm(struct file *file, int mask)
+/*
+ * fsnotify_file_area_perm - permission hook before access to file range
+ */
+static inline int fsnotify_file_area_perm(struct file *file, int perm_mask,
+					  const loff_t *ppos, size_t count)
 {
-	int ret;
-	__u32 fsnotify_mask = 0;
+	__u32 fsnotify_mask = FS_ACCESS_PERM;
+
+	/*
+	 * filesystem may be modified in the context of permission events
+	 * (e.g. by HSM filling a file on access), so sb freeze protection
+	 * must not be held.
+	 */
+	lockdep_assert_once(file_write_not_started(file));
 
-	if (!(mask & (MAY_READ | MAY_OPEN)))
+	if (!(perm_mask & MAY_READ))
 		return 0;
 
-	if (mask & MAY_OPEN) {
-		fsnotify_mask = FS_OPEN_PERM;
+	return fsnotify_file(file, fsnotify_mask);
+}
+
+/*
+ * fsnotify_file_perm - permission hook before file access
+ */
+static inline int fsnotify_file_perm(struct file *file, int perm_mask)
+{
+	return fsnotify_file_area_perm(file, perm_mask, NULL, 0);
+}
 
-		if (file->f_flags & __FMODE_EXEC) {
-			ret = fsnotify_file(file, FS_OPEN_EXEC_PERM);
+/*
+ * fsnotify_open_perm - permission hook before file open
+ */
+static inline int fsnotify_open_perm(struct file *file)
+{
+	int ret;
 
-			if (ret)
-				return ret;
-		}
-	} else if (mask & MAY_READ) {
-		fsnotify_mask = FS_ACCESS_PERM;
+	if (file->f_flags & __FMODE_EXEC) {
+		ret = fsnotify_file(file, FS_OPEN_EXEC_PERM);
+		if (ret)
+			return ret;
 	}
 
-	return fsnotify_file(file, fsnotify_mask);
+	return fsnotify_file(file, FS_OPEN_PERM);
 }
 
 /*
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index c0892d75ce33..7f63be5ca0f1 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -472,10 +472,8 @@ typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t;
 struct fsnotify_mark_connector {
 	spinlock_t lock;
 	unsigned short type;	/* Type of object [lock] */
-#define FSNOTIFY_CONN_FLAG_HAS_FSID	0x01
 #define FSNOTIFY_CONN_FLAG_HAS_IREF	0x02
 	unsigned short flags;	/* flags [lock] */
-	__kernel_fsid_t fsid;	/* fsid of filesystem containing object */
 	union {
 		/* Object pointer [lock] */
 		fsnotify_connp_t *obj;
@@ -530,6 +528,8 @@ struct fsnotify_mark {
 #define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY	0x0100
 #define FSNOTIFY_MARK_FLAG_NO_IREF		0x0200
 #define FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS	0x0400
+#define FSNOTIFY_MARK_FLAG_HAS_FSID		0x0800
+#define FSNOTIFY_MARK_FLAG_WEAK_FSID		0x1000
 	unsigned int flags;		/* flags [mark->lock] */
 };
 
@@ -763,11 +763,10 @@ extern struct fsnotify_mark *fsnotify_find_mark(fsnotify_connp_t *connp,
 /* attach the mark to the object */
 extern int fsnotify_add_mark(struct fsnotify_mark *mark,
 			     fsnotify_connp_t *connp, unsigned int obj_type,
-			     int add_flags, __kernel_fsid_t *fsid);
+			     int add_flags);
 extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
 				    fsnotify_connp_t *connp,
-				    unsigned int obj_type, int add_flags,
-				    __kernel_fsid_t *fsid);
+				    unsigned int obj_type, int add_flags);
 
 /* attach the mark to the inode */
 static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
@@ -775,15 +774,14 @@ static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 					  int add_flags)
 {
 	return fsnotify_add_mark(mark, &inode->i_fsnotify_marks,
-				 FSNOTIFY_OBJ_TYPE_INODE, add_flags, NULL);
+				 FSNOTIFY_OBJ_TYPE_INODE, add_flags);
 }
 static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark,
 						 struct inode *inode,
 						 int add_flags)
 {
 	return fsnotify_add_mark_locked(mark, &inode->i_fsnotify_marks,
-					FSNOTIFY_OBJ_TYPE_INODE, add_flags,
-					NULL);
+					FSNOTIFY_OBJ_TYPE_INODE, add_flags);
 }
 
 /* given a group and a mark, flag mark to be freed when all references are dropped */
diff --git a/include/linux/fw_table.h b/include/linux/fw_table.h
index ff8fa58d5818..ca49947f0a77 100644
--- a/include/linux/fw_table.h
+++ b/include/linux/fw_table.h
@@ -25,9 +25,6 @@ struct acpi_subtable_proc {
 	int count;
 };
 
-#include <linux/acpi.h>
-#include <acpi/acpi.h>
-
 union acpi_subtable_headers {
 	struct acpi_subtable_header common;
 	struct acpi_hmat_structure hmat;
diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h
index 6583a58670c5..1b6053da8754 100644
--- a/include/linux/gfp_types.h
+++ b/include/linux/gfp_types.h
@@ -162,25 +162,25 @@ typedef unsigned int __bitwise gfp_t;
  * %__GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim.
  *
  * The default allocator behavior depends on the request size. We have a concept
- * of so called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER).
+ * of so-called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER).
  * !costly allocations are too essential to fail so they are implicitly
  * non-failing by default (with some exceptions like OOM victims might fail so
  * the caller still has to check for failures) while costly requests try to be
  * not disruptive and back off even without invoking the OOM killer.
  * The following three modifiers might be used to override some of these
- * implicit rules
+ * implicit rules.
  *
  * %__GFP_NORETRY: The VM implementation will try only very lightweight
  * memory direct reclaim to get some memory under memory pressure (thus
  * it can sleep). It will avoid disruptive actions like OOM killer. The
  * caller must handle the failure which is quite likely to happen under
  * heavy memory pressure. The flag is suitable when failure can easily be
- * handled at small cost, such as reduced throughput
+ * handled at small cost, such as reduced throughput.
  *
  * %__GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim
  * procedures that have previously failed if there is some indication
- * that progress has been made else where.  It can wait for other
- * tasks to attempt high level approaches to freeing memory such as
+ * that progress has been made elsewhere.  It can wait for other
+ * tasks to attempt high-level approaches to freeing memory such as
  * compaction (which removes fragmentation) and page-out.
  * There is still a definite limit to the number of retries, but it is
  * a larger limit than with %__GFP_NORETRY.
@@ -230,7 +230,7 @@ typedef unsigned int __bitwise gfp_t;
  * is being zeroed (either via __GFP_ZERO or via init_on_alloc, provided that
  * __GFP_SKIP_ZERO is not set). This flag is intended for optimization: setting
  * memory tags at the same time as zeroing memory has minimal additional
- * performace impact.
+ * performance impact.
  *
  * %__GFP_SKIP_KASAN makes KASAN skip unpoisoning on page allocation.
  * Used for userspace and vmalloc pages; the latter are unpoisoned by
@@ -274,7 +274,8 @@ typedef unsigned int __bitwise gfp_t;
  * accounted to kmemcg.
  *
  * %GFP_NOWAIT is for kernel allocations that should not stall for direct
- * reclaim, start physical IO or use any filesystem callback.
+ * reclaim, start physical IO or use any filesystem callback.  It is very
+ * likely to fail to allocate memory, even for very small allocations.
  *
  * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages
  * that do not require the starting of any physical IO.
@@ -325,7 +326,7 @@ typedef unsigned int __bitwise gfp_t;
 #define GFP_ATOMIC	(__GFP_HIGH|__GFP_KSWAPD_RECLAIM)
 #define GFP_KERNEL	(__GFP_RECLAIM | __GFP_IO | __GFP_FS)
 #define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT)
-#define GFP_NOWAIT	(__GFP_KSWAPD_RECLAIM)
+#define GFP_NOWAIT	(__GFP_KSWAPD_RECLAIM | __GFP_NOWARN)
 #define GFP_NOIO	(__GFP_RECLAIM)
 #define GFP_NOFS	(__GFP_RECLAIM | __GFP_IO)
 #define GFP_USER	(__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
diff --git a/include/linux/hid-sensor-ids.h b/include/linux/hid-sensor-ids.h
index 6730ee900ee1..13b1e65fbdcc 100644
--- a/include/linux/hid-sensor-ids.h
+++ b/include/linux/hid-sensor-ids.h
@@ -21,10 +21,6 @@
 #define HID_USAGE_SENSOR_ALS					0x200041
 #define HID_USAGE_SENSOR_DATA_LIGHT				0x2004d0
 #define HID_USAGE_SENSOR_LIGHT_ILLUM				0x2004d1
-#define HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE		0x2004d2
-#define HID_USAGE_SENSOR_LIGHT_CHROMATICITY			0x2004d3
-#define HID_USAGE_SENSOR_LIGHT_CHROMATICITY_X			0x2004d4
-#define HID_USAGE_SENSOR_LIGHT_CHROMATICITY_Y			0x2004d5
 
 /* PROX (200011) */
 #define HID_USAGE_SENSOR_PROX                                   0x200011
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 5a8387a4a712..bf43f3ff6664 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -679,6 +679,7 @@ struct hid_device {							/* device report descriptor */
 	struct list_head debug_list;
 	spinlock_t  debug_list_lock;
 	wait_queue_head_t debug_wait;
+	struct kref			ref;
 
 	unsigned int id;						/* system unique id */
 
@@ -687,6 +688,8 @@ struct hid_device {							/* device report descriptor */
 #endif /* CONFIG_BPF */
 };
 
+void hiddev_free(struct kref *ref);
+
 #define to_hid_device(pdev) \
 	container_of(pdev, struct hid_device, dev)
 
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 4cacc0e43b51..451c1dff0e87 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -454,7 +454,7 @@ static inline void memcpy_from_folio(char *to, struct folio *folio,
 		memcpy(to, from, chunk);
 		kunmap_local(from);
 
-		from += chunk;
+		to += chunk;
 		offset += chunk;
 		len -= chunk;
 	} while (len > 0);
@@ -484,6 +484,82 @@ static inline void memcpy_to_folio(struct folio *folio, size_t offset,
 }
 
 /**
+ * folio_zero_tail - Zero the tail of a folio.
+ * @folio: The folio to zero.
+ * @offset: The byte offset in the folio to start zeroing at.
+ * @kaddr: The address the folio is currently mapped to.
+ *
+ * If you have already used kmap_local_folio() to map a folio, written
+ * some data to it and now need to zero the end of the folio (and flush
+ * the dcache), you can use this function.  If you do not have the
+ * folio kmapped (eg the folio has been partially populated by DMA),
+ * use folio_zero_range() or folio_zero_segment() instead.
+ *
+ * Return: An address which can be passed to kunmap_local().
+ */
+static inline __must_check void *folio_zero_tail(struct folio *folio,
+		size_t offset, void *kaddr)
+{
+	size_t len = folio_size(folio) - offset;
+
+	if (folio_test_highmem(folio)) {
+		size_t max = PAGE_SIZE - offset_in_page(offset);
+
+		while (len > max) {
+			memset(kaddr, 0, max);
+			kunmap_local(kaddr);
+			len -= max;
+			offset += max;
+			max = PAGE_SIZE;
+			kaddr = kmap_local_folio(folio, offset);
+		}
+	}
+
+	memset(kaddr, 0, len);
+	flush_dcache_folio(folio);
+
+	return kaddr;
+}
+
+/**
+ * folio_fill_tail - Copy some data to a folio and pad with zeroes.
+ * @folio: The destination folio.
+ * @offset: The offset into @folio at which to start copying.
+ * @from: The data to copy.
+ * @len: How many bytes of data to copy.
+ *
+ * This function is most useful for filesystems which support inline data.
+ * When they want to copy data from the inode into the page cache, this
+ * function does everything for them.  It supports large folios even on
+ * HIGHMEM configurations.
+ */
+static inline void folio_fill_tail(struct folio *folio, size_t offset,
+		const char *from, size_t len)
+{
+	char *to = kmap_local_folio(folio, offset);
+
+	VM_BUG_ON(offset + len > folio_size(folio));
+
+	if (folio_test_highmem(folio)) {
+		size_t max = PAGE_SIZE - offset_in_page(offset);
+
+		while (len > max) {
+			memcpy(to, from, max);
+			kunmap_local(to);
+			len -= max;
+			from += max;
+			offset += max;
+			max = PAGE_SIZE;
+			to = kmap_local_folio(folio, offset);
+		}
+	}
+
+	memcpy(to, from, len);
+	to = folio_zero_tail(folio, offset + len, to + len);
+	kunmap_local(to);
+}
+
+/**
  * memcpy_from_file_folio - Copy some bytes from a file folio.
  * @to: The destination buffer.
  * @folio: The folio to copy from.
diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h
index ddc7ebb70523..5f4c74facf6a 100644
--- a/include/linux/hisi_acc_qm.h
+++ b/include/linux/hisi_acc_qm.h
@@ -108,17 +108,13 @@ enum qm_stop_reason {
 };
 
 enum qm_state {
-	QM_INIT = 0,
-	QM_START,
-	QM_CLOSE,
+	QM_WORK = 0,
 	QM_STOP,
 };
 
 enum qp_state {
-	QP_INIT = 1,
-	QP_START,
+	QP_START = 1,
 	QP_STOP,
-	QP_CLOSE,
 };
 
 enum qm_hw_ver {
@@ -160,6 +156,11 @@ enum qm_cap_bits {
 	QM_SUPPORT_RPM,
 };
 
+struct qm_dev_alg {
+	u64 alg_msk;
+	const char *alg;
+};
+
 struct dfx_diff_registers {
 	u32 *regs;
 	u32 reg_offset;
@@ -265,6 +266,16 @@ struct hisi_qm_cap_info {
 	u32 v3_val;
 };
 
+struct hisi_qm_cap_record {
+	u32 type;
+	u32 cap_val;
+};
+
+struct hisi_qm_cap_tables {
+	struct hisi_qm_cap_record *qm_cap_table;
+	struct hisi_qm_cap_record *dev_cap_table;
+};
+
 struct hisi_qm_list {
 	struct mutex lock;
 	struct list_head list;
@@ -365,7 +376,6 @@ struct hisi_qm {
 	struct work_struct rst_work;
 	struct work_struct cmd_process;
 
-	const char *algs;
 	bool use_sva;
 
 	resource_size_t phys_base;
@@ -376,6 +386,8 @@ struct hisi_qm {
 	u32 mb_qos;
 	u32 type_rate;
 	struct qm_err_isolate isolate_data;
+
+	struct hisi_qm_cap_tables cap_tables;
 };
 
 struct hisi_qp_status {
@@ -563,6 +575,8 @@ void hisi_qm_regs_dump(struct seq_file *s, struct debugfs_regset32 *regset);
 u32 hisi_qm_get_hw_info(struct hisi_qm *qm,
 			const struct hisi_qm_cap_info *info_table,
 			u32 index, bool is_read);
+int hisi_qm_set_algs(struct hisi_qm *qm, u64 alg_msk, const struct qm_dev_alg *dev_algs,
+		     u32 dev_algs_size);
 
 /* Used by VFIO ACC live migration driver */
 struct pci_driver *hisi_sec_get_pf_driver(void);
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 0ee140176f10..87e3bedf8eb0 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -13,13 +13,13 @@
 #define _LINUX_HRTIMER_H
 
 #include <linux/hrtimer_defs.h>
-#include <linux/rbtree.h>
+#include <linux/hrtimer_types.h>
 #include <linux/init.h>
 #include <linux/list.h>
-#include <linux/percpu.h>
+#include <linux/percpu-defs.h>
+#include <linux/rbtree.h>
 #include <linux/seqlock.h>
 #include <linux/timer.h>
-#include <linux/timerqueue.h>
 
 struct hrtimer_clock_base;
 struct hrtimer_cpu_base;
@@ -60,14 +60,6 @@ enum hrtimer_mode {
 };
 
 /*
- * Return values for the callback function
- */
-enum hrtimer_restart {
-	HRTIMER_NORESTART,	/* Timer is not restarted */
-	HRTIMER_RESTART,	/* Timer must be restarted */
-};
-
-/*
  * Values to track state of the timer
  *
  * Possible states:
@@ -95,38 +87,6 @@ enum hrtimer_restart {
 #define HRTIMER_STATE_ENQUEUED	0x01
 
 /**
- * struct hrtimer - the basic hrtimer structure
- * @node:	timerqueue node, which also manages node.expires,
- *		the absolute expiry time in the hrtimers internal
- *		representation. The time is related to the clock on
- *		which the timer is based. Is setup by adding
- *		slack to the _softexpires value. For non range timers
- *		identical to _softexpires.
- * @_softexpires: the absolute earliest expiry time of the hrtimer.
- *		The time which was given as expiry time when the timer
- *		was armed.
- * @function:	timer expiry callback function
- * @base:	pointer to the timer base (per cpu and per clock)
- * @state:	state information (See bit values above)
- * @is_rel:	Set if the timer was armed relative
- * @is_soft:	Set if hrtimer will be expired in soft interrupt context.
- * @is_hard:	Set if hrtimer will be expired in hard interrupt context
- *		even on RT.
- *
- * The hrtimer structure must be initialized by hrtimer_init()
- */
-struct hrtimer {
-	struct timerqueue_node		node;
-	ktime_t				_softexpires;
-	enum hrtimer_restart		(*function)(struct hrtimer *);
-	struct hrtimer_clock_base	*base;
-	u8				state;
-	u8				is_rel;
-	u8				is_soft;
-	u8				is_hard;
-};
-
-/**
  * struct hrtimer_sleeper - simple sleeper structure
  * @timer:	embedded timer structure
  * @task:	task to wake up
@@ -531,9 +491,9 @@ extern void sysrq_timer_list_show(void);
 
 int hrtimers_prepare_cpu(unsigned int cpu);
 #ifdef CONFIG_HOTPLUG_CPU
-int hrtimers_dead_cpu(unsigned int cpu);
+int hrtimers_cpu_dying(unsigned int cpu);
 #else
-#define hrtimers_dead_cpu	NULL
+#define hrtimers_cpu_dying	NULL
 #endif
 
 #endif
diff --git a/include/linux/hrtimer_types.h b/include/linux/hrtimer_types.h
new file mode 100644
index 000000000000..ad66a3081735
--- /dev/null
+++ b/include/linux/hrtimer_types.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_HRTIMER_TYPES_H
+#define _LINUX_HRTIMER_TYPES_H
+
+#include <linux/types.h>
+#include <linux/timerqueue_types.h>
+
+struct hrtimer_clock_base;
+
+/*
+ * Return values for the callback function
+ */
+enum hrtimer_restart {
+	HRTIMER_NORESTART,	/* Timer is not restarted */
+	HRTIMER_RESTART,	/* Timer must be restarted */
+};
+
+/**
+ * struct hrtimer - the basic hrtimer structure
+ * @node:	timerqueue node, which also manages node.expires,
+ *		the absolute expiry time in the hrtimers internal
+ *		representation. The time is related to the clock on
+ *		which the timer is based. Is setup by adding
+ *		slack to the _softexpires value. For non range timers
+ *		identical to _softexpires.
+ * @_softexpires: the absolute earliest expiry time of the hrtimer.
+ *		The time which was given as expiry time when the timer
+ *		was armed.
+ * @function:	timer expiry callback function
+ * @base:	pointer to the timer base (per cpu and per clock)
+ * @state:	state information (See bit values above)
+ * @is_rel:	Set if the timer was armed relative
+ * @is_soft:	Set if hrtimer will be expired in soft interrupt context.
+ * @is_hard:	Set if hrtimer will be expired in hard interrupt context
+ *		even on RT.
+ *
+ * The hrtimer structure must be initialized by hrtimer_init()
+ */
+struct hrtimer {
+	struct timerqueue_node		node;
+	ktime_t				_softexpires;
+	enum hrtimer_restart		(*function)(struct hrtimer *);
+	struct hrtimer_clock_base	*base;
+	u8				state;
+	u8				is_rel;
+	u8				is_soft;
+	u8				is_hard;
+};
+
+#endif /* _LINUX_HRTIMER_TYPES_H */
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index fa0350b0812a..5adb86af35fc 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -67,6 +67,26 @@ extern struct kobj_attribute shmem_enabled_attr;
 #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
 #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
 
+/*
+ * Mask of all large folio orders supported for anonymous THP; all orders up to
+ * and including PMD_ORDER, except order-0 (which is not "huge") and order-1
+ * (which is a limitation of the THP implementation).
+ */
+#define THP_ORDERS_ALL_ANON	((BIT(PMD_ORDER + 1) - 1) & ~(BIT(0) | BIT(1)))
+
+/*
+ * Mask of all large folio orders supported for file THP.
+ */
+#define THP_ORDERS_ALL_FILE	(BIT(PMD_ORDER) | BIT(PUD_ORDER))
+
+/*
+ * Mask of all large folio orders supported for THP.
+ */
+#define THP_ORDERS_ALL		(THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE)
+
+#define thp_vma_allowable_order(vma, vm_flags, smaps, in_pf, enforce_sysfs, order) \
+	(!!thp_vma_allowable_orders(vma, vm_flags, smaps, in_pf, enforce_sysfs, BIT(order)))
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define HPAGE_PMD_SHIFT PMD_SHIFT
 #define HPAGE_PMD_SIZE	((1UL) << HPAGE_PMD_SHIFT)
@@ -77,45 +97,105 @@ extern struct kobj_attribute shmem_enabled_attr;
 #define HPAGE_PUD_MASK	(~(HPAGE_PUD_SIZE - 1))
 
 extern unsigned long transparent_hugepage_flags;
+extern unsigned long huge_anon_orders_always;
+extern unsigned long huge_anon_orders_madvise;
+extern unsigned long huge_anon_orders_inherit;
 
-#define hugepage_flags_enabled()					       \
-	(transparent_hugepage_flags &				       \
-	 ((1<<TRANSPARENT_HUGEPAGE_FLAG) |		       \
-	  (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)))
-#define hugepage_flags_always()				\
-	(transparent_hugepage_flags &			\
-	 (1<<TRANSPARENT_HUGEPAGE_FLAG))
+static inline bool hugepage_global_enabled(void)
+{
+	return transparent_hugepage_flags &
+			((1<<TRANSPARENT_HUGEPAGE_FLAG) |
+			(1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG));
+}
+
+static inline bool hugepage_global_always(void)
+{
+	return transparent_hugepage_flags &
+			(1<<TRANSPARENT_HUGEPAGE_FLAG);
+}
+
+static inline bool hugepage_flags_enabled(void)
+{
+	/*
+	 * We cover both the anon and the file-backed case here; we must return
+	 * true if globally enabled, even when all anon sizes are set to never.
+	 * So we don't need to look at huge_anon_orders_inherit.
+	 */
+	return hugepage_global_enabled() ||
+	       huge_anon_orders_always ||
+	       huge_anon_orders_madvise;
+}
+
+static inline int highest_order(unsigned long orders)
+{
+	return fls_long(orders) - 1;
+}
+
+static inline int next_order(unsigned long *orders, int prev)
+{
+	*orders &= ~BIT(prev);
+	return highest_order(*orders);
+}
 
 /*
  * Do the below checks:
  *   - For file vma, check if the linear page offset of vma is
- *     HPAGE_PMD_NR aligned within the file.  The hugepage is
- *     guaranteed to be hugepage-aligned within the file, but we must
- *     check that the PMD-aligned addresses in the VMA map to
- *     PMD-aligned offsets within the file, else the hugepage will
- *     not be PMD-mappable.
- *   - For all vmas, check if the haddr is in an aligned HPAGE_PMD_SIZE
+ *     order-aligned within the file.  The hugepage is
+ *     guaranteed to be order-aligned within the file, but we must
+ *     check that the order-aligned addresses in the VMA map to
+ *     order-aligned offsets within the file, else the hugepage will
+ *     not be mappable.
+ *   - For all vmas, check if the haddr is in an aligned hugepage
  *     area.
  */
-static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
-		unsigned long addr)
+static inline bool thp_vma_suitable_order(struct vm_area_struct *vma,
+		unsigned long addr, int order)
 {
+	unsigned long hpage_size = PAGE_SIZE << order;
 	unsigned long haddr;
 
 	/* Don't have to check pgoff for anonymous vma */
 	if (!vma_is_anonymous(vma)) {
 		if (!IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff,
-				HPAGE_PMD_NR))
+				hpage_size >> PAGE_SHIFT))
 			return false;
 	}
 
-	haddr = addr & HPAGE_PMD_MASK;
+	haddr = ALIGN_DOWN(addr, hpage_size);
 
-	if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end)
+	if (haddr < vma->vm_start || haddr + hpage_size > vma->vm_end)
 		return false;
 	return true;
 }
 
+/*
+ * Filter the bitfield of input orders to the ones suitable for use in the vma.
+ * See thp_vma_suitable_order().
+ * All orders that pass the checks are returned as a bitfield.
+ */
+static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma,
+		unsigned long addr, unsigned long orders)
+{
+	int order;
+
+	/*
+	 * Iterate over orders, highest to lowest, removing orders that don't
+	 * meet alignment requirements from the set. Exit loop at first order
+	 * that meets requirements, since all lower orders must also meet
+	 * requirements.
+	 */
+
+	order = highest_order(orders);
+
+	while (orders) {
+		if (thp_vma_suitable_order(vma, addr, order))
+			break;
+		order = next_order(&orders, order);
+	}
+
+	return orders;
+}
+
 static inline bool file_thp_enabled(struct vm_area_struct *vma)
 {
 	struct inode *inode;
@@ -126,12 +206,55 @@ static inline bool file_thp_enabled(struct vm_area_struct *vma)
 	inode = vma->vm_file->f_inode;
 
 	return (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) &&
-	       (vma->vm_flags & VM_EXEC) &&
 	       !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode);
 }
 
-bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags,
-			bool smaps, bool in_pf, bool enforce_sysfs);
+unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
+					 unsigned long vm_flags, bool smaps,
+					 bool in_pf, bool enforce_sysfs,
+					 unsigned long orders);
+
+/**
+ * thp_vma_allowable_orders - determine hugepage orders that are allowed for vma
+ * @vma:  the vm area to check
+ * @vm_flags: use these vm_flags instead of vma->vm_flags
+ * @smaps: whether answer will be used for smaps file
+ * @in_pf: whether answer will be used by page fault handler
+ * @enforce_sysfs: whether sysfs config should be taken into account
+ * @orders: bitfield of all orders to consider
+ *
+ * Calculates the intersection of the requested hugepage orders and the allowed
+ * hugepage orders for the provided vma. Permitted orders are encoded as a set
+ * bit at the corresponding bit position (bit-2 corresponds to order-2, bit-3
+ * corresponds to order-3, etc). Order-0 is never considered a hugepage order.
+ *
+ * Return: bitfield of orders allowed for hugepage in the vma. 0 if no hugepage
+ * orders are allowed.
+ */
+static inline
+unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma,
+				       unsigned long vm_flags, bool smaps,
+				       bool in_pf, bool enforce_sysfs,
+				       unsigned long orders)
+{
+	/* Optimization to check if required orders are enabled early. */
+	if (enforce_sysfs && vma_is_anonymous(vma)) {
+		unsigned long mask = READ_ONCE(huge_anon_orders_always);
+
+		if (vm_flags & VM_HUGEPAGE)
+			mask |= READ_ONCE(huge_anon_orders_madvise);
+		if (hugepage_global_always() ||
+		    ((vm_flags & VM_HUGEPAGE) && hugepage_global_enabled()))
+			mask |= READ_ONCE(huge_anon_orders_inherit);
+
+		orders &= mask;
+		if (!orders)
+			return 0;
+	}
+
+	return __thp_vma_allowable_orders(vma, vm_flags, smaps, in_pf,
+					  enforce_sysfs, orders);
+}
 
 #define transparent_hugepage_use_zero_page()				\
 	(transparent_hugepage_flags &					\
@@ -267,17 +390,24 @@ static inline bool folio_test_pmd_mappable(struct folio *folio)
 	return false;
 }
 
-static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
-		unsigned long addr)
+static inline bool thp_vma_suitable_order(struct vm_area_struct *vma,
+		unsigned long addr, int order)
 {
 	return false;
 }
 
-static inline bool hugepage_vma_check(struct vm_area_struct *vma,
-				      unsigned long vm_flags, bool smaps,
-				      bool in_pf, bool enforce_sysfs)
+static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma,
+		unsigned long addr, unsigned long orders)
 {
-	return false;
+	return 0;
+}
+
+static inline unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma,
+					unsigned long vm_flags, bool smaps,
+					bool in_pf, bool enforce_sysfs,
+					unsigned long orders)
+{
+	return 0;
 }
 
 static inline void folio_prep_large_rmappable(struct folio *folio) {}
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d3acecc5db4b..c1ee640d87b1 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -829,7 +829,7 @@ static inline unsigned huge_page_shift(struct hstate *h)
 
 static inline bool hstate_is_gigantic(struct hstate *h)
 {
-	return huge_page_order(h) > MAX_ORDER;
+	return huge_page_order(h) > MAX_PAGE_ORDER;
 }
 
 static inline unsigned int pages_per_huge_page(const struct hstate *h)
@@ -1268,10 +1268,7 @@ static inline bool __vma_shareable_lock(struct vm_area_struct *vma)
 	return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data;
 }
 
-static inline bool __vma_private_lock(struct vm_area_struct *vma)
-{
-	return (!(vma->vm_flags & VM_MAYSHARE)) && vma->vm_private_data;
-}
+bool __vma_private_lock(struct vm_area_struct *vma);
 
 /*
  * Safe version of huge_pte_offset() to check the locks.  See comments
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 958771bac9c0..83c4d060a559 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -172,11 +172,11 @@
 #define IEEE80211_SN_MODULO		(IEEE80211_MAX_SN + 1)
 
 
-/* PV1 Layout 11ah 9.8.3.1 */
+/* PV1 Layout IEEE 802.11-2020 9.8.3.1 */
 #define IEEE80211_PV1_FCTL_VERS		0x0003
 #define IEEE80211_PV1_FCTL_FTYPE	0x001c
 #define IEEE80211_PV1_FCTL_STYPE	0x00e0
-#define IEEE80211_PV1_FCTL_TODS		0x0100
+#define IEEE80211_PV1_FCTL_FROMDS		0x0100
 #define IEEE80211_PV1_FCTL_MOREFRAGS	0x0200
 #define IEEE80211_PV1_FCTL_PM		0x0400
 #define IEEE80211_PV1_FCTL_MOREDATA	0x0800
@@ -2720,6 +2720,7 @@ static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len)
 
 #define IEEE80211_6GHZ_CTRL_REG_LPI_AP	0
 #define IEEE80211_6GHZ_CTRL_REG_SP_AP	1
+#define IEEE80211_6GHZ_CTRL_REG_VLP_AP	2
 
 /**
  * struct ieee80211_he_6ghz_oper - HE 6 GHz operation Information field
@@ -2830,12 +2831,14 @@ ieee80211_he_oper_size(const u8 *he_oper_ie)
 static inline const struct ieee80211_he_6ghz_oper *
 ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper)
 {
-	const u8 *ret = (const void *)&he_oper->optional;
+	const u8 *ret;
 	u32 he_oper_params;
 
 	if (!he_oper)
 		return NULL;
 
+	ret = (const void *)&he_oper->optional;
+
 	he_oper_params = le32_to_cpu(he_oper->he_oper_params);
 
 	if (!(he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO))
@@ -4445,7 +4448,8 @@ ieee80211_is_protected_dual_of_public_action(struct sk_buff *skb)
 		action != WLAN_PUB_ACTION_LOC_TRACK_NOTI &&
 		action != WLAN_PUB_ACTION_FTM_REQUEST &&
 		action != WLAN_PUB_ACTION_FTM_RESPONSE &&
-		action != WLAN_PUB_ACTION_FILS_DISCOVERY;
+		action != WLAN_PUB_ACTION_FILS_DISCOVERY &&
+		action != WLAN_PUB_ACTION_VENDOR_SPECIFIC;
 }
 
 /**
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 3028af87716e..c1645c86eed9 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -540,7 +540,7 @@ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci)
 	struct vlan_ethhdr *veth = skb_vlan_eth_hdr(skb);
 
 	if (!eth_type_vlan(veth->h_vlan_proto))
-		return -EINVAL;
+		return -ENODATA;
 
 	*vlan_tci = ntohs(veth->h_vlan_TCI);
 	return 0;
@@ -561,7 +561,7 @@ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb,
 		return 0;
 	} else {
 		*vlan_tci = 0;
-		return -EINVAL;
+		return -ENODATA;
 	}
 }
 
diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h
index c1c76a70a6ce..adb83a42a6b9 100644
--- a/include/linux/indirect_call_wrapper.h
+++ b/include/linux/indirect_call_wrapper.h
@@ -11,7 +11,7 @@
  *  @__VA_ARGS__: arguments for @f
  *
  * Avoid retpoline overhead for known builtin, checking @f vs each of them and
- * eventually invoking directly the builtin function. The functions are check
+ * eventually invoking directly the builtin function. The functions are checked
  * in the given order. Fallback to the indirect call.
  */
 #define INDIRECT_CALL_1(f, f1, ...)					\
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 40fc5813cf93..bccb3f1f6262 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -37,13 +37,6 @@ extern struct cred init_cred;
 
 #define INIT_TASK_COMM "swapper"
 
-/* Attach to the init_task data structure for proper alignment */
-#ifdef CONFIG_ARCH_TASK_STRUCT_ON_STACK
-#define __init_task_data __section(".data..init_task")
-#else
-#define __init_task_data /**/
-#endif
-
 /* Attach to the thread_info data structure for proper alignment */
 #define __init_thread_info __section(".data..init_thread_info")
 
diff --git a/include/linux/intel_tpmi.h b/include/linux/intel_tpmi.h
index ee07393445f9..a3529b962be6 100644
--- a/include/linux/intel_tpmi.h
+++ b/include/linux/intel_tpmi.h
@@ -12,6 +12,19 @@
 #define TPMI_MINOR_VERSION(val)	FIELD_GET(GENMASK(4, 0), val)
 #define TPMI_MAJOR_VERSION(val)	FIELD_GET(GENMASK(7, 5), val)
 
+/*
+ * List of supported TMPI IDs.
+ * Some TMPI IDs are not used by Linux, so the numbers are not consecutive.
+ */
+enum intel_tpmi_id {
+	TPMI_ID_RAPL = 0,	/* Running Average Power Limit */
+	TPMI_ID_PEM = 1,	/* Power and Perf excursion Monitor */
+	TPMI_ID_UNCORE = 2,	/* Uncore Frequency Scaling */
+	TPMI_ID_SST = 5,	/* Speed Select Technology */
+	TPMI_CONTROL_ID = 0x80,	/* Special ID for getting feature status */
+	TPMI_INFO_ID = 0x81,	/* Special ID for PCI BDF and Package ID information */
+};
+
 /**
  * struct intel_tpmi_plat_info - Platform information for a TPMI device instance
  * @package_id:	CPU Package id
@@ -32,7 +45,6 @@ struct intel_tpmi_plat_info {
 struct intel_tpmi_plat_info *tpmi_get_platform_data(struct auxiliary_device *auxdev);
 struct resource *tpmi_get_resource_at_index(struct auxiliary_device *auxdev, int index);
 int tpmi_get_resource_count(struct auxiliary_device *auxdev);
-
-int tpmi_get_feature_status(struct auxiliary_device *auxdev, int feature_id, int *locked,
-			    int *disabled);
+int tpmi_get_feature_status(struct auxiliary_device *auxdev, int feature_id, bool *read_blocked,
+			    bool *write_blocked);
 #endif
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index aefb73eeeebf..68ed6697fece 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -6,71 +6,13 @@
 #include <linux/xarray.h>
 #include <uapi/linux/io_uring.h>
 
-enum io_uring_cmd_flags {
-	IO_URING_F_COMPLETE_DEFER	= 1,
-	IO_URING_F_UNLOCKED		= 2,
-	/* the request is executed from poll, it should not be freed */
-	IO_URING_F_MULTISHOT		= 4,
-	/* executed by io-wq */
-	IO_URING_F_IOWQ			= 8,
-	/* int's last bit, sign checks are usually faster than a bit test */
-	IO_URING_F_NONBLOCK		= INT_MIN,
-
-	/* ctx state flags, for URING_CMD */
-	IO_URING_F_SQE128		= (1 << 8),
-	IO_URING_F_CQE32		= (1 << 9),
-	IO_URING_F_IOPOLL		= (1 << 10),
-
-	/* set when uring wants to cancel a previously issued command */
-	IO_URING_F_CANCEL		= (1 << 11),
-	IO_URING_F_COMPAT		= (1 << 12),
-};
-
-/* only top 8 bits of sqe->uring_cmd_flags for kernel internal use */
-#define IORING_URING_CMD_CANCELABLE	(1U << 30)
-#define IORING_URING_CMD_POLLED		(1U << 31)
-
-struct io_uring_cmd {
-	struct file	*file;
-	const struct io_uring_sqe *sqe;
-	union {
-		/* callback to defer completions to task context */
-		void (*task_work_cb)(struct io_uring_cmd *cmd, unsigned);
-		/* used for polled completion */
-		void *cookie;
-	};
-	u32		cmd_op;
-	u32		flags;
-	u8		pdu[32]; /* available inline for free use */
-};
-
-static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe)
-{
-	return sqe->cmd;
-}
-
 #if defined(CONFIG_IO_URING)
-int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
-			      struct iov_iter *iter, void *ioucmd);
-void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2,
-			unsigned issue_flags);
-struct sock *io_uring_get_socket(struct file *file);
 void __io_uring_cancel(bool cancel_all);
 void __io_uring_free(struct task_struct *tsk);
 void io_uring_unreg_ringfd(void);
 const char *io_uring_get_opcode(u8 opcode);
-void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
-			    void (*task_work_cb)(struct io_uring_cmd *, unsigned),
-			    unsigned flags);
-/* users should follow semantics of IOU_F_TWQ_LAZY_WAKE */
-void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd,
-			void (*task_work_cb)(struct io_uring_cmd *, unsigned));
-
-static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
-			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
-{
-	__io_uring_cmd_do_in_task(ioucmd, task_work_cb, 0);
-}
+int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags);
+bool io_is_uring_fops(struct file *file);
 
 static inline void io_uring_files_cancel(void)
 {
@@ -89,32 +31,7 @@ static inline void io_uring_free(struct task_struct *tsk)
 	if (tsk->io_uring)
 		__io_uring_free(tsk);
 }
-int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags);
-void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
-		unsigned int issue_flags);
-struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd);
 #else
-static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
-			      struct iov_iter *iter, void *ioucmd)
-{
-	return -EOPNOTSUPP;
-}
-static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret,
-		ssize_t ret2, unsigned issue_flags)
-{
-}
-static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
-			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
-{
-}
-static inline void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd,
-			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
-{
-}
-static inline struct sock *io_uring_get_socket(struct file *file)
-{
-	return NULL;
-}
 static inline void io_uring_task_cancel(void)
 {
 }
@@ -133,13 +50,9 @@ static inline int io_uring_cmd_sock(struct io_uring_cmd *cmd,
 {
 	return -EOPNOTSUPP;
 }
-static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
-		unsigned int issue_flags)
-{
-}
-static inline struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd)
+static inline bool io_is_uring_fops(struct file *file)
 {
-	return NULL;
+	return false;
 }
 #endif
 
diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h
new file mode 100644
index 000000000000..e453a997c060
--- /dev/null
+++ b/include/linux/io_uring/cmd.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _LINUX_IO_URING_CMD_H
+#define _LINUX_IO_URING_CMD_H
+
+#include <uapi/linux/io_uring.h>
+#include <linux/io_uring_types.h>
+
+/* only top 8 bits of sqe->uring_cmd_flags for kernel internal use */
+#define IORING_URING_CMD_CANCELABLE	(1U << 30)
+
+struct io_uring_cmd {
+	struct file	*file;
+	const struct io_uring_sqe *sqe;
+	/* callback to defer completions to task context */
+	void (*task_work_cb)(struct io_uring_cmd *cmd, unsigned);
+	u32		cmd_op;
+	u32		flags;
+	u8		pdu[32]; /* available inline for free use */
+};
+
+static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe)
+{
+	return sqe->cmd;
+}
+
+#if defined(CONFIG_IO_URING)
+int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
+			      struct iov_iter *iter, void *ioucmd);
+void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2,
+			unsigned issue_flags);
+void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
+			    void (*task_work_cb)(struct io_uring_cmd *, unsigned),
+			    unsigned flags);
+
+void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
+		unsigned int issue_flags);
+
+#else
+static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
+			      struct iov_iter *iter, void *ioucmd)
+{
+	return -EOPNOTSUPP;
+}
+static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret,
+		ssize_t ret2, unsigned issue_flags)
+{
+}
+static inline void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
+			    void (*task_work_cb)(struct io_uring_cmd *, unsigned),
+			    unsigned flags)
+{
+}
+static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
+		unsigned int issue_flags)
+{
+}
+#endif
+
+/* users must follow the IOU_F_TWQ_LAZY_WAKE semantics */
+static inline void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd,
+			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
+{
+	__io_uring_cmd_do_in_task(ioucmd, task_work_cb, IOU_F_TWQ_LAZY_WAKE);
+}
+
+static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
+			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
+{
+	__io_uring_cmd_do_in_task(ioucmd, task_work_cb, 0);
+}
+
+static inline struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd)
+{
+	return cmd_to_io_kiocb(cmd)->task;
+}
+
+#endif /* _LINUX_IO_URING_CMD_H */
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index d3009d56af0b..854ad67a5f70 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -7,6 +7,37 @@
 #include <linux/llist.h>
 #include <uapi/linux/io_uring.h>
 
+enum {
+	/*
+	 * A hint to not wake right away but delay until there are enough of
+	 * tw's queued to match the number of CQEs the task is waiting for.
+	 *
+	 * Must not be used wirh requests generating more than one CQE.
+	 * It's also ignored unless IORING_SETUP_DEFER_TASKRUN is set.
+	 */
+	IOU_F_TWQ_LAZY_WAKE			= 1,
+};
+
+enum io_uring_cmd_flags {
+	IO_URING_F_COMPLETE_DEFER	= 1,
+	IO_URING_F_UNLOCKED		= 2,
+	/* the request is executed from poll, it should not be freed */
+	IO_URING_F_MULTISHOT		= 4,
+	/* executed by io-wq */
+	IO_URING_F_IOWQ			= 8,
+	/* int's last bit, sign checks are usually faster than a bit test */
+	IO_URING_F_NONBLOCK		= INT_MIN,
+
+	/* ctx state flags, for URING_CMD */
+	IO_URING_F_SQE128		= (1 << 8),
+	IO_URING_F_CQE32		= (1 << 9),
+	IO_URING_F_IOPOLL		= (1 << 10),
+
+	/* set when uring wants to cancel a previously issued command */
+	IO_URING_F_CANCEL		= (1 << 11),
+	IO_URING_F_COMPAT		= (1 << 12),
+};
+
 struct io_wq_work_node {
 	struct io_wq_work_node *next;
 };
@@ -340,6 +371,9 @@ struct io_ring_ctx {
 
 	struct list_head	io_buffers_cache;
 
+	/* deferred free list, protected by ->uring_lock */
+	struct hlist_head	io_buf_list;
+
 	/* Keep this last, we don't need it for the fast path */
 	struct wait_queue_head		poll_wq;
 	struct io_restriction		restrictions;
@@ -355,9 +389,6 @@ struct io_ring_ctx {
 	struct wait_queue_head		rsrc_quiesce_wq;
 	unsigned			rsrc_quiesce;
 
-	#if defined(CONFIG_UNIX)
-		struct socket		*ring_sock;
-	#endif
 	/* hashed buffered write serialization */
 	struct io_wq_hash		*hash_map;
 
@@ -431,6 +462,7 @@ enum {
 	/* keep async read/write and isreg together and in order */
 	REQ_F_SUPPORT_NOWAIT_BIT,
 	REQ_F_ISREG_BIT,
+	REQ_F_POLL_NO_LAZY_BIT,
 
 	/* not a real bit, just to check we're not overflowing the space */
 	__REQ_F_LAST_BIT,
@@ -498,6 +530,8 @@ enum {
 	REQ_F_CLEAR_POLLIN	= BIT(REQ_F_CLEAR_POLLIN_BIT),
 	/* hashed into ->cancel_hash_locked, protected by ->uring_lock */
 	REQ_F_HASH_LOCKED	= BIT(REQ_F_HASH_LOCKED_BIT),
+	/* don't use lazy poll wake for this request */
+	REQ_F_POLL_NO_LAZY	= BIT(REQ_F_POLL_NO_LAZY_BIT),
 };
 
 typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts);
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index ec289c1016f5..6291aa7b079b 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -845,6 +845,7 @@ static inline void dev_iommu_priv_set(struct device *dev, void *priv)
 	dev->iommu->priv = priv;
 }
 
+extern struct mutex iommu_probe_device_lock;
 int iommu_probe_device(struct device *dev);
 
 int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f);
diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 14f5cfabbbc8..db7fe25f3370 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -331,6 +331,9 @@ extern int
 walk_system_ram_res(u64 start, u64 end, void *arg,
 		    int (*func)(struct resource *, void *));
 extern int
+walk_system_ram_res_rev(u64 start, u64 end, void *arg,
+			int (*func)(struct resource *, void *));
+extern int
 walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, u64 end,
 		    void *arg, int (*func)(struct resource *, void *));
 
diff --git a/include/linux/ipc.h b/include/linux/ipc.h
index e1c9eea6015b..9b1434247aab 100644
--- a/include/linux/ipc.h
+++ b/include/linux/ipc.h
@@ -2,7 +2,7 @@
 #ifndef _LINUX_IPC_H
 #define _LINUX_IPC_H
 
-#include <linux/spinlock.h>
+#include <linux/spinlock_types.h>
 #include <linux/uidgid.h>
 #include <linux/rhashtable-types.h>
 #include <uapi/linux/ipc.h>
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index 8cd11a223260..136f2980cba3 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -66,6 +66,9 @@ void irq_work_sync(struct irq_work *work);
 void irq_work_run(void);
 bool irq_work_needs_cpu(void);
 void irq_work_single(void *arg);
+
+void arch_irq_work_raise(void);
+
 #else
 static inline bool irq_work_needs_cpu(void) { return false; }
 static inline void irq_work_run(void) { }
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 2b665c32f5fe..147feebd508c 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -12,6 +12,7 @@
 #ifndef _LINUX_TRACE_IRQFLAGS_H
 #define _LINUX_TRACE_IRQFLAGS_H
 
+#include <linux/irqflags_types.h>
 #include <linux/typecheck.h>
 #include <linux/cleanup.h>
 #include <asm/irqflags.h>
@@ -34,19 +35,6 @@
 
 #ifdef CONFIG_TRACE_IRQFLAGS
 
-/* Per-task IRQ trace events information. */
-struct irqtrace_events {
-	unsigned int	irq_events;
-	unsigned long	hardirq_enable_ip;
-	unsigned long	hardirq_disable_ip;
-	unsigned int	hardirq_enable_event;
-	unsigned int	hardirq_disable_event;
-	unsigned long	softirq_disable_ip;
-	unsigned long	softirq_enable_ip;
-	unsigned int	softirq_disable_event;
-	unsigned int	softirq_enable_event;
-};
-
 DECLARE_PER_CPU(int, hardirqs_enabled);
 DECLARE_PER_CPU(int, hardirq_context);
 
diff --git a/include/linux/irqflags_types.h b/include/linux/irqflags_types.h
new file mode 100644
index 000000000000..c13f0d915097
--- /dev/null
+++ b/include/linux/irqflags_types.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_IRQFLAGS_TYPES_H
+#define _LINUX_IRQFLAGS_TYPES_H
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+
+/* Per-task IRQ trace events information. */
+struct irqtrace_events {
+	unsigned int	irq_events;
+	unsigned long	hardirq_enable_ip;
+	unsigned long	hardirq_disable_ip;
+	unsigned int	hardirq_enable_event;
+	unsigned int	hardirq_disable_event;
+	unsigned long	softirq_disable_ip;
+	unsigned long	softirq_enable_ip;
+	unsigned int	softirq_disable_event;
+	unsigned int	softirq_enable_event;
+};
+
+#endif
+
+#endif /* _LINUX_IRQFLAGS_TYPES_H */
diff --git a/include/linux/ism.h b/include/linux/ism.h
index 9a4c204df3da..5428edd90982 100644
--- a/include/linux/ism.h
+++ b/include/linux/ism.h
@@ -86,7 +86,6 @@ int  ism_register_dmb(struct ism_dev *dev, struct ism_dmb *dmb,
 int  ism_unregister_dmb(struct ism_dev *dev, struct ism_dmb *dmb);
 int  ism_move(struct ism_dev *dev, u64 dmb_tok, unsigned int idx, bool sf,
 	      unsigned int offset, void *data, unsigned int size);
-u8  *ism_get_seid(void);
 
 const struct smcd_ops *ism_get_smcd_ops(void);
 
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 6dcbb4eb80fb..971f3e826e15 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -756,11 +756,6 @@ struct journal_s
 	unsigned long		j_flags;
 
 	/**
-	 * @j_atomic_flags: Atomic journaling state flags.
-	 */
-	unsigned long		j_atomic_flags;
-
-	/**
 	 * @j_errno:
 	 *
 	 * Is there an outstanding uncleared error on the journal (from a prior
@@ -999,6 +994,13 @@ struct journal_s
 	struct block_device	*j_fs_dev;
 
 	/**
+	 * @j_fs_dev_wb_err:
+	 *
+	 * Records the errseq of the client fs's backing block device.
+	 */
+	errseq_t		j_fs_dev_wb_err;
+
+	/**
 	 * @j_total_len: Total maximum capacity of the journal region on disk.
 	 */
 	unsigned int		j_total_len;
@@ -1374,6 +1376,9 @@ JBD2_FEATURE_INCOMPAT_FUNCS(csum2,		CSUM_V2)
 JBD2_FEATURE_INCOMPAT_FUNCS(csum3,		CSUM_V3)
 JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit,	FAST_COMMIT)
 
+/* Journal high priority write IO operation flags */
+#define JBD2_JOURNAL_REQ_FLAGS		(REQ_META | REQ_SYNC | REQ_IDLE)
+
 /*
  * Journal flag definitions
  */
@@ -1397,12 +1402,6 @@ JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit,	FAST_COMMIT)
 					JBD2_JOURNAL_FLUSH_ZEROOUT)
 
 /*
- * Journal atomic flag definitions
- */
-#define JBD2_CHECKPOINT_IO_ERROR	0x001	/* Detect io error while writing
-						 * buffer back to disk */
-
-/*
  * Function declarations for the journaling transaction and buffer
  * management
  */
@@ -1695,6 +1694,25 @@ static inline void jbd2_journal_abort_handle(handle_t *handle)
 	handle->h_aborted = 1;
 }
 
+static inline void jbd2_init_fs_dev_write_error(journal_t *journal)
+{
+	struct address_space *mapping = journal->j_fs_dev->bd_inode->i_mapping;
+
+	/*
+	 * Save the original wb_err value of client fs's bdev mapping which
+	 * could be used to detect the client fs's metadata async write error.
+	 */
+	errseq_check_and_advance(&mapping->wb_err, &journal->j_fs_dev_wb_err);
+}
+
+static inline int jbd2_check_fs_dev_write_error(journal_t *journal)
+{
+	struct address_space *mapping = journal->j_fs_dev->bd_inode->i_mapping;
+
+	return errseq_check(&mapping->wb_err,
+			    READ_ONCE(journal->j_fs_dev_wb_err));
+}
+
 #endif /* __KERNEL__   */
 
 /* Comparison functions for transaction IDs: perform comparisons using
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 72cb693b075b..dbb06d789e74 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -4,6 +4,7 @@
 
 #include <linux/bug.h>
 #include <linux/kasan-enabled.h>
+#include <linux/kasan-tags.h>
 #include <linux/kernel.h>
 #include <linux/static_key.h>
 #include <linux/types.h>
@@ -129,20 +130,39 @@ static __always_inline void kasan_poison_slab(struct slab *slab)
 		__kasan_poison_slab(slab);
 }
 
-void __kasan_unpoison_object_data(struct kmem_cache *cache, void *object);
-static __always_inline void kasan_unpoison_object_data(struct kmem_cache *cache,
+void __kasan_unpoison_new_object(struct kmem_cache *cache, void *object);
+/**
+ * kasan_unpoison_new_object - Temporarily unpoison a new slab object.
+ * @cache: Cache the object belong to.
+ * @object: Pointer to the object.
+ *
+ * This function is intended for the slab allocator's internal use. It
+ * temporarily unpoisons an object from a newly allocated slab without doing
+ * anything else. The object must later be repoisoned by
+ * kasan_poison_new_object().
+ */
+static __always_inline void kasan_unpoison_new_object(struct kmem_cache *cache,
 							void *object)
 {
 	if (kasan_enabled())
-		__kasan_unpoison_object_data(cache, object);
+		__kasan_unpoison_new_object(cache, object);
 }
 
-void __kasan_poison_object_data(struct kmem_cache *cache, void *object);
-static __always_inline void kasan_poison_object_data(struct kmem_cache *cache,
+void __kasan_poison_new_object(struct kmem_cache *cache, void *object);
+/**
+ * kasan_unpoison_new_object - Repoison a new slab object.
+ * @cache: Cache the object belong to.
+ * @object: Pointer to the object.
+ *
+ * This function is intended for the slab allocator's internal use. It
+ * repoisons an object that was previously unpoisoned by
+ * kasan_unpoison_new_object() without doing anything else.
+ */
+static __always_inline void kasan_poison_new_object(struct kmem_cache *cache,
 							void *object)
 {
 	if (kasan_enabled())
-		__kasan_poison_object_data(cache, object);
+		__kasan_poison_new_object(cache, object);
 }
 
 void * __must_check __kasan_init_slab_obj(struct kmem_cache *cache,
@@ -172,13 +192,6 @@ static __always_inline void kasan_kfree_large(void *ptr)
 		__kasan_kfree_large(ptr, _RET_IP_);
 }
 
-void __kasan_slab_free_mempool(void *ptr, unsigned long ip);
-static __always_inline void kasan_slab_free_mempool(void *ptr)
-{
-	if (kasan_enabled())
-		__kasan_slab_free_mempool(ptr, _RET_IP_);
-}
-
 void * __must_check __kasan_slab_alloc(struct kmem_cache *s,
 				       void *object, gfp_t flags, bool init);
 static __always_inline void * __must_check kasan_slab_alloc(
@@ -219,6 +232,113 @@ static __always_inline void * __must_check kasan_krealloc(const void *object,
 	return (void *)object;
 }
 
+bool __kasan_mempool_poison_pages(struct page *page, unsigned int order,
+				  unsigned long ip);
+/**
+ * kasan_mempool_poison_pages - Check and poison a mempool page allocation.
+ * @page: Pointer to the page allocation.
+ * @order: Order of the allocation.
+ *
+ * This function is intended for kernel subsystems that cache page allocations
+ * to reuse them instead of freeing them back to page_alloc (e.g. mempool).
+ *
+ * This function is similar to kasan_mempool_poison_object() but operates on
+ * page allocations.
+ *
+ * Before the poisoned allocation can be reused, it must be unpoisoned via
+ * kasan_mempool_unpoison_pages().
+ *
+ * Return: true if the allocation can be safely reused; false otherwise.
+ */
+static __always_inline bool kasan_mempool_poison_pages(struct page *page,
+						       unsigned int order)
+{
+	if (kasan_enabled())
+		return __kasan_mempool_poison_pages(page, order, _RET_IP_);
+	return true;
+}
+
+void __kasan_mempool_unpoison_pages(struct page *page, unsigned int order,
+				    unsigned long ip);
+/**
+ * kasan_mempool_unpoison_pages - Unpoison a mempool page allocation.
+ * @page: Pointer to the page allocation.
+ * @order: Order of the allocation.
+ *
+ * This function is intended for kernel subsystems that cache page allocations
+ * to reuse them instead of freeing them back to page_alloc (e.g. mempool).
+ *
+ * This function unpoisons a page allocation that was previously poisoned by
+ * kasan_mempool_poison_pages() without zeroing the allocation's memory. For
+ * the tag-based modes, this function assigns a new tag to the allocation.
+ */
+static __always_inline void kasan_mempool_unpoison_pages(struct page *page,
+							 unsigned int order)
+{
+	if (kasan_enabled())
+		__kasan_mempool_unpoison_pages(page, order, _RET_IP_);
+}
+
+bool __kasan_mempool_poison_object(void *ptr, unsigned long ip);
+/**
+ * kasan_mempool_poison_object - Check and poison a mempool slab allocation.
+ * @ptr: Pointer to the slab allocation.
+ *
+ * This function is intended for kernel subsystems that cache slab allocations
+ * to reuse them instead of freeing them back to the slab allocator (e.g.
+ * mempool).
+ *
+ * This function poisons a slab allocation and saves a free stack trace for it
+ * without initializing the allocation's memory and without putting it into the
+ * quarantine (for the Generic mode).
+ *
+ * This function also performs checks to detect double-free and invalid-free
+ * bugs and reports them. The caller can use the return value of this function
+ * to find out if the allocation is buggy.
+ *
+ * Before the poisoned allocation can be reused, it must be unpoisoned via
+ * kasan_mempool_unpoison_object().
+ *
+ * This function operates on all slab allocations including large kmalloc
+ * allocations (the ones returned by kmalloc_large() or by kmalloc() with the
+ * size > KMALLOC_MAX_SIZE).
+ *
+ * Return: true if the allocation can be safely reused; false otherwise.
+ */
+static __always_inline bool kasan_mempool_poison_object(void *ptr)
+{
+	if (kasan_enabled())
+		return __kasan_mempool_poison_object(ptr, _RET_IP_);
+	return true;
+}
+
+void __kasan_mempool_unpoison_object(void *ptr, size_t size, unsigned long ip);
+/**
+ * kasan_mempool_unpoison_object - Unpoison a mempool slab allocation.
+ * @ptr: Pointer to the slab allocation.
+ * @size: Size to be unpoisoned.
+ *
+ * This function is intended for kernel subsystems that cache slab allocations
+ * to reuse them instead of freeing them back to the slab allocator (e.g.
+ * mempool).
+ *
+ * This function unpoisons a slab allocation that was previously poisoned via
+ * kasan_mempool_poison_object() and saves an alloc stack trace for it without
+ * initializing the allocation's memory. For the tag-based modes, this function
+ * does not assign a new tag to the allocation and instead restores the
+ * original tags based on the pointer value.
+ *
+ * This function operates on all slab allocations including large kmalloc
+ * allocations (the ones returned by kmalloc_large() or by kmalloc() with the
+ * size > KMALLOC_MAX_SIZE).
+ */
+static __always_inline void kasan_mempool_unpoison_object(void *ptr,
+							  size_t size)
+{
+	if (kasan_enabled())
+		__kasan_mempool_unpoison_object(ptr, size, _RET_IP_);
+}
+
 /*
  * Unlike kasan_check_read/write(), kasan_check_byte() is performed even for
  * the hardware tag-based mode that doesn't rely on compiler instrumentation.
@@ -242,9 +362,9 @@ static inline bool kasan_unpoison_pages(struct page *page, unsigned int order,
 	return false;
 }
 static inline void kasan_poison_slab(struct slab *slab) {}
-static inline void kasan_unpoison_object_data(struct kmem_cache *cache,
+static inline void kasan_unpoison_new_object(struct kmem_cache *cache,
 					void *object) {}
-static inline void kasan_poison_object_data(struct kmem_cache *cache,
+static inline void kasan_poison_new_object(struct kmem_cache *cache,
 					void *object) {}
 static inline void *kasan_init_slab_obj(struct kmem_cache *cache,
 				const void *object)
@@ -256,7 +376,6 @@ static inline bool kasan_slab_free(struct kmem_cache *s, void *object, bool init
 	return false;
 }
 static inline void kasan_kfree_large(void *ptr) {}
-static inline void kasan_slab_free_mempool(void *ptr) {}
 static inline void *kasan_slab_alloc(struct kmem_cache *s, void *object,
 				   gfp_t flags, bool init)
 {
@@ -276,6 +395,17 @@ static inline void *kasan_krealloc(const void *object, size_t new_size,
 {
 	return (void *)object;
 }
+static inline bool kasan_mempool_poison_pages(struct page *page, unsigned int order)
+{
+	return true;
+}
+static inline void kasan_mempool_unpoison_pages(struct page *page, unsigned int order) {}
+static inline bool kasan_mempool_poison_object(void *ptr)
+{
+	return true;
+}
+static inline void kasan_mempool_unpoison_object(void *ptr, size_t size) {}
+
 static inline bool kasan_check_byte(const void *address)
 {
 	return true;
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 8227455192b7..400cb6c02176 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -403,7 +403,7 @@ bool kexec_load_permitted(int kexec_image_type);
 
 /* List of defined/legal kexec file flags */
 #define KEXEC_FILE_FLAGS	(KEXEC_FILE_UNLOAD | KEXEC_FILE_ON_CRASH | \
-				 KEXEC_FILE_NO_INITRAMFS)
+				 KEXEC_FILE_NO_INITRAMFS | KEXEC_FILE_DEBUG)
 
 /* flag to track if kexec reboot is in progress */
 extern bool kexec_in_progress;
@@ -500,6 +500,13 @@ static inline int crash_hotplug_memory_support(void) { return 0; }
 static inline unsigned int crash_get_elfcorehdr_size(void) { return 0; }
 #endif
 
+extern bool kexec_file_dbg_print;
+
+#define kexec_dprintk(fmt, ...)					\
+	printk("%s" fmt,					\
+	       kexec_file_dbg_print ? KERN_INFO : KERN_DEBUG,	\
+	       ##__VA_ARGS__)
+
 #else /* !CONFIG_KEXEC_CORE */
 struct pt_regs;
 struct task_struct;
diff --git a/include/linux/key-type.h b/include/linux/key-type.h
index 7d985a1dfe4a..5caf3ce82373 100644
--- a/include/linux/key-type.h
+++ b/include/linux/key-type.h
@@ -73,6 +73,7 @@ struct key_type {
 
 	unsigned int flags;
 #define KEY_TYPE_NET_DOMAIN	0x00000001 /* Keys of this type have a net namespace domain */
+#define KEY_TYPE_INSTANT_REAP	0x00000002 /* Keys of this type don't have a delay after expiring */
 
 	/* vet a description */
 	int (*vet_description)(const char *description);
diff --git a/include/linux/kfence.h b/include/linux/kfence.h
index 401af4757514..88100cc9caba 100644
--- a/include/linux/kfence.h
+++ b/include/linux/kfence.h
@@ -223,6 +223,8 @@ bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *sla
 
 #else /* CONFIG_KFENCE */
 
+#define kfence_sample_interval	(0)
+
 static inline bool is_kfence_address(const void *addr) { return false; }
 static inline void kfence_alloc_pool_and_metadata(void) { }
 static inline void kfence_init(void) { }
diff --git a/include/linux/kmsan_types.h b/include/linux/kmsan_types.h
index 8bfa6c98176d..929287981afe 100644
--- a/include/linux/kmsan_types.h
+++ b/include/linux/kmsan_types.h
@@ -9,6 +9,8 @@
 #ifndef _LINUX_KMSAN_TYPES_H
 #define _LINUX_KMSAN_TYPES_H
 
+#include <linux/types.h>
+
 /* These constants are defined in the MSan LLVM instrumentation pass. */
 #define KMSAN_RETVAL_SIZE 800
 #define KMSAN_PARAM_SIZE 800
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index ab1da3142b06..0ff44d6633e3 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -139,7 +139,7 @@ static inline bool kprobe_ftrace(struct kprobe *p)
  *
  */
 struct kretprobe_holder {
-	struct kretprobe	*rp;
+	struct kretprobe __rcu *rp;
 	struct objpool_head	pool;
 };
 
@@ -197,10 +197,8 @@ extern int arch_trampoline_kprobe(struct kprobe *p);
 #ifdef CONFIG_KRETPROBE_ON_RETHOOK
 static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance *ri)
 {
-	RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(),
-		"Kretprobe is accessed from instance under preemptive context");
-
-	return (struct kretprobe *)READ_ONCE(ri->node.rethook->data);
+	/* rethook::data is non-changed field, so that you can access it freely. */
+	return (struct kretprobe *)ri->node.rethook->data;
 }
 static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri)
 {
@@ -245,10 +243,7 @@ unsigned long kretprobe_trampoline_handler(struct pt_regs *regs,
 
 static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance *ri)
 {
-	RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(),
-		"Kretprobe is accessed from instance under preemptive context");
-
-	return READ_ONCE(ri->rph->rp);
+	return rcu_dereference_check(ri->rph->rp, rcu_read_lock_any_held());
 }
 
 static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri)
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index c2dd786a30e1..401348e9f92b 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -76,8 +76,8 @@ static inline void ksm_exit(struct mm_struct *mm)
  * We'd like to make this conditional on vma->vm_flags & VM_MERGEABLE,
  * but what if the vma was unmerged while the page was swapped out?
  */
-struct page *ksm_might_need_to_copy(struct page *page,
-			struct vm_area_struct *vma, unsigned long address);
+struct folio *ksm_might_need_to_copy(struct folio *folio,
+			struct vm_area_struct *vma, unsigned long addr);
 
 void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc);
 void folio_migrate_ksm(struct folio *newfolio, struct folio *folio);
@@ -129,10 +129,10 @@ static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 	return 0;
 }
 
-static inline struct page *ksm_might_need_to_copy(struct page *page,
-			struct vm_area_struct *vma, unsigned long address)
+static inline struct folio *ksm_might_need_to_copy(struct folio *folio,
+			struct vm_area_struct *vma, unsigned long addr)
 {
-	return page;
+	return folio;
 }
 
 static inline void rmap_walk_ksm(struct folio *folio,
diff --git a/include/linux/ktime.h b/include/linux/ktime.h
index 73f20deb497d..3a4e723eae0f 100644
--- a/include/linux/ktime.h
+++ b/include/linux/ktime.h
@@ -21,12 +21,10 @@
 #ifndef _LINUX_KTIME_H
 #define _LINUX_KTIME_H
 
-#include <linux/time.h>
-#include <linux/jiffies.h>
 #include <asm/bug.h>
-
-/* Nanosecond scalar representation for kernel time values */
-typedef s64	ktime_t;
+#include <linux/jiffies.h>
+#include <linux/time.h>
+#include <linux/types.h>
 
 /**
  * ktime_set - Set a ktime_t variable from a seconds/nanoseconds value
diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h
index 7303b4bc2ce0..287f590ed56b 100644
--- a/include/linux/linkmode.h
+++ b/include/linux/linkmode.h
@@ -10,6 +10,11 @@ static inline void linkmode_zero(unsigned long *dst)
 	bitmap_zero(dst, __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
+static inline void linkmode_fill(unsigned long *dst)
+{
+	bitmap_fill(dst, __ETHTOOL_LINK_MODE_MASK_NBITS);
+}
+
 static inline void linkmode_copy(unsigned long *dst, const unsigned long *src)
 {
 	bitmap_copy(dst, src, __ETHTOOL_LINK_MODE_MASK_NBITS);
diff --git a/include/linux/list.h b/include/linux/list.h
index 1837caedf723..059aa1fff41e 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -1119,6 +1119,26 @@ static inline void hlist_move_list(struct hlist_head *old,
 	old->first = NULL;
 }
 
+/**
+ * hlist_splice_init() - move all entries from one list to another
+ * @from: hlist_head from which entries will be moved
+ * @last: last entry on the @from list
+ * @to:   hlist_head to which entries will be moved
+ *
+ * @to can be empty, @from must contain at least @last.
+ */
+static inline void hlist_splice_init(struct hlist_head *from,
+				     struct hlist_node *last,
+				     struct hlist_head *to)
+{
+	if (to->first)
+		to->first->pprev = &last->next;
+	last->next = to->first;
+	to->first = from->first;
+	from->first->pprev = &to->first;
+	from->first = NULL;
+}
+
 #define hlist_entry(ptr, type, member) container_of(ptr,type,member)
 
 #define hlist_for_each(pos, head) \
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index b35968ee9fb5..7675a48a0701 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -73,8 +73,10 @@ void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *paren
 
 /**
  * list_lru_add: add an element to the lru list's tail
- * @list_lru: the lru pointer
+ * @lru: the lru pointer
  * @item: the item to be added.
+ * @nid: the node id of the sublist to add the item to.
+ * @memcg: the cgroup of the sublist to add the item to.
  *
  * If the element is already part of a list, this function returns doing
  * nothing. Therefore the caller does not need to keep state about whether or
@@ -83,24 +85,54 @@ void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *paren
  * the caller organize itself in a way that elements can be in more than
  * one type of list, it is up to the caller to fully remove the item from
  * the previous list (with list_lru_del() for instance) before moving it
- * to @list_lru
+ * to @lru.
+ *
+ * Return: true if the list was updated, false otherwise
+ */
+bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid,
+		    struct mem_cgroup *memcg);
+
+/**
+ * list_lru_add_obj: add an element to the lru list's tail
+ * @lru: the lru pointer
+ * @item: the item to be added.
+ *
+ * This function is similar to list_lru_add(), but the NUMA node and the
+ * memcg of the sublist is determined by @item list_head. This assumption is
+ * valid for slab objects LRU such as dentries, inodes, etc.
  *
  * Return value: true if the list was updated, false otherwise
  */
-bool list_lru_add(struct list_lru *lru, struct list_head *item);
+bool list_lru_add_obj(struct list_lru *lru, struct list_head *item);
 
 /**
- * list_lru_del: delete an element to the lru list
- * @list_lru: the lru pointer
+ * list_lru_del: delete an element from the lru list
+ * @lru: the lru pointer
  * @item: the item to be deleted.
+ * @nid: the node id of the sublist to delete the item from.
+ * @memcg: the cgroup of the sublist to delete the item from.
  *
- * This function works analogously as list_lru_add in terms of list
+ * This function works analogously as list_lru_add() in terms of list
  * manipulation. The comments about an element already pertaining to
- * a list are also valid for list_lru_del.
+ * a list are also valid for list_lru_del().
  *
- * Return value: true if the list was updated, false otherwise
+ * Return: true if the list was updated, false otherwise
  */
-bool list_lru_del(struct list_lru *lru, struct list_head *item);
+bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid,
+		    struct mem_cgroup *memcg);
+
+/**
+ * list_lru_del_obj: delete an element from the lru list
+ * @lru: the lru pointer
+ * @item: the item to be deleted.
+ *
+ * This function is similar to list_lru_del(), but the NUMA node and the
+ * memcg of the sublist is determined by @item list_head. This assumption is
+ * valid for slab objects LRU such as dentries, inodes, etc.
+ *
+ * Return value: true if the list was updated, false otherwise.
+ */
+bool list_lru_del_obj(struct list_lru *lru, struct list_head *item);
 
 /**
  * list_lru_count_one: return the number of objects currently held by @lru
@@ -108,9 +140,11 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item);
  * @nid: the node id to count from.
  * @memcg: the cgroup to count from.
  *
- * Always return a non-negative number, 0 for empty lists. There is no
- * guarantee that the list is not updated while the count is being computed.
- * Callers that want such a guarantee need to provide an outer lock.
+ * There is no guarantee that the list is not updated while the count is being
+ * computed. Callers that want such a guarantee need to provide an outer lock.
+ *
+ * Return: 0 for empty lists, otherwise the number of objects
+ * currently held by @lru.
  */
 unsigned long list_lru_count_one(struct list_lru *lru,
 				 int nid, struct mem_cgroup *memcg);
@@ -136,12 +170,28 @@ static inline unsigned long list_lru_count(struct list_lru *lru)
 void list_lru_isolate(struct list_lru_one *list, struct list_head *item);
 void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item,
 			   struct list_head *head);
+/**
+ * list_lru_putback: undo list_lru_isolate
+ * @lru: the lru pointer.
+ * @item: the item to put back.
+ * @nid: the node id of the sublist to put the item back to.
+ * @memcg: the cgroup of the sublist to put the item back to.
+ *
+ * Put back an isolated item into its original LRU. Note that unlike
+ * list_lru_add, this does not increment the node LRU count (as
+ * list_lru_isolate does not originally decrement this count).
+ *
+ * Since we might have dropped the LRU lock in between, recompute list_lru_one
+ * from the node's id and memcg.
+ */
+void list_lru_putback(struct list_lru *lru, struct list_head *item, int nid,
+		      struct mem_cgroup *memcg);
 
 typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item,
 		struct list_lru_one *list, spinlock_t *lock, void *cb_arg);
 
 /**
- * list_lru_walk_one: walk a list_lru, isolating and disposing freeable items.
+ * list_lru_walk_one: walk a @lru, isolating and disposing freeable items.
  * @lru: the lru pointer.
  * @nid: the node id to scan from.
  * @memcg: the cgroup to scan from.
@@ -150,24 +200,24 @@ typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item,
  * @cb_arg: opaque type that will be passed to @isolate
  * @nr_to_walk: how many items to scan.
  *
- * This function will scan all elements in a particular list_lru, calling the
+ * This function will scan all elements in a particular @lru, calling the
  * @isolate callback for each of those items, along with the current list
  * spinlock and a caller-provided opaque. The @isolate callback can choose to
  * drop the lock internally, but *must* return with the lock held. The callback
- * will return an enum lru_status telling the list_lru infrastructure what to
+ * will return an enum lru_status telling the @lru infrastructure what to
  * do with the object being scanned.
  *
- * Please note that nr_to_walk does not mean how many objects will be freed,
+ * Please note that @nr_to_walk does not mean how many objects will be freed,
  * just how many objects will be scanned.
  *
- * Return value: the number of objects effectively removed from the LRU.
+ * Return: the number of objects effectively removed from the LRU.
  */
 unsigned long list_lru_walk_one(struct list_lru *lru,
 				int nid, struct mem_cgroup *memcg,
 				list_lru_walk_cb isolate, void *cb_arg,
 				unsigned long *nr_to_walk);
 /**
- * list_lru_walk_one_irq: walk a list_lru, isolating and disposing freeable items.
+ * list_lru_walk_one_irq: walk a @lru, isolating and disposing freeable items.
  * @lru: the lru pointer.
  * @nid: the node id to scan from.
  * @memcg: the cgroup to scan from.
@@ -176,7 +226,7 @@ unsigned long list_lru_walk_one(struct list_lru *lru,
  * @cb_arg: opaque type that will be passed to @isolate
  * @nr_to_walk: how many items to scan.
  *
- * Same as @list_lru_walk_one except that the spinlock is acquired with
+ * Same as list_lru_walk_one() except that the spinlock is acquired with
  * spin_lock_irq().
  */
 unsigned long list_lru_walk_one_irq(struct list_lru *lru,
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index dc2844b071c2..08b0d1d9d78b 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -82,63 +82,6 @@ struct lock_chain {
 	u64				chain_key;
 };
 
-#define MAX_LOCKDEP_KEYS_BITS		13
-#define MAX_LOCKDEP_KEYS		(1UL << MAX_LOCKDEP_KEYS_BITS)
-#define INITIAL_CHAIN_KEY		-1
-
-struct held_lock {
-	/*
-	 * One-way hash of the dependency chain up to this point. We
-	 * hash the hashes step by step as the dependency chain grows.
-	 *
-	 * We use it for dependency-caching and we skip detection
-	 * passes and dependency-updates if there is a cache-hit, so
-	 * it is absolutely critical for 100% coverage of the validator
-	 * to have a unique key value for every unique dependency path
-	 * that can occur in the system, to make a unique hash value
-	 * as likely as possible - hence the 64-bit width.
-	 *
-	 * The task struct holds the current hash value (initialized
-	 * with zero), here we store the previous hash value:
-	 */
-	u64				prev_chain_key;
-	unsigned long			acquire_ip;
-	struct lockdep_map		*instance;
-	struct lockdep_map		*nest_lock;
-#ifdef CONFIG_LOCK_STAT
-	u64 				waittime_stamp;
-	u64				holdtime_stamp;
-#endif
-	/*
-	 * class_idx is zero-indexed; it points to the element in
-	 * lock_classes this held lock instance belongs to. class_idx is in
-	 * the range from 0 to (MAX_LOCKDEP_KEYS-1) inclusive.
-	 */
-	unsigned int			class_idx:MAX_LOCKDEP_KEYS_BITS;
-	/*
-	 * The lock-stack is unified in that the lock chains of interrupt
-	 * contexts nest ontop of process context chains, but we 'separate'
-	 * the hashes by starting with 0 if we cross into an interrupt
-	 * context, and we also keep do not add cross-context lock
-	 * dependencies - the lock usage graph walking covers that area
-	 * anyway, and we'd just unnecessarily increase the number of
-	 * dependencies otherwise. [Note: hardirq and softirq contexts
-	 * are separated from each other too.]
-	 *
-	 * The following field is used to detect when we cross into an
-	 * interrupt context:
-	 */
-	unsigned int irq_context:2; /* bit 0 - soft, bit 1 - hard */
-	unsigned int trylock:1;						/* 16 bits */
-
-	unsigned int read:2;        /* see lock_acquire() comment */
-	unsigned int check:1;       /* see lock_acquire() comment */
-	unsigned int hardirqs_off:1;
-	unsigned int sync:1;
-	unsigned int references:11;					/* 32 bits */
-	unsigned int pin_count;
-};
-
 /*
  * Initialization, self-test and debugging-output methods:
  */
diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h
index 2ebc323d345a..70d30d40ea4a 100644
--- a/include/linux/lockdep_types.h
+++ b/include/linux/lockdep_types.h
@@ -127,12 +127,12 @@ struct lock_class {
 	unsigned long			usage_mask;
 	const struct lock_trace		*usage_traces[LOCK_TRACE_STATES];
 
+	const char			*name;
 	/*
 	 * Generation counter, when doing certain classes of graph walking,
 	 * to ensure that we check one node only once:
 	 */
 	int				name_version;
-	const char			*name;
 
 	u8				wait_type_inner;
 	u8				wait_type_outer;
@@ -198,6 +198,63 @@ struct lockdep_map {
 
 struct pin_cookie { unsigned int val; };
 
+#define MAX_LOCKDEP_KEYS_BITS		13
+#define MAX_LOCKDEP_KEYS		(1UL << MAX_LOCKDEP_KEYS_BITS)
+#define INITIAL_CHAIN_KEY		-1
+
+struct held_lock {
+	/*
+	 * One-way hash of the dependency chain up to this point. We
+	 * hash the hashes step by step as the dependency chain grows.
+	 *
+	 * We use it for dependency-caching and we skip detection
+	 * passes and dependency-updates if there is a cache-hit, so
+	 * it is absolutely critical for 100% coverage of the validator
+	 * to have a unique key value for every unique dependency path
+	 * that can occur in the system, to make a unique hash value
+	 * as likely as possible - hence the 64-bit width.
+	 *
+	 * The task struct holds the current hash value (initialized
+	 * with zero), here we store the previous hash value:
+	 */
+	u64				prev_chain_key;
+	unsigned long			acquire_ip;
+	struct lockdep_map		*instance;
+	struct lockdep_map		*nest_lock;
+#ifdef CONFIG_LOCK_STAT
+	u64 				waittime_stamp;
+	u64				holdtime_stamp;
+#endif
+	/*
+	 * class_idx is zero-indexed; it points to the element in
+	 * lock_classes this held lock instance belongs to. class_idx is in
+	 * the range from 0 to (MAX_LOCKDEP_KEYS-1) inclusive.
+	 */
+	unsigned int			class_idx:MAX_LOCKDEP_KEYS_BITS;
+	/*
+	 * The lock-stack is unified in that the lock chains of interrupt
+	 * contexts nest ontop of process context chains, but we 'separate'
+	 * the hashes by starting with 0 if we cross into an interrupt
+	 * context, and we also keep do not add cross-context lock
+	 * dependencies - the lock usage graph walking covers that area
+	 * anyway, and we'd just unnecessarily increase the number of
+	 * dependencies otherwise. [Note: hardirq and softirq contexts
+	 * are separated from each other too.]
+	 *
+	 * The following field is used to detect when we cross into an
+	 * interrupt context:
+	 */
+	unsigned int irq_context:2; /* bit 0 - soft, bit 1 - hard */
+	unsigned int trylock:1;						/* 16 bits */
+
+	unsigned int read:2;        /* see lock_acquire() comment */
+	unsigned int check:1;       /* see lock_acquire() comment */
+	unsigned int hardirqs_off:1;
+	unsigned int sync:1;
+	unsigned int references:11;					/* 32 bits */
+	unsigned int pin_count;
+};
+
 #else /* !CONFIG_LOCKDEP */
 
 /*
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index ff217a5ce552..185924c56378 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -171,6 +171,8 @@ LSM_HOOK(int, 0, file_alloc_security, struct file *file)
 LSM_HOOK(void, LSM_RET_VOID, file_free_security, struct file *file)
 LSM_HOOK(int, 0, file_ioctl, struct file *file, unsigned int cmd,
 	 unsigned long arg)
+LSM_HOOK(int, 0, file_ioctl_compat, struct file *file, unsigned int cmd,
+	 unsigned long arg)
 LSM_HOOK(int, 0, mmap_addr, unsigned long addr)
 LSM_HOOK(int, 0, mmap_file, struct file *file, unsigned long reqprot,
 	 unsigned long prot, unsigned long flags)
@@ -262,6 +264,10 @@ LSM_HOOK(int, 0, sem_semop, struct kern_ipc_perm *perm, struct sembuf *sops,
 LSM_HOOK(int, 0, netlink_send, struct sock *sk, struct sk_buff *skb)
 LSM_HOOK(void, LSM_RET_VOID, d_instantiate, struct dentry *dentry,
 	 struct inode *inode)
+LSM_HOOK(int, -EOPNOTSUPP, getselfattr, unsigned int attr,
+	 struct lsm_ctx __user *ctx, size_t *size, u32 flags)
+LSM_HOOK(int, -EOPNOTSUPP, setselfattr, unsigned int attr,
+	 struct lsm_ctx *ctx, size_t size, u32 flags)
 LSM_HOOK(int, -EINVAL, getprocattr, struct task_struct *p, const char *name,
 	 char **value)
 LSM_HOOK(int, -EINVAL, setprocattr, const char *name, void *value, size_t size)
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index dcb5e5b5eb13..a2ade0ffe9e7 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -25,6 +25,7 @@
 #ifndef __LINUX_LSM_HOOKS_H
 #define __LINUX_LSM_HOOKS_H
 
+#include <uapi/linux/lsm.h>
 #include <linux/security.h>
 #include <linux/init.h>
 #include <linux/rculist.h>
@@ -42,6 +43,18 @@ struct security_hook_heads {
 	#undef LSM_HOOK
 } __randomize_layout;
 
+/**
+ * struct lsm_id - Identify a Linux Security Module.
+ * @lsm: name of the LSM, must be approved by the LSM maintainers
+ * @id: LSM ID number from uapi/linux/lsm.h
+ *
+ * Contains the information that identifies the LSM.
+ */
+struct lsm_id {
+	const char	*name;
+	u64		id;
+};
+
 /*
  * Security module hook list structure.
  * For use with generic list macros for common operations.
@@ -50,7 +63,7 @@ struct security_hook_list {
 	struct hlist_node		list;
 	struct hlist_head		*head;
 	union security_list_options	hook;
-	const char			*lsm;
+	const struct lsm_id		*lsmid;
 } __randomize_layout;
 
 /*
@@ -104,7 +117,7 @@ extern struct security_hook_heads security_hook_heads;
 extern char *lsm_names;
 
 extern void security_add_hooks(struct security_hook_list *hooks, int count,
-				const char *lsm);
+			       const struct lsm_id *lsmid);
 
 #define LSM_FLAG_LEGACY_MAJOR	BIT(0)
 #define LSM_FLAG_EXCLUSIVE	BIT(1)
diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h
index d01e850b570f..b3d63123b945 100644
--- a/include/linux/maple_tree.h
+++ b/include/linux/maple_tree.h
@@ -256,6 +256,8 @@ struct maple_tree {
 	struct maple_tree name = MTREE_INIT(name, 0)
 
 #define mtree_lock(mt)		spin_lock((&(mt)->ma_lock))
+#define mtree_lock_nested(mas, subclass) \
+		spin_lock_nested((&(mt)->ma_lock), subclass)
 #define mtree_unlock(mt)	spin_unlock((&(mt)->ma_lock))
 
 /*
@@ -327,6 +329,9 @@ int mtree_store(struct maple_tree *mt, unsigned long index,
 		void *entry, gfp_t gfp);
 void *mtree_erase(struct maple_tree *mt, unsigned long index);
 
+int mtree_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp);
+int __mt_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp);
+
 void mtree_destroy(struct maple_tree *mt);
 void __mt_destroy(struct maple_tree *mt);
 
@@ -345,6 +350,36 @@ static inline bool mtree_empty(const struct maple_tree *mt)
 /* Advanced API */
 
 /*
+ * Maple State Status
+ * ma_active means the maple state is pointing to a node and offset and can
+ * continue operating on the tree.
+ * ma_start means we have not searched the tree.
+ * ma_root means we have searched the tree and the entry we found lives in
+ * the root of the tree (ie it has index 0, length 1 and is the only entry in
+ * the tree).
+ * ma_none means we have searched the tree and there is no node in the
+ * tree for this entry.  For example, we searched for index 1 in an empty
+ * tree.  Or we have a tree which points to a full leaf node and we
+ * searched for an entry which is larger than can be contained in that
+ * leaf node.
+ * ma_pause means the data within the maple state may be stale, restart the
+ * operation
+ * ma_overflow means the search has reached the upper limit of the search
+ * ma_underflow means the search has reached the lower limit of the search
+ * ma_error means there was an error, check the node for the error number.
+ */
+enum maple_status {
+	ma_active,
+	ma_start,
+	ma_root,
+	ma_none,
+	ma_pause,
+	ma_overflow,
+	ma_underflow,
+	ma_error,
+};
+
+/*
  * The maple state is defined in the struct ma_state and is used to keep track
  * of information during operations, and even between operations when using the
  * advanced API.
@@ -376,6 +411,13 @@ static inline bool mtree_empty(const struct maple_tree *mt)
  * When returning a value the maple state index and last respectively contain
  * the start and end of the range for the entry.  Ranges are inclusive in the
  * Maple Tree.
+ *
+ * The status of the state is used to determine how the next action should treat
+ * the state.  For instance, if the status is ma_start then the next action
+ * should start at the root of the tree and walk down.  If the status is
+ * ma_pause then the node may be stale data and should be discarded.  If the
+ * status is ma_overflow, then the last action hit the upper limit.
+ *
  */
 struct ma_state {
 	struct maple_tree *tree;	/* The tree we're operating in */
@@ -385,9 +427,11 @@ struct ma_state {
 	unsigned long min;		/* The minimum index of this node - implied pivot min */
 	unsigned long max;		/* The maximum index of this node - implied pivot max */
 	struct maple_alloc *alloc;	/* Allocated nodes for this operation */
+	enum maple_status status;	/* The status of the state (active, start, none, etc) */
 	unsigned char depth;		/* depth of tree descent during write */
 	unsigned char offset;
 	unsigned char mas_flags;
+	unsigned char end;		/* The end of the node */
 };
 
 struct ma_wr_state {
@@ -397,7 +441,6 @@ struct ma_wr_state {
 	unsigned long r_max;		/* range max */
 	enum maple_type type;		/* mas->node type */
 	unsigned char offset_end;	/* The offset where the write ends */
-	unsigned char node_end;		/* mas->node end */
 	unsigned long *pivots;		/* mas->node->pivots pointer */
 	unsigned long end_piv;		/* The pivot at the offset end */
 	void __rcu **slots;		/* mas->node->slots pointer */
@@ -406,30 +449,16 @@ struct ma_wr_state {
 };
 
 #define mas_lock(mas)           spin_lock(&((mas)->tree->ma_lock))
+#define mas_lock_nested(mas, subclass) \
+		spin_lock_nested(&((mas)->tree->ma_lock), subclass)
 #define mas_unlock(mas)         spin_unlock(&((mas)->tree->ma_lock))
 
-
 /*
  * Special values for ma_state.node.
- * MAS_START means we have not searched the tree.
- * MAS_ROOT means we have searched the tree and the entry we found lives in
- * the root of the tree (ie it has index 0, length 1 and is the only entry in
- * the tree).
- * MAS_NONE means we have searched the tree and there is no node in the
- * tree for this entry.  For example, we searched for index 1 in an empty
- * tree.  Or we have a tree which points to a full leaf node and we
- * searched for an entry which is larger than can be contained in that
- * leaf node.
  * MA_ERROR represents an errno.  After dropping the lock and attempting
  * to resolve the error, the walk would have to be restarted from the
  * top of the tree as the tree may have been modified.
  */
-#define MAS_START	((struct maple_enode *)1UL)
-#define MAS_ROOT	((struct maple_enode *)5UL)
-#define MAS_NONE	((struct maple_enode *)9UL)
-#define MAS_PAUSE	((struct maple_enode *)17UL)
-#define MAS_OVERFLOW	((struct maple_enode *)33UL)
-#define MAS_UNDERFLOW	((struct maple_enode *)65UL)
 #define MA_ERROR(err) \
 		((struct maple_enode *)(((unsigned long)err << 2) | 2UL))
 
@@ -438,7 +467,8 @@ struct ma_wr_state {
 		.tree = mt,						\
 		.index = first,						\
 		.last = end,						\
-		.node = MAS_START,					\
+		.node = NULL,						\
+		.status = ma_start,					\
 		.min = 0,						\
 		.max = ULONG_MAX,					\
 		.alloc = NULL,						\
@@ -469,7 +499,6 @@ void *mas_find_range(struct ma_state *mas, unsigned long max);
 void *mas_find_rev(struct ma_state *mas, unsigned long min);
 void *mas_find_range_rev(struct ma_state *mas, unsigned long max);
 int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp);
-bool mas_is_err(struct ma_state *mas);
 
 bool mas_nomem(struct ma_state *mas, gfp_t gfp);
 void mas_pause(struct ma_state *mas);
@@ -498,28 +527,18 @@ static inline void mas_init(struct ma_state *mas, struct maple_tree *tree,
 	mas->tree = tree;
 	mas->index = mas->last = addr;
 	mas->max = ULONG_MAX;
-	mas->node = MAS_START;
-}
-
-/* Checks if a mas has not found anything */
-static inline bool mas_is_none(const struct ma_state *mas)
-{
-	return mas->node == MAS_NONE;
+	mas->status = ma_start;
+	mas->node = NULL;
 }
 
-/* Checks if a mas has been paused */
-static inline bool mas_is_paused(const struct ma_state *mas)
+static inline bool mas_is_active(struct ma_state *mas)
 {
-	return mas->node == MAS_PAUSE;
+	return mas->status == ma_active;
 }
 
-/* Check if the mas is pointing to a node or not */
-static inline bool mas_is_active(struct ma_state *mas)
+static inline bool mas_is_err(struct ma_state *mas)
 {
-	if ((unsigned long)mas->node >= MAPLE_RESERVED_RANGE)
-		return true;
-
-	return false;
+	return mas->status == ma_error;
 }
 
 /**
@@ -532,9 +551,10 @@ static inline bool mas_is_active(struct ma_state *mas)
  *
  * Context: Any context.
  */
-static inline void mas_reset(struct ma_state *mas)
+static __always_inline void mas_reset(struct ma_state *mas)
 {
-	mas->node = MAS_START;
+	mas->status = ma_start;
+	mas->node = NULL;
 }
 
 /**
@@ -550,6 +570,131 @@ static inline void mas_reset(struct ma_state *mas)
  */
 #define mas_for_each(__mas, __entry, __max) \
 	while (((__entry) = mas_find((__mas), (__max))) != NULL)
+
+#ifdef CONFIG_DEBUG_MAPLE_TREE
+enum mt_dump_format {
+	mt_dump_dec,
+	mt_dump_hex,
+};
+
+extern atomic_t maple_tree_tests_run;
+extern atomic_t maple_tree_tests_passed;
+
+void mt_dump(const struct maple_tree *mt, enum mt_dump_format format);
+void mas_dump(const struct ma_state *mas);
+void mas_wr_dump(const struct ma_wr_state *wr_mas);
+void mt_validate(struct maple_tree *mt);
+void mt_cache_shrink(void);
+#define MT_BUG_ON(__tree, __x) do {					\
+	atomic_inc(&maple_tree_tests_run);				\
+	if (__x) {							\
+		pr_info("BUG at %s:%d (%u)\n",				\
+		__func__, __LINE__, __x);				\
+		mt_dump(__tree, mt_dump_hex);				\
+		pr_info("Pass: %u Run:%u\n",				\
+			atomic_read(&maple_tree_tests_passed),		\
+			atomic_read(&maple_tree_tests_run));		\
+		dump_stack();						\
+	} else {							\
+		atomic_inc(&maple_tree_tests_passed);			\
+	}								\
+} while (0)
+
+#define MAS_BUG_ON(__mas, __x) do {					\
+	atomic_inc(&maple_tree_tests_run);				\
+	if (__x) {							\
+		pr_info("BUG at %s:%d (%u)\n",				\
+		__func__, __LINE__, __x);				\
+		mas_dump(__mas);					\
+		mt_dump((__mas)->tree, mt_dump_hex);			\
+		pr_info("Pass: %u Run:%u\n",				\
+			atomic_read(&maple_tree_tests_passed),		\
+			atomic_read(&maple_tree_tests_run));		\
+		dump_stack();						\
+	} else {							\
+		atomic_inc(&maple_tree_tests_passed);			\
+	}								\
+} while (0)
+
+#define MAS_WR_BUG_ON(__wrmas, __x) do {				\
+	atomic_inc(&maple_tree_tests_run);				\
+	if (__x) {							\
+		pr_info("BUG at %s:%d (%u)\n",				\
+		__func__, __LINE__, __x);				\
+		mas_wr_dump(__wrmas);					\
+		mas_dump((__wrmas)->mas);				\
+		mt_dump((__wrmas)->mas->tree, mt_dump_hex);		\
+		pr_info("Pass: %u Run:%u\n",				\
+			atomic_read(&maple_tree_tests_passed),		\
+			atomic_read(&maple_tree_tests_run));		\
+		dump_stack();						\
+	} else {							\
+		atomic_inc(&maple_tree_tests_passed);			\
+	}								\
+} while (0)
+
+#define MT_WARN_ON(__tree, __x)  ({					\
+	int ret = !!(__x);						\
+	atomic_inc(&maple_tree_tests_run);				\
+	if (ret) {							\
+		pr_info("WARN at %s:%d (%u)\n",				\
+		__func__, __LINE__, __x);				\
+		mt_dump(__tree, mt_dump_hex);				\
+		pr_info("Pass: %u Run:%u\n",				\
+			atomic_read(&maple_tree_tests_passed),		\
+			atomic_read(&maple_tree_tests_run));		\
+		dump_stack();						\
+	} else {							\
+		atomic_inc(&maple_tree_tests_passed);			\
+	}								\
+	unlikely(ret);							\
+})
+
+#define MAS_WARN_ON(__mas, __x) ({					\
+	int ret = !!(__x);						\
+	atomic_inc(&maple_tree_tests_run);				\
+	if (ret) {							\
+		pr_info("WARN at %s:%d (%u)\n",				\
+		__func__, __LINE__, __x);				\
+		mas_dump(__mas);					\
+		mt_dump((__mas)->tree, mt_dump_hex);			\
+		pr_info("Pass: %u Run:%u\n",				\
+			atomic_read(&maple_tree_tests_passed),		\
+			atomic_read(&maple_tree_tests_run));		\
+		dump_stack();						\
+	} else {							\
+		atomic_inc(&maple_tree_tests_passed);			\
+	}								\
+	unlikely(ret);							\
+})
+
+#define MAS_WR_WARN_ON(__wrmas, __x) ({					\
+	int ret = !!(__x);						\
+	atomic_inc(&maple_tree_tests_run);				\
+	if (ret) {							\
+		pr_info("WARN at %s:%d (%u)\n",				\
+		__func__, __LINE__, __x);				\
+		mas_wr_dump(__wrmas);					\
+		mas_dump((__wrmas)->mas);				\
+		mt_dump((__wrmas)->mas->tree, mt_dump_hex);		\
+		pr_info("Pass: %u Run:%u\n",				\
+			atomic_read(&maple_tree_tests_passed),		\
+			atomic_read(&maple_tree_tests_run));		\
+		dump_stack();						\
+	} else {							\
+		atomic_inc(&maple_tree_tests_passed);			\
+	}								\
+	unlikely(ret);							\
+})
+#else
+#define MT_BUG_ON(__tree, __x)		BUG_ON(__x)
+#define MAS_BUG_ON(__mas, __x)		BUG_ON(__x)
+#define MAS_WR_BUG_ON(__mas, __x)	BUG_ON(__x)
+#define MT_WARN_ON(__tree, __x)		WARN_ON(__x)
+#define MAS_WARN_ON(__mas, __x)		WARN_ON(__x)
+#define MAS_WR_WARN_ON(__mas, __x)	WARN_ON(__x)
+#endif /* CONFIG_DEBUG_MAPLE_TREE */
+
 /**
  * __mas_set_range() - Set up Maple Tree operation state to a sub-range of the
  * current location.
@@ -563,6 +708,9 @@ static inline void mas_reset(struct ma_state *mas)
 static inline void __mas_set_range(struct ma_state *mas, unsigned long start,
 		unsigned long last)
 {
+	/* Ensure the range starts within the current slot */
+	MAS_WARN_ON(mas, mas_is_active(mas) &&
+		   (mas->index > start || mas->last < start));
 	mas->index = start;
 	mas->last = last;
 }
@@ -580,8 +728,8 @@ static inline void __mas_set_range(struct ma_state *mas, unsigned long start,
 static inline
 void mas_set_range(struct ma_state *mas, unsigned long start, unsigned long last)
 {
+	mas_reset(mas);
 	__mas_set_range(mas, start, last);
-	mas->node = MAS_START;
 }
 
 /**
@@ -706,129 +854,4 @@ void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max);
 	for (__entry = mt_find(__tree, &(__index), __max); \
 		__entry; __entry = mt_find_after(__tree, &(__index), __max))
 
-
-#ifdef CONFIG_DEBUG_MAPLE_TREE
-enum mt_dump_format {
-	mt_dump_dec,
-	mt_dump_hex,
-};
-
-extern atomic_t maple_tree_tests_run;
-extern atomic_t maple_tree_tests_passed;
-
-void mt_dump(const struct maple_tree *mt, enum mt_dump_format format);
-void mas_dump(const struct ma_state *mas);
-void mas_wr_dump(const struct ma_wr_state *wr_mas);
-void mt_validate(struct maple_tree *mt);
-void mt_cache_shrink(void);
-#define MT_BUG_ON(__tree, __x) do {					\
-	atomic_inc(&maple_tree_tests_run);				\
-	if (__x) {							\
-		pr_info("BUG at %s:%d (%u)\n",				\
-		__func__, __LINE__, __x);				\
-		mt_dump(__tree, mt_dump_hex);				\
-		pr_info("Pass: %u Run:%u\n",				\
-			atomic_read(&maple_tree_tests_passed),		\
-			atomic_read(&maple_tree_tests_run));		\
-		dump_stack();						\
-	} else {							\
-		atomic_inc(&maple_tree_tests_passed);			\
-	}								\
-} while (0)
-
-#define MAS_BUG_ON(__mas, __x) do {					\
-	atomic_inc(&maple_tree_tests_run);				\
-	if (__x) {							\
-		pr_info("BUG at %s:%d (%u)\n",				\
-		__func__, __LINE__, __x);				\
-		mas_dump(__mas);					\
-		mt_dump((__mas)->tree, mt_dump_hex);			\
-		pr_info("Pass: %u Run:%u\n",				\
-			atomic_read(&maple_tree_tests_passed),		\
-			atomic_read(&maple_tree_tests_run));		\
-		dump_stack();						\
-	} else {							\
-		atomic_inc(&maple_tree_tests_passed);			\
-	}								\
-} while (0)
-
-#define MAS_WR_BUG_ON(__wrmas, __x) do {				\
-	atomic_inc(&maple_tree_tests_run);				\
-	if (__x) {							\
-		pr_info("BUG at %s:%d (%u)\n",				\
-		__func__, __LINE__, __x);				\
-		mas_wr_dump(__wrmas);					\
-		mas_dump((__wrmas)->mas);				\
-		mt_dump((__wrmas)->mas->tree, mt_dump_hex);		\
-		pr_info("Pass: %u Run:%u\n",				\
-			atomic_read(&maple_tree_tests_passed),		\
-			atomic_read(&maple_tree_tests_run));		\
-		dump_stack();						\
-	} else {							\
-		atomic_inc(&maple_tree_tests_passed);			\
-	}								\
-} while (0)
-
-#define MT_WARN_ON(__tree, __x)  ({					\
-	int ret = !!(__x);						\
-	atomic_inc(&maple_tree_tests_run);				\
-	if (ret) {							\
-		pr_info("WARN at %s:%d (%u)\n",				\
-		__func__, __LINE__, __x);				\
-		mt_dump(__tree, mt_dump_hex);				\
-		pr_info("Pass: %u Run:%u\n",				\
-			atomic_read(&maple_tree_tests_passed),		\
-			atomic_read(&maple_tree_tests_run));		\
-		dump_stack();						\
-	} else {							\
-		atomic_inc(&maple_tree_tests_passed);			\
-	}								\
-	unlikely(ret);							\
-})
-
-#define MAS_WARN_ON(__mas, __x) ({					\
-	int ret = !!(__x);						\
-	atomic_inc(&maple_tree_tests_run);				\
-	if (ret) {							\
-		pr_info("WARN at %s:%d (%u)\n",				\
-		__func__, __LINE__, __x);				\
-		mas_dump(__mas);					\
-		mt_dump((__mas)->tree, mt_dump_hex);			\
-		pr_info("Pass: %u Run:%u\n",				\
-			atomic_read(&maple_tree_tests_passed),		\
-			atomic_read(&maple_tree_tests_run));		\
-		dump_stack();						\
-	} else {							\
-		atomic_inc(&maple_tree_tests_passed);			\
-	}								\
-	unlikely(ret);							\
-})
-
-#define MAS_WR_WARN_ON(__wrmas, __x) ({					\
-	int ret = !!(__x);						\
-	atomic_inc(&maple_tree_tests_run);				\
-	if (ret) {							\
-		pr_info("WARN at %s:%d (%u)\n",				\
-		__func__, __LINE__, __x);				\
-		mas_wr_dump(__wrmas);					\
-		mas_dump((__wrmas)->mas);				\
-		mt_dump((__wrmas)->mas->tree, mt_dump_hex);		\
-		pr_info("Pass: %u Run:%u\n",				\
-			atomic_read(&maple_tree_tests_passed),		\
-			atomic_read(&maple_tree_tests_run));		\
-		dump_stack();						\
-	} else {							\
-		atomic_inc(&maple_tree_tests_passed);			\
-	}								\
-	unlikely(ret);							\
-})
-#else
-#define MT_BUG_ON(__tree, __x)		BUG_ON(__x)
-#define MAS_BUG_ON(__mas, __x)		BUG_ON(__x)
-#define MAS_WR_BUG_ON(__mas, __x)	BUG_ON(__x)
-#define MT_WARN_ON(__tree, __x)		WARN_ON(__x)
-#define MAS_WARN_ON(__mas, __x)		WARN_ON(__x)
-#define MAS_WR_WARN_ON(__mas, __x)	WARN_ON(__x)
-#endif /* CONFIG_DEBUG_MAPLE_TREE */
-
 #endif /*_LINUX_MAPLE_TREE_H */
diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index 8fa23bdcedbf..79ceee3c8673 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -38,6 +38,7 @@ struct mdio_device {
 	/* Bus address of the MDIO device (0-31) */
 	int addr;
 	int flags;
+	int reset_state;
 	struct gpio_desc *reset_gpio;
 	struct reset_control *reset_ctrl;
 	unsigned int reset_assert_delay;
@@ -420,7 +421,7 @@ static inline u32 linkmode_adv_to_mii_t1_adv_m_t(unsigned long *advertising)
  * A function that translates value of following registers to the linkmode:
  * IEEE 802.3-2018 45.2.3.10 "EEE control and capability 1" register (3.20)
  * IEEE 802.3-2018 45.2.7.13 "EEE advertisement 1" register (7.60)
- * IEEE 802.3-2018 45.2.7.14 "EEE "link partner ability 1 register (7.61)
+ * IEEE 802.3-2018 45.2.7.14 "EEE link partner ability 1" register (7.61)
  */
 static inline void mii_eee_cap1_mod_linkmode_t(unsigned long *adv, u32 val)
 {
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index ae3bde302f70..b695f9e946da 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -123,6 +123,7 @@ int memblock_physmem_add(phys_addr_t base, phys_addr_t size);
 void memblock_trim_memory(phys_addr_t align);
 bool memblock_overlaps_region(struct memblock_type *type,
 			      phys_addr_t base, phys_addr_t size);
+bool memblock_validate_numa_coverage(unsigned long threshold_bytes);
 int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size);
 int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size);
 int memblock_mark_mirror(phys_addr_t base, phys_addr_t size);
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 7bdcf3020d7a..20ff87f8e001 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -219,6 +219,12 @@ struct mem_cgroup {
 
 #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
 	unsigned long zswap_max;
+
+	/*
+	 * Prevent pages from this memcg from being written back from zswap to
+	 * swap, and from being swapped out on zswap store failures.
+	 */
+	bool zswap_writeback;
 #endif
 
 	unsigned long soft_limit;
@@ -324,7 +330,7 @@ struct mem_cgroup {
 	struct deferred_split deferred_split_queue;
 #endif
 
-#ifdef CONFIG_LRU_GEN
+#ifdef CONFIG_LRU_GEN_WALKS_MMU
 	/* per-memcg mm_struct list */
 	struct lru_gen_mm_list mm_list;
 #endif
@@ -821,6 +827,11 @@ static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg)
 	return !memcg || css_tryget(&memcg->css);
 }
 
+static inline bool mem_cgroup_tryget_online(struct mem_cgroup *memcg)
+{
+	return !memcg || css_tryget_online(&memcg->css);
+}
+
 static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 	if (memcg)
@@ -1046,8 +1057,8 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 	return x;
 }
 
-void mem_cgroup_flush_stats(void);
-void mem_cgroup_flush_stats_ratelimited(void);
+void mem_cgroup_flush_stats(struct mem_cgroup *memcg);
+void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg);
 
 void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 			      int val);
@@ -1187,6 +1198,11 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page)
 	return NULL;
 }
 
+static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg)
+{
+	return NULL;
+}
+
 static inline bool folio_memcg_kmem(struct folio *folio)
 {
 	return false;
@@ -1349,6 +1365,11 @@ static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg)
 	return true;
 }
 
+static inline bool mem_cgroup_tryget_online(struct mem_cgroup *memcg)
+{
+	return true;
+}
+
 static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 }
@@ -1548,11 +1569,11 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 	return node_page_state(lruvec_pgdat(lruvec), idx);
 }
 
-static inline void mem_cgroup_flush_stats(void)
+static inline void mem_cgroup_flush_stats(struct mem_cgroup *memcg)
 {
 }
 
-static inline void mem_cgroup_flush_stats_ratelimited(void)
+static inline void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg)
 {
 }
 
@@ -1926,6 +1947,7 @@ static inline void count_objcg_event(struct obj_cgroup *objcg,
 bool obj_cgroup_may_zswap(struct obj_cgroup *objcg);
 void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size);
 void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size);
+bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg);
 #else
 static inline bool obj_cgroup_may_zswap(struct obj_cgroup *objcg)
 {
@@ -1939,6 +1961,11 @@ static inline void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg,
 					     size_t size)
 {
 }
+static inline bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg)
+{
+	/* if zswap is disabled, do not block pages going to the swapping device */
+	return true;
+}
 #endif
 
 #endif /* _LINUX_MEMCONTROL_H */
diff --git a/include/linux/mempool.h b/include/linux/mempool.h
index 4aae6c06c5f2..7be1e32e6d42 100644
--- a/include/linux/mempool.h
+++ b/include/linux/mempool.h
@@ -51,6 +51,7 @@ extern mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn,
 extern int mempool_resize(mempool_t *pool, int new_min_nr);
 extern void mempool_destroy(mempool_t *pool);
 extern void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask) __malloc;
+extern void *mempool_alloc_preallocated(mempool_t *pool) __malloc;
 extern void mempool_free(void *element, mempool_t *pool);
 
 /*
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 1314d9c5f05b..744c830f4b13 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -196,8 +196,6 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 		struct dev_pagemap *pgmap);
 bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn);
 
-unsigned long vmem_altmap_offset(struct vmem_altmap *altmap);
-void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns);
 unsigned long memremap_compat_align(void);
 #else
 static inline void *devm_memremap_pages(struct device *dev,
@@ -228,16 +226,6 @@ static inline bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn)
 	return false;
 }
 
-static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
-{
-	return 0;
-}
-
-static inline void vmem_altmap_free(struct vmem_altmap *altmap,
-		unsigned long nr_pfns)
-{
-}
-
 /* when memremap_pages() is disabled all archs can remap a single page */
 static inline unsigned long memremap_compat_align(void)
 {
diff --git a/include/linux/mii_timestamper.h b/include/linux/mii_timestamper.h
index fa940bbaf8ae..26b04f73f214 100644
--- a/include/linux/mii_timestamper.h
+++ b/include/linux/mii_timestamper.h
@@ -9,6 +9,7 @@
 #include <linux/device.h>
 #include <linux/ethtool.h>
 #include <linux/skbuff.h>
+#include <linux/net_tstamp.h>
 
 struct phy_device;
 
@@ -51,7 +52,8 @@ struct mii_timestamper {
 			 struct sk_buff *skb, int type);
 
 	int  (*hwtstamp)(struct mii_timestamper *mii_ts,
-			 struct ifreq *ifreq);
+			 struct kernel_hwtstamp_config *kernel_config,
+			 struct netlink_ext_ack *extack);
 
 	void (*link_state)(struct mii_timestamper *mii_ts,
 			   struct phy_device *phydev);
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 820bca965fb6..01275c6e8468 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -918,7 +918,7 @@ static inline u8 get_cqe_tls_offload(struct mlx5_cqe64 *cqe)
 	return (cqe->tls_outer_l3_tunneled >> 3) & 0x3;
 }
 
-static inline bool cqe_has_vlan(struct mlx5_cqe64 *cqe)
+static inline bool cqe_has_vlan(const struct mlx5_cqe64 *cqe)
 {
 	return cqe->l4_l3_hdr_type & 0x1;
 }
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index d2b8d4a74a30..7ee5b79ff3d6 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -150,6 +150,7 @@ enum {
 	MLX5_REG_MTPPSE		 = 0x9054,
 	MLX5_REG_MTUTC		 = 0x9055,
 	MLX5_REG_MPEGC		 = 0x9056,
+	MLX5_REG_MPIR		 = 0x9059,
 	MLX5_REG_MCQS		 = 0x9060,
 	MLX5_REG_MCQI		 = 0x9061,
 	MLX5_REG_MCC		 = 0x9062,
@@ -678,6 +679,8 @@ struct mlx5e_resources {
 		struct mlx5_td             td;
 		u32			   mkey;
 		struct mlx5_sq_bfreg       bfreg;
+#define MLX5_MAX_NUM_TC 8
+		u32                        tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC];
 	} hw_objs;
 	struct net_device *uplink_netdev;
 	struct mutex uplink_netdev_lock;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6f3631425f38..fee20fc010c2 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -435,7 +435,7 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8         flow_table_modify[0x1];
 	u8         reformat[0x1];
 	u8         decap[0x1];
-	u8         reserved_at_9[0x1];
+	u8         reset_root_to_default[0x1];
 	u8         pop_vlan[0x1];
 	u8         push_vlan[0x1];
 	u8         reserved_at_c[0x1];
@@ -621,7 +621,7 @@ struct mlx5_ifc_fte_match_set_misc_bits {
 
 	u8         reserved_at_140[0x8];
 	u8         bth_dst_qp[0x18];
-	u8	   reserved_at_160[0x20];
+	u8	   inner_esp_spi[0x20];
 	u8	   outer_esp_spi[0x20];
 	u8         reserved_at_1a0[0x60];
 };
@@ -1801,7 +1801,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         disable_local_lb_uc[0x1];
 	u8         disable_local_lb_mc[0x1];
 	u8         log_min_hairpin_wq_data_sz[0x5];
-	u8         reserved_at_3e8[0x2];
+	u8         reserved_at_3e8[0x1];
+	u8         silent_mode[0x1];
 	u8         vhca_state[0x1];
 	u8         log_max_vlan_list[0x5];
 	u8         reserved_at_3f0[0x3];
@@ -1818,7 +1819,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         reserved_at_460[0x1];
 	u8         ats[0x1];
-	u8         reserved_at_462[0x1];
+	u8         cross_vhca_rqt[0x1];
 	u8         log_max_uctx[0x5];
 	u8         reserved_at_468[0x1];
 	u8         crypto[0x1];
@@ -1943,6 +1944,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 enum {
 	MLX5_CROSS_VHCA_OBJ_TO_OBJ_SUPPORTED_LOCAL_FLOW_TABLE_TO_REMOTE_FLOW_TABLE_MISS  = 0x80000,
+	MLX5_CROSS_VHCA_OBJ_TO_OBJ_SUPPORTED_LOCAL_FLOW_TABLE_ROOT_TO_REMOTE_FLOW_TABLE  = (1ULL << 20),
 };
 
 enum {
@@ -1992,7 +1994,11 @@ struct mlx5_ifc_cmd_hca_cap_2_bits {
 	u8	   reserved_at_260[0x120];
 	u8	   reserved_at_380[0x10];
 	u8	   ec_vf_vport_base[0x10];
-	u8	   reserved_at_3a0[0x460];
+
+	u8	   reserved_at_3a0[0x10];
+	u8	   max_rqt_vhca_id[0x10];
+
+	u8	   reserved_at_3c0[0x440];
 };
 
 enum mlx5_ifc_flow_destination_type {
@@ -2151,6 +2157,13 @@ struct mlx5_ifc_rq_num_bits {
 	u8         rq_num[0x18];
 };
 
+struct mlx5_ifc_rq_vhca_bits {
+	u8         reserved_at_0[0x8];
+	u8         rq_num[0x18];
+	u8         reserved_at_20[0x10];
+	u8         rq_vhca_id[0x10];
+};
+
 struct mlx5_ifc_mac_address_layout_bits {
 	u8         reserved_at_0[0x10];
 	u8         mac_addr_47_32[0x10];
@@ -3901,7 +3914,10 @@ struct mlx5_ifc_rqtc_bits {
 
 	u8    reserved_at_e0[0x6a0];
 
-	struct mlx5_ifc_rq_num_bits rq_num[];
+	union {
+		DECLARE_FLEX_ARRAY(struct mlx5_ifc_rq_num_bits, rq_num);
+		DECLARE_FLEX_ARRAY(struct mlx5_ifc_rq_vhca_bits, rq_vhca);
+	};
 };
 
 enum {
@@ -4744,7 +4760,10 @@ struct mlx5_ifc_set_l2_table_entry_in_bits {
 
 	u8         reserved_at_c0[0x20];
 
-	u8         reserved_at_e0[0x13];
+	u8         reserved_at_e0[0x10];
+	u8         silent_mode_valid[0x1];
+	u8         silent_mode[0x1];
+	u8         reserved_at_f2[0x1];
 	u8         vlan_valid[0x1];
 	u8         vlan[0xc];
 
@@ -10089,6 +10108,20 @@ struct mlx5_ifc_mpegc_reg_bits {
 	u8         reserved_at_60[0x100];
 };
 
+struct mlx5_ifc_mpir_reg_bits {
+	u8         sdm[0x1];
+	u8         reserved_at_1[0x1b];
+	u8         host_buses[0x4];
+
+	u8         reserved_at_20[0x20];
+
+	u8         local_port[0x8];
+	u8         reserved_at_28[0x15];
+	u8         sd_group[0x3];
+
+	u8         reserved_at_60[0x20];
+};
+
 enum {
 	MLX5_MTUTC_FREQ_ADJ_UNITS_PPB          = 0x0,
 	MLX5_MTUTC_FREQ_ADJ_UNITS_SCALED_PPM   = 0x1,
@@ -10103,7 +10136,10 @@ enum {
 struct mlx5_ifc_mtutc_reg_bits {
 	u8         reserved_at_0[0x5];
 	u8         freq_adj_units[0x3];
-	u8         reserved_at_8[0x14];
+	u8         reserved_at_8[0x3];
+	u8         log_max_freq_adjustment[0x5];
+
+	u8         reserved_at_10[0xc];
 	u8         operation[0x4];
 
 	u8         freq_adjustment[0x20];
@@ -12001,6 +12037,13 @@ enum {
 	MLX5_IPSEC_ASO_INC_SN            = 0x2,
 };
 
+enum {
+	MLX5_IPSEC_ASO_REPLAY_WIN_32BIT  = 0x0,
+	MLX5_IPSEC_ASO_REPLAY_WIN_64BIT  = 0x1,
+	MLX5_IPSEC_ASO_REPLAY_WIN_128BIT = 0x2,
+	MLX5_IPSEC_ASO_REPLAY_WIN_256BIT = 0x3,
+};
+
 struct mlx5_ifc_ipsec_aso_bits {
 	u8         valid[0x1];
 	u8         reserved_at_201[0x1];
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 418d26608ece..f5a97dec5169 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -886,8 +886,8 @@ static inline bool vma_is_anonymous(struct vm_area_struct *vma)
  */
 static inline bool vma_is_initial_heap(const struct vm_area_struct *vma)
 {
-       return vma->vm_start <= vma->vm_mm->brk &&
-		vma->vm_end >= vma->vm_mm->start_brk;
+	return vma->vm_start < vma->vm_mm->brk &&
+		vma->vm_end > vma->vm_mm->start_brk;
 }
 
 /*
@@ -901,8 +901,8 @@ static inline bool vma_is_initial_stack(const struct vm_area_struct *vma)
 	 * its "stack".  It's not even well-defined for programs written
 	 * languages like Go.
 	 */
-       return vma->vm_start <= vma->vm_mm->start_stack &&
-	       vma->vm_end >= vma->vm_mm->start_stack;
+	return vma->vm_start <= vma->vm_mm->start_stack &&
+		vma->vm_end >= vma->vm_mm->start_stack;
 }
 
 static inline bool vma_is_temporary_stack(struct vm_area_struct *vma)
@@ -994,6 +994,17 @@ static inline int vma_iter_bulk_alloc(struct vma_iterator *vmi,
 	return mas_expected_entries(&vmi->mas, count);
 }
 
+static inline int vma_iter_clear_gfp(struct vma_iterator *vmi,
+			unsigned long start, unsigned long end, gfp_t gfp)
+{
+	__mas_set_range(&vmi->mas, start, end - 1);
+	mas_store_gfp(&vmi->mas, NULL, gfp);
+	if (unlikely(mas_is_err(&vmi->mas)))
+		return -ENOMEM;
+
+	return 0;
+}
+
 /* Free any unused preallocations */
 static inline void vma_iter_free(struct vma_iterator *vmi)
 {
@@ -1804,7 +1815,7 @@ static inline void vma_set_access_pid_bit(struct vm_area_struct *vma)
 
 static inline u8 page_kasan_tag(const struct page *page)
 {
-	u8 tag = 0xff;
+	u8 tag = KASAN_TAG_KERNEL;
 
 	if (kasan_enabled()) {
 		tag = (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK;
@@ -1833,7 +1844,7 @@ static inline void page_kasan_tag_set(struct page *page, u8 tag)
 static inline void page_kasan_tag_reset(struct page *page)
 {
 	if (kasan_enabled())
-		page_kasan_tag_set(page, 0xff);
+		page_kasan_tag_set(page, KASAN_TAG_KERNEL);
 }
 
 #else /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */
@@ -1953,15 +1964,15 @@ static inline bool page_maybe_dma_pinned(struct page *page)
  *
  * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq.
  */
-static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
-					  struct page *page)
+static inline bool folio_needs_cow_for_dma(struct vm_area_struct *vma,
+					  struct folio *folio)
 {
 	VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1));
 
 	if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags))
 		return false;
 
-	return page_maybe_dma_pinned(page);
+	return folio_maybe_dma_pinned(folio);
 }
 
 /**
@@ -2373,7 +2384,8 @@ extern void truncate_pagecache(struct inode *inode, loff_t new);
 extern void truncate_setsize(struct inode *inode, loff_t newsize);
 void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to);
 void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end);
-int generic_error_remove_page(struct address_space *mapping, struct page *page);
+int generic_error_remove_folio(struct address_space *mapping,
+		struct folio *folio);
 
 struct vm_area_struct *lock_mm_and_find_vma(struct mm_struct *mm,
 		unsigned long address, struct pt_regs *regs);
@@ -3859,6 +3871,32 @@ void vmemmap_free(unsigned long start, unsigned long end,
 		struct vmem_altmap *altmap);
 #endif
 
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
+{
+	/* number of pfns from base where pfn_to_page() is valid */
+	if (altmap)
+		return altmap->reserve + altmap->free;
+	return 0;
+}
+
+static inline void vmem_altmap_free(struct vmem_altmap *altmap,
+				    unsigned long nr_pfns)
+{
+	altmap->alloc -= nr_pfns;
+}
+#else
+static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
+{
+	return 0;
+}
+
+static inline void vmem_altmap_free(struct vmem_altmap *altmap,
+				    unsigned long nr_pfns)
+{
+}
+#endif
+
 #define VMEMMAP_RESERVE_NR	2
 #ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP
 static inline bool __vmemmap_can_optimize(struct vmem_altmap *altmap,
@@ -3904,6 +3942,7 @@ enum mf_flags {
 	MF_UNPOISON = 1 << 4,
 	MF_SW_SIMULATED = 1 << 5,
 	MF_NO_RETRY = 1 << 6,
+	MF_MEM_PRE_REMOVE = 1 << 7,
 };
 int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
 		      unsigned long count, int mf_flags);
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 9ae7def16cb2..f4fe593c1400 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -232,22 +232,27 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio,
 	if (folio_test_unevictable(folio) || !lrugen->enabled)
 		return false;
 	/*
-	 * There are three common cases for this page:
-	 * 1. If it's hot, e.g., freshly faulted in or previously hot and
-	 *    migrated, add it to the youngest generation.
-	 * 2. If it's cold but can't be evicted immediately, i.e., an anon page
-	 *    not in swapcache or a dirty page pending writeback, add it to the
-	 *    second oldest generation.
-	 * 3. Everything else (clean, cold) is added to the oldest generation.
+	 * There are four common cases for this page:
+	 * 1. If it's hot, i.e., freshly faulted in, add it to the youngest
+	 *    generation, and it's protected over the rest below.
+	 * 2. If it can't be evicted immediately, i.e., a dirty page pending
+	 *    writeback, add it to the second youngest generation.
+	 * 3. If it should be evicted first, e.g., cold and clean from
+	 *    folio_rotate_reclaimable(), add it to the oldest generation.
+	 * 4. Everything else falls between 2 & 3 above and is added to the
+	 *    second oldest generation if it's considered inactive, or the
+	 *    oldest generation otherwise. See lru_gen_is_active().
 	 */
 	if (folio_test_active(folio))
 		seq = lrugen->max_seq;
 	else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) ||
 		 (folio_test_reclaim(folio) &&
 		  (folio_test_dirty(folio) || folio_test_writeback(folio))))
-		seq = lrugen->min_seq[type] + 1;
-	else
+		seq = lrugen->max_seq - 1;
+	else if (reclaiming || lrugen->min_seq[type] + MIN_NR_GENS >= lrugen->max_seq)
 		seq = lrugen->min_seq[type];
+	else
+		seq = lrugen->min_seq[type] + 1;
 
 	gen = lru_gen_from_seq(seq);
 	flags = (gen + 1UL) << LRU_GEN_PGOFF;
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 957ce38768b2..b2d3a88a34d1 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -125,7 +125,7 @@ struct page {
 			struct page_pool *pp;
 			unsigned long _pp_mapping_pad;
 			unsigned long dma_addr;
-			atomic_long_t pp_frag_count;
+			atomic_long_t pp_ref_count;
 		};
 		struct {	/* Tail pages of compound page */
 			unsigned long compound_head;	/* Bit zero is set */
@@ -401,11 +401,11 @@ FOLIO_MATCH(compound_head, _head_2a);
  * @pmd_huge_pte:     Protected by ptdesc->ptl, used for THPs.
  * @__page_mapping:   Aliases with page->mapping. Unused for page tables.
  * @pt_mm:            Used for x86 pgds.
- * @pt_frag_refcount: For fragmented page table tracking. Powerpc and s390 only.
+ * @pt_frag_refcount: For fragmented page table tracking. Powerpc only.
  * @_pt_pad_2:        Padding to ensure proper alignment.
  * @ptl:              Lock for the page table.
  * @__page_type:      Same as page->page_type. Unused for page tables.
- * @_refcount:        Same as page refcount. Used for s390 page tables.
+ * @__page_refcount:  Same as page refcount.
  * @pt_memcg_data:    Memcg data. Tracked for page tables here.
  *
  * This struct overlays struct page for now. Do not modify without a good
@@ -438,7 +438,7 @@ struct ptdesc {
 #endif
 	};
 	unsigned int __page_type;
-	atomic_t _refcount;
+	atomic_t __page_refcount;
 #ifdef CONFIG_MEMCG
 	unsigned long pt_memcg_data;
 #endif
@@ -452,7 +452,7 @@ TABLE_MATCH(compound_head, _pt_pad_1);
 TABLE_MATCH(mapping, __page_mapping);
 TABLE_MATCH(rcu_head, pt_rcu_head);
 TABLE_MATCH(page_type, __page_type);
-TABLE_MATCH(_refcount, _refcount);
+TABLE_MATCH(_refcount, __page_refcount);
 #ifdef CONFIG_MEMCG
 TABLE_MATCH(memcg_data, pt_memcg_data);
 #endif
@@ -600,6 +600,9 @@ struct vma_numab_state {
 	 */
 	unsigned long pids_active[2];
 
+	/* MM scan sequence ID when scan first started after VMA creation */
+	int start_scan_seq;
+
 	/*
 	 * MM scan sequence ID when the VMA was last completely scanned.
 	 * A VMA is not eligible for scanning if prev_scan_seq == numa_scan_seq
@@ -958,7 +961,7 @@ struct mm_struct {
 		 */
 		unsigned long ksm_zero_pages;
 #endif /* CONFIG_KSM */
-#ifdef CONFIG_LRU_GEN
+#ifdef CONFIG_LRU_GEN_WALKS_MMU
 		struct {
 			/* this mm_struct is on lru_gen_mm_list */
 			struct list_head list;
@@ -973,7 +976,7 @@ struct mm_struct {
 			struct mem_cgroup *memcg;
 #endif
 		} lru_gen;
-#endif /* CONFIG_LRU_GEN */
+#endif /* CONFIG_LRU_GEN_WALKS_MMU */
 	} __randomize_layout;
 
 	/*
@@ -1011,11 +1014,13 @@ struct lru_gen_mm_list {
 	spinlock_t lock;
 };
 
+#endif /* CONFIG_LRU_GEN */
+
+#ifdef CONFIG_LRU_GEN_WALKS_MMU
+
 void lru_gen_add_mm(struct mm_struct *mm);
 void lru_gen_del_mm(struct mm_struct *mm);
-#ifdef CONFIG_MEMCG
 void lru_gen_migrate_mm(struct mm_struct *mm);
-#endif
 
 static inline void lru_gen_init_mm(struct mm_struct *mm)
 {
@@ -1036,7 +1041,7 @@ static inline void lru_gen_use_mm(struct mm_struct *mm)
 	WRITE_ONCE(mm->lru_gen.bitmap, -1);
 }
 
-#else /* !CONFIG_LRU_GEN */
+#else /* !CONFIG_LRU_GEN_WALKS_MMU */
 
 static inline void lru_gen_add_mm(struct mm_struct *mm)
 {
@@ -1046,11 +1051,9 @@ static inline void lru_gen_del_mm(struct mm_struct *mm)
 {
 }
 
-#ifdef CONFIG_MEMCG
 static inline void lru_gen_migrate_mm(struct mm_struct *mm)
 {
 }
-#endif
 
 static inline void lru_gen_init_mm(struct mm_struct *mm)
 {
@@ -1060,7 +1063,7 @@ static inline void lru_gen_use_mm(struct mm_struct *mm)
 {
 }
 
-#endif /* CONFIG_LRU_GEN */
+#endif /* CONFIG_LRU_GEN_WALKS_MMU */
 
 struct vma_iterator {
 	struct ma_state mas;
@@ -1071,7 +1074,8 @@ struct vma_iterator {
 		.mas = {						\
 			.tree = &(__mm)->mm_mt,				\
 			.index = __addr,				\
-			.node = MAS_START,				\
+			.node = NULL,					\
+			.status = ma_start,				\
 		},							\
 	}
 
diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h
index aa44fff8bb9d..a2f6179b672b 100644
--- a/include/linux/mm_types_task.h
+++ b/include/linux/mm_types_task.h
@@ -9,9 +9,6 @@
  */
 
 #include <linux/types.h>
-#include <linux/threads.h>
-#include <linux/atomic.h>
-#include <linux/cpumask.h>
 
 #include <asm/page.h>
 
@@ -36,6 +33,8 @@ enum {
 	NR_MM_COUNTERS
 };
 
+struct page;
+
 struct page_frag {
 	struct page *page;
 #if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 3c25226beeed..4ed33b127821 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -22,18 +22,21 @@
 #include <linux/mm_types.h>
 #include <linux/page-flags.h>
 #include <linux/local_lock.h>
+#include <linux/zswap.h>
 #include <asm/page.h>
 
 /* Free memory management - zoned buddy allocator.  */
 #ifndef CONFIG_ARCH_FORCE_MAX_ORDER
-#define MAX_ORDER 10
+#define MAX_PAGE_ORDER 10
 #else
-#define MAX_ORDER CONFIG_ARCH_FORCE_MAX_ORDER
+#define MAX_PAGE_ORDER CONFIG_ARCH_FORCE_MAX_ORDER
 #endif
-#define MAX_ORDER_NR_PAGES (1 << MAX_ORDER)
+#define MAX_ORDER_NR_PAGES (1 << MAX_PAGE_ORDER)
 
 #define IS_MAX_ORDER_ALIGNED(pfn) IS_ALIGNED(pfn, MAX_ORDER_NR_PAGES)
 
+#define NR_PAGE_ORDERS (MAX_PAGE_ORDER + 1)
+
 /*
  * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed
  * costly to service.  That is between allocation orders which should
@@ -95,7 +98,7 @@ static inline bool migratetype_is_mergeable(int mt)
 }
 
 #define for_each_migratetype_order(order, type) \
-	for (order = 0; order <= MAX_ORDER; order++) \
+	for (order = 0; order < NR_PAGE_ORDERS; order++) \
 		for (type = 0; type < MIGRATE_TYPES; type++)
 
 extern int page_group_by_mobility_disabled;
@@ -207,6 +210,10 @@ enum node_stat_item {
 	PGPROMOTE_SUCCESS,	/* promote successfully */
 	PGPROMOTE_CANDIDATE,	/* candidate pages to promote */
 #endif
+	/* PGDEMOTE_*: pages demoted */
+	PGDEMOTE_KSWAPD,
+	PGDEMOTE_DIRECT,
+	PGDEMOTE_KHUGEPAGED,
 	NR_VM_NODE_STAT_ITEMS
 };
 
@@ -435,14 +442,12 @@ struct lru_gen_folio {
 	atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
 	/* whether the multi-gen LRU is enabled */
 	bool enabled;
-#ifdef CONFIG_MEMCG
 	/* the memcg generation this lru_gen_folio belongs to */
 	u8 gen;
 	/* the list segment this lru_gen_folio belongs to */
 	u8 seg;
 	/* per-node lru_gen_folio list for global reclaim */
 	struct hlist_nulls_node list;
-#endif
 };
 
 enum {
@@ -488,11 +493,6 @@ struct lru_gen_mm_walk {
 	bool force_scan;
 };
 
-void lru_gen_init_lruvec(struct lruvec *lruvec);
-void lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
-
-#ifdef CONFIG_MEMCG
-
 /*
  * For each node, memcgs are divided into two generations: the old and the
  * young. For each generation, memcgs are randomly sharded into multiple bins
@@ -505,33 +505,37 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
  * the old generation, is incremented when all its bins become empty.
  *
  * There are four operations:
- * 1. MEMCG_LRU_HEAD, which moves an memcg to the head of a random bin in its
+ * 1. MEMCG_LRU_HEAD, which moves a memcg to the head of a random bin in its
  *    current generation (old or young) and updates its "seg" to "head";
- * 2. MEMCG_LRU_TAIL, which moves an memcg to the tail of a random bin in its
+ * 2. MEMCG_LRU_TAIL, which moves a memcg to the tail of a random bin in its
  *    current generation (old or young) and updates its "seg" to "tail";
- * 3. MEMCG_LRU_OLD, which moves an memcg to the head of a random bin in the old
+ * 3. MEMCG_LRU_OLD, which moves a memcg to the head of a random bin in the old
  *    generation, updates its "gen" to "old" and resets its "seg" to "default";
- * 4. MEMCG_LRU_YOUNG, which moves an memcg to the tail of a random bin in the
+ * 4. MEMCG_LRU_YOUNG, which moves a memcg to the tail of a random bin in the
  *    young generation, updates its "gen" to "young" and resets its "seg" to
  *    "default".
  *
  * The events that trigger the above operations are:
  * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD;
- * 2. The first attempt to reclaim an memcg below low, which triggers
+ * 2. The first attempt to reclaim a memcg below low, which triggers
  *    MEMCG_LRU_TAIL;
- * 3. The first attempt to reclaim an memcg below reclaimable size threshold,
- *    which triggers MEMCG_LRU_TAIL;
- * 4. The second attempt to reclaim an memcg below reclaimable size threshold,
- *    which triggers MEMCG_LRU_YOUNG;
- * 5. Attempting to reclaim an memcg below min, which triggers MEMCG_LRU_YOUNG;
+ * 3. The first attempt to reclaim a memcg offlined or below reclaimable size
+ *    threshold, which triggers MEMCG_LRU_TAIL;
+ * 4. The second attempt to reclaim a memcg offlined or below reclaimable size
+ *    threshold, which triggers MEMCG_LRU_YOUNG;
+ * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG;
  * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG;
- * 7. Offlining an memcg, which triggers MEMCG_LRU_OLD.
+ * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD.
  *
- * Note that memcg LRU only applies to global reclaim, and the round-robin
- * incrementing of their max_seq counters ensures the eventual fairness to all
- * eligible memcgs. For memcg reclaim, it still relies on mem_cgroup_iter().
+ * Notes:
+ * 1. Memcg LRU only applies to global reclaim, and the round-robin incrementing
+ *    of their max_seq counters ensures the eventual fairness to all eligible
+ *    memcgs. For memcg reclaim, it still relies on mem_cgroup_iter().
+ * 2. There are only two valid generations: old (seq) and young (seq+1).
+ *    MEMCG_NR_GENS is set to three so that when reading the generation counter
+ *    locklessly, a stale value (seq-1) does not wraparound to young.
  */
-#define MEMCG_NR_GENS	2
+#define MEMCG_NR_GENS	3
 #define MEMCG_NR_BINS	8
 
 struct lru_gen_memcg {
@@ -546,6 +550,8 @@ struct lru_gen_memcg {
 };
 
 void lru_gen_init_pgdat(struct pglist_data *pgdat);
+void lru_gen_init_lruvec(struct lruvec *lruvec);
+void lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
 
 void lru_gen_init_memcg(struct mem_cgroup *memcg);
 void lru_gen_exit_memcg(struct mem_cgroup *memcg);
@@ -554,19 +560,6 @@ void lru_gen_offline_memcg(struct mem_cgroup *memcg);
 void lru_gen_release_memcg(struct mem_cgroup *memcg);
 void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid);
 
-#else /* !CONFIG_MEMCG */
-
-#define MEMCG_NR_GENS	1
-
-struct lru_gen_memcg {
-};
-
-static inline void lru_gen_init_pgdat(struct pglist_data *pgdat)
-{
-}
-
-#endif /* CONFIG_MEMCG */
-
 #else /* !CONFIG_LRU_GEN */
 
 static inline void lru_gen_init_pgdat(struct pglist_data *pgdat)
@@ -581,8 +574,6 @@ static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 {
 }
 
-#ifdef CONFIG_MEMCG
-
 static inline void lru_gen_init_memcg(struct mem_cgroup *memcg)
 {
 }
@@ -607,8 +598,6 @@ static inline void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid)
 {
 }
 
-#endif /* CONFIG_MEMCG */
-
 #endif /* CONFIG_LRU_GEN */
 
 struct lruvec {
@@ -631,12 +620,15 @@ struct lruvec {
 #ifdef CONFIG_LRU_GEN
 	/* evictable pages divided into generations */
 	struct lru_gen_folio		lrugen;
+#ifdef CONFIG_LRU_GEN_WALKS_MMU
 	/* to concurrently iterate lru_gen_mm_list */
 	struct lru_gen_mm_state		mm_state;
 #endif
+#endif /* CONFIG_LRU_GEN */
 #ifdef CONFIG_MEMCG
 	struct pglist_data *pgdat;
 #endif
+	struct zswap_lruvec_state zswap_lruvec_state;
 };
 
 /* Isolate for asynchronous migration */
@@ -943,10 +935,10 @@ struct zone {
 	CACHELINE_PADDING(_pad1_);
 
 	/* free areas of different sizes */
-	struct free_area	free_area[MAX_ORDER + 1];
+	struct free_area	free_area[NR_PAGE_ORDERS];
 
 #ifdef CONFIG_UNACCEPTED_MEMORY
-	/* Pages to be accepted. All pages on the list are MAX_ORDER */
+	/* Pages to be accepted. All pages on the list are MAX_PAGE_ORDER */
 	struct list_head	unaccepted_pages;
 #endif
 
@@ -1756,8 +1748,8 @@ static inline bool movable_only_nodes(nodemask_t *nodes)
 #define SECTION_BLOCKFLAGS_BITS \
 	((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS)
 
-#if (MAX_ORDER + PAGE_SHIFT) > SECTION_SIZE_BITS
-#error Allocator MAX_ORDER exceeds SECTION_SIZE
+#if (MAX_PAGE_ORDER + PAGE_SHIFT) > SECTION_SIZE_BITS
+#error Allocator MAX_PAGE_ORDER exceeds SECTION_SIZE
 #endif
 
 static inline unsigned long pfn_to_section_nr(unsigned long pfn)
@@ -1789,6 +1781,7 @@ static inline unsigned long section_nr_to_pfn(unsigned long sec)
 #define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK)
 
 struct mem_section_usage {
+	struct rcu_head rcu;
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 	DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION);
 #endif
@@ -1982,7 +1975,7 @@ static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
 {
 	int idx = subsection_map_index(pfn);
 
-	return test_bit(idx, ms->usage->subsection_map);
+	return test_bit(idx, READ_ONCE(ms->usage)->subsection_map);
 }
 #else
 static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
@@ -2006,6 +1999,7 @@ static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
 static inline int pfn_valid(unsigned long pfn)
 {
 	struct mem_section *ms;
+	int ret;
 
 	/*
 	 * Ensure the upper PAGE_SHIFT bits are clear in the
@@ -2019,13 +2013,19 @@ static inline int pfn_valid(unsigned long pfn)
 	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
 		return 0;
 	ms = __pfn_to_section(pfn);
-	if (!valid_section(ms))
+	rcu_read_lock();
+	if (!valid_section(ms)) {
+		rcu_read_unlock();
 		return 0;
+	}
 	/*
 	 * Traditionally early sections always returned pfn_valid() for
 	 * the entire section-sized span.
 	 */
-	return early_section(ms) || pfn_section_valid(ms, pfn);
+	ret = early_section(ms) || pfn_section_valid(ms, pfn);
+	rcu_read_unlock();
+
+	return ret;
 }
 #endif
 
diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h
index b8da2db4ecd2..cd4d5c8781f5 100644
--- a/include/linux/mnt_idmapping.h
+++ b/include/linux/mnt_idmapping.h
@@ -244,7 +244,4 @@ static inline kgid_t mapped_fsgid(struct mnt_idmap *idmap,
 	return from_vfsgid(idmap, fs_userns, VFSGIDT_INIT(current_fsgid()));
 }
 
-bool check_fsmapping(const struct mnt_idmap *idmap,
-		     const struct super_block *sb);
-
 #endif /* _LINUX_MNT_IDMAPPING_H */
diff --git a/include/linux/module.h b/include/linux/module.h
index a98e188cf37b..96bc462872c0 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -540,6 +540,8 @@ struct module {
 	struct static_call_site *static_call_sites;
 #endif
 #if IS_ENABLED(CONFIG_KUNIT)
+	int num_kunit_init_suites;
+	struct kunit_suite **kunit_init_suites;
 	int num_kunit_suites;
 	struct kunit_suite **kunit_suites;
 #endif
@@ -668,7 +670,7 @@ extern void __module_get(struct module *module);
  * @module: the module we should check for
  *
  * Only try to get a module reference count if the module is not being removed.
- * This call will fail if the module is already being removed.
+ * This call will fail if the module is in the process of being removed.
  *
  * Care must also be taken to ensure the module exists and is alive prior to
  * usage of this call. This can be gauranteed through two means:
diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 4fa9726bc328..bfb85fd13e1f 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -385,6 +385,8 @@ extern bool parameq(const char *name1, const char *name2);
  */
 extern bool parameqn(const char *name1, const char *name2, size_t n);
 
+typedef int (*parse_unknown_fn)(char *param, char *val, const char *doing, void *arg);
+
 /* Called on module insert or kernel boot */
 extern char *parse_args(const char *name,
 		      char *args,
@@ -392,9 +394,7 @@ extern char *parse_args(const char *name,
 		      unsigned num,
 		      s16 level_min,
 		      s16 level_max,
-		      void *arg,
-		      int (*unknown)(char *param, char *val,
-				     const char *doing, void *arg));
+		      void *arg, parse_unknown_fn unknown);
 
 /* Called by module remove. */
 #ifdef CONFIG_SYSFS
diff --git a/include/linux/mount.h b/include/linux/mount.h
index ac3dd2876197..c34c18b4e8f3 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -50,8 +50,7 @@ struct path;
 #define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME )
 
 #define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \
-			    MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | \
-			    MNT_CURSOR)
+			    MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | MNT_ONRB)
 
 #define MNT_INTERNAL	0x4000
 
@@ -65,7 +64,7 @@ struct path;
 #define MNT_SYNC_UMOUNT		0x2000000
 #define MNT_MARKED		0x4000000
 #define MNT_UMOUNT		0x8000000
-#define MNT_CURSOR		0x10000000
+#define MNT_ONRB		0x10000000
 
 struct vfsmount {
 	struct dentry *mnt_root;	/* root of the mounted tree */
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index c29ace15a053..e84522e31301 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1003,6 +1003,8 @@ struct nand_op_parser {
 /**
  * struct nand_operation - NAND operation descriptor
  * @cs: the CS line to select for this NAND operation
+ * @deassert_wp: set to true when the operation requires the WP pin to be
+ *		 de-asserted (ERASE, PROG, ...)
  * @instrs: array of instructions to execute
  * @ninstrs: length of the @instrs array
  *
@@ -1010,6 +1012,7 @@ struct nand_op_parser {
  */
 struct nand_operation {
 	unsigned int cs;
+	bool deassert_wp;
 	const struct nand_op_instr *instrs;
 	unsigned int ninstrs;
 };
@@ -1021,6 +1024,14 @@ struct nand_operation {
 		.ninstrs = ARRAY_SIZE(_instrs),			\
 	}
 
+#define NAND_DESTRUCTIVE_OPERATION(_cs, _instrs)		\
+	{							\
+		.cs = _cs,					\
+		.deassert_wp = true,				\
+		.instrs = _instrs,				\
+		.ninstrs = ARRAY_SIZE(_instrs),			\
+	}
+
 int nand_op_parser_exec_op(struct nand_chip *chip,
 			   const struct nand_op_parser *parser,
 			   const struct nand_operation *op, bool check_only);
@@ -1104,6 +1115,7 @@ struct nand_controller_ops {
  *			the bus without restarting an entire read operation nor
  *			changing the column.
  * @supported_op.cont_read: The controller supports sequential cache reads.
+ * @controller_wp:	the controller is in charge of handling the WP pin.
  */
 struct nand_controller {
 	struct mutex lock;
@@ -1112,6 +1124,7 @@ struct nand_controller {
 		unsigned int data_only_read: 1;
 		unsigned int cont_read: 1;
 	} supported_op;
+	bool controller_wp;
 };
 
 static inline void nand_controller_init(struct nand_controller *nfc)
@@ -1265,6 +1278,7 @@ struct nand_secure_region {
  * @cont_read: Sequential page read internals
  * @cont_read.ongoing: Whether a continuous read is ongoing or not
  * @cont_read.first_page: Start of the continuous read operation
+ * @cont_read.pause_page: End of the current sequential cache read operation
  * @cont_read.last_page: End of the continuous read operation
  * @controller: The hardware controller	structure which is shared among multiple
  *              independent devices
@@ -1321,6 +1335,7 @@ struct nand_chip {
 	struct {
 		bool ongoing;
 		unsigned int first_page;
+		unsigned int pause_page;
 		unsigned int last_page;
 	} cont_read;
 
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index a33aa9eb9fc3..7e208d46ba5b 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -20,6 +20,7 @@
 #include <linux/osq_lock.h>
 #include <linux/debug_locks.h>
 #include <linux/cleanup.h>
+#include <linux/mutex_types.h>
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # define __DEP_MAP_MUTEX_INITIALIZER(lockname)			\
@@ -33,49 +34,6 @@
 
 #ifndef CONFIG_PREEMPT_RT
 
-/*
- * Simple, straightforward mutexes with strict semantics:
- *
- * - only one task can hold the mutex at a time
- * - only the owner can unlock the mutex
- * - multiple unlocks are not permitted
- * - recursive locking is not permitted
- * - a mutex object must be initialized via the API
- * - a mutex object must not be initialized via memset or copying
- * - task may not exit with mutex held
- * - memory areas where held locks reside must not be freed
- * - held mutexes must not be reinitialized
- * - mutexes may not be used in hardware or software interrupt
- *   contexts such as tasklets and timers
- *
- * These semantics are fully enforced when DEBUG_MUTEXES is
- * enabled. Furthermore, besides enforcing the above rules, the mutex
- * debugging code also implements a number of additional features
- * that make lock debugging easier and faster:
- *
- * - uses symbolic names of mutexes, whenever they are printed in debug output
- * - point-of-acquire tracking, symbolic lookup of function names
- * - list of all locks held in the system, printout of them
- * - owner tracking
- * - detects self-recursing locks and prints out all relevant info
- * - detects multi-task circular deadlocks and prints out all affected
- *   locks and tasks (and only those tasks)
- */
-struct mutex {
-	atomic_long_t		owner;
-	raw_spinlock_t		wait_lock;
-#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
-	struct optimistic_spin_queue osq; /* Spinner MCS lock */
-#endif
-	struct list_head	wait_list;
-#ifdef CONFIG_DEBUG_MUTEXES
-	void			*magic;
-#endif
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map	dep_map;
-#endif
-};
-
 #ifdef CONFIG_DEBUG_MUTEXES
 
 #define __DEBUG_MUTEX_INITIALIZER(lockname)				\
@@ -131,14 +89,6 @@ extern bool mutex_is_locked(struct mutex *lock);
 /*
  * Preempt-RT variant based on rtmutexes.
  */
-#include <linux/rtmutex.h>
-
-struct mutex {
-	struct rt_mutex_base	rtmutex;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map	dep_map;
-#endif
-};
 
 #define __MUTEX_INITIALIZER(mutexname)					\
 {									\
@@ -221,6 +171,7 @@ extern void mutex_unlock(struct mutex *lock);
 extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
 
 DEFINE_GUARD(mutex, struct mutex *, mutex_lock(_T), mutex_unlock(_T))
-DEFINE_FREE(mutex, struct mutex *, if (_T) mutex_unlock(_T))
+DEFINE_GUARD_COND(mutex, _try, mutex_trylock(_T))
+DEFINE_GUARD_COND(mutex, _intr, mutex_lock_interruptible(_T) == 0)
 
 #endif /* __LINUX_MUTEX_H */
diff --git a/include/linux/mutex_types.h b/include/linux/mutex_types.h
new file mode 100644
index 000000000000..fdf7f515fde8
--- /dev/null
+++ b/include/linux/mutex_types.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_MUTEX_TYPES_H
+#define __LINUX_MUTEX_TYPES_H
+
+#include <linux/atomic.h>
+#include <linux/lockdep_types.h>
+#include <linux/osq_lock.h>
+#include <linux/spinlock_types.h>
+#include <linux/types.h>
+
+#ifndef CONFIG_PREEMPT_RT
+
+/*
+ * Simple, straightforward mutexes with strict semantics:
+ *
+ * - only one task can hold the mutex at a time
+ * - only the owner can unlock the mutex
+ * - multiple unlocks are not permitted
+ * - recursive locking is not permitted
+ * - a mutex object must be initialized via the API
+ * - a mutex object must not be initialized via memset or copying
+ * - task may not exit with mutex held
+ * - memory areas where held locks reside must not be freed
+ * - held mutexes must not be reinitialized
+ * - mutexes may not be used in hardware or software interrupt
+ *   contexts such as tasklets and timers
+ *
+ * These semantics are fully enforced when DEBUG_MUTEXES is
+ * enabled. Furthermore, besides enforcing the above rules, the mutex
+ * debugging code also implements a number of additional features
+ * that make lock debugging easier and faster:
+ *
+ * - uses symbolic names of mutexes, whenever they are printed in debug output
+ * - point-of-acquire tracking, symbolic lookup of function names
+ * - list of all locks held in the system, printout of them
+ * - owner tracking
+ * - detects self-recursing locks and prints out all relevant info
+ * - detects multi-task circular deadlocks and prints out all affected
+ *   locks and tasks (and only those tasks)
+ */
+struct mutex {
+	atomic_long_t		owner;
+	raw_spinlock_t		wait_lock;
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
+	struct optimistic_spin_queue osq; /* Spinner MCS lock */
+#endif
+	struct list_head	wait_list;
+#ifdef CONFIG_DEBUG_MUTEXES
+	void			*magic;
+#endif
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+};
+
+#else /* !CONFIG_PREEMPT_RT */
+/*
+ * Preempt-RT variant based on rtmutexes.
+ */
+#include <linux/rtmutex.h>
+
+struct mutex {
+	struct rt_mutex_base	rtmutex;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+};
+
+#endif /* CONFIG_PREEMPT_RT */
+
+#endif /* __LINUX_MUTEX_TYPES_H */
diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h
index ed42bd5f639f..0aa4411528fc 100644
--- a/include/linux/net/intel/i40e_client.h
+++ b/include/linux/net/intel/i40e_client.h
@@ -45,7 +45,7 @@ struct i40e_qv_info {
 
 struct i40e_qvlist_info {
 	u32 num_vectors;
-	struct i40e_qv_info qv_info[];
+	struct i40e_qv_info qv_info[] __counted_by(num_vectors);
 };
 
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index a16c9cc063fe..118c40258d07 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -382,6 +382,7 @@ struct napi_struct {
 	/* control-path-only fields follow */
 	struct list_head	dev_list;
 	struct hlist_node	napi_hash_node;
+	int			irq;
 };
 
 enum {
@@ -665,6 +666,10 @@ struct netdev_queue {
 #ifdef CONFIG_XDP_SOCKETS
 	struct xsk_buff_pool    *pool;
 #endif
+	/* NAPI instance for the queue
+	 * Readers and writers must hold RTNL
+	 */
+	struct napi_struct      *napi;
 /*
  * write-mostly part
  */
@@ -1324,6 +1329,9 @@ struct netdev_net_notifier {
  * int (*ndo_mdb_del)(struct net_device *dev, struct nlattr *tb[],
  *		      struct netlink_ext_ack *extack);
  *	Deletes the MDB entry from dev.
+ * int (*ndo_mdb_del_bulk)(struct net_device *dev, struct nlattr *tb[],
+ *			   struct netlink_ext_ack *extack);
+ *	Bulk deletes MDB entries from dev.
  * int (*ndo_mdb_dump)(struct net_device *dev, struct sk_buff *skb,
  *		       struct netlink_callback *cb);
  *	Dumps MDB entries from dev. The first argument (marker) in the netlink
@@ -1606,6 +1614,9 @@ struct net_device_ops {
 	int			(*ndo_mdb_del)(struct net_device *dev,
 					       struct nlattr *tb[],
 					       struct netlink_ext_ack *extack);
+	int			(*ndo_mdb_del_bulk)(struct net_device *dev,
+						    struct nlattr *tb[],
+						    struct netlink_ext_ack *extack);
 	int			(*ndo_mdb_dump)(struct net_device *dev,
 						struct sk_buff *skb,
 						struct netlink_callback *cb);
@@ -1797,6 +1808,13 @@ enum netdev_ml_priv_type {
 	ML_PRIV_CAN,
 };
 
+enum netdev_stat_type {
+	NETDEV_PCPU_STAT_NONE,
+	NETDEV_PCPU_STAT_LSTATS, /* struct pcpu_lstats */
+	NETDEV_PCPU_STAT_TSTATS, /* struct pcpu_sw_netstats */
+	NETDEV_PCPU_STAT_DSTATS, /* struct pcpu_dstats */
+};
+
 /**
  *	struct net_device - The DEVICE structure.
  *
@@ -1858,6 +1876,7 @@ enum netdev_ml_priv_type {
  *	@netdev_ops:	Includes several pointers to callbacks,
  *			if one wants to override the ndo_*() functions
  *	@xdp_metadata_ops:	Includes pointers to XDP metadata callbacks.
+ *	@xsk_tx_metadata_ops:	Includes pointers to AF_XDP TX metadata callbacks.
  *	@ethtool_ops:	Management operations
  *	@l3mdev_ops:	Layer 3 master device operations
  *	@ndisc_ops:	Includes callbacks for different IPv6 neighbour
@@ -1991,10 +2010,14 @@ enum netdev_ml_priv_type {
  *
  * 	@ml_priv:	Mid-layer private
  *	@ml_priv_type:  Mid-layer private type
- * 	@lstats:	Loopback statistics
- * 	@tstats:	Tunnel statistics
- * 	@dstats:	Dummy statistics
- * 	@vstats:	Virtual ethernet statistics
+ *
+ *	@pcpu_stat_type:	Type of device statistics which the core should
+ *				allocate/free: none, lstats, tstats, dstats. none
+ *				means the driver is handling statistics allocation/
+ *				freeing internally.
+ *	@lstats:		Loopback statistics: packets, bytes
+ *	@tstats:		Tunnel statistics: RX/TX packets, RX/TX bytes
+ *	@dstats:		Dummy statistics: RX/TX/drop packets, RX/TX bytes
  *
  *	@garp_port:	GARP
  *	@mrp_port:	MRP
@@ -2080,6 +2103,72 @@ enum netdev_ml_priv_type {
  */
 
 struct net_device {
+	/* Cacheline organization can be found documented in
+	 * Documentation/networking/net_cachelines/net_device.rst.
+	 * Please update the document when adding new fields.
+	 */
+
+	/* TX read-mostly hotpath */
+	__cacheline_group_begin(net_device_read_tx);
+	unsigned long long	priv_flags;
+	const struct net_device_ops *netdev_ops;
+	const struct header_ops *header_ops;
+	struct netdev_queue	*_tx;
+	netdev_features_t	gso_partial_features;
+	unsigned int		real_num_tx_queues;
+	unsigned int		gso_max_size;
+	unsigned int		gso_ipv4_max_size;
+	u16			gso_max_segs;
+	s16			num_tc;
+	/* Note : dev->mtu is often read without holding a lock.
+	 * Writers usually hold RTNL.
+	 * It is recommended to use READ_ONCE() to annotate the reads,
+	 * and to use WRITE_ONCE() to annotate the writes.
+	 */
+	unsigned int		mtu;
+	unsigned short		needed_headroom;
+	struct netdev_tc_txq	tc_to_txq[TC_MAX_QUEUE];
+#ifdef CONFIG_XPS
+	struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX];
+#endif
+#ifdef CONFIG_NETFILTER_EGRESS
+	struct nf_hook_entries __rcu *nf_hooks_egress;
+#endif
+#ifdef CONFIG_NET_XGRESS
+	struct bpf_mprog_entry __rcu *tcx_egress;
+#endif
+	__cacheline_group_end(net_device_read_tx);
+
+	/* TXRX read-mostly hotpath */
+	__cacheline_group_begin(net_device_read_txrx);
+	unsigned int		flags;
+	unsigned short		hard_header_len;
+	netdev_features_t	features;
+	struct inet6_dev __rcu	*ip6_ptr;
+	__cacheline_group_end(net_device_read_txrx);
+
+	/* RX read-mostly hotpath */
+	__cacheline_group_begin(net_device_read_rx);
+	struct bpf_prog __rcu	*xdp_prog;
+	struct list_head	ptype_specific;
+	int			ifindex;
+	unsigned int		real_num_rx_queues;
+	struct netdev_rx_queue	*_rx;
+	unsigned long		gro_flush_timeout;
+	int			napi_defer_hard_irqs;
+	unsigned int		gro_max_size;
+	unsigned int		gro_ipv4_max_size;
+	rx_handler_func_t __rcu	*rx_handler;
+	void __rcu		*rx_handler_data;
+	possible_net_t			nd_net;
+#ifdef CONFIG_NETPOLL
+	struct netpoll_info __rcu	*npinfo;
+#endif
+#ifdef CONFIG_NET_XGRESS
+	struct bpf_mprog_entry __rcu *tcx_ingress;
+#endif
+	__cacheline_group_end(net_device_read_rx);
+
 	char			name[IFNAMSIZ];
 	struct netdev_name_node	*name_node;
 	struct dev_ifalias	__rcu *ifalias;
@@ -2104,7 +2193,6 @@ struct net_device {
 	struct list_head	unreg_list;
 	struct list_head	close_list;
 	struct list_head	ptype_all;
-	struct list_head	ptype_specific;
 
 	struct {
 		struct list_head upper;
@@ -2112,31 +2200,18 @@ struct net_device {
 	} adj_list;
 
 	/* Read-mostly cache-line for fast-path access */
-	unsigned int		flags;
 	xdp_features_t		xdp_features;
-	unsigned long long	priv_flags;
-	const struct net_device_ops *netdev_ops;
 	const struct xdp_metadata_ops *xdp_metadata_ops;
-	int			ifindex;
+	const struct xsk_tx_metadata_ops *xsk_tx_metadata_ops;
 	unsigned short		gflags;
-	unsigned short		hard_header_len;
 
-	/* Note : dev->mtu is often read without holding a lock.
-	 * Writers usually hold RTNL.
-	 * It is recommended to use READ_ONCE() to annotate the reads,
-	 * and to use WRITE_ONCE() to annotate the writes.
-	 */
-	unsigned int		mtu;
-	unsigned short		needed_headroom;
 	unsigned short		needed_tailroom;
 
-	netdev_features_t	features;
 	netdev_features_t	hw_features;
 	netdev_features_t	wanted_features;
 	netdev_features_t	vlan_features;
 	netdev_features_t	hw_enc_features;
 	netdev_features_t	mpls_features;
-	netdev_features_t	gso_partial_features;
 
 	unsigned int		min_mtu;
 	unsigned int		max_mtu;
@@ -2174,8 +2249,6 @@ struct net_device {
 	const struct tlsdev_ops *tlsdev_ops;
 #endif
 
-	const struct header_ops *header_ops;
-
 	unsigned char		operstate;
 	unsigned char		link_mode;
 
@@ -2216,9 +2289,7 @@ struct net_device {
 
 
 	/* Protocol-specific pointers */
-
 	struct in_device __rcu	*ip_ptr;
-	struct inet6_dev __rcu	*ip6_ptr;
 #if IS_ENABLED(CONFIG_VLAN_8021Q)
 	struct vlan_info __rcu	*vlan_info;
 #endif
@@ -2253,26 +2324,13 @@ struct net_device {
 	/* Interface address info used in eth_type_trans() */
 	const unsigned char	*dev_addr;
 
-	struct netdev_rx_queue	*_rx;
 	unsigned int		num_rx_queues;
-	unsigned int		real_num_rx_queues;
-
-	struct bpf_prog __rcu	*xdp_prog;
-	unsigned long		gro_flush_timeout;
-	int			napi_defer_hard_irqs;
 #define GRO_LEGACY_MAX_SIZE	65536u
 /* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE),
  * and shinfo->gso_segs is a 16bit field.
  */
 #define GRO_MAX_SIZE		(8 * 65535u)
-	unsigned int		gro_max_size;
-	unsigned int		gro_ipv4_max_size;
 	unsigned int		xdp_zc_max_segs;
-	rx_handler_func_t __rcu	*rx_handler;
-	void __rcu		*rx_handler_data;
-#ifdef CONFIG_NET_XGRESS
-	struct bpf_mprog_entry __rcu *tcx_ingress;
-#endif
 	struct netdev_queue __rcu *ingress_queue;
 #ifdef CONFIG_NETFILTER_INGRESS
 	struct nf_hook_entries __rcu *nf_hooks_ingress;
@@ -2287,25 +2345,13 @@ struct net_device {
 /*
  * Cache lines mostly used on transmit path
  */
-	struct netdev_queue	*_tx ____cacheline_aligned_in_smp;
 	unsigned int		num_tx_queues;
-	unsigned int		real_num_tx_queues;
 	struct Qdisc __rcu	*qdisc;
 	unsigned int		tx_queue_len;
 	spinlock_t		tx_global_lock;
 
 	struct xdp_dev_bulk_queue __percpu *xdp_bulkq;
 
-#ifdef CONFIG_XPS
-	struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX];
-#endif
-#ifdef CONFIG_NET_XGRESS
-	struct bpf_mprog_entry __rcu *tcx_egress;
-#endif
-#ifdef CONFIG_NETFILTER_EGRESS
-	struct nf_hook_entries __rcu *nf_hooks_egress;
-#endif
-
 #ifdef CONFIG_NET_SCHED
 	DECLARE_HASHTABLE	(qdisc_hash, 4);
 #endif
@@ -2344,16 +2390,11 @@ struct net_device {
 	bool needs_free_netdev;
 	void (*priv_destructor)(struct net_device *dev);
 
-#ifdef CONFIG_NETPOLL
-	struct netpoll_info __rcu	*npinfo;
-#endif
-
-	possible_net_t			nd_net;
-
 	/* mid-layer private */
 	void				*ml_priv;
 	enum netdev_ml_priv_type	ml_priv_type;
 
+	enum netdev_stat_type		pcpu_stat_type:8;
 	union {
 		struct pcpu_lstats __percpu		*lstats;
 		struct pcpu_sw_netstats __percpu	*tstats;
@@ -2383,20 +2424,15 @@ struct net_device {
  */
 #define GSO_MAX_SIZE		(8 * GSO_MAX_SEGS)
 
-	unsigned int		gso_max_size;
 #define TSO_LEGACY_MAX_SIZE	65536
 #define TSO_MAX_SIZE		UINT_MAX
 	unsigned int		tso_max_size;
-	u16			gso_max_segs;
 #define TSO_MAX_SEGS		U16_MAX
 	u16			tso_max_segs;
-	unsigned int		gso_ipv4_max_size;
 
 #ifdef CONFIG_DCB
 	const struct dcbnl_rtnl_ops *dcbnl_ops;
 #endif
-	s16			num_tc;
-	struct netdev_tc_txq	tc_to_txq[TC_MAX_QUEUE];
 	u8			prio_tc_map[TC_BITMASK + 1];
 
 #if IS_ENABLED(CONFIG_FCOE)
@@ -2435,6 +2471,10 @@ struct net_device {
 #if IS_ENABLED(CONFIG_DPLL)
 	struct dpll_pin		*dpll_pin;
 #endif
+#if IS_ENABLED(CONFIG_PAGE_POOL)
+	/** @page_pools: page pools created for this netdevice */
+	struct hlist_head	page_pools;
+#endif
 };
 #define to_net_dev(d) container_of(d, struct net_device, dev)
 
@@ -2639,6 +2679,15 @@ static inline void *netdev_priv(const struct net_device *dev)
  */
 #define SET_NETDEV_DEVTYPE(net, devtype)	((net)->dev.type = (devtype))
 
+void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index,
+			  enum netdev_queue_type type,
+			  struct napi_struct *napi);
+
+static inline void netif_napi_set_irq(struct napi_struct *napi, int irq)
+{
+	napi->irq = irq;
+}
+
 /* Default NAPI poll() weight
  * Device drivers are strongly advised to not use bigger value
  */
@@ -2755,6 +2804,16 @@ struct pcpu_sw_netstats {
 	struct u64_stats_sync   syncp;
 } __aligned(4 * sizeof(u64));
 
+struct pcpu_dstats {
+	u64			rx_packets;
+	u64			rx_bytes;
+	u64			rx_drops;
+	u64			tx_packets;
+	u64			tx_bytes;
+	u64			tx_drops;
+	struct u64_stats_sync	syncp;
+} __aligned(8 * sizeof(u64));
+
 struct pcpu_lstats {
 	u64_stats_t packets;
 	u64_stats_t bytes;
@@ -3942,6 +4001,9 @@ int generic_hwtstamp_get_lower(struct net_device *dev,
 int generic_hwtstamp_set_lower(struct net_device *dev,
 			       struct kernel_hwtstamp_config *kernel_cfg,
 			       struct netlink_ext_ack *extack);
+int dev_set_hwtstamp_phylib(struct net_device *dev,
+			    struct kernel_hwtstamp_config *cfg,
+			    struct netlink_ext_ack *extack);
 int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *userdata);
 unsigned int dev_get_flags(const struct net_device *);
 int __dev_change_flags(struct net_device *dev, unsigned int flags,
@@ -4174,6 +4236,15 @@ static inline void netdev_ref_replace(struct net_device *odev,
 void linkwatch_fire_event(struct net_device *dev);
 
 /**
+ * linkwatch_sync_dev - sync linkwatch for the given device
+ * @dev: network device to sync linkwatch for
+ *
+ * Sync linkwatch for the given device, removing it from the
+ * pending work list (if queued).
+ */
+void linkwatch_sync_dev(struct net_device *dev);
+
+/**
  *	netif_carrier_ok - test if carrier present
  *	@dev: network device
  *
diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h
index 7834c0be2831..61aa48f46dd7 100644
--- a/include/linux/netfilter_ipv6.h
+++ b/include/linux/netfilter_ipv6.h
@@ -51,7 +51,7 @@ struct nf_ipv6_ops {
 	u32 (*cookie_init_sequence)(const struct ipv6hdr *iph,
 				    const struct tcphdr *th, u16 *mssp);
 	int (*cookie_v6_check)(const struct ipv6hdr *iph,
-			       const struct tcphdr *th, __u32 cookie);
+			       const struct tcphdr *th);
 #endif
 	void (*route_input)(struct sk_buff *skb);
 	int (*fragment)(struct net *net, struct sock *sk, struct sk_buff *skb,
@@ -179,16 +179,16 @@ static inline u32 nf_ipv6_cookie_init_sequence(const struct ipv6hdr *iph,
 }
 
 static inline int nf_cookie_v6_check(const struct ipv6hdr *iph,
-				     const struct tcphdr *th, __u32 cookie)
+				     const struct tcphdr *th)
 {
 #if IS_ENABLED(CONFIG_SYN_COOKIES)
 #if IS_MODULE(CONFIG_IPV6)
 	const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops();
 
 	if (v6_ops)
-		return v6_ops->cookie_v6_check(iph, th, cookie);
+		return v6_ops->cookie_v6_check(iph, th);
 #elif IS_BUILTIN(CONFIG_IPV6)
-	return __cookie_v6_check(iph, th, cookie);
+	return __cookie_v6_check(iph, th);
 #endif
 #endif
 	return 0;
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 75d7de34c908..1a4445bf2ab9 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -228,10 +228,12 @@ bool netlink_strict_get_check(struct sk_buff *skb);
 int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock);
 int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid,
 		      __u32 group, gfp_t allocation);
+
+typedef int (*netlink_filter_fn)(struct sock *dsk, struct sk_buff *skb, void *data);
+
 int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb,
 			       __u32 portid, __u32 group, gfp_t allocation,
-			       int (*filter)(struct sock *dsk,
-					     struct sk_buff *skb, void *data),
+			       netlink_filter_fn filter,
 			       void *filter_data);
 int netlink_set_err(struct sock *ssk, __u32 portid, __u32 group, int code);
 int netlink_register_notifier(struct notifier_block *nb);
@@ -351,5 +353,6 @@ bool netlink_ns_capable(const struct sk_buff *skb,
 			struct user_namespace *ns, int cap);
 bool netlink_capable(const struct sk_buff *skb, int cap);
 bool netlink_net_capable(const struct sk_buff *skb, int cap);
+struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast);
 
 #endif	/* __LINUX_NETLINK_H */
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index c11c4db34639..ef8d2d618d5b 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -869,4 +869,26 @@ enum {
 	RCA4_TYPE_MASK_OTHER_LAYOUT_MAX	= 15,
 };
 
+enum nfs_cb_opnum4 {
+	OP_CB_GETATTR = 3,
+	OP_CB_RECALL  = 4,
+
+	/* Callback operations new to NFSv4.1 */
+	OP_CB_LAYOUTRECALL  = 5,
+	OP_CB_NOTIFY        = 6,
+	OP_CB_PUSH_DELEG    = 7,
+	OP_CB_RECALL_ANY    = 8,
+	OP_CB_RECALLABLE_OBJ_AVAIL = 9,
+	OP_CB_RECALL_SLOT   = 10,
+	OP_CB_SEQUENCE      = 11,
+	OP_CB_WANTS_CANCELLED = 12,
+	OP_CB_NOTIFY_LOCK   = 13,
+	OP_CB_NOTIFY_DEVICEID = 14,
+
+	/* Callback operations new to NFSv4.2 */
+	OP_CB_OFFLOAD = 15,
+
+	OP_CB_ILLEGAL = 10044,
+};
+
 #endif
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 279262057a92..f5ce7b101146 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -595,7 +595,6 @@ extern void nfs_complete_unlink(struct dentry *dentry, struct inode *);
  * linux/fs/nfs/write.c
  */
 extern int  nfs_congestion_kb;
-extern int  nfs_writepage(struct page *page, struct writeback_control *wbc);
 extern int  nfs_writepages(struct address_space *, struct writeback_control *);
 extern int  nfs_flush_incompatible(struct file *file, struct folio *folio);
 extern int  nfs_update_folio(struct file *file, struct folio *folio,
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 8d07116caaf1..b61438313a73 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -93,10 +93,10 @@
 #include <linux/threads.h>
 #include <linux/bitmap.h>
 #include <linux/minmax.h>
+#include <linux/nodemask_types.h>
 #include <linux/numa.h>
 #include <linux/random.h>
 
-typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t;
 extern nodemask_t _unused_nodemask_arg_;
 
 /**
diff --git a/include/linux/nodemask_types.h b/include/linux/nodemask_types.h
new file mode 100644
index 000000000000..6b28d97ea6ed
--- /dev/null
+++ b/include/linux/nodemask_types.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_NODEMASK_TYPES_H
+#define __LINUX_NODEMASK_TYPES_H
+
+#include <linux/bitops.h>
+#include <linux/numa.h>
+
+typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t;
+
+#endif /* __LINUX_NODEMASK_TYPES_H */
diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h
index 771cb0285872..5601d14e2886 100644
--- a/include/linux/nsproxy.h
+++ b/include/linux/nsproxy.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_NSPROXY_H
 #define _LINUX_NSPROXY_H
 
+#include <linux/refcount.h>
 #include <linux/spinlock.h>
 #include <linux/sched.h>
 
diff --git a/include/linux/nubus.h b/include/linux/nubus.h
index bdcd85e622d8..4d103ac8f5c7 100644
--- a/include/linux/nubus.h
+++ b/include/linux/nubus.h
@@ -89,8 +89,6 @@ struct nubus_driver {
 	void (*remove)(struct nubus_board *board);
 };
 
-extern struct bus_type nubus_bus_type;
-
 /* Generic NuBus interface functions, modelled after the PCI interface */
 #ifdef CONFIG_PROC_FS
 extern bool nubus_populate_procfs;
diff --git a/include/linux/numa.h b/include/linux/numa.h
index a904861de800..915033a75731 100644
--- a/include/linux/numa.h
+++ b/include/linux/numa.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_NUMA_H
 #define _LINUX_NUMA_H
+#include <linux/init.h>
 #include <linux/types.h>
 
 #ifdef CONFIG_NODES_SHIFT
@@ -22,34 +23,26 @@
 #endif
 
 #ifdef CONFIG_NUMA
-#include <linux/printk.h>
 #include <asm/sparsemem.h>
 
 /* Generic implementation available */
 int numa_nearest_node(int node, unsigned int state);
 
 #ifndef memory_add_physaddr_to_nid
-static inline int memory_add_physaddr_to_nid(u64 start)
-{
-	pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n",
-			start);
-	return 0;
-}
+int memory_add_physaddr_to_nid(u64 start);
 #endif
+
 #ifndef phys_to_target_node
-static inline int phys_to_target_node(u64 start)
-{
-	pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n",
-			start);
-	return 0;
-}
+int phys_to_target_node(u64 start);
 #endif
+
 #ifndef numa_fill_memblks
 static inline int __init numa_fill_memblks(u64 start, u64 end)
 {
 	return NUMA_NO_MEMBLK;
 }
 #endif
+
 #else /* !CONFIG_NUMA */
 static inline int numa_nearest_node(int node, unsigned int state)
 {
diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h
index 5581dbd3bd34..ea8fb31379e3 100644
--- a/include/linux/osq_lock.h
+++ b/include/linux/osq_lock.h
@@ -6,11 +6,6 @@
  * An MCS like lock especially tailored for optimistic spinning for sleeping
  * lock implementations (mutex, rwsem, etc).
  */
-struct optimistic_spin_node {
-	struct optimistic_spin_node *next, *prev;
-	int locked; /* 1 if lock acquired */
-	int cpu; /* encoded CPU # + 1 value */
-};
 
 struct optimistic_spin_queue {
 	/*
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index a88e64acebfe..735cddc13d20 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -772,19 +772,14 @@ static __always_inline void SetPageUptodate(struct page *page)
 
 CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL)
 
-bool __folio_start_writeback(struct folio *folio, bool keep_write);
-bool set_page_writeback(struct page *page);
+void __folio_start_writeback(struct folio *folio, bool keep_write);
+void set_page_writeback(struct page *page);
 
 #define folio_start_writeback(folio)			\
 	__folio_start_writeback(folio, false)
 #define folio_start_writeback_keepwrite(folio)	\
 	__folio_start_writeback(folio, true)
 
-static inline bool test_set_page_writeback(struct page *page)
-{
-	return set_page_writeback(page);
-}
-
 static __always_inline bool folio_test_head(struct folio *folio)
 {
 	return test_bit(PG_head, folio_flags(folio, FOLIO_PF_ANY));
diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h
index e83c4c095041..3f2409b968ec 100644
--- a/include/linux/pageblock-flags.h
+++ b/include/linux/pageblock-flags.h
@@ -41,14 +41,14 @@ extern unsigned int pageblock_order;
  * Huge pages are a constant size, but don't exceed the maximum allocation
  * granularity.
  */
-#define pageblock_order		min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_ORDER)
+#define pageblock_order		min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_PAGE_ORDER)
 
 #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
 
 #else /* CONFIG_HUGETLB_PAGE */
 
 /* If huge pages are not used, group by MAX_ORDER_NR_PAGES */
-#define pageblock_order		MAX_ORDER
+#define pageblock_order		MAX_PAGE_ORDER
 
 #endif /* CONFIG_HUGETLB_PAGE */
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index bcc1ea44b4e8..06142ff7f9ce 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -204,6 +204,8 @@ enum mapping_flags {
 	AS_NO_WRITEBACK_TAGS = 5,
 	AS_LARGE_FOLIO_SUPPORT = 6,
 	AS_RELEASE_ALWAYS,	/* Call ->release_folio(), even if no private data */
+	AS_STABLE_WRITES,	/* must wait for writeback before modifying
+				   folio contents */
 };
 
 /**
@@ -289,6 +291,21 @@ static inline void mapping_clear_release_always(struct address_space *mapping)
 	clear_bit(AS_RELEASE_ALWAYS, &mapping->flags);
 }
 
+static inline bool mapping_stable_writes(const struct address_space *mapping)
+{
+	return test_bit(AS_STABLE_WRITES, &mapping->flags);
+}
+
+static inline void mapping_set_stable_writes(struct address_space *mapping)
+{
+	set_bit(AS_STABLE_WRITES, &mapping->flags);
+}
+
+static inline void mapping_clear_stable_writes(struct address_space *mapping)
+{
+	clear_bit(AS_STABLE_WRITES, &mapping->flags);
+}
+
 static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
 {
 	return mapping->gfp_mask;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 60ca768bc867..58a4c976c39b 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1239,6 +1239,8 @@ int pci_read_config_dword(const struct pci_dev *dev, int where, u32 *val);
 int pci_write_config_byte(const struct pci_dev *dev, int where, u8 val);
 int pci_write_config_word(const struct pci_dev *dev, int where, u16 val);
 int pci_write_config_dword(const struct pci_dev *dev, int where, u32 val);
+void pci_clear_and_set_config_dword(const struct pci_dev *dev, int pos,
+				    u32 clear, u32 set);
 
 int pcie_capability_read_word(struct pci_dev *dev, int pos, u16 *val);
 int pcie_capability_read_dword(struct pci_dev *dev, int pos, u32 *val);
@@ -1829,6 +1831,7 @@ extern bool pcie_ports_native;
 int pci_disable_link_state(struct pci_dev *pdev, int state);
 int pci_disable_link_state_locked(struct pci_dev *pdev, int state);
 int pci_enable_link_state(struct pci_dev *pdev, int state);
+int pci_enable_link_state_locked(struct pci_dev *pdev, int state);
 void pcie_no_aspm(void);
 bool pcie_aspm_support_enabled(void);
 bool pcie_aspm_enabled(struct pci_dev *pdev);
@@ -1839,6 +1842,8 @@ static inline int pci_disable_link_state_locked(struct pci_dev *pdev, int state)
 { return 0; }
 static inline int pci_enable_link_state(struct pci_dev *pdev, int state)
 { return 0; }
+static inline int pci_enable_link_state_locked(struct pci_dev *pdev, int state)
+{ return 0; }
 static inline void pcie_no_aspm(void) { }
 static inline bool pcie_aspm_support_enabled(void) { return false; }
 static inline bool pcie_aspm_enabled(struct pci_dev *pdev) { return false; }
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 275799b5f535..844ffdac8d7d 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2605,6 +2605,8 @@
 #define PCI_VENDOR_ID_TEKRAM		0x1de1
 #define PCI_DEVICE_ID_TEKRAM_DC290	0xdc29
 
+#define PCI_VENDOR_ID_ALIBABA		0x1ded
+
 #define PCI_VENDOR_ID_TEHUTI		0x1fc9
 #define PCI_DEVICE_ID_TEHUTI_3009	0x3009
 #define PCI_DEVICE_ID_TEHUTI_3010	0x3010
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 143fbc10ecfe..b3b34f6670cf 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -60,12 +60,6 @@ struct pmu_hw_events {
 	DECLARE_BITMAP(used_mask, ARMPMU_MAX_HWEVENTS);
 
 	/*
-	 * Hardware lock to serialize accesses to PMU registers. Needed for the
-	 * read/modify/write sequences.
-	 */
-	raw_spinlock_t		pmu_lock;
-
-	/*
 	 * When using percpu IRQs, we need a percpu dev_id. Place it here as we
 	 * already have to allocate this struct per cpu.
 	 */
@@ -189,4 +183,26 @@ void armpmu_free_irq(int irq, int cpu);
 #define ARMV8_SPE_PDEV_NAME "arm,spe-v1"
 #define ARMV8_TRBE_PDEV_NAME "arm,trbe"
 
+/* Why does everything I do descend into this? */
+#define __GEN_PMU_FORMAT_ATTR(cfg, lo, hi)				\
+	(lo) == (hi) ? #cfg ":" #lo "\n" : #cfg ":" #lo "-" #hi
+
+#define _GEN_PMU_FORMAT_ATTR(cfg, lo, hi)				\
+	__GEN_PMU_FORMAT_ATTR(cfg, lo, hi)
+
+#define GEN_PMU_FORMAT_ATTR(name)					\
+	PMU_FORMAT_ATTR(name,						\
+	_GEN_PMU_FORMAT_ATTR(ATTR_CFG_FLD_##name##_CFG,			\
+			     ATTR_CFG_FLD_##name##_LO,			\
+			     ATTR_CFG_FLD_##name##_HI))
+
+#define _ATTR_CFG_GET_FLD(attr, cfg, lo, hi)				\
+	((((attr)->cfg) >> lo) & GENMASK_ULL(hi - lo, 0))
+
+#define ATTR_CFG_GET_FLD(attr, name)					\
+	_ATTR_CFG_GET_FLD(attr,						\
+			  ATTR_CFG_FLD_##name##_CFG,			\
+			  ATTR_CFG_FLD_##name##_LO,			\
+			  ATTR_CFG_FLD_##name##_HI)
+
 #endif /* __ARM_PMU_H__ */
diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h
index 9c226adf938a..46377e134d67 100644
--- a/include/linux/perf/arm_pmuv3.h
+++ b/include/linux/perf/arm_pmuv3.h
@@ -215,21 +215,27 @@
 #define ARMV8_PMU_PMCR_DP	(1 << 5) /* Disable CCNT if non-invasive debug*/
 #define ARMV8_PMU_PMCR_LC	(1 << 6) /* Overflow on 64 bit cycle counter */
 #define ARMV8_PMU_PMCR_LP	(1 << 7) /* Long event counter enable */
-#define ARMV8_PMU_PMCR_N_SHIFT	11  /* Number of counters supported */
-#define ARMV8_PMU_PMCR_N_MASK	0x1f
-#define ARMV8_PMU_PMCR_MASK	0xff    /* Mask for writable bits */
+#define ARMV8_PMU_PMCR_N	GENMASK(15, 11) /* Number of counters supported */
+/* Mask for writable bits */
+#define ARMV8_PMU_PMCR_MASK	(ARMV8_PMU_PMCR_E | ARMV8_PMU_PMCR_P | \
+				 ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_D | \
+				 ARMV8_PMU_PMCR_X | ARMV8_PMU_PMCR_DP | \
+				 ARMV8_PMU_PMCR_LC | ARMV8_PMU_PMCR_LP)
 
 /*
  * PMOVSR: counters overflow flag status reg
  */
-#define ARMV8_PMU_OVSR_MASK		0xffffffff	/* Mask for writable bits */
-#define ARMV8_PMU_OVERFLOWED_MASK	ARMV8_PMU_OVSR_MASK
+#define ARMV8_PMU_OVSR_P		GENMASK(30, 0)
+#define ARMV8_PMU_OVSR_C		BIT(31)
+/* Mask for writable bits is both P and C fields */
+#define ARMV8_PMU_OVERFLOWED_MASK	(ARMV8_PMU_OVSR_P | ARMV8_PMU_OVSR_C)
 
 /*
  * PMXEVTYPER: Event selection reg
  */
-#define ARMV8_PMU_EVTYPE_MASK	0xc800ffff	/* Mask for writable bits */
-#define ARMV8_PMU_EVTYPE_EVENT	0xffff		/* Mask for EVENT bits */
+#define ARMV8_PMU_EVTYPE_EVENT	GENMASK(15, 0)	/* Mask for EVENT bits */
+#define ARMV8_PMU_EVTYPE_TH	GENMASK_ULL(43, 32) /* arm64 only */
+#define ARMV8_PMU_EVTYPE_TC	GENMASK_ULL(63, 61) /* arm64 only */
 
 /*
  * Event filters for PMUv3
@@ -244,19 +250,19 @@
 /*
  * PMUSERENR: user enable reg
  */
-#define ARMV8_PMU_USERENR_MASK	0xf		/* Mask for writable bits */
 #define ARMV8_PMU_USERENR_EN	(1 << 0) /* PMU regs can be accessed at EL0 */
 #define ARMV8_PMU_USERENR_SW	(1 << 1) /* PMSWINC can be written at EL0 */
 #define ARMV8_PMU_USERENR_CR	(1 << 2) /* Cycle counter can be read at EL0 */
 #define ARMV8_PMU_USERENR_ER	(1 << 3) /* Event counter can be read at EL0 */
+/* Mask for writable bits */
+#define ARMV8_PMU_USERENR_MASK	(ARMV8_PMU_USERENR_EN | ARMV8_PMU_USERENR_SW | \
+				 ARMV8_PMU_USERENR_CR | ARMV8_PMU_USERENR_ER)
 
 /* PMMIR_EL1.SLOTS mask */
-#define ARMV8_PMU_SLOTS_MASK	0xff
-
-#define ARMV8_PMU_BUS_SLOTS_SHIFT 8
-#define ARMV8_PMU_BUS_SLOTS_MASK 0xff
-#define ARMV8_PMU_BUS_WIDTH_SHIFT 16
-#define ARMV8_PMU_BUS_WIDTH_MASK 0xf
+#define ARMV8_PMU_SLOTS		GENMASK(7, 0)
+#define ARMV8_PMU_BUS_SLOTS	GENMASK(15, 8)
+#define ARMV8_PMU_BUS_WIDTH	GENMASK(19, 16)
+#define ARMV8_PMU_THWIDTH	GENMASK(23, 20)
 
 /*
  * This code is really good
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index afb028c54f33..d2a15c0c6f8a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -843,11 +843,11 @@ struct perf_event {
 };
 
 /*
- *           ,-----------------------[1:n]----------------------.
- *           V                                                  V
- * perf_event_context <-[1:n]-> perf_event_pmu_context <--- perf_event
- *           ^                      ^     |                     |
- *           `--------[1:n]---------'     `-[n:1]-> pmu <-[1:n]-'
+ *           ,-----------------------[1:n]------------------------.
+ *           V                                                    V
+ * perf_event_context <-[1:n]-> perf_event_pmu_context <-[1:n]- perf_event
+ *                                        |                       |
+ *                                        `--[n:1]-> pmu <-[1:n]--'
  *
  *
  * struct perf_event_pmu_context  lifetime is refcount based and RCU freed
@@ -865,6 +865,9 @@ struct perf_event {
  * ctx->mutex pinning the configuration. Since we hold a reference on
  * group_leader (through the filedesc) it can't go away, therefore it's
  * associated pmu_ctx must exist and cannot change due to ctx->mutex.
+ *
+ * perf_event holds a refcount on perf_event_context
+ * perf_event holds a refcount on perf_event_pmu_context
  */
 struct perf_event_pmu_context {
 	struct pmu			*pmu;
@@ -1140,6 +1143,15 @@ static inline bool branch_sample_priv(const struct perf_event *event)
 	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_PRIV_SAVE;
 }
 
+static inline bool branch_sample_counters(const struct perf_event *event)
+{
+	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS;
+}
+
+static inline bool branch_sample_call_stack(const struct perf_event *event)
+{
+	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;
+}
 
 struct perf_sample_data {
 	/*
@@ -1174,6 +1186,7 @@ struct perf_sample_data {
 	struct perf_callchain_entry	*callchain;
 	struct perf_raw_record		*raw;
 	struct perf_branch_stack	*br_stack;
+	u64				*br_stack_cntr;
 	union perf_sample_weight	weight;
 	union  perf_mem_data_src	data_src;
 	u64				txn;
@@ -1251,7 +1264,8 @@ static inline void perf_sample_save_raw_data(struct perf_sample_data *data,
 
 static inline void perf_sample_save_brstack(struct perf_sample_data *data,
 					    struct perf_event *event,
-					    struct perf_branch_stack *brs)
+					    struct perf_branch_stack *brs,
+					    u64 *brs_cntr)
 {
 	int size = sizeof(u64); /* nr */
 
@@ -1259,7 +1273,16 @@ static inline void perf_sample_save_brstack(struct perf_sample_data *data,
 		size += sizeof(u64);
 	size += brs->nr * sizeof(struct perf_branch_entry);
 
+	/*
+	 * The extension space for counters is appended after the
+	 * struct perf_branch_stack. It is used to store the occurrences
+	 * of events of each branch.
+	 */
+	if (brs_cntr)
+		size += brs->nr * sizeof(u64);
+
 	data->br_stack = brs;
+	data->br_stack_cntr = brs_cntr;
 	data->dyn_size += size;
 	data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
 }
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index af7639c3b0a3..466cf477551a 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -184,6 +184,13 @@ static inline int pmd_young(pmd_t pmd)
 }
 #endif
 
+#ifndef pmd_dirty
+static inline int pmd_dirty(pmd_t pmd)
+{
+	return 0;
+}
+#endif
+
 /*
  * A facility to provide lazy MMU batching.  This allows PTE updates and
  * page invalidations to be delayed until a call to leave lazy MMU mode
@@ -375,7 +382,7 @@ static inline bool arch_has_hw_nonleaf_pmd_young(void)
  */
 static inline bool arch_has_hw_pte_young(void)
 {
-	return false;
+	return IS_ENABLED(CONFIG_ARCH_HAS_HW_PTE_YOUNG);
 }
 #endif
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 3cc52826f18e..684efaeca07c 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -327,7 +327,8 @@ struct mdio_bus_stats {
 
 /**
  * struct phy_package_shared - Shared information in PHY packages
- * @addr: Common PHY address used to combine PHYs in one package
+ * @base_addr: Base PHY address of PHY package used to combine PHYs
+ *   in one package and for offset calculation of phy_package_read/write
  * @refcnt: Number of PHYs connected to this shared data
  * @flags: Initialization of PHY package
  * @priv_size: Size of the shared private data @priv
@@ -338,7 +339,7 @@ struct mdio_bus_stats {
  * phy_package_leave().
  */
 struct phy_package_shared {
-	int addr;
+	u8 base_addr;
 	refcount_t refcnt;
 	unsigned long flags;
 	size_t priv_size;
@@ -568,7 +569,6 @@ struct macsec_ops;
  *      - Bits [31:24] are reserved for defining generic
  *        PHY driver behavior.
  * @irq: IRQ number of the PHY's interrupt (-1 if none)
- * @phy_timer: The timer for handling the state machine
  * @phylink: Pointer to phylink instance for this PHY
  * @sfp_bus_attached: Flag indicating whether the SFP bus has been attached
  * @sfp_bus: SFP bus attached to this PHY's fiber port
@@ -605,6 +605,8 @@ struct macsec_ops;
  * @irq_rerun: Flag indicating interrupts occurred while PHY was suspended,
  *             requiring a rerun of the interrupt handler after resume
  * @interface: enum phy_interface_t value
+ * @possible_interfaces: bitmap if interface modes that the attached PHY
+ *			 will switch between depending on media speed.
  * @skb: Netlink message for cable diagnostics
  * @nest: Netlink nest used for cable diagnostics
  * @ehdr: nNtlink header for cable diagnostics
@@ -674,6 +676,7 @@ struct phy_device {
 	u32 dev_flags;
 
 	phy_interface_t interface;
+	DECLARE_PHY_INTERFACE_MASK(possible_interfaces);
 
 	/*
 	 * forced speed & duplex (no autoneg)
@@ -1560,9 +1563,11 @@ static inline bool phy_has_txtstamp(struct phy_device *phydev)
 	return phydev && phydev->mii_ts && phydev->mii_ts->txtstamp;
 }
 
-static inline int phy_hwtstamp(struct phy_device *phydev, struct ifreq *ifr)
+static inline int phy_hwtstamp(struct phy_device *phydev,
+			       struct kernel_hwtstamp_config *cfg,
+			       struct netlink_ext_ack *extack)
 {
-	return phydev->mii_ts->hwtstamp(phydev->mii_ts, ifr);
+	return phydev->mii_ts->hwtstamp(phydev->mii_ts, cfg, extack);
 }
 
 static inline bool phy_rxtstamp(struct phy_device *phydev, struct sk_buff *skb,
@@ -1861,6 +1866,7 @@ int genphy_c45_an_config_aneg(struct phy_device *phydev);
 int genphy_c45_an_disable_aneg(struct phy_device *phydev);
 int genphy_c45_read_mdix(struct phy_device *phydev);
 int genphy_c45_pma_read_abilities(struct phy_device *phydev);
+int genphy_c45_pma_read_ext_abilities(struct phy_device *phydev);
 int genphy_c45_pma_baset1_read_abilities(struct phy_device *phydev);
 int genphy_c45_read_eee_abilities(struct phy_device *phydev);
 int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev);
@@ -1970,10 +1976,10 @@ int phy_ethtool_get_link_ksettings(struct net_device *ndev,
 int phy_ethtool_set_link_ksettings(struct net_device *ndev,
 				   const struct ethtool_link_ksettings *cmd);
 int phy_ethtool_nway_reset(struct net_device *ndev);
-int phy_package_join(struct phy_device *phydev, int addr, size_t priv_size);
+int phy_package_join(struct phy_device *phydev, int base_addr, size_t priv_size);
 void phy_package_leave(struct phy_device *phydev);
 int devm_phy_package_join(struct device *dev, struct phy_device *phydev,
-			  int addr, size_t priv_size);
+			  int base_addr, size_t priv_size);
 
 int __init mdio_bus_init(void);
 void mdio_bus_exit(void);
@@ -1996,48 +2002,83 @@ int __phy_hwtstamp_set(struct phy_device *phydev,
 		       struct kernel_hwtstamp_config *config,
 		       struct netlink_ext_ack *extack);
 
-static inline int phy_package_read(struct phy_device *phydev, u32 regnum)
+static inline int phy_package_address(struct phy_device *phydev,
+				      unsigned int addr_offset)
 {
 	struct phy_package_shared *shared = phydev->shared;
+	u8 base_addr = shared->base_addr;
 
-	if (!shared)
+	if (addr_offset >= PHY_MAX_ADDR - base_addr)
 		return -EIO;
 
-	return mdiobus_read(phydev->mdio.bus, shared->addr, regnum);
+	/* we know that addr will be in the range 0..31 and thus the
+	 * implicit cast to a signed int is not a problem.
+	 */
+	return base_addr + addr_offset;
 }
 
-static inline int __phy_package_read(struct phy_device *phydev, u32 regnum)
+static inline int phy_package_read(struct phy_device *phydev,
+				   unsigned int addr_offset, u32 regnum)
 {
-	struct phy_package_shared *shared = phydev->shared;
+	int addr = phy_package_address(phydev, addr_offset);
 
-	if (!shared)
-		return -EIO;
+	if (addr < 0)
+		return addr;
+
+	return mdiobus_read(phydev->mdio.bus, addr, regnum);
+}
+
+static inline int __phy_package_read(struct phy_device *phydev,
+				     unsigned int addr_offset, u32 regnum)
+{
+	int addr = phy_package_address(phydev, addr_offset);
+
+	if (addr < 0)
+		return addr;
 
-	return __mdiobus_read(phydev->mdio.bus, shared->addr, regnum);
+	return __mdiobus_read(phydev->mdio.bus, addr, regnum);
 }
 
 static inline int phy_package_write(struct phy_device *phydev,
-				    u32 regnum, u16 val)
+				    unsigned int addr_offset, u32 regnum,
+				    u16 val)
 {
-	struct phy_package_shared *shared = phydev->shared;
+	int addr = phy_package_address(phydev, addr_offset);
 
-	if (!shared)
-		return -EIO;
+	if (addr < 0)
+		return addr;
 
-	return mdiobus_write(phydev->mdio.bus, shared->addr, regnum, val);
+	return mdiobus_write(phydev->mdio.bus, addr, regnum, val);
 }
 
 static inline int __phy_package_write(struct phy_device *phydev,
-				      u32 regnum, u16 val)
+				      unsigned int addr_offset, u32 regnum,
+				      u16 val)
 {
-	struct phy_package_shared *shared = phydev->shared;
+	int addr = phy_package_address(phydev, addr_offset);
 
-	if (!shared)
-		return -EIO;
+	if (addr < 0)
+		return addr;
 
-	return __mdiobus_write(phydev->mdio.bus, shared->addr, regnum, val);
+	return __mdiobus_write(phydev->mdio.bus, addr, regnum, val);
 }
 
+int __phy_package_read_mmd(struct phy_device *phydev,
+			   unsigned int addr_offset, int devad,
+			   u32 regnum);
+
+int phy_package_read_mmd(struct phy_device *phydev,
+			 unsigned int addr_offset, int devad,
+			 u32 regnum);
+
+int __phy_package_write_mmd(struct phy_device *phydev,
+			    unsigned int addr_offset, int devad,
+			    u32 regnum, u16 val);
+
+int phy_package_write_mmd(struct phy_device *phydev,
+			  unsigned int addr_offset, int devad,
+			  u32 regnum, u16 val);
+
 static inline bool __phy_package_set_once(struct phy_device *phydev,
 					  unsigned int b)
 {
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 875439ab45de..d589f89c612c 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -99,72 +99,6 @@ static inline bool phylink_autoneg_inband(unsigned int mode)
 }
 
 /**
- * phylink_pcs_neg_mode() - helper to determine PCS inband mode
- * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND.
- * @interface: interface mode to be used
- * @advertising: adertisement ethtool link mode mask
- *
- * Determines the negotiation mode to be used by the PCS, and returns
- * one of:
- *
- * - %PHYLINK_PCS_NEG_NONE: interface mode does not support inband
- * - %PHYLINK_PCS_NEG_OUTBAND: an out of band mode (e.g. reading the PHY)
- *   will be used.
- * - %PHYLINK_PCS_NEG_INBAND_DISABLED: inband mode selected but autoneg
- *   disabled
- * - %PHYLINK_PCS_NEG_INBAND_ENABLED: inband mode selected and autoneg enabled
- *
- * Note: this is for cases where the PCS itself is involved in negotiation
- * (e.g. Clause 37, SGMII and similar) not Clause 73.
- */
-static inline unsigned int phylink_pcs_neg_mode(unsigned int mode,
-						phy_interface_t interface,
-						const unsigned long *advertising)
-{
-	unsigned int neg_mode;
-
-	switch (interface) {
-	case PHY_INTERFACE_MODE_SGMII:
-	case PHY_INTERFACE_MODE_QSGMII:
-	case PHY_INTERFACE_MODE_QUSGMII:
-	case PHY_INTERFACE_MODE_USXGMII:
-		/* These protocols are designed for use with a PHY which
-		 * communicates its negotiation result back to the MAC via
-		 * inband communication. Note: there exist PHYs that run
-		 * with SGMII but do not send the inband data.
-		 */
-		if (!phylink_autoneg_inband(mode))
-			neg_mode = PHYLINK_PCS_NEG_OUTBAND;
-		else
-			neg_mode = PHYLINK_PCS_NEG_INBAND_ENABLED;
-		break;
-
-	case PHY_INTERFACE_MODE_1000BASEX:
-	case PHY_INTERFACE_MODE_2500BASEX:
-		/* 1000base-X is designed for use media-side for Fibre
-		 * connections, and thus the Autoneg bit needs to be
-		 * taken into account. We also do this for 2500base-X
-		 * as well, but drivers may not support this, so may
-		 * need to override this.
-		 */
-		if (!phylink_autoneg_inband(mode))
-			neg_mode = PHYLINK_PCS_NEG_OUTBAND;
-		else if (linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
-					   advertising))
-			neg_mode = PHYLINK_PCS_NEG_INBAND_ENABLED;
-		else
-			neg_mode = PHYLINK_PCS_NEG_INBAND_DISABLED;
-		break;
-
-	default:
-		neg_mode = PHYLINK_PCS_NEG_NONE;
-		break;
-	}
-
-	return neg_mode;
-}
-
-/**
  * struct phylink_link_state - link state structure
  * @advertising: ethtool bitmask containing advertised link modes
  * @lp_advertising: ethtool bitmask containing link partner advertised link
diff --git a/include/linux/pid.h b/include/linux/pid.h
index 653a527574c4..395cacce1179 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -2,18 +2,12 @@
 #ifndef _LINUX_PID_H
 #define _LINUX_PID_H
 
+#include <linux/pid_types.h>
 #include <linux/rculist.h>
-#include <linux/wait.h>
+#include <linux/rcupdate.h>
 #include <linux/refcount.h>
-
-enum pid_type
-{
-	PIDTYPE_PID,
-	PIDTYPE_TGID,
-	PIDTYPE_PGID,
-	PIDTYPE_SID,
-	PIDTYPE_MAX,
-};
+#include <linux/sched.h>
+#include <linux/wait.h>
 
 /*
  * What is struct pid?
@@ -110,9 +104,6 @@ extern void exchange_tids(struct task_struct *task, struct task_struct *old);
 extern void transfer_pid(struct task_struct *old, struct task_struct *new,
 			 enum pid_type);
 
-struct pid_namespace;
-extern struct pid_namespace init_pid_ns;
-
 extern int pid_max;
 extern int pid_max_min, pid_max_max;
 
@@ -215,4 +206,127 @@ pid_t pid_vnr(struct pid *pid);
 		}							\
 		task = tg___;						\
 	} while_each_pid_task(pid, type, task)
+
+static inline struct pid *task_pid(struct task_struct *task)
+{
+	return task->thread_pid;
+}
+
+/*
+ * the helpers to get the task's different pids as they are seen
+ * from various namespaces
+ *
+ * task_xid_nr()     : global id, i.e. the id seen from the init namespace;
+ * task_xid_vnr()    : virtual id, i.e. the id seen from the pid namespace of
+ *                     current.
+ * task_xid_nr_ns()  : id seen from the ns specified;
+ *
+ * see also pid_nr() etc in include/linux/pid.h
+ */
+pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns);
+
+static inline pid_t task_pid_nr(struct task_struct *tsk)
+{
+	return tsk->pid;
+}
+
+static inline pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
+{
+	return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns);
+}
+
+static inline pid_t task_pid_vnr(struct task_struct *tsk)
+{
+	return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL);
+}
+
+
+static inline pid_t task_tgid_nr(struct task_struct *tsk)
+{
+	return tsk->tgid;
+}
+
+/**
+ * pid_alive - check that a task structure is not stale
+ * @p: Task structure to be checked.
+ *
+ * Test if a process is not yet dead (at most zombie state)
+ * If pid_alive fails, then pointers within the task structure
+ * can be stale and must not be dereferenced.
+ *
+ * Return: 1 if the process is alive. 0 otherwise.
+ */
+static inline int pid_alive(const struct task_struct *p)
+{
+	return p->thread_pid != NULL;
+}
+
+static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
+{
+	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns);
+}
+
+static inline pid_t task_pgrp_vnr(struct task_struct *tsk)
+{
+	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL);
+}
+
+
+static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
+{
+	return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns);
+}
+
+static inline pid_t task_session_vnr(struct task_struct *tsk)
+{
+	return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL);
+}
+
+static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
+{
+	return __task_pid_nr_ns(tsk, PIDTYPE_TGID, ns);
+}
+
+static inline pid_t task_tgid_vnr(struct task_struct *tsk)
+{
+	return __task_pid_nr_ns(tsk, PIDTYPE_TGID, NULL);
+}
+
+static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
+{
+	pid_t pid = 0;
+
+	rcu_read_lock();
+	if (pid_alive(tsk))
+		pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns);
+	rcu_read_unlock();
+
+	return pid;
+}
+
+static inline pid_t task_ppid_nr(const struct task_struct *tsk)
+{
+	return task_ppid_nr_ns(tsk, &init_pid_ns);
+}
+
+/* Obsolete, do not use: */
+static inline pid_t task_pgrp_nr(struct task_struct *tsk)
+{
+	return task_pgrp_nr_ns(tsk, &init_pid_ns);
+}
+
+/**
+ * is_global_init - check if a task structure is init. Since init
+ * is free to have sub-threads we need to check tgid.
+ * @tsk: Task structure to be checked.
+ *
+ * Check if a task structure is the first user space task the kernel created.
+ *
+ * Return: 1 if the task structure is init. 0 otherwise.
+ */
+static inline int is_global_init(struct task_struct *tsk)
+{
+	return task_tgid_nr(tsk) == 1;
+}
+
 #endif /* _LINUX_PID_H */
diff --git a/include/linux/pid_types.h b/include/linux/pid_types.h
new file mode 100644
index 000000000000..c2aee1d91dcf
--- /dev/null
+++ b/include/linux/pid_types.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_PID_TYPES_H
+#define _LINUX_PID_TYPES_H
+
+enum pid_type {
+	PIDTYPE_PID,
+	PIDTYPE_TGID,
+	PIDTYPE_PGID,
+	PIDTYPE_SID,
+	PIDTYPE_MAX,
+};
+
+struct pid_namespace;
+extern struct pid_namespace init_pid_ns;
+
+#endif /* _LINUX_PID_TYPES_H */
diff --git a/include/linux/platform_data/microchip-ksz.h b/include/linux/platform_data/microchip-ksz.h
index ea1cc6d829e9..f177416635a2 100644
--- a/include/linux/platform_data/microchip-ksz.h
+++ b/include/linux/platform_data/microchip-ksz.h
@@ -20,10 +20,31 @@
 #define __MICROCHIP_KSZ_H
 
 #include <linux/types.h>
+#include <linux/platform_data/dsa.h>
+
+enum ksz_chip_id {
+	KSZ8563_CHIP_ID = 0x8563,
+	KSZ8795_CHIP_ID = 0x8795,
+	KSZ8794_CHIP_ID = 0x8794,
+	KSZ8765_CHIP_ID = 0x8765,
+	KSZ8830_CHIP_ID = 0x8830,
+	KSZ9477_CHIP_ID = 0x00947700,
+	KSZ9896_CHIP_ID = 0x00989600,
+	KSZ9897_CHIP_ID = 0x00989700,
+	KSZ9893_CHIP_ID = 0x00989300,
+	KSZ9563_CHIP_ID = 0x00956300,
+	KSZ9567_CHIP_ID = 0x00956700,
+	LAN9370_CHIP_ID = 0x00937000,
+	LAN9371_CHIP_ID = 0x00937100,
+	LAN9372_CHIP_ID = 0x00937200,
+	LAN9373_CHIP_ID = 0x00937300,
+	LAN9374_CHIP_ID = 0x00937400,
+};
 
 struct ksz_platform_data {
+	/* Must be first such that dsa_register_switch() can access it */
+	struct dsa_chip_data cd;
 	u32 chip_id;
-	u16 enabled_ports;
 };
 
 #endif
diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h
index 63e630276499..ab1c7deff118 100644
--- a/include/linux/platform_data/x86/asus-wmi.h
+++ b/include/linux/platform_data/x86/asus-wmi.h
@@ -114,6 +114,9 @@
 /* Charging mode - 1=Barrel, 2=USB */
 #define ASUS_WMI_DEVID_CHARGE_MODE	0x0012006C
 
+/* MCU powersave mode */
+#define ASUS_WMI_DEVID_MCU_POWERSAVE   0x001200E2
+
 /* epu is connected? 1 == true */
 #define ASUS_WMI_DEVID_EGPU_CONNECTED	0x00090018
 /* egpu on/off */
diff --git a/include/linux/platform_data/x86/clk-lpss.h b/include/linux/platform_data/x86/clk-lpss.h
index 41df326583f9..7f132029316a 100644
--- a/include/linux/platform_data/x86/clk-lpss.h
+++ b/include/linux/platform_data/x86/clk-lpss.h
@@ -15,6 +15,6 @@ struct lpss_clk_data {
 	struct clk *clk;
 };
 
-extern int lpss_atom_clk_init(void);
+int lpss_atom_clk_init(void);
 
 #endif /* __CLK_LPSS_H */
diff --git a/include/linux/plist.h b/include/linux/plist.h
index 0f352c1d3c80..8c1c8adf7fe9 100644
--- a/include/linux/plist.h
+++ b/include/linux/plist.h
@@ -75,20 +75,10 @@
 
 #include <linux/container_of.h>
 #include <linux/list.h>
-#include <linux/types.h>
+#include <linux/plist_types.h>
 
 #include <asm/bug.h>
 
-struct plist_head {
-	struct list_head node_list;
-};
-
-struct plist_node {
-	int			prio;
-	struct list_head	prio_list;
-	struct list_head	node_list;
-};
-
 /**
  * PLIST_HEAD_INIT - static struct plist_head initializer
  * @head:	struct plist_head variable name
diff --git a/include/linux/plist_types.h b/include/linux/plist_types.h
new file mode 100644
index 000000000000..c37e784330af
--- /dev/null
+++ b/include/linux/plist_types.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _LINUX_PLIST_TYPES_H
+#define _LINUX_PLIST_TYPES_H
+
+#include <linux/types.h>
+
+struct plist_head {
+	struct list_head node_list;
+};
+
+struct plist_node {
+	int			prio;
+	struct list_head	prio_list;
+	struct list_head	node_list;
+};
+
+#endif /* _LINUX_PLIST_TYPES_H */
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index ccd97bcef269..76dcb7f37bcd 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -45,18 +45,6 @@ struct dev_pm_opp_supply {
 	unsigned long u_watt;
 };
 
-/**
- * struct dev_pm_opp_icc_bw - Interconnect bandwidth values
- * @avg:	Average bandwidth corresponding to this OPP (in icc units)
- * @peak:	Peak bandwidth corresponding to this OPP (in icc units)
- *
- * This structure stores the bandwidth values for a single interconnect path.
- */
-struct dev_pm_opp_icc_bw {
-	u32 avg;
-	u32 peak;
-};
-
 typedef int (*config_regulators_t)(struct device *dev,
 			struct dev_pm_opp *old_opp, struct dev_pm_opp *new_opp,
 			struct regulator **regulators, unsigned int count);
@@ -74,8 +62,10 @@ typedef int (*config_clks_t)(struct device *dev, struct opp_table *opp_table,
  * @supported_hw_count: Number of elements in the array.
  * @regulator_names: Array of pointers to the names of the regulator, NULL terminated.
  * @genpd_names: Null terminated array of pointers containing names of genpd to
- *		 attach.
- * @virt_devs: Pointer to return the array of virtual devices.
+ *		attach. Mutually exclusive with required_devs.
+ * @virt_devs: Pointer to return the array of genpd virtual devices. Mutually
+ *		exclusive with required_devs.
+ * @required_devs: Required OPP devices. Mutually exclusive with genpd_names/virt_devs.
  *
  * This structure contains platform specific OPP configurations for the device.
  */
@@ -90,11 +80,15 @@ struct dev_pm_opp_config {
 	const char * const *regulator_names;
 	const char * const *genpd_names;
 	struct device ***virt_devs;
+	struct device **required_devs;
 };
 
+#define OPP_LEVEL_UNSET			U32_MAX
+
 /**
  * struct dev_pm_opp_data - The data to use to initialize an OPP.
- * @level: The performance level for the OPP.
+ * @level: The performance level for the OPP. Set level to OPP_LEVEL_UNSET if
+ * level field isn't used.
  * @freq: The clock rate in Hz for the OPP.
  * @u_volt: The voltage in uV for the OPP.
  */
@@ -157,7 +151,7 @@ struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev,
 					      unsigned int *level);
 
 struct dev_pm_opp *dev_pm_opp_find_level_floor(struct device *dev,
-					       unsigned long *level);
+					       unsigned int *level);
 
 struct dev_pm_opp *dev_pm_opp_find_bw_ceil(struct device *dev,
 					   unsigned int *bw, int index);
@@ -324,7 +318,7 @@ static inline struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev,
 }
 
 static inline struct dev_pm_opp *dev_pm_opp_find_level_floor(struct device *dev,
-							     unsigned long *level)
+							     unsigned int *level)
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }
diff --git a/include/linux/poison.h b/include/linux/poison.h
index 851a855d3868..27a7dad17eef 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -83,6 +83,8 @@
 
 /********** net/core/skbuff.c **********/
 #define SKB_LIST_POISON_NEXT	((void *)(0x800 + POISON_POINTER_DELTA))
+/********** net/ **********/
+#define NET_PTR_POISON		((void *)(0x801 + POISON_POINTER_DELTA))
 
 /********** kernel/bpf/ **********/
 #define BPF_PTR_POISON ((void *)(0xeB9FUL + POISON_POINTER_DELTA))
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index d607f51404fc..dc7b738de299 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -2,40 +2,16 @@
 #ifndef _linux_POSIX_TIMERS_H
 #define _linux_POSIX_TIMERS_H
 
-#include <linux/spinlock.h>
+#include <linux/alarmtimer.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
-#include <linux/alarmtimer.h>
+#include <linux/posix-timers_types.h>
+#include <linux/spinlock.h>
 #include <linux/timerqueue.h>
 
 struct kernel_siginfo;
 struct task_struct;
 
-/*
- * Bit fields within a clockid:
- *
- * The most significant 29 bits hold either a pid or a file descriptor.
- *
- * Bit 2 indicates whether a cpu clock refers to a thread or a process.
- *
- * Bits 1 and 0 give the type: PROF=0, VIRT=1, SCHED=2, or FD=3.
- *
- * A clockid is invalid if bits 2, 1, and 0 are all set.
- */
-#define CPUCLOCK_PID(clock)		((pid_t) ~((clock) >> 3))
-#define CPUCLOCK_PERTHREAD(clock) \
-	(((clock) & (clockid_t) CPUCLOCK_PERTHREAD_MASK) != 0)
-
-#define CPUCLOCK_PERTHREAD_MASK	4
-#define CPUCLOCK_WHICH(clock)	((clock) & (clockid_t) CPUCLOCK_CLOCK_MASK)
-#define CPUCLOCK_CLOCK_MASK	3
-#define CPUCLOCK_PROF		0
-#define CPUCLOCK_VIRT		1
-#define CPUCLOCK_SCHED		2
-#define CPUCLOCK_MAX		3
-#define CLOCKFD			CPUCLOCK_MAX
-#define CLOCKFD_MASK		(CPUCLOCK_PERTHREAD_MASK|CPUCLOCK_CLOCK_MASK)
-
 static inline clockid_t make_process_cpuclock(const unsigned int pid,
 		const clockid_t clock)
 {
@@ -109,44 +85,6 @@ static inline void cpu_timer_setexpires(struct cpu_timer *ctmr, u64 exp)
 	ctmr->node.expires = exp;
 }
 
-/**
- * posix_cputimer_base - Container per posix CPU clock
- * @nextevt:		Earliest-expiration cache
- * @tqhead:		timerqueue head for cpu_timers
- */
-struct posix_cputimer_base {
-	u64			nextevt;
-	struct timerqueue_head	tqhead;
-};
-
-/**
- * posix_cputimers - Container for posix CPU timer related data
- * @bases:		Base container for posix CPU clocks
- * @timers_active:	Timers are queued.
- * @expiry_active:	Timer expiry is active. Used for
- *			process wide timers to avoid multiple
- *			task trying to handle expiry concurrently
- *
- * Used in task_struct and signal_struct
- */
-struct posix_cputimers {
-	struct posix_cputimer_base	bases[CPUCLOCK_MAX];
-	unsigned int			timers_active;
-	unsigned int			expiry_active;
-};
-
-/**
- * posix_cputimers_work - Container for task work based posix CPU timer expiry
- * @work:	The task work to be scheduled
- * @mutex:	Mutex held around expiry in context of this task work
- * @scheduled:  @work has been scheduled already, no further processing
- */
-struct posix_cputimers_work {
-	struct callback_head	work;
-	struct mutex		mutex;
-	unsigned int		scheduled;
-};
-
 static inline void posix_cputimers_init(struct posix_cputimers *pct)
 {
 	memset(pct, 0, sizeof(*pct));
@@ -179,7 +117,6 @@ static inline void posix_cputimers_rt_watchdog(struct posix_cputimers *pct,
 		.bases = INIT_CPU_TIMERBASES(s.posix_cputimers.bases),	\
 	},
 #else
-struct posix_cputimers { };
 struct cpu_timer { };
 #define INIT_CPU_TIMERS(s)
 static inline void posix_cputimers_init(struct posix_cputimers *pct) { }
diff --git a/include/linux/posix-timers_types.h b/include/linux/posix-timers_types.h
new file mode 100644
index 000000000000..a4712c1008c9
--- /dev/null
+++ b/include/linux/posix-timers_types.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _linux_POSIX_TIMERS_TYPES_H
+#define _linux_POSIX_TIMERS_TYPES_H
+
+#include <linux/mutex_types.h>
+#include <linux/timerqueue_types.h>
+#include <linux/types.h>
+
+/*
+ * Bit fields within a clockid:
+ *
+ * The most significant 29 bits hold either a pid or a file descriptor.
+ *
+ * Bit 2 indicates whether a cpu clock refers to a thread or a process.
+ *
+ * Bits 1 and 0 give the type: PROF=0, VIRT=1, SCHED=2, or FD=3.
+ *
+ * A clockid is invalid if bits 2, 1, and 0 are all set.
+ */
+#define CPUCLOCK_PID(clock)		((pid_t) ~((clock) >> 3))
+#define CPUCLOCK_PERTHREAD(clock) \
+	(((clock) & (clockid_t) CPUCLOCK_PERTHREAD_MASK) != 0)
+
+#define CPUCLOCK_PERTHREAD_MASK	4
+#define CPUCLOCK_WHICH(clock)	((clock) & (clockid_t) CPUCLOCK_CLOCK_MASK)
+#define CPUCLOCK_CLOCK_MASK	3
+#define CPUCLOCK_PROF		0
+#define CPUCLOCK_VIRT		1
+#define CPUCLOCK_SCHED		2
+#define CPUCLOCK_MAX		3
+#define CLOCKFD			CPUCLOCK_MAX
+#define CLOCKFD_MASK		(CPUCLOCK_PERTHREAD_MASK|CPUCLOCK_CLOCK_MASK)
+
+#ifdef CONFIG_POSIX_TIMERS
+
+/**
+ * posix_cputimer_base - Container per posix CPU clock
+ * @nextevt:		Earliest-expiration cache
+ * @tqhead:		timerqueue head for cpu_timers
+ */
+struct posix_cputimer_base {
+	u64			nextevt;
+	struct timerqueue_head	tqhead;
+};
+
+/**
+ * posix_cputimers - Container for posix CPU timer related data
+ * @bases:		Base container for posix CPU clocks
+ * @timers_active:	Timers are queued.
+ * @expiry_active:	Timer expiry is active. Used for
+ *			process wide timers to avoid multiple
+ *			task trying to handle expiry concurrently
+ *
+ * Used in task_struct and signal_struct
+ */
+struct posix_cputimers {
+	struct posix_cputimer_base	bases[CPUCLOCK_MAX];
+	unsigned int			timers_active;
+	unsigned int			expiry_active;
+};
+
+/**
+ * posix_cputimers_work - Container for task work based posix CPU timer expiry
+ * @work:	The task work to be scheduled
+ * @mutex:	Mutex held around expiry in context of this task work
+ * @scheduled:  @work has been scheduled already, no further processing
+ */
+struct posix_cputimers_work {
+	struct callback_head	work;
+	struct mutex		mutex;
+	unsigned int		scheduled;
+};
+
+#else /* CONFIG_POSIX_TIMERS */
+
+struct posix_cputimers { };
+
+#endif /* CONFIG_POSIX_TIMERS */
+
+#endif /* _linux_POSIX_TIMERS_TYPES_H */
diff --git a/include/linux/prandom.h b/include/linux/prandom.h
index f2ed5b72b3d6..f7f1e5251c67 100644
--- a/include/linux/prandom.h
+++ b/include/linux/prandom.h
@@ -10,7 +10,6 @@
 
 #include <linux/types.h>
 #include <linux/once.h>
-#include <linux/percpu.h>
 #include <linux/random.h>
 
 struct rnd_state {
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 9aa6358a1a16..7233e9cf1bab 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -9,7 +9,7 @@
 
 #include <linux/linkage.h>
 #include <linux/cleanup.h>
-#include <linux/list.h>
+#include <linux/types.h>
 
 /*
  * We put the hardirq and softirq counter into the preemption
@@ -360,7 +360,9 @@ void preempt_notifier_unregister(struct preempt_notifier *notifier);
 static inline void preempt_notifier_init(struct preempt_notifier *notifier,
 				     struct preempt_ops *ops)
 {
-	INIT_HLIST_NODE(&notifier->link);
+	/* INIT_HLIST_NODE() open coded, to avoid dependency on list.h */
+	notifier->link.next = NULL;
+	notifier->link.pprev = NULL;
 	notifier->ops = ops;
 }
 
diff --git a/include/linux/property.h b/include/linux/property.h
index 9f2585d705a8..97f901c0914e 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -489,6 +489,13 @@ struct software_node {
 	const struct property_entry *properties;
 };
 
+#define SOFTWARE_NODE(_name_, _properties_, _parent_)	\
+	(struct software_node) {			\
+		.name = _name_,				\
+		.properties = _properties_,		\
+		.parent = _parent_,			\
+	}
+
 bool is_software_node(const struct fwnode_handle *fwnode);
 const struct software_node *
 to_software_node(const struct fwnode_handle *fwnode);
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index 4fa4ef0a173a..06cc8888199e 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -74,7 +74,7 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags);
 
 int dquot_alloc_inode(struct inode *inode);
 
-int dquot_claim_space_nodirty(struct inode *inode, qsize_t number);
+void dquot_claim_space_nodirty(struct inode *inode, qsize_t number);
 void dquot_free_inode(struct inode *inode);
 void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number);
 
@@ -257,10 +257,9 @@ static inline void __dquot_free_space(struct inode *inode, qsize_t number,
 		inode_sub_bytes(inode, number);
 }
 
-static inline int dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
+static inline void dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
 {
 	inode_add_bytes(inode, number);
-	return 0;
 }
 
 static inline int dquot_reclaim_space_nodirty(struct inode *inode,
@@ -358,14 +357,10 @@ static inline int dquot_reserve_block(struct inode *inode, qsize_t nr)
 				DQUOT_SPACE_WARN|DQUOT_SPACE_RESERVE);
 }
 
-static inline int dquot_claim_block(struct inode *inode, qsize_t nr)
+static inline void dquot_claim_block(struct inode *inode, qsize_t nr)
 {
-	int ret;
-
-	ret = dquot_claim_space_nodirty(inode, nr << inode->i_blkbits);
-	if (!ret)
-		mark_inode_dirty_sync(inode);
-	return ret;
+	dquot_claim_space_nodirty(inode, nr << inode->i_blkbits);
+	mark_inode_dirty_sync(inode);
 }
 
 static inline void dquot_reclaim_block(struct inode *inode, qsize_t nr)
diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h
index 5e0f74f2f8ca..d07f0848802e 100644
--- a/include/linux/rcupdate_wait.h
+++ b/include/linux/rcupdate_wait.h
@@ -8,6 +8,7 @@
 
 #include <linux/rcupdate.h>
 #include <linux/completion.h>
+#include <linux/sched.h>
 
 /*
  * Structure allowing asynchronous waiting on RCU.
@@ -55,4 +56,13 @@ do {									\
 #define synchronize_rcu_mult(...) \
 	_wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__)
 
+static inline void cond_resched_rcu(void)
+{
+#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU)
+	rcu_read_unlock();
+	cond_resched();
+	rcu_read_lock();
+#endif
+}
+
 #endif /* _LINUX_SCHED_RCUPDATE_WAIT_H */
diff --git a/include/linux/reboot.h b/include/linux/reboot.h
index c4cc3b89ced1..abcdde4df697 100644
--- a/include/linux/reboot.h
+++ b/include/linux/reboot.h
@@ -177,7 +177,17 @@ void ctrl_alt_del(void);
 
 extern void orderly_poweroff(bool force);
 extern void orderly_reboot(void);
-void hw_protection_shutdown(const char *reason, int ms_until_forced);
+void __hw_protection_shutdown(const char *reason, int ms_until_forced, bool shutdown);
+
+static inline void hw_protection_reboot(const char *reason, int ms_until_forced)
+{
+	__hw_protection_shutdown(reason, ms_until_forced, false);
+}
+
+static inline void hw_protection_shutdown(const char *reason, int ms_until_forced)
+{
+	__hw_protection_shutdown(reason, ms_until_forced, true);
+}
 
 /*
  * Emergency restart, callable from an interrupt handler.
diff --git a/include/linux/refcount.h b/include/linux/refcount.h
index a62fcca97486..85c6df0d1bef 100644
--- a/include/linux/refcount.h
+++ b/include/linux/refcount.h
@@ -96,22 +96,11 @@
 #include <linux/bug.h>
 #include <linux/compiler.h>
 #include <linux/limits.h>
+#include <linux/refcount_types.h>
 #include <linux/spinlock_types.h>
 
 struct mutex;
 
-/**
- * typedef refcount_t - variant of atomic_t specialized for reference counts
- * @refs: atomic_t counter field
- *
- * The counter saturates at REFCOUNT_SATURATED and will not move once
- * there. This avoids wrapping the counter and causing 'spurious'
- * use-after-free bugs.
- */
-typedef struct refcount_struct {
-	atomic_t refs;
-} refcount_t;
-
 #define REFCOUNT_INIT(n)	{ .refs = ATOMIC_INIT(n), }
 #define REFCOUNT_MAX		INT_MAX
 #define REFCOUNT_SATURATED	(INT_MIN / 2)
diff --git a/include/linux/refcount_types.h b/include/linux/refcount_types.h
new file mode 100644
index 000000000000..162004f06edf
--- /dev/null
+++ b/include/linux/refcount_types.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_REFCOUNT_TYPES_H
+#define _LINUX_REFCOUNT_TYPES_H
+
+#include <linux/types.h>
+
+/**
+ * typedef refcount_t - variant of atomic_t specialized for reference counts
+ * @refs: atomic_t counter field
+ *
+ * The counter saturates at REFCOUNT_SATURATED and will not move once
+ * there. This avoids wrapping the counter and causing 'spurious'
+ * use-after-free bugs.
+ */
+typedef struct refcount_struct {
+	atomic_t refs;
+} refcount_t;
+
+#endif /* _LINUX_REFCOUNT_TYPES_H */
diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h
index 39b666b40ea6..4660582a3302 100644
--- a/include/linux/regulator/consumer.h
+++ b/include/linux/regulator/consumer.h
@@ -33,6 +33,7 @@
 
 #include <linux/err.h>
 #include <linux/suspend.h>
+#include <regulator/regulator.h>
 
 struct device;
 struct notifier_block;
@@ -85,52 +86,6 @@ struct regulator_dev;
 #define REGULATOR_MODE_STANDBY			0x8
 
 /*
- * Regulator notifier events.
- *
- * UNDER_VOLTAGE  Regulator output is under voltage.
- * OVER_CURRENT   Regulator output current is too high.
- * REGULATION_OUT Regulator output is out of regulation.
- * FAIL           Regulator output has failed.
- * OVER_TEMP      Regulator over temp.
- * FORCE_DISABLE  Regulator forcibly shut down by software.
- * VOLTAGE_CHANGE Regulator voltage changed.
- *                Data passed is old voltage cast to (void *).
- * DISABLE        Regulator was disabled.
- * PRE_VOLTAGE_CHANGE   Regulator is about to have voltage changed.
- *                      Data passed is "struct pre_voltage_change_data"
- * ABORT_VOLTAGE_CHANGE Regulator voltage change failed for some reason.
- *                      Data passed is old voltage cast to (void *).
- * PRE_DISABLE    Regulator is about to be disabled
- * ABORT_DISABLE  Regulator disable failed for some reason
- *
- * NOTE: These events can be OR'ed together when passed into handler.
- */
-
-#define REGULATOR_EVENT_UNDER_VOLTAGE		0x01
-#define REGULATOR_EVENT_OVER_CURRENT		0x02
-#define REGULATOR_EVENT_REGULATION_OUT		0x04
-#define REGULATOR_EVENT_FAIL			0x08
-#define REGULATOR_EVENT_OVER_TEMP		0x10
-#define REGULATOR_EVENT_FORCE_DISABLE		0x20
-#define REGULATOR_EVENT_VOLTAGE_CHANGE		0x40
-#define REGULATOR_EVENT_DISABLE			0x80
-#define REGULATOR_EVENT_PRE_VOLTAGE_CHANGE	0x100
-#define REGULATOR_EVENT_ABORT_VOLTAGE_CHANGE	0x200
-#define REGULATOR_EVENT_PRE_DISABLE		0x400
-#define REGULATOR_EVENT_ABORT_DISABLE		0x800
-#define REGULATOR_EVENT_ENABLE			0x1000
-/*
- * Following notifications should be emitted only if detected condition
- * is such that the HW is likely to still be working but consumers should
- * take a recovery action to prevent problems esacalating into errors.
- */
-#define REGULATOR_EVENT_UNDER_VOLTAGE_WARN	0x2000
-#define REGULATOR_EVENT_OVER_CURRENT_WARN	0x4000
-#define REGULATOR_EVENT_OVER_VOLTAGE_WARN	0x8000
-#define REGULATOR_EVENT_OVER_TEMP_WARN		0x10000
-#define REGULATOR_EVENT_WARN_MASK		0x1E000
-
-/*
  * Regulator errors that can be queried using regulator_get_error_flags
  *
  * UNDER_VOLTAGE  Regulator output is under voltage.
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index 4b7eceb3828b..22a07c0900a4 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -51,12 +51,7 @@ enum regulator_detection_severity {
 
 /* Initialize struct linear_range for regulators */
 #define REGULATOR_LINEAR_RANGE(_min_uV, _min_sel, _max_sel, _step_uV)	\
-{									\
-	.min		= _min_uV,					\
-	.min_sel	= _min_sel,					\
-	.max_sel	= _max_sel,					\
-	.step		= _step_uV,					\
-}
+	LINEAR_RANGE(_min_uV, _min_sel, _max_sel, _step_uV)
 
 /**
  * struct regulator_ops - regulator operations.
diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h
index 621b7f4a3639..0cd76d264727 100644
--- a/include/linux/regulator/machine.h
+++ b/include/linux/regulator/machine.h
@@ -49,6 +49,13 @@ struct regulator;
 #define DISABLE_IN_SUSPEND	1
 #define ENABLE_IN_SUSPEND	2
 
+/*
+ * Default time window (in milliseconds) following a critical under-voltage
+ * event during which less critical actions can be safely carried out by the
+ * system.
+ */
+#define REGULATOR_DEF_UV_LESS_CRITICAL_WINDOW_MS	10
+
 /* Regulator active discharge flags */
 enum regulator_active_discharge {
 	REGULATOR_ACTIVE_DISCHARGE_DEFAULT,
@@ -127,6 +134,8 @@ struct notification_limit {
  * @ramp_disable: Disable ramp delay when initialising or when setting voltage.
  * @soft_start: Enable soft start so that voltage ramps slowly.
  * @pull_down: Enable pull down when regulator is disabled.
+ * @system_critical: Set if the regulator is critical to system stability or
+ *                   functionality.
  * @over_current_protection: Auto disable on over current event.
  *
  * @over_current_detection: Configure over current limits.
@@ -153,6 +162,13 @@ struct notification_limit {
  *		      regulator_active_discharge values are used for
  *		      initialisation.
  * @enable_time: Turn-on time of the rails (unit: microseconds)
+ * @uv_less_critical_window_ms: Specifies the time window (in milliseconds)
+ *                              following a critical under-voltage (UV) event
+ *                              during which less critical actions can be
+ *                              safely carried out by the system (for example
+ *                              logging). After this time window more critical
+ *                              actions should be done (for example prevent
+ *                              HW damage).
  */
 struct regulation_constraints {
 
@@ -204,6 +220,7 @@ struct regulation_constraints {
 	unsigned int settling_time_up;
 	unsigned int settling_time_down;
 	unsigned int enable_time;
+	unsigned int uv_less_critical_window_ms;
 
 	unsigned int active_discharge;
 
@@ -214,6 +231,7 @@ struct regulation_constraints {
 	unsigned ramp_disable:1; /* disable ramp delay */
 	unsigned soft_start:1;	/* ramp voltage slowly */
 	unsigned pull_down:1;	/* pull down resistor when regulator off */
+	unsigned system_critical:1;	/* critical to system stability */
 	unsigned over_current_protection:1; /* auto disable on over current */
 	unsigned over_current_detection:1; /* notify on over current */
 	unsigned over_voltage_detection:1; /* notify on over voltage */
diff --git a/include/linux/restart_block.h b/include/linux/restart_block.h
index 980a65594412..13f17676c5f4 100644
--- a/include/linux/restart_block.h
+++ b/include/linux/restart_block.h
@@ -7,8 +7,8 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
-#include <linux/time64.h>
 
+struct __kernel_timespec;
 struct timespec;
 struct old_timespec32;
 struct pollfd;
diff --git a/include/linux/resume_user_mode.h b/include/linux/resume_user_mode.h
index f8f3e958e9cf..e0135e0adae0 100644
--- a/include/linux/resume_user_mode.h
+++ b/include/linux/resume_user_mode.h
@@ -6,6 +6,7 @@
 #include <linux/sched.h>
 #include <linux/task_work.h>
 #include <linux/memcontrol.h>
+#include <linux/rseq.h>
 #include <linux/blk-cgroup.h>
 
 /**
diff --git a/include/linux/rethook.h b/include/linux/rethook.h
index ce69b2b7bc35..ba60962805f6 100644
--- a/include/linux/rethook.h
+++ b/include/linux/rethook.h
@@ -28,7 +28,12 @@ typedef void (*rethook_handler_t) (struct rethook_node *, void *, unsigned long,
  */
 struct rethook {
 	void			*data;
-	rethook_handler_t	handler;
+	/*
+	 * To avoid sparse warnings, this uses a raw function pointer with
+	 * __rcu, instead of rethook_handler_t. But this must be same as
+	 * rethook_handler_t.
+	 */
+	void (__rcu *handler) (struct rethook_node *, void *, unsigned long, struct pt_regs *);
 	struct objpool_head	pool;
 	struct rcu_head		rcu;
 };
diff --git a/include/linux/rhashtable-types.h b/include/linux/rhashtable-types.h
index 57467cbf4c5b..b6f3797277ff 100644
--- a/include/linux/rhashtable-types.h
+++ b/include/linux/rhashtable-types.h
@@ -12,7 +12,7 @@
 #include <linux/atomic.h>
 #include <linux/compiler.h>
 #include <linux/mutex.h>
-#include <linux/workqueue.h>
+#include <linux/workqueue_types.h>
 
 struct rhash_head {
 	struct rhash_head __rcu		*next;
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index b26fe858fd44..b7944a833668 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -121,6 +121,11 @@ static inline void anon_vma_lock_write(struct anon_vma *anon_vma)
 	down_write(&anon_vma->root->rwsem);
 }
 
+static inline int anon_vma_trylock_write(struct anon_vma *anon_vma)
+{
+	return down_write_trylock(&anon_vma->root->rwsem);
+}
+
 static inline void anon_vma_unlock_write(struct anon_vma *anon_vma)
 {
 	up_write(&anon_vma->root->rwsem);
@@ -172,133 +177,323 @@ struct anon_vma *folio_get_anon_vma(struct folio *folio);
 typedef int __bitwise rmap_t;
 
 /*
- * No special request: if the page is a subpage of a compound page, it is
- * mapped via a PTE. The mapped (sub)page is possibly shared between processes.
+ * No special request: A mapped anonymous (sub)page is possibly shared between
+ * processes.
  */
 #define RMAP_NONE		((__force rmap_t)0)
 
-/* The (sub)page is exclusive to a single process. */
+/* The anonymous (sub)page is exclusive to a single process. */
 #define RMAP_EXCLUSIVE		((__force rmap_t)BIT(0))
 
 /*
- * The compound page is not mapped via PTEs, but instead via a single PMD and
- * should be accounted accordingly.
+ * Internally, we're using an enum to specify the granularity. We make the
+ * compiler emit specialized code for each granularity.
  */
-#define RMAP_COMPOUND		((__force rmap_t)BIT(1))
+enum rmap_level {
+	RMAP_LEVEL_PTE = 0,
+	RMAP_LEVEL_PMD,
+};
+
+static inline void __folio_rmap_sanity_checks(struct folio *folio,
+		struct page *page, int nr_pages, enum rmap_level level)
+{
+	/* hugetlb folios are handled separately. */
+	VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio);
+
+	/*
+	 * TODO: we get driver-allocated folios that have nothing to do with
+	 * the rmap using vm_insert_page(); therefore, we cannot assume that
+	 * folio_test_large_rmappable() holds for large folios. We should
+	 * handle any desired mapcount+stats accounting for these folios in
+	 * VM_MIXEDMAP VMAs separately, and then sanity-check here that
+	 * we really only get rmappable folios.
+	 */
+
+	VM_WARN_ON_ONCE(nr_pages <= 0);
+	VM_WARN_ON_FOLIO(page_folio(page) != folio, folio);
+	VM_WARN_ON_FOLIO(page_folio(page + nr_pages - 1) != folio, folio);
+
+	switch (level) {
+	case RMAP_LEVEL_PTE:
+		break;
+	case RMAP_LEVEL_PMD:
+		/*
+		 * We don't support folios larger than a single PMD yet. So
+		 * when RMAP_LEVEL_PMD is set, we assume that we are creating
+		 * a single "entire" mapping of the folio.
+		 */
+		VM_WARN_ON_FOLIO(folio_nr_pages(folio) != HPAGE_PMD_NR, folio);
+		VM_WARN_ON_FOLIO(nr_pages != HPAGE_PMD_NR, folio);
+		break;
+	default:
+		VM_WARN_ON_ONCE(true);
+	}
+}
 
 /*
  * rmap interfaces called when adding or removing pte of page
  */
 void folio_move_anon_rmap(struct folio *, struct vm_area_struct *);
-void page_add_anon_rmap(struct page *, struct vm_area_struct *,
-		unsigned long address, rmap_t flags);
-void page_add_new_anon_rmap(struct page *, struct vm_area_struct *,
-		unsigned long address);
+void folio_add_anon_rmap_ptes(struct folio *, struct page *, int nr_pages,
+		struct vm_area_struct *, unsigned long address, rmap_t flags);
+#define folio_add_anon_rmap_pte(folio, page, vma, address, flags) \
+	folio_add_anon_rmap_ptes(folio, page, 1, vma, address, flags)
+void folio_add_anon_rmap_pmd(struct folio *, struct page *,
+		struct vm_area_struct *, unsigned long address, rmap_t flags);
 void folio_add_new_anon_rmap(struct folio *, struct vm_area_struct *,
 		unsigned long address);
-void page_add_file_rmap(struct page *, struct vm_area_struct *,
-		bool compound);
-void folio_add_file_rmap_range(struct folio *, struct page *, unsigned int nr,
-		struct vm_area_struct *, bool compound);
-void page_remove_rmap(struct page *, struct vm_area_struct *,
-		bool compound);
-
-void hugepage_add_anon_rmap(struct folio *, struct vm_area_struct *,
+void folio_add_file_rmap_ptes(struct folio *, struct page *, int nr_pages,
+		struct vm_area_struct *);
+#define folio_add_file_rmap_pte(folio, page, vma) \
+	folio_add_file_rmap_ptes(folio, page, 1, vma)
+void folio_add_file_rmap_pmd(struct folio *, struct page *,
+		struct vm_area_struct *);
+void folio_remove_rmap_ptes(struct folio *, struct page *, int nr_pages,
+		struct vm_area_struct *);
+#define folio_remove_rmap_pte(folio, page, vma) \
+	folio_remove_rmap_ptes(folio, page, 1, vma)
+void folio_remove_rmap_pmd(struct folio *, struct page *,
+		struct vm_area_struct *);
+
+void hugetlb_add_anon_rmap(struct folio *, struct vm_area_struct *,
 		unsigned long address, rmap_t flags);
-void hugepage_add_new_anon_rmap(struct folio *, struct vm_area_struct *,
+void hugetlb_add_new_anon_rmap(struct folio *, struct vm_area_struct *,
 		unsigned long address);
 
-static inline void __page_dup_rmap(struct page *page, bool compound)
+/* See folio_try_dup_anon_rmap_*() */
+static inline int hugetlb_try_dup_anon_rmap(struct folio *folio,
+		struct vm_area_struct *vma)
 {
-	if (compound) {
-		struct folio *folio = (struct folio *)page;
+	VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio);
+	VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
 
-		VM_BUG_ON_PAGE(compound && !PageHead(page), page);
-		atomic_inc(&folio->_entire_mapcount);
-	} else {
-		atomic_inc(&page->_mapcount);
+	if (PageAnonExclusive(&folio->page)) {
+		if (unlikely(folio_needs_cow_for_dma(vma, folio)))
+			return -EBUSY;
+		ClearPageAnonExclusive(&folio->page);
 	}
+	atomic_inc(&folio->_entire_mapcount);
+	return 0;
+}
+
+/* See folio_try_share_anon_rmap_*() */
+static inline int hugetlb_try_share_anon_rmap(struct folio *folio)
+{
+	VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio);
+	VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
+	VM_WARN_ON_FOLIO(!PageAnonExclusive(&folio->page), folio);
+
+	/* Paired with the memory barrier in try_grab_folio(). */
+	if (IS_ENABLED(CONFIG_HAVE_FAST_GUP))
+		smp_mb();
+
+	if (unlikely(folio_maybe_dma_pinned(folio)))
+		return -EBUSY;
+	ClearPageAnonExclusive(&folio->page);
+
+	/*
+	 * This is conceptually a smp_wmb() paired with the smp_rmb() in
+	 * gup_must_unshare().
+	 */
+	if (IS_ENABLED(CONFIG_HAVE_FAST_GUP))
+		smp_mb__after_atomic();
+	return 0;
+}
+
+static inline void hugetlb_add_file_rmap(struct folio *folio)
+{
+	VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio);
+	VM_WARN_ON_FOLIO(folio_test_anon(folio), folio);
+
+	atomic_inc(&folio->_entire_mapcount);
+}
+
+static inline void hugetlb_remove_rmap(struct folio *folio)
+{
+	VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio);
+
+	atomic_dec(&folio->_entire_mapcount);
 }
 
-static inline void page_dup_file_rmap(struct page *page, bool compound)
+static __always_inline void __folio_dup_file_rmap(struct folio *folio,
+		struct page *page, int nr_pages, enum rmap_level level)
 {
-	__page_dup_rmap(page, compound);
+	__folio_rmap_sanity_checks(folio, page, nr_pages, level);
+
+	switch (level) {
+	case RMAP_LEVEL_PTE:
+		do {
+			atomic_inc(&page->_mapcount);
+		} while (page++, --nr_pages > 0);
+		break;
+	case RMAP_LEVEL_PMD:
+		atomic_inc(&folio->_entire_mapcount);
+		break;
+	}
 }
 
 /**
- * page_try_dup_anon_rmap - try duplicating a mapping of an already mapped
- *			    anonymous page
- * @page: the page to duplicate the mapping for
- * @compound: the page is mapped as compound or as a small page
- * @vma: the source vma
+ * folio_dup_file_rmap_ptes - duplicate PTE mappings of a page range of a folio
+ * @folio:	The folio to duplicate the mappings of
+ * @page:	The first page to duplicate the mappings of
+ * @nr_pages:	The number of pages of which the mapping will be duplicated
  *
- * The caller needs to hold the PT lock and the vma->vma_mm->write_protect_seq.
+ * The page range of the folio is defined by [page, page + nr_pages)
  *
- * Duplicating the mapping can only fail if the page may be pinned; device
- * private pages cannot get pinned and consequently this function cannot fail.
+ * The caller needs to hold the page table lock.
+ */
+static inline void folio_dup_file_rmap_ptes(struct folio *folio,
+		struct page *page, int nr_pages)
+{
+	__folio_dup_file_rmap(folio, page, nr_pages, RMAP_LEVEL_PTE);
+}
+#define folio_dup_file_rmap_pte(folio, page) \
+	folio_dup_file_rmap_ptes(folio, page, 1)
+
+/**
+ * folio_dup_file_rmap_pmd - duplicate a PMD mapping of a page range of a folio
+ * @folio:	The folio to duplicate the mapping of
+ * @page:	The first page to duplicate the mapping of
  *
- * If duplicating the mapping succeeds, the page has to be mapped R/O into
- * the parent and the child. It must *not* get mapped writable after this call.
+ * The page range of the folio is defined by [page, page + HPAGE_PMD_NR)
  *
- * Returns 0 if duplicating the mapping succeeded. Returns -EBUSY otherwise.
+ * The caller needs to hold the page table lock.
  */
-static inline int page_try_dup_anon_rmap(struct page *page, bool compound,
-					 struct vm_area_struct *vma)
+static inline void folio_dup_file_rmap_pmd(struct folio *folio,
+		struct page *page)
 {
-	VM_BUG_ON_PAGE(!PageAnon(page), page);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	__folio_dup_file_rmap(folio, page, HPAGE_PMD_NR, RMAP_LEVEL_PTE);
+#else
+	WARN_ON_ONCE(true);
+#endif
+}
 
-	/*
-	 * No need to check+clear for already shared pages, including KSM
-	 * pages.
-	 */
-	if (!PageAnonExclusive(page))
-		goto dup;
+static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio,
+		struct page *page, int nr_pages, struct vm_area_struct *src_vma,
+		enum rmap_level level)
+{
+	bool maybe_pinned;
+	int i;
+
+	VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
+	__folio_rmap_sanity_checks(folio, page, nr_pages, level);
 
 	/*
-	 * If this page may have been pinned by the parent process,
-	 * don't allow to duplicate the mapping but instead require to e.g.,
-	 * copy the page immediately for the child so that we'll always
-	 * guarantee the pinned page won't be randomly replaced in the
+	 * If this folio may have been pinned by the parent process,
+	 * don't allow to duplicate the mappings but instead require to e.g.,
+	 * copy the subpage immediately for the child so that we'll always
+	 * guarantee the pinned folio won't be randomly replaced in the
 	 * future on write faults.
 	 */
-	if (likely(!is_device_private_page(page) &&
-	    unlikely(page_needs_cow_for_dma(vma, page))))
-		return -EBUSY;
+	maybe_pinned = likely(!folio_is_device_private(folio)) &&
+		       unlikely(folio_needs_cow_for_dma(src_vma, folio));
 
-	ClearPageAnonExclusive(page);
 	/*
-	 * It's okay to share the anon page between both processes, mapping
-	 * the page R/O into both processes.
+	 * No need to check+clear for already shared PTEs/PMDs of the
+	 * folio. But if any page is PageAnonExclusive, we must fallback to
+	 * copying if the folio maybe pinned.
 	 */
-dup:
-	__page_dup_rmap(page, compound);
+	switch (level) {
+	case RMAP_LEVEL_PTE:
+		if (unlikely(maybe_pinned)) {
+			for (i = 0; i < nr_pages; i++)
+				if (PageAnonExclusive(page + i))
+					return -EBUSY;
+		}
+		do {
+			if (PageAnonExclusive(page))
+				ClearPageAnonExclusive(page);
+			atomic_inc(&page->_mapcount);
+		} while (page++, --nr_pages > 0);
+		break;
+	case RMAP_LEVEL_PMD:
+		if (PageAnonExclusive(page)) {
+			if (unlikely(maybe_pinned))
+				return -EBUSY;
+			ClearPageAnonExclusive(page);
+		}
+		atomic_inc(&folio->_entire_mapcount);
+		break;
+	}
 	return 0;
 }
 
 /**
- * page_try_share_anon_rmap - try marking an exclusive anonymous page possibly
- *			      shared to prepare for KSM or temporary unmapping
- * @page: the exclusive anonymous page to try marking possibly shared
+ * folio_try_dup_anon_rmap_ptes - try duplicating PTE mappings of a page range
+ *				  of a folio
+ * @folio:	The folio to duplicate the mappings of
+ * @page:	The first page to duplicate the mappings of
+ * @nr_pages:	The number of pages of which the mapping will be duplicated
+ * @src_vma:	The vm area from which the mappings are duplicated
+ *
+ * The page range of the folio is defined by [page, page + nr_pages)
  *
- * The caller needs to hold the PT lock and has to have the page table entry
- * cleared/invalidated.
+ * The caller needs to hold the page table lock and the
+ * vma->vma_mm->write_protect_seq.
  *
- * This is similar to page_try_dup_anon_rmap(), however, not used during fork()
- * to duplicate a mapping, but instead to prepare for KSM or temporarily
- * unmapping a page (swap, migration) via page_remove_rmap().
+ * Duplicating the mappings can only fail if the folio may be pinned; device
+ * private folios cannot get pinned and consequently this function cannot fail
+ * for them.
  *
- * Marking the page shared can only fail if the page may be pinned; device
- * private pages cannot get pinned and consequently this function cannot fail.
+ * If duplicating the mappings succeeded, the duplicated PTEs have to be R/O in
+ * the parent and the child. They must *not* be writable after this call
+ * succeeded.
  *
- * Returns 0 if marking the page possibly shared succeeded. Returns -EBUSY
- * otherwise.
+ * Returns 0 if duplicating the mappings succeeded. Returns -EBUSY otherwise.
  */
-static inline int page_try_share_anon_rmap(struct page *page)
+static inline int folio_try_dup_anon_rmap_ptes(struct folio *folio,
+		struct page *page, int nr_pages, struct vm_area_struct *src_vma)
 {
-	VM_BUG_ON_PAGE(!PageAnon(page) || !PageAnonExclusive(page), page);
+	return __folio_try_dup_anon_rmap(folio, page, nr_pages, src_vma,
+					 RMAP_LEVEL_PTE);
+}
+#define folio_try_dup_anon_rmap_pte(folio, page, vma) \
+	folio_try_dup_anon_rmap_ptes(folio, page, 1, vma)
 
-	/* device private pages cannot get pinned via GUP. */
-	if (unlikely(is_device_private_page(page))) {
+/**
+ * folio_try_dup_anon_rmap_pmd - try duplicating a PMD mapping of a page range
+ *				 of a folio
+ * @folio:	The folio to duplicate the mapping of
+ * @page:	The first page to duplicate the mapping of
+ * @src_vma:	The vm area from which the mapping is duplicated
+ *
+ * The page range of the folio is defined by [page, page + HPAGE_PMD_NR)
+ *
+ * The caller needs to hold the page table lock and the
+ * vma->vma_mm->write_protect_seq.
+ *
+ * Duplicating the mapping can only fail if the folio may be pinned; device
+ * private folios cannot get pinned and consequently this function cannot fail
+ * for them.
+ *
+ * If duplicating the mapping succeeds, the duplicated PMD has to be R/O in
+ * the parent and the child. They must *not* be writable after this call
+ * succeeded.
+ *
+ * Returns 0 if duplicating the mapping succeeded. Returns -EBUSY otherwise.
+ */
+static inline int folio_try_dup_anon_rmap_pmd(struct folio *folio,
+		struct page *page, struct vm_area_struct *src_vma)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	return __folio_try_dup_anon_rmap(folio, page, HPAGE_PMD_NR, src_vma,
+					 RMAP_LEVEL_PMD);
+#else
+	WARN_ON_ONCE(true);
+	return -EBUSY;
+#endif
+}
+
+static __always_inline int __folio_try_share_anon_rmap(struct folio *folio,
+		struct page *page, int nr_pages, enum rmap_level level)
+{
+	VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
+	VM_WARN_ON_FOLIO(!PageAnonExclusive(page), folio);
+	__folio_rmap_sanity_checks(folio, page, nr_pages, level);
+
+	/* device private folios cannot get pinned via GUP. */
+	if (unlikely(folio_is_device_private(folio))) {
 		ClearPageAnonExclusive(page);
 		return 0;
 	}
@@ -349,7 +544,7 @@ static inline int page_try_share_anon_rmap(struct page *page)
 	if (IS_ENABLED(CONFIG_HAVE_FAST_GUP))
 		smp_mb();
 
-	if (unlikely(page_maybe_dma_pinned(page)))
+	if (unlikely(folio_maybe_dma_pinned(folio)))
 		return -EBUSY;
 	ClearPageAnonExclusive(page);
 
@@ -362,6 +557,68 @@ static inline int page_try_share_anon_rmap(struct page *page)
 	return 0;
 }
 
+/**
+ * folio_try_share_anon_rmap_pte - try marking an exclusive anonymous page
+ *				   mapped by a PTE possibly shared to prepare
+ *				   for KSM or temporary unmapping
+ * @folio:	The folio to share a mapping of
+ * @page:	The mapped exclusive page
+ *
+ * The caller needs to hold the page table lock and has to have the page table
+ * entries cleared/invalidated.
+ *
+ * This is similar to folio_try_dup_anon_rmap_pte(), however, not used during
+ * fork() to duplicate mappings, but instead to prepare for KSM or temporarily
+ * unmapping parts of a folio (swap, migration) via folio_remove_rmap_pte().
+ *
+ * Marking the mapped page shared can only fail if the folio maybe pinned;
+ * device private folios cannot get pinned and consequently this function cannot
+ * fail.
+ *
+ * Returns 0 if marking the mapped page possibly shared succeeded. Returns
+ * -EBUSY otherwise.
+ */
+static inline int folio_try_share_anon_rmap_pte(struct folio *folio,
+		struct page *page)
+{
+	return __folio_try_share_anon_rmap(folio, page, 1, RMAP_LEVEL_PTE);
+}
+
+/**
+ * folio_try_share_anon_rmap_pmd - try marking an exclusive anonymous page
+ *				   range mapped by a PMD possibly shared to
+ *				   prepare for temporary unmapping
+ * @folio:	The folio to share the mapping of
+ * @page:	The first page to share the mapping of
+ *
+ * The page range of the folio is defined by [page, page + HPAGE_PMD_NR)
+ *
+ * The caller needs to hold the page table lock and has to have the page table
+ * entries cleared/invalidated.
+ *
+ * This is similar to folio_try_dup_anon_rmap_pmd(), however, not used during
+ * fork() to duplicate a mapping, but instead to prepare for temporarily
+ * unmapping parts of a folio (swap, migration) via folio_remove_rmap_pmd().
+ *
+ * Marking the mapped pages shared can only fail if the folio maybe pinned;
+ * device private folios cannot get pinned and consequently this function cannot
+ * fail.
+ *
+ * Returns 0 if marking the mapped pages possibly shared succeeded. Returns
+ * -EBUSY otherwise.
+ */
+static inline int folio_try_share_anon_rmap_pmd(struct folio *folio,
+		struct page *page)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	return __folio_try_share_anon_rmap(folio, page, HPAGE_PMD_NR,
+					   RMAP_LEVEL_PMD);
+#else
+	WARN_ON_ONCE(true);
+	return -EBUSY;
+#endif
+}
+
 /*
  * Called from mm/vmscan.c to handle paging out
  */
diff --git a/include/linux/rseq.h b/include/linux/rseq.h
new file mode 100644
index 000000000000..bc8af3eb5598
--- /dev/null
+++ b/include/linux/rseq.h
@@ -0,0 +1,131 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+#ifndef _LINUX_RSEQ_H
+#define _LINUX_RSEQ_H
+
+#ifdef CONFIG_RSEQ
+
+#include <linux/preempt.h>
+#include <linux/sched.h>
+
+/*
+ * Map the event mask on the user-space ABI enum rseq_cs_flags
+ * for direct mask checks.
+ */
+enum rseq_event_mask_bits {
+	RSEQ_EVENT_PREEMPT_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT,
+	RSEQ_EVENT_SIGNAL_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT,
+	RSEQ_EVENT_MIGRATE_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT,
+};
+
+enum rseq_event_mask {
+	RSEQ_EVENT_PREEMPT	= (1U << RSEQ_EVENT_PREEMPT_BIT),
+	RSEQ_EVENT_SIGNAL	= (1U << RSEQ_EVENT_SIGNAL_BIT),
+	RSEQ_EVENT_MIGRATE	= (1U << RSEQ_EVENT_MIGRATE_BIT),
+};
+
+static inline void rseq_set_notify_resume(struct task_struct *t)
+{
+	if (t->rseq)
+		set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
+}
+
+void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs);
+
+static inline void rseq_handle_notify_resume(struct ksignal *ksig,
+					     struct pt_regs *regs)
+{
+	if (current->rseq)
+		__rseq_handle_notify_resume(ksig, regs);
+}
+
+static inline void rseq_signal_deliver(struct ksignal *ksig,
+				       struct pt_regs *regs)
+{
+	preempt_disable();
+	__set_bit(RSEQ_EVENT_SIGNAL_BIT, &current->rseq_event_mask);
+	preempt_enable();
+	rseq_handle_notify_resume(ksig, regs);
+}
+
+/* rseq_preempt() requires preemption to be disabled. */
+static inline void rseq_preempt(struct task_struct *t)
+{
+	__set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask);
+	rseq_set_notify_resume(t);
+}
+
+/* rseq_migrate() requires preemption to be disabled. */
+static inline void rseq_migrate(struct task_struct *t)
+{
+	__set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask);
+	rseq_set_notify_resume(t);
+}
+
+/*
+ * If parent process has a registered restartable sequences area, the
+ * child inherits. Unregister rseq for a clone with CLONE_VM set.
+ */
+static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
+{
+	if (clone_flags & CLONE_VM) {
+		t->rseq = NULL;
+		t->rseq_len = 0;
+		t->rseq_sig = 0;
+		t->rseq_event_mask = 0;
+	} else {
+		t->rseq = current->rseq;
+		t->rseq_len = current->rseq_len;
+		t->rseq_sig = current->rseq_sig;
+		t->rseq_event_mask = current->rseq_event_mask;
+	}
+}
+
+static inline void rseq_execve(struct task_struct *t)
+{
+	t->rseq = NULL;
+	t->rseq_len = 0;
+	t->rseq_sig = 0;
+	t->rseq_event_mask = 0;
+}
+
+#else
+
+static inline void rseq_set_notify_resume(struct task_struct *t)
+{
+}
+static inline void rseq_handle_notify_resume(struct ksignal *ksig,
+					     struct pt_regs *regs)
+{
+}
+static inline void rseq_signal_deliver(struct ksignal *ksig,
+				       struct pt_regs *regs)
+{
+}
+static inline void rseq_preempt(struct task_struct *t)
+{
+}
+static inline void rseq_migrate(struct task_struct *t)
+{
+}
+static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
+{
+}
+static inline void rseq_execve(struct task_struct *t)
+{
+}
+
+#endif
+
+#ifdef CONFIG_DEBUG_RSEQ
+
+void rseq_syscall(struct pt_regs *regs);
+
+#else
+
+static inline void rseq_syscall(struct pt_regs *regs)
+{
+}
+
+#endif
+
+#endif /* _LINUX_RSEQ_H */
diff --git a/include/linux/rslib.h b/include/linux/rslib.h
index 238bb85243d3..a04dacbdc8ae 100644
--- a/include/linux/rslib.h
+++ b/include/linux/rslib.h
@@ -10,7 +10,6 @@
 #ifndef _RSLIB_H_
 #define _RSLIB_H_
 
-#include <linux/list.h>
 #include <linux/types.h>	/* for gfp_t */
 #include <linux/gfp.h>		/* for GFP_KERNEL */
 
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 3d6cf306cd55..410529fca18b 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -10,6 +10,13 @@
 #include <uapi/linux/rtnetlink.h>
 
 extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo);
+
+static inline int rtnetlink_maybe_send(struct sk_buff *skb, struct net *net,
+				       u32 pid, u32 group, int echo)
+{
+	return !skb ? 0 : rtnetlink_send(skb, net, pid, group, echo);
+}
+
 extern int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid);
 extern void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid,
 			u32 group, const struct nlmsghdr *nlh, gfp_t flags);
@@ -72,6 +79,18 @@ static inline bool lockdep_rtnl_is_held(void)
 #define rtnl_dereference(p)					\
 	rcu_dereference_protected(p, lockdep_rtnl_is_held())
 
+/**
+ * rcu_replace_pointer_rtnl - replace an RCU pointer under rtnl_lock, returning
+ * its old value
+ * @rp: RCU pointer, whose value is returned
+ * @p: regular pointer
+ *
+ * Perform a replacement under rtnl_lock, where @rp is an RCU-annotated
+ * pointer. The old value of @rp is returned, and @rp is set to @p
+ */
+#define rcu_replace_pointer_rtnl(rp, p)			\
+	rcu_replace_pointer(rp, p, lockdep_rtnl_is_held())
+
 static inline struct netdev_queue *dev_ingress_queue(struct net_device *dev)
 {
 	return rtnl_dereference(dev->ingress_queue);
@@ -130,4 +149,26 @@ extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 
 extern void rtnl_offload_xstats_notify(struct net_device *dev);
 
+static inline int rtnl_has_listeners(const struct net *net, u32 group)
+{
+	struct sock *rtnl = net->rtnl;
+
+	return netlink_has_listeners(rtnl, group);
+}
+
+/**
+ * rtnl_notify_needed - check if notification is needed
+ * @net: Pointer to the net namespace
+ * @nlflags: netlink ingress message flags
+ * @group: rtnl group
+ *
+ * Based on the ingress message flags and rtnl group, returns true
+ * if a notification is needed, false otherwise.
+ */
+static inline bool
+rtnl_notify_needed(const struct net *net, u16 nlflags, u32 group)
+{
+	return (nlflags & NLM_F_ECHO) || rtnl_has_listeners(net, group);
+}
+
 #endif	/* __LINUX_RTNETLINK_H */
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 1dd530ce8b45..9c29689ff505 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -203,11 +203,11 @@ extern void up_read(struct rw_semaphore *sem);
 extern void up_write(struct rw_semaphore *sem);
 
 DEFINE_GUARD(rwsem_read, struct rw_semaphore *, down_read(_T), up_read(_T))
-DEFINE_GUARD(rwsem_write, struct rw_semaphore *, down_write(_T), up_write(_T))
-
-DEFINE_FREE(up_read, struct rw_semaphore *, if (_T) up_read(_T))
-DEFINE_FREE(up_write, struct rw_semaphore *, if (_T) up_write(_T))
+DEFINE_GUARD_COND(rwsem_read, _try, down_read_trylock(_T))
+DEFINE_GUARD_COND(rwsem_read, _intr, down_read_interruptible(_T) == 0)
 
+DEFINE_GUARD(rwsem_write, struct rw_semaphore *, down_write(_T), up_write(_T))
+DEFINE_GUARD_COND(rwsem_write, _try, down_write_trylock(_T))
 
 /*
  * downgrade write lock to read lock
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 292c31697248..9a66147915b2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -10,33 +10,41 @@
 #include <uapi/linux/sched.h>
 
 #include <asm/current.h>
-
-#include <linux/pid.h>
-#include <linux/sem.h>
+#include <asm/processor.h>
+#include <linux/thread_info.h>
+#include <linux/preempt.h>
+#include <linux/cpumask.h>
+
+#include <linux/cache.h>
+#include <linux/irqflags_types.h>
+#include <linux/smp_types.h>
+#include <linux/pid_types.h>
+#include <linux/sem_types.h>
 #include <linux/shm.h>
 #include <linux/kmsan_types.h>
-#include <linux/mutex.h>
-#include <linux/plist.h>
-#include <linux/hrtimer.h>
-#include <linux/irqflags.h>
-#include <linux/seccomp.h>
-#include <linux/nodemask.h>
-#include <linux/rcupdate.h>
-#include <linux/refcount.h>
+#include <linux/mutex_types.h>
+#include <linux/plist_types.h>
+#include <linux/hrtimer_types.h>
+#include <linux/timer_types.h>
+#include <linux/seccomp_types.h>
+#include <linux/nodemask_types.h>
+#include <linux/refcount_types.h>
 #include <linux/resource.h>
 #include <linux/latencytop.h>
 #include <linux/sched/prio.h>
 #include <linux/sched/types.h>
 #include <linux/signal_types.h>
-#include <linux/syscall_user_dispatch.h>
+#include <linux/syscall_user_dispatch_types.h>
 #include <linux/mm_types_task.h>
 #include <linux/task_io_accounting.h>
-#include <linux/posix-timers.h>
-#include <linux/rseq.h>
-#include <linux/seqlock.h>
+#include <linux/posix-timers_types.h>
+#include <linux/restart_block.h>
+#include <uapi/linux/rseq.h>
+#include <linux/seqlock_types.h>
 #include <linux/kcsan.h>
 #include <linux/rv.h>
 #include <linux/livepatch_sched.h>
+#include <linux/uidgid_types.h>
 #include <asm/kmap_size.h>
 
 /* task_struct member predeclarations (sorted alphabetically): */
@@ -63,11 +71,13 @@ struct robust_list_head;
 struct root_domain;
 struct rq;
 struct sched_attr;
+struct sched_dl_entity;
 struct seq_file;
 struct sighand_struct;
 struct signal_struct;
 struct task_delay_info;
 struct task_group;
+struct task_struct;
 struct user_event_mm;
 
 /*
@@ -413,42 +423,6 @@ struct load_weight {
 	u32				inv_weight;
 };
 
-/**
- * struct util_est - Estimation utilization of FAIR tasks
- * @enqueued: instantaneous estimated utilization of a task/cpu
- * @ewma:     the Exponential Weighted Moving Average (EWMA)
- *            utilization of a task
- *
- * Support data structure to track an Exponential Weighted Moving Average
- * (EWMA) of a FAIR task's utilization. New samples are added to the moving
- * average each time a task completes an activation. Sample's weight is chosen
- * so that the EWMA will be relatively insensitive to transient changes to the
- * task's workload.
- *
- * The enqueued attribute has a slightly different meaning for tasks and cpus:
- * - task:   the task's util_avg at last task dequeue time
- * - cfs_rq: the sum of util_est.enqueued for each RUNNABLE task on that CPU
- * Thus, the util_est.enqueued of a task represents the contribution on the
- * estimated utilization of the CPU where that task is currently enqueued.
- *
- * Only for tasks we track a moving average of the past instantaneous
- * estimated utilization. This allows to absorb sporadic drops in utilization
- * of an otherwise almost periodic task.
- *
- * The UTIL_AVG_UNCHANGED flag is used to synchronize util_est with util_avg
- * updates. When a task is dequeued, its util_est should not be updated if its
- * util_avg has not been updated in the meantime.
- * This information is mapped into the MSB bit of util_est.enqueued at dequeue
- * time. Since max value of util_est.enqueued for a task is 1024 (PELT util_avg
- * for a task) it is safe to use MSB.
- */
-struct util_est {
-	unsigned int			enqueued;
-	unsigned int			ewma;
-#define UTIL_EST_WEIGHT_SHIFT		2
-#define UTIL_AVG_UNCHANGED		0x80000000
-} __attribute__((__aligned__(sizeof(u64))));
-
 /*
  * The load/runnable/util_avg accumulates an infinite geometric series
  * (see __update_load_avg_cfs_rq() in kernel/sched/pelt.c).
@@ -503,9 +477,20 @@ struct sched_avg {
 	unsigned long			load_avg;
 	unsigned long			runnable_avg;
 	unsigned long			util_avg;
-	struct util_est			util_est;
+	unsigned int			util_est;
 } ____cacheline_aligned;
 
+/*
+ * The UTIL_AVG_UNCHANGED flag is used to synchronize util_est with util_avg
+ * updates. When a task is dequeued, its util_est should not be updated if its
+ * util_avg has not been updated in the meantime.
+ * This information is mapped into the MSB bit of util_est at dequeue time.
+ * Since max value of util_est for a task is 1024 (PELT util_avg for a task)
+ * it is safe to use MSB.
+ */
+#define UTIL_EST_WEIGHT_SHIFT		2
+#define UTIL_AVG_UNCHANGED		0x80000000
+
 struct sched_statistics {
 #ifdef CONFIG_SCHEDSTATS
 	u64				wait_start;
@@ -523,7 +508,7 @@ struct sched_statistics {
 	u64				block_max;
 	s64				sum_block_runtime;
 
-	u64				exec_max;
+	s64				exec_max;
 	u64				slice_max;
 
 	u64				nr_migrations_cold;
@@ -553,7 +538,7 @@ struct sched_entity {
 	struct load_weight		load;
 	struct rb_node			run_node;
 	u64				deadline;
-	u64				min_deadline;
+	u64				min_vruntime;
 
 	struct list_head		group_node;
 	unsigned int			on_rq;
@@ -607,6 +592,9 @@ struct sched_rt_entity {
 #endif
 } __randomize_layout;
 
+typedef bool (*dl_server_has_tasks_f)(struct sched_dl_entity *);
+typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *);
+
 struct sched_dl_entity {
 	struct rb_node			rb_node;
 
@@ -654,6 +642,7 @@ struct sched_dl_entity {
 	unsigned int			dl_yielded        : 1;
 	unsigned int			dl_non_contending : 1;
 	unsigned int			dl_overrun	  : 1;
+	unsigned int			dl_server         : 1;
 
 	/*
 	 * Bandwidth enforcement timer. Each -deadline task has its
@@ -668,7 +657,20 @@ struct sched_dl_entity {
 	 * timer is needed to decrease the active utilization at the correct
 	 * time.
 	 */
-	struct hrtimer inactive_timer;
+	struct hrtimer			inactive_timer;
+
+	/*
+	 * Bits for DL-server functionality. Also see the comment near
+	 * dl_server_update().
+	 *
+	 * @rq the runqueue this server is for
+	 *
+	 * @server_has_tasks() returns true if @server_pick return a
+	 * runnable task.
+	 */
+	struct rq			*rq;
+	dl_server_has_tasks_f		server_has_tasks;
+	dl_server_pick_f		server_pick;
 
 #ifdef CONFIG_RT_MUTEXES
 	/*
@@ -795,6 +797,7 @@ struct task_struct {
 	struct sched_entity		se;
 	struct sched_rt_entity		rt;
 	struct sched_dl_entity		dl;
+	struct sched_dl_entity		*dl_server;
 	const struct sched_class	*sched_class;
 
 #ifdef CONFIG_SCHED_CORE
@@ -1561,114 +1564,6 @@ struct task_struct {
 	 */
 };
 
-static inline struct pid *task_pid(struct task_struct *task)
-{
-	return task->thread_pid;
-}
-
-/*
- * the helpers to get the task's different pids as they are seen
- * from various namespaces
- *
- * task_xid_nr()     : global id, i.e. the id seen from the init namespace;
- * task_xid_vnr()    : virtual id, i.e. the id seen from the pid namespace of
- *                     current.
- * task_xid_nr_ns()  : id seen from the ns specified;
- *
- * see also pid_nr() etc in include/linux/pid.h
- */
-pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns);
-
-static inline pid_t task_pid_nr(struct task_struct *tsk)
-{
-	return tsk->pid;
-}
-
-static inline pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
-{
-	return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns);
-}
-
-static inline pid_t task_pid_vnr(struct task_struct *tsk)
-{
-	return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL);
-}
-
-
-static inline pid_t task_tgid_nr(struct task_struct *tsk)
-{
-	return tsk->tgid;
-}
-
-/**
- * pid_alive - check that a task structure is not stale
- * @p: Task structure to be checked.
- *
- * Test if a process is not yet dead (at most zombie state)
- * If pid_alive fails, then pointers within the task structure
- * can be stale and must not be dereferenced.
- *
- * Return: 1 if the process is alive. 0 otherwise.
- */
-static inline int pid_alive(const struct task_struct *p)
-{
-	return p->thread_pid != NULL;
-}
-
-static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
-{
-	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns);
-}
-
-static inline pid_t task_pgrp_vnr(struct task_struct *tsk)
-{
-	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL);
-}
-
-
-static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
-{
-	return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns);
-}
-
-static inline pid_t task_session_vnr(struct task_struct *tsk)
-{
-	return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL);
-}
-
-static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
-{
-	return __task_pid_nr_ns(tsk, PIDTYPE_TGID, ns);
-}
-
-static inline pid_t task_tgid_vnr(struct task_struct *tsk)
-{
-	return __task_pid_nr_ns(tsk, PIDTYPE_TGID, NULL);
-}
-
-static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
-{
-	pid_t pid = 0;
-
-	rcu_read_lock();
-	if (pid_alive(tsk))
-		pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns);
-	rcu_read_unlock();
-
-	return pid;
-}
-
-static inline pid_t task_ppid_nr(const struct task_struct *tsk)
-{
-	return task_ppid_nr_ns(tsk, &init_pid_ns);
-}
-
-/* Obsolete, do not use: */
-static inline pid_t task_pgrp_nr(struct task_struct *tsk)
-{
-	return task_pgrp_nr_ns(tsk, &init_pid_ns);
-}
-
 #define TASK_REPORT_IDLE	(TASK_REPORT + 1)
 #define TASK_REPORT_MAX		(TASK_REPORT_IDLE << 1)
 
@@ -1712,20 +1607,6 @@ static inline char task_state_to_char(struct task_struct *tsk)
 	return task_index_to_char(task_state_index(tsk));
 }
 
-/**
- * is_global_init - check if a task structure is init. Since init
- * is free to have sub-threads we need to check tgid.
- * @tsk: Task structure to be checked.
- *
- * Check if a task structure is the first user space task the kernel created.
- *
- * Return: 1 if the task structure is init. 0 otherwise.
- */
-static inline int is_global_init(struct task_struct *tsk)
-{
-	return task_tgid_nr(tsk) == 1;
-}
-
 extern struct pid *cad_pid;
 
 /*
@@ -1955,9 +1836,7 @@ extern void ia64_set_curr_task(int cpu, struct task_struct *p);
 void yield(void);
 
 union thread_union {
-#ifndef CONFIG_ARCH_TASK_STRUCT_ON_STACK
 	struct task_struct task;
-#endif
 #ifndef CONFIG_THREAD_INFO_IN_TASK
 	struct thread_info thread_info;
 #endif
@@ -2177,15 +2056,6 @@ extern int __cond_resched_rwlock_write(rwlock_t *lock);
 	__cond_resched_rwlock_write(lock);					\
 })
 
-static inline void cond_resched_rcu(void)
-{
-#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU)
-	rcu_read_unlock();
-	cond_resched();
-	rcu_read_lock();
-#endif
-}
-
 #ifdef CONFIG_PREEMPT_DYNAMIC
 
 extern bool preempt_model_none(void);
@@ -2227,37 +2097,6 @@ static inline bool preempt_model_preemptible(void)
 	return preempt_model_full() || preempt_model_rt();
 }
 
-/*
- * Does a critical section need to be broken due to another
- * task waiting?: (technically does not depend on CONFIG_PREEMPTION,
- * but a general need for low latency)
- */
-static inline int spin_needbreak(spinlock_t *lock)
-{
-#ifdef CONFIG_PREEMPTION
-	return spin_is_contended(lock);
-#else
-	return 0;
-#endif
-}
-
-/*
- * Check if a rwlock is contended.
- * Returns non-zero if there is another task waiting on the rwlock.
- * Returns zero if the lock is not contended or the system / underlying
- * rwlock implementation does not support contention detection.
- * Technically does not depend on CONFIG_PREEMPTION, but a general need
- * for low latency.
- */
-static inline int rwlock_needbreak(rwlock_t *lock)
-{
-#ifdef CONFIG_PREEMPTION
-	return rwlock_is_contended(lock);
-#else
-	return 0;
-#endif
-}
-
 static __always_inline bool need_resched(void)
 {
 	return unlikely(tif_need_resched());
@@ -2292,6 +2131,8 @@ extern bool sched_task_on_rq(struct task_struct *p);
 extern unsigned long get_wchan(struct task_struct *p);
 extern struct task_struct *cpu_curr_snapshot(int cpu);
 
+#include <linux/spinlock.h>
+
 /*
  * In order to reduce various lock holder preemption latencies provide an
  * interface to see if a vCPU is currently running or not.
@@ -2328,129 +2169,6 @@ static inline bool owner_on_cpu(struct task_struct *owner)
 unsigned long sched_cpu_util(int cpu);
 #endif /* CONFIG_SMP */
 
-#ifdef CONFIG_RSEQ
-
-/*
- * Map the event mask on the user-space ABI enum rseq_cs_flags
- * for direct mask checks.
- */
-enum rseq_event_mask_bits {
-	RSEQ_EVENT_PREEMPT_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT,
-	RSEQ_EVENT_SIGNAL_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT,
-	RSEQ_EVENT_MIGRATE_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT,
-};
-
-enum rseq_event_mask {
-	RSEQ_EVENT_PREEMPT	= (1U << RSEQ_EVENT_PREEMPT_BIT),
-	RSEQ_EVENT_SIGNAL	= (1U << RSEQ_EVENT_SIGNAL_BIT),
-	RSEQ_EVENT_MIGRATE	= (1U << RSEQ_EVENT_MIGRATE_BIT),
-};
-
-static inline void rseq_set_notify_resume(struct task_struct *t)
-{
-	if (t->rseq)
-		set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
-}
-
-void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs);
-
-static inline void rseq_handle_notify_resume(struct ksignal *ksig,
-					     struct pt_regs *regs)
-{
-	if (current->rseq)
-		__rseq_handle_notify_resume(ksig, regs);
-}
-
-static inline void rseq_signal_deliver(struct ksignal *ksig,
-				       struct pt_regs *regs)
-{
-	preempt_disable();
-	__set_bit(RSEQ_EVENT_SIGNAL_BIT, &current->rseq_event_mask);
-	preempt_enable();
-	rseq_handle_notify_resume(ksig, regs);
-}
-
-/* rseq_preempt() requires preemption to be disabled. */
-static inline void rseq_preempt(struct task_struct *t)
-{
-	__set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask);
-	rseq_set_notify_resume(t);
-}
-
-/* rseq_migrate() requires preemption to be disabled. */
-static inline void rseq_migrate(struct task_struct *t)
-{
-	__set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask);
-	rseq_set_notify_resume(t);
-}
-
-/*
- * If parent process has a registered restartable sequences area, the
- * child inherits. Unregister rseq for a clone with CLONE_VM set.
- */
-static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
-{
-	if (clone_flags & CLONE_VM) {
-		t->rseq = NULL;
-		t->rseq_len = 0;
-		t->rseq_sig = 0;
-		t->rseq_event_mask = 0;
-	} else {
-		t->rseq = current->rseq;
-		t->rseq_len = current->rseq_len;
-		t->rseq_sig = current->rseq_sig;
-		t->rseq_event_mask = current->rseq_event_mask;
-	}
-}
-
-static inline void rseq_execve(struct task_struct *t)
-{
-	t->rseq = NULL;
-	t->rseq_len = 0;
-	t->rseq_sig = 0;
-	t->rseq_event_mask = 0;
-}
-
-#else
-
-static inline void rseq_set_notify_resume(struct task_struct *t)
-{
-}
-static inline void rseq_handle_notify_resume(struct ksignal *ksig,
-					     struct pt_regs *regs)
-{
-}
-static inline void rseq_signal_deliver(struct ksignal *ksig,
-				       struct pt_regs *regs)
-{
-}
-static inline void rseq_preempt(struct task_struct *t)
-{
-}
-static inline void rseq_migrate(struct task_struct *t)
-{
-}
-static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
-{
-}
-static inline void rseq_execve(struct task_struct *t)
-{
-}
-
-#endif
-
-#ifdef CONFIG_DEBUG_RSEQ
-
-void rseq_syscall(struct pt_regs *regs);
-
-#else
-
-static inline void rseq_syscall(struct pt_regs *regs)
-{
-}
-
-#endif
-
 #ifdef CONFIG_SCHED_CORE
 extern void sched_core_free(struct task_struct *tsk);
 extern void sched_core_fork(struct task_struct *p);
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index fe1a46f30d24..2b461129d1fa 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -2,6 +2,7 @@
 #define _LINUX_SCHED_ISOLATION_H
 
 #include <linux/cpumask.h>
+#include <linux/cpuset.h>
 #include <linux/init.h>
 #include <linux/tick.h>
 
@@ -67,7 +68,8 @@ static inline bool housekeeping_cpu(int cpu, enum hk_type type)
 static inline bool cpu_is_isolated(int cpu)
 {
 	return !housekeeping_test_cpu(cpu, HK_TYPE_DOMAIN) ||
-		 !housekeeping_test_cpu(cpu, HK_TYPE_TICK);
+	       !housekeeping_test_cpu(cpu, HK_TYPE_TICK) ||
+	       cpuset_cpu_is_isolated(cpu);
 }
 
 #endif /* _LINUX_SCHED_ISOLATION_H */
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 3499c1a8b929..4b7664c56208 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -9,6 +9,7 @@
 #include <linux/sched/task.h>
 #include <linux/cred.h>
 #include <linux/refcount.h>
+#include <linux/pid.h>
 #include <linux/posix-timers.h>
 #include <linux/mm_types.h>
 #include <asm/ptrace.h>
@@ -432,7 +433,6 @@ static inline bool fault_signal_pending(vm_fault_t fault_flags,
  * This is required every time the blocked sigset_t changes.
  * callers must hold sighand->siglock.
  */
-extern void recalc_sigpending_and_wake(struct task_struct *t);
 extern void recalc_sigpending(void);
 extern void calculate_sigpending(void);
 
@@ -646,6 +646,9 @@ extern bool current_is_single_threaded(void);
 #define while_each_thread(g, t) \
 	while ((t = next_thread(t)) != g)
 
+#define for_other_threads(p, t)	\
+	for (t = p; (t = next_thread(t)) != p; )
+
 #define __for_each_thread(signal, t)	\
 	list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node, \
 		lockdep_is_held(&tasklist_lock))
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index a23af225c898..d362aacf9f89 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -7,6 +7,8 @@
  * functionality:
  */
 
+#include <linux/rcupdate.h>
+#include <linux/refcount.h>
 #include <linux/sched.h>
 #include <linux/uaccess.h>
 
@@ -226,4 +228,6 @@ static inline void task_unlock(struct task_struct *p)
 	spin_unlock(&p->alloc_lock);
 }
 
+DEFINE_GUARD(task_lock, struct task_struct *, task_lock(_T), task_unlock(_T))
+
 #endif /* _LINUX_SCHED_TASK_H */
diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h
index f158b025c175..ccd72b978e1f 100644
--- a/include/linux/sched/task_stack.h
+++ b/include/linux/sched/task_stack.h
@@ -8,6 +8,7 @@
 
 #include <linux/sched.h>
 #include <linux/magic.h>
+#include <linux/refcount.h>
 
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index de545ba85218..a6e04b4a21d7 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -279,6 +279,14 @@ void arch_update_thermal_pressure(const struct cpumask *cpus,
 { }
 #endif
 
+#ifndef arch_scale_freq_ref
+static __always_inline
+unsigned int arch_scale_freq_ref(int cpu)
+{
+	return 0;
+}
+#endif
+
 static inline int task_node(const struct task_struct *p)
 {
 	return cpu_to_node(task_cpu(p));
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 175079552f68..709ad84809e1 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -3,6 +3,7 @@
 #define _LINUX_SECCOMP_H
 
 #include <uapi/linux/seccomp.h>
+#include <linux/seccomp_types.h>
 
 #define SECCOMP_FILTER_FLAG_MASK	(SECCOMP_FILTER_FLAG_TSYNC | \
 					 SECCOMP_FILTER_FLAG_LOG | \
@@ -21,25 +22,6 @@
 #include <linux/atomic.h>
 #include <asm/seccomp.h>
 
-struct seccomp_filter;
-/**
- * struct seccomp - the state of a seccomp'ed process
- *
- * @mode:  indicates one of the valid values above for controlled
- *         system calls available to a process.
- * @filter_count: number of seccomp filters
- * @filter: must always point to a valid seccomp-filter or NULL as it is
- *          accessed without locking during system call entry.
- *
- *          @filter must only be accessed from the context of current as there
- *          is no read locking.
- */
-struct seccomp {
-	int mode;
-	atomic_t filter_count;
-	struct seccomp_filter *filter;
-};
-
 #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
 extern int __secure_computing(const struct seccomp_data *sd);
 static inline int secure_computing(void)
@@ -64,8 +46,6 @@ static inline int seccomp_mode(struct seccomp *s)
 
 #include <linux/errno.h>
 
-struct seccomp { };
-struct seccomp_filter { };
 struct seccomp_data;
 
 #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
@@ -126,6 +106,8 @@ static inline long seccomp_get_metadata(struct task_struct *task,
 
 #ifdef CONFIG_SECCOMP_CACHE_DEBUG
 struct seq_file;
+struct pid_namespace;
+struct pid;
 
 int proc_pid_seccomp_cache(struct seq_file *m, struct pid_namespace *ns,
 			   struct pid *pid, struct task_struct *task);
diff --git a/include/linux/seccomp_types.h b/include/linux/seccomp_types.h
new file mode 100644
index 000000000000..cf0a0355024f
--- /dev/null
+++ b/include/linux/seccomp_types.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SECCOMP_TYPES_H
+#define _LINUX_SECCOMP_TYPES_H
+
+#include <linux/types.h>
+
+#ifdef CONFIG_SECCOMP
+
+struct seccomp_filter;
+/**
+ * struct seccomp - the state of a seccomp'ed process
+ *
+ * @mode:  indicates one of the valid values above for controlled
+ *         system calls available to a process.
+ * @filter_count: number of seccomp filters
+ * @filter: must always point to a valid seccomp-filter or NULL as it is
+ *          accessed without locking during system call entry.
+ *
+ *          @filter must only be accessed from the context of current as there
+ *          is no read locking.
+ */
+struct seccomp {
+	int mode;
+	atomic_t filter_count;
+	struct seccomp_filter *filter;
+};
+
+#else
+
+struct seccomp { };
+struct seccomp_filter { };
+
+#endif
+
+#endif /* _LINUX_SECCOMP_TYPES_H */
diff --git a/include/linux/security.h b/include/linux/security.h
index 1d1df326c881..d0eb20f90b26 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -32,6 +32,7 @@
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/sockptr.h>
+#include <uapi/linux/lsm.h>
 
 struct linux_binprm;
 struct cred;
@@ -60,6 +61,7 @@ struct fs_parameter;
 enum fs_value_type;
 struct watch;
 struct watch_notification;
+struct lsm_ctx;
 
 /* Default (no) options for the capable function */
 #define CAP_OPT_NONE 0x0
@@ -138,6 +140,8 @@ enum lockdown_reason {
 };
 
 extern const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1];
+extern u32 lsm_active_cnt;
+extern const struct lsm_id *lsm_idlist[];
 
 /* These functions are in security/commoncap.c */
 extern int cap_capable(const struct cred *cred, struct user_namespace *ns,
@@ -261,6 +265,7 @@ int unregister_blocking_lsm_notifier(struct notifier_block *nb);
 /* prototypes */
 extern int security_init(void);
 extern int early_security_init(void);
+extern u64 lsm_name_to_attr(const char *name);
 
 /* Security operations */
 int security_binder_set_context_mgr(const struct cred *mgr);
@@ -389,6 +394,8 @@ int security_file_permission(struct file *file, int mask);
 int security_file_alloc(struct file *file);
 void security_file_free(struct file *file);
 int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+int security_file_ioctl_compat(struct file *file, unsigned int cmd,
+			       unsigned long arg);
 int security_mmap_file(struct file *file, unsigned long prot,
 			unsigned long flags);
 int security_mmap_addr(unsigned long addr);
@@ -470,10 +477,13 @@ int security_sem_semctl(struct kern_ipc_perm *sma, int cmd);
 int security_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops,
 			unsigned nsops, int alter);
 void security_d_instantiate(struct dentry *dentry, struct inode *inode);
-int security_getprocattr(struct task_struct *p, const char *lsm, const char *name,
+int security_getselfattr(unsigned int attr, struct lsm_ctx __user *ctx,
+			 size_t __user *size, u32 flags);
+int security_setselfattr(unsigned int attr, struct lsm_ctx __user *ctx,
+			 size_t size, u32 flags);
+int security_getprocattr(struct task_struct *p, int lsmid, const char *name,
 			 char **value);
-int security_setprocattr(const char *lsm, const char *name, void *value,
-			 size_t size);
+int security_setprocattr(int lsmid, const char *name, void *value, size_t size);
 int security_netlink_send(struct sock *sk, struct sk_buff *skb);
 int security_ismaclabel(const char *name);
 int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen);
@@ -484,6 +494,8 @@ int security_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen);
 int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen);
 int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen);
 int security_locked_down(enum lockdown_reason what);
+int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, size_t *uctx_len,
+		      void *val, size_t val_len, u64 id, u64 flags);
 #else /* CONFIG_SECURITY */
 
 static inline int call_blocking_lsm_notifier(enum lsm_event event, void *data)
@@ -501,6 +513,11 @@ static inline  int unregister_blocking_lsm_notifier(struct notifier_block *nb)
 	return 0;
 }
 
+static inline u64 lsm_name_to_attr(const char *name)
+{
+	return LSM_ATTR_UNDEF;
+}
+
 static inline void security_free_mnt_opts(void **mnt_opts)
 {
 }
@@ -987,6 +1004,13 @@ static inline int security_file_ioctl(struct file *file, unsigned int cmd,
 	return 0;
 }
 
+static inline int security_file_ioctl_compat(struct file *file,
+					     unsigned int cmd,
+					     unsigned long arg)
+{
+	return 0;
+}
+
 static inline int security_mmap_file(struct file *file, unsigned long prot,
 				     unsigned long flags)
 {
@@ -1337,14 +1361,28 @@ static inline void security_d_instantiate(struct dentry *dentry,
 					  struct inode *inode)
 { }
 
-static inline int security_getprocattr(struct task_struct *p, const char *lsm,
+static inline int security_getselfattr(unsigned int attr,
+				       struct lsm_ctx __user *ctx,
+				       size_t __user *size, u32 flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int security_setselfattr(unsigned int attr,
+				       struct lsm_ctx __user *ctx,
+				       size_t size, u32 flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int security_getprocattr(struct task_struct *p, int lsmid,
 				       const char *name, char **value)
 {
 	return -EINVAL;
 }
 
-static inline int security_setprocattr(const char *lsm, char *name,
-				       void *value, size_t size)
+static inline int security_setprocattr(int lsmid, char *name, void *value,
+				       size_t size)
 {
 	return -EINVAL;
 }
@@ -1395,6 +1433,12 @@ static inline int security_locked_down(enum lockdown_reason what)
 {
 	return 0;
 }
+static inline int lsm_fill_user_ctx(struct lsm_ctx __user *uctx,
+				    size_t *uctx_len, void *val, size_t val_len,
+				    u64 id, u64 flags)
+{
+	return -EOPNOTSUPP;
+}
 #endif	/* CONFIG_SECURITY */
 
 #if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE)
diff --git a/include/linux/sem.h b/include/linux/sem.h
index 5608a500c43e..c4deefe42aeb 100644
--- a/include/linux/sem.h
+++ b/include/linux/sem.h
@@ -3,25 +3,17 @@
 #define _LINUX_SEM_H
 
 #include <uapi/linux/sem.h>
+#include <linux/sem_types.h>
 
 struct task_struct;
-struct sem_undo_list;
 
 #ifdef CONFIG_SYSVIPC
 
-struct sysv_sem {
-	struct sem_undo_list *undo_list;
-};
-
 extern int copy_semundo(unsigned long clone_flags, struct task_struct *tsk);
 extern void exit_sem(struct task_struct *tsk);
 
 #else
 
-struct sysv_sem {
-	/* empty */
-};
-
 static inline int copy_semundo(unsigned long clone_flags, struct task_struct *tsk)
 {
 	return 0;
diff --git a/include/linux/sem_types.h b/include/linux/sem_types.h
new file mode 100644
index 000000000000..73df1971a7ae
--- /dev/null
+++ b/include/linux/sem_types.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SEM_TYPES_H
+#define _LINUX_SEM_TYPES_H
+
+struct sem_undo_list;
+
+struct sysv_sem {
+#ifdef CONFIG_SYSVIPC
+	struct sem_undo_list *undo_list;
+#endif
+};
+
+#endif /* _LINUX_SEM_TYPES_H */
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index e92f9d5577ba..d90d8ee29d81 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -18,6 +18,7 @@
 #include <linux/lockdep.h>
 #include <linux/mutex.h>
 #include <linux/preempt.h>
+#include <linux/seqlock_types.h>
 #include <linux/spinlock.h>
 
 #include <asm/processor.h>
@@ -37,37 +38,6 @@
  */
 #define KCSAN_SEQLOCK_REGION_MAX 1000
 
-/*
- * Sequence counters (seqcount_t)
- *
- * This is the raw counting mechanism, without any writer protection.
- *
- * Write side critical sections must be serialized and non-preemptible.
- *
- * If readers can be invoked from hardirq or softirq contexts,
- * interrupts or bottom halves must also be respectively disabled before
- * entering the write section.
- *
- * This mechanism can't be used if the protected data contains pointers,
- * as the writer can invalidate a pointer that a reader is following.
- *
- * If the write serialization mechanism is one of the common kernel
- * locking primitives, use a sequence counter with associated lock
- * (seqcount_LOCKNAME_t) instead.
- *
- * If it's desired to automatically handle the sequence counter writer
- * serialization and non-preemptibility requirements, use a sequential
- * lock (seqlock_t) instead.
- *
- * See Documentation/locking/seqlock.rst
- */
-typedef struct seqcount {
-	unsigned sequence;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map dep_map;
-#endif
-} seqcount_t;
-
 static inline void __seqcount_init(seqcount_t *s, const char *name,
 					  struct lock_class_key *key)
 {
@@ -132,28 +102,6 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
  */
 
 /*
- * For PREEMPT_RT, seqcount_LOCKNAME_t write side critical sections cannot
- * disable preemption. It can lead to higher latencies, and the write side
- * sections will not be able to acquire locks which become sleeping locks
- * (e.g. spinlock_t).
- *
- * To remain preemptible while avoiding a possible livelock caused by the
- * reader preempting the writer, use a different technique: let the reader
- * detect if a seqcount_LOCKNAME_t writer is in progress. If that is the
- * case, acquire then release the associated LOCKNAME writer serialization
- * lock. This will allow any possibly-preempted writer to make progress
- * until the end of its writer serialization lock critical section.
- *
- * This lock-unlock technique must be implemented for all of PREEMPT_RT
- * sleeping locks.  See Documentation/locking/locktypes.rst
- */
-#if defined(CONFIG_LOCKDEP) || defined(CONFIG_PREEMPT_RT)
-#define __SEQ_LOCK(expr)	expr
-#else
-#define __SEQ_LOCK(expr)
-#endif
-
-/*
  * typedef seqcount_LOCKNAME_t - sequence counter with LOCKNAME associated
  * @seqcount:	The real sequence counter
  * @lock:	Pointer to the associated lock
@@ -194,11 +142,6 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
  * @lockbase:		prefix for associated lock/unlock
  */
 #define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockbase)	\
-typedef struct seqcount_##lockname {					\
-	seqcount_t		seqcount;				\
-	__SEQ_LOCK(locktype	*lock);					\
-} seqcount_##lockname##_t;						\
-									\
 static __always_inline seqcount_t *					\
 __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s)			\
 {									\
@@ -284,6 +227,7 @@ SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t,  false,    raw_spin)
 SEQCOUNT_LOCKNAME(spinlock,     spinlock_t,      __SEQ_RT, spin)
 SEQCOUNT_LOCKNAME(rwlock,       rwlock_t,        __SEQ_RT, read)
 SEQCOUNT_LOCKNAME(mutex,        struct mutex,    true,     mutex)
+#undef SEQCOUNT_LOCKNAME
 
 /*
  * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t
@@ -794,25 +738,6 @@ static inline void raw_write_seqcount_latch(seqcount_latch_t *s)
 	smp_wmb();      /* increment "sequence" before following stores */
 }
 
-/*
- * Sequential locks (seqlock_t)
- *
- * Sequence counters with an embedded spinlock for writer serialization
- * and non-preemptibility.
- *
- * For more info, see:
- *    - Comments on top of seqcount_t
- *    - Documentation/locking/seqlock.rst
- */
-typedef struct {
-	/*
-	 * Make sure that readers don't starve writers on PREEMPT_RT: use
-	 * seqcount_spinlock_t instead of seqcount_t. Check __SEQ_LOCK().
-	 */
-	seqcount_spinlock_t seqcount;
-	spinlock_t lock;
-} seqlock_t;
-
 #define __SEQLOCK_UNLOCKED(lockname)					\
 	{								\
 		.seqcount = SEQCNT_SPINLOCK_ZERO(lockname, &(lockname).lock), \
diff --git a/include/linux/seqlock_types.h b/include/linux/seqlock_types.h
new file mode 100644
index 000000000000..dfdf43e3fa3d
--- /dev/null
+++ b/include/linux/seqlock_types.h
@@ -0,0 +1,93 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_SEQLOCK_TYPES_H
+#define __LINUX_SEQLOCK_TYPES_H
+
+#include <linux/lockdep_types.h>
+#include <linux/mutex_types.h>
+#include <linux/spinlock_types.h>
+
+/*
+ * Sequence counters (seqcount_t)
+ *
+ * This is the raw counting mechanism, without any writer protection.
+ *
+ * Write side critical sections must be serialized and non-preemptible.
+ *
+ * If readers can be invoked from hardirq or softirq contexts,
+ * interrupts or bottom halves must also be respectively disabled before
+ * entering the write section.
+ *
+ * This mechanism can't be used if the protected data contains pointers,
+ * as the writer can invalidate a pointer that a reader is following.
+ *
+ * If the write serialization mechanism is one of the common kernel
+ * locking primitives, use a sequence counter with associated lock
+ * (seqcount_LOCKNAME_t) instead.
+ *
+ * If it's desired to automatically handle the sequence counter writer
+ * serialization and non-preemptibility requirements, use a sequential
+ * lock (seqlock_t) instead.
+ *
+ * See Documentation/locking/seqlock.rst
+ */
+typedef struct seqcount {
+	unsigned sequence;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map dep_map;
+#endif
+} seqcount_t;
+
+/*
+ * For PREEMPT_RT, seqcount_LOCKNAME_t write side critical sections cannot
+ * disable preemption. It can lead to higher latencies, and the write side
+ * sections will not be able to acquire locks which become sleeping locks
+ * (e.g. spinlock_t).
+ *
+ * To remain preemptible while avoiding a possible livelock caused by the
+ * reader preempting the writer, use a different technique: let the reader
+ * detect if a seqcount_LOCKNAME_t writer is in progress. If that is the
+ * case, acquire then release the associated LOCKNAME writer serialization
+ * lock. This will allow any possibly-preempted writer to make progress
+ * until the end of its writer serialization lock critical section.
+ *
+ * This lock-unlock technique must be implemented for all of PREEMPT_RT
+ * sleeping locks.  See Documentation/locking/locktypes.rst
+ */
+#if defined(CONFIG_LOCKDEP) || defined(CONFIG_PREEMPT_RT)
+#define __SEQ_LOCK(expr)	expr
+#else
+#define __SEQ_LOCK(expr)
+#endif
+
+#define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockbase)	\
+typedef struct seqcount_##lockname {					\
+	seqcount_t		seqcount;				\
+	__SEQ_LOCK(locktype	*lock);					\
+} seqcount_##lockname##_t;
+
+SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t,  false,    raw_spin)
+SEQCOUNT_LOCKNAME(spinlock,     spinlock_t,      __SEQ_RT, spin)
+SEQCOUNT_LOCKNAME(rwlock,       rwlock_t,        __SEQ_RT, read)
+SEQCOUNT_LOCKNAME(mutex,        struct mutex,    true,     mutex)
+#undef SEQCOUNT_LOCKNAME
+
+/*
+ * Sequential locks (seqlock_t)
+ *
+ * Sequence counters with an embedded spinlock for writer serialization
+ * and non-preemptibility.
+ *
+ * For more info, see:
+ *    - Comments on top of seqcount_t
+ *    - Documentation/locking/seqlock.rst
+ */
+typedef struct {
+	/*
+	 * Make sure that readers don't starve writers on PREEMPT_RT: use
+	 * seqcount_spinlock_t instead of seqcount_t. Check __SEQ_LOCK().
+	 */
+	seqcount_spinlock_t seqcount;
+	spinlock_t lock;
+} seqlock_t;
+
+#endif /* __LINUX_SEQLOCK_TYPES_H */
diff --git a/include/linux/shm.h b/include/linux/shm.h
index d8e69aed3d32..c55bef0538e5 100644
--- a/include/linux/shm.h
+++ b/include/linux/shm.h
@@ -2,12 +2,12 @@
 #ifndef _LINUX_SHM_H_
 #define _LINUX_SHM_H_
 
-#include <linux/list.h>
+#include <linux/types.h>
 #include <asm/page.h>
-#include <uapi/linux/shm.h>
 #include <asm/shmparam.h>
 
 struct file;
+struct task_struct;
 
 #ifdef CONFIG_SYSVIPC
 struct sysv_shm {
diff --git a/include/linux/signal.h b/include/linux/signal.h
index 3b98e7a28538..f19816832f05 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -3,6 +3,7 @@
 #define _LINUX_SIGNAL_H
 
 #include <linux/bug.h>
+#include <linux/list.h>
 #include <linux/signal_types.h>
 #include <linux/string.h>
 
diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h
index a70b2bdbf4d9..caf4f7a59ab9 100644
--- a/include/linux/signal_types.h
+++ b/include/linux/signal_types.h
@@ -6,7 +6,7 @@
  * Basic signal handling related data type definitions:
  */
 
-#include <linux/list.h>
+#include <linux/types.h>
 #include <uapi/linux/signal.h>
 
 typedef struct kernel_siginfo {
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 27998f73183e..a5ae952454c8 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -566,6 +566,15 @@ struct ubuf_info_msgzc {
 int mm_account_pinned_pages(struct mmpin *mmp, size_t size);
 void mm_unaccount_pinned_pages(struct mmpin *mmp);
 
+/* Preserve some data across TX submission and completion.
+ *
+ * Note, this state is stored in the driver. Extending the layout
+ * might need some special care.
+ */
+struct xsk_tx_metadata_compl {
+	__u64 *tx_timestamp;
+};
+
 /* This data is invariant across clones and lives at
  * the end of the header data, ie. at skb->end.
  */
@@ -578,7 +587,10 @@ struct skb_shared_info {
 	/* Warning: this field is not always filled in (UFO)! */
 	unsigned short	gso_segs;
 	struct sk_buff	*frag_list;
-	struct skb_shared_hwtstamps hwtstamps;
+	union {
+		struct skb_shared_hwtstamps hwtstamps;
+		struct xsk_tx_metadata_compl xsk_meta;
+	};
 	unsigned int	gso_type;
 	u32		tskey;
 
@@ -742,7 +754,6 @@ typedef unsigned char *sk_buff_data_t;
  *	@dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL
  *	@cb: Control buffer. Free for use by every layer. Put private vars here
  *	@_skb_refdst: destination entry (with norefcount bit)
- *	@sp: the security path, used for xfrm
  *	@len: Length of actual data
  *	@data_len: Data length
  *	@mac_len: Length of link layer header
@@ -776,7 +787,6 @@ typedef unsigned char *sk_buff_data_t;
  *	@tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue)
  *	@_sk_redir: socket redirection information for skmsg
  *	@_nfct: Associated connection, if any (with nfctinfo bits)
- *	@nf_bridge: Saved data about a bridged frame - see br_netfilter.c
  *	@skb_iif: ifindex of device we arrived on
  *	@tc_index: Traffic control index
  *	@hash: the packet hash
@@ -1057,7 +1067,7 @@ struct sk_buff {
 	refcount_t		users;
 
 #ifdef CONFIG_SKB_EXTENSIONS
-	/* only useable after checking ->active_extensions != 0 */
+	/* only usable after checking ->active_extensions != 0 */
 	struct skb_ext		*extensions;
 #endif
 };
@@ -3299,7 +3309,7 @@ static inline struct page *__dev_alloc_pages(gfp_t gfp_mask,
 					     unsigned int order)
 {
 	/* This piece of code contains several assumptions.
-	 * 1.  This is for device Rx, therefor a cold page is preferred.
+	 * 1.  This is for device Rx, therefore a cold page is preferred.
 	 * 2.  The expectation is the user wants a compound page.
 	 * 3.  If requesting a order 0 page it will not be compound
 	 *     due to the check to see if order has a value in prep_new_page
@@ -3997,6 +4007,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features
 				 unsigned int offset);
 struct sk_buff *skb_vlan_untag(struct sk_buff *skb);
 int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len);
+int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev);
 int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci);
 int skb_vlan_pop(struct sk_buff *skb);
 int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci);
@@ -4235,10 +4246,13 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a,
 {
 	const void *a = skb_metadata_end(skb_a);
 	const void *b = skb_metadata_end(skb_b);
-	/* Using more efficient varaiant than plain call to memcmp(). */
-#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
 	u64 diffs = 0;
 
+	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
+	    BITS_PER_LONG != 64)
+		goto slow;
+
+	/* Using more efficient variant than plain call to memcmp(). */
 	switch (meta_len) {
 #define __it(x, op) (x -= sizeof(u##op))
 #define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op))
@@ -4258,11 +4272,11 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a,
 		fallthrough;
 	case  4: diffs |= __it_diff(a, b, 32);
 		break;
+	default:
+slow:
+		return memcmp(a - meta_len, b - meta_len, meta_len);
 	}
 	return diffs;
-#else
-	return memcmp(a - meta_len, b - meta_len, meta_len);
-#endif
 }
 
 static inline bool skb_metadata_differs(const struct sk_buff *skb_a,
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index c1637515a8a4..888a4b217829 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -100,12 +100,18 @@ struct sk_psock {
 	void (*saved_close)(struct sock *sk, long timeout);
 	void (*saved_write_space)(struct sock *sk);
 	void (*saved_data_ready)(struct sock *sk);
+	/* psock_update_sk_prot may be called with restore=false many times
+	 * so the handler must be safe for this case. It will be called
+	 * exactly once with restore=true when the psock is being destroyed
+	 * and psock refcnt is zero, but before an RCU grace period.
+	 */
 	int  (*psock_update_sk_prot)(struct sock *sk, struct sk_psock *psock,
 				     bool restore);
 	struct proto			*sk_proto;
 	struct mutex			work_mutex;
 	struct sk_psock_work_state	work_state;
 	struct delayed_work		work;
+	struct sock			*sk_pair;
 	struct rcu_work			rwork;
 };
 
diff --git a/include/linux/slab.h b/include/linux/slab.h
index d6d6ffeeb9a2..b5f5ee8308d0 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -24,7 +24,7 @@
 
 /*
  * Flags to pass to kmem_cache_create().
- * The ones marked DEBUG are only valid if CONFIG_DEBUG_SLAB is set.
+ * The ones marked DEBUG need CONFIG_SLUB_DEBUG enabled, otherwise are no-op
  */
 /* DEBUG: Perform (expensive) checks on alloc/free */
 #define SLAB_CONSISTENCY_CHECKS	((slab_flags_t __force)0x00000100U)
@@ -302,25 +302,15 @@ static inline unsigned int arch_slab_minalign(void)
  * Kmalloc array related definitions
  */
 
-#ifdef CONFIG_SLAB
 /*
- * SLAB and SLUB directly allocates requests fitting in to an order-1 page
+ * SLUB directly allocates requests fitting in to an order-1 page
  * (PAGE_SIZE*2).  Larger requests are passed to the page allocator.
  */
 #define KMALLOC_SHIFT_HIGH	(PAGE_SHIFT + 1)
-#define KMALLOC_SHIFT_MAX	(MAX_ORDER + PAGE_SHIFT)
-#ifndef KMALLOC_SHIFT_LOW
-#define KMALLOC_SHIFT_LOW	5
-#endif
-#endif
-
-#ifdef CONFIG_SLUB
-#define KMALLOC_SHIFT_HIGH	(PAGE_SHIFT + 1)
-#define KMALLOC_SHIFT_MAX	(MAX_ORDER + PAGE_SHIFT)
+#define KMALLOC_SHIFT_MAX	(MAX_PAGE_ORDER + PAGE_SHIFT)
 #ifndef KMALLOC_SHIFT_LOW
 #define KMALLOC_SHIFT_LOW	3
 #endif
-#endif
 
 /* Maximum allocatable size */
 #define KMALLOC_MAX_SIZE	(1UL << KMALLOC_SHIFT_MAX)
@@ -788,12 +778,4 @@ size_t kmalloc_size_roundup(size_t size);
 
 void __init kmem_cache_init_late(void);
 
-#if defined(CONFIG_SMP) && defined(CONFIG_SLAB)
-int slab_prepare_cpu(unsigned int cpu);
-int slab_dead_cpu(unsigned int cpu);
-#else
-#define slab_prepare_cpu	NULL
-#define slab_dead_cpu		NULL
-#endif
-
 #endif	/* _LINUX_SLAB_H */
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
deleted file mode 100644
index a61e7d55d0d3..000000000000
--- a/include/linux/slab_def.h
+++ /dev/null
@@ -1,124 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_SLAB_DEF_H
-#define	_LINUX_SLAB_DEF_H
-
-#include <linux/kfence.h>
-#include <linux/reciprocal_div.h>
-
-/*
- * Definitions unique to the original Linux SLAB allocator.
- */
-
-struct kmem_cache {
-	struct array_cache __percpu *cpu_cache;
-
-/* 1) Cache tunables. Protected by slab_mutex */
-	unsigned int batchcount;
-	unsigned int limit;
-	unsigned int shared;
-
-	unsigned int size;
-	struct reciprocal_value reciprocal_buffer_size;
-/* 2) touched by every alloc & free from the backend */
-
-	slab_flags_t flags;		/* constant flags */
-	unsigned int num;		/* # of objs per slab */
-
-/* 3) cache_grow/shrink */
-	/* order of pgs per slab (2^n) */
-	unsigned int gfporder;
-
-	/* force GFP flags, e.g. GFP_DMA */
-	gfp_t allocflags;
-
-	size_t colour;			/* cache colouring range */
-	unsigned int colour_off;	/* colour offset */
-	unsigned int freelist_size;
-
-	/* constructor func */
-	void (*ctor)(void *obj);
-
-/* 4) cache creation/removal */
-	const char *name;
-	struct list_head list;
-	int refcount;
-	int object_size;
-	int align;
-
-/* 5) statistics */
-#ifdef CONFIG_DEBUG_SLAB
-	unsigned long num_active;
-	unsigned long num_allocations;
-	unsigned long high_mark;
-	unsigned long grown;
-	unsigned long reaped;
-	unsigned long errors;
-	unsigned long max_freeable;
-	unsigned long node_allocs;
-	unsigned long node_frees;
-	unsigned long node_overflow;
-	atomic_t allochit;
-	atomic_t allocmiss;
-	atomic_t freehit;
-	atomic_t freemiss;
-
-	/*
-	 * If debugging is enabled, then the allocator can add additional
-	 * fields and/or padding to every object. 'size' contains the total
-	 * object size including these internal fields, while 'obj_offset'
-	 * and 'object_size' contain the offset to the user object and its
-	 * size.
-	 */
-	int obj_offset;
-#endif /* CONFIG_DEBUG_SLAB */
-
-#ifdef CONFIG_KASAN_GENERIC
-	struct kasan_cache kasan_info;
-#endif
-
-#ifdef CONFIG_SLAB_FREELIST_RANDOM
-	unsigned int *random_seq;
-#endif
-
-#ifdef CONFIG_HARDENED_USERCOPY
-	unsigned int useroffset;	/* Usercopy region offset */
-	unsigned int usersize;		/* Usercopy region size */
-#endif
-
-	struct kmem_cache_node *node[MAX_NUMNODES];
-};
-
-static inline void *nearest_obj(struct kmem_cache *cache, const struct slab *slab,
-				void *x)
-{
-	void *object = x - (x - slab->s_mem) % cache->size;
-	void *last_object = slab->s_mem + (cache->num - 1) * cache->size;
-
-	if (unlikely(object > last_object))
-		return last_object;
-	else
-		return object;
-}
-
-/*
- * We want to avoid an expensive divide : (offset / cache->size)
- *   Using the fact that size is a constant for a particular cache,
- *   we can replace (offset / cache->size) by
- *   reciprocal_divide(offset, cache->reciprocal_buffer_size)
- */
-static inline unsigned int obj_to_index(const struct kmem_cache *cache,
-					const struct slab *slab, void *obj)
-{
-	u32 offset = (obj - slab->s_mem);
-	return reciprocal_divide(offset, cache->reciprocal_buffer_size);
-}
-
-static inline int objs_per_slab(const struct kmem_cache *cache,
-				     const struct slab *slab)
-{
-	if (is_kfence_address(slab_address(slab)))
-		return 1;
-	return cache->num;
-}
-
-#endif	/* _LINUX_SLAB_DEF_H */
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
deleted file mode 100644
index deb90cf4bffb..000000000000
--- a/include/linux/slub_def.h
+++ /dev/null
@@ -1,204 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_SLUB_DEF_H
-#define _LINUX_SLUB_DEF_H
-
-/*
- * SLUB : A Slab allocator without object queues.
- *
- * (C) 2007 SGI, Christoph Lameter
- */
-#include <linux/kfence.h>
-#include <linux/kobject.h>
-#include <linux/reciprocal_div.h>
-#include <linux/local_lock.h>
-
-enum stat_item {
-	ALLOC_FASTPATH,		/* Allocation from cpu slab */
-	ALLOC_SLOWPATH,		/* Allocation by getting a new cpu slab */
-	FREE_FASTPATH,		/* Free to cpu slab */
-	FREE_SLOWPATH,		/* Freeing not to cpu slab */
-	FREE_FROZEN,		/* Freeing to frozen slab */
-	FREE_ADD_PARTIAL,	/* Freeing moves slab to partial list */
-	FREE_REMOVE_PARTIAL,	/* Freeing removes last object */
-	ALLOC_FROM_PARTIAL,	/* Cpu slab acquired from node partial list */
-	ALLOC_SLAB,		/* Cpu slab acquired from page allocator */
-	ALLOC_REFILL,		/* Refill cpu slab from slab freelist */
-	ALLOC_NODE_MISMATCH,	/* Switching cpu slab */
-	FREE_SLAB,		/* Slab freed to the page allocator */
-	CPUSLAB_FLUSH,		/* Abandoning of the cpu slab */
-	DEACTIVATE_FULL,	/* Cpu slab was full when deactivated */
-	DEACTIVATE_EMPTY,	/* Cpu slab was empty when deactivated */
-	DEACTIVATE_TO_HEAD,	/* Cpu slab was moved to the head of partials */
-	DEACTIVATE_TO_TAIL,	/* Cpu slab was moved to the tail of partials */
-	DEACTIVATE_REMOTE_FREES,/* Slab contained remotely freed objects */
-	DEACTIVATE_BYPASS,	/* Implicit deactivation */
-	ORDER_FALLBACK,		/* Number of times fallback was necessary */
-	CMPXCHG_DOUBLE_CPU_FAIL,/* Failure of this_cpu_cmpxchg_double */
-	CMPXCHG_DOUBLE_FAIL,	/* Number of times that cmpxchg double did not match */
-	CPU_PARTIAL_ALLOC,	/* Used cpu partial on alloc */
-	CPU_PARTIAL_FREE,	/* Refill cpu partial on free */
-	CPU_PARTIAL_NODE,	/* Refill cpu partial from node partial */
-	CPU_PARTIAL_DRAIN,	/* Drain cpu partial to node partial */
-	NR_SLUB_STAT_ITEMS
-};
-
-#ifndef CONFIG_SLUB_TINY
-/*
- * When changing the layout, make sure freelist and tid are still compatible
- * with this_cpu_cmpxchg_double() alignment requirements.
- */
-struct kmem_cache_cpu {
-	union {
-		struct {
-			void **freelist;	/* Pointer to next available object */
-			unsigned long tid;	/* Globally unique transaction id */
-		};
-		freelist_aba_t freelist_tid;
-	};
-	struct slab *slab;	/* The slab from which we are allocating */
-#ifdef CONFIG_SLUB_CPU_PARTIAL
-	struct slab *partial;	/* Partially allocated frozen slabs */
-#endif
-	local_lock_t lock;	/* Protects the fields above */
-#ifdef CONFIG_SLUB_STATS
-	unsigned stat[NR_SLUB_STAT_ITEMS];
-#endif
-};
-#endif /* CONFIG_SLUB_TINY */
-
-#ifdef CONFIG_SLUB_CPU_PARTIAL
-#define slub_percpu_partial(c)		((c)->partial)
-
-#define slub_set_percpu_partial(c, p)		\
-({						\
-	slub_percpu_partial(c) = (p)->next;	\
-})
-
-#define slub_percpu_partial_read_once(c)     READ_ONCE(slub_percpu_partial(c))
-#else
-#define slub_percpu_partial(c)			NULL
-
-#define slub_set_percpu_partial(c, p)
-
-#define slub_percpu_partial_read_once(c)	NULL
-#endif // CONFIG_SLUB_CPU_PARTIAL
-
-/*
- * Word size structure that can be atomically updated or read and that
- * contains both the order and the number of objects that a slab of the
- * given order would contain.
- */
-struct kmem_cache_order_objects {
-	unsigned int x;
-};
-
-/*
- * Slab cache management.
- */
-struct kmem_cache {
-#ifndef CONFIG_SLUB_TINY
-	struct kmem_cache_cpu __percpu *cpu_slab;
-#endif
-	/* Used for retrieving partial slabs, etc. */
-	slab_flags_t flags;
-	unsigned long min_partial;
-	unsigned int size;	/* The size of an object including metadata */
-	unsigned int object_size;/* The size of an object without metadata */
-	struct reciprocal_value reciprocal_size;
-	unsigned int offset;	/* Free pointer offset */
-#ifdef CONFIG_SLUB_CPU_PARTIAL
-	/* Number of per cpu partial objects to keep around */
-	unsigned int cpu_partial;
-	/* Number of per cpu partial slabs to keep around */
-	unsigned int cpu_partial_slabs;
-#endif
-	struct kmem_cache_order_objects oo;
-
-	/* Allocation and freeing of slabs */
-	struct kmem_cache_order_objects min;
-	gfp_t allocflags;	/* gfp flags to use on each alloc */
-	int refcount;		/* Refcount for slab cache destroy */
-	void (*ctor)(void *);
-	unsigned int inuse;		/* Offset to metadata */
-	unsigned int align;		/* Alignment */
-	unsigned int red_left_pad;	/* Left redzone padding size */
-	const char *name;	/* Name (only for display!) */
-	struct list_head list;	/* List of slab caches */
-#ifdef CONFIG_SYSFS
-	struct kobject kobj;	/* For sysfs */
-#endif
-#ifdef CONFIG_SLAB_FREELIST_HARDENED
-	unsigned long random;
-#endif
-
-#ifdef CONFIG_NUMA
-	/*
-	 * Defragmentation by allocating from a remote node.
-	 */
-	unsigned int remote_node_defrag_ratio;
-#endif
-
-#ifdef CONFIG_SLAB_FREELIST_RANDOM
-	unsigned int *random_seq;
-#endif
-
-#ifdef CONFIG_KASAN_GENERIC
-	struct kasan_cache kasan_info;
-#endif
-
-#ifdef CONFIG_HARDENED_USERCOPY
-	unsigned int useroffset;	/* Usercopy region offset */
-	unsigned int usersize;		/* Usercopy region size */
-#endif
-
-	struct kmem_cache_node *node[MAX_NUMNODES];
-};
-
-#if defined(CONFIG_SYSFS) && !defined(CONFIG_SLUB_TINY)
-#define SLAB_SUPPORTS_SYSFS
-void sysfs_slab_unlink(struct kmem_cache *);
-void sysfs_slab_release(struct kmem_cache *);
-#else
-static inline void sysfs_slab_unlink(struct kmem_cache *s)
-{
-}
-static inline void sysfs_slab_release(struct kmem_cache *s)
-{
-}
-#endif
-
-void *fixup_red_left(struct kmem_cache *s, void *p);
-
-static inline void *nearest_obj(struct kmem_cache *cache, const struct slab *slab,
-				void *x) {
-	void *object = x - (x - slab_address(slab)) % cache->size;
-	void *last_object = slab_address(slab) +
-		(slab->objects - 1) * cache->size;
-	void *result = (unlikely(object > last_object)) ? last_object : object;
-
-	result = fixup_red_left(cache, result);
-	return result;
-}
-
-/* Determine object index from a given position */
-static inline unsigned int __obj_to_index(const struct kmem_cache *cache,
-					  void *addr, void *obj)
-{
-	return reciprocal_divide(kasan_reset_tag(obj) - addr,
-				 cache->reciprocal_size);
-}
-
-static inline unsigned int obj_to_index(const struct kmem_cache *cache,
-					const struct slab *slab, void *obj)
-{
-	if (is_kfence_address(obj))
-		return 0;
-	return __obj_to_index(cache, slab_address(slab), obj);
-}
-
-static inline int objs_per_slab(const struct kmem_cache *cache,
-				     const struct slab *slab)
-{
-	return slab->objects;
-}
-#endif /* _LINUX_SLUB_DEF_H */
diff --git a/include/linux/soc/apple/rtkit.h b/include/linux/soc/apple/rtkit.h
index fc456f75c131..8c9ca857ccf6 100644
--- a/include/linux/soc/apple/rtkit.h
+++ b/include/linux/soc/apple/rtkit.h
@@ -161,24 +161,6 @@ int apple_rtkit_send_message(struct apple_rtkit *rtk, u8 ep, u64 message,
 			     struct completion *completion, bool atomic);
 
 /*
- * Send a message to the given endpoint and wait until it has been submitted
- * to the hardware FIFO.
- * Will return zero on success and a negative error code on failure
- * (e.g. -ETIME when the message couldn't be written within the given
- * timeout)
- *
- * @rtk:            RTKit reference
- * @ep:             target endpoint
- * @message:        message to be sent
- * @timeout:        timeout in milliseconds to allow the message transmission
- *                  to be completed
- * @atomic:         if set to true this function can be called from atomic
- *                  context.
- */
-int apple_rtkit_send_message_wait(struct apple_rtkit *rtk, u8 ep, u64 message,
-				  unsigned long timeout, bool atomic);
-
-/*
  * Process incoming messages in atomic context.
  * This only guarantees that messages arrive as far as the recv_message_early
  * callback; drivers expecting to handle incoming messages synchronously
diff --git a/include/linux/soc/mediatek/mtk-mmsys.h b/include/linux/soc/mediatek/mtk-mmsys.h
index 2475ef914746..4885b065b849 100644
--- a/include/linux/soc/mediatek/mtk-mmsys.h
+++ b/include/linux/soc/mediatek/mtk-mmsys.h
@@ -62,6 +62,14 @@ enum mtk_ddp_comp_id {
 	DDP_COMPONENT_OVL_2L1,
 	DDP_COMPONENT_OVL_2L2,
 	DDP_COMPONENT_OVL1,
+	DDP_COMPONENT_PADDING0,
+	DDP_COMPONENT_PADDING1,
+	DDP_COMPONENT_PADDING2,
+	DDP_COMPONENT_PADDING3,
+	DDP_COMPONENT_PADDING4,
+	DDP_COMPONENT_PADDING5,
+	DDP_COMPONENT_PADDING6,
+	DDP_COMPONENT_PADDING7,
 	DDP_COMPONENT_POSTMASK0,
 	DDP_COMPONENT_PWM0,
 	DDP_COMPONENT_PWM1,
diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h
index 6b0a7dc48a4b..f866d5c8ed32 100644
--- a/include/linux/spi/spi-mem.h
+++ b/include/linux/spi/spi-mem.h
@@ -233,6 +233,8 @@ static inline void *spi_mem_get_drvdata(struct spi_mem *mem)
  *		    limitations)
  * @supports_op: check if an operation is supported by the controller
  * @exec_op: execute a SPI memory operation
+ *           not all driver provides supports_op(), so it can return -EOPNOTSUPP
+ *           if the op is not supported by the driver/controller
  * @get_name: get a custom name for the SPI mem device from the controller.
  *	      This might be needed if the controller driver has been ported
  *	      to use the SPI mem layer and a custom name is used to keep
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 255a0562aea5..471fe2ff9066 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -20,6 +20,9 @@
 
 #include <uapi/linux/spi/spi.h>
 
+/* Max no. of CS supported per spi device */
+#define SPI_CS_CNT_MAX 4
+
 struct dma_chan;
 struct software_node;
 struct ptp_system_timestamp;
@@ -132,7 +135,8 @@ extern void spi_transfer_cs_change_delay_exec(struct spi_message *msg,
  * @max_speed_hz: Maximum clock rate to be used with this chip
  *	(on this board); may be changed by the device's driver.
  *	The spi_transfer.speed_hz can override this for each transfer.
- * @chip_select: Chipselect, distinguishing chips handled by @controller.
+ * @chip_select: Array of physical chipselect, spi->chipselect[i] gives
+ *	the corresponding physical CS for logical CS i.
  * @mode: The spi mode defines how data is clocked out and in.
  *	This may be changed by the device's driver.
  *	The "active low" default for chipselect mode can be overridden
@@ -157,8 +161,8 @@ extern void spi_transfer_cs_change_delay_exec(struct spi_message *msg,
  *	the device will bind to the named driver and only the named driver.
  *	Do not set directly, because core frees it; use driver_set_override() to
  *	set or clear it.
- * @cs_gpiod: GPIO descriptor of the chipselect line (optional, NULL when
- *	not using a GPIO line)
+ * @cs_gpiod: Array of GPIO descriptors of the corresponding chipselect lines
+ *	(optional, NULL when not using a GPIO line)
  * @word_delay: delay to be inserted between consecutive
  *	words of a transfer
  * @cs_setup: delay to be introduced by the controller after CS is asserted
@@ -167,6 +171,7 @@ extern void spi_transfer_cs_change_delay_exec(struct spi_message *msg,
  *	deasserted. If @cs_change_delay is used from @spi_transfer, then the
  *	two delays will be added up.
  * @pcpu_statistics: statistics for the spi_device
+ * @cs_index_mask: Bit mask of the active chipselect(s) in the chipselect array
  *
  * A @spi_device is used to interchange data between an SPI slave
  * (usually a discrete chip) and CPU memory.
@@ -182,7 +187,7 @@ struct spi_device {
 	struct spi_controller	*controller;
 	struct spi_controller	*master;	/* Compatibility layer */
 	u32			max_speed_hz;
-	u8			chip_select;
+	u8			chip_select[SPI_CS_CNT_MAX];
 	u8			bits_per_word;
 	bool			rt;
 #define SPI_NO_TX		BIT(31)		/* No transmit wire */
@@ -213,7 +218,7 @@ struct spi_device {
 	void			*controller_data;
 	char			modalias[SPI_NAME_SIZE];
 	const char		*driver_override;
-	struct gpio_desc	*cs_gpiod;	/* Chip select GPIO descriptor */
+	struct gpio_desc	*cs_gpiod[SPI_CS_CNT_MAX];	/* Chip select gpio desc */
 	struct spi_delay	word_delay; /* Inter-word delay */
 	/* CS delays */
 	struct spi_delay	cs_setup;
@@ -223,6 +228,13 @@ struct spi_device {
 	/* The statistics */
 	struct spi_statistics __percpu	*pcpu_statistics;
 
+	/* Bit mask of the chipselect(s) that the driver need to use from
+	 * the chipselect array.When the controller is capable to handle
+	 * multiple chip selects & memories are connected in parallel
+	 * then more than one bit need to be set in cs_index_mask.
+	 */
+	u32			cs_index_mask : SPI_CS_CNT_MAX;
+
 	/*
 	 * Likely need more hooks for more protocol options affecting how
 	 * the controller talks to each chip, like:
@@ -279,22 +291,33 @@ static inline void *spi_get_drvdata(const struct spi_device *spi)
 
 static inline u8 spi_get_chipselect(const struct spi_device *spi, u8 idx)
 {
-	return spi->chip_select;
+	return spi->chip_select[idx];
 }
 
 static inline void spi_set_chipselect(struct spi_device *spi, u8 idx, u8 chipselect)
 {
-	spi->chip_select = chipselect;
+	spi->chip_select[idx] = chipselect;
 }
 
 static inline struct gpio_desc *spi_get_csgpiod(const struct spi_device *spi, u8 idx)
 {
-	return spi->cs_gpiod;
+	return spi->cs_gpiod[idx];
 }
 
 static inline void spi_set_csgpiod(struct spi_device *spi, u8 idx, struct gpio_desc *csgpiod)
 {
-	spi->cs_gpiod = csgpiod;
+	spi->cs_gpiod[idx] = csgpiod;
+}
+
+static inline bool spi_is_csgpiod(struct spi_device *spi)
+{
+	u8 idx;
+
+	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) {
+		if (spi_get_csgpiod(spi, idx))
+			return true;
+	}
+	return false;
 }
 
 /**
@@ -399,6 +422,8 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch
  * @bus_lock_spinlock: spinlock for SPI bus locking
  * @bus_lock_mutex: mutex for exclusion of multiple callers
  * @bus_lock_flag: indicates that the SPI bus is locked for exclusive use
+ * @multi_cs_cap: indicates that the SPI Controller can assert/de-assert
+ *	more than one chip select at once.
  * @setup: updates the device mode and clocking records used by a
  *	device's SPI controller; protocol code may call this.  This
  *	must fail if an unrecognized or unsupported mode is requested.
@@ -461,10 +486,13 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch
  *                  - return 1 if the transfer is still in progress. When
  *                    the driver is finished with this transfer it must
  *                    call spi_finalize_current_transfer() so the subsystem
- *                    can issue the next transfer. Note: transfer_one and
- *                    transfer_one_message are mutually exclusive; when both
- *                    are set, the generic subsystem does not call your
- *                    transfer_one callback.
+ *                    can issue the next transfer. If the transfer fails, the
+ *                    driver must set the flag SPI_TRANS_FAIL_IO to
+ *                    spi_transfer->error first, before calling
+ *                    spi_finalize_current_transfer().
+ *                    Note: transfer_one and transfer_one_message are mutually
+ *                    exclusive; when both are set, the generic subsystem does
+ *                    not call your transfer_one callback.
  * @handle_err: the subsystem calls the driver to handle an error that occurs
  *		in the generic implementation of transfer_one_message().
  * @mem_ops: optimized/dedicated operations for interactions with SPI memory.
@@ -567,6 +595,11 @@ struct spi_controller {
 #define SPI_CONTROLLER_MUST_TX		BIT(4)	/* Requires tx */
 #define SPI_CONTROLLER_GPIO_SS		BIT(5)	/* GPIO CS must select slave */
 #define SPI_CONTROLLER_SUSPENDED	BIT(6)	/* Currently suspended */
+	/*
+	 * The spi-controller has multi chip select capability and can
+	 * assert/de-assert more than one chip select at once.
+	 */
+#define SPI_CONTROLLER_MULTI_CS		BIT(7)
 
 	/* Flag indicating if the allocation of this struct is devres-managed */
 	bool			devm_allocated;
@@ -677,7 +710,8 @@ struct spi_controller {
 	bool				rt;
 	bool				auto_runtime_pm;
 	bool				cur_msg_mapped;
-	char				last_cs;
+	char				last_cs[SPI_CS_CNT_MAX];
+	char				last_cs_index_mask;
 	bool				last_cs_mode_high;
 	bool                            fallback;
 	struct completion               xfer_completion;
@@ -1040,6 +1074,7 @@ struct spi_transfer {
 	unsigned	len;
 
 #define SPI_TRANS_FAIL_NO_START	BIT(0)
+#define SPI_TRANS_FAIL_IO	BIT(1)
 	u16		error;
 
 	dma_addr_t	tx_dma;
@@ -1638,8 +1673,6 @@ spi_transfer_is_last(struct spi_controller *ctlr, struct spi_transfer *xfer)
 /* Compatibility layer */
 #define spi_master			spi_controller
 
-#define SPI_MASTER_HALF_DUPLEX		SPI_CONTROLLER_HALF_DUPLEX
-
 #define spi_master_get_devdata(_ctlr)	spi_controller_get_devdata(_ctlr)
 #define spi_master_set_devdata(_ctlr, _data)	\
 	spi_controller_set_devdata(_ctlr, _data)
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 31d3d747a9db..eaac8b0da25b 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -449,6 +449,37 @@ static __always_inline int spin_is_contended(spinlock_t *lock)
 	return raw_spin_is_contended(&lock->rlock);
 }
 
+/*
+ * Does a critical section need to be broken due to another
+ * task waiting?: (technically does not depend on CONFIG_PREEMPTION,
+ * but a general need for low latency)
+ */
+static inline int spin_needbreak(spinlock_t *lock)
+{
+#ifdef CONFIG_PREEMPTION
+	return spin_is_contended(lock);
+#else
+	return 0;
+#endif
+}
+
+/*
+ * Check if a rwlock is contended.
+ * Returns non-zero if there is another task waiting on the rwlock.
+ * Returns zero if the lock is not contended or the system / underlying
+ * rwlock implementation does not support contention detection.
+ * Technically does not depend on CONFIG_PREEMPTION, but a general need
+ * for low latency.
+ */
+static inline int rwlock_needbreak(rwlock_t *lock)
+{
+#ifdef CONFIG_PREEMPTION
+	return rwlock_is_contended(lock);
+#else
+	return 0;
+#endif
+}
+
 #define assert_spin_locked(lock)	assert_raw_spin_locked(&(lock)->rlock)
 
 #else  /* !CONFIG_PREEMPT_RT */
@@ -507,6 +538,8 @@ DEFINE_LOCK_GUARD_1(raw_spinlock, raw_spinlock_t,
 		    raw_spin_lock(_T->lock),
 		    raw_spin_unlock(_T->lock))
 
+DEFINE_LOCK_GUARD_1_COND(raw_spinlock, _try, raw_spin_trylock(_T->lock))
+
 DEFINE_LOCK_GUARD_1(raw_spinlock_nested, raw_spinlock_t,
 		    raw_spin_lock_nested(_T->lock, SINGLE_DEPTH_NESTING),
 		    raw_spin_unlock(_T->lock))
@@ -515,23 +548,62 @@ DEFINE_LOCK_GUARD_1(raw_spinlock_irq, raw_spinlock_t,
 		    raw_spin_lock_irq(_T->lock),
 		    raw_spin_unlock_irq(_T->lock))
 
+DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irq, _try, raw_spin_trylock_irq(_T->lock))
+
 DEFINE_LOCK_GUARD_1(raw_spinlock_irqsave, raw_spinlock_t,
 		    raw_spin_lock_irqsave(_T->lock, _T->flags),
 		    raw_spin_unlock_irqrestore(_T->lock, _T->flags),
 		    unsigned long flags)
 
+DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irqsave, _try,
+			 raw_spin_trylock_irqsave(_T->lock, _T->flags))
+
 DEFINE_LOCK_GUARD_1(spinlock, spinlock_t,
 		    spin_lock(_T->lock),
 		    spin_unlock(_T->lock))
 
+DEFINE_LOCK_GUARD_1_COND(spinlock, _try, spin_trylock(_T->lock))
+
 DEFINE_LOCK_GUARD_1(spinlock_irq, spinlock_t,
 		    spin_lock_irq(_T->lock),
 		    spin_unlock_irq(_T->lock))
 
+DEFINE_LOCK_GUARD_1_COND(spinlock_irq, _try,
+			 spin_trylock_irq(_T->lock))
+
 DEFINE_LOCK_GUARD_1(spinlock_irqsave, spinlock_t,
 		    spin_lock_irqsave(_T->lock, _T->flags),
 		    spin_unlock_irqrestore(_T->lock, _T->flags),
 		    unsigned long flags)
 
+DEFINE_LOCK_GUARD_1_COND(spinlock_irqsave, _try,
+			 spin_trylock_irqsave(_T->lock, _T->flags))
+
+DEFINE_LOCK_GUARD_1(read_lock, rwlock_t,
+		    read_lock(_T->lock),
+		    read_unlock(_T->lock))
+
+DEFINE_LOCK_GUARD_1(read_lock_irq, rwlock_t,
+		    read_lock_irq(_T->lock),
+		    read_unlock_irq(_T->lock))
+
+DEFINE_LOCK_GUARD_1(read_lock_irqsave, rwlock_t,
+		    read_lock_irqsave(_T->lock, _T->flags),
+		    read_unlock_irqrestore(_T->lock, _T->flags),
+		    unsigned long flags)
+
+DEFINE_LOCK_GUARD_1(write_lock, rwlock_t,
+		    write_lock(_T->lock),
+		    write_unlock(_T->lock))
+
+DEFINE_LOCK_GUARD_1(write_lock_irq, rwlock_t,
+		    write_lock_irq(_T->lock),
+		    write_unlock_irq(_T->lock))
+
+DEFINE_LOCK_GUARD_1(write_lock_irqsave, rwlock_t,
+		    write_lock_irqsave(_T->lock, _T->flags),
+		    write_unlock_irqrestore(_T->lock, _T->flags),
+		    unsigned long flags)
+
 #undef __LINUX_INSIDE_SPINLOCK_H
 #endif /* __LINUX_SPINLOCK_H */
diff --git a/include/linux/splice.h b/include/linux/splice.h
index 6c461573434d..9dec4861d09f 100644
--- a/include/linux/splice.h
+++ b/include/linux/splice.h
@@ -68,28 +68,37 @@ typedef int (splice_actor)(struct pipe_inode_info *, struct pipe_buffer *,
 typedef int (splice_direct_actor)(struct pipe_inode_info *,
 				  struct splice_desc *);
 
-extern ssize_t splice_from_pipe(struct pipe_inode_info *, struct file *,
-				loff_t *, size_t, unsigned int,
-				splice_actor *);
-extern ssize_t __splice_from_pipe(struct pipe_inode_info *,
-				  struct splice_desc *, splice_actor *);
-extern ssize_t splice_to_pipe(struct pipe_inode_info *,
-			      struct splice_pipe_desc *);
-extern ssize_t add_to_pipe(struct pipe_inode_info *,
-			      struct pipe_buffer *);
-long vfs_splice_read(struct file *in, loff_t *ppos,
-		     struct pipe_inode_info *pipe, size_t len,
-		     unsigned int flags);
-extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *,
-				      splice_direct_actor *);
-extern long do_splice(struct file *in, loff_t *off_in,
-		      struct file *out, loff_t *off_out,
-		      size_t len, unsigned int flags);
+ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out,
+			 loff_t *ppos, size_t len, unsigned int flags,
+			 splice_actor *actor);
+ssize_t __splice_from_pipe(struct pipe_inode_info *pipe,
+			   struct splice_desc *sd, splice_actor *actor);
+ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
+			      struct splice_pipe_desc *spd);
+ssize_t add_to_pipe(struct pipe_inode_info *pipe, struct pipe_buffer *buf);
+ssize_t vfs_splice_read(struct file *in, loff_t *ppos,
+			struct pipe_inode_info *pipe, size_t len,
+			unsigned int flags);
+ssize_t splice_direct_to_actor(struct file *file, struct splice_desc *sd,
+			       splice_direct_actor *actor);
+ssize_t do_splice(struct file *in, loff_t *off_in, struct file *out,
+		  loff_t *off_out, size_t len, unsigned int flags);
+ssize_t do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
+			 loff_t *opos, size_t len, unsigned int flags);
+ssize_t splice_file_range(struct file *in, loff_t *ppos, struct file *out,
+			  loff_t *opos, size_t len);
 
-extern long do_tee(struct file *in, struct file *out, size_t len,
-		   unsigned int flags);
-extern ssize_t splice_to_socket(struct pipe_inode_info *pipe, struct file *out,
-				loff_t *ppos, size_t len, unsigned int flags);
+static inline long splice_copy_file_range(struct file *in, loff_t pos_in,
+					  struct file *out, loff_t pos_out,
+					  size_t len)
+{
+	return splice_file_range(in, &pos_in, out, &pos_out, len);
+}
+
+ssize_t do_tee(struct file *in, struct file *out, size_t len,
+	       unsigned int flags);
+ssize_t splice_to_socket(struct pipe_inode_info *pipe, struct file *out,
+			 loff_t *ppos, size_t len, unsigned int flags);
 
 /*
  * for dynamic pipe sizing
diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h
index e58306783d8e..adcbb8f23600 100644
--- a/include/linux/stackdepot.h
+++ b/include/linux/stackdepot.h
@@ -11,8 +11,6 @@
  * SLUB_DEBUG needs 256 bytes per object for that). Since allocation and free
  * stack traces often repeat, using stack depot allows to save about 100x space.
  *
- * Stack traces are never removed from the stack depot.
- *
  * Author: Alexander Potapenko <glider@google.com>
  * Copyright (C) 2016 Google, Inc.
  *
@@ -32,6 +30,18 @@ typedef u32 depot_stack_handle_t;
  */
 #define STACK_DEPOT_EXTRA_BITS 5
 
+typedef u32 depot_flags_t;
+
+/*
+ * Flags that can be passed to stack_depot_save_flags(); see the comment next
+ * to its declaration for more details.
+ */
+#define STACK_DEPOT_FLAG_CAN_ALLOC	((depot_flags_t)0x0001)
+#define STACK_DEPOT_FLAG_GET		((depot_flags_t)0x0002)
+
+#define STACK_DEPOT_FLAGS_NUM	2
+#define STACK_DEPOT_FLAGS_MASK	((depot_flags_t)((1 << STACK_DEPOT_FLAGS_NUM) - 1))
+
 /*
  * Using stack depot requires its initialization, which can be done in 3 ways:
  *
@@ -69,31 +79,39 @@ static inline int stack_depot_early_init(void)	{ return 0; }
 #endif
 
 /**
- * __stack_depot_save - Save a stack trace to stack depot
+ * stack_depot_save_flags - Save a stack trace to stack depot
  *
  * @entries:		Pointer to the stack trace
  * @nr_entries:		Number of frames in the stack
  * @alloc_flags:	Allocation GFP flags
- * @can_alloc:		Allocate stack pools (increased chance of failure if false)
+ * @depot_flags:	Stack depot flags
+ *
+ * Saves a stack trace from @entries array of size @nr_entries.
+ *
+ * If STACK_DEPOT_FLAG_CAN_ALLOC is set in @depot_flags, stack depot can
+ * replenish the stack pools in case no space is left (allocates using GFP
+ * flags of @alloc_flags). Otherwise, stack depot avoids any allocations and
+ * fails if no space is left to store the stack trace.
  *
- * Saves a stack trace from @entries array of size @nr_entries. If @can_alloc is
- * %true, stack depot can replenish the stack pools in case no space is left
- * (allocates using GFP flags of @alloc_flags). If @can_alloc is %false, avoids
- * any allocations and fails if no space is left to store the stack trace.
+ * If STACK_DEPOT_FLAG_GET is set in @depot_flags, stack depot will increment
+ * the refcount on the saved stack trace if it already exists in stack depot.
+ * Users of this flag must also call stack_depot_put() when keeping the stack
+ * trace is no longer required to avoid overflowing the refcount.
  *
  * If the provided stack trace comes from the interrupt context, only the part
  * up to the interrupt entry is saved.
  *
- * Context: Any context, but setting @can_alloc to %false is required if
+ * Context: Any context, but setting STACK_DEPOT_FLAG_CAN_ALLOC is required if
  *          alloc_pages() cannot be used from the current context. Currently
  *          this is the case for contexts where neither %GFP_ATOMIC nor
  *          %GFP_NOWAIT can be used (NMI, raw_spin_lock).
  *
  * Return: Handle of the stack struct stored in depot, 0 on failure
  */
-depot_stack_handle_t __stack_depot_save(unsigned long *entries,
-					unsigned int nr_entries,
-					gfp_t gfp_flags, bool can_alloc);
+depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
+					    unsigned int nr_entries,
+					    gfp_t gfp_flags,
+					    depot_flags_t depot_flags);
 
 /**
  * stack_depot_save - Save a stack trace to stack depot
@@ -102,8 +120,11 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries,
  * @nr_entries:		Number of frames in the stack
  * @alloc_flags:	Allocation GFP flags
  *
- * Context: Contexts where allocations via alloc_pages() are allowed.
- *          See __stack_depot_save() for more details.
+ * Does not increment the refcount on the saved stack trace; see
+ * stack_depot_save_flags() for more details.
+ *
+ * Context: Contexts where allocations via alloc_pages() are allowed;
+ *          see stack_depot_save_flags() for more details.
  *
  * Return: Handle of the stack trace stored in depot, 0 on failure
  */
@@ -142,6 +163,18 @@ int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size,
 		       int spaces);
 
 /**
+ * stack_depot_put - Drop a reference to a stack trace from stack depot
+ *
+ * @handle:	Stack depot handle returned from stack_depot_save()
+ *
+ * The stack trace is evicted from stack depot once all references to it have
+ * been dropped (once the number of stack_depot_evict() calls matches the
+ * number of stack_depot_save_flags() calls with STACK_DEPOT_FLAG_GET set for
+ * this stack trace).
+ */
+void stack_depot_put(depot_stack_handle_t handle);
+
+/**
  * stack_depot_set_extra_bits - Set extra bits in a stack depot handle
  *
  * @handle:	Stack depot handle returned from stack_depot_save()
diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h
index c36e7a3b45e7..3be2cb564710 100644
--- a/include/linux/stackleak.h
+++ b/include/linux/stackleak.h
@@ -14,6 +14,7 @@
 
 #ifdef CONFIG_GCC_PLUGIN_STACKLEAK
 #include <asm/stacktrace.h>
+#include <linux/linkage.h>
 
 /*
  * The lowest address on tsk's stack which we can plausibly erase.
@@ -76,6 +77,11 @@ static inline void stackleak_task_init(struct task_struct *t)
 # endif
 }
 
+asmlinkage void noinstr stackleak_erase(void);
+asmlinkage void noinstr stackleak_erase_on_task_stack(void);
+asmlinkage void noinstr stackleak_erase_off_task_stack(void);
+void __no_caller_saved_registers noinstr stackleak_track_stack(void);
+
 #else /* !CONFIG_GCC_PLUGIN_STACKLEAK */
 static inline void stackleak_task_init(struct task_struct *t) { }
 #endif
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 0b4658a7eceb..dee5ad6e48c5 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -175,6 +175,7 @@ struct stmmac_fpe_cfg {
 	bool hs_enable;				/* FPE handshake enable */
 	enum stmmac_fpe_state lp_fpe_state;	/* Link Partner FPE state */
 	enum stmmac_fpe_state lo_fpe_state;	/* Local station FPE state */
+	u32 fpe_csr;				/* MAC_FPE_CTRL_STS reg cache */
 };
 
 struct stmmac_safety_feature_cfg {
diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h
index db30a159f9d5..f22bf915dcf6 100644
--- a/include/linux/sunrpc/bc_xprt.h
+++ b/include/linux/sunrpc/bc_xprt.h
@@ -20,7 +20,8 @@
 #ifdef CONFIG_SUNRPC_BACKCHANNEL
 struct rpc_rqst *xprt_lookup_bc_request(struct rpc_xprt *xprt, __be32 xid);
 void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied);
-void xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task);
+void xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task,
+		const struct rpc_timeout *to);
 void xprt_free_bc_request(struct rpc_rqst *req);
 int xprt_setup_backchannel(struct rpc_xprt *, unsigned int min_reqs);
 void xprt_destroy_backchannel(struct rpc_xprt *, unsigned int max_reqs);
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index e9d4377d03c6..5e9d1469c6fa 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -252,7 +252,6 @@ void		rpc_clnt_probe_trunked_xprts(struct rpc_clnt *,
 
 const char *rpc_proc_name(const struct rpc_task *task);
 
-void rpc_clnt_xprt_switch_put(struct rpc_clnt *);
 void rpc_clnt_xprt_switch_add_xprt(struct rpc_clnt *, struct rpc_xprt *);
 void rpc_clnt_xprt_switch_remove_xprt(struct rpc_clnt *, struct rpc_xprt *);
 bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt,
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 8ada7dc802d3..2d61987b3545 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -38,6 +38,17 @@ struct rpc_wait {
 };
 
 /*
+ * This describes a timeout strategy
+ */
+struct rpc_timeout {
+	unsigned long		to_initval,		/* initial timeout */
+				to_maxval,		/* max timeout */
+				to_increment;		/* if !exponential */
+	unsigned int		to_retries;		/* max # of retries */
+	unsigned char		to_exponential;
+};
+
+/*
  * This is the RPC task struct
  */
 struct rpc_task {
@@ -205,7 +216,8 @@ struct rpc_wait_queue {
  */
 struct rpc_task *rpc_new_task(const struct rpc_task_setup *);
 struct rpc_task *rpc_run_task(const struct rpc_task_setup *);
-struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req);
+struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req,
+		struct rpc_timeout *timeout);
 void		rpc_put_task(struct rpc_task *);
 void		rpc_put_task_async(struct rpc_task *);
 bool		rpc_task_set_rpc_status(struct rpc_task *task, int rpc_status);
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index b10f987509cc..67cf1c9efd80 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -69,7 +69,6 @@ struct svc_serv {
 	struct svc_program *	sv_program;	/* RPC program */
 	struct svc_stat *	sv_stats;	/* RPC statistics */
 	spinlock_t		sv_lock;
-	struct kref		sv_refcnt;
 	unsigned int		sv_nrthreads;	/* # of server threads */
 	unsigned int		sv_maxconn;	/* max connections allowed or
 						 * '0' causing max to be based
@@ -97,31 +96,13 @@ struct svc_serv {
 #endif /* CONFIG_SUNRPC_BACKCHANNEL */
 };
 
-/**
- * svc_get() - increment reference count on a SUNRPC serv
- * @serv:  the svc_serv to have count incremented
- *
- * Returns: the svc_serv that was passed in.
- */
-static inline struct svc_serv *svc_get(struct svc_serv *serv)
-{
-	kref_get(&serv->sv_refcnt);
-	return serv;
-}
-
-void svc_destroy(struct kref *);
+/* This is used by pool_stats to find and lock an svc */
+struct svc_info {
+	struct svc_serv		*serv;
+	struct mutex		*mutex;
+};
 
-/**
- * svc_put - decrement reference count on a SUNRPC serv
- * @serv:  the svc_serv to have count decremented
- *
- * When the reference count reaches zero, svc_destroy()
- * is called to clean up and free the serv.
- */
-static inline void svc_put(struct svc_serv *serv)
-{
-	kref_put(&serv->sv_refcnt, svc_destroy);
-}
+void svc_destroy(struct svc_serv **svcp);
 
 /*
  * Maximum payload size supported by a kernel RPC server.
@@ -250,6 +231,8 @@ struct svc_rqst {
 	struct net		*rq_bc_net;	/* pointer to backchannel's
 						 * net namespace
 						 */
+	unsigned long	bc_to_initval;
+	unsigned int	bc_to_retries;
 	void **			rq_lease_breaker; /* The v4 client breaking a lease */
 	unsigned int		rq_status_counter; /* RPC processing counter */
 };
@@ -260,8 +243,6 @@ enum {
 	RQ_LOCAL,		/* local request */
 	RQ_USEDEFERRAL,		/* use deferral */
 	RQ_DROPME,		/* drop current reply */
-	RQ_SPLICE_OK,		/* turned off in gss privacy to prevent
-				 * encrypting page cache pages */
 	RQ_VICTIM,		/* Have agreed to shut down */
 	RQ_DATA,		/* request has data */
 };
@@ -433,7 +414,7 @@ void		   svc_exit_thread(struct svc_rqst *);
 struct svc_serv *  svc_create_pooled(struct svc_program *, unsigned int,
 				     int (*threadfn)(void *data));
 int		   svc_set_num_threads(struct svc_serv *, struct svc_pool *, int);
-int		   svc_pool_stats_open(struct svc_serv *serv, struct file *file);
+int		   svc_pool_stats_open(struct svc_info *si, struct file *file);
 void		   svc_process(struct svc_rqst *rqstp);
 void		   svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp);
 int		   svc_register(const struct svc_serv *, struct net *, const int,
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index a5ee0af2a310..e7595ae62fe2 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -65,6 +65,7 @@ extern unsigned int svcrdma_ord;
 extern unsigned int svcrdma_max_requests;
 extern unsigned int svcrdma_max_bc_requests;
 extern unsigned int svcrdma_max_req_size;
+extern struct workqueue_struct *svcrdma_wq;
 
 extern struct percpu_counter svcrdma_stat_read;
 extern struct percpu_counter svcrdma_stat_recv;
@@ -97,6 +98,7 @@ struct svcxprt_rdma {
 	u32		     sc_pending_recvs;
 	u32		     sc_recv_batch;
 	struct list_head     sc_rq_dto_q;
+	struct list_head     sc_read_complete_q;
 	spinlock_t	     sc_rq_dto_lock;
 	struct ib_qp         *sc_qp;
 	struct ib_cq         *sc_rq_cq;
@@ -115,6 +117,13 @@ struct svcxprt_rdma {
 /* sc_flags */
 #define RDMAXPRT_CONN_PENDING	3
 
+static inline struct svcxprt_rdma *svc_rdma_rqst_rdma(struct svc_rqst *rqstp)
+{
+	struct svc_xprt *xprt = rqstp->rq_xprt;
+
+	return container_of(xprt, struct svcxprt_rdma, sc_xprt);
+}
+
 /*
  * Default connection parameters
  */
@@ -126,6 +135,43 @@ enum {
 
 #define RPCSVC_MAXPAYLOAD_RDMA	RPCSVC_MAXPAYLOAD
 
+/**
+ * svc_rdma_send_cid_init - Initialize a Receive Queue completion ID
+ * @rdma: controlling transport
+ * @cid: completion ID to initialize
+ */
+static inline void svc_rdma_recv_cid_init(struct svcxprt_rdma *rdma,
+					  struct rpc_rdma_cid *cid)
+{
+	cid->ci_queue_id = rdma->sc_rq_cq->res.id;
+	cid->ci_completion_id = atomic_inc_return(&rdma->sc_completion_ids);
+}
+
+/**
+ * svc_rdma_send_cid_init - Initialize a Send Queue completion ID
+ * @rdma: controlling transport
+ * @cid: completion ID to initialize
+ */
+static inline void svc_rdma_send_cid_init(struct svcxprt_rdma *rdma,
+					  struct rpc_rdma_cid *cid)
+{
+	cid->ci_queue_id = rdma->sc_sq_cq->res.id;
+	cid->ci_completion_id = atomic_inc_return(&rdma->sc_completion_ids);
+}
+
+/*
+ * A chunk context tracks all I/O for moving one Read or Write
+ * chunk. This is a set of rdma_rw's that handle data movement
+ * for all segments of one chunk.
+ */
+struct svc_rdma_chunk_ctxt {
+	struct rpc_rdma_cid	cc_cid;
+	struct ib_cqe		cc_cqe;
+	struct list_head	cc_rwctxts;
+	ktime_t			cc_posttime;
+	int			cc_sqecount;
+};
+
 struct svc_rdma_recv_ctxt {
 	struct llist_node	rc_node;
 	struct list_head	rc_list;
@@ -136,22 +182,33 @@ struct svc_rdma_recv_ctxt {
 	void			*rc_recv_buf;
 	struct xdr_stream	rc_stream;
 	u32			rc_byte_len;
-	unsigned int		rc_page_count;
 	u32			rc_inv_rkey;
 	__be32			rc_msgtype;
 
+	/* State for pulling a Read chunk */
+	unsigned int		rc_pageoff;
+	unsigned int		rc_curpage;
+	unsigned int		rc_readbytes;
+	struct xdr_buf		rc_saved_arg;
+	struct svc_rdma_chunk_ctxt	rc_cc;
+
 	struct svc_rdma_pcl	rc_call_pcl;
 
 	struct svc_rdma_pcl	rc_read_pcl;
 	struct svc_rdma_chunk	*rc_cur_result_payload;
 	struct svc_rdma_pcl	rc_write_pcl;
 	struct svc_rdma_pcl	rc_reply_pcl;
+
+	unsigned int		rc_page_count;
+	struct page		*rc_pages[RPCSVC_MAXPAGES];
 };
 
 struct svc_rdma_send_ctxt {
 	struct llist_node	sc_node;
 	struct rpc_rdma_cid	sc_cid;
+	struct work_struct	sc_work;
 
+	struct svcxprt_rdma	*sc_rdma;
 	struct ib_send_wr	sc_send_wr;
 	struct ib_cqe		sc_cqe;
 	struct xdr_buf		sc_hdrbuf;
@@ -180,6 +237,11 @@ extern int svc_rdma_recvfrom(struct svc_rqst *);
 
 /* svc_rdma_rw.c */
 extern void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma);
+extern void svc_rdma_cc_init(struct svcxprt_rdma *rdma,
+			     struct svc_rdma_chunk_ctxt *cc);
+extern void svc_rdma_cc_release(struct svcxprt_rdma *rdma,
+				struct svc_rdma_chunk_ctxt *cc,
+				enum dma_data_direction dir);
 extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
 				     const struct svc_rdma_chunk *chunk,
 				     const struct xdr_buf *xdr);
@@ -200,7 +262,8 @@ extern int svc_rdma_send(struct svcxprt_rdma *rdma,
 			 struct svc_rdma_send_ctxt *ctxt);
 extern int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 				  struct svc_rdma_send_ctxt *sctxt,
-				  const struct svc_rdma_recv_ctxt *rctxt,
+				  const struct svc_rdma_pcl *write_pcl,
+				  const struct svc_rdma_pcl *reply_pcl,
 				  const struct xdr_buf *xdr);
 extern void svc_rdma_send_error_msg(struct svcxprt_rdma *rdma,
 				    struct svc_rdma_send_ctxt *sctxt,
diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h
index 6f90203edbf8..61c455f1e1f5 100644
--- a/include/linux/sunrpc/svcauth.h
+++ b/include/linux/sunrpc/svcauth.h
@@ -131,8 +131,11 @@ enum svc_auth_status {
  *   This call releases a domain.
  *
  * set_client()
- *   Givens a pending request (struct svc_rqst), finds and assigns
+ *   Given a pending request (struct svc_rqst), finds and assigns
  *   an appropriate 'auth_domain' as the client.
+ *
+ * pseudoflavor()
+ *   Returns RPC_AUTH pseudoflavor in use by @rqstp.
  */
 struct auth_ops {
 	char *	name;
@@ -143,11 +146,13 @@ struct auth_ops {
 	int			(*release)(struct svc_rqst *rqstp);
 	void			(*domain_release)(struct auth_domain *dom);
 	enum svc_auth_status	(*set_client)(struct svc_rqst *rqstp);
+	rpc_authflavor_t	(*pseudoflavor)(struct svc_rqst *rqstp);
 };
 
 struct svc_xprt;
 
 extern enum svc_auth_status svc_authenticate(struct svc_rqst *rqstp);
+extern rpc_authflavor_t svc_auth_flavor(struct svc_rqst *rqstp);
 extern int	svc_authorise(struct svc_rqst *rqstp);
 extern enum svc_auth_status svc_set_client(struct svc_rqst *rqstp);
 extern int	svc_auth_register(rpc_authflavor_t flavor, struct auth_ops *aops);
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index f85d3a0daca2..464f6a9492ab 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -30,17 +30,6 @@
 #define RPC_MAXCWND(xprt)	((xprt)->max_reqs << RPC_CWNDSHIFT)
 #define RPCXPRT_CONGESTED(xprt) ((xprt)->cong >= (xprt)->cwnd)
 
-/*
- * This describes a timeout strategy
- */
-struct rpc_timeout {
-	unsigned long		to_initval,		/* initial timeout */
-				to_maxval,		/* max timeout */
-				to_increment;		/* if !exponential */
-	unsigned int		to_retries;		/* max # of retries */
-	unsigned char		to_exponential;
-};
-
 enum rpc_display_format_t {
 	RPC_DISPLAY_ADDR = 0,
 	RPC_DISPLAY_PORT,
diff --git a/include/linux/surface_aggregator/serial_hub.h b/include/linux/surface_aggregator/serial_hub.h
index 5c4ae1a26183..d8dbef6b7fc2 100644
--- a/include/linux/surface_aggregator/serial_hub.h
+++ b/include/linux/surface_aggregator/serial_hub.h
@@ -12,7 +12,7 @@
 #ifndef _LINUX_SURFACE_AGGREGATOR_SERIAL_HUB_H
 #define _LINUX_SURFACE_AGGREGATOR_SERIAL_HUB_H
 
-#include <linux/crc-ccitt.h>
+#include <linux/crc-itu-t.h>
 #include <linux/kref.h>
 #include <linux/ktime.h>
 #include <linux/list.h>
@@ -188,7 +188,7 @@ static_assert(sizeof(struct ssh_command) == 8);
  */
 static inline u16 ssh_crc(const u8 *buf, size_t len)
 {
-	return crc_ccitt_false(0xffff, buf, len);
+	return crc_itu_t(0xffff, buf, len);
 }
 
 /*
diff --git a/include/linux/swap.h b/include/linux/swap.h
index f6dd6575b905..4db00ddad261 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -397,9 +397,6 @@ void folio_deactivate(struct folio *folio);
 void folio_mark_lazyfree(struct folio *folio);
 extern void swap_setup(void);
 
-extern void lru_cache_add_inactive_or_unevictable(struct page *page,
-						struct vm_area_struct *vma);
-
 /* linux/mm/vmscan.c */
 extern unsigned long zone_reclaimable_pages(struct zone *zone);
 extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
@@ -490,13 +487,12 @@ extern sector_t swapdev_block(int, pgoff_t);
 extern int __swap_count(swp_entry_t entry);
 extern int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry);
 extern int swp_swapcount(swp_entry_t entry);
-extern struct swap_info_struct *page_swap_info(struct page *);
-extern struct swap_info_struct *swp_swap_info(swp_entry_t entry);
+struct swap_info_struct *swp_swap_info(swp_entry_t entry);
 struct backing_dev_info;
 extern int init_swap_address_space(unsigned int type, unsigned long nr_pages);
 extern void exit_swap_address_space(unsigned int type);
 extern struct swap_info_struct *get_swap_device(swp_entry_t entry);
-sector_t swap_page_sector(struct page *page);
+sector_t swap_folio_sector(struct folio *folio);
 
 static inline void put_swap_device(struct swap_info_struct *si)
 {
diff --git a/include/linux/syscall_user_dispatch.h b/include/linux/syscall_user_dispatch.h
index 641ca8880995..3858a6ffdd5c 100644
--- a/include/linux/syscall_user_dispatch.h
+++ b/include/linux/syscall_user_dispatch.h
@@ -6,16 +6,10 @@
 #define _SYSCALL_USER_DISPATCH_H
 
 #include <linux/thread_info.h>
+#include <linux/syscall_user_dispatch_types.h>
 
 #ifdef CONFIG_GENERIC_ENTRY
 
-struct syscall_user_dispatch {
-	char __user	*selector;
-	unsigned long	offset;
-	unsigned long	len;
-	bool		on_dispatch;
-};
-
 int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
 			      unsigned long len, char __user *selector);
 
@@ -29,7 +23,6 @@ int syscall_user_dispatch_set_config(struct task_struct *task, unsigned long siz
 				     void __user *data);
 
 #else
-struct syscall_user_dispatch {};
 
 static inline int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
 					    unsigned long len, char __user *selector)
diff --git a/include/linux/syscall_user_dispatch_types.h b/include/linux/syscall_user_dispatch_types.h
new file mode 100644
index 000000000000..3be36b06c7d7
--- /dev/null
+++ b/include/linux/syscall_user_dispatch_types.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _SYSCALL_USER_DISPATCH_TYPES_H
+#define _SYSCALL_USER_DISPATCH_TYPES_H
+
+#include <linux/types.h>
+
+#ifdef CONFIG_GENERIC_ENTRY
+
+struct syscall_user_dispatch {
+	char __user	*selector;
+	unsigned long	offset;
+	unsigned long	len;
+	bool		on_dispatch;
+};
+
+#else
+
+struct syscall_user_dispatch {};
+
+#endif
+
+#endif /* _SYSCALL_USER_DISPATCH_TYPES_H */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index fd9d12de7e92..5c0dbef55792 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -71,9 +71,12 @@ struct clone_args;
 struct open_how;
 struct mount_attr;
 struct landlock_ruleset_attr;
+struct lsm_ctx;
 enum landlock_rule_type;
 struct cachestat_range;
 struct cachestat;
+struct statmount;
+struct mnt_id_req;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -407,6 +410,12 @@ asmlinkage long sys_statfs64(const char __user *path, size_t sz,
 asmlinkage long sys_fstatfs(unsigned int fd, struct statfs __user *buf);
 asmlinkage long sys_fstatfs64(unsigned int fd, size_t sz,
 				struct statfs64 __user *buf);
+asmlinkage long sys_statmount(const struct mnt_id_req __user *req,
+			      struct statmount __user *buf, size_t bufsize,
+			      unsigned int flags);
+asmlinkage long sys_listmount(const struct mnt_id_req __user *req,
+			      u64 __user *buf, size_t bufsize,
+			      unsigned int flags);
 asmlinkage long sys_truncate(const char __user *path, long length);
 asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length);
 #if BITS_PER_LONG == 32
@@ -949,6 +958,11 @@ asmlinkage long sys_cachestat(unsigned int fd,
 		struct cachestat_range __user *cstat_range,
 		struct cachestat __user *cstat, unsigned int flags);
 asmlinkage long sys_map_shadow_stack(unsigned long addr, unsigned long size, unsigned int flags);
+asmlinkage long sys_lsm_get_self_attr(unsigned int attr, struct lsm_ctx *ctx,
+				      size_t *size, __u32 flags);
+asmlinkage long sys_lsm_set_self_attr(unsigned int attr, struct lsm_ctx *ctx,
+				      size_t size, __u32 flags);
+asmlinkage long sys_lsm_list_modules(u64 *ids, size_t *size, u32 flags);
 
 /*
  * Architecture-specific system calls
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 61b40ea81f4d..ee7d33b89e9e 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -210,11 +210,6 @@ struct ctl_table_root {
 	int (*permissions)(struct ctl_table_header *head, struct ctl_table *table);
 };
 
-/* struct ctl_path describes where in the hierarchy a table is added */
-struct ctl_path {
-	const char *procname;
-};
-
 #define register_sysctl(path, table)	\
 	register_sysctl_sz(path, table, ARRAY_SIZE(table))
 
@@ -255,8 +250,6 @@ extern int unaligned_enabled;
 extern int unaligned_dump_stack;
 extern int no_unaligned_warning;
 
-#define SYSCTL_PERM_EMPTY_DIR	(1 << 0)
-
 #else /* CONFIG_SYSCTL */
 
 static inline void register_sysctl_init(const char *path, struct ctl_table *table)
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 68f3d315d2e1..89b290d8c8dc 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -169,7 +169,7 @@ struct tcp_request_sock {
 #ifdef CONFIG_TCP_AO
 	u8				ao_keyid;
 	u8				ao_rcv_next;
-	u8				maclen;
+	bool				used_tcp_ao;
 #endif
 };
 
@@ -180,37 +180,131 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)
 
 static inline bool tcp_rsk_used_ao(const struct request_sock *req)
 {
-	/* The real length of MAC is saved in the request socket,
-	 * signing anything with zero-length makes no sense, so here is
-	 * a little hack..
-	 */
 #ifndef CONFIG_TCP_AO
 	return false;
 #else
-	return tcp_rsk(req)->maclen != 0;
+	return tcp_rsk(req)->used_tcp_ao;
 #endif
 }
 
 #define TCP_RMEM_TO_WIN_SCALE 8
 
 struct tcp_sock {
+	/* Cacheline organization can be found documented in
+	 * Documentation/networking/net_cachelines/tcp_sock.rst.
+	 * Please update the document when adding new fields.
+	 */
+
 	/* inet_connection_sock has to be the first member of tcp_sock */
 	struct inet_connection_sock	inet_conn;
-	u16	tcp_header_len;	/* Bytes of tcp header to send		*/
+
+	/* TX read-mostly hotpath cache lines */
+	__cacheline_group_begin(tcp_sock_read_tx);
+	/* timestamp of last sent data packet (for restart window) */
+	u32	max_window;	/* Maximal window ever seen from peer	*/
+	u32	rcv_ssthresh;	/* Current window clamp			*/
+	u32	reordering;	/* Packet reordering metric.		*/
+	u32	notsent_lowat;	/* TCP_NOTSENT_LOWAT */
 	u16	gso_segs;	/* Max number of segs per GSO packet	*/
+	/* from STCP, retrans queue hinting */
+	struct sk_buff *lost_skb_hint;
+	struct sk_buff *retransmit_skb_hint;
+	__cacheline_group_end(tcp_sock_read_tx);
+
+	/* TXRX read-mostly hotpath cache lines */
+	__cacheline_group_begin(tcp_sock_read_txrx);
+	u32	tsoffset;	/* timestamp offset */
+	u32	snd_wnd;	/* The window we expect to receive	*/
+	u32	mss_cache;	/* Cached effective mss, not including SACKS */
+	u32	snd_cwnd;	/* Sending congestion window		*/
+	u32	prr_out;	/* Total number of pkts sent during Recovery. */
+	u32	lost_out;	/* Lost packets			*/
+	u32	sacked_out;	/* SACK'd packets			*/
+	u16	tcp_header_len;	/* Bytes of tcp header to send		*/
+	u8	chrono_type : 2,	/* current chronograph type */
+		repair      : 1,
+		is_sack_reneg:1,    /* in recovery from loss with SACK reneg? */
+		is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */
+	__cacheline_group_end(tcp_sock_read_txrx);
+
+	/* RX read-mostly hotpath cache lines */
+	__cacheline_group_begin(tcp_sock_read_rx);
+	u32	copied_seq;	/* Head of yet unread data */
+	u32	rcv_tstamp;	/* timestamp of last received ACK (for keepalives) */
+	u32	snd_wl1;	/* Sequence for window update		*/
+	u32	tlp_high_seq;	/* snd_nxt at the time of TLP */
+	u32	rttvar_us;	/* smoothed mdev_max			*/
+	u32	retrans_out;	/* Retransmitted packets out		*/
+	u16	advmss;		/* Advertised MSS			*/
+	u16	urg_data;	/* Saved octet of OOB data and control flags */
+	u32	lost;		/* Total data packets lost incl. rexmits */
+	struct  minmax rtt_min;
+	/* OOO segments go in this rbtree. Socket lock must be held. */
+	struct rb_root	out_of_order_queue;
+	u32	snd_ssthresh;	/* Slow start size threshold		*/
+	__cacheline_group_end(tcp_sock_read_rx);
 
+	/* TX read-write hotpath cache lines */
+	__cacheline_group_begin(tcp_sock_write_tx) ____cacheline_aligned;
+	u32	segs_out;	/* RFC4898 tcpEStatsPerfSegsOut
+				 * The total number of segments sent.
+				 */
+	u32	data_segs_out;	/* RFC4898 tcpEStatsPerfDataSegsOut
+				 * total number of data segments sent.
+				 */
+	u64	bytes_sent;	/* RFC4898 tcpEStatsPerfHCDataOctetsOut
+				 * total number of data bytes sent.
+				 */
+	u32	snd_sml;	/* Last byte of the most recently transmitted small packet */
+	u32	chrono_start;	/* Start time in jiffies of a TCP chrono */
+	u32	chrono_stat[3];	/* Time in jiffies for chrono_stat stats */
+	u32	write_seq;	/* Tail(+1) of data held in tcp send buffer */
+	u32	pushed_seq;	/* Last pushed seq, required to talk to windows */
+	u32	lsndtime;
+	u32	mdev_us;	/* medium deviation			*/
+	u64	tcp_wstamp_ns;	/* departure time for next sent data packet */
+	u64	tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */
+	u64	tcp_mstamp;	/* most recent packet received/sent */
+	u32	rtt_seq;	/* sequence number to update rttvar	*/
+	struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */
+	struct sk_buff *highest_sack;   /* skb just after the highest
+					 * skb with SACKed bit set
+					 * (validity guaranteed only if
+					 * sacked_out > 0)
+					 */
+	u8	ecn_flags;	/* ECN status bits.			*/
+	__cacheline_group_end(tcp_sock_write_tx);
+
+	/* TXRX read-write hotpath cache lines */
+	__cacheline_group_begin(tcp_sock_write_txrx);
 /*
  *	Header prediction flags
  *	0x5?10 << 16 + snd_wnd in net byte order
  */
 	__be32	pred_flags;
-
+	u32	rcv_nxt;	/* What we want to receive next		*/
+	u32	snd_nxt;	/* Next sequence we send		*/
+	u32	snd_una;	/* First byte we want an ack for	*/
+	u32	window_clamp;	/* Maximal window to advertise		*/
+	u32	srtt_us;	/* smoothed round trip time << 3 in usecs */
+	u32	packets_out;	/* Packets which are "in flight"	*/
+	u32	snd_up;		/* Urgent pointer		*/
+	u32	delivered;	/* Total data packets delivered incl. rexmits */
+	u32	delivered_ce;	/* Like the above but only ECE marked packets */
+	u32	app_limited;	/* limited until "delivered" reaches this val */
+	u32	rcv_wnd;	/* Current receiver window		*/
 /*
- *	RFC793 variables by their proper names. This means you can
- *	read the code and the spec side by side (and laugh ...)
- *	See RFC793 and RFC1122. The RFC writes these in capitals.
+ *      Options received (usually on last packet, some only on SYN packets).
  */
-	u64	bytes_received;	/* RFC4898 tcpEStatsAppHCThruOctetsReceived
+	struct tcp_options_received rx_opt;
+	u8	nonagle     : 4,/* Disable Nagle algorithm?             */
+		rate_app_limited:1;  /* rate_{delivered,interval_us} limited? */
+	__cacheline_group_end(tcp_sock_write_txrx);
+
+	/* RX read-write hotpath cache lines */
+	__cacheline_group_begin(tcp_sock_write_rx);
+	u64	bytes_received;
+				/* RFC4898 tcpEStatsAppHCThruOctetsReceived
 				 * sum(delta(rcv_nxt)), or how many bytes
 				 * were acked.
 				 */
@@ -220,45 +314,44 @@ struct tcp_sock {
 	u32	data_segs_in;	/* RFC4898 tcpEStatsPerfDataSegsIn
 				 * total number of data segments in.
 				 */
- 	u32	rcv_nxt;	/* What we want to receive next 	*/
-	u32	copied_seq;	/* Head of yet unread data		*/
 	u32	rcv_wup;	/* rcv_nxt on last window update sent	*/
- 	u32	snd_nxt;	/* Next sequence we send		*/
-	u32	segs_out;	/* RFC4898 tcpEStatsPerfSegsOut
-				 * The total number of segments sent.
-				 */
-	u32	data_segs_out;	/* RFC4898 tcpEStatsPerfDataSegsOut
-				 * total number of data segments sent.
-				 */
-	u64	bytes_sent;	/* RFC4898 tcpEStatsPerfHCDataOctetsOut
-				 * total number of data bytes sent.
-				 */
+	u32	max_packets_out;  /* max packets_out in last window */
+	u32	cwnd_usage_seq;  /* right edge of cwnd usage tracking flight */
+	u32	rate_delivered;    /* saved rate sample: packets delivered */
+	u32	rate_interval_us;  /* saved rate sample: time elapsed */
+	u32	rcv_rtt_last_tsecr;
+	u64	first_tx_mstamp;  /* start of window send phase */
+	u64	delivered_mstamp; /* time we reached "delivered" */
 	u64	bytes_acked;	/* RFC4898 tcpEStatsAppHCThruOctetsAcked
 				 * sum(delta(snd_una)), or how many bytes
 				 * were acked.
 				 */
+	struct {
+		u32	rtt_us;
+		u32	seq;
+		u64	time;
+	} rcv_rtt_est;
+/* Receiver queue space */
+	struct {
+		u32	space;
+		u32	seq;
+		u64	time;
+	} rcvq_space;
+	__cacheline_group_end(tcp_sock_write_rx);
+	/* End of Hot Path */
+
+/*
+ *	RFC793 variables by their proper names. This means you can
+ *	read the code and the spec side by side (and laugh ...)
+ *	See RFC793 and RFC1122. The RFC writes these in capitals.
+ */
 	u32	dsack_dups;	/* RFC4898 tcpEStatsStackDSACKDups
 				 * total number of DSACK blocks received
 				 */
- 	u32	snd_una;	/* First byte we want an ack for	*/
- 	u32	snd_sml;	/* Last byte of the most recently transmitted small packet */
-	u32	rcv_tstamp;	/* timestamp of last received ACK (for keepalives) */
-	u32	lsndtime;	/* timestamp of last sent data packet (for restart window) */
 	u32	last_oow_ack_time;  /* timestamp of last out-of-window ACK */
 	u32	compressed_ack_rcv_nxt;
-
-	u32	tsoffset;	/* timestamp offset */
-
 	struct list_head tsq_node; /* anchor in tsq_tasklet.head list */
-	struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */
-
-	u32	snd_wl1;	/* Sequence for window update		*/
-	u32	snd_wnd;	/* The window we expect to receive	*/
-	u32	max_window;	/* Maximal window ever seen from peer	*/
-	u32	mss_cache;	/* Cached effective mss, not including SACKS */
 
-	u32	window_clamp;	/* Maximal window to advertise		*/
-	u32	rcv_ssthresh;	/* Current window clamp			*/
 	u8	scaling_ratio;	/* see tcp_win_from_space() */
 	/* Information of the most recently (s)acked skb */
 	struct tcp_rack {
@@ -272,24 +365,16 @@ struct tcp_sock {
 		   dsack_seen:1, /* Whether DSACK seen after last adj */
 		   advanced:1;	 /* mstamp advanced since last lost marking */
 	} rack;
-	u16	advmss;		/* Advertised MSS			*/
 	u8	compressed_ack;
 	u8	dup_ack_counter:2,
 		tlp_retrans:1,	/* TLP is a retransmission */
 		tcp_usec_ts:1, /* TSval values in usec */
 		unused:4;
-	u32	chrono_start;	/* Start time in jiffies of a TCP chrono */
-	u32	chrono_stat[3];	/* Time in jiffies for chrono_stat stats */
-	u8	chrono_type:2,	/* current chronograph type */
-		rate_app_limited:1,  /* rate_{delivered,interval_us} limited? */
+	u8	thin_lto    : 1,/* Use linear timeouts for thin streams */
+		recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */
 		fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */
 		fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */
-		is_sack_reneg:1,    /* in recovery from loss with SACK reneg? */
-		fastopen_client_fail:2; /* reason why fastopen failed */
-	u8	nonagle     : 4,/* Disable Nagle algorithm?             */
-		thin_lto    : 1,/* Use linear timeouts for thin streams */
-		recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */
-		repair      : 1,
+		fastopen_client_fail:2, /* reason why fastopen failed */
 		frto        : 1;/* F-RTO (RFC5682) activated in CA_Loss */
 	u8	repair_queue;
 	u8	save_syn:2,	/* Save headers of SYN packet */
@@ -297,45 +382,19 @@ struct tcp_sock {
 		syn_fastopen:1,	/* SYN includes Fast Open option */
 		syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */
 		syn_fastopen_ch:1, /* Active TFO re-enabling probe */
-		syn_data_acked:1,/* data in SYN is acked by SYN-ACK */
-		is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */
-	u32	tlp_high_seq;	/* snd_nxt at the time of TLP */
+		syn_data_acked:1;/* data in SYN is acked by SYN-ACK */
 
 	u32	tcp_tx_delay;	/* delay (in usec) added to TX packets */
-	u64	tcp_wstamp_ns;	/* departure time for next sent data packet */
-	u64	tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */
 
 /* RTT measurement */
-	u64	tcp_mstamp;	/* most recent packet received/sent */
-	u32	srtt_us;	/* smoothed round trip time << 3 in usecs */
-	u32	mdev_us;	/* medium deviation			*/
 	u32	mdev_max_us;	/* maximal mdev for the last rtt period	*/
-	u32	rttvar_us;	/* smoothed mdev_max			*/
-	u32	rtt_seq;	/* sequence number to update rttvar	*/
-	struct  minmax rtt_min;
 
-	u32	packets_out;	/* Packets which are "in flight"	*/
-	u32	retrans_out;	/* Retransmitted packets out		*/
-	u32	max_packets_out;  /* max packets_out in last window */
-	u32	cwnd_usage_seq;  /* right edge of cwnd usage tracking flight */
-
-	u16	urg_data;	/* Saved octet of OOB data and control flags */
-	u8	ecn_flags;	/* ECN status bits.			*/
 	u8	keepalive_probes; /* num of allowed keep alive probes	*/
-	u32	reordering;	/* Packet reordering metric.		*/
 	u32	reord_seen;	/* number of data packet reordering events */
-	u32	snd_up;		/* Urgent pointer		*/
-
-/*
- *      Options received (usually on last packet, some only on SYN packets).
- */
-	struct tcp_options_received rx_opt;
 
 /*
  *	Slow start and congestion control (see also Nagle, and Karn & Partridge)
  */
- 	u32	snd_ssthresh;	/* Slow start size threshold		*/
- 	u32	snd_cwnd;	/* Sending congestion window		*/
 	u32	snd_cwnd_cnt;	/* Linear increase counter		*/
 	u32	snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */
 	u32	snd_cwnd_used;
@@ -343,32 +402,10 @@ struct tcp_sock {
 	u32	prior_cwnd;	/* cwnd right before starting loss recovery */
 	u32	prr_delivered;	/* Number of newly delivered packets to
 				 * receiver in Recovery. */
-	u32	prr_out;	/* Total number of pkts sent during Recovery. */
-	u32	delivered;	/* Total data packets delivered incl. rexmits */
-	u32	delivered_ce;	/* Like the above but only ECE marked packets */
-	u32	lost;		/* Total data packets lost incl. rexmits */
-	u32	app_limited;	/* limited until "delivered" reaches this val */
-	u64	first_tx_mstamp;  /* start of window send phase */
-	u64	delivered_mstamp; /* time we reached "delivered" */
-	u32	rate_delivered;    /* saved rate sample: packets delivered */
-	u32	rate_interval_us;  /* saved rate sample: time elapsed */
-
- 	u32	rcv_wnd;	/* Current receiver window		*/
-	u32	write_seq;	/* Tail(+1) of data held in tcp send buffer */
-	u32	notsent_lowat;	/* TCP_NOTSENT_LOWAT */
-	u32	pushed_seq;	/* Last pushed seq, required to talk to windows */
-	u32	lost_out;	/* Lost packets			*/
-	u32	sacked_out;	/* SACK'd packets			*/
 
 	struct hrtimer	pacing_timer;
 	struct hrtimer	compressed_ack_timer;
 
-	/* from STCP, retrans queue hinting */
-	struct sk_buff* lost_skb_hint;
-	struct sk_buff *retransmit_skb_hint;
-
-	/* OOO segments go in this rbtree. Socket lock must be held. */
-	struct rb_root	out_of_order_queue;
 	struct sk_buff	*ooo_last_skb; /* cache rb_last(out_of_order_queue) */
 
 	/* SACKs data, these 2 need to be together (see tcp_options_write) */
@@ -377,12 +414,6 @@ struct tcp_sock {
 
 	struct tcp_sack_block recv_sack_cache[4];
 
-	struct sk_buff *highest_sack;   /* skb just after the highest
-					 * skb with SACKed bit set
-					 * (validity guaranteed only if
-					 * sacked_out > 0)
-					 */
-
 	int     lost_cnt_hint;
 
 	u32	prior_ssthresh; /* ssthresh saved at recovery start	*/
@@ -433,21 +464,6 @@ struct tcp_sock {
 
 	u32 rcv_ooopack; /* Received out-of-order packets, for tcpinfo */
 
-/* Receiver side RTT estimation */
-	u32 rcv_rtt_last_tsecr;
-	struct {
-		u32	rtt_us;
-		u32	seq;
-		u64	time;
-	} rcv_rtt_est;
-
-/* Receiver queue space */
-	struct {
-		u32	space;
-		u32	seq;
-		u64	time;
-	} rcvq_space;
-
 /* TCP-specific MTU probe information. */
 	struct {
 		u32		  probe_seq_start;
diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h
index 17eb1c5205d3..911ddf92dcee 100644
--- a/include/linux/tee_drv.h
+++ b/include/linux/tee_drv.h
@@ -84,6 +84,7 @@ struct tee_param {
  * @release:		release this open file
  * @open_session:	open a new session
  * @close_session:	close a session
+ * @system_session:	declare session as a system session
  * @invoke_func:	invoke a trusted function
  * @cancel_req:		request cancel of an ongoing invoke or open
  * @supp_recv:		called for supplicant to get a command
@@ -100,6 +101,7 @@ struct tee_driver_ops {
 			    struct tee_ioctl_open_session_arg *arg,
 			    struct tee_param *param);
 	int (*close_session)(struct tee_context *ctx, u32 session);
+	int (*system_session)(struct tee_context *ctx, u32 session);
 	int (*invoke_func)(struct tee_context *ctx,
 			   struct tee_ioctl_invoke_arg *arg,
 			   struct tee_param *param);
@@ -430,6 +432,20 @@ int tee_client_open_session(struct tee_context *ctx,
 int tee_client_close_session(struct tee_context *ctx, u32 session);
 
 /**
+ * tee_client_system_session() - Declare session as a system session
+ * @ctx:	TEE Context
+ * @session:	Session id
+ *
+ * This function requests TEE to provision an entry context ready to use for
+ * that session only. The provisioned entry context is used for command
+ * invocation and session closure, not for command cancelling requests.
+ * TEE releases the provisioned context upon session closure.
+ *
+ * Return < 0 on error else 0 if an entry context has been provisioned.
+ */
+int tee_client_system_session(struct tee_context *ctx, u32 session);
+
+/**
  * tee_client_invoke_func() - Invoke a function in a Trusted Application
  * @ctx:	TEE Context
  * @arg:	Invoke arguments, see description of
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index cee814d5d1ac..bf84595a4e86 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -51,18 +51,23 @@ enum thermal_notify_event {
 	THERMAL_DEVICE_POWER_CAPABILITY_CHANGED, /* power capability changed */
 	THERMAL_TABLE_CHANGED, /* Thermal table(s) changed */
 	THERMAL_EVENT_KEEP_ALIVE, /* Request for user space handler to respond */
+	THERMAL_TZ_BIND_CDEV, /* Cooling dev is bind to the thermal zone */
+	THERMAL_TZ_UNBIND_CDEV, /* Cooling dev is unbind from the thermal zone */
+	THERMAL_INSTANCE_WEIGHT_CHANGED, /* Thermal instance weight changed */
 };
 
 /**
  * struct thermal_trip - representation of a point in temperature domain
  * @temperature: temperature value in miliCelsius
  * @hysteresis: relative hysteresis in miliCelsius
+ * @threshold: trip crossing notification threshold miliCelsius
  * @type: trip point type
  * @priv: pointer to driver data associated with this trip
  */
 struct thermal_trip {
 	int temperature;
 	int hysteresis;
+	int threshold;
 	enum thermal_trip_type type;
 	void *priv;
 };
@@ -115,6 +120,7 @@ struct thermal_cooling_device {
  * @id:		unique id number for each thermal zone
  * @type:	the thermal zone device type
  * @device:	&struct device for this thermal zone
+ * @removal:	removal completion
  * @trip_temp_attrs:	attributes for trip points for sysfs: trip temperature
  * @trip_type_attrs:	attributes for trip points for sysfs: trip type
  * @trip_hyst_attrs:	attributes for trip points for sysfs: trip hysteresis
@@ -149,11 +155,13 @@ struct thermal_cooling_device {
  * @node:	node in thermal_tz_list (in thermal_core.c)
  * @poll_queue:	delayed work for polling
  * @notify_event: Last notification event
+ * @suspended: thermal zone suspend indicator
  */
 struct thermal_zone_device {
 	int id;
 	char type[THERMAL_NAME_LENGTH];
 	struct device device;
+	struct completion removal;
 	struct attribute_group trips_attribute_group;
 	struct thermal_attr *trip_temp_attrs;
 	struct thermal_attr *trip_type_attrs;
@@ -181,6 +189,7 @@ struct thermal_zone_device {
 	struct list_head node;
 	struct delayed_work poll_queue;
 	enum thermal_notify_event notify_event;
+	bool suspended;
 };
 
 /**
@@ -193,6 +202,8 @@ struct thermal_zone_device {
  *			thermal zone.
  * @throttle:	callback called for every trip point even if temperature is
  *		below the trip point temperature
+ * @update_tz:	callback called when thermal zone internals have changed, e.g.
+ *		thermal cooling instance was added/removed
  * @governor_list:	node in thermal_governor_list (in thermal_core.c)
  */
 struct thermal_governor {
@@ -201,6 +212,8 @@ struct thermal_governor {
 	void (*unbind_from_tz)(struct thermal_zone_device *tz);
 	int (*throttle)(struct thermal_zone_device *tz,
 			const struct thermal_trip *trip);
+	void (*update_tz)(struct thermal_zone_device *tz,
+			  enum thermal_notify_event reason);
 	struct list_head	governor_list;
 };
 
@@ -280,10 +293,6 @@ int __thermal_zone_get_trip(struct thermal_zone_device *tz, int trip_id,
 			    struct thermal_trip *trip);
 int thermal_zone_get_trip(struct thermal_zone_device *tz, int trip_id,
 			  struct thermal_trip *trip);
-
-int thermal_zone_set_trip(struct thermal_zone_device *tz, int trip_id,
-			  const struct thermal_trip *trip);
-
 int for_each_thermal_trip(struct thermal_zone_device *tz,
 			  int (*cb)(struct thermal_trip *, void *),
 			  void *data);
@@ -291,16 +300,11 @@ int thermal_zone_for_each_trip(struct thermal_zone_device *tz,
 			       int (*cb)(struct thermal_trip *, void *),
 			       void *data);
 int thermal_zone_get_num_trips(struct thermal_zone_device *tz);
+void thermal_zone_set_trip_temp(struct thermal_zone_device *tz,
+				struct thermal_trip *trip, int temp);
 
 int thermal_zone_get_crit_temp(struct thermal_zone_device *tz, int *temp);
 
-#ifdef CONFIG_THERMAL_ACPI
-int thermal_acpi_active_trip_temp(struct acpi_device *adev, int id, int *ret_temp);
-int thermal_acpi_passive_trip_temp(struct acpi_device *adev, int *ret_temp);
-int thermal_acpi_hot_trip_temp(struct acpi_device *adev, int *ret_temp);
-int thermal_acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp);
-#endif
-
 #ifdef CONFIG_THERMAL
 struct thermal_zone_device *thermal_zone_device_register_with_trips(
 					const char *type,
diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h
index 03d9c5ac01d1..876e31b4461d 100644
--- a/include/linux/time_namespace.h
+++ b/include/linux/time_namespace.h
@@ -7,10 +7,13 @@
 #include <linux/nsproxy.h>
 #include <linux/ns_common.h>
 #include <linux/err.h>
+#include <linux/time64.h>
 
 struct user_namespace;
 extern struct user_namespace init_user_ns;
 
+struct vm_area_struct;
+
 struct timens_offsets {
 	struct timespec64 monotonic;
 	struct timespec64 boottime;
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index fe1e467ba046..7c43e98cf211 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -4,6 +4,7 @@
 
 #include <linux/errno.h>
 #include <linux/clocksource_ids.h>
+#include <linux/ktime.h>
 
 /* Included from linux/ktime.h */
 
diff --git a/include/linux/timer.h b/include/linux/timer.h
index 26a545bb0153..f18a2f1eb79e 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -7,21 +7,7 @@
 #include <linux/stddef.h>
 #include <linux/debugobjects.h>
 #include <linux/stringify.h>
-
-struct timer_list {
-	/*
-	 * All fields that change during normal runtime grouped to the
-	 * same cacheline
-	 */
-	struct hlist_node	entry;
-	unsigned long		expires;
-	void			(*function)(struct timer_list *);
-	u32			flags;
-
-#ifdef CONFIG_LOCKDEP
-	struct lockdep_map	lockdep_map;
-#endif
-};
+#include <linux/timer_types.h>
 
 #ifdef CONFIG_LOCKDEP
 /*
diff --git a/include/linux/timer_types.h b/include/linux/timer_types.h
new file mode 100644
index 000000000000..fae5a388f914
--- /dev/null
+++ b/include/linux/timer_types.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_TIMER_TYPES_H
+#define _LINUX_TIMER_TYPES_H
+
+#include <linux/lockdep_types.h>
+#include <linux/types.h>
+
+struct timer_list {
+	/*
+	 * All fields that change during normal runtime grouped to the
+	 * same cacheline
+	 */
+	struct hlist_node	entry;
+	unsigned long		expires;
+	void			(*function)(struct timer_list *);
+	u32			flags;
+
+#ifdef CONFIG_LOCKDEP
+	struct lockdep_map	lockdep_map;
+#endif
+};
+
+#endif /* _LINUX_TIMER_TYPES_H */
diff --git a/include/linux/timerqueue.h b/include/linux/timerqueue.h
index adc80e29168e..62973f7d4610 100644
--- a/include/linux/timerqueue.h
+++ b/include/linux/timerqueue.h
@@ -3,18 +3,7 @@
 #define _LINUX_TIMERQUEUE_H
 
 #include <linux/rbtree.h>
-#include <linux/ktime.h>
-
-
-struct timerqueue_node {
-	struct rb_node node;
-	ktime_t expires;
-};
-
-struct timerqueue_head {
-	struct rb_root_cached rb_root;
-};
-
+#include <linux/timerqueue_types.h>
 
 extern bool timerqueue_add(struct timerqueue_head *head,
 			   struct timerqueue_node *node);
diff --git a/include/linux/timerqueue_types.h b/include/linux/timerqueue_types.h
new file mode 100644
index 000000000000..dc298d0923e3
--- /dev/null
+++ b/include/linux/timerqueue_types.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_TIMERQUEUE_TYPES_H
+#define _LINUX_TIMERQUEUE_TYPES_H
+
+#include <linux/rbtree_types.h>
+#include <linux/types.h>
+
+struct timerqueue_node {
+	struct rb_node node;
+	ktime_t expires;
+};
+
+struct timerqueue_head {
+	struct rb_root_cached rb_root;
+};
+
+#endif /* _LINUX_TIMERQUEUE_TYPES_H */
diff --git a/include/linux/tnum.h b/include/linux/tnum.h
index 1c3948a1d6ad..3c13240077b8 100644
--- a/include/linux/tnum.h
+++ b/include/linux/tnum.h
@@ -106,6 +106,10 @@ int tnum_sbin(char *str, size_t size, struct tnum a);
 struct tnum tnum_subreg(struct tnum a);
 /* Returns the tnum with the lower 32-bit subreg cleared */
 struct tnum tnum_clear_subreg(struct tnum a);
+/* Returns the tnum with the lower 32-bit subreg in *reg* set to the lower
+ * 32-bit subreg in *subreg*
+ */
+struct tnum tnum_with_subreg(struct tnum reg, struct tnum subreg);
 /* Returns the tnum with the lower 32-bit subreg set to value */
 struct tnum tnum_const_subreg(struct tnum a, u32 value);
 /* Returns true if 32-bit subreg @a is a known constant*/
diff --git a/include/linux/torture.h b/include/linux/torture.h
index c98d0c83d117..1541454da03e 100644
--- a/include/linux/torture.h
+++ b/include/linux/torture.h
@@ -21,6 +21,7 @@
 #include <linux/debugobjects.h>
 #include <linux/bug.h>
 #include <linux/compiler.h>
+#include <linux/hrtimer.h>
 
 /* Definitions for a non-string torture-test module parameter. */
 #define torture_param(type, name, init, msg) \
diff --git a/include/linux/types.h b/include/linux/types.h
index 253168bb3fe1..2bc8766ba20c 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -120,6 +120,9 @@ typedef s64			int64_t;
 #define aligned_be64		__aligned_be64
 #define aligned_le64		__aligned_le64
 
+/* Nanosecond scalar representation for kernel time values */
+typedef s64	ktime_t;
+
 /**
  * The type used for indexing onto a disc or disc partition.
  *
diff --git a/include/linux/uidgid.h b/include/linux/uidgid.h
index b0542cd11aeb..f85ec5613721 100644
--- a/include/linux/uidgid.h
+++ b/include/linux/uidgid.h
@@ -12,20 +12,12 @@
  * to detect when we overlook these differences.
  *
  */
-#include <linux/types.h>
+#include <linux/uidgid_types.h>
 #include <linux/highuid.h>
 
 struct user_namespace;
 extern struct user_namespace init_user_ns;
-
-typedef struct {
-	uid_t val;
-} kuid_t;
-
-
-typedef struct {
-	gid_t val;
-} kgid_t;
+struct uid_gid_map;
 
 #define KUIDT_INIT(value) (kuid_t){ value }
 #define KGIDT_INIT(value) (kgid_t){ value }
@@ -138,6 +130,9 @@ static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid)
 	return from_kgid(ns, gid) != (gid_t) -1;
 }
 
+u32 map_id_down(struct uid_gid_map *map, u32 id);
+u32 map_id_up(struct uid_gid_map *map, u32 id);
+
 #else
 
 static inline kuid_t make_kuid(struct user_namespace *from, uid_t uid)
@@ -186,6 +181,15 @@ static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid)
 	return gid_valid(gid);
 }
 
+static inline u32 map_id_down(struct uid_gid_map *map, u32 id)
+{
+	return id;
+}
+
+static inline u32 map_id_up(struct uid_gid_map *map, u32 id)
+{
+	return id;
+}
 #endif /* CONFIG_USER_NS */
 
 #endif /* _LINUX_UIDGID_H */
diff --git a/include/linux/uidgid_types.h b/include/linux/uidgid_types.h
new file mode 100644
index 000000000000..b35ac4955a33
--- /dev/null
+++ b/include/linux/uidgid_types.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_UIDGID_TYPES_H
+#define _LINUX_UIDGID_TYPES_H
+
+#include <linux/types.h>
+
+typedef struct {
+	uid_t val;
+} kuid_t;
+
+typedef struct {
+	gid_t val;
+} kgid_t;
+
+#endif /* _LINUX_UIDGID_TYPES_H */
diff --git a/include/linux/uio.h b/include/linux/uio.h
index b6214cbf2a43..bea9c89922d9 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -347,8 +347,6 @@ ssize_t import_iovec(int type, const struct iovec __user *uvec,
 ssize_t __import_iovec(int type, const struct iovec __user *uvec,
 		 unsigned nr_segs, unsigned fast_segs, struct iovec **iovp,
 		 struct iov_iter *i, bool compat);
-int import_single_range(int type, void __user *buf, size_t len,
-		 struct iovec *iov, struct iov_iter *i);
 int import_ubuf(int type, void __user *buf, size_t len, struct iov_iter *i);
 
 static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction,
diff --git a/include/linux/units.h b/include/linux/units.h
index ff1bd6b5f5b3..45110daaf8d3 100644
--- a/include/linux/units.h
+++ b/include/linux/units.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_UNITS_H
 #define _LINUX_UNITS_H
 
+#include <linux/bits.h>
 #include <linux/math.h>
 
 /* Metric prefixes in accordance with Système international (d'unités) */
diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h
index b513749582d7..e4de6bc1f69b 100644
--- a/include/linux/usb/phy.h
+++ b/include/linux/usb/phy.h
@@ -144,10 +144,6 @@ struct usb_phy {
 	 */
 	int	(*set_wakeup)(struct usb_phy *x, bool enabled);
 
-	/* notify phy port status change */
-	int	(*notify_port_status)(struct usb_phy *x, int port,
-				      u16 portstatus, u16 portchange);
-
 	/* notify phy connect status change */
 	int	(*notify_connect)(struct usb_phy *x,
 			enum usb_device_speed speed);
@@ -321,15 +317,6 @@ usb_phy_set_wakeup(struct usb_phy *x, bool enabled)
 }
 
 static inline int
-usb_phy_notify_port_status(struct usb_phy *x, int port, u16 portstatus, u16 portchange)
-{
-	if (x && x->notify_port_status)
-		return x->notify_port_status(x, port, portstatus, portchange);
-	else
-		return 0;
-}
-
-static inline int
 usb_phy_notify_connect(struct usb_phy *x, enum usb_device_speed speed)
 {
 	if (x && x->notify_connect)
diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h
index 287e9d83fb8b..33a4c146dc19 100644
--- a/include/linux/usb/r8152.h
+++ b/include/linux/usb/r8152.h
@@ -30,6 +30,7 @@
 #define VENDOR_ID_NVIDIA		0x0955
 #define VENDOR_ID_TPLINK		0x2357
 #define VENDOR_ID_DLINK			0x2001
+#define VENDOR_ID_ASUS			0x0b05
 
 #if IS_REACHABLE(CONFIG_USB_RTL8152)
 extern u8 rtl8152_get_version(struct usb_interface *intf);
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index f2dc19f40d05..e4056547fbe6 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -93,6 +93,17 @@ extern int mwriteprotect_range(struct mm_struct *dst_mm,
 extern long uffd_wp_range(struct vm_area_struct *vma,
 			  unsigned long start, unsigned long len, bool enable_wp);
 
+/* move_pages */
+void double_pt_lock(spinlock_t *ptl1, spinlock_t *ptl2);
+void double_pt_unlock(spinlock_t *ptl1, spinlock_t *ptl2);
+ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
+		   unsigned long dst_start, unsigned long src_start,
+		   unsigned long len, __u64 flags);
+int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval,
+			struct vm_area_struct *dst_vma,
+			struct vm_area_struct *src_vma,
+			unsigned long dst_addr, unsigned long src_addr);
+
 /* mm helpers */
 static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,
 					struct vm_userfaultfd_ctx vm_ctx)
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 454e9295970c..a65b2513f8cd 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -289,16 +289,12 @@ void vfio_combine_iova_ranges(struct rb_root_cached *root, u32 cur_nodes,
 /*
  * External user API
  */
-#if IS_ENABLED(CONFIG_VFIO_GROUP)
 struct iommu_group *vfio_file_iommu_group(struct file *file);
+
+#if IS_ENABLED(CONFIG_VFIO_GROUP)
 bool vfio_file_is_group(struct file *file);
 bool vfio_file_has_dev(struct file *file, struct vfio_device *device);
 #else
-static inline struct iommu_group *vfio_file_iommu_group(struct file *file)
-{
-	return NULL;
-}
-
 static inline bool vfio_file_is_group(struct file *file)
 {
 	return false;
diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h
index d0f2797420f7..a09e13a577a9 100644
--- a/include/linux/virtio_pci_modern.h
+++ b/include/linux/virtio_pci_modern.h
@@ -5,13 +5,6 @@
 #include <linux/pci.h>
 #include <linux/virtio_pci.h>
 
-struct virtio_pci_modern_common_cfg {
-	struct virtio_pci_common_cfg cfg;
-
-	__le16 queue_notify_data;	/* read-write */
-	__le16 queue_reset;		/* read-write */
-};
-
 /**
  * struct virtio_pci_modern_device - info for modern PCI virtio
  * @pci_dev:	    Ptr to the PCI device struct
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index ebb3ce63d64d..c82089dee0c8 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -256,4 +256,5 @@ void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit);
 void virtio_transport_deliver_tap_pkt(struct sk_buff *skb);
 int virtio_transport_purge_skbs(void *vsk, struct sk_buff_head *list);
 int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t read_actor);
+int virtio_transport_notify_set_rcvlowat(struct vsock_sock *vsk, int val);
 #endif /* _LINUX_VIRTIO_VSOCK_H */
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 8abfa1240040..747943bc8cc2 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -41,9 +41,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		PGSTEAL_KSWAPD,
 		PGSTEAL_DIRECT,
 		PGSTEAL_KHUGEPAGED,
-		PGDEMOTE_KSWAPD,
-		PGDEMOTE_DIRECT,
-		PGDEMOTE_KHUGEPAGED,
 		PGSCAN_KSWAPD,
 		PGSCAN_DIRECT,
 		PGSCAN_KHUGEPAGED,
@@ -145,6 +142,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #ifdef CONFIG_ZSWAP
 		ZSWPIN,
 		ZSWPOUT,
+		ZSWPWB,
 #endif
 #ifdef CONFIG_X86
 		DIRECT_MAP_LEVEL2_SPLIT,
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index fed855bae6d8..343906a98d6e 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -556,19 +556,25 @@ static inline void mod_lruvec_state(struct lruvec *lruvec,
 	local_irq_restore(flags);
 }
 
-void __mod_lruvec_page_state(struct page *page,
+void __lruvec_stat_mod_folio(struct folio *folio,
 			     enum node_stat_item idx, int val);
 
-static inline void mod_lruvec_page_state(struct page *page,
+static inline void lruvec_stat_mod_folio(struct folio *folio,
 					 enum node_stat_item idx, int val)
 {
 	unsigned long flags;
 
 	local_irq_save(flags);
-	__mod_lruvec_page_state(page, idx, val);
+	__lruvec_stat_mod_folio(folio, idx, val);
 	local_irq_restore(flags);
 }
 
+static inline void mod_lruvec_page_state(struct page *page,
+					 enum node_stat_item idx, int val)
+{
+	lruvec_stat_mod_folio(page_folio(page), idx, val);
+}
+
 #else
 
 static inline void __mod_lruvec_state(struct lruvec *lruvec,
@@ -583,37 +589,25 @@ static inline void mod_lruvec_state(struct lruvec *lruvec,
 	mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
 }
 
-static inline void __mod_lruvec_page_state(struct page *page,
-					   enum node_stat_item idx, int val)
-{
-	__mod_node_page_state(page_pgdat(page), idx, val);
-}
-
-static inline void mod_lruvec_page_state(struct page *page,
+static inline void __lruvec_stat_mod_folio(struct folio *folio,
 					 enum node_stat_item idx, int val)
 {
-	mod_node_page_state(page_pgdat(page), idx, val);
+	__mod_node_page_state(folio_pgdat(folio), idx, val);
 }
 
-#endif /* CONFIG_MEMCG */
-
-static inline void __inc_lruvec_page_state(struct page *page,
-					   enum node_stat_item idx)
+static inline void lruvec_stat_mod_folio(struct folio *folio,
+					 enum node_stat_item idx, int val)
 {
-	__mod_lruvec_page_state(page, idx, 1);
+	mod_node_page_state(folio_pgdat(folio), idx, val);
 }
 
-static inline void __dec_lruvec_page_state(struct page *page,
-					   enum node_stat_item idx)
+static inline void mod_lruvec_page_state(struct page *page,
+					 enum node_stat_item idx, int val)
 {
-	__mod_lruvec_page_state(page, idx, -1);
+	mod_node_page_state(page_pgdat(page), idx, val);
 }
 
-static inline void __lruvec_stat_mod_folio(struct folio *folio,
-					   enum node_stat_item idx, int val)
-{
-	__mod_lruvec_page_state(&folio->page, idx, val);
-}
+#endif /* CONFIG_MEMCG */
 
 static inline void __lruvec_stat_add_folio(struct folio *folio,
 					   enum node_stat_item idx)
@@ -627,24 +621,6 @@ static inline void __lruvec_stat_sub_folio(struct folio *folio,
 	__lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio));
 }
 
-static inline void inc_lruvec_page_state(struct page *page,
-					 enum node_stat_item idx)
-{
-	mod_lruvec_page_state(page, idx, 1);
-}
-
-static inline void dec_lruvec_page_state(struct page *page,
-					 enum node_stat_item idx)
-{
-	mod_lruvec_page_state(page, idx, -1);
-}
-
-static inline void lruvec_stat_mod_folio(struct folio *folio,
-					 enum node_stat_item idx, int val)
-{
-	mod_lruvec_page_state(&folio->page, idx, val);
-}
-
 static inline void lruvec_stat_add_folio(struct folio *folio,
 					 enum node_stat_item idx)
 {
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 3473b663176f..8aa3372f21a0 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -9,7 +9,6 @@
 #include <linux/spinlock.h>
 
 #include <asm/current.h>
-#include <uapi/linux/wait.h>
 
 typedef struct wait_queue_entry wait_queue_entry_t;
 
diff --git a/include/linux/wmi.h b/include/linux/wmi.h
index 763bd382cf2d..686291b87852 100644
--- a/include/linux/wmi.h
+++ b/include/linux/wmi.h
@@ -11,7 +11,6 @@
 #include <linux/device.h>
 #include <linux/acpi.h>
 #include <linux/mod_devicetable.h>
-#include <uapi/linux/wmi.h>
 
 /**
  * struct wmi_device - WMI device structure
@@ -22,11 +21,17 @@
  */
 struct wmi_device {
 	struct device dev;
-
-	/* private: used by the WMI driver core */
 	bool setable;
 };
 
+/**
+ * to_wmi_device() - Helper macro to cast a device to a wmi_device
+ * @device: device struct
+ *
+ * Cast a struct device to a struct wmi_device.
+ */
+#define to_wmi_device(device)	container_of(device, struct wmi_device, dev)
+
 extern acpi_status wmidev_evaluate_method(struct wmi_device *wdev,
 					  u8 instance, u32 method_id,
 					  const struct acpi_buffer *in,
@@ -35,9 +40,9 @@ extern acpi_status wmidev_evaluate_method(struct wmi_device *wdev,
 extern union acpi_object *wmidev_block_query(struct wmi_device *wdev,
 					     u8 instance);
 
-u8 wmidev_instance_count(struct wmi_device *wdev);
+acpi_status wmidev_block_set(struct wmi_device *wdev, u8 instance, const struct acpi_buffer *in);
 
-extern int set_required_buffer_size(struct wmi_device *wdev, u64 length);
+u8 wmidev_instance_count(struct wmi_device *wdev);
 
 /**
  * struct wmi_driver - WMI driver structure
@@ -47,11 +52,8 @@ extern int set_required_buffer_size(struct wmi_device *wdev, u64 length);
  * @probe: Callback for device binding
  * @remove: Callback for device unbinding
  * @notify: Callback for receiving WMI events
- * @filter_callback: Callback for filtering device IOCTLs
  *
  * This represents WMI drivers which handle WMI devices.
- * @filter_callback is only necessary for drivers which
- * want to set up a WMI IOCTL interface.
  */
 struct wmi_driver {
 	struct device_driver driver;
@@ -61,8 +63,6 @@ struct wmi_driver {
 	int (*probe)(struct wmi_device *wdev, const void *context);
 	void (*remove)(struct wmi_device *wdev);
 	void (*notify)(struct wmi_device *device, union acpi_object *data);
-	long (*filter_callback)(struct wmi_device *wdev, unsigned int cmd,
-				struct wmi_ioctl_buffer *arg);
 };
 
 extern int __must_check __wmi_driver_register(struct wmi_driver *driver,
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 24b1e5070f4d..2cc0a9606175 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -14,12 +14,7 @@
 #include <linux/atomic.h>
 #include <linux/cpumask.h>
 #include <linux/rcupdate.h>
-
-struct workqueue_struct;
-
-struct work_struct;
-typedef void (*work_func_t)(struct work_struct *work);
-void delayed_work_timer_fn(struct timer_list *t);
+#include <linux/workqueue_types.h>
 
 /*
  * The first word is the work queue pointer and the flags rolled into
@@ -95,15 +90,6 @@ enum {
 #define WORK_STRUCT_FLAG_MASK    ((1ul << WORK_STRUCT_FLAG_BITS) - 1)
 #define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK)
 
-struct work_struct {
-	atomic_long_t data;
-	struct list_head entry;
-	work_func_t func;
-#ifdef CONFIG_LOCKDEP
-	struct lockdep_map lockdep_map;
-#endif
-};
-
 #define WORK_DATA_INIT()	ATOMIC_LONG_INIT((unsigned long)WORK_STRUCT_NO_POOL)
 #define WORK_DATA_STATIC_INIT()	\
 	ATOMIC_LONG_INIT((unsigned long)(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC))
@@ -491,7 +477,7 @@ struct workqueue_attrs *alloc_workqueue_attrs(void);
 void free_workqueue_attrs(struct workqueue_attrs *attrs);
 int apply_workqueue_attrs(struct workqueue_struct *wq,
 			  const struct workqueue_attrs *attrs);
-int workqueue_set_unbound_cpumask(cpumask_var_t cpumask);
+extern int workqueue_unbound_exclude_cpumask(cpumask_var_t cpumask);
 
 extern bool queue_work_on(int cpu, struct workqueue_struct *wq,
 			struct work_struct *work);
diff --git a/include/linux/workqueue_types.h b/include/linux/workqueue_types.h
new file mode 100644
index 000000000000..4c38824f3ab4
--- /dev/null
+++ b/include/linux/workqueue_types.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_WORKQUEUE_TYPES_H
+#define _LINUX_WORKQUEUE_TYPES_H
+
+#include <linux/atomic.h>
+#include <linux/lockdep_types.h>
+#include <linux/timer_types.h>
+#include <linux/types.h>
+
+struct workqueue_struct;
+
+struct work_struct;
+typedef void (*work_func_t)(struct work_struct *work);
+void delayed_work_timer_fn(struct timer_list *t);
+
+struct work_struct {
+	atomic_long_t data;
+	struct list_head entry;
+	work_func_t func;
+#ifdef CONFIG_LOCKDEP
+	struct lockdep_map lockdep_map;
+#endif
+};
+
+#endif /* _LINUX_WORKQUEUE_TYPES_H */
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 083387c00f0c..6d0a14f7019d 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -193,7 +193,6 @@ void inode_io_list_del(struct inode *inode);
 /* writeback.h requires fs.h; it, too, is not included from here. */
 static inline void wait_on_inode(struct inode *inode)
 {
-	might_sleep();
 	wait_on_bit(&inode->i_state, __I_NEW, TASK_UNINTERRUPTIBLE);
 }
 
diff --git a/include/linux/zswap.h b/include/linux/zswap.h
index 2a60ce39cfde..0b709f5bc65f 100644
--- a/include/linux/zswap.h
+++ b/include/linux/zswap.h
@@ -5,19 +5,41 @@
 #include <linux/types.h>
 #include <linux/mm_types.h>
 
+struct lruvec;
+
 extern u64 zswap_pool_total_size;
 extern atomic_t zswap_stored_pages;
 
 #ifdef CONFIG_ZSWAP
 
+struct zswap_lruvec_state {
+	/*
+	 * Number of pages in zswap that should be protected from the shrinker.
+	 * This number is an estimate of the following counts:
+	 *
+	 * a) Recent page faults.
+	 * b) Recent insertion to the zswap LRU. This includes new zswap stores,
+	 *    as well as recent zswap LRU rotations.
+	 *
+	 * These pages are likely to be warm, and might incur IO if the are written
+	 * to swap.
+	 */
+	atomic_long_t nr_zswap_protected;
+};
+
 bool zswap_store(struct folio *folio);
 bool zswap_load(struct folio *folio);
 void zswap_invalidate(int type, pgoff_t offset);
 void zswap_swapon(int type);
 void zswap_swapoff(int type);
-
+void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg);
+void zswap_lruvec_state_init(struct lruvec *lruvec);
+void zswap_folio_swapin(struct folio *folio);
+bool is_zswap_enabled(void);
 #else
 
+struct zswap_lruvec_state {};
+
 static inline bool zswap_store(struct folio *folio)
 {
 	return false;
@@ -31,6 +53,14 @@ static inline bool zswap_load(struct folio *folio)
 static inline void zswap_invalidate(int type, pgoff_t offset) {}
 static inline void zswap_swapon(int type) {}
 static inline void zswap_swapoff(int type) {}
+static inline void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) {}
+static inline void zswap_lruvec_state_init(struct lruvec *lruvec) {}
+static inline void zswap_folio_swapin(struct folio *folio) {}
+
+static inline bool is_zswap_enabled(void)
+{
+	return false;
+}
 
 #endif
 
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 4ae0580b63ca..e1e5e72b901e 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -137,6 +137,7 @@ struct tc_action_ops {
 
 #ifdef CONFIG_NET_CLS_ACT
 
+#define ACT_P_BOUND 0
 #define ACT_P_CREATED 1
 #define ACT_P_DELETED 1
 
@@ -191,7 +192,7 @@ int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index,
 			      struct nlattr *est, struct tc_action **a,
 			      const struct tc_action_ops *ops, int bind,
 			      u32 flags);
-void tcf_idr_insert_many(struct tc_action *actions[]);
+void tcf_idr_insert_many(struct tc_action *actions[], int init_res[]);
 void tcf_idr_cleanup(struct tc_action_net *tn, u32 index);
 int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
 			struct tc_action **a, int bind);
@@ -207,8 +208,7 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 		    struct nlattr *est,
 		    struct tc_action *actions[], int init_res[], size_t *attr_size,
 		    u32 flags, u32 fl_flags, struct netlink_ext_ack *extack);
-struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, bool police,
-					 bool rtnl_held,
+struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, u32 flags,
 					 struct netlink_ext_ack *extack);
 struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 				    struct nlattr *nla, struct nlattr *est,
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 82da55101b5a..61ebe723ee4d 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -31,17 +31,22 @@ struct prefix_info {
 	__u8			length;
 	__u8			prefix_len;
 
+	union __packed {
+		__u8		flags;
+		struct __packed {
 #if defined(__BIG_ENDIAN_BITFIELD)
-	__u8			onlink : 1,
+			__u8	onlink : 1,
 			 	autoconf : 1,
 				reserved : 6;
 #elif defined(__LITTLE_ENDIAN_BITFIELD)
-	__u8			reserved : 6,
+			__u8	reserved : 6,
 				autoconf : 1,
 				onlink : 1;
 #else
 #error "Please fix <asm/byteorder.h>"
 #endif
+		};
+	};
 	__be32			valid;
 	__be32			prefered;
 	__be32			reserved2;
@@ -49,6 +54,9 @@ struct prefix_info {
 	struct in6_addr		prefix;
 };
 
+/* rfc4861 4.6.2: IPv6 PIO is 32 bytes in size */
+static_assert(sizeof(struct prefix_info) == 32);
+
 #include <linux/ipv6.h>
 #include <linux/netdevice.h>
 #include <net/if_inet6.h>
diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index 5531dd08061e..0754c463224a 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -15,6 +15,7 @@ struct key;
 struct sock;
 struct socket;
 struct rxrpc_call;
+struct rxrpc_peer;
 enum rxrpc_abort_reason;
 
 enum rxrpc_interruptibility {
@@ -41,13 +42,14 @@ void rxrpc_kernel_new_call_notification(struct socket *,
 					rxrpc_notify_new_call_t,
 					rxrpc_discard_new_call_t);
 struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
-					   struct sockaddr_rxrpc *srx,
+					   struct rxrpc_peer *peer,
 					   struct key *key,
 					   unsigned long user_call_ID,
 					   s64 tx_total_len,
 					   u32 hard_timeout,
 					   gfp_t gfp,
 					   rxrpc_notify_rx_t notify_rx,
+					   u16 service_id,
 					   bool upgrade,
 					   enum rxrpc_interruptibility interruptibility,
 					   unsigned int debug_id);
@@ -60,9 +62,14 @@ bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *,
 			     u32, int, enum rxrpc_abort_reason);
 void rxrpc_kernel_shutdown_call(struct socket *sock, struct rxrpc_call *call);
 void rxrpc_kernel_put_call(struct socket *sock, struct rxrpc_call *call);
-void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *,
-			   struct sockaddr_rxrpc *);
-bool rxrpc_kernel_get_srtt(struct socket *, struct rxrpc_call *, u32 *);
+struct rxrpc_peer *rxrpc_kernel_lookup_peer(struct socket *sock,
+					    struct sockaddr_rxrpc *srx, gfp_t gfp);
+void rxrpc_kernel_put_peer(struct rxrpc_peer *peer);
+struct rxrpc_peer *rxrpc_kernel_get_peer(struct rxrpc_peer *peer);
+struct rxrpc_peer *rxrpc_kernel_get_call_peer(struct socket *sock, struct rxrpc_call *call);
+const struct sockaddr_rxrpc *rxrpc_kernel_remote_srx(const struct rxrpc_peer *peer);
+const struct sockaddr *rxrpc_kernel_remote_addr(const struct rxrpc_peer *peer);
+unsigned int rxrpc_kernel_get_srtt(const struct rxrpc_peer *);
 int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t,
 			       rxrpc_user_attach_call_t, unsigned long, gfp_t,
 			       unsigned int);
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 824c258143a3..49c4640027d8 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -75,6 +75,7 @@ struct unix_sock {
 };
 
 #define unix_sk(ptr) container_of_const(ptr, struct unix_sock, sk)
+#define unix_peer(sk) (unix_sk(sk)->peer)
 
 #define peer_wait peer_wq.wait
 
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index e302c0e804d0..535701efc1e5 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -137,7 +137,6 @@ struct vsock_transport {
 	u64 (*stream_rcvhiwat)(struct vsock_sock *);
 	bool (*stream_is_active)(struct vsock_sock *);
 	bool (*stream_allow)(u32 cid, u32 port);
-	int (*set_rcvlowat)(struct vsock_sock *vsk, int val);
 
 	/* SEQ_PACKET. */
 	ssize_t (*seqpacket_dequeue)(struct vsock_sock *vsk, struct msghdr *msg,
@@ -168,6 +167,7 @@ struct vsock_transport {
 		struct vsock_transport_send_notify_data *);
 	/* sk_lock held by the caller */
 	void (*notify_buffer_size)(struct vsock_sock *, u64 *);
+	int (*notify_set_rcvlowat)(struct vsock_sock *vsk, int val);
 
 	/* Shutdown. */
 	int (*shutdown)(struct vsock_sock *, int);
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 20988623c5cc..8f8dd9173714 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -189,6 +189,7 @@ struct blocked_key {
 struct smp_csrk {
 	bdaddr_t bdaddr;
 	u8 bdaddr_type;
+	u8 link_type;
 	u8 type;
 	u8 val[16];
 };
@@ -198,6 +199,7 @@ struct smp_ltk {
 	struct rcu_head rcu;
 	bdaddr_t bdaddr;
 	u8 bdaddr_type;
+	u8 link_type;
 	u8 authenticated;
 	u8 type;
 	u8 enc_size;
@@ -212,6 +214,7 @@ struct smp_irk {
 	bdaddr_t rpa;
 	bdaddr_t bdaddr;
 	u8 addr_type;
+	u8 link_type;
 	u8 val[16];
 };
 
@@ -219,6 +222,8 @@ struct link_key {
 	struct list_head list;
 	struct rcu_head rcu;
 	bdaddr_t bdaddr;
+	u8 bdaddr_type;
+	u8 link_type;
 	u8 type;
 	u8 val[HCI_LINK_KEY_SIZE];
 	u8 pin_len;
@@ -534,7 +539,6 @@ struct hci_dev {
 	struct work_struct	tx_work;
 
 	struct delayed_work	le_scan_disable;
-	struct delayed_work	le_scan_restart;
 
 	struct sk_buff_head	rx_q;
 	struct sk_buff_head	raw_q;
@@ -952,7 +956,6 @@ void hci_inquiry_cache_flush(struct hci_dev *hdev);
 /* ----- HCI Connections ----- */
 enum {
 	HCI_CONN_AUTH_PEND,
-	HCI_CONN_REAUTH_PEND,
 	HCI_CONN_ENCRYPT_PEND,
 	HCI_CONN_RSWITCH_PEND,
 	HCI_CONN_MODE_CHANGE_PEND,
@@ -1227,11 +1230,11 @@ static inline struct hci_conn *hci_conn_hash_lookup_cis(struct hci_dev *hdev,
 			continue;
 
 		/* Match CIG ID if set */
-		if (cig != BT_ISO_QOS_CIG_UNSET && cig != c->iso_qos.ucast.cig)
+		if (cig != c->iso_qos.ucast.cig)
 			continue;
 
 		/* Match CIS ID if set */
-		if (id != BT_ISO_QOS_CIS_UNSET && id != c->iso_qos.ucast.cis)
+		if (id != c->iso_qos.ucast.cis)
 			continue;
 
 		/* Match destination address if set */
@@ -1293,6 +1296,30 @@ static inline struct hci_conn *hci_conn_hash_lookup_big(struct hci_dev *hdev,
 }
 
 static inline struct hci_conn *
+hci_conn_hash_lookup_big_state(struct hci_dev *hdev, __u8 handle,  __u16 state)
+{
+	struct hci_conn_hash *h = &hdev->conn_hash;
+	struct hci_conn  *c;
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(c, &h->list, list) {
+		if (bacmp(&c->dst, BDADDR_ANY) || c->type != ISO_LINK ||
+			c->state != state)
+			continue;
+
+		if (handle == c->iso_qos.bcast.big) {
+			rcu_read_unlock();
+			return c;
+		}
+	}
+
+	rcu_read_unlock();
+
+	return NULL;
+}
+
+static inline struct hci_conn *
 hci_conn_hash_lookup_pa_sync_big_handle(struct hci_dev *hdev, __u8 big)
 {
 	struct hci_conn_hash *h = &hdev->conn_hash;
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index b137a33a1b68..cf79656ce09c 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -52,7 +52,7 @@
  * such wiphy can have zero, one, or many virtual interfaces associated with
  * it, which need to be identified as such by pointing the network interface's
  * @ieee80211_ptr pointer to a &struct wireless_dev which further describes
- * the wireless part of the interface, normally this struct is embedded in the
+ * the wireless part of the interface. Normally this struct is embedded in the
  * network interface's private data area. Drivers can optionally allow creating
  * or destroying virtual interfaces on the fly, but without at least one or the
  * ability to create some the wireless device isn't useful.
@@ -117,6 +117,11 @@ struct wiphy;
  *	This may be due to the driver or due to regulatory bandwidth
  *	restrictions.
  * @IEEE80211_CHAN_NO_EHT: EHT operation is not permitted on this channel.
+ * @IEEE80211_CHAN_DFS_CONCURRENT: See %NL80211_RRF_DFS_CONCURRENT
+ * @IEEE80211_CHAN_NO_UHB_VLP_CLIENT: Client connection with VLP AP
+ *	not permitted using this channel
+ * @IEEE80211_CHAN_NO_UHB_AFC_CLIENT: Client connection with AFC AP
+ *	not permitted using this channel
  */
 enum ieee80211_channel_flags {
 	IEEE80211_CHAN_DISABLED		= 1<<0,
@@ -140,6 +145,9 @@ enum ieee80211_channel_flags {
 	IEEE80211_CHAN_16MHZ		= 1<<18,
 	IEEE80211_CHAN_NO_320MHZ	= 1<<19,
 	IEEE80211_CHAN_NO_EHT		= 1<<20,
+	IEEE80211_CHAN_DFS_CONCURRENT	= 1<<21,
+	IEEE80211_CHAN_NO_UHB_VLP_CLIENT= 1<<22,
+	IEEE80211_CHAN_NO_UHB_AFC_CLIENT= 1<<23,
 };
 
 #define IEEE80211_CHAN_NO_HT40 \
@@ -977,6 +985,15 @@ cfg80211_chandef_compatible(const struct cfg80211_chan_def *chandef1,
 			    const struct cfg80211_chan_def *chandef2);
 
 /**
+ * nl80211_chan_width_to_mhz - get the channel width in MHz
+ * @chan_width: the channel width from &enum nl80211_chan_width
+ *
+ * Return: channel width in MHz if the chan_width from &enum nl80211_chan_width
+ * is valid. -1 otherwise.
+ */
+int nl80211_chan_width_to_mhz(enum nl80211_chan_width chan_width);
+
+/**
  * cfg80211_chandef_valid - check if a channel definition is valid
  * @chandef: the channel definition to check
  * Return: %true if the channel definition is valid. %false otherwise.
@@ -1665,6 +1682,21 @@ struct link_station_del_parameters {
 };
 
 /**
+ * struct cfg80211_ttlm_params: TID to link mapping parameters
+ *
+ * Used for setting a TID to link mapping.
+ *
+ * @dlink: Downlink TID to link mapping, as defined in section 9.4.2.314
+ *     (TID-To-Link Mapping element) in Draft P802.11be_D4.0.
+ * @ulink: Uplink TID to link mapping, as defined in section 9.4.2.314
+ *     (TID-To-Link Mapping element) in Draft P802.11be_D4.0.
+ */
+struct cfg80211_ttlm_params {
+	u16 dlink[8];
+	u16 ulink[8];
+};
+
+/**
  * struct station_parameters - station parameters
  *
  * Used to change and create a new station.
@@ -2560,7 +2592,7 @@ struct cfg80211_scan_info {
  * @short_ssid: short ssid to scan for
  * @bssid: bssid to scan for
  * @channel_idx: idx of the channel in the channel array in the scan request
- *	 which the above info relvant to
+ *	 which the above info is relevant to
  * @unsolicited_probe: the AP transmits unsolicited probe response every 20 TU
  * @short_ssid_valid: @short_ssid is valid and can be used
  * @psc_no_listen: when set, and the channel is a PSC channel, no need to wait
@@ -2608,6 +2640,8 @@ struct cfg80211_scan_6ghz_params {
  * @n_6ghz_params: number of 6 GHz params
  * @scan_6ghz_params: 6 GHz params
  * @bssid: BSSID to scan for (most commonly, the wildcard BSSID)
+ * @tsf_report_link_id: for MLO, indicates the link ID of the BSS that should be
+ *      used for TSF reporting. Can be set to -1 to indicate no preference.
  */
 struct cfg80211_scan_request {
 	struct cfg80211_ssid *ssids;
@@ -2636,6 +2670,7 @@ struct cfg80211_scan_request {
 	bool scan_6ghz;
 	u32 n_6ghz_params;
 	struct cfg80211_scan_6ghz_params *scan_6ghz_params;
+	s8 tsf_report_link_id;
 
 	/* keep last */
 	struct ieee80211_channel *channels[] __counted_by(n_channels);
@@ -2816,6 +2851,13 @@ enum cfg80211_signal_type {
  *	the BSS that requested the scan in which the beacon/probe was received.
  * @chains: bitmask for filled values in @chain_signal.
  * @chain_signal: per-chain signal strength of last received BSS in dBm.
+ * @restrict_use: restrict usage, if not set, assume @use_for is
+ *	%NL80211_BSS_USE_FOR_NORMAL.
+ * @use_for: bitmap of possible usage for this BSS, see
+ *	&enum nl80211_bss_use_for
+ * @cannot_use_reasons: the reasons (bitmap) for not being able to connect,
+ *	if @restrict_use is set and @use_for is zero (empty); may be 0 for
+ *	unspecified reasons; see &enum nl80211_bss_cannot_use_reasons
  * @drv_data: Data to be passed through to @inform_bss
  */
 struct cfg80211_inform_bss {
@@ -2827,6 +2869,9 @@ struct cfg80211_inform_bss {
 	u8 chains;
 	s8 chain_signal[IEEE80211_MAX_CHAINS];
 
+	u8 restrict_use:1, use_for:7;
+	u8 cannot_use_reasons;
+
 	void *drv_data;
 };
 
@@ -2878,6 +2923,11 @@ struct cfg80211_bss_ies {
  * @chain_signal: per-chain signal strength of last received BSS in dBm.
  * @bssid_index: index in the multiple BSS set
  * @max_bssid_indicator: max number of members in the BSS set
+ * @use_for: bitmap of possible usage for this BSS, see
+ *	&enum nl80211_bss_use_for
+ * @cannot_use_reasons: the reasons (bitmap) for not being able to connect,
+ *	if @restrict_use is set and @use_for is zero (empty); may be 0 for
+ *	unspecified reasons; see &enum nl80211_bss_cannot_use_reasons
  * @priv: private area for driver use, has at least wiphy->bss_priv_size bytes
  */
 struct cfg80211_bss {
@@ -2903,6 +2953,9 @@ struct cfg80211_bss {
 	u8 bssid_index;
 	u8 max_bssid_indicator;
 
+	u8 use_for;
+	u8 cannot_use_reasons;
+
 	u8 priv[] __aligned(sizeof(void *));
 };
 
@@ -3180,8 +3233,8 @@ struct cfg80211_ibss_params {
  *
  * @behaviour: requested BSS selection behaviour.
  * @param: parameters for requestion behaviour.
- * @band_pref: preferred band for %NL80211_BSS_SELECT_ATTR_BAND_PREF.
- * @adjust: parameters for %NL80211_BSS_SELECT_ATTR_RSSI_ADJUST.
+ * @param.band_pref: preferred band for %NL80211_BSS_SELECT_ATTR_BAND_PREF.
+ * @param.adjust: parameters for %NL80211_BSS_SELECT_ATTR_RSSI_ADJUST.
  */
 struct cfg80211_bss_selection {
 	enum nl80211_bss_select_attr behaviour;
@@ -4493,6 +4546,7 @@ struct mgmt_frame_regs {
  * @del_link_station: Remove a link of a station.
  *
  * @set_hw_timestamp: Enable/disable HW timestamping of TM/FTM frames.
+ * @set_ttlm: set the TID to link mapping.
  */
 struct cfg80211_ops {
 	int	(*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow);
@@ -4852,6 +4906,8 @@ struct cfg80211_ops {
 				    struct link_station_del_parameters *params);
 	int	(*set_hw_timestamp)(struct wiphy *wiphy, struct net_device *dev,
 				    struct cfg80211_set_hw_timestamp *hwts);
+	int	(*set_ttlm)(struct wiphy *wiphy, struct net_device *dev,
+			    struct cfg80211_ttlm_params *params);
 };
 
 /*
@@ -4910,6 +4966,8 @@ struct cfg80211_ops {
  *	NL80211_REGDOM_SET_BY_DRIVER.
  * @WIPHY_FLAG_CHANNEL_CHANGE_ON_BEACON: reg_call_notifier() is called if driver
  *	set this flag to update channels on beacon hints.
+ * @WIPHY_FLAG_SUPPORTS_NSTR_NONPRIMARY: support connection to non-primary link
+ *	of an NSTR mobile AP MLD.
  */
 enum wiphy_flags {
 	WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK		= BIT(0),
@@ -4923,7 +4981,7 @@ enum wiphy_flags {
 	WIPHY_FLAG_IBSS_RSN			= BIT(8),
 	WIPHY_FLAG_MESH_AUTH			= BIT(10),
 	WIPHY_FLAG_SUPPORTS_EXT_KCK_32          = BIT(11),
-	/* use hole at 12 */
+	WIPHY_FLAG_SUPPORTS_NSTR_NONPRIMARY	= BIT(12),
 	WIPHY_FLAG_SUPPORTS_FW_ROAM		= BIT(13),
 	WIPHY_FLAG_AP_UAPSD			= BIT(14),
 	WIPHY_FLAG_SUPPORTS_TDLS		= BIT(15),
@@ -6013,7 +6071,6 @@ void wiphy_delayed_work_flush(struct wiphy *wiphy,
  *	wireless device if it has no netdev
  * @u: union containing data specific to @iftype
  * @connected: indicates if connected or not (STA mode)
- * @bssid: (private) Used by the internal configuration code
  * @wext: (private) Used by the internal wireless extensions compat code
  * @wext.ibss: (private) IBSS data part of wext handling
  * @wext.connect: (private) connection handling data
@@ -6033,8 +6090,6 @@ void wiphy_delayed_work_flush(struct wiphy *wiphy,
  * @mgmt_registrations: list of registrations for management frames
  * @mgmt_registrations_need_update: mgmt registrations were updated,
  *	need to propagate the update to the driver
- * @beacon_interval: beacon interval used on this device for transmitting
- *	beacons, 0 when not valid
  * @address: The address for this device, valid only if @netdev is %NULL
  * @is_running: true if this is a non-netdev device that has been started, e.g.
  *	the P2P Device.
@@ -7116,6 +7171,23 @@ int cfg80211_get_ies_channel_number(const u8 *ie, size_t ielen,
 				    enum nl80211_band band);
 
 /**
+ * cfg80211_ssid_eq - compare two SSIDs
+ * @a: first SSID
+ * @b: second SSID
+ *
+ * Return: %true if SSIDs are equal, %false otherwise.
+ */
+static inline bool
+cfg80211_ssid_eq(struct cfg80211_ssid *a, struct cfg80211_ssid *b)
+{
+	if (WARN_ON(!a || !b))
+		return false;
+	if (a->ssid_len != b->ssid_len)
+		return false;
+	return memcmp(a->ssid, b->ssid, a->ssid_len) ? false : true;
+}
+
+/**
  * cfg80211_inform_bss_data - inform cfg80211 of a new BSS
  *
  * @wiphy: the wiphy reporting the BSS
@@ -7162,6 +7234,25 @@ cfg80211_inform_bss(struct wiphy *wiphy,
 }
 
 /**
+ * __cfg80211_get_bss - get a BSS reference
+ * @wiphy: the wiphy this BSS struct belongs to
+ * @channel: the channel to search on (or %NULL)
+ * @bssid: the desired BSSID (or %NULL)
+ * @ssid: the desired SSID (or %NULL)
+ * @ssid_len: length of the SSID (or 0)
+ * @bss_type: type of BSS, see &enum ieee80211_bss_type
+ * @privacy: privacy filter, see &enum ieee80211_privacy
+ * @use_for: indicates which use is intended
+ */
+struct cfg80211_bss *__cfg80211_get_bss(struct wiphy *wiphy,
+					struct ieee80211_channel *channel,
+					const u8 *bssid,
+					const u8 *ssid, size_t ssid_len,
+					enum ieee80211_bss_type bss_type,
+					enum ieee80211_privacy privacy,
+					u32 use_for);
+
+/**
  * cfg80211_get_bss - get a BSS reference
  * @wiphy: the wiphy this BSS struct belongs to
  * @channel: the channel to search on (or %NULL)
@@ -7170,13 +7261,20 @@ cfg80211_inform_bss(struct wiphy *wiphy,
  * @ssid_len: length of the SSID (or 0)
  * @bss_type: type of BSS, see &enum ieee80211_bss_type
  * @privacy: privacy filter, see &enum ieee80211_privacy
+ *
+ * This version implies regular usage, %NL80211_BSS_USE_FOR_NORMAL.
  */
-struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy,
-				      struct ieee80211_channel *channel,
-				      const u8 *bssid,
-				      const u8 *ssid, size_t ssid_len,
-				      enum ieee80211_bss_type bss_type,
-				      enum ieee80211_privacy privacy);
+static inline struct cfg80211_bss *
+cfg80211_get_bss(struct wiphy *wiphy, struct ieee80211_channel *channel,
+		 const u8 *bssid, const u8 *ssid, size_t ssid_len,
+		 enum ieee80211_bss_type bss_type,
+		 enum ieee80211_privacy privacy)
+{
+	return __cfg80211_get_bss(wiphy, channel, bssid, ssid, ssid_len,
+				  bss_type, privacy,
+				  NL80211_BSS_USE_FOR_NORMAL);
+}
+
 static inline struct cfg80211_bss *
 cfg80211_get_ibss(struct wiphy *wiphy,
 		  struct ieee80211_channel *channel,
@@ -7270,8 +7368,6 @@ void cfg80211_auth_timeout(struct net_device *dev, const u8 *addr);
 
 /**
  * struct cfg80211_rx_assoc_resp_data - association response data
- * @bss: the BSS that association was requested with, ownership of the pointer
- *	moves to cfg80211 in the call to cfg80211_rx_assoc_resp()
  * @buf: (Re)Association Response frame (header + body)
  * @len: length of the frame data
  * @uapsd_queues: bitmap of queues configured for uapsd. Same format
@@ -7281,6 +7377,8 @@ void cfg80211_auth_timeout(struct net_device *dev, const u8 *addr);
  * @ap_mld_addr: AP MLD address (in case of MLO)
  * @links: per-link information indexed by link ID, use links[0] for
  *	non-MLO connections
+ * @links.bss: the BSS that association was requested with, ownership of the
+ *      pointer moves to cfg80211 in the call to cfg80211_rx_assoc_resp()
  * @links.status: Set this (along with a BSS pointer) for links that
  *	were rejected by the AP.
  */
@@ -7309,7 +7407,7 @@ struct cfg80211_rx_assoc_resp_data {
  * This function may sleep. The caller must hold the corresponding wdev's mutex.
  */
 void cfg80211_rx_assoc_resp(struct net_device *dev,
-			    struct cfg80211_rx_assoc_resp_data *data);
+			    const struct cfg80211_rx_assoc_resp_data *data);
 
 /**
  * struct cfg80211_assoc_failure - association failure data
@@ -7428,7 +7526,7 @@ void cfg80211_notify_new_peer_candidate(struct net_device *dev,
  * RFkill integration in cfg80211 is almost invisible to drivers,
  * as cfg80211 automatically registers an rfkill instance for each
  * wireless device it knows about. Soft kill is also translated
- * into disconnecting and turning all interfaces off, drivers are
+ * into disconnecting and turning all interfaces off. Drivers are
  * expected to turn off the device when all interfaces are down.
  *
  * However, devices may have a hard RFkill line, in which case they
@@ -7476,7 +7574,7 @@ static inline void wiphy_rfkill_stop_polling(struct wiphy *wiphy)
  * the configuration mechanism.
  *
  * A driver supporting vendor commands must register them as an array
- * in struct wiphy, with handlers for each one, each command has an
+ * in struct wiphy, with handlers for each one. Each command has an
  * OUI and sub command ID to identify it.
  *
  * Note that this feature should not be (ab)used to implement protocol
@@ -7640,7 +7738,7 @@ static inline void cfg80211_vendor_event(struct sk_buff *skb, gfp_t gfp)
  * interact with driver-specific tools to aid, for instance,
  * factory programming.
  *
- * This chapter describes how drivers interact with it, for more
+ * This chapter describes how drivers interact with it. For more
  * information see the nl80211 book's chapter on it.
  */
 
@@ -9299,4 +9397,60 @@ bool cfg80211_valid_disable_subchannel_bitmap(u16 *bitmap,
  */
 void cfg80211_links_removed(struct net_device *dev, u16 link_mask);
 
+/**
+ * cfg80211_schedule_channels_check - schedule regulatory check if needed
+ * @wdev: the wireless device to check
+ *
+ * In case the device supports NO_IR or DFS relaxations, schedule regulatory
+ * channels check, as previous concurrent operation conditions may not
+ * hold anymore.
+ */
+void cfg80211_schedule_channels_check(struct wireless_dev *wdev);
+
+#ifdef CONFIG_CFG80211_DEBUGFS
+/**
+ * wiphy_locked_debugfs_read - do a locked read in debugfs
+ * @wiphy: the wiphy to use
+ * @file: the file being read
+ * @buf: the buffer to fill and then read from
+ * @bufsize: size of the buffer
+ * @userbuf: the user buffer to copy to
+ * @count: read count
+ * @ppos: read position
+ * @handler: the read handler to call (under wiphy lock)
+ * @data: additional data to pass to the read handler
+ */
+ssize_t wiphy_locked_debugfs_read(struct wiphy *wiphy, struct file *file,
+				  char *buf, size_t bufsize,
+				  char __user *userbuf, size_t count,
+				  loff_t *ppos,
+				  ssize_t (*handler)(struct wiphy *wiphy,
+						     struct file *file,
+						     char *buf,
+						     size_t bufsize,
+						     void *data),
+				  void *data);
+
+/**
+ * wiphy_locked_debugfs_write - do a locked write in debugfs
+ * @wiphy: the wiphy to use
+ * @file: the file being written to
+ * @buf: the buffer to copy the user data to
+ * @bufsize: size of the buffer
+ * @userbuf: the user buffer to copy from
+ * @count: read count
+ * @handler: the write handler to call (under wiphy lock)
+ * @data: additional data to pass to the write handler
+ */
+ssize_t wiphy_locked_debugfs_write(struct wiphy *wiphy, struct file *file,
+				   char *buf, size_t bufsize,
+				   const char __user *userbuf, size_t count,
+				   ssize_t (*handler)(struct wiphy *wiphy,
+						      struct file *file,
+						      char *buf,
+						      size_t count,
+						      void *data),
+				   void *data);
+#endif
+
 #endif /* __NET_CFG80211_H */
diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index f79ce133e51a..cd95711b12b8 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -20,6 +20,7 @@ struct wpan_phy;
 struct wpan_phy_cca;
 struct cfg802154_scan_request;
 struct cfg802154_beacon_request;
+struct ieee802154_addr;
 
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 struct ieee802154_llsec_device_key;
@@ -77,6 +78,12 @@ struct cfg802154_ops {
 				struct cfg802154_beacon_request *request);
 	int	(*stop_beacons)(struct wpan_phy *wpan_phy,
 				struct wpan_dev *wpan_dev);
+	int	(*associate)(struct wpan_phy *wpan_phy,
+			     struct wpan_dev *wpan_dev,
+			     struct ieee802154_addr *coord);
+	int	(*disassociate)(struct wpan_phy *wpan_phy,
+				struct wpan_dev *wpan_dev,
+				struct ieee802154_addr *target);
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 	void	(*get_llsec_table)(struct wpan_phy *wpan_phy,
 				   struct wpan_dev *wpan_dev,
@@ -304,6 +311,22 @@ struct ieee802154_coord_desc {
 };
 
 /**
+ * struct ieee802154_pan_device - PAN device information
+ * @pan_id: the PAN ID of this device
+ * @mode: the preferred mode to reach the device
+ * @short_addr: the short address of this device
+ * @extended_addr: the extended address of this device
+ * @node: the list node
+ */
+struct ieee802154_pan_device {
+	__le16 pan_id;
+	u8 mode;
+	__le16 short_addr;
+	__le64 extended_addr;
+	struct list_head node;
+};
+
+/**
  * struct cfg802154_scan_request - Scan request
  *
  * @type: type of scan to be performed
@@ -478,6 +501,13 @@ struct wpan_dev {
 
 	/* fallback for acknowledgment bit setting */
 	bool ackreq;
+
+	/* Associations */
+	struct mutex association_lock;
+	struct ieee802154_pan_device *parent;
+	struct list_head children;
+	unsigned int max_associations;
+	unsigned int nchildren;
 };
 
 #define to_phy(_dev)	container_of(_dev, struct wpan_phy, dev)
@@ -529,4 +559,46 @@ static inline const char *wpan_phy_name(struct wpan_phy *phy)
 void ieee802154_configure_durations(struct wpan_phy *phy,
 				    unsigned int page, unsigned int channel);
 
+/**
+ * cfg802154_device_is_associated - Checks whether we are associated to any device
+ * @wpan_dev: the wpan device
+ * @return: true if we are associated
+ */
+bool cfg802154_device_is_associated(struct wpan_dev *wpan_dev);
+
+/**
+ * cfg802154_device_is_parent - Checks if a device is our coordinator
+ * @wpan_dev: the wpan device
+ * @target: the expected parent
+ * @return: true if @target is our coordinator
+ */
+bool cfg802154_device_is_parent(struct wpan_dev *wpan_dev,
+				struct ieee802154_addr *target);
+
+/**
+ * cfg802154_device_is_child - Checks whether a device is associated to us
+ * @wpan_dev: the wpan device
+ * @target: the expected child
+ * @return: the PAN device
+ */
+struct ieee802154_pan_device *
+cfg802154_device_is_child(struct wpan_dev *wpan_dev,
+			  struct ieee802154_addr *target);
+
+/**
+ * cfg802154_set_max_associations - Limit the number of future associations
+ * @wpan_dev: the wpan device
+ * @max: the maximum number of devices we accept to associate
+ * @return: the old maximum value
+ */
+unsigned int cfg802154_set_max_associations(struct wpan_dev *wpan_dev,
+					    unsigned int max);
+
+/**
+ * cfg802154_get_free_short_addr - Get a free address among the known devices
+ * @wpan_dev: the wpan device
+ * @return: a random short address expectedly unused on our PAN
+ */
+__le16 cfg802154_get_free_short_addr(struct wpan_dev *wpan_dev);
+
 #endif /* __NET_CFG802154_H */
diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h
index 3c70ad53a49c..6d3a20163260 100644
--- a/include/net/dropreason-core.h
+++ b/include/net/dropreason-core.h
@@ -85,7 +85,10 @@
 	FN(IPV6_NDISC_BAD_OPTIONS)	\
 	FN(IPV6_NDISC_NS_OTHERHOST)	\
 	FN(QUEUE_PURGE)			\
-	FN(TC_ERROR)			\
+	FN(TC_COOKIE_ERROR)		\
+	FN(PACKET_SOCK_ERROR)		\
+	FN(TC_CHAIN_NOTFOUND)		\
+	FN(TC_RECLASSIFY_LOOP)		\
 	FNe(MAX)
 
 /**
@@ -376,8 +379,23 @@ enum skb_drop_reason {
 	SKB_DROP_REASON_IPV6_NDISC_NS_OTHERHOST,
 	/** @SKB_DROP_REASON_QUEUE_PURGE: bulk free. */
 	SKB_DROP_REASON_QUEUE_PURGE,
-	/** @SKB_DROP_REASON_TC_ERROR: generic internal tc error. */
-	SKB_DROP_REASON_TC_ERROR,
+	/**
+	 * @SKB_DROP_REASON_TC_COOKIE_ERROR: An error occurred whilst
+	 * processing a tc ext cookie.
+	 */
+	SKB_DROP_REASON_TC_COOKIE_ERROR,
+	/**
+	 * @SKB_DROP_REASON_PACKET_SOCK_ERROR: generic packet socket errors
+	 * after its filter matches an incoming packet.
+	 */
+	SKB_DROP_REASON_PACKET_SOCK_ERROR,
+	/** @SKB_DROP_REASON_TC_CHAIN_NOTFOUND: tc chain lookup failed. */
+	SKB_DROP_REASON_TC_CHAIN_NOTFOUND,
+	/**
+	 * @SKB_DROP_REASON_TC_RECLASSIFY_LOOP: tc exceeded max reclassify loop
+	 * iterations.
+	 */
+	SKB_DROP_REASON_TC_RECLASSIFY_LOOP,
 	/**
 	 * @SKB_DROP_REASON_MAX: the maximum of core drop reasons, which
 	 * shouldn't be used as a real 'reason' - only for tracing code gen
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 82da359bca03..d17855c52ef9 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -172,8 +172,7 @@ void fib_rules_unregister(struct fib_rules_ops *);
 
 int fib_rules_lookup(struct fib_rules_ops *, struct flowi *, int flags,
 		     struct fib_lookup_arg *);
-int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table,
-			 u32 flags);
+int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table);
 bool fib_rule_matchall(const struct fib_rule *rule);
 int fib_rules_dump(struct net *net, struct notifier_block *nb, int family,
 		   struct netlink_ext_ack *extack);
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index e18a4c0d69ee..e61469129402 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -8,10 +8,15 @@
 
 #define GENLMSG_DEFAULT_SIZE (NLMSG_DEFAULT_SIZE - GENL_HDRLEN)
 
+/* Binding to multicast group requires %CAP_NET_ADMIN */
+#define GENL_MCAST_CAP_NET_ADMIN	BIT(0)
+/* Binding to multicast group requires %CAP_SYS_ADMIN */
+#define GENL_MCAST_CAP_SYS_ADMIN	BIT(1)
+
 /**
  * struct genl_multicast_group - generic netlink multicast group
  * @name: name of the multicast group, names are per-family
- * @flags: GENL_* flags (%GENL_ADMIN_PERM or %GENL_UNS_ADMIN_PERM)
+ * @flags: GENL_MCAST_* flags
  */
 struct genl_multicast_group {
 	char			name[GENL_NAMSIZ];
@@ -49,6 +54,9 @@ struct genl_info;
  * @split_ops: the split do/dump form of operation definition
  * @n_split_ops: number of entries in @split_ops, not that with split do/dump
  *	ops the number of entries is not the same as number of commands
+ * @sock_priv_size: the size of per-socket private memory
+ * @sock_priv_init: the per-socket private memory initializer
+ * @sock_priv_destroy: the per-socket private memory destructor
  *
  * Attribute policies (the combination of @policy and @maxattr fields)
  * can be attached at the family level or at the operation level.
@@ -82,11 +90,17 @@ struct genl_family {
 	const struct genl_multicast_group *mcgrps;
 	struct module		*module;
 
+	size_t			sock_priv_size;
+	void			(*sock_priv_init)(void *priv);
+	void			(*sock_priv_destroy)(void *priv);
+
 /* private: internal use only */
 	/* protocol family identifier */
 	int			id;
 	/* starting number of multicast group IDs in this family */
 	unsigned int		mcgrp_offset;
+	/* list of per-socket privs */
+	struct xarray		*sock_privs;
 };
 
 /**
@@ -296,6 +310,8 @@ static inline bool genl_info_is_ntf(const struct genl_info *info)
 	return !info->nlhdr;
 }
 
+void *__genl_sk_priv_get(struct genl_family *family, struct sock *sk);
+void *genl_sk_priv_get(struct genl_family *family, struct sock *sk);
 int genl_register_family(struct genl_family *family);
 int genl_unregister_family(const struct genl_family *family);
 void genl_notify(const struct genl_family *family, struct sk_buff *skb,
@@ -436,6 +452,35 @@ static inline void genlmsg_cancel(struct sk_buff *skb, void *hdr)
 }
 
 /**
+ * genlmsg_multicast_netns_filtered - multicast a netlink message
+ *				      to a specific netns with filter
+ *				      function
+ * @family: the generic netlink family
+ * @net: the net namespace
+ * @skb: netlink message as socket buffer
+ * @portid: own netlink portid to avoid sending to yourself
+ * @group: offset of multicast group in groups array
+ * @flags: allocation flags
+ * @filter: filter function
+ * @filter_data: filter function private data
+ *
+ * Return: 0 on success, negative error code for failure.
+ */
+static inline int
+genlmsg_multicast_netns_filtered(const struct genl_family *family,
+				 struct net *net, struct sk_buff *skb,
+				 u32 portid, unsigned int group, gfp_t flags,
+				 netlink_filter_fn filter,
+				 void *filter_data)
+{
+	if (WARN_ON_ONCE(group >= family->n_mcgrps))
+		return -EINVAL;
+	group = family->mcgrp_offset + group;
+	return nlmsg_multicast_filtered(net->genl_sock, skb, portid, group,
+					flags, filter, filter_data);
+}
+
+/**
  * genlmsg_multicast_netns - multicast a netlink message to a specific netns
  * @family: the generic netlink family
  * @net: the net namespace
@@ -448,10 +493,8 @@ static inline int genlmsg_multicast_netns(const struct genl_family *family,
 					  struct net *net, struct sk_buff *skb,
 					  u32 portid, unsigned int group, gfp_t flags)
 {
-	if (WARN_ON_ONCE(group >= family->n_mcgrps))
-		return -EINVAL;
-	group = family->mcgrp_offset + group;
-	return nlmsg_multicast(net->genl_sock, skb, portid, group, flags);
+	return genlmsg_multicast_netns_filtered(family, net, skb, portid,
+						group, flags, NULL, NULL);
 }
 
 /**
diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h
index 063313df447d..4de858f9929e 100644
--- a/include/net/ieee802154_netdev.h
+++ b/include/net/ieee802154_netdev.h
@@ -125,6 +125,35 @@ struct ieee802154_hdr_fc {
 #endif
 };
 
+struct ieee802154_assoc_req_pl {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	u8 reserved1:1,
+	   device_type:1,
+	   power_source:1,
+	   rx_on_when_idle:1,
+	   assoc_type:1,
+	   reserved2:1,
+	   security_cap:1,
+	   alloc_addr:1;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+	u8 alloc_addr:1,
+	   security_cap:1,
+	   reserved2:1,
+	   assoc_type:1,
+	   rx_on_when_idle:1,
+	   power_source:1,
+	   device_type:1,
+	   reserved1:1;
+#else
+#error	"Please fix <asm/byteorder.h>"
+#endif
+} __packed;
+
+struct ieee802154_assoc_resp_pl {
+	__le16 short_addr;
+	u8 status;
+} __packed;
+
 enum ieee802154_frame_version {
 	IEEE802154_2003_STD,
 	IEEE802154_2006_STD,
@@ -140,6 +169,19 @@ enum ieee802154_addressing_mode {
 	IEEE802154_EXTENDED_ADDRESSING,
 };
 
+enum ieee802154_association_status {
+	IEEE802154_ASSOCIATION_SUCCESSFUL = 0x00,
+	IEEE802154_PAN_AT_CAPACITY = 0x01,
+	IEEE802154_PAN_ACCESS_DENIED = 0x02,
+	IEEE802154_HOPPING_SEQUENCE_OFFSET_DUP = 0x03,
+	IEEE802154_FAST_ASSOCIATION_SUCCESSFUL = 0x80,
+};
+
+enum ieee802154_disassociation_reason {
+	IEEE802154_COORD_WISHES_DEVICE_TO_LEAVE = 0x1,
+	IEEE802154_DEVICE_WISHES_TO_LEAVE = 0x2,
+};
+
 struct ieee802154_hdr {
 	struct ieee802154_hdr_fc fc;
 	u8 seq;
@@ -163,6 +205,24 @@ struct ieee802154_beacon_req_frame {
 	struct ieee802154_mac_cmd_pl mac_pl;
 };
 
+struct ieee802154_association_req_frame {
+	struct ieee802154_hdr mhr;
+	struct ieee802154_mac_cmd_pl mac_pl;
+	struct ieee802154_assoc_req_pl assoc_req_pl;
+};
+
+struct ieee802154_association_resp_frame {
+	struct ieee802154_hdr mhr;
+	struct ieee802154_mac_cmd_pl mac_pl;
+	struct ieee802154_assoc_resp_pl assoc_resp_pl;
+};
+
+struct ieee802154_disassociation_notif_frame {
+	struct ieee802154_hdr mhr;
+	struct ieee802154_mac_cmd_pl mac_pl;
+	u8 disassoc_pl;
+};
+
 /* pushes hdr onto the skb. fields of hdr->fc that can be calculated from
  * the contents of hdr will be, and the actual value of those bits in
  * hdr->fc will be ignored. this includes the INTRA_PAN bit and the frame
diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index 3e454c4d7ba6..f07642264c1e 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -22,10 +22,6 @@
 #define IF_RS_SENT	0x10
 #define IF_READY	0x80000000
 
-/* prefix flags */
-#define IF_PREFIX_ONLINK	0x01
-#define IF_PREFIX_AUTOCONF	0x02
-
 enum {
 	INET6_IFADDR_STATE_PREDAD,
 	INET6_IFADDR_STATE_DAD,
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 3ecfeadbfa06..7f1b38458743 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -88,7 +88,7 @@ struct inet_bind_bucket {
 	unsigned short		fast_sk_family;
 	bool			fast_ipv6_only;
 	struct hlist_node	node;
-	struct hlist_head	owners;
+	struct hlist_head	bhash2;
 };
 
 struct inet_bind2_bucket {
@@ -96,22 +96,17 @@ struct inet_bind2_bucket {
 	int			l3mdev;
 	unsigned short		port;
 #if IS_ENABLED(CONFIG_IPV6)
-	unsigned short		family;
-#endif
-	union {
-#if IS_ENABLED(CONFIG_IPV6)
-		struct in6_addr		v6_rcv_saddr;
+	unsigned short		addr_type;
+	struct in6_addr		v6_rcv_saddr;
+#define rcv_saddr		v6_rcv_saddr.s6_addr32[3]
+#else
+	__be32			rcv_saddr;
 #endif
-		__be32			rcv_saddr;
-	};
 	/* Node in the bhash2 inet_bind_hashbucket chain */
 	struct hlist_node	node;
+	struct hlist_node	bhash_node;
 	/* List of sockets hashed to this bucket */
 	struct hlist_head	owners;
-	/* bhash has twsk in owners, but bhash2 has twsk in
-	 * deathrow not to add a member in struct sock_common.
-	 */
-	struct hlist_head	deathrow;
 };
 
 static inline struct net *ib_net(const struct inet_bind_bucket *ib)
@@ -241,7 +236,7 @@ bool inet_bind_bucket_match(const struct inet_bind_bucket *tb,
 struct inet_bind2_bucket *
 inet_bind2_bucket_create(struct kmem_cache *cachep, struct net *net,
 			 struct inet_bind_hashbucket *head,
-			 unsigned short port, int l3mdev,
+			 struct inet_bind_bucket *tb,
 			 const struct sock *sk);
 
 void inet_bind2_bucket_destroy(struct kmem_cache *cachep,
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 74db6d97cae1..aa86453f6b9b 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -234,10 +234,7 @@ struct inet_sock {
 	int			uc_index;
 	int			mc_index;
 	__be32			mc_addr;
-	struct {
-		__u16 lo;
-		__u16 hi;
-	}			local_port_range;
+	u32			local_port_range;	/* high << 16 | low */
 
 	struct ip_mc_socklist __rcu	*mc_list;
 	struct inet_cork_full	cork;
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index b14999ff55db..f28da08a37b4 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -75,13 +75,9 @@ struct inet_timewait_sock {
 	struct timer_list	tw_timer;
 	struct inet_bind_bucket	*tw_tb;
 	struct inet_bind2_bucket	*tw_tb2;
-	struct hlist_node		tw_bind2_node;
 };
 #define tw_tclass tw_tos
 
-#define twsk_for_each_bound_bhash2(__tw, list) \
-	hlist_for_each_entry(__tw, list, tw_bind2_node)
-
 static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk)
 {
 	return (struct inet_timewait_sock *)sk;
diff --git a/include/net/ip.h b/include/net/ip.h
index 1fc4c8d69e33..de0c69c57e3c 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -349,8 +349,14 @@ static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_o
 	} \
 }
 
-void inet_get_local_port_range(const struct net *net, int *low, int *high);
-void inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high);
+static inline void inet_get_local_port_range(const struct net *net, int *low, int *high)
+{
+	u32 range = READ_ONCE(net->ipv4.ip_local_ports.range);
+
+	*low = range & 0xffff;
+	*high = range >> 16;
+}
+bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high);
 
 #ifdef CONFIG_SYSCTL
 static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 1ba9f4ddf2f6..9ba6413fd2e3 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -179,9 +179,6 @@ struct fib6_info {
 
 	refcount_t			fib6_ref;
 	unsigned long			expires;
-
-	struct hlist_node		gc_link;
-
 	struct dst_metrics		*fib6_metrics;
 #define fib6_pmtu		fib6_metrics->metrics[RTAX_MTU-1]
 
@@ -250,6 +247,19 @@ static inline bool fib6_requires_src(const struct fib6_info *rt)
 	return rt->fib6_src.plen > 0;
 }
 
+static inline void fib6_clean_expires(struct fib6_info *f6i)
+{
+	f6i->fib6_flags &= ~RTF_EXPIRES;
+	f6i->expires = 0;
+}
+
+static inline void fib6_set_expires(struct fib6_info *f6i,
+				    unsigned long expires)
+{
+	f6i->expires = expires;
+	f6i->fib6_flags |= RTF_EXPIRES;
+}
+
 static inline bool fib6_check_expired(const struct fib6_info *f6i)
 {
 	if (f6i->fib6_flags & RTF_EXPIRES)
@@ -257,11 +267,6 @@ static inline bool fib6_check_expired(const struct fib6_info *f6i)
 	return false;
 }
 
-static inline bool fib6_has_expires(const struct fib6_info *f6i)
-{
-	return f6i->fib6_flags & RTF_EXPIRES;
-}
-
 /* Function to safely get fn->fn_sernum for passed in rt
  * and store result in passed in cookie.
  * Return true if we can get cookie safely
@@ -383,7 +388,6 @@ struct fib6_table {
 	struct inet_peer_base	tb6_peers;
 	unsigned int		flags;
 	unsigned int		fib_seq;
-	struct hlist_head       tb6_gc_hlist;	/* GC candidates */
 #define RT6_TABLE_HAS_DFLT_ROUTER	BIT(0)
 };
 
@@ -500,48 +504,6 @@ void fib6_gc_cleanup(void);
 
 int fib6_init(void);
 
-/* fib6_info must be locked by the caller, and fib6_info->fib6_table can be
- * NULL.
- */
-static inline void fib6_set_expires_locked(struct fib6_info *f6i,
-					   unsigned long expires)
-{
-	struct fib6_table *tb6;
-
-	tb6 = f6i->fib6_table;
-	f6i->expires = expires;
-	if (tb6 && !fib6_has_expires(f6i))
-		hlist_add_head(&f6i->gc_link, &tb6->tb6_gc_hlist);
-	f6i->fib6_flags |= RTF_EXPIRES;
-}
-
-/* fib6_info must be locked by the caller, and fib6_info->fib6_table can be
- * NULL.  If fib6_table is NULL, the fib6_info will no be inserted into the
- * list of GC candidates until it is inserted into a table.
- */
-static inline void fib6_set_expires(struct fib6_info *f6i,
-				    unsigned long expires)
-{
-	spin_lock_bh(&f6i->fib6_table->tb6_lock);
-	fib6_set_expires_locked(f6i, expires);
-	spin_unlock_bh(&f6i->fib6_table->tb6_lock);
-}
-
-static inline void fib6_clean_expires_locked(struct fib6_info *f6i)
-{
-	if (fib6_has_expires(f6i))
-		hlist_del_init(&f6i->gc_link);
-	f6i->fib6_flags &= ~RTF_EXPIRES;
-	f6i->expires = 0;
-}
-
-static inline void fib6_clean_expires(struct fib6_info *f6i)
-{
-	spin_lock_bh(&f6i->fib6_table->tb6_lock);
-	fib6_clean_expires_locked(f6i);
-	spin_unlock_bh(&f6i->fib6_table->tb6_lock);
-}
-
 struct ipv6_route_iter {
 	struct seq_net_private p;
 	struct fib6_walker w;
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index f346b4efbc30..2d746f4c9a0a 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -416,6 +416,17 @@ static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph,
 		return 0;
 }
 
+static inline __be32 ip_tunnel_get_flowlabel(const struct iphdr *iph,
+					     const struct sk_buff *skb)
+{
+	__be16 payload_protocol = skb_protocol(skb, true);
+
+	if (payload_protocol == htons(ETH_P_IPV6))
+		return ip6_flowlabel((const struct ipv6hdr *)iph);
+	else
+		return 0;
+}
+
 static inline u8 ip_tunnel_get_ttl(const struct iphdr *iph,
 				       const struct sk_buff *skb)
 {
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 78d38dd88aba..cf25ea21d770 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -784,11 +784,6 @@ static inline bool ipv6_addr_v4mapped(const struct in6_addr *a)
 					cpu_to_be32(0x0000ffff))) == 0UL;
 }
 
-static inline bool ipv6_addr_v4mapped_any(const struct in6_addr *a)
-{
-	return ipv6_addr_v4mapped(a) && ipv4_is_zeronet(a->s6_addr32[3]);
-}
-
 static inline bool ipv6_addr_v4mapped_loopback(const struct in6_addr *a)
 {
 	return ipv6_addr_v4mapped(a) && ipv4_is_loopback(a->s6_addr32[3]);
diff --git a/include/net/iucv/iucv.h b/include/net/iucv/iucv.h
index f9e88401d7da..8b2055d64a6b 100644
--- a/include/net/iucv/iucv.h
+++ b/include/net/iucv/iucv.h
@@ -80,7 +80,7 @@ struct iucv_array {
 	u32 length;
 } __attribute__ ((aligned (8)));
 
-extern struct bus_type iucv_bus;
+extern const struct bus_type iucv_bus;
 extern struct device *iucv_root;
 
 /*
@@ -489,7 +489,7 @@ struct iucv_interface {
 	int (*path_sever)(struct iucv_path *path, u8 userdata[16]);
 	int (*iucv_register)(struct iucv_handler *handler, int smp);
 	void (*iucv_unregister)(struct iucv_handler *handler, int smp);
-	struct bus_type *bus;
+	const struct bus_type *bus;
 	struct device *root;
 };
 
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 580781ff9dcf..d400fe2e8668 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -476,9 +476,9 @@ struct ieee80211_ba_event {
 /**
  * struct ieee80211_event - event to be sent to the driver
  * @type: The event itself. See &enum ieee80211_event_type.
- * @rssi: relevant if &type is %RSSI_EVENT
- * @mlme: relevant if &type is %AUTH_EVENT
- * @ba: relevant if &type is %BAR_RX_EVENT or %BA_FRAME_TIMEOUT
+ * @u.rssi: relevant if &type is %RSSI_EVENT
+ * @u.mlme: relevant if &type is %AUTH_EVENT
+ * @u.ba: relevant if &type is %BAR_RX_EVENT or %BA_FRAME_TIMEOUT
  * @u:union holding the fields above
  */
 struct ieee80211_event {
@@ -541,8 +541,6 @@ struct ieee80211_fils_discovery {
  * @link_id: link ID, or 0 for non-MLO
  * @htc_trig_based_pkt_ext: default PE in 4us units, if BSS supports HE
  * @uora_exists: is the UORA element advertised by AP
- * @ack_enabled: indicates support to receive a multi-TID that solicits either
- *	ACK, BACK or both
  * @uora_ocw_range: UORA element's OCW Range field
  * @frame_time_rts_th: HE duration RTS threshold, in units of 32us
  * @he_support: does this BSS support HE
@@ -1150,11 +1148,6 @@ ieee80211_rate_get_vht_nss(const struct ieee80211_tx_rate *rate)
  * @ack: union part for pure ACK data
  * @ack.cookie: cookie for the ACK
  * @driver_data: array of driver_data pointers
- * @ampdu_ack_len: number of acked aggregated frames.
- * 	relevant only if IEEE80211_TX_STAT_AMPDU was set.
- * @ampdu_len: number of aggregated frames.
- * 	relevant only if IEEE80211_TX_STAT_AMPDU was set.
- * @ack_signal: signal strength of the ACK frame
  */
 struct ieee80211_tx_info {
 	/* common information */
@@ -1362,6 +1355,9 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
  *	the frame.
  * @RX_FLAG_FAILED_PLCP_CRC: Set this flag if the PCLP check failed on
  *	the frame.
+ * @RX_FLAG_MACTIME: The timestamp passed in the RX status (@mactime
+ *	field) is valid if this field is non-zero, and the position
+ *	where the timestamp was sampled depends on the value.
  * @RX_FLAG_MACTIME_START: The timestamp passed in the RX status (@mactime
  *	field) is valid and contains the time the first symbol of the MPDU
  *	was received. This is useful in monitor mode and for proper IBSS
@@ -1371,6 +1367,11 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
  *	(including FCS) was received.
  * @RX_FLAG_MACTIME_PLCP_START: The timestamp passed in the RX status (@mactime
  *	field) is valid and contains the time the SYNC preamble was received.
+ * @RX_FLAG_MACTIME_IS_RTAP_TS64: The timestamp passed in the RX status @mactime
+ *	is only for use in the radiotap timestamp header, not otherwise a valid
+ *	@mactime value. Note this is a separate flag so that we continue to see
+ *	%RX_FLAG_MACTIME as unset. Also note that in this case the timestamp is
+ *	reported to be 64 bits wide, not just 32.
  * @RX_FLAG_NO_SIGNAL_VAL: The signal strength value is not present.
  *	Valid only for data frames (mainly A-MPDU)
  * @RX_FLAG_AMPDU_DETAILS: A-MPDU details are known, in particular the reference
@@ -1441,12 +1442,12 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
 enum mac80211_rx_flags {
 	RX_FLAG_MMIC_ERROR		= BIT(0),
 	RX_FLAG_DECRYPTED		= BIT(1),
-	RX_FLAG_MACTIME_PLCP_START	= BIT(2),
+	RX_FLAG_ONLY_MONITOR		= BIT(2),
 	RX_FLAG_MMIC_STRIPPED		= BIT(3),
 	RX_FLAG_IV_STRIPPED		= BIT(4),
 	RX_FLAG_FAILED_FCS_CRC		= BIT(5),
 	RX_FLAG_FAILED_PLCP_CRC 	= BIT(6),
-	RX_FLAG_MACTIME_START		= BIT(7),
+	RX_FLAG_MACTIME_IS_RTAP_TS64	= BIT(7),
 	RX_FLAG_NO_SIGNAL_VAL		= BIT(8),
 	RX_FLAG_AMPDU_DETAILS		= BIT(9),
 	RX_FLAG_PN_VALIDATED		= BIT(10),
@@ -1455,8 +1456,10 @@ enum mac80211_rx_flags {
 	RX_FLAG_AMPDU_IS_LAST		= BIT(13),
 	RX_FLAG_AMPDU_DELIM_CRC_ERROR	= BIT(14),
 	RX_FLAG_AMPDU_DELIM_CRC_KNOWN	= BIT(15),
-	RX_FLAG_MACTIME_END		= BIT(16),
-	RX_FLAG_ONLY_MONITOR		= BIT(17),
+	RX_FLAG_MACTIME			= BIT(16) | BIT(17),
+	RX_FLAG_MACTIME_PLCP_START	= 1 << 16,
+	RX_FLAG_MACTIME_START		= 2 << 16,
+	RX_FLAG_MACTIME_END		= 3 << 16,
 	RX_FLAG_SKIP_MONITOR		= BIT(18),
 	RX_FLAG_AMSDU_MORE		= BIT(19),
 	RX_FLAG_RADIOTAP_TLV_AT_END	= BIT(20),
@@ -2686,6 +2689,9 @@ struct ieee80211_txq {
  * @IEEE80211_HW_MLO_MCAST_MULTI_LINK_TX: Hardware/driver handles transmitting
  *	multicast frames on all links, mac80211 should not do that.
  *
+ * @IEEE80211_HW_DISALLOW_PUNCTURING: HW requires disabling puncturing in EHT
+ *	and connecting with a lower bandwidth instead
+ *
  * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays
  */
 enum ieee80211_hw_flags {
@@ -2743,6 +2749,7 @@ enum ieee80211_hw_flags {
 	IEEE80211_HW_SUPPORTS_CONC_MON_RX_DECAP,
 	IEEE80211_HW_DETECTS_COLOR_COLLISION,
 	IEEE80211_HW_MLO_MCAST_MULTI_LINK_TX,
+	IEEE80211_HW_DISALLOW_PUNCTURING,
 
 	/* keep last, obviously */
 	NUM_IEEE80211_HW_FLAGS
@@ -2831,8 +2838,6 @@ enum ieee80211_hw_flags {
  *	the default is _GI | _BANDWIDTH.
  *	Use the %IEEE80211_RADIOTAP_VHT_KNOWN_\* values.
  *
- * @radiotap_he: HE radiotap validity flags
- *
  * @radiotap_timestamp: Information for the radiotap timestamp field; if the
  *	@units_pos member is set to a non-negative value then the timestamp
  *	field will be added and populated from the &struct ieee80211_rx_status
@@ -4267,6 +4272,8 @@ struct ieee80211_prep_tx_info {
  *	disable background CAC/radar detection.
  * @net_fill_forward_path: Called from .ndo_fill_forward_path in order to
  *	resolve a path for hardware flow offloading
+ * @can_activate_links: Checks if a specific active_links bitmap is
+ *	supported by the driver.
  * @change_vif_links: Change the valid links on an interface, note that while
  *	removing the old link information is still valid (link_conf pointer),
  *	but may immediately disappear after the function returns. The old or
@@ -4647,6 +4654,9 @@ struct ieee80211_ops {
 				     struct ieee80211_sta *sta,
 				     struct net_device_path_ctx *ctx,
 				     struct net_device_path *path);
+	bool (*can_activate_links)(struct ieee80211_hw *hw,
+				   struct ieee80211_vif *vif,
+				   u16 active_links);
 	int (*change_vif_links)(struct ieee80211_hw *hw,
 				struct ieee80211_vif *vif,
 				u16 old_links, u16 new_links,
@@ -5809,12 +5819,11 @@ void ieee80211_set_key_rx_seq(struct ieee80211_key_conf *keyconf,
  * ieee80211_remove_key - remove the given key
  * @keyconf: the parameter passed with the set key
  *
+ * Context: Must be called with the wiphy mutex held.
+ *
  * Remove the given key. If the key was uploaded to the hardware at the
  * time this function is called, it is not deleted in the hardware but
  * instead assumed to have been removed already.
- *
- * Note that due to locking considerations this function can (currently)
- * only be called during key iteration (ieee80211_iter_keys().)
  */
 void ieee80211_remove_key(struct ieee80211_key_conf *keyconf);
 
@@ -6368,12 +6377,12 @@ ieee80211_txq_airtime_check(struct ieee80211_hw *hw, struct ieee80211_txq *txq);
  * @iter: iterator function that will be called for each key
  * @iter_data: custom data to pass to the iterator function
  *
+ * Context: Must be called with wiphy mutex held; can sleep.
+ *
  * This function can be used to iterate all the keys known to
  * mac80211, even those that weren't previously programmed into
  * the device. This is intended for use in WoWLAN if the device
- * needs reprogramming of the keys during suspend. Note that due
- * to locking reasons, it is also only safe to call this at few
- * spots since it must hold the RTNL and be able to sleep.
+ * needs reprogramming of the keys during suspend.
  *
  * The order in which the keys are iterated matches the order
  * in which they were originally installed and handed to the
@@ -7435,6 +7444,9 @@ static inline bool ieee80211_is_tx_data(struct sk_buff *skb)
  * @vif: interface to set active links on
  * @active_links: the new active links bitmap
  *
+ * Context: Must be called with wiphy mutex held; may sleep; calls
+ *	back into the driver.
+ *
  * This changes the active links on an interface. The interface
  * must be in client mode (in AP mode, all links are always active),
  * and @active_links must be a subset of the vif's valid_links.
@@ -7442,6 +7454,7 @@ static inline bool ieee80211_is_tx_data(struct sk_buff *skb)
  * If a link is switched off and another is switched on at the same
  * time (e.g. active_links going from 0x1 to 0x10) then you will get
  * a sequence of calls like
+ *
  *  - change_vif_links(0x11)
  *  - unassign_vif_chanctx(link_id=0)
  *  - change_sta_links(0x11) for each affected STA (the AP)
@@ -7451,10 +7464,6 @@ static inline bool ieee80211_is_tx_data(struct sk_buff *skb)
  *  - change_sta_links(0x10) for each affected STA (the AP)
  *  - assign_vif_chanctx(link_id=4)
  *  - change_vif_links(0x10)
- *
- * Note: This function acquires some mac80211 locks and must not
- *	 be called with any driver locks held that could cause a
- *	 lock dependency inversion. Best call it without locks.
  */
 int ieee80211_set_active_links(struct ieee80211_vif *vif, u16 active_links);
 
diff --git a/include/net/macsec.h b/include/net/macsec.h
index ebf9bc54036a..dbd22180cc5c 100644
--- a/include/net/macsec.h
+++ b/include/net/macsec.h
@@ -247,6 +247,23 @@ struct macsec_secy {
 
 /**
  * struct macsec_context - MACsec context for hardware offloading
+ * @netdev: a valid pointer to a struct net_device if @offload ==
+ *	MACSEC_OFFLOAD_MAC
+ * @phydev: a valid pointer to a struct phy_device if @offload ==
+ *	MACSEC_OFFLOAD_PHY
+ * @offload: MACsec offload status
+ * @secy: pointer to a MACsec SecY
+ * @rx_sc: pointer to a RX SC
+ * @update_pn: when updating the SA, update the next PN
+ * @assoc_num: association number of the target SA
+ * @key: key of the target SA
+ * @rx_sa: pointer to an RX SA if a RX SA is added/updated/removed
+ * @tx_sa: pointer to an TX SA if a TX SA is added/updated/removed
+ * @tx_sc_stats: pointer to TX SC stats structure
+ * @tx_sa_stats: pointer to TX SA stats structure
+ * @rx_sc_stats: pointer to RX SC stats structure
+ * @rx_sa_stats: pointer to RX SA stats structure
+ * @dev_stats: pointer to dev stats structure
  */
 struct macsec_context {
 	union {
@@ -277,6 +294,33 @@ struct macsec_context {
 
 /**
  * struct macsec_ops - MACsec offloading operations
+ * @mdo_dev_open: called when the MACsec interface transitions to the up state
+ * @mdo_dev_stop: called when the MACsec interface transitions to the down
+ *	state
+ * @mdo_add_secy: called when a new SecY is added
+ * @mdo_upd_secy: called when the SecY flags are changed or the MAC address of
+ *	the MACsec interface is changed
+ * @mdo_del_secy: called when the hw offload is disabled or the MACsec
+ *	interface is removed
+ * @mdo_add_rxsc: called when a new RX SC is added
+ * @mdo_upd_rxsc: called when a certain RX SC is updated
+ * @mdo_del_rxsc: called when a certain RX SC is removed
+ * @mdo_add_rxsa: called when a new RX SA is added
+ * @mdo_upd_rxsa: called when a certain RX SA is updated
+ * @mdo_del_rxsa: called when a certain RX SA is removed
+ * @mdo_add_txsa: called when a new TX SA is added
+ * @mdo_upd_txsa: called when a certain TX SA is updated
+ * @mdo_del_txsa: called when a certain TX SA is removed
+ * @mdo_get_dev_stats: called when dev stats are read
+ * @mdo_get_tx_sc_stats: called when TX SC stats are read
+ * @mdo_get_tx_sa_stats: called when TX SA stats are read
+ * @mdo_get_rx_sc_stats: called when RX SC stats are read
+ * @mdo_get_rx_sa_stats: called when RX SA stats are read
+ * @mdo_insert_tx_tag: called to insert the TX tag
+ * @needed_headroom: number of bytes reserved at the beginning of the sk_buff
+ *	for the TX tag
+ * @needed_tailroom: number of bytes reserved at the end of the sk_buff for the
+ *	TX tag
  */
 struct macsec_ops {
 	/* Device wide */
@@ -303,6 +347,11 @@ struct macsec_ops {
 	int (*mdo_get_tx_sa_stats)(struct macsec_context *ctx);
 	int (*mdo_get_rx_sc_stats)(struct macsec_context *ctx);
 	int (*mdo_get_rx_sa_stats)(struct macsec_context *ctx);
+	/* Offload tag */
+	int (*mdo_insert_tx_tag)(struct phy_device *phydev,
+				 struct sk_buff *skb);
+	unsigned int needed_headroom;
+	unsigned int needed_tailroom;
 };
 
 void macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa);
@@ -325,4 +374,9 @@ static inline void *macsec_netdev_priv(const struct net_device *dev)
 	return netdev_priv(dev);
 }
 
+static inline u64 sci_to_cpu(sci_t sci)
+{
+	return be64_to_cpu((__force __be64)sci);
+}
+
 #endif /* _NET_MACSEC_H_ */
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 88b6ef7ce1a6..76f2fd2645b7 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -293,6 +293,7 @@ struct gdma_queue {
 
 	u32 head;
 	u32 tail;
+	struct list_head entry;
 
 	/* Extra fields specific to EQ/CQ. */
 	union {
@@ -328,6 +329,7 @@ struct gdma_queue_spec {
 			void *context;
 
 			unsigned long log2_throttle_limit;
+			unsigned int msix_index;
 		} eq;
 
 		struct {
@@ -344,7 +346,9 @@ struct gdma_queue_spec {
 
 struct gdma_irq_context {
 	void (*handler)(void *arg);
-	void *arg;
+	/* Protect the eq_list */
+	spinlock_t lock;
+	struct list_head eq_list;
 	char name[MANA_IRQ_NAME_SZ];
 };
 
@@ -355,7 +359,6 @@ struct gdma_context {
 	unsigned int		max_num_queues;
 	unsigned int		max_num_msix;
 	unsigned int		num_msix_usable;
-	struct gdma_resource	msix_resource;
 	struct gdma_irq_context	*irq_contexts;
 
 	/* L2 MTU */
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 6e3e9c1363db..76147feb0d10 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -353,6 +353,25 @@ struct mana_tx_qp {
 struct mana_ethtool_stats {
 	u64 stop_queue;
 	u64 wake_queue;
+	u64 hc_rx_discards_no_wqe;
+	u64 hc_rx_err_vport_disabled;
+	u64 hc_rx_bytes;
+	u64 hc_rx_ucast_pkts;
+	u64 hc_rx_ucast_bytes;
+	u64 hc_rx_bcast_pkts;
+	u64 hc_rx_bcast_bytes;
+	u64 hc_rx_mcast_pkts;
+	u64 hc_rx_mcast_bytes;
+	u64 hc_tx_err_gf_disabled;
+	u64 hc_tx_err_vport_disabled;
+	u64 hc_tx_err_inval_vportoffset_pkt;
+	u64 hc_tx_err_vlan_enforcement;
+	u64 hc_tx_err_eth_type_enforcement;
+	u64 hc_tx_err_sa_enforcement;
+	u64 hc_tx_err_sqpdid_enforcement;
+	u64 hc_tx_err_cqpdid_enforcement;
+	u64 hc_tx_err_mtu_violation;
+	u64 hc_tx_err_inval_oob;
 	u64 hc_tx_bytes;
 	u64 hc_tx_ucast_pkts;
 	u64 hc_tx_ucast_bytes;
@@ -360,6 +379,7 @@ struct mana_ethtool_stats {
 	u64 hc_tx_bcast_bytes;
 	u64 hc_tx_mcast_pkts;
 	u64 hc_tx_mcast_bytes;
+	u64 hc_tx_err_gdma;
 	u64 tx_cqe_err;
 	u64 tx_cqe_unknown_type;
 	u64 rx_coalesced_err;
@@ -602,8 +622,8 @@ struct mana_query_gf_stat_resp {
 	struct gdma_resp_hdr hdr;
 	u64 reported_stats;
 	/* rx errors/discards */
-	u64 discard_rx_nowqe;
-	u64 err_rx_vport_disabled;
+	u64 rx_discards_nowqe;
+	u64 rx_err_vport_disabled;
 	/* rx bytes/packets */
 	u64 hc_rx_bytes;
 	u64 hc_rx_ucast_pkts;
@@ -613,16 +633,16 @@ struct mana_query_gf_stat_resp {
 	u64 hc_rx_mcast_pkts;
 	u64 hc_rx_mcast_bytes;
 	/* tx errors */
-	u64 err_tx_gf_disabled;
-	u64 err_tx_vport_disabled;
-	u64 err_tx_inval_vport_offset_pkt;
-	u64 err_tx_vlan_enforcement;
-	u64 err_tx_ethtype_enforcement;
-	u64 err_tx_SA_enforecement;
-	u64 err_tx_SQPDID_enforcement;
-	u64 err_tx_CQPDID_enforcement;
-	u64 err_tx_mtu_violation;
-	u64 err_tx_inval_oob;
+	u64 tx_err_gf_disabled;
+	u64 tx_err_vport_disabled;
+	u64 tx_err_inval_vport_offset_pkt;
+	u64 tx_err_vlan_enforcement;
+	u64 tx_err_ethtype_enforcement;
+	u64 tx_err_SA_enforcement;
+	u64 tx_err_SQPDID_enforcement;
+	u64 tx_err_CQPDID_enforcement;
+	u64 tx_err_mtu_violation;
+	u64 tx_err_inval_oob;
 	/* tx bytes/packets */
 	u64 hc_tx_bytes;
 	u64 hc_tx_ucast_pkts;
@@ -632,7 +652,7 @@ struct mana_query_gf_stat_resp {
 	u64 hc_tx_mcast_pkts;
 	u64 hc_tx_mcast_bytes;
 	/* tx error */
-	u64 err_tx_gdma;
+	u64 tx_err_gdma;
 }; /* HW DATA */
 
 /* Configure vPort Rx Steering */
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 07022bb0d44d..0d28172193fa 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -162,7 +162,7 @@ struct neighbour {
 	struct rcu_head		rcu;
 	struct net_device	*dev;
 	netdevice_tracker	dev_tracker;
-	u8			primary_key[0];
+	u8			primary_key[];
 } __randomize_layout;
 
 struct neigh_ops {
diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h
index cdcafb30d437..aa1716fb0e53 100644
--- a/include/net/netdev_rx_queue.h
+++ b/include/net/netdev_rx_queue.h
@@ -21,6 +21,10 @@ struct netdev_rx_queue {
 #ifdef CONFIG_XDP_SOCKETS
 	struct xsk_buff_pool            *pool;
 #endif
+	/* NAPI instance for the queue
+	 * Readers and writers must hold RTNL
+	 */
+	struct napi_struct		*napi;
 } ____cacheline_aligned_in_smp;
 
 /*
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index fe1507c1db82..956c752ceb31 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -62,6 +62,8 @@ struct nf_flowtable_type {
 						  enum flow_offload_tuple_dir dir,
 						  struct nf_flow_rule *flow_rule);
 	void				(*free)(struct nf_flowtable *ft);
+	void				(*get)(struct nf_flowtable *ft);
+	void				(*put)(struct nf_flowtable *ft);
 	nf_hookfn			*hook;
 	struct module			*owner;
 };
@@ -72,12 +74,13 @@ enum nf_flowtable_flags {
 };
 
 struct nf_flowtable {
-	struct list_head		list;
-	struct rhashtable		rhashtable;
-	int				priority;
+	unsigned int			flags;		/* readonly in datapath */
+	int				priority;	/* control path (padding hole) */
+	struct rhashtable		rhashtable;	/* datapath, read-mostly members come first */
+
+	struct list_head		list;		/* slowpath parts */
 	const struct nf_flowtable_type	*type;
 	struct delayed_work		gc_work;
-	unsigned int			flags;
 	struct flow_block		flow_block;
 	struct rw_semaphore		flow_block_lock; /* Guards flow_block */
 	possible_net_t			net;
@@ -240,6 +243,11 @@ nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table,
 	}
 
 	list_add_tail(&block_cb->list, &block->cb_list);
+	up_write(&flow_table->flow_block_lock);
+
+	if (flow_table->type->get)
+		flow_table->type->get(flow_table);
+	return 0;
 
 unlock:
 	up_write(&flow_table->flow_block_lock);
@@ -262,6 +270,9 @@ nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table,
 		WARN_ON(true);
 	}
 	up_write(&flow_table->flow_block_lock);
+
+	if (flow_table->type->put)
+		flow_table->type->put(flow_table);
 }
 
 void flow_offload_route_init(struct flow_offload *flow,
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 3bbd13ab1ecf..b157c5cafd14 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -178,9 +178,9 @@ static inline __be32 nft_reg_load_be32(const u32 *sreg)
 	return *(__force __be32 *)sreg;
 }
 
-static inline void nft_reg_store64(u32 *dreg, u64 val)
+static inline void nft_reg_store64(u64 *dreg, u64 val)
 {
-	put_unaligned(val, (u64 *)dreg);
+	put_unaligned(val, dreg);
 }
 
 static inline u64 nft_reg_load64(const u32 *sreg)
diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h
index 947973623dc7..60a7d0ce3080 100644
--- a/include/net/netfilter/nf_tables_ipv4.h
+++ b/include/net/netfilter/nf_tables_ipv4.h
@@ -30,7 +30,7 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt)
 		return -1;
 
 	len = iph_totlen(pkt->skb, iph);
-	thoff = iph->ihl * 4;
+	thoff = skb_network_offset(pkt->skb) + (iph->ihl * 4);
 	if (pkt->skb->len < len)
 		return -1;
 	else if (len < thoff)
diff --git a/include/net/netkit.h b/include/net/netkit.h
index 0ba2e6b847ca..9ec0163739f4 100644
--- a/include/net/netkit.h
+++ b/include/net/netkit.h
@@ -10,6 +10,7 @@ int netkit_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 int netkit_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 int netkit_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog);
 int netkit_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr);
+INDIRECT_CALLABLE_DECLARE(struct net_device *netkit_peer_dev(struct net_device *dev));
 #else
 static inline int netkit_prog_attach(const union bpf_attr *attr,
 				     struct bpf_prog *prog)
@@ -34,5 +35,10 @@ static inline int netkit_prog_query(const union bpf_attr *attr,
 {
 	return -EINVAL;
 }
+
+static inline struct net_device *netkit_peer_dev(struct net_device *dev)
+{
+	return NULL;
+}
 #endif /* CONFIG_NETKIT */
 #endif /* __NET_NETKIT_H */
diff --git a/include/net/netlink.h b/include/net/netlink.h
index 83bdf787aeee..c19ff921b661 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -1011,6 +1011,20 @@ static inline struct sk_buff *nlmsg_new(size_t payload, gfp_t flags)
 }
 
 /**
+ * nlmsg_new_large - Allocate a new netlink message with non-contiguous
+ * physical memory
+ * @payload: size of the message payload
+ *
+ * The allocated skb is unable to have frag page for shinfo->frags*,
+ * as the NULL setting for skb->head in netlink_skb_destructor() will
+ * bypass most of the handling in skb_release_data()
+ */
+static inline struct sk_buff *nlmsg_new_large(size_t payload)
+{
+	return netlink_alloc_large_skb(nlmsg_total_size(payload), 0);
+}
+
+/**
  * nlmsg_end - Finalize a netlink message
  * @skb: socket buffer the message is stored in
  * @nlh: netlink message header
@@ -1073,21 +1087,29 @@ static inline void nlmsg_free(struct sk_buff *skb)
 }
 
 /**
- * nlmsg_multicast - multicast a netlink message
+ * nlmsg_multicast_filtered - multicast a netlink message with filter function
  * @sk: netlink socket to spread messages to
  * @skb: netlink message as socket buffer
  * @portid: own netlink portid to avoid sending to yourself
  * @group: multicast group id
  * @flags: allocation flags
+ * @filter: filter function
+ * @filter_data: filter function private data
+ *
+ * Return: 0 on success, negative error code for failure.
  */
-static inline int nlmsg_multicast(struct sock *sk, struct sk_buff *skb,
-				  u32 portid, unsigned int group, gfp_t flags)
+static inline int nlmsg_multicast_filtered(struct sock *sk, struct sk_buff *skb,
+					   u32 portid, unsigned int group,
+					   gfp_t flags,
+					   netlink_filter_fn filter,
+					   void *filter_data)
 {
 	int err;
 
 	NETLINK_CB(skb).dst_group = group;
 
-	err = netlink_broadcast(sk, skb, portid, group, flags);
+	err = netlink_broadcast_filtered(sk, skb, portid, group, flags,
+					 filter, filter_data);
 	if (err > 0)
 		err = 0;
 
@@ -1095,6 +1117,21 @@ static inline int nlmsg_multicast(struct sock *sk, struct sk_buff *skb,
 }
 
 /**
+ * nlmsg_multicast - multicast a netlink message
+ * @sk: netlink socket to spread messages to
+ * @skb: netlink message as socket buffer
+ * @portid: own netlink portid to avoid sending to yourself
+ * @group: multicast group id
+ * @flags: allocation flags
+ */
+static inline int nlmsg_multicast(struct sock *sk, struct sk_buff *skb,
+				  u32 portid, unsigned int group, gfp_t flags)
+{
+	return nlmsg_multicast_filtered(sk, skb, portid, group, flags,
+					NULL, NULL);
+}
+
+/**
  * nlmsg_unicast - unicast a netlink message
  * @sk: netlink socket to spread message to
  * @skb: netlink message as socket buffer
@@ -1200,7 +1237,7 @@ static inline void *nla_data(const struct nlattr *nla)
  * nla_len - length of payload
  * @nla: netlink attribute
  */
-static inline int nla_len(const struct nlattr *nla)
+static inline u16 nla_len(const struct nlattr *nla)
 {
 	return nla->nla_len - NLA_HDRLEN;
 }
diff --git a/include/net/netns/core.h b/include/net/netns/core.h
index a91ef9f8de60..78214f1b43a2 100644
--- a/include/net/netns/core.h
+++ b/include/net/netns/core.h
@@ -13,6 +13,7 @@ struct netns_core {
 	struct ctl_table_header	*sysctl_hdr;
 
 	int	sysctl_somaxconn;
+	int	sysctl_optmem_max;
 	u8	sysctl_txrehash;
 
 #ifdef CONFIG_PROC_FS
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 73f43f699199..c356c458b340 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -19,8 +19,7 @@ struct hlist_head;
 struct fib_table;
 struct sock;
 struct local_ports {
-	seqlock_t	lock;
-	int		range[2];
+	u32		range;	/* high << 16 | low */
 	bool		warned;
 };
 
@@ -42,6 +41,38 @@ struct inet_timewait_death_row {
 struct tcp_fastopen_context;
 
 struct netns_ipv4 {
+	/* Cacheline organization can be found documented in
+	 * Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst.
+	 * Please update the document when adding new fields.
+	 */
+
+	/* TX readonly hotpath cache lines */
+	__cacheline_group_begin(netns_ipv4_read_tx);
+	u8 sysctl_tcp_early_retrans;
+	u8 sysctl_tcp_tso_win_divisor;
+	u8 sysctl_tcp_tso_rtt_log;
+	u8 sysctl_tcp_autocorking;
+	int sysctl_tcp_min_snd_mss;
+	unsigned int sysctl_tcp_notsent_lowat;
+	int sysctl_tcp_limit_output_bytes;
+	int sysctl_tcp_min_rtt_wlen;
+	int sysctl_tcp_wmem[3];
+	u8 sysctl_ip_fwd_use_pmtu;
+	__cacheline_group_end(netns_ipv4_read_tx);
+
+	/* TXRX readonly hotpath cache lines */
+	__cacheline_group_begin(netns_ipv4_read_txrx);
+	u8 sysctl_tcp_moderate_rcvbuf;
+	__cacheline_group_end(netns_ipv4_read_txrx);
+
+	/* RX readonly hotpath cache line */
+	__cacheline_group_begin(netns_ipv4_read_rx);
+	u8 sysctl_ip_early_demux;
+	u8 sysctl_tcp_early_demux;
+	int sysctl_tcp_reordering;
+	int sysctl_tcp_rmem[3];
+	__cacheline_group_end(netns_ipv4_read_rx);
+
 	struct inet_timewait_death_row tcp_death_row;
 	struct udp_table *udp_table;
 
@@ -96,17 +127,14 @@ struct netns_ipv4 {
 
 	u8 sysctl_ip_default_ttl;
 	u8 sysctl_ip_no_pmtu_disc;
-	u8 sysctl_ip_fwd_use_pmtu;
 	u8 sysctl_ip_fwd_update_priority;
 	u8 sysctl_ip_nonlocal_bind;
 	u8 sysctl_ip_autobind_reuse;
 	/* Shall we try to damage output packets if routing dev changes? */
 	u8 sysctl_ip_dynaddr;
-	u8 sysctl_ip_early_demux;
 #ifdef CONFIG_NET_L3_MASTER_DEV
 	u8 sysctl_raw_l3mdev_accept;
 #endif
-	u8 sysctl_tcp_early_demux;
 	u8 sysctl_udp_early_demux;
 
 	u8 sysctl_nexthop_compat_mode;
@@ -119,7 +147,6 @@ struct netns_ipv4 {
 	u8 sysctl_tcp_mtu_probing;
 	int sysctl_tcp_mtu_probe_floor;
 	int sysctl_tcp_base_mss;
-	int sysctl_tcp_min_snd_mss;
 	int sysctl_tcp_probe_threshold;
 	u32 sysctl_tcp_probe_interval;
 
@@ -135,17 +162,14 @@ struct netns_ipv4 {
 	u8 sysctl_tcp_backlog_ack_defer;
 	u8 sysctl_tcp_pingpong_thresh;
 
-	int sysctl_tcp_reordering;
 	u8 sysctl_tcp_retries1;
 	u8 sysctl_tcp_retries2;
 	u8 sysctl_tcp_orphan_retries;
 	u8 sysctl_tcp_tw_reuse;
 	int sysctl_tcp_fin_timeout;
-	unsigned int sysctl_tcp_notsent_lowat;
 	u8 sysctl_tcp_sack;
 	u8 sysctl_tcp_window_scaling;
 	u8 sysctl_tcp_timestamps;
-	u8 sysctl_tcp_early_retrans;
 	u8 sysctl_tcp_recovery;
 	u8 sysctl_tcp_thin_linear_timeouts;
 	u8 sysctl_tcp_slow_start_after_idle;
@@ -161,21 +185,13 @@ struct netns_ipv4 {
 	u8 sysctl_tcp_frto;
 	u8 sysctl_tcp_nometrics_save;
 	u8 sysctl_tcp_no_ssthresh_metrics_save;
-	u8 sysctl_tcp_moderate_rcvbuf;
-	u8 sysctl_tcp_tso_win_divisor;
 	u8 sysctl_tcp_workaround_signed_windows;
-	int sysctl_tcp_limit_output_bytes;
 	int sysctl_tcp_challenge_ack_limit;
-	int sysctl_tcp_min_rtt_wlen;
 	u8 sysctl_tcp_min_tso_segs;
-	u8 sysctl_tcp_tso_rtt_log;
-	u8 sysctl_tcp_autocorking;
 	u8 sysctl_tcp_reflect_tos;
 	int sysctl_tcp_invalid_ratelimit;
 	int sysctl_tcp_pacing_ss_ratio;
 	int sysctl_tcp_pacing_ca_ratio;
-	int sysctl_tcp_wmem[3];
-	int sysctl_tcp_rmem[3];
 	unsigned int sysctl_tcp_child_ehash_entries;
 	unsigned long sysctl_tcp_comp_sack_delay_ns;
 	unsigned long sysctl_tcp_comp_sack_slack_ns;
diff --git a/include/net/netns/smc.h b/include/net/netns/smc.h
index 582212ada3ba..fc752a50f91b 100644
--- a/include/net/netns/smc.h
+++ b/include/net/netns/smc.h
@@ -22,5 +22,7 @@ struct netns_smc {
 	int				sysctl_smcr_testlink_time;
 	int				sysctl_wmem;
 	int				sysctl_rmem;
+	int				sysctl_max_links_per_lgr;
+	int				sysctl_max_conns_per_lgr;
 };
 #endif
diff --git a/include/net/nl802154.h b/include/net/nl802154.h
index 8cd9d141f5af..4c752f799957 100644
--- a/include/net/nl802154.h
+++ b/include/net/nl802154.h
@@ -78,6 +78,10 @@ enum nl802154_commands {
 	NL802154_CMD_SCAN_DONE,
 	NL802154_CMD_SEND_BEACONS,
 	NL802154_CMD_STOP_BEACONS,
+	NL802154_CMD_ASSOCIATE,
+	NL802154_CMD_DISASSOCIATE,
+	NL802154_CMD_SET_MAX_ASSOCIATIONS,
+	NL802154_CMD_LIST_ASSOCIATIONS,
 
 	/* add new commands above here */
 
@@ -147,6 +151,8 @@ enum nl802154_attrs {
 	NL802154_ATTR_SCAN_DURATION,
 	NL802154_ATTR_SCAN_DONE_REASON,
 	NL802154_ATTR_BEACON_INTERVAL,
+	NL802154_ATTR_MAX_ASSOCIATIONS,
+	NL802154_ATTR_PEER,
 
 	/* add attributes here, update the policy in nl802154.c */
 
@@ -385,8 +391,6 @@ enum nl802154_supported_bool_states {
 	NL802154_SUPPORTED_BOOL_MAX = __NL802154_SUPPORTED_BOOL_AFTER_LAST - 1
 };
 
-#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
-
 enum nl802154_dev_addr_modes {
 	NL802154_DEV_ADDR_NONE,
 	__NL802154_DEV_ADDR_INVALID,
@@ -406,12 +410,26 @@ enum nl802154_dev_addr_attrs {
 	NL802154_DEV_ADDR_ATTR_SHORT,
 	NL802154_DEV_ADDR_ATTR_EXTENDED,
 	NL802154_DEV_ADDR_ATTR_PAD,
+	NL802154_DEV_ADDR_ATTR_PEER_TYPE,
 
 	/* keep last */
 	__NL802154_DEV_ADDR_ATTR_AFTER_LAST,
 	NL802154_DEV_ADDR_ATTR_MAX = __NL802154_DEV_ADDR_ATTR_AFTER_LAST - 1
 };
 
+enum nl802154_peer_type {
+	NL802154_PEER_TYPE_UNSPEC,
+
+	NL802154_PEER_TYPE_PARENT,
+	NL802154_PEER_TYPE_CHILD,
+
+	/* keep last */
+	__NL802154_PEER_TYPE_AFTER_LAST,
+	NL802154_PEER_TYPE_MAX = __NL802154_PEER_TYPE_AFTER_LAST - 1
+};
+
+#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
+
 enum nl802154_key_id_modes {
 	NL802154_KEY_ID_MODE_IMPLICIT,
 	NL802154_KEY_ID_MODE_INDEX,
diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h
index 4ebd544ae977..1d397c1a0043 100644
--- a/include/net/page_pool/helpers.h
+++ b/include/net/page_pool/helpers.h
@@ -11,7 +11,7 @@
  * The page_pool allocator is optimized for recycling page or page fragment used
  * by skb packet and xdp frame.
  *
- * Basic use involves replacing and alloc_pages() calls with page_pool_alloc(),
+ * Basic use involves replacing any alloc_pages() calls with page_pool_alloc(),
  * which allocate memory with or without page splitting depending on the
  * requested memory size.
  *
@@ -29,7 +29,7 @@
  * page allocated from page pool. Page splitting enables memory saving and thus
  * avoids TLB/cache miss for data access, but there also is some cost to
  * implement page splitting, mainly some cache line dirtying/bouncing for
- * 'struct page' and atomic operation for page->pp_frag_count.
+ * 'struct page' and atomic operation for page->pp_ref_count.
  *
  * The API keeps track of in-flight pages, in order to let API users know when
  * it is safe to free a page_pool object, the API users must call
@@ -37,15 +37,15 @@
  * attach the page_pool object to a page_pool-aware object like skbs marked with
  * skb_mark_for_recycle().
  *
- * page_pool_put_page() may be called multi times on the same page if a page is
- * split into multi fragments. For the last fragment, it will either recycle the
- * page, or in case of page->_refcount > 1, it will release the DMA mapping and
- * in-flight state accounting.
+ * page_pool_put_page() may be called multiple times on the same page if a page
+ * is split into multiple fragments. For the last fragment, it will either
+ * recycle the page, or in case of page->_refcount > 1, it will release the DMA
+ * mapping and in-flight state accounting.
  *
  * dma_sync_single_range_for_device() is only called for the last fragment when
  * page_pool is created with PP_FLAG_DMA_SYNC_DEV flag, so it depends on the
  * last freed fragment to do the sync_for_device operation for all fragments in
- * the same page when a page is split, the API user must setup pool->p.max_len
+ * the same page when a page is split. The API user must setup pool->p.max_len
  * and pool->p.offset correctly and ensure that page_pool_put_page() is called
  * with dma_sync_size being -1 for fragment API.
  */
@@ -55,16 +55,12 @@
 #include <net/page_pool/types.h>
 
 #ifdef CONFIG_PAGE_POOL_STATS
+/* Deprecated driver-facing API, use netlink instead */
 int page_pool_ethtool_stats_get_count(void);
 u8 *page_pool_ethtool_stats_get_strings(u8 *data);
 u64 *page_pool_ethtool_stats_get(u64 *data, void *stats);
 
-/*
- * Drivers that wish to harvest page pool stats and report them to users
- * (perhaps via ethtool, debugfs, or another mechanism) can allocate a
- * struct page_pool_stats call page_pool_get_stats to get stats for the specified pool.
- */
-bool page_pool_get_stats(struct page_pool *pool,
+bool page_pool_get_stats(const struct page_pool *pool,
 			 struct page_pool_stats *stats);
 #else
 static inline int page_pool_ethtool_stats_get_count(void)
@@ -214,69 +210,82 @@ inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool)
 	return pool->p.dma_dir;
 }
 
-/* pp_frag_count represents the number of writers who can update the page
- * either by updating skb->data or via DMA mappings for the device.
- * We can't rely on the page refcnt for that as we don't know who might be
- * holding page references and we can't reliably destroy or sync DMA mappings
- * of the fragments.
+/**
+ * page_pool_fragment_page() - split a fresh page into fragments
+ * @page:	page to split
+ * @nr:		references to set
+ *
+ * pp_ref_count represents the number of outstanding references to the page,
+ * which will be freed using page_pool APIs (rather than page allocator APIs
+ * like put_page()). Such references are usually held by page_pool-aware
+ * objects like skbs marked for page pool recycling.
  *
- * When pp_frag_count reaches 0 we can either recycle the page if the page
- * refcnt is 1 or return it back to the memory allocator and destroy any
- * mappings we have.
+ * This helper allows the caller to take (set) multiple references to a
+ * freshly allocated page. The page must be freshly allocated (have a
+ * pp_ref_count of 1). This is commonly done by drivers and
+ * "fragment allocators" to save atomic operations - either when they know
+ * upfront how many references they will need; or to take MAX references and
+ * return the unused ones with a single atomic dec(), instead of performing
+ * multiple atomic inc() operations.
  */
 static inline void page_pool_fragment_page(struct page *page, long nr)
 {
-	atomic_long_set(&page->pp_frag_count, nr);
+	atomic_long_set(&page->pp_ref_count, nr);
 }
 
-static inline long page_pool_defrag_page(struct page *page, long nr)
+static inline long page_pool_unref_page(struct page *page, long nr)
 {
 	long ret;
 
-	/* If nr == pp_frag_count then we have cleared all remaining
+	/* If nr == pp_ref_count then we have cleared all remaining
 	 * references to the page:
 	 * 1. 'n == 1': no need to actually overwrite it.
 	 * 2. 'n != 1': overwrite it with one, which is the rare case
-	 *              for pp_frag_count draining.
+	 *              for pp_ref_count draining.
 	 *
 	 * The main advantage to doing this is that not only we avoid a atomic
 	 * update, as an atomic_read is generally a much cheaper operation than
 	 * an atomic update, especially when dealing with a page that may be
-	 * partitioned into only 2 or 3 pieces; but also unify the pp_frag_count
+	 * referenced by only 2 or 3 users; but also unify the pp_ref_count
 	 * handling by ensuring all pages have partitioned into only 1 piece
 	 * initially, and only overwrite it when the page is partitioned into
 	 * more than one piece.
 	 */
-	if (atomic_long_read(&page->pp_frag_count) == nr) {
+	if (atomic_long_read(&page->pp_ref_count) == nr) {
 		/* As we have ensured nr is always one for constant case using
 		 * the BUILD_BUG_ON(), only need to handle the non-constant case
-		 * here for pp_frag_count draining, which is a rare case.
+		 * here for pp_ref_count draining, which is a rare case.
 		 */
 		BUILD_BUG_ON(__builtin_constant_p(nr) && nr != 1);
 		if (!__builtin_constant_p(nr))
-			atomic_long_set(&page->pp_frag_count, 1);
+			atomic_long_set(&page->pp_ref_count, 1);
 
 		return 0;
 	}
 
-	ret = atomic_long_sub_return(nr, &page->pp_frag_count);
+	ret = atomic_long_sub_return(nr, &page->pp_ref_count);
 	WARN_ON(ret < 0);
 
-	/* We are the last user here too, reset pp_frag_count back to 1 to
+	/* We are the last user here too, reset pp_ref_count back to 1 to
 	 * ensure all pages have been partitioned into 1 piece initially,
 	 * this should be the rare case when the last two fragment users call
-	 * page_pool_defrag_page() currently.
+	 * page_pool_unref_page() currently.
 	 */
 	if (unlikely(!ret))
-		atomic_long_set(&page->pp_frag_count, 1);
+		atomic_long_set(&page->pp_ref_count, 1);
 
 	return ret;
 }
 
-static inline bool page_pool_is_last_frag(struct page *page)
+static inline void page_pool_ref_page(struct page *page)
+{
+	atomic_long_inc(&page->pp_ref_count);
+}
+
+static inline bool page_pool_is_last_ref(struct page *page)
 {
-	/* If page_pool_defrag_page() returns 0, we were the last user */
-	return page_pool_defrag_page(page, 1) == 0;
+	/* If page_pool_unref_page() returns 0, we were the last user */
+	return page_pool_unref_page(page, 1) == 0;
 }
 
 /**
@@ -301,10 +310,10 @@ static inline void page_pool_put_page(struct page_pool *pool,
 	 * allow registering MEM_TYPE_PAGE_POOL, but shield linker.
 	 */
 #ifdef CONFIG_PAGE_POOL
-	if (!page_pool_is_last_frag(page))
+	if (!page_pool_is_last_ref(page))
 		return;
 
-	page_pool_put_defragged_page(pool, page, dma_sync_size, allow_direct);
+	page_pool_put_unrefed_page(pool, page, dma_sync_size, allow_direct);
 #endif
 }
 
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index 6fc5134095ed..76481c465375 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -5,6 +5,7 @@
 
 #include <linux/dma-direction.h>
 #include <linux/ptr_ring.h>
+#include <linux/types.h>
 
 #define PP_FLAG_DMA_MAP		BIT(0) /* Should page_pool do the DMA
 					* map/unmap
@@ -48,24 +49,30 @@ struct pp_alloc_cache {
  * @pool_size:	size of the ptr_ring
  * @nid:	NUMA node id to allocate from pages from
  * @dev:	device, for DMA pre-mapping purposes
+ * @netdev:	netdev this pool will serve (leave as NULL if none or multiple)
  * @napi:	NAPI which is the sole consumer of pages, otherwise NULL
  * @dma_dir:	DMA mapping direction
  * @max_len:	max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV
  * @offset:	DMA sync address offset for PP_FLAG_DMA_SYNC_DEV
  */
 struct page_pool_params {
-	unsigned int	flags;
-	unsigned int	order;
-	unsigned int	pool_size;
-	int		nid;
-	struct device	*dev;
-	struct napi_struct *napi;
-	enum dma_data_direction dma_dir;
-	unsigned int	max_len;
-	unsigned int	offset;
+	struct_group_tagged(page_pool_params_fast, fast,
+		unsigned int	flags;
+		unsigned int	order;
+		unsigned int	pool_size;
+		int		nid;
+		struct device	*dev;
+		struct napi_struct *napi;
+		enum dma_data_direction dma_dir;
+		unsigned int	max_len;
+		unsigned int	offset;
+	);
+	struct_group_tagged(page_pool_params_slow, slow,
+		struct net_device *netdev;
 /* private: used by test code only */
-	void (*init_callback)(struct page *page, void *arg);
-	void *init_arg;
+		void (*init_callback)(struct page *page, void *arg);
+		void *init_arg;
+	);
 };
 
 #ifdef CONFIG_PAGE_POOL_STATS
@@ -119,7 +126,9 @@ struct page_pool_stats {
 #endif
 
 struct page_pool {
-	struct page_pool_params p;
+	struct page_pool_params_fast p;
+
+	bool has_init_callback;
 
 	long frag_users;
 	struct page *frag_page;
@@ -178,6 +187,16 @@ struct page_pool {
 	refcount_t user_cnt;
 
 	u64 destroy_cnt;
+
+	/* Slow/Control-path information follows */
+	struct page_pool_params_slow slow;
+	/* User-facing fields, protected by page_pools_lock */
+	struct {
+		struct hlist_node list;
+		u64 detach_time;
+		u32 napi_id;
+		u32 id;
+	} user;
 };
 
 struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp);
@@ -215,9 +234,9 @@ static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data,
 }
 #endif
 
-void page_pool_put_defragged_page(struct page_pool *pool, struct page *page,
-				  unsigned int dma_sync_size,
-				  bool allow_direct);
+void page_pool_put_unrefed_page(struct page_pool *pool, struct page *page,
+				unsigned int dma_sync_size,
+				bool allow_direct);
 
 static inline bool is_page_pool_compiled_in(void)
 {
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index a76c9171db0e..f308e8268651 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -154,12 +154,6 @@ __cls_set_class(unsigned long *clp, unsigned long cl)
 	return xchg(clp, cl);
 }
 
-static inline void tcf_set_drop_reason(struct tcf_result *res,
-				       enum skb_drop_reason reason)
-{
-	res->drop_reason = reason;
-}
-
 static inline void
 __tcf_bind_filter(struct Qdisc *q, struct tcf_result *r, unsigned long base)
 {
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 9fa1d0794dfa..1e200d9a066d 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -275,24 +275,6 @@ static inline void skb_txtime_consumed(struct sk_buff *skb)
 	skb->tstamp = ktime_set(0, 0);
 }
 
-struct tc_skb_cb {
-	struct qdisc_skb_cb qdisc_cb;
-
-	u16 mru;
-	u8 post_ct:1;
-	u8 post_ct_snat:1;
-	u8 post_ct_dnat:1;
-	u16 zone; /* Only valid if post_ct = true */
-};
-
-static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb)
-{
-	struct tc_skb_cb *cb = (struct tc_skb_cb *)skb->cb;
-
-	BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb));
-	return cb;
-}
-
 static inline bool tc_qdisc_stats_dump(struct Qdisc *sch,
 				       unsigned long cl,
 				       struct qdisc_walker *arg)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index dcb9160e6467..ba3e1b315de8 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -19,6 +19,7 @@
 #include <net/gen_stats.h>
 #include <net/rtnetlink.h>
 #include <net/flow_offload.h>
+#include <linux/xarray.h>
 
 struct Qdisc_ops;
 struct qdisc_walker;
@@ -332,7 +333,6 @@ struct tcf_result {
 		};
 		const struct tcf_proto *goto_tp;
 	};
-	enum skb_drop_reason		drop_reason;
 };
 
 struct tcf_chain;
@@ -457,6 +457,7 @@ struct tcf_chain {
 };
 
 struct tcf_block {
+	struct xarray ports; /* datapath accessible */
 	/* Lock protects tcf_block and lifetime-management data of chains
 	 * attached to the block (refcnt, action_refcnt, explicitly_created).
 	 */
@@ -483,6 +484,8 @@ struct tcf_block {
 	struct mutex proto_destroy_lock; /* Lock for proto_destroy hashtable. */
 };
 
+struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index);
+
 static inline bool lockdep_tcf_chain_is_locked(struct tcf_chain *chain)
 {
 	return lockdep_is_held(&chain->filter_chain_lock);
@@ -1037,6 +1040,37 @@ static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch)
 	return skb;
 }
 
+struct tc_skb_cb {
+	struct qdisc_skb_cb qdisc_cb;
+	u32 drop_reason;
+
+	u16 zone; /* Only valid if post_ct = true */
+	u16 mru;
+	u8 post_ct:1;
+	u8 post_ct_snat:1;
+	u8 post_ct_dnat:1;
+};
+
+static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb)
+{
+	struct tc_skb_cb *cb = (struct tc_skb_cb *)skb->cb;
+
+	BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb));
+	return cb;
+}
+
+static inline enum skb_drop_reason
+tcf_get_drop_reason(const struct sk_buff *skb)
+{
+	return tc_skb_cb(skb)->drop_reason;
+}
+
+static inline void tcf_set_drop_reason(const struct sk_buff *skb,
+				       enum skb_drop_reason reason)
+{
+	tc_skb_cb(skb)->drop_reason = reason;
+}
+
 /* Instead of calling kfree_skb() while root qdisc lock is held,
  * queue the skb for future freeing at end of __dev_xmit_skb()
  */
diff --git a/include/net/scm.h b/include/net/scm.h
index e8c76b4be2fe..cf68acec4d70 100644
--- a/include/net/scm.h
+++ b/include/net/scm.h
@@ -5,6 +5,7 @@
 #include <linux/limits.h>
 #include <linux/net.h>
 #include <linux/cred.h>
+#include <linux/file.h>
 #include <linux/security.h>
 #include <linux/pid.h>
 #include <linux/nsproxy.h>
@@ -208,5 +209,13 @@ static inline void scm_recv_unix(struct socket *sock, struct msghdr *msg,
 	scm_destroy_cred(scm);
 }
 
+static inline int scm_recv_one_fd(struct file *f, int __user *ufd,
+				  unsigned int flags)
+{
+	if (!ufd)
+		return -EFAULT;
+	return receive_fd(f, ufd, flags);
+}
+
 #endif /* __LINUX_NET_SCM_H */
 
diff --git a/include/net/smc.h b/include/net/smc.h
index a002552be29c..c9dcb30e3fd9 100644
--- a/include/net/smc.h
+++ b/include/net/smc.h
@@ -52,9 +52,14 @@ struct smcd_dmb {
 struct smcd_dev;
 struct ism_client;
 
+struct smcd_gid {
+	u64	gid;
+	u64	gid_ext;
+};
+
 struct smcd_ops {
-	int (*query_remote_gid)(struct smcd_dev *dev, u64 rgid, u32 vid_valid,
-				u32 vid);
+	int (*query_remote_gid)(struct smcd_dev *dev, struct smcd_gid *rgid,
+				u32 vid_valid, u32 vid);
 	int (*register_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb,
 			    struct ism_client *client);
 	int (*unregister_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb);
@@ -62,14 +67,13 @@ struct smcd_ops {
 	int (*del_vlan_id)(struct smcd_dev *dev, u64 vlan_id);
 	int (*set_vlan_required)(struct smcd_dev *dev);
 	int (*reset_vlan_required)(struct smcd_dev *dev);
-	int (*signal_event)(struct smcd_dev *dev, u64 rgid, u32 trigger_irq,
-			    u32 event_code, u64 info);
+	int (*signal_event)(struct smcd_dev *dev, struct smcd_gid *rgid,
+			    u32 trigger_irq, u32 event_code, u64 info);
 	int (*move_data)(struct smcd_dev *dev, u64 dmb_tok, unsigned int idx,
 			 bool sf, unsigned int offset, void *data,
 			 unsigned int size);
 	int (*supports_v2)(void);
-	u8* (*get_system_eid)(void);
-	u64 (*get_local_gid)(struct smcd_dev *dev);
+	void (*get_local_gid)(struct smcd_dev *dev, struct smcd_gid *gid);
 	u16 (*get_chid)(struct smcd_dev *dev);
 	struct device* (*get_dev)(struct smcd_dev *dev);
 };
diff --git a/include/net/sock.h b/include/net/sock.h
index 1d6931caf0c3..a7f815c7cfdf 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -76,19 +76,6 @@
  * the other protocols.
  */
 
-/* Define this to get the SOCK_DBG debugging facility. */
-#define SOCK_DEBUGGING
-#ifdef SOCK_DEBUGGING
-#define SOCK_DEBUG(sk, msg...) do { if ((sk) && sock_flag((sk), SOCK_DBG)) \
-					printk(KERN_DEBUG msg); } while (0)
-#else
-/* Validate arguments and do nothing */
-static inline __printf(2, 3)
-void SOCK_DEBUG(const struct sock *sk, const char *msg, ...)
-{
-}
-#endif
-
 /* This is the per-socket lock.  The spinlock provides a synchronization
  * between user contexts and software interrupt processing, whereas the
  * mini-semaphore synchronizes multiple users amongst themselves.
@@ -277,8 +264,6 @@ struct sk_filter;
   *	@sk_pacing_status: Pacing status (requested, handled by sch_fq)
   *	@sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE)
   *	@sk_sndbuf: size of send buffer in bytes
-  *	@__sk_flags_offset: empty field used to determine location of bitfield
-  *	@sk_padding: unused element for alignment
   *	@sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets
   *	@sk_no_check_rx: allow zero checksum in RX packets
   *	@sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
@@ -352,7 +337,6 @@ struct sk_filter;
   *	@sk_txtime_report_errors: set report errors mode for SO_TXTIME
   *	@sk_txtime_unused: unused txtime flags
   *	@ns_tracker: tracker for netns reference
-  *	@sk_bind2_node: bind node in the bhash2 table
   */
 struct sock {
 	/*
@@ -544,7 +528,6 @@ struct sock {
 #endif
 	struct rcu_head		sk_rcu;
 	netns_tracker		ns_tracker;
-	struct hlist_node	sk_bind2_node;
 };
 
 enum sk_pacing {
@@ -873,16 +856,6 @@ static inline void sk_add_bind_node(struct sock *sk,
 	hlist_add_head(&sk->sk_bind_node, list);
 }
 
-static inline void __sk_del_bind2_node(struct sock *sk)
-{
-	__hlist_del(&sk->sk_bind2_node);
-}
-
-static inline void sk_add_bind2_node(struct sock *sk, struct hlist_head *list)
-{
-	hlist_add_head(&sk->sk_bind2_node, list);
-}
-
 #define sk_for_each(__sk, list) \
 	hlist_for_each_entry(__sk, list, sk_node)
 #define sk_for_each_rcu(__sk, list) \
@@ -900,8 +873,6 @@ static inline void sk_add_bind2_node(struct sock *sk, struct hlist_head *list)
 	hlist_for_each_entry_safe(__sk, tmp, list, sk_node)
 #define sk_for_each_bound(__sk, list) \
 	hlist_for_each_entry(__sk, list, sk_bind_node)
-#define sk_for_each_bound_bhash2(__sk, list) \
-	hlist_for_each_entry(__sk, list, sk_bind2_node)
 
 /**
  * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset
@@ -2799,6 +2770,11 @@ static inline bool sk_is_tcp(const struct sock *sk)
 	return sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP;
 }
 
+static inline bool sk_is_stream_unix(const struct sock *sk)
+{
+	return sk->sk_family == AF_UNIX && sk->sk_type == SOCK_STREAM;
+}
+
 /**
  * sk_eat_skb - Release a skb if it is no longer needed
  * @sk: socket to eat this skb from
@@ -2920,7 +2896,6 @@ extern __u32 sysctl_wmem_max;
 extern __u32 sysctl_rmem_max;
 
 extern int sysctl_tstamp_allow_data;
-extern int sysctl_optmem_max;
 
 extern __u32 sysctl_wmem_default;
 extern __u32 sysctl_rmem_default;
diff --git a/include/net/tc_act/tc_ct.h b/include/net/tc_act/tc_ct.h
index 8a6dbfb23336..77f87c622a2e 100644
--- a/include/net/tc_act/tc_ct.h
+++ b/include/net/tc_act/tc_ct.h
@@ -58,6 +58,11 @@ static inline struct nf_flowtable *tcf_ct_ft(const struct tc_action *a)
 	return to_ct_params(a)->nf_ft;
 }
 
+static inline struct nf_conntrack_helper *tcf_ct_helper(const struct tc_action *a)
+{
+	return to_ct_params(a)->helper;
+}
+
 #else
 static inline uint16_t tcf_ct_zone(const struct tc_action *a) { return 0; }
 static inline int tcf_ct_action(const struct tc_action *a) { return 0; }
@@ -65,6 +70,10 @@ static inline struct nf_flowtable *tcf_ct_ft(const struct tc_action *a)
 {
 	return NULL;
 }
+static inline struct nf_conntrack_helper *tcf_ct_helper(const struct tc_action *a)
+{
+	return NULL;
+}
 #endif /* CONFIG_NF_CONNTRACK */
 
 #if IS_ENABLED(CONFIG_NET_ACT_CT)
diff --git a/include/net/tc_act/tc_ipt.h b/include/net/tc_act/tc_ipt.h
deleted file mode 100644
index 4225fcb1c6ba..000000000000
--- a/include/net/tc_act/tc_ipt.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __NET_TC_IPT_H
-#define __NET_TC_IPT_H
-
-#include <net/act_api.h>
-
-struct xt_entry_target;
-
-struct tcf_ipt {
-	struct tc_action	common;
-	u32			tcfi_hook;
-	char			*tcfi_tname;
-	struct xt_entry_target	*tcfi_t;
-};
-#define to_ipt(a) ((struct tcf_ipt *)a)
-
-#endif /* __NET_TC_IPT_H */
diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h
index 32ce8ea36950..75722d967bf2 100644
--- a/include/net/tc_act/tc_mirred.h
+++ b/include/net/tc_act/tc_mirred.h
@@ -8,6 +8,7 @@
 struct tcf_mirred {
 	struct tc_action	common;
 	int			tcfm_eaction;
+	u32                     tcfm_blockid;
 	bool			tcfm_mac_header_xmit;
 	struct net_device __rcu	*tcfm_dev;
 	netdevice_tracker	tcfm_dev_tracker;
diff --git a/include/net/tc_wrapper.h b/include/net/tc_wrapper.h
index a6d481b5bcbc..a608546bcefc 100644
--- a/include/net/tc_wrapper.h
+++ b/include/net/tc_wrapper.h
@@ -117,10 +117,6 @@ static inline int tc_act(struct sk_buff *skb, const struct tc_action *a,
 	if (a->ops->act == tcf_ife_act)
 		return tcf_ife_act(skb, a, res);
 #endif
-#if IS_BUILTIN(CONFIG_NET_ACT_IPT)
-	if (a->ops->act == tcf_ipt_act)
-		return tcf_ipt_act(skb, a, res);
-#endif
 #if IS_BUILTIN(CONFIG_NET_ACT_SIMP)
 	if (a->ops->act == tcf_simp_act)
 		return tcf_simp_act(skb, a, res);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index d2f0736b76b8..dd78a1181031 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -490,13 +490,14 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb);
 /* From syncookies.c */
 struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 				 struct request_sock *req,
-				 struct dst_entry *dst, u32 tsoff);
-int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
-		      u32 cookie);
+				 struct dst_entry *dst);
+int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th);
 struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb);
 struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
-					    const struct tcp_request_sock_ops *af_ops,
-					    struct sock *sk, struct sk_buff *skb);
+					    struct sock *sk, struct sk_buff *skb,
+					    struct tcp_options_received *tcp_opt,
+					    int mss, u32 tsoff);
+
 #ifdef CONFIG_SYN_COOKIES
 
 /* Syncookies use a monotonic timer which increments every 60 seconds.
@@ -582,12 +583,15 @@ __u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss);
 u64 cookie_init_timestamp(struct request_sock *req, u64 now);
 bool cookie_timestamp_decode(const struct net *net,
 			     struct tcp_options_received *opt);
-bool cookie_ecn_ok(const struct tcp_options_received *opt,
-		   const struct net *net, const struct dst_entry *dst);
+
+static inline bool cookie_ecn_ok(const struct net *net, const struct dst_entry *dst)
+{
+	return READ_ONCE(net->ipv4.sysctl_tcp_ecn) ||
+		dst_feature(dst, RTAX_FEATURE_ECN);
+}
 
 /* From net/ipv6/syncookies.c */
-int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th,
-		      u32 cookie);
+int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th);
 struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb);
 
 u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph,
@@ -1514,17 +1518,22 @@ static inline int tcp_full_space(const struct sock *sk)
 	return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf));
 }
 
-static inline void tcp_adjust_rcv_ssthresh(struct sock *sk)
+static inline void __tcp_adjust_rcv_ssthresh(struct sock *sk, u32 new_ssthresh)
 {
 	int unused_mem = sk_unused_reserved_mem(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
+	tp->rcv_ssthresh = min(tp->rcv_ssthresh, new_ssthresh);
 	if (unused_mem)
 		tp->rcv_ssthresh = max_t(u32, tp->rcv_ssthresh,
 					 tcp_win_from_space(sk, unused_mem));
 }
 
+static inline void tcp_adjust_rcv_ssthresh(struct sock *sk)
+{
+	__tcp_adjust_rcv_ssthresh(sk, 4U * tcp_sk(sk)->advmss);
+}
+
 void tcp_cleanup_rbuf(struct sock *sk, int copied);
 void __tcp_cleanup_rbuf(struct sock *sk, int copied);
 
@@ -1783,8 +1792,6 @@ struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk,
 					 const struct sock *addr_sk);
 
 #ifdef CONFIG_TCP_MD5SIG
-#include <linux/jump_label.h>
-extern struct static_key_false_deferred tcp_md5_needed;
 struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index,
 					   const union tcp_md5_addr *addr,
 					   int family, bool any_l3index);
diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h
index b56be10838f0..471e177362b4 100644
--- a/include/net/tcp_ao.h
+++ b/include/net/tcp_ao.h
@@ -62,11 +62,17 @@ static inline int tcp_ao_maclen(const struct tcp_ao_key *key)
 	return key->maclen;
 }
 
+/* Use tcp_ao_len_aligned() for TCP header calculations */
 static inline int tcp_ao_len(const struct tcp_ao_key *key)
 {
 	return tcp_ao_maclen(key) + sizeof(struct tcp_ao_hdr);
 }
 
+static inline int tcp_ao_len_aligned(const struct tcp_ao_key *key)
+{
+	return round_up(tcp_ao_len(key), 4);
+}
+
 static inline unsigned int tcp_ao_digest_size(struct tcp_ao_key *key)
 {
 	return key->digest_size;
@@ -121,12 +127,35 @@ struct tcp_ao_info {
 	struct rcu_head		rcu;
 };
 
+#ifdef CONFIG_TCP_MD5SIG
+#include <linux/jump_label.h>
+extern struct static_key_false_deferred tcp_md5_needed;
+#define static_branch_tcp_md5()	static_branch_unlikely(&tcp_md5_needed.key)
+#else
+#define static_branch_tcp_md5()	false
+#endif
+#ifdef CONFIG_TCP_AO
+/* TCP-AO structures and functions */
+#include <linux/jump_label.h>
+extern struct static_key_false_deferred tcp_ao_needed;
+#define static_branch_tcp_ao()	static_branch_unlikely(&tcp_ao_needed.key)
+#else
+#define static_branch_tcp_ao()	false
+#endif
+
+static inline bool tcp_hash_should_produce_warnings(void)
+{
+	return static_branch_tcp_md5() || static_branch_tcp_ao();
+}
+
 #define tcp_hash_fail(msg, family, skb, fmt, ...)			\
 do {									\
 	const struct tcphdr *th = tcp_hdr(skb);				\
 	char hdr_flags[6];						\
 	char *f = hdr_flags;						\
 									\
+	if (!tcp_hash_should_produce_warnings())			\
+		break;							\
 	if (th->fin)							\
 		*f++ = 'F';						\
 	if (th->syn)							\
@@ -153,9 +182,6 @@ do {									\
 
 #ifdef CONFIG_TCP_AO
 /* TCP-AO structures and functions */
-#include <linux/jump_label.h>
-extern struct static_key_false_deferred tcp_ao_needed;
-
 struct tcp4_ao_context {
 	__be32		saddr;
 	__be32		daddr;
@@ -265,8 +291,7 @@ void tcp_ao_established(struct sock *sk);
 void tcp_ao_finish_connect(struct sock *sk, struct sk_buff *skb);
 void tcp_ao_connect_init(struct sock *sk);
 void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb,
-		      struct tcp_request_sock *treq,
-		      unsigned short int family, int l3index);
+		      struct request_sock *req, unsigned short int family);
 #else /* CONFIG_TCP_AO */
 
 static inline int tcp_ao_transmit_skb(struct sock *sk, struct sk_buff *skb,
@@ -277,8 +302,7 @@ static inline int tcp_ao_transmit_skb(struct sock *sk, struct sk_buff *skb,
 }
 
 static inline void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb,
-				    struct tcp_request_sock *treq,
-				    unsigned short int family, int l3index)
+				    struct request_sock *req, unsigned short int family)
 {
 }
 
diff --git a/include/net/tcp_states.h b/include/net/tcp_states.h
index cc00118acca1..d60e8148ff4c 100644
--- a/include/net/tcp_states.h
+++ b/include/net/tcp_states.h
@@ -22,6 +22,7 @@ enum {
 	TCP_LISTEN,
 	TCP_CLOSING,	/* Now a valid state */
 	TCP_NEW_SYN_RECV,
+	TCP_BOUND_INACTIVE, /* Pseudo-state for inet_diag */
 
 	TCP_MAX_STATES	/* Leave at the end! */
 };
@@ -43,6 +44,7 @@ enum {
 	TCPF_LISTEN	 = (1 << TCP_LISTEN),
 	TCPF_CLOSING	 = (1 << TCP_CLOSING),
 	TCPF_NEW_SYN_RECV = (1 << TCP_NEW_SYN_RECV),
+	TCPF_BOUND_INACTIVE = (1 << TCP_BOUND_INACTIVE),
 };
 
 #endif	/* _LINUX_TCP_STATES_H */
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 6a9f8a5f387c..33ba6fc151cf 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -210,22 +210,23 @@ struct vxlan_rdst {
 };
 
 struct vxlan_config {
-	union vxlan_addr	remote_ip;
-	union vxlan_addr	saddr;
-	__be32			vni;
-	int			remote_ifindex;
-	int			mtu;
-	__be16			dst_port;
-	u16			port_min;
-	u16			port_max;
-	u8			tos;
-	u8			ttl;
-	__be32			label;
-	u32			flags;
-	unsigned long		age_interval;
-	unsigned int		addrmax;
-	bool			no_share;
-	enum ifla_vxlan_df	df;
+	union vxlan_addr		remote_ip;
+	union vxlan_addr		saddr;
+	__be32				vni;
+	int				remote_ifindex;
+	int				mtu;
+	__be16				dst_port;
+	u16				port_min;
+	u16				port_max;
+	u8				tos;
+	u8				ttl;
+	__be32				label;
+	enum ifla_vxlan_label_policy	label_policy;
+	u32				flags;
+	unsigned long			age_interval;
+	unsigned int			addrmax;
+	bool				no_share;
+	enum ifla_vxlan_df		df;
 };
 
 enum {
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 349c36fb5fd8..e6770dd40c91 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -16,7 +16,7 @@
  *
  * The XDP RX-queue info (xdp_rxq_info) is associated with the driver
  * level RX-ring queues.  It is information that is specific to how
- * the driver have configured a given RX-ring queue.
+ * the driver has configured a given RX-ring queue.
  *
  * Each xdp_buff frame received in the driver carries a (pointer)
  * reference to this xdp_rxq_info structure.  This provides the XDP
@@ -32,7 +32,7 @@
  * The struct is not directly tied to the XDP prog.  A new XDP prog
  * can be attached as long as it doesn't change the underlying
  * RX-ring.  If the RX-ring does change significantly, the NIC driver
- * naturally need to stop the RX-ring before purging and reallocating
+ * naturally needs to stop the RX-ring before purging and reallocating
  * memory.  In that process the driver MUST call unregister (which
  * also applies for driver shutdown and unload).  The register API is
  * also mandatory during RX-ring setup.
@@ -369,7 +369,12 @@ xdp_data_meta_unsupported(const struct xdp_buff *xdp)
 
 static inline bool xdp_metalen_invalid(unsigned long metalen)
 {
-	return (metalen & (sizeof(__u32) - 1)) || (metalen > 32);
+	unsigned long meta_max;
+
+	meta_max = type_max(typeof_member(struct skb_shared_info, meta_len));
+	BUILD_BUG_ON(!__builtin_constant_p(meta_max));
+
+	return !IS_ALIGNED(metalen, sizeof(u32)) || metalen > meta_max;
 }
 
 struct xdp_attachment_info {
@@ -399,6 +404,10 @@ void xdp_attachment_setup(struct xdp_attachment_info *info,
 			   NETDEV_XDP_RX_METADATA_HASH, \
 			   bpf_xdp_metadata_rx_hash, \
 			   xmo_rx_hash) \
+	XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_VLAN_TAG, \
+			   NETDEV_XDP_RX_METADATA_VLAN_TAG, \
+			   bpf_xdp_metadata_rx_vlan_tag, \
+			   xmo_rx_vlan_tag) \
 
 enum xdp_rx_metadata {
 #define XDP_METADATA_KFUNC(name, _, __, ___) name,
@@ -427,6 +436,7 @@ enum xdp_rss_hash_type {
 	XDP_RSS_L4_UDP		= BIT(5),
 	XDP_RSS_L4_SCTP		= BIT(6),
 	XDP_RSS_L4_IPSEC	= BIT(7), /* L4 based hash include IPSEC SPI */
+	XDP_RSS_L4_ICMP		= BIT(8),
 
 	/* Second part: RSS hash type combinations used for driver HW mapping */
 	XDP_RSS_TYPE_NONE            = 0,
@@ -442,11 +452,13 @@ enum xdp_rss_hash_type {
 	XDP_RSS_TYPE_L4_IPV4_UDP     = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_UDP,
 	XDP_RSS_TYPE_L4_IPV4_SCTP    = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_SCTP,
 	XDP_RSS_TYPE_L4_IPV4_IPSEC   = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC,
+	XDP_RSS_TYPE_L4_IPV4_ICMP    = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_ICMP,
 
 	XDP_RSS_TYPE_L4_IPV6_TCP     = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_TCP,
 	XDP_RSS_TYPE_L4_IPV6_UDP     = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_UDP,
 	XDP_RSS_TYPE_L4_IPV6_SCTP    = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_SCTP,
 	XDP_RSS_TYPE_L4_IPV6_IPSEC   = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC,
+	XDP_RSS_TYPE_L4_IPV6_ICMP    = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_ICMP,
 
 	XDP_RSS_TYPE_L4_IPV6_TCP_EX  = XDP_RSS_TYPE_L4_IPV6_TCP  | XDP_RSS_L3_DYNHDR,
 	XDP_RSS_TYPE_L4_IPV6_UDP_EX  = XDP_RSS_TYPE_L4_IPV6_UDP  | XDP_RSS_L3_DYNHDR,
@@ -457,6 +469,8 @@ struct xdp_metadata_ops {
 	int	(*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp);
 	int	(*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash,
 			       enum xdp_rss_hash_type *rss_type);
+	int	(*xmo_rx_vlan_tag)(const struct xdp_md *ctx, __be16 *vlan_proto,
+				   u16 *vlan_tci);
 };
 
 #ifdef CONFIG_NET
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index f83128007fb0..3cb4dc9bd70e 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -30,6 +30,7 @@ struct xdp_umem {
 	struct user_struct *user;
 	refcount_t users;
 	u8 flags;
+	u8 tx_metadata_len;
 	bool zc;
 	struct page **pgs;
 	int id;
@@ -92,12 +93,105 @@ struct xdp_sock {
 	struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */
 };
 
+/*
+ * AF_XDP TX metadata hooks for network devices.
+ * The following hooks can be defined; unless noted otherwise, they are
+ * optional and can be filled with a null pointer.
+ *
+ * void (*tmo_request_timestamp)(void *priv)
+ *     Called when AF_XDP frame requested egress timestamp.
+ *
+ * u64 (*tmo_fill_timestamp)(void *priv)
+ *     Called when AF_XDP frame, that had requested egress timestamp,
+ *     received a completion. The hook needs to return the actual HW timestamp.
+ *
+ * void (*tmo_request_checksum)(u16 csum_start, u16 csum_offset, void *priv)
+ *     Called when AF_XDP frame requested HW checksum offload. csum_start
+ *     indicates position where checksumming should start.
+ *     csum_offset indicates position where checksum should be stored.
+ *
+ */
+struct xsk_tx_metadata_ops {
+	void	(*tmo_request_timestamp)(void *priv);
+	u64	(*tmo_fill_timestamp)(void *priv);
+	void	(*tmo_request_checksum)(u16 csum_start, u16 csum_offset, void *priv);
+};
+
 #ifdef CONFIG_XDP_SOCKETS
 
 int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
 int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp);
 void __xsk_map_flush(void);
 
+/**
+ *  xsk_tx_metadata_to_compl - Save enough relevant metadata information
+ *  to perform tx completion in the future.
+ *  @meta: pointer to AF_XDP metadata area
+ *  @compl: pointer to output struct xsk_tx_metadata_to_compl
+ *
+ *  This function should be called by the networking device when
+ *  it prepares AF_XDP egress packet. The value of @compl should be stored
+ *  and passed to xsk_tx_metadata_complete upon TX completion.
+ */
+static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta,
+					    struct xsk_tx_metadata_compl *compl)
+{
+	if (!meta)
+		return;
+
+	if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP)
+		compl->tx_timestamp = &meta->completion.tx_timestamp;
+	else
+		compl->tx_timestamp = NULL;
+}
+
+/**
+ *  xsk_tx_metadata_request - Evaluate AF_XDP TX metadata at submission
+ *  and call appropriate xsk_tx_metadata_ops operation.
+ *  @meta: pointer to AF_XDP metadata area
+ *  @ops: pointer to struct xsk_tx_metadata_ops
+ *  @priv: pointer to driver-private aread
+ *
+ *  This function should be called by the networking device when
+ *  it prepares AF_XDP egress packet.
+ */
+static inline void xsk_tx_metadata_request(const struct xsk_tx_metadata *meta,
+					   const struct xsk_tx_metadata_ops *ops,
+					   void *priv)
+{
+	if (!meta)
+		return;
+
+	if (ops->tmo_request_timestamp)
+		if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP)
+			ops->tmo_request_timestamp(priv);
+
+	if (ops->tmo_request_checksum)
+		if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM)
+			ops->tmo_request_checksum(meta->request.csum_start,
+						  meta->request.csum_offset, priv);
+}
+
+/**
+ *  xsk_tx_metadata_complete - Evaluate AF_XDP TX metadata at completion
+ *  and call appropriate xsk_tx_metadata_ops operation.
+ *  @compl: pointer to completion metadata produced from xsk_tx_metadata_to_compl
+ *  @ops: pointer to struct xsk_tx_metadata_ops
+ *  @priv: pointer to driver-private aread
+ *
+ *  This function should be called by the networking device upon
+ *  AF_XDP egress completion.
+ */
+static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl,
+					    const struct xsk_tx_metadata_ops *ops,
+					    void *priv)
+{
+	if (!compl)
+		return;
+
+	*compl->tx_timestamp = ops->tmo_fill_timestamp(priv);
+}
+
 #else
 
 static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
@@ -114,6 +208,23 @@ static inline void __xsk_map_flush(void)
 {
 }
 
+static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta,
+					    struct xsk_tx_metadata_compl *compl)
+{
+}
+
+static inline void xsk_tx_metadata_request(struct xsk_tx_metadata *meta,
+					   const struct xsk_tx_metadata_ops *ops,
+					   void *priv)
+{
+}
+
+static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl,
+					    const struct xsk_tx_metadata_ops *ops,
+					    void *priv)
+{
+}
+
 #endif /* CONFIG_XDP_SOCKETS */
 
 #if defined(CONFIG_XDP_SOCKETS) && defined(CONFIG_DEBUG_NET)
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 1f6fc8c7a84c..526c1e7f505e 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -12,6 +12,12 @@
 #define XDP_UMEM_MIN_CHUNK_SHIFT 11
 #define XDP_UMEM_MIN_CHUNK_SIZE (1 << XDP_UMEM_MIN_CHUNK_SHIFT)
 
+struct xsk_cb_desc {
+	void *src;
+	u8 off;
+	u8 bytes;
+};
+
 #ifdef CONFIG_XDP_SOCKETS
 
 void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries);
@@ -47,6 +53,12 @@ static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
 	xp_set_rxq_info(pool, rxq);
 }
 
+static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool,
+				    struct xsk_cb_desc *desc)
+{
+	xp_fill_cb(pool, desc);
+}
+
 static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool)
 {
 #ifdef CONFIG_NET_RX_BUSY_POLL
@@ -165,6 +177,30 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
 	return xp_raw_get_data(pool, addr);
 }
 
+#define XDP_TXMD_FLAGS_VALID ( \
+		XDP_TXMD_FLAGS_TIMESTAMP | \
+		XDP_TXMD_FLAGS_CHECKSUM | \
+	0)
+
+static inline bool xsk_buff_valid_tx_metadata(struct xsk_tx_metadata *meta)
+{
+	return !(meta->flags & ~XDP_TXMD_FLAGS_VALID);
+}
+
+static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr)
+{
+	struct xsk_tx_metadata *meta;
+
+	if (!pool->tx_metadata_len)
+		return NULL;
+
+	meta = xp_raw_get_data(pool, addr) - pool->tx_metadata_len;
+	if (unlikely(!xsk_buff_valid_tx_metadata(meta)))
+		return NULL; /* no way to signal the error to the user */
+
+	return meta;
+}
+
 static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool)
 {
 	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
@@ -250,6 +286,11 @@ static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
 {
 }
 
+static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool,
+				    struct xsk_cb_desc *desc)
+{
+}
+
 static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool)
 {
 	return 0;
@@ -324,6 +365,16 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
 	return NULL;
 }
 
+static inline bool xsk_buff_valid_tx_metadata(struct xsk_tx_metadata *meta)
+{
+	return false;
+}
+
+static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr)
+{
+	return NULL;
+}
+
 static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool)
 {
 }
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index c9bb0f892f55..1d107241b901 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -2190,4 +2190,13 @@ static inline int register_xfrm_interface_bpf(void)
 
 #endif
 
+#if IS_ENABLED(CONFIG_DEBUG_INFO_BTF)
+int register_xfrm_state_bpf(void);
+#else
+static inline int register_xfrm_state_bpf(void)
+{
+	return 0;
+}
+#endif
+
 #endif	/* _NET_XFRM_H */
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index b0bdff26fc88..99dd7376df6a 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -12,6 +12,7 @@
 
 struct xsk_buff_pool;
 struct xdp_rxq_info;
+struct xsk_cb_desc;
 struct xsk_queue;
 struct xdp_desc;
 struct xdp_umem;
@@ -33,6 +34,7 @@ struct xdp_buff_xsk {
 };
 
 #define XSK_CHECK_PRIV_TYPE(t) BUILD_BUG_ON(sizeof(t) > offsetofend(struct xdp_buff_xsk, cb))
+#define XSK_TX_COMPL_FITS(t) BUILD_BUG_ON(sizeof(struct xsk_tx_metadata_compl) > sizeof(t))
 
 struct xsk_dma_map {
 	dma_addr_t *dma_pages;
@@ -77,10 +79,12 @@ struct xsk_buff_pool {
 	u32 chunk_size;
 	u32 chunk_shift;
 	u32 frame_len;
+	u8 tx_metadata_len; /* inherited from umem */
 	u8 cached_need_wakeup;
 	bool uses_need_wakeup;
 	bool dma_need_sync;
 	bool unaligned;
+	bool tx_sw_csum;
 	void *addrs;
 	/* Mutual exclusion of the completion ring in the SKB mode. Two cases to protect:
 	 * NAPI TX thread and sendmsg error paths in the SKB destructor callback and when
@@ -132,6 +136,7 @@ static inline void xp_init_xskb_dma(struct xdp_buff_xsk *xskb, struct xsk_buff_p
 
 /* AF_XDP ZC drivers, via xdp_sock_buff.h */
 void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq);
+void xp_fill_cb(struct xsk_buff_pool *pool, struct xsk_cb_desc *desc);
 int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
 	       unsigned long attrs, struct page **pages, u32 nr_pages);
 void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs);
@@ -233,4 +238,9 @@ static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb)
 	return xskb->orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT);
 }
 
+static inline bool xp_tx_metadata_enabled(const struct xsk_buff_pool *pool)
+{
+	return pool->tx_metadata_len > 0;
+}
+
 #endif /* XSK_BUFF_POOL_H_ */
diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index 95896472a82b..565a85044541 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -77,6 +77,13 @@ static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter,
 {
 	__rdma_block_iter_start(biter, umem->sgt_append.sgt.sgl,
 				umem->sgt_append.sgt.nents, pgsz);
+	biter->__sg_advance = ib_umem_offset(umem) & ~(pgsz - 1);
+	biter->__sg_numblocks = ib_umem_num_dma_blocks(umem, pgsz);
+}
+
+static inline bool __rdma_umem_block_iter_next(struct ib_block_iter *biter)
+{
+	return __rdma_block_iter_next(biter) && biter->__sg_numblocks--;
 }
 
 /**
@@ -92,7 +99,7 @@ static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter,
  */
 #define rdma_umem_for_each_dma_block(umem, biter, pgsz)                        \
 	for (__rdma_umem_block_iter_start(biter, umem, pgsz);                  \
-	     __rdma_block_iter_next(biter);)
+	     __rdma_umem_block_iter_next(biter);)
 
 #ifdef CONFIG_INFINIBAND_USER_MEM
 
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index fb1a2d6b1969..b7b6b58dd348 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2850,6 +2850,7 @@ struct ib_block_iter {
 	/* internal states */
 	struct scatterlist *__sg;	/* sg holding the current aligned block */
 	dma_addr_t __dma_addr;		/* unaligned DMA address of this block */
+	size_t __sg_numblocks;		/* ib_umem_num_dma_blocks() */
 	unsigned int __sg_nents;	/* number of SG entries */
 	unsigned int __sg_advance;	/* number of bytes to advance in sg in next step */
 	unsigned int __pg_bit;		/* alignment of current block */
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 10480eb582b2..5ec1e71a09de 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -167,19 +167,25 @@ struct scsi_device {
 	 * power state for system suspend/resume (suspend to RAM and
 	 * hibernation) operations.
 	 */
-	bool manage_system_start_stop;
+	unsigned manage_system_start_stop:1;
 
 	/*
 	 * If true, let the high-level device driver (sd) manage the device
 	 * power state for runtime device suspand and resume operations.
 	 */
-	bool manage_runtime_start_stop;
+	unsigned manage_runtime_start_stop:1;
 
 	/*
 	 * If true, let the high-level device driver (sd) manage the device
 	 * power state for system shutdown (power off) operations.
 	 */
-	bool manage_shutdown;
+	unsigned manage_shutdown:1;
+
+	/*
+	 * If set and if the device is runtime suspended, ask the high-level
+	 * device driver (sd) to force a runtime resume of the device.
+	 */
+	unsigned force_runtime_start_on_system_start:1;
 
 	unsigned removable:1;
 	unsigned changed:1;	/* Data invalid due to media change */
diff --git a/include/soc/fsl/qe/qmc.h b/include/soc/fsl/qe/qmc.h
index 3c61a50d2ae2..2a333fc1ea81 100644
--- a/include/soc/fsl/qe/qmc.h
+++ b/include/soc/fsl/qe/qmc.h
@@ -9,6 +9,7 @@
 #ifndef __SOC_FSL_QMC_H__
 #define __SOC_FSL_QMC_H__
 
+#include <linux/bits.h>
 #include <linux/types.h>
 
 struct device_node;
@@ -16,9 +17,11 @@ struct device;
 struct qmc_chan;
 
 struct qmc_chan *qmc_chan_get_byphandle(struct device_node *np, const char *phandle_name);
+struct qmc_chan *qmc_chan_get_bychild(struct device_node *np);
 void qmc_chan_put(struct qmc_chan *chan);
 struct qmc_chan *devm_qmc_chan_get_byphandle(struct device *dev, struct device_node *np,
 					     const char *phandle_name);
+struct qmc_chan *devm_qmc_chan_get_bychild(struct device *dev, struct device_node *np);
 
 enum qmc_mode {
 	QMC_TRANSPARENT,
@@ -37,6 +40,16 @@ struct qmc_chan_info {
 
 int qmc_chan_get_info(struct qmc_chan *chan, struct qmc_chan_info *info);
 
+struct qmc_chan_ts_info {
+	u64 rx_ts_mask_avail;
+	u64 tx_ts_mask_avail;
+	u64 rx_ts_mask;
+	u64 tx_ts_mask;
+};
+
+int qmc_chan_get_ts_info(struct qmc_chan *chan, struct qmc_chan_ts_info *ts_info);
+int qmc_chan_set_ts_info(struct qmc_chan *chan, const struct qmc_chan_ts_info *ts_info);
+
 struct qmc_chan_param {
 	enum qmc_mode mode;
 	union {
@@ -56,8 +69,20 @@ int qmc_chan_set_param(struct qmc_chan *chan, const struct qmc_chan_param *param
 int qmc_chan_write_submit(struct qmc_chan *chan, dma_addr_t addr, size_t length,
 			  void (*complete)(void *context), void *context);
 
+/* Flags available (ORed) for read complete() flags parameter in HDLC mode.
+ * No flags are available in transparent mode and the read complete() flags
+ * parameter has no meaning in transparent mode.
+ */
+#define QMC_RX_FLAG_HDLC_LAST	BIT(11) /* Last in frame */
+#define QMC_RX_FLAG_HDLC_FIRST	BIT(10) /* First in frame */
+#define QMC_RX_FLAG_HDLC_OVF	BIT(5)  /* Data overflow */
+#define QMC_RX_FLAG_HDLC_UNA	BIT(4)  /* Unaligned (ie. bits received not multiple of 8) */
+#define QMC_RX_FLAG_HDLC_ABORT	BIT(3)  /* Received an abort sequence (seven consecutive ones) */
+#define QMC_RX_FLAG_HDLC_CRC	BIT(2)  /* CRC error */
+
 int qmc_chan_read_submit(struct qmc_chan *chan, dma_addr_t addr, size_t length,
-			 void (*complete)(void *context, size_t length),
+			 void (*complete)(void *context, size_t length,
+					  unsigned int flags),
 			 void *context);
 
 #define QMC_CHAN_READ  (1<<0)
diff --git a/include/soc/microchip/mpfs.h b/include/soc/microchip/mpfs.h
index f916dcde457f..09722f83b0ca 100644
--- a/include/soc/microchip/mpfs.h
+++ b/include/soc/microchip/mpfs.h
@@ -38,6 +38,8 @@ int mpfs_blocking_transaction(struct mpfs_sys_controller *mpfs_client, struct mp
 
 struct mpfs_sys_controller *mpfs_sys_controller_get(struct device *dev);
 
+struct mtd_info *mpfs_sys_controller_get_flash(struct mpfs_sys_controller *mpfs_client);
+
 #endif /* if IS_ENABLED(CONFIG_POLARFIRE_SOC_SYS_CTRL) */
 
 #if IS_ENABLED(CONFIG_MCHP_CLK_MPFS)
diff --git a/include/soc/tegra/mc.h b/include/soc/tegra/mc.h
index 71ae37d3bedd..af1d73a7f0cd 100644
--- a/include/soc/tegra/mc.h
+++ b/include/soc/tegra/mc.h
@@ -162,6 +162,7 @@ struct tegra_mc_ops {
 	 */
 	int (*probe)(struct tegra_mc *mc);
 	void (*remove)(struct tegra_mc *mc);
+	int (*resume)(struct tegra_mc *mc);
 	irqreturn_t (*handle_irq)(int irq, void *data);
 	int (*probe_device)(struct tegra_mc *mc, struct device *dev);
 };
diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h
index 043f8ac65dbf..68e053fe7340 100644
--- a/include/sound/cs35l41.h
+++ b/include/sound/cs35l41.h
@@ -906,6 +906,6 @@ int cs35l41_init_boost(struct device *dev, struct regmap *regmap,
 bool cs35l41_safe_reset(struct regmap *regmap, enum cs35l41_boost_type b_type);
 int cs35l41_mdsync_up(struct regmap *regmap);
 int cs35l41_global_enable(struct device *dev, struct regmap *regmap, enum cs35l41_boost_type b_type,
-			  int enable, bool firmware_running);
+			  int enable, struct cs_dsp *dsp);
 
 #endif /* __CS35L41_H */
diff --git a/include/trace/events/9p.h b/include/trace/events/9p.h
index 4dfa6d7f83ba..cd104a1343e2 100644
--- a/include/trace/events/9p.h
+++ b/include/trace/events/9p.h
@@ -178,18 +178,21 @@ TRACE_EVENT(9p_protocol_dump,
 		    __field(	void *,		clnt				)
 		    __field(	__u8,		type				)
 		    __field(	__u16,		tag				)
-		    __array(	unsigned char,	line,	P9_PROTO_DUMP_SZ	)
+		    __dynamic_array(unsigned char, line,
+				min_t(size_t, pdu->capacity, P9_PROTO_DUMP_SZ))
 		    ),
 
 	    TP_fast_assign(
 		    __entry->clnt   =  clnt;
 		    __entry->type   =  pdu->id;
 		    __entry->tag    =  pdu->tag;
-		    memcpy(__entry->line, pdu->sdata, P9_PROTO_DUMP_SZ);
+		    memcpy(__get_dynamic_array(line), pdu->sdata,
+				__get_dynamic_array_len(line));
 		    ),
-	    TP_printk("clnt %lu %s(tag = %d)\n%.3x: %16ph\n%.3x: %16ph\n",
+	    TP_printk("clnt %lu %s(tag = %d)\n%*ph\n",
 		      (unsigned long)__entry->clnt, show_9p_op(__entry->type),
-		      __entry->tag, 0, __entry->line, 16, __entry->line + 16)
+		      __entry->tag, __get_dynamic_array_len(line),
+		      __get_dynamic_array(line))
  );
 
 
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index e9d412d19dbb..5194b7e6dc8d 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -18,97 +18,6 @@
 #ifndef __AFS_DECLARE_TRACE_ENUMS_ONCE_ONLY
 #define __AFS_DECLARE_TRACE_ENUMS_ONCE_ONLY
 
-enum afs_call_trace {
-	afs_call_trace_alloc,
-	afs_call_trace_free,
-	afs_call_trace_get,
-	afs_call_trace_put,
-	afs_call_trace_wake,
-	afs_call_trace_work,
-};
-
-enum afs_server_trace {
-	afs_server_trace_alloc,
-	afs_server_trace_callback,
-	afs_server_trace_destroy,
-	afs_server_trace_free,
-	afs_server_trace_gc,
-	afs_server_trace_get_by_addr,
-	afs_server_trace_get_by_uuid,
-	afs_server_trace_get_caps,
-	afs_server_trace_get_install,
-	afs_server_trace_get_new_cbi,
-	afs_server_trace_get_probe,
-	afs_server_trace_give_up_cb,
-	afs_server_trace_purging,
-	afs_server_trace_put_call,
-	afs_server_trace_put_cbi,
-	afs_server_trace_put_find_rsq,
-	afs_server_trace_put_probe,
-	afs_server_trace_put_slist,
-	afs_server_trace_put_slist_isort,
-	afs_server_trace_put_uuid_rsq,
-	afs_server_trace_update,
-};
-
-
-enum afs_volume_trace {
-	afs_volume_trace_alloc,
-	afs_volume_trace_free,
-	afs_volume_trace_get_alloc_sbi,
-	afs_volume_trace_get_cell_insert,
-	afs_volume_trace_get_new_op,
-	afs_volume_trace_get_query_alias,
-	afs_volume_trace_put_cell_dup,
-	afs_volume_trace_put_cell_root,
-	afs_volume_trace_put_destroy_sbi,
-	afs_volume_trace_put_free_fc,
-	afs_volume_trace_put_put_op,
-	afs_volume_trace_put_query_alias,
-	afs_volume_trace_put_validate_fc,
-	afs_volume_trace_remove,
-};
-
-enum afs_cell_trace {
-	afs_cell_trace_alloc,
-	afs_cell_trace_free,
-	afs_cell_trace_get_queue_dns,
-	afs_cell_trace_get_queue_manage,
-	afs_cell_trace_get_queue_new,
-	afs_cell_trace_get_vol,
-	afs_cell_trace_insert,
-	afs_cell_trace_manage,
-	afs_cell_trace_put_candidate,
-	afs_cell_trace_put_destroy,
-	afs_cell_trace_put_queue_fail,
-	afs_cell_trace_put_queue_work,
-	afs_cell_trace_put_vol,
-	afs_cell_trace_see_source,
-	afs_cell_trace_see_ws,
-	afs_cell_trace_unuse_alias,
-	afs_cell_trace_unuse_check_alias,
-	afs_cell_trace_unuse_delete,
-	afs_cell_trace_unuse_fc,
-	afs_cell_trace_unuse_lookup,
-	afs_cell_trace_unuse_mntpt,
-	afs_cell_trace_unuse_no_pin,
-	afs_cell_trace_unuse_parse,
-	afs_cell_trace_unuse_pin,
-	afs_cell_trace_unuse_probe,
-	afs_cell_trace_unuse_sbi,
-	afs_cell_trace_unuse_ws,
-	afs_cell_trace_use_alias,
-	afs_cell_trace_use_check_alias,
-	afs_cell_trace_use_fc,
-	afs_cell_trace_use_fc_alias,
-	afs_cell_trace_use_lookup,
-	afs_cell_trace_use_mntpt,
-	afs_cell_trace_use_pin,
-	afs_cell_trace_use_probe,
-	afs_cell_trace_use_sbi,
-	afs_cell_trace_wait,
-};
-
 enum afs_fs_operation {
 	afs_FS_FetchData		= 130,	/* AFS Fetch file data */
 	afs_FS_FetchACL			= 131,	/* AFS Fetch file ACL */
@@ -202,121 +111,6 @@ enum yfs_cm_operation {
 	yfs_CB_CallBack			= 64204,
 };
 
-enum afs_edit_dir_op {
-	afs_edit_dir_create,
-	afs_edit_dir_create_error,
-	afs_edit_dir_create_inval,
-	afs_edit_dir_create_nospc,
-	afs_edit_dir_delete,
-	afs_edit_dir_delete_error,
-	afs_edit_dir_delete_inval,
-	afs_edit_dir_delete_noent,
-};
-
-enum afs_edit_dir_reason {
-	afs_edit_dir_for_create,
-	afs_edit_dir_for_link,
-	afs_edit_dir_for_mkdir,
-	afs_edit_dir_for_rename_0,
-	afs_edit_dir_for_rename_1,
-	afs_edit_dir_for_rename_2,
-	afs_edit_dir_for_rmdir,
-	afs_edit_dir_for_silly_0,
-	afs_edit_dir_for_silly_1,
-	afs_edit_dir_for_symlink,
-	afs_edit_dir_for_unlink,
-};
-
-enum afs_eproto_cause {
-	afs_eproto_bad_status,
-	afs_eproto_cb_count,
-	afs_eproto_cb_fid_count,
-	afs_eproto_cellname_len,
-	afs_eproto_file_type,
-	afs_eproto_ibulkst_cb_count,
-	afs_eproto_ibulkst_count,
-	afs_eproto_motd_len,
-	afs_eproto_offline_msg_len,
-	afs_eproto_volname_len,
-	afs_eproto_yvl_fsendpt4_len,
-	afs_eproto_yvl_fsendpt6_len,
-	afs_eproto_yvl_fsendpt_num,
-	afs_eproto_yvl_fsendpt_type,
-	afs_eproto_yvl_vlendpt4_len,
-	afs_eproto_yvl_vlendpt6_len,
-	afs_eproto_yvl_vlendpt_type,
-};
-
-enum afs_io_error {
-	afs_io_error_cm_reply,
-	afs_io_error_extract,
-	afs_io_error_fs_probe_fail,
-	afs_io_error_vl_lookup_fail,
-	afs_io_error_vl_probe_fail,
-};
-
-enum afs_file_error {
-	afs_file_error_dir_bad_magic,
-	afs_file_error_dir_big,
-	afs_file_error_dir_missing_page,
-	afs_file_error_dir_name_too_long,
-	afs_file_error_dir_over_end,
-	afs_file_error_dir_small,
-	afs_file_error_dir_unmarked_ext,
-	afs_file_error_mntpt,
-	afs_file_error_writeback_fail,
-};
-
-enum afs_flock_event {
-	afs_flock_acquired,
-	afs_flock_callback_break,
-	afs_flock_defer_unlock,
-	afs_flock_extend_fail,
-	afs_flock_fail_other,
-	afs_flock_fail_perm,
-	afs_flock_no_lockers,
-	afs_flock_release_fail,
-	afs_flock_silly_delete,
-	afs_flock_timestamp,
-	afs_flock_try_to_lock,
-	afs_flock_vfs_lock,
-	afs_flock_vfs_locking,
-	afs_flock_waited,
-	afs_flock_waiting,
-	afs_flock_work_extending,
-	afs_flock_work_retry,
-	afs_flock_work_unlocking,
-	afs_flock_would_block,
-};
-
-enum afs_flock_operation {
-	afs_flock_op_copy_lock,
-	afs_flock_op_flock,
-	afs_flock_op_grant,
-	afs_flock_op_lock,
-	afs_flock_op_release_lock,
-	afs_flock_op_return_ok,
-	afs_flock_op_return_eagain,
-	afs_flock_op_return_edeadlk,
-	afs_flock_op_return_error,
-	afs_flock_op_set_lock,
-	afs_flock_op_unlock,
-	afs_flock_op_wake,
-};
-
-enum afs_cb_break_reason {
-	afs_cb_break_no_break,
-	afs_cb_break_no_promise,
-	afs_cb_break_for_callback,
-	afs_cb_break_for_deleted,
-	afs_cb_break_for_lapsed,
-	afs_cb_break_for_s_reinit,
-	afs_cb_break_for_unlink,
-	afs_cb_break_for_v_break,
-	afs_cb_break_for_volume_callback,
-	afs_cb_break_for_zap,
-};
-
 #endif /* end __AFS_DECLARE_TRACE_ENUMS_ONCE_ONLY */
 
 /*
@@ -357,9 +151,11 @@ enum afs_cb_break_reason {
 	EM(afs_volume_trace_alloc,		"ALLOC         ") \
 	EM(afs_volume_trace_free,		"FREE          ") \
 	EM(afs_volume_trace_get_alloc_sbi,	"GET sbi-alloc ") \
+	EM(afs_volume_trace_get_callback,	"GET callback  ") \
 	EM(afs_volume_trace_get_cell_insert,	"GET cell-insrt") \
 	EM(afs_volume_trace_get_new_op,		"GET op-new    ") \
 	EM(afs_volume_trace_get_query_alias,	"GET cell-alias") \
+	EM(afs_volume_trace_put_callback,	"PUT callback  ") \
 	EM(afs_volume_trace_put_cell_dup,	"PUT cell-dup  ") \
 	EM(afs_volume_trace_put_cell_root,	"PUT cell-root ") \
 	EM(afs_volume_trace_put_destroy_sbi,	"PUT sbi-destry") \
@@ -391,6 +187,7 @@ enum afs_cb_break_reason {
 	EM(afs_cell_trace_unuse_fc,		"UNU fc    ") \
 	EM(afs_cell_trace_unuse_lookup,		"UNU lookup") \
 	EM(afs_cell_trace_unuse_mntpt,		"UNU mntpt ") \
+	EM(afs_cell_trace_unuse_no_pin,		"UNU no-pin") \
 	EM(afs_cell_trace_unuse_parse,		"UNU parse ") \
 	EM(afs_cell_trace_unuse_pin,		"UNU pin   ") \
 	EM(afs_cell_trace_unuse_probe,		"UNU probe ") \
@@ -407,6 +204,40 @@ enum afs_cb_break_reason {
 	EM(afs_cell_trace_use_sbi,		"USE sbi   ") \
 	E_(afs_cell_trace_wait,			"WAIT      ")
 
+#define afs_alist_traces \
+	EM(afs_alist_trace_alloc,		"ALLOC     ") \
+	EM(afs_alist_trace_get_estate,		"GET estate") \
+	EM(afs_alist_trace_get_vlgetcaps,	"GET vgtcap") \
+	EM(afs_alist_trace_get_vlprobe,		"GET vprobe") \
+	EM(afs_alist_trace_get_vlrotate_set,	"GET vl-rot") \
+	EM(afs_alist_trace_put_estate,		"PUT estate") \
+	EM(afs_alist_trace_put_getaddru,	"PUT GtAdrU") \
+	EM(afs_alist_trace_put_parse_empty,	"PUT p-empt") \
+	EM(afs_alist_trace_put_parse_error,	"PUT p-err ") \
+	EM(afs_alist_trace_put_server_dup,	"PUT sv-dup") \
+	EM(afs_alist_trace_put_server_oom,	"PUT sv-oom") \
+	EM(afs_alist_trace_put_server_update,	"PUT sv-upd") \
+	EM(afs_alist_trace_put_vlgetcaps,	"PUT vgtcap") \
+	EM(afs_alist_trace_put_vlprobe,		"PUT vprobe") \
+	EM(afs_alist_trace_put_vlrotate_end,	"PUT vr-end") \
+	EM(afs_alist_trace_put_vlrotate_fail,	"PUT vr-fai") \
+	EM(afs_alist_trace_put_vlrotate_next,	"PUT vr-nxt") \
+	EM(afs_alist_trace_put_vlrotate_restart,"PUT vr-rst") \
+	EM(afs_alist_trace_put_vlserver,	"PUT vlsrvr") \
+	EM(afs_alist_trace_put_vlserver_old,	"PUT vs-old") \
+	E_(afs_alist_trace_free,		"FREE      ")
+
+#define afs_estate_traces \
+	EM(afs_estate_trace_alloc_probe,	"ALLOC prob") \
+	EM(afs_estate_trace_alloc_server,	"ALLOC srvr") \
+	EM(afs_estate_trace_get_server_state,	"GET srv-st") \
+	EM(afs_estate_trace_get_getcaps,	"GET getcap") \
+	EM(afs_estate_trace_put_getcaps,	"PUT getcap") \
+	EM(afs_estate_trace_put_probe,		"PUT probe ") \
+	EM(afs_estate_trace_put_server,		"PUT server") \
+	EM(afs_estate_trace_put_server_state,	"PUT srv-st") \
+	E_(afs_estate_trace_free,		"FREE      ")
+
 #define afs_fs_operations \
 	EM(afs_FS_FetchData,			"FS.FetchData") \
 	EM(afs_FS_FetchStatus,			"FS.FetchStatus") \
@@ -604,15 +435,67 @@ enum afs_cb_break_reason {
 
 #define afs_cb_break_reasons						\
 	EM(afs_cb_break_no_break,		"no-break")		\
-	EM(afs_cb_break_no_promise,		"no-promise")		\
 	EM(afs_cb_break_for_callback,		"break-cb")		\
+	EM(afs_cb_break_for_creation_regress,	"creation-regress")	\
 	EM(afs_cb_break_for_deleted,		"break-del")		\
-	EM(afs_cb_break_for_lapsed,		"break-lapsed")		\
 	EM(afs_cb_break_for_s_reinit,		"s-reinit")		\
 	EM(afs_cb_break_for_unlink,		"break-unlink")		\
-	EM(afs_cb_break_for_v_break,		"break-v")		\
+	EM(afs_cb_break_for_update_regress,	"update-regress")	\
 	EM(afs_cb_break_for_volume_callback,	"break-v-cb")		\
-	E_(afs_cb_break_for_zap,		"break-zap")
+	EM(afs_cb_break_for_vos_release,	"break-vos-release")	\
+	E_(afs_cb_break_volume_excluded,	"vol-excluded")
+
+#define afs_rotate_traces						\
+	EM(afs_rotate_trace_aborted,		"Abortd")		\
+	EM(afs_rotate_trace_busy_sleep,		"BsySlp")		\
+	EM(afs_rotate_trace_check_vol_status,	"VolStt")		\
+	EM(afs_rotate_trace_failed,		"Failed")		\
+	EM(afs_rotate_trace_iter,		"Iter  ")		\
+	EM(afs_rotate_trace_iterate_addr,	"ItAddr")		\
+	EM(afs_rotate_trace_next_server,	"NextSv")		\
+	EM(afs_rotate_trace_no_more_servers,	"NoMore")		\
+	EM(afs_rotate_trace_nomem,		"Nomem ")		\
+	EM(afs_rotate_trace_probe_error,	"PrbErr")		\
+	EM(afs_rotate_trace_probe_fileserver,	"PrbFsv")		\
+	EM(afs_rotate_trace_probe_none,		"PrbNon")		\
+	EM(afs_rotate_trace_probe_response,	"PrbRsp")		\
+	EM(afs_rotate_trace_probe_superseded,	"PrbSup")		\
+	EM(afs_rotate_trace_restart,		"Rstart")		\
+	EM(afs_rotate_trace_retry_server,	"RtrySv")		\
+	EM(afs_rotate_trace_selected_server,	"SlctSv")		\
+	EM(afs_rotate_trace_stale_lock,		"StlLck")		\
+	EM(afs_rotate_trace_start,		"Start ")		\
+	EM(afs_rotate_trace_stop,		"Stop  ")		\
+	E_(afs_rotate_trace_stopped,		"Stoppd")
+
+/*
+ * Generate enums for tracing information.
+ */
+#ifndef __AFS_GENERATE_TRACE_ENUMS_ONCE_ONLY
+#define __AFS_GENERATE_TRACE_ENUMS_ONCE_ONLY
+
+#undef EM
+#undef E_
+#define EM(a, b) a,
+#define E_(a, b) a
+
+enum afs_alist_trace		{ afs_alist_traces } __mode(byte);
+enum afs_call_trace		{ afs_call_traces } __mode(byte);
+enum afs_cb_break_reason	{ afs_cb_break_reasons } __mode(byte);
+enum afs_cell_trace		{ afs_cell_traces } __mode(byte);
+enum afs_edit_dir_op		{ afs_edit_dir_ops } __mode(byte);
+enum afs_edit_dir_reason	{ afs_edit_dir_reasons } __mode(byte);
+enum afs_eproto_cause		{ afs_eproto_causes } __mode(byte);
+enum afs_estate_trace		{ afs_estate_traces } __mode(byte);
+enum afs_file_error		{ afs_file_errors } __mode(byte);
+enum afs_flock_event		{ afs_flock_events } __mode(byte);
+enum afs_flock_operation	{ afs_flock_operations } __mode(byte);
+enum afs_io_error		{ afs_io_errors } __mode(byte);
+enum afs_rotate_trace		{ afs_rotate_traces } __mode(byte);
+enum afs_server_trace		{ afs_server_traces } __mode(byte);
+enum afs_volume_trace		{ afs_volume_traces } __mode(byte);
+
+#endif /* end __AFS_GENERATE_TRACE_ENUMS_ONCE_ONLY */
 
 /*
  * Export enum symbols via userspace.
@@ -622,21 +505,24 @@ enum afs_cb_break_reason {
 #define EM(a, b) TRACE_DEFINE_ENUM(a);
 #define E_(a, b) TRACE_DEFINE_ENUM(a);
 
+afs_alist_traces;
 afs_call_traces;
-afs_server_traces;
+afs_cb_break_reasons;
 afs_cell_traces;
-afs_fs_operations;
-afs_vl_operations;
 afs_cm_operations;
-yfs_cm_operations;
 afs_edit_dir_ops;
 afs_edit_dir_reasons;
 afs_eproto_causes;
-afs_io_errors;
+afs_estate_traces;
 afs_file_errors;
-afs_flock_types;
 afs_flock_operations;
-afs_cb_break_reasons;
+afs_flock_types;
+afs_fs_operations;
+afs_io_errors;
+afs_rotate_traces;
+afs_server_traces;
+afs_vl_operations;
+yfs_cm_operations;
 
 /*
  * Now redefine the EM() and E_() macros to map the enums to the strings that
@@ -654,12 +540,12 @@ TRACE_EVENT(afs_receive_data,
 	    TP_ARGS(call, iter, want_more, ret),
 
 	    TP_STRUCT__entry(
-		    __field(loff_t,			remain		)
-		    __field(unsigned int,		call		)
-		    __field(enum afs_call_state,	state		)
-		    __field(unsigned short,		unmarshall	)
-		    __field(bool,			want_more	)
-		    __field(int,			ret		)
+		    __field(loff_t,			remain)
+		    __field(unsigned int,		call)
+		    __field(enum afs_call_state,	state)
+		    __field(unsigned short,		unmarshall)
+		    __field(bool,			want_more)
+		    __field(int,			ret)
 			     ),
 
 	    TP_fast_assign(
@@ -686,9 +572,9 @@ TRACE_EVENT(afs_notify_call,
 	    TP_ARGS(rxcall, call),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(enum afs_call_state,	state		)
-		    __field(unsigned short,		unmarshall	)
+		    __field(unsigned int,		call)
+		    __field(enum afs_call_state,	state)
+		    __field(unsigned short,		unmarshall)
 			     ),
 
 	    TP_fast_assign(
@@ -708,9 +594,9 @@ TRACE_EVENT(afs_cb_call,
 	    TP_ARGS(call),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(u32,			op		)
-		    __field(u16,			service_id	)
+		    __field(unsigned int,		call)
+		    __field(u32,			op)
+		    __field(u16,			service_id)
 			     ),
 
 	    TP_fast_assign(
@@ -733,11 +619,11 @@ TRACE_EVENT(afs_call,
 	    TP_ARGS(call_debug_id, op, ref, outstanding, where),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(int,			op		)
-		    __field(int,			ref		)
-		    __field(int,			outstanding	)
-		    __field(const void *,		where		)
+		    __field(unsigned int,		call)
+		    __field(int,			op)
+		    __field(int,			ref)
+		    __field(int,			outstanding)
+		    __field(const void *,		where)
 			     ),
 
 	    TP_fast_assign(
@@ -762,9 +648,9 @@ TRACE_EVENT(afs_make_fs_call,
 	    TP_ARGS(call, fid),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(enum afs_fs_operation,	op		)
-		    __field_struct(struct afs_fid,	fid		)
+		    __field(unsigned int,		call)
+		    __field(enum afs_fs_operation,	op)
+		    __field_struct(struct afs_fid,	fid)
 			     ),
 
 	    TP_fast_assign(
@@ -794,10 +680,10 @@ TRACE_EVENT(afs_make_fs_calli,
 	    TP_ARGS(call, fid, i),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(unsigned int,		i		)
-		    __field(enum afs_fs_operation,	op		)
-		    __field_struct(struct afs_fid,	fid		)
+		    __field(unsigned int,		call)
+		    __field(unsigned int,		i)
+		    __field(enum afs_fs_operation,	op)
+		    __field_struct(struct afs_fid,	fid)
 			     ),
 
 	    TP_fast_assign(
@@ -829,10 +715,10 @@ TRACE_EVENT(afs_make_fs_call1,
 	    TP_ARGS(call, fid, name),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(enum afs_fs_operation,	op		)
-		    __field_struct(struct afs_fid,	fid		)
-		    __array(char,			name, 24	)
+		    __field(unsigned int,		call)
+		    __field(enum afs_fs_operation,	op)
+		    __field_struct(struct afs_fid,	fid)
+		    __array(char,			name, 24)
 			     ),
 
 	    TP_fast_assign(
@@ -866,11 +752,11 @@ TRACE_EVENT(afs_make_fs_call2,
 	    TP_ARGS(call, fid, name, name2),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(enum afs_fs_operation,	op		)
-		    __field_struct(struct afs_fid,	fid		)
-		    __array(char,			name, 24	)
-		    __array(char,			name2, 24	)
+		    __field(unsigned int,		call)
+		    __field(enum afs_fs_operation,	op)
+		    __field_struct(struct afs_fid,	fid)
+		    __array(char,			name, 24)
+		    __array(char,			name2, 24)
 			     ),
 
 	    TP_fast_assign(
@@ -907,8 +793,8 @@ TRACE_EVENT(afs_make_vl_call,
 	    TP_ARGS(call),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(enum afs_vl_operation,	op		)
+		    __field(unsigned int,		call)
+		    __field(enum afs_vl_operation,	op)
 			     ),
 
 	    TP_fast_assign(
@@ -927,10 +813,10 @@ TRACE_EVENT(afs_call_done,
 	    TP_ARGS(call),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(struct rxrpc_call *,	rx_call		)
-		    __field(int,			ret		)
-		    __field(u32,			abort_code	)
+		    __field(unsigned int,		call)
+		    __field(struct rxrpc_call *,	rx_call)
+		    __field(int,			ret)
+		    __field(u32,			abort_code)
 			     ),
 
 	    TP_fast_assign(
@@ -953,10 +839,10 @@ TRACE_EVENT(afs_send_data,
 	    TP_ARGS(call, msg),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(unsigned int,		flags		)
-		    __field(loff_t,			offset		)
-		    __field(loff_t,			count		)
+		    __field(unsigned int,		call)
+		    __field(unsigned int,		flags)
+		    __field(loff_t,			offset)
+		    __field(loff_t,			count)
 			     ),
 
 	    TP_fast_assign(
@@ -977,10 +863,10 @@ TRACE_EVENT(afs_sent_data,
 	    TP_ARGS(call, msg, ret),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(int,			ret		)
-		    __field(loff_t,			offset		)
-		    __field(loff_t,			count		)
+		    __field(unsigned int,		call)
+		    __field(int,			ret)
+		    __field(loff_t,			offset)
+		    __field(loff_t,			count)
 			     ),
 
 	    TP_fast_assign(
@@ -1001,9 +887,9 @@ TRACE_EVENT(afs_dir_check_failed,
 	    TP_ARGS(vnode, off, i_size),
 
 	    TP_STRUCT__entry(
-		    __field(struct afs_vnode *,		vnode		)
-		    __field(loff_t,			off		)
-		    __field(loff_t,			i_size		)
+		    __field(struct afs_vnode *,		vnode)
+		    __field(loff_t,			off)
+		    __field(loff_t,			i_size)
 			     ),
 
 	    TP_fast_assign(
@@ -1022,11 +908,11 @@ TRACE_EVENT(afs_folio_dirty,
 	    TP_ARGS(vnode, where, folio),
 
 	    TP_STRUCT__entry(
-		    __field(struct afs_vnode *,		vnode		)
-		    __field(const char *,		where		)
-		    __field(pgoff_t,			index		)
-		    __field(unsigned long,		from		)
-		    __field(unsigned long,		to		)
+		    __field(struct afs_vnode *,		vnode)
+		    __field(const char *,		where)
+		    __field(pgoff_t,			index)
+		    __field(unsigned long,		from)
+		    __field(unsigned long,		to)
 			     ),
 
 	    TP_fast_assign(
@@ -1056,11 +942,11 @@ TRACE_EVENT(afs_call_state,
 	    TP_ARGS(call, from, to, ret, remote_abort),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(enum afs_call_state,	from		)
-		    __field(enum afs_call_state,	to		)
-		    __field(int,			ret		)
-		    __field(u32,			abort		)
+		    __field(unsigned int,		call)
+		    __field(enum afs_call_state,	from)
+		    __field(enum afs_call_state,	to)
+		    __field(int,			ret)
+		    __field(u32,			abort)
 			     ),
 
 	    TP_fast_assign(
@@ -1084,9 +970,9 @@ TRACE_EVENT(afs_lookup,
 	    TP_ARGS(dvnode, name, fid),
 
 	    TP_STRUCT__entry(
-		    __field_struct(struct afs_fid,	dfid		)
-		    __field_struct(struct afs_fid,	fid		)
-		    __array(char,			name, 24	)
+		    __field_struct(struct afs_fid,	dfid)
+		    __field_struct(struct afs_fid,	fid)
+		    __array(char,			name, 24)
 			     ),
 
 	    TP_fast_assign(
@@ -1116,15 +1002,15 @@ TRACE_EVENT(afs_edit_dir,
 	    TP_ARGS(dvnode, why, op, block, slot, f_vnode, f_unique, name),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		vnode		)
-		    __field(unsigned int,		unique		)
-		    __field(enum afs_edit_dir_reason,	why		)
-		    __field(enum afs_edit_dir_op,	op		)
-		    __field(unsigned int,		block		)
-		    __field(unsigned short,		slot		)
-		    __field(unsigned int,		f_vnode		)
-		    __field(unsigned int,		f_unique	)
-		    __array(char,			name, 24	)
+		    __field(unsigned int,		vnode)
+		    __field(unsigned int,		unique)
+		    __field(enum afs_edit_dir_reason,	why)
+		    __field(enum afs_edit_dir_op,	op)
+		    __field(unsigned int,		block)
+		    __field(unsigned short,		slot)
+		    __field(unsigned int,		f_vnode)
+		    __field(unsigned int,		f_unique)
+		    __array(char,			name, 24)
 			     ),
 
 	    TP_fast_assign(
@@ -1157,8 +1043,8 @@ TRACE_EVENT(afs_protocol_error,
 	    TP_ARGS(call, cause),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(enum afs_eproto_cause,	cause		)
+		    __field(unsigned int,		call)
+		    __field(enum afs_eproto_cause,	cause)
 			     ),
 
 	    TP_fast_assign(
@@ -1177,9 +1063,9 @@ TRACE_EVENT(afs_io_error,
 	    TP_ARGS(call, error, where),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,	call		)
-		    __field(int,		error		)
-		    __field(enum afs_io_error,	where		)
+		    __field(unsigned int,	call)
+		    __field(int,		error)
+		    __field(enum afs_io_error,	where)
 			     ),
 
 	    TP_fast_assign(
@@ -1199,9 +1085,9 @@ TRACE_EVENT(afs_file_error,
 	    TP_ARGS(vnode, error, where),
 
 	    TP_STRUCT__entry(
-		    __field_struct(struct afs_fid,	fid		)
-		    __field(int,			error		)
-		    __field(enum afs_file_error,	where		)
+		    __field_struct(struct afs_fid,	fid)
+		    __field(int,			error)
+		    __field(enum afs_file_error,	where)
 			     ),
 
 	    TP_fast_assign(
@@ -1222,9 +1108,9 @@ TRACE_EVENT(afs_cm_no_server,
 	    TP_ARGS(call, srx),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,			call	)
-		    __field(unsigned int,			op_id	)
-		    __field_struct(struct sockaddr_rxrpc,	srx	)
+		    __field(unsigned int,			call)
+		    __field(unsigned int,			op_id)
+		    __field_struct(struct sockaddr_rxrpc,	srx)
 			     ),
 
 	    TP_fast_assign(
@@ -1243,9 +1129,9 @@ TRACE_EVENT(afs_cm_no_server_u,
 	    TP_ARGS(call, uuid),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,			call	)
-		    __field(unsigned int,			op_id	)
-		    __field_struct(uuid_t,			uuid	)
+		    __field(unsigned int,			call)
+		    __field(unsigned int,			op_id)
+		    __field_struct(uuid_t,			uuid)
 			     ),
 
 	    TP_fast_assign(
@@ -1265,11 +1151,11 @@ TRACE_EVENT(afs_flock_ev,
 	    TP_ARGS(vnode, fl, event, error),
 
 	    TP_STRUCT__entry(
-		    __field_struct(struct afs_fid,	fid		)
-		    __field(enum afs_flock_event,	event		)
-		    __field(enum afs_lock_state,	state		)
-		    __field(int,			error		)
-		    __field(unsigned int,		debug_id	)
+		    __field_struct(struct afs_fid,	fid)
+		    __field(enum afs_flock_event,	event)
+		    __field(enum afs_lock_state,	state)
+		    __field(int,			error)
+		    __field(unsigned int,		debug_id)
 			     ),
 
 	    TP_fast_assign(
@@ -1295,13 +1181,13 @@ TRACE_EVENT(afs_flock_op,
 	    TP_ARGS(vnode, fl, op),
 
 	    TP_STRUCT__entry(
-		    __field_struct(struct afs_fid,	fid		)
-		    __field(loff_t,			from		)
-		    __field(loff_t,			len		)
-		    __field(enum afs_flock_operation,	op		)
-		    __field(unsigned char,		type		)
-		    __field(unsigned int,		flags		)
-		    __field(unsigned int,		debug_id	)
+		    __field_struct(struct afs_fid,	fid)
+		    __field(loff_t,			from)
+		    __field(loff_t,			len)
+		    __field(enum afs_flock_operation,	op)
+		    __field(unsigned char,		type)
+		    __field(unsigned int,		flags)
+		    __field(unsigned int,		debug_id)
 			     ),
 
 	    TP_fast_assign(
@@ -1328,7 +1214,7 @@ TRACE_EVENT(afs_reload_dir,
 	    TP_ARGS(vnode),
 
 	    TP_STRUCT__entry(
-		    __field_struct(struct afs_fid,	fid		)
+		    __field_struct(struct afs_fid,	fid)
 			     ),
 
 	    TP_fast_assign(
@@ -1345,8 +1231,8 @@ TRACE_EVENT(afs_silly_rename,
 	    TP_ARGS(vnode, done),
 
 	    TP_STRUCT__entry(
-		    __field_struct(struct afs_fid,	fid		)
-		    __field(bool,			done		)
+		    __field_struct(struct afs_fid,	fid)
+		    __field(bool,			done)
 			     ),
 
 	    TP_fast_assign(
@@ -1365,9 +1251,9 @@ TRACE_EVENT(afs_get_tree,
 	    TP_ARGS(cell, volume),
 
 	    TP_STRUCT__entry(
-		    __field(u64,			vid		)
-		    __array(char,			cell, 24	)
-		    __array(char,			volume, 24	)
+		    __field(u64,			vid)
+		    __array(char,			cell, 24)
+		    __array(char,			volume, 24)
 			     ),
 
 	    TP_fast_assign(
@@ -1385,6 +1271,30 @@ TRACE_EVENT(afs_get_tree,
 		      __entry->cell, __entry->volume, __entry->vid)
 	    );
 
+TRACE_EVENT(afs_cb_v_break,
+	    TP_PROTO(afs_volid_t vid, unsigned int cb_v_break,
+		     enum afs_cb_break_reason reason),
+
+	    TP_ARGS(vid, cb_v_break, reason),
+
+	    TP_STRUCT__entry(
+		    __field(afs_volid_t,		vid)
+		    __field(unsigned int,		cb_v_break)
+		    __field(enum afs_cb_break_reason,	reason)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->vid	= vid;
+		    __entry->cb_v_break	= cb_v_break;
+		    __entry->reason	= reason;
+			   ),
+
+	    TP_printk("%llx vb=%x %s",
+		      __entry->vid,
+		      __entry->cb_v_break,
+		      __print_symbolic(__entry->reason, afs_cb_break_reasons))
+	    );
+
 TRACE_EVENT(afs_cb_break,
 	    TP_PROTO(struct afs_fid *fid, unsigned int cb_break,
 		     enum afs_cb_break_reason reason, bool skipped),
@@ -1392,10 +1302,10 @@ TRACE_EVENT(afs_cb_break,
 	    TP_ARGS(fid, cb_break, reason, skipped),
 
 	    TP_STRUCT__entry(
-		    __field_struct(struct afs_fid,	fid		)
-		    __field(unsigned int,		cb_break	)
-		    __field(enum afs_cb_break_reason,	reason		)
-		    __field(bool,			skipped		)
+		    __field_struct(struct afs_fid,	fid)
+		    __field(unsigned int,		cb_break)
+		    __field(enum afs_cb_break_reason,	reason)
+		    __field(bool,			skipped)
 			     ),
 
 	    TP_fast_assign(
@@ -1418,8 +1328,8 @@ TRACE_EVENT(afs_cb_miss,
 	    TP_ARGS(fid, reason),
 
 	    TP_STRUCT__entry(
-		    __field_struct(struct afs_fid,	fid		)
-		    __field(enum afs_cb_break_reason,	reason		)
+		    __field_struct(struct afs_fid,	fid)
+		    __field(enum afs_cb_break_reason,	reason)
 			     ),
 
 	    TP_fast_assign(
@@ -1439,10 +1349,10 @@ TRACE_EVENT(afs_server,
 	    TP_ARGS(server_debug_id, ref, active, reason),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		server		)
-		    __field(int,			ref		)
-		    __field(int,			active		)
-		    __field(int,			reason		)
+		    __field(unsigned int,		server)
+		    __field(int,			ref)
+		    __field(int,			active)
+		    __field(int,			reason)
 			     ),
 
 	    TP_fast_assign(
@@ -1465,9 +1375,9 @@ TRACE_EVENT(afs_volume,
 	    TP_ARGS(vid, ref, reason),
 
 	    TP_STRUCT__entry(
-		    __field(afs_volid_t,		vid		)
-		    __field(int,			ref		)
-		    __field(enum afs_volume_trace,	reason		)
+		    __field(afs_volid_t,		vid)
+		    __field(int,			ref)
+		    __field(enum afs_volume_trace,	reason)
 			     ),
 
 	    TP_fast_assign(
@@ -1489,10 +1399,10 @@ TRACE_EVENT(afs_cell,
 	    TP_ARGS(cell_debug_id, ref, active, reason),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		cell		)
-		    __field(int,			ref		)
-		    __field(int,			active		)
-		    __field(int,			reason		)
+		    __field(unsigned int,		cell)
+		    __field(int,			ref)
+		    __field(int,			active)
+		    __field(int,			reason)
 			     ),
 
 	    TP_fast_assign(
@@ -1509,6 +1419,199 @@ TRACE_EVENT(afs_cell,
 		      __entry->active)
 	    );
 
+TRACE_EVENT(afs_alist,
+	    TP_PROTO(unsigned int alist_debug_id, int ref, enum afs_alist_trace reason),
+
+	    TP_ARGS(alist_debug_id, ref, reason),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		alist)
+		    __field(int,			ref)
+		    __field(int,			active)
+		    __field(int,			reason)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->alist = alist_debug_id;
+		    __entry->ref = ref;
+		    __entry->reason = reason;
+			   ),
+
+	    TP_printk("AL=%08x %s r=%d",
+		      __entry->alist,
+		      __print_symbolic(__entry->reason, afs_alist_traces),
+		      __entry->ref)
+	    );
+
+TRACE_EVENT(afs_estate,
+	    TP_PROTO(unsigned int server_debug_id, unsigned int estate_debug_id,
+		     int ref, enum afs_estate_trace reason),
+
+	    TP_ARGS(server_debug_id, estate_debug_id, ref, reason),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		server)
+		    __field(unsigned int,		estate)
+		    __field(int,			ref)
+		    __field(int,			active)
+		    __field(int,			reason)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->server = server_debug_id;
+		    __entry->estate = estate_debug_id;
+		    __entry->ref = ref;
+		    __entry->reason = reason;
+			   ),
+
+	    TP_printk("ES=%08x[%x] %s r=%d",
+		      __entry->server,
+		      __entry->estate,
+		      __print_symbolic(__entry->reason, afs_estate_traces),
+		      __entry->ref)
+	    );
+
+TRACE_EVENT(afs_fs_probe,
+	    TP_PROTO(struct afs_server *server, bool tx, struct afs_endpoint_state *estate,
+		     unsigned int addr_index, int error, s32 abort_code, unsigned int rtt_us),
+
+	    TP_ARGS(server, tx, estate, addr_index, error, abort_code, rtt_us),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		server)
+		    __field(unsigned int,		estate)
+		    __field(bool,			tx)
+		    __field(u16,			addr_index)
+		    __field(short,			error)
+		    __field(s32,			abort_code)
+		    __field(unsigned int,		rtt_us)
+		    __field_struct(struct sockaddr_rxrpc, srx)
+			     ),
+
+	    TP_fast_assign(
+		    struct afs_addr_list *alist = estate->addresses;
+		    __entry->server = server->debug_id;
+		    __entry->estate = estate->probe_seq;
+		    __entry->tx = tx;
+		    __entry->addr_index = addr_index;
+		    __entry->error = error;
+		    __entry->abort_code = abort_code;
+		    __entry->rtt_us = rtt_us;
+		    memcpy(&__entry->srx, rxrpc_kernel_remote_srx(alist->addrs[addr_index].peer),
+			   sizeof(__entry->srx));
+			   ),
+
+	    TP_printk("s=%08x %s pq=%x ax=%u e=%d ac=%d rtt=%d %pISpc",
+		      __entry->server, __entry->tx ? "tx" : "rx", __entry->estate,
+		      __entry->addr_index, __entry->error, __entry->abort_code, __entry->rtt_us,
+		      &__entry->srx.transport)
+	    );
+
+TRACE_EVENT(afs_vl_probe,
+	    TP_PROTO(struct afs_vlserver *server, bool tx, struct afs_addr_list *alist,
+		     unsigned int addr_index, int error, s32 abort_code, unsigned int rtt_us),
+
+	    TP_ARGS(server, tx, alist, addr_index, error, abort_code, rtt_us),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		server)
+		    __field(bool,			tx)
+		    __field(unsigned short,		flags)
+		    __field(u16,			addr_index)
+		    __field(short,			error)
+		    __field(s32,			abort_code)
+		    __field(unsigned int,		rtt_us)
+		    __field_struct(struct sockaddr_rxrpc, srx)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->server = server->debug_id;
+		    __entry->tx = tx;
+		    __entry->addr_index = addr_index;
+		    __entry->error = error;
+		    __entry->abort_code = abort_code;
+		    __entry->rtt_us = rtt_us;
+		    memcpy(&__entry->srx, rxrpc_kernel_remote_srx(alist->addrs[addr_index].peer),
+			   sizeof(__entry->srx));
+			   ),
+
+	    TP_printk("vl=%08x %s ax=%u e=%d ac=%d rtt=%d %pISpc",
+		      __entry->server, __entry->tx ? "tx" : "rx", __entry->addr_index,
+		      __entry->error, __entry->abort_code, __entry->rtt_us,
+		      &__entry->srx.transport)
+	    );
+
+TRACE_EVENT(afs_rotate,
+	    TP_PROTO(struct afs_operation *op, enum afs_rotate_trace reason, unsigned int extra),
+
+	    TP_ARGS(op, reason, extra),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		op)
+		    __field(unsigned int,		flags)
+		    __field(unsigned int,		extra)
+		    __field(unsigned short,		iteration)
+		    __field(short,			server_index)
+		    __field(short,			addr_index)
+		    __field(enum afs_rotate_trace,	reason)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->op = op->debug_id;
+		    __entry->flags = op->flags;
+		    __entry->iteration = op->nr_iterations;
+		    __entry->server_index = op->server_index;
+		    __entry->addr_index = op->addr_index;
+		    __entry->reason = reason;
+		    __entry->extra = extra;
+			   ),
+
+	    TP_printk("OP=%08x it=%02x %s fl=%x sx=%d ax=%d ext=%d",
+		      __entry->op,
+		      __entry->iteration,
+		      __print_symbolic(__entry->reason, afs_rotate_traces),
+		      __entry->flags,
+		      __entry->server_index,
+		      __entry->addr_index,
+		      __entry->extra)
+	    );
+
+TRACE_EVENT(afs_make_call,
+	    TP_PROTO(struct afs_call *call),
+
+	    TP_ARGS(call),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		call)
+		    __field(bool,			is_vl)
+		    __field(enum afs_fs_operation,	op)
+		    __field_struct(struct afs_fid,	fid)
+		    __field_struct(struct sockaddr_rxrpc, srx)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call = call->debug_id;
+		    __entry->op = call->operation_ID;
+		    __entry->fid = call->fid;
+		    memcpy(&__entry->srx, rxrpc_kernel_remote_srx(call->peer),
+			   sizeof(__entry->srx));
+		    __entry->srx.srx_service = call->service_id;
+		    __entry->is_vl = (__entry->srx.srx_service == VL_SERVICE ||
+				      __entry->srx.srx_service == YFS_VL_SERVICE);
+			   ),
+
+	    TP_printk("c=%08x %pISpc+%u %s %llx:%llx:%x",
+		      __entry->call,
+		      &__entry->srx.transport,
+		      __entry->srx.srx_service,
+		      __entry->is_vl ?
+		      __print_symbolic(__entry->op, afs_vl_operations) :
+		      __print_symbolic(__entry->op, afs_fs_operations),
+		      __entry->fid.vid,
+		      __entry->fid.vnode,
+		      __entry->fid.unique)
+	    );
+
 #endif /* _TRACE_AFS_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 279a7a0c90c0..90b0222390e5 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -21,7 +21,7 @@ struct btrfs_delayed_data_ref;
 struct btrfs_delayed_ref_head;
 struct btrfs_block_group;
 struct btrfs_free_cluster;
-struct map_lookup;
+struct btrfs_chunk_map;
 struct extent_buffer;
 struct btrfs_work;
 struct btrfs_workqueue;
@@ -265,20 +265,20 @@ DEFINE_EVENT(btrfs__inode, btrfs_inode_evict,
 	__print_symbolic_u64(type,					\
 		{ EXTENT_MAP_LAST_BYTE, "LAST_BYTE" 	},		\
 		{ EXTENT_MAP_HOLE, 	"HOLE" 		},		\
-		{ EXTENT_MAP_INLINE, 	"INLINE" 	},		\
-		{ EXTENT_MAP_DELALLOC,	"DELALLOC" 	})
+		{ EXTENT_MAP_INLINE,	"INLINE"	})
 
 #define show_map_type(type)			\
 	type, (type >= EXTENT_MAP_LAST_BYTE) ? "-" :  __show_map_type(type)
 
 #define show_map_flags(flag)						\
 	__print_flags(flag, "|",					\
-		{ (1 << EXTENT_FLAG_PINNED), 		"PINNED" 	},\
-		{ (1 << EXTENT_FLAG_COMPRESSED), 	"COMPRESSED" 	},\
-		{ (1 << EXTENT_FLAG_PREALLOC), 		"PREALLOC" 	},\
-		{ (1 << EXTENT_FLAG_LOGGING),	 	"LOGGING" 	},\
-		{ (1 << EXTENT_FLAG_FILLING),	 	"FILLING" 	},\
-		{ (1 << EXTENT_FLAG_FS_MAPPING),	"FS_MAPPING"	})
+		{ EXTENT_FLAG_PINNED,		"PINNED"	},\
+		{ EXTENT_FLAG_COMPRESS_ZLIB,	"COMPRESS_ZLIB"	},\
+		{ EXTENT_FLAG_COMPRESS_LZO,	"COMPRESS_LZO"	},\
+		{ EXTENT_FLAG_COMPRESS_ZSTD,	"COMPRESS_ZSTD"	},\
+		{ EXTENT_FLAG_PREALLOC,		"PREALLOC"	},\
+		{ EXTENT_FLAG_LOGGING,		"LOGGING"	},\
+		{ EXTENT_FLAG_FILLING,		"FILLING"	})
 
 TRACE_EVENT_CONDITION(btrfs_get_extent,
 
@@ -297,9 +297,8 @@ TRACE_EVENT_CONDITION(btrfs_get_extent,
 		__field(	u64,  orig_start	)
 		__field(	u64,  block_start	)
 		__field(	u64,  block_len		)
-		__field(	unsigned long,  flags	)
+		__field(	u32,  flags		)
 		__field(	int,  refs		)
-		__field(	unsigned int,  compress_type	)
 	),
 
 	TP_fast_assign_btrfs(root->fs_info,
@@ -312,13 +311,11 @@ TRACE_EVENT_CONDITION(btrfs_get_extent,
 		__entry->block_len	= map->block_len;
 		__entry->flags		= map->flags;
 		__entry->refs		= refcount_read(&map->refs);
-		__entry->compress_type	= map->compress_type;
 	),
 
 	TP_printk_btrfs("root=%llu(%s) ino=%llu start=%llu len=%llu "
 		  "orig_start=%llu block_start=%llu(%s) "
-		  "block_len=%llu flags=%s refs=%u "
-		  "compress_type=%u",
+		  "block_len=%llu flags=%s refs=%u",
 		  show_root_type(__entry->root_objectid),
 		  __entry->ino,
 		  __entry->start,
@@ -327,7 +324,7 @@ TRACE_EVENT_CONDITION(btrfs_get_extent,
 		  show_map_type(__entry->block_start),
 		  __entry->block_len,
 		  show_map_flags(__entry->flags),
-		  __entry->refs, __entry->compress_type)
+		  __entry->refs)
 );
 
 TRACE_EVENT(btrfs_handle_em_exist,
@@ -1061,7 +1058,7 @@ DEFINE_EVENT(btrfs_delayed_ref_head,  run_delayed_ref_head,
 DECLARE_EVENT_CLASS(btrfs__chunk,
 
 	TP_PROTO(const struct btrfs_fs_info *fs_info,
-		 const struct map_lookup *map, u64 offset, u64 size),
+		 const struct btrfs_chunk_map *map, u64 offset, u64 size),
 
 	TP_ARGS(fs_info, map, offset, size),
 
@@ -1095,7 +1092,7 @@ DECLARE_EVENT_CLASS(btrfs__chunk,
 DEFINE_EVENT(btrfs__chunk,  btrfs_chunk_alloc,
 
 	TP_PROTO(const struct btrfs_fs_info *fs_info,
-		 const struct map_lookup *map, u64 offset, u64 size),
+		 const struct btrfs_chunk_map *map, u64 offset, u64 size),
 
 	TP_ARGS(fs_info, map, offset, size)
 );
@@ -1103,7 +1100,7 @@ DEFINE_EVENT(btrfs__chunk,  btrfs_chunk_alloc,
 DEFINE_EVENT(btrfs__chunk,  btrfs_chunk_free,
 
 	TP_PROTO(const struct btrfs_fs_info *fs_info,
-		 const struct map_lookup *map, u64 offset, u64 size),
+		 const struct btrfs_chunk_map *map, u64 offset, u64 size),
 
 	TP_ARGS(fs_info, map, offset, size)
 );
@@ -2099,17 +2096,12 @@ TRACE_EVENT(btrfs_set_extent_bit,
 		__field(	unsigned,	set_bits)
 	),
 
-	TP_fast_assign_btrfs(tree->fs_info,
-		__entry->owner = tree->owner;
-		if (tree->inode) {
-			const struct btrfs_inode *inode = tree->inode;
+	TP_fast_assign_btrfs(extent_io_tree_to_fs_info(tree),
+		const struct btrfs_inode *inode = extent_io_tree_to_inode_const(tree);
 
-			__entry->ino	= btrfs_ino(inode);
-			__entry->rootid	= inode->root->root_key.objectid;
-		} else {
-			__entry->ino	= 0;
-			__entry->rootid	= 0;
-		}
+		__entry->owner		= tree->owner;
+		__entry->ino		= inode ? btrfs_ino(inode) : 0;
+		__entry->rootid		= inode ? inode->root->root_key.objectid : 0;
 		__entry->start		= start;
 		__entry->len		= len;
 		__entry->set_bits	= set_bits;
@@ -2137,17 +2129,12 @@ TRACE_EVENT(btrfs_clear_extent_bit,
 		__field(	unsigned,	clear_bits)
 	),
 
-	TP_fast_assign_btrfs(tree->fs_info,
-		__entry->owner = tree->owner;
-		if (tree->inode) {
-			const struct btrfs_inode *inode = tree->inode;
+	TP_fast_assign_btrfs(extent_io_tree_to_fs_info(tree),
+		const struct btrfs_inode *inode = extent_io_tree_to_inode_const(tree);
 
-			__entry->ino	= btrfs_ino(inode);
-			__entry->rootid	= inode->root->root_key.objectid;
-		} else {
-			__entry->ino	= 0;
-			__entry->rootid	= 0;
-		}
+		__entry->owner		= tree->owner;
+		__entry->ino		= inode ? btrfs_ino(inode) : 0;
+		__entry->rootid		= inode ? inode->root->root_key.objectid : 0;
 		__entry->start		= start;
 		__entry->len		= len;
 		__entry->clear_bits	= clear_bits;
@@ -2176,17 +2163,12 @@ TRACE_EVENT(btrfs_convert_extent_bit,
 		__field(	unsigned,	clear_bits)
 	),
 
-	TP_fast_assign_btrfs(tree->fs_info,
-		__entry->owner = tree->owner;
-		if (tree->inode) {
-			const struct btrfs_inode *inode = tree->inode;
+	TP_fast_assign_btrfs(extent_io_tree_to_fs_info(tree),
+		const struct btrfs_inode *inode = extent_io_tree_to_inode_const(tree);
 
-			__entry->ino	= btrfs_ino(inode);
-			__entry->rootid	= inode->root->root_key.objectid;
-		} else {
-			__entry->ino	= 0;
-			__entry->rootid	= 0;
-		}
+		__entry->owner		= tree->owner;
+		__entry->ino		= inode ? btrfs_ino(inode) : 0;
+		__entry->rootid		= inode ? inode->root->root_key.objectid : 0;
 		__entry->start		= start;
 		__entry->len		= len;
 		__entry->set_bits	= set_bits;
diff --git a/include/trace/events/ksm.h b/include/trace/events/ksm.h
index b5ac35c1d0e8..e728647b5d26 100644
--- a/include/trace/events/ksm.h
+++ b/include/trace/events/ksm.h
@@ -245,6 +245,39 @@ TRACE_EVENT(ksm_remove_rmap_item,
 			__entry->pfn, __entry->rmap_item, __entry->mm)
 );
 
+/**
+ * ksm_advisor - called after the advisor has run
+ *
+ * @scan_time:		scan time in seconds
+ * @pages_to_scan:	new pages_to_scan value
+ * @cpu_percent:	cpu usage in percent
+ *
+ * Allows to trace the ksm advisor.
+ */
+TRACE_EVENT(ksm_advisor,
+
+	TP_PROTO(s64 scan_time, unsigned long pages_to_scan,
+		 unsigned int cpu_percent),
+
+	TP_ARGS(scan_time, pages_to_scan, cpu_percent),
+
+	TP_STRUCT__entry(
+		__field(s64,		scan_time)
+		__field(unsigned long,	pages_to_scan)
+		__field(unsigned int,	cpu_percent)
+	),
+
+	TP_fast_assign(
+		__entry->scan_time	= scan_time;
+		__entry->pages_to_scan	= pages_to_scan;
+		__entry->cpu_percent	= cpu_percent;
+	),
+
+	TP_printk("ksm scan time %lld pages_to_scan %lu cpu percent %u",
+			__entry->scan_time, __entry->pages_to_scan,
+			__entry->cpu_percent)
+);
+
 #endif /* _TRACE_KSM_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index 718df1d9b834..110c1475c527 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -22,47 +22,37 @@
  ** Event classes
  **/
 
-DECLARE_EVENT_CLASS(rpcrdma_completion_class,
+DECLARE_EVENT_CLASS(rpcrdma_simple_cid_class,
 	TP_PROTO(
-		const struct ib_wc *wc,
 		const struct rpc_rdma_cid *cid
 	),
 
-	TP_ARGS(wc, cid),
+	TP_ARGS(cid),
 
 	TP_STRUCT__entry(
 		__field(u32, cq_id)
 		__field(int, completion_id)
-		__field(unsigned long, status)
-		__field(unsigned int, vendor_err)
 	),
 
 	TP_fast_assign(
 		__entry->cq_id = cid->ci_queue_id;
 		__entry->completion_id = cid->ci_completion_id;
-		__entry->status = wc->status;
-		if (wc->status)
-			__entry->vendor_err = wc->vendor_err;
-		else
-			__entry->vendor_err = 0;
 	),
 
-	TP_printk("cq.id=%u cid=%d status=%s (%lu/0x%x)",
-		__entry->cq_id, __entry->completion_id,
-		rdma_show_wc_status(__entry->status),
-		__entry->status, __entry->vendor_err
+	TP_printk("cq.id=%d cid=%d",
+		__entry->cq_id, __entry->completion_id
 	)
 );
 
-#define DEFINE_COMPLETION_EVENT(name)					\
-		DEFINE_EVENT(rpcrdma_completion_class, name,		\
+#define DEFINE_SIMPLE_CID_EVENT(name)					\
+		DEFINE_EVENT(rpcrdma_simple_cid_class, name,		\
 				TP_PROTO(				\
-					const struct ib_wc *wc,		\
 					const struct rpc_rdma_cid *cid	\
 				),					\
-				TP_ARGS(wc, cid))
+				TP_ARGS(cid)				\
+		)
 
-DECLARE_EVENT_CLASS(rpcrdma_send_completion_class,
+DECLARE_EVENT_CLASS(rpcrdma_completion_class,
 	TP_PROTO(
 		const struct ib_wc *wc,
 		const struct rpc_rdma_cid *cid
@@ -73,20 +63,29 @@ DECLARE_EVENT_CLASS(rpcrdma_send_completion_class,
 	TP_STRUCT__entry(
 		__field(u32, cq_id)
 		__field(int, completion_id)
+		__field(unsigned long, status)
+		__field(unsigned int, vendor_err)
 	),
 
 	TP_fast_assign(
 		__entry->cq_id = cid->ci_queue_id;
 		__entry->completion_id = cid->ci_completion_id;
+		__entry->status = wc->status;
+		if (wc->status)
+			__entry->vendor_err = wc->vendor_err;
+		else
+			__entry->vendor_err = 0;
 	),
 
-	TP_printk("cq.id=%u cid=%d",
-		__entry->cq_id, __entry->completion_id
+	TP_printk("cq.id=%u cid=%d status=%s (%lu/0x%x)",
+		__entry->cq_id, __entry->completion_id,
+		rdma_show_wc_status(__entry->status),
+		__entry->status, __entry->vendor_err
 	)
 );
 
-#define DEFINE_SEND_COMPLETION_EVENT(name)				\
-		DEFINE_EVENT(rpcrdma_send_completion_class, name,	\
+#define DEFINE_COMPLETION_EVENT(name)					\
+		DEFINE_EVENT(rpcrdma_completion_class, name,		\
 				TP_PROTO(				\
 					const struct ib_wc *wc,		\
 					const struct rpc_rdma_cid *cid	\
@@ -978,27 +977,7 @@ TRACE_EVENT(xprtrdma_post_send_err,
 	)
 );
 
-TRACE_EVENT(xprtrdma_post_recv,
-	TP_PROTO(
-		const struct rpcrdma_rep *rep
-	),
-
-	TP_ARGS(rep),
-
-	TP_STRUCT__entry(
-		__field(u32, cq_id)
-		__field(int, completion_id)
-	),
-
-	TP_fast_assign(
-		__entry->cq_id = rep->rr_cid.ci_queue_id;
-		__entry->completion_id = rep->rr_cid.ci_completion_id;
-	),
-
-	TP_printk("cq.id=%d cid=%d",
-		__entry->cq_id, __entry->completion_id
-	)
-);
+DEFINE_SIMPLE_CID_EVENT(xprtrdma_post_recv);
 
 TRACE_EVENT(xprtrdma_post_recvs,
 	TP_PROTO(
@@ -1783,29 +1762,29 @@ DEFINE_ERROR_EVENT(chunk);
 
 DECLARE_EVENT_CLASS(svcrdma_dma_map_class,
 	TP_PROTO(
-		const struct svcxprt_rdma *rdma,
+		const struct rpc_rdma_cid *cid,
 		u64 dma_addr,
 		u32 length
 	),
 
-	TP_ARGS(rdma, dma_addr, length),
+	TP_ARGS(cid, dma_addr, length),
 
 	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(int, completion_id)
 		__field(u64, dma_addr)
 		__field(u32, length)
-		__string(device, rdma->sc_cm_id->device->name)
-		__string(addr, rdma->sc_xprt.xpt_remotebuf)
 	),
 
 	TP_fast_assign(
+		__entry->cq_id = cid->ci_queue_id;
+		__entry->completion_id = cid->ci_completion_id;
 		__entry->dma_addr = dma_addr;
 		__entry->length = length;
-		__assign_str(device, rdma->sc_cm_id->device->name);
-		__assign_str(addr, rdma->sc_xprt.xpt_remotebuf);
 	),
 
-	TP_printk("addr=%s device=%s dma_addr=%llu length=%u",
-		__get_str(addr), __get_str(device),
+	TP_printk("cq.id=%u cid=%d dma_addr=%llu length=%u",
+		__entry->cq_id, __entry->completion_id,
 		__entry->dma_addr, __entry->length
 	)
 );
@@ -1813,11 +1792,12 @@ DECLARE_EVENT_CLASS(svcrdma_dma_map_class,
 #define DEFINE_SVC_DMA_EVENT(name)					\
 		DEFINE_EVENT(svcrdma_dma_map_class, svcrdma_##name,	\
 				TP_PROTO(				\
-					const struct svcxprt_rdma *rdma,\
+					const struct rpc_rdma_cid *cid, \
 					u64 dma_addr,			\
 					u32 length			\
 				),					\
-				TP_ARGS(rdma, dma_addr, length))
+				TP_ARGS(cid, dma_addr, length)		\
+		)
 
 DEFINE_SVC_DMA_EVENT(dma_map_page);
 DEFINE_SVC_DMA_EVENT(dma_map_err);
@@ -1826,33 +1806,37 @@ DEFINE_SVC_DMA_EVENT(dma_unmap_page);
 TRACE_EVENT(svcrdma_dma_map_rw_err,
 	TP_PROTO(
 		const struct svcxprt_rdma *rdma,
+		u64 offset,
+		u32 handle,
 		unsigned int nents,
 		int status
 	),
 
-	TP_ARGS(rdma, nents, status),
+	TP_ARGS(rdma, offset, handle, nents, status),
 
 	TP_STRUCT__entry(
-		__field(int, status)
+		__field(u32, cq_id)
+		__field(u32, handle)
+		__field(u64, offset)
 		__field(unsigned int, nents)
-		__string(device, rdma->sc_cm_id->device->name)
-		__string(addr, rdma->sc_xprt.xpt_remotebuf)
+		__field(int, status)
 	),
 
 	TP_fast_assign(
-		__entry->status = status;
+		__entry->cq_id = rdma->sc_sq_cq->res.id;
+		__entry->handle = handle;
+		__entry->offset = offset;
 		__entry->nents = nents;
-		__assign_str(device, rdma->sc_cm_id->device->name);
-		__assign_str(addr, rdma->sc_xprt.xpt_remotebuf);
+		__entry->status = status;
 	),
 
-	TP_printk("addr=%s device=%s nents=%u status=%d",
-		__get_str(addr), __get_str(device), __entry->nents,
-		__entry->status
+	TP_printk("cq.id=%u 0x%016llx:0x%08x nents=%u status=%d",
+		__entry->cq_id, (unsigned long long)__entry->offset,
+		__entry->handle, __entry->nents, __entry->status
 	)
 );
 
-TRACE_EVENT(svcrdma_no_rwctx_err,
+TRACE_EVENT(svcrdma_rwctx_empty,
 	TP_PROTO(
 		const struct svcxprt_rdma *rdma,
 		unsigned int num_sges
@@ -1861,79 +1845,75 @@ TRACE_EVENT(svcrdma_no_rwctx_err,
 	TP_ARGS(rdma, num_sges),
 
 	TP_STRUCT__entry(
+		__field(u32, cq_id)
 		__field(unsigned int, num_sges)
-		__string(device, rdma->sc_cm_id->device->name)
-		__string(addr, rdma->sc_xprt.xpt_remotebuf)
 	),
 
 	TP_fast_assign(
+		__entry->cq_id = rdma->sc_sq_cq->res.id;
 		__entry->num_sges = num_sges;
-		__assign_str(device, rdma->sc_cm_id->device->name);
-		__assign_str(addr, rdma->sc_xprt.xpt_remotebuf);
 	),
 
-	TP_printk("addr=%s device=%s num_sges=%d",
-		__get_str(addr), __get_str(device), __entry->num_sges
+	TP_printk("cq.id=%u num_sges=%d",
+		__entry->cq_id, __entry->num_sges
 	)
 );
 
 TRACE_EVENT(svcrdma_page_overrun_err,
 	TP_PROTO(
-		const struct svcxprt_rdma *rdma,
-		const struct svc_rqst *rqst,
+		const struct rpc_rdma_cid *cid,
 		unsigned int pageno
 	),
 
-	TP_ARGS(rdma, rqst, pageno),
+	TP_ARGS(cid, pageno),
 
 	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(int, completion_id)
 		__field(unsigned int, pageno)
-		__field(u32, xid)
-		__string(device, rdma->sc_cm_id->device->name)
-		__string(addr, rdma->sc_xprt.xpt_remotebuf)
 	),
 
 	TP_fast_assign(
+		__entry->cq_id = cid->ci_queue_id;
+		__entry->completion_id = cid->ci_completion_id;
 		__entry->pageno = pageno;
-		__entry->xid = __be32_to_cpu(rqst->rq_xid);
-		__assign_str(device, rdma->sc_cm_id->device->name);
-		__assign_str(addr, rdma->sc_xprt.xpt_remotebuf);
 	),
 
-	TP_printk("addr=%s device=%s xid=0x%08x pageno=%u", __get_str(addr),
-		__get_str(device), __entry->xid, __entry->pageno
+	TP_printk("cq.id=%u cid=%d pageno=%u",
+		__entry->cq_id, __entry->completion_id,
+		__entry->pageno
 	)
 );
 
 TRACE_EVENT(svcrdma_small_wrch_err,
 	TP_PROTO(
-		const struct svcxprt_rdma *rdma,
+		const struct rpc_rdma_cid *cid,
 		unsigned int remaining,
 		unsigned int seg_no,
 		unsigned int num_segs
 	),
 
-	TP_ARGS(rdma, remaining, seg_no, num_segs),
+	TP_ARGS(cid, remaining, seg_no, num_segs),
 
 	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(int, completion_id)
 		__field(unsigned int, remaining)
 		__field(unsigned int, seg_no)
 		__field(unsigned int, num_segs)
-		__string(device, rdma->sc_cm_id->device->name)
-		__string(addr, rdma->sc_xprt.xpt_remotebuf)
 	),
 
 	TP_fast_assign(
+		__entry->cq_id = cid->ci_queue_id;
+		__entry->completion_id = cid->ci_completion_id;
 		__entry->remaining = remaining;
 		__entry->seg_no = seg_no;
 		__entry->num_segs = num_segs;
-		__assign_str(device, rdma->sc_cm_id->device->name);
-		__assign_str(addr, rdma->sc_xprt.xpt_remotebuf);
 	),
 
-	TP_printk("addr=%s device=%s remaining=%u seg_no=%u num_segs=%u",
-		__get_str(addr), __get_str(device), __entry->remaining,
-		__entry->seg_no, __entry->num_segs
+	TP_printk("cq.id=%u cid=%d remaining=%u seg_no=%u num_segs=%u",
+		__entry->cq_id, __entry->completion_id,
+		__entry->remaining, __entry->seg_no, __entry->num_segs
 	)
 );
 
@@ -2020,31 +2000,11 @@ TRACE_EVENT(svcrdma_post_send,
 	)
 );
 
-DEFINE_SEND_COMPLETION_EVENT(svcrdma_wc_send);
+DEFINE_SIMPLE_CID_EVENT(svcrdma_wc_send);
 DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_send_flush);
 DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_send_err);
 
-TRACE_EVENT(svcrdma_post_recv,
-	TP_PROTO(
-		const struct svc_rdma_recv_ctxt *ctxt
-	),
-
-	TP_ARGS(ctxt),
-
-	TP_STRUCT__entry(
-		__field(u32, cq_id)
-		__field(int, completion_id)
-	),
-
-	TP_fast_assign(
-		__entry->cq_id = ctxt->rc_cid.ci_queue_id;
-		__entry->completion_id = ctxt->rc_cid.ci_completion_id;
-	),
-
-	TP_printk("cq.id=%d cid=%d",
-		__entry->cq_id, __entry->completion_id
-	)
-);
+DEFINE_SIMPLE_CID_EVENT(svcrdma_post_recv);
 
 DEFINE_RECEIVE_SUCCESS_EVENT(svcrdma_wc_recv);
 DEFINE_RECEIVE_FLUSH_EVENT(svcrdma_wc_recv_flush);
@@ -2152,8 +2112,9 @@ TRACE_EVENT(svcrdma_wc_read,
 
 DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_read_flush);
 DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_read_err);
+DEFINE_SIMPLE_CID_EVENT(svcrdma_read_finished);
 
-DEFINE_SEND_COMPLETION_EVENT(svcrdma_wc_write);
+DEFINE_SIMPLE_CID_EVENT(svcrdma_wc_write);
 DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_write_flush);
 DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_write_err);
 
@@ -2184,65 +2145,74 @@ TRACE_EVENT(svcrdma_qp_error,
 	)
 );
 
-DECLARE_EVENT_CLASS(svcrdma_sendqueue_event,
+DECLARE_EVENT_CLASS(svcrdma_sendqueue_class,
 	TP_PROTO(
-		const struct svcxprt_rdma *rdma
+		const struct svcxprt_rdma *rdma,
+		const struct rpc_rdma_cid *cid
 	),
 
-	TP_ARGS(rdma),
+	TP_ARGS(rdma, cid),
 
 	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(int, completion_id)
 		__field(int, avail)
 		__field(int, depth)
-		__string(addr, rdma->sc_xprt.xpt_remotebuf)
 	),
 
 	TP_fast_assign(
+		__entry->cq_id = cid->ci_queue_id;
+		__entry->completion_id = cid->ci_completion_id;
 		__entry->avail = atomic_read(&rdma->sc_sq_avail);
 		__entry->depth = rdma->sc_sq_depth;
-		__assign_str(addr, rdma->sc_xprt.xpt_remotebuf);
 	),
 
-	TP_printk("addr=%s sc_sq_avail=%d/%d",
-		__get_str(addr), __entry->avail, __entry->depth
+	TP_printk("cq.id=%u cid=%d sc_sq_avail=%d/%d",
+		__entry->cq_id, __entry->completion_id,
+		__entry->avail, __entry->depth
 	)
 );
 
 #define DEFINE_SQ_EVENT(name)						\
-		DEFINE_EVENT(svcrdma_sendqueue_event, svcrdma_sq_##name,\
-				TP_PROTO(				\
-					const struct svcxprt_rdma *rdma \
-				),					\
-				TP_ARGS(rdma))
+		DEFINE_EVENT(svcrdma_sendqueue_class, name,		\
+			TP_PROTO(					\
+				const struct svcxprt_rdma *rdma,	\
+				const struct rpc_rdma_cid *cid		\
+			),						\
+			TP_ARGS(rdma, cid)				\
+		)
 
-DEFINE_SQ_EVENT(full);
-DEFINE_SQ_EVENT(retry);
+DEFINE_SQ_EVENT(svcrdma_sq_full);
+DEFINE_SQ_EVENT(svcrdma_sq_retry);
 
 TRACE_EVENT(svcrdma_sq_post_err,
 	TP_PROTO(
 		const struct svcxprt_rdma *rdma,
+		const struct rpc_rdma_cid *cid,
 		int status
 	),
 
-	TP_ARGS(rdma, status),
+	TP_ARGS(rdma, cid, status),
 
 	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(int, completion_id)
 		__field(int, avail)
 		__field(int, depth)
 		__field(int, status)
-		__string(addr, rdma->sc_xprt.xpt_remotebuf)
 	),
 
 	TP_fast_assign(
+		__entry->cq_id = cid->ci_queue_id;
+		__entry->completion_id = cid->ci_completion_id;
 		__entry->avail = atomic_read(&rdma->sc_sq_avail);
 		__entry->depth = rdma->sc_sq_depth;
 		__entry->status = status;
-		__assign_str(addr, rdma->sc_xprt.xpt_remotebuf);
 	),
 
-	TP_printk("addr=%s sc_sq_avail=%d/%d status=%d",
-		__get_str(addr), __entry->avail, __entry->depth,
-		__entry->status
+	TP_printk("cq.id=%u cid=%d sc_sq_avail=%d/%d status=%d",
+		__entry->cq_id, __entry->completion_id,
+		__entry->avail, __entry->depth, __entry->status
 	)
 );
 
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 4c53a5ef6257..4c1ef7b3705c 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -178,7 +178,9 @@
 #define rxrpc_peer_traces \
 	EM(rxrpc_peer_free,			"FREE        ") \
 	EM(rxrpc_peer_get_accept,		"GET accept  ") \
+	EM(rxrpc_peer_get_application,		"GET app     ") \
 	EM(rxrpc_peer_get_bundle,		"GET bundle  ") \
+	EM(rxrpc_peer_get_call,			"GET call    ") \
 	EM(rxrpc_peer_get_client_conn,		"GET cln-conn") \
 	EM(rxrpc_peer_get_input,		"GET input   ") \
 	EM(rxrpc_peer_get_input_error,		"GET inpt-err") \
@@ -187,6 +189,7 @@
 	EM(rxrpc_peer_get_service_conn,		"GET srv-conn") \
 	EM(rxrpc_peer_new_client,		"NEW client  ") \
 	EM(rxrpc_peer_new_prealloc,		"NEW prealloc") \
+	EM(rxrpc_peer_put_application,		"PUT app     ") \
 	EM(rxrpc_peer_put_bundle,		"PUT bundle  ") \
 	EM(rxrpc_peer_put_call,			"PUT call    ") \
 	EM(rxrpc_peer_put_conn,			"PUT conn    ") \
@@ -328,7 +331,7 @@
 	E_(rxrpc_rtt_tx_ping,			"PING")
 
 #define rxrpc_rtt_rx_traces \
-	EM(rxrpc_rtt_rx_cancel,			"CNCL") \
+	EM(rxrpc_rtt_rx_other_ack,		"OACK") \
 	EM(rxrpc_rtt_rx_obsolete,		"OBSL") \
 	EM(rxrpc_rtt_rx_lost,			"LOST") \
 	EM(rxrpc_rtt_rx_ping_response,		"PONG") \
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 6188ad0d9e0d..dbb01b4b7451 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -493,33 +493,30 @@ DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_blocked,
  */
 DECLARE_EVENT_CLASS(sched_stat_runtime,
 
-	TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime),
+	TP_PROTO(struct task_struct *tsk, u64 runtime),
 
-	TP_ARGS(tsk, __perf_count(runtime), vruntime),
+	TP_ARGS(tsk, __perf_count(runtime)),
 
 	TP_STRUCT__entry(
 		__array( char,	comm,	TASK_COMM_LEN	)
 		__field( pid_t,	pid			)
 		__field( u64,	runtime			)
-		__field( u64,	vruntime			)
 	),
 
 	TP_fast_assign(
 		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
 		__entry->pid		= tsk->pid;
 		__entry->runtime	= runtime;
-		__entry->vruntime	= vruntime;
 	),
 
-	TP_printk("comm=%s pid=%d runtime=%Lu [ns] vruntime=%Lu [ns]",
+	TP_printk("comm=%s pid=%d runtime=%Lu [ns]",
 			__entry->comm, __entry->pid,
-			(unsigned long long)__entry->runtime,
-			(unsigned long long)__entry->vruntime)
+			(unsigned long long)__entry->runtime)
 );
 
 DEFINE_EVENT(sched_stat_runtime, sched_stat_runtime,
-	     TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime),
-	     TP_ARGS(tsk, runtime, vruntime));
+	     TP_PROTO(struct task_struct *tsk, u64 runtime),
+	     TP_ARGS(tsk, runtime));
 
 /*
  * Tracepoint for showing priority inheritance modifying a tasks
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 337c90787fb1..cdd3a45e6003 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1675,7 +1675,6 @@ DEFINE_SVCXDRBUF_EVENT(sendto);
 	svc_rqst_flag(LOCAL)						\
 	svc_rqst_flag(USEDEFERRAL)					\
 	svc_rqst_flag(DROPME)						\
-	svc_rqst_flag(SPLICE_OK)					\
 	svc_rqst_flag(VICTIM)						\
 	svc_rqst_flag_end(DATA)
 
diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
index b4bc2828fa09..1ef58a04fc57 100644
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -46,22 +46,21 @@ DEFINE_EVENT(timer_class, timer_init,
 
 /**
  * timer_start - called when the timer is started
- * @timer:	pointer to struct timer_list
- * @expires:	the timers expiry time
- * @flags:	the timers flags
+ * @timer:		pointer to struct timer_list
+ * @bucket_expiry:	the bucket expiry time
  */
 TRACE_EVENT(timer_start,
 
 	TP_PROTO(struct timer_list *timer,
-		unsigned long expires,
-		unsigned int flags),
+		unsigned long bucket_expiry),
 
-	TP_ARGS(timer, expires, flags),
+	TP_ARGS(timer, bucket_expiry),
 
 	TP_STRUCT__entry(
 		__field( void *,	timer		)
 		__field( void *,	function	)
 		__field( unsigned long,	expires		)
+		__field( unsigned long,	bucket_expiry	)
 		__field( unsigned long,	now		)
 		__field( unsigned int,	flags		)
 	),
@@ -69,15 +68,16 @@ TRACE_EVENT(timer_start,
 	TP_fast_assign(
 		__entry->timer		= timer;
 		__entry->function	= timer->function;
-		__entry->expires	= expires;
+		__entry->expires	= timer->expires;
+		__entry->bucket_expiry	= bucket_expiry;
 		__entry->now		= jiffies;
-		__entry->flags		= flags;
+		__entry->flags		= timer->flags;
 	),
 
-	TP_printk("timer=%p function=%ps expires=%lu [timeout=%ld] cpu=%u idx=%u flags=%s",
+	TP_printk("timer=%p function=%ps expires=%lu [timeout=%ld] bucket_expiry=%lu cpu=%u idx=%u flags=%s",
 		  __entry->timer, __entry->function, __entry->expires,
 		  (long)__entry->expires - __entry->now,
-		  __entry->flags & TIMER_CPUMASK,
+		  __entry->bucket_expiry, __entry->flags & TIMER_CPUMASK,
 		  __entry->flags >> TIMER_ARRAYSHIFT,
 		  decode_timer_flags(__entry->flags & TIMER_TRACE_FLAGMASK))
 );
@@ -142,6 +142,26 @@ DEFINE_EVENT(timer_class, timer_cancel,
 	TP_ARGS(timer)
 );
 
+TRACE_EVENT(timer_base_idle,
+
+	TP_PROTO(bool is_idle, unsigned int cpu),
+
+	TP_ARGS(is_idle, cpu),
+
+	TP_STRUCT__entry(
+		__field( bool,		is_idle	)
+		__field( unsigned int,	cpu	)
+	),
+
+	TP_fast_assign(
+		__entry->is_idle	= is_idle;
+		__entry->cpu		= cpu;
+	),
+
+	TP_printk("is_idle=%d cpu=%d",
+		  __entry->is_idle, __entry->cpu)
+);
+
 #define decode_clockid(type)						\
 	__print_symbolic(type,						\
 		{ CLOCK_REALTIME,	"CLOCK_REALTIME"	},	\
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 756b013fb832..75f00965ab15 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -829,8 +829,21 @@ __SYSCALL(__NR_futex_wait, sys_futex_wait)
 #define __NR_futex_requeue 456
 __SYSCALL(__NR_futex_requeue, sys_futex_requeue)
 
+#define __NR_statmount   457
+__SYSCALL(__NR_statmount, sys_statmount)
+
+#define __NR_listmount   458
+__SYSCALL(__NR_listmount, sys_listmount)
+
+#define __NR_lsm_get_self_attr 459
+__SYSCALL(__NR_lsm_get_self_attr, sys_lsm_get_self_attr)
+#define __NR_lsm_set_self_attr 460
+__SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr)
+#define __NR_lsm_list_modules 461
+__SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules)
+
 #undef __NR_syscalls
-#define __NR_syscalls 457
+#define __NR_syscalls 462
 
 /*
  * 32 bit systems traditionally used different
diff --git a/include/uapi/linux/batadv_packet.h b/include/uapi/linux/batadv_packet.h
index 9204e4494b25..6e25753015df 100644
--- a/include/uapi/linux/batadv_packet.h
+++ b/include/uapi/linux/batadv_packet.h
@@ -116,6 +116,9 @@ enum batadv_icmp_packettype {
  * only need routable IPv4 multicast packets we signed up for explicitly
  * @BATADV_MCAST_WANT_NO_RTR6: we have no IPv6 multicast router and therefore
  * only need routable IPv6 multicast packets we signed up for explicitly
+ * @BATADV_MCAST_HAVE_MC_PTYPE_CAPA: we can parse, receive and forward
+ * batman-adv multicast packets with a multicast tracker TVLV. And all our
+ * hard interfaces have an MTU of at least 1280 bytes.
  */
 enum batadv_mcast_flags {
 	BATADV_MCAST_WANT_ALL_UNSNOOPABLES	= 1UL << 0,
@@ -123,6 +126,7 @@ enum batadv_mcast_flags {
 	BATADV_MCAST_WANT_ALL_IPV6		= 1UL << 2,
 	BATADV_MCAST_WANT_NO_RTR4		= 1UL << 3,
 	BATADV_MCAST_WANT_NO_RTR6		= 1UL << 4,
+	BATADV_MCAST_HAVE_MC_PTYPE_CAPA		= 1UL << 5,
 };
 
 /* tt data subtypes */
@@ -174,14 +178,16 @@ enum batadv_bla_claimframe {
  * @BATADV_TVLV_TT: translation table tvlv
  * @BATADV_TVLV_ROAM: roaming advertisement tvlv
  * @BATADV_TVLV_MCAST: multicast capability tvlv
+ * @BATADV_TVLV_MCAST_TRACKER: multicast tracker tvlv
  */
 enum batadv_tvlv_type {
-	BATADV_TVLV_GW		= 0x01,
-	BATADV_TVLV_DAT		= 0x02,
-	BATADV_TVLV_NC		= 0x03,
-	BATADV_TVLV_TT		= 0x04,
-	BATADV_TVLV_ROAM	= 0x05,
-	BATADV_TVLV_MCAST	= 0x06,
+	BATADV_TVLV_GW			= 0x01,
+	BATADV_TVLV_DAT			= 0x02,
+	BATADV_TVLV_NC			= 0x03,
+	BATADV_TVLV_TT			= 0x04,
+	BATADV_TVLV_ROAM		= 0x05,
+	BATADV_TVLV_MCAST		= 0x06,
+	BATADV_TVLV_MCAST_TRACKER	= 0x07,
 };
 
 #pragma pack(2)
@@ -488,6 +494,25 @@ struct batadv_bcast_packet {
 };
 
 /**
+ * struct batadv_mcast_packet - multicast packet for network payload
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the general header
+ * @ttl: time to live for this packet, part of the general header
+ * @reserved: reserved byte for alignment
+ * @tvlv_len: length of the appended tvlv buffer (in bytes)
+ */
+struct batadv_mcast_packet {
+	__u8 packet_type;
+	__u8 version;
+	__u8 ttl;
+	__u8 reserved;
+	__be16 tvlv_len;
+	/* "4 bytes boundary + 2 bytes" long to make the payload after the
+	 * following ethernet header again 4 bytes boundary aligned
+	 */
+};
+
+/**
  * struct batadv_coded_packet - network coded packet
  * @packet_type: batman-adv packet type, part of the general header
  * @version: batman-adv protocol version, part of the general header
@@ -628,6 +653,14 @@ struct batadv_tvlv_mcast_data {
 	__u8 reserved[3];
 };
 
+/**
+ * struct batadv_tvlv_mcast_tracker - payload of a multicast tracker tvlv
+ * @num_dests: number of subsequent destination originator MAC addresses
+ */
+struct batadv_tvlv_mcast_tracker {
+	__be16	num_dests;
+};
+
 #pragma pack()
 
 #endif /* _UAPI_LINUX_BATADV_PACKET_H_ */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0f6cdf52b1da..754e68ca8744 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1074,9 +1074,11 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_TCX = 11,
 	BPF_LINK_TYPE_UPROBE_MULTI = 12,
 	BPF_LINK_TYPE_NETKIT = 13,
-	MAX_BPF_LINK_TYPE,
+	__MAX_BPF_LINK_TYPE,
 };
 
+#define MAX_BPF_LINK_TYPE __MAX_BPF_LINK_TYPE
+
 enum bpf_perf_event_type {
 	BPF_PERF_EVENT_UNSPEC = 0,
 	BPF_PERF_EVENT_UPROBE = 1,
@@ -1200,6 +1202,9 @@ enum bpf_perf_event_type {
  */
 #define BPF_F_XDP_DEV_BOUND_ONLY	(1U << 6)
 
+/* The verifier internal test flag. Behavior is undefined */
+#define BPF_F_TEST_REG_INVARIANTS	(1U << 7)
+
 /* link_create.kprobe_multi.flags used in LINK_CREATE command for
  * BPF_TRACE_KPROBE_MULTI attach type to create return probe.
  */
@@ -4517,6 +4522,8 @@ union bpf_attr {
  * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags)
  *	Description
  *		Return a user or a kernel stack in bpf program provided buffer.
+ *		Note: the user stack will only be populated if the *task* is
+ *		the current task; all other tasks will return -EOPNOTSUPP.
  *		To achieve this, the helper needs *task*, which is a valid
  *		pointer to **struct task_struct**. To store the stacktrace, the
  *		bpf program provides *buf* with a nonnegative *size*.
@@ -4528,6 +4535,7 @@ union bpf_attr {
  *
  *		**BPF_F_USER_STACK**
  *			Collect a user space stack instead of a kernel stack.
+ *			The *task* must be the current task.
  *		**BPF_F_USER_BUILD_ID**
  *			Collect buildid+offset instead of ips for user stack,
  *			only valid if **BPF_F_USER_STACK** is also specified.
@@ -6557,6 +6565,16 @@ struct bpf_link_info {
 			__u64 missed;
 		} kprobe_multi;
 		struct {
+			__aligned_u64 path;
+			__aligned_u64 offsets;
+			__aligned_u64 ref_ctr_offsets;
+			__aligned_u64 cookies;
+			__u32 path_size; /* in/out: real path size on success, including zero byte */
+			__u32 count; /* in/out: uprobe_multi offsets/ref_ctr_offsets/cookies count */
+			__u32 flags;
+			__u32 pid;
+		} uprobe_multi;
+		struct {
 			__u32 type; /* enum bpf_perf_event_type */
 			__u32 :32;
 			union {
@@ -6886,6 +6904,7 @@ enum {
 	BPF_TCP_LISTEN,
 	BPF_TCP_CLOSING,	/* Now a valid state */
 	BPF_TCP_NEW_SYN_RECV,
+	BPF_TCP_BOUND_INACTIVE,
 
 	BPF_TCP_MAX_STATES	/* Leave at the end! */
 };
@@ -7151,40 +7170,31 @@ struct bpf_spin_lock {
 };
 
 struct bpf_timer {
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[2];
 } __attribute__((aligned(8)));
 
 struct bpf_dynptr {
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[2];
 } __attribute__((aligned(8)));
 
 struct bpf_list_head {
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[2];
 } __attribute__((aligned(8)));
 
 struct bpf_list_node {
-	__u64 :64;
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[3];
 } __attribute__((aligned(8)));
 
 struct bpf_rb_root {
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[2];
 } __attribute__((aligned(8)));
 
 struct bpf_rb_node {
-	__u64 :64;
-	__u64 :64;
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[4];
 } __attribute__((aligned(8)));
 
 struct bpf_refcount {
-	__u32 :32;
+	__u32 __opaque[1];
 } __attribute__((aligned(4)));
 
 struct bpf_sysctl {
diff --git a/include/uapi/linux/bpfilter.h b/include/uapi/linux/bpfilter.h
deleted file mode 100644
index cbc1f5813f50..000000000000
--- a/include/uapi/linux/bpfilter.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _UAPI_LINUX_BPFILTER_H
-#define _UAPI_LINUX_BPFILTER_H
-
-#include <linux/if.h>
-
-enum {
-	BPFILTER_IPT_SO_SET_REPLACE = 64,
-	BPFILTER_IPT_SO_SET_ADD_COUNTERS = 65,
-	BPFILTER_IPT_SET_MAX,
-};
-
-enum {
-	BPFILTER_IPT_SO_GET_INFO = 64,
-	BPFILTER_IPT_SO_GET_ENTRIES = 65,
-	BPFILTER_IPT_SO_GET_REVISION_MATCH = 66,
-	BPFILTER_IPT_SO_GET_REVISION_TARGET = 67,
-	BPFILTER_IPT_GET_MAX,
-};
-
-#endif /* _UAPI_LINUX_BPFILTER_H */
diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h
index c25fc9614594..d24e8e121507 100644
--- a/include/uapi/linux/btrfs_tree.h
+++ b/include/uapi/linux/btrfs_tree.h
@@ -219,6 +219,22 @@
  */
 #define BTRFS_METADATA_ITEM_KEY	169
 
+/*
+ * Special inline ref key which stores the id of the subvolume which originally
+ * created the extent. This subvolume owns the extent permanently from the
+ * perspective of simple quotas. Needed to know which subvolume to free quota
+ * usage from when the extent is deleted.
+ *
+ * Stored as an inline ref rather to avoid wasting space on a separate item on
+ * top of the existing extent item. However, unlike the other inline refs,
+ * there is one one owner ref per extent rather than one per extent.
+ *
+ * Because of this, it goes at the front of the list of inline refs, and thus
+ * must have a lower type value than any other inline ref type (to satisfy the
+ * disk format rule that inline refs have non-decreasing type).
+ */
+#define BTRFS_EXTENT_OWNER_REF_KEY	172
+
 #define BTRFS_TREE_BLOCK_REF_KEY	176
 
 #define BTRFS_EXTENT_DATA_REF_KEY	178
@@ -234,14 +250,6 @@
 #define BTRFS_SHARED_DATA_REF_KEY	184
 
 /*
- * Special inline ref key which stores the id of the subvolume which originally
- * created the extent. This subvolume owns the extent permanently from the
- * perspective of simple quotas. Needed to know which subvolume to free quota
- * usage from when the extent is deleted.
- */
-#define BTRFS_EXTENT_OWNER_REF_KEY	188
-
-/*
  * block groups give us hints into the extent allocation trees.  Which
  * blocks are free etc etc
  */
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index b3c8383d342d..130cae0d3e20 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -139,6 +139,8 @@ enum devlink_command {
 	DEVLINK_CMD_SELFTESTS_GET,	/* can dump */
 	DEVLINK_CMD_SELFTESTS_RUN,
 
+	DEVLINK_CMD_NOTIFY_FILTER_SET,
+
 	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
 	DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
diff --git a/include/uapi/linux/dpll.h b/include/uapi/linux/dpll.h
index 715a491d2727..b4e947f9bfbc 100644
--- a/include/uapi/linux/dpll.h
+++ b/include/uapi/linux/dpll.h
@@ -179,6 +179,7 @@ enum dpll_a_pin {
 	DPLL_A_PIN_PHASE_ADJUST_MAX,
 	DPLL_A_PIN_PHASE_ADJUST,
 	DPLL_A_PIN_PHASE_OFFSET,
+	DPLL_A_PIN_FRACTIONAL_FREQUENCY_OFFSET,
 
 	__DPLL_A_PIN_MAX,
 	DPLL_A_PIN_MAX = (__DPLL_A_PIN_MAX - 1)
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index f7fba0dc87e5..06ef6b78b7de 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1266,6 +1266,8 @@ struct ethtool_rxfh_indir {
  *	hardware hash key.
  * @hfunc: Defines the current RSS hash function used by HW (or to be set to).
  *	Valid values are one of the %ETH_RSS_HASH_*.
+ * @input_xfrm: Defines how the input data is transformed. Valid values are one
+ *	of %RXH_XFRM_*.
  * @rsvd8: Reserved for future use; see the note on reserved space.
  * @rsvd32: Reserved for future use; see the note on reserved space.
  * @rss_config: RX ring/queue index for each hash value i.e., indirection table
@@ -1285,7 +1287,8 @@ struct ethtool_rxfh {
 	__u32   indir_size;
 	__u32   key_size;
 	__u8	hfunc;
-	__u8	rsvd8[3];
+	__u8	input_xfrm;
+	__u8	rsvd8[2];
 	__u32	rsvd32;
 	__u32   rss_config[];
 };
@@ -1992,6 +1995,15 @@ static inline int ethtool_validate_duplex(__u8 duplex)
 
 #define WOL_MODE_COUNT		8
 
+/* RSS hash function data
+ * XOR the corresponding source and destination fields of each specified
+ * protocol. Both copies of the XOR'ed fields are fed into the RSS and RXHASH
+ * calculation. Note that this XORing reduces the input set entropy and could
+ * be exploited to reduce the RSS queue spread.
+ */
+#define	RXH_XFRM_SYM_XOR	(1 << 0)
+#define	RXH_XFRM_NO_CHANGE	0xff
+
 /* L2-L4 network traffic flow types */
 #define	TCP_V4_FLOW	0x01	/* hash or spec (tcp_ip4_spec) */
 #define	UDP_V4_FLOW	0x02	/* hash or spec (udp_ip4_spec) */
@@ -2128,18 +2140,6 @@ enum ethtool_reset_flags {
  *	refused. For drivers: ignore this field (use kernel's
  *	__ETHTOOL_LINK_MODE_MASK_NBITS instead), any change to it will
  *	be overwritten by kernel.
- * @supported: Bitmap with each bit meaning given by
- *	%ethtool_link_mode_bit_indices for the link modes, physical
- *	connectors and other link features for which the interface
- *	supports autonegotiation or auto-detection.  Read-only.
- * @advertising: Bitmap with each bit meaning given by
- *	%ethtool_link_mode_bit_indices for the link modes, physical
- *	connectors and other link features that are advertised through
- *	autonegotiation or enabled for auto-detection.
- * @lp_advertising: Bitmap with each bit meaning given by
- *	%ethtool_link_mode_bit_indices for the link modes, and other
- *	link features that the link partner advertised through
- *	autonegotiation; 0 if unknown or not applicable.  Read-only.
  * @transceiver: Used to distinguish different possible PHY types,
  *	reported consistently by PHYLIB.  Read-only.
  * @master_slave_cfg: Master/slave port mode.
@@ -2181,6 +2181,21 @@ enum ethtool_reset_flags {
  * %set_link_ksettings() should validate all fields other than @cmd
  * and @link_mode_masks_nwords that are not described as read-only or
  * deprecated, and must ignore all fields described as read-only.
+ *
+ * @link_mode_masks is divided into three bitfields, each of length
+ * @link_mode_masks_nwords:
+ * - supported: Bitmap with each bit meaning given by
+ *	%ethtool_link_mode_bit_indices for the link modes, physical
+ *	connectors and other link features for which the interface
+ *	supports autonegotiation or auto-detection.  Read-only.
+ * - advertising: Bitmap with each bit meaning given by
+ *	%ethtool_link_mode_bit_indices for the link modes, physical
+ *	connectors and other link features that are advertised through
+ *	autonegotiation or enabled for auto-detection.
+ * - lp_advertising: Bitmap with each bit meaning given by
+ *	%ethtool_link_mode_bit_indices for the link modes, and other
+ *	link features that the link partner advertised through
+ *	autonegotiation; 0 if unknown or not applicable.  Read-only.
  */
 struct ethtool_link_settings {
 	__u32	cmd;
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 73e2c10dc2cc..3f89074aa06c 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -908,6 +908,7 @@ enum {
 	ETHTOOL_A_RSS_HFUNC,		/* u32 */
 	ETHTOOL_A_RSS_INDIR,		/* binary */
 	ETHTOOL_A_RSS_HKEY,		/* binary */
+	ETHTOOL_A_RSS_INPUT_XFRM,	/* u32 */
 
 	__ETHTOOL_A_RSS_CNT,
 	ETHTOOL_A_RSS_MAX = (__ETHTOOL_A_RSS_CNT - 1),
diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index 6c80f96049bd..282e90aeb163 100644
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -116,5 +116,8 @@
 #define AT_HANDLE_FID		AT_REMOVEDIR	/* file handle is needed to
 					compare object identity and may not
 					be usable to open_by_handle_at(2) */
+#if defined(__KERNEL__)
+#define AT_GETATTR_NOSEC	0x80000000
+#endif
 
 #endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index da43810b7485..48ad69f7722e 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -316,6 +316,7 @@ typedef int __bitwise __kernel_rwf_t;
 #define PAGE_IS_SWAPPED		(1 << 4)
 #define PAGE_IS_PFNZERO		(1 << 5)
 #define PAGE_IS_HUGE		(1 << 6)
+#define PAGE_IS_SOFT_DIRTY	(1 << 7)
 
 /*
  * struct page_region - Page region with flags
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index db92a7202b34..e7418d15fe39 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -209,7 +209,7 @@
  *  - add FUSE_HAS_EXPIRE_ONLY
  *
  *  7.39
- *  - add FUSE_DIRECT_IO_RELAX
+ *  - add FUSE_DIRECT_IO_ALLOW_MMAP
  *  - add FUSE_STATX and related structures
  */
 
@@ -409,8 +409,7 @@ struct fuse_file_lock {
  * FUSE_CREATE_SUPP_GROUP: add supplementary group info to create, mkdir,
  *			symlink and mknod (single group that matches parent)
  * FUSE_HAS_EXPIRE_ONLY: kernel supports expiry-only entry invalidation
- * FUSE_DIRECT_IO_RELAX: relax restrictions in FOPEN_DIRECT_IO mode, for now
- *                       allow shared mmap
+ * FUSE_DIRECT_IO_ALLOW_MMAP: allow shared mmap in FOPEN_DIRECT_IO mode.
  */
 #define FUSE_ASYNC_READ		(1 << 0)
 #define FUSE_POSIX_LOCKS	(1 << 1)
@@ -449,7 +448,10 @@ struct fuse_file_lock {
 #define FUSE_HAS_INODE_DAX	(1ULL << 33)
 #define FUSE_CREATE_SUPP_GROUP	(1ULL << 34)
 #define FUSE_HAS_EXPIRE_ONLY	(1ULL << 35)
-#define FUSE_DIRECT_IO_RELAX	(1ULL << 36)
+#define FUSE_DIRECT_IO_ALLOW_MMAP (1ULL << 36)
+
+/* Obsolete alias for FUSE_DIRECT_IO_ALLOW_MMAP */
+#define FUSE_DIRECT_IO_RELAX	FUSE_DIRECT_IO_ALLOW_MMAP
 
 /**
  * CUSE INIT request/reply flags
diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index 2e23f99dc0f1..a5b743a2f775 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -757,6 +757,7 @@ enum {
 	MDBE_ATTR_VNI,
 	MDBE_ATTR_IFINDEX,
 	MDBE_ATTR_SRC_VNI,
+	MDBE_ATTR_STATE_MASK,
 	__MDBE_ATTR_MAX,
 };
 #define MDBE_ATTR_MAX (__MDBE_ATTR_MAX - 1)
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 29ff80da2775..ab9bcff96e4d 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -461,6 +461,286 @@ enum in6_addr_gen_mode {
 
 /* Bridge section */
 
+/**
+ * DOC: Bridge enum definition
+ *
+ * Please *note* that the timer values in the following section are expected
+ * in clock_t format, which is seconds multiplied by USER_HZ (generally
+ * defined as 100).
+ *
+ * @IFLA_BR_FORWARD_DELAY
+ *   The bridge forwarding delay is the time spent in LISTENING state
+ *   (before moving to LEARNING) and in LEARNING state (before moving
+ *   to FORWARDING). Only relevant if STP is enabled.
+ *
+ *   The valid values are between (2 * USER_HZ) and (30 * USER_HZ).
+ *   The default value is (15 * USER_HZ).
+ *
+ * @IFLA_BR_HELLO_TIME
+ *   The time between hello packets sent by the bridge, when it is a root
+ *   bridge or a designated bridge. Only relevant if STP is enabled.
+ *
+ *   The valid values are between (1 * USER_HZ) and (10 * USER_HZ).
+ *   The default value is (2 * USER_HZ).
+ *
+ * @IFLA_BR_MAX_AGE
+ *   The hello packet timeout is the time until another bridge in the
+ *   spanning tree is assumed to be dead, after reception of its last hello
+ *   message. Only relevant if STP is enabled.
+ *
+ *   The valid values are between (6 * USER_HZ) and (40 * USER_HZ).
+ *   The default value is (20 * USER_HZ).
+ *
+ * @IFLA_BR_AGEING_TIME
+ *   Configure the bridge's FDB entries aging time. It is the time a MAC
+ *   address will be kept in the FDB after a packet has been received from
+ *   that address. After this time has passed, entries are cleaned up.
+ *   Allow values outside the 802.1 standard specification for special cases:
+ *
+ *     * 0 - entry never ages (all permanent)
+ *     * 1 - entry disappears (no persistence)
+ *
+ *   The default value is (300 * USER_HZ).
+ *
+ * @IFLA_BR_STP_STATE
+ *   Turn spanning tree protocol on (*IFLA_BR_STP_STATE* > 0) or off
+ *   (*IFLA_BR_STP_STATE* == 0) for this bridge.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_PRIORITY
+ *   Set this bridge's spanning tree priority, used during STP root bridge
+ *   election.
+ *
+ *   The valid values are between 0 and 65535.
+ *
+ * @IFLA_BR_VLAN_FILTERING
+ *   Turn VLAN filtering on (*IFLA_BR_VLAN_FILTERING* > 0) or off
+ *   (*IFLA_BR_VLAN_FILTERING* == 0). When disabled, the bridge will not
+ *   consider the VLAN tag when handling packets.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_VLAN_PROTOCOL
+ *   Set the protocol used for VLAN filtering.
+ *
+ *   The valid values are 0x8100(802.1Q) or 0x88A8(802.1AD). The default value
+ *   is 0x8100(802.1Q).
+ *
+ * @IFLA_BR_GROUP_FWD_MASK
+ *   The group forwarding mask. This is the bitmask that is applied to
+ *   decide whether to forward incoming frames destined to link-local
+ *   addresses (of the form 01:80:C2:00:00:0X).
+ *
+ *   The default value is 0, which means the bridge does not forward any
+ *   link-local frames coming on this port.
+ *
+ * @IFLA_BR_ROOT_ID
+ *   The bridge root id, read only.
+ *
+ * @IFLA_BR_BRIDGE_ID
+ *   The bridge id, read only.
+ *
+ * @IFLA_BR_ROOT_PORT
+ *   The bridge root port, read only.
+ *
+ * @IFLA_BR_ROOT_PATH_COST
+ *   The bridge root path cost, read only.
+ *
+ * @IFLA_BR_TOPOLOGY_CHANGE
+ *   The bridge topology change, read only.
+ *
+ * @IFLA_BR_TOPOLOGY_CHANGE_DETECTED
+ *   The bridge topology change detected, read only.
+ *
+ * @IFLA_BR_HELLO_TIMER
+ *   The bridge hello timer, read only.
+ *
+ * @IFLA_BR_TCN_TIMER
+ *   The bridge tcn timer, read only.
+ *
+ * @IFLA_BR_TOPOLOGY_CHANGE_TIMER
+ *   The bridge topology change timer, read only.
+ *
+ * @IFLA_BR_GC_TIMER
+ *   The bridge gc timer, read only.
+ *
+ * @IFLA_BR_GROUP_ADDR
+ *   Set the MAC address of the multicast group this bridge uses for STP.
+ *   The address must be a link-local address in standard Ethernet MAC address
+ *   format. It is an address of the form 01:80:C2:00:00:0X, with X in [0, 4..f].
+ *
+ *   The default value is 0.
+ *
+ * @IFLA_BR_FDB_FLUSH
+ *   Flush bridge's fdb dynamic entries.
+ *
+ * @IFLA_BR_MCAST_ROUTER
+ *   Set bridge's multicast router if IGMP snooping is enabled.
+ *   The valid values are:
+ *
+ *     * 0 - disabled.
+ *     * 1 - automatic (queried).
+ *     * 2 - permanently enabled.
+ *
+ *   The default value is 1.
+ *
+ * @IFLA_BR_MCAST_SNOOPING
+ *   Turn multicast snooping on (*IFLA_BR_MCAST_SNOOPING* > 0) or off
+ *   (*IFLA_BR_MCAST_SNOOPING* == 0).
+ *
+ *   The default value is 1.
+ *
+ * @IFLA_BR_MCAST_QUERY_USE_IFADDR
+ *   If enabled use the bridge's own IP address as source address for IGMP
+ *   queries (*IFLA_BR_MCAST_QUERY_USE_IFADDR* > 0) or the default of 0.0.0.0
+ *   (*IFLA_BR_MCAST_QUERY_USE_IFADDR* == 0).
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_QUERIER
+ *   Enable (*IFLA_BR_MULTICAST_QUERIER* > 0) or disable
+ *   (*IFLA_BR_MULTICAST_QUERIER* == 0) IGMP querier, ie sending of multicast
+ *   queries by the bridge.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_HASH_ELASTICITY
+ *   Set multicast database hash elasticity, It is the maximum chain length in
+ *   the multicast hash table. This attribute is *deprecated* and the value
+ *   is always 16.
+ *
+ * @IFLA_BR_MCAST_HASH_MAX
+ *   Set maximum size of the multicast hash table
+ *
+ *   The default value is 4096, the value must be a power of 2.
+ *
+ * @IFLA_BR_MCAST_LAST_MEMBER_CNT
+ *   The Last Member Query Count is the number of Group-Specific Queries
+ *   sent before the router assumes there are no local members. The Last
+ *   Member Query Count is also the number of Group-and-Source-Specific
+ *   Queries sent before the router assumes there are no listeners for a
+ *   particular source.
+ *
+ *   The default value is 2.
+ *
+ * @IFLA_BR_MCAST_STARTUP_QUERY_CNT
+ *   The Startup Query Count is the number of Queries sent out on startup,
+ *   separated by the Startup Query Interval.
+ *
+ *   The default value is 2.
+ *
+ * @IFLA_BR_MCAST_LAST_MEMBER_INTVL
+ *   The Last Member Query Interval is the Max Response Time inserted into
+ *   Group-Specific Queries sent in response to Leave Group messages, and
+ *   is also the amount of time between Group-Specific Query messages.
+ *
+ *   The default value is (1 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_MEMBERSHIP_INTVL
+ *   The interval after which the bridge will leave a group, if no membership
+ *   reports for this group are received.
+ *
+ *   The default value is (260 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_QUERIER_INTVL
+ *   The interval between queries sent by other routers. if no queries are
+ *   seen after this delay has passed, the bridge will start to send its own
+ *   queries (as if *IFLA_BR_MCAST_QUERIER_INTVL* was enabled).
+ *
+ *   The default value is (255 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_QUERY_INTVL
+ *   The Query Interval is the interval between General Queries sent by
+ *   the Querier.
+ *
+ *   The default value is (125 * USER_HZ). The minimum value is (1 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_QUERY_RESPONSE_INTVL
+ *   The Max Response Time used to calculate the Max Resp Code inserted
+ *   into the periodic General Queries.
+ *
+ *   The default value is (10 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_STARTUP_QUERY_INTVL
+ *   The interval between queries in the startup phase.
+ *
+ *   The default value is (125 * USER_HZ) / 4. The minimum value is (1 * USER_HZ).
+ *
+ * @IFLA_BR_NF_CALL_IPTABLES
+ *   Enable (*NF_CALL_IPTABLES* > 0) or disable (*NF_CALL_IPTABLES* == 0)
+ *   iptables hooks on the bridge.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_NF_CALL_IP6TABLES
+ *   Enable (*NF_CALL_IP6TABLES* > 0) or disable (*NF_CALL_IP6TABLES* == 0)
+ *   ip6tables hooks on the bridge.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_NF_CALL_ARPTABLES
+ *   Enable (*NF_CALL_ARPTABLES* > 0) or disable (*NF_CALL_ARPTABLES* == 0)
+ *   arptables hooks on the bridge.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_VLAN_DEFAULT_PVID
+ *   VLAN ID applied to untagged and priority-tagged incoming packets.
+ *
+ *   The default value is 1. Setting to the special value 0 makes all ports of
+ *   this bridge not have a PVID by default, which means that they will
+ *   not accept VLAN-untagged traffic.
+ *
+ * @IFLA_BR_PAD
+ *   Bridge attribute padding type for netlink message.
+ *
+ * @IFLA_BR_VLAN_STATS_ENABLED
+ *   Enable (*IFLA_BR_VLAN_STATS_ENABLED* == 1) or disable
+ *   (*IFLA_BR_VLAN_STATS_ENABLED* == 0) per-VLAN stats accounting.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_STATS_ENABLED
+ *   Enable (*IFLA_BR_MCAST_STATS_ENABLED* > 0) or disable
+ *   (*IFLA_BR_MCAST_STATS_ENABLED* == 0) multicast (IGMP/MLD) stats
+ *   accounting.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_IGMP_VERSION
+ *   Set the IGMP version.
+ *
+ *   The valid values are 2 and 3. The default value is 2.
+ *
+ * @IFLA_BR_MCAST_MLD_VERSION
+ *   Set the MLD version.
+ *
+ *   The valid values are 1 and 2. The default value is 1.
+ *
+ * @IFLA_BR_VLAN_STATS_PER_PORT
+ *   Enable (*IFLA_BR_VLAN_STATS_PER_PORT* == 1) or disable
+ *   (*IFLA_BR_VLAN_STATS_PER_PORT* == 0) per-VLAN per-port stats accounting.
+ *   Can be changed only when there are no port VLANs configured.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MULTI_BOOLOPT
+ *   The multi_boolopt is used to control new boolean options to avoid adding
+ *   new netlink attributes. You can look at ``enum br_boolopt_id`` for those
+ *   options.
+ *
+ * @IFLA_BR_MCAST_QUERIER_STATE
+ *   Bridge mcast querier states, read only.
+ *
+ * @IFLA_BR_FDB_N_LEARNED
+ *   The number of dynamically learned FDB entries for the current bridge,
+ *   read only.
+ *
+ * @IFLA_BR_FDB_MAX_LEARNED
+ *   Set the number of max dynamically learned FDB entries for the current
+ *   bridge.
+ */
 enum {
 	IFLA_BR_UNSPEC,
 	IFLA_BR_FORWARD_DELAY,
@@ -522,11 +802,252 @@ struct ifla_bridge_id {
 	__u8	addr[6]; /* ETH_ALEN */
 };
 
+/**
+ * DOC: Bridge mode enum definition
+ *
+ * @BRIDGE_MODE_HAIRPIN
+ *   Controls whether traffic may be sent back out of the port on which it
+ *   was received. This option is also called reflective relay mode, and is
+ *   used to support basic VEPA (Virtual Ethernet Port Aggregator)
+ *   capabilities. By default, this flag is turned off and the bridge will
+ *   not forward traffic back out of the receiving port.
+ */
 enum {
 	BRIDGE_MODE_UNSPEC,
 	BRIDGE_MODE_HAIRPIN,
 };
 
+/**
+ * DOC: Bridge port enum definition
+ *
+ * @IFLA_BRPORT_STATE
+ *   The operation state of the port. Here are the valid values.
+ *
+ *     * 0 - port is in STP *DISABLED* state. Make this port completely
+ *       inactive for STP. This is also called BPDU filter and could be used
+ *       to disable STP on an untrusted port, like a leaf virtual device.
+ *       The traffic forwarding is also stopped on this port.
+ *     * 1 - port is in STP *LISTENING* state. Only valid if STP is enabled
+ *       on the bridge. In this state the port listens for STP BPDUs and
+ *       drops all other traffic frames.
+ *     * 2 - port is in STP *LEARNING* state. Only valid if STP is enabled on
+ *       the bridge. In this state the port will accept traffic only for the
+ *       purpose of updating MAC address tables.
+ *     * 3 - port is in STP *FORWARDING* state. Port is fully active.
+ *     * 4 - port is in STP *BLOCKING* state. Only valid if STP is enabled on
+ *       the bridge. This state is used during the STP election process.
+ *       In this state, port will only process STP BPDUs.
+ *
+ * @IFLA_BRPORT_PRIORITY
+ *   The STP port priority. The valid values are between 0 and 255.
+ *
+ * @IFLA_BRPORT_COST
+ *   The STP path cost of the port. The valid values are between 1 and 65535.
+ *
+ * @IFLA_BRPORT_MODE
+ *   Set the bridge port mode. See *BRIDGE_MODE_HAIRPIN* for more details.
+ *
+ * @IFLA_BRPORT_GUARD
+ *   Controls whether STP BPDUs will be processed by the bridge port. By
+ *   default, the flag is turned off to allow BPDU processing. Turning this
+ *   flag on will disable the bridge port if a STP BPDU packet is received.
+ *
+ *   If the bridge has Spanning Tree enabled, hostile devices on the network
+ *   may send BPDU on a port and cause network failure. Setting *guard on*
+ *   will detect and stop this by disabling the port. The port will be
+ *   restarted if the link is brought down, or removed and reattached.
+ *
+ * @IFLA_BRPORT_PROTECT
+ *   Controls whether a given port is allowed to become a root port or not.
+ *   Only used when STP is enabled on the bridge. By default the flag is off.
+ *
+ *   This feature is also called root port guard. If BPDU is received from a
+ *   leaf (edge) port, it should not be elected as root port. This could
+ *   be used if using STP on a bridge and the downstream bridges are not fully
+ *   trusted; this prevents a hostile guest from rerouting traffic.
+ *
+ * @IFLA_BRPORT_FAST_LEAVE
+ *   This flag allows the bridge to immediately stop multicast traffic
+ *   forwarding on a port that receives an IGMP Leave message. It is only used
+ *   when IGMP snooping is enabled on the bridge. By default the flag is off.
+ *
+ * @IFLA_BRPORT_LEARNING
+ *   Controls whether a given port will learn *source* MAC addresses from
+ *   received traffic or not. Also controls whether dynamic FDB entries
+ *   (which can also be added by software) will be refreshed by incoming
+ *   traffic. By default this flag is on.
+ *
+ * @IFLA_BRPORT_UNICAST_FLOOD
+ *   Controls whether unicast traffic for which there is no FDB entry will
+ *   be flooded towards this port. By default this flag is on.
+ *
+ * @IFLA_BRPORT_PROXYARP
+ *   Enable proxy ARP on this port.
+ *
+ * @IFLA_BRPORT_LEARNING_SYNC
+ *   Controls whether a given port will sync MAC addresses learned on device
+ *   port to bridge FDB.
+ *
+ * @IFLA_BRPORT_PROXYARP_WIFI
+ *   Enable proxy ARP on this port which meets extended requirements by
+ *   IEEE 802.11 and Hotspot 2.0 specifications.
+ *
+ * @IFLA_BRPORT_ROOT_ID
+ *
+ * @IFLA_BRPORT_BRIDGE_ID
+ *
+ * @IFLA_BRPORT_DESIGNATED_PORT
+ *
+ * @IFLA_BRPORT_DESIGNATED_COST
+ *
+ * @IFLA_BRPORT_ID
+ *
+ * @IFLA_BRPORT_NO
+ *
+ * @IFLA_BRPORT_TOPOLOGY_CHANGE_ACK
+ *
+ * @IFLA_BRPORT_CONFIG_PENDING
+ *
+ * @IFLA_BRPORT_MESSAGE_AGE_TIMER
+ *
+ * @IFLA_BRPORT_FORWARD_DELAY_TIMER
+ *
+ * @IFLA_BRPORT_HOLD_TIMER
+ *
+ * @IFLA_BRPORT_FLUSH
+ *   Flush bridge ports' fdb dynamic entries.
+ *
+ * @IFLA_BRPORT_MULTICAST_ROUTER
+ *   Configure the port's multicast router presence. A port with
+ *   a multicast router will receive all multicast traffic.
+ *   The valid values are:
+ *
+ *     * 0 disable multicast routers on this port
+ *     * 1 let the system detect the presence of routers (default)
+ *     * 2 permanently enable multicast traffic forwarding on this port
+ *     * 3 enable multicast routers temporarily on this port, not depending
+ *         on incoming queries.
+ *
+ * @IFLA_BRPORT_PAD
+ *
+ * @IFLA_BRPORT_MCAST_FLOOD
+ *   Controls whether a given port will flood multicast traffic for which
+ *   there is no MDB entry. By default this flag is on.
+ *
+ * @IFLA_BRPORT_MCAST_TO_UCAST
+ *   Controls whether a given port will replicate packets using unicast
+ *   instead of multicast. By default this flag is off.
+ *
+ *   This is done by copying the packet per host and changing the multicast
+ *   destination MAC to a unicast one accordingly.
+ *
+ *   *mcast_to_unicast* works on top of the multicast snooping feature of the
+ *   bridge. Which means unicast copies are only delivered to hosts which
+ *   are interested in unicast and signaled this via IGMP/MLD reports previously.
+ *
+ *   This feature is intended for interface types which have a more reliable
+ *   and/or efficient way to deliver unicast packets than broadcast ones
+ *   (e.g. WiFi).
+ *
+ *   However, it should only be enabled on interfaces where no IGMPv2/MLDv1
+ *   report suppression takes place. IGMP/MLD report suppression issue is
+ *   usually overcome by the network daemon (supplicant) enabling AP isolation
+ *   and by that separating all STAs.
+ *
+ *   Delivery of STA-to-STA IP multicast is made possible again by enabling
+ *   and utilizing the bridge hairpin mode, which considers the incoming port
+ *   as a potential outgoing port, too (see *BRIDGE_MODE_HAIRPIN* option).
+ *   Hairpin mode is performed after multicast snooping, therefore leading
+ *   to only deliver reports to STAs running a multicast router.
+ *
+ * @IFLA_BRPORT_VLAN_TUNNEL
+ *   Controls whether vlan to tunnel mapping is enabled on the port.
+ *   By default this flag is off.
+ *
+ * @IFLA_BRPORT_BCAST_FLOOD
+ *   Controls flooding of broadcast traffic on the given port. By default
+ *   this flag is on.
+ *
+ * @IFLA_BRPORT_GROUP_FWD_MASK
+ *   Set the group forward mask. This is a bitmask that is applied to
+ *   decide whether to forward incoming frames destined to link-local
+ *   addresses. The addresses of the form are 01:80:C2:00:00:0X (defaults
+ *   to 0, which means the bridge does not forward any link-local frames
+ *   coming on this port).
+ *
+ * @IFLA_BRPORT_NEIGH_SUPPRESS
+ *   Controls whether neighbor discovery (arp and nd) proxy and suppression
+ *   is enabled on the port. By default this flag is off.
+ *
+ * @IFLA_BRPORT_ISOLATED
+ *   Controls whether a given port will be isolated, which means it will be
+ *   able to communicate with non-isolated ports only. By default this
+ *   flag is off.
+ *
+ * @IFLA_BRPORT_BACKUP_PORT
+ *   Set a backup port. If the port loses carrier all traffic will be
+ *   redirected to the configured backup port. Set the value to 0 to disable
+ *   it.
+ *
+ * @IFLA_BRPORT_MRP_RING_OPEN
+ *
+ * @IFLA_BRPORT_MRP_IN_OPEN
+ *
+ * @IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT
+ *   The number of per-port EHT hosts limit. The default value is 512.
+ *   Setting to 0 is not allowed.
+ *
+ * @IFLA_BRPORT_MCAST_EHT_HOSTS_CNT
+ *   The current number of tracked hosts, read only.
+ *
+ * @IFLA_BRPORT_LOCKED
+ *   Controls whether a port will be locked, meaning that hosts behind the
+ *   port will not be able to communicate through the port unless an FDB
+ *   entry with the unit's MAC address is in the FDB. The common use case is
+ *   that hosts are allowed access through authentication with the IEEE 802.1X
+ *   protocol or based on whitelists. By default this flag is off.
+ *
+ *   Please note that secure 802.1X deployments should always use the
+ *   *BR_BOOLOPT_NO_LL_LEARN* flag, to not permit the bridge to populate its
+ *   FDB based on link-local (EAPOL) traffic received on the port.
+ *
+ * @IFLA_BRPORT_MAB
+ *   Controls whether a port will use MAC Authentication Bypass (MAB), a
+ *   technique through which select MAC addresses may be allowed on a locked
+ *   port, without using 802.1X authentication. Packets with an unknown source
+ *   MAC address generates a "locked" FDB entry on the incoming bridge port.
+ *   The common use case is for user space to react to these bridge FDB
+ *   notifications and optionally replace the locked FDB entry with a normal
+ *   one, allowing traffic to pass for whitelisted MAC addresses.
+ *
+ *   Setting this flag also requires *IFLA_BRPORT_LOCKED* and
+ *   *IFLA_BRPORT_LEARNING*. *IFLA_BRPORT_LOCKED* ensures that unauthorized
+ *   data packets are dropped, and *IFLA_BRPORT_LEARNING* allows the dynamic
+ *   FDB entries installed by user space (as replacements for the locked FDB
+ *   entries) to be refreshed and/or aged out.
+ *
+ * @IFLA_BRPORT_MCAST_N_GROUPS
+ *
+ * @IFLA_BRPORT_MCAST_MAX_GROUPS
+ *   Sets the maximum number of MDB entries that can be registered for a
+ *   given port. Attempts to register more MDB entries at the port than this
+ *   limit allows will be rejected, whether they are done through netlink
+ *   (e.g. the bridge tool), or IGMP or MLD membership reports. Setting a
+ *   limit of 0 disables the limit. The default value is 0.
+ *
+ * @IFLA_BRPORT_NEIGH_VLAN_SUPPRESS
+ *   Controls whether neighbor discovery (arp and nd) proxy and suppression is
+ *   enabled for a given port. By default this flag is off.
+ *
+ *   Note that this option only takes effect when *IFLA_BRPORT_NEIGH_SUPPRESS*
+ *   is enabled for a given port.
+ *
+ * @IFLA_BRPORT_BACKUP_NHID
+ *   The FDB nexthop object ID to attach to packets being redirected to a
+ *   backup port that has VLAN tunnel mapping enabled (via the
+ *   *IFLA_BRPORT_VLAN_TUNNEL* option). Setting a value of 0 (default) has
+ *   the effect of not attaching any ID.
+ */
 enum {
 	IFLA_BRPORT_UNSPEC,
 	IFLA_BRPORT_STATE,	/* Spanning tree state     */
@@ -856,6 +1377,7 @@ enum {
 	IFLA_VXLAN_DF,
 	IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */
 	IFLA_VXLAN_LOCALBYPASS,
+	IFLA_VXLAN_LABEL_POLICY, /* IPv6 flow label policy; ifla_vxlan_label_policy */
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
@@ -873,6 +1395,13 @@ enum ifla_vxlan_df {
 	VXLAN_DF_MAX = __VXLAN_DF_END - 1,
 };
 
+enum ifla_vxlan_label_policy {
+	VXLAN_LABEL_FIXED = 0,
+	VXLAN_LABEL_INHERIT = 1,
+	__VXLAN_LABEL_END,
+	VXLAN_LABEL_MAX = __VXLAN_LABEL_END - 1,
+};
+
 /* GENEVE section */
 enum {
 	IFLA_GENEVE_UNSPEC,
diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
index 8d48863472b9..d31698410410 100644
--- a/include/uapi/linux/if_xdp.h
+++ b/include/uapi/linux/if_xdp.h
@@ -33,7 +33,13 @@
 #define XDP_USE_SG	(1 << 4)
 
 /* Flags for xsk_umem_config flags */
-#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
+#define XDP_UMEM_UNALIGNED_CHUNK_FLAG	(1 << 0)
+
+/* Force checksum calculation in software. Can be used for testing or
+ * working around potential HW issues. This option causes performance
+ * degradation and only works in XDP_COPY mode.
+ */
+#define XDP_UMEM_TX_SW_CSUM		(1 << 1)
 
 struct sockaddr_xdp {
 	__u16 sxdp_family;
@@ -76,6 +82,7 @@ struct xdp_umem_reg {
 	__u32 chunk_size;
 	__u32 headroom;
 	__u32 flags;
+	__u32 tx_metadata_len;
 };
 
 struct xdp_statistics {
@@ -105,6 +112,41 @@ struct xdp_options {
 #define XSK_UNALIGNED_BUF_ADDR_MASK \
 	((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1)
 
+/* Request transmit timestamp. Upon completion, put it into tx_timestamp
+ * field of struct xsk_tx_metadata.
+ */
+#define XDP_TXMD_FLAGS_TIMESTAMP		(1 << 0)
+
+/* Request transmit checksum offload. Checksum start position and offset
+ * are communicated via csum_start and csum_offset fields of struct
+ * xsk_tx_metadata.
+ */
+#define XDP_TXMD_FLAGS_CHECKSUM			(1 << 1)
+
+/* AF_XDP offloads request. 'request' union member is consumed by the driver
+ * when the packet is being transmitted. 'completion' union member is
+ * filled by the driver when the transmit completion arrives.
+ */
+struct xsk_tx_metadata {
+	__u64 flags;
+
+	union {
+		struct {
+			/* XDP_TXMD_FLAGS_CHECKSUM */
+
+			/* Offset from desc->addr where checksumming should start. */
+			__u16 csum_start;
+			/* Offset from csum_start where checksum should be stored. */
+			__u16 csum_offset;
+		} request;
+
+		struct {
+			/* XDP_TXMD_FLAGS_TIMESTAMP */
+			__u64 tx_timestamp;
+		} completion;
+	};
+};
+
 /* Rx/Tx descriptor */
 struct xdp_desc {
 	__u64 addr;
@@ -121,4 +163,7 @@ struct xdp_desc {
  */
 #define XDP_PKT_CONTD (1 << 0)
 
+/* TX packet carries valid metadata. */
+#define XDP_TX_METADATA (1 << 1)
+
 #endif /* _LINUX_IF_XDP_H */
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index f1c16f817742..7a673b52827b 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -71,6 +71,7 @@ struct io_uring_sqe {
 		__u32		uring_cmd_flags;
 		__u32		waitid_flags;
 		__u32		futex_flags;
+		__u32		install_fd_flags;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
 	/* pack this to avoid bogus arm OABI complaints */
@@ -253,6 +254,7 @@ enum io_uring_op {
 	IORING_OP_FUTEX_WAIT,
 	IORING_OP_FUTEX_WAKE,
 	IORING_OP_FUTEX_WAITV,
+	IORING_OP_FIXED_FD_INSTALL,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
@@ -387,6 +389,13 @@ enum {
 #define IORING_MSG_RING_FLAGS_PASS	(1U << 1)
 
 /*
+ * IORING_OP_FIXED_FD_INSTALL flags (sqe->install_fd_flags)
+ *
+ * IORING_FIXED_FD_NO_CLOEXEC	Don't mark the fd as O_CLOEXEC
+ */
+#define IORING_FIXED_FD_NO_CLOEXEC	(1U << 0)
+
+/*
  * IO completion data structure (Completion Queue Entry)
  */
 struct io_uring_cqe {
@@ -558,6 +567,9 @@ enum {
 	/* register a range of fixed file slots for automatic slot allocation */
 	IORING_REGISTER_FILE_ALLOC_RANGE	= 25,
 
+	/* return status information for a buffer group */
+	IORING_REGISTER_PBUF_STATUS		= 26,
+
 	/* this goes last */
 	IORING_REGISTER_LAST,
 
@@ -684,6 +696,13 @@ struct io_uring_buf_reg {
 	__u64	resv[3];
 };
 
+/* argument for IORING_REGISTER_PBUF_STATUS */
+struct io_uring_buf_status {
+	__u32	buf_group;	/* input */
+	__u32	head;		/* output */
+	__u32	resv[8];
+};
+
 /*
  * io_uring_restriction->opcode values
  */
diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h
index 01766dd839b0..c17bb096ea68 100644
--- a/include/uapi/linux/kexec.h
+++ b/include/uapi/linux/kexec.h
@@ -25,6 +25,7 @@
 #define KEXEC_FILE_UNLOAD	0x00000001
 #define KEXEC_FILE_ON_CRASH	0x00000002
 #define KEXEC_FILE_NO_INITRAMFS	0x00000004
+#define KEXEC_FILE_DEBUG	0x00000008
 
 /* These values match the ELF architecture values.
  * Unless there is a good reason that should continue to be the case.
diff --git a/include/uapi/linux/lsm.h b/include/uapi/linux/lsm.h
new file mode 100644
index 000000000000..f8aef9ade549
--- /dev/null
+++ b/include/uapi/linux/lsm.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Linux Security Modules (LSM) - User space API
+ *
+ * Copyright (C) 2022 Casey Schaufler <casey@schaufler-ca.com>
+ * Copyright (C) 2022 Intel Corporation
+ */
+
+#ifndef _UAPI_LINUX_LSM_H
+#define _UAPI_LINUX_LSM_H
+
+#include <linux/stddef.h>
+#include <linux/types.h>
+#include <linux/unistd.h>
+
+/**
+ * struct lsm_ctx - LSM context information
+ * @id: the LSM id number, see LSM_ID_XXX
+ * @flags: LSM specific flags
+ * @len: length of the lsm_ctx struct, @ctx and any other data or padding
+ * @ctx_len: the size of @ctx
+ * @ctx: the LSM context value
+ *
+ * The @len field MUST be equal to the size of the lsm_ctx struct
+ * plus any additional padding and/or data placed after @ctx.
+ *
+ * In all cases @ctx_len MUST be equal to the length of @ctx.
+ * If @ctx is a string value it should be nul terminated with
+ * @ctx_len equal to `strlen(@ctx) + 1`.  Binary values are
+ * supported.
+ *
+ * The @flags and @ctx fields SHOULD only be interpreted by the
+ * LSM specified by @id; they MUST be set to zero/0 when not used.
+ */
+struct lsm_ctx {
+	__u64 id;
+	__u64 flags;
+	__u64 len;
+	__u64 ctx_len;
+	__u8 ctx[] __counted_by(ctx_len);
+};
+
+/*
+ * ID tokens to identify Linux Security Modules (LSMs)
+ *
+ * These token values are used to uniquely identify specific LSMs
+ * in the kernel as well as in the kernel's LSM userspace API.
+ *
+ * A value of zero/0 is considered undefined and should not be used
+ * outside the kernel. Values 1-99 are reserved for potential
+ * future use.
+ */
+#define LSM_ID_UNDEF		0
+#define LSM_ID_CAPABILITY	100
+#define LSM_ID_SELINUX		101
+#define LSM_ID_SMACK		102
+#define LSM_ID_TOMOYO		103
+#define LSM_ID_APPARMOR		104
+#define LSM_ID_YAMA		105
+#define LSM_ID_LOADPIN		106
+#define LSM_ID_SAFESETID	107
+#define LSM_ID_LOCKDOWN		108
+#define LSM_ID_BPF		109
+#define LSM_ID_LANDLOCK		110
+
+/*
+ * LSM_ATTR_XXX definitions identify different LSM attributes
+ * which are used in the kernel's LSM userspace API. Support
+ * for these attributes vary across the different LSMs. None
+ * are required.
+ *
+ * A value of zero/0 is considered undefined and should not be used
+ * outside the kernel. Values 1-99 are reserved for potential
+ * future use.
+ */
+#define LSM_ATTR_UNDEF		0
+#define LSM_ATTR_CURRENT	100
+#define LSM_ATTR_EXEC		101
+#define LSM_ATTR_FSCREATE	102
+#define LSM_ATTR_KEYCREATE	103
+#define LSM_ATTR_PREV		104
+#define LSM_ATTR_SOCKCREATE	105
+
+/*
+ * LSM_FLAG_XXX definitions identify special handling instructions
+ * for the API.
+ */
+#define LSM_FLAG_SINGLE	0x0001
+
+#endif /* _UAPI_LINUX_LSM_H */
diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h
index bb242fdcfe6b..ad5478dbad00 100644
--- a/include/uapi/linux/mount.h
+++ b/include/uapi/linux/mount.h
@@ -138,4 +138,74 @@ struct mount_attr {
 /* List of all mount_attr versions. */
 #define MOUNT_ATTR_SIZE_VER0	32 /* sizeof first published struct */
 
+
+/*
+ * Structure for getting mount/superblock/filesystem info with statmount(2).
+ *
+ * The interface is similar to statx(2): individual fields or groups can be
+ * selected with the @mask argument of statmount().  Kernel will set the @mask
+ * field according to the supported fields.
+ *
+ * If string fields are selected, then the caller needs to pass a buffer that
+ * has space after the fixed part of the structure.  Nul terminated strings are
+ * copied there and offsets relative to @str are stored in the relevant fields.
+ * If the buffer is too small, then EOVERFLOW is returned.  The actually used
+ * size is returned in @size.
+ */
+struct statmount {
+	__u32 size;		/* Total size, including strings */
+	__u32 __spare1;
+	__u64 mask;		/* What results were written */
+	__u32 sb_dev_major;	/* Device ID */
+	__u32 sb_dev_minor;
+	__u64 sb_magic;		/* ..._SUPER_MAGIC */
+	__u32 sb_flags;		/* SB_{RDONLY,SYNCHRONOUS,DIRSYNC,LAZYTIME} */
+	__u32 fs_type;		/* [str] Filesystem type */
+	__u64 mnt_id;		/* Unique ID of mount */
+	__u64 mnt_parent_id;	/* Unique ID of parent (for root == mnt_id) */
+	__u32 mnt_id_old;	/* Reused IDs used in proc/.../mountinfo */
+	__u32 mnt_parent_id_old;
+	__u64 mnt_attr;		/* MOUNT_ATTR_... */
+	__u64 mnt_propagation;	/* MS_{SHARED,SLAVE,PRIVATE,UNBINDABLE} */
+	__u64 mnt_peer_group;	/* ID of shared peer group */
+	__u64 mnt_master;	/* Mount receives propagation from this ID */
+	__u64 propagate_from;	/* Propagation from in current namespace */
+	__u32 mnt_root;		/* [str] Root of mount relative to root of fs */
+	__u32 mnt_point;	/* [str] Mountpoint relative to current root */
+	__u64 __spare2[50];
+	char str[];		/* Variable size part containing strings */
+};
+
+/*
+ * Structure for passing mount ID and miscellaneous parameters to statmount(2)
+ * and listmount(2).
+ *
+ * For statmount(2) @param represents the request mask.
+ * For listmount(2) @param represents the last listed mount id (or zero).
+ */
+struct mnt_id_req {
+	__u32 size;
+	__u32 spare;
+	__u64 mnt_id;
+	__u64 param;
+};
+
+/* List of all mnt_id_req versions. */
+#define MNT_ID_REQ_SIZE_VER0	24 /* sizeof first published struct */
+
+/*
+ * @mask bits for statmount(2)
+ */
+#define STATMOUNT_SB_BASIC		0x00000001U     /* Want/got sb_... */
+#define STATMOUNT_MNT_BASIC		0x00000002U	/* Want/got mnt_... */
+#define STATMOUNT_PROPAGATE_FROM	0x00000004U	/* Want/got propagate_from */
+#define STATMOUNT_MNT_ROOT		0x00000008U	/* Want/got mnt_root  */
+#define STATMOUNT_MNT_POINT		0x00000010U	/* Want/got mnt_point */
+#define STATMOUNT_FS_TYPE		0x00000020U	/* Want/got fs_type */
+
+/*
+ * Special @mnt_id values that can be passed to listmount
+ */
+#define LSMT_ROOT		0xffffffffffffffff	/* root mount */
+
 #endif /* _UAPI_LINUX_MOUNT_H */
diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h
index a6451561f3f8..74cfe496891e 100644
--- a/include/uapi/linux/mptcp.h
+++ b/include/uapi/linux/mptcp.h
@@ -57,6 +57,7 @@ struct mptcp_info {
 	__u64	mptcpi_bytes_sent;
 	__u64	mptcpi_bytes_received;
 	__u64	mptcpi_bytes_acked;
+	__u8	mptcpi_subflows_total;
 };
 
 /* MPTCP Reset reason codes, rfc8684 */
diff --git a/include/uapi/linux/mptcp_pm.h b/include/uapi/linux/mptcp_pm.h
index b5d11aece408..50589e5dd6a3 100644
--- a/include/uapi/linux/mptcp_pm.h
+++ b/include/uapi/linux/mptcp_pm.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
 /* Do not edit directly, auto-generated from: */
-/*	Documentation/netlink/specs/mptcp.yaml */
+/*	Documentation/netlink/specs/mptcp_pm.yaml */
 /* YNL-GEN uapi header */
 
 #ifndef _UAPI_LINUX_MPTCP_PM_H
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 2943a151d4f1..93cb411adf72 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -44,13 +44,30 @@ enum netdev_xdp_act {
  *   timestamp via bpf_xdp_metadata_rx_timestamp().
  * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet
  *   hash via bpf_xdp_metadata_rx_hash().
+ * @NETDEV_XDP_RX_METADATA_VLAN_TAG: Device is capable of exposing receive
+ *   packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag().
  */
 enum netdev_xdp_rx_metadata {
 	NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
 	NETDEV_XDP_RX_METADATA_HASH = 2,
+	NETDEV_XDP_RX_METADATA_VLAN_TAG = 4,
+};
 
-	/* private: */
-	NETDEV_XDP_RX_METADATA_MASK = 3,
+/**
+ * enum netdev_xsk_flags
+ * @NETDEV_XSK_FLAGS_TX_TIMESTAMP: HW timestamping egress packets is supported
+ *   by the driver.
+ * @NETDEV_XSK_FLAGS_TX_CHECKSUM: L3 checksum HW offload is supported by the
+ *   driver.
+ */
+enum netdev_xsk_flags {
+	NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1,
+	NETDEV_XSK_FLAGS_TX_CHECKSUM = 2,
+};
+
+enum netdev_queue_type {
+	NETDEV_QUEUE_TYPE_RX,
+	NETDEV_QUEUE_TYPE_TX,
 };
 
 enum {
@@ -59,21 +76,80 @@ enum {
 	NETDEV_A_DEV_XDP_FEATURES,
 	NETDEV_A_DEV_XDP_ZC_MAX_SEGS,
 	NETDEV_A_DEV_XDP_RX_METADATA_FEATURES,
+	NETDEV_A_DEV_XSK_FEATURES,
 
 	__NETDEV_A_DEV_MAX,
 	NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
 };
 
 enum {
+	NETDEV_A_PAGE_POOL_ID = 1,
+	NETDEV_A_PAGE_POOL_IFINDEX,
+	NETDEV_A_PAGE_POOL_NAPI_ID,
+	NETDEV_A_PAGE_POOL_INFLIGHT,
+	NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
+	NETDEV_A_PAGE_POOL_DETACH_TIME,
+
+	__NETDEV_A_PAGE_POOL_MAX,
+	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)
+};
+
+enum {
+	NETDEV_A_PAGE_POOL_STATS_INFO = 1,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST = 8,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT,
+
+	__NETDEV_A_PAGE_POOL_STATS_MAX,
+	NETDEV_A_PAGE_POOL_STATS_MAX = (__NETDEV_A_PAGE_POOL_STATS_MAX - 1)
+};
+
+enum {
+	NETDEV_A_NAPI_IFINDEX = 1,
+	NETDEV_A_NAPI_ID,
+	NETDEV_A_NAPI_IRQ,
+	NETDEV_A_NAPI_PID,
+
+	__NETDEV_A_NAPI_MAX,
+	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
+};
+
+enum {
+	NETDEV_A_QUEUE_ID = 1,
+	NETDEV_A_QUEUE_IFINDEX,
+	NETDEV_A_QUEUE_TYPE,
+	NETDEV_A_QUEUE_NAPI_ID,
+
+	__NETDEV_A_QUEUE_MAX,
+	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
+};
+
+enum {
 	NETDEV_CMD_DEV_GET = 1,
 	NETDEV_CMD_DEV_ADD_NTF,
 	NETDEV_CMD_DEV_DEL_NTF,
 	NETDEV_CMD_DEV_CHANGE_NTF,
+	NETDEV_CMD_PAGE_POOL_GET,
+	NETDEV_CMD_PAGE_POOL_ADD_NTF,
+	NETDEV_CMD_PAGE_POOL_DEL_NTF,
+	NETDEV_CMD_PAGE_POOL_CHANGE_NTF,
+	NETDEV_CMD_PAGE_POOL_STATS_GET,
+	NETDEV_CMD_QUEUE_GET,
+	NETDEV_CMD_NAPI_GET,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
 };
 
 #define NETDEV_MCGRP_MGMT	"mgmt"
+#define NETDEV_MCGRP_PAGE_POOL	"page-pool"
 
 #endif /* _UAPI_LINUX_NETDEV_H */
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index dced2c49daec..1ccdcae24372 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -72,7 +72,7 @@
  * For drivers supporting TDLS with external setup (WIPHY_FLAG_SUPPORTS_TDLS
  * and WIPHY_FLAG_TDLS_EXTERNAL_SETUP), the station lifetime is as follows:
  *  - a setup station entry is added, not yet authorized, without any rate
- *    or capability information, this just exists to avoid race conditions
+ *    or capability information; this just exists to avoid race conditions
  *  - when the TDLS setup is done, a single NL80211_CMD_SET_STATION is valid
  *    to add rate and capability information to the station and at the same
  *    time mark it authorized.
@@ -87,7 +87,7 @@
  * DOC: Frame transmission/registration support
  *
  * Frame transmission and registration support exists to allow userspace
- * management entities such as wpa_supplicant react to management frames
+ * management entities such as wpa_supplicant to react to management frames
  * that are not being handled by the kernel. This includes, for example,
  * certain classes of action frames that cannot be handled in the kernel
  * for various reasons.
@@ -113,7 +113,7 @@
  *
  * Frame transmission allows userspace to send for example the required
  * responses to action frames. It is subject to some sanity checking,
- * but many frames can be transmitted. When a frame was transmitted, its
+ * but many frames can be transmitted. When a frame is transmitted, its
  * status is indicated to the sending socket.
  *
  * For more technical details, see the corresponding command descriptions
@@ -123,7 +123,7 @@
 /**
  * DOC: Virtual interface / concurrency capabilities
  *
- * Some devices are able to operate with virtual MACs, they can have
+ * Some devices are able to operate with virtual MACs; they can have
  * more than one virtual interface. The capability handling for this
  * is a bit complex though, as there may be a number of restrictions
  * on the types of concurrency that are supported.
@@ -135,7 +135,7 @@
  * Once concurrency is desired, more attributes must be observed:
  * To start with, since some interface types are purely managed in
  * software, like the AP-VLAN type in mac80211 for example, there's
- * an additional list of these, they can be added at any time and
+ * an additional list of these; they can be added at any time and
  * are only restricted by some semantic restrictions (e.g. AP-VLAN
  * cannot be added without a corresponding AP interface). This list
  * is exported in the %NL80211_ATTR_SOFTWARE_IFTYPES attribute.
@@ -164,7 +164,7 @@
  * Packet coalesce feature helps to reduce number of received interrupts
  * to host by buffering these packets in firmware/hardware for some
  * predefined time. Received interrupt will be generated when one of the
- * following events occur.
+ * following events occurs.
  * a) Expiration of hardware timer whose expiration time is set to maximum
  * coalescing delay of matching coalesce rule.
  * b) Coalescing buffer in hardware reaches its limit.
@@ -174,7 +174,7 @@
  * rule.
  * a) Maximum coalescing delay
  * b) List of packet patterns which needs to be matched
- * c) Condition for coalescence. pattern 'match' or 'no match'
+ * c) Condition for coalescence: pattern 'match' or 'no match'
  * Multiple such rules can be created.
  */
 
@@ -213,7 +213,7 @@
 /**
  * DOC: FILS shared key authentication offload
  *
- * FILS shared key authentication offload can be advertized by drivers by
+ * FILS shared key authentication offload can be advertised by drivers by
  * setting @NL80211_EXT_FEATURE_FILS_SK_OFFLOAD flag. The drivers that support
  * FILS shared key authentication offload should be able to construct the
  * authentication and association frames for FILS shared key authentication and
@@ -239,7 +239,7 @@
  * The PMKSA can be maintained in userspace persistently so that it can be used
  * later after reboots or wifi turn off/on also.
  *
- * %NL80211_ATTR_FILS_CACHE_ID is the cache identifier advertized by a FILS
+ * %NL80211_ATTR_FILS_CACHE_ID is the cache identifier advertised by a FILS
  * capable AP supporting PMK caching. It specifies the scope within which the
  * PMKSAs are cached in an ESS. %NL80211_CMD_SET_PMKSA and
  * %NL80211_CMD_DEL_PMKSA are enhanced to allow support for PMKSA caching based
@@ -290,12 +290,12 @@
  * If the configuration needs to be applied for specific peer then the MAC
  * address of the peer needs to be passed in %NL80211_ATTR_MAC, otherwise the
  * configuration will be applied for all the connected peers in the vif except
- * any peers that have peer specific configuration for the TID by default; if
- * the %NL80211_TID_CONFIG_ATTR_OVERRIDE flag is set, peer specific values
+ * any peers that have peer-specific configuration for the TID by default; if
+ * the %NL80211_TID_CONFIG_ATTR_OVERRIDE flag is set, peer-specific values
  * will be overwritten.
  *
- * All this configuration is valid only for STA's current connection
- * i.e. the configuration will be reset to default when the STA connects back
+ * All this configuration is valid only for STA's current connection,
+ * i.e., the configuration will be reset to default when the STA connects back
  * after disconnection/roaming, and this configuration will be cleared when
  * the interface goes down.
  */
@@ -521,7 +521,7 @@
  *	%NL80211_ATTR_SCHED_SCAN_PLANS. If %NL80211_ATTR_SCHED_SCAN_PLANS is
  *	not specified and only %NL80211_ATTR_SCHED_SCAN_INTERVAL is specified,
  *	scheduled scan will run in an infinite loop with the specified interval.
- *	These attributes are mutually exculsive,
+ *	These attributes are mutually exclusive,
  *	i.e. NL80211_ATTR_SCHED_SCAN_INTERVAL must not be passed if
  *	NL80211_ATTR_SCHED_SCAN_PLANS is defined.
  *	If for some reason scheduled scan is aborted by the driver, all scan
@@ -552,7 +552,7 @@
  *	%NL80211_CMD_STOP_SCHED_SCAN command is received or when the interface
  *	is brought down while a scheduled scan was running.
  *
- * @NL80211_CMD_GET_SURVEY: get survey resuls, e.g. channel occupation
+ * @NL80211_CMD_GET_SURVEY: get survey results, e.g. channel occupation
  *      or noise level
  * @NL80211_CMD_NEW_SURVEY_RESULTS: survey data notification (as a reply to
  *	NL80211_CMD_GET_SURVEY and on the "scan" multicast group)
@@ -563,12 +563,13 @@
  *	using %NL80211_ATTR_SSID, %NL80211_ATTR_FILS_CACHE_ID,
  *	%NL80211_ATTR_PMKID, and %NL80211_ATTR_PMK in case of FILS
  *	authentication where %NL80211_ATTR_FILS_CACHE_ID is the identifier
- *	advertized by a FILS capable AP identifying the scope of PMKSA in an
+ *	advertised by a FILS capable AP identifying the scope of PMKSA in an
  *	ESS.
  * @NL80211_CMD_DEL_PMKSA: Delete a PMKSA cache entry, using %NL80211_ATTR_MAC
  *	(for the BSSID) and %NL80211_ATTR_PMKID or using %NL80211_ATTR_SSID,
  *	%NL80211_ATTR_FILS_CACHE_ID, and %NL80211_ATTR_PMKID in case of FILS
- *	authentication.
+ *	authentication. Additionally in case of SAE offload and OWE offloads
+ *	PMKSA entry can be deleted using %NL80211_ATTR_SSID.
  * @NL80211_CMD_FLUSH_PMKSA: Flush all PMKSA cache entries.
  *
  * @NL80211_CMD_REG_CHANGE: indicates to userspace the regulatory domain
@@ -607,7 +608,7 @@
  *	BSSID in case of station mode). %NL80211_ATTR_SSID is used to specify
  *	the SSID (mainly for association, but is included in authentication
  *	request, too, to help BSS selection. %NL80211_ATTR_WIPHY_FREQ +
- *	%NL80211_ATTR_WIPHY_FREQ_OFFSET is used to specify the frequence of the
+ *	%NL80211_ATTR_WIPHY_FREQ_OFFSET is used to specify the frequency of the
  *	channel in MHz. %NL80211_ATTR_AUTH_TYPE is used to specify the
  *	authentication type. %NL80211_ATTR_IE is used to define IEs
  *	(VendorSpecificInfo, but also including RSN IE and FT IEs) to be added
@@ -816,7 +817,7 @@
  *	reached.
  * @NL80211_CMD_SET_CHANNEL: Set the channel (using %NL80211_ATTR_WIPHY_FREQ
  *	and the attributes determining channel width) the given interface
- *	(identifed by %NL80211_ATTR_IFINDEX) shall operate on.
+ *	(identified by %NL80211_ATTR_IFINDEX) shall operate on.
  *	In case multiple channels are supported by the device, the mechanism
  *	with which it switches channels is implementation-defined.
  *	When a monitor interface is given, it can only switch channel while
@@ -888,7 +889,7 @@
  *	inform userspace of the new replay counter.
  *
  * @NL80211_CMD_PMKSA_CANDIDATE: This is used as an event to inform userspace
- *	of PMKSA caching dandidates.
+ *	of PMKSA caching candidates.
  *
  * @NL80211_CMD_TDLS_OPER: Perform a high-level TDLS command (e.g. link setup).
  *	In addition, this can be used as an event to request userspace to take
@@ -924,7 +925,7 @@
  *
  * @NL80211_CMD_PROBE_CLIENT: Probe an associated station on an AP interface
  *	by sending a null data frame to it and reporting when the frame is
- *	acknowleged. This is used to allow timing out inactive clients. Uses
+ *	acknowledged. This is used to allow timing out inactive clients. Uses
  *	%NL80211_ATTR_IFINDEX and %NL80211_ATTR_MAC. The command returns a
  *	direct reply with an %NL80211_ATTR_COOKIE that is later used to match
  *	up the event with the request. The event includes the same data and
@@ -1135,11 +1136,15 @@
  * @NL80211_CMD_DEL_PMK: For offloaded 4-Way handshake, delete the previously
  *	configured PMK for the authenticator address identified by
  *	%NL80211_ATTR_MAC.
- * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates an 802.1X FT roam was
- *	completed successfully. Drivers that support 4 way handshake offload
- *	should send this event after indicating 802.1X FT assocation with
- *	%NL80211_CMD_ROAM. If the 4 way handshake failed %NL80211_CMD_DISCONNECT
- *	should be indicated instead.
+ * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates port is authorized and
+ *	open for regular data traffic. For STA/P2P-client, this event is sent
+ *	with AP MAC address and for AP/P2P-GO, the event carries the STA/P2P-
+ *	client MAC address.
+ *	Drivers that support 4 way handshake offload should send this event for
+ *	STA/P2P-client after successful 4-way HS or after 802.1X FT following
+ *	NL80211_CMD_CONNECT or NL80211_CMD_ROAM. Drivers using AP/P2P-GO 4-way
+ *	handshake offload should send this event on successful completion of
+ *	4-way handshake with the peer (STA/P2P-client).
  * @NL80211_CMD_CONTROL_PORT_FRAME: Control Port (e.g. PAE) frame TX request
  *	and RX notification.  This command is used both as a request to transmit
  *	a control port frame and as a notification that a control port frame
@@ -1323,6 +1328,11 @@
  *	Multi-Link reconfiguration. %NL80211_ATTR_MLO_LINKS is used to provide
  *	information about the removed STA MLD setup links.
  *
+ * @NL80211_CMD_SET_TID_TO_LINK_MAPPING: Set the TID to Link Mapping for a
+ *      non-AP MLD station. The %NL80211_ATTR_MLO_TTLM_DLINK and
+ *      %NL80211_ATTR_MLO_TTLM_ULINK attributes are used to specify the
+ *      TID to Link mapping for downlink/uplink traffic.
+ *
  * @NL80211_CMD_MAX: highest used command number
  * @__NL80211_CMD_AFTER_LAST: internal use
  */
@@ -1578,6 +1588,8 @@ enum nl80211_commands {
 
 	NL80211_CMD_LINKS_REMOVED,
 
+	NL80211_CMD_SET_TID_TO_LINK_MAPPING,
+
 	/* add new commands above here */
 
 	/* used to define NL80211_CMD_MAX below */
@@ -1835,7 +1847,7 @@ enum nl80211_commands {
  *	using %CMD_CONTROL_PORT_FRAME.  If control port routing over NL80211 is
  *	to be used then userspace must also use the %NL80211_ATTR_SOCKET_OWNER
  *	flag. When used with %NL80211_ATTR_CONTROL_PORT_NO_PREAUTH, pre-auth
- *	frames are not forwared over the control port.
+ *	frames are not forwarded over the control port.
  *
  * @NL80211_ATTR_TESTDATA: Testmode data blob, passed through to the driver.
  *	We recommend using nested, driver-specific attributes within this.
@@ -1972,10 +1984,10 @@ enum nl80211_commands {
  *	bit. Depending on which antennas are selected in the bitmap, 802.11n
  *	drivers can derive which chainmasks to use (if all antennas belonging to
  *	a particular chain are disabled this chain should be disabled) and if
- *	a chain has diversity antennas wether diversity should be used or not.
+ *	a chain has diversity antennas whether diversity should be used or not.
  *	HT capabilities (STBC, TX Beamforming, Antenna selection) can be
  *	derived from the available chains after applying the antenna mask.
- *	Non-802.11n drivers can derive wether to use diversity or not.
+ *	Non-802.11n drivers can derive whether to use diversity or not.
  *	Drivers may reject configurations or RX/TX mask combinations they cannot
  *	support by returning -EINVAL.
  *
@@ -2545,7 +2557,7 @@ enum nl80211_commands {
  *	from successful FILS authentication and is used with
  *	%NL80211_CMD_CONNECT.
  *
- * @NL80211_ATTR_FILS_CACHE_ID: A 2-octet identifier advertized by a FILS AP
+ * @NL80211_ATTR_FILS_CACHE_ID: A 2-octet identifier advertised by a FILS AP
  *	identifying the scope of PMKSAs. This is used with
  *	@NL80211_CMD_SET_PMKSA and @NL80211_CMD_DEL_PMKSA.
  *
@@ -2826,6 +2838,19 @@ enum nl80211_commands {
  * @NL80211_ATTR_MLO_LINK_DISABLED: Flag attribute indicating that the link is
  *	disabled.
  *
+ * @NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA: Include BSS usage data, i.e.
+ *	include BSSes that can only be used in restricted scenarios and/or
+ *	cannot be used at all.
+ *
+ * @NL80211_ATTR_MLO_TTLM_DLINK: Binary attribute specifying the downlink TID to
+ *      link mapping. The length is 8 * sizeof(u16). For each TID the link
+ *      mapping is as defined in section 9.4.2.314 (TID-To-Link Mapping element)
+ *      in Draft P802.11be_D4.0.
+ * @NL80211_ATTR_MLO_TTLM_ULINK: Binary attribute specifying the uplink TID to
+ *      link mapping. The length is 8 * sizeof(u16). For each TID the link
+ *      mapping is as defined in section 9.4.2.314 (TID-To-Link Mapping element)
+ *      in Draft P802.11be_D4.0.
+ *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -3364,6 +3389,11 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_MLO_LINK_DISABLED,
 
+	NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA,
+
+	NL80211_ATTR_MLO_TTLM_DLINK,
+	NL80211_ATTR_MLO_TTLM_ULINK,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -4170,7 +4200,7 @@ enum nl80211_wmm_rule {
  *	(100 * dBm).
  * @NL80211_FREQUENCY_ATTR_DFS_STATE: current state for DFS
  *	(enum nl80211_dfs_state)
- * @NL80211_FREQUENCY_ATTR_DFS_TIME: time in miliseconds for how long
+ * @NL80211_FREQUENCY_ATTR_DFS_TIME: time in milliseconds for how long
  *	this channel is in this DFS state.
  * @NL80211_FREQUENCY_ATTR_NO_HT40_MINUS: HT40- isn't possible with this
  *	channel as the control channel
@@ -4226,6 +4256,14 @@ enum nl80211_wmm_rule {
  *	in current regulatory domain.
  * @NL80211_FREQUENCY_ATTR_PSD: Power spectral density (in dBm) that
  *	is allowed on this channel in current regulatory domain.
+ * @NL80211_FREQUENCY_ATTR_DFS_CONCURRENT: Operation on this channel is
+ *	allowed for peer-to-peer or adhoc communication under the control
+ *	of a DFS master which operates on the same channel (FCC-594280 D01
+ *	Section B.3). Should be used together with %NL80211_RRF_DFS only.
+ * @NL80211_FREQUENCY_ATTR_NO_UHB_VLP_CLIENT: Client connection to VLP AP
+ *	not allowed using this channel
+ * @NL80211_FREQUENCY_ATTR_NO_UHB_AFC_CLIENT: Client connection to AFC AP
+ *	not allowed using this channel
  * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number
  *	currently defined
  * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use
@@ -4265,6 +4303,9 @@ enum nl80211_frequency_attr {
 	NL80211_FREQUENCY_ATTR_NO_320MHZ,
 	NL80211_FREQUENCY_ATTR_NO_EHT,
 	NL80211_FREQUENCY_ATTR_PSD,
+	NL80211_FREQUENCY_ATTR_DFS_CONCURRENT,
+	NL80211_FREQUENCY_ATTR_NO_UHB_VLP_CLIENT,
+	NL80211_FREQUENCY_ATTR_NO_UHB_AFC_CLIENT,
 
 	/* keep last */
 	__NL80211_FREQUENCY_ATTR_AFTER_LAST,
@@ -4470,6 +4511,12 @@ enum nl80211_sched_scan_match_attr {
  * @NL80211_RRF_NO_320MHZ: 320MHz operation not allowed
  * @NL80211_RRF_NO_EHT: EHT operation not allowed
  * @NL80211_RRF_PSD: Ruleset has power spectral density value
+ * @NL80211_RRF_DFS_CONCURRENT: Operation on this channel is allowed for
+	peer-to-peer or adhoc communication under the control of a DFS master
+	which operates on the same channel (FCC-594280 D01 Section B.3).
+	Should be used together with %NL80211_RRF_DFS only.
+ * @NL80211_RRF_NO_UHB_VLP_CLIENT: Client connection to VLP AP not allowed
+ * @NL80211_RRF_NO_UHB_AFC_CLIENT: Client connection to AFC AP not allowed
  */
 enum nl80211_reg_rule_flags {
 	NL80211_RRF_NO_OFDM		= 1<<0,
@@ -4491,6 +4538,9 @@ enum nl80211_reg_rule_flags {
 	NL80211_RRF_NO_320MHZ		= 1<<18,
 	NL80211_RRF_NO_EHT		= 1<<19,
 	NL80211_RRF_PSD			= 1<<20,
+	NL80211_RRF_DFS_CONCURRENT	= 1<<21,
+	NL80211_RRF_NO_UHB_VLP_CLIENT	= 1<<22,
+	NL80211_RRF_NO_UHB_AFC_CLIENT	= 1<<23,
 };
 
 #define NL80211_RRF_PASSIVE_SCAN	NL80211_RRF_NO_IR
@@ -5028,6 +5078,33 @@ enum nl80211_bss_scan_width {
 };
 
 /**
+ * enum nl80211_bss_use_for - bitmap indicating possible BSS use
+ * @NL80211_BSS_USE_FOR_NORMAL: Use this BSS for normal "connection",
+ *	including IBSS/MBSS depending on the type.
+ * @NL80211_BSS_USE_FOR_MLD_LINK: This BSS can be used as a link in an
+ *	MLO connection. Note that for an MLO connection, all links including
+ *	the assoc link must have this flag set, and the assoc link must
+ *	additionally have %NL80211_BSS_USE_FOR_NORMAL set.
+ */
+enum nl80211_bss_use_for {
+	NL80211_BSS_USE_FOR_NORMAL = 1 << 0,
+	NL80211_BSS_USE_FOR_MLD_LINK = 1 << 1,
+};
+
+/**
+ * enum nl80211_bss_cannot_use_reasons - reason(s) connection to a
+ *	BSS isn't possible
+ * @NL80211_BSS_CANNOT_USE_NSTR_NONPRIMARY: NSTR nonprimary links aren't
+ *	supported by the device, and this BSS entry represents one.
+ * @NL80211_BSS_CANNOT_USE_UHB_PWR_MISMATCH: STA is not supporting
+ *	the AP power type (SP, VLP, AP) that the AP uses.
+ */
+enum nl80211_bss_cannot_use_reasons {
+	NL80211_BSS_CANNOT_USE_NSTR_NONPRIMARY	= 1 << 0,
+	NL80211_BSS_CANNOT_USE_UHB_PWR_MISMATCH	= 1 << 1,
+};
+
+/**
  * enum nl80211_bss - netlink attributes for a BSS
  *
  * @__NL80211_BSS_INVALID: invalid
@@ -5079,6 +5156,14 @@ enum nl80211_bss_scan_width {
  * @NL80211_BSS_FREQUENCY_OFFSET: frequency offset in KHz
  * @NL80211_BSS_MLO_LINK_ID: MLO link ID of the BSS (u8).
  * @NL80211_BSS_MLD_ADDR: MLD address of this BSS if connected to it.
+ * @NL80211_BSS_USE_FOR: u32 bitmap attribute indicating what the BSS can be
+ *	used for, see &enum nl80211_bss_use_for.
+ * @NL80211_BSS_CANNOT_USE_REASONS: Indicates the reason that this BSS cannot
+ *	be used for all or some of the possible uses by the device reporting it,
+ *	even though its presence was detected.
+ *	This is a u64 attribute containing a bitmap of values from
+ *	&enum nl80211_cannot_use_reasons, note that the attribute may be missing
+ *	if no reasons are specified.
  * @__NL80211_BSS_AFTER_LAST: internal
  * @NL80211_BSS_MAX: highest BSS attribute
  */
@@ -5106,6 +5191,8 @@ enum nl80211_bss {
 	NL80211_BSS_FREQUENCY_OFFSET,
 	NL80211_BSS_MLO_LINK_ID,
 	NL80211_BSS_MLD_ADDR,
+	NL80211_BSS_USE_FOR,
+	NL80211_BSS_CANNOT_USE_REASONS,
 
 	/* keep last */
 	__NL80211_BSS_AFTER_LAST,
@@ -5454,7 +5541,7 @@ enum nl80211_tx_rate_setting {
  *	(%NL80211_TID_CONFIG_ATTR_TIDS, %NL80211_TID_CONFIG_ATTR_OVERRIDE).
  * @NL80211_TID_CONFIG_ATTR_PEER_SUPP: same as the previous per-vif one, but
  *	per peer instead.
- * @NL80211_TID_CONFIG_ATTR_OVERRIDE: flag attribue, if set indicates
+ * @NL80211_TID_CONFIG_ATTR_OVERRIDE: flag attribute, if set indicates
  *	that the new configuration overrides all previous peer
  *	configurations, otherwise previous peer specific configurations
  *	should be left untouched.
@@ -5837,7 +5924,7 @@ enum nl80211_attr_coalesce_rule {
 
 /**
  * enum nl80211_coalesce_condition - coalesce rule conditions
- * @NL80211_COALESCE_CONDITION_MATCH: coalaesce Rx packets when patterns
+ * @NL80211_COALESCE_CONDITION_MATCH: coalesce Rx packets when patterns
  *	in a rule are matched.
  * @NL80211_COALESCE_CONDITION_NO_MATCH: coalesce Rx packets when patterns
  *	in a rule are not matched.
@@ -5936,7 +6023,7 @@ enum nl80211_if_combination_attrs {
  * enum nl80211_plink_state - state of a mesh peer link finite state machine
  *
  * @NL80211_PLINK_LISTEN: initial state, considered the implicit
- *	state of non existent mesh peer links
+ *	state of non-existent mesh peer links
  * @NL80211_PLINK_OPN_SNT: mesh plink open frame has been sent to
  *	this mesh peer
  * @NL80211_PLINK_OPN_RCVD: mesh plink open frame has been received
@@ -6229,7 +6316,7 @@ enum nl80211_feature_flags {
  *	request to use RRM (see %NL80211_ATTR_USE_RRM) with
  *	%NL80211_CMD_ASSOCIATE and %NL80211_CMD_CONNECT requests, which will set
  *	the ASSOC_REQ_USE_RRM flag in the association request even if
- *	NL80211_FEATURE_QUIET is not advertized.
+ *	NL80211_FEATURE_QUIET is not advertised.
  * @NL80211_EXT_FEATURE_MU_MIMO_AIR_SNIFFER: This device supports MU-MIMO air
  *	sniffer which means that it can be configured to hear packets from
  *	certain groups which can be configured by the
@@ -6241,13 +6328,15 @@ enum nl80211_feature_flags {
  *	the BSS that the interface that requested the scan is connected to
  *	(if available).
  * @NL80211_EXT_FEATURE_BSS_PARENT_TSF: Per BSS, this driver reports the
- *	time the last beacon/probe was received. The time is the TSF of the
- *	BSS that the interface that requested the scan is connected to
- *	(if available).
+ *	time the last beacon/probe was received. For a non-MLO connection, the
+ *	time is the TSF of the BSS that the interface that requested the scan is
+ *	connected to (if available). For an MLO connection, the time is the TSF
+ *	of the BSS corresponding with link ID specified in the scan request (if
+ *	specified).
  * @NL80211_EXT_FEATURE_SET_SCAN_DWELL: This driver supports configuration of
  *	channel dwell time.
  * @NL80211_EXT_FEATURE_BEACON_RATE_LEGACY: Driver supports beacon rate
- *	configuration (AP/mesh), supporting a legacy (non HT/VHT) rate.
+ *	configuration (AP/mesh), supporting a legacy (non-HT/VHT) rate.
  * @NL80211_EXT_FEATURE_BEACON_RATE_HT: Driver supports beacon rate
  *	configuration (AP/mesh) with HT rates.
  * @NL80211_EXT_FEATURE_BEACON_RATE_VHT: Driver supports beacon rate
@@ -6426,6 +6515,11 @@ enum nl80211_feature_flags {
  * @NL80211_EXT_FEATURE_OWE_OFFLOAD_AP: Driver/Device wants to do OWE DH IE
  *	handling in AP mode.
  *
+ * @NL80211_EXT_FEATURE_DFS_CONCURRENT: The device supports peer-to-peer or
+ *	ad hoc operation on DFS channels under the control of a concurrent
+ *	DFS master on the same channel as described in FCC-594280 D01
+ *	(Section B.3). This, for example, allows P2P GO and P2P clients to
+ *	operate on DFS channels as long as there's a concurrent BSS connection.
  * @NUM_NL80211_EXT_FEATURES: number of extended features.
  * @MAX_NL80211_EXT_FEATURES: highest extended feature index.
  */
@@ -6499,6 +6593,7 @@ enum nl80211_ext_feature_index {
 	NL80211_EXT_FEATURE_AUTH_AND_DEAUTH_RANDOM_TA,
 	NL80211_EXT_FEATURE_OWE_OFFLOAD,
 	NL80211_EXT_FEATURE_OWE_OFFLOAD_AP,
+	NL80211_EXT_FEATURE_DFS_CONCURRENT,
 
 	/* add new features before the definition below */
 	NUM_NL80211_EXT_FEATURES,
@@ -6583,7 +6678,7 @@ enum nl80211_timeout_reason {
  *	request parameters IE in the probe request
  * @NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP: accept broadcast probe responses
  * @NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE: send probe request frames at
- *	rate of at least 5.5M. In case non OCE AP is discovered in the channel,
+ *	rate of at least 5.5M. In case non-OCE AP is discovered in the channel,
  *	only the first probe req in the channel will be sent in high rate.
  * @NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION: allow probe request
  *	tx deferral (dot11FILSProbeDelay shall be set to 15ms)
@@ -6619,7 +6714,7 @@ enum nl80211_timeout_reason {
  *	received on the 2.4/5 GHz channels to actively scan only the 6GHz
  *	channels on which APs are expected to be found. Note that when not set,
  *	the scan logic would scan all 6GHz channels, but since transmission of
- *	probe requests on non PSC channels is limited, it is highly likely that
+ *	probe requests on non-PSC channels is limited, it is highly likely that
  *	these channels would passively be scanned. Also note that when the flag
  *	is set, in addition to the colocated APs, PSC channels would also be
  *	scanned if the user space has asked for it.
@@ -6951,7 +7046,7 @@ enum nl80211_nan_func_term_reason {
  *	The instance ID for the follow up Service Discovery Frame. This is u8.
  * @NL80211_NAN_FUNC_FOLLOW_UP_REQ_ID: relevant if the function's type
  *	is follow up. This is a u8.
- *	The requestor instance ID for the follow up Service Discovery Frame.
+ *	The requester instance ID for the follow up Service Discovery Frame.
  * @NL80211_NAN_FUNC_FOLLOW_UP_DEST: the MAC address of the recipient of the
  *	follow up Service Discovery Frame. This is a binary attribute.
  * @NL80211_NAN_FUNC_CLOSE_RANGE: is this function limited for devices in a
@@ -7341,7 +7436,7 @@ enum nl80211_peer_measurement_attrs {
  * @NL80211_PMSR_FTM_CAPA_ATTR_TRIGGER_BASED: flag attribute indicating if
  *	trigger based ranging measurement is supported
  * @NL80211_PMSR_FTM_CAPA_ATTR_NON_TRIGGER_BASED: flag attribute indicating
- *	if non trigger based ranging measurement is supported
+ *	if non-trigger-based ranging measurement is supported
  *
  * @NUM_NL80211_PMSR_FTM_CAPA_ATTR: internal
  * @NL80211_PMSR_FTM_CAPA_ATTR_MAX: highest attribute number
@@ -7395,7 +7490,7 @@ enum nl80211_peer_measurement_ftm_capa {
  *      if neither %NL80211_PMSR_FTM_REQ_ATTR_TRIGGER_BASED nor
  *	%NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED is set, EDCA based
  *	ranging will be used.
- * @NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED: request non trigger based
+ * @NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED: request non-trigger-based
  *	ranging measurement (flag)
  *	This attribute and %NL80211_PMSR_FTM_REQ_ATTR_TRIGGER_BASED are
  *	mutually exclusive.
@@ -7473,7 +7568,7 @@ enum nl80211_peer_measurement_ftm_failure_reasons {
  * @NL80211_PMSR_FTM_RESP_ATTR_NUM_FTMR_ATTEMPTS: number of FTM Request frames
  *	transmitted (u32, optional)
  * @NL80211_PMSR_FTM_RESP_ATTR_NUM_FTMR_SUCCESSES: number of FTM Request frames
- *	that were acknowleged (u32, optional)
+ *	that were acknowledged (u32, optional)
  * @NL80211_PMSR_FTM_RESP_ATTR_BUSY_RETRY_TIME: retry time received from the
  *	busy peer (u32, seconds)
  * @NL80211_PMSR_FTM_RESP_ATTR_NUM_BURSTS_EXP: actual number of bursts exponent
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 39c6a250dd1b..3a64499b0f5d 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -204,6 +204,8 @@ enum perf_branch_sample_type_shift {
 
 	PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT	= 18, /* save privilege mode */
 
+	PERF_SAMPLE_BRANCH_COUNTERS_SHIFT	= 19, /* save occurrences of events on a branch */
+
 	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
 };
 
@@ -235,6 +237,8 @@ enum perf_branch_sample_type {
 
 	PERF_SAMPLE_BRANCH_PRIV_SAVE	= 1U << PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT,
 
+	PERF_SAMPLE_BRANCH_COUNTERS	= 1U << PERF_SAMPLE_BRANCH_COUNTERS_SHIFT,
+
 	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
 
@@ -982,6 +986,12 @@ enum perf_event_type {
 	 *	{ u64                   nr;
 	 *	  { u64	hw_idx; } && PERF_SAMPLE_BRANCH_HW_INDEX
 	 *        { u64 from, to, flags } lbr[nr];
+	 *        #
+	 *        # The format of the counters is decided by the
+	 *        # "branch_counter_nr" and "branch_counter_width",
+	 *        # which are defined in the ABI.
+	 *        #
+	 *        { u64 counters; } cntr[nr] && PERF_SAMPLE_BRANCH_COUNTERS
 	 *      } && PERF_SAMPLE_BRANCH_STACK
 	 *
 	 * 	{ u64			abi; # enum perf_sample_regs_abi
@@ -1427,6 +1437,9 @@ struct perf_branch_entry {
 		reserved:31;
 };
 
+/* Size of used info bits in struct perf_branch_entry */
+#define PERF_BRANCH_ENTRY_INFO_BITS_MAX		33
+
 union perf_sample_weight {
 	__u64		full;
 #if defined(__LITTLE_ENDIAN_BITFIELD)
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index c7082cc60d21..ea277039f89d 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -99,7 +99,7 @@ enum {
  * versions.
  */
 #define TCA_ACT_GACT 5
-#define TCA_ACT_IPT 6
+#define TCA_ACT_IPT 6 /* obsoleted, can be reused */
 #define TCA_ACT_PEDIT 7
 #define TCA_ACT_MIRRED 8
 #define TCA_ACT_NAT 9
@@ -120,7 +120,7 @@ enum tca_id {
 	TCA_ID_UNSPEC = 0,
 	TCA_ID_POLICE = 1,
 	TCA_ID_GACT = TCA_ACT_GACT,
-	TCA_ID_IPT = TCA_ACT_IPT,
+	TCA_ID_IPT = TCA_ACT_IPT, /* Obsoleted, can be reused */
 	TCA_ID_PEDIT = TCA_ACT_PEDIT,
 	TCA_ID_MIRRED = TCA_ACT_MIRRED,
 	TCA_ID_NAT = TCA_ACT_NAT,
@@ -280,37 +280,6 @@ struct tc_u32_pcnt {
 
 #define TC_U32_MAXDEPTH 8
 
-
-/* RSVP filter */
-
-enum {
-	TCA_RSVP_UNSPEC,
-	TCA_RSVP_CLASSID,
-	TCA_RSVP_DST,
-	TCA_RSVP_SRC,
-	TCA_RSVP_PINFO,
-	TCA_RSVP_POLICE,
-	TCA_RSVP_ACT,
-	__TCA_RSVP_MAX
-};
-
-#define TCA_RSVP_MAX (__TCA_RSVP_MAX - 1 )
-
-struct tc_rsvp_gpi {
-	__u32	key;
-	__u32	mask;
-	int	offset;
-};
-
-struct tc_rsvp_pinfo {
-	struct tc_rsvp_gpi dpi;
-	struct tc_rsvp_gpi spi;
-	__u8	protocol;
-	__u8	tunnelid;
-	__u8	tunnelhdr;
-	__u8	pad;
-};
-
 /* ROUTE filter */
 
 enum {
@@ -341,22 +310,6 @@ enum {
 
 #define TCA_FW_MAX (__TCA_FW_MAX - 1)
 
-/* TC index filter */
-
-enum {
-	TCA_TCINDEX_UNSPEC,
-	TCA_TCINDEX_HASH,
-	TCA_TCINDEX_MASK,
-	TCA_TCINDEX_SHIFT,
-	TCA_TCINDEX_FALL_THROUGH,
-	TCA_TCINDEX_CLASSID,
-	TCA_TCINDEX_POLICE,
-	TCA_TCINDEX_ACT,
-	__TCA_TCINDEX_MAX
-};
-
-#define TCA_TCINDEX_MAX     (__TCA_TCINDEX_MAX - 1)
-
 /* Flow filter */
 
 enum {
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index f762a10bfb78..a3cd0c2dc995 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -477,115 +477,6 @@ enum {
 
 #define TCA_HFSC_MAX (__TCA_HFSC_MAX - 1)
 
-
-/* CBQ section */
-
-#define TC_CBQ_MAXPRIO		8
-#define TC_CBQ_MAXLEVEL		8
-#define TC_CBQ_DEF_EWMA		5
-
-struct tc_cbq_lssopt {
-	unsigned char	change;
-	unsigned char	flags;
-#define TCF_CBQ_LSS_BOUNDED	1
-#define TCF_CBQ_LSS_ISOLATED	2
-	unsigned char  	ewma_log;
-	unsigned char  	level;
-#define TCF_CBQ_LSS_FLAGS	1
-#define TCF_CBQ_LSS_EWMA	2
-#define TCF_CBQ_LSS_MAXIDLE	4
-#define TCF_CBQ_LSS_MINIDLE	8
-#define TCF_CBQ_LSS_OFFTIME	0x10
-#define TCF_CBQ_LSS_AVPKT	0x20
-	__u32		maxidle;
-	__u32		minidle;
-	__u32		offtime;
-	__u32		avpkt;
-};
-
-struct tc_cbq_wrropt {
-	unsigned char	flags;
-	unsigned char	priority;
-	unsigned char	cpriority;
-	unsigned char	__reserved;
-	__u32		allot;
-	__u32		weight;
-};
-
-struct tc_cbq_ovl {
-	unsigned char	strategy;
-#define	TC_CBQ_OVL_CLASSIC	0
-#define	TC_CBQ_OVL_DELAY	1
-#define	TC_CBQ_OVL_LOWPRIO	2
-#define	TC_CBQ_OVL_DROP		3
-#define	TC_CBQ_OVL_RCLASSIC	4
-	unsigned char	priority2;
-	__u16		pad;
-	__u32		penalty;
-};
-
-struct tc_cbq_police {
-	unsigned char	police;
-	unsigned char	__res1;
-	unsigned short	__res2;
-};
-
-struct tc_cbq_fopt {
-	__u32		split;
-	__u32		defmap;
-	__u32		defchange;
-};
-
-struct tc_cbq_xstats {
-	__u32		borrows;
-	__u32		overactions;
-	__s32		avgidle;
-	__s32		undertime;
-};
-
-enum {
-	TCA_CBQ_UNSPEC,
-	TCA_CBQ_LSSOPT,
-	TCA_CBQ_WRROPT,
-	TCA_CBQ_FOPT,
-	TCA_CBQ_OVL_STRATEGY,
-	TCA_CBQ_RATE,
-	TCA_CBQ_RTAB,
-	TCA_CBQ_POLICE,
-	__TCA_CBQ_MAX,
-};
-
-#define TCA_CBQ_MAX	(__TCA_CBQ_MAX - 1)
-
-/* dsmark section */
-
-enum {
-	TCA_DSMARK_UNSPEC,
-	TCA_DSMARK_INDICES,
-	TCA_DSMARK_DEFAULT_INDEX,
-	TCA_DSMARK_SET_TC_INDEX,
-	TCA_DSMARK_MASK,
-	TCA_DSMARK_VALUE,
-	__TCA_DSMARK_MAX,
-};
-
-#define TCA_DSMARK_MAX (__TCA_DSMARK_MAX - 1)
-
-/* ATM  section */
-
-enum {
-	TCA_ATM_UNSPEC,
-	TCA_ATM_FD,		/* file/socket descriptor */
-	TCA_ATM_PTR,		/* pointer to descriptor - later */
-	TCA_ATM_HDR,		/* LL header */
-	TCA_ATM_EXCESS,		/* excess traffic class (0 for CLP)  */
-	TCA_ATM_ADDR,		/* PVC address (for output only) */
-	TCA_ATM_STATE,		/* VC state (ATM_VS_*; for output only) */
-	__TCA_ATM_MAX,
-};
-
-#define TCA_ATM_MAX	(__TCA_ATM_MAX - 1)
-
 /* Network emulator */
 
 enum {
diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h
index 6c0aa577730f..5a43c23f53bf 100644
--- a/include/uapi/linux/raid/md_p.h
+++ b/include/uapi/linux/raid/md_p.h
@@ -2,15 +2,11 @@
 /*
    md_p.h : physical layout of Linux RAID devices
           Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman
-	  
+
    This program is free software; you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation; either version 2, or (at your option)
    any later version.
-   
-   You should have received a copy of the GNU General Public License
-   (for example /usr/src/linux/COPYING); if not, write to the Free
-   Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.  
 */
 
 #ifndef _MD_P_H
@@ -237,7 +233,7 @@ struct mdp_superblock_1 {
 	char	set_name[32];	/* set and interpreted by user-space */
 
 	__le64	ctime;		/* lo 40 bits are seconds, top 24 are microseconds or 0*/
-	__le32	level;		/* -4 (multipath), -1 (linear), 0,1,4,5 */
+	__le32	level;		/* 0,1,4,5 */
 	__le32	layout;		/* only for raid5 and raid10 currently */
 	__le64	size;		/* used size of component devices, in 512byte sectors */
 
diff --git a/include/uapi/linux/raid/md_u.h b/include/uapi/linux/raid/md_u.h
index 105307244961..7be89a4906e7 100644
--- a/include/uapi/linux/raid/md_u.h
+++ b/include/uapi/linux/raid/md_u.h
@@ -2,15 +2,11 @@
 /*
    md_u.h : user <=> kernel API between Linux raidtools and RAID drivers
           Copyright (C) 1998 Ingo Molnar
-	  
+
    This program is free software; you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation; either version 2, or (at your option)
    any later version.
-   
-   You should have received a copy of the GNU General Public License
-   (for example /usr/src/linux/COPYING); if not, write to the Free
-   Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.  
 */
 
 #ifndef _UAPI_MD_U_H
@@ -107,11 +103,6 @@ typedef struct mdu_array_info_s {
 
 } mdu_array_info_t;
 
-/* non-obvious values for 'level' */
-#define	LEVEL_MULTIPATH		(-4)
-#define	LEVEL_LINEAR		(-1)
-#define	LEVEL_FAULTY		(-5)
-
 /* we need a value for 'no level specified' and 0
  * means 'raid0', so we need something else.  This is
  * for internal use only
diff --git a/include/uapi/linux/resource.h b/include/uapi/linux/resource.h
index ac5d6a3031db..4fc22908bc09 100644
--- a/include/uapi/linux/resource.h
+++ b/include/uapi/linux/resource.h
@@ -2,7 +2,7 @@
 #ifndef _UAPI_LINUX_RESOURCE_H
 #define _UAPI_LINUX_RESOURCE_H
 
-#include <linux/time.h>
+#include <linux/time_types.h>
 #include <linux/types.h>
 
 /*
diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h
index 837fcd4b0abc..b531e3ef011a 100644
--- a/include/uapi/linux/smc.h
+++ b/include/uapi/linux/smc.h
@@ -160,6 +160,8 @@ enum {
 	SMC_NLA_LGR_D_CHID,		/* u16 */
 	SMC_NLA_LGR_D_PAD,		/* flag */
 	SMC_NLA_LGR_D_V2_COMMON,	/* nest */
+	SMC_NLA_LGR_D_EXT_GID,		/* u64 */
+	SMC_NLA_LGR_D_PEER_EXT_GID,	/* u64 */
 	__SMC_NLA_LGR_D_MAX,
 	SMC_NLA_LGR_D_MAX = __SMC_NLA_LGR_D_MAX - 1
 };
diff --git a/include/uapi/linux/smc_diag.h b/include/uapi/linux/smc_diag.h
index 8cb3a6fef553..58eceb7f5df2 100644
--- a/include/uapi/linux/smc_diag.h
+++ b/include/uapi/linux/smc_diag.h
@@ -107,6 +107,8 @@ struct smcd_diag_dmbinfo {		/* SMC-D Socket internals */
 	__aligned_u64	my_gid;		/* My GID */
 	__aligned_u64	token;		/* Token of DMB */
 	__aligned_u64	peer_token;	/* Token of remote DMBE */
+	__aligned_u64	peer_gid_ext;	/* Peer GID (extended part) */
+	__aligned_u64	my_gid_ext;	/* My GID (extended part) */
 };
 
 #endif /* _UAPI_SMC_DIAG_H_ */
diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h
index 7cab2c65d3d7..2f2ee82d5517 100644
--- a/include/uapi/linux/stat.h
+++ b/include/uapi/linux/stat.h
@@ -154,6 +154,7 @@ struct statx {
 #define STATX_BTIME		0x00000800U	/* Want/got stx_btime */
 #define STATX_MNT_ID		0x00001000U	/* Got stx_mnt_id */
 #define STATX_DIOALIGN		0x00002000U	/* Want/got direct I/O alignment info */
+#define STATX_MNT_ID_UNIQUE	0x00004000U	/* Want/got extended stx_mount_id */
 
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 
diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h
index 5c6c4269f7ef..2ec6f35cda32 100644
--- a/include/uapi/linux/stddef.h
+++ b/include/uapi/linux/stddef.h
@@ -27,7 +27,7 @@
 	union { \
 		struct { MEMBERS } ATTRS; \
 		struct TAG { MEMBERS } ATTRS NAME; \
-	}
+	} ATTRS
 
 #ifdef __cplusplus
 /* sizeof(struct{}) is 1 in C++, not 0, can't use C version of the macro. */
diff --git a/include/uapi/linux/tc_act/tc_ipt.h b/include/uapi/linux/tc_act/tc_ipt.h
deleted file mode 100644
index c48d7da6750d..000000000000
--- a/include/uapi/linux/tc_act/tc_ipt.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef __LINUX_TC_IPT_H
-#define __LINUX_TC_IPT_H
-
-#include <linux/pkt_cls.h>
-
-enum {
-	TCA_IPT_UNSPEC,
-	TCA_IPT_TABLE,
-	TCA_IPT_HOOK,
-	TCA_IPT_INDEX,
-	TCA_IPT_CNT,
-	TCA_IPT_TM,
-	TCA_IPT_TARG,
-	TCA_IPT_PAD,
-	__TCA_IPT_MAX
-};
-#define TCA_IPT_MAX (__TCA_IPT_MAX - 1)
-                                                                                
-#endif
diff --git a/include/uapi/linux/tc_act/tc_mirred.h b/include/uapi/linux/tc_act/tc_mirred.h
index 2500a0005d05..c61e76f3c23b 100644
--- a/include/uapi/linux/tc_act/tc_mirred.h
+++ b/include/uapi/linux/tc_act/tc_mirred.h
@@ -21,6 +21,7 @@ enum {
 	TCA_MIRRED_TM,
 	TCA_MIRRED_PARMS,
 	TCA_MIRRED_PAD,
+	TCA_MIRRED_BLOCKID,
 	__TCA_MIRRED_MAX
 };
 #define TCA_MIRRED_MAX (__TCA_MIRRED_MAX - 1)
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index 0dbc81015018..2841e4ea8f2c 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -41,7 +41,8 @@
 			   UFFD_FEATURE_WP_HUGETLBFS_SHMEM |	\
 			   UFFD_FEATURE_WP_UNPOPULATED |	\
 			   UFFD_FEATURE_POISON |		\
-			   UFFD_FEATURE_WP_ASYNC)
+			   UFFD_FEATURE_WP_ASYNC |		\
+			   UFFD_FEATURE_MOVE)
 #define UFFD_API_IOCTLS				\
 	((__u64)1 << _UFFDIO_REGISTER |		\
 	 (__u64)1 << _UFFDIO_UNREGISTER |	\
@@ -50,6 +51,7 @@
 	((__u64)1 << _UFFDIO_WAKE |		\
 	 (__u64)1 << _UFFDIO_COPY |		\
 	 (__u64)1 << _UFFDIO_ZEROPAGE |		\
+	 (__u64)1 << _UFFDIO_MOVE |		\
 	 (__u64)1 << _UFFDIO_WRITEPROTECT |	\
 	 (__u64)1 << _UFFDIO_CONTINUE |		\
 	 (__u64)1 << _UFFDIO_POISON)
@@ -73,6 +75,7 @@
 #define _UFFDIO_WAKE			(0x02)
 #define _UFFDIO_COPY			(0x03)
 #define _UFFDIO_ZEROPAGE		(0x04)
+#define _UFFDIO_MOVE			(0x05)
 #define _UFFDIO_WRITEPROTECT		(0x06)
 #define _UFFDIO_CONTINUE		(0x07)
 #define _UFFDIO_POISON			(0x08)
@@ -92,6 +95,8 @@
 				      struct uffdio_copy)
 #define UFFDIO_ZEROPAGE		_IOWR(UFFDIO, _UFFDIO_ZEROPAGE,	\
 				      struct uffdio_zeropage)
+#define UFFDIO_MOVE		_IOWR(UFFDIO, _UFFDIO_MOVE,	\
+				      struct uffdio_move)
 #define UFFDIO_WRITEPROTECT	_IOWR(UFFDIO, _UFFDIO_WRITEPROTECT, \
 				      struct uffdio_writeprotect)
 #define UFFDIO_CONTINUE		_IOWR(UFFDIO, _UFFDIO_CONTINUE,	\
@@ -222,6 +227,9 @@ struct uffdio_api {
 	 * asynchronous mode is supported in which the write fault is
 	 * automatically resolved and write-protection is un-set.
 	 * It implies UFFD_FEATURE_WP_UNPOPULATED.
+	 *
+	 * UFFD_FEATURE_MOVE indicates that the kernel supports moving an
+	 * existing page contents from userspace.
 	 */
 #define UFFD_FEATURE_PAGEFAULT_FLAG_WP		(1<<0)
 #define UFFD_FEATURE_EVENT_FORK			(1<<1)
@@ -239,6 +247,7 @@ struct uffdio_api {
 #define UFFD_FEATURE_WP_UNPOPULATED		(1<<13)
 #define UFFD_FEATURE_POISON			(1<<14)
 #define UFFD_FEATURE_WP_ASYNC			(1<<15)
+#define UFFD_FEATURE_MOVE			(1<<16)
 	__u64 features;
 
 	__u64 ioctls;
@@ -347,6 +356,24 @@ struct uffdio_poison {
 	__s64 updated;
 };
 
+struct uffdio_move {
+	__u64 dst;
+	__u64 src;
+	__u64 len;
+	/*
+	 * Especially if used to atomically remove memory from the
+	 * address space the wake on the dst range is not needed.
+	 */
+#define UFFDIO_MOVE_MODE_DONTWAKE		((__u64)1<<0)
+#define UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES	((__u64)1<<1)
+	__u64 mode;
+	/*
+	 * "move" is written by the ioctl and must be at the end: the
+	 * copy_from_user will not read the last 8 bytes.
+	 */
+	__s64 move;
+};
+
 /*
  * Flags for the userfaultfd(2) system call itself.
  */
diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h
index 4a195b68f28f..b383c2fe0cf3 100644
--- a/include/uapi/linux/v4l2-subdev.h
+++ b/include/uapi/linux/v4l2-subdev.h
@@ -239,7 +239,7 @@ struct v4l2_subdev_routing {
  * set (which is the default), the 'stream' fields will be forced to 0 by the
  * kernel.
  */
- #define V4L2_SUBDEV_CLIENT_CAP_STREAMS		(1U << 0)
+ #define V4L2_SUBDEV_CLIENT_CAP_STREAMS		(1ULL << 0)
 
 /**
  * struct v4l2_subdev_client_capability - Capabilities of the client accessing
diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index f703afc7ad31..44f4dd2add18 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -166,6 +166,17 @@ struct virtio_pci_common_cfg {
 	__le32 queue_used_hi;		/* read-write */
 };
 
+/*
+ * Warning: do not use sizeof on this: use offsetofend for
+ * specific fields you need.
+ */
+struct virtio_pci_modern_common_cfg {
+	struct virtio_pci_common_cfg cfg;
+
+	__le16 queue_notify_data;	/* read-write */
+	__le16 queue_reset;		/* read-write */
+};
+
 /* Fields in VIRTIO_PCI_CAP_PCI_CFG: */
 struct virtio_pci_cfg_cap {
 	struct virtio_pci_cap cap;
diff --git a/include/uapi/regulator/regulator.h b/include/uapi/regulator/regulator.h
new file mode 100644
index 000000000000..71bf71a22e7f
--- /dev/null
+++ b/include/uapi/regulator/regulator.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Regulator uapi header
+ *
+ * Author: Naresh Solanki <Naresh.Solanki@9elements.com>
+ */
+
+#ifndef _UAPI_REGULATOR_H
+#define _UAPI_REGULATOR_H
+
+#ifdef __KERNEL__
+#include <linux/types.h>
+#else
+#include <stdint.h>
+#endif
+
+/*
+ * Regulator notifier events.
+ *
+ * UNDER_VOLTAGE  Regulator output is under voltage.
+ * OVER_CURRENT   Regulator output current is too high.
+ * REGULATION_OUT Regulator output is out of regulation.
+ * FAIL           Regulator output has failed.
+ * OVER_TEMP      Regulator over temp.
+ * FORCE_DISABLE  Regulator forcibly shut down by software.
+ * VOLTAGE_CHANGE Regulator voltage changed.
+ *                Data passed is old voltage cast to (void *).
+ * DISABLE        Regulator was disabled.
+ * PRE_VOLTAGE_CHANGE   Regulator is about to have voltage changed.
+ *                      Data passed is "struct pre_voltage_change_data"
+ * ABORT_VOLTAGE_CHANGE Regulator voltage change failed for some reason.
+ *                      Data passed is old voltage cast to (void *).
+ * PRE_DISABLE    Regulator is about to be disabled
+ * ABORT_DISABLE  Regulator disable failed for some reason
+ *
+ * NOTE: These events can be OR'ed together when passed into handler.
+ */
+
+#define REGULATOR_EVENT_UNDER_VOLTAGE		0x01
+#define REGULATOR_EVENT_OVER_CURRENT		0x02
+#define REGULATOR_EVENT_REGULATION_OUT		0x04
+#define REGULATOR_EVENT_FAIL			0x08
+#define REGULATOR_EVENT_OVER_TEMP		0x10
+#define REGULATOR_EVENT_FORCE_DISABLE		0x20
+#define REGULATOR_EVENT_VOLTAGE_CHANGE		0x40
+#define REGULATOR_EVENT_DISABLE			0x80
+#define REGULATOR_EVENT_PRE_VOLTAGE_CHANGE	0x100
+#define REGULATOR_EVENT_ABORT_VOLTAGE_CHANGE	0x200
+#define REGULATOR_EVENT_PRE_DISABLE		0x400
+#define REGULATOR_EVENT_ABORT_DISABLE		0x800
+#define REGULATOR_EVENT_ENABLE			0x1000
+/*
+ * Following notifications should be emitted only if detected condition
+ * is such that the HW is likely to still be working but consumers should
+ * take a recovery action to prevent problems escalating into errors.
+ */
+#define REGULATOR_EVENT_UNDER_VOLTAGE_WARN	0x2000
+#define REGULATOR_EVENT_OVER_CURRENT_WARN	0x4000
+#define REGULATOR_EVENT_OVER_VOLTAGE_WARN	0x8000
+#define REGULATOR_EVENT_OVER_TEMP_WARN		0x10000
+#define REGULATOR_EVENT_WARN_MASK		0x1E000
+
+struct reg_genl_event {
+	char reg_name[32];
+	uint64_t event;
+};
+
+/* attributes of reg_genl_family */
+enum {
+	REG_GENL_ATTR_UNSPEC,
+	REG_GENL_ATTR_EVENT,	/* reg event info needed by user space */
+	__REG_GENL_ATTR_MAX,
+};
+
+#define REG_GENL_ATTR_MAX (__REG_GENL_ATTR_MAX - 1)
+
+/* commands supported by the reg_genl_family */
+enum {
+	REG_GENL_CMD_UNSPEC,
+	REG_GENL_CMD_EVENT,	/* kernel->user notifications for reg events */
+	__REG_GENL_CMD_MAX,
+};
+
+#define REG_GENL_CMD_MAX (__REG_GENL_CMD_MAX - 1)
+
+#define REG_GENL_FAMILY_NAME		"reg_event"
+#define REG_GENL_VERSION		0x01
+#define REG_GENL_MCAST_GROUP_NAME	"reg_mc_group"
+
+#endif /* _UAPI_REGULATOR_H */
diff --git a/include/uapi/scsi/scsi_bsg_mpi3mr.h b/include/uapi/scsi/scsi_bsg_mpi3mr.h
index 907d345f04f9..c72ce387286a 100644
--- a/include/uapi/scsi/scsi_bsg_mpi3mr.h
+++ b/include/uapi/scsi/scsi_bsg_mpi3mr.h
@@ -491,6 +491,8 @@ struct mpi3_nvme_encapsulated_error_reply {
 #define MPI3MR_NVME_DATA_FORMAT_PRP	0
 #define MPI3MR_NVME_DATA_FORMAT_SGL1	1
 #define MPI3MR_NVME_DATA_FORMAT_SGL2	2
+#define MPI3MR_NVMESGL_DATA_SEGMENT	0x00
+#define MPI3MR_NVMESGL_LAST_SEGMENT	0x03
 
 /* MPI3: task management related definitions */
 struct mpi3_scsi_task_mgmt_request {
diff --git a/include/ufs/ufs.h b/include/ufs/ufs.h
index e77ab1786856..b6003749bc83 100644
--- a/include/ufs/ufs.h
+++ b/include/ufs/ufs.h
@@ -14,6 +14,7 @@
 #include <linux/bitops.h>
 #include <linux/types.h>
 #include <uapi/scsi/scsi_bsg_ufs.h>
+#include <linux/time64.h>
 
 /*
  * Using static_assert() is not allowed in UAPI header files. Hence the check
@@ -551,6 +552,14 @@ struct ufs_vreg_info {
 	struct ufs_vreg *vdd_hba;
 };
 
+/* UFS device descriptor wPeriodicRTCUpdate bit9 defines RTC time baseline */
+#define UFS_RTC_TIME_BASELINE BIT(9)
+
+enum ufs_rtc_time {
+	UFS_RTC_RELATIVE,
+	UFS_RTC_ABSOLUTE
+};
+
 struct ufs_dev_info {
 	bool	f_power_on_wp_en;
 	/* Keeps information if any of the LU is power on write protected */
@@ -578,6 +587,11 @@ struct ufs_dev_info {
 
 	/* UFS EXT_IID Enable */
 	bool	b_ext_iid_en;
+
+	/* UFS RTC */
+	enum ufs_rtc_time rtc_type;
+	time64_t rtc_time_baseline;
+	u32 rtc_update_period;
 };
 
 /*
diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index 7f0b2c5599cd..8e2bce9a4f21 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -16,6 +16,7 @@
 #include <linux/blk-crypto-profile.h>
 #include <linux/blk-mq.h>
 #include <linux/devfreq.h>
+#include <linux/fault-inject.h>
 #include <linux/msi.h>
 #include <linux/pm_runtime.h>
 #include <linux/dma-direction.h>
@@ -911,6 +912,8 @@ enum ufshcd_mcq_opr {
  * @mcq_base: Multi circular queue registers base address
  * @uhq: array of supported hardware queues
  * @dev_cmd_queue: Queue for issuing device management commands
+ * @mcq_opr: MCQ operation and runtime registers
+ * @ufs_rtc_update_work: A work for UFS RTC periodic update
  */
 struct ufs_hba {
 	void __iomem *mmio_base;
@@ -1058,6 +1061,10 @@ struct ufs_hba {
 	struct delayed_work debugfs_ee_work;
 	u32 debugfs_ee_rate_limit_ms;
 #endif
+#ifdef CONFIG_SCSI_UFS_FAULT_INJECTION
+	struct fault_attr trigger_eh_attr;
+	struct fault_attr timeout_attr;
+#endif
 	u32 luns_avail;
 	unsigned int nr_hw_queues;
 	unsigned int nr_queues[HCTX_MAX_TYPES];
@@ -1071,6 +1078,8 @@ struct ufs_hba {
 	struct ufs_hw_queue *uhq;
 	struct ufs_hw_queue *dev_cmd_queue;
 	struct ufshcd_mcq_opr_info_t mcq_opr[OPR_MAX];
+
+	struct delayed_work ufs_rtc_update_work;
 };
 
 /**
@@ -1231,6 +1240,8 @@ static inline void ufshcd_rmwl(struct ufs_hba *hba, u32 mask, u32 val, u32 reg)
 	ufshcd_writel(hba, tmp, reg);
 }
 
+void ufshcd_enable_irq(struct ufs_hba *hba);
+void ufshcd_disable_irq(struct ufs_hba *hba);
 int ufshcd_alloc_host(struct device *, struct ufs_hba **);
 void ufshcd_dealloc_host(struct ufs_hba *);
 int ufshcd_hba_enable(struct ufs_hba *hba);
@@ -1360,7 +1371,6 @@ static inline int ufshcd_disable_host_tx_lcc(struct ufs_hba *hba)
 	return ufshcd_dme_set(hba, UIC_ARG_MIB(PA_LOCAL_TX_LCC_ENABLE), 0);
 }
 
-void ufshcd_auto_hibern8_enable(struct ufs_hba *hba);
 void ufshcd_auto_hibern8_update(struct ufs_hba *hba, u32 ahit);
 void ufshcd_fixup_dev_quirks(struct ufs_hba *hba,
 			     const struct ufs_dev_quirk *fixups);
diff --git a/include/ufs/unipro.h b/include/ufs/unipro.h
index 256eb3a43f54..360e1245fb40 100644
--- a/include/ufs/unipro.h
+++ b/include/ufs/unipro.h
@@ -193,7 +193,7 @@
 #define DME_LocalAFC0ReqTimeOutVal		0xD043
 
 /* PA power modes */
-enum {
+enum ufs_pa_pwr_mode {
 	FAST_MODE	= 1,
 	SLOW_MODE	= 2,
 	FASTAUTO_MODE	= 4,
@@ -205,7 +205,7 @@ enum {
 #define PWRMODE_RX_OFFSET	4
 
 /* PA TX/RX Frequency Series */
-enum {
+enum ufs_hs_gear_rate {
 	PA_HS_MODE_A	= 1,
 	PA_HS_MODE_B	= 2,
 };
diff --git a/include/vdso/gettime.h b/include/vdso/gettime.h
new file mode 100644
index 000000000000..c50d152e7b3e
--- /dev/null
+++ b/include/vdso/gettime.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _VDSO_GETTIME_H
+#define _VDSO_GETTIME_H
+
+#include <linux/types.h>
+
+struct __kernel_timespec;
+struct timezone;
+
+#if !defined(CONFIG_64BIT) || defined(BUILD_VDSO32_64)
+struct old_timespec32;
+int __vdso_clock_getres(clockid_t clock, struct old_timespec32 *res);
+int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts);
+#else
+int __vdso_clock_getres(clockid_t clock, struct __kernel_timespec *res);
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
+#endif
+
+__kernel_old_time_t __vdso_time(__kernel_old_time_t *t);
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
+int __vdso_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts);
+
+#endif
diff --git a/include/xen/events.h b/include/xen/events.h
index 23932b0673dc..3b07409f8032 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -88,7 +88,6 @@ void xen_irq_resume(void);
 
 /* Clear an irq's pending state, in preparation for polling on it */
 void xen_clear_irq_pending(int irq);
-void xen_set_irq_pending(int irq);
 bool xen_test_irq_pending(int irq);
 
 /* Poll waiting for an irq to become pending.  In the usual case, the
@@ -101,8 +100,8 @@ void xen_poll_irq_timeout(int irq, u64 timeout);
 
 /* Determine the IRQ which is bound to an event channel */
 unsigned int irq_from_evtchn(evtchn_port_t evtchn);
-int irq_from_virq(unsigned int cpu, unsigned int virq);
-evtchn_port_t evtchn_from_irq(unsigned irq);
+int irq_evtchn_from_virq(unsigned int cpu, unsigned int virq,
+			 evtchn_port_t *evtchn);
 
 int xen_set_callback_via(uint64_t via);
 int xen_evtchn_do_upcall(void);
@@ -122,9 +121,6 @@ int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
 /* De-allocates the above mentioned physical interrupt. */
 int xen_destroy_irq(int irq);
 
-/* Return irq from pirq */
-int xen_irq_from_pirq(unsigned pirq);
-
 /* Return the pirq allocated to the irq. */
 int xen_pirq_from_irq(unsigned irq);
 
diff --git a/init/Kconfig b/init/Kconfig
index 9ffb103fc927..8df18f3a9748 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1676,6 +1676,56 @@ config MEMBARRIER
 
 	  If unsure, say Y.
 
+config KCMP
+	bool "Enable kcmp() system call" if EXPERT
+	help
+	  Enable the kernel resource comparison system call. It provides
+	  user-space with the ability to compare two processes to see if they
+	  share a common resource, such as a file descriptor or even virtual
+	  memory space.
+
+	  If unsure, say N.
+
+config RSEQ
+	bool "Enable rseq() system call" if EXPERT
+	default y
+	depends on HAVE_RSEQ
+	select MEMBARRIER
+	help
+	  Enable the restartable sequences system call. It provides a
+	  user-space cache for the current CPU number value, which
+	  speeds up getting the current CPU number from user-space,
+	  as well as an ABI to speed up user-space operations on
+	  per-CPU data.
+
+	  If unsure, say Y.
+
+config DEBUG_RSEQ
+	default n
+	bool "Enable debugging of rseq() system call" if EXPERT
+	depends on RSEQ && DEBUG_KERNEL
+	help
+	  Enable extra debugging checks for the rseq system call.
+
+	  If unsure, say N.
+
+config CACHESTAT_SYSCALL
+	bool "Enable cachestat() system call" if EXPERT
+	default y
+	help
+	  Enable the cachestat system call, which queries the page cache
+	  statistics of a file (number of cached pages, dirty pages,
+	  pages marked for writeback, (recently) evicted pages).
+
+	  If unsure say Y here.
+
+config PC104
+	bool "PC/104 support" if EXPERT
+	help
+	  Expose PC/104 form factor device drivers and options available for
+	  selection and configuration. Enable this option if your target
+	  machine has a PC/104 bus.
+
 config KALLSYMS
 	bool "Load all symbols for debugging/ksymoops" if EXPERT
 	default y
@@ -1740,57 +1790,12 @@ config KALLSYMS_BASE_RELATIVE
 
 # end of the "standard kernel features (expert users)" menu
 
-# syscall, maps, verifier
-
 config ARCH_HAS_MEMBARRIER_CALLBACKS
 	bool
 
 config ARCH_HAS_MEMBARRIER_SYNC_CORE
 	bool
 
-config KCMP
-	bool "Enable kcmp() system call" if EXPERT
-	help
-	  Enable the kernel resource comparison system call. It provides
-	  user-space with the ability to compare two processes to see if they
-	  share a common resource, such as a file descriptor or even virtual
-	  memory space.
-
-	  If unsure, say N.
-
-config RSEQ
-	bool "Enable rseq() system call" if EXPERT
-	default y
-	depends on HAVE_RSEQ
-	select MEMBARRIER
-	help
-	  Enable the restartable sequences system call. It provides a
-	  user-space cache for the current CPU number value, which
-	  speeds up getting the current CPU number from user-space,
-	  as well as an ABI to speed up user-space operations on
-	  per-CPU data.
-
-	  If unsure, say Y.
-
-config CACHESTAT_SYSCALL
-	bool "Enable cachestat() system call" if EXPERT
-	default y
-	help
-	  Enable the cachestat system call, which queries the page cache
-	  statistics of a file (number of cached pages, dirty pages,
-	  pages marked for writeback, (recently) evicted pages).
-
-	  If unsure say Y here.
-
-config DEBUG_RSEQ
-	default n
-	bool "Enabled debugging of rseq() system call" if EXPERT
-	depends on RSEQ && DEBUG_KERNEL
-	help
-	  Enable extra debugging checks for the rseq system call.
-
-	  If unsure, say N.
-
 config HAVE_PERF_EVENTS
 	bool
 	help
@@ -1805,13 +1810,6 @@ config PERF_USE_VMALLOC
 	help
 	  See tools/perf/design.txt for details
 
-config PC104
-	bool "PC/104 support" if EXPERT
-	help
-	  Expose PC/104 form factor device drivers and options available for
-	  selection and configuration. Enable this option if your target
-	  machine has a PC/104 bus.
-
 menu "Kernel Performance Events And Counters"
 
 config PERF_EVENTS
diff --git a/init/init_task.c b/init/init_task.c
index 5727d42149c3..7ecb458eb3da 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -12,6 +12,7 @@
 #include <linux/audit.h>
 #include <linux/numa.h>
 #include <linux/scs.h>
+#include <linux/plist.h>
 
 #include <linux/uaccess.h>
 
@@ -51,8 +52,7 @@ static struct sighand_struct init_sighand = {
 };
 
 #ifdef CONFIG_SHADOW_CALL_STACK
-unsigned long init_shadow_call_stack[SCS_SIZE / sizeof(long)]
-		__init_task_data = {
+unsigned long init_shadow_call_stack[SCS_SIZE / sizeof(long)] = {
 	[(SCS_SIZE / sizeof(long)) - 1] = SCS_END_MAGIC
 };
 #endif
@@ -61,12 +61,7 @@ unsigned long init_shadow_call_stack[SCS_SIZE / sizeof(long)]
  * Set up the first task table, touch at your own risk!. Base=0,
  * limit=0x1fffff (=2MB)
  */
-struct task_struct init_task
-#ifdef CONFIG_ARCH_TASK_STRUCT_ON_STACK
-	__init_task_data
-#endif
-	__aligned(L1_CACHE_BYTES)
-= {
+struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 	.thread_info	= INIT_THREAD_INFO(init_task),
 	.stack_refcount	= REFCOUNT_INIT(1),
diff --git a/io_uring/Makefile b/io_uring/Makefile
index e5be47e4fc3b..2cdc51825405 100644
--- a/io_uring/Makefile
+++ b/io_uring/Makefile
@@ -8,6 +8,6 @@ obj-$(CONFIG_IO_URING)		+= io_uring.o xattr.o nop.o fs.o splice.o \
 					statx.o net.o msg_ring.o timeout.o \
 					sqpoll.o fdinfo.o tctx.o poll.o \
 					cancel.o kbuf.o rsrc.o rw.o opdef.o \
-					notif.o waitid.o
+					notif.o waitid.o register.o
 obj-$(CONFIG_IO_WQ)		+= io-wq.o
 obj-$(CONFIG_FUTEX)		+= futex.o
diff --git a/io_uring/alloc_cache.h b/io_uring/alloc_cache.h
index 241245cb54a6..bf2fb26a6539 100644
--- a/io_uring/alloc_cache.h
+++ b/io_uring/alloc_cache.h
@@ -16,8 +16,7 @@ static inline bool io_alloc_cache_put(struct io_alloc_cache *cache,
 	if (cache->nr_cached < cache->max_cached) {
 		cache->nr_cached++;
 		wq_stack_add_head(&entry->node, &cache->list);
-		/* KASAN poisons object */
-		kasan_slab_free_mempool(entry);
+		kasan_mempool_poison_object(entry);
 		return true;
 	}
 	return false;
@@ -34,7 +33,7 @@ static inline struct io_cache_entry *io_alloc_cache_get(struct io_alloc_cache *c
 		struct io_cache_entry *entry;
 
 		entry = container_of(cache->list.next, struct io_cache_entry, node);
-		kasan_unpoison_range(entry, cache->elem_size);
+		kasan_mempool_unpoison_object(entry, cache->elem_size);
 		cache->list.next = cache->list.next->next;
 		cache->nr_cached--;
 		return entry;
diff --git a/io_uring/cancel.c b/io_uring/cancel.c
index 3c19cccb1aec..8a8b07dfc444 100644
--- a/io_uring/cancel.c
+++ b/io_uring/cancel.c
@@ -273,7 +273,7 @@ int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg)
 	};
 	ktime_t timeout = KTIME_MAX;
 	struct io_uring_sync_cancel_reg sc;
-	struct fd f = { };
+	struct file *file = NULL;
 	DEFINE_WAIT(wait);
 	int ret, i;
 
@@ -295,10 +295,10 @@ int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg)
 	/* we can grab a normal file descriptor upfront */
 	if ((cd.flags & IORING_ASYNC_CANCEL_FD) &&
 	   !(cd.flags & IORING_ASYNC_CANCEL_FD_FIXED)) {
-		f = fdget(sc.fd);
-		if (!f.file)
+		file = fget(sc.fd);
+		if (!file)
 			return -EBADF;
-		cd.file = f.file;
+		cd.file = file;
 	}
 
 	ret = __io_sync_cancel(current->io_uring, &cd, sc.fd);
@@ -348,6 +348,7 @@ int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg)
 	if (ret == -ENOENT || ret > 0)
 		ret = 0;
 out:
-	fdput(f);
+	if (file)
+		fput(file);
 	return ret;
 }
diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
index f04a43044d91..976e9500f651 100644
--- a/io_uring/fdinfo.c
+++ b/io_uring/fdinfo.c
@@ -145,13 +145,8 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
 	if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) {
 		struct io_sq_data *sq = ctx->sq_data;
 
-		if (mutex_trylock(&sq->lock)) {
-			if (sq->thread) {
-				sq_pid = task_pid_nr(sq->thread);
-				sq_cpu = task_cpu(sq->thread);
-			}
-			mutex_unlock(&sq->lock);
-		}
+		sq_pid = sq->task_pid;
+		sq_cpu = sq->sq_cpu;
 	}
 
 	seq_printf(m, "SqThread:\t%d\n", sq_pid);
diff --git a/io_uring/filetable.c b/io_uring/filetable.c
index e7d749991de4..6e86e6188dbe 100644
--- a/io_uring/filetable.c
+++ b/io_uring/filetable.c
@@ -87,13 +87,10 @@ static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file,
 		io_file_bitmap_clear(&ctx->file_table, slot_index);
 	}
 
-	ret = io_scm_file_account(ctx, file);
-	if (!ret) {
-		*io_get_tag_slot(ctx->file_data, slot_index) = 0;
-		io_fixed_file_set(file_slot, file);
-		io_file_bitmap_set(&ctx->file_table, slot_index);
-	}
-	return ret;
+	*io_get_tag_slot(ctx->file_data, slot_index) = 0;
+	io_fixed_file_set(file_slot, file);
+	io_file_bitmap_set(&ctx->file_table, slot_index);
+	return 0;
 }
 
 int __io_fixed_fd_install(struct io_ring_ctx *ctx, struct file *file,
diff --git a/io_uring/fs.c b/io_uring/fs.c
index 08e3b175469c..eccea851dd5a 100644
--- a/io_uring/fs.c
+++ b/io_uring/fs.c
@@ -254,7 +254,7 @@ int io_linkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	newf = u64_to_user_ptr(READ_ONCE(sqe->addr2));
 	lnk->flags = READ_ONCE(sqe->hardlink_flags);
 
-	lnk->oldpath = getname(oldf);
+	lnk->oldpath = getname_uflags(oldf, lnk->flags);
 	if (IS_ERR(lnk->oldpath))
 		return PTR_ERR(lnk->oldpath);
 
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index ed254076c723..09b6d860deba 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -60,7 +60,6 @@
 #include <linux/net.h>
 #include <net/sock.h>
 #include <net/af_unix.h>
-#include <net/scm.h>
 #include <linux/anon_inodes.h>
 #include <linux/sched/mm.h>
 #include <linux/uaccess.h>
@@ -70,6 +69,7 @@
 #include <linux/fadvise.h>
 #include <linux/task_work.h>
 #include <linux/io_uring.h>
+#include <linux/io_uring/cmd.h>
 #include <linux/audit.h>
 #include <linux/security.h>
 #include <asm/shmparam.h>
@@ -85,6 +85,7 @@
 #include "opdef.h"
 #include "refs.h"
 #include "tctx.h"
+#include "register.h"
 #include "sqpoll.h"
 #include "fdinfo.h"
 #include "kbuf.h"
@@ -103,9 +104,6 @@
 #define IORING_MAX_ENTRIES	32768
 #define IORING_MAX_CQ_ENTRIES	(2 * IORING_MAX_ENTRIES)
 
-#define IORING_MAX_RESTRICTIONS	(IORING_RESTRICTION_LAST + \
-				 IORING_REGISTER_LAST + IORING_OP_LAST)
-
 #define SQE_COMMON_FLAGS (IOSQE_FIXED_FILE | IOSQE_IO_LINK | \
 			  IOSQE_IO_HARDLINK | IOSQE_ASYNC)
 
@@ -129,11 +127,6 @@ enum {
 	IO_CHECK_CQ_DROPPED_BIT,
 };
 
-enum {
-	IO_EVENTFD_OP_SIGNAL_BIT,
-	IO_EVENTFD_OP_FREE_BIT,
-};
-
 struct io_defer_entry {
 	struct list_head	list;
 	struct io_kiocb		*req;
@@ -177,19 +170,6 @@ static struct ctl_table kernel_io_uring_disabled_table[] = {
 };
 #endif
 
-struct sock *io_uring_get_socket(struct file *file)
-{
-#if defined(CONFIG_UNIX)
-	if (io_is_uring_fops(file)) {
-		struct io_ring_ctx *ctx = file->private_data;
-
-		return ctx->ring_sock->sk;
-	}
-#endif
-	return NULL;
-}
-EXPORT_SYMBOL(io_uring_get_socket);
-
 static inline void io_submit_flush_completions(struct io_ring_ctx *ctx)
 {
 	if (!wq_list_empty(&ctx->submit_state.compl_reqs) ||
@@ -271,6 +251,7 @@ static __cold void io_fallback_req_func(struct work_struct *work)
 	struct io_kiocb *req, *tmp;
 	struct io_tw_state ts = { .locked = true, };
 
+	percpu_ref_get(&ctx->refs);
 	mutex_lock(&ctx->uring_lock);
 	llist_for_each_entry_safe(req, tmp, node, io_task_work.node)
 		req->io_task_work.func(req, &ts);
@@ -278,6 +259,7 @@ static __cold void io_fallback_req_func(struct work_struct *work)
 		return;
 	io_submit_flush_completions(ctx);
 	mutex_unlock(&ctx->uring_lock);
+	percpu_ref_put(&ctx->refs);
 }
 
 static int io_alloc_hash_table(struct io_hash_table *table, unsigned bits)
@@ -325,6 +307,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	INIT_LIST_HEAD(&ctx->sqd_list);
 	INIT_LIST_HEAD(&ctx->cq_overflow_list);
 	INIT_LIST_HEAD(&ctx->io_buffers_cache);
+	INIT_HLIST_HEAD(&ctx->io_buf_list);
 	io_alloc_cache_init(&ctx->rsrc_node_cache, IO_NODE_ALLOC_CACHE_MAX,
 			    sizeof(struct io_rsrc_node));
 	io_alloc_cache_init(&ctx->apoll_cache, IO_ALLOC_CACHE_MAX,
@@ -551,14 +534,13 @@ static __cold void io_queue_deferred(struct io_ring_ctx *ctx)
 	}
 }
 
-
-static void io_eventfd_ops(struct rcu_head *rcu)
+void io_eventfd_ops(struct rcu_head *rcu)
 {
 	struct io_ev_fd *ev_fd = container_of(rcu, struct io_ev_fd, rcu);
 	int ops = atomic_xchg(&ev_fd->ops, 0);
 
 	if (ops & BIT(IO_EVENTFD_OP_SIGNAL_BIT))
-		eventfd_signal_mask(ev_fd->cq_ev_fd, 1, EPOLL_URING_WAKE);
+		eventfd_signal_mask(ev_fd->cq_ev_fd, EPOLL_URING_WAKE);
 
 	/* IO_EVENTFD_OP_FREE_BIT may not be set here depending on callback
 	 * ordering in a race but if references are 0 we know we have to free
@@ -594,7 +576,7 @@ static void io_eventfd_signal(struct io_ring_ctx *ctx)
 		goto out;
 
 	if (likely(eventfd_signal_allowed())) {
-		eventfd_signal_mask(ev_fd->cq_ev_fd, 1, EPOLL_URING_WAKE);
+		eventfd_signal_mask(ev_fd->cq_ev_fd, EPOLL_URING_WAKE);
 	} else {
 		atomic_inc(&ev_fd->refs);
 		if (!atomic_fetch_or(BIT(IO_EVENTFD_OP_SIGNAL_BIT), &ev_fd->ops))
@@ -1895,14 +1877,19 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
 			io_req_complete_defer(req);
 		else
 			io_req_complete_post(req, issue_flags);
-	} else if (ret != IOU_ISSUE_SKIP_COMPLETE)
-		return ret;
 
-	/* If the op doesn't have a file, we're not polling for it */
-	if ((req->ctx->flags & IORING_SETUP_IOPOLL) && def->iopoll_queue)
-		io_iopoll_req_issued(req, issue_flags);
+		return 0;
+	}
 
-	return 0;
+	if (ret == IOU_ISSUE_SKIP_COMPLETE) {
+		ret = 0;
+		io_arm_ltimeout(req);
+
+		/* If the op doesn't have a file, we're not polling for it */
+		if ((req->ctx->flags & IORING_SETUP_IOPOLL) && def->iopoll_queue)
+			io_iopoll_req_issued(req, issue_flags);
+	}
+	return ret;
 }
 
 int io_poll_issue(struct io_kiocb *req, struct io_tw_state *ts)
@@ -2073,9 +2060,7 @@ static inline void io_queue_sqe(struct io_kiocb *req)
 	 * We async punt it if the file wasn't marked NOWAIT, or if the file
 	 * doesn't support non-blocking read/write attempts
 	 */
-	if (likely(!ret))
-		io_arm_ltimeout(req);
-	else
+	if (unlikely(ret))
 		io_queue_async(req, ret);
 }
 
@@ -2630,8 +2615,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 		__set_current_state(TASK_RUNNING);
 		atomic_set(&ctx->cq_wait_nr, 0);
 
-		if (ret < 0)
-			break;
 		/*
 		 * Run task_work after scheduling and before io_should_wake().
 		 * If we got woken because of task_work being processed, run it
@@ -2641,6 +2624,18 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 		if (!llist_empty(&ctx->work_llist))
 			io_run_local_work(ctx);
 
+		/*
+		 * Non-local task_work will be run on exit to userspace, but
+		 * if we're using DEFER_TASKRUN, then we could have waited
+		 * with a timeout for a number of requests. If the timeout
+		 * hits, we could have some requests ready to process. Ensure
+		 * this break is _after_ we have run task_work, to avoid
+		 * deferring running potentially pending requests until the
+		 * next time we wait for events.
+		 */
+		if (ret < 0)
+			break;
+
 		check_cq = READ_ONCE(ctx->check_cq);
 		if (unlikely(check_cq)) {
 			/* let the caller flush overflows, retry */
@@ -2666,7 +2661,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 	return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0;
 }
 
-static void io_mem_free(void *ptr)
+void io_mem_free(void *ptr)
 {
 	if (!ptr)
 		return;
@@ -2697,6 +2692,7 @@ static void *__io_uaddr_map(struct page ***pages, unsigned short *npages,
 {
 	struct page **page_array;
 	unsigned int nr_pages;
+	void *page_addr;
 	int ret, i;
 
 	*npages = 0;
@@ -2718,27 +2714,29 @@ err:
 		io_pages_free(&page_array, ret > 0 ? ret : 0);
 		return ret < 0 ? ERR_PTR(ret) : ERR_PTR(-EFAULT);
 	}
-	/*
-	 * Should be a single page. If the ring is small enough that we can
-	 * use a normal page, that is fine. If we need multiple pages, then
-	 * userspace should use a huge page. That's the only way to guarantee
-	 * that we get contigious memory, outside of just being lucky or
-	 * (currently) having low memory fragmentation.
-	 */
-	if (page_array[0] != page_array[ret - 1])
-		goto err;
 
-	/*
-	 * Can't support mapping user allocated ring memory on 32-bit archs
-	 * where it could potentially reside in highmem. Just fail those with
-	 * -EINVAL, just like we did on kernels that didn't support this
-	 * feature.
-	 */
+	page_addr = page_address(page_array[0]);
 	for (i = 0; i < nr_pages; i++) {
-		if (PageHighMem(page_array[i])) {
-			ret = -EINVAL;
+		ret = -EINVAL;
+
+		/*
+		 * Can't support mapping user allocated ring memory on 32-bit
+		 * archs where it could potentially reside in highmem. Just
+		 * fail those with -EINVAL, just like we did on kernels that
+		 * didn't support this feature.
+		 */
+		if (PageHighMem(page_array[i]))
 			goto err;
-		}
+
+		/*
+		 * No support for discontig pages for now, should either be a
+		 * single normal page, or a huge page. Later on we can add
+		 * support for remapping discontig pages, for now we will
+		 * just fail them with EINVAL.
+		 */
+		if (page_address(page_array[i]) != page_addr)
+			goto err;
+		page_addr += PAGE_SIZE;
 	}
 
 	*pages = page_array;
@@ -2775,7 +2773,7 @@ static void io_rings_free(struct io_ring_ctx *ctx)
 	}
 }
 
-static void *io_mem_alloc(size_t size)
+void *io_mem_alloc(size_t size)
 {
 	gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP;
 	void *ret;
@@ -2825,61 +2823,6 @@ static unsigned long rings_size(struct io_ring_ctx *ctx, unsigned int sq_entries
 	return off;
 }
 
-static int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg,
-			       unsigned int eventfd_async)
-{
-	struct io_ev_fd *ev_fd;
-	__s32 __user *fds = arg;
-	int fd;
-
-	ev_fd = rcu_dereference_protected(ctx->io_ev_fd,
-					lockdep_is_held(&ctx->uring_lock));
-	if (ev_fd)
-		return -EBUSY;
-
-	if (copy_from_user(&fd, fds, sizeof(*fds)))
-		return -EFAULT;
-
-	ev_fd = kmalloc(sizeof(*ev_fd), GFP_KERNEL);
-	if (!ev_fd)
-		return -ENOMEM;
-
-	ev_fd->cq_ev_fd = eventfd_ctx_fdget(fd);
-	if (IS_ERR(ev_fd->cq_ev_fd)) {
-		int ret = PTR_ERR(ev_fd->cq_ev_fd);
-		kfree(ev_fd);
-		return ret;
-	}
-
-	spin_lock(&ctx->completion_lock);
-	ctx->evfd_last_cq_tail = ctx->cached_cq_tail;
-	spin_unlock(&ctx->completion_lock);
-
-	ev_fd->eventfd_async = eventfd_async;
-	ctx->has_evfd = true;
-	rcu_assign_pointer(ctx->io_ev_fd, ev_fd);
-	atomic_set(&ev_fd->refs, 1);
-	atomic_set(&ev_fd->ops, 0);
-	return 0;
-}
-
-static int io_eventfd_unregister(struct io_ring_ctx *ctx)
-{
-	struct io_ev_fd *ev_fd;
-
-	ev_fd = rcu_dereference_protected(ctx->io_ev_fd,
-					lockdep_is_held(&ctx->uring_lock));
-	if (ev_fd) {
-		ctx->has_evfd = false;
-		rcu_assign_pointer(ctx->io_ev_fd, NULL);
-		if (!atomic_fetch_or(BIT(IO_EVENTFD_OP_FREE_BIT), &ev_fd->ops))
-			call_rcu(&ev_fd->rcu, io_eventfd_ops);
-		return 0;
-	}
-
-	return -ENXIO;
-}
-
 static void io_req_caches_free(struct io_ring_ctx *ctx)
 {
 	struct io_kiocb *req;
@@ -2932,13 +2875,6 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
 		io_rsrc_node_destroy(ctx, ctx->rsrc_node);
 
 	WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list));
-
-#if defined(CONFIG_UNIX)
-	if (ctx->ring_sock) {
-		ctx->ring_sock->file = NULL; /* so that iput() is called */
-		sock_release(ctx->ring_sock);
-	}
-#endif
 	WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list));
 
 	io_alloc_cache_free(&ctx->rsrc_node_cache, io_rsrc_node_cache_free);
@@ -2947,6 +2883,7 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
 		ctx->mm_account = NULL;
 	}
 	io_rings_free(ctx);
+	io_kbuf_mmap_list_free(ctx);
 
 	percpu_ref_exit(&ctx->refs);
 	free_uid(ctx->user);
@@ -2977,7 +2914,7 @@ static __cold void io_activate_pollwq_cb(struct callback_head *cb)
 	percpu_ref_put(&ctx->refs);
 }
 
-static __cold void io_activate_pollwq(struct io_ring_ctx *ctx)
+__cold void io_activate_pollwq(struct io_ring_ctx *ctx)
 {
 	spin_lock(&ctx->completion_lock);
 	/* already activated or in progress */
@@ -3036,19 +2973,6 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait)
 	return mask;
 }
 
-static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id)
-{
-	const struct cred *creds;
-
-	creds = xa_erase(&ctx->personalities, id);
-	if (creds) {
-		put_cred(creds);
-		return 0;
-	}
-
-	return -EINVAL;
-}
-
 struct io_tctx_exit {
 	struct callback_head		task_work;
 	struct completion		completion;
@@ -3141,12 +3065,7 @@ static __cold void io_ring_exit_work(struct work_struct *work)
 	init_completion(&exit.completion);
 	init_task_work(&exit.task_work, io_tctx_exit_cb);
 	exit.ctx = ctx;
-	/*
-	 * Some may use context even when all refs and requests have been put,
-	 * and they are free to do so while still holding uring_lock or
-	 * completion_lock, see io_req_task_submit(). Apart from other work,
-	 * this lock/unlock section also waits them to finish.
-	 */
+
 	mutex_lock(&ctx->uring_lock);
 	while (!list_empty(&ctx->tctx_list)) {
 		WARN_ON_ONCE(time_after(jiffies, timeout));
@@ -3475,25 +3394,27 @@ static void *io_uring_validate_mmap_request(struct file *file,
 	struct page *page;
 	void *ptr;
 
-	/* Don't allow mmap if the ring was setup without it */
-	if (ctx->flags & IORING_SETUP_NO_MMAP)
-		return ERR_PTR(-EINVAL);
-
 	switch (offset & IORING_OFF_MMAP_MASK) {
 	case IORING_OFF_SQ_RING:
 	case IORING_OFF_CQ_RING:
+		/* Don't allow mmap if the ring was setup without it */
+		if (ctx->flags & IORING_SETUP_NO_MMAP)
+			return ERR_PTR(-EINVAL);
 		ptr = ctx->rings;
 		break;
 	case IORING_OFF_SQES:
+		/* Don't allow mmap if the ring was setup without it */
+		if (ctx->flags & IORING_SETUP_NO_MMAP)
+			return ERR_PTR(-EINVAL);
 		ptr = ctx->sq_sqes;
 		break;
 	case IORING_OFF_PBUF_RING: {
 		unsigned int bgid;
 
 		bgid = (offset & ~IORING_OFF_MMAP_MASK) >> IORING_OFF_PBUF_SHIFT;
-		mutex_lock(&ctx->uring_lock);
+		rcu_read_lock();
 		ptr = io_pbuf_get_address(ctx, bgid);
-		mutex_unlock(&ctx->uring_lock);
+		rcu_read_unlock();
 		if (!ptr)
 			return ERR_PTR(-EINVAL);
 		break;
@@ -3645,7 +3566,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 		size_t, argsz)
 {
 	struct io_ring_ctx *ctx;
-	struct fd f;
+	struct file *file;
 	long ret;
 
 	if (unlikely(flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP |
@@ -3663,20 +3584,19 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 		if (unlikely(!tctx || fd >= IO_RINGFD_REG_MAX))
 			return -EINVAL;
 		fd = array_index_nospec(fd, IO_RINGFD_REG_MAX);
-		f.file = tctx->registered_rings[fd];
-		f.flags = 0;
-		if (unlikely(!f.file))
+		file = tctx->registered_rings[fd];
+		if (unlikely(!file))
 			return -EBADF;
 	} else {
-		f = fdget(fd);
-		if (unlikely(!f.file))
+		file = fget(fd);
+		if (unlikely(!file))
 			return -EBADF;
 		ret = -EOPNOTSUPP;
-		if (unlikely(!io_is_uring_fops(f.file)))
+		if (unlikely(!io_is_uring_fops(file)))
 			goto out;
 	}
 
-	ctx = f.file->private_data;
+	ctx = file->private_data;
 	ret = -EBADFD;
 	if (unlikely(ctx->flags & IORING_SETUP_R_DISABLED))
 		goto out;
@@ -3770,7 +3690,8 @@ iopoll_locked:
 		}
 	}
 out:
-	fdput(f);
+	if (!(flags & IORING_ENTER_REGISTERED_RING))
+		fput(file);
 	return ret;
 }
 
@@ -3862,32 +3783,12 @@ static int io_uring_install_fd(struct file *file)
 /*
  * Allocate an anonymous fd, this is what constitutes the application
  * visible backing of an io_uring instance. The application mmaps this
- * fd to gain access to the SQ/CQ ring details. If UNIX sockets are enabled,
- * we have to tie this fd to a socket for file garbage collection purposes.
+ * fd to gain access to the SQ/CQ ring details.
  */
 static struct file *io_uring_get_file(struct io_ring_ctx *ctx)
 {
-	struct file *file;
-#if defined(CONFIG_UNIX)
-	int ret;
-
-	ret = sock_create_kern(&init_net, PF_UNIX, SOCK_RAW, IPPROTO_IP,
-				&ctx->ring_sock);
-	if (ret)
-		return ERR_PTR(ret);
-#endif
-
-	file = anon_inode_getfile_secure("[io_uring]", &io_uring_fops, ctx,
+	return anon_inode_getfile_secure("[io_uring]", &io_uring_fops, ctx,
 					 O_RDWR | O_CLOEXEC, NULL);
-#if defined(CONFIG_UNIX)
-	if (IS_ERR(file)) {
-		sock_release(ctx->ring_sock);
-		ctx->ring_sock = NULL;
-	} else {
-		ctx->ring_sock->file = file;
-	}
-#endif
-	return file;
 }
 
 static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
@@ -4154,506 +4055,6 @@ SYSCALL_DEFINE2(io_uring_setup, u32, entries,
 	return io_uring_setup(entries, params);
 }
 
-static __cold int io_probe(struct io_ring_ctx *ctx, void __user *arg,
-			   unsigned nr_args)
-{
-	struct io_uring_probe *p;
-	size_t size;
-	int i, ret;
-
-	size = struct_size(p, ops, nr_args);
-	if (size == SIZE_MAX)
-		return -EOVERFLOW;
-	p = kzalloc(size, GFP_KERNEL);
-	if (!p)
-		return -ENOMEM;
-
-	ret = -EFAULT;
-	if (copy_from_user(p, arg, size))
-		goto out;
-	ret = -EINVAL;
-	if (memchr_inv(p, 0, size))
-		goto out;
-
-	p->last_op = IORING_OP_LAST - 1;
-	if (nr_args > IORING_OP_LAST)
-		nr_args = IORING_OP_LAST;
-
-	for (i = 0; i < nr_args; i++) {
-		p->ops[i].op = i;
-		if (!io_issue_defs[i].not_supported)
-			p->ops[i].flags = IO_URING_OP_SUPPORTED;
-	}
-	p->ops_len = i;
-
-	ret = 0;
-	if (copy_to_user(arg, p, size))
-		ret = -EFAULT;
-out:
-	kfree(p);
-	return ret;
-}
-
-static int io_register_personality(struct io_ring_ctx *ctx)
-{
-	const struct cred *creds;
-	u32 id;
-	int ret;
-
-	creds = get_current_cred();
-
-	ret = xa_alloc_cyclic(&ctx->personalities, &id, (void *)creds,
-			XA_LIMIT(0, USHRT_MAX), &ctx->pers_next, GFP_KERNEL);
-	if (ret < 0) {
-		put_cred(creds);
-		return ret;
-	}
-	return id;
-}
-
-static __cold int io_register_restrictions(struct io_ring_ctx *ctx,
-					   void __user *arg, unsigned int nr_args)
-{
-	struct io_uring_restriction *res;
-	size_t size;
-	int i, ret;
-
-	/* Restrictions allowed only if rings started disabled */
-	if (!(ctx->flags & IORING_SETUP_R_DISABLED))
-		return -EBADFD;
-
-	/* We allow only a single restrictions registration */
-	if (ctx->restrictions.registered)
-		return -EBUSY;
-
-	if (!arg || nr_args > IORING_MAX_RESTRICTIONS)
-		return -EINVAL;
-
-	size = array_size(nr_args, sizeof(*res));
-	if (size == SIZE_MAX)
-		return -EOVERFLOW;
-
-	res = memdup_user(arg, size);
-	if (IS_ERR(res))
-		return PTR_ERR(res);
-
-	ret = 0;
-
-	for (i = 0; i < nr_args; i++) {
-		switch (res[i].opcode) {
-		case IORING_RESTRICTION_REGISTER_OP:
-			if (res[i].register_op >= IORING_REGISTER_LAST) {
-				ret = -EINVAL;
-				goto out;
-			}
-
-			__set_bit(res[i].register_op,
-				  ctx->restrictions.register_op);
-			break;
-		case IORING_RESTRICTION_SQE_OP:
-			if (res[i].sqe_op >= IORING_OP_LAST) {
-				ret = -EINVAL;
-				goto out;
-			}
-
-			__set_bit(res[i].sqe_op, ctx->restrictions.sqe_op);
-			break;
-		case IORING_RESTRICTION_SQE_FLAGS_ALLOWED:
-			ctx->restrictions.sqe_flags_allowed = res[i].sqe_flags;
-			break;
-		case IORING_RESTRICTION_SQE_FLAGS_REQUIRED:
-			ctx->restrictions.sqe_flags_required = res[i].sqe_flags;
-			break;
-		default:
-			ret = -EINVAL;
-			goto out;
-		}
-	}
-
-out:
-	/* Reset all restrictions if an error happened */
-	if (ret != 0)
-		memset(&ctx->restrictions, 0, sizeof(ctx->restrictions));
-	else
-		ctx->restrictions.registered = true;
-
-	kfree(res);
-	return ret;
-}
-
-static int io_register_enable_rings(struct io_ring_ctx *ctx)
-{
-	if (!(ctx->flags & IORING_SETUP_R_DISABLED))
-		return -EBADFD;
-
-	if (ctx->flags & IORING_SETUP_SINGLE_ISSUER && !ctx->submitter_task) {
-		WRITE_ONCE(ctx->submitter_task, get_task_struct(current));
-		/*
-		 * Lazy activation attempts would fail if it was polled before
-		 * submitter_task is set.
-		 */
-		if (wq_has_sleeper(&ctx->poll_wq))
-			io_activate_pollwq(ctx);
-	}
-
-	if (ctx->restrictions.registered)
-		ctx->restricted = 1;
-
-	ctx->flags &= ~IORING_SETUP_R_DISABLED;
-	if (ctx->sq_data && wq_has_sleeper(&ctx->sq_data->wait))
-		wake_up(&ctx->sq_data->wait);
-	return 0;
-}
-
-static __cold int __io_register_iowq_aff(struct io_ring_ctx *ctx,
-					 cpumask_var_t new_mask)
-{
-	int ret;
-
-	if (!(ctx->flags & IORING_SETUP_SQPOLL)) {
-		ret = io_wq_cpu_affinity(current->io_uring, new_mask);
-	} else {
-		mutex_unlock(&ctx->uring_lock);
-		ret = io_sqpoll_wq_cpu_affinity(ctx, new_mask);
-		mutex_lock(&ctx->uring_lock);
-	}
-
-	return ret;
-}
-
-static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx,
-				       void __user *arg, unsigned len)
-{
-	cpumask_var_t new_mask;
-	int ret;
-
-	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
-		return -ENOMEM;
-
-	cpumask_clear(new_mask);
-	if (len > cpumask_size())
-		len = cpumask_size();
-
-	if (in_compat_syscall()) {
-		ret = compat_get_bitmap(cpumask_bits(new_mask),
-					(const compat_ulong_t __user *)arg,
-					len * 8 /* CHAR_BIT */);
-	} else {
-		ret = copy_from_user(new_mask, arg, len);
-	}
-
-	if (ret) {
-		free_cpumask_var(new_mask);
-		return -EFAULT;
-	}
-
-	ret = __io_register_iowq_aff(ctx, new_mask);
-	free_cpumask_var(new_mask);
-	return ret;
-}
-
-static __cold int io_unregister_iowq_aff(struct io_ring_ctx *ctx)
-{
-	return __io_register_iowq_aff(ctx, NULL);
-}
-
-static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
-					       void __user *arg)
-	__must_hold(&ctx->uring_lock)
-{
-	struct io_tctx_node *node;
-	struct io_uring_task *tctx = NULL;
-	struct io_sq_data *sqd = NULL;
-	__u32 new_count[2];
-	int i, ret;
-
-	if (copy_from_user(new_count, arg, sizeof(new_count)))
-		return -EFAULT;
-	for (i = 0; i < ARRAY_SIZE(new_count); i++)
-		if (new_count[i] > INT_MAX)
-			return -EINVAL;
-
-	if (ctx->flags & IORING_SETUP_SQPOLL) {
-		sqd = ctx->sq_data;
-		if (sqd) {
-			/*
-			 * Observe the correct sqd->lock -> ctx->uring_lock
-			 * ordering. Fine to drop uring_lock here, we hold
-			 * a ref to the ctx.
-			 */
-			refcount_inc(&sqd->refs);
-			mutex_unlock(&ctx->uring_lock);
-			mutex_lock(&sqd->lock);
-			mutex_lock(&ctx->uring_lock);
-			if (sqd->thread)
-				tctx = sqd->thread->io_uring;
-		}
-	} else {
-		tctx = current->io_uring;
-	}
-
-	BUILD_BUG_ON(sizeof(new_count) != sizeof(ctx->iowq_limits));
-
-	for (i = 0; i < ARRAY_SIZE(new_count); i++)
-		if (new_count[i])
-			ctx->iowq_limits[i] = new_count[i];
-	ctx->iowq_limits_set = true;
-
-	if (tctx && tctx->io_wq) {
-		ret = io_wq_max_workers(tctx->io_wq, new_count);
-		if (ret)
-			goto err;
-	} else {
-		memset(new_count, 0, sizeof(new_count));
-	}
-
-	if (sqd) {
-		mutex_unlock(&sqd->lock);
-		io_put_sq_data(sqd);
-	}
-
-	if (copy_to_user(arg, new_count, sizeof(new_count)))
-		return -EFAULT;
-
-	/* that's it for SQPOLL, only the SQPOLL task creates requests */
-	if (sqd)
-		return 0;
-
-	/* now propagate the restriction to all registered users */
-	list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
-		struct io_uring_task *tctx = node->task->io_uring;
-
-		if (WARN_ON_ONCE(!tctx->io_wq))
-			continue;
-
-		for (i = 0; i < ARRAY_SIZE(new_count); i++)
-			new_count[i] = ctx->iowq_limits[i];
-		/* ignore errors, it always returns zero anyway */
-		(void)io_wq_max_workers(tctx->io_wq, new_count);
-	}
-	return 0;
-err:
-	if (sqd) {
-		mutex_unlock(&sqd->lock);
-		io_put_sq_data(sqd);
-	}
-	return ret;
-}
-
-static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
-			       void __user *arg, unsigned nr_args)
-	__releases(ctx->uring_lock)
-	__acquires(ctx->uring_lock)
-{
-	int ret;
-
-	/*
-	 * We don't quiesce the refs for register anymore and so it can't be
-	 * dying as we're holding a file ref here.
-	 */
-	if (WARN_ON_ONCE(percpu_ref_is_dying(&ctx->refs)))
-		return -ENXIO;
-
-	if (ctx->submitter_task && ctx->submitter_task != current)
-		return -EEXIST;
-
-	if (ctx->restricted) {
-		opcode = array_index_nospec(opcode, IORING_REGISTER_LAST);
-		if (!test_bit(opcode, ctx->restrictions.register_op))
-			return -EACCES;
-	}
-
-	switch (opcode) {
-	case IORING_REGISTER_BUFFERS:
-		ret = -EFAULT;
-		if (!arg)
-			break;
-		ret = io_sqe_buffers_register(ctx, arg, nr_args, NULL);
-		break;
-	case IORING_UNREGISTER_BUFFERS:
-		ret = -EINVAL;
-		if (arg || nr_args)
-			break;
-		ret = io_sqe_buffers_unregister(ctx);
-		break;
-	case IORING_REGISTER_FILES:
-		ret = -EFAULT;
-		if (!arg)
-			break;
-		ret = io_sqe_files_register(ctx, arg, nr_args, NULL);
-		break;
-	case IORING_UNREGISTER_FILES:
-		ret = -EINVAL;
-		if (arg || nr_args)
-			break;
-		ret = io_sqe_files_unregister(ctx);
-		break;
-	case IORING_REGISTER_FILES_UPDATE:
-		ret = io_register_files_update(ctx, arg, nr_args);
-		break;
-	case IORING_REGISTER_EVENTFD:
-		ret = -EINVAL;
-		if (nr_args != 1)
-			break;
-		ret = io_eventfd_register(ctx, arg, 0);
-		break;
-	case IORING_REGISTER_EVENTFD_ASYNC:
-		ret = -EINVAL;
-		if (nr_args != 1)
-			break;
-		ret = io_eventfd_register(ctx, arg, 1);
-		break;
-	case IORING_UNREGISTER_EVENTFD:
-		ret = -EINVAL;
-		if (arg || nr_args)
-			break;
-		ret = io_eventfd_unregister(ctx);
-		break;
-	case IORING_REGISTER_PROBE:
-		ret = -EINVAL;
-		if (!arg || nr_args > 256)
-			break;
-		ret = io_probe(ctx, arg, nr_args);
-		break;
-	case IORING_REGISTER_PERSONALITY:
-		ret = -EINVAL;
-		if (arg || nr_args)
-			break;
-		ret = io_register_personality(ctx);
-		break;
-	case IORING_UNREGISTER_PERSONALITY:
-		ret = -EINVAL;
-		if (arg)
-			break;
-		ret = io_unregister_personality(ctx, nr_args);
-		break;
-	case IORING_REGISTER_ENABLE_RINGS:
-		ret = -EINVAL;
-		if (arg || nr_args)
-			break;
-		ret = io_register_enable_rings(ctx);
-		break;
-	case IORING_REGISTER_RESTRICTIONS:
-		ret = io_register_restrictions(ctx, arg, nr_args);
-		break;
-	case IORING_REGISTER_FILES2:
-		ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_FILE);
-		break;
-	case IORING_REGISTER_FILES_UPDATE2:
-		ret = io_register_rsrc_update(ctx, arg, nr_args,
-					      IORING_RSRC_FILE);
-		break;
-	case IORING_REGISTER_BUFFERS2:
-		ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_BUFFER);
-		break;
-	case IORING_REGISTER_BUFFERS_UPDATE:
-		ret = io_register_rsrc_update(ctx, arg, nr_args,
-					      IORING_RSRC_BUFFER);
-		break;
-	case IORING_REGISTER_IOWQ_AFF:
-		ret = -EINVAL;
-		if (!arg || !nr_args)
-			break;
-		ret = io_register_iowq_aff(ctx, arg, nr_args);
-		break;
-	case IORING_UNREGISTER_IOWQ_AFF:
-		ret = -EINVAL;
-		if (arg || nr_args)
-			break;
-		ret = io_unregister_iowq_aff(ctx);
-		break;
-	case IORING_REGISTER_IOWQ_MAX_WORKERS:
-		ret = -EINVAL;
-		if (!arg || nr_args != 2)
-			break;
-		ret = io_register_iowq_max_workers(ctx, arg);
-		break;
-	case IORING_REGISTER_RING_FDS:
-		ret = io_ringfd_register(ctx, arg, nr_args);
-		break;
-	case IORING_UNREGISTER_RING_FDS:
-		ret = io_ringfd_unregister(ctx, arg, nr_args);
-		break;
-	case IORING_REGISTER_PBUF_RING:
-		ret = -EINVAL;
-		if (!arg || nr_args != 1)
-			break;
-		ret = io_register_pbuf_ring(ctx, arg);
-		break;
-	case IORING_UNREGISTER_PBUF_RING:
-		ret = -EINVAL;
-		if (!arg || nr_args != 1)
-			break;
-		ret = io_unregister_pbuf_ring(ctx, arg);
-		break;
-	case IORING_REGISTER_SYNC_CANCEL:
-		ret = -EINVAL;
-		if (!arg || nr_args != 1)
-			break;
-		ret = io_sync_cancel(ctx, arg);
-		break;
-	case IORING_REGISTER_FILE_ALLOC_RANGE:
-		ret = -EINVAL;
-		if (!arg || nr_args)
-			break;
-		ret = io_register_file_alloc_range(ctx, arg);
-		break;
-	default:
-		ret = -EINVAL;
-		break;
-	}
-
-	return ret;
-}
-
-SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode,
-		void __user *, arg, unsigned int, nr_args)
-{
-	struct io_ring_ctx *ctx;
-	long ret = -EBADF;
-	struct fd f;
-	bool use_registered_ring;
-
-	use_registered_ring = !!(opcode & IORING_REGISTER_USE_REGISTERED_RING);
-	opcode &= ~IORING_REGISTER_USE_REGISTERED_RING;
-
-	if (opcode >= IORING_REGISTER_LAST)
-		return -EINVAL;
-
-	if (use_registered_ring) {
-		/*
-		 * Ring fd has been registered via IORING_REGISTER_RING_FDS, we
-		 * need only dereference our task private array to find it.
-		 */
-		struct io_uring_task *tctx = current->io_uring;
-
-		if (unlikely(!tctx || fd >= IO_RINGFD_REG_MAX))
-			return -EINVAL;
-		fd = array_index_nospec(fd, IO_RINGFD_REG_MAX);
-		f.file = tctx->registered_rings[fd];
-		f.flags = 0;
-		if (unlikely(!f.file))
-			return -EBADF;
-	} else {
-		f = fdget(fd);
-		if (unlikely(!f.file))
-			return -EBADF;
-		ret = -EOPNOTSUPP;
-		if (!io_is_uring_fops(f.file))
-			goto out_fput;
-	}
-
-	ctx = f.file->private_data;
-
-	mutex_lock(&ctx->uring_lock);
-	ret = __io_uring_register(ctx, opcode, arg, nr_args);
-	mutex_unlock(&ctx->uring_lock);
-	trace_io_uring_register(ctx, opcode, ctx->nr_user_files, ctx->nr_user_bufs, ret);
-out_fput:
-	fdput(f);
-	return ret;
-}
-
 static int __init io_uring_init(void)
 {
 #define __BUILD_BUG_VERIFY_OFFSET_SIZE(stype, eoffset, esize, ename) do { \
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index dc6d779b452b..04e33f25919c 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -15,16 +15,6 @@
 #include <trace/events/io_uring.h>
 #endif
 
-enum {
-	/*
-	 * A hint to not wake right away but delay until there are enough of
-	 * tw's queued to match the number of CQEs the task is waiting for.
-	 *
-	 * Must not be used wirh requests generating more than one CQE.
-	 * It's also ignored unless IORING_SETUP_DEFER_TASKRUN is set.
-	 */
-	IOU_F_TWQ_LAZY_WAKE			= 1,
-};
 
 enum {
 	IOU_OK			= 0,
@@ -54,7 +44,6 @@ struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
 			       unsigned issue_flags);
 
 void __io_req_task_work_add(struct io_kiocb *req, unsigned flags);
-bool io_is_uring_fops(struct file *file);
 bool io_alloc_async_data(struct io_kiocb *req);
 void io_req_task_queue(struct io_kiocb *req);
 void io_queue_iowq(struct io_kiocb *req, struct io_tw_state *ts_dont_use);
@@ -86,6 +75,17 @@ bool __io_alloc_req_refill(struct io_ring_ctx *ctx);
 bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
 			bool cancel_all);
 
+void *io_mem_alloc(size_t size);
+void io_mem_free(void *ptr);
+
+enum {
+	IO_EVENTFD_OP_SIGNAL_BIT,
+	IO_EVENTFD_OP_FREE_BIT,
+};
+
+void io_eventfd_ops(struct rcu_head *rcu);
+void io_activate_pollwq(struct io_ring_ctx *ctx);
+
 #if defined(CONFIG_PROVE_LOCKING)
 static inline void io_lockdep_assert_cq_locked(struct io_ring_ctx *ctx)
 {
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index a1e4239c7d75..18df5a9d2f5e 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -33,19 +33,42 @@ struct io_provide_buf {
 	__u16				bid;
 };
 
+struct io_buf_free {
+	struct hlist_node		list;
+	void				*mem;
+	size_t				size;
+	int				inuse;
+};
+
+static struct io_buffer_list *__io_buffer_get_list(struct io_ring_ctx *ctx,
+						   struct io_buffer_list *bl,
+						   unsigned int bgid)
+{
+	if (bl && bgid < BGID_ARRAY)
+		return &bl[bgid];
+
+	return xa_load(&ctx->io_bl_xa, bgid);
+}
+
 static inline struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx,
 							unsigned int bgid)
 {
-	if (ctx->io_bl && bgid < BGID_ARRAY)
-		return &ctx->io_bl[bgid];
+	lockdep_assert_held(&ctx->uring_lock);
 
-	return xa_load(&ctx->io_bl_xa, bgid);
+	return __io_buffer_get_list(ctx, ctx->io_bl, bgid);
 }
 
 static int io_buffer_add_list(struct io_ring_ctx *ctx,
 			      struct io_buffer_list *bl, unsigned int bgid)
 {
+	/*
+	 * Store buffer group ID and finally mark the list as visible.
+	 * The normal lookup doesn't care about the visibility as we're
+	 * always under the ->uring_lock, but the RCU lookup from mmap does.
+	 */
 	bl->bgid = bgid;
+	smp_store_release(&bl->is_ready, 1);
+
 	if (bgid < BGID_ARRAY)
 		return 0;
 
@@ -196,21 +219,40 @@ void __user *io_buffer_select(struct io_kiocb *req, size_t *len,
 
 static __cold int io_init_bl_list(struct io_ring_ctx *ctx)
 {
+	struct io_buffer_list *bl;
 	int i;
 
-	ctx->io_bl = kcalloc(BGID_ARRAY, sizeof(struct io_buffer_list),
-				GFP_KERNEL);
-	if (!ctx->io_bl)
+	bl = kcalloc(BGID_ARRAY, sizeof(struct io_buffer_list), GFP_KERNEL);
+	if (!bl)
 		return -ENOMEM;
 
 	for (i = 0; i < BGID_ARRAY; i++) {
-		INIT_LIST_HEAD(&ctx->io_bl[i].buf_list);
-		ctx->io_bl[i].bgid = i;
+		INIT_LIST_HEAD(&bl[i].buf_list);
+		bl[i].bgid = i;
 	}
 
+	smp_store_release(&ctx->io_bl, bl);
 	return 0;
 }
 
+/*
+ * Mark the given mapped range as free for reuse
+ */
+static void io_kbuf_mark_free(struct io_ring_ctx *ctx, struct io_buffer_list *bl)
+{
+	struct io_buf_free *ibf;
+
+	hlist_for_each_entry(ibf, &ctx->io_buf_list, list) {
+		if (bl->buf_ring == ibf->mem) {
+			ibf->inuse = 0;
+			return;
+		}
+	}
+
+	/* can't happen... */
+	WARN_ON_ONCE(1);
+}
+
 static int __io_remove_buffers(struct io_ring_ctx *ctx,
 			       struct io_buffer_list *bl, unsigned nbufs)
 {
@@ -223,7 +265,11 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx,
 	if (bl->is_mapped) {
 		i = bl->buf_ring->tail - bl->head;
 		if (bl->is_mmap) {
-			folio_put(virt_to_folio(bl->buf_ring));
+			/*
+			 * io_kbuf_list_free() will free the page(s) at
+			 * ->release() time.
+			 */
+			io_kbuf_mark_free(ctx, bl);
 			bl->buf_ring = NULL;
 			bl->is_mmap = 0;
 		} else if (bl->buf_nr_pages) {
@@ -274,9 +320,17 @@ void io_destroy_buffers(struct io_ring_ctx *ctx)
 	xa_for_each(&ctx->io_bl_xa, index, bl) {
 		xa_erase(&ctx->io_bl_xa, bl->bgid);
 		__io_remove_buffers(ctx, bl, -1U);
-		kfree(bl);
+		kfree_rcu(bl, rcu);
 	}
 
+	/*
+	 * Move deferred locked entries to cache before pruning
+	 */
+	spin_lock(&ctx->completion_lock);
+	if (!list_empty(&ctx->io_buffers_comp))
+		list_splice_init(&ctx->io_buffers_comp, &ctx->io_buffers_cache);
+	spin_unlock(&ctx->completion_lock);
+
 	list_for_each_safe(item, tmp, &ctx->io_buffers_cache) {
 		buf = list_entry(item, struct io_buffer, list);
 		kmem_cache_free(io_buf_cachep, buf);
@@ -460,7 +514,16 @@ int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags)
 		INIT_LIST_HEAD(&bl->buf_list);
 		ret = io_buffer_add_list(ctx, bl, p->bgid);
 		if (ret) {
-			kfree(bl);
+			/*
+			 * Doesn't need rcu free as it was never visible, but
+			 * let's keep it consistent throughout. Also can't
+			 * be a lower indexed array group, as adding one
+			 * where lookup failed cannot happen.
+			 */
+			if (p->bgid >= BGID_ARRAY)
+				kfree_rcu(bl, rcu);
+			else
+				WARN_ON_ONCE(1);
 			goto err;
 		}
 	}
@@ -531,19 +594,63 @@ error_unpin:
 	return -EINVAL;
 }
 
-static int io_alloc_pbuf_ring(struct io_uring_buf_reg *reg,
+/*
+ * See if we have a suitable region that we can reuse, rather than allocate
+ * both a new io_buf_free and mem region again. We leave it on the list as
+ * even a reused entry will need freeing at ring release.
+ */
+static struct io_buf_free *io_lookup_buf_free_entry(struct io_ring_ctx *ctx,
+						    size_t ring_size)
+{
+	struct io_buf_free *ibf, *best = NULL;
+	size_t best_dist;
+
+	hlist_for_each_entry(ibf, &ctx->io_buf_list, list) {
+		size_t dist;
+
+		if (ibf->inuse || ibf->size < ring_size)
+			continue;
+		dist = ibf->size - ring_size;
+		if (!best || dist < best_dist) {
+			best = ibf;
+			if (!dist)
+				break;
+			best_dist = dist;
+		}
+	}
+
+	return best;
+}
+
+static int io_alloc_pbuf_ring(struct io_ring_ctx *ctx,
+			      struct io_uring_buf_reg *reg,
 			      struct io_buffer_list *bl)
 {
-	gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP;
+	struct io_buf_free *ibf;
 	size_t ring_size;
 	void *ptr;
 
 	ring_size = reg->ring_entries * sizeof(struct io_uring_buf_ring);
-	ptr = (void *) __get_free_pages(gfp, get_order(ring_size));
-	if (!ptr)
-		return -ENOMEM;
 
-	bl->buf_ring = ptr;
+	/* Reuse existing entry, if we can */
+	ibf = io_lookup_buf_free_entry(ctx, ring_size);
+	if (!ibf) {
+		ptr = io_mem_alloc(ring_size);
+		if (IS_ERR(ptr))
+			return PTR_ERR(ptr);
+
+		/* Allocate and store deferred free entry */
+		ibf = kmalloc(sizeof(*ibf), GFP_KERNEL_ACCOUNT);
+		if (!ibf) {
+			io_mem_free(ptr);
+			return -ENOMEM;
+		}
+		ibf->mem = ptr;
+		ibf->size = ring_size;
+		hlist_add_head(&ibf->list, &ctx->io_buf_list);
+	}
+	ibf->inuse = 1;
+	bl->buf_ring = ibf->mem;
 	bl->is_mapped = 1;
 	bl->is_mmap = 1;
 	return 0;
@@ -555,6 +662,8 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
 	struct io_buffer_list *bl, *free_bl = NULL;
 	int ret;
 
+	lockdep_assert_held(&ctx->uring_lock);
+
 	if (copy_from_user(&reg, arg, sizeof(reg)))
 		return -EFAULT;
 
@@ -599,7 +708,7 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
 	if (!(reg.flags & IOU_PBUF_RING_MMAP))
 		ret = io_pin_pbuf_ring(&reg, bl);
 	else
-		ret = io_alloc_pbuf_ring(&reg, bl);
+		ret = io_alloc_pbuf_ring(ctx, &reg, bl);
 
 	if (!ret) {
 		bl->nr_entries = reg.ring_entries;
@@ -609,7 +718,7 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
 		return 0;
 	}
 
-	kfree(free_bl);
+	kfree_rcu(free_bl, rcu);
 	return ret;
 }
 
@@ -618,6 +727,8 @@ int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
 	struct io_uring_buf_reg reg;
 	struct io_buffer_list *bl;
 
+	lockdep_assert_held(&ctx->uring_lock);
+
 	if (copy_from_user(&reg, arg, sizeof(reg)))
 		return -EFAULT;
 	if (reg.resv[0] || reg.resv[1] || reg.resv[2])
@@ -634,18 +745,68 @@ int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
 	__io_remove_buffers(ctx, bl, -1U);
 	if (bl->bgid >= BGID_ARRAY) {
 		xa_erase(&ctx->io_bl_xa, bl->bgid);
-		kfree(bl);
+		kfree_rcu(bl, rcu);
 	}
 	return 0;
 }
 
+int io_register_pbuf_status(struct io_ring_ctx *ctx, void __user *arg)
+{
+	struct io_uring_buf_status buf_status;
+	struct io_buffer_list *bl;
+	int i;
+
+	if (copy_from_user(&buf_status, arg, sizeof(buf_status)))
+		return -EFAULT;
+
+	for (i = 0; i < ARRAY_SIZE(buf_status.resv); i++)
+		if (buf_status.resv[i])
+			return -EINVAL;
+
+	bl = io_buffer_get_list(ctx, buf_status.buf_group);
+	if (!bl)
+		return -ENOENT;
+	if (!bl->is_mapped)
+		return -EINVAL;
+
+	buf_status.head = bl->head;
+	if (copy_to_user(arg, &buf_status, sizeof(buf_status)))
+		return -EFAULT;
+
+	return 0;
+}
+
 void *io_pbuf_get_address(struct io_ring_ctx *ctx, unsigned long bgid)
 {
 	struct io_buffer_list *bl;
 
-	bl = io_buffer_get_list(ctx, bgid);
+	bl = __io_buffer_get_list(ctx, smp_load_acquire(&ctx->io_bl), bgid);
+
 	if (!bl || !bl->is_mmap)
 		return NULL;
+	/*
+	 * Ensure the list is fully setup. Only strictly needed for RCU lookup
+	 * via mmap, and in that case only for the array indexed groups. For
+	 * the xarray lookups, it's either visible and ready, or not at all.
+	 */
+	if (!smp_load_acquire(&bl->is_ready))
+		return NULL;
 
 	return bl->buf_ring;
 }
+
+/*
+ * Called at or after ->release(), free the mmap'ed buffers that we used
+ * for memory mapped provided buffer rings.
+ */
+void io_kbuf_mmap_list_free(struct io_ring_ctx *ctx)
+{
+	struct io_buf_free *ibf;
+	struct hlist_node *tmp;
+
+	hlist_for_each_entry_safe(ibf, tmp, &ctx->io_buf_list, list) {
+		hlist_del(&ibf->list);
+		io_mem_free(ibf->mem);
+		kfree(ibf);
+	}
+}
diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h
index f2d615236b2c..53dfaa71a397 100644
--- a/io_uring/kbuf.h
+++ b/io_uring/kbuf.h
@@ -15,6 +15,7 @@ struct io_buffer_list {
 			struct page **buf_pages;
 			struct io_uring_buf_ring *buf_ring;
 		};
+		struct rcu_head rcu;
 	};
 	__u16 bgid;
 
@@ -28,6 +29,8 @@ struct io_buffer_list {
 	__u8 is_mapped;
 	/* ring mapped provided buffers, but mmap'ed by application */
 	__u8 is_mmap;
+	/* bl is visible from an RCU point of view for lookup */
+	__u8 is_ready;
 };
 
 struct io_buffer {
@@ -50,6 +53,9 @@ int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags);
 
 int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg);
 int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg);
+int io_register_pbuf_status(struct io_ring_ctx *ctx, void __user *arg);
+
+void io_kbuf_mmap_list_free(struct io_ring_ctx *ctx);
 
 unsigned int __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags);
 
diff --git a/io_uring/opdef.c b/io_uring/opdef.c
index 799db44283c7..6705634e5f52 100644
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -469,6 +469,12 @@ const struct io_issue_def io_issue_defs[] = {
 		.prep			= io_eopnotsupp_prep,
 #endif
 	},
+	[IORING_OP_FIXED_FD_INSTALL] = {
+		.needs_file		= 1,
+		.audit_skip		= 1,
+		.prep			= io_install_fixed_fd_prep,
+		.issue			= io_install_fixed_fd,
+	},
 };
 
 const struct io_cold_def io_cold_defs[] = {
@@ -704,6 +710,9 @@ const struct io_cold_def io_cold_defs[] = {
 	[IORING_OP_FUTEX_WAITV] = {
 		.name			= "FUTEX_WAITV",
 	},
+	[IORING_OP_FIXED_FD_INSTALL] = {
+		.name			= "FIXED_FD_INSTALL",
+	},
 };
 
 const char *io_uring_get_opcode(u8 opcode)
diff --git a/io_uring/openclose.c b/io_uring/openclose.c
index fb73adb89067..0fe0dd305546 100644
--- a/io_uring/openclose.c
+++ b/io_uring/openclose.c
@@ -31,6 +31,11 @@ struct io_close {
 	u32				file_slot;
 };
 
+struct io_fixed_install {
+	struct file			*file;
+	unsigned int			o_flags;
+};
+
 static bool io_openat_force_async(struct io_open *open)
 {
 	/*
@@ -241,7 +246,7 @@ int io_close(struct io_kiocb *req, unsigned int issue_flags)
 		return -EAGAIN;
 	}
 
-	file = __close_fd_get_file(close->fd);
+	file = file_close_fd_locked(files, close->fd);
 	spin_unlock(&files->file_lock);
 	if (!file)
 		goto err;
@@ -254,3 +259,42 @@ err:
 	io_req_set_res(req, ret, 0);
 	return IOU_OK;
 }
+
+int io_install_fixed_fd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_fixed_install *ifi;
+	unsigned int flags;
+
+	if (sqe->off || sqe->addr || sqe->len || sqe->buf_index ||
+	    sqe->splice_fd_in || sqe->addr3)
+		return -EINVAL;
+
+	/* must be a fixed file */
+	if (!(req->flags & REQ_F_FIXED_FILE))
+		return -EBADF;
+
+	flags = READ_ONCE(sqe->install_fd_flags);
+	if (flags & ~IORING_FIXED_FD_NO_CLOEXEC)
+		return -EINVAL;
+
+	/* default to O_CLOEXEC, disable if IORING_FIXED_FD_NO_CLOEXEC is set */
+	ifi = io_kiocb_to_cmd(req, struct io_fixed_install);
+	ifi->o_flags = O_CLOEXEC;
+	if (flags & IORING_FIXED_FD_NO_CLOEXEC)
+		ifi->o_flags = 0;
+
+	return 0;
+}
+
+int io_install_fixed_fd(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_fixed_install *ifi;
+	int ret;
+
+	ifi = io_kiocb_to_cmd(req, struct io_fixed_install);
+	ret = receive_fd(req->file, NULL, ifi->o_flags);
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_set_res(req, ret, 0);
+	return IOU_OK;
+}
diff --git a/io_uring/openclose.h b/io_uring/openclose.h
index 4b1c28d3a66c..8a93c98ad0ad 100644
--- a/io_uring/openclose.h
+++ b/io_uring/openclose.h
@@ -12,3 +12,6 @@ int io_openat2(struct io_kiocb *req, unsigned int issue_flags);
 
 int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
 int io_close(struct io_kiocb *req, unsigned int issue_flags);
+
+int io_install_fixed_fd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_install_fixed_fd(struct io_kiocb *req, unsigned int issue_flags);
diff --git a/io_uring/poll.c b/io_uring/poll.c
index d38d05edb4fa..d59b74a99d4e 100644
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -366,11 +366,16 @@ void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts)
 
 static void __io_poll_execute(struct io_kiocb *req, int mask)
 {
+	unsigned flags = 0;
+
 	io_req_set_res(req, mask, 0);
 	req->io_task_work.func = io_poll_task_func;
 
 	trace_io_uring_task_add(req, mask);
-	__io_req_task_work_add(req, IOU_F_TWQ_LAZY_WAKE);
+
+	if (!(req->flags & REQ_F_POLL_NO_LAZY))
+		flags = IOU_F_TWQ_LAZY_WAKE;
+	__io_req_task_work_add(req, flags);
 }
 
 static inline void io_poll_execute(struct io_kiocb *req, int res)
@@ -526,10 +531,19 @@ static void __io_queue_proc(struct io_poll *poll, struct io_poll_table *pt,
 	poll->head = head;
 	poll->wait.private = (void *) wqe_private;
 
-	if (poll->events & EPOLLEXCLUSIVE)
+	if (poll->events & EPOLLEXCLUSIVE) {
+		/*
+		 * Exclusive waits may only wake a limited amount of entries
+		 * rather than all of them, this may interfere with lazy
+		 * wake if someone does wait(events > 1). Ensure we don't do
+		 * lazy wake for those, as we need to process each one as they
+		 * come in.
+		 */
+		req->flags |= REQ_F_POLL_NO_LAZY;
 		add_wait_queue_exclusive(head, &poll->wait);
-	else
+	} else {
 		add_wait_queue(head, &poll->wait);
+	}
 }
 
 static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head,
diff --git a/io_uring/register.c b/io_uring/register.c
new file mode 100644
index 000000000000..708dd1d89add
--- /dev/null
+++ b/io_uring/register.c
@@ -0,0 +1,605 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Code related to the io_uring_register() syscall
+ *
+ * Copyright (C) 2023 Jens Axboe
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/syscalls.h>
+#include <linux/refcount.h>
+#include <linux/bits.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/nospec.h>
+#include <linux/io_uring.h>
+#include <linux/io_uring_types.h>
+
+#include "io_uring.h"
+#include "opdef.h"
+#include "tctx.h"
+#include "rsrc.h"
+#include "sqpoll.h"
+#include "register.h"
+#include "cancel.h"
+#include "kbuf.h"
+
+#define IORING_MAX_RESTRICTIONS	(IORING_RESTRICTION_LAST + \
+				 IORING_REGISTER_LAST + IORING_OP_LAST)
+
+static int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg,
+			       unsigned int eventfd_async)
+{
+	struct io_ev_fd *ev_fd;
+	__s32 __user *fds = arg;
+	int fd;
+
+	ev_fd = rcu_dereference_protected(ctx->io_ev_fd,
+					lockdep_is_held(&ctx->uring_lock));
+	if (ev_fd)
+		return -EBUSY;
+
+	if (copy_from_user(&fd, fds, sizeof(*fds)))
+		return -EFAULT;
+
+	ev_fd = kmalloc(sizeof(*ev_fd), GFP_KERNEL);
+	if (!ev_fd)
+		return -ENOMEM;
+
+	ev_fd->cq_ev_fd = eventfd_ctx_fdget(fd);
+	if (IS_ERR(ev_fd->cq_ev_fd)) {
+		int ret = PTR_ERR(ev_fd->cq_ev_fd);
+		kfree(ev_fd);
+		return ret;
+	}
+
+	spin_lock(&ctx->completion_lock);
+	ctx->evfd_last_cq_tail = ctx->cached_cq_tail;
+	spin_unlock(&ctx->completion_lock);
+
+	ev_fd->eventfd_async = eventfd_async;
+	ctx->has_evfd = true;
+	rcu_assign_pointer(ctx->io_ev_fd, ev_fd);
+	atomic_set(&ev_fd->refs, 1);
+	atomic_set(&ev_fd->ops, 0);
+	return 0;
+}
+
+int io_eventfd_unregister(struct io_ring_ctx *ctx)
+{
+	struct io_ev_fd *ev_fd;
+
+	ev_fd = rcu_dereference_protected(ctx->io_ev_fd,
+					lockdep_is_held(&ctx->uring_lock));
+	if (ev_fd) {
+		ctx->has_evfd = false;
+		rcu_assign_pointer(ctx->io_ev_fd, NULL);
+		if (!atomic_fetch_or(BIT(IO_EVENTFD_OP_FREE_BIT), &ev_fd->ops))
+			call_rcu(&ev_fd->rcu, io_eventfd_ops);
+		return 0;
+	}
+
+	return -ENXIO;
+}
+
+static __cold int io_probe(struct io_ring_ctx *ctx, void __user *arg,
+			   unsigned nr_args)
+{
+	struct io_uring_probe *p;
+	size_t size;
+	int i, ret;
+
+	size = struct_size(p, ops, nr_args);
+	if (size == SIZE_MAX)
+		return -EOVERFLOW;
+	p = kzalloc(size, GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	ret = -EFAULT;
+	if (copy_from_user(p, arg, size))
+		goto out;
+	ret = -EINVAL;
+	if (memchr_inv(p, 0, size))
+		goto out;
+
+	p->last_op = IORING_OP_LAST - 1;
+	if (nr_args > IORING_OP_LAST)
+		nr_args = IORING_OP_LAST;
+
+	for (i = 0; i < nr_args; i++) {
+		p->ops[i].op = i;
+		if (!io_issue_defs[i].not_supported)
+			p->ops[i].flags = IO_URING_OP_SUPPORTED;
+	}
+	p->ops_len = i;
+
+	ret = 0;
+	if (copy_to_user(arg, p, size))
+		ret = -EFAULT;
+out:
+	kfree(p);
+	return ret;
+}
+
+int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id)
+{
+	const struct cred *creds;
+
+	creds = xa_erase(&ctx->personalities, id);
+	if (creds) {
+		put_cred(creds);
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+
+static int io_register_personality(struct io_ring_ctx *ctx)
+{
+	const struct cred *creds;
+	u32 id;
+	int ret;
+
+	creds = get_current_cred();
+
+	ret = xa_alloc_cyclic(&ctx->personalities, &id, (void *)creds,
+			XA_LIMIT(0, USHRT_MAX), &ctx->pers_next, GFP_KERNEL);
+	if (ret < 0) {
+		put_cred(creds);
+		return ret;
+	}
+	return id;
+}
+
+static __cold int io_register_restrictions(struct io_ring_ctx *ctx,
+					   void __user *arg, unsigned int nr_args)
+{
+	struct io_uring_restriction *res;
+	size_t size;
+	int i, ret;
+
+	/* Restrictions allowed only if rings started disabled */
+	if (!(ctx->flags & IORING_SETUP_R_DISABLED))
+		return -EBADFD;
+
+	/* We allow only a single restrictions registration */
+	if (ctx->restrictions.registered)
+		return -EBUSY;
+
+	if (!arg || nr_args > IORING_MAX_RESTRICTIONS)
+		return -EINVAL;
+
+	size = array_size(nr_args, sizeof(*res));
+	if (size == SIZE_MAX)
+		return -EOVERFLOW;
+
+	res = memdup_user(arg, size);
+	if (IS_ERR(res))
+		return PTR_ERR(res);
+
+	ret = 0;
+
+	for (i = 0; i < nr_args; i++) {
+		switch (res[i].opcode) {
+		case IORING_RESTRICTION_REGISTER_OP:
+			if (res[i].register_op >= IORING_REGISTER_LAST) {
+				ret = -EINVAL;
+				goto out;
+			}
+
+			__set_bit(res[i].register_op,
+				  ctx->restrictions.register_op);
+			break;
+		case IORING_RESTRICTION_SQE_OP:
+			if (res[i].sqe_op >= IORING_OP_LAST) {
+				ret = -EINVAL;
+				goto out;
+			}
+
+			__set_bit(res[i].sqe_op, ctx->restrictions.sqe_op);
+			break;
+		case IORING_RESTRICTION_SQE_FLAGS_ALLOWED:
+			ctx->restrictions.sqe_flags_allowed = res[i].sqe_flags;
+			break;
+		case IORING_RESTRICTION_SQE_FLAGS_REQUIRED:
+			ctx->restrictions.sqe_flags_required = res[i].sqe_flags;
+			break;
+		default:
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+out:
+	/* Reset all restrictions if an error happened */
+	if (ret != 0)
+		memset(&ctx->restrictions, 0, sizeof(ctx->restrictions));
+	else
+		ctx->restrictions.registered = true;
+
+	kfree(res);
+	return ret;
+}
+
+static int io_register_enable_rings(struct io_ring_ctx *ctx)
+{
+	if (!(ctx->flags & IORING_SETUP_R_DISABLED))
+		return -EBADFD;
+
+	if (ctx->flags & IORING_SETUP_SINGLE_ISSUER && !ctx->submitter_task) {
+		WRITE_ONCE(ctx->submitter_task, get_task_struct(current));
+		/*
+		 * Lazy activation attempts would fail if it was polled before
+		 * submitter_task is set.
+		 */
+		if (wq_has_sleeper(&ctx->poll_wq))
+			io_activate_pollwq(ctx);
+	}
+
+	if (ctx->restrictions.registered)
+		ctx->restricted = 1;
+
+	ctx->flags &= ~IORING_SETUP_R_DISABLED;
+	if (ctx->sq_data && wq_has_sleeper(&ctx->sq_data->wait))
+		wake_up(&ctx->sq_data->wait);
+	return 0;
+}
+
+static __cold int __io_register_iowq_aff(struct io_ring_ctx *ctx,
+					 cpumask_var_t new_mask)
+{
+	int ret;
+
+	if (!(ctx->flags & IORING_SETUP_SQPOLL)) {
+		ret = io_wq_cpu_affinity(current->io_uring, new_mask);
+	} else {
+		mutex_unlock(&ctx->uring_lock);
+		ret = io_sqpoll_wq_cpu_affinity(ctx, new_mask);
+		mutex_lock(&ctx->uring_lock);
+	}
+
+	return ret;
+}
+
+static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx,
+				       void __user *arg, unsigned len)
+{
+	cpumask_var_t new_mask;
+	int ret;
+
+	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	cpumask_clear(new_mask);
+	if (len > cpumask_size())
+		len = cpumask_size();
+
+	if (in_compat_syscall()) {
+		ret = compat_get_bitmap(cpumask_bits(new_mask),
+					(const compat_ulong_t __user *)arg,
+					len * 8 /* CHAR_BIT */);
+	} else {
+		ret = copy_from_user(new_mask, arg, len);
+	}
+
+	if (ret) {
+		free_cpumask_var(new_mask);
+		return -EFAULT;
+	}
+
+	ret = __io_register_iowq_aff(ctx, new_mask);
+	free_cpumask_var(new_mask);
+	return ret;
+}
+
+static __cold int io_unregister_iowq_aff(struct io_ring_ctx *ctx)
+{
+	return __io_register_iowq_aff(ctx, NULL);
+}
+
+static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
+					       void __user *arg)
+	__must_hold(&ctx->uring_lock)
+{
+	struct io_tctx_node *node;
+	struct io_uring_task *tctx = NULL;
+	struct io_sq_data *sqd = NULL;
+	__u32 new_count[2];
+	int i, ret;
+
+	if (copy_from_user(new_count, arg, sizeof(new_count)))
+		return -EFAULT;
+	for (i = 0; i < ARRAY_SIZE(new_count); i++)
+		if (new_count[i] > INT_MAX)
+			return -EINVAL;
+
+	if (ctx->flags & IORING_SETUP_SQPOLL) {
+		sqd = ctx->sq_data;
+		if (sqd) {
+			/*
+			 * Observe the correct sqd->lock -> ctx->uring_lock
+			 * ordering. Fine to drop uring_lock here, we hold
+			 * a ref to the ctx.
+			 */
+			refcount_inc(&sqd->refs);
+			mutex_unlock(&ctx->uring_lock);
+			mutex_lock(&sqd->lock);
+			mutex_lock(&ctx->uring_lock);
+			if (sqd->thread)
+				tctx = sqd->thread->io_uring;
+		}
+	} else {
+		tctx = current->io_uring;
+	}
+
+	BUILD_BUG_ON(sizeof(new_count) != sizeof(ctx->iowq_limits));
+
+	for (i = 0; i < ARRAY_SIZE(new_count); i++)
+		if (new_count[i])
+			ctx->iowq_limits[i] = new_count[i];
+	ctx->iowq_limits_set = true;
+
+	if (tctx && tctx->io_wq) {
+		ret = io_wq_max_workers(tctx->io_wq, new_count);
+		if (ret)
+			goto err;
+	} else {
+		memset(new_count, 0, sizeof(new_count));
+	}
+
+	if (sqd) {
+		mutex_unlock(&sqd->lock);
+		io_put_sq_data(sqd);
+	}
+
+	if (copy_to_user(arg, new_count, sizeof(new_count)))
+		return -EFAULT;
+
+	/* that's it for SQPOLL, only the SQPOLL task creates requests */
+	if (sqd)
+		return 0;
+
+	/* now propagate the restriction to all registered users */
+	list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
+		struct io_uring_task *tctx = node->task->io_uring;
+
+		if (WARN_ON_ONCE(!tctx->io_wq))
+			continue;
+
+		for (i = 0; i < ARRAY_SIZE(new_count); i++)
+			new_count[i] = ctx->iowq_limits[i];
+		/* ignore errors, it always returns zero anyway */
+		(void)io_wq_max_workers(tctx->io_wq, new_count);
+	}
+	return 0;
+err:
+	if (sqd) {
+		mutex_unlock(&sqd->lock);
+		io_put_sq_data(sqd);
+	}
+	return ret;
+}
+
+static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
+			       void __user *arg, unsigned nr_args)
+	__releases(ctx->uring_lock)
+	__acquires(ctx->uring_lock)
+{
+	int ret;
+
+	/*
+	 * We don't quiesce the refs for register anymore and so it can't be
+	 * dying as we're holding a file ref here.
+	 */
+	if (WARN_ON_ONCE(percpu_ref_is_dying(&ctx->refs)))
+		return -ENXIO;
+
+	if (ctx->submitter_task && ctx->submitter_task != current)
+		return -EEXIST;
+
+	if (ctx->restricted) {
+		opcode = array_index_nospec(opcode, IORING_REGISTER_LAST);
+		if (!test_bit(opcode, ctx->restrictions.register_op))
+			return -EACCES;
+	}
+
+	switch (opcode) {
+	case IORING_REGISTER_BUFFERS:
+		ret = -EFAULT;
+		if (!arg)
+			break;
+		ret = io_sqe_buffers_register(ctx, arg, nr_args, NULL);
+		break;
+	case IORING_UNREGISTER_BUFFERS:
+		ret = -EINVAL;
+		if (arg || nr_args)
+			break;
+		ret = io_sqe_buffers_unregister(ctx);
+		break;
+	case IORING_REGISTER_FILES:
+		ret = -EFAULT;
+		if (!arg)
+			break;
+		ret = io_sqe_files_register(ctx, arg, nr_args, NULL);
+		break;
+	case IORING_UNREGISTER_FILES:
+		ret = -EINVAL;
+		if (arg || nr_args)
+			break;
+		ret = io_sqe_files_unregister(ctx);
+		break;
+	case IORING_REGISTER_FILES_UPDATE:
+		ret = io_register_files_update(ctx, arg, nr_args);
+		break;
+	case IORING_REGISTER_EVENTFD:
+		ret = -EINVAL;
+		if (nr_args != 1)
+			break;
+		ret = io_eventfd_register(ctx, arg, 0);
+		break;
+	case IORING_REGISTER_EVENTFD_ASYNC:
+		ret = -EINVAL;
+		if (nr_args != 1)
+			break;
+		ret = io_eventfd_register(ctx, arg, 1);
+		break;
+	case IORING_UNREGISTER_EVENTFD:
+		ret = -EINVAL;
+		if (arg || nr_args)
+			break;
+		ret = io_eventfd_unregister(ctx);
+		break;
+	case IORING_REGISTER_PROBE:
+		ret = -EINVAL;
+		if (!arg || nr_args > 256)
+			break;
+		ret = io_probe(ctx, arg, nr_args);
+		break;
+	case IORING_REGISTER_PERSONALITY:
+		ret = -EINVAL;
+		if (arg || nr_args)
+			break;
+		ret = io_register_personality(ctx);
+		break;
+	case IORING_UNREGISTER_PERSONALITY:
+		ret = -EINVAL;
+		if (arg)
+			break;
+		ret = io_unregister_personality(ctx, nr_args);
+		break;
+	case IORING_REGISTER_ENABLE_RINGS:
+		ret = -EINVAL;
+		if (arg || nr_args)
+			break;
+		ret = io_register_enable_rings(ctx);
+		break;
+	case IORING_REGISTER_RESTRICTIONS:
+		ret = io_register_restrictions(ctx, arg, nr_args);
+		break;
+	case IORING_REGISTER_FILES2:
+		ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_FILE);
+		break;
+	case IORING_REGISTER_FILES_UPDATE2:
+		ret = io_register_rsrc_update(ctx, arg, nr_args,
+					      IORING_RSRC_FILE);
+		break;
+	case IORING_REGISTER_BUFFERS2:
+		ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_BUFFER);
+		break;
+	case IORING_REGISTER_BUFFERS_UPDATE:
+		ret = io_register_rsrc_update(ctx, arg, nr_args,
+					      IORING_RSRC_BUFFER);
+		break;
+	case IORING_REGISTER_IOWQ_AFF:
+		ret = -EINVAL;
+		if (!arg || !nr_args)
+			break;
+		ret = io_register_iowq_aff(ctx, arg, nr_args);
+		break;
+	case IORING_UNREGISTER_IOWQ_AFF:
+		ret = -EINVAL;
+		if (arg || nr_args)
+			break;
+		ret = io_unregister_iowq_aff(ctx);
+		break;
+	case IORING_REGISTER_IOWQ_MAX_WORKERS:
+		ret = -EINVAL;
+		if (!arg || nr_args != 2)
+			break;
+		ret = io_register_iowq_max_workers(ctx, arg);
+		break;
+	case IORING_REGISTER_RING_FDS:
+		ret = io_ringfd_register(ctx, arg, nr_args);
+		break;
+	case IORING_UNREGISTER_RING_FDS:
+		ret = io_ringfd_unregister(ctx, arg, nr_args);
+		break;
+	case IORING_REGISTER_PBUF_RING:
+		ret = -EINVAL;
+		if (!arg || nr_args != 1)
+			break;
+		ret = io_register_pbuf_ring(ctx, arg);
+		break;
+	case IORING_UNREGISTER_PBUF_RING:
+		ret = -EINVAL;
+		if (!arg || nr_args != 1)
+			break;
+		ret = io_unregister_pbuf_ring(ctx, arg);
+		break;
+	case IORING_REGISTER_SYNC_CANCEL:
+		ret = -EINVAL;
+		if (!arg || nr_args != 1)
+			break;
+		ret = io_sync_cancel(ctx, arg);
+		break;
+	case IORING_REGISTER_FILE_ALLOC_RANGE:
+		ret = -EINVAL;
+		if (!arg || nr_args)
+			break;
+		ret = io_register_file_alloc_range(ctx, arg);
+		break;
+	case IORING_REGISTER_PBUF_STATUS:
+		ret = -EINVAL;
+		if (!arg || nr_args != 1)
+			break;
+		ret = io_register_pbuf_status(ctx, arg);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode,
+		void __user *, arg, unsigned int, nr_args)
+{
+	struct io_ring_ctx *ctx;
+	long ret = -EBADF;
+	struct file *file;
+	bool use_registered_ring;
+
+	use_registered_ring = !!(opcode & IORING_REGISTER_USE_REGISTERED_RING);
+	opcode &= ~IORING_REGISTER_USE_REGISTERED_RING;
+
+	if (opcode >= IORING_REGISTER_LAST)
+		return -EINVAL;
+
+	if (use_registered_ring) {
+		/*
+		 * Ring fd has been registered via IORING_REGISTER_RING_FDS, we
+		 * need only dereference our task private array to find it.
+		 */
+		struct io_uring_task *tctx = current->io_uring;
+
+		if (unlikely(!tctx || fd >= IO_RINGFD_REG_MAX))
+			return -EINVAL;
+		fd = array_index_nospec(fd, IO_RINGFD_REG_MAX);
+		file = tctx->registered_rings[fd];
+		if (unlikely(!file))
+			return -EBADF;
+	} else {
+		file = fget(fd);
+		if (unlikely(!file))
+			return -EBADF;
+		ret = -EOPNOTSUPP;
+		if (!io_is_uring_fops(file))
+			goto out_fput;
+	}
+
+	ctx = file->private_data;
+
+	mutex_lock(&ctx->uring_lock);
+	ret = __io_uring_register(ctx, opcode, arg, nr_args);
+	mutex_unlock(&ctx->uring_lock);
+	trace_io_uring_register(ctx, opcode, ctx->nr_user_files, ctx->nr_user_bufs, ret);
+out_fput:
+	if (!use_registered_ring)
+		fput(file);
+	return ret;
+}
diff --git a/io_uring/register.h b/io_uring/register.h
new file mode 100644
index 000000000000..c9da997d503c
--- /dev/null
+++ b/io_uring/register.h
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef IORING_REGISTER_H
+#define IORING_REGISTER_H
+
+int io_eventfd_unregister(struct io_ring_ctx *ctx);
+int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id);
+
+#endif
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index 7034be555334..4818b79231dd 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -24,7 +24,6 @@ struct io_rsrc_update {
 };
 
 static void io_rsrc_buf_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc);
-static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc);
 static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
 				  struct io_mapped_ubuf **pimu,
 				  struct page **last_hpage);
@@ -157,7 +156,7 @@ static void io_rsrc_put_work(struct io_rsrc_node *node)
 
 	switch (node->type) {
 	case IORING_RSRC_FILE:
-		io_rsrc_file_put(node->ctx, prsrc);
+		fput(prsrc->file);
 		break;
 	case IORING_RSRC_BUFFER:
 		io_rsrc_buf_put(node->ctx, prsrc);
@@ -402,23 +401,13 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 				break;
 			}
 			/*
-			 * Don't allow io_uring instances to be registered. If
-			 * UNIX isn't enabled, then this causes a reference
-			 * cycle and this instance can never get freed. If UNIX
-			 * is enabled we'll handle it just fine, but there's
-			 * still no point in allowing a ring fd as it doesn't
-			 * support regular read/write anyway.
+			 * Don't allow io_uring instances to be registered.
 			 */
 			if (io_is_uring_fops(file)) {
 				fput(file);
 				err = -EBADF;
 				break;
 			}
-			err = io_scm_file_account(ctx, file);
-			if (err) {
-				fput(file);
-				break;
-			}
 			*io_get_tag_slot(data, i) = tag;
 			io_fixed_file_set(file_slot, file);
 			io_file_bitmap_set(&ctx->file_table, i);
@@ -675,22 +664,12 @@ void __io_sqe_files_unregister(struct io_ring_ctx *ctx)
 	for (i = 0; i < ctx->nr_user_files; i++) {
 		struct file *file = io_file_from_index(&ctx->file_table, i);
 
-		/* skip scm accounted files, they'll be freed by ->ring_sock */
-		if (!file || io_file_need_scm(file))
+		if (!file)
 			continue;
 		io_file_bitmap_clear(&ctx->file_table, i);
 		fput(file);
 	}
 
-#if defined(CONFIG_UNIX)
-	if (ctx->ring_sock) {
-		struct sock *sock = ctx->ring_sock->sk;
-		struct sk_buff *skb;
-
-		while ((skb = skb_dequeue(&sock->sk_receive_queue)) != NULL)
-			kfree_skb(skb);
-	}
-#endif
 	io_free_file_tables(&ctx->file_table);
 	io_file_table_set_alloc_range(ctx, 0, 0);
 	io_rsrc_data_free(ctx->file_data);
@@ -718,137 +697,6 @@ int io_sqe_files_unregister(struct io_ring_ctx *ctx)
 	return ret;
 }
 
-/*
- * Ensure the UNIX gc is aware of our file set, so we are certain that
- * the io_uring can be safely unregistered on process exit, even if we have
- * loops in the file referencing. We account only files that can hold other
- * files because otherwise they can't form a loop and so are not interesting
- * for GC.
- */
-int __io_scm_file_account(struct io_ring_ctx *ctx, struct file *file)
-{
-#if defined(CONFIG_UNIX)
-	struct sock *sk = ctx->ring_sock->sk;
-	struct sk_buff_head *head = &sk->sk_receive_queue;
-	struct scm_fp_list *fpl;
-	struct sk_buff *skb;
-
-	if (likely(!io_file_need_scm(file)))
-		return 0;
-
-	/*
-	 * See if we can merge this file into an existing skb SCM_RIGHTS
-	 * file set. If there's no room, fall back to allocating a new skb
-	 * and filling it in.
-	 */
-	spin_lock_irq(&head->lock);
-	skb = skb_peek(head);
-	if (skb && UNIXCB(skb).fp->count < SCM_MAX_FD)
-		__skb_unlink(skb, head);
-	else
-		skb = NULL;
-	spin_unlock_irq(&head->lock);
-
-	if (!skb) {
-		fpl = kzalloc(sizeof(*fpl), GFP_KERNEL);
-		if (!fpl)
-			return -ENOMEM;
-
-		skb = alloc_skb(0, GFP_KERNEL);
-		if (!skb) {
-			kfree(fpl);
-			return -ENOMEM;
-		}
-
-		fpl->user = get_uid(current_user());
-		fpl->max = SCM_MAX_FD;
-		fpl->count = 0;
-
-		UNIXCB(skb).fp = fpl;
-		skb->sk = sk;
-		skb->destructor = io_uring_destruct_scm;
-		refcount_add(skb->truesize, &sk->sk_wmem_alloc);
-	}
-
-	fpl = UNIXCB(skb).fp;
-	fpl->fp[fpl->count++] = get_file(file);
-	unix_inflight(fpl->user, file);
-	skb_queue_head(head, skb);
-	fput(file);
-#endif
-	return 0;
-}
-
-static __cold void io_rsrc_file_scm_put(struct io_ring_ctx *ctx, struct file *file)
-{
-#if defined(CONFIG_UNIX)
-	struct sock *sock = ctx->ring_sock->sk;
-	struct sk_buff_head list, *head = &sock->sk_receive_queue;
-	struct sk_buff *skb;
-	int i;
-
-	__skb_queue_head_init(&list);
-
-	/*
-	 * Find the skb that holds this file in its SCM_RIGHTS. When found,
-	 * remove this entry and rearrange the file array.
-	 */
-	skb = skb_dequeue(head);
-	while (skb) {
-		struct scm_fp_list *fp;
-
-		fp = UNIXCB(skb).fp;
-		for (i = 0; i < fp->count; i++) {
-			int left;
-
-			if (fp->fp[i] != file)
-				continue;
-
-			unix_notinflight(fp->user, fp->fp[i]);
-			left = fp->count - 1 - i;
-			if (left) {
-				memmove(&fp->fp[i], &fp->fp[i + 1],
-						left * sizeof(struct file *));
-			}
-			fp->count--;
-			if (!fp->count) {
-				kfree_skb(skb);
-				skb = NULL;
-			} else {
-				__skb_queue_tail(&list, skb);
-			}
-			fput(file);
-			file = NULL;
-			break;
-		}
-
-		if (!file)
-			break;
-
-		__skb_queue_tail(&list, skb);
-
-		skb = skb_dequeue(head);
-	}
-
-	if (skb_peek(&list)) {
-		spin_lock_irq(&head->lock);
-		while ((skb = __skb_dequeue(&list)) != NULL)
-			__skb_queue_tail(head, skb);
-		spin_unlock_irq(&head->lock);
-	}
-#endif
-}
-
-static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc)
-{
-	struct file *file = prsrc->file;
-
-	if (likely(!io_file_need_scm(file)))
-		fput(file);
-	else
-		io_rsrc_file_scm_put(ctx, file);
-}
-
 int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 			  unsigned nr_args, u64 __user *tags)
 {
@@ -897,21 +745,12 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 			goto fail;
 
 		/*
-		 * Don't allow io_uring instances to be registered. If UNIX
-		 * isn't enabled, then this causes a reference cycle and this
-		 * instance can never get freed. If UNIX is enabled we'll
-		 * handle it just fine, but there's still no point in allowing
-		 * a ring fd as it doesn't support regular read/write anyway.
+		 * Don't allow io_uring instances to be registered.
 		 */
 		if (io_is_uring_fops(file)) {
 			fput(file);
 			goto fail;
 		}
-		ret = io_scm_file_account(ctx, file);
-		if (ret) {
-			fput(file);
-			goto fail;
-		}
 		file_slot = io_fixed_file_slot(&ctx->file_table, i);
 		io_fixed_file_set(file_slot, file);
 		io_file_bitmap_set(&ctx->file_table, i);
@@ -1258,7 +1097,7 @@ int io_import_fixed(int ddir, struct iov_iter *iter,
 		 */
 		const struct bio_vec *bvec = imu->bvec;
 
-		if (offset <= bvec->bv_len) {
+		if (offset < bvec->bv_len) {
 			/*
 			 * Note, huge pages buffers consists of one large
 			 * bvec entry and should always go this way. The other
diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index 8625181fb87a..7238b9cfe33b 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -75,28 +75,6 @@ int io_sqe_files_unregister(struct io_ring_ctx *ctx);
 int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 			  unsigned nr_args, u64 __user *tags);
 
-int __io_scm_file_account(struct io_ring_ctx *ctx, struct file *file);
-
-#if defined(CONFIG_UNIX)
-static inline bool io_file_need_scm(struct file *filp)
-{
-	return !!unix_get_socket(filp);
-}
-#else
-static inline bool io_file_need_scm(struct file *filp)
-{
-	return false;
-}
-#endif
-
-static inline int io_scm_file_account(struct io_ring_ctx *ctx,
-				      struct file *file)
-{
-	if (likely(!io_file_need_scm(file)))
-		return 0;
-	return __io_scm_file_account(ctx, file);
-}
-
 int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg,
 			     unsigned nr_args);
 int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg,
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 64390d4e20c1..0c856726b15d 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -10,7 +10,7 @@
 #include <linux/poll.h>
 #include <linux/nospec.h>
 #include <linux/compat.h>
-#include <linux/io_uring.h>
+#include <linux/io_uring/cmd.h>
 
 #include <uapi/linux/io_uring.h>
 
@@ -589,15 +589,19 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw)
 	struct iovec *iov;
 	int ret;
 
+	iorw->bytes_done = 0;
+	iorw->free_iovec = NULL;
+
 	/* submission path, ->uring_lock should already be taken */
 	ret = io_import_iovec(rw, req, &iov, &iorw->s, 0);
 	if (unlikely(ret < 0))
 		return ret;
 
-	iorw->bytes_done = 0;
-	iorw->free_iovec = iov;
-	if (iov)
+	if (iov) {
+		iorw->free_iovec = iov;
 		req->flags |= REQ_F_NEED_CLEANUP;
+	}
+
 	return 0;
 }
 
diff --git a/io_uring/splice.c b/io_uring/splice.c
index 7c4469e9540e..3b659cd23e9d 100644
--- a/io_uring/splice.c
+++ b/io_uring/splice.c
@@ -51,7 +51,7 @@ int io_tee(struct io_kiocb *req, unsigned int issue_flags)
 	struct file *out = sp->file_out;
 	unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
 	struct file *in;
-	long ret = 0;
+	ssize_t ret = 0;
 
 	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
 
@@ -92,7 +92,7 @@ int io_splice(struct io_kiocb *req, unsigned int issue_flags)
 	unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
 	loff_t *poff_in, *poff_out;
 	struct file *in;
-	long ret = 0;
+	ssize_t ret = 0;
 
 	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
 
diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index bd6c2c7959a5..65b5dbe3c850 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -214,6 +214,7 @@ static bool io_sqd_handle_event(struct io_sq_data *sqd)
 			did_sig = get_signal(&ksig);
 		cond_resched();
 		mutex_lock(&sqd->lock);
+		sqd->sq_cpu = raw_smp_processor_id();
 	}
 	return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
 }
@@ -229,10 +230,15 @@ static int io_sq_thread(void *data)
 	snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid);
 	set_task_comm(current, buf);
 
-	if (sqd->sq_cpu != -1)
+	/* reset to our pid after we've set task_comm, for fdinfo */
+	sqd->task_pid = current->pid;
+
+	if (sqd->sq_cpu != -1) {
 		set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu));
-	else
+	} else {
 		set_cpus_allowed_ptr(current, cpu_online_mask);
+		sqd->sq_cpu = raw_smp_processor_id();
+	}
 
 	mutex_lock(&sqd->lock);
 	while (1) {
@@ -261,6 +267,7 @@ static int io_sq_thread(void *data)
 				mutex_unlock(&sqd->lock);
 				cond_resched();
 				mutex_lock(&sqd->lock);
+				sqd->sq_cpu = raw_smp_processor_id();
 			}
 			continue;
 		}
@@ -294,6 +301,7 @@ static int io_sq_thread(void *data)
 				mutex_unlock(&sqd->lock);
 				schedule();
 				mutex_lock(&sqd->lock);
+				sqd->sq_cpu = raw_smp_processor_id();
 			}
 			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
 				atomic_andnot(IORING_SQ_NEED_WAKEUP,
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index acbc2924ecd2..c33fca585dde 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -2,12 +2,12 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/file.h>
-#include <linux/io_uring.h>
+#include <linux/io_uring/cmd.h>
 #include <linux/security.h>
 #include <linux/nospec.h>
 
 #include <uapi/linux/io_uring.h>
-#include <uapi/asm-generic/ioctls.h>
+#include <asm/ioctls.h>
 
 #include "io_uring.h"
 #include "rsrc.h"
@@ -52,12 +52,6 @@ void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
 }
 EXPORT_SYMBOL_GPL(io_uring_cmd_mark_cancelable);
 
-struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd)
-{
-	return cmd_to_io_kiocb(cmd)->task;
-}
-EXPORT_SYMBOL_GPL(io_uring_cmd_get_task);
-
 static void io_uring_cmd_work(struct io_kiocb *req, struct io_tw_state *ts)
 {
 	struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
@@ -78,13 +72,6 @@ void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
 }
 EXPORT_SYMBOL_GPL(__io_uring_cmd_do_in_task);
 
-void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd,
-			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
-{
-	__io_uring_cmd_do_in_task(ioucmd, task_work_cb, IOU_F_TWQ_LAZY_WAKE);
-}
-EXPORT_SYMBOL_GPL(io_uring_cmd_do_in_task_lazy);
-
 static inline void io_req_set_cqe32_extra(struct io_kiocb *req,
 					  u64 extra1, u64 extra2)
 {
@@ -182,7 +169,6 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
 			return -EOPNOTSUPP;
 		issue_flags |= IO_URING_F_IOPOLL;
 		req->iopoll_completed = 0;
-		WRITE_ONCE(ioucmd->cookie, NULL);
 	}
 
 	ret = file->f_op->uring_cmd(ioucmd, issue_flags);
diff --git a/ipc/shm.c b/ipc/shm.c
index 222aaf035afb..a89f001a8bf0 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -29,6 +29,7 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/shm.h>
+#include <uapi/linux/shm.h>
 #include <linux/init.h>
 #include <linux/file.h>
 #include <linux/mman.h>
diff --git a/ipc/util.h b/ipc/util.h
index 67bdd2aa2c28..a55d6cebe6d3 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -14,6 +14,7 @@
 #include <linux/unistd.h>
 #include <linux/err.h>
 #include <linux/ipc_namespace.h>
+#include <linux/pid.h>
 
 /*
  * The IPC ID contains 2 separate numbers - index and sequence number.
diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec
index 7aff28ded2f4..946dffa048b7 100644
--- a/kernel/Kconfig.kexec
+++ b/kernel/Kconfig.kexec
@@ -36,6 +36,8 @@ config KEXEC
 config KEXEC_FILE
 	bool "Enable kexec file based system call"
 	depends on ARCH_SUPPORTS_KEXEC_FILE
+	select CRYPTO
+	select CRYPTO_SHA256
 	select KEXEC_CORE
 	help
 	  This is new version of kexec system call. This system call is
@@ -94,10 +96,8 @@ config KEXEC_JUMP
 config CRASH_DUMP
 	bool "kernel crash dumps"
 	depends on ARCH_SUPPORTS_CRASH_DUMP
-	depends on ARCH_SUPPORTS_KEXEC
 	select CRASH_CORE
 	select KEXEC_CORE
-	select KEXEC
 	help
 	  Generate crash dump after being started by kexec.
 	  This should be normally only set in special crash dump kernels
diff --git a/kernel/Makefile b/kernel/Makefile
index 3947122d618b..ce105a5558fc 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -114,6 +114,7 @@ obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o
 obj-$(CONFIG_HAVE_STATIC_CALL) += static_call.o
 obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call_inline.o
 obj-$(CONFIG_CFI_CLANG) += cfi.o
+obj-$(CONFIG_NUMA) += numa.o
 
 obj-$(CONFIG_PERF_EVENTS) += events/
 
diff --git a/kernel/async.c b/kernel/async.c
index b2c4ba5686ee..97f224a5257b 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -46,11 +46,12 @@ asynchronous and synchronous parts of the kernel.
 
 #include <linux/async.h>
 #include <linux/atomic.h>
-#include <linux/ktime.h>
 #include <linux/export.h>
-#include <linux/wait.h>
+#include <linux/ktime.h>
+#include <linux/pid.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/wait.h>
 #include <linux/workqueue.h>
 
 #include "workqueue_internal.h"
@@ -145,6 +146,39 @@ static void async_run_entry_fn(struct work_struct *work)
 	wake_up(&async_done);
 }
 
+static async_cookie_t __async_schedule_node_domain(async_func_t func,
+						   void *data, int node,
+						   struct async_domain *domain,
+						   struct async_entry *entry)
+{
+	async_cookie_t newcookie;
+	unsigned long flags;
+
+	INIT_LIST_HEAD(&entry->domain_list);
+	INIT_LIST_HEAD(&entry->global_list);
+	INIT_WORK(&entry->work, async_run_entry_fn);
+	entry->func = func;
+	entry->data = data;
+	entry->domain = domain;
+
+	spin_lock_irqsave(&async_lock, flags);
+
+	/* allocate cookie and queue */
+	newcookie = entry->cookie = next_cookie++;
+
+	list_add_tail(&entry->domain_list, &domain->pending);
+	if (domain->registered)
+		list_add_tail(&entry->global_list, &async_global_pending);
+
+	atomic_inc(&entry_count);
+	spin_unlock_irqrestore(&async_lock, flags);
+
+	/* schedule for execution */
+	queue_work_node(node, system_unbound_wq, &entry->work);
+
+	return newcookie;
+}
+
 /**
  * async_schedule_node_domain - NUMA specific version of async_schedule_domain
  * @func: function to execute asynchronously
@@ -186,29 +220,8 @@ async_cookie_t async_schedule_node_domain(async_func_t func, void *data,
 		func(data, newcookie);
 		return newcookie;
 	}
-	INIT_LIST_HEAD(&entry->domain_list);
-	INIT_LIST_HEAD(&entry->global_list);
-	INIT_WORK(&entry->work, async_run_entry_fn);
-	entry->func = func;
-	entry->data = data;
-	entry->domain = domain;
-
-	spin_lock_irqsave(&async_lock, flags);
-
-	/* allocate cookie and queue */
-	newcookie = entry->cookie = next_cookie++;
 
-	list_add_tail(&entry->domain_list, &domain->pending);
-	if (domain->registered)
-		list_add_tail(&entry->global_list, &async_global_pending);
-
-	atomic_inc(&entry_count);
-	spin_unlock_irqrestore(&async_lock, flags);
-
-	/* schedule for execution */
-	queue_work_node(node, system_unbound_wq, &entry->work);
-
-	return newcookie;
+	return __async_schedule_node_domain(func, data, node, domain, entry);
 }
 EXPORT_SYMBOL_GPL(async_schedule_node_domain);
 
@@ -232,6 +245,35 @@ async_cookie_t async_schedule_node(async_func_t func, void *data, int node)
 EXPORT_SYMBOL_GPL(async_schedule_node);
 
 /**
+ * async_schedule_dev_nocall - A simplified variant of async_schedule_dev()
+ * @func: function to execute asynchronously
+ * @dev: device argument to be passed to function
+ *
+ * @dev is used as both the argument for the function and to provide NUMA
+ * context for where to run the function.
+ *
+ * If the asynchronous execution of @func is scheduled successfully, return
+ * true. Otherwise, do nothing and return false, unlike async_schedule_dev()
+ * that will run the function synchronously then.
+ */
+bool async_schedule_dev_nocall(async_func_t func, struct device *dev)
+{
+	struct async_entry *entry;
+
+	entry = kzalloc(sizeof(struct async_entry), GFP_KERNEL);
+
+	/* Give up if there is no memory or too much work. */
+	if (!entry || atomic_read(&entry_count) > MAX_WORK) {
+		kfree(entry);
+		return false;
+	}
+
+	__async_schedule_node_domain(func, dev, dev_to_node(dev),
+				     &async_dfl_domain, entry);
+	return true;
+}
+
+/**
  * async_synchronize_full - synchronize all asynchronous function calls
  *
  * This function waits until all asynchronous function calls have been done.
diff --git a/kernel/audit.c b/kernel/audit.c
index 16205dd29843..9c8e5f732c4c 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -487,15 +487,19 @@ static void auditd_conn_free(struct rcu_head *rcu)
  * @pid: auditd PID
  * @portid: auditd netlink portid
  * @net: auditd network namespace pointer
+ * @skb: the netlink command from the audit daemon
+ * @ack: netlink ack flag, cleared if ack'd here
  *
  * Description:
  * This function will obtain and drop network namespace references as
  * necessary.  Returns zero on success, negative values on failure.
  */
-static int auditd_set(struct pid *pid, u32 portid, struct net *net)
+static int auditd_set(struct pid *pid, u32 portid, struct net *net,
+		      struct sk_buff *skb, bool *ack)
 {
 	unsigned long flags;
 	struct auditd_connection *ac_old, *ac_new;
+	struct nlmsghdr *nlh;
 
 	if (!pid || !net)
 		return -EINVAL;
@@ -507,6 +511,13 @@ static int auditd_set(struct pid *pid, u32 portid, struct net *net)
 	ac_new->portid = portid;
 	ac_new->net = get_net(net);
 
+	/* send the ack now to avoid a race with the queue backlog */
+	if (*ack) {
+		nlh = nlmsg_hdr(skb);
+		netlink_ack(skb, nlh, 0, NULL);
+		*ack = false;
+	}
+
 	spin_lock_irqsave(&auditd_conn_lock, flags);
 	ac_old = rcu_dereference_protected(auditd_conn,
 					   lockdep_is_held(&auditd_conn_lock));
@@ -1200,7 +1211,8 @@ static int audit_replace(struct pid *pid)
 	return auditd_send_unicast_skb(skb);
 }
 
-static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
+			     bool *ack)
 {
 	u32			seq;
 	void			*data;
@@ -1293,7 +1305,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 				/* register a new auditd connection */
 				err = auditd_set(req_pid,
 						 NETLINK_CB(skb).portid,
-						 sock_net(NETLINK_CB(skb).sk));
+						 sock_net(NETLINK_CB(skb).sk),
+						 skb, ack);
 				if (audit_enabled != AUDIT_OFF)
 					audit_log_config_change("audit_pid",
 								new_pid,
@@ -1538,9 +1551,10 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
  * Parse the provided skb and deal with any messages that may be present,
  * malformed skbs are discarded.
  */
-static void audit_receive(struct sk_buff  *skb)
+static void audit_receive(struct sk_buff *skb)
 {
 	struct nlmsghdr *nlh;
+	bool ack;
 	/*
 	 * len MUST be signed for nlmsg_next to be able to dec it below 0
 	 * if the nlmsg_len was not aligned
@@ -1553,9 +1567,12 @@ static void audit_receive(struct sk_buff  *skb)
 
 	audit_ctl_lock();
 	while (nlmsg_ok(nlh, len)) {
-		err = audit_receive_msg(skb, nlh);
-		/* if err or if this message says it wants a response */
-		if (err || (nlh->nlmsg_flags & NLM_F_ACK))
+		ack = nlh->nlmsg_flags & NLM_F_ACK;
+		err = audit_receive_msg(skb, nlh, &ack);
+
+		/* send an ack if the user asked for one and audit_receive_msg
+		 * didn't already do it, or if there was an error. */
+		if (ack || err)
 			netlink_ack(skb, nlh, err, NULL);
 
 		nlh = nlmsg_next(nlh, &len);
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 91e82e34b51e..7a98cd176a12 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -531,7 +531,7 @@ int audit_exe_compare(struct task_struct *tsk, struct audit_fsnotify_mark *mark)
 	if (tsk != current)
 		return 0;
 
-	if (WARN_ON_ONCE(!current->mm))
+	if (!current->mm)
 		return 0;
 	exe_file = get_mm_exe_file(current->mm);
 	if (!exe_file)
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 2058e89b5ddd..0bdbbbeab155 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -867,11 +867,11 @@ int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
 	}
 
 	if (old_ptr)
-		map->ops->map_fd_put_ptr(old_ptr);
+		map->ops->map_fd_put_ptr(map, old_ptr, true);
 	return 0;
 }
 
-static long fd_array_map_delete_elem(struct bpf_map *map, void *key)
+static long __fd_array_map_delete_elem(struct bpf_map *map, void *key, bool need_defer)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	void *old_ptr;
@@ -890,13 +890,18 @@ static long fd_array_map_delete_elem(struct bpf_map *map, void *key)
 	}
 
 	if (old_ptr) {
-		map->ops->map_fd_put_ptr(old_ptr);
+		map->ops->map_fd_put_ptr(map, old_ptr, need_defer);
 		return 0;
 	} else {
 		return -ENOENT;
 	}
 }
 
+static long fd_array_map_delete_elem(struct bpf_map *map, void *key)
+{
+	return __fd_array_map_delete_elem(map, key, true);
+}
+
 static void *prog_fd_array_get_ptr(struct bpf_map *map,
 				   struct file *map_file, int fd)
 {
@@ -913,8 +918,9 @@ static void *prog_fd_array_get_ptr(struct bpf_map *map,
 	return prog;
 }
 
-static void prog_fd_array_put_ptr(void *ptr)
+static void prog_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
 {
+	/* bpf_prog is freed after one RCU or tasks trace grace period */
 	bpf_prog_put(ptr);
 }
 
@@ -924,13 +930,13 @@ static u32 prog_fd_array_sys_lookup_elem(void *ptr)
 }
 
 /* decrement refcnt of all bpf_progs that are stored in this map */
-static void bpf_fd_array_map_clear(struct bpf_map *map)
+static void bpf_fd_array_map_clear(struct bpf_map *map, bool need_defer)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	int i;
 
 	for (i = 0; i < array->map.max_entries; i++)
-		fd_array_map_delete_elem(map, &i);
+		__fd_array_map_delete_elem(map, &i, need_defer);
 }
 
 static void prog_array_map_seq_show_elem(struct bpf_map *map, void *key,
@@ -1012,11 +1018,16 @@ static void prog_array_map_poke_untrack(struct bpf_map *map,
 	mutex_unlock(&aux->poke_mutex);
 }
 
+void __weak bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
+				      struct bpf_prog *new, struct bpf_prog *old)
+{
+	WARN_ON_ONCE(1);
+}
+
 static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 				    struct bpf_prog *old,
 				    struct bpf_prog *new)
 {
-	u8 *old_addr, *new_addr, *old_bypass_addr;
 	struct prog_poke_elem *elem;
 	struct bpf_array_aux *aux;
 
@@ -1025,7 +1036,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 
 	list_for_each_entry(elem, &aux->poke_progs, list) {
 		struct bpf_jit_poke_descriptor *poke;
-		int i, ret;
+		int i;
 
 		for (i = 0; i < elem->aux->size_poke_tab; i++) {
 			poke = &elem->aux->poke_tab[i];
@@ -1044,21 +1055,10 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 			 *    activated, so tail call updates can arrive from here
 			 *    while JIT is still finishing its final fixup for
 			 *    non-activated poke entries.
-			 * 3) On program teardown, the program's kallsym entry gets
-			 *    removed out of RCU callback, but we can only untrack
-			 *    from sleepable context, therefore bpf_arch_text_poke()
-			 *    might not see that this is in BPF text section and
-			 *    bails out with -EINVAL. As these are unreachable since
-			 *    RCU grace period already passed, we simply skip them.
-			 * 4) Also programs reaching refcount of zero while patching
+			 * 3) Also programs reaching refcount of zero while patching
 			 *    is in progress is okay since we're protected under
 			 *    poke_mutex and untrack the programs before the JIT
-			 *    buffer is freed. When we're still in the middle of
-			 *    patching and suddenly kallsyms entry of the program
-			 *    gets evicted, we just skip the rest which is fine due
-			 *    to point 3).
-			 * 5) Any other error happening below from bpf_arch_text_poke()
-			 *    is a unexpected bug.
+			 *    buffer is freed.
 			 */
 			if (!READ_ONCE(poke->tailcall_target_stable))
 				continue;
@@ -1068,39 +1068,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 			    poke->tail_call.key != key)
 				continue;
 
-			old_bypass_addr = old ? NULL : poke->bypass_addr;
-			old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL;
-			new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL;
-
-			if (new) {
-				ret = bpf_arch_text_poke(poke->tailcall_target,
-							 BPF_MOD_JUMP,
-							 old_addr, new_addr);
-				BUG_ON(ret < 0 && ret != -EINVAL);
-				if (!old) {
-					ret = bpf_arch_text_poke(poke->tailcall_bypass,
-								 BPF_MOD_JUMP,
-								 poke->bypass_addr,
-								 NULL);
-					BUG_ON(ret < 0 && ret != -EINVAL);
-				}
-			} else {
-				ret = bpf_arch_text_poke(poke->tailcall_bypass,
-							 BPF_MOD_JUMP,
-							 old_bypass_addr,
-							 poke->bypass_addr);
-				BUG_ON(ret < 0 && ret != -EINVAL);
-				/* let other CPUs finish the execution of program
-				 * so that it will not possible to expose them
-				 * to invalid nop, stack unwind, nop state
-				 */
-				if (!ret)
-					synchronize_rcu();
-				ret = bpf_arch_text_poke(poke->tailcall_target,
-							 BPF_MOD_JUMP,
-							 old_addr, NULL);
-				BUG_ON(ret < 0 && ret != -EINVAL);
-			}
+			bpf_arch_poke_desc_update(poke, new, old);
 		}
 	}
 }
@@ -1109,7 +1077,7 @@ static void prog_array_map_clear_deferred(struct work_struct *work)
 {
 	struct bpf_map *map = container_of(work, struct bpf_array_aux,
 					   work)->map;
-	bpf_fd_array_map_clear(map);
+	bpf_fd_array_map_clear(map, true);
 	bpf_map_put(map);
 }
 
@@ -1189,7 +1157,7 @@ static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
 {
 	struct bpf_event_entry *ee;
 
-	ee = kzalloc(sizeof(*ee), GFP_ATOMIC);
+	ee = kzalloc(sizeof(*ee), GFP_KERNEL);
 	if (ee) {
 		ee->event = perf_file->private_data;
 		ee->perf_file = perf_file;
@@ -1239,8 +1207,9 @@ err_out:
 	return ee;
 }
 
-static void perf_event_fd_array_put_ptr(void *ptr)
+static void perf_event_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
 {
+	/* bpf_perf_event is freed after one RCU grace period */
 	bpf_event_entry_free_rcu(ptr);
 }
 
@@ -1258,7 +1227,7 @@ static void perf_event_fd_array_release(struct bpf_map *map,
 	for (i = 0; i < array->map.max_entries; i++) {
 		ee = READ_ONCE(array->ptrs[i]);
 		if (ee && ee->map_file == map_file)
-			fd_array_map_delete_elem(map, &i);
+			__fd_array_map_delete_elem(map, &i, true);
 	}
 	rcu_read_unlock();
 }
@@ -1266,7 +1235,7 @@ static void perf_event_fd_array_release(struct bpf_map *map,
 static void perf_event_fd_array_map_free(struct bpf_map *map)
 {
 	if (map->map_flags & BPF_F_PRESERVE_ELEMS)
-		bpf_fd_array_map_clear(map);
+		bpf_fd_array_map_clear(map, false);
 	fd_array_map_free(map);
 }
 
@@ -1294,7 +1263,7 @@ static void *cgroup_fd_array_get_ptr(struct bpf_map *map,
 	return cgroup_get_from_fd(fd);
 }
 
-static void cgroup_fd_array_put_ptr(void *ptr)
+static void cgroup_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
 {
 	/* cgroup_put free cgrp after a rcu grace period */
 	cgroup_put(ptr);
@@ -1302,7 +1271,7 @@ static void cgroup_fd_array_put_ptr(void *ptr)
 
 static void cgroup_fd_array_free(struct bpf_map *map)
 {
-	bpf_fd_array_map_clear(map);
+	bpf_fd_array_map_clear(map, false);
 	fd_array_map_free(map);
 }
 
@@ -1347,7 +1316,7 @@ static void array_of_map_free(struct bpf_map *map)
 	 * is protected by fdget/fdput.
 	 */
 	bpf_map_meta_free(map->inner_map_meta);
-	bpf_fd_array_map_clear(map);
+	bpf_fd_array_map_clear(map, false);
 	fd_array_map_free(map);
 }
 
diff --git a/kernel/bpf/bpf_cgrp_storage.c b/kernel/bpf/bpf_cgrp_storage.c
index d44fe8dd9732..28efd0a3f220 100644
--- a/kernel/bpf/bpf_cgrp_storage.c
+++ b/kernel/bpf/bpf_cgrp_storage.c
@@ -82,7 +82,7 @@ static void *bpf_cgrp_storage_lookup_elem(struct bpf_map *map, void *key)
 	int fd;
 
 	fd = *(int *)key;
-	cgroup = cgroup_get_from_fd(fd);
+	cgroup = cgroup_v1v2_get_from_fd(fd);
 	if (IS_ERR(cgroup))
 		return ERR_CAST(cgroup);
 
@@ -101,7 +101,7 @@ static long bpf_cgrp_storage_update_elem(struct bpf_map *map, void *key,
 	int fd;
 
 	fd = *(int *)key;
-	cgroup = cgroup_get_from_fd(fd);
+	cgroup = cgroup_v1v2_get_from_fd(fd);
 	if (IS_ERR(cgroup))
 		return PTR_ERR(cgroup);
 
@@ -131,7 +131,7 @@ static long bpf_cgrp_storage_delete_elem(struct bpf_map *map, void *key)
 	int err, fd;
 
 	fd = *(int *)key;
-	cgroup = cgroup_get_from_fd(fd);
+	cgroup = cgroup_v1v2_get_from_fd(fd);
 	if (IS_ERR(cgroup))
 		return PTR_ERR(cgroup);
 
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index e14c822f8911..e8e910395bf6 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -298,6 +298,18 @@ BTF_ID(func, bpf_lsm_kernel_module_request)
 BTF_ID(func, bpf_lsm_kernel_read_file)
 BTF_ID(func, bpf_lsm_kernfs_init_security)
 
+#ifdef CONFIG_SECURITY_PATH
+BTF_ID(func, bpf_lsm_path_unlink)
+BTF_ID(func, bpf_lsm_path_mkdir)
+BTF_ID(func, bpf_lsm_path_rmdir)
+BTF_ID(func, bpf_lsm_path_truncate)
+BTF_ID(func, bpf_lsm_path_symlink)
+BTF_ID(func, bpf_lsm_path_link)
+BTF_ID(func, bpf_lsm_path_rename)
+BTF_ID(func, bpf_lsm_path_chmod)
+BTF_ID(func, bpf_lsm_path_chown)
+#endif /* CONFIG_SECURITY_PATH */
+
 #ifdef CONFIG_KEYS
 BTF_ID(func, bpf_lsm_key_free)
 #endif /* CONFIG_KEYS */
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index db6176fb64dc..02068bd0e4d9 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -352,18 +352,24 @@ const struct bpf_link_ops bpf_struct_ops_link_lops = {
 int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
 				      struct bpf_tramp_link *link,
 				      const struct btf_func_model *model,
-				      void *image, void *image_end)
+				      void *stub_func, void *image, void *image_end)
 {
-	u32 flags;
+	u32 flags = BPF_TRAMP_F_INDIRECT;
+	int size;
 
 	tlinks[BPF_TRAMP_FENTRY].links[0] = link;
 	tlinks[BPF_TRAMP_FENTRY].nr_links = 1;
-	/* BPF_TRAMP_F_RET_FENTRY_RET is only used by bpf_struct_ops,
-	 * and it must be used alone.
-	 */
-	flags = model->ret_size > 0 ? BPF_TRAMP_F_RET_FENTRY_RET : 0;
+
+	if (model->ret_size > 0)
+		flags |= BPF_TRAMP_F_RET_FENTRY_RET;
+
+	size = arch_bpf_trampoline_size(model, flags, tlinks, NULL);
+	if (size < 0)
+		return size;
+	if (size > (unsigned long)image_end - (unsigned long)image)
+		return -E2BIG;
 	return arch_prepare_bpf_trampoline(NULL, image, image_end,
-					   model, flags, tlinks, NULL);
+					   model, flags, tlinks, stub_func);
 }
 
 static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
@@ -497,11 +503,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 
 		err = bpf_struct_ops_prepare_trampoline(tlinks, link,
 							&st_ops->func_models[i],
+							*(void **)(st_ops->cfi_stubs + moff),
 							image, image_end);
 		if (err < 0)
 			goto reset_unlock;
 
-		*(void **)(kdata + moff) = image;
+		*(void **)(kdata + moff) = image + cfi_get_offset();
 		image += err;
 
 		/* put prog_id to udata */
@@ -515,7 +522,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 			if (err)
 				goto reset_unlock;
 		}
-		set_memory_rox((long)st_map->image, 1);
+		arch_protect_bpf_trampoline(st_map->image, PAGE_SIZE);
 		/* Let bpf_link handle registration & unregistration.
 		 *
 		 * Pair with smp_load_acquire() during lookup_elem().
@@ -524,7 +531,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 		goto unlock;
 	}
 
-	set_memory_rox((long)st_map->image, 1);
+	arch_protect_bpf_trampoline(st_map->image, PAGE_SIZE);
 	err = st_ops->reg(kdata);
 	if (likely(!err)) {
 		/* This refcnt increment on the map here after
@@ -547,8 +554,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 	 * there was a race in registering the struct_ops (under the same name) to
 	 * a sub-system through different struct_ops's maps.
 	 */
-	set_memory_nx((long)st_map->image, 1);
-	set_memory_rw((long)st_map->image, 1);
+	arch_unprotect_bpf_trampoline(st_map->image, PAGE_SIZE);
 
 reset_unlock:
 	bpf_struct_ops_map_put_progs(st_map);
@@ -616,7 +622,7 @@ static void __bpf_struct_ops_map_free(struct bpf_map *map)
 		bpf_struct_ops_map_put_progs(st_map);
 	bpf_map_area_free(st_map->links);
 	if (st_map->image) {
-		bpf_jit_free_exec(st_map->image);
+		arch_free_bpf_trampoline(st_map->image, PAGE_SIZE);
 		bpf_jit_uncharge_modmem(PAGE_SIZE);
 	}
 	bpf_map_area_free(st_map->uvalue);
@@ -691,7 +697,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 		return ERR_PTR(ret);
 	}
 
-	st_map->image = bpf_jit_alloc_exec(PAGE_SIZE);
+	st_map->image = arch_alloc_bpf_trampoline(PAGE_SIZE);
 	if (!st_map->image) {
 		/* __bpf_struct_ops_map_free() uses st_map->image as flag
 		 * for "charged or not". In this case, we need to unchange
@@ -711,7 +717,6 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 	}
 
 	mutex_init(&st_map->lock);
-	set_vm_flush_reset_perms(st_map->image);
 	bpf_map_init_from_attr(map, attr);
 
 	return map;
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 15d71d2986d3..51e8b4bee0c8 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3840,9 +3840,6 @@ end:
 	return ERR_PTR(ret);
 }
 
-#define GRAPH_ROOT_MASK (BPF_LIST_HEAD | BPF_RB_ROOT)
-#define GRAPH_NODE_MASK (BPF_LIST_NODE | BPF_RB_NODE)
-
 int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec)
 {
 	int i;
@@ -3855,13 +3852,13 @@ int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec)
 	 * Hence we only need to ensure that bpf_{list_head,rb_root} ownership
 	 * does not form cycles.
 	 */
-	if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & GRAPH_ROOT_MASK))
+	if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & BPF_GRAPH_ROOT))
 		return 0;
 	for (i = 0; i < rec->cnt; i++) {
 		struct btf_struct_meta *meta;
 		u32 btf_id;
 
-		if (!(rec->fields[i].type & GRAPH_ROOT_MASK))
+		if (!(rec->fields[i].type & BPF_GRAPH_ROOT))
 			continue;
 		btf_id = rec->fields[i].graph_root.value_btf_id;
 		meta = btf_find_struct_meta(btf, btf_id);
@@ -3873,7 +3870,7 @@ int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec)
 		 * to check ownership cycle for a type unless it's also a
 		 * node type.
 		 */
-		if (!(rec->field_mask & GRAPH_NODE_MASK))
+		if (!(rec->field_mask & BPF_GRAPH_NODE))
 			continue;
 
 		/* We need to ensure ownership acyclicity among all types. The
@@ -3909,7 +3906,7 @@ int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec)
 		 * - A is both an root and node.
 		 * - B is only an node.
 		 */
-		if (meta->record->field_mask & GRAPH_ROOT_MASK)
+		if (meta->record->field_mask & BPF_GRAPH_ROOT)
 			return -ELOOP;
 	}
 	return 0;
@@ -6768,222 +6765,64 @@ int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *pr
 	return btf_check_func_type_match(log, btf1, t1, btf2, t2);
 }
 
-static int btf_check_func_arg_match(struct bpf_verifier_env *env,
-				    const struct btf *btf, u32 func_id,
-				    struct bpf_reg_state *regs,
-				    bool ptr_to_mem_ok,
-				    bool processing_call)
+static bool btf_is_dynptr_ptr(const struct btf *btf, const struct btf_type *t)
 {
-	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
-	struct bpf_verifier_log *log = &env->log;
-	const char *func_name, *ref_tname;
-	const struct btf_type *t, *ref_t;
-	const struct btf_param *args;
-	u32 i, nargs, ref_id;
-	int ret;
-
-	t = btf_type_by_id(btf, func_id);
-	if (!t || !btf_type_is_func(t)) {
-		/* These checks were already done by the verifier while loading
-		 * struct bpf_func_info or in add_kfunc_call().
-		 */
-		bpf_log(log, "BTF of func_id %u doesn't point to KIND_FUNC\n",
-			func_id);
-		return -EFAULT;
-	}
-	func_name = btf_name_by_offset(btf, t->name_off);
-
-	t = btf_type_by_id(btf, t->type);
-	if (!t || !btf_type_is_func_proto(t)) {
-		bpf_log(log, "Invalid BTF of func %s\n", func_name);
-		return -EFAULT;
-	}
-	args = (const struct btf_param *)(t + 1);
-	nargs = btf_type_vlen(t);
-	if (nargs > MAX_BPF_FUNC_REG_ARGS) {
-		bpf_log(log, "Function %s has %d > %d args\n", func_name, nargs,
-			MAX_BPF_FUNC_REG_ARGS);
-		return -EINVAL;
-	}
-
-	/* check that BTF function arguments match actual types that the
-	 * verifier sees.
-	 */
-	for (i = 0; i < nargs; i++) {
-		enum bpf_arg_type arg_type = ARG_DONTCARE;
-		u32 regno = i + 1;
-		struct bpf_reg_state *reg = &regs[regno];
-
-		t = btf_type_skip_modifiers(btf, args[i].type, NULL);
-		if (btf_type_is_scalar(t)) {
-			if (reg->type == SCALAR_VALUE)
-				continue;
-			bpf_log(log, "R%d is not a scalar\n", regno);
-			return -EINVAL;
-		}
-
-		if (!btf_type_is_ptr(t)) {
-			bpf_log(log, "Unrecognized arg#%d type %s\n",
-				i, btf_type_str(t));
-			return -EINVAL;
-		}
-
-		ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id);
-		ref_tname = btf_name_by_offset(btf, ref_t->name_off);
-
-		ret = check_func_arg_reg_off(env, reg, regno, arg_type);
-		if (ret < 0)
-			return ret;
+	const char *name;
 
-		if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) {
-			/* If function expects ctx type in BTF check that caller
-			 * is passing PTR_TO_CTX.
-			 */
-			if (reg->type != PTR_TO_CTX) {
-				bpf_log(log,
-					"arg#%d expected pointer to ctx, but got %s\n",
-					i, btf_type_str(t));
-				return -EINVAL;
-			}
-		} else if (ptr_to_mem_ok && processing_call) {
-			const struct btf_type *resolve_ret;
-			u32 type_size;
+	t = btf_type_by_id(btf, t->type); /* skip PTR */
 
-			resolve_ret = btf_resolve_size(btf, ref_t, &type_size);
-			if (IS_ERR(resolve_ret)) {
-				bpf_log(log,
-					"arg#%d reference type('%s %s') size cannot be determined: %ld\n",
-					i, btf_type_str(ref_t), ref_tname,
-					PTR_ERR(resolve_ret));
-				return -EINVAL;
-			}
+	while (btf_type_is_modifier(t))
+		t = btf_type_by_id(btf, t->type);
 
-			if (check_mem_reg(env, reg, regno, type_size))
-				return -EINVAL;
-		} else {
-			bpf_log(log, "reg type unsupported for arg#%d function %s#%d\n", i,
-				func_name, func_id);
-			return -EINVAL;
-		}
+	/* allow either struct or struct forward declaration */
+	if (btf_type_is_struct(t) ||
+	    (btf_type_is_fwd(t) && btf_type_kflag(t) == 0)) {
+		name = btf_str_by_offset(btf, t->name_off);
+		return name && strcmp(name, "bpf_dynptr") == 0;
 	}
 
-	return 0;
-}
-
-/* Compare BTF of a function declaration with given bpf_reg_state.
- * Returns:
- * EFAULT - there is a verifier bug. Abort verification.
- * EINVAL - there is a type mismatch or BTF is not available.
- * 0 - BTF matches with what bpf_reg_state expects.
- * Only PTR_TO_CTX and SCALAR_VALUE states are recognized.
- */
-int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog,
-				struct bpf_reg_state *regs)
-{
-	struct bpf_prog *prog = env->prog;
-	struct btf *btf = prog->aux->btf;
-	bool is_global;
-	u32 btf_id;
-	int err;
-
-	if (!prog->aux->func_info)
-		return -EINVAL;
-
-	btf_id = prog->aux->func_info[subprog].type_id;
-	if (!btf_id)
-		return -EFAULT;
-
-	if (prog->aux->func_info_aux[subprog].unreliable)
-		return -EINVAL;
-
-	is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL;
-	err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, false);
-
-	/* Compiler optimizations can remove arguments from static functions
-	 * or mismatched type can be passed into a global function.
-	 * In such cases mark the function as unreliable from BTF point of view.
-	 */
-	if (err)
-		prog->aux->func_info_aux[subprog].unreliable = true;
-	return err;
-}
-
-/* Compare BTF of a function call with given bpf_reg_state.
- * Returns:
- * EFAULT - there is a verifier bug. Abort verification.
- * EINVAL - there is a type mismatch or BTF is not available.
- * 0 - BTF matches with what bpf_reg_state expects.
- * Only PTR_TO_CTX and SCALAR_VALUE states are recognized.
- *
- * NOTE: the code is duplicated from btf_check_subprog_arg_match()
- * because btf_check_func_arg_match() is still doing both. Once that
- * function is split in 2, we can call from here btf_check_subprog_arg_match()
- * first, and then treat the calling part in a new code path.
- */
-int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
-			   struct bpf_reg_state *regs)
-{
-	struct bpf_prog *prog = env->prog;
-	struct btf *btf = prog->aux->btf;
-	bool is_global;
-	u32 btf_id;
-	int err;
-
-	if (!prog->aux->func_info)
-		return -EINVAL;
-
-	btf_id = prog->aux->func_info[subprog].type_id;
-	if (!btf_id)
-		return -EFAULT;
-
-	if (prog->aux->func_info_aux[subprog].unreliable)
-		return -EINVAL;
-
-	is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL;
-	err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, true);
-
-	/* Compiler optimizations can remove arguments from static functions
-	 * or mismatched type can be passed into a global function.
-	 * In such cases mark the function as unreliable from BTF point of view.
-	 */
-	if (err)
-		prog->aux->func_info_aux[subprog].unreliable = true;
-	return err;
+	return false;
 }
 
-/* Convert BTF of a function into bpf_reg_state if possible
+/* Process BTF of a function to produce high-level expectation of function
+ * arguments (like ARG_PTR_TO_CTX, or ARG_PTR_TO_MEM, etc). This information
+ * is cached in subprog info for reuse.
  * Returns:
  * EFAULT - there is a verifier bug. Abort verification.
  * EINVAL - cannot convert BTF.
- * 0 - Successfully converted BTF into bpf_reg_state
- * (either PTR_TO_CTX or SCALAR_VALUE).
+ * 0 - Successfully processed BTF and constructed argument expectations.
  */
-int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
-			  struct bpf_reg_state *regs, bool is_ex_cb)
+int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog)
 {
+	bool is_global = subprog_aux(env, subprog)->linkage == BTF_FUNC_GLOBAL;
+	struct bpf_subprog_info *sub = subprog_info(env, subprog);
 	struct bpf_verifier_log *log = &env->log;
 	struct bpf_prog *prog = env->prog;
 	enum bpf_prog_type prog_type = prog->type;
 	struct btf *btf = prog->aux->btf;
 	const struct btf_param *args;
-	const struct btf_type *t, *ref_t;
+	const struct btf_type *t, *ref_t, *fn_t;
 	u32 i, nargs, btf_id;
 	const char *tname;
 
-	if (!prog->aux->func_info ||
-	    prog->aux->func_info_aux[subprog].linkage != BTF_FUNC_GLOBAL) {
+	if (sub->args_cached)
+		return 0;
+
+	if (!prog->aux->func_info) {
 		bpf_log(log, "Verifier bug\n");
 		return -EFAULT;
 	}
 
 	btf_id = prog->aux->func_info[subprog].type_id;
 	if (!btf_id) {
+		if (!is_global) /* not fatal for static funcs */
+			return -EINVAL;
 		bpf_log(log, "Global functions need valid BTF\n");
 		return -EFAULT;
 	}
 
-	t = btf_type_by_id(btf, btf_id);
-	if (!t || !btf_type_is_func(t)) {
+	fn_t = btf_type_by_id(btf, btf_id);
+	if (!fn_t || !btf_type_is_func(fn_t)) {
 		/* These checks were already done by the verifier while loading
 		 * struct bpf_func_info
 		 */
@@ -6991,11 +6830,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 			subprog);
 		return -EFAULT;
 	}
-	tname = btf_name_by_offset(btf, t->name_off);
-
-	if (log->level & BPF_LOG_LEVEL)
-		bpf_log(log, "Validating %s() func#%d...\n",
-			tname, subprog);
+	tname = btf_name_by_offset(btf, fn_t->name_off);
 
 	if (prog->aux->func_info_aux[subprog].unreliable) {
 		bpf_log(log, "Verifier bug in function %s()\n", tname);
@@ -7004,7 +6839,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 	if (prog_type == BPF_PROG_TYPE_EXT)
 		prog_type = prog->aux->dst_prog->type;
 
-	t = btf_type_by_id(btf, t->type);
+	t = btf_type_by_id(btf, fn_t->type);
 	if (!t || !btf_type_is_func_proto(t)) {
 		bpf_log(log, "Invalid type of function %s()\n", tname);
 		return -EFAULT;
@@ -7030,24 +6865,54 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 	 * Only PTR_TO_CTX and SCALAR are supported atm.
 	 */
 	for (i = 0; i < nargs; i++) {
-		struct bpf_reg_state *reg = &regs[i + 1];
+		bool is_nonnull = false;
+		const char *tag;
 
 		t = btf_type_by_id(btf, args[i].type);
+
+		tag = btf_find_decl_tag_value(btf, fn_t, i, "arg:");
+		if (IS_ERR(tag) && PTR_ERR(tag) == -ENOENT) {
+			tag = NULL;
+		} else if (IS_ERR(tag)) {
+			bpf_log(log, "arg#%d type's tag fetching failure: %ld\n", i, PTR_ERR(tag));
+			return PTR_ERR(tag);
+		}
+		/* 'arg:<tag>' decl_tag takes precedence over derivation of
+		 * register type from BTF type itself
+		 */
+		if (tag) {
+			/* disallow arg tags in static subprogs */
+			if (!is_global) {
+				bpf_log(log, "arg#%d type tag is not supported in static functions\n", i);
+				return -EOPNOTSUPP;
+			}
+			if (strcmp(tag, "ctx") == 0) {
+				sub->args[i].arg_type = ARG_PTR_TO_CTX;
+				continue;
+			}
+			if (strcmp(tag, "nonnull") == 0)
+				is_nonnull = true;
+		}
+
 		while (btf_type_is_modifier(t))
 			t = btf_type_by_id(btf, t->type);
 		if (btf_type_is_int(t) || btf_is_any_enum(t)) {
-			reg->type = SCALAR_VALUE;
+			sub->args[i].arg_type = ARG_ANYTHING;
 			continue;
 		}
-		if (btf_type_is_ptr(t)) {
-			if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) {
-				reg->type = PTR_TO_CTX;
-				continue;
-			}
+		if (btf_type_is_ptr(t) && btf_get_prog_ctx_type(log, btf, t, prog_type, i)) {
+			sub->args[i].arg_type = ARG_PTR_TO_CTX;
+			continue;
+		}
+		if (btf_type_is_ptr(t) && btf_is_dynptr_ptr(btf, t)) {
+			sub->args[i].arg_type = ARG_PTR_TO_DYNPTR | MEM_RDONLY;
+			continue;
+		}
+		if (is_global && btf_type_is_ptr(t)) {
+			u32 mem_size;
 
 			t = btf_type_skip_modifiers(btf, t->type, NULL);
-
-			ref_t = btf_resolve_size(btf, t, &reg->mem_size);
+			ref_t = btf_resolve_size(btf, t, &mem_size);
 			if (IS_ERR(ref_t)) {
 				bpf_log(log,
 				    "arg#%d reference type('%s %s') size cannot be determined: %ld\n",
@@ -7056,23 +6921,22 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 				return -EINVAL;
 			}
 
-			reg->type = PTR_TO_MEM | PTR_MAYBE_NULL;
-			reg->id = ++env->id_gen;
-
+			sub->args[i].arg_type = is_nonnull ? ARG_PTR_TO_MEM : ARG_PTR_TO_MEM_OR_NULL;
+			sub->args[i].mem_size = mem_size;
 			continue;
 		}
+		if (is_nonnull) {
+			bpf_log(log, "arg#%d marked as non-null, but is not a pointer type\n", i);
+			return -EINVAL;
+		}
 		bpf_log(log, "Arg#%d type %s in %s() is not supported yet.\n",
 			i, btf_type_str(t), tname);
 		return -EINVAL;
 	}
-	/* We have already ensured that the callback returns an integer, just
-	 * like all global subprogs. We need to determine it only has a single
-	 * scalar argument.
-	 */
-	if (is_ex_cb && (nargs != 1 || regs[BPF_REG_1].type != SCALAR_VALUE)) {
-		bpf_log(log, "exception cb only supports single integer argument\n");
-		return -EINVAL;
-	}
+
+	sub->arg_cnt = nargs;
+	sub->args_cached = true;
+
 	return 0;
 }
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 08626b519ce2..ea6843be2616 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -64,8 +64,8 @@
 #define OFF	insn->off
 #define IMM	insn->imm
 
-struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma;
-bool bpf_global_ma_set, bpf_global_percpu_ma_set;
+struct bpf_mem_alloc bpf_global_ma;
+bool bpf_global_ma_set;
 
 /* No hurry in this branch
  *
@@ -121,6 +121,9 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 #endif
 
 	INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode);
+#ifdef CONFIG_FINEIBT
+	INIT_LIST_HEAD_RCU(&fp->aux->ksym_prefix.lnode);
+#endif
 	mutex_init(&fp->aux->used_maps_mutex);
 	mutex_init(&fp->aux->dst_mutex);
 
@@ -371,14 +374,18 @@ static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, s32 end_old,
 static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old,
 				s32 end_new, s32 curr, const bool probe_pass)
 {
-	const s32 off_min = S16_MIN, off_max = S16_MAX;
+	s64 off_min, off_max, off;
 	s32 delta = end_new - end_old;
-	s32 off;
 
-	if (insn->code == (BPF_JMP32 | BPF_JA))
+	if (insn->code == (BPF_JMP32 | BPF_JA)) {
 		off = insn->imm;
-	else
+		off_min = S32_MIN;
+		off_max = S32_MAX;
+	} else {
 		off = insn->off;
+		off_min = S16_MIN;
+		off_max = S16_MAX;
+	}
 
 	if (curr < pos && curr + off + 1 >= end_old)
 		off += delta;
@@ -683,6 +690,23 @@ void bpf_prog_kallsyms_add(struct bpf_prog *fp)
 	fp->aux->ksym.prog = true;
 
 	bpf_ksym_add(&fp->aux->ksym);
+
+#ifdef CONFIG_FINEIBT
+	/*
+	 * When FineIBT, code in the __cfi_foo() symbols can get executed
+	 * and hence unwinder needs help.
+	 */
+	if (cfi_mode != CFI_FINEIBT)
+		return;
+
+	snprintf(fp->aux->ksym_prefix.name, KSYM_NAME_LEN,
+		 "__cfi_%s", fp->aux->ksym.name);
+
+	fp->aux->ksym_prefix.start = (unsigned long) fp->bpf_func - 16;
+	fp->aux->ksym_prefix.end   = (unsigned long) fp->bpf_func;
+
+	bpf_ksym_add(&fp->aux->ksym_prefix);
+#endif
 }
 
 void bpf_prog_kallsyms_del(struct bpf_prog *fp)
@@ -691,6 +715,11 @@ void bpf_prog_kallsyms_del(struct bpf_prog *fp)
 		return;
 
 	bpf_ksym_del(&fp->aux->ksym);
+#ifdef CONFIG_FINEIBT
+	if (cfi_mode != CFI_FINEIBT)
+		return;
+	bpf_ksym_del(&fp->aux->ksym_prefix);
+#endif
 }
 
 static struct bpf_ksym *bpf_ksym_find(unsigned long addr)
@@ -928,20 +957,20 @@ out:
 	return ptr;
 }
 
-void bpf_prog_pack_free(struct bpf_binary_header *hdr)
+void bpf_prog_pack_free(void *ptr, u32 size)
 {
 	struct bpf_prog_pack *pack = NULL, *tmp;
 	unsigned int nbits;
 	unsigned long pos;
 
 	mutex_lock(&pack_mutex);
-	if (hdr->size > BPF_PROG_PACK_SIZE) {
-		bpf_jit_free_exec(hdr);
+	if (size > BPF_PROG_PACK_SIZE) {
+		bpf_jit_free_exec(ptr);
 		goto out;
 	}
 
 	list_for_each_entry(tmp, &pack_list, list) {
-		if ((void *)hdr >= tmp->ptr && (tmp->ptr + BPF_PROG_PACK_SIZE) > (void *)hdr) {
+		if (ptr >= tmp->ptr && (tmp->ptr + BPF_PROG_PACK_SIZE) > ptr) {
 			pack = tmp;
 			break;
 		}
@@ -950,10 +979,10 @@ void bpf_prog_pack_free(struct bpf_binary_header *hdr)
 	if (WARN_ONCE(!pack, "bpf_prog_pack bug\n"))
 		goto out;
 
-	nbits = BPF_PROG_SIZE_TO_NBITS(hdr->size);
-	pos = ((unsigned long)hdr - (unsigned long)pack->ptr) >> BPF_PROG_CHUNK_SHIFT;
+	nbits = BPF_PROG_SIZE_TO_NBITS(size);
+	pos = ((unsigned long)ptr - (unsigned long)pack->ptr) >> BPF_PROG_CHUNK_SHIFT;
 
-	WARN_ONCE(bpf_arch_text_invalidate(hdr, hdr->size),
+	WARN_ONCE(bpf_arch_text_invalidate(ptr, size),
 		  "bpf_prog_pack bug: missing bpf_arch_text_invalidate?\n");
 
 	bitmap_clear(pack->bitmap, pos, nbits);
@@ -1100,8 +1129,7 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr,
 
 	*rw_header = kvmalloc(size, GFP_KERNEL);
 	if (!*rw_header) {
-		bpf_arch_text_copy(&ro_header->size, &size, sizeof(size));
-		bpf_prog_pack_free(ro_header);
+		bpf_prog_pack_free(ro_header, size);
 		bpf_jit_uncharge_modmem(size);
 		return NULL;
 	}
@@ -1132,7 +1160,7 @@ int bpf_jit_binary_pack_finalize(struct bpf_prog *prog,
 	kvfree(rw_header);
 
 	if (IS_ERR(ptr)) {
-		bpf_prog_pack_free(ro_header);
+		bpf_prog_pack_free(ro_header, ro_header->size);
 		return PTR_ERR(ptr);
 	}
 	return 0;
@@ -1153,7 +1181,7 @@ void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header,
 {
 	u32 size = ro_header->size;
 
-	bpf_prog_pack_free(ro_header);
+	bpf_prog_pack_free(ro_header, size);
 	kvfree(rw_header);
 	bpf_jit_uncharge_modmem(size);
 }
@@ -2664,12 +2692,16 @@ void __bpf_free_used_maps(struct bpf_prog_aux *aux,
 			  struct bpf_map **used_maps, u32 len)
 {
 	struct bpf_map *map;
+	bool sleepable;
 	u32 i;
 
+	sleepable = aux->sleepable;
 	for (i = 0; i < len; i++) {
 		map = used_maps[i];
 		if (map->ops->map_poke_untrack)
 			map->ops->map_poke_untrack(map, aux);
+		if (sleepable)
+			atomic64_dec(&map->sleepable_refcnt);
 		bpf_map_put(map);
 	}
 }
@@ -2934,9 +2966,7 @@ static int __init bpf_global_ma_init(void)
 
 	ret = bpf_mem_alloc_init(&bpf_global_ma, 0, false);
 	bpf_global_ma_set = !ret;
-	ret = bpf_mem_alloc_init(&bpf_global_percpu_ma, 0, true);
-	bpf_global_percpu_ma_set = !ret;
-	return !bpf_global_ma_set || !bpf_global_percpu_ma_set;
+	return ret;
 }
 late_initcall(bpf_global_ma_init);
 #endif
diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c
index e01c741e54e7..2e73533a3811 100644
--- a/kernel/bpf/cpumask.c
+++ b/kernel/bpf/cpumask.c
@@ -96,6 +96,12 @@ __bpf_kfunc void bpf_cpumask_release(struct bpf_cpumask *cpumask)
 	migrate_enable();
 }
 
+__bpf_kfunc void bpf_cpumask_release_dtor(void *cpumask)
+{
+	bpf_cpumask_release(cpumask);
+}
+CFI_NOSEAL(bpf_cpumask_release_dtor);
+
 /**
  * bpf_cpumask_first() - Get the index of the first nonzero bit in the cpumask.
  * @cpumask: The cpumask being queried.
@@ -405,6 +411,17 @@ __bpf_kfunc u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1,
 	return cpumask_any_and_distribute(src1, src2);
 }
 
+/**
+ * bpf_cpumask_weight() - Return the number of bits in @cpumask.
+ * @cpumask: The cpumask being queried.
+ *
+ * Count the number of set bits in the given cpumask.
+ */
+__bpf_kfunc u32 bpf_cpumask_weight(const struct cpumask *cpumask)
+{
+	return cpumask_weight(cpumask);
+}
+
 __bpf_kfunc_end_defs();
 
 BTF_SET8_START(cpumask_kfunc_btf_ids)
@@ -432,6 +449,7 @@ BTF_ID_FLAGS(func, bpf_cpumask_full, KF_RCU)
 BTF_ID_FLAGS(func, bpf_cpumask_copy, KF_RCU)
 BTF_ID_FLAGS(func, bpf_cpumask_any_distribute, KF_RCU)
 BTF_ID_FLAGS(func, bpf_cpumask_any_and_distribute, KF_RCU)
+BTF_ID_FLAGS(func, bpf_cpumask_weight, KF_RCU)
 BTF_SET8_END(cpumask_kfunc_btf_ids)
 
 static const struct btf_kfunc_id_set cpumask_kfunc_set = {
@@ -441,7 +459,7 @@ static const struct btf_kfunc_id_set cpumask_kfunc_set = {
 
 BTF_ID_LIST(cpumask_dtor_ids)
 BTF_ID(struct, bpf_cpumask)
-BTF_ID(func, bpf_cpumask_release)
+BTF_ID(func, bpf_cpumask_release_dtor)
 
 static int __init cpumask_kfunc_init(void)
 {
diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c
index fa3e9225aedc..70fb82bf1637 100644
--- a/kernel/bpf/dispatcher.c
+++ b/kernel/bpf/dispatcher.c
@@ -150,14 +150,11 @@ void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,
 			goto out;
 		d->rw_image = bpf_jit_alloc_exec(PAGE_SIZE);
 		if (!d->rw_image) {
-			u32 size = PAGE_SIZE;
-
-			bpf_arch_text_copy(d->image, &size, sizeof(size));
-			bpf_prog_pack_free((struct bpf_binary_header *)d->image);
+			bpf_prog_pack_free(d->image, PAGE_SIZE);
 			d->image = NULL;
 			goto out;
 		}
-		bpf_image_ksym_add(d->image, &d->ksym);
+		bpf_image_ksym_add(d->image, PAGE_SIZE, &d->ksym);
 	}
 
 	prev_num_progs = d->num_progs;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index fd8d4b0addfc..03a6a2500b6a 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -7,6 +7,7 @@
 #include <linux/jhash.h>
 #include <linux/filter.h>
 #include <linux/rculist_nulls.h>
+#include <linux/rcupdate_wait.h>
 #include <linux/random.h>
 #include <uapi/linux/btf.h>
 #include <linux/rcupdate_trace.h>
@@ -897,7 +898,7 @@ static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l)
 
 	if (map->ops->map_fd_put_ptr) {
 		ptr = fd_htab_map_get_ptr(map, l);
-		map->ops->map_fd_put_ptr(ptr);
+		map->ops->map_fd_put_ptr(map, ptr, true);
 	}
 }
 
@@ -2484,7 +2485,7 @@ static void fd_htab_map_free(struct bpf_map *map)
 		hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
 			void *ptr = fd_htab_map_get_ptr(map, l);
 
-			map->ops->map_fd_put_ptr(ptr);
+			map->ops->map_fd_put_ptr(map, ptr, false);
 		}
 	}
 
@@ -2523,9 +2524,15 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
 	if (IS_ERR(ptr))
 		return PTR_ERR(ptr);
 
+	/* The htab bucket lock is always held during update operations in fd
+	 * htab map, and the following rcu_read_lock() is only used to avoid
+	 * the WARN_ON_ONCE in htab_map_update_elem().
+	 */
+	rcu_read_lock();
 	ret = htab_map_update_elem(map, key, &ptr, map_flags);
+	rcu_read_unlock();
 	if (ret)
-		map->ops->map_fd_put_ptr(ptr);
+		map->ops->map_fd_put_ptr(map, ptr, false);
 
 	return ret;
 }
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 56b0c1f678ee..be72824f32b2 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -32,12 +32,13 @@
  *
  * Different map implementations will rely on rcu in map methods
  * lookup/update/delete, therefore eBPF programs must run under rcu lock
- * if program is allowed to access maps, so check rcu_read_lock_held in
- * all three functions.
+ * if program is allowed to access maps, so check rcu_read_lock_held() or
+ * rcu_read_lock_trace_held() in all three functions.
  */
 BPF_CALL_2(bpf_map_lookup_elem, struct bpf_map *, map, void *, key)
 {
-	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+		     !rcu_read_lock_bh_held());
 	return (unsigned long) map->ops->map_lookup_elem(map, key);
 }
 
@@ -53,7 +54,8 @@ const struct bpf_func_proto bpf_map_lookup_elem_proto = {
 BPF_CALL_4(bpf_map_update_elem, struct bpf_map *, map, void *, key,
 	   void *, value, u64, flags)
 {
-	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+		     !rcu_read_lock_bh_held());
 	return map->ops->map_update_elem(map, key, value, flags);
 }
 
@@ -70,7 +72,8 @@ const struct bpf_func_proto bpf_map_update_elem_proto = {
 
 BPF_CALL_2(bpf_map_delete_elem, struct bpf_map *, map, void *, key)
 {
-	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+		     !rcu_read_lock_bh_held());
 	return map->ops->map_delete_elem(map, key);
 }
 
@@ -1937,10 +1940,7 @@ void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu)
 		ma = &bpf_global_percpu_ma;
 	else
 		ma = &bpf_global_ma;
-	if (rec && rec->refcount_off >= 0)
-		bpf_mem_free_rcu(ma, p);
-	else
-		bpf_mem_free(ma, p);
+	bpf_mem_free_rcu(ma, p);
 }
 
 __bpf_kfunc void bpf_obj_drop_impl(void *p__alloc, void *meta__ign)
@@ -2150,6 +2150,12 @@ __bpf_kfunc void bpf_task_release(struct task_struct *p)
 	put_task_struct_rcu_user(p);
 }
 
+__bpf_kfunc void bpf_task_release_dtor(void *p)
+{
+	put_task_struct_rcu_user(p);
+}
+CFI_NOSEAL(bpf_task_release_dtor);
+
 #ifdef CONFIG_CGROUPS
 /**
  * bpf_cgroup_acquire - Acquire a reference to a cgroup. A cgroup acquired by
@@ -2174,6 +2180,12 @@ __bpf_kfunc void bpf_cgroup_release(struct cgroup *cgrp)
 	cgroup_put(cgrp);
 }
 
+__bpf_kfunc void bpf_cgroup_release_dtor(void *cgrp)
+{
+	cgroup_put(cgrp);
+}
+CFI_NOSEAL(bpf_cgroup_release_dtor);
+
 /**
  * bpf_cgroup_ancestor - Perform a lookup on an entry in a cgroup's ancestor
  * array. A cgroup returned by this kfunc which is not subsequently stored in a
@@ -2231,6 +2243,25 @@ __bpf_kfunc long bpf_task_under_cgroup(struct task_struct *task,
 	rcu_read_unlock();
 	return ret;
 }
+
+/**
+ * bpf_task_get_cgroup1 - Acquires the associated cgroup of a task within a
+ * specific cgroup1 hierarchy. The cgroup1 hierarchy is identified by its
+ * hierarchy ID.
+ * @task: The target task
+ * @hierarchy_id: The ID of a cgroup1 hierarchy
+ *
+ * On success, the cgroup is returen. On failure, NULL is returned.
+ */
+__bpf_kfunc struct cgroup *
+bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id)
+{
+	struct cgroup *cgrp = task_get_cgroup1(task, hierarchy_id);
+
+	if (IS_ERR(cgrp))
+		return NULL;
+	return cgrp;
+}
 #endif /* CONFIG_CGROUPS */
 
 /**
@@ -2506,7 +2537,7 @@ __bpf_kfunc void bpf_throw(u64 cookie)
 	 * which skips compiler generated instrumentation to do the same.
 	 */
 	kasan_unpoison_task_stack_below((void *)(long)ctx.sp);
-	ctx.aux->bpf_exception_cb(cookie, ctx.sp, ctx.bp);
+	ctx.aux->bpf_exception_cb(cookie, ctx.sp, ctx.bp, 0, 0);
 	WARN(1, "A call to BPF exception callback should never return\n");
 }
 
@@ -2520,7 +2551,7 @@ BTF_ID_FLAGS(func, bpf_obj_new_impl, KF_ACQUIRE | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_percpu_obj_new_impl, KF_ACQUIRE | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_obj_drop_impl, KF_RELEASE)
 BTF_ID_FLAGS(func, bpf_percpu_obj_drop_impl, KF_RELEASE)
-BTF_ID_FLAGS(func, bpf_refcount_acquire_impl, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_refcount_acquire_impl, KF_ACQUIRE | KF_RET_NULL | KF_RCU)
 BTF_ID_FLAGS(func, bpf_list_push_front_impl)
 BTF_ID_FLAGS(func, bpf_list_push_back_impl)
 BTF_ID_FLAGS(func, bpf_list_pop_front, KF_ACQUIRE | KF_RET_NULL)
@@ -2537,6 +2568,7 @@ BTF_ID_FLAGS(func, bpf_cgroup_release, KF_RELEASE)
 BTF_ID_FLAGS(func, bpf_cgroup_ancestor, KF_ACQUIRE | KF_RCU | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_cgroup_from_id, KF_ACQUIRE | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_task_under_cgroup, KF_RCU)
+BTF_ID_FLAGS(func, bpf_task_get_cgroup1, KF_ACQUIRE | KF_RCU | KF_RET_NULL)
 #endif
 BTF_ID_FLAGS(func, bpf_task_from_pid, KF_ACQUIRE | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_throw)
@@ -2550,10 +2582,10 @@ static const struct btf_kfunc_id_set generic_kfunc_set = {
 
 BTF_ID_LIST(generic_dtor_ids)
 BTF_ID(struct, task_struct)
-BTF_ID(func, bpf_task_release)
+BTF_ID(func, bpf_task_release_dtor)
 #ifdef CONFIG_CGROUPS
 BTF_ID(struct, cgroup)
-BTF_ID(func, bpf_cgroup_release)
+BTF_ID(func, bpf_cgroup_release_dtor)
 #endif
 
 BTF_SET8_START(common_btf_ids)
@@ -2610,6 +2642,7 @@ static int __init kfunc_init(void)
 
 	ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &generic_kfunc_set);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &generic_kfunc_set);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &generic_kfunc_set);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &generic_kfunc_set);
 	ret = ret ?: register_btf_id_dtor_kfuncs(generic_dtors,
 						  ARRAY_SIZE(generic_dtors),
@@ -2618,3 +2651,22 @@ static int __init kfunc_init(void)
 }
 
 late_initcall(kfunc_init);
+
+/* Get a pointer to dynptr data up to len bytes for read only access. If
+ * the dynptr doesn't have continuous data up to len bytes, return NULL.
+ */
+const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u32 len)
+{
+	return bpf_dynptr_slice(ptr, 0, NULL, len);
+}
+
+/* Get a pointer to dynptr data up to len bytes for read write access. If
+ * the dynptr doesn't have continuous data up to len bytes, or the dynptr
+ * is read only, return NULL.
+ */
+void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u32 len)
+{
+	if (__bpf_dynptr_is_rdonly(ptr))
+		return NULL;
+	return (void *)__bpf_dynptr_data(ptr, len);
+}
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 1aafb2ff2e95..41e0a55c35f5 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -599,8 +599,15 @@ EXPORT_SYMBOL(bpf_prog_get_type_path);
  */
 static int bpf_show_options(struct seq_file *m, struct dentry *root)
 {
-	umode_t mode = d_inode(root)->i_mode & S_IALLUGO & ~S_ISVTX;
-
+	struct inode *inode = d_inode(root);
+	umode_t mode = inode->i_mode & S_IALLUGO & ~S_ISVTX;
+
+	if (!uid_eq(inode->i_uid, GLOBAL_ROOT_UID))
+		seq_printf(m, ",uid=%u",
+			   from_kuid_munged(&init_user_ns, inode->i_uid));
+	if (!gid_eq(inode->i_gid, GLOBAL_ROOT_GID))
+		seq_printf(m, ",gid=%u",
+			   from_kgid_munged(&init_user_ns, inode->i_gid));
 	if (mode != S_IRWXUGO)
 		seq_printf(m, ",mode=%o", mode);
 	return 0;
@@ -625,15 +632,21 @@ static const struct super_operations bpf_super_ops = {
 };
 
 enum {
+	OPT_UID,
+	OPT_GID,
 	OPT_MODE,
 };
 
 static const struct fs_parameter_spec bpf_fs_parameters[] = {
+	fsparam_u32	("uid",				OPT_UID),
+	fsparam_u32	("gid",				OPT_GID),
 	fsparam_u32oct	("mode",			OPT_MODE),
 	{}
 };
 
 struct bpf_mount_opts {
+	kuid_t uid;
+	kgid_t gid;
 	umode_t mode;
 };
 
@@ -641,6 +654,8 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param)
 {
 	struct bpf_mount_opts *opts = fc->fs_private;
 	struct fs_parse_result result;
+	kuid_t uid;
+	kgid_t gid;
 	int opt;
 
 	opt = fs_parse(fc, bpf_fs_parameters, param, &result);
@@ -662,12 +677,42 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	}
 
 	switch (opt) {
+	case OPT_UID:
+		uid = make_kuid(current_user_ns(), result.uint_32);
+		if (!uid_valid(uid))
+			goto bad_value;
+
+		/*
+		 * The requested uid must be representable in the
+		 * filesystem's idmapping.
+		 */
+		if (!kuid_has_mapping(fc->user_ns, uid))
+			goto bad_value;
+
+		opts->uid = uid;
+		break;
+	case OPT_GID:
+		gid = make_kgid(current_user_ns(), result.uint_32);
+		if (!gid_valid(gid))
+			goto bad_value;
+
+		/*
+		 * The requested gid must be representable in the
+		 * filesystem's idmapping.
+		 */
+		if (!kgid_has_mapping(fc->user_ns, gid))
+			goto bad_value;
+
+		opts->gid = gid;
+		break;
 	case OPT_MODE:
 		opts->mode = result.uint_32 & S_IALLUGO;
 		break;
 	}
 
 	return 0;
+bad_value:
+	return invalfc(fc, "Bad value for '%s'", param->key);
 }
 
 struct bpf_preload_ops *bpf_preload_ops;
@@ -750,6 +795,8 @@ static int bpf_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_op = &bpf_super_ops;
 
 	inode = sb->s_root->d_inode;
+	inode->i_uid = opts->uid;
+	inode->i_gid = opts->gid;
 	inode->i_op = &bpf_dir_iops;
 	inode->i_mode &= ~S_IALLUGO;
 	populate_bpffs(sb->s_root);
@@ -785,6 +832,8 @@ static int bpf_init_fs_context(struct fs_context *fc)
 		return -ENOMEM;
 
 	opts->mode = S_IRWXUGO;
+	opts->uid = current_fsuid();
+	opts->gid = current_fsgid();
 
 	fc->fs_private = opts;
 	fc->ops = &bpf_context_ops;
diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c
index 850494423530..594a234f122b 100644
--- a/kernel/bpf/log.c
+++ b/kernel/bpf/log.c
@@ -10,6 +10,8 @@
 #include <linux/bpf_verifier.h>
 #include <linux/math64.h>
 
+#define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args)
+
 static bool bpf_verifier_log_attr_valid(const struct bpf_verifier_log *log)
 {
 	/* ubuf and len_total should both be specified (or not) together */
@@ -325,3 +327,505 @@ __printf(2, 3) void bpf_log(struct bpf_verifier_log *log,
 	va_end(args);
 }
 EXPORT_SYMBOL_GPL(bpf_log);
+
+static const struct bpf_line_info *
+find_linfo(const struct bpf_verifier_env *env, u32 insn_off)
+{
+	const struct bpf_line_info *linfo;
+	const struct bpf_prog *prog;
+	u32 i, nr_linfo;
+
+	prog = env->prog;
+	nr_linfo = prog->aux->nr_linfo;
+
+	if (!nr_linfo || insn_off >= prog->len)
+		return NULL;
+
+	linfo = prog->aux->linfo;
+	for (i = 1; i < nr_linfo; i++)
+		if (insn_off < linfo[i].insn_off)
+			break;
+
+	return &linfo[i - 1];
+}
+
+static const char *ltrim(const char *s)
+{
+	while (isspace(*s))
+		s++;
+
+	return s;
+}
+
+__printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env,
+				  u32 insn_off,
+				  const char *prefix_fmt, ...)
+{
+	const struct bpf_line_info *linfo;
+
+	if (!bpf_verifier_log_needed(&env->log))
+		return;
+
+	linfo = find_linfo(env, insn_off);
+	if (!linfo || linfo == env->prev_linfo)
+		return;
+
+	if (prefix_fmt) {
+		va_list args;
+
+		va_start(args, prefix_fmt);
+		bpf_verifier_vlog(&env->log, prefix_fmt, args);
+		va_end(args);
+	}
+
+	verbose(env, "%s\n",
+		ltrim(btf_name_by_offset(env->prog->aux->btf,
+					 linfo->line_off)));
+
+	env->prev_linfo = linfo;
+}
+
+static const char *btf_type_name(const struct btf *btf, u32 id)
+{
+	return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off);
+}
+
+/* string representation of 'enum bpf_reg_type'
+ *
+ * Note that reg_type_str() can not appear more than once in a single verbose()
+ * statement.
+ */
+const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type)
+{
+	char postfix[16] = {0}, prefix[64] = {0};
+	static const char * const str[] = {
+		[NOT_INIT]		= "?",
+		[SCALAR_VALUE]		= "scalar",
+		[PTR_TO_CTX]		= "ctx",
+		[CONST_PTR_TO_MAP]	= "map_ptr",
+		[PTR_TO_MAP_VALUE]	= "map_value",
+		[PTR_TO_STACK]		= "fp",
+		[PTR_TO_PACKET]		= "pkt",
+		[PTR_TO_PACKET_META]	= "pkt_meta",
+		[PTR_TO_PACKET_END]	= "pkt_end",
+		[PTR_TO_FLOW_KEYS]	= "flow_keys",
+		[PTR_TO_SOCKET]		= "sock",
+		[PTR_TO_SOCK_COMMON]	= "sock_common",
+		[PTR_TO_TCP_SOCK]	= "tcp_sock",
+		[PTR_TO_TP_BUFFER]	= "tp_buffer",
+		[PTR_TO_XDP_SOCK]	= "xdp_sock",
+		[PTR_TO_BTF_ID]		= "ptr_",
+		[PTR_TO_MEM]		= "mem",
+		[PTR_TO_BUF]		= "buf",
+		[PTR_TO_FUNC]		= "func",
+		[PTR_TO_MAP_KEY]	= "map_key",
+		[CONST_PTR_TO_DYNPTR]	= "dynptr_ptr",
+	};
+
+	if (type & PTR_MAYBE_NULL) {
+		if (base_type(type) == PTR_TO_BTF_ID)
+			strncpy(postfix, "or_null_", 16);
+		else
+			strncpy(postfix, "_or_null", 16);
+	}
+
+	snprintf(prefix, sizeof(prefix), "%s%s%s%s%s%s%s",
+		 type & MEM_RDONLY ? "rdonly_" : "",
+		 type & MEM_RINGBUF ? "ringbuf_" : "",
+		 type & MEM_USER ? "user_" : "",
+		 type & MEM_PERCPU ? "percpu_" : "",
+		 type & MEM_RCU ? "rcu_" : "",
+		 type & PTR_UNTRUSTED ? "untrusted_" : "",
+		 type & PTR_TRUSTED ? "trusted_" : ""
+	);
+
+	snprintf(env->tmp_str_buf, TMP_STR_BUF_LEN, "%s%s%s",
+		 prefix, str[base_type(type)], postfix);
+	return env->tmp_str_buf;
+}
+
+const char *dynptr_type_str(enum bpf_dynptr_type type)
+{
+	switch (type) {
+	case BPF_DYNPTR_TYPE_LOCAL:
+		return "local";
+	case BPF_DYNPTR_TYPE_RINGBUF:
+		return "ringbuf";
+	case BPF_DYNPTR_TYPE_SKB:
+		return "skb";
+	case BPF_DYNPTR_TYPE_XDP:
+		return "xdp";
+	case BPF_DYNPTR_TYPE_INVALID:
+		return "<invalid>";
+	default:
+		WARN_ONCE(1, "unknown dynptr type %d\n", type);
+		return "<unknown>";
+	}
+}
+
+const char *iter_type_str(const struct btf *btf, u32 btf_id)
+{
+	if (!btf || btf_id == 0)
+		return "<invalid>";
+
+	/* we already validated that type is valid and has conforming name */
+	return btf_type_name(btf, btf_id) + sizeof(ITER_PREFIX) - 1;
+}
+
+const char *iter_state_str(enum bpf_iter_state state)
+{
+	switch (state) {
+	case BPF_ITER_STATE_ACTIVE:
+		return "active";
+	case BPF_ITER_STATE_DRAINED:
+		return "drained";
+	case BPF_ITER_STATE_INVALID:
+		return "<invalid>";
+	default:
+		WARN_ONCE(1, "unknown iter state %d\n", state);
+		return "<unknown>";
+	}
+}
+
+static char slot_type_char[] = {
+	[STACK_INVALID]	= '?',
+	[STACK_SPILL]	= 'r',
+	[STACK_MISC]	= 'm',
+	[STACK_ZERO]	= '0',
+	[STACK_DYNPTR]	= 'd',
+	[STACK_ITER]	= 'i',
+};
+
+static void print_liveness(struct bpf_verifier_env *env,
+			   enum bpf_reg_liveness live)
+{
+	if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE))
+	    verbose(env, "_");
+	if (live & REG_LIVE_READ)
+		verbose(env, "r");
+	if (live & REG_LIVE_WRITTEN)
+		verbose(env, "w");
+	if (live & REG_LIVE_DONE)
+		verbose(env, "D");
+}
+
+#define UNUM_MAX_DECIMAL U16_MAX
+#define SNUM_MAX_DECIMAL S16_MAX
+#define SNUM_MIN_DECIMAL S16_MIN
+
+static bool is_unum_decimal(u64 num)
+{
+	return num <= UNUM_MAX_DECIMAL;
+}
+
+static bool is_snum_decimal(s64 num)
+{
+	return num >= SNUM_MIN_DECIMAL && num <= SNUM_MAX_DECIMAL;
+}
+
+static void verbose_unum(struct bpf_verifier_env *env, u64 num)
+{
+	if (is_unum_decimal(num))
+		verbose(env, "%llu", num);
+	else
+		verbose(env, "%#llx", num);
+}
+
+static void verbose_snum(struct bpf_verifier_env *env, s64 num)
+{
+	if (is_snum_decimal(num))
+		verbose(env, "%lld", num);
+	else
+		verbose(env, "%#llx", num);
+}
+
+int tnum_strn(char *str, size_t size, struct tnum a)
+{
+	/* print as a constant, if tnum is fully known */
+	if (a.mask == 0) {
+		if (is_unum_decimal(a.value))
+			return snprintf(str, size, "%llu", a.value);
+		else
+			return snprintf(str, size, "%#llx", a.value);
+	}
+	return snprintf(str, size, "(%#llx; %#llx)", a.value, a.mask);
+}
+EXPORT_SYMBOL_GPL(tnum_strn);
+
+static void print_scalar_ranges(struct bpf_verifier_env *env,
+				const struct bpf_reg_state *reg,
+				const char **sep)
+{
+	/* For signed ranges, we want to unify 64-bit and 32-bit values in the
+	 * output as much as possible, but there is a bit of a complication.
+	 * If we choose to print values as decimals, this is natural to do,
+	 * because negative 64-bit and 32-bit values >= -S32_MIN have the same
+	 * representation due to sign extension. But if we choose to print
+	 * them in hex format (see is_snum_decimal()), then sign extension is
+	 * misleading.
+	 * E.g., smin=-2 and smin32=-2 are exactly the same in decimal, but in
+	 * hex they will be smin=0xfffffffffffffffe and smin32=0xfffffffe, two
+	 * very different numbers.
+	 * So we avoid sign extension if we choose to print values in hex.
+	 */
+	struct {
+		const char *name;
+		u64 val;
+		bool omit;
+	} minmaxs[] = {
+		{"smin",   reg->smin_value,         reg->smin_value == S64_MIN},
+		{"smax",   reg->smax_value,         reg->smax_value == S64_MAX},
+		{"umin",   reg->umin_value,         reg->umin_value == 0},
+		{"umax",   reg->umax_value,         reg->umax_value == U64_MAX},
+		{"smin32",
+		 is_snum_decimal((s64)reg->s32_min_value)
+			 ? (s64)reg->s32_min_value
+			 : (u32)reg->s32_min_value, reg->s32_min_value == S32_MIN},
+		{"smax32",
+		 is_snum_decimal((s64)reg->s32_max_value)
+			 ? (s64)reg->s32_max_value
+			 : (u32)reg->s32_max_value, reg->s32_max_value == S32_MAX},
+		{"umin32", reg->u32_min_value,      reg->u32_min_value == 0},
+		{"umax32", reg->u32_max_value,      reg->u32_max_value == U32_MAX},
+	}, *m1, *m2, *mend = &minmaxs[ARRAY_SIZE(minmaxs)];
+	bool neg1, neg2;
+
+	for (m1 = &minmaxs[0]; m1 < mend; m1++) {
+		if (m1->omit)
+			continue;
+
+		neg1 = m1->name[0] == 's' && (s64)m1->val < 0;
+
+		verbose(env, "%s%s=", *sep, m1->name);
+		*sep = ",";
+
+		for (m2 = m1 + 2; m2 < mend; m2 += 2) {
+			if (m2->omit || m2->val != m1->val)
+				continue;
+			/* don't mix negatives with positives */
+			neg2 = m2->name[0] == 's' && (s64)m2->val < 0;
+			if (neg2 != neg1)
+				continue;
+			m2->omit = true;
+			verbose(env, "%s=", m2->name);
+		}
+
+		if (m1->name[0] == 's')
+			verbose_snum(env, m1->val);
+		else
+			verbose_unum(env, m1->val);
+	}
+}
+
+static bool type_is_map_ptr(enum bpf_reg_type t) {
+	switch (base_type(t)) {
+	case CONST_PTR_TO_MAP:
+	case PTR_TO_MAP_KEY:
+	case PTR_TO_MAP_VALUE:
+		return true;
+	default:
+		return false;
+	}
+}
+
+/*
+ * _a stands for append, was shortened to avoid multiline statements below.
+ * This macro is used to output a comma separated list of attributes.
+ */
+#define verbose_a(fmt, ...) ({ verbose(env, "%s" fmt, sep, ##__VA_ARGS__); sep = ","; })
+
+static void print_reg_state(struct bpf_verifier_env *env,
+			    const struct bpf_func_state *state,
+			    const struct bpf_reg_state *reg)
+{
+	enum bpf_reg_type t;
+	const char *sep = "";
+
+	t = reg->type;
+	if (t == SCALAR_VALUE && reg->precise)
+		verbose(env, "P");
+	if (t == SCALAR_VALUE && tnum_is_const(reg->var_off)) {
+		/* reg->off should be 0 for SCALAR_VALUE */
+		verbose_snum(env, reg->var_off.value + reg->off);
+		return;
+	}
+
+	verbose(env, "%s", reg_type_str(env, t));
+	if (t == PTR_TO_STACK) {
+		if (state->frameno != reg->frameno)
+			verbose(env, "[%d]", reg->frameno);
+		if (tnum_is_const(reg->var_off)) {
+			verbose_snum(env, reg->var_off.value + reg->off);
+			return;
+		}
+	}
+	if (base_type(t) == PTR_TO_BTF_ID)
+		verbose(env, "%s", btf_type_name(reg->btf, reg->btf_id));
+	verbose(env, "(");
+	if (reg->id)
+		verbose_a("id=%d", reg->id);
+	if (reg->ref_obj_id)
+		verbose_a("ref_obj_id=%d", reg->ref_obj_id);
+	if (type_is_non_owning_ref(reg->type))
+		verbose_a("%s", "non_own_ref");
+	if (type_is_map_ptr(t)) {
+		if (reg->map_ptr->name[0])
+			verbose_a("map=%s", reg->map_ptr->name);
+		verbose_a("ks=%d,vs=%d",
+			  reg->map_ptr->key_size,
+			  reg->map_ptr->value_size);
+	}
+	if (t != SCALAR_VALUE && reg->off) {
+		verbose_a("off=");
+		verbose_snum(env, reg->off);
+	}
+	if (type_is_pkt_pointer(t)) {
+		verbose_a("r=");
+		verbose_unum(env, reg->range);
+	}
+	if (base_type(t) == PTR_TO_MEM) {
+		verbose_a("sz=");
+		verbose_unum(env, reg->mem_size);
+	}
+	if (t == CONST_PTR_TO_DYNPTR)
+		verbose_a("type=%s",  dynptr_type_str(reg->dynptr.type));
+	if (tnum_is_const(reg->var_off)) {
+		/* a pointer register with fixed offset */
+		if (reg->var_off.value) {
+			verbose_a("imm=");
+			verbose_snum(env, reg->var_off.value);
+		}
+	} else {
+		print_scalar_ranges(env, reg, &sep);
+		if (!tnum_is_unknown(reg->var_off)) {
+			char tn_buf[48];
+
+			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+			verbose_a("var_off=%s", tn_buf);
+		}
+	}
+	verbose(env, ")");
+}
+
+void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_state *state,
+			  bool print_all)
+{
+	const struct bpf_reg_state *reg;
+	int i;
+
+	if (state->frameno)
+		verbose(env, " frame%d:", state->frameno);
+	for (i = 0; i < MAX_BPF_REG; i++) {
+		reg = &state->regs[i];
+		if (reg->type == NOT_INIT)
+			continue;
+		if (!print_all && !reg_scratched(env, i))
+			continue;
+		verbose(env, " R%d", i);
+		print_liveness(env, reg->live);
+		verbose(env, "=");
+		print_reg_state(env, state, reg);
+	}
+	for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
+		char types_buf[BPF_REG_SIZE + 1];
+		const char *sep = "";
+		bool valid = false;
+		u8 slot_type;
+		int j;
+
+		if (!print_all && !stack_slot_scratched(env, i))
+			continue;
+
+		for (j = 0; j < BPF_REG_SIZE; j++) {
+			slot_type = state->stack[i].slot_type[j];
+			if (slot_type != STACK_INVALID)
+				valid = true;
+			types_buf[j] = slot_type_char[slot_type];
+		}
+		types_buf[BPF_REG_SIZE] = 0;
+		if (!valid)
+			continue;
+
+		reg = &state->stack[i].spilled_ptr;
+		switch (state->stack[i].slot_type[BPF_REG_SIZE - 1]) {
+		case STACK_SPILL:
+			/* print MISC/ZERO/INVALID slots above subreg spill */
+			for (j = 0; j < BPF_REG_SIZE; j++)
+				if (state->stack[i].slot_type[j] == STACK_SPILL)
+					break;
+			types_buf[j] = '\0';
+
+			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
+			print_liveness(env, reg->live);
+			verbose(env, "=%s", types_buf);
+			print_reg_state(env, state, reg);
+			break;
+		case STACK_DYNPTR:
+			/* skip to main dynptr slot */
+			i += BPF_DYNPTR_NR_SLOTS - 1;
+			reg = &state->stack[i].spilled_ptr;
+
+			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
+			print_liveness(env, reg->live);
+			verbose(env, "=dynptr_%s(", dynptr_type_str(reg->dynptr.type));
+			if (reg->id)
+				verbose_a("id=%d", reg->id);
+			if (reg->ref_obj_id)
+				verbose_a("ref_id=%d", reg->ref_obj_id);
+			if (reg->dynptr_id)
+				verbose_a("dynptr_id=%d", reg->dynptr_id);
+			verbose(env, ")");
+			break;
+		case STACK_ITER:
+			/* only main slot has ref_obj_id set; skip others */
+			if (!reg->ref_obj_id)
+				continue;
+
+			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
+			print_liveness(env, reg->live);
+			verbose(env, "=iter_%s(ref_id=%d,state=%s,depth=%u)",
+				iter_type_str(reg->iter.btf, reg->iter.btf_id),
+				reg->ref_obj_id, iter_state_str(reg->iter.state),
+				reg->iter.depth);
+			break;
+		case STACK_MISC:
+		case STACK_ZERO:
+		default:
+			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
+			print_liveness(env, reg->live);
+			verbose(env, "=%s", types_buf);
+			break;
+		}
+	}
+	if (state->acquired_refs && state->refs[0].id) {
+		verbose(env, " refs=%d", state->refs[0].id);
+		for (i = 1; i < state->acquired_refs; i++)
+			if (state->refs[i].id)
+				verbose(env, ",%d", state->refs[i].id);
+	}
+	if (state->in_callback_fn)
+		verbose(env, " cb");
+	if (state->in_async_callback_fn)
+		verbose(env, " async_cb");
+	verbose(env, "\n");
+	if (!print_all)
+		mark_verifier_state_clean(env);
+}
+
+static inline u32 vlog_alignment(u32 pos)
+{
+	return round_up(max(pos + BPF_LOG_MIN_ALIGNMENT / 2, BPF_LOG_ALIGNMENT),
+			BPF_LOG_MIN_ALIGNMENT) - pos - 1;
+}
+
+void print_insn_state(struct bpf_verifier_env *env, const struct bpf_func_state *state)
+{
+	if (env->prev_log_pos && env->prev_log_pos == env->log.end_pos) {
+		/* remove new line character */
+		bpf_vlog_reset(&env->log, env->prev_log_pos - 1);
+		verbose(env, "%*c;", vlog_alignment(env->prev_insn_print_pos), ' ');
+	} else {
+		verbose(env, "%d:", env->insn_idx);
+	}
+	print_verifier_state(env, state, false);
+}
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 17c7e7782a1f..b32be680da6c 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -231,6 +231,9 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key)
 	struct lpm_trie_node *node, *found = NULL;
 	struct bpf_lpm_trie_key *key = _key;
 
+	if (key->prefixlen > trie->max_prefixlen)
+		return NULL;
+
 	/* Start walking the trie from the root node ... */
 
 	for (node = rcu_dereference_check(trie->root, rcu_read_lock_bh_held());
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index cd5eafaba97e..8ef269e66ba5 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -127,12 +127,21 @@ void *bpf_map_fd_get_ptr(struct bpf_map *map,
 	return inner_map;
 }
 
-void bpf_map_fd_put_ptr(void *ptr)
+void bpf_map_fd_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
 {
-	/* ptr->ops->map_free() has to go through one
-	 * rcu grace period by itself.
+	struct bpf_map *inner_map = ptr;
+
+	/* Defer the freeing of inner map according to the sleepable attribute
+	 * of bpf program which owns the outer map, so unnecessary waiting for
+	 * RCU tasks trace grace period can be avoided.
 	 */
-	bpf_map_put(ptr);
+	if (need_defer) {
+		if (atomic64_read(&map->sleepable_refcnt))
+			WRITE_ONCE(inner_map->free_after_mult_rcu_gp, true);
+		else
+			WRITE_ONCE(inner_map->free_after_rcu_gp, true);
+	}
+	bpf_map_put(inner_map);
 }
 
 u32 bpf_map_fd_sys_lookup_elem(void *ptr)
diff --git a/kernel/bpf/map_in_map.h b/kernel/bpf/map_in_map.h
index bcb7534afb3c..7d61602354de 100644
--- a/kernel/bpf/map_in_map.h
+++ b/kernel/bpf/map_in_map.h
@@ -13,7 +13,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd);
 void bpf_map_meta_free(struct bpf_map *map_meta);
 void *bpf_map_fd_get_ptr(struct bpf_map *map, struct file *map_file,
 			 int ufd);
-void bpf_map_fd_put_ptr(void *ptr);
+void bpf_map_fd_put_ptr(struct bpf_map *map, void *ptr, bool need_defer);
 u32 bpf_map_fd_sys_lookup_elem(void *ptr);
 
 #endif
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 63b909d277d4..550f02e2cb13 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -121,6 +121,8 @@ struct bpf_mem_caches {
 	struct bpf_mem_cache cache[NUM_CACHES];
 };
 
+static const u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096};
+
 static struct llist_node notrace *__llist_del_first(struct llist_head *head)
 {
 	struct llist_node *entry, *next;
@@ -462,11 +464,17 @@ static void notrace irq_work_raise(struct bpf_mem_cache *c)
  * consume ~ 11 Kbyte per cpu.
  * Typical case will be between 11K and 116K closer to 11K.
  * bpf progs can and should share bpf_mem_cache when possible.
+ *
+ * Percpu allocation is typically rare. To avoid potential unnecessary large
+ * memory consumption, set low_mark = 1 and high_mark = 3, resulting in c->batch = 1.
  */
 static void init_refill_work(struct bpf_mem_cache *c)
 {
 	init_irq_work(&c->refill_work, bpf_mem_refill);
-	if (c->unit_size <= 256) {
+	if (c->percpu_size) {
+		c->low_watermark = 1;
+		c->high_watermark = 3;
+	} else if (c->unit_size <= 256) {
 		c->low_watermark = 32;
 		c->high_watermark = 96;
 	} else {
@@ -483,32 +491,16 @@ static void init_refill_work(struct bpf_mem_cache *c)
 
 static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
 {
-	/* To avoid consuming memory assume that 1st run of bpf
-	 * prog won't be doing more than 4 map_update_elem from
-	 * irq disabled region
-	 */
-	alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu), false);
-}
-
-static int check_obj_size(struct bpf_mem_cache *c, unsigned int idx)
-{
-	struct llist_node *first;
-	unsigned int obj_size;
+	int cnt = 1;
 
-	first = c->free_llist.first;
-	if (!first)
-		return 0;
-
-	if (c->percpu_size)
-		obj_size = pcpu_alloc_size(((void **)first)[1]);
-	else
-		obj_size = ksize(first);
-	if (obj_size != c->unit_size) {
-		WARN_ONCE(1, "bpf_mem_cache[%u]: percpu %d, unexpected object size %u, expect %u\n",
-			  idx, c->percpu_size, obj_size, c->unit_size);
-		return -EINVAL;
-	}
-	return 0;
+	/* To avoid consuming memory, for non-percpu allocation, assume that
+	 * 1st run of bpf prog won't be doing more than 4 map_update_elem from
+	 * irq disabled region if unit size is less than or equal to 256.
+	 * For all other cases, let us just do one allocation.
+	 */
+	if (!c->percpu_size && c->unit_size <= 256)
+		cnt = 4;
+	alloc_bulk(c, cnt, cpu_to_node(cpu), false);
 }
 
 /* When size != 0 bpf_mem_cache for each cpu.
@@ -520,11 +512,13 @@ static int check_obj_size(struct bpf_mem_cache *c, unsigned int idx)
  */
 int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 {
-	static u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096};
-	int cpu, i, err, unit_size, percpu_size = 0;
 	struct bpf_mem_caches *cc, __percpu *pcc;
 	struct bpf_mem_cache *c, __percpu *pc;
 	struct obj_cgroup *objcg = NULL;
+	int cpu, i, unit_size, percpu_size = 0;
+
+	if (percpu && size == 0)
+		return -EINVAL;
 
 	/* room for llist_node and per-cpu pointer */
 	if (percpu)
@@ -544,6 +538,8 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 		if (memcg_bpf_enabled())
 			objcg = get_obj_cgroup_from_current();
 #endif
+		ma->objcg = objcg;
+
 		for_each_possible_cpu(cpu) {
 			c = per_cpu_ptr(pc, cpu);
 			c->unit_size = unit_size;
@@ -560,10 +556,10 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 	pcc = __alloc_percpu_gfp(sizeof(*cc), 8, GFP_KERNEL);
 	if (!pcc)
 		return -ENOMEM;
-	err = 0;
 #ifdef CONFIG_MEMCG_KMEM
 	objcg = get_obj_cgroup_from_current();
 #endif
+	ma->objcg = objcg;
 	for_each_possible_cpu(cpu) {
 		cc = per_cpu_ptr(pcc, cpu);
 		for (i = 0; i < NUM_CACHES; i++) {
@@ -574,28 +570,62 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 			c->tgt = c;
 
 			init_refill_work(c);
-			/* Another bpf_mem_cache will be used when allocating
-			 * c->unit_size in bpf_mem_alloc(), so doesn't prefill
-			 * for the bpf_mem_cache because these free objects will
-			 * never be used.
-			 */
-			if (i != bpf_mem_cache_idx(c->unit_size))
-				continue;
 			prefill_mem_cache(c, cpu);
-			err = check_obj_size(c, i);
-			if (err)
-				goto out;
 		}
 	}
 
-out:
 	ma->caches = pcc;
-	/* refill_work is either zeroed or initialized, so it is safe to
-	 * call irq_work_sync().
-	 */
-	if (err)
-		bpf_mem_alloc_destroy(ma);
-	return err;
+	return 0;
+}
+
+int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg)
+{
+	struct bpf_mem_caches __percpu *pcc;
+
+	pcc = __alloc_percpu_gfp(sizeof(struct bpf_mem_caches), 8, GFP_KERNEL);
+	if (!pcc)
+		return -ENOMEM;
+
+	ma->caches = pcc;
+	ma->objcg = objcg;
+	ma->percpu = true;
+	return 0;
+}
+
+int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size)
+{
+	struct bpf_mem_caches *cc, __percpu *pcc;
+	int cpu, i, unit_size, percpu_size;
+	struct obj_cgroup *objcg;
+	struct bpf_mem_cache *c;
+
+	i = bpf_mem_cache_idx(size);
+	if (i < 0)
+		return -EINVAL;
+
+	/* room for llist_node and per-cpu pointer */
+	percpu_size = LLIST_NODE_SZ + sizeof(void *);
+
+	unit_size = sizes[i];
+	objcg = ma->objcg;
+	pcc = ma->caches;
+
+	for_each_possible_cpu(cpu) {
+		cc = per_cpu_ptr(pcc, cpu);
+		c = &cc->cache[i];
+		if (c->unit_size)
+			break;
+
+		c->unit_size = unit_size;
+		c->objcg = objcg;
+		c->percpu_size = percpu_size;
+		c->tgt = c;
+
+		init_refill_work(c);
+		prefill_mem_cache(c, cpu);
+	}
+
+	return 0;
 }
 
 static void drain_mem_cache(struct bpf_mem_cache *c)
@@ -729,9 +759,8 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 			rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress);
 			rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
 		}
-		/* objcg is the same across cpus */
-		if (c->objcg)
-			obj_cgroup_put(c->objcg);
+		if (ma->objcg)
+			obj_cgroup_put(ma->objcg);
 		destroy_mem_alloc(ma, rcu_in_progress);
 	}
 	if (ma->caches) {
@@ -747,8 +776,8 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 				rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
 			}
 		}
-		if (c->objcg)
-			obj_cgroup_put(c->objcg);
+		if (ma->objcg)
+			obj_cgroup_put(ma->objcg);
 		destroy_mem_alloc(ma, rcu_in_progress);
 	}
 }
@@ -869,9 +898,11 @@ void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size)
 	void *ret;
 
 	if (!size)
-		return ZERO_SIZE_PTR;
+		return NULL;
 
-	idx = bpf_mem_cache_idx(size + LLIST_NODE_SZ);
+	if (!ma->percpu)
+		size += LLIST_NODE_SZ;
+	idx = bpf_mem_cache_idx(size);
 	if (idx < 0)
 		return NULL;
 
@@ -879,26 +910,17 @@ void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size)
 	return !ret ? NULL : ret + LLIST_NODE_SZ;
 }
 
-static notrace int bpf_mem_free_idx(void *ptr, bool percpu)
-{
-	size_t size;
-
-	if (percpu)
-		size = pcpu_alloc_size(*((void **)ptr));
-	else
-		size = ksize(ptr - LLIST_NODE_SZ);
-	return bpf_mem_cache_idx(size);
-}
-
 void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr)
 {
+	struct bpf_mem_cache *c;
 	int idx;
 
 	if (!ptr)
 		return;
 
-	idx = bpf_mem_free_idx(ptr, ma->percpu);
-	if (idx < 0)
+	c = *(void **)(ptr - LLIST_NODE_SZ);
+	idx = bpf_mem_cache_idx(c->unit_size);
+	if (WARN_ON_ONCE(idx < 0))
 		return;
 
 	unit_free(this_cpu_ptr(ma->caches)->cache + idx, ptr);
@@ -906,13 +928,15 @@ void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr)
 
 void notrace bpf_mem_free_rcu(struct bpf_mem_alloc *ma, void *ptr)
 {
+	struct bpf_mem_cache *c;
 	int idx;
 
 	if (!ptr)
 		return;
 
-	idx = bpf_mem_free_idx(ptr, ma->percpu);
-	if (idx < 0)
+	c = *(void **)(ptr - LLIST_NODE_SZ);
+	idx = bpf_mem_cache_idx(c->unit_size);
+	if (WARN_ON_ONCE(idx < 0))
 		return;
 
 	unit_free_rcu(this_cpu_ptr(ma->caches)->cache + idx, ptr);
@@ -978,47 +1002,11 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags)
 		memcg = get_memcg(c);
 		old_memcg = set_active_memcg(memcg);
 		ret = __alloc(c, NUMA_NO_NODE, GFP_KERNEL | __GFP_NOWARN | __GFP_ACCOUNT);
+		if (ret)
+			*(struct bpf_mem_cache **)ret = c;
 		set_active_memcg(old_memcg);
 		mem_cgroup_put(memcg);
 	}
 
 	return !ret ? NULL : ret + LLIST_NODE_SZ;
 }
-
-/* The alignment of dynamic per-cpu area is 8, so c->unit_size and the
- * actual size of dynamic per-cpu area will always be matched and there is
- * no need to adjust size_index for per-cpu allocation. However for the
- * simplicity of the implementation, use an unified size_index for both
- * kmalloc and per-cpu allocation.
- */
-static __init int bpf_mem_cache_adjust_size(void)
-{
-	unsigned int size;
-
-	/* Adjusting the indexes in size_index() according to the object_size
-	 * of underlying slab cache, so bpf_mem_alloc() will select a
-	 * bpf_mem_cache with unit_size equal to the object_size of
-	 * the underlying slab cache.
-	 *
-	 * The maximal value of KMALLOC_MIN_SIZE and __kmalloc_minalign() is
-	 * 256-bytes, so only do adjustment for [8-bytes, 192-bytes].
-	 */
-	for (size = 192; size >= 8; size -= 8) {
-		unsigned int kmalloc_size, index;
-
-		kmalloc_size = kmalloc_size_roundup(size);
-		if (kmalloc_size == size)
-			continue;
-
-		if (kmalloc_size <= 192)
-			index = size_index[(kmalloc_size - 1) / 8];
-		else
-			index = fls(kmalloc_size - 1) - 1;
-		/* Only overwrite if necessary */
-		if (size_index[(size - 1) / 8] != index)
-			size_index[(size - 1) / 8] = index;
-	}
-
-	return 0;
-}
-subsys_initcall(bpf_mem_cache_adjust_size);
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index d6b277482085..dff7ba539701 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -388,6 +388,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 {
 	u32 trace_nr, copy_len, elem_size, num_elem, max_depth;
 	bool user_build_id = flags & BPF_F_USER_BUILD_ID;
+	bool crosstask = task && task != current;
 	u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
 	bool user = flags & BPF_F_USER_STACK;
 	struct perf_callchain_entry *trace;
@@ -410,6 +411,14 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 	if (task && user && !user_mode(regs))
 		goto err_fault;
 
+	/* get_perf_callchain does not support crosstask user stack walking
+	 * but returns an empty stack instead of NULL.
+	 */
+	if (crosstask && user) {
+		err = -EOPNOTSUPP;
+		goto clear;
+	}
+
 	num_elem = size / elem_size;
 	max_depth = num_elem + skip;
 	if (sysctl_perf_event_max_stack < max_depth)
@@ -421,7 +430,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 		trace = get_callchain_entry_for_task(task, max_depth);
 	else
 		trace = get_perf_callchain(regs, 0, kernel, user, max_depth,
-					   false, false);
+					   crosstask, false);
 	if (unlikely(!trace))
 		goto err_fault;
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0ed286b8a0f0..a1f18681721c 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -142,9 +142,13 @@ static u32 bpf_map_value_size(const struct bpf_map *map)
 
 static void maybe_wait_bpf_programs(struct bpf_map *map)
 {
-	/* Wait for any running BPF programs to complete so that
-	 * userspace, when we return to it, knows that all programs
-	 * that could be running use the new map value.
+	/* Wait for any running non-sleepable BPF programs to complete so that
+	 * userspace, when we return to it, knows that all non-sleepable
+	 * programs that could be running use the new map value. For sleepable
+	 * BPF programs, synchronize_rcu_tasks_trace() should be used to wait
+	 * for the completions of these programs, but considering the waiting
+	 * time can be very long and userspace may think it will hang forever,
+	 * so don't handle sleepable BPF programs now.
 	 */
 	if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS ||
 	    map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)
@@ -180,15 +184,11 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file,
 		err = bpf_percpu_cgroup_storage_update(map, key, value,
 						       flags);
 	} else if (IS_FD_ARRAY(map)) {
-		rcu_read_lock();
 		err = bpf_fd_array_map_update_elem(map, map_file, key, value,
 						   flags);
-		rcu_read_unlock();
 	} else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
-		rcu_read_lock();
 		err = bpf_fd_htab_map_update_elem(map, map_file, key, value,
 						  flags);
-		rcu_read_unlock();
 	} else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
 		/* rcu_read_lock() is not needed */
 		err = bpf_fd_reuseport_array_update_elem(map, key, value,
@@ -203,7 +203,6 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file,
 		rcu_read_unlock();
 	}
 	bpf_enable_instrumentation();
-	maybe_wait_bpf_programs(map);
 
 	return err;
 }
@@ -264,7 +263,6 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
 	}
 
 	bpf_enable_instrumentation();
-	maybe_wait_bpf_programs(map);
 
 	return err;
 }
@@ -694,6 +692,7 @@ static void bpf_map_free_deferred(struct work_struct *work)
 {
 	struct bpf_map *map = container_of(work, struct bpf_map, work);
 	struct btf_record *rec = map->record;
+	struct btf *btf = map->btf;
 
 	security_bpf_map_free(map);
 	bpf_map_release_memcg(map);
@@ -709,6 +708,10 @@ static void bpf_map_free_deferred(struct work_struct *work)
 	 * template bpf_map struct used during verification.
 	 */
 	btf_record_free(rec);
+	/* Delay freeing of btf for maps, as map_free callback may need
+	 * struct_meta info which will be freed with btf_put().
+	 */
+	btf_put(btf);
 }
 
 static void bpf_map_put_uref(struct bpf_map *map)
@@ -719,6 +722,28 @@ static void bpf_map_put_uref(struct bpf_map *map)
 	}
 }
 
+static void bpf_map_free_in_work(struct bpf_map *map)
+{
+	INIT_WORK(&map->work, bpf_map_free_deferred);
+	/* Avoid spawning kworkers, since they all might contend
+	 * for the same mutex like slab_mutex.
+	 */
+	queue_work(system_unbound_wq, &map->work);
+}
+
+static void bpf_map_free_rcu_gp(struct rcu_head *rcu)
+{
+	bpf_map_free_in_work(container_of(rcu, struct bpf_map, rcu));
+}
+
+static void bpf_map_free_mult_rcu_gp(struct rcu_head *rcu)
+{
+	if (rcu_trace_implies_rcu_gp())
+		bpf_map_free_rcu_gp(rcu);
+	else
+		call_rcu(rcu, bpf_map_free_rcu_gp);
+}
+
 /* decrement map refcnt and schedule it for freeing via workqueue
  * (underlying map implementation ops->map_free() might sleep)
  */
@@ -727,12 +752,14 @@ void bpf_map_put(struct bpf_map *map)
 	if (atomic64_dec_and_test(&map->refcnt)) {
 		/* bpf_map_free_id() must be called first */
 		bpf_map_free_id(map);
-		btf_put(map->btf);
-		INIT_WORK(&map->work, bpf_map_free_deferred);
-		/* Avoid spawning kworkers, since they all might contend
-		 * for the same mutex like slab_mutex.
-		 */
-		queue_work(system_unbound_wq, &map->work);
+
+		WARN_ON_ONCE(atomic64_read(&map->sleepable_refcnt));
+		if (READ_ONCE(map->free_after_mult_rcu_gp))
+			call_rcu_tasks_trace(&map->rcu, bpf_map_free_mult_rcu_gp);
+		else if (READ_ONCE(map->free_after_rcu_gp))
+			call_rcu(&map->rcu, bpf_map_free_rcu_gp);
+		else
+			bpf_map_free_in_work(map);
 	}
 }
 EXPORT_SYMBOL_GPL(bpf_map_put);
@@ -1524,6 +1551,8 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
 	}
 
 	err = bpf_map_update_value(map, f.file, key, value, attr->flags);
+	if (!err)
+		maybe_wait_bpf_programs(map);
 
 	kvfree(value);
 free_key:
@@ -1579,7 +1608,8 @@ static int map_delete_elem(union bpf_attr *attr, bpfptr_t uattr)
 	err = map->ops->map_delete_elem(map, key);
 	rcu_read_unlock();
 	bpf_enable_instrumentation();
-	maybe_wait_bpf_programs(map);
+	if (!err)
+		maybe_wait_bpf_programs(map);
 out:
 	kvfree(key);
 err_put:
@@ -1676,6 +1706,9 @@ int generic_map_delete_batch(struct bpf_map *map,
 	if (!max_count)
 		return 0;
 
+	if (put_user(0, &uattr->batch.count))
+		return -EFAULT;
+
 	key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN);
 	if (!key)
 		return -ENOMEM;
@@ -1705,7 +1738,6 @@ int generic_map_delete_batch(struct bpf_map *map,
 
 	kvfree(key);
 
-	maybe_wait_bpf_programs(map);
 	return err;
 }
 
@@ -1733,6 +1765,9 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file,
 	if (!max_count)
 		return 0;
 
+	if (put_user(0, &uattr->batch.count))
+		return -EFAULT;
+
 	key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN);
 	if (!key)
 		return -ENOMEM;
@@ -1763,6 +1798,7 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file,
 
 	kvfree(value);
 	kvfree(key);
+
 	return err;
 }
 
@@ -2573,7 +2609,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 				 BPF_F_SLEEPABLE |
 				 BPF_F_TEST_RND_HI32 |
 				 BPF_F_XDP_HAS_FRAGS |
-				 BPF_F_XDP_DEV_BOUND_ONLY))
+				 BPF_F_XDP_DEV_BOUND_ONLY |
+				 BPF_F_TEST_REG_INVARIANTS))
 		return -EINVAL;
 
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
@@ -2701,6 +2738,22 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 			goto free_prog_sec;
 	}
 
+	/*
+	 * Bookkeeping for managing the program attachment chain.
+	 *
+	 * It might be tempting to set attach_tracing_prog flag at the attachment
+	 * time, but this will not prevent from loading bunch of tracing prog
+	 * first, then attach them one to another.
+	 *
+	 * The flag attach_tracing_prog is set for the whole program lifecycle, and
+	 * doesn't have to be cleared in bpf_tracing_link_release, since tracing
+	 * programs cannot change attachment target.
+	 */
+	if (type == BPF_PROG_TYPE_TRACING && dst_prog &&
+	    dst_prog->type == BPF_PROG_TYPE_TRACING) {
+		prog->aux->attach_tracing_prog = true;
+	}
+
 	/* find program type: socket_filter vs tracing_filter */
 	err = find_prog_type(type, prog);
 	if (err < 0)
@@ -3134,7 +3187,12 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 	}
 
 	if (tgt_prog_fd) {
-		/* For now we only allow new targets for BPF_PROG_TYPE_EXT */
+		/*
+		 * For now we only allow new targets for BPF_PROG_TYPE_EXT. If this
+		 * part would be changed to implement the same for
+		 * BPF_PROG_TYPE_TRACING, do not forget to update the way how
+		 * attach_tracing_prog flag is set.
+		 */
 		if (prog->type != BPF_PROG_TYPE_EXT) {
 			err = -EINVAL;
 			goto out_put_prog;
@@ -3179,6 +3237,10 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 	 *
 	 * - if prog->aux->dst_trampoline and tgt_prog is NULL, the program
 	 *   was detached and is going for re-attachment.
+	 *
+	 * - if prog->aux->dst_trampoline is NULL and tgt_prog and prog->aux->attach_btf
+	 *   are NULL, then program was already attached and user did not provide
+	 *   tgt_prog_fd so we have no way to find out or create trampoline
 	 */
 	if (!prog->aux->dst_trampoline && !tgt_prog) {
 		/*
@@ -3192,6 +3254,11 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 			err = -EINVAL;
 			goto out_unlock;
 		}
+		/* We can allow re-attach only if we have valid attach_btf. */
+		if (!prog->aux->attach_btf) {
+			err = -EINVAL;
+			goto out_unlock;
+		}
 		btf_id = prog->aux->attach_btf_id;
 		key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf, btf_id);
 	}
@@ -4919,8 +4986,10 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
 	else
 		BPF_DO_BATCH(map->ops->map_delete_batch, map, attr, uattr);
 err_put:
-	if (has_write)
+	if (has_write) {
+		maybe_wait_bpf_programs(map);
 		bpf_map_write_active_dec(map);
+	}
 	fdput(f);
 	return err;
 }
@@ -5322,6 +5391,11 @@ static int bpf_prog_bind_map(union bpf_attr *attr)
 		goto out_unlock;
 	}
 
+	/* The bpf program will not access the bpf map, but for the sake of
+	 * simplicity, increase sleepable_refcnt for sleepable program as well.
+	 */
+	if (prog->aux->sleepable)
+		atomic64_inc(&map->sleepable_refcnt);
 	memcpy(used_maps_new, used_maps_old,
 	       sizeof(used_maps_old[0]) * prog->aux->used_map_cnt);
 	used_maps_new[prog->aux->used_map_cnt] = map;
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index 26082b97894d..e5c3500443c6 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -70,15 +70,13 @@ static struct task_struct *task_group_seq_get_next(struct bpf_iter_seq_task_comm
 		return NULL;
 
 retry:
-	task = next_thread(task);
+	task = __next_thread(task);
+	if (!task)
+		return NULL;
 
 	next_tid = __task_pid_nr_ns(task, PIDTYPE_PID, common->ns);
-	if (!next_tid || next_tid == common->pid) {
-		/* Run out of tasks of a process.  The tasks of a
-		 * thread_group are linked as circular linked list.
-		 */
-		return NULL;
-	}
+	if (!next_tid)
+		goto retry;
 
 	if (skip_if_dup_files && task->files == task->group_leader->files)
 		goto retry;
@@ -980,7 +978,6 @@ __bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it,
 	BUILD_BUG_ON(__alignof__(struct bpf_iter_task_kern) !=
 					__alignof__(struct bpf_iter_task));
 
-	kit->task = kit->pos = NULL;
 	switch (flags) {
 	case BPF_TASK_ITER_ALL_THREADS:
 	case BPF_TASK_ITER_ALL_PROCS:
@@ -1017,20 +1014,16 @@ __bpf_kfunc struct task_struct *bpf_iter_task_next(struct bpf_iter_task *it)
 	if (flags == BPF_TASK_ITER_ALL_PROCS)
 		goto get_next_task;
 
-	kit->pos = next_thread(kit->pos);
-	if (kit->pos == kit->task) {
-		if (flags == BPF_TASK_ITER_PROC_THREADS) {
-			kit->pos = NULL;
-			return pos;
-		}
-	} else
+	kit->pos = __next_thread(kit->pos);
+	if (kit->pos || flags == BPF_TASK_ITER_PROC_THREADS)
 		return pos;
 
 get_next_task:
-	kit->pos = next_task(kit->pos);
-	kit->task = kit->pos;
-	if (kit->pos == &init_task)
+	kit->task = next_task(kit->task);
+	if (kit->task == &init_task)
 		kit->pos = NULL;
+	else
+		kit->pos = kit->task;
 
 	return pos;
 }
diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c
index 3d7127f439a1..9dbc31b25e3d 100644
--- a/kernel/bpf/tnum.c
+++ b/kernel/bpf/tnum.c
@@ -172,12 +172,6 @@ bool tnum_in(struct tnum a, struct tnum b)
 	return a.value == b.value;
 }
 
-int tnum_strn(char *str, size_t size, struct tnum a)
-{
-	return snprintf(str, size, "(%#llx; %#llx)", a.value, a.mask);
-}
-EXPORT_SYMBOL_GPL(tnum_strn);
-
 int tnum_sbin(char *str, size_t size, struct tnum a)
 {
 	size_t n;
@@ -208,7 +202,12 @@ struct tnum tnum_clear_subreg(struct tnum a)
 	return tnum_lshift(tnum_rshift(a, 32), 32);
 }
 
+struct tnum tnum_with_subreg(struct tnum reg, struct tnum subreg)
+{
+	return tnum_or(tnum_clear_subreg(reg), tnum_subreg(subreg));
+}
+
 struct tnum tnum_const_subreg(struct tnum a, u32 value)
 {
-	return tnum_or(tnum_clear_subreg(a), tnum_const(value));
+	return tnum_with_subreg(a, tnum_const(value));
 }
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index e97aeda3a86b..d382f5ebe06c 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -115,10 +115,10 @@ bool bpf_prog_has_trampoline(const struct bpf_prog *prog)
 		(ptype == BPF_PROG_TYPE_LSM && eatype == BPF_LSM_MAC);
 }
 
-void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym)
+void bpf_image_ksym_add(void *data, unsigned int size, struct bpf_ksym *ksym)
 {
 	ksym->start = (unsigned long) data;
-	ksym->end = ksym->start + PAGE_SIZE;
+	ksym->end = ksym->start + size;
 	bpf_ksym_add(ksym);
 	perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, ksym->start,
 			   PAGE_SIZE, false, ksym->name);
@@ -254,8 +254,8 @@ bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_a
 static void bpf_tramp_image_free(struct bpf_tramp_image *im)
 {
 	bpf_image_ksym_del(&im->ksym);
-	bpf_jit_free_exec(im->image);
-	bpf_jit_uncharge_modmem(PAGE_SIZE);
+	arch_free_bpf_trampoline(im->image, im->size);
+	bpf_jit_uncharge_modmem(im->size);
 	percpu_ref_exit(&im->pcref);
 	kfree_rcu(im, rcu);
 }
@@ -349,7 +349,7 @@ static void bpf_tramp_image_put(struct bpf_tramp_image *im)
 	call_rcu_tasks_trace(&im->rcu, __bpf_tramp_image_put_rcu_tasks);
 }
 
-static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key)
+static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, int size)
 {
 	struct bpf_tramp_image *im;
 	struct bpf_ksym *ksym;
@@ -360,15 +360,15 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key)
 	if (!im)
 		goto out;
 
-	err = bpf_jit_charge_modmem(PAGE_SIZE);
+	err = bpf_jit_charge_modmem(size);
 	if (err)
 		goto out_free_im;
+	im->size = size;
 
 	err = -ENOMEM;
-	im->image = image = bpf_jit_alloc_exec(PAGE_SIZE);
+	im->image = image = arch_alloc_bpf_trampoline(size);
 	if (!image)
 		goto out_uncharge;
-	set_vm_flush_reset_perms(image);
 
 	err = percpu_ref_init(&im->pcref, __bpf_tramp_image_release, 0, GFP_KERNEL);
 	if (err)
@@ -377,13 +377,13 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key)
 	ksym = &im->ksym;
 	INIT_LIST_HEAD_RCU(&ksym->lnode);
 	snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu", key);
-	bpf_image_ksym_add(image, ksym);
+	bpf_image_ksym_add(image, size, ksym);
 	return im;
 
 out_free_image:
-	bpf_jit_free_exec(im->image);
+	arch_free_bpf_trampoline(im->image, im->size);
 out_uncharge:
-	bpf_jit_uncharge_modmem(PAGE_SIZE);
+	bpf_jit_uncharge_modmem(size);
 out_free_im:
 	kfree(im);
 out:
@@ -396,7 +396,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
 	struct bpf_tramp_links *tlinks;
 	u32 orig_flags = tr->flags;
 	bool ip_arg = false;
-	int err, total;
+	int err, total, size;
 
 	tlinks = bpf_trampoline_get_progs(tr, &total, &ip_arg);
 	if (IS_ERR(tlinks))
@@ -409,12 +409,6 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
 		goto out;
 	}
 
-	im = bpf_tramp_image_alloc(tr->key);
-	if (IS_ERR(im)) {
-		err = PTR_ERR(im);
-		goto out;
-	}
-
 	/* clear all bits except SHARE_IPMODIFY and TAIL_CALL_CTX */
 	tr->flags &= (BPF_TRAMP_F_SHARE_IPMODIFY | BPF_TRAMP_F_TAIL_CALL_CTX);
 
@@ -438,13 +432,31 @@ again:
 		tr->flags |= BPF_TRAMP_F_ORIG_STACK;
 #endif
 
-	err = arch_prepare_bpf_trampoline(im, im->image, im->image + PAGE_SIZE,
+	size = arch_bpf_trampoline_size(&tr->func.model, tr->flags,
+					tlinks, tr->func.addr);
+	if (size < 0) {
+		err = size;
+		goto out;
+	}
+
+	if (size > PAGE_SIZE) {
+		err = -E2BIG;
+		goto out;
+	}
+
+	im = bpf_tramp_image_alloc(tr->key, size);
+	if (IS_ERR(im)) {
+		err = PTR_ERR(im);
+		goto out;
+	}
+
+	err = arch_prepare_bpf_trampoline(im, im->image, im->image + size,
 					  &tr->func.model, tr->flags, tlinks,
 					  tr->func.addr);
 	if (err < 0)
 		goto out_free;
 
-	set_memory_rox((long)im->image, 1);
+	arch_protect_bpf_trampoline(im->image, im->size);
 
 	WARN_ON(tr->cur_image && total == 0);
 	if (tr->cur_image)
@@ -464,9 +476,8 @@ again:
 		tr->fops->func = NULL;
 		tr->fops->trampoline = 0;
 
-		/* reset im->image memory attr for arch_prepare_bpf_trampoline */
-		set_memory_nx((long)im->image, 1);
-		set_memory_rw((long)im->image, 1);
+		/* free im memory and reallocate later */
+		bpf_tramp_image_free(im);
 		goto again;
 	}
 #endif
@@ -1032,10 +1043,50 @@ bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog)
 }
 
 int __weak
-arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end,
+arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
 			    const struct btf_func_model *m, u32 flags,
 			    struct bpf_tramp_links *tlinks,
-			    void *orig_call)
+			    void *func_addr)
+{
+	return -ENOTSUPP;
+}
+
+void * __weak arch_alloc_bpf_trampoline(unsigned int size)
+{
+	void *image;
+
+	if (WARN_ON_ONCE(size > PAGE_SIZE))
+		return NULL;
+	image = bpf_jit_alloc_exec(PAGE_SIZE);
+	if (image)
+		set_vm_flush_reset_perms(image);
+	return image;
+}
+
+void __weak arch_free_bpf_trampoline(void *image, unsigned int size)
+{
+	WARN_ON_ONCE(size > PAGE_SIZE);
+	/* bpf_jit_free_exec doesn't need "size", but
+	 * bpf_prog_pack_free() needs it.
+	 */
+	bpf_jit_free_exec(image);
+}
+
+void __weak arch_protect_bpf_trampoline(void *image, unsigned int size)
+{
+	WARN_ON_ONCE(size > PAGE_SIZE);
+	set_memory_rox((long)image, 1);
+}
+
+void __weak arch_unprotect_bpf_trampoline(void *image, unsigned int size)
+{
+	WARN_ON_ONCE(size > PAGE_SIZE);
+	set_memory_nx((long)image, 1);
+	set_memory_rw((long)image, 1);
+}
+
+int __weak arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
+				    struct bpf_tramp_links *tlinks, void *func_addr)
 {
 	return -ENOTSUPP;
 }
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index bd1c42eb540f..adbf330d364b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -26,6 +26,7 @@
 #include <linux/poison.h>
 #include <linux/module.h>
 #include <linux/cpumask.h>
+#include <linux/bpf_mem_alloc.h>
 #include <net/xdp.h>
 
 #include "disasm.h"
@@ -41,6 +42,9 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
 #undef BPF_LINK_TYPE
 };
 
+struct bpf_mem_alloc bpf_global_percpu_ma;
+static bool bpf_global_percpu_ma_set;
+
 /* bpf_check() is a static code analyzer that walks eBPF program
  * instruction by instruction and updates register/stack state.
  * All paths of conditional branches are analyzed until 'bpf_exit' insn.
@@ -191,6 +195,8 @@ struct bpf_verifier_stack_elem {
 					  POISON_POINTER_DELTA))
 #define BPF_MAP_PTR(X)		((struct bpf_map *)((X) & ~BPF_MAP_PTR_UNPRIV))
 
+#define BPF_GLOBAL_PERCPU_MA_MAX_SIZE  512
+
 static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx);
 static int release_reference(struct bpf_verifier_env *env, int ref_obj_id);
 static void invalidate_non_owning_refs(struct bpf_verifier_env *env);
@@ -335,29 +341,14 @@ struct bpf_kfunc_call_arg_meta {
 
 struct btf *btf_vmlinux;
 
-static DEFINE_MUTEX(bpf_verifier_lock);
-
-static const struct bpf_line_info *
-find_linfo(const struct bpf_verifier_env *env, u32 insn_off)
+static const char *btf_type_name(const struct btf *btf, u32 id)
 {
-	const struct bpf_line_info *linfo;
-	const struct bpf_prog *prog;
-	u32 i, nr_linfo;
-
-	prog = env->prog;
-	nr_linfo = prog->aux->nr_linfo;
-
-	if (!nr_linfo || insn_off >= prog->len)
-		return NULL;
-
-	linfo = prog->aux->linfo;
-	for (i = 1; i < nr_linfo; i++)
-		if (insn_off < linfo[i].insn_off)
-			break;
-
-	return &linfo[i - 1];
+	return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off);
 }
 
+static DEFINE_MUTEX(bpf_verifier_lock);
+static DEFINE_MUTEX(bpf_percpu_ma_lock);
+
 __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...)
 {
 	struct bpf_verifier_env *env = private_data;
@@ -371,73 +362,25 @@ __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...)
 	va_end(args);
 }
 
-static const char *ltrim(const char *s)
-{
-	while (isspace(*s))
-		s++;
-
-	return s;
-}
-
-__printf(3, 4) static void verbose_linfo(struct bpf_verifier_env *env,
-					 u32 insn_off,
-					 const char *prefix_fmt, ...)
-{
-	const struct bpf_line_info *linfo;
-
-	if (!bpf_verifier_log_needed(&env->log))
-		return;
-
-	linfo = find_linfo(env, insn_off);
-	if (!linfo || linfo == env->prev_linfo)
-		return;
-
-	if (prefix_fmt) {
-		va_list args;
-
-		va_start(args, prefix_fmt);
-		bpf_verifier_vlog(&env->log, prefix_fmt, args);
-		va_end(args);
-	}
-
-	verbose(env, "%s\n",
-		ltrim(btf_name_by_offset(env->prog->aux->btf,
-					 linfo->line_off)));
-
-	env->prev_linfo = linfo;
-}
-
 static void verbose_invalid_scalar(struct bpf_verifier_env *env,
 				   struct bpf_reg_state *reg,
-				   struct tnum *range, const char *ctx,
+				   struct bpf_retval_range range, const char *ctx,
 				   const char *reg_name)
 {
-	char tn_buf[48];
+	bool unknown = true;
 
-	verbose(env, "At %s the register %s ", ctx, reg_name);
-	if (!tnum_is_unknown(reg->var_off)) {
-		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
-		verbose(env, "has value %s", tn_buf);
-	} else {
-		verbose(env, "has unknown scalar value");
+	verbose(env, "%s the register %s has", ctx, reg_name);
+	if (reg->smin_value > S64_MIN) {
+		verbose(env, " smin=%lld", reg->smin_value);
+		unknown = false;
 	}
-	tnum_strn(tn_buf, sizeof(tn_buf), *range);
-	verbose(env, " should have been in %s\n", tn_buf);
-}
-
-static bool type_is_pkt_pointer(enum bpf_reg_type type)
-{
-	type = base_type(type);
-	return type == PTR_TO_PACKET ||
-	       type == PTR_TO_PACKET_META;
-}
-
-static bool type_is_sk_pointer(enum bpf_reg_type type)
-{
-	return type == PTR_TO_SOCKET ||
-		type == PTR_TO_SOCK_COMMON ||
-		type == PTR_TO_TCP_SOCK ||
-		type == PTR_TO_XDP_SOCK;
+	if (reg->smax_value < S64_MAX) {
+		verbose(env, " smax=%lld", reg->smax_value);
+		unknown = false;
+	}
+	if (unknown)
+		verbose(env, " unknown scalar value");
+	verbose(env, " should have been in [%d, %d]\n", range.minval, range.maxval);
 }
 
 static bool type_may_be_null(u32 type)
@@ -463,16 +406,6 @@ static bool reg_not_null(const struct bpf_reg_state *reg)
 		type == PTR_TO_MEM;
 }
 
-static bool type_is_ptr_alloc_obj(u32 type)
-{
-	return base_type(type) == PTR_TO_BTF_ID && type_flag(type) & MEM_ALLOC;
-}
-
-static bool type_is_non_owning_ref(u32 type)
-{
-	return type_is_ptr_alloc_obj(type) && type_flag(type) & NON_OWN_REF;
-}
-
 static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg)
 {
 	struct btf_record *rec = NULL;
@@ -495,6 +428,31 @@ static bool subprog_is_global(const struct bpf_verifier_env *env, int subprog)
 	return aux && aux[subprog].linkage == BTF_FUNC_GLOBAL;
 }
 
+static const char *subprog_name(const struct bpf_verifier_env *env, int subprog)
+{
+	struct bpf_func_info *info;
+
+	if (!env->prog->aux->func_info)
+		return "";
+
+	info = &env->prog->aux->func_info[subprog];
+	return btf_type_name(env->prog->aux->btf, info->type_id);
+}
+
+static void mark_subprog_exc_cb(struct bpf_verifier_env *env, int subprog)
+{
+	struct bpf_subprog_info *info = subprog_info(env, subprog);
+
+	info->is_cb = true;
+	info->is_async_cb = true;
+	info->is_exception_cb = true;
+}
+
+static bool subprog_is_exc_cb(struct bpf_verifier_env *env, int subprog)
+{
+	return subprog_info(env, subprog)->is_exception_cb;
+}
+
 static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
 {
 	return btf_record_has_field(reg_btf_record(reg), BPF_SPIN_LOCK);
@@ -542,13 +500,12 @@ static bool is_dynptr_ref_function(enum bpf_func_id func_id)
 	return func_id == BPF_FUNC_dynptr_data;
 }
 
-static bool is_callback_calling_kfunc(u32 btf_id);
+static bool is_sync_callback_calling_kfunc(u32 btf_id);
 static bool is_bpf_throw_kfunc(struct bpf_insn *insn);
 
-static bool is_callback_calling_function(enum bpf_func_id func_id)
+static bool is_sync_callback_calling_function(enum bpf_func_id func_id)
 {
 	return func_id == BPF_FUNC_for_each_map_elem ||
-	       func_id == BPF_FUNC_timer_set_callback ||
 	       func_id == BPF_FUNC_find_vma ||
 	       func_id == BPF_FUNC_loop ||
 	       func_id == BPF_FUNC_user_ringbuf_drain;
@@ -559,6 +516,18 @@ static bool is_async_callback_calling_function(enum bpf_func_id func_id)
 	return func_id == BPF_FUNC_timer_set_callback;
 }
 
+static bool is_callback_calling_function(enum bpf_func_id func_id)
+{
+	return is_sync_callback_calling_function(func_id) ||
+	       is_async_callback_calling_function(func_id);
+}
+
+static bool is_sync_callback_calling_insn(struct bpf_insn *insn)
+{
+	return (bpf_helper_call(insn) && is_sync_callback_calling_function(insn->imm)) ||
+	       (bpf_pseudo_kfunc_call(insn) && is_sync_callback_calling_kfunc(insn->imm));
+}
+
 static bool is_storage_get_function(enum bpf_func_id func_id)
 {
 	return func_id == BPF_FUNC_sk_storage_get ||
@@ -589,83 +558,6 @@ static bool is_cmpxchg_insn(const struct bpf_insn *insn)
 	       insn->imm == BPF_CMPXCHG;
 }
 
-/* string representation of 'enum bpf_reg_type'
- *
- * Note that reg_type_str() can not appear more than once in a single verbose()
- * statement.
- */
-static const char *reg_type_str(struct bpf_verifier_env *env,
-				enum bpf_reg_type type)
-{
-	char postfix[16] = {0}, prefix[64] = {0};
-	static const char * const str[] = {
-		[NOT_INIT]		= "?",
-		[SCALAR_VALUE]		= "scalar",
-		[PTR_TO_CTX]		= "ctx",
-		[CONST_PTR_TO_MAP]	= "map_ptr",
-		[PTR_TO_MAP_VALUE]	= "map_value",
-		[PTR_TO_STACK]		= "fp",
-		[PTR_TO_PACKET]		= "pkt",
-		[PTR_TO_PACKET_META]	= "pkt_meta",
-		[PTR_TO_PACKET_END]	= "pkt_end",
-		[PTR_TO_FLOW_KEYS]	= "flow_keys",
-		[PTR_TO_SOCKET]		= "sock",
-		[PTR_TO_SOCK_COMMON]	= "sock_common",
-		[PTR_TO_TCP_SOCK]	= "tcp_sock",
-		[PTR_TO_TP_BUFFER]	= "tp_buffer",
-		[PTR_TO_XDP_SOCK]	= "xdp_sock",
-		[PTR_TO_BTF_ID]		= "ptr_",
-		[PTR_TO_MEM]		= "mem",
-		[PTR_TO_BUF]		= "buf",
-		[PTR_TO_FUNC]		= "func",
-		[PTR_TO_MAP_KEY]	= "map_key",
-		[CONST_PTR_TO_DYNPTR]	= "dynptr_ptr",
-	};
-
-	if (type & PTR_MAYBE_NULL) {
-		if (base_type(type) == PTR_TO_BTF_ID)
-			strncpy(postfix, "or_null_", 16);
-		else
-			strncpy(postfix, "_or_null", 16);
-	}
-
-	snprintf(prefix, sizeof(prefix), "%s%s%s%s%s%s%s",
-		 type & MEM_RDONLY ? "rdonly_" : "",
-		 type & MEM_RINGBUF ? "ringbuf_" : "",
-		 type & MEM_USER ? "user_" : "",
-		 type & MEM_PERCPU ? "percpu_" : "",
-		 type & MEM_RCU ? "rcu_" : "",
-		 type & PTR_UNTRUSTED ? "untrusted_" : "",
-		 type & PTR_TRUSTED ? "trusted_" : ""
-	);
-
-	snprintf(env->tmp_str_buf, TMP_STR_BUF_LEN, "%s%s%s",
-		 prefix, str[base_type(type)], postfix);
-	return env->tmp_str_buf;
-}
-
-static char slot_type_char[] = {
-	[STACK_INVALID]	= '?',
-	[STACK_SPILL]	= 'r',
-	[STACK_MISC]	= 'm',
-	[STACK_ZERO]	= '0',
-	[STACK_DYNPTR]	= 'd',
-	[STACK_ITER]	= 'i',
-};
-
-static void print_liveness(struct bpf_verifier_env *env,
-			   enum bpf_reg_liveness live)
-{
-	if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE))
-	    verbose(env, "_");
-	if (live & REG_LIVE_READ)
-		verbose(env, "r");
-	if (live & REG_LIVE_WRITTEN)
-		verbose(env, "w");
-	if (live & REG_LIVE_DONE)
-		verbose(env, "D");
-}
-
 static int __get_spi(s32 off)
 {
 	return (-off - 1) / BPF_REG_SIZE;
@@ -730,92 +622,6 @@ static int iter_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
 	return stack_slot_obj_get_spi(env, reg, "iter", nr_slots);
 }
 
-static const char *btf_type_name(const struct btf *btf, u32 id)
-{
-	return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off);
-}
-
-static const char *dynptr_type_str(enum bpf_dynptr_type type)
-{
-	switch (type) {
-	case BPF_DYNPTR_TYPE_LOCAL:
-		return "local";
-	case BPF_DYNPTR_TYPE_RINGBUF:
-		return "ringbuf";
-	case BPF_DYNPTR_TYPE_SKB:
-		return "skb";
-	case BPF_DYNPTR_TYPE_XDP:
-		return "xdp";
-	case BPF_DYNPTR_TYPE_INVALID:
-		return "<invalid>";
-	default:
-		WARN_ONCE(1, "unknown dynptr type %d\n", type);
-		return "<unknown>";
-	}
-}
-
-static const char *iter_type_str(const struct btf *btf, u32 btf_id)
-{
-	if (!btf || btf_id == 0)
-		return "<invalid>";
-
-	/* we already validated that type is valid and has conforming name */
-	return btf_type_name(btf, btf_id) + sizeof(ITER_PREFIX) - 1;
-}
-
-static const char *iter_state_str(enum bpf_iter_state state)
-{
-	switch (state) {
-	case BPF_ITER_STATE_ACTIVE:
-		return "active";
-	case BPF_ITER_STATE_DRAINED:
-		return "drained";
-	case BPF_ITER_STATE_INVALID:
-		return "<invalid>";
-	default:
-		WARN_ONCE(1, "unknown iter state %d\n", state);
-		return "<unknown>";
-	}
-}
-
-static void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno)
-{
-	env->scratched_regs |= 1U << regno;
-}
-
-static void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi)
-{
-	env->scratched_stack_slots |= 1ULL << spi;
-}
-
-static bool reg_scratched(const struct bpf_verifier_env *env, u32 regno)
-{
-	return (env->scratched_regs >> regno) & 1;
-}
-
-static bool stack_slot_scratched(const struct bpf_verifier_env *env, u64 regno)
-{
-	return (env->scratched_stack_slots >> regno) & 1;
-}
-
-static bool verifier_state_scratched(const struct bpf_verifier_env *env)
-{
-	return env->scratched_regs || env->scratched_stack_slots;
-}
-
-static void mark_verifier_state_clean(struct bpf_verifier_env *env)
-{
-	env->scratched_regs = 0U;
-	env->scratched_stack_slots = 0ULL;
-}
-
-/* Used for printing the entire verifier state. */
-static void mark_verifier_state_scratched(struct bpf_verifier_env *env)
-{
-	env->scratched_regs = ~0U;
-	env->scratched_stack_slots = ~0ULL;
-}
-
 static enum bpf_dynptr_type arg_to_dynptr_type(enum bpf_arg_type arg_type)
 {
 	switch (arg_type & DYNPTR_TYPE_FLAG_MASK) {
@@ -1349,230 +1155,25 @@ static bool is_spilled_scalar_reg(const struct bpf_stack_state *stack)
 	       stack->spilled_ptr.type == SCALAR_VALUE;
 }
 
-static void scrub_spilled_slot(u8 *stype)
-{
-	if (*stype != STACK_INVALID)
-		*stype = STACK_MISC;
-}
-
-static void print_scalar_ranges(struct bpf_verifier_env *env,
-				const struct bpf_reg_state *reg,
-				const char **sep)
-{
-	struct {
-		const char *name;
-		u64 val;
-		bool omit;
-	} minmaxs[] = {
-		{"smin",   reg->smin_value,         reg->smin_value == S64_MIN},
-		{"smax",   reg->smax_value,         reg->smax_value == S64_MAX},
-		{"umin",   reg->umin_value,         reg->umin_value == 0},
-		{"umax",   reg->umax_value,         reg->umax_value == U64_MAX},
-		{"smin32", (s64)reg->s32_min_value, reg->s32_min_value == S32_MIN},
-		{"smax32", (s64)reg->s32_max_value, reg->s32_max_value == S32_MAX},
-		{"umin32", reg->u32_min_value,      reg->u32_min_value == 0},
-		{"umax32", reg->u32_max_value,      reg->u32_max_value == U32_MAX},
-	}, *m1, *m2, *mend = &minmaxs[ARRAY_SIZE(minmaxs)];
-	bool neg1, neg2;
-
-	for (m1 = &minmaxs[0]; m1 < mend; m1++) {
-		if (m1->omit)
-			continue;
-
-		neg1 = m1->name[0] == 's' && (s64)m1->val < 0;
-
-		verbose(env, "%s%s=", *sep, m1->name);
-		*sep = ",";
-
-		for (m2 = m1 + 2; m2 < mend; m2 += 2) {
-			if (m2->omit || m2->val != m1->val)
-				continue;
-			/* don't mix negatives with positives */
-			neg2 = m2->name[0] == 's' && (s64)m2->val < 0;
-			if (neg2 != neg1)
-				continue;
-			m2->omit = true;
-			verbose(env, "%s=", m2->name);
-		}
-
-		verbose(env, m1->name[0] == 's' ? "%lld" : "%llu", m1->val);
-	}
-}
-
-static void print_verifier_state(struct bpf_verifier_env *env,
-				 const struct bpf_func_state *state,
-				 bool print_all)
-{
-	const struct bpf_reg_state *reg;
-	enum bpf_reg_type t;
-	int i;
-
-	if (state->frameno)
-		verbose(env, " frame%d:", state->frameno);
-	for (i = 0; i < MAX_BPF_REG; i++) {
-		reg = &state->regs[i];
-		t = reg->type;
-		if (t == NOT_INIT)
-			continue;
-		if (!print_all && !reg_scratched(env, i))
-			continue;
-		verbose(env, " R%d", i);
-		print_liveness(env, reg->live);
-		verbose(env, "=");
-		if (t == SCALAR_VALUE && reg->precise)
-			verbose(env, "P");
-		if ((t == SCALAR_VALUE || t == PTR_TO_STACK) &&
-		    tnum_is_const(reg->var_off)) {
-			/* reg->off should be 0 for SCALAR_VALUE */
-			verbose(env, "%s", t == SCALAR_VALUE ? "" : reg_type_str(env, t));
-			verbose(env, "%lld", reg->var_off.value + reg->off);
-		} else {
-			const char *sep = "";
-
-			verbose(env, "%s", reg_type_str(env, t));
-			if (base_type(t) == PTR_TO_BTF_ID)
-				verbose(env, "%s", btf_type_name(reg->btf, reg->btf_id));
-			verbose(env, "(");
-/*
- * _a stands for append, was shortened to avoid multiline statements below.
- * This macro is used to output a comma separated list of attributes.
+/* Mark stack slot as STACK_MISC, unless it is already STACK_INVALID, in which
+ * case they are equivalent, or it's STACK_ZERO, in which case we preserve
+ * more precise STACK_ZERO.
+ * Note, in uprivileged mode leaving STACK_INVALID is wrong, so we take
+ * env->allow_ptr_leaks into account and force STACK_MISC, if necessary.
  */
-#define verbose_a(fmt, ...) ({ verbose(env, "%s" fmt, sep, __VA_ARGS__); sep = ","; })
-
-			if (reg->id)
-				verbose_a("id=%d", reg->id);
-			if (reg->ref_obj_id)
-				verbose_a("ref_obj_id=%d", reg->ref_obj_id);
-			if (type_is_non_owning_ref(reg->type))
-				verbose_a("%s", "non_own_ref");
-			if (t != SCALAR_VALUE)
-				verbose_a("off=%d", reg->off);
-			if (type_is_pkt_pointer(t))
-				verbose_a("r=%d", reg->range);
-			else if (base_type(t) == CONST_PTR_TO_MAP ||
-				 base_type(t) == PTR_TO_MAP_KEY ||
-				 base_type(t) == PTR_TO_MAP_VALUE)
-				verbose_a("ks=%d,vs=%d",
-					  reg->map_ptr->key_size,
-					  reg->map_ptr->value_size);
-			if (tnum_is_const(reg->var_off)) {
-				/* Typically an immediate SCALAR_VALUE, but
-				 * could be a pointer whose offset is too big
-				 * for reg->off
-				 */
-				verbose_a("imm=%llx", reg->var_off.value);
-			} else {
-				print_scalar_ranges(env, reg, &sep);
-				if (!tnum_is_unknown(reg->var_off)) {
-					char tn_buf[48];
-
-					tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
-					verbose_a("var_off=%s", tn_buf);
-				}
-			}
-#undef verbose_a
-
-			verbose(env, ")");
-		}
-	}
-	for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
-		char types_buf[BPF_REG_SIZE + 1];
-		bool valid = false;
-		int j;
-
-		for (j = 0; j < BPF_REG_SIZE; j++) {
-			if (state->stack[i].slot_type[j] != STACK_INVALID)
-				valid = true;
-			types_buf[j] = slot_type_char[state->stack[i].slot_type[j]];
-		}
-		types_buf[BPF_REG_SIZE] = 0;
-		if (!valid)
-			continue;
-		if (!print_all && !stack_slot_scratched(env, i))
-			continue;
-		switch (state->stack[i].slot_type[BPF_REG_SIZE - 1]) {
-		case STACK_SPILL:
-			reg = &state->stack[i].spilled_ptr;
-			t = reg->type;
-
-			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
-			print_liveness(env, reg->live);
-			verbose(env, "=%s", t == SCALAR_VALUE ? "" : reg_type_str(env, t));
-			if (t == SCALAR_VALUE && reg->precise)
-				verbose(env, "P");
-			if (t == SCALAR_VALUE && tnum_is_const(reg->var_off))
-				verbose(env, "%lld", reg->var_off.value + reg->off);
-			break;
-		case STACK_DYNPTR:
-			i += BPF_DYNPTR_NR_SLOTS - 1;
-			reg = &state->stack[i].spilled_ptr;
-
-			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
-			print_liveness(env, reg->live);
-			verbose(env, "=dynptr_%s", dynptr_type_str(reg->dynptr.type));
-			if (reg->ref_obj_id)
-				verbose(env, "(ref_id=%d)", reg->ref_obj_id);
-			break;
-		case STACK_ITER:
-			/* only main slot has ref_obj_id set; skip others */
-			reg = &state->stack[i].spilled_ptr;
-			if (!reg->ref_obj_id)
-				continue;
-
-			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
-			print_liveness(env, reg->live);
-			verbose(env, "=iter_%s(ref_id=%d,state=%s,depth=%u)",
-				iter_type_str(reg->iter.btf, reg->iter.btf_id),
-				reg->ref_obj_id, iter_state_str(reg->iter.state),
-				reg->iter.depth);
-			break;
-		case STACK_MISC:
-		case STACK_ZERO:
-		default:
-			reg = &state->stack[i].spilled_ptr;
-
-			for (j = 0; j < BPF_REG_SIZE; j++)
-				types_buf[j] = slot_type_char[state->stack[i].slot_type[j]];
-			types_buf[BPF_REG_SIZE] = 0;
-
-			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
-			print_liveness(env, reg->live);
-			verbose(env, "=%s", types_buf);
-			break;
-		}
-	}
-	if (state->acquired_refs && state->refs[0].id) {
-		verbose(env, " refs=%d", state->refs[0].id);
-		for (i = 1; i < state->acquired_refs; i++)
-			if (state->refs[i].id)
-				verbose(env, ",%d", state->refs[i].id);
-	}
-	if (state->in_callback_fn)
-		verbose(env, " cb");
-	if (state->in_async_callback_fn)
-		verbose(env, " async_cb");
-	verbose(env, "\n");
-	if (!print_all)
-		mark_verifier_state_clean(env);
-}
-
-static inline u32 vlog_alignment(u32 pos)
+static void mark_stack_slot_misc(struct bpf_verifier_env *env, u8 *stype)
 {
-	return round_up(max(pos + BPF_LOG_MIN_ALIGNMENT / 2, BPF_LOG_ALIGNMENT),
-			BPF_LOG_MIN_ALIGNMENT) - pos - 1;
+	if (*stype == STACK_ZERO)
+		return;
+	if (env->allow_ptr_leaks && *stype == STACK_INVALID)
+		return;
+	*stype = STACK_MISC;
 }
 
-static void print_insn_state(struct bpf_verifier_env *env,
-			     const struct bpf_func_state *state)
+static void scrub_spilled_slot(u8 *stype)
 {
-	if (env->prev_log_pos && env->prev_log_pos == env->log.end_pos) {
-		/* remove new line character */
-		bpf_vlog_reset(&env->log, env->prev_log_pos - 1);
-		verbose(env, "%*c;", vlog_alignment(env->prev_insn_print_pos), ' ');
-	} else {
-		verbose(env, "%d:", env->insn_idx);
-	}
-	print_verifier_state(env, state, false);
+	if (*stype != STACK_INVALID)
+		*stype = STACK_MISC;
 }
 
 /* copy array src of length n * size bytes to dst. dst is reallocated if it's too
@@ -1669,9 +1270,16 @@ static int resize_reference_state(struct bpf_func_state *state, size_t n)
 	return 0;
 }
 
-static int grow_stack_state(struct bpf_func_state *state, int size)
+/* Possibly update state->allocated_stack to be at least size bytes. Also
+ * possibly update the function's high-water mark in its bpf_subprog_info.
+ */
+static int grow_stack_state(struct bpf_verifier_env *env, struct bpf_func_state *state, int size)
 {
-	size_t old_n = state->allocated_stack / BPF_REG_SIZE, n = size / BPF_REG_SIZE;
+	size_t old_n = state->allocated_stack / BPF_REG_SIZE, n;
+
+	/* The stack size is always a multiple of BPF_REG_SIZE. */
+	size = round_up(size, BPF_REG_SIZE);
+	n = size / BPF_REG_SIZE;
 
 	if (old_n >= n)
 		return 0;
@@ -1681,6 +1289,11 @@ static int grow_stack_state(struct bpf_func_state *state, int size)
 		return -ENOMEM;
 
 	state->allocated_stack = size;
+
+	/* update known max for given subprogram */
+	if (env->subprog_info[state->subprogno].stack_depth < size)
+		env->subprog_info[state->subprogno].stack_depth = size;
+
 	return 0;
 }
 
@@ -1780,8 +1393,8 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
 	int i, err;
 
 	dst_state->jmp_history = copy_array(dst_state->jmp_history, src->jmp_history,
-					    src->jmp_history_cnt, sizeof(struct bpf_idx_pair),
-					    GFP_USER);
+					  src->jmp_history_cnt, sizeof(*dst_state->jmp_history),
+					  GFP_USER);
 	if (!dst_state->jmp_history)
 		return -ENOMEM;
 	dst_state->jmp_history_cnt = src->jmp_history_cnt;
@@ -1803,6 +1416,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
 	dst_state->first_insn_idx = src->first_insn_idx;
 	dst_state->last_insn_idx = src->last_insn_idx;
 	dst_state->dfs_depth = src->dfs_depth;
+	dst_state->callback_unroll_depth = src->callback_unroll_depth;
 	dst_state->used_as_loop_entry = src->used_as_loop_entry;
 	for (i = 0; i <= src->curframe; i++) {
 		dst = dst_state->frame[i];
@@ -2155,10 +1769,14 @@ static void __mark_reg_known_zero(struct bpf_reg_state *reg)
 	__mark_reg_known(reg, 0);
 }
 
-static void __mark_reg_const_zero(struct bpf_reg_state *reg)
+static void __mark_reg_const_zero(const struct bpf_verifier_env *env, struct bpf_reg_state *reg)
 {
 	__mark_reg_known(reg, 0);
 	reg->type = SCALAR_VALUE;
+	/* all scalars are assumed imprecise initially (unless unprivileged,
+	 * in which case everything is forced to be precise)
+	 */
+	reg->precise = !env->bpf_capable;
 }
 
 static void mark_reg_known_zero(struct bpf_verifier_env *env,
@@ -2324,69 +1942,214 @@ static void __update_reg_bounds(struct bpf_reg_state *reg)
 /* Uses signed min/max values to inform unsigned, and vice-versa */
 static void __reg32_deduce_bounds(struct bpf_reg_state *reg)
 {
-	/* Learn sign from signed bounds.
-	 * If we cannot cross the sign boundary, then signed and unsigned bounds
-	 * are the same, so combine.  This works even in the negative case, e.g.
-	 * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff.
+	/* If upper 32 bits of u64/s64 range don't change, we can use lower 32
+	 * bits to improve our u32/s32 boundaries.
+	 *
+	 * E.g., the case where we have upper 32 bits as zero ([10, 20] in
+	 * u64) is pretty trivial, it's obvious that in u32 we'll also have
+	 * [10, 20] range. But this property holds for any 64-bit range as
+	 * long as upper 32 bits in that entire range of values stay the same.
+	 *
+	 * E.g., u64 range [0x10000000A, 0x10000000F] ([4294967306, 4294967311]
+	 * in decimal) has the same upper 32 bits throughout all the values in
+	 * that range. As such, lower 32 bits form a valid [0xA, 0xF] ([10, 15])
+	 * range.
+	 *
+	 * Note also, that [0xA, 0xF] is a valid range both in u32 and in s32,
+	 * following the rules outlined below about u64/s64 correspondence
+	 * (which equally applies to u32 vs s32 correspondence). In general it
+	 * depends on actual hexadecimal values of 32-bit range. They can form
+	 * only valid u32, or only valid s32 ranges in some cases.
+	 *
+	 * So we use all these insights to derive bounds for subregisters here.
 	 */
-	if (reg->s32_min_value >= 0 || reg->s32_max_value < 0) {
-		reg->s32_min_value = reg->u32_min_value =
-			max_t(u32, reg->s32_min_value, reg->u32_min_value);
-		reg->s32_max_value = reg->u32_max_value =
-			min_t(u32, reg->s32_max_value, reg->u32_max_value);
-		return;
+	if ((reg->umin_value >> 32) == (reg->umax_value >> 32)) {
+		/* u64 to u32 casting preserves validity of low 32 bits as
+		 * a range, if upper 32 bits are the same
+		 */
+		reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)reg->umin_value);
+		reg->u32_max_value = min_t(u32, reg->u32_max_value, (u32)reg->umax_value);
+
+		if ((s32)reg->umin_value <= (s32)reg->umax_value) {
+			reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->umin_value);
+			reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->umax_value);
+		}
+	}
+	if ((reg->smin_value >> 32) == (reg->smax_value >> 32)) {
+		/* low 32 bits should form a proper u32 range */
+		if ((u32)reg->smin_value <= (u32)reg->smax_value) {
+			reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)reg->smin_value);
+			reg->u32_max_value = min_t(u32, reg->u32_max_value, (u32)reg->smax_value);
+		}
+		/* low 32 bits should form a proper s32 range */
+		if ((s32)reg->smin_value <= (s32)reg->smax_value) {
+			reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->smin_value);
+			reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->smax_value);
+		}
+	}
+	/* Special case where upper bits form a small sequence of two
+	 * sequential numbers (in 32-bit unsigned space, so 0xffffffff to
+	 * 0x00000000 is also valid), while lower bits form a proper s32 range
+	 * going from negative numbers to positive numbers. E.g., let's say we
+	 * have s64 range [-1, 1] ([0xffffffffffffffff, 0x0000000000000001]).
+	 * Possible s64 values are {-1, 0, 1} ({0xffffffffffffffff,
+	 * 0x0000000000000000, 0x00000000000001}). Ignoring upper 32 bits,
+	 * we still get a valid s32 range [-1, 1] ([0xffffffff, 0x00000001]).
+	 * Note that it doesn't have to be 0xffffffff going to 0x00000000 in
+	 * upper 32 bits. As a random example, s64 range
+	 * [0xfffffff0fffffff0; 0xfffffff100000010], forms a valid s32 range
+	 * [-16, 16] ([0xfffffff0; 0x00000010]) in its 32 bit subregister.
+	 */
+	if ((u32)(reg->umin_value >> 32) + 1 == (u32)(reg->umax_value >> 32) &&
+	    (s32)reg->umin_value < 0 && (s32)reg->umax_value >= 0) {
+		reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->umin_value);
+		reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->umax_value);
+	}
+	if ((u32)(reg->smin_value >> 32) + 1 == (u32)(reg->smax_value >> 32) &&
+	    (s32)reg->smin_value < 0 && (s32)reg->smax_value >= 0) {
+		reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->smin_value);
+		reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->smax_value);
+	}
+	/* if u32 range forms a valid s32 range (due to matching sign bit),
+	 * try to learn from that
+	 */
+	if ((s32)reg->u32_min_value <= (s32)reg->u32_max_value) {
+		reg->s32_min_value = max_t(s32, reg->s32_min_value, reg->u32_min_value);
+		reg->s32_max_value = min_t(s32, reg->s32_max_value, reg->u32_max_value);
 	}
-	/* Learn sign from unsigned bounds.  Signed bounds cross the sign
-	 * boundary, so we must be careful.
+	/* If we cannot cross the sign boundary, then signed and unsigned bounds
+	 * are the same, so combine.  This works even in the negative case, e.g.
+	 * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff.
 	 */
-	if ((s32)reg->u32_max_value >= 0) {
-		/* Positive.  We can't learn anything from the smin, but smax
-		 * is positive, hence safe.
-		 */
-		reg->s32_min_value = reg->u32_min_value;
-		reg->s32_max_value = reg->u32_max_value =
-			min_t(u32, reg->s32_max_value, reg->u32_max_value);
-	} else if ((s32)reg->u32_min_value < 0) {
-		/* Negative.  We can't learn anything from the smax, but smin
-		 * is negative, hence safe.
-		 */
-		reg->s32_min_value = reg->u32_min_value =
-			max_t(u32, reg->s32_min_value, reg->u32_min_value);
-		reg->s32_max_value = reg->u32_max_value;
+	if ((u32)reg->s32_min_value <= (u32)reg->s32_max_value) {
+		reg->u32_min_value = max_t(u32, reg->s32_min_value, reg->u32_min_value);
+		reg->u32_max_value = min_t(u32, reg->s32_max_value, reg->u32_max_value);
 	}
 }
 
 static void __reg64_deduce_bounds(struct bpf_reg_state *reg)
 {
-	/* Learn sign from signed bounds.
-	 * If we cannot cross the sign boundary, then signed and unsigned bounds
+	/* If u64 range forms a valid s64 range (due to matching sign bit),
+	 * try to learn from that. Let's do a bit of ASCII art to see when
+	 * this is happening. Let's take u64 range first:
+	 *
+	 * 0             0x7fffffffffffffff 0x8000000000000000        U64_MAX
+	 * |-------------------------------|--------------------------------|
+	 *
+	 * Valid u64 range is formed when umin and umax are anywhere in the
+	 * range [0, U64_MAX], and umin <= umax. u64 case is simple and
+	 * straightforward. Let's see how s64 range maps onto the same range
+	 * of values, annotated below the line for comparison:
+	 *
+	 * 0             0x7fffffffffffffff 0x8000000000000000        U64_MAX
+	 * |-------------------------------|--------------------------------|
+	 * 0                        S64_MAX S64_MIN                        -1
+	 *
+	 * So s64 values basically start in the middle and they are logically
+	 * contiguous to the right of it, wrapping around from -1 to 0, and
+	 * then finishing as S64_MAX (0x7fffffffffffffff) right before
+	 * S64_MIN. We can try drawing the continuity of u64 vs s64 values
+	 * more visually as mapped to sign-agnostic range of hex values.
+	 *
+	 *  u64 start                                               u64 end
+	 *  _______________________________________________________________
+	 * /                                                               \
+	 * 0             0x7fffffffffffffff 0x8000000000000000        U64_MAX
+	 * |-------------------------------|--------------------------------|
+	 * 0                        S64_MAX S64_MIN                        -1
+	 *                                / \
+	 * >------------------------------   ------------------------------->
+	 * s64 continues...        s64 end   s64 start          s64 "midpoint"
+	 *
+	 * What this means is that, in general, we can't always derive
+	 * something new about u64 from any random s64 range, and vice versa.
+	 *
+	 * But we can do that in two particular cases. One is when entire
+	 * u64/s64 range is *entirely* contained within left half of the above
+	 * diagram or when it is *entirely* contained in the right half. I.e.:
+	 *
+	 * |-------------------------------|--------------------------------|
+	 *     ^                   ^            ^                 ^
+	 *     A                   B            C                 D
+	 *
+	 * [A, B] and [C, D] are contained entirely in their respective halves
+	 * and form valid contiguous ranges as both u64 and s64 values. [A, B]
+	 * will be non-negative both as u64 and s64 (and in fact it will be
+	 * identical ranges no matter the signedness). [C, D] treated as s64
+	 * will be a range of negative values, while in u64 it will be
+	 * non-negative range of values larger than 0x8000000000000000.
+	 *
+	 * Now, any other range here can't be represented in both u64 and s64
+	 * simultaneously. E.g., [A, C], [A, D], [B, C], [B, D] are valid
+	 * contiguous u64 ranges, but they are discontinuous in s64. [B, C]
+	 * in s64 would be properly presented as [S64_MIN, C] and [B, S64_MAX],
+	 * for example. Similarly, valid s64 range [D, A] (going from negative
+	 * to positive values), would be two separate [D, U64_MAX] and [0, A]
+	 * ranges as u64. Currently reg_state can't represent two segments per
+	 * numeric domain, so in such situations we can only derive maximal
+	 * possible range ([0, U64_MAX] for u64, and [S64_MIN, S64_MAX] for s64).
+	 *
+	 * So we use these facts to derive umin/umax from smin/smax and vice
+	 * versa only if they stay within the same "half". This is equivalent
+	 * to checking sign bit: lower half will have sign bit as zero, upper
+	 * half have sign bit 1. Below in code we simplify this by just
+	 * casting umin/umax as smin/smax and checking if they form valid
+	 * range, and vice versa. Those are equivalent checks.
+	 */
+	if ((s64)reg->umin_value <= (s64)reg->umax_value) {
+		reg->smin_value = max_t(s64, reg->smin_value, reg->umin_value);
+		reg->smax_value = min_t(s64, reg->smax_value, reg->umax_value);
+	}
+	/* If we cannot cross the sign boundary, then signed and unsigned bounds
 	 * are the same, so combine.  This works even in the negative case, e.g.
 	 * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff.
 	 */
-	if (reg->smin_value >= 0 || reg->smax_value < 0) {
-		reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value,
-							  reg->umin_value);
-		reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value,
-							  reg->umax_value);
-		return;
+	if ((u64)reg->smin_value <= (u64)reg->smax_value) {
+		reg->umin_value = max_t(u64, reg->smin_value, reg->umin_value);
+		reg->umax_value = min_t(u64, reg->smax_value, reg->umax_value);
 	}
-	/* Learn sign from unsigned bounds.  Signed bounds cross the sign
-	 * boundary, so we must be careful.
+}
+
+static void __reg_deduce_mixed_bounds(struct bpf_reg_state *reg)
+{
+	/* Try to tighten 64-bit bounds from 32-bit knowledge, using 32-bit
+	 * values on both sides of 64-bit range in hope to have tigher range.
+	 * E.g., if r1 is [0x1'00000000, 0x3'80000000], and we learn from
+	 * 32-bit signed > 0 operation that s32 bounds are now [1; 0x7fffffff].
+	 * With this, we can substitute 1 as low 32-bits of _low_ 64-bit bound
+	 * (0x100000000 -> 0x100000001) and 0x7fffffff as low 32-bits of
+	 * _high_ 64-bit bound (0x380000000 -> 0x37fffffff) and arrive at a
+	 * better overall bounds for r1 as [0x1'000000001; 0x3'7fffffff].
+	 * We just need to make sure that derived bounds we are intersecting
+	 * with are well-formed ranges in respecitve s64 or u64 domain, just
+	 * like we do with similar kinds of 32-to-64 or 64-to-32 adjustments.
 	 */
-	if ((s64)reg->umax_value >= 0) {
-		/* Positive.  We can't learn anything from the smin, but smax
-		 * is positive, hence safe.
-		 */
-		reg->smin_value = reg->umin_value;
-		reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value,
-							  reg->umax_value);
-	} else if ((s64)reg->umin_value < 0) {
-		/* Negative.  We can't learn anything from the smax, but smin
-		 * is negative, hence safe.
-		 */
-		reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value,
-							  reg->umin_value);
-		reg->smax_value = reg->umax_value;
+	__u64 new_umin, new_umax;
+	__s64 new_smin, new_smax;
+
+	/* u32 -> u64 tightening, it's always well-formed */
+	new_umin = (reg->umin_value & ~0xffffffffULL) | reg->u32_min_value;
+	new_umax = (reg->umax_value & ~0xffffffffULL) | reg->u32_max_value;
+	reg->umin_value = max_t(u64, reg->umin_value, new_umin);
+	reg->umax_value = min_t(u64, reg->umax_value, new_umax);
+	/* u32 -> s64 tightening, u32 range embedded into s64 preserves range validity */
+	new_smin = (reg->smin_value & ~0xffffffffULL) | reg->u32_min_value;
+	new_smax = (reg->smax_value & ~0xffffffffULL) | reg->u32_max_value;
+	reg->smin_value = max_t(s64, reg->smin_value, new_smin);
+	reg->smax_value = min_t(s64, reg->smax_value, new_smax);
+
+	/* if s32 can be treated as valid u32 range, we can use it as well */
+	if ((u32)reg->s32_min_value <= (u32)reg->s32_max_value) {
+		/* s32 -> u64 tightening */
+		new_umin = (reg->umin_value & ~0xffffffffULL) | (u32)reg->s32_min_value;
+		new_umax = (reg->umax_value & ~0xffffffffULL) | (u32)reg->s32_max_value;
+		reg->umin_value = max_t(u64, reg->umin_value, new_umin);
+		reg->umax_value = min_t(u64, reg->umax_value, new_umax);
+		/* s32 -> s64 tightening */
+		new_smin = (reg->smin_value & ~0xffffffffULL) | (u32)reg->s32_min_value;
+		new_smax = (reg->smax_value & ~0xffffffffULL) | (u32)reg->s32_max_value;
+		reg->smin_value = max_t(s64, reg->smin_value, new_smin);
+		reg->smax_value = min_t(s64, reg->smax_value, new_smax);
 	}
 }
 
@@ -2394,6 +2157,7 @@ static void __reg_deduce_bounds(struct bpf_reg_state *reg)
 {
 	__reg32_deduce_bounds(reg);
 	__reg64_deduce_bounds(reg);
+	__reg_deduce_mixed_bounds(reg);
 }
 
 /* Attempts to improve var_off based on unsigned min/max information */
@@ -2415,6 +2179,7 @@ static void reg_bounds_sync(struct bpf_reg_state *reg)
 	__update_reg_bounds(reg);
 	/* We might have learned something about the sign bit. */
 	__reg_deduce_bounds(reg);
+	__reg_deduce_bounds(reg);
 	/* We might have learned some bits from the bounds. */
 	__reg_bound_offset(reg);
 	/* Intersecting with the old var_off might have improved our bounds
@@ -2424,6 +2189,56 @@ static void reg_bounds_sync(struct bpf_reg_state *reg)
 	__update_reg_bounds(reg);
 }
 
+static int reg_bounds_sanity_check(struct bpf_verifier_env *env,
+				   struct bpf_reg_state *reg, const char *ctx)
+{
+	const char *msg;
+
+	if (reg->umin_value > reg->umax_value ||
+	    reg->smin_value > reg->smax_value ||
+	    reg->u32_min_value > reg->u32_max_value ||
+	    reg->s32_min_value > reg->s32_max_value) {
+		    msg = "range bounds violation";
+		    goto out;
+	}
+
+	if (tnum_is_const(reg->var_off)) {
+		u64 uval = reg->var_off.value;
+		s64 sval = (s64)uval;
+
+		if (reg->umin_value != uval || reg->umax_value != uval ||
+		    reg->smin_value != sval || reg->smax_value != sval) {
+			msg = "const tnum out of sync with range bounds";
+			goto out;
+		}
+	}
+
+	if (tnum_subreg_is_const(reg->var_off)) {
+		u32 uval32 = tnum_subreg(reg->var_off).value;
+		s32 sval32 = (s32)uval32;
+
+		if (reg->u32_min_value != uval32 || reg->u32_max_value != uval32 ||
+		    reg->s32_min_value != sval32 || reg->s32_max_value != sval32) {
+			msg = "const subreg tnum out of sync with range bounds";
+			goto out;
+		}
+	}
+
+	return 0;
+out:
+	verbose(env, "REG INVARIANTS VIOLATION (%s): %s u64=[%#llx, %#llx] "
+		"s64=[%#llx, %#llx] u32=[%#x, %#x] s32=[%#x, %#x] var_off=(%#llx, %#llx)\n",
+		ctx, msg, reg->umin_value, reg->umax_value,
+		reg->smin_value, reg->smax_value,
+		reg->u32_min_value, reg->u32_max_value,
+		reg->s32_min_value, reg->s32_max_value,
+		reg->var_off.value, reg->var_off.mask);
+	if (env->test_reg_invariants)
+		return -EFAULT;
+	__mark_reg_unbounded(reg);
+	return 0;
+}
+
 static bool __reg32_bound_s64(s32 a)
 {
 	return a >= 0 && a <= S32_MAX;
@@ -2448,51 +2263,6 @@ static void __reg_assign_32_into_64(struct bpf_reg_state *reg)
 	}
 }
 
-static void __reg_combine_32_into_64(struct bpf_reg_state *reg)
-{
-	/* special case when 64-bit register has upper 32-bit register
-	 * zeroed. Typically happens after zext or <<32, >>32 sequence
-	 * allowing us to use 32-bit bounds directly,
-	 */
-	if (tnum_equals_const(tnum_clear_subreg(reg->var_off), 0)) {
-		__reg_assign_32_into_64(reg);
-	} else {
-		/* Otherwise the best we can do is push lower 32bit known and
-		 * unknown bits into register (var_off set from jmp logic)
-		 * then learn as much as possible from the 64-bit tnum
-		 * known and unknown bits. The previous smin/smax bounds are
-		 * invalid here because of jmp32 compare so mark them unknown
-		 * so they do not impact tnum bounds calculation.
-		 */
-		__mark_reg64_unbounded(reg);
-	}
-	reg_bounds_sync(reg);
-}
-
-static bool __reg64_bound_s32(s64 a)
-{
-	return a >= S32_MIN && a <= S32_MAX;
-}
-
-static bool __reg64_bound_u32(u64 a)
-{
-	return a >= U32_MIN && a <= U32_MAX;
-}
-
-static void __reg_combine_64_into_32(struct bpf_reg_state *reg)
-{
-	__mark_reg32_unbounded(reg);
-	if (__reg64_bound_s32(reg->smin_value) && __reg64_bound_s32(reg->smax_value)) {
-		reg->s32_min_value = (s32)reg->smin_value;
-		reg->s32_max_value = (s32)reg->smax_value;
-	}
-	if (__reg64_bound_u32(reg->umin_value) && __reg64_bound_u32(reg->umax_value)) {
-		reg->u32_min_value = (u32)reg->umin_value;
-		reg->u32_max_value = (u32)reg->umax_value;
-	}
-	reg_bounds_sync(reg);
-}
-
 /* Mark a register as having a completely unknown (scalar) value. */
 static void __mark_reg_unknown(const struct bpf_verifier_env *env,
 			       struct bpf_reg_state *reg)
@@ -2580,6 +2350,11 @@ static void init_reg_state(struct bpf_verifier_env *env,
 	regs[BPF_REG_FP].frameno = state->frameno;
 }
 
+static struct bpf_retval_range retval_range(s32 minval, s32 maxval)
+{
+	return (struct bpf_retval_range){ minval, maxval };
+}
+
 #define BPF_MAIN_FUNC (-1)
 static void init_func_state(struct bpf_verifier_env *env,
 			    struct bpf_func_state *state,
@@ -2588,7 +2363,7 @@ static void init_func_state(struct bpf_verifier_env *env,
 	state->callsite = callsite;
 	state->frameno = frameno;
 	state->subprogno = subprogno;
-	state->callback_ret_range = tnum_range(0, 0);
+	state->callback_ret_range = retval_range(0, 0);
 	init_reg_state(env, state);
 	mark_verifier_state_scratched(env);
 }
@@ -3132,6 +2907,7 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env)
 			if (env->subprog_info[i].start != ex_cb_insn)
 				continue;
 			env->exception_callback_subprog = i;
+			mark_subprog_exc_cb(env, i);
 			break;
 		}
 	}
@@ -3434,13 +3210,11 @@ static void mark_insn_zext(struct bpf_verifier_env *env,
 	reg->subreg_def = DEF_NOT_SUBREG;
 }
 
-static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
-			 enum reg_arg_type t)
+static int __check_reg_arg(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno,
+			   enum reg_arg_type t)
 {
-	struct bpf_verifier_state *vstate = env->cur_state;
-	struct bpf_func_state *state = vstate->frame[vstate->curframe];
 	struct bpf_insn *insn = env->prog->insnsi + env->insn_idx;
-	struct bpf_reg_state *reg, *regs = state->regs;
+	struct bpf_reg_state *reg;
 	bool rw64;
 
 	if (regno >= MAX_BPF_REG) {
@@ -3481,6 +3255,30 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
 	return 0;
 }
 
+static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
+			 enum reg_arg_type t)
+{
+	struct bpf_verifier_state *vstate = env->cur_state;
+	struct bpf_func_state *state = vstate->frame[vstate->curframe];
+
+	return __check_reg_arg(env, state->regs, regno, t);
+}
+
+static int insn_stack_access_flags(int frameno, int spi)
+{
+	return INSN_F_STACK_ACCESS | (spi << INSN_F_SPI_SHIFT) | frameno;
+}
+
+static int insn_stack_access_spi(int insn_flags)
+{
+	return (insn_flags >> INSN_F_SPI_SHIFT) & INSN_F_SPI_MASK;
+}
+
+static int insn_stack_access_frameno(int insn_flags)
+{
+	return insn_flags & INSN_F_FRAMENO_MASK;
+}
+
 static void mark_jmp_point(struct bpf_verifier_env *env, int idx)
 {
 	env->insn_aux_data[idx].jmp_point = true;
@@ -3492,36 +3290,76 @@ static bool is_jmp_point(struct bpf_verifier_env *env, int insn_idx)
 }
 
 /* for any branch, call, exit record the history of jmps in the given state */
-static int push_jmp_history(struct bpf_verifier_env *env,
-			    struct bpf_verifier_state *cur)
+static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur,
+			    int insn_flags)
 {
 	u32 cnt = cur->jmp_history_cnt;
-	struct bpf_idx_pair *p;
+	struct bpf_jmp_history_entry *p;
 	size_t alloc_size;
 
-	if (!is_jmp_point(env, env->insn_idx))
+	/* combine instruction flags if we already recorded this instruction */
+	if (env->cur_hist_ent) {
+		/* atomic instructions push insn_flags twice, for READ and
+		 * WRITE sides, but they should agree on stack slot
+		 */
+		WARN_ONCE((env->cur_hist_ent->flags & insn_flags) &&
+			  (env->cur_hist_ent->flags & insn_flags) != insn_flags,
+			  "verifier insn history bug: insn_idx %d cur flags %x new flags %x\n",
+			  env->insn_idx, env->cur_hist_ent->flags, insn_flags);
+		env->cur_hist_ent->flags |= insn_flags;
 		return 0;
+	}
 
 	cnt++;
 	alloc_size = kmalloc_size_roundup(size_mul(cnt, sizeof(*p)));
 	p = krealloc(cur->jmp_history, alloc_size, GFP_USER);
 	if (!p)
 		return -ENOMEM;
-	p[cnt - 1].idx = env->insn_idx;
-	p[cnt - 1].prev_idx = env->prev_insn_idx;
 	cur->jmp_history = p;
+
+	p = &cur->jmp_history[cnt - 1];
+	p->idx = env->insn_idx;
+	p->prev_idx = env->prev_insn_idx;
+	p->flags = insn_flags;
 	cur->jmp_history_cnt = cnt;
+	env->cur_hist_ent = p;
+
 	return 0;
 }
 
+static struct bpf_jmp_history_entry *get_jmp_hist_entry(struct bpf_verifier_state *st,
+						        u32 hist_end, int insn_idx)
+{
+	if (hist_end > 0 && st->jmp_history[hist_end - 1].idx == insn_idx)
+		return &st->jmp_history[hist_end - 1];
+	return NULL;
+}
+
 /* Backtrack one insn at a time. If idx is not at the top of recorded
  * history then previous instruction came from straight line execution.
+ * Return -ENOENT if we exhausted all instructions within given state.
+ *
+ * It's legal to have a bit of a looping with the same starting and ending
+ * insn index within the same state, e.g.: 3->4->5->3, so just because current
+ * instruction index is the same as state's first_idx doesn't mean we are
+ * done. If there is still some jump history left, we should keep going. We
+ * need to take into account that we might have a jump history between given
+ * state's parent and itself, due to checkpointing. In this case, we'll have
+ * history entry recording a jump from last instruction of parent state and
+ * first instruction of given state.
  */
 static int get_prev_insn_idx(struct bpf_verifier_state *st, int i,
 			     u32 *history)
 {
 	u32 cnt = *history;
 
+	if (i == st->first_insn_idx) {
+		if (cnt == 0)
+			return -ENOENT;
+		if (cnt == 1 && st->jmp_history[0].idx == i)
+			return -ENOENT;
+	}
+
 	if (cnt && st->jmp_history[cnt - 1].idx == i) {
 		i = st->jmp_history[cnt - 1].prev_idx;
 		(*history)--;
@@ -3623,16 +3461,6 @@ static inline void bt_clear_frame_slot(struct backtrack_state *bt, u32 frame, u3
 	bt->stack_masks[frame] &= ~(1ull << slot);
 }
 
-static inline void bt_set_slot(struct backtrack_state *bt, u32 slot)
-{
-	bt_set_frame_slot(bt, bt->frame, slot);
-}
-
-static inline void bt_clear_slot(struct backtrack_state *bt, u32 slot)
-{
-	bt_clear_frame_slot(bt, bt->frame, slot);
-}
-
 static inline u32 bt_frame_reg_mask(struct backtrack_state *bt, u32 frame)
 {
 	return bt->reg_masks[frame];
@@ -3658,9 +3486,9 @@ static inline bool bt_is_reg_set(struct backtrack_state *bt, u32 reg)
 	return bt->reg_masks[bt->frame] & (1 << reg);
 }
 
-static inline bool bt_is_slot_set(struct backtrack_state *bt, u32 slot)
+static inline bool bt_is_frame_slot_set(struct backtrack_state *bt, u32 frame, u32 slot)
 {
-	return bt->stack_masks[bt->frame] & (1ull << slot);
+	return bt->stack_masks[frame] & (1ull << slot);
 }
 
 /* format registers bitmask, e.g., "r0,r2,r4" for 0x15 mask */
@@ -3702,6 +3530,8 @@ static void fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask)
 	}
 }
 
+static bool calls_callback(struct bpf_verifier_env *env, int insn_idx);
+
 /* For given verifier state backtrack_insn() is called from the last insn to
  * the first insn. Its purpose is to compute a bitmask of registers and
  * stack slots that needs precision in the parent verifier state.
@@ -3712,7 +3542,7 @@ static void fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask)
  *   - *was* processed previously during backtracking.
  */
 static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
-			  struct backtrack_state *bt)
+			  struct bpf_jmp_history_entry *hist, struct backtrack_state *bt)
 {
 	const struct bpf_insn_cbs cbs = {
 		.cb_call	= disasm_kfunc_name,
@@ -3725,7 +3555,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 	u8 mode = BPF_MODE(insn->code);
 	u32 dreg = insn->dst_reg;
 	u32 sreg = insn->src_reg;
-	u32 spi, i;
+	u32 spi, i, fr;
 
 	if (insn->code == 0)
 		return 0;
@@ -3786,20 +3616,15 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 		 * by 'precise' mark in corresponding register of this state.
 		 * No further tracking necessary.
 		 */
-		if (insn->src_reg != BPF_REG_FP)
+		if (!hist || !(hist->flags & INSN_F_STACK_ACCESS))
 			return 0;
-
 		/* dreg = *(u64 *)[fp - off] was a fill from the stack.
 		 * that [fp - off] slot contains scalar that needs to be
 		 * tracked with precision
 		 */
-		spi = (-insn->off - 1) / BPF_REG_SIZE;
-		if (spi >= 64) {
-			verbose(env, "BUG spi %d\n", spi);
-			WARN_ONCE(1, "verifier backtracking bug");
-			return -EFAULT;
-		}
-		bt_set_slot(bt, spi);
+		spi = insn_stack_access_spi(hist->flags);
+		fr = insn_stack_access_frameno(hist->flags);
+		bt_set_frame_slot(bt, fr, spi);
 	} else if (class == BPF_STX || class == BPF_ST) {
 		if (bt_is_reg_set(bt, dreg))
 			/* stx & st shouldn't be using _scalar_ dst_reg
@@ -3808,17 +3633,13 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 			 */
 			return -ENOTSUPP;
 		/* scalars can only be spilled into stack */
-		if (insn->dst_reg != BPF_REG_FP)
+		if (!hist || !(hist->flags & INSN_F_STACK_ACCESS))
 			return 0;
-		spi = (-insn->off - 1) / BPF_REG_SIZE;
-		if (spi >= 64) {
-			verbose(env, "BUG spi %d\n", spi);
-			WARN_ONCE(1, "verifier backtracking bug");
-			return -EFAULT;
-		}
-		if (!bt_is_slot_set(bt, spi))
+		spi = insn_stack_access_spi(hist->flags);
+		fr = insn_stack_access_frameno(hist->flags);
+		if (!bt_is_frame_slot_set(bt, fr, spi))
 			return 0;
-		bt_clear_slot(bt, spi);
+		bt_clear_frame_slot(bt, fr, spi);
 		if (class == BPF_STX)
 			bt_set_reg(bt, sreg);
 	} else if (class == BPF_JMP || class == BPF_JMP32) {
@@ -3862,10 +3683,14 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 					WARN_ONCE(1, "verifier backtracking bug");
 					return -EFAULT;
 				}
-				/* we don't track register spills perfectly,
-				 * so fallback to force-precise instead of failing */
-				if (bt_stack_mask(bt) != 0)
-					return -ENOTSUPP;
+				/* we are now tracking register spills correctly,
+				 * so any instance of leftover slots is a bug
+				 */
+				if (bt_stack_mask(bt) != 0) {
+					verbose(env, "BUG stack slots %llx\n", bt_stack_mask(bt));
+					WARN_ONCE(1, "verifier backtracking bug (subprog leftover stack slots)");
+					return -EFAULT;
+				}
 				/* propagate r1-r5 to the caller */
 				for (i = BPF_REG_1; i <= BPF_REG_5; i++) {
 					if (bt_is_reg_set(bt, i)) {
@@ -3877,24 +3702,24 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 					return -EFAULT;
 				return 0;
 			}
-		} else if ((bpf_helper_call(insn) &&
-			    is_callback_calling_function(insn->imm) &&
-			    !is_async_callback_calling_function(insn->imm)) ||
-			   (bpf_pseudo_kfunc_call(insn) && is_callback_calling_kfunc(insn->imm))) {
-			/* callback-calling helper or kfunc call, which means
-			 * we are exiting from subprog, but unlike the subprog
-			 * call handling above, we shouldn't propagate
-			 * precision of r1-r5 (if any requested), as they are
-			 * not actually arguments passed directly to callback
-			 * subprogs
+		} else if (is_sync_callback_calling_insn(insn) && idx != subseq_idx - 1) {
+			/* exit from callback subprog to callback-calling helper or
+			 * kfunc call. Use idx/subseq_idx check to discern it from
+			 * straight line code backtracking.
+			 * Unlike the subprog call handling above, we shouldn't
+			 * propagate precision of r1-r5 (if any requested), as they are
+			 * not actually arguments passed directly to callback subprogs
 			 */
 			if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) {
 				verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
 				WARN_ONCE(1, "verifier backtracking bug");
 				return -EFAULT;
 			}
-			if (bt_stack_mask(bt) != 0)
-				return -ENOTSUPP;
+			if (bt_stack_mask(bt) != 0) {
+				verbose(env, "BUG stack slots %llx\n", bt_stack_mask(bt));
+				WARN_ONCE(1, "verifier backtracking bug (callback leftover stack slots)");
+				return -EFAULT;
+			}
 			/* clear r1-r5 in callback subprog's mask */
 			for (i = BPF_REG_1; i <= BPF_REG_5; i++)
 				bt_clear_reg(bt, i);
@@ -3921,10 +3746,18 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 		} else if (opcode == BPF_EXIT) {
 			bool r0_precise;
 
+			/* Backtracking to a nested function call, 'idx' is a part of
+			 * the inner frame 'subseq_idx' is a part of the outer frame.
+			 * In case of a regular function call, instructions giving
+			 * precision to registers R1-R5 should have been found already.
+			 * In case of a callback, it is ok to have R1-R5 marked for
+			 * backtracking, as these registers are set by the function
+			 * invoking callback.
+			 */
+			if (subseq_idx >= 0 && calls_callback(env, subseq_idx))
+				for (i = BPF_REG_1; i <= BPF_REG_5; i++)
+					bt_clear_reg(bt, i);
 			if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) {
-				/* if backtracing was looking for registers R1-R5
-				 * they should have been found already.
-				 */
 				verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
 				WARN_ONCE(1, "verifier backtracking bug");
 				return -EFAULT;
@@ -4323,6 +4156,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
 	for (;;) {
 		DECLARE_BITMAP(mask, 64);
 		u32 history = st->jmp_history_cnt;
+		struct bpf_jmp_history_entry *hist;
 
 		if (env->log.level & BPF_LOG_LEVEL2) {
 			verbose(env, "mark_precise: frame%d: last_idx %d first_idx %d subseq_idx %d \n",
@@ -4386,7 +4220,8 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
 				err = 0;
 				skip_first = false;
 			} else {
-				err = backtrack_insn(env, i, subseq_idx, bt);
+				hist = get_jmp_hist_entry(st, history, i);
+				err = backtrack_insn(env, i, subseq_idx, hist, bt);
 			}
 			if (err == -ENOTSUPP) {
 				mark_all_scalars_precise(env, env->cur_state);
@@ -4401,10 +4236,10 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
 				 * Nothing to be tracked further in the parent state.
 				 */
 				return 0;
-			if (i == first_idx)
-				break;
 			subseq_idx = i;
 			i = get_prev_insn_idx(st, i, &history);
+			if (i == -ENOENT)
+				break;
 			if (i >= env->prog->len) {
 				/* This can happen if backtracking reached insn 0
 				 * and there are still reg_mask or stack_mask
@@ -4439,22 +4274,10 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
 			bitmap_from_u64(mask, bt_frame_stack_mask(bt, fr));
 			for_each_set_bit(i, mask, 64) {
 				if (i >= func->allocated_stack / BPF_REG_SIZE) {
-					/* the sequence of instructions:
-					 * 2: (bf) r3 = r10
-					 * 3: (7b) *(u64 *)(r3 -8) = r0
-					 * 4: (79) r4 = *(u64 *)(r10 -8)
-					 * doesn't contain jmps. It's backtracked
-					 * as a single block.
-					 * During backtracking insn 3 is not recognized as
-					 * stack access, so at the end of backtracking
-					 * stack slot fp-8 is still marked in stack_mask.
-					 * However the parent state may not have accessed
-					 * fp-8 and it's "unallocated" stack space.
-					 * In such case fallback to conservative.
-					 */
-					mark_all_scalars_precise(env, env->cur_state);
-					bt_reset(bt);
-					return 0;
+					verbose(env, "BUG backtracking (stack slot %d, total slots %d)\n",
+						i, func->allocated_stack / BPF_REG_SIZE);
+					WARN_ONCE(1, "verifier backtracking bug (stack slot out of bounds)");
+					return -EFAULT;
 				}
 
 				if (!is_spilled_scalar_reg(&func->stack[i])) {
@@ -4544,9 +4367,17 @@ static bool register_is_null(struct bpf_reg_state *reg)
 	return reg->type == SCALAR_VALUE && tnum_equals_const(reg->var_off, 0);
 }
 
-static bool register_is_const(struct bpf_reg_state *reg)
+/* check if register is a constant scalar value */
+static bool is_reg_const(struct bpf_reg_state *reg, bool subreg32)
 {
-	return reg->type == SCALAR_VALUE && tnum_is_const(reg->var_off);
+	return reg->type == SCALAR_VALUE &&
+	       tnum_is_const(subreg32 ? tnum_subreg(reg->var_off) : reg->var_off);
+}
+
+/* assuming is_reg_const() is true, return constant value of a register */
+static u64 reg_const_value(struct bpf_reg_state *reg, bool subreg32)
+{
+	return subreg32 ? tnum_subreg(reg->var_off).value : reg->var_off.value;
 }
 
 static bool __is_scalar_unbounded(struct bpf_reg_state *reg)
@@ -4583,7 +4414,8 @@ static void copy_register_state(struct bpf_reg_state *dst, const struct bpf_reg_
 	dst->live = live;
 }
 
-static void save_register_state(struct bpf_func_state *state,
+static void save_register_state(struct bpf_verifier_env *env,
+				struct bpf_func_state *state,
 				int spi, struct bpf_reg_state *reg,
 				int size)
 {
@@ -4598,7 +4430,7 @@ static void save_register_state(struct bpf_func_state *state,
 
 	/* size < 8 bytes spill */
 	for (; i; i--)
-		scrub_spilled_slot(&state->stack[spi].slot_type[i - 1]);
+		mark_stack_slot_misc(env, &state->stack[spi].slot_type[i - 1]);
 }
 
 static bool is_bpf_st_mem(struct bpf_insn *insn)
@@ -4619,16 +4451,13 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 	int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err;
 	struct bpf_insn *insn = &env->prog->insnsi[insn_idx];
 	struct bpf_reg_state *reg = NULL;
-	u32 dst_reg = insn->dst_reg;
+	int insn_flags = insn_stack_access_flags(state->frameno, spi);
 
-	err = grow_stack_state(state, round_up(slot + 1, BPF_REG_SIZE));
-	if (err)
-		return err;
 	/* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0,
 	 * so it's aligned access and [off, off + size) are within stack limits
 	 */
 	if (!env->allow_ptr_leaks &&
-	    state->stack[spi].slot_type[0] == STACK_SPILL &&
+	    is_spilled_reg(&state->stack[spi]) &&
 	    size != BPF_REG_SIZE) {
 		verbose(env, "attempt to corrupt spilled pointer on stack\n");
 		return -EACCES;
@@ -4658,20 +4487,8 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 		return err;
 
 	mark_stack_slot_scratched(env, spi);
-	if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) &&
-	    !register_is_null(reg) && env->bpf_capable) {
-		if (dst_reg != BPF_REG_FP) {
-			/* The backtracking logic can only recognize explicit
-			 * stack slot address like [fp - 8]. Other spill of
-			 * scalar via different register has to be conservative.
-			 * Backtrack from here and mark all registers as precise
-			 * that contributed into 'reg' being a constant.
-			 */
-			err = mark_chain_precision(env, value_regno);
-			if (err)
-				return err;
-		}
-		save_register_state(state, spi, reg, size);
+	if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) && env->bpf_capable) {
+		save_register_state(env, state, spi, reg, size);
 		/* Break the relation on a narrowing spill. */
 		if (fls64(reg->umax_value) > BITS_PER_BYTE * size)
 			state->stack[spi].spilled_ptr.id = 0;
@@ -4681,7 +4498,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 
 		__mark_reg_known(&fake_reg, insn->imm);
 		fake_reg.type = SCALAR_VALUE;
-		save_register_state(state, spi, &fake_reg, size);
+		save_register_state(env, state, spi, &fake_reg, size);
 	} else if (reg && is_spillable_regtype(reg->type)) {
 		/* register containing pointer is being spilled into stack */
 		if (size != BPF_REG_SIZE) {
@@ -4693,7 +4510,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 			verbose(env, "cannot spill pointers to stack into stack frame of the caller\n");
 			return -EINVAL;
 		}
-		save_register_state(state, spi, reg, size);
+		save_register_state(env, state, spi, reg, size);
 	} else {
 		u8 type = STACK_MISC;
 
@@ -4718,7 +4535,12 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 		/* when we zero initialize stack slots mark them as such */
 		if ((reg && register_is_null(reg)) ||
 		    (!reg && is_bpf_st_mem(insn) && insn->imm == 0)) {
-			/* backtracking doesn't work for STACK_ZERO yet. */
+			/* STACK_ZERO case happened because register spill
+			 * wasn't properly aligned at the stack slot boundary,
+			 * so it's not a register spill anymore; force
+			 * originating register to be precise to make
+			 * STACK_ZERO correct for subsequent states
+			 */
 			err = mark_chain_precision(env, value_regno);
 			if (err)
 				return err;
@@ -4727,9 +4549,12 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 
 		/* Mark slots affected by this stack write. */
 		for (i = 0; i < size; i++)
-			state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] =
-				type;
+			state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] = type;
+		insn_flags = 0; /* not a register spill */
 	}
+
+	if (insn_flags)
+		return push_jmp_history(env, env->cur_state, insn_flags);
 	return 0;
 }
 
@@ -4779,10 +4604,6 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env,
 	    (!value_reg && is_bpf_st_mem(insn) && insn->imm == 0))
 		writing_zero = true;
 
-	err = grow_stack_state(state, round_up(-min_off, BPF_REG_SIZE));
-	if (err)
-		return err;
-
 	for (i = min_off; i < max_off; i++) {
 		int spi;
 
@@ -4881,21 +4702,10 @@ static void mark_reg_stack_read(struct bpf_verifier_env *env,
 		zeros++;
 	}
 	if (zeros == max_off - min_off) {
-		/* any access_size read into register is zero extended,
-		 * so the whole register == const_zero
+		/* Any access_size read into register is zero extended,
+		 * so the whole register == const_zero.
 		 */
-		__mark_reg_const_zero(&state->regs[dst_regno]);
-		/* backtracking doesn't support STACK_ZERO yet,
-		 * so mark it precise here, so that later
-		 * backtracking can stop here.
-		 * Backtracking may not need this if this register
-		 * doesn't participate in pointer adjustment.
-		 * Forward propagation of precise flag is not
-		 * necessary either. This mark is only to stop
-		 * backtracking. Any register that contributed
-		 * to const 0 was marked precise before spill.
-		 */
-		state->regs[dst_regno].precise = true;
+		__mark_reg_const_zero(env, &state->regs[dst_regno]);
 	} else {
 		/* have read misc data from the stack */
 		mark_reg_unknown(env, state->regs, dst_regno);
@@ -4922,6 +4732,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 	int i, slot = -off - 1, spi = slot / BPF_REG_SIZE;
 	struct bpf_reg_state *reg;
 	u8 *stype, type;
+	int insn_flags = insn_stack_access_flags(reg_state->frameno, spi);
 
 	stype = reg_state->stack[spi].slot_type;
 	reg = &reg_state->stack[spi].spilled_ptr;
@@ -4954,25 +4765,42 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 				copy_register_state(&state->regs[dst_regno], reg);
 				state->regs[dst_regno].subreg_def = subreg_def;
 			} else {
+				int spill_cnt = 0, zero_cnt = 0;
+
 				for (i = 0; i < size; i++) {
 					type = stype[(slot - i) % BPF_REG_SIZE];
-					if (type == STACK_SPILL)
+					if (type == STACK_SPILL) {
+						spill_cnt++;
 						continue;
+					}
 					if (type == STACK_MISC)
 						continue;
+					if (type == STACK_ZERO) {
+						zero_cnt++;
+						continue;
+					}
 					if (type == STACK_INVALID && env->allow_uninit_stack)
 						continue;
 					verbose(env, "invalid read from stack off %d+%d size %d\n",
 						off, i, size);
 					return -EACCES;
 				}
-				mark_reg_unknown(env, state->regs, dst_regno);
+
+				if (spill_cnt == size &&
+				    tnum_is_const(reg->var_off) && reg->var_off.value == 0) {
+					__mark_reg_const_zero(env, &state->regs[dst_regno]);
+					/* this IS register fill, so keep insn_flags */
+				} else if (zero_cnt == size) {
+					/* similarly to mark_reg_stack_read(), preserve zeroes */
+					__mark_reg_const_zero(env, &state->regs[dst_regno]);
+					insn_flags = 0; /* not restoring original register state */
+				} else {
+					mark_reg_unknown(env, state->regs, dst_regno);
+					insn_flags = 0; /* not restoring original register state */
+				}
 			}
 			state->regs[dst_regno].live |= REG_LIVE_WRITTEN;
-			return 0;
-		}
-
-		if (dst_regno >= 0) {
+		} else if (dst_regno >= 0) {
 			/* restore register state from stack */
 			copy_register_state(&state->regs[dst_regno], reg);
 			/* mark reg as written since spilled pointer state likely
@@ -5008,7 +4836,10 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 		mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
 		if (dst_regno >= 0)
 			mark_reg_stack_read(env, reg_state, off, off + size, dst_regno);
+		insn_flags = 0; /* we are not restoring spilled register */
 	}
+	if (insn_flags)
+		return push_jmp_history(env, env->cur_state, insn_flags);
 	return 0;
 }
 
@@ -5298,8 +5129,8 @@ static int __check_ptr_off_reg(struct bpf_verifier_env *env,
 	return 0;
 }
 
-int check_ptr_off_reg(struct bpf_verifier_env *env,
-		      const struct bpf_reg_state *reg, int regno)
+static int check_ptr_off_reg(struct bpf_verifier_env *env,
+		             const struct bpf_reg_state *reg, int regno)
 {
 	return __check_ptr_off_reg(env, reg, regno, false);
 }
@@ -5403,10 +5234,23 @@ BTF_SET_END(rcu_protected_types)
 static bool rcu_protected_object(const struct btf *btf, u32 btf_id)
 {
 	if (!btf_is_kernel(btf))
-		return false;
+		return true;
 	return btf_id_set_contains(&rcu_protected_types, btf_id);
 }
 
+static struct btf_record *kptr_pointee_btf_record(struct btf_field *kptr_field)
+{
+	struct btf_struct_meta *meta;
+
+	if (btf_is_kernel(kptr_field->kptr.btf))
+		return NULL;
+
+	meta = btf_find_struct_meta(kptr_field->kptr.btf,
+				    kptr_field->kptr.btf_id);
+
+	return meta ? meta->record : NULL;
+}
+
 static bool rcu_safe_kptr(const struct btf_field *field)
 {
 	const struct btf_field_kptr *kptr = &field->kptr;
@@ -5417,12 +5261,25 @@ static bool rcu_safe_kptr(const struct btf_field *field)
 
 static u32 btf_ld_kptr_type(struct bpf_verifier_env *env, struct btf_field *kptr_field)
 {
+	struct btf_record *rec;
+	u32 ret;
+
+	ret = PTR_MAYBE_NULL;
 	if (rcu_safe_kptr(kptr_field) && in_rcu_cs(env)) {
-		if (kptr_field->type != BPF_KPTR_PERCPU)
-			return PTR_MAYBE_NULL | MEM_RCU;
-		return PTR_MAYBE_NULL | MEM_RCU | MEM_PERCPU;
+		ret |= MEM_RCU;
+		if (kptr_field->type == BPF_KPTR_PERCPU)
+			ret |= MEM_PERCPU;
+		else if (!btf_is_kernel(kptr_field->kptr.btf))
+			ret |= MEM_ALLOC;
+
+		rec = kptr_pointee_btf_record(kptr_field);
+		if (rec && btf_record_has_field(rec, BPF_GRAPH_NODE))
+			ret |= NON_OWN_REF;
+	} else {
+		ret |= PTR_UNTRUSTED;
 	}
-	return PTR_MAYBE_NULL | PTR_UNTRUSTED;
+
+	return ret;
 }
 
 static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno,
@@ -5911,20 +5768,6 @@ static int check_ptr_alignment(struct bpf_verifier_env *env,
 					   strict);
 }
 
-static int update_stack_depth(struct bpf_verifier_env *env,
-			      const struct bpf_func_state *func,
-			      int off)
-{
-	u16 stack = env->subprog_info[func->subprogno].stack_depth;
-
-	if (stack >= -off)
-		return 0;
-
-	/* update known max for given subprogram */
-	env->subprog_info[func->subprogno].stack_depth = -off;
-	return 0;
-}
-
 /* starting from main bpf function walk all instructions of the function
  * and recursively walk all callees that given function can call.
  * Ignore jump and exit insns.
@@ -6196,9 +6039,10 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
 	 * values are also truncated so we push 64-bit bounds into
 	 * 32-bit bounds. Above were truncated < 32-bits already.
 	 */
-	if (size >= 4)
-		return;
-	__reg_combine_64_into_32(reg);
+	if (size < 4) {
+		__mark_reg32_unbounded(reg);
+		reg_bounds_sync(reg);
+	}
 }
 
 static void set_sext64_default_val(struct bpf_reg_state *reg, int size)
@@ -6713,13 +6557,14 @@ static int check_ptr_to_map_access(struct bpf_verifier_env *env,
  * The minimum valid offset is -MAX_BPF_STACK for writes, and
  * -state->allocated_stack for reads.
  */
-static int check_stack_slot_within_bounds(int off,
-					  struct bpf_func_state *state,
-					  enum bpf_access_type t)
+static int check_stack_slot_within_bounds(struct bpf_verifier_env *env,
+                                          s64 off,
+                                          struct bpf_func_state *state,
+                                          enum bpf_access_type t)
 {
 	int min_valid_off;
 
-	if (t == BPF_WRITE)
+	if (t == BPF_WRITE || env->allow_uninit_stack)
 		min_valid_off = -MAX_BPF_STACK;
 	else
 		min_valid_off = -state->allocated_stack;
@@ -6742,7 +6587,7 @@ static int check_stack_access_within_bounds(
 	struct bpf_reg_state *regs = cur_regs(env);
 	struct bpf_reg_state *reg = regs + regno;
 	struct bpf_func_state *state = func(env, reg);
-	int min_off, max_off;
+	s64 min_off, max_off;
 	int err;
 	char *err_extra;
 
@@ -6755,11 +6600,8 @@ static int check_stack_access_within_bounds(
 		err_extra = " write to";
 
 	if (tnum_is_const(reg->var_off)) {
-		min_off = reg->var_off.value + off;
-		if (access_size > 0)
-			max_off = min_off + access_size - 1;
-		else
-			max_off = min_off;
+		min_off = (s64)reg->var_off.value + off;
+		max_off = min_off + access_size;
 	} else {
 		if (reg->smax_value >= BPF_MAX_VAR_OFF ||
 		    reg->smin_value <= -BPF_MAX_VAR_OFF) {
@@ -6768,15 +6610,12 @@ static int check_stack_access_within_bounds(
 			return -EACCES;
 		}
 		min_off = reg->smin_value + off;
-		if (access_size > 0)
-			max_off = reg->smax_value + off + access_size - 1;
-		else
-			max_off = min_off;
+		max_off = reg->smax_value + off + access_size;
 	}
 
-	err = check_stack_slot_within_bounds(min_off, state, type);
-	if (!err)
-		err = check_stack_slot_within_bounds(max_off, state, type);
+	err = check_stack_slot_within_bounds(env, min_off, state, type);
+	if (!err && max_off > 0)
+		err = -EINVAL; /* out of stack access into non-negative offsets */
 
 	if (err) {
 		if (tnum_is_const(reg->var_off)) {
@@ -6786,11 +6625,16 @@ static int check_stack_access_within_bounds(
 			char tn_buf[48];
 
 			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
-			verbose(env, "invalid variable-offset%s stack R%d var_off=%s size=%d\n",
-				err_extra, regno, tn_buf, access_size);
+			verbose(env, "invalid variable-offset%s stack R%d var_off=%s off=%d size=%d\n",
+				err_extra, regno, tn_buf, off, access_size);
 		}
+		return err;
 	}
-	return err;
+
+	/* Note that there is no stack access with offset zero, so the needed stack
+	 * size is -min_off, not -min_off+1.
+	 */
+	return grow_stack_state(env, state, -min_off /* size */);
 }
 
 /* check whether memory at (regno + off) is accessible for t = (read | write)
@@ -6805,7 +6649,6 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 {
 	struct bpf_reg_state *regs = cur_regs(env);
 	struct bpf_reg_state *reg = regs + regno;
-	struct bpf_func_state *state;
 	int size, err = 0;
 
 	size = bpf_size_to_bytes(bpf_size);
@@ -6948,11 +6791,6 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		if (err)
 			return err;
 
-		state = func(env, reg);
-		err = update_stack_depth(env, state, off);
-		if (err)
-			return err;
-
 		if (t == BPF_READ)
 			err = check_stack_read(env, regno, off, size,
 					       value_regno);
@@ -7141,13 +6979,13 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 			       BPF_SIZE(insn->code), BPF_WRITE, -1, true, false);
 	if (err)
 		return err;
-
 	return 0;
 }
 
 /* When register 'regno' is used to read the stack (either directly or through
  * a helper function) make sure that it's within stack boundary and, depending
- * on the access type, that all elements of the stack are initialized.
+ * on the access type and privileges, that all elements of the stack are
+ * initialized.
  *
  * 'off' includes 'regno->off', but not its dynamic part (if any).
  *
@@ -7255,8 +7093,11 @@ static int check_stack_range_initialized(
 
 		slot = -i - 1;
 		spi = slot / BPF_REG_SIZE;
-		if (state->allocated_stack <= slot)
-			goto err;
+		if (state->allocated_stack <= slot) {
+			verbose(env, "verifier bug: allocated_stack too small");
+			return -EFAULT;
+		}
+
 		stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE];
 		if (*stype == STACK_MISC)
 			goto mark;
@@ -7280,7 +7121,6 @@ static int check_stack_range_initialized(
 			goto mark;
 		}
 
-err:
 		if (tnum_is_const(reg->var_off)) {
 			verbose(env, "invalid%s read from stack R%d off %d+%d size %d\n",
 				err_extra, regno, min_off, i - min_off, access_size);
@@ -7305,7 +7145,7 @@ mark:
 		 * helper may write to the entire memory range.
 		 */
 	}
-	return update_stack_depth(env, state, min_off);
+	return 0;
 }
 
 static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
@@ -7401,6 +7241,12 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
 	}
 }
 
+/* verify arguments to helpers or kfuncs consisting of a pointer and an access
+ * size.
+ *
+ * @regno is the register containing the access size. regno-1 is the register
+ * containing the pointer.
+ */
 static int check_mem_size_reg(struct bpf_verifier_env *env,
 			      struct bpf_reg_state *reg, u32 regno,
 			      bool zero_size_allowed,
@@ -7435,12 +7281,10 @@ static int check_mem_size_reg(struct bpf_verifier_env *env,
 		return -EACCES;
 	}
 
-	if (reg->umin_value == 0) {
-		err = check_helper_mem_access(env, regno - 1, 0,
-					      zero_size_allowed,
-					      meta);
-		if (err)
-			return err;
+	if (reg->umin_value == 0 && !zero_size_allowed) {
+		verbose(env, "R%d invalid zero-sized read: u64=[%lld,%lld]\n",
+			regno, reg->umin_value, reg->umax_value);
+		return -EACCES;
 	}
 
 	if (reg->umax_value >= BPF_MAX_VAR_SIZ) {
@@ -7456,8 +7300,8 @@ static int check_mem_size_reg(struct bpf_verifier_env *env,
 	return err;
 }
 
-int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
-		   u32 regno, u32 mem_size)
+static int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
+			 u32 regno, u32 mem_size)
 {
 	bool may_be_null = type_may_be_null(reg->type);
 	struct bpf_reg_state saved_reg;
@@ -8102,7 +7946,7 @@ static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx,
 	/* switch to DRAINED state, but keep the depth unchanged */
 	/* mark current iter state as drained and assume returned NULL */
 	cur_iter->iter.state = BPF_ITER_STATE_DRAINED;
-	__mark_reg_const_zero(&cur_fr->regs[BPF_REG_0]);
+	__mark_reg_const_zero(env, &cur_fr->regs[BPF_REG_0]);
 
 	return 0;
 }
@@ -8442,9 +8286,9 @@ reg_find_field_offset(const struct bpf_reg_state *reg, s32 off, u32 fields)
 	return field;
 }
 
-int check_func_arg_reg_off(struct bpf_verifier_env *env,
-			   const struct bpf_reg_state *reg, int regno,
-			   enum bpf_arg_type arg_type)
+static int check_func_arg_reg_off(struct bpf_verifier_env *env,
+				  const struct bpf_reg_state *reg, int regno,
+				  enum bpf_arg_type arg_type)
 {
 	u32 type = reg->type;
 
@@ -8578,6 +8422,54 @@ static enum bpf_dynptr_type dynptr_get_type(struct bpf_verifier_env *env,
 	return state->stack[spi].spilled_ptr.dynptr.type;
 }
 
+static int check_reg_const_str(struct bpf_verifier_env *env,
+			       struct bpf_reg_state *reg, u32 regno)
+{
+	struct bpf_map *map = reg->map_ptr;
+	int err;
+	int map_off;
+	u64 map_addr;
+	char *str_ptr;
+
+	if (reg->type != PTR_TO_MAP_VALUE)
+		return -EINVAL;
+
+	if (!bpf_map_is_rdonly(map)) {
+		verbose(env, "R%d does not point to a readonly map'\n", regno);
+		return -EACCES;
+	}
+
+	if (!tnum_is_const(reg->var_off)) {
+		verbose(env, "R%d is not a constant address'\n", regno);
+		return -EACCES;
+	}
+
+	if (!map->ops->map_direct_value_addr) {
+		verbose(env, "no direct value access support for this map type\n");
+		return -EACCES;
+	}
+
+	err = check_map_access(env, regno, reg->off,
+			       map->value_size - reg->off, false,
+			       ACCESS_HELPER);
+	if (err)
+		return err;
+
+	map_off = reg->off + reg->var_off.value;
+	err = map->ops->map_direct_value_addr(map, &map_addr, map_off);
+	if (err) {
+		verbose(env, "direct value access on string failed\n");
+		return err;
+	}
+
+	str_ptr = (char *)(long)(map_addr);
+	if (!strnchr(str_ptr + map_off, map->value_size - map_off, 0)) {
+		verbose(env, "string is not zero-terminated\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 			  struct bpf_call_arg_meta *meta,
 			  const struct bpf_func_proto *fn,
@@ -8822,44 +8714,9 @@ skip_type_check:
 	}
 	case ARG_PTR_TO_CONST_STR:
 	{
-		struct bpf_map *map = reg->map_ptr;
-		int map_off;
-		u64 map_addr;
-		char *str_ptr;
-
-		if (!bpf_map_is_rdonly(map)) {
-			verbose(env, "R%d does not point to a readonly map'\n", regno);
-			return -EACCES;
-		}
-
-		if (!tnum_is_const(reg->var_off)) {
-			verbose(env, "R%d is not a constant address'\n", regno);
-			return -EACCES;
-		}
-
-		if (!map->ops->map_direct_value_addr) {
-			verbose(env, "no direct value access support for this map type\n");
-			return -EACCES;
-		}
-
-		err = check_map_access(env, regno, reg->off,
-				       map->value_size - reg->off, false,
-				       ACCESS_HELPER);
+		err = check_reg_const_str(env, reg, regno);
 		if (err)
 			return err;
-
-		map_off = reg->off + reg->var_off.value;
-		err = map->ops->map_direct_value_addr(map, &map_addr, map_off);
-		if (err) {
-			verbose(env, "direct value access on string failed\n");
-			return err;
-		}
-
-		str_ptr = (char *)(long)(map_addr);
-		if (!strnchr(str_ptr + map_off, map->value_size - map_off, 0)) {
-			verbose(env, "string is not zero-terminated\n");
-			return -EINVAL;
-		}
 		break;
 	}
 	case ARG_PTR_TO_KPTR:
@@ -9328,7 +9185,7 @@ static void clear_caller_saved_regs(struct bpf_verifier_env *env,
 	/* after the call registers r0 - r5 were scratched */
 	for (i = 0; i < CALLER_SAVED_REGS; i++) {
 		mark_reg_not_init(env, regs, caller_saved[i]);
-		check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
+		__check_reg_arg(env, regs, caller_saved[i], DST_OP_NO_MARK);
 	}
 }
 
@@ -9341,11 +9198,10 @@ static int set_callee_state(struct bpf_verifier_env *env,
 			    struct bpf_func_state *caller,
 			    struct bpf_func_state *callee, int insn_idx);
 
-static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
-			     int *insn_idx, int subprog,
-			     set_callee_state_fn set_callee_state_cb)
+static int setup_func_entry(struct bpf_verifier_env *env, int subprog, int callsite,
+			    set_callee_state_fn set_callee_state_cb,
+			    struct bpf_verifier_state *state)
 {
-	struct bpf_verifier_state *state = env->cur_state;
 	struct bpf_func_state *caller, *callee;
 	int err;
 
@@ -9355,54 +9211,168 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		return -E2BIG;
 	}
 
-	caller = state->frame[state->curframe];
 	if (state->frame[state->curframe + 1]) {
 		verbose(env, "verifier bug. Frame %d already allocated\n",
 			state->curframe + 1);
 		return -EFAULT;
 	}
 
-	err = btf_check_subprog_call(env, subprog, caller->regs);
-	if (err == -EFAULT)
-		return err;
-	if (subprog_is_global(env, subprog)) {
-		if (err) {
-			verbose(env, "Caller passes invalid args into func#%d\n",
-				subprog);
-			return err;
-		} else {
-			if (env->log.level & BPF_LOG_LEVEL)
-				verbose(env,
-					"Func#%d is global and valid. Skipping.\n",
-					subprog);
-			clear_caller_saved_regs(env, caller->regs);
+	caller = state->frame[state->curframe];
+	callee = kzalloc(sizeof(*callee), GFP_KERNEL);
+	if (!callee)
+		return -ENOMEM;
+	state->frame[state->curframe + 1] = callee;
 
-			/* All global functions return a 64-bit SCALAR_VALUE */
-			mark_reg_unknown(env, caller->regs, BPF_REG_0);
-			caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG;
+	/* callee cannot access r0, r6 - r9 for reading and has to write
+	 * into its own stack before reading from it.
+	 * callee can read/write into caller's stack
+	 */
+	init_func_state(env, callee,
+			/* remember the callsite, it will be used by bpf_exit */
+			callsite,
+			state->curframe + 1 /* frameno within this callchain */,
+			subprog /* subprog number within this prog */);
+	/* Transfer references to the callee */
+	err = copy_reference_state(callee, caller);
+	err = err ?: set_callee_state_cb(env, caller, callee, callsite);
+	if (err)
+		goto err_out;
 
-			/* continue with next insn after call */
-			return 0;
+	/* only increment it after check_reg_arg() finished */
+	state->curframe++;
+
+	return 0;
+
+err_out:
+	free_func_state(callee);
+	state->frame[state->curframe + 1] = NULL;
+	return err;
+}
+
+static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog,
+				    const struct btf *btf,
+				    struct bpf_reg_state *regs)
+{
+	struct bpf_subprog_info *sub = subprog_info(env, subprog);
+	struct bpf_verifier_log *log = &env->log;
+	u32 i;
+	int ret;
+
+	ret = btf_prepare_func_args(env, subprog);
+	if (ret)
+		return ret;
+
+	/* check that BTF function arguments match actual types that the
+	 * verifier sees.
+	 */
+	for (i = 0; i < sub->arg_cnt; i++) {
+		u32 regno = i + 1;
+		struct bpf_reg_state *reg = &regs[regno];
+		struct bpf_subprog_arg_info *arg = &sub->args[i];
+
+		if (arg->arg_type == ARG_ANYTHING) {
+			if (reg->type != SCALAR_VALUE) {
+				bpf_log(log, "R%d is not a scalar\n", regno);
+				return -EINVAL;
+			}
+		} else if (arg->arg_type == ARG_PTR_TO_CTX) {
+			ret = check_func_arg_reg_off(env, reg, regno, ARG_DONTCARE);
+			if (ret < 0)
+				return ret;
+			/* If function expects ctx type in BTF check that caller
+			 * is passing PTR_TO_CTX.
+			 */
+			if (reg->type != PTR_TO_CTX) {
+				bpf_log(log, "arg#%d expects pointer to ctx\n", i);
+				return -EINVAL;
+			}
+		} else if (base_type(arg->arg_type) == ARG_PTR_TO_MEM) {
+			ret = check_func_arg_reg_off(env, reg, regno, ARG_DONTCARE);
+			if (ret < 0)
+				return ret;
+			if (check_mem_reg(env, reg, regno, arg->mem_size))
+				return -EINVAL;
+			if (!(arg->arg_type & PTR_MAYBE_NULL) && (reg->type & PTR_MAYBE_NULL)) {
+				bpf_log(log, "arg#%d is expected to be non-NULL\n", i);
+				return -EINVAL;
+			}
+		} else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) {
+			ret = process_dynptr_func(env, regno, -1, arg->arg_type, 0);
+			if (ret)
+				return ret;
+		} else {
+			bpf_log(log, "verifier bug: unrecognized arg#%d type %d\n",
+				i, arg->arg_type);
+			return -EFAULT;
 		}
 	}
 
+	return 0;
+}
+
+/* Compare BTF of a function call with given bpf_reg_state.
+ * Returns:
+ * EFAULT - there is a verifier bug. Abort verification.
+ * EINVAL - there is a type mismatch or BTF is not available.
+ * 0 - BTF matches with what bpf_reg_state expects.
+ * Only PTR_TO_CTX and SCALAR_VALUE states are recognized.
+ */
+static int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
+				  struct bpf_reg_state *regs)
+{
+	struct bpf_prog *prog = env->prog;
+	struct btf *btf = prog->aux->btf;
+	u32 btf_id;
+	int err;
+
+	if (!prog->aux->func_info)
+		return -EINVAL;
+
+	btf_id = prog->aux->func_info[subprog].type_id;
+	if (!btf_id)
+		return -EFAULT;
+
+	if (prog->aux->func_info_aux[subprog].unreliable)
+		return -EINVAL;
+
+	err = btf_check_func_arg_match(env, subprog, btf, regs);
+	/* Compiler optimizations can remove arguments from static functions
+	 * or mismatched type can be passed into a global function.
+	 * In such cases mark the function as unreliable from BTF point of view.
+	 */
+	if (err)
+		prog->aux->func_info_aux[subprog].unreliable = true;
+	return err;
+}
+
+static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
+			      int insn_idx, int subprog,
+			      set_callee_state_fn set_callee_state_cb)
+{
+	struct bpf_verifier_state *state = env->cur_state, *callback_state;
+	struct bpf_func_state *caller, *callee;
+	int err;
+
+	caller = state->frame[state->curframe];
+	err = btf_check_subprog_call(env, subprog, caller->regs);
+	if (err == -EFAULT)
+		return err;
+
 	/* set_callee_state is used for direct subprog calls, but we are
 	 * interested in validating only BPF helpers that can call subprogs as
 	 * callbacks
 	 */
-	if (set_callee_state_cb != set_callee_state) {
-		env->subprog_info[subprog].is_cb = true;
-		if (bpf_pseudo_kfunc_call(insn) &&
-		    !is_callback_calling_kfunc(insn->imm)) {
-			verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n",
-				func_id_name(insn->imm), insn->imm);
-			return -EFAULT;
-		} else if (!bpf_pseudo_kfunc_call(insn) &&
-			   !is_callback_calling_function(insn->imm)) { /* helper */
-			verbose(env, "verifier bug: helper %s#%d not marked as callback-calling\n",
-				func_id_name(insn->imm), insn->imm);
-			return -EFAULT;
-		}
+	env->subprog_info[subprog].is_cb = true;
+	if (bpf_pseudo_kfunc_call(insn) &&
+	    !is_sync_callback_calling_kfunc(insn->imm)) {
+		verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n",
+			func_id_name(insn->imm), insn->imm);
+		return -EFAULT;
+	} else if (!bpf_pseudo_kfunc_call(insn) &&
+		   !is_callback_calling_function(insn->imm)) { /* helper */
+		verbose(env, "verifier bug: helper %s#%d not marked as callback-calling\n",
+			func_id_name(insn->imm), insn->imm);
+		return -EFAULT;
 	}
 
 	if (insn->code == (BPF_JMP | BPF_CALL) &&
@@ -9413,53 +9383,88 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		/* there is no real recursion here. timer callbacks are async */
 		env->subprog_info[subprog].is_async_cb = true;
 		async_cb = push_async_cb(env, env->subprog_info[subprog].start,
-					 *insn_idx, subprog);
+					 insn_idx, subprog);
 		if (!async_cb)
 			return -EFAULT;
 		callee = async_cb->frame[0];
 		callee->async_entry_cnt = caller->async_entry_cnt + 1;
 
 		/* Convert bpf_timer_set_callback() args into timer callback args */
-		err = set_callee_state_cb(env, caller, callee, *insn_idx);
+		err = set_callee_state_cb(env, caller, callee, insn_idx);
 		if (err)
 			return err;
 
+		return 0;
+	}
+
+	/* for callback functions enqueue entry to callback and
+	 * proceed with next instruction within current frame.
+	 */
+	callback_state = push_stack(env, env->subprog_info[subprog].start, insn_idx, false);
+	if (!callback_state)
+		return -ENOMEM;
+
+	err = setup_func_entry(env, subprog, insn_idx, set_callee_state_cb,
+			       callback_state);
+	if (err)
+		return err;
+
+	callback_state->callback_unroll_depth++;
+	callback_state->frame[callback_state->curframe - 1]->callback_depth++;
+	caller->callback_depth = 0;
+	return 0;
+}
+
+static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
+			   int *insn_idx)
+{
+	struct bpf_verifier_state *state = env->cur_state;
+	struct bpf_func_state *caller;
+	int err, subprog, target_insn;
+
+	target_insn = *insn_idx + insn->imm + 1;
+	subprog = find_subprog(env, target_insn);
+	if (subprog < 0) {
+		verbose(env, "verifier bug. No program starts at insn %d\n", target_insn);
+		return -EFAULT;
+	}
+
+	caller = state->frame[state->curframe];
+	err = btf_check_subprog_call(env, subprog, caller->regs);
+	if (err == -EFAULT)
+		return err;
+	if (subprog_is_global(env, subprog)) {
+		const char *sub_name = subprog_name(env, subprog);
+
+		if (err) {
+			verbose(env, "Caller passes invalid args into func#%d ('%s')\n",
+				subprog, sub_name);
+			return err;
+		}
+
+		verbose(env, "Func#%d ('%s') is global and assumed valid.\n",
+			subprog, sub_name);
+		/* mark global subprog for verifying after main prog */
+		subprog_aux(env, subprog)->called = true;
 		clear_caller_saved_regs(env, caller->regs);
+
+		/* All global functions return a 64-bit SCALAR_VALUE */
 		mark_reg_unknown(env, caller->regs, BPF_REG_0);
 		caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG;
+
 		/* continue with next insn after call */
 		return 0;
 	}
 
-	callee = kzalloc(sizeof(*callee), GFP_KERNEL);
-	if (!callee)
-		return -ENOMEM;
-	state->frame[state->curframe + 1] = callee;
-
-	/* callee cannot access r0, r6 - r9 for reading and has to write
-	 * into its own stack before reading from it.
-	 * callee can read/write into caller's stack
+	/* for regular function entry setup new frame and continue
+	 * from that frame.
 	 */
-	init_func_state(env, callee,
-			/* remember the callsite, it will be used by bpf_exit */
-			*insn_idx /* callsite */,
-			state->curframe + 1 /* frameno within this callchain */,
-			subprog /* subprog number within this prog */);
-
-	/* Transfer references to the callee */
-	err = copy_reference_state(callee, caller);
-	if (err)
-		goto err_out;
-
-	err = set_callee_state_cb(env, caller, callee, *insn_idx);
+	err = setup_func_entry(env, subprog, *insn_idx, set_callee_state, state);
 	if (err)
-		goto err_out;
+		return err;
 
 	clear_caller_saved_regs(env, caller->regs);
 
-	/* only increment it after check_reg_arg() finished */
-	state->curframe++;
-
 	/* and go analyze first insn of the callee */
 	*insn_idx = env->subprog_info[subprog].start - 1;
 
@@ -9467,14 +9472,10 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		verbose(env, "caller:\n");
 		print_verifier_state(env, caller, true);
 		verbose(env, "callee:\n");
-		print_verifier_state(env, callee, true);
+		print_verifier_state(env, state->frame[state->curframe], true);
 	}
-	return 0;
 
-err_out:
-	free_func_state(callee);
-	state->frame[state->curframe + 1] = NULL;
-	return err;
+	return 0;
 }
 
 int map_set_for_each_callback_args(struct bpf_verifier_env *env,
@@ -9518,22 +9519,6 @@ static int set_callee_state(struct bpf_verifier_env *env,
 	return 0;
 }
 
-static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
-			   int *insn_idx)
-{
-	int subprog, target_insn;
-
-	target_insn = *insn_idx + insn->imm + 1;
-	subprog = find_subprog(env, target_insn);
-	if (subprog < 0) {
-		verbose(env, "verifier bug. No program starts at insn %d\n",
-			target_insn);
-		return -EFAULT;
-	}
-
-	return __check_func_call(env, insn, insn_idx, subprog, set_callee_state);
-}
-
 static int set_map_elem_callback_state(struct bpf_verifier_env *env,
 				       struct bpf_func_state *caller,
 				       struct bpf_func_state *callee,
@@ -9560,7 +9545,7 @@ static int set_map_elem_callback_state(struct bpf_verifier_env *env,
 		return err;
 
 	callee->in_callback_fn = true;
-	callee->callback_ret_range = tnum_range(0, 1);
+	callee->callback_ret_range = retval_range(0, 1);
 	return 0;
 }
 
@@ -9582,7 +9567,7 @@ static int set_loop_callback_state(struct bpf_verifier_env *env,
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
 
 	callee->in_callback_fn = true;
-	callee->callback_ret_range = tnum_range(0, 1);
+	callee->callback_ret_range = retval_range(0, 1);
 	return 0;
 }
 
@@ -9612,7 +9597,7 @@ static int set_timer_callback_state(struct bpf_verifier_env *env,
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
 	callee->in_async_callback_fn = true;
-	callee->callback_ret_range = tnum_range(0, 1);
+	callee->callback_ret_range = retval_range(0, 1);
 	return 0;
 }
 
@@ -9631,7 +9616,7 @@ static int set_find_vma_callback_state(struct bpf_verifier_env *env,
 	callee->regs[BPF_REG_2].type = PTR_TO_BTF_ID;
 	__mark_reg_known_zero(&callee->regs[BPF_REG_2]);
 	callee->regs[BPF_REG_2].btf =  btf_vmlinux;
-	callee->regs[BPF_REG_2].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA],
+	callee->regs[BPF_REG_2].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA];
 
 	/* pointer to stack or null */
 	callee->regs[BPF_REG_3] = caller->regs[BPF_REG_4];
@@ -9640,7 +9625,7 @@ static int set_find_vma_callback_state(struct bpf_verifier_env *env,
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
 	callee->in_callback_fn = true;
-	callee->callback_ret_range = tnum_range(0, 1);
+	callee->callback_ret_range = retval_range(0, 1);
 	return 0;
 }
 
@@ -9663,7 +9648,7 @@ static int set_user_ringbuf_callback_state(struct bpf_verifier_env *env,
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
 
 	callee->in_callback_fn = true;
-	callee->callback_ret_range = tnum_range(0, 1);
+	callee->callback_ret_range = retval_range(0, 1);
 	return 0;
 }
 
@@ -9695,7 +9680,7 @@ static int set_rbtree_add_callback_state(struct bpf_verifier_env *env,
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
 	callee->in_callback_fn = true;
-	callee->callback_ret_range = tnum_range(0, 1);
+	callee->callback_ret_range = retval_range(0, 1);
 	return 0;
 }
 
@@ -9724,11 +9709,17 @@ static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env)
 	return is_rbtree_lock_required_kfunc(kfunc_btf_id);
 }
 
+static bool retval_range_within(struct bpf_retval_range range, const struct bpf_reg_state *reg)
+{
+	return range.minval <= reg->smin_value && reg->smax_value <= range.maxval;
+}
+
 static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 {
-	struct bpf_verifier_state *state = env->cur_state;
+	struct bpf_verifier_state *state = env->cur_state, *prev_st;
 	struct bpf_func_state *caller, *callee;
 	struct bpf_reg_state *r0;
+	bool in_callback_fn;
 	int err;
 
 	callee = state->frame[state->curframe];
@@ -9746,17 +9737,28 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 
 	caller = state->frame[state->curframe - 1];
 	if (callee->in_callback_fn) {
-		/* enforce R0 return value range [0, 1]. */
-		struct tnum range = callee->callback_ret_range;
-
 		if (r0->type != SCALAR_VALUE) {
 			verbose(env, "R0 not a scalar value\n");
 			return -EACCES;
 		}
-		if (!tnum_in(range, r0->var_off)) {
-			verbose_invalid_scalar(env, r0, &range, "callback return", "R0");
+
+		/* we are going to rely on register's precise value */
+		err = mark_reg_read(env, r0, r0->parent, REG_LIVE_READ64);
+		err = err ?: mark_chain_precision(env, BPF_REG_0);
+		if (err)
+			return err;
+
+		/* enforce R0 return value range */
+		if (!retval_range_within(callee->callback_ret_range, r0)) {
+			verbose_invalid_scalar(env, r0, callee->callback_ret_range,
+					       "At callback return", "R0");
 			return -EINVAL;
 		}
+		if (!calls_callback(env, callee->callsite)) {
+			verbose(env, "BUG: in callback at %d, callsite %d !calls_callback\n",
+				*insn_idx, callee->callsite);
+			return -EFAULT;
+		}
 	} else {
 		/* return to the caller whatever r0 had in the callee */
 		caller->regs[BPF_REG_0] = *r0;
@@ -9774,7 +9776,16 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 			return err;
 	}
 
-	*insn_idx = callee->callsite + 1;
+	/* for callbacks like bpf_loop or bpf_for_each_map_elem go back to callsite,
+	 * there function call logic would reschedule callback visit. If iteration
+	 * converges is_state_visited() would prune that visit eventually.
+	 */
+	in_callback_fn = callee->in_callback_fn;
+	if (in_callback_fn)
+		*insn_idx = callee->callsite;
+	else
+		*insn_idx = callee->callsite + 1;
+
 	if (env->log.level & BPF_LOG_LEVEL) {
 		verbose(env, "returning from callee:\n");
 		print_verifier_state(env, callee, true);
@@ -9785,17 +9796,36 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 	 * bpf_throw, this will be done by copy_verifier_state for extra frames. */
 	free_func_state(callee);
 	state->frame[state->curframe--] = NULL;
+
+	/* for callbacks widen imprecise scalars to make programs like below verify:
+	 *
+	 *   struct ctx { int i; }
+	 *   void cb(int idx, struct ctx *ctx) { ctx->i++; ... }
+	 *   ...
+	 *   struct ctx = { .i = 0; }
+	 *   bpf_loop(100, cb, &ctx, 0);
+	 *
+	 * This is similar to what is done in process_iter_next_call() for open
+	 * coded iterators.
+	 */
+	prev_st = in_callback_fn ? find_prev_entry(env, state, *insn_idx) : NULL;
+	if (prev_st) {
+		err = widen_imprecise_scalars(env, prev_st, state);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
-static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
-				   int func_id,
-				   struct bpf_call_arg_meta *meta)
+static int do_refine_retval_range(struct bpf_verifier_env *env,
+				  struct bpf_reg_state *regs, int ret_type,
+				  int func_id,
+				  struct bpf_call_arg_meta *meta)
 {
 	struct bpf_reg_state *ret_reg = &regs[BPF_REG_0];
 
 	if (ret_type != RET_INTEGER)
-		return;
+		return 0;
 
 	switch (func_id) {
 	case BPF_FUNC_get_stack:
@@ -9821,6 +9851,8 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
 		reg_bounds_sync(ret_reg);
 		break;
 	}
+
+	return reg_bounds_sanity_check(env, ret_reg, "retval");
 }
 
 static int
@@ -9890,7 +9922,7 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 	val = reg->var_off.value;
 	max = map->max_entries;
 
-	if (!(register_is_const(reg) && val < max)) {
+	if (!(is_reg_const(reg, false) && val < max)) {
 		bpf_map_key_store(aux, BPF_MAP_KEY_POISON);
 		return 0;
 	}
@@ -10187,24 +10219,37 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		}
 		break;
 	case BPF_FUNC_for_each_map_elem:
-		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
-					set_map_elem_callback_state);
+		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+					 set_map_elem_callback_state);
 		break;
 	case BPF_FUNC_timer_set_callback:
-		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
-					set_timer_callback_state);
+		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+					 set_timer_callback_state);
 		break;
 	case BPF_FUNC_find_vma:
-		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
-					set_find_vma_callback_state);
+		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+					 set_find_vma_callback_state);
 		break;
 	case BPF_FUNC_snprintf:
 		err = check_bpf_snprintf_call(env, regs);
 		break;
 	case BPF_FUNC_loop:
 		update_loop_inline_state(env, meta.subprogno);
-		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
-					set_loop_callback_state);
+		/* Verifier relies on R1 value to determine if bpf_loop() iteration
+		 * is finished, thus mark it precise.
+		 */
+		err = mark_chain_precision(env, BPF_REG_1);
+		if (err)
+			return err;
+		if (cur_func(env)->callback_depth < regs[BPF_REG_1].umax_value) {
+			err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+						 set_loop_callback_state);
+		} else {
+			cur_func(env)->callback_depth = 0;
+			if (env->log.level & BPF_LOG_LEVEL2)
+				verbose(env, "frame%d bpf_loop iteration limit reached\n",
+					env->cur_state->curframe);
+		}
 		break;
 	case BPF_FUNC_dynptr_from_mem:
 		if (regs[BPF_REG_1].type != PTR_TO_MAP_VALUE) {
@@ -10300,8 +10345,8 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		break;
 	}
 	case BPF_FUNC_user_ringbuf_drain:
-		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
-					set_user_ringbuf_callback_state);
+		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+					 set_user_ringbuf_callback_state);
 		break;
 	}
 
@@ -10472,7 +10517,9 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		regs[BPF_REG_0].ref_obj_id = id;
 	}
 
-	do_refine_retval_range(regs, fn->ret_type, func_id, &meta);
+	err = do_refine_retval_range(env, regs, fn->ret_type, func_id, &meta);
+	if (err)
+		return err;
 
 	err = check_map_func_compatibility(env, meta.map_ptr, func_id);
 	if (err)
@@ -10650,6 +10697,11 @@ static bool is_kfunc_arg_nullable(const struct btf *btf, const struct btf_param
 	return __kfunc_param_match_suffix(btf, arg, "__nullable");
 }
 
+static bool is_kfunc_arg_const_str(const struct btf *btf, const struct btf_param *arg)
+{
+	return __kfunc_param_match_suffix(btf, arg, "__str");
+}
+
 static bool is_kfunc_arg_scalar_with_name(const struct btf *btf,
 					  const struct btf_param *arg,
 					  const char *name)
@@ -10793,6 +10845,7 @@ enum kfunc_ptr_arg_type {
 	KF_ARG_PTR_TO_RB_ROOT,
 	KF_ARG_PTR_TO_RB_NODE,
 	KF_ARG_PTR_TO_NULL,
+	KF_ARG_PTR_TO_CONST_STR,
 };
 
 enum special_kfunc_type {
@@ -10943,6 +10996,9 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env,
 	if (is_kfunc_arg_rbtree_node(meta->btf, &args[argno]))
 		return KF_ARG_PTR_TO_RB_NODE;
 
+	if (is_kfunc_arg_const_str(meta->btf, &args[argno]))
+		return KF_ARG_PTR_TO_CONST_STR;
+
 	if ((base_type(reg->type) == PTR_TO_BTF_ID || reg2btf_ids[base_type(reg->type)])) {
 		if (!btf_type_is_struct(ref_t)) {
 			verbose(env, "kernel function %s args#%d pointer type %s %s is not supported\n",
@@ -11189,7 +11245,7 @@ static bool is_bpf_graph_api_kfunc(u32 btf_id)
 	       btf_id == special_kfunc_list[KF_bpf_refcount_acquire_impl];
 }
 
-static bool is_callback_calling_kfunc(u32 btf_id)
+static bool is_sync_callback_calling_kfunc(u32 btf_id)
 {
 	return btf_id == special_kfunc_list[KF_bpf_rbtree_add_impl];
 }
@@ -11574,6 +11630,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 		case KF_ARG_PTR_TO_MEM_SIZE:
 		case KF_ARG_PTR_TO_CALLBACK:
 		case KF_ARG_PTR_TO_REFCOUNTED_KPTR:
+		case KF_ARG_PTR_TO_CONST_STR:
 			/* Trusted by default */
 			break;
 		default:
@@ -11845,6 +11902,15 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 			meta->arg_btf = reg->btf;
 			meta->arg_btf_id = reg->btf_id;
 			break;
+		case KF_ARG_PTR_TO_CONST_STR:
+			if (reg->type != PTR_TO_MAP_VALUE) {
+				verbose(env, "arg#%d doesn't point to a const string\n", i);
+				return -EINVAL;
+			}
+			ret = check_reg_const_str(env, reg, regno);
+			if (ret)
+				return ret;
+			break;
 		}
 	}
 
@@ -11899,7 +11965,7 @@ static int fetch_kfunc_meta(struct bpf_verifier_env *env,
 	return 0;
 }
 
-static int check_return_code(struct bpf_verifier_env *env, int regno);
+static int check_return_code(struct bpf_verifier_env *env, int regno, const char *reg_name);
 
 static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			    int *insn_idx_p)
@@ -11941,6 +12007,21 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		return -EACCES;
 	}
 
+	/* Check the arguments */
+	err = check_kfunc_args(env, &meta, insn_idx);
+	if (err < 0)
+		return err;
+
+	if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) {
+		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+					 set_rbtree_add_callback_state);
+		if (err) {
+			verbose(env, "kfunc %s#%d failed callback verification\n",
+				func_name, meta.func_id);
+			return err;
+		}
+	}
+
 	rcu_lock = is_kfunc_bpf_rcu_read_lock(&meta);
 	rcu_unlock = is_kfunc_bpf_rcu_read_unlock(&meta);
 
@@ -11976,10 +12057,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		return -EINVAL;
 	}
 
-	/* Check the arguments */
-	err = check_kfunc_args(env, &meta, insn_idx);
-	if (err < 0)
-		return err;
 	/* In case of release function, we get register number of refcounted
 	 * PTR_TO_BTF_ID in bpf_kfunc_arg_meta, do the release now.
 	 */
@@ -12013,16 +12090,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		}
 	}
 
-	if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) {
-		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
-					set_rbtree_add_callback_state);
-		if (err) {
-			verbose(env, "kfunc %s#%d failed callback verification\n",
-				func_name, meta.func_id);
-			return err;
-		}
-	}
-
 	if (meta.func_id == special_kfunc_list[KF_bpf_throw]) {
 		if (!bpf_jit_supports_exceptions()) {
 			verbose(env, "JIT does not support calling kfunc %s#%d\n",
@@ -12035,7 +12102,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		 * to bpf_throw becomes the return value of the program.
 		 */
 		if (!env->exception_callback_subprog) {
-			err = check_return_code(env, BPF_REG_1);
+			err = check_return_code(env, BPF_REG_1, "R1");
 			if (err < 0)
 				return err;
 		}
@@ -12074,9 +12141,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 				if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl] && !bpf_global_ma_set)
 					return -ENOMEM;
 
-				if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl] && !bpf_global_percpu_ma_set)
-					return -ENOMEM;
-
 				if (((u64)(u32)meta.arg_constant.value) != meta.arg_constant.value) {
 					verbose(env, "local type ID argument must be in range [0, U32_MAX]\n");
 					return -EINVAL;
@@ -12097,6 +12161,35 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 					return -EINVAL;
 				}
 
+				if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
+					if (ret_t->size > BPF_GLOBAL_PERCPU_MA_MAX_SIZE) {
+						verbose(env, "bpf_percpu_obj_new type size (%d) is greater than %d\n",
+							ret_t->size, BPF_GLOBAL_PERCPU_MA_MAX_SIZE);
+						return -EINVAL;
+					}
+
+					if (!bpf_global_percpu_ma_set) {
+						mutex_lock(&bpf_percpu_ma_lock);
+						if (!bpf_global_percpu_ma_set) {
+							/* Charge memory allocated with bpf_global_percpu_ma to
+							 * root memcg. The obj_cgroup for root memcg is NULL.
+							 */
+							err = bpf_mem_alloc_percpu_init(&bpf_global_percpu_ma, NULL);
+							if (!err)
+								bpf_global_percpu_ma_set = true;
+						}
+						mutex_unlock(&bpf_percpu_ma_lock);
+						if (err)
+							return err;
+					}
+
+					mutex_lock(&bpf_percpu_ma_lock);
+					err = bpf_mem_alloc_percpu_unit_init(&bpf_global_percpu_ma, ret_t->size);
+					mutex_unlock(&bpf_percpu_ma_lock);
+					if (err)
+						return err;
+				}
+
 				struct_meta = btf_find_struct_meta(ret_btf, ret_btf_id);
 				if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
 					if (!__btf_type_is_scalar_struct(env, ret_btf, ret_t, 0)) {
@@ -13953,13 +14046,12 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 
 		/* check dest operand */
 		err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
+		err = err ?: adjust_reg_min_max_vals(env, insn);
 		if (err)
 			return err;
-
-		return adjust_reg_min_max_vals(env, insn);
 	}
 
-	return 0;
+	return reg_bounds_sanity_check(env, &regs[insn->dst_reg], "alu");
 }
 
 static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
@@ -14041,161 +14133,130 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
 	}));
 }
 
-static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode)
-{
-	struct tnum subreg = tnum_subreg(reg->var_off);
-	s32 sval = (s32)val;
-
-	switch (opcode) {
-	case BPF_JEQ:
-		if (tnum_is_const(subreg))
-			return !!tnum_equals_const(subreg, val);
-		else if (val < reg->u32_min_value || val > reg->u32_max_value)
-			return 0;
-		else if (sval < reg->s32_min_value || sval > reg->s32_max_value)
-			return 0;
-		break;
-	case BPF_JNE:
-		if (tnum_is_const(subreg))
-			return !tnum_equals_const(subreg, val);
-		else if (val < reg->u32_min_value || val > reg->u32_max_value)
-			return 1;
-		else if (sval < reg->s32_min_value || sval > reg->s32_max_value)
-			return 1;
-		break;
-	case BPF_JSET:
-		if ((~subreg.mask & subreg.value) & val)
-			return 1;
-		if (!((subreg.mask | subreg.value) & val))
-			return 0;
-		break;
-	case BPF_JGT:
-		if (reg->u32_min_value > val)
-			return 1;
-		else if (reg->u32_max_value <= val)
-			return 0;
-		break;
-	case BPF_JSGT:
-		if (reg->s32_min_value > sval)
-			return 1;
-		else if (reg->s32_max_value <= sval)
-			return 0;
-		break;
-	case BPF_JLT:
-		if (reg->u32_max_value < val)
-			return 1;
-		else if (reg->u32_min_value >= val)
-			return 0;
-		break;
-	case BPF_JSLT:
-		if (reg->s32_max_value < sval)
-			return 1;
-		else if (reg->s32_min_value >= sval)
-			return 0;
-		break;
-	case BPF_JGE:
-		if (reg->u32_min_value >= val)
-			return 1;
-		else if (reg->u32_max_value < val)
-			return 0;
-		break;
-	case BPF_JSGE:
-		if (reg->s32_min_value >= sval)
-			return 1;
-		else if (reg->s32_max_value < sval)
-			return 0;
-		break;
-	case BPF_JLE:
-		if (reg->u32_max_value <= val)
-			return 1;
-		else if (reg->u32_min_value > val)
-			return 0;
-		break;
-	case BPF_JSLE:
-		if (reg->s32_max_value <= sval)
-			return 1;
-		else if (reg->s32_min_value > sval)
-			return 0;
-		break;
-	}
-
-	return -1;
-}
-
-
-static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
-{
-	s64 sval = (s64)val;
+/*
+ * <reg1> <op> <reg2>, currently assuming reg2 is a constant
+ */
+static int is_scalar_branch_taken(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2,
+				  u8 opcode, bool is_jmp32)
+{
+	struct tnum t1 = is_jmp32 ? tnum_subreg(reg1->var_off) : reg1->var_off;
+	struct tnum t2 = is_jmp32 ? tnum_subreg(reg2->var_off) : reg2->var_off;
+	u64 umin1 = is_jmp32 ? (u64)reg1->u32_min_value : reg1->umin_value;
+	u64 umax1 = is_jmp32 ? (u64)reg1->u32_max_value : reg1->umax_value;
+	s64 smin1 = is_jmp32 ? (s64)reg1->s32_min_value : reg1->smin_value;
+	s64 smax1 = is_jmp32 ? (s64)reg1->s32_max_value : reg1->smax_value;
+	u64 umin2 = is_jmp32 ? (u64)reg2->u32_min_value : reg2->umin_value;
+	u64 umax2 = is_jmp32 ? (u64)reg2->u32_max_value : reg2->umax_value;
+	s64 smin2 = is_jmp32 ? (s64)reg2->s32_min_value : reg2->smin_value;
+	s64 smax2 = is_jmp32 ? (s64)reg2->s32_max_value : reg2->smax_value;
 
 	switch (opcode) {
 	case BPF_JEQ:
-		if (tnum_is_const(reg->var_off))
-			return !!tnum_equals_const(reg->var_off, val);
-		else if (val < reg->umin_value || val > reg->umax_value)
+		/* constants, umin/umax and smin/smax checks would be
+		 * redundant in this case because they all should match
+		 */
+		if (tnum_is_const(t1) && tnum_is_const(t2))
+			return t1.value == t2.value;
+		/* non-overlapping ranges */
+		if (umin1 > umax2 || umax1 < umin2)
 			return 0;
-		else if (sval < reg->smin_value || sval > reg->smax_value)
+		if (smin1 > smax2 || smax1 < smin2)
 			return 0;
+		if (!is_jmp32) {
+			/* if 64-bit ranges are inconclusive, see if we can
+			 * utilize 32-bit subrange knowledge to eliminate
+			 * branches that can't be taken a priori
+			 */
+			if (reg1->u32_min_value > reg2->u32_max_value ||
+			    reg1->u32_max_value < reg2->u32_min_value)
+				return 0;
+			if (reg1->s32_min_value > reg2->s32_max_value ||
+			    reg1->s32_max_value < reg2->s32_min_value)
+				return 0;
+		}
 		break;
 	case BPF_JNE:
-		if (tnum_is_const(reg->var_off))
-			return !tnum_equals_const(reg->var_off, val);
-		else if (val < reg->umin_value || val > reg->umax_value)
+		/* constants, umin/umax and smin/smax checks would be
+		 * redundant in this case because they all should match
+		 */
+		if (tnum_is_const(t1) && tnum_is_const(t2))
+			return t1.value != t2.value;
+		/* non-overlapping ranges */
+		if (umin1 > umax2 || umax1 < umin2)
 			return 1;
-		else if (sval < reg->smin_value || sval > reg->smax_value)
+		if (smin1 > smax2 || smax1 < smin2)
 			return 1;
+		if (!is_jmp32) {
+			/* if 64-bit ranges are inconclusive, see if we can
+			 * utilize 32-bit subrange knowledge to eliminate
+			 * branches that can't be taken a priori
+			 */
+			if (reg1->u32_min_value > reg2->u32_max_value ||
+			    reg1->u32_max_value < reg2->u32_min_value)
+				return 1;
+			if (reg1->s32_min_value > reg2->s32_max_value ||
+			    reg1->s32_max_value < reg2->s32_min_value)
+				return 1;
+		}
 		break;
 	case BPF_JSET:
-		if ((~reg->var_off.mask & reg->var_off.value) & val)
+		if (!is_reg_const(reg2, is_jmp32)) {
+			swap(reg1, reg2);
+			swap(t1, t2);
+		}
+		if (!is_reg_const(reg2, is_jmp32))
+			return -1;
+		if ((~t1.mask & t1.value) & t2.value)
 			return 1;
-		if (!((reg->var_off.mask | reg->var_off.value) & val))
+		if (!((t1.mask | t1.value) & t2.value))
 			return 0;
 		break;
 	case BPF_JGT:
-		if (reg->umin_value > val)
+		if (umin1 > umax2)
 			return 1;
-		else if (reg->umax_value <= val)
+		else if (umax1 <= umin2)
 			return 0;
 		break;
 	case BPF_JSGT:
-		if (reg->smin_value > sval)
+		if (smin1 > smax2)
 			return 1;
-		else if (reg->smax_value <= sval)
+		else if (smax1 <= smin2)
 			return 0;
 		break;
 	case BPF_JLT:
-		if (reg->umax_value < val)
+		if (umax1 < umin2)
 			return 1;
-		else if (reg->umin_value >= val)
+		else if (umin1 >= umax2)
 			return 0;
 		break;
 	case BPF_JSLT:
-		if (reg->smax_value < sval)
+		if (smax1 < smin2)
 			return 1;
-		else if (reg->smin_value >= sval)
+		else if (smin1 >= smax2)
 			return 0;
 		break;
 	case BPF_JGE:
-		if (reg->umin_value >= val)
+		if (umin1 >= umax2)
 			return 1;
-		else if (reg->umax_value < val)
+		else if (umax1 < umin2)
 			return 0;
 		break;
 	case BPF_JSGE:
-		if (reg->smin_value >= sval)
+		if (smin1 >= smax2)
 			return 1;
-		else if (reg->smax_value < sval)
+		else if (smax1 < smin2)
 			return 0;
 		break;
 	case BPF_JLE:
-		if (reg->umax_value <= val)
+		if (umax1 <= umin2)
 			return 1;
-		else if (reg->umin_value > val)
+		else if (umin1 > umax2)
 			return 0;
 		break;
 	case BPF_JSLE:
-		if (reg->smax_value <= sval)
+		if (smax1 <= smin2)
 			return 1;
-		else if (reg->smin_value > sval)
+		else if (smin1 > smax2)
 			return 0;
 		break;
 	}
@@ -14203,41 +14264,6 @@ static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
 	return -1;
 }
 
-/* compute branch direction of the expression "if (reg opcode val) goto target;"
- * and return:
- *  1 - branch will be taken and "goto target" will be executed
- *  0 - branch will not be taken and fall-through to next insn
- * -1 - unknown. Example: "if (reg < 5)" is unknown when register value
- *      range [0,10]
- */
-static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode,
-			   bool is_jmp32)
-{
-	if (__is_pointer_value(false, reg)) {
-		if (!reg_not_null(reg))
-			return -1;
-
-		/* If pointer is valid tests against zero will fail so we can
-		 * use this to direct branch taken.
-		 */
-		if (val != 0)
-			return -1;
-
-		switch (opcode) {
-		case BPF_JEQ:
-			return 0;
-		case BPF_JNE:
-			return 1;
-		default:
-			return -1;
-		}
-	}
-
-	if (is_jmp32)
-		return is_branch32_taken(reg, val, opcode);
-	return is_branch64_taken(reg, val, opcode);
-}
-
 static int flip_opcode(u32 opcode)
 {
 	/* How can we transform "a <op> b" into "b <op> a"? */
@@ -14299,216 +14325,280 @@ static int is_pkt_ptr_branch_taken(struct bpf_reg_state *dst_reg,
 	return -1;
 }
 
-/* Adjusts the register min/max values in the case that the dst_reg is the
- * variable register that we are working on, and src_reg is a constant or we're
- * simply doing a BPF_K check.
- * In JEQ/JNE cases we also adjust the var_off values.
+/* compute branch direction of the expression "if (<reg1> opcode <reg2>) goto target;"
+ * and return:
+ *  1 - branch will be taken and "goto target" will be executed
+ *  0 - branch will not be taken and fall-through to next insn
+ * -1 - unknown. Example: "if (reg1 < 5)" is unknown when register value
+ *      range [0,10]
  */
-static void reg_set_min_max(struct bpf_reg_state *true_reg,
-			    struct bpf_reg_state *false_reg,
-			    u64 val, u32 val32,
-			    u8 opcode, bool is_jmp32)
-{
-	struct tnum false_32off = tnum_subreg(false_reg->var_off);
-	struct tnum false_64off = false_reg->var_off;
-	struct tnum true_32off = tnum_subreg(true_reg->var_off);
-	struct tnum true_64off = true_reg->var_off;
-	s64 sval = (s64)val;
-	s32 sval32 = (s32)val32;
-
-	/* If the dst_reg is a pointer, we can't learn anything about its
-	 * variable offset from the compare (unless src_reg were a pointer into
-	 * the same object, but we don't bother with that.
-	 * Since false_reg and true_reg have the same type by construction, we
-	 * only need to check one of them for pointerness.
-	 */
-	if (__is_pointer_value(false, false_reg))
-		return;
+static int is_branch_taken(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2,
+			   u8 opcode, bool is_jmp32)
+{
+	if (reg_is_pkt_pointer_any(reg1) && reg_is_pkt_pointer_any(reg2) && !is_jmp32)
+		return is_pkt_ptr_branch_taken(reg1, reg2, opcode);
+
+	if (__is_pointer_value(false, reg1) || __is_pointer_value(false, reg2)) {
+		u64 val;
+
+		/* arrange that reg2 is a scalar, and reg1 is a pointer */
+		if (!is_reg_const(reg2, is_jmp32)) {
+			opcode = flip_opcode(opcode);
+			swap(reg1, reg2);
+		}
+		/* and ensure that reg2 is a constant */
+		if (!is_reg_const(reg2, is_jmp32))
+			return -1;
+
+		if (!reg_not_null(reg1))
+			return -1;
+
+		/* If pointer is valid tests against zero will fail so we can
+		 * use this to direct branch taken.
+		 */
+		val = reg_const_value(reg2, is_jmp32);
+		if (val != 0)
+			return -1;
 
+		switch (opcode) {
+		case BPF_JEQ:
+			return 0;
+		case BPF_JNE:
+			return 1;
+		default:
+			return -1;
+		}
+	}
+
+	/* now deal with two scalars, but not necessarily constants */
+	return is_scalar_branch_taken(reg1, reg2, opcode, is_jmp32);
+}
+
+/* Opcode that corresponds to a *false* branch condition.
+ * E.g., if r1 < r2, then reverse (false) condition is r1 >= r2
+ */
+static u8 rev_opcode(u8 opcode)
+{
 	switch (opcode) {
-	/* JEQ/JNE comparison doesn't change the register equivalence.
-	 *
-	 * r1 = r2;
-	 * if (r1 == 42) goto label;
-	 * ...
-	 * label: // here both r1 and r2 are known to be 42.
-	 *
-	 * Hence when marking register as known preserve it's ID.
+	case BPF_JEQ:		return BPF_JNE;
+	case BPF_JNE:		return BPF_JEQ;
+	/* JSET doesn't have it's reverse opcode in BPF, so add
+	 * BPF_X flag to denote the reverse of that operation
 	 */
+	case BPF_JSET:		return BPF_JSET | BPF_X;
+	case BPF_JSET | BPF_X:	return BPF_JSET;
+	case BPF_JGE:		return BPF_JLT;
+	case BPF_JGT:		return BPF_JLE;
+	case BPF_JLE:		return BPF_JGT;
+	case BPF_JLT:		return BPF_JGE;
+	case BPF_JSGE:		return BPF_JSLT;
+	case BPF_JSGT:		return BPF_JSLE;
+	case BPF_JSLE:		return BPF_JSGT;
+	case BPF_JSLT:		return BPF_JSGE;
+	default:		return 0;
+	}
+}
+
+/* Refine range knowledge for <reg1> <op> <reg>2 conditional operation. */
+static void regs_refine_cond_op(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2,
+				u8 opcode, bool is_jmp32)
+{
+	struct tnum t;
+	u64 val;
+
+again:
+	switch (opcode) {
 	case BPF_JEQ:
 		if (is_jmp32) {
-			__mark_reg32_known(true_reg, val32);
-			true_32off = tnum_subreg(true_reg->var_off);
+			reg1->u32_min_value = max(reg1->u32_min_value, reg2->u32_min_value);
+			reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value);
+			reg1->s32_min_value = max(reg1->s32_min_value, reg2->s32_min_value);
+			reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value);
+			reg2->u32_min_value = reg1->u32_min_value;
+			reg2->u32_max_value = reg1->u32_max_value;
+			reg2->s32_min_value = reg1->s32_min_value;
+			reg2->s32_max_value = reg1->s32_max_value;
+
+			t = tnum_intersect(tnum_subreg(reg1->var_off), tnum_subreg(reg2->var_off));
+			reg1->var_off = tnum_with_subreg(reg1->var_off, t);
+			reg2->var_off = tnum_with_subreg(reg2->var_off, t);
 		} else {
-			___mark_reg_known(true_reg, val);
-			true_64off = true_reg->var_off;
+			reg1->umin_value = max(reg1->umin_value, reg2->umin_value);
+			reg1->umax_value = min(reg1->umax_value, reg2->umax_value);
+			reg1->smin_value = max(reg1->smin_value, reg2->smin_value);
+			reg1->smax_value = min(reg1->smax_value, reg2->smax_value);
+			reg2->umin_value = reg1->umin_value;
+			reg2->umax_value = reg1->umax_value;
+			reg2->smin_value = reg1->smin_value;
+			reg2->smax_value = reg1->smax_value;
+
+			reg1->var_off = tnum_intersect(reg1->var_off, reg2->var_off);
+			reg2->var_off = reg1->var_off;
 		}
 		break;
 	case BPF_JNE:
+		if (!is_reg_const(reg2, is_jmp32))
+			swap(reg1, reg2);
+		if (!is_reg_const(reg2, is_jmp32))
+			break;
+
+		/* try to recompute the bound of reg1 if reg2 is a const and
+		 * is exactly the edge of reg1.
+		 */
+		val = reg_const_value(reg2, is_jmp32);
 		if (is_jmp32) {
-			__mark_reg32_known(false_reg, val32);
-			false_32off = tnum_subreg(false_reg->var_off);
+			/* u32_min_value is not equal to 0xffffffff at this point,
+			 * because otherwise u32_max_value is 0xffffffff as well,
+			 * in such a case both reg1 and reg2 would be constants,
+			 * jump would be predicted and reg_set_min_max() won't
+			 * be called.
+			 *
+			 * Same reasoning works for all {u,s}{min,max}{32,64} cases
+			 * below.
+			 */
+			if (reg1->u32_min_value == (u32)val)
+				reg1->u32_min_value++;
+			if (reg1->u32_max_value == (u32)val)
+				reg1->u32_max_value--;
+			if (reg1->s32_min_value == (s32)val)
+				reg1->s32_min_value++;
+			if (reg1->s32_max_value == (s32)val)
+				reg1->s32_max_value--;
 		} else {
-			___mark_reg_known(false_reg, val);
-			false_64off = false_reg->var_off;
+			if (reg1->umin_value == (u64)val)
+				reg1->umin_value++;
+			if (reg1->umax_value == (u64)val)
+				reg1->umax_value--;
+			if (reg1->smin_value == (s64)val)
+				reg1->smin_value++;
+			if (reg1->smax_value == (s64)val)
+				reg1->smax_value--;
 		}
 		break;
 	case BPF_JSET:
+		if (!is_reg_const(reg2, is_jmp32))
+			swap(reg1, reg2);
+		if (!is_reg_const(reg2, is_jmp32))
+			break;
+		val = reg_const_value(reg2, is_jmp32);
+		/* BPF_JSET (i.e., TRUE branch, *not* BPF_JSET | BPF_X)
+		 * requires single bit to learn something useful. E.g., if we
+		 * know that `r1 & 0x3` is true, then which bits (0, 1, or both)
+		 * are actually set? We can learn something definite only if
+		 * it's a single-bit value to begin with.
+		 *
+		 * BPF_JSET | BPF_X (i.e., negation of BPF_JSET) doesn't have
+		 * this restriction. I.e., !(r1 & 0x3) means neither bit 0 nor
+		 * bit 1 is set, which we can readily use in adjustments.
+		 */
+		if (!is_power_of_2(val))
+			break;
 		if (is_jmp32) {
-			false_32off = tnum_and(false_32off, tnum_const(~val32));
-			if (is_power_of_2(val32))
-				true_32off = tnum_or(true_32off,
-						     tnum_const(val32));
+			t = tnum_or(tnum_subreg(reg1->var_off), tnum_const(val));
+			reg1->var_off = tnum_with_subreg(reg1->var_off, t);
 		} else {
-			false_64off = tnum_and(false_64off, tnum_const(~val));
-			if (is_power_of_2(val))
-				true_64off = tnum_or(true_64off,
-						     tnum_const(val));
+			reg1->var_off = tnum_or(reg1->var_off, tnum_const(val));
 		}
 		break;
-	case BPF_JGE:
-	case BPF_JGT:
-	{
+	case BPF_JSET | BPF_X: /* reverse of BPF_JSET, see rev_opcode() */
+		if (!is_reg_const(reg2, is_jmp32))
+			swap(reg1, reg2);
+		if (!is_reg_const(reg2, is_jmp32))
+			break;
+		val = reg_const_value(reg2, is_jmp32);
 		if (is_jmp32) {
-			u32 false_umax = opcode == BPF_JGT ? val32  : val32 - 1;
-			u32 true_umin = opcode == BPF_JGT ? val32 + 1 : val32;
-
-			false_reg->u32_max_value = min(false_reg->u32_max_value,
-						       false_umax);
-			true_reg->u32_min_value = max(true_reg->u32_min_value,
-						      true_umin);
+			t = tnum_and(tnum_subreg(reg1->var_off), tnum_const(~val));
+			reg1->var_off = tnum_with_subreg(reg1->var_off, t);
 		} else {
-			u64 false_umax = opcode == BPF_JGT ? val    : val - 1;
-			u64 true_umin = opcode == BPF_JGT ? val + 1 : val;
-
-			false_reg->umax_value = min(false_reg->umax_value, false_umax);
-			true_reg->umin_value = max(true_reg->umin_value, true_umin);
+			reg1->var_off = tnum_and(reg1->var_off, tnum_const(~val));
 		}
 		break;
-	}
-	case BPF_JSGE:
-	case BPF_JSGT:
-	{
+	case BPF_JLE:
 		if (is_jmp32) {
-			s32 false_smax = opcode == BPF_JSGT ? sval32    : sval32 - 1;
-			s32 true_smin = opcode == BPF_JSGT ? sval32 + 1 : sval32;
-
-			false_reg->s32_max_value = min(false_reg->s32_max_value, false_smax);
-			true_reg->s32_min_value = max(true_reg->s32_min_value, true_smin);
+			reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value);
+			reg2->u32_min_value = max(reg1->u32_min_value, reg2->u32_min_value);
 		} else {
-			s64 false_smax = opcode == BPF_JSGT ? sval    : sval - 1;
-			s64 true_smin = opcode == BPF_JSGT ? sval + 1 : sval;
-
-			false_reg->smax_value = min(false_reg->smax_value, false_smax);
-			true_reg->smin_value = max(true_reg->smin_value, true_smin);
+			reg1->umax_value = min(reg1->umax_value, reg2->umax_value);
+			reg2->umin_value = max(reg1->umin_value, reg2->umin_value);
 		}
 		break;
-	}
-	case BPF_JLE:
 	case BPF_JLT:
-	{
 		if (is_jmp32) {
-			u32 false_umin = opcode == BPF_JLT ? val32  : val32 + 1;
-			u32 true_umax = opcode == BPF_JLT ? val32 - 1 : val32;
-
-			false_reg->u32_min_value = max(false_reg->u32_min_value,
-						       false_umin);
-			true_reg->u32_max_value = min(true_reg->u32_max_value,
-						      true_umax);
+			reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value - 1);
+			reg2->u32_min_value = max(reg1->u32_min_value + 1, reg2->u32_min_value);
 		} else {
-			u64 false_umin = opcode == BPF_JLT ? val    : val + 1;
-			u64 true_umax = opcode == BPF_JLT ? val - 1 : val;
-
-			false_reg->umin_value = max(false_reg->umin_value, false_umin);
-			true_reg->umax_value = min(true_reg->umax_value, true_umax);
+			reg1->umax_value = min(reg1->umax_value, reg2->umax_value - 1);
+			reg2->umin_value = max(reg1->umin_value + 1, reg2->umin_value);
 		}
 		break;
-	}
 	case BPF_JSLE:
+		if (is_jmp32) {
+			reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value);
+			reg2->s32_min_value = max(reg1->s32_min_value, reg2->s32_min_value);
+		} else {
+			reg1->smax_value = min(reg1->smax_value, reg2->smax_value);
+			reg2->smin_value = max(reg1->smin_value, reg2->smin_value);
+		}
+		break;
 	case BPF_JSLT:
-	{
 		if (is_jmp32) {
-			s32 false_smin = opcode == BPF_JSLT ? sval32    : sval32 + 1;
-			s32 true_smax = opcode == BPF_JSLT ? sval32 - 1 : sval32;
-
-			false_reg->s32_min_value = max(false_reg->s32_min_value, false_smin);
-			true_reg->s32_max_value = min(true_reg->s32_max_value, true_smax);
+			reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value - 1);
+			reg2->s32_min_value = max(reg1->s32_min_value + 1, reg2->s32_min_value);
 		} else {
-			s64 false_smin = opcode == BPF_JSLT ? sval    : sval + 1;
-			s64 true_smax = opcode == BPF_JSLT ? sval - 1 : sval;
-
-			false_reg->smin_value = max(false_reg->smin_value, false_smin);
-			true_reg->smax_value = min(true_reg->smax_value, true_smax);
+			reg1->smax_value = min(reg1->smax_value, reg2->smax_value - 1);
+			reg2->smin_value = max(reg1->smin_value + 1, reg2->smin_value);
 		}
 		break;
-	}
+	case BPF_JGE:
+	case BPF_JGT:
+	case BPF_JSGE:
+	case BPF_JSGT:
+		/* just reuse LE/LT logic above */
+		opcode = flip_opcode(opcode);
+		swap(reg1, reg2);
+		goto again;
 	default:
 		return;
 	}
-
-	if (is_jmp32) {
-		false_reg->var_off = tnum_or(tnum_clear_subreg(false_64off),
-					     tnum_subreg(false_32off));
-		true_reg->var_off = tnum_or(tnum_clear_subreg(true_64off),
-					    tnum_subreg(true_32off));
-		__reg_combine_32_into_64(false_reg);
-		__reg_combine_32_into_64(true_reg);
-	} else {
-		false_reg->var_off = false_64off;
-		true_reg->var_off = true_64off;
-		__reg_combine_64_into_32(false_reg);
-		__reg_combine_64_into_32(true_reg);
-	}
 }
 
-/* Same as above, but for the case that dst_reg holds a constant and src_reg is
- * the variable reg.
+/* Adjusts the register min/max values in the case that the dst_reg and
+ * src_reg are both SCALAR_VALUE registers (or we are simply doing a BPF_K
+ * check, in which case we havea fake SCALAR_VALUE representing insn->imm).
+ * Technically we can do similar adjustments for pointers to the same object,
+ * but we don't support that right now.
  */
-static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
-				struct bpf_reg_state *false_reg,
-				u64 val, u32 val32,
-				u8 opcode, bool is_jmp32)
+static int reg_set_min_max(struct bpf_verifier_env *env,
+			   struct bpf_reg_state *true_reg1,
+			   struct bpf_reg_state *true_reg2,
+			   struct bpf_reg_state *false_reg1,
+			   struct bpf_reg_state *false_reg2,
+			   u8 opcode, bool is_jmp32)
 {
-	opcode = flip_opcode(opcode);
-	/* This uses zero as "not present in table"; luckily the zero opcode,
-	 * BPF_JA, can't get here.
+	int err;
+
+	/* If either register is a pointer, we can't learn anything about its
+	 * variable offset from the compare (unless they were a pointer into
+	 * the same object, but we don't bother with that).
 	 */
-	if (opcode)
-		reg_set_min_max(true_reg, false_reg, val, val32, opcode, is_jmp32);
-}
-
-/* Regs are known to be equal, so intersect their min/max/var_off */
-static void __reg_combine_min_max(struct bpf_reg_state *src_reg,
-				  struct bpf_reg_state *dst_reg)
-{
-	src_reg->umin_value = dst_reg->umin_value = max(src_reg->umin_value,
-							dst_reg->umin_value);
-	src_reg->umax_value = dst_reg->umax_value = min(src_reg->umax_value,
-							dst_reg->umax_value);
-	src_reg->smin_value = dst_reg->smin_value = max(src_reg->smin_value,
-							dst_reg->smin_value);
-	src_reg->smax_value = dst_reg->smax_value = min(src_reg->smax_value,
-							dst_reg->smax_value);
-	src_reg->var_off = dst_reg->var_off = tnum_intersect(src_reg->var_off,
-							     dst_reg->var_off);
-	reg_bounds_sync(src_reg);
-	reg_bounds_sync(dst_reg);
-}
+	if (false_reg1->type != SCALAR_VALUE || false_reg2->type != SCALAR_VALUE)
+		return 0;
 
-static void reg_combine_min_max(struct bpf_reg_state *true_src,
-				struct bpf_reg_state *true_dst,
-				struct bpf_reg_state *false_src,
-				struct bpf_reg_state *false_dst,
-				u8 opcode)
-{
-	switch (opcode) {
-	case BPF_JEQ:
-		__reg_combine_min_max(true_src, true_dst);
-		break;
-	case BPF_JNE:
-		__reg_combine_min_max(false_src, false_dst);
-		break;
-	}
+	/* fallthrough (FALSE) branch */
+	regs_refine_cond_op(false_reg1, false_reg2, rev_opcode(opcode), is_jmp32);
+	reg_bounds_sync(false_reg1);
+	reg_bounds_sync(false_reg2);
+
+	/* jump (TRUE) branch */
+	regs_refine_cond_op(true_reg1, true_reg2, opcode, is_jmp32);
+	reg_bounds_sync(true_reg1);
+	reg_bounds_sync(true_reg2);
+
+	err = reg_bounds_sanity_check(env, true_reg1, "true_reg1");
+	err = err ?: reg_bounds_sanity_check(env, true_reg2, "true_reg2");
+	err = err ?: reg_bounds_sanity_check(env, false_reg1, "false_reg1");
+	err = err ?: reg_bounds_sanity_check(env, false_reg2, "false_reg2");
+	return err;
 }
 
 static void mark_ptr_or_null_reg(struct bpf_func_state *state,
@@ -14706,6 +14796,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs;
 	struct bpf_reg_state *dst_reg, *other_branch_regs, *src_reg = NULL;
 	struct bpf_reg_state *eq_branch_regs;
+	struct bpf_reg_state fake_reg = {};
 	u8 opcode = BPF_OP(insn->code);
 	bool is_jmp32;
 	int pred = -1;
@@ -14746,42 +14837,13 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 			verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
 			return -EINVAL;
 		}
+		src_reg = &fake_reg;
+		src_reg->type = SCALAR_VALUE;
+		__mark_reg_known(src_reg, insn->imm);
 	}
 
 	is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
-
-	if (BPF_SRC(insn->code) == BPF_K) {
-		pred = is_branch_taken(dst_reg, insn->imm, opcode, is_jmp32);
-	} else if (src_reg->type == SCALAR_VALUE &&
-		   is_jmp32 && tnum_is_const(tnum_subreg(src_reg->var_off))) {
-		pred = is_branch_taken(dst_reg,
-				       tnum_subreg(src_reg->var_off).value,
-				       opcode,
-				       is_jmp32);
-	} else if (src_reg->type == SCALAR_VALUE &&
-		   !is_jmp32 && tnum_is_const(src_reg->var_off)) {
-		pred = is_branch_taken(dst_reg,
-				       src_reg->var_off.value,
-				       opcode,
-				       is_jmp32);
-	} else if (dst_reg->type == SCALAR_VALUE &&
-		   is_jmp32 && tnum_is_const(tnum_subreg(dst_reg->var_off))) {
-		pred = is_branch_taken(src_reg,
-				       tnum_subreg(dst_reg->var_off).value,
-				       flip_opcode(opcode),
-				       is_jmp32);
-	} else if (dst_reg->type == SCALAR_VALUE &&
-		   !is_jmp32 && tnum_is_const(dst_reg->var_off)) {
-		pred = is_branch_taken(src_reg,
-				       dst_reg->var_off.value,
-				       flip_opcode(opcode),
-				       is_jmp32);
-	} else if (reg_is_pkt_pointer_any(dst_reg) &&
-		   reg_is_pkt_pointer_any(src_reg) &&
-		   !is_jmp32) {
-		pred = is_pkt_ptr_branch_taken(dst_reg, src_reg, opcode);
-	}
-
+	pred = is_branch_taken(dst_reg, src_reg, opcode, is_jmp32);
 	if (pred >= 0) {
 		/* If we get here with a dst_reg pointer type it is because
 		 * above is_branch_taken() special cased the 0 comparison.
@@ -14829,53 +14891,27 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 		return -EFAULT;
 	other_branch_regs = other_branch->frame[other_branch->curframe]->regs;
 
-	/* detect if we are comparing against a constant value so we can adjust
-	 * our min/max values for our dst register.
-	 * this is only legit if both are scalars (or pointers to the same
-	 * object, I suppose, see the PTR_MAYBE_NULL related if block below),
-	 * because otherwise the different base pointers mean the offsets aren't
-	 * comparable.
-	 */
 	if (BPF_SRC(insn->code) == BPF_X) {
-		struct bpf_reg_state *src_reg = &regs[insn->src_reg];
-
-		if (dst_reg->type == SCALAR_VALUE &&
-		    src_reg->type == SCALAR_VALUE) {
-			if (tnum_is_const(src_reg->var_off) ||
-			    (is_jmp32 &&
-			     tnum_is_const(tnum_subreg(src_reg->var_off))))
-				reg_set_min_max(&other_branch_regs[insn->dst_reg],
-						dst_reg,
-						src_reg->var_off.value,
-						tnum_subreg(src_reg->var_off).value,
-						opcode, is_jmp32);
-			else if (tnum_is_const(dst_reg->var_off) ||
-				 (is_jmp32 &&
-				  tnum_is_const(tnum_subreg(dst_reg->var_off))))
-				reg_set_min_max_inv(&other_branch_regs[insn->src_reg],
-						    src_reg,
-						    dst_reg->var_off.value,
-						    tnum_subreg(dst_reg->var_off).value,
-						    opcode, is_jmp32);
-			else if (!is_jmp32 &&
-				 (opcode == BPF_JEQ || opcode == BPF_JNE))
-				/* Comparing for equality, we can combine knowledge */
-				reg_combine_min_max(&other_branch_regs[insn->src_reg],
-						    &other_branch_regs[insn->dst_reg],
-						    src_reg, dst_reg, opcode);
-			if (src_reg->id &&
-			    !WARN_ON_ONCE(src_reg->id != other_branch_regs[insn->src_reg].id)) {
-				find_equal_scalars(this_branch, src_reg);
-				find_equal_scalars(other_branch, &other_branch_regs[insn->src_reg]);
-			}
-
-		}
-	} else if (dst_reg->type == SCALAR_VALUE) {
-		reg_set_min_max(&other_branch_regs[insn->dst_reg],
-					dst_reg, insn->imm, (u32)insn->imm,
-					opcode, is_jmp32);
+		err = reg_set_min_max(env,
+				      &other_branch_regs[insn->dst_reg],
+				      &other_branch_regs[insn->src_reg],
+				      dst_reg, src_reg, opcode, is_jmp32);
+	} else /* BPF_SRC(insn->code) == BPF_K */ {
+		err = reg_set_min_max(env,
+				      &other_branch_regs[insn->dst_reg],
+				      src_reg /* fake one */,
+				      dst_reg, src_reg /* same fake one */,
+				      opcode, is_jmp32);
 	}
+	if (err)
+		return err;
 
+	if (BPF_SRC(insn->code) == BPF_X &&
+	    src_reg->type == SCALAR_VALUE && src_reg->id &&
+	    !WARN_ON_ONCE(src_reg->id != other_branch_regs[insn->src_reg].id)) {
+		find_equal_scalars(this_branch, src_reg);
+		find_equal_scalars(other_branch, &other_branch_regs[insn->src_reg]);
+	}
 	if (dst_reg->type == SCALAR_VALUE && dst_reg->id &&
 	    !WARN_ON_ONCE(dst_reg->id != other_branch_regs[insn->dst_reg].id)) {
 		find_equal_scalars(this_branch, dst_reg);
@@ -15147,12 +15183,13 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	return 0;
 }
 
-static int check_return_code(struct bpf_verifier_env *env, int regno)
+static int check_return_code(struct bpf_verifier_env *env, int regno, const char *reg_name)
 {
+	const char *exit_ctx = "At program exit";
 	struct tnum enforce_attach_type_range = tnum_unknown;
 	const struct bpf_prog *prog = env->prog;
 	struct bpf_reg_state *reg;
-	struct tnum range = tnum_range(0, 1), const_0 = tnum_const(0);
+	struct bpf_retval_range range = retval_range(0, 1);
 	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
 	int err;
 	struct bpf_func_state *frame = env->cur_state->frame[0];
@@ -15194,17 +15231,9 @@ static int check_return_code(struct bpf_verifier_env *env, int regno)
 
 	if (frame->in_async_callback_fn) {
 		/* enforce return zero from async callbacks like timer */
-		if (reg->type != SCALAR_VALUE) {
-			verbose(env, "In async callback the register R%d is not a known value (%s)\n",
-				regno, reg_type_str(env, reg->type));
-			return -EINVAL;
-		}
-
-		if (!tnum_in(const_0, reg->var_off)) {
-			verbose_invalid_scalar(env, reg, &const_0, "async callback", "R0");
-			return -EINVAL;
-		}
-		return 0;
+		exit_ctx = "At async callback return";
+		range = retval_range(0, 0);
+		goto enforce_retval;
 	}
 
 	if (is_subprog && !frame->in_exception_callback_fn) {
@@ -15227,14 +15256,14 @@ static int check_return_code(struct bpf_verifier_env *env, int regno)
 		    env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME ||
 		    env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME ||
 		    env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETSOCKNAME)
-			range = tnum_range(1, 1);
+			range = retval_range(1, 1);
 		if (env->prog->expected_attach_type == BPF_CGROUP_INET4_BIND ||
 		    env->prog->expected_attach_type == BPF_CGROUP_INET6_BIND)
-			range = tnum_range(0, 3);
+			range = retval_range(0, 3);
 		break;
 	case BPF_PROG_TYPE_CGROUP_SKB:
 		if (env->prog->expected_attach_type == BPF_CGROUP_INET_EGRESS) {
-			range = tnum_range(0, 3);
+			range = retval_range(0, 3);
 			enforce_attach_type_range = tnum_range(2, 3);
 		}
 		break;
@@ -15247,13 +15276,13 @@ static int check_return_code(struct bpf_verifier_env *env, int regno)
 	case BPF_PROG_TYPE_RAW_TRACEPOINT:
 		if (!env->prog->aux->attach_btf_id)
 			return 0;
-		range = tnum_const(0);
+		range = retval_range(0, 0);
 		break;
 	case BPF_PROG_TYPE_TRACING:
 		switch (env->prog->expected_attach_type) {
 		case BPF_TRACE_FENTRY:
 		case BPF_TRACE_FEXIT:
-			range = tnum_const(0);
+			range = retval_range(0, 0);
 			break;
 		case BPF_TRACE_RAW_TP:
 		case BPF_MODIFY_RETURN:
@@ -15265,7 +15294,7 @@ static int check_return_code(struct bpf_verifier_env *env, int regno)
 		}
 		break;
 	case BPF_PROG_TYPE_SK_LOOKUP:
-		range = tnum_range(SK_DROP, SK_PASS);
+		range = retval_range(SK_DROP, SK_PASS);
 		break;
 
 	case BPF_PROG_TYPE_LSM:
@@ -15279,12 +15308,12 @@ static int check_return_code(struct bpf_verifier_env *env, int regno)
 			/* Make sure programs that attach to void
 			 * hooks don't try to modify return value.
 			 */
-			range = tnum_range(1, 1);
+			range = retval_range(1, 1);
 		}
 		break;
 
 	case BPF_PROG_TYPE_NETFILTER:
-		range = tnum_range(NF_DROP, NF_ACCEPT);
+		range = retval_range(NF_DROP, NF_ACCEPT);
 		break;
 	case BPF_PROG_TYPE_EXT:
 		/* freplace program can return anything as its return value
@@ -15294,15 +15323,21 @@ static int check_return_code(struct bpf_verifier_env *env, int regno)
 		return 0;
 	}
 
+enforce_retval:
 	if (reg->type != SCALAR_VALUE) {
-		verbose(env, "At program exit the register R%d is not a known value (%s)\n",
-			regno, reg_type_str(env, reg->type));
+		verbose(env, "%s the register R%d is not a known value (%s)\n",
+			exit_ctx, regno, reg_type_str(env, reg->type));
 		return -EINVAL;
 	}
 
-	if (!tnum_in(range, reg->var_off)) {
-		verbose_invalid_scalar(env, reg, &range, "program exit", "R0");
-		if (prog->expected_attach_type == BPF_LSM_CGROUP &&
+	err = mark_chain_precision(env, regno);
+	if (err)
+		return err;
+
+	if (!retval_range_within(range, reg)) {
+		verbose_invalid_scalar(env, reg, range, exit_ctx, reg_name);
+		if (!is_subprog &&
+		    prog->expected_attach_type == BPF_LSM_CGROUP &&
 		    prog_type == BPF_PROG_TYPE_LSM &&
 		    !prog->aux->attach_func_proto->type)
 			verbose(env, "Note, BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n");
@@ -15375,6 +15410,15 @@ static bool is_force_checkpoint(struct bpf_verifier_env *env, int insn_idx)
 	return env->insn_aux_data[insn_idx].force_checkpoint;
 }
 
+static void mark_calls_callback(struct bpf_verifier_env *env, int idx)
+{
+	env->insn_aux_data[idx].calls_callback = true;
+}
+
+static bool calls_callback(struct bpf_verifier_env *env, int insn_idx)
+{
+	return env->insn_aux_data[insn_idx].calls_callback;
+}
 
 enum {
 	DONE_EXPLORING = 0,
@@ -15386,8 +15430,7 @@ enum {
  * w - next instruction
  * e - edge
  */
-static int push_insn(int t, int w, int e, struct bpf_verifier_env *env,
-		     bool loop_ok)
+static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
 {
 	int *insn_stack = env->cfg.insn_stack;
 	int *insn_state = env->cfg.insn_state;
@@ -15419,7 +15462,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env,
 		insn_stack[env->cfg.cur_stack++] = w;
 		return KEEP_EXPLORING;
 	} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
-		if (loop_ok && env->bpf_capable)
+		if (env->bpf_capable)
 			return DONE_EXPLORING;
 		verbose_linfo(env, t, "%d: ", t);
 		verbose_linfo(env, w, "%d: ", w);
@@ -15439,24 +15482,20 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns,
 				struct bpf_verifier_env *env,
 				bool visit_callee)
 {
-	int ret;
+	int ret, insn_sz;
 
-	ret = push_insn(t, t + 1, FALLTHROUGH, env, false);
+	insn_sz = bpf_is_ldimm64(&insns[t]) ? 2 : 1;
+	ret = push_insn(t, t + insn_sz, FALLTHROUGH, env);
 	if (ret)
 		return ret;
 
-	mark_prune_point(env, t + 1);
+	mark_prune_point(env, t + insn_sz);
 	/* when we exit from subprog, we need to record non-linear history */
-	mark_jmp_point(env, t + 1);
+	mark_jmp_point(env, t + insn_sz);
 
 	if (visit_callee) {
 		mark_prune_point(env, t);
-		ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env,
-				/* It's ok to allow recursion from CFG point of
-				 * view. __check_func_call() will do the actual
-				 * check.
-				 */
-				bpf_pseudo_func(insns + t));
+		ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env);
 	}
 	return ret;
 }
@@ -15469,15 +15508,17 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns,
 static int visit_insn(int t, struct bpf_verifier_env *env)
 {
 	struct bpf_insn *insns = env->prog->insnsi, *insn = &insns[t];
-	int ret, off;
+	int ret, off, insn_sz;
 
 	if (bpf_pseudo_func(insn))
 		return visit_func_call_insn(t, insns, env, true);
 
 	/* All non-branch instructions have a single fall-through edge. */
 	if (BPF_CLASS(insn->code) != BPF_JMP &&
-	    BPF_CLASS(insn->code) != BPF_JMP32)
-		return push_insn(t, t + 1, FALLTHROUGH, env, false);
+	    BPF_CLASS(insn->code) != BPF_JMP32) {
+		insn_sz = bpf_is_ldimm64(insn) ? 2 : 1;
+		return push_insn(t, t + insn_sz, FALLTHROUGH, env);
+	}
 
 	switch (BPF_OP(insn->code)) {
 	case BPF_EXIT:
@@ -15491,6 +15532,21 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
 			 * async state will be pushed for further exploration.
 			 */
 			mark_prune_point(env, t);
+		/* For functions that invoke callbacks it is not known how many times
+		 * callback would be called. Verifier models callback calling functions
+		 * by repeatedly visiting callback bodies and returning to origin call
+		 * instruction.
+		 * In order to stop such iteration verifier needs to identify when a
+		 * state identical some state from a previous iteration is reached.
+		 * Check below forces creation of checkpoint before callback calling
+		 * instruction to allow search for such identical states.
+		 */
+		if (is_sync_callback_calling_insn(insn)) {
+			mark_calls_callback(env, t);
+			mark_force_checkpoint(env, t);
+			mark_prune_point(env, t);
+			mark_jmp_point(env, t);
+		}
 		if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) {
 			struct bpf_kfunc_call_arg_meta meta;
 
@@ -15523,8 +15579,7 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
 			off = insn->imm;
 
 		/* unconditional jump with single edge */
-		ret = push_insn(t, t + off + 1, FALLTHROUGH, env,
-				true);
+		ret = push_insn(t, t + off + 1, FALLTHROUGH, env);
 		if (ret)
 			return ret;
 
@@ -15537,11 +15592,11 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
 		/* conditional jump with two edges */
 		mark_prune_point(env, t);
 
-		ret = push_insn(t, t + 1, FALLTHROUGH, env, true);
+		ret = push_insn(t, t + 1, FALLTHROUGH, env);
 		if (ret)
 			return ret;
 
-		return push_insn(t, t + insn->off + 1, BRANCH, env, true);
+		return push_insn(t, t + insn->off + 1, BRANCH, env);
 	}
 }
 
@@ -15607,11 +15662,21 @@ walk_cfg:
 	}
 
 	for (i = 0; i < insn_cnt; i++) {
+		struct bpf_insn *insn = &env->prog->insnsi[i];
+
 		if (insn_state[i] != EXPLORED) {
 			verbose(env, "unreachable insn %d\n", i);
 			ret = -EINVAL;
 			goto err_free;
 		}
+		if (bpf_is_ldimm64(insn)) {
+			if (insn_state[i + 1] != 0) {
+				verbose(env, "jump into the middle of ldimm64 insn %d\n", i);
+				ret = -EINVAL;
+				goto err_free;
+			}
+			i++; /* skip second half of ldimm64 */
+		}
 	}
 	ret = 0; /* cfg looks good */
 
@@ -16951,10 +17016,16 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 				}
 				goto skip_inf_loop_check;
 			}
+			if (calls_callback(env, insn_idx)) {
+				if (states_equal(env, &sl->state, cur, true))
+					goto hit;
+				goto skip_inf_loop_check;
+			}
 			/* attempt to detect infinite loop to avoid unnecessary doomed work */
 			if (states_maybe_looping(&sl->state, cur) &&
 			    states_equal(env, &sl->state, cur, false) &&
-			    !iter_active_depths_differ(&sl->state, cur)) {
+			    !iter_active_depths_differ(&sl->state, cur) &&
+			    sl->state.callback_unroll_depth == cur->callback_unroll_depth) {
 				verbose_linfo(env, insn_idx, "; ");
 				verbose(env, "infinite loop detected at insn %d\n", insn_idx);
 				verbose(env, "cur state:");
@@ -17031,7 +17102,8 @@ hit:
 			 * the precision needs to be propagated back in
 			 * the current state.
 			 */
-			err = err ? : push_jmp_history(env, cur);
+			if (is_jmp_point(env, env->insn_idx))
+				err = err ? : push_jmp_history(env, cur, 0);
 			err = err ? : propagate_precision(env, &sl->state);
 			if (err)
 				return err;
@@ -17256,6 +17328,9 @@ static int do_check(struct bpf_verifier_env *env)
 		u8 class;
 		int err;
 
+		/* reset current history entry on each new instruction */
+		env->cur_hist_ent = NULL;
+
 		env->prev_insn_idx = prev_insn_idx;
 		if (env->insn_idx >= insn_cnt) {
 			verbose(env, "invalid insn idx %d insn_cnt %d\n",
@@ -17295,7 +17370,7 @@ static int do_check(struct bpf_verifier_env *env)
 		}
 
 		if (is_jmp_point(env, env->insn_idx)) {
-			err = push_jmp_history(env, state);
+			err = push_jmp_history(env, state, 0);
 			if (err)
 				return err;
 		}
@@ -17372,10 +17447,8 @@ static int do_check(struct bpf_verifier_env *env)
 					       insn->off, BPF_SIZE(insn->code),
 					       BPF_READ, insn->dst_reg, false,
 					       BPF_MODE(insn->code) == BPF_MEMSX);
-			if (err)
-				return err;
-
-			err = save_aux_ptr_type(env, src_reg_type, true);
+			err = err ?: save_aux_ptr_type(env, src_reg_type, true);
+			err = err ?: reg_bounds_sanity_check(env, &regs[insn->dst_reg], "ldx");
 			if (err)
 				return err;
 		} else if (class == BPF_STX) {
@@ -17551,7 +17624,7 @@ process_bpf_exit_full:
 					continue;
 				}
 
-				err = check_return_code(env, BPF_REG_0);
+				err = check_return_code(env, BPF_REG_0, "R0");
 				if (err)
 					return err;
 process_bpf_exit:
@@ -18012,10 +18085,12 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
 				return -E2BIG;
 			}
 
+			if (env->prog->aux->sleepable)
+				atomic64_inc(&map->sleepable_refcnt);
 			/* hold the map. If the program is rejected by verifier,
 			 * the map will be released by release_maps() or it
 			 * will be used by the valid program until it's unloaded
-			 * and all maps are released in free_used_maps()
+			 * and all maps are released in bpf_free_used_maps()
 			 */
 			bpf_map_inc(map);
 
@@ -19232,9 +19307,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 
 		env->exception_callback_subprog = env->subprog_cnt - 1;
 		/* Don't update insn_cnt, as add_hidden_subprog always appends insns */
-		env->subprog_info[env->exception_callback_subprog].is_cb = true;
-		env->subprog_info[env->exception_callback_subprog].is_async_cb = true;
-		env->subprog_info[env->exception_callback_subprog].is_exception_cb = true;
+		mark_subprog_exc_cb(env, env->exception_callback_subprog);
 	}
 
 	for (i = 0; i < insn_cnt; i++, insn++) {
@@ -19934,9 +20007,10 @@ static void free_states(struct bpf_verifier_env *env)
 	}
 }
 
-static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_ex_cb)
+static int do_check_common(struct bpf_verifier_env *env, int subprog)
 {
 	bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
+	struct bpf_subprog_info *sub = subprog_info(env, subprog);
 	struct bpf_verifier_state *state;
 	struct bpf_reg_state *regs;
 	int ret, i;
@@ -19963,46 +20037,71 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_ex
 	state->first_insn_idx = env->subprog_info[subprog].start;
 	state->last_insn_idx = -1;
 
+
 	regs = state->frame[state->curframe]->regs;
 	if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) {
-		ret = btf_prepare_func_args(env, subprog, regs, is_ex_cb);
+		const char *sub_name = subprog_name(env, subprog);
+		struct bpf_subprog_arg_info *arg;
+		struct bpf_reg_state *reg;
+
+		verbose(env, "Validating %s() func#%d...\n", sub_name, subprog);
+		ret = btf_prepare_func_args(env, subprog);
 		if (ret)
 			goto out;
-		for (i = BPF_REG_1; i <= BPF_REG_5; i++) {
-			if (regs[i].type == PTR_TO_CTX)
+
+		if (subprog_is_exc_cb(env, subprog)) {
+			state->frame[0]->in_exception_callback_fn = true;
+			/* We have already ensured that the callback returns an integer, just
+			 * like all global subprogs. We need to determine it only has a single
+			 * scalar argument.
+			 */
+			if (sub->arg_cnt != 1 || sub->args[0].arg_type != ARG_ANYTHING) {
+				verbose(env, "exception cb only supports single integer argument\n");
+				ret = -EINVAL;
+				goto out;
+			}
+		}
+		for (i = BPF_REG_1; i <= sub->arg_cnt; i++) {
+			arg = &sub->args[i - BPF_REG_1];
+			reg = &regs[i];
+
+			if (arg->arg_type == ARG_PTR_TO_CTX) {
+				reg->type = PTR_TO_CTX;
 				mark_reg_known_zero(env, regs, i);
-			else if (regs[i].type == SCALAR_VALUE)
+			} else if (arg->arg_type == ARG_ANYTHING) {
+				reg->type = SCALAR_VALUE;
 				mark_reg_unknown(env, regs, i);
-			else if (base_type(regs[i].type) == PTR_TO_MEM) {
-				const u32 mem_size = regs[i].mem_size;
-
+			} else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) {
+				/* assume unspecial LOCAL dynptr type */
+				__mark_dynptr_reg(reg, BPF_DYNPTR_TYPE_LOCAL, true, ++env->id_gen);
+			} else if (base_type(arg->arg_type) == ARG_PTR_TO_MEM) {
+				reg->type = PTR_TO_MEM;
+				if (arg->arg_type & PTR_MAYBE_NULL)
+					reg->type |= PTR_MAYBE_NULL;
 				mark_reg_known_zero(env, regs, i);
-				regs[i].mem_size = mem_size;
-				regs[i].id = ++env->id_gen;
+				reg->mem_size = arg->mem_size;
+				reg->id = ++env->id_gen;
+			} else {
+				WARN_ONCE(1, "BUG: unhandled arg#%d type %d\n",
+					  i - BPF_REG_1, arg->arg_type);
+				ret = -EFAULT;
+				goto out;
 			}
 		}
-		if (is_ex_cb) {
-			state->frame[0]->in_exception_callback_fn = true;
-			env->subprog_info[subprog].is_cb = true;
-			env->subprog_info[subprog].is_async_cb = true;
-			env->subprog_info[subprog].is_exception_cb = true;
-		}
 	} else {
+		/* if main BPF program has associated BTF info, validate that
+		 * it's matching expected signature, and otherwise mark BTF
+		 * info for main program as unreliable
+		 */
+		if (env->prog->aux->func_info_aux) {
+			ret = btf_prepare_func_args(env, 0);
+			if (ret || sub->arg_cnt != 1 || sub->args[0].arg_type != ARG_PTR_TO_CTX)
+				env->prog->aux->func_info_aux[0].unreliable = true;
+		}
+
 		/* 1st arg to a function */
 		regs[BPF_REG_1].type = PTR_TO_CTX;
 		mark_reg_known_zero(env, regs, BPF_REG_1);
-		ret = btf_check_subprog_arg_match(env, subprog, regs);
-		if (ret == -EFAULT)
-			/* unlikely verifier bug. abort.
-			 * ret == 0 and ret < 0 are sadly acceptable for
-			 * main() function due to backward compatibility.
-			 * Like socket filter program may be written as:
-			 * int bpf_prog(struct pt_regs *ctx)
-			 * and never dereference that ctx in the program.
-			 * 'struct pt_regs' is a type mismatch for socket
-			 * filter that should be using 'struct __sk_buff'.
-			 */
-			goto out;
 	}
 
 	ret = do_check(env);
@@ -20021,8 +20120,11 @@ out:
 	return ret;
 }
 
-/* Verify all global functions in a BPF program one by one based on their BTF.
- * All global functions must pass verification. Otherwise the whole program is rejected.
+/* Lazily verify all global functions based on their BTF, if they are called
+ * from main BPF program or any of subprograms transitively.
+ * BPF global subprogs called from dead code are not validated.
+ * All callable global functions must pass verification.
+ * Otherwise the whole program is rejected.
  * Consider:
  * int bar(int);
  * int foo(int f)
@@ -20041,25 +20143,50 @@ out:
 static int do_check_subprogs(struct bpf_verifier_env *env)
 {
 	struct bpf_prog_aux *aux = env->prog->aux;
-	int i, ret;
+	struct bpf_func_info_aux *sub_aux;
+	int i, ret, new_cnt;
 
 	if (!aux->func_info)
 		return 0;
 
+	/* exception callback is presumed to be always called */
+	if (env->exception_callback_subprog)
+		subprog_aux(env, env->exception_callback_subprog)->called = true;
+
+again:
+	new_cnt = 0;
 	for (i = 1; i < env->subprog_cnt; i++) {
-		if (aux->func_info_aux[i].linkage != BTF_FUNC_GLOBAL)
+		if (!subprog_is_global(env, i))
+			continue;
+
+		sub_aux = subprog_aux(env, i);
+		if (!sub_aux->called || sub_aux->verified)
 			continue;
+
 		env->insn_idx = env->subprog_info[i].start;
 		WARN_ON_ONCE(env->insn_idx == 0);
-		ret = do_check_common(env, i, env->exception_callback_subprog == i);
+		ret = do_check_common(env, i);
 		if (ret) {
 			return ret;
 		} else if (env->log.level & BPF_LOG_LEVEL) {
-			verbose(env,
-				"Func#%d is safe for any args that match its prototype\n",
-				i);
+			verbose(env, "Func#%d ('%s') is safe for any args that match its prototype\n",
+				i, subprog_name(env, i));
 		}
+
+		/* We verified new global subprog, it might have called some
+		 * more global subprogs that we haven't verified yet, so we
+		 * need to do another pass over subprogs to verify those.
+		 */
+		sub_aux->verified = true;
+		new_cnt++;
 	}
+
+	/* We can't loop forever as we verify at least one global subprog on
+	 * each pass.
+	 */
+	if (new_cnt)
+		goto again;
+
 	return 0;
 }
 
@@ -20068,7 +20195,7 @@ static int do_check_main(struct bpf_verifier_env *env)
 	int ret;
 
 	env->insn_idx = 0;
-	ret = do_check_common(env, 0, false);
+	ret = do_check_common(env, 0);
 	if (!ret)
 		env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
 	return ret;
@@ -20190,6 +20317,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 			    struct bpf_attach_target_info *tgt_info)
 {
 	bool prog_extension = prog->type == BPF_PROG_TYPE_EXT;
+	bool prog_tracing = prog->type == BPF_PROG_TYPE_TRACING;
 	const char prefix[] = "btf_trace_";
 	int ret = 0, subprog = -1, i;
 	const struct btf_type *t;
@@ -20260,10 +20388,21 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 			bpf_log(log, "Can attach to only JITed progs\n");
 			return -EINVAL;
 		}
-		if (tgt_prog->type == prog->type) {
-			/* Cannot fentry/fexit another fentry/fexit program.
-			 * Cannot attach program extension to another extension.
-			 * It's ok to attach fentry/fexit to extension program.
+		if (prog_tracing) {
+			if (aux->attach_tracing_prog) {
+				/*
+				 * Target program is an fentry/fexit which is already attached
+				 * to another tracing program. More levels of nesting
+				 * attachment are not allowed.
+				 */
+				bpf_log(log, "Cannot nest tracing program attach more than once\n");
+				return -EINVAL;
+			}
+		} else if (tgt_prog->type == prog->type) {
+			/*
+			 * To avoid potential call chain cycles, prevent attaching of a
+			 * program extension to another extension. It's ok to attach
+			 * fentry/fexit to extension program.
 			 */
 			bpf_log(log, "Cannot recursively attach\n");
 			return -EINVAL;
@@ -20276,16 +20415,15 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 			 * except fentry/fexit. The reason is the following.
 			 * The fentry/fexit programs are used for performance
 			 * analysis, stats and can be attached to any program
-			 * type except themselves. When extension program is
-			 * replacing XDP function it is necessary to allow
-			 * performance analysis of all functions. Both original
-			 * XDP program and its program extension. Hence
-			 * attaching fentry/fexit to BPF_PROG_TYPE_EXT is
-			 * allowed. If extending of fentry/fexit was allowed it
-			 * would be possible to create long call chain
-			 * fentry->extension->fentry->extension beyond
-			 * reasonable stack size. Hence extending fentry is not
-			 * allowed.
+			 * type. When extension program is replacing XDP function
+			 * it is necessary to allow performance analysis of all
+			 * functions. Both original XDP program and its program
+			 * extension. Hence attaching fentry/fexit to
+			 * BPF_PROG_TYPE_EXT is allowed. If extending of
+			 * fentry/fexit was allowed it would be possible to create
+			 * long call chain fentry->extension->fentry->extension
+			 * beyond reasonable stack size. Hence extending fentry
+			 * is not allowed.
 			 */
 			bpf_log(log, "Cannot extend fentry/fexit\n");
 			return -EINVAL;
@@ -20662,6 +20800,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 
 	if (is_priv)
 		env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ;
+	env->test_reg_invariants = attr->prog_flags & BPF_F_TEST_REG_INVARIANTS;
 
 	env->explored_states = kvcalloc(state_htab_size(env),
 				       sizeof(struct bpf_verifier_state_list *),
@@ -20704,8 +20843,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 	if (ret < 0)
 		goto skip_full_check;
 
-	ret = do_check_subprogs(env);
-	ret = ret ?: do_check_main(env);
+	ret = do_check_main(env);
+	ret = ret ?: do_check_subprogs(env);
 
 	if (ret == 0 && bpf_prog_is_offloaded(env->prog->aux))
 		ret = bpf_prog_offload_finalize(env);
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index c56071f150f2..520b90dd97ec 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -164,13 +164,13 @@ struct cgroup_mgctx {
 #define DEFINE_CGROUP_MGCTX(name)						\
 	struct cgroup_mgctx name = CGROUP_MGCTX_INIT(name)
 
-extern spinlock_t css_set_lock;
 extern struct cgroup_subsys *cgroup_subsys[];
 extern struct list_head cgroup_roots;
 
 /* iterate across the hierarchies */
 #define for_each_root(root)						\
-	list_for_each_entry((root), &cgroup_roots, root_list)
+	list_for_each_entry_rcu((root), &cgroup_roots, root_list,	\
+				lockdep_is_held(&cgroup_mutex))
 
 /**
  * for_each_subsys - iterate all enabled cgroup subsystems
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 76db6c67e39a..04d11a7dd95f 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -1262,6 +1262,40 @@ int cgroup1_get_tree(struct fs_context *fc)
 	return ret;
 }
 
+/**
+ * task_get_cgroup1 - Acquires the associated cgroup of a task within a
+ * specific cgroup1 hierarchy. The cgroup1 hierarchy is identified by its
+ * hierarchy ID.
+ * @tsk: The target task
+ * @hierarchy_id: The ID of a cgroup1 hierarchy
+ *
+ * On success, the cgroup is returned. On failure, ERR_PTR is returned.
+ * We limit it to cgroup1 only.
+ */
+struct cgroup *task_get_cgroup1(struct task_struct *tsk, int hierarchy_id)
+{
+	struct cgroup *cgrp = ERR_PTR(-ENOENT);
+	struct cgroup_root *root;
+	unsigned long flags;
+
+	rcu_read_lock();
+	for_each_root(root) {
+		/* cgroup1 only*/
+		if (root == &cgrp_dfl_root)
+			continue;
+		if (root->hierarchy_id != hierarchy_id)
+			continue;
+		spin_lock_irqsave(&css_set_lock, flags);
+		cgrp = task_cgroup_from_root(tsk, root);
+		if (!cgrp || !cgroup_tryget(cgrp))
+			cgrp = ERR_PTR(-ENOENT);
+		spin_unlock_irqrestore(&css_set_lock, flags);
+		break;
+	}
+	rcu_read_unlock();
+	return cgrp;
+}
+
 static int __init cgroup1_wq_init(void)
 {
 	/*
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 1d5b9de3b1b9..8f3cef1a4d8a 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1315,7 +1315,7 @@ static void cgroup_exit_root_id(struct cgroup_root *root)
 
 void cgroup_free_root(struct cgroup_root *root)
 {
-	kfree(root);
+	kfree_rcu(root, rcu);
 }
 
 static void cgroup_destroy_root(struct cgroup_root *root)
@@ -1347,10 +1347,9 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 
 	spin_unlock_irq(&css_set_lock);
 
-	if (!list_empty(&root->root_list)) {
-		list_del(&root->root_list);
-		cgroup_root_count--;
-	}
+	WARN_ON_ONCE(list_empty(&root->root_list));
+	list_del_rcu(&root->root_list);
+	cgroup_root_count--;
 
 	if (!have_favordynmods)
 		cgroup_favor_dynmods(root, false);
@@ -1390,7 +1389,15 @@ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset,
 		}
 	}
 
-	BUG_ON(!res_cgroup);
+	/*
+	 * If cgroup_mutex is not held, the cgrp_cset_link will be freed
+	 * before we remove the cgroup root from the root_list. Consequently,
+	 * when accessing a cgroup root, the cset_link may have already been
+	 * freed, resulting in a NULL res_cgroup. However, by holding the
+	 * cgroup_mutex, we ensure that res_cgroup can't be NULL.
+	 * If we don't hold cgroup_mutex in the caller, we must do the NULL
+	 * check.
+	 */
 	return res_cgroup;
 }
 
@@ -1413,6 +1420,11 @@ current_cgns_cgroup_from_root(struct cgroup_root *root)
 
 	rcu_read_unlock();
 
+	/*
+	 * The namespace_sem is held by current, so the root cgroup can't
+	 * be umounted. Therefore, we can ensure that the res is non-NULL.
+	 */
+	WARN_ON_ONCE(!res);
 	return res;
 }
 
@@ -1449,7 +1461,6 @@ static struct cgroup *current_cgns_cgroup_dfl(void)
 static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
 					    struct cgroup_root *root)
 {
-	lockdep_assert_held(&cgroup_mutex);
 	lockdep_assert_held(&css_set_lock);
 
 	return __cset_cgroup_from_root(cset, root);
@@ -1457,7 +1468,9 @@ static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
 
 /*
  * Return the cgroup for "task" from the given hierarchy. Must be
- * called with cgroup_mutex and css_set_lock held.
+ * called with css_set_lock held to prevent task's groups from being modified.
+ * Must be called with either cgroup_mutex or rcu read lock to prevent the
+ * cgroup root from being destroyed.
  */
 struct cgroup *task_cgroup_from_root(struct task_struct *task,
 				     struct cgroup_root *root)
@@ -2032,7 +2045,7 @@ void init_cgroup_root(struct cgroup_fs_context *ctx)
 	struct cgroup_root *root = ctx->root;
 	struct cgroup *cgrp = &root->cgrp;
 
-	INIT_LIST_HEAD(&root->root_list);
+	INIT_LIST_HEAD_RCU(&root->root_list);
 	atomic_set(&root->nr_cgrps, 1);
 	cgrp->root = root;
 	init_cgroup_housekeeping(cgrp);
@@ -2115,7 +2128,7 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 	 * care of subsystems' refcounts, which are explicitly dropped in
 	 * the failure exit path.
 	 */
-	list_add(&root->root_list, &cgroup_roots);
+	list_add_rcu(&root->root_list, &cgroup_roots);
 	cgroup_root_count++;
 
 	/*
@@ -3885,14 +3898,6 @@ static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of,
 	return psi_trigger_poll(&ctx->psi.trigger, of->file, pt);
 }
 
-static int cgroup_pressure_open(struct kernfs_open_file *of)
-{
-	if (of->file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE))
-		return -EPERM;
-
-	return 0;
-}
-
 static void cgroup_pressure_release(struct kernfs_open_file *of)
 {
 	struct cgroup_file_ctx *ctx = of->priv;
@@ -5299,7 +5304,6 @@ static struct cftype cgroup_psi_files[] = {
 	{
 		.name = "io.pressure",
 		.file_offset = offsetof(struct cgroup, psi_files[PSI_IO]),
-		.open = cgroup_pressure_open,
 		.seq_show = cgroup_io_pressure_show,
 		.write = cgroup_io_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5308,7 +5312,6 @@ static struct cftype cgroup_psi_files[] = {
 	{
 		.name = "memory.pressure",
 		.file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]),
-		.open = cgroup_pressure_open,
 		.seq_show = cgroup_memory_pressure_show,
 		.write = cgroup_memory_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5317,7 +5320,6 @@ static struct cftype cgroup_psi_files[] = {
 	{
 		.name = "cpu.pressure",
 		.file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]),
-		.open = cgroup_pressure_open,
 		.seq_show = cgroup_cpu_pressure_show,
 		.write = cgroup_cpu_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5327,7 +5329,6 @@ static struct cftype cgroup_psi_files[] = {
 	{
 		.name = "irq.pressure",
 		.file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]),
-		.open = cgroup_pressure_open,
 		.seq_show = cgroup_irq_pressure_show,
 		.write = cgroup_irq_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -6277,7 +6278,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 	if (!buf)
 		goto out;
 
-	cgroup_lock();
+	rcu_read_lock();
 	spin_lock_irq(&css_set_lock);
 
 	for_each_root(root) {
@@ -6288,6 +6289,11 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 		if (root == &cgrp_dfl_root && !READ_ONCE(cgrp_dfl_visible))
 			continue;
 
+		cgrp = task_cgroup_from_root(tsk, root);
+		/* The root has already been unmounted. */
+		if (!cgrp)
+			continue;
+
 		seq_printf(m, "%d:", root->hierarchy_id);
 		if (root != &cgrp_dfl_root)
 			for_each_subsys(ss, ssid)
@@ -6298,9 +6304,6 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 			seq_printf(m, "%sname=%s", count ? "," : "",
 				   root->name);
 		seq_putc(m, ':');
-
-		cgrp = task_cgroup_from_root(tsk, root);
-
 		/*
 		 * On traditional hierarchies, all zombie tasks show up as
 		 * belonging to the root cgroup.  On the default hierarchy,
@@ -6332,7 +6335,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 	retval = 0;
 out_unlock:
 	spin_unlock_irq(&css_set_lock);
-	cgroup_unlock();
+	rcu_read_unlock();
 	kfree(buf);
 out:
 	return retval;
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 615daaf87f1f..dfbb16aca9f4 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -25,6 +25,7 @@
 #include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/cpuset.h>
+#include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
@@ -43,6 +44,7 @@
 #include <linux/sched/isolation.h>
 #include <linux/cgroup.h>
 #include <linux/wait.h>
+#include <linux/workqueue.h>
 
 DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key);
 DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key);
@@ -204,6 +206,11 @@ struct cpuset {
  */
 static cpumask_var_t	subpartitions_cpus;
 
+/*
+ * Exclusive CPUs in isolated partitions
+ */
+static cpumask_var_t	isolated_cpus;
+
 /* List of remote partition root children */
 static struct list_head remote_children;
 
@@ -1317,6 +1324,7 @@ static void compute_effective_cpumask(struct cpumask *new_cpus,
  */
 enum partition_cmd {
 	partcmd_enable,		/* Enable partition root	  */
+	partcmd_enablei,	/* Enable isolated partition root */
 	partcmd_disable,	/* Disable partition root	  */
 	partcmd_update,		/* Update parent's effective_cpus */
 	partcmd_invalidate,	/* Make partition invalid	  */
@@ -1419,6 +1427,109 @@ static void reset_partition_data(struct cpuset *cs)
 }
 
 /*
+ * partition_xcpus_newstate - Exclusive CPUs state change
+ * @old_prs: old partition_root_state
+ * @new_prs: new partition_root_state
+ * @xcpus: exclusive CPUs with state change
+ */
+static void partition_xcpus_newstate(int old_prs, int new_prs, struct cpumask *xcpus)
+{
+	WARN_ON_ONCE(old_prs == new_prs);
+	if (new_prs == PRS_ISOLATED)
+		cpumask_or(isolated_cpus, isolated_cpus, xcpus);
+	else
+		cpumask_andnot(isolated_cpus, isolated_cpus, xcpus);
+}
+
+/*
+ * partition_xcpus_add - Add new exclusive CPUs to partition
+ * @new_prs: new partition_root_state
+ * @parent: parent cpuset
+ * @xcpus: exclusive CPUs to be added
+ * Return: true if isolated_cpus modified, false otherwise
+ *
+ * Remote partition if parent == NULL
+ */
+static bool partition_xcpus_add(int new_prs, struct cpuset *parent,
+				struct cpumask *xcpus)
+{
+	bool isolcpus_updated;
+
+	WARN_ON_ONCE(new_prs < 0);
+	lockdep_assert_held(&callback_lock);
+	if (!parent)
+		parent = &top_cpuset;
+
+
+	if (parent == &top_cpuset)
+		cpumask_or(subpartitions_cpus, subpartitions_cpus, xcpus);
+
+	isolcpus_updated = (new_prs != parent->partition_root_state);
+	if (isolcpus_updated)
+		partition_xcpus_newstate(parent->partition_root_state, new_prs,
+					 xcpus);
+
+	cpumask_andnot(parent->effective_cpus, parent->effective_cpus, xcpus);
+	return isolcpus_updated;
+}
+
+/*
+ * partition_xcpus_del - Remove exclusive CPUs from partition
+ * @old_prs: old partition_root_state
+ * @parent: parent cpuset
+ * @xcpus: exclusive CPUs to be removed
+ * Return: true if isolated_cpus modified, false otherwise
+ *
+ * Remote partition if parent == NULL
+ */
+static bool partition_xcpus_del(int old_prs, struct cpuset *parent,
+				struct cpumask *xcpus)
+{
+	bool isolcpus_updated;
+
+	WARN_ON_ONCE(old_prs < 0);
+	lockdep_assert_held(&callback_lock);
+	if (!parent)
+		parent = &top_cpuset;
+
+	if (parent == &top_cpuset)
+		cpumask_andnot(subpartitions_cpus, subpartitions_cpus, xcpus);
+
+	isolcpus_updated = (old_prs != parent->partition_root_state);
+	if (isolcpus_updated)
+		partition_xcpus_newstate(old_prs, parent->partition_root_state,
+					 xcpus);
+
+	cpumask_and(xcpus, xcpus, cpu_active_mask);
+	cpumask_or(parent->effective_cpus, parent->effective_cpus, xcpus);
+	return isolcpus_updated;
+}
+
+static void update_unbound_workqueue_cpumask(bool isolcpus_updated)
+{
+	int ret;
+
+	lockdep_assert_cpus_held();
+
+	if (!isolcpus_updated)
+		return;
+
+	ret = workqueue_unbound_exclude_cpumask(isolated_cpus);
+	WARN_ON_ONCE(ret < 0);
+}
+
+/**
+ * cpuset_cpu_is_isolated - Check if the given CPU is isolated
+ * @cpu: the CPU number to be checked
+ * Return: true if CPU is used in an isolated partition, false otherwise
+ */
+bool cpuset_cpu_is_isolated(int cpu)
+{
+	return cpumask_test_cpu(cpu, isolated_cpus);
+}
+EXPORT_SYMBOL_GPL(cpuset_cpu_is_isolated);
+
+/*
  * compute_effective_exclusive_cpumask - compute effective exclusive CPUs
  * @cs: cpuset
  * @xcpus: effective exclusive CPUs value to be set
@@ -1456,14 +1567,18 @@ static inline bool is_local_partition(struct cpuset *cs)
 /*
  * remote_partition_enable - Enable current cpuset as a remote partition root
  * @cs: the cpuset to update
+ * @new_prs: new partition_root_state
  * @tmp: temparary masks
  * Return: 1 if successful, 0 if error
  *
  * Enable the current cpuset to become a remote partition root taking CPUs
  * directly from the top cpuset. cpuset_mutex must be held by the caller.
  */
-static int remote_partition_enable(struct cpuset *cs, struct tmpmasks *tmp)
+static int remote_partition_enable(struct cpuset *cs, int new_prs,
+				   struct tmpmasks *tmp)
 {
+	bool isolcpus_updated;
+
 	/*
 	 * The user must have sysadmin privilege.
 	 */
@@ -1485,26 +1600,22 @@ static int remote_partition_enable(struct cpuset *cs, struct tmpmasks *tmp)
 		return 0;
 
 	spin_lock_irq(&callback_lock);
-	cpumask_andnot(top_cpuset.effective_cpus,
-		       top_cpuset.effective_cpus, tmp->new_cpus);
-	cpumask_or(subpartitions_cpus,
-		   subpartitions_cpus, tmp->new_cpus);
-
+	isolcpus_updated = partition_xcpus_add(new_prs, NULL, tmp->new_cpus);
+	list_add(&cs->remote_sibling, &remote_children);
 	if (cs->use_parent_ecpus) {
 		struct cpuset *parent = parent_cs(cs);
 
 		cs->use_parent_ecpus = false;
 		parent->child_ecpus_count--;
 	}
-	list_add(&cs->remote_sibling, &remote_children);
 	spin_unlock_irq(&callback_lock);
+	update_unbound_workqueue_cpumask(isolcpus_updated);
 
 	/*
 	 * Proprogate changes in top_cpuset's effective_cpus down the hierarchy.
 	 */
 	update_tasks_cpumask(&top_cpuset, tmp->new_cpus);
 	update_sibling_cpumasks(&top_cpuset, NULL, tmp);
-
 	return 1;
 }
 
@@ -1519,23 +1630,22 @@ static int remote_partition_enable(struct cpuset *cs, struct tmpmasks *tmp)
  */
 static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp)
 {
+	bool isolcpus_updated;
+
 	compute_effective_exclusive_cpumask(cs, tmp->new_cpus);
 	WARN_ON_ONCE(!is_remote_partition(cs));
 	WARN_ON_ONCE(!cpumask_subset(tmp->new_cpus, subpartitions_cpus));
 
 	spin_lock_irq(&callback_lock);
-	cpumask_andnot(subpartitions_cpus,
-		       subpartitions_cpus, tmp->new_cpus);
-	cpumask_and(tmp->new_cpus,
-		    tmp->new_cpus, cpu_active_mask);
-	cpumask_or(top_cpuset.effective_cpus,
-		   top_cpuset.effective_cpus, tmp->new_cpus);
 	list_del_init(&cs->remote_sibling);
+	isolcpus_updated = partition_xcpus_del(cs->partition_root_state,
+					       NULL, tmp->new_cpus);
 	cs->partition_root_state = -cs->partition_root_state;
 	if (!cs->prs_err)
 		cs->prs_err = PERR_INVCPUS;
 	reset_partition_data(cs);
 	spin_unlock_irq(&callback_lock);
+	update_unbound_workqueue_cpumask(isolcpus_updated);
 
 	/*
 	 * Proprogate changes in top_cpuset's effective_cpus down the hierarchy.
@@ -1557,6 +1667,8 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *newmask,
 			       struct tmpmasks *tmp)
 {
 	bool adding, deleting;
+	int prs = cs->partition_root_state;
+	int isolcpus_updated = 0;
 
 	if (WARN_ON_ONCE(!is_remote_partition(cs)))
 		return;
@@ -1580,21 +1692,12 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *newmask,
 		goto invalidate;
 
 	spin_lock_irq(&callback_lock);
-	if (adding) {
-		cpumask_or(subpartitions_cpus,
-			   subpartitions_cpus, tmp->addmask);
-		cpumask_andnot(top_cpuset.effective_cpus,
-			       top_cpuset.effective_cpus, tmp->addmask);
-	}
-	if (deleting) {
-		cpumask_andnot(subpartitions_cpus,
-			       subpartitions_cpus, tmp->delmask);
-		cpumask_and(tmp->delmask,
-			    tmp->delmask, cpu_active_mask);
-		cpumask_or(top_cpuset.effective_cpus,
-			   top_cpuset.effective_cpus, tmp->delmask);
-	}
+	if (adding)
+		isolcpus_updated += partition_xcpus_add(prs, NULL, tmp->addmask);
+	if (deleting)
+		isolcpus_updated += partition_xcpus_del(prs, NULL, tmp->delmask);
 	spin_unlock_irq(&callback_lock);
+	update_unbound_workqueue_cpumask(isolcpus_updated);
 
 	/*
 	 * Proprogate changes in top_cpuset's effective_cpus down the hierarchy.
@@ -1676,11 +1779,11 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus)
  * @tmp:     Temporary addmask and delmask
  * Return:   0 or a partition root state error code
  *
- * For partcmd_enable, the cpuset is being transformed from a non-partition
- * root to a partition root. The effective_xcpus (cpus_allowed if effective_xcpus
- * not set) mask of the given cpuset will be taken away from parent's
- * effective_cpus. The function will return 0 if all the CPUs listed in
- * effective_xcpus can be granted or an error code will be returned.
+ * For partcmd_enable*, the cpuset is being transformed from a non-partition
+ * root to a partition root. The effective_xcpus (cpus_allowed if
+ * effective_xcpus not set) mask of the given cpuset will be taken away from
+ * parent's effective_cpus. The function will return 0 if all the CPUs listed
+ * in effective_xcpus can be granted or an error code will be returned.
  *
  * For partcmd_disable, the cpuset is being transformed from a partition
  * root back to a non-partition root. Any CPUs in effective_xcpus will be
@@ -1695,7 +1798,7 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus)
  *
  * For partcmd_invalidate, the current partition will be made invalid.
  *
- * The partcmd_enable and partcmd_disable commands are used by
+ * The partcmd_enable* and partcmd_disable commands are used by
  * update_prstate(). An error code may be returned and the caller will check
  * for error.
  *
@@ -1716,6 +1819,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 	int part_error = PERR_NONE;	/* Partition error? */
 	int subparts_delta = 0;
 	struct cpumask *xcpus;		/* cs effective_xcpus */
+	int isolcpus_updated = 0;
 	bool nocpu;
 
 	lockdep_assert_held(&cpuset_mutex);
@@ -1760,7 +1864,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 
 	nocpu = tasks_nocpu_error(parent, cs, xcpus);
 
-	if (cmd == partcmd_enable) {
+	if ((cmd == partcmd_enable) || (cmd == partcmd_enablei)) {
 		/*
 		 * Enabling partition root is not allowed if its
 		 * effective_xcpus is empty or doesn't overlap with
@@ -1783,6 +1887,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 		cpumask_copy(tmp->delmask, xcpus);
 		deleting = true;
 		subparts_delta++;
+		new_prs = (cmd == partcmd_enable) ? PRS_ROOT : PRS_ISOLATED;
 	} else if (cmd == partcmd_disable) {
 		/*
 		 * May need to add cpus to parent's effective_cpus for
@@ -1792,6 +1897,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 			  cpumask_and(tmp->addmask, xcpus, parent->effective_xcpus);
 		if (adding)
 			subparts_delta--;
+		new_prs = PRS_MEMBER;
 	} else if (newmask) {
 		/*
 		 * Empty cpumask is not allowed
@@ -1940,38 +2046,28 @@ write_error:
 	 * newly deleted ones will be added back to effective_cpus.
 	 */
 	spin_lock_irq(&callback_lock);
-	if (adding) {
-		if (parent == &top_cpuset)
-			cpumask_andnot(subpartitions_cpus,
-				       subpartitions_cpus, tmp->addmask);
-		/*
-		 * Some of the CPUs in effective_xcpus might have been offlined.
-		 */
-		cpumask_or(parent->effective_cpus,
-			   parent->effective_cpus, tmp->addmask);
-		cpumask_and(parent->effective_cpus,
-			    parent->effective_cpus, cpu_active_mask);
-	}
-	if (deleting) {
-		if (parent == &top_cpuset)
-			cpumask_or(subpartitions_cpus,
-				   subpartitions_cpus, tmp->delmask);
-		cpumask_andnot(parent->effective_cpus,
-			       parent->effective_cpus, tmp->delmask);
-	}
-
-	if (is_partition_valid(parent)) {
-		parent->nr_subparts += subparts_delta;
-		WARN_ON_ONCE(parent->nr_subparts < 0);
-	}
-
 	if (old_prs != new_prs) {
 		cs->partition_root_state = new_prs;
 		if (new_prs <= 0)
 			cs->nr_subparts = 0;
 	}
+	/*
+	 * Adding to parent's effective_cpus means deletion CPUs from cs
+	 * and vice versa.
+	 */
+	if (adding)
+		isolcpus_updated += partition_xcpus_del(old_prs, parent,
+							tmp->addmask);
+	if (deleting)
+		isolcpus_updated += partition_xcpus_add(new_prs, parent,
+							tmp->delmask);
 
+	if (is_partition_valid(parent)) {
+		parent->nr_subparts += subparts_delta;
+		WARN_ON_ONCE(parent->nr_subparts < 0);
+	}
 	spin_unlock_irq(&callback_lock);
+	update_unbound_workqueue_cpumask(isolcpus_updated);
 
 	if ((old_prs != new_prs) && (cmd == partcmd_update))
 		update_partition_exclusive(cs, new_prs);
@@ -2948,6 +3044,7 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 	int err = PERR_NONE, old_prs = cs->partition_root_state;
 	struct cpuset *parent = parent_cs(cs);
 	struct tmpmasks tmpmask;
+	bool new_xcpus_state = false;
 
 	if (old_prs == new_prs)
 		return 0;
@@ -2977,6 +3074,9 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 		goto out;
 
 	if (!old_prs) {
+		enum partition_cmd cmd = (new_prs == PRS_ROOT)
+				       ? partcmd_enable : partcmd_enablei;
+
 		/*
 		 * cpus_allowed cannot be empty.
 		 */
@@ -2985,19 +3085,18 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 			goto out;
 		}
 
-		err = update_parent_effective_cpumask(cs, partcmd_enable,
-						      NULL, &tmpmask);
+		err = update_parent_effective_cpumask(cs, cmd, NULL, &tmpmask);
 		/*
 		 * If an attempt to become local partition root fails,
 		 * try to become a remote partition root instead.
 		 */
-		if (err && remote_partition_enable(cs, &tmpmask))
+		if (err && remote_partition_enable(cs, new_prs, &tmpmask))
 			err = 0;
 	} else if (old_prs && new_prs) {
 		/*
 		 * A change in load balance state only, no change in cpumasks.
 		 */
-		;
+		new_xcpus_state = true;
 	} else {
 		/*
 		 * Switching back to member is always allowed even if it
@@ -3029,7 +3128,10 @@ out:
 	WRITE_ONCE(cs->prs_err, err);
 	if (!is_partition_valid(cs))
 		reset_partition_data(cs);
+	else if (new_xcpus_state)
+		partition_xcpus_newstate(old_prs, new_prs, cs->effective_xcpus);
 	spin_unlock_irq(&callback_lock);
+	update_unbound_workqueue_cpumask(new_xcpus_state);
 
 	/* Force update if switching back to member */
 	update_cpumasks_hier(cs, &tmpmask, !new_prs ? HIER_CHECKALL : 0);
@@ -3386,6 +3488,7 @@ typedef enum {
 	FILE_SUBPARTS_CPULIST,
 	FILE_EXCLUSIVE_CPULIST,
 	FILE_EFFECTIVE_XCPULIST,
+	FILE_ISOLATED_CPULIST,
 	FILE_CPU_EXCLUSIVE,
 	FILE_MEM_EXCLUSIVE,
 	FILE_MEM_HARDWALL,
@@ -3582,6 +3685,9 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
 	case FILE_SUBPARTS_CPULIST:
 		seq_printf(sf, "%*pbl\n", cpumask_pr_args(subpartitions_cpus));
 		break;
+	case FILE_ISOLATED_CPULIST:
+		seq_printf(sf, "%*pbl\n", cpumask_pr_args(isolated_cpus));
+		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -3875,6 +3981,13 @@ static struct cftype dfl_files[] = {
 		.flags = CFTYPE_ONLY_ON_ROOT | CFTYPE_DEBUG,
 	},
 
+	{
+		.name = "cpus.isolated",
+		.seq_show = cpuset_common_seq_show,
+		.private = FILE_ISOLATED_CPULIST,
+		.flags = CFTYPE_ONLY_ON_ROOT,
+	},
+
 	{ }	/* terminate */
 };
 
@@ -4194,6 +4307,7 @@ int __init cpuset_init(void)
 	BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_xcpus, GFP_KERNEL));
 	BUG_ON(!alloc_cpumask_var(&top_cpuset.exclusive_cpus, GFP_KERNEL));
 	BUG_ON(!zalloc_cpumask_var(&subpartitions_cpus, GFP_KERNEL));
+	BUG_ON(!zalloc_cpumask_var(&isolated_cpus, GFP_KERNEL));
 
 	cpumask_setall(top_cpuset.cpus_allowed);
 	nodes_setall(top_cpuset.mems_allowed);
@@ -4306,6 +4420,30 @@ void cpuset_force_rebuild(void)
 	force_rebuild = true;
 }
 
+/*
+ * Attempt to acquire a cpus_read_lock while a hotplug operation may be in
+ * progress.
+ * Return: true if successful, false otherwise
+ *
+ * To avoid circular lock dependency between cpuset_mutex and cpus_read_lock,
+ * cpus_read_trylock() is used here to acquire the lock.
+ */
+static bool cpuset_hotplug_cpus_read_trylock(void)
+{
+	int retries = 0;
+
+	while (!cpus_read_trylock()) {
+		/*
+		 * CPU hotplug still in progress. Retry 5 times
+		 * with a 10ms wait before bailing out.
+		 */
+		if (++retries > 5)
+			return false;
+		msleep(10);
+	}
+	return true;
+}
+
 /**
  * cpuset_hotplug_update_tasks - update tasks in a cpuset for hotunplug
  * @cs: cpuset in interest
@@ -4322,6 +4460,7 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
 	bool cpus_updated;
 	bool mems_updated;
 	bool remote;
+	int partcmd = -1;
 	struct cpuset *parent;
 retry:
 	wait_event(cpuset_attach_wq, cs->attach_in_progress == 0);
@@ -4353,11 +4492,13 @@ retry:
 		compute_partition_effective_cpumask(cs, &new_cpus);
 
 	if (remote && cpumask_empty(&new_cpus) &&
-	    partition_is_populated(cs, NULL)) {
+	    partition_is_populated(cs, NULL) &&
+	    cpuset_hotplug_cpus_read_trylock()) {
 		remote_partition_disable(cs, tmp);
 		compute_effective_cpumask(&new_cpus, cs, parent);
 		remote = false;
 		cpuset_force_rebuild();
+		cpus_read_unlock();
 	}
 
 	/*
@@ -4368,18 +4509,28 @@ retry:
 	 *    partitions.
 	 */
 	if (is_local_partition(cs) && (!is_partition_valid(parent) ||
-				tasks_nocpu_error(parent, cs, &new_cpus))) {
-		update_parent_effective_cpumask(cs, partcmd_invalidate, NULL, tmp);
-		compute_effective_cpumask(&new_cpus, cs, parent);
-		cpuset_force_rebuild();
-	}
+				tasks_nocpu_error(parent, cs, &new_cpus)))
+		partcmd = partcmd_invalidate;
 	/*
 	 * On the other hand, an invalid partition root may be transitioned
 	 * back to a regular one.
 	 */
-	else if (is_partition_valid(parent) && is_partition_invalid(cs)) {
-		update_parent_effective_cpumask(cs, partcmd_update, NULL, tmp);
-		if (is_partition_valid(cs)) {
+	else if (is_partition_valid(parent) && is_partition_invalid(cs))
+		partcmd = partcmd_update;
+
+	/*
+	 * cpus_read_lock needs to be held before calling
+	 * update_parent_effective_cpumask(). To avoid circular lock
+	 * dependency between cpuset_mutex and cpus_read_lock,
+	 * cpus_read_trylock() is used here to acquire the lock.
+	 */
+	if (partcmd >= 0) {
+		if (!cpuset_hotplug_cpus_read_trylock())
+			goto update_tasks;
+
+		update_parent_effective_cpumask(cs, partcmd, NULL, tmp);
+		cpus_read_unlock();
+		if ((partcmd == partcmd_invalidate) || is_partition_valid(cs)) {
 			compute_partition_effective_cpumask(cs, &new_cpus);
 			cpuset_force_rebuild();
 		}
diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c
index 122dacb3a443..66d1708042a7 100644
--- a/kernel/cgroup/legacy_freezer.c
+++ b/kernel/cgroup/legacy_freezer.c
@@ -66,9 +66,15 @@ static struct freezer *parent_freezer(struct freezer *freezer)
 bool cgroup_freezing(struct task_struct *task)
 {
 	bool ret;
+	unsigned int state;
 
 	rcu_read_lock();
-	ret = task_freezer(task)->state & CGROUP_FREEZING;
+	/* Check if the cgroup is still FREEZING, but not FROZEN. The extra
+	 * !FROZEN check is required, because the FREEZING bit is not cleared
+	 * when the state FROZEN is reached.
+	 */
+	state = task_freezer(task)->state;
+	ret = (state & CGROUP_FREEZING) && !(state & CGROUP_FROZEN);
 	rcu_read_unlock();
 
 	return ret;
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index c0adb7254b45..a8350d2d63e6 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -74,64 +74,109 @@ __bpf_kfunc void cgroup_rstat_updated(struct cgroup *cgrp, int cpu)
 }
 
 /**
- * cgroup_rstat_cpu_pop_updated - iterate and dismantle rstat_cpu updated tree
- * @pos: current position
- * @root: root of the tree to traversal
+ * cgroup_rstat_push_children - push children cgroups into the given list
+ * @head: current head of the list (= subtree root)
+ * @child: first child of the root
  * @cpu: target cpu
+ * Return: A new singly linked list of cgroups to be flush
  *
- * Walks the updated rstat_cpu tree on @cpu from @root.  %NULL @pos starts
- * the traversal and %NULL return indicates the end.  During traversal,
- * each returned cgroup is unlinked from the tree.  Must be called with the
- * matching cgroup_rstat_cpu_lock held.
+ * Iteratively traverse down the cgroup_rstat_cpu updated tree level by
+ * level and push all the parents first before their next level children
+ * into a singly linked list built from the tail backward like "pushing"
+ * cgroups into a stack. The root is pushed by the caller.
+ */
+static struct cgroup *cgroup_rstat_push_children(struct cgroup *head,
+						 struct cgroup *child, int cpu)
+{
+	struct cgroup *chead = child;	/* Head of child cgroup level */
+	struct cgroup *ghead = NULL;	/* Head of grandchild cgroup level */
+	struct cgroup *parent, *grandchild;
+	struct cgroup_rstat_cpu *crstatc;
+
+	child->rstat_flush_next = NULL;
+
+next_level:
+	while (chead) {
+		child = chead;
+		chead = child->rstat_flush_next;
+		parent = cgroup_parent(child);
+
+		/* updated_next is parent cgroup terminated */
+		while (child != parent) {
+			child->rstat_flush_next = head;
+			head = child;
+			crstatc = cgroup_rstat_cpu(child, cpu);
+			grandchild = crstatc->updated_children;
+			if (grandchild != child) {
+				/* Push the grand child to the next level */
+				crstatc->updated_children = child;
+				grandchild->rstat_flush_next = ghead;
+				ghead = grandchild;
+			}
+			child = crstatc->updated_next;
+			crstatc->updated_next = NULL;
+		}
+	}
+
+	if (ghead) {
+		chead = ghead;
+		ghead = NULL;
+		goto next_level;
+	}
+	return head;
+}
+
+/**
+ * cgroup_rstat_updated_list - return a list of updated cgroups to be flushed
+ * @root: root of the cgroup subtree to traverse
+ * @cpu: target cpu
+ * Return: A singly linked list of cgroups to be flushed
+ *
+ * Walks the updated rstat_cpu tree on @cpu from @root.  During traversal,
+ * each returned cgroup is unlinked from the updated tree.
  *
  * The only ordering guarantee is that, for a parent and a child pair
- * covered by a given traversal, if a child is visited, its parent is
- * guaranteed to be visited afterwards.
+ * covered by a given traversal, the child is before its parent in
+ * the list.
+ *
+ * Note that updated_children is self terminated and points to a list of
+ * child cgroups if not empty. Whereas updated_next is like a sibling link
+ * within the children list and terminated by the parent cgroup. An exception
+ * here is the cgroup root whose updated_next can be self terminated.
  */
-static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
-						   struct cgroup *root, int cpu)
+static struct cgroup *cgroup_rstat_updated_list(struct cgroup *root, int cpu)
 {
-	struct cgroup_rstat_cpu *rstatc;
-	struct cgroup *parent;
-
-	if (pos == root)
-		return NULL;
+	raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu);
+	struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(root, cpu);
+	struct cgroup *head = NULL, *parent, *child;
+	unsigned long flags;
 
 	/*
-	 * We're gonna walk down to the first leaf and visit/remove it.  We
-	 * can pick whatever unvisited node as the starting point.
+	 * The _irqsave() is needed because cgroup_rstat_lock is
+	 * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring
+	 * this lock with the _irq() suffix only disables interrupts on
+	 * a non-PREEMPT_RT kernel. The raw_spinlock_t below disables
+	 * interrupts on both configurations. The _irqsave() ensures
+	 * that interrupts are always disabled and later restored.
 	 */
-	if (!pos) {
-		pos = root;
-		/* return NULL if this subtree is not on-list */
-		if (!cgroup_rstat_cpu(pos, cpu)->updated_next)
-			return NULL;
-	} else {
-		pos = cgroup_parent(pos);
-	}
+	raw_spin_lock_irqsave(cpu_lock, flags);
 
-	/* walk down to the first leaf */
-	while (true) {
-		rstatc = cgroup_rstat_cpu(pos, cpu);
-		if (rstatc->updated_children == pos)
-			break;
-		pos = rstatc->updated_children;
-	}
+	/* Return NULL if this subtree is not on-list */
+	if (!rstatc->updated_next)
+		goto unlock_ret;
 
 	/*
-	 * Unlink @pos from the tree.  As the updated_children list is
+	 * Unlink @root from its parent. As the updated_children list is
 	 * singly linked, we have to walk it to find the removal point.
-	 * However, due to the way we traverse, @pos will be the first
-	 * child in most cases. The only exception is @root.
 	 */
-	parent = cgroup_parent(pos);
+	parent = cgroup_parent(root);
 	if (parent) {
 		struct cgroup_rstat_cpu *prstatc;
 		struct cgroup **nextp;
 
 		prstatc = cgroup_rstat_cpu(parent, cpu);
 		nextp = &prstatc->updated_children;
-		while (*nextp != pos) {
+		while (*nextp != root) {
 			struct cgroup_rstat_cpu *nrstatc;
 
 			nrstatc = cgroup_rstat_cpu(*nextp, cpu);
@@ -142,7 +187,17 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
 	}
 
 	rstatc->updated_next = NULL;
-	return pos;
+
+	/* Push @root to the list first before pushing the children */
+	head = root;
+	root->rstat_flush_next = NULL;
+	child = rstatc->updated_children;
+	rstatc->updated_children = root;
+	if (child != root)
+		head = cgroup_rstat_push_children(head, child, cpu);
+unlock_ret:
+	raw_spin_unlock_irqrestore(cpu_lock, flags);
+	return head;
 }
 
 /*
@@ -176,21 +231,9 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
 	lockdep_assert_held(&cgroup_rstat_lock);
 
 	for_each_possible_cpu(cpu) {
-		raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock,
-						       cpu);
-		struct cgroup *pos = NULL;
-		unsigned long flags;
+		struct cgroup *pos = cgroup_rstat_updated_list(cgrp, cpu);
 
-		/*
-		 * The _irqsave() is needed because cgroup_rstat_lock is
-		 * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring
-		 * this lock with the _irq() suffix only disables interrupts on
-		 * a non-PREEMPT_RT kernel. The raw_spinlock_t below disables
-		 * interrupts on both configurations. The _irqsave() ensures
-		 * that interrupts are always disabled and later restored.
-		 */
-		raw_spin_lock_irqsave(cpu_lock, flags);
-		while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) {
+		for (; pos; pos = pos->rstat_flush_next) {
 			struct cgroup_subsys_state *css;
 
 			cgroup_base_stat_flush(pos, cpu);
@@ -202,7 +245,6 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
 				css->ss->css_rstat_flush(css, cpu);
 			rcu_read_unlock();
 		}
-		raw_spin_unlock_irqrestore(cpu_lock, flags);
 
 		/* play nice and yield if necessary */
 		if (need_resched() || spin_needbreak(&cgroup_rstat_lock)) {
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 9e4c6780adde..e6ec3ba4950b 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -2113,7 +2113,7 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 	[CPUHP_HRTIMERS_PREPARE] = {
 		.name			= "hrtimers:prepare",
 		.startup.single		= hrtimers_prepare_cpu,
-		.teardown.single	= hrtimers_dead_cpu,
+		.teardown.single	= NULL,
 	},
 	[CPUHP_SMPCFD_PREPARE] = {
 		.name			= "smpcfd:prepare",
@@ -2125,11 +2125,6 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 		.startup.single		= relay_prepare_cpu,
 		.teardown.single	= NULL,
 	},
-	[CPUHP_SLAB_PREPARE] = {
-		.name			= "slab:prepare",
-		.startup.single		= slab_prepare_cpu,
-		.teardown.single	= slab_dead_cpu,
-	},
 	[CPUHP_RCUTREE_PREP] = {
 		.name			= "RCU/tree:prepare",
 		.startup.single		= rcutree_prepare_cpu,
@@ -2205,6 +2200,12 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 		.startup.single		= NULL,
 		.teardown.single	= smpcfd_dying_cpu,
 	},
+	[CPUHP_AP_HRTIMERS_DYING] = {
+		.name			= "hrtimers:dying",
+		.startup.single		= NULL,
+		.teardown.single	= hrtimers_cpu_dying,
+	},
+
 	/* Entry state on starting. Interrupts enabled from here on. Transient
 	 * state for synchronsization */
 	[CPUHP_AP_ONLINE] = {
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index efe87d501c8c..d48315667752 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -13,7 +13,6 @@
 #include <linux/memory.h>
 #include <linux/cpuhotplug.h>
 #include <linux/memblock.h>
-#include <linux/kexec.h>
 #include <linux/kmemleak.h>
 
 #include <asm/page.h>
@@ -199,7 +198,7 @@ static __initdata char *suffix_tbl[] = {
  * It returns 0 on success and -EINVAL on failure.
  */
 static int __init parse_crashkernel_suffix(char *cmdline,
-					   unsigned long long	*crash_size,
+					   unsigned long long *crash_size,
 					   const char *suffix)
 {
 	char *cur = cmdline;
@@ -268,9 +267,9 @@ static int __init __parse_crashkernel(char *cmdline,
 			     unsigned long long *crash_base,
 			     const char *suffix)
 {
-	char	*first_colon, *first_space;
-	char	*ck_cmdline;
-	char	*name = "crashkernel=";
+	char *first_colon, *first_space;
+	char *ck_cmdline;
+	char *name = "crashkernel=";
 
 	BUG_ON(!crash_size || !crash_base);
 	*crash_size = 0;
@@ -440,7 +439,7 @@ retry:
 		return;
 	}
 
-	if ((crash_base > CRASH_ADDR_LOW_MAX) &&
+	if ((crash_base >= CRASH_ADDR_LOW_MAX) &&
 	     crash_low_size && reserve_crashkernel_low(crash_low_size)) {
 		memblock_phys_free(crash_base, crash_size);
 		return;
@@ -551,9 +550,11 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map,
 		phdr->p_filesz = phdr->p_memsz = mend - mstart + 1;
 		phdr->p_align = 0;
 		ehdr->e_phnum++;
-		pr_debug("Crash PT_LOAD ELF header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n",
-			phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz,
-			ehdr->e_phnum, phdr->p_offset);
+#ifdef CONFIG_KEXEC_FILE
+		kexec_dprintk("Crash PT_LOAD ELF header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n",
+			      phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz,
+			      ehdr->e_phnum, phdr->p_offset);
+#endif
 		phdr++;
 	}
 
@@ -565,9 +566,8 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map,
 int crash_exclude_mem_range(struct crash_mem *mem,
 			    unsigned long long mstart, unsigned long long mend)
 {
-	int i, j;
+	int i;
 	unsigned long long start, end, p_start, p_end;
-	struct range temp_range = {0, 0};
 
 	for (i = 0; i < mem->nr_ranges; i++) {
 		start = mem->ranges[i].start;
@@ -575,72 +575,51 @@ int crash_exclude_mem_range(struct crash_mem *mem,
 		p_start = mstart;
 		p_end = mend;
 
-		if (mstart > end || mend < start)
+		if (p_start > end)
 			continue;
 
+		/*
+		 * Because the memory ranges in mem->ranges are stored in
+		 * ascending order, when we detect `p_end < start`, we can
+		 * immediately exit the for loop, as the subsequent memory
+		 * ranges will definitely be outside the range we are looking
+		 * for.
+		 */
+		if (p_end < start)
+			break;
+
 		/* Truncate any area outside of range */
-		if (mstart < start)
+		if (p_start < start)
 			p_start = start;
-		if (mend > end)
+		if (p_end > end)
 			p_end = end;
 
 		/* Found completely overlapping range */
 		if (p_start == start && p_end == end) {
-			mem->ranges[i].start = 0;
-			mem->ranges[i].end = 0;
-			if (i < mem->nr_ranges - 1) {
-				/* Shift rest of the ranges to left */
-				for (j = i; j < mem->nr_ranges - 1; j++) {
-					mem->ranges[j].start =
-						mem->ranges[j+1].start;
-					mem->ranges[j].end =
-							mem->ranges[j+1].end;
-				}
-
-				/*
-				 * Continue to check if there are another overlapping ranges
-				 * from the current position because of shifting the above
-				 * mem ranges.
-				 */
-				i--;
-				mem->nr_ranges--;
-				continue;
-			}
+			memmove(&mem->ranges[i], &mem->ranges[i + 1],
+				(mem->nr_ranges - (i + 1)) * sizeof(mem->ranges[i]));
+			i--;
 			mem->nr_ranges--;
-			return 0;
-		}
-
-		if (p_start > start && p_end < end) {
+		} else if (p_start > start && p_end < end) {
 			/* Split original range */
+			if (mem->nr_ranges >= mem->max_nr_ranges)
+				return -ENOMEM;
+
+			memmove(&mem->ranges[i + 2], &mem->ranges[i + 1],
+				(mem->nr_ranges - (i + 1)) * sizeof(mem->ranges[i]));
+
 			mem->ranges[i].end = p_start - 1;
-			temp_range.start = p_end + 1;
-			temp_range.end = end;
+			mem->ranges[i + 1].start = p_end + 1;
+			mem->ranges[i + 1].end = end;
+
+			i++;
+			mem->nr_ranges++;
 		} else if (p_start != start)
 			mem->ranges[i].end = p_start - 1;
 		else
 			mem->ranges[i].start = p_end + 1;
-		break;
-	}
-
-	/* If a split happened, add the split to array */
-	if (!temp_range.end)
-		return 0;
-
-	/* Split happened */
-	if (i == mem->max_nr_ranges - 1)
-		return -ENOMEM;
-
-	/* Location where new range should go */
-	j = i + 1;
-	if (j < mem->nr_ranges) {
-		/* Move over all ranges one slot towards the end */
-		for (i = mem->nr_ranges - 1; i >= j; i--)
-			mem->ranges[i + 1] = mem->ranges[i];
 	}
 
-	mem->ranges[j].start = temp_range.start;
-	mem->ranges[j].end = temp_range.end;
-	mem->nr_ranges++;
 	return 0;
 }
 
@@ -802,7 +781,7 @@ static int __init crash_save_vmcoreinfo_init(void)
 	VMCOREINFO_OFFSET(list_head, prev);
 	VMCOREINFO_OFFSET(vmap_area, va_start);
 	VMCOREINFO_OFFSET(vmap_area, list);
-	VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER + 1);
+	VMCOREINFO_LENGTH(zone.free_area, NR_PAGE_ORDERS);
 	log_buf_vmcoreinfo_setup();
 	VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
 	VMCOREINFO_NUMBER(NR_FREE_PAGES);
diff --git a/kernel/cred.c b/kernel/cred.c
index 3c714cb31660..c033a201c808 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -43,10 +43,6 @@ static struct group_info init_groups = { .usage = REFCOUNT_INIT(2) };
  */
 struct cred init_cred = {
 	.usage			= ATOMIC_INIT(4),
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	.subscribers		= ATOMIC_INIT(2),
-	.magic			= CRED_MAGIC,
-#endif
 	.uid			= GLOBAL_ROOT_UID,
 	.gid			= GLOBAL_ROOT_GID,
 	.suid			= GLOBAL_ROOT_UID,
@@ -66,31 +62,6 @@ struct cred init_cred = {
 	.ucounts		= &init_ucounts,
 };
 
-static inline void set_cred_subscribers(struct cred *cred, int n)
-{
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	atomic_set(&cred->subscribers, n);
-#endif
-}
-
-static inline int read_cred_subscribers(const struct cred *cred)
-{
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	return atomic_read(&cred->subscribers);
-#else
-	return 0;
-#endif
-}
-
-static inline void alter_cred_subscribers(const struct cred *_cred, int n)
-{
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	struct cred *cred = (struct cred *) _cred;
-
-	atomic_add(n, &cred->subscribers);
-#endif
-}
-
 /*
  * The RCU callback to actually dispose of a set of credentials
  */
@@ -100,20 +71,9 @@ static void put_cred_rcu(struct rcu_head *rcu)
 
 	kdebug("put_cred_rcu(%p)", cred);
 
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	if (cred->magic != CRED_MAGIC_DEAD ||
-	    atomic_read(&cred->usage) != 0 ||
-	    read_cred_subscribers(cred) != 0)
-		panic("CRED: put_cred_rcu() sees %p with"
-		      " mag %x, put %p, usage %d, subscr %d\n",
-		      cred, cred->magic, cred->put_addr,
-		      atomic_read(&cred->usage),
-		      read_cred_subscribers(cred));
-#else
-	if (atomic_read(&cred->usage) != 0)
-		panic("CRED: put_cred_rcu() sees %p with usage %d\n",
-		      cred, atomic_read(&cred->usage));
-#endif
+	if (atomic_long_read(&cred->usage) != 0)
+		panic("CRED: put_cred_rcu() sees %p with usage %ld\n",
+		      cred, atomic_long_read(&cred->usage));
 
 	security_cred_free(cred);
 	key_put(cred->session_keyring);
@@ -137,16 +97,10 @@ static void put_cred_rcu(struct rcu_head *rcu)
  */
 void __put_cred(struct cred *cred)
 {
-	kdebug("__put_cred(%p{%d,%d})", cred,
-	       atomic_read(&cred->usage),
-	       read_cred_subscribers(cred));
-
-	BUG_ON(atomic_read(&cred->usage) != 0);
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	BUG_ON(read_cred_subscribers(cred) != 0);
-	cred->magic = CRED_MAGIC_DEAD;
-	cred->put_addr = __builtin_return_address(0);
-#endif
+	kdebug("__put_cred(%p{%ld})", cred,
+	       atomic_long_read(&cred->usage));
+
+	BUG_ON(atomic_long_read(&cred->usage) != 0);
 	BUG_ON(cred == current->cred);
 	BUG_ON(cred == current->real_cred);
 
@@ -164,9 +118,8 @@ void exit_creds(struct task_struct *tsk)
 {
 	struct cred *real_cred, *cred;
 
-	kdebug("exit_creds(%u,%p,%p,{%d,%d})", tsk->pid, tsk->real_cred, tsk->cred,
-	       atomic_read(&tsk->cred->usage),
-	       read_cred_subscribers(tsk->cred));
+	kdebug("exit_creds(%u,%p,%p,{%ld})", tsk->pid, tsk->real_cred, tsk->cred,
+	       atomic_long_read(&tsk->cred->usage));
 
 	real_cred = (struct cred *) tsk->real_cred;
 	tsk->real_cred = NULL;
@@ -174,15 +127,10 @@ void exit_creds(struct task_struct *tsk)
 	cred = (struct cred *) tsk->cred;
 	tsk->cred = NULL;
 
-	validate_creds(cred);
 	if (real_cred == cred) {
-		alter_cred_subscribers(cred, -2);
 		put_cred_many(cred, 2);
 	} else {
-		validate_creds(real_cred);
-		alter_cred_subscribers(real_cred, -1);
 		put_cred(real_cred);
-		alter_cred_subscribers(cred, -1);
 		put_cred(cred);
 	}
 
@@ -230,10 +178,7 @@ struct cred *cred_alloc_blank(void)
 	if (!new)
 		return NULL;
 
-	atomic_set(&new->usage, 1);
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	new->magic = CRED_MAGIC;
-#endif
+	atomic_long_set(&new->usage, 1);
 	if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
 
@@ -264,8 +209,6 @@ struct cred *prepare_creds(void)
 	const struct cred *old;
 	struct cred *new;
 
-	validate_process_creds();
-
 	new = kmem_cache_alloc(cred_jar, GFP_KERNEL);
 	if (!new)
 		return NULL;
@@ -276,8 +219,7 @@ struct cred *prepare_creds(void)
 	memcpy(new, old, sizeof(struct cred));
 
 	new->non_rcu = 0;
-	atomic_set(&new->usage, 1);
-	set_cred_subscribers(new, 0);
+	atomic_long_set(&new->usage, 1);
 	get_group_info(new->group_info);
 	get_uid(new->user);
 	get_user_ns(new->user_ns);
@@ -300,7 +242,6 @@ struct cred *prepare_creds(void)
 	if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
 
-	validate_creds(new);
 	return new;
 
 error:
@@ -362,10 +303,8 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 		clone_flags & CLONE_THREAD
 	    ) {
 		p->real_cred = get_cred_many(p->cred, 2);
-		alter_cred_subscribers(p->cred, 2);
-		kdebug("share_creds(%p{%d,%d})",
-		       p->cred, atomic_read(&p->cred->usage),
-		       read_cred_subscribers(p->cred));
+		kdebug("share_creds(%p{%ld})",
+		       p->cred, atomic_long_read(&p->cred->usage));
 		inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
 		return 0;
 	}
@@ -404,8 +343,6 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 
 	p->cred = p->real_cred = get_cred(new);
 	inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
-	alter_cred_subscribers(new, 2);
-	validate_creds(new);
 	return 0;
 
 error_put:
@@ -457,17 +394,11 @@ int commit_creds(struct cred *new)
 	struct task_struct *task = current;
 	const struct cred *old = task->real_cred;
 
-	kdebug("commit_creds(%p{%d,%d})", new,
-	       atomic_read(&new->usage),
-	       read_cred_subscribers(new));
+	kdebug("commit_creds(%p{%ld})", new,
+	       atomic_long_read(&new->usage));
 
 	BUG_ON(task->cred != old);
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	BUG_ON(read_cred_subscribers(old) < 2);
-	validate_creds(old);
-	validate_creds(new);
-#endif
-	BUG_ON(atomic_read(&new->usage) < 1);
+	BUG_ON(atomic_long_read(&new->usage) < 1);
 
 	get_cred(new); /* we will require a ref for the subj creds too */
 
@@ -502,14 +433,12 @@ int commit_creds(struct cred *new)
 	 * RLIMIT_NPROC limits on user->processes have already been checked
 	 * in set_user().
 	 */
-	alter_cred_subscribers(new, 2);
 	if (new->user != old->user || new->user_ns != old->user_ns)
 		inc_rlimit_ucounts(new->ucounts, UCOUNT_RLIMIT_NPROC, 1);
 	rcu_assign_pointer(task->real_cred, new);
 	rcu_assign_pointer(task->cred, new);
 	if (new->user != old->user || new->user_ns != old->user_ns)
 		dec_rlimit_ucounts(old->ucounts, UCOUNT_RLIMIT_NPROC, 1);
-	alter_cred_subscribers(old, -2);
 
 	/* send notifications */
 	if (!uid_eq(new->uid,   old->uid)  ||
@@ -539,14 +468,10 @@ EXPORT_SYMBOL(commit_creds);
  */
 void abort_creds(struct cred *new)
 {
-	kdebug("abort_creds(%p{%d,%d})", new,
-	       atomic_read(&new->usage),
-	       read_cred_subscribers(new));
+	kdebug("abort_creds(%p{%ld})", new,
+	       atomic_long_read(&new->usage));
 
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	BUG_ON(read_cred_subscribers(new) != 0);
-#endif
-	BUG_ON(atomic_read(&new->usage) < 1);
+	BUG_ON(atomic_long_read(&new->usage) < 1);
 	put_cred(new);
 }
 EXPORT_SYMBOL(abort_creds);
@@ -562,12 +487,8 @@ const struct cred *override_creds(const struct cred *new)
 {
 	const struct cred *old = current->cred;
 
-	kdebug("override_creds(%p{%d,%d})", new,
-	       atomic_read(&new->usage),
-	       read_cred_subscribers(new));
-
-	validate_creds(old);
-	validate_creds(new);
+	kdebug("override_creds(%p{%ld})", new,
+	       atomic_long_read(&new->usage));
 
 	/*
 	 * NOTE! This uses 'get_new_cred()' rather than 'get_cred()'.
@@ -576,18 +497,12 @@ const struct cred *override_creds(const struct cred *new)
 	 * we are only installing the cred into the thread-synchronous
 	 * '->cred' pointer, not the '->real_cred' pointer that is
 	 * visible to other threads under RCU.
-	 *
-	 * Also note that we did validate_creds() manually, not depending
-	 * on the validation in 'get_cred()'.
 	 */
 	get_new_cred((struct cred *)new);
-	alter_cred_subscribers(new, 1);
 	rcu_assign_pointer(current->cred, new);
-	alter_cred_subscribers(old, -1);
 
-	kdebug("override_creds() = %p{%d,%d}", old,
-	       atomic_read(&old->usage),
-	       read_cred_subscribers(old));
+	kdebug("override_creds() = %p{%ld}", old,
+	       atomic_long_read(&old->usage));
 	return old;
 }
 EXPORT_SYMBOL(override_creds);
@@ -603,15 +518,10 @@ void revert_creds(const struct cred *old)
 {
 	const struct cred *override = current->cred;
 
-	kdebug("revert_creds(%p{%d,%d})", old,
-	       atomic_read(&old->usage),
-	       read_cred_subscribers(old));
+	kdebug("revert_creds(%p{%ld})", old,
+	       atomic_long_read(&old->usage));
 
-	validate_creds(old);
-	validate_creds(override);
-	alter_cred_subscribers(old, 1);
 	rcu_assign_pointer(current->cred, old);
-	alter_cred_subscribers(override, -1);
 	put_cred(override);
 }
 EXPORT_SYMBOL(revert_creds);
@@ -731,12 +641,10 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 	kdebug("prepare_kernel_cred() alloc %p", new);
 
 	old = get_task_cred(daemon);
-	validate_creds(old);
 
 	*new = *old;
 	new->non_rcu = 0;
-	atomic_set(&new->usage, 1);
-	set_cred_subscribers(new, 0);
+	atomic_long_set(&new->usage, 1);
 	get_uid(new->user);
 	get_user_ns(new->user_ns);
 	get_group_info(new->group_info);
@@ -760,7 +668,6 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 		goto error;
 
 	put_cred(old);
-	validate_creds(new);
 	return new;
 
 error:
@@ -825,109 +732,3 @@ int set_create_files_as(struct cred *new, struct inode *inode)
 	return security_kernel_create_files_as(new, inode);
 }
 EXPORT_SYMBOL(set_create_files_as);
-
-#ifdef CONFIG_DEBUG_CREDENTIALS
-
-bool creds_are_invalid(const struct cred *cred)
-{
-	if (cred->magic != CRED_MAGIC)
-		return true;
-	return false;
-}
-EXPORT_SYMBOL(creds_are_invalid);
-
-/*
- * dump invalid credentials
- */
-static void dump_invalid_creds(const struct cred *cred, const char *label,
-			       const struct task_struct *tsk)
-{
-	pr_err("%s credentials: %p %s%s%s\n",
-	       label, cred,
-	       cred == &init_cred ? "[init]" : "",
-	       cred == tsk->real_cred ? "[real]" : "",
-	       cred == tsk->cred ? "[eff]" : "");
-	pr_err("->magic=%x, put_addr=%p\n",
-	       cred->magic, cred->put_addr);
-	pr_err("->usage=%d, subscr=%d\n",
-	       atomic_read(&cred->usage),
-	       read_cred_subscribers(cred));
-	pr_err("->*uid = { %d,%d,%d,%d }\n",
-		from_kuid_munged(&init_user_ns, cred->uid),
-		from_kuid_munged(&init_user_ns, cred->euid),
-		from_kuid_munged(&init_user_ns, cred->suid),
-		from_kuid_munged(&init_user_ns, cred->fsuid));
-	pr_err("->*gid = { %d,%d,%d,%d }\n",
-		from_kgid_munged(&init_user_ns, cred->gid),
-		from_kgid_munged(&init_user_ns, cred->egid),
-		from_kgid_munged(&init_user_ns, cred->sgid),
-		from_kgid_munged(&init_user_ns, cred->fsgid));
-#ifdef CONFIG_SECURITY
-	pr_err("->security is %p\n", cred->security);
-	if ((unsigned long) cred->security >= PAGE_SIZE &&
-	    (((unsigned long) cred->security & 0xffffff00) !=
-	     (POISON_FREE << 24 | POISON_FREE << 16 | POISON_FREE << 8)))
-		pr_err("->security {%x, %x}\n",
-		       ((u32*)cred->security)[0],
-		       ((u32*)cred->security)[1]);
-#endif
-}
-
-/*
- * report use of invalid credentials
- */
-void __noreturn __invalid_creds(const struct cred *cred, const char *file, unsigned line)
-{
-	pr_err("Invalid credentials\n");
-	pr_err("At %s:%u\n", file, line);
-	dump_invalid_creds(cred, "Specified", current);
-	BUG();
-}
-EXPORT_SYMBOL(__invalid_creds);
-
-/*
- * check the credentials on a process
- */
-void __validate_process_creds(struct task_struct *tsk,
-			      const char *file, unsigned line)
-{
-	if (tsk->cred == tsk->real_cred) {
-		if (unlikely(read_cred_subscribers(tsk->cred) < 2 ||
-			     creds_are_invalid(tsk->cred)))
-			goto invalid_creds;
-	} else {
-		if (unlikely(read_cred_subscribers(tsk->real_cred) < 1 ||
-			     read_cred_subscribers(tsk->cred) < 1 ||
-			     creds_are_invalid(tsk->real_cred) ||
-			     creds_are_invalid(tsk->cred)))
-			goto invalid_creds;
-	}
-	return;
-
-invalid_creds:
-	pr_err("Invalid process credentials\n");
-	pr_err("At %s:%u\n", file, line);
-
-	dump_invalid_creds(tsk->real_cred, "Real", tsk);
-	if (tsk->cred != tsk->real_cred)
-		dump_invalid_creds(tsk->cred, "Effective", tsk);
-	else
-		pr_err("Effective creds == Real creds\n");
-	BUG();
-}
-EXPORT_SYMBOL(__validate_process_creds);
-
-/*
- * check creds for do_exit()
- */
-void validate_creds_for_do_exit(struct task_struct *tsk)
-{
-	kdebug("validate_creds_for_do_exit(%p,%p{%d,%d})",
-	       tsk->real_cred, tsk->cred,
-	       atomic_read(&tsk->cred->usage),
-	       read_cred_subscribers(tsk->cred));
-
-	__validate_process_creds(tsk, __FILE__, __LINE__);
-}
-
-#endif /* CONFIG_DEBUG_CREDENTIALS */
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index c21abc77c53e..ff5683a57f77 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -132,8 +132,10 @@ int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
 
 void dma_release_coherent_memory(struct device *dev)
 {
-	if (dev)
+	if (dev) {
 		_dma_release_coherent_memory(dev->dma_mem);
+		dev->dma_mem = NULL;
+	}
 }
 
 static void *__dma_alloc_from_coherent(struct device *dev,
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 73c95815789a..98b2e192fd69 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -677,7 +677,6 @@ int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
 		return -ENOMEM;
 	map[0].cpu_start = cpu_start;
 	map[0].dma_start = dma_start;
-	map[0].offset = offset;
 	map[0].size = size;
 	dev->dma_range_map = map;
 	return 0;
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index b481c48a31a6..d10613eb0f63 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -84,8 +84,8 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
 	void *addr;
 	int ret = -ENOMEM;
 
-	/* Cannot allocate larger than MAX_ORDER */
-	order = min(get_order(pool_size), MAX_ORDER);
+	/* Cannot allocate larger than MAX_PAGE_ORDER */
+	order = min(get_order(pool_size), MAX_PAGE_ORDER);
 
 	do {
 		pool_size = 1 << (PAGE_SHIFT + order);
@@ -190,7 +190,7 @@ static int __init dma_atomic_pool_init(void)
 
 	/*
 	 * If coherent_pool was not used on the command line, default the pool
-	 * sizes to 128KB per 1GB of memory, min 128KB, max MAX_ORDER.
+	 * sizes to 128KB per 1GB of memory, min 128KB, max MAX_PAGE_ORDER.
 	 */
 	if (!atomic_pool_size) {
 		unsigned long pages = totalram_pages() / (SZ_1G / SZ_128K);
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 33d942615be5..97c298b210bc 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -686,8 +686,8 @@ static struct io_tlb_pool *swiotlb_alloc_pool(struct device *dev,
 	size_t pool_size;
 	size_t tlb_size;
 
-	if (nslabs > SLABS_PER_PAGE << MAX_ORDER) {
-		nslabs = SLABS_PER_PAGE << MAX_ORDER;
+	if (nslabs > SLABS_PER_PAGE << MAX_PAGE_ORDER) {
+		nslabs = SLABS_PER_PAGE << MAX_PAGE_ORDER;
 		nareas = limit_nareas(nareas, nslabs);
 	}
 
@@ -957,7 +957,7 @@ static void dec_used(struct io_tlb_mem *mem, unsigned int nslots)
 #endif /* CONFIG_DEBUG_FS */
 
 /**
- * swiotlb_area_find_slots() - search for slots in one IO TLB memory area
+ * swiotlb_search_pool_area() - search one memory area in one pool
  * @dev:	Device which maps the buffer.
  * @pool:	Memory pool to be searched.
  * @area_index:	Index of the IO TLB memory area to be searched.
@@ -972,7 +972,7 @@ static void dec_used(struct io_tlb_mem *mem, unsigned int nslots)
  *
  * Return: Index of the first allocated slot, or -1 on error.
  */
-static int swiotlb_area_find_slots(struct device *dev, struct io_tlb_pool *pool,
+static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool,
 		int area_index, phys_addr_t orig_addr, size_t alloc_size,
 		unsigned int alloc_align_mask)
 {
@@ -1066,41 +1066,50 @@ found:
 	return slot_index;
 }
 
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+
 /**
- * swiotlb_pool_find_slots() - search for slots in one memory pool
+ * swiotlb_search_area() - search one memory area in all pools
  * @dev:	Device which maps the buffer.
- * @pool:	Memory pool to be searched.
+ * @start_cpu:	Start CPU number.
+ * @cpu_offset:	Offset from @start_cpu.
  * @orig_addr:	Original (non-bounced) IO buffer address.
  * @alloc_size: Total requested size of the bounce buffer,
  *		including initial alignment padding.
  * @alloc_align_mask:	Required alignment of the allocated buffer.
+ * @retpool:	Used memory pool, updated on return.
  *
- * Search through one memory pool to find a sequence of slots that match the
+ * Search one memory area in all pools for a sequence of slots that match the
  * allocation constraints.
  *
  * Return: Index of the first allocated slot, or -1 on error.
  */
-static int swiotlb_pool_find_slots(struct device *dev, struct io_tlb_pool *pool,
-		phys_addr_t orig_addr, size_t alloc_size,
-		unsigned int alloc_align_mask)
+static int swiotlb_search_area(struct device *dev, int start_cpu,
+		int cpu_offset, phys_addr_t orig_addr, size_t alloc_size,
+		unsigned int alloc_align_mask, struct io_tlb_pool **retpool)
 {
-	int start = raw_smp_processor_id() & (pool->nareas - 1);
-	int i = start, index;
-
-	do {
-		index = swiotlb_area_find_slots(dev, pool, i, orig_addr,
-						alloc_size, alloc_align_mask);
-		if (index >= 0)
-			return index;
-		if (++i >= pool->nareas)
-			i = 0;
-	} while (i != start);
+	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
+	struct io_tlb_pool *pool;
+	int area_index;
+	int index = -1;
 
-	return -1;
+	rcu_read_lock();
+	list_for_each_entry_rcu(pool, &mem->pools, node) {
+		if (cpu_offset >= pool->nareas)
+			continue;
+		area_index = (start_cpu + cpu_offset) & (pool->nareas - 1);
+		index = swiotlb_search_pool_area(dev, pool, area_index,
+						 orig_addr, alloc_size,
+						 alloc_align_mask);
+		if (index >= 0) {
+			*retpool = pool;
+			break;
+		}
+	}
+	rcu_read_unlock();
+	return index;
 }
 
-#ifdef CONFIG_SWIOTLB_DYNAMIC
-
 /**
  * swiotlb_find_slots() - search for slots in the whole swiotlb
  * @dev:	Device which maps the buffer.
@@ -1124,18 +1133,17 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
 	unsigned long nslabs;
 	unsigned long flags;
 	u64 phys_limit;
+	int cpu, i;
 	int index;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(pool, &mem->pools, node) {
-		index = swiotlb_pool_find_slots(dev, pool, orig_addr,
-						alloc_size, alloc_align_mask);
-		if (index >= 0) {
-			rcu_read_unlock();
+	cpu = raw_smp_processor_id();
+	for (i = 0; i < default_nareas; ++i) {
+		index = swiotlb_search_area(dev, cpu, i, orig_addr, alloc_size,
+					    alloc_align_mask, &pool);
+		if (index >= 0)
 			goto found;
-		}
 	}
-	rcu_read_unlock();
+
 	if (!mem->can_grow)
 		return -1;
 
@@ -1148,8 +1156,8 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
 	if (!pool)
 		return -1;
 
-	index = swiotlb_pool_find_slots(dev, pool, orig_addr,
-					alloc_size, alloc_align_mask);
+	index = swiotlb_search_pool_area(dev, pool, 0, orig_addr,
+					 alloc_size, alloc_align_mask);
 	if (index < 0) {
 		swiotlb_dyn_free(&pool->rcu);
 		return -1;
@@ -1192,9 +1200,21 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
 		size_t alloc_size, unsigned int alloc_align_mask,
 		struct io_tlb_pool **retpool)
 {
-	*retpool = &dev->dma_io_tlb_mem->defpool;
-	return swiotlb_pool_find_slots(dev, *retpool,
-				       orig_addr, alloc_size, alloc_align_mask);
+	struct io_tlb_pool *pool;
+	int start, i;
+	int index;
+
+	*retpool = pool = &dev->dma_io_tlb_mem->defpool;
+	i = start = raw_smp_processor_id() & (pool->nareas - 1);
+	do {
+		index = swiotlb_search_pool_area(dev, pool, i, orig_addr,
+						 alloc_size, alloc_align_mask);
+		if (index >= 0)
+			return index;
+		if (++i >= pool->nareas)
+			i = 0;
+	} while (i != start);
+	return -1;
 }
 
 #endif /* CONFIG_SWIOTLB_DYNAMIC */
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index d7ee4bc3f2ba..88cb3c88aaa5 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -15,26 +15,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
-/* See comment for enter_from_user_mode() in entry-common.h */
-static __always_inline void __enter_from_user_mode(struct pt_regs *regs)
-{
-	arch_enter_from_user_mode(regs);
-	lockdep_hardirqs_off(CALLER_ADDR0);
-
-	CT_WARN_ON(__ct_state() != CONTEXT_USER);
-	user_exit_irqoff();
-
-	instrumentation_begin();
-	kmsan_unpoison_entry_regs(regs);
-	trace_hardirqs_off_finish();
-	instrumentation_end();
-}
-
-void noinstr enter_from_user_mode(struct pt_regs *regs)
-{
-	__enter_from_user_mode(regs);
-}
-
 static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
 {
 	if (unlikely(audit_context())) {
@@ -45,7 +25,7 @@ static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
 	}
 }
 
-static long syscall_trace_enter(struct pt_regs *regs, long syscall,
+long syscall_trace_enter(struct pt_regs *regs, long syscall,
 				unsigned long work)
 {
 	long ret = 0;
@@ -85,67 +65,24 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
 	return ret ? : syscall;
 }
 
-static __always_inline long
-__syscall_enter_from_user_work(struct pt_regs *regs, long syscall)
-{
-	unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
-
-	if (work & SYSCALL_WORK_ENTER)
-		syscall = syscall_trace_enter(regs, syscall, work);
-
-	return syscall;
-}
-
-long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall)
-{
-	return __syscall_enter_from_user_work(regs, syscall);
-}
-
-noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
-{
-	long ret;
-
-	__enter_from_user_mode(regs);
-
-	instrumentation_begin();
-	local_irq_enable();
-	ret = __syscall_enter_from_user_work(regs, syscall);
-	instrumentation_end();
-
-	return ret;
-}
-
 noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
 {
-	__enter_from_user_mode(regs);
+	enter_from_user_mode(regs);
 	instrumentation_begin();
 	local_irq_enable();
 	instrumentation_end();
 }
 
-/* See comment for exit_to_user_mode() in entry-common.h */
-static __always_inline void __exit_to_user_mode(void)
-{
-	instrumentation_begin();
-	trace_hardirqs_on_prepare();
-	lockdep_hardirqs_on_prepare();
-	instrumentation_end();
-
-	user_enter_irqoff();
-	arch_exit_to_user_mode();
-	lockdep_hardirqs_on(CALLER_ADDR0);
-}
-
-void noinstr exit_to_user_mode(void)
-{
-	__exit_to_user_mode();
-}
-
 /* Workaround to allow gradual conversion of architecture code */
 void __weak arch_do_signal_or_restart(struct pt_regs *regs) { }
 
-static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
-					    unsigned long ti_work)
+/**
+ * exit_to_user_mode_loop - do any pending work before leaving to user space
+ * @regs:	Pointer to pt_regs on entry stack
+ * @ti_work:	TIF work flags as read by the caller
+ */
+__always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
+						     unsigned long ti_work)
 {
 	/*
 	 * Before returning to user space ensure that all pending work
@@ -190,27 +127,6 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 	return ti_work;
 }
 
-static void exit_to_user_mode_prepare(struct pt_regs *regs)
-{
-	unsigned long ti_work;
-
-	lockdep_assert_irqs_disabled();
-
-	/* Flush pending rcuog wakeup before the last need_resched() check */
-	tick_nohz_user_enter_prepare();
-
-	ti_work = read_thread_flags();
-	if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
-		ti_work = exit_to_user_mode_loop(regs, ti_work);
-
-	arch_exit_to_user_mode_prepare(regs, ti_work);
-
-	/* Ensure that kernel state is sane for a return to userspace */
-	kmap_assert_nomap();
-	lockdep_assert_irqs_disabled();
-	lockdep_sys_exit();
-}
-
 /*
  * If SYSCALL_EMU is set, then the only reason to report is when
  * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
@@ -295,12 +211,12 @@ __visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs)
 	instrumentation_begin();
 	__syscall_exit_to_user_mode_work(regs);
 	instrumentation_end();
-	__exit_to_user_mode();
+	exit_to_user_mode();
 }
 
 noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs)
 {
-	__enter_from_user_mode(regs);
+	enter_from_user_mode(regs);
 }
 
 noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs)
@@ -308,7 +224,7 @@ noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs)
 	instrumentation_begin();
 	exit_to_user_mode_prepare(regs);
 	instrumentation_end();
-	__exit_to_user_mode();
+	exit_to_user_mode();
 }
 
 noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 683dc086ef10..f0f0f71213a1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1814,31 +1814,34 @@ static inline void perf_event__state_init(struct perf_event *event)
 					      PERF_EVENT_STATE_INACTIVE;
 }
 
-static void __perf_event_read_size(struct perf_event *event, int nr_siblings)
+static int __perf_event_read_size(u64 read_format, int nr_siblings)
 {
 	int entry = sizeof(u64); /* value */
 	int size = 0;
 	int nr = 1;
 
-	if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
 		size += sizeof(u64);
 
-	if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
 		size += sizeof(u64);
 
-	if (event->attr.read_format & PERF_FORMAT_ID)
+	if (read_format & PERF_FORMAT_ID)
 		entry += sizeof(u64);
 
-	if (event->attr.read_format & PERF_FORMAT_LOST)
+	if (read_format & PERF_FORMAT_LOST)
 		entry += sizeof(u64);
 
-	if (event->attr.read_format & PERF_FORMAT_GROUP) {
+	if (read_format & PERF_FORMAT_GROUP) {
 		nr += nr_siblings;
 		size += sizeof(u64);
 	}
 
-	size += entry * nr;
-	event->read_size = size;
+	/*
+	 * Since perf_event_validate_size() limits this to 16k and inhibits
+	 * adding more siblings, this will never overflow.
+	 */
+	return size + nr * entry;
 }
 
 static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
@@ -1888,8 +1891,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
  */
 static void perf_event__header_size(struct perf_event *event)
 {
-	__perf_event_read_size(event,
-			       event->group_leader->nr_siblings);
+	event->read_size =
+		__perf_event_read_size(event->attr.read_format,
+				       event->group_leader->nr_siblings);
 	__perf_event_header_size(event, event->attr.sample_type);
 }
 
@@ -1920,23 +1924,44 @@ static void perf_event__id_header_size(struct perf_event *event)
 	event->id_header_size = size;
 }
 
+/*
+ * Check that adding an event to the group does not result in anybody
+ * overflowing the 64k event limit imposed by the output buffer.
+ *
+ * Specifically, check that the read_size for the event does not exceed 16k,
+ * read_size being the one term that grows with groups size. Since read_size
+ * depends on per-event read_format, also (re)check the existing events.
+ *
+ * This leaves 48k for the constant size fields and things like callchains,
+ * branch stacks and register sets.
+ */
 static bool perf_event_validate_size(struct perf_event *event)
 {
-	/*
-	 * The values computed here will be over-written when we actually
-	 * attach the event.
-	 */
-	__perf_event_read_size(event, event->group_leader->nr_siblings + 1);
-	__perf_event_header_size(event, event->attr.sample_type & ~PERF_SAMPLE_READ);
-	perf_event__id_header_size(event);
+	struct perf_event *sibling, *group_leader = event->group_leader;
+
+	if (__perf_event_read_size(event->attr.read_format,
+				   group_leader->nr_siblings + 1) > 16*1024)
+		return false;
+
+	if (__perf_event_read_size(group_leader->attr.read_format,
+				   group_leader->nr_siblings + 1) > 16*1024)
+		return false;
 
 	/*
-	 * Sum the lot; should not exceed the 64k limit we have on records.
-	 * Conservative limit to allow for callchains and other variable fields.
+	 * When creating a new group leader, group_leader->ctx is initialized
+	 * after the size has been validated, but we cannot safely use
+	 * for_each_sibling_event() until group_leader->ctx is set. A new group
+	 * leader cannot have any siblings yet, so we can safely skip checking
+	 * the non-existent siblings.
 	 */
-	if (event->read_size + event->header_size +
-	    event->id_header_size + sizeof(struct perf_event_header) >= 16*1024)
-		return false;
+	if (event == group_leader)
+		return true;
+
+	for_each_sibling_event(sibling, group_leader) {
+		if (__perf_event_read_size(sibling->attr.read_format,
+					   group_leader->nr_siblings + 1) > 16*1024)
+			return false;
+	}
 
 	return true;
 }
@@ -4828,6 +4853,11 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx,
 	void *task_ctx_data = NULL;
 
 	if (!ctx->task) {
+		/*
+		 * perf_pmu_migrate_context() / __perf_pmu_install_event()
+		 * relies on the fact that find_get_pmu_context() cannot fail
+		 * for CPU contexts.
+		 */
 		struct perf_cpu_pmu_context *cpc;
 
 		cpc = per_cpu_ptr(pmu->cpu_pmu_context, event->cpu);
@@ -7367,6 +7397,14 @@ void perf_output_sample(struct perf_output_handle *handle,
 			if (branch_sample_hw_index(event))
 				perf_output_put(handle, data->br_stack->hw_idx);
 			perf_output_copy(handle, data->br_stack->entries, size);
+			/*
+			 * Add the extension space which is appended
+			 * right after the struct perf_branch_stack.
+			 */
+			if (data->br_stack_cntr) {
+				size = data->br_stack->nr * sizeof(u64);
+				perf_output_copy(handle, data->br_stack_cntr, size);
+			}
 		} else {
 			/*
 			 * we always store at least the value of nr
@@ -11395,9 +11433,30 @@ static DEVICE_ATTR_RW(perf_event_mux_interval_ms);
 static struct attribute *pmu_dev_attrs[] = {
 	&dev_attr_type.attr,
 	&dev_attr_perf_event_mux_interval_ms.attr,
+	&dev_attr_nr_addr_filters.attr,
+	NULL,
+};
+
+static umode_t pmu_dev_is_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct pmu *pmu = dev_get_drvdata(dev);
+
+	if (n == 2 && !pmu->nr_addr_filters)
+		return 0;
+
+	return a->mode;
+}
+
+static struct attribute_group pmu_dev_attr_group = {
+	.is_visible = pmu_dev_is_visible,
+	.attrs = pmu_dev_attrs,
+};
+
+static const struct attribute_group *pmu_dev_groups[] = {
+	&pmu_dev_attr_group,
 	NULL,
 };
-ATTRIBUTE_GROUPS(pmu_dev);
 
 static int pmu_bus_running;
 static struct bus_type pmu_bus = {
@@ -11434,18 +11493,11 @@ static int pmu_dev_alloc(struct pmu *pmu)
 	if (ret)
 		goto free_dev;
 
-	/* For PMUs with address filters, throw in an extra attribute: */
-	if (pmu->nr_addr_filters)
-		ret = device_create_file(pmu->dev, &dev_attr_nr_addr_filters);
-
-	if (ret)
-		goto del_dev;
-
-	if (pmu->attr_update)
+	if (pmu->attr_update) {
 		ret = sysfs_update_groups(&pmu->dev->kobj, pmu->attr_update);
-
-	if (ret)
-		goto del_dev;
+		if (ret)
+			goto del_dev;
+	}
 
 out:
 	return ret;
@@ -12889,6 +12941,9 @@ static void __perf_pmu_install_event(struct pmu *pmu,
 				     int cpu, struct perf_event *event)
 {
 	struct perf_event_pmu_context *epc;
+	struct perf_event_context *old_ctx = event->ctx;
+
+	get_ctx(ctx); /* normally find_get_context() */
 
 	event->cpu = cpu;
 	epc = find_get_pmu_context(pmu, ctx, event);
@@ -12897,6 +12952,11 @@ static void __perf_pmu_install_event(struct pmu *pmu,
 	if (event->state >= PERF_EVENT_STATE_OFF)
 		event->state = PERF_EVENT_STATE_INACTIVE;
 	perf_install_in_context(ctx, event, cpu);
+
+	/*
+	 * Now that event->ctx is updated and visible, put the old ctx.
+	 */
+	put_ctx(old_ctx);
 }
 
 static void __perf_pmu_install(struct perf_event_context *ctx,
@@ -12935,6 +12995,10 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 	struct perf_event_context *src_ctx, *dst_ctx;
 	LIST_HEAD(events);
 
+	/*
+	 * Since per-cpu context is persistent, no need to grab an extra
+	 * reference.
+	 */
 	src_ctx = &per_cpu_ptr(&perf_cpu_context, src_cpu)->ctx;
 	dst_ctx = &per_cpu_ptr(&perf_cpu_context, dst_cpu)->ctx;
 
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index e8d82c2f07d0..60ed43d1c29e 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -610,8 +610,8 @@ static struct page *rb_alloc_aux_page(int node, int order)
 {
 	struct page *page;
 
-	if (order > MAX_ORDER)
-		order = MAX_ORDER;
+	if (order > MAX_PAGE_ORDER)
+		order = MAX_PAGE_ORDER;
 
 	do {
 		page = alloc_pages_node(node, PERF_AUX_GFP, order);
@@ -702,9 +702,9 @@ int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event,
 
 	/*
 	 * kcalloc_node() is unable to allocate buffer if the size is larger
-	 * than: PAGE_SIZE << MAX_ORDER; directly bail out in this case.
+	 * than: PAGE_SIZE << MAX_PAGE_ORDER; directly bail out in this case.
 	 */
-	if (get_order((unsigned long)nr_pages * sizeof(void *)) > MAX_ORDER)
+	if (get_order((unsigned long)nr_pages * sizeof(void *)) > MAX_PAGE_ORDER)
 		return -ENOMEM;
 	rb->aux_pages = kcalloc_node(nr_pages, sizeof(void *), GFP_KERNEL,
 				     node);
@@ -821,7 +821,7 @@ struct perf_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags)
 	size = sizeof(struct perf_buffer);
 	size += nr_pages * sizeof(void *);
 
-	if (order_base_2(size) > PAGE_SHIFT+MAX_ORDER)
+	if (order_base_2(size) > PAGE_SHIFT+MAX_PAGE_ORDER)
 		goto fail;
 
 	node = (cpu == -1) ? cpu : cpu_to_node(cpu);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 435aac1d8c27..485bb0389b48 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -181,7 +181,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 
 	if (new_page) {
 		folio_get(new_folio);
-		page_add_new_anon_rmap(new_page, vma, addr);
+		folio_add_new_anon_rmap(new_folio, vma, addr);
 		folio_add_lru_vma(new_folio, vma);
 	} else
 		/* no new page, just dec_mm_counter for old_page */
@@ -198,7 +198,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 		set_pte_at_notify(mm, addr, pvmw.pte,
 				  mk_pte(new_page, vma->vm_page_prot));
 
-	page_remove_rmap(old_page, vma, false);
+	folio_remove_rmap_pte(old_folio, old_page, vma);
 	if (!folio_mapped(old_folio))
 		folio_free_swap(old_folio);
 	page_vma_mapped_walk_done(&pvmw);
diff --git a/kernel/exit.c b/kernel/exit.c
index ee9f43bed49a..3988a02efaef 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -69,8 +69,10 @@
 #include <linux/rethook.h>
 #include <linux/sysfs.h>
 #include <linux/user_events.h>
-
 #include <linux/uaccess.h>
+
+#include <uapi/linux/wait.h>
+
 #include <asm/unistd.h>
 #include <asm/mmu_context.h>
 
@@ -824,8 +826,6 @@ void __noreturn do_exit(long code)
 	ptrace_event(PTRACE_EVENT_EXIT, code);
 	user_events_exit(tsk);
 
-	validate_creds_for_do_exit(tsk);
-
 	io_uring_files_cancel();
 	exit_signals(tsk);  /* sets PF_EXITING */
 
@@ -909,7 +909,6 @@ void __noreturn do_exit(long code)
 	if (tsk->task_frag.page)
 		put_page(tsk->task_frag.page);
 
-	validate_creds_for_do_exit(tsk);
 	exit_task_stack_account(tsk);
 
 	check_stack_usage();
diff --git a/kernel/fork.c b/kernel/fork.c
index 10917c3e1f03..c981fa6171c1 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -53,6 +53,7 @@
 #include <linux/seccomp.h>
 #include <linux/swap.h>
 #include <linux/syscalls.h>
+#include <linux/syscall_user_dispatch.h>
 #include <linux/jiffies.h>
 #include <linux/futex.h>
 #include <linux/compat.h>
@@ -99,6 +100,7 @@
 #include <linux/stackprotector.h>
 #include <linux/user_events.h>
 #include <linux/iommu.h>
+#include <linux/rseq.h>
 
 #include <asm/pgalloc.h>
 #include <linux/uaccess.h>
@@ -165,7 +167,6 @@ void __weak arch_release_task_struct(struct task_struct *tsk)
 {
 }
 
-#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
 static struct kmem_cache *task_struct_cachep;
 
 static inline struct task_struct *alloc_task_struct_node(int node)
@@ -177,9 +178,6 @@ static inline void free_task_struct(struct task_struct *tsk)
 {
 	kmem_cache_free(task_struct_cachep, tsk);
 }
-#endif
-
-#ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR
 
 /*
  * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
@@ -412,24 +410,6 @@ void thread_stack_cache_init(void)
 }
 
 # endif /* THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) */
-#else /* CONFIG_ARCH_THREAD_STACK_ALLOCATOR */
-
-static int alloc_thread_stack_node(struct task_struct *tsk, int node)
-{
-	unsigned long *stack;
-
-	stack = arch_alloc_thread_stack_node(tsk, node);
-	tsk->stack = stack;
-	return stack ? 0 : -ENOMEM;
-}
-
-static void free_thread_stack(struct task_struct *tsk)
-{
-	arch_free_thread_stack(tsk);
-	tsk->stack = NULL;
-}
-
-#endif /* !CONFIG_ARCH_THREAD_STACK_ALLOCATOR */
 
 /* SLAB cache for signal_struct structures (tsk->signal) */
 static struct kmem_cache *signal_cachep;
@@ -650,7 +630,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	int retval;
 	unsigned long charge = 0;
 	LIST_HEAD(uf);
-	VMA_ITERATOR(old_vmi, oldmm, 0);
 	VMA_ITERATOR(vmi, mm, 0);
 
 	uprobe_start_dup_mmap();
@@ -678,16 +657,22 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		goto out;
 	khugepaged_fork(mm, oldmm);
 
-	retval = vma_iter_bulk_alloc(&vmi, oldmm->map_count);
-	if (retval)
+	/* Use __mt_dup() to efficiently build an identical maple tree. */
+	retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL);
+	if (unlikely(retval))
 		goto out;
 
 	mt_clear_in_rcu(vmi.mas.tree);
-	for_each_vma(old_vmi, mpnt) {
+	for_each_vma(vmi, mpnt) {
 		struct file *file;
 
 		vma_start_write(mpnt);
 		if (mpnt->vm_flags & VM_DONTCOPY) {
+			retval = vma_iter_clear_gfp(&vmi, mpnt->vm_start,
+						    mpnt->vm_end, GFP_KERNEL);
+			if (retval)
+				goto loop_out;
+
 			vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt));
 			continue;
 		}
@@ -749,9 +734,11 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		if (is_vm_hugetlb_page(tmp))
 			hugetlb_dup_vma_private(tmp);
 
-		/* Link the vma into the MT */
-		if (vma_iter_bulk_store(&vmi, tmp))
-			goto fail_nomem_vmi_store;
+		/*
+		 * Link the vma into the MT. After using __mt_dup(), memory
+		 * allocation is not necessary here, so it cannot fail.
+		 */
+		vma_iter_bulk_store(&vmi, tmp);
 
 		mm->map_count++;
 		if (!(tmp->vm_flags & VM_WIPEONFORK))
@@ -760,15 +747,28 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		if (tmp->vm_ops && tmp->vm_ops->open)
 			tmp->vm_ops->open(tmp);
 
-		if (retval)
+		if (retval) {
+			mpnt = vma_next(&vmi);
 			goto loop_out;
+		}
 	}
 	/* a new mm has just been created */
 	retval = arch_dup_mmap(oldmm, mm);
 loop_out:
 	vma_iter_free(&vmi);
-	if (!retval)
+	if (!retval) {
 		mt_set_in_rcu(vmi.mas.tree);
+	} else if (mpnt) {
+		/*
+		 * The entire maple tree has already been duplicated. If the
+		 * mmap duplication fails, mark the failure point with
+		 * XA_ZERO_ENTRY. In exit_mmap(), if this marker is encountered,
+		 * stop releasing VMAs that have not been duplicated after this
+		 * point.
+		 */
+		mas_set_range(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1);
+		mas_store(&vmi.mas, XA_ZERO_ENTRY);
+	}
 out:
 	mmap_write_unlock(mm);
 	flush_tlb_mm(oldmm);
@@ -778,8 +778,6 @@ fail_uprobe_end:
 	uprobe_end_dup_mmap();
 	return retval;
 
-fail_nomem_vmi_store:
-	unlink_anon_vmas(tmp);
 fail_nomem_anon_vma_fork:
 	mpol_put(vma_policy(tmp));
 fail_nomem_policy:
@@ -1021,7 +1019,6 @@ static void set_max_threads(unsigned int max_threads_suggested)
 int arch_task_struct_size __read_mostly;
 #endif
 
-#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
 static void task_struct_whitelist(unsigned long *offset, unsigned long *size)
 {
 	/* Fetch thread_struct whitelist for the architecture. */
@@ -1036,12 +1033,10 @@ static void task_struct_whitelist(unsigned long *offset, unsigned long *size)
 	else
 		*offset += offsetof(struct task_struct, thread);
 }
-#endif /* CONFIG_ARCH_TASK_STRUCT_ALLOCATOR */
 
 void __init fork_init(void)
 {
 	int i;
-#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
 #ifndef ARCH_MIN_TASKALIGN
 #define ARCH_MIN_TASKALIGN	0
 #endif
@@ -1054,7 +1049,6 @@ void __init fork_init(void)
 			arch_task_struct_size, align,
 			SLAB_PANIC|SLAB_ACCOUNT,
 			useroffset, usersize, NULL);
-#endif
 
 	/* do the arch specific task caches init */
 	arch_task_cache_init();
@@ -1588,7 +1582,7 @@ static void complete_vfork_done(struct task_struct *tsk)
 static int wait_for_vfork_done(struct task_struct *child,
 				struct completion *vfork)
 {
-	unsigned int state = TASK_UNINTERRUPTIBLE|TASK_KILLABLE|TASK_FREEZABLE;
+	unsigned int state = TASK_KILLABLE|TASK_FREEZABLE;
 	int killed;
 
 	cgroup_enter_frozen();
@@ -2928,7 +2922,7 @@ pid_t kernel_clone(struct kernel_clone_args *args)
 		get_task_struct(p);
 	}
 
-	if (IS_ENABLED(CONFIG_LRU_GEN) && !(clone_flags & CLONE_VM)) {
+	if (IS_ENABLED(CONFIG_LRU_GEN_WALKS_MMU) && !(clone_flags & CLONE_VM)) {
 		/* lock the task to synchronize with memcg migration */
 		task_lock(p);
 		lru_gen_add_mm(p->mm);
diff --git a/kernel/freezer.c b/kernel/freezer.c
index c450fa8b8b5e..f57aaf96b829 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -187,6 +187,7 @@ static int __restore_freezer_state(struct task_struct *p, void *arg)
 
 	if (state != TASK_RUNNING) {
 		WRITE_ONCE(p->__state, state);
+		p->saved_state = TASK_RUNNING;
 		return 1;
 	}
 
@@ -201,7 +202,7 @@ void __thaw_task(struct task_struct *p)
 	if (WARN_ON_ONCE(freezing(p)))
 		goto unlock;
 
-	if (task_call_func(p, __restore_freezer_state, NULL))
+	if (!frozen(p) || task_call_func(p, __restore_freezer_state, NULL))
 		goto unlock;
 
 	wake_up_state(p, TASK_FROZEN);
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 52695c59d041..e0e853412c15 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -34,6 +34,7 @@
 #include <linux/compat.h>
 #include <linux/jhash.h>
 #include <linux/pagemap.h>
+#include <linux/plist.h>
 #include <linux/memblock.h>
 #include <linux/fault-inject.h>
 #include <linux/slab.h>
@@ -700,7 +701,8 @@ retry:
 	owner = uval & FUTEX_TID_MASK;
 
 	if (pending_op && !pi && !owner) {
-		futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+		futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1,
+			   FUTEX_BITSET_MATCH_ANY);
 		return 0;
 	}
 
@@ -752,8 +754,10 @@ retry:
 	 * Wake robust non-PI futexes here. The wakeup of
 	 * PI futexes happens in exit_pi_state():
 	 */
-	if (!pi && (uval & FUTEX_WAITERS))
-		futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+	if (!pi && (uval & FUTEX_WAITERS)) {
+		futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1,
+			   FUTEX_BITSET_MATCH_ANY);
+	}
 
 	return 0;
 }
diff --git a/kernel/futex/requeue.c b/kernel/futex/requeue.c
index eb21f065816b..b47bb764b352 100644
--- a/kernel/futex/requeue.c
+++ b/kernel/futex/requeue.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
+#include <linux/plist.h>
 #include <linux/sched/signal.h>
 
 #include "futex.h"
diff --git a/kernel/futex/waitwake.c b/kernel/futex/waitwake.c
index 61b112897a84..3a10375d9521 100644
--- a/kernel/futex/waitwake.c
+++ b/kernel/futex/waitwake.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
+#include <linux/plist.h>
 #include <linux/sched/task.h>
 #include <linux/sched/signal.h>
 #include <linux/freezer.h>
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index be5642a4ec49..a08031b57a61 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -52,6 +52,8 @@ atomic_t __kexec_lock = ATOMIC_INIT(0);
 /* Flag to indicate we are going to kexec a new kernel */
 bool kexec_in_progress = false;
 
+bool kexec_file_dbg_print;
+
 int kexec_should_crash(struct task_struct *p)
 {
 	/*
@@ -276,8 +278,8 @@ int kimage_is_destination_range(struct kimage *image,
 		unsigned long mstart, mend;
 
 		mstart = image->segment[i].mem;
-		mend = mstart + image->segment[i].memsz;
-		if ((end > mstart) && (start < mend))
+		mend = mstart + image->segment[i].memsz - 1;
+		if ((end >= mstart) && (start <= mend))
 			return 1;
 	}
 
@@ -370,7 +372,7 @@ static struct page *kimage_alloc_normal_control_pages(struct kimage *image,
 		pfn   = page_to_boot_pfn(pages);
 		epfn  = pfn + count;
 		addr  = pfn << PAGE_SHIFT;
-		eaddr = epfn << PAGE_SHIFT;
+		eaddr = (epfn << PAGE_SHIFT) - 1;
 		if ((epfn >= (KEXEC_CONTROL_MEMORY_LIMIT >> PAGE_SHIFT)) ||
 			      kimage_is_destination_range(image, addr, eaddr)) {
 			list_add(&pages->lru, &extra_pages);
@@ -430,7 +432,7 @@ static struct page *kimage_alloc_crash_control_pages(struct kimage *image,
 
 	pages = NULL;
 	size = (1 << order) << PAGE_SHIFT;
-	hole_start = (image->control_page + (size - 1)) & ~(size - 1);
+	hole_start = ALIGN(image->control_page, size);
 	hole_end   = hole_start + size - 1;
 	while (hole_end <= crashk_res.end) {
 		unsigned long i;
@@ -447,7 +449,7 @@ static struct page *kimage_alloc_crash_control_pages(struct kimage *image,
 			mend   = mstart + image->segment[i].memsz - 1;
 			if ((hole_end >= mstart) && (hole_start <= mend)) {
 				/* Advance the hole to the end of the segment */
-				hole_start = (mend + (size - 1)) & ~(size - 1);
+				hole_start = ALIGN(mend, size);
 				hole_end   = hole_start + size - 1;
 				break;
 			}
@@ -455,7 +457,7 @@ static struct page *kimage_alloc_crash_control_pages(struct kimage *image,
 		/* If I don't overlap any segments I have found my hole! */
 		if (i == image->nr_segments) {
 			pages = pfn_to_page(hole_start >> PAGE_SHIFT);
-			image->control_page = hole_end;
+			image->control_page = hole_end + 1;
 			break;
 		}
 	}
@@ -716,7 +718,7 @@ static struct page *kimage_alloc_page(struct kimage *image,
 
 		/* If the page is not a destination page use it */
 		if (!kimage_is_destination_range(image, addr,
-						  addr + PAGE_SIZE))
+						  addr + PAGE_SIZE - 1))
 			break;
 
 		/*
@@ -1063,9 +1065,10 @@ __bpf_kfunc void crash_kexec(struct pt_regs *regs)
 	 * panic().  Otherwise parallel calls of panic() and crash_kexec()
 	 * may stop each other.  To exclude them, we use panic_cpu here too.
 	 */
+	old_cpu = PANIC_CPU_INVALID;
 	this_cpu = raw_smp_processor_id();
-	old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu);
-	if (old_cpu == PANIC_CPU_INVALID) {
+
+	if (atomic_try_cmpxchg(&panic_cpu, &old_cpu, this_cpu)) {
 		/* This is the 1st CPU which comes here, so go ahead. */
 		__crash_kexec(regs);
 
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index f9a419cd22d4..bef2f6f2571b 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -123,6 +123,8 @@ void kimage_file_post_load_cleanup(struct kimage *image)
 	 */
 	kfree(image->image_loader_data);
 	image->image_loader_data = NULL;
+
+	kexec_file_dbg_print = false;
 }
 
 #ifdef CONFIG_KEXEC_SIG
@@ -202,6 +204,8 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 	if (ret < 0)
 		return ret;
 	image->kernel_buf_len = ret;
+	kexec_dprintk("kernel: %p kernel_size: %#lx\n",
+		      image->kernel_buf, image->kernel_buf_len);
 
 	/* Call arch image probe handlers */
 	ret = arch_kexec_kernel_image_probe(image, image->kernel_buf,
@@ -278,6 +282,7 @@ kimage_file_alloc_init(struct kimage **rimage, int kernel_fd,
 	if (!image)
 		return -ENOMEM;
 
+	kexec_file_dbg_print = !!(flags & KEXEC_FILE_DEBUG);
 	image->file_mode = 1;
 
 	if (kexec_on_panic) {
@@ -384,13 +389,14 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
 	if (ret)
 		goto out;
 
+	kexec_dprintk("nr_segments = %lu\n", image->nr_segments);
 	for (i = 0; i < image->nr_segments; i++) {
 		struct kexec_segment *ksegment;
 
 		ksegment = &image->segment[i];
-		pr_debug("Loading segment %d: buf=0x%p bufsz=0x%zx mem=0x%lx memsz=0x%zx\n",
-			 i, ksegment->buf, ksegment->bufsz, ksegment->mem,
-			 ksegment->memsz);
+		kexec_dprintk("segment[%d]: buf=0x%p bufsz=0x%zx mem=0x%lx memsz=0x%zx\n",
+			      i, ksegment->buf, ksegment->bufsz, ksegment->mem,
+			      ksegment->memsz);
 
 		ret = kimage_load_segment(image, &image->segment[i]);
 		if (ret)
@@ -403,6 +409,8 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
 	if (ret)
 		goto out;
 
+	kexec_dprintk("kexec_file_load: type:%u, start:0x%lx head:0x%lx flags:0x%lx\n",
+		      image->type, image->start, image->head, flags);
 	/*
 	 * Free up any temporary buffers allocated which are not needed
 	 * after image has been loaded
@@ -426,11 +434,11 @@ static int locate_mem_hole_top_down(unsigned long start, unsigned long end,
 	unsigned long temp_start, temp_end;
 
 	temp_end = min(end, kbuf->buf_max);
-	temp_start = temp_end - kbuf->memsz;
+	temp_start = temp_end - kbuf->memsz + 1;
 
 	do {
 		/* align down start */
-		temp_start = temp_start & (~(kbuf->buf_align - 1));
+		temp_start = ALIGN_DOWN(temp_start, kbuf->buf_align);
 
 		if (temp_start < start || temp_start < kbuf->buf_min)
 			return 0;
@@ -592,6 +600,8 @@ static int kexec_walk_resources(struct kexec_buf *kbuf,
 					   IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
 					   crashk_res.start, crashk_res.end,
 					   kbuf, func);
+	else if (kbuf->top_down)
+		return walk_system_ram_res_rev(0, ULONG_MAX, kbuf, func);
 	else
 		return walk_system_ram_res(0, ULONG_MAX, kbuf, func);
 }
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 075a632e6c7c..d5a0ee40bf66 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2252,7 +2252,7 @@ int register_kretprobe(struct kretprobe *rp)
 		rp->rph = NULL;
 		return -ENOMEM;
 	}
-	rp->rph->rp = rp;
+	rcu_assign_pointer(rp->rph->rp, rp);
 	rp->nmissed = 0;
 	/* Establish function entry probe point */
 	ret = register_kprobe(&rp->kp);
@@ -2300,7 +2300,7 @@ void unregister_kretprobes(struct kretprobe **rps, int num)
 #ifdef CONFIG_KRETPROBE_ON_RETHOOK
 		rethook_free(rps[i]->rh);
 #else
-		rps[i]->rph->rp = NULL;
+		rcu_assign_pointer(rps[i]->rph->rp, NULL);
 #endif
 	}
 	mutex_unlock(&kprobe_mutex);
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index e85b5ad3e206..151bd3de5936 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3497,7 +3497,8 @@ static int alloc_chain_hlocks(int req)
 		size = chain_block_size(curr);
 		if (likely(size >= req)) {
 			del_chain_block(0, size, chain_block_next(curr));
-			add_chain_block(curr + req, size - req);
+			if (size > req)
+				add_chain_block(curr + req, size - req);
 			return curr;
 		}
 	}
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 2deeeca3e71b..cbae8c0b89ab 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -532,6 +532,11 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
  * This function must not be used in interrupt context. Unlocking
  * of a not locked mutex is not allowed.
  *
+ * The caller must ensure that the mutex stays alive until this function has
+ * returned - mutex_unlock() can NOT directly be used to release an object such
+ * that another concurrent task can free it.
+ * Mutexes are different from spinlocks & refcounts in this aspect.
+ *
  * This function is similar to (but not equivalent to) up().
  */
 void __sched mutex_unlock(struct mutex *lock)
diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
index d5610ad52b92..75a6f6133866 100644
--- a/kernel/locking/osq_lock.c
+++ b/kernel/locking/osq_lock.c
@@ -11,6 +11,13 @@
  * called from interrupt context and we have preemption disabled while
  * spinning.
  */
+
+struct optimistic_spin_node {
+	struct optimistic_spin_node *next, *prev;
+	int locked; /* 1 if lock acquired */
+	int cpu; /* encoded CPU # + 1 value */
+};
+
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node);
 
 /*
@@ -37,32 +44,28 @@ static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val)
 /*
  * Get a stable @node->next pointer, either for unlock() or unqueue() purposes.
  * Can return NULL in case we were the last queued and we updated @lock instead.
+ *
+ * If osq_lock() is being cancelled there must be a previous node
+ * and 'old_cpu' is its CPU #.
+ * For osq_unlock() there is never a previous node and old_cpu is
+ * set to OSQ_UNLOCKED_VAL.
  */
 static inline struct optimistic_spin_node *
 osq_wait_next(struct optimistic_spin_queue *lock,
 	      struct optimistic_spin_node *node,
-	      struct optimistic_spin_node *prev)
+	      int old_cpu)
 {
-	struct optimistic_spin_node *next = NULL;
 	int curr = encode_cpu(smp_processor_id());
-	int old;
-
-	/*
-	 * If there is a prev node in queue, then the 'old' value will be
-	 * the prev node's CPU #, else it's set to OSQ_UNLOCKED_VAL since if
-	 * we're currently last in queue, then the queue will then become empty.
-	 */
-	old = prev ? prev->cpu : OSQ_UNLOCKED_VAL;
 
 	for (;;) {
 		if (atomic_read(&lock->tail) == curr &&
-		    atomic_cmpxchg_acquire(&lock->tail, curr, old) == curr) {
+		    atomic_cmpxchg_acquire(&lock->tail, curr, old_cpu) == curr) {
 			/*
 			 * We were the last queued, we moved @lock back. @prev
 			 * will now observe @lock and will complete its
 			 * unlock()/unqueue().
 			 */
-			break;
+			return NULL;
 		}
 
 		/*
@@ -76,15 +79,15 @@ osq_wait_next(struct optimistic_spin_queue *lock,
 		 * wait for a new @node->next from its Step-C.
 		 */
 		if (node->next) {
+			struct optimistic_spin_node *next;
+
 			next = xchg(&node->next, NULL);
 			if (next)
-				break;
+				return next;
 		}
 
 		cpu_relax();
 	}
-
-	return next;
 }
 
 bool osq_lock(struct optimistic_spin_queue *lock)
@@ -186,7 +189,7 @@ bool osq_lock(struct optimistic_spin_queue *lock)
 	 * back to @prev.
 	 */
 
-	next = osq_wait_next(lock, node, prev);
+	next = osq_wait_next(lock, node, prev->cpu);
 	if (!next)
 		return false;
 
@@ -226,7 +229,7 @@ void osq_unlock(struct optimistic_spin_queue *lock)
 		return;
 	}
 
-	next = osq_wait_next(lock, node, NULL);
+	next = osq_wait_next(lock, node, OSQ_UNLOCKED_VAL);
 	if (next)
 		WRITE_ONCE(next->locked, 1);
 }
diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c
index 14235671a1a7..87b03d2e41db 100644
--- a/kernel/locking/spinlock_debug.c
+++ b/kernel/locking/spinlock_debug.c
@@ -12,6 +12,7 @@
 #include <linux/debug_locks.h>
 #include <linux/delay.h>
 #include <linux/export.h>
+#include <linux/pid.h>
 
 void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name,
 			  struct lock_class_key *key, short inner)
diff --git a/kernel/module/dups.c b/kernel/module/dups.c
index f3d7ea1e96d8..9a92f2f8c9d3 100644
--- a/kernel/module/dups.c
+++ b/kernel/module/dups.c
@@ -207,7 +207,7 @@ bool kmod_dup_request_exists_wait(char *module_name, bool wait, int *dup_ret)
 	 * optimization enabled ...
 	 */
 	ret = wait_for_completion_state(&kmod_req->first_req_done,
-					TASK_UNINTERRUPTIBLE | TASK_KILLABLE);
+					TASK_KILLABLE);
 	if (ret) {
 		*dup_ret = ret;
 		return true;
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 98fedfdb8db5..36681911c05a 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -2199,6 +2199,9 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 	mod->kunit_suites = section_objs(info, ".kunit_test_suites",
 					      sizeof(*mod->kunit_suites),
 					      &mod->num_kunit_suites);
+	mod->kunit_init_suites = section_objs(info, ".kunit_init_test_suites",
+					      sizeof(*mod->kunit_init_suites),
+					      &mod->num_kunit_init_suites);
 #endif
 
 	mod->extable = section_objs(info, "__ex_table",
diff --git a/kernel/numa.c b/kernel/numa.c
new file mode 100644
index 000000000000..67ca6b8585c0
--- /dev/null
+++ b/kernel/numa.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/printk.h>
+#include <linux/numa.h>
+
+/* Stub functions: */
+
+#ifndef memory_add_physaddr_to_nid
+int memory_add_physaddr_to_nid(u64 start)
+{
+	pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n",
+			start);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
+#endif
+
+#ifndef phys_to_target_node
+int phys_to_target_node(u64 start)
+{
+	pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n",
+			start);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(phys_to_target_node);
+#endif
diff --git a/kernel/params.c b/kernel/params.c
index 2d4a0564697e..2e447f8ae183 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -1,19 +1,20 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
-/* Helpers for initial module or kernel cmdline parsing
-   Copyright (C) 2001 Rusty Russell.
-
-*/
+/*
+ * Helpers for initial module or kernel cmdline parsing
+ * Copyright (C) 2001 Rusty Russell.
+ */
+#include <linux/ctype.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/kstrtox.h>
-#include <linux/string.h>
-#include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
-#include <linux/device.h>
-#include <linux/err.h>
-#include <linux/slab.h>
-#include <linux/ctype.h>
+#include <linux/overflow.h>
 #include <linux/security.h>
+#include <linux/slab.h>
+#include <linux/string.h>
 
 #ifdef CONFIG_SYSFS
 /* Protects all built-in parameters, modules use their own param_lock */
@@ -48,7 +49,7 @@ static void *kmalloc_parameter(unsigned int size)
 {
 	struct kmalloced_param *p;
 
-	p = kmalloc(sizeof(*p) + size, GFP_KERNEL);
+	p = kmalloc(size_add(sizeof(*p), size), GFP_KERNEL);
 	if (!p)
 		return NULL;
 
@@ -120,9 +121,7 @@ static int parse_one(char *param,
 		     unsigned num_params,
 		     s16 min_level,
 		     s16 max_level,
-		     void *arg,
-		     int (*handle_unknown)(char *param, char *val,
-				     const char *doing, void *arg))
+		     void *arg, parse_unknown_fn handle_unknown)
 {
 	unsigned int i;
 	int err;
@@ -165,9 +164,7 @@ char *parse_args(const char *doing,
 		 unsigned num,
 		 s16 min_level,
 		 s16 max_level,
-		 void *arg,
-		 int (*unknown)(char *param, char *val,
-				const char *doing, void *arg))
+		 void *arg, parse_unknown_fn unknown)
 {
 	char *param, *val, *err = NULL;
 
@@ -264,17 +261,22 @@ EXPORT_SYMBOL_GPL(param_set_uint_minmax);
 
 int param_set_charp(const char *val, const struct kernel_param *kp)
 {
-	if (strlen(val) > 1024) {
+	size_t len, maxlen = 1024;
+
+	len = strnlen(val, maxlen + 1);
+	if (len == maxlen + 1) {
 		pr_err("%s: string parameter too long\n", kp->name);
 		return -ENOSPC;
 	}
 
 	maybe_kfree_parameter(*(char **)kp->arg);
 
-	/* This is a hack.  We can't kmalloc in early boot, and we
-	 * don't need to; this mangled commandline is preserved. */
+	/*
+	 * This is a hack. We can't kmalloc() in early boot, and we
+	 * don't need to; this mangled commandline is preserved.
+	 */
 	if (slab_is_available()) {
-		*(char **)kp->arg = kmalloc_parameter(strlen(val)+1);
+		*(char **)kp->arg = kmalloc_parameter(len + 1);
 		if (!*(char **)kp->arg)
 			return -ENOMEM;
 		strcpy(*(char **)kp->arg, val);
@@ -512,7 +514,7 @@ int param_set_copystring(const char *val, const struct kernel_param *kp)
 {
 	const struct kparam_string *kps = kp->str;
 
-	if (strlen(val)+1 > kps->maxlen) {
+	if (strnlen(val, kps->maxlen) == kps->maxlen) {
 		pr_err("%s: string doesn't fit in %u chars.\n",
 		       kp->name, kps->maxlen-1);
 		return -ENOSPC;
@@ -743,8 +745,10 @@ void module_param_sysfs_remove(struct module *mod)
 {
 	if (mod->mkobj.mp) {
 		sysfs_remove_group(&mod->mkobj.kobj, &mod->mkobj.mp->grp);
-		/* We are positive that no one is using any param
-		 * attrs at this point.  Deallocate immediately. */
+		/*
+		 * We are positive that no one is using any param
+		 * attrs at this point. Deallocate immediately.
+		 */
 		free_module_param_attrs(&mod->mkobj);
 	}
 }
diff --git a/kernel/pid.c b/kernel/pid.c
index 6500ef956f2f..b52b10865454 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -700,7 +700,7 @@ static int pidfd_getfd(struct pid *pid, int fd)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ret = receive_fd(file, O_CLOEXEC);
+	ret = receive_fd(file, NULL, O_CLOEXEC);
 	fput(file);
 
 	return ret;
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 3028b2218aa4..7ade20e95232 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -23,6 +23,7 @@
 #include <linux/sched/task.h>
 #include <linux/sched/signal.h>
 #include <linux/idr.h>
+#include <uapi/linux/wait.h>
 #include "pid_sysctl.h"
 
 static DEFINE_MUTEX(pid_caches_mutex);
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index dee341ae4ace..4b0b7cf2e019 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -642,9 +642,9 @@ int hibernation_platform_enter(void)
  */
 static void power_down(void)
 {
-#ifdef CONFIG_SUSPEND
 	int error;
 
+#ifdef CONFIG_SUSPEND
 	if (hibernation_mode == HIBERNATION_SUSPEND) {
 		error = suspend_devices_and_enter(mem_sleep_current);
 		if (error) {
@@ -667,7 +667,13 @@ static void power_down(void)
 		kernel_restart(NULL);
 		break;
 	case HIBERNATION_PLATFORM:
-		hibernation_platform_enter();
+		error = hibernation_platform_enter();
+		if (error == -EAGAIN || error == -EBUSY) {
+			swsusp_unmark();
+			events_check_enabled = false;
+			pr_info("Wakeup event detected during hibernation, rolling back.\n");
+			return;
+		}
 		fallthrough;
 	case HIBERNATION_SHUTDOWN:
 		if (kernel_can_power_off())
diff --git a/kernel/power/main.c b/kernel/power/main.c
index f6425ae3e8b0..b1ae9b677d03 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -60,22 +60,6 @@ EXPORT_SYMBOL_GPL(lock_system_sleep);
 
 void unlock_system_sleep(unsigned int flags)
 {
-	/*
-	 * Don't use freezer_count() because we don't want the call to
-	 * try_to_freeze() here.
-	 *
-	 * Reason:
-	 * Fundamentally, we just don't need it, because freezing condition
-	 * doesn't come into effect until we release the
-	 * system_transition_mutex lock, since the freezer always works with
-	 * system_transition_mutex held.
-	 *
-	 * More importantly, in the case of hibernation,
-	 * unlock_system_sleep() gets called in snapshot_read() and
-	 * snapshot_write() when the freezing condition is still in effect.
-	 * Which means, if we use try_to_freeze() here, it would make them
-	 * enter the refrigerator, thus causing hibernation to lockup.
-	 */
 	if (!(flags & PF_NOFREEZE))
 		current->flags &= ~PF_NOFREEZE;
 	mutex_unlock(&system_transition_mutex);
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 17fd9aaaf084..8499a39c62f4 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -175,6 +175,8 @@ extern int swsusp_write(unsigned int flags);
 void swsusp_close(void);
 #ifdef CONFIG_SUSPEND
 extern int swsusp_unmark(void);
+#else
+static inline int swsusp_unmark(void) { return 0; }
 #endif
 
 struct __kernel_old_timeval;
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 50a15408c3fc..5c96ff067c64 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1119,7 +1119,7 @@ static void mark_nosave_pages(struct memory_bitmap *bm)
 int create_basic_memory_bitmaps(void)
 {
 	struct memory_bitmap *bm1, *bm2;
-	int error = 0;
+	int error;
 
 	if (forbidden_pages_map && free_pages_map)
 		return 0;
@@ -1487,11 +1487,11 @@ static bool copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
 	s_page = pfn_to_page(src_pfn);
 	d_page = pfn_to_page(dst_pfn);
 	if (PageHighMem(s_page)) {
-		src = kmap_atomic(s_page);
-		dst = kmap_atomic(d_page);
+		src = kmap_local_page(s_page);
+		dst = kmap_local_page(d_page);
 		zeros_only = do_copy_page(dst, src);
-		kunmap_atomic(dst);
-		kunmap_atomic(src);
+		kunmap_local(dst);
+		kunmap_local(src);
 	} else {
 		if (PageHighMem(d_page)) {
 			/*
@@ -1499,9 +1499,9 @@ static bool copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
 			 * data modified by kmap_atomic()
 			 */
 			zeros_only = safe_copy_page(buffer, s_page);
-			dst = kmap_atomic(d_page);
+			dst = kmap_local_page(d_page);
 			copy_page(dst, buffer);
-			kunmap_atomic(dst);
+			kunmap_local(dst);
 		} else {
 			zeros_only = safe_copy_page(page_address(d_page), s_page);
 		}
@@ -2778,7 +2778,7 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca)
 int snapshot_write_next(struct snapshot_handle *handle)
 {
 	static struct chain_allocator ca;
-	int error = 0;
+	int error;
 
 next:
 	/* Check if we have already loaded the entire image */
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index a2cb0babb5ec..6053ddddaf65 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -451,7 +451,7 @@ err_close:
 static int swap_write_page(struct swap_map_handle *handle, void *buf,
 		struct hib_bio_batch *hb)
 {
-	int error = 0;
+	int error;
 	sector_t offset;
 
 	if (!handle->cur)
@@ -606,11 +606,11 @@ static int crc32_threadfn(void *data)
 	unsigned i;
 
 	while (1) {
-		wait_event(d->go, atomic_read(&d->ready) ||
+		wait_event(d->go, atomic_read_acquire(&d->ready) ||
 		                  kthread_should_stop());
 		if (kthread_should_stop()) {
 			d->thr = NULL;
-			atomic_set(&d->stop, 1);
+			atomic_set_release(&d->stop, 1);
 			wake_up(&d->done);
 			break;
 		}
@@ -619,7 +619,7 @@ static int crc32_threadfn(void *data)
 		for (i = 0; i < d->run_threads; i++)
 			*d->crc32 = crc32_le(*d->crc32,
 			                     d->unc[i], *d->unc_len[i]);
-		atomic_set(&d->stop, 1);
+		atomic_set_release(&d->stop, 1);
 		wake_up(&d->done);
 	}
 	return 0;
@@ -649,12 +649,12 @@ static int lzo_compress_threadfn(void *data)
 	struct cmp_data *d = data;
 
 	while (1) {
-		wait_event(d->go, atomic_read(&d->ready) ||
+		wait_event(d->go, atomic_read_acquire(&d->ready) ||
 		                  kthread_should_stop());
 		if (kthread_should_stop()) {
 			d->thr = NULL;
 			d->ret = -1;
-			atomic_set(&d->stop, 1);
+			atomic_set_release(&d->stop, 1);
 			wake_up(&d->done);
 			break;
 		}
@@ -663,7 +663,7 @@ static int lzo_compress_threadfn(void *data)
 		d->ret = lzo1x_1_compress(d->unc, d->unc_len,
 		                          d->cmp + LZO_HEADER, &d->cmp_len,
 		                          d->wrk);
-		atomic_set(&d->stop, 1);
+		atomic_set_release(&d->stop, 1);
 		wake_up(&d->done);
 	}
 	return 0;
@@ -798,7 +798,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
 
 			data[thr].unc_len = off;
 
-			atomic_set(&data[thr].ready, 1);
+			atomic_set_release(&data[thr].ready, 1);
 			wake_up(&data[thr].go);
 		}
 
@@ -806,12 +806,12 @@ static int save_image_lzo(struct swap_map_handle *handle,
 			break;
 
 		crc->run_threads = thr;
-		atomic_set(&crc->ready, 1);
+		atomic_set_release(&crc->ready, 1);
 		wake_up(&crc->go);
 
 		for (run_threads = thr, thr = 0; thr < run_threads; thr++) {
 			wait_event(data[thr].done,
-			           atomic_read(&data[thr].stop));
+				atomic_read_acquire(&data[thr].stop));
 			atomic_set(&data[thr].stop, 0);
 
 			ret = data[thr].ret;
@@ -850,7 +850,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
 			}
 		}
 
-		wait_event(crc->done, atomic_read(&crc->stop));
+		wait_event(crc->done, atomic_read_acquire(&crc->stop));
 		atomic_set(&crc->stop, 0);
 	}
 
@@ -1132,12 +1132,12 @@ static int lzo_decompress_threadfn(void *data)
 	struct dec_data *d = data;
 
 	while (1) {
-		wait_event(d->go, atomic_read(&d->ready) ||
+		wait_event(d->go, atomic_read_acquire(&d->ready) ||
 		                  kthread_should_stop());
 		if (kthread_should_stop()) {
 			d->thr = NULL;
 			d->ret = -1;
-			atomic_set(&d->stop, 1);
+			atomic_set_release(&d->stop, 1);
 			wake_up(&d->done);
 			break;
 		}
@@ -1150,7 +1150,7 @@ static int lzo_decompress_threadfn(void *data)
 			flush_icache_range((unsigned long)d->unc,
 					   (unsigned long)d->unc + d->unc_len);
 
-		atomic_set(&d->stop, 1);
+		atomic_set_release(&d->stop, 1);
 		wake_up(&d->done);
 	}
 	return 0;
@@ -1335,7 +1335,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 		}
 
 		if (crc->run_threads) {
-			wait_event(crc->done, atomic_read(&crc->stop));
+			wait_event(crc->done, atomic_read_acquire(&crc->stop));
 			atomic_set(&crc->stop, 0);
 			crc->run_threads = 0;
 		}
@@ -1371,7 +1371,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 					pg = 0;
 			}
 
-			atomic_set(&data[thr].ready, 1);
+			atomic_set_release(&data[thr].ready, 1);
 			wake_up(&data[thr].go);
 		}
 
@@ -1390,7 +1390,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 
 		for (run_threads = thr, thr = 0; thr < run_threads; thr++) {
 			wait_event(data[thr].done,
-			           atomic_read(&data[thr].stop));
+				atomic_read_acquire(&data[thr].stop));
 			atomic_set(&data[thr].stop, 0);
 
 			ret = data[thr].ret;
@@ -1421,7 +1421,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 				ret = snapshot_write_next(snapshot);
 				if (ret <= 0) {
 					crc->run_threads = thr + 1;
-					atomic_set(&crc->ready, 1);
+					atomic_set_release(&crc->ready, 1);
 					wake_up(&crc->go);
 					goto out_finish;
 				}
@@ -1429,13 +1429,13 @@ static int load_image_lzo(struct swap_map_handle *handle,
 		}
 
 		crc->run_threads = thr;
-		atomic_set(&crc->ready, 1);
+		atomic_set_release(&crc->ready, 1);
 		wake_up(&crc->go);
 	}
 
 out_finish:
 	if (crc->run_threads) {
-		wait_event(crc->done, atomic_read(&crc->stop));
+		wait_event(crc->done, atomic_read_acquire(&crc->stop));
 		atomic_set(&crc->stop, 0);
 	}
 	stop = ktime_get();
@@ -1566,7 +1566,6 @@ put:
 
 /**
  * swsusp_close - close resume device.
- * @exclusive: Close the resume device which is exclusively opened.
  */
 
 void swsusp_close(void)
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index d8b5e13a2229..2fabd497d659 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -145,20 +145,9 @@ void __ptrace_unlink(struct task_struct *child)
 	 */
 	if (!(child->flags & PF_EXITING) &&
 	    (child->signal->flags & SIGNAL_STOP_STOPPED ||
-	     child->signal->group_stop_count)) {
+	     child->signal->group_stop_count))
 		child->jobctl |= JOBCTL_STOP_PENDING;
 
-		/*
-		 * This is only possible if this thread was cloned by the
-		 * traced task running in the stopped group, set the signal
-		 * for the future reports.
-		 * FIXME: we should change ptrace_init_task() to handle this
-		 * case.
-		 */
-		if (!(child->jobctl & JOBCTL_STOP_SIGMASK))
-			child->jobctl |= SIGSTOP;
-	}
-
 	/*
 	 * If transition to TASK_STOPPED is pending or in TASK_TRACED, kick
 	 * @child in the butt.  Note that @resume should be used iff @child
@@ -386,6 +375,34 @@ static int check_ptrace_options(unsigned long data)
 	return 0;
 }
 
+static inline void ptrace_set_stopped(struct task_struct *task)
+{
+	guard(spinlock)(&task->sighand->siglock);
+
+	/*
+	 * If the task is already STOPPED, set JOBCTL_TRAP_STOP and
+	 * TRAPPING, and kick it so that it transits to TRACED.  TRAPPING
+	 * will be cleared if the child completes the transition or any
+	 * event which clears the group stop states happens.  We'll wait
+	 * for the transition to complete before returning from this
+	 * function.
+	 *
+	 * This hides STOPPED -> RUNNING -> TRACED transition from the
+	 * attaching thread but a different thread in the same group can
+	 * still observe the transient RUNNING state.  IOW, if another
+	 * thread's WNOHANG wait(2) on the stopped tracee races against
+	 * ATTACH, the wait(2) may fail due to the transient RUNNING.
+	 *
+	 * The following task_is_stopped() test is safe as both transitions
+	 * in and out of STOPPED are protected by siglock.
+	 */
+	if (task_is_stopped(task) &&
+	    task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) {
+		task->jobctl &= ~JOBCTL_STOPPED;
+		signal_wake_up_state(task, __TASK_STOPPED);
+	}
+}
+
 static int ptrace_attach(struct task_struct *task, long request,
 			 unsigned long addr,
 			 unsigned long flags)
@@ -393,17 +410,17 @@ static int ptrace_attach(struct task_struct *task, long request,
 	bool seize = (request == PTRACE_SEIZE);
 	int retval;
 
-	retval = -EIO;
 	if (seize) {
 		if (addr != 0)
-			goto out;
+			return -EIO;
 		/*
 		 * This duplicates the check in check_ptrace_options() because
 		 * ptrace_attach() and ptrace_setoptions() have historically
 		 * used different error codes for unknown ptrace options.
 		 */
 		if (flags & ~(unsigned long)PTRACE_O_MASK)
-			goto out;
+			return -EIO;
+
 		retval = check_ptrace_options(flags);
 		if (retval)
 			return retval;
@@ -414,88 +431,54 @@ static int ptrace_attach(struct task_struct *task, long request,
 
 	audit_ptrace(task);
 
-	retval = -EPERM;
 	if (unlikely(task->flags & PF_KTHREAD))
-		goto out;
+		return -EPERM;
 	if (same_thread_group(task, current))
-		goto out;
+		return -EPERM;
 
 	/*
 	 * Protect exec's credential calculations against our interference;
 	 * SUID, SGID and LSM creds get determined differently
 	 * under ptrace.
 	 */
-	retval = -ERESTARTNOINTR;
-	if (mutex_lock_interruptible(&task->signal->cred_guard_mutex))
-		goto out;
+	scoped_cond_guard (mutex_intr, return -ERESTARTNOINTR,
+			   &task->signal->cred_guard_mutex) {
 
-	task_lock(task);
-	retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS);
-	task_unlock(task);
-	if (retval)
-		goto unlock_creds;
+		scoped_guard (task_lock, task) {
+			retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS);
+			if (retval)
+				return retval;
+		}
 
-	write_lock_irq(&tasklist_lock);
-	retval = -EPERM;
-	if (unlikely(task->exit_state))
-		goto unlock_tasklist;
-	if (task->ptrace)
-		goto unlock_tasklist;
+		scoped_guard (write_lock_irq, &tasklist_lock) {
+			if (unlikely(task->exit_state))
+				return -EPERM;
+			if (task->ptrace)
+				return -EPERM;
 
-	task->ptrace = flags;
+			task->ptrace = flags;
 
-	ptrace_link(task, current);
+			ptrace_link(task, current);
 
-	/* SEIZE doesn't trap tracee on attach */
-	if (!seize)
-		send_sig_info(SIGSTOP, SEND_SIG_PRIV, task);
+			/* SEIZE doesn't trap tracee on attach */
+			if (!seize)
+				send_sig_info(SIGSTOP, SEND_SIG_PRIV, task);
 
-	spin_lock(&task->sighand->siglock);
+			ptrace_set_stopped(task);
+		}
+	}
 
 	/*
-	 * If the task is already STOPPED, set JOBCTL_TRAP_STOP and
-	 * TRAPPING, and kick it so that it transits to TRACED.  TRAPPING
-	 * will be cleared if the child completes the transition or any
-	 * event which clears the group stop states happens.  We'll wait
-	 * for the transition to complete before returning from this
-	 * function.
-	 *
-	 * This hides STOPPED -> RUNNING -> TRACED transition from the
-	 * attaching thread but a different thread in the same group can
-	 * still observe the transient RUNNING state.  IOW, if another
-	 * thread's WNOHANG wait(2) on the stopped tracee races against
-	 * ATTACH, the wait(2) may fail due to the transient RUNNING.
-	 *
-	 * The following task_is_stopped() test is safe as both transitions
-	 * in and out of STOPPED are protected by siglock.
+	 * We do not bother to change retval or clear JOBCTL_TRAPPING
+	 * if wait_on_bit() was interrupted by SIGKILL. The tracer will
+	 * not return to user-mode, it will exit and clear this bit in
+	 * __ptrace_unlink() if it wasn't already cleared by the tracee;
+	 * and until then nobody can ptrace this task.
 	 */
-	if (task_is_stopped(task) &&
-	    task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) {
-		task->jobctl &= ~JOBCTL_STOPPED;
-		signal_wake_up_state(task, __TASK_STOPPED);
-	}
-
-	spin_unlock(&task->sighand->siglock);
-
-	retval = 0;
-unlock_tasklist:
-	write_unlock_irq(&tasklist_lock);
-unlock_creds:
-	mutex_unlock(&task->signal->cred_guard_mutex);
-out:
-	if (!retval) {
-		/*
-		 * We do not bother to change retval or clear JOBCTL_TRAPPING
-		 * if wait_on_bit() was interrupted by SIGKILL. The tracer will
-		 * not return to user-mode, it will exit and clear this bit in
-		 * __ptrace_unlink() if it wasn't already cleared by the tracee;
-		 * and until then nobody can ptrace this task.
-		 */
-		wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, TASK_KILLABLE);
-		proc_ptrace_connector(task, PTRACE_ATTACH);
-	}
+	wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, TASK_KILLABLE);
+	proc_ptrace_connector(task, PTRACE_ATTACH);
 
-	return retval;
+	return 0;
 }
 
 /**
diff --git a/kernel/reboot.c b/kernel/reboot.c
index 395a0ea3c7a8..22c16e2564cc 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -59,6 +59,14 @@ struct sys_off_handler {
 };
 
 /*
+ * This variable is used to indicate if a halt was initiated instead of a
+ * reboot when the reboot call was invoked with LINUX_REBOOT_CMD_POWER_OFF, but
+ * the system cannot be powered off. This allowes kernel_halt() to notify users
+ * of that.
+ */
+static bool poweroff_fallback_to_halt;
+
+/*
  * Temporary stub that prevents linkage failure while we're in process
  * of removing all uses of legacy pm_power_off() around the kernel.
  */
@@ -297,7 +305,10 @@ void kernel_halt(void)
 	kernel_shutdown_prepare(SYSTEM_HALT);
 	migrate_to_reboot_cpu();
 	syscore_shutdown();
-	pr_emerg("System halted\n");
+	if (poweroff_fallback_to_halt)
+		pr_emerg("Power off not available: System halted instead\n");
+	else
+		pr_emerg("System halted\n");
 	kmsg_dump(KMSG_DUMP_SHUTDOWN);
 	machine_halt();
 }
@@ -732,8 +743,10 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
 	/* Instead of trying to make the power_off code look like
 	 * halt when pm_power_off is not set do it the easy way.
 	 */
-	if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !kernel_can_power_off())
+	if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !kernel_can_power_off()) {
+		poweroff_fallback_to_halt = true;
 		cmd = LINUX_REBOOT_CMD_HALT;
+	}
 
 	mutex_lock(&system_transition_mutex);
 	switch (cmd) {
@@ -957,21 +970,24 @@ static void hw_failure_emergency_poweroff(int poweroff_delay_ms)
 }
 
 /**
- * hw_protection_shutdown - Trigger an emergency system poweroff
+ * __hw_protection_shutdown - Trigger an emergency system shutdown or reboot
  *
- * @reason:		Reason of emergency shutdown to be printed.
- * @ms_until_forced:	Time to wait for orderly shutdown before tiggering a
- *			forced shudown. Negative value disables the forced
- *			shutdown.
+ * @reason:		Reason of emergency shutdown or reboot to be printed.
+ * @ms_until_forced:	Time to wait for orderly shutdown or reboot before
+ *			triggering it. Negative value disables the forced
+ *			shutdown or reboot.
+ * @shutdown:		If true, indicates that a shutdown will happen
+ *			after the critical tempeature is reached.
+ *			If false, indicates that a reboot will happen
+ *			after the critical tempeature is reached.
  *
- * Initiate an emergency system shutdown in order to protect hardware from
- * further damage. Usage examples include a thermal protection or a voltage or
- * current regulator failures.
- * NOTE: The request is ignored if protection shutdown is already pending even
- * if the previous request has given a large timeout for forced shutdown.
- * Can be called from any context.
+ * Initiate an emergency system shutdown or reboot in order to protect
+ * hardware from further damage. Usage examples include a thermal protection.
+ * NOTE: The request is ignored if protection shutdown or reboot is already
+ * pending even if the previous request has given a large timeout for forced
+ * shutdown/reboot.
  */
-void hw_protection_shutdown(const char *reason, int ms_until_forced)
+void __hw_protection_shutdown(const char *reason, int ms_until_forced, bool shutdown)
 {
 	static atomic_t allow_proceed = ATOMIC_INIT(1);
 
@@ -986,9 +1002,12 @@ void hw_protection_shutdown(const char *reason, int ms_until_forced)
 	 * orderly_poweroff failure
 	 */
 	hw_failure_emergency_poweroff(ms_until_forced);
-	orderly_poweroff(true);
+	if (shutdown)
+		orderly_poweroff(true);
+	else
+		orderly_reboot();
 }
-EXPORT_SYMBOL_GPL(hw_protection_shutdown);
+EXPORT_SYMBOL_GPL(__hw_protection_shutdown);
 
 static int __init reboot_setup(char *str)
 {
diff --git a/kernel/relay.c b/kernel/relay.c
index 83fe0325cde1..a8e90e98bf2c 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -1073,167 +1073,6 @@ static ssize_t relay_file_read(struct file *filp,
 	return written;
 }
 
-static void relay_consume_bytes(struct rchan_buf *rbuf, int bytes_consumed)
-{
-	rbuf->bytes_consumed += bytes_consumed;
-
-	if (rbuf->bytes_consumed >= rbuf->chan->subbuf_size) {
-		relay_subbufs_consumed(rbuf->chan, rbuf->cpu, 1);
-		rbuf->bytes_consumed %= rbuf->chan->subbuf_size;
-	}
-}
-
-static void relay_pipe_buf_release(struct pipe_inode_info *pipe,
-				   struct pipe_buffer *buf)
-{
-	struct rchan_buf *rbuf;
-
-	rbuf = (struct rchan_buf *)page_private(buf->page);
-	relay_consume_bytes(rbuf, buf->private);
-}
-
-static const struct pipe_buf_operations relay_pipe_buf_ops = {
-	.release	= relay_pipe_buf_release,
-	.try_steal	= generic_pipe_buf_try_steal,
-	.get		= generic_pipe_buf_get,
-};
-
-static void relay_page_release(struct splice_pipe_desc *spd, unsigned int i)
-{
-}
-
-/*
- *	subbuf_splice_actor - splice up to one subbuf's worth of data
- */
-static ssize_t subbuf_splice_actor(struct file *in,
-			       loff_t *ppos,
-			       struct pipe_inode_info *pipe,
-			       size_t len,
-			       unsigned int flags,
-			       int *nonpad_ret)
-{
-	unsigned int pidx, poff, total_len, subbuf_pages, nr_pages;
-	struct rchan_buf *rbuf = in->private_data;
-	unsigned int subbuf_size = rbuf->chan->subbuf_size;
-	uint64_t pos = (uint64_t) *ppos;
-	uint32_t alloc_size = (uint32_t) rbuf->chan->alloc_size;
-	size_t read_start = (size_t) do_div(pos, alloc_size);
-	size_t read_subbuf = read_start / subbuf_size;
-	size_t padding = rbuf->padding[read_subbuf];
-	size_t nonpad_end = read_subbuf * subbuf_size + subbuf_size - padding;
-	struct page *pages[PIPE_DEF_BUFFERS];
-	struct partial_page partial[PIPE_DEF_BUFFERS];
-	struct splice_pipe_desc spd = {
-		.pages = pages,
-		.nr_pages = 0,
-		.nr_pages_max = PIPE_DEF_BUFFERS,
-		.partial = partial,
-		.ops = &relay_pipe_buf_ops,
-		.spd_release = relay_page_release,
-	};
-	ssize_t ret;
-
-	if (rbuf->subbufs_produced == rbuf->subbufs_consumed)
-		return 0;
-	if (splice_grow_spd(pipe, &spd))
-		return -ENOMEM;
-
-	/*
-	 * Adjust read len, if longer than what is available
-	 */
-	if (len > (subbuf_size - read_start % subbuf_size))
-		len = subbuf_size - read_start % subbuf_size;
-
-	subbuf_pages = rbuf->chan->alloc_size >> PAGE_SHIFT;
-	pidx = (read_start / PAGE_SIZE) % subbuf_pages;
-	poff = read_start & ~PAGE_MASK;
-	nr_pages = min_t(unsigned int, subbuf_pages, spd.nr_pages_max);
-
-	for (total_len = 0; spd.nr_pages < nr_pages; spd.nr_pages++) {
-		unsigned int this_len, this_end, private;
-		unsigned int cur_pos = read_start + total_len;
-
-		if (!len)
-			break;
-
-		this_len = min_t(unsigned long, len, PAGE_SIZE - poff);
-		private = this_len;
-
-		spd.pages[spd.nr_pages] = rbuf->page_array[pidx];
-		spd.partial[spd.nr_pages].offset = poff;
-
-		this_end = cur_pos + this_len;
-		if (this_end >= nonpad_end) {
-			this_len = nonpad_end - cur_pos;
-			private = this_len + padding;
-		}
-		spd.partial[spd.nr_pages].len = this_len;
-		spd.partial[spd.nr_pages].private = private;
-
-		len -= this_len;
-		total_len += this_len;
-		poff = 0;
-		pidx = (pidx + 1) % subbuf_pages;
-
-		if (this_end >= nonpad_end) {
-			spd.nr_pages++;
-			break;
-		}
-	}
-
-	ret = 0;
-	if (!spd.nr_pages)
-		goto out;
-
-	ret = *nonpad_ret = splice_to_pipe(pipe, &spd);
-	if (ret < 0 || ret < total_len)
-		goto out;
-
-        if (read_start + ret == nonpad_end)
-                ret += padding;
-
-out:
-	splice_shrink_spd(&spd);
-	return ret;
-}
-
-static ssize_t relay_file_splice_read(struct file *in,
-				      loff_t *ppos,
-				      struct pipe_inode_info *pipe,
-				      size_t len,
-				      unsigned int flags)
-{
-	ssize_t spliced;
-	int ret;
-	int nonpad_ret = 0;
-
-	ret = 0;
-	spliced = 0;
-
-	while (len && !spliced) {
-		ret = subbuf_splice_actor(in, ppos, pipe, len, flags, &nonpad_ret);
-		if (ret < 0)
-			break;
-		else if (!ret) {
-			if (flags & SPLICE_F_NONBLOCK)
-				ret = -EAGAIN;
-			break;
-		}
-
-		*ppos += ret;
-		if (ret > len)
-			len = 0;
-		else
-			len -= ret;
-		spliced += nonpad_ret;
-		nonpad_ret = 0;
-	}
-
-	if (spliced)
-		return spliced;
-
-	return ret;
-}
 
 const struct file_operations relay_file_operations = {
 	.open		= relay_file_open,
@@ -1242,6 +1081,5 @@ const struct file_operations relay_file_operations = {
 	.read		= relay_file_read,
 	.llseek		= no_llseek,
 	.release	= relay_file_release,
-	.splice_read	= relay_file_splice_read,
 };
 EXPORT_SYMBOL_GPL(relay_file_operations);
diff --git a/kernel/resource.c b/kernel/resource.c
index 866ef3663a0b..fcbca39dbc45 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -27,6 +27,8 @@
 #include <linux/mount.h>
 #include <linux/resource_ext.h>
 #include <uapi/linux/magic.h>
+#include <linux/string.h>
+#include <linux/vmalloc.h>
 #include <asm/io.h>
 
 
@@ -430,6 +432,61 @@ int walk_system_ram_res(u64 start, u64 end, void *arg,
 }
 
 /*
+ * This function, being a variant of walk_system_ram_res(), calls the @func
+ * callback against all memory ranges of type System RAM which are marked as
+ * IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY in reversed order, i.e., from
+ * higher to lower.
+ */
+int walk_system_ram_res_rev(u64 start, u64 end, void *arg,
+				int (*func)(struct resource *, void *))
+{
+	struct resource res, *rams;
+	int rams_size = 16, i;
+	unsigned long flags;
+	int ret = -1;
+
+	/* create a list */
+	rams = kvcalloc(rams_size, sizeof(struct resource), GFP_KERNEL);
+	if (!rams)
+		return ret;
+
+	flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+	i = 0;
+	while ((start < end) &&
+		(!find_next_iomem_res(start, end, flags, IORES_DESC_NONE, &res))) {
+		if (i >= rams_size) {
+			/* re-alloc */
+			struct resource *rams_new;
+
+			rams_new = kvrealloc(rams, rams_size * sizeof(struct resource),
+					     (rams_size + 16) * sizeof(struct resource),
+					     GFP_KERNEL);
+			if (!rams_new)
+				goto out;
+
+			rams = rams_new;
+			rams_size += 16;
+		}
+
+		rams[i].start = res.start;
+		rams[i++].end = res.end;
+
+		start = res.end + 1;
+	}
+
+	/* go reverse */
+	for (i--; i >= 0; i--) {
+		ret = (*func)(&rams[i], arg);
+		if (ret)
+			break;
+	}
+
+out:
+	kvfree(rams);
+	return ret;
+}
+
+/*
  * This function calls the @func callback against all memory ranges, which
  * are ranges marked as IORESOURCE_MEM and IORESOUCE_BUSY.
  */
@@ -1844,8 +1901,8 @@ get_free_mem_region(struct device *dev, struct resource *base,
 
 	write_lock(&resource_lock);
 	for (addr = gfr_start(base, size, align, flags);
-	     gfr_continue(base, addr, size, flags);
-	     addr = gfr_next(addr, size, flags)) {
+	     gfr_continue(base, addr, align, flags);
+	     addr = gfr_next(addr, align, flags)) {
 		if (__region_intersects(base, addr, size, 0, IORES_DESC_NONE) !=
 		    REGION_DISJOINT)
 			continue;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a708d225c28e..9116bcc90346 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -57,6 +57,7 @@
 #include <linux/profile.h>
 #include <linux/psi.h>
 #include <linux/rcuwait_api.h>
+#include <linux/rseq.h>
 #include <linux/sched/wake_q.h>
 #include <linux/scs.h>
 #include <linux/slab.h>
@@ -1131,6 +1132,28 @@ static void wake_up_idle_cpu(int cpu)
 	if (cpu == smp_processor_id())
 		return;
 
+	/*
+	 * Set TIF_NEED_RESCHED and send an IPI if in the non-polling
+	 * part of the idle loop. This forces an exit from the idle loop
+	 * and a round trip to schedule(). Now this could be optimized
+	 * because a simple new idle loop iteration is enough to
+	 * re-evaluate the next tick. Provided some re-ordering of tick
+	 * nohz functions that would need to follow TIF_NR_POLLING
+	 * clearing:
+	 *
+	 * - On most archs, a simple fetch_or on ti::flags with a
+	 *   "0" value would be enough to know if an IPI needs to be sent.
+	 *
+	 * - x86 needs to perform a last need_resched() check between
+	 *   monitor and mwait which doesn't take timers into account.
+	 *   There a dedicated TIF_TIMER flag would be required to
+	 *   fetch_or here and be checked along with TIF_NEED_RESCHED
+	 *   before mwait().
+	 *
+	 * However, remote timer enqueue is not such a frequent event
+	 * and testing of the above solutions didn't appear to report
+	 * much benefits.
+	 */
 	if (set_nr_and_not_polling(rq->idle))
 		smp_send_reschedule(cpu);
 	else
@@ -2124,12 +2147,14 @@ void activate_task(struct rq *rq, struct task_struct *p, int flags)
 
 	enqueue_task(rq, p, flags);
 
-	p->on_rq = TASK_ON_RQ_QUEUED;
+	WRITE_ONCE(p->on_rq, TASK_ON_RQ_QUEUED);
+	ASSERT_EXCLUSIVE_WRITER(p->on_rq);
 }
 
 void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 {
-	p->on_rq = (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING;
+	WRITE_ONCE(p->on_rq, (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING);
+	ASSERT_EXCLUSIVE_WRITER(p->on_rq);
 
 	dequeue_task(rq, p, flags);
 }
@@ -3795,6 +3820,8 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 		rq->idle_stamp = 0;
 	}
 #endif
+
+	p->dl_server = NULL;
 }
 
 /*
@@ -4509,10 +4536,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	memset(&p->stats, 0, sizeof(p->stats));
 #endif
 
-	RB_CLEAR_NODE(&p->dl.rb_node);
-	init_dl_task_timer(&p->dl);
-	init_dl_inactive_task_timer(&p->dl);
-	__dl_clear_params(p);
+	init_dl_entity(&p->dl);
 
 	INIT_LIST_HEAD(&p->rt.run_list);
 	p->rt.timeout		= 0;
@@ -6004,12 +6028,27 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 			p = pick_next_task_idle(rq);
 		}
 
+		/*
+		 * This is the fast path; it cannot be a DL server pick;
+		 * therefore even if @p == @prev, ->dl_server must be NULL.
+		 */
+		if (p->dl_server)
+			p->dl_server = NULL;
+
 		return p;
 	}
 
 restart:
 	put_prev_task_balance(rq, prev, rf);
 
+	/*
+	 * We've updated @prev and no longer need the server link, clear it.
+	 * Must be done before ->pick_next_task() because that can (re)set
+	 * ->dl_server.
+	 */
+	if (prev->dl_server)
+		prev->dl_server = NULL;
+
 	for_each_class(class) {
 		p = class->pick_next_task(rq);
 		if (p)
@@ -7429,18 +7468,13 @@ int sched_core_idle_cpu(int cpu)
  * required to meet deadlines.
  */
 unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
-				 enum cpu_util_type type,
-				 struct task_struct *p)
+				 unsigned long *min,
+				 unsigned long *max)
 {
-	unsigned long dl_util, util, irq, max;
+	unsigned long util, irq, scale;
 	struct rq *rq = cpu_rq(cpu);
 
-	max = arch_scale_cpu_capacity(cpu);
-
-	if (!uclamp_is_used() &&
-	    type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) {
-		return max;
-	}
+	scale = arch_scale_cpu_capacity(cpu);
 
 	/*
 	 * Early check to see if IRQ/steal time saturates the CPU, can be
@@ -7448,45 +7482,49 @@ unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
 	 * update_irq_load_avg().
 	 */
 	irq = cpu_util_irq(rq);
-	if (unlikely(irq >= max))
-		return max;
+	if (unlikely(irq >= scale)) {
+		if (min)
+			*min = scale;
+		if (max)
+			*max = scale;
+		return scale;
+	}
+
+	if (min) {
+		/*
+		 * The minimum utilization returns the highest level between:
+		 * - the computed DL bandwidth needed with the IRQ pressure which
+		 *   steals time to the deadline task.
+		 * - The minimum performance requirement for CFS and/or RT.
+		 */
+		*min = max(irq + cpu_bw_dl(rq), uclamp_rq_get(rq, UCLAMP_MIN));
+
+		/*
+		 * When an RT task is runnable and uclamp is not used, we must
+		 * ensure that the task will run at maximum compute capacity.
+		 */
+		if (!uclamp_is_used() && rt_rq_is_runnable(&rq->rt))
+			*min = max(*min, scale);
+	}
 
 	/*
 	 * Because the time spend on RT/DL tasks is visible as 'lost' time to
 	 * CFS tasks and we use the same metric to track the effective
 	 * utilization (PELT windows are synchronized) we can directly add them
 	 * to obtain the CPU's actual utilization.
-	 *
-	 * CFS and RT utilization can be boosted or capped, depending on
-	 * utilization clamp constraints requested by currently RUNNABLE
-	 * tasks.
-	 * When there are no CFS RUNNABLE tasks, clamps are released and
-	 * frequency will be gracefully reduced with the utilization decay.
 	 */
 	util = util_cfs + cpu_util_rt(rq);
-	if (type == FREQUENCY_UTIL)
-		util = uclamp_rq_util_with(rq, util, p);
-
-	dl_util = cpu_util_dl(rq);
+	util += cpu_util_dl(rq);
 
 	/*
-	 * For frequency selection we do not make cpu_util_dl() a permanent part
-	 * of this sum because we want to use cpu_bw_dl() later on, but we need
-	 * to check if the CFS+RT+DL sum is saturated (ie. no idle time) such
-	 * that we select f_max when there is no idle time.
-	 *
-	 * NOTE: numerical errors or stop class might cause us to not quite hit
-	 * saturation when we should -- something for later.
+	 * The maximum hint is a soft bandwidth requirement, which can be lower
+	 * than the actual utilization because of uclamp_max requirements.
 	 */
-	if (util + dl_util >= max)
-		return max;
+	if (max)
+		*max = min(scale, uclamp_rq_get(rq, UCLAMP_MAX));
 
-	/*
-	 * OTOH, for energy computation we need the estimated running time, so
-	 * include util_dl and ignore dl_bw.
-	 */
-	if (type == ENERGY_UTIL)
-		util += dl_util;
+	if (util >= scale)
+		return scale;
 
 	/*
 	 * There is still idle time; further improve the number by using the
@@ -7497,28 +7535,15 @@ unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
 	 *   U' = irq + --------- * U
 	 *                 max
 	 */
-	util = scale_irq_capacity(util, irq, max);
+	util = scale_irq_capacity(util, irq, scale);
 	util += irq;
 
-	/*
-	 * Bandwidth required by DEADLINE must always be granted while, for
-	 * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism
-	 * to gracefully reduce the frequency when no tasks show up for longer
-	 * periods of time.
-	 *
-	 * Ideally we would like to set bw_dl as min/guaranteed freq and util +
-	 * bw_dl as requested freq. However, cpufreq is not yet ready for such
-	 * an interface. So, we only do the latter for now.
-	 */
-	if (type == FREQUENCY_UTIL)
-		util += cpu_bw_dl(rq);
-
-	return min(max, util);
+	return min(scale, util);
 }
 
 unsigned long sched_cpu_util(int cpu)
 {
-	return effective_cpu_util(cpu, cpu_util_cfs(cpu), ENERGY_UTIL, NULL);
+	return effective_cpu_util(cpu, cpu_util_cfs(cpu), NULL, NULL);
 }
 #endif /* CONFIG_SMP */
 
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 5888176354e2..95c3c097083e 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -47,7 +47,7 @@ struct sugov_cpu {
 	u64			last_update;
 
 	unsigned long		util;
-	unsigned long		bw_dl;
+	unsigned long		bw_min;
 
 	/* The field below is for single-CPU policies only: */
 #ifdef CONFIG_NO_HZ_COMMON
@@ -115,6 +115,28 @@ static void sugov_deferred_update(struct sugov_policy *sg_policy)
 }
 
 /**
+ * get_capacity_ref_freq - get the reference frequency that has been used to
+ * correlate frequency and compute capacity for a given cpufreq policy. We use
+ * the CPU managing it for the arch_scale_freq_ref() call in the function.
+ * @policy: the cpufreq policy of the CPU in question.
+ *
+ * Return: the reference CPU frequency to compute a capacity.
+ */
+static __always_inline
+unsigned long get_capacity_ref_freq(struct cpufreq_policy *policy)
+{
+	unsigned int freq = arch_scale_freq_ref(policy->cpu);
+
+	if (freq)
+		return freq;
+
+	if (arch_scale_freq_invariant())
+		return policy->cpuinfo.max_freq;
+
+	return policy->cur;
+}
+
+/**
  * get_next_freq - Compute a new frequency for a given cpufreq policy.
  * @sg_policy: schedutil policy object to compute the new frequency for.
  * @util: Current CPU utilization.
@@ -140,10 +162,9 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
 				  unsigned long util, unsigned long max)
 {
 	struct cpufreq_policy *policy = sg_policy->policy;
-	unsigned int freq = arch_scale_freq_invariant() ?
-				policy->cpuinfo.max_freq : policy->cur;
+	unsigned int freq;
 
-	util = map_util_perf(util);
+	freq = get_capacity_ref_freq(policy);
 	freq = map_util_freq(util, freq, max);
 
 	if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)
@@ -153,14 +174,31 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
 	return cpufreq_driver_resolve_freq(policy, freq);
 }
 
-static void sugov_get_util(struct sugov_cpu *sg_cpu)
+unsigned long sugov_effective_cpu_perf(int cpu, unsigned long actual,
+				 unsigned long min,
+				 unsigned long max)
+{
+	/* Add dvfs headroom to actual utilization */
+	actual = map_util_perf(actual);
+	/* Actually we don't need to target the max performance */
+	if (actual < max)
+		max = actual;
+
+	/*
+	 * Ensure at least minimum performance while providing more compute
+	 * capacity when possible.
+	 */
+	return max(min, max);
+}
+
+static void sugov_get_util(struct sugov_cpu *sg_cpu, unsigned long boost)
 {
-	unsigned long util = cpu_util_cfs_boost(sg_cpu->cpu);
-	struct rq *rq = cpu_rq(sg_cpu->cpu);
+	unsigned long min, max, util = cpu_util_cfs_boost(sg_cpu->cpu);
 
-	sg_cpu->bw_dl = cpu_bw_dl(rq);
-	sg_cpu->util = effective_cpu_util(sg_cpu->cpu, util,
-					  FREQUENCY_UTIL, NULL);
+	util = effective_cpu_util(sg_cpu->cpu, util, &min, &max);
+	util = max(util, boost);
+	sg_cpu->bw_min = min;
+	sg_cpu->util = sugov_effective_cpu_perf(sg_cpu->cpu, util, min, max);
 }
 
 /**
@@ -251,18 +289,16 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
  * This mechanism is designed to boost high frequently IO waiting tasks, while
  * being more conservative on tasks which does sporadic IO operations.
  */
-static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
+static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
 			       unsigned long max_cap)
 {
-	unsigned long boost;
-
 	/* No boost currently required */
 	if (!sg_cpu->iowait_boost)
-		return;
+		return 0;
 
 	/* Reset boost if the CPU appears to have been idle enough */
 	if (sugov_iowait_reset(sg_cpu, time, false))
-		return;
+		return 0;
 
 	if (!sg_cpu->iowait_boost_pending) {
 		/*
@@ -271,7 +307,7 @@ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
 		sg_cpu->iowait_boost >>= 1;
 		if (sg_cpu->iowait_boost < IOWAIT_BOOST_MIN) {
 			sg_cpu->iowait_boost = 0;
-			return;
+			return 0;
 		}
 	}
 
@@ -281,10 +317,7 @@ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
 	 * sg_cpu->util is already in capacity scale; convert iowait_boost
 	 * into the same scale so we can compare.
 	 */
-	boost = (sg_cpu->iowait_boost * max_cap) >> SCHED_CAPACITY_SHIFT;
-	boost = uclamp_rq_util_with(cpu_rq(sg_cpu->cpu), boost, NULL);
-	if (sg_cpu->util < boost)
-		sg_cpu->util = boost;
+	return (sg_cpu->iowait_boost * max_cap) >> SCHED_CAPACITY_SHIFT;
 }
 
 #ifdef CONFIG_NO_HZ_COMMON
@@ -306,7 +339,7 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
  */
 static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu)
 {
-	if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl)
+	if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_min)
 		sg_cpu->sg_policy->limits_changed = true;
 }
 
@@ -314,6 +347,8 @@ static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
 					      u64 time, unsigned long max_cap,
 					      unsigned int flags)
 {
+	unsigned long boost;
+
 	sugov_iowait_boost(sg_cpu, time, flags);
 	sg_cpu->last_update = time;
 
@@ -322,8 +357,8 @@ static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
 	if (!sugov_should_update_freq(sg_cpu->sg_policy, time))
 		return false;
 
-	sugov_get_util(sg_cpu);
-	sugov_iowait_apply(sg_cpu, time, max_cap);
+	boost = sugov_iowait_apply(sg_cpu, time, max_cap);
+	sugov_get_util(sg_cpu, boost);
 
 	return true;
 }
@@ -407,8 +442,8 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
 	    sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
 		sg_cpu->util = prev_util;
 
-	cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
-				   map_util_perf(sg_cpu->util), max_cap);
+	cpufreq_driver_adjust_perf(sg_cpu->cpu, sg_cpu->bw_min,
+				   sg_cpu->util, max_cap);
 
 	sg_cpu->sg_policy->last_freq_update_time = time;
 }
@@ -424,9 +459,10 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
 
 	for_each_cpu(j, policy->cpus) {
 		struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
+		unsigned long boost;
 
-		sugov_get_util(j_sg_cpu);
-		sugov_iowait_apply(j_sg_cpu, time, max_cap);
+		boost = sugov_iowait_apply(j_sg_cpu, time, max_cap);
+		sugov_get_util(j_sg_cpu, boost);
 
 		util = max(j_sg_cpu->util, util);
 	}
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index b28114478b82..a04a436af8cc 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -54,8 +54,14 @@ static int __init sched_dl_sysctl_init(void)
 late_initcall(sched_dl_sysctl_init);
 #endif
 
+static bool dl_server(struct sched_dl_entity *dl_se)
+{
+	return dl_se->dl_server;
+}
+
 static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
 {
+	BUG_ON(dl_server(dl_se));
 	return container_of(dl_se, struct task_struct, dl);
 }
 
@@ -64,12 +70,19 @@ static inline struct rq *rq_of_dl_rq(struct dl_rq *dl_rq)
 	return container_of(dl_rq, struct rq, dl);
 }
 
-static inline struct dl_rq *dl_rq_of_se(struct sched_dl_entity *dl_se)
+static inline struct rq *rq_of_dl_se(struct sched_dl_entity *dl_se)
 {
-	struct task_struct *p = dl_task_of(dl_se);
-	struct rq *rq = task_rq(p);
+	struct rq *rq = dl_se->rq;
+
+	if (!dl_server(dl_se))
+		rq = task_rq(dl_task_of(dl_se));
+
+	return rq;
+}
 
-	return &rq->dl;
+static inline struct dl_rq *dl_rq_of_se(struct sched_dl_entity *dl_se)
+{
+	return &rq_of_dl_se(dl_se)->dl;
 }
 
 static inline int on_dl_rq(struct sched_dl_entity *dl_se)
@@ -335,6 +348,8 @@ static void dl_change_utilization(struct task_struct *p, u64 new_bw)
 	__add_rq_bw(new_bw, &rq->dl);
 }
 
+static void __dl_clear_params(struct sched_dl_entity *dl_se);
+
 /*
  * The utilization of a task cannot be immediately removed from
  * the rq active utilization (running_bw) when the task blocks.
@@ -389,12 +404,11 @@ static void dl_change_utilization(struct task_struct *p, u64 new_bw)
  * up, and checks if the task is still in the "ACTIVE non contending"
  * state or not (in the second case, it updates running_bw).
  */
-static void task_non_contending(struct task_struct *p)
+static void task_non_contending(struct sched_dl_entity *dl_se)
 {
-	struct sched_dl_entity *dl_se = &p->dl;
 	struct hrtimer *timer = &dl_se->inactive_timer;
-	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
-	struct rq *rq = rq_of_dl_rq(dl_rq);
+	struct rq *rq = rq_of_dl_se(dl_se);
+	struct dl_rq *dl_rq = &rq->dl;
 	s64 zerolag_time;
 
 	/*
@@ -424,24 +438,33 @@ static void task_non_contending(struct task_struct *p)
 	 * utilization now, instead of starting a timer
 	 */
 	if ((zerolag_time < 0) || hrtimer_active(&dl_se->inactive_timer)) {
-		if (dl_task(p))
+		if (dl_server(dl_se)) {
 			sub_running_bw(dl_se, dl_rq);
-		if (!dl_task(p) || READ_ONCE(p->__state) == TASK_DEAD) {
-			struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
-
-			if (READ_ONCE(p->__state) == TASK_DEAD)
-				sub_rq_bw(&p->dl, &rq->dl);
-			raw_spin_lock(&dl_b->lock);
-			__dl_sub(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
-			raw_spin_unlock(&dl_b->lock);
-			__dl_clear_params(p);
+		} else {
+			struct task_struct *p = dl_task_of(dl_se);
+
+			if (dl_task(p))
+				sub_running_bw(dl_se, dl_rq);
+
+			if (!dl_task(p) || READ_ONCE(p->__state) == TASK_DEAD) {
+				struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+
+				if (READ_ONCE(p->__state) == TASK_DEAD)
+					sub_rq_bw(dl_se, &rq->dl);
+				raw_spin_lock(&dl_b->lock);
+				__dl_sub(dl_b, dl_se->dl_bw, dl_bw_cpus(task_cpu(p)));
+				raw_spin_unlock(&dl_b->lock);
+				__dl_clear_params(dl_se);
+			}
 		}
 
 		return;
 	}
 
 	dl_se->dl_non_contending = 1;
-	get_task_struct(p);
+	if (!dl_server(dl_se))
+		get_task_struct(dl_task_of(dl_se));
+
 	hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL_HARD);
 }
 
@@ -468,8 +491,10 @@ static void task_contending(struct sched_dl_entity *dl_se, int flags)
 		 * will not touch the rq's active utilization,
 		 * so we are still safe.
 		 */
-		if (hrtimer_try_to_cancel(&dl_se->inactive_timer) == 1)
-			put_task_struct(dl_task_of(dl_se));
+		if (hrtimer_try_to_cancel(&dl_se->inactive_timer) == 1) {
+			if (!dl_server(dl_se))
+				put_task_struct(dl_task_of(dl_se));
+		}
 	} else {
 		/*
 		 * Since "dl_non_contending" is not set, the
@@ -482,10 +507,8 @@ static void task_contending(struct sched_dl_entity *dl_se, int flags)
 	}
 }
 
-static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
+static inline int is_leftmost(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
-	struct sched_dl_entity *dl_se = &p->dl;
-
 	return rb_first_cached(&dl_rq->root) == &dl_se->rb_node;
 }
 
@@ -737,8 +760,10 @@ static inline void deadline_queue_pull_task(struct rq *rq)
 }
 #endif /* CONFIG_SMP */
 
+static void
+enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags);
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags);
-static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags);
+static void dequeue_dl_entity(struct sched_dl_entity *dl_se, int flags);
 static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p, int flags);
 
 static inline void replenish_dl_new_period(struct sched_dl_entity *dl_se,
@@ -986,8 +1011,7 @@ static inline bool dl_is_implicit(struct sched_dl_entity *dl_se)
  */
 static void update_dl_entity(struct sched_dl_entity *dl_se)
 {
-	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
-	struct rq *rq = rq_of_dl_rq(dl_rq);
+	struct rq *rq = rq_of_dl_se(dl_se);
 
 	if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
 	    dl_entity_overflow(dl_se, rq_clock(rq))) {
@@ -1018,11 +1042,11 @@ static inline u64 dl_next_period(struct sched_dl_entity *dl_se)
  * actually started or not (i.e., the replenishment instant is in
  * the future or in the past).
  */
-static int start_dl_timer(struct task_struct *p)
+static int start_dl_timer(struct sched_dl_entity *dl_se)
 {
-	struct sched_dl_entity *dl_se = &p->dl;
 	struct hrtimer *timer = &dl_se->dl_timer;
-	struct rq *rq = task_rq(p);
+	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+	struct rq *rq = rq_of_dl_rq(dl_rq);
 	ktime_t now, act;
 	s64 delta;
 
@@ -1056,13 +1080,33 @@ static int start_dl_timer(struct task_struct *p)
 	 * and observe our state.
 	 */
 	if (!hrtimer_is_queued(timer)) {
-		get_task_struct(p);
+		if (!dl_server(dl_se))
+			get_task_struct(dl_task_of(dl_se));
 		hrtimer_start(timer, act, HRTIMER_MODE_ABS_HARD);
 	}
 
 	return 1;
 }
 
+static void __push_dl_task(struct rq *rq, struct rq_flags *rf)
+{
+#ifdef CONFIG_SMP
+	/*
+	 * Queueing this task back might have overloaded rq, check if we need
+	 * to kick someone away.
+	 */
+	if (has_pushable_dl_tasks(rq)) {
+		/*
+		 * Nothing relies on rq->lock after this, so its safe to drop
+		 * rq->lock.
+		 */
+		rq_unpin_lock(rq, rf);
+		push_dl_task(rq);
+		rq_repin_lock(rq, rf);
+	}
+#endif
+}
+
 /*
  * This is the bandwidth enforcement timer callback. If here, we know
  * a task is not on its dl_rq, since the fact that the timer was running
@@ -1081,10 +1125,34 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	struct sched_dl_entity *dl_se = container_of(timer,
 						     struct sched_dl_entity,
 						     dl_timer);
-	struct task_struct *p = dl_task_of(dl_se);
+	struct task_struct *p;
 	struct rq_flags rf;
 	struct rq *rq;
 
+	if (dl_server(dl_se)) {
+		struct rq *rq = rq_of_dl_se(dl_se);
+		struct rq_flags rf;
+
+		rq_lock(rq, &rf);
+		if (dl_se->dl_throttled) {
+			sched_clock_tick();
+			update_rq_clock(rq);
+
+			if (dl_se->server_has_tasks(dl_se)) {
+				enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH);
+				resched_curr(rq);
+				__push_dl_task(rq, &rf);
+			} else {
+				replenish_dl_entity(dl_se);
+			}
+
+		}
+		rq_unlock(rq, &rf);
+
+		return HRTIMER_NORESTART;
+	}
+
+	p = dl_task_of(dl_se);
 	rq = task_rq_lock(p, &rf);
 
 	/*
@@ -1155,21 +1223,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	else
 		resched_curr(rq);
 
-#ifdef CONFIG_SMP
-	/*
-	 * Queueing this task back might have overloaded rq, check if we need
-	 * to kick someone away.
-	 */
-	if (has_pushable_dl_tasks(rq)) {
-		/*
-		 * Nothing relies on rq->lock after this, so its safe to drop
-		 * rq->lock.
-		 */
-		rq_unpin_lock(rq, &rf);
-		push_dl_task(rq);
-		rq_repin_lock(rq, &rf);
-	}
-#endif
+	__push_dl_task(rq, &rf);
 
 unlock:
 	task_rq_unlock(rq, p, &rf);
@@ -1183,7 +1237,7 @@ unlock:
 	return HRTIMER_NORESTART;
 }
 
-void init_dl_task_timer(struct sched_dl_entity *dl_se)
+static void init_dl_task_timer(struct sched_dl_entity *dl_se)
 {
 	struct hrtimer *timer = &dl_se->dl_timer;
 
@@ -1211,12 +1265,11 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
  */
 static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se)
 {
-	struct task_struct *p = dl_task_of(dl_se);
-	struct rq *rq = rq_of_dl_rq(dl_rq_of_se(dl_se));
+	struct rq *rq = rq_of_dl_se(dl_se);
 
 	if (dl_time_before(dl_se->deadline, rq_clock(rq)) &&
 	    dl_time_before(rq_clock(rq), dl_next_period(dl_se))) {
-		if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(p)))
+		if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(dl_se)))
 			return;
 		dl_se->dl_throttled = 1;
 		if (dl_se->runtime > 0)
@@ -1267,44 +1320,19 @@ static u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se)
 	return (delta * u_act) >> BW_SHIFT;
 }
 
-/*
- * Update the current task's runtime statistics (provided it is still
- * a -deadline task and has not been removed from the dl_rq).
- */
-static void update_curr_dl(struct rq *rq)
+static inline void
+update_stats_dequeue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se,
+                        int flags);
+static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec)
 {
-	struct task_struct *curr = rq->curr;
-	struct sched_dl_entity *dl_se = &curr->dl;
-	u64 delta_exec, scaled_delta_exec;
-	int cpu = cpu_of(rq);
-	u64 now;
-
-	if (!dl_task(curr) || !on_dl_rq(dl_se))
-		return;
+	s64 scaled_delta_exec;
 
-	/*
-	 * Consumed budget is computed considering the time as
-	 * observed by schedulable tasks (excluding time spent
-	 * in hardirq context, etc.). Deadlines are instead
-	 * computed using hard walltime. This seems to be the more
-	 * natural solution, but the full ramifications of this
-	 * approach need further study.
-	 */
-	now = rq_clock_task(rq);
-	delta_exec = now - curr->se.exec_start;
-	if (unlikely((s64)delta_exec <= 0)) {
+	if (unlikely(delta_exec <= 0)) {
 		if (unlikely(dl_se->dl_yielded))
 			goto throttle;
 		return;
 	}
 
-	schedstat_set(curr->stats.exec_max,
-		      max(curr->stats.exec_max, delta_exec));
-
-	trace_sched_stat_runtime(curr, delta_exec, 0);
-
-	update_current_exec_runtime(curr, now, delta_exec);
-
 	if (dl_entity_is_special(dl_se))
 		return;
 
@@ -1316,10 +1344,9 @@ static void update_curr_dl(struct rq *rq)
 	 * according to current frequency and CPU maximum capacity.
 	 */
 	if (unlikely(dl_se->flags & SCHED_FLAG_RECLAIM)) {
-		scaled_delta_exec = grub_reclaim(delta_exec,
-						 rq,
-						 &curr->dl);
+		scaled_delta_exec = grub_reclaim(delta_exec, rq, dl_se);
 	} else {
+		int cpu = cpu_of(rq);
 		unsigned long scale_freq = arch_scale_freq_capacity(cpu);
 		unsigned long scale_cpu = arch_scale_cpu_capacity(cpu);
 
@@ -1338,11 +1365,20 @@ throttle:
 		    (dl_se->flags & SCHED_FLAG_DL_OVERRUN))
 			dl_se->dl_overrun = 1;
 
-		__dequeue_task_dl(rq, curr, 0);
-		if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(curr)))
-			enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);
+		dequeue_dl_entity(dl_se, 0);
+		if (!dl_server(dl_se)) {
+			update_stats_dequeue_dl(&rq->dl, dl_se, 0);
+			dequeue_pushable_dl_task(rq, dl_task_of(dl_se));
+		}
+
+		if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(dl_se))) {
+			if (dl_server(dl_se))
+				enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH);
+			else
+				enqueue_task_dl(rq, dl_task_of(dl_se), ENQUEUE_REPLENISH);
+		}
 
-		if (!is_leftmost(curr, &rq->dl))
+		if (!is_leftmost(dl_se, &rq->dl))
 			resched_curr(rq);
 	}
 
@@ -1372,20 +1408,82 @@ throttle:
 	}
 }
 
+void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec)
+{
+	update_curr_dl_se(dl_se->rq, dl_se, delta_exec);
+}
+
+void dl_server_start(struct sched_dl_entity *dl_se)
+{
+	if (!dl_server(dl_se)) {
+		dl_se->dl_server = 1;
+		setup_new_dl_entity(dl_se);
+	}
+	enqueue_dl_entity(dl_se, ENQUEUE_WAKEUP);
+}
+
+void dl_server_stop(struct sched_dl_entity *dl_se)
+{
+	dequeue_dl_entity(dl_se, DEQUEUE_SLEEP);
+}
+
+void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
+		    dl_server_has_tasks_f has_tasks,
+		    dl_server_pick_f pick)
+{
+	dl_se->rq = rq;
+	dl_se->server_has_tasks = has_tasks;
+	dl_se->server_pick = pick;
+}
+
+/*
+ * Update the current task's runtime statistics (provided it is still
+ * a -deadline task and has not been removed from the dl_rq).
+ */
+static void update_curr_dl(struct rq *rq)
+{
+	struct task_struct *curr = rq->curr;
+	struct sched_dl_entity *dl_se = &curr->dl;
+	s64 delta_exec;
+
+	if (!dl_task(curr) || !on_dl_rq(dl_se))
+		return;
+
+	/*
+	 * Consumed budget is computed considering the time as
+	 * observed by schedulable tasks (excluding time spent
+	 * in hardirq context, etc.). Deadlines are instead
+	 * computed using hard walltime. This seems to be the more
+	 * natural solution, but the full ramifications of this
+	 * approach need further study.
+	 */
+	delta_exec = update_curr_common(rq);
+	update_curr_dl_se(rq, dl_se, delta_exec);
+}
+
 static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
 {
 	struct sched_dl_entity *dl_se = container_of(timer,
 						     struct sched_dl_entity,
 						     inactive_timer);
-	struct task_struct *p = dl_task_of(dl_se);
+	struct task_struct *p = NULL;
 	struct rq_flags rf;
 	struct rq *rq;
 
-	rq = task_rq_lock(p, &rf);
+	if (!dl_server(dl_se)) {
+		p = dl_task_of(dl_se);
+		rq = task_rq_lock(p, &rf);
+	} else {
+		rq = dl_se->rq;
+		rq_lock(rq, &rf);
+	}
 
 	sched_clock_tick();
 	update_rq_clock(rq);
 
+	if (dl_server(dl_se))
+		goto no_task;
+
 	if (!dl_task(p) || READ_ONCE(p->__state) == TASK_DEAD) {
 		struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
 
@@ -1398,23 +1496,30 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
 		raw_spin_lock(&dl_b->lock);
 		__dl_sub(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
 		raw_spin_unlock(&dl_b->lock);
-		__dl_clear_params(p);
+		__dl_clear_params(dl_se);
 
 		goto unlock;
 	}
+
+no_task:
 	if (dl_se->dl_non_contending == 0)
 		goto unlock;
 
 	sub_running_bw(dl_se, &rq->dl);
 	dl_se->dl_non_contending = 0;
 unlock:
-	task_rq_unlock(rq, p, &rf);
-	put_task_struct(p);
+
+	if (!dl_server(dl_se)) {
+		task_rq_unlock(rq, p, &rf);
+		put_task_struct(p);
+	} else {
+		rq_unlock(rq, &rf);
+	}
 
 	return HRTIMER_NORESTART;
 }
 
-void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se)
+static void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se)
 {
 	struct hrtimer *timer = &dl_se->inactive_timer;
 
@@ -1472,10 +1577,8 @@ static inline void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {}
 static inline
 void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
-	int prio = dl_task_of(dl_se)->prio;
 	u64 deadline = dl_se->deadline;
 
-	WARN_ON(!dl_prio(prio));
 	dl_rq->dl_nr_running++;
 	add_nr_running(rq_of_dl_rq(dl_rq), 1);
 
@@ -1485,9 +1588,6 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 static inline
 void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
-	int prio = dl_task_of(dl_se)->prio;
-
-	WARN_ON(!dl_prio(prio));
 	WARN_ON(!dl_rq->dl_nr_running);
 	dl_rq->dl_nr_running--;
 	sub_nr_running(rq_of_dl_rq(dl_rq), 1);
@@ -1609,6 +1709,41 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
 	update_stats_enqueue_dl(dl_rq_of_se(dl_se), dl_se, flags);
 
 	/*
+	 * Check if a constrained deadline task was activated
+	 * after the deadline but before the next period.
+	 * If that is the case, the task will be throttled and
+	 * the replenishment timer will be set to the next period.
+	 */
+	if (!dl_se->dl_throttled && !dl_is_implicit(dl_se))
+		dl_check_constrained_dl(dl_se);
+
+	if (flags & (ENQUEUE_RESTORE|ENQUEUE_MIGRATING)) {
+		struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+
+		add_rq_bw(dl_se, dl_rq);
+		add_running_bw(dl_se, dl_rq);
+	}
+
+	/*
+	 * If p is throttled, we do not enqueue it. In fact, if it exhausted
+	 * its budget it needs a replenishment and, since it now is on
+	 * its rq, the bandwidth timer callback (which clearly has not
+	 * run yet) will take care of this.
+	 * However, the active utilization does not depend on the fact
+	 * that the task is on the runqueue or not (but depends on the
+	 * task's state - in GRUB parlance, "inactive" vs "active contending").
+	 * In other words, even if a task is throttled its utilization must
+	 * be counted in the active utilization; hence, we need to call
+	 * add_running_bw().
+	 */
+	if (dl_se->dl_throttled && !(flags & ENQUEUE_REPLENISH)) {
+		if (flags & ENQUEUE_WAKEUP)
+			task_contending(dl_se, flags);
+
+		return;
+	}
+
+	/*
 	 * If this is a wakeup or a new instance, the scheduling
 	 * parameters of the task might need updating. Otherwise,
 	 * we want a replenishment of its runtime.
@@ -1619,17 +1754,35 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
 	} else if (flags & ENQUEUE_REPLENISH) {
 		replenish_dl_entity(dl_se);
 	} else if ((flags & ENQUEUE_RESTORE) &&
-		  dl_time_before(dl_se->deadline,
-				 rq_clock(rq_of_dl_rq(dl_rq_of_se(dl_se))))) {
+		   dl_time_before(dl_se->deadline, rq_clock(rq_of_dl_se(dl_se)))) {
 		setup_new_dl_entity(dl_se);
 	}
 
 	__enqueue_dl_entity(dl_se);
 }
 
-static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
+static void dequeue_dl_entity(struct sched_dl_entity *dl_se, int flags)
 {
 	__dequeue_dl_entity(dl_se);
+
+	if (flags & (DEQUEUE_SAVE|DEQUEUE_MIGRATING)) {
+		struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+
+		sub_running_bw(dl_se, dl_rq);
+		sub_rq_bw(dl_se, dl_rq);
+	}
+
+	/*
+	 * This check allows to start the inactive timer (or to immediately
+	 * decrease the active utilization, if needed) in two cases:
+	 * when the task blocks and when it is terminating
+	 * (p->state == TASK_DEAD). We can handle the two cases in the same
+	 * way, because from GRUB's point of view the same thing is happening
+	 * (the task moves from "active contending" to "active non contending"
+	 * or "inactive")
+	 */
+	if (flags & DEQUEUE_SLEEP)
+		task_non_contending(dl_se);
 }
 
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
@@ -1674,76 +1827,31 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 		return;
 	}
 
-	/*
-	 * Check if a constrained deadline task was activated
-	 * after the deadline but before the next period.
-	 * If that is the case, the task will be throttled and
-	 * the replenishment timer will be set to the next period.
-	 */
-	if (!p->dl.dl_throttled && !dl_is_implicit(&p->dl))
-		dl_check_constrained_dl(&p->dl);
-
-	if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & ENQUEUE_RESTORE) {
-		add_rq_bw(&p->dl, &rq->dl);
-		add_running_bw(&p->dl, &rq->dl);
-	}
-
-	/*
-	 * If p is throttled, we do not enqueue it. In fact, if it exhausted
-	 * its budget it needs a replenishment and, since it now is on
-	 * its rq, the bandwidth timer callback (which clearly has not
-	 * run yet) will take care of this.
-	 * However, the active utilization does not depend on the fact
-	 * that the task is on the runqueue or not (but depends on the
-	 * task's state - in GRUB parlance, "inactive" vs "active contending").
-	 * In other words, even if a task is throttled its utilization must
-	 * be counted in the active utilization; hence, we need to call
-	 * add_running_bw().
-	 */
-	if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH)) {
-		if (flags & ENQUEUE_WAKEUP)
-			task_contending(&p->dl, flags);
-
-		return;
-	}
-
 	check_schedstat_required();
 	update_stats_wait_start_dl(dl_rq_of_se(&p->dl), &p->dl);
 
+	if (p->on_rq == TASK_ON_RQ_MIGRATING)
+		flags |= ENQUEUE_MIGRATING;
+
 	enqueue_dl_entity(&p->dl, flags);
 
-	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
-		enqueue_pushable_dl_task(rq, p);
-}
+	if (dl_server(&p->dl))
+		return;
 
-static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
-{
-	update_stats_dequeue_dl(&rq->dl, &p->dl, flags);
-	dequeue_dl_entity(&p->dl);
-	dequeue_pushable_dl_task(rq, p);
+	if (!task_current(rq, p) && !p->dl.dl_throttled && p->nr_cpus_allowed > 1)
+		enqueue_pushable_dl_task(rq, p);
 }
 
 static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
 	update_curr_dl(rq);
-	__dequeue_task_dl(rq, p, flags);
 
-	if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & DEQUEUE_SAVE) {
-		sub_running_bw(&p->dl, &rq->dl);
-		sub_rq_bw(&p->dl, &rq->dl);
-	}
+	if (p->on_rq == TASK_ON_RQ_MIGRATING)
+		flags |= DEQUEUE_MIGRATING;
 
-	/*
-	 * This check allows to start the inactive timer (or to immediately
-	 * decrease the active utilization, if needed) in two cases:
-	 * when the task blocks and when it is terminating
-	 * (p->state == TASK_DEAD). We can handle the two cases in the same
-	 * way, because from GRUB's point of view the same thing is happening
-	 * (the task moves from "active contending" to "active non contending"
-	 * or "inactive")
-	 */
-	if (flags & DEQUEUE_SLEEP)
-		task_non_contending(p);
+	dequeue_dl_entity(&p->dl, flags);
+	if (!p->dl.dl_throttled && !dl_server(&p->dl))
+		dequeue_pushable_dl_task(rq, p);
 }
 
 /*
@@ -1933,12 +2041,12 @@ static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p,
 }
 
 #ifdef CONFIG_SCHED_HRTICK
-static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
+static void start_hrtick_dl(struct rq *rq, struct sched_dl_entity *dl_se)
 {
-	hrtick_start(rq, p->dl.runtime);
+	hrtick_start(rq, dl_se->runtime);
 }
 #else /* !CONFIG_SCHED_HRTICK */
-static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
+static void start_hrtick_dl(struct rq *rq, struct sched_dl_entity *dl_se)
 {
 }
 #endif
@@ -1958,9 +2066,6 @@ static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first)
 	if (!first)
 		return;
 
-	if (hrtick_enabled_dl(rq))
-		start_hrtick_dl(rq, p);
-
 	if (rq->curr->sched_class != &dl_sched_class)
 		update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0);
 
@@ -1983,12 +2088,25 @@ static struct task_struct *pick_task_dl(struct rq *rq)
 	struct dl_rq *dl_rq = &rq->dl;
 	struct task_struct *p;
 
+again:
 	if (!sched_dl_runnable(rq))
 		return NULL;
 
 	dl_se = pick_next_dl_entity(dl_rq);
 	WARN_ON_ONCE(!dl_se);
-	p = dl_task_of(dl_se);
+
+	if (dl_server(dl_se)) {
+		p = dl_se->server_pick(dl_se);
+		if (!p) {
+			WARN_ON_ONCE(1);
+			dl_se->dl_yielded = 1;
+			update_curr_dl_se(rq, dl_se, 0);
+			goto again;
+		}
+		p->dl_server = dl_se;
+	} else {
+		p = dl_task_of(dl_se);
+	}
 
 	return p;
 }
@@ -1998,9 +2116,15 @@ static struct task_struct *pick_next_task_dl(struct rq *rq)
 	struct task_struct *p;
 
 	p = pick_task_dl(rq);
-	if (p)
+	if (!p)
+		return p;
+
+	if (!p->dl_server)
 		set_next_task_dl(rq, p, true);
 
+	if (hrtick_enabled(rq))
+		start_hrtick_dl(rq, &p->dl);
+
 	return p;
 }
 
@@ -2038,8 +2162,8 @@ static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued)
 	 * be set and schedule() will start a new hrtick for the next task.
 	 */
 	if (hrtick_enabled_dl(rq) && queued && p->dl.runtime > 0 &&
-	    is_leftmost(p, &rq->dl))
-		start_hrtick_dl(rq, p);
+	    is_leftmost(&p->dl, &rq->dl))
+		start_hrtick_dl(rq, &p->dl);
 }
 
 static void task_fork_dl(struct task_struct *p)
@@ -2558,7 +2682,7 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
 	 * will reset the task parameters.
 	 */
 	if (task_on_rq_queued(p) && p->dl.dl_runtime)
-		task_non_contending(p);
+		task_non_contending(&p->dl);
 
 	/*
 	 * In case a task is setscheduled out from SCHED_DEADLINE we need to
@@ -2966,10 +3090,8 @@ bool __checkparam_dl(const struct sched_attr *attr)
 /*
  * This function clears the sched_dl_entity static params.
  */
-void __dl_clear_params(struct task_struct *p)
+static void __dl_clear_params(struct sched_dl_entity *dl_se)
 {
-	struct sched_dl_entity *dl_se = &p->dl;
-
 	dl_se->dl_runtime		= 0;
 	dl_se->dl_deadline		= 0;
 	dl_se->dl_period		= 0;
@@ -2981,12 +3103,21 @@ void __dl_clear_params(struct task_struct *p)
 	dl_se->dl_yielded		= 0;
 	dl_se->dl_non_contending	= 0;
 	dl_se->dl_overrun		= 0;
+	dl_se->dl_server		= 0;
 
 #ifdef CONFIG_RT_MUTEXES
 	dl_se->pi_se			= dl_se;
 #endif
 }
 
+void init_dl_entity(struct sched_dl_entity *dl_se)
+{
+	RB_CLEAR_NODE(&dl_se->rb_node);
+	init_dl_task_timer(dl_se);
+	init_dl_inactive_task_timer(dl_se);
+	__dl_clear_params(dl_se);
+}
+
 bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
 {
 	struct sched_dl_entity *dl_se = &p->dl;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 4580a450700e..8d5d98a5834d 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -628,8 +628,8 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
 
 void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 {
-	s64 left_vruntime = -1, min_vruntime, right_vruntime = -1, spread;
-	struct sched_entity *last, *first;
+	s64 left_vruntime = -1, min_vruntime, right_vruntime = -1, left_deadline = -1, spread;
+	struct sched_entity *last, *first, *root;
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long flags;
 
@@ -644,15 +644,20 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			SPLIT_NS(cfs_rq->exec_clock));
 
 	raw_spin_rq_lock_irqsave(rq, flags);
+	root = __pick_root_entity(cfs_rq);
+	if (root)
+		left_vruntime = root->min_vruntime;
 	first = __pick_first_entity(cfs_rq);
 	if (first)
-		left_vruntime = first->vruntime;
+		left_deadline = first->deadline;
 	last = __pick_last_entity(cfs_rq);
 	if (last)
 		right_vruntime = last->vruntime;
 	min_vruntime = cfs_rq->min_vruntime;
 	raw_spin_rq_unlock_irqrestore(rq, flags);
 
+	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "left_deadline",
+			SPLIT_NS(left_deadline));
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "left_vruntime",
 			SPLIT_NS(left_vruntime));
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "min_vruntime",
@@ -679,8 +684,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			cfs_rq->avg.runnable_avg);
 	SEQ_printf(m, "  .%-30s: %lu\n", "util_avg",
 			cfs_rq->avg.util_avg);
-	SEQ_printf(m, "  .%-30s: %u\n", "util_est_enqueued",
-			cfs_rq->avg.util_est.enqueued);
+	SEQ_printf(m, "  .%-30s: %u\n", "util_est",
+			cfs_rq->avg.util_est);
 	SEQ_printf(m, "  .%-30s: %ld\n", "removed.load_avg",
 			cfs_rq->removed.load_avg);
 	SEQ_printf(m, "  .%-30s: %ld\n", "removed.util_avg",
@@ -1070,8 +1075,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 	P(se.avg.runnable_avg);
 	P(se.avg.util_avg);
 	P(se.avg.last_update_time);
-	P(se.avg.util_est.ewma);
-	PM(se.avg.util_est.enqueued, ~UTIL_AVG_UNCHANGED);
+	PM(se.avg.util_est, ~UTIL_AVG_UNCHANGED);
 #endif
 #ifdef CONFIG_UCLAMP_TASK
 	__PS("uclamp.min", p->uclamp_req[UCLAMP_MIN].value);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2048138ce54b..533547e3c90a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -551,7 +551,11 @@ static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime)
 static inline bool entity_before(const struct sched_entity *a,
 				 const struct sched_entity *b)
 {
-	return (s64)(a->vruntime - b->vruntime) < 0;
+	/*
+	 * Tiebreak on vruntime seems unnecessary since it can
+	 * hardly happen.
+	 */
+	return (s64)(a->deadline - b->deadline) < 0;
 }
 
 static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -720,7 +724,7 @@ static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
  * Note: using 'avg_vruntime() > se->vruntime' is inacurate due
  *       to the loss in precision caused by the division.
  */
-int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static int vruntime_eligible(struct cfs_rq *cfs_rq, u64 vruntime)
 {
 	struct sched_entity *curr = cfs_rq->curr;
 	s64 avg = cfs_rq->avg_vruntime;
@@ -733,7 +737,12 @@ int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		load += weight;
 	}
 
-	return avg >= entity_key(cfs_rq, se) * load;
+	return avg >= (s64)(vruntime - cfs_rq->min_vruntime) * load;
+}
+
+int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	return vruntime_eligible(cfs_rq, se->vruntime);
 }
 
 static u64 __update_min_vruntime(struct cfs_rq *cfs_rq, u64 vruntime)
@@ -752,9 +761,8 @@ static u64 __update_min_vruntime(struct cfs_rq *cfs_rq, u64 vruntime)
 
 static void update_min_vruntime(struct cfs_rq *cfs_rq)
 {
-	struct sched_entity *se = __pick_first_entity(cfs_rq);
+	struct sched_entity *se = __pick_root_entity(cfs_rq);
 	struct sched_entity *curr = cfs_rq->curr;
-
 	u64 vruntime = cfs_rq->min_vruntime;
 
 	if (curr) {
@@ -766,9 +774,9 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
 
 	if (se) {
 		if (!curr)
-			vruntime = se->vruntime;
+			vruntime = se->min_vruntime;
 		else
-			vruntime = min_vruntime(vruntime, se->vruntime);
+			vruntime = min_vruntime(vruntime, se->min_vruntime);
 	}
 
 	/* ensure we never gain time by being placed backwards. */
@@ -781,34 +789,34 @@ static inline bool __entity_less(struct rb_node *a, const struct rb_node *b)
 	return entity_before(__node_2_se(a), __node_2_se(b));
 }
 
-#define deadline_gt(field, lse, rse) ({ (s64)((lse)->field - (rse)->field) > 0; })
+#define vruntime_gt(field, lse, rse) ({ (s64)((lse)->field - (rse)->field) > 0; })
 
-static inline void __update_min_deadline(struct sched_entity *se, struct rb_node *node)
+static inline void __min_vruntime_update(struct sched_entity *se, struct rb_node *node)
 {
 	if (node) {
 		struct sched_entity *rse = __node_2_se(node);
-		if (deadline_gt(min_deadline, se, rse))
-			se->min_deadline = rse->min_deadline;
+		if (vruntime_gt(min_vruntime, se, rse))
+			se->min_vruntime = rse->min_vruntime;
 	}
 }
 
 /*
- * se->min_deadline = min(se->deadline, left->min_deadline, right->min_deadline)
+ * se->min_vruntime = min(se->vruntime, {left,right}->min_vruntime)
  */
-static inline bool min_deadline_update(struct sched_entity *se, bool exit)
+static inline bool min_vruntime_update(struct sched_entity *se, bool exit)
 {
-	u64 old_min_deadline = se->min_deadline;
+	u64 old_min_vruntime = se->min_vruntime;
 	struct rb_node *node = &se->run_node;
 
-	se->min_deadline = se->deadline;
-	__update_min_deadline(se, node->rb_right);
-	__update_min_deadline(se, node->rb_left);
+	se->min_vruntime = se->vruntime;
+	__min_vruntime_update(se, node->rb_right);
+	__min_vruntime_update(se, node->rb_left);
 
-	return se->min_deadline == old_min_deadline;
+	return se->min_vruntime == old_min_vruntime;
 }
 
-RB_DECLARE_CALLBACKS(static, min_deadline_cb, struct sched_entity,
-		     run_node, min_deadline, min_deadline_update);
+RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity,
+		     run_node, min_vruntime, min_vruntime_update);
 
 /*
  * Enqueue an entity into the rb-tree:
@@ -816,18 +824,28 @@ RB_DECLARE_CALLBACKS(static, min_deadline_cb, struct sched_entity,
 static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	avg_vruntime_add(cfs_rq, se);
-	se->min_deadline = se->deadline;
+	se->min_vruntime = se->vruntime;
 	rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
-				__entity_less, &min_deadline_cb);
+				__entity_less, &min_vruntime_cb);
 }
 
 static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	rb_erase_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
-				  &min_deadline_cb);
+				  &min_vruntime_cb);
 	avg_vruntime_sub(cfs_rq, se);
 }
 
+struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq)
+{
+	struct rb_node *root = cfs_rq->tasks_timeline.rb_root.rb_node;
+
+	if (!root)
+		return NULL;
+
+	return __node_2_se(root);
+}
+
 struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
 {
 	struct rb_node *left = rb_first_cached(&cfs_rq->tasks_timeline);
@@ -850,23 +868,29 @@ struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
  *     with the earliest virtual deadline.
  *
  * We can do this in O(log n) time due to an augmented RB-tree. The
- * tree keeps the entries sorted on service, but also functions as a
- * heap based on the deadline by keeping:
+ * tree keeps the entries sorted on deadline, but also functions as a
+ * heap based on the vruntime by keeping:
  *
- *  se->min_deadline = min(se->deadline, se->{left,right}->min_deadline)
+ *  se->min_vruntime = min(se->vruntime, se->{left,right}->min_vruntime)
  *
- * Which allows an EDF like search on (sub)trees.
+ * Which allows tree pruning through eligibility.
  */
-static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq)
+static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
 {
 	struct rb_node *node = cfs_rq->tasks_timeline.rb_root.rb_node;
+	struct sched_entity *se = __pick_first_entity(cfs_rq);
 	struct sched_entity *curr = cfs_rq->curr;
 	struct sched_entity *best = NULL;
-	struct sched_entity *best_left = NULL;
+
+	/*
+	 * We can safely skip eligibility check if there is only one entity
+	 * in this cfs_rq, saving some cycles.
+	 */
+	if (cfs_rq->nr_running == 1)
+		return curr && curr->on_rq ? curr : se;
 
 	if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr)))
 		curr = NULL;
-	best = curr;
 
 	/*
 	 * Once selected, run a task until it either becomes non-eligible or
@@ -875,95 +899,45 @@ static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq)
 	if (sched_feat(RUN_TO_PARITY) && curr && curr->vlag == curr->deadline)
 		return curr;
 
+	/* Pick the leftmost entity if it's eligible */
+	if (se && entity_eligible(cfs_rq, se)) {
+		best = se;
+		goto found;
+	}
+
+	/* Heap search for the EEVD entity */
 	while (node) {
-		struct sched_entity *se = __node_2_se(node);
+		struct rb_node *left = node->rb_left;
 
 		/*
-		 * If this entity is not eligible, try the left subtree.
+		 * Eligible entities in left subtree are always better
+		 * choices, since they have earlier deadlines.
 		 */
-		if (!entity_eligible(cfs_rq, se)) {
-			node = node->rb_left;
+		if (left && vruntime_eligible(cfs_rq,
+					__node_2_se(left)->min_vruntime)) {
+			node = left;
 			continue;
 		}
 
-		/*
-		 * Now we heap search eligible trees for the best (min_)deadline
-		 */
-		if (!best || deadline_gt(deadline, best, se))
-			best = se;
+		se = __node_2_se(node);
 
 		/*
-		 * Every se in a left branch is eligible, keep track of the
-		 * branch with the best min_deadline
+		 * The left subtree either is empty or has no eligible
+		 * entity, so check the current node since it is the one
+		 * with earliest deadline that might be eligible.
 		 */
-		if (node->rb_left) {
-			struct sched_entity *left = __node_2_se(node->rb_left);
-
-			if (!best_left || deadline_gt(min_deadline, best_left, left))
-				best_left = left;
-
-			/*
-			 * min_deadline is in the left branch. rb_left and all
-			 * descendants are eligible, so immediately switch to the second
-			 * loop.
-			 */
-			if (left->min_deadline == se->min_deadline)
-				break;
-		}
-
-		/* min_deadline is at this node, no need to look right */
-		if (se->deadline == se->min_deadline)
+		if (entity_eligible(cfs_rq, se)) {
+			best = se;
 			break;
-
-		/* else min_deadline is in the right branch. */
-		node = node->rb_right;
-	}
-
-	/*
-	 * We ran into an eligible node which is itself the best.
-	 * (Or nr_running == 0 and both are NULL)
-	 */
-	if (!best_left || (s64)(best_left->min_deadline - best->deadline) > 0)
-		return best;
-
-	/*
-	 * Now best_left and all of its children are eligible, and we are just
-	 * looking for deadline == min_deadline
-	 */
-	node = &best_left->run_node;
-	while (node) {
-		struct sched_entity *se = __node_2_se(node);
-
-		/* min_deadline is the current node */
-		if (se->deadline == se->min_deadline)
-			return se;
-
-		/* min_deadline is in the left branch */
-		if (node->rb_left &&
-		    __node_2_se(node->rb_left)->min_deadline == se->min_deadline) {
-			node = node->rb_left;
-			continue;
 		}
 
-		/* else min_deadline is in the right branch */
 		node = node->rb_right;
 	}
-	return NULL;
-}
-
-static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
-{
-	struct sched_entity *se = __pick_eevdf(cfs_rq);
-
-	if (!se) {
-		struct sched_entity *left = __pick_first_entity(cfs_rq);
-		if (left) {
-			pr_err("EEVDF scheduling fail, picking leftmost\n");
-			return left;
-		}
-	}
+found:
+	if (!best || (curr && entity_before(curr, best)))
+		best = curr;
 
-	return se;
+	return best;
 }
 
 #ifdef CONFIG_SCHED_DEBUG
@@ -1129,23 +1103,17 @@ static void update_tg_load_avg(struct cfs_rq *cfs_rq)
 }
 #endif /* CONFIG_SMP */
 
-/*
- * Update the current task's runtime statistics.
- */
-static void update_curr(struct cfs_rq *cfs_rq)
+static s64 update_curr_se(struct rq *rq, struct sched_entity *curr)
 {
-	struct sched_entity *curr = cfs_rq->curr;
-	u64 now = rq_clock_task(rq_of(cfs_rq));
-	u64 delta_exec;
-
-	if (unlikely(!curr))
-		return;
+	u64 now = rq_clock_task(rq);
+	s64 delta_exec;
 
 	delta_exec = now - curr->exec_start;
-	if (unlikely((s64)delta_exec <= 0))
-		return;
+	if (unlikely(delta_exec <= 0))
+		return delta_exec;
 
 	curr->exec_start = now;
+	curr->sum_exec_runtime += delta_exec;
 
 	if (schedstat_enabled()) {
 		struct sched_statistics *stats;
@@ -1155,20 +1123,54 @@ static void update_curr(struct cfs_rq *cfs_rq)
 				max(delta_exec, stats->exec_max));
 	}
 
-	curr->sum_exec_runtime += delta_exec;
-	schedstat_add(cfs_rq->exec_clock, delta_exec);
+	return delta_exec;
+}
+
+static inline void update_curr_task(struct task_struct *p, s64 delta_exec)
+{
+	trace_sched_stat_runtime(p, delta_exec);
+	account_group_exec_runtime(p, delta_exec);
+	cgroup_account_cputime(p, delta_exec);
+	if (p->dl_server)
+		dl_server_update(p->dl_server, delta_exec);
+}
+
+/*
+ * Used by other classes to account runtime.
+ */
+s64 update_curr_common(struct rq *rq)
+{
+	struct task_struct *curr = rq->curr;
+	s64 delta_exec;
+
+	delta_exec = update_curr_se(rq, &curr->se);
+	if (likely(delta_exec > 0))
+		update_curr_task(curr, delta_exec);
+
+	return delta_exec;
+}
+
+/*
+ * Update the current task's runtime statistics.
+ */
+static void update_curr(struct cfs_rq *cfs_rq)
+{
+	struct sched_entity *curr = cfs_rq->curr;
+	s64 delta_exec;
+
+	if (unlikely(!curr))
+		return;
+
+	delta_exec = update_curr_se(rq_of(cfs_rq), curr);
+	if (unlikely(delta_exec <= 0))
+		return;
 
 	curr->vruntime += calc_delta_fair(delta_exec, curr);
 	update_deadline(cfs_rq, curr);
 	update_min_vruntime(cfs_rq);
 
-	if (entity_is_task(curr)) {
-		struct task_struct *curtask = task_of(curr);
-
-		trace_sched_stat_runtime(curtask, delta_exec, curr->vruntime);
-		cgroup_account_cputime(curtask, delta_exec);
-		account_group_exec_runtime(curtask, delta_exec);
-	}
+	if (entity_is_task(curr))
+		update_curr_task(task_of(curr), delta_exec);
 
 	account_cfs_rq_runtime(cfs_rq, delta_exec);
 }
@@ -3164,7 +3166,7 @@ static bool vma_is_accessed(struct mm_struct *mm, struct vm_area_struct *vma)
 	 * This is also done to avoid any side effect of task scanning
 	 * amplifying the unfairness of disjoint set of VMAs' access.
 	 */
-	if (READ_ONCE(current->mm->numa_scan_seq) < 2)
+	if ((READ_ONCE(current->mm->numa_scan_seq) - vma->numab_state->start_scan_seq) < 2)
 		return true;
 
 	pids = vma->numab_state->pids_active[0] | vma->numab_state->pids_active[1];
@@ -3307,6 +3309,8 @@ retry_pids:
 			if (!vma->numab_state)
 				continue;
 
+			vma->numab_state->start_scan_seq = mm->numa_scan_seq;
+
 			vma->numab_state->next_scan = now +
 				msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
 
@@ -3666,41 +3670,140 @@ static inline void
 dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
 #endif
 
+static void reweight_eevdf(struct cfs_rq *cfs_rq, struct sched_entity *se,
+			   unsigned long weight)
+{
+	unsigned long old_weight = se->load.weight;
+	u64 avruntime = avg_vruntime(cfs_rq);
+	s64 vlag, vslice;
+
+	/*
+	 * VRUNTIME
+	 * ========
+	 *
+	 * COROLLARY #1: The virtual runtime of the entity needs to be
+	 * adjusted if re-weight at !0-lag point.
+	 *
+	 * Proof: For contradiction assume this is not true, so we can
+	 * re-weight without changing vruntime at !0-lag point.
+	 *
+	 *             Weight	VRuntime   Avg-VRuntime
+	 *     before    w          v            V
+	 *      after    w'         v'           V'
+	 *
+	 * Since lag needs to be preserved through re-weight:
+	 *
+	 *	lag = (V - v)*w = (V'- v')*w', where v = v'
+	 *	==>	V' = (V - v)*w/w' + v		(1)
+	 *
+	 * Let W be the total weight of the entities before reweight,
+	 * since V' is the new weighted average of entities:
+	 *
+	 *	V' = (WV + w'v - wv) / (W + w' - w)	(2)
+	 *
+	 * by using (1) & (2) we obtain:
+	 *
+	 *	(WV + w'v - wv) / (W + w' - w) = (V - v)*w/w' + v
+	 *	==> (WV-Wv+Wv+w'v-wv)/(W+w'-w) = (V - v)*w/w' + v
+	 *	==> (WV - Wv)/(W + w' - w) + v = (V - v)*w/w' + v
+	 *	==>	(V - v)*W/(W + w' - w) = (V - v)*w/w' (3)
+	 *
+	 * Since we are doing at !0-lag point which means V != v, we
+	 * can simplify (3):
+	 *
+	 *	==>	W / (W + w' - w) = w / w'
+	 *	==>	Ww' = Ww + ww' - ww
+	 *	==>	W * (w' - w) = w * (w' - w)
+	 *	==>	W = w	(re-weight indicates w' != w)
+	 *
+	 * So the cfs_rq contains only one entity, hence vruntime of
+	 * the entity @v should always equal to the cfs_rq's weighted
+	 * average vruntime @V, which means we will always re-weight
+	 * at 0-lag point, thus breach assumption. Proof completed.
+	 *
+	 *
+	 * COROLLARY #2: Re-weight does NOT affect weighted average
+	 * vruntime of all the entities.
+	 *
+	 * Proof: According to corollary #1, Eq. (1) should be:
+	 *
+	 *	(V - v)*w = (V' - v')*w'
+	 *	==>    v' = V' - (V - v)*w/w'		(4)
+	 *
+	 * According to the weighted average formula, we have:
+	 *
+	 *	V' = (WV - wv + w'v') / (W - w + w')
+	 *	   = (WV - wv + w'(V' - (V - v)w/w')) / (W - w + w')
+	 *	   = (WV - wv + w'V' - Vw + wv) / (W - w + w')
+	 *	   = (WV + w'V' - Vw) / (W - w + w')
+	 *
+	 *	==>  V'*(W - w + w') = WV + w'V' - Vw
+	 *	==>	V' * (W - w) = (W - w) * V	(5)
+	 *
+	 * If the entity is the only one in the cfs_rq, then reweight
+	 * always occurs at 0-lag point, so V won't change. Or else
+	 * there are other entities, hence W != w, then Eq. (5) turns
+	 * into V' = V. So V won't change in either case, proof done.
+	 *
+	 *
+	 * So according to corollary #1 & #2, the effect of re-weight
+	 * on vruntime should be:
+	 *
+	 *	v' = V' - (V - v) * w / w'		(4)
+	 *	   = V  - (V - v) * w / w'
+	 *	   = V  - vl * w / w'
+	 *	   = V  - vl'
+	 */
+	if (avruntime != se->vruntime) {
+		vlag = (s64)(avruntime - se->vruntime);
+		vlag = div_s64(vlag * old_weight, weight);
+		se->vruntime = avruntime - vlag;
+	}
+
+	/*
+	 * DEADLINE
+	 * ========
+	 *
+	 * When the weight changes, the virtual time slope changes and
+	 * we should adjust the relative virtual deadline accordingly.
+	 *
+	 *	d' = v' + (d - v)*w/w'
+	 *	   = V' - (V - v)*w/w' + (d - v)*w/w'
+	 *	   = V  - (V - v)*w/w' + (d - v)*w/w'
+	 *	   = V  + (d - V)*w/w'
+	 */
+	vslice = (s64)(se->deadline - avruntime);
+	vslice = div_s64(vslice * old_weight, weight);
+	se->deadline = avruntime + vslice;
+}
+
 static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 			    unsigned long weight)
 {
-	unsigned long old_weight = se->load.weight;
+	bool curr = cfs_rq->curr == se;
 
 	if (se->on_rq) {
 		/* commit outstanding execution time */
-		if (cfs_rq->curr == se)
+		if (curr)
 			update_curr(cfs_rq);
 		else
-			avg_vruntime_sub(cfs_rq, se);
+			__dequeue_entity(cfs_rq, se);
 		update_load_sub(&cfs_rq->load, se->load.weight);
 	}
 	dequeue_load_avg(cfs_rq, se);
 
-	update_load_set(&se->load, weight);
-
 	if (!se->on_rq) {
 		/*
 		 * Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i),
 		 * we need to scale se->vlag when w_i changes.
 		 */
-		se->vlag = div_s64(se->vlag * old_weight, weight);
+		se->vlag = div_s64(se->vlag * se->load.weight, weight);
 	} else {
-		s64 deadline = se->deadline - se->vruntime;
-		/*
-		 * When the weight changes, the virtual time slope changes and
-		 * we should adjust the relative virtual deadline accordingly.
-		 */
-		deadline = div_s64(deadline * old_weight, weight);
-		se->deadline = se->vruntime + deadline;
-		if (se != cfs_rq->curr)
-			min_deadline_cb_propagate(&se->run_node, NULL);
+		reweight_eevdf(cfs_rq, se, weight);
 	}
 
+	update_load_set(&se->load, weight);
+
 #ifdef CONFIG_SMP
 	do {
 		u32 divider = get_pelt_divider(&se->avg);
@@ -3712,8 +3815,17 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 	enqueue_load_avg(cfs_rq, se);
 	if (se->on_rq) {
 		update_load_add(&cfs_rq->load, se->load.weight);
-		if (cfs_rq->curr != se)
-			avg_vruntime_add(cfs_rq, se);
+		if (!curr)
+			__enqueue_entity(cfs_rq, se);
+
+		/*
+		 * The entity's vruntime has been adjusted, so let's check
+		 * whether the rq-wide min_vruntime needs updated too. Since
+		 * the calculations above require stable min_vruntime rather
+		 * than up-to-date one, we do the update at the end of the
+		 * reweight process.
+		 */
+		update_min_vruntime(cfs_rq);
 	}
 }
 
@@ -3857,14 +3969,11 @@ static void update_cfs_group(struct sched_entity *se)
 
 #ifndef CONFIG_SMP
 	shares = READ_ONCE(gcfs_rq->tg->shares);
-
-	if (likely(se->load.weight == shares))
-		return;
 #else
-	shares   = calc_group_shares(gcfs_rq);
+	shares = calc_group_shares(gcfs_rq);
 #endif
-
-	reweight_entity(cfs_rq_of(se), se, shares);
+	if (unlikely(se->load.weight != shares))
+		reweight_entity(cfs_rq_of(se), se, shares);
 }
 
 #else /* CONFIG_FAIR_GROUP_SCHED */
@@ -3991,6 +4100,10 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq)
 	if (cfs_rq->tg == &root_task_group)
 		return;
 
+	/* rq has been offline and doesn't contribute to the share anymore: */
+	if (!cpu_active(cpu_of(rq_of(cfs_rq))))
+		return;
+
 	/*
 	 * For migration heavy workloads, access to tg->load_avg can be
 	 * unbound. Limit the update rate to at most once per ms.
@@ -4007,6 +4120,49 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq)
 	}
 }
 
+static inline void clear_tg_load_avg(struct cfs_rq *cfs_rq)
+{
+	long delta;
+	u64 now;
+
+	/*
+	 * No need to update load_avg for root_task_group, as it is not used.
+	 */
+	if (cfs_rq->tg == &root_task_group)
+		return;
+
+	now = sched_clock_cpu(cpu_of(rq_of(cfs_rq)));
+	delta = 0 - cfs_rq->tg_load_avg_contrib;
+	atomic_long_add(delta, &cfs_rq->tg->load_avg);
+	cfs_rq->tg_load_avg_contrib = 0;
+	cfs_rq->last_update_tg_load_avg = now;
+}
+
+/* CPU offline callback: */
+static void __maybe_unused clear_tg_offline_cfs_rqs(struct rq *rq)
+{
+	struct task_group *tg;
+
+	lockdep_assert_rq_held(rq);
+
+	/*
+	 * The rq clock has already been updated in
+	 * set_rq_offline(), so we should skip updating
+	 * the rq clock again in unthrottle_cfs_rq().
+	 */
+	rq_clock_start_loop_update(rq);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(tg, &task_groups, list) {
+		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
+
+		clear_tg_load_avg(cfs_rq);
+	}
+	rcu_read_unlock();
+
+	rq_clock_stop_loop_update(rq);
+}
+
 /*
  * Called within set_task_rq() right before setting a task's CPU. The
  * caller only guarantees p->pi_lock is held; no other assumptions,
@@ -4303,6 +4459,8 @@ static inline bool skip_blocked_update(struct sched_entity *se)
 
 static inline void update_tg_load_avg(struct cfs_rq *cfs_rq) {}
 
+static inline void clear_tg_offline_cfs_rqs(struct rq *rq) {}
+
 static inline int propagate_entity_load_avg(struct sched_entity *se)
 {
 	return 0;
@@ -4665,11 +4823,14 @@ static inline unsigned long task_util(struct task_struct *p)
 	return READ_ONCE(p->se.avg.util_avg);
 }
 
-static inline unsigned long _task_util_est(struct task_struct *p)
+static inline unsigned long task_runnable(struct task_struct *p)
 {
-	struct util_est ue = READ_ONCE(p->se.avg.util_est);
+	return READ_ONCE(p->se.avg.runnable_avg);
+}
 
-	return max(ue.ewma, (ue.enqueued & ~UTIL_AVG_UNCHANGED));
+static inline unsigned long _task_util_est(struct task_struct *p)
+{
+	return READ_ONCE(p->se.avg.util_est) & ~UTIL_AVG_UNCHANGED;
 }
 
 static inline unsigned long task_util_est(struct task_struct *p)
@@ -4686,9 +4847,9 @@ static inline void util_est_enqueue(struct cfs_rq *cfs_rq,
 		return;
 
 	/* Update root cfs_rq's estimated utilization */
-	enqueued  = cfs_rq->avg.util_est.enqueued;
+	enqueued  = cfs_rq->avg.util_est;
 	enqueued += _task_util_est(p);
-	WRITE_ONCE(cfs_rq->avg.util_est.enqueued, enqueued);
+	WRITE_ONCE(cfs_rq->avg.util_est, enqueued);
 
 	trace_sched_util_est_cfs_tp(cfs_rq);
 }
@@ -4702,34 +4863,20 @@ static inline void util_est_dequeue(struct cfs_rq *cfs_rq,
 		return;
 
 	/* Update root cfs_rq's estimated utilization */
-	enqueued  = cfs_rq->avg.util_est.enqueued;
+	enqueued  = cfs_rq->avg.util_est;
 	enqueued -= min_t(unsigned int, enqueued, _task_util_est(p));
-	WRITE_ONCE(cfs_rq->avg.util_est.enqueued, enqueued);
+	WRITE_ONCE(cfs_rq->avg.util_est, enqueued);
 
 	trace_sched_util_est_cfs_tp(cfs_rq);
 }
 
 #define UTIL_EST_MARGIN (SCHED_CAPACITY_SCALE / 100)
 
-/*
- * Check if a (signed) value is within a specified (unsigned) margin,
- * based on the observation that:
- *
- *     abs(x) < y := (unsigned)(x + y - 1) < (2 * y - 1)
- *
- * NOTE: this only works when value + margin < INT_MAX.
- */
-static inline bool within_margin(int value, int margin)
-{
-	return ((unsigned int)(value + margin - 1) < (2 * margin - 1));
-}
-
 static inline void util_est_update(struct cfs_rq *cfs_rq,
 				   struct task_struct *p,
 				   bool task_sleep)
 {
-	long last_ewma_diff, last_enqueued_diff;
-	struct util_est ue;
+	unsigned int ewma, dequeued, last_ewma_diff;
 
 	if (!sched_feat(UTIL_EST))
 		return;
@@ -4741,71 +4888,73 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
 	if (!task_sleep)
 		return;
 
+	/* Get current estimate of utilization */
+	ewma = READ_ONCE(p->se.avg.util_est);
+
 	/*
 	 * If the PELT values haven't changed since enqueue time,
 	 * skip the util_est update.
 	 */
-	ue = p->se.avg.util_est;
-	if (ue.enqueued & UTIL_AVG_UNCHANGED)
+	if (ewma & UTIL_AVG_UNCHANGED)
 		return;
 
-	last_enqueued_diff = ue.enqueued;
+	/* Get utilization at dequeue */
+	dequeued = task_util(p);
 
 	/*
 	 * Reset EWMA on utilization increases, the moving average is used only
 	 * to smooth utilization decreases.
 	 */
-	ue.enqueued = task_util(p);
-	if (sched_feat(UTIL_EST_FASTUP)) {
-		if (ue.ewma < ue.enqueued) {
-			ue.ewma = ue.enqueued;
-			goto done;
-		}
+	if (ewma <= dequeued) {
+		ewma = dequeued;
+		goto done;
 	}
 
 	/*
 	 * Skip update of task's estimated utilization when its members are
 	 * already ~1% close to its last activation value.
 	 */
-	last_ewma_diff = ue.enqueued - ue.ewma;
-	last_enqueued_diff -= ue.enqueued;
-	if (within_margin(last_ewma_diff, UTIL_EST_MARGIN)) {
-		if (!within_margin(last_enqueued_diff, UTIL_EST_MARGIN))
-			goto done;
-
-		return;
-	}
+	last_ewma_diff = ewma - dequeued;
+	if (last_ewma_diff < UTIL_EST_MARGIN)
+		goto done;
 
 	/*
 	 * To avoid overestimation of actual task utilization, skip updates if
 	 * we cannot grant there is idle time in this CPU.
 	 */
-	if (task_util(p) > arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq))))
+	if (dequeued > arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq))))
 		return;
 
 	/*
+	 * To avoid underestimate of task utilization, skip updates of EWMA if
+	 * we cannot grant that thread got all CPU time it wanted.
+	 */
+	if ((dequeued + UTIL_EST_MARGIN) < task_runnable(p))
+		goto done;
+
+
+	/*
 	 * Update Task's estimated utilization
 	 *
 	 * When *p completes an activation we can consolidate another sample
-	 * of the task size. This is done by storing the current PELT value
-	 * as ue.enqueued and by using this value to update the Exponential
-	 * Weighted Moving Average (EWMA):
+	 * of the task size. This is done by using this value to update the
+	 * Exponential Weighted Moving Average (EWMA):
 	 *
 	 *  ewma(t) = w *  task_util(p) + (1-w) * ewma(t-1)
 	 *          = w *  task_util(p) +         ewma(t-1)  - w * ewma(t-1)
 	 *          = w * (task_util(p) -         ewma(t-1)) +     ewma(t-1)
-	 *          = w * (      last_ewma_diff            ) +     ewma(t-1)
-	 *          = w * (last_ewma_diff  +  ewma(t-1) / w)
+	 *          = w * (      -last_ewma_diff           ) +     ewma(t-1)
+	 *          = w * (-last_ewma_diff +  ewma(t-1) / w)
 	 *
 	 * Where 'w' is the weight of new samples, which is configured to be
 	 * 0.25, thus making w=1/4 ( >>= UTIL_EST_WEIGHT_SHIFT)
 	 */
-	ue.ewma <<= UTIL_EST_WEIGHT_SHIFT;
-	ue.ewma  += last_ewma_diff;
-	ue.ewma >>= UTIL_EST_WEIGHT_SHIFT;
+	ewma <<= UTIL_EST_WEIGHT_SHIFT;
+	ewma  -= last_ewma_diff;
+	ewma >>= UTIL_EST_WEIGHT_SHIFT;
 done:
-	ue.enqueued |= UTIL_AVG_UNCHANGED;
-	WRITE_ONCE(p->se.avg.util_est, ue);
+	ewma |= UTIL_AVG_UNCHANGED;
+	WRITE_ONCE(p->se.avg.util_est, ewma);
 
 	trace_sched_util_est_se_tp(&p->se);
 }
@@ -7533,16 +7682,16 @@ cpu_util(int cpu, struct task_struct *p, int dst_cpu, int boost)
 	if (sched_feat(UTIL_EST)) {
 		unsigned long util_est;
 
-		util_est = READ_ONCE(cfs_rq->avg.util_est.enqueued);
+		util_est = READ_ONCE(cfs_rq->avg.util_est);
 
 		/*
 		 * During wake-up @p isn't enqueued yet and doesn't contribute
-		 * to any cpu_rq(cpu)->cfs.avg.util_est.enqueued.
+		 * to any cpu_rq(cpu)->cfs.avg.util_est.
 		 * If @dst_cpu == @cpu add it to "simulate" cpu_util after @p
 		 * has been enqueued.
 		 *
 		 * During exec (@dst_cpu = -1) @p is enqueued and does
-		 * contribute to cpu_rq(cpu)->cfs.util_est.enqueued.
+		 * contribute to cpu_rq(cpu)->cfs.util_est.
 		 * Remove it to "simulate" cpu_util without @p's contribution.
 		 *
 		 * Despite the task_on_rq_queued(@p) check there is still a
@@ -7671,7 +7820,7 @@ static inline void eenv_pd_busy_time(struct energy_env *eenv,
 	for_each_cpu(cpu, pd_cpus) {
 		unsigned long util = cpu_util(cpu, p, -1, 0);
 
-		busy_time += effective_cpu_util(cpu, util, ENERGY_UTIL, NULL);
+		busy_time += effective_cpu_util(cpu, util, NULL, NULL);
 	}
 
 	eenv->pd_busy_time = min(eenv->pd_cap, busy_time);
@@ -7694,7 +7843,7 @@ eenv_pd_max_util(struct energy_env *eenv, struct cpumask *pd_cpus,
 	for_each_cpu(cpu, pd_cpus) {
 		struct task_struct *tsk = (cpu == dst_cpu) ? p : NULL;
 		unsigned long util = cpu_util(cpu, p, dst_cpu, 1);
-		unsigned long eff_util;
+		unsigned long eff_util, min, max;
 
 		/*
 		 * Performance domain frequency: utilization clamping
@@ -7703,7 +7852,23 @@ eenv_pd_max_util(struct energy_env *eenv, struct cpumask *pd_cpus,
 		 * NOTE: in case RT tasks are running, by default the
 		 * FREQUENCY_UTIL's utilization can be max OPP.
 		 */
-		eff_util = effective_cpu_util(cpu, util, FREQUENCY_UTIL, tsk);
+		eff_util = effective_cpu_util(cpu, util, &min, &max);
+
+		/* Task's uclamp can modify min and max value */
+		if (tsk && uclamp_is_used()) {
+			min = max(min, uclamp_eff_value(p, UCLAMP_MIN));
+
+			/*
+			 * If there is no active max uclamp constraint,
+			 * directly use task's one, otherwise keep max.
+			 */
+			if (uclamp_rq_is_idle(cpu_rq(cpu)))
+				max = uclamp_eff_value(p, UCLAMP_MAX);
+			else
+				max = max(max, uclamp_eff_value(p, UCLAMP_MAX));
+		}
+
+		eff_util = sugov_effective_cpu_perf(cpu, eff_util, min, max);
 		max_util = max(max_util, eff_util);
 	}
 
@@ -8105,7 +8270,6 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
 	struct task_struct *curr = rq->curr;
 	struct sched_entity *se = &curr->se, *pse = &p->se;
 	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
-	int next_buddy_marked = 0;
 	int cse_is_idle, pse_is_idle;
 
 	if (unlikely(se == pse))
@@ -8122,7 +8286,6 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
 
 	if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK)) {
 		set_next_buddy(pse);
-		next_buddy_marked = 1;
 	}
 
 	/*
@@ -8955,7 +9118,7 @@ static int detach_tasks(struct lb_env *env)
 		case migrate_util:
 			util = task_util_est(p);
 
-			if (util > env->imbalance)
+			if (shr_bound(util, env->sd->nr_balance_failed) > env->imbalance)
 				goto next;
 
 			env->imbalance -= util;
@@ -11079,12 +11242,16 @@ static int should_we_balance(struct lb_env *env)
 			continue;
 		}
 
-		/* Are we the first idle CPU? */
+		/*
+		 * Are we the first idle core in a non-SMT domain or higher,
+		 * or the first idle CPU in a SMT domain?
+		 */
 		return cpu == env->dst_cpu;
 	}
 
-	if (idle_smt == env->dst_cpu)
-		return true;
+	/* Are we the first idle CPU with busy siblings? */
+	if (idle_smt != -1)
+		return idle_smt == env->dst_cpu;
 
 	/* Are we the first CPU of this group ? */
 	return group_balance_cpu(sg) == env->dst_cpu;
@@ -12304,6 +12471,9 @@ static void rq_offline_fair(struct rq *rq)
 
 	/* Ensure any throttled groups are reachable by pick_next_task */
 	unthrottle_offline_cfs_rqs(rq);
+
+	/* Ensure that we remove rq contribution to group share: */
+	clear_tg_offline_cfs_rqs(rq);
 }
 
 #endif /* CONFIG_SMP */
@@ -12927,19 +13097,6 @@ next_cpu:
 	return 0;
 }
 
-#else /* CONFIG_FAIR_GROUP_SCHED */
-
-void free_fair_sched_group(struct task_group *tg) { }
-
-int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
-{
-	return 1;
-}
-
-void online_fair_sched_group(struct task_group *tg) { }
-
-void unregister_fair_sched_group(struct task_group *tg) { }
-
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
 
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index a3ddf84de430..143f55df890b 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -83,7 +83,6 @@ SCHED_FEAT(WA_BIAS, true)
  * UtilEstimation. Use estimated CPU utilization.
  */
 SCHED_FEAT(UTIL_EST, true)
-SCHED_FEAT(UTIL_EST_FASTUP, true)
 
 SCHED_FEAT(LATENCY_WARN, false)
 
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 565f8374ddbb..31231925f1ec 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -258,6 +258,36 @@ static void do_idle(void)
 	while (!need_resched()) {
 		rmb();
 
+		/*
+		 * Interrupts shouldn't be re-enabled from that point on until
+		 * the CPU sleeping instruction is reached. Otherwise an interrupt
+		 * may fire and queue a timer that would be ignored until the CPU
+		 * wakes from the sleeping instruction. And testing need_resched()
+		 * doesn't tell about pending needed timer reprogram.
+		 *
+		 * Several cases to consider:
+		 *
+		 * - SLEEP-UNTIL-PENDING-INTERRUPT based instructions such as
+		 *   "wfi" or "mwait" are fine because they can be entered with
+		 *   interrupt disabled.
+		 *
+		 * - sti;mwait() couple is fine because the interrupts are
+		 *   re-enabled only upon the execution of mwait, leaving no gap
+		 *   in-between.
+		 *
+		 * - ROLLBACK based idle handlers with the sleeping instruction
+		 *   called with interrupts enabled are NOT fine. In this scheme
+		 *   when the interrupt detects it has interrupted an idle handler,
+		 *   it rolls back to its beginning which performs the
+		 *   need_resched() check before re-executing the sleeping
+		 *   instruction. This can leak a pending needed timer reprogram.
+		 *   If such a scheme is really mandatory due to the lack of an
+		 *   appropriate CPU sleeping instruction, then a FAST-FORWARD
+		 *   must instead be applied: when the interrupt detects it has
+		 *   interrupted an idle handler, it must resume to the end of
+		 *   this idle handler so that the generic idle loop is iterated
+		 *   again to reprogram the tick.
+		 */
 		local_irq_disable();
 
 		if (cpu_is_offline(cpu)) {
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
index 3a0e0dc28721..9e1083465fbc 100644
--- a/kernel/sched/pelt.h
+++ b/kernel/sched/pelt.h
@@ -52,13 +52,13 @@ static inline void cfs_se_util_change(struct sched_avg *avg)
 		return;
 
 	/* Avoid store if the flag has been already reset */
-	enqueued = avg->util_est.enqueued;
+	enqueued = avg->util_est;
 	if (!(enqueued & UTIL_AVG_UNCHANGED))
 		return;
 
 	/* Reset flag to report util_avg has been updated */
 	enqueued &= ~UTIL_AVG_UNCHANGED;
-	WRITE_ONCE(avg->util_est.enqueued, enqueued);
+	WRITE_ONCE(avg->util_est, enqueued);
 }
 
 static inline u64 rq_clock_pelt(struct rq *rq)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 6aaf0a3d6081..3261b067b67e 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1002,24 +1002,15 @@ static void update_curr_rt(struct rq *rq)
 {
 	struct task_struct *curr = rq->curr;
 	struct sched_rt_entity *rt_se = &curr->rt;
-	u64 delta_exec;
-	u64 now;
+	s64 delta_exec;
 
 	if (curr->sched_class != &rt_sched_class)
 		return;
 
-	now = rq_clock_task(rq);
-	delta_exec = now - curr->se.exec_start;
-	if (unlikely((s64)delta_exec <= 0))
+	delta_exec = update_curr_common(rq);
+	if (unlikely(delta_exec <= 0))
 		return;
 
-	schedstat_set(curr->stats.exec_max,
-		      max(curr->stats.exec_max, delta_exec));
-
-	trace_sched_stat_runtime(curr, delta_exec, 0);
-
-	update_current_exec_runtime(curr, now, delta_exec);
-
 	if (!rt_bandwidth_enabled())
 		return;
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 2e5a95486a42..001fe047bd5d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -273,8 +273,6 @@ struct rt_bandwidth {
 	unsigned int		rt_period_active;
 };
 
-void __dl_clear_params(struct task_struct *p);
-
 static inline int dl_bandwidth_enabled(void)
 {
 	return sysctl_sched_rt_runtime >= 0;
@@ -315,6 +313,33 @@ extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *att
 extern int  dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
 extern int  dl_bw_check_overflow(int cpu);
 
+/*
+ * SCHED_DEADLINE supports servers (nested scheduling) with the following
+ * interface:
+ *
+ *   dl_se::rq -- runqueue we belong to.
+ *
+ *   dl_se::server_has_tasks() -- used on bandwidth enforcement; we 'stop' the
+ *                                server when it runs out of tasks to run.
+ *
+ *   dl_se::server_pick() -- nested pick_next_task(); we yield the period if this
+ *                           returns NULL.
+ *
+ *   dl_server_update() -- called from update_curr_common(), propagates runtime
+ *                         to the server.
+ *
+ *   dl_server_start()
+ *   dl_server_stop()  -- start/stop the server when it has (no) tasks.
+ *
+ *   dl_server_init() -- initializes the server.
+ */
+extern void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec);
+extern void dl_server_start(struct sched_dl_entity *dl_se);
+extern void dl_server_stop(struct sched_dl_entity *dl_se);
+extern void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
+		    dl_server_has_tasks_f has_tasks,
+		    dl_server_pick_f pick);
+
 #ifdef CONFIG_CGROUP_SCHED
 
 struct cfs_rq;
@@ -436,10 +461,21 @@ static inline int walk_tg_tree(tg_visitor down, tg_visitor up, void *data)
 
 extern int tg_nop(struct task_group *tg, void *data);
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
 extern void free_fair_sched_group(struct task_group *tg);
 extern int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent);
 extern void online_fair_sched_group(struct task_group *tg);
 extern void unregister_fair_sched_group(struct task_group *tg);
+#else
+static inline void free_fair_sched_group(struct task_group *tg) { }
+static inline int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
+{
+       return 1;
+}
+static inline void online_fair_sched_group(struct task_group *tg) { }
+static inline void unregister_fair_sched_group(struct task_group *tg) { }
+#endif
+
 extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 			struct sched_entity *se, int cpu,
 			struct sched_entity *parent);
@@ -2179,6 +2215,10 @@ extern const u32		sched_prio_to_wmult[40];
  * MOVE - paired with SAVE/RESTORE, explicitly does not preserve the location
  *        in the runqueue.
  *
+ * NOCLOCK - skip the update_rq_clock() (avoids double updates)
+ *
+ * MIGRATION - p->on_rq == TASK_ON_RQ_MIGRATING (used for DEADLINE)
+ *
  * ENQUEUE_HEAD      - place at front of runqueue (tail if not specified)
  * ENQUEUE_REPLENISH - CBS (replenish runtime and postpone deadline)
  * ENQUEUE_MIGRATED  - the task was migrated during wakeup
@@ -2189,6 +2229,7 @@ extern const u32		sched_prio_to_wmult[40];
 #define DEQUEUE_SAVE		0x02 /* Matches ENQUEUE_RESTORE */
 #define DEQUEUE_MOVE		0x04 /* Matches ENQUEUE_MOVE */
 #define DEQUEUE_NOCLOCK		0x08 /* Matches ENQUEUE_NOCLOCK */
+#define DEQUEUE_MIGRATING	0x100 /* Matches ENQUEUE_MIGRATING */
 
 #define ENQUEUE_WAKEUP		0x01
 #define ENQUEUE_RESTORE		0x02
@@ -2203,6 +2244,7 @@ extern const u32		sched_prio_to_wmult[40];
 #define ENQUEUE_MIGRATED	0x00
 #endif
 #define ENQUEUE_INITIAL		0x80
+#define ENQUEUE_MIGRATING	0x100
 
 #define RETRY_TASK		((void *)-1UL)
 
@@ -2212,6 +2254,8 @@ struct affinity_context {
 	unsigned int flags;
 };
 
+extern s64 update_curr_common(struct rq *rq);
+
 struct sched_class {
 
 #ifdef CONFIG_UCLAMP_TASK
@@ -2425,8 +2469,7 @@ extern struct rt_bandwidth def_rt_bandwidth;
 extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
 extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
 
-extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
-extern void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se);
+extern void init_dl_entity(struct sched_dl_entity *dl_se);
 
 #define BW_SHIFT		20
 #define BW_UNIT			(1 << BW_SHIFT)
@@ -2822,6 +2865,7 @@ DEFINE_LOCK_GUARD_2(double_rq_lock, struct rq,
 		    double_rq_lock(_T->lock, _T->lock2),
 		    double_rq_unlock(_T->lock, _T->lock2))
 
+extern struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq);
 extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq);
 extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq);
 
@@ -2961,24 +3005,14 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #endif
 
 #ifdef CONFIG_SMP
-/**
- * enum cpu_util_type - CPU utilization type
- * @FREQUENCY_UTIL:	Utilization used to select frequency
- * @ENERGY_UTIL:	Utilization used during energy calculation
- *
- * The utilization signals of all scheduling classes (CFS/RT/DL) and IRQ time
- * need to be aggregated differently depending on the usage made of them. This
- * enum is used within effective_cpu_util() to differentiate the types of
- * utilization expected by the callers, and adjust the aggregation accordingly.
- */
-enum cpu_util_type {
-	FREQUENCY_UTIL,
-	ENERGY_UTIL,
-};
-
 unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
-				 enum cpu_util_type type,
-				 struct task_struct *p);
+				 unsigned long *min,
+				 unsigned long *max);
+
+unsigned long sugov_effective_cpu_perf(int cpu, unsigned long actual,
+				 unsigned long min,
+				 unsigned long max);
+
 
 /*
  * Verify the fitness of task @p to run on @cpu taking into account the
@@ -3035,59 +3069,6 @@ static inline bool uclamp_rq_is_idle(struct rq *rq)
 	return rq->uclamp_flags & UCLAMP_FLAG_IDLE;
 }
 
-/**
- * uclamp_rq_util_with - clamp @util with @rq and @p effective uclamp values.
- * @rq:		The rq to clamp against. Must not be NULL.
- * @util:	The util value to clamp.
- * @p:		The task to clamp against. Can be NULL if you want to clamp
- *		against @rq only.
- *
- * Clamps the passed @util to the max(@rq, @p) effective uclamp values.
- *
- * If sched_uclamp_used static key is disabled, then just return the util
- * without any clamping since uclamp aggregation at the rq level in the fast
- * path is disabled, rendering this operation a NOP.
- *
- * Use uclamp_eff_value() if you don't care about uclamp values at rq level. It
- * will return the correct effective uclamp value of the task even if the
- * static key is disabled.
- */
-static __always_inline
-unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
-				  struct task_struct *p)
-{
-	unsigned long min_util = 0;
-	unsigned long max_util = 0;
-
-	if (!static_branch_likely(&sched_uclamp_used))
-		return util;
-
-	if (p) {
-		min_util = uclamp_eff_value(p, UCLAMP_MIN);
-		max_util = uclamp_eff_value(p, UCLAMP_MAX);
-
-		/*
-		 * Ignore last runnable task's max clamp, as this task will
-		 * reset it. Similarly, no need to read the rq's min clamp.
-		 */
-		if (uclamp_rq_is_idle(rq))
-			goto out;
-	}
-
-	min_util = max_t(unsigned long, min_util, uclamp_rq_get(rq, UCLAMP_MIN));
-	max_util = max_t(unsigned long, max_util, uclamp_rq_get(rq, UCLAMP_MAX));
-out:
-	/*
-	 * Since CPU's {min,max}_util clamps are MAX aggregated considering
-	 * RUNNABLE tasks with _different_ clamps, we can end up with an
-	 * inversion. Fix it now when the clamps are applied.
-	 */
-	if (unlikely(min_util >= max_util))
-		return min_util;
-
-	return clamp(util, min_util, max_util);
-}
-
 /* Is the rq being capped/throttled by uclamp_max? */
 static inline bool uclamp_rq_is_capped(struct rq *rq)
 {
@@ -3125,13 +3106,6 @@ static inline unsigned long uclamp_eff_value(struct task_struct *p,
 	return SCHED_CAPACITY_SCALE;
 }
 
-static inline
-unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
-				  struct task_struct *p)
-{
-	return util;
-}
-
 static inline bool uclamp_rq_is_capped(struct rq *rq) { return false; }
 
 static inline bool uclamp_is_used(void)
@@ -3261,16 +3235,6 @@ extern int sched_dynamic_mode(const char *str);
 extern void sched_dynamic_update(int mode);
 #endif
 
-static inline void update_current_exec_runtime(struct task_struct *curr,
-						u64 now, u64 delta_exec)
-{
-	curr->se.sum_exec_runtime += delta_exec;
-	account_group_exec_runtime(curr, delta_exec);
-
-	curr->se.exec_start = now;
-	cgroup_account_cputime(curr, delta_exec);
-}
-
 #ifdef CONFIG_SCHED_MM_CID
 
 #define SCHED_MM_CID_PERIOD_NS	(100ULL * 1000000)	/* 100ms */
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 6cf7304e6449..b1b8fe61c532 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -70,18 +70,7 @@ static void yield_task_stop(struct rq *rq)
 
 static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
 {
-	struct task_struct *curr = rq->curr;
-	u64 now, delta_exec;
-
-	now = rq_clock_task(rq);
-	delta_exec = now - curr->se.exec_start;
-	if (unlikely((s64)delta_exec < 0))
-		delta_exec = 0;
-
-	schedstat_set(curr->stats.exec_max,
-		      max(curr->stats.exec_max, delta_exec));
-
-	update_current_exec_runtime(curr, now, delta_exec);
+	update_curr_common(rq);
 }
 
 /*
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 255999ba9190..aca7b437882e 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -1072,7 +1072,7 @@ static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd, struct seccomp_kn
 	 */
 	list_del_init(&addfd->list);
 	if (!addfd->setfd)
-		fd = receive_fd(addfd->file, addfd->flags);
+		fd = receive_fd(addfd->file, NULL, addfd->flags);
 	else
 		fd = receive_fd_replace(addfd->fd, addfd->file, addfd->flags);
 	addfd->ret = fd;
diff --git a/kernel/signal.c b/kernel/signal.c
index 47a7602dfe8d..c9c57d053ce4 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -171,16 +171,6 @@ static bool recalc_sigpending_tsk(struct task_struct *t)
 	return false;
 }
 
-/*
- * After recalculating TIF_SIGPENDING, we need to make sure the task wakes up.
- * This is superfluous when called on current, the wakeup is a harmless no-op.
- */
-void recalc_sigpending_and_wake(struct task_struct *t)
-{
-	if (recalc_sigpending_tsk(t))
-		signal_wake_up(t, 0);
-}
-
 void recalc_sigpending(void)
 {
 	if (!recalc_sigpending_tsk(current) && !freezing(current))
@@ -1348,10 +1338,8 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t,
 		action->sa.sa_handler = SIG_DFL;
 		if (handler == HANDLER_EXIT)
 			action->sa.sa_flags |= SA_IMMUTABLE;
-		if (blocked) {
+		if (blocked)
 			sigdelset(&t->blocked, sig);
-			recalc_sigpending_and_wake(t);
-		}
 	}
 	/*
 	 * Don't clear SIGNAL_UNKILLABLE for traced tasks, users won't expect
@@ -1361,6 +1349,9 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t,
 	    (!t->ptrace || (handler == HANDLER_EXIT)))
 		t->signal->flags &= ~SIGNAL_UNKILLABLE;
 	ret = send_signal_locked(sig, info, t, PIDTYPE_PID);
+	/* This can happen if the signal was already pending and blocked */
+	if (!task_sigpending(t))
+		signal_wake_up(t, 0);
 	spin_unlock_irqrestore(&t->sighand->siglock, flags);
 
 	return ret;
@@ -1376,12 +1367,12 @@ int force_sig_info(struct kernel_siginfo *info)
  */
 int zap_other_threads(struct task_struct *p)
 {
-	struct task_struct *t = p;
+	struct task_struct *t;
 	int count = 0;
 
 	p->signal->group_stop_count = 0;
 
-	while_each_thread(p, t) {
+	for_other_threads(p, t) {
 		task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
 		/* Don't require de_thread to wait for the vhost_worker */
 		if ((t->flags & (PF_IO_WORKER | PF_USER_WORKER)) != PF_USER_WORKER)
@@ -2465,12 +2456,10 @@ static bool do_signal_stop(int signr)
 			sig->group_exit_code = signr;
 
 		sig->group_stop_count = 0;
-
 		if (task_set_jobctl_pending(current, signr | gstop))
 			sig->group_stop_count++;
 
-		t = current;
-		while_each_thread(current, t) {
+		for_other_threads(current, t) {
 			/*
 			 * Setting state to TASK_STOPPED for a group
 			 * stop is always done with the siglock held,
@@ -2966,8 +2955,7 @@ static void retarget_shared_pending(struct task_struct *tsk, sigset_t *which)
 	if (sigisemptyset(&retarget))
 		return;
 
-	t = tsk;
-	while_each_thread(tsk, t) {
+	for_other_threads(tsk, t) {
 		if (t->flags & PF_EXITING)
 			continue;
 
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index 4f65824879ab..afb3c116da91 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -126,7 +126,7 @@ EXPORT_SYMBOL_GPL(stack_trace_save);
 
 /**
  * stack_trace_save_tsk - Save a task stack trace into a storage array
- * @task:	The task to examine
+ * @tsk:	The task to examine
  * @store:	Pointer to storage array
  * @size:	Size of the storage array
  * @skipnr:	Number of entries to skip at the start of the stack trace
diff --git a/kernel/sys.c b/kernel/sys.c
index 420d9cb9cc8e..e219fcfa112d 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2394,6 +2394,10 @@ static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3,
 	if (bits & PR_MDWE_NO_INHERIT && !(bits & PR_MDWE_REFUSE_EXEC_GAIN))
 		return -EINVAL;
 
+	/* PARISC cannot allow mdwe as it needs writable stacks */
+	if (IS_ENABLED(CONFIG_PARISC))
+		return -EINVAL;
+
 	current_bits = get_current_mdwe();
 	if (current_bits && current_bits != bits)
 		return -EPERM; /* Cannot unset the flags */
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index e1a6e3c675c0..faad00cce269 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -171,6 +171,9 @@ COND_SYSCALL(landlock_add_rule);
 COND_SYSCALL(landlock_restrict_self);
 COND_SYSCALL(fadvise64_64);
 COND_SYSCALL_COMPAT(fadvise64_64);
+COND_SYSCALL(lsm_get_self_attr);
+COND_SYSCALL(lsm_set_self_attr);
+COND_SYSCALL(lsm_list_modules);
 
 /* CONFIG_MMU only */
 COND_SYSCALL(swapon);
@@ -201,6 +204,20 @@ COND_SYSCALL(recvmmsg_time32);
 COND_SYSCALL_COMPAT(recvmmsg_time32);
 COND_SYSCALL_COMPAT(recvmmsg_time64);
 
+/* Posix timer syscalls may be configured out */
+COND_SYSCALL(timer_create);
+COND_SYSCALL(timer_gettime);
+COND_SYSCALL(timer_getoverrun);
+COND_SYSCALL(timer_settime);
+COND_SYSCALL(timer_delete);
+COND_SYSCALL(clock_adjtime);
+COND_SYSCALL(getitimer);
+COND_SYSCALL(setitimer);
+COND_SYSCALL(alarm);
+COND_SYSCALL_COMPAT(timer_create);
+COND_SYSCALL_COMPAT(getitimer);
+COND_SYSCALL_COMPAT(setitimer);
+
 /*
  * Architecture specific syscalls: see further below
  */
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 238262e4aba7..760793998cdd 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -2219,29 +2219,22 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
 	}
 }
 
-int hrtimers_dead_cpu(unsigned int scpu)
+int hrtimers_cpu_dying(unsigned int dying_cpu)
 {
 	struct hrtimer_cpu_base *old_base, *new_base;
-	int i;
+	int i, ncpu = cpumask_first(cpu_active_mask);
 
-	BUG_ON(cpu_online(scpu));
-	tick_cancel_sched_timer(scpu);
+	tick_cancel_sched_timer(dying_cpu);
+
+	old_base = this_cpu_ptr(&hrtimer_bases);
+	new_base = &per_cpu(hrtimer_bases, ncpu);
 
-	/*
-	 * this BH disable ensures that raise_softirq_irqoff() does
-	 * not wakeup ksoftirqd (and acquire the pi-lock) while
-	 * holding the cpu_base lock
-	 */
-	local_bh_disable();
-	local_irq_disable();
-	old_base = &per_cpu(hrtimer_bases, scpu);
-	new_base = this_cpu_ptr(&hrtimer_bases);
 	/*
 	 * The caller is globally serialized and nobody else
 	 * takes two locks at once, deadlock is not possible.
 	 */
-	raw_spin_lock(&new_base->lock);
-	raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
+	raw_spin_lock(&old_base->lock);
+	raw_spin_lock_nested(&new_base->lock, SINGLE_DEPTH_NESTING);
 
 	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
 		migrate_hrtimer_list(&old_base->clock_base[i],
@@ -2252,15 +2245,13 @@ int hrtimers_dead_cpu(unsigned int scpu)
 	 * The migration might have changed the first expiring softirq
 	 * timer on this CPU. Update it.
 	 */
-	hrtimer_update_softirq_timer(new_base, false);
+	__hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT);
+	/* Tell the other CPU to retrigger the next event */
+	smp_call_function_single(ncpu, retrigger_next_event, NULL, 0);
 
-	raw_spin_unlock(&old_base->lock);
 	raw_spin_unlock(&new_base->lock);
+	raw_spin_unlock(&old_base->lock);
 
-	/* Check, if we got expired work to do */
-	__hrtimer_peek_ahead_timers();
-	local_irq_enable();
-	local_bh_enable();
 	return 0;
 }
 
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index 828aeecbd1e8..9b6fcb8d85e7 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -17,40 +17,6 @@
 #include <linux/time_namespace.h>
 #include <linux/compat.h>
 
-#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
-/* Architectures may override SYS_NI and COMPAT_SYS_NI */
-#include <asm/syscall_wrapper.h>
-#endif
-
-asmlinkage long sys_ni_posix_timers(void)
-{
-	pr_err_once("process %d (%s) attempted a POSIX timer syscall "
-		    "while CONFIG_POSIX_TIMERS is not set\n",
-		    current->pid, current->comm);
-	return -ENOSYS;
-}
-
-#ifndef SYS_NI
-#define SYS_NI(name)  SYSCALL_ALIAS(sys_##name, sys_ni_posix_timers)
-#endif
-
-#ifndef COMPAT_SYS_NI
-#define COMPAT_SYS_NI(name)  SYSCALL_ALIAS(compat_sys_##name, sys_ni_posix_timers)
-#endif
-
-SYS_NI(timer_create);
-SYS_NI(timer_gettime);
-SYS_NI(timer_getoverrun);
-SYS_NI(timer_settime);
-SYS_NI(timer_delete);
-SYS_NI(clock_adjtime);
-SYS_NI(getitimer);
-SYS_NI(setitimer);
-SYS_NI(clock_adjtime32);
-#ifdef __ARCH_WANT_SYS_ALARM
-SYS_NI(alarm);
-#endif
-
 /*
  * We preserve minimal support for CLOCK_REALTIME and CLOCK_MONOTONIC
  * as it is easy to remain compatible with little code. CLOCK_BOOTTIME
@@ -158,18 +124,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 				 which_clock);
 }
 
-#ifdef CONFIG_COMPAT
-COMPAT_SYS_NI(timer_create);
-#endif
-
-#if defined(CONFIG_COMPAT) || defined(CONFIG_ALPHA)
-COMPAT_SYS_NI(getitimer);
-COMPAT_SYS_NI(setitimer);
-#endif
-
 #ifdef CONFIG_COMPAT_32BIT_TIME
-SYS_NI(timer_settime32);
-SYS_NI(timer_gettime32);
 
 SYSCALL_DEFINE2(clock_settime32, const clockid_t, which_clock,
 		struct old_timespec32 __user *, tp)
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 649f2b48e8f0..481b7ab65e2c 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -56,7 +56,6 @@ extern int clockevents_program_event(struct clock_event_device *dev,
 				     ktime_t expires, bool force);
 extern void clockevents_handle_noop(struct clock_event_device *dev);
 extern int __clockevents_update_freq(struct clock_event_device *dev, u32 freq);
-extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt);
 
 /* Broadcasting support */
 # ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
@@ -197,3 +196,5 @@ void hrtimers_resume_local(void);
 #else
 #define JIFFIES_SHIFT	8
 #endif
+
+extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index be77b021e5d6..a17d26002831 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -839,6 +839,10 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
 		ts->next_timer = next_tick;
 	}
 
+	/* Make sure next_tick is never before basemono! */
+	if (WARN_ON_ONCE(basemono > next_tick))
+		next_tick = basemono;
+
 	/*
 	 * If the tick is due in the next period, keep it ticking or
 	 * force prod the timer.
@@ -887,7 +891,6 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
 	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
 	u64 basemono = ts->timer_expires_base;
 	u64 expires = ts->timer_expires;
-	ktime_t tick = expires;
 
 	/* Make sure we won't be trying to stop it twice in a row. */
 	ts->timer_expires_base = 0;
@@ -910,7 +913,7 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
 	/* Skip reprogram of event if it's not changed */
 	if (ts->tick_stopped && (expires == ts->next_tick)) {
 		/* Sanity check: make sure clockevent is actually programmed */
-		if (tick == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer))
+		if (expires == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer))
 			return;
 
 		WARN_ON_ONCE(1);
@@ -920,11 +923,11 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
 	}
 
 	/*
-	 * nohz_stop_sched_tick() can be called several times before
-	 * nohz_restart_sched_tick() is called. This happens when
-	 * interrupts arrive which do not cause a reschedule. In the
-	 * first call we save the current tick time, so we can restart
-	 * the scheduler tick in nohz_restart_sched_tick().
+	 * tick_nohz_stop_tick() can be called several times before
+	 * tick_nohz_restart_sched_tick() is called. This happens when
+	 * interrupts arrive which do not cause a reschedule. In the first
+	 * call we save the current tick time, so we can restart the
+	 * scheduler tick in tick_nohz_restart_sched_tick().
 	 */
 	if (!ts->tick_stopped) {
 		calc_load_nohz_start();
@@ -935,7 +938,7 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
 		trace_tick_stop(1, TICK_DEP_MASK_NONE);
 	}
 
-	ts->next_tick = tick;
+	ts->next_tick = expires;
 
 	/*
 	 * If the expiration time == KTIME_MAX, then we simply stop
@@ -950,11 +953,11 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
 	}
 
 	if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
-		hrtimer_start(&ts->sched_timer, tick,
+		hrtimer_start(&ts->sched_timer, expires,
 			      HRTIMER_MODE_ABS_PINNED_HARD);
 	} else {
-		hrtimer_set_expires(&ts->sched_timer, tick);
-		tick_program_event(tick, 1);
+		hrtimer_set_expires(&ts->sched_timer, expires);
+		tick_program_event(expires, 1);
 	}
 }
 
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 63a8ce7177dd..352b161113cd 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -571,18 +571,15 @@ static int calc_wheel_index(unsigned long expires, unsigned long clk,
 static void
 trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer)
 {
-	if (!is_timers_nohz_active())
-		return;
-
 	/*
-	 * TODO: This wants some optimizing similar to the code below, but we
-	 * will do that when we switch from push to pull for deferrable timers.
+	 * Deferrable timers do not prevent the CPU from entering dynticks and
+	 * are not taken into account on the idle/nohz_full path. An IPI when a
+	 * new deferrable timer is enqueued will wake up the remote CPU but
+	 * nothing will be done with the deferrable timer base. Therefore skip
+	 * the remote IPI for deferrable timers completely.
 	 */
-	if (timer->flags & TIMER_DEFERRABLE) {
-		if (tick_nohz_full_cpu(base->cpu))
-			wake_up_nohz_cpu(base->cpu);
+	if (!is_timers_nohz_active() || timer->flags & TIMER_DEFERRABLE)
 		return;
-	}
 
 	/*
 	 * We might have to IPI the remote CPU if the base is idle and the
@@ -606,7 +603,7 @@ static void enqueue_timer(struct timer_base *base, struct timer_list *timer,
 	__set_bit(idx, base->pending_map);
 	timer_set_idx(timer, idx);
 
-	trace_timer_start(timer, timer->expires, timer->flags);
+	trace_timer_start(timer, bucket_expiry);
 
 	/*
 	 * Check whether this is the new first expiring timer. The
@@ -942,31 +939,34 @@ get_target_base(struct timer_base *base, unsigned tflags)
 	return get_timer_this_cpu_base(tflags);
 }
 
-static inline void forward_timer_base(struct timer_base *base)
+static inline void __forward_timer_base(struct timer_base *base,
+					unsigned long basej)
 {
-	unsigned long jnow = READ_ONCE(jiffies);
-
 	/*
-	 * No need to forward if we are close enough below jiffies.
-	 * Also while executing timers, base->clk is 1 offset ahead
-	 * of jiffies to avoid endless requeuing to current jiffies.
+	 * Check whether we can forward the base. We can only do that when
+	 * @basej is past base->clk otherwise we might rewind base->clk.
 	 */
-	if ((long)(jnow - base->clk) < 1)
+	if (time_before_eq(basej, base->clk))
 		return;
 
 	/*
 	 * If the next expiry value is > jiffies, then we fast forward to
 	 * jiffies otherwise we forward to the next expiry value.
 	 */
-	if (time_after(base->next_expiry, jnow)) {
-		base->clk = jnow;
+	if (time_after(base->next_expiry, basej)) {
+		base->clk = basej;
 	} else {
 		if (WARN_ON_ONCE(time_before(base->next_expiry, base->clk)))
 			return;
 		base->clk = base->next_expiry;
 	}
+
 }
 
+static inline void forward_timer_base(struct timer_base *base)
+{
+	__forward_timer_base(base, READ_ONCE(jiffies));
+}
 
 /*
  * We are using hashed locking: Holding per_cpu(timer_bases[x]).lock means
@@ -1803,8 +1803,10 @@ static int next_pending_bucket(struct timer_base *base, unsigned offset,
 /*
  * Search the first expiring timer in the various clock levels. Caller must
  * hold base->lock.
+ *
+ * Store next expiry time in base->next_expiry.
  */
-static unsigned long __next_timer_interrupt(struct timer_base *base)
+static void next_expiry_recalc(struct timer_base *base)
 {
 	unsigned long clk, next, adj;
 	unsigned lvl, offset = 0;
@@ -1870,10 +1872,9 @@ static unsigned long __next_timer_interrupt(struct timer_base *base)
 		clk += adj;
 	}
 
+	base->next_expiry = next;
 	base->next_expiry_recalc = false;
 	base->timers_pending = !(next == base->clk + NEXT_TIMER_MAX_DELTA);
-
-	return next;
 }
 
 #ifdef CONFIG_NO_HZ_COMMON
@@ -1921,8 +1922,9 @@ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires)
 u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 {
 	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
+	unsigned long nextevt = basej + NEXT_TIMER_MAX_DELTA;
 	u64 expires = KTIME_MAX;
-	unsigned long nextevt;
+	bool was_idle;
 
 	/*
 	 * Pretend that there is no timer pending if the cpu is offline.
@@ -1933,37 +1935,44 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 
 	raw_spin_lock(&base->lock);
 	if (base->next_expiry_recalc)
-		base->next_expiry = __next_timer_interrupt(base);
-	nextevt = base->next_expiry;
+		next_expiry_recalc(base);
 
 	/*
 	 * We have a fresh next event. Check whether we can forward the
-	 * base. We can only do that when @basej is past base->clk
-	 * otherwise we might rewind base->clk.
+	 * base.
 	 */
-	if (time_after(basej, base->clk)) {
-		if (time_after(nextevt, basej))
-			base->clk = basej;
-		else if (time_after(nextevt, base->clk))
-			base->clk = nextevt;
-	}
+	__forward_timer_base(base, basej);
 
-	if (time_before_eq(nextevt, basej)) {
-		expires = basem;
-		base->is_idle = false;
+	if (base->timers_pending) {
+		nextevt = base->next_expiry;
+
+		/* If we missed a tick already, force 0 delta */
+		if (time_before(nextevt, basej))
+			nextevt = basej;
+		expires = basem + (u64)(nextevt - basej) * TICK_NSEC;
 	} else {
-		if (base->timers_pending)
-			expires = basem + (u64)(nextevt - basej) * TICK_NSEC;
 		/*
-		 * If we expect to sleep more than a tick, mark the base idle.
-		 * Also the tick is stopped so any added timer must forward
-		 * the base clk itself to keep granularity small. This idle
-		 * logic is only maintained for the BASE_STD base, deferrable
-		 * timers may still see large granularity skew (by design).
+		 * Move next_expiry for the empty base into the future to
+		 * prevent a unnecessary raise of the timer softirq when the
+		 * next_expiry value will be reached even if there is no timer
+		 * pending.
 		 */
-		if ((expires - basem) > TICK_NSEC)
-			base->is_idle = true;
+		base->next_expiry = nextevt;
 	}
+
+	/*
+	 * Base is idle if the next event is more than a tick away.
+	 *
+	 * If the base is marked idle then any timer add operation must forward
+	 * the base clk itself to keep granularity small. This idle logic is
+	 * only maintained for the BASE_STD base, deferrable timers may still
+	 * see large granularity skew (by design).
+	 */
+	was_idle = base->is_idle;
+	base->is_idle = time_after(nextevt, basej + 1);
+	if (was_idle != base->is_idle)
+		trace_timer_base_idle(base->is_idle, base->cpu);
+
 	raw_spin_unlock(&base->lock);
 
 	return cmp_next_hrtimer_event(basem, expires);
@@ -1984,7 +1993,10 @@ void timer_clear_idle(void)
 	 * sending the IPI a few instructions smaller for the cost of taking
 	 * the lock in the exit from idle path.
 	 */
-	base->is_idle = false;
+	if (base->is_idle) {
+		base->is_idle = false;
+		trace_timer_base_idle(false, smp_processor_id());
+	}
 }
 #endif
 
@@ -2015,8 +2027,12 @@ static inline void __run_timers(struct timer_base *base)
 		 */
 		WARN_ON_ONCE(!levels && !base->next_expiry_recalc
 			     && base->timers_pending);
+		/*
+		 * While executing timers, base->clk is set 1 offset ahead of
+		 * jiffies to avoid endless requeuing to current jiffies.
+		 */
 		base->clk++;
-		base->next_expiry = __next_timer_interrupt(base);
+		next_expiry_recalc(base);
 
 		while (levels--)
 			expire_timers(base, heads + levels);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 84e8a0f6e4e0..7ac6c52b25eb 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -24,6 +24,7 @@
 #include <linux/key.h>
 #include <linux/verification.h>
 #include <linux/namei.h>
+#include <linux/fileattr.h>
 
 #include <net/bpf_sk_storage.h>
 
@@ -41,6 +42,9 @@
 #define bpf_event_rcu_dereference(p)					\
 	rcu_dereference_protected(p, lockdep_is_held(&bpf_event_mutex))
 
+#define MAX_UPROBE_MULTI_CNT (1U << 20)
+#define MAX_KPROBE_MULTI_CNT (1U << 20)
+
 #ifdef CONFIG_MODULES
 struct bpf_trace_module {
 	struct module *module;
@@ -1376,6 +1380,8 @@ __bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr,
 			       struct bpf_dynptr_kern *sig_ptr,
 			       struct bpf_key *trusted_keyring)
 {
+	const void *data, *sig;
+	u32 data_len, sig_len;
 	int ret;
 
 	if (trusted_keyring->has_ref) {
@@ -1392,10 +1398,12 @@ __bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr,
 			return ret;
 	}
 
-	return verify_pkcs7_signature(data_ptr->data,
-				      __bpf_dynptr_size(data_ptr),
-				      sig_ptr->data,
-				      __bpf_dynptr_size(sig_ptr),
+	data_len = __bpf_dynptr_size(data_ptr);
+	data = __bpf_dynptr_data(data_ptr, data_len);
+	sig_len = __bpf_dynptr_size(sig_ptr);
+	sig = __bpf_dynptr_data(sig_ptr, sig_len);
+
+	return verify_pkcs7_signature(data, data_len, sig, sig_len,
 				      trusted_keyring->key,
 				      VERIFYING_UNSPECIFIED_SIGNATURE, NULL,
 				      NULL);
@@ -1427,6 +1435,72 @@ static int __init bpf_key_sig_kfuncs_init(void)
 late_initcall(bpf_key_sig_kfuncs_init);
 #endif /* CONFIG_KEYS */
 
+/* filesystem kfuncs */
+__bpf_kfunc_start_defs();
+
+/**
+ * bpf_get_file_xattr - get xattr of a file
+ * @file: file to get xattr from
+ * @name__str: name of the xattr
+ * @value_ptr: output buffer of the xattr value
+ *
+ * Get xattr *name__str* of *file* and store the output in *value_ptr*.
+ *
+ * For security reasons, only *name__str* with prefix "user." is allowed.
+ *
+ * Return: 0 on success, a negative value on error.
+ */
+__bpf_kfunc int bpf_get_file_xattr(struct file *file, const char *name__str,
+				   struct bpf_dynptr_kern *value_ptr)
+{
+	struct dentry *dentry;
+	u32 value_len;
+	void *value;
+	int ret;
+
+	if (strncmp(name__str, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN))
+		return -EPERM;
+
+	value_len = __bpf_dynptr_size(value_ptr);
+	value = __bpf_dynptr_data_rw(value_ptr, value_len);
+	if (!value)
+		return -EINVAL;
+
+	dentry = file_dentry(file);
+	ret = inode_permission(&nop_mnt_idmap, dentry->d_inode, MAY_READ);
+	if (ret)
+		return ret;
+	return __vfs_getxattr(dentry, dentry->d_inode, name__str, value, value_len);
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_SET8_START(fs_kfunc_set_ids)
+BTF_ID_FLAGS(func, bpf_get_file_xattr, KF_SLEEPABLE | KF_TRUSTED_ARGS)
+BTF_SET8_END(fs_kfunc_set_ids)
+
+static int bpf_get_file_xattr_filter(const struct bpf_prog *prog, u32 kfunc_id)
+{
+	if (!btf_id_set8_contains(&fs_kfunc_set_ids, kfunc_id))
+		return 0;
+
+	/* Only allow to attach from LSM hooks, to avoid recursion */
+	return prog->type != BPF_PROG_TYPE_LSM ? -EACCES : 0;
+}
+
+static const struct btf_kfunc_id_set bpf_fs_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set = &fs_kfunc_set_ids,
+	.filter = bpf_get_file_xattr_filter,
+};
+
+static int __init bpf_fs_kfuncs_init(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_LSM, &bpf_fs_kfunc_set);
+}
+
+late_initcall(bpf_fs_kfuncs_init);
+
 static const struct bpf_func_proto *
 bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -2899,6 +2973,8 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	cnt = attr->link_create.kprobe_multi.cnt;
 	if (!cnt)
 		return -EINVAL;
+	if (cnt > MAX_KPROBE_MULTI_CNT)
+		return -E2BIG;
 
 	size = cnt * sizeof(*addrs);
 	addrs = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL);
@@ -3029,6 +3105,7 @@ struct bpf_uprobe_multi_link;
 struct bpf_uprobe {
 	struct bpf_uprobe_multi_link *link;
 	loff_t offset;
+	unsigned long ref_ctr_offset;
 	u64 cookie;
 	struct uprobe_consumer consumer;
 };
@@ -3037,6 +3114,7 @@ struct bpf_uprobe_multi_link {
 	struct path path;
 	struct bpf_link link;
 	u32 cnt;
+	u32 flags;
 	struct bpf_uprobe *uprobes;
 	struct task_struct *task;
 };
@@ -3078,9 +3156,79 @@ static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link)
 	kfree(umulti_link);
 }
 
+static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link,
+						struct bpf_link_info *info)
+{
+	u64 __user *uref_ctr_offsets = u64_to_user_ptr(info->uprobe_multi.ref_ctr_offsets);
+	u64 __user *ucookies = u64_to_user_ptr(info->uprobe_multi.cookies);
+	u64 __user *uoffsets = u64_to_user_ptr(info->uprobe_multi.offsets);
+	u64 __user *upath = u64_to_user_ptr(info->uprobe_multi.path);
+	u32 upath_size = info->uprobe_multi.path_size;
+	struct bpf_uprobe_multi_link *umulti_link;
+	u32 ucount = info->uprobe_multi.count;
+	int err = 0, i;
+	long left;
+
+	if (!upath ^ !upath_size)
+		return -EINVAL;
+
+	if ((uoffsets || uref_ctr_offsets || ucookies) && !ucount)
+		return -EINVAL;
+
+	umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
+	info->uprobe_multi.count = umulti_link->cnt;
+	info->uprobe_multi.flags = umulti_link->flags;
+	info->uprobe_multi.pid = umulti_link->task ?
+				 task_pid_nr_ns(umulti_link->task, task_active_pid_ns(current)) : 0;
+
+	if (upath) {
+		char *p, *buf;
+
+		upath_size = min_t(u32, upath_size, PATH_MAX);
+
+		buf = kmalloc(upath_size, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+		p = d_path(&umulti_link->path, buf, upath_size);
+		if (IS_ERR(p)) {
+			kfree(buf);
+			return PTR_ERR(p);
+		}
+		upath_size = buf + upath_size - p;
+		left = copy_to_user(upath, p, upath_size);
+		kfree(buf);
+		if (left)
+			return -EFAULT;
+		info->uprobe_multi.path_size = upath_size;
+	}
+
+	if (!uoffsets && !ucookies && !uref_ctr_offsets)
+		return 0;
+
+	if (ucount < umulti_link->cnt)
+		err = -ENOSPC;
+	else
+		ucount = umulti_link->cnt;
+
+	for (i = 0; i < ucount; i++) {
+		if (uoffsets &&
+		    put_user(umulti_link->uprobes[i].offset, uoffsets + i))
+			return -EFAULT;
+		if (uref_ctr_offsets &&
+		    put_user(umulti_link->uprobes[i].ref_ctr_offset, uref_ctr_offsets + i))
+			return -EFAULT;
+		if (ucookies &&
+		    put_user(umulti_link->uprobes[i].cookie, ucookies + i))
+			return -EFAULT;
+	}
+
+	return err;
+}
+
 static const struct bpf_link_ops bpf_uprobe_multi_link_lops = {
 	.release = bpf_uprobe_multi_link_release,
 	.dealloc = bpf_uprobe_multi_link_dealloc,
+	.fill_link_info = bpf_uprobe_multi_link_fill_link_info,
 };
 
 static int uprobe_prog_run(struct bpf_uprobe *uprobe,
@@ -3168,7 +3316,6 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 {
 	struct bpf_uprobe_multi_link *link = NULL;
 	unsigned long __user *uref_ctr_offsets;
-	unsigned long *ref_ctr_offsets = NULL;
 	struct bpf_link_primer link_primer;
 	struct bpf_uprobe *uprobes = NULL;
 	struct task_struct *task = NULL;
@@ -3202,6 +3349,8 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 
 	if (!upath || !uoffsets || !cnt)
 		return -EINVAL;
+	if (cnt > MAX_UPROBE_MULTI_CNT)
+		return -E2BIG;
 
 	uref_ctr_offsets = u64_to_user_ptr(attr->link_create.uprobe_multi.ref_ctr_offsets);
 	ucookies = u64_to_user_ptr(attr->link_create.uprobe_multi.cookies);
@@ -3241,22 +3390,20 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	if (!uprobes || !link)
 		goto error_free;
 
-	if (uref_ctr_offsets) {
-		ref_ctr_offsets = kvcalloc(cnt, sizeof(*ref_ctr_offsets), GFP_KERNEL);
-		if (!ref_ctr_offsets)
-			goto error_free;
-	}
-
 	for (i = 0; i < cnt; i++) {
-		if (ucookies && __get_user(uprobes[i].cookie, ucookies + i)) {
+		if (__get_user(uprobes[i].offset, uoffsets + i)) {
 			err = -EFAULT;
 			goto error_free;
 		}
-		if (uref_ctr_offsets && __get_user(ref_ctr_offsets[i], uref_ctr_offsets + i)) {
+		if (uprobes[i].offset < 0) {
+			err = -EINVAL;
+			goto error_free;
+		}
+		if (uref_ctr_offsets && __get_user(uprobes[i].ref_ctr_offset, uref_ctr_offsets + i)) {
 			err = -EFAULT;
 			goto error_free;
 		}
-		if (__get_user(uprobes[i].offset, uoffsets + i)) {
+		if (ucookies && __get_user(uprobes[i].cookie, ucookies + i)) {
 			err = -EFAULT;
 			goto error_free;
 		}
@@ -3276,6 +3423,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	link->uprobes = uprobes;
 	link->path = path;
 	link->task = task;
+	link->flags = flags;
 
 	bpf_link_init(&link->link, BPF_LINK_TYPE_UPROBE_MULTI,
 		      &bpf_uprobe_multi_link_lops, prog);
@@ -3283,7 +3431,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	for (i = 0; i < cnt; i++) {
 		err = uprobe_register_refctr(d_real_inode(link->path.dentry),
 					     uprobes[i].offset,
-					     ref_ctr_offsets ? ref_ctr_offsets[i] : 0,
+					     uprobes[i].ref_ctr_offset,
 					     &uprobes[i].consumer);
 		if (err) {
 			bpf_uprobe_unregister(&path, uprobes, i);
@@ -3295,11 +3443,9 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	if (err)
 		goto error_free;
 
-	kvfree(ref_ctr_offsets);
 	return bpf_link_settle(&link_primer);
 
 error_free:
-	kvfree(ref_ctr_offsets);
 	kvfree(uprobes);
 	kfree(link);
 	if (task)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 8de8bec5f366..b01ae7d36021 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1183,18 +1183,19 @@ static void __add_hash_entry(struct ftrace_hash *hash,
 	hash->count++;
 }
 
-static int add_hash_entry(struct ftrace_hash *hash, unsigned long ip)
+static struct ftrace_func_entry *
+add_hash_entry(struct ftrace_hash *hash, unsigned long ip)
 {
 	struct ftrace_func_entry *entry;
 
 	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry)
-		return -ENOMEM;
+		return NULL;
 
 	entry->ip = ip;
 	__add_hash_entry(hash, entry);
 
-	return 0;
+	return entry;
 }
 
 static void
@@ -1349,7 +1350,6 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash)
 	struct ftrace_func_entry *entry;
 	struct ftrace_hash *new_hash;
 	int size;
-	int ret;
 	int i;
 
 	new_hash = alloc_ftrace_hash(size_bits);
@@ -1366,8 +1366,7 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash)
 	size = 1 << hash->size_bits;
 	for (i = 0; i < size; i++) {
 		hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
-			ret = add_hash_entry(new_hash, entry->ip);
-			if (ret < 0)
+			if (add_hash_entry(new_hash, entry->ip) == NULL)
 				goto free_hash;
 		}
 	}
@@ -2536,7 +2535,7 @@ ftrace_find_unique_ops(struct dyn_ftrace *rec)
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 /* Protected by rcu_tasks for reading, and direct_mutex for writing */
-static struct ftrace_hash *direct_functions = EMPTY_HASH;
+static struct ftrace_hash __rcu *direct_functions = EMPTY_HASH;
 static DEFINE_MUTEX(direct_mutex);
 int ftrace_direct_func_count;
 
@@ -2555,39 +2554,6 @@ unsigned long ftrace_find_rec_direct(unsigned long ip)
 	return entry->direct;
 }
 
-static struct ftrace_func_entry*
-ftrace_add_rec_direct(unsigned long ip, unsigned long addr,
-		      struct ftrace_hash **free_hash)
-{
-	struct ftrace_func_entry *entry;
-
-	if (ftrace_hash_empty(direct_functions) ||
-	    direct_functions->count > 2 * (1 << direct_functions->size_bits)) {
-		struct ftrace_hash *new_hash;
-		int size = ftrace_hash_empty(direct_functions) ? 0 :
-			direct_functions->count + 1;
-
-		if (size < 32)
-			size = 32;
-
-		new_hash = dup_hash(direct_functions, size);
-		if (!new_hash)
-			return NULL;
-
-		*free_hash = direct_functions;
-		direct_functions = new_hash;
-	}
-
-	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
-	if (!entry)
-		return NULL;
-
-	entry->ip = ip;
-	entry->direct = addr;
-	__add_hash_entry(direct_functions, entry);
-	return entry;
-}
-
 static void call_direct_funcs(unsigned long ip, unsigned long pip,
 			      struct ftrace_ops *ops, struct ftrace_regs *fregs)
 {
@@ -4223,8 +4189,8 @@ enter_record(struct ftrace_hash *hash, struct dyn_ftrace *rec, int clear_filter)
 		/* Do nothing if it exists */
 		if (entry)
 			return 0;
-
-		ret = add_hash_entry(hash, rec->ip);
+		if (add_hash_entry(hash, rec->ip) == NULL)
+			ret = -ENOMEM;
 	}
 	return ret;
 }
@@ -5266,7 +5232,8 @@ __ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove)
 		return 0;
 	}
 
-	return add_hash_entry(hash, ip);
+	entry = add_hash_entry(hash, ip);
+	return entry ? 0 :  -ENOMEM;
 }
 
 static int
@@ -5410,7 +5377,7 @@ static void remove_direct_functions_hash(struct ftrace_hash *hash, unsigned long
  */
 int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 {
-	struct ftrace_hash *hash, *free_hash = NULL;
+	struct ftrace_hash *hash, *new_hash = NULL, *free_hash = NULL;
 	struct ftrace_func_entry *entry, *new;
 	int err = -EBUSY, size, i;
 
@@ -5436,17 +5403,44 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 		}
 	}
 
-	/* ... and insert them to direct_functions hash. */
 	err = -ENOMEM;
+
+	/* Make a copy hash to place the new and the old entries in */
+	size = hash->count + direct_functions->count;
+	if (size > 32)
+		size = 32;
+	new_hash = alloc_ftrace_hash(fls(size));
+	if (!new_hash)
+		goto out_unlock;
+
+	/* Now copy over the existing direct entries */
+	size = 1 << direct_functions->size_bits;
+	for (i = 0; i < size; i++) {
+		hlist_for_each_entry(entry, &direct_functions->buckets[i], hlist) {
+			new = add_hash_entry(new_hash, entry->ip);
+			if (!new)
+				goto out_unlock;
+			new->direct = entry->direct;
+		}
+	}
+
+	/* ... and add the new entries */
+	size = 1 << hash->size_bits;
 	for (i = 0; i < size; i++) {
 		hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
-			new = ftrace_add_rec_direct(entry->ip, addr, &free_hash);
+			new = add_hash_entry(new_hash, entry->ip);
 			if (!new)
-				goto out_remove;
+				goto out_unlock;
+			/* Update both the copy and the hash entry */
+			new->direct = addr;
 			entry->direct = addr;
 		}
 	}
 
+	free_hash = direct_functions;
+	rcu_assign_pointer(direct_functions, new_hash);
+	new_hash = NULL;
+
 	ops->func = call_direct_funcs;
 	ops->flags = MULTI_FLAGS;
 	ops->trampoline = FTRACE_REGS_ADDR;
@@ -5454,17 +5448,17 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 
 	err = register_ftrace_function_nolock(ops);
 
- out_remove:
-	if (err)
-		remove_direct_functions_hash(hash, addr);
-
  out_unlock:
 	mutex_unlock(&direct_mutex);
 
-	if (free_hash) {
+	if (free_hash && free_hash != EMPTY_HASH) {
 		synchronize_rcu_tasks();
 		free_ftrace_hash(free_hash);
 	}
+
+	if (new_hash)
+		free_ftrace_hash(new_hash);
+
 	return err;
 }
 EXPORT_SYMBOL_GPL(register_ftrace_direct);
@@ -6309,7 +6303,7 @@ ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer)
 
 				if (entry)
 					continue;
-				if (add_hash_entry(hash, rec->ip) < 0)
+				if (add_hash_entry(hash, rec->ip) == NULL)
 					goto out;
 			} else {
 				if (entry) {
diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c
index 6fd7d4ecbbc6..fa03094e9e69 100644
--- a/kernel/trace/rethook.c
+++ b/kernel/trace/rethook.c
@@ -48,7 +48,7 @@ static void rethook_free_rcu(struct rcu_head *head)
  */
 void rethook_stop(struct rethook *rh)
 {
-	WRITE_ONCE(rh->handler, NULL);
+	rcu_assign_pointer(rh->handler, NULL);
 }
 
 /**
@@ -63,7 +63,7 @@ void rethook_stop(struct rethook *rh)
  */
 void rethook_free(struct rethook *rh)
 {
-	WRITE_ONCE(rh->handler, NULL);
+	rethook_stop(rh);
 
 	call_rcu(&rh->rcu, rethook_free_rcu);
 }
@@ -82,6 +82,12 @@ static int rethook_fini_pool(struct objpool_head *head, void *context)
 	return 0;
 }
 
+static inline rethook_handler_t rethook_get_handler(struct rethook *rh)
+{
+	return (rethook_handler_t)rcu_dereference_check(rh->handler,
+							rcu_read_lock_any_held());
+}
+
 /**
  * rethook_alloc() - Allocate struct rethook.
  * @data: a data to pass the @handler when hooking the return.
@@ -107,7 +113,7 @@ struct rethook *rethook_alloc(void *data, rethook_handler_t handler,
 		return ERR_PTR(-ENOMEM);
 
 	rh->data = data;
-	rh->handler = handler;
+	rcu_assign_pointer(rh->handler, handler);
 
 	/* initialize the objpool for rethook nodes */
 	if (objpool_init(&rh->pool, num, size, GFP_KERNEL, rh,
@@ -135,9 +141,10 @@ static void free_rethook_node_rcu(struct rcu_head *head)
  */
 void rethook_recycle(struct rethook_node *node)
 {
-	lockdep_assert_preemption_disabled();
+	rethook_handler_t handler;
 
-	if (likely(READ_ONCE(node->rethook->handler)))
+	handler = rethook_get_handler(node->rethook);
+	if (likely(handler))
 		objpool_push(node, &node->rethook->pool);
 	else
 		call_rcu(&node->rcu, free_rethook_node_rcu);
@@ -153,9 +160,7 @@ NOKPROBE_SYMBOL(rethook_recycle);
  */
 struct rethook_node *rethook_try_get(struct rethook *rh)
 {
-	rethook_handler_t handler = READ_ONCE(rh->handler);
-
-	lockdep_assert_preemption_disabled();
+	rethook_handler_t handler = rethook_get_handler(rh);
 
 	/* Check whether @rh is going to be freed. */
 	if (unlikely(!handler))
@@ -300,7 +305,7 @@ unsigned long rethook_trampoline_handler(struct pt_regs *regs,
 		rhn = container_of(first, struct rethook_node, llist);
 		if (WARN_ON_ONCE(rhn->frame != frame))
 			break;
-		handler = READ_ONCE(rhn->rethook->handler);
+		handler = rethook_get_handler(rhn->rethook);
 		if (handler)
 			handler(rhn, rhn->rethook->data,
 				correct_ret_addr, regs);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 43cc47d7faaf..9286f88fcd32 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -644,8 +644,8 @@ static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt)
 
 	*cnt = rb_time_cnt(top);
 
-	/* If top and bottom counts don't match, this interrupted a write */
-	if (*cnt != rb_time_cnt(bottom))
+	/* If top, msb or bottom counts don't match, this interrupted a write */
+	if (*cnt != rb_time_cnt(msb) || *cnt != rb_time_cnt(bottom))
 		return false;
 
 	/* The shift to msb will lose its cnt bits */
@@ -700,44 +700,6 @@ rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set)
 	return local_try_cmpxchg(l, &expect, set);
 }
 
-static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
-{
-	unsigned long cnt, top, bottom, msb;
-	unsigned long cnt2, top2, bottom2, msb2;
-	u64 val;
-
-	/* The cmpxchg always fails if it interrupted an update */
-	 if (!__rb_time_read(t, &val, &cnt2))
-		 return false;
-
-	 if (val != expect)
-		 return false;
-
-	 cnt = local_read(&t->cnt);
-	 if ((cnt & 3) != cnt2)
-		 return false;
-
-	 cnt2 = cnt + 1;
-
-	 rb_time_split(val, &top, &bottom, &msb);
-	 top = rb_time_val_cnt(top, cnt);
-	 bottom = rb_time_val_cnt(bottom, cnt);
-
-	 rb_time_split(set, &top2, &bottom2, &msb2);
-	 top2 = rb_time_val_cnt(top2, cnt2);
-	 bottom2 = rb_time_val_cnt(bottom2, cnt2);
-
-	if (!rb_time_read_cmpxchg(&t->cnt, cnt, cnt2))
-		return false;
-	if (!rb_time_read_cmpxchg(&t->msb, msb, msb2))
-		return false;
-	if (!rb_time_read_cmpxchg(&t->top, top, top2))
-		return false;
-	if (!rb_time_read_cmpxchg(&t->bottom, bottom, bottom2))
-		return false;
-	return true;
-}
-
 #else /* 64 bits */
 
 /* local64_t always succeeds */
@@ -751,11 +713,6 @@ static void rb_time_set(rb_time_t *t, u64 val)
 {
 	local64_set(&t->time, val);
 }
-
-static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
-{
-	return local64_try_cmpxchg(&t->time, &expect, set);
-}
 #endif
 
 /*
@@ -924,9 +881,14 @@ static __always_inline bool full_hit(struct trace_buffer *buffer, int cpu, int f
 	if (!nr_pages || !full)
 		return true;
 
-	dirty = ring_buffer_nr_dirty_pages(buffer, cpu);
+	/*
+	 * Add one as dirty will never equal nr_pages, as the sub-buffer
+	 * that the writer is on is not counted as dirty.
+	 * This is needed if "buffer_percent" is set to 100.
+	 */
+	dirty = ring_buffer_nr_dirty_pages(buffer, cpu) + 1;
 
-	return (dirty * 100) > (full * nr_pages);
+	return (dirty * 100) >= (full * nr_pages);
 }
 
 /*
@@ -987,7 +949,8 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu)
 	/* make sure the waiters see the new index */
 	smp_wmb();
 
-	rb_wake_up_waiters(&rbwork->work);
+	/* This can be called in any context */
+	irq_work_queue(&rbwork->work);
 }
 
 /**
@@ -1787,6 +1750,8 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 		free_buffer_page(bpage);
 	}
 
+	free_page((unsigned long)cpu_buffer->free_page);
+
 	kfree(cpu_buffer);
 }
 
@@ -2407,7 +2372,7 @@ rb_iter_head_event(struct ring_buffer_iter *iter)
 	 */
 	barrier();
 
-	if ((iter->head + length) > commit || length > BUF_MAX_DATA_SIZE)
+	if ((iter->head + length) > commit || length > BUF_PAGE_SIZE)
 		/* Writer corrupted the read? */
 		goto reset;
 
@@ -2981,25 +2946,6 @@ static unsigned rb_calculate_event_length(unsigned length)
 	return length;
 }
 
-static u64 rb_time_delta(struct ring_buffer_event *event)
-{
-	switch (event->type_len) {
-	case RINGBUF_TYPE_PADDING:
-		return 0;
-
-	case RINGBUF_TYPE_TIME_EXTEND:
-		return rb_event_time_stamp(event);
-
-	case RINGBUF_TYPE_TIME_STAMP:
-		return 0;
-
-	case RINGBUF_TYPE_DATA:
-		return event->time_delta;
-	default:
-		return 0;
-	}
-}
-
 static inline bool
 rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 		  struct ring_buffer_event *event)
@@ -3007,8 +2953,6 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 	unsigned long new_index, old_index;
 	struct buffer_page *bpage;
 	unsigned long addr;
-	u64 write_stamp;
-	u64 delta;
 
 	new_index = rb_event_index(event);
 	old_index = new_index + rb_event_ts_length(event);
@@ -3017,41 +2961,34 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 
 	bpage = READ_ONCE(cpu_buffer->tail_page);
 
-	delta = rb_time_delta(event);
-
-	if (!rb_time_read(&cpu_buffer->write_stamp, &write_stamp))
-		return false;
-
-	/* Make sure the write stamp is read before testing the location */
-	barrier();
-
+	/*
+	 * Make sure the tail_page is still the same and
+	 * the next write location is the end of this event
+	 */
 	if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) {
 		unsigned long write_mask =
 			local_read(&bpage->write) & ~RB_WRITE_MASK;
 		unsigned long event_length = rb_event_length(event);
 
-		/* Something came in, can't discard */
-		if (!rb_time_cmpxchg(&cpu_buffer->write_stamp,
-				       write_stamp, write_stamp - delta))
-			return false;
-
 		/*
-		 * It's possible that the event time delta is zero
-		 * (has the same time stamp as the previous event)
-		 * in which case write_stamp and before_stamp could
-		 * be the same. In such a case, force before_stamp
-		 * to be different than write_stamp. It doesn't
-		 * matter what it is, as long as its different.
+		 * For the before_stamp to be different than the write_stamp
+		 * to make sure that the next event adds an absolute
+		 * value and does not rely on the saved write stamp, which
+		 * is now going to be bogus.
+		 *
+		 * By setting the before_stamp to zero, the next event
+		 * is not going to use the write_stamp and will instead
+		 * create an absolute timestamp. This means there's no
+		 * reason to update the wirte_stamp!
 		 */
-		if (!delta)
-			rb_time_set(&cpu_buffer->before_stamp, 0);
+		rb_time_set(&cpu_buffer->before_stamp, 0);
 
 		/*
 		 * If an event were to come in now, it would see that the
 		 * write_stamp and the before_stamp are different, and assume
 		 * that this event just added itself before updating
 		 * the write stamp. The interrupting event will fix the
-		 * write stamp for us, and use the before stamp as its delta.
+		 * write stamp for us, and use an absolute timestamp.
 		 */
 
 		/*
@@ -3488,7 +3425,7 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer,
 		return;
 
 	/*
-	 * If this interrupted another event, 
+	 * If this interrupted another event,
 	 */
 	if (atomic_inc_return(this_cpu_ptr(&checking)) != 1)
 		goto out;
@@ -3582,7 +3519,10 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		 * absolute timestamp.
 		 * Don't bother if this is the start of a new page (w == 0).
 		 */
-		if (unlikely(!a_ok || !b_ok || (info->before != info->after && w))) {
+		if (!w) {
+			/* Use the sub-buffer timestamp */
+			info->delta = 0;
+		} else if (unlikely(!a_ok || !b_ok || info->before != info->after)) {
 			info->add_timestamp |= RB_ADD_STAMP_FORCE | RB_ADD_STAMP_EXTEND;
 			info->length += RB_LEN_TIME_EXTEND;
 		} else {
@@ -3605,26 +3545,19 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 
 	/* See if we shot pass the end of this buffer page */
 	if (unlikely(write > BUF_PAGE_SIZE)) {
-		/* before and after may now different, fix it up*/
-		b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
-		a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
-		if (a_ok && b_ok && info->before != info->after)
-			(void)rb_time_cmpxchg(&cpu_buffer->before_stamp,
-					      info->before, info->after);
-		if (a_ok && b_ok)
-			check_buffer(cpu_buffer, info, CHECK_FULL_PAGE);
+		check_buffer(cpu_buffer, info, CHECK_FULL_PAGE);
 		return rb_move_tail(cpu_buffer, tail, info);
 	}
 
 	if (likely(tail == w)) {
-		u64 save_before;
-		bool s_ok;
-
 		/* Nothing interrupted us between A and C */
  /*D*/		rb_time_set(&cpu_buffer->write_stamp, info->ts);
-		barrier();
- /*E*/		s_ok = rb_time_read(&cpu_buffer->before_stamp, &save_before);
-		RB_WARN_ON(cpu_buffer, !s_ok);
+		/*
+		 * If something came in between C and D, the write stamp
+		 * may now not be in sync. But that's fine as the before_stamp
+		 * will be different and then next event will just be forced
+		 * to use an absolute timestamp.
+		 */
 		if (likely(!(info->add_timestamp &
 			     (RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE))))
 			/* This did not interrupt any time update */
@@ -3632,41 +3565,40 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		else
 			/* Just use full timestamp for interrupting event */
 			info->delta = info->ts;
-		barrier();
 		check_buffer(cpu_buffer, info, tail);
-		if (unlikely(info->ts != save_before)) {
-			/* SLOW PATH - Interrupted between C and E */
-
-			a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
-			RB_WARN_ON(cpu_buffer, !a_ok);
-
-			/* Write stamp must only go forward */
-			if (save_before > info->after) {
-				/*
-				 * We do not care about the result, only that
-				 * it gets updated atomically.
-				 */
-				(void)rb_time_cmpxchg(&cpu_buffer->write_stamp,
-						      info->after, save_before);
-			}
-		}
 	} else {
 		u64 ts;
 		/* SLOW PATH - Interrupted between A and C */
-		a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
-		/* Was interrupted before here, write_stamp must be valid */
+
+		/* Save the old before_stamp */
+		a_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
 		RB_WARN_ON(cpu_buffer, !a_ok);
+
+		/*
+		 * Read a new timestamp and update the before_stamp to make
+		 * the next event after this one force using an absolute
+		 * timestamp. This is in case an interrupt were to come in
+		 * between E and F.
+		 */
 		ts = rb_time_stamp(cpu_buffer->buffer);
+		rb_time_set(&cpu_buffer->before_stamp, ts);
+
 		barrier();
- /*E*/		if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) &&
-		    info->after < ts &&
-		    rb_time_cmpxchg(&cpu_buffer->write_stamp,
-				    info->after, ts)) {
-			/* Nothing came after this event between C and E */
+ /*E*/		a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
+		/* Was interrupted before here, write_stamp must be valid */
+		RB_WARN_ON(cpu_buffer, !a_ok);
+		barrier();
+ /*F*/		if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) &&
+		    info->after == info->before && info->after < ts) {
+			/*
+			 * Nothing came after this event between C and F, it is
+			 * safe to use info->after for the delta as it
+			 * matched info->before and is still valid.
+			 */
 			info->delta = ts - info->after;
 		} else {
 			/*
-			 * Interrupted between C and E:
+			 * Interrupted between C and F:
 			 * Lost the previous events time stamp. Just set the
 			 * delta to zero, and this will be the same time as
 			 * the event this event interrupted. And the events that
@@ -3717,6 +3649,12 @@ rb_reserve_next_event(struct trace_buffer *buffer,
 	int nr_loops = 0;
 	int add_ts_default;
 
+	/* ring buffer does cmpxchg, make sure it is safe in NMI context */
+	if (!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) &&
+	    (unlikely(in_nmi()))) {
+		return NULL;
+	}
+
 	rb_start_commit(cpu_buffer);
 	/* The commit page can not change after this */
 
@@ -3740,6 +3678,8 @@ rb_reserve_next_event(struct trace_buffer *buffer,
 	if (ring_buffer_time_stamp_abs(cpu_buffer->buffer)) {
 		add_ts_default = RB_ADD_STAMP_ABSOLUTE;
 		info.length += RB_LEN_TIME_EXTEND;
+		if (info.length > BUF_MAX_DATA_SIZE)
+			goto out_fail;
 	} else {
 		add_ts_default = RB_ADD_STAMP_NONE;
 	}
@@ -5121,7 +5061,8 @@ ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags)
 	if (!iter)
 		return NULL;
 
-	iter->event = kmalloc(BUF_MAX_DATA_SIZE, flags);
+	/* Holds the entire event: data and meta data */
+	iter->event = kmalloc(BUF_PAGE_SIZE, flags);
 	if (!iter->event) {
 		kfree(iter);
 		return NULL;
diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c
index 8dfe85499d4a..354c2117be43 100644
--- a/kernel/trace/synth_event_gen_test.c
+++ b/kernel/trace/synth_event_gen_test.c
@@ -477,6 +477,17 @@ static int __init synth_event_gen_test_init(void)
 
 	ret = test_trace_synth_event();
 	WARN_ON(ret);
+
+	/* Disable when done */
+	trace_array_set_clr_event(gen_synth_test->tr,
+				  "synthetic",
+				  "gen_synth_test", false);
+	trace_array_set_clr_event(empty_synth_test->tr,
+				  "synthetic",
+				  "empty_synth_test", false);
+	trace_array_set_clr_event(create_synth_test->tr,
+				  "synthetic",
+				  "create_synth_test", false);
  out:
 	return ret;
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 9aebf904ff97..a0defe156b57 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1894,6 +1894,9 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu,
 	__update_max_tr(tr, tsk, cpu);
 
 	arch_spin_unlock(&tr->max_lock);
+
+	/* Any waiters on the old snapshot buffer need to wake up */
+	ring_buffer_wake_waiters(tr->array_buffer.buffer, RING_BUFFER_ALL_CPUS);
 }
 
 /**
@@ -1945,12 +1948,23 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
 static int wait_on_pipe(struct trace_iterator *iter, int full)
 {
+	int ret;
+
 	/* Iterators are static, they should be filled or empty */
 	if (trace_buffer_iter(iter, iter->cpu_file))
 		return 0;
 
-	return ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file,
-				full);
+	ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+	/*
+	 * Make sure this is still the snapshot buffer, as if a snapshot were
+	 * to happen, this would now be the main buffer.
+	 */
+	if (iter->snapshot)
+		iter->array_buffer = &iter->tr->max_buffer;
+#endif
+	return ret;
 }
 
 #ifdef CONFIG_FTRACE_STARTUP_TEST
@@ -2360,13 +2374,7 @@ int is_tracing_stopped(void)
 	return global_trace.stop_count;
 }
 
-/**
- * tracing_start - quick start of the tracer
- *
- * If tracing is enabled but was stopped by tracing_stop,
- * this will start the tracer back up.
- */
-void tracing_start(void)
+static void tracing_start_tr(struct trace_array *tr)
 {
 	struct trace_buffer *buffer;
 	unsigned long flags;
@@ -2374,119 +2382,83 @@ void tracing_start(void)
 	if (tracing_disabled)
 		return;
 
-	raw_spin_lock_irqsave(&global_trace.start_lock, flags);
-	if (--global_trace.stop_count) {
-		if (global_trace.stop_count < 0) {
+	raw_spin_lock_irqsave(&tr->start_lock, flags);
+	if (--tr->stop_count) {
+		if (WARN_ON_ONCE(tr->stop_count < 0)) {
 			/* Someone screwed up their debugging */
-			WARN_ON_ONCE(1);
-			global_trace.stop_count = 0;
+			tr->stop_count = 0;
 		}
 		goto out;
 	}
 
 	/* Prevent the buffers from switching */
-	arch_spin_lock(&global_trace.max_lock);
+	arch_spin_lock(&tr->max_lock);
 
-	buffer = global_trace.array_buffer.buffer;
+	buffer = tr->array_buffer.buffer;
 	if (buffer)
 		ring_buffer_record_enable(buffer);
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-	buffer = global_trace.max_buffer.buffer;
+	buffer = tr->max_buffer.buffer;
 	if (buffer)
 		ring_buffer_record_enable(buffer);
 #endif
 
-	arch_spin_unlock(&global_trace.max_lock);
-
- out:
-	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
-}
-
-static void tracing_start_tr(struct trace_array *tr)
-{
-	struct trace_buffer *buffer;
-	unsigned long flags;
-
-	if (tracing_disabled)
-		return;
-
-	/* If global, we need to also start the max tracer */
-	if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
-		return tracing_start();
-
-	raw_spin_lock_irqsave(&tr->start_lock, flags);
-
-	if (--tr->stop_count) {
-		if (tr->stop_count < 0) {
-			/* Someone screwed up their debugging */
-			WARN_ON_ONCE(1);
-			tr->stop_count = 0;
-		}
-		goto out;
-	}
-
-	buffer = tr->array_buffer.buffer;
-	if (buffer)
-		ring_buffer_record_enable(buffer);
+	arch_spin_unlock(&tr->max_lock);
 
  out:
 	raw_spin_unlock_irqrestore(&tr->start_lock, flags);
 }
 
 /**
- * tracing_stop - quick stop of the tracer
+ * tracing_start - quick start of the tracer
  *
- * Light weight way to stop tracing. Use in conjunction with
- * tracing_start.
+ * If tracing is enabled but was stopped by tracing_stop,
+ * this will start the tracer back up.
  */
-void tracing_stop(void)
+void tracing_start(void)
+
+{
+	return tracing_start_tr(&global_trace);
+}
+
+static void tracing_stop_tr(struct trace_array *tr)
 {
 	struct trace_buffer *buffer;
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&global_trace.start_lock, flags);
-	if (global_trace.stop_count++)
+	raw_spin_lock_irqsave(&tr->start_lock, flags);
+	if (tr->stop_count++)
 		goto out;
 
 	/* Prevent the buffers from switching */
-	arch_spin_lock(&global_trace.max_lock);
+	arch_spin_lock(&tr->max_lock);
 
-	buffer = global_trace.array_buffer.buffer;
+	buffer = tr->array_buffer.buffer;
 	if (buffer)
 		ring_buffer_record_disable(buffer);
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-	buffer = global_trace.max_buffer.buffer;
+	buffer = tr->max_buffer.buffer;
 	if (buffer)
 		ring_buffer_record_disable(buffer);
 #endif
 
-	arch_spin_unlock(&global_trace.max_lock);
+	arch_spin_unlock(&tr->max_lock);
 
  out:
-	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
+	raw_spin_unlock_irqrestore(&tr->start_lock, flags);
 }
 
-static void tracing_stop_tr(struct trace_array *tr)
+/**
+ * tracing_stop - quick stop of the tracer
+ *
+ * Light weight way to stop tracing. Use in conjunction with
+ * tracing_start.
+ */
+void tracing_stop(void)
 {
-	struct trace_buffer *buffer;
-	unsigned long flags;
-
-	/* If global, we need to also stop the max tracer */
-	if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
-		return tracing_stop();
-
-	raw_spin_lock_irqsave(&tr->start_lock, flags);
-	if (tr->stop_count++)
-		goto out;
-
-	buffer = tr->array_buffer.buffer;
-	if (buffer)
-		ring_buffer_record_disable(buffer);
-
- out:
-	raw_spin_unlock_irqrestore(&tr->start_lock, flags);
+	return tracing_stop_tr(&global_trace);
 }
 
 static int trace_save_cmdline(struct task_struct *tsk)
@@ -2770,8 +2742,11 @@ void trace_buffered_event_enable(void)
 	for_each_tracing_cpu(cpu) {
 		page = alloc_pages_node(cpu_to_node(cpu),
 					GFP_KERNEL | __GFP_NORETRY, 0);
-		if (!page)
-			goto failed;
+		/* This is just an optimization and can handle failures */
+		if (!page) {
+			pr_err("Failed to allocate event buffer\n");
+			break;
+		}
 
 		event = page_address(page);
 		memset(event, 0, sizeof(*event));
@@ -2785,10 +2760,6 @@ void trace_buffered_event_enable(void)
 			WARN_ON_ONCE(1);
 		preempt_enable();
 	}
-
-	return;
- failed:
-	trace_buffered_event_disable();
 }
 
 static void enable_trace_buffered_event(void *data)
@@ -2823,11 +2794,9 @@ void trace_buffered_event_disable(void)
 	if (--trace_buffered_event_ref)
 		return;
 
-	preempt_disable();
 	/* For each CPU, set the buffer as used. */
-	smp_call_function_many(tracing_buffer_mask,
-			       disable_trace_buffered_event, NULL, 1);
-	preempt_enable();
+	on_each_cpu_mask(tracing_buffer_mask, disable_trace_buffered_event,
+			 NULL, true);
 
 	/* Wait for all current users to finish */
 	synchronize_rcu();
@@ -2836,17 +2805,19 @@ void trace_buffered_event_disable(void)
 		free_page((unsigned long)per_cpu(trace_buffered_event, cpu));
 		per_cpu(trace_buffered_event, cpu) = NULL;
 	}
+
 	/*
-	 * Make sure trace_buffered_event is NULL before clearing
-	 * trace_buffered_event_cnt.
+	 * Wait for all CPUs that potentially started checking if they can use
+	 * their event buffer only after the previous synchronize_rcu() call and
+	 * they still read a valid pointer from trace_buffered_event. It must be
+	 * ensured they don't see cleared trace_buffered_event_cnt else they
+	 * could wrongly decide to use the pointed-to buffer which is now freed.
 	 */
-	smp_wmb();
+	synchronize_rcu();
 
-	preempt_disable();
-	/* Do the work on each cpu */
-	smp_call_function_many(tracing_buffer_mask,
-			       enable_trace_buffered_event, NULL, 1);
-	preempt_enable();
+	/* For each CPU, relinquish the buffer */
+	on_each_cpu_mask(tracing_buffer_mask, enable_trace_buffered_event, NULL,
+			 true);
 }
 
 static struct trace_buffer *temp_buffer;
@@ -4765,7 +4736,11 @@ static int s_show(struct seq_file *m, void *v)
 		iter->leftover = ret;
 
 	} else {
-		print_trace_line(iter);
+		ret = print_trace_line(iter);
+		if (ret == TRACE_TYPE_PARTIAL_LINE) {
+			iter->seq.full = 0;
+			trace_seq_puts(&iter->seq, "[LINE TOO BIG]\n");
+		}
 		ret = trace_print_seq(m, &iter->seq);
 		/*
 		 * If we overflow the seq_file buffer, then it will
@@ -5007,6 +4982,12 @@ int tracing_release_file_tr(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+int tracing_single_release_file_tr(struct inode *inode, struct file *filp)
+{
+	tracing_release_file_tr(inode, filp);
+	return single_release(inode, filp);
+}
+
 static int tracing_mark_open(struct inode *inode, struct file *filp)
 {
 	stream_open(inode, filp);
@@ -6387,13 +6368,15 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr,
 	if (!tr->array_buffer.buffer)
 		return 0;
 
+	/* Do not allow tracing while resizing ring buffer */
+	tracing_stop_tr(tr);
+
 	ret = ring_buffer_resize(tr->array_buffer.buffer, size, cpu);
 	if (ret < 0)
-		return ret;
+		goto out_start;
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-	if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL) ||
-	    !tr->current_trace->use_max_tr)
+	if (!tr->allocated_snapshot)
 		goto out;
 
 	ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu);
@@ -6418,7 +6401,7 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr,
 			WARN_ON(1);
 			tracing_disabled = 1;
 		}
-		return ret;
+		goto out_start;
 	}
 
 	update_buffer_entries(&tr->max_buffer, cpu);
@@ -6427,7 +6410,8 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr,
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
 	update_buffer_entries(&tr->array_buffer, cpu);
-
+ out_start:
+	tracing_start_tr(tr);
 	return ret;
 }
 
@@ -8547,7 +8531,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 
 		wait_index = READ_ONCE(iter->wait_index);
 
-		ret = wait_on_pipe(iter, iter->tr->buffer_percent);
+		ret = wait_on_pipe(iter, iter->snapshot ? 0 : iter->tr->buffer_percent);
 		if (ret)
 			goto out;
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index b7f4ea25a194..0489e72c8169 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -617,6 +617,7 @@ int tracing_open_generic(struct inode *inode, struct file *filp);
 int tracing_open_generic_tr(struct inode *inode, struct file *filp);
 int tracing_open_file_tr(struct inode *inode, struct file *filp);
 int tracing_release_file_tr(struct inode *inode, struct file *filp);
+int tracing_single_release_file_tr(struct inode *inode, struct file *filp);
 bool tracing_is_disabled(void);
 bool tracer_tracing_is_on(struct trace_array *tr);
 void tracer_tracing_on(struct trace_array *tr);
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 1abc07fba1b9..5ecf3c8bde20 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -5623,10 +5623,12 @@ static int event_hist_open(struct inode *inode, struct file *file)
 {
 	int ret;
 
-	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	ret = tracing_open_file_tr(inode, file);
 	if (ret)
 		return ret;
 
+	/* Clear private_data to avoid warning in single_open() */
+	file->private_data = NULL;
 	return single_open(file, hist_show, file);
 }
 
@@ -5634,7 +5636,7 @@ const struct file_operations event_hist_fops = {
 	.open = event_hist_open,
 	.read = seq_read,
 	.llseek = seq_lseek,
-	.release = single_release,
+	.release = tracing_single_release_file_tr,
 };
 
 #ifdef CONFIG_HIST_TRIGGERS_DEBUG
@@ -5900,10 +5902,12 @@ static int event_hist_debug_open(struct inode *inode, struct file *file)
 {
 	int ret;
 
-	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	ret = tracing_open_file_tr(inode, file);
 	if (ret)
 		return ret;
 
+	/* Clear private_data to avoid warning in single_open() */
+	file->private_data = NULL;
 	return single_open(file, hist_debug_show, file);
 }
 
@@ -5911,7 +5915,7 @@ const struct file_operations event_hist_debug_fops = {
 	.open = event_hist_debug_open,
 	.read = seq_read,
 	.llseek = seq_lseek,
-	.release = single_release,
+	.release = tracing_single_release_file_tr,
 };
 #endif
 
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 846e02c0fb59..e7af286af4f1 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -1137,7 +1137,7 @@ EXPORT_SYMBOL_GPL(synth_event_add_fields);
  * @cmd: A pointer to the dynevent_cmd struct representing the new event
  * @name: The name of the synthetic event
  * @mod: The module creating the event, NULL if not created from a module
- * @args: Variable number of arg (pairs), one pair for each field
+ * @...: Variable number of arg (pairs), one pair for each field
  *
  * NOTE: Users normally won't want to call this function directly, but
  * rather use the synth_event_gen_cmd_start() wrapper, which
@@ -1695,7 +1695,7 @@ __synth_event_trace_end(struct synth_event_trace_state *trace_state)
  * synth_event_trace - Trace a synthetic event
  * @file: The trace_event_file representing the synthetic event
  * @n_vals: The number of values in vals
- * @args: Variable number of args containing the event values
+ * @...: Variable number of args containing the event values
  *
  * Trace a synthetic event using the values passed in the variable
  * argument list.
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index 9365ce407426..e76f5e1efdf2 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -2177,14 +2177,12 @@ static int user_events_open(struct inode *node, struct file *file)
 static ssize_t user_events_write(struct file *file, const char __user *ubuf,
 				 size_t count, loff_t *ppos)
 {
-	struct iovec iov;
 	struct iov_iter i;
 
 	if (unlikely(*ppos != 0))
 		return -EFAULT;
 
-	if (unlikely(import_single_range(ITER_SOURCE, (char __user *)ubuf,
-					 count, &iov, &i)))
+	if (unlikely(import_ubuf(ITER_SOURCE, (char __user *)ubuf, count, &i)))
 		return -EFAULT;
 
 	return user_events_write_core(file, &i);
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index d8b302d01083..3e7fa44dc2b2 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -1587,11 +1587,12 @@ static enum print_line_t trace_print_print(struct trace_iterator *iter,
 {
 	struct print_entry *field;
 	struct trace_seq *s = &iter->seq;
+	int max = iter->ent_size - offsetof(struct print_entry, buf);
 
 	trace_assign_type(field, iter->ent);
 
 	seq_print_ip_sym(s, field->ip, flags);
-	trace_seq_printf(s, ": %s", field->buf);
+	trace_seq_printf(s, ": %.*s", max, field->buf);
 
 	return trace_handle_return(s);
 }
@@ -1600,10 +1601,11 @@ static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags,
 					 struct trace_event *event)
 {
 	struct print_entry *field;
+	int max = iter->ent_size - offsetof(struct print_entry, buf);
 
 	trace_assign_type(field, iter->ent);
 
-	trace_seq_printf(&iter->seq, "# %lx %s", field->ip, field->buf);
+	trace_seq_printf(&iter->seq, "# %lx %.*s", field->ip, max, field->buf);
 
 	return trace_handle_return(&iter->seq);
 }
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 99c051de412a..a84b85d8aac1 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -151,7 +151,7 @@ fetch_store_string(unsigned long addr, void *dest, void *base)
 		return -ENOMEM;
 
 	if (addr == FETCH_TOKEN_COMM)
-		ret = strlcpy(dst, current->comm, maxlen);
+		ret = strscpy(dst, current->comm, maxlen);
 	else
 		ret = strncpy_from_user(dst, src, maxlen);
 	if (ret >= 0) {
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index eabe8bcc7042..ce4d99df5f0e 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -231,7 +231,7 @@ void __put_user_ns(struct user_namespace *ns)
 }
 EXPORT_SYMBOL(__put_user_ns);
 
-/**
+/*
  * struct idmap_key - holds the information necessary to find an idmapping in a
  * sorted idmap array. It is passed to cmp_map_id() as first argument.
  */
@@ -241,7 +241,7 @@ struct idmap_key {
 	u32 count; /* == 0 unless used with map_id_range_down() */
 };
 
-/**
+/*
  * cmp_map_id - Function to be passed to bsearch() to find the requested
  * idmapping. Expects struct idmap_key to be passed via @k.
  */
@@ -271,7 +271,7 @@ static int cmp_map_id(const void *k, const void *e)
 	return 1;
 }
 
-/**
+/*
  * map_id_range_down_max - Find idmap via binary search in ordered idmap array.
  * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS.
  */
@@ -288,7 +288,7 @@ map_id_range_down_max(unsigned extents, struct uid_gid_map *map, u32 id, u32 cou
 		       sizeof(struct uid_gid_extent), cmp_map_id);
 }
 
-/**
+/*
  * map_id_range_down_base - Find idmap via binary search in static extent array.
  * Can only be called if number of mappings is equal or less than
  * UID_GID_MAP_MAX_BASE_EXTENTS.
@@ -332,12 +332,12 @@ static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count)
 	return id;
 }
 
-static u32 map_id_down(struct uid_gid_map *map, u32 id)
+u32 map_id_down(struct uid_gid_map *map, u32 id)
 {
 	return map_id_range_down(map, id, 1);
 }
 
-/**
+/*
  * map_id_up_base - Find idmap via binary search in static extent array.
  * Can only be called if number of mappings is equal or less than
  * UID_GID_MAP_MAX_BASE_EXTENTS.
@@ -358,7 +358,7 @@ map_id_up_base(unsigned extents, struct uid_gid_map *map, u32 id)
 	return NULL;
 }
 
-/**
+/*
  * map_id_up_max - Find idmap via binary search in ordered idmap array.
  * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS.
  */
@@ -375,7 +375,7 @@ map_id_up_max(unsigned extents, struct uid_gid_map *map, u32 id)
 		       sizeof(struct uid_gid_extent), cmp_map_id);
 }
 
-static u32 map_id_up(struct uid_gid_map *map, u32 id)
+u32 map_id_up(struct uid_gid_map *map, u32 id)
 {
 	struct uid_gid_extent *extent;
 	unsigned extents = map->nr_extents;
@@ -770,7 +770,7 @@ static bool mappings_overlap(struct uid_gid_map *new_map,
 	return false;
 }
 
-/**
+/*
  * insert_extent - Safely insert a new idmap extent into struct uid_gid_map.
  * Takes care to allocate a 4K block of memory if the number of mappings exceeds
  * UID_GID_MAP_MAX_BASE_EXTENTS.
@@ -839,7 +839,7 @@ static int cmp_extents_reverse(const void *a, const void *b)
 	return 0;
 }
 
-/**
+/*
  * sort_idmaps - Sorts an array of idmap entries.
  * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS.
  */
diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c
index 778b4056700f..03b90d7d2175 100644
--- a/kernel/watch_queue.c
+++ b/kernel/watch_queue.c
@@ -270,7 +270,7 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes)
 		goto error;
 
 	ret = -ENOMEM;
-	pages = kcalloc(sizeof(struct page *), nr_pages, GFP_KERNEL);
+	pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL);
 	if (!pages)
 		goto error;
 
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 5cd6d4e26915..81a8862295d6 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -91,7 +91,7 @@ static DEFINE_PER_CPU(atomic_t, hrtimer_interrupts);
 static DEFINE_PER_CPU(int, hrtimer_interrupts_saved);
 static DEFINE_PER_CPU(bool, watchdog_hardlockup_warned);
 static DEFINE_PER_CPU(bool, watchdog_hardlockup_touched);
-static unsigned long watchdog_hardlockup_all_cpu_dumped;
+static unsigned long hard_lockup_nmi_warn;
 
 notrace void arch_touch_nmi_watchdog(void)
 {
@@ -151,12 +151,32 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs)
 	 */
 	if (is_hardlockup(cpu)) {
 		unsigned int this_cpu = smp_processor_id();
+		unsigned long flags;
 
 		/* Only print hardlockups once. */
 		if (per_cpu(watchdog_hardlockup_warned, cpu))
 			return;
 
+		/*
+		 * Prevent multiple hard-lockup reports if one cpu is already
+		 * engaged in dumping all cpu back traces.
+		 */
+		if (sysctl_hardlockup_all_cpu_backtrace) {
+			if (test_and_set_bit_lock(0, &hard_lockup_nmi_warn))
+				return;
+		}
+
+		/*
+		 * NOTE: we call printk_cpu_sync_get_irqsave() after printing
+		 * the lockup message. While it would be nice to serialize
+		 * that printout, we really want to make sure that if some
+		 * other CPU somehow locked up while holding the lock associated
+		 * with printk_cpu_sync_get_irqsave() that we can still at least
+		 * get the message about the lockup out.
+		 */
 		pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n", cpu);
+		printk_cpu_sync_get_irqsave(flags);
+
 		print_modules();
 		print_irqtrace_events(current);
 		if (cpu == this_cpu) {
@@ -164,17 +184,17 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs)
 				show_regs(regs);
 			else
 				dump_stack();
+			printk_cpu_sync_put_irqrestore(flags);
 		} else {
+			printk_cpu_sync_put_irqrestore(flags);
 			trigger_single_cpu_backtrace(cpu);
 		}
 
-		/*
-		 * Perform multi-CPU dump only once to avoid multiple
-		 * hardlockups generating interleaving traces
-		 */
-		if (sysctl_hardlockup_all_cpu_backtrace &&
-		    !test_and_set_bit(0, &watchdog_hardlockup_all_cpu_dumped))
+		if (sysctl_hardlockup_all_cpu_backtrace) {
 			trigger_allbutcpu_cpu_backtrace(cpu);
+			if (!hardlockup_panic)
+				clear_bit_unlock(0, &hard_lockup_nmi_warn);
+		}
 
 		if (hardlockup_panic)
 			nmi_panic(regs, "Hard LOCKUP");
@@ -448,6 +468,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	struct pt_regs *regs = get_irq_regs();
 	int duration;
 	int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace;
+	unsigned long flags;
 
 	if (!watchdog_enabled)
 		return HRTIMER_NORESTART;
@@ -514,6 +535,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 		/* Start period for the next softlockup warning. */
 		update_report_ts();
 
+		printk_cpu_sync_get_irqsave(flags);
 		pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
 			smp_processor_id(), duration,
 			current->comm, task_pid_nr(current));
@@ -523,10 +545,12 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 			show_regs(regs);
 		else
 			dump_stack();
+		printk_cpu_sync_put_irqrestore(flags);
 
 		if (softlockup_all_cpu_backtrace) {
 			trigger_allbutcpu_cpu_backtrace(smp_processor_id());
-			clear_bit_unlock(0, &soft_lockup_nmi_warn);
+			if (!softlockup_panic)
+				clear_bit_unlock(0, &soft_lockup_nmi_warn);
 		}
 
 		add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 6e578f576a6f..76e60faed892 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -381,6 +381,12 @@ static bool workqueue_freezing;		/* PL: have wqs started freezing? */
 /* PL&A: allowable cpus for unbound wqs and work items */
 static cpumask_var_t wq_unbound_cpumask;
 
+/* PL: user requested unbound cpumask via sysfs */
+static cpumask_var_t wq_requested_unbound_cpumask;
+
+/* PL: isolated cpumask to be excluded from unbound cpumask */
+static cpumask_var_t wq_isolated_cpumask;
+
 /* for further constrain wq_unbound_cpumask by cmdline parameter*/
 static struct cpumask wq_cmdline_cpumask __initdata;
 
@@ -1684,9 +1690,6 @@ static int wq_select_unbound_cpu(int cpu)
 		pr_warn_once("workqueue: round-robin CPU selection forced, expect performance impact\n");
 	}
 
-	if (cpumask_empty(wq_unbound_cpumask))
-		return cpu;
-
 	new_cpu = __this_cpu_read(wq_rr_cpu_last);
 	new_cpu = cpumask_next_and(new_cpu, wq_unbound_cpumask, cpu_online_mask);
 	if (unlikely(new_cpu >= nr_cpu_ids)) {
@@ -4411,19 +4414,6 @@ static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx)
 	mutex_unlock(&ctx->wq->mutex);
 }
 
-static void apply_wqattrs_lock(void)
-{
-	/* CPUs should stay stable across pwq creations and installations */
-	cpus_read_lock();
-	mutex_lock(&wq_pool_mutex);
-}
-
-static void apply_wqattrs_unlock(void)
-{
-	mutex_unlock(&wq_pool_mutex);
-	cpus_read_unlock();
-}
-
 static int apply_workqueue_attrs_locked(struct workqueue_struct *wq,
 					const struct workqueue_attrs *attrs)
 {
@@ -5828,39 +5818,40 @@ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask)
 }
 
 /**
- *  workqueue_set_unbound_cpumask - Set the low-level unbound cpumask
- *  @cpumask: the cpumask to set
- *
- *  The low-level workqueues cpumask is a global cpumask that limits
- *  the affinity of all unbound workqueues.  This function check the @cpumask
- *  and apply it to all unbound workqueues and updates all pwqs of them.
+ * workqueue_unbound_exclude_cpumask - Exclude given CPUs from unbound cpumask
+ * @exclude_cpumask: the cpumask to be excluded from wq_unbound_cpumask
  *
- *  Return:	0	- Success
- *  		-EINVAL	- Invalid @cpumask
- *  		-ENOMEM	- Failed to allocate memory for attrs or pwqs.
+ * This function can be called from cpuset code to provide a set of isolated
+ * CPUs that should be excluded from wq_unbound_cpumask. The caller must hold
+ * either cpus_read_lock or cpus_write_lock.
  */
-int workqueue_set_unbound_cpumask(cpumask_var_t cpumask)
+int workqueue_unbound_exclude_cpumask(cpumask_var_t exclude_cpumask)
 {
-	int ret = -EINVAL;
+	cpumask_var_t cpumask;
+	int ret = 0;
+
+	if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL))
+		return -ENOMEM;
+
+	lockdep_assert_cpus_held();
+	mutex_lock(&wq_pool_mutex);
+
+	/* Save the current isolated cpumask & export it via sysfs */
+	cpumask_copy(wq_isolated_cpumask, exclude_cpumask);
 
 	/*
-	 * Not excluding isolated cpus on purpose.
-	 * If the user wishes to include them, we allow that.
+	 * If the operation fails, it will fall back to
+	 * wq_requested_unbound_cpumask which is initially set to
+	 * (HK_TYPE_WQ ∩ HK_TYPE_DOMAIN) house keeping mask and rewritten
+	 * by any subsequent write to workqueue/cpumask sysfs file.
 	 */
-	cpumask_and(cpumask, cpumask, cpu_possible_mask);
-	if (!cpumask_empty(cpumask)) {
-		apply_wqattrs_lock();
-		if (cpumask_equal(cpumask, wq_unbound_cpumask)) {
-			ret = 0;
-			goto out_unlock;
-		}
-
+	if (!cpumask_andnot(cpumask, wq_requested_unbound_cpumask, exclude_cpumask))
+		cpumask_copy(cpumask, wq_requested_unbound_cpumask);
+	if (!cpumask_equal(cpumask, wq_unbound_cpumask))
 		ret = workqueue_apply_unbound_cpumask(cpumask);
 
-out_unlock:
-		apply_wqattrs_unlock();
-	}
-
+	mutex_unlock(&wq_pool_mutex);
+	free_cpumask_var(cpumask);
 	return ret;
 }
 
@@ -5982,6 +5973,19 @@ static struct attribute *wq_sysfs_attrs[] = {
 };
 ATTRIBUTE_GROUPS(wq_sysfs);
 
+static void apply_wqattrs_lock(void)
+{
+	/* CPUs should stay stable across pwq creations and installations */
+	cpus_read_lock();
+	mutex_lock(&wq_pool_mutex);
+}
+
+static void apply_wqattrs_unlock(void)
+{
+	mutex_unlock(&wq_pool_mutex);
+	cpus_read_unlock();
+}
+
 static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr,
 			    char *buf)
 {
@@ -6158,19 +6162,74 @@ static struct bus_type wq_subsys = {
 	.dev_groups			= wq_sysfs_groups,
 };
 
-static ssize_t wq_unbound_cpumask_show(struct device *dev,
-		struct device_attribute *attr, char *buf)
+/**
+ *  workqueue_set_unbound_cpumask - Set the low-level unbound cpumask
+ *  @cpumask: the cpumask to set
+ *
+ *  The low-level workqueues cpumask is a global cpumask that limits
+ *  the affinity of all unbound workqueues.  This function check the @cpumask
+ *  and apply it to all unbound workqueues and updates all pwqs of them.
+ *
+ *  Return:	0	- Success
+ *		-EINVAL	- Invalid @cpumask
+ *		-ENOMEM	- Failed to allocate memory for attrs or pwqs.
+ */
+static int workqueue_set_unbound_cpumask(cpumask_var_t cpumask)
+{
+	int ret = -EINVAL;
+
+	/*
+	 * Not excluding isolated cpus on purpose.
+	 * If the user wishes to include them, we allow that.
+	 */
+	cpumask_and(cpumask, cpumask, cpu_possible_mask);
+	if (!cpumask_empty(cpumask)) {
+		apply_wqattrs_lock();
+		cpumask_copy(wq_requested_unbound_cpumask, cpumask);
+		if (cpumask_equal(cpumask, wq_unbound_cpumask)) {
+			ret = 0;
+			goto out_unlock;
+		}
+
+		ret = workqueue_apply_unbound_cpumask(cpumask);
+
+out_unlock:
+		apply_wqattrs_unlock();
+	}
+
+	return ret;
+}
+
+static ssize_t __wq_cpumask_show(struct device *dev,
+		struct device_attribute *attr, char *buf, cpumask_var_t mask)
 {
 	int written;
 
 	mutex_lock(&wq_pool_mutex);
-	written = scnprintf(buf, PAGE_SIZE, "%*pb\n",
-			    cpumask_pr_args(wq_unbound_cpumask));
+	written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask));
 	mutex_unlock(&wq_pool_mutex);
 
 	return written;
 }
 
+static ssize_t wq_unbound_cpumask_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return __wq_cpumask_show(dev, attr, buf, wq_unbound_cpumask);
+}
+
+static ssize_t wq_requested_cpumask_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return __wq_cpumask_show(dev, attr, buf, wq_requested_unbound_cpumask);
+}
+
+static ssize_t wq_isolated_cpumask_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return __wq_cpumask_show(dev, attr, buf, wq_isolated_cpumask);
+}
+
 static ssize_t wq_unbound_cpumask_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
@@ -6188,9 +6247,13 @@ static ssize_t wq_unbound_cpumask_store(struct device *dev,
 	return ret ? ret : count;
 }
 
-static struct device_attribute wq_sysfs_cpumask_attr =
+static struct device_attribute wq_sysfs_cpumask_attrs[] = {
 	__ATTR(cpumask, 0644, wq_unbound_cpumask_show,
-	       wq_unbound_cpumask_store);
+	       wq_unbound_cpumask_store),
+	__ATTR(cpumask_requested, 0444, wq_requested_cpumask_show, NULL),
+	__ATTR(cpumask_isolated, 0444, wq_isolated_cpumask_show, NULL),
+	__ATTR_NULL,
+};
 
 static int __init wq_sysfs_init(void)
 {
@@ -6203,7 +6266,13 @@ static int __init wq_sysfs_init(void)
 
 	dev_root = bus_get_dev_root(&wq_subsys);
 	if (dev_root) {
-		err = device_create_file(dev_root, &wq_sysfs_cpumask_attr);
+		struct device_attribute *attr;
+
+		for (attr = wq_sysfs_cpumask_attrs; attr->attr.name; attr++) {
+			err = device_create_file(dev_root, attr);
+			if (err)
+				break;
+		}
 		put_device(dev_root);
 	}
 	return err;
@@ -6515,6 +6584,17 @@ static inline void wq_watchdog_init(void) { }
 
 #endif	/* CONFIG_WQ_WATCHDOG */
 
+static void __init restrict_unbound_cpumask(const char *name, const struct cpumask *mask)
+{
+	if (!cpumask_intersects(wq_unbound_cpumask, mask)) {
+		pr_warn("workqueue: Restricting unbound_cpumask (%*pb) with %s (%*pb) leaves no CPU, ignoring\n",
+			cpumask_pr_args(wq_unbound_cpumask), name, cpumask_pr_args(mask));
+		return;
+	}
+
+	cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, mask);
+}
+
 /**
  * workqueue_init_early - early init for workqueue subsystem
  *
@@ -6534,11 +6614,16 @@ void __init workqueue_init_early(void)
 	BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long));
 
 	BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL));
-	cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_WQ));
-	cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_DOMAIN));
+	BUG_ON(!alloc_cpumask_var(&wq_requested_unbound_cpumask, GFP_KERNEL));
+	BUG_ON(!zalloc_cpumask_var(&wq_isolated_cpumask, GFP_KERNEL));
 
+	cpumask_copy(wq_unbound_cpumask, cpu_possible_mask);
+	restrict_unbound_cpumask("HK_TYPE_WQ", housekeeping_cpumask(HK_TYPE_WQ));
+	restrict_unbound_cpumask("HK_TYPE_DOMAIN", housekeeping_cpumask(HK_TYPE_DOMAIN));
 	if (!cpumask_empty(&wq_cmdline_cpumask))
-		cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, &wq_cmdline_cpumask);
+		restrict_unbound_cpumask("workqueue.unbound_cpus", &wq_cmdline_cpumask);
+
+	cpumask_copy(wq_requested_unbound_cpumask, wq_unbound_cpumask);
 
 	pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC);
 
diff --git a/lib/Kconfig b/lib/Kconfig
index 3ea1c830efab..5ddda7c2ed9b 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -713,10 +713,20 @@ config ARCH_STACKWALK
 config STACKDEPOT
 	bool
 	select STACKTRACE
+	help
+	  Stack depot: stack trace storage that avoids duplication
 
 config STACKDEPOT_ALWAYS_INIT
 	bool
 	select STACKDEPOT
+	help
+	  Always initialize stack depot during early boot
+
+config STACKDEPOT_MAX_FRAMES
+	int "Maximum number of frames in trace saved in stack depot"
+	range 1 256
+	default 64
+	depends on STACKDEPOT
 
 config REF_TRACKER
 	bool
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index cc7d53d9dc01..97ce28f4d154 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -763,6 +763,8 @@ config DEBUG_STACK_USAGE
 	help
 	  Enables the display of the minimum amount of free stack which each
 	  task has ever had available in the sysrq-T and sysrq-P debug output.
+	  Also emits a message to dmesg when a process exits if that process
+	  used more stack space than previously exiting processes.
 
 	  This option will slow down process creation somewhat.
 
@@ -1739,21 +1741,6 @@ config DEBUG_MAPLE_TREE
 
 endmenu
 
-config DEBUG_CREDENTIALS
-	bool "Debug credential management"
-	depends on DEBUG_KERNEL
-	help
-	  Enable this to turn on some debug checking for credential
-	  management.  The additional code keeps track of the number of
-	  pointers from task_structs to any given cred struct, and checks to
-	  see that this number never exceeds the usage count of the cred
-	  struct.
-
-	  Furthermore, if SELinux is enabled, this also checks that the
-	  security pointer in the cred struct is never seen to be invalid.
-
-	  If unsure, say N.
-
 source "kernel/rcu/Kconfig.debug"
 
 config DEBUG_WQ_FORCE_RR_CPU
@@ -1985,7 +1972,6 @@ config FAULT_INJECTION
 config FAILSLAB
 	bool "Fault-injection capability for kmalloc"
 	depends on FAULT_INJECTION
-	depends on SLAB || SLUB
 	help
 	  Provide fault-injection capability for kmalloc.
 
@@ -2103,10 +2089,6 @@ config KCOV
 	  KCOV exposes kernel code coverage information in a form suitable
 	  for coverage-guided fuzzing (randomized testing).
 
-	  If RANDOMIZE_BASE is enabled, PC values will not be stable across
-	  different machines and across reboots. If you need stable PC values,
-	  disable RANDOMIZE_BASE.
-
 	  For more details, see Documentation/dev-tools/kcov.rst.
 
 config KCOV_ENABLE_COMPARISONS
diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
index fdca89c05745..e6eda054ab27 100644
--- a/lib/Kconfig.kasan
+++ b/lib/Kconfig.kasan
@@ -37,7 +37,7 @@ menuconfig KASAN
 		     (HAVE_ARCH_KASAN_SW_TAGS && CC_HAS_KASAN_SW_TAGS)) && \
 		    CC_HAS_WORKING_NOSANITIZE_ADDRESS) || \
 		   HAVE_ARCH_KASAN_HW_TAGS
-	depends on (SLUB && SYSFS && !SLUB_TINY) || (SLAB && !DEBUG_SLAB)
+	depends on SYSFS && !SLUB_TINY
 	select STACKDEPOT_ALWAYS_INIT
 	help
 	  Enables KASAN (Kernel Address Sanitizer) - a dynamic memory safety
@@ -78,7 +78,7 @@ config KASAN_GENERIC
 	bool "Generic KASAN"
 	depends on HAVE_ARCH_KASAN && CC_HAS_KASAN_GENERIC
 	depends on CC_HAS_WORKING_NOSANITIZE_ADDRESS
-	select SLUB_DEBUG if SLUB
+	select SLUB_DEBUG
 	select CONSTRUCTORS
 	help
 	  Enables Generic KASAN.
@@ -89,13 +89,11 @@ config KASAN_GENERIC
 	  overhead of ~50% for dynamic allocations.
 	  The performance slowdown is ~x3.
 
-	  (Incompatible with CONFIG_DEBUG_SLAB: the kernel does not boot.)
-
 config KASAN_SW_TAGS
 	bool "Software Tag-Based KASAN"
 	depends on HAVE_ARCH_KASAN_SW_TAGS && CC_HAS_KASAN_SW_TAGS
 	depends on CC_HAS_WORKING_NOSANITIZE_ADDRESS
-	select SLUB_DEBUG if SLUB
+	select SLUB_DEBUG
 	select CONSTRUCTORS
 	help
 	  Enables Software Tag-Based KASAN.
@@ -110,12 +108,9 @@ config KASAN_SW_TAGS
 	  May potentially introduce problems related to pointer casting and
 	  comparison, as it embeds a tag into the top byte of each pointer.
 
-	  (Incompatible with CONFIG_DEBUG_SLAB: the kernel does not boot.)
-
 config KASAN_HW_TAGS
 	bool "Hardware Tag-Based KASAN"
 	depends on HAVE_ARCH_KASAN_HW_TAGS
-	depends on SLUB
 	help
 	  Enables Hardware Tag-Based KASAN.
 
@@ -134,7 +129,7 @@ endchoice
 choice
 	prompt "Instrumentation type"
 	depends on KASAN_GENERIC || KASAN_SW_TAGS
-	default KASAN_OUTLINE
+	default KASAN_INLINE if !ARCH_DISABLE_KASAN_INLINE
 
 config KASAN_OUTLINE
 	bool "Outline instrumentation"
@@ -207,4 +202,25 @@ config KASAN_MODULE_TEST
 	  A part of the KASAN test suite that is not integrated with KUnit.
 	  Incompatible with Hardware Tag-Based KASAN.
 
+config KASAN_EXTRA_INFO
+	bool "Record and report more information"
+	depends on KASAN
+	help
+	  Record and report more information to help us find the cause of the
+	  bug and to help us correlate the error with other system events.
+
+	  Currently, the CPU number and timestamp are additionally
+	  recorded for each heap block at allocation and free time, and
+	  8 bytes will be added to each metadata structure that records
+	  allocation or free information.
+
+	  In Generic KASAN, each kmalloc-8 and kmalloc-16 object will add
+	  16 bytes of additional memory consumption, and each kmalloc-32
+	  object will add 8 bytes of additional memory consumption, not
+	  affecting other larger objects.
+
+	  In SW_TAGS KASAN and HW_TAGS KASAN, depending on the stack_ring_size
+	  boot parameter, it will add 8 * stack_ring_size bytes of additional
+	  memory consumption.
+
 endif # KASAN
diff --git a/lib/Kconfig.kfence b/lib/Kconfig.kfence
index 459dda9ef619..6fbbebec683a 100644
--- a/lib/Kconfig.kfence
+++ b/lib/Kconfig.kfence
@@ -5,7 +5,7 @@ config HAVE_ARCH_KFENCE
 
 menuconfig KFENCE
 	bool "KFENCE: low-overhead sampling-based memory safety error detector"
-	depends on HAVE_ARCH_KFENCE && (SLAB || SLUB)
+	depends on HAVE_ARCH_KFENCE
 	select STACKTRACE
 	select IRQ_WORK
 	help
diff --git a/lib/Kconfig.kmsan b/lib/Kconfig.kmsan
index ef2c8f256c57..0541d7b079cc 100644
--- a/lib/Kconfig.kmsan
+++ b/lib/Kconfig.kmsan
@@ -11,7 +11,7 @@ config HAVE_KMSAN_COMPILER
 config KMSAN
 	bool "KMSAN: detector of uninitialized values use"
 	depends on HAVE_ARCH_KMSAN && HAVE_KMSAN_COMPILER
-	depends on SLUB && DEBUG_KERNEL && !KASAN && !KCSAN
+	depends on DEBUG_KERNEL && !KASAN && !KCSAN
 	depends on !PREEMPT_RT
 	select STACKDEPOT
 	select STACKDEPOT_ALWAYS_INIT
diff --git a/lib/closure.c b/lib/closure.c
index f86c9eeafb35..c16540552d61 100644
--- a/lib/closure.c
+++ b/lib/closure.c
@@ -36,7 +36,7 @@ static inline void closure_put_after_sub(struct closure *cl, int flags)
 			closure_debug_destroy(cl);
 
 			if (destructor)
-				destructor(cl);
+				destructor(&cl->work);
 
 			if (parent)
 				closure_put(parent);
@@ -108,8 +108,9 @@ struct closure_syncer {
 	int			done;
 };
 
-static void closure_sync_fn(struct closure *cl)
+static CLOSURE_CALLBACK(closure_sync_fn)
 {
+	struct closure *cl = container_of(ws, struct closure, work);
 	struct closure_syncer *s = cl->s;
 	struct task_struct *p;
 
diff --git a/lib/crc-ccitt.c b/lib/crc-ccitt.c
index d1a7d29d2ac9..9cddf35d3b66 100644
--- a/lib/crc-ccitt.c
+++ b/lib/crc-ccitt.c
@@ -49,46 +49,6 @@ u16 const crc_ccitt_table[256] = {
 };
 EXPORT_SYMBOL(crc_ccitt_table);
 
-/*
- * Similar table to calculate CRC16 variant known as CRC-CCITT-FALSE
- * Reflected bits order, does not augment final value.
- */
-u16 const crc_ccitt_false_table[256] = {
-    0x0000, 0x1021, 0x2042, 0x3063, 0x4084, 0x50A5, 0x60C6, 0x70E7,
-    0x8108, 0x9129, 0xA14A, 0xB16B, 0xC18C, 0xD1AD, 0xE1CE, 0xF1EF,
-    0x1231, 0x0210, 0x3273, 0x2252, 0x52B5, 0x4294, 0x72F7, 0x62D6,
-    0x9339, 0x8318, 0xB37B, 0xA35A, 0xD3BD, 0xC39C, 0xF3FF, 0xE3DE,
-    0x2462, 0x3443, 0x0420, 0x1401, 0x64E6, 0x74C7, 0x44A4, 0x5485,
-    0xA56A, 0xB54B, 0x8528, 0x9509, 0xE5EE, 0xF5CF, 0xC5AC, 0xD58D,
-    0x3653, 0x2672, 0x1611, 0x0630, 0x76D7, 0x66F6, 0x5695, 0x46B4,
-    0xB75B, 0xA77A, 0x9719, 0x8738, 0xF7DF, 0xE7FE, 0xD79D, 0xC7BC,
-    0x48C4, 0x58E5, 0x6886, 0x78A7, 0x0840, 0x1861, 0x2802, 0x3823,
-    0xC9CC, 0xD9ED, 0xE98E, 0xF9AF, 0x8948, 0x9969, 0xA90A, 0xB92B,
-    0x5AF5, 0x4AD4, 0x7AB7, 0x6A96, 0x1A71, 0x0A50, 0x3A33, 0x2A12,
-    0xDBFD, 0xCBDC, 0xFBBF, 0xEB9E, 0x9B79, 0x8B58, 0xBB3B, 0xAB1A,
-    0x6CA6, 0x7C87, 0x4CE4, 0x5CC5, 0x2C22, 0x3C03, 0x0C60, 0x1C41,
-    0xEDAE, 0xFD8F, 0xCDEC, 0xDDCD, 0xAD2A, 0xBD0B, 0x8D68, 0x9D49,
-    0x7E97, 0x6EB6, 0x5ED5, 0x4EF4, 0x3E13, 0x2E32, 0x1E51, 0x0E70,
-    0xFF9F, 0xEFBE, 0xDFDD, 0xCFFC, 0xBF1B, 0xAF3A, 0x9F59, 0x8F78,
-    0x9188, 0x81A9, 0xB1CA, 0xA1EB, 0xD10C, 0xC12D, 0xF14E, 0xE16F,
-    0x1080, 0x00A1, 0x30C2, 0x20E3, 0x5004, 0x4025, 0x7046, 0x6067,
-    0x83B9, 0x9398, 0xA3FB, 0xB3DA, 0xC33D, 0xD31C, 0xE37F, 0xF35E,
-    0x02B1, 0x1290, 0x22F3, 0x32D2, 0x4235, 0x5214, 0x6277, 0x7256,
-    0xB5EA, 0xA5CB, 0x95A8, 0x8589, 0xF56E, 0xE54F, 0xD52C, 0xC50D,
-    0x34E2, 0x24C3, 0x14A0, 0x0481, 0x7466, 0x6447, 0x5424, 0x4405,
-    0xA7DB, 0xB7FA, 0x8799, 0x97B8, 0xE75F, 0xF77E, 0xC71D, 0xD73C,
-    0x26D3, 0x36F2, 0x0691, 0x16B0, 0x6657, 0x7676, 0x4615, 0x5634,
-    0xD94C, 0xC96D, 0xF90E, 0xE92F, 0x99C8, 0x89E9, 0xB98A, 0xA9AB,
-    0x5844, 0x4865, 0x7806, 0x6827, 0x18C0, 0x08E1, 0x3882, 0x28A3,
-    0xCB7D, 0xDB5C, 0xEB3F, 0xFB1E, 0x8BF9, 0x9BD8, 0xABBB, 0xBB9A,
-    0x4A75, 0x5A54, 0x6A37, 0x7A16, 0x0AF1, 0x1AD0, 0x2AB3, 0x3A92,
-    0xFD2E, 0xED0F, 0xDD6C, 0xCD4D, 0xBDAA, 0xAD8B, 0x9DE8, 0x8DC9,
-    0x7C26, 0x6C07, 0x5C64, 0x4C45, 0x3CA2, 0x2C83, 0x1CE0, 0x0CC1,
-    0xEF1F, 0xFF3E, 0xCF5D, 0xDF7C, 0xAF9B, 0xBFBA, 0x8FD9, 0x9FF8,
-    0x6E17, 0x7E36, 0x4E55, 0x5E74, 0x2E93, 0x3EB2, 0x0ED1, 0x1EF0
-};
-EXPORT_SYMBOL(crc_ccitt_false_table);
-
 /**
  *	crc_ccitt - recompute the CRC (CRC-CCITT variant) for the data
  *	buffer
@@ -104,20 +64,5 @@ u16 crc_ccitt(u16 crc, u8 const *buffer, size_t len)
 }
 EXPORT_SYMBOL(crc_ccitt);
 
-/**
- *	crc_ccitt_false - recompute the CRC (CRC-CCITT-FALSE variant)
- *	for the data buffer
- *	@crc: previous CRC value
- *	@buffer: data pointer
- *	@len: number of bytes in the buffer
- */
-u16 crc_ccitt_false(u16 crc, u8 const *buffer, size_t len)
-{
-	while (len--)
-		crc = crc_ccitt_false_byte(crc, *buffer++);
-	return crc;
-}
-EXPORT_SYMBOL(crc_ccitt_false);
-
 MODULE_DESCRIPTION("CRC-CCITT calculations");
 MODULE_LICENSE("GPL");
diff --git a/lib/crypto/aesgcm.c b/lib/crypto/aesgcm.c
index c632d6e17af8..6bba6473fdf3 100644
--- a/lib/crypto/aesgcm.c
+++ b/lib/crypto/aesgcm.c
@@ -73,6 +73,19 @@ static void aesgcm_ghash(be128 *ghash, const be128 *key, const void *src,
 	}
 }
 
+/**
+ * aesgcm_mac - Generates the authentication tag using AES-GCM algorithm.
+ * @ctx: The data structure that will hold the AES-GCM key schedule
+ * @src: The input source data.
+ * @src_len: Length of the source data.
+ * @assoc: Points to the associated data.
+ * @assoc_len: Length of the associated data values.
+ * @ctr: Points to the counter value.
+ * @authtag: The output buffer for the authentication tag.
+ *
+ * It takes in the AES-GCM context, source data, associated data, counter value,
+ * and an output buffer for the authentication tag.
+ */
 static void aesgcm_mac(const struct aesgcm_ctx *ctx, const u8 *src, int src_len,
 		       const u8 *assoc, int assoc_len, __be32 *ctr, u8 *authtag)
 {
diff --git a/lib/crypto/mpi/ec.c b/lib/crypto/mpi/ec.c
index 40f5908e57a4..e16dca1e23d5 100644
--- a/lib/crypto/mpi/ec.c
+++ b/lib/crypto/mpi/ec.c
@@ -584,6 +584,9 @@ void mpi_ec_init(struct mpi_ec_ctx *ctx, enum gcry_mpi_ec_models model,
 	ctx->a = mpi_copy(a);
 	ctx->b = mpi_copy(b);
 
+	ctx->d = NULL;
+	ctx->t.two_inv_p = NULL;
+
 	ctx->t.p_barrett = use_barrett > 0 ? mpi_barrett_init(ctx->p, 0) : NULL;
 
 	mpi_ec_get_reset(ctx);
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 2a8e9d63fbe3..fb12a9bacd2f 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -620,9 +620,8 @@ static void debug_objects_fill_pool(void)
 static void
 __debug_object_init(void *addr, const struct debug_obj_descr *descr, int onstack)
 {
-	enum debug_obj_state state;
+	struct debug_obj *obj, o;
 	struct debug_bucket *db;
-	struct debug_obj *obj;
 	unsigned long flags;
 
 	debug_objects_fill_pool();
@@ -643,24 +642,18 @@ __debug_object_init(void *addr, const struct debug_obj_descr *descr, int onstack
 	case ODEBUG_STATE_INIT:
 	case ODEBUG_STATE_INACTIVE:
 		obj->state = ODEBUG_STATE_INIT;
-		break;
-
-	case ODEBUG_STATE_ACTIVE:
-		state = obj->state;
-		raw_spin_unlock_irqrestore(&db->lock, flags);
-		debug_print_object(obj, "init");
-		debug_object_fixup(descr->fixup_init, addr, state);
-		return;
-
-	case ODEBUG_STATE_DESTROYED:
 		raw_spin_unlock_irqrestore(&db->lock, flags);
-		debug_print_object(obj, "init");
 		return;
 	default:
 		break;
 	}
 
+	o = *obj;
 	raw_spin_unlock_irqrestore(&db->lock, flags);
+	debug_print_object(&o, "init");
+
+	if (o.state == ODEBUG_STATE_ACTIVE)
+		debug_object_fixup(descr->fixup_init, addr, o.state);
 }
 
 /**
@@ -701,11 +694,9 @@ EXPORT_SYMBOL_GPL(debug_object_init_on_stack);
 int debug_object_activate(void *addr, const struct debug_obj_descr *descr)
 {
 	struct debug_obj o = { .object = addr, .state = ODEBUG_STATE_NOTAVAILABLE, .descr = descr };
-	enum debug_obj_state state;
 	struct debug_bucket *db;
 	struct debug_obj *obj;
 	unsigned long flags;
-	int ret;
 
 	if (!debug_objects_enabled)
 		return 0;
@@ -717,49 +708,38 @@ int debug_object_activate(void *addr, const struct debug_obj_descr *descr)
 	raw_spin_lock_irqsave(&db->lock, flags);
 
 	obj = lookup_object_or_alloc(addr, db, descr, false, true);
-	if (likely(!IS_ERR_OR_NULL(obj))) {
-		bool print_object = false;
-
+	if (unlikely(!obj)) {
+		raw_spin_unlock_irqrestore(&db->lock, flags);
+		debug_objects_oom();
+		return 0;
+	} else if (likely(!IS_ERR(obj))) {
 		switch (obj->state) {
-		case ODEBUG_STATE_INIT:
-		case ODEBUG_STATE_INACTIVE:
-			obj->state = ODEBUG_STATE_ACTIVE;
-			ret = 0;
-			break;
-
 		case ODEBUG_STATE_ACTIVE:
-			state = obj->state;
-			raw_spin_unlock_irqrestore(&db->lock, flags);
-			debug_print_object(obj, "activate");
-			ret = debug_object_fixup(descr->fixup_activate, addr, state);
-			return ret ? 0 : -EINVAL;
-
 		case ODEBUG_STATE_DESTROYED:
-			print_object = true;
-			ret = -EINVAL;
+			o = *obj;
 			break;
+		case ODEBUG_STATE_INIT:
+		case ODEBUG_STATE_INACTIVE:
+			obj->state = ODEBUG_STATE_ACTIVE;
+			fallthrough;
 		default:
-			ret = 0;
-			break;
+			raw_spin_unlock_irqrestore(&db->lock, flags);
+			return 0;
 		}
-		raw_spin_unlock_irqrestore(&db->lock, flags);
-		if (print_object)
-			debug_print_object(obj, "activate");
-		return ret;
 	}
 
 	raw_spin_unlock_irqrestore(&db->lock, flags);
+	debug_print_object(&o, "activate");
 
-	/* If NULL the allocation has hit OOM */
-	if (!obj) {
-		debug_objects_oom();
-		return 0;
+	switch (o.state) {
+	case ODEBUG_STATE_ACTIVE:
+	case ODEBUG_STATE_NOTAVAILABLE:
+		if (debug_object_fixup(descr->fixup_activate, addr, o.state))
+			return 0;
+		fallthrough;
+	default:
+		return -EINVAL;
 	}
-
-	/* Object is neither static nor tracked. It's not initialized */
-	debug_print_object(&o, "activate");
-	ret = debug_object_fixup(descr->fixup_activate, addr, ODEBUG_STATE_NOTAVAILABLE);
-	return ret ? 0 : -EINVAL;
 }
 EXPORT_SYMBOL_GPL(debug_object_activate);
 
@@ -770,10 +750,10 @@ EXPORT_SYMBOL_GPL(debug_object_activate);
  */
 void debug_object_deactivate(void *addr, const struct debug_obj_descr *descr)
 {
+	struct debug_obj o = { .object = addr, .state = ODEBUG_STATE_NOTAVAILABLE, .descr = descr };
 	struct debug_bucket *db;
 	struct debug_obj *obj;
 	unsigned long flags;
-	bool print_object = false;
 
 	if (!debug_objects_enabled)
 		return;
@@ -785,33 +765,24 @@ void debug_object_deactivate(void *addr, const struct debug_obj_descr *descr)
 	obj = lookup_object(addr, db);
 	if (obj) {
 		switch (obj->state) {
+		case ODEBUG_STATE_DESTROYED:
+			break;
 		case ODEBUG_STATE_INIT:
 		case ODEBUG_STATE_INACTIVE:
 		case ODEBUG_STATE_ACTIVE:
-			if (!obj->astate)
-				obj->state = ODEBUG_STATE_INACTIVE;
-			else
-				print_object = true;
-			break;
-
-		case ODEBUG_STATE_DESTROYED:
-			print_object = true;
-			break;
+			if (obj->astate)
+				break;
+			obj->state = ODEBUG_STATE_INACTIVE;
+			fallthrough;
 		default:
-			break;
+			raw_spin_unlock_irqrestore(&db->lock, flags);
+			return;
 		}
+		o = *obj;
 	}
 
 	raw_spin_unlock_irqrestore(&db->lock, flags);
-	if (!obj) {
-		struct debug_obj o = { .object = addr,
-				       .state = ODEBUG_STATE_NOTAVAILABLE,
-				       .descr = descr };
-
-		debug_print_object(&o, "deactivate");
-	} else if (print_object) {
-		debug_print_object(obj, "deactivate");
-	}
+	debug_print_object(&o, "deactivate");
 }
 EXPORT_SYMBOL_GPL(debug_object_deactivate);
 
@@ -822,11 +793,9 @@ EXPORT_SYMBOL_GPL(debug_object_deactivate);
  */
 void debug_object_destroy(void *addr, const struct debug_obj_descr *descr)
 {
-	enum debug_obj_state state;
+	struct debug_obj *obj, o;
 	struct debug_bucket *db;
-	struct debug_obj *obj;
 	unsigned long flags;
-	bool print_object = false;
 
 	if (!debug_objects_enabled)
 		return;
@@ -836,32 +805,31 @@ void debug_object_destroy(void *addr, const struct debug_obj_descr *descr)
 	raw_spin_lock_irqsave(&db->lock, flags);
 
 	obj = lookup_object(addr, db);
-	if (!obj)
-		goto out_unlock;
+	if (!obj) {
+		raw_spin_unlock_irqrestore(&db->lock, flags);
+		return;
+	}
 
 	switch (obj->state) {
+	case ODEBUG_STATE_ACTIVE:
+	case ODEBUG_STATE_DESTROYED:
+		break;
 	case ODEBUG_STATE_NONE:
 	case ODEBUG_STATE_INIT:
 	case ODEBUG_STATE_INACTIVE:
 		obj->state = ODEBUG_STATE_DESTROYED;
-		break;
-	case ODEBUG_STATE_ACTIVE:
-		state = obj->state;
+		fallthrough;
+	default:
 		raw_spin_unlock_irqrestore(&db->lock, flags);
-		debug_print_object(obj, "destroy");
-		debug_object_fixup(descr->fixup_destroy, addr, state);
 		return;
-
-	case ODEBUG_STATE_DESTROYED:
-		print_object = true;
-		break;
-	default:
-		break;
 	}
-out_unlock:
+
+	o = *obj;
 	raw_spin_unlock_irqrestore(&db->lock, flags);
-	if (print_object)
-		debug_print_object(obj, "destroy");
+	debug_print_object(&o, "destroy");
+
+	if (o.state == ODEBUG_STATE_ACTIVE)
+		debug_object_fixup(descr->fixup_destroy, addr, o.state);
 }
 EXPORT_SYMBOL_GPL(debug_object_destroy);
 
@@ -872,9 +840,8 @@ EXPORT_SYMBOL_GPL(debug_object_destroy);
  */
 void debug_object_free(void *addr, const struct debug_obj_descr *descr)
 {
-	enum debug_obj_state state;
+	struct debug_obj *obj, o;
 	struct debug_bucket *db;
-	struct debug_obj *obj;
 	unsigned long flags;
 
 	if (!debug_objects_enabled)
@@ -885,24 +852,26 @@ void debug_object_free(void *addr, const struct debug_obj_descr *descr)
 	raw_spin_lock_irqsave(&db->lock, flags);
 
 	obj = lookup_object(addr, db);
-	if (!obj)
-		goto out_unlock;
+	if (!obj) {
+		raw_spin_unlock_irqrestore(&db->lock, flags);
+		return;
+	}
 
 	switch (obj->state) {
 	case ODEBUG_STATE_ACTIVE:
-		state = obj->state;
-		raw_spin_unlock_irqrestore(&db->lock, flags);
-		debug_print_object(obj, "free");
-		debug_object_fixup(descr->fixup_free, addr, state);
-		return;
+		break;
 	default:
 		hlist_del(&obj->node);
 		raw_spin_unlock_irqrestore(&db->lock, flags);
 		free_object(obj);
 		return;
 	}
-out_unlock:
+
+	o = *obj;
 	raw_spin_unlock_irqrestore(&db->lock, flags);
+	debug_print_object(&o, "free");
+
+	debug_object_fixup(descr->fixup_free, addr, o.state);
 }
 EXPORT_SYMBOL_GPL(debug_object_free);
 
@@ -954,10 +923,10 @@ void
 debug_object_active_state(void *addr, const struct debug_obj_descr *descr,
 			  unsigned int expect, unsigned int next)
 {
+	struct debug_obj o = { .object = addr, .state = ODEBUG_STATE_NOTAVAILABLE, .descr = descr };
 	struct debug_bucket *db;
 	struct debug_obj *obj;
 	unsigned long flags;
-	bool print_object = false;
 
 	if (!debug_objects_enabled)
 		return;
@@ -970,28 +939,19 @@ debug_object_active_state(void *addr, const struct debug_obj_descr *descr,
 	if (obj) {
 		switch (obj->state) {
 		case ODEBUG_STATE_ACTIVE:
-			if (obj->astate == expect)
-				obj->astate = next;
-			else
-				print_object = true;
-			break;
-
+			if (obj->astate != expect)
+				break;
+			obj->astate = next;
+			raw_spin_unlock_irqrestore(&db->lock, flags);
+			return;
 		default:
-			print_object = true;
 			break;
 		}
+		o = *obj;
 	}
 
 	raw_spin_unlock_irqrestore(&db->lock, flags);
-	if (!obj) {
-		struct debug_obj o = { .object = addr,
-				       .state = ODEBUG_STATE_NOTAVAILABLE,
-				       .descr = descr };
-
-		debug_print_object(&o, "active_state");
-	} else if (print_object) {
-		debug_print_object(obj, "active_state");
-	}
+	debug_print_object(&o, "active_state");
 }
 EXPORT_SYMBOL_GPL(debug_object_active_state);
 
@@ -999,12 +959,10 @@ EXPORT_SYMBOL_GPL(debug_object_active_state);
 static void __debug_check_no_obj_freed(const void *address, unsigned long size)
 {
 	unsigned long flags, oaddr, saddr, eaddr, paddr, chunks;
-	const struct debug_obj_descr *descr;
-	enum debug_obj_state state;
+	int cnt, objs_checked = 0;
+	struct debug_obj *obj, o;
 	struct debug_bucket *db;
 	struct hlist_node *tmp;
-	struct debug_obj *obj;
-	int cnt, objs_checked = 0;
 
 	saddr = (unsigned long) address;
 	eaddr = saddr + size;
@@ -1026,12 +984,10 @@ repeat:
 
 			switch (obj->state) {
 			case ODEBUG_STATE_ACTIVE:
-				descr = obj->descr;
-				state = obj->state;
+				o = *obj;
 				raw_spin_unlock_irqrestore(&db->lock, flags);
-				debug_print_object(obj, "free");
-				debug_object_fixup(descr->fixup_free,
-						   (void *) oaddr, state);
+				debug_print_object(&o, "free");
+				debug_object_fixup(o.descr->fixup_free, (void *)oaddr, o.state);
 				goto repeat;
 			default:
 				hlist_del(&obj->node);
diff --git a/lib/errname.c b/lib/errname.c
index dd1b998552cd..4f9112b38f3a 100644
--- a/lib/errname.c
+++ b/lib/errname.c
@@ -111,9 +111,6 @@ static const char *names_0[] = {
 	E(ENOSPC),
 	E(ENOSR),
 	E(ENOSTR),
-#ifdef ENOSYM
-	E(ENOSYM),
-#endif
 	E(ENOSYS),
 	E(ENOTBLK),
 	E(ENOTCONN),
@@ -144,9 +141,6 @@ static const char *names_0[] = {
 #endif
 	E(EREMOTE),
 	E(EREMOTEIO),
-#ifdef EREMOTERELEASE
-	E(EREMOTERELEASE),
-#endif
 	E(ERESTART),
 	E(ERFKILL),
 	E(EROFS),
diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c
index c8c33cbaae9e..2e4fedc81621 100644
--- a/lib/fortify_kunit.c
+++ b/lib/fortify_kunit.c
@@ -15,6 +15,7 @@
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <kunit/device.h>
 #include <kunit/test.h>
 #include <linux/device.h>
 #include <linux/slab.h>
@@ -269,7 +270,7 @@ DEFINE_ALLOC_SIZE_TEST_PAIR(kvmalloc)
 	size_t len;							\
 									\
 	/* Create dummy device for devm_kmalloc()-family tests. */	\
-	dev = root_device_register(dev_name);				\
+	dev = kunit_device_register(test, dev_name);			\
 	KUNIT_ASSERT_FALSE_MSG(test, IS_ERR(dev),			\
 			       "Cannot register test device\n");	\
 									\
@@ -303,7 +304,7 @@ DEFINE_ALLOC_SIZE_TEST_PAIR(kvmalloc)
 	checker(len, devm_kmemdup(dev, "Ohai", len, gfp),		\
 		devm_kfree(dev, p));					\
 									\
-	device_unregister(dev);						\
+	kunit_device_unregister(test, dev);				\
 } while (0)
 DEFINE_ALLOC_SIZE_TEST_PAIR(devm_kmalloc)
 
diff --git a/lib/fw_table.c b/lib/fw_table.c
index b51f30a28e47..c49a09ee3853 100644
--- a/lib/fw_table.c
+++ b/lib/fw_table.c
@@ -7,7 +7,7 @@
  *  Copyright (C) 2023 Intel Corp.
  */
 #include <linux/errno.h>
-#include <linux/fw_table.h>
+#include <linux/acpi.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
@@ -85,11 +85,6 @@ acpi_get_subtable_type(char *id)
 	return ACPI_SUBTABLE_COMMON;
 }
 
-static __init_or_acpilib bool has_handler(struct acpi_subtable_proc *proc)
-{
-	return proc->handler || proc->handler_arg;
-}
-
 static __init_or_acpilib int call_handler(struct acpi_subtable_proc *proc,
 					  union acpi_subtable_headers *hdr,
 					  unsigned long end)
@@ -133,7 +128,6 @@ acpi_parse_entries_array(char *id, unsigned long table_size,
 	unsigned long table_end, subtable_len, entry_len;
 	struct acpi_subtable_entry entry;
 	int count = 0;
-	int errs = 0;
 	int i;
 
 	table_end = (unsigned long)table_header + table_header->length;
@@ -145,25 +139,19 @@ acpi_parse_entries_array(char *id, unsigned long table_size,
 	    ((unsigned long)table_header + table_size);
 	subtable_len = acpi_get_subtable_header_length(&entry);
 
-	while (((unsigned long)entry.hdr) + subtable_len  < table_end) {
-		if (max_entries && count >= max_entries)
-			break;
-
+	while (((unsigned long)entry.hdr) + subtable_len < table_end) {
 		for (i = 0; i < proc_num; i++) {
 			if (acpi_get_entry_type(&entry) != proc[i].id)
 				continue;
-			if (!has_handler(&proc[i]) ||
-			    (!errs &&
-			     call_handler(&proc[i], entry.hdr, table_end))) {
-				errs++;
-				continue;
-			}
+
+			if (!max_entries || count < max_entries)
+				if (call_handler(&proc[i], entry.hdr, table_end))
+					return -EINVAL;
 
 			proc[i].count++;
+			count++;
 			break;
 		}
-		if (i != proc_num)
-			count++;
 
 		/*
 		 * If entry->length is 0, break from this loop to avoid
@@ -180,9 +168,9 @@ acpi_parse_entries_array(char *id, unsigned long table_size,
 	}
 
 	if (max_entries && count > max_entries) {
-		pr_warn("[%4.4s:0x%02x] found the maximum %i entries\n",
-			id, proc->id, count);
+		pr_warn("[%4.4s:0x%02x] ignored %i entries of %i found\n",
+			id, proc->id, count - max_entries, count);
 	}
 
-	return errs ? -EINVAL : count;
+	return count;
 }
diff --git a/lib/group_cpus.c b/lib/group_cpus.c
index aa3f6815bb12..ee272c4cefcc 100644
--- a/lib/group_cpus.c
+++ b/lib/group_cpus.c
@@ -366,13 +366,25 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps)
 	if (!masks)
 		goto fail_node_to_cpumask;
 
-	/* Stabilize the cpumasks */
-	cpus_read_lock();
 	build_node_to_cpumask(node_to_cpumask);
 
+	/*
+	 * Make a local cache of 'cpu_present_mask', so the two stages
+	 * spread can observe consistent 'cpu_present_mask' without holding
+	 * cpu hotplug lock, then we can reduce deadlock risk with cpu
+	 * hotplug code.
+	 *
+	 * Here CPU hotplug may happen when reading `cpu_present_mask`, and
+	 * we can live with the case because it only affects that hotplug
+	 * CPU is handled in the 1st or 2nd stage, and either way is correct
+	 * from API user viewpoint since 2-stage spread is sort of
+	 * optimization.
+	 */
+	cpumask_copy(npresmsk, data_race(cpu_present_mask));
+
 	/* grouping present CPUs first */
 	ret = __group_cpus_evenly(curgrp, numgrps, node_to_cpumask,
-				  cpu_present_mask, nmsk, masks);
+				  npresmsk, nmsk, masks);
 	if (ret < 0)
 		goto fail_build_affinity;
 	nr_present = ret;
@@ -387,15 +399,13 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps)
 		curgrp = 0;
 	else
 		curgrp = nr_present;
-	cpumask_andnot(npresmsk, cpu_possible_mask, cpu_present_mask);
+	cpumask_andnot(npresmsk, cpu_possible_mask, npresmsk);
 	ret = __group_cpus_evenly(curgrp, numgrps, node_to_cpumask,
 				  npresmsk, nmsk, masks);
 	if (ret >= 0)
 		nr_others = ret;
 
  fail_build_affinity:
-	cpus_read_unlock();
-
 	if (ret >= 0)
 		WARN_ON(nr_present + nr_others < numgrps);
 
diff --git a/lib/idr.c b/lib/idr.c
index 13f2758c2377..da36054c3ca0 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -508,7 +508,7 @@ void ida_free(struct ida *ida, unsigned int id)
 			goto delete;
 		xas_store(&xas, xa_mk_value(v));
 	} else {
-		if (!test_bit(bit, bitmap->bitmap))
+		if (!bitmap || !test_bit(bit, bitmap->bitmap))
 			goto err;
 		__clear_bit(bit, bitmap->bitmap);
 		xas_set_mark(&xas, XA_FREE_MARK);
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index de7d11cf4c63..e0aa6b440ca5 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -409,7 +409,7 @@ size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, size_t byte
 		void *kaddr = kmap_local_page(page);
 		size_t n = min(bytes, (size_t)PAGE_SIZE - offset);
 
-		n = iterate_and_advance(i, bytes, kaddr,
+		n = iterate_and_advance(i, n, kaddr + offset,
 					copy_to_user_iter_nofault,
 					memcpy_to_iter);
 		kunmap_local(kaddr);
@@ -1369,19 +1369,6 @@ ssize_t import_iovec(int type, const struct iovec __user *uvec,
 }
 EXPORT_SYMBOL(import_iovec);
 
-int import_single_range(int rw, void __user *buf, size_t len,
-		 struct iovec *iov, struct iov_iter *i)
-{
-	if (len > MAX_RW_COUNT)
-		len = MAX_RW_COUNT;
-	if (unlikely(!access_ok(buf, len)))
-		return -EFAULT;
-
-	iov_iter_ubuf(i, rw, buf, len);
-	return 0;
-}
-EXPORT_SYMBOL(import_single_range);
-
 int import_ubuf(int rw, void __user *buf, size_t len, struct iov_iter *i)
 {
 	if (len > MAX_RW_COUNT)
diff --git a/lib/kunit/Makefile b/lib/kunit/Makefile
index 46f75f23dfe4..309659a32a78 100644
--- a/lib/kunit/Makefile
+++ b/lib/kunit/Makefile
@@ -7,7 +7,8 @@ kunit-objs +=				test.o \
 					assert.o \
 					try-catch.o \
 					executor.o \
-					attributes.o
+					attributes.o \
+					device.o
 
 ifeq ($(CONFIG_KUNIT_DEBUGFS),y)
 kunit-objs +=				debugfs.o
diff --git a/lib/kunit/attributes.c b/lib/kunit/attributes.c
index 1b512f7e1838..2cf04cc09372 100644
--- a/lib/kunit/attributes.c
+++ b/lib/kunit/attributes.c
@@ -58,6 +58,16 @@ static const char *attr_enum_to_string(void *attr, const char * const str_list[]
 	return str_list[val];
 }
 
+static const char *attr_bool_to_string(void *attr, bool *to_free)
+{
+	bool val = (bool)attr;
+
+	*to_free = false;
+	if (val)
+		return "true";
+	return "false";
+}
+
 static const char *attr_speed_to_string(void *attr, bool *to_free)
 {
 	return attr_enum_to_string(attr, speed_str_list, to_free);
@@ -166,6 +176,37 @@ static int attr_string_filter(void *attr, const char *input, int *err)
 	return false;
 }
 
+static int attr_bool_filter(void *attr, const char *input, int *err)
+{
+	int i, input_int = -1;
+	long val = (long)attr;
+	const char *input_str = NULL;
+
+	for (i = 0; input[i]; i++) {
+		if (!strchr(op_list, input[i])) {
+			input_str = input + i;
+			break;
+		}
+	}
+
+	if (!input_str) {
+		*err = -EINVAL;
+		pr_err("kunit executor: filter value not found: %s\n", input);
+		return false;
+	}
+
+	if (!strcmp(input_str, "true"))
+		input_int = (int)true;
+	else if (!strcmp(input_str, "false"))
+		input_int = (int)false;
+	else {
+		*err = -EINVAL;
+		pr_err("kunit executor: invalid filter input: %s\n", input);
+		return false;
+	}
+
+	return int_filter(val, input, input_int, err);
+}
 
 /* Get Attribute Methods */
 
@@ -194,6 +235,17 @@ static void *attr_module_get(void *test_or_suite, bool is_test)
 		return (void *) "";
 }
 
+static void *attr_is_init_get(void *test_or_suite, bool is_test)
+{
+	struct kunit_suite *suite = is_test ? NULL : test_or_suite;
+	struct kunit_case *test = is_test ? test_or_suite : NULL;
+
+	if (test)
+		return ((void *) NULL);
+	else
+		return ((void *) suite->is_init);
+}
+
 /* List of all Test Attributes */
 
 static struct kunit_attr kunit_attr_list[] = {
@@ -212,6 +264,14 @@ static struct kunit_attr kunit_attr_list[] = {
 		.filter = attr_string_filter,
 		.attr_default = (void *)"",
 		.print = PRINT_SUITE,
+	},
+	{
+		.name = "is_init",
+		.get_attr = attr_is_init_get,
+		.to_string = attr_bool_to_string,
+		.filter = attr_bool_filter,
+		.attr_default = (void *)false,
+		.print = PRINT_SUITE,
 	}
 };
 
diff --git a/lib/kunit/debugfs.c b/lib/kunit/debugfs.c
index 270d185737e6..d548750a325a 100644
--- a/lib/kunit/debugfs.c
+++ b/lib/kunit/debugfs.c
@@ -8,12 +8,14 @@
 #include <linux/module.h>
 
 #include <kunit/test.h>
+#include <kunit/test-bug.h>
 
 #include "string-stream.h"
 #include "debugfs.h"
 
 #define KUNIT_DEBUGFS_ROOT             "kunit"
 #define KUNIT_DEBUGFS_RESULTS          "results"
+#define KUNIT_DEBUGFS_RUN              "run"
 
 /*
  * Create a debugfs representation of test suites:
@@ -21,6 +23,8 @@
  * Path						Semantics
  * /sys/kernel/debug/kunit/<testsuite>/results	Show results of last run for
  *						testsuite
+ * /sys/kernel/debug/kunit/<testsuite>/run	Write to this file to trigger
+ *						testsuite to run
  *
  */
 
@@ -60,12 +64,14 @@ static void debugfs_print_result(struct seq_file *seq, struct string_stream *log
 static int debugfs_print_results(struct seq_file *seq, void *v)
 {
 	struct kunit_suite *suite = (struct kunit_suite *)seq->private;
-	enum kunit_status success = kunit_suite_has_succeeded(suite);
+	enum kunit_status success;
 	struct kunit_case *test_case;
 
 	if (!suite)
 		return 0;
 
+	success = kunit_suite_has_succeeded(suite);
+
 	/* Print KTAP header so the debugfs log can be parsed as valid KTAP. */
 	seq_puts(seq, "KTAP version 1\n");
 	seq_puts(seq, "1..1\n");
@@ -99,6 +105,51 @@ static int debugfs_results_open(struct inode *inode, struct file *file)
 	return single_open(file, debugfs_print_results, suite);
 }
 
+/*
+ * Print a usage message to the debugfs "run" file
+ * (/sys/kernel/debug/kunit/<testsuite>/run) if opened.
+ */
+static int debugfs_print_run(struct seq_file *seq, void *v)
+{
+	struct kunit_suite *suite = (struct kunit_suite *)seq->private;
+
+	seq_puts(seq, "Write to this file to trigger the test suite to run.\n");
+	seq_printf(seq, "usage: echo \"any string\" > /sys/kernel/debugfs/kunit/%s/run\n",
+			suite->name);
+	return 0;
+}
+
+/*
+ * The debugfs "run" file (/sys/kernel/debug/kunit/<testsuite>/run)
+ * contains no information. Write to the file to trigger the test suite
+ * to run.
+ */
+static int debugfs_run_open(struct inode *inode, struct file *file)
+{
+	struct kunit_suite *suite;
+
+	suite = (struct kunit_suite *)inode->i_private;
+
+	return single_open(file, debugfs_print_run, suite);
+}
+
+/*
+ * Trigger a test suite to run by writing to the suite's "run" debugfs
+ * file found at: /sys/kernel/debug/kunit/<testsuite>/run
+ *
+ * Note: what is written to this file will not be saved.
+ */
+static ssize_t debugfs_run(struct file *file,
+		const char __user *buf, size_t count, loff_t *ppos)
+{
+	struct inode *f_inode = file->f_inode;
+	struct kunit_suite *suite = (struct kunit_suite *) f_inode->i_private;
+
+	__kunit_test_suites_init(&suite, 1);
+
+	return count;
+}
+
 static const struct file_operations debugfs_results_fops = {
 	.open = debugfs_results_open,
 	.read = seq_read,
@@ -106,17 +157,43 @@ static const struct file_operations debugfs_results_fops = {
 	.release = debugfs_release,
 };
 
+static const struct file_operations debugfs_run_fops = {
+	.open = debugfs_run_open,
+	.read = seq_read,
+	.write = debugfs_run,
+	.llseek = seq_lseek,
+	.release = debugfs_release,
+};
+
 void kunit_debugfs_create_suite(struct kunit_suite *suite)
 {
 	struct kunit_case *test_case;
+	struct string_stream *stream;
+
+	/* If suite log already allocated, do not create new debugfs files. */
+	if (suite->log)
+		return;
 
-	/* Allocate logs before creating debugfs representation. */
-	suite->log = alloc_string_stream(GFP_KERNEL);
-	string_stream_set_append_newlines(suite->log, true);
+	/*
+	 * Allocate logs before creating debugfs representation.
+	 * The suite->log and test_case->log pointer are expected to be NULL
+	 * if there isn't a log, so only set it if the log stream was created
+	 * successfully.
+	 */
+	stream = alloc_string_stream(GFP_KERNEL);
+	if (IS_ERR_OR_NULL(stream))
+		return;
+
+	string_stream_set_append_newlines(stream, true);
+	suite->log = stream;
 
 	kunit_suite_for_each_test_case(suite, test_case) {
-		test_case->log = alloc_string_stream(GFP_KERNEL);
-		string_stream_set_append_newlines(test_case->log, true);
+		stream = alloc_string_stream(GFP_KERNEL);
+		if (IS_ERR_OR_NULL(stream))
+			goto err;
+
+		string_stream_set_append_newlines(stream, true);
+		test_case->log = stream;
 	}
 
 	suite->debugfs = debugfs_create_dir(suite->name, debugfs_rootdir);
@@ -124,6 +201,19 @@ void kunit_debugfs_create_suite(struct kunit_suite *suite)
 	debugfs_create_file(KUNIT_DEBUGFS_RESULTS, S_IFREG | 0444,
 			    suite->debugfs,
 			    suite, &debugfs_results_fops);
+
+	/* Do not create file to re-run test if test runs on init */
+	if (!suite->is_init) {
+		debugfs_create_file(KUNIT_DEBUGFS_RUN, S_IFREG | 0644,
+				    suite->debugfs,
+				    suite, &debugfs_run_fops);
+	}
+	return;
+
+err:
+	string_stream_destroy(suite->log);
+	kunit_suite_for_each_test_case(suite, test_case)
+		string_stream_destroy(test_case->log);
 }
 
 void kunit_debugfs_destroy_suite(struct kunit_suite *suite)
diff --git a/lib/kunit/device-impl.h b/lib/kunit/device-impl.h
new file mode 100644
index 000000000000..54bd55836405
--- /dev/null
+++ b/lib/kunit/device-impl.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * KUnit internal header for device helpers
+ *
+ * Header for KUnit-internal driver / bus management.
+ *
+ * Copyright (C) 2023, Google LLC.
+ * Author: David Gow <davidgow@google.com>
+ */
+
+#ifndef _KUNIT_DEVICE_IMPL_H
+#define _KUNIT_DEVICE_IMPL_H
+
+// For internal use only -- registers the kunit_bus.
+int kunit_bus_init(void);
+
+#endif //_KUNIT_DEVICE_IMPL_H
diff --git a/lib/kunit/device.c b/lib/kunit/device.c
new file mode 100644
index 000000000000..f5371287b375
--- /dev/null
+++ b/lib/kunit/device.c
@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KUnit-managed device implementation
+ *
+ * Implementation of struct kunit_device helpers for fake devices whose
+ * lifecycle is managed by KUnit.
+ *
+ * Copyright (C) 2023, Google LLC.
+ * Author: David Gow <davidgow@google.com>
+ */
+
+#include <linux/device.h>
+
+#include <kunit/test.h>
+#include <kunit/device.h>
+#include <kunit/resource.h>
+
+#include "device-impl.h"
+
+/* Wrappers for use with kunit_add_action() */
+KUNIT_DEFINE_ACTION_WRAPPER(device_unregister_wrapper, device_unregister, struct device *);
+KUNIT_DEFINE_ACTION_WRAPPER(driver_unregister_wrapper, driver_unregister, struct device_driver *);
+
+/* The root device for the KUnit bus, parent of all kunit_devices. */
+static struct device *kunit_bus_device;
+
+/* A device owned by a KUnit test. */
+struct kunit_device {
+	struct device dev;
+	/* The KUnit test which owns this device. */
+	struct kunit *owner;
+	/* If the driver is managed by KUnit and unique to this device. */
+	const struct device_driver *driver;
+};
+
+#define to_kunit_device(d) container_of_const(d, struct kunit_device, dev)
+
+static struct bus_type kunit_bus_type = {
+	.name		= "kunit",
+};
+
+/* Register the 'kunit_bus' used for fake devices. */
+int kunit_bus_init(void)
+{
+	int error;
+
+	kunit_bus_device = root_device_register("kunit");
+	if (!kunit_bus_device)
+		return -ENOMEM;
+
+	error = bus_register(&kunit_bus_type);
+	if (error)
+		bus_unregister(&kunit_bus_type);
+	return error;
+}
+
+/* Release a 'fake' KUnit device. */
+static void kunit_device_release(struct device *d)
+{
+	kfree(to_kunit_device(d));
+}
+
+/*
+ * Create and register a KUnit-managed struct device_driver on the kunit_bus.
+ * Returns an error pointer on failure.
+ */
+struct device_driver *kunit_driver_create(struct kunit *test, const char *name)
+{
+	struct device_driver *driver;
+	int err = -ENOMEM;
+
+	driver = kunit_kzalloc(test, sizeof(*driver), GFP_KERNEL);
+
+	if (!driver)
+		return ERR_PTR(err);
+
+	driver->name = name;
+	driver->bus = &kunit_bus_type;
+	driver->owner = THIS_MODULE;
+
+	err = driver_register(driver);
+	if (err) {
+		kunit_kfree(test, driver);
+		return ERR_PTR(err);
+	}
+
+	kunit_add_action(test, driver_unregister_wrapper, driver);
+	return driver;
+}
+EXPORT_SYMBOL_GPL(kunit_driver_create);
+
+/* Helper which creates a kunit_device, attaches it to the kunit_bus*/
+static struct kunit_device *kunit_device_register_internal(struct kunit *test,
+							   const char *name,
+							   const struct device_driver *drv)
+{
+	struct kunit_device *kunit_dev;
+	int err = -ENOMEM;
+
+	kunit_dev = kzalloc(sizeof(*kunit_dev), GFP_KERNEL);
+	if (!kunit_dev)
+		return ERR_PTR(err);
+
+	kunit_dev->owner = test;
+
+	err = dev_set_name(&kunit_dev->dev, "%s.%s", test->name, name);
+	if (err) {
+		kfree(kunit_dev);
+		return ERR_PTR(err);
+	}
+
+	kunit_dev->dev.release = kunit_device_release;
+	kunit_dev->dev.bus = &kunit_bus_type;
+	kunit_dev->dev.parent = kunit_bus_device;
+
+	err = device_register(&kunit_dev->dev);
+	if (err) {
+		put_device(&kunit_dev->dev);
+		return ERR_PTR(err);
+	}
+
+	kunit_add_action(test, device_unregister_wrapper, &kunit_dev->dev);
+
+	return kunit_dev;
+}
+
+/*
+ * Create and register a new KUnit-managed device, using the user-supplied device_driver.
+ * On failure, returns an error pointer.
+ */
+struct device *kunit_device_register_with_driver(struct kunit *test,
+						 const char *name,
+						 const struct device_driver *drv)
+{
+	struct kunit_device *kunit_dev = kunit_device_register_internal(test, name, drv);
+
+	if (IS_ERR_OR_NULL(kunit_dev))
+		return ERR_CAST(kunit_dev);
+
+	return &kunit_dev->dev;
+}
+EXPORT_SYMBOL_GPL(kunit_device_register_with_driver);
+
+/*
+ * Create and register a new KUnit-managed device, including a matching device_driver.
+ * On failure, returns an error pointer.
+ */
+struct device *kunit_device_register(struct kunit *test, const char *name)
+{
+	struct device_driver *drv;
+	struct kunit_device *dev;
+
+	drv = kunit_driver_create(test, name);
+	if (IS_ERR(drv))
+		return ERR_CAST(drv);
+
+	dev = kunit_device_register_internal(test, name, drv);
+	if (IS_ERR(dev)) {
+		kunit_release_action(test, driver_unregister_wrapper, (void *)drv);
+		return ERR_CAST(dev);
+	}
+
+	/* Request the driver be freed. */
+	dev->driver = drv;
+
+
+	return &dev->dev;
+}
+EXPORT_SYMBOL_GPL(kunit_device_register);
+
+/* Unregisters a KUnit-managed device early (including the driver, if automatically created). */
+void kunit_device_unregister(struct kunit *test, struct device *dev)
+{
+	const struct device_driver *driver = to_kunit_device(dev)->driver;
+
+	kunit_release_action(test, device_unregister_wrapper, dev);
+	if (driver)
+		kunit_release_action(test, driver_unregister_wrapper, (void *)driver);
+}
+EXPORT_SYMBOL_GPL(kunit_device_unregister);
+
diff --git a/lib/kunit/executor.c b/lib/kunit/executor.c
index 1236b3cd2fbb..717b9599036b 100644
--- a/lib/kunit/executor.c
+++ b/lib/kunit/executor.c
@@ -12,6 +12,8 @@
  */
 extern struct kunit_suite * const __kunit_suites_start[];
 extern struct kunit_suite * const __kunit_suites_end[];
+extern struct kunit_suite * const __kunit_init_suites_start[];
+extern struct kunit_suite * const __kunit_init_suites_end[];
 
 static char *action_param;
 
@@ -292,6 +294,37 @@ void kunit_exec_list_tests(struct kunit_suite_set *suite_set, bool include_attr)
 	}
 }
 
+struct kunit_suite_set kunit_merge_suite_sets(struct kunit_suite_set init_suite_set,
+		struct kunit_suite_set suite_set)
+{
+	struct kunit_suite_set total_suite_set = {NULL, NULL};
+	struct kunit_suite **total_suite_start = NULL;
+	size_t init_num_suites, num_suites, suite_size;
+	int i = 0;
+
+	init_num_suites = init_suite_set.end - init_suite_set.start;
+	num_suites = suite_set.end - suite_set.start;
+	suite_size = sizeof(suite_set.start);
+
+	/* Allocate memory for array of all kunit suites */
+	total_suite_start = kmalloc_array(init_num_suites + num_suites, suite_size, GFP_KERNEL);
+	if (!total_suite_start)
+		return total_suite_set;
+
+	/* Append and mark init suites and then append all other kunit suites */
+	memcpy(total_suite_start, init_suite_set.start, init_num_suites * suite_size);
+	for (i = 0; i < init_num_suites; i++)
+		total_suite_start[i]->is_init = true;
+
+	memcpy(total_suite_start + init_num_suites, suite_set.start, num_suites * suite_size);
+
+	/* Set kunit suite set start and end */
+	total_suite_set.start = total_suite_start;
+	total_suite_set.end = total_suite_start + (init_num_suites + num_suites);
+
+	return total_suite_set;
+}
+
 #if IS_BUILTIN(CONFIG_KUNIT)
 
 static char *kunit_shutdown;
@@ -313,21 +346,41 @@ static void kunit_handle_shutdown(void)
 
 int kunit_run_all_tests(void)
 {
-	struct kunit_suite_set suite_set = {
+	struct kunit_suite_set suite_set = {NULL, NULL};
+	struct kunit_suite_set filtered_suite_set = {NULL, NULL};
+	struct kunit_suite_set init_suite_set = {
+		__kunit_init_suites_start, __kunit_init_suites_end,
+	};
+	struct kunit_suite_set normal_suite_set = {
 		__kunit_suites_start, __kunit_suites_end,
 	};
+	size_t init_num_suites = init_suite_set.end - init_suite_set.start;
 	int err = 0;
+
+	if (init_num_suites > 0) {
+		suite_set = kunit_merge_suite_sets(init_suite_set, normal_suite_set);
+		if (!suite_set.start)
+			goto out;
+	} else
+		suite_set = normal_suite_set;
+
 	if (!kunit_enabled()) {
 		pr_info("kunit: disabled\n");
-		goto out;
+		goto free_out;
 	}
 
 	if (filter_glob_param || filter_param) {
-		suite_set = kunit_filter_suites(&suite_set, filter_glob_param,
+		filtered_suite_set = kunit_filter_suites(&suite_set, filter_glob_param,
 				filter_param, filter_action_param, &err);
+
+		/* Free original suite set before using filtered suite set */
+		if (init_num_suites > 0)
+			kfree(suite_set.start);
+		suite_set = filtered_suite_set;
+
 		if (err) {
 			pr_err("kunit executor: error filtering suites: %d\n", err);
-			goto out;
+			goto free_out;
 		}
 	}
 
@@ -340,9 +393,12 @@ int kunit_run_all_tests(void)
 	else
 		pr_err("kunit executor: unknown action '%s'\n", action_param);
 
-	if (filter_glob_param || filter_param) { /* a copy was made of each suite */
+free_out:
+	if (filter_glob_param || filter_param)
 		kunit_free_suite_set(suite_set);
-	}
+	else if (init_num_suites > 0)
+		/* Don't use kunit_free_suite_set because suites aren't individually allocated */
+		kfree(suite_set.start);
 
 out:
 	kunit_handle_shutdown();
diff --git a/lib/kunit/kunit-example-test.c b/lib/kunit/kunit-example-test.c
index 6bb5c2ef6696..798924f7cc86 100644
--- a/lib/kunit/kunit-example-test.c
+++ b/lib/kunit/kunit-example-test.c
@@ -169,6 +169,16 @@ static int subtract_one(int i)
 }
 
 /*
+ * If the function to be replaced is static within a module it is
+ * useful to export a pointer to that function instead of having
+ * to change the static function to a non-static exported function.
+ *
+ * This pointer simulates a module exporting a pointer to a static
+ * function.
+ */
+static int (* const add_one_fn_ptr)(int i) = add_one;
+
+/*
  * This test shows the use of static stubs.
  */
 static void example_static_stub_test(struct kunit *test)
@@ -187,6 +197,30 @@ static void example_static_stub_test(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, add_one(1), 2);
 }
 
+/*
+ * This test shows the use of static stubs when the function being
+ * replaced is provided as a pointer-to-function instead of the
+ * actual function. This is useful for providing access to static
+ * functions in a module by exporting a pointer to that function
+ * instead of having to change the static function to a non-static
+ * exported function.
+ */
+static void example_static_stub_using_fn_ptr_test(struct kunit *test)
+{
+	/* By default, function is not stubbed. */
+	KUNIT_EXPECT_EQ(test, add_one(1), 2);
+
+	/* Replace add_one() with subtract_one(). */
+	kunit_activate_static_stub(test, add_one_fn_ptr, subtract_one);
+
+	/* add_one() is now replaced. */
+	KUNIT_EXPECT_EQ(test, add_one(1), 0);
+
+	/* Return add_one() to normal. */
+	kunit_deactivate_static_stub(test, add_one_fn_ptr);
+	KUNIT_EXPECT_EQ(test, add_one(1), 2);
+}
+
 static const struct example_param {
 	int value;
 } example_params_array[] = {
@@ -222,6 +256,20 @@ static void example_params_test(struct kunit *test)
 }
 
 /*
+ * This test shows the use of test->priv.
+ */
+static void example_priv_test(struct kunit *test)
+{
+	/* unless setup in suite->init(), test->priv is NULL */
+	KUNIT_ASSERT_NULL(test, test->priv);
+
+	/* but can be used to pass arbitrary data to other functions */
+	test->priv = kunit_kzalloc(test, 1, GFP_KERNEL);
+	KUNIT_EXPECT_NOT_NULL(test, test->priv);
+	KUNIT_ASSERT_PTR_EQ(test, test->priv, kunit_get_current_test()->priv);
+}
+
+/*
  * This test should always pass. Can be used to practice filtering attributes.
  */
 static void example_slow_test(struct kunit *test)
@@ -245,6 +293,8 @@ static struct kunit_case example_test_cases[] = {
 	KUNIT_CASE(example_mark_skipped_test),
 	KUNIT_CASE(example_all_expect_macros_test),
 	KUNIT_CASE(example_static_stub_test),
+	KUNIT_CASE(example_static_stub_using_fn_ptr_test),
+	KUNIT_CASE(example_priv_test),
 	KUNIT_CASE_PARAM(example_params_test, example_gen_params),
 	KUNIT_CASE_SLOW(example_slow_test),
 	{}
@@ -287,4 +337,41 @@ static struct kunit_suite example_test_suite = {
  */
 kunit_test_suites(&example_test_suite);
 
+static int __init init_add(int x, int y)
+{
+	return (x + y);
+}
+
+/*
+ * This test should always pass. Can be used to test init suites.
+ */
+static void __init example_init_test(struct kunit *test)
+{
+	KUNIT_EXPECT_EQ(test, init_add(1, 1), 2);
+}
+
+/*
+ * The kunit_case struct cannot be marked as __initdata as this will be
+ * used in debugfs to retrieve results after test has run
+ */
+static struct kunit_case __refdata example_init_test_cases[] = {
+	KUNIT_CASE(example_init_test),
+	{}
+};
+
+/*
+ * The kunit_suite struct cannot be marked as __initdata as this will be
+ * used in debugfs to retrieve results after test has run
+ */
+static struct kunit_suite example_init_test_suite = {
+	.name = "example_init",
+	.test_cases = example_init_test_cases,
+};
+
+/*
+ * This registers the test suite and marks the suite as using init data
+ * and/or functions.
+ */
+kunit_test_init_section_suites(&example_init_test_suite);
+
 MODULE_LICENSE("GPL v2");
diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c
index 99d2a3a528e1..c4259d910356 100644
--- a/lib/kunit/kunit-test.c
+++ b/lib/kunit/kunit-test.c
@@ -5,9 +5,13 @@
  * Copyright (C) 2019, Google LLC.
  * Author: Brendan Higgins <brendanhiggins@google.com>
  */
+#include "linux/gfp_types.h"
 #include <kunit/test.h>
 #include <kunit/test-bug.h>
 
+#include <linux/device.h>
+#include <kunit/device.h>
+
 #include "string-stream.h"
 #include "try-catch-impl.h"
 
@@ -538,10 +542,7 @@ static struct kunit_suite kunit_resource_test_suite = {
 #if IS_BUILTIN(CONFIG_KUNIT_TEST)
 
 /* This avoids a cast warning if kfree() is passed direct to kunit_add_action(). */
-static void kfree_wrapper(void *p)
-{
-	kfree(p);
-}
+KUNIT_DEFINE_ACTION_WRAPPER(kfree_wrapper, kfree, const void *);
 
 static void kunit_log_test(struct kunit *test)
 {
@@ -562,7 +563,7 @@ static void kunit_log_test(struct kunit *test)
 	KUNIT_EXPECT_TRUE(test, test->log->append_newlines);
 
 	full_log = string_stream_get_string(test->log);
-	kunit_add_action(test, (kunit_action_t *)kfree, full_log);
+	kunit_add_action(test, kfree_wrapper, full_log);
 	KUNIT_EXPECT_NOT_ERR_OR_NULL(test,
 				     strstr(full_log, "put this in log."));
 	KUNIT_EXPECT_NOT_ERR_OR_NULL(test,
@@ -690,6 +691,134 @@ static struct kunit_case kunit_current_test_cases[] = {
 	{}
 };
 
+static void test_dev_action(void *priv)
+{
+	*(void **)priv = (void *)1;
+}
+
+static void kunit_device_test(struct kunit *test)
+{
+	struct device *test_device;
+	long action_was_run = 0;
+
+	test_device = kunit_device_register(test, "my_device");
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, test_device);
+
+	// Add an action to verify cleanup.
+	devm_add_action(test_device, test_dev_action, &action_was_run);
+
+	KUNIT_EXPECT_EQ(test, action_was_run, 0);
+
+	kunit_device_unregister(test, test_device);
+
+	KUNIT_EXPECT_EQ(test, action_was_run, 1);
+}
+
+static void kunit_device_cleanup_test(struct kunit *test)
+{
+	struct device *test_device;
+	long action_was_run = 0;
+
+	test_device = kunit_device_register(test, "my_device");
+	KUNIT_ASSERT_NOT_NULL(test, test_device);
+
+	/* Add an action to verify cleanup. */
+	devm_add_action(test_device, test_dev_action, &action_was_run);
+
+	KUNIT_EXPECT_EQ(test, action_was_run, 0);
+
+	/* Force KUnit to run cleanup early. */
+	kunit_cleanup(test);
+
+	KUNIT_EXPECT_EQ(test, action_was_run, 1);
+}
+
+struct driver_test_state {
+	bool driver_device_probed;
+	bool driver_device_removed;
+	long action_was_run;
+};
+
+static int driver_probe_hook(struct device *dev)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct driver_test_state *state = (struct driver_test_state *)test->priv;
+
+	state->driver_device_probed = true;
+	return 0;
+}
+
+static int driver_remove_hook(struct device *dev)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct driver_test_state *state = (struct driver_test_state *)test->priv;
+
+	state->driver_device_removed = true;
+	return 0;
+}
+
+static void kunit_device_driver_test(struct kunit *test)
+{
+	struct device_driver *test_driver;
+	struct device *test_device;
+	struct driver_test_state *test_state = kunit_kzalloc(test, sizeof(*test_state), GFP_KERNEL);
+
+	test->priv = test_state;
+	test_driver = kunit_driver_create(test, "my_driver");
+
+	// This can fail with an error pointer.
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, test_driver);
+
+	test_driver->probe = driver_probe_hook;
+	test_driver->remove = driver_remove_hook;
+
+	test_device = kunit_device_register_with_driver(test, "my_device", test_driver);
+
+	// This can fail with an error pointer.
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, test_device);
+
+	// Make sure the probe function was called.
+	KUNIT_ASSERT_TRUE(test, test_state->driver_device_probed);
+
+	// Add an action to verify cleanup.
+	devm_add_action(test_device, test_dev_action, &test_state->action_was_run);
+
+	KUNIT_EXPECT_EQ(test, test_state->action_was_run, 0);
+
+	kunit_device_unregister(test, test_device);
+	test_device = NULL;
+
+	// Make sure the remove hook was called.
+	KUNIT_ASSERT_TRUE(test, test_state->driver_device_removed);
+
+	// We're going to test this again.
+	test_state->driver_device_probed = false;
+
+	// The driver should not automatically be destroyed by
+	// kunit_device_unregister, so we can re-use it.
+	test_device = kunit_device_register_with_driver(test, "my_device", test_driver);
+
+	// This can fail with an error pointer.
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, test_device);
+
+	// Probe was called again.
+	KUNIT_ASSERT_TRUE(test, test_state->driver_device_probed);
+
+	// Everything is automatically freed here.
+}
+
+static struct kunit_case kunit_device_test_cases[] = {
+	KUNIT_CASE(kunit_device_test),
+	KUNIT_CASE(kunit_device_cleanup_test),
+	KUNIT_CASE(kunit_device_driver_test),
+	{}
+};
+
+static struct kunit_suite kunit_device_test_suite = {
+	.name = "kunit_device",
+	.test_cases = kunit_device_test_cases,
+};
+
 static struct kunit_suite kunit_current_test_suite = {
 	.name = "kunit_current",
 	.test_cases = kunit_current_test_cases,
@@ -697,6 +826,6 @@ static struct kunit_suite kunit_current_test_suite = {
 
 kunit_test_suites(&kunit_try_catch_test_suite, &kunit_resource_test_suite,
 		  &kunit_log_test_suite, &kunit_status_test_suite,
-		  &kunit_current_test_suite);
+		  &kunit_current_test_suite, &kunit_device_test_suite);
 
 MODULE_LICENSE("GPL v2");
diff --git a/lib/kunit/string-stream-test.c b/lib/kunit/string-stream-test.c
index 06822766f29a..03fb511826f7 100644
--- a/lib/kunit/string-stream-test.c
+++ b/lib/kunit/string-stream-test.c
@@ -72,7 +72,7 @@ static void string_stream_unmanaged_init_test(struct kunit *test)
 
 	KUNIT_EXPECT_EQ(test, stream->length, 0);
 	KUNIT_EXPECT_TRUE(test, list_empty(&stream->fragments));
-	KUNIT_EXPECT_EQ(test, stream->gfp, GFP_KERNEL);
+	KUNIT_EXPECT_TRUE(test, (stream->gfp == GFP_KERNEL));
 	KUNIT_EXPECT_FALSE(test, stream->append_newlines);
 
 	KUNIT_EXPECT_TRUE(test, string_stream_is_empty(stream));
diff --git a/lib/kunit/string-stream.c b/lib/kunit/string-stream.c
index a6f3616c2048..54f4fdcbfac8 100644
--- a/lib/kunit/string-stream.c
+++ b/lib/kunit/string-stream.c
@@ -173,7 +173,7 @@ void string_stream_destroy(struct string_stream *stream)
 {
 	KUNIT_STATIC_STUB_REDIRECT(string_stream_destroy, stream);
 
-	if (!stream)
+	if (IS_ERR_OR_NULL(stream))
 		return;
 
 	string_stream_clear(stream);
diff --git a/lib/kunit/test.c b/lib/kunit/test.c
index f2eb71f1a66c..f95d2093a0aa 100644
--- a/lib/kunit/test.c
+++ b/lib/kunit/test.c
@@ -13,15 +13,19 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
+#include <linux/mutex.h>
 #include <linux/panic.h>
 #include <linux/sched/debug.h>
 #include <linux/sched.h>
 
 #include "debugfs.h"
+#include "device-impl.h"
 #include "hooks-impl.h"
 #include "string-stream.h"
 #include "try-catch-impl.h"
 
+static DEFINE_MUTEX(kunit_run_lock);
+
 /*
  * Hook to fail the current test and print an error message to the log.
  */
@@ -338,6 +342,36 @@ void kunit_init_test(struct kunit *test, const char *name, struct string_stream
 }
 EXPORT_SYMBOL_GPL(kunit_init_test);
 
+/* Only warn when a test takes more than twice the threshold */
+#define KUNIT_SPEED_WARNING_MULTIPLIER	2
+
+/* Slow tests are defined as taking more than 1s */
+#define KUNIT_SPEED_SLOW_THRESHOLD_S	1
+
+#define KUNIT_SPEED_SLOW_WARNING_THRESHOLD_S	\
+	(KUNIT_SPEED_WARNING_MULTIPLIER * KUNIT_SPEED_SLOW_THRESHOLD_S)
+
+#define s_to_timespec64(s) ns_to_timespec64((s) * NSEC_PER_SEC)
+
+static void kunit_run_case_check_speed(struct kunit *test,
+				       struct kunit_case *test_case,
+				       struct timespec64 duration)
+{
+	struct timespec64 slow_thr =
+		s_to_timespec64(KUNIT_SPEED_SLOW_WARNING_THRESHOLD_S);
+	enum kunit_speed speed = test_case->attr.speed;
+
+	if (timespec64_compare(&duration, &slow_thr) < 0)
+		return;
+
+	if (speed == KUNIT_SPEED_VERY_SLOW || speed == KUNIT_SPEED_SLOW)
+		return;
+
+	kunit_warn(test,
+		   "Test should be marked slow (runtime: %lld.%09lds)",
+		   duration.tv_sec, duration.tv_nsec);
+}
+
 /*
  * Initializes and runs test case. Does not clean up or do post validations.
  */
@@ -345,6 +379,8 @@ static void kunit_run_case_internal(struct kunit *test,
 				    struct kunit_suite *suite,
 				    struct kunit_case *test_case)
 {
+	struct timespec64 start, end;
+
 	if (suite->init) {
 		int ret;
 
@@ -356,7 +392,13 @@ static void kunit_run_case_internal(struct kunit *test,
 		}
 	}
 
+	ktime_get_ts64(&start);
+
 	test_case->run_case(test);
+
+	ktime_get_ts64(&end);
+
+	kunit_run_case_check_speed(test, test_case, timespec64_sub(end, start));
 }
 
 static void kunit_case_internal_cleanup(struct kunit *test)
@@ -622,6 +664,7 @@ int kunit_run_tests(struct kunit_suite *suite)
 				test.param_index++;
 				test.status = KUNIT_SUCCESS;
 				test.status_comment[0] = '\0';
+				test.priv = NULL;
 			}
 		}
 
@@ -654,6 +697,9 @@ static void kunit_init_suite(struct kunit_suite *suite)
 	kunit_debugfs_create_suite(suite);
 	suite->status_comment[0] = '\0';
 	suite->suite_init_err = 0;
+
+	if (suite->log)
+		string_stream_clear(suite->log);
 }
 
 bool kunit_enabled(void)
@@ -670,6 +716,13 @@ int __kunit_test_suites_init(struct kunit_suite * const * const suites, int num_
 		return 0;
 	}
 
+	kunit_suite_counter = 1;
+
+	/* Use mutex lock to guard against running tests concurrently. */
+	if (mutex_lock_interruptible(&kunit_run_lock)) {
+		pr_err("kunit: test interrupted\n");
+		return -EINTR;
+	}
 	static_branch_inc(&kunit_running);
 
 	for (i = 0; i < num_suites; i++) {
@@ -678,6 +731,7 @@ int __kunit_test_suites_init(struct kunit_suite * const * const suites, int num_
 	}
 
 	static_branch_dec(&kunit_running);
+	mutex_unlock(&kunit_run_lock);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(__kunit_test_suites_init);
@@ -696,36 +750,46 @@ void __kunit_test_suites_exit(struct kunit_suite **suites, int num_suites)
 
 	for (i = 0; i < num_suites; i++)
 		kunit_exit_suite(suites[i]);
-
-	kunit_suite_counter = 1;
 }
 EXPORT_SYMBOL_GPL(__kunit_test_suites_exit);
 
 #ifdef CONFIG_MODULES
 static void kunit_module_init(struct module *mod)
 {
-	struct kunit_suite_set suite_set = {
+	struct kunit_suite_set suite_set, filtered_set;
+	struct kunit_suite_set normal_suite_set = {
 		mod->kunit_suites, mod->kunit_suites + mod->num_kunit_suites,
 	};
+	struct kunit_suite_set init_suite_set = {
+		mod->kunit_init_suites, mod->kunit_init_suites + mod->num_kunit_init_suites,
+	};
 	const char *action = kunit_action();
 	int err = 0;
 
-	suite_set = kunit_filter_suites(&suite_set,
+	if (mod->num_kunit_init_suites > 0)
+		suite_set = kunit_merge_suite_sets(init_suite_set, normal_suite_set);
+	else
+		suite_set = normal_suite_set;
+
+	filtered_set = kunit_filter_suites(&suite_set,
 					kunit_filter_glob() ?: "*.*",
 					kunit_filter(), kunit_filter_action(),
 					&err);
 	if (err)
 		pr_err("kunit module: error filtering suites: %d\n", err);
 
-	mod->kunit_suites = (struct kunit_suite **)suite_set.start;
-	mod->num_kunit_suites = suite_set.end - suite_set.start;
+	mod->kunit_suites = (struct kunit_suite **)filtered_set.start;
+	mod->num_kunit_suites = filtered_set.end - filtered_set.start;
+
+	if (mod->num_kunit_init_suites > 0)
+		kfree(suite_set.start);
 
 	if (!action)
-		kunit_exec_run_tests(&suite_set, false);
+		kunit_exec_run_tests(&filtered_set, false);
 	else if (!strcmp(action, "list"))
-		kunit_exec_list_tests(&suite_set, false);
+		kunit_exec_list_tests(&filtered_set, false);
 	else if (!strcmp(action, "list_attr"))
-		kunit_exec_list_tests(&suite_set, true);
+		kunit_exec_list_tests(&filtered_set, true);
 	else
 		pr_err("kunit: unknown action '%s'\n", action);
 }
@@ -772,6 +836,8 @@ static struct notifier_block kunit_mod_nb = {
 };
 #endif
 
+KUNIT_DEFINE_ACTION_WRAPPER(kfree_action_wrapper, kfree, const void *)
+
 void *kunit_kmalloc_array(struct kunit *test, size_t n, size_t size, gfp_t gfp)
 {
 	void *data;
@@ -781,7 +847,7 @@ void *kunit_kmalloc_array(struct kunit *test, size_t n, size_t size, gfp_t gfp)
 	if (!data)
 		return NULL;
 
-	if (kunit_add_action_or_reset(test, (kunit_action_t *)kfree, data) != 0)
+	if (kunit_add_action_or_reset(test, kfree_action_wrapper, data) != 0)
 		return NULL;
 
 	return data;
@@ -793,7 +859,7 @@ void kunit_kfree(struct kunit *test, const void *ptr)
 	if (!ptr)
 		return;
 
-	kunit_release_action(test, (kunit_action_t *)kfree, (void *)ptr);
+	kunit_release_action(test, kfree_action_wrapper, (void *)ptr);
 }
 EXPORT_SYMBOL_GPL(kunit_kfree);
 
@@ -838,6 +904,8 @@ static int __init kunit_init(void)
 	kunit_install_hooks();
 
 	kunit_debugfs_init();
+
+	kunit_bus_init();
 #ifdef CONFIG_MODULES
 	return register_module_notifier(&kunit_mod_nb);
 #else
diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index bb24d84a4922..6f241bb38799 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -4,6 +4,8 @@
  * Copyright (c) 2018-2022 Oracle Corporation
  * Authors: Liam R. Howlett <Liam.Howlett@oracle.com>
  *	    Matthew Wilcox <willy@infradead.org>
+ * Copyright (c) 2023 ByteDance
+ * Author: Peng Zhang <zhangpeng.00@bytedance.com>
  */
 
 /*
@@ -14,8 +16,8 @@
  * and are simply the slot index + the minimum of the node.
  *
  * In regular B-Tree terms, pivots are called keys.  The term pivot is used to
- * indicate that the tree is specifying ranges,  Pivots may appear in the
- * subtree with an entry attached to the value where as keys are unique to a
+ * indicate that the tree is specifying ranges.  Pivots may appear in the
+ * subtree with an entry attached to the value whereas keys are unique to a
  * specific position of a B-tree.  Pivot values are inclusive of the slot with
  * the same index.
  *
@@ -165,6 +167,11 @@ static inline int mt_alloc_bulk(gfp_t gfp, size_t size, void **nodes)
 	return kmem_cache_alloc_bulk(maple_node_cache, gfp, size, nodes);
 }
 
+static inline void mt_free_one(struct maple_node *node)
+{
+	kmem_cache_free(maple_node_cache, node);
+}
+
 static inline void mt_free_bulk(size_t size, void __rcu **nodes)
 {
 	kmem_cache_free_bulk(maple_node_cache, size, (void **)nodes);
@@ -205,23 +212,29 @@ static unsigned int mas_mt_height(struct ma_state *mas)
 	return mt_height(mas->tree);
 }
 
-static inline enum maple_type mte_node_type(const struct maple_enode *entry)
+static inline unsigned int mt_attr(struct maple_tree *mt)
+{
+	return mt->ma_flags & ~MT_FLAGS_HEIGHT_MASK;
+}
+
+static __always_inline enum maple_type mte_node_type(
+		const struct maple_enode *entry)
 {
 	return ((unsigned long)entry >> MAPLE_NODE_TYPE_SHIFT) &
 		MAPLE_NODE_TYPE_MASK;
 }
 
-static inline bool ma_is_dense(const enum maple_type type)
+static __always_inline bool ma_is_dense(const enum maple_type type)
 {
 	return type < maple_leaf_64;
 }
 
-static inline bool ma_is_leaf(const enum maple_type type)
+static __always_inline bool ma_is_leaf(const enum maple_type type)
 {
 	return type < maple_range_64;
 }
 
-static inline bool mte_is_leaf(const struct maple_enode *entry)
+static __always_inline bool mte_is_leaf(const struct maple_enode *entry)
 {
 	return ma_is_leaf(mte_node_type(entry));
 }
@@ -230,60 +243,50 @@ static inline bool mte_is_leaf(const struct maple_enode *entry)
  * We also reserve values with the bottom two bits set to '10' which are
  * below 4096
  */
-static inline bool mt_is_reserved(const void *entry)
+static __always_inline bool mt_is_reserved(const void *entry)
 {
 	return ((unsigned long)entry < MAPLE_RESERVED_RANGE) &&
 		xa_is_internal(entry);
 }
 
-static inline void mas_set_err(struct ma_state *mas, long err)
+static __always_inline void mas_set_err(struct ma_state *mas, long err)
 {
 	mas->node = MA_ERROR(err);
+	mas->status = ma_error;
 }
 
-static inline bool mas_is_ptr(const struct ma_state *mas)
+static __always_inline bool mas_is_ptr(const struct ma_state *mas)
 {
-	return mas->node == MAS_ROOT;
+	return mas->status == ma_root;
 }
 
-static inline bool mas_is_start(const struct ma_state *mas)
+static __always_inline bool mas_is_start(const struct ma_state *mas)
 {
-	return mas->node == MAS_START;
+	return mas->status == ma_start;
 }
 
-bool mas_is_err(struct ma_state *mas)
+static __always_inline bool mas_is_none(const struct ma_state *mas)
 {
-	return xa_is_err(mas->node);
+	return mas->status == ma_none;
 }
 
-static __always_inline bool mas_is_overflow(struct ma_state *mas)
+static __always_inline bool mas_is_paused(const struct ma_state *mas)
 {
-	if (unlikely(mas->node == MAS_OVERFLOW))
-		return true;
-
-	return false;
+	return mas->status == ma_pause;
 }
 
-static __always_inline bool mas_is_underflow(struct ma_state *mas)
+static __always_inline bool mas_is_overflow(struct ma_state *mas)
 {
-	if (unlikely(mas->node == MAS_UNDERFLOW))
-		return true;
-
-	return false;
+	return mas->status == ma_overflow;
 }
 
-static inline bool mas_searchable(struct ma_state *mas)
+static inline bool mas_is_underflow(struct ma_state *mas)
 {
-	if (mas_is_none(mas))
-		return false;
-
-	if (mas_is_ptr(mas))
-		return false;
-
-	return true;
+	return mas->status == ma_underflow;
 }
 
-static inline struct maple_node *mte_to_node(const struct maple_enode *entry)
+static __always_inline struct maple_node *mte_to_node(
+		const struct maple_enode *entry)
 {
 	return (struct maple_node *)((unsigned long)entry & ~MAPLE_NODE_MASK);
 }
@@ -360,12 +363,12 @@ static inline bool mte_has_null(const struct maple_enode *node)
 	return (unsigned long)node & MAPLE_ENODE_NULL;
 }
 
-static inline bool ma_is_root(struct maple_node *node)
+static __always_inline bool ma_is_root(struct maple_node *node)
 {
 	return ((unsigned long)node->parent & MA_ROOT_PARENT);
 }
 
-static inline bool mte_is_root(const struct maple_enode *node)
+static __always_inline bool mte_is_root(const struct maple_enode *node)
 {
 	return ma_is_root(mte_to_node(node));
 }
@@ -375,7 +378,7 @@ static inline bool mas_is_root_limits(const struct ma_state *mas)
 	return !mas->min && mas->max == ULONG_MAX;
 }
 
-static inline bool mt_is_alloc(struct maple_tree *mt)
+static __always_inline bool mt_is_alloc(struct maple_tree *mt)
 {
 	return (mt->ma_flags & MT_FLAGS_ALLOC_RANGE);
 }
@@ -514,11 +517,12 @@ void mas_set_parent(struct ma_state *mas, struct maple_enode *enode,
  *
  * Return: The slot in the parent node where @enode resides.
  */
-static inline unsigned int mte_parent_slot(const struct maple_enode *enode)
+static __always_inline
+unsigned int mte_parent_slot(const struct maple_enode *enode)
 {
 	unsigned long val = (unsigned long)mte_to_node(enode)->parent;
 
-	if (val & MA_ROOT_PARENT)
+	if (unlikely(val & MA_ROOT_PARENT))
 		return 0;
 
 	/*
@@ -534,7 +538,8 @@ static inline unsigned int mte_parent_slot(const struct maple_enode *enode)
  *
  * Return: The parent maple node.
  */
-static inline struct maple_node *mte_parent(const struct maple_enode *enode)
+static __always_inline
+struct maple_node *mte_parent(const struct maple_enode *enode)
 {
 	return (void *)((unsigned long)
 			(mte_to_node(enode)->parent) & ~MAPLE_NODE_MASK);
@@ -546,7 +551,7 @@ static inline struct maple_node *mte_parent(const struct maple_enode *enode)
  *
  * Return: true if dead, false otherwise.
  */
-static inline bool ma_dead_node(const struct maple_node *node)
+static __always_inline bool ma_dead_node(const struct maple_node *node)
 {
 	struct maple_node *parent;
 
@@ -562,7 +567,7 @@ static inline bool ma_dead_node(const struct maple_node *node)
  *
  * Return: true if dead, false otherwise.
  */
-static inline bool mte_dead_node(const struct maple_enode *enode)
+static __always_inline bool mte_dead_node(const struct maple_enode *enode)
 {
 	struct maple_node *parent, *node;
 
@@ -680,35 +685,6 @@ static inline unsigned long *ma_gaps(struct maple_node *node,
 }
 
 /*
- * mas_pivot() - Get the pivot at @piv of the maple encoded node.
- * @mas: The maple state.
- * @piv: The pivot.
- *
- * Return: the pivot at @piv of @mn.
- */
-static inline unsigned long mas_pivot(struct ma_state *mas, unsigned char piv)
-{
-	struct maple_node *node = mas_mn(mas);
-	enum maple_type type = mte_node_type(mas->node);
-
-	if (MAS_WARN_ON(mas, piv >= mt_pivots[type])) {
-		mas_set_err(mas, -EIO);
-		return 0;
-	}
-
-	switch (type) {
-	case maple_arange_64:
-		return node->ma64.pivot[piv];
-	case maple_range_64:
-	case maple_leaf_64:
-		return node->mr64.pivot[piv];
-	case maple_dense:
-		return 0;
-	}
-	return 0;
-}
-
-/*
  * mas_safe_pivot() - get the pivot at @piv or mas->max.
  * @mas: The maple state
  * @pivots: The pointer to the maple node pivots
@@ -718,7 +694,7 @@ static inline unsigned long mas_pivot(struct ma_state *mas, unsigned char piv)
  * Return: The pivot at @piv within the limit of the @pivots array, @mas->max
  * otherwise.
  */
-static inline unsigned long
+static __always_inline unsigned long
 mas_safe_pivot(const struct ma_state *mas, unsigned long *pivots,
 	       unsigned char piv, enum maple_type type)
 {
@@ -759,7 +735,6 @@ static inline void mte_set_pivot(struct maple_enode *mn, unsigned char piv,
 
 	BUG_ON(piv >= mt_pivots[type]);
 	switch (type) {
-	default:
 	case maple_range_64:
 	case maple_leaf_64:
 		node->mr64.pivot[piv] = val;
@@ -783,7 +758,6 @@ static inline void mte_set_pivot(struct maple_enode *mn, unsigned char piv,
 static inline void __rcu **ma_slots(struct maple_node *mn, enum maple_type mt)
 {
 	switch (mt) {
-	default:
 	case maple_arange_64:
 		return mn->ma64.slot;
 	case maple_range_64:
@@ -792,6 +766,8 @@ static inline void __rcu **ma_slots(struct maple_node *mn, enum maple_type mt)
 	case maple_dense:
 		return mn->slot;
 	}
+
+	return NULL;
 }
 
 static inline bool mt_write_locked(const struct maple_tree *mt)
@@ -800,20 +776,20 @@ static inline bool mt_write_locked(const struct maple_tree *mt)
 		lockdep_is_held(&mt->ma_lock);
 }
 
-static inline bool mt_locked(const struct maple_tree *mt)
+static __always_inline bool mt_locked(const struct maple_tree *mt)
 {
 	return mt_external_lock(mt) ? mt_lock_is_held(mt) :
 		lockdep_is_held(&mt->ma_lock);
 }
 
-static inline void *mt_slot(const struct maple_tree *mt,
+static __always_inline void *mt_slot(const struct maple_tree *mt,
 		void __rcu **slots, unsigned char offset)
 {
 	return rcu_dereference_check(slots[offset], mt_locked(mt));
 }
 
-static inline void *mt_slot_locked(struct maple_tree *mt, void __rcu **slots,
-				   unsigned char offset)
+static __always_inline void *mt_slot_locked(struct maple_tree *mt,
+		void __rcu **slots, unsigned char offset)
 {
 	return rcu_dereference_protected(slots[offset], mt_write_locked(mt));
 }
@@ -825,8 +801,8 @@ static inline void *mt_slot_locked(struct maple_tree *mt, void __rcu **slots,
  *
  * Return: The entry stored in @slots at the @offset.
  */
-static inline void *mas_slot_locked(struct ma_state *mas, void __rcu **slots,
-				       unsigned char offset)
+static __always_inline void *mas_slot_locked(struct ma_state *mas,
+		void __rcu **slots, unsigned char offset)
 {
 	return mt_slot_locked(mas->tree, slots, offset);
 }
@@ -839,8 +815,8 @@ static inline void *mas_slot_locked(struct ma_state *mas, void __rcu **slots,
  *
  * Return: The entry stored in @slots at the @offset
  */
-static inline void *mas_slot(struct ma_state *mas, void __rcu **slots,
-			     unsigned char offset)
+static __always_inline void *mas_slot(struct ma_state *mas, void __rcu **slots,
+		unsigned char offset)
 {
 	return mt_slot(mas->tree, slots, offset);
 }
@@ -851,7 +827,7 @@ static inline void *mas_slot(struct ma_state *mas, void __rcu **slots,
  *
  * Return: The pointer to the root of the tree
  */
-static inline void *mas_root(struct ma_state *mas)
+static __always_inline void *mas_root(struct ma_state *mas)
 {
 	return rcu_dereference_check(mas->tree->ma_root, mt_locked(mas->tree));
 }
@@ -954,10 +930,8 @@ static inline unsigned char ma_meta_end(struct maple_node *mn,
 /*
  * ma_meta_gap() - Get the largest gap location of a node from the metadata
  * @mn: The maple node
- * @mt: The maple node type
  */
-static inline unsigned char ma_meta_gap(struct maple_node *mn,
-					enum maple_type mt)
+static inline unsigned char ma_meta_gap(struct maple_node *mn)
 {
 	return mn->ma64.meta.gap;
 }
@@ -1112,14 +1086,16 @@ static int mas_ascend(struct ma_state *mas)
 		return 0;
 	}
 
-	if (!mas->min)
+	min = 0;
+	max = ULONG_MAX;
+	if (!mas->offset) {
+		min = mas->min;
 		set_min = true;
+	}
 
 	if (mas->max == ULONG_MAX)
 		set_max = true;
 
-	min = 0;
-	max = ULONG_MAX;
 	do {
 		p_enode = a_enode;
 		a_type = mas_parent_type(mas, p_enode);
@@ -1258,6 +1234,7 @@ static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp)
 	if (mas->mas_flags & MA_STATE_PREALLOC) {
 		if (allocated)
 			return;
+		BUG_ON(!allocated);
 		WARN_ON(!allocated);
 	}
 
@@ -1363,14 +1340,14 @@ static void mas_node_count(struct ma_state *mas, int count)
  * mas_start() - Sets up maple state for operations.
  * @mas: The maple state.
  *
- * If mas->node == MAS_START, then set the min, max and depth to
+ * If mas->status == mas_start, then set the min, max and depth to
  * defaults.
  *
  * Return:
- * - If mas->node is an error or not MAS_START, return NULL.
- * - If it's an empty tree:     NULL & mas->node == MAS_NONE
- * - If it's a single entry:    The entry & mas->node == MAS_ROOT
- * - If it's a tree:            NULL & mas->node == safe root node.
+ * - If mas->node is an error or not mas_start, return NULL.
+ * - If it's an empty tree:     NULL & mas->status == ma_none
+ * - If it's a single entry:    The entry & mas->status == mas_root
+ * - If it's a tree:            NULL & mas->status == safe root node.
  */
 static inline struct maple_enode *mas_start(struct ma_state *mas)
 {
@@ -1386,6 +1363,7 @@ retry:
 		/* Tree with nodes */
 		if (likely(xa_is_node(root))) {
 			mas->depth = 1;
+			mas->status = ma_active;
 			mas->node = mte_safe_root(root);
 			mas->offset = 0;
 			if (mte_dead_node(mas->node))
@@ -1396,13 +1374,14 @@ retry:
 
 		/* empty tree */
 		if (unlikely(!root)) {
-			mas->node = MAS_NONE;
+			mas->node = NULL;
+			mas->status = ma_none;
 			mas->offset = MAPLE_NODE_SLOTS;
 			return NULL;
 		}
 
 		/* Single entry tree */
-		mas->node = MAS_ROOT;
+		mas->status = ma_root;
 		mas->offset = MAPLE_NODE_SLOTS;
 
 		/* Single entry tree. */
@@ -1425,10 +1404,8 @@ retry:
  * Uses metadata to find the end of the data when possible.
  * Return: The zero indexed last slot with data (may be null).
  */
-static inline unsigned char ma_data_end(struct maple_node *node,
-					enum maple_type type,
-					unsigned long *pivots,
-					unsigned long max)
+static __always_inline unsigned char ma_data_end(struct maple_node *node,
+		enum maple_type type, unsigned long *pivots, unsigned long max)
 {
 	unsigned char offset;
 
@@ -1541,6 +1518,9 @@ static unsigned long mas_leaf_max_gap(struct ma_state *mas)
 		gap = ULONG_MAX - pivots[max_piv];
 		if (gap > max_gap)
 			max_gap = gap;
+
+		if (max_gap > pivots[max_piv] - mas->min)
+			return max_gap;
 	}
 
 	for (; i <= max_piv; i++) {
@@ -1608,7 +1588,7 @@ static inline unsigned long mas_max_gap(struct ma_state *mas)
 
 	node = mas_mn(mas);
 	MAS_BUG_ON(mas, mt != maple_arange_64);
-	offset = ma_meta_gap(node, mt);
+	offset = ma_meta_gap(node);
 	gaps = ma_gaps(node, mt);
 	return gaps[offset];
 }
@@ -1639,7 +1619,7 @@ static inline void mas_parent_gap(struct ma_state *mas, unsigned char offset,
 
 ascend:
 	MAS_BUG_ON(mas, pmt != maple_arange_64);
-	meta_offset = ma_meta_gap(pnode, pmt);
+	meta_offset = ma_meta_gap(pnode);
 	meta_gap = pgaps[meta_offset];
 
 	pgaps[offset] = new;
@@ -1987,27 +1967,13 @@ complete:
 
 /*
  * mas_leaf_set_meta() - Set the metadata of a leaf if possible.
- * @mas: The maple state
  * @node: The maple node
- * @pivots: pointer to the maple node pivots
  * @mt: The maple type
- * @end: The assumed end
- *
- * Note, end may be incremented within this function but not modified at the
- * source.  This is fine since the metadata is the last thing to be stored in a
- * node during a write.
+ * @end: The node end
  */
-static inline void mas_leaf_set_meta(struct ma_state *mas,
-		struct maple_node *node, unsigned long *pivots,
+static inline void mas_leaf_set_meta(struct maple_node *node,
 		enum maple_type mt, unsigned char end)
 {
-	/* There is no room for metadata already */
-	if (mt_pivots[mt] <= end)
-		return;
-
-	if (pivots[end] && pivots[end] < mas->max)
-		end++;
-
 	if (end < mt_slots[mt] - 1)
 		ma_set_meta(node, mt, 0, end);
 }
@@ -2064,7 +2030,7 @@ static inline void mab_mas_cp(struct maple_big_node *b_node,
 
 		ma_set_meta(node, mt, offset, end);
 	} else {
-		mas_leaf_set_meta(mas, node, pivots, mt, end);
+		mas_leaf_set_meta(node, mt, end);
 	}
 }
 
@@ -2152,11 +2118,11 @@ static noinline_for_kasan void mas_store_b_node(struct ma_wr_state *wr_mas,
 	}
 
 	slot = offset_end + 1;
-	if (slot > wr_mas->node_end)
+	if (slot > mas->end)
 		goto b_end;
 
 	/* Copy end data to the end of the node. */
-	mas_mab_cp(mas, slot, wr_mas->node_end + 1, b_node, ++b_end);
+	mas_mab_cp(mas, slot, mas->end + 1, b_node, ++b_end);
 	b_node->b_end--;
 	return;
 
@@ -2211,19 +2177,21 @@ static inline bool mas_next_sibling(struct ma_state *mas)
 }
 
 /*
- * mte_node_or_node() - Return the encoded node or MAS_NONE.
+ * mte_node_or_none() - Set the enode and state.
  * @enode: The encoded maple node.
  *
- * Shorthand to avoid setting %NULLs in the tree or maple_subtree_state.
- *
- * Return: @enode or MAS_NONE
+ * Set the node to the enode and the status.
  */
-static inline struct maple_enode *mte_node_or_none(struct maple_enode *enode)
+static inline void mas_node_or_none(struct ma_state *mas,
+		struct maple_enode *enode)
 {
-	if (enode)
-		return enode;
-
-	return ma_enode_ptr(MAS_NONE);
+	if (enode) {
+		mas->node = enode;
+		mas->status = ma_active;
+	} else {
+		mas->node = NULL;
+		mas->status = ma_none;
+	}
 }
 
 /*
@@ -2245,8 +2213,8 @@ static inline void mas_wr_node_walk(struct ma_wr_state *wr_mas)
 
 	wr_mas->node = mas_mn(wr_mas->mas);
 	wr_mas->pivots = ma_pivots(wr_mas->node, wr_mas->type);
-	count = wr_mas->node_end = ma_data_end(wr_mas->node, wr_mas->type,
-					       wr_mas->pivots, mas->max);
+	count = mas->end = ma_data_end(wr_mas->node, wr_mas->type,
+				       wr_mas->pivots, mas->max);
 	offset = mas->offset;
 
 	while (offset < count && mas->index > wr_mas->pivots[offset])
@@ -2535,7 +2503,7 @@ static inline void mast_set_split_parents(struct maple_subtree_state *mast,
 }
 
 /*
- * mas_topiary_node() - Dispose of a singe node
+ * mas_topiary_node() - Dispose of a single node
  * @mas: The maple state for pushing nodes
  * @enode: The encoded maple node
  * @in_rcu: If the tree is in rcu mode
@@ -2543,13 +2511,15 @@ static inline void mast_set_split_parents(struct maple_subtree_state *mast,
  * The node will either be RCU freed or pushed back on the maple state.
  */
 static inline void mas_topiary_node(struct ma_state *mas,
-		struct maple_enode *enode, bool in_rcu)
+		struct ma_state *tmp_mas, bool in_rcu)
 {
 	struct maple_node *tmp;
+	struct maple_enode *enode;
 
-	if (enode == MAS_NONE)
+	if (mas_is_none(tmp_mas))
 		return;
 
+	enode = tmp_mas->node;
 	tmp = mte_to_node(enode);
 	mte_set_node_dead(enode);
 	if (in_rcu)
@@ -2589,8 +2559,8 @@ static inline void mas_topiary_replace(struct ma_state *mas,
 	/* Update the parent pointers in the tree */
 	tmp[0] = *mas;
 	tmp[0].offset = 0;
-	tmp[1].node = MAS_NONE;
-	tmp[2].node = MAS_NONE;
+	tmp[1].status = ma_none;
+	tmp[2].status = ma_none;
 	while (!mte_is_leaf(tmp[0].node)) {
 		n = 0;
 		for (i = 0; i < 3; i++) {
@@ -2610,7 +2580,7 @@ static inline void mas_topiary_replace(struct ma_state *mas,
 			break;
 
 		while (n < 3)
-			tmp_next[n++].node = MAS_NONE;
+			tmp_next[n++].status = ma_none;
 
 		for (i = 0; i < 3; i++)
 			tmp[i] = tmp_next[i];
@@ -2623,8 +2593,8 @@ static inline void mas_topiary_replace(struct ma_state *mas,
 	tmp[0] = *mas;
 	tmp[0].offset = 0;
 	tmp[0].node = old_enode;
-	tmp[1].node = MAS_NONE;
-	tmp[2].node = MAS_NONE;
+	tmp[1].status = ma_none;
+	tmp[2].status = ma_none;
 	in_rcu = mt_in_rcu(mas->tree);
 	do {
 		n = 0;
@@ -2639,7 +2609,7 @@ static inline void mas_topiary_replace(struct ma_state *mas,
 				if ((tmp_next[n].min >= tmp_next->index) &&
 				    (tmp_next[n].max <= tmp_next->last)) {
 					mat_add(&subtrees, tmp_next[n].node);
-					tmp_next[n].node = MAS_NONE;
+					tmp_next[n].status = ma_none;
 				} else {
 					n++;
 				}
@@ -2650,16 +2620,16 @@ static inline void mas_topiary_replace(struct ma_state *mas,
 			break;
 
 		while (n < 3)
-			tmp_next[n++].node = MAS_NONE;
+			tmp_next[n++].status = ma_none;
 
 		for (i = 0; i < 3; i++) {
-			mas_topiary_node(mas, tmp[i].node, in_rcu);
+			mas_topiary_node(mas, &tmp[i], in_rcu);
 			tmp[i] = tmp_next[i];
 		}
 	} while (!mte_is_leaf(tmp[0].node));
 
 	for (i = 0; i < 3; i++)
-		mas_topiary_node(mas, tmp[i].node, in_rcu);
+		mas_topiary_node(mas, &tmp[i], in_rcu);
 
 	mas_mat_destroy(mas, &subtrees);
 }
@@ -2698,9 +2668,9 @@ static inline void mast_cp_to_nodes(struct maple_subtree_state *mast,
 {
 	bool new_lmax = true;
 
-	mast->l->node = mte_node_or_none(left);
-	mast->m->node = mte_node_or_none(middle);
-	mast->r->node = mte_node_or_none(right);
+	mas_node_or_none(mast->l, left);
+	mas_node_or_none(mast->m, middle);
+	mas_node_or_none(mast->r, right);
 
 	mast->l->min = mast->orig_l->min;
 	if (split == mast->bn->b_end) {
@@ -2796,32 +2766,29 @@ static inline void *mtree_range_walk(struct ma_state *mas)
 	min = mas->min;
 	max = mas->max;
 	do {
-		offset = 0;
 		last = next;
 		node = mte_to_node(next);
 		type = mte_node_type(next);
 		pivots = ma_pivots(node, type);
 		end = ma_data_end(node, type, pivots, max);
-		if (unlikely(ma_dead_node(node)))
-			goto dead_node;
-
-		if (pivots[offset] >= mas->index) {
-			prev_max = max;
-			prev_min = min;
-			max = pivots[offset];
+		prev_min = min;
+		prev_max = max;
+		if (pivots[0] >= mas->index) {
+			offset = 0;
+			max = pivots[0];
 			goto next;
 		}
 
-		do {
+		offset = 1;
+		while (offset < end) {
+			if (pivots[offset] >= mas->index) {
+				max = pivots[offset];
+				break;
+			}
 			offset++;
-		} while ((offset < end) && (pivots[offset] < mas->index));
+		}
 
-		prev_min = min;
 		min = pivots[offset - 1] + 1;
-		prev_max = max;
-		if (likely(offset < end && pivots[offset]))
-			max = pivots[offset];
-
 next:
 		slots = ma_slots(node, type);
 		next = mt_slot(mas->tree, slots, offset);
@@ -2829,6 +2796,7 @@ next:
 			goto dead_node;
 	} while (!ma_is_leaf(type));
 
+	mas->end = end;
 	mas->offset = offset;
 	mas->index = min;
 	mas->last = max;
@@ -2879,7 +2847,7 @@ static int mas_spanning_rebalance(struct ma_state *mas,
 	mast->l = &l_mas;
 	mast->m = &m_mas;
 	mast->r = &r_mas;
-	l_mas.node = r_mas.node = m_mas.node = MAS_NONE;
+	l_mas.status = r_mas.status = m_mas.status = ma_none;
 
 	/* Check if this is not root and has sufficient data.  */
 	if (((mast->orig_l->min != 0) || (mast->orig_r->max != ULONG_MAX)) &&
@@ -3167,7 +3135,7 @@ done:
  * @mas: The maple state
  * @height: The height of the tree in case it's a new root.
  */
-static inline bool mas_split_final_node(struct maple_subtree_state *mast,
+static inline void mas_split_final_node(struct maple_subtree_state *mast,
 					struct ma_state *mas, int height)
 {
 	struct maple_enode *ancestor;
@@ -3191,7 +3159,6 @@ static inline bool mas_split_final_node(struct maple_subtree_state *mast,
 	mast->l->node = ancestor;
 	mab_mas_cp(mast->bn, 0, mt_slots[mast->bn->type] - 1, mast->l, true);
 	mas->offset = mast->bn->b_end - 1;
-	return true;
 }
 
 /*
@@ -3406,7 +3373,6 @@ static int mas_split(struct ma_state *mas, struct maple_big_node *b_node)
 		/* Try to push left. */
 		if (mas_push_data(mas, height, &mast, true))
 			break;
-
 		/* Try to push right. */
 		if (mas_push_data(mas, height, &mast, false))
 			break;
@@ -3495,6 +3461,7 @@ static noinline_for_kasan int mas_commit_b_node(struct ma_wr_state *wr_mas,
 	mas_replace_node(wr_mas->mas, old_enode);
 reuse_node:
 	mas_update_gap(wr_mas->mas);
+	wr_mas->mas->end = b_end;
 	return 1;
 }
 
@@ -3521,6 +3488,7 @@ static inline int mas_root_expand(struct ma_state *mas, void *entry)
 	slots = ma_slots(node, type);
 	node->parent = ma_parent_ptr(mas_tree_parent(mas));
 	mas->node = mt_mk_node(node, type);
+	mas->status = ma_active;
 
 	if (mas->index) {
 		if (contents) {
@@ -3553,7 +3521,7 @@ static inline void mas_store_root(struct ma_state *mas, void *entry)
 		mas_root_expand(mas, entry);
 	else {
 		rcu_assign_pointer(mas->tree->ma_root, entry);
-		mas->node = MAS_START;
+		mas->status = ma_start;
 	}
 }
 
@@ -3730,23 +3698,17 @@ static inline void *mtree_lookup_walk(struct ma_state *mas)
 	enum maple_type type;
 	void __rcu **slots;
 	unsigned char end;
-	unsigned long max;
 
 	next = mas->node;
-	max = ULONG_MAX;
 	do {
-		offset = 0;
 		node = mte_to_node(next);
 		type = mte_node_type(next);
 		pivots = ma_pivots(node, type);
-		end = ma_data_end(node, type, pivots, max);
-		if (unlikely(ma_dead_node(node)))
-			goto dead_node;
+		end = mt_pivots[type];
+		offset = 0;
 		do {
-			if (pivots[offset] >= mas->index) {
-				max = pivots[offset];
+			if (pivots[offset] >= mas->index)
 				break;
-			}
 		} while (++offset < end);
 
 		slots = ma_slots(node, type);
@@ -3785,7 +3747,7 @@ static inline int mas_new_root(struct ma_state *mas, void *entry)
 		mas->depth = 0;
 		mas_set_height(mas);
 		rcu_assign_pointer(mas->tree->ma_root, entry);
-		mas->node = MAS_START;
+		mas->status = ma_start;
 		goto done;
 	}
 
@@ -3798,6 +3760,7 @@ static inline int mas_new_root(struct ma_state *mas, void *entry)
 	slots = ma_slots(node, type);
 	node->parent = ma_parent_ptr(mas_tree_parent(mas));
 	mas->node = mt_mk_node(node, type);
+	mas->status = ma_active;
 	rcu_assign_pointer(slots[0], entry);
 	pivots[0] = mas->last;
 	mas->depth = 1;
@@ -3891,10 +3854,10 @@ static inline int mas_wr_spanning_store(struct ma_wr_state *wr_mas)
 
 	memset(&b_node, 0, sizeof(struct maple_big_node));
 	/* Copy l_mas and store the value in b_node. */
-	mas_store_b_node(&l_wr_mas, &b_node, l_wr_mas.node_end);
+	mas_store_b_node(&l_wr_mas, &b_node, l_mas.end);
 	/* Copy r_mas into b_node. */
-	if (r_mas.offset <= r_wr_mas.node_end)
-		mas_mab_cp(&r_mas, r_mas.offset, r_wr_mas.node_end,
+	if (r_mas.offset <= r_mas.end)
+		mas_mab_cp(&r_mas, r_mas.offset, r_mas.end,
 			   &b_node, b_node.b_end + 1);
 	else
 		b_node.b_end++;
@@ -3936,7 +3899,7 @@ static inline bool mas_wr_node_store(struct ma_wr_state *wr_mas,
 	if (mas->last == wr_mas->end_piv)
 		offset_end++; /* don't copy this offset */
 	else if (unlikely(wr_mas->r_max == ULONG_MAX))
-		mas_bulk_rebalance(mas, wr_mas->node_end, wr_mas->type);
+		mas_bulk_rebalance(mas, mas->end, wr_mas->type);
 
 	/* set up node. */
 	if (in_rcu) {
@@ -3972,12 +3935,12 @@ static inline bool mas_wr_node_store(struct ma_wr_state *wr_mas,
 	 * this range wrote to the end of the node or it overwrote the rest of
 	 * the data
 	 */
-	if (offset_end > wr_mas->node_end)
+	if (offset_end > mas->end)
 		goto done;
 
 	dst_offset = mas->offset + 1;
 	/* Copy to the end of node if necessary. */
-	copy_size = wr_mas->node_end - offset_end + 1;
+	copy_size = mas->end - offset_end + 1;
 	memcpy(dst_slots + dst_offset, wr_mas->slots + offset_end,
 	       sizeof(void *) * copy_size);
 	memcpy(dst_pivots + dst_offset, wr_mas->pivots + offset_end,
@@ -3987,7 +3950,7 @@ static inline bool mas_wr_node_store(struct ma_wr_state *wr_mas,
 		dst_pivots[new_end] = mas->max;
 
 done:
-	mas_leaf_set_meta(mas, newnode, dst_pivots, maple_leaf_64, new_end);
+	mas_leaf_set_meta(newnode, maple_leaf_64, new_end);
 	if (in_rcu) {
 		struct maple_enode *old_enode = mas->node;
 
@@ -3998,6 +3961,7 @@ done:
 	}
 	trace_ma_write(__func__, mas, 0, wr_mas->entry);
 	mas_update_gap(mas);
+	mas->end = new_end;
 	return true;
 }
 
@@ -4063,10 +4027,10 @@ static inline void mas_wr_extend_null(struct ma_wr_state *wr_mas)
 	} else {
 		/* Check next slot(s) if we are overwriting the end */
 		if ((mas->last == wr_mas->end_piv) &&
-		    (wr_mas->node_end != wr_mas->offset_end) &&
+		    (mas->end != wr_mas->offset_end) &&
 		    !wr_mas->slots[wr_mas->offset_end + 1]) {
 			wr_mas->offset_end++;
-			if (wr_mas->offset_end == wr_mas->node_end)
+			if (wr_mas->offset_end == mas->end)
 				mas->last = mas->max;
 			else
 				mas->last = wr_mas->pivots[wr_mas->offset_end];
@@ -4091,11 +4055,11 @@ static inline void mas_wr_extend_null(struct ma_wr_state *wr_mas)
 
 static inline void mas_wr_end_piv(struct ma_wr_state *wr_mas)
 {
-	while ((wr_mas->offset_end < wr_mas->node_end) &&
+	while ((wr_mas->offset_end < wr_mas->mas->end) &&
 	       (wr_mas->mas->last > wr_mas->pivots[wr_mas->offset_end]))
 		wr_mas->offset_end++;
 
-	if (wr_mas->offset_end < wr_mas->node_end)
+	if (wr_mas->offset_end < wr_mas->mas->end)
 		wr_mas->end_piv = wr_mas->pivots[wr_mas->offset_end];
 	else
 		wr_mas->end_piv = wr_mas->mas->max;
@@ -4107,7 +4071,7 @@ static inline void mas_wr_end_piv(struct ma_wr_state *wr_mas)
 static inline unsigned char mas_wr_new_end(struct ma_wr_state *wr_mas)
 {
 	struct ma_state *mas = wr_mas->mas;
-	unsigned char new_end = wr_mas->node_end + 2;
+	unsigned char new_end = mas->end + 2;
 
 	new_end -= wr_mas->offset_end - mas->offset;
 	if (wr_mas->r_min == mas->index)
@@ -4141,10 +4105,7 @@ static inline bool mas_wr_append(struct ma_wr_state *wr_mas,
 	if (mt_in_rcu(mas->tree))
 		return false;
 
-	if (mas->offset != wr_mas->node_end)
-		return false;
-
-	end = wr_mas->node_end;
+	end = mas->end;
 	if (mas->offset != end)
 		return false;
 
@@ -4178,6 +4139,7 @@ static inline bool mas_wr_append(struct ma_wr_state *wr_mas,
 	if (!wr_mas->content || !wr_mas->entry)
 		mas_update_gap(mas);
 
+	mas->end = new_end;
 	trace_ma_write(__func__, mas, new_end, wr_mas->entry);
 	return  true;
 }
@@ -4195,7 +4157,7 @@ static void mas_wr_bnode(struct ma_wr_state *wr_mas)
 	trace_ma_write(__func__, wr_mas->mas, 0, wr_mas->entry);
 	memset(&b_node, 0, sizeof(struct maple_big_node));
 	mas_store_b_node(wr_mas, &b_node, wr_mas->offset_end);
-	mas_commit_b_node(wr_mas, &b_node, wr_mas->node_end);
+	mas_commit_b_node(wr_mas, &b_node, wr_mas->mas->end);
 }
 
 static inline void mas_wr_modify(struct ma_wr_state *wr_mas)
@@ -4223,7 +4185,7 @@ static inline void mas_wr_modify(struct ma_wr_state *wr_mas)
 	if (mas_wr_append(wr_mas, new_end))
 		return;
 
-	if (new_end == wr_mas->node_end && mas_wr_slot_store(wr_mas))
+	if (new_end == mas->end && mas_wr_slot_store(wr_mas))
 		return;
 
 	if (mas_wr_node_store(wr_mas, new_end))
@@ -4328,7 +4290,7 @@ exists:
 
 }
 
-static inline void mas_rewalk(struct ma_state *mas, unsigned long index)
+static __always_inline void mas_rewalk(struct ma_state *mas, unsigned long index)
 {
 retry:
 	mas_set(mas, index);
@@ -4337,7 +4299,7 @@ retry:
 		goto retry;
 }
 
-static inline bool mas_rewalk_if_dead(struct ma_state *mas,
+static __always_inline bool mas_rewalk_if_dead(struct ma_state *mas,
 		struct maple_node *node, const unsigned long index)
 {
 	if (unlikely(ma_dead_node(node))) {
@@ -4349,14 +4311,16 @@ static inline bool mas_rewalk_if_dead(struct ma_state *mas,
 
 /*
  * mas_prev_node() - Find the prev non-null entry at the same level in the
- * tree.  The prev value will be mas->node[mas->offset] or MAS_NONE.
+ * tree.  The prev value will be mas->node[mas->offset] or the status will be
+ * ma_none.
  * @mas: The maple state
  * @min: The lower limit to search
  *
- * The prev node value will be mas->node[mas->offset] or MAS_NONE.
+ * The prev node value will be mas->node[mas->offset] or the status will be
+ * ma_none.
  * Return: 1 if the node is dead, 0 otherwise.
  */
-static inline int mas_prev_node(struct ma_state *mas, unsigned long min)
+static int mas_prev_node(struct ma_state *mas, unsigned long min)
 {
 	enum maple_type mt;
 	int offset, level;
@@ -4416,13 +4380,14 @@ static inline int mas_prev_node(struct ma_state *mas, unsigned long min)
 	if (unlikely(mte_dead_node(mas->node)))
 		return 1;
 
+	mas->end = mas->offset;
 	return 0;
 
 no_entry:
 	if (unlikely(ma_dead_node(node)))
 		return 1;
 
-	mas->node = MAS_NONE;
+	mas->status = ma_underflow;
 	return 0;
 }
 
@@ -4436,8 +4401,7 @@ no_entry:
  *
  * Return: The entry in the previous slot which is possibly NULL
  */
-static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty,
-			   bool set_underflow)
+static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty)
 {
 	void *entry;
 	void __rcu **slots;
@@ -4470,13 +4434,16 @@ again:
 		mas->last = mas->index - 1;
 		mas->index = mas_safe_min(mas, pivots, mas->offset);
 	} else  {
+		if (mas->index <= min)
+			goto underflow;
+
 		if (mas_prev_node(mas, min)) {
 			mas_rewalk(mas, save_point);
 			goto retry;
 		}
 
-		if (mas_is_none(mas))
-			goto underflow;
+		if (WARN_ON_ONCE(mas_is_underflow(mas)))
+			return NULL;
 
 		mas->last = mas->max;
 		node = mas_mn(mas);
@@ -4490,12 +4457,15 @@ again:
 	if (unlikely(mas_rewalk_if_dead(mas, node, save_point)))
 		goto retry;
 
+
 	if (likely(entry))
 		return entry;
 
 	if (!empty) {
-		if (mas->index <= min)
-			goto underflow;
+		if (mas->index <= min) {
+			mas->status = ma_underflow;
+			return NULL;
+		}
 
 		goto again;
 	}
@@ -4503,8 +4473,7 @@ again:
 	return entry;
 
 underflow:
-	if (set_underflow)
-		mas->node = MAS_UNDERFLOW;
+	mas->status = ma_underflow;
 	return NULL;
 }
 
@@ -4513,28 +4482,30 @@ underflow:
  * @mas: The maple state
  * @max: The maximum pivot value to check.
  *
- * The next value will be mas->node[mas->offset] or MAS_NONE.
+ * The next value will be mas->node[mas->offset] or the status will have
+ * overflowed.
  * Return: 1 on dead node, 0 otherwise.
  */
-static inline int mas_next_node(struct ma_state *mas, struct maple_node *node,
-				unsigned long max)
+static int mas_next_node(struct ma_state *mas, struct maple_node *node,
+		unsigned long max)
 {
 	unsigned long min;
 	unsigned long *pivots;
 	struct maple_enode *enode;
+	struct maple_node *tmp;
 	int level = 0;
 	unsigned char node_end;
 	enum maple_type mt;
 	void __rcu **slots;
 
 	if (mas->max >= max)
-		goto no_entry;
+		goto overflow;
 
 	min = mas->max + 1;
 	level = 0;
 	do {
 		if (ma_is_root(node))
-			goto no_entry;
+			goto overflow;
 
 		/* Walk up. */
 		if (unlikely(mas_ascend(mas)))
@@ -4574,6 +4545,10 @@ static inline int mas_next_node(struct ma_state *mas, struct maple_node *node,
 		pivots = ma_pivots(node, mt);
 
 	mas->max = mas_safe_pivot(mas, pivots, mas->offset, mt);
+	tmp = mte_to_node(enode);
+	mt = mte_node_type(enode);
+	pivots = ma_pivots(tmp, mt);
+	mas->end = ma_data_end(tmp, mt, pivots, mas->max);
 	if (unlikely(ma_dead_node(node)))
 		return 1;
 
@@ -4581,11 +4556,11 @@ static inline int mas_next_node(struct ma_state *mas, struct maple_node *node,
 	mas->min = min;
 	return 0;
 
-no_entry:
+overflow:
 	if (unlikely(ma_dead_node(node)))
 		return 1;
 
-	mas->node = MAS_NONE;
+	mas->status = ma_overflow;
 	return 0;
 }
 
@@ -4600,15 +4575,13 @@ no_entry:
  *
  * Return: The entry in the next slot which is possibly NULL
  */
-static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty,
-			   bool set_overflow)
+static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty)
 {
 	void __rcu **slots;
 	unsigned long *pivots;
 	unsigned long pivot;
 	enum maple_type type;
 	struct maple_node *node;
-	unsigned char data_end;
 	unsigned long save_point = mas->last;
 	void *entry;
 
@@ -4616,42 +4589,45 @@ retry:
 	node = mas_mn(mas);
 	type = mte_node_type(mas->node);
 	pivots = ma_pivots(node, type);
-	data_end = ma_data_end(node, type, pivots, mas->max);
 	if (unlikely(mas_rewalk_if_dead(mas, node, save_point)))
 		goto retry;
 
 	if (mas->max >= max) {
-		if (likely(mas->offset < data_end))
+		if (likely(mas->offset < mas->end))
 			pivot = pivots[mas->offset];
 		else
-			goto overflow;
+			pivot = mas->max;
 
 		if (unlikely(mas_rewalk_if_dead(mas, node, save_point)))
 			goto retry;
 
-		if (pivot >= max)
-			goto overflow;
+		if (pivot >= max) { /* Was at the limit, next will extend beyond */
+			mas->status = ma_overflow;
+			return NULL;
+		}
 	}
 
-	if (likely(mas->offset < data_end)) {
+	if (likely(mas->offset < mas->end)) {
 		mas->index = pivots[mas->offset] + 1;
 again:
 		mas->offset++;
-		if (likely(mas->offset < data_end))
+		if (likely(mas->offset < mas->end))
 			mas->last = pivots[mas->offset];
 		else
 			mas->last = mas->max;
 	} else  {
+		if (mas->last >= max) {
+			mas->status = ma_overflow;
+			return NULL;
+		}
+
 		if (mas_next_node(mas, node, max)) {
 			mas_rewalk(mas, save_point);
 			goto retry;
 		}
 
-		if (WARN_ON_ONCE(mas_is_none(mas))) {
-			mas->node = MAS_OVERFLOW;
+		if (WARN_ON_ONCE(mas_is_overflow(mas)))
 			return NULL;
-			goto overflow;
-		}
 
 		mas->offset = 0;
 		mas->index = mas->min;
@@ -4669,21 +4645,18 @@ again:
 	if (entry)
 		return entry;
 
+
 	if (!empty) {
-		if (mas->last >= max)
-			goto overflow;
+		if (mas->last >= max) {
+			mas->status = ma_overflow;
+			return NULL;
+		}
 
 		mas->index = mas->last + 1;
-		/* Node cannot end on NULL, so it's safe to short-cut here */
 		goto again;
 	}
 
 	return entry;
-
-overflow:
-	if (set_overflow)
-		mas->node = MAS_OVERFLOW;
-	return NULL;
 }
 
 /*
@@ -4702,11 +4675,11 @@ overflow:
 static inline void *mas_next_entry(struct ma_state *mas, unsigned long limit)
 {
 	if (mas->last >= limit) {
-		mas->node = MAS_OVERFLOW;
+		mas->status = ma_overflow;
 		return NULL;
 	}
 
-	return mas_next_slot(mas, limit, false, true);
+	return mas_next_slot(mas, limit, false);
 }
 
 /*
@@ -4874,7 +4847,7 @@ done:
  * @mas: The maple state.
  *
  * mas->index and mas->last will be set to the range if there is a value.  If
- * mas->node is MAS_NONE, reset to MAS_START.
+ * mas->status is ma_none, reset to ma_start
  *
  * Return: the entry at the location or %NULL.
  */
@@ -4883,7 +4856,7 @@ void *mas_walk(struct ma_state *mas)
 	void *entry;
 
 	if (!mas_is_active(mas) || !mas_is_start(mas))
-		mas->node = MAS_START;
+		mas->status = ma_start;
 retry:
 	entry = mas_state_walk(mas);
 	if (mas_is_start(mas)) {
@@ -4899,7 +4872,7 @@ retry:
 
 		mas->index = 1;
 		mas->last = ULONG_MAX;
-		mas->node = MAS_NONE;
+		mas->status = ma_none;
 		return NULL;
 	}
 
@@ -5026,6 +4999,7 @@ int mas_empty_area(struct ma_state *mas, unsigned long min,
 	unsigned char offset;
 	unsigned long *pivots;
 	enum maple_type mt;
+	struct maple_node *node;
 
 	if (min > max)
 		return -EINVAL;
@@ -5056,12 +5030,14 @@ int mas_empty_area(struct ma_state *mas, unsigned long min,
 	if (unlikely(offset == MAPLE_NODE_SLOTS))
 		return -EBUSY;
 
+	node = mas_mn(mas);
 	mt = mte_node_type(mas->node);
-	pivots = ma_pivots(mas_mn(mas), mt);
+	pivots = ma_pivots(node, mt);
 	min = mas_safe_min(mas, pivots, offset);
 	if (mas->index < min)
 		mas->index = min;
 	mas->last = mas->index + size - 1;
+	mas->end = ma_data_end(node, mt, pivots, mas->max);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mas_empty_area);
@@ -5122,6 +5098,7 @@ int mas_empty_area_rev(struct ma_state *mas, unsigned long min,
 		mas->last = max;
 
 	mas->index = mas->last - size + 1;
+	mas->end = mas_data_end(mas);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mas_empty_area_rev);
@@ -5501,13 +5478,24 @@ int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp)
 
 	mas_wr_end_piv(&wr_mas);
 	node_size = mas_wr_new_end(&wr_mas);
+
+	/* Slot store, does not require additional nodes */
+	if (node_size == mas->end) {
+		/* reuse node */
+		if (!mt_in_rcu(mas->tree))
+			return 0;
+		/* shifting boundary */
+		if (wr_mas.offset_end - mas->offset == 1)
+			return 0;
+	}
+
 	if (node_size >= mt_slots[wr_mas.type]) {
 		/* Split, worst case for now. */
 		request = 1 + mas_mt_height(mas) * 2;
 		goto ask_now;
 	}
 
-	/* New root needs a singe node */
+	/* New root needs a single node */
 	if (unlikely(mte_is_root(mas->node)))
 		goto ask_now;
 
@@ -5555,7 +5543,7 @@ void mas_destroy(struct ma_state *mas)
 
 		mas_start(mas);
 		mtree_range_walk(mas);
-		end = mas_data_end(mas) + 1;
+		end = mas->end + 1;
 		if (end < mt_min_slot_count(mas->node) - 1)
 			mas_destroy_rebalance(mas, end);
 
@@ -5573,7 +5561,7 @@ void mas_destroy(struct ma_state *mas)
 			mt_free_bulk(count, (void __rcu **)&node->slot[1]);
 			total -= count;
 		}
-		kmem_cache_free(maple_node_cache, node);
+		mt_free_one(ma_mnode_ptr(node));
 		total--;
 	}
 
@@ -5643,33 +5631,46 @@ int mas_expected_entries(struct ma_state *mas, unsigned long nr_entries)
 }
 EXPORT_SYMBOL_GPL(mas_expected_entries);
 
-static inline bool mas_next_setup(struct ma_state *mas, unsigned long max,
+static bool mas_next_setup(struct ma_state *mas, unsigned long max,
 		void **entry)
 {
 	bool was_none = mas_is_none(mas);
 
 	if (unlikely(mas->last >= max)) {
-		mas->node = MAS_OVERFLOW;
+		mas->status = ma_overflow;
 		return true;
 	}
 
-	if (mas_is_active(mas))
+	switch (mas->status) {
+	case ma_active:
 		return false;
-
-	if (mas_is_none(mas) || mas_is_paused(mas)) {
-		mas->node = MAS_START;
-	} else if (mas_is_overflow(mas)) {
+	case ma_none:
+		fallthrough;
+	case ma_pause:
+		mas->status = ma_start;
+		fallthrough;
+	case ma_start:
+		mas_walk(mas); /* Retries on dead nodes handled by mas_walk */
+		break;
+	case ma_overflow:
 		/* Overflowed before, but the max changed */
-		mas->node = MAS_START;
-	} else if (mas_is_underflow(mas)) {
-		mas->node = MAS_START;
+		mas->status = ma_active;
+		break;
+	case ma_underflow:
+		/* The user expects the mas to be one before where it is */
+		mas->status = ma_active;
 		*entry = mas_walk(mas);
 		if (*entry)
 			return true;
+		break;
+	case ma_root:
+		break;
+	case ma_error:
+		return true;
 	}
 
-	if (mas_is_start(mas))
-		*entry = mas_walk(mas); /* Retries on dead nodes handled by mas_walk */
+	if (likely(mas_is_active(mas))) /* Fast path */
+		return false;
 
 	if (mas_is_ptr(mas)) {
 		*entry = NULL;
@@ -5679,7 +5680,7 @@ static inline bool mas_next_setup(struct ma_state *mas, unsigned long max,
 		}
 		mas->index = 1;
 		mas->last = ULONG_MAX;
-		mas->node = MAS_NONE;
+		mas->status = ma_none;
 		return true;
 	}
 
@@ -5708,7 +5709,7 @@ void *mas_next(struct ma_state *mas, unsigned long max)
 		return entry;
 
 	/* Retries on dead nodes handled by mas_next_slot */
-	return mas_next_slot(mas, max, false, true);
+	return mas_next_slot(mas, max, false);
 }
 EXPORT_SYMBOL_GPL(mas_next);
 
@@ -5731,7 +5732,7 @@ void *mas_next_range(struct ma_state *mas, unsigned long max)
 		return entry;
 
 	/* Retries on dead nodes handled by mas_next_slot */
-	return mas_next_slot(mas, max, true, true);
+	return mas_next_slot(mas, max, true);
 }
 EXPORT_SYMBOL_GPL(mas_next_range);
 
@@ -5759,37 +5760,48 @@ void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max)
 }
 EXPORT_SYMBOL_GPL(mt_next);
 
-static inline bool mas_prev_setup(struct ma_state *mas, unsigned long min,
-		void **entry)
+static bool mas_prev_setup(struct ma_state *mas, unsigned long min, void **entry)
 {
 	if (unlikely(mas->index <= min)) {
-		mas->node = MAS_UNDERFLOW;
+		mas->status = ma_underflow;
 		return true;
 	}
 
-	if (mas_is_active(mas))
+	switch (mas->status) {
+	case ma_active:
 		return false;
-
-	if (mas_is_overflow(mas)) {
-		mas->node = MAS_START;
+	case ma_start:
+		break;
+	case ma_none:
+		fallthrough;
+	case ma_pause:
+		mas->status = ma_start;
+		break;
+	case ma_underflow:
+		/* underflowed before but the min changed */
+		mas->status = ma_active;
+		break;
+	case ma_overflow:
+		/* User expects mas to be one after where it is */
+		mas->status = ma_active;
 		*entry = mas_walk(mas);
 		if (*entry)
 			return true;
-	}
-
-	if (mas_is_none(mas) || mas_is_paused(mas)) {
-		mas->node = MAS_START;
-	} else if (mas_is_underflow(mas)) {
-		/* underflowed before but the min changed */
-		mas->node = MAS_START;
+		break;
+	case ma_root:
+		break;
+	case ma_error:
+		return true;
 	}
 
 	if (mas_is_start(mas))
 		mas_walk(mas);
 
 	if (unlikely(mas_is_ptr(mas))) {
-		if (!mas->index)
-			goto none;
+		if (!mas->index) {
+			mas->status = ma_none;
+			return true;
+		}
 		mas->index = mas->last = 0;
 		*entry = mas_root(mas);
 		return true;
@@ -5799,7 +5811,7 @@ static inline bool mas_prev_setup(struct ma_state *mas, unsigned long min,
 		if (mas->index) {
 			/* Walked to out-of-range pointer? */
 			mas->index = mas->last = 0;
-			mas->node = MAS_ROOT;
+			mas->status = ma_root;
 			*entry = mas_root(mas);
 			return true;
 		}
@@ -5807,10 +5819,6 @@ static inline bool mas_prev_setup(struct ma_state *mas, unsigned long min,
 	}
 
 	return false;
-
-none:
-	mas->node = MAS_NONE;
-	return true;
 }
 
 /**
@@ -5819,7 +5827,7 @@ none:
  * @min: The minimum value to check.
  *
  * Must hold rcu_read_lock or the write lock.
- * Will reset mas to MAS_START if the node is MAS_NONE.  Will stop on not
+ * Will reset mas to ma_start if the status is ma_none.  Will stop on not
  * searchable nodes.
  *
  * Return: the previous value or %NULL.
@@ -5831,7 +5839,7 @@ void *mas_prev(struct ma_state *mas, unsigned long min)
 	if (mas_prev_setup(mas, min, &entry))
 		return entry;
 
-	return mas_prev_slot(mas, min, false, true);
+	return mas_prev_slot(mas, min, false);
 }
 EXPORT_SYMBOL_GPL(mas_prev);
 
@@ -5842,7 +5850,7 @@ EXPORT_SYMBOL_GPL(mas_prev);
  *
  * Sets @mas->index and @mas->last to the range.
  * Must hold rcu_read_lock or the write lock.
- * Will reset mas to MAS_START if the node is MAS_NONE.  Will stop on not
+ * Will reset mas to ma_start if the node is ma_none.  Will stop on not
  * searchable nodes.
  *
  * Return: the previous value or %NULL.
@@ -5854,7 +5862,7 @@ void *mas_prev_range(struct ma_state *mas, unsigned long min)
 	if (mas_prev_setup(mas, min, &entry))
 		return entry;
 
-	return mas_prev_slot(mas, min, true, true);
+	return mas_prev_slot(mas, min, true);
 }
 EXPORT_SYMBOL_GPL(mas_prev_range);
 
@@ -5897,7 +5905,8 @@ EXPORT_SYMBOL_GPL(mt_prev);
  */
 void mas_pause(struct ma_state *mas)
 {
-	mas->node = MAS_PAUSE;
+	mas->status = ma_pause;
+	mas->node = NULL;
 }
 EXPORT_SYMBOL_GPL(mas_pause);
 
@@ -5909,35 +5918,54 @@ EXPORT_SYMBOL_GPL(mas_pause);
  *
  * Returns: True if entry is the answer, false otherwise.
  */
-static inline bool mas_find_setup(struct ma_state *mas, unsigned long max,
-		void **entry)
+static __always_inline bool mas_find_setup(struct ma_state *mas, unsigned long max, void **entry)
 {
-	if (mas_is_active(mas)) {
+	switch (mas->status) {
+	case ma_active:
 		if (mas->last < max)
 			return false;
-
 		return true;
-	}
-
-	if (mas_is_paused(mas)) {
+	case ma_start:
+		break;
+	case ma_pause:
 		if (unlikely(mas->last >= max))
 			return true;
 
 		mas->index = ++mas->last;
-		mas->node = MAS_START;
-	} else if (mas_is_none(mas)) {
+		mas->status = ma_start;
+		break;
+	case ma_none:
 		if (unlikely(mas->last >= max))
 			return true;
 
 		mas->index = mas->last;
-		mas->node = MAS_START;
-	} else if (mas_is_overflow(mas) || mas_is_underflow(mas)) {
-		if (mas->index > max) {
-			mas->node = MAS_OVERFLOW;
+		mas->status = ma_start;
+		break;
+	case ma_underflow:
+		/* mas is pointing at entry before unable to go lower */
+		if (unlikely(mas->index >= max)) {
+			mas->status = ma_overflow;
 			return true;
 		}
 
-		mas->node = MAS_START;
+		mas->status = ma_active;
+		*entry = mas_walk(mas);
+		if (*entry)
+			return true;
+		break;
+	case ma_overflow:
+		if (unlikely(mas->last >= max))
+			return true;
+
+		mas->status = ma_active;
+		*entry = mas_walk(mas);
+		if (*entry)
+			return true;
+		break;
+	case ma_root:
+		break;
+	case ma_error:
+		return true;
 	}
 
 	if (mas_is_start(mas)) {
@@ -5951,12 +5979,11 @@ static inline bool mas_find_setup(struct ma_state *mas, unsigned long max,
 
 	}
 
-	if (unlikely(!mas_searchable(mas))) {
-		if (unlikely(mas_is_ptr(mas)))
-			goto ptr_out_of_range;
+	if (unlikely(mas_is_ptr(mas)))
+		goto ptr_out_of_range;
 
+	if (unlikely(mas_is_none(mas)))
 		return true;
-	}
 
 	if (mas->index == max)
 		return true;
@@ -5964,7 +5991,7 @@ static inline bool mas_find_setup(struct ma_state *mas, unsigned long max,
 	return false;
 
 ptr_out_of_range:
-	mas->node = MAS_NONE;
+	mas->status = ma_none;
 	mas->index = 1;
 	mas->last = ULONG_MAX;
 	return true;
@@ -5978,7 +6005,7 @@ ptr_out_of_range:
  *
  * Must hold rcu_read_lock or the write lock.
  * If an entry exists, last and index are updated accordingly.
- * May set @mas->node to MAS_NONE.
+ * May set @mas->status to ma_overflow.
  *
  * Return: The entry or %NULL.
  */
@@ -5990,7 +6017,10 @@ void *mas_find(struct ma_state *mas, unsigned long max)
 		return entry;
 
 	/* Retries on dead nodes handled by mas_next_slot */
-	return mas_next_slot(mas, max, false, false);
+	entry = mas_next_slot(mas, max, false);
+	/* Ignore overflow */
+	mas->status = ma_active;
+	return entry;
 }
 EXPORT_SYMBOL_GPL(mas_find);
 
@@ -6002,7 +6032,7 @@ EXPORT_SYMBOL_GPL(mas_find);
  *
  * Must hold rcu_read_lock or the write lock.
  * If an entry exists, last and index are updated accordingly.
- * May set @mas->node to MAS_NONE.
+ * May set @mas->status to ma_overflow.
  *
  * Return: The entry or %NULL.
  */
@@ -6014,7 +6044,7 @@ void *mas_find_range(struct ma_state *mas, unsigned long max)
 		return entry;
 
 	/* Retries on dead nodes handled by mas_next_slot */
-	return mas_next_slot(mas, max, true, false);
+	return mas_next_slot(mas, max, true);
 }
 EXPORT_SYMBOL_GPL(mas_find_range);
 
@@ -6026,36 +6056,48 @@ EXPORT_SYMBOL_GPL(mas_find_range);
  *
  * Returns: True if entry is the answer, false otherwise.
  */
-static inline bool mas_find_rev_setup(struct ma_state *mas, unsigned long min,
+static bool mas_find_rev_setup(struct ma_state *mas, unsigned long min,
 		void **entry)
 {
-	if (mas_is_active(mas)) {
-		if (mas->index > min)
-			return false;
 
-		return true;
-	}
-
-	if (mas_is_paused(mas)) {
+	switch (mas->status) {
+	case ma_active:
+		goto active;
+	case ma_start:
+		break;
+	case ma_pause:
 		if (unlikely(mas->index <= min)) {
-			mas->node = MAS_NONE;
+			mas->status = ma_underflow;
 			return true;
 		}
-		mas->node = MAS_START;
 		mas->last = --mas->index;
-	} else if (mas_is_none(mas)) {
+		mas->status = ma_start;
+		break;
+	case ma_none:
 		if (mas->index <= min)
 			goto none;
 
 		mas->last = mas->index;
-		mas->node = MAS_START;
-	} else if (mas_is_underflow(mas) || mas_is_overflow(mas)) {
-		if (mas->last <= min) {
-			mas->node = MAS_UNDERFLOW;
+		mas->status = ma_start;
+		break;
+	case ma_overflow: /* user expects the mas to be one after where it is */
+		if (unlikely(mas->index <= min)) {
+			mas->status = ma_underflow;
 			return true;
 		}
 
-		mas->node = MAS_START;
+		mas->status = ma_active;
+		break;
+	case ma_underflow: /* user expects the mas to be one before where it is */
+		if (unlikely(mas->index <= min))
+			return true;
+
+		mas->status = ma_active;
+		break;
+	case ma_root:
+		break;
+	case ma_error:
+		return true;
 	}
 
 	if (mas_is_start(mas)) {
@@ -6068,29 +6110,28 @@ static inline bool mas_find_rev_setup(struct ma_state *mas, unsigned long min,
 			return true;
 	}
 
-	if (unlikely(!mas_searchable(mas))) {
-		if (mas_is_ptr(mas))
-			goto none;
+	if (unlikely(mas_is_ptr(mas)))
+		goto none;
 
-		if (mas_is_none(mas)) {
-			/*
-			 * Walked to the location, and there was nothing so the
-			 * previous location is 0.
-			 */
-			mas->last = mas->index = 0;
-			mas->node = MAS_ROOT;
-			*entry = mas_root(mas);
-			return true;
-		}
+	if (unlikely(mas_is_none(mas))) {
+		/*
+		 * Walked to the location, and there was nothing so the previous
+		 * location is 0.
+		 */
+		mas->last = mas->index = 0;
+		mas->status = ma_root;
+		*entry = mas_root(mas);
+		return true;
 	}
 
+active:
 	if (mas->index < min)
 		return true;
 
 	return false;
 
 none:
-	mas->node = MAS_NONE;
+	mas->status = ma_none;
 	return true;
 }
 
@@ -6103,7 +6144,7 @@ none:
  *
  * Must hold rcu_read_lock or the write lock.
  * If an entry exists, last and index are updated accordingly.
- * May set @mas->node to MAS_NONE.
+ * May set @mas->status to ma_underflow.
  *
  * Return: The entry or %NULL.
  */
@@ -6115,7 +6156,7 @@ void *mas_find_rev(struct ma_state *mas, unsigned long min)
 		return entry;
 
 	/* Retries on dead nodes handled by mas_prev_slot */
-	return mas_prev_slot(mas, min, false, false);
+	return mas_prev_slot(mas, min, false);
 
 }
 EXPORT_SYMBOL_GPL(mas_find_rev);
@@ -6129,7 +6170,7 @@ EXPORT_SYMBOL_GPL(mas_find_rev);
  *
  * Must hold rcu_read_lock or the write lock.
  * If an entry exists, last and index are updated accordingly.
- * May set @mas->node to MAS_NONE.
+ * May set @mas->status to ma_underflow.
  *
  * Return: The entry or %NULL.
  */
@@ -6141,7 +6182,7 @@ void *mas_find_range_rev(struct ma_state *mas, unsigned long min)
 		return entry;
 
 	/* Retries on dead nodes handled by mas_prev_slot */
-	return mas_prev_slot(mas, min, true, false);
+	return mas_prev_slot(mas, min, true);
 }
 EXPORT_SYMBOL_GPL(mas_find_range_rev);
 
@@ -6161,8 +6202,8 @@ void *mas_erase(struct ma_state *mas)
 	void *entry;
 	MA_WR_STATE(wr_mas, mas, NULL);
 
-	if (mas_is_none(mas) || mas_is_paused(mas))
-		mas->node = MAS_START;
+	if (!mas_is_active(mas) || !mas_is_start(mas))
+		mas->status = ma_start;
 
 	/* Retry unnecessary when holding the write lock. */
 	entry = mas_state_walk(mas);
@@ -6207,7 +6248,7 @@ bool mas_nomem(struct ma_state *mas, gfp_t gfp)
 	if (!mas_allocated(mas))
 		return false;
 
-	mas->node = MAS_START;
+	mas->status = ma_start;
 	return true;
 }
 
@@ -6465,6 +6506,278 @@ void *mtree_erase(struct maple_tree *mt, unsigned long index)
 }
 EXPORT_SYMBOL(mtree_erase);
 
+/*
+ * mas_dup_free() - Free an incomplete duplication of a tree.
+ * @mas: The maple state of a incomplete tree.
+ *
+ * The parameter @mas->node passed in indicates that the allocation failed on
+ * this node. This function frees all nodes starting from @mas->node in the
+ * reverse order of mas_dup_build(). There is no need to hold the source tree
+ * lock at this time.
+ */
+static void mas_dup_free(struct ma_state *mas)
+{
+	struct maple_node *node;
+	enum maple_type type;
+	void __rcu **slots;
+	unsigned char count, i;
+
+	/* Maybe the first node allocation failed. */
+	if (mas_is_none(mas))
+		return;
+
+	while (!mte_is_root(mas->node)) {
+		mas_ascend(mas);
+		if (mas->offset) {
+			mas->offset--;
+			do {
+				mas_descend(mas);
+				mas->offset = mas_data_end(mas);
+			} while (!mte_is_leaf(mas->node));
+
+			mas_ascend(mas);
+		}
+
+		node = mte_to_node(mas->node);
+		type = mte_node_type(mas->node);
+		slots = ma_slots(node, type);
+		count = mas_data_end(mas) + 1;
+		for (i = 0; i < count; i++)
+			((unsigned long *)slots)[i] &= ~MAPLE_NODE_MASK;
+		mt_free_bulk(count, slots);
+	}
+
+	node = mte_to_node(mas->node);
+	mt_free_one(node);
+}
+
+/*
+ * mas_copy_node() - Copy a maple node and replace the parent.
+ * @mas: The maple state of source tree.
+ * @new_mas: The maple state of new tree.
+ * @parent: The parent of the new node.
+ *
+ * Copy @mas->node to @new_mas->node, set @parent to be the parent of
+ * @new_mas->node. If memory allocation fails, @mas is set to -ENOMEM.
+ */
+static inline void mas_copy_node(struct ma_state *mas, struct ma_state *new_mas,
+		struct maple_pnode *parent)
+{
+	struct maple_node *node = mte_to_node(mas->node);
+	struct maple_node *new_node = mte_to_node(new_mas->node);
+	unsigned long val;
+
+	/* Copy the node completely. */
+	memcpy(new_node, node, sizeof(struct maple_node));
+	/* Update the parent node pointer. */
+	val = (unsigned long)node->parent & MAPLE_NODE_MASK;
+	new_node->parent = ma_parent_ptr(val | (unsigned long)parent);
+}
+
+/*
+ * mas_dup_alloc() - Allocate child nodes for a maple node.
+ * @mas: The maple state of source tree.
+ * @new_mas: The maple state of new tree.
+ * @gfp: The GFP_FLAGS to use for allocations.
+ *
+ * This function allocates child nodes for @new_mas->node during the duplication
+ * process. If memory allocation fails, @mas is set to -ENOMEM.
+ */
+static inline void mas_dup_alloc(struct ma_state *mas, struct ma_state *new_mas,
+		gfp_t gfp)
+{
+	struct maple_node *node = mte_to_node(mas->node);
+	struct maple_node *new_node = mte_to_node(new_mas->node);
+	enum maple_type type;
+	unsigned char request, count, i;
+	void __rcu **slots;
+	void __rcu **new_slots;
+	unsigned long val;
+
+	/* Allocate memory for child nodes. */
+	type = mte_node_type(mas->node);
+	new_slots = ma_slots(new_node, type);
+	request = mas_data_end(mas) + 1;
+	count = mt_alloc_bulk(gfp, request, (void **)new_slots);
+	if (unlikely(count < request)) {
+		memset(new_slots, 0, request * sizeof(void *));
+		mas_set_err(mas, -ENOMEM);
+		return;
+	}
+
+	/* Restore node type information in slots. */
+	slots = ma_slots(node, type);
+	for (i = 0; i < count; i++) {
+		val = (unsigned long)mt_slot_locked(mas->tree, slots, i);
+		val &= MAPLE_NODE_MASK;
+		((unsigned long *)new_slots)[i] |= val;
+	}
+}
+
+/*
+ * mas_dup_build() - Build a new maple tree from a source tree
+ * @mas: The maple state of source tree, need to be in MAS_START state.
+ * @new_mas: The maple state of new tree, need to be in MAS_START state.
+ * @gfp: The GFP_FLAGS to use for allocations.
+ *
+ * This function builds a new tree in DFS preorder. If the memory allocation
+ * fails, the error code -ENOMEM will be set in @mas, and @new_mas points to the
+ * last node. mas_dup_free() will free the incomplete duplication of a tree.
+ *
+ * Note that the attributes of the two trees need to be exactly the same, and the
+ * new tree needs to be empty, otherwise -EINVAL will be set in @mas.
+ */
+static inline void mas_dup_build(struct ma_state *mas, struct ma_state *new_mas,
+		gfp_t gfp)
+{
+	struct maple_node *node;
+	struct maple_pnode *parent = NULL;
+	struct maple_enode *root;
+	enum maple_type type;
+
+	if (unlikely(mt_attr(mas->tree) != mt_attr(new_mas->tree)) ||
+	    unlikely(!mtree_empty(new_mas->tree))) {
+		mas_set_err(mas, -EINVAL);
+		return;
+	}
+
+	root = mas_start(mas);
+	if (mas_is_ptr(mas) || mas_is_none(mas))
+		goto set_new_tree;
+
+	node = mt_alloc_one(gfp);
+	if (!node) {
+		new_mas->status = ma_none;
+		mas_set_err(mas, -ENOMEM);
+		return;
+	}
+
+	type = mte_node_type(mas->node);
+	root = mt_mk_node(node, type);
+	new_mas->node = root;
+	new_mas->min = 0;
+	new_mas->max = ULONG_MAX;
+	root = mte_mk_root(root);
+	while (1) {
+		mas_copy_node(mas, new_mas, parent);
+		if (!mte_is_leaf(mas->node)) {
+			/* Only allocate child nodes for non-leaf nodes. */
+			mas_dup_alloc(mas, new_mas, gfp);
+			if (unlikely(mas_is_err(mas)))
+				return;
+		} else {
+			/*
+			 * This is the last leaf node and duplication is
+			 * completed.
+			 */
+			if (mas->max == ULONG_MAX)
+				goto done;
+
+			/* This is not the last leaf node and needs to go up. */
+			do {
+				mas_ascend(mas);
+				mas_ascend(new_mas);
+			} while (mas->offset == mas_data_end(mas));
+
+			/* Move to the next subtree. */
+			mas->offset++;
+			new_mas->offset++;
+		}
+
+		mas_descend(mas);
+		parent = ma_parent_ptr(mte_to_node(new_mas->node));
+		mas_descend(new_mas);
+		mas->offset = 0;
+		new_mas->offset = 0;
+	}
+done:
+	/* Specially handle the parent of the root node. */
+	mte_to_node(root)->parent = ma_parent_ptr(mas_tree_parent(new_mas));
+set_new_tree:
+	/* Make them the same height */
+	new_mas->tree->ma_flags = mas->tree->ma_flags;
+	rcu_assign_pointer(new_mas->tree->ma_root, root);
+}
+
+/**
+ * __mt_dup(): Duplicate an entire maple tree
+ * @mt: The source maple tree
+ * @new: The new maple tree
+ * @gfp: The GFP_FLAGS to use for allocations
+ *
+ * This function duplicates a maple tree in Depth-First Search (DFS) pre-order
+ * traversal. It uses memcpy() to copy nodes in the source tree and allocate
+ * new child nodes in non-leaf nodes. The new node is exactly the same as the
+ * source node except for all the addresses stored in it. It will be faster than
+ * traversing all elements in the source tree and inserting them one by one into
+ * the new tree.
+ * The user needs to ensure that the attributes of the source tree and the new
+ * tree are the same, and the new tree needs to be an empty tree, otherwise
+ * -EINVAL will be returned.
+ * Note that the user needs to manually lock the source tree and the new tree.
+ *
+ * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If
+ * the attributes of the two trees are different or the new tree is not an empty
+ * tree.
+ */
+int __mt_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp)
+{
+	int ret = 0;
+	MA_STATE(mas, mt, 0, 0);
+	MA_STATE(new_mas, new, 0, 0);
+
+	mas_dup_build(&mas, &new_mas, gfp);
+	if (unlikely(mas_is_err(&mas))) {
+		ret = xa_err(mas.node);
+		if (ret == -ENOMEM)
+			mas_dup_free(&new_mas);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(__mt_dup);
+
+/**
+ * mtree_dup(): Duplicate an entire maple tree
+ * @mt: The source maple tree
+ * @new: The new maple tree
+ * @gfp: The GFP_FLAGS to use for allocations
+ *
+ * This function duplicates a maple tree in Depth-First Search (DFS) pre-order
+ * traversal. It uses memcpy() to copy nodes in the source tree and allocate
+ * new child nodes in non-leaf nodes. The new node is exactly the same as the
+ * source node except for all the addresses stored in it. It will be faster than
+ * traversing all elements in the source tree and inserting them one by one into
+ * the new tree.
+ * The user needs to ensure that the attributes of the source tree and the new
+ * tree are the same, and the new tree needs to be an empty tree, otherwise
+ * -EINVAL will be returned.
+ *
+ * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If
+ * the attributes of the two trees are different or the new tree is not an empty
+ * tree.
+ */
+int mtree_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp)
+{
+	int ret = 0;
+	MA_STATE(mas, mt, 0, 0);
+	MA_STATE(new_mas, new, 0, 0);
+
+	mas_lock(&new_mas);
+	mas_lock_nested(&mas, SINGLE_DEPTH_NESTING);
+	mas_dup_build(&mas, &new_mas, gfp);
+	mas_unlock(&mas);
+	if (unlikely(mas_is_err(&mas))) {
+		ret = xa_err(mas.node);
+		if (ret == -ENOMEM)
+			mas_dup_free(&new_mas);
+	}
+
+	mas_unlock(&new_mas);
+	return ret;
+}
+EXPORT_SYMBOL(mtree_dup);
+
 /**
  * __mt_destroy() - Walk and free all nodes of a locked maple tree.
  * @mt: The maple tree
@@ -6479,7 +6792,7 @@ void __mt_destroy(struct maple_tree *mt)
 	if (xa_is_node(root))
 		mte_destroy_walk(root, mt);
 
-	mt->ma_flags = 0;
+	mt->ma_flags = mt_attr(mt);
 }
 EXPORT_SYMBOL_GPL(__mt_destroy);
 
@@ -6538,7 +6851,7 @@ retry:
 	if (entry)
 		goto unlock;
 
-	while (mas_searchable(&mas) && (mas.last < max)) {
+	while (mas_is_active(&mas) && (mas.last < max)) {
 		entry = mas_next_entry(&mas, max);
 		if (likely(entry && !xa_is_zero(entry)))
 			break;
@@ -6620,26 +6933,6 @@ unsigned int mt_nr_allocated(void)
 	return kmem_cache_nr_allocated(maple_node_cache);
 }
 
-/*
- * mas_dead_node() - Check if the maple state is pointing to a dead node.
- * @mas: The maple state
- * @index: The index to restore in @mas.
- *
- * Used in test code.
- * Return: 1 if @mas has been reset to MAS_START, 0 otherwise.
- */
-static inline int mas_dead_node(struct ma_state *mas, unsigned long index)
-{
-	if (unlikely(!mas_searchable(mas) || mas_is_start(mas)))
-		return 0;
-
-	if (likely(!mte_dead_node(mas->node)))
-		return 0;
-
-	mas_rewalk(mas, index);
-	return 1;
-}
-
 void mt_cache_shrink(void)
 {
 }
@@ -6678,11 +6971,11 @@ static inline struct maple_enode *mas_get_slot(struct ma_state *mas,
 static void mas_dfs_postorder(struct ma_state *mas, unsigned long max)
 {
 
-	struct maple_enode *p = MAS_NONE, *mn = mas->node;
+	struct maple_enode *p, *mn = mas->node;
 	unsigned long p_min, p_max;
 
 	mas_next_node(mas, mas_mn(mas), max);
-	if (!mas_is_none(mas))
+	if (!mas_is_overflow(mas))
 		return;
 
 	if (mte_is_root(mn))
@@ -6695,7 +6988,7 @@ static void mas_dfs_postorder(struct ma_state *mas, unsigned long max)
 		p_min = mas->min;
 		p_max = mas->max;
 		mas_prev_node(mas, 0);
-	} while (!mas_is_none(mas));
+	} while (!mas_is_underflow(mas));
 
 	mas->node = p;
 	mas->max = p_max;
@@ -6718,7 +7011,6 @@ static void mt_dump_range(unsigned long min, unsigned long max,
 		else
 			pr_info("%.*s%lx-%lx: ", depth * 2, spaces, min, max);
 		break;
-	default:
 	case mt_dump_dec:
 		if (min == max)
 			pr_info("%.*s%lu: ", depth * 2, spaces, min);
@@ -6758,7 +7050,6 @@ static void mt_dump_range64(const struct maple_tree *mt, void *entry,
 		case mt_dump_hex:
 			pr_cont("%p %lX ", node->slot[i], node->pivot[i]);
 			break;
-		default:
 		case mt_dump_dec:
 			pr_cont("%p %lu ", node->slot[i], node->pivot[i]);
 		}
@@ -6788,7 +7079,6 @@ static void mt_dump_range64(const struct maple_tree *mt, void *entry,
 				pr_err("node %p last (%lx) > max (%lx) at pivot %d!\n",
 					node, last, max, i);
 				break;
-			default:
 			case mt_dump_dec:
 				pr_err("node %p last (%lu) > max (%lu) at pivot %d!\n",
 					node, last, max, i);
@@ -6813,7 +7103,6 @@ static void mt_dump_arange64(const struct maple_tree *mt, void *entry,
 		case mt_dump_hex:
 			pr_cont("%lx ", node->gap[i]);
 			break;
-		default:
 		case mt_dump_dec:
 			pr_cont("%lu ", node->gap[i]);
 		}
@@ -6824,7 +7113,6 @@ static void mt_dump_arange64(const struct maple_tree *mt, void *entry,
 		case mt_dump_hex:
 			pr_cont("%p %lX ", node->slot[i], node->pivot[i]);
 			break;
-		default:
 		case mt_dump_dec:
 			pr_cont("%p %lu ", node->slot[i], node->pivot[i]);
 		}
@@ -6965,7 +7253,8 @@ static void mas_validate_gaps(struct ma_state *mas)
 
 counted:
 	if (mt == maple_arange_64) {
-		offset = ma_meta_gap(node, mt);
+		MT_BUG_ON(mas->tree, !gaps);
+		offset = ma_meta_gap(node);
 		if (offset > i) {
 			pr_err("gap offset %p[%u] is invalid\n", node, offset);
 			MT_BUG_ON(mas->tree, 1);
@@ -6977,7 +7266,6 @@ counted:
 			MT_BUG_ON(mas->tree, 1);
 		}
 
-		MT_BUG_ON(mas->tree, !gaps);
 		for (i++ ; i < mt_slot_count(mte); i++) {
 			if (gaps[i] != 0) {
 				pr_err("gap %p[%u] beyond node limit != 0\n",
@@ -7155,7 +7443,7 @@ static void mt_validate_nulls(struct maple_tree *mt)
 	MA_STATE(mas, mt, 0, 0);
 
 	mas_start(&mas);
-	if (mas_is_none(&mas) || (mas.node == MAS_ROOT))
+	if (mas_is_none(&mas) || (mas_is_ptr(&mas)))
 		return;
 
 	while (!mte_is_leaf(mas.node))
@@ -7172,7 +7460,7 @@ static void mt_validate_nulls(struct maple_tree *mt)
 		last = entry;
 		if (offset == mas_data_end(&mas)) {
 			mas_next_node(&mas, mas_mn(&mas), ULONG_MAX);
-			if (mas_is_none(&mas))
+			if (mas_is_overflow(&mas))
 				return;
 			offset = 0;
 			slots = ma_slots(mte_to_node(mas.node),
@@ -7181,7 +7469,7 @@ static void mt_validate_nulls(struct maple_tree *mt)
 			offset++;
 		}
 
-	} while (!mas_is_none(&mas));
+	} while (!mas_is_overflow(&mas));
 }
 
 /*
@@ -7196,13 +7484,13 @@ void mt_validate(struct maple_tree *mt)
 	MA_STATE(mas, mt, 0, 0);
 	rcu_read_lock();
 	mas_start(&mas);
-	if (!mas_searchable(&mas))
+	if (!mas_is_active(&mas))
 		goto done;
 
 	while (!mte_is_leaf(mas.node))
 		mas_descend(&mas);
 
-	while (!mas_is_none(&mas)) {
+	while (!mas_is_overflow(&mas)) {
 		MAS_WARN_ON(&mas, mte_dead_node(mas.node));
 		end = mas_data_end(&mas);
 		if (MAS_WARN_ON(&mas, (end < mt_min_slot_count(mas.node)) &&
@@ -7227,16 +7515,35 @@ EXPORT_SYMBOL_GPL(mt_validate);
 void mas_dump(const struct ma_state *mas)
 {
 	pr_err("MAS: tree=%p enode=%p ", mas->tree, mas->node);
-	if (mas_is_none(mas))
-		pr_err("(MAS_NONE) ");
-	else if (mas_is_ptr(mas))
-		pr_err("(MAS_ROOT) ");
-	else if (mas_is_start(mas))
-		 pr_err("(MAS_START) ");
-	else if (mas_is_paused(mas))
-		pr_err("(MAS_PAUSED) ");
-
-	pr_err("[%u] index=%lx last=%lx\n", mas->offset, mas->index, mas->last);
+	switch (mas->status) {
+	case ma_active:
+		pr_err("(ma_active)");
+		break;
+	case ma_none:
+		pr_err("(ma_none)");
+		break;
+	case ma_root:
+		pr_err("(ma_root)");
+		break;
+	case ma_start:
+		pr_err("(ma_start) ");
+		break;
+	case ma_pause:
+		pr_err("(ma_pause) ");
+		break;
+	case ma_overflow:
+		pr_err("(ma_overflow) ");
+		break;
+	case ma_underflow:
+		pr_err("(ma_underflow) ");
+		break;
+	case ma_error:
+		pr_err("(ma_error) ");
+		break;
+	}
+
+	pr_err("[%u/%u] index=%lx last=%lx\n", mas->offset, mas->end,
+	       mas->index, mas->last);
 	pr_err("     min=%lx max=%lx alloc=%p, depth=%u, flags=%x\n",
 	       mas->min, mas->max, mas->alloc, mas->depth, mas->mas_flags);
 	if (mas->index > mas->last)
@@ -7249,7 +7556,7 @@ void mas_wr_dump(const struct ma_wr_state *wr_mas)
 	pr_err("WR_MAS: node=%p r_min=%lx r_max=%lx\n",
 	       wr_mas->node, wr_mas->r_min, wr_mas->r_max);
 	pr_err("        type=%u off_end=%u, node_end=%u, end_piv=%lx\n",
-	       wr_mas->type, wr_mas->offset_end, wr_mas->node_end,
+	       wr_mas->type, wr_mas->offset_end, wr_mas->mas->end,
 	       wr_mas->end_piv);
 }
 EXPORT_SYMBOL_GPL(mas_wr_dump);
diff --git a/lib/objpool.c b/lib/objpool.c
index ce0087f64400..cfdc02420884 100644
--- a/lib/objpool.c
+++ b/lib/objpool.c
@@ -201,6 +201,23 @@ static inline void *objpool_try_get_slot(struct objpool_head *pool, int cpu)
 	while (head != READ_ONCE(slot->last)) {
 		void *obj;
 
+		/*
+		 * data visibility of 'last' and 'head' could be out of
+		 * order since memory updating of 'last' and 'head' are
+		 * performed in push() and pop() independently
+		 *
+		 * before any retrieving attempts, pop() must guarantee
+		 * 'last' is behind 'head', that is to say, there must
+		 * be available objects in slot, which could be ensured
+		 * by condition 'last != head && last - head <= nr_objs'
+		 * that is equivalent to 'last - head - 1 < nr_objs' as
+		 * 'last' and 'head' are both unsigned int32
+		 */
+		if (READ_ONCE(slot->last) - head - 1 >= pool->nr_objs) {
+			head = READ_ONCE(slot->head);
+			continue;
+		}
+
 		/* obj must be retrieved before moving forward head */
 		obj = READ_ONCE(slot->entries[head & slot->mask]);
 
diff --git a/lib/overflow_kunit.c b/lib/overflow_kunit.c
index 34db0b3aa502..c527f6b75789 100644
--- a/lib/overflow_kunit.c
+++ b/lib/overflow_kunit.c
@@ -6,6 +6,7 @@
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <kunit/device.h>
 #include <kunit/test.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
@@ -618,7 +619,7 @@ static void overflow_allocation_test(struct kunit *test)
 } while (0)
 
 	/* Create dummy device for devm_kmalloc()-family tests. */
-	dev = root_device_register(device_name);
+	dev = kunit_device_register(test, device_name);
 	KUNIT_ASSERT_FALSE_MSG(test, IS_ERR(dev),
 			       "Cannot register test device\n");
 
@@ -634,8 +635,6 @@ static void overflow_allocation_test(struct kunit *test)
 	check_allocation_overflow(devm_kmalloc);
 	check_allocation_overflow(devm_kzalloc);
 
-	device_unregister(dev);
-
 	kunit_info(test, "%d allocation overflow tests finished\n", count);
 #undef check_allocation_overflow
 }
diff --git a/lib/raid6/s390vx.uc b/lib/raid6/s390vx.uc
index b25dfc9c7759..cd0b9e95f499 100644
--- a/lib/raid6/s390vx.uc
+++ b/lib/raid6/s390vx.uc
@@ -158,7 +158,7 @@ static void raid6_s390vx$#_xor_syndrome(int disks, int start, int stop,
 
 static int raid6_s390vx$#_valid(void)
 {
-	return MACHINE_HAS_VX;
+	return cpu_has_vx();
 }
 
 const struct raid6_calls raid6_s390vx$# = {
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index 2f5aa851834e..a0be5d05c7f0 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -18,11 +18,14 @@
 #include <linux/jhash.h>
 #include <linux/kernel.h>
 #include <linux/kmsan.h>
+#include <linux/list.h>
 #include <linux/mm.h>
 #include <linux/mutex.h>
 #include <linux/percpu.h>
 #include <linux/printk.h>
+#include <linux/refcount.h>
 #include <linux/slab.h>
+#include <linux/spinlock.h>
 #include <linux/stacktrace.h>
 #include <linux/stackdepot.h>
 #include <linux/string.h>
@@ -32,14 +35,23 @@
 
 #define DEPOT_HANDLE_BITS (sizeof(depot_stack_handle_t) * 8)
 
-#define DEPOT_VALID_BITS 1
 #define DEPOT_POOL_ORDER 2 /* Pool size order, 4 pages */
 #define DEPOT_POOL_SIZE (1LL << (PAGE_SHIFT + DEPOT_POOL_ORDER))
 #define DEPOT_STACK_ALIGN 4
 #define DEPOT_OFFSET_BITS (DEPOT_POOL_ORDER + PAGE_SHIFT - DEPOT_STACK_ALIGN)
-#define DEPOT_POOL_INDEX_BITS (DEPOT_HANDLE_BITS - DEPOT_VALID_BITS - \
-			       DEPOT_OFFSET_BITS - STACK_DEPOT_EXTRA_BITS)
+#define DEPOT_POOL_INDEX_BITS (DEPOT_HANDLE_BITS - DEPOT_OFFSET_BITS - \
+			       STACK_DEPOT_EXTRA_BITS)
+#if IS_ENABLED(CONFIG_KMSAN) && CONFIG_STACKDEPOT_MAX_FRAMES >= 32
+/*
+ * KMSAN is frequently used in fuzzing scenarios and thus saves a lot of stack
+ * traces. As KMSAN does not support evicting stack traces from the stack
+ * depot, the stack depot capacity might be reached quickly with large stack
+ * records. Adjust the maximum number of stack depot pools for this case.
+ */
+#define DEPOT_POOLS_CAP (8192 * (CONFIG_STACKDEPOT_MAX_FRAMES / 16))
+#else
 #define DEPOT_POOLS_CAP 8192
+#endif
 #define DEPOT_MAX_POOLS \
 	(((1LL << (DEPOT_POOL_INDEX_BITS)) < DEPOT_POOLS_CAP) ? \
 	 (1LL << (DEPOT_POOL_INDEX_BITS)) : DEPOT_POOLS_CAP)
@@ -50,19 +62,22 @@ union handle_parts {
 	struct {
 		u32 pool_index	: DEPOT_POOL_INDEX_BITS;
 		u32 offset	: DEPOT_OFFSET_BITS;
-		u32 valid	: DEPOT_VALID_BITS;
 		u32 extra	: STACK_DEPOT_EXTRA_BITS;
 	};
 };
 
 struct stack_record {
-	struct stack_record *next;	/* Link in the hash table */
-	u32 hash;			/* Hash in the hash table */
+	struct list_head list;		/* Links in hash table or freelist */
+	u32 hash;			/* Hash in hash table */
 	u32 size;			/* Number of stored frames */
 	union handle_parts handle;
-	unsigned long entries[];	/* Variable-sized array of frames */
+	refcount_t count;
+	unsigned long entries[CONFIG_STACKDEPOT_MAX_FRAMES];	/* Frames */
 };
 
+#define DEPOT_STACK_RECORD_SIZE \
+	ALIGN(sizeof(struct stack_record), 1 << DEPOT_STACK_ALIGN)
+
 static bool stack_depot_disabled;
 static bool __stack_depot_early_init_requested __initdata = IS_ENABLED(CONFIG_STACKDEPOT_ALWAYS_INIT);
 static bool __stack_depot_early_init_passed __initdata;
@@ -75,40 +90,34 @@ static bool __stack_depot_early_init_passed __initdata;
 /* Initial seed for jhash2. */
 #define STACK_HASH_SEED 0x9747b28c
 
-/* Hash table of pointers to stored stack traces. */
-static struct stack_record **stack_table;
+/* Hash table of stored stack records. */
+static struct list_head *stack_table;
 /* Fixed order of the number of table buckets. Used when KASAN is enabled. */
 static unsigned int stack_bucket_number_order;
 /* Hash mask for indexing the table. */
 static unsigned int stack_hash_mask;
 
-/* Array of memory regions that store stack traces. */
+/* Array of memory regions that store stack records. */
 static void *stack_pools[DEPOT_MAX_POOLS];
-/* Currently used pool in stack_pools. */
-static int pool_index;
-/* Offset to the unused space in the currently used pool. */
-static size_t pool_offset;
-/* Lock that protects the variables above. */
-static DEFINE_RAW_SPINLOCK(pool_lock);
+/* Newly allocated pool that is not yet added to stack_pools. */
+static void *new_pool;
+/* Number of pools in stack_pools. */
+static int pools_num;
+/* Freelist of stack records within stack_pools. */
+static LIST_HEAD(free_stacks);
 /*
  * Stack depot tries to keep an extra pool allocated even before it runs out
- * of space in the currently used pool.
- * This flag marks that this next extra pool needs to be allocated and
- * initialized. It has the value 0 when either the next pool is not yet
- * initialized or the limit on the number of pools is reached.
+ * of space in the currently used pool. This flag marks whether this extra pool
+ * needs to be allocated. It has the value 0 when either an extra pool is not
+ * yet allocated or if the limit on the number of pools is reached.
  */
-static int next_pool_required = 1;
+static bool new_pool_required = true;
+/* Lock that protects the variables above. */
+static DEFINE_RWLOCK(pool_rwlock);
 
 static int __init disable_stack_depot(char *str)
 {
-	int ret;
-
-	ret = kstrtobool(str, &stack_depot_disabled);
-	if (!ret && stack_depot_disabled) {
-		pr_info("disabled\n");
-		stack_table = NULL;
-	}
-	return 0;
+	return kstrtobool(str, &stack_depot_disabled);
 }
 early_param("stack_depot_disable", disable_stack_depot);
 
@@ -120,6 +129,15 @@ void __init stack_depot_request_early_init(void)
 	__stack_depot_early_init_requested = true;
 }
 
+/* Initialize list_head's within the hash table. */
+static void init_stack_table(unsigned long entries)
+{
+	unsigned long i;
+
+	for (i = 0; i < entries; i++)
+		INIT_LIST_HEAD(&stack_table[i]);
+}
+
 /* Allocates a hash table via memblock. Can only be used during early boot. */
 int __init stack_depot_early_init(void)
 {
@@ -131,6 +149,15 @@ int __init stack_depot_early_init(void)
 	__stack_depot_early_init_passed = true;
 
 	/*
+	 * Print disabled message even if early init has not been requested:
+	 * stack_depot_init() will not print one.
+	 */
+	if (stack_depot_disabled) {
+		pr_info("disabled\n");
+		return 0;
+	}
+
+	/*
 	 * If KASAN is enabled, use the maximum order: KASAN is frequently used
 	 * in fuzzing scenarios, which leads to a large number of different
 	 * stack traces being stored in stack depot.
@@ -138,21 +165,25 @@ int __init stack_depot_early_init(void)
 	if (kasan_enabled() && !stack_bucket_number_order)
 		stack_bucket_number_order = STACK_BUCKET_NUMBER_ORDER_MAX;
 
-	if (!__stack_depot_early_init_requested || stack_depot_disabled)
+	/*
+	 * Check if early init has been requested after setting
+	 * stack_bucket_number_order: stack_depot_init() uses its value.
+	 */
+	if (!__stack_depot_early_init_requested)
 		return 0;
 
 	/*
 	 * If stack_bucket_number_order is not set, leave entries as 0 to rely
-	 * on the automatic calculations performed by alloc_large_system_hash.
+	 * on the automatic calculations performed by alloc_large_system_hash().
 	 */
 	if (stack_bucket_number_order)
 		entries = 1UL << stack_bucket_number_order;
 	pr_info("allocating hash table via alloc_large_system_hash\n");
 	stack_table = alloc_large_system_hash("stackdepot",
-						sizeof(struct stack_record *),
+						sizeof(struct list_head),
 						entries,
 						STACK_HASH_TABLE_SCALE,
-						HASH_EARLY | HASH_ZERO,
+						HASH_EARLY,
 						NULL,
 						&stack_hash_mask,
 						1UL << STACK_BUCKET_NUMBER_ORDER_MIN,
@@ -162,6 +193,14 @@ int __init stack_depot_early_init(void)
 		stack_depot_disabled = true;
 		return -ENOMEM;
 	}
+	if (!entries) {
+		/*
+		 * Obtain the number of entries that was calculated by
+		 * alloc_large_system_hash().
+		 */
+		entries = stack_hash_mask + 1;
+	}
+	init_stack_table(entries);
 
 	return 0;
 }
@@ -202,7 +241,7 @@ int stack_depot_init(void)
 		entries = 1UL << STACK_BUCKET_NUMBER_ORDER_MAX;
 
 	pr_info("allocating hash table of %lu entries via kvcalloc\n", entries);
-	stack_table = kvcalloc(entries, sizeof(struct stack_record *), GFP_KERNEL);
+	stack_table = kvcalloc(entries, sizeof(struct list_head), GFP_KERNEL);
 	if (!stack_table) {
 		pr_err("hash table allocation failed, disabling\n");
 		stack_depot_disabled = true;
@@ -210,6 +249,7 @@ int stack_depot_init(void)
 		goto out_unlock;
 	}
 	stack_hash_mask = entries - 1;
+	init_stack_table(entries);
 
 out_unlock:
 	mutex_unlock(&stack_depot_init_mutex);
@@ -218,41 +258,103 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(stack_depot_init);
 
-/* Uses preallocated memory to initialize a new stack depot pool. */
-static void depot_init_pool(void **prealloc)
+/* Initializes a stack depol pool. */
+static void depot_init_pool(void *pool)
 {
+	int offset;
+
+	lockdep_assert_held_write(&pool_rwlock);
+
+	WARN_ON(!list_empty(&free_stacks));
+
+	/* Initialize handles and link stack records into the freelist. */
+	for (offset = 0; offset <= DEPOT_POOL_SIZE - DEPOT_STACK_RECORD_SIZE;
+	     offset += DEPOT_STACK_RECORD_SIZE) {
+		struct stack_record *stack = pool + offset;
+
+		stack->handle.pool_index = pools_num;
+		stack->handle.offset = offset >> DEPOT_STACK_ALIGN;
+		stack->handle.extra = 0;
+
+		list_add(&stack->list, &free_stacks);
+	}
+
+	/* Save reference to the pool to be used by depot_fetch_stack(). */
+	stack_pools[pools_num] = pool;
+	pools_num++;
+}
+
+/* Keeps the preallocated memory to be used for a new stack depot pool. */
+static void depot_keep_new_pool(void **prealloc)
+{
+	lockdep_assert_held_write(&pool_rwlock);
+
 	/*
-	 * If the next pool is already initialized or the maximum number of
+	 * If a new pool is already saved or the maximum number of
 	 * pools is reached, do not use the preallocated memory.
-	 * smp_load_acquire() here pairs with smp_store_release() below and
-	 * in depot_alloc_stack().
 	 */
-	if (!smp_load_acquire(&next_pool_required))
+	if (!new_pool_required)
 		return;
 
-	/* Check if the current pool is not yet allocated. */
-	if (stack_pools[pool_index] == NULL) {
-		/* Use the preallocated memory for the current pool. */
-		stack_pools[pool_index] = *prealloc;
+	/*
+	 * Use the preallocated memory for the new pool
+	 * as long as we do not exceed the maximum number of pools.
+	 */
+	if (pools_num < DEPOT_MAX_POOLS) {
+		new_pool = *prealloc;
 		*prealloc = NULL;
-	} else {
-		/*
-		 * Otherwise, use the preallocated memory for the next pool
-		 * as long as we do not exceed the maximum number of pools.
-		 */
-		if (pool_index + 1 < DEPOT_MAX_POOLS) {
-			stack_pools[pool_index + 1] = *prealloc;
-			*prealloc = NULL;
-		}
-		/*
-		 * At this point, either the next pool is initialized or the
-		 * maximum number of pools is reached. In either case, take
-		 * note that initializing another pool is not required.
-		 * This smp_store_release pairs with smp_load_acquire() above
-		 * and in stack_depot_save().
-		 */
-		smp_store_release(&next_pool_required, 0);
 	}
+
+	/*
+	 * At this point, either a new pool is kept or the maximum
+	 * number of pools is reached. In either case, take note that
+	 * keeping another pool is not required.
+	 */
+	new_pool_required = false;
+}
+
+/* Updates references to the current and the next stack depot pools. */
+static bool depot_update_pools(void **prealloc)
+{
+	lockdep_assert_held_write(&pool_rwlock);
+
+	/* Check if we still have objects in the freelist. */
+	if (!list_empty(&free_stacks))
+		goto out_keep_prealloc;
+
+	/* Check if we have a new pool saved and use it. */
+	if (new_pool) {
+		depot_init_pool(new_pool);
+		new_pool = NULL;
+
+		/* Take note that we might need a new new_pool. */
+		if (pools_num < DEPOT_MAX_POOLS)
+			new_pool_required = true;
+
+		/* Try keeping the preallocated memory for new_pool. */
+		goto out_keep_prealloc;
+	}
+
+	/* Bail out if we reached the pool limit. */
+	if (unlikely(pools_num >= DEPOT_MAX_POOLS)) {
+		WARN_ONCE(1, "Stack depot reached limit capacity");
+		return false;
+	}
+
+	/* Check if we have preallocated memory and use it. */
+	if (*prealloc) {
+		depot_init_pool(*prealloc);
+		*prealloc = NULL;
+		return true;
+	}
+
+	return false;
+
+out_keep_prealloc:
+	/* Keep the preallocated memory for a new pool if required. */
+	if (*prealloc)
+		depot_keep_new_pool(prealloc);
+	return true;
 }
 
 /* Allocates a new stack in a stack depot pool. */
@@ -260,62 +362,72 @@ static struct stack_record *
 depot_alloc_stack(unsigned long *entries, int size, u32 hash, void **prealloc)
 {
 	struct stack_record *stack;
-	size_t required_size = struct_size(stack, entries, size);
 
-	required_size = ALIGN(required_size, 1 << DEPOT_STACK_ALIGN);
+	lockdep_assert_held_write(&pool_rwlock);
 
-	/* Check if there is not enough space in the current pool. */
-	if (unlikely(pool_offset + required_size > DEPOT_POOL_SIZE)) {
-		/* Bail out if we reached the pool limit. */
-		if (unlikely(pool_index + 1 >= DEPOT_MAX_POOLS)) {
-			WARN_ONCE(1, "Stack depot reached limit capacity");
-			return NULL;
-		}
+	/* Update current and new pools if required and possible. */
+	if (!depot_update_pools(prealloc))
+		return NULL;
 
-		/*
-		 * Move on to the next pool.
-		 * WRITE_ONCE pairs with potential concurrent read in
-		 * stack_depot_fetch().
-		 */
-		WRITE_ONCE(pool_index, pool_index + 1);
-		pool_offset = 0;
-		/*
-		 * If the maximum number of pools is not reached, take note
-		 * that the next pool needs to initialized.
-		 * smp_store_release() here pairs with smp_load_acquire() in
-		 * stack_depot_save() and depot_init_pool().
-		 */
-		if (pool_index + 1 < DEPOT_MAX_POOLS)
-			smp_store_release(&next_pool_required, 1);
-	}
+	/* Check if we have a stack record to save the stack trace. */
+	if (list_empty(&free_stacks))
+		return NULL;
 
-	/* Assign the preallocated memory to a pool if required. */
-	if (*prealloc)
-		depot_init_pool(prealloc);
+	/* Get and unlink the first entry from the freelist. */
+	stack = list_first_entry(&free_stacks, struct stack_record, list);
+	list_del(&stack->list);
 
-	/* Check if we have a pool to save the stack trace. */
-	if (stack_pools[pool_index] == NULL)
-		return NULL;
+	/* Limit number of saved frames to CONFIG_STACKDEPOT_MAX_FRAMES. */
+	if (size > CONFIG_STACKDEPOT_MAX_FRAMES)
+		size = CONFIG_STACKDEPOT_MAX_FRAMES;
 
 	/* Save the stack trace. */
-	stack = stack_pools[pool_index] + pool_offset;
 	stack->hash = hash;
 	stack->size = size;
-	stack->handle.pool_index = pool_index;
-	stack->handle.offset = pool_offset >> DEPOT_STACK_ALIGN;
-	stack->handle.valid = 1;
-	stack->handle.extra = 0;
+	/* stack->handle is already filled in by depot_init_pool(). */
+	refcount_set(&stack->count, 1);
 	memcpy(stack->entries, entries, flex_array_size(stack, entries, size));
-	pool_offset += required_size;
+
 	/*
 	 * Let KMSAN know the stored stack record is initialized. This shall
 	 * prevent false positive reports if instrumented code accesses it.
 	 */
-	kmsan_unpoison_memory(stack, required_size);
+	kmsan_unpoison_memory(stack, DEPOT_STACK_RECORD_SIZE);
 
 	return stack;
 }
 
+static struct stack_record *depot_fetch_stack(depot_stack_handle_t handle)
+{
+	union handle_parts parts = { .handle = handle };
+	void *pool;
+	size_t offset = parts.offset << DEPOT_STACK_ALIGN;
+	struct stack_record *stack;
+
+	lockdep_assert_held(&pool_rwlock);
+
+	if (parts.pool_index > pools_num) {
+		WARN(1, "pool index %d out of bounds (%d) for stack id %08x\n",
+		     parts.pool_index, pools_num, handle);
+		return NULL;
+	}
+
+	pool = stack_pools[parts.pool_index];
+	if (!pool)
+		return NULL;
+
+	stack = pool + offset;
+	return stack;
+}
+
+/* Links stack into the freelist. */
+static void depot_free_stack(struct stack_record *stack)
+{
+	lockdep_assert_held_write(&pool_rwlock);
+
+	list_add(&stack->list, &free_stacks);
+}
+
 /* Calculates the hash for a stack. */
 static inline u32 hash_stack(unsigned long *entries, unsigned int size)
 {
@@ -340,13 +452,17 @@ int stackdepot_memcmp(const unsigned long *u1, const unsigned long *u2,
 }
 
 /* Finds a stack in a bucket of the hash table. */
-static inline struct stack_record *find_stack(struct stack_record *bucket,
+static inline struct stack_record *find_stack(struct list_head *bucket,
 					     unsigned long *entries, int size,
 					     u32 hash)
 {
+	struct list_head *pos;
 	struct stack_record *found;
 
-	for (found = bucket; found; found = found->next) {
+	lockdep_assert_held(&pool_rwlock);
+
+	list_for_each(pos, bucket) {
+		found = list_entry(pos, struct stack_record, list);
 		if (found->hash == hash &&
 		    found->size == size &&
 		    !stackdepot_memcmp(entries, found->entries, size))
@@ -355,17 +471,24 @@ static inline struct stack_record *find_stack(struct stack_record *bucket,
 	return NULL;
 }
 
-depot_stack_handle_t __stack_depot_save(unsigned long *entries,
-					unsigned int nr_entries,
-					gfp_t alloc_flags, bool can_alloc)
+depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
+					    unsigned int nr_entries,
+					    gfp_t alloc_flags,
+					    depot_flags_t depot_flags)
 {
-	struct stack_record *found = NULL, **bucket;
-	union handle_parts retval = { .handle = 0 };
+	struct list_head *bucket;
+	struct stack_record *found = NULL;
+	depot_stack_handle_t handle = 0;
 	struct page *page = NULL;
 	void *prealloc = NULL;
+	bool can_alloc = depot_flags & STACK_DEPOT_FLAG_CAN_ALLOC;
+	bool need_alloc = false;
 	unsigned long flags;
 	u32 hash;
 
+	if (WARN_ON(depot_flags & ~STACK_DEPOT_FLAGS_MASK))
+		return 0;
+
 	/*
 	 * If this stack trace is from an interrupt, including anything before
 	 * interrupt entry usually leads to unbounded stack depot growth.
@@ -377,28 +500,36 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries,
 	nr_entries = filter_irq_stacks(entries, nr_entries);
 
 	if (unlikely(nr_entries == 0) || stack_depot_disabled)
-		goto fast_exit;
+		return 0;
 
 	hash = hash_stack(entries, nr_entries);
 	bucket = &stack_table[hash & stack_hash_mask];
 
-	/*
-	 * Fast path: look the stack trace up without locking.
-	 * The smp_load_acquire() here pairs with smp_store_release() to
-	 * |bucket| below.
-	 */
-	found = find_stack(smp_load_acquire(bucket), entries, nr_entries, hash);
-	if (found)
+	read_lock_irqsave(&pool_rwlock, flags);
+	printk_deferred_enter();
+
+	/* Fast path: look the stack trace up without full locking. */
+	found = find_stack(bucket, entries, nr_entries, hash);
+	if (found) {
+		if (depot_flags & STACK_DEPOT_FLAG_GET)
+			refcount_inc(&found->count);
+		printk_deferred_exit();
+		read_unlock_irqrestore(&pool_rwlock, flags);
 		goto exit;
+	}
+
+	/* Take note if another stack pool needs to be allocated. */
+	if (new_pool_required)
+		need_alloc = true;
+
+	printk_deferred_exit();
+	read_unlock_irqrestore(&pool_rwlock, flags);
 
 	/*
-	 * Check if another stack pool needs to be initialized. If so, allocate
-	 * the memory now - we won't be able to do that under the lock.
-	 *
-	 * The smp_load_acquire() here pairs with smp_store_release() to
-	 * |next_pool_inited| in depot_alloc_stack() and depot_init_pool().
+	 * Allocate memory for a new pool if required now:
+	 * we won't be able to do that under the lock.
 	 */
-	if (unlikely(can_alloc && smp_load_acquire(&next_pool_required))) {
+	if (unlikely(can_alloc && need_alloc)) {
 		/*
 		 * Zero out zone modifiers, as we don't have specific zone
 		 * requirements. Keep the flags related to allocation in atomic
@@ -412,63 +543,56 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries,
 			prealloc = page_address(page);
 	}
 
-	raw_spin_lock_irqsave(&pool_lock, flags);
+	write_lock_irqsave(&pool_rwlock, flags);
+	printk_deferred_enter();
 
-	found = find_stack(*bucket, entries, nr_entries, hash);
+	found = find_stack(bucket, entries, nr_entries, hash);
 	if (!found) {
 		struct stack_record *new =
 			depot_alloc_stack(entries, nr_entries, hash, &prealloc);
 
 		if (new) {
-			new->next = *bucket;
-			/*
-			 * This smp_store_release() pairs with
-			 * smp_load_acquire() from |bucket| above.
-			 */
-			smp_store_release(bucket, new);
+			list_add(&new->list, bucket);
 			found = new;
 		}
-	} else if (prealloc) {
+	} else {
+		if (depot_flags & STACK_DEPOT_FLAG_GET)
+			refcount_inc(&found->count);
 		/*
 		 * Stack depot already contains this stack trace, but let's
-		 * keep the preallocated memory for the future.
+		 * keep the preallocated memory for future.
 		 */
-		depot_init_pool(&prealloc);
+		if (prealloc)
+			depot_keep_new_pool(&prealloc);
 	}
 
-	raw_spin_unlock_irqrestore(&pool_lock, flags);
+	printk_deferred_exit();
+	write_unlock_irqrestore(&pool_rwlock, flags);
 exit:
 	if (prealloc) {
 		/* Stack depot didn't use this memory, free it. */
 		free_pages((unsigned long)prealloc, DEPOT_POOL_ORDER);
 	}
 	if (found)
-		retval.handle = found->handle.handle;
-fast_exit:
-	return retval.handle;
+		handle = found->handle.handle;
+	return handle;
 }
-EXPORT_SYMBOL_GPL(__stack_depot_save);
+EXPORT_SYMBOL_GPL(stack_depot_save_flags);
 
 depot_stack_handle_t stack_depot_save(unsigned long *entries,
 				      unsigned int nr_entries,
 				      gfp_t alloc_flags)
 {
-	return __stack_depot_save(entries, nr_entries, alloc_flags, true);
+	return stack_depot_save_flags(entries, nr_entries, alloc_flags,
+				      STACK_DEPOT_FLAG_CAN_ALLOC);
 }
 EXPORT_SYMBOL_GPL(stack_depot_save);
 
 unsigned int stack_depot_fetch(depot_stack_handle_t handle,
 			       unsigned long **entries)
 {
-	union handle_parts parts = { .handle = handle };
-	/*
-	 * READ_ONCE pairs with potential concurrent write in
-	 * depot_alloc_stack.
-	 */
-	int pool_index_cached = READ_ONCE(pool_index);
-	void *pool;
-	size_t offset = parts.offset << DEPOT_STACK_ALIGN;
 	struct stack_record *stack;
+	unsigned long flags;
 
 	*entries = NULL;
 	/*
@@ -477,24 +601,51 @@ unsigned int stack_depot_fetch(depot_stack_handle_t handle,
 	 */
 	kmsan_unpoison_memory(entries, sizeof(*entries));
 
-	if (!handle)
+	if (!handle || stack_depot_disabled)
 		return 0;
 
-	if (parts.pool_index > pool_index_cached) {
-		WARN(1, "pool index %d out of bounds (%d) for stack id %08x\n",
-			parts.pool_index, pool_index_cached, handle);
-		return 0;
-	}
-	pool = stack_pools[parts.pool_index];
-	if (!pool)
-		return 0;
-	stack = pool + offset;
+	read_lock_irqsave(&pool_rwlock, flags);
+	printk_deferred_enter();
+
+	stack = depot_fetch_stack(handle);
+
+	printk_deferred_exit();
+	read_unlock_irqrestore(&pool_rwlock, flags);
 
 	*entries = stack->entries;
 	return stack->size;
 }
 EXPORT_SYMBOL_GPL(stack_depot_fetch);
 
+void stack_depot_put(depot_stack_handle_t handle)
+{
+	struct stack_record *stack;
+	unsigned long flags;
+
+	if (!handle || stack_depot_disabled)
+		return;
+
+	write_lock_irqsave(&pool_rwlock, flags);
+	printk_deferred_enter();
+
+	stack = depot_fetch_stack(handle);
+	if (WARN_ON(!stack))
+		goto out;
+
+	if (refcount_dec_and_test(&stack->count)) {
+		/* Unlink stack from the hash table. */
+		list_del(&stack->list);
+
+		/* Free stack. */
+		depot_free_stack(stack);
+	}
+
+out:
+	printk_deferred_exit();
+	write_unlock_irqrestore(&pool_rwlock, flags);
+}
+EXPORT_SYMBOL_GPL(stack_depot_put);
+
 void stack_depot_print(depot_stack_handle_t stack)
 {
 	unsigned long *entries;
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 7916503e6a6a..569e6d2dc55c 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -5144,22 +5144,6 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 0x1 } },
 	},
-	{
-		"ALU_MOVSX | BPF_W",
-		.u.insns_int = {
-			BPF_LD_IMM64(R2, 0x00000000deadbeefLL),
-			BPF_LD_IMM64(R3, 0xdeadbeefdeadbeefLL),
-			BPF_MOVSX32_REG(R1, R3, 32),
-			BPF_JMP_REG(BPF_JEQ, R2, R1, 2),
-			BPF_MOV32_IMM(R0, 2),
-			BPF_EXIT_INSN(),
-			BPF_MOV32_IMM(R0, 1),
-			BPF_EXIT_INSN(),
-		},
-		INTERNAL,
-		{ },
-		{ { 0, 0x1 } },
-	},
 	/* MOVSX64 REG */
 	{
 		"ALU64_MOVSX | BPF_B",
@@ -6293,7 +6277,7 @@ static struct bpf_test tests[] = {
 	},
 	/* BPF_ALU64 | BPF_MOD | BPF_K off=1 (SMOD64) */
 	{
-		"ALU64_SMOD_X: -7 % 2 = -1",
+		"ALU64_SMOD_K: -7 % 2 = -1",
 		.u.insns_int = {
 			BPF_LD_IMM64(R0, -7),
 			BPF_ALU64_IMM_OFF(BPF_MOD, R0, 2, 1),
@@ -12215,7 +12199,6 @@ static struct bpf_test tests[] = {
 	BPF_JMP32_IMM_ZEXT(JLE),
 	BPF_JMP32_IMM_ZEXT(JSGT),
 	BPF_JMP32_IMM_ZEXT(JSGE),
-	BPF_JMP32_IMM_ZEXT(JSGT),
 	BPF_JMP32_IMM_ZEXT(JSLT),
 	BPF_JMP32_IMM_ZEXT(JSLE),
 #undef BPF_JMP2_IMM_ZEXT
@@ -12251,7 +12234,6 @@ static struct bpf_test tests[] = {
 	BPF_JMP32_REG_ZEXT(JLE),
 	BPF_JMP32_REG_ZEXT(JSGT),
 	BPF_JMP32_REG_ZEXT(JSGE),
-	BPF_JMP32_REG_ZEXT(JSGT),
 	BPF_JMP32_REG_ZEXT(JSLT),
 	BPF_JMP32_REG_ZEXT(JSLE),
 #undef BPF_JMP2_REG_ZEXT
diff --git a/lib/test_firmware.c b/lib/test_firmware.c
index add4699fc6cd..9cfdcd6d21db 100644
--- a/lib/test_firmware.c
+++ b/lib/test_firmware.c
@@ -1132,6 +1132,7 @@ static const char * const fw_upload_err_str[] = {
 	[FW_UPLOAD_ERR_INVALID_SIZE] = "invalid-file-size",
 	[FW_UPLOAD_ERR_RW_ERROR]     = "read-write-error",
 	[FW_UPLOAD_ERR_WEAROUT]	     = "flash-wearout",
+	[FW_UPLOAD_ERR_FW_INVALID]   = "firmware-invalid",
 };
 
 static void upload_err_inject_error(struct test_firmware_upload *tst,
diff --git a/lib/test_ida.c b/lib/test_ida.c
index b06880625961..072a49897e71 100644
--- a/lib/test_ida.c
+++ b/lib/test_ida.c
@@ -13,7 +13,7 @@ static unsigned int tests_run;
 static unsigned int tests_passed;
 
 #ifdef __KERNEL__
-void ida_dump(struct ida *ida) { }
+static void ida_dump(struct ida *ida) { }
 #endif
 #define IDA_BUG_ON(ida, x) do {						\
 	tests_run++;							\
@@ -150,6 +150,45 @@ static void ida_check_conv(struct ida *ida)
 	IDA_BUG_ON(ida, !ida_is_empty(ida));
 }
 
+/*
+ * Check various situations where we attempt to free an ID we don't own.
+ */
+static void ida_check_bad_free(struct ida *ida)
+{
+	unsigned long i;
+
+	printk("vvv Ignore \"not allocated\" warnings\n");
+	/* IDA is empty; all of these will fail */
+	ida_free(ida, 0);
+	for (i = 0; i < 31; i++)
+		ida_free(ida, 1 << i);
+
+	/* IDA contains a single value entry */
+	IDA_BUG_ON(ida, ida_alloc_min(ida, 3, GFP_KERNEL) != 3);
+	ida_free(ida, 0);
+	for (i = 0; i < 31; i++)
+		ida_free(ida, 1 << i);
+
+	/* IDA contains a single bitmap */
+	IDA_BUG_ON(ida, ida_alloc_min(ida, 1023, GFP_KERNEL) != 1023);
+	ida_free(ida, 0);
+	for (i = 0; i < 31; i++)
+		ida_free(ida, 1 << i);
+
+	/* IDA contains a tree */
+	IDA_BUG_ON(ida, ida_alloc_min(ida, (1 << 20) - 1, GFP_KERNEL) != (1 << 20) - 1);
+	ida_free(ida, 0);
+	for (i = 0; i < 31; i++)
+		ida_free(ida, 1 << i);
+	printk("^^^ \"not allocated\" warnings over\n");
+
+	ida_free(ida, 3);
+	ida_free(ida, 1023);
+	ida_free(ida, (1 << 20) - 1);
+
+	IDA_BUG_ON(ida, !ida_is_empty(ida));
+}
+
 static DEFINE_IDA(ida);
 
 static int ida_checks(void)
@@ -162,6 +201,7 @@ static int ida_checks(void)
 	ida_check_leaf(&ida, 1024 * 64);
 	ida_check_max(&ida);
 	ida_check_conv(&ida);
+	ida_check_bad_free(&ida);
 
 	printk("IDA: %u of %u tests passed\n", tests_passed, tests_run);
 	return (tests_run != tests_passed) ? 0 : -EINVAL;
diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c
index 464eeb90d5ad..29185ac5c727 100644
--- a/lib/test_maple_tree.c
+++ b/lib/test_maple_tree.c
@@ -43,6 +43,7 @@ atomic_t maple_tree_tests_passed;
 /* #define BENCH_NODE_STORE */
 /* #define BENCH_AWALK */
 /* #define BENCH_WALK */
+/* #define BENCH_LOAD */
 /* #define BENCH_MT_FOR_EACH */
 /* #define BENCH_FORK */
 /* #define BENCH_MAS_FOR_EACH */
@@ -54,6 +55,11 @@ atomic_t maple_tree_tests_passed;
 #else
 #define cond_resched()			do {} while (0)
 #endif
+
+#define mas_is_none(x)		((x)->status == ma_none)
+#define mas_is_overflow(x)	((x)->status == ma_overflow)
+#define mas_is_underflow(x)	((x)->status == ma_underflow)
+
 static int __init mtree_insert_index(struct maple_tree *mt,
 				     unsigned long index, gfp_t gfp)
 {
@@ -582,7 +588,7 @@ static noinline void __init check_find(struct maple_tree *mt)
 	MT_BUG_ON(mt, last != mas.last);
 
 
-	mas.node = MAS_NONE;
+	mas.status = ma_none;
 	mas.index = ULONG_MAX;
 	mas.last = ULONG_MAX;
 	entry2 = mas_prev(&mas, 0);
@@ -1749,6 +1755,19 @@ static noinline void __init bench_walk(struct maple_tree *mt)
 }
 #endif
 
+#if defined(BENCH_LOAD)
+static noinline void __init bench_load(struct maple_tree *mt)
+{
+	int i, max = 2500, count = 550000000;
+
+	for (i = 0; i < max; i += 10)
+		mtree_store_range(mt, i, i + 5, xa_mk_value(i), GFP_KERNEL);
+
+	for (i = 0; i < count; i++)
+		mtree_load(mt, 1470);
+}
+#endif
+
 #if defined(BENCH_MT_FOR_EACH)
 static noinline void __init bench_mt_for_each(struct maple_tree *mt)
 {
@@ -1834,47 +1853,48 @@ static noinline void __init bench_mas_prev(struct maple_tree *mt)
 }
 #endif
 /* check_forking - simulate the kernel forking sequence with the tree. */
-static noinline void __init check_forking(struct maple_tree *mt)
+static noinline void __init check_forking(void)
 {
-
-	struct maple_tree newmt;
-	int i, nr_entries = 134;
+	struct maple_tree mt, newmt;
+	int i, nr_entries = 134, ret;
 	void *val;
-	MA_STATE(mas, mt, 0, 0);
-	MA_STATE(newmas, mt, 0, 0);
-	struct rw_semaphore newmt_lock;
+	MA_STATE(mas, &mt, 0, 0);
+	MA_STATE(newmas, &newmt, 0, 0);
+	struct rw_semaphore mt_lock, newmt_lock;
 
+	init_rwsem(&mt_lock);
 	init_rwsem(&newmt_lock);
 
-	for (i = 0; i <= nr_entries; i++)
-		mtree_store_range(mt, i*10, i*10 + 5,
-				  xa_mk_value(i), GFP_KERNEL);
+	mt_init_flags(&mt, MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN);
+	mt_set_external_lock(&mt, &mt_lock);
 
-	mt_set_non_kernel(99999);
 	mt_init_flags(&newmt, MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN);
 	mt_set_external_lock(&newmt, &newmt_lock);
-	newmas.tree = &newmt;
-	mas_reset(&newmas);
-	mas_reset(&mas);
-	down_write(&newmt_lock);
-	mas.index = 0;
-	mas.last = 0;
-	if (mas_expected_entries(&newmas, nr_entries)) {
+
+	down_write(&mt_lock);
+	for (i = 0; i <= nr_entries; i++) {
+		mas_set_range(&mas, i*10, i*10 + 5);
+		mas_store_gfp(&mas, xa_mk_value(i), GFP_KERNEL);
+	}
+
+	down_write_nested(&newmt_lock, SINGLE_DEPTH_NESTING);
+	ret = __mt_dup(&mt, &newmt, GFP_KERNEL);
+	if (ret) {
 		pr_err("OOM!");
 		BUG_ON(1);
 	}
-	rcu_read_lock();
-	mas_for_each(&mas, val, ULONG_MAX) {
-		newmas.index = mas.index;
-		newmas.last = mas.last;
+
+	mas_set(&newmas, 0);
+	mas_for_each(&newmas, val, ULONG_MAX)
 		mas_store(&newmas, val);
-	}
-	rcu_read_unlock();
+
 	mas_destroy(&newmas);
+	mas_destroy(&mas);
 	mt_validate(&newmt);
-	mt_set_non_kernel(0);
 	__mt_destroy(&newmt);
+	__mt_destroy(&mt);
 	up_write(&newmt_lock);
+	up_write(&mt_lock);
 }
 
 static noinline void __init check_iteration(struct maple_tree *mt)
@@ -1977,49 +1997,51 @@ static noinline void __init check_mas_store_gfp(struct maple_tree *mt)
 }
 
 #if defined(BENCH_FORK)
-static noinline void __init bench_forking(struct maple_tree *mt)
+static noinline void __init bench_forking(void)
 {
-
-	struct maple_tree newmt;
-	int i, nr_entries = 134, nr_fork = 80000;
+	struct maple_tree mt, newmt;
+	int i, nr_entries = 134, nr_fork = 80000, ret;
 	void *val;
-	MA_STATE(mas, mt, 0, 0);
-	MA_STATE(newmas, mt, 0, 0);
-	struct rw_semaphore newmt_lock;
+	MA_STATE(mas, &mt, 0, 0);
+	MA_STATE(newmas, &newmt, 0, 0);
+	struct rw_semaphore mt_lock, newmt_lock;
 
+	init_rwsem(&mt_lock);
 	init_rwsem(&newmt_lock);
-	mt_set_external_lock(&newmt, &newmt_lock);
 
-	for (i = 0; i <= nr_entries; i++)
-		mtree_store_range(mt, i*10, i*10 + 5,
-				  xa_mk_value(i), GFP_KERNEL);
+	mt_init_flags(&mt, MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN);
+	mt_set_external_lock(&mt, &mt_lock);
+
+	down_write(&mt_lock);
+	for (i = 0; i <= nr_entries; i++) {
+		mas_set_range(&mas, i*10, i*10 + 5);
+		mas_store_gfp(&mas, xa_mk_value(i), GFP_KERNEL);
+	}
 
 	for (i = 0; i < nr_fork; i++) {
-		mt_set_non_kernel(99999);
-		mt_init_flags(&newmt, MT_FLAGS_ALLOC_RANGE);
-		newmas.tree = &newmt;
-		mas_reset(&newmas);
-		mas_reset(&mas);
-		mas.index = 0;
-		mas.last = 0;
-		rcu_read_lock();
-		down_write(&newmt_lock);
-		if (mas_expected_entries(&newmas, nr_entries)) {
-			printk("OOM!");
+		mt_init_flags(&newmt,
+			      MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN);
+		mt_set_external_lock(&newmt, &newmt_lock);
+
+		down_write_nested(&newmt_lock, SINGLE_DEPTH_NESTING);
+		ret = __mt_dup(&mt, &newmt, GFP_KERNEL);
+		if (ret) {
+			pr_err("OOM!");
 			BUG_ON(1);
 		}
-		mas_for_each(&mas, val, ULONG_MAX) {
-			newmas.index = mas.index;
-			newmas.last = mas.last;
+
+		mas_set(&newmas, 0);
+		mas_for_each(&newmas, val, ULONG_MAX)
 			mas_store(&newmas, val);
-		}
+
 		mas_destroy(&newmas);
-		rcu_read_unlock();
 		mt_validate(&newmt);
-		mt_set_non_kernel(0);
 		__mt_destroy(&newmt);
 		up_write(&newmt_lock);
 	}
+	mas_destroy(&mas);
+	__mt_destroy(&mt);
+	up_write(&mt_lock);
 }
 #endif
 
@@ -2175,7 +2197,7 @@ static noinline void __init next_prev_test(struct maple_tree *mt)
 	MT_BUG_ON(mt, val != NULL);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 5);
-	MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW);
+	MT_BUG_ON(mt, !mas_is_underflow(&mas));
 
 	mas.index = 0;
 	mas.last = 5;
@@ -3039,10 +3061,6 @@ static noinline void __init check_empty_area_fill(struct maple_tree *mt)
  *		DNE	active		active		range of NULL
  */
 
-#define mas_active(x)		(((x).node != MAS_ROOT) && \
-				 ((x).node != MAS_START) && \
-				 ((x).node != MAS_PAUSE) && \
-				 ((x).node != MAS_NONE))
 static noinline void __init check_state_handling(struct maple_tree *mt)
 {
 	MA_STATE(mas, mt, 0, 0);
@@ -3057,7 +3075,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	/* prev: Start -> underflow*/
 	entry = mas_prev(&mas, 0);
 	MT_BUG_ON(mt, entry != NULL);
-	MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW);
+	MT_BUG_ON(mt, mas.status != ma_underflow);
 
 	/* prev: Start -> root */
 	mas_set(&mas, 10);
@@ -3065,7 +3083,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	/* prev: pause -> root */
 	mas_set(&mas, 10);
@@ -3074,7 +3092,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	/* next: start -> none */
 	mas_set(&mas, 0);
@@ -3082,7 +3100,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, mas.index != 1);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
 	MT_BUG_ON(mt, entry != NULL);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* next: start -> none*/
 	mas_set(&mas, 10);
@@ -3090,7 +3108,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, mas.index != 1);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
 	MT_BUG_ON(mt, entry != NULL);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* find: start -> root */
 	mas_set(&mas, 0);
@@ -3098,21 +3116,21 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	/* find: root -> none */
 	entry = mas_find(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 1);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* find: none -> none */
 	entry = mas_find(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 1);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* find: start -> none */
 	mas_set(&mas, 10);
@@ -3120,14 +3138,14 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 1);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* find_rev: none -> root */
 	entry = mas_find_rev(&mas, 0);
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	/* find_rev: start -> root */
 	mas_set(&mas, 0);
@@ -3135,21 +3153,21 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	/* find_rev: root -> none */
 	entry = mas_find_rev(&mas, 0);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* find_rev: none -> none */
 	entry = mas_find_rev(&mas, 0);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* find_rev: start -> root */
 	mas_set(&mas, 10);
@@ -3157,7 +3175,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	/* walk: start -> none */
 	mas_set(&mas, 10);
@@ -3165,7 +3183,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 1);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* walk: pause -> none*/
 	mas_set(&mas, 10);
@@ -3174,7 +3192,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 1);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* walk: none -> none */
 	mas.index = mas.last = 10;
@@ -3182,14 +3200,14 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 1);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* walk: none -> none */
 	entry = mas_walk(&mas);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 1);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* walk: start -> root */
 	mas_set(&mas, 0);
@@ -3197,7 +3215,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	/* walk: pause -> root */
 	mas_set(&mas, 0);
@@ -3206,22 +3224,22 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	/* walk: none -> root */
-	mas.node = MAS_NONE;
+	mas.status = ma_none;
 	entry = mas_walk(&mas);
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	/* walk: root -> root */
 	entry = mas_walk(&mas);
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	/* walk: root -> none */
 	mas_set(&mas, 10);
@@ -3229,7 +3247,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 1);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* walk: none -> root */
 	mas.index = mas.last = 0;
@@ -3237,7 +3255,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	mas_unlock(&mas);
 
@@ -3255,7 +3273,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* next: pause ->active */
 	mas_set(&mas, 0);
@@ -3264,126 +3282,132 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* next: none ->active */
 	mas.index = mas.last = 0;
 	mas.offset = 0;
-	mas.node = MAS_NONE;
+	mas.status = ma_none;
 	entry = mas_next(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
-	/* next:active ->active */
-	entry = mas_next(&mas, ULONG_MAX);
+	/* next:active ->active (spanning limit) */
+	entry = mas_next(&mas, 0x2100);
 	MT_BUG_ON(mt, entry != ptr2);
 	MT_BUG_ON(mt, mas.index != 0x2000);
 	MT_BUG_ON(mt, mas.last != 0x2500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
-	/* next:active -> active beyond data */
+	/* next:active -> overflow (limit reached) beyond data */
 	entry = mas_next(&mas, 0x2999);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x2501);
 	MT_BUG_ON(mt, mas.last != 0x2fff);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_overflow(&mas));
 
-	/* Continue after last range ends after max */
+	/* next:overflow -> active (limit changed) */
 	entry = mas_next(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != ptr3);
 	MT_BUG_ON(mt, mas.index != 0x3000);
 	MT_BUG_ON(mt, mas.last != 0x3500);
-	MT_BUG_ON(mt, !mas_active(mas));
-
-	/* next:active -> active continued */
-	entry = mas_next(&mas, ULONG_MAX);
-	MT_BUG_ON(mt, entry != NULL);
-	MT_BUG_ON(mt, mas.index != 0x3501);
-	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
-	/* next:active -> overflow  */
+	/* next:active ->  overflow (limit reached) */
 	entry = mas_next(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x3501);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, mas.node != MAS_OVERFLOW);
+	MT_BUG_ON(mt, !mas_is_overflow(&mas));
 
 	/* next:overflow -> overflow  */
 	entry = mas_next(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x3501);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, mas.node != MAS_OVERFLOW);
+	MT_BUG_ON(mt, !mas_is_overflow(&mas));
 
 	/* prev:overflow -> active  */
 	entry = mas_prev(&mas, 0);
 	MT_BUG_ON(mt, entry != ptr3);
 	MT_BUG_ON(mt, mas.index != 0x3000);
 	MT_BUG_ON(mt, mas.last != 0x3500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* next: none -> active, skip value at location */
 	mas_set(&mas, 0);
 	entry = mas_next(&mas, ULONG_MAX);
-	mas.node = MAS_NONE;
+	mas.status = ma_none;
 	mas.offset = 0;
 	entry = mas_next(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != ptr2);
 	MT_BUG_ON(mt, mas.index != 0x2000);
 	MT_BUG_ON(mt, mas.last != 0x2500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* prev:active ->active */
 	entry = mas_prev(&mas, 0);
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
-	/* prev:active -> active spanning end range */
+	/* prev:active -> underflow (span limit) */
+	mas_next(&mas, ULONG_MAX);
+	entry = mas_prev(&mas, 0x1200);
+	MT_BUG_ON(mt, entry != ptr);
+	MT_BUG_ON(mt, mas.index != 0x1000);
+	MT_BUG_ON(mt, mas.last != 0x1500);
+	MT_BUG_ON(mt, !mas_is_active(&mas)); /* spanning limit */
+	entry = mas_prev(&mas, 0x1200); /* underflow */
+	MT_BUG_ON(mt, entry != NULL);
+	MT_BUG_ON(mt, mas.index != 0x1000);
+	MT_BUG_ON(mt, mas.last != 0x1500);
+	MT_BUG_ON(mt, !mas_is_underflow(&mas));
+
+	/* prev:underflow -> underflow (lower limit) spanning end range */
 	entry = mas_prev(&mas, 0x0100);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0x0FFF);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_underflow(&mas));
 
-	/* prev:active -> underflow */
+	/* prev:underflow -> underflow */
 	entry = mas_prev(&mas, 0);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0x0FFF);
-	MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW);
+	MT_BUG_ON(mt, !mas_is_underflow(&mas));
 
 	/* prev:underflow -> underflow */
 	entry = mas_prev(&mas, 0);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0x0FFF);
-	MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW);
+	MT_BUG_ON(mt, !mas_is_underflow(&mas));
 
 	/* next:underflow -> active */
 	entry = mas_next(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* prev:first value -> underflow */
 	entry = mas_prev(&mas, 0x1000);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW);
+	MT_BUG_ON(mt, !mas_is_underflow(&mas));
 
 	/* find:underflow -> first value */
 	entry = mas_find(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* prev: pause ->active */
 	mas_set(&mas, 0x3600);
@@ -3394,21 +3418,21 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr2);
 	MT_BUG_ON(mt, mas.index != 0x2000);
 	MT_BUG_ON(mt, mas.last != 0x2500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
-	/* prev:active -> active spanning min */
+	/* prev:active -> underflow spanning min */
 	entry = mas_prev(&mas, 0x1600);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x1501);
 	MT_BUG_ON(mt, mas.last != 0x1FFF);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_underflow(&mas));
 
 	/* prev: active ->active, continue */
 	entry = mas_prev(&mas, 0);
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* find: start ->active */
 	mas_set(&mas, 0);
@@ -3416,7 +3440,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* find: pause ->active */
 	mas_set(&mas, 0);
@@ -3425,7 +3449,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* find: start ->active on value */;
 	mas_set(&mas, 1200);
@@ -3433,14 +3457,14 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* find:active ->active */
 	entry = mas_find(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != ptr2);
 	MT_BUG_ON(mt, mas.index != 0x2000);
 	MT_BUG_ON(mt, mas.last != 0x2500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 
 	/* find:active -> active (NULL)*/
@@ -3448,35 +3472,35 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x2501);
 	MT_BUG_ON(mt, mas.last != 0x2FFF);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MAS_BUG_ON(&mas, !mas_is_active(&mas));
 
 	/* find: overflow ->active */
 	entry = mas_find(&mas, 0x5000);
 	MT_BUG_ON(mt, entry != ptr3);
 	MT_BUG_ON(mt, mas.index != 0x3000);
 	MT_BUG_ON(mt, mas.last != 0x3500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* find:active -> active (NULL) end*/
 	entry = mas_find(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x3501);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MAS_BUG_ON(&mas, !mas_is_active(&mas));
 
 	/* find_rev: active (END) ->active */
 	entry = mas_find_rev(&mas, 0);
 	MT_BUG_ON(mt, entry != ptr3);
 	MT_BUG_ON(mt, mas.index != 0x3000);
 	MT_BUG_ON(mt, mas.last != 0x3500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* find_rev:active ->active */
 	entry = mas_find_rev(&mas, 0);
 	MT_BUG_ON(mt, entry != ptr2);
 	MT_BUG_ON(mt, mas.index != 0x2000);
 	MT_BUG_ON(mt, mas.last != 0x2500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* find_rev: pause ->active */
 	mas_pause(&mas);
@@ -3484,14 +3508,14 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
-	/* find_rev:active -> active */
+	/* find_rev:active -> underflow */
 	entry = mas_find_rev(&mas, 0);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0x0FFF);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_underflow(&mas));
 
 	/* find_rev: start ->active */
 	mas_set(&mas, 0x1200);
@@ -3499,7 +3523,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* mas_walk start ->active */
 	mas_set(&mas, 0x1200);
@@ -3507,7 +3531,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* mas_walk start ->active */
 	mas_set(&mas, 0x1600);
@@ -3515,7 +3539,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x1501);
 	MT_BUG_ON(mt, mas.last != 0x1fff);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* mas_walk pause ->active */
 	mas_set(&mas, 0x1200);
@@ -3524,7 +3548,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* mas_walk pause -> active */
 	mas_set(&mas, 0x1600);
@@ -3533,25 +3557,25 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x1501);
 	MT_BUG_ON(mt, mas.last != 0x1fff);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* mas_walk none -> active */
 	mas_set(&mas, 0x1200);
-	mas.node = MAS_NONE;
+	mas.status = ma_none;
 	entry = mas_walk(&mas);
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* mas_walk none -> active */
 	mas_set(&mas, 0x1600);
-	mas.node = MAS_NONE;
+	mas.status = ma_none;
 	entry = mas_walk(&mas);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x1501);
 	MT_BUG_ON(mt, mas.last != 0x1fff);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* mas_walk active -> active */
 	mas.index = 0x1200;
@@ -3561,7 +3585,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* mas_walk active -> active */
 	mas.index = 0x1600;
@@ -3570,7 +3594,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x1501);
 	MT_BUG_ON(mt, mas.last != 0x1fff);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	mas_unlock(&mas);
 }
@@ -3585,10 +3609,6 @@ static int __init maple_tree_seed(void)
 
 	pr_info("\nTEST STARTING\n\n");
 
-	mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE);
-	check_root_expand(&tree);
-	mtree_destroy(&tree);
-
 #if defined(BENCH_SLOT_STORE)
 #define BENCH
 	mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE);
@@ -3617,13 +3637,18 @@ static int __init maple_tree_seed(void)
 	mtree_destroy(&tree);
 	goto skip;
 #endif
-#if defined(BENCH_FORK)
+#if defined(BENCH_LOAD)
 #define BENCH
 	mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE);
-	bench_forking(&tree);
+	bench_load(&tree);
 	mtree_destroy(&tree);
 	goto skip;
 #endif
+#if defined(BENCH_FORK)
+#define BENCH
+	bench_forking();
+	goto skip;
+#endif
 #if defined(BENCH_MT_FOR_EACH)
 #define BENCH
 	mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE);
@@ -3647,13 +3672,15 @@ static int __init maple_tree_seed(void)
 #endif
 
 	mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE);
-	check_iteration(&tree);
+	check_root_expand(&tree);
 	mtree_destroy(&tree);
 
 	mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE);
-	check_forking(&tree);
+	check_iteration(&tree);
 	mtree_destroy(&tree);
 
+	check_forking();
+
 	mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE);
 	check_mas_store_gfp(&tree);
 	mtree_destroy(&tree);
diff --git a/lib/test_meminit.c b/lib/test_meminit.c
index 0ae35223d773..0dc173849a54 100644
--- a/lib/test_meminit.c
+++ b/lib/test_meminit.c
@@ -93,7 +93,7 @@ static int __init test_pages(int *total_failures)
 	int failures = 0, num_tests = 0;
 	int i;
 
-	for (i = 0; i <= MAX_ORDER; i++)
+	for (i = 0; i < NR_PAGE_ORDERS; i++)
 		num_tests += do_alloc_pages_order(i, &failures);
 
 	REPORT_FAILURES_IN_FN();
diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index c20f6cb4bf55..42b585208249 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -16,6 +16,7 @@
 #include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/rcupdate.h>
+#include <linux/rcupdate_wait.h>
 #include <linux/rhashtable.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
diff --git a/lib/test_sysctl.c b/lib/test_sysctl.c
index 8036aa91a1cb..9321d850931f 100644
--- a/lib/test_sysctl.c
+++ b/lib/test_sysctl.c
@@ -35,6 +35,8 @@ static struct {
 	struct ctl_table_header *test_h_setup_node;
 	struct ctl_table_header *test_h_mnt;
 	struct ctl_table_header *test_h_mnterror;
+	struct ctl_table_header *empty_add;
+	struct ctl_table_header *empty;
 } sysctl_test_headers;
 
 struct test_sysctl_data {
@@ -130,7 +132,6 @@ static struct ctl_table test_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_do_large_bitmap,
 	},
-	{ }
 };
 
 static void test_sysctl_calc_match_int_ok(void)
@@ -184,7 +185,6 @@ static struct ctl_table test_table_unregister[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 	},
-	{}
 };
 
 static int test_sysctl_run_unregister_nested(void)
@@ -220,6 +220,25 @@ static int test_sysctl_run_register_mount_point(void)
 	return 0;
 }
 
+static struct ctl_table test_table_empty[] = { };
+
+static int test_sysctl_run_register_empty(void)
+{
+	/* Tets that an empty dir can be created */
+	sysctl_test_headers.empty_add
+		= register_sysctl("debug/test_sysctl/empty_add", test_table_empty);
+	if (!sysctl_test_headers.empty_add)
+		return -ENOMEM;
+
+	/* Test that register on top of an empty dir works */
+	sysctl_test_headers.empty
+		= register_sysctl("debug/test_sysctl/empty_add/empty", test_table_empty);
+	if (!sysctl_test_headers.empty)
+		return -ENOMEM;
+
+	return 0;
+}
+
 static int __init test_sysctl_init(void)
 {
 	int err;
@@ -233,6 +252,10 @@ static int __init test_sysctl_init(void)
 		goto out;
 
 	err = test_sysctl_run_register_mount_point();
+	if (err)
+		goto out;
+
+	err = test_sysctl_run_register_empty();
 
 out:
 	return err;
@@ -248,6 +271,10 @@ static void __exit test_sysctl_exit(void)
 		unregister_sysctl_table(sysctl_test_headers.test_h_mnt);
 	if (sysctl_test_headers.test_h_mnterror)
 		unregister_sysctl_table(sysctl_test_headers.test_h_mnterror);
+	if (sysctl_test_headers.empty)
+		unregister_sysctl_table(sysctl_test_headers.empty);
+	if (sysctl_test_headers.empty_add)
+		unregister_sysctl_table(sysctl_test_headers.empty_add);
 }
 
 module_exit(test_sysctl_exit);
diff --git a/lib/trace_readwrite.c b/lib/trace_readwrite.c
index 62b4e8b3c733..a94cd56a1e4c 100644
--- a/lib/trace_readwrite.c
+++ b/lib/trace_readwrite.c
@@ -7,7 +7,7 @@
 
 #include <linux/ftrace.h>
 #include <linux/module.h>
-#include <asm-generic/io.h>
+#include <linux/io.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/rwmmio.h>
diff --git a/lib/ubsan.c b/lib/ubsan.c
index 3f90810f9f42..df4f8d1354bb 100644
--- a/lib/ubsan.c
+++ b/lib/ubsan.c
@@ -204,8 +204,8 @@ static void ubsan_prologue(struct source_location *loc, const char *reason)
 {
 	current->in_ubsan++;
 
-	pr_err("========================================"
-		"========================================\n");
+	pr_warn(CUT_HERE);
+
 	pr_err("UBSAN: %s in %s:%d:%d\n", reason, loc->file_name,
 		loc->line & LINE_MASK, loc->column & COLUMN_MASK);
 
@@ -215,8 +215,7 @@ static void ubsan_prologue(struct source_location *loc, const char *reason)
 static void ubsan_epilogue(void)
 {
 	dump_stack();
-	pr_err("========================================"
-		"========================================\n");
+	pr_warn("---[ end trace ]---\n");
 
 	current->in_ubsan--;
 
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 3e3733a7084f..552738f14275 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -2111,15 +2111,20 @@ char *fwnode_full_name_string(struct fwnode_handle *fwnode, char *buf,
 
 	/* Loop starting from the root node to the current node. */
 	for (depth = fwnode_count_parents(fwnode); depth >= 0; depth--) {
-		struct fwnode_handle *__fwnode =
-			fwnode_get_nth_parent(fwnode, depth);
+		/*
+		 * Only get a reference for other nodes (i.e. parent nodes).
+		 * fwnode refcount may be 0 here.
+		 */
+		struct fwnode_handle *__fwnode = depth ?
+			fwnode_get_nth_parent(fwnode, depth) : fwnode;
 
 		buf = string(buf, end, fwnode_get_name_prefix(__fwnode),
 			     default_str_spec);
 		buf = string(buf, end, fwnode_get_name(__fwnode),
 			     default_str_spec);
 
-		fwnode_handle_put(__fwnode);
+		if (depth)
+			fwnode_handle_put(__fwnode);
 	}
 
 	return buf;
diff --git a/lib/zstd/common/fse_decompress.c b/lib/zstd/common/fse_decompress.c
index a0d06095be83..8dcb8ca39767 100644
--- a/lib/zstd/common/fse_decompress.c
+++ b/lib/zstd/common/fse_decompress.c
@@ -312,7 +312,7 @@ size_t FSE_decompress_wksp(void* dst, size_t dstCapacity, const void* cSrc, size
 
 typedef struct {
     short ncount[FSE_MAX_SYMBOL_VALUE + 1];
-    FSE_DTable dtable[1]; /* Dynamically sized */
+    FSE_DTable dtable[]; /* Dynamically sized */
 } FSE_DecompressWksp;
 
 
diff --git a/mm/Kconfig b/mm/Kconfig
index 89971a894b60..1902cfe4cc4f 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -61,6 +61,20 @@ config ZSWAP_EXCLUSIVE_LOADS_DEFAULT_ON
 	  The cost is that if the page was never dirtied and needs to be
 	  swapped out again, it will be re-compressed.
 
+config ZSWAP_SHRINKER_DEFAULT_ON
+	bool "Shrink the zswap pool on memory pressure"
+	depends on ZSWAP
+	default n
+	help
+	  If selected, the zswap shrinker will be enabled, and the pages
+	  stored in the zswap pool will become available for reclaim (i.e
+	  written back to the backing swap device) on memory pressure.
+
+	  This means that zswap writeback could happen even if the pool is
+	  not yet full, or the cgroup zswap limit has not been reached,
+	  reducing the chance that cold pages will reside in the zswap pool
+	  and consume memory indefinitely.
+
 choice
 	prompt "Default compressor"
 	depends on ZSWAP
@@ -226,52 +240,17 @@ config ZSMALLOC_CHAIN_SIZE
 
 	  For more information, see zsmalloc documentation.
 
-menu "SLAB allocator options"
-
-choice
-	prompt "Choose SLAB allocator"
-	default SLUB
-	help
-	   This option allows to select a slab allocator.
-
-config SLAB_DEPRECATED
-	bool "SLAB (DEPRECATED)"
-	depends on !PREEMPT_RT
-	help
-	  Deprecated and scheduled for removal in a few cycles. Replaced by
-	  SLUB.
-
-	  If you cannot migrate to SLUB, please contact linux-mm@kvack.org
-	  and the people listed in the SLAB ALLOCATOR section of MAINTAINERS
-	  file, explaining why.
-
-	  The regular slab allocator that is established and known to work
-	  well in all environments. It organizes cache hot objects in
-	  per cpu and per node queues.
+menu "Slab allocator options"
 
 config SLUB
-	bool "SLUB (Unqueued Allocator)"
-	help
-	   SLUB is a slab allocator that minimizes cache line usage
-	   instead of managing queues of cached objects (SLAB approach).
-	   Per cpu caching is realized using slabs of objects instead
-	   of queues of objects. SLUB can use memory efficiently
-	   and has enhanced diagnostics. SLUB is the default choice for
-	   a slab allocator.
-
-endchoice
-
-config SLAB
-	bool
-	default y
-	depends on SLAB_DEPRECATED
+	def_bool y
 
 config SLUB_TINY
-	bool "Configure SLUB for minimal memory footprint"
-	depends on SLUB && EXPERT
+	bool "Configure for minimal memory footprint"
+	depends on EXPERT
 	select SLAB_MERGE_DEFAULT
 	help
-	   Configures the SLUB allocator in a way to achieve minimal memory
+	   Configures the slab allocator in a way to achieve minimal memory
 	   footprint, sacrificing scalability, debugging and other features.
 	   This is intended only for the smallest system that had used the
 	   SLOB allocator and is not recommended for systems with more than
@@ -282,7 +261,6 @@ config SLUB_TINY
 config SLAB_MERGE_DEFAULT
 	bool "Allow slab caches to be merged"
 	default y
-	depends on SLAB || SLUB
 	help
 	  For reduced kernel memory fragmentation, slab caches can be
 	  merged when they share the same size and other characteristics.
@@ -296,7 +274,7 @@ config SLAB_MERGE_DEFAULT
 
 config SLAB_FREELIST_RANDOM
 	bool "Randomize slab freelist"
-	depends on SLAB || (SLUB && !SLUB_TINY)
+	depends on !SLUB_TINY
 	help
 	  Randomizes the freelist order used on creating new pages. This
 	  security feature reduces the predictability of the kernel slab
@@ -304,21 +282,19 @@ config SLAB_FREELIST_RANDOM
 
 config SLAB_FREELIST_HARDENED
 	bool "Harden slab freelist metadata"
-	depends on SLAB || (SLUB && !SLUB_TINY)
+	depends on !SLUB_TINY
 	help
 	  Many kernel heap attacks try to target slab cache metadata and
 	  other infrastructure. This options makes minor performance
 	  sacrifices to harden the kernel slab allocator against common
-	  freelist exploit methods. Some slab implementations have more
-	  sanity-checking than others. This option is most effective with
-	  CONFIG_SLUB.
+	  freelist exploit methods.
 
 config SLUB_STATS
 	default n
-	bool "Enable SLUB performance statistics"
-	depends on SLUB && SYSFS && !SLUB_TINY
+	bool "Enable performance statistics"
+	depends on SYSFS && !SLUB_TINY
 	help
-	  SLUB statistics are useful to debug SLUBs allocation behavior in
+	  The statistics are useful to debug slab allocation behavior in
 	  order find ways to optimize the allocator. This should never be
 	  enabled for production use since keeping statistics slows down
 	  the allocator by a few percentage points. The slabinfo command
@@ -328,8 +304,8 @@ config SLUB_STATS
 
 config SLUB_CPU_PARTIAL
 	default y
-	depends on SLUB && SMP && !SLUB_TINY
-	bool "SLUB per cpu partial cache"
+	depends on SMP && !SLUB_TINY
+	bool "Enable per cpu partial caches"
 	help
 	  Per cpu partial caches accelerate objects allocation and freeing
 	  that is local to a processor at the price of more indeterminism
@@ -339,7 +315,7 @@ config SLUB_CPU_PARTIAL
 
 config RANDOM_KMALLOC_CACHES
 	default n
-	depends on SLUB && !SLUB_TINY
+	depends on !SLUB_TINY
 	bool "Randomize slab caches for normal kmalloc"
 	help
 	  A hardening feature that creates multiple copies of slab caches for
@@ -354,7 +330,7 @@ config RANDOM_KMALLOC_CACHES
 	  limited degree of memory and CPU overhead that relates to hardware and
 	  system workload.
 
-endmenu # SLAB allocator options
+endmenu # Slab allocator options
 
 config SHUFFLE_PAGE_ALLOCATOR
 	bool "Page allocator randomization"
@@ -367,7 +343,7 @@ config SHUFFLE_PAGE_ALLOCATOR
 	  the presence of a memory-side-cache. There are also incidental
 	  security benefits as it reduces the predictability of page
 	  allocations to compliment SLAB_FREELIST_RANDOM, but the
-	  default granularity of shuffling on the MAX_ORDER i.e, 10th
+	  default granularity of shuffling on the MAX_PAGE_ORDER i.e, 10th
 	  order of pages is selected based on cache utilization benefits
 	  on x86.
 
@@ -699,8 +675,8 @@ config HUGETLB_PAGE_SIZE_VARIABLE
 	  HUGETLB_PAGE_ORDER when there are multiple HugeTLB page sizes available
 	  on a platform.
 
-	  Note that the pageblock_order cannot exceed MAX_ORDER and will be
-	  clamped down to MAX_ORDER.
+	  Note that the pageblock_order cannot exceed MAX_PAGE_ORDER and will be
+	  clamped down to MAX_PAGE_ORDER.
 
 config CONTIG_ALLOC
 	def_bool (MEMORY_ISOLATION && COMPACTION) || CMA
@@ -756,7 +732,7 @@ config DEFAULT_MMAP_MIN_ADDR
 	  from userspace allocation.  Keeping a user from writing to low pages
 	  can help reduce the impact of kernel NULL pointer bugs.
 
-	  For most ia64, ppc64 and x86 users with lots of address space
+	  For most ppc64 and x86 users with lots of address space
 	  a value of 65536 is reasonable and should cause no problems.
 	  On arm and other archs it should not be higher than 32768.
 	  Programs which use vm86 functionality or have some need to map
@@ -859,6 +835,12 @@ choice
 	  madvise(MADV_HUGEPAGE) but it won't risk to increase the
 	  memory footprint of applications without a guaranteed
 	  benefit.
+
+	config TRANSPARENT_HUGEPAGE_NEVER
+		bool "never"
+	help
+	  Disable Transparent Hugepage by default. It can still be
+	  enabled at runtime via sysfs.
 endchoice
 
 config THP_SWAP
@@ -1201,13 +1183,6 @@ config ANON_VMA_NAME
 	  area from being merged with adjacent virtual memory areas due to the
 	  difference in their name.
 
-config USERFAULTFD
-	bool "Enable userfaultfd() system call"
-	depends on MMU
-	help
-	  Enable the userfaultfd() system call that allows to intercept and
-	  handle page faults in userland.
-
 config HAVE_ARCH_USERFAULTFD_WP
 	bool
 	help
@@ -1218,6 +1193,14 @@ config HAVE_ARCH_USERFAULTFD_MINOR
 	help
 	  Arch has userfaultfd minor fault support
 
+menuconfig USERFAULTFD
+	bool "Enable userfaultfd() system call"
+	depends on MMU
+	help
+	  Enable the userfaultfd() system call that allows to intercept and
+	  handle page faults in userland.
+
+if USERFAULTFD
 config PTE_MARKER_UFFD_WP
 	bool "Userfaultfd write protection support for shmem/hugetlbfs"
 	default y
@@ -1227,6 +1210,7 @@ config PTE_MARKER_UFFD_WP
 	  Allows to create marker PTEs for userfaultfd write protection
 	  purposes.  It is required to enable userfaultfd write protection on
 	  file-backed memory types like shmem and hugetlbfs.
+endif # USERFAULTFD
 
 # multi-gen LRU {
 config LRU_GEN
@@ -1252,6 +1236,10 @@ config LRU_GEN_STATS
 	  from evicted generations for debugging purpose.
 
 	  This option has a per-memcg and per-node memory overhead.
+
+config LRU_GEN_WALKS_MMU
+	def_bool y
+	depends on LRU_GEN && ARCH_HAS_HW_PTE_YOUNG
 # }
 
 config ARCH_SUPPORTS_PER_VMA_LOCK
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index 018a5bd2f576..321ab379994f 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -45,18 +45,10 @@ config DEBUG_PAGEALLOC_ENABLE_DEFAULT
 	  Enable debug page memory allocations by default? This value
 	  can be overridden by debug_pagealloc=off|on.
 
-config DEBUG_SLAB
-	bool "Debug slab memory allocations"
-	depends on DEBUG_KERNEL && SLAB
-	help
-	  Say Y here to have the kernel do limited verification on memory
-	  allocation as well as poisoning memory on free to catch use of freed
-	  memory. This can make kmalloc/kfree-intensive workloads much slower.
-
 config SLUB_DEBUG
 	default y
 	bool "Enable SLUB debugging support" if EXPERT
-	depends on SLUB && SYSFS && !SLUB_TINY
+	depends on SYSFS && !SLUB_TINY
 	select STACKDEPOT if STACKTRACE_SUPPORT
 	help
 	  SLUB has extensive debug support features. Disabling these can
@@ -66,7 +58,7 @@ config SLUB_DEBUG
 
 config SLUB_DEBUG_ON
 	bool "SLUB debugging on by default"
-	depends on SLUB && SLUB_DEBUG
+	depends on SLUB_DEBUG
 	select STACKDEPOT_ALWAYS_INIT if STACKTRACE_SUPPORT
 	default n
 	help
@@ -231,8 +223,8 @@ config DEBUG_KMEMLEAK
 	  allocations. See Documentation/dev-tools/kmemleak.rst for more
 	  details.
 
-	  Enabling DEBUG_SLAB or SLUB_DEBUG may increase the chances
-	  of finding leaks due to the slab objects poisoning.
+	  Enabling SLUB_DEBUG may increase the chances of finding leaks
+	  due to the slab objects poisoning.
 
 	  In order to access the kmemleak file, debugfs needs to be
 	  mounted (usually at /sys/kernel/debug).
diff --git a/mm/Makefile b/mm/Makefile
index 33873c8aedb3..e4b5b75aaec9 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -4,7 +4,6 @@
 #
 
 KASAN_SANITIZE_slab_common.o := n
-KASAN_SANITIZE_slab.o := n
 KASAN_SANITIZE_slub.o := n
 KCSAN_SANITIZE_kmemleak.o := n
 
@@ -12,7 +11,6 @@ KCSAN_SANITIZE_kmemleak.o := n
 # the same word but accesses to different bits of that word. Re-enable KCSAN
 # for these when we have more consensus on what to do about them.
 KCSAN_SANITIZE_slab_common.o := n
-KCSAN_SANITIZE_slab.o := n
 KCSAN_SANITIZE_slub.o := n
 KCSAN_SANITIZE_page_alloc.o := n
 # But enable explicit instrumentation for memory barriers.
@@ -22,7 +20,6 @@ KCSAN_INSTRUMENT_BARRIERS := y
 # flaky coverage that is not a function of syscall inputs. E.g. slab is out of
 # free pages, or a task is migrated between nodes.
 KCOV_INSTRUMENT_slab_common.o := n
-KCOV_INSTRUMENT_slab.o := n
 KCOV_INSTRUMENT_slub.o := n
 KCOV_INSTRUMENT_page_alloc.o := n
 KCOV_INSTRUMENT_debug-pagealloc.o := n
@@ -66,6 +63,7 @@ obj-y += page-alloc.o
 obj-y += init-mm.o
 obj-y += memblock.o
 obj-y += $(memory-hotplug-y)
+obj-y += slub.o
 
 ifdef CONFIG_MMU
 	obj-$(CONFIG_ADVISE_SYSCALLS)	+= madvise.o
@@ -82,8 +80,6 @@ obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o
 obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o
 obj-$(CONFIG_KSM) += ksm.o
 obj-$(CONFIG_PAGE_POISONING) += page_poison.o
-obj-$(CONFIG_SLAB) += slab.o
-obj-$(CONFIG_SLUB) += slub.o
 obj-$(CONFIG_KASAN)	+= kasan/
 obj-$(CONFIG_KFENCE) += kfence/
 obj-$(CONFIG_KMSAN)	+= kmsan/
diff --git a/mm/cma.c b/mm/cma.c
index 2b2494fd6b59..7c09c47e530b 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -244,7 +244,7 @@ int __init cma_declare_contiguous_nid(phys_addr_t base,
 {
 	phys_addr_t memblock_end = memblock_end_of_DRAM();
 	phys_addr_t highmem_start;
-	int ret = 0;
+	int ret;
 
 	/*
 	 * We can't use __pa(high_memory) directly, since high_memory
diff --git a/mm/compaction.c b/mm/compaction.c
index 01ba298739dd..27ada42924d5 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -999,7 +999,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			 * a valid page order. Consider only values in the
 			 * valid order range to prevent low_pfn overflow.
 			 */
-			if (freepage_order > 0 && freepage_order <= MAX_ORDER) {
+			if (freepage_order > 0 && freepage_order <= MAX_PAGE_ORDER) {
 				low_pfn += (1UL << freepage_order) - 1;
 				nr_scanned += (1UL << freepage_order) - 1;
 			}
@@ -1017,7 +1017,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if (PageCompound(page) && !cc->alloc_contig) {
 			const unsigned int order = compound_order(page);
 
-			if (likely(order <= MAX_ORDER)) {
+			if (likely(order <= MAX_PAGE_ORDER)) {
 				low_pfn += (1UL << order) - 1;
 				nr_scanned += (1UL << order) - 1;
 			}
@@ -1611,6 +1611,9 @@ static void fast_isolate_freepages(struct compact_control *cc)
 						min(pageblock_end_pfn(min_pfn),
 						    zone_end_pfn(cc->zone)),
 						cc->zone);
+					if (page && !suitable_migration_target(cc, page))
+						page = NULL;
+
 					cc->free_pfn = min_pfn;
 				}
 			}
@@ -2226,7 +2229,7 @@ static enum compact_result __compact_finished(struct compact_control *cc)
 
 	/* Direct compactor: Is a suitable page free? */
 	ret = COMPACT_NO_SUITABLE_PAGE;
-	for (order = cc->order; order <= MAX_ORDER; order++) {
+	for (order = cc->order; order < NR_PAGE_ORDERS; order++) {
 		struct free_area *area = &cc->zone->free_area[order];
 		bool can_steal;
 
diff --git a/mm/damon/core-test.h b/mm/damon/core-test.h
index 649adf91ebc5..0cee634f3544 100644
--- a/mm/damon/core-test.h
+++ b/mm/damon/core-test.h
@@ -4,7 +4,7 @@
  *
  * Copyright 2019 Amazon.com, Inc. or its affiliates.  All rights reserved.
  *
- * Author: SeongJae Park <sjpark@amazon.de>
+ * Author: SeongJae Park <sj@kernel.org>
  */
 
 #ifdef CONFIG_DAMON_KUNIT_TEST
@@ -122,18 +122,25 @@ static void damon_test_split_at(struct kunit *test)
 {
 	struct damon_ctx *c = damon_new_ctx();
 	struct damon_target *t;
-	struct damon_region *r;
+	struct damon_region *r, *r_new;
 
 	t = damon_new_target();
 	r = damon_new_region(0, 100);
+	r->nr_accesses_bp = 420000;
+	r->nr_accesses = 42;
+	r->last_nr_accesses = 15;
 	damon_add_region(r, t);
 	damon_split_region_at(t, r, 25);
 	KUNIT_EXPECT_EQ(test, r->ar.start, 0ul);
 	KUNIT_EXPECT_EQ(test, r->ar.end, 25ul);
 
-	r = damon_next_region(r);
-	KUNIT_EXPECT_EQ(test, r->ar.start, 25ul);
-	KUNIT_EXPECT_EQ(test, r->ar.end, 100ul);
+	r_new = damon_next_region(r);
+	KUNIT_EXPECT_EQ(test, r_new->ar.start, 25ul);
+	KUNIT_EXPECT_EQ(test, r_new->ar.end, 100ul);
+
+	KUNIT_EXPECT_EQ(test, r->nr_accesses_bp, r_new->nr_accesses_bp);
+	KUNIT_EXPECT_EQ(test, r->nr_accesses, r_new->nr_accesses);
+	KUNIT_EXPECT_EQ(test, r->last_nr_accesses, r_new->last_nr_accesses);
 
 	damon_free_target(t);
 	damon_destroy_ctx(c);
@@ -295,6 +302,16 @@ static void damon_test_set_regions(struct kunit *test)
 	damon_destroy_target(t);
 }
 
+static void damon_test_nr_accesses_to_accesses_bp(struct kunit *test)
+{
+	struct damon_attrs attrs = {
+		.sample_interval = 10,
+		.aggr_interval = ((unsigned long)UINT_MAX + 1) * 10
+	};
+
+	KUNIT_EXPECT_EQ(test, damon_nr_accesses_to_accesses_bp(123, &attrs), 0);
+}
+
 static void damon_test_update_monitoring_result(struct kunit *test)
 {
 	struct damon_attrs old_attrs = {
@@ -439,6 +456,37 @@ static void damos_test_filter_out(struct kunit *test)
 	damos_free_filter(f);
 }
 
+static void damon_test_feed_loop_next_input(struct kunit *test)
+{
+	unsigned long last_input = 900000, current_score = 200;
+
+	/*
+	 * If current score is lower than the goal, which is always 10,000
+	 * (read the comment on damon_feed_loop_next_input()'s comment), next
+	 * input should be higher than the last input.
+	 */
+	KUNIT_EXPECT_GT(test,
+			damon_feed_loop_next_input(last_input, current_score),
+			last_input);
+
+	/*
+	 * If current score is higher than the goal, next input should be lower
+	 * than the last input.
+	 */
+	current_score = 250000000;
+	KUNIT_EXPECT_LT(test,
+			damon_feed_loop_next_input(last_input, current_score),
+			last_input);
+
+	/*
+	 * The next input depends on the distance between the current score and
+	 * the goal
+	 */
+	KUNIT_EXPECT_GT(test,
+			damon_feed_loop_next_input(last_input, 200),
+			damon_feed_loop_next_input(last_input, 2000));
+}
+
 static struct kunit_case damon_test_cases[] = {
 	KUNIT_CASE(damon_test_target),
 	KUNIT_CASE(damon_test_regions),
@@ -449,11 +497,13 @@ static struct kunit_case damon_test_cases[] = {
 	KUNIT_CASE(damon_test_split_regions_of),
 	KUNIT_CASE(damon_test_ops_registration),
 	KUNIT_CASE(damon_test_set_regions),
+	KUNIT_CASE(damon_test_nr_accesses_to_accesses_bp),
 	KUNIT_CASE(damon_test_update_monitoring_result),
 	KUNIT_CASE(damon_test_set_attrs),
 	KUNIT_CASE(damon_test_moving_sum),
 	KUNIT_CASE(damos_test_new_filter),
 	KUNIT_CASE(damos_test_filter_out),
+	KUNIT_CASE(damon_test_feed_loop_next_input),
 	{},
 };
 
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 630077d95dc6..36f6f1d21ff0 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -2,7 +2,7 @@
 /*
  * Data Access Monitor
  *
- * Author: SeongJae Park <sjpark@amazon.de>
+ * Author: SeongJae Park <sj@kernel.org>
  */
 
 #define pr_fmt(fmt) "damon: " fmt
@@ -445,6 +445,8 @@ struct damon_ctx *damon_new_ctx(void)
 	if (!ctx)
 		return NULL;
 
+	init_completion(&ctx->kdamond_started);
+
 	ctx->attrs.sample_interval = 5 * 1000;
 	ctx->attrs.aggr_interval = 100 * 1000;
 	ctx->attrs.ops_update_interval = 60 * 1000 * 1000;
@@ -668,11 +670,14 @@ static int __damon_start(struct damon_ctx *ctx)
 	mutex_lock(&ctx->kdamond_lock);
 	if (!ctx->kdamond) {
 		err = 0;
+		reinit_completion(&ctx->kdamond_started);
 		ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond.%d",
 				nr_running_ctxs);
 		if (IS_ERR(ctx->kdamond)) {
 			err = PTR_ERR(ctx->kdamond);
 			ctx->kdamond = NULL;
+		} else {
+			wait_for_completion(&ctx->kdamond_started);
 		}
 	}
 	mutex_unlock(&ctx->kdamond_lock);
@@ -924,7 +929,7 @@ static bool __damos_filter_out(struct damon_ctx *ctx, struct damon_target *t,
 		matched = true;
 		break;
 	default:
-		break;
+		return false;
 	}
 
 	return matched == filter->matching;
@@ -1038,26 +1043,76 @@ static void damon_do_apply_schemes(struct damon_ctx *c,
 	}
 }
 
-/* Shouldn't be called if quota->ms and quota->sz are zero */
+/*
+ * damon_feed_loop_next_input() - get next input to achieve a target score.
+ * @last_input	The last input.
+ * @score	Current score that made with @last_input.
+ *
+ * Calculate next input to achieve the target score, based on the last input
+ * and current score.  Assuming the input and the score are positively
+ * proportional, calculate how much compensation should be added to or
+ * subtracted from the last input as a proportion of the last input.  Avoid
+ * next input always being zero by setting it non-zero always.  In short form
+ * (assuming support of float and signed calculations), the algorithm is as
+ * below.
+ *
+ * next_input = max(last_input * ((goal - current) / goal + 1), 1)
+ *
+ * For simple implementation, we assume the target score is always 10,000.  The
+ * caller should adjust @score for this.
+ *
+ * Returns next input that assumed to achieve the target score.
+ */
+static unsigned long damon_feed_loop_next_input(unsigned long last_input,
+		unsigned long score)
+{
+	const unsigned long goal = 10000;
+	unsigned long score_goal_diff = max(goal, score) - min(goal, score);
+	unsigned long score_goal_diff_bp = score_goal_diff * 10000 / goal;
+	unsigned long compensation = last_input * score_goal_diff_bp / 10000;
+	/* Set minimum input as 10000 to avoid compensation be zero */
+	const unsigned long min_input = 10000;
+
+	if (goal > score)
+		return last_input + compensation;
+	if (last_input > compensation + min_input)
+		return last_input - compensation;
+	return min_input;
+}
+
+/* Shouldn't be called if quota->ms, quota->sz, and quota->get_score unset */
 static void damos_set_effective_quota(struct damos_quota *quota)
 {
 	unsigned long throughput;
 	unsigned long esz;
 
-	if (!quota->ms) {
+	if (!quota->ms && !quota->get_score) {
 		quota->esz = quota->sz;
 		return;
 	}
 
-	if (quota->total_charged_ns)
-		throughput = quota->total_charged_sz * 1000000 /
-			quota->total_charged_ns;
-	else
-		throughput = PAGE_SIZE * 1024;
-	esz = throughput * quota->ms;
+	if (quota->get_score) {
+		quota->esz_bp = damon_feed_loop_next_input(
+				max(quota->esz_bp, 10000UL),
+				quota->get_score(quota->get_score_arg));
+		esz = quota->esz_bp / 10000;
+	}
+
+	if (quota->ms) {
+		if (quota->total_charged_ns)
+			throughput = quota->total_charged_sz * 1000000 /
+				quota->total_charged_ns;
+		else
+			throughput = PAGE_SIZE * 1024;
+		if (quota->get_score)
+			esz = min(throughput * quota->ms, esz);
+		else
+			esz = throughput * quota->ms;
+	}
 
 	if (quota->sz && quota->sz < esz)
 		esz = quota->sz;
+
 	quota->esz = esz;
 }
 
@@ -1069,7 +1124,7 @@ static void damos_adjust_quota(struct damon_ctx *c, struct damos *s)
 	unsigned long cumulated_sz;
 	unsigned int score, max_score = 0;
 
-	if (!quota->ms && !quota->sz)
+	if (!quota->ms && !quota->sz && !quota->get_score)
 		return;
 
 	/* New charge window starts */
@@ -1225,6 +1280,7 @@ static void damon_split_region_at(struct damon_target *t,
 	new->age = r->age;
 	new->last_nr_accesses = r->last_nr_accesses;
 	new->nr_accesses_bp = r->nr_accesses_bp;
+	new->nr_accesses = r->nr_accesses;
 
 	damon_insert_region(new, r, damon_next_region(r), t);
 }
@@ -1432,6 +1488,7 @@ static int kdamond_fn(void *data)
 
 	pr_debug("kdamond (%d) starts\n", current->pid);
 
+	complete(&ctx->kdamond_started);
 	kdamond_init_intervals_sis(ctx);
 
 	if (ctx->ops.init)
diff --git a/mm/damon/dbgfs-test.h b/mm/damon/dbgfs-test.h
index 0bb0d532b159..2d85217f5ba4 100644
--- a/mm/damon/dbgfs-test.h
+++ b/mm/damon/dbgfs-test.h
@@ -2,7 +2,7 @@
 /*
  * DAMON Debugfs Interface Unit Tests
  *
- * Author: SeongJae Park <sjpark@amazon.de>
+ * Author: SeongJae Park <sj@kernel.org>
  */
 
 #ifdef CONFIG_DAMON_DBGFS_KUNIT_TEST
diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c
index dc0ea1fc30ca..7dac24e69e3b 100644
--- a/mm/damon/dbgfs.c
+++ b/mm/damon/dbgfs.c
@@ -2,7 +2,7 @@
 /*
  * DAMON Debugfs Interface
  *
- * Author: SeongJae Park <sjpark@amazon.de>
+ * Author: SeongJae Park <sj@kernel.org>
  */
 
 #define pr_fmt(fmt) "damon-dbgfs: " fmt
diff --git a/mm/damon/modules-common.c b/mm/damon/modules-common.c
index b2381a8466ec..7cf96574cde7 100644
--- a/mm/damon/modules-common.c
+++ b/mm/damon/modules-common.c
@@ -2,7 +2,7 @@
 /*
  * Common Primitives for DAMON Modules
  *
- * Author: SeongJae Park <sjpark@amazon.de>
+ * Author: SeongJae Park <sj@kernel.org>
  */
 
 #include <linux/damon.h>
diff --git a/mm/damon/sysfs-common.h b/mm/damon/sysfs-common.h
index 5ff081226e28..4c37a166eb81 100644
--- a/mm/damon/sysfs-common.h
+++ b/mm/damon/sysfs-common.h
@@ -56,3 +56,6 @@ int damon_sysfs_schemes_update_regions_stop(struct damon_ctx *ctx);
 int damon_sysfs_schemes_clear_regions(
 		struct damon_sysfs_schemes *sysfs_schemes,
 		struct damon_ctx *ctx);
+
+void damos_sysfs_set_quota_scores(struct damon_sysfs_schemes *sysfs_schemes,
+		struct damon_ctx *ctx);
diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c
index 45bd0fd4a8b1..8dbaac6e5c2d 100644
--- a/mm/damon/sysfs-schemes.c
+++ b/mm/damon/sysfs-schemes.c
@@ -139,6 +139,13 @@ static const struct kobj_type damon_sysfs_scheme_region_ktype = {
  * damon_sysfs_before_damos_apply() understands the situation by showing the
  * 'finished' status and do nothing.
  *
+ * If DAMOS is not applied to any region due to any reasons including the
+ * access pattern, the watermarks, the quotas, and the filters,
+ * ->before_damos_apply() will not be called back.  Until the situation is
+ * changed, the update will not be finished.  To avoid this,
+ * damon_sysfs_after_sampling() set the status as 'finished' if more than two
+ * apply intervals of the scheme is passed while the state is 'idle'.
+ *
  *  Finally, the tried regions request handling finisher function
  *  (damon_sysfs_schemes_update_regions_stop()) unregisters the callbacks.
  */
@@ -154,6 +161,7 @@ struct damon_sysfs_scheme_regions {
 	int nr_regions;
 	unsigned long total_bytes;
 	enum damos_sysfs_regions_upd_status upd_status;
+	unsigned long upd_timeout_jiffies;
 };
 
 static struct damon_sysfs_scheme_regions *
@@ -162,6 +170,9 @@ damon_sysfs_scheme_regions_alloc(void)
 	struct damon_sysfs_scheme_regions *regions = kmalloc(sizeof(*regions),
 			GFP_KERNEL);
 
+	if (!regions)
+		return NULL;
+
 	regions->kobj = (struct kobject){};
 	INIT_LIST_HEAD(&regions->regions_list);
 	regions->nr_regions = 0;
@@ -810,6 +821,203 @@ static const struct kobj_type damon_sysfs_watermarks_ktype = {
 };
 
 /*
+ * quota goal directory
+ */
+
+struct damos_sysfs_quota_goal {
+	struct kobject kobj;
+	unsigned long target_value;
+	unsigned long current_value;
+};
+
+static struct damos_sysfs_quota_goal *damos_sysfs_quota_goal_alloc(void)
+{
+	return kzalloc(sizeof(struct damos_sysfs_quota_goal), GFP_KERNEL);
+}
+
+static ssize_t target_value_show(struct kobject *kobj,
+		struct kobj_attribute *attr, char *buf)
+{
+	struct damos_sysfs_quota_goal *goal = container_of(kobj, struct
+			damos_sysfs_quota_goal, kobj);
+
+	return sysfs_emit(buf, "%lu\n", goal->target_value);
+}
+
+static ssize_t target_value_store(struct kobject *kobj,
+		struct kobj_attribute *attr, const char *buf, size_t count)
+{
+	struct damos_sysfs_quota_goal *goal = container_of(kobj, struct
+			damos_sysfs_quota_goal, kobj);
+	int err = kstrtoul(buf, 0, &goal->target_value);
+
+	return err ? err : count;
+}
+
+static ssize_t current_value_show(struct kobject *kobj,
+		struct kobj_attribute *attr, char *buf)
+{
+	struct damos_sysfs_quota_goal *goal = container_of(kobj, struct
+			damos_sysfs_quota_goal, kobj);
+
+	return sysfs_emit(buf, "%lu\n", goal->current_value);
+}
+
+static ssize_t current_value_store(struct kobject *kobj,
+		struct kobj_attribute *attr, const char *buf, size_t count)
+{
+	struct damos_sysfs_quota_goal *goal = container_of(kobj, struct
+			damos_sysfs_quota_goal, kobj);
+	int err = kstrtoul(buf, 0, &goal->current_value);
+
+	/* feed callback should check existence of this file and read value */
+	return err ? err : count;
+}
+
+static void damos_sysfs_quota_goal_release(struct kobject *kobj)
+{
+	/* or, notify this release to the feed callback */
+	kfree(container_of(kobj, struct damos_sysfs_quota_goal, kobj));
+}
+
+static struct kobj_attribute damos_sysfs_quota_goal_target_value_attr =
+		__ATTR_RW_MODE(target_value, 0600);
+
+static struct kobj_attribute damos_sysfs_quota_goal_current_value_attr =
+		__ATTR_RW_MODE(current_value, 0600);
+
+static struct attribute *damos_sysfs_quota_goal_attrs[] = {
+	&damos_sysfs_quota_goal_target_value_attr.attr,
+	&damos_sysfs_quota_goal_current_value_attr.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(damos_sysfs_quota_goal);
+
+static const struct kobj_type damos_sysfs_quota_goal_ktype = {
+	.release = damos_sysfs_quota_goal_release,
+	.sysfs_ops = &kobj_sysfs_ops,
+	.default_groups = damos_sysfs_quota_goal_groups,
+};
+
+/*
+ * quota goals directory
+ */
+
+struct damos_sysfs_quota_goals {
+	struct kobject kobj;
+	struct damos_sysfs_quota_goal **goals_arr;	/* counted by nr */
+	int nr;
+};
+
+static struct damos_sysfs_quota_goals *damos_sysfs_quota_goals_alloc(void)
+{
+	return kzalloc(sizeof(struct damos_sysfs_quota_goals), GFP_KERNEL);
+}
+
+static void damos_sysfs_quota_goals_rm_dirs(
+		struct damos_sysfs_quota_goals *goals)
+{
+	struct damos_sysfs_quota_goal **goals_arr = goals->goals_arr;
+	int i;
+
+	for (i = 0; i < goals->nr; i++)
+		kobject_put(&goals_arr[i]->kobj);
+	goals->nr = 0;
+	kfree(goals_arr);
+	goals->goals_arr = NULL;
+}
+
+static int damos_sysfs_quota_goals_add_dirs(
+		struct damos_sysfs_quota_goals *goals, int nr_goals)
+{
+	struct damos_sysfs_quota_goal **goals_arr, *goal;
+	int err, i;
+
+	damos_sysfs_quota_goals_rm_dirs(goals);
+	if (!nr_goals)
+		return 0;
+
+	goals_arr = kmalloc_array(nr_goals, sizeof(*goals_arr),
+			GFP_KERNEL | __GFP_NOWARN);
+	if (!goals_arr)
+		return -ENOMEM;
+	goals->goals_arr = goals_arr;
+
+	for (i = 0; i < nr_goals; i++) {
+		goal = damos_sysfs_quota_goal_alloc();
+		if (!goal) {
+			damos_sysfs_quota_goals_rm_dirs(goals);
+			return -ENOMEM;
+		}
+
+		err = kobject_init_and_add(&goal->kobj,
+				&damos_sysfs_quota_goal_ktype, &goals->kobj,
+				"%d", i);
+		if (err) {
+			kobject_put(&goal->kobj);
+			damos_sysfs_quota_goals_rm_dirs(goals);
+			return err;
+		}
+
+		goals_arr[i] = goal;
+		goals->nr++;
+	}
+	return 0;
+}
+
+static ssize_t nr_goals_show(struct kobject *kobj,
+		struct kobj_attribute *attr, char *buf)
+{
+	struct damos_sysfs_quota_goals *goals = container_of(kobj,
+			struct damos_sysfs_quota_goals, kobj);
+
+	return sysfs_emit(buf, "%d\n", goals->nr);
+}
+
+static ssize_t nr_goals_store(struct kobject *kobj,
+		struct kobj_attribute *attr, const char *buf, size_t count)
+{
+	struct damos_sysfs_quota_goals *goals;
+	int nr, err = kstrtoint(buf, 0, &nr);
+
+	if (err)
+		return err;
+	if (nr < 0)
+		return -EINVAL;
+
+	goals = container_of(kobj, struct damos_sysfs_quota_goals, kobj);
+
+	if (!mutex_trylock(&damon_sysfs_lock))
+		return -EBUSY;
+	err = damos_sysfs_quota_goals_add_dirs(goals, nr);
+	mutex_unlock(&damon_sysfs_lock);
+	if (err)
+		return err;
+
+	return count;
+}
+
+static void damos_sysfs_quota_goals_release(struct kobject *kobj)
+{
+	kfree(container_of(kobj, struct damos_sysfs_quota_goals, kobj));
+}
+
+static struct kobj_attribute damos_sysfs_quota_goals_nr_attr =
+		__ATTR_RW_MODE(nr_goals, 0600);
+
+static struct attribute *damos_sysfs_quota_goals_attrs[] = {
+	&damos_sysfs_quota_goals_nr_attr.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(damos_sysfs_quota_goals);
+
+static const struct kobj_type damos_sysfs_quota_goals_ktype = {
+	.release = damos_sysfs_quota_goals_release,
+	.sysfs_ops = &kobj_sysfs_ops,
+	.default_groups = damos_sysfs_quota_goals_groups,
+};
+
+/*
  * scheme/weights directory
  */
 
@@ -927,6 +1135,7 @@ static const struct kobj_type damon_sysfs_weights_ktype = {
 struct damon_sysfs_quotas {
 	struct kobject kobj;
 	struct damon_sysfs_weights *weights;
+	struct damos_sysfs_quota_goals *goals;
 	unsigned long ms;
 	unsigned long sz;
 	unsigned long reset_interval_ms;
@@ -940,6 +1149,7 @@ static struct damon_sysfs_quotas *damon_sysfs_quotas_alloc(void)
 static int damon_sysfs_quotas_add_dirs(struct damon_sysfs_quotas *quotas)
 {
 	struct damon_sysfs_weights *weights;
+	struct damos_sysfs_quota_goals *goals;
 	int err;
 
 	weights = damon_sysfs_weights_alloc(0, 0, 0);
@@ -948,16 +1158,35 @@ static int damon_sysfs_quotas_add_dirs(struct damon_sysfs_quotas *quotas)
 
 	err = kobject_init_and_add(&weights->kobj, &damon_sysfs_weights_ktype,
 			&quotas->kobj, "weights");
-	if (err)
+	if (err) {
 		kobject_put(&weights->kobj);
-	else
-		quotas->weights = weights;
+		return err;
+	}
+	quotas->weights = weights;
+
+	goals = damos_sysfs_quota_goals_alloc();
+	if (!goals) {
+		kobject_put(&weights->kobj);
+		return -ENOMEM;
+	}
+	err = kobject_init_and_add(&goals->kobj,
+			&damos_sysfs_quota_goals_ktype, &quotas->kobj,
+			"goals");
+	if (err) {
+		kobject_put(&weights->kobj);
+		kobject_put(&goals->kobj);
+	} else {
+		quotas->goals = goals;
+	}
+
 	return err;
 }
 
 static void damon_sysfs_quotas_rm_dirs(struct damon_sysfs_quotas *quotas)
 {
 	kobject_put(&quotas->weights->kobj);
+	damos_sysfs_quota_goals_rm_dirs(quotas->goals);
+	kobject_put(&quotas->goals->kobj);
 }
 
 static ssize_t ms_show(struct kobject *kobj, struct kobj_attribute *attr,
@@ -1639,6 +1868,50 @@ static int damon_sysfs_set_scheme_filters(struct damos *scheme,
 	return 0;
 }
 
+static unsigned long damos_sysfs_get_quota_score(void *arg)
+{
+	return (unsigned long)arg;
+}
+
+static void damos_sysfs_set_quota_score(
+		struct damos_sysfs_quota_goals *sysfs_goals,
+		struct damos_quota *quota)
+{
+	struct damos_sysfs_quota_goal *sysfs_goal;
+	int i;
+
+	quota->get_score = NULL;
+	quota->get_score_arg = (void *)0;
+	for (i = 0; i < sysfs_goals->nr; i++) {
+		sysfs_goal = sysfs_goals->goals_arr[i];
+		if (!sysfs_goal->target_value)
+			continue;
+
+		/* Higher score makes scheme less aggressive */
+		quota->get_score_arg = (void *)max(
+				(unsigned long)quota->get_score_arg,
+				sysfs_goal->current_value * 10000 /
+				sysfs_goal->target_value);
+		quota->get_score = damos_sysfs_get_quota_score;
+	}
+}
+
+void damos_sysfs_set_quota_scores(struct damon_sysfs_schemes *sysfs_schemes,
+		struct damon_ctx *ctx)
+{
+	struct damos *scheme;
+	int i = 0;
+
+	damon_for_each_scheme(scheme, ctx) {
+		struct damon_sysfs_scheme *sysfs_scheme;
+
+		sysfs_scheme = sysfs_schemes->schemes_arr[i];
+		damos_sysfs_set_quota_score(sysfs_scheme->quotas->goals,
+				&scheme->quota);
+		i++;
+	}
+}
+
 static struct damos *damon_sysfs_mk_scheme(
 		struct damon_sysfs_scheme *sysfs_scheme)
 {
@@ -1676,6 +1949,8 @@ static struct damos *damon_sysfs_mk_scheme(
 		.low = sysfs_wmarks->low,
 	};
 
+	damos_sysfs_set_quota_score(sysfs_quotas->goals, &quota);
+
 	scheme = damon_new_scheme(&pattern, sysfs_scheme->action,
 			sysfs_scheme->apply_interval_us, &quota, &wmarks);
 	if (!scheme)
@@ -1716,6 +1991,8 @@ static void damon_sysfs_update_scheme(struct damos *scheme,
 	scheme->quota.weight_nr_accesses = sysfs_weights->nr_accesses;
 	scheme->quota.weight_age = sysfs_weights->age;
 
+	damos_sysfs_set_quota_score(sysfs_quotas->goals, &scheme->quota);
+
 	scheme->wmarks.metric = sysfs_wmarks->metric;
 	scheme->wmarks.interval = sysfs_wmarks->interval_us;
 	scheme->wmarks.high = sysfs_wmarks->high;
@@ -1823,6 +2100,8 @@ static int damon_sysfs_before_damos_apply(struct damon_ctx *ctx,
 		return 0;
 
 	region = damon_sysfs_scheme_region_alloc(r);
+	if (!region)
+		return 0;
 	list_add_tail(&region->list, &sysfs_regions->regions_list);
 	sysfs_regions->nr_regions++;
 	if (kobject_init_and_add(&region->kobj,
@@ -1849,7 +2128,9 @@ static int damon_sysfs_after_sampling(struct damon_ctx *ctx)
 	for (i = 0; i < sysfs_schemes->nr; i++) {
 		sysfs_regions = sysfs_schemes->schemes_arr[i]->tried_regions;
 		if (sysfs_regions->upd_status ==
-				DAMOS_TRIED_REGIONS_UPD_STARTED)
+				DAMOS_TRIED_REGIONS_UPD_STARTED ||
+				time_after(jiffies,
+					sysfs_regions->upd_timeout_jiffies))
 			sysfs_regions->upd_status =
 				DAMOS_TRIED_REGIONS_UPD_FINISHED;
 	}
@@ -1880,14 +2161,41 @@ int damon_sysfs_schemes_clear_regions(
 	return 0;
 }
 
+static struct damos *damos_sysfs_nth_scheme(int n, struct damon_ctx *ctx)
+{
+	struct damos *scheme;
+	int i = 0;
+
+	damon_for_each_scheme(scheme, ctx) {
+		if (i == n)
+			return scheme;
+		i++;
+	}
+	return NULL;
+}
+
 static void damos_tried_regions_init_upd_status(
-		struct damon_sysfs_schemes *sysfs_schemes)
+		struct damon_sysfs_schemes *sysfs_schemes,
+		struct damon_ctx *ctx)
 {
 	int i;
+	struct damos *scheme;
+	struct damon_sysfs_scheme_regions *sysfs_regions;
 
-	for (i = 0; i < sysfs_schemes->nr; i++)
-		sysfs_schemes->schemes_arr[i]->tried_regions->upd_status =
-			DAMOS_TRIED_REGIONS_UPD_IDLE;
+	for (i = 0; i < sysfs_schemes->nr; i++) {
+		sysfs_regions = sysfs_schemes->schemes_arr[i]->tried_regions;
+		scheme = damos_sysfs_nth_scheme(i, ctx);
+		if (!scheme) {
+			sysfs_regions->upd_status =
+				DAMOS_TRIED_REGIONS_UPD_FINISHED;
+			continue;
+		}
+		sysfs_regions->upd_status = DAMOS_TRIED_REGIONS_UPD_IDLE;
+		sysfs_regions->upd_timeout_jiffies = jiffies +
+			2 * usecs_to_jiffies(scheme->apply_interval_us ?
+					scheme->apply_interval_us :
+					ctx->attrs.sample_interval);
+	}
 }
 
 /* Called from damon_sysfs_cmd_request_callback under damon_sysfs_lock */
@@ -1897,7 +2205,7 @@ int damon_sysfs_schemes_update_regions_start(
 {
 	damon_sysfs_schemes_clear_regions(sysfs_schemes, ctx);
 	damon_sysfs_schemes_for_damos_callback = sysfs_schemes;
-	damos_tried_regions_init_upd_status(sysfs_schemes);
+	damos_tried_regions_init_upd_status(sysfs_schemes, ctx);
 	damos_regions_upd_total_bytes_only = total_bytes_only;
 	ctx->callback.before_damos_apply = damon_sysfs_before_damos_apply;
 	ctx->callback.after_sampling = damon_sysfs_after_sampling;
diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c
index e27846708b5a..1f891e18b4ee 100644
--- a/mm/damon/sysfs.c
+++ b/mm/damon/sysfs.c
@@ -995,6 +995,11 @@ enum damon_sysfs_cmd {
 	/* @DAMON_SYSFS_CMD_COMMIT: Update kdamond inputs. */
 	DAMON_SYSFS_CMD_COMMIT,
 	/*
+	 * @DAMON_SYSFS_CMD_COMMIT_SCHEMES_QUOTA_GOALS: Commit the quota goals
+	 * to DAMON.
+	 */
+	DAMON_SYSFS_CMD_COMMIT_SCHEMES_QUOTA_GOALS,
+	/*
 	 * @DAMON_SYSFS_CMD_UPDATE_SCHEMES_STATS: Update scheme stats sysfs
 	 * files.
 	 */
@@ -1025,6 +1030,7 @@ static const char * const damon_sysfs_cmd_strs[] = {
 	"on",
 	"off",
 	"commit",
+	"commit_schemes_quota_goals",
 	"update_schemes_stats",
 	"update_schemes_tried_bytes",
 	"update_schemes_tried_regions",
@@ -1172,7 +1178,7 @@ static int damon_sysfs_update_target(struct damon_target *target,
 		struct damon_ctx *ctx,
 		struct damon_sysfs_target *sys_target)
 {
-	int err;
+	int err = 0;
 
 	if (damon_target_has_pid(ctx)) {
 		err = damon_sysfs_update_target_pid(target, sys_target->pid);
@@ -1203,8 +1209,10 @@ static int damon_sysfs_set_targets(struct damon_ctx *ctx,
 
 	damon_for_each_target_safe(t, next, ctx) {
 		if (i < sysfs_targets->nr) {
-			damon_sysfs_update_target(t, ctx,
+			err = damon_sysfs_update_target(t, ctx,
 					sysfs_targets->targets_arr[i]);
+			if (err)
+				return err;
 		} else {
 			if (damon_target_has_pid(ctx))
 				put_pid(t->pid);
@@ -1349,6 +1357,24 @@ static int damon_sysfs_commit_input(struct damon_sysfs_kdamond *kdamond)
 			kdamond->contexts->contexts_arr[0]);
 }
 
+static int damon_sysfs_commit_schemes_quota_goals(
+		struct damon_sysfs_kdamond *sysfs_kdamond)
+{
+	struct damon_ctx *ctx;
+	struct damon_sysfs_context *sysfs_ctx;
+
+	if (!damon_sysfs_kdamond_running(sysfs_kdamond))
+		return -EINVAL;
+	/* TODO: Support multiple contexts per kdamond */
+	if (sysfs_kdamond->contexts->nr != 1)
+		return -EINVAL;
+
+	ctx = sysfs_kdamond->damon_ctx;
+	sysfs_ctx = sysfs_kdamond->contexts->contexts_arr[0];
+	damos_sysfs_set_quota_scores(sysfs_ctx->schemes, ctx);
+	return 0;
+}
+
 /*
  * damon_sysfs_cmd_request_callback() - DAMON callback for handling requests.
  * @c:		The DAMON context of the callback.
@@ -1377,6 +1403,9 @@ static int damon_sysfs_cmd_request_callback(struct damon_ctx *c, bool active)
 	case DAMON_SYSFS_CMD_COMMIT:
 		err = damon_sysfs_commit_input(kdamond);
 		break;
+	case DAMON_SYSFS_CMD_COMMIT_SCHEMES_QUOTA_GOALS:
+		err = damon_sysfs_commit_schemes_quota_goals(kdamond);
+		break;
 	case DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_BYTES:
 		total_bytes_only = true;
 		fallthrough;
diff --git a/mm/damon/vaddr-test.h b/mm/damon/vaddr-test.h
index dcf1ca6b31cc..83626483f82b 100644
--- a/mm/damon/vaddr-test.h
+++ b/mm/damon/vaddr-test.h
@@ -4,7 +4,7 @@
  *
  * Copyright 2019 Amazon.com, Inc. or its affiliates.  All rights reserved.
  *
- * Author: SeongJae Park <sjpark@amazon.de>
+ * Author: SeongJae Park <sj@kernel.org>
  */
 
 #ifdef CONFIG_DAMON_VADDR_KUNIT_TEST
diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
index a4d1f63c5b23..381559e4a1fa 100644
--- a/mm/damon/vaddr.c
+++ b/mm/damon/vaddr.c
@@ -2,14 +2,14 @@
 /*
  * DAMON Primitives for Virtual Address Spaces
  *
- * Author: SeongJae Park <sjpark@amazon.de>
+ * Author: SeongJae Park <sj@kernel.org>
  */
 
 #define pr_fmt(fmt) "damon-va: " fmt
 
-#include <asm-generic/mman-common.h>
 #include <linux/highmem.h>
 #include <linux/hugetlb.h>
+#include <linux/mman.h>
 #include <linux/mmu_notifier.h>
 #include <linux/page_idle.h>
 #include <linux/pagewalk.h>
diff --git a/mm/debug_page_alloc.c b/mm/debug_page_alloc.c
index f9d145730fd1..6755f0c9d4a3 100644
--- a/mm/debug_page_alloc.c
+++ b/mm/debug_page_alloc.c
@@ -22,7 +22,7 @@ static int __init debug_guardpage_minorder_setup(char *buf)
 {
 	unsigned long res;
 
-	if (kstrtoul(buf, 10, &res) < 0 ||  res > MAX_ORDER / 2) {
+	if (kstrtoul(buf, 10, &res) < 0 ||  res > MAX_PAGE_ORDER / 2) {
 		pr_err("Bad debug_guardpage_minorder value\n");
 		return 0;
 	}
diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index e651500e597a..5662e29fe253 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -1091,7 +1091,7 @@ debug_vm_pgtable_alloc_huge_page(struct pgtable_debug_args *args, int order)
 	struct page *page = NULL;
 
 #ifdef CONFIG_CONTIG_ALLOC
-	if (order > MAX_ORDER) {
+	if (order > MAX_PAGE_ORDER) {
 		page = alloc_contig_pages((1 << order), GFP_KERNEL,
 					  first_online_node, NULL);
 		if (page) {
@@ -1101,7 +1101,7 @@ debug_vm_pgtable_alloc_huge_page(struct pgtable_debug_args *args, int order)
 	}
 #endif
 
-	if (order <= MAX_ORDER)
+	if (order <= MAX_PAGE_ORDER)
 		page = alloc_pages(GFP_KERNEL, order);
 
 	return page;
diff --git a/mm/dmapool.c b/mm/dmapool.c
index a151a21e571b..f0bfc6c490f4 100644
--- a/mm/dmapool.c
+++ b/mm/dmapool.c
@@ -36,7 +36,7 @@
 #include <linux/types.h>
 #include <linux/wait.h>
 
-#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB_DEBUG_ON)
+#ifdef CONFIG_SLUB_DEBUG_ON
 #define DMAPOOL_DEBUG 1
 #endif
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 9710f43a89ac..ea49677c6338 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -45,6 +45,7 @@
 #include <linux/migrate.h>
 #include <linux/pipe_fs_i.h>
 #include <linux/splice.h>
+#include <linux/rcupdate_wait.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include "internal.h"
@@ -113,11 +114,11 @@
  *    ->i_pages lock		(try_to_unmap_one)
  *    ->lruvec->lru_lock	(follow_page->mark_page_accessed)
  *    ->lruvec->lru_lock	(check_pte_range->isolate_lru_page)
- *    ->private_lock		(page_remove_rmap->set_page_dirty)
- *    ->i_pages lock		(page_remove_rmap->set_page_dirty)
- *    bdi.wb->list_lock		(page_remove_rmap->set_page_dirty)
- *    ->inode->i_lock		(page_remove_rmap->set_page_dirty)
- *    ->memcg->move_lock	(page_remove_rmap->folio_memcg_lock)
+ *    ->private_lock		(folio_remove_rmap_pte->set_page_dirty)
+ *    ->i_pages lock		(folio_remove_rmap_pte->set_page_dirty)
+ *    bdi.wb->list_lock		(folio_remove_rmap_pte->set_page_dirty)
+ *    ->inode->i_lock		(folio_remove_rmap_pte->set_page_dirty)
+ *    ->memcg->move_lock	(folio_remove_rmap_pte->folio_memcg_lock)
  *    bdi.wb->list_lock		(zap_pte_range->set_page_dirty)
  *    ->inode->i_lock		(zap_pte_range->set_page_dirty)
  *    ->private_lock		(zap_pte_range->block_dirty_folio)
@@ -1623,7 +1624,7 @@ EXPORT_SYMBOL_GPL(__folio_lock_killable);
 static int __folio_lock_async(struct folio *folio, struct wait_page_queue *wait)
 {
 	struct wait_queue_head *q = folio_waitqueue(folio);
-	int ret = 0;
+	int ret;
 
 	wait->folio = folio;
 	wait->bit_nr = PG_locked;
@@ -2173,7 +2174,7 @@ update_start:
 
 	if (nr) {
 		folio = fbatch->folios[nr - 1];
-		*start = folio->index + folio_nr_pages(folio);
+		*start = folio_next_index(folio);
 	}
 out:
 	rcu_read_unlock();
@@ -2608,6 +2609,15 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter,
 		end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count);
 
 		/*
+		 * Pairs with a barrier in
+		 * block_write_end()->mark_buffer_dirty() or other page
+		 * dirtying routines like iomap_write_end() to ensure
+		 * changes to page contents are visible before we see
+		 * increased inode size.
+		 */
+		smp_rmb();
+
+		/*
 		 * Once we start copying data, we don't want to be touching any
 		 * cachelines that might be contended:
 		 */
@@ -3371,7 +3381,7 @@ static bool filemap_map_pmd(struct vm_fault *vmf, struct folio *folio,
 		}
 	}
 
-	if (pmd_none(*vmf->pmd))
+	if (pmd_none(*vmf->pmd) && vmf->prealloc_pte)
 		pmd_install(mm, vmf->pmd, &vmf->prealloc_pte);
 
 	return false;
@@ -3443,7 +3453,7 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
 		 * handled in the specific fault path, and it'll prohibit the
 		 * fault-around logic.
 		 */
-		if (!pte_none(vmf->pte[count]))
+		if (!pte_none(ptep_get(&vmf->pte[count])))
 			goto skip;
 
 		count++;
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index 10c3247542cb..50412014f16f 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -46,9 +46,9 @@ void mark_page_accessed(struct page *page)
 }
 EXPORT_SYMBOL(mark_page_accessed);
 
-bool set_page_writeback(struct page *page)
+void set_page_writeback(struct page *page)
 {
-	return folio_start_writeback(page_folio(page));
+	folio_start_writeback(page_folio(page));
 }
 EXPORT_SYMBOL(set_page_writeback);
 
@@ -77,12 +77,6 @@ bool redirty_page_for_writepage(struct writeback_control *wbc,
 }
 EXPORT_SYMBOL(redirty_page_for_writepage);
 
-void lru_cache_add_inactive_or_unevictable(struct page *page,
-		struct vm_area_struct *vma)
-{
-	folio_add_lru_vma(page_folio(page), vma);
-}
-
 int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 		pgoff_t index, gfp_t gfp)
 {
@@ -122,13 +116,3 @@ void putback_lru_page(struct page *page)
 {
 	folio_putback_lru(page_folio(page));
 }
-
-#ifdef CONFIG_MMU
-void page_add_new_anon_rmap(struct page *page, struct vm_area_struct *vma,
-		unsigned long address)
-{
-	VM_BUG_ON_PAGE(PageTail(page), page);
-
-	return folio_add_new_anon_rmap((struct folio *)page, vma, address);
-}
-#endif
diff --git a/mm/gup.c b/mm/gup.c
index 231711efa390..df83182ec72d 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -177,7 +177,7 @@ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags)
 	/*
 	 * Adjust the pincount before re-checking the PTE for changes.
 	 * This is essentially a smp_mb() and is paired with a memory
-	 * barrier in page_try_share_anon_rmap().
+	 * barrier in folio_try_share_anon_rmap_*().
 	 */
 	smp_mb__after_atomic();
 
@@ -710,6 +710,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 		spin_unlock(ptl);
 		if (page)
 			return page;
+		return no_page_table(vma, flags);
 	}
 	if (likely(!pmd_trans_huge(pmdval)))
 		return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
@@ -758,6 +759,7 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma,
 		spin_unlock(ptl);
 		if (page)
 			return page;
+		return no_page_table(vma, flags);
 	}
 	if (unlikely(pud_bad(*pud)))
 		return no_page_table(vma, flags);
diff --git a/mm/highmem.c b/mm/highmem.c
index e19269093a93..bd48ba445dd4 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -799,8 +799,6 @@ void set_page_address(struct page *page, void *virtual)
 		}
 		spin_unlock_irqrestore(&pas->lock, flags);
 	}
-
-	return;
 }
 
 void __init page_address_init(void)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f31f02472396..94ef5c02b459 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -74,12 +74,23 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
 static atomic_t huge_zero_refcount;
 struct page *huge_zero_page __read_mostly;
 unsigned long huge_zero_pfn __read_mostly = ~0UL;
+unsigned long huge_anon_orders_always __read_mostly;
+unsigned long huge_anon_orders_madvise __read_mostly;
+unsigned long huge_anon_orders_inherit __read_mostly;
+
+unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
+					 unsigned long vm_flags, bool smaps,
+					 bool in_pf, bool enforce_sysfs,
+					 unsigned long orders)
+{
+	/* Check the intersection of requested and supported orders. */
+	orders &= vma_is_anonymous(vma) ?
+			THP_ORDERS_ALL_ANON : THP_ORDERS_ALL_FILE;
+	if (!orders)
+		return 0;
 
-bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags,
-			bool smaps, bool in_pf, bool enforce_sysfs)
-{
 	if (!vma->vm_mm)		/* vdso */
-		return false;
+		return 0;
 
 	/*
 	 * Explicitly disabled through madvise or prctl, or some
@@ -88,16 +99,16 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags,
 	 * */
 	if ((vm_flags & VM_NOHUGEPAGE) ||
 	    test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
-		return false;
+		return 0;
 	/*
 	 * If the hardware/firmware marked hugepage support disabled.
 	 */
 	if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED))
-		return false;
+		return 0;
 
 	/* khugepaged doesn't collapse DAX vma, but page fault is fine. */
 	if (vma_is_dax(vma))
-		return in_pf;
+		return in_pf ? orders : 0;
 
 	/*
 	 * khugepaged special VMA and hugetlb VMA.
@@ -105,17 +116,29 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags,
 	 * VM_MIXEDMAP set.
 	 */
 	if (!in_pf && !smaps && (vm_flags & VM_NO_KHUGEPAGED))
-		return false;
+		return 0;
 
 	/*
-	 * Check alignment for file vma and size for both file and anon vma.
+	 * Check alignment for file vma and size for both file and anon vma by
+	 * filtering out the unsuitable orders.
 	 *
 	 * Skip the check for page fault. Huge fault does the check in fault
-	 * handlers. And this check is not suitable for huge PUD fault.
+	 * handlers.
 	 */
-	if (!in_pf &&
-	    !transhuge_vma_suitable(vma, (vma->vm_end - HPAGE_PMD_SIZE)))
-		return false;
+	if (!in_pf) {
+		int order = highest_order(orders);
+		unsigned long addr;
+
+		while (orders) {
+			addr = vma->vm_end - (PAGE_SIZE << order);
+			if (thp_vma_suitable_order(vma, addr, order))
+				break;
+			order = next_order(&orders, order);
+		}
+
+		if (!orders)
+			return 0;
+	}
 
 	/*
 	 * Enabled via shmem mount options or sysfs settings.
@@ -124,29 +147,33 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags,
 	 */
 	if (!in_pf && shmem_file(vma->vm_file))
 		return shmem_is_huge(file_inode(vma->vm_file), vma->vm_pgoff,
-				     !enforce_sysfs, vma->vm_mm, vm_flags);
-
-	/* Enforce sysfs THP requirements as necessary */
-	if (enforce_sysfs &&
-	    (!hugepage_flags_enabled() || (!(vm_flags & VM_HUGEPAGE) &&
-					   !hugepage_flags_always())))
-		return false;
+				     !enforce_sysfs, vma->vm_mm, vm_flags)
+			? orders : 0;
 
 	if (!vma_is_anonymous(vma)) {
 		/*
+		 * Enforce sysfs THP requirements as necessary. Anonymous vmas
+		 * were already handled in thp_vma_allowable_orders().
+		 */
+		if (enforce_sysfs &&
+		    (!hugepage_global_enabled() || (!(vm_flags & VM_HUGEPAGE) &&
+						    !hugepage_global_always())))
+			return 0;
+
+		/*
 		 * Trust that ->huge_fault() handlers know what they are doing
 		 * in fault path.
 		 */
 		if (((in_pf || smaps)) && vma->vm_ops->huge_fault)
-			return true;
+			return orders;
 		/* Only regular file is valid in collapse path */
 		if (((!in_pf || smaps)) && file_thp_enabled(vma))
-			return true;
-		return false;
+			return orders;
+		return 0;
 	}
 
 	if (vma_is_temporary_stack(vma))
-		return false;
+		return 0;
 
 	/*
 	 * THPeligible bit of smaps should show 1 for proper VMAs even
@@ -156,9 +183,9 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags,
 	 * the first page fault.
 	 */
 	if (!vma->anon_vma)
-		return (smaps || in_pf);
+		return (smaps || in_pf) ? orders : 0;
 
-	return true;
+	return orders;
 }
 
 static bool get_huge_zero_page(void)
@@ -412,9 +439,136 @@ static const struct attribute_group hugepage_attr_group = {
 	.attrs = hugepage_attr,
 };
 
+static void hugepage_exit_sysfs(struct kobject *hugepage_kobj);
+static void thpsize_release(struct kobject *kobj);
+static DEFINE_SPINLOCK(huge_anon_orders_lock);
+static LIST_HEAD(thpsize_list);
+
+struct thpsize {
+	struct kobject kobj;
+	struct list_head node;
+	int order;
+};
+
+#define to_thpsize(kobj) container_of(kobj, struct thpsize, kobj)
+
+static ssize_t thpsize_enabled_show(struct kobject *kobj,
+				    struct kobj_attribute *attr, char *buf)
+{
+	int order = to_thpsize(kobj)->order;
+	const char *output;
+
+	if (test_bit(order, &huge_anon_orders_always))
+		output = "[always] inherit madvise never";
+	else if (test_bit(order, &huge_anon_orders_inherit))
+		output = "always [inherit] madvise never";
+	else if (test_bit(order, &huge_anon_orders_madvise))
+		output = "always inherit [madvise] never";
+	else
+		output = "always inherit madvise [never]";
+
+	return sysfs_emit(buf, "%s\n", output);
+}
+
+static ssize_t thpsize_enabled_store(struct kobject *kobj,
+				     struct kobj_attribute *attr,
+				     const char *buf, size_t count)
+{
+	int order = to_thpsize(kobj)->order;
+	ssize_t ret = count;
+
+	if (sysfs_streq(buf, "always")) {
+		spin_lock(&huge_anon_orders_lock);
+		clear_bit(order, &huge_anon_orders_inherit);
+		clear_bit(order, &huge_anon_orders_madvise);
+		set_bit(order, &huge_anon_orders_always);
+		spin_unlock(&huge_anon_orders_lock);
+	} else if (sysfs_streq(buf, "inherit")) {
+		spin_lock(&huge_anon_orders_lock);
+		clear_bit(order, &huge_anon_orders_always);
+		clear_bit(order, &huge_anon_orders_madvise);
+		set_bit(order, &huge_anon_orders_inherit);
+		spin_unlock(&huge_anon_orders_lock);
+	} else if (sysfs_streq(buf, "madvise")) {
+		spin_lock(&huge_anon_orders_lock);
+		clear_bit(order, &huge_anon_orders_always);
+		clear_bit(order, &huge_anon_orders_inherit);
+		set_bit(order, &huge_anon_orders_madvise);
+		spin_unlock(&huge_anon_orders_lock);
+	} else if (sysfs_streq(buf, "never")) {
+		spin_lock(&huge_anon_orders_lock);
+		clear_bit(order, &huge_anon_orders_always);
+		clear_bit(order, &huge_anon_orders_inherit);
+		clear_bit(order, &huge_anon_orders_madvise);
+		spin_unlock(&huge_anon_orders_lock);
+	} else
+		ret = -EINVAL;
+
+	return ret;
+}
+
+static struct kobj_attribute thpsize_enabled_attr =
+	__ATTR(enabled, 0644, thpsize_enabled_show, thpsize_enabled_store);
+
+static struct attribute *thpsize_attrs[] = {
+	&thpsize_enabled_attr.attr,
+	NULL,
+};
+
+static const struct attribute_group thpsize_attr_group = {
+	.attrs = thpsize_attrs,
+};
+
+static const struct kobj_type thpsize_ktype = {
+	.release = &thpsize_release,
+	.sysfs_ops = &kobj_sysfs_ops,
+};
+
+static struct thpsize *thpsize_create(int order, struct kobject *parent)
+{
+	unsigned long size = (PAGE_SIZE << order) / SZ_1K;
+	struct thpsize *thpsize;
+	int ret;
+
+	thpsize = kzalloc(sizeof(*thpsize), GFP_KERNEL);
+	if (!thpsize)
+		return ERR_PTR(-ENOMEM);
+
+	ret = kobject_init_and_add(&thpsize->kobj, &thpsize_ktype, parent,
+				   "hugepages-%lukB", size);
+	if (ret) {
+		kfree(thpsize);
+		return ERR_PTR(ret);
+	}
+
+	ret = sysfs_create_group(&thpsize->kobj, &thpsize_attr_group);
+	if (ret) {
+		kobject_put(&thpsize->kobj);
+		return ERR_PTR(ret);
+	}
+
+	thpsize->order = order;
+	return thpsize;
+}
+
+static void thpsize_release(struct kobject *kobj)
+{
+	kfree(to_thpsize(kobj));
+}
+
 static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj)
 {
 	int err;
+	struct thpsize *thpsize;
+	unsigned long orders;
+	int order;
+
+	/*
+	 * Default to setting PMD-sized THP to inherit the global setting and
+	 * disable all other sizes. powerpc's PMD_ORDER isn't a compile-time
+	 * constant so we have to do this here.
+	 */
+	huge_anon_orders_inherit = BIT(PMD_ORDER);
 
 	*hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj);
 	if (unlikely(!*hugepage_kobj)) {
@@ -434,8 +588,24 @@ static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj)
 		goto remove_hp_group;
 	}
 
+	orders = THP_ORDERS_ALL_ANON;
+	order = highest_order(orders);
+	while (orders) {
+		thpsize = thpsize_create(order, *hugepage_kobj);
+		if (IS_ERR(thpsize)) {
+			pr_err("failed to create thpsize for order %d\n", order);
+			err = PTR_ERR(thpsize);
+			goto remove_all;
+		}
+		list_add(&thpsize->node, &thpsize_list);
+		order = next_order(&orders, order);
+	}
+
 	return 0;
 
+remove_all:
+	hugepage_exit_sysfs(*hugepage_kobj);
+	return err;
 remove_hp_group:
 	sysfs_remove_group(*hugepage_kobj, &hugepage_attr_group);
 delete_obj:
@@ -445,6 +615,13 @@ delete_obj:
 
 static void __init hugepage_exit_sysfs(struct kobject *hugepage_kobj)
 {
+	struct thpsize *thpsize, *tmp;
+
+	list_for_each_entry_safe(thpsize, tmp, &thpsize_list, node) {
+		list_del(&thpsize->node);
+		kobject_put(&thpsize->kobj);
+	}
+
 	sysfs_remove_group(hugepage_kobj, &khugepaged_attr_group);
 	sysfs_remove_group(hugepage_kobj, &hugepage_attr_group);
 	kobject_put(hugepage_kobj);
@@ -505,7 +682,7 @@ static int __init hugepage_init(void)
 	/*
 	 * hugepages can't be allocated by the buddy allocator
 	 */
-	MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER > MAX_ORDER);
+	MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER > MAX_PAGE_ORDER);
 	/*
 	 * we use page->mapping and page->index in second tail page
 	 * as list_head: assuming THP order >= 2
@@ -811,7 +988,7 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 	struct folio *folio;
 	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
 
-	if (!transhuge_vma_suitable(vma, haddr))
+	if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER))
 		return VM_FAULT_FALLBACK;
 	if (unlikely(anon_vma_prepare(vma)))
 		return VM_FAULT_OOM;
@@ -1098,6 +1275,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 {
 	spinlock_t *dst_ptl, *src_ptl;
 	struct page *src_page;
+	struct folio *src_folio;
 	pmd_t pmd;
 	pgtable_t pgtable = NULL;
 	int ret = -ENOMEM;
@@ -1164,11 +1342,12 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 
 	src_page = pmd_page(pmd);
 	VM_BUG_ON_PAGE(!PageHead(src_page), src_page);
+	src_folio = page_folio(src_page);
 
-	get_page(src_page);
-	if (unlikely(page_try_dup_anon_rmap(src_page, true, src_vma))) {
+	folio_get(src_folio);
+	if (unlikely(folio_try_dup_anon_rmap_pmd(src_folio, src_page, src_vma))) {
 		/* Page maybe pinned: split and retry the fault on PTEs. */
-		put_page(src_page);
+		folio_put(src_folio);
 		pte_free(dst_mm, pgtable);
 		spin_unlock(src_ptl);
 		spin_unlock(dst_ptl);
@@ -1277,8 +1456,8 @@ int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	}
 
 	/*
-	 * TODO: once we support anonymous pages, use page_try_dup_anon_rmap()
-	 * and split if duplicating fails.
+	 * TODO: once we support anonymous pages, use
+	 * folio_try_dup_anon_rmap_*() and split if duplicating fails.
 	 */
 	pudp_set_wrprotect(src_mm, addr, src_pud);
 	pud = pud_mkold(pud_wrprotect(pud));
@@ -1721,7 +1900,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 
 		if (pmd_present(orig_pmd)) {
 			page = pmd_page(orig_pmd);
-			page_remove_rmap(page, vma, true);
+			folio_remove_rmap_pmd(page_folio(page), page, vma);
 			VM_BUG_ON_PAGE(page_mapcount(page) < 0, page);
 			VM_BUG_ON_PAGE(!PageHead(page), page);
 		} else if (thp_migration_supported()) {
@@ -1964,6 +2143,128 @@ unlock:
 	return ret;
 }
 
+#ifdef CONFIG_USERFAULTFD
+/*
+ * The PT lock for src_pmd and the mmap_lock for reading are held by
+ * the caller, but it must return after releasing the page_table_lock.
+ * Just move the page from src_pmd to dst_pmd if possible.
+ * Return zero if succeeded in moving the page, -EAGAIN if it needs to be
+ * repeated by the caller, or other errors in case of failure.
+ */
+int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval,
+			struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+			unsigned long dst_addr, unsigned long src_addr)
+{
+	pmd_t _dst_pmd, src_pmdval;
+	struct page *src_page;
+	struct folio *src_folio;
+	struct anon_vma *src_anon_vma;
+	spinlock_t *src_ptl, *dst_ptl;
+	pgtable_t src_pgtable;
+	struct mmu_notifier_range range;
+	int err = 0;
+
+	src_pmdval = *src_pmd;
+	src_ptl = pmd_lockptr(mm, src_pmd);
+
+	lockdep_assert_held(src_ptl);
+	mmap_assert_locked(mm);
+
+	/* Sanity checks before the operation */
+	if (WARN_ON_ONCE(!pmd_none(dst_pmdval)) || WARN_ON_ONCE(src_addr & ~HPAGE_PMD_MASK) ||
+	    WARN_ON_ONCE(dst_addr & ~HPAGE_PMD_MASK)) {
+		spin_unlock(src_ptl);
+		return -EINVAL;
+	}
+
+	if (!pmd_trans_huge(src_pmdval)) {
+		spin_unlock(src_ptl);
+		if (is_pmd_migration_entry(src_pmdval)) {
+			pmd_migration_entry_wait(mm, &src_pmdval);
+			return -EAGAIN;
+		}
+		return -ENOENT;
+	}
+
+	src_page = pmd_page(src_pmdval);
+	if (unlikely(!PageAnonExclusive(src_page))) {
+		spin_unlock(src_ptl);
+		return -EBUSY;
+	}
+
+	src_folio = page_folio(src_page);
+	folio_get(src_folio);
+	spin_unlock(src_ptl);
+
+	flush_cache_range(src_vma, src_addr, src_addr + HPAGE_PMD_SIZE);
+	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, src_addr,
+				src_addr + HPAGE_PMD_SIZE);
+	mmu_notifier_invalidate_range_start(&range);
+
+	folio_lock(src_folio);
+
+	/*
+	 * split_huge_page walks the anon_vma chain without the page
+	 * lock. Serialize against it with the anon_vma lock, the page
+	 * lock is not enough.
+	 */
+	src_anon_vma = folio_get_anon_vma(src_folio);
+	if (!src_anon_vma) {
+		err = -EAGAIN;
+		goto unlock_folio;
+	}
+	anon_vma_lock_write(src_anon_vma);
+
+	dst_ptl = pmd_lockptr(mm, dst_pmd);
+	double_pt_lock(src_ptl, dst_ptl);
+	if (unlikely(!pmd_same(*src_pmd, src_pmdval) ||
+		     !pmd_same(*dst_pmd, dst_pmdval))) {
+		err = -EAGAIN;
+		goto unlock_ptls;
+	}
+	if (folio_maybe_dma_pinned(src_folio) ||
+	    !PageAnonExclusive(&src_folio->page)) {
+		err = -EBUSY;
+		goto unlock_ptls;
+	}
+
+	if (WARN_ON_ONCE(!folio_test_head(src_folio)) ||
+	    WARN_ON_ONCE(!folio_test_anon(src_folio))) {
+		err = -EBUSY;
+		goto unlock_ptls;
+	}
+
+	folio_move_anon_rmap(src_folio, dst_vma);
+	WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr));
+
+	src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd);
+	/* Folio got pinned from under us. Put it back and fail the move. */
+	if (folio_maybe_dma_pinned(src_folio)) {
+		set_pmd_at(mm, src_addr, src_pmd, src_pmdval);
+		err = -EBUSY;
+		goto unlock_ptls;
+	}
+
+	_dst_pmd = mk_huge_pmd(&src_folio->page, dst_vma->vm_page_prot);
+	/* Follow mremap() behavior and treat the entry dirty after the move */
+	_dst_pmd = pmd_mkwrite(pmd_mkdirty(_dst_pmd), dst_vma);
+	set_pmd_at(mm, dst_addr, dst_pmd, _dst_pmd);
+
+	src_pgtable = pgtable_trans_huge_withdraw(mm, src_pmd);
+	pgtable_trans_huge_deposit(mm, dst_pmd, src_pgtable);
+unlock_ptls:
+	double_pt_unlock(src_ptl, dst_ptl);
+	anon_vma_unlock_write(src_anon_vma);
+	put_anon_vma(src_anon_vma);
+unlock_folio:
+	/* unblock rmap walks */
+	folio_unlock(src_folio);
+	mmu_notifier_invalidate_range_end(&range);
+	folio_put(src_folio);
+	return err;
+}
+#endif /* CONFIG_USERFAULTFD */
+
 /*
  * Returns page table lock pointer if a given pmd maps a thp, NULL otherwise.
  *
@@ -2099,6 +2400,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long haddr, bool freeze)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	struct folio *folio;
 	struct page *page;
 	pgtable_t pgtable;
 	pmd_t old_pmd, _pmd;
@@ -2133,12 +2435,13 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 			page = pfn_swap_entry_to_page(entry);
 		} else {
 			page = pmd_page(old_pmd);
-			if (!PageDirty(page) && pmd_dirty(old_pmd))
-				set_page_dirty(page);
-			if (!PageReferenced(page) && pmd_young(old_pmd))
-				SetPageReferenced(page);
-			page_remove_rmap(page, vma, true);
-			put_page(page);
+			folio = page_folio(page);
+			if (!folio_test_dirty(folio) && pmd_dirty(old_pmd))
+				folio_set_dirty(folio);
+			if (!folio_test_referenced(folio) && pmd_young(old_pmd))
+				folio_set_referenced(folio);
+			folio_remove_rmap_pmd(folio, page, vma);
+			folio_put(folio);
 		}
 		add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR);
 		return;
@@ -2194,16 +2497,18 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		uffd_wp = pmd_swp_uffd_wp(old_pmd);
 	} else {
 		page = pmd_page(old_pmd);
+		folio = page_folio(page);
 		if (pmd_dirty(old_pmd)) {
 			dirty = true;
-			SetPageDirty(page);
+			folio_set_dirty(folio);
 		}
 		write = pmd_write(old_pmd);
 		young = pmd_young(old_pmd);
 		soft_dirty = pmd_soft_dirty(old_pmd);
 		uffd_wp = pmd_uffd_wp(old_pmd);
 
-		VM_BUG_ON_PAGE(!page_count(page), page);
+		VM_WARN_ON_FOLIO(!folio_ref_count(folio), folio);
+		VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
 
 		/*
 		 * Without "freeze", we'll simply split the PMD, propagating the
@@ -2218,13 +2523,21 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		 * In case we cannot clear PageAnonExclusive(), split the PMD
 		 * only and let try_to_migrate_one() fail later.
 		 *
-		 * See page_try_share_anon_rmap(): invalidate PMD first.
+		 * See folio_try_share_anon_rmap_pmd(): invalidate PMD first.
 		 */
-		anon_exclusive = PageAnon(page) && PageAnonExclusive(page);
-		if (freeze && anon_exclusive && page_try_share_anon_rmap(page))
+		anon_exclusive = PageAnonExclusive(page);
+		if (freeze && anon_exclusive &&
+		    folio_try_share_anon_rmap_pmd(folio, page))
 			freeze = false;
-		if (!freeze)
-			page_ref_add(page, HPAGE_PMD_NR - 1);
+		if (!freeze) {
+			rmap_t rmap_flags = RMAP_NONE;
+
+			folio_ref_add(folio, HPAGE_PMD_NR - 1);
+			if (anon_exclusive)
+				rmap_flags |= RMAP_EXCLUSIVE;
+			folio_add_anon_rmap_ptes(folio, page, HPAGE_PMD_NR,
+						 vma, haddr, rmap_flags);
+		}
 	}
 
 	/*
@@ -2267,8 +2580,6 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 			entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot));
 			if (write)
 				entry = pte_mkwrite(entry, vma);
-			if (anon_exclusive)
-				SetPageAnonExclusive(page + i);
 			if (!young)
 				entry = pte_mkold(entry);
 			/* NOTE: this may set soft-dirty too on some archs */
@@ -2278,7 +2589,6 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 				entry = pte_mksoft_dirty(entry);
 			if (uffd_wp)
 				entry = pte_mkuffd_wp(entry);
-			page_add_anon_rmap(page + i, vma, addr, RMAP_NONE);
 		}
 		VM_BUG_ON(!pte_none(ptep_get(pte)));
 		set_pte_at(mm, addr, pte, entry);
@@ -2287,7 +2597,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	pte_unmap(pte - 1);
 
 	if (!pmd_migration)
-		page_remove_rmap(page, vma, true);
+		folio_remove_rmap_pmd(folio, page, vma);
 	if (freeze)
 		put_page(page);
 
@@ -2379,7 +2689,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
 static void unmap_folio(struct folio *folio)
 {
 	enum ttu_flags ttu_flags = TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD |
-		TTU_SYNC;
+		TTU_SYNC | TTU_BATCH_FLUSH;
 
 	VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
 
@@ -2392,6 +2702,8 @@ static void unmap_folio(struct folio *folio)
 		try_to_migrate(folio, ttu_flags);
 	else
 		try_to_unmap(folio, ttu_flags | TTU_IGNORE_MLOCK);
+
+	try_to_unmap_flush();
 }
 
 static void remap_page(struct folio *folio, unsigned long nr)
@@ -2507,13 +2819,13 @@ static void __split_huge_page_tail(struct folio *folio, int tail,
 	clear_compound_head(page_tail);
 
 	/* Finally unfreeze refcount. Additional reference from page cache. */
-	page_ref_unfreeze(page_tail, 1 + (!PageAnon(head) ||
-					  PageSwapCache(head)));
+	page_ref_unfreeze(page_tail, 1 + (!folio_test_anon(folio) ||
+					  folio_test_swapcache(folio)));
 
-	if (page_is_young(head))
-		set_page_young(page_tail);
-	if (page_is_idle(head))
-		set_page_idle(page_tail);
+	if (folio_test_young(folio))
+		folio_set_young(new_folio);
+	if (folio_test_idle(folio))
+		folio_set_idle(new_folio);
 
 	folio_xchg_last_cpupid(new_folio, folio_last_cpupid(folio));
 
@@ -2769,13 +3081,15 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 			int nr = folio_nr_pages(folio);
 
 			xas_split(&xas, folio, folio_order(folio));
-			if (folio_test_swapbacked(folio)) {
-				__lruvec_stat_mod_folio(folio, NR_SHMEM_THPS,
-							-nr);
-			} else {
-				__lruvec_stat_mod_folio(folio, NR_FILE_THPS,
-							-nr);
-				filemap_nr_thps_dec(mapping);
+			if (folio_test_pmd_mappable(folio)) {
+				if (folio_test_swapbacked(folio)) {
+					__lruvec_stat_mod_folio(folio,
+							NR_SHMEM_THPS, -nr);
+				} else {
+					__lruvec_stat_mod_folio(folio,
+							NR_FILE_THPS, -nr);
+					filemap_nr_thps_dec(mapping);
+				}
 			}
 		}
 
@@ -2821,7 +3135,7 @@ void folio_undo_large_rmappable(struct folio *folio)
 	spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
 	if (!list_empty(&folio->_deferred_list)) {
 		ds_queue->split_queue_len--;
-		list_del(&folio->_deferred_list);
+		list_del_init(&folio->_deferred_list);
 	}
 	spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
 }
@@ -3226,6 +3540,7 @@ late_initcall(split_huge_pages_debugfs);
 int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 		struct page *page)
 {
+	struct folio *folio = page_folio(page);
 	struct vm_area_struct *vma = pvmw->vma;
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long address = pvmw->address;
@@ -3240,15 +3555,15 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 	flush_cache_range(vma, address, address + HPAGE_PMD_SIZE);
 	pmdval = pmdp_invalidate(vma, address, pvmw->pmd);
 
-	/* See page_try_share_anon_rmap(): invalidate PMD first. */
-	anon_exclusive = PageAnon(page) && PageAnonExclusive(page);
-	if (anon_exclusive && page_try_share_anon_rmap(page)) {
+	/* See folio_try_share_anon_rmap_pmd(): invalidate PMD first. */
+	anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(page);
+	if (anon_exclusive && folio_try_share_anon_rmap_pmd(folio, page)) {
 		set_pmd_at(mm, address, pvmw->pmd, pmdval);
 		return -EBUSY;
 	}
 
 	if (pmd_dirty(pmdval))
-		set_page_dirty(page);
+		folio_set_dirty(folio);
 	if (pmd_write(pmdval))
 		entry = make_writable_migration_entry(page_to_pfn(page));
 	else if (anon_exclusive)
@@ -3265,8 +3580,8 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 	if (pmd_uffd_wp(pmdval))
 		pmdswp = pmd_swp_mkuffd_wp(pmdswp);
 	set_pmd_at(mm, address, pvmw->pmd, pmdswp);
-	page_remove_rmap(page, vma, true);
-	put_page(page);
+	folio_remove_rmap_pmd(folio, page, vma);
+	folio_put(folio);
 	trace_set_migration_pmd(address, pmd_val(pmdswp));
 
 	return 0;
@@ -3274,6 +3589,7 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 
 void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
 {
+	struct folio *folio = page_folio(new);
 	struct vm_area_struct *vma = pvmw->vma;
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long address = pvmw->address;
@@ -3285,7 +3601,7 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
 		return;
 
 	entry = pmd_to_swp_entry(*pvmw->pmd);
-	get_page(new);
+	folio_get(folio);
 	pmde = mk_huge_pmd(new, READ_ONCE(vma->vm_page_prot));
 	if (pmd_swp_soft_dirty(*pvmw->pmd))
 		pmde = pmd_mksoft_dirty(pmde);
@@ -3296,20 +3612,20 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
 	if (!is_migration_entry_young(entry))
 		pmde = pmd_mkold(pmde);
 	/* NOTE: this may contain setting soft-dirty on some archs */
-	if (PageDirty(new) && is_migration_entry_dirty(entry))
+	if (folio_test_dirty(folio) && is_migration_entry_dirty(entry))
 		pmde = pmd_mkdirty(pmde);
 
-	if (PageAnon(new)) {
-		rmap_t rmap_flags = RMAP_COMPOUND;
+	if (folio_test_anon(folio)) {
+		rmap_t rmap_flags = RMAP_NONE;
 
 		if (!is_readable_migration_entry(entry))
 			rmap_flags |= RMAP_EXCLUSIVE;
 
-		page_add_anon_rmap(new, vma, haddr, rmap_flags);
+		folio_add_anon_rmap_pmd(folio, new, vma, haddr, rmap_flags);
 	} else {
-		page_add_file_rmap(new, vma, true);
+		folio_add_file_rmap_pmd(folio, new, vma);
 	}
-	VM_BUG_ON(pmd_write(pmde) && PageAnon(new) && !PageAnonExclusive(new));
+	VM_BUG_ON(pmd_write(pmde) && folio_test_anon(folio) && !PageAnonExclusive(new));
 	set_pmd_at(mm, haddr, pvmw->pmd, pmde);
 
 	/* No need to invalidate - it was non-present before */
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 1169ef2f2176..ed1581b670d4 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1141,7 +1141,7 @@ static inline struct resv_map *inode_resv_map(struct inode *inode)
 	 * The VERY common case is inode->mapping == &inode->i_data but,
 	 * this may not be true for device special inodes.
 	 */
-	return (struct resv_map *)(&inode->i_data)->private_data;
+	return (struct resv_map *)(&inode->i_data)->i_private_data;
 }
 
 static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
@@ -1182,6 +1182,13 @@ static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag)
 	return (get_vma_private_data(vma) & flag) != 0;
 }
 
+bool __vma_private_lock(struct vm_area_struct *vma)
+{
+	return !(vma->vm_flags & VM_MAYSHARE) &&
+		get_vma_private_data(vma) & ~HPAGE_RESV_MASK &&
+		is_vma_resv_set(vma, HPAGE_RESV_OWNER);
+}
+
 void hugetlb_dup_vma_private(struct vm_area_struct *vma)
 {
 	VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
@@ -3403,7 +3410,7 @@ static void __init prep_and_add_bootmem_folios(struct hstate *h,
 
 /*
  * Put bootmem huge pages into the standard lists after mem_map is up.
- * Note: This only applies to gigantic (order > MAX_ORDER) pages.
+ * Note: This only applies to gigantic (order > MAX_PAGE_ORDER) pages.
  */
 static void __init gather_bootmem_prealloc(void)
 {
@@ -4783,7 +4790,7 @@ static int __init default_hugepagesz_setup(char *s)
 	 * The number of default huge pages (for this size) could have been
 	 * specified as the first hugetlb parameter: hugepages=X.  If so,
 	 * then default_hstate_max_huge_pages is set.  If the default huge
-	 * page size is gigantic (> MAX_ORDER), then the pages must be
+	 * page size is gigantic (> MAX_PAGE_ORDER), then the pages must be
 	 * allocated here from bootmem allocator.
 	 */
 	if (default_hstate_max_huge_pages) {
@@ -5278,7 +5285,7 @@ hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long add
 	pte_t newpte = make_huge_pte(vma, &new_folio->page, 1);
 
 	__folio_mark_uptodate(new_folio);
-	hugepage_add_new_anon_rmap(new_folio, vma, addr);
+	hugetlb_add_new_anon_rmap(new_folio, vma, addr);
 	if (userfaultfd_wp(vma) && huge_pte_uffd_wp(old))
 		newpte = huge_pte_mkuffd_wp(newpte);
 	set_huge_pte_at(vma->vm_mm, addr, ptep, newpte, sz);
@@ -5401,9 +5408,8 @@ again:
 			 * sleep during the process.
 			 */
 			if (!folio_test_anon(pte_folio)) {
-				page_dup_file_rmap(&pte_folio->page, true);
-			} else if (page_try_dup_anon_rmap(&pte_folio->page,
-							  true, src_vma)) {
+				hugetlb_add_file_rmap(pte_folio);
+			} else if (hugetlb_try_dup_anon_rmap(pte_folio, src_vma)) {
 				pte_t src_pte_old = entry;
 				struct folio *new_folio;
 
@@ -5669,7 +5675,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 					make_pte_marker(PTE_MARKER_UFFD_WP),
 					sz);
 		hugetlb_count_sub(pages_per_huge_page(h), mm);
-		page_remove_rmap(page, vma, true);
+		hugetlb_remove_rmap(page_folio(page));
 
 		spin_unlock(ptl);
 		tlb_remove_page_size(tlb, page, huge_page_size(h));
@@ -5980,8 +5986,8 @@ retry_avoidcopy:
 
 		/* Break COW or unshare */
 		huge_ptep_clear_flush(vma, haddr, ptep);
-		page_remove_rmap(&old_folio->page, vma, true);
-		hugepage_add_new_anon_rmap(new_folio, vma, haddr);
+		hugetlb_remove_rmap(old_folio);
+		hugetlb_add_new_anon_rmap(new_folio, vma, haddr);
 		if (huge_pte_uffd_wp(pte))
 			newpte = huge_pte_mkuffd_wp(newpte);
 		set_huge_pte_at(mm, haddr, ptep, newpte, huge_page_size(h));
@@ -6270,9 +6276,9 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 		goto backout;
 
 	if (anon_rmap)
-		hugepage_add_new_anon_rmap(folio, vma, haddr);
+		hugetlb_add_new_anon_rmap(folio, vma, haddr);
 	else
-		page_dup_file_rmap(&folio->page, true);
+		hugetlb_add_file_rmap(folio);
 	new_pte = make_huge_pte(vma, &folio->page, ((vma->vm_flags & VM_WRITE)
 				&& (vma->vm_flags & VM_SHARED)));
 	/*
@@ -6723,9 +6729,9 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
 		goto out_release_unlock;
 
 	if (folio_in_pagecache)
-		page_dup_file_rmap(&folio->page, true);
+		hugetlb_add_file_rmap(folio);
 	else
-		hugepage_add_new_anon_rmap(folio, dst_vma, dst_addr);
+		hugetlb_add_new_anon_rmap(folio, dst_vma, dst_addr);
 
 	/*
 	 * For either: (1) CONTINUE on a non-shared VMA, or (2) UFFDIO_COPY
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 87818ee7f01d..da177e49d956 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -14,6 +14,7 @@
 #include <linux/moduleparam.h>
 #include <linux/bootmem_info.h>
 #include <linux/mmdebug.h>
+#include <linux/pagewalk.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include "hugetlb_vmemmap.h"
@@ -45,21 +46,14 @@ struct vmemmap_remap_walk {
 	unsigned long		flags;
 };
 
-static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start, bool flush)
+static int vmemmap_split_pmd(pmd_t *pmd, struct page *head, unsigned long start,
+			     struct vmemmap_remap_walk *walk)
 {
 	pmd_t __pmd;
 	int i;
 	unsigned long addr = start;
-	struct page *head;
 	pte_t *pgtable;
 
-	spin_lock(&init_mm.page_table_lock);
-	head = pmd_leaf(*pmd) ? pmd_page(*pmd) : NULL;
-	spin_unlock(&init_mm.page_table_lock);
-
-	if (!head)
-		return 0;
-
 	pgtable = pte_alloc_one_kernel(&init_mm);
 	if (!pgtable)
 		return -ENOMEM;
@@ -88,7 +82,7 @@ static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start, bool flush)
 		/* Make pte visible before pmd. See comment in pmd_install(). */
 		smp_wmb();
 		pmd_populate_kernel(&init_mm, pmd, pgtable);
-		if (flush)
+		if (!(walk->flags & VMEMMAP_SPLIT_NO_TLB_FLUSH))
 			flush_tlb_kernel_range(start, start + PMD_SIZE);
 	} else {
 		pte_free_kernel(&init_mm, pgtable);
@@ -98,123 +92,83 @@ static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start, bool flush)
 	return 0;
 }
 
-static void vmemmap_pte_range(pmd_t *pmd, unsigned long addr,
-			      unsigned long end,
-			      struct vmemmap_remap_walk *walk)
+static int vmemmap_pmd_entry(pmd_t *pmd, unsigned long addr,
+			     unsigned long next, struct mm_walk *walk)
 {
-	pte_t *pte = pte_offset_kernel(pmd, addr);
+	int ret = 0;
+	struct page *head;
+	struct vmemmap_remap_walk *vmemmap_walk = walk->private;
+
+	/* Only splitting, not remapping the vmemmap pages. */
+	if (!vmemmap_walk->remap_pte)
+		walk->action = ACTION_CONTINUE;
 
+	spin_lock(&init_mm.page_table_lock);
+	head = pmd_leaf(*pmd) ? pmd_page(*pmd) : NULL;
 	/*
-	 * The reuse_page is found 'first' in table walk before we start
-	 * remapping (which is calling @walk->remap_pte).
+	 * Due to HugeTLB alignment requirements and the vmemmap
+	 * pages being at the start of the hotplugged memory
+	 * region in memory_hotplug.memmap_on_memory case. Checking
+	 * the vmemmap page associated with the first vmemmap page
+	 * if it is self-hosted is sufficient.
+	 *
+	 * [                  hotplugged memory                  ]
+	 * [        section        ][...][        section        ]
+	 * [ vmemmap ][              usable memory               ]
+	 *   ^  | ^                        |
+	 *   +--+ |                        |
+	 *        +------------------------+
 	 */
-	if (!walk->reuse_page) {
-		walk->reuse_page = pte_page(ptep_get(pte));
-		/*
-		 * Because the reuse address is part of the range that we are
-		 * walking, skip the reuse address range.
-		 */
-		addr += PAGE_SIZE;
-		pte++;
-		walk->nr_walked++;
-	}
+	if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG) && unlikely(!vmemmap_walk->nr_walked)) {
+		struct page *page = head ? head + pte_index(addr) :
+				    pte_page(ptep_get(pte_offset_kernel(pmd, addr)));
 
-	for (; addr != end; addr += PAGE_SIZE, pte++) {
-		walk->remap_pte(pte, addr, walk);
-		walk->nr_walked++;
+		if (PageVmemmapSelfHosted(page))
+			ret = -ENOTSUPP;
 	}
-}
-
-static int vmemmap_pmd_range(pud_t *pud, unsigned long addr,
-			     unsigned long end,
-			     struct vmemmap_remap_walk *walk)
-{
-	pmd_t *pmd;
-	unsigned long next;
-
-	pmd = pmd_offset(pud, addr);
-	do {
-		int ret;
-
-		ret = split_vmemmap_huge_pmd(pmd, addr & PMD_MASK,
-				!(walk->flags & VMEMMAP_SPLIT_NO_TLB_FLUSH));
-		if (ret)
-			return ret;
-
-		next = pmd_addr_end(addr, end);
-
-		/*
-		 * We are only splitting, not remapping the hugetlb vmemmap
-		 * pages.
-		 */
-		if (!walk->remap_pte)
-			continue;
-
-		vmemmap_pte_range(pmd, addr, next, walk);
-	} while (pmd++, addr = next, addr != end);
+	spin_unlock(&init_mm.page_table_lock);
+	if (!head || ret)
+		return ret;
 
-	return 0;
+	return vmemmap_split_pmd(pmd, head, addr & PMD_MASK, vmemmap_walk);
 }
 
-static int vmemmap_pud_range(p4d_t *p4d, unsigned long addr,
-			     unsigned long end,
-			     struct vmemmap_remap_walk *walk)
+static int vmemmap_pte_entry(pte_t *pte, unsigned long addr,
+			     unsigned long next, struct mm_walk *walk)
 {
-	pud_t *pud;
-	unsigned long next;
+	struct vmemmap_remap_walk *vmemmap_walk = walk->private;
 
-	pud = pud_offset(p4d, addr);
-	do {
-		int ret;
-
-		next = pud_addr_end(addr, end);
-		ret = vmemmap_pmd_range(pud, addr, next, walk);
-		if (ret)
-			return ret;
-	} while (pud++, addr = next, addr != end);
+	/*
+	 * The reuse_page is found 'first' in page table walking before
+	 * starting remapping.
+	 */
+	if (!vmemmap_walk->reuse_page)
+		vmemmap_walk->reuse_page = pte_page(ptep_get(pte));
+	else
+		vmemmap_walk->remap_pte(pte, addr, vmemmap_walk);
+	vmemmap_walk->nr_walked++;
 
 	return 0;
 }
 
-static int vmemmap_p4d_range(pgd_t *pgd, unsigned long addr,
-			     unsigned long end,
-			     struct vmemmap_remap_walk *walk)
-{
-	p4d_t *p4d;
-	unsigned long next;
-
-	p4d = p4d_offset(pgd, addr);
-	do {
-		int ret;
-
-		next = p4d_addr_end(addr, end);
-		ret = vmemmap_pud_range(p4d, addr, next, walk);
-		if (ret)
-			return ret;
-	} while (p4d++, addr = next, addr != end);
-
-	return 0;
-}
+static const struct mm_walk_ops vmemmap_remap_ops = {
+	.pmd_entry	= vmemmap_pmd_entry,
+	.pte_entry	= vmemmap_pte_entry,
+};
 
 static int vmemmap_remap_range(unsigned long start, unsigned long end,
 			       struct vmemmap_remap_walk *walk)
 {
-	unsigned long addr = start;
-	unsigned long next;
-	pgd_t *pgd;
-
-	VM_BUG_ON(!PAGE_ALIGNED(start));
-	VM_BUG_ON(!PAGE_ALIGNED(end));
+	int ret;
 
-	pgd = pgd_offset_k(addr);
-	do {
-		int ret;
+	VM_BUG_ON(!PAGE_ALIGNED(start | end));
 
-		next = pgd_addr_end(addr, end);
-		ret = vmemmap_p4d_range(pgd, addr, next, walk);
-		if (ret)
-			return ret;
-	} while (pgd++, addr = next, addr != end);
+	mmap_read_lock(&init_mm);
+	ret = walk_page_range_novma(&init_mm, start, end, &vmemmap_remap_ops,
+				    NULL, walk);
+	mmap_read_unlock(&init_mm);
+	if (ret)
+		return ret;
 
 	if (walk->remap_pte && !(walk->flags & VMEMMAP_REMAP_NO_TLB_FLUSH))
 		flush_tlb_kernel_range(start, end);
@@ -328,9 +282,8 @@ static void vmemmap_restore_pte(pte_t *pte, unsigned long addr,
  * Return: %0 on success, negative error code otherwise.
  */
 static int vmemmap_remap_split(unsigned long start, unsigned long end,
-				unsigned long reuse)
+			       unsigned long reuse)
 {
-	int ret;
 	struct vmemmap_remap_walk walk = {
 		.remap_pte	= NULL,
 		.flags		= VMEMMAP_SPLIT_NO_TLB_FLUSH,
@@ -339,11 +292,7 @@ static int vmemmap_remap_split(unsigned long start, unsigned long end,
 	/* See the comment in the vmemmap_remap_free(). */
 	BUG_ON(start - reuse != PAGE_SIZE);
 
-	mmap_read_lock(&init_mm);
-	ret = vmemmap_remap_range(reuse, end, &walk);
-	mmap_read_unlock(&init_mm);
-
-	return ret;
+	return vmemmap_remap_range(reuse, end, &walk);
 }
 
 /**
@@ -406,7 +355,6 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end,
 	 */
 	BUG_ON(start - reuse != PAGE_SIZE);
 
-	mmap_read_lock(&init_mm);
 	ret = vmemmap_remap_range(reuse, end, &walk);
 	if (ret && walk.nr_walked) {
 		end = reuse + walk.nr_walked * PAGE_SIZE;
@@ -425,7 +373,6 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end,
 
 		vmemmap_remap_range(reuse, end, &walk);
 	}
-	mmap_read_unlock(&init_mm);
 
 	return ret;
 }
@@ -482,11 +429,7 @@ static int vmemmap_remap_alloc(unsigned long start, unsigned long end,
 	if (alloc_vmemmap_page_list(start, end, &vmemmap_pages))
 		return -ENOMEM;
 
-	mmap_read_lock(&init_mm);
-	vmemmap_remap_range(reuse, end, &walk);
-	mmap_read_unlock(&init_mm);
-
-	return 0;
+	return vmemmap_remap_range(reuse, end, &walk);
 }
 
 DEFINE_STATIC_KEY_FALSE(hugetlb_optimize_vmemmap_key);
@@ -495,14 +438,14 @@ EXPORT_SYMBOL(hugetlb_optimize_vmemmap_key);
 static bool vmemmap_optimize_enabled = IS_ENABLED(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON);
 core_param(hugetlb_free_vmemmap, vmemmap_optimize_enabled, bool, 0);
 
-static int __hugetlb_vmemmap_restore_folio(const struct hstate *h, struct folio *folio, unsigned long flags)
+static int __hugetlb_vmemmap_restore_folio(const struct hstate *h,
+					   struct folio *folio, unsigned long flags)
 {
 	int ret;
-	struct page *head = &folio->page;
-	unsigned long vmemmap_start = (unsigned long)head, vmemmap_end;
+	unsigned long vmemmap_start = (unsigned long)&folio->page, vmemmap_end;
 	unsigned long vmemmap_reuse;
 
-	VM_WARN_ON_ONCE(!PageHuge(head));
+	VM_WARN_ON_ONCE_FOLIO(!folio_test_hugetlb(folio), folio);
 	if (!folio_test_hugetlb_vmemmap_optimized(folio))
 		return 0;
 
@@ -565,7 +508,7 @@ long hugetlb_vmemmap_restore_folios(const struct hstate *h,
 	list_for_each_entry_safe(folio, t_folio, folio_list, lru) {
 		if (folio_test_hugetlb_vmemmap_optimized(folio)) {
 			ret = __hugetlb_vmemmap_restore_folio(h, folio,
-						VMEMMAP_REMAP_NO_TLB_FLUSH);
+							      VMEMMAP_REMAP_NO_TLB_FLUSH);
 			if (ret)
 				break;
 			restored++;
@@ -583,9 +526,9 @@ long hugetlb_vmemmap_restore_folios(const struct hstate *h,
 }
 
 /* Return true iff a HugeTLB whose vmemmap should and can be optimized. */
-static bool vmemmap_should_optimize(const struct hstate *h, const struct page *head)
+static bool vmemmap_should_optimize_folio(const struct hstate *h, struct folio *folio)
 {
-	if (HPageVmemmapOptimized((struct page *)head))
+	if (folio_test_hugetlb_vmemmap_optimized(folio))
 		return false;
 
 	if (!READ_ONCE(vmemmap_optimize_enabled))
@@ -594,65 +537,20 @@ static bool vmemmap_should_optimize(const struct hstate *h, const struct page *h
 	if (!hugetlb_vmemmap_optimizable(h))
 		return false;
 
-	if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) {
-		pmd_t *pmdp, pmd;
-		struct page *vmemmap_page;
-		unsigned long vaddr = (unsigned long)head;
-
-		/*
-		 * Only the vmemmap page's vmemmap page can be self-hosted.
-		 * Walking the page tables to find the backing page of the
-		 * vmemmap page.
-		 */
-		pmdp = pmd_off_k(vaddr);
-		/*
-		 * The READ_ONCE() is used to stabilize *pmdp in a register or
-		 * on the stack so that it will stop changing under the code.
-		 * The only concurrent operation where it can be changed is
-		 * split_vmemmap_huge_pmd() (*pmdp will be stable after this
-		 * operation).
-		 */
-		pmd = READ_ONCE(*pmdp);
-		if (pmd_leaf(pmd))
-			vmemmap_page = pmd_page(pmd) + pte_index(vaddr);
-		else
-			vmemmap_page = pte_page(*pte_offset_kernel(pmdp, vaddr));
-		/*
-		 * Due to HugeTLB alignment requirements and the vmemmap pages
-		 * being at the start of the hotplugged memory region in
-		 * memory_hotplug.memmap_on_memory case. Checking any vmemmap
-		 * page's vmemmap page if it is marked as VmemmapSelfHosted is
-		 * sufficient.
-		 *
-		 * [                  hotplugged memory                  ]
-		 * [        section        ][...][        section        ]
-		 * [ vmemmap ][              usable memory               ]
-		 *   ^   |     |                                        |
-		 *   +---+     |                                        |
-		 *     ^       |                                        |
-		 *     +-------+                                        |
-		 *          ^                                           |
-		 *          +-------------------------------------------+
-		 */
-		if (PageVmemmapSelfHosted(vmemmap_page))
-			return false;
-	}
-
 	return true;
 }
 
 static int __hugetlb_vmemmap_optimize_folio(const struct hstate *h,
-					struct folio *folio,
-					struct list_head *vmemmap_pages,
-					unsigned long flags)
+					    struct folio *folio,
+					    struct list_head *vmemmap_pages,
+					    unsigned long flags)
 {
 	int ret = 0;
-	struct page *head = &folio->page;
-	unsigned long vmemmap_start = (unsigned long)head, vmemmap_end;
+	unsigned long vmemmap_start = (unsigned long)&folio->page, vmemmap_end;
 	unsigned long vmemmap_reuse;
 
-	VM_WARN_ON_ONCE(!PageHuge(head));
-	if (!vmemmap_should_optimize(h, head))
+	VM_WARN_ON_ONCE_FOLIO(!folio_test_hugetlb(folio), folio);
+	if (!vmemmap_should_optimize_folio(h, folio))
 		return ret;
 
 	static_branch_inc(&hugetlb_optimize_vmemmap_key);
@@ -680,7 +578,7 @@ static int __hugetlb_vmemmap_optimize_folio(const struct hstate *h,
 	 * the caller.
 	 */
 	ret = vmemmap_remap_free(vmemmap_start, vmemmap_end, vmemmap_reuse,
-							vmemmap_pages, flags);
+				 vmemmap_pages, flags);
 	if (ret) {
 		static_branch_dec(&hugetlb_optimize_vmemmap_key);
 		folio_clear_hugetlb_vmemmap_optimized(folio);
@@ -707,12 +605,12 @@ void hugetlb_vmemmap_optimize_folio(const struct hstate *h, struct folio *folio)
 	free_vmemmap_page_list(&vmemmap_pages);
 }
 
-static int hugetlb_vmemmap_split(const struct hstate *h, struct page *head)
+static int hugetlb_vmemmap_split_folio(const struct hstate *h, struct folio *folio)
 {
-	unsigned long vmemmap_start = (unsigned long)head, vmemmap_end;
+	unsigned long vmemmap_start = (unsigned long)&folio->page, vmemmap_end;
 	unsigned long vmemmap_reuse;
 
-	if (!vmemmap_should_optimize(h, head))
+	if (!vmemmap_should_optimize_folio(h, folio))
 		return 0;
 
 	vmemmap_end	= vmemmap_start + hugetlb_vmemmap_size(h);
@@ -732,7 +630,7 @@ void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_l
 	LIST_HEAD(vmemmap_pages);
 
 	list_for_each_entry(folio, folio_list, lru) {
-		int ret = hugetlb_vmemmap_split(h, &folio->page);
+		int ret = hugetlb_vmemmap_split_folio(h, folio);
 
 		/*
 		 * Spliting the PMD requires allocating a page, thus lets fail
@@ -747,9 +645,10 @@ void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_l
 	flush_tlb_all();
 
 	list_for_each_entry(folio, folio_list, lru) {
-		int ret = __hugetlb_vmemmap_optimize_folio(h, folio,
-						&vmemmap_pages,
-						VMEMMAP_REMAP_NO_TLB_FLUSH);
+		int ret;
+
+		ret = __hugetlb_vmemmap_optimize_folio(h, folio, &vmemmap_pages,
+						       VMEMMAP_REMAP_NO_TLB_FLUSH);
 
 		/*
 		 * Pages to be freed may have been accumulated.  If we
@@ -763,9 +662,8 @@ void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_l
 			flush_tlb_all();
 			free_vmemmap_page_list(&vmemmap_pages);
 			INIT_LIST_HEAD(&vmemmap_pages);
-			__hugetlb_vmemmap_optimize_folio(h, folio,
-						&vmemmap_pages,
-						VMEMMAP_REMAP_NO_TLB_FLUSH);
+			__hugetlb_vmemmap_optimize_folio(h, folio, &vmemmap_pages,
+							 VMEMMAP_REMAP_NO_TLB_FLUSH);
 		}
 	}
 
diff --git a/mm/internal.h b/mm/internal.h
index b61034bd50f5..f309a010d50f 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -54,12 +54,12 @@ void page_writeback_init(void);
 
 /*
  * If a 16GB hugetlb folio were mapped by PTEs of all of its 4kB pages,
- * its nr_pages_mapped would be 0x400000: choose the COMPOUND_MAPPED bit
+ * its nr_pages_mapped would be 0x400000: choose the ENTIRELY_MAPPED bit
  * above that range, instead of 2*(PMD_SIZE/PAGE_SIZE).  Hugetlb currently
  * leaves nr_pages_mapped at 0, but avoid surprise if it participates later.
  */
-#define COMPOUND_MAPPED		0x800000
-#define FOLIO_PAGES_MAPPED	(COMPOUND_MAPPED - 1)
+#define ENTIRELY_MAPPED		0x800000
+#define FOLIO_PAGES_MAPPED	(ENTIRELY_MAPPED - 1)
 
 /*
  * Flags passed to __show_mem() and show_free_areas() to suppress output in
@@ -138,7 +138,7 @@ void filemap_free_folio(struct address_space *mapping, struct folio *folio);
 int truncate_inode_folio(struct address_space *mapping, struct folio *folio);
 bool truncate_inode_partial_folio(struct folio *folio, loff_t start,
 		loff_t end);
-long invalidate_inode_page(struct page *page);
+long mapping_evict_folio(struct address_space *mapping, struct folio *folio);
 unsigned long mapping_try_invalidate(struct address_space *mapping,
 		pgoff_t start, pgoff_t end, unsigned long *nr_failed);
 
@@ -335,7 +335,7 @@ static inline bool page_is_buddy(struct page *page, struct page *buddy,
  * satisfies the following equation:
  *     P = B & ~(1 << O)
  *
- * Assumption: *_mem_map is contiguous at least up to MAX_ORDER
+ * Assumption: *_mem_map is contiguous at least up to MAX_PAGE_ORDER
  */
 static inline unsigned long
 __find_buddy_pfn(unsigned long page_pfn, unsigned int order)
@@ -616,7 +616,7 @@ folio_within_range(struct folio *folio, struct vm_area_struct *vma,
 		unsigned long start, unsigned long end)
 {
 	pgoff_t pgoff, addr;
-	unsigned long vma_pglen = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	unsigned long vma_pglen = vma_pages(vma);
 
 	VM_WARN_ON_FOLIO(folio_test_ksm(folio), folio);
 	if (start > end)
@@ -650,8 +650,8 @@ folio_within_vma(struct folio *folio, struct vm_area_struct *vma)
  * should be called with vma's mmap_lock held for read or write,
  * under page table lock for the pte/pmd being added or removed.
  *
- * mlock is usually called at the end of page_add_*_rmap(), munlock at
- * the end of page_remove_rmap(); but new anon folios are managed by
+ * mlock is usually called at the end of folio_add_*_rmap_*(), munlock at
+ * the end of folio_remove_rmap_*(); but new anon folios are managed by
  * folio_add_lru_vma() calling mlock_new_folio().
  */
 void mlock_folio(struct folio *folio);
@@ -1047,7 +1047,7 @@ enum {
  * * Ordinary GUP: Using the PT lock
  * * GUP-fast and fork(): mm->write_protect_seq
  * * GUP-fast and KSM or temporary unmapping (swap, migration): see
- *    page_try_share_anon_rmap()
+ *    folio_try_share_anon_rmap_*()
  *
  * Must be called with the (sub)page that's actually referenced via the
  * page table entry, which might not necessarily be the head page for a
@@ -1090,7 +1090,7 @@ static inline bool gup_must_unshare(struct vm_area_struct *vma,
 		return is_cow_mapping(vma->vm_flags);
 	}
 
-	/* Paired with a memory barrier in page_try_share_anon_rmap(). */
+	/* Paired with a memory barrier in folio_try_share_anon_rmap_*(). */
 	if (IS_ENABLED(CONFIG_HAVE_FAST_GUP))
 		smp_rmb();
 
@@ -1135,8 +1135,6 @@ static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma)
 static inline void vma_iter_config(struct vma_iterator *vmi,
 		unsigned long index, unsigned long last)
 {
-	MAS_BUG_ON(&vmi->mas, vmi->mas.node != MAS_START &&
-		   (vmi->mas.index > index || vmi->mas.last < index));
 	__mas_set_range(&vmi->mas, index, last - 1);
 }
 
@@ -1154,17 +1152,6 @@ static inline void vma_iter_clear(struct vma_iterator *vmi)
 	mas_store_prealloc(&vmi->mas, NULL);
 }
 
-static inline int vma_iter_clear_gfp(struct vma_iterator *vmi,
-			unsigned long start, unsigned long end, gfp_t gfp)
-{
-	__mas_set_range(&vmi->mas, start, end - 1);
-	mas_store_gfp(&vmi->mas, NULL, gfp);
-	if (unlikely(mas_is_err(&vmi->mas)))
-		return -ENOMEM;
-
-	return 0;
-}
-
 static inline struct vm_area_struct *vma_iter_load(struct vma_iterator *vmi)
 {
 	return mas_walk(&vmi->mas);
@@ -1176,13 +1163,13 @@ static inline void vma_iter_store(struct vma_iterator *vmi,
 {
 
 #if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
-	if (MAS_WARN_ON(&vmi->mas, vmi->mas.node != MAS_START &&
+	if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start &&
 			vmi->mas.index > vma->vm_start)) {
 		pr_warn("%lx > %lx\n store vma %lx-%lx\n into slot %lx-%lx\n",
 			vmi->mas.index, vma->vm_start, vma->vm_start,
 			vma->vm_end, vmi->mas.index, vmi->mas.last);
 	}
-	if (MAS_WARN_ON(&vmi->mas, vmi->mas.node != MAS_START &&
+	if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start &&
 			vmi->mas.last <  vma->vm_start)) {
 		pr_warn("%lx < %lx\nstore vma %lx-%lx\ninto slot %lx-%lx\n",
 		       vmi->mas.last, vma->vm_start, vma->vm_start, vma->vm_end,
@@ -1190,7 +1177,7 @@ static inline void vma_iter_store(struct vma_iterator *vmi,
 	}
 #endif
 
-	if (vmi->mas.node != MAS_START &&
+	if (vmi->mas.status != ma_start &&
 	    ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start)))
 		vma_iter_invalidate(vmi);
 
@@ -1201,7 +1188,7 @@ static inline void vma_iter_store(struct vma_iterator *vmi,
 static inline int vma_iter_store_gfp(struct vma_iterator *vmi,
 			struct vm_area_struct *vma, gfp_t gfp)
 {
-	if (vmi->mas.node != MAS_START &&
+	if (vmi->mas.status != ma_start &&
 	    ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start)))
 		vma_iter_invalidate(vmi);
 
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 256930da578a..610efae91220 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -20,8 +20,10 @@
 #include <linux/module.h>
 #include <linux/printk.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/sched/task_stack.h>
 #include <linux/slab.h>
+#include <linux/stackdepot.h>
 #include <linux/stacktrace.h>
 #include <linux/string.h>
 #include <linux/types.h>
@@ -37,19 +39,35 @@ struct slab *kasan_addr_to_slab(const void *addr)
 	return NULL;
 }
 
-depot_stack_handle_t kasan_save_stack(gfp_t flags, bool can_alloc)
+depot_stack_handle_t kasan_save_stack(gfp_t flags, depot_flags_t depot_flags)
 {
 	unsigned long entries[KASAN_STACK_DEPTH];
 	unsigned int nr_entries;
 
 	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0);
-	return __stack_depot_save(entries, nr_entries, flags, can_alloc);
+	return stack_depot_save_flags(entries, nr_entries, flags, depot_flags);
 }
 
-void kasan_set_track(struct kasan_track *track, gfp_t flags)
+void kasan_set_track(struct kasan_track *track, depot_stack_handle_t stack)
 {
+#ifdef CONFIG_KASAN_EXTRA_INFO
+	u32 cpu = raw_smp_processor_id();
+	u64 ts_nsec = local_clock();
+
+	track->cpu = cpu;
+	track->timestamp = ts_nsec >> 3;
+#endif /* CONFIG_KASAN_EXTRA_INFO */
 	track->pid = current->pid;
-	track->stack = kasan_save_stack(flags, true);
+	track->stack = stack;
+}
+
+void kasan_save_track(struct kasan_track *track, gfp_t flags)
+{
+	depot_stack_handle_t stack;
+
+	stack = kasan_save_stack(flags,
+			STACK_DEPOT_FLAG_CAN_ALLOC | STACK_DEPOT_FLAG_GET);
+	kasan_set_track(track, stack);
 }
 
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
@@ -69,6 +87,9 @@ EXPORT_SYMBOL(kasan_disable_current);
 
 void __kasan_unpoison_range(const void *address, size_t size)
 {
+	if (is_kfence_address(address))
+		return;
+
 	kasan_unpoison(address, size, false);
 }
 
@@ -133,12 +154,12 @@ void __kasan_poison_slab(struct slab *slab)
 		     KASAN_SLAB_REDZONE, false);
 }
 
-void __kasan_unpoison_object_data(struct kmem_cache *cache, void *object)
+void __kasan_unpoison_new_object(struct kmem_cache *cache, void *object)
 {
 	kasan_unpoison(object, cache->object_size, false);
 }
 
-void __kasan_poison_object_data(struct kmem_cache *cache, void *object)
+void __kasan_poison_new_object(struct kmem_cache *cache, void *object)
 {
 	kasan_poison(object, round_up(cache->object_size, KASAN_GRANULE_SIZE),
 			KASAN_SLAB_REDZONE, false);
@@ -153,10 +174,6 @@ void __kasan_poison_object_data(struct kmem_cache *cache, void *object)
  * 2. A cache might be SLAB_TYPESAFE_BY_RCU, which means objects can be
  *    accessed after being freed. We preassign tags for objects in these
  *    caches as well.
- * 3. For SLAB allocator we can't preassign tags randomly since the freelist
- *    is stored as an array of indexes instead of a linked list. Assign tags
- *    based on objects indexes, so that objects that are next to each other
- *    get different tags.
  */
 static inline u8 assign_tag(struct kmem_cache *cache,
 					const void *object, bool init)
@@ -171,17 +188,12 @@ static inline u8 assign_tag(struct kmem_cache *cache,
 	if (!cache->ctor && !(cache->flags & SLAB_TYPESAFE_BY_RCU))
 		return init ? KASAN_TAG_KERNEL : kasan_random_tag();
 
-	/* For caches that either have a constructor or SLAB_TYPESAFE_BY_RCU: */
-#ifdef CONFIG_SLAB
-	/* For SLAB assign tags based on the object index in the freelist. */
-	return (u8)obj_to_index(cache, virt_to_slab(object), (void *)object);
-#else
 	/*
-	 * For SLUB assign a random tag during slab creation, otherwise reuse
+	 * For caches that either have a constructor or SLAB_TYPESAFE_BY_RCU,
+	 * assign a random tag during slab creation, otherwise reuse
 	 * the already assigned tag.
 	 */
 	return init ? kasan_random_tag() : get_tag(object);
-#endif
 }
 
 void * __must_check __kasan_init_slab_obj(struct kmem_cache *cache,
@@ -197,8 +209,8 @@ void * __must_check __kasan_init_slab_obj(struct kmem_cache *cache,
 	return (void *)object;
 }
 
-static inline bool ____kasan_slab_free(struct kmem_cache *cache, void *object,
-				unsigned long ip, bool quarantine, bool init)
+static inline bool poison_slab_object(struct kmem_cache *cache, void *object,
+				      unsigned long ip, bool init)
 {
 	void *tagged_object;
 
@@ -208,16 +220,12 @@ static inline bool ____kasan_slab_free(struct kmem_cache *cache, void *object,
 	tagged_object = object;
 	object = kasan_reset_tag(object);
 
-	if (is_kfence_address(object))
-		return false;
-
-	if (unlikely(nearest_obj(cache, virt_to_slab(object), object) !=
-	    object)) {
+	if (unlikely(nearest_obj(cache, virt_to_slab(object), object) != object)) {
 		kasan_report_invalid_free(tagged_object, ip, KASAN_REPORT_INVALID_FREE);
 		return true;
 	}
 
-	/* RCU slabs could be legally used after free within the RCU period */
+	/* RCU slabs could be legally used after free within the RCU period. */
 	if (unlikely(cache->flags & SLAB_TYPESAFE_BY_RCU))
 		return false;
 
@@ -229,22 +237,45 @@ static inline bool ____kasan_slab_free(struct kmem_cache *cache, void *object,
 	kasan_poison(object, round_up(cache->object_size, KASAN_GRANULE_SIZE),
 			KASAN_SLAB_FREE, init);
 
-	if ((IS_ENABLED(CONFIG_KASAN_GENERIC) && !quarantine))
-		return false;
-
 	if (kasan_stack_collection_enabled())
 		kasan_save_free_info(cache, tagged_object);
 
-	return kasan_quarantine_put(cache, object);
+	return false;
 }
 
 bool __kasan_slab_free(struct kmem_cache *cache, void *object,
 				unsigned long ip, bool init)
 {
-	return ____kasan_slab_free(cache, object, ip, true, init);
+	if (is_kfence_address(object))
+		return false;
+
+	/*
+	 * If the object is buggy, do not let slab put the object onto the
+	 * freelist. The object will thus never be allocated again and its
+	 * metadata will never get released.
+	 */
+	if (poison_slab_object(cache, object, ip, init))
+		return true;
+
+	/*
+	 * If the object is put into quarantine, do not let slab put the object
+	 * onto the freelist for now. The object's metadata is kept until the
+	 * object gets evicted from quarantine.
+	 */
+	if (kasan_quarantine_put(cache, object))
+		return true;
+
+	/*
+	 * If the object is not put into quarantine, it will likely be quickly
+	 * reallocated. Thus, release its metadata now.
+	 */
+	kasan_release_object_meta(cache, object);
+
+	/* Let slab put the object onto the freelist. */
+	return false;
 }
 
-static inline bool ____kasan_kfree_large(void *ptr, unsigned long ip)
+static inline bool check_page_allocation(void *ptr, unsigned long ip)
 {
 	if (!kasan_arch_is_ready())
 		return false;
@@ -259,40 +290,28 @@ static inline bool ____kasan_kfree_large(void *ptr, unsigned long ip)
 		return true;
 	}
 
-	/*
-	 * The object will be poisoned by kasan_poison_pages() or
-	 * kasan_slab_free_mempool().
-	 */
-
 	return false;
 }
 
 void __kasan_kfree_large(void *ptr, unsigned long ip)
 {
-	____kasan_kfree_large(ptr, ip);
+	check_page_allocation(ptr, ip);
+
+	/* The object will be poisoned by kasan_poison_pages(). */
 }
 
-void __kasan_slab_free_mempool(void *ptr, unsigned long ip)
+static inline void unpoison_slab_object(struct kmem_cache *cache, void *object,
+					gfp_t flags, bool init)
 {
-	struct folio *folio;
-
-	folio = virt_to_folio(ptr);
-
 	/*
-	 * Even though this function is only called for kmem_cache_alloc and
-	 * kmalloc backed mempool allocations, those allocations can still be
-	 * !PageSlab() when the size provided to kmalloc is larger than
-	 * KMALLOC_MAX_SIZE, and kmalloc falls back onto page_alloc.
+	 * Unpoison the whole object. For kmalloc() allocations,
+	 * poison_kmalloc_redzone() will do precise poisoning.
 	 */
-	if (unlikely(!folio_test_slab(folio))) {
-		if (____kasan_kfree_large(ptr, ip))
-			return;
-		kasan_poison(ptr, folio_size(folio), KASAN_PAGE_FREE, false);
-	} else {
-		struct slab *slab = folio_slab(folio);
+	kasan_unpoison(object, cache->object_size, init);
 
-		____kasan_slab_free(slab->slab_cache, ptr, ip, false, false);
-	}
+	/* Save alloc info (if possible) for non-kmalloc() allocations. */
+	if (kasan_stack_collection_enabled() && !is_kmalloc_cache(cache))
+		kasan_save_alloc_info(cache, object, flags);
 }
 
 void * __must_check __kasan_slab_alloc(struct kmem_cache *cache,
@@ -317,39 +336,18 @@ void * __must_check __kasan_slab_alloc(struct kmem_cache *cache,
 	tag = assign_tag(cache, object, false);
 	tagged_object = set_tag(object, tag);
 
-	/*
-	 * Unpoison the whole object.
-	 * For kmalloc() allocations, kasan_kmalloc() will do precise poisoning.
-	 */
-	kasan_unpoison(tagged_object, cache->object_size, init);
-
-	/* Save alloc info (if possible) for non-kmalloc() allocations. */
-	if (kasan_stack_collection_enabled() && !is_kmalloc_cache(cache))
-		kasan_save_alloc_info(cache, tagged_object, flags);
+	/* Unpoison the object and save alloc info for non-kmalloc() allocations. */
+	unpoison_slab_object(cache, tagged_object, flags, init);
 
 	return tagged_object;
 }
 
-static inline void *____kasan_kmalloc(struct kmem_cache *cache,
+static inline void poison_kmalloc_redzone(struct kmem_cache *cache,
 				const void *object, size_t size, gfp_t flags)
 {
 	unsigned long redzone_start;
 	unsigned long redzone_end;
 
-	if (gfpflags_allow_blocking(flags))
-		kasan_quarantine_reduce();
-
-	if (unlikely(object == NULL))
-		return NULL;
-
-	if (is_kfence_address(kasan_reset_tag(object)))
-		return (void *)object;
-
-	/*
-	 * The object has already been unpoisoned by kasan_slab_alloc() for
-	 * kmalloc() or by kasan_krealloc() for krealloc().
-	 */
-
 	/*
 	 * The redzone has byte-level precision for the generic mode.
 	 * Partially poison the last object granule to cover the unaligned
@@ -373,34 +371,34 @@ static inline void *____kasan_kmalloc(struct kmem_cache *cache,
 	if (kasan_stack_collection_enabled() && is_kmalloc_cache(cache))
 		kasan_save_alloc_info(cache, (void *)object, flags);
 
-	/* Keep the tag that was set by kasan_slab_alloc(). */
-	return (void *)object;
 }
 
 void * __must_check __kasan_kmalloc(struct kmem_cache *cache, const void *object,
 					size_t size, gfp_t flags)
 {
-	return ____kasan_kmalloc(cache, object, size, flags);
+	if (gfpflags_allow_blocking(flags))
+		kasan_quarantine_reduce();
+
+	if (unlikely(object == NULL))
+		return NULL;
+
+	if (is_kfence_address(object))
+		return (void *)object;
+
+	/* The object has already been unpoisoned by kasan_slab_alloc(). */
+	poison_kmalloc_redzone(cache, object, size, flags);
+
+	/* Keep the tag that was set by kasan_slab_alloc(). */
+	return (void *)object;
 }
 EXPORT_SYMBOL(__kasan_kmalloc);
 
-void * __must_check __kasan_kmalloc_large(const void *ptr, size_t size,
+static inline void poison_kmalloc_large_redzone(const void *ptr, size_t size,
 						gfp_t flags)
 {
 	unsigned long redzone_start;
 	unsigned long redzone_end;
 
-	if (gfpflags_allow_blocking(flags))
-		kasan_quarantine_reduce();
-
-	if (unlikely(ptr == NULL))
-		return NULL;
-
-	/*
-	 * The object has already been unpoisoned by kasan_unpoison_pages() for
-	 * alloc_pages() or by kasan_krealloc() for krealloc().
-	 */
-
 	/*
 	 * The redzone has byte-level precision for the generic mode.
 	 * Partially poison the last object granule to cover the unaligned
@@ -410,12 +408,25 @@ void * __must_check __kasan_kmalloc_large(const void *ptr, size_t size,
 		kasan_poison_last_granule(ptr, size);
 
 	/* Poison the aligned part of the redzone. */
-	redzone_start = round_up((unsigned long)(ptr + size),
-				KASAN_GRANULE_SIZE);
+	redzone_start = round_up((unsigned long)(ptr + size), KASAN_GRANULE_SIZE);
 	redzone_end = (unsigned long)ptr + page_size(virt_to_page(ptr));
 	kasan_poison((void *)redzone_start, redzone_end - redzone_start,
 		     KASAN_PAGE_REDZONE, false);
+}
+
+void * __must_check __kasan_kmalloc_large(const void *ptr, size_t size,
+						gfp_t flags)
+{
+	if (gfpflags_allow_blocking(flags))
+		kasan_quarantine_reduce();
+
+	if (unlikely(ptr == NULL))
+		return NULL;
 
+	/* The object has already been unpoisoned by kasan_unpoison_pages(). */
+	poison_kmalloc_large_redzone(ptr, size, flags);
+
+	/* Keep the tag that was set by alloc_pages(). */
 	return (void *)ptr;
 }
 
@@ -423,9 +434,15 @@ void * __must_check __kasan_krealloc(const void *object, size_t size, gfp_t flag
 {
 	struct slab *slab;
 
+	if (gfpflags_allow_blocking(flags))
+		kasan_quarantine_reduce();
+
 	if (unlikely(object == ZERO_SIZE_PTR))
 		return (void *)object;
 
+	if (is_kfence_address(object))
+		return (void *)object;
+
 	/*
 	 * Unpoison the object's data.
 	 * Part of it might already have been unpoisoned, but it's unknown
@@ -437,9 +454,91 @@ void * __must_check __kasan_krealloc(const void *object, size_t size, gfp_t flag
 
 	/* Piggy-back on kmalloc() instrumentation to poison the redzone. */
 	if (unlikely(!slab))
-		return __kasan_kmalloc_large(object, size, flags);
+		poison_kmalloc_large_redzone(object, size, flags);
 	else
-		return ____kasan_kmalloc(slab->slab_cache, object, size, flags);
+		poison_kmalloc_redzone(slab->slab_cache, object, size, flags);
+
+	return (void *)object;
+}
+
+bool __kasan_mempool_poison_pages(struct page *page, unsigned int order,
+				  unsigned long ip)
+{
+	unsigned long *ptr;
+
+	if (unlikely(PageHighMem(page)))
+		return true;
+
+	/* Bail out if allocation was excluded due to sampling. */
+	if (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
+	    page_kasan_tag(page) == KASAN_TAG_KERNEL)
+		return true;
+
+	ptr = page_address(page);
+
+	if (check_page_allocation(ptr, ip))
+		return false;
+
+	kasan_poison(ptr, PAGE_SIZE << order, KASAN_PAGE_FREE, false);
+
+	return true;
+}
+
+void __kasan_mempool_unpoison_pages(struct page *page, unsigned int order,
+				    unsigned long ip)
+{
+	__kasan_unpoison_pages(page, order, false);
+}
+
+bool __kasan_mempool_poison_object(void *ptr, unsigned long ip)
+{
+	struct folio *folio = virt_to_folio(ptr);
+	struct slab *slab;
+
+	/*
+	 * This function can be called for large kmalloc allocation that get
+	 * their memory from page_alloc. Thus, the folio might not be a slab.
+	 */
+	if (unlikely(!folio_test_slab(folio))) {
+		if (check_page_allocation(ptr, ip))
+			return false;
+		kasan_poison(ptr, folio_size(folio), KASAN_PAGE_FREE, false);
+		return true;
+	}
+
+	if (is_kfence_address(ptr))
+		return false;
+
+	slab = folio_slab(folio);
+	return !poison_slab_object(slab->slab_cache, ptr, ip, false);
+}
+
+void __kasan_mempool_unpoison_object(void *ptr, size_t size, unsigned long ip)
+{
+	struct slab *slab;
+	gfp_t flags = 0; /* Might be executing under a lock. */
+
+	slab = virt_to_slab(ptr);
+
+	/*
+	 * This function can be called for large kmalloc allocation that get
+	 * their memory from page_alloc.
+	 */
+	if (unlikely(!slab)) {
+		kasan_unpoison(ptr, size, false);
+		poison_kmalloc_large_redzone(ptr, size, flags);
+		return;
+	}
+
+	if (is_kfence_address(ptr))
+		return;
+
+	/* Unpoison the object and save alloc info for non-kmalloc() allocations. */
+	unpoison_slab_object(slab->slab_cache, ptr, size, flags);
+
+	/* Poison the redzone and save alloc info for kmalloc() allocations. */
+	if (is_kmalloc_cache(slab->slab_cache))
+		poison_kmalloc_redzone(slab->slab_cache, ptr, size, flags);
 }
 
 bool __kasan_check_byte(const void *address, unsigned long ip)
diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c
index 4d837ab83f08..24c13dfb1e94 100644
--- a/mm/kasan/generic.c
+++ b/mm/kasan/generic.c
@@ -25,6 +25,8 @@
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
 #include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stackdepot.h>
 #include <linux/stacktrace.h>
 #include <linux/string.h>
 #include <linux/types.h>
@@ -361,6 +363,8 @@ void kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
 {
 	unsigned int ok_size;
 	unsigned int optimal_size;
+	unsigned int rem_free_meta_size;
+	unsigned int orig_alloc_meta_offset;
 
 	if (!kasan_requires_meta())
 		return;
@@ -378,49 +382,77 @@ void kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
 
 	ok_size = *size;
 
-	/* Add alloc meta into redzone. */
+	/* Add alloc meta into the redzone. */
 	cache->kasan_info.alloc_meta_offset = *size;
 	*size += sizeof(struct kasan_alloc_meta);
 
-	/*
-	 * If alloc meta doesn't fit, don't add it.
-	 * This can only happen with SLAB, as it has KMALLOC_MAX_SIZE equal
-	 * to KMALLOC_MAX_CACHE_SIZE and doesn't fall back to page_alloc for
-	 * larger sizes.
-	 */
+	/* If alloc meta doesn't fit, don't add it. */
 	if (*size > KMALLOC_MAX_SIZE) {
 		cache->kasan_info.alloc_meta_offset = 0;
 		*size = ok_size;
 		/* Continue, since free meta might still fit. */
 	}
 
+	ok_size = *size;
+	orig_alloc_meta_offset = cache->kasan_info.alloc_meta_offset;
+
 	/*
-	 * Add free meta into redzone when it's not possible to store
+	 * Store free meta in the redzone when it's not possible to store
 	 * it in the object. This is the case when:
 	 * 1. Object is SLAB_TYPESAFE_BY_RCU, which means that it can
 	 *    be touched after it was freed, or
 	 * 2. Object has a constructor, which means it's expected to
-	 *    retain its content until the next allocation, or
-	 * 3. Object is too small.
-	 * Otherwise cache->kasan_info.free_meta_offset = 0 is implied.
+	 *    retain its content until the next allocation.
 	 */
-	if ((cache->flags & SLAB_TYPESAFE_BY_RCU) || cache->ctor ||
-	    cache->object_size < sizeof(struct kasan_free_meta)) {
-		ok_size = *size;
-
+	if ((cache->flags & SLAB_TYPESAFE_BY_RCU) || cache->ctor) {
 		cache->kasan_info.free_meta_offset = *size;
 		*size += sizeof(struct kasan_free_meta);
+		goto free_meta_added;
+	}
 
-		/* If free meta doesn't fit, don't add it. */
-		if (*size > KMALLOC_MAX_SIZE) {
-			cache->kasan_info.free_meta_offset = KASAN_NO_FREE_META;
-			*size = ok_size;
-		}
+	/*
+	 * Otherwise, if the object is large enough to contain free meta,
+	 * store it within the object.
+	 */
+	if (sizeof(struct kasan_free_meta) <= cache->object_size) {
+		/* cache->kasan_info.free_meta_offset = 0 is implied. */
+		goto free_meta_added;
+	}
+
+	/*
+	 * For smaller objects, store the beginning of free meta within the
+	 * object and the end in the redzone. And thus shift the location of
+	 * alloc meta to free up space for free meta.
+	 * This is only possible when slub_debug is disabled, as otherwise
+	 * the end of free meta will overlap with slub_debug metadata.
+	 */
+	if (!__slub_debug_enabled()) {
+		rem_free_meta_size = sizeof(struct kasan_free_meta) -
+							cache->object_size;
+		*size += rem_free_meta_size;
+		if (cache->kasan_info.alloc_meta_offset != 0)
+			cache->kasan_info.alloc_meta_offset += rem_free_meta_size;
+		goto free_meta_added;
+	}
+
+	/*
+	 * If the object is small and slub_debug is enabled, store free meta
+	 * in the redzone after alloc meta.
+	 */
+	cache->kasan_info.free_meta_offset = *size;
+	*size += sizeof(struct kasan_free_meta);
+
+free_meta_added:
+	/* If free meta doesn't fit, don't add it. */
+	if (*size > KMALLOC_MAX_SIZE) {
+		cache->kasan_info.free_meta_offset = KASAN_NO_FREE_META;
+		cache->kasan_info.alloc_meta_offset = orig_alloc_meta_offset;
+		*size = ok_size;
 	}
 
 	/* Calculate size with optimal redzone. */
 	optimal_size = cache->object_size + optimal_redzone(cache->object_size);
-	/* Limit it with KMALLOC_MAX_SIZE (relevant for SLAB only). */
+	/* Limit it with KMALLOC_MAX_SIZE. */
 	if (optimal_size > KMALLOC_MAX_SIZE)
 		optimal_size = KMALLOC_MAX_SIZE;
 	/* Use optimal size if the size with added metas is not large enough. */
@@ -450,8 +482,63 @@ void kasan_init_object_meta(struct kmem_cache *cache, const void *object)
 	struct kasan_alloc_meta *alloc_meta;
 
 	alloc_meta = kasan_get_alloc_meta(cache, object);
-	if (alloc_meta)
+	if (alloc_meta) {
+		/* Zero out alloc meta to mark it as invalid. */
 		__memset(alloc_meta, 0, sizeof(*alloc_meta));
+
+		/*
+		 * Temporarily disable KASAN bug reporting to allow instrumented
+		 * raw_spin_lock_init to access aux_lock, which resides inside
+		 * of a redzone.
+		 */
+		kasan_disable_current();
+		raw_spin_lock_init(&alloc_meta->aux_lock);
+		kasan_enable_current();
+	}
+
+	/*
+	 * Explicitly marking free meta as invalid is not required: the shadow
+	 * value for the first 8 bytes of a newly allocated object is not
+	 * KASAN_SLAB_FREE_META.
+	 */
+}
+
+static void release_alloc_meta(struct kasan_alloc_meta *meta)
+{
+	/* Evict the stack traces from stack depot. */
+	stack_depot_put(meta->alloc_track.stack);
+	stack_depot_put(meta->aux_stack[0]);
+	stack_depot_put(meta->aux_stack[1]);
+
+	/* Zero out alloc meta to mark it as invalid. */
+	__memset(meta, 0, sizeof(*meta));
+}
+
+static void release_free_meta(const void *object, struct kasan_free_meta *meta)
+{
+	/* Check if free meta is valid. */
+	if (*(u8 *)kasan_mem_to_shadow(object) != KASAN_SLAB_FREE_META)
+		return;
+
+	/* Evict the stack trace from the stack depot. */
+	stack_depot_put(meta->free_track.stack);
+
+	/* Mark free meta as invalid. */
+	*(u8 *)kasan_mem_to_shadow(object) = KASAN_SLAB_FREE;
+}
+
+void kasan_release_object_meta(struct kmem_cache *cache, const void *object)
+{
+	struct kasan_alloc_meta *alloc_meta;
+	struct kasan_free_meta *free_meta;
+
+	alloc_meta = kasan_get_alloc_meta(cache, object);
+	if (alloc_meta)
+		release_alloc_meta(alloc_meta);
+
+	free_meta = kasan_get_free_meta(cache, object);
+	if (free_meta)
+		release_free_meta(object, free_meta);
 }
 
 size_t kasan_metadata_size(struct kmem_cache *cache, bool in_object)
@@ -472,12 +559,14 @@ size_t kasan_metadata_size(struct kmem_cache *cache, bool in_object)
 			sizeof(struct kasan_free_meta) : 0);
 }
 
-static void __kasan_record_aux_stack(void *addr, bool can_alloc)
+static void __kasan_record_aux_stack(void *addr, depot_flags_t depot_flags)
 {
 	struct slab *slab = kasan_addr_to_slab(addr);
 	struct kmem_cache *cache;
 	struct kasan_alloc_meta *alloc_meta;
 	void *object;
+	depot_stack_handle_t new_handle, old_handle;
+	unsigned long flags;
 
 	if (is_kfence_address(addr) || !slab)
 		return;
@@ -488,18 +577,33 @@ static void __kasan_record_aux_stack(void *addr, bool can_alloc)
 	if (!alloc_meta)
 		return;
 
+	new_handle = kasan_save_stack(0, depot_flags);
+
+	/*
+	 * Temporarily disable KASAN bug reporting to allow instrumented
+	 * spinlock functions to access aux_lock, which resides inside of a
+	 * redzone.
+	 */
+	kasan_disable_current();
+	raw_spin_lock_irqsave(&alloc_meta->aux_lock, flags);
+	old_handle = alloc_meta->aux_stack[1];
 	alloc_meta->aux_stack[1] = alloc_meta->aux_stack[0];
-	alloc_meta->aux_stack[0] = kasan_save_stack(0, can_alloc);
+	alloc_meta->aux_stack[0] = new_handle;
+	raw_spin_unlock_irqrestore(&alloc_meta->aux_lock, flags);
+	kasan_enable_current();
+
+	stack_depot_put(old_handle);
 }
 
 void kasan_record_aux_stack(void *addr)
 {
-	return __kasan_record_aux_stack(addr, true);
+	return __kasan_record_aux_stack(addr,
+			STACK_DEPOT_FLAG_CAN_ALLOC | STACK_DEPOT_FLAG_GET);
 }
 
 void kasan_record_aux_stack_noalloc(void *addr)
 {
-	return __kasan_record_aux_stack(addr, false);
+	return __kasan_record_aux_stack(addr, STACK_DEPOT_FLAG_GET);
 }
 
 void kasan_save_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags)
@@ -507,8 +611,13 @@ void kasan_save_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags)
 	struct kasan_alloc_meta *alloc_meta;
 
 	alloc_meta = kasan_get_alloc_meta(cache, object);
-	if (alloc_meta)
-		kasan_set_track(&alloc_meta->alloc_track, flags);
+	if (!alloc_meta)
+		return;
+
+	/* Evict previous stack traces (might exist for krealloc or mempool). */
+	release_alloc_meta(alloc_meta);
+
+	kasan_save_track(&alloc_meta->alloc_track, flags);
 }
 
 void kasan_save_free_info(struct kmem_cache *cache, void *object)
@@ -519,7 +628,11 @@ void kasan_save_free_info(struct kmem_cache *cache, void *object)
 	if (!free_meta)
 		return;
 
-	kasan_set_track(&free_meta->free_track, 0);
-	/* The object was freed and has free track set. */
-	*(u8 *)kasan_mem_to_shadow(object) = KASAN_SLAB_FREETRACK;
+	/* Evict previous stack trace (might exist for mempool). */
+	release_free_meta(object, free_meta);
+
+	kasan_save_track(&free_meta->free_track, 0);
+
+	/* Mark free meta as valid. */
+	*(u8 *)kasan_mem_to_shadow(object) = KASAN_SLAB_FREE_META;
 }
diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c
index 06141bbc1e51..2b994092a2d4 100644
--- a/mm/kasan/hw_tags.c
+++ b/mm/kasan/hw_tags.c
@@ -57,7 +57,12 @@ enum kasan_mode kasan_mode __ro_after_init;
 EXPORT_SYMBOL_GPL(kasan_mode);
 
 /* Whether to enable vmalloc tagging. */
+#ifdef CONFIG_KASAN_VMALLOC
 DEFINE_STATIC_KEY_TRUE(kasan_flag_vmalloc);
+#else
+DEFINE_STATIC_KEY_FALSE(kasan_flag_vmalloc);
+#endif
+EXPORT_SYMBOL_GPL(kasan_flag_vmalloc);
 
 #define PAGE_ALLOC_SAMPLE_DEFAULT	1
 #define PAGE_ALLOC_SAMPLE_ORDER_DEFAULT	3
@@ -119,6 +124,9 @@ static int __init early_kasan_flag_vmalloc(char *arg)
 	if (!arg)
 		return -EINVAL;
 
+	if (!IS_ENABLED(CONFIG_KASAN_VMALLOC))
+		return 0;
+
 	if (!strcmp(arg, "off"))
 		kasan_arg_vmalloc = KASAN_ARG_VMALLOC_OFF;
 	else if (!strcmp(arg, "on"))
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index 8b06bab5c406..d0f172f2b978 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -6,6 +6,7 @@
 #include <linux/kasan.h>
 #include <linux/kasan-tags.h>
 #include <linux/kfence.h>
+#include <linux/spinlock.h>
 #include <linux/stackdepot.h>
 
 #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
@@ -48,6 +49,7 @@ DECLARE_PER_CPU(long, kasan_page_alloc_skip);
 
 static inline bool kasan_vmalloc_enabled(void)
 {
+	/* Static branch is never enabled with CONFIG_KASAN_VMALLOC disabled. */
 	return static_branch_likely(&kasan_flag_vmalloc);
 }
 
@@ -81,6 +83,11 @@ static inline bool kasan_sample_page_alloc(unsigned int order)
 
 #else /* CONFIG_KASAN_HW_TAGS */
 
+static inline bool kasan_vmalloc_enabled(void)
+{
+	return IS_ENABLED(CONFIG_KASAN_VMALLOC);
+}
+
 static inline bool kasan_async_fault_possible(void)
 {
 	return false;
@@ -100,21 +107,21 @@ static inline bool kasan_sample_page_alloc(unsigned int order)
 
 #ifdef CONFIG_KASAN_GENERIC
 
-/* Generic KASAN uses per-object metadata to store stack traces. */
+/*
+ * Generic KASAN uses per-object metadata to store alloc and free stack traces
+ * and the quarantine link.
+ */
 static inline bool kasan_requires_meta(void)
 {
-	/*
-	 * Technically, Generic KASAN always collects stack traces right now.
-	 * However, let's use kasan_stack_collection_enabled() in case the
-	 * kasan.stacktrace command-line argument is changed to affect
-	 * Generic KASAN.
-	 */
-	return kasan_stack_collection_enabled();
+	return true;
 }
 
 #else /* CONFIG_KASAN_GENERIC */
 
-/* Tag-based KASAN modes do not use per-object metadata. */
+/*
+ * Tag-based KASAN modes do not use per-object metadata: they use the stack
+ * ring to store alloc and free stack traces and do not use qurantine.
+ */
 static inline bool kasan_requires_meta(void)
 {
 	return false;
@@ -149,7 +156,7 @@ static inline bool kasan_requires_meta(void)
 
 #ifdef CONFIG_KASAN_GENERIC
 
-#define KASAN_SLAB_FREETRACK	0xFA  /* freed slab object with free track */
+#define KASAN_SLAB_FREE_META	0xFA  /* freed slab object with free meta */
 #define KASAN_GLOBAL_REDZONE	0xF9  /* redzone for global variable */
 
 /* Stack redzone shadow values. Compiler ABI, do not change. */
@@ -187,6 +194,10 @@ static inline bool kasan_requires_meta(void)
 struct kasan_track {
 	u32 pid;
 	depot_stack_handle_t stack;
+#ifdef CONFIG_KASAN_EXTRA_INFO
+	u64 cpu:20;
+	u64 timestamp:44;
+#endif /* CONFIG_KASAN_EXTRA_INFO */
 };
 
 enum kasan_report_type {
@@ -242,9 +253,25 @@ struct kasan_global {
 
 #ifdef CONFIG_KASAN_GENERIC
 
+/*
+ * Alloc meta contains the allocation-related information about a slab object.
+ * Alloc meta is saved when an object is allocated and is kept until either the
+ * object returns to the slab freelist (leaves quarantine for quarantined
+ * objects or gets freed for the non-quarantined ones) or reallocated via
+ * krealloc or through a mempool.
+ * Alloc meta is stored inside of the object's redzone.
+ * Alloc meta is considered valid whenever it contains non-zero data.
+ */
 struct kasan_alloc_meta {
 	struct kasan_track alloc_track;
 	/* Free track is stored in kasan_free_meta. */
+	/*
+	 * aux_lock protects aux_stack from accesses from concurrent
+	 * kasan_record_aux_stack calls. It is a raw spinlock to avoid sleeping
+	 * on RT kernels, as kasan_record_aux_stack_noalloc can be called from
+	 * non-sleepable contexts.
+	 */
+	raw_spinlock_t aux_lock;
 	depot_stack_handle_t aux_stack[2];
 };
 
@@ -260,8 +287,12 @@ struct qlist_node {
 #define KASAN_NO_FREE_META INT_MAX
 
 /*
- * Free meta is only used by Generic mode while the object is in quarantine.
- * After that, slab allocator stores the freelist pointer in the object.
+ * Free meta contains the freeing-related information about a slab object.
+ * Free meta is only kept for quarantined objects and for mempool objects until
+ * the object gets allocated again.
+ * Free meta is stored within the object's memory.
+ * Free meta is considered valid whenever the value of the shadow byte that
+ * corresponds to the first 8 bytes of the object is KASAN_SLAB_FREE_META.
  */
 struct kasan_free_meta {
 	struct qlist_node quarantine_link;
@@ -275,8 +306,7 @@ struct kasan_free_meta {
 struct kasan_stack_ring_entry {
 	void *ptr;
 	size_t size;
-	u32 pid;
-	depot_stack_handle_t stack;
+	struct kasan_track track;
 	bool is_free;
 };
 
@@ -291,6 +321,12 @@ struct kasan_stack_ring {
 
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 
+static __always_inline bool addr_in_shadow(const void *addr)
+{
+	return addr >= (void *)KASAN_SHADOW_START &&
+		addr < (void *)KASAN_SHADOW_END;
+}
+
 #ifndef kasan_shadow_to_mem
 static inline const void *kasan_shadow_to_mem(const void *shadow_addr)
 {
@@ -357,24 +393,24 @@ void kasan_report_invalid_free(void *object, unsigned long ip, enum kasan_report
 struct slab *kasan_addr_to_slab(const void *addr);
 
 #ifdef CONFIG_KASAN_GENERIC
-void kasan_init_cache_meta(struct kmem_cache *cache, unsigned int *size);
-void kasan_init_object_meta(struct kmem_cache *cache, const void *object);
 struct kasan_alloc_meta *kasan_get_alloc_meta(struct kmem_cache *cache,
 						const void *object);
 struct kasan_free_meta *kasan_get_free_meta(struct kmem_cache *cache,
 						const void *object);
+void kasan_init_object_meta(struct kmem_cache *cache, const void *object);
+void kasan_release_object_meta(struct kmem_cache *cache, const void *object);
 #else
-static inline void kasan_init_cache_meta(struct kmem_cache *cache, unsigned int *size) { }
 static inline void kasan_init_object_meta(struct kmem_cache *cache, const void *object) { }
+static inline void kasan_release_object_meta(struct kmem_cache *cache, const void *object) { }
 #endif
 
-depot_stack_handle_t kasan_save_stack(gfp_t flags, bool can_alloc);
-void kasan_set_track(struct kasan_track *track, gfp_t flags);
+depot_stack_handle_t kasan_save_stack(gfp_t flags, depot_flags_t depot_flags);
+void kasan_set_track(struct kasan_track *track, depot_stack_handle_t stack);
+void kasan_save_track(struct kasan_track *track, gfp_t flags);
 void kasan_save_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags);
 void kasan_save_free_info(struct kmem_cache *cache, void *object);
 
-#if defined(CONFIG_KASAN_GENERIC) && \
-	(defined(CONFIG_SLAB) || defined(CONFIG_SLUB))
+#ifdef CONFIG_KASAN_GENERIC
 bool kasan_quarantine_put(struct kmem_cache *cache, void *object);
 void kasan_quarantine_reduce(void);
 void kasan_quarantine_remove_cache(struct kmem_cache *cache);
@@ -444,35 +480,23 @@ static inline u8 kasan_random_tag(void) { return 0; }
 
 static inline void kasan_poison(const void *addr, size_t size, u8 value, bool init)
 {
-	addr = kasan_reset_tag(addr);
-
-	/* Skip KFENCE memory if called explicitly outside of sl*b. */
-	if (is_kfence_address(addr))
-		return;
-
 	if (WARN_ON((unsigned long)addr & KASAN_GRANULE_MASK))
 		return;
 	if (WARN_ON(size & KASAN_GRANULE_MASK))
 		return;
 
-	hw_set_mem_tag_range((void *)addr, size, value, init);
+	hw_set_mem_tag_range(kasan_reset_tag(addr), size, value, init);
 }
 
 static inline void kasan_unpoison(const void *addr, size_t size, bool init)
 {
 	u8 tag = get_tag(addr);
 
-	addr = kasan_reset_tag(addr);
-
-	/* Skip KFENCE memory if called explicitly outside of sl*b. */
-	if (is_kfence_address(addr))
-		return;
-
 	if (WARN_ON((unsigned long)addr & KASAN_GRANULE_MASK))
 		return;
 	size = round_up(size, KASAN_GRANULE_SIZE);
 
-	hw_set_mem_tag_range((void *)addr, size, tag, init);
+	hw_set_mem_tag_range(kasan_reset_tag(addr), size, tag, init);
 }
 
 static inline bool kasan_byte_accessible(const void *addr)
@@ -491,8 +515,6 @@ static inline bool kasan_byte_accessible(const void *addr)
  * @size - range size, must be aligned to KASAN_GRANULE_SIZE
  * @value - value that's written to metadata for the range
  * @init - whether to initialize the memory range (only for hardware tag-based)
- *
- * The size gets aligned to KASAN_GRANULE_SIZE before marking the range.
  */
 void kasan_poison(const void *addr, size_t size, u8 value, bool init);
 
diff --git a/mm/kasan/kasan_test.c b/mm/kasan/kasan_test.c
index 8281eb42464b..971cfff4ca0b 100644
--- a/mm/kasan/kasan_test.c
+++ b/mm/kasan/kasan_test.c
@@ -13,6 +13,7 @@
 #include <linux/io.h>
 #include <linux/kasan.h>
 #include <linux/kernel.h>
+#include <linux/mempool.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
 #include <linux/module.h>
@@ -213,17 +214,32 @@ static void kmalloc_node_oob_right(struct kunit *test)
 }
 
 /*
- * These kmalloc_pagealloc_* tests try allocating a memory chunk that doesn't
- * fit into a slab cache and therefore is allocated via the page allocator
- * fallback. Since this kind of fallback is only implemented for SLUB, these
- * tests are limited to that allocator.
+ * Check that KASAN detects an out-of-bounds access for a big object allocated
+ * via kmalloc(). But not as big as to trigger the page_alloc fallback.
  */
-static void kmalloc_pagealloc_oob_right(struct kunit *test)
+static void kmalloc_big_oob_right(struct kunit *test)
 {
 	char *ptr;
-	size_t size = KMALLOC_MAX_CACHE_SIZE + 10;
+	size_t size = KMALLOC_MAX_CACHE_SIZE - 256;
+
+	ptr = kmalloc(size, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
+
+	OPTIMIZER_HIDE_VAR(ptr);
+	KUNIT_EXPECT_KASAN_FAIL(test, ptr[size] = 0);
+	kfree(ptr);
+}
 
-	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_SLUB);
+/*
+ * The kmalloc_large_* tests below use kmalloc() to allocate a memory chunk
+ * that does not fit into the largest slab cache and therefore is allocated via
+ * the page_alloc fallback.
+ */
+
+static void kmalloc_large_oob_right(struct kunit *test)
+{
+	char *ptr;
+	size_t size = KMALLOC_MAX_CACHE_SIZE + 10;
 
 	ptr = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
@@ -234,13 +250,11 @@ static void kmalloc_pagealloc_oob_right(struct kunit *test)
 	kfree(ptr);
 }
 
-static void kmalloc_pagealloc_uaf(struct kunit *test)
+static void kmalloc_large_uaf(struct kunit *test)
 {
 	char *ptr;
 	size_t size = KMALLOC_MAX_CACHE_SIZE + 10;
 
-	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_SLUB);
-
 	ptr = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 	kfree(ptr);
@@ -248,20 +262,18 @@ static void kmalloc_pagealloc_uaf(struct kunit *test)
 	KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr)[0]);
 }
 
-static void kmalloc_pagealloc_invalid_free(struct kunit *test)
+static void kmalloc_large_invalid_free(struct kunit *test)
 {
 	char *ptr;
 	size_t size = KMALLOC_MAX_CACHE_SIZE + 10;
 
-	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_SLUB);
-
 	ptr = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 
 	KUNIT_EXPECT_KASAN_FAIL(test, kfree(ptr + 1));
 }
 
-static void pagealloc_oob_right(struct kunit *test)
+static void page_alloc_oob_right(struct kunit *test)
 {
 	char *ptr;
 	struct page *pages;
@@ -283,7 +295,7 @@ static void pagealloc_oob_right(struct kunit *test)
 	free_pages((unsigned long)ptr, order);
 }
 
-static void pagealloc_uaf(struct kunit *test)
+static void page_alloc_uaf(struct kunit *test)
 {
 	char *ptr;
 	struct page *pages;
@@ -297,23 +309,6 @@ static void pagealloc_uaf(struct kunit *test)
 	KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr)[0]);
 }
 
-static void kmalloc_large_oob_right(struct kunit *test)
-{
-	char *ptr;
-	size_t size = KMALLOC_MAX_CACHE_SIZE - 256;
-
-	/*
-	 * Allocate a chunk that is large enough, but still fits into a slab
-	 * and does not trigger the page allocator fallback in SLUB.
-	 */
-	ptr = kmalloc(size, GFP_KERNEL);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
-
-	OPTIMIZER_HIDE_VAR(ptr);
-	KUNIT_EXPECT_KASAN_FAIL(test, ptr[size] = 0);
-	kfree(ptr);
-}
-
 static void krealloc_more_oob_helper(struct kunit *test,
 					size_t size1, size_t size2)
 {
@@ -403,20 +398,14 @@ static void krealloc_less_oob(struct kunit *test)
 	krealloc_less_oob_helper(test, 235, 201);
 }
 
-static void krealloc_pagealloc_more_oob(struct kunit *test)
+static void krealloc_large_more_oob(struct kunit *test)
 {
-	/* page_alloc fallback in only implemented for SLUB. */
-	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_SLUB);
-
 	krealloc_more_oob_helper(test, KMALLOC_MAX_CACHE_SIZE + 201,
 					KMALLOC_MAX_CACHE_SIZE + 235);
 }
 
-static void krealloc_pagealloc_less_oob(struct kunit *test)
+static void krealloc_large_less_oob(struct kunit *test)
 {
-	/* page_alloc fallback in only implemented for SLUB. */
-	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_SLUB);
-
 	krealloc_less_oob_helper(test, KMALLOC_MAX_CACHE_SIZE + 235,
 					KMALLOC_MAX_CACHE_SIZE + 201);
 }
@@ -493,14 +482,17 @@ static void kmalloc_oob_memset_2(struct kunit *test)
 {
 	char *ptr;
 	size_t size = 128 - KASAN_GRANULE_SIZE;
+	size_t memset_size = 2;
 
 	KASAN_TEST_NEEDS_CHECKED_MEMINTRINSICS(test);
 
 	ptr = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 
+	OPTIMIZER_HIDE_VAR(ptr);
 	OPTIMIZER_HIDE_VAR(size);
-	KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 1, 0, 2));
+	OPTIMIZER_HIDE_VAR(memset_size);
+	KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 1, 0, memset_size));
 	kfree(ptr);
 }
 
@@ -508,14 +500,17 @@ static void kmalloc_oob_memset_4(struct kunit *test)
 {
 	char *ptr;
 	size_t size = 128 - KASAN_GRANULE_SIZE;
+	size_t memset_size = 4;
 
 	KASAN_TEST_NEEDS_CHECKED_MEMINTRINSICS(test);
 
 	ptr = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 
+	OPTIMIZER_HIDE_VAR(ptr);
 	OPTIMIZER_HIDE_VAR(size);
-	KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 3, 0, 4));
+	OPTIMIZER_HIDE_VAR(memset_size);
+	KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 3, 0, memset_size));
 	kfree(ptr);
 }
 
@@ -523,14 +518,17 @@ static void kmalloc_oob_memset_8(struct kunit *test)
 {
 	char *ptr;
 	size_t size = 128 - KASAN_GRANULE_SIZE;
+	size_t memset_size = 8;
 
 	KASAN_TEST_NEEDS_CHECKED_MEMINTRINSICS(test);
 
 	ptr = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 
+	OPTIMIZER_HIDE_VAR(ptr);
 	OPTIMIZER_HIDE_VAR(size);
-	KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 7, 0, 8));
+	OPTIMIZER_HIDE_VAR(memset_size);
+	KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 7, 0, memset_size));
 	kfree(ptr);
 }
 
@@ -538,14 +536,17 @@ static void kmalloc_oob_memset_16(struct kunit *test)
 {
 	char *ptr;
 	size_t size = 128 - KASAN_GRANULE_SIZE;
+	size_t memset_size = 16;
 
 	KASAN_TEST_NEEDS_CHECKED_MEMINTRINSICS(test);
 
 	ptr = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 
+	OPTIMIZER_HIDE_VAR(ptr);
 	OPTIMIZER_HIDE_VAR(size);
-	KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 15, 0, 16));
+	OPTIMIZER_HIDE_VAR(memset_size);
+	KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 15, 0, memset_size));
 	kfree(ptr);
 }
 
@@ -696,6 +697,126 @@ static void kmalloc_uaf3(struct kunit *test)
 	KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr1)[8]);
 }
 
+static void kmalloc_double_kzfree(struct kunit *test)
+{
+	char *ptr;
+	size_t size = 16;
+
+	ptr = kmalloc(size, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
+
+	kfree_sensitive(ptr);
+	KUNIT_EXPECT_KASAN_FAIL(test, kfree_sensitive(ptr));
+}
+
+/* Check that ksize() does NOT unpoison whole object. */
+static void ksize_unpoisons_memory(struct kunit *test)
+{
+	char *ptr;
+	size_t size = 128 - KASAN_GRANULE_SIZE - 5;
+	size_t real_size;
+
+	ptr = kmalloc(size, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
+
+	real_size = ksize(ptr);
+	KUNIT_EXPECT_GT(test, real_size, size);
+
+	OPTIMIZER_HIDE_VAR(ptr);
+
+	/* These accesses shouldn't trigger a KASAN report. */
+	ptr[0] = 'x';
+	ptr[size - 1] = 'x';
+
+	/* These must trigger a KASAN report. */
+	if (IS_ENABLED(CONFIG_KASAN_GENERIC))
+		KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr)[size]);
+	KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr)[size + 5]);
+	KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr)[real_size - 1]);
+
+	kfree(ptr);
+}
+
+/*
+ * Check that a use-after-free is detected by ksize() and via normal accesses
+ * after it.
+ */
+static void ksize_uaf(struct kunit *test)
+{
+	char *ptr;
+	int size = 128 - KASAN_GRANULE_SIZE;
+
+	ptr = kmalloc(size, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
+	kfree(ptr);
+
+	OPTIMIZER_HIDE_VAR(ptr);
+	KUNIT_EXPECT_KASAN_FAIL(test, ksize(ptr));
+	KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr)[0]);
+	KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr)[size]);
+}
+
+/*
+ * The two tests below check that Generic KASAN prints auxiliary stack traces
+ * for RCU callbacks and workqueues. The reports need to be inspected manually.
+ *
+ * These tests are still enabled for other KASAN modes to make sure that all
+ * modes report bad accesses in tested scenarios.
+ */
+
+static struct kasan_rcu_info {
+	int i;
+	struct rcu_head rcu;
+} *global_rcu_ptr;
+
+static void rcu_uaf_reclaim(struct rcu_head *rp)
+{
+	struct kasan_rcu_info *fp =
+		container_of(rp, struct kasan_rcu_info, rcu);
+
+	kfree(fp);
+	((volatile struct kasan_rcu_info *)fp)->i;
+}
+
+static void rcu_uaf(struct kunit *test)
+{
+	struct kasan_rcu_info *ptr;
+
+	ptr = kmalloc(sizeof(struct kasan_rcu_info), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
+
+	global_rcu_ptr = rcu_dereference_protected(
+				(struct kasan_rcu_info __rcu *)ptr, NULL);
+
+	KUNIT_EXPECT_KASAN_FAIL(test,
+		call_rcu(&global_rcu_ptr->rcu, rcu_uaf_reclaim);
+		rcu_barrier());
+}
+
+static void workqueue_uaf_work(struct work_struct *work)
+{
+	kfree(work);
+}
+
+static void workqueue_uaf(struct kunit *test)
+{
+	struct workqueue_struct *workqueue;
+	struct work_struct *work;
+
+	workqueue = create_workqueue("kasan_workqueue_test");
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, workqueue);
+
+	work = kmalloc(sizeof(struct work_struct), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, work);
+
+	INIT_WORK(work, workqueue_uaf_work);
+	queue_work(workqueue, work);
+	destroy_workqueue(workqueue);
+
+	KUNIT_EXPECT_KASAN_FAIL(test,
+		((volatile struct work_struct *)work)->data);
+}
+
 static void kfree_via_page(struct kunit *test)
 {
 	char *ptr;
@@ -746,6 +867,69 @@ static void kmem_cache_oob(struct kunit *test)
 	kmem_cache_destroy(cache);
 }
 
+static void kmem_cache_double_free(struct kunit *test)
+{
+	char *p;
+	size_t size = 200;
+	struct kmem_cache *cache;
+
+	cache = kmem_cache_create("test_cache", size, 0, 0, NULL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, cache);
+
+	p = kmem_cache_alloc(cache, GFP_KERNEL);
+	if (!p) {
+		kunit_err(test, "Allocation failed: %s\n", __func__);
+		kmem_cache_destroy(cache);
+		return;
+	}
+
+	kmem_cache_free(cache, p);
+	KUNIT_EXPECT_KASAN_FAIL(test, kmem_cache_free(cache, p));
+	kmem_cache_destroy(cache);
+}
+
+static void kmem_cache_invalid_free(struct kunit *test)
+{
+	char *p;
+	size_t size = 200;
+	struct kmem_cache *cache;
+
+	cache = kmem_cache_create("test_cache", size, 0, SLAB_TYPESAFE_BY_RCU,
+				  NULL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, cache);
+
+	p = kmem_cache_alloc(cache, GFP_KERNEL);
+	if (!p) {
+		kunit_err(test, "Allocation failed: %s\n", __func__);
+		kmem_cache_destroy(cache);
+		return;
+	}
+
+	/* Trigger invalid free, the object doesn't get freed. */
+	KUNIT_EXPECT_KASAN_FAIL(test, kmem_cache_free(cache, p + 1));
+
+	/*
+	 * Properly free the object to prevent the "Objects remaining in
+	 * test_cache on __kmem_cache_shutdown" BUG failure.
+	 */
+	kmem_cache_free(cache, p);
+
+	kmem_cache_destroy(cache);
+}
+
+static void empty_cache_ctor(void *object) { }
+
+static void kmem_cache_double_destroy(struct kunit *test)
+{
+	struct kmem_cache *cache;
+
+	/* Provide a constructor to prevent cache merging. */
+	cache = kmem_cache_create("test_cache", 200, 0, 0, empty_cache_ctor);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, cache);
+	kmem_cache_destroy(cache);
+	KUNIT_EXPECT_KASAN_FAIL(test, kmem_cache_destroy(cache));
+}
+
 static void kmem_cache_accounted(struct kunit *test)
 {
 	int i;
@@ -798,6 +982,303 @@ static void kmem_cache_bulk(struct kunit *test)
 	kmem_cache_destroy(cache);
 }
 
+static void *mempool_prepare_kmalloc(struct kunit *test, mempool_t *pool, size_t size)
+{
+	int pool_size = 4;
+	int ret;
+	void *elem;
+
+	memset(pool, 0, sizeof(*pool));
+	ret = mempool_init_kmalloc_pool(pool, pool_size, size);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
+	/*
+	 * Allocate one element to prevent mempool from freeing elements to the
+	 * underlying allocator and instead make it add them to the element
+	 * list when the tests trigger double-free and invalid-free bugs.
+	 * This allows testing KASAN annotations in add_element().
+	 */
+	elem = mempool_alloc_preallocated(pool);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, elem);
+
+	return elem;
+}
+
+static struct kmem_cache *mempool_prepare_slab(struct kunit *test, mempool_t *pool, size_t size)
+{
+	struct kmem_cache *cache;
+	int pool_size = 4;
+	int ret;
+
+	cache = kmem_cache_create("test_cache", size, 0, 0, NULL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, cache);
+
+	memset(pool, 0, sizeof(*pool));
+	ret = mempool_init_slab_pool(pool, pool_size, cache);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
+	/*
+	 * Do not allocate one preallocated element, as we skip the double-free
+	 * and invalid-free tests for slab mempool for simplicity.
+	 */
+
+	return cache;
+}
+
+static void *mempool_prepare_page(struct kunit *test, mempool_t *pool, int order)
+{
+	int pool_size = 4;
+	int ret;
+	void *elem;
+
+	memset(pool, 0, sizeof(*pool));
+	ret = mempool_init_page_pool(pool, pool_size, order);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
+	elem = mempool_alloc_preallocated(pool);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, elem);
+
+	return elem;
+}
+
+static void mempool_oob_right_helper(struct kunit *test, mempool_t *pool, size_t size)
+{
+	char *elem;
+
+	elem = mempool_alloc_preallocated(pool);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, elem);
+
+	OPTIMIZER_HIDE_VAR(elem);
+
+	if (IS_ENABLED(CONFIG_KASAN_GENERIC))
+		KUNIT_EXPECT_KASAN_FAIL(test,
+			((volatile char *)&elem[size])[0]);
+	else
+		KUNIT_EXPECT_KASAN_FAIL(test,
+			((volatile char *)&elem[round_up(size, KASAN_GRANULE_SIZE)])[0]);
+
+	mempool_free(elem, pool);
+}
+
+static void mempool_kmalloc_oob_right(struct kunit *test)
+{
+	mempool_t pool;
+	size_t size = 128 - KASAN_GRANULE_SIZE - 5;
+	void *extra_elem;
+
+	extra_elem = mempool_prepare_kmalloc(test, &pool, size);
+
+	mempool_oob_right_helper(test, &pool, size);
+
+	mempool_free(extra_elem, &pool);
+	mempool_exit(&pool);
+}
+
+static void mempool_kmalloc_large_oob_right(struct kunit *test)
+{
+	mempool_t pool;
+	size_t size = KMALLOC_MAX_CACHE_SIZE + 1;
+	void *extra_elem;
+
+	extra_elem = mempool_prepare_kmalloc(test, &pool, size);
+
+	mempool_oob_right_helper(test, &pool, size);
+
+	mempool_free(extra_elem, &pool);
+	mempool_exit(&pool);
+}
+
+static void mempool_slab_oob_right(struct kunit *test)
+{
+	mempool_t pool;
+	size_t size = 123;
+	struct kmem_cache *cache;
+
+	cache = mempool_prepare_slab(test, &pool, size);
+
+	mempool_oob_right_helper(test, &pool, size);
+
+	mempool_exit(&pool);
+	kmem_cache_destroy(cache);
+}
+
+/*
+ * Skip the out-of-bounds test for page mempool. With Generic KASAN, page
+ * allocations have no redzones, and thus the out-of-bounds detection is not
+ * guaranteed; see https://bugzilla.kernel.org/show_bug.cgi?id=210503. With
+ * the tag-based KASAN modes, the neighboring allocation might have the same
+ * tag; see https://bugzilla.kernel.org/show_bug.cgi?id=203505.
+ */
+
+static void mempool_uaf_helper(struct kunit *test, mempool_t *pool, bool page)
+{
+	char *elem, *ptr;
+
+	elem = mempool_alloc_preallocated(pool);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, elem);
+
+	mempool_free(elem, pool);
+
+	ptr = page ? page_address((struct page *)elem) : elem;
+	KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr)[0]);
+}
+
+static void mempool_kmalloc_uaf(struct kunit *test)
+{
+	mempool_t pool;
+	size_t size = 128;
+	void *extra_elem;
+
+	extra_elem = mempool_prepare_kmalloc(test, &pool, size);
+
+	mempool_uaf_helper(test, &pool, false);
+
+	mempool_free(extra_elem, &pool);
+	mempool_exit(&pool);
+}
+
+static void mempool_kmalloc_large_uaf(struct kunit *test)
+{
+	mempool_t pool;
+	size_t size = KMALLOC_MAX_CACHE_SIZE + 1;
+	void *extra_elem;
+
+	extra_elem = mempool_prepare_kmalloc(test, &pool, size);
+
+	mempool_uaf_helper(test, &pool, false);
+
+	mempool_free(extra_elem, &pool);
+	mempool_exit(&pool);
+}
+
+static void mempool_slab_uaf(struct kunit *test)
+{
+	mempool_t pool;
+	size_t size = 123;
+	struct kmem_cache *cache;
+
+	cache = mempool_prepare_slab(test, &pool, size);
+
+	mempool_uaf_helper(test, &pool, false);
+
+	mempool_exit(&pool);
+	kmem_cache_destroy(cache);
+}
+
+static void mempool_page_alloc_uaf(struct kunit *test)
+{
+	mempool_t pool;
+	int order = 2;
+	void *extra_elem;
+
+	extra_elem = mempool_prepare_page(test, &pool, order);
+
+	mempool_uaf_helper(test, &pool, true);
+
+	mempool_free(extra_elem, &pool);
+	mempool_exit(&pool);
+}
+
+static void mempool_double_free_helper(struct kunit *test, mempool_t *pool)
+{
+	char *elem;
+
+	elem = mempool_alloc_preallocated(pool);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, elem);
+
+	mempool_free(elem, pool);
+
+	KUNIT_EXPECT_KASAN_FAIL(test, mempool_free(elem, pool));
+}
+
+static void mempool_kmalloc_double_free(struct kunit *test)
+{
+	mempool_t pool;
+	size_t size = 128;
+	char *extra_elem;
+
+	extra_elem = mempool_prepare_kmalloc(test, &pool, size);
+
+	mempool_double_free_helper(test, &pool);
+
+	mempool_free(extra_elem, &pool);
+	mempool_exit(&pool);
+}
+
+static void mempool_kmalloc_large_double_free(struct kunit *test)
+{
+	mempool_t pool;
+	size_t size = KMALLOC_MAX_CACHE_SIZE + 1;
+	char *extra_elem;
+
+	extra_elem = mempool_prepare_kmalloc(test, &pool, size);
+
+	mempool_double_free_helper(test, &pool);
+
+	mempool_free(extra_elem, &pool);
+	mempool_exit(&pool);
+}
+
+static void mempool_page_alloc_double_free(struct kunit *test)
+{
+	mempool_t pool;
+	int order = 2;
+	char *extra_elem;
+
+	extra_elem = mempool_prepare_page(test, &pool, order);
+
+	mempool_double_free_helper(test, &pool);
+
+	mempool_free(extra_elem, &pool);
+	mempool_exit(&pool);
+}
+
+static void mempool_kmalloc_invalid_free_helper(struct kunit *test, mempool_t *pool)
+{
+	char *elem;
+
+	elem = mempool_alloc_preallocated(pool);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, elem);
+
+	KUNIT_EXPECT_KASAN_FAIL(test, mempool_free(elem + 1, pool));
+
+	mempool_free(elem, pool);
+}
+
+static void mempool_kmalloc_invalid_free(struct kunit *test)
+{
+	mempool_t pool;
+	size_t size = 128;
+	char *extra_elem;
+
+	extra_elem = mempool_prepare_kmalloc(test, &pool, size);
+
+	mempool_kmalloc_invalid_free_helper(test, &pool);
+
+	mempool_free(extra_elem, &pool);
+	mempool_exit(&pool);
+}
+
+static void mempool_kmalloc_large_invalid_free(struct kunit *test)
+{
+	mempool_t pool;
+	size_t size = KMALLOC_MAX_CACHE_SIZE + 1;
+	char *extra_elem;
+
+	extra_elem = mempool_prepare_kmalloc(test, &pool, size);
+
+	mempool_kmalloc_invalid_free_helper(test, &pool);
+
+	mempool_free(extra_elem, &pool);
+	mempool_exit(&pool);
+}
+
+/*
+ * Skip the invalid-free test for page mempool. The invalid-free detection only
+ * works for compound pages and mempool preallocates all page elements without
+ * the __GFP_COMP flag.
+ */
+
 static char global_array[10];
 
 static void kasan_global_oob_right(struct kunit *test)
@@ -837,53 +1318,6 @@ static void kasan_global_oob_left(struct kunit *test)
 	KUNIT_EXPECT_KASAN_FAIL(test, *(volatile char *)p);
 }
 
-/* Check that ksize() does NOT unpoison whole object. */
-static void ksize_unpoisons_memory(struct kunit *test)
-{
-	char *ptr;
-	size_t size = 128 - KASAN_GRANULE_SIZE - 5;
-	size_t real_size;
-
-	ptr = kmalloc(size, GFP_KERNEL);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
-
-	real_size = ksize(ptr);
-	KUNIT_EXPECT_GT(test, real_size, size);
-
-	OPTIMIZER_HIDE_VAR(ptr);
-
-	/* These accesses shouldn't trigger a KASAN report. */
-	ptr[0] = 'x';
-	ptr[size - 1] = 'x';
-
-	/* These must trigger a KASAN report. */
-	if (IS_ENABLED(CONFIG_KASAN_GENERIC))
-		KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr)[size]);
-	KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr)[size + 5]);
-	KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr)[real_size - 1]);
-
-	kfree(ptr);
-}
-
-/*
- * Check that a use-after-free is detected by ksize() and via normal accesses
- * after it.
- */
-static void ksize_uaf(struct kunit *test)
-{
-	char *ptr;
-	int size = 128 - KASAN_GRANULE_SIZE;
-
-	ptr = kmalloc(size, GFP_KERNEL);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
-	kfree(ptr);
-
-	OPTIMIZER_HIDE_VAR(ptr);
-	KUNIT_EXPECT_KASAN_FAIL(test, ksize(ptr));
-	KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr)[0]);
-	KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr)[size]);
-}
-
 static void kasan_stack_oob(struct kunit *test)
 {
 	char stack_array[10];
@@ -926,69 +1360,6 @@ static void kasan_alloca_oob_right(struct kunit *test)
 	KUNIT_EXPECT_KASAN_FAIL(test, *(volatile char *)p);
 }
 
-static void kmem_cache_double_free(struct kunit *test)
-{
-	char *p;
-	size_t size = 200;
-	struct kmem_cache *cache;
-
-	cache = kmem_cache_create("test_cache", size, 0, 0, NULL);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, cache);
-
-	p = kmem_cache_alloc(cache, GFP_KERNEL);
-	if (!p) {
-		kunit_err(test, "Allocation failed: %s\n", __func__);
-		kmem_cache_destroy(cache);
-		return;
-	}
-
-	kmem_cache_free(cache, p);
-	KUNIT_EXPECT_KASAN_FAIL(test, kmem_cache_free(cache, p));
-	kmem_cache_destroy(cache);
-}
-
-static void kmem_cache_invalid_free(struct kunit *test)
-{
-	char *p;
-	size_t size = 200;
-	struct kmem_cache *cache;
-
-	cache = kmem_cache_create("test_cache", size, 0, SLAB_TYPESAFE_BY_RCU,
-				  NULL);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, cache);
-
-	p = kmem_cache_alloc(cache, GFP_KERNEL);
-	if (!p) {
-		kunit_err(test, "Allocation failed: %s\n", __func__);
-		kmem_cache_destroy(cache);
-		return;
-	}
-
-	/* Trigger invalid free, the object doesn't get freed. */
-	KUNIT_EXPECT_KASAN_FAIL(test, kmem_cache_free(cache, p + 1));
-
-	/*
-	 * Properly free the object to prevent the "Objects remaining in
-	 * test_cache on __kmem_cache_shutdown" BUG failure.
-	 */
-	kmem_cache_free(cache, p);
-
-	kmem_cache_destroy(cache);
-}
-
-static void empty_cache_ctor(void *object) { }
-
-static void kmem_cache_double_destroy(struct kunit *test)
-{
-	struct kmem_cache *cache;
-
-	/* Provide a constructor to prevent cache merging. */
-	cache = kmem_cache_create("test_cache", 200, 0, 0, empty_cache_ctor);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, cache);
-	kmem_cache_destroy(cache);
-	KUNIT_EXPECT_KASAN_FAIL(test, kmem_cache_destroy(cache));
-}
-
 static void kasan_memchr(struct kunit *test)
 {
 	char *ptr;
@@ -1150,79 +1521,6 @@ static void kasan_bitops_tags(struct kunit *test)
 	kfree(bits);
 }
 
-static void kmalloc_double_kzfree(struct kunit *test)
-{
-	char *ptr;
-	size_t size = 16;
-
-	ptr = kmalloc(size, GFP_KERNEL);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
-
-	kfree_sensitive(ptr);
-	KUNIT_EXPECT_KASAN_FAIL(test, kfree_sensitive(ptr));
-}
-
-/*
- * The two tests below check that Generic KASAN prints auxiliary stack traces
- * for RCU callbacks and workqueues. The reports need to be inspected manually.
- *
- * These tests are still enabled for other KASAN modes to make sure that all
- * modes report bad accesses in tested scenarios.
- */
-
-static struct kasan_rcu_info {
-	int i;
-	struct rcu_head rcu;
-} *global_rcu_ptr;
-
-static void rcu_uaf_reclaim(struct rcu_head *rp)
-{
-	struct kasan_rcu_info *fp =
-		container_of(rp, struct kasan_rcu_info, rcu);
-
-	kfree(fp);
-	((volatile struct kasan_rcu_info *)fp)->i;
-}
-
-static void rcu_uaf(struct kunit *test)
-{
-	struct kasan_rcu_info *ptr;
-
-	ptr = kmalloc(sizeof(struct kasan_rcu_info), GFP_KERNEL);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
-
-	global_rcu_ptr = rcu_dereference_protected(
-				(struct kasan_rcu_info __rcu *)ptr, NULL);
-
-	KUNIT_EXPECT_KASAN_FAIL(test,
-		call_rcu(&global_rcu_ptr->rcu, rcu_uaf_reclaim);
-		rcu_barrier());
-}
-
-static void workqueue_uaf_work(struct work_struct *work)
-{
-	kfree(work);
-}
-
-static void workqueue_uaf(struct kunit *test)
-{
-	struct workqueue_struct *workqueue;
-	struct work_struct *work;
-
-	workqueue = create_workqueue("kasan_workqueue_test");
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, workqueue);
-
-	work = kmalloc(sizeof(struct work_struct), GFP_KERNEL);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, work);
-
-	INIT_WORK(work, workqueue_uaf_work);
-	queue_work(workqueue, work);
-	destroy_workqueue(workqueue);
-
-	KUNIT_EXPECT_KASAN_FAIL(test,
-		((volatile struct work_struct *)work)->data);
-}
-
 static void vmalloc_helpers_tags(struct kunit *test)
 {
 	void *ptr;
@@ -1232,6 +1530,9 @@ static void vmalloc_helpers_tags(struct kunit *test)
 
 	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_VMALLOC);
 
+	if (!kasan_vmalloc_enabled())
+		kunit_skip(test, "Test requires kasan.vmalloc=on");
+
 	ptr = vmalloc(PAGE_SIZE);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 
@@ -1266,6 +1567,9 @@ static void vmalloc_oob(struct kunit *test)
 
 	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_VMALLOC);
 
+	if (!kasan_vmalloc_enabled())
+		kunit_skip(test, "Test requires kasan.vmalloc=on");
+
 	v_ptr = vmalloc(size);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, v_ptr);
 
@@ -1319,6 +1623,9 @@ static void vmap_tags(struct kunit *test)
 
 	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_VMALLOC);
 
+	if (!kasan_vmalloc_enabled())
+		kunit_skip(test, "Test requires kasan.vmalloc=on");
+
 	p_page = alloc_pages(GFP_KERNEL, 1);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, p_page);
 	p_ptr = page_address(p_page);
@@ -1437,7 +1744,7 @@ static void match_all_not_assigned(struct kunit *test)
 		free_pages((unsigned long)ptr, order);
 	}
 
-	if (!IS_ENABLED(CONFIG_KASAN_VMALLOC))
+	if (!kasan_vmalloc_enabled())
 		return;
 
 	for (i = 0; i < 256; i++) {
@@ -1490,6 +1797,14 @@ static void match_all_mem_tag(struct kunit *test)
 
 	/* For each possible tag value not matching the pointer tag. */
 	for (tag = KASAN_TAG_MIN; tag <= KASAN_TAG_KERNEL; tag++) {
+		/*
+		 * For Software Tag-Based KASAN, skip the majority of tag
+		 * values to avoid the test printing too many reports.
+		 */
+		if (IS_ENABLED(CONFIG_KASAN_SW_TAGS) &&
+		    tag >= KASAN_TAG_MIN + 8 && tag <= KASAN_TAG_KERNEL - 8)
+			continue;
+
 		if (tag == get_tag(ptr))
 			continue;
 
@@ -1509,16 +1824,16 @@ static struct kunit_case kasan_kunit_test_cases[] = {
 	KUNIT_CASE(kmalloc_oob_right),
 	KUNIT_CASE(kmalloc_oob_left),
 	KUNIT_CASE(kmalloc_node_oob_right),
-	KUNIT_CASE(kmalloc_pagealloc_oob_right),
-	KUNIT_CASE(kmalloc_pagealloc_uaf),
-	KUNIT_CASE(kmalloc_pagealloc_invalid_free),
-	KUNIT_CASE(pagealloc_oob_right),
-	KUNIT_CASE(pagealloc_uaf),
+	KUNIT_CASE(kmalloc_big_oob_right),
 	KUNIT_CASE(kmalloc_large_oob_right),
+	KUNIT_CASE(kmalloc_large_uaf),
+	KUNIT_CASE(kmalloc_large_invalid_free),
+	KUNIT_CASE(page_alloc_oob_right),
+	KUNIT_CASE(page_alloc_uaf),
 	KUNIT_CASE(krealloc_more_oob),
 	KUNIT_CASE(krealloc_less_oob),
-	KUNIT_CASE(krealloc_pagealloc_more_oob),
-	KUNIT_CASE(krealloc_pagealloc_less_oob),
+	KUNIT_CASE(krealloc_large_more_oob),
+	KUNIT_CASE(krealloc_large_less_oob),
 	KUNIT_CASE(krealloc_uaf),
 	KUNIT_CASE(kmalloc_oob_16),
 	KUNIT_CASE(kmalloc_uaf_16),
@@ -1533,29 +1848,41 @@ static struct kunit_case kasan_kunit_test_cases[] = {
 	KUNIT_CASE(kmalloc_uaf_memset),
 	KUNIT_CASE(kmalloc_uaf2),
 	KUNIT_CASE(kmalloc_uaf3),
+	KUNIT_CASE(kmalloc_double_kzfree),
+	KUNIT_CASE(ksize_unpoisons_memory),
+	KUNIT_CASE(ksize_uaf),
+	KUNIT_CASE(rcu_uaf),
+	KUNIT_CASE(workqueue_uaf),
 	KUNIT_CASE(kfree_via_page),
 	KUNIT_CASE(kfree_via_phys),
 	KUNIT_CASE(kmem_cache_oob),
+	KUNIT_CASE(kmem_cache_double_free),
+	KUNIT_CASE(kmem_cache_invalid_free),
+	KUNIT_CASE(kmem_cache_double_destroy),
 	KUNIT_CASE(kmem_cache_accounted),
 	KUNIT_CASE(kmem_cache_bulk),
+	KUNIT_CASE(mempool_kmalloc_oob_right),
+	KUNIT_CASE(mempool_kmalloc_large_oob_right),
+	KUNIT_CASE(mempool_slab_oob_right),
+	KUNIT_CASE(mempool_kmalloc_uaf),
+	KUNIT_CASE(mempool_kmalloc_large_uaf),
+	KUNIT_CASE(mempool_slab_uaf),
+	KUNIT_CASE(mempool_page_alloc_uaf),
+	KUNIT_CASE(mempool_kmalloc_double_free),
+	KUNIT_CASE(mempool_kmalloc_large_double_free),
+	KUNIT_CASE(mempool_page_alloc_double_free),
+	KUNIT_CASE(mempool_kmalloc_invalid_free),
+	KUNIT_CASE(mempool_kmalloc_large_invalid_free),
 	KUNIT_CASE(kasan_global_oob_right),
 	KUNIT_CASE(kasan_global_oob_left),
 	KUNIT_CASE(kasan_stack_oob),
 	KUNIT_CASE(kasan_alloca_oob_left),
 	KUNIT_CASE(kasan_alloca_oob_right),
-	KUNIT_CASE(ksize_unpoisons_memory),
-	KUNIT_CASE(ksize_uaf),
-	KUNIT_CASE(kmem_cache_double_free),
-	KUNIT_CASE(kmem_cache_invalid_free),
-	KUNIT_CASE(kmem_cache_double_destroy),
 	KUNIT_CASE(kasan_memchr),
 	KUNIT_CASE(kasan_memcmp),
 	KUNIT_CASE(kasan_strings),
 	KUNIT_CASE(kasan_bitops_generic),
 	KUNIT_CASE(kasan_bitops_tags),
-	KUNIT_CASE(kmalloc_double_kzfree),
-	KUNIT_CASE(rcu_uaf),
-	KUNIT_CASE(workqueue_uaf),
 	KUNIT_CASE(vmalloc_helpers_tags),
 	KUNIT_CASE(vmalloc_oob),
 	KUNIT_CASE(vmap_tags),
diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c
index ca4529156735..3ba02efb952a 100644
--- a/mm/kasan/quarantine.c
+++ b/mm/kasan/quarantine.c
@@ -143,11 +143,9 @@ static void *qlink_to_object(struct qlist_node *qlink, struct kmem_cache *cache)
 static void qlink_free(struct qlist_node *qlink, struct kmem_cache *cache)
 {
 	void *object = qlink_to_object(qlink, cache);
-	struct kasan_free_meta *meta = kasan_get_free_meta(cache, object);
-	unsigned long flags;
+	struct kasan_free_meta *free_meta = kasan_get_free_meta(cache, object);
 
-	if (IS_ENABLED(CONFIG_SLAB))
-		local_irq_save(flags);
+	kasan_release_object_meta(cache, object);
 
 	/*
 	 * If init_on_free is enabled and KASAN's free metadata is stored in
@@ -157,18 +155,9 @@ static void qlink_free(struct qlist_node *qlink, struct kmem_cache *cache)
 	 */
 	if (slab_want_init_on_free(cache) &&
 	    cache->kasan_info.free_meta_offset == 0)
-		memzero_explicit(meta, sizeof(*meta));
-
-	/*
-	 * As the object now gets freed from the quarantine, assume that its
-	 * free track is no longer valid.
-	 */
-	*(u8 *)kasan_mem_to_shadow(object) = KASAN_SLAB_FREE;
+		memzero_explicit(free_meta, sizeof(*free_meta));
 
 	___cache_free(cache, object, _THIS_IP_);
-
-	if (IS_ENABLED(CONFIG_SLAB))
-		local_irq_restore(flags);
 }
 
 static void qlist_free_all(struct qlist_head *q, struct kmem_cache *cache)
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index e77facb62900..7afa4feb03e1 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -23,6 +23,7 @@
 #include <linux/stacktrace.h>
 #include <linux/string.h>
 #include <linux/types.h>
+#include <linux/vmalloc.h>
 #include <linux/kasan.h>
 #include <linux/module.h>
 #include <linux/sched/task_stack.h>
@@ -262,7 +263,19 @@ static void print_error_description(struct kasan_report_info *info)
 
 static void print_track(struct kasan_track *track, const char *prefix)
 {
+#ifdef CONFIG_KASAN_EXTRA_INFO
+	u64 ts_nsec = track->timestamp;
+	unsigned long rem_usec;
+
+	ts_nsec <<= 3;
+	rem_usec = do_div(ts_nsec, NSEC_PER_SEC) / 1000;
+
+	pr_err("%s by task %u on cpu %d at %lu.%06lus:\n",
+			prefix, track->pid, track->cpu,
+			(unsigned long)ts_nsec, rem_usec);
+#else
 	pr_err("%s by task %u:\n", prefix, track->pid);
+#endif /* CONFIG_KASAN_EXTRA_INFO */
 	if (track->stack)
 		stack_depot_print(track->stack);
 	else
@@ -623,37 +636,43 @@ void kasan_report_async(void)
 
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 /*
- * With CONFIG_KASAN_INLINE, accesses to bogus pointers (outside the high
- * canonical half of the address space) cause out-of-bounds shadow memory reads
- * before the actual access. For addresses in the low canonical half of the
- * address space, as well as most non-canonical addresses, that out-of-bounds
- * shadow memory access lands in the non-canonical part of the address space.
- * Help the user figure out what the original bogus pointer was.
+ * With compiler-based KASAN modes, accesses to bogus pointers (outside of the
+ * mapped kernel address space regions) cause faults when KASAN tries to check
+ * the shadow memory before the actual memory access. This results in cryptic
+ * GPF reports, which are hard for users to interpret. This hook helps users to
+ * figure out what the original bogus pointer was.
  */
 void kasan_non_canonical_hook(unsigned long addr)
 {
 	unsigned long orig_addr;
 	const char *bug_type;
 
+	/*
+	 * All addresses that came as a result of the memory-to-shadow mapping
+	 * (even for bogus pointers) must be >= KASAN_SHADOW_OFFSET.
+	 */
 	if (addr < KASAN_SHADOW_OFFSET)
 		return;
 
-	orig_addr = (addr - KASAN_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT;
+	orig_addr = (unsigned long)kasan_shadow_to_mem((void *)addr);
+
 	/*
 	 * For faults near the shadow address for NULL, we can be fairly certain
 	 * that this is a KASAN shadow memory access.
-	 * For faults that correspond to shadow for low canonical addresses, we
-	 * can still be pretty sure - that shadow region is a fairly narrow
-	 * chunk of the non-canonical address space.
-	 * But faults that look like shadow for non-canonical addresses are a
-	 * really large chunk of the address space. In that case, we still
-	 * print the decoded address, but make it clear that this is not
-	 * necessarily what's actually going on.
+	 * For faults that correspond to the shadow for low or high canonical
+	 * addresses, we can still be pretty sure: these shadow regions are a
+	 * fairly narrow chunk of the address space.
+	 * But the shadow for non-canonical addresses is a really large chunk
+	 * of the address space. For this case, we still print the decoded
+	 * address, but make it clear that this is not necessarily what's
+	 * actually going on.
 	 */
 	if (orig_addr < PAGE_SIZE)
 		bug_type = "null-ptr-deref";
 	else if (orig_addr < TASK_SIZE)
 		bug_type = "probably user-memory-access";
+	else if (addr_in_shadow((void *)addr))
+		bug_type = "probably wild-memory-access";
 	else
 		bug_type = "maybe wild-memory-access";
 	pr_alert("KASAN: %s in range [0x%016lx-0x%016lx]\n", bug_type,
diff --git a/mm/kasan/report_generic.c b/mm/kasan/report_generic.c
index 99cbcd73cff7..f5b8e37b3805 100644
--- a/mm/kasan/report_generic.c
+++ b/mm/kasan/report_generic.c
@@ -110,7 +110,7 @@ static const char *get_shadow_bug_type(struct kasan_report_info *info)
 		bug_type = "use-after-free";
 		break;
 	case KASAN_SLAB_FREE:
-	case KASAN_SLAB_FREETRACK:
+	case KASAN_SLAB_FREE_META:
 		bug_type = "slab-use-after-free";
 		break;
 	case KASAN_ALLOCA_LEFT:
@@ -173,8 +173,8 @@ void kasan_complete_mode_report_info(struct kasan_report_info *info)
 		memcpy(&info->alloc_track, &alloc_meta->alloc_track,
 		       sizeof(info->alloc_track));
 
-	if (*(u8 *)kasan_mem_to_shadow(info->object) == KASAN_SLAB_FREETRACK) {
-		/* Free meta must be present with KASAN_SLAB_FREETRACK. */
+	if (*(u8 *)kasan_mem_to_shadow(info->object) == KASAN_SLAB_FREE_META) {
+		/* Free meta must be present with KASAN_SLAB_FREE_META. */
 		free_meta = kasan_get_free_meta(info->cache, info->object);
 		memcpy(&info->free_track, &free_meta->free_track,
 		       sizeof(info->free_track));
diff --git a/mm/kasan/report_tags.c b/mm/kasan/report_tags.c
index 8b8bfdb3cfdb..d15f8f580e2c 100644
--- a/mm/kasan/report_tags.c
+++ b/mm/kasan/report_tags.c
@@ -7,6 +7,7 @@
 #include <linux/atomic.h>
 
 #include "kasan.h"
+#include "../slab.h"
 
 extern struct kasan_stack_ring stack_ring;
 
@@ -31,10 +32,6 @@ void kasan_complete_mode_report_info(struct kasan_report_info *info)
 	unsigned long flags;
 	u64 pos;
 	struct kasan_stack_ring_entry *entry;
-	void *ptr;
-	u32 pid;
-	depot_stack_handle_t stack;
-	bool is_free;
 	bool alloc_found = false, free_found = false;
 
 	if ((!info->cache || !info->object) && !info->bug_type) {
@@ -61,18 +58,12 @@ void kasan_complete_mode_report_info(struct kasan_report_info *info)
 
 		entry = &stack_ring.entries[i % stack_ring.size];
 
-		/* Paired with smp_store_release() in save_stack_info(). */
-		ptr = (void *)smp_load_acquire(&entry->ptr);
-
-		if (kasan_reset_tag(ptr) != info->object ||
-		    get_tag(ptr) != get_tag(info->access_addr))
+		if (kasan_reset_tag(entry->ptr) != info->object ||
+		    get_tag(entry->ptr) != get_tag(info->access_addr) ||
+		    info->cache->object_size != entry->size)
 			continue;
 
-		pid = READ_ONCE(entry->pid);
-		stack = READ_ONCE(entry->stack);
-		is_free = READ_ONCE(entry->is_free);
-
-		if (is_free) {
+		if (entry->is_free) {
 			/*
 			 * Second free of the same object.
 			 * Give up on trying to find the alloc entry.
@@ -80,8 +71,8 @@ void kasan_complete_mode_report_info(struct kasan_report_info *info)
 			if (free_found)
 				break;
 
-			info->free_track.pid = pid;
-			info->free_track.stack = stack;
+			memcpy(&info->free_track, &entry->track,
+			       sizeof(info->free_track));
 			free_found = true;
 
 			/*
@@ -95,8 +86,8 @@ void kasan_complete_mode_report_info(struct kasan_report_info *info)
 			if (alloc_found)
 				break;
 
-			info->alloc_track.pid = pid;
-			info->alloc_track.stack = stack;
+			memcpy(&info->alloc_track, &entry->track,
+			       sizeof(info->alloc_track));
 			alloc_found = true;
 
 			/*
diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c
index d687f09a7ae3..9ef84f31833f 100644
--- a/mm/kasan/shadow.c
+++ b/mm/kasan/shadow.c
@@ -130,15 +130,11 @@ void kasan_poison(const void *addr, size_t size, u8 value, bool init)
 
 	/*
 	 * Perform shadow offset calculation based on untagged address, as
-	 * some of the callers (e.g. kasan_poison_object_data) pass tagged
+	 * some of the callers (e.g. kasan_poison_new_object) pass tagged
 	 * addresses to this function.
 	 */
 	addr = kasan_reset_tag(addr);
 
-	/* Skip KFENCE memory if called explicitly outside of sl*b. */
-	if (is_kfence_address(addr))
-		return;
-
 	if (WARN_ON((unsigned long)addr & KASAN_GRANULE_MASK))
 		return;
 	if (WARN_ON(size & KASAN_GRANULE_MASK))
@@ -149,7 +145,7 @@ void kasan_poison(const void *addr, size_t size, u8 value, bool init)
 
 	__memset(shadow_start, value, shadow_end - shadow_start);
 }
-EXPORT_SYMBOL(kasan_poison);
+EXPORT_SYMBOL_GPL(kasan_poison);
 
 #ifdef CONFIG_KASAN_GENERIC
 void kasan_poison_last_granule(const void *addr, size_t size)
@@ -170,19 +166,11 @@ void kasan_unpoison(const void *addr, size_t size, bool init)
 
 	/*
 	 * Perform shadow offset calculation based on untagged address, as
-	 * some of the callers (e.g. kasan_unpoison_object_data) pass tagged
+	 * some of the callers (e.g. kasan_unpoison_new_object) pass tagged
 	 * addresses to this function.
 	 */
 	addr = kasan_reset_tag(addr);
 
-	/*
-	 * Skip KFENCE memory if called explicitly outside of sl*b. Also note
-	 * that calls to ksize(), where size is not a multiple of machine-word
-	 * size, would otherwise poison the invalid portion of the word.
-	 */
-	if (is_kfence_address(addr))
-		return;
-
 	if (WARN_ON((unsigned long)addr & KASAN_GRANULE_MASK))
 		return;
 
diff --git a/mm/kasan/tags.c b/mm/kasan/tags.c
index 7dcfe341d48e..d65d48b85f90 100644
--- a/mm/kasan/tags.c
+++ b/mm/kasan/tags.c
@@ -13,6 +13,8 @@
 #include <linux/memblock.h>
 #include <linux/memory.h>
 #include <linux/mm.h>
+#include <linux/sched/clock.h>
+#include <linux/stackdepot.h>
 #include <linux/static_key.h>
 #include <linux/string.h>
 #include <linux/types.h>
@@ -96,12 +98,13 @@ static void save_stack_info(struct kmem_cache *cache, void *object,
 			gfp_t gfp_flags, bool is_free)
 {
 	unsigned long flags;
-	depot_stack_handle_t stack;
+	depot_stack_handle_t stack, old_stack;
 	u64 pos;
 	struct kasan_stack_ring_entry *entry;
 	void *old_ptr;
 
-	stack = kasan_save_stack(gfp_flags, true);
+	stack = kasan_save_stack(gfp_flags,
+			STACK_DEPOT_FLAG_CAN_ALLOC | STACK_DEPOT_FLAG_GET);
 
 	/*
 	 * Prevent save_stack_info() from modifying stack ring
@@ -120,17 +123,18 @@ next:
 	if (!try_cmpxchg(&entry->ptr, &old_ptr, STACK_RING_BUSY_PTR))
 		goto next; /* Busy slot. */
 
-	WRITE_ONCE(entry->size, cache->object_size);
-	WRITE_ONCE(entry->pid, current->pid);
-	WRITE_ONCE(entry->stack, stack);
-	WRITE_ONCE(entry->is_free, is_free);
+	old_stack = entry->track.stack;
 
-	/*
-	 * Paired with smp_load_acquire() in kasan_complete_mode_report_info().
-	 */
-	smp_store_release(&entry->ptr, (s64)object);
+	entry->size = cache->object_size;
+	kasan_set_track(&entry->track, stack);
+	entry->is_free = is_free;
+
+	entry->ptr = object;
 
 	read_unlock_irqrestore(&stack_ring.lock, flags);
+
+	if (old_stack)
+		stack_depot_put(old_stack);
 }
 
 void kasan_save_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags)
diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index 3872528d0963..8350f5c06f2e 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -463,11 +463,7 @@ static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t g
 	/* Set required slab fields. */
 	slab = virt_to_slab((void *)meta->addr);
 	slab->slab_cache = cache;
-#if defined(CONFIG_SLUB)
 	slab->objects = 1;
-#elif defined(CONFIG_SLAB)
-	slab->s_mem = addr;
-#endif
 
 	/* Memory initialization. */
 	set_canary(meta);
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 064654717843..2b219acb528e 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -17,6 +17,7 @@
 #include <linux/userfaultfd_k.h>
 #include <linux/page_idle.h>
 #include <linux/page_table_check.h>
+#include <linux/rcupdate_wait.h>
 #include <linux/swapops.h>
 #include <linux/shmem_fs.h>
 #include <linux/ksm.h>
@@ -446,7 +447,8 @@ void khugepaged_enter_vma(struct vm_area_struct *vma,
 {
 	if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) &&
 	    hugepage_flags_enabled()) {
-		if (hugepage_vma_check(vma, vm_flags, false, false, true))
+		if (thp_vma_allowable_order(vma, vm_flags, false, false, true,
+					    PMD_ORDER))
 			__khugepaged_enter(vma->vm_mm);
 	}
 }
@@ -493,11 +495,6 @@ static void release_pte_folio(struct folio *folio)
 	folio_putback_lru(folio);
 }
 
-static void release_pte_page(struct page *page)
-{
-	release_pte_folio(page_folio(page));
-}
-
 static void release_pte_pages(pte_t *pte, pte_t *_pte,
 		struct list_head *compound_pagelist)
 {
@@ -686,6 +683,7 @@ static void __collapse_huge_page_copy_succeeded(pte_t *pte,
 						spinlock_t *ptl,
 						struct list_head *compound_pagelist)
 {
+	struct folio *src_folio;
 	struct page *src_page;
 	struct page *tmp;
 	pte_t *_pte;
@@ -707,16 +705,17 @@ static void __collapse_huge_page_copy_succeeded(pte_t *pte,
 			}
 		} else {
 			src_page = pte_page(pteval);
-			if (!PageCompound(src_page))
-				release_pte_page(src_page);
+			src_folio = page_folio(src_page);
+			if (!folio_test_large(src_folio))
+				release_pte_folio(src_folio);
 			/*
 			 * ptl mostly unnecessary, but preempt has to
 			 * be disabled to update the per-cpu stats
-			 * inside page_remove_rmap().
+			 * inside folio_remove_rmap_pte().
 			 */
 			spin_lock(ptl);
 			ptep_clear(vma->vm_mm, address, _pte);
-			page_remove_rmap(src_page, vma, false);
+			folio_remove_rmap_pte(src_folio, src_page, vma);
 			spin_unlock(ptl);
 			free_page_and_swap_cache(src_page);
 		}
@@ -922,16 +921,16 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
 	if (!vma)
 		return SCAN_VMA_NULL;
 
-	if (!transhuge_vma_suitable(vma, address))
+	if (!thp_vma_suitable_order(vma, address, PMD_ORDER))
 		return SCAN_ADDRESS_RANGE;
-	if (!hugepage_vma_check(vma, vma->vm_flags, false, false,
-				cc->is_khugepaged))
+	if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false,
+				     cc->is_khugepaged, PMD_ORDER))
 		return SCAN_VMA_CHECK;
 	/*
 	 * Anon VMA expected, the address may be unmapped then
 	 * remapped to file after khugepaged reaquired the mmap_lock.
 	 *
-	 * hugepage_vma_check may return true for qualified file
+	 * thp_vma_allowable_order may return true for qualified file
 	 * vmas.
 	 */
 	if (expect_anon && (!(*vmap)->anon_vma || !vma_is_anonymous(*vmap)))
@@ -1089,6 +1088,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
 	pmd_t *pmd, _pmd;
 	pte_t *pte;
 	pgtable_t pgtable;
+	struct folio *folio;
 	struct page *hpage;
 	spinlock_t *pmd_ptl, *pte_ptl;
 	int result = SCAN_FAIL;
@@ -1139,6 +1139,9 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
 	 * Prevent all access to pagetables with the exception of
 	 * gup_fast later handled by the ptep_clear_flush and the VM
 	 * handled by the anon_vma lock + PG_lock.
+	 *
+	 * UFFDIO_MOVE is prevented to race as well thanks to the
+	 * mmap_lock.
 	 */
 	mmap_write_lock(mm);
 	result = hugepage_vma_revalidate(mm, address, true, &vma, cc);
@@ -1208,13 +1211,13 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
 	if (unlikely(result != SCAN_SUCCEED))
 		goto out_up_write;
 
+	folio = page_folio(hpage);
 	/*
-	 * spin_lock() below is not the equivalent of smp_wmb(), but
-	 * the smp_wmb() inside __SetPageUptodate() can be reused to
-	 * avoid the copy_huge_page writes to become visible after
-	 * the set_pmd_at() write.
+	 * The smp_wmb() inside __folio_mark_uptodate() ensures the
+	 * copy_huge_page writes become visible before the set_pmd_at()
+	 * write.
 	 */
-	__SetPageUptodate(hpage);
+	__folio_mark_uptodate(folio);
 	pgtable = pmd_pgtable(_pmd);
 
 	_pmd = mk_huge_pmd(hpage, vma->vm_page_prot);
@@ -1222,8 +1225,8 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
 
 	spin_lock(pmd_ptl);
 	BUG_ON(!pmd_none(*pmd));
-	page_add_new_anon_rmap(hpage, vma, address);
-	lru_cache_add_inactive_or_unevictable(hpage, vma);
+	folio_add_new_anon_rmap(folio, vma, address);
+	folio_add_lru_vma(folio, vma);
 	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, address, pmd, _pmd);
 	update_mmu_cache_pmd(vma, address, pmd);
@@ -1503,7 +1506,8 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 	 * and map it by a PMD, regardless of sysfs THP settings. As such, let's
 	 * analogously elide sysfs THP settings here.
 	 */
-	if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false))
+	if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false, false,
+				     PMD_ORDER))
 		return SCAN_VMA_CHECK;
 
 	/* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */
@@ -1619,7 +1623,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 		 * PTE dirty? Shmem page is already dirty; file is read-only.
 		 */
 		ptep_clear(mm, addr, pte);
-		page_remove_rmap(page, vma, false);
+		folio_remove_rmap_pte(folio, page, vma);
 		nr_ptes++;
 	}
 
@@ -2119,23 +2123,23 @@ immap_locked:
 		xas_lock_irq(&xas);
 	}
 
-	nr = thp_nr_pages(hpage);
+	folio = page_folio(hpage);
+	nr = folio_nr_pages(folio);
 	if (is_shmem)
-		__mod_lruvec_page_state(hpage, NR_SHMEM_THPS, nr);
+		__lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, nr);
 	else
-		__mod_lruvec_page_state(hpage, NR_FILE_THPS, nr);
+		__lruvec_stat_mod_folio(folio, NR_FILE_THPS, nr);
 
 	if (nr_none) {
-		__mod_lruvec_page_state(hpage, NR_FILE_PAGES, nr_none);
+		__lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr_none);
 		/* nr_none is always 0 for non-shmem. */
-		__mod_lruvec_page_state(hpage, NR_SHMEM, nr_none);
+		__lruvec_stat_mod_folio(folio, NR_SHMEM, nr_none);
 	}
 
 	/*
 	 * Mark hpage as uptodate before inserting it into the page cache so
 	 * that it isn't mistaken for an fallocated but unwritten page.
 	 */
-	folio = page_folio(hpage);
 	folio_mark_uptodate(folio);
 	folio_ref_add(folio, HPAGE_PMD_NR - 1);
 
@@ -2145,7 +2149,7 @@ immap_locked:
 
 	/* Join all the small entries into a single multi-index entry. */
 	xas_set_order(&xas, start, HPAGE_PMD_ORDER);
-	xas_store(&xas, hpage);
+	xas_store(&xas, folio);
 	WARN_ON_ONCE(xas_error(&xas));
 	xas_unlock_irq(&xas);
 
@@ -2156,7 +2160,7 @@ immap_locked:
 	retract_page_tables(mapping, start);
 	if (cc && !cc->is_khugepaged)
 		result = SCAN_PTE_MAPPED_HUGEPAGE;
-	unlock_page(hpage);
+	folio_unlock(folio);
 
 	/*
 	 * The collapse has succeeded, so free the old pages.
@@ -2368,7 +2372,8 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result,
 			progress++;
 			break;
 		}
-		if (!hugepage_vma_check(vma, vma->vm_flags, false, false, true)) {
+		if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false,
+					     true, PMD_ORDER)) {
 skip:
 			progress++;
 			continue;
@@ -2492,7 +2497,7 @@ static void khugepaged_do_scan(struct collapse_control *cc)
 	while (true) {
 		cond_resched();
 
-		if (unlikely(kthread_should_stop() || try_to_freeze()))
+		if (unlikely(kthread_should_stop()))
 			break;
 
 		spin_lock(&khugepaged_mm_lock);
@@ -2705,7 +2710,8 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev,
 
 	*prev = vma;
 
-	if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false))
+	if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false, false,
+				     PMD_ORDER))
 		return -EINVAL;
 
 	cc = kmalloc(sizeof(*cc), GFP_KERNEL);
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 1eacca03bedd..6a540c2b27c5 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -14,17 +14,15 @@
  * The following locks and mutexes are used by kmemleak:
  *
  * - kmemleak_lock (raw_spinlock_t): protects the object_list as well as
- *   del_state modifications and accesses to the object_tree_root (or
- *   object_phys_tree_root). The object_list is the main list holding the
- *   metadata (struct kmemleak_object) for the allocated memory blocks.
- *   The object_tree_root and object_phys_tree_root are red
- *   black trees used to look-up metadata based on a pointer to the
- *   corresponding memory block. The object_phys_tree_root is for objects
- *   allocated with physical address. The kmemleak_object structures are
- *   added to the object_list and object_tree_root (or object_phys_tree_root)
- *   in the create_object() function called from the kmemleak_alloc() (or
- *   kmemleak_alloc_phys()) callback and removed in delete_object() called from
- *   the kmemleak_free() callback
+ *   del_state modifications and accesses to the object trees
+ *   (object_tree_root, object_phys_tree_root, object_percpu_tree_root). The
+ *   object_list is the main list holding the metadata (struct
+ *   kmemleak_object) for the allocated memory blocks. The object trees are
+ *   red black trees used to look-up metadata based on a pointer to the
+ *   corresponding memory block. The kmemleak_object structures are added to
+ *   the object_list and the object tree root in the create_object() function
+ *   called from the kmemleak_alloc{,_phys,_percpu}() callback and removed in
+ *   delete_object() called from the kmemleak_free{,_phys,_percpu}() callback
  * - kmemleak_object.lock (raw_spinlock_t): protects a kmemleak_object.
  *   Accesses to the metadata (e.g. count) are protected by this lock. Note
  *   that some members of this structure may be protected by other means
@@ -178,6 +176,8 @@ struct kmemleak_object {
 #define OBJECT_FULL_SCAN	(1 << 3)
 /* flag set for object allocated with physical address */
 #define OBJECT_PHYS		(1 << 4)
+/* flag set for per-CPU pointers */
+#define OBJECT_PERCPU		(1 << 5)
 
 /* set when __remove_object() called */
 #define DELSTATE_REMOVED	(1 << 0)
@@ -206,6 +206,8 @@ static LIST_HEAD(mem_pool_free_list);
 static struct rb_root object_tree_root = RB_ROOT;
 /* search tree for object (with OBJECT_PHYS flag) boundaries */
 static struct rb_root object_phys_tree_root = RB_ROOT;
+/* search tree for object (with OBJECT_PERCPU flag) boundaries */
+static struct rb_root object_percpu_tree_root = RB_ROOT;
 /* protecting the access to object_list, object_tree_root (or object_phys_tree_root) */
 static DEFINE_RAW_SPINLOCK(kmemleak_lock);
 
@@ -298,7 +300,7 @@ static void hex_dump_object(struct seq_file *seq,
 	const u8 *ptr = (const u8 *)object->pointer;
 	size_t len;
 
-	if (WARN_ON_ONCE(object->flags & OBJECT_PHYS))
+	if (WARN_ON_ONCE(object->flags & (OBJECT_PHYS | OBJECT_PERCPU)))
 		return;
 
 	/* limit the number of lines to HEX_MAX_LINES */
@@ -355,16 +357,14 @@ static void print_unreferenced(struct seq_file *seq,
 	int i;
 	unsigned long *entries;
 	unsigned int nr_entries;
-	unsigned int msecs_age = jiffies_to_msecs(jiffies - object->jiffies);
 
 	nr_entries = stack_depot_fetch(object->trace_handle, &entries);
 	warn_or_seq_printf(seq, "unreferenced object 0x%08lx (size %zu):\n",
 			  object->pointer, object->size);
-	warn_or_seq_printf(seq, "  comm \"%s\", pid %d, jiffies %lu (age %d.%03ds)\n",
-			   object->comm, object->pid, object->jiffies,
-			   msecs_age / 1000, msecs_age % 1000);
+	warn_or_seq_printf(seq, "  comm \"%s\", pid %d, jiffies %lu\n",
+			   object->comm, object->pid, object->jiffies);
 	hex_dump_object(seq, object);
-	warn_or_seq_printf(seq, "  backtrace:\n");
+	warn_or_seq_printf(seq, "  backtrace (crc %x):\n", object->checksum);
 
 	for (i = 0; i < nr_entries; i++) {
 		void *ptr = (void *)entries[i];
@@ -392,6 +392,15 @@ static void dump_object_info(struct kmemleak_object *object)
 		stack_depot_print(object->trace_handle);
 }
 
+static struct rb_root *object_tree(unsigned long objflags)
+{
+	if (objflags & OBJECT_PHYS)
+		return &object_phys_tree_root;
+	if (objflags & OBJECT_PERCPU)
+		return &object_percpu_tree_root;
+	return &object_tree_root;
+}
+
 /*
  * Look-up a memory block metadata (kmemleak_object) in the object search
  * tree based on a pointer value. If alias is 0, only values pointing to the
@@ -399,10 +408,9 @@ static void dump_object_info(struct kmemleak_object *object)
  * when calling this function.
  */
 static struct kmemleak_object *__lookup_object(unsigned long ptr, int alias,
-					       bool is_phys)
+					       unsigned int objflags)
 {
-	struct rb_node *rb = is_phys ? object_phys_tree_root.rb_node :
-			     object_tree_root.rb_node;
+	struct rb_node *rb = object_tree(objflags)->rb_node;
 	unsigned long untagged_ptr = (unsigned long)kasan_reset_tag((void *)ptr);
 
 	while (rb) {
@@ -431,7 +439,7 @@ static struct kmemleak_object *__lookup_object(unsigned long ptr, int alias,
 /* Look-up a kmemleak object which allocated with virtual address. */
 static struct kmemleak_object *lookup_object(unsigned long ptr, int alias)
 {
-	return __lookup_object(ptr, alias, false);
+	return __lookup_object(ptr, alias, 0);
 }
 
 /*
@@ -544,14 +552,14 @@ static void put_object(struct kmemleak_object *object)
  * Look up an object in the object search tree and increase its use_count.
  */
 static struct kmemleak_object *__find_and_get_object(unsigned long ptr, int alias,
-						     bool is_phys)
+						     unsigned int objflags)
 {
 	unsigned long flags;
 	struct kmemleak_object *object;
 
 	rcu_read_lock();
 	raw_spin_lock_irqsave(&kmemleak_lock, flags);
-	object = __lookup_object(ptr, alias, is_phys);
+	object = __lookup_object(ptr, alias, objflags);
 	raw_spin_unlock_irqrestore(&kmemleak_lock, flags);
 
 	/* check whether the object is still available */
@@ -565,19 +573,16 @@ static struct kmemleak_object *__find_and_get_object(unsigned long ptr, int alia
 /* Look up and get an object which allocated with virtual address. */
 static struct kmemleak_object *find_and_get_object(unsigned long ptr, int alias)
 {
-	return __find_and_get_object(ptr, alias, false);
+	return __find_and_get_object(ptr, alias, 0);
 }
 
 /*
- * Remove an object from the object_tree_root (or object_phys_tree_root)
- * and object_list. Must be called with the kmemleak_lock held _if_ kmemleak
- * is still enabled.
+ * Remove an object from its object tree and object_list. Must be called with
+ * the kmemleak_lock held _if_ kmemleak is still enabled.
  */
 static void __remove_object(struct kmemleak_object *object)
 {
-	rb_erase(&object->rb_node, object->flags & OBJECT_PHYS ?
-				   &object_phys_tree_root :
-				   &object_tree_root);
+	rb_erase(&object->rb_node, object_tree(object->flags));
 	if (!(object->del_state & DELSTATE_NO_DELETE))
 		list_del_rcu(&object->object_list);
 	object->del_state |= DELSTATE_REMOVED;
@@ -585,11 +590,11 @@ static void __remove_object(struct kmemleak_object *object)
 
 static struct kmemleak_object *__find_and_remove_object(unsigned long ptr,
 							int alias,
-							bool is_phys)
+							unsigned int objflags)
 {
 	struct kmemleak_object *object;
 
-	object = __lookup_object(ptr, alias, is_phys);
+	object = __lookup_object(ptr, alias, objflags);
 	if (object)
 		__remove_object(object);
 
@@ -597,19 +602,18 @@ static struct kmemleak_object *__find_and_remove_object(unsigned long ptr,
 }
 
 /*
- * Look up an object in the object search tree and remove it from both
- * object_tree_root (or object_phys_tree_root) and object_list. The
- * returned object's use_count should be at least 1, as initially set
- * by create_object().
+ * Look up an object in the object search tree and remove it from both object
+ * tree root and object_list. The returned object's use_count should be at
+ * least 1, as initially set by create_object().
  */
 static struct kmemleak_object *find_and_remove_object(unsigned long ptr, int alias,
-						      bool is_phys)
+						      unsigned int objflags)
 {
 	unsigned long flags;
 	struct kmemleak_object *object;
 
 	raw_spin_lock_irqsave(&kmemleak_lock, flags);
-	object = __find_and_remove_object(ptr, alias, is_phys);
+	object = __find_and_remove_object(ptr, alias, objflags);
 	raw_spin_unlock_irqrestore(&kmemleak_lock, flags);
 
 	return object;
@@ -642,32 +646,16 @@ static struct kmemleak_object *__alloc_object(gfp_t gfp)
 	if (!object) {
 		pr_warn("Cannot allocate a kmemleak_object structure\n");
 		kmemleak_disable();
+		return NULL;
 	}
 
-	return object;
-}
-
-static int __link_object(struct kmemleak_object *object, unsigned long ptr,
-			 size_t size, int min_count, bool is_phys)
-{
-
-	struct kmemleak_object *parent;
-	struct rb_node **link, *rb_parent;
-	unsigned long untagged_ptr;
-	unsigned long untagged_objp;
-
 	INIT_LIST_HEAD(&object->object_list);
 	INIT_LIST_HEAD(&object->gray_list);
 	INIT_HLIST_HEAD(&object->area_list);
 	raw_spin_lock_init(&object->lock);
 	atomic_set(&object->use_count, 1);
-	object->flags = OBJECT_ALLOCATED | (is_phys ? OBJECT_PHYS : 0);
-	object->pointer = ptr;
-	object->size = kfence_ksize((void *)ptr) ?: size;
 	object->excess_ref = 0;
-	object->min_count = min_count;
 	object->count = 0;			/* white color initially */
-	object->jiffies = jiffies;
 	object->checksum = 0;
 	object->del_state = 0;
 
@@ -692,17 +680,34 @@ static int __link_object(struct kmemleak_object *object, unsigned long ptr,
 	/* kernel backtrace */
 	object->trace_handle = set_track_prepare();
 
+	return object;
+}
+
+static int __link_object(struct kmemleak_object *object, unsigned long ptr,
+			 size_t size, int min_count, unsigned int objflags)
+{
+
+	struct kmemleak_object *parent;
+	struct rb_node **link, *rb_parent;
+	unsigned long untagged_ptr;
+	unsigned long untagged_objp;
+
+	object->flags = OBJECT_ALLOCATED | objflags;
+	object->pointer = ptr;
+	object->size = kfence_ksize((void *)ptr) ?: size;
+	object->min_count = min_count;
+	object->jiffies = jiffies;
+
 	untagged_ptr = (unsigned long)kasan_reset_tag((void *)ptr);
 	/*
 	 * Only update min_addr and max_addr with object
 	 * storing virtual address.
 	 */
-	if (!is_phys) {
+	if (!(objflags & (OBJECT_PHYS | OBJECT_PERCPU))) {
 		min_addr = min(min_addr, untagged_ptr);
 		max_addr = max(max_addr, untagged_ptr + size);
 	}
-	link = is_phys ? &object_phys_tree_root.rb_node :
-		&object_tree_root.rb_node;
+	link = &object_tree(objflags)->rb_node;
 	rb_parent = NULL;
 	while (*link) {
 		rb_parent = *link;
@@ -724,8 +729,7 @@ static int __link_object(struct kmemleak_object *object, unsigned long ptr,
 		}
 	}
 	rb_link_node(&object->rb_node, rb_parent, link);
-	rb_insert_color(&object->rb_node, is_phys ? &object_phys_tree_root :
-					  &object_tree_root);
+	rb_insert_color(&object->rb_node, object_tree(objflags));
 	list_add_tail_rcu(&object->object_list, &object_list);
 
 	return 0;
@@ -733,11 +737,10 @@ static int __link_object(struct kmemleak_object *object, unsigned long ptr,
 
 /*
  * Create the metadata (struct kmemleak_object) corresponding to an allocated
- * memory block and add it to the object_list and object_tree_root (or
- * object_phys_tree_root).
+ * memory block and add it to the object_list and object tree.
  */
 static void __create_object(unsigned long ptr, size_t size,
-				int min_count, gfp_t gfp, bool is_phys)
+				int min_count, gfp_t gfp, unsigned int objflags)
 {
 	struct kmemleak_object *object;
 	unsigned long flags;
@@ -748,7 +751,7 @@ static void __create_object(unsigned long ptr, size_t size,
 		return;
 
 	raw_spin_lock_irqsave(&kmemleak_lock, flags);
-	ret = __link_object(object, ptr, size, min_count, is_phys);
+	ret = __link_object(object, ptr, size, min_count, objflags);
 	raw_spin_unlock_irqrestore(&kmemleak_lock, flags);
 	if (ret)
 		mem_pool_free(object);
@@ -758,14 +761,21 @@ static void __create_object(unsigned long ptr, size_t size,
 static void create_object(unsigned long ptr, size_t size,
 			  int min_count, gfp_t gfp)
 {
-	__create_object(ptr, size, min_count, gfp, false);
+	__create_object(ptr, size, min_count, gfp, 0);
 }
 
 /* Create kmemleak object which allocated with physical address. */
 static void create_object_phys(unsigned long ptr, size_t size,
 			       int min_count, gfp_t gfp)
 {
-	__create_object(ptr, size, min_count, gfp, true);
+	__create_object(ptr, size, min_count, gfp, OBJECT_PHYS);
+}
+
+/* Create kmemleak object corresponding to a per-CPU allocation. */
+static void create_object_percpu(unsigned long ptr, size_t size,
+				 int min_count, gfp_t gfp)
+{
+	__create_object(ptr, size, min_count, gfp, OBJECT_PERCPU);
 }
 
 /*
@@ -792,11 +802,11 @@ static void __delete_object(struct kmemleak_object *object)
  * Look up the metadata (struct kmemleak_object) corresponding to ptr and
  * delete it.
  */
-static void delete_object_full(unsigned long ptr)
+static void delete_object_full(unsigned long ptr, unsigned int objflags)
 {
 	struct kmemleak_object *object;
 
-	object = find_and_remove_object(ptr, 0, false);
+	object = find_and_remove_object(ptr, 0, objflags);
 	if (!object) {
 #ifdef DEBUG
 		kmemleak_warn("Freeing unknown object at 0x%08lx\n",
@@ -812,7 +822,8 @@ static void delete_object_full(unsigned long ptr)
  * delete it. If the memory block is partially freed, the function may create
  * additional metadata for the remaining parts of the block.
  */
-static void delete_object_part(unsigned long ptr, size_t size, bool is_phys)
+static void delete_object_part(unsigned long ptr, size_t size,
+			       unsigned int objflags)
 {
 	struct kmemleak_object *object, *object_l, *object_r;
 	unsigned long start, end, flags;
@@ -826,7 +837,7 @@ static void delete_object_part(unsigned long ptr, size_t size, bool is_phys)
 		goto out;
 
 	raw_spin_lock_irqsave(&kmemleak_lock, flags);
-	object = __find_and_remove_object(ptr, 1, is_phys);
+	object = __find_and_remove_object(ptr, 1, objflags);
 	if (!object) {
 #ifdef DEBUG
 		kmemleak_warn("Partially freeing unknown object at 0x%08lx (size %zu)\n",
@@ -844,11 +855,11 @@ static void delete_object_part(unsigned long ptr, size_t size, bool is_phys)
 	end = object->pointer + object->size;
 	if ((ptr > start) &&
 	    !__link_object(object_l, start, ptr - start,
-			   object->min_count, is_phys))
+			   object->min_count, objflags))
 		object_l = NULL;
 	if ((ptr + size < end) &&
 	    !__link_object(object_r, ptr + size, end - ptr - size,
-			   object->min_count, is_phys))
+			   object->min_count, objflags))
 		object_r = NULL;
 
 unlock:
@@ -879,11 +890,11 @@ static void paint_it(struct kmemleak_object *object, int color)
 	raw_spin_unlock_irqrestore(&object->lock, flags);
 }
 
-static void paint_ptr(unsigned long ptr, int color, bool is_phys)
+static void paint_ptr(unsigned long ptr, int color, unsigned int objflags)
 {
 	struct kmemleak_object *object;
 
-	object = __find_and_get_object(ptr, 0, is_phys);
+	object = __find_and_get_object(ptr, 0, objflags);
 	if (!object) {
 		kmemleak_warn("Trying to color unknown object at 0x%08lx as %s\n",
 			      ptr,
@@ -901,16 +912,16 @@ static void paint_ptr(unsigned long ptr, int color, bool is_phys)
  */
 static void make_gray_object(unsigned long ptr)
 {
-	paint_ptr(ptr, KMEMLEAK_GREY, false);
+	paint_ptr(ptr, KMEMLEAK_GREY, 0);
 }
 
 /*
  * Mark the object as black-colored so that it is ignored from scans and
  * reporting.
  */
-static void make_black_object(unsigned long ptr, bool is_phys)
+static void make_black_object(unsigned long ptr, unsigned int objflags)
 {
-	paint_ptr(ptr, KMEMLEAK_BLACK, is_phys);
+	paint_ptr(ptr, KMEMLEAK_BLACK, objflags);
 }
 
 /*
@@ -1046,8 +1057,6 @@ EXPORT_SYMBOL_GPL(kmemleak_alloc);
 void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size,
 				 gfp_t gfp)
 {
-	unsigned int cpu;
-
 	pr_debug("%s(0x%px, %zu)\n", __func__, ptr, size);
 
 	/*
@@ -1055,9 +1064,7 @@ void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size,
 	 * (min_count is set to 0).
 	 */
 	if (kmemleak_enabled && ptr && !IS_ERR(ptr))
-		for_each_possible_cpu(cpu)
-			create_object((unsigned long)per_cpu_ptr(ptr, cpu),
-				      size, 0, gfp);
+		create_object_percpu((unsigned long)ptr, size, 0, gfp);
 }
 EXPORT_SYMBOL_GPL(kmemleak_alloc_percpu);
 
@@ -1098,7 +1105,7 @@ void __ref kmemleak_free(const void *ptr)
 	pr_debug("%s(0x%px)\n", __func__, ptr);
 
 	if (kmemleak_free_enabled && ptr && !IS_ERR(ptr))
-		delete_object_full((unsigned long)ptr);
+		delete_object_full((unsigned long)ptr, 0);
 }
 EXPORT_SYMBOL_GPL(kmemleak_free);
 
@@ -1116,7 +1123,7 @@ void __ref kmemleak_free_part(const void *ptr, size_t size)
 	pr_debug("%s(0x%px)\n", __func__, ptr);
 
 	if (kmemleak_enabled && ptr && !IS_ERR(ptr))
-		delete_object_part((unsigned long)ptr, size, false);
+		delete_object_part((unsigned long)ptr, size, 0);
 }
 EXPORT_SYMBOL_GPL(kmemleak_free_part);
 
@@ -1129,14 +1136,10 @@ EXPORT_SYMBOL_GPL(kmemleak_free_part);
  */
 void __ref kmemleak_free_percpu(const void __percpu *ptr)
 {
-	unsigned int cpu;
-
 	pr_debug("%s(0x%px)\n", __func__, ptr);
 
 	if (kmemleak_free_enabled && ptr && !IS_ERR(ptr))
-		for_each_possible_cpu(cpu)
-			delete_object_full((unsigned long)per_cpu_ptr(ptr,
-								      cpu));
+		delete_object_full((unsigned long)ptr, OBJECT_PERCPU);
 }
 EXPORT_SYMBOL_GPL(kmemleak_free_percpu);
 
@@ -1150,6 +1153,7 @@ EXPORT_SYMBOL_GPL(kmemleak_free_percpu);
 void __ref kmemleak_update_trace(const void *ptr)
 {
 	struct kmemleak_object *object;
+	depot_stack_handle_t trace_handle;
 	unsigned long flags;
 
 	pr_debug("%s(0x%px)\n", __func__, ptr);
@@ -1166,8 +1170,9 @@ void __ref kmemleak_update_trace(const void *ptr)
 		return;
 	}
 
+	trace_handle = set_track_prepare();
 	raw_spin_lock_irqsave(&object->lock, flags);
-	object->trace_handle = set_track_prepare();
+	object->trace_handle = trace_handle;
 	raw_spin_unlock_irqrestore(&object->lock, flags);
 
 	put_object(object);
@@ -1204,7 +1209,7 @@ void __ref kmemleak_ignore(const void *ptr)
 	pr_debug("%s(0x%px)\n", __func__, ptr);
 
 	if (kmemleak_enabled && ptr && !IS_ERR(ptr))
-		make_black_object((unsigned long)ptr, false);
+		make_black_object((unsigned long)ptr, 0);
 }
 EXPORT_SYMBOL(kmemleak_ignore);
 
@@ -1278,7 +1283,7 @@ void __ref kmemleak_free_part_phys(phys_addr_t phys, size_t size)
 	pr_debug("%s(0x%px)\n", __func__, &phys);
 
 	if (kmemleak_enabled)
-		delete_object_part((unsigned long)phys, size, true);
+		delete_object_part((unsigned long)phys, size, OBJECT_PHYS);
 }
 EXPORT_SYMBOL(kmemleak_free_part_phys);
 
@@ -1292,7 +1297,7 @@ void __ref kmemleak_ignore_phys(phys_addr_t phys)
 	pr_debug("%s(0x%px)\n", __func__, &phys);
 
 	if (kmemleak_enabled)
-		make_black_object((unsigned long)phys, true);
+		make_black_object((unsigned long)phys, OBJECT_PHYS);
 }
 EXPORT_SYMBOL(kmemleak_ignore_phys);
 
@@ -1303,7 +1308,7 @@ static bool update_checksum(struct kmemleak_object *object)
 {
 	u32 old_csum = object->checksum;
 
-	if (WARN_ON_ONCE(object->flags & OBJECT_PHYS))
+	if (WARN_ON_ONCE(object->flags & (OBJECT_PHYS | OBJECT_PERCPU)))
 		return false;
 
 	kasan_disable_current();
@@ -1459,7 +1464,6 @@ static void scan_object(struct kmemleak_object *object)
 {
 	struct kmemleak_scan_area *area;
 	unsigned long flags;
-	void *obj_ptr;
 
 	/*
 	 * Once the object->lock is acquired, the corresponding memory block
@@ -1472,14 +1476,27 @@ static void scan_object(struct kmemleak_object *object)
 		/* already freed object */
 		goto out;
 
-	obj_ptr = object->flags & OBJECT_PHYS ?
-		  __va((phys_addr_t)object->pointer) :
-		  (void *)object->pointer;
+	if (object->flags & OBJECT_PERCPU) {
+		unsigned int cpu;
 
-	if (hlist_empty(&object->area_list) ||
+		for_each_possible_cpu(cpu) {
+			void *start = per_cpu_ptr((void __percpu *)object->pointer, cpu);
+			void *end = start + object->size;
+
+			scan_block(start, end, object);
+
+			raw_spin_unlock_irqrestore(&object->lock, flags);
+			cond_resched();
+			raw_spin_lock_irqsave(&object->lock, flags);
+			if (!(object->flags & OBJECT_ALLOCATED))
+				break;
+		}
+	} else if (hlist_empty(&object->area_list) ||
 	    object->flags & OBJECT_FULL_SCAN) {
-		void *start = obj_ptr;
-		void *end = obj_ptr + object->size;
+		void *start = object->flags & OBJECT_PHYS ?
+				__va((phys_addr_t)object->pointer) :
+				(void *)object->pointer;
+		void *end = start + object->size;
 		void *next;
 
 		do {
@@ -1494,11 +1511,12 @@ static void scan_object(struct kmemleak_object *object)
 			cond_resched();
 			raw_spin_lock_irqsave(&object->lock, flags);
 		} while (object->flags & OBJECT_ALLOCATED);
-	} else
+	} else {
 		hlist_for_each_entry(area, &object->area_list, node)
 			scan_block((void *)area->start,
 				   (void *)(area->start + area->size),
 				   object);
+	}
 out:
 	raw_spin_unlock_irqrestore(&object->lock, flags);
 }
diff --git a/mm/kmsan/core.c b/mm/kmsan/core.c
index c19f47af0424..cf2d70e9c9a5 100644
--- a/mm/kmsan/core.c
+++ b/mm/kmsan/core.c
@@ -76,7 +76,7 @@ depot_stack_handle_t kmsan_save_stack_with_flags(gfp_t flags,
 	/* Don't sleep. */
 	flags &= ~(__GFP_DIRECT_RECLAIM | __GFP_KSWAPD_RECLAIM);
 
-	handle = __stack_depot_save(entries, nr_entries, flags, true);
+	handle = stack_depot_save(entries, nr_entries, flags);
 	return stack_depot_set_extra_bits(handle, extra);
 }
 
@@ -185,11 +185,10 @@ depot_stack_handle_t kmsan_internal_chain_origin(depot_stack_handle_t id)
 	/*
 	 * @entries is a local var in non-instrumented code, so KMSAN does not
 	 * know it is initialized. Explicitly unpoison it to avoid false
-	 * positives when __stack_depot_save() passes it to instrumented code.
+	 * positives when stack_depot_save() passes it to instrumented code.
 	 */
 	kmsan_internal_unpoison_memory(entries, sizeof(entries), false);
-	handle = __stack_depot_save(entries, ARRAY_SIZE(entries), __GFP_HIGH,
-				    true);
+	handle = stack_depot_save(entries, ARRAY_SIZE(entries), __GFP_HIGH);
 	return stack_depot_set_extra_bits(handle, extra_bits);
 }
 
diff --git a/mm/kmsan/init.c b/mm/kmsan/init.c
index ffedf4dbc49d..3ac3b8921d36 100644
--- a/mm/kmsan/init.c
+++ b/mm/kmsan/init.c
@@ -96,7 +96,7 @@ void __init kmsan_init_shadow(void)
 struct metadata_page_pair {
 	struct page *shadow, *origin;
 };
-static struct metadata_page_pair held_back[MAX_ORDER + 1] __initdata;
+static struct metadata_page_pair held_back[NR_PAGE_ORDERS] __initdata;
 
 /*
  * Eager metadata allocation. When the memblock allocator is freeing pages to
@@ -141,7 +141,7 @@ struct smallstack {
 
 static struct smallstack collect = {
 	.index = 0,
-	.order = MAX_ORDER,
+	.order = MAX_PAGE_ORDER,
 };
 
 static void smallstack_push(struct smallstack *stack, struct page *pages)
@@ -211,8 +211,8 @@ static void kmsan_memblock_discard(void)
 	 *    order=N-1,
 	 *  - repeat.
 	 */
-	collect.order = MAX_ORDER;
-	for (int i = MAX_ORDER; i >= 0; i--) {
+	collect.order = MAX_PAGE_ORDER;
+	for (int i = MAX_PAGE_ORDER; i >= 0; i--) {
 		if (held_back[i].shadow)
 			smallstack_push(&collect, held_back[i].shadow);
 		if (held_back[i].origin)
diff --git a/mm/ksm.c b/mm/ksm.c
index 7efcc68ccc6e..8c001819cf10 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -21,6 +21,7 @@
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/coredump.h>
+#include <linux/sched/cputime.h>
 #include <linux/rwsem.h>
 #include <linux/pagemap.h>
 #include <linux/rmap.h>
@@ -248,6 +249,9 @@ static struct kmem_cache *rmap_item_cache;
 static struct kmem_cache *stable_node_cache;
 static struct kmem_cache *mm_slot_cache;
 
+/* Default number of pages to scan per batch */
+#define DEFAULT_PAGES_TO_SCAN 100
+
 /* The number of pages scanned */
 static unsigned long ksm_pages_scanned;
 
@@ -276,7 +280,7 @@ static unsigned int ksm_stable_node_chains_prune_millisecs = 2000;
 static int ksm_max_page_sharing = 256;
 
 /* Number of pages ksmd should scan in one batch */
-static unsigned int ksm_thread_pages_to_scan = 100;
+static unsigned int ksm_thread_pages_to_scan = DEFAULT_PAGES_TO_SCAN;
 
 /* Milliseconds ksmd should sleep between batches */
 static unsigned int ksm_thread_sleep_millisecs = 20;
@@ -297,6 +301,172 @@ unsigned long ksm_zero_pages;
 /* The number of pages that have been skipped due to "smart scanning" */
 static unsigned long ksm_pages_skipped;
 
+/* Don't scan more than max pages per batch. */
+static unsigned long ksm_advisor_max_pages_to_scan = 30000;
+
+/* Min CPU for scanning pages per scan */
+#define KSM_ADVISOR_MIN_CPU 10
+
+/* Max CPU for scanning pages per scan */
+static unsigned int ksm_advisor_max_cpu =  70;
+
+/* Target scan time in seconds to analyze all KSM candidate pages. */
+static unsigned long ksm_advisor_target_scan_time = 200;
+
+/* Exponentially weighted moving average. */
+#define EWMA_WEIGHT 30
+
+/**
+ * struct advisor_ctx - metadata for KSM advisor
+ * @start_scan: start time of the current scan
+ * @scan_time: scan time of previous scan
+ * @change: change in percent to pages_to_scan parameter
+ * @cpu_time: cpu time consumed by the ksmd thread in the previous scan
+ */
+struct advisor_ctx {
+	ktime_t start_scan;
+	unsigned long scan_time;
+	unsigned long change;
+	unsigned long long cpu_time;
+};
+static struct advisor_ctx advisor_ctx;
+
+/* Define different advisor's */
+enum ksm_advisor_type {
+	KSM_ADVISOR_NONE,
+	KSM_ADVISOR_SCAN_TIME,
+};
+static enum ksm_advisor_type ksm_advisor;
+
+#ifdef CONFIG_SYSFS
+/*
+ * Only called through the sysfs control interface:
+ */
+
+/* At least scan this many pages per batch. */
+static unsigned long ksm_advisor_min_pages_to_scan = 500;
+
+static void set_advisor_defaults(void)
+{
+	if (ksm_advisor == KSM_ADVISOR_NONE) {
+		ksm_thread_pages_to_scan = DEFAULT_PAGES_TO_SCAN;
+	} else if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) {
+		advisor_ctx = (const struct advisor_ctx){ 0 };
+		ksm_thread_pages_to_scan = ksm_advisor_min_pages_to_scan;
+	}
+}
+#endif /* CONFIG_SYSFS */
+
+static inline void advisor_start_scan(void)
+{
+	if (ksm_advisor == KSM_ADVISOR_SCAN_TIME)
+		advisor_ctx.start_scan = ktime_get();
+}
+
+/*
+ * Use previous scan time if available, otherwise use current scan time as an
+ * approximation for the previous scan time.
+ */
+static inline unsigned long prev_scan_time(struct advisor_ctx *ctx,
+					   unsigned long scan_time)
+{
+	return ctx->scan_time ? ctx->scan_time : scan_time;
+}
+
+/* Calculate exponential weighted moving average */
+static unsigned long ewma(unsigned long prev, unsigned long curr)
+{
+	return ((100 - EWMA_WEIGHT) * prev + EWMA_WEIGHT * curr) / 100;
+}
+
+/*
+ * The scan time advisor is based on the current scan rate and the target
+ * scan rate.
+ *
+ *      new_pages_to_scan = pages_to_scan * (scan_time / target_scan_time)
+ *
+ * To avoid perturbations it calculates a change factor of previous changes.
+ * A new change factor is calculated for each iteration and it uses an
+ * exponentially weighted moving average. The new pages_to_scan value is
+ * multiplied with that change factor:
+ *
+ *      new_pages_to_scan *= change facor
+ *
+ * The new_pages_to_scan value is limited by the cpu min and max values. It
+ * calculates the cpu percent for the last scan and calculates the new
+ * estimated cpu percent cost for the next scan. That value is capped by the
+ * cpu min and max setting.
+ *
+ * In addition the new pages_to_scan value is capped by the max and min
+ * limits.
+ */
+static void scan_time_advisor(void)
+{
+	unsigned int cpu_percent;
+	unsigned long cpu_time;
+	unsigned long cpu_time_diff;
+	unsigned long cpu_time_diff_ms;
+	unsigned long pages;
+	unsigned long per_page_cost;
+	unsigned long factor;
+	unsigned long change;
+	unsigned long last_scan_time;
+	unsigned long scan_time;
+
+	/* Convert scan time to seconds */
+	scan_time = div_s64(ktime_ms_delta(ktime_get(), advisor_ctx.start_scan),
+			    MSEC_PER_SEC);
+	scan_time = scan_time ? scan_time : 1;
+
+	/* Calculate CPU consumption of ksmd background thread */
+	cpu_time = task_sched_runtime(current);
+	cpu_time_diff = cpu_time - advisor_ctx.cpu_time;
+	cpu_time_diff_ms = cpu_time_diff / 1000 / 1000;
+
+	cpu_percent = (cpu_time_diff_ms * 100) / (scan_time * 1000);
+	cpu_percent = cpu_percent ? cpu_percent : 1;
+	last_scan_time = prev_scan_time(&advisor_ctx, scan_time);
+
+	/* Calculate scan time as percentage of target scan time */
+	factor = ksm_advisor_target_scan_time * 100 / scan_time;
+	factor = factor ? factor : 1;
+
+	/*
+	 * Calculate scan time as percentage of last scan time and use
+	 * exponentially weighted average to smooth it
+	 */
+	change = scan_time * 100 / last_scan_time;
+	change = change ? change : 1;
+	change = ewma(advisor_ctx.change, change);
+
+	/* Calculate new scan rate based on target scan rate. */
+	pages = ksm_thread_pages_to_scan * 100 / factor;
+	/* Update pages_to_scan by weighted change percentage. */
+	pages = pages * change / 100;
+
+	/* Cap new pages_to_scan value */
+	per_page_cost = ksm_thread_pages_to_scan / cpu_percent;
+	per_page_cost = per_page_cost ? per_page_cost : 1;
+
+	pages = min(pages, per_page_cost * ksm_advisor_max_cpu);
+	pages = max(pages, per_page_cost * KSM_ADVISOR_MIN_CPU);
+	pages = min(pages, ksm_advisor_max_pages_to_scan);
+
+	/* Update advisor context */
+	advisor_ctx.change = change;
+	advisor_ctx.scan_time = scan_time;
+	advisor_ctx.cpu_time = cpu_time;
+
+	ksm_thread_pages_to_scan = pages;
+	trace_ksm_advisor(scan_time, pages, cpu_percent);
+}
+
+static void advisor_stop_scan(void)
+{
+	if (ksm_advisor == KSM_ADVISOR_SCAN_TIME)
+		scan_time_advisor();
+}
+
 #ifdef CONFIG_NUMA
 /* Zeroed when merging across nodes is not allowed */
 static unsigned int ksm_merge_across_nodes = 1;
@@ -468,7 +638,7 @@ static int break_ksm_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long nex
 			page = pfn_swap_entry_to_page(entry);
 	}
 	/* return 1 if the page is an normal ksm page or KSM-placed zero page */
-	ret = (page && PageKsm(page)) || is_ksm_zero_pte(*pte);
+	ret = (page && PageKsm(page)) || is_ksm_zero_pte(ptent);
 	pte_unmap_unlock(pte, ptl);
 	return ret;
 }
@@ -1099,9 +1269,9 @@ error:
 static u32 calc_checksum(struct page *page)
 {
 	u32 checksum;
-	void *addr = kmap_atomic(page);
+	void *addr = kmap_local_page(page);
 	checksum = xxhash(addr, PAGE_SIZE, 0);
-	kunmap_atomic(addr);
+	kunmap_local(addr);
 	return checksum;
 }
 
@@ -1161,8 +1331,9 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 			goto out_unlock;
 		}
 
-		/* See page_try_share_anon_rmap(): clear PTE first. */
-		if (anon_exclusive && page_try_share_anon_rmap(page)) {
+		/* See folio_try_share_anon_rmap_pte(): clear PTE first. */
+		if (anon_exclusive &&
+		    folio_try_share_anon_rmap_pte(page_folio(page), page)) {
 			set_pte_at(mm, pvmw.address, pvmw.pte, entry);
 			goto out_unlock;
 		}
@@ -1199,6 +1370,7 @@ out:
 static int replace_page(struct vm_area_struct *vma, struct page *page,
 			struct page *kpage, pte_t orig_pte)
 {
+	struct folio *kfolio = page_folio(kpage);
 	struct mm_struct *mm = vma->vm_mm;
 	struct folio *folio;
 	pmd_t *pmd;
@@ -1238,15 +1410,16 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 		goto out_mn;
 	}
 	VM_BUG_ON_PAGE(PageAnonExclusive(page), page);
-	VM_BUG_ON_PAGE(PageAnon(kpage) && PageAnonExclusive(kpage), kpage);
+	VM_BUG_ON_FOLIO(folio_test_anon(kfolio) && PageAnonExclusive(kpage),
+			kfolio);
 
 	/*
 	 * No need to check ksm_use_zero_pages here: we can only have a
 	 * zero_page here if ksm_use_zero_pages was enabled already.
 	 */
 	if (!is_zero_pfn(page_to_pfn(kpage))) {
-		get_page(kpage);
-		page_add_anon_rmap(kpage, vma, addr, RMAP_NONE);
+		folio_get(kfolio);
+		folio_add_anon_rmap_pte(kfolio, kpage, vma, addr, RMAP_NONE);
 		newpte = mk_pte(kpage, vma->vm_page_prot);
 	} else {
 		/*
@@ -1277,7 +1450,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 	set_pte_at_notify(mm, addr, ptep, newpte);
 
 	folio = page_folio(page);
-	page_remove_rmap(page, vma, false);
+	folio_remove_rmap_pte(folio, page, vma);
 	if (!folio_mapped(folio))
 		folio_free_swap(folio);
 	folio_put(folio);
@@ -2401,6 +2574,7 @@ static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page)
 
 	mm_slot = ksm_scan.mm_slot;
 	if (mm_slot == &ksm_mm_head) {
+		advisor_start_scan();
 		trace_ksm_start_scan(ksm_scan.seqnr, ksm_rmap_items);
 
 		/*
@@ -2558,6 +2732,8 @@ no_vmas:
 	if (mm_slot != &ksm_mm_head)
 		goto next_mm;
 
+	advisor_stop_scan();
+
 	trace_ksm_stop_scan(ksm_scan.seqnr, ksm_rmap_items);
 	ksm_scan.seqnr++;
 	return NULL;
@@ -2604,11 +2780,9 @@ static int ksm_scan_thread(void *nothing)
 			ksm_do_scan(ksm_thread_pages_to_scan);
 		mutex_unlock(&ksm_thread_mutex);
 
-		try_to_freeze();
-
 		if (ksmd_should_run()) {
 			sleep_ms = READ_ONCE(ksm_thread_sleep_millisecs);
-			wait_event_interruptible_timeout(ksm_iter_wait,
+			wait_event_freezable_timeout(ksm_iter_wait,
 				sleep_ms != READ_ONCE(ksm_thread_sleep_millisecs),
 				msecs_to_jiffies(sleep_ms));
 		} else {
@@ -2875,49 +3049,53 @@ void __ksm_exit(struct mm_struct *mm)
 	trace_ksm_exit(mm);
 }
 
-struct page *ksm_might_need_to_copy(struct page *page,
-			struct vm_area_struct *vma, unsigned long address)
+struct folio *ksm_might_need_to_copy(struct folio *folio,
+			struct vm_area_struct *vma, unsigned long addr)
 {
-	struct folio *folio = page_folio(page);
+	struct page *page = folio_page(folio, 0);
 	struct anon_vma *anon_vma = folio_anon_vma(folio);
-	struct page *new_page;
+	struct folio *new_folio;
 
-	if (PageKsm(page)) {
-		if (page_stable_node(page) &&
+	if (folio_test_large(folio))
+		return folio;
+
+	if (folio_test_ksm(folio)) {
+		if (folio_stable_node(folio) &&
 		    !(ksm_run & KSM_RUN_UNMERGE))
-			return page;	/* no need to copy it */
+			return folio;	/* no need to copy it */
 	} else if (!anon_vma) {
-		return page;		/* no need to copy it */
-	} else if (page->index == linear_page_index(vma, address) &&
+		return folio;		/* no need to copy it */
+	} else if (folio->index == linear_page_index(vma, addr) &&
 			anon_vma->root == vma->anon_vma->root) {
-		return page;		/* still no need to copy it */
+		return folio;		/* still no need to copy it */
 	}
 	if (PageHWPoison(page))
 		return ERR_PTR(-EHWPOISON);
-	if (!PageUptodate(page))
-		return page;		/* let do_swap_page report the error */
-
-	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
-	if (new_page &&
-	    mem_cgroup_charge(page_folio(new_page), vma->vm_mm, GFP_KERNEL)) {
-		put_page(new_page);
-		new_page = NULL;
-	}
-	if (new_page) {
-		if (copy_mc_user_highpage(new_page, page, address, vma)) {
-			put_page(new_page);
-			memory_failure_queue(page_to_pfn(page), 0);
+	if (!folio_test_uptodate(folio))
+		return folio;		/* let do_swap_page report the error */
+
+	new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr, false);
+	if (new_folio &&
+	    mem_cgroup_charge(new_folio, vma->vm_mm, GFP_KERNEL)) {
+		folio_put(new_folio);
+		new_folio = NULL;
+	}
+	if (new_folio) {
+		if (copy_mc_user_highpage(folio_page(new_folio, 0), page,
+								addr, vma)) {
+			folio_put(new_folio);
+			memory_failure_queue(folio_pfn(folio), 0);
 			return ERR_PTR(-EHWPOISON);
 		}
-		SetPageDirty(new_page);
-		__SetPageUptodate(new_page);
-		__SetPageLocked(new_page);
+		folio_set_dirty(new_folio);
+		__folio_mark_uptodate(new_folio);
+		__folio_set_locked(new_folio);
 #ifdef CONFIG_SWAP
 		count_vm_event(KSM_SWPIN_COPY);
 #endif
 	}
 
-	return new_page;
+	return new_folio;
 }
 
 void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc)
@@ -3244,6 +3422,9 @@ static ssize_t pages_to_scan_store(struct kobject *kobj,
 	unsigned int nr_pages;
 	int err;
 
+	if (ksm_advisor != KSM_ADVISOR_NONE)
+		return -EINVAL;
+
 	err = kstrtouint(buf, 10, &nr_pages);
 	if (err)
 		return -EINVAL;
@@ -3563,6 +3744,130 @@ static ssize_t smart_scan_store(struct kobject *kobj,
 }
 KSM_ATTR(smart_scan);
 
+static ssize_t advisor_mode_show(struct kobject *kobj,
+				 struct kobj_attribute *attr, char *buf)
+{
+	const char *output;
+
+	if (ksm_advisor == KSM_ADVISOR_NONE)
+		output = "[none] scan-time";
+	else if (ksm_advisor == KSM_ADVISOR_SCAN_TIME)
+		output = "none [scan-time]";
+
+	return sysfs_emit(buf, "%s\n", output);
+}
+
+static ssize_t advisor_mode_store(struct kobject *kobj,
+				  struct kobj_attribute *attr, const char *buf,
+				  size_t count)
+{
+	enum ksm_advisor_type curr_advisor = ksm_advisor;
+
+	if (sysfs_streq("scan-time", buf))
+		ksm_advisor = KSM_ADVISOR_SCAN_TIME;
+	else if (sysfs_streq("none", buf))
+		ksm_advisor = KSM_ADVISOR_NONE;
+	else
+		return -EINVAL;
+
+	/* Set advisor default values */
+	if (curr_advisor != ksm_advisor)
+		set_advisor_defaults();
+
+	return count;
+}
+KSM_ATTR(advisor_mode);
+
+static ssize_t advisor_max_cpu_show(struct kobject *kobj,
+				    struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%u\n", ksm_advisor_max_cpu);
+}
+
+static ssize_t advisor_max_cpu_store(struct kobject *kobj,
+				     struct kobj_attribute *attr,
+				     const char *buf, size_t count)
+{
+	int err;
+	unsigned long value;
+
+	err = kstrtoul(buf, 10, &value);
+	if (err)
+		return -EINVAL;
+
+	ksm_advisor_max_cpu = value;
+	return count;
+}
+KSM_ATTR(advisor_max_cpu);
+
+static ssize_t advisor_min_pages_to_scan_show(struct kobject *kobj,
+					struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%lu\n", ksm_advisor_min_pages_to_scan);
+}
+
+static ssize_t advisor_min_pages_to_scan_store(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					const char *buf, size_t count)
+{
+	int err;
+	unsigned long value;
+
+	err = kstrtoul(buf, 10, &value);
+	if (err)
+		return -EINVAL;
+
+	ksm_advisor_min_pages_to_scan = value;
+	return count;
+}
+KSM_ATTR(advisor_min_pages_to_scan);
+
+static ssize_t advisor_max_pages_to_scan_show(struct kobject *kobj,
+					struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%lu\n", ksm_advisor_max_pages_to_scan);
+}
+
+static ssize_t advisor_max_pages_to_scan_store(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					const char *buf, size_t count)
+{
+	int err;
+	unsigned long value;
+
+	err = kstrtoul(buf, 10, &value);
+	if (err)
+		return -EINVAL;
+
+	ksm_advisor_max_pages_to_scan = value;
+	return count;
+}
+KSM_ATTR(advisor_max_pages_to_scan);
+
+static ssize_t advisor_target_scan_time_show(struct kobject *kobj,
+					     struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%lu\n", ksm_advisor_target_scan_time);
+}
+
+static ssize_t advisor_target_scan_time_store(struct kobject *kobj,
+					      struct kobj_attribute *attr,
+					      const char *buf, size_t count)
+{
+	int err;
+	unsigned long value;
+
+	err = kstrtoul(buf, 10, &value);
+	if (err)
+		return -EINVAL;
+	if (value < 1)
+		return -EINVAL;
+
+	ksm_advisor_target_scan_time = value;
+	return count;
+}
+KSM_ATTR(advisor_target_scan_time);
+
 static struct attribute *ksm_attrs[] = {
 	&sleep_millisecs_attr.attr,
 	&pages_to_scan_attr.attr,
@@ -3585,6 +3890,11 @@ static struct attribute *ksm_attrs[] = {
 	&use_zero_pages_attr.attr,
 	&general_profit_attr.attr,
 	&smart_scan_attr.attr,
+	&advisor_mode_attr.attr,
+	&advisor_max_cpu_attr.attr,
+	&advisor_min_pages_to_scan_attr.attr,
+	&advisor_max_pages_to_scan_attr.attr,
+	&advisor_target_scan_time_attr.attr,
 	NULL,
 };
 
diff --git a/mm/list_lru.c b/mm/list_lru.c
index a05e5bef3b40..35b0147542a9 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -59,28 +59,6 @@ list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx)
 	}
 	return &lru->node[nid].lru;
 }
-
-static inline struct list_lru_one *
-list_lru_from_kmem(struct list_lru *lru, int nid, void *ptr,
-		   struct mem_cgroup **memcg_ptr)
-{
-	struct list_lru_node *nlru = &lru->node[nid];
-	struct list_lru_one *l = &nlru->lru;
-	struct mem_cgroup *memcg = NULL;
-
-	if (!list_lru_memcg_aware(lru))
-		goto out;
-
-	memcg = mem_cgroup_from_slab_obj(ptr);
-	if (!memcg)
-		goto out;
-
-	l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg));
-out:
-	if (memcg_ptr)
-		*memcg_ptr = memcg;
-	return l;
-}
 #else
 static void list_lru_register(struct list_lru *lru)
 {
@@ -105,32 +83,21 @@ list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx)
 {
 	return &lru->node[nid].lru;
 }
-
-static inline struct list_lru_one *
-list_lru_from_kmem(struct list_lru *lru, int nid, void *ptr,
-		   struct mem_cgroup **memcg_ptr)
-{
-	if (memcg_ptr)
-		*memcg_ptr = NULL;
-	return &lru->node[nid].lru;
-}
 #endif /* CONFIG_MEMCG_KMEM */
 
-bool list_lru_add(struct list_lru *lru, struct list_head *item)
+bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid,
+		    struct mem_cgroup *memcg)
 {
-	int nid = page_to_nid(virt_to_page(item));
 	struct list_lru_node *nlru = &lru->node[nid];
-	struct mem_cgroup *memcg;
 	struct list_lru_one *l;
 
 	spin_lock(&nlru->lock);
 	if (list_empty(item)) {
-		l = list_lru_from_kmem(lru, nid, item, &memcg);
+		l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg));
 		list_add_tail(item, &l->list);
 		/* Set shrinker bit if the first element was added */
 		if (!l->nr_items++)
-			set_shrinker_bit(memcg, nid,
-					 lru_shrinker_id(lru));
+			set_shrinker_bit(memcg, nid, lru_shrinker_id(lru));
 		nlru->nr_items++;
 		spin_unlock(&nlru->lock);
 		return true;
@@ -140,15 +107,25 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item)
 }
 EXPORT_SYMBOL_GPL(list_lru_add);
 
-bool list_lru_del(struct list_lru *lru, struct list_head *item)
+bool list_lru_add_obj(struct list_lru *lru, struct list_head *item)
 {
 	int nid = page_to_nid(virt_to_page(item));
+	struct mem_cgroup *memcg = list_lru_memcg_aware(lru) ?
+		mem_cgroup_from_slab_obj(item) : NULL;
+
+	return list_lru_add(lru, item, nid, memcg);
+}
+EXPORT_SYMBOL_GPL(list_lru_add_obj);
+
+bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid,
+		    struct mem_cgroup *memcg)
+{
 	struct list_lru_node *nlru = &lru->node[nid];
 	struct list_lru_one *l;
 
 	spin_lock(&nlru->lock);
 	if (!list_empty(item)) {
-		l = list_lru_from_kmem(lru, nid, item, NULL);
+		l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg));
 		list_del_init(item);
 		l->nr_items--;
 		nlru->nr_items--;
@@ -160,6 +137,16 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item)
 }
 EXPORT_SYMBOL_GPL(list_lru_del);
 
+bool list_lru_del_obj(struct list_lru *lru, struct list_head *item)
+{
+	int nid = page_to_nid(virt_to_page(item));
+	struct mem_cgroup *memcg = list_lru_memcg_aware(lru) ?
+		mem_cgroup_from_slab_obj(item) : NULL;
+
+	return list_lru_del(lru, item, nid, memcg);
+}
+EXPORT_SYMBOL_GPL(list_lru_del_obj);
+
 void list_lru_isolate(struct list_lru_one *list, struct list_head *item)
 {
 	list_del_init(item);
@@ -175,6 +162,20 @@ void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item,
 }
 EXPORT_SYMBOL_GPL(list_lru_isolate_move);
 
+void list_lru_putback(struct list_lru *lru, struct list_head *item, int nid,
+		      struct mem_cgroup *memcg)
+{
+	struct list_lru_one *list =
+		list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg));
+
+	if (list_empty(item)) {
+		list_add_tail(item, &list->list);
+		if (!list->nr_items++)
+			set_shrinker_bit(memcg, nid, lru_shrinker_id(lru));
+	}
+}
+EXPORT_SYMBOL_GPL(list_lru_putback);
+
 unsigned long list_lru_count_one(struct list_lru *lru,
 				 int nid, struct mem_cgroup *memcg)
 {
diff --git a/mm/madvise.c b/mm/madvise.c
index cf4d694280e9..912155a94ed5 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -180,7 +180,7 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
 	for (addr = start; addr < end; addr += PAGE_SIZE) {
 		pte_t pte;
 		swp_entry_t entry;
-		struct page *page;
+		struct folio *folio;
 
 		if (!ptep++) {
 			ptep = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
@@ -198,10 +198,10 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
 		pte_unmap_unlock(ptep, ptl);
 		ptep = NULL;
 
-		page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE,
+		folio = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE,
 					     vma, addr, &splug);
-		if (page)
-			put_page(page);
+		if (folio)
+			folio_put(folio);
 	}
 
 	if (ptep)
@@ -223,17 +223,17 @@ static void shmem_swapin_range(struct vm_area_struct *vma,
 {
 	XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start));
 	pgoff_t end_index = linear_page_index(vma, end) - 1;
-	struct page *page;
+	struct folio *folio;
 	struct swap_iocb *splug = NULL;
 
 	rcu_read_lock();
-	xas_for_each(&xas, page, end_index) {
+	xas_for_each(&xas, folio, end_index) {
 		unsigned long addr;
 		swp_entry_t entry;
 
-		if (!xa_is_value(page))
+		if (!xa_is_value(folio))
 			continue;
-		entry = radix_to_swp_entry(page);
+		entry = radix_to_swp_entry(folio);
 		/* There might be swapin error entries in shmem mapping. */
 		if (non_swap_entry(entry))
 			continue;
@@ -243,10 +243,10 @@ static void shmem_swapin_range(struct vm_area_struct *vma,
 		xas_pause(&xas);
 		rcu_read_unlock();
 
-		page = read_swap_cache_async(entry, mapping_gfp_mask(mapping),
+		folio = read_swap_cache_async(entry, mapping_gfp_mask(mapping),
 					     vma, addr, &splug);
-		if (page)
-			put_page(page);
+		if (folio)
+			folio_put(folio);
 
 		rcu_read_lock();
 	}
@@ -335,6 +335,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
 	struct folio *folio = NULL;
 	LIST_HEAD(folio_list);
 	bool pageout_anon_only_filter;
+	unsigned int batch_count = 0;
 
 	if (fatal_signal_pending(current))
 		return -EINTR;
@@ -416,6 +417,7 @@ huge_unlock:
 regular_folio:
 #endif
 	tlb_change_page_size(tlb, PAGE_SIZE);
+restart:
 	start_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	if (!start_pte)
 		return 0;
@@ -424,6 +426,15 @@ regular_folio:
 	for (; addr < end; pte++, addr += PAGE_SIZE) {
 		ptent = ptep_get(pte);
 
+		if (++batch_count == SWAP_CLUSTER_MAX) {
+			batch_count = 0;
+			if (need_resched()) {
+				pte_unmap_unlock(start_pte, ptl);
+				cond_resched();
+				goto restart;
+			}
+		}
+
 		if (pte_none(ptent))
 			continue;
 
diff --git a/mm/memblock.c b/mm/memblock.c
index 5a88d6d24d79..8c194d8afeec 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -735,6 +735,40 @@ int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
 }
 
 /**
+ * memblock_validate_numa_coverage - check if amount of memory with
+ * no node ID assigned is less than a threshold
+ * @threshold_bytes: maximal number of pages that can have unassigned node
+ * ID (in bytes).
+ *
+ * A buggy firmware may report memory that does not belong to any node.
+ * Check if amount of such memory is below @threshold_bytes.
+ *
+ * Return: true on success, false on failure.
+ */
+bool __init_memblock memblock_validate_numa_coverage(unsigned long threshold_bytes)
+{
+	unsigned long nr_pages = 0;
+	unsigned long start_pfn, end_pfn, mem_size_mb;
+	int nid, i;
+
+	/* calculate lose page */
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
+		if (nid == NUMA_NO_NODE)
+			nr_pages += end_pfn - start_pfn;
+	}
+
+	if ((nr_pages << PAGE_SHIFT) >= threshold_bytes) {
+		mem_size_mb = memblock_phys_mem_size() >> 20;
+		pr_err("NUMA: no nodes coverage for %luMB of %luMB RAM\n",
+		       (nr_pages << PAGE_SHIFT) >> 20, mem_size_mb);
+		return false;
+	}
+
+	return true;
+}
+
+
+/**
  * memblock_isolate_range - isolate given range into disjoint memblocks
  * @type: memblock type to isolate range for
  * @base: base of range to isolate
@@ -2079,12 +2113,13 @@ static void __init __free_pages_memory(unsigned long start, unsigned long end)
 		 * Free the pages in the largest chunks alignment allows.
 		 *
 		 * __ffs() behaviour is undefined for 0. start == 0 is
-		 * MAX_ORDER-aligned, set order to MAX_ORDER for the case.
+		 * MAX_PAGE_ORDER-aligned, set order to MAX_PAGE_ORDER for
+		 * the case.
 		 */
 		if (start)
-			order = min_t(int, MAX_ORDER, __ffs(start));
+			order = min_t(int, MAX_PAGE_ORDER, __ffs(start));
 		else
-			order = MAX_ORDER;
+			order = MAX_PAGE_ORDER;
 
 		while (start + (1UL << order) > end)
 			order--;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 774bd6e21e27..e4c8735e7c85 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -64,6 +64,7 @@
 #include <linux/psi.h>
 #include <linux/seq_buf.h>
 #include <linux/sched/isolation.h>
+#include <linux/kmemleak.h>
 #include "internal.h"
 #include <net/sock.h>
 #include <net/ip.h>
@@ -573,116 +574,6 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
 	return mz;
 }
 
-/*
- * memcg and lruvec stats flushing
- *
- * Many codepaths leading to stats update or read are performance sensitive and
- * adding stats flushing in such codepaths is not desirable. So, to optimize the
- * flushing the kernel does:
- *
- * 1) Periodically and asynchronously flush the stats every 2 seconds to not let
- *    rstat update tree grow unbounded.
- *
- * 2) Flush the stats synchronously on reader side only when there are more than
- *    (MEMCG_CHARGE_BATCH * nr_cpus) update events. Though this optimization
- *    will let stats be out of sync by atmost (MEMCG_CHARGE_BATCH * nr_cpus) but
- *    only for 2 seconds due to (1).
- */
-static void flush_memcg_stats_dwork(struct work_struct *w);
-static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork);
-static DEFINE_PER_CPU(unsigned int, stats_updates);
-static atomic_t stats_flush_ongoing = ATOMIC_INIT(0);
-static atomic_t stats_flush_threshold = ATOMIC_INIT(0);
-static u64 flush_next_time;
-
-#define FLUSH_TIME (2UL*HZ)
-
-/*
- * Accessors to ensure that preemption is disabled on PREEMPT_RT because it can
- * not rely on this as part of an acquired spinlock_t lock. These functions are
- * never used in hardirq context on PREEMPT_RT and therefore disabling preemtion
- * is sufficient.
- */
-static void memcg_stats_lock(void)
-{
-	preempt_disable_nested();
-	VM_WARN_ON_IRQS_ENABLED();
-}
-
-static void __memcg_stats_lock(void)
-{
-	preempt_disable_nested();
-}
-
-static void memcg_stats_unlock(void)
-{
-	preempt_enable_nested();
-}
-
-static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val)
-{
-	unsigned int x;
-
-	if (!val)
-		return;
-
-	cgroup_rstat_updated(memcg->css.cgroup, smp_processor_id());
-
-	x = __this_cpu_add_return(stats_updates, abs(val));
-	if (x > MEMCG_CHARGE_BATCH) {
-		/*
-		 * If stats_flush_threshold exceeds the threshold
-		 * (>num_online_cpus()), cgroup stats update will be triggered
-		 * in __mem_cgroup_flush_stats(). Increasing this var further
-		 * is redundant and simply adds overhead in atomic update.
-		 */
-		if (atomic_read(&stats_flush_threshold) <= num_online_cpus())
-			atomic_add(x / MEMCG_CHARGE_BATCH, &stats_flush_threshold);
-		__this_cpu_write(stats_updates, 0);
-	}
-}
-
-static void do_flush_stats(void)
-{
-	/*
-	 * We always flush the entire tree, so concurrent flushers can just
-	 * skip. This avoids a thundering herd problem on the rstat global lock
-	 * from memcg flushers (e.g. reclaim, refault, etc).
-	 */
-	if (atomic_read(&stats_flush_ongoing) ||
-	    atomic_xchg(&stats_flush_ongoing, 1))
-		return;
-
-	WRITE_ONCE(flush_next_time, jiffies_64 + 2*FLUSH_TIME);
-
-	cgroup_rstat_flush(root_mem_cgroup->css.cgroup);
-
-	atomic_set(&stats_flush_threshold, 0);
-	atomic_set(&stats_flush_ongoing, 0);
-}
-
-void mem_cgroup_flush_stats(void)
-{
-	if (atomic_read(&stats_flush_threshold) > num_online_cpus())
-		do_flush_stats();
-}
-
-void mem_cgroup_flush_stats_ratelimited(void)
-{
-	if (time_after64(jiffies_64, READ_ONCE(flush_next_time)))
-		mem_cgroup_flush_stats();
-}
-
-static void flush_memcg_stats_dwork(struct work_struct *w)
-{
-	/*
-	 * Always flush here so that flushing in latency-sensitive paths is
-	 * as cheap as possible.
-	 */
-	do_flush_stats();
-	queue_delayed_work(system_unbound_wq, &stats_flush_dwork, FLUSH_TIME);
-}
-
 /* Subset of vm_event_item to report for memcg event stats */
 static const unsigned int memcg_vm_event_stat[] = {
 	PGPGIN,
@@ -703,6 +594,7 @@ static const unsigned int memcg_vm_event_stat[] = {
 #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
 	ZSWPIN,
 	ZSWPOUT,
+	ZSWPWB,
 #endif
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	THP_FAULT_ALLOC,
@@ -740,6 +632,9 @@ struct memcg_vmstats_percpu {
 	/* Cgroup1: threshold notifications & softlimit tree updates */
 	unsigned long		nr_page_events;
 	unsigned long		targets[MEM_CGROUP_NTARGETS];
+
+	/* Stats updates since the last flush */
+	unsigned int		stats_updates;
 };
 
 struct memcg_vmstats {
@@ -754,8 +649,134 @@ struct memcg_vmstats {
 	/* Pending child counts during tree propagation */
 	long			state_pending[MEMCG_NR_STAT];
 	unsigned long		events_pending[NR_MEMCG_EVENTS];
+
+	/* Stats updates since the last flush */
+	atomic64_t		stats_updates;
 };
 
+/*
+ * memcg and lruvec stats flushing
+ *
+ * Many codepaths leading to stats update or read are performance sensitive and
+ * adding stats flushing in such codepaths is not desirable. So, to optimize the
+ * flushing the kernel does:
+ *
+ * 1) Periodically and asynchronously flush the stats every 2 seconds to not let
+ *    rstat update tree grow unbounded.
+ *
+ * 2) Flush the stats synchronously on reader side only when there are more than
+ *    (MEMCG_CHARGE_BATCH * nr_cpus) update events. Though this optimization
+ *    will let stats be out of sync by atmost (MEMCG_CHARGE_BATCH * nr_cpus) but
+ *    only for 2 seconds due to (1).
+ */
+static void flush_memcg_stats_dwork(struct work_struct *w);
+static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork);
+static u64 flush_last_time;
+
+#define FLUSH_TIME (2UL*HZ)
+
+/*
+ * Accessors to ensure that preemption is disabled on PREEMPT_RT because it can
+ * not rely on this as part of an acquired spinlock_t lock. These functions are
+ * never used in hardirq context on PREEMPT_RT and therefore disabling preemtion
+ * is sufficient.
+ */
+static void memcg_stats_lock(void)
+{
+	preempt_disable_nested();
+	VM_WARN_ON_IRQS_ENABLED();
+}
+
+static void __memcg_stats_lock(void)
+{
+	preempt_disable_nested();
+}
+
+static void memcg_stats_unlock(void)
+{
+	preempt_enable_nested();
+}
+
+
+static bool memcg_should_flush_stats(struct mem_cgroup *memcg)
+{
+	return atomic64_read(&memcg->vmstats->stats_updates) >
+		MEMCG_CHARGE_BATCH * num_online_cpus();
+}
+
+static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val)
+{
+	int cpu = smp_processor_id();
+	unsigned int x;
+
+	if (!val)
+		return;
+
+	cgroup_rstat_updated(memcg->css.cgroup, cpu);
+
+	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
+		x = __this_cpu_add_return(memcg->vmstats_percpu->stats_updates,
+					  abs(val));
+
+		if (x < MEMCG_CHARGE_BATCH)
+			continue;
+
+		/*
+		 * If @memcg is already flush-able, increasing stats_updates is
+		 * redundant. Avoid the overhead of the atomic update.
+		 */
+		if (!memcg_should_flush_stats(memcg))
+			atomic64_add(x, &memcg->vmstats->stats_updates);
+		__this_cpu_write(memcg->vmstats_percpu->stats_updates, 0);
+	}
+}
+
+static void do_flush_stats(struct mem_cgroup *memcg)
+{
+	if (mem_cgroup_is_root(memcg))
+		WRITE_ONCE(flush_last_time, jiffies_64);
+
+	cgroup_rstat_flush(memcg->css.cgroup);
+}
+
+/*
+ * mem_cgroup_flush_stats - flush the stats of a memory cgroup subtree
+ * @memcg: root of the subtree to flush
+ *
+ * Flushing is serialized by the underlying global rstat lock. There is also a
+ * minimum amount of work to be done even if there are no stat updates to flush.
+ * Hence, we only flush the stats if the updates delta exceeds a threshold. This
+ * avoids unnecessary work and contention on the underlying lock.
+ */
+void mem_cgroup_flush_stats(struct mem_cgroup *memcg)
+{
+	if (mem_cgroup_disabled())
+		return;
+
+	if (!memcg)
+		memcg = root_mem_cgroup;
+
+	if (memcg_should_flush_stats(memcg))
+		do_flush_stats(memcg);
+}
+
+void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg)
+{
+	/* Only flush if the periodic flusher is one full cycle late */
+	if (time_after64(jiffies_64, READ_ONCE(flush_last_time) + 2*FLUSH_TIME))
+		mem_cgroup_flush_stats(memcg);
+}
+
+static void flush_memcg_stats_dwork(struct work_struct *w)
+{
+	/*
+	 * Deliberately ignore memcg_should_flush_stats() here so that flushing
+	 * in latency-sensitive paths is as cheap as possible.
+	 */
+	do_flush_stats(root_mem_cgroup);
+	queue_delayed_work(system_unbound_wq, &stats_flush_dwork, FLUSH_TIME);
+}
+
 unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
 {
 	long x = READ_ONCE(memcg->vmstats->state[idx]);
@@ -870,16 +891,15 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 		__mod_memcg_lruvec_state(lruvec, idx, val);
 }
 
-void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx,
+void __lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx,
 			     int val)
 {
-	struct page *head = compound_head(page); /* rmap on tail pages */
 	struct mem_cgroup *memcg;
-	pg_data_t *pgdat = page_pgdat(page);
+	pg_data_t *pgdat = folio_pgdat(folio);
 	struct lruvec *lruvec;
 
 	rcu_read_lock();
-	memcg = page_memcg(head);
+	memcg = folio_memcg(folio);
 	/* Untracked pages have no memcg, no lruvec. Update only the node */
 	if (!memcg) {
 		rcu_read_unlock();
@@ -891,7 +911,7 @@ void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx,
 	__mod_lruvec_state(lruvec, idx, val);
 	rcu_read_unlock();
 }
-EXPORT_SYMBOL(__mod_lruvec_page_state);
+EXPORT_SYMBOL(__lruvec_stat_mod_folio);
 
 void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val)
 {
@@ -1627,7 +1647,7 @@ static void memcg_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
 	 *
 	 * Current memory state:
 	 */
-	mem_cgroup_flush_stats();
+	mem_cgroup_flush_stats(memcg);
 
 	for (i = 0; i < ARRAY_SIZE(memory_stats); i++) {
 		u64 size;
@@ -2936,7 +2956,8 @@ void mem_cgroup_commit_charge(struct folio *folio, struct mem_cgroup *memcg)
  * Moreover, it should not come from DMA buffer and is not readily
  * reclaimable. So those GFP bits should be masked off.
  */
-#define OBJCGS_CLEAR_MASK	(__GFP_DMA | __GFP_RECLAIMABLE | __GFP_ACCOUNT)
+#define OBJCGS_CLEAR_MASK	(__GFP_DMA | __GFP_RECLAIMABLE | \
+				 __GFP_ACCOUNT | __GFP_NOFAIL)
 
 /*
  * mod_objcg_mlstate() may be called with irq enabled, so
@@ -3165,6 +3186,7 @@ __always_inline struct obj_cgroup *current_obj_cgroup(void)
 	return NULL;
 
 from_memcg:
+	objcg = NULL;
 	for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) {
 		/*
 		 * Memcg pointer is protected by scope (see set_active_memcg())
@@ -3175,7 +3197,6 @@ from_memcg:
 		objcg = rcu_dereference_check(memcg->objcg, 1);
 		if (likely(objcg))
 			break;
-		objcg = NULL;
 	}
 
 	return objcg;
@@ -4176,7 +4197,7 @@ static int memcg_numa_stat_show(struct seq_file *m, void *v)
 	int nid;
 	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
 
-	mem_cgroup_flush_stats();
+	mem_cgroup_flush_stats(memcg);
 
 	for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) {
 		seq_printf(m, "%s=%lu", stat->name,
@@ -4257,7 +4278,7 @@ static void memcg1_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
 
 	BUILD_BUG_ON(ARRAY_SIZE(memcg1_stat_names) != ARRAY_SIZE(memcg1_stats));
 
-	mem_cgroup_flush_stats();
+	mem_cgroup_flush_stats(memcg);
 
 	for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) {
 		unsigned long nr;
@@ -4378,7 +4399,7 @@ static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap)
 	 * only one element of the array here.
 	 */
 	for (; i >= 0 && unlikely(t->entries[i].threshold > usage); i--)
-		eventfd_signal(t->entries[i].eventfd, 1);
+		eventfd_signal(t->entries[i].eventfd);
 
 	/* i = current_threshold + 1 */
 	i++;
@@ -4390,7 +4411,7 @@ static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap)
 	 * only one element of the array here.
 	 */
 	for (; i < t->size && unlikely(t->entries[i].threshold <= usage); i++)
-		eventfd_signal(t->entries[i].eventfd, 1);
+		eventfd_signal(t->entries[i].eventfd);
 
 	/* Update current_threshold */
 	t->current_threshold = i - 1;
@@ -4430,7 +4451,7 @@ static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg)
 	spin_lock(&memcg_oom_lock);
 
 	list_for_each_entry(ev, &memcg->oom_notify, list)
-		eventfd_signal(ev->eventfd, 1);
+		eventfd_signal(ev->eventfd);
 
 	spin_unlock(&memcg_oom_lock);
 	return 0;
@@ -4649,7 +4670,7 @@ static int mem_cgroup_oom_register_event(struct mem_cgroup *memcg,
 
 	/* already in OOM ? */
 	if (memcg->under_oom)
-		eventfd_signal(eventfd, 1);
+		eventfd_signal(eventfd);
 	spin_unlock(&memcg_oom_lock);
 
 	return 0;
@@ -4753,7 +4774,7 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
 	struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
 	struct mem_cgroup *parent;
 
-	mem_cgroup_flush_stats();
+	mem_cgroup_flush_stats(memcg);
 
 	*pdirty = memcg_page_state(memcg, NR_FILE_DIRTY);
 	*pwriteback = memcg_page_state(memcg, NR_WRITEBACK);
@@ -4941,7 +4962,7 @@ static void memcg_event_remove(struct work_struct *work)
 	event->unregister_event(memcg, event->eventfd);
 
 	/* Notify userspace the event is going away. */
-	eventfd_signal(event->eventfd, 1);
+	eventfd_signal(event->eventfd);
 
 	eventfd_ctx_put(event->eventfd);
 	kfree(event);
@@ -5149,7 +5170,7 @@ out_kfree:
 	return ret;
 }
 
-#if defined(CONFIG_MEMCG_KMEM) && (defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG))
+#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_SLUB_DEBUG)
 static int mem_cgroup_slab_show(struct seq_file *m, void *p)
 {
 	/*
@@ -5258,8 +5279,7 @@ static struct cftype mem_cgroup_legacy_files[] = {
 		.write = mem_cgroup_reset,
 		.read_u64 = mem_cgroup_read_u64,
 	},
-#if defined(CONFIG_MEMCG_KMEM) && \
-	(defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG))
+#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_SLUB_DEBUG)
 	{
 		.name = "kmem.slabinfo",
 		.seq_show = mem_cgroup_slab_show,
@@ -5517,6 +5537,8 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	WRITE_ONCE(memcg->soft_limit, PAGE_COUNTER_MAX);
 #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
 	memcg->zswap_max = PAGE_COUNTER_MAX;
+	WRITE_ONCE(memcg->zswap_writeback,
+		!parent || READ_ONCE(parent->zswap_writeback));
 #endif
 	page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX);
 	if (parent) {
@@ -5613,6 +5635,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 	page_counter_set_min(&memcg->memory, 0);
 	page_counter_set_low(&memcg->memory, 0);
 
+	zswap_memcg_offline_cleanup(memcg);
+
 	memcg_offline_kmem(memcg);
 	reparent_shrinker_deferred(memcg);
 	wb_memcg_offline(memcg);
@@ -5783,6 +5807,10 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 			}
 		}
 	}
+	statc->stats_updates = 0;
+	/* We are in a per-cpu loop here, only do the atomic write once */
+	if (atomic64_read(&memcg->vmstats->stats_updates))
+		atomic64_set(&memcg->vmstats->stats_updates, 0);
 }
 
 #ifdef CONFIG_MMU
@@ -6782,6 +6810,10 @@ static ssize_t memory_max_write(struct kernfs_open_file *of,
 	return nbytes;
 }
 
+/*
+ * Note: don't forget to update the 'samples/cgroup/memcg_event_listener'
+ * if any new events become available.
+ */
 static void __memory_events_show(struct seq_file *m, atomic_long_t *events)
 {
 	seq_printf(m, "low %lu\n", atomic_long_read(&events[MEMCG_LOW]));
@@ -6838,7 +6870,7 @@ static int memory_numa_stat_show(struct seq_file *m, void *v)
 	int i;
 	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
 
-	mem_cgroup_flush_stats();
+	mem_cgroup_flush_stats(memcg);
 
 	for (i = 0; i < ARRAY_SIZE(memory_stats); i++) {
 		int nid;
@@ -7542,6 +7574,17 @@ void mem_cgroup_migrate(struct folio *old, struct folio *new)
 
 	/* Transfer the charge and the css ref */
 	commit_charge(new, memcg);
+	/*
+	 * If the old folio is a large folio and is in the split queue, it needs
+	 * to be removed from the split queue now, in case getting an incorrect
+	 * split queue in destroy_large_folio() after the memcg of the old folio
+	 * is cleared.
+	 *
+	 * In addition, the old folio is about to be freed after migration, so
+	 * removing from the split queue a bit earlier seems reasonable.
+	 */
+	if (folio_test_large(old) && folio_test_large_rmappable(old))
+		folio_undo_large_rmappable(old);
 	old->memcg_data = 0;
 }
 
@@ -8069,7 +8112,11 @@ bool obj_cgroup_may_zswap(struct obj_cgroup *objcg)
 			break;
 		}
 
-		cgroup_rstat_flush(memcg->css.cgroup);
+		/*
+		 * mem_cgroup_flush_stats() ignores small changes. Use
+		 * do_flush_stats() directly to get accurate stats for charging.
+		 */
+		do_flush_stats(memcg);
 		pages = memcg_page_state(memcg, MEMCG_ZSWAP_B) / PAGE_SIZE;
 		if (pages < max)
 			continue;
@@ -8131,11 +8178,19 @@ void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size)
 	rcu_read_unlock();
 }
 
+bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg)
+{
+	/* if zswap is disabled, do not block pages going to the swapping device */
+	return !is_zswap_enabled() || !memcg || READ_ONCE(memcg->zswap_writeback);
+}
+
 static u64 zswap_current_read(struct cgroup_subsys_state *css,
 			      struct cftype *cft)
 {
-	cgroup_rstat_flush(css->cgroup);
-	return memcg_page_state(mem_cgroup_from_css(css), MEMCG_ZSWAP_B);
+	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+
+	mem_cgroup_flush_stats(memcg);
+	return memcg_page_state(memcg, MEMCG_ZSWAP_B);
 }
 
 static int zswap_max_show(struct seq_file *m, void *v)
@@ -8161,6 +8216,31 @@ static ssize_t zswap_max_write(struct kernfs_open_file *of,
 	return nbytes;
 }
 
+static int zswap_writeback_show(struct seq_file *m, void *v)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
+
+	seq_printf(m, "%d\n", READ_ONCE(memcg->zswap_writeback));
+	return 0;
+}
+
+static ssize_t zswap_writeback_write(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+	int zswap_writeback;
+	ssize_t parse_ret = kstrtoint(strstrip(buf), 0, &zswap_writeback);
+
+	if (parse_ret)
+		return parse_ret;
+
+	if (zswap_writeback != 0 && zswap_writeback != 1)
+		return -EINVAL;
+
+	WRITE_ONCE(memcg->zswap_writeback, zswap_writeback);
+	return nbytes;
+}
+
 static struct cftype zswap_files[] = {
 	{
 		.name = "zswap.current",
@@ -8173,6 +8253,11 @@ static struct cftype zswap_files[] = {
 		.seq_show = zswap_max_show,
 		.write = zswap_max_write,
 	},
+	{
+		.name = "zswap.writeback",
+		.seq_show = zswap_writeback_show,
+		.write = zswap_writeback_write,
+	},
 	{ }	/* terminate */
 };
 #endif /* CONFIG_MEMCG_KMEM && CONFIG_ZSWAP */
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 660c21859118..4f9b61f4a668 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -595,10 +595,9 @@ struct task_struct *task_early_kill(struct task_struct *tsk, int force_early)
 /*
  * Collect processes when the error hit an anonymous page.
  */
-static void collect_procs_anon(struct page *page, struct list_head *to_kill,
-				int force_early)
+static void collect_procs_anon(struct folio *folio, struct page *page,
+		struct list_head *to_kill, int force_early)
 {
-	struct folio *folio = page_folio(page);
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
 	struct anon_vma *av;
@@ -633,12 +632,12 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 /*
  * Collect processes when the error hit a file mapped page.
  */
-static void collect_procs_file(struct page *page, struct list_head *to_kill,
-				int force_early)
+static void collect_procs_file(struct folio *folio, struct page *page,
+		struct list_head *to_kill, int force_early)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
-	struct address_space *mapping = page->mapping;
+	struct address_space *mapping = folio->mapping;
 	pgoff_t pgoff;
 
 	i_mmap_lock_read(mapping);
@@ -679,7 +678,7 @@ static void add_to_kill_fsdax(struct task_struct *tsk, struct page *p,
  */
 static void collect_procs_fsdax(struct page *page,
 		struct address_space *mapping, pgoff_t pgoff,
-		struct list_head *to_kill)
+		struct list_head *to_kill, bool pre_remove)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
@@ -687,8 +686,15 @@ static void collect_procs_fsdax(struct page *page,
 	i_mmap_lock_read(mapping);
 	rcu_read_lock();
 	for_each_process(tsk) {
-		struct task_struct *t = task_early_kill(tsk, true);
+		struct task_struct *t = tsk;
 
+		/*
+		 * Search for all tasks while MF_MEM_PRE_REMOVE is set, because
+		 * the current may not be the one accessing the fsdax page.
+		 * Otherwise, search for the current task.
+		 */
+		if (!pre_remove)
+			t = task_early_kill(tsk, true);
 		if (!t)
 			continue;
 		vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
@@ -704,17 +710,17 @@ static void collect_procs_fsdax(struct page *page,
 /*
  * Collect the processes who have the corrupted page mapped to kill.
  */
-static void collect_procs(struct page *page, struct list_head *tokill,
-				int force_early)
+static void collect_procs(struct folio *folio, struct page *page,
+		struct list_head *tokill, int force_early)
 {
-	if (!page->mapping)
+	if (!folio->mapping)
 		return;
 	if (unlikely(PageKsm(page)))
 		collect_procs_ksm(page, tokill, force_early);
 	else if (PageAnon(page))
-		collect_procs_anon(page, tokill, force_early);
+		collect_procs_anon(folio, page, tokill, force_early);
 	else
-		collect_procs_file(page, tokill, force_early);
+		collect_procs_file(folio, page, tokill, force_early);
 }
 
 struct hwpoison_walk {
@@ -902,39 +908,38 @@ static const char * const action_page_types[] = {
  * The page count will stop it from being freed by unpoison.
  * Stress tests should be aware of this memory leak problem.
  */
-static int delete_from_lru_cache(struct page *p)
+static int delete_from_lru_cache(struct folio *folio)
 {
-	if (isolate_lru_page(p)) {
+	if (folio_isolate_lru(folio)) {
 		/*
 		 * Clear sensible page flags, so that the buddy system won't
-		 * complain when the page is unpoison-and-freed.
+		 * complain when the folio is unpoison-and-freed.
 		 */
-		ClearPageActive(p);
-		ClearPageUnevictable(p);
+		folio_clear_active(folio);
+		folio_clear_unevictable(folio);
 
 		/*
 		 * Poisoned page might never drop its ref count to 0 so we have
 		 * to uncharge it manually from its memcg.
 		 */
-		mem_cgroup_uncharge(page_folio(p));
+		mem_cgroup_uncharge(folio);
 
 		/*
-		 * drop the page count elevated by isolate_lru_page()
+		 * drop the refcount elevated by folio_isolate_lru()
 		 */
-		put_page(p);
+		folio_put(folio);
 		return 0;
 	}
 	return -EIO;
 }
 
-static int truncate_error_page(struct page *p, unsigned long pfn,
+static int truncate_error_folio(struct folio *folio, unsigned long pfn,
 				struct address_space *mapping)
 {
 	int ret = MF_FAILED;
 
-	if (mapping->a_ops->error_remove_page) {
-		struct folio *folio = page_folio(p);
-		int err = mapping->a_ops->error_remove_page(mapping, p);
+	if (mapping->a_ops->error_remove_folio) {
+		int err = mapping->a_ops->error_remove_folio(mapping, folio);
 
 		if (err != 0)
 			pr_info("%#lx: Failed to punch page: %d\n", pfn, err);
@@ -947,7 +952,7 @@ static int truncate_error_page(struct page *p, unsigned long pfn,
 		 * If the file system doesn't support it just invalidate
 		 * This fails on dirty or anything with private pages
 		 */
-		if (invalidate_inode_page(p))
+		if (mapping_evict_folio(mapping, folio))
 			ret = MF_RECOVERED;
 		else
 			pr_info("%#lx: Failed to invalidate\n",	pfn);
@@ -1014,17 +1019,18 @@ static int me_unknown(struct page_state *ps, struct page *p)
  */
 static int me_pagecache_clean(struct page_state *ps, struct page *p)
 {
+	struct folio *folio = page_folio(p);
 	int ret;
 	struct address_space *mapping;
 	bool extra_pins;
 
-	delete_from_lru_cache(p);
+	delete_from_lru_cache(folio);
 
 	/*
-	 * For anonymous pages we're done the only reference left
+	 * For anonymous folios the only reference left
 	 * should be the one m_f() holds.
 	 */
-	if (PageAnon(p)) {
+	if (folio_test_anon(folio)) {
 		ret = MF_RECOVERED;
 		goto out;
 	}
@@ -1036,11 +1042,9 @@ static int me_pagecache_clean(struct page_state *ps, struct page *p)
 	 * has a reference, because it could be file system metadata
 	 * and that's not safe to truncate.
 	 */
-	mapping = page_mapping(p);
+	mapping = folio_mapping(folio);
 	if (!mapping) {
-		/*
-		 * Page has been teared down in the meanwhile
-		 */
+		/* Folio has been torn down in the meantime */
 		ret = MF_FAILED;
 		goto out;
 	}
@@ -1056,12 +1060,12 @@ static int me_pagecache_clean(struct page_state *ps, struct page *p)
 	 *
 	 * Open: to take i_rwsem or not for this? Right now we don't.
 	 */
-	ret = truncate_error_page(p, page_to_pfn(p), mapping);
+	ret = truncate_error_folio(folio, page_to_pfn(p), mapping);
 	if (has_extra_refcount(ps, p, extra_pins))
 		ret = MF_FAILED;
 
 out:
-	unlock_page(p);
+	folio_unlock(folio);
 
 	return ret;
 }
@@ -1139,15 +1143,16 @@ static int me_pagecache_dirty(struct page_state *ps, struct page *p)
  */
 static int me_swapcache_dirty(struct page_state *ps, struct page *p)
 {
+	struct folio *folio = page_folio(p);
 	int ret;
 	bool extra_pins = false;
 
-	ClearPageDirty(p);
+	folio_clear_dirty(folio);
 	/* Trigger EIO in shmem: */
-	ClearPageUptodate(p);
+	folio_clear_uptodate(folio);
 
-	ret = delete_from_lru_cache(p) ? MF_FAILED : MF_DELAYED;
-	unlock_page(p);
+	ret = delete_from_lru_cache(folio) ? MF_FAILED : MF_DELAYED;
+	folio_unlock(folio);
 
 	if (ret == MF_DELAYED)
 		extra_pins = true;
@@ -1165,7 +1170,7 @@ static int me_swapcache_clean(struct page_state *ps, struct page *p)
 
 	delete_from_swap_cache(folio);
 
-	ret = delete_from_lru_cache(p) ? MF_FAILED : MF_RECOVERED;
+	ret = delete_from_lru_cache(folio) ? MF_FAILED : MF_RECOVERED;
 	folio_unlock(folio);
 
 	if (has_extra_refcount(ps, p, false))
@@ -1182,25 +1187,25 @@ static int me_swapcache_clean(struct page_state *ps, struct page *p)
  */
 static int me_huge_page(struct page_state *ps, struct page *p)
 {
+	struct folio *folio = page_folio(p);
 	int res;
-	struct page *hpage = compound_head(p);
 	struct address_space *mapping;
 	bool extra_pins = false;
 
-	mapping = page_mapping(hpage);
+	mapping = folio_mapping(folio);
 	if (mapping) {
-		res = truncate_error_page(hpage, page_to_pfn(p), mapping);
+		res = truncate_error_folio(folio, page_to_pfn(p), mapping);
 		/* The page is kept in page cache. */
 		extra_pins = true;
-		unlock_page(hpage);
+		folio_unlock(folio);
 	} else {
-		unlock_page(hpage);
+		folio_unlock(folio);
 		/*
 		 * migration entry prevents later access on error hugepage,
 		 * so we can free and dissolve it into buddy to save healthy
 		 * subpages.
 		 */
-		put_page(hpage);
+		folio_put(folio);
 		if (__page_handle_poison(p) >= 0) {
 			page_ref_inc(p);
 			res = MF_RECOVERED;
@@ -1571,7 +1576,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * This check implies we don't kill processes if their pages
 	 * are in the swap cache early. Those are always late kills.
 	 */
-	if (!page_mapped(hpage))
+	if (!page_mapped(p))
 		return true;
 
 	if (PageSwapCache(p)) {
@@ -1602,7 +1607,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * mapped in dirty form.  This has to be done before try_to_unmap,
 	 * because ttu takes the rmap data structures down.
 	 */
-	collect_procs(hpage, &tokill, flags & MF_ACTION_REQUIRED);
+	collect_procs(folio, p, &tokill, flags & MF_ACTION_REQUIRED);
 
 	if (PageHuge(hpage) && !PageAnon(hpage)) {
 		/*
@@ -1622,10 +1627,10 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
 		try_to_unmap(folio, ttu);
 	}
 
-	unmap_success = !page_mapped(hpage);
+	unmap_success = !page_mapped(p);
 	if (!unmap_success)
 		pr_err("%#lx: failed to unmap page (mapcount=%d)\n",
-		       pfn, page_mapcount(hpage));
+		       pfn, page_mapcount(p));
 
 	/*
 	 * try_to_unmap() might put mlocked page in lru cache, so call
@@ -1705,7 +1710,7 @@ static void unmap_and_kill(struct list_head *to_kill, unsigned long pfn,
 		 * mapping being torn down is communicated in siginfo, see
 		 * kill_proc()
 		 */
-		loff_t start = (index << PAGE_SHIFT) & ~(size - 1);
+		loff_t start = ((loff_t)index << PAGE_SHIFT) & ~(size - 1);
 
 		unmap_mapping_range(mapping, start, size, 0);
 	}
@@ -1772,7 +1777,7 @@ static int mf_generic_kill_procs(unsigned long long pfn, int flags,
 	 * SIGBUS (i.e. MF_MUST_KILL)
 	 */
 	flags |= MF_ACTION_REQUIRED | MF_MUST_KILL;
-	collect_procs(&folio->page, &to_kill, true);
+	collect_procs(folio, &folio->page, &to_kill, true);
 
 	unmap_and_kill(&to_kill, pfn, folio->mapping, folio->index, flags);
 unlock:
@@ -1795,6 +1800,7 @@ int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
 	dax_entry_t cookie;
 	struct page *page;
 	size_t end = index + count;
+	bool pre_remove = mf_flags & MF_MEM_PRE_REMOVE;
 
 	mf_flags |= MF_ACTION_REQUIRED | MF_MUST_KILL;
 
@@ -1806,9 +1812,14 @@ int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
 		if (!page)
 			goto unlock;
 
-		SetPageHWPoison(page);
+		if (!pre_remove)
+			SetPageHWPoison(page);
 
-		collect_procs_fsdax(page, mapping, index, &to_kill);
+		/*
+		 * The pre_remove case is revoking access, the memory is still
+		 * good and could theoretically be put back into service.
+		 */
+		collect_procs_fsdax(page, mapping, index, &to_kill, pre_remove);
 		unmap_and_kill(&to_kill, page_to_pfn(page), mapping,
 				index, mf_flags);
 unlock:
@@ -2317,8 +2328,8 @@ try_again:
 	 * We use page flags to determine what action should be taken, but
 	 * the flags can be modified by the error containment action.  One
 	 * example is an mlocked page, where PG_mlocked is cleared by
-	 * page_remove_rmap() in try_to_unmap_one(). So to determine page status
-	 * correctly, we save a copy of the page flags at this time.
+	 * folio_remove_rmap_*() in try_to_unmap_one(). So to determine page
+	 * status correctly, we save a copy of the page flags at this time.
 	 */
 	page_flags = p->flags;
 
@@ -2602,37 +2613,37 @@ unlock_mutex:
 }
 EXPORT_SYMBOL(unpoison_memory);
 
-static bool isolate_page(struct page *page, struct list_head *pagelist)
+static bool mf_isolate_folio(struct folio *folio, struct list_head *pagelist)
 {
 	bool isolated = false;
 
-	if (PageHuge(page)) {
-		isolated = isolate_hugetlb(page_folio(page), pagelist);
+	if (folio_test_hugetlb(folio)) {
+		isolated = isolate_hugetlb(folio, pagelist);
 	} else {
-		bool lru = !__PageMovable(page);
+		bool lru = !__folio_test_movable(folio);
 
 		if (lru)
-			isolated = isolate_lru_page(page);
+			isolated = folio_isolate_lru(folio);
 		else
-			isolated = isolate_movable_page(page,
+			isolated = isolate_movable_page(&folio->page,
 							ISOLATE_UNEVICTABLE);
 
 		if (isolated) {
-			list_add(&page->lru, pagelist);
+			list_add(&folio->lru, pagelist);
 			if (lru)
-				inc_node_page_state(page, NR_ISOLATED_ANON +
-						    page_is_file_lru(page));
+				node_stat_add_folio(folio, NR_ISOLATED_ANON +
+						    folio_is_file_lru(folio));
 		}
 	}
 
 	/*
-	 * If we succeed to isolate the page, we grabbed another refcount on
-	 * the page, so we can safely drop the one we got from get_any_page().
-	 * If we failed to isolate the page, it means that we cannot go further
+	 * If we succeed to isolate the folio, we grabbed another refcount on
+	 * the folio, so we can safely drop the one we got from get_any_page().
+	 * If we failed to isolate the folio, it means that we cannot go further
 	 * and we will return an error, so drop the reference we got from
 	 * get_any_page() as well.
 	 */
-	put_page(page);
+	folio_put(folio);
 	return isolated;
 }
 
@@ -2645,40 +2656,40 @@ static int soft_offline_in_use_page(struct page *page)
 {
 	long ret = 0;
 	unsigned long pfn = page_to_pfn(page);
-	struct page *hpage = compound_head(page);
+	struct folio *folio = page_folio(page);
 	char const *msg_page[] = {"page", "hugepage"};
-	bool huge = PageHuge(page);
+	bool huge = folio_test_hugetlb(folio);
 	LIST_HEAD(pagelist);
 	struct migration_target_control mtc = {
 		.nid = NUMA_NO_NODE,
 		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
 	};
 
-	if (!huge && PageTransHuge(hpage)) {
+	if (!huge && folio_test_large(folio)) {
 		if (try_to_split_thp_page(page)) {
 			pr_info("soft offline: %#lx: thp split failed\n", pfn);
 			return -EBUSY;
 		}
-		hpage = page;
+		folio = page_folio(page);
 	}
 
-	lock_page(page);
+	folio_lock(folio);
 	if (!huge)
-		wait_on_page_writeback(page);
+		folio_wait_writeback(folio);
 	if (PageHWPoison(page)) {
-		unlock_page(page);
-		put_page(page);
+		folio_unlock(folio);
+		folio_put(folio);
 		pr_info("soft offline: %#lx page already poisoned\n", pfn);
 		return 0;
 	}
 
-	if (!huge && PageLRU(page) && !PageSwapCache(page))
+	if (!huge && folio_test_lru(folio) && !folio_test_swapcache(folio))
 		/*
 		 * Try to invalidate first. This should work for
 		 * non dirty unmapped page cache pages.
 		 */
-		ret = invalidate_inode_page(page);
-	unlock_page(page);
+		ret = mapping_evict_folio(folio_mapping(folio), folio);
+	folio_unlock(folio);
 
 	if (ret) {
 		pr_info("soft_offline: %#lx: invalidated\n", pfn);
@@ -2686,7 +2697,7 @@ static int soft_offline_in_use_page(struct page *page)
 		return 0;
 	}
 
-	if (isolate_page(hpage, &pagelist)) {
+	if (mf_isolate_folio(folio, &pagelist)) {
 		ret = migrate_pages(&pagelist, alloc_migration_target, NULL,
 			(unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_FAILURE, NULL);
 		if (!ret) {
diff --git a/mm/memory.c b/mm/memory.c
index 1f18ed4a5497..7e1f4849463a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -123,9 +123,7 @@ static bool vmf_orig_pte_uffd_wp(struct vm_fault *vmf)
 /*
  * A number of key systems in x86 including ioremap() rely on the assumption
  * that high_memory defines the upper bound on direct map memory, then end
- * of ZONE_NORMAL.  Under CONFIG_DISCONTIG this means that max_low_pfn and
- * highstart_pfn must be the same; there must be no gap between ZONE_NORMAL
- * and ZONE_HIGHMEM.
+ * of ZONE_NORMAL.
  */
 void *high_memory;
 EXPORT_SYMBOL(high_memory);
@@ -374,6 +372,8 @@ void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas,
 		 * be 0.  This will underflow and is okay.
 		 */
 		next = mas_find(mas, ceiling - 1);
+		if (unlikely(xa_is_zero(next)))
+			next = NULL;
 
 		/*
 		 * Hide vma from rmap and truncate_pagecache before freeing
@@ -395,6 +395,8 @@ void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas,
 			       && !is_vm_hugetlb_page(next)) {
 				vma = next;
 				next = mas_find(mas, ceiling - 1);
+				if (unlikely(xa_is_zero(next)))
+					next = NULL;
 				if (mm_wr_locked)
 					vma_start_write(vma);
 				unlink_anon_vmas(vma);
@@ -706,6 +708,7 @@ static void restore_exclusive_pte(struct vm_area_struct *vma,
 				  struct page *page, unsigned long address,
 				  pte_t *ptep)
 {
+	struct folio *folio = page_folio(page);
 	pte_t orig_pte;
 	pte_t pte;
 	swp_entry_t entry;
@@ -721,14 +724,15 @@ static void restore_exclusive_pte(struct vm_area_struct *vma,
 	else if (is_writable_device_exclusive_entry(entry))
 		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
 
-	VM_BUG_ON(pte_write(pte) && !(PageAnon(page) && PageAnonExclusive(page)));
+	VM_BUG_ON_FOLIO(pte_write(pte) && (!folio_test_anon(folio) &&
+					   PageAnonExclusive(page)), folio);
 
 	/*
 	 * No need to take a page reference as one was already
 	 * created when the swap entry was made.
 	 */
-	if (PageAnon(page))
-		page_add_anon_rmap(page, vma, address, RMAP_NONE);
+	if (folio_test_anon(folio))
+		folio_add_anon_rmap_pte(folio, page, vma, address, RMAP_NONE);
 	else
 		/*
 		 * Currently device exclusive access only supports anonymous
@@ -779,6 +783,7 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	unsigned long vm_flags = dst_vma->vm_flags;
 	pte_t orig_pte = ptep_get(src_pte);
 	pte_t pte = orig_pte;
+	struct folio *folio;
 	struct page *page;
 	swp_entry_t entry = pte_to_swp_entry(orig_pte);
 
@@ -823,6 +828,7 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		}
 	} else if (is_device_private_entry(entry)) {
 		page = pfn_swap_entry_to_page(entry);
+		folio = page_folio(page);
 
 		/*
 		 * Update rss count even for unaddressable pages, as
@@ -833,10 +839,10 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		 * for unaddressable pages, at some point. But for now
 		 * keep things as they are.
 		 */
-		get_page(page);
+		folio_get(folio);
 		rss[mm_counter(page)]++;
 		/* Cannot fail as these pages cannot get pinned. */
-		BUG_ON(page_try_dup_anon_rmap(page, false, src_vma));
+		folio_try_dup_anon_rmap_pte(folio, page, src_vma);
 
 		/*
 		 * We do not preserve soft-dirty information, because so
@@ -950,7 +956,7 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
 		 * future.
 		 */
 		folio_get(folio);
-		if (unlikely(page_try_dup_anon_rmap(page, false, src_vma))) {
+		if (unlikely(folio_try_dup_anon_rmap_pte(folio, page, src_vma))) {
 			/* Page may be pinned, we have to copy. */
 			folio_put(folio);
 			return copy_present_page(dst_vma, src_vma, dst_pte, src_pte,
@@ -959,7 +965,7 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
 		rss[MM_ANONPAGES]++;
 	} else if (page) {
 		folio_get(folio);
-		page_dup_file_rmap(page, false);
+		folio_dup_file_rmap_pte(folio, page);
 		rss[mm_counter_file(page)]++;
 	}
 
@@ -988,12 +994,17 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
 	return 0;
 }
 
-static inline struct folio *page_copy_prealloc(struct mm_struct *src_mm,
-		struct vm_area_struct *vma, unsigned long addr)
+static inline struct folio *folio_prealloc(struct mm_struct *src_mm,
+		struct vm_area_struct *vma, unsigned long addr, bool need_zero)
 {
 	struct folio *new_folio;
 
-	new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr, false);
+	if (need_zero)
+		new_folio = vma_alloc_zeroed_movable_folio(vma, addr);
+	else
+		new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma,
+					    addr, false);
+
 	if (!new_folio)
 		return NULL;
 
@@ -1125,7 +1136,7 @@ again:
 	} else if (ret == -EBUSY) {
 		goto out;
 	} else if (ret ==  -EAGAIN) {
-		prealloc = page_copy_prealloc(src_mm, src_vma, addr);
+		prealloc = folio_prealloc(src_mm, src_vma, addr, false);
 		if (!prealloc)
 			return -ENOMEM;
 	} else if (ret) {
@@ -1423,6 +1434,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	arch_enter_lazy_mmu_mode();
 	do {
 		pte_t ptent = ptep_get(pte);
+		struct folio *folio;
 		struct page *page;
 
 		if (pte_none(ptent))
@@ -1448,21 +1460,22 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 				continue;
 			}
 
+			folio = page_folio(page);
 			delay_rmap = 0;
-			if (!PageAnon(page)) {
+			if (!folio_test_anon(folio)) {
 				if (pte_dirty(ptent)) {
-					set_page_dirty(page);
+					folio_set_dirty(folio);
 					if (tlb_delay_rmap(tlb)) {
 						delay_rmap = 1;
 						force_flush = 1;
 					}
 				}
 				if (pte_young(ptent) && likely(vma_has_recency(vma)))
-					mark_page_accessed(page);
+					folio_mark_accessed(folio);
 			}
 			rss[mm_counter(page)]--;
 			if (!delay_rmap) {
-				page_remove_rmap(page, vma, false);
+				folio_remove_rmap_pte(folio, page, vma);
 				if (unlikely(page_mapcount(page) < 0))
 					print_bad_pte(vma, addr, ptent, page);
 			}
@@ -1478,6 +1491,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 		if (is_device_private_entry(entry) ||
 		    is_device_exclusive_entry(entry)) {
 			page = pfn_swap_entry_to_page(entry);
+			folio = page_folio(page);
 			if (unlikely(!should_zap_page(details, page)))
 				continue;
 			/*
@@ -1489,8 +1503,8 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 			WARN_ON_ONCE(!vma_is_anonymous(vma));
 			rss[mm_counter(page)]--;
 			if (is_device_private_entry(entry))
-				page_remove_rmap(page, vma, false);
-			put_page(page);
+				folio_remove_rmap_pte(folio, page, vma);
+			folio_put(folio);
 		} else if (!non_swap_entry(entry)) {
 			/* Genuine swap entry, hence a private anon page */
 			if (!should_zap_cows(details))
@@ -1517,6 +1531,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 				continue;
 		} else {
 			/* We should have covered all the swap entry types */
+			pr_alert("unrecognized swap entry 0x%lx\n", entry.val);
 			WARN_ON_ONCE(1);
 		}
 		pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
@@ -1743,7 +1758,8 @@ void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas,
 		unmap_single_vma(tlb, vma, start, end, &details,
 				 mm_wr_locked);
 		hugetlb_zap_end(vma, &details);
-	} while ((vma = mas_find(mas, tree_end - 1)) != NULL);
+		vma = mas_find(mas, tree_end - 1);
+	} while (vma && likely(!xa_is_zero(vma)));
 	mmu_notifier_invalidate_range_end(&range);
 }
 
@@ -1836,21 +1852,26 @@ pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
 
 static int validate_page_before_insert(struct page *page)
 {
-	if (PageAnon(page) || PageSlab(page) || page_has_type(page))
+	struct folio *folio = page_folio(page);
+
+	if (folio_test_anon(folio) || folio_test_slab(folio) ||
+	    page_has_type(page))
 		return -EINVAL;
-	flush_dcache_page(page);
+	flush_dcache_folio(folio);
 	return 0;
 }
 
 static int insert_page_into_pte_locked(struct vm_area_struct *vma, pte_t *pte,
 			unsigned long addr, struct page *page, pgprot_t prot)
 {
+	struct folio *folio = page_folio(page);
+
 	if (!pte_none(ptep_get(pte)))
 		return -EBUSY;
 	/* Ok, finally just insert the thing.. */
-	get_page(page);
+	folio_get(folio);
 	inc_mm_counter(vma->vm_mm, mm_counter_file(page));
-	page_add_file_rmap(page, vma, false);
+	folio_add_file_rmap_pte(folio, page, vma);
 	set_pte_at(vma->vm_mm, addr, pte, mk_pte(page, prot));
 	return 0;
 }
@@ -2835,7 +2856,8 @@ static inline int __wp_page_copy_user(struct page *dst, struct page *src,
 	 * just copying from the original user address. If that
 	 * fails, we just zero-fill it. Live with it.
 	 */
-	kaddr = kmap_atomic(dst);
+	kaddr = kmap_local_page(dst);
+	pagefault_disable();
 	uaddr = (void __user *)(addr & PAGE_MASK);
 
 	/*
@@ -2903,7 +2925,8 @@ warn:
 pte_unlock:
 	if (vmf->pte)
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
-	kunmap_atomic(kaddr);
+	pagefault_enable();
+	kunmap_local(kaddr);
 	flush_dcache_page(dst);
 
 	return ret;
@@ -3101,6 +3124,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 	int page_copied = 0;
 	struct mmu_notifier_range range;
 	vm_fault_t ret;
+	bool pfn_is_zero;
 
 	delayacct_wpcopy_start();
 
@@ -3110,16 +3134,13 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 	if (unlikely(ret))
 		goto out;
 
-	if (is_zero_pfn(pte_pfn(vmf->orig_pte))) {
-		new_folio = vma_alloc_zeroed_movable_folio(vma, vmf->address);
-		if (!new_folio)
-			goto oom;
-	} else {
+	pfn_is_zero = is_zero_pfn(pte_pfn(vmf->orig_pte));
+	new_folio = folio_prealloc(mm, vma, vmf->address, pfn_is_zero);
+	if (!new_folio)
+		goto oom;
+
+	if (!pfn_is_zero) {
 		int err;
-		new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma,
-				vmf->address, false);
-		if (!new_folio)
-			goto oom;
 
 		err = __wp_page_copy_user(&new_folio->page, vmf->page, vmf);
 		if (err) {
@@ -3140,10 +3161,6 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 		kmsan_copy_page_meta(&new_folio->page, vmf->page);
 	}
 
-	if (mem_cgroup_charge(new_folio, mm, GFP_KERNEL))
-		goto oom_free_new;
-	folio_throttle_swaprate(new_folio, GFP_KERNEL);
-
 	__folio_mark_uptodate(new_folio);
 
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm,
@@ -3206,10 +3223,10 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 			 * threads.
 			 *
 			 * The critical issue is to order this
-			 * page_remove_rmap with the ptp_clear_flush above.
-			 * Those stores are ordered by (if nothing else,)
+			 * folio_remove_rmap_pte() with the ptp_clear_flush
+			 * above. Those stores are ordered by (if nothing else,)
 			 * the barrier present in the atomic_add_negative
-			 * in page_remove_rmap.
+			 * in folio_remove_rmap_pte();
 			 *
 			 * Then the TLB flush in ptep_clear_flush ensures that
 			 * no process can access the old page before the
@@ -3218,7 +3235,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 			 * mapcount is visible. So transitively, TLBs to
 			 * old page will be flushed before it can be reused.
 			 */
-			page_remove_rmap(vmf->page, vma, false);
+			folio_remove_rmap_pte(old_folio, vmf->page, vma);
 		}
 
 		/* Free the old page.. */
@@ -3242,8 +3259,6 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 
 	delayacct_wpcopy_end();
 	return 0;
-oom_free_new:
-	folio_put(new_folio);
 oom:
 	ret = VM_FAULT_OOM;
 out:
@@ -3623,8 +3638,8 @@ EXPORT_SYMBOL_GPL(unmap_mapping_pages);
 void unmap_mapping_range(struct address_space *mapping,
 		loff_t const holebegin, loff_t const holelen, int even_cows)
 {
-	pgoff_t hba = holebegin >> PAGE_SHIFT;
-	pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	pgoff_t hba = (pgoff_t)(holebegin) >> PAGE_SHIFT;
+	pgoff_t hlen = ((pgoff_t)(holelen) + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
 	/* Check for overflow. */
 	if (sizeof(holelen) > sizeof(hlen)) {
@@ -3874,9 +3889,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 
 				folio_add_lru(folio);
 
-				/* To provide entry to swap_readpage() */
+				/* To provide entry to swap_read_folio() */
 				folio->swap = entry;
-				swap_readpage(page, true, NULL);
+				swap_read_folio(folio, true, NULL);
 				folio->private = NULL;
 			}
 		} else {
@@ -3934,15 +3949,18 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		 * page->index of !PageKSM() pages would be nonlinear inside the
 		 * anon VMA -- PageKSM() is lost on actual swapout.
 		 */
-		page = ksm_might_need_to_copy(page, vma, vmf->address);
-		if (unlikely(!page)) {
+		folio = ksm_might_need_to_copy(folio, vma, vmf->address);
+		if (unlikely(!folio)) {
 			ret = VM_FAULT_OOM;
+			folio = swapcache;
 			goto out_page;
-		} else if (unlikely(PTR_ERR(page) == -EHWPOISON)) {
+		} else if (unlikely(folio == ERR_PTR(-EHWPOISON))) {
 			ret = VM_FAULT_HWPOISON;
+			folio = swapcache;
 			goto out_page;
 		}
-		folio = page_folio(page);
+		if (folio != swapcache)
+			page = folio_page(folio, 0);
 
 		/*
 		 * If we want to map a page that's in the swapcache writable, we
@@ -4060,10 +4078,11 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 
 	/* ksm created a completely new copy */
 	if (unlikely(folio != swapcache && swapcache)) {
-		page_add_new_anon_rmap(page, vma, vmf->address);
+		folio_add_new_anon_rmap(folio, vma, vmf->address);
 		folio_add_lru_vma(folio, vma);
 	} else {
-		page_add_anon_rmap(page, vma, vmf->address, rmap_flags);
+		folio_add_anon_rmap_pte(folio, page, vma, vmf->address,
+					rmap_flags);
 	}
 
 	VM_BUG_ON(!folio_test_anon(folio) ||
@@ -4117,6 +4136,84 @@ out_release:
 	return ret;
 }
 
+static bool pte_range_none(pte_t *pte, int nr_pages)
+{
+	int i;
+
+	for (i = 0; i < nr_pages; i++) {
+		if (!pte_none(ptep_get_lockless(pte + i)))
+			return false;
+	}
+
+	return true;
+}
+
+static struct folio *alloc_anon_folio(struct vm_fault *vmf)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	struct vm_area_struct *vma = vmf->vma;
+	unsigned long orders;
+	struct folio *folio;
+	unsigned long addr;
+	pte_t *pte;
+	gfp_t gfp;
+	int order;
+
+	/*
+	 * If uffd is active for the vma we need per-page fault fidelity to
+	 * maintain the uffd semantics.
+	 */
+	if (unlikely(userfaultfd_armed(vma)))
+		goto fallback;
+
+	/*
+	 * Get a list of all the (large) orders below PMD_ORDER that are enabled
+	 * for this vma. Then filter out the orders that can't be allocated over
+	 * the faulting address and still be fully contained in the vma.
+	 */
+	orders = thp_vma_allowable_orders(vma, vma->vm_flags, false, true, true,
+					  BIT(PMD_ORDER) - 1);
+	orders = thp_vma_suitable_orders(vma, vmf->address, orders);
+
+	if (!orders)
+		goto fallback;
+
+	pte = pte_offset_map(vmf->pmd, vmf->address & PMD_MASK);
+	if (!pte)
+		return ERR_PTR(-EAGAIN);
+
+	/*
+	 * Find the highest order where the aligned range is completely
+	 * pte_none(). Note that all remaining orders will be completely
+	 * pte_none().
+	 */
+	order = highest_order(orders);
+	while (orders) {
+		addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order);
+		if (pte_range_none(pte + pte_index(addr), 1 << order))
+			break;
+		order = next_order(&orders, order);
+	}
+
+	pte_unmap(pte);
+
+	/* Try allocating the highest of the remaining orders. */
+	gfp = vma_thp_gfp_mask(vma);
+	while (orders) {
+		addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order);
+		folio = vma_alloc_folio(gfp, order, vma, addr, true);
+		if (folio) {
+			clear_huge_page(&folio->page, vmf->address, 1 << order);
+			return folio;
+		}
+		order = next_order(&orders, order);
+	}
+
+fallback:
+#endif
+	return vma_alloc_zeroed_movable_folio(vmf->vma, vmf->address);
+}
+
 /*
  * We enter with non-exclusive mmap_lock (to exclude vma changes,
  * but allow concurrent faults), and pte mapped but not yet locked.
@@ -4126,9 +4223,12 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 {
 	bool uffd_wp = vmf_orig_pte_uffd_wp(vmf);
 	struct vm_area_struct *vma = vmf->vma;
+	unsigned long addr = vmf->address;
 	struct folio *folio;
 	vm_fault_t ret = 0;
+	int nr_pages = 1;
 	pte_t entry;
+	int i;
 
 	/* File mapping without ->vm_ops ? */
 	if (vma->vm_flags & VM_SHARED)
@@ -4168,10 +4268,16 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	/* Allocate our own private page. */
 	if (unlikely(anon_vma_prepare(vma)))
 		goto oom;
-	folio = vma_alloc_zeroed_movable_folio(vma, vmf->address);
+	/* Returns NULL on OOM or ERR_PTR(-EAGAIN) if we must retry the fault */
+	folio = alloc_anon_folio(vmf);
+	if (IS_ERR(folio))
+		return 0;
 	if (!folio)
 		goto oom;
 
+	nr_pages = folio_nr_pages(folio);
+	addr = ALIGN_DOWN(vmf->address, nr_pages * PAGE_SIZE);
+
 	if (mem_cgroup_charge(folio, vma->vm_mm, GFP_KERNEL))
 		goto oom_free_page;
 	folio_throttle_swaprate(folio, GFP_KERNEL);
@@ -4188,12 +4294,15 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	if (vma->vm_flags & VM_WRITE)
 		entry = pte_mkwrite(pte_mkdirty(entry), vma);
 
-	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
-			&vmf->ptl);
+	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl);
 	if (!vmf->pte)
 		goto release;
-	if (vmf_pte_changed(vmf)) {
-		update_mmu_tlb(vma, vmf->address, vmf->pte);
+	if (nr_pages == 1 && vmf_pte_changed(vmf)) {
+		update_mmu_tlb(vma, addr, vmf->pte);
+		goto release;
+	} else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) {
+		for (i = 0; i < nr_pages; i++)
+			update_mmu_tlb(vma, addr + PAGE_SIZE * i, vmf->pte + i);
 		goto release;
 	}
 
@@ -4208,16 +4317,17 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 		return handle_userfault(vmf, VM_UFFD_MISSING);
 	}
 
-	inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
-	folio_add_new_anon_rmap(folio, vma, vmf->address);
+	folio_ref_add(folio, nr_pages - 1);
+	add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr_pages);
+	folio_add_new_anon_rmap(folio, vma, addr);
 	folio_add_lru_vma(folio, vma);
 setpte:
 	if (uffd_wp)
 		entry = pte_mkuffd_wp(entry);
-	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry);
+	set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr_pages);
 
 	/* No need to invalidate - it was non-present before */
-	update_mmu_cache_range(vmf, vma, vmf->address, vmf->pte, 1);
+	update_mmu_cache_range(vmf, vma, addr, vmf->pte, nr_pages);
 unlock:
 	if (vmf->pte)
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
@@ -4239,6 +4349,7 @@ oom:
 static vm_fault_t __do_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
+	struct folio *folio;
 	vm_fault_t ret;
 
 	/*
@@ -4267,27 +4378,26 @@ static vm_fault_t __do_fault(struct vm_fault *vmf)
 			    VM_FAULT_DONE_COW)))
 		return ret;
 
+	folio = page_folio(vmf->page);
 	if (unlikely(PageHWPoison(vmf->page))) {
-		struct page *page = vmf->page;
 		vm_fault_t poisonret = VM_FAULT_HWPOISON;
 		if (ret & VM_FAULT_LOCKED) {
-			if (page_mapped(page))
-				unmap_mapping_pages(page_mapping(page),
-						    page->index, 1, false);
-			/* Retry if a clean page was removed from the cache. */
-			if (invalidate_inode_page(page))
+			if (page_mapped(vmf->page))
+				unmap_mapping_folio(folio);
+			/* Retry if a clean folio was removed from the cache. */
+			if (mapping_evict_folio(folio->mapping, folio))
 				poisonret = VM_FAULT_NOPAGE;
-			unlock_page(page);
+			folio_unlock(folio);
 		}
-		put_page(page);
+		folio_put(folio);
 		vmf->page = NULL;
 		return poisonret;
 	}
 
 	if (unlikely(!(ret & VM_FAULT_LOCKED)))
-		lock_page(vmf->page);
+		folio_lock(folio);
 	else
-		VM_BUG_ON_PAGE(!PageLocked(vmf->page), vmf->page);
+		VM_BUG_ON_PAGE(!folio_test_locked(folio), vmf->page);
 
 	return ret;
 }
@@ -4308,17 +4418,17 @@ static void deposit_prealloc_pte(struct vm_fault *vmf)
 
 vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 {
+	struct folio *folio = page_folio(page);
 	struct vm_area_struct *vma = vmf->vma;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
 	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
 	pmd_t entry;
 	vm_fault_t ret = VM_FAULT_FALLBACK;
 
-	if (!transhuge_vma_suitable(vma, haddr))
+	if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER))
 		return ret;
 
-	page = compound_head(page);
-	if (compound_order(page) != HPAGE_PMD_ORDER)
+	if (page != &folio->page || folio_order(folio) != HPAGE_PMD_ORDER)
 		return ret;
 
 	/*
@@ -4327,7 +4437,7 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 	 * check.  This kind of THP just can be PTE mapped.  Access to
 	 * the corrupted subpage should trigger SIGBUS as expected.
 	 */
-	if (unlikely(PageHasHWPoisoned(page)))
+	if (unlikely(folio_test_has_hwpoisoned(folio)))
 		return ret;
 
 	/*
@@ -4351,7 +4461,7 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 
 	add_mm_counter(vma->vm_mm, mm_counter_file(page), HPAGE_PMD_NR);
-	page_add_file_rmap(page, vma, true);
+	folio_add_file_rmap_pmd(folio, page, vma);
 
 	/*
 	 * deposit and withdraw with pmd lock held
@@ -4414,7 +4524,7 @@ void set_pte_range(struct vm_fault *vmf, struct folio *folio,
 		folio_add_lru_vma(folio, vma);
 	} else {
 		add_mm_counter(vma->vm_mm, mm_counter_file(page), nr);
-		folio_add_file_rmap_range(folio, page, nr, vma, false);
+		folio_add_file_rmap_ptes(folio, page, nr, vma);
 	}
 	set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr);
 
@@ -4640,6 +4750,7 @@ static vm_fault_t do_read_fault(struct vm_fault *vmf)
 static vm_fault_t do_cow_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
+	struct folio *folio;
 	vm_fault_t ret;
 
 	ret = vmf_can_call_fault(vmf);
@@ -4648,16 +4759,11 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf)
 	if (ret)
 		return ret;
 
-	vmf->cow_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address);
-	if (!vmf->cow_page)
+	folio = folio_prealloc(vma->vm_mm, vma, vmf->address, false);
+	if (!folio)
 		return VM_FAULT_OOM;
 
-	if (mem_cgroup_charge(page_folio(vmf->cow_page), vma->vm_mm,
-				GFP_KERNEL)) {
-		put_page(vmf->cow_page);
-		return VM_FAULT_OOM;
-	}
-	folio_throttle_swaprate(page_folio(vmf->cow_page), GFP_KERNEL);
+	vmf->cow_page = &folio->page;
 
 	ret = __do_fault(vmf);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
@@ -4666,7 +4772,7 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf)
 		return ret;
 
 	copy_user_highpage(vmf->cow_page, vmf->page, vmf->address, vma);
-	__SetPageUptodate(vmf->cow_page);
+	__folio_mark_uptodate(folio);
 
 	ret |= finish_fault(vmf);
 	unlock_page(vmf->page);
@@ -4675,7 +4781,7 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf)
 		goto uncharge_out;
 	return ret;
 uncharge_out:
-	put_page(vmf->cow_page);
+	folio_put(folio);
 	return ret;
 }
 
@@ -5112,7 +5218,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
 		return VM_FAULT_OOM;
 retry_pud:
 	if (pud_none(*vmf.pud) &&
-	    hugepage_vma_check(vma, vm_flags, false, true, true)) {
+	    thp_vma_allowable_order(vma, vm_flags, false, true, true, PUD_ORDER)) {
 		ret = create_huge_pud(&vmf);
 		if (!(ret & VM_FAULT_FALLBACK))
 			return ret;
@@ -5146,7 +5252,7 @@ retry_pud:
 		goto retry_pud;
 
 	if (pmd_none(*vmf.pmd) &&
-	    hugepage_vma_check(vma, vm_flags, false, true, true)) {
+	    thp_vma_allowable_order(vma, vm_flags, false, true, true, PMD_ORDER)) {
 		ret = create_huge_pmd(&vmf);
 		if (!(ret & VM_FAULT_FALLBACK))
 			return ret;
@@ -5849,7 +5955,7 @@ static int __access_remote_vm(struct mm_struct *mm, unsigned long addr,
 			if (bytes > PAGE_SIZE-offset)
 				bytes = PAGE_SIZE-offset;
 
-			maddr = kmap(page);
+			maddr = kmap_local_page(page);
 			if (write) {
 				copy_to_user_page(vma, page, addr,
 						  maddr + offset, buf, bytes);
@@ -5858,8 +5964,7 @@ static int __access_remote_vm(struct mm_struct *mm, unsigned long addr,
 				copy_from_user_page(vma, page, addr,
 						    buf, maddr + offset, bytes);
 			}
-			kunmap(page);
-			put_page(page);
+			unmap_and_put_page(page, maddr);
 		}
 		len -= bytes;
 		buf += bytes;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index ab41a511e20a..b3c0ff52bb72 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -645,7 +645,7 @@ static void online_pages_range(unsigned long start_pfn, unsigned long nr_pages)
 	unsigned long pfn;
 
 	/*
-	 * Online the pages in MAX_ORDER aligned chunks. The callback might
+	 * Online the pages in MAX_PAGE_ORDER aligned chunks. The callback might
 	 * decide to not expose all pages to the buddy (e.g., expose them
 	 * later). We account all pages as being online and belonging to this
 	 * zone ("present").
@@ -660,12 +660,13 @@ static void online_pages_range(unsigned long start_pfn, unsigned long nr_pages)
 		 * Free to online pages in the largest chunks alignment allows.
 		 *
 		 * __ffs() behaviour is undefined for 0. start == 0 is
-		 * MAX_ORDER-aligned, Set order to MAX_ORDER for the case.
+		 * MAX_PAGE_ORDER-aligned, Set order to MAX_PAGE_ORDER for
+		 * the case.
 		 */
 		if (pfn)
-			order = min_t(int, MAX_ORDER, __ffs(pfn));
+			order = min_t(int, MAX_PAGE_ORDER, __ffs(pfn));
 		else
-			order = MAX_ORDER;
+			order = MAX_PAGE_ORDER;
 
 		(*online_page_callback)(pfn_to_page(pfn), order);
 		pfn += (1UL << order);
@@ -1129,6 +1130,9 @@ void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages)
 	kasan_remove_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages));
 }
 
+/*
+ * Must be called with mem_hotplug_lock in write mode.
+ */
 int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
 		       struct zone *zone, struct memory_group *group)
 {
@@ -1149,7 +1153,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
 			 !IS_ALIGNED(pfn + nr_pages, PAGES_PER_SECTION)))
 		return -EINVAL;
 
-	mem_hotplug_begin();
 
 	/* associate pfn range with the zone */
 	move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_ISOLATE);
@@ -1208,7 +1211,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
 	writeback_set_ratelimit();
 
 	memory_notify(MEM_ONLINE, &arg);
-	mem_hotplug_done();
 	return 0;
 
 failed_addition:
@@ -1217,7 +1219,6 @@ failed_addition:
 		 (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1);
 	memory_notify(MEM_CANCEL_ONLINE, &arg);
 	remove_pfn_range_from_zone(zone, pfn, nr_pages);
-	mem_hotplug_done();
 	return ret;
 }
 
@@ -1380,6 +1381,85 @@ static bool mhp_supports_memmap_on_memory(unsigned long size)
 	return arch_supports_memmap_on_memory(vmemmap_size);
 }
 
+static void __ref remove_memory_blocks_and_altmaps(u64 start, u64 size)
+{
+	unsigned long memblock_size = memory_block_size_bytes();
+	u64 cur_start;
+
+	/*
+	 * For memmap_on_memory, the altmaps were added on a per-memblock
+	 * basis; we have to process each individual memory block.
+	 */
+	for (cur_start = start; cur_start < start + size;
+	     cur_start += memblock_size) {
+		struct vmem_altmap *altmap = NULL;
+		struct memory_block *mem;
+
+		mem = find_memory_block(pfn_to_section_nr(PFN_DOWN(cur_start)));
+		if (WARN_ON_ONCE(!mem))
+			continue;
+
+		altmap = mem->altmap;
+		mem->altmap = NULL;
+
+		remove_memory_block_devices(cur_start, memblock_size);
+
+		arch_remove_memory(cur_start, memblock_size, altmap);
+
+		/* Verify that all vmemmap pages have actually been freed. */
+		WARN(altmap->alloc, "Altmap not fully unmapped");
+		kfree(altmap);
+	}
+}
+
+static int create_altmaps_and_memory_blocks(int nid, struct memory_group *group,
+					    u64 start, u64 size)
+{
+	unsigned long memblock_size = memory_block_size_bytes();
+	u64 cur_start;
+	int ret;
+
+	for (cur_start = start; cur_start < start + size;
+	     cur_start += memblock_size) {
+		struct mhp_params params = { .pgprot =
+						     pgprot_mhp(PAGE_KERNEL) };
+		struct vmem_altmap mhp_altmap = {
+			.base_pfn = PHYS_PFN(cur_start),
+			.end_pfn = PHYS_PFN(cur_start + memblock_size - 1),
+		};
+
+		mhp_altmap.free = memory_block_memmap_on_memory_pages();
+		params.altmap = kmemdup(&mhp_altmap, sizeof(struct vmem_altmap),
+					GFP_KERNEL);
+		if (!params.altmap) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		/* call arch's memory hotadd */
+		ret = arch_add_memory(nid, cur_start, memblock_size, &params);
+		if (ret < 0) {
+			kfree(params.altmap);
+			goto out;
+		}
+
+		/* create memory block devices after memory was added */
+		ret = create_memory_block_devices(cur_start, memblock_size,
+						  params.altmap, group);
+		if (ret) {
+			arch_remove_memory(cur_start, memblock_size, NULL);
+			kfree(params.altmap);
+			goto out;
+		}
+	}
+
+	return 0;
+out:
+	if (ret && cur_start != start)
+		remove_memory_blocks_and_altmaps(start, cur_start - start);
+	return ret;
+}
+
 /*
  * NOTE: The caller must call lock_device_hotplug() to serialize hotplug
  * and online/offline operations (triggered e.g. by sysfs).
@@ -1390,10 +1470,6 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 {
 	struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) };
 	enum memblock_flags memblock_flags = MEMBLOCK_NONE;
-	struct vmem_altmap mhp_altmap = {
-		.base_pfn =  PHYS_PFN(res->start),
-		.end_pfn  =  PHYS_PFN(res->end),
-	};
 	struct memory_group *group = NULL;
 	u64 start, size;
 	bool new_node = false;
@@ -1436,30 +1512,22 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 	/*
 	 * Self hosted memmap array
 	 */
-	if (mhp_flags & MHP_MEMMAP_ON_MEMORY) {
-		if (mhp_supports_memmap_on_memory(size)) {
-			mhp_altmap.free = memory_block_memmap_on_memory_pages();
-			params.altmap = kmalloc(sizeof(struct vmem_altmap), GFP_KERNEL);
-			if (!params.altmap) {
-				ret = -ENOMEM;
-				goto error;
-			}
+	if ((mhp_flags & MHP_MEMMAP_ON_MEMORY) &&
+	    mhp_supports_memmap_on_memory(memory_block_size_bytes())) {
+		ret = create_altmaps_and_memory_blocks(nid, group, start, size);
+		if (ret)
+			goto error;
+	} else {
+		ret = arch_add_memory(nid, start, size, &params);
+		if (ret < 0)
+			goto error;
 
-			memcpy(params.altmap, &mhp_altmap, sizeof(mhp_altmap));
+		/* create memory block devices after memory was added */
+		ret = create_memory_block_devices(start, size, NULL, group);
+		if (ret) {
+			arch_remove_memory(start, size, params.altmap);
+			goto error;
 		}
-		/* fallback to not using altmap  */
-	}
-
-	/* call arch's memory hotadd */
-	ret = arch_add_memory(nid, start, size, &params);
-	if (ret < 0)
-		goto error_free;
-
-	/* create memory block devices after memory was added */
-	ret = create_memory_block_devices(start, size, params.altmap, group);
-	if (ret) {
-		arch_remove_memory(start, size, NULL);
-		goto error_free;
 	}
 
 	if (new_node) {
@@ -1496,8 +1564,6 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 		walk_memory_blocks(start, size, NULL, online_memory_block);
 
 	return ret;
-error_free:
-	kfree(params.altmap);
 error:
 	if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK))
 		memblock_remove(start, size);
@@ -1863,6 +1929,9 @@ static int count_system_ram_pages_cb(unsigned long start_pfn,
 	return 0;
 }
 
+/*
+ * Must be called with mem_hotplug_lock in write mode.
+ */
 int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 			struct zone *zone, struct memory_group *group)
 {
@@ -1885,8 +1954,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 			 !IS_ALIGNED(start_pfn + nr_pages, PAGES_PER_SECTION)))
 		return -EINVAL;
 
-	mem_hotplug_begin();
-
 	/*
 	 * Don't allow to offline memory blocks that contain holes.
 	 * Consequently, memory blocks with holes can never get onlined
@@ -2031,7 +2098,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 
 	memory_notify(MEM_OFFLINE, &arg);
 	remove_pfn_range_from_zone(zone, start_pfn, nr_pages);
-	mem_hotplug_done();
 	return 0;
 
 failed_removal_isolated:
@@ -2046,7 +2112,6 @@ failed_removal:
 		 (unsigned long long) start_pfn << PAGE_SHIFT,
 		 ((unsigned long long) end_pfn << PAGE_SHIFT) - 1,
 		 reason);
-	mem_hotplug_done();
 	return ret;
 }
 
@@ -2068,17 +2133,13 @@ static int check_memblock_offlined_cb(struct memory_block *mem, void *arg)
 	return 0;
 }
 
-static int test_has_altmap_cb(struct memory_block *mem, void *arg)
+static int count_memory_range_altmaps_cb(struct memory_block *mem, void *arg)
 {
-	struct memory_block **mem_ptr = (struct memory_block **)arg;
-	/*
-	 * return the memblock if we have altmap
-	 * and break callback.
-	 */
-	if (mem->altmap) {
-		*mem_ptr = mem;
-		return 1;
-	}
+	u64 *num_altmaps = (u64 *)arg;
+
+	if (mem->altmap)
+		*num_altmaps += 1;
+
 	return 0;
 }
 
@@ -2152,11 +2213,29 @@ void try_offline_node(int nid)
 }
 EXPORT_SYMBOL(try_offline_node);
 
+static int memory_blocks_have_altmaps(u64 start, u64 size)
+{
+	u64 num_memblocks = size / memory_block_size_bytes();
+	u64 num_altmaps = 0;
+
+	if (!mhp_memmap_on_memory())
+		return 0;
+
+	walk_memory_blocks(start, size, &num_altmaps,
+			   count_memory_range_altmaps_cb);
+
+	if (num_altmaps == 0)
+		return 0;
+
+	if (WARN_ON_ONCE(num_memblocks != num_altmaps))
+		return -EINVAL;
+
+	return 1;
+}
+
 static int __ref try_remove_memory(u64 start, u64 size)
 {
-	struct memory_block *mem;
-	int rc = 0, nid = NUMA_NO_NODE;
-	struct vmem_altmap *altmap = NULL;
+	int rc, nid = NUMA_NO_NODE;
 
 	BUG_ON(check_hotplug_memory_range(start, size));
 
@@ -2173,45 +2252,26 @@ static int __ref try_remove_memory(u64 start, u64 size)
 	if (rc)
 		return rc;
 
-	/*
-	 * We only support removing memory added with MHP_MEMMAP_ON_MEMORY in
-	 * the same granularity it was added - a single memory block.
-	 */
-	if (mhp_memmap_on_memory()) {
-		rc = walk_memory_blocks(start, size, &mem, test_has_altmap_cb);
-		if (rc) {
-			if (size != memory_block_size_bytes()) {
-				pr_warn("Refuse to remove %#llx - %#llx,"
-					"wrong granularity\n",
-					start, start + size);
-				return -EINVAL;
-			}
-			altmap = mem->altmap;
-			/*
-			 * Mark altmap NULL so that we can add a debug
-			 * check on memblock free.
-			 */
-			mem->altmap = NULL;
-		}
-	}
-
 	/* remove memmap entry */
 	firmware_map_remove(start, start + size, "System RAM");
 
-	/*
-	 * Memory block device removal under the device_hotplug_lock is
-	 * a barrier against racing online attempts.
-	 */
-	remove_memory_block_devices(start, size);
-
 	mem_hotplug_begin();
 
-	arch_remove_memory(start, size, altmap);
-
-	/* Verify that all vmemmap pages have actually been freed. */
-	if (altmap) {
-		WARN(altmap->alloc, "Altmap not fully unmapped");
-		kfree(altmap);
+	rc = memory_blocks_have_altmaps(start, size);
+	if (rc < 0) {
+		mem_hotplug_done();
+		return rc;
+	} else if (!rc) {
+		/*
+		 * Memory block device removal under the device_hotplug_lock is
+		 * a barrier against racing online attempts.
+		 * No altmaps present, do the removal directly
+		 */
+		remove_memory_block_devices(start, size);
+		arch_remove_memory(start, size, NULL);
+	} else {
+		/* all memblocks in the range have altmaps */
+		remove_memory_blocks_and_altmaps(start, size);
 	}
 
 	if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) {
diff --git a/mm/mempool.c b/mm/mempool.c
index 734bcf5afbb7..dbbf0e9fb424 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -20,7 +20,7 @@
 #include <linux/writeback.h>
 #include "slab.h"
 
-#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB_DEBUG_ON)
+#ifdef CONFIG_SLUB_DEBUG_ON
 static void poison_error(mempool_t *pool, void *element, size_t size,
 			 size_t byte)
 {
@@ -56,6 +56,10 @@ static void __check_element(mempool_t *pool, void *element, size_t size)
 
 static void check_element(mempool_t *pool, void *element)
 {
+	/* Skip checking: KASAN might save its metadata in the element. */
+	if (kasan_enabled())
+		return;
+
 	/* Mempools backed by slab allocator */
 	if (pool->free == mempool_kfree) {
 		__check_element(pool, element, (size_t)pool->pool_data);
@@ -64,10 +68,10 @@ static void check_element(mempool_t *pool, void *element)
 	} else if (pool->free == mempool_free_pages) {
 		/* Mempools backed by page allocator */
 		int order = (int)(long)pool->pool_data;
-		void *addr = kmap_atomic((struct page *)element);
+		void *addr = kmap_local_page((struct page *)element);
 
 		__check_element(pool, addr, 1UL << (PAGE_SHIFT + order));
-		kunmap_atomic(addr);
+		kunmap_local(addr);
 	}
 }
 
@@ -81,6 +85,10 @@ static void __poison_element(void *element, size_t size)
 
 static void poison_element(mempool_t *pool, void *element)
 {
+	/* Skip poisoning: KASAN might save its metadata in the element. */
+	if (kasan_enabled())
+		return;
+
 	/* Mempools backed by slab allocator */
 	if (pool->alloc == mempool_kmalloc) {
 		__poison_element(element, (size_t)pool->pool_data);
@@ -89,47 +97,49 @@ static void poison_element(mempool_t *pool, void *element)
 	} else if (pool->alloc == mempool_alloc_pages) {
 		/* Mempools backed by page allocator */
 		int order = (int)(long)pool->pool_data;
-		void *addr = kmap_atomic((struct page *)element);
+		void *addr = kmap_local_page((struct page *)element);
 
 		__poison_element(addr, 1UL << (PAGE_SHIFT + order));
-		kunmap_atomic(addr);
+		kunmap_local(addr);
 	}
 }
-#else /* CONFIG_DEBUG_SLAB || CONFIG_SLUB_DEBUG_ON */
+#else /* CONFIG_SLUB_DEBUG_ON */
 static inline void check_element(mempool_t *pool, void *element)
 {
 }
 static inline void poison_element(mempool_t *pool, void *element)
 {
 }
-#endif /* CONFIG_DEBUG_SLAB || CONFIG_SLUB_DEBUG_ON */
+#endif /* CONFIG_SLUB_DEBUG_ON */
 
-static __always_inline void kasan_poison_element(mempool_t *pool, void *element)
+static __always_inline bool kasan_poison_element(mempool_t *pool, void *element)
 {
 	if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc)
-		kasan_slab_free_mempool(element);
+		return kasan_mempool_poison_object(element);
 	else if (pool->alloc == mempool_alloc_pages)
-		kasan_poison_pages(element, (unsigned long)pool->pool_data,
-				   false);
+		return kasan_mempool_poison_pages(element,
+						(unsigned long)pool->pool_data);
+	return true;
 }
 
 static void kasan_unpoison_element(mempool_t *pool, void *element)
 {
 	if (pool->alloc == mempool_kmalloc)
-		kasan_unpoison_range(element, (size_t)pool->pool_data);
+		kasan_mempool_unpoison_object(element, (size_t)pool->pool_data);
 	else if (pool->alloc == mempool_alloc_slab)
-		kasan_unpoison_range(element, kmem_cache_size(pool->pool_data));
+		kasan_mempool_unpoison_object(element,
+					      kmem_cache_size(pool->pool_data));
 	else if (pool->alloc == mempool_alloc_pages)
-		kasan_unpoison_pages(element, (unsigned long)pool->pool_data,
-				     false);
+		kasan_mempool_unpoison_pages(element,
+					     (unsigned long)pool->pool_data);
 }
 
 static __always_inline void add_element(mempool_t *pool, void *element)
 {
 	BUG_ON(pool->curr_nr >= pool->min_nr);
 	poison_element(pool, element);
-	kasan_poison_element(pool, element);
-	pool->elements[pool->curr_nr++] = element;
+	if (kasan_poison_element(pool, element))
+		pool->elements[pool->curr_nr++] = element;
 }
 
 static void *remove_element(mempool_t *pool)
@@ -447,6 +457,43 @@ repeat_alloc:
 EXPORT_SYMBOL(mempool_alloc);
 
 /**
+ * mempool_alloc_preallocated - allocate an element from preallocated elements
+ *                              belonging to a specific memory pool
+ * @pool:      pointer to the memory pool which was allocated via
+ *             mempool_create().
+ *
+ * This function is similar to mempool_alloc, but it only attempts allocating
+ * an element from the preallocated elements. It does not sleep and immediately
+ * returns if no preallocated elements are available.
+ *
+ * Return: pointer to the allocated element or %NULL if no elements are
+ * available.
+ */
+void *mempool_alloc_preallocated(mempool_t *pool)
+{
+	void *element;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pool->lock, flags);
+	if (likely(pool->curr_nr)) {
+		element = remove_element(pool);
+		spin_unlock_irqrestore(&pool->lock, flags);
+		/* paired with rmb in mempool_free(), read comment there */
+		smp_wmb();
+		/*
+		 * Update the allocation stack trace as this is more useful
+		 * for debugging.
+		 */
+		kmemleak_update_trace(element);
+		return element;
+	}
+	spin_unlock_irqrestore(&pool->lock, flags);
+
+	return NULL;
+}
+EXPORT_SYMBOL(mempool_alloc_preallocated);
+
+/**
  * mempool_free - return an element to the pool.
  * @element:   pool element pointer.
  * @pool:      pointer to the memory pool which was allocated via
diff --git a/mm/memremap.c b/mm/memremap.c
index bee85560a243..9e9fb1972fff 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -7,6 +7,7 @@
 #include <linux/memremap.h>
 #include <linux/pfn_t.h>
 #include <linux/swap.h>
+#include <linux/mm.h>
 #include <linux/mmzone.h>
 #include <linux/swapops.h>
 #include <linux/types.h>
@@ -422,19 +423,6 @@ void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap)
 }
 EXPORT_SYMBOL_GPL(devm_memunmap_pages);
 
-unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
-{
-	/* number of pfns from base where pfn_to_page() is valid */
-	if (altmap)
-		return altmap->reserve + altmap->free;
-	return 0;
-}
-
-void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns)
-{
-	altmap->alloc -= nr_pfns;
-}
-
 /**
  * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn
  * @pfn: page frame number to lookup page_map
@@ -485,21 +473,11 @@ void free_zone_device_page(struct page *page)
 		__ClearPageAnonExclusive(page);
 
 	/*
-	 * When a device managed page is freed, the page->mapping field
+	 * When a device managed page is freed, the folio->mapping field
 	 * may still contain a (stale) mapping value. For example, the
-	 * lower bits of page->mapping may still identify the page as an
-	 * anonymous page. Ultimately, this entire field is just stale
-	 * and wrong, and it will cause errors if not cleared.  One
-	 * example is:
-	 *
-	 *  migrate_vma_pages()
-	 *    migrate_vma_insert_page()
-	 *      page_add_new_anon_rmap()
-	 *        __page_set_anon_rmap()
-	 *          ...checks page->mapping, via PageAnon(page) call,
-	 *            and incorrectly concludes that the page is an
-	 *            anonymous page. Therefore, it incorrectly,
-	 *            silently fails to set up the new anon rmap.
+	 * lower bits of folio->mapping may still identify the folio as an
+	 * anonymous folio. Ultimately, this entire field is just stale
+	 * and wrong, and it will cause errors if not cleared.
 	 *
 	 * For other types of ZONE_DEVICE pages, migration is either
 	 * handled differently or not done at all, so there is no need
diff --git a/mm/migrate.c b/mm/migrate.c
index 35a88334bb3c..bde8273cf15b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -249,20 +249,20 @@ static bool remove_migration_pte(struct folio *folio,
 
 			pte = arch_make_huge_pte(pte, shift, vma->vm_flags);
 			if (folio_test_anon(folio))
-				hugepage_add_anon_rmap(folio, vma, pvmw.address,
-						       rmap_flags);
+				hugetlb_add_anon_rmap(folio, vma, pvmw.address,
+						      rmap_flags);
 			else
-				page_dup_file_rmap(new, true);
+				hugetlb_add_file_rmap(folio);
 			set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte,
 					psize);
 		} else
 #endif
 		{
 			if (folio_test_anon(folio))
-				page_add_anon_rmap(new, vma, pvmw.address,
-						   rmap_flags);
+				folio_add_anon_rmap_pte(folio, new, vma,
+							pvmw.address, rmap_flags);
 			else
-				page_add_file_rmap(new, vma, false);
+				folio_add_file_rmap_pte(folio, new, vma);
 			set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte);
 		}
 		if (vma->vm_flags & VM_LOCKED)
@@ -405,6 +405,7 @@ int folio_migrate_mapping(struct address_space *mapping,
 	int dirty;
 	int expected_count = folio_expected_refs(mapping, folio) + extra_count;
 	long nr = folio_nr_pages(folio);
+	long entries, i;
 
 	if (!mapping) {
 		/* Anonymous page without mapping */
@@ -442,8 +443,10 @@ int folio_migrate_mapping(struct address_space *mapping,
 			folio_set_swapcache(newfolio);
 			newfolio->private = folio_get_private(folio);
 		}
+		entries = nr;
 	} else {
 		VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio);
+		entries = 1;
 	}
 
 	/* Move dirty while page refs frozen and newpage not yet exposed */
@@ -453,7 +456,11 @@ int folio_migrate_mapping(struct address_space *mapping,
 		folio_set_dirty(newfolio);
 	}
 
-	xas_store(&xas, newfolio);
+	/* Swap cache still stores N entries instead of a high-order entry */
+	for (i = 0; i < entries; i++) {
+		xas_store(&xas, newfolio);
+		xas_next(&xas);
+	}
 
 	/*
 	 * Drop cache reference from old page by unfreezing
@@ -746,7 +753,7 @@ static int __buffer_migrate_folio(struct address_space *mapping,
 
 recheck_buffers:
 		busy = false;
-		spin_lock(&mapping->private_lock);
+		spin_lock(&mapping->i_private_lock);
 		bh = head;
 		do {
 			if (atomic_read(&bh->b_count)) {
@@ -760,7 +767,7 @@ recheck_buffers:
 				rc = -EAGAIN;
 				goto unlock_buffers;
 			}
-			spin_unlock(&mapping->private_lock);
+			spin_unlock(&mapping->i_private_lock);
 			invalidate_bh_lrus();
 			invalidated = true;
 			goto recheck_buffers;
@@ -787,7 +794,7 @@ recheck_buffers:
 	rc = MIGRATEPAGE_SUCCESS;
 unlock_buffers:
 	if (check_refs)
-		spin_unlock(&mapping->private_lock);
+		spin_unlock(&mapping->i_private_lock);
 	bh = head;
 	do {
 		unlock_buffer(bh);
@@ -1018,38 +1025,31 @@ out:
 }
 
 /*
- * To record some information during migration, we use some unused
- * fields (mapping and private) of struct folio of the newly allocated
- * destination folio.  This is safe because nobody is using them
- * except us.
+ * To record some information during migration, we use unused private
+ * field of struct folio of the newly allocated destination folio.
+ * This is safe because nobody is using it except us.
  */
-union migration_ptr {
-	struct anon_vma *anon_vma;
-	struct address_space *mapping;
-};
-
 enum {
 	PAGE_WAS_MAPPED = BIT(0),
 	PAGE_WAS_MLOCKED = BIT(1),
+	PAGE_OLD_STATES = PAGE_WAS_MAPPED | PAGE_WAS_MLOCKED,
 };
 
 static void __migrate_folio_record(struct folio *dst,
-				   unsigned long old_page_state,
+				   int old_page_state,
 				   struct anon_vma *anon_vma)
 {
-	union migration_ptr ptr = { .anon_vma = anon_vma };
-	dst->mapping = ptr.mapping;
-	dst->private = (void *)old_page_state;
+	dst->private = (void *)anon_vma + old_page_state;
 }
 
 static void __migrate_folio_extract(struct folio *dst,
 				   int *old_page_state,
 				   struct anon_vma **anon_vmap)
 {
-	union migration_ptr ptr = { .mapping = dst->mapping };
-	*anon_vmap = ptr.anon_vma;
-	*old_page_state = (unsigned long)dst->private;
-	dst->mapping = NULL;
+	unsigned long private = (unsigned long)dst->private;
+
+	*anon_vmap = (struct anon_vma *)(private & ~PAGE_OLD_STATES);
+	*old_page_state = private & PAGE_OLD_STATES;
 	dst->private = NULL;
 }
 
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index 8ac1f79f754a..b6c27c76e1a0 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -107,6 +107,7 @@ again:
 
 	for (; addr < end; addr += PAGE_SIZE, ptep++) {
 		unsigned long mpfn = 0, pfn;
+		struct folio *folio;
 		struct page *page;
 		swp_entry_t entry;
 		pte_t pte;
@@ -168,41 +169,43 @@ again:
 		}
 
 		/*
-		 * By getting a reference on the page we pin it and that blocks
+		 * By getting a reference on the folio we pin it and that blocks
 		 * any kind of migration. Side effect is that it "freezes" the
 		 * pte.
 		 *
-		 * We drop this reference after isolating the page from the lru
-		 * for non device page (device page are not on the lru and thus
+		 * We drop this reference after isolating the folio from the lru
+		 * for non device folio (device folio are not on the lru and thus
 		 * can't be dropped from it).
 		 */
-		get_page(page);
+		folio = page_folio(page);
+		folio_get(folio);
 
 		/*
-		 * We rely on trylock_page() to avoid deadlock between
+		 * We rely on folio_trylock() to avoid deadlock between
 		 * concurrent migrations where each is waiting on the others
-		 * page lock. If we can't immediately lock the page we fail this
+		 * folio lock. If we can't immediately lock the folio we fail this
 		 * migration as it is only best effort anyway.
 		 *
-		 * If we can lock the page it's safe to set up a migration entry
-		 * now. In the common case where the page is mapped once in a
+		 * If we can lock the folio it's safe to set up a migration entry
+		 * now. In the common case where the folio is mapped once in a
 		 * single process setting up the migration entry now is an
 		 * optimisation to avoid walking the rmap later with
 		 * try_to_migrate().
 		 */
-		if (trylock_page(page)) {
+		if (folio_trylock(folio)) {
 			bool anon_exclusive;
 			pte_t swp_pte;
 
 			flush_cache_page(vma, addr, pte_pfn(pte));
-			anon_exclusive = PageAnon(page) && PageAnonExclusive(page);
+			anon_exclusive = folio_test_anon(folio) &&
+					  PageAnonExclusive(page);
 			if (anon_exclusive) {
 				pte = ptep_clear_flush(vma, addr, ptep);
 
-				if (page_try_share_anon_rmap(page)) {
+				if (folio_try_share_anon_rmap_pte(folio, page)) {
 					set_pte_at(mm, addr, ptep, pte);
-					unlock_page(page);
-					put_page(page);
+					folio_unlock(folio);
+					folio_put(folio);
 					mpfn = 0;
 					goto next;
 				}
@@ -214,7 +217,7 @@ again:
 
 			/* Set the dirty flag on the folio now the pte is gone. */
 			if (pte_dirty(pte))
-				folio_mark_dirty(page_folio(page));
+				folio_mark_dirty(folio);
 
 			/* Setup special migration page table entry */
 			if (mpfn & MIGRATE_PFN_WRITE)
@@ -248,16 +251,16 @@ again:
 
 			/*
 			 * This is like regular unmap: we remove the rmap and
-			 * drop page refcount. Page won't be freed, as we took
-			 * a reference just above.
+			 * drop the folio refcount. The folio won't be freed, as
+			 * we took a reference just above.
 			 */
-			page_remove_rmap(page, vma, false);
-			put_page(page);
+			folio_remove_rmap_pte(folio, page, vma);
+			folio_put(folio);
 
 			if (pte_present(pte))
 				unmapped++;
 		} else {
-			put_page(page);
+			folio_put(folio);
 			mpfn = 0;
 		}
 
@@ -564,6 +567,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 				    struct page *page,
 				    unsigned long *src)
 {
+	struct folio *folio = page_folio(page);
 	struct vm_area_struct *vma = migrate->vma;
 	struct mm_struct *mm = vma->vm_mm;
 	bool flush = false;
@@ -596,17 +600,17 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 		goto abort;
 	if (unlikely(anon_vma_prepare(vma)))
 		goto abort;
-	if (mem_cgroup_charge(page_folio(page), vma->vm_mm, GFP_KERNEL))
+	if (mem_cgroup_charge(folio, vma->vm_mm, GFP_KERNEL))
 		goto abort;
 
 	/*
-	 * The memory barrier inside __SetPageUptodate makes sure that
-	 * preceding stores to the page contents become visible before
+	 * The memory barrier inside __folio_mark_uptodate makes sure that
+	 * preceding stores to the folio contents become visible before
 	 * the set_pte_at() write.
 	 */
-	__SetPageUptodate(page);
+	__folio_mark_uptodate(folio);
 
-	if (is_device_private_page(page)) {
+	if (folio_is_device_private(folio)) {
 		swp_entry_t swp_entry;
 
 		if (vma->vm_flags & VM_WRITE)
@@ -617,8 +621,8 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 						page_to_pfn(page));
 		entry = swp_entry_to_pte(swp_entry);
 	} else {
-		if (is_zone_device_page(page) &&
-		    !is_device_coherent_page(page)) {
+		if (folio_is_zone_device(folio) &&
+		    !folio_is_device_coherent(folio)) {
 			pr_warn_once("Unsupported ZONE_DEVICE page type.\n");
 			goto abort;
 		}
@@ -652,10 +656,10 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 		goto unlock_abort;
 
 	inc_mm_counter(mm, MM_ANONPAGES);
-	page_add_new_anon_rmap(page, vma, addr);
-	if (!is_zone_device_page(page))
-		lru_cache_add_inactive_or_unevictable(page, vma);
-	get_page(page);
+	folio_add_new_anon_rmap(folio, vma, addr);
+	if (!folio_is_zone_device(folio))
+		folio_add_lru_vma(folio, vma);
+	folio_get(folio);
 
 	if (flush) {
 		flush_cache_page(vma, addr, pte_pfn(orig_pte));
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 077bfe393b5e..89dc29f1e6c6 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -796,6 +796,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn)
  * - physical memory bank size is not necessarily the exact multiple of the
  *   arbitrary section size
  * - early reserved memory may not be listed in memblock.memory
+ * - non-memory regions covered by the contigious flatmem mapping
  * - memory layouts defined with memmap= kernel parameter may not align
  *   nicely with memmap sections
  *
@@ -826,7 +827,7 @@ static void __init init_unavailable_range(unsigned long spfn,
 	}
 
 	if (pgcnt)
-		pr_info("On node %d, zone %s: %lld pages in unavailable ranges",
+		pr_info("On node %d, zone %s: %lld pages in unavailable ranges\n",
 			node, zone_names[zone], pgcnt);
 }
 
@@ -1454,7 +1455,7 @@ static inline void setup_usemap(struct zone *zone) {}
 /* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */
 void __init set_pageblock_order(void)
 {
-	unsigned int order = MAX_ORDER;
+	unsigned int order = MAX_PAGE_ORDER;
 
 	/* Check that pageblock_nr_pages has not already been setup */
 	if (pageblock_order)
@@ -1466,8 +1467,7 @@ void __init set_pageblock_order(void)
 
 	/*
 	 * Assume the largest contiguous order of interest is a huge page.
-	 * This value may be variable depending on boot parameters on IA64 and
-	 * powerpc.
+	 * This value may be variable depending on boot parameters on powerpc.
 	 */
 	pageblock_order = order;
 }
@@ -1628,8 +1628,8 @@ void __init *memmap_alloc(phys_addr_t size, phys_addr_t align,
 #ifdef CONFIG_FLATMEM
 static void __init alloc_node_mem_map(struct pglist_data *pgdat)
 {
-	unsigned long __maybe_unused start = 0;
-	unsigned long __maybe_unused offset = 0;
+	unsigned long start, offset, size, end;
+	struct page *map;
 
 	/* Skip empty nodes */
 	if (!pgdat->node_spanned_pages)
@@ -1637,33 +1637,24 @@ static void __init alloc_node_mem_map(struct pglist_data *pgdat)
 
 	start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1);
 	offset = pgdat->node_start_pfn - start;
-	/* ia64 gets its own node_mem_map, before this, without bootmem */
-	if (!pgdat->node_mem_map) {
-		unsigned long size, end;
-		struct page *map;
-
-		/*
-		 * The zone's endpoints aren't required to be MAX_ORDER
-		 * aligned but the node_mem_map endpoints must be in order
-		 * for the buddy allocator to function correctly.
-		 */
-		end = pgdat_end_pfn(pgdat);
-		end = ALIGN(end, MAX_ORDER_NR_PAGES);
-		size =  (end - start) * sizeof(struct page);
-		map = memmap_alloc(size, SMP_CACHE_BYTES, MEMBLOCK_LOW_LIMIT,
-				   pgdat->node_id, false);
-		if (!map)
-			panic("Failed to allocate %ld bytes for node %d memory map\n",
-			      size, pgdat->node_id);
-		pgdat->node_mem_map = map + offset;
-	}
-	pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n",
-				__func__, pgdat->node_id, (unsigned long)pgdat,
-				(unsigned long)pgdat->node_mem_map);
-#ifndef CONFIG_NUMA
 	/*
-	 * With no DISCONTIG, the global mem_map is just set as node 0's
+		 * The zone's endpoints aren't required to be MAX_PAGE_ORDER
+	 * aligned but the node_mem_map endpoints must be in order
+	 * for the buddy allocator to function correctly.
 	 */
+	end = ALIGN(pgdat_end_pfn(pgdat), MAX_ORDER_NR_PAGES);
+	size =  (end - start) * sizeof(struct page);
+	map = memmap_alloc(size, SMP_CACHE_BYTES, MEMBLOCK_LOW_LIMIT,
+			   pgdat->node_id, false);
+	if (!map)
+		panic("Failed to allocate %ld bytes for node %d memory map\n",
+		      size, pgdat->node_id);
+	pgdat->node_mem_map = map + offset;
+	pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n",
+		 __func__, pgdat->node_id, (unsigned long)pgdat,
+		 (unsigned long)pgdat->node_mem_map);
+#ifndef CONFIG_NUMA
+	/* the global mem_map is just set as node 0's */
 	if (pgdat == NODE_DATA(0)) {
 		mem_map = NODE_DATA(0)->node_mem_map;
 		if (page_to_pfn(mem_map) != pgdat->node_start_pfn)
@@ -1973,11 +1964,11 @@ static void __init deferred_free_range(unsigned long pfn,
 	if (nr_pages == MAX_ORDER_NR_PAGES && IS_MAX_ORDER_ALIGNED(pfn)) {
 		for (i = 0; i < nr_pages; i += pageblock_nr_pages)
 			set_pageblock_migratetype(page + i, MIGRATE_MOVABLE);
-		__free_pages_core(page, MAX_ORDER);
+		__free_pages_core(page, MAX_PAGE_ORDER);
 		return;
 	}
 
-	/* Accept chunks smaller than MAX_ORDER upfront */
+	/* Accept chunks smaller than MAX_PAGE_ORDER upfront */
 	accept_memory(PFN_PHYS(pfn), PFN_PHYS(pfn + nr_pages));
 
 	for (i = 0; i < nr_pages; i++, page++, pfn++) {
@@ -2000,8 +1991,8 @@ static inline void __init pgdat_init_report_one_done(void)
 /*
  * Returns true if page needs to be initialized or freed to buddy allocator.
  *
- * We check if a current MAX_ORDER block is valid by only checking the validity
- * of the head pfn.
+ * We check if a current MAX_PAGE_ORDER block is valid by only checking the
+ * validity of the head pfn.
  */
 static inline bool __init deferred_pfn_valid(unsigned long pfn)
 {
@@ -2158,8 +2149,8 @@ deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn,
 	deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, start_pfn);
 
 	/*
-	 * Initialize and free pages in MAX_ORDER sized increments so that we
-	 * can avoid introducing any issues with the buddy allocator.
+	 * Initialize and free pages in MAX_PAGE_ORDER sized increments so that
+	 * we can avoid introducing any issues with the buddy allocator.
 	 */
 	while (spfn < end_pfn) {
 		deferred_init_maxorder(&i, zone, &spfn, &epfn);
@@ -2300,7 +2291,7 @@ bool __init deferred_grow_zone(struct zone *zone, unsigned int order)
 	}
 
 	/*
-	 * Initialize and free pages in MAX_ORDER sized increments so
+	 * Initialize and free pages in MAX_PAGE_ORDER sized increments so
 	 * that we can avoid introducing any issues with the buddy
 	 * allocator.
 	 */
@@ -2518,7 +2509,7 @@ void *__init alloc_large_system_hash(const char *tablename,
 			else
 				table = memblock_alloc_raw(size,
 							   SMP_CACHE_BYTES);
-		} else if (get_order(size) > MAX_ORDER || hashdist) {
+		} else if (get_order(size) > MAX_PAGE_ORDER || hashdist) {
 			table = vmalloc_huge(size, gfp_flags);
 			virt = true;
 			if (table)
@@ -2765,7 +2756,7 @@ void __init mm_core_init(void)
 
 	/*
 	 * page_ext requires contiguous pages,
-	 * bigger than MAX_ORDER unless SPARSEMEM.
+	 * bigger than MAX_PAGE_ORDER unless SPARSEMEM.
 	 */
 	page_ext_init_flatmem();
 	mem_debugging_and_hardening_init();
diff --git a/mm/mmap.c b/mm/mmap.c
index 1971bfffcc03..b78e83d351d2 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1829,6 +1829,9 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 		 */
 		pgoff = 0;
 		get_area = shmem_get_unmapped_area;
+	} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
+		/* Ensures that larger anonymous mappings are THP aligned. */
+		get_area = thp_get_unmapped_area;
 	}
 
 	addr = get_area(file, addr, len, pgoff, flags);
@@ -2207,42 +2210,7 @@ struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned lon
 }
 #endif
 
-/*
- * IA64 has some horrid mapping rules: it can expand both up and down,
- * but with various special rules.
- *
- * We'll get rid of this architecture eventually, so the ugliness is
- * temporary.
- */
-#ifdef CONFIG_IA64
-static inline bool vma_expand_ok(struct vm_area_struct *vma, unsigned long addr)
-{
-	return REGION_NUMBER(addr) == REGION_NUMBER(vma->vm_start) &&
-		REGION_OFFSET(addr) < RGN_MAP_LIMIT;
-}
-
-/*
- * IA64 stacks grow down, but there's a special register backing store
- * that can grow up. Only sequentially, though, so the new address must
- * match vm_end.
- */
-static inline int vma_expand_up(struct vm_area_struct *vma, unsigned long addr)
-{
-	if (!vma_expand_ok(vma, addr))
-		return -EFAULT;
-	if (vma->vm_end != (addr & PAGE_MASK))
-		return -EFAULT;
-	return expand_upwards(vma, addr);
-}
-
-static inline bool vma_expand_down(struct vm_area_struct *vma, unsigned long addr)
-{
-	if (!vma_expand_ok(vma, addr))
-		return -EFAULT;
-	return expand_downwards(vma, addr);
-}
-
-#elif defined(CONFIG_STACK_GROWSUP)
+#if defined(CONFIG_STACK_GROWSUP)
 
 #define vma_expand_up(vma,addr) expand_upwards(vma, addr)
 #define vma_expand_down(vma, addr) (-EFAULT)
@@ -3294,10 +3262,11 @@ void exit_mmap(struct mm_struct *mm)
 	arch_exit_mmap(mm);
 
 	vma = mas_find(&mas, ULONG_MAX);
-	if (!vma) {
+	if (!vma || unlikely(xa_is_zero(vma))) {
 		/* Can happen if dup_mmap() received an OOM */
 		mmap_read_unlock(mm);
-		return;
+		mmap_write_lock(mm);
+		goto destroy;
 	}
 
 	lru_add_drain();
@@ -3332,11 +3301,13 @@ void exit_mmap(struct mm_struct *mm)
 		remove_vma(vma, true);
 		count++;
 		cond_resched();
-	} while ((vma = mas_find(&mas, ULONG_MAX)) != NULL);
+		vma = mas_find(&mas, ULONG_MAX);
+	} while (vma && likely(!xa_is_zero(vma)));
 
 	BUG_ON(count != mm->map_count);
 
 	trace_exit_mmap(mm);
+destroy:
 	__mt_destroy(&mm->mm_mt);
 	mmap_write_unlock(mm);
 	vm_unacct_memory(nr_accounted);
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index 4f559f4ddd21..604ddf08affe 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -55,7 +55,7 @@ static void tlb_flush_rmap_batch(struct mmu_gather_batch *batch, struct vm_area_
 
 		if (encoded_page_flags(enc)) {
 			struct page *page = encoded_page_ptr(enc);
-			page_remove_rmap(page, vma, false);
+			folio_remove_rmap_pte(page_folio(page), page, vma);
 		}
 	}
 }
diff --git a/mm/mmzone.c b/mm/mmzone.c
index b594d3f268fe..c01896eca736 100644
--- a/mm/mmzone.c
+++ b/mm/mmzone.c
@@ -78,6 +78,7 @@ void lruvec_init(struct lruvec *lruvec)
 
 	memset(lruvec, 0, sizeof(struct lruvec));
 	spin_lock_init(&lruvec->lru_lock);
+	zswap_lruvec_state_init(lruvec);
 
 	for_each_lru(lru)
 		INIT_LIST_HEAD(&lruvec->lists[lru]);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 9e6071fde34a..91ccd82097c2 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -399,10 +399,11 @@ static int dump_task(struct task_struct *p, void *arg)
 		return 0;
 	}
 
-	pr_info("[%7d] %5d %5d %8lu %8lu %8ld %8lu         %5hd %s\n",
+	pr_info("[%7d] %5d %5d %8lu %8lu %8lu %8lu %9lu %8ld %8lu         %5hd %s\n",
 		task->pid, from_kuid(&init_user_ns, task_uid(task)),
 		task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
-		mm_pgtables_bytes(task->mm),
+		get_mm_counter(task->mm, MM_ANONPAGES), get_mm_counter(task->mm, MM_FILEPAGES),
+		get_mm_counter(task->mm, MM_SHMEMPAGES), mm_pgtables_bytes(task->mm),
 		get_mm_counter(task->mm, MM_SWAPENTS),
 		task->signal->oom_score_adj, task->comm);
 	task_unlock(task);
@@ -423,7 +424,7 @@ static int dump_task(struct task_struct *p, void *arg)
 static void dump_tasks(struct oom_control *oc)
 {
 	pr_info("Tasks state (memory values in pages):\n");
-	pr_info("[  pid  ]   uid  tgid total_vm      rss pgtables_bytes swapents oom_score_adj name\n");
+	pr_info("[  pid  ]   uid  tgid total_vm      rss rss_anon rss_file rss_shmem pgtables_bytes swapents oom_score_adj name\n");
 
 	if (is_memcg_oom(oc))
 		mem_cgroup_scan_tasks(oc->memcg, dump_task, oc);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 46f2f5d3d183..cd4e4ae77c40 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -692,7 +692,6 @@ static int __bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ra
 
 	if (min_ratio > 100 * BDI_RATIO_SCALE)
 		return -EINVAL;
-	min_ratio *= BDI_RATIO_SCALE;
 
 	spin_lock_bh(&bdi_lock);
 	if (min_ratio > bdi->max_ratio) {
@@ -729,7 +728,8 @@ static int __bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ra
 		ret = -EINVAL;
 	} else {
 		bdi->max_ratio = max_ratio;
-		bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) / 100;
+		bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) /
+						(100 * BDI_RATIO_SCALE);
 	}
 	spin_unlock_bh(&bdi_lock);
 
@@ -2982,67 +2982,63 @@ bool __folio_end_writeback(struct folio *folio)
 	return ret;
 }
 
-bool __folio_start_writeback(struct folio *folio, bool keep_write)
+void __folio_start_writeback(struct folio *folio, bool keep_write)
 {
 	long nr = folio_nr_pages(folio);
 	struct address_space *mapping = folio_mapping(folio);
-	bool ret;
 	int access_ret;
 
+	VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio);
+
 	folio_memcg_lock(folio);
 	if (mapping && mapping_use_writeback_tags(mapping)) {
 		XA_STATE(xas, &mapping->i_pages, folio_index(folio));
 		struct inode *inode = mapping->host;
 		struct backing_dev_info *bdi = inode_to_bdi(inode);
 		unsigned long flags;
+		bool on_wblist;
 
 		xas_lock_irqsave(&xas, flags);
 		xas_load(&xas);
-		ret = folio_test_set_writeback(folio);
-		if (!ret) {
-			bool on_wblist;
+		folio_test_set_writeback(folio);
 
-			on_wblist = mapping_tagged(mapping,
-						   PAGECACHE_TAG_WRITEBACK);
+		on_wblist = mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK);
 
-			xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK);
-			if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) {
-				struct bdi_writeback *wb = inode_to_wb(inode);
-
-				wb_stat_mod(wb, WB_WRITEBACK, nr);
-				if (!on_wblist)
-					wb_inode_writeback_start(wb);
-			}
+		xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK);
+		if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) {
+			struct bdi_writeback *wb = inode_to_wb(inode);
 
-			/*
-			 * We can come through here when swapping
-			 * anonymous folios, so we don't necessarily
-			 * have an inode to track for sync.
-			 */
-			if (mapping->host && !on_wblist)
-				sb_mark_inode_writeback(mapping->host);
+			wb_stat_mod(wb, WB_WRITEBACK, nr);
+			if (!on_wblist)
+				wb_inode_writeback_start(wb);
 		}
+
+		/*
+		 * We can come through here when swapping anonymous
+		 * folios, so we don't necessarily have an inode to
+		 * track for sync.
+		 */
+		if (mapping->host && !on_wblist)
+			sb_mark_inode_writeback(mapping->host);
 		if (!folio_test_dirty(folio))
 			xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY);
 		if (!keep_write)
 			xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE);
 		xas_unlock_irqrestore(&xas, flags);
 	} else {
-		ret = folio_test_set_writeback(folio);
-	}
-	if (!ret) {
-		lruvec_stat_mod_folio(folio, NR_WRITEBACK, nr);
-		zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr);
+		folio_test_set_writeback(folio);
 	}
+
+	lruvec_stat_mod_folio(folio, NR_WRITEBACK, nr);
+	zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr);
 	folio_memcg_unlock(folio);
+
 	access_ret = arch_make_folio_accessible(folio);
 	/*
 	 * If writeback has been triggered on a page that cannot be made
 	 * accessible, it is too late to recover here.
 	 */
 	VM_BUG_ON_FOLIO(access_ret != 0, folio);
-
-	return ret;
 }
 EXPORT_SYMBOL(__folio_start_writeback);
 
@@ -3107,7 +3103,7 @@ EXPORT_SYMBOL_GPL(folio_wait_writeback_killable);
  */
 void folio_wait_stable(struct folio *folio)
 {
-	if (folio_inode(folio)->i_sb->s_iflags & SB_I_STABLE_WRITES)
+	if (mapping_stable_writes(folio_mapping(folio)))
 		folio_wait_writeback(folio);
 }
 EXPORT_SYMBOL_GPL(folio_wait_stable);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 733732e7e0ba..150d4f23b010 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -727,7 +727,7 @@ buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn,
 	unsigned long higher_page_pfn;
 	struct page *higher_page;
 
-	if (order >= MAX_ORDER - 1)
+	if (order >= MAX_PAGE_ORDER - 1)
 		return false;
 
 	higher_page_pfn = buddy_pfn & pfn;
@@ -782,7 +782,7 @@ static inline void __free_one_page(struct page *page,
 	VM_BUG_ON_PAGE(pfn & ((1 << order) - 1), page);
 	VM_BUG_ON_PAGE(bad_range(zone, page), page);
 
-	while (order < MAX_ORDER) {
+	while (order < MAX_PAGE_ORDER) {
 		if (compaction_capture(capc, page, order, migratetype)) {
 			__mod_zone_freepage_state(zone, -(1 << order),
 								migratetype);
@@ -916,6 +916,9 @@ static inline bool page_expected_state(struct page *page,
 #ifdef CONFIG_MEMCG
 			page->memcg_data |
 #endif
+#ifdef CONFIG_PAGE_POOL
+			((page->pp_magic & ~0x3UL) == PP_SIGNATURE) |
+#endif
 			(page->flags & check_flags)))
 		return false;
 
@@ -942,6 +945,10 @@ static const char *page_bad_reason(struct page *page, unsigned long flags)
 	if (unlikely(page->memcg_data))
 		bad_reason = "page still charged to cgroup";
 #endif
+#ifdef CONFIG_PAGE_POOL
+	if (unlikely((page->pp_magic & ~0x3UL) == PP_SIGNATURE))
+		bad_reason = "page_pool leak";
+#endif
 	return bad_reason;
 }
 
@@ -1059,7 +1066,7 @@ static inline bool should_skip_kasan_poison(struct page *page, fpi_t fpi_flags)
 	if (IS_ENABLED(CONFIG_KASAN_GENERIC))
 		return deferred_pages_enabled();
 
-	return page_kasan_tag(page) == 0xff;
+	return page_kasan_tag(page) == KASAN_TAG_KERNEL;
 }
 
 static void kernel_init_pages(struct page *page, int numpages)
@@ -1086,13 +1093,11 @@ static __always_inline bool free_pages_prepare(struct page *page,
 	trace_mm_page_free(page, order);
 	kmsan_free_page(page, order);
 
+	if (memcg_kmem_online() && PageMemcgKmem(page))
+		__memcg_kmem_uncharge_page(page, order);
+
 	if (unlikely(PageHWPoison(page)) && !order) {
-		/*
-		 * Do not let hwpoison pages hit pcplists/buddy
-		 * Untie memcg state and reset page's owner
-		 */
-		if (memcg_kmem_online() && PageMemcgKmem(page))
-			__memcg_kmem_uncharge_page(page, order);
+		/* Do not let hwpoison pages hit pcplists/buddy */
 		reset_page_owner(page, order);
 		page_table_check_free(page, order);
 		return false;
@@ -1123,8 +1128,6 @@ static __always_inline bool free_pages_prepare(struct page *page,
 	}
 	if (PageMappingFlags(page))
 		page->mapping = NULL;
-	if (memcg_kmem_online() && PageMemcgKmem(page))
-		__memcg_kmem_uncharge_page(page, order);
 	if (is_check_pages_enabled()) {
 		if (free_page_is_bad(page))
 			bad++;
@@ -1259,7 +1262,6 @@ static void free_one_page(struct zone *zone,
 static void __free_pages_ok(struct page *page, unsigned int order,
 			    fpi_t fpi_flags)
 {
-	unsigned long flags;
 	int migratetype;
 	unsigned long pfn = page_to_pfn(page);
 	struct zone *zone = page_zone(page);
@@ -1274,13 +1276,7 @@ static void __free_pages_ok(struct page *page, unsigned int order,
 	 */
 	migratetype = get_pfnblock_migratetype(page, pfn);
 
-	spin_lock_irqsave(&zone->lock, flags);
-	if (unlikely(has_isolate_pageblock(zone) ||
-		is_migrate_isolate(migratetype))) {
-		migratetype = get_pfnblock_migratetype(page, pfn);
-	}
-	__free_one_page(page, pfn, zone, order, migratetype, fpi_flags);
-	spin_unlock_irqrestore(&zone->lock, flags);
+	free_one_page(zone, page, pfn, order, migratetype, fpi_flags);
 
 	__count_vm_events(PGFREE, 1 << order);
 }
@@ -1308,7 +1304,7 @@ void __free_pages_core(struct page *page, unsigned int order)
 	atomic_long_add(nr_pages, &page_zone(page)->managed_pages);
 
 	if (page_contains_unaccepted(page, order)) {
-		if (order == MAX_ORDER && __free_unaccepted(page))
+		if (order == MAX_PAGE_ORDER && __free_unaccepted(page))
 			return;
 
 		accept_page(page, order);
@@ -1338,7 +1334,7 @@ void __free_pages_core(struct page *page, unsigned int order)
  *
  * Note: the function may return non-NULL struct page even for a page block
  * which contains a memory hole (i.e. there is no physical memory for a subset
- * of the pfn range). For example, if the pageblock order is MAX_ORDER, which
+ * of the pfn range). For example, if the pageblock order is MAX_PAGE_ORDER, which
  * will fall into 2 sub-sections, and the end pfn of the pageblock may be hole
  * even though the start pfn is online and valid. This should be safe most of
  * the time because struct pages are still initialized via init_unavailable_range()
@@ -1571,7 +1567,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
 	struct page *page;
 
 	/* Find a page of the appropriate size in the preferred list */
-	for (current_order = order; current_order <= MAX_ORDER; ++current_order) {
+	for (current_order = order; current_order < NR_PAGE_ORDERS; ++current_order) {
 		area = &(zone->free_area[current_order]);
 		page = get_page_from_free_area(area, migratetype);
 		if (!page)
@@ -1884,10 +1880,14 @@ static void reserve_highatomic_pageblock(struct page *page, struct zone *zone)
 	unsigned long max_managed, flags;
 
 	/*
-	 * Limit the number reserved to 1 pageblock or roughly 1% of a zone.
+	 * The number reserved as: minimum is 1 pageblock, maximum is
+	 * roughly 1% of a zone. But if 1% of a zone falls below a
+	 * pageblock size, then don't reserve any pageblocks.
 	 * Check is race-prone but harmless.
 	 */
-	max_managed = (zone_managed_pages(zone) / 100) + pageblock_nr_pages;
+	if ((zone_managed_pages(zone) / 100) < pageblock_nr_pages)
+		return;
+	max_managed = ALIGN((zone_managed_pages(zone) / 100), pageblock_nr_pages);
 	if (zone->nr_reserved_highatomic >= max_managed)
 		return;
 
@@ -1941,7 +1941,7 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac,
 			continue;
 
 		spin_lock_irqsave(&zone->lock, flags);
-		for (order = 0; order <= MAX_ORDER; order++) {
+		for (order = 0; order < NR_PAGE_ORDERS; order++) {
 			struct free_area *area = &(zone->free_area[order]);
 
 			page = get_page_from_free_area(area, MIGRATE_HIGHATOMIC);
@@ -2025,7 +2025,7 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype,
 	 * approximates finding the pageblock with the most free pages, which
 	 * would be too costly to do exactly.
 	 */
-	for (current_order = MAX_ORDER; current_order >= min_order;
+	for (current_order = MAX_PAGE_ORDER; current_order >= min_order;
 				--current_order) {
 		area = &(zone->free_area[current_order]);
 		fallback_mt = find_suitable_fallback(area, current_order,
@@ -2051,8 +2051,7 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype,
 	return false;
 
 find_smallest:
-	for (current_order = order; current_order <= MAX_ORDER;
-							current_order++) {
+	for (current_order = order; current_order < NR_PAGE_ORDERS; current_order++) {
 		area = &(zone->free_area[current_order]);
 		fallback_mt = find_suitable_fallback(area, current_order,
 				start_migratetype, false, &can_steal);
@@ -2064,7 +2063,7 @@ find_smallest:
 	 * This should not happen - we already found a suitable fallback
 	 * when looking for the largest page.
 	 */
-	VM_BUG_ON(current_order > MAX_ORDER);
+	VM_BUG_ON(current_order > MAX_PAGE_ORDER);
 
 do_steal:
 	page = get_page_from_free_area(area, fallback_mt);
@@ -3007,7 +3006,7 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 		return true;
 
 	/* For a high-order request, check at least one suitable page is free */
-	for (o = order; o <= MAX_ORDER; o++) {
+	for (o = order; o < NR_PAGE_ORDERS; o++) {
 		struct free_area *area = &z->free_area[o];
 		int mt;
 
@@ -3951,14 +3950,9 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
 	else
 		(*no_progress_loops)++;
 
-	/*
-	 * Make sure we converge to OOM if we cannot make any progress
-	 * several times in the row.
-	 */
-	if (*no_progress_loops > MAX_RECLAIM_RETRIES) {
-		/* Before OOM, exhaust highatomic_reserve */
-		return unreserve_highatomic_pageblock(ac, true);
-	}
+	if (*no_progress_loops > MAX_RECLAIM_RETRIES)
+		goto out;
+
 
 	/*
 	 * Keep reclaiming pages while there is a chance this will lead
@@ -4001,6 +3995,11 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
 		schedule_timeout_uninterruptible(1);
 	else
 		cond_resched();
+out:
+	/* Before OOM, exhaust highatomic_reserve */
+	if (!ret)
+		return unreserve_highatomic_pageblock(ac, true);
+
 	return ret;
 }
 
@@ -4541,7 +4540,7 @@ struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid,
 	 * There are several places where we assume that the order value is sane
 	 * so bail out early if the request is out of bound.
 	 */
-	if (WARN_ON_ONCE_GFP(order > MAX_ORDER, gfp))
+	if (WARN_ON_ONCE_GFP(order > MAX_PAGE_ORDER, gfp))
 		return NULL;
 
 	gfp &= gfp_allowed_mask;
@@ -4823,7 +4822,7 @@ static void *make_alloc_exact(unsigned long addr, unsigned int order,
  * minimum number of pages to satisfy the request.  alloc_pages() can only
  * allocate memory in power-of-two pages.
  *
- * This function is also limited by MAX_ORDER.
+ * This function is also limited by MAX_PAGE_ORDER.
  *
  * Memory allocated by this function must be released by free_pages_exact().
  *
@@ -6381,7 +6380,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 	order = 0;
 	outer_start = start;
 	while (!PageBuddy(pfn_to_page(outer_start))) {
-		if (++order > MAX_ORDER) {
+		if (++order > MAX_PAGE_ORDER) {
 			outer_start = start;
 			break;
 		}
@@ -6635,7 +6634,7 @@ bool is_free_buddy_page(struct page *page)
 	unsigned long pfn = page_to_pfn(page);
 	unsigned int order;
 
-	for (order = 0; order <= MAX_ORDER; order++) {
+	for (order = 0; order < NR_PAGE_ORDERS; order++) {
 		struct page *page_head = page - (pfn & ((1 << order) - 1));
 
 		if (PageBuddy(page_head) &&
@@ -6643,7 +6642,7 @@ bool is_free_buddy_page(struct page *page)
 			break;
 	}
 
-	return order <= MAX_ORDER;
+	return order <= MAX_PAGE_ORDER;
 }
 EXPORT_SYMBOL(is_free_buddy_page);
 
@@ -6690,7 +6689,7 @@ bool take_page_off_buddy(struct page *page)
 	bool ret = false;
 
 	spin_lock_irqsave(&zone->lock, flags);
-	for (order = 0; order <= MAX_ORDER; order++) {
+	for (order = 0; order < NR_PAGE_ORDERS; order++) {
 		struct page *page_head = page - (pfn & ((1 << order) - 1));
 		int page_order = buddy_order(page_head);
 
@@ -6815,9 +6814,9 @@ static bool try_to_accept_memory_one(struct zone *zone)
 	__mod_zone_page_state(zone, NR_UNACCEPTED, -MAX_ORDER_NR_PAGES);
 	spin_unlock_irqrestore(&zone->lock, flags);
 
-	accept_page(page, MAX_ORDER);
+	accept_page(page, MAX_PAGE_ORDER);
 
-	__free_pages_ok(page, MAX_ORDER, FPI_TO_TAIL);
+	__free_pages_ok(page, MAX_PAGE_ORDER, FPI_TO_TAIL);
 
 	if (last)
 		static_branch_dec(&zones_with_unaccepted_pages);
diff --git a/mm/page_io.c b/mm/page_io.c
index cb559ae324c6..ae2b49055e43 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -201,7 +201,12 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
 		folio_end_writeback(folio);
 		return 0;
 	}
-	__swap_writepage(&folio->page, wbc);
+	if (!mem_cgroup_zswap_writeback_enabled(folio_memcg(folio))) {
+		folio_mark_dirty(folio);
+		return AOP_WRITEPAGE_ACTIVATE;
+	}
+
+	__swap_writepage(folio, wbc);
 	return 0;
 }
 
@@ -288,16 +293,16 @@ static void sio_write_complete(struct kiocb *iocb, long ret)
 	mempool_free(sio, sio_pool);
 }
 
-static void swap_writepage_fs(struct page *page, struct writeback_control *wbc)
+static void swap_writepage_fs(struct folio *folio, struct writeback_control *wbc)
 {
 	struct swap_iocb *sio = NULL;
-	struct swap_info_struct *sis = page_swap_info(page);
+	struct swap_info_struct *sis = swp_swap_info(folio->swap);
 	struct file *swap_file = sis->swap_file;
-	loff_t pos = page_file_offset(page);
+	loff_t pos = folio_file_pos(folio);
 
-	count_swpout_vm_event(page_folio(page));
-	set_page_writeback(page);
-	unlock_page(page);
+	count_swpout_vm_event(folio);
+	folio_start_writeback(folio);
+	folio_unlock(folio);
 	if (wbc->swap_plug)
 		sio = *wbc->swap_plug;
 	if (sio) {
@@ -315,8 +320,8 @@ static void swap_writepage_fs(struct page *page, struct writeback_control *wbc)
 		sio->pages = 0;
 		sio->len = 0;
 	}
-	bvec_set_page(&sio->bvec[sio->pages], page, thp_size(page), 0);
-	sio->len += thp_size(page);
+	bvec_set_folio(&sio->bvec[sio->pages], folio, folio_size(folio), 0);
+	sio->len += folio_size(folio);
 	sio->pages += 1;
 	if (sio->pages == ARRAY_SIZE(sio->bvec) || !wbc->swap_plug) {
 		swap_write_unplug(sio);
@@ -326,17 +331,16 @@ static void swap_writepage_fs(struct page *page, struct writeback_control *wbc)
 		*wbc->swap_plug = sio;
 }
 
-static void swap_writepage_bdev_sync(struct page *page,
+static void swap_writepage_bdev_sync(struct folio *folio,
 		struct writeback_control *wbc, struct swap_info_struct *sis)
 {
 	struct bio_vec bv;
 	struct bio bio;
-	struct folio *folio = page_folio(page);
 
 	bio_init(&bio, sis->bdev, &bv, 1,
 		 REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc));
-	bio.bi_iter.bi_sector = swap_page_sector(page);
-	__bio_add_page(&bio, page, thp_size(page), 0);
+	bio.bi_iter.bi_sector = swap_folio_sector(folio);
+	bio_add_folio_nofail(&bio, folio, folio_size(folio), 0);
 
 	bio_associate_blkg_from_page(&bio, folio);
 	count_swpout_vm_event(folio);
@@ -348,18 +352,17 @@ static void swap_writepage_bdev_sync(struct page *page,
 	__end_swap_bio_write(&bio);
 }
 
-static void swap_writepage_bdev_async(struct page *page,
+static void swap_writepage_bdev_async(struct folio *folio,
 		struct writeback_control *wbc, struct swap_info_struct *sis)
 {
 	struct bio *bio;
-	struct folio *folio = page_folio(page);
 
 	bio = bio_alloc(sis->bdev, 1,
 			REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc),
 			GFP_NOIO);
-	bio->bi_iter.bi_sector = swap_page_sector(page);
+	bio->bi_iter.bi_sector = swap_folio_sector(folio);
 	bio->bi_end_io = end_swap_bio_write;
-	__bio_add_page(bio, page, thp_size(page), 0);
+	bio_add_folio_nofail(bio, folio, folio_size(folio), 0);
 
 	bio_associate_blkg_from_page(bio, folio);
 	count_swpout_vm_event(folio);
@@ -368,22 +371,22 @@ static void swap_writepage_bdev_async(struct page *page,
 	submit_bio(bio);
 }
 
-void __swap_writepage(struct page *page, struct writeback_control *wbc)
+void __swap_writepage(struct folio *folio, struct writeback_control *wbc)
 {
-	struct swap_info_struct *sis = page_swap_info(page);
+	struct swap_info_struct *sis = swp_swap_info(folio->swap);
 
-	VM_BUG_ON_PAGE(!PageSwapCache(page), page);
+	VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio);
 	/*
 	 * ->flags can be updated non-atomicially (scan_swap_map_slots),
 	 * but that will never affect SWP_FS_OPS, so the data_race
 	 * is safe.
 	 */
 	if (data_race(sis->flags & SWP_FS_OPS))
-		swap_writepage_fs(page, wbc);
+		swap_writepage_fs(folio, wbc);
 	else if (sis->flags & SWP_SYNCHRONOUS_IO)
-		swap_writepage_bdev_sync(page, wbc, sis);
+		swap_writepage_bdev_sync(folio, wbc, sis);
 	else
-		swap_writepage_bdev_async(page, wbc, sis);
+		swap_writepage_bdev_async(folio, wbc, sis);
 }
 
 void swap_write_unplug(struct swap_iocb *sio)
@@ -422,12 +425,11 @@ static void sio_read_complete(struct kiocb *iocb, long ret)
 	mempool_free(sio, sio_pool);
 }
 
-static void swap_readpage_fs(struct page *page,
-			     struct swap_iocb **plug)
+static void swap_read_folio_fs(struct folio *folio, struct swap_iocb **plug)
 {
-	struct swap_info_struct *sis = page_swap_info(page);
+	struct swap_info_struct *sis = swp_swap_info(folio->swap);
 	struct swap_iocb *sio = NULL;
-	loff_t pos = page_file_offset(page);
+	loff_t pos = folio_file_pos(folio);
 
 	if (plug)
 		sio = *plug;
@@ -446,8 +448,8 @@ static void swap_readpage_fs(struct page *page,
 		sio->pages = 0;
 		sio->len = 0;
 	}
-	bvec_set_page(&sio->bvec[sio->pages], page, thp_size(page), 0);
-	sio->len += thp_size(page);
+	bvec_set_folio(&sio->bvec[sio->pages], folio, folio_size(folio), 0);
+	sio->len += folio_size(folio);
 	sio->pages += 1;
 	if (sio->pages == ARRAY_SIZE(sio->bvec) || !plug) {
 		swap_read_unplug(sio);
@@ -457,15 +459,15 @@ static void swap_readpage_fs(struct page *page,
 		*plug = sio;
 }
 
-static void swap_readpage_bdev_sync(struct page *page,
+static void swap_read_folio_bdev_sync(struct folio *folio,
 		struct swap_info_struct *sis)
 {
 	struct bio_vec bv;
 	struct bio bio;
 
 	bio_init(&bio, sis->bdev, &bv, 1, REQ_OP_READ);
-	bio.bi_iter.bi_sector = swap_page_sector(page);
-	__bio_add_page(&bio, page, thp_size(page), 0);
+	bio.bi_iter.bi_sector = swap_folio_sector(folio);
+	bio_add_folio_nofail(&bio, folio, folio_size(folio), 0);
 	/*
 	 * Keep this task valid during swap readpage because the oom killer may
 	 * attempt to access it in the page fault retry time check.
@@ -477,23 +479,23 @@ static void swap_readpage_bdev_sync(struct page *page,
 	put_task_struct(current);
 }
 
-static void swap_readpage_bdev_async(struct page *page,
+static void swap_read_folio_bdev_async(struct folio *folio,
 		struct swap_info_struct *sis)
 {
 	struct bio *bio;
 
 	bio = bio_alloc(sis->bdev, 1, REQ_OP_READ, GFP_KERNEL);
-	bio->bi_iter.bi_sector = swap_page_sector(page);
+	bio->bi_iter.bi_sector = swap_folio_sector(folio);
 	bio->bi_end_io = end_swap_bio_read;
-	__bio_add_page(bio, page, thp_size(page), 0);
+	bio_add_folio_nofail(bio, folio, folio_size(folio), 0);
 	count_vm_event(PSWPIN);
 	submit_bio(bio);
 }
 
-void swap_readpage(struct page *page, bool synchronous, struct swap_iocb **plug)
+void swap_read_folio(struct folio *folio, bool synchronous,
+		struct swap_iocb **plug)
 {
-	struct folio *folio = page_folio(page);
-	struct swap_info_struct *sis = page_swap_info(page);
+	struct swap_info_struct *sis = swp_swap_info(folio->swap);
 	bool workingset = folio_test_workingset(folio);
 	unsigned long pflags;
 	bool in_thrashing;
@@ -517,11 +519,11 @@ void swap_readpage(struct page *page, bool synchronous, struct swap_iocb **plug)
 		folio_mark_uptodate(folio);
 		folio_unlock(folio);
 	} else if (data_race(sis->flags & SWP_FS_OPS)) {
-		swap_readpage_fs(page, plug);
+		swap_read_folio_fs(folio, plug);
 	} else if (synchronous || (sis->flags & SWP_SYNCHRONOUS_IO)) {
-		swap_readpage_bdev_sync(page, sis);
+		swap_read_folio_bdev_sync(folio, sis);
 	} else {
-		swap_readpage_bdev_async(page, sis);
+		swap_read_folio_bdev_async(folio, sis);
 	}
 
 	if (workingset) {
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index bcf99ba747a0..cd0ea3668253 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -226,7 +226,7 @@ static void unset_migratetype_isolate(struct page *page, int migratetype)
 	 */
 	if (PageBuddy(page)) {
 		order = buddy_order(page);
-		if (order >= pageblock_order && order < MAX_ORDER) {
+		if (order >= pageblock_order && order < MAX_PAGE_ORDER) {
 			buddy = find_buddy_page_pfn(page, page_to_pfn(page),
 						    order, NULL);
 			if (buddy && !is_migrate_isolate_page(buddy)) {
@@ -290,11 +290,12 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  *			isolate_single_pageblock()
  * @migratetype:	migrate type to set in error recovery.
  *
- * Free and in-use pages can be as big as MAX_ORDER and contain more than one
+ * Free and in-use pages can be as big as MAX_PAGE_ORDER and contain more than one
  * pageblock. When not all pageblocks within a page are isolated at the same
  * time, free page accounting can go wrong. For example, in the case of
- * MAX_ORDER = pageblock_order + 1, a MAX_ORDER page has two pagelbocks.
- * [         MAX_ORDER           ]
+ * MAX_PAGE_ORDER = pageblock_order + 1, a MAX_PAGE_ORDER page has two
+ * pagelbocks.
+ * [      MAX_PAGE_ORDER         ]
  * [  pageblock0  |  pageblock1  ]
  * When either pageblock is isolated, if it is a free page, the page is not
  * split into separate migratetype lists, which is supposed to; if it is an
@@ -451,7 +452,7 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags,
 				 * the free page to the right migratetype list.
 				 *
 				 * head_pfn is not used here as a hugetlb page order
-				 * can be bigger than MAX_ORDER, but after it is
+				 * can be bigger than MAX_PAGE_ORDER, but after it is
 				 * freed, the free page order is not. Use pfn within
 				 * the range to find the head of the free page.
 				 */
@@ -459,7 +460,7 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags,
 				outer_pfn = pfn;
 				while (!PageBuddy(pfn_to_page(outer_pfn))) {
 					/* stop if we cannot find the free page */
-					if (++order > MAX_ORDER)
+					if (++order > MAX_PAGE_ORDER)
 						goto failed;
 					outer_pfn &= ~0UL << order;
 				}
@@ -660,8 +661,8 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
 	int ret;
 
 	/*
-	 * Note: pageblock_nr_pages != MAX_ORDER. Then, chunks of free pages
-	 * are not aligned to pageblock_nr_pages.
+	 * Note: pageblock_nr_pages != MAX_PAGE_ORDER. Then, chunks of free
+	 * pages are not aligned to pageblock_nr_pages.
 	 * Then we just check migratetype first.
 	 */
 	for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 4f13ce7d2452..5634e5d890f8 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -32,6 +32,8 @@ struct page_owner {
 	char comm[TASK_COMM_LEN];
 	pid_t pid;
 	pid_t tgid;
+	pid_t free_pid;
+	pid_t free_tgid;
 };
 
 static bool page_owner_enabled __initdata;
@@ -119,7 +121,6 @@ static noinline depot_stack_handle_t save_stack(gfp_t flags)
 	 * Sometimes page metadata allocation tracking requires more
 	 * memory to be allocated:
 	 * - when new stack trace is saved to stack depot
-	 * - when backtrace itself is calculated (ia64)
 	 */
 	if (current->in_page_owner)
 		return dummy_handle;
@@ -152,6 +153,8 @@ void __reset_page_owner(struct page *page, unsigned short order)
 		page_owner = get_page_owner(page_ext);
 		page_owner->free_handle = handle;
 		page_owner->free_ts_nsec = free_ts_nsec;
+		page_owner->free_pid = current->pid;
+		page_owner->free_tgid = current->tgid;
 		page_ext = page_ext_next(page_ext);
 	}
 	page_ext_put(page_ext);
@@ -253,6 +256,8 @@ void __folio_copy_owner(struct folio *newfolio, struct folio *old)
 	new_page_owner->handle = old_page_owner->handle;
 	new_page_owner->pid = old_page_owner->pid;
 	new_page_owner->tgid = old_page_owner->tgid;
+	new_page_owner->free_pid = old_page_owner->free_pid;
+	new_page_owner->free_tgid = old_page_owner->free_tgid;
 	new_page_owner->ts_nsec = old_page_owner->ts_nsec;
 	new_page_owner->free_ts_nsec = old_page_owner->ts_nsec;
 	strcpy(new_page_owner->comm, old_page_owner->comm);
@@ -315,7 +320,7 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 				unsigned long freepage_order;
 
 				freepage_order = buddy_order_unsafe(page);
-				if (freepage_order <= MAX_ORDER)
+				if (freepage_order <= MAX_PAGE_ORDER)
 					pfn += (1UL << freepage_order) - 1;
 				continue;
 			}
@@ -495,7 +500,8 @@ void __dump_page_owner(const struct page *page)
 	if (!handle) {
 		pr_alert("page_owner free stack trace missing\n");
 	} else {
-		pr_alert("page last free stack trace:\n");
+		pr_alert("page last free pid %d tgid %d stack trace:\n",
+			  page_owner->free_pid, page_owner->free_tgid);
 		stack_depot_print(handle);
 	}
 
@@ -549,7 +555,7 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 		if (PageBuddy(page)) {
 			unsigned long freepage_order = buddy_order_unsafe(page);
 
-			if (freepage_order <= MAX_ORDER)
+			if (freepage_order <= MAX_PAGE_ORDER)
 				pfn += (1UL << freepage_order) - 1;
 			continue;
 		}
@@ -657,7 +663,7 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
 			if (PageBuddy(page)) {
 				unsigned long order = buddy_order_unsafe(page);
 
-				if (order > 0 && order <= MAX_ORDER)
+				if (order > 0 && order <= MAX_PAGE_ORDER)
 					pfn += (1UL << order) - 1;
 				continue;
 			}
diff --git a/mm/page_poison.c b/mm/page_poison.c
index b4f456437b7e..3e9037363cf9 100644
--- a/mm/page_poison.c
+++ b/mm/page_poison.c
@@ -21,13 +21,13 @@ early_param("page_poison", early_page_poison_param);
 
 static void poison_page(struct page *page)
 {
-	void *addr = kmap_atomic(page);
+	void *addr = kmap_local_page(page);
 
 	/* KASAN still think the page is in-use, so skip it. */
 	kasan_disable_current();
 	memset(kasan_reset_tag(addr), PAGE_POISON, PAGE_SIZE);
 	kasan_enable_current();
-	kunmap_atomic(addr);
+	kunmap_local(addr);
 }
 
 void __kernel_poison_pages(struct page *page, int n)
@@ -77,7 +77,7 @@ static void unpoison_page(struct page *page)
 {
 	void *addr;
 
-	addr = kmap_atomic(page);
+	addr = kmap_local_page(page);
 	kasan_disable_current();
 	/*
 	 * Page poisoning when enabled poisons each and every page
@@ -86,7 +86,7 @@ static void unpoison_page(struct page *page)
 	 */
 	check_poison_mem(page, kasan_reset_tag(addr), PAGE_SIZE);
 	kasan_enable_current();
-	kunmap_atomic(addr);
+	kunmap_local(addr);
 }
 
 void __kernel_unpoison_pages(struct page *page, int n)
diff --git a/mm/page_reporting.c b/mm/page_reporting.c
index b021f482a4cb..e4c428e61d8c 100644
--- a/mm/page_reporting.c
+++ b/mm/page_reporting.c
@@ -20,7 +20,7 @@ static int page_order_update_notify(const char *val, const struct kernel_param *
 	 * If param is set beyond this limit, order is set to default
 	 * pageblock_order value
 	 */
-	return  param_set_uint_minmax(val, kp, 0, MAX_ORDER);
+	return  param_set_uint_minmax(val, kp, 0, MAX_PAGE_ORDER);
 }
 
 static const struct kernel_param_ops page_reporting_param_ops = {
@@ -276,7 +276,7 @@ page_reporting_process_zone(struct page_reporting_dev_info *prdev,
 		return err;
 
 	/* Process each free list starting from lowest order/mt */
-	for (order = page_reporting_order; order <= MAX_ORDER; order++) {
+	for (order = page_reporting_order; order < NR_PAGE_ORDERS; order++) {
 		for (mt = 0; mt < MIGRATE_TYPES; mt++) {
 			/* We do not pull pages from the isolate free list */
 			if (is_migrate_isolate(mt))
@@ -370,7 +370,7 @@ int page_reporting_register(struct page_reporting_dev_info *prdev)
 	 */
 
 	if (page_reporting_order == -1) {
-		if (prdev->order > 0 && prdev->order <= MAX_ORDER)
+		if (prdev->order > 0 && prdev->order <= MAX_PAGE_ORDER)
 			page_reporting_order = prdev->order;
 		else
 			page_reporting_order = pageblock_order;
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index e0b368e545ed..74d2de15fb5e 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -268,7 +268,8 @@ restart:
 			 * cleared *pmd but not decremented compound_mapcount().
 			 */
 			if ((pvmw->flags & PVMW_SYNC) &&
-			    transhuge_vma_suitable(vma, pvmw->address) &&
+			    thp_vma_suitable_order(vma, pvmw->address,
+						   PMD_ORDER) &&
 			    (pvmw->nr_pages >= HPAGE_PMD_NR)) {
 				spinlock_t *ptl = pmd_lock(mm, pvmw->pmd);
 
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index b7d7e4fcfad7..f46c80b18ce4 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -539,6 +539,11 @@ int walk_page_range(struct mm_struct *mm, unsigned long start,
  * not backed by VMAs. Because 'unusual' entries may be walked this function
  * will also not lock the PTEs for the pte_entry() callback. This is useful for
  * walking the kernel pages tables or page tables for firmware.
+ *
+ * Note: Be careful to walk the kernel pages tables, the caller may be need to
+ * take other effective approache (mmap lock may be insufficient) to prevent
+ * the intermediate kernel page tables belonging to the specified address range
+ * from being freed (e.g. memory hot-remove).
  */
 int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
 			  unsigned long end, const struct mm_walk_ops *ops,
@@ -556,7 +561,29 @@ int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
 	if (start >= end || !walk.mm)
 		return -EINVAL;
 
-	mmap_assert_write_locked(walk.mm);
+	/*
+	 * 1) For walking the user virtual address space:
+	 *
+	 * The mmap lock protects the page walker from changes to the page
+	 * tables during the walk.  However a read lock is insufficient to
+	 * protect those areas which don't have a VMA as munmap() detaches
+	 * the VMAs before downgrading to a read lock and actually tearing
+	 * down PTEs/page tables. In which case, the mmap write lock should
+	 * be hold.
+	 *
+	 * 2) For walking the kernel virtual address space:
+	 *
+	 * The kernel intermediate page tables usually do not be freed, so
+	 * the mmap map read lock is sufficient. But there are some exceptions.
+	 * E.g. memory hot-remove. In which case, the mmap lock is insufficient
+	 * to prevent the intermediate kernel pages tables belonging to the
+	 * specified address range from being freed. The caller should take
+	 * other actions to prevent this race.
+	 */
+	if (mm == &init_mm)
+		mmap_assert_locked(walk.mm);
+	else
+		mmap_assert_write_locked(walk.mm);
 
 	return walk_pgd_range(start, end, &walk);
 }
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index 0523edab03a6..b308e96cd05a 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -53,7 +53,10 @@ static int process_vm_rw_pages(struct page **pages,
 }
 
 /* Maximum number of pages kmalloc'd to hold struct page's during copy */
-#define PVM_MAX_KMALLOC_PAGES (PAGE_SIZE * 2)
+#define PVM_MAX_KMALLOC_PAGES 2
+
+/* Maximum number of pages that can be stored at a time */
+#define PVM_MAX_USER_PAGES (PVM_MAX_KMALLOC_PAGES * PAGE_SIZE / sizeof(struct page *))
 
 /**
  * process_vm_rw_single_vec - read/write pages from task specified
@@ -79,8 +82,6 @@ static int process_vm_rw_single_vec(unsigned long addr,
 	unsigned long start_offset = addr - pa;
 	unsigned long nr_pages;
 	ssize_t rc = 0;
-	unsigned long max_pages_per_loop = PVM_MAX_KMALLOC_PAGES
-		/ sizeof(struct pages *);
 	unsigned int flags = 0;
 
 	/* Work out address and page range required */
@@ -92,7 +93,7 @@ static int process_vm_rw_single_vec(unsigned long addr,
 		flags |= FOLL_WRITE;
 
 	while (!rc && nr_pages && iov_iter_count(iter)) {
-		int pinned_pages = min(nr_pages, max_pages_per_loop);
+		int pinned_pages = min_t(unsigned long, nr_pages, PVM_MAX_USER_PAGES);
 		int locked = 1;
 		size_t bytes;
 
@@ -171,7 +172,7 @@ static ssize_t process_vm_rw_core(pid_t pid, struct iov_iter *iter,
 		iov_len = rvec[i].iov_len;
 		if (iov_len > 0) {
 			nr_pages_iov = ((unsigned long)rvec[i].iov_base
-					+ iov_len)
+					+ iov_len - 1)
 				/ PAGE_SIZE - (unsigned long)rvec[i].iov_base
 				/ PAGE_SIZE + 1;
 			nr_pages = max(nr_pages, nr_pages_iov);
@@ -184,8 +185,8 @@ static ssize_t process_vm_rw_core(pid_t pid, struct iov_iter *iter,
 	if (nr_pages > PVM_MAX_PP_ARRAY_COUNT) {
 		/* For reliability don't try to kmalloc more than
 		   2 pages worth */
-		process_pages = kmalloc(min_t(size_t, PVM_MAX_KMALLOC_PAGES,
-					      sizeof(struct pages *)*nr_pages),
+		process_pages = kmalloc(min_t(size_t, PVM_MAX_KMALLOC_PAGES * PAGE_SIZE,
+					      sizeof(struct page *)*nr_pages),
 					GFP_KERNEL);
 
 		if (!process_pages)
diff --git a/mm/readahead.c b/mm/readahead.c
index 6925e6959fd3..23620c57c122 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -511,16 +511,14 @@ void page_cache_ra_order(struct readahead_control *ractl,
 		unsigned int order = new_order;
 
 		/* Align with smaller pages if needed */
-		if (index & ((1UL << order) - 1)) {
+		if (index & ((1UL << order) - 1))
 			order = __ffs(index);
-			if (order == 1)
-				order = 0;
-		}
 		/* Don't allocate pages past EOF */
-		while (index + (1UL << order) - 1 > limit) {
-			if (--order == 1)
-				order = 0;
-		}
+		while (index + (1UL << order) - 1 > limit)
+			order--;
+		/* THP machinery does not support order-1 */
+		if (order == 1)
+			order = 0;
 		err = ra_alloc_folio(ractl, index, mark, order, gfp);
 		if (err)
 			break;
diff --git a/mm/rmap.c b/mm/rmap.c
index 7a27a2b41802..f5d43edad529 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -470,7 +470,7 @@ void __init anon_vma_init(void)
 /*
  * Getting a lock on a stable anon_vma from a page off the LRU is tricky!
  *
- * Since there is no serialization what so ever against page_remove_rmap()
+ * Since there is no serialization what so ever against folio_remove_rmap_*()
  * the best this function can do is return a refcount increased anon_vma
  * that might have been relevant to this page.
  *
@@ -487,9 +487,15 @@ void __init anon_vma_init(void)
  * [ something equivalent to page_mapped_in_vma() ].
  *
  * Since anon_vma's slab is SLAB_TYPESAFE_BY_RCU and we know from
- * page_remove_rmap() that the anon_vma pointer from page->mapping is valid
+ * folio_remove_rmap_*() that the anon_vma pointer from page->mapping is valid
  * if there is a mapcount, we can dereference the anon_vma after observing
  * those.
+ *
+ * NOTE: the caller should normally hold folio lock when calling this.  If
+ * not, the caller needs to double check the anon_vma didn't change after
+ * taking the anon_vma lock for either read or write (UFFDIO_MOVE can modify it
+ * concurrently without folio lock protection). See folio_lock_anon_vma_read()
+ * which has already covered that, and comment above remap_pages().
  */
 struct anon_vma *folio_get_anon_vma(struct folio *folio)
 {
@@ -542,6 +548,7 @@ struct anon_vma *folio_lock_anon_vma_read(struct folio *folio,
 	struct anon_vma *root_anon_vma;
 	unsigned long anon_mapping;
 
+retry:
 	rcu_read_lock();
 	anon_mapping = (unsigned long)READ_ONCE(folio->mapping);
 	if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
@@ -553,6 +560,17 @@ struct anon_vma *folio_lock_anon_vma_read(struct folio *folio,
 	root_anon_vma = READ_ONCE(anon_vma->root);
 	if (down_read_trylock(&root_anon_vma->rwsem)) {
 		/*
+		 * folio_move_anon_rmap() might have changed the anon_vma as we
+		 * might not hold the folio lock here.
+		 */
+		if (unlikely((unsigned long)READ_ONCE(folio->mapping) !=
+			     anon_mapping)) {
+			up_read(&root_anon_vma->rwsem);
+			rcu_read_unlock();
+			goto retry;
+		}
+
+		/*
 		 * If the folio is still mapped, then this anon_vma is still
 		 * its anon_vma, and holding the mutex ensures that it will
 		 * not go away, see anon_vma_free().
@@ -586,6 +604,18 @@ struct anon_vma *folio_lock_anon_vma_read(struct folio *folio,
 	rcu_read_unlock();
 	anon_vma_lock_read(anon_vma);
 
+	/*
+	 * folio_move_anon_rmap() might have changed the anon_vma as we might
+	 * not hold the folio lock here.
+	 */
+	if (unlikely((unsigned long)READ_ONCE(folio->mapping) !=
+		     anon_mapping)) {
+		anon_vma_unlock_read(anon_vma);
+		put_anon_vma(anon_vma);
+		anon_vma = NULL;
+		goto retry;
+	}
+
 	if (atomic_dec_and_test(&anon_vma->refcount)) {
 		/*
 		 * Oops, we held the last refcount, release the lock
@@ -1127,6 +1157,48 @@ int folio_total_mapcount(struct folio *folio)
 	return mapcount;
 }
 
+static __always_inline unsigned int __folio_add_rmap(struct folio *folio,
+		struct page *page, int nr_pages, enum rmap_level level,
+		int *nr_pmdmapped)
+{
+	atomic_t *mapped = &folio->_nr_pages_mapped;
+	int first, nr = 0;
+
+	__folio_rmap_sanity_checks(folio, page, nr_pages, level);
+
+	switch (level) {
+	case RMAP_LEVEL_PTE:
+		do {
+			first = atomic_inc_and_test(&page->_mapcount);
+			if (first && folio_test_large(folio)) {
+				first = atomic_inc_return_relaxed(mapped);
+				first = (first < ENTIRELY_MAPPED);
+			}
+
+			if (first)
+				nr++;
+		} while (page++, --nr_pages > 0);
+		break;
+	case RMAP_LEVEL_PMD:
+		first = atomic_inc_and_test(&folio->_entire_mapcount);
+		if (first) {
+			nr = atomic_add_return_relaxed(ENTIRELY_MAPPED, mapped);
+			if (likely(nr < ENTIRELY_MAPPED + ENTIRELY_MAPPED)) {
+				*nr_pmdmapped = folio_nr_pages(folio);
+				nr = *nr_pmdmapped - (nr & FOLIO_PAGES_MAPPED);
+				/* Raced ahead of a remove and another add? */
+				if (unlikely(nr < 0))
+					nr = 0;
+			} else {
+				/* Raced ahead of a remove of ENTIRELY_MAPPED */
+				nr = 0;
+			}
+		}
+		break;
+	}
+	return nr;
+}
+
 /**
  * folio_move_anon_rmap - move a folio to our anon_vma
  * @folio:	The folio to move to our anon_vma
@@ -1198,12 +1270,12 @@ static void __page_check_anon_rmap(struct folio *folio, struct page *page,
 	 * The page's anon-rmap details (mapping and index) are guaranteed to
 	 * be set up correctly at this point.
 	 *
-	 * We have exclusion against page_add_anon_rmap because the caller
+	 * We have exclusion against folio_add_anon_rmap_*() because the caller
 	 * always holds the page locked.
 	 *
-	 * We have exclusion against page_add_new_anon_rmap because those pages
+	 * We have exclusion against folio_add_new_anon_rmap because those pages
 	 * are initially only visible via the pagetables, and the pte is locked
-	 * over the call to page_add_new_anon_rmap.
+	 * over the call to folio_add_new_anon_rmap.
 	 */
 	VM_BUG_ON_FOLIO(folio_anon_vma(folio)->root != vma->anon_vma->root,
 			folio);
@@ -1211,54 +1283,13 @@ static void __page_check_anon_rmap(struct folio *folio, struct page *page,
 		       page);
 }
 
-/**
- * page_add_anon_rmap - add pte mapping to an anonymous page
- * @page:	the page to add the mapping to
- * @vma:	the vm area in which the mapping is added
- * @address:	the user virtual address mapped
- * @flags:	the rmap flags
- *
- * The caller needs to hold the pte lock, and the page must be locked in
- * the anon_vma case: to serialize mapping,index checking after setting,
- * and to ensure that PageAnon is not being upgraded racily to PageKsm
- * (but PageKsm is never downgraded to PageAnon).
- */
-void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma,
-		unsigned long address, rmap_t flags)
+static __always_inline void __folio_add_anon_rmap(struct folio *folio,
+		struct page *page, int nr_pages, struct vm_area_struct *vma,
+		unsigned long address, rmap_t flags, enum rmap_level level)
 {
-	struct folio *folio = page_folio(page);
-	atomic_t *mapped = &folio->_nr_pages_mapped;
-	int nr = 0, nr_pmdmapped = 0;
-	bool compound = flags & RMAP_COMPOUND;
-	bool first;
-
-	/* Is page being mapped by PTE? Is this its first map to be added? */
-	if (likely(!compound)) {
-		first = atomic_inc_and_test(&page->_mapcount);
-		nr = first;
-		if (first && folio_test_large(folio)) {
-			nr = atomic_inc_return_relaxed(mapped);
-			nr = (nr < COMPOUND_MAPPED);
-		}
-	} else if (folio_test_pmd_mappable(folio)) {
-		/* That test is redundant: it's for safety or to optimize out */
-
-		first = atomic_inc_and_test(&folio->_entire_mapcount);
-		if (first) {
-			nr = atomic_add_return_relaxed(COMPOUND_MAPPED, mapped);
-			if (likely(nr < COMPOUND_MAPPED + COMPOUND_MAPPED)) {
-				nr_pmdmapped = folio_nr_pages(folio);
-				nr = nr_pmdmapped - (nr & FOLIO_PAGES_MAPPED);
-				/* Raced ahead of a remove and another add? */
-				if (unlikely(nr < 0))
-					nr = 0;
-			} else {
-				/* Raced ahead of a remove of COMPOUND_MAPPED */
-				nr = 0;
-			}
-		}
-	}
+	int i, nr, nr_pmdmapped = 0;
 
+	nr = __folio_add_rmap(folio, page, nr_pages, level, &nr_pmdmapped);
 	if (nr_pmdmapped)
 		__lruvec_stat_mod_folio(folio, NR_ANON_THPS, nr_pmdmapped);
 	if (nr)
@@ -1272,18 +1303,34 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma,
 		 * folio->index right when not given the address of the head
 		 * page.
 		 */
-		VM_WARN_ON_FOLIO(folio_test_large(folio) && !compound, folio);
+		VM_WARN_ON_FOLIO(folio_test_large(folio) &&
+				 level != RMAP_LEVEL_PMD, folio);
 		__folio_set_anon(folio, vma, address,
 				 !!(flags & RMAP_EXCLUSIVE));
 	} else if (likely(!folio_test_ksm(folio))) {
 		__page_check_anon_rmap(folio, page, vma, address);
 	}
-	if (flags & RMAP_EXCLUSIVE)
-		SetPageAnonExclusive(page);
-	/* While PTE-mapping a THP we have a PMD and a PTE mapping. */
-	VM_WARN_ON_FOLIO((atomic_read(&page->_mapcount) > 0 ||
-			  (folio_test_large(folio) && folio_entire_mapcount(folio) > 1)) &&
-			 PageAnonExclusive(page), folio);
+
+	if (flags & RMAP_EXCLUSIVE) {
+		switch (level) {
+		case RMAP_LEVEL_PTE:
+			for (i = 0; i < nr_pages; i++)
+				SetPageAnonExclusive(page + i);
+			break;
+		case RMAP_LEVEL_PMD:
+			SetPageAnonExclusive(page);
+			break;
+		}
+	}
+	for (i = 0; i < nr_pages; i++) {
+		struct page *cur_page = page + i;
+
+		/* While PTE-mapping a THP we have a PMD and a PTE mapping. */
+		VM_WARN_ON_FOLIO((atomic_read(&cur_page->_mapcount) > 0 ||
+				  (folio_test_large(folio) &&
+				   folio_entire_mapcount(folio) > 1)) &&
+				 PageAnonExclusive(cur_page), folio);
+	}
 
 	/*
 	 * For large folio, only mlock it if it's fully mapped to VMA. It's
@@ -1296,182 +1343,200 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma,
 }
 
 /**
+ * folio_add_anon_rmap_ptes - add PTE mappings to a page range of an anon folio
+ * @folio:	The folio to add the mappings to
+ * @page:	The first page to add
+ * @nr_pages:	The number of pages which will be mapped
+ * @vma:	The vm area in which the mappings are added
+ * @address:	The user virtual address of the first page to map
+ * @flags:	The rmap flags
+ *
+ * The page range of folio is defined by [first_page, first_page + nr_pages)
+ *
+ * The caller needs to hold the page table lock, and the page must be locked in
+ * the anon_vma case: to serialize mapping,index checking after setting,
+ * and to ensure that an anon folio is not being upgraded racily to a KSM folio
+ * (but KSM folios are never downgraded).
+ */
+void folio_add_anon_rmap_ptes(struct folio *folio, struct page *page,
+		int nr_pages, struct vm_area_struct *vma, unsigned long address,
+		rmap_t flags)
+{
+	__folio_add_anon_rmap(folio, page, nr_pages, vma, address, flags,
+			      RMAP_LEVEL_PTE);
+}
+
+/**
+ * folio_add_anon_rmap_pmd - add a PMD mapping to a page range of an anon folio
+ * @folio:	The folio to add the mapping to
+ * @page:	The first page to add
+ * @vma:	The vm area in which the mapping is added
+ * @address:	The user virtual address of the first page to map
+ * @flags:	The rmap flags
+ *
+ * The page range of folio is defined by [first_page, first_page + HPAGE_PMD_NR)
+ *
+ * The caller needs to hold the page table lock, and the page must be locked in
+ * the anon_vma case: to serialize mapping,index checking after setting.
+ */
+void folio_add_anon_rmap_pmd(struct folio *folio, struct page *page,
+		struct vm_area_struct *vma, unsigned long address, rmap_t flags)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	__folio_add_anon_rmap(folio, page, HPAGE_PMD_NR, vma, address, flags,
+			      RMAP_LEVEL_PMD);
+#else
+	WARN_ON_ONCE(true);
+#endif
+}
+
+/**
  * folio_add_new_anon_rmap - Add mapping to a new anonymous folio.
  * @folio:	The folio to add the mapping to.
  * @vma:	the vm area in which the mapping is added
  * @address:	the user virtual address mapped
  *
- * Like page_add_anon_rmap() but must only be called on *new* folios.
+ * Like folio_add_anon_rmap_*() but must only be called on *new* folios.
  * This means the inc-and-test can be bypassed.
  * The folio does not have to be locked.
  *
- * If the folio is large, it is accounted as a THP.  As the folio
+ * If the folio is pmd-mappable, it is accounted as a THP.  As the folio
  * is new, it's assumed to be mapped exclusively by a single process.
  */
 void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
 		unsigned long address)
 {
-	int nr;
+	int nr = folio_nr_pages(folio);
 
-	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
+	VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio);
+	VM_BUG_ON_VMA(address < vma->vm_start ||
+			address + (nr << PAGE_SHIFT) > vma->vm_end, vma);
 	__folio_set_swapbacked(folio);
+	__folio_set_anon(folio, vma, address, true);
 
-	if (likely(!folio_test_pmd_mappable(folio))) {
+	if (likely(!folio_test_large(folio))) {
 		/* increment count (starts at -1) */
 		atomic_set(&folio->_mapcount, 0);
-		nr = 1;
+		SetPageAnonExclusive(&folio->page);
+	} else if (!folio_test_pmd_mappable(folio)) {
+		int i;
+
+		for (i = 0; i < nr; i++) {
+			struct page *page = folio_page(folio, i);
+
+			/* increment count (starts at -1) */
+			atomic_set(&page->_mapcount, 0);
+			SetPageAnonExclusive(page);
+		}
+
+		atomic_set(&folio->_nr_pages_mapped, nr);
 	} else {
 		/* increment count (starts at -1) */
 		atomic_set(&folio->_entire_mapcount, 0);
-		atomic_set(&folio->_nr_pages_mapped, COMPOUND_MAPPED);
-		nr = folio_nr_pages(folio);
+		atomic_set(&folio->_nr_pages_mapped, ENTIRELY_MAPPED);
+		SetPageAnonExclusive(&folio->page);
 		__lruvec_stat_mod_folio(folio, NR_ANON_THPS, nr);
 	}
 
 	__lruvec_stat_mod_folio(folio, NR_ANON_MAPPED, nr);
-	__folio_set_anon(folio, vma, address, true);
-	SetPageAnonExclusive(&folio->page);
 }
 
-/**
- * folio_add_file_rmap_range - add pte mapping to page range of a folio
- * @folio:	The folio to add the mapping to
- * @page:	The first page to add
- * @nr_pages:	The number of pages which will be mapped
- * @vma:	the vm area in which the mapping is added
- * @compound:	charge the page as compound or small page
- *
- * The page range of folio is defined by [first_page, first_page + nr_pages)
- *
- * The caller needs to hold the pte lock.
- */
-void folio_add_file_rmap_range(struct folio *folio, struct page *page,
-			unsigned int nr_pages, struct vm_area_struct *vma,
-			bool compound)
+static __always_inline void __folio_add_file_rmap(struct folio *folio,
+		struct page *page, int nr_pages, struct vm_area_struct *vma,
+		enum rmap_level level)
 {
-	atomic_t *mapped = &folio->_nr_pages_mapped;
-	unsigned int nr_pmdmapped = 0, first;
-	int nr = 0;
-
-	VM_WARN_ON_FOLIO(compound && !folio_test_pmd_mappable(folio), folio);
-
-	/* Is page being mapped by PTE? Is this its first map to be added? */
-	if (likely(!compound)) {
-		do {
-			first = atomic_inc_and_test(&page->_mapcount);
-			if (first && folio_test_large(folio)) {
-				first = atomic_inc_return_relaxed(mapped);
-				first = (first < COMPOUND_MAPPED);
-			}
-
-			if (first)
-				nr++;
-		} while (page++, --nr_pages > 0);
-	} else if (folio_test_pmd_mappable(folio)) {
-		/* That test is redundant: it's for safety or to optimize out */
+	int nr, nr_pmdmapped = 0;
 
-		first = atomic_inc_and_test(&folio->_entire_mapcount);
-		if (first) {
-			nr = atomic_add_return_relaxed(COMPOUND_MAPPED, mapped);
-			if (likely(nr < COMPOUND_MAPPED + COMPOUND_MAPPED)) {
-				nr_pmdmapped = folio_nr_pages(folio);
-				nr = nr_pmdmapped - (nr & FOLIO_PAGES_MAPPED);
-				/* Raced ahead of a remove and another add? */
-				if (unlikely(nr < 0))
-					nr = 0;
-			} else {
-				/* Raced ahead of a remove of COMPOUND_MAPPED */
-				nr = 0;
-			}
-		}
-	}
+	VM_WARN_ON_FOLIO(folio_test_anon(folio), folio);
 
+	nr = __folio_add_rmap(folio, page, nr_pages, level, &nr_pmdmapped);
 	if (nr_pmdmapped)
 		__lruvec_stat_mod_folio(folio, folio_test_swapbacked(folio) ?
 			NR_SHMEM_PMDMAPPED : NR_FILE_PMDMAPPED, nr_pmdmapped);
 	if (nr)
 		__lruvec_stat_mod_folio(folio, NR_FILE_MAPPED, nr);
 
-	/* See comments in page_add_anon_rmap() */
+	/* See comments in folio_add_anon_rmap_*() */
 	if (!folio_test_large(folio))
 		mlock_vma_folio(folio, vma);
 }
 
 /**
- * page_add_file_rmap - add pte mapping to a file page
- * @page:	the page to add the mapping to
- * @vma:	the vm area in which the mapping is added
- * @compound:	charge the page as compound or small page
+ * folio_add_file_rmap_ptes - add PTE mappings to a page range of a folio
+ * @folio:	The folio to add the mappings to
+ * @page:	The first page to add
+ * @nr_pages:	The number of pages that will be mapped using PTEs
+ * @vma:	The vm area in which the mappings are added
+ *
+ * The page range of the folio is defined by [page, page + nr_pages)
  *
- * The caller needs to hold the pte lock.
+ * The caller needs to hold the page table lock.
  */
-void page_add_file_rmap(struct page *page, struct vm_area_struct *vma,
-		bool compound)
+void folio_add_file_rmap_ptes(struct folio *folio, struct page *page,
+		int nr_pages, struct vm_area_struct *vma)
 {
-	struct folio *folio = page_folio(page);
-	unsigned int nr_pages;
-
-	VM_WARN_ON_ONCE_PAGE(compound && !PageTransHuge(page), page);
-
-	if (likely(!compound))
-		nr_pages = 1;
-	else
-		nr_pages = folio_nr_pages(folio);
-
-	folio_add_file_rmap_range(folio, page, nr_pages, vma, compound);
+	__folio_add_file_rmap(folio, page, nr_pages, vma, RMAP_LEVEL_PTE);
 }
 
 /**
- * page_remove_rmap - take down pte mapping from a page
- * @page:	page to remove mapping from
- * @vma:	the vm area from which the mapping is removed
- * @compound:	uncharge the page as compound or small page
+ * folio_add_file_rmap_pmd - add a PMD mapping to a page range of a folio
+ * @folio:	The folio to add the mapping to
+ * @page:	The first page to add
+ * @vma:	The vm area in which the mapping is added
  *
- * The caller needs to hold the pte lock.
+ * The page range of the folio is defined by [page, page + HPAGE_PMD_NR)
+ *
+ * The caller needs to hold the page table lock.
  */
-void page_remove_rmap(struct page *page, struct vm_area_struct *vma,
-		bool compound)
+void folio_add_file_rmap_pmd(struct folio *folio, struct page *page,
+		struct vm_area_struct *vma)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	__folio_add_file_rmap(folio, page, HPAGE_PMD_NR, vma, RMAP_LEVEL_PMD);
+#else
+	WARN_ON_ONCE(true);
+#endif
+}
+
+static __always_inline void __folio_remove_rmap(struct folio *folio,
+		struct page *page, int nr_pages, struct vm_area_struct *vma,
+		enum rmap_level level)
 {
-	struct folio *folio = page_folio(page);
 	atomic_t *mapped = &folio->_nr_pages_mapped;
-	int nr = 0, nr_pmdmapped = 0;
-	bool last;
+	int last, nr = 0, nr_pmdmapped = 0;
 	enum node_stat_item idx;
 
-	VM_BUG_ON_PAGE(compound && !PageHead(page), page);
-
-	/* Hugetlb pages are not counted in NR_*MAPPED */
-	if (unlikely(folio_test_hugetlb(folio))) {
-		/* hugetlb pages are always mapped with pmds */
-		atomic_dec(&folio->_entire_mapcount);
-		return;
-	}
+	__folio_rmap_sanity_checks(folio, page, nr_pages, level);
 
-	/* Is page being unmapped by PTE? Is this its last map to be removed? */
-	if (likely(!compound)) {
-		last = atomic_add_negative(-1, &page->_mapcount);
-		nr = last;
-		if (last && folio_test_large(folio)) {
-			nr = atomic_dec_return_relaxed(mapped);
-			nr = (nr < COMPOUND_MAPPED);
-		}
-	} else if (folio_test_pmd_mappable(folio)) {
-		/* That test is redundant: it's for safety or to optimize out */
+	switch (level) {
+	case RMAP_LEVEL_PTE:
+		do {
+			last = atomic_add_negative(-1, &page->_mapcount);
+			if (last && folio_test_large(folio)) {
+				last = atomic_dec_return_relaxed(mapped);
+				last = (last < ENTIRELY_MAPPED);
+			}
 
+			if (last)
+				nr++;
+		} while (page++, --nr_pages > 0);
+		break;
+	case RMAP_LEVEL_PMD:
 		last = atomic_add_negative(-1, &folio->_entire_mapcount);
 		if (last) {
-			nr = atomic_sub_return_relaxed(COMPOUND_MAPPED, mapped);
-			if (likely(nr < COMPOUND_MAPPED)) {
+			nr = atomic_sub_return_relaxed(ENTIRELY_MAPPED, mapped);
+			if (likely(nr < ENTIRELY_MAPPED)) {
 				nr_pmdmapped = folio_nr_pages(folio);
 				nr = nr_pmdmapped - (nr & FOLIO_PAGES_MAPPED);
 				/* Raced ahead of another remove and an add? */
 				if (unlikely(nr < 0))
 					nr = 0;
 			} else {
-				/* An add of COMPOUND_MAPPED raced ahead */
+				/* An add of ENTIRELY_MAPPED raced ahead */
 				nr = 0;
 			}
 		}
+		break;
 	}
 
 	if (nr_pmdmapped) {
@@ -1488,18 +1553,18 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma,
 		__lruvec_stat_mod_folio(folio, idx, -nr);
 
 		/*
-		 * Queue anon THP for deferred split if at least one
+		 * Queue anon large folio for deferred split if at least one
 		 * page of the folio is unmapped and at least one page
 		 * is still mapped.
 		 */
-		if (folio_test_pmd_mappable(folio) && folio_test_anon(folio))
-			if (!compound || nr < nr_pmdmapped)
+		if (folio_test_large(folio) && folio_test_anon(folio))
+			if (level == RMAP_LEVEL_PTE || nr < nr_pmdmapped)
 				deferred_split_folio(folio);
 	}
 
 	/*
 	 * It would be tidy to reset folio_test_anon mapping when fully
-	 * unmapped, but that might overwrite a racing page_add_anon_rmap
+	 * unmapped, but that might overwrite a racing folio_add_anon_rmap_*()
 	 * which increments mapcount after us but sets mapping before us:
 	 * so leave the reset to free_pages_prepare, and remember that
 	 * it's only reliable while mapped.
@@ -1508,6 +1573,43 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma,
 	munlock_vma_folio(folio, vma);
 }
 
+/**
+ * folio_remove_rmap_ptes - remove PTE mappings from a page range of a folio
+ * @folio:	The folio to remove the mappings from
+ * @page:	The first page to remove
+ * @nr_pages:	The number of pages that will be removed from the mapping
+ * @vma:	The vm area from which the mappings are removed
+ *
+ * The page range of the folio is defined by [page, page + nr_pages)
+ *
+ * The caller needs to hold the page table lock.
+ */
+void folio_remove_rmap_ptes(struct folio *folio, struct page *page,
+		int nr_pages, struct vm_area_struct *vma)
+{
+	__folio_remove_rmap(folio, page, nr_pages, vma, RMAP_LEVEL_PTE);
+}
+
+/**
+ * folio_remove_rmap_pmd - remove a PMD mapping from a page range of a folio
+ * @folio:	The folio to remove the mapping from
+ * @page:	The first page to remove
+ * @vma:	The vm area from which the mapping is removed
+ *
+ * The page range of the folio is defined by [page, page + HPAGE_PMD_NR)
+ *
+ * The caller needs to hold the page table lock.
+ */
+void folio_remove_rmap_pmd(struct folio *folio, struct page *page,
+		struct vm_area_struct *vma)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	__folio_remove_rmap(folio, page, HPAGE_PMD_NR, vma, RMAP_LEVEL_PMD);
+#else
+	WARN_ON_ONCE(true);
+#endif
+}
+
 /*
  * @arg: enum ttu_flags will be passed to this argument
  */
@@ -1526,7 +1628,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 
 	/*
 	 * When racing against e.g. zap_pte_range() on another cpu,
-	 * in between its ptep_get_and_clear_full() and page_remove_rmap(),
+	 * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(),
 	 * try_to_unmap() may return before page_mapped() has become false,
 	 * if page table locking is skipped: use TTU_SYNC to wait for that.
 	 */
@@ -1764,9 +1866,9 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 				break;
 			}
 
-			/* See page_try_share_anon_rmap(): clear PTE first. */
+			/* See folio_try_share_anon_rmap(): clear PTE first. */
 			if (anon_exclusive &&
-			    page_try_share_anon_rmap(subpage)) {
+			    folio_try_share_anon_rmap_pte(folio, subpage)) {
 				swap_free(entry);
 				set_pte_at(mm, address, pvmw.pte, pteval);
 				ret = false;
@@ -1804,7 +1906,10 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 			dec_mm_counter(mm, mm_counter_file(&folio->page));
 		}
 discard:
-		page_remove_rmap(subpage, vma, folio_test_hugetlb(folio));
+		if (unlikely(folio_test_hugetlb(folio)))
+			hugetlb_remove_rmap(folio);
+		else
+			folio_remove_rmap_pte(folio, subpage, vma);
 		if (vma->vm_flags & VM_LOCKED)
 			mlock_drain_local();
 		folio_put(folio);
@@ -1872,7 +1977,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 
 	/*
 	 * When racing against e.g. zap_pte_range() on another cpu,
-	 * in between its ptep_get_and_clear_full() and page_remove_rmap(),
+	 * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(),
 	 * try_to_migrate() may return before page_mapped() has become false,
 	 * if page table locking is skipped: use TTU_SYNC to wait for that.
 	 */
@@ -2037,7 +2142,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			pte_t swp_pte;
 
 			if (anon_exclusive)
-				BUG_ON(page_try_share_anon_rmap(subpage));
+				WARN_ON_ONCE(folio_try_share_anon_rmap_pte(folio,
+									   subpage));
 
 			/*
 			 * Store the pfn of the page in a special migration
@@ -2108,14 +2214,19 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			VM_BUG_ON_PAGE(pte_write(pteval) && folio_test_anon(folio) &&
 				       !anon_exclusive, subpage);
 
-			/* See page_try_share_anon_rmap(): clear PTE first. */
-			if (anon_exclusive &&
-			    page_try_share_anon_rmap(subpage)) {
-				if (folio_test_hugetlb(folio))
+			/* See folio_try_share_anon_rmap_pte(): clear PTE first. */
+			if (folio_test_hugetlb(folio)) {
+				if (anon_exclusive &&
+				    hugetlb_try_share_anon_rmap(folio)) {
 					set_huge_pte_at(mm, address, pvmw.pte,
 							pteval, hsz);
-				else
-					set_pte_at(mm, address, pvmw.pte, pteval);
+					ret = false;
+					page_vma_mapped_walk_done(&pvmw);
+					break;
+				}
+			} else if (anon_exclusive &&
+				   folio_try_share_anon_rmap_pte(folio, subpage)) {
+				set_pte_at(mm, address, pvmw.pte, pteval);
 				ret = false;
 				page_vma_mapped_walk_done(&pvmw);
 				break;
@@ -2157,7 +2268,10 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			 */
 		}
 
-		page_remove_rmap(subpage, vma, folio_test_hugetlb(folio));
+		if (unlikely(folio_test_hugetlb(folio)))
+			hugetlb_remove_rmap(folio);
+		else
+			folio_remove_rmap_pte(folio, subpage, vma);
 		if (vma->vm_flags & VM_LOCKED)
 			mlock_drain_local();
 		folio_put(folio);
@@ -2296,7 +2410,7 @@ static bool page_make_device_exclusive_one(struct folio *folio,
 		 * There is a reference on the page for the swap entry which has
 		 * been removed, so shouldn't take another.
 		 */
-		page_remove_rmap(subpage, vma, false);
+		folio_remove_rmap_pte(folio, subpage, vma);
 	}
 
 	mmu_notifier_invalidate_range_end(&range);
@@ -2580,12 +2694,11 @@ void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc)
  * The following two functions are for anonymous (private mapped) hugepages.
  * Unlike common anonymous pages, anonymous hugepages have no accounting code
  * and no lru code, because we handle hugepages differently from common pages.
- *
- * RMAP_COMPOUND is ignored.
  */
-void hugepage_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
-			    unsigned long address, rmap_t flags)
+void hugetlb_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
+		unsigned long address, rmap_t flags)
 {
+	VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio);
 	VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
 
 	atomic_inc(&folio->_entire_mapcount);
@@ -2595,9 +2708,11 @@ void hugepage_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
 			 PageAnonExclusive(&folio->page), folio);
 }
 
-void hugepage_add_new_anon_rmap(struct folio *folio,
-			struct vm_area_struct *vma, unsigned long address)
+void hugetlb_add_new_anon_rmap(struct folio *folio,
+		struct vm_area_struct *vma, unsigned long address)
 {
+	VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio);
+
 	BUG_ON(address < vma->vm_start || address >= vma->vm_end);
 	/* increment count (starts at -1) */
 	atomic_set(&folio->_entire_mapcount, 0);
diff --git a/mm/shmem.c b/mm/shmem.c
index 91e2620148b2..d7c84ff62186 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -79,6 +79,7 @@ static struct vfsmount *shm_mnt __ro_after_init;
 #include <linux/rmap.h>
 #include <linux/uuid.h>
 #include <linux/quotaops.h>
+#include <linux/rcupdate_wait.h>
 
 #include <linux/uaccess.h>
 
@@ -1080,7 +1081,24 @@ whole_folios:
 				}
 				VM_BUG_ON_FOLIO(folio_test_writeback(folio),
 						folio);
-				truncate_inode_folio(mapping, folio);
+
+				if (!folio_test_large(folio)) {
+					truncate_inode_folio(mapping, folio);
+				} else if (truncate_inode_partial_folio(folio, lstart, lend)) {
+					/*
+					 * If we split a page, reset the loop so
+					 * that we pick up the new sub pages.
+					 * Otherwise the THP was entirely
+					 * dropped or the target range was
+					 * zeroed, so just continue the loop as
+					 * is.
+					 */
+					if (!folio_test_large(folio)) {
+						folio_unlock(folio);
+						index = start;
+						break;
+					}
+				}
 			}
 			folio_unlock(folio);
 		}
@@ -1497,8 +1515,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 
 		mutex_unlock(&shmem_swaplist_mutex);
 		BUG_ON(folio_mapped(folio));
-		swap_writepage(&folio->page, wbc);
-		return 0;
+		return swap_writepage(&folio->page, wbc);
 	}
 
 	mutex_unlock(&shmem_swaplist_mutex);
@@ -1553,15 +1570,13 @@ static struct folio *shmem_swapin_cluster(swp_entry_t swap, gfp_t gfp,
 {
 	struct mempolicy *mpol;
 	pgoff_t ilx;
-	struct page *page;
+	struct folio *folio;
 
 	mpol = shmem_get_pgoff_policy(info, index, 0, &ilx);
-	page = swap_cluster_readahead(swap, gfp, mpol, ilx);
+	folio = swap_cluster_readahead(swap, gfp, mpol, ilx);
 	mpol_cond_put(mpol);
 
-	if (!page)
-		return NULL;
-	return page_folio(page);
+	return folio;
 }
 
 /*
@@ -4445,8 +4460,8 @@ static void __init shmem_destroy_inodecache(void)
 }
 
 /* Keep the page in page cache instead of truncating it */
-static int shmem_error_remove_page(struct address_space *mapping,
-				   struct page *page)
+static int shmem_error_remove_folio(struct address_space *mapping,
+				   struct folio *folio)
 {
 	return 0;
 }
@@ -4461,7 +4476,7 @@ const struct address_space_operations shmem_aops = {
 #ifdef CONFIG_MIGRATION
 	.migrate_folio	= migrate_folio,
 #endif
-	.error_remove_page = shmem_error_remove_page,
+	.error_remove_folio = shmem_error_remove_folio,
 };
 EXPORT_SYMBOL(shmem_aops);
 
diff --git a/mm/show_mem.c b/mm/show_mem.c
index ba0808d6917f..8dcfafbd283c 100644
--- a/mm/show_mem.c
+++ b/mm/show_mem.c
@@ -352,8 +352,8 @@ static void show_free_areas(unsigned int filter, nodemask_t *nodemask, int max_z
 
 	for_each_populated_zone(zone) {
 		unsigned int order;
-		unsigned long nr[MAX_ORDER + 1], flags, total = 0;
-		unsigned char types[MAX_ORDER + 1];
+		unsigned long nr[NR_PAGE_ORDERS], flags, total = 0;
+		unsigned char types[NR_PAGE_ORDERS];
 
 		if (zone_idx(zone) > max_zone_idx)
 			continue;
@@ -363,7 +363,7 @@ static void show_free_areas(unsigned int filter, nodemask_t *nodemask, int max_z
 		printk(KERN_CONT "%s: ", zone->name);
 
 		spin_lock_irqsave(&zone->lock, flags);
-		for (order = 0; order <= MAX_ORDER; order++) {
+		for (order = 0; order < NR_PAGE_ORDERS; order++) {
 			struct free_area *area = &zone->free_area[order];
 			int type;
 
@@ -377,7 +377,7 @@ static void show_free_areas(unsigned int filter, nodemask_t *nodemask, int max_z
 			}
 		}
 		spin_unlock_irqrestore(&zone->lock, flags);
-		for (order = 0; order <= MAX_ORDER; order++) {
+		for (order = 0; order < NR_PAGE_ORDERS; order++) {
 			printk(KERN_CONT "%lu*%lukB ",
 			       nr[order], K(1UL) << order);
 			if (nr[order])
diff --git a/mm/shrinker.c b/mm/shrinker.c
index dd91eab43ed3..dc5d2a6fcfc4 100644
--- a/mm/shrinker.c
+++ b/mm/shrinker.c
@@ -126,7 +126,7 @@ static int expand_one_shrinker_info(struct mem_cgroup *memcg, int new_size,
 		if (new_nr_max <= old->map_nr_max)
 			continue;
 
-		new = kvmalloc_node(sizeof(*new) + new_size, GFP_KERNEL, nid);
+		new = kvzalloc_node(sizeof(*new) + new_size, GFP_KERNEL, nid);
 		if (!new)
 			return -ENOMEM;
 
diff --git a/mm/shuffle.h b/mm/shuffle.h
index a6bdf54f96f1..61bbcddeeee6 100644
--- a/mm/shuffle.h
+++ b/mm/shuffle.h
@@ -4,7 +4,7 @@
 #define _MM_SHUFFLE_H
 #include <linux/jump_label.h>
 
-#define SHUFFLE_ORDER MAX_ORDER
+#define SHUFFLE_ORDER MAX_PAGE_ORDER
 
 #ifdef CONFIG_SHUFFLE_PAGE_ALLOCATOR
 DECLARE_STATIC_KEY_FALSE(page_alloc_shuffle_key);
diff --git a/mm/slab.c b/mm/slab.c
deleted file mode 100644
index 9ad3d0f2d1a5..000000000000
--- a/mm/slab.c
+++ /dev/null
@@ -1,4026 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * linux/mm/slab.c
- * Written by Mark Hemment, 1996/97.
- * (markhe@nextd.demon.co.uk)
- *
- * kmem_cache_destroy() + some cleanup - 1999 Andrea Arcangeli
- *
- * Major cleanup, different bufctl logic, per-cpu arrays
- *	(c) 2000 Manfred Spraul
- *
- * Cleanup, make the head arrays unconditional, preparation for NUMA
- * 	(c) 2002 Manfred Spraul
- *
- * An implementation of the Slab Allocator as described in outline in;
- *	UNIX Internals: The New Frontiers by Uresh Vahalia
- *	Pub: Prentice Hall	ISBN 0-13-101908-2
- * or with a little more detail in;
- *	The Slab Allocator: An Object-Caching Kernel Memory Allocator
- *	Jeff Bonwick (Sun Microsystems).
- *	Presented at: USENIX Summer 1994 Technical Conference
- *
- * The memory is organized in caches, one cache for each object type.
- * (e.g. inode_cache, dentry_cache, buffer_head, vm_area_struct)
- * Each cache consists out of many slabs (they are small (usually one
- * page long) and always contiguous), and each slab contains multiple
- * initialized objects.
- *
- * This means, that your constructor is used only for newly allocated
- * slabs and you must pass objects with the same initializations to
- * kmem_cache_free.
- *
- * Each cache can only support one memory type (GFP_DMA, GFP_HIGHMEM,
- * normal). If you need a special memory type, then must create a new
- * cache for that memory type.
- *
- * In order to reduce fragmentation, the slabs are sorted in 3 groups:
- *   full slabs with 0 free objects
- *   partial slabs
- *   empty slabs with no allocated objects
- *
- * If partial slabs exist, then new allocations come from these slabs,
- * otherwise from empty slabs or new slabs are allocated.
- *
- * kmem_cache_destroy() CAN CRASH if you try to allocate from the cache
- * during kmem_cache_destroy(). The caller must prevent concurrent allocs.
- *
- * Each cache has a short per-cpu head array, most allocs
- * and frees go into that array, and if that array overflows, then 1/2
- * of the entries in the array are given back into the global cache.
- * The head array is strictly LIFO and should improve the cache hit rates.
- * On SMP, it additionally reduces the spinlock operations.
- *
- * The c_cpuarray may not be read with enabled local interrupts -
- * it's changed with a smp_call_function().
- *
- * SMP synchronization:
- *  constructors and destructors are called without any locking.
- *  Several members in struct kmem_cache and struct slab never change, they
- *	are accessed without any locking.
- *  The per-cpu arrays are never accessed from the wrong cpu, no locking,
- *  	and local interrupts are disabled so slab code is preempt-safe.
- *  The non-constant members are protected with a per-cache irq spinlock.
- *
- * Many thanks to Mark Hemment, who wrote another per-cpu slab patch
- * in 2000 - many ideas in the current implementation are derived from
- * his patch.
- *
- * Further notes from the original documentation:
- *
- * 11 April '97.  Started multi-threading - markhe
- *	The global cache-chain is protected by the mutex 'slab_mutex'.
- *	The sem is only needed when accessing/extending the cache-chain, which
- *	can never happen inside an interrupt (kmem_cache_create(),
- *	kmem_cache_shrink() and kmem_cache_reap()).
- *
- *	At present, each engine can be growing a cache.  This should be blocked.
- *
- * 15 March 2005. NUMA slab allocator.
- *	Shai Fultheim <shai@scalex86.org>.
- *	Shobhit Dayal <shobhit@calsoftinc.com>
- *	Alok N Kataria <alokk@calsoftinc.com>
- *	Christoph Lameter <christoph@lameter.com>
- *
- *	Modified the slab allocator to be node aware on NUMA systems.
- *	Each node has its own list of partial, free and full slabs.
- *	All object allocations for a node occur from node specific slab lists.
- */
-
-#include	<linux/slab.h>
-#include	<linux/mm.h>
-#include	<linux/poison.h>
-#include	<linux/swap.h>
-#include	<linux/cache.h>
-#include	<linux/interrupt.h>
-#include	<linux/init.h>
-#include	<linux/compiler.h>
-#include	<linux/cpuset.h>
-#include	<linux/proc_fs.h>
-#include	<linux/seq_file.h>
-#include	<linux/notifier.h>
-#include	<linux/kallsyms.h>
-#include	<linux/kfence.h>
-#include	<linux/cpu.h>
-#include	<linux/sysctl.h>
-#include	<linux/module.h>
-#include	<linux/rcupdate.h>
-#include	<linux/string.h>
-#include	<linux/uaccess.h>
-#include	<linux/nodemask.h>
-#include	<linux/kmemleak.h>
-#include	<linux/mempolicy.h>
-#include	<linux/mutex.h>
-#include	<linux/fault-inject.h>
-#include	<linux/rtmutex.h>
-#include	<linux/reciprocal_div.h>
-#include	<linux/debugobjects.h>
-#include	<linux/memory.h>
-#include	<linux/prefetch.h>
-#include	<linux/sched/task_stack.h>
-
-#include	<net/sock.h>
-
-#include	<asm/cacheflush.h>
-#include	<asm/tlbflush.h>
-#include	<asm/page.h>
-
-#include <trace/events/kmem.h>
-
-#include	"internal.h"
-
-#include	"slab.h"
-
-/*
- * DEBUG	- 1 for kmem_cache_create() to honour; SLAB_RED_ZONE & SLAB_POISON.
- *		  0 for faster, smaller code (especially in the critical paths).
- *
- * STATS	- 1 to collect stats for /proc/slabinfo.
- *		  0 for faster, smaller code (especially in the critical paths).
- *
- * FORCED_DEBUG	- 1 enables SLAB_RED_ZONE and SLAB_POISON (if possible)
- */
-
-#ifdef CONFIG_DEBUG_SLAB
-#define	DEBUG		1
-#define	STATS		1
-#define	FORCED_DEBUG	1
-#else
-#define	DEBUG		0
-#define	STATS		0
-#define	FORCED_DEBUG	0
-#endif
-
-/* Shouldn't this be in a header file somewhere? */
-#define	BYTES_PER_WORD		sizeof(void *)
-#define	REDZONE_ALIGN		max(BYTES_PER_WORD, __alignof__(unsigned long long))
-
-#ifndef ARCH_KMALLOC_FLAGS
-#define ARCH_KMALLOC_FLAGS SLAB_HWCACHE_ALIGN
-#endif
-
-#define FREELIST_BYTE_INDEX (((PAGE_SIZE >> BITS_PER_BYTE) \
-				<= SLAB_OBJ_MIN_SIZE) ? 1 : 0)
-
-#if FREELIST_BYTE_INDEX
-typedef unsigned char freelist_idx_t;
-#else
-typedef unsigned short freelist_idx_t;
-#endif
-
-#define SLAB_OBJ_MAX_NUM ((1 << sizeof(freelist_idx_t) * BITS_PER_BYTE) - 1)
-
-/*
- * struct array_cache
- *
- * Purpose:
- * - LIFO ordering, to hand out cache-warm objects from _alloc
- * - reduce the number of linked list operations
- * - reduce spinlock operations
- *
- * The limit is stored in the per-cpu structure to reduce the data cache
- * footprint.
- *
- */
-struct array_cache {
-	unsigned int avail;
-	unsigned int limit;
-	unsigned int batchcount;
-	unsigned int touched;
-	void *entry[];	/*
-			 * Must have this definition in here for the proper
-			 * alignment of array_cache. Also simplifies accessing
-			 * the entries.
-			 */
-};
-
-struct alien_cache {
-	spinlock_t lock;
-	struct array_cache ac;
-};
-
-/*
- * Need this for bootstrapping a per node allocator.
- */
-#define NUM_INIT_LISTS (2 * MAX_NUMNODES)
-static struct kmem_cache_node __initdata init_kmem_cache_node[NUM_INIT_LISTS];
-#define	CACHE_CACHE 0
-#define	SIZE_NODE (MAX_NUMNODES)
-
-static int drain_freelist(struct kmem_cache *cache,
-			struct kmem_cache_node *n, int tofree);
-static void free_block(struct kmem_cache *cachep, void **objpp, int len,
-			int node, struct list_head *list);
-static void slabs_destroy(struct kmem_cache *cachep, struct list_head *list);
-static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp);
-static void cache_reap(struct work_struct *unused);
-
-static inline void fixup_objfreelist_debug(struct kmem_cache *cachep,
-						void **list);
-static inline void fixup_slab_list(struct kmem_cache *cachep,
-				struct kmem_cache_node *n, struct slab *slab,
-				void **list);
-
-#define INDEX_NODE kmalloc_index(sizeof(struct kmem_cache_node))
-
-static void kmem_cache_node_init(struct kmem_cache_node *parent)
-{
-	INIT_LIST_HEAD(&parent->slabs_full);
-	INIT_LIST_HEAD(&parent->slabs_partial);
-	INIT_LIST_HEAD(&parent->slabs_free);
-	parent->total_slabs = 0;
-	parent->free_slabs = 0;
-	parent->shared = NULL;
-	parent->alien = NULL;
-	parent->colour_next = 0;
-	raw_spin_lock_init(&parent->list_lock);
-	parent->free_objects = 0;
-	parent->free_touched = 0;
-}
-
-#define MAKE_LIST(cachep, listp, slab, nodeid)				\
-	do {								\
-		INIT_LIST_HEAD(listp);					\
-		list_splice(&get_node(cachep, nodeid)->slab, listp);	\
-	} while (0)
-
-#define	MAKE_ALL_LISTS(cachep, ptr, nodeid)				\
-	do {								\
-	MAKE_LIST((cachep), (&(ptr)->slabs_full), slabs_full, nodeid);	\
-	MAKE_LIST((cachep), (&(ptr)->slabs_partial), slabs_partial, nodeid); \
-	MAKE_LIST((cachep), (&(ptr)->slabs_free), slabs_free, nodeid);	\
-	} while (0)
-
-#define CFLGS_OBJFREELIST_SLAB	((slab_flags_t __force)0x40000000U)
-#define CFLGS_OFF_SLAB		((slab_flags_t __force)0x80000000U)
-#define	OBJFREELIST_SLAB(x)	((x)->flags & CFLGS_OBJFREELIST_SLAB)
-#define	OFF_SLAB(x)	((x)->flags & CFLGS_OFF_SLAB)
-
-#define BATCHREFILL_LIMIT	16
-/*
- * Optimization question: fewer reaps means less probability for unnecessary
- * cpucache drain/refill cycles.
- *
- * OTOH the cpuarrays can contain lots of objects,
- * which could lock up otherwise freeable slabs.
- */
-#define REAPTIMEOUT_AC		(2*HZ)
-#define REAPTIMEOUT_NODE	(4*HZ)
-
-#if STATS
-#define	STATS_INC_ACTIVE(x)	((x)->num_active++)
-#define	STATS_DEC_ACTIVE(x)	((x)->num_active--)
-#define	STATS_INC_ALLOCED(x)	((x)->num_allocations++)
-#define	STATS_INC_GROWN(x)	((x)->grown++)
-#define	STATS_ADD_REAPED(x, y)	((x)->reaped += (y))
-#define	STATS_SET_HIGH(x)						\
-	do {								\
-		if ((x)->num_active > (x)->high_mark)			\
-			(x)->high_mark = (x)->num_active;		\
-	} while (0)
-#define	STATS_INC_ERR(x)	((x)->errors++)
-#define	STATS_INC_NODEALLOCS(x)	((x)->node_allocs++)
-#define	STATS_INC_NODEFREES(x)	((x)->node_frees++)
-#define STATS_INC_ACOVERFLOW(x)   ((x)->node_overflow++)
-#define	STATS_SET_FREEABLE(x, i)					\
-	do {								\
-		if ((x)->max_freeable < i)				\
-			(x)->max_freeable = i;				\
-	} while (0)
-#define STATS_INC_ALLOCHIT(x)	atomic_inc(&(x)->allochit)
-#define STATS_INC_ALLOCMISS(x)	atomic_inc(&(x)->allocmiss)
-#define STATS_INC_FREEHIT(x)	atomic_inc(&(x)->freehit)
-#define STATS_INC_FREEMISS(x)	atomic_inc(&(x)->freemiss)
-#else
-#define	STATS_INC_ACTIVE(x)	do { } while (0)
-#define	STATS_DEC_ACTIVE(x)	do { } while (0)
-#define	STATS_INC_ALLOCED(x)	do { } while (0)
-#define	STATS_INC_GROWN(x)	do { } while (0)
-#define	STATS_ADD_REAPED(x, y)	do { (void)(y); } while (0)
-#define	STATS_SET_HIGH(x)	do { } while (0)
-#define	STATS_INC_ERR(x)	do { } while (0)
-#define	STATS_INC_NODEALLOCS(x)	do { } while (0)
-#define	STATS_INC_NODEFREES(x)	do { } while (0)
-#define STATS_INC_ACOVERFLOW(x)   do { } while (0)
-#define	STATS_SET_FREEABLE(x, i) do { } while (0)
-#define STATS_INC_ALLOCHIT(x)	do { } while (0)
-#define STATS_INC_ALLOCMISS(x)	do { } while (0)
-#define STATS_INC_FREEHIT(x)	do { } while (0)
-#define STATS_INC_FREEMISS(x)	do { } while (0)
-#endif
-
-#if DEBUG
-
-/*
- * memory layout of objects:
- * 0		: objp
- * 0 .. cachep->obj_offset - BYTES_PER_WORD - 1: padding. This ensures that
- * 		the end of an object is aligned with the end of the real
- * 		allocation. Catches writes behind the end of the allocation.
- * cachep->obj_offset - BYTES_PER_WORD .. cachep->obj_offset - 1:
- * 		redzone word.
- * cachep->obj_offset: The real object.
- * cachep->size - 2* BYTES_PER_WORD: redzone word [BYTES_PER_WORD long]
- * cachep->size - 1* BYTES_PER_WORD: last caller address
- *					[BYTES_PER_WORD long]
- */
-static int obj_offset(struct kmem_cache *cachep)
-{
-	return cachep->obj_offset;
-}
-
-static unsigned long long *dbg_redzone1(struct kmem_cache *cachep, void *objp)
-{
-	BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
-	return (unsigned long long *) (objp + obj_offset(cachep) -
-				      sizeof(unsigned long long));
-}
-
-static unsigned long long *dbg_redzone2(struct kmem_cache *cachep, void *objp)
-{
-	BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
-	if (cachep->flags & SLAB_STORE_USER)
-		return (unsigned long long *)(objp + cachep->size -
-					      sizeof(unsigned long long) -
-					      REDZONE_ALIGN);
-	return (unsigned long long *) (objp + cachep->size -
-				       sizeof(unsigned long long));
-}
-
-static void **dbg_userword(struct kmem_cache *cachep, void *objp)
-{
-	BUG_ON(!(cachep->flags & SLAB_STORE_USER));
-	return (void **)(objp + cachep->size - BYTES_PER_WORD);
-}
-
-#else
-
-#define obj_offset(x)			0
-#define dbg_redzone1(cachep, objp)	({BUG(); (unsigned long long *)NULL;})
-#define dbg_redzone2(cachep, objp)	({BUG(); (unsigned long long *)NULL;})
-#define dbg_userword(cachep, objp)	({BUG(); (void **)NULL;})
-
-#endif
-
-/*
- * Do not go above this order unless 0 objects fit into the slab or
- * overridden on the command line.
- */
-#define	SLAB_MAX_ORDER_HI	1
-#define	SLAB_MAX_ORDER_LO	0
-static int slab_max_order = SLAB_MAX_ORDER_LO;
-static bool slab_max_order_set __initdata;
-
-static inline void *index_to_obj(struct kmem_cache *cache,
-				 const struct slab *slab, unsigned int idx)
-{
-	return slab->s_mem + cache->size * idx;
-}
-
-#define BOOT_CPUCACHE_ENTRIES	1
-/* internal cache of cache description objs */
-static struct kmem_cache kmem_cache_boot = {
-	.batchcount = 1,
-	.limit = BOOT_CPUCACHE_ENTRIES,
-	.shared = 1,
-	.size = sizeof(struct kmem_cache),
-	.name = "kmem_cache",
-};
-
-static DEFINE_PER_CPU(struct delayed_work, slab_reap_work);
-
-static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
-{
-	return this_cpu_ptr(cachep->cpu_cache);
-}
-
-/*
- * Calculate the number of objects and left-over bytes for a given buffer size.
- */
-static unsigned int cache_estimate(unsigned long gfporder, size_t buffer_size,
-		slab_flags_t flags, size_t *left_over)
-{
-	unsigned int num;
-	size_t slab_size = PAGE_SIZE << gfporder;
-
-	/*
-	 * The slab management structure can be either off the slab or
-	 * on it. For the latter case, the memory allocated for a
-	 * slab is used for:
-	 *
-	 * - @buffer_size bytes for each object
-	 * - One freelist_idx_t for each object
-	 *
-	 * We don't need to consider alignment of freelist because
-	 * freelist will be at the end of slab page. The objects will be
-	 * at the correct alignment.
-	 *
-	 * If the slab management structure is off the slab, then the
-	 * alignment will already be calculated into the size. Because
-	 * the slabs are all pages aligned, the objects will be at the
-	 * correct alignment when allocated.
-	 */
-	if (flags & (CFLGS_OBJFREELIST_SLAB | CFLGS_OFF_SLAB)) {
-		num = slab_size / buffer_size;
-		*left_over = slab_size % buffer_size;
-	} else {
-		num = slab_size / (buffer_size + sizeof(freelist_idx_t));
-		*left_over = slab_size %
-			(buffer_size + sizeof(freelist_idx_t));
-	}
-
-	return num;
-}
-
-#if DEBUG
-#define slab_error(cachep, msg) __slab_error(__func__, cachep, msg)
-
-static void __slab_error(const char *function, struct kmem_cache *cachep,
-			char *msg)
-{
-	pr_err("slab error in %s(): cache `%s': %s\n",
-	       function, cachep->name, msg);
-	dump_stack();
-	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
-}
-#endif
-
-/*
- * By default on NUMA we use alien caches to stage the freeing of
- * objects allocated from other nodes. This causes massive memory
- * inefficiencies when using fake NUMA setup to split memory into a
- * large number of small nodes, so it can be disabled on the command
- * line
-  */
-
-static int use_alien_caches __read_mostly = 1;
-static int __init noaliencache_setup(char *s)
-{
-	use_alien_caches = 0;
-	return 1;
-}
-__setup("noaliencache", noaliencache_setup);
-
-static int __init slab_max_order_setup(char *str)
-{
-	get_option(&str, &slab_max_order);
-	slab_max_order = slab_max_order < 0 ? 0 :
-				min(slab_max_order, MAX_ORDER);
-	slab_max_order_set = true;
-
-	return 1;
-}
-__setup("slab_max_order=", slab_max_order_setup);
-
-#ifdef CONFIG_NUMA
-/*
- * Special reaping functions for NUMA systems called from cache_reap().
- * These take care of doing round robin flushing of alien caches (containing
- * objects freed on different nodes from which they were allocated) and the
- * flushing of remote pcps by calling drain_node_pages.
- */
-static DEFINE_PER_CPU(unsigned long, slab_reap_node);
-
-static void init_reap_node(int cpu)
-{
-	per_cpu(slab_reap_node, cpu) = next_node_in(cpu_to_mem(cpu),
-						    node_online_map);
-}
-
-static void next_reap_node(void)
-{
-	int node = __this_cpu_read(slab_reap_node);
-
-	node = next_node_in(node, node_online_map);
-	__this_cpu_write(slab_reap_node, node);
-}
-
-#else
-#define init_reap_node(cpu) do { } while (0)
-#define next_reap_node(void) do { } while (0)
-#endif
-
-/*
- * Initiate the reap timer running on the target CPU.  We run at around 1 to 2Hz
- * via the workqueue/eventd.
- * Add the CPU number into the expiration time to minimize the possibility of
- * the CPUs getting into lockstep and contending for the global cache chain
- * lock.
- */
-static void start_cpu_timer(int cpu)
-{
-	struct delayed_work *reap_work = &per_cpu(slab_reap_work, cpu);
-
-	if (reap_work->work.func == NULL) {
-		init_reap_node(cpu);
-		INIT_DEFERRABLE_WORK(reap_work, cache_reap);
-		schedule_delayed_work_on(cpu, reap_work,
-					__round_jiffies_relative(HZ, cpu));
-	}
-}
-
-static void init_arraycache(struct array_cache *ac, int limit, int batch)
-{
-	if (ac) {
-		ac->avail = 0;
-		ac->limit = limit;
-		ac->batchcount = batch;
-		ac->touched = 0;
-	}
-}
-
-static struct array_cache *alloc_arraycache(int node, int entries,
-					    int batchcount, gfp_t gfp)
-{
-	size_t memsize = sizeof(void *) * entries + sizeof(struct array_cache);
-	struct array_cache *ac = NULL;
-
-	ac = kmalloc_node(memsize, gfp, node);
-	/*
-	 * The array_cache structures contain pointers to free object.
-	 * However, when such objects are allocated or transferred to another
-	 * cache the pointers are not cleared and they could be counted as
-	 * valid references during a kmemleak scan. Therefore, kmemleak must
-	 * not scan such objects.
-	 */
-	kmemleak_no_scan(ac);
-	init_arraycache(ac, entries, batchcount);
-	return ac;
-}
-
-static noinline void cache_free_pfmemalloc(struct kmem_cache *cachep,
-					struct slab *slab, void *objp)
-{
-	struct kmem_cache_node *n;
-	int slab_node;
-	LIST_HEAD(list);
-
-	slab_node = slab_nid(slab);
-	n = get_node(cachep, slab_node);
-
-	raw_spin_lock(&n->list_lock);
-	free_block(cachep, &objp, 1, slab_node, &list);
-	raw_spin_unlock(&n->list_lock);
-
-	slabs_destroy(cachep, &list);
-}
-
-/*
- * Transfer objects in one arraycache to another.
- * Locking must be handled by the caller.
- *
- * Return the number of entries transferred.
- */
-static int transfer_objects(struct array_cache *to,
-		struct array_cache *from, unsigned int max)
-{
-	/* Figure out how many entries to transfer */
-	int nr = min3(from->avail, max, to->limit - to->avail);
-
-	if (!nr)
-		return 0;
-
-	memcpy(to->entry + to->avail, from->entry + from->avail - nr,
-			sizeof(void *) *nr);
-
-	from->avail -= nr;
-	to->avail += nr;
-	return nr;
-}
-
-/* &alien->lock must be held by alien callers. */
-static __always_inline void __free_one(struct array_cache *ac, void *objp)
-{
-	/* Avoid trivial double-free. */
-	if (IS_ENABLED(CONFIG_SLAB_FREELIST_HARDENED) &&
-	    WARN_ON_ONCE(ac->avail > 0 && ac->entry[ac->avail - 1] == objp))
-		return;
-	ac->entry[ac->avail++] = objp;
-}
-
-#ifndef CONFIG_NUMA
-
-#define drain_alien_cache(cachep, alien) do { } while (0)
-#define reap_alien(cachep, n) do { } while (0)
-
-static inline struct alien_cache **alloc_alien_cache(int node,
-						int limit, gfp_t gfp)
-{
-	return NULL;
-}
-
-static inline void free_alien_cache(struct alien_cache **ac_ptr)
-{
-}
-
-static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
-{
-	return 0;
-}
-
-static inline gfp_t gfp_exact_node(gfp_t flags)
-{
-	return flags & ~__GFP_NOFAIL;
-}
-
-#else	/* CONFIG_NUMA */
-
-static struct alien_cache *__alloc_alien_cache(int node, int entries,
-						int batch, gfp_t gfp)
-{
-	size_t memsize = sizeof(void *) * entries + sizeof(struct alien_cache);
-	struct alien_cache *alc = NULL;
-
-	alc = kmalloc_node(memsize, gfp, node);
-	if (alc) {
-		kmemleak_no_scan(alc);
-		init_arraycache(&alc->ac, entries, batch);
-		spin_lock_init(&alc->lock);
-	}
-	return alc;
-}
-
-static struct alien_cache **alloc_alien_cache(int node, int limit, gfp_t gfp)
-{
-	struct alien_cache **alc_ptr;
-	int i;
-
-	if (limit > 1)
-		limit = 12;
-	alc_ptr = kcalloc_node(nr_node_ids, sizeof(void *), gfp, node);
-	if (!alc_ptr)
-		return NULL;
-
-	for_each_node(i) {
-		if (i == node || !node_online(i))
-			continue;
-		alc_ptr[i] = __alloc_alien_cache(node, limit, 0xbaadf00d, gfp);
-		if (!alc_ptr[i]) {
-			for (i--; i >= 0; i--)
-				kfree(alc_ptr[i]);
-			kfree(alc_ptr);
-			return NULL;
-		}
-	}
-	return alc_ptr;
-}
-
-static void free_alien_cache(struct alien_cache **alc_ptr)
-{
-	int i;
-
-	if (!alc_ptr)
-		return;
-	for_each_node(i)
-	    kfree(alc_ptr[i]);
-	kfree(alc_ptr);
-}
-
-static void __drain_alien_cache(struct kmem_cache *cachep,
-				struct array_cache *ac, int node,
-				struct list_head *list)
-{
-	struct kmem_cache_node *n = get_node(cachep, node);
-
-	if (ac->avail) {
-		raw_spin_lock(&n->list_lock);
-		/*
-		 * Stuff objects into the remote nodes shared array first.
-		 * That way we could avoid the overhead of putting the objects
-		 * into the free lists and getting them back later.
-		 */
-		if (n->shared)
-			transfer_objects(n->shared, ac, ac->limit);
-
-		free_block(cachep, ac->entry, ac->avail, node, list);
-		ac->avail = 0;
-		raw_spin_unlock(&n->list_lock);
-	}
-}
-
-/*
- * Called from cache_reap() to regularly drain alien caches round robin.
- */
-static void reap_alien(struct kmem_cache *cachep, struct kmem_cache_node *n)
-{
-	int node = __this_cpu_read(slab_reap_node);
-
-	if (n->alien) {
-		struct alien_cache *alc = n->alien[node];
-		struct array_cache *ac;
-
-		if (alc) {
-			ac = &alc->ac;
-			if (ac->avail && spin_trylock_irq(&alc->lock)) {
-				LIST_HEAD(list);
-
-				__drain_alien_cache(cachep, ac, node, &list);
-				spin_unlock_irq(&alc->lock);
-				slabs_destroy(cachep, &list);
-			}
-		}
-	}
-}
-
-static void drain_alien_cache(struct kmem_cache *cachep,
-				struct alien_cache **alien)
-{
-	int i = 0;
-	struct alien_cache *alc;
-	struct array_cache *ac;
-	unsigned long flags;
-
-	for_each_online_node(i) {
-		alc = alien[i];
-		if (alc) {
-			LIST_HEAD(list);
-
-			ac = &alc->ac;
-			spin_lock_irqsave(&alc->lock, flags);
-			__drain_alien_cache(cachep, ac, i, &list);
-			spin_unlock_irqrestore(&alc->lock, flags);
-			slabs_destroy(cachep, &list);
-		}
-	}
-}
-
-static int __cache_free_alien(struct kmem_cache *cachep, void *objp,
-				int node, int slab_node)
-{
-	struct kmem_cache_node *n;
-	struct alien_cache *alien = NULL;
-	struct array_cache *ac;
-	LIST_HEAD(list);
-
-	n = get_node(cachep, node);
-	STATS_INC_NODEFREES(cachep);
-	if (n->alien && n->alien[slab_node]) {
-		alien = n->alien[slab_node];
-		ac = &alien->ac;
-		spin_lock(&alien->lock);
-		if (unlikely(ac->avail == ac->limit)) {
-			STATS_INC_ACOVERFLOW(cachep);
-			__drain_alien_cache(cachep, ac, slab_node, &list);
-		}
-		__free_one(ac, objp);
-		spin_unlock(&alien->lock);
-		slabs_destroy(cachep, &list);
-	} else {
-		n = get_node(cachep, slab_node);
-		raw_spin_lock(&n->list_lock);
-		free_block(cachep, &objp, 1, slab_node, &list);
-		raw_spin_unlock(&n->list_lock);
-		slabs_destroy(cachep, &list);
-	}
-	return 1;
-}
-
-static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
-{
-	int slab_node = slab_nid(virt_to_slab(objp));
-	int node = numa_mem_id();
-	/*
-	 * Make sure we are not freeing an object from another node to the array
-	 * cache on this cpu.
-	 */
-	if (likely(node == slab_node))
-		return 0;
-
-	return __cache_free_alien(cachep, objp, node, slab_node);
-}
-
-/*
- * Construct gfp mask to allocate from a specific node but do not reclaim or
- * warn about failures.
- */
-static inline gfp_t gfp_exact_node(gfp_t flags)
-{
-	return (flags | __GFP_THISNODE | __GFP_NOWARN) & ~(__GFP_RECLAIM|__GFP_NOFAIL);
-}
-#endif
-
-static int init_cache_node(struct kmem_cache *cachep, int node, gfp_t gfp)
-{
-	struct kmem_cache_node *n;
-
-	/*
-	 * Set up the kmem_cache_node for cpu before we can
-	 * begin anything. Make sure some other cpu on this
-	 * node has not already allocated this
-	 */
-	n = get_node(cachep, node);
-	if (n) {
-		raw_spin_lock_irq(&n->list_lock);
-		n->free_limit = (1 + nr_cpus_node(node)) * cachep->batchcount +
-				cachep->num;
-		raw_spin_unlock_irq(&n->list_lock);
-
-		return 0;
-	}
-
-	n = kmalloc_node(sizeof(struct kmem_cache_node), gfp, node);
-	if (!n)
-		return -ENOMEM;
-
-	kmem_cache_node_init(n);
-	n->next_reap = jiffies + REAPTIMEOUT_NODE +
-		    ((unsigned long)cachep) % REAPTIMEOUT_NODE;
-
-	n->free_limit =
-		(1 + nr_cpus_node(node)) * cachep->batchcount + cachep->num;
-
-	/*
-	 * The kmem_cache_nodes don't come and go as CPUs
-	 * come and go.  slab_mutex provides sufficient
-	 * protection here.
-	 */
-	cachep->node[node] = n;
-
-	return 0;
-}
-
-#if defined(CONFIG_NUMA) || defined(CONFIG_SMP)
-/*
- * Allocates and initializes node for a node on each slab cache, used for
- * either memory or cpu hotplug.  If memory is being hot-added, the kmem_cache_node
- * will be allocated off-node since memory is not yet online for the new node.
- * When hotplugging memory or a cpu, existing nodes are not replaced if
- * already in use.
- *
- * Must hold slab_mutex.
- */
-static int init_cache_node_node(int node)
-{
-	int ret;
-	struct kmem_cache *cachep;
-
-	list_for_each_entry(cachep, &slab_caches, list) {
-		ret = init_cache_node(cachep, node, GFP_KERNEL);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-#endif
-
-static int setup_kmem_cache_node(struct kmem_cache *cachep,
-				int node, gfp_t gfp, bool force_change)
-{
-	int ret = -ENOMEM;
-	struct kmem_cache_node *n;
-	struct array_cache *old_shared = NULL;
-	struct array_cache *new_shared = NULL;
-	struct alien_cache **new_alien = NULL;
-	LIST_HEAD(list);
-
-	if (use_alien_caches) {
-		new_alien = alloc_alien_cache(node, cachep->limit, gfp);
-		if (!new_alien)
-			goto fail;
-	}
-
-	if (cachep->shared) {
-		new_shared = alloc_arraycache(node,
-			cachep->shared * cachep->batchcount, 0xbaadf00d, gfp);
-		if (!new_shared)
-			goto fail;
-	}
-
-	ret = init_cache_node(cachep, node, gfp);
-	if (ret)
-		goto fail;
-
-	n = get_node(cachep, node);
-	raw_spin_lock_irq(&n->list_lock);
-	if (n->shared && force_change) {
-		free_block(cachep, n->shared->entry,
-				n->shared->avail, node, &list);
-		n->shared->avail = 0;
-	}
-
-	if (!n->shared || force_change) {
-		old_shared = n->shared;
-		n->shared = new_shared;
-		new_shared = NULL;
-	}
-
-	if (!n->alien) {
-		n->alien = new_alien;
-		new_alien = NULL;
-	}
-
-	raw_spin_unlock_irq(&n->list_lock);
-	slabs_destroy(cachep, &list);
-
-	/*
-	 * To protect lockless access to n->shared during irq disabled context.
-	 * If n->shared isn't NULL in irq disabled context, accessing to it is
-	 * guaranteed to be valid until irq is re-enabled, because it will be
-	 * freed after synchronize_rcu().
-	 */
-	if (old_shared && force_change)
-		synchronize_rcu();
-
-fail:
-	kfree(old_shared);
-	kfree(new_shared);
-	free_alien_cache(new_alien);
-
-	return ret;
-}
-
-#ifdef CONFIG_SMP
-
-static void cpuup_canceled(long cpu)
-{
-	struct kmem_cache *cachep;
-	struct kmem_cache_node *n = NULL;
-	int node = cpu_to_mem(cpu);
-	const struct cpumask *mask = cpumask_of_node(node);
-
-	list_for_each_entry(cachep, &slab_caches, list) {
-		struct array_cache *nc;
-		struct array_cache *shared;
-		struct alien_cache **alien;
-		LIST_HEAD(list);
-
-		n = get_node(cachep, node);
-		if (!n)
-			continue;
-
-		raw_spin_lock_irq(&n->list_lock);
-
-		/* Free limit for this kmem_cache_node */
-		n->free_limit -= cachep->batchcount;
-
-		/* cpu is dead; no one can alloc from it. */
-		nc = per_cpu_ptr(cachep->cpu_cache, cpu);
-		free_block(cachep, nc->entry, nc->avail, node, &list);
-		nc->avail = 0;
-
-		if (!cpumask_empty(mask)) {
-			raw_spin_unlock_irq(&n->list_lock);
-			goto free_slab;
-		}
-
-		shared = n->shared;
-		if (shared) {
-			free_block(cachep, shared->entry,
-				   shared->avail, node, &list);
-			n->shared = NULL;
-		}
-
-		alien = n->alien;
-		n->alien = NULL;
-
-		raw_spin_unlock_irq(&n->list_lock);
-
-		kfree(shared);
-		if (alien) {
-			drain_alien_cache(cachep, alien);
-			free_alien_cache(alien);
-		}
-
-free_slab:
-		slabs_destroy(cachep, &list);
-	}
-	/*
-	 * In the previous loop, all the objects were freed to
-	 * the respective cache's slabs,  now we can go ahead and
-	 * shrink each nodelist to its limit.
-	 */
-	list_for_each_entry(cachep, &slab_caches, list) {
-		n = get_node(cachep, node);
-		if (!n)
-			continue;
-		drain_freelist(cachep, n, INT_MAX);
-	}
-}
-
-static int cpuup_prepare(long cpu)
-{
-	struct kmem_cache *cachep;
-	int node = cpu_to_mem(cpu);
-	int err;
-
-	/*
-	 * We need to do this right in the beginning since
-	 * alloc_arraycache's are going to use this list.
-	 * kmalloc_node allows us to add the slab to the right
-	 * kmem_cache_node and not this cpu's kmem_cache_node
-	 */
-	err = init_cache_node_node(node);
-	if (err < 0)
-		goto bad;
-
-	/*
-	 * Now we can go ahead with allocating the shared arrays and
-	 * array caches
-	 */
-	list_for_each_entry(cachep, &slab_caches, list) {
-		err = setup_kmem_cache_node(cachep, node, GFP_KERNEL, false);
-		if (err)
-			goto bad;
-	}
-
-	return 0;
-bad:
-	cpuup_canceled(cpu);
-	return -ENOMEM;
-}
-
-int slab_prepare_cpu(unsigned int cpu)
-{
-	int err;
-
-	mutex_lock(&slab_mutex);
-	err = cpuup_prepare(cpu);
-	mutex_unlock(&slab_mutex);
-	return err;
-}
-
-/*
- * This is called for a failed online attempt and for a successful
- * offline.
- *
- * Even if all the cpus of a node are down, we don't free the
- * kmem_cache_node of any cache. This is to avoid a race between cpu_down, and
- * a kmalloc allocation from another cpu for memory from the node of
- * the cpu going down.  The kmem_cache_node structure is usually allocated from
- * kmem_cache_create() and gets destroyed at kmem_cache_destroy().
- */
-int slab_dead_cpu(unsigned int cpu)
-{
-	mutex_lock(&slab_mutex);
-	cpuup_canceled(cpu);
-	mutex_unlock(&slab_mutex);
-	return 0;
-}
-#endif
-
-static int slab_online_cpu(unsigned int cpu)
-{
-	start_cpu_timer(cpu);
-	return 0;
-}
-
-static int slab_offline_cpu(unsigned int cpu)
-{
-	/*
-	 * Shutdown cache reaper. Note that the slab_mutex is held so
-	 * that if cache_reap() is invoked it cannot do anything
-	 * expensive but will only modify reap_work and reschedule the
-	 * timer.
-	 */
-	cancel_delayed_work_sync(&per_cpu(slab_reap_work, cpu));
-	/* Now the cache_reaper is guaranteed to be not running. */
-	per_cpu(slab_reap_work, cpu).work.func = NULL;
-	return 0;
-}
-
-#if defined(CONFIG_NUMA)
-/*
- * Drains freelist for a node on each slab cache, used for memory hot-remove.
- * Returns -EBUSY if all objects cannot be drained so that the node is not
- * removed.
- *
- * Must hold slab_mutex.
- */
-static int __meminit drain_cache_node_node(int node)
-{
-	struct kmem_cache *cachep;
-	int ret = 0;
-
-	list_for_each_entry(cachep, &slab_caches, list) {
-		struct kmem_cache_node *n;
-
-		n = get_node(cachep, node);
-		if (!n)
-			continue;
-
-		drain_freelist(cachep, n, INT_MAX);
-
-		if (!list_empty(&n->slabs_full) ||
-		    !list_empty(&n->slabs_partial)) {
-			ret = -EBUSY;
-			break;
-		}
-	}
-	return ret;
-}
-
-static int __meminit slab_memory_callback(struct notifier_block *self,
-					unsigned long action, void *arg)
-{
-	struct memory_notify *mnb = arg;
-	int ret = 0;
-	int nid;
-
-	nid = mnb->status_change_nid;
-	if (nid < 0)
-		goto out;
-
-	switch (action) {
-	case MEM_GOING_ONLINE:
-		mutex_lock(&slab_mutex);
-		ret = init_cache_node_node(nid);
-		mutex_unlock(&slab_mutex);
-		break;
-	case MEM_GOING_OFFLINE:
-		mutex_lock(&slab_mutex);
-		ret = drain_cache_node_node(nid);
-		mutex_unlock(&slab_mutex);
-		break;
-	case MEM_ONLINE:
-	case MEM_OFFLINE:
-	case MEM_CANCEL_ONLINE:
-	case MEM_CANCEL_OFFLINE:
-		break;
-	}
-out:
-	return notifier_from_errno(ret);
-}
-#endif /* CONFIG_NUMA */
-
-/*
- * swap the static kmem_cache_node with kmalloced memory
- */
-static void __init init_list(struct kmem_cache *cachep, struct kmem_cache_node *list,
-				int nodeid)
-{
-	struct kmem_cache_node *ptr;
-
-	ptr = kmalloc_node(sizeof(struct kmem_cache_node), GFP_NOWAIT, nodeid);
-	BUG_ON(!ptr);
-
-	memcpy(ptr, list, sizeof(struct kmem_cache_node));
-	/*
-	 * Do not assume that spinlocks can be initialized via memcpy:
-	 */
-	raw_spin_lock_init(&ptr->list_lock);
-
-	MAKE_ALL_LISTS(cachep, ptr, nodeid);
-	cachep->node[nodeid] = ptr;
-}
-
-/*
- * For setting up all the kmem_cache_node for cache whose buffer_size is same as
- * size of kmem_cache_node.
- */
-static void __init set_up_node(struct kmem_cache *cachep, int index)
-{
-	int node;
-
-	for_each_online_node(node) {
-		cachep->node[node] = &init_kmem_cache_node[index + node];
-		cachep->node[node]->next_reap = jiffies +
-		    REAPTIMEOUT_NODE +
-		    ((unsigned long)cachep) % REAPTIMEOUT_NODE;
-	}
-}
-
-/*
- * Initialisation.  Called after the page allocator have been initialised and
- * before smp_init().
- */
-void __init kmem_cache_init(void)
-{
-	int i;
-
-	kmem_cache = &kmem_cache_boot;
-
-	if (!IS_ENABLED(CONFIG_NUMA) || num_possible_nodes() == 1)
-		use_alien_caches = 0;
-
-	for (i = 0; i < NUM_INIT_LISTS; i++)
-		kmem_cache_node_init(&init_kmem_cache_node[i]);
-
-	/*
-	 * Fragmentation resistance on low memory - only use bigger
-	 * page orders on machines with more than 32MB of memory if
-	 * not overridden on the command line.
-	 */
-	if (!slab_max_order_set && totalram_pages() > (32 << 20) >> PAGE_SHIFT)
-		slab_max_order = SLAB_MAX_ORDER_HI;
-
-	/* Bootstrap is tricky, because several objects are allocated
-	 * from caches that do not exist yet:
-	 * 1) initialize the kmem_cache cache: it contains the struct
-	 *    kmem_cache structures of all caches, except kmem_cache itself:
-	 *    kmem_cache is statically allocated.
-	 *    Initially an __init data area is used for the head array and the
-	 *    kmem_cache_node structures, it's replaced with a kmalloc allocated
-	 *    array at the end of the bootstrap.
-	 * 2) Create the first kmalloc cache.
-	 *    The struct kmem_cache for the new cache is allocated normally.
-	 *    An __init data area is used for the head array.
-	 * 3) Create the remaining kmalloc caches, with minimally sized
-	 *    head arrays.
-	 * 4) Replace the __init data head arrays for kmem_cache and the first
-	 *    kmalloc cache with kmalloc allocated arrays.
-	 * 5) Replace the __init data for kmem_cache_node for kmem_cache and
-	 *    the other cache's with kmalloc allocated memory.
-	 * 6) Resize the head arrays of the kmalloc caches to their final sizes.
-	 */
-
-	/* 1) create the kmem_cache */
-
-	/*
-	 * struct kmem_cache size depends on nr_node_ids & nr_cpu_ids
-	 */
-	create_boot_cache(kmem_cache, "kmem_cache",
-		offsetof(struct kmem_cache, node) +
-				  nr_node_ids * sizeof(struct kmem_cache_node *),
-				  SLAB_HWCACHE_ALIGN, 0, 0);
-	list_add(&kmem_cache->list, &slab_caches);
-	slab_state = PARTIAL;
-
-	/*
-	 * Initialize the caches that provide memory for the  kmem_cache_node
-	 * structures first.  Without this, further allocations will bug.
-	 */
-	new_kmalloc_cache(INDEX_NODE, KMALLOC_NORMAL, ARCH_KMALLOC_FLAGS);
-	slab_state = PARTIAL_NODE;
-	setup_kmalloc_cache_index_table();
-
-	/* 5) Replace the bootstrap kmem_cache_node */
-	{
-		int nid;
-
-		for_each_online_node(nid) {
-			init_list(kmem_cache, &init_kmem_cache_node[CACHE_CACHE + nid], nid);
-
-			init_list(kmalloc_caches[KMALLOC_NORMAL][INDEX_NODE],
-					  &init_kmem_cache_node[SIZE_NODE + nid], nid);
-		}
-	}
-
-	create_kmalloc_caches(ARCH_KMALLOC_FLAGS);
-}
-
-void __init kmem_cache_init_late(void)
-{
-	struct kmem_cache *cachep;
-
-	/* 6) resize the head arrays to their final sizes */
-	mutex_lock(&slab_mutex);
-	list_for_each_entry(cachep, &slab_caches, list)
-		if (enable_cpucache(cachep, GFP_NOWAIT))
-			BUG();
-	mutex_unlock(&slab_mutex);
-
-	/* Done! */
-	slab_state = FULL;
-
-#ifdef CONFIG_NUMA
-	/*
-	 * Register a memory hotplug callback that initializes and frees
-	 * node.
-	 */
-	hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI);
-#endif
-
-	/*
-	 * The reap timers are started later, with a module init call: That part
-	 * of the kernel is not yet operational.
-	 */
-}
-
-static int __init cpucache_init(void)
-{
-	int ret;
-
-	/*
-	 * Register the timers that return unneeded pages to the page allocator
-	 */
-	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "SLAB online",
-				slab_online_cpu, slab_offline_cpu);
-	WARN_ON(ret < 0);
-
-	return 0;
-}
-__initcall(cpucache_init);
-
-static noinline void
-slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
-{
-#if DEBUG
-	struct kmem_cache_node *n;
-	unsigned long flags;
-	int node;
-	static DEFINE_RATELIMIT_STATE(slab_oom_rs, DEFAULT_RATELIMIT_INTERVAL,
-				      DEFAULT_RATELIMIT_BURST);
-
-	if ((gfpflags & __GFP_NOWARN) || !__ratelimit(&slab_oom_rs))
-		return;
-
-	pr_warn("SLAB: Unable to allocate memory on node %d, gfp=%#x(%pGg)\n",
-		nodeid, gfpflags, &gfpflags);
-	pr_warn("  cache: %s, object size: %d, order: %d\n",
-		cachep->name, cachep->size, cachep->gfporder);
-
-	for_each_kmem_cache_node(cachep, node, n) {
-		unsigned long total_slabs, free_slabs, free_objs;
-
-		raw_spin_lock_irqsave(&n->list_lock, flags);
-		total_slabs = n->total_slabs;
-		free_slabs = n->free_slabs;
-		free_objs = n->free_objects;
-		raw_spin_unlock_irqrestore(&n->list_lock, flags);
-
-		pr_warn("  node %d: slabs: %ld/%ld, objs: %ld/%ld\n",
-			node, total_slabs - free_slabs, total_slabs,
-			(total_slabs * cachep->num) - free_objs,
-			total_slabs * cachep->num);
-	}
-#endif
-}
-
-/*
- * Interface to system's page allocator. No need to hold the
- * kmem_cache_node ->list_lock.
- *
- * If we requested dmaable memory, we will get it. Even if we
- * did not request dmaable memory, we might get it, but that
- * would be relatively rare and ignorable.
- */
-static struct slab *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
-								int nodeid)
-{
-	struct folio *folio;
-	struct slab *slab;
-
-	flags |= cachep->allocflags;
-
-	folio = (struct folio *) __alloc_pages_node(nodeid, flags, cachep->gfporder);
-	if (!folio) {
-		slab_out_of_memory(cachep, flags, nodeid);
-		return NULL;
-	}
-
-	slab = folio_slab(folio);
-
-	account_slab(slab, cachep->gfporder, cachep, flags);
-	__folio_set_slab(folio);
-	/* Make the flag visible before any changes to folio->mapping */
-	smp_wmb();
-	/* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */
-	if (sk_memalloc_socks() && folio_is_pfmemalloc(folio))
-		slab_set_pfmemalloc(slab);
-
-	return slab;
-}
-
-/*
- * Interface to system's page release.
- */
-static void kmem_freepages(struct kmem_cache *cachep, struct slab *slab)
-{
-	int order = cachep->gfporder;
-	struct folio *folio = slab_folio(slab);
-
-	BUG_ON(!folio_test_slab(folio));
-	__slab_clear_pfmemalloc(slab);
-	page_mapcount_reset(&folio->page);
-	folio->mapping = NULL;
-	/* Make the mapping reset visible before clearing the flag */
-	smp_wmb();
-	__folio_clear_slab(folio);
-
-	mm_account_reclaimed_pages(1 << order);
-	unaccount_slab(slab, order, cachep);
-	__free_pages(&folio->page, order);
-}
-
-static void kmem_rcu_free(struct rcu_head *head)
-{
-	struct kmem_cache *cachep;
-	struct slab *slab;
-
-	slab = container_of(head, struct slab, rcu_head);
-	cachep = slab->slab_cache;
-
-	kmem_freepages(cachep, slab);
-}
-
-#if DEBUG
-static inline bool is_debug_pagealloc_cache(struct kmem_cache *cachep)
-{
-	return debug_pagealloc_enabled_static() && OFF_SLAB(cachep) &&
-			((cachep->size % PAGE_SIZE) == 0);
-}
-
-#ifdef CONFIG_DEBUG_PAGEALLOC
-static void slab_kernel_map(struct kmem_cache *cachep, void *objp, int map)
-{
-	if (!is_debug_pagealloc_cache(cachep))
-		return;
-
-	__kernel_map_pages(virt_to_page(objp), cachep->size / PAGE_SIZE, map);
-}
-
-#else
-static inline void slab_kernel_map(struct kmem_cache *cachep, void *objp,
-				int map) {}
-
-#endif
-
-static void poison_obj(struct kmem_cache *cachep, void *addr, unsigned char val)
-{
-	int size = cachep->object_size;
-	addr = &((char *)addr)[obj_offset(cachep)];
-
-	memset(addr, val, size);
-	*(unsigned char *)(addr + size - 1) = POISON_END;
-}
-
-static void dump_line(char *data, int offset, int limit)
-{
-	int i;
-	unsigned char error = 0;
-	int bad_count = 0;
-
-	pr_err("%03x: ", offset);
-	for (i = 0; i < limit; i++) {
-		if (data[offset + i] != POISON_FREE) {
-			error = data[offset + i];
-			bad_count++;
-		}
-	}
-	print_hex_dump(KERN_CONT, "", 0, 16, 1,
-			&data[offset], limit, 1);
-
-	if (bad_count == 1) {
-		error ^= POISON_FREE;
-		if (!(error & (error - 1))) {
-			pr_err("Single bit error detected. Probably bad RAM.\n");
-#ifdef CONFIG_X86
-			pr_err("Run memtest86+ or a similar memory test tool.\n");
-#else
-			pr_err("Run a memory test tool.\n");
-#endif
-		}
-	}
-}
-#endif
-
-#if DEBUG
-
-static void print_objinfo(struct kmem_cache *cachep, void *objp, int lines)
-{
-	int i, size;
-	char *realobj;
-
-	if (cachep->flags & SLAB_RED_ZONE) {
-		pr_err("Redzone: 0x%llx/0x%llx\n",
-		       *dbg_redzone1(cachep, objp),
-		       *dbg_redzone2(cachep, objp));
-	}
-
-	if (cachep->flags & SLAB_STORE_USER)
-		pr_err("Last user: (%pSR)\n", *dbg_userword(cachep, objp));
-	realobj = (char *)objp + obj_offset(cachep);
-	size = cachep->object_size;
-	for (i = 0; i < size && lines; i += 16, lines--) {
-		int limit;
-		limit = 16;
-		if (i + limit > size)
-			limit = size - i;
-		dump_line(realobj, i, limit);
-	}
-}
-
-static void check_poison_obj(struct kmem_cache *cachep, void *objp)
-{
-	char *realobj;
-	int size, i;
-	int lines = 0;
-
-	if (is_debug_pagealloc_cache(cachep))
-		return;
-
-	realobj = (char *)objp + obj_offset(cachep);
-	size = cachep->object_size;
-
-	for (i = 0; i < size; i++) {
-		char exp = POISON_FREE;
-		if (i == size - 1)
-			exp = POISON_END;
-		if (realobj[i] != exp) {
-			int limit;
-			/* Mismatch ! */
-			/* Print header */
-			if (lines == 0) {
-				pr_err("Slab corruption (%s): %s start=%px, len=%d\n",
-				       print_tainted(), cachep->name,
-				       realobj, size);
-				print_objinfo(cachep, objp, 0);
-			}
-			/* Hexdump the affected line */
-			i = (i / 16) * 16;
-			limit = 16;
-			if (i + limit > size)
-				limit = size - i;
-			dump_line(realobj, i, limit);
-			i += 16;
-			lines++;
-			/* Limit to 5 lines */
-			if (lines > 5)
-				break;
-		}
-	}
-	if (lines != 0) {
-		/* Print some data about the neighboring objects, if they
-		 * exist:
-		 */
-		struct slab *slab = virt_to_slab(objp);
-		unsigned int objnr;
-
-		objnr = obj_to_index(cachep, slab, objp);
-		if (objnr) {
-			objp = index_to_obj(cachep, slab, objnr - 1);
-			realobj = (char *)objp + obj_offset(cachep);
-			pr_err("Prev obj: start=%px, len=%d\n", realobj, size);
-			print_objinfo(cachep, objp, 2);
-		}
-		if (objnr + 1 < cachep->num) {
-			objp = index_to_obj(cachep, slab, objnr + 1);
-			realobj = (char *)objp + obj_offset(cachep);
-			pr_err("Next obj: start=%px, len=%d\n", realobj, size);
-			print_objinfo(cachep, objp, 2);
-		}
-	}
-}
-#endif
-
-#if DEBUG
-static void slab_destroy_debugcheck(struct kmem_cache *cachep,
-						struct slab *slab)
-{
-	int i;
-
-	if (OBJFREELIST_SLAB(cachep) && cachep->flags & SLAB_POISON) {
-		poison_obj(cachep, slab->freelist - obj_offset(cachep),
-			POISON_FREE);
-	}
-
-	for (i = 0; i < cachep->num; i++) {
-		void *objp = index_to_obj(cachep, slab, i);
-
-		if (cachep->flags & SLAB_POISON) {
-			check_poison_obj(cachep, objp);
-			slab_kernel_map(cachep, objp, 1);
-		}
-		if (cachep->flags & SLAB_RED_ZONE) {
-			if (*dbg_redzone1(cachep, objp) != RED_INACTIVE)
-				slab_error(cachep, "start of a freed object was overwritten");
-			if (*dbg_redzone2(cachep, objp) != RED_INACTIVE)
-				slab_error(cachep, "end of a freed object was overwritten");
-		}
-	}
-}
-#else
-static void slab_destroy_debugcheck(struct kmem_cache *cachep,
-						struct slab *slab)
-{
-}
-#endif
-
-/**
- * slab_destroy - destroy and release all objects in a slab
- * @cachep: cache pointer being destroyed
- * @slab: slab being destroyed
- *
- * Destroy all the objs in a slab, and release the mem back to the system.
- * Before calling the slab must have been unlinked from the cache. The
- * kmem_cache_node ->list_lock is not held/needed.
- */
-static void slab_destroy(struct kmem_cache *cachep, struct slab *slab)
-{
-	void *freelist;
-
-	freelist = slab->freelist;
-	slab_destroy_debugcheck(cachep, slab);
-	if (unlikely(cachep->flags & SLAB_TYPESAFE_BY_RCU))
-		call_rcu(&slab->rcu_head, kmem_rcu_free);
-	else
-		kmem_freepages(cachep, slab);
-
-	/*
-	 * From now on, we don't use freelist
-	 * although actual page can be freed in rcu context
-	 */
-	if (OFF_SLAB(cachep))
-		kfree(freelist);
-}
-
-/*
- * Update the size of the caches before calling slabs_destroy as it may
- * recursively call kfree.
- */
-static void slabs_destroy(struct kmem_cache *cachep, struct list_head *list)
-{
-	struct slab *slab, *n;
-
-	list_for_each_entry_safe(slab, n, list, slab_list) {
-		list_del(&slab->slab_list);
-		slab_destroy(cachep, slab);
-	}
-}
-
-/**
- * calculate_slab_order - calculate size (page order) of slabs
- * @cachep: pointer to the cache that is being created
- * @size: size of objects to be created in this cache.
- * @flags: slab allocation flags
- *
- * Also calculates the number of objects per slab.
- *
- * This could be made much more intelligent.  For now, try to avoid using
- * high order pages for slabs.  When the gfp() functions are more friendly
- * towards high-order requests, this should be changed.
- *
- * Return: number of left-over bytes in a slab
- */
-static size_t calculate_slab_order(struct kmem_cache *cachep,
-				size_t size, slab_flags_t flags)
-{
-	size_t left_over = 0;
-	int gfporder;
-
-	for (gfporder = 0; gfporder <= KMALLOC_MAX_ORDER; gfporder++) {
-		unsigned int num;
-		size_t remainder;
-
-		num = cache_estimate(gfporder, size, flags, &remainder);
-		if (!num)
-			continue;
-
-		/* Can't handle number of objects more than SLAB_OBJ_MAX_NUM */
-		if (num > SLAB_OBJ_MAX_NUM)
-			break;
-
-		if (flags & CFLGS_OFF_SLAB) {
-			struct kmem_cache *freelist_cache;
-			size_t freelist_size;
-			size_t freelist_cache_size;
-
-			freelist_size = num * sizeof(freelist_idx_t);
-			if (freelist_size > KMALLOC_MAX_CACHE_SIZE) {
-				freelist_cache_size = PAGE_SIZE << get_order(freelist_size);
-			} else {
-				freelist_cache = kmalloc_slab(freelist_size, 0u, _RET_IP_);
-				if (!freelist_cache)
-					continue;
-				freelist_cache_size = freelist_cache->size;
-
-				/*
-				 * Needed to avoid possible looping condition
-				 * in cache_grow_begin()
-				 */
-				if (OFF_SLAB(freelist_cache))
-					continue;
-			}
-
-			/* check if off slab has enough benefit */
-			if (freelist_cache_size > cachep->size / 2)
-				continue;
-		}
-
-		/* Found something acceptable - save it away */
-		cachep->num = num;
-		cachep->gfporder = gfporder;
-		left_over = remainder;
-
-		/*
-		 * A VFS-reclaimable slab tends to have most allocations
-		 * as GFP_NOFS and we really don't want to have to be allocating
-		 * higher-order pages when we are unable to shrink dcache.
-		 */
-		if (flags & SLAB_RECLAIM_ACCOUNT)
-			break;
-
-		/*
-		 * Large number of objects is good, but very large slabs are
-		 * currently bad for the gfp()s.
-		 */
-		if (gfporder >= slab_max_order)
-			break;
-
-		/*
-		 * Acceptable internal fragmentation?
-		 */
-		if (left_over * 8 <= (PAGE_SIZE << gfporder))
-			break;
-	}
-	return left_over;
-}
-
-static struct array_cache __percpu *alloc_kmem_cache_cpus(
-		struct kmem_cache *cachep, int entries, int batchcount)
-{
-	int cpu;
-	size_t size;
-	struct array_cache __percpu *cpu_cache;
-
-	size = sizeof(void *) * entries + sizeof(struct array_cache);
-	cpu_cache = __alloc_percpu(size, sizeof(void *));
-
-	if (!cpu_cache)
-		return NULL;
-
-	for_each_possible_cpu(cpu) {
-		init_arraycache(per_cpu_ptr(cpu_cache, cpu),
-				entries, batchcount);
-	}
-
-	return cpu_cache;
-}
-
-static int __ref setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
-{
-	if (slab_state >= FULL)
-		return enable_cpucache(cachep, gfp);
-
-	cachep->cpu_cache = alloc_kmem_cache_cpus(cachep, 1, 1);
-	if (!cachep->cpu_cache)
-		return 1;
-
-	if (slab_state == DOWN) {
-		/* Creation of first cache (kmem_cache). */
-		set_up_node(kmem_cache, CACHE_CACHE);
-	} else if (slab_state == PARTIAL) {
-		/* For kmem_cache_node */
-		set_up_node(cachep, SIZE_NODE);
-	} else {
-		int node;
-
-		for_each_online_node(node) {
-			cachep->node[node] = kmalloc_node(
-				sizeof(struct kmem_cache_node), gfp, node);
-			BUG_ON(!cachep->node[node]);
-			kmem_cache_node_init(cachep->node[node]);
-		}
-	}
-
-	cachep->node[numa_mem_id()]->next_reap =
-			jiffies + REAPTIMEOUT_NODE +
-			((unsigned long)cachep) % REAPTIMEOUT_NODE;
-
-	cpu_cache_get(cachep)->avail = 0;
-	cpu_cache_get(cachep)->limit = BOOT_CPUCACHE_ENTRIES;
-	cpu_cache_get(cachep)->batchcount = 1;
-	cpu_cache_get(cachep)->touched = 0;
-	cachep->batchcount = 1;
-	cachep->limit = BOOT_CPUCACHE_ENTRIES;
-	return 0;
-}
-
-slab_flags_t kmem_cache_flags(unsigned int object_size,
-	slab_flags_t flags, const char *name)
-{
-	return flags;
-}
-
-struct kmem_cache *
-__kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
-		   slab_flags_t flags, void (*ctor)(void *))
-{
-	struct kmem_cache *cachep;
-
-	cachep = find_mergeable(size, align, flags, name, ctor);
-	if (cachep) {
-		cachep->refcount++;
-
-		/*
-		 * Adjust the object sizes so that we clear
-		 * the complete object on kzalloc.
-		 */
-		cachep->object_size = max_t(int, cachep->object_size, size);
-	}
-	return cachep;
-}
-
-static bool set_objfreelist_slab_cache(struct kmem_cache *cachep,
-			size_t size, slab_flags_t flags)
-{
-	size_t left;
-
-	cachep->num = 0;
-
-	/*
-	 * If slab auto-initialization on free is enabled, store the freelist
-	 * off-slab, so that its contents don't end up in one of the allocated
-	 * objects.
-	 */
-	if (unlikely(slab_want_init_on_free(cachep)))
-		return false;
-
-	if (cachep->ctor || flags & SLAB_TYPESAFE_BY_RCU)
-		return false;
-
-	left = calculate_slab_order(cachep, size,
-			flags | CFLGS_OBJFREELIST_SLAB);
-	if (!cachep->num)
-		return false;
-
-	if (cachep->num * sizeof(freelist_idx_t) > cachep->object_size)
-		return false;
-
-	cachep->colour = left / cachep->colour_off;
-
-	return true;
-}
-
-static bool set_off_slab_cache(struct kmem_cache *cachep,
-			size_t size, slab_flags_t flags)
-{
-	size_t left;
-
-	cachep->num = 0;
-
-	/*
-	 * Always use on-slab management when SLAB_NOLEAKTRACE
-	 * to avoid recursive calls into kmemleak.
-	 */
-	if (flags & SLAB_NOLEAKTRACE)
-		return false;
-
-	/*
-	 * Size is large, assume best to place the slab management obj
-	 * off-slab (should allow better packing of objs).
-	 */
-	left = calculate_slab_order(cachep, size, flags | CFLGS_OFF_SLAB);
-	if (!cachep->num)
-		return false;
-
-	/*
-	 * If the slab has been placed off-slab, and we have enough space then
-	 * move it on-slab. This is at the expense of any extra colouring.
-	 */
-	if (left >= cachep->num * sizeof(freelist_idx_t))
-		return false;
-
-	cachep->colour = left / cachep->colour_off;
-
-	return true;
-}
-
-static bool set_on_slab_cache(struct kmem_cache *cachep,
-			size_t size, slab_flags_t flags)
-{
-	size_t left;
-
-	cachep->num = 0;
-
-	left = calculate_slab_order(cachep, size, flags);
-	if (!cachep->num)
-		return false;
-
-	cachep->colour = left / cachep->colour_off;
-
-	return true;
-}
-
-/*
- * __kmem_cache_create - Create a cache.
- * @cachep: cache management descriptor
- * @flags: SLAB flags
- *
- * Returns zero on success, nonzero on failure.
- *
- * The flags are
- *
- * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5)
- * to catch references to uninitialised memory.
- *
- * %SLAB_RED_ZONE - Insert `Red' zones around the allocated memory to check
- * for buffer overruns.
- *
- * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware
- * cacheline.  This can be beneficial if you're counting cycles as closely
- * as davem.
- */
-int __kmem_cache_create(struct kmem_cache *cachep, slab_flags_t flags)
-{
-	size_t ralign = BYTES_PER_WORD;
-	gfp_t gfp;
-	int err;
-	unsigned int size = cachep->size;
-
-#if DEBUG
-#if FORCED_DEBUG
-	/*
-	 * Enable redzoning and last user accounting, except for caches with
-	 * large objects, if the increased size would increase the object size
-	 * above the next power of two: caches with object sizes just above a
-	 * power of two have a significant amount of internal fragmentation.
-	 */
-	if (size < 4096 || fls(size - 1) == fls(size-1 + REDZONE_ALIGN +
-						2 * sizeof(unsigned long long)))
-		flags |= SLAB_RED_ZONE | SLAB_STORE_USER;
-	if (!(flags & SLAB_TYPESAFE_BY_RCU))
-		flags |= SLAB_POISON;
-#endif
-#endif
-
-	/*
-	 * Check that size is in terms of words.  This is needed to avoid
-	 * unaligned accesses for some archs when redzoning is used, and makes
-	 * sure any on-slab bufctl's are also correctly aligned.
-	 */
-	size = ALIGN(size, BYTES_PER_WORD);
-
-	if (flags & SLAB_RED_ZONE) {
-		ralign = REDZONE_ALIGN;
-		/* If redzoning, ensure that the second redzone is suitably
-		 * aligned, by adjusting the object size accordingly. */
-		size = ALIGN(size, REDZONE_ALIGN);
-	}
-
-	/* 3) caller mandated alignment */
-	if (ralign < cachep->align) {
-		ralign = cachep->align;
-	}
-	/* disable debug if necessary */
-	if (ralign > __alignof__(unsigned long long))
-		flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
-	/*
-	 * 4) Store it.
-	 */
-	cachep->align = ralign;
-	cachep->colour_off = cache_line_size();
-	/* Offset must be a multiple of the alignment. */
-	if (cachep->colour_off < cachep->align)
-		cachep->colour_off = cachep->align;
-
-	if (slab_is_available())
-		gfp = GFP_KERNEL;
-	else
-		gfp = GFP_NOWAIT;
-
-#if DEBUG
-
-	/*
-	 * Both debugging options require word-alignment which is calculated
-	 * into align above.
-	 */
-	if (flags & SLAB_RED_ZONE) {
-		/* add space for red zone words */
-		cachep->obj_offset += sizeof(unsigned long long);
-		size += 2 * sizeof(unsigned long long);
-	}
-	if (flags & SLAB_STORE_USER) {
-		/* user store requires one word storage behind the end of
-		 * the real object. But if the second red zone needs to be
-		 * aligned to 64 bits, we must allow that much space.
-		 */
-		if (flags & SLAB_RED_ZONE)
-			size += REDZONE_ALIGN;
-		else
-			size += BYTES_PER_WORD;
-	}
-#endif
-
-	kasan_cache_create(cachep, &size, &flags);
-
-	size = ALIGN(size, cachep->align);
-	/*
-	 * We should restrict the number of objects in a slab to implement
-	 * byte sized index. Refer comment on SLAB_OBJ_MIN_SIZE definition.
-	 */
-	if (FREELIST_BYTE_INDEX && size < SLAB_OBJ_MIN_SIZE)
-		size = ALIGN(SLAB_OBJ_MIN_SIZE, cachep->align);
-
-#if DEBUG
-	/*
-	 * To activate debug pagealloc, off-slab management is necessary
-	 * requirement. In early phase of initialization, small sized slab
-	 * doesn't get initialized so it would not be possible. So, we need
-	 * to check size >= 256. It guarantees that all necessary small
-	 * sized slab is initialized in current slab initialization sequence.
-	 */
-	if (debug_pagealloc_enabled_static() && (flags & SLAB_POISON) &&
-		size >= 256 && cachep->object_size > cache_line_size()) {
-		if (size < PAGE_SIZE || size % PAGE_SIZE == 0) {
-			size_t tmp_size = ALIGN(size, PAGE_SIZE);
-
-			if (set_off_slab_cache(cachep, tmp_size, flags)) {
-				flags |= CFLGS_OFF_SLAB;
-				cachep->obj_offset += tmp_size - size;
-				size = tmp_size;
-				goto done;
-			}
-		}
-	}
-#endif
-
-	if (set_objfreelist_slab_cache(cachep, size, flags)) {
-		flags |= CFLGS_OBJFREELIST_SLAB;
-		goto done;
-	}
-
-	if (set_off_slab_cache(cachep, size, flags)) {
-		flags |= CFLGS_OFF_SLAB;
-		goto done;
-	}
-
-	if (set_on_slab_cache(cachep, size, flags))
-		goto done;
-
-	return -E2BIG;
-
-done:
-	cachep->freelist_size = cachep->num * sizeof(freelist_idx_t);
-	cachep->flags = flags;
-	cachep->allocflags = __GFP_COMP;
-	if (flags & SLAB_CACHE_DMA)
-		cachep->allocflags |= GFP_DMA;
-	if (flags & SLAB_CACHE_DMA32)
-		cachep->allocflags |= GFP_DMA32;
-	if (flags & SLAB_RECLAIM_ACCOUNT)
-		cachep->allocflags |= __GFP_RECLAIMABLE;
-	cachep->size = size;
-	cachep->reciprocal_buffer_size = reciprocal_value(size);
-
-#if DEBUG
-	/*
-	 * If we're going to use the generic kernel_map_pages()
-	 * poisoning, then it's going to smash the contents of
-	 * the redzone and userword anyhow, so switch them off.
-	 */
-	if (IS_ENABLED(CONFIG_PAGE_POISONING) &&
-		(cachep->flags & SLAB_POISON) &&
-		is_debug_pagealloc_cache(cachep))
-		cachep->flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
-#endif
-
-	err = setup_cpu_cache(cachep, gfp);
-	if (err) {
-		__kmem_cache_release(cachep);
-		return err;
-	}
-
-	return 0;
-}
-
-#if DEBUG
-static void check_irq_off(void)
-{
-	BUG_ON(!irqs_disabled());
-}
-
-static void check_irq_on(void)
-{
-	BUG_ON(irqs_disabled());
-}
-
-static void check_mutex_acquired(void)
-{
-	BUG_ON(!mutex_is_locked(&slab_mutex));
-}
-
-static void check_spinlock_acquired(struct kmem_cache *cachep)
-{
-#ifdef CONFIG_SMP
-	check_irq_off();
-	assert_raw_spin_locked(&get_node(cachep, numa_mem_id())->list_lock);
-#endif
-}
-
-static void check_spinlock_acquired_node(struct kmem_cache *cachep, int node)
-{
-#ifdef CONFIG_SMP
-	check_irq_off();
-	assert_raw_spin_locked(&get_node(cachep, node)->list_lock);
-#endif
-}
-
-#else
-#define check_irq_off()	do { } while(0)
-#define check_irq_on()	do { } while(0)
-#define check_mutex_acquired()	do { } while(0)
-#define check_spinlock_acquired(x) do { } while(0)
-#define check_spinlock_acquired_node(x, y) do { } while(0)
-#endif
-
-static void drain_array_locked(struct kmem_cache *cachep, struct array_cache *ac,
-				int node, bool free_all, struct list_head *list)
-{
-	int tofree;
-
-	if (!ac || !ac->avail)
-		return;
-
-	tofree = free_all ? ac->avail : (ac->limit + 4) / 5;
-	if (tofree > ac->avail)
-		tofree = (ac->avail + 1) / 2;
-
-	free_block(cachep, ac->entry, tofree, node, list);
-	ac->avail -= tofree;
-	memmove(ac->entry, &(ac->entry[tofree]), sizeof(void *) * ac->avail);
-}
-
-static void do_drain(void *arg)
-{
-	struct kmem_cache *cachep = arg;
-	struct array_cache *ac;
-	int node = numa_mem_id();
-	struct kmem_cache_node *n;
-	LIST_HEAD(list);
-
-	check_irq_off();
-	ac = cpu_cache_get(cachep);
-	n = get_node(cachep, node);
-	raw_spin_lock(&n->list_lock);
-	free_block(cachep, ac->entry, ac->avail, node, &list);
-	raw_spin_unlock(&n->list_lock);
-	ac->avail = 0;
-	slabs_destroy(cachep, &list);
-}
-
-static void drain_cpu_caches(struct kmem_cache *cachep)
-{
-	struct kmem_cache_node *n;
-	int node;
-	LIST_HEAD(list);
-
-	on_each_cpu(do_drain, cachep, 1);
-	check_irq_on();
-	for_each_kmem_cache_node(cachep, node, n)
-		if (n->alien)
-			drain_alien_cache(cachep, n->alien);
-
-	for_each_kmem_cache_node(cachep, node, n) {
-		raw_spin_lock_irq(&n->list_lock);
-		drain_array_locked(cachep, n->shared, node, true, &list);
-		raw_spin_unlock_irq(&n->list_lock);
-
-		slabs_destroy(cachep, &list);
-	}
-}
-
-/*
- * Remove slabs from the list of free slabs.
- * Specify the number of slabs to drain in tofree.
- *
- * Returns the actual number of slabs released.
- */
-static int drain_freelist(struct kmem_cache *cache,
-			struct kmem_cache_node *n, int tofree)
-{
-	struct list_head *p;
-	int nr_freed;
-	struct slab *slab;
-
-	nr_freed = 0;
-	while (nr_freed < tofree && !list_empty(&n->slabs_free)) {
-
-		raw_spin_lock_irq(&n->list_lock);
-		p = n->slabs_free.prev;
-		if (p == &n->slabs_free) {
-			raw_spin_unlock_irq(&n->list_lock);
-			goto out;
-		}
-
-		slab = list_entry(p, struct slab, slab_list);
-		list_del(&slab->slab_list);
-		n->free_slabs--;
-		n->total_slabs--;
-		/*
-		 * Safe to drop the lock. The slab is no longer linked
-		 * to the cache.
-		 */
-		n->free_objects -= cache->num;
-		raw_spin_unlock_irq(&n->list_lock);
-		slab_destroy(cache, slab);
-		nr_freed++;
-
-		cond_resched();
-	}
-out:
-	return nr_freed;
-}
-
-bool __kmem_cache_empty(struct kmem_cache *s)
-{
-	int node;
-	struct kmem_cache_node *n;
-
-	for_each_kmem_cache_node(s, node, n)
-		if (!list_empty(&n->slabs_full) ||
-		    !list_empty(&n->slabs_partial))
-			return false;
-	return true;
-}
-
-int __kmem_cache_shrink(struct kmem_cache *cachep)
-{
-	int ret = 0;
-	int node;
-	struct kmem_cache_node *n;
-
-	drain_cpu_caches(cachep);
-
-	check_irq_on();
-	for_each_kmem_cache_node(cachep, node, n) {
-		drain_freelist(cachep, n, INT_MAX);
-
-		ret += !list_empty(&n->slabs_full) ||
-			!list_empty(&n->slabs_partial);
-	}
-	return (ret ? 1 : 0);
-}
-
-int __kmem_cache_shutdown(struct kmem_cache *cachep)
-{
-	return __kmem_cache_shrink(cachep);
-}
-
-void __kmem_cache_release(struct kmem_cache *cachep)
-{
-	int i;
-	struct kmem_cache_node *n;
-
-	cache_random_seq_destroy(cachep);
-
-	free_percpu(cachep->cpu_cache);
-
-	/* NUMA: free the node structures */
-	for_each_kmem_cache_node(cachep, i, n) {
-		kfree(n->shared);
-		free_alien_cache(n->alien);
-		kfree(n);
-		cachep->node[i] = NULL;
-	}
-}
-
-/*
- * Get the memory for a slab management obj.
- *
- * For a slab cache when the slab descriptor is off-slab, the
- * slab descriptor can't come from the same cache which is being created,
- * Because if it is the case, that means we defer the creation of
- * the kmalloc_{dma,}_cache of size sizeof(slab descriptor) to this point.
- * And we eventually call down to __kmem_cache_create(), which
- * in turn looks up in the kmalloc_{dma,}_caches for the desired-size one.
- * This is a "chicken-and-egg" problem.
- *
- * So the off-slab slab descriptor shall come from the kmalloc_{dma,}_caches,
- * which are all initialized during kmem_cache_init().
- */
-static void *alloc_slabmgmt(struct kmem_cache *cachep,
-				   struct slab *slab, int colour_off,
-				   gfp_t local_flags, int nodeid)
-{
-	void *freelist;
-	void *addr = slab_address(slab);
-
-	slab->s_mem = addr + colour_off;
-	slab->active = 0;
-
-	if (OBJFREELIST_SLAB(cachep))
-		freelist = NULL;
-	else if (OFF_SLAB(cachep)) {
-		/* Slab management obj is off-slab. */
-		freelist = kmalloc_node(cachep->freelist_size,
-					      local_flags, nodeid);
-	} else {
-		/* We will use last bytes at the slab for freelist */
-		freelist = addr + (PAGE_SIZE << cachep->gfporder) -
-				cachep->freelist_size;
-	}
-
-	return freelist;
-}
-
-static inline freelist_idx_t get_free_obj(struct slab *slab, unsigned int idx)
-{
-	return ((freelist_idx_t *) slab->freelist)[idx];
-}
-
-static inline void set_free_obj(struct slab *slab,
-					unsigned int idx, freelist_idx_t val)
-{
-	((freelist_idx_t *)(slab->freelist))[idx] = val;
-}
-
-static void cache_init_objs_debug(struct kmem_cache *cachep, struct slab *slab)
-{
-#if DEBUG
-	int i;
-
-	for (i = 0; i < cachep->num; i++) {
-		void *objp = index_to_obj(cachep, slab, i);
-
-		if (cachep->flags & SLAB_STORE_USER)
-			*dbg_userword(cachep, objp) = NULL;
-
-		if (cachep->flags & SLAB_RED_ZONE) {
-			*dbg_redzone1(cachep, objp) = RED_INACTIVE;
-			*dbg_redzone2(cachep, objp) = RED_INACTIVE;
-		}
-		/*
-		 * Constructors are not allowed to allocate memory from the same
-		 * cache which they are a constructor for.  Otherwise, deadlock.
-		 * They must also be threaded.
-		 */
-		if (cachep->ctor && !(cachep->flags & SLAB_POISON)) {
-			kasan_unpoison_object_data(cachep,
-						   objp + obj_offset(cachep));
-			cachep->ctor(objp + obj_offset(cachep));
-			kasan_poison_object_data(
-				cachep, objp + obj_offset(cachep));
-		}
-
-		if (cachep->flags & SLAB_RED_ZONE) {
-			if (*dbg_redzone2(cachep, objp) != RED_INACTIVE)
-				slab_error(cachep, "constructor overwrote the end of an object");
-			if (*dbg_redzone1(cachep, objp) != RED_INACTIVE)
-				slab_error(cachep, "constructor overwrote the start of an object");
-		}
-		/* need to poison the objs? */
-		if (cachep->flags & SLAB_POISON) {
-			poison_obj(cachep, objp, POISON_FREE);
-			slab_kernel_map(cachep, objp, 0);
-		}
-	}
-#endif
-}
-
-#ifdef CONFIG_SLAB_FREELIST_RANDOM
-/* Hold information during a freelist initialization */
-struct freelist_init_state {
-	unsigned int pos;
-	unsigned int *list;
-	unsigned int count;
-};
-
-/*
- * Initialize the state based on the randomization method available.
- * return true if the pre-computed list is available, false otherwise.
- */
-static bool freelist_state_initialize(struct freelist_init_state *state,
-				struct kmem_cache *cachep,
-				unsigned int count)
-{
-	bool ret;
-	if (!cachep->random_seq) {
-		ret = false;
-	} else {
-		state->list = cachep->random_seq;
-		state->count = count;
-		state->pos = get_random_u32_below(count);
-		ret = true;
-	}
-	return ret;
-}
-
-/* Get the next entry on the list and randomize it using a random shift */
-static freelist_idx_t next_random_slot(struct freelist_init_state *state)
-{
-	if (state->pos >= state->count)
-		state->pos = 0;
-	return state->list[state->pos++];
-}
-
-/* Swap two freelist entries */
-static void swap_free_obj(struct slab *slab, unsigned int a, unsigned int b)
-{
-	swap(((freelist_idx_t *) slab->freelist)[a],
-		((freelist_idx_t *) slab->freelist)[b]);
-}
-
-/*
- * Shuffle the freelist initialization state based on pre-computed lists.
- * return true if the list was successfully shuffled, false otherwise.
- */
-static bool shuffle_freelist(struct kmem_cache *cachep, struct slab *slab)
-{
-	unsigned int objfreelist = 0, i, rand, count = cachep->num;
-	struct freelist_init_state state;
-	bool precomputed;
-
-	if (count < 2)
-		return false;
-
-	precomputed = freelist_state_initialize(&state, cachep, count);
-
-	/* Take a random entry as the objfreelist */
-	if (OBJFREELIST_SLAB(cachep)) {
-		if (!precomputed)
-			objfreelist = count - 1;
-		else
-			objfreelist = next_random_slot(&state);
-		slab->freelist = index_to_obj(cachep, slab, objfreelist) +
-						obj_offset(cachep);
-		count--;
-	}
-
-	/*
-	 * On early boot, generate the list dynamically.
-	 * Later use a pre-computed list for speed.
-	 */
-	if (!precomputed) {
-		for (i = 0; i < count; i++)
-			set_free_obj(slab, i, i);
-
-		/* Fisher-Yates shuffle */
-		for (i = count - 1; i > 0; i--) {
-			rand = get_random_u32_below(i + 1);
-			swap_free_obj(slab, i, rand);
-		}
-	} else {
-		for (i = 0; i < count; i++)
-			set_free_obj(slab, i, next_random_slot(&state));
-	}
-
-	if (OBJFREELIST_SLAB(cachep))
-		set_free_obj(slab, cachep->num - 1, objfreelist);
-
-	return true;
-}
-#else
-static inline bool shuffle_freelist(struct kmem_cache *cachep,
-				struct slab *slab)
-{
-	return false;
-}
-#endif /* CONFIG_SLAB_FREELIST_RANDOM */
-
-static void cache_init_objs(struct kmem_cache *cachep,
-			    struct slab *slab)
-{
-	int i;
-	void *objp;
-	bool shuffled;
-
-	cache_init_objs_debug(cachep, slab);
-
-	/* Try to randomize the freelist if enabled */
-	shuffled = shuffle_freelist(cachep, slab);
-
-	if (!shuffled && OBJFREELIST_SLAB(cachep)) {
-		slab->freelist = index_to_obj(cachep, slab, cachep->num - 1) +
-						obj_offset(cachep);
-	}
-
-	for (i = 0; i < cachep->num; i++) {
-		objp = index_to_obj(cachep, slab, i);
-		objp = kasan_init_slab_obj(cachep, objp);
-
-		/* constructor could break poison info */
-		if (DEBUG == 0 && cachep->ctor) {
-			kasan_unpoison_object_data(cachep, objp);
-			cachep->ctor(objp);
-			kasan_poison_object_data(cachep, objp);
-		}
-
-		if (!shuffled)
-			set_free_obj(slab, i, i);
-	}
-}
-
-static void *slab_get_obj(struct kmem_cache *cachep, struct slab *slab)
-{
-	void *objp;
-
-	objp = index_to_obj(cachep, slab, get_free_obj(slab, slab->active));
-	slab->active++;
-
-	return objp;
-}
-
-static void slab_put_obj(struct kmem_cache *cachep,
-			struct slab *slab, void *objp)
-{
-	unsigned int objnr = obj_to_index(cachep, slab, objp);
-#if DEBUG
-	unsigned int i;
-
-	/* Verify double free bug */
-	for (i = slab->active; i < cachep->num; i++) {
-		if (get_free_obj(slab, i) == objnr) {
-			pr_err("slab: double free detected in cache '%s', objp %px\n",
-			       cachep->name, objp);
-			BUG();
-		}
-	}
-#endif
-	slab->active--;
-	if (!slab->freelist)
-		slab->freelist = objp + obj_offset(cachep);
-
-	set_free_obj(slab, slab->active, objnr);
-}
-
-/*
- * Grow (by 1) the number of slabs within a cache.  This is called by
- * kmem_cache_alloc() when there are no active objs left in a cache.
- */
-static struct slab *cache_grow_begin(struct kmem_cache *cachep,
-				gfp_t flags, int nodeid)
-{
-	void *freelist;
-	size_t offset;
-	gfp_t local_flags;
-	int slab_node;
-	struct kmem_cache_node *n;
-	struct slab *slab;
-
-	/*
-	 * Be lazy and only check for valid flags here,  keeping it out of the
-	 * critical path in kmem_cache_alloc().
-	 */
-	if (unlikely(flags & GFP_SLAB_BUG_MASK))
-		flags = kmalloc_fix_flags(flags);
-
-	WARN_ON_ONCE(cachep->ctor && (flags & __GFP_ZERO));
-	local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);
-
-	check_irq_off();
-	if (gfpflags_allow_blocking(local_flags))
-		local_irq_enable();
-
-	/*
-	 * Get mem for the objs.  Attempt to allocate a physical page from
-	 * 'nodeid'.
-	 */
-	slab = kmem_getpages(cachep, local_flags, nodeid);
-	if (!slab)
-		goto failed;
-
-	slab_node = slab_nid(slab);
-	n = get_node(cachep, slab_node);
-
-	/* Get colour for the slab, and cal the next value. */
-	n->colour_next++;
-	if (n->colour_next >= cachep->colour)
-		n->colour_next = 0;
-
-	offset = n->colour_next;
-	if (offset >= cachep->colour)
-		offset = 0;
-
-	offset *= cachep->colour_off;
-
-	/*
-	 * Call kasan_poison_slab() before calling alloc_slabmgmt(), so
-	 * page_address() in the latter returns a non-tagged pointer,
-	 * as it should be for slab pages.
-	 */
-	kasan_poison_slab(slab);
-
-	/* Get slab management. */
-	freelist = alloc_slabmgmt(cachep, slab, offset,
-			local_flags & ~GFP_CONSTRAINT_MASK, slab_node);
-	if (OFF_SLAB(cachep) && !freelist)
-		goto opps1;
-
-	slab->slab_cache = cachep;
-	slab->freelist = freelist;
-
-	cache_init_objs(cachep, slab);
-
-	if (gfpflags_allow_blocking(local_flags))
-		local_irq_disable();
-
-	return slab;
-
-opps1:
-	kmem_freepages(cachep, slab);
-failed:
-	if (gfpflags_allow_blocking(local_flags))
-		local_irq_disable();
-	return NULL;
-}
-
-static void cache_grow_end(struct kmem_cache *cachep, struct slab *slab)
-{
-	struct kmem_cache_node *n;
-	void *list = NULL;
-
-	check_irq_off();
-
-	if (!slab)
-		return;
-
-	INIT_LIST_HEAD(&slab->slab_list);
-	n = get_node(cachep, slab_nid(slab));
-
-	raw_spin_lock(&n->list_lock);
-	n->total_slabs++;
-	if (!slab->active) {
-		list_add_tail(&slab->slab_list, &n->slabs_free);
-		n->free_slabs++;
-	} else
-		fixup_slab_list(cachep, n, slab, &list);
-
-	STATS_INC_GROWN(cachep);
-	n->free_objects += cachep->num - slab->active;
-	raw_spin_unlock(&n->list_lock);
-
-	fixup_objfreelist_debug(cachep, &list);
-}
-
-#if DEBUG
-
-/*
- * Perform extra freeing checks:
- * - detect bad pointers.
- * - POISON/RED_ZONE checking
- */
-static void kfree_debugcheck(const void *objp)
-{
-	if (!virt_addr_valid(objp)) {
-		pr_err("kfree_debugcheck: out of range ptr %lxh\n",
-		       (unsigned long)objp);
-		BUG();
-	}
-}
-
-static inline void verify_redzone_free(struct kmem_cache *cache, void *obj)
-{
-	unsigned long long redzone1, redzone2;
-
-	redzone1 = *dbg_redzone1(cache, obj);
-	redzone2 = *dbg_redzone2(cache, obj);
-
-	/*
-	 * Redzone is ok.
-	 */
-	if (redzone1 == RED_ACTIVE && redzone2 == RED_ACTIVE)
-		return;
-
-	if (redzone1 == RED_INACTIVE && redzone2 == RED_INACTIVE)
-		slab_error(cache, "double free detected");
-	else
-		slab_error(cache, "memory outside object was overwritten");
-
-	pr_err("%px: redzone 1:0x%llx, redzone 2:0x%llx\n",
-	       obj, redzone1, redzone2);
-}
-
-static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
-				   unsigned long caller)
-{
-	unsigned int objnr;
-	struct slab *slab;
-
-	BUG_ON(virt_to_cache(objp) != cachep);
-
-	objp -= obj_offset(cachep);
-	kfree_debugcheck(objp);
-	slab = virt_to_slab(objp);
-
-	if (cachep->flags & SLAB_RED_ZONE) {
-		verify_redzone_free(cachep, objp);
-		*dbg_redzone1(cachep, objp) = RED_INACTIVE;
-		*dbg_redzone2(cachep, objp) = RED_INACTIVE;
-	}
-	if (cachep->flags & SLAB_STORE_USER)
-		*dbg_userword(cachep, objp) = (void *)caller;
-
-	objnr = obj_to_index(cachep, slab, objp);
-
-	BUG_ON(objnr >= cachep->num);
-	BUG_ON(objp != index_to_obj(cachep, slab, objnr));
-
-	if (cachep->flags & SLAB_POISON) {
-		poison_obj(cachep, objp, POISON_FREE);
-		slab_kernel_map(cachep, objp, 0);
-	}
-	return objp;
-}
-
-#else
-#define kfree_debugcheck(x) do { } while(0)
-#define cache_free_debugcheck(x, objp, z) (objp)
-#endif
-
-static inline void fixup_objfreelist_debug(struct kmem_cache *cachep,
-						void **list)
-{
-#if DEBUG
-	void *next = *list;
-	void *objp;
-
-	while (next) {
-		objp = next - obj_offset(cachep);
-		next = *(void **)next;
-		poison_obj(cachep, objp, POISON_FREE);
-	}
-#endif
-}
-
-static inline void fixup_slab_list(struct kmem_cache *cachep,
-				struct kmem_cache_node *n, struct slab *slab,
-				void **list)
-{
-	/* move slabp to correct slabp list: */
-	list_del(&slab->slab_list);
-	if (slab->active == cachep->num) {
-		list_add(&slab->slab_list, &n->slabs_full);
-		if (OBJFREELIST_SLAB(cachep)) {
-#if DEBUG
-			/* Poisoning will be done without holding the lock */
-			if (cachep->flags & SLAB_POISON) {
-				void **objp = slab->freelist;
-
-				*objp = *list;
-				*list = objp;
-			}
-#endif
-			slab->freelist = NULL;
-		}
-	} else
-		list_add(&slab->slab_list, &n->slabs_partial);
-}
-
-/* Try to find non-pfmemalloc slab if needed */
-static noinline struct slab *get_valid_first_slab(struct kmem_cache_node *n,
-					struct slab *slab, bool pfmemalloc)
-{
-	if (!slab)
-		return NULL;
-
-	if (pfmemalloc)
-		return slab;
-
-	if (!slab_test_pfmemalloc(slab))
-		return slab;
-
-	/* No need to keep pfmemalloc slab if we have enough free objects */
-	if (n->free_objects > n->free_limit) {
-		slab_clear_pfmemalloc(slab);
-		return slab;
-	}
-
-	/* Move pfmemalloc slab to the end of list to speed up next search */
-	list_del(&slab->slab_list);
-	if (!slab->active) {
-		list_add_tail(&slab->slab_list, &n->slabs_free);
-		n->free_slabs++;
-	} else
-		list_add_tail(&slab->slab_list, &n->slabs_partial);
-
-	list_for_each_entry(slab, &n->slabs_partial, slab_list) {
-		if (!slab_test_pfmemalloc(slab))
-			return slab;
-	}
-
-	n->free_touched = 1;
-	list_for_each_entry(slab, &n->slabs_free, slab_list) {
-		if (!slab_test_pfmemalloc(slab)) {
-			n->free_slabs--;
-			return slab;
-		}
-	}
-
-	return NULL;
-}
-
-static struct slab *get_first_slab(struct kmem_cache_node *n, bool pfmemalloc)
-{
-	struct slab *slab;
-
-	assert_raw_spin_locked(&n->list_lock);
-	slab = list_first_entry_or_null(&n->slabs_partial, struct slab,
-					slab_list);
-	if (!slab) {
-		n->free_touched = 1;
-		slab = list_first_entry_or_null(&n->slabs_free, struct slab,
-						slab_list);
-		if (slab)
-			n->free_slabs--;
-	}
-
-	if (sk_memalloc_socks())
-		slab = get_valid_first_slab(n, slab, pfmemalloc);
-
-	return slab;
-}
-
-static noinline void *cache_alloc_pfmemalloc(struct kmem_cache *cachep,
-				struct kmem_cache_node *n, gfp_t flags)
-{
-	struct slab *slab;
-	void *obj;
-	void *list = NULL;
-
-	if (!gfp_pfmemalloc_allowed(flags))
-		return NULL;
-
-	raw_spin_lock(&n->list_lock);
-	slab = get_first_slab(n, true);
-	if (!slab) {
-		raw_spin_unlock(&n->list_lock);
-		return NULL;
-	}
-
-	obj = slab_get_obj(cachep, slab);
-	n->free_objects--;
-
-	fixup_slab_list(cachep, n, slab, &list);
-
-	raw_spin_unlock(&n->list_lock);
-	fixup_objfreelist_debug(cachep, &list);
-
-	return obj;
-}
-
-/*
- * Slab list should be fixed up by fixup_slab_list() for existing slab
- * or cache_grow_end() for new slab
- */
-static __always_inline int alloc_block(struct kmem_cache *cachep,
-		struct array_cache *ac, struct slab *slab, int batchcount)
-{
-	/*
-	 * There must be at least one object available for
-	 * allocation.
-	 */
-	BUG_ON(slab->active >= cachep->num);
-
-	while (slab->active < cachep->num && batchcount--) {
-		STATS_INC_ALLOCED(cachep);
-		STATS_INC_ACTIVE(cachep);
-		STATS_SET_HIGH(cachep);
-
-		ac->entry[ac->avail++] = slab_get_obj(cachep, slab);
-	}
-
-	return batchcount;
-}
-
-static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags)
-{
-	int batchcount;
-	struct kmem_cache_node *n;
-	struct array_cache *ac, *shared;
-	int node;
-	void *list = NULL;
-	struct slab *slab;
-
-	check_irq_off();
-	node = numa_mem_id();
-
-	ac = cpu_cache_get(cachep);
-	batchcount = ac->batchcount;
-	if (!ac->touched && batchcount > BATCHREFILL_LIMIT) {
-		/*
-		 * If there was little recent activity on this cache, then
-		 * perform only a partial refill.  Otherwise we could generate
-		 * refill bouncing.
-		 */
-		batchcount = BATCHREFILL_LIMIT;
-	}
-	n = get_node(cachep, node);
-
-	BUG_ON(ac->avail > 0 || !n);
-	shared = READ_ONCE(n->shared);
-	if (!n->free_objects && (!shared || !shared->avail))
-		goto direct_grow;
-
-	raw_spin_lock(&n->list_lock);
-	shared = READ_ONCE(n->shared);
-
-	/* See if we can refill from the shared array */
-	if (shared && transfer_objects(ac, shared, batchcount)) {
-		shared->touched = 1;
-		goto alloc_done;
-	}
-
-	while (batchcount > 0) {
-		/* Get slab alloc is to come from. */
-		slab = get_first_slab(n, false);
-		if (!slab)
-			goto must_grow;
-
-		check_spinlock_acquired(cachep);
-
-		batchcount = alloc_block(cachep, ac, slab, batchcount);
-		fixup_slab_list(cachep, n, slab, &list);
-	}
-
-must_grow:
-	n->free_objects -= ac->avail;
-alloc_done:
-	raw_spin_unlock(&n->list_lock);
-	fixup_objfreelist_debug(cachep, &list);
-
-direct_grow:
-	if (unlikely(!ac->avail)) {
-		/* Check if we can use obj in pfmemalloc slab */
-		if (sk_memalloc_socks()) {
-			void *obj = cache_alloc_pfmemalloc(cachep, n, flags);
-
-			if (obj)
-				return obj;
-		}
-
-		slab = cache_grow_begin(cachep, gfp_exact_node(flags), node);
-
-		/*
-		 * cache_grow_begin() can reenable interrupts,
-		 * then ac could change.
-		 */
-		ac = cpu_cache_get(cachep);
-		if (!ac->avail && slab)
-			alloc_block(cachep, ac, slab, batchcount);
-		cache_grow_end(cachep, slab);
-
-		if (!ac->avail)
-			return NULL;
-	}
-	ac->touched = 1;
-
-	return ac->entry[--ac->avail];
-}
-
-#if DEBUG
-static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
-				gfp_t flags, void *objp, unsigned long caller)
-{
-	WARN_ON_ONCE(cachep->ctor && (flags & __GFP_ZERO));
-	if (!objp || is_kfence_address(objp))
-		return objp;
-	if (cachep->flags & SLAB_POISON) {
-		check_poison_obj(cachep, objp);
-		slab_kernel_map(cachep, objp, 1);
-		poison_obj(cachep, objp, POISON_INUSE);
-	}
-	if (cachep->flags & SLAB_STORE_USER)
-		*dbg_userword(cachep, objp) = (void *)caller;
-
-	if (cachep->flags & SLAB_RED_ZONE) {
-		if (*dbg_redzone1(cachep, objp) != RED_INACTIVE ||
-				*dbg_redzone2(cachep, objp) != RED_INACTIVE) {
-			slab_error(cachep, "double free, or memory outside object was overwritten");
-			pr_err("%px: redzone 1:0x%llx, redzone 2:0x%llx\n",
-			       objp, *dbg_redzone1(cachep, objp),
-			       *dbg_redzone2(cachep, objp));
-		}
-		*dbg_redzone1(cachep, objp) = RED_ACTIVE;
-		*dbg_redzone2(cachep, objp) = RED_ACTIVE;
-	}
-
-	objp += obj_offset(cachep);
-	if (cachep->ctor && cachep->flags & SLAB_POISON)
-		cachep->ctor(objp);
-	if ((unsigned long)objp & (arch_slab_minalign() - 1)) {
-		pr_err("0x%px: not aligned to arch_slab_minalign()=%u\n", objp,
-		       arch_slab_minalign());
-	}
-	return objp;
-}
-#else
-#define cache_alloc_debugcheck_after(a, b, objp, d) (objp)
-#endif
-
-static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
-{
-	void *objp;
-	struct array_cache *ac;
-
-	check_irq_off();
-
-	ac = cpu_cache_get(cachep);
-	if (likely(ac->avail)) {
-		ac->touched = 1;
-		objp = ac->entry[--ac->avail];
-
-		STATS_INC_ALLOCHIT(cachep);
-		goto out;
-	}
-
-	STATS_INC_ALLOCMISS(cachep);
-	objp = cache_alloc_refill(cachep, flags);
-	/*
-	 * the 'ac' may be updated by cache_alloc_refill(),
-	 * and kmemleak_erase() requires its correct value.
-	 */
-	ac = cpu_cache_get(cachep);
-
-out:
-	/*
-	 * To avoid a false negative, if an object that is in one of the
-	 * per-CPU caches is leaked, we need to make sure kmemleak doesn't
-	 * treat the array pointers as a reference to the object.
-	 */
-	if (objp)
-		kmemleak_erase(&ac->entry[ac->avail]);
-	return objp;
-}
-
-#ifdef CONFIG_NUMA
-static void *____cache_alloc_node(struct kmem_cache *, gfp_t, int);
-
-/*
- * Try allocating on another node if PFA_SPREAD_SLAB is a mempolicy is set.
- *
- * If we are in_interrupt, then process context, including cpusets and
- * mempolicy, may not apply and should not be used for allocation policy.
- */
-static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
-{
-	int nid_alloc, nid_here;
-
-	if (in_interrupt() || (flags & __GFP_THISNODE))
-		return NULL;
-	nid_alloc = nid_here = numa_mem_id();
-	if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
-		nid_alloc = cpuset_slab_spread_node();
-	else if (current->mempolicy)
-		nid_alloc = mempolicy_slab_node();
-	if (nid_alloc != nid_here)
-		return ____cache_alloc_node(cachep, flags, nid_alloc);
-	return NULL;
-}
-
-/*
- * Fallback function if there was no memory available and no objects on a
- * certain node and fall back is permitted. First we scan all the
- * available node for available objects. If that fails then we
- * perform an allocation without specifying a node. This allows the page
- * allocator to do its reclaim / fallback magic. We then insert the
- * slab into the proper nodelist and then allocate from it.
- */
-static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
-{
-	struct zonelist *zonelist;
-	struct zoneref *z;
-	struct zone *zone;
-	enum zone_type highest_zoneidx = gfp_zone(flags);
-	void *obj = NULL;
-	struct slab *slab;
-	int nid;
-	unsigned int cpuset_mems_cookie;
-
-	if (flags & __GFP_THISNODE)
-		return NULL;
-
-retry_cpuset:
-	cpuset_mems_cookie = read_mems_allowed_begin();
-	zonelist = node_zonelist(mempolicy_slab_node(), flags);
-
-retry:
-	/*
-	 * Look through allowed nodes for objects available
-	 * from existing per node queues.
-	 */
-	for_each_zone_zonelist(zone, z, zonelist, highest_zoneidx) {
-		nid = zone_to_nid(zone);
-
-		if (cpuset_zone_allowed(zone, flags) &&
-			get_node(cache, nid) &&
-			get_node(cache, nid)->free_objects) {
-				obj = ____cache_alloc_node(cache,
-					gfp_exact_node(flags), nid);
-				if (obj)
-					break;
-		}
-	}
-
-	if (!obj) {
-		/*
-		 * This allocation will be performed within the constraints
-		 * of the current cpuset / memory policy requirements.
-		 * We may trigger various forms of reclaim on the allowed
-		 * set and go into memory reserves if necessary.
-		 */
-		slab = cache_grow_begin(cache, flags, numa_mem_id());
-		cache_grow_end(cache, slab);
-		if (slab) {
-			nid = slab_nid(slab);
-			obj = ____cache_alloc_node(cache,
-				gfp_exact_node(flags), nid);
-
-			/*
-			 * Another processor may allocate the objects in
-			 * the slab since we are not holding any locks.
-			 */
-			if (!obj)
-				goto retry;
-		}
-	}
-
-	if (unlikely(!obj && read_mems_allowed_retry(cpuset_mems_cookie)))
-		goto retry_cpuset;
-	return obj;
-}
-
-/*
- * An interface to enable slab creation on nodeid
- */
-static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
-				int nodeid)
-{
-	struct slab *slab;
-	struct kmem_cache_node *n;
-	void *obj = NULL;
-	void *list = NULL;
-
-	VM_BUG_ON(nodeid < 0 || nodeid >= MAX_NUMNODES);
-	n = get_node(cachep, nodeid);
-	BUG_ON(!n);
-
-	check_irq_off();
-	raw_spin_lock(&n->list_lock);
-	slab = get_first_slab(n, false);
-	if (!slab)
-		goto must_grow;
-
-	check_spinlock_acquired_node(cachep, nodeid);
-
-	STATS_INC_NODEALLOCS(cachep);
-	STATS_INC_ACTIVE(cachep);
-	STATS_SET_HIGH(cachep);
-
-	BUG_ON(slab->active == cachep->num);
-
-	obj = slab_get_obj(cachep, slab);
-	n->free_objects--;
-
-	fixup_slab_list(cachep, n, slab, &list);
-
-	raw_spin_unlock(&n->list_lock);
-	fixup_objfreelist_debug(cachep, &list);
-	return obj;
-
-must_grow:
-	raw_spin_unlock(&n->list_lock);
-	slab = cache_grow_begin(cachep, gfp_exact_node(flags), nodeid);
-	if (slab) {
-		/* This slab isn't counted yet so don't update free_objects */
-		obj = slab_get_obj(cachep, slab);
-	}
-	cache_grow_end(cachep, slab);
-
-	return obj ? obj : fallback_alloc(cachep, flags);
-}
-
-static __always_inline void *
-__do_cache_alloc(struct kmem_cache *cachep, gfp_t flags, int nodeid)
-{
-	void *objp = NULL;
-	int slab_node = numa_mem_id();
-
-	if (nodeid == NUMA_NO_NODE) {
-		if (current->mempolicy || cpuset_do_slab_mem_spread()) {
-			objp = alternate_node_alloc(cachep, flags);
-			if (objp)
-				goto out;
-		}
-		/*
-		 * Use the locally cached objects if possible.
-		 * However ____cache_alloc does not allow fallback
-		 * to other nodes. It may fail while we still have
-		 * objects on other nodes available.
-		 */
-		objp = ____cache_alloc(cachep, flags);
-		nodeid = slab_node;
-	} else if (nodeid == slab_node) {
-		objp = ____cache_alloc(cachep, flags);
-	} else if (!get_node(cachep, nodeid)) {
-		/* Node not bootstrapped yet */
-		objp = fallback_alloc(cachep, flags);
-		goto out;
-	}
-
-	/*
-	 * We may just have run out of memory on the local node.
-	 * ____cache_alloc_node() knows how to locate memory on other nodes
-	 */
-	if (!objp)
-		objp = ____cache_alloc_node(cachep, flags, nodeid);
-out:
-	return objp;
-}
-#else
-
-static __always_inline void *
-__do_cache_alloc(struct kmem_cache *cachep, gfp_t flags, int nodeid __maybe_unused)
-{
-	return ____cache_alloc(cachep, flags);
-}
-
-#endif /* CONFIG_NUMA */
-
-static __always_inline void *
-slab_alloc_node(struct kmem_cache *cachep, struct list_lru *lru, gfp_t flags,
-		int nodeid, size_t orig_size, unsigned long caller)
-{
-	unsigned long save_flags;
-	void *objp;
-	struct obj_cgroup *objcg = NULL;
-	bool init = false;
-
-	flags &= gfp_allowed_mask;
-	cachep = slab_pre_alloc_hook(cachep, lru, &objcg, 1, flags);
-	if (unlikely(!cachep))
-		return NULL;
-
-	objp = kfence_alloc(cachep, orig_size, flags);
-	if (unlikely(objp))
-		goto out;
-
-	local_irq_save(save_flags);
-	objp = __do_cache_alloc(cachep, flags, nodeid);
-	local_irq_restore(save_flags);
-	objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller);
-	prefetchw(objp);
-	init = slab_want_init_on_alloc(flags, cachep);
-
-out:
-	slab_post_alloc_hook(cachep, objcg, flags, 1, &objp, init,
-				cachep->object_size);
-	return objp;
-}
-
-static __always_inline void *
-slab_alloc(struct kmem_cache *cachep, struct list_lru *lru, gfp_t flags,
-	   size_t orig_size, unsigned long caller)
-{
-	return slab_alloc_node(cachep, lru, flags, NUMA_NO_NODE, orig_size,
-			       caller);
-}
-
-/*
- * Caller needs to acquire correct kmem_cache_node's list_lock
- * @list: List of detached free slabs should be freed by caller
- */
-static void free_block(struct kmem_cache *cachep, void **objpp,
-			int nr_objects, int node, struct list_head *list)
-{
-	int i;
-	struct kmem_cache_node *n = get_node(cachep, node);
-	struct slab *slab;
-
-	n->free_objects += nr_objects;
-
-	for (i = 0; i < nr_objects; i++) {
-		void *objp;
-		struct slab *slab;
-
-		objp = objpp[i];
-
-		slab = virt_to_slab(objp);
-		list_del(&slab->slab_list);
-		check_spinlock_acquired_node(cachep, node);
-		slab_put_obj(cachep, slab, objp);
-		STATS_DEC_ACTIVE(cachep);
-
-		/* fixup slab chains */
-		if (slab->active == 0) {
-			list_add(&slab->slab_list, &n->slabs_free);
-			n->free_slabs++;
-		} else {
-			/* Unconditionally move a slab to the end of the
-			 * partial list on free - maximum time for the
-			 * other objects to be freed, too.
-			 */
-			list_add_tail(&slab->slab_list, &n->slabs_partial);
-		}
-	}
-
-	while (n->free_objects > n->free_limit && !list_empty(&n->slabs_free)) {
-		n->free_objects -= cachep->num;
-
-		slab = list_last_entry(&n->slabs_free, struct slab, slab_list);
-		list_move(&slab->slab_list, list);
-		n->free_slabs--;
-		n->total_slabs--;
-	}
-}
-
-static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac)
-{
-	int batchcount;
-	struct kmem_cache_node *n;
-	int node = numa_mem_id();
-	LIST_HEAD(list);
-
-	batchcount = ac->batchcount;
-
-	check_irq_off();
-	n = get_node(cachep, node);
-	raw_spin_lock(&n->list_lock);
-	if (n->shared) {
-		struct array_cache *shared_array = n->shared;
-		int max = shared_array->limit - shared_array->avail;
-		if (max) {
-			if (batchcount > max)
-				batchcount = max;
-			memcpy(&(shared_array->entry[shared_array->avail]),
-			       ac->entry, sizeof(void *) * batchcount);
-			shared_array->avail += batchcount;
-			goto free_done;
-		}
-	}
-
-	free_block(cachep, ac->entry, batchcount, node, &list);
-free_done:
-#if STATS
-	{
-		int i = 0;
-		struct slab *slab;
-
-		list_for_each_entry(slab, &n->slabs_free, slab_list) {
-			BUG_ON(slab->active);
-
-			i++;
-		}
-		STATS_SET_FREEABLE(cachep, i);
-	}
-#endif
-	raw_spin_unlock(&n->list_lock);
-	ac->avail -= batchcount;
-	memmove(ac->entry, &(ac->entry[batchcount]), sizeof(void *)*ac->avail);
-	slabs_destroy(cachep, &list);
-}
-
-/*
- * Release an obj back to its cache. If the obj has a constructed state, it must
- * be in this state _before_ it is released.  Called with disabled ints.
- */
-static __always_inline void __cache_free(struct kmem_cache *cachep, void *objp,
-					 unsigned long caller)
-{
-	bool init;
-
-	memcg_slab_free_hook(cachep, virt_to_slab(objp), &objp, 1);
-
-	if (is_kfence_address(objp)) {
-		kmemleak_free_recursive(objp, cachep->flags);
-		__kfence_free(objp);
-		return;
-	}
-
-	/*
-	 * As memory initialization might be integrated into KASAN,
-	 * kasan_slab_free and initialization memset must be
-	 * kept together to avoid discrepancies in behavior.
-	 */
-	init = slab_want_init_on_free(cachep);
-	if (init && !kasan_has_integrated_init())
-		memset(objp, 0, cachep->object_size);
-	/* KASAN might put objp into memory quarantine, delaying its reuse. */
-	if (kasan_slab_free(cachep, objp, init))
-		return;
-
-	/* Use KCSAN to help debug racy use-after-free. */
-	if (!(cachep->flags & SLAB_TYPESAFE_BY_RCU))
-		__kcsan_check_access(objp, cachep->object_size,
-				     KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT);
-
-	___cache_free(cachep, objp, caller);
-}
-
-void ___cache_free(struct kmem_cache *cachep, void *objp,
-		unsigned long caller)
-{
-	struct array_cache *ac = cpu_cache_get(cachep);
-
-	check_irq_off();
-	kmemleak_free_recursive(objp, cachep->flags);
-	objp = cache_free_debugcheck(cachep, objp, caller);
-
-	/*
-	 * Skip calling cache_free_alien() when the platform is not numa.
-	 * This will avoid cache misses that happen while accessing slabp (which
-	 * is per page memory  reference) to get nodeid. Instead use a global
-	 * variable to skip the call, which is mostly likely to be present in
-	 * the cache.
-	 */
-	if (nr_online_nodes > 1 && cache_free_alien(cachep, objp))
-		return;
-
-	if (ac->avail < ac->limit) {
-		STATS_INC_FREEHIT(cachep);
-	} else {
-		STATS_INC_FREEMISS(cachep);
-		cache_flusharray(cachep, ac);
-	}
-
-	if (sk_memalloc_socks()) {
-		struct slab *slab = virt_to_slab(objp);
-
-		if (unlikely(slab_test_pfmemalloc(slab))) {
-			cache_free_pfmemalloc(cachep, slab, objp);
-			return;
-		}
-	}
-
-	__free_one(ac, objp);
-}
-
-static __always_inline
-void *__kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru,
-			     gfp_t flags)
-{
-	void *ret = slab_alloc(cachep, lru, flags, cachep->object_size, _RET_IP_);
-
-	trace_kmem_cache_alloc(_RET_IP_, ret, cachep, flags, NUMA_NO_NODE);
-
-	return ret;
-}
-
-void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
-{
-	return __kmem_cache_alloc_lru(cachep, NULL, flags);
-}
-EXPORT_SYMBOL(kmem_cache_alloc);
-
-void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru,
-			   gfp_t flags)
-{
-	return __kmem_cache_alloc_lru(cachep, lru, flags);
-}
-EXPORT_SYMBOL(kmem_cache_alloc_lru);
-
-static __always_inline void
-cache_alloc_debugcheck_after_bulk(struct kmem_cache *s, gfp_t flags,
-				  size_t size, void **p, unsigned long caller)
-{
-	size_t i;
-
-	for (i = 0; i < size; i++)
-		p[i] = cache_alloc_debugcheck_after(s, flags, p[i], caller);
-}
-
-int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
-			  void **p)
-{
-	struct obj_cgroup *objcg = NULL;
-	unsigned long irqflags;
-	size_t i;
-
-	s = slab_pre_alloc_hook(s, NULL, &objcg, size, flags);
-	if (!s)
-		return 0;
-
-	local_irq_save(irqflags);
-	for (i = 0; i < size; i++) {
-		void *objp = kfence_alloc(s, s->object_size, flags) ?:
-			     __do_cache_alloc(s, flags, NUMA_NO_NODE);
-
-		if (unlikely(!objp))
-			goto error;
-		p[i] = objp;
-	}
-	local_irq_restore(irqflags);
-
-	cache_alloc_debugcheck_after_bulk(s, flags, size, p, _RET_IP_);
-
-	/*
-	 * memcg and kmem_cache debug support and memory initialization.
-	 * Done outside of the IRQ disabled section.
-	 */
-	slab_post_alloc_hook(s, objcg, flags, size, p,
-			slab_want_init_on_alloc(flags, s), s->object_size);
-	/* FIXME: Trace call missing. Christoph would like a bulk variant */
-	return size;
-error:
-	local_irq_restore(irqflags);
-	cache_alloc_debugcheck_after_bulk(s, flags, i, p, _RET_IP_);
-	slab_post_alloc_hook(s, objcg, flags, i, p, false, s->object_size);
-	kmem_cache_free_bulk(s, i, p);
-	return 0;
-}
-EXPORT_SYMBOL(kmem_cache_alloc_bulk);
-
-/**
- * kmem_cache_alloc_node - Allocate an object on the specified node
- * @cachep: The cache to allocate from.
- * @flags: See kmalloc().
- * @nodeid: node number of the target node.
- *
- * Identical to kmem_cache_alloc but it will allocate memory on the given
- * node, which can improve the performance for cpu bound structures.
- *
- * Fallback to other node is possible if __GFP_THISNODE is not set.
- *
- * Return: pointer to the new object or %NULL in case of error
- */
-void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
-{
-	void *ret = slab_alloc_node(cachep, NULL, flags, nodeid, cachep->object_size, _RET_IP_);
-
-	trace_kmem_cache_alloc(_RET_IP_, ret, cachep, flags, nodeid);
-
-	return ret;
-}
-EXPORT_SYMBOL(kmem_cache_alloc_node);
-
-void *__kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
-			     int nodeid, size_t orig_size,
-			     unsigned long caller)
-{
-	return slab_alloc_node(cachep, NULL, flags, nodeid,
-			       orig_size, caller);
-}
-
-#ifdef CONFIG_PRINTK
-void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab)
-{
-	struct kmem_cache *cachep;
-	unsigned int objnr;
-	void *objp;
-
-	kpp->kp_ptr = object;
-	kpp->kp_slab = slab;
-	cachep = slab->slab_cache;
-	kpp->kp_slab_cache = cachep;
-	objp = object - obj_offset(cachep);
-	kpp->kp_data_offset = obj_offset(cachep);
-	slab = virt_to_slab(objp);
-	objnr = obj_to_index(cachep, slab, objp);
-	objp = index_to_obj(cachep, slab, objnr);
-	kpp->kp_objp = objp;
-	if (DEBUG && cachep->flags & SLAB_STORE_USER)
-		kpp->kp_ret = *dbg_userword(cachep, objp);
-}
-#endif
-
-static __always_inline
-void __do_kmem_cache_free(struct kmem_cache *cachep, void *objp,
-			  unsigned long caller)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	debug_check_no_locks_freed(objp, cachep->object_size);
-	if (!(cachep->flags & SLAB_DEBUG_OBJECTS))
-		debug_check_no_obj_freed(objp, cachep->object_size);
-	__cache_free(cachep, objp, caller);
-	local_irq_restore(flags);
-}
-
-void __kmem_cache_free(struct kmem_cache *cachep, void *objp,
-		       unsigned long caller)
-{
-	__do_kmem_cache_free(cachep, objp, caller);
-}
-
-/**
- * kmem_cache_free - Deallocate an object
- * @cachep: The cache the allocation was from.
- * @objp: The previously allocated object.
- *
- * Free an object which was previously allocated from this
- * cache.
- */
-void kmem_cache_free(struct kmem_cache *cachep, void *objp)
-{
-	cachep = cache_from_obj(cachep, objp);
-	if (!cachep)
-		return;
-
-	trace_kmem_cache_free(_RET_IP_, objp, cachep);
-	__do_kmem_cache_free(cachep, objp, _RET_IP_);
-}
-EXPORT_SYMBOL(kmem_cache_free);
-
-void kmem_cache_free_bulk(struct kmem_cache *orig_s, size_t size, void **p)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	for (int i = 0; i < size; i++) {
-		void *objp = p[i];
-		struct kmem_cache *s;
-
-		if (!orig_s) {
-			struct folio *folio = virt_to_folio(objp);
-
-			/* called via kfree_bulk */
-			if (!folio_test_slab(folio)) {
-				local_irq_restore(flags);
-				free_large_kmalloc(folio, objp);
-				local_irq_save(flags);
-				continue;
-			}
-			s = folio_slab(folio)->slab_cache;
-		} else {
-			s = cache_from_obj(orig_s, objp);
-		}
-
-		if (!s)
-			continue;
-
-		debug_check_no_locks_freed(objp, s->object_size);
-		if (!(s->flags & SLAB_DEBUG_OBJECTS))
-			debug_check_no_obj_freed(objp, s->object_size);
-
-		__cache_free(s, objp, _RET_IP_);
-	}
-	local_irq_restore(flags);
-
-	/* FIXME: add tracing */
-}
-EXPORT_SYMBOL(kmem_cache_free_bulk);
-
-/*
- * This initializes kmem_cache_node or resizes various caches for all nodes.
- */
-static int setup_kmem_cache_nodes(struct kmem_cache *cachep, gfp_t gfp)
-{
-	int ret;
-	int node;
-	struct kmem_cache_node *n;
-
-	for_each_online_node(node) {
-		ret = setup_kmem_cache_node(cachep, node, gfp, true);
-		if (ret)
-			goto fail;
-
-	}
-
-	return 0;
-
-fail:
-	if (!cachep->list.next) {
-		/* Cache is not active yet. Roll back what we did */
-		node--;
-		while (node >= 0) {
-			n = get_node(cachep, node);
-			if (n) {
-				kfree(n->shared);
-				free_alien_cache(n->alien);
-				kfree(n);
-				cachep->node[node] = NULL;
-			}
-			node--;
-		}
-	}
-	return -ENOMEM;
-}
-
-/* Always called with the slab_mutex held */
-static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
-			    int batchcount, int shared, gfp_t gfp)
-{
-	struct array_cache __percpu *cpu_cache, *prev;
-	int cpu;
-
-	cpu_cache = alloc_kmem_cache_cpus(cachep, limit, batchcount);
-	if (!cpu_cache)
-		return -ENOMEM;
-
-	prev = cachep->cpu_cache;
-	cachep->cpu_cache = cpu_cache;
-	/*
-	 * Without a previous cpu_cache there's no need to synchronize remote
-	 * cpus, so skip the IPIs.
-	 */
-	if (prev)
-		kick_all_cpus_sync();
-
-	check_irq_on();
-	cachep->batchcount = batchcount;
-	cachep->limit = limit;
-	cachep->shared = shared;
-
-	if (!prev)
-		goto setup_node;
-
-	for_each_online_cpu(cpu) {
-		LIST_HEAD(list);
-		int node;
-		struct kmem_cache_node *n;
-		struct array_cache *ac = per_cpu_ptr(prev, cpu);
-
-		node = cpu_to_mem(cpu);
-		n = get_node(cachep, node);
-		raw_spin_lock_irq(&n->list_lock);
-		free_block(cachep, ac->entry, ac->avail, node, &list);
-		raw_spin_unlock_irq(&n->list_lock);
-		slabs_destroy(cachep, &list);
-	}
-	free_percpu(prev);
-
-setup_node:
-	return setup_kmem_cache_nodes(cachep, gfp);
-}
-
-/* Called with slab_mutex held always */
-static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp)
-{
-	int err;
-	int limit = 0;
-	int shared = 0;
-	int batchcount = 0;
-
-	err = cache_random_seq_create(cachep, cachep->num, gfp);
-	if (err)
-		goto end;
-
-	/*
-	 * The head array serves three purposes:
-	 * - create a LIFO ordering, i.e. return objects that are cache-warm
-	 * - reduce the number of spinlock operations.
-	 * - reduce the number of linked list operations on the slab and
-	 *   bufctl chains: array operations are cheaper.
-	 * The numbers are guessed, we should auto-tune as described by
-	 * Bonwick.
-	 */
-	if (cachep->size > 131072)
-		limit = 1;
-	else if (cachep->size > PAGE_SIZE)
-		limit = 8;
-	else if (cachep->size > 1024)
-		limit = 24;
-	else if (cachep->size > 256)
-		limit = 54;
-	else
-		limit = 120;
-
-	/*
-	 * CPU bound tasks (e.g. network routing) can exhibit cpu bound
-	 * allocation behaviour: Most allocs on one cpu, most free operations
-	 * on another cpu. For these cases, an efficient object passing between
-	 * cpus is necessary. This is provided by a shared array. The array
-	 * replaces Bonwick's magazine layer.
-	 * On uniprocessor, it's functionally equivalent (but less efficient)
-	 * to a larger limit. Thus disabled by default.
-	 */
-	shared = 0;
-	if (cachep->size <= PAGE_SIZE && num_possible_cpus() > 1)
-		shared = 8;
-
-#if DEBUG
-	/*
-	 * With debugging enabled, large batchcount lead to excessively long
-	 * periods with disabled local interrupts. Limit the batchcount
-	 */
-	if (limit > 32)
-		limit = 32;
-#endif
-	batchcount = (limit + 1) / 2;
-	err = do_tune_cpucache(cachep, limit, batchcount, shared, gfp);
-end:
-	if (err)
-		pr_err("enable_cpucache failed for %s, error %d\n",
-		       cachep->name, -err);
-	return err;
-}
-
-/*
- * Drain an array if it contains any elements taking the node lock only if
- * necessary. Note that the node listlock also protects the array_cache
- * if drain_array() is used on the shared array.
- */
-static void drain_array(struct kmem_cache *cachep, struct kmem_cache_node *n,
-			 struct array_cache *ac, int node)
-{
-	LIST_HEAD(list);
-
-	/* ac from n->shared can be freed if we don't hold the slab_mutex. */
-	check_mutex_acquired();
-
-	if (!ac || !ac->avail)
-		return;
-
-	if (ac->touched) {
-		ac->touched = 0;
-		return;
-	}
-
-	raw_spin_lock_irq(&n->list_lock);
-	drain_array_locked(cachep, ac, node, false, &list);
-	raw_spin_unlock_irq(&n->list_lock);
-
-	slabs_destroy(cachep, &list);
-}
-
-/**
- * cache_reap - Reclaim memory from caches.
- * @w: work descriptor
- *
- * Called from workqueue/eventd every few seconds.
- * Purpose:
- * - clear the per-cpu caches for this CPU.
- * - return freeable pages to the main free memory pool.
- *
- * If we cannot acquire the cache chain mutex then just give up - we'll try
- * again on the next iteration.
- */
-static void cache_reap(struct work_struct *w)
-{
-	struct kmem_cache *searchp;
-	struct kmem_cache_node *n;
-	int node = numa_mem_id();
-	struct delayed_work *work = to_delayed_work(w);
-
-	if (!mutex_trylock(&slab_mutex))
-		/* Give up. Setup the next iteration. */
-		goto out;
-
-	list_for_each_entry(searchp, &slab_caches, list) {
-		check_irq_on();
-
-		/*
-		 * We only take the node lock if absolutely necessary and we
-		 * have established with reasonable certainty that
-		 * we can do some work if the lock was obtained.
-		 */
-		n = get_node(searchp, node);
-
-		reap_alien(searchp, n);
-
-		drain_array(searchp, n, cpu_cache_get(searchp), node);
-
-		/*
-		 * These are racy checks but it does not matter
-		 * if we skip one check or scan twice.
-		 */
-		if (time_after(n->next_reap, jiffies))
-			goto next;
-
-		n->next_reap = jiffies + REAPTIMEOUT_NODE;
-
-		drain_array(searchp, n, n->shared, node);
-
-		if (n->free_touched)
-			n->free_touched = 0;
-		else {
-			int freed;
-
-			freed = drain_freelist(searchp, n, (n->free_limit +
-				5 * searchp->num - 1) / (5 * searchp->num));
-			STATS_ADD_REAPED(searchp, freed);
-		}
-next:
-		cond_resched();
-	}
-	check_irq_on();
-	mutex_unlock(&slab_mutex);
-	next_reap_node();
-out:
-	/* Set up the next iteration */
-	schedule_delayed_work_on(smp_processor_id(), work,
-				round_jiffies_relative(REAPTIMEOUT_AC));
-}
-
-void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
-{
-	unsigned long active_objs, num_objs, active_slabs;
-	unsigned long total_slabs = 0, free_objs = 0, shared_avail = 0;
-	unsigned long free_slabs = 0;
-	int node;
-	struct kmem_cache_node *n;
-
-	for_each_kmem_cache_node(cachep, node, n) {
-		check_irq_on();
-		raw_spin_lock_irq(&n->list_lock);
-
-		total_slabs += n->total_slabs;
-		free_slabs += n->free_slabs;
-		free_objs += n->free_objects;
-
-		if (n->shared)
-			shared_avail += n->shared->avail;
-
-		raw_spin_unlock_irq(&n->list_lock);
-	}
-	num_objs = total_slabs * cachep->num;
-	active_slabs = total_slabs - free_slabs;
-	active_objs = num_objs - free_objs;
-
-	sinfo->active_objs = active_objs;
-	sinfo->num_objs = num_objs;
-	sinfo->active_slabs = active_slabs;
-	sinfo->num_slabs = total_slabs;
-	sinfo->shared_avail = shared_avail;
-	sinfo->limit = cachep->limit;
-	sinfo->batchcount = cachep->batchcount;
-	sinfo->shared = cachep->shared;
-	sinfo->objects_per_slab = cachep->num;
-	sinfo->cache_order = cachep->gfporder;
-}
-
-void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *cachep)
-{
-#if STATS
-	{			/* node stats */
-		unsigned long high = cachep->high_mark;
-		unsigned long allocs = cachep->num_allocations;
-		unsigned long grown = cachep->grown;
-		unsigned long reaped = cachep->reaped;
-		unsigned long errors = cachep->errors;
-		unsigned long max_freeable = cachep->max_freeable;
-		unsigned long node_allocs = cachep->node_allocs;
-		unsigned long node_frees = cachep->node_frees;
-		unsigned long overflows = cachep->node_overflow;
-
-		seq_printf(m, " : globalstat %7lu %6lu %5lu %4lu %4lu %4lu %4lu %4lu %4lu",
-			   allocs, high, grown,
-			   reaped, errors, max_freeable, node_allocs,
-			   node_frees, overflows);
-	}
-	/* cpu stats */
-	{
-		unsigned long allochit = atomic_read(&cachep->allochit);
-		unsigned long allocmiss = atomic_read(&cachep->allocmiss);
-		unsigned long freehit = atomic_read(&cachep->freehit);
-		unsigned long freemiss = atomic_read(&cachep->freemiss);
-
-		seq_printf(m, " : cpustat %6lu %6lu %6lu %6lu",
-			   allochit, allocmiss, freehit, freemiss);
-	}
-#endif
-}
-
-#define MAX_SLABINFO_WRITE 128
-/**
- * slabinfo_write - Tuning for the slab allocator
- * @file: unused
- * @buffer: user buffer
- * @count: data length
- * @ppos: unused
- *
- * Return: %0 on success, negative error code otherwise.
- */
-ssize_t slabinfo_write(struct file *file, const char __user *buffer,
-		       size_t count, loff_t *ppos)
-{
-	char kbuf[MAX_SLABINFO_WRITE + 1], *tmp;
-	int limit, batchcount, shared, res;
-	struct kmem_cache *cachep;
-
-	if (count > MAX_SLABINFO_WRITE)
-		return -EINVAL;
-	if (copy_from_user(&kbuf, buffer, count))
-		return -EFAULT;
-	kbuf[MAX_SLABINFO_WRITE] = '\0';
-
-	tmp = strchr(kbuf, ' ');
-	if (!tmp)
-		return -EINVAL;
-	*tmp = '\0';
-	tmp++;
-	if (sscanf(tmp, " %d %d %d", &limit, &batchcount, &shared) != 3)
-		return -EINVAL;
-
-	/* Find the cache in the chain of caches. */
-	mutex_lock(&slab_mutex);
-	res = -EINVAL;
-	list_for_each_entry(cachep, &slab_caches, list) {
-		if (!strcmp(cachep->name, kbuf)) {
-			if (limit < 1 || batchcount < 1 ||
-					batchcount > limit || shared < 0) {
-				res = 0;
-			} else {
-				res = do_tune_cpucache(cachep, limit,
-						       batchcount, shared,
-						       GFP_KERNEL);
-			}
-			break;
-		}
-	}
-	mutex_unlock(&slab_mutex);
-	if (res >= 0)
-		res = count;
-	return res;
-}
-
-#ifdef CONFIG_HARDENED_USERCOPY
-/*
- * Rejects incorrectly sized objects and objects that are to be copied
- * to/from userspace but do not fall entirely within the containing slab
- * cache's usercopy region.
- *
- * Returns NULL if check passes, otherwise const char * to name of cache
- * to indicate an error.
- */
-void __check_heap_object(const void *ptr, unsigned long n,
-			 const struct slab *slab, bool to_user)
-{
-	struct kmem_cache *cachep;
-	unsigned int objnr;
-	unsigned long offset;
-
-	ptr = kasan_reset_tag(ptr);
-
-	/* Find and validate object. */
-	cachep = slab->slab_cache;
-	objnr = obj_to_index(cachep, slab, (void *)ptr);
-	BUG_ON(objnr >= cachep->num);
-
-	/* Find offset within object. */
-	if (is_kfence_address(ptr))
-		offset = ptr - kfence_object_start(ptr);
-	else
-		offset = ptr - index_to_obj(cachep, slab, objnr) - obj_offset(cachep);
-
-	/* Allow address range falling entirely within usercopy region. */
-	if (offset >= cachep->useroffset &&
-	    offset - cachep->useroffset <= cachep->usersize &&
-	    n <= cachep->useroffset - offset + cachep->usersize)
-		return;
-
-	usercopy_abort("SLAB object", cachep->name, to_user, offset, n);
-}
-#endif /* CONFIG_HARDENED_USERCOPY */
diff --git a/mm/slab.h b/mm/slab.h
index 3d07fb428393..54deeb0428c6 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -1,10 +1,20 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef MM_SLAB_H
 #define MM_SLAB_H
+
+#include <linux/reciprocal_div.h>
+#include <linux/list_lru.h>
+#include <linux/local_lock.h>
+#include <linux/random.h>
+#include <linux/kobject.h>
+#include <linux/sched/mm.h>
+#include <linux/memcontrol.h>
+#include <linux/kfence.h>
+#include <linux/kasan.h>
+
 /*
  * Internal slab definitions
  */
-void __init kmem_cache_init(void);
 
 #ifdef CONFIG_64BIT
 # ifdef system_has_cmpxchg128
@@ -42,21 +52,6 @@ typedef union {
 struct slab {
 	unsigned long __page_flags;
 
-#if defined(CONFIG_SLAB)
-
-	struct kmem_cache *slab_cache;
-	union {
-		struct {
-			struct list_head slab_list;
-			void *freelist;	/* array of free object indexes */
-			void *s_mem;	/* first object */
-		};
-		struct rcu_head rcu_head;
-	};
-	unsigned int active;
-
-#elif defined(CONFIG_SLUB)
-
 	struct kmem_cache *slab_cache;
 	union {
 		struct {
@@ -91,10 +86,6 @@ struct slab {
 	};
 	unsigned int __unused;
 
-#else
-#error "Unexpected slab allocator configured"
-#endif
-
 	atomic_t __page_refcount;
 #ifdef CONFIG_MEMCG
 	unsigned long memcg_data;
@@ -111,7 +102,7 @@ SLAB_MATCH(memcg_data, memcg_data);
 #endif
 #undef SLAB_MATCH
 static_assert(sizeof(struct slab) <= sizeof(struct page));
-#if defined(system_has_freelist_aba) && defined(CONFIG_SLUB)
+#if defined(system_has_freelist_aba)
 static_assert(IS_ALIGNED(offsetof(struct slab, freelist), sizeof(freelist_aba_t)));
 #endif
 
@@ -228,21 +219,138 @@ static inline size_t slab_size(const struct slab *slab)
 	return PAGE_SIZE << slab_order(slab);
 }
 
-#ifdef CONFIG_SLAB
-#include <linux/slab_def.h>
+#ifdef CONFIG_SLUB_CPU_PARTIAL
+#define slub_percpu_partial(c)			((c)->partial)
+
+#define slub_set_percpu_partial(c, p)		\
+({						\
+	slub_percpu_partial(c) = (p)->next;	\
+})
+
+#define slub_percpu_partial_read_once(c)	READ_ONCE(slub_percpu_partial(c))
+#else
+#define slub_percpu_partial(c)			NULL
+
+#define slub_set_percpu_partial(c, p)
+
+#define slub_percpu_partial_read_once(c)	NULL
+#endif // CONFIG_SLUB_CPU_PARTIAL
+
+/*
+ * Word size structure that can be atomically updated or read and that
+ * contains both the order and the number of objects that a slab of the
+ * given order would contain.
+ */
+struct kmem_cache_order_objects {
+	unsigned int x;
+};
+
+/*
+ * Slab cache management.
+ */
+struct kmem_cache {
+#ifndef CONFIG_SLUB_TINY
+	struct kmem_cache_cpu __percpu *cpu_slab;
+#endif
+	/* Used for retrieving partial slabs, etc. */
+	slab_flags_t flags;
+	unsigned long min_partial;
+	unsigned int size;		/* Object size including metadata */
+	unsigned int object_size;	/* Object size without metadata */
+	struct reciprocal_value reciprocal_size;
+	unsigned int offset;		/* Free pointer offset */
+#ifdef CONFIG_SLUB_CPU_PARTIAL
+	/* Number of per cpu partial objects to keep around */
+	unsigned int cpu_partial;
+	/* Number of per cpu partial slabs to keep around */
+	unsigned int cpu_partial_slabs;
+#endif
+	struct kmem_cache_order_objects oo;
+
+	/* Allocation and freeing of slabs */
+	struct kmem_cache_order_objects min;
+	gfp_t allocflags;		/* gfp flags to use on each alloc */
+	int refcount;			/* Refcount for slab cache destroy */
+	void (*ctor)(void *object);	/* Object constructor */
+	unsigned int inuse;		/* Offset to metadata */
+	unsigned int align;		/* Alignment */
+	unsigned int red_left_pad;	/* Left redzone padding size */
+	const char *name;		/* Name (only for display!) */
+	struct list_head list;		/* List of slab caches */
+#ifdef CONFIG_SYSFS
+	struct kobject kobj;		/* For sysfs */
+#endif
+#ifdef CONFIG_SLAB_FREELIST_HARDENED
+	unsigned long random;
 #endif
 
-#ifdef CONFIG_SLUB
-#include <linux/slub_def.h>
+#ifdef CONFIG_NUMA
+	/*
+	 * Defragmentation by allocating from a remote node.
+	 */
+	unsigned int remote_node_defrag_ratio;
 #endif
 
-#include <linux/memcontrol.h>
-#include <linux/fault-inject.h>
-#include <linux/kasan.h>
-#include <linux/kmemleak.h>
-#include <linux/random.h>
-#include <linux/sched/mm.h>
-#include <linux/list_lru.h>
+#ifdef CONFIG_SLAB_FREELIST_RANDOM
+	unsigned int *random_seq;
+#endif
+
+#ifdef CONFIG_KASAN_GENERIC
+	struct kasan_cache kasan_info;
+#endif
+
+#ifdef CONFIG_HARDENED_USERCOPY
+	unsigned int useroffset;	/* Usercopy region offset */
+	unsigned int usersize;		/* Usercopy region size */
+#endif
+
+	struct kmem_cache_node *node[MAX_NUMNODES];
+};
+
+#if defined(CONFIG_SYSFS) && !defined(CONFIG_SLUB_TINY)
+#define SLAB_SUPPORTS_SYSFS
+void sysfs_slab_unlink(struct kmem_cache *s);
+void sysfs_slab_release(struct kmem_cache *s);
+#else
+static inline void sysfs_slab_unlink(struct kmem_cache *s) { }
+static inline void sysfs_slab_release(struct kmem_cache *s) { }
+#endif
+
+void *fixup_red_left(struct kmem_cache *s, void *p);
+
+static inline void *nearest_obj(struct kmem_cache *cache,
+				const struct slab *slab, void *x)
+{
+	void *object = x - (x - slab_address(slab)) % cache->size;
+	void *last_object = slab_address(slab) +
+		(slab->objects - 1) * cache->size;
+	void *result = (unlikely(object > last_object)) ? last_object : object;
+
+	result = fixup_red_left(cache, result);
+	return result;
+}
+
+/* Determine object index from a given position */
+static inline unsigned int __obj_to_index(const struct kmem_cache *cache,
+					  void *addr, void *obj)
+{
+	return reciprocal_divide(kasan_reset_tag(obj) - addr,
+				 cache->reciprocal_size);
+}
+
+static inline unsigned int obj_to_index(const struct kmem_cache *cache,
+					const struct slab *slab, void *obj)
+{
+	if (is_kfence_address(obj))
+		return 0;
+	return __obj_to_index(cache, slab_address(slab), obj);
+}
+
+static inline int objs_per_slab(const struct kmem_cache *cache,
+				const struct slab *slab)
+{
+	return slab->objects;
+}
 
 /*
  * State of the slab allocator.
@@ -281,19 +389,39 @@ extern const struct kmalloc_info_struct {
 void setup_kmalloc_cache_index_table(void);
 void create_kmalloc_caches(slab_flags_t);
 
-/* Find the kmalloc slab corresponding for a certain size */
-struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags, unsigned long caller);
+extern u8 kmalloc_size_index[24];
+
+static inline unsigned int size_index_elem(unsigned int bytes)
+{
+	return (bytes - 1) / 8;
+}
+
+/*
+ * Find the kmem_cache structure that serves a given size of
+ * allocation
+ *
+ * This assumes size is larger than zero and not larger than
+ * KMALLOC_MAX_CACHE_SIZE and the caller must check that.
+ */
+static inline struct kmem_cache *
+kmalloc_slab(size_t size, gfp_t flags, unsigned long caller)
+{
+	unsigned int index;
+
+	if (size <= 192)
+		index = kmalloc_size_index[size_index_elem(size)];
+	else
+		index = fls(size - 1);
 
-void *__kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags,
-			      int node, size_t orig_size,
-			      unsigned long caller);
-void __kmem_cache_free(struct kmem_cache *s, void *x, unsigned long caller);
+	return kmalloc_caches[kmalloc_type(flags, caller)][index];
+}
 
 gfp_t kmalloc_fix_flags(gfp_t flags);
 
 /* Functions provided by the slab allocators */
 int __kmem_cache_create(struct kmem_cache *, slab_flags_t flags);
 
+void __init kmem_cache_init(void);
 void __init new_kmalloc_cache(int idx, enum kmalloc_cache_type type,
 			      slab_flags_t flags);
 extern void create_boot_cache(struct kmem_cache *, const char *name,
@@ -320,26 +448,16 @@ static inline bool is_kmalloc_cache(struct kmem_cache *s)
 			 SLAB_CACHE_DMA32 | SLAB_PANIC | \
 			 SLAB_TYPESAFE_BY_RCU | SLAB_DEBUG_OBJECTS )
 
-#if defined(CONFIG_DEBUG_SLAB)
-#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER)
-#elif defined(CONFIG_SLUB_DEBUG)
+#ifdef CONFIG_SLUB_DEBUG
 #define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
 			  SLAB_TRACE | SLAB_CONSISTENCY_CHECKS)
 #else
 #define SLAB_DEBUG_FLAGS (0)
 #endif
 
-#if defined(CONFIG_SLAB)
-#define SLAB_CACHE_FLAGS (SLAB_MEM_SPREAD | SLAB_NOLEAKTRACE | \
-			  SLAB_RECLAIM_ACCOUNT | SLAB_TEMPORARY | \
-			  SLAB_ACCOUNT | SLAB_NO_MERGE)
-#elif defined(CONFIG_SLUB)
 #define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \
 			  SLAB_TEMPORARY | SLAB_ACCOUNT | \
 			  SLAB_NO_USER_FLAGS | SLAB_KMALLOC | SLAB_NO_MERGE)
-#else
-#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE)
-#endif
 
 /* Common flags available with current configuration */
 #define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS)
@@ -387,12 +505,6 @@ void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s);
 ssize_t slabinfo_write(struct file *file, const char __user *buffer,
 		       size_t count, loff_t *ppos);
 
-static inline enum node_stat_item cache_vmstat_idx(struct kmem_cache *s)
-{
-	return (s->flags & SLAB_RECLAIM_ACCOUNT) ?
-		NR_SLAB_RECLAIMABLE_B : NR_SLAB_UNRECLAIMABLE_B;
-}
-
 #ifdef CONFIG_SLUB_DEBUG
 #ifdef CONFIG_SLUB_DEBUG_ON
 DECLARE_STATIC_KEY_TRUE(slub_debug_enabled);
@@ -452,238 +564,32 @@ int memcg_alloc_slab_cgroups(struct slab *slab, struct kmem_cache *s,
 				 gfp_t gfp, bool new_slab);
 void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
 		     enum node_stat_item idx, int nr);
-
-static inline void memcg_free_slab_cgroups(struct slab *slab)
-{
-	kfree(slab_objcgs(slab));
-	slab->memcg_data = 0;
-}
-
-static inline size_t obj_full_size(struct kmem_cache *s)
-{
-	/*
-	 * For each accounted object there is an extra space which is used
-	 * to store obj_cgroup membership. Charge it too.
-	 */
-	return s->size + sizeof(struct obj_cgroup *);
-}
-
-/*
- * Returns false if the allocation should fail.
- */
-static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s,
-					     struct list_lru *lru,
-					     struct obj_cgroup **objcgp,
-					     size_t objects, gfp_t flags)
-{
-	struct obj_cgroup *objcg;
-
-	if (!memcg_kmem_online())
-		return true;
-
-	if (!(flags & __GFP_ACCOUNT) && !(s->flags & SLAB_ACCOUNT))
-		return true;
-
-	/*
-	 * The obtained objcg pointer is safe to use within the current scope,
-	 * defined by current task or set_active_memcg() pair.
-	 * obj_cgroup_get() is used to get a permanent reference.
-	 */
-	objcg = current_obj_cgroup();
-	if (!objcg)
-		return true;
-
-	if (lru) {
-		int ret;
-		struct mem_cgroup *memcg;
-
-		memcg = get_mem_cgroup_from_objcg(objcg);
-		ret = memcg_list_lru_alloc(memcg, lru, flags);
-		css_put(&memcg->css);
-
-		if (ret)
-			return false;
-	}
-
-	if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s)))
-		return false;
-
-	*objcgp = objcg;
-	return true;
-}
-
-static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
-					      struct obj_cgroup *objcg,
-					      gfp_t flags, size_t size,
-					      void **p)
-{
-	struct slab *slab;
-	unsigned long off;
-	size_t i;
-
-	if (!memcg_kmem_online() || !objcg)
-		return;
-
-	for (i = 0; i < size; i++) {
-		if (likely(p[i])) {
-			slab = virt_to_slab(p[i]);
-
-			if (!slab_objcgs(slab) &&
-			    memcg_alloc_slab_cgroups(slab, s, flags,
-							 false)) {
-				obj_cgroup_uncharge(objcg, obj_full_size(s));
-				continue;
-			}
-
-			off = obj_to_index(s, slab, p[i]);
-			obj_cgroup_get(objcg);
-			slab_objcgs(slab)[off] = objcg;
-			mod_objcg_state(objcg, slab_pgdat(slab),
-					cache_vmstat_idx(s), obj_full_size(s));
-		} else {
-			obj_cgroup_uncharge(objcg, obj_full_size(s));
-		}
-	}
-}
-
-static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
-					void **p, int objects)
-{
-	struct obj_cgroup **objcgs;
-	int i;
-
-	if (!memcg_kmem_online())
-		return;
-
-	objcgs = slab_objcgs(slab);
-	if (!objcgs)
-		return;
-
-	for (i = 0; i < objects; i++) {
-		struct obj_cgroup *objcg;
-		unsigned int off;
-
-		off = obj_to_index(s, slab, p[i]);
-		objcg = objcgs[off];
-		if (!objcg)
-			continue;
-
-		objcgs[off] = NULL;
-		obj_cgroup_uncharge(objcg, obj_full_size(s));
-		mod_objcg_state(objcg, slab_pgdat(slab), cache_vmstat_idx(s),
-				-obj_full_size(s));
-		obj_cgroup_put(objcg);
-	}
-}
-
 #else /* CONFIG_MEMCG_KMEM */
 static inline struct obj_cgroup **slab_objcgs(struct slab *slab)
 {
 	return NULL;
 }
 
-static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr)
-{
-	return NULL;
-}
-
 static inline int memcg_alloc_slab_cgroups(struct slab *slab,
 					       struct kmem_cache *s, gfp_t gfp,
 					       bool new_slab)
 {
 	return 0;
 }
-
-static inline void memcg_free_slab_cgroups(struct slab *slab)
-{
-}
-
-static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s,
-					     struct list_lru *lru,
-					     struct obj_cgroup **objcgp,
-					     size_t objects, gfp_t flags)
-{
-	return true;
-}
-
-static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
-					      struct obj_cgroup *objcg,
-					      gfp_t flags, size_t size,
-					      void **p)
-{
-}
-
-static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
-					void **p, int objects)
-{
-}
 #endif /* CONFIG_MEMCG_KMEM */
 
-static inline struct kmem_cache *virt_to_cache(const void *obj)
-{
-	struct slab *slab;
-
-	slab = virt_to_slab(obj);
-	if (WARN_ONCE(!slab, "%s: Object is not a Slab page!\n",
-					__func__))
-		return NULL;
-	return slab->slab_cache;
-}
-
-static __always_inline void account_slab(struct slab *slab, int order,
-					 struct kmem_cache *s, gfp_t gfp)
-{
-	if (memcg_kmem_online() && (s->flags & SLAB_ACCOUNT))
-		memcg_alloc_slab_cgroups(slab, s, gfp, true);
-
-	mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s),
-			    PAGE_SIZE << order);
-}
-
-static __always_inline void unaccount_slab(struct slab *slab, int order,
-					   struct kmem_cache *s)
-{
-	if (memcg_kmem_online())
-		memcg_free_slab_cgroups(slab);
-
-	mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s),
-			    -(PAGE_SIZE << order));
-}
-
-static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
-{
-	struct kmem_cache *cachep;
-
-	if (!IS_ENABLED(CONFIG_SLAB_FREELIST_HARDENED) &&
-	    !kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS))
-		return s;
-
-	cachep = virt_to_cache(x);
-	if (WARN(cachep && cachep != s,
-		  "%s: Wrong slab cache. %s but object is from %s\n",
-		  __func__, s->name, cachep->name))
-		print_tracking(cachep, x);
-	return cachep;
-}
-
-void free_large_kmalloc(struct folio *folio, void *object);
-
 size_t __ksize(const void *objp);
 
 static inline size_t slab_ksize(const struct kmem_cache *s)
 {
-#ifndef CONFIG_SLUB
-	return s->object_size;
-
-#else /* CONFIG_SLUB */
-# ifdef CONFIG_SLUB_DEBUG
+#ifdef CONFIG_SLUB_DEBUG
 	/*
 	 * Debugging requires use of the padding between object
 	 * and whatever may come after it.
 	 */
 	if (s->flags & (SLAB_RED_ZONE | SLAB_POISON))
 		return s->object_size;
-# endif
+#endif
 	if (s->flags & SLAB_KASAN)
 		return s->object_size;
 	/*
@@ -697,128 +603,9 @@ static inline size_t slab_ksize(const struct kmem_cache *s)
 	 * Else we can use all the padding etc for the allocation
 	 */
 	return s->size;
-#endif
-}
-
-static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
-						     struct list_lru *lru,
-						     struct obj_cgroup **objcgp,
-						     size_t size, gfp_t flags)
-{
-	flags &= gfp_allowed_mask;
-
-	might_alloc(flags);
-
-	if (should_failslab(s, flags))
-		return NULL;
-
-	if (!memcg_slab_pre_alloc_hook(s, lru, objcgp, size, flags))
-		return NULL;
-
-	return s;
-}
-
-static inline void slab_post_alloc_hook(struct kmem_cache *s,
-					struct obj_cgroup *objcg, gfp_t flags,
-					size_t size, void **p, bool init,
-					unsigned int orig_size)
-{
-	unsigned int zero_size = s->object_size;
-	bool kasan_init = init;
-	size_t i;
-
-	flags &= gfp_allowed_mask;
-
-	/*
-	 * For kmalloc object, the allocated memory size(object_size) is likely
-	 * larger than the requested size(orig_size). If redzone check is
-	 * enabled for the extra space, don't zero it, as it will be redzoned
-	 * soon. The redzone operation for this extra space could be seen as a
-	 * replacement of current poisoning under certain debug option, and
-	 * won't break other sanity checks.
-	 */
-	if (kmem_cache_debug_flags(s, SLAB_STORE_USER | SLAB_RED_ZONE) &&
-	    (s->flags & SLAB_KMALLOC))
-		zero_size = orig_size;
-
-	/*
-	 * When slub_debug is enabled, avoid memory initialization integrated
-	 * into KASAN and instead zero out the memory via the memset below with
-	 * the proper size. Otherwise, KASAN might overwrite SLUB redzones and
-	 * cause false-positive reports. This does not lead to a performance
-	 * penalty on production builds, as slub_debug is not intended to be
-	 * enabled there.
-	 */
-	if (__slub_debug_enabled())
-		kasan_init = false;
-
-	/*
-	 * As memory initialization might be integrated into KASAN,
-	 * kasan_slab_alloc and initialization memset must be
-	 * kept together to avoid discrepancies in behavior.
-	 *
-	 * As p[i] might get tagged, memset and kmemleak hook come after KASAN.
-	 */
-	for (i = 0; i < size; i++) {
-		p[i] = kasan_slab_alloc(s, p[i], flags, kasan_init);
-		if (p[i] && init && (!kasan_init || !kasan_has_integrated_init()))
-			memset(p[i], 0, zero_size);
-		kmemleak_alloc_recursive(p[i], s->object_size, 1,
-					 s->flags, flags);
-		kmsan_slab_alloc(s, p[i], flags);
-	}
-
-	memcg_slab_post_alloc_hook(s, objcg, flags, size, p);
 }
 
-/*
- * The slab lists for all objects.
- */
-struct kmem_cache_node {
-#ifdef CONFIG_SLAB
-	raw_spinlock_t list_lock;
-	struct list_head slabs_partial;	/* partial list first, better asm code */
-	struct list_head slabs_full;
-	struct list_head slabs_free;
-	unsigned long total_slabs;	/* length of all slab lists */
-	unsigned long free_slabs;	/* length of free slab list only */
-	unsigned long free_objects;
-	unsigned int free_limit;
-	unsigned int colour_next;	/* Per-node cache coloring */
-	struct array_cache *shared;	/* shared per node */
-	struct alien_cache **alien;	/* on other nodes */
-	unsigned long next_reap;	/* updated without locking */
-	int free_touched;		/* updated without locking */
-#endif
-
-#ifdef CONFIG_SLUB
-	spinlock_t list_lock;
-	unsigned long nr_partial;
-	struct list_head partial;
 #ifdef CONFIG_SLUB_DEBUG
-	atomic_long_t nr_slabs;
-	atomic_long_t total_objects;
-	struct list_head full;
-#endif
-#endif
-
-};
-
-static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
-{
-	return s->node[node];
-}
-
-/*
- * Iterator over all nodes. The body will be executed for each node that has
- * a kmem_cache_node structure allocated (which is true for all online nodes)
- */
-#define for_each_kmem_cache_node(__s, __node, __n) \
-	for (__node = 0; __node < nr_node_ids; __node++) \
-		 if ((__n = get_node(__s, __node)))
-
-
-#if defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG)
 void dump_unreclaimable_slab(void);
 #else
 static inline void dump_unreclaimable_slab(void)
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 8d431193c273..238293b1dbe1 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -21,6 +21,7 @@
 #include <linux/swiotlb.h>
 #include <linux/proc_fs.h>
 #include <linux/debugfs.h>
+#include <linux/kmemleak.h>
 #include <linux/kasan.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
@@ -71,10 +72,8 @@ static int __init setup_slab_merge(char *str)
 	return 1;
 }
 
-#ifdef CONFIG_SLUB
 __setup_param("slub_nomerge", slub_nomerge, setup_slab_nomerge, 0);
 __setup_param("slub_merge", slub_merge, setup_slab_merge, 0);
-#endif
 
 __setup("slab_nomerge", setup_slab_nomerge);
 __setup("slab_merge", setup_slab_merge);
@@ -197,10 +196,6 @@ struct kmem_cache *find_mergeable(unsigned int size, unsigned int align,
 		if (s->size - size >= sizeof(void *))
 			continue;
 
-		if (IS_ENABLED(CONFIG_SLAB) && align &&
-			(align > s->align || s->align % align))
-			continue;
-
 		return s;
 	}
 	return NULL;
@@ -670,7 +665,7 @@ EXPORT_SYMBOL(random_kmalloc_seed);
  * of two cache sizes there. The size of larger slabs can be determined using
  * fls.
  */
-static u8 size_index[24] __ro_after_init = {
+u8 kmalloc_size_index[24] __ro_after_init = {
 	3,	/* 8 */
 	4,	/* 16 */
 	5,	/* 24 */
@@ -697,33 +692,6 @@ static u8 size_index[24] __ro_after_init = {
 	2	/* 192 */
 };
 
-static inline unsigned int size_index_elem(unsigned int bytes)
-{
-	return (bytes - 1) / 8;
-}
-
-/*
- * Find the kmem_cache structure that serves a given size of
- * allocation
- */
-struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags, unsigned long caller)
-{
-	unsigned int index;
-
-	if (size <= 192) {
-		if (!size)
-			return ZERO_SIZE_PTR;
-
-		index = size_index[size_index_elem(size)];
-	} else {
-		if (WARN_ON_ONCE(size > KMALLOC_MAX_CACHE_SIZE))
-			return NULL;
-		index = fls(size - 1);
-	}
-
-	return kmalloc_caches[kmalloc_type(flags, caller)][index];
-}
-
 size_t kmalloc_size_roundup(size_t size)
 {
 	if (size && size <= KMALLOC_MAX_CACHE_SIZE) {
@@ -848,9 +816,9 @@ void __init setup_kmalloc_cache_index_table(void)
 	for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) {
 		unsigned int elem = size_index_elem(i);
 
-		if (elem >= ARRAY_SIZE(size_index))
+		if (elem >= ARRAY_SIZE(kmalloc_size_index))
 			break;
-		size_index[elem] = KMALLOC_SHIFT_LOW;
+		kmalloc_size_index[elem] = KMALLOC_SHIFT_LOW;
 	}
 
 	if (KMALLOC_MIN_SIZE >= 64) {
@@ -859,7 +827,7 @@ void __init setup_kmalloc_cache_index_table(void)
 		 * is 64 byte.
 		 */
 		for (i = 64 + 8; i <= 96; i += 8)
-			size_index[size_index_elem(i)] = 7;
+			kmalloc_size_index[size_index_elem(i)] = 7;
 
 	}
 
@@ -870,7 +838,7 @@ void __init setup_kmalloc_cache_index_table(void)
 		 * instead.
 		 */
 		for (i = 128 + 8; i <= 192; i += 8)
-			size_index[size_index_elem(i)] = 8;
+			kmalloc_size_index[size_index_elem(i)] = 8;
 	}
 }
 
@@ -968,95 +936,6 @@ void __init create_kmalloc_caches(slab_flags_t flags)
 	slab_state = UP;
 }
 
-void free_large_kmalloc(struct folio *folio, void *object)
-{
-	unsigned int order = folio_order(folio);
-
-	if (WARN_ON_ONCE(order == 0))
-		pr_warn_once("object pointer: 0x%p\n", object);
-
-	kmemleak_free(object);
-	kasan_kfree_large(object);
-	kmsan_kfree_large(object);
-
-	mod_lruvec_page_state(folio_page(folio, 0), NR_SLAB_UNRECLAIMABLE_B,
-			      -(PAGE_SIZE << order));
-	__free_pages(folio_page(folio, 0), order);
-}
-
-static void *__kmalloc_large_node(size_t size, gfp_t flags, int node);
-static __always_inline
-void *__do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller)
-{
-	struct kmem_cache *s;
-	void *ret;
-
-	if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) {
-		ret = __kmalloc_large_node(size, flags, node);
-		trace_kmalloc(caller, ret, size,
-			      PAGE_SIZE << get_order(size), flags, node);
-		return ret;
-	}
-
-	s = kmalloc_slab(size, flags, caller);
-
-	if (unlikely(ZERO_OR_NULL_PTR(s)))
-		return s;
-
-	ret = __kmem_cache_alloc_node(s, flags, node, size, caller);
-	ret = kasan_kmalloc(s, ret, size, flags);
-	trace_kmalloc(caller, ret, size, s->size, flags, node);
-	return ret;
-}
-
-void *__kmalloc_node(size_t size, gfp_t flags, int node)
-{
-	return __do_kmalloc_node(size, flags, node, _RET_IP_);
-}
-EXPORT_SYMBOL(__kmalloc_node);
-
-void *__kmalloc(size_t size, gfp_t flags)
-{
-	return __do_kmalloc_node(size, flags, NUMA_NO_NODE, _RET_IP_);
-}
-EXPORT_SYMBOL(__kmalloc);
-
-void *__kmalloc_node_track_caller(size_t size, gfp_t flags,
-				  int node, unsigned long caller)
-{
-	return __do_kmalloc_node(size, flags, node, caller);
-}
-EXPORT_SYMBOL(__kmalloc_node_track_caller);
-
-/**
- * kfree - free previously allocated memory
- * @object: pointer returned by kmalloc() or kmem_cache_alloc()
- *
- * If @object is NULL, no operation is performed.
- */
-void kfree(const void *object)
-{
-	struct folio *folio;
-	struct slab *slab;
-	struct kmem_cache *s;
-
-	trace_kfree(_RET_IP_, object);
-
-	if (unlikely(ZERO_OR_NULL_PTR(object)))
-		return;
-
-	folio = virt_to_folio(object);
-	if (unlikely(!folio_test_slab(folio))) {
-		free_large_kmalloc(folio, (void *)object);
-		return;
-	}
-
-	slab = folio_slab(folio);
-	s = slab->slab_cache;
-	__kmem_cache_free(s, (void *)object, _RET_IP_);
-}
-EXPORT_SYMBOL(kfree);
-
 /**
  * __ksize -- Report full size of underlying allocation
  * @object: pointer to the object
@@ -1093,30 +972,6 @@ size_t __ksize(const void *object)
 	return slab_ksize(folio_slab(folio)->slab_cache);
 }
 
-void *kmalloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size)
-{
-	void *ret = __kmem_cache_alloc_node(s, gfpflags, NUMA_NO_NODE,
-					    size, _RET_IP_);
-
-	trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags, NUMA_NO_NODE);
-
-	ret = kasan_kmalloc(s, ret, size, gfpflags);
-	return ret;
-}
-EXPORT_SYMBOL(kmalloc_trace);
-
-void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags,
-			 int node, size_t size)
-{
-	void *ret = __kmem_cache_alloc_node(s, gfpflags, node, size, _RET_IP_);
-
-	trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags, node);
-
-	ret = kasan_kmalloc(s, ret, size, gfpflags);
-	return ret;
-}
-EXPORT_SYMBOL(kmalloc_node_trace);
-
 gfp_t kmalloc_fix_flags(gfp_t flags)
 {
 	gfp_t invalid_mask = flags & GFP_SLAB_BUG_MASK;
@@ -1129,57 +984,6 @@ gfp_t kmalloc_fix_flags(gfp_t flags)
 	return flags;
 }
 
-/*
- * To avoid unnecessary overhead, we pass through large allocation requests
- * directly to the page allocator. We use __GFP_COMP, because we will need to
- * know the allocation order to free the pages properly in kfree.
- */
-
-static void *__kmalloc_large_node(size_t size, gfp_t flags, int node)
-{
-	struct page *page;
-	void *ptr = NULL;
-	unsigned int order = get_order(size);
-
-	if (unlikely(flags & GFP_SLAB_BUG_MASK))
-		flags = kmalloc_fix_flags(flags);
-
-	flags |= __GFP_COMP;
-	page = alloc_pages_node(node, flags, order);
-	if (page) {
-		ptr = page_address(page);
-		mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B,
-				      PAGE_SIZE << order);
-	}
-
-	ptr = kasan_kmalloc_large(ptr, size, flags);
-	/* As ptr might get tagged, call kmemleak hook after KASAN. */
-	kmemleak_alloc(ptr, size, 1, flags);
-	kmsan_kmalloc_large(ptr, size, flags);
-
-	return ptr;
-}
-
-void *kmalloc_large(size_t size, gfp_t flags)
-{
-	void *ret = __kmalloc_large_node(size, flags, NUMA_NO_NODE);
-
-	trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << get_order(size),
-		      flags, NUMA_NO_NODE);
-	return ret;
-}
-EXPORT_SYMBOL(kmalloc_large);
-
-void *kmalloc_large_node(size_t size, gfp_t flags, int node)
-{
-	void *ret = __kmalloc_large_node(size, flags, node);
-
-	trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << get_order(size),
-		      flags, node);
-	return ret;
-}
-EXPORT_SYMBOL(kmalloc_large_node);
-
 #ifdef CONFIG_SLAB_FREELIST_RANDOM
 /* Randomize a generic freelist */
 static void freelist_randomize(unsigned int *list,
@@ -1222,12 +1026,8 @@ void cache_random_seq_destroy(struct kmem_cache *cachep)
 }
 #endif /* CONFIG_SLAB_FREELIST_RANDOM */
 
-#if defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG)
-#ifdef CONFIG_SLAB
-#define SLABINFO_RIGHTS (0600)
-#else
+#ifdef CONFIG_SLUB_DEBUG
 #define SLABINFO_RIGHTS (0400)
-#endif
 
 static void print_slabinfo_header(struct seq_file *m)
 {
@@ -1235,18 +1035,10 @@ static void print_slabinfo_header(struct seq_file *m)
 	 * Output format version, so at least we can change it
 	 * without _too_ many complaints.
 	 */
-#ifdef CONFIG_DEBUG_SLAB
-	seq_puts(m, "slabinfo - version: 2.1 (statistics)\n");
-#else
 	seq_puts(m, "slabinfo - version: 2.1\n");
-#endif
 	seq_puts(m, "# name            <active_objs> <num_objs> <objsize> <objperslab> <pagesperslab>");
 	seq_puts(m, " : tunables <limit> <batchcount> <sharedfactor>");
 	seq_puts(m, " : slabdata <active_slabs> <num_slabs> <sharedavail>");
-#ifdef CONFIG_DEBUG_SLAB
-	seq_puts(m, " : globalstat <listallocs> <maxobjs> <grown> <reaped> <error> <maxfreeable> <nodeallocs> <remotefrees> <alienoverflow>");
-	seq_puts(m, " : cpustat <allochit> <allocmiss> <freehit> <freemiss>");
-#endif
 	seq_putc(m, '\n');
 }
 
@@ -1370,7 +1162,7 @@ static int __init slab_proc_init(void)
 }
 module_init(slab_proc_init);
 
-#endif /* CONFIG_SLAB || CONFIG_SLUB_DEBUG */
+#endif /* CONFIG_SLUB_DEBUG */
 
 static __always_inline __realloc_size(2) void *
 __do_krealloc(const void *p, size_t new_size, gfp_t flags)
@@ -1488,10 +1280,3 @@ EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);
 EXPORT_TRACEPOINT_SYMBOL(kfree);
 EXPORT_TRACEPOINT_SYMBOL(kmem_cache_free);
 
-int should_failslab(struct kmem_cache *s, gfp_t gfpflags)
-{
-	if (__should_failslab(s, gfpflags))
-		return -ENOMEM;
-	return 0;
-}
-ALLOW_ERROR_INJECTION(should_failslab, ERRNO);
diff --git a/mm/slub.c b/mm/slub.c
index 63d281dfacdb..2ef88bbf56a3 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -34,6 +34,7 @@
 #include <linux/memory.h>
 #include <linux/math64.h>
 #include <linux/fault-inject.h>
+#include <linux/kmemleak.h>
 #include <linux/stacktrace.h>
 #include <linux/prefetch.h>
 #include <linux/memcontrol.h>
@@ -76,13 +77,28 @@
  *
  *   Frozen slabs
  *
- *   If a slab is frozen then it is exempt from list management. It is not
- *   on any list except per cpu partial list. The processor that froze the
+ *   If a slab is frozen then it is exempt from list management. It is
+ *   the cpu slab which is actively allocated from by the processor that
+ *   froze it and it is not on any list. The processor that froze the
  *   slab is the one who can perform list operations on the slab. Other
  *   processors may put objects onto the freelist but the processor that
  *   froze the slab is the only one that can retrieve the objects from the
  *   slab's freelist.
  *
+ *   CPU partial slabs
+ *
+ *   The partially empty slabs cached on the CPU partial list are used
+ *   for performance reasons, which speeds up the allocation process.
+ *   These slabs are not frozen, but are also exempt from list management,
+ *   by clearing the PG_workingset flag when moving out of the node
+ *   partial list. Please see __slab_free() for more details.
+ *
+ *   To sum up, the current scheme is:
+ *   - node partial slab: PG_Workingset && !frozen
+ *   - cpu partial slab: !PG_Workingset && !frozen
+ *   - cpu slab: !PG_Workingset && frozen
+ *   - full slab: !PG_Workingset && !frozen
+ *
  *   list_lock
  *
  *   The list_lock protects the partial and full list on each node and
@@ -204,9 +220,9 @@ DEFINE_STATIC_KEY_FALSE(slub_debug_enabled);
 
 /* Structure holding parameters for get_partial() call chain */
 struct partial_context {
-	struct slab **slab;
 	gfp_t flags;
 	unsigned int orig_size;
+	void *object;
 };
 
 static inline bool kmem_cache_debug(struct kmem_cache *s)
@@ -330,6 +346,60 @@ static void debugfs_slab_add(struct kmem_cache *);
 static inline void debugfs_slab_add(struct kmem_cache *s) { }
 #endif
 
+enum stat_item {
+	ALLOC_FASTPATH,		/* Allocation from cpu slab */
+	ALLOC_SLOWPATH,		/* Allocation by getting a new cpu slab */
+	FREE_FASTPATH,		/* Free to cpu slab */
+	FREE_SLOWPATH,		/* Freeing not to cpu slab */
+	FREE_FROZEN,		/* Freeing to frozen slab */
+	FREE_ADD_PARTIAL,	/* Freeing moves slab to partial list */
+	FREE_REMOVE_PARTIAL,	/* Freeing removes last object */
+	ALLOC_FROM_PARTIAL,	/* Cpu slab acquired from node partial list */
+	ALLOC_SLAB,		/* Cpu slab acquired from page allocator */
+	ALLOC_REFILL,		/* Refill cpu slab from slab freelist */
+	ALLOC_NODE_MISMATCH,	/* Switching cpu slab */
+	FREE_SLAB,		/* Slab freed to the page allocator */
+	CPUSLAB_FLUSH,		/* Abandoning of the cpu slab */
+	DEACTIVATE_FULL,	/* Cpu slab was full when deactivated */
+	DEACTIVATE_EMPTY,	/* Cpu slab was empty when deactivated */
+	DEACTIVATE_TO_HEAD,	/* Cpu slab was moved to the head of partials */
+	DEACTIVATE_TO_TAIL,	/* Cpu slab was moved to the tail of partials */
+	DEACTIVATE_REMOTE_FREES,/* Slab contained remotely freed objects */
+	DEACTIVATE_BYPASS,	/* Implicit deactivation */
+	ORDER_FALLBACK,		/* Number of times fallback was necessary */
+	CMPXCHG_DOUBLE_CPU_FAIL,/* Failures of this_cpu_cmpxchg_double */
+	CMPXCHG_DOUBLE_FAIL,	/* Failures of slab freelist update */
+	CPU_PARTIAL_ALLOC,	/* Used cpu partial on alloc */
+	CPU_PARTIAL_FREE,	/* Refill cpu partial on free */
+	CPU_PARTIAL_NODE,	/* Refill cpu partial from node partial */
+	CPU_PARTIAL_DRAIN,	/* Drain cpu partial to node partial */
+	NR_SLUB_STAT_ITEMS
+};
+
+#ifndef CONFIG_SLUB_TINY
+/*
+ * When changing the layout, make sure freelist and tid are still compatible
+ * with this_cpu_cmpxchg_double() alignment requirements.
+ */
+struct kmem_cache_cpu {
+	union {
+		struct {
+			void **freelist;	/* Pointer to next available object */
+			unsigned long tid;	/* Globally unique transaction id */
+		};
+		freelist_aba_t freelist_tid;
+	};
+	struct slab *slab;	/* The slab from which we are allocating */
+#ifdef CONFIG_SLUB_CPU_PARTIAL
+	struct slab *partial;	/* Partially allocated frozen slabs */
+#endif
+	local_lock_t lock;	/* Protects the fields above */
+#ifdef CONFIG_SLUB_STATS
+	unsigned int stat[NR_SLUB_STAT_ITEMS];
+#endif
+};
+#endif /* CONFIG_SLUB_TINY */
+
 static inline void stat(const struct kmem_cache *s, enum stat_item si)
 {
 #ifdef CONFIG_SLUB_STATS
@@ -341,6 +411,41 @@ static inline void stat(const struct kmem_cache *s, enum stat_item si)
 #endif
 }
 
+static inline
+void stat_add(const struct kmem_cache *s, enum stat_item si, int v)
+{
+#ifdef CONFIG_SLUB_STATS
+	raw_cpu_add(s->cpu_slab->stat[si], v);
+#endif
+}
+
+/*
+ * The slab lists for all objects.
+ */
+struct kmem_cache_node {
+	spinlock_t list_lock;
+	unsigned long nr_partial;
+	struct list_head partial;
+#ifdef CONFIG_SLUB_DEBUG
+	atomic_long_t nr_slabs;
+	atomic_long_t total_objects;
+	struct list_head full;
+#endif
+};
+
+static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
+{
+	return s->node[node];
+}
+
+/*
+ * Iterator over all nodes. The body will be executed for each node that has
+ * a kmem_cache_node structure allocated (which is true for all online nodes)
+ */
+#define for_each_kmem_cache_node(__s, __node, __n) \
+	for (__node = 0; __node < nr_node_ids; __node++) \
+		 if ((__n = get_node(__s, __node)))
+
 /*
  * Tracks for which NUMA nodes we have kmem_cache_nodes allocated.
  * Corresponds to node_state[N_NORMAL_MEMORY], but can temporarily
@@ -522,7 +627,7 @@ static __always_inline void slab_unlock(struct slab *slab)
 	struct page *page = slab_page(slab);
 
 	VM_BUG_ON_PAGE(PageTail(page), page);
-	__bit_spin_unlock(PG_locked, &page->flags);
+	bit_spin_unlock(PG_locked, &page->flags);
 }
 
 static inline bool
@@ -870,20 +975,20 @@ static inline void set_orig_size(struct kmem_cache *s,
 				void *object, unsigned int orig_size)
 {
 	void *p = kasan_reset_tag(object);
+	unsigned int kasan_meta_size;
 
 	if (!slub_debug_orig_size(s))
 		return;
 
-#ifdef CONFIG_KASAN_GENERIC
 	/*
-	 * KASAN could save its free meta data in object's data area at
-	 * offset 0, if the size is larger than 'orig_size', it will
-	 * overlap the data redzone in [orig_size+1, object_size], and
-	 * the check should be skipped.
+	 * KASAN can save its free meta data inside of the object at offset 0.
+	 * If this meta data size is larger than 'orig_size', it will overlap
+	 * the data redzone in [orig_size+1, object_size]. Thus, we adjust
+	 * 'orig_size' to be as at least as big as KASAN's meta data.
 	 */
-	if (kasan_metadata_size(s, true) > orig_size)
-		orig_size = s->object_size;
-#endif
+	kasan_meta_size = kasan_metadata_size(s, true);
+	if (kasan_meta_size > orig_size)
+		orig_size = kasan_meta_size;
 
 	p += get_info_end(s);
 	p += sizeof(struct track) * 2;
@@ -1192,7 +1297,7 @@ static int check_object(struct kmem_cache *s, struct slab *slab,
 {
 	u8 *p = object;
 	u8 *endobject = object + s->object_size;
-	unsigned int orig_size;
+	unsigned int orig_size, kasan_meta_size;
 
 	if (s->flags & SLAB_RED_ZONE) {
 		if (!check_bytes_and_report(s, slab, object, "Left Redzone",
@@ -1222,12 +1327,23 @@ static int check_object(struct kmem_cache *s, struct slab *slab,
 	}
 
 	if (s->flags & SLAB_POISON) {
-		if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON) &&
-			(!check_bytes_and_report(s, slab, p, "Poison", p,
-					POISON_FREE, s->object_size - 1) ||
-			 !check_bytes_and_report(s, slab, p, "End Poison",
-				p + s->object_size - 1, POISON_END, 1)))
-			return 0;
+		if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON)) {
+			/*
+			 * KASAN can save its free meta data inside of the
+			 * object at offset 0. Thus, skip checking the part of
+			 * the redzone that overlaps with the meta data.
+			 */
+			kasan_meta_size = kasan_metadata_size(s, true);
+			if (kasan_meta_size < s->object_size - 1 &&
+			    !check_bytes_and_report(s, slab, p, "Poison",
+					p + kasan_meta_size, POISON_FREE,
+					s->object_size - kasan_meta_size - 1))
+				return 0;
+			if (kasan_meta_size < s->object_size &&
+			    !check_bytes_and_report(s, slab, p, "End Poison",
+					p + s->object_size - 1, POISON_END, 1))
+				return 0;
+		}
 		/*
 		 * check_pad_bytes cleans up on its own.
 		 */
@@ -1759,12 +1875,214 @@ static bool freelist_corrupted(struct kmem_cache *s, struct slab *slab,
 #endif
 #endif /* CONFIG_SLUB_DEBUG */
 
+static inline enum node_stat_item cache_vmstat_idx(struct kmem_cache *s)
+{
+	return (s->flags & SLAB_RECLAIM_ACCOUNT) ?
+		NR_SLAB_RECLAIMABLE_B : NR_SLAB_UNRECLAIMABLE_B;
+}
+
+#ifdef CONFIG_MEMCG_KMEM
+static inline void memcg_free_slab_cgroups(struct slab *slab)
+{
+	kfree(slab_objcgs(slab));
+	slab->memcg_data = 0;
+}
+
+static inline size_t obj_full_size(struct kmem_cache *s)
+{
+	/*
+	 * For each accounted object there is an extra space which is used
+	 * to store obj_cgroup membership. Charge it too.
+	 */
+	return s->size + sizeof(struct obj_cgroup *);
+}
+
+/*
+ * Returns false if the allocation should fail.
+ */
+static bool __memcg_slab_pre_alloc_hook(struct kmem_cache *s,
+					struct list_lru *lru,
+					struct obj_cgroup **objcgp,
+					size_t objects, gfp_t flags)
+{
+	/*
+	 * The obtained objcg pointer is safe to use within the current scope,
+	 * defined by current task or set_active_memcg() pair.
+	 * obj_cgroup_get() is used to get a permanent reference.
+	 */
+	struct obj_cgroup *objcg = current_obj_cgroup();
+	if (!objcg)
+		return true;
+
+	if (lru) {
+		int ret;
+		struct mem_cgroup *memcg;
+
+		memcg = get_mem_cgroup_from_objcg(objcg);
+		ret = memcg_list_lru_alloc(memcg, lru, flags);
+		css_put(&memcg->css);
+
+		if (ret)
+			return false;
+	}
+
+	if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s)))
+		return false;
+
+	*objcgp = objcg;
+	return true;
+}
+
+/*
+ * Returns false if the allocation should fail.
+ */
+static __fastpath_inline
+bool memcg_slab_pre_alloc_hook(struct kmem_cache *s, struct list_lru *lru,
+			       struct obj_cgroup **objcgp, size_t objects,
+			       gfp_t flags)
+{
+	if (!memcg_kmem_online())
+		return true;
+
+	if (likely(!(flags & __GFP_ACCOUNT) && !(s->flags & SLAB_ACCOUNT)))
+		return true;
+
+	return likely(__memcg_slab_pre_alloc_hook(s, lru, objcgp, objects,
+						  flags));
+}
+
+static void __memcg_slab_post_alloc_hook(struct kmem_cache *s,
+					 struct obj_cgroup *objcg,
+					 gfp_t flags, size_t size,
+					 void **p)
+{
+	struct slab *slab;
+	unsigned long off;
+	size_t i;
+
+	flags &= gfp_allowed_mask;
+
+	for (i = 0; i < size; i++) {
+		if (likely(p[i])) {
+			slab = virt_to_slab(p[i]);
+
+			if (!slab_objcgs(slab) &&
+			    memcg_alloc_slab_cgroups(slab, s, flags, false)) {
+				obj_cgroup_uncharge(objcg, obj_full_size(s));
+				continue;
+			}
+
+			off = obj_to_index(s, slab, p[i]);
+			obj_cgroup_get(objcg);
+			slab_objcgs(slab)[off] = objcg;
+			mod_objcg_state(objcg, slab_pgdat(slab),
+					cache_vmstat_idx(s), obj_full_size(s));
+		} else {
+			obj_cgroup_uncharge(objcg, obj_full_size(s));
+		}
+	}
+}
+
+static __fastpath_inline
+void memcg_slab_post_alloc_hook(struct kmem_cache *s, struct obj_cgroup *objcg,
+				gfp_t flags, size_t size, void **p)
+{
+	if (likely(!memcg_kmem_online() || !objcg))
+		return;
+
+	return __memcg_slab_post_alloc_hook(s, objcg, flags, size, p);
+}
+
+static void __memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
+				   void **p, int objects,
+				   struct obj_cgroup **objcgs)
+{
+	for (int i = 0; i < objects; i++) {
+		struct obj_cgroup *objcg;
+		unsigned int off;
+
+		off = obj_to_index(s, slab, p[i]);
+		objcg = objcgs[off];
+		if (!objcg)
+			continue;
+
+		objcgs[off] = NULL;
+		obj_cgroup_uncharge(objcg, obj_full_size(s));
+		mod_objcg_state(objcg, slab_pgdat(slab), cache_vmstat_idx(s),
+				-obj_full_size(s));
+		obj_cgroup_put(objcg);
+	}
+}
+
+static __fastpath_inline
+void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p,
+			  int objects)
+{
+	struct obj_cgroup **objcgs;
+
+	if (!memcg_kmem_online())
+		return;
+
+	objcgs = slab_objcgs(slab);
+	if (likely(!objcgs))
+		return;
+
+	__memcg_slab_free_hook(s, slab, p, objects, objcgs);
+}
+
+static inline
+void memcg_slab_alloc_error_hook(struct kmem_cache *s, int objects,
+			   struct obj_cgroup *objcg)
+{
+	if (objcg)
+		obj_cgroup_uncharge(objcg, objects * obj_full_size(s));
+}
+#else /* CONFIG_MEMCG_KMEM */
+static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr)
+{
+	return NULL;
+}
+
+static inline void memcg_free_slab_cgroups(struct slab *slab)
+{
+}
+
+static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s,
+					     struct list_lru *lru,
+					     struct obj_cgroup **objcgp,
+					     size_t objects, gfp_t flags)
+{
+	return true;
+}
+
+static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
+					      struct obj_cgroup *objcg,
+					      gfp_t flags, size_t size,
+					      void **p)
+{
+}
+
+static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
+					void **p, int objects)
+{
+}
+
+static inline
+void memcg_slab_alloc_error_hook(struct kmem_cache *s, int objects,
+				 struct obj_cgroup *objcg)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
 /*
  * Hooks for other subsystems that check memory allocations. In a typical
  * production configuration these hooks all should produce no code at all.
+ *
+ * Returns true if freeing of the object can proceed, false if its reuse
+ * was delayed by KASAN quarantine, or it was returned to KFENCE.
  */
-static __always_inline bool slab_free_hook(struct kmem_cache *s,
-						void *x, bool init)
+static __always_inline
+bool slab_free_hook(struct kmem_cache *s, void *x, bool init)
 {
 	kmemleak_free_recursive(x, s->flags);
 	kmsan_slab_free(s, x);
@@ -1779,6 +2097,9 @@ static __always_inline bool slab_free_hook(struct kmem_cache *s,
 		__kcsan_check_access(x, s->object_size,
 				     KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT);
 
+	if (kfence_free(x))
+		return false;
+
 	/*
 	 * As memory initialization might be integrated into KASAN,
 	 * kasan_slab_free and initialization memset's must be
@@ -1787,7 +2108,7 @@ static __always_inline bool slab_free_hook(struct kmem_cache *s,
 	 * The initialization memset's clear the object and the metadata,
 	 * but don't touch the SLAB redzone.
 	 */
-	if (init) {
+	if (unlikely(init)) {
 		int rsize;
 
 		if (!kasan_has_integrated_init())
@@ -1797,7 +2118,7 @@ static __always_inline bool slab_free_hook(struct kmem_cache *s,
 		       s->size - s->inuse - rsize);
 	}
 	/* KASAN might put x into memory quarantine, delaying its reuse. */
-	return kasan_slab_free(s, x, init);
+	return !kasan_slab_free(s, x, init);
 }
 
 static inline bool slab_free_freelist_hook(struct kmem_cache *s,
@@ -1807,23 +2128,26 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s,
 
 	void *object;
 	void *next = *head;
-	void *old_tail = *tail ? *tail : *head;
+	void *old_tail = *tail;
+	bool init;
 
 	if (is_kfence_address(next)) {
 		slab_free_hook(s, next, false);
-		return true;
+		return false;
 	}
 
 	/* Head and tail of the reconstructed freelist */
 	*head = NULL;
 	*tail = NULL;
 
+	init = slab_want_init_on_free(s);
+
 	do {
 		object = next;
 		next = get_freepointer(s, object);
 
 		/* If object's reuse doesn't have to be delayed */
-		if (!slab_free_hook(s, object, slab_want_init_on_free(s))) {
+		if (likely(slab_free_hook(s, object, init))) {
 			/* Move object to the new freelist */
 			set_freepointer(s, object, *head);
 			*head = object;
@@ -1838,9 +2162,6 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s,
 		}
 	} while (object != old_tail);
 
-	if (*head == *tail)
-		*tail = NULL;
-
 	return *head != NULL;
 }
 
@@ -1849,9 +2170,9 @@ static void *setup_object(struct kmem_cache *s, void *object)
 	setup_object_debug(s, object);
 	object = kasan_init_slab_obj(s, object);
 	if (unlikely(s->ctor)) {
-		kasan_unpoison_object_data(s, object);
+		kasan_unpoison_new_object(s, object);
 		s->ctor(object);
-		kasan_poison_object_data(s, object);
+		kasan_poison_new_object(s, object);
 	}
 	return object;
 }
@@ -1866,11 +2187,7 @@ static inline struct slab *alloc_slab_page(gfp_t flags, int node,
 	struct slab *slab;
 	unsigned int order = oo_order(oo);
 
-	if (node == NUMA_NO_NODE)
-		folio = (struct folio *)alloc_pages(flags, order);
-	else
-		folio = (struct folio *)__alloc_pages_node(node, flags, order);
-
+	folio = (struct folio *)alloc_pages_node(node, flags, order);
 	if (!folio)
 		return NULL;
 
@@ -1993,6 +2310,26 @@ static inline bool shuffle_freelist(struct kmem_cache *s, struct slab *slab)
 }
 #endif /* CONFIG_SLAB_FREELIST_RANDOM */
 
+static __always_inline void account_slab(struct slab *slab, int order,
+					 struct kmem_cache *s, gfp_t gfp)
+{
+	if (memcg_kmem_online() && (s->flags & SLAB_ACCOUNT))
+		memcg_alloc_slab_cgroups(slab, s, gfp, true);
+
+	mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s),
+			    PAGE_SIZE << order);
+}
+
+static __always_inline void unaccount_slab(struct slab *slab, int order,
+					   struct kmem_cache *s)
+{
+	if (memcg_kmem_online())
+		memcg_free_slab_cgroups(slab);
+
+	mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s),
+			    -(PAGE_SIZE << order));
+}
+
 static struct slab *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 {
 	struct slab *slab;
@@ -2117,6 +2454,25 @@ static void discard_slab(struct kmem_cache *s, struct slab *slab)
 }
 
 /*
+ * SLUB reuses PG_workingset bit to keep track of whether it's on
+ * the per-node partial list.
+ */
+static inline bool slab_test_node_partial(const struct slab *slab)
+{
+	return folio_test_workingset((struct folio *)slab_folio(slab));
+}
+
+static inline void slab_set_node_partial(struct slab *slab)
+{
+	set_bit(PG_workingset, folio_flags(slab_folio(slab), 0));
+}
+
+static inline void slab_clear_node_partial(struct slab *slab)
+{
+	clear_bit(PG_workingset, folio_flags(slab_folio(slab), 0));
+}
+
+/*
  * Management of partially allocated slabs.
  */
 static inline void
@@ -2127,6 +2483,7 @@ __add_partial(struct kmem_cache_node *n, struct slab *slab, int tail)
 		list_add_tail(&slab->slab_list, &n->partial);
 	else
 		list_add(&slab->slab_list, &n->partial);
+	slab_set_node_partial(slab);
 }
 
 static inline void add_partial(struct kmem_cache_node *n,
@@ -2141,11 +2498,12 @@ static inline void remove_partial(struct kmem_cache_node *n,
 {
 	lockdep_assert_held(&n->list_lock);
 	list_del(&slab->slab_list);
+	slab_clear_node_partial(slab);
 	n->nr_partial--;
 }
 
 /*
- * Called only for kmem_cache_debug() caches instead of acquire_slab(), with a
+ * Called only for kmem_cache_debug() caches instead of remove_partial(), with a
  * slab from the n->partial list. Remove only a single object from the slab, do
  * the alloc_debug_processing() checks and leave the slab on the list, or move
  * it to full list if it was the last free object.
@@ -2213,51 +2571,6 @@ static void *alloc_single_from_new_slab(struct kmem_cache *s,
 	return object;
 }
 
-/*
- * Remove slab from the partial list, freeze it and
- * return the pointer to the freelist.
- *
- * Returns a list of objects or NULL if it fails.
- */
-static inline void *acquire_slab(struct kmem_cache *s,
-		struct kmem_cache_node *n, struct slab *slab,
-		int mode)
-{
-	void *freelist;
-	unsigned long counters;
-	struct slab new;
-
-	lockdep_assert_held(&n->list_lock);
-
-	/*
-	 * Zap the freelist and set the frozen bit.
-	 * The old freelist is the list of objects for the
-	 * per cpu allocation list.
-	 */
-	freelist = slab->freelist;
-	counters = slab->counters;
-	new.counters = counters;
-	if (mode) {
-		new.inuse = slab->objects;
-		new.freelist = NULL;
-	} else {
-		new.freelist = freelist;
-	}
-
-	VM_BUG_ON(new.frozen);
-	new.frozen = 1;
-
-	if (!__slab_update_freelist(s, slab,
-			freelist, counters,
-			new.freelist, new.counters,
-			"acquire_slab"))
-		return NULL;
-
-	remove_partial(n, slab);
-	WARN_ON(!freelist);
-	return freelist;
-}
-
 #ifdef CONFIG_SLUB_CPU_PARTIAL
 static void put_cpu_partial(struct kmem_cache *s, struct slab *slab, int drain);
 #else
@@ -2269,11 +2582,11 @@ static inline bool pfmemalloc_match(struct slab *slab, gfp_t gfpflags);
 /*
  * Try to allocate a partial slab from a specific node.
  */
-static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
-			      struct partial_context *pc)
+static struct slab *get_partial_node(struct kmem_cache *s,
+				     struct kmem_cache_node *n,
+				     struct partial_context *pc)
 {
-	struct slab *slab, *slab2;
-	void *object = NULL;
+	struct slab *slab, *slab2, *partial = NULL;
 	unsigned long flags;
 	unsigned int partial_slabs = 0;
 
@@ -2288,27 +2601,25 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
 
 	spin_lock_irqsave(&n->list_lock, flags);
 	list_for_each_entry_safe(slab, slab2, &n->partial, slab_list) {
-		void *t;
-
 		if (!pfmemalloc_match(slab, pc->flags))
 			continue;
 
 		if (IS_ENABLED(CONFIG_SLUB_TINY) || kmem_cache_debug(s)) {
-			object = alloc_single_from_partial(s, n, slab,
+			void *object = alloc_single_from_partial(s, n, slab,
 							pc->orig_size);
-			if (object)
+			if (object) {
+				partial = slab;
+				pc->object = object;
 				break;
+			}
 			continue;
 		}
 
-		t = acquire_slab(s, n, slab, object == NULL);
-		if (!t)
-			break;
+		remove_partial(n, slab);
 
-		if (!object) {
-			*pc->slab = slab;
+		if (!partial) {
+			partial = slab;
 			stat(s, ALLOC_FROM_PARTIAL);
-			object = t;
 		} else {
 			put_cpu_partial(s, slab, 0);
 			stat(s, CPU_PARTIAL_NODE);
@@ -2324,20 +2635,21 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
 
 	}
 	spin_unlock_irqrestore(&n->list_lock, flags);
-	return object;
+	return partial;
 }
 
 /*
  * Get a slab from somewhere. Search in increasing NUMA distances.
  */
-static void *get_any_partial(struct kmem_cache *s, struct partial_context *pc)
+static struct slab *get_any_partial(struct kmem_cache *s,
+				    struct partial_context *pc)
 {
 #ifdef CONFIG_NUMA
 	struct zonelist *zonelist;
 	struct zoneref *z;
 	struct zone *zone;
 	enum zone_type highest_zoneidx = gfp_zone(pc->flags);
-	void *object;
+	struct slab *slab;
 	unsigned int cpuset_mems_cookie;
 
 	/*
@@ -2372,8 +2684,8 @@ static void *get_any_partial(struct kmem_cache *s, struct partial_context *pc)
 
 			if (n && cpuset_zone_allowed(zone, pc->flags) &&
 					n->nr_partial > s->min_partial) {
-				object = get_partial_node(s, n, pc);
-				if (object) {
+				slab = get_partial_node(s, n, pc);
+				if (slab) {
 					/*
 					 * Don't check read_mems_allowed_retry()
 					 * here - if mems_allowed was updated in
@@ -2381,7 +2693,7 @@ static void *get_any_partial(struct kmem_cache *s, struct partial_context *pc)
 					 * between allocation and the cpuset
 					 * update
 					 */
-					return object;
+					return slab;
 				}
 			}
 		}
@@ -2393,17 +2705,18 @@ static void *get_any_partial(struct kmem_cache *s, struct partial_context *pc)
 /*
  * Get a partial slab, lock it and return it.
  */
-static void *get_partial(struct kmem_cache *s, int node, struct partial_context *pc)
+static struct slab *get_partial(struct kmem_cache *s, int node,
+				struct partial_context *pc)
 {
-	void *object;
+	struct slab *slab;
 	int searchnode = node;
 
 	if (node == NUMA_NO_NODE)
 		searchnode = numa_mem_id();
 
-	object = get_partial_node(s, get_node(s, searchnode), pc);
-	if (object || node != NUMA_NO_NODE)
-		return object;
+	slab = get_partial_node(s, get_node(s, searchnode), pc);
+	if (slab || node != NUMA_NO_NODE)
+		return slab;
 
 	return get_any_partial(s, pc);
 }
@@ -2492,10 +2805,8 @@ static void init_kmem_cache_cpus(struct kmem_cache *s)
 static void deactivate_slab(struct kmem_cache *s, struct slab *slab,
 			    void *freelist)
 {
-	enum slab_modes { M_NONE, M_PARTIAL, M_FREE, M_FULL_NOLIST };
 	struct kmem_cache_node *n = get_node(s, slab_nid(slab));
 	int free_delta = 0;
-	enum slab_modes mode = M_NONE;
 	void *nextfree, *freelist_iter, *freelist_tail;
 	int tail = DEACTIVATE_TO_HEAD;
 	unsigned long flags = 0;
@@ -2533,80 +2844,52 @@ static void deactivate_slab(struct kmem_cache *s, struct slab *slab,
 	/*
 	 * Stage two: Unfreeze the slab while splicing the per-cpu
 	 * freelist to the head of slab's freelist.
-	 *
-	 * Ensure that the slab is unfrozen while the list presence
-	 * reflects the actual number of objects during unfreeze.
-	 *
-	 * We first perform cmpxchg holding lock and insert to list
-	 * when it succeed. If there is mismatch then the slab is not
-	 * unfrozen and number of objects in the slab may have changed.
-	 * Then release lock and retry cmpxchg again.
 	 */
-redo:
-
-	old.freelist = READ_ONCE(slab->freelist);
-	old.counters = READ_ONCE(slab->counters);
-	VM_BUG_ON(!old.frozen);
-
-	/* Determine target state of the slab */
-	new.counters = old.counters;
-	if (freelist_tail) {
-		new.inuse -= free_delta;
-		set_freepointer(s, freelist_tail, old.freelist);
-		new.freelist = freelist;
-	} else
-		new.freelist = old.freelist;
-
-	new.frozen = 0;
+	do {
+		old.freelist = READ_ONCE(slab->freelist);
+		old.counters = READ_ONCE(slab->counters);
+		VM_BUG_ON(!old.frozen);
+
+		/* Determine target state of the slab */
+		new.counters = old.counters;
+		new.frozen = 0;
+		if (freelist_tail) {
+			new.inuse -= free_delta;
+			set_freepointer(s, freelist_tail, old.freelist);
+			new.freelist = freelist;
+		} else {
+			new.freelist = old.freelist;
+		}
+	} while (!slab_update_freelist(s, slab,
+		old.freelist, old.counters,
+		new.freelist, new.counters,
+		"unfreezing slab"));
 
+	/*
+	 * Stage three: Manipulate the slab list based on the updated state.
+	 */
 	if (!new.inuse && n->nr_partial >= s->min_partial) {
-		mode = M_FREE;
+		stat(s, DEACTIVATE_EMPTY);
+		discard_slab(s, slab);
+		stat(s, FREE_SLAB);
 	} else if (new.freelist) {
-		mode = M_PARTIAL;
-		/*
-		 * Taking the spinlock removes the possibility that
-		 * acquire_slab() will see a slab that is frozen
-		 */
 		spin_lock_irqsave(&n->list_lock, flags);
-	} else {
-		mode = M_FULL_NOLIST;
-	}
-
-
-	if (!slab_update_freelist(s, slab,
-				old.freelist, old.counters,
-				new.freelist, new.counters,
-				"unfreezing slab")) {
-		if (mode == M_PARTIAL)
-			spin_unlock_irqrestore(&n->list_lock, flags);
-		goto redo;
-	}
-
-
-	if (mode == M_PARTIAL) {
 		add_partial(n, slab, tail);
 		spin_unlock_irqrestore(&n->list_lock, flags);
 		stat(s, tail);
-	} else if (mode == M_FREE) {
-		stat(s, DEACTIVATE_EMPTY);
-		discard_slab(s, slab);
-		stat(s, FREE_SLAB);
-	} else if (mode == M_FULL_NOLIST) {
+	} else {
 		stat(s, DEACTIVATE_FULL);
 	}
 }
 
 #ifdef CONFIG_SLUB_CPU_PARTIAL
-static void __unfreeze_partials(struct kmem_cache *s, struct slab *partial_slab)
+static void __put_partials(struct kmem_cache *s, struct slab *partial_slab)
 {
 	struct kmem_cache_node *n = NULL, *n2 = NULL;
 	struct slab *slab, *slab_to_discard = NULL;
 	unsigned long flags = 0;
 
 	while (partial_slab) {
-		struct slab new;
-		struct slab old;
-
 		slab = partial_slab;
 		partial_slab = slab->next;
 
@@ -2619,23 +2902,7 @@ static void __unfreeze_partials(struct kmem_cache *s, struct slab *partial_slab)
 			spin_lock_irqsave(&n->list_lock, flags);
 		}
 
-		do {
-
-			old.freelist = slab->freelist;
-			old.counters = slab->counters;
-			VM_BUG_ON(!old.frozen);
-
-			new.counters = old.counters;
-			new.freelist = old.freelist;
-
-			new.frozen = 0;
-
-		} while (!__slab_update_freelist(s, slab,
-				old.freelist, old.counters,
-				new.freelist, new.counters,
-				"unfreezing slab"));
-
-		if (unlikely(!new.inuse && n->nr_partial >= s->min_partial)) {
+		if (unlikely(!slab->inuse && n->nr_partial >= s->min_partial)) {
 			slab->next = slab_to_discard;
 			slab_to_discard = slab;
 		} else {
@@ -2658,9 +2925,9 @@ static void __unfreeze_partials(struct kmem_cache *s, struct slab *partial_slab)
 }
 
 /*
- * Unfreeze all the cpu partial slabs.
+ * Put all the cpu partial slabs to the node partial list.
  */
-static void unfreeze_partials(struct kmem_cache *s)
+static void put_partials(struct kmem_cache *s)
 {
 	struct slab *partial_slab;
 	unsigned long flags;
@@ -2671,11 +2938,11 @@ static void unfreeze_partials(struct kmem_cache *s)
 	local_unlock_irqrestore(&s->cpu_slab->lock, flags);
 
 	if (partial_slab)
-		__unfreeze_partials(s, partial_slab);
+		__put_partials(s, partial_slab);
 }
 
-static void unfreeze_partials_cpu(struct kmem_cache *s,
-				  struct kmem_cache_cpu *c)
+static void put_partials_cpu(struct kmem_cache *s,
+			     struct kmem_cache_cpu *c)
 {
 	struct slab *partial_slab;
 
@@ -2683,12 +2950,11 @@ static void unfreeze_partials_cpu(struct kmem_cache *s,
 	c->partial = NULL;
 
 	if (partial_slab)
-		__unfreeze_partials(s, partial_slab);
+		__put_partials(s, partial_slab);
 }
 
 /*
- * Put a slab that was just frozen (in __slab_free|get_partial_node) into a
- * partial slab slot if available.
+ * Put a slab into a partial slab slot if available.
  *
  * If we did not find a slot then simply move all the partials to the
  * per node partial list.
@@ -2696,7 +2962,7 @@ static void unfreeze_partials_cpu(struct kmem_cache *s,
 static void put_cpu_partial(struct kmem_cache *s, struct slab *slab, int drain)
 {
 	struct slab *oldslab;
-	struct slab *slab_to_unfreeze = NULL;
+	struct slab *slab_to_put = NULL;
 	unsigned long flags;
 	int slabs = 0;
 
@@ -2711,7 +2977,7 @@ static void put_cpu_partial(struct kmem_cache *s, struct slab *slab, int drain)
 			 * per node partial list. Postpone the actual unfreezing
 			 * outside of the critical section.
 			 */
-			slab_to_unfreeze = oldslab;
+			slab_to_put = oldslab;
 			oldslab = NULL;
 		} else {
 			slabs = oldslab->slabs;
@@ -2727,17 +2993,17 @@ static void put_cpu_partial(struct kmem_cache *s, struct slab *slab, int drain)
 
 	local_unlock_irqrestore(&s->cpu_slab->lock, flags);
 
-	if (slab_to_unfreeze) {
-		__unfreeze_partials(s, slab_to_unfreeze);
+	if (slab_to_put) {
+		__put_partials(s, slab_to_put);
 		stat(s, CPU_PARTIAL_DRAIN);
 	}
 }
 
 #else	/* CONFIG_SLUB_CPU_PARTIAL */
 
-static inline void unfreeze_partials(struct kmem_cache *s) { }
-static inline void unfreeze_partials_cpu(struct kmem_cache *s,
-				  struct kmem_cache_cpu *c) { }
+static inline void put_partials(struct kmem_cache *s) { }
+static inline void put_partials_cpu(struct kmem_cache *s,
+				    struct kmem_cache_cpu *c) { }
 
 #endif	/* CONFIG_SLUB_CPU_PARTIAL */
 
@@ -2779,7 +3045,7 @@ static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
 		stat(s, CPUSLAB_FLUSH);
 	}
 
-	unfreeze_partials_cpu(s, c);
+	put_partials_cpu(s, c);
 }
 
 struct slub_flush_work {
@@ -2807,7 +3073,7 @@ static void flush_cpu_slab(struct work_struct *w)
 	if (c->slab)
 		flush_slab(s, c);
 
-	unfreeze_partials(s);
+	put_partials(s);
 }
 
 static bool has_cpu_slab(int cpu, struct kmem_cache *s)
@@ -3074,6 +3340,33 @@ static inline void *get_freelist(struct kmem_cache *s, struct slab *slab)
 }
 
 /*
+ * Freeze the partial slab and return the pointer to the freelist.
+ */
+static inline void *freeze_slab(struct kmem_cache *s, struct slab *slab)
+{
+	struct slab new;
+	unsigned long counters;
+	void *freelist;
+
+	do {
+		freelist = slab->freelist;
+		counters = slab->counters;
+
+		new.counters = counters;
+		VM_BUG_ON(new.frozen);
+
+		new.inuse = slab->objects;
+		new.frozen = 1;
+
+	} while (!slab_update_freelist(s, slab,
+		freelist, counters,
+		NULL, new.counters,
+		"freeze_slab"));
+
+	return freelist;
+}
+
+/*
  * Slow path. The lockless freelist is empty or we need to perform
  * debugging duties.
  *
@@ -3115,7 +3408,6 @@ reread_slab:
 			node = NUMA_NO_NODE;
 		goto new_slab;
 	}
-redo:
 
 	if (unlikely(!node_match(slab, node))) {
 		/*
@@ -3191,7 +3483,8 @@ deactivate_slab:
 
 new_slab:
 
-	if (slub_percpu_partial(c)) {
+#ifdef CONFIG_SLUB_CPU_PARTIAL
+	while (slub_percpu_partial(c)) {
 		local_lock_irqsave(&s->cpu_slab->lock, flags);
 		if (unlikely(c->slab)) {
 			local_unlock_irqrestore(&s->cpu_slab->lock, flags);
@@ -3203,21 +3496,45 @@ new_slab:
 			goto new_objects;
 		}
 
-		slab = c->slab = slub_percpu_partial(c);
+		slab = slub_percpu_partial(c);
 		slub_set_percpu_partial(c, slab);
 		local_unlock_irqrestore(&s->cpu_slab->lock, flags);
 		stat(s, CPU_PARTIAL_ALLOC);
-		goto redo;
+
+		if (unlikely(!node_match(slab, node) ||
+			     !pfmemalloc_match(slab, gfpflags))) {
+			slab->next = NULL;
+			__put_partials(s, slab);
+			continue;
+		}
+
+		freelist = freeze_slab(s, slab);
+		goto retry_load_slab;
 	}
+#endif
 
 new_objects:
 
 	pc.flags = gfpflags;
-	pc.slab = &slab;
 	pc.orig_size = orig_size;
-	freelist = get_partial(s, node, &pc);
-	if (freelist)
-		goto check_new_slab;
+	slab = get_partial(s, node, &pc);
+	if (slab) {
+		if (kmem_cache_debug(s)) {
+			freelist = pc.object;
+			/*
+			 * For debug caches here we had to go through
+			 * alloc_single_from_partial() so just store the
+			 * tracking info and return the object.
+			 */
+			if (s->flags & SLAB_STORE_USER)
+				set_track(s, freelist, TRACK_ALLOC, addr);
+
+			return freelist;
+		}
+
+		freelist = freeze_slab(s, slab);
+		goto retry_load_slab;
+	}
 
 	slub_put_cpu_ptr(s->cpu_slab);
 	slab = new_slab(s, gfpflags, node);
@@ -3253,20 +3570,6 @@ new_objects:
 
 	inc_slabs_node(s, slab_nid(slab), slab->objects);
 
-check_new_slab:
-
-	if (kmem_cache_debug(s)) {
-		/*
-		 * For debug caches here we had to go through
-		 * alloc_single_from_partial() so just store the tracking info
-		 * and return the object
-		 */
-		if (s->flags & SLAB_STORE_USER)
-			set_track(s, freelist, TRACK_ALLOC, addr);
-
-		return freelist;
-	}
-
 	if (unlikely(!pfmemalloc_match(slab, gfpflags))) {
 		/*
 		 * For !pfmemalloc_match() case we don't load freelist so that
@@ -3409,12 +3712,11 @@ static void *__slab_alloc_node(struct kmem_cache *s,
 	void *object;
 
 	pc.flags = gfpflags;
-	pc.slab = &slab;
 	pc.orig_size = orig_size;
-	object = get_partial(s, node, &pc);
+	slab = get_partial(s, node, &pc);
 
-	if (object)
-		return object;
+	if (slab)
+		return pc.object;
 
 	slab = new_slab(s, gfpflags, node);
 	if (unlikely(!slab)) {
@@ -3440,6 +3742,86 @@ static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s,
 			0, sizeof(void *));
 }
 
+noinline int should_failslab(struct kmem_cache *s, gfp_t gfpflags)
+{
+	if (__should_failslab(s, gfpflags))
+		return -ENOMEM;
+	return 0;
+}
+ALLOW_ERROR_INJECTION(should_failslab, ERRNO);
+
+static __fastpath_inline
+struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
+				       struct list_lru *lru,
+				       struct obj_cgroup **objcgp,
+				       size_t size, gfp_t flags)
+{
+	flags &= gfp_allowed_mask;
+
+	might_alloc(flags);
+
+	if (unlikely(should_failslab(s, flags)))
+		return NULL;
+
+	if (unlikely(!memcg_slab_pre_alloc_hook(s, lru, objcgp, size, flags)))
+		return NULL;
+
+	return s;
+}
+
+static __fastpath_inline
+void slab_post_alloc_hook(struct kmem_cache *s,	struct obj_cgroup *objcg,
+			  gfp_t flags, size_t size, void **p, bool init,
+			  unsigned int orig_size)
+{
+	unsigned int zero_size = s->object_size;
+	bool kasan_init = init;
+	size_t i;
+	gfp_t init_flags = flags & gfp_allowed_mask;
+
+	/*
+	 * For kmalloc object, the allocated memory size(object_size) is likely
+	 * larger than the requested size(orig_size). If redzone check is
+	 * enabled for the extra space, don't zero it, as it will be redzoned
+	 * soon. The redzone operation for this extra space could be seen as a
+	 * replacement of current poisoning under certain debug option, and
+	 * won't break other sanity checks.
+	 */
+	if (kmem_cache_debug_flags(s, SLAB_STORE_USER | SLAB_RED_ZONE) &&
+	    (s->flags & SLAB_KMALLOC))
+		zero_size = orig_size;
+
+	/*
+	 * When slub_debug is enabled, avoid memory initialization integrated
+	 * into KASAN and instead zero out the memory via the memset below with
+	 * the proper size. Otherwise, KASAN might overwrite SLUB redzones and
+	 * cause false-positive reports. This does not lead to a performance
+	 * penalty on production builds, as slub_debug is not intended to be
+	 * enabled there.
+	 */
+	if (__slub_debug_enabled())
+		kasan_init = false;
+
+	/*
+	 * As memory initialization might be integrated into KASAN,
+	 * kasan_slab_alloc and initialization memset must be
+	 * kept together to avoid discrepancies in behavior.
+	 *
+	 * As p[i] might get tagged, memset and kmemleak hook come after KASAN.
+	 */
+	for (i = 0; i < size; i++) {
+		p[i] = kasan_slab_alloc(s, p[i], init_flags, kasan_init);
+		if (p[i] && init && (!kasan_init ||
+				     !kasan_has_integrated_init()))
+			memset(p[i], 0, zero_size);
+		kmemleak_alloc_recursive(p[i], s->object_size, 1,
+					 s->flags, init_flags);
+		kmsan_slab_alloc(s, p[i], init_flags);
+	}
+
+	memcg_slab_post_alloc_hook(s, objcg, flags, size, p);
+}
+
 /*
  * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc)
  * have the fastpath folded into their functions. So no function call
@@ -3458,7 +3840,7 @@ static __fastpath_inline void *slab_alloc_node(struct kmem_cache *s, struct list
 	bool init = false;
 
 	s = slab_pre_alloc_hook(s, lru, &objcg, 1, gfpflags);
-	if (!s)
+	if (unlikely(!s))
 		return NULL;
 
 	object = kfence_alloc(s, orig_size, gfpflags);
@@ -3480,53 +3862,169 @@ out:
 	return object;
 }
 
-static __fastpath_inline void *slab_alloc(struct kmem_cache *s, struct list_lru *lru,
-		gfp_t gfpflags, unsigned long addr, size_t orig_size)
+void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
 {
-	return slab_alloc_node(s, lru, gfpflags, NUMA_NO_NODE, addr, orig_size);
+	void *ret = slab_alloc_node(s, NULL, gfpflags, NUMA_NO_NODE, _RET_IP_,
+				    s->object_size);
+
+	trace_kmem_cache_alloc(_RET_IP_, ret, s, gfpflags, NUMA_NO_NODE);
+
+	return ret;
 }
+EXPORT_SYMBOL(kmem_cache_alloc);
 
-static __fastpath_inline
-void *__kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru,
-			     gfp_t gfpflags)
+void *kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru,
+			   gfp_t gfpflags)
 {
-	void *ret = slab_alloc(s, lru, gfpflags, _RET_IP_, s->object_size);
+	void *ret = slab_alloc_node(s, lru, gfpflags, NUMA_NO_NODE, _RET_IP_,
+				    s->object_size);
 
 	trace_kmem_cache_alloc(_RET_IP_, ret, s, gfpflags, NUMA_NO_NODE);
 
 	return ret;
 }
+EXPORT_SYMBOL(kmem_cache_alloc_lru);
 
-void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
+/**
+ * kmem_cache_alloc_node - Allocate an object on the specified node
+ * @s: The cache to allocate from.
+ * @gfpflags: See kmalloc().
+ * @node: node number of the target node.
+ *
+ * Identical to kmem_cache_alloc but it will allocate memory on the given
+ * node, which can improve the performance for cpu bound structures.
+ *
+ * Fallback to other node is possible if __GFP_THISNODE is not set.
+ *
+ * Return: pointer to the new object or %NULL in case of error
+ */
+void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node)
 {
-	return __kmem_cache_alloc_lru(s, NULL, gfpflags);
+	void *ret = slab_alloc_node(s, NULL, gfpflags, node, _RET_IP_, s->object_size);
+
+	trace_kmem_cache_alloc(_RET_IP_, ret, s, gfpflags, node);
+
+	return ret;
 }
-EXPORT_SYMBOL(kmem_cache_alloc);
+EXPORT_SYMBOL(kmem_cache_alloc_node);
 
-void *kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru,
-			   gfp_t gfpflags)
+/*
+ * To avoid unnecessary overhead, we pass through large allocation requests
+ * directly to the page allocator. We use __GFP_COMP, because we will need to
+ * know the allocation order to free the pages properly in kfree.
+ */
+static void *__kmalloc_large_node(size_t size, gfp_t flags, int node)
 {
-	return __kmem_cache_alloc_lru(s, lru, gfpflags);
+	struct folio *folio;
+	void *ptr = NULL;
+	unsigned int order = get_order(size);
+
+	if (unlikely(flags & GFP_SLAB_BUG_MASK))
+		flags = kmalloc_fix_flags(flags);
+
+	flags |= __GFP_COMP;
+	folio = (struct folio *)alloc_pages_node(node, flags, order);
+	if (folio) {
+		ptr = folio_address(folio);
+		lruvec_stat_mod_folio(folio, NR_SLAB_UNRECLAIMABLE_B,
+				      PAGE_SIZE << order);
+	}
+
+	ptr = kasan_kmalloc_large(ptr, size, flags);
+	/* As ptr might get tagged, call kmemleak hook after KASAN. */
+	kmemleak_alloc(ptr, size, 1, flags);
+	kmsan_kmalloc_large(ptr, size, flags);
+
+	return ptr;
 }
-EXPORT_SYMBOL(kmem_cache_alloc_lru);
 
-void *__kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags,
-			      int node, size_t orig_size,
-			      unsigned long caller)
+void *kmalloc_large(size_t size, gfp_t flags)
 {
-	return slab_alloc_node(s, NULL, gfpflags, node,
-			       caller, orig_size);
+	void *ret = __kmalloc_large_node(size, flags, NUMA_NO_NODE);
+
+	trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << get_order(size),
+		      flags, NUMA_NO_NODE);
+	return ret;
 }
+EXPORT_SYMBOL(kmalloc_large);
 
-void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node)
+void *kmalloc_large_node(size_t size, gfp_t flags, int node)
 {
-	void *ret = slab_alloc_node(s, NULL, gfpflags, node, _RET_IP_, s->object_size);
+	void *ret = __kmalloc_large_node(size, flags, node);
 
-	trace_kmem_cache_alloc(_RET_IP_, ret, s, gfpflags, node);
+	trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << get_order(size),
+		      flags, node);
+	return ret;
+}
+EXPORT_SYMBOL(kmalloc_large_node);
 
+static __always_inline
+void *__do_kmalloc_node(size_t size, gfp_t flags, int node,
+			unsigned long caller)
+{
+	struct kmem_cache *s;
+	void *ret;
+
+	if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) {
+		ret = __kmalloc_large_node(size, flags, node);
+		trace_kmalloc(caller, ret, size,
+			      PAGE_SIZE << get_order(size), flags, node);
+		return ret;
+	}
+
+	if (unlikely(!size))
+		return ZERO_SIZE_PTR;
+
+	s = kmalloc_slab(size, flags, caller);
+
+	ret = slab_alloc_node(s, NULL, flags, node, caller, size);
+	ret = kasan_kmalloc(s, ret, size, flags);
+	trace_kmalloc(caller, ret, size, s->size, flags, node);
 	return ret;
 }
-EXPORT_SYMBOL(kmem_cache_alloc_node);
+
+void *__kmalloc_node(size_t size, gfp_t flags, int node)
+{
+	return __do_kmalloc_node(size, flags, node, _RET_IP_);
+}
+EXPORT_SYMBOL(__kmalloc_node);
+
+void *__kmalloc(size_t size, gfp_t flags)
+{
+	return __do_kmalloc_node(size, flags, NUMA_NO_NODE, _RET_IP_);
+}
+EXPORT_SYMBOL(__kmalloc);
+
+void *__kmalloc_node_track_caller(size_t size, gfp_t flags,
+				  int node, unsigned long caller)
+{
+	return __do_kmalloc_node(size, flags, node, caller);
+}
+EXPORT_SYMBOL(__kmalloc_node_track_caller);
+
+void *kmalloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size)
+{
+	void *ret = slab_alloc_node(s, NULL, gfpflags, NUMA_NO_NODE,
+					    _RET_IP_, size);
+
+	trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags, NUMA_NO_NODE);
+
+	ret = kasan_kmalloc(s, ret, size, gfpflags);
+	return ret;
+}
+EXPORT_SYMBOL(kmalloc_trace);
+
+void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags,
+			 int node, size_t size)
+{
+	void *ret = slab_alloc_node(s, NULL, gfpflags, node, _RET_IP_, size);
+
+	trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags, node);
+
+	ret = kasan_kmalloc(s, ret, size, gfpflags);
+	return ret;
+}
+EXPORT_SYMBOL(kmalloc_node_trace);
 
 static noinline void free_to_partial_list(
 	struct kmem_cache *s, struct slab *slab,
@@ -3608,12 +4106,10 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab,
 	unsigned long counters;
 	struct kmem_cache_node *n = NULL;
 	unsigned long flags;
+	bool on_node_partial;
 
 	stat(s, FREE_SLOWPATH);
 
-	if (kfence_free(head))
-		return;
-
 	if (IS_ENABLED(CONFIG_SLUB_TINY) || kmem_cache_debug(s)) {
 		free_to_partial_list(s, slab, head, tail, cnt, addr);
 		return;
@@ -3631,18 +4127,8 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab,
 		was_frozen = new.frozen;
 		new.inuse -= cnt;
 		if ((!new.inuse || !prior) && !was_frozen) {
-
-			if (kmem_cache_has_cpu_partial(s) && !prior) {
-
-				/*
-				 * Slab was on no list before and will be
-				 * partially empty
-				 * We can defer the list move and instead
-				 * freeze it.
-				 */
-				new.frozen = 1;
-
-			} else { /* Needs to be taken off a list */
+			/* Needs to be taken off a list */
+			if (!kmem_cache_has_cpu_partial(s) || prior) {
 
 				n = get_node(s, slab_nid(slab));
 				/*
@@ -3655,6 +4141,7 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab,
 				 */
 				spin_lock_irqsave(&n->list_lock, flags);
 
+				on_node_partial = slab_test_node_partial(slab);
 			}
 		}
 
@@ -3671,9 +4158,9 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab,
 			 * activity can be necessary.
 			 */
 			stat(s, FREE_FROZEN);
-		} else if (new.frozen) {
+		} else if (kmem_cache_has_cpu_partial(s) && !prior) {
 			/*
-			 * If we just froze the slab then put it onto the
+			 * If we started with a full slab then put it onto the
 			 * per cpu partial list.
 			 */
 			put_cpu_partial(s, slab, 1);
@@ -3683,6 +4170,15 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab,
 		return;
 	}
 
+	/*
+	 * This slab was partially empty but not on the per-node partial list,
+	 * in which case we shouldn't manipulate its list, just return.
+	 */
+	if (prior && !on_node_partial) {
+		spin_unlock_irqrestore(&n->list_lock, flags);
+		return;
+	}
+
 	if (unlikely(!new.inuse && n->nr_partial >= s->min_partial))
 		goto slab_empty;
 
@@ -3735,7 +4231,6 @@ static __always_inline void do_slab_free(struct kmem_cache *s,
 				struct slab *slab, void *head, void *tail,
 				int cnt, unsigned long addr)
 {
-	void *tail_obj = tail ? : head;
 	struct kmem_cache_cpu *c;
 	unsigned long tid;
 	void **freelist;
@@ -3754,14 +4249,14 @@ redo:
 	barrier();
 
 	if (unlikely(slab != c->slab)) {
-		__slab_free(s, slab, head, tail_obj, cnt, addr);
+		__slab_free(s, slab, head, tail, cnt, addr);
 		return;
 	}
 
 	if (USE_LOCKLESS_FAST_PATH()) {
 		freelist = READ_ONCE(c->freelist);
 
-		set_freepointer(s, tail_obj, freelist);
+		set_freepointer(s, tail, freelist);
 
 		if (unlikely(!__update_cpu_freelist_fast(s, freelist, head, tid))) {
 			note_cmpxchg_failure("slab_free", s, tid);
@@ -3778,60 +4273,143 @@ redo:
 		tid = c->tid;
 		freelist = c->freelist;
 
-		set_freepointer(s, tail_obj, freelist);
+		set_freepointer(s, tail, freelist);
 		c->freelist = head;
 		c->tid = next_tid(tid);
 
 		local_unlock(&s->cpu_slab->lock);
 	}
-	stat(s, FREE_FASTPATH);
+	stat_add(s, FREE_FASTPATH, cnt);
 }
 #else /* CONFIG_SLUB_TINY */
 static void do_slab_free(struct kmem_cache *s,
 				struct slab *slab, void *head, void *tail,
 				int cnt, unsigned long addr)
 {
-	void *tail_obj = tail ? : head;
-
-	__slab_free(s, slab, head, tail_obj, cnt, addr);
+	__slab_free(s, slab, head, tail, cnt, addr);
 }
 #endif /* CONFIG_SLUB_TINY */
 
-static __fastpath_inline void slab_free(struct kmem_cache *s, struct slab *slab,
-				      void *head, void *tail, void **p, int cnt,
-				      unsigned long addr)
+static __fastpath_inline
+void slab_free(struct kmem_cache *s, struct slab *slab, void *object,
+	       unsigned long addr)
+{
+	memcg_slab_free_hook(s, slab, &object, 1);
+
+	if (likely(slab_free_hook(s, object, slab_want_init_on_free(s))))
+		do_slab_free(s, slab, object, object, 1, addr);
+}
+
+static __fastpath_inline
+void slab_free_bulk(struct kmem_cache *s, struct slab *slab, void *head,
+		    void *tail, void **p, int cnt, unsigned long addr)
 {
 	memcg_slab_free_hook(s, slab, p, cnt);
 	/*
 	 * With KASAN enabled slab_free_freelist_hook modifies the freelist
 	 * to remove objects, whose reuse must be delayed.
 	 */
-	if (slab_free_freelist_hook(s, &head, &tail, &cnt))
+	if (likely(slab_free_freelist_hook(s, &head, &tail, &cnt)))
 		do_slab_free(s, slab, head, tail, cnt, addr);
 }
 
 #ifdef CONFIG_KASAN_GENERIC
 void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr)
 {
-	do_slab_free(cache, virt_to_slab(x), x, NULL, 1, addr);
+	do_slab_free(cache, virt_to_slab(x), x, x, 1, addr);
 }
 #endif
 
-void __kmem_cache_free(struct kmem_cache *s, void *x, unsigned long caller)
+static inline struct kmem_cache *virt_to_cache(const void *obj)
 {
-	slab_free(s, virt_to_slab(x), x, NULL, &x, 1, caller);
+	struct slab *slab;
+
+	slab = virt_to_slab(obj);
+	if (WARN_ONCE(!slab, "%s: Object is not a Slab page!\n", __func__))
+		return NULL;
+	return slab->slab_cache;
 }
 
+static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
+{
+	struct kmem_cache *cachep;
+
+	if (!IS_ENABLED(CONFIG_SLAB_FREELIST_HARDENED) &&
+	    !kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS))
+		return s;
+
+	cachep = virt_to_cache(x);
+	if (WARN(cachep && cachep != s,
+		 "%s: Wrong slab cache. %s but object is from %s\n",
+		 __func__, s->name, cachep->name))
+		print_tracking(cachep, x);
+	return cachep;
+}
+
+/**
+ * kmem_cache_free - Deallocate an object
+ * @s: The cache the allocation was from.
+ * @x: The previously allocated object.
+ *
+ * Free an object which was previously allocated from this
+ * cache.
+ */
 void kmem_cache_free(struct kmem_cache *s, void *x)
 {
 	s = cache_from_obj(s, x);
 	if (!s)
 		return;
 	trace_kmem_cache_free(_RET_IP_, x, s);
-	slab_free(s, virt_to_slab(x), x, NULL, &x, 1, _RET_IP_);
+	slab_free(s, virt_to_slab(x), x, _RET_IP_);
 }
 EXPORT_SYMBOL(kmem_cache_free);
 
+static void free_large_kmalloc(struct folio *folio, void *object)
+{
+	unsigned int order = folio_order(folio);
+
+	if (WARN_ON_ONCE(order == 0))
+		pr_warn_once("object pointer: 0x%p\n", object);
+
+	kmemleak_free(object);
+	kasan_kfree_large(object);
+	kmsan_kfree_large(object);
+
+	lruvec_stat_mod_folio(folio, NR_SLAB_UNRECLAIMABLE_B,
+			      -(PAGE_SIZE << order));
+	folio_put(folio);
+}
+
+/**
+ * kfree - free previously allocated memory
+ * @object: pointer returned by kmalloc() or kmem_cache_alloc()
+ *
+ * If @object is NULL, no operation is performed.
+ */
+void kfree(const void *object)
+{
+	struct folio *folio;
+	struct slab *slab;
+	struct kmem_cache *s;
+	void *x = (void *)object;
+
+	trace_kfree(_RET_IP_, object);
+
+	if (unlikely(ZERO_OR_NULL_PTR(object)))
+		return;
+
+	folio = virt_to_folio(object);
+	if (unlikely(!folio_test_slab(folio))) {
+		free_large_kmalloc(folio, (void *)object);
+		return;
+	}
+
+	slab = folio_slab(folio);
+	s = slab->slab_cache;
+	slab_free(s, slab, x, _RET_IP_);
+}
+EXPORT_SYMBOL(kfree);
+
 struct detached_freelist {
 	struct slab *slab;
 	void *tail;
@@ -3911,6 +4489,27 @@ int build_detached_freelist(struct kmem_cache *s, size_t size,
 	return same;
 }
 
+/*
+ * Internal bulk free of objects that were not initialised by the post alloc
+ * hooks and thus should not be processed by the free hooks
+ */
+static void __kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
+{
+	if (!size)
+		return;
+
+	do {
+		struct detached_freelist df;
+
+		size = build_detached_freelist(s, size, p, &df);
+		if (!df.slab)
+			continue;
+
+		do_slab_free(df.s, df.slab, df.freelist, df.tail, df.cnt,
+			     _RET_IP_);
+	} while (likely(size));
+}
+
 /* Note that interrupts must be enabled when calling this function. */
 void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
 {
@@ -3924,15 +4523,16 @@ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
 		if (!df.slab)
 			continue;
 
-		slab_free(df.s, df.slab, df.freelist, df.tail, &p[size], df.cnt,
-			  _RET_IP_);
+		slab_free_bulk(df.s, df.slab, df.freelist, df.tail, &p[size],
+			       df.cnt, _RET_IP_);
 	} while (likely(size));
 }
 EXPORT_SYMBOL(kmem_cache_free_bulk);
 
 #ifndef CONFIG_SLUB_TINY
-static inline int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags,
-			size_t size, void **p, struct obj_cgroup *objcg)
+static inline
+int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
+			    void **p)
 {
 	struct kmem_cache_cpu *c;
 	unsigned long irqflags;
@@ -3986,6 +4586,7 @@ static inline int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags,
 		c->freelist = get_freepointer(s, object);
 		p[i] = object;
 		maybe_wipe_obj_freeptr(s, p[i]);
+		stat(s, ALLOC_FASTPATH);
 	}
 	c->tid = next_tid(c->tid);
 	local_unlock_irqrestore(&s->cpu_slab->lock, irqflags);
@@ -3995,14 +4596,13 @@ static inline int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags,
 
 error:
 	slub_put_cpu_ptr(s->cpu_slab);
-	slab_post_alloc_hook(s, objcg, flags, i, p, false, s->object_size);
-	kmem_cache_free_bulk(s, i, p);
+	__kmem_cache_free_bulk(s, i, p);
 	return 0;
 
 }
 #else /* CONFIG_SLUB_TINY */
 static int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags,
-			size_t size, void **p, struct obj_cgroup *objcg)
+				   size_t size, void **p)
 {
 	int i;
 
@@ -4025,8 +4625,7 @@ static int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags,
 	return i;
 
 error:
-	slab_post_alloc_hook(s, objcg, flags, i, p, false, s->object_size);
-	kmem_cache_free_bulk(s, i, p);
+	__kmem_cache_free_bulk(s, i, p);
 	return 0;
 }
 #endif /* CONFIG_SLUB_TINY */
@@ -4046,15 +4645,19 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 	if (unlikely(!s))
 		return 0;
 
-	i = __kmem_cache_alloc_bulk(s, flags, size, p, objcg);
+	i = __kmem_cache_alloc_bulk(s, flags, size, p);
 
 	/*
 	 * memcg and kmem_cache debug support and memory initialization.
 	 * Done outside of the IRQ disabled fastpath loop.
 	 */
-	if (i != 0)
+	if (likely(i != 0)) {
 		slab_post_alloc_hook(s, objcg, flags, size, p,
 			slab_want_init_on_alloc(flags, s), s->object_size);
+	} else {
+		memcg_slab_alloc_error_hook(s, size, objcg);
+	}
+
 	return i;
 }
 EXPORT_SYMBOL(kmem_cache_alloc_bulk);
@@ -4187,7 +4790,7 @@ static inline int calculate_order(unsigned int size)
 	 * Doh this slab cannot be placed using slub_max_order.
 	 */
 	order = get_order(size);
-	if (order <= MAX_ORDER)
+	if (order <= MAX_PAGE_ORDER)
 		return order;
 	return -ENOSYS;
 }
@@ -4715,7 +5318,7 @@ __setup("slub_min_order=", setup_slub_min_order);
 static int __init setup_slub_max_order(char *str)
 {
 	get_option(&str, (int *)&slub_max_order);
-	slub_max_order = min_t(unsigned int, slub_max_order, MAX_ORDER);
+	slub_max_order = min_t(unsigned int, slub_max_order, MAX_PAGE_ORDER);
 
 	if (slub_min_order > slub_max_order)
 		slub_min_order = slub_max_order;
@@ -4831,6 +5434,7 @@ static int __kmem_cache_do_shrink(struct kmem_cache *s)
 
 			if (free == slab->objects) {
 				list_move(&slab->slab_list, &discard);
+				slab_clear_node_partial(slab);
 				n->nr_partial--;
 				dec_slabs_node(s, node, slab->objects);
 			} else if (free <= SHRINK_PROMOTE_MAX)
diff --git a/mm/sparse.c b/mm/sparse.c
index 77d91e565045..338cf946dee8 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -792,6 +792,13 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
 		unsigned long section_nr = pfn_to_section_nr(pfn);
 
 		/*
+		 * Mark the section invalid so that valid_section()
+		 * return false. This prevents code from dereferencing
+		 * ms->usage array.
+		 */
+		ms->section_mem_map &= ~SECTION_HAS_MEM_MAP;
+
+		/*
 		 * When removing an early section, the usage map is kept (as the
 		 * usage maps of other sections fall into the same page). It
 		 * will be re-used when re-adding the section - which is then no
@@ -799,16 +806,10 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
 		 * was allocated during boot.
 		 */
 		if (!PageReserved(virt_to_page(ms->usage))) {
-			kfree(ms->usage);
-			ms->usage = NULL;
+			kfree_rcu(ms->usage, rcu);
+			WRITE_ONCE(ms->usage, NULL);
 		}
 		memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
-		/*
-		 * Mark the section invalid so that valid_section()
-		 * return false. This prevents code from dereferencing
-		 * ms->usage array.
-		 */
-		ms->section_mem_map &= ~SECTION_HAS_MEM_MAP;
 	}
 
 	/*
diff --git a/mm/swap.h b/mm/swap.h
index 73c332ee4d91..758c46ca671e 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -10,7 +10,8 @@ struct mempolicy;
 /* linux/mm/page_io.c */
 int sio_pool_init(void);
 struct swap_iocb;
-void swap_readpage(struct page *page, bool do_poll, struct swap_iocb **plug);
+void swap_read_folio(struct folio *folio, bool do_poll,
+		struct swap_iocb **plug);
 void __swap_read_unplug(struct swap_iocb *plug);
 static inline void swap_read_unplug(struct swap_iocb *plug)
 {
@@ -19,7 +20,7 @@ static inline void swap_read_unplug(struct swap_iocb *plug)
 }
 void swap_write_unplug(struct swap_iocb *sio);
 int swap_writepage(struct page *page, struct writeback_control *wbc);
-void __swap_writepage(struct page *page, struct writeback_control *wbc);
+void __swap_writepage(struct folio *folio, struct writeback_control *wbc);
 
 /* linux/mm/swap_state.c */
 /* One swap address space for each 64M swap space */
@@ -45,25 +46,24 @@ struct folio *swap_cache_get_folio(swp_entry_t entry,
 struct folio *filemap_get_incore_folio(struct address_space *mapping,
 		pgoff_t index);
 
-struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
-				   struct vm_area_struct *vma,
-				   unsigned long addr,
-				   struct swap_iocb **plug);
-struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
-				     struct mempolicy *mpol, pgoff_t ilx,
-				     bool *new_page_allocated);
-struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag,
-				    struct mempolicy *mpol, pgoff_t ilx);
+struct folio *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
+		struct vm_area_struct *vma, unsigned long addr,
+		struct swap_iocb **plug);
+struct folio *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_flags,
+		struct mempolicy *mpol, pgoff_t ilx, bool *new_page_allocated,
+		bool skip_if_exists);
+struct folio *swap_cluster_readahead(swp_entry_t entry, gfp_t flag,
+		struct mempolicy *mpol, pgoff_t ilx);
 struct page *swapin_readahead(swp_entry_t entry, gfp_t flag,
 			      struct vm_fault *vmf);
 
 static inline unsigned int folio_swap_flags(struct folio *folio)
 {
-	return page_swap_info(&folio->page)->flags;
+	return swp_swap_info(folio->swap)->flags;
 }
 #else /* CONFIG_SWAP */
 struct swap_iocb;
-static inline void swap_readpage(struct page *page, bool do_poll,
+static inline void swap_read_folio(struct folio *folio, bool do_poll,
 		struct swap_iocb **plug)
 {
 }
@@ -80,7 +80,7 @@ static inline void show_swap_cache_info(void)
 {
 }
 
-static inline struct page *swap_cluster_readahead(swp_entry_t entry,
+static inline struct folio *swap_cluster_readahead(swp_entry_t entry,
 			gfp_t gfp_mask, struct mempolicy *mpol, pgoff_t ilx)
 {
 	return NULL;
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 85d9e5806a6a..e671266ad772 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -410,13 +410,12 @@ struct folio *filemap_get_incore_folio(struct address_space *mapping,
 	return folio;
 }
 
-struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
-				     struct mempolicy *mpol, pgoff_t ilx,
-				     bool *new_page_allocated)
+struct folio *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
+		struct mempolicy *mpol, pgoff_t ilx, bool *new_page_allocated,
+		bool skip_if_exists)
 {
 	struct swap_info_struct *si;
 	struct folio *folio;
-	struct page *page;
 	void *shadow = NULL;
 
 	*new_page_allocated = false;
@@ -433,10 +432,8 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		 */
 		folio = filemap_get_folio(swap_address_space(entry),
 						swp_offset(entry));
-		if (!IS_ERR(folio)) {
-			page = folio_file_page(folio, swp_offset(entry));
-			goto got_page;
-		}
+		if (!IS_ERR(folio))
+			goto got_folio;
 
 		/*
 		 * Just skip read ahead for unused swap slot.
@@ -450,7 +447,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 			goto fail_put_swap;
 
 		/*
-		 * Get a new page to read into from swap.  Allocate it now,
+		 * Get a new folio to read into from swap.  Allocate it now,
 		 * before marking swap_map SWAP_HAS_CACHE, when -EEXIST will
 		 * cause any racers to loop around until we add it to cache.
 		 */
@@ -471,17 +468,28 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 			goto fail_put_swap;
 
 		/*
+		 * Protect against a recursive call to __read_swap_cache_async()
+		 * on the same entry waiting forever here because SWAP_HAS_CACHE
+		 * is set but the folio is not the swap cache yet. This can
+		 * happen today if mem_cgroup_swapin_charge_folio() below
+		 * triggers reclaim through zswap, which may call
+		 * __read_swap_cache_async() in the writeback path.
+		 */
+		if (skip_if_exists)
+			goto fail_put_swap;
+
+		/*
 		 * We might race against __delete_from_swap_cache(), and
 		 * stumble across a swap_map entry whose SWAP_HAS_CACHE
 		 * has not yet been cleared.  Or race against another
 		 * __read_swap_cache_async(), which has set SWAP_HAS_CACHE
-		 * in swap_map, but not yet added its page to swap cache.
+		 * in swap_map, but not yet added its folio to swap cache.
 		 */
 		schedule_timeout_uninterruptible(1);
 	}
 
 	/*
-	 * The swap entry is ours to swap in. Prepare the new page.
+	 * The swap entry is ours to swap in. Prepare the new folio.
 	 */
 
 	__folio_set_locked(folio);
@@ -502,10 +510,9 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 	/* Caller will initiate read into locked folio */
 	folio_add_lru(folio);
 	*new_page_allocated = true;
-	page = &folio->page;
-got_page:
+got_folio:
 	put_swap_device(si);
-	return page;
+	return folio;
 
 fail_unlock:
 	put_swap_folio(folio, entry);
@@ -523,26 +530,26 @@ fail_put_swap:
  * the swap entry is no longer in use.
  *
  * get/put_swap_device() aren't needed to call this function, because
- * __read_swap_cache_async() call them and swap_readpage() holds the
+ * __read_swap_cache_async() call them and swap_read_folio() holds the
  * swap cache folio lock.
  */
-struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
-				   struct vm_area_struct *vma,
-				   unsigned long addr, struct swap_iocb **plug)
+struct folio *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
+		struct vm_area_struct *vma, unsigned long addr,
+		struct swap_iocb **plug)
 {
 	bool page_allocated;
 	struct mempolicy *mpol;
 	pgoff_t ilx;
-	struct page *page;
+	struct folio *folio;
 
 	mpol = get_vma_policy(vma, addr, 0, &ilx);
-	page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
-					&page_allocated);
+	folio = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
+					&page_allocated, false);
 	mpol_cond_put(mpol);
 
 	if (page_allocated)
-		swap_readpage(page, false, plug);
-	return page;
+		swap_read_folio(folio, false, plug);
+	return folio;
 }
 
 static unsigned int __swapin_nr_pages(unsigned long prev_offset,
@@ -613,7 +620,7 @@ static unsigned long swapin_nr_pages(unsigned long offset)
  * @mpol: NUMA memory allocation policy to be applied
  * @ilx: NUMA interleave index, for use only when MPOL_INTERLEAVE
  *
- * Returns the struct page for entry and addr, after queueing swapin.
+ * Returns the struct folio for entry and addr, after queueing swapin.
  *
  * Primitive swap readahead code. We simply read an aligned block of
  * (1 << page_cluster) entries in the swap area. This method is chosen
@@ -624,10 +631,10 @@ static unsigned long swapin_nr_pages(unsigned long offset)
  * are used for every page of the readahead: neighbouring pages on swap
  * are fairly likely to have been swapped out from the same node.
  */
-struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
+struct folio *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
 				    struct mempolicy *mpol, pgoff_t ilx)
 {
-	struct page *page;
+	struct folio *folio;
 	unsigned long entry_offset = swp_offset(entry);
 	unsigned long offset = entry_offset;
 	unsigned long start_offset, end_offset;
@@ -652,30 +659,31 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
 	blk_start_plug(&plug);
 	for (offset = start_offset; offset <= end_offset ; offset++) {
 		/* Ok, do the async read-ahead now */
-		page = __read_swap_cache_async(
+		folio = __read_swap_cache_async(
 				swp_entry(swp_type(entry), offset),
-				gfp_mask, mpol, ilx, &page_allocated);
-		if (!page)
+				gfp_mask, mpol, ilx, &page_allocated, false);
+		if (!folio)
 			continue;
 		if (page_allocated) {
-			swap_readpage(page, false, &splug);
+			swap_read_folio(folio, false, &splug);
 			if (offset != entry_offset) {
-				SetPageReadahead(page);
+				folio_set_readahead(folio);
 				count_vm_event(SWAP_RA);
 			}
 		}
-		put_page(page);
+		folio_put(folio);
 	}
 	blk_finish_plug(&plug);
 	swap_read_unplug(splug);
 	lru_add_drain();	/* Push any new pages onto the LRU now */
 skip:
 	/* The page was likely read above, so no need for plugging here */
-	page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
-					&page_allocated);
+	folio = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
+					&page_allocated, false);
 	if (unlikely(page_allocated))
-		swap_readpage(page, false, NULL);
-	return page;
+		swap_read_folio(folio, false, NULL);
+	zswap_folio_swapin(folio);
+	return folio;
 }
 
 int init_swap_address_space(unsigned int type, unsigned long nr_pages)
@@ -779,7 +787,7 @@ static void swap_ra_info(struct vm_fault *vmf,
  * @targ_ilx: NUMA interleave index, for use only when MPOL_INTERLEAVE
  * @vmf: fault information
  *
- * Returns the struct page for entry and addr, after queueing swapin.
+ * Returns the struct folio for entry and addr, after queueing swapin.
  *
  * Primitive swap readahead code. We simply read in a few pages whose
  * virtual addresses are around the fault address in the same vma.
@@ -787,13 +795,12 @@ static void swap_ra_info(struct vm_fault *vmf,
  * Caller must hold read mmap_lock if vmf->vma is not NULL.
  *
  */
-static struct page *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
-				       struct mempolicy *mpol, pgoff_t targ_ilx,
-				       struct vm_fault *vmf)
+static struct folio *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
+		struct mempolicy *mpol, pgoff_t targ_ilx, struct vm_fault *vmf)
 {
 	struct blk_plug plug;
 	struct swap_iocb *splug = NULL;
-	struct page *page;
+	struct folio *folio;
 	pte_t *pte = NULL, pentry;
 	unsigned long addr;
 	swp_entry_t entry;
@@ -826,18 +833,18 @@ static struct page *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
 			continue;
 		pte_unmap(pte);
 		pte = NULL;
-		page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
-						&page_allocated);
-		if (!page)
+		folio = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
+						&page_allocated, false);
+		if (!folio)
 			continue;
 		if (page_allocated) {
-			swap_readpage(page, false, &splug);
+			swap_read_folio(folio, false, &splug);
 			if (i != ra_info.offset) {
-				SetPageReadahead(page);
+				folio_set_readahead(folio);
 				count_vm_event(SWAP_RA);
 			}
 		}
-		put_page(page);
+		folio_put(folio);
 	}
 	if (pte)
 		pte_unmap(pte);
@@ -845,12 +852,13 @@ static struct page *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
 	swap_read_unplug(splug);
 	lru_add_drain();
 skip:
-	/* The page was likely read above, so no need for plugging here */
-	page = __read_swap_cache_async(targ_entry, gfp_mask, mpol, targ_ilx,
-					&page_allocated);
+	/* The folio was likely read above, so no need for plugging here */
+	folio = __read_swap_cache_async(targ_entry, gfp_mask, mpol, targ_ilx,
+					&page_allocated, false);
 	if (unlikely(page_allocated))
-		swap_readpage(page, false, NULL);
-	return page;
+		swap_read_folio(folio, false, NULL);
+	zswap_folio_swapin(folio);
+	return folio;
 }
 
 /**
@@ -870,14 +878,17 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
 {
 	struct mempolicy *mpol;
 	pgoff_t ilx;
-	struct page *page;
+	struct folio *folio;
 
 	mpol = get_vma_policy(vmf->vma, vmf->address, 0, &ilx);
-	page = swap_use_vma_readahead() ?
+	folio = swap_use_vma_readahead() ?
 		swap_vma_readahead(entry, gfp_mask, mpol, ilx, vmf) :
 		swap_cluster_readahead(entry, gfp_mask, mpol, ilx);
 	mpol_cond_put(mpol);
-	return page;
+
+	if (!folio)
+		return NULL;
+	return folio_file_page(folio, swp_offset(entry));
 }
 
 #ifdef CONFIG_SYSFS
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 4bc70f459164..556ff7347d5f 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -42,6 +42,7 @@
 #include <linux/completion.h>
 #include <linux/suspend.h>
 #include <linux/zswap.h>
+#include <linux/plist.h>
 
 #include <asm/tlbflush.h>
 #include <linux/swapops.h>
@@ -227,14 +228,14 @@ offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset)
 	BUG();
 }
 
-sector_t swap_page_sector(struct page *page)
+sector_t swap_folio_sector(struct folio *folio)
 {
-	struct swap_info_struct *sis = page_swap_info(page);
+	struct swap_info_struct *sis = swp_swap_info(folio->swap);
 	struct swap_extent *se;
 	sector_t sector;
 	pgoff_t offset;
 
-	offset = __page_file_index(page);
+	offset = swp_offset(folio->swap);
 	se = offset_to_swap_extent(sis, offset);
 	sector = se->start_block + (offset - se->start_page);
 	return sector << (PAGE_SHIFT - 9);
@@ -1495,9 +1496,9 @@ int swp_swapcount(swp_entry_t entry)
 
 	do {
 		page = list_next_entry(page, lru);
-		map = kmap_atomic(page);
+		map = kmap_local_page(page);
 		tmp_count = map[offset];
-		kunmap_atomic(map);
+		kunmap_local(map);
 
 		count += (tmp_count & ~COUNT_CONTINUED) * n;
 		n *= (SWAP_CONT_MAX + 1);
@@ -1741,18 +1742,24 @@ static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte)
 static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, swp_entry_t entry, struct folio *folio)
 {
-	struct page *page = folio_file_page(folio, swp_offset(entry));
-	struct page *swapcache;
+	struct page *page;
+	struct folio *swapcache;
 	spinlock_t *ptl;
 	pte_t *pte, new_pte, old_pte;
-	bool hwpoisoned = PageHWPoison(page);
+	bool hwpoisoned = false;
 	int ret = 1;
 
-	swapcache = page;
-	page = ksm_might_need_to_copy(page, vma, addr);
-	if (unlikely(!page))
+	swapcache = folio;
+	folio = ksm_might_need_to_copy(folio, vma, addr);
+	if (unlikely(!folio))
 		return -ENOMEM;
-	else if (unlikely(PTR_ERR(page) == -EHWPOISON))
+	else if (unlikely(folio == ERR_PTR(-EHWPOISON))) {
+		hwpoisoned = true;
+		folio = swapcache;
+	}
+
+	page = folio_file_page(folio, swp_offset(entry));
+	if (PageHWPoison(page))
 		hwpoisoned = true;
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
@@ -1764,13 +1771,12 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 
 	old_pte = ptep_get(pte);
 
-	if (unlikely(hwpoisoned || !PageUptodate(page))) {
+	if (unlikely(hwpoisoned || !folio_test_uptodate(folio))) {
 		swp_entry_t swp_entry;
 
 		dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
 		if (hwpoisoned) {
-			swp_entry = make_hwpoison_entry(swapcache);
-			page = swapcache;
+			swp_entry = make_hwpoison_entry(page);
 		} else {
 			swp_entry = make_poisoned_swp_entry();
 		}
@@ -1784,31 +1790,27 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	 * when reading from swap. This metadata may be indexed by swap entry
 	 * so this must be called before swap_free().
 	 */
-	arch_swap_restore(entry, page_folio(page));
-
-	/* See do_swap_page() */
-	BUG_ON(!PageAnon(page) && PageMappedToDisk(page));
-	BUG_ON(PageAnon(page) && PageAnonExclusive(page));
+	arch_swap_restore(entry, folio);
 
 	dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
 	inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
-	get_page(page);
-	if (page == swapcache) {
+	folio_get(folio);
+	if (folio == swapcache) {
 		rmap_t rmap_flags = RMAP_NONE;
 
 		/*
-		 * See do_swap_page(): PageWriteback() would be problematic.
-		 * However, we do a wait_on_page_writeback() just before this
-		 * call and have the page locked.
+		 * See do_swap_page(): writeback would be problematic.
+		 * However, we do a folio_wait_writeback() just before this
+		 * call and have the folio locked.
 		 */
-		VM_BUG_ON_PAGE(PageWriteback(page), page);
+		VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio);
 		if (pte_swp_exclusive(old_pte))
 			rmap_flags |= RMAP_EXCLUSIVE;
 
-		page_add_anon_rmap(page, vma, addr, rmap_flags);
+		folio_add_anon_rmap_pte(folio, page, vma, addr, rmap_flags);
 	} else { /* ksm created a completely new copy */
-		page_add_new_anon_rmap(page, vma, addr);
-		lru_cache_add_inactive_or_unevictable(page, vma);
+		folio_add_new_anon_rmap(folio, vma, addr);
+		folio_add_lru_vma(folio, vma);
 	}
 	new_pte = pte_mkold(mk_pte(page, vma->vm_page_prot));
 	if (pte_swp_soft_dirty(old_pte))
@@ -1821,9 +1823,9 @@ setpte:
 out:
 	if (pte)
 		pte_unmap_unlock(pte, ptl);
-	if (page != swapcache) {
-		unlock_page(page);
-		put_page(page);
+	if (folio != swapcache) {
+		folio_unlock(folio);
+		folio_put(folio);
 	}
 	return ret;
 }
@@ -2224,7 +2226,7 @@ EXPORT_SYMBOL_GPL(add_swap_extent);
 /*
  * A `swap extent' is a simple thing which maps a contiguous range of pages
  * onto a contiguous range of disk blocks.  A rbtree of swap extents is
- * built at swapon time and is then used at swap_writepage/swap_readpage
+ * built at swapon time and is then used at swap_writepage/swap_read_folio
  * time for locating where on disk a page belongs.
  *
  * If the swapfile is an S_ISBLK block device, a single extent is installed.
@@ -3368,18 +3370,12 @@ struct swap_info_struct *swp_swap_info(swp_entry_t entry)
 	return swap_type_to_swap_info(swp_type(entry));
 }
 
-struct swap_info_struct *page_swap_info(struct page *page)
-{
-	swp_entry_t entry = page_swap_entry(page);
-	return swp_swap_info(entry);
-}
-
 /*
  * out-of-line methods to avoid include hell.
  */
 struct address_space *swapcache_mapping(struct folio *folio)
 {
-	return page_swap_info(&folio->page)->swap_file->f_mapping;
+	return swp_swap_info(folio->swap)->swap_file->f_mapping;
 }
 EXPORT_SYMBOL_GPL(swapcache_mapping);
 
@@ -3477,9 +3473,9 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
 		if (!(count & COUNT_CONTINUED))
 			goto out_unlock_cont;
 
-		map = kmap_atomic(list_page) + offset;
+		map = kmap_local_page(list_page) + offset;
 		count = *map;
-		kunmap_atomic(map);
+		kunmap_local(map);
 
 		/*
 		 * If this continuation count now has some space in it,
@@ -3529,7 +3525,7 @@ static bool swap_count_continued(struct swap_info_struct *si,
 	spin_lock(&si->cont_lock);
 	offset &= ~PAGE_MASK;
 	page = list_next_entry(head, lru);
-	map = kmap_atomic(page) + offset;
+	map = kmap_local_page(page) + offset;
 
 	if (count == SWAP_MAP_MAX)	/* initial increment from swap_map */
 		goto init_map;		/* jump over SWAP_CONT_MAX checks */
@@ -3539,27 +3535,27 @@ static bool swap_count_continued(struct swap_info_struct *si,
 		 * Think of how you add 1 to 999
 		 */
 		while (*map == (SWAP_CONT_MAX | COUNT_CONTINUED)) {
-			kunmap_atomic(map);
+			kunmap_local(map);
 			page = list_next_entry(page, lru);
 			BUG_ON(page == head);
-			map = kmap_atomic(page) + offset;
+			map = kmap_local_page(page) + offset;
 		}
 		if (*map == SWAP_CONT_MAX) {
-			kunmap_atomic(map);
+			kunmap_local(map);
 			page = list_next_entry(page, lru);
 			if (page == head) {
 				ret = false;	/* add count continuation */
 				goto out;
 			}
-			map = kmap_atomic(page) + offset;
+			map = kmap_local_page(page) + offset;
 init_map:		*map = 0;		/* we didn't zero the page */
 		}
 		*map += 1;
-		kunmap_atomic(map);
+		kunmap_local(map);
 		while ((page = list_prev_entry(page, lru)) != head) {
-			map = kmap_atomic(page) + offset;
+			map = kmap_local_page(page) + offset;
 			*map = COUNT_CONTINUED;
-			kunmap_atomic(map);
+			kunmap_local(map);
 		}
 		ret = true;			/* incremented */
 
@@ -3569,21 +3565,21 @@ init_map:		*map = 0;		/* we didn't zero the page */
 		 */
 		BUG_ON(count != COUNT_CONTINUED);
 		while (*map == COUNT_CONTINUED) {
-			kunmap_atomic(map);
+			kunmap_local(map);
 			page = list_next_entry(page, lru);
 			BUG_ON(page == head);
-			map = kmap_atomic(page) + offset;
+			map = kmap_local_page(page) + offset;
 		}
 		BUG_ON(*map == 0);
 		*map -= 1;
 		if (*map == 0)
 			count = 0;
-		kunmap_atomic(map);
+		kunmap_local(map);
 		while ((page = list_prev_entry(page, lru)) != head) {
-			map = kmap_atomic(page) + offset;
+			map = kmap_local_page(page) + offset;
 			*map = SWAP_CONT_MAX | count;
 			count = COUNT_CONTINUED;
-			kunmap_atomic(map);
+			kunmap_local(map);
 		}
 		ret = count == COUNT_CONTINUED;
 	}
diff --git a/mm/truncate.c b/mm/truncate.c
index 8e3aa9e8618e..725b150e47ac 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -250,10 +250,9 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end)
 /*
  * Used to get rid of pages on hardware memory corruption.
  */
-int generic_error_remove_page(struct address_space *mapping, struct page *page)
+int generic_error_remove_folio(struct address_space *mapping,
+		struct folio *folio)
 {
-	VM_BUG_ON_PAGE(PageTail(page), page);
-
 	if (!mapping)
 		return -EINVAL;
 	/*
@@ -262,13 +261,26 @@ int generic_error_remove_page(struct address_space *mapping, struct page *page)
 	 */
 	if (!S_ISREG(mapping->host->i_mode))
 		return -EIO;
-	return truncate_inode_folio(mapping, page_folio(page));
+	return truncate_inode_folio(mapping, folio);
 }
-EXPORT_SYMBOL(generic_error_remove_page);
+EXPORT_SYMBOL(generic_error_remove_folio);
 
-static long mapping_evict_folio(struct address_space *mapping,
-		struct folio *folio)
+/**
+ * mapping_evict_folio() - Remove an unused folio from the page-cache.
+ * @mapping: The mapping this folio belongs to.
+ * @folio: The folio to remove.
+ *
+ * Safely remove one folio from the page cache.
+ * It only drops clean, unused folios.
+ *
+ * Context: Folio must be locked.
+ * Return: The number of pages successfully removed.
+ */
+long mapping_evict_folio(struct address_space *mapping, struct folio *folio)
 {
+	/* The page may have been truncated before it was locked */
+	if (!mapping)
+		return 0;
 	if (folio_test_dirty(folio) || folio_test_writeback(folio))
 		return 0;
 	/* The refcount will be elevated if any page in the folio is mapped */
@@ -282,27 +294,6 @@ static long mapping_evict_folio(struct address_space *mapping,
 }
 
 /**
- * invalidate_inode_page() - Remove an unused page from the pagecache.
- * @page: The page to remove.
- *
- * Safely invalidate one page from its pagecache mapping.
- * It only drops clean, unused pages.
- *
- * Context: Page must be locked.
- * Return: The number of pages successfully removed.
- */
-long invalidate_inode_page(struct page *page)
-{
-	struct folio *folio = page_folio(page);
-	struct address_space *mapping = folio_mapping(folio);
-
-	/* The page may have been truncated before it was locked */
-	if (!mapping)
-		return 0;
-	return mapping_evict_folio(mapping, folio);
-}
-
-/**
  * truncate_inode_pages_range - truncate range of pages specified by start & end byte offsets
  * @mapping: mapping to truncate
  * @lstart: offset from which to truncate
@@ -560,9 +551,9 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 EXPORT_SYMBOL(invalidate_mapping_pages);
 
 /*
- * This is like invalidate_inode_page(), except it ignores the page's
+ * This is like mapping_evict_folio(), except it ignores the folio's
  * refcount.  We do this because invalidate_inode_pages2() needs stronger
- * invalidation guarantees, and cannot afford to leave pages behind because
+ * invalidation guarantees, and cannot afford to leave folios behind because
  * shrink_page_list() has a temp ref on them, or because they're transiently
  * sitting in the folio_add_lru() caches.
  */
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 96d9eae5c7cc..216ab4c8621f 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -114,9 +114,9 @@ int mfill_atomic_install_pte(pmd_t *dst_pmd,
 		/* Usually, cache pages are already added to LRU */
 		if (newly_allocated)
 			folio_add_lru(folio);
-		page_add_file_rmap(page, dst_vma, false);
+		folio_add_file_rmap_pte(folio, page, dst_vma);
 	} else {
-		page_add_new_anon_rmap(page, dst_vma, dst_addr);
+		folio_add_new_anon_rmap(folio, dst_vma, dst_addr);
 		folio_add_lru_vma(folio, dst_vma);
 	}
 
@@ -312,7 +312,7 @@ static int mfill_atomic_pte_poison(pmd_t *dst_pmd,
 
 	ret = -EEXIST;
 	/* Refuse to overwrite any PTE, even a PTE marker (e.g. UFFD WP). */
-	if (!pte_none(*dst_pte))
+	if (!pte_none(ptep_get(dst_pte)))
 		goto out_unlock;
 
 	set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
@@ -842,3 +842,626 @@ out_unlock:
 	mmap_read_unlock(dst_mm);
 	return err;
 }
+
+
+void double_pt_lock(spinlock_t *ptl1,
+		    spinlock_t *ptl2)
+	__acquires(ptl1)
+	__acquires(ptl2)
+{
+	spinlock_t *ptl_tmp;
+
+	if (ptl1 > ptl2) {
+		/* exchange ptl1 and ptl2 */
+		ptl_tmp = ptl1;
+		ptl1 = ptl2;
+		ptl2 = ptl_tmp;
+	}
+	/* lock in virtual address order to avoid lock inversion */
+	spin_lock(ptl1);
+	if (ptl1 != ptl2)
+		spin_lock_nested(ptl2, SINGLE_DEPTH_NESTING);
+	else
+		__acquire(ptl2);
+}
+
+void double_pt_unlock(spinlock_t *ptl1,
+		      spinlock_t *ptl2)
+	__releases(ptl1)
+	__releases(ptl2)
+{
+	spin_unlock(ptl1);
+	if (ptl1 != ptl2)
+		spin_unlock(ptl2);
+	else
+		__release(ptl2);
+}
+
+
+static int move_present_pte(struct mm_struct *mm,
+			    struct vm_area_struct *dst_vma,
+			    struct vm_area_struct *src_vma,
+			    unsigned long dst_addr, unsigned long src_addr,
+			    pte_t *dst_pte, pte_t *src_pte,
+			    pte_t orig_dst_pte, pte_t orig_src_pte,
+			    spinlock_t *dst_ptl, spinlock_t *src_ptl,
+			    struct folio *src_folio)
+{
+	int err = 0;
+
+	double_pt_lock(dst_ptl, src_ptl);
+
+	if (!pte_same(*src_pte, orig_src_pte) ||
+	    !pte_same(*dst_pte, orig_dst_pte)) {
+		err = -EAGAIN;
+		goto out;
+	}
+	if (folio_test_large(src_folio) ||
+	    folio_maybe_dma_pinned(src_folio) ||
+	    !PageAnonExclusive(&src_folio->page)) {
+		err = -EBUSY;
+		goto out;
+	}
+
+	folio_move_anon_rmap(src_folio, dst_vma);
+	WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr));
+
+	orig_src_pte = ptep_clear_flush(src_vma, src_addr, src_pte);
+	/* Folio got pinned from under us. Put it back and fail the move. */
+	if (folio_maybe_dma_pinned(src_folio)) {
+		set_pte_at(mm, src_addr, src_pte, orig_src_pte);
+		err = -EBUSY;
+		goto out;
+	}
+
+	orig_dst_pte = mk_pte(&src_folio->page, dst_vma->vm_page_prot);
+	/* Follow mremap() behavior and treat the entry dirty after the move */
+	orig_dst_pte = pte_mkwrite(pte_mkdirty(orig_dst_pte), dst_vma);
+
+	set_pte_at(mm, dst_addr, dst_pte, orig_dst_pte);
+out:
+	double_pt_unlock(dst_ptl, src_ptl);
+	return err;
+}
+
+static int move_swap_pte(struct mm_struct *mm,
+			 unsigned long dst_addr, unsigned long src_addr,
+			 pte_t *dst_pte, pte_t *src_pte,
+			 pte_t orig_dst_pte, pte_t orig_src_pte,
+			 spinlock_t *dst_ptl, spinlock_t *src_ptl)
+{
+	if (!pte_swp_exclusive(orig_src_pte))
+		return -EBUSY;
+
+	double_pt_lock(dst_ptl, src_ptl);
+
+	if (!pte_same(*src_pte, orig_src_pte) ||
+	    !pte_same(*dst_pte, orig_dst_pte)) {
+		double_pt_unlock(dst_ptl, src_ptl);
+		return -EAGAIN;
+	}
+
+	orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte);
+	set_pte_at(mm, dst_addr, dst_pte, orig_src_pte);
+	double_pt_unlock(dst_ptl, src_ptl);
+
+	return 0;
+}
+
+/*
+ * The mmap_lock for reading is held by the caller. Just move the page
+ * from src_pmd to dst_pmd if possible, and return true if succeeded
+ * in moving the page.
+ */
+static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
+			  struct vm_area_struct *dst_vma,
+			  struct vm_area_struct *src_vma,
+			  unsigned long dst_addr, unsigned long src_addr,
+			  __u64 mode)
+{
+	swp_entry_t entry;
+	pte_t orig_src_pte, orig_dst_pte;
+	pte_t src_folio_pte;
+	spinlock_t *src_ptl, *dst_ptl;
+	pte_t *src_pte = NULL;
+	pte_t *dst_pte = NULL;
+
+	struct folio *src_folio = NULL;
+	struct anon_vma *src_anon_vma = NULL;
+	struct mmu_notifier_range range;
+	int err = 0;
+
+	flush_cache_range(src_vma, src_addr, src_addr + PAGE_SIZE);
+	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm,
+				src_addr, src_addr + PAGE_SIZE);
+	mmu_notifier_invalidate_range_start(&range);
+retry:
+	dst_pte = pte_offset_map_nolock(mm, dst_pmd, dst_addr, &dst_ptl);
+
+	/* Retry if a huge pmd materialized from under us */
+	if (unlikely(!dst_pte)) {
+		err = -EAGAIN;
+		goto out;
+	}
+
+	src_pte = pte_offset_map_nolock(mm, src_pmd, src_addr, &src_ptl);
+
+	/*
+	 * We held the mmap_lock for reading so MADV_DONTNEED
+	 * can zap transparent huge pages under us, or the
+	 * transparent huge page fault can establish new
+	 * transparent huge pages under us.
+	 */
+	if (unlikely(!src_pte)) {
+		err = -EAGAIN;
+		goto out;
+	}
+
+	/* Sanity checks before the operation */
+	if (WARN_ON_ONCE(pmd_none(*dst_pmd)) ||	WARN_ON_ONCE(pmd_none(*src_pmd)) ||
+	    WARN_ON_ONCE(pmd_trans_huge(*dst_pmd)) || WARN_ON_ONCE(pmd_trans_huge(*src_pmd))) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	spin_lock(dst_ptl);
+	orig_dst_pte = *dst_pte;
+	spin_unlock(dst_ptl);
+	if (!pte_none(orig_dst_pte)) {
+		err = -EEXIST;
+		goto out;
+	}
+
+	spin_lock(src_ptl);
+	orig_src_pte = *src_pte;
+	spin_unlock(src_ptl);
+	if (pte_none(orig_src_pte)) {
+		if (!(mode & UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES))
+			err = -ENOENT;
+		else /* nothing to do to move a hole */
+			err = 0;
+		goto out;
+	}
+
+	/* If PTE changed after we locked the folio them start over */
+	if (src_folio && unlikely(!pte_same(src_folio_pte, orig_src_pte))) {
+		err = -EAGAIN;
+		goto out;
+	}
+
+	if (pte_present(orig_src_pte)) {
+		/*
+		 * Pin and lock both source folio and anon_vma. Since we are in
+		 * RCU read section, we can't block, so on contention have to
+		 * unmap the ptes, obtain the lock and retry.
+		 */
+		if (!src_folio) {
+			struct folio *folio;
+
+			/*
+			 * Pin the page while holding the lock to be sure the
+			 * page isn't freed under us
+			 */
+			spin_lock(src_ptl);
+			if (!pte_same(orig_src_pte, *src_pte)) {
+				spin_unlock(src_ptl);
+				err = -EAGAIN;
+				goto out;
+			}
+
+			folio = vm_normal_folio(src_vma, src_addr, orig_src_pte);
+			if (!folio || !PageAnonExclusive(&folio->page)) {
+				spin_unlock(src_ptl);
+				err = -EBUSY;
+				goto out;
+			}
+
+			folio_get(folio);
+			src_folio = folio;
+			src_folio_pte = orig_src_pte;
+			spin_unlock(src_ptl);
+
+			if (!folio_trylock(src_folio)) {
+				pte_unmap(&orig_src_pte);
+				pte_unmap(&orig_dst_pte);
+				src_pte = dst_pte = NULL;
+				/* now we can block and wait */
+				folio_lock(src_folio);
+				goto retry;
+			}
+
+			if (WARN_ON_ONCE(!folio_test_anon(src_folio))) {
+				err = -EBUSY;
+				goto out;
+			}
+		}
+
+		/* at this point we have src_folio locked */
+		if (folio_test_large(src_folio)) {
+			/* split_folio() can block */
+			pte_unmap(&orig_src_pte);
+			pte_unmap(&orig_dst_pte);
+			src_pte = dst_pte = NULL;
+			err = split_folio(src_folio);
+			if (err)
+				goto out;
+			/* have to reacquire the folio after it got split */
+			folio_unlock(src_folio);
+			folio_put(src_folio);
+			src_folio = NULL;
+			goto retry;
+		}
+
+		if (!src_anon_vma) {
+			/*
+			 * folio_referenced walks the anon_vma chain
+			 * without the folio lock. Serialize against it with
+			 * the anon_vma lock, the folio lock is not enough.
+			 */
+			src_anon_vma = folio_get_anon_vma(src_folio);
+			if (!src_anon_vma) {
+				/* page was unmapped from under us */
+				err = -EAGAIN;
+				goto out;
+			}
+			if (!anon_vma_trylock_write(src_anon_vma)) {
+				pte_unmap(&orig_src_pte);
+				pte_unmap(&orig_dst_pte);
+				src_pte = dst_pte = NULL;
+				/* now we can block and wait */
+				anon_vma_lock_write(src_anon_vma);
+				goto retry;
+			}
+		}
+
+		err = move_present_pte(mm,  dst_vma, src_vma,
+				       dst_addr, src_addr, dst_pte, src_pte,
+				       orig_dst_pte, orig_src_pte,
+				       dst_ptl, src_ptl, src_folio);
+	} else {
+		entry = pte_to_swp_entry(orig_src_pte);
+		if (non_swap_entry(entry)) {
+			if (is_migration_entry(entry)) {
+				pte_unmap(&orig_src_pte);
+				pte_unmap(&orig_dst_pte);
+				src_pte = dst_pte = NULL;
+				migration_entry_wait(mm, src_pmd, src_addr);
+				err = -EAGAIN;
+			} else
+				err = -EFAULT;
+			goto out;
+		}
+
+		err = move_swap_pte(mm, dst_addr, src_addr,
+				    dst_pte, src_pte,
+				    orig_dst_pte, orig_src_pte,
+				    dst_ptl, src_ptl);
+	}
+
+out:
+	if (src_anon_vma) {
+		anon_vma_unlock_write(src_anon_vma);
+		put_anon_vma(src_anon_vma);
+	}
+	if (src_folio) {
+		folio_unlock(src_folio);
+		folio_put(src_folio);
+	}
+	if (dst_pte)
+		pte_unmap(dst_pte);
+	if (src_pte)
+		pte_unmap(src_pte);
+	mmu_notifier_invalidate_range_end(&range);
+
+	return err;
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline bool move_splits_huge_pmd(unsigned long dst_addr,
+					unsigned long src_addr,
+					unsigned long src_end)
+{
+	return (src_addr & ~HPAGE_PMD_MASK) || (dst_addr & ~HPAGE_PMD_MASK) ||
+		src_end - src_addr < HPAGE_PMD_SIZE;
+}
+#else
+static inline bool move_splits_huge_pmd(unsigned long dst_addr,
+					unsigned long src_addr,
+					unsigned long src_end)
+{
+	/* This is unreachable anyway, just to avoid warnings when HPAGE_PMD_SIZE==0 */
+	return false;
+}
+#endif
+
+static inline bool vma_move_compatible(struct vm_area_struct *vma)
+{
+	return !(vma->vm_flags & (VM_PFNMAP | VM_IO |  VM_HUGETLB |
+				  VM_MIXEDMAP | VM_SHADOW_STACK));
+}
+
+static int validate_move_areas(struct userfaultfd_ctx *ctx,
+			       struct vm_area_struct *src_vma,
+			       struct vm_area_struct *dst_vma)
+{
+	/* Only allow moving if both have the same access and protection */
+	if ((src_vma->vm_flags & VM_ACCESS_FLAGS) != (dst_vma->vm_flags & VM_ACCESS_FLAGS) ||
+	    pgprot_val(src_vma->vm_page_prot) != pgprot_val(dst_vma->vm_page_prot))
+		return -EINVAL;
+
+	/* Only allow moving if both are mlocked or both aren't */
+	if ((src_vma->vm_flags & VM_LOCKED) != (dst_vma->vm_flags & VM_LOCKED))
+		return -EINVAL;
+
+	/*
+	 * For now, we keep it simple and only move between writable VMAs.
+	 * Access flags are equal, therefore cheching only the source is enough.
+	 */
+	if (!(src_vma->vm_flags & VM_WRITE))
+		return -EINVAL;
+
+	/* Check if vma flags indicate content which can be moved */
+	if (!vma_move_compatible(src_vma) || !vma_move_compatible(dst_vma))
+		return -EINVAL;
+
+	/* Ensure dst_vma is registered in uffd we are operating on */
+	if (!dst_vma->vm_userfaultfd_ctx.ctx ||
+	    dst_vma->vm_userfaultfd_ctx.ctx != ctx)
+		return -EINVAL;
+
+	/* Only allow moving across anonymous vmas */
+	if (!vma_is_anonymous(src_vma) || !vma_is_anonymous(dst_vma))
+		return -EINVAL;
+
+	/*
+	 * Ensure the dst_vma has a anon_vma or this page
+	 * would get a NULL anon_vma when moved in the
+	 * dst_vma.
+	 */
+	if (unlikely(anon_vma_prepare(dst_vma)))
+		return -ENOMEM;
+
+	return 0;
+}
+
+/**
+ * move_pages - move arbitrary anonymous pages of an existing vma
+ * @ctx: pointer to the userfaultfd context
+ * @mm: the address space to move pages
+ * @dst_start: start of the destination virtual memory range
+ * @src_start: start of the source virtual memory range
+ * @len: length of the virtual memory range
+ * @mode: flags from uffdio_move.mode
+ *
+ * Must be called with mmap_lock held for read.
+ *
+ * move_pages() remaps arbitrary anonymous pages atomically in zero
+ * copy. It only works on non shared anonymous pages because those can
+ * be relocated without generating non linear anon_vmas in the rmap
+ * code.
+ *
+ * It provides a zero copy mechanism to handle userspace page faults.
+ * The source vma pages should have mapcount == 1, which can be
+ * enforced by using madvise(MADV_DONTFORK) on src vma.
+ *
+ * The thread receiving the page during the userland page fault
+ * will receive the faulting page in the source vma through the network,
+ * storage or any other I/O device (MADV_DONTFORK in the source vma
+ * avoids move_pages() to fail with -EBUSY if the process forks before
+ * move_pages() is called), then it will call move_pages() to map the
+ * page in the faulting address in the destination vma.
+ *
+ * This userfaultfd command works purely via pagetables, so it's the
+ * most efficient way to move physical non shared anonymous pages
+ * across different virtual addresses. Unlike mremap()/mmap()/munmap()
+ * it does not create any new vmas. The mapping in the destination
+ * address is atomic.
+ *
+ * It only works if the vma protection bits are identical from the
+ * source and destination vma.
+ *
+ * It can remap non shared anonymous pages within the same vma too.
+ *
+ * If the source virtual memory range has any unmapped holes, or if
+ * the destination virtual memory range is not a whole unmapped hole,
+ * move_pages() will fail respectively with -ENOENT or -EEXIST. This
+ * provides a very strict behavior to avoid any chance of memory
+ * corruption going unnoticed if there are userland race conditions.
+ * Only one thread should resolve the userland page fault at any given
+ * time for any given faulting address. This means that if two threads
+ * try to both call move_pages() on the same destination address at the
+ * same time, the second thread will get an explicit error from this
+ * command.
+ *
+ * The command retval will return "len" is successful. The command
+ * however can be interrupted by fatal signals or errors. If
+ * interrupted it will return the number of bytes successfully
+ * remapped before the interruption if any, or the negative error if
+ * none. It will never return zero. Either it will return an error or
+ * an amount of bytes successfully moved. If the retval reports a
+ * "short" remap, the move_pages() command should be repeated by
+ * userland with src+retval, dst+reval, len-retval if it wants to know
+ * about the error that interrupted it.
+ *
+ * The UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES flag can be specified to
+ * prevent -ENOENT errors to materialize if there are holes in the
+ * source virtual range that is being remapped. The holes will be
+ * accounted as successfully remapped in the retval of the
+ * command. This is mostly useful to remap hugepage naturally aligned
+ * virtual regions without knowing if there are transparent hugepage
+ * in the regions or not, but preventing the risk of having to split
+ * the hugepmd during the remap.
+ *
+ * If there's any rmap walk that is taking the anon_vma locks without
+ * first obtaining the folio lock (the only current instance is
+ * folio_referenced), they will have to verify if the folio->mapping
+ * has changed after taking the anon_vma lock. If it changed they
+ * should release the lock and retry obtaining a new anon_vma, because
+ * it means the anon_vma was changed by move_pages() before the lock
+ * could be obtained. This is the only additional complexity added to
+ * the rmap code to provide this anonymous page remapping functionality.
+ */
+ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
+		   unsigned long dst_start, unsigned long src_start,
+		   unsigned long len, __u64 mode)
+{
+	struct vm_area_struct *src_vma, *dst_vma;
+	unsigned long src_addr, dst_addr;
+	pmd_t *src_pmd, *dst_pmd;
+	long err = -EINVAL;
+	ssize_t moved = 0;
+
+	/* Sanitize the command parameters. */
+	if (WARN_ON_ONCE(src_start & ~PAGE_MASK) ||
+	    WARN_ON_ONCE(dst_start & ~PAGE_MASK) ||
+	    WARN_ON_ONCE(len & ~PAGE_MASK))
+		goto out;
+
+	/* Does the address range wrap, or is the span zero-sized? */
+	if (WARN_ON_ONCE(src_start + len <= src_start) ||
+	    WARN_ON_ONCE(dst_start + len <= dst_start))
+		goto out;
+
+	/*
+	 * Make sure the vma is not shared, that the src and dst remap
+	 * ranges are both valid and fully within a single existing
+	 * vma.
+	 */
+	src_vma = find_vma(mm, src_start);
+	if (!src_vma || (src_vma->vm_flags & VM_SHARED))
+		goto out;
+	if (src_start < src_vma->vm_start ||
+	    src_start + len > src_vma->vm_end)
+		goto out;
+
+	dst_vma = find_vma(mm, dst_start);
+	if (!dst_vma || (dst_vma->vm_flags & VM_SHARED))
+		goto out;
+	if (dst_start < dst_vma->vm_start ||
+	    dst_start + len > dst_vma->vm_end)
+		goto out;
+
+	err = validate_move_areas(ctx, src_vma, dst_vma);
+	if (err)
+		goto out;
+
+	for (src_addr = src_start, dst_addr = dst_start;
+	     src_addr < src_start + len;) {
+		spinlock_t *ptl;
+		pmd_t dst_pmdval;
+		unsigned long step_size;
+
+		/*
+		 * Below works because anonymous area would not have a
+		 * transparent huge PUD. If file-backed support is added,
+		 * that case would need to be handled here.
+		 */
+		src_pmd = mm_find_pmd(mm, src_addr);
+		if (unlikely(!src_pmd)) {
+			if (!(mode & UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES)) {
+				err = -ENOENT;
+				break;
+			}
+			src_pmd = mm_alloc_pmd(mm, src_addr);
+			if (unlikely(!src_pmd)) {
+				err = -ENOMEM;
+				break;
+			}
+		}
+		dst_pmd = mm_alloc_pmd(mm, dst_addr);
+		if (unlikely(!dst_pmd)) {
+			err = -ENOMEM;
+			break;
+		}
+
+		dst_pmdval = pmdp_get_lockless(dst_pmd);
+		/*
+		 * If the dst_pmd is mapped as THP don't override it and just
+		 * be strict. If dst_pmd changes into TPH after this check, the
+		 * move_pages_huge_pmd() will detect the change and retry
+		 * while move_pages_pte() will detect the change and fail.
+		 */
+		if (unlikely(pmd_trans_huge(dst_pmdval))) {
+			err = -EEXIST;
+			break;
+		}
+
+		ptl = pmd_trans_huge_lock(src_pmd, src_vma);
+		if (ptl) {
+			if (pmd_devmap(*src_pmd)) {
+				spin_unlock(ptl);
+				err = -ENOENT;
+				break;
+			}
+
+			/* Check if we can move the pmd without splitting it. */
+			if (move_splits_huge_pmd(dst_addr, src_addr, src_start + len) ||
+			    !pmd_none(dst_pmdval)) {
+				struct folio *folio = pfn_folio(pmd_pfn(*src_pmd));
+
+				if (!folio || !PageAnonExclusive(&folio->page)) {
+					spin_unlock(ptl);
+					err = -EBUSY;
+					break;
+				}
+
+				spin_unlock(ptl);
+				split_huge_pmd(src_vma, src_pmd, src_addr);
+				/* The folio will be split by move_pages_pte() */
+				continue;
+			}
+
+			err = move_pages_huge_pmd(mm, dst_pmd, src_pmd,
+						  dst_pmdval, dst_vma, src_vma,
+						  dst_addr, src_addr);
+			step_size = HPAGE_PMD_SIZE;
+		} else {
+			if (pmd_none(*src_pmd)) {
+				if (!(mode & UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES)) {
+					err = -ENOENT;
+					break;
+				}
+				if (unlikely(__pte_alloc(mm, src_pmd))) {
+					err = -ENOMEM;
+					break;
+				}
+			}
+
+			if (unlikely(pte_alloc(mm, dst_pmd))) {
+				err = -ENOMEM;
+				break;
+			}
+
+			err = move_pages_pte(mm, dst_pmd, src_pmd,
+					     dst_vma, src_vma,
+					     dst_addr, src_addr, mode);
+			step_size = PAGE_SIZE;
+		}
+
+		cond_resched();
+
+		if (fatal_signal_pending(current)) {
+			/* Do not override an error */
+			if (!err || err == -EAGAIN)
+				err = -EINTR;
+			break;
+		}
+
+		if (err) {
+			if (err == -EAGAIN)
+				continue;
+			break;
+		}
+
+		/* Proceed to the next page */
+		dst_addr += step_size;
+		src_addr += step_size;
+		moved += step_size;
+	}
+
+out:
+	VM_WARN_ON(moved < 0);
+	VM_WARN_ON(err > 0);
+	VM_WARN_ON(!moved && !err);
+	return moved ? moved : err;
+}
diff --git a/mm/util.c b/mm/util.c
index aa01f6ea5a75..5a6a9802583b 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -414,6 +414,15 @@ static int mmap_is_legacy(struct rlimit *rlim_stack)
 
 static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
 {
+#ifdef CONFIG_STACK_GROWSUP
+	/*
+	 * For an upwards growing stack the calculation is much simpler.
+	 * Memory for the maximum stack size is reserved at the top of the
+	 * task. mmap_base starts directly below the stack and grows
+	 * downwards.
+	 */
+	return PAGE_ALIGN_DOWN(mmap_upper_limit(rlim_stack) - rnd);
+#else
 	unsigned long gap = rlim_stack->rlim_cur;
 	unsigned long pad = stack_guard_gap;
 
@@ -431,6 +440,7 @@ static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
 		gap = MAX_GAP;
 
 	return PAGE_ALIGN(STACK_TOP - gap - rnd);
+#endif
 }
 
 void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
@@ -1037,11 +1047,11 @@ int __weak memcmp_pages(struct page *page1, struct page *page2)
 	char *addr1, *addr2;
 	int ret;
 
-	addr1 = kmap_atomic(page1);
-	addr2 = kmap_atomic(page2);
+	addr1 = kmap_local_page(page1);
+	addr2 = kmap_local_page(page2);
 	ret = memcmp(addr1, addr2, PAGE_SIZE);
-	kunmap_atomic(addr2);
-	kunmap_atomic(addr1);
+	kunmap_local(addr2);
+	kunmap_local(addr1);
 	return ret;
 }
 
diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index 22c6689d9302..bd5183dfd879 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -169,7 +169,7 @@ static bool vmpressure_event(struct vmpressure *vmpr,
 			continue;
 		if (level < ev->level)
 			continue;
-		eventfd_signal(ev->efd, 1);
+		eventfd_signal(ev->efd);
 		ret = true;
 	}
 	mutex_unlock(&vmpr->events_lock);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 506f8220c5fe..4f9c854ce6cc 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -411,10 +411,10 @@ static int reclaimer_offset(void)
 {
 	BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD !=
 			PGDEMOTE_DIRECT - PGDEMOTE_KSWAPD);
-	BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD !=
-			PGSCAN_DIRECT - PGSCAN_KSWAPD);
 	BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD !=
 			PGDEMOTE_KHUGEPAGED - PGDEMOTE_KSWAPD);
+	BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD !=
+			PGSCAN_DIRECT - PGSCAN_KSWAPD);
 	BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD !=
 			PGSCAN_KHUGEPAGED - PGSCAN_KSWAPD);
 
@@ -977,7 +977,8 @@ static unsigned int demote_folio_list(struct list_head *demote_folios,
 		      (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION,
 		      &nr_succeeded);
 
-	__count_vm_events(PGDEMOTE_KSWAPD + reclaimer_offset(), nr_succeeded);
+	mod_node_page_state(pgdat, PGDEMOTE_KSWAPD + reclaimer_offset(),
+			    nr_succeeded);
 
 	return nr_succeeded;
 }
@@ -2222,7 +2223,7 @@ static void prepare_scan_control(pg_data_t *pgdat, struct scan_control *sc)
 	 * Flush the memory cgroup stats, so that we read accurate per-memcg
 	 * lruvec stats for heuristics.
 	 */
-	mem_cgroup_flush_stats();
+	mem_cgroup_flush_stats(sc->target_mem_cgroup);
 
 	/*
 	 * Determine the scan balance between anon and file LRUs.
@@ -2667,13 +2668,14 @@ static void get_item_key(void *item, int *key)
 	key[1] = hash >> BLOOM_FILTER_SHIFT;
 }
 
-static bool test_bloom_filter(struct lruvec *lruvec, unsigned long seq, void *item)
+static bool test_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq,
+			      void *item)
 {
 	int key[2];
 	unsigned long *filter;
 	int gen = filter_gen_from_seq(seq);
 
-	filter = READ_ONCE(lruvec->mm_state.filters[gen]);
+	filter = READ_ONCE(mm_state->filters[gen]);
 	if (!filter)
 		return true;
 
@@ -2682,13 +2684,14 @@ static bool test_bloom_filter(struct lruvec *lruvec, unsigned long seq, void *it
 	return test_bit(key[0], filter) && test_bit(key[1], filter);
 }
 
-static void update_bloom_filter(struct lruvec *lruvec, unsigned long seq, void *item)
+static void update_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq,
+				void *item)
 {
 	int key[2];
 	unsigned long *filter;
 	int gen = filter_gen_from_seq(seq);
 
-	filter = READ_ONCE(lruvec->mm_state.filters[gen]);
+	filter = READ_ONCE(mm_state->filters[gen]);
 	if (!filter)
 		return;
 
@@ -2700,12 +2703,12 @@ static void update_bloom_filter(struct lruvec *lruvec, unsigned long seq, void *
 		set_bit(key[1], filter);
 }
 
-static void reset_bloom_filter(struct lruvec *lruvec, unsigned long seq)
+static void reset_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq)
 {
 	unsigned long *filter;
 	int gen = filter_gen_from_seq(seq);
 
-	filter = lruvec->mm_state.filters[gen];
+	filter = mm_state->filters[gen];
 	if (filter) {
 		bitmap_clear(filter, 0, BIT(BLOOM_FILTER_SHIFT));
 		return;
@@ -2713,13 +2716,15 @@ static void reset_bloom_filter(struct lruvec *lruvec, unsigned long seq)
 
 	filter = bitmap_zalloc(BIT(BLOOM_FILTER_SHIFT),
 			       __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN);
-	WRITE_ONCE(lruvec->mm_state.filters[gen], filter);
+	WRITE_ONCE(mm_state->filters[gen], filter);
 }
 
 /******************************************************************************
  *                          mm_struct list
  ******************************************************************************/
 
+#ifdef CONFIG_LRU_GEN_WALKS_MMU
+
 static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg)
 {
 	static struct lru_gen_mm_list mm_list = {
@@ -2736,6 +2741,29 @@ static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg)
 	return &mm_list;
 }
 
+static struct lru_gen_mm_state *get_mm_state(struct lruvec *lruvec)
+{
+	return &lruvec->mm_state;
+}
+
+static struct mm_struct *get_next_mm(struct lru_gen_mm_walk *walk)
+{
+	int key;
+	struct mm_struct *mm;
+	struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
+	struct lru_gen_mm_state *mm_state = get_mm_state(walk->lruvec);
+
+	mm = list_entry(mm_state->head, struct mm_struct, lru_gen.list);
+	key = pgdat->node_id % BITS_PER_TYPE(mm->lru_gen.bitmap);
+
+	if (!walk->force_scan && !test_bit(key, &mm->lru_gen.bitmap))
+		return NULL;
+
+	clear_bit(key, &mm->lru_gen.bitmap);
+
+	return mmget_not_zero(mm) ? mm : NULL;
+}
+
 void lru_gen_add_mm(struct mm_struct *mm)
 {
 	int nid;
@@ -2751,10 +2779,11 @@ void lru_gen_add_mm(struct mm_struct *mm)
 
 	for_each_node_state(nid, N_MEMORY) {
 		struct lruvec *lruvec = get_lruvec(memcg, nid);
+		struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 
 		/* the first addition since the last iteration */
-		if (lruvec->mm_state.tail == &mm_list->fifo)
-			lruvec->mm_state.tail = &mm->lru_gen.list;
+		if (mm_state->tail == &mm_list->fifo)
+			mm_state->tail = &mm->lru_gen.list;
 	}
 
 	list_add_tail(&mm->lru_gen.list, &mm_list->fifo);
@@ -2780,14 +2809,15 @@ void lru_gen_del_mm(struct mm_struct *mm)
 
 	for_each_node(nid) {
 		struct lruvec *lruvec = get_lruvec(memcg, nid);
+		struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 
 		/* where the current iteration continues after */
-		if (lruvec->mm_state.head == &mm->lru_gen.list)
-			lruvec->mm_state.head = lruvec->mm_state.head->prev;
+		if (mm_state->head == &mm->lru_gen.list)
+			mm_state->head = mm_state->head->prev;
 
 		/* where the last iteration ended before */
-		if (lruvec->mm_state.tail == &mm->lru_gen.list)
-			lruvec->mm_state.tail = lruvec->mm_state.tail->next;
+		if (mm_state->tail == &mm->lru_gen.list)
+			mm_state->tail = mm_state->tail->next;
 	}
 
 	list_del_init(&mm->lru_gen.list);
@@ -2830,10 +2860,30 @@ void lru_gen_migrate_mm(struct mm_struct *mm)
 }
 #endif
 
+#else /* !CONFIG_LRU_GEN_WALKS_MMU */
+
+static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg)
+{
+	return NULL;
+}
+
+static struct lru_gen_mm_state *get_mm_state(struct lruvec *lruvec)
+{
+	return NULL;
+}
+
+static struct mm_struct *get_next_mm(struct lru_gen_mm_walk *walk)
+{
+	return NULL;
+}
+
+#endif
+
 static void reset_mm_stats(struct lruvec *lruvec, struct lru_gen_mm_walk *walk, bool last)
 {
 	int i;
 	int hist;
+	struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 
 	lockdep_assert_held(&get_mm_list(lruvec_memcg(lruvec))->lock);
 
@@ -2841,42 +2891,18 @@ static void reset_mm_stats(struct lruvec *lruvec, struct lru_gen_mm_walk *walk,
 		hist = lru_hist_from_seq(walk->max_seq);
 
 		for (i = 0; i < NR_MM_STATS; i++) {
-			WRITE_ONCE(lruvec->mm_state.stats[hist][i],
-				   lruvec->mm_state.stats[hist][i] + walk->mm_stats[i]);
+			WRITE_ONCE(mm_state->stats[hist][i],
+				   mm_state->stats[hist][i] + walk->mm_stats[i]);
 			walk->mm_stats[i] = 0;
 		}
 	}
 
 	if (NR_HIST_GENS > 1 && last) {
-		hist = lru_hist_from_seq(lruvec->mm_state.seq + 1);
+		hist = lru_hist_from_seq(mm_state->seq + 1);
 
 		for (i = 0; i < NR_MM_STATS; i++)
-			WRITE_ONCE(lruvec->mm_state.stats[hist][i], 0);
-	}
-}
-
-static bool should_skip_mm(struct mm_struct *mm, struct lru_gen_mm_walk *walk)
-{
-	int type;
-	unsigned long size = 0;
-	struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
-	int key = pgdat->node_id % BITS_PER_TYPE(mm->lru_gen.bitmap);
-
-	if (!walk->force_scan && !test_bit(key, &mm->lru_gen.bitmap))
-		return true;
-
-	clear_bit(key, &mm->lru_gen.bitmap);
-
-	for (type = !walk->can_swap; type < ANON_AND_FILE; type++) {
-		size += type ? get_mm_counter(mm, MM_FILEPAGES) :
-			       get_mm_counter(mm, MM_ANONPAGES) +
-			       get_mm_counter(mm, MM_SHMEMPAGES);
+			WRITE_ONCE(mm_state->stats[hist][i], 0);
 	}
-
-	if (size < MIN_LRU_BATCH)
-		return true;
-
-	return !mmget_not_zero(mm);
 }
 
 static bool iterate_mm_list(struct lruvec *lruvec, struct lru_gen_mm_walk *walk,
@@ -2887,7 +2913,7 @@ static bool iterate_mm_list(struct lruvec *lruvec, struct lru_gen_mm_walk *walk,
 	struct mm_struct *mm = NULL;
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
-	struct lru_gen_mm_state *mm_state = &lruvec->mm_state;
+	struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 
 	/*
 	 * mm_state->seq is incremented after each iteration of mm_list. There
@@ -2925,11 +2951,7 @@ static bool iterate_mm_list(struct lruvec *lruvec, struct lru_gen_mm_walk *walk,
 			mm_state->tail = mm_state->head->next;
 			walk->force_scan = true;
 		}
-
-		mm = list_entry(mm_state->head, struct mm_struct, lru_gen.list);
-		if (should_skip_mm(mm, walk))
-			mm = NULL;
-	} while (!mm);
+	} while (!(mm = get_next_mm(walk)));
 done:
 	if (*iter || last)
 		reset_mm_stats(lruvec, walk, last);
@@ -2937,7 +2959,7 @@ done:
 	spin_unlock(&mm_list->lock);
 
 	if (mm && first)
-		reset_bloom_filter(lruvec, walk->max_seq + 1);
+		reset_bloom_filter(mm_state, walk->max_seq + 1);
 
 	if (*iter)
 		mmput_async(*iter);
@@ -2952,7 +2974,7 @@ static bool iterate_mm_list_nowalk(struct lruvec *lruvec, unsigned long max_seq)
 	bool success = false;
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
-	struct lru_gen_mm_state *mm_state = &lruvec->mm_state;
+	struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 
 	spin_lock(&mm_list->lock);
 
@@ -3248,7 +3270,6 @@ static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned
 	return pfn;
 }
 
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
 static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr)
 {
 	unsigned long pfn = pmd_pfn(pmd);
@@ -3266,7 +3287,6 @@ static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned
 
 	return pfn;
 }
-#endif
 
 static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg,
 				   struct pglist_data *pgdat, bool can_swap)
@@ -3369,7 +3389,6 @@ restart:
 	return suitable_to_scan(total, young);
 }
 
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
 static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area_struct *vma,
 				  struct mm_walk *args, unsigned long *bitmap, unsigned long *first)
 {
@@ -3447,12 +3466,6 @@ next:
 done:
 	*first = -1;
 }
-#else
-static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area_struct *vma,
-				  struct mm_walk *args, unsigned long *bitmap, unsigned long *first)
-{
-}
-#endif
 
 static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end,
 			   struct mm_walk *args)
@@ -3465,6 +3478,7 @@ static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end,
 	DECLARE_BITMAP(bitmap, MIN_LRU_BATCH);
 	unsigned long first = -1;
 	struct lru_gen_mm_walk *walk = args->private;
+	struct lru_gen_mm_state *mm_state = get_mm_state(walk->lruvec);
 
 	VM_WARN_ON_ONCE(pud_leaf(*pud));
 
@@ -3487,7 +3501,6 @@ restart:
 			continue;
 		}
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 		if (pmd_trans_huge(val)) {
 			unsigned long pfn = pmd_pfn(val);
 			struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
@@ -3506,7 +3519,7 @@ restart:
 			walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first);
 			continue;
 		}
-#endif
+
 		walk->mm_stats[MM_NONLEAF_TOTAL]++;
 
 		if (should_clear_pmd_young()) {
@@ -3516,7 +3529,7 @@ restart:
 			walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first);
 		}
 
-		if (!walk->force_scan && !test_bloom_filter(walk->lruvec, walk->max_seq, pmd + i))
+		if (!walk->force_scan && !test_bloom_filter(mm_state, walk->max_seq, pmd + i))
 			continue;
 
 		walk->mm_stats[MM_NONLEAF_FOUND]++;
@@ -3527,7 +3540,7 @@ restart:
 		walk->mm_stats[MM_NONLEAF_ADDED]++;
 
 		/* carry over to the next generation */
-		update_bloom_filter(walk->lruvec, walk->max_seq + 1, pmd + i);
+		update_bloom_filter(mm_state, walk->max_seq + 1, pmd + i);
 	}
 
 	walk_pmd_range_locked(pud, -1, vma, args, bitmap, &first);
@@ -3734,16 +3747,25 @@ next:
 	return success;
 }
 
-static void inc_max_seq(struct lruvec *lruvec, bool can_swap, bool force_scan)
+static bool inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
+			bool can_swap, bool force_scan)
 {
+	bool success;
 	int prev, next;
 	int type, zone;
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
 restart:
+	if (max_seq < READ_ONCE(lrugen->max_seq))
+		return false;
+
 	spin_lock_irq(&lruvec->lru_lock);
 
 	VM_WARN_ON_ONCE(!seq_is_valid(lruvec));
 
+	success = max_seq == lrugen->max_seq;
+	if (!success)
+		goto unlock;
+
 	for (type = ANON_AND_FILE - 1; type >= 0; type--) {
 		if (get_nr_gens(lruvec, type) != MAX_NR_GENS)
 			continue;
@@ -3787,8 +3809,10 @@ restart:
 	WRITE_ONCE(lrugen->timestamps[next], jiffies);
 	/* make sure preceding modifications appear */
 	smp_store_release(&lrugen->max_seq, lrugen->max_seq + 1);
-
+unlock:
 	spin_unlock_irq(&lruvec->lru_lock);
+
+	return success;
 }
 
 static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
@@ -3798,14 +3822,16 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
 	struct lru_gen_mm_walk *walk;
 	struct mm_struct *mm = NULL;
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
+	struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 
 	VM_WARN_ON_ONCE(max_seq > READ_ONCE(lrugen->max_seq));
 
+	if (!mm_state)
+		return inc_max_seq(lruvec, max_seq, can_swap, force_scan);
+
 	/* see the comment in iterate_mm_list() */
-	if (max_seq <= READ_ONCE(lruvec->mm_state.seq)) {
-		success = false;
-		goto done;
-	}
+	if (max_seq <= READ_ONCE(mm_state->seq))
+		return false;
 
 	/*
 	 * If the hardware doesn't automatically set the accessed bit, fallback
@@ -3835,8 +3861,10 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
 			walk_mm(lruvec, mm, walk);
 	} while (mm);
 done:
-	if (success)
-		inc_max_seq(lruvec, can_swap, force_scan);
+	if (success) {
+		success = inc_max_seq(lruvec, max_seq, can_swap, force_scan);
+		WARN_ON_ONCE(!success);
+	}
 
 	return success;
 }
@@ -3955,11 +3983,13 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 	int young = 0;
 	pte_t *pte = pvmw->pte;
 	unsigned long addr = pvmw->address;
+	struct vm_area_struct *vma = pvmw->vma;
 	struct folio *folio = pfn_folio(pvmw->pfn);
 	bool can_swap = !folio_is_file_lru(folio);
 	struct mem_cgroup *memcg = folio_memcg(folio);
 	struct pglist_data *pgdat = folio_pgdat(folio);
 	struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
+	struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 	DEFINE_MAX_SEQ(lruvec);
 	int old_gen, new_gen = lru_gen_from_seq(max_seq);
 
@@ -3969,11 +3999,15 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 	if (spin_is_contended(pvmw->ptl))
 		return;
 
+	/* exclude special VMAs containing anon pages from COW */
+	if (vma->vm_flags & VM_SPECIAL)
+		return;
+
 	/* avoid taking the LRU lock under the PTL when possible */
 	walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL;
 
-	start = max(addr & PMD_MASK, pvmw->vma->vm_start);
-	end = min(addr | ~PMD_MASK, pvmw->vma->vm_end - 1) + 1;
+	start = max(addr & PMD_MASK, vma->vm_start);
+	end = min(addr | ~PMD_MASK, vma->vm_end - 1) + 1;
 
 	if (end - start > MIN_LRU_BATCH * PAGE_SIZE) {
 		if (addr - start < MIN_LRU_BATCH * PAGE_SIZE / 2)
@@ -3998,7 +4032,7 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 		unsigned long pfn;
 		pte_t ptent = ptep_get(pte + i);
 
-		pfn = get_pte_pfn(ptent, pvmw->vma, addr);
+		pfn = get_pte_pfn(ptent, vma, addr);
 		if (pfn == -1)
 			continue;
 
@@ -4009,7 +4043,7 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 		if (!folio)
 			continue;
 
-		if (!ptep_test_and_clear_young(pvmw->vma, addr, pte + i))
+		if (!ptep_test_and_clear_young(vma, addr, pte + i))
 			VM_WARN_ON_ONCE(true);
 
 		young++;
@@ -4038,8 +4072,8 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 	mem_cgroup_unlock_pages();
 
 	/* feedback from rmap walkers to page table walkers */
-	if (suitable_to_scan(i, young))
-		update_bloom_filter(lruvec, max_seq, pvmw->pmd);
+	if (mm_state && suitable_to_scan(i, young))
+		update_bloom_filter(mm_state, max_seq, pvmw->pmd);
 }
 
 /******************************************************************************
@@ -4055,13 +4089,6 @@ enum {
 	MEMCG_LRU_YOUNG,
 };
 
-#ifdef CONFIG_MEMCG
-
-static int lru_gen_memcg_seg(struct lruvec *lruvec)
-{
-	return READ_ONCE(lruvec->lrugen.seg);
-}
-
 static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op)
 {
 	int seg;
@@ -4089,6 +4116,9 @@ static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op)
 	else
 		VM_WARN_ON_ONCE(true);
 
+	WRITE_ONCE(lruvec->lrugen.seg, seg);
+	WRITE_ONCE(lruvec->lrugen.gen, new);
+
 	hlist_nulls_del_rcu(&lruvec->lrugen.list);
 
 	if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD)
@@ -4099,15 +4129,14 @@ static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op)
 	pgdat->memcg_lru.nr_memcgs[old]--;
 	pgdat->memcg_lru.nr_memcgs[new]++;
 
-	lruvec->lrugen.gen = new;
-	WRITE_ONCE(lruvec->lrugen.seg, seg);
-
 	if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq))
 		WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1);
 
 	spin_unlock_irqrestore(&pgdat->memcg_lru.lock, flags);
 }
 
+#ifdef CONFIG_MEMCG
+
 void lru_gen_online_memcg(struct mem_cgroup *memcg)
 {
 	int gen;
@@ -4124,11 +4153,11 @@ void lru_gen_online_memcg(struct mem_cgroup *memcg)
 
 		gen = get_memcg_gen(pgdat->memcg_lru.seq);
 
+		lruvec->lrugen.gen = gen;
+
 		hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]);
 		pgdat->memcg_lru.nr_memcgs[gen]++;
 
-		lruvec->lrugen.gen = gen;
-
 		spin_unlock_irq(&pgdat->memcg_lru.lock);
 	}
 }
@@ -4175,18 +4204,11 @@ void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid)
 	struct lruvec *lruvec = get_lruvec(memcg, nid);
 
 	/* see the comment on MEMCG_NR_GENS */
-	if (lru_gen_memcg_seg(lruvec) != MEMCG_LRU_HEAD)
+	if (READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_HEAD)
 		lru_gen_rotate_memcg(lruvec, MEMCG_LRU_HEAD);
 }
 
-#else /* !CONFIG_MEMCG */
-
-static int lru_gen_memcg_seg(struct lruvec *lruvec)
-{
-	return 0;
-}
-
-#endif
+#endif /* CONFIG_MEMCG */
 
 /******************************************************************************
  *                          the eviction
@@ -4232,7 +4254,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
 	}
 
 	/* protected */
-	if (tier > tier_idx) {
+	if (tier > tier_idx || refs == BIT(LRU_REFS_WIDTH)) {
 		int hist = lru_hist_from_seq(lrugen->min_seq[type]);
 
 		gen = folio_inc_gen(lruvec, folio, false);
@@ -4598,7 +4620,12 @@ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq,
 	}
 
 	/* try to scrape all its memory if this memcg was deleted */
-	*nr_to_scan = mem_cgroup_online(memcg) ? (total >> sc->priority) : total;
+	if (!mem_cgroup_online(memcg)) {
+		*nr_to_scan = total;
+		return false;
+	}
+
+	*nr_to_scan = total >> sc->priority;
 
 	/*
 	 * The aging tries to be lazy to reduce the overhead, while the eviction
@@ -4635,7 +4662,7 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool
 	DEFINE_MAX_SEQ(lruvec);
 
 	if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg))
-		return 0;
+		return -1;
 
 	if (!should_run_aging(lruvec, max_seq, sc, can_swap, &nr_to_scan))
 		return nr_to_scan;
@@ -4648,20 +4675,41 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool
 	return try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, false) ? -1 : 0;
 }
 
-static unsigned long get_nr_to_reclaim(struct scan_control *sc)
+static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc)
 {
+	int i;
+	enum zone_watermarks mark;
+
 	/* don't abort memcg reclaim to ensure fairness */
 	if (!root_reclaim(sc))
-		return -1;
+		return false;
+
+	if (sc->nr_reclaimed >= max(sc->nr_to_reclaim, compact_gap(sc->order)))
+		return true;
+
+	/* check the order to exclude compaction-induced reclaim */
+	if (!current_is_kswapd() || sc->order)
+		return false;
+
+	mark = sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING ?
+	       WMARK_PROMO : WMARK_HIGH;
 
-	return max(sc->nr_to_reclaim, compact_gap(sc->order));
+	for (i = 0; i <= sc->reclaim_idx; i++) {
+		struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i;
+		unsigned long size = wmark_pages(zone, mark) + MIN_LRU_BATCH;
+
+		if (managed_zone(zone) && !zone_watermark_ok(zone, 0, size, sc->reclaim_idx, 0))
+			return false;
+	}
+
+	/* kswapd should abort if all eligible zones are safe */
+	return true;
 }
 
 static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 {
 	long nr_to_scan;
 	unsigned long scanned = 0;
-	unsigned long nr_to_reclaim = get_nr_to_reclaim(sc);
 	int swappiness = get_swappiness(lruvec, sc);
 
 	/* clean file folios are more likely to exist */
@@ -4683,13 +4731,13 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 		if (scanned >= nr_to_scan)
 			break;
 
-		if (sc->nr_reclaimed >= nr_to_reclaim)
+		if (should_abort_scan(lruvec, sc))
 			break;
 
 		cond_resched();
 	}
 
-	/* whether try_to_inc_max_seq() was successful */
+	/* whether this lruvec should be rotated */
 	return nr_to_scan < 0;
 }
 
@@ -4698,14 +4746,9 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
 	bool success;
 	unsigned long scanned = sc->nr_scanned;
 	unsigned long reclaimed = sc->nr_reclaimed;
-	int seg = lru_gen_memcg_seg(lruvec);
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 
-	/* see the comment on MEMCG_NR_GENS */
-	if (!lruvec_is_sizable(lruvec, sc))
-		return seg != MEMCG_LRU_TAIL ? MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG;
-
 	mem_cgroup_calculate_protection(NULL, memcg);
 
 	if (mem_cgroup_below_min(NULL, memcg))
@@ -4713,7 +4756,7 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
 
 	if (mem_cgroup_below_low(NULL, memcg)) {
 		/* see the comment on MEMCG_NR_GENS */
-		if (seg != MEMCG_LRU_TAIL)
+		if (READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_TAIL)
 			return MEMCG_LRU_TAIL;
 
 		memcg_memory_event(memcg, MEMCG_LOW);
@@ -4729,10 +4772,16 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
 
 	flush_reclaim_state(sc);
 
-	return success ? MEMCG_LRU_YOUNG : 0;
-}
+	if (success && mem_cgroup_online(memcg))
+		return MEMCG_LRU_YOUNG;
 
-#ifdef CONFIG_MEMCG
+	if (!success && lruvec_is_sizable(lruvec, sc))
+		return 0;
+
+	/* one retry if offlined or too small */
+	return READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_TAIL ?
+	       MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG;
+}
 
 static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc)
 {
@@ -4743,14 +4792,13 @@ static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc)
 	struct lruvec *lruvec;
 	struct lru_gen_folio *lrugen;
 	struct mem_cgroup *memcg;
-	const struct hlist_nulls_node *pos;
-	unsigned long nr_to_reclaim = get_nr_to_reclaim(sc);
+	struct hlist_nulls_node *pos;
 
+	gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq));
 	bin = first_bin = get_random_u32_below(MEMCG_NR_BINS);
 restart:
 	op = 0;
 	memcg = NULL;
-	gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq));
 
 	rcu_read_lock();
 
@@ -4761,6 +4809,10 @@ restart:
 		}
 
 		mem_cgroup_put(memcg);
+		memcg = NULL;
+
+		if (gen != READ_ONCE(lrugen->gen))
+			continue;
 
 		lruvec = container_of(lrugen, struct lruvec, lrugen);
 		memcg = lruvec_memcg(lruvec);
@@ -4777,7 +4829,7 @@ restart:
 
 		rcu_read_lock();
 
-		if (sc->nr_reclaimed >= nr_to_reclaim)
+		if (should_abort_scan(lruvec, sc))
 			break;
 	}
 
@@ -4788,7 +4840,7 @@ restart:
 
 	mem_cgroup_put(memcg);
 
-	if (sc->nr_reclaimed >= nr_to_reclaim)
+	if (!is_a_nulls(pos))
 		return;
 
 	/* restart if raced with lru_gen_rotate_memcg() */
@@ -4822,20 +4874,6 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc
 	blk_finish_plug(&plug);
 }
 
-#else /* !CONFIG_MEMCG */
-
-static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc)
-{
-	BUILD_BUG();
-}
-
-static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
-{
-	BUILD_BUG();
-}
-
-#endif
-
 static void set_initial_priority(struct pglist_data *pgdat, struct scan_control *sc)
 {
 	int priority;
@@ -4845,16 +4883,14 @@ static void set_initial_priority(struct pglist_data *pgdat, struct scan_control
 	if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH)
 		return;
 	/*
-	 * Determine the initial priority based on ((total / MEMCG_NR_GENS) >>
-	 * priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, where the
-	 * estimated reclaimed_to_scanned_ratio = inactive / total.
+	 * Determine the initial priority based on
+	 * (total >> priority) * reclaimed_to_scanned_ratio = nr_to_reclaim,
+	 * where reclaimed_to_scanned_ratio = inactive / total.
 	 */
 	reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE);
 	if (get_swappiness(lruvec, sc))
 		reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON);
 
-	reclaimable /= MEMCG_NR_GENS;
-
 	/* round down reclaimable and round up sc->nr_to_reclaim */
 	priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1);
 
@@ -5185,6 +5221,7 @@ static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec,
 	int type, tier;
 	int hist = lru_hist_from_seq(seq);
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
+	struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 
 	for (tier = 0; tier < MAX_NR_TIERS; tier++) {
 		seq_printf(m, "            %10d", tier);
@@ -5210,6 +5247,9 @@ static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec,
 		seq_putc(m, '\n');
 	}
 
+	if (!mm_state)
+		return;
+
 	seq_puts(m, "                      ");
 	for (i = 0; i < NR_MM_STATS; i++) {
 		const char *s = "      ";
@@ -5217,10 +5257,10 @@ static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec,
 
 		if (seq == max_seq && NR_HIST_GENS == 1) {
 			s = "LOYNFA";
-			n = READ_ONCE(lruvec->mm_state.stats[hist][i]);
+			n = READ_ONCE(mm_state->stats[hist][i]);
 		} else if (seq != max_seq && NR_HIST_GENS > 1) {
 			s = "loynfa";
-			n = READ_ONCE(lruvec->mm_state.stats[hist][i]);
+			n = READ_ONCE(mm_state->stats[hist][i]);
 		}
 
 		seq_printf(m, " %10lu%c", n, s[i]);
@@ -5484,11 +5524,24 @@ static const struct file_operations lru_gen_ro_fops = {
  *                          initialization
  ******************************************************************************/
 
+void lru_gen_init_pgdat(struct pglist_data *pgdat)
+{
+	int i, j;
+
+	spin_lock_init(&pgdat->memcg_lru.lock);
+
+	for (i = 0; i < MEMCG_NR_GENS; i++) {
+		for (j = 0; j < MEMCG_NR_BINS; j++)
+			INIT_HLIST_NULLS_HEAD(&pgdat->memcg_lru.fifo[i][j], i);
+	}
+}
+
 void lru_gen_init_lruvec(struct lruvec *lruvec)
 {
 	int i;
 	int gen, type, zone;
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
+	struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 
 	lrugen->max_seq = MIN_NR_GENS + 1;
 	lrugen->enabled = lru_gen_enabled();
@@ -5499,47 +5552,46 @@ void lru_gen_init_lruvec(struct lruvec *lruvec)
 	for_each_gen_type_zone(gen, type, zone)
 		INIT_LIST_HEAD(&lrugen->folios[gen][type][zone]);
 
-	lruvec->mm_state.seq = MIN_NR_GENS;
+	if (mm_state)
+		mm_state->seq = MIN_NR_GENS;
 }
 
 #ifdef CONFIG_MEMCG
 
-void lru_gen_init_pgdat(struct pglist_data *pgdat)
+void lru_gen_init_memcg(struct mem_cgroup *memcg)
 {
-	int i, j;
-
-	spin_lock_init(&pgdat->memcg_lru.lock);
+	struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
 
-	for (i = 0; i < MEMCG_NR_GENS; i++) {
-		for (j = 0; j < MEMCG_NR_BINS; j++)
-			INIT_HLIST_NULLS_HEAD(&pgdat->memcg_lru.fifo[i][j], i);
-	}
-}
+	if (!mm_list)
+		return;
 
-void lru_gen_init_memcg(struct mem_cgroup *memcg)
-{
-	INIT_LIST_HEAD(&memcg->mm_list.fifo);
-	spin_lock_init(&memcg->mm_list.lock);
+	INIT_LIST_HEAD(&mm_list->fifo);
+	spin_lock_init(&mm_list->lock);
 }
 
 void lru_gen_exit_memcg(struct mem_cgroup *memcg)
 {
 	int i;
 	int nid;
+	struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
 
-	VM_WARN_ON_ONCE(!list_empty(&memcg->mm_list.fifo));
+	VM_WARN_ON_ONCE(mm_list && !list_empty(&mm_list->fifo));
 
 	for_each_node(nid) {
 		struct lruvec *lruvec = get_lruvec(memcg, nid);
+		struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 
 		VM_WARN_ON_ONCE(memchr_inv(lruvec->lrugen.nr_pages, 0,
 					   sizeof(lruvec->lrugen.nr_pages)));
 
 		lruvec->lrugen.list.next = LIST_POISON1;
 
+		if (!mm_state)
+			continue;
+
 		for (i = 0; i < NR_BLOOM_FILTERS; i++) {
-			bitmap_free(lruvec->mm_state.filters[i]);
-			lruvec->mm_state.filters[i] = NULL;
+			bitmap_free(mm_state->filters[i]);
+			mm_state->filters[i] = NULL;
 		}
 	}
 }
@@ -5565,14 +5617,17 @@ late_initcall(init_lru_gen);
 
 static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
 {
+	BUILD_BUG();
 }
 
 static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 {
+	BUILD_BUG();
 }
 
 static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc)
 {
+	BUILD_BUG();
 }
 
 #endif /* CONFIG_LRU_GEN */
@@ -6365,7 +6420,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 	 * scan_control uses s8 fields for order, priority, and reclaim_idx.
 	 * Confirm they are large enough for max values.
 	 */
-	BUILD_BUG_ON(MAX_ORDER >= S8_MAX);
+	BUILD_BUG_ON(MAX_PAGE_ORDER >= S8_MAX);
 	BUILD_BUG_ON(DEF_PRIORITY > S8_MAX);
 	BUILD_BUG_ON(MAX_NR_ZONES > S8_MAX);
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 359460deb377..db79935e4a54 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1059,7 +1059,7 @@ static void fill_contig_page_info(struct zone *zone,
 	info->free_blocks_total = 0;
 	info->free_blocks_suitable = 0;
 
-	for (order = 0; order <= MAX_ORDER; order++) {
+	for (order = 0; order < NR_PAGE_ORDERS; order++) {
 		unsigned long blocks;
 
 		/*
@@ -1092,7 +1092,7 @@ static int __fragmentation_index(unsigned int order, struct contig_page_info *in
 {
 	unsigned long requested = 1UL << order;
 
-	if (WARN_ON_ONCE(order > MAX_ORDER))
+	if (WARN_ON_ONCE(order > MAX_PAGE_ORDER))
 		return 0;
 
 	if (!info->free_blocks_total)
@@ -1249,6 +1249,9 @@ const char * const vmstat_text[] = {
 	"pgpromote_success",
 	"pgpromote_candidate",
 #endif
+	"pgdemote_kswapd",
+	"pgdemote_direct",
+	"pgdemote_khugepaged",
 
 	/* enum writeback_stat_item counters */
 	"nr_dirty_threshold",
@@ -1279,9 +1282,6 @@ const char * const vmstat_text[] = {
 	"pgsteal_kswapd",
 	"pgsteal_direct",
 	"pgsteal_khugepaged",
-	"pgdemote_kswapd",
-	"pgdemote_direct",
-	"pgdemote_khugepaged",
 	"pgscan_kswapd",
 	"pgscan_direct",
 	"pgscan_khugepaged",
@@ -1401,6 +1401,7 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_ZSWAP
 	"zswpin",
 	"zswpout",
+	"zswpwb",
 #endif
 #ifdef CONFIG_X86
 	"direct_map_level2_splits",
@@ -1475,7 +1476,7 @@ static void frag_show_print(struct seq_file *m, pg_data_t *pgdat,
 	int order;
 
 	seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name);
-	for (order = 0; order <= MAX_ORDER; ++order)
+	for (order = 0; order < NR_PAGE_ORDERS; ++order)
 		/*
 		 * Access to nr_free is lockless as nr_free is used only for
 		 * printing purposes. Use data_race to avoid KCSAN warning.
@@ -1504,7 +1505,7 @@ static void pagetypeinfo_showfree_print(struct seq_file *m,
 					pgdat->node_id,
 					zone->name,
 					migratetype_names[mtype]);
-		for (order = 0; order <= MAX_ORDER; ++order) {
+		for (order = 0; order < NR_PAGE_ORDERS; ++order) {
 			unsigned long freecount = 0;
 			struct free_area *area;
 			struct list_head *curr;
@@ -1544,7 +1545,7 @@ static void pagetypeinfo_showfree(struct seq_file *m, void *arg)
 
 	/* Print header */
 	seq_printf(m, "%-43s ", "Free pages count per migrate type at order");
-	for (order = 0; order <= MAX_ORDER; ++order)
+	for (order = 0; order < NR_PAGE_ORDERS; ++order)
 		seq_printf(m, "%6d ", order);
 	seq_putc(m, '\n');
 
@@ -2180,7 +2181,7 @@ static void unusable_show_print(struct seq_file *m,
 	seq_printf(m, "Node %d, zone %8s ",
 				pgdat->node_id,
 				zone->name);
-	for (order = 0; order <= MAX_ORDER; ++order) {
+	for (order = 0; order < NR_PAGE_ORDERS; ++order) {
 		fill_contig_page_info(zone, order, &info);
 		index = unusable_free_index(order, &info);
 		seq_printf(m, "%d.%03d ", index / 1000, index % 1000);
@@ -2232,7 +2233,7 @@ static void extfrag_show_print(struct seq_file *m,
 	seq_printf(m, "Node %d, zone %8s ",
 				pgdat->node_id,
 				zone->name);
-	for (order = 0; order <= MAX_ORDER; ++order) {
+	for (order = 0; order < NR_PAGE_ORDERS; ++order) {
 		fill_contig_page_info(zone, order, &info);
 		index = __fragmentation_index(order, &info);
 		seq_printf(m, "%2d.%03d ", index / 1000, index % 1000);
diff --git a/mm/workingset.c b/mm/workingset.c
index b192e44a0e7c..226012974328 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -313,10 +313,10 @@ static void lru_gen_refault(struct folio *folio, void *shadow)
 	 * 1. For pages accessed through page tables, hotter pages pushed out
 	 *    hot pages which refaulted immediately.
 	 * 2. For pages accessed multiple times through file descriptors,
-	 *    numbers of accesses might have been out of the range.
+	 *    they would have been protected by sort_folio().
 	 */
-	if (lru_gen_in_fault() || refs == BIT(LRU_REFS_WIDTH)) {
-		folio_set_workingset(folio);
+	if (lru_gen_in_fault() || refs >= BIT(LRU_REFS_WIDTH) - 1) {
+		set_mask_bits(&folio->flags, 0, LRU_REFS_MASK | BIT(PG_workingset));
 		mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta);
 	}
 unlock:
@@ -425,8 +425,16 @@ bool workingset_test_recent(void *shadow, bool file, bool *workingset)
 	struct pglist_data *pgdat;
 	unsigned long eviction;
 
-	if (lru_gen_enabled())
-		return lru_gen_test_recent(shadow, file, &eviction_lruvec, &eviction, workingset);
+	rcu_read_lock();
+
+	if (lru_gen_enabled()) {
+		bool recent = lru_gen_test_recent(shadow, file,
+				&eviction_lruvec, &eviction, workingset);
+
+		rcu_read_unlock();
+		return recent;
+	}
+
 
 	unpack_shadow(shadow, &memcgid, &pgdat, &eviction, workingset);
 	eviction <<= bucket_order;
@@ -448,8 +456,20 @@ bool workingset_test_recent(void *shadow, bool file, bool *workingset)
 	 * configurations instead.
 	 */
 	eviction_memcg = mem_cgroup_from_id(memcgid);
-	if (!mem_cgroup_disabled() && !eviction_memcg)
+	if (!mem_cgroup_disabled() &&
+	    (!eviction_memcg || !mem_cgroup_tryget(eviction_memcg))) {
+		rcu_read_unlock();
 		return false;
+	}
+
+	rcu_read_unlock();
+
+	/*
+	 * Flush stats (and potentially sleep) outside the RCU read section.
+	 * XXX: With per-memcg flushing and thresholding, is ratelimiting
+	 * still needed here?
+	 */
+	mem_cgroup_flush_stats_ratelimited(eviction_memcg);
 
 	eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat);
 	refault = atomic_long_read(&eviction_lruvec->nonresident_age);
@@ -493,6 +513,7 @@ bool workingset_test_recent(void *shadow, bool file, bool *workingset)
 		}
 	}
 
+	mem_cgroup_put(eviction_memcg);
 	return refault_distance <= workingset_size;
 }
 
@@ -519,19 +540,16 @@ void workingset_refault(struct folio *folio, void *shadow)
 		return;
 	}
 
-	/* Flush stats (and potentially sleep) before holding RCU read lock */
-	mem_cgroup_flush_stats_ratelimited();
-
-	rcu_read_lock();
-
 	/*
 	 * The activation decision for this folio is made at the level
 	 * where the eviction occurred, as that is where the LRU order
 	 * during folio reclaim is being determined.
 	 *
 	 * However, the cgroup that will own the folio is the one that
-	 * is actually experiencing the refault event.
+	 * is actually experiencing the refault event. Make sure the folio is
+	 * locked to guarantee folio_memcg() stability throughout.
 	 */
+	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 	nr = folio_nr_pages(folio);
 	memcg = folio_memcg(folio);
 	pgdat = folio_pgdat(folio);
@@ -540,7 +558,7 @@ void workingset_refault(struct folio *folio, void *shadow)
 	mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr);
 
 	if (!workingset_test_recent(shadow, file, &workingset))
-		goto out;
+		return;
 
 	folio_set_active(folio);
 	workingset_age_nonresident(lruvec, nr);
@@ -556,8 +574,6 @@ void workingset_refault(struct folio *folio, void *shadow)
 		lru_note_cost_refault(folio);
 		mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file, nr);
 	}
-out:
-	rcu_read_unlock();
 }
 
 /**
@@ -615,12 +631,12 @@ void workingset_update_node(struct xa_node *node)
 
 	if (node->count && node->count == node->nr_values) {
 		if (list_empty(&node->private_list)) {
-			list_lru_add(&shadow_nodes, &node->private_list);
+			list_lru_add_obj(&shadow_nodes, &node->private_list);
 			__inc_lruvec_kmem_state(node, WORKINGSET_NODES);
 		}
 	} else {
 		if (!list_empty(&node->private_list)) {
-			list_lru_del(&shadow_nodes, &node->private_list);
+			list_lru_del_obj(&shadow_nodes, &node->private_list);
 			__dec_lruvec_kmem_state(node, WORKINGSET_NODES);
 		}
 	}
@@ -664,7 +680,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
 		struct lruvec *lruvec;
 		int i;
 
-		mem_cgroup_flush_stats();
+		mem_cgroup_flush_stats_ratelimited(sc->memcg);
 		lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid));
 		for (pages = 0, i = 0; i < NR_LRU_LISTS; i++)
 			pages += lruvec_page_state_local(lruvec,
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index b1c0dad7f4cf..c937635e0ad1 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -1364,9 +1364,12 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp)
 	int newfg;
 	struct zspage *zspage;
 
-	if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE))
+	if (unlikely(!size))
 		return (unsigned long)ERR_PTR(-EINVAL);
 
+	if (unlikely(size > ZS_MAX_ALLOC_SIZE))
+		return (unsigned long)ERR_PTR(-ENOSPC);
+
 	handle = cache_alloc_handle(pool, gfp);
 	if (!handle)
 		return (unsigned long)ERR_PTR(-ENOMEM);
diff --git a/mm/zswap.c b/mm/zswap.c
index 74411dfdad92..ca25b676048e 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -35,6 +35,7 @@
 #include <linux/writeback.h>
 #include <linux/pagemap.h>
 #include <linux/workqueue.h>
+#include <linux/list_lru.h>
 
 #include "swap.h"
 #include "internal.h"
@@ -147,6 +148,16 @@ module_param_named(exclusive_loads, zswap_exclusive_loads_enabled, bool, 0644);
 /* Number of zpools in zswap_pool (empirically determined for scalability) */
 #define ZSWAP_NR_ZPOOLS 32
 
+/* Enable/disable memory pressure-based shrinker. */
+static bool zswap_shrinker_enabled = IS_ENABLED(
+		CONFIG_ZSWAP_SHRINKER_DEFAULT_ON);
+module_param_named(shrinker_enabled, zswap_shrinker_enabled, bool, 0644);
+
+bool is_zswap_enabled(void)
+{
+	return zswap_enabled;
+}
+
 /*********************************
 * data structures
 **********************************/
@@ -155,8 +166,8 @@ struct crypto_acomp_ctx {
 	struct crypto_acomp *acomp;
 	struct acomp_req *req;
 	struct crypto_wait wait;
-	u8 *dstmem;
-	struct mutex *mutex;
+	u8 *buffer;
+	struct mutex mutex;
 };
 
 /*
@@ -174,8 +185,10 @@ struct zswap_pool {
 	struct work_struct shrink_work;
 	struct hlist_node node;
 	char tfm_name[CRYPTO_MAX_ALG_NAME];
-	struct list_head lru;
-	spinlock_t lru_lock;
+	struct list_lru list_lru;
+	struct mem_cgroup *next_shrink;
+	struct shrinker *shrinker;
+	atomic_t nr_stored;
 };
 
 /*
@@ -274,32 +287,72 @@ static bool zswap_can_accept(void)
 			DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE);
 }
 
+static u64 get_zswap_pool_size(struct zswap_pool *pool)
+{
+	u64 pool_size = 0;
+	int i;
+
+	for (i = 0; i < ZSWAP_NR_ZPOOLS; i++)
+		pool_size += zpool_get_total_size(pool->zpools[i]);
+
+	return pool_size;
+}
+
 static void zswap_update_total_size(void)
 {
 	struct zswap_pool *pool;
 	u64 total = 0;
-	int i;
 
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(pool, &zswap_pools, list)
-		for (i = 0; i < ZSWAP_NR_ZPOOLS; i++)
-			total += zpool_get_total_size(pool->zpools[i]);
+		total += get_zswap_pool_size(pool);
 
 	rcu_read_unlock();
 
 	zswap_pool_total_size = total;
 }
 
+/* should be called under RCU */
+#ifdef CONFIG_MEMCG
+static inline struct mem_cgroup *mem_cgroup_from_entry(struct zswap_entry *entry)
+{
+	return entry->objcg ? obj_cgroup_memcg(entry->objcg) : NULL;
+}
+#else
+static inline struct mem_cgroup *mem_cgroup_from_entry(struct zswap_entry *entry)
+{
+	return NULL;
+}
+#endif
+
+static inline int entry_to_nid(struct zswap_entry *entry)
+{
+	return page_to_nid(virt_to_page(entry));
+}
+
+void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg)
+{
+	struct zswap_pool *pool;
+
+	/* lock out zswap pools list modification */
+	spin_lock(&zswap_pools_lock);
+	list_for_each_entry(pool, &zswap_pools, list) {
+		if (pool->next_shrink == memcg)
+			pool->next_shrink = mem_cgroup_iter(NULL, pool->next_shrink, NULL);
+	}
+	spin_unlock(&zswap_pools_lock);
+}
+
 /*********************************
 * zswap entry functions
 **********************************/
 static struct kmem_cache *zswap_entry_cache;
 
-static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp)
+static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp, int nid)
 {
 	struct zswap_entry *entry;
-	entry = kmem_cache_alloc(zswap_entry_cache, gfp);
+	entry = kmem_cache_alloc_node(zswap_entry_cache, gfp, nid);
 	if (!entry)
 		return NULL;
 	entry->refcount = 1;
@@ -313,6 +366,100 @@ static void zswap_entry_cache_free(struct zswap_entry *entry)
 }
 
 /*********************************
+* zswap lruvec functions
+**********************************/
+void zswap_lruvec_state_init(struct lruvec *lruvec)
+{
+	atomic_long_set(&lruvec->zswap_lruvec_state.nr_zswap_protected, 0);
+}
+
+void zswap_folio_swapin(struct folio *folio)
+{
+	struct lruvec *lruvec;
+
+	if (folio) {
+		lruvec = folio_lruvec(folio);
+		atomic_long_inc(&lruvec->zswap_lruvec_state.nr_zswap_protected);
+	}
+}
+
+/*********************************
+* lru functions
+**********************************/
+static void zswap_lru_add(struct list_lru *list_lru, struct zswap_entry *entry)
+{
+	atomic_long_t *nr_zswap_protected;
+	unsigned long lru_size, old, new;
+	int nid = entry_to_nid(entry);
+	struct mem_cgroup *memcg;
+	struct lruvec *lruvec;
+
+	/*
+	 * Note that it is safe to use rcu_read_lock() here, even in the face of
+	 * concurrent memcg offlining. Thanks to the memcg->kmemcg_id indirection
+	 * used in list_lru lookup, only two scenarios are possible:
+	 *
+	 * 1. list_lru_add() is called before memcg->kmemcg_id is updated. The
+	 *    new entry will be reparented to memcg's parent's list_lru.
+	 * 2. list_lru_add() is called after memcg->kmemcg_id is updated. The
+	 *    new entry will be added directly to memcg's parent's list_lru.
+	 *
+	 * Similar reasoning holds for list_lru_del() and list_lru_putback().
+	 */
+	rcu_read_lock();
+	memcg = mem_cgroup_from_entry(entry);
+	/* will always succeed */
+	list_lru_add(list_lru, &entry->lru, nid, memcg);
+
+	/* Update the protection area */
+	lru_size = list_lru_count_one(list_lru, nid, memcg);
+	lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid));
+	nr_zswap_protected = &lruvec->zswap_lruvec_state.nr_zswap_protected;
+	old = atomic_long_inc_return(nr_zswap_protected);
+	/*
+	 * Decay to avoid overflow and adapt to changing workloads.
+	 * This is based on LRU reclaim cost decaying heuristics.
+	 */
+	do {
+		new = old > lru_size / 4 ? old / 2 : old;
+	} while (!atomic_long_try_cmpxchg(nr_zswap_protected, &old, new));
+	rcu_read_unlock();
+}
+
+static void zswap_lru_del(struct list_lru *list_lru, struct zswap_entry *entry)
+{
+	int nid = entry_to_nid(entry);
+	struct mem_cgroup *memcg;
+
+	rcu_read_lock();
+	memcg = mem_cgroup_from_entry(entry);
+	/* will always succeed */
+	list_lru_del(list_lru, &entry->lru, nid, memcg);
+	rcu_read_unlock();
+}
+
+static void zswap_lru_putback(struct list_lru *list_lru,
+		struct zswap_entry *entry)
+{
+	int nid = entry_to_nid(entry);
+	spinlock_t *lock = &list_lru->node[nid].lock;
+	struct mem_cgroup *memcg;
+	struct lruvec *lruvec;
+
+	rcu_read_lock();
+	memcg = mem_cgroup_from_entry(entry);
+	spin_lock(lock);
+	/* we cannot use list_lru_add here, because it increments node's lru count */
+	list_lru_putback(list_lru, &entry->lru, nid, memcg);
+	spin_unlock(lock);
+
+	lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(entry_to_nid(entry)));
+	/* increment the protection area to account for the LRU rotation. */
+	atomic_long_inc(&lruvec->zswap_lruvec_state.nr_zswap_protected);
+	rcu_read_unlock();
+}
+
+/*********************************
 * rbtree functions
 **********************************/
 static struct zswap_entry *zswap_rb_search(struct rb_root *root, pgoff_t offset)
@@ -396,10 +543,9 @@ static void zswap_free_entry(struct zswap_entry *entry)
 	if (!entry->length)
 		atomic_dec(&zswap_same_filled_pages);
 	else {
-		spin_lock(&entry->pool->lru_lock);
-		list_del(&entry->lru);
-		spin_unlock(&entry->pool->lru_lock);
+		zswap_lru_del(&entry->pool->list_lru, entry);
 		zpool_free(zswap_find_zpool(entry), entry->handle);
+		atomic_dec(&entry->pool->nr_stored);
 		zswap_pool_put(entry->pool);
 	}
 	zswap_entry_cache_free(entry);
@@ -442,65 +588,132 @@ static struct zswap_entry *zswap_entry_find_get(struct rb_root *root,
 }
 
 /*********************************
-* per-cpu code
+* shrinker functions
 **********************************/
-static DEFINE_PER_CPU(u8 *, zswap_dstmem);
-/*
- * If users dynamically change the zpool type and compressor at runtime, i.e.
- * zswap is running, zswap can have more than one zpool on one cpu, but they
- * are sharing dtsmem. So we need this mutex to be per-cpu.
- */
-static DEFINE_PER_CPU(struct mutex *, zswap_mutex);
+static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_one *l,
+				       spinlock_t *lock, void *arg);
 
-static int zswap_dstmem_prepare(unsigned int cpu)
+static unsigned long zswap_shrinker_scan(struct shrinker *shrinker,
+		struct shrink_control *sc)
 {
-	struct mutex *mutex;
-	u8 *dst;
+	struct lruvec *lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid));
+	unsigned long shrink_ret, nr_protected, lru_size;
+	struct zswap_pool *pool = shrinker->private_data;
+	bool encountered_page_in_swapcache = false;
+
+	if (!zswap_shrinker_enabled ||
+			!mem_cgroup_zswap_writeback_enabled(sc->memcg)) {
+		sc->nr_scanned = 0;
+		return SHRINK_STOP;
+	}
 
-	dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
-	if (!dst)
-		return -ENOMEM;
+	nr_protected =
+		atomic_long_read(&lruvec->zswap_lruvec_state.nr_zswap_protected);
+	lru_size = list_lru_shrink_count(&pool->list_lru, sc);
 
-	mutex = kmalloc_node(sizeof(*mutex), GFP_KERNEL, cpu_to_node(cpu));
-	if (!mutex) {
-		kfree(dst);
-		return -ENOMEM;
+	/*
+	 * Abort if we are shrinking into the protected region.
+	 *
+	 * This short-circuiting is necessary because if we have too many multiple
+	 * concurrent reclaimers getting the freeable zswap object counts at the
+	 * same time (before any of them made reasonable progress), the total
+	 * number of reclaimed objects might be more than the number of unprotected
+	 * objects (i.e the reclaimers will reclaim into the protected area of the
+	 * zswap LRU).
+	 */
+	if (nr_protected >= lru_size - sc->nr_to_scan) {
+		sc->nr_scanned = 0;
+		return SHRINK_STOP;
 	}
 
-	mutex_init(mutex);
-	per_cpu(zswap_dstmem, cpu) = dst;
-	per_cpu(zswap_mutex, cpu) = mutex;
-	return 0;
+	shrink_ret = list_lru_shrink_walk(&pool->list_lru, sc, &shrink_memcg_cb,
+		&encountered_page_in_swapcache);
+
+	if (encountered_page_in_swapcache)
+		return SHRINK_STOP;
+
+	return shrink_ret ? shrink_ret : SHRINK_STOP;
 }
 
-static int zswap_dstmem_dead(unsigned int cpu)
+static unsigned long zswap_shrinker_count(struct shrinker *shrinker,
+		struct shrink_control *sc)
 {
-	struct mutex *mutex;
-	u8 *dst;
+	struct zswap_pool *pool = shrinker->private_data;
+	struct mem_cgroup *memcg = sc->memcg;
+	struct lruvec *lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(sc->nid));
+	unsigned long nr_backing, nr_stored, nr_freeable, nr_protected;
 
-	mutex = per_cpu(zswap_mutex, cpu);
-	kfree(mutex);
-	per_cpu(zswap_mutex, cpu) = NULL;
+	if (!zswap_shrinker_enabled || !mem_cgroup_zswap_writeback_enabled(memcg))
+		return 0;
 
-	dst = per_cpu(zswap_dstmem, cpu);
-	kfree(dst);
-	per_cpu(zswap_dstmem, cpu) = NULL;
+#ifdef CONFIG_MEMCG_KMEM
+	mem_cgroup_flush_stats(memcg);
+	nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT;
+	nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED);
+#else
+	/* use pool stats instead of memcg stats */
+	nr_backing = get_zswap_pool_size(pool) >> PAGE_SHIFT;
+	nr_stored = atomic_read(&pool->nr_stored);
+#endif
 
-	return 0;
+	if (!nr_stored)
+		return 0;
+
+	nr_protected =
+		atomic_long_read(&lruvec->zswap_lruvec_state.nr_zswap_protected);
+	nr_freeable = list_lru_shrink_count(&pool->list_lru, sc);
+	/*
+	 * Subtract the lru size by an estimate of the number of pages
+	 * that should be protected.
+	 */
+	nr_freeable = nr_freeable > nr_protected ? nr_freeable - nr_protected : 0;
+
+	/*
+	 * Scale the number of freeable pages by the memory saving factor.
+	 * This ensures that the better zswap compresses memory, the fewer
+	 * pages we will evict to swap (as it will otherwise incur IO for
+	 * relatively small memory saving).
+	 */
+	return mult_frac(nr_freeable, nr_backing, nr_stored);
+}
+
+static void zswap_alloc_shrinker(struct zswap_pool *pool)
+{
+	pool->shrinker =
+		shrinker_alloc(SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, "mm-zswap");
+	if (!pool->shrinker)
+		return;
+
+	pool->shrinker->private_data = pool;
+	pool->shrinker->scan_objects = zswap_shrinker_scan;
+	pool->shrinker->count_objects = zswap_shrinker_count;
+	pool->shrinker->batch = 0;
+	pool->shrinker->seeks = DEFAULT_SEEKS;
 }
 
+/*********************************
+* per-cpu code
+**********************************/
 static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 {
 	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
 	struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu);
 	struct crypto_acomp *acomp;
 	struct acomp_req *req;
+	int ret;
+
+	mutex_init(&acomp_ctx->mutex);
+
+	acomp_ctx->buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
+	if (!acomp_ctx->buffer)
+		return -ENOMEM;
 
 	acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu));
 	if (IS_ERR(acomp)) {
 		pr_err("could not alloc crypto acomp %s : %ld\n",
 				pool->tfm_name, PTR_ERR(acomp));
-		return PTR_ERR(acomp);
+		ret = PTR_ERR(acomp);
+		goto acomp_fail;
 	}
 	acomp_ctx->acomp = acomp;
 
@@ -508,8 +721,8 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 	if (!req) {
 		pr_err("could not alloc crypto acomp_request %s\n",
 		       pool->tfm_name);
-		crypto_free_acomp(acomp_ctx->acomp);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto req_fail;
 	}
 	acomp_ctx->req = req;
 
@@ -522,10 +735,13 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 	acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 				   crypto_req_done, &acomp_ctx->wait);
 
-	acomp_ctx->mutex = per_cpu(zswap_mutex, cpu);
-	acomp_ctx->dstmem = per_cpu(zswap_dstmem, cpu);
-
 	return 0;
+
+req_fail:
+	crypto_free_acomp(acomp_ctx->acomp);
+acomp_fail:
+	kfree(acomp_ctx->buffer);
+	return ret;
 }
 
 static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node)
@@ -538,6 +754,7 @@ static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node)
 			acomp_request_free(acomp_ctx->req);
 		if (!IS_ERR_OR_NULL(acomp_ctx->acomp))
 			crypto_free_acomp(acomp_ctx->acomp);
+		kfree(acomp_ctx->buffer);
 	}
 
 	return 0;
@@ -632,21 +849,16 @@ static void zswap_invalidate_entry(struct zswap_tree *tree,
 		zswap_entry_put(tree, entry);
 }
 
-static int zswap_reclaim_entry(struct zswap_pool *pool)
+static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_one *l,
+				       spinlock_t *lock, void *arg)
 {
-	struct zswap_entry *entry;
+	struct zswap_entry *entry = container_of(item, struct zswap_entry, lru);
+	bool *encountered_page_in_swapcache = (bool *)arg;
 	struct zswap_tree *tree;
 	pgoff_t swpoffset;
-	int ret;
+	enum lru_status ret = LRU_REMOVED_RETRY;
+	int writeback_result;
 
-	/* Get an entry off the LRU */
-	spin_lock(&pool->lru_lock);
-	if (list_empty(&pool->lru)) {
-		spin_unlock(&pool->lru_lock);
-		return -EINVAL;
-	}
-	entry = list_last_entry(&pool->lru, struct zswap_entry, lru);
-	list_del_init(&entry->lru);
 	/*
 	 * Once the lru lock is dropped, the entry might get freed. The
 	 * swpoffset is copied to the stack, and entry isn't deref'd again
@@ -654,29 +866,48 @@ static int zswap_reclaim_entry(struct zswap_pool *pool)
 	 */
 	swpoffset = swp_offset(entry->swpentry);
 	tree = zswap_trees[swp_type(entry->swpentry)];
-	spin_unlock(&pool->lru_lock);
+	list_lru_isolate(l, item);
+	/*
+	 * It's safe to drop the lock here because we return either
+	 * LRU_REMOVED_RETRY or LRU_RETRY.
+	 */
+	spin_unlock(lock);
 
 	/* Check for invalidate() race */
 	spin_lock(&tree->lock);
-	if (entry != zswap_rb_search(&tree->rbroot, swpoffset)) {
-		ret = -EAGAIN;
+	if (entry != zswap_rb_search(&tree->rbroot, swpoffset))
 		goto unlock;
-	}
+
 	/* Hold a reference to prevent a free during writeback */
 	zswap_entry_get(entry);
 	spin_unlock(&tree->lock);
 
-	ret = zswap_writeback_entry(entry, tree);
+	writeback_result = zswap_writeback_entry(entry, tree);
 
 	spin_lock(&tree->lock);
-	if (ret) {
-		/* Writeback failed, put entry back on LRU */
-		spin_lock(&pool->lru_lock);
-		list_move(&entry->lru, &pool->lru);
-		spin_unlock(&pool->lru_lock);
+	if (writeback_result) {
+		zswap_reject_reclaim_fail++;
+		zswap_lru_putback(&entry->pool->list_lru, entry);
+		ret = LRU_RETRY;
+
+		/*
+		 * Encountering a page already in swap cache is a sign that we are shrinking
+		 * into the warmer region. We should terminate shrinking (if we're in the dynamic
+		 * shrinker context).
+		 */
+		if (writeback_result == -EEXIST && encountered_page_in_swapcache) {
+			ret = LRU_SKIP;
+			*encountered_page_in_swapcache = true;
+		}
+
 		goto put_unlock;
 	}
+	zswap_written_back_pages++;
+
+	if (entry->objcg)
+		count_objcg_event(entry->objcg, ZSWPWB);
 
+	count_vm_event(ZSWPWB);
 	/*
 	 * Writeback started successfully, the page now belongs to the
 	 * swapcache. Drop the entry from zswap - unless invalidate already
@@ -689,24 +920,94 @@ put_unlock:
 	zswap_entry_put(tree, entry);
 unlock:
 	spin_unlock(&tree->lock);
-	return ret ? -EAGAIN : 0;
+	spin_lock(lock);
+	return ret;
+}
+
+static int shrink_memcg(struct mem_cgroup *memcg)
+{
+	struct zswap_pool *pool;
+	int nid, shrunk = 0;
+
+	if (!mem_cgroup_zswap_writeback_enabled(memcg))
+		return -EINVAL;
+
+	/*
+	 * Skip zombies because their LRUs are reparented and we would be
+	 * reclaiming from the parent instead of the dead memcg.
+	 */
+	if (memcg && !mem_cgroup_online(memcg))
+		return -ENOENT;
+
+	pool = zswap_pool_current_get();
+	if (!pool)
+		return -EINVAL;
+
+	for_each_node_state(nid, N_NORMAL_MEMORY) {
+		unsigned long nr_to_walk = 1;
+
+		shrunk += list_lru_walk_one(&pool->list_lru, nid, memcg,
+					    &shrink_memcg_cb, NULL, &nr_to_walk);
+	}
+	zswap_pool_put(pool);
+	return shrunk ? 0 : -EAGAIN;
 }
 
 static void shrink_worker(struct work_struct *w)
 {
 	struct zswap_pool *pool = container_of(w, typeof(*pool),
 						shrink_work);
+	struct mem_cgroup *memcg;
 	int ret, failures = 0;
 
+	/* global reclaim will select cgroup in a round-robin fashion. */
 	do {
-		ret = zswap_reclaim_entry(pool);
-		if (ret) {
-			zswap_reject_reclaim_fail++;
-			if (ret != -EAGAIN)
+		spin_lock(&zswap_pools_lock);
+		pool->next_shrink = mem_cgroup_iter(NULL, pool->next_shrink, NULL);
+		memcg = pool->next_shrink;
+
+		/*
+		 * We need to retry if we have gone through a full round trip, or if we
+		 * got an offline memcg (or else we risk undoing the effect of the
+		 * zswap memcg offlining cleanup callback). This is not catastrophic
+		 * per se, but it will keep the now offlined memcg hostage for a while.
+		 *
+		 * Note that if we got an online memcg, we will keep the extra
+		 * reference in case the original reference obtained by mem_cgroup_iter
+		 * is dropped by the zswap memcg offlining callback, ensuring that the
+		 * memcg is not killed when we are reclaiming.
+		 */
+		if (!memcg) {
+			spin_unlock(&zswap_pools_lock);
+			if (++failures == MAX_RECLAIM_RETRIES)
 				break;
+
+			goto resched;
+		}
+
+		if (!mem_cgroup_tryget_online(memcg)) {
+			/* drop the reference from mem_cgroup_iter() */
+			mem_cgroup_iter_break(NULL, memcg);
+			pool->next_shrink = NULL;
+			spin_unlock(&zswap_pools_lock);
+
 			if (++failures == MAX_RECLAIM_RETRIES)
 				break;
+
+			goto resched;
 		}
+		spin_unlock(&zswap_pools_lock);
+
+		ret = shrink_memcg(memcg);
+		/* drop the extra reference */
+		mem_cgroup_put(memcg);
+
+		if (ret == -EINVAL)
+			break;
+		if (ret && ++failures == MAX_RECLAIM_RETRIES)
+			break;
+
+resched:
 		cond_resched();
 	} while (!zswap_can_accept());
 	zswap_pool_put(pool);
@@ -760,6 +1061,11 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 				       &pool->node);
 	if (ret)
 		goto error;
+
+	zswap_alloc_shrinker(pool);
+	if (!pool->shrinker)
+		goto error;
+
 	pr_debug("using %s compressor\n", pool->tfm_name);
 
 	/* being the current pool takes 1 ref; this func expects the
@@ -767,14 +1073,19 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 	 */
 	kref_init(&pool->kref);
 	INIT_LIST_HEAD(&pool->list);
-	INIT_LIST_HEAD(&pool->lru);
-	spin_lock_init(&pool->lru_lock);
+	if (list_lru_init_memcg(&pool->list_lru, pool->shrinker))
+		goto lru_fail;
+	shrinker_register(pool->shrinker);
 	INIT_WORK(&pool->shrink_work, shrink_worker);
+	atomic_set(&pool->nr_stored, 0);
 
 	zswap_pool_debug("created", pool);
 
 	return pool;
 
+lru_fail:
+	list_lru_destroy(&pool->list_lru);
+	shrinker_free(pool->shrinker);
 error:
 	if (pool->acomp_ctx)
 		free_percpu(pool->acomp_ctx);
@@ -832,8 +1143,16 @@ static void zswap_pool_destroy(struct zswap_pool *pool)
 
 	zswap_pool_debug("destroying", pool);
 
+	shrinker_free(pool->shrinker);
 	cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node);
 	free_percpu(pool->acomp_ctx);
+	list_lru_destroy(&pool->list_lru);
+
+	spin_lock(&zswap_pools_lock);
+	mem_cgroup_iter_break(NULL, pool->next_shrink);
+	pool->next_shrink = NULL;
+	spin_unlock(&zswap_pools_lock);
+
 	for (i = 0; i < ZSWAP_NR_ZPOOLS; i++)
 		zpool_destroy_pool(pool->zpools[i]);
 	kfree(pool);
@@ -1040,18 +1359,47 @@ static int zswap_enabled_param_set(const char *val,
 	return ret;
 }
 
+static void __zswap_load(struct zswap_entry *entry, struct page *page)
+{
+	struct zpool *zpool = zswap_find_zpool(entry);
+	struct scatterlist input, output;
+	struct crypto_acomp_ctx *acomp_ctx;
+	u8 *src;
+
+	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
+	mutex_lock(&acomp_ctx->mutex);
+
+	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
+	if (!zpool_can_sleep_mapped(zpool)) {
+		memcpy(acomp_ctx->buffer, src, entry->length);
+		src = acomp_ctx->buffer;
+		zpool_unmap_handle(zpool, entry->handle);
+	}
+
+	sg_init_one(&input, src, entry->length);
+	sg_init_table(&output, 1);
+	sg_set_page(&output, page, PAGE_SIZE, 0);
+	acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, PAGE_SIZE);
+	BUG_ON(crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait));
+	BUG_ON(acomp_ctx->req->dlen != PAGE_SIZE);
+	mutex_unlock(&acomp_ctx->mutex);
+
+	if (zpool_can_sleep_mapped(zpool))
+		zpool_unmap_handle(zpool, entry->handle);
+}
+
 /*********************************
 * writeback code
 **********************************/
 /*
- * Attempts to free an entry by adding a page to the swap cache,
- * decompressing the entry data into the page, and issuing a
- * bio write to write the page back to the swap device.
+ * Attempts to free an entry by adding a folio to the swap cache,
+ * decompressing the entry data into the folio, and issuing a
+ * bio write to write the folio back to the swap device.
  *
- * This can be thought of as a "resumed writeback" of the page
+ * This can be thought of as a "resumed writeback" of the folio
  * to the swap device.  We are basically resuming the same swap
  * writeback path that was intercepted with the zswap_store()
- * in the first place.  After the page has been decompressed into
+ * in the first place.  After the folio has been decompressed into
  * the swap cache, the compressed version stored by zswap can be
  * freed.
  */
@@ -1059,108 +1407,58 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 				 struct zswap_tree *tree)
 {
 	swp_entry_t swpentry = entry->swpentry;
-	struct page *page;
+	struct folio *folio;
 	struct mempolicy *mpol;
-	struct scatterlist input, output;
-	struct crypto_acomp_ctx *acomp_ctx;
-	struct zpool *pool = zswap_find_zpool(entry);
-	bool page_was_allocated;
-	u8 *src, *tmp = NULL;
-	unsigned int dlen;
-	int ret;
+	bool folio_was_allocated;
 	struct writeback_control wbc = {
 		.sync_mode = WB_SYNC_NONE,
 	};
 
-	if (!zpool_can_sleep_mapped(pool)) {
-		tmp = kmalloc(PAGE_SIZE, GFP_KERNEL);
-		if (!tmp)
-			return -ENOMEM;
-	}
-
-	/* try to allocate swap cache page */
+	/* try to allocate swap cache folio */
 	mpol = get_task_policy(current);
-	page = __read_swap_cache_async(swpentry, GFP_KERNEL, mpol,
-				NO_INTERLEAVE_INDEX, &page_was_allocated);
-	if (!page) {
-		ret = -ENOMEM;
-		goto fail;
-	}
+	folio = __read_swap_cache_async(swpentry, GFP_KERNEL, mpol,
+				NO_INTERLEAVE_INDEX, &folio_was_allocated, true);
+	if (!folio)
+		return -ENOMEM;
 
-	/* Found an existing page, we raced with load/swapin */
-	if (!page_was_allocated) {
-		put_page(page);
-		ret = -EEXIST;
-		goto fail;
+	/*
+	 * Found an existing folio, we raced with load/swapin. We generally
+	 * writeback cold folios from zswap, and swapin means the folio just
+	 * became hot. Skip this folio and let the caller find another one.
+	 */
+	if (!folio_was_allocated) {
+		folio_put(folio);
+		return -EEXIST;
 	}
 
 	/*
-	 * Page is locked, and the swapcache is now secured against
+	 * folio is locked, and the swapcache is now secured against
 	 * concurrent swapping to and from the slot. Verify that the
 	 * swap entry hasn't been invalidated and recycled behind our
 	 * backs (our zswap_entry reference doesn't prevent that), to
-	 * avoid overwriting a new swap page with old compressed data.
+	 * avoid overwriting a new swap folio with old compressed data.
 	 */
 	spin_lock(&tree->lock);
 	if (zswap_rb_search(&tree->rbroot, swp_offset(entry->swpentry)) != entry) {
 		spin_unlock(&tree->lock);
-		delete_from_swap_cache(page_folio(page));
-		ret = -ENOMEM;
-		goto fail;
+		delete_from_swap_cache(folio);
+		return -ENOMEM;
 	}
 	spin_unlock(&tree->lock);
 
-	/* decompress */
-	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
-	dlen = PAGE_SIZE;
-
-	src = zpool_map_handle(pool, entry->handle, ZPOOL_MM_RO);
-	if (!zpool_can_sleep_mapped(pool)) {
-		memcpy(tmp, src, entry->length);
-		src = tmp;
-		zpool_unmap_handle(pool, entry->handle);
-	}
-
-	mutex_lock(acomp_ctx->mutex);
-	sg_init_one(&input, src, entry->length);
-	sg_init_table(&output, 1);
-	sg_set_page(&output, page, PAGE_SIZE, 0);
-	acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, dlen);
-	ret = crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait);
-	dlen = acomp_ctx->req->dlen;
-	mutex_unlock(acomp_ctx->mutex);
+	__zswap_load(entry, &folio->page);
 
-	if (!zpool_can_sleep_mapped(pool))
-		kfree(tmp);
-	else
-		zpool_unmap_handle(pool, entry->handle);
-
-	BUG_ON(ret);
-	BUG_ON(dlen != PAGE_SIZE);
-
-	/* page is up to date */
-	SetPageUptodate(page);
+	/* folio is up to date */
+	folio_mark_uptodate(folio);
 
 	/* move it to the tail of the inactive list after end_writeback */
-	SetPageReclaim(page);
+	folio_set_reclaim(folio);
 
 	/* start writeback */
-	__swap_writepage(page, &wbc);
-	put_page(page);
-	zswap_written_back_pages++;
+	__swap_writepage(folio, &wbc);
+	folio_put(folio);
 
-	return ret;
-
-fail:
-	if (!zpool_can_sleep_mapped(pool))
-		kfree(tmp);
-
-	/*
-	 * If we get here because the page is already in swapcache, a
-	 * load may be happening concurrently. It is safe and okay to
-	 * not free the entry. It is also okay to return !0.
-	 */
-	return ret;
+	return 0;
 }
 
 static int zswap_is_page_same_filled(void *ptr, unsigned long *value)
@@ -1204,6 +1502,7 @@ bool zswap_store(struct folio *folio)
 	struct scatterlist input, output;
 	struct crypto_acomp_ctx *acomp_ctx;
 	struct obj_cgroup *objcg = NULL;
+	struct mem_cgroup *memcg = NULL;
 	struct zswap_pool *pool;
 	struct zpool *zpool;
 	unsigned int dlen = PAGE_SIZE;
@@ -1235,15 +1534,15 @@ bool zswap_store(struct folio *folio)
 		zswap_invalidate_entry(tree, dupentry);
 	}
 	spin_unlock(&tree->lock);
-
-	/*
-	 * XXX: zswap reclaim does not work with cgroups yet. Without a
-	 * cgroup-aware entry LRU, we will push out entries system-wide based on
-	 * local cgroup limits.
-	 */
 	objcg = get_obj_cgroup_from_folio(folio);
-	if (objcg && !obj_cgroup_may_zswap(objcg))
-		goto reject;
+	if (objcg && !obj_cgroup_may_zswap(objcg)) {
+		memcg = get_mem_cgroup_from_objcg(objcg);
+		if (shrink_memcg(memcg)) {
+			mem_cgroup_put(memcg);
+			goto reject;
+		}
+		mem_cgroup_put(memcg);
+	}
 
 	/* reclaim space if needed */
 	if (zswap_is_full()) {
@@ -1260,23 +1559,23 @@ bool zswap_store(struct folio *folio)
 	}
 
 	/* allocate entry */
-	entry = zswap_entry_cache_alloc(GFP_KERNEL);
+	entry = zswap_entry_cache_alloc(GFP_KERNEL, page_to_nid(page));
 	if (!entry) {
 		zswap_reject_kmemcache_fail++;
 		goto reject;
 	}
 
 	if (zswap_same_filled_pages_enabled) {
-		src = kmap_atomic(page);
+		src = kmap_local_page(page);
 		if (zswap_is_page_same_filled(src, &value)) {
-			kunmap_atomic(src);
+			kunmap_local(src);
 			entry->swpentry = swp_entry(type, offset);
 			entry->length = 0;
 			entry->value = value;
 			atomic_inc(&zswap_same_filled_pages);
 			goto insert_entry;
 		}
-		kunmap_atomic(src);
+		kunmap_local(src);
 	}
 
 	if (!zswap_non_same_filled_pages_enabled)
@@ -1287,16 +1586,29 @@ bool zswap_store(struct folio *folio)
 	if (!entry->pool)
 		goto freepage;
 
+	if (objcg) {
+		memcg = get_mem_cgroup_from_objcg(objcg);
+		if (memcg_list_lru_alloc(memcg, &entry->pool->list_lru, GFP_KERNEL)) {
+			mem_cgroup_put(memcg);
+			goto put_pool;
+		}
+		mem_cgroup_put(memcg);
+	}
+
 	/* compress */
 	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
 
-	mutex_lock(acomp_ctx->mutex);
+	mutex_lock(&acomp_ctx->mutex);
 
-	dst = acomp_ctx->dstmem;
+	dst = acomp_ctx->buffer;
 	sg_init_table(&input, 1);
-	sg_set_page(&input, page, PAGE_SIZE, 0);
+	sg_set_page(&input, &folio->page, PAGE_SIZE, 0);
 
-	/* zswap_dstmem is of size (PAGE_SIZE * 2). Reflect same in sg_list */
+	/*
+	 * We need PAGE_SIZE * 2 here since there maybe over-compression case,
+	 * and hardware-accelerators may won't check the dst buffer size, so
+	 * giving the dst buffer with enough length to avoid buffer overflow.
+	 */
 	sg_init_one(&output, dst, PAGE_SIZE * 2);
 	acomp_request_set_params(acomp_ctx->req, &input, &output, PAGE_SIZE, dlen);
 	/*
@@ -1336,7 +1648,7 @@ bool zswap_store(struct folio *folio)
 	buf = zpool_map_handle(zpool, handle, ZPOOL_MM_WO);
 	memcpy(buf, dst, dlen);
 	zpool_unmap_handle(zpool, handle);
-	mutex_unlock(acomp_ctx->mutex);
+	mutex_unlock(&acomp_ctx->mutex);
 
 	/* populate entry */
 	entry->swpentry = swp_entry(type, offset);
@@ -1365,9 +1677,9 @@ insert_entry:
 		zswap_invalidate_entry(tree, dupentry);
 	}
 	if (entry->length) {
-		spin_lock(&entry->pool->lru_lock);
-		list_add(&entry->lru, &entry->pool->lru);
-		spin_unlock(&entry->pool->lru_lock);
+		INIT_LIST_HEAD(&entry->lru);
+		zswap_lru_add(&entry->pool->list_lru, entry);
+		atomic_inc(&entry->pool->nr_stored);
 	}
 	spin_unlock(&tree->lock);
 
@@ -1379,7 +1691,8 @@ insert_entry:
 	return true;
 
 put_dstmem:
-	mutex_unlock(acomp_ctx->mutex);
+	mutex_unlock(&acomp_ctx->mutex);
+put_pool:
 	zswap_pool_put(entry->pool);
 freepage:
 	zswap_entry_cache_free(entry);
@@ -1403,12 +1716,7 @@ bool zswap_load(struct folio *folio)
 	struct page *page = &folio->page;
 	struct zswap_tree *tree = zswap_trees[type];
 	struct zswap_entry *entry;
-	struct scatterlist input, output;
-	struct crypto_acomp_ctx *acomp_ctx;
-	u8 *src, *dst, *tmp;
-	struct zpool *zpool;
-	unsigned int dlen;
-	bool ret;
+	u8 *dst;
 
 	VM_WARN_ON_ONCE(!folio_test_locked(folio));
 
@@ -1421,67 +1729,30 @@ bool zswap_load(struct folio *folio)
 	}
 	spin_unlock(&tree->lock);
 
-	if (!entry->length) {
-		dst = kmap_atomic(page);
+	if (entry->length)
+		__zswap_load(entry, page);
+	else {
+		dst = kmap_local_page(page);
 		zswap_fill_page(dst, entry->value);
-		kunmap_atomic(dst);
-		ret = true;
-		goto stats;
-	}
-
-	zpool = zswap_find_zpool(entry);
-	if (!zpool_can_sleep_mapped(zpool)) {
-		tmp = kmalloc(entry->length, GFP_KERNEL);
-		if (!tmp) {
-			ret = false;
-			goto freeentry;
-		}
-	}
-
-	/* decompress */
-	dlen = PAGE_SIZE;
-	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
-
-	if (!zpool_can_sleep_mapped(zpool)) {
-		memcpy(tmp, src, entry->length);
-		src = tmp;
-		zpool_unmap_handle(zpool, entry->handle);
+		kunmap_local(dst);
 	}
 
-	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
-	mutex_lock(acomp_ctx->mutex);
-	sg_init_one(&input, src, entry->length);
-	sg_init_table(&output, 1);
-	sg_set_page(&output, page, PAGE_SIZE, 0);
-	acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, dlen);
-	if (crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait))
-		WARN_ON(1);
-	mutex_unlock(acomp_ctx->mutex);
-
-	if (zpool_can_sleep_mapped(zpool))
-		zpool_unmap_handle(zpool, entry->handle);
-	else
-		kfree(tmp);
-
-	ret = true;
-stats:
 	count_vm_event(ZSWPIN);
 	if (entry->objcg)
 		count_objcg_event(entry->objcg, ZSWPIN);
-freeentry:
+
 	spin_lock(&tree->lock);
-	if (ret && zswap_exclusive_loads_enabled) {
+	if (zswap_exclusive_loads_enabled) {
 		zswap_invalidate_entry(tree, entry);
 		folio_mark_dirty(folio);
 	} else if (entry->length) {
-		spin_lock(&entry->pool->lru_lock);
-		list_move(&entry->lru, &entry->pool->lru);
-		spin_unlock(&entry->pool->lru_lock);
+		zswap_lru_del(&entry->pool->list_lru, entry);
+		zswap_lru_add(&entry->pool->list_lru, entry);
 	}
 	zswap_entry_put(tree, entry);
 	spin_unlock(&tree->lock);
 
-	return ret;
+	return true;
 }
 
 void zswap_invalidate(int type, pgoff_t offset)
@@ -1595,13 +1866,6 @@ static int zswap_setup(void)
 		goto cache_fail;
 	}
 
-	ret = cpuhp_setup_state(CPUHP_MM_ZSWP_MEM_PREPARE, "mm/zswap:prepare",
-				zswap_dstmem_prepare, zswap_dstmem_dead);
-	if (ret) {
-		pr_err("dstmem alloc failed\n");
-		goto dstmem_fail;
-	}
-
 	ret = cpuhp_setup_state_multi(CPUHP_MM_ZSWP_POOL_PREPARE,
 				      "mm/zswap_pool:prepare",
 				      zswap_cpu_comp_prepare,
@@ -1633,8 +1897,6 @@ fallback_fail:
 	if (pool)
 		zswap_pool_destroy(pool);
 hp_fail:
-	cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE);
-dstmem_fail:
 	kmem_cache_destroy(zswap_entry_cache);
 cache_fail:
 	/* if built-in, we aren't unloaded on failure; don't allow use */
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 0beb44f2fe1f..f00158234505 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -407,6 +407,8 @@ int vlan_vids_add_by_dev(struct net_device *dev,
 		return 0;
 
 	list_for_each_entry(vid_info, &vlan_info->vid_list, list) {
+		if (!vlan_hw_filter_capable(by_dev, vid_info->proto))
+			continue;
 		err = vlan_vid_add(dev, vid_info->proto, vid_info->vid);
 		if (err)
 			goto unwind;
@@ -417,6 +419,8 @@ unwind:
 	list_for_each_entry_continue_reverse(vid_info,
 					     &vlan_info->vid_list,
 					     list) {
+		if (!vlan_hw_filter_capable(by_dev, vid_info->proto))
+			continue;
 		vlan_vid_del(dev, vid_info->proto, vid_info->vid);
 	}
 
@@ -436,8 +440,11 @@ void vlan_vids_del_by_dev(struct net_device *dev,
 	if (!vlan_info)
 		return;
 
-	list_for_each_entry(vid_info, &vlan_info->vid_list, list)
+	list_for_each_entry(vid_info, &vlan_info->vid_list, list) {
+		if (!vlan_hw_filter_capable(by_dev, vid_info->proto))
+			continue;
 		vlan_vid_del(dev, vid_info->proto, vid_info->vid);
+	}
 }
 EXPORT_SYMBOL(vlan_vids_del_by_dev);
 
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 2a7f1b15714a..407b2335f091 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -702,20 +702,7 @@ static int vlan_ethtool_get_ts_info(struct net_device *dev,
 				    struct ethtool_ts_info *info)
 {
 	const struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
-	const struct ethtool_ops *ops = vlan->real_dev->ethtool_ops;
-	struct phy_device *phydev = vlan->real_dev->phydev;
-
-	if (phy_has_tsinfo(phydev)) {
-		return phy_ts_info(phydev, info);
-	} else if (ops->get_ts_info) {
-		return ops->get_ts_info(vlan->real_dev, info);
-	} else {
-		info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
-			SOF_TIMESTAMPING_SOFTWARE;
-		info->phc_index = -1;
-	}
-
-	return 0;
+	return ethtool_get_ts_info_by_layer(vlan->real_dev, info);
 }
 
 static void vlan_dev_get_stats64(struct net_device *dev,
diff --git a/net/9p/protocol.c b/net/9p/protocol.c
index 4e3a2a1ffcb3..0e6603b1ec90 100644
--- a/net/9p/protocol.c
+++ b/net/9p/protocol.c
@@ -394,6 +394,8 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt,
 				uint16_t *nwname = va_arg(ap, uint16_t *);
 				char ***wnames = va_arg(ap, char ***);
 
+				*wnames = NULL;
+
 				errcode = p9pdu_readf(pdu, proto_version,
 								"w", nwname);
 				if (!errcode) {
@@ -403,6 +405,8 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt,
 							  GFP_NOFS);
 					if (!*wnames)
 						errcode = -ENOMEM;
+					else
+						(*wnames)[0] = NULL;
 				}
 
 				if (!errcode) {
@@ -414,8 +418,10 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt,
 								proto_version,
 								"s",
 								&(*wnames)[i]);
-						if (errcode)
+						if (errcode) {
+							(*wnames)[i] = NULL;
 							break;
+						}
 					}
 				}
 
@@ -423,11 +429,14 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt,
 					if (*wnames) {
 						int i;
 
-						for (i = 0; i < *nwname; i++)
+						for (i = 0; i < *nwname; i++) {
+							if (!(*wnames)[i])
+								break;
 							kfree((*wnames)[i]);
+						}
+						kfree(*wnames);
+						*wnames = NULL;
 					}
-					kfree(*wnames);
-					*wnames = NULL;
 				}
 			}
 			break;
diff --git a/net/Kconfig b/net/Kconfig
index 3ec6bc98fa05..4adc47d0c9c2 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -233,8 +233,6 @@ source "net/bridge/netfilter/Kconfig"
 
 endif
 
-source "net/bpfilter/Kconfig"
-
 source "net/dccp/Kconfig"
 source "net/sctp/Kconfig"
 source "net/rds/Kconfig"
diff --git a/net/Makefile b/net/Makefile
index 4c4dc535453d..b06b5539e7a6 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -19,7 +19,6 @@ obj-$(CONFIG_TLS)		+= tls/
 obj-$(CONFIG_XFRM)		+= xfrm/
 obj-$(CONFIG_UNIX_SCM)		+= unix/
 obj-y				+= ipv6/
-obj-$(CONFIG_BPFILTER)		+= bpfilter/
 obj-$(CONFIG_PACKET)		+= packet/
 obj-$(CONFIG_NET_KEY)		+= key/
 obj-$(CONFIG_BRIDGE)		+= bridge/
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 9ba04a69ec2a..198f5ba2feae 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1581,7 +1581,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	}
 
 	/* Build a packet */
-	SOCK_DEBUG(sk, "SK %p: Got address.\n", sk);
+	net_dbg_ratelimited("SK %p: Got address.\n", sk);
 
 	/* For headers */
 	size = sizeof(struct ddpehdr) + len + ddp_dl->header_length;
@@ -1602,7 +1602,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 
 	dev = rt->dev;
 
-	SOCK_DEBUG(sk, "SK %p: Size needed %d, device %s\n",
+	net_dbg_ratelimited("SK %p: Size needed %d, device %s\n",
 			sk, size, dev->name);
 
 	hard_header_len = dev->hard_header_len;
@@ -1631,7 +1631,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	skb_reserve(skb, hard_header_len);
 	skb->dev = dev;
 
-	SOCK_DEBUG(sk, "SK %p: Begin build.\n", sk);
+	net_dbg_ratelimited("SK %p: Begin build.\n", sk);
 
 	ddp = skb_put(skb, sizeof(struct ddpehdr));
 	ddp->deh_len_hops  = htons(len + sizeof(*ddp));
@@ -1642,7 +1642,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	ddp->deh_dport = usat->sat_port;
 	ddp->deh_sport = at->src_port;
 
-	SOCK_DEBUG(sk, "SK %p: Copy user data (%zd bytes).\n", sk, len);
+	net_dbg_ratelimited("SK %p: Copy user data (%zd bytes).\n", sk, len);
 
 	err = memcpy_from_msg(skb_put(skb, len), msg, len);
 	if (err) {
@@ -1666,7 +1666,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 
 		if (skb2) {
 			loopback = 1;
-			SOCK_DEBUG(sk, "SK %p: send out(copy).\n", sk);
+			net_dbg_ratelimited("SK %p: send out(copy).\n", sk);
 			/*
 			 * If it fails it is queued/sent above in the aarp queue
 			 */
@@ -1675,7 +1675,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	}
 
 	if (dev->flags & IFF_LOOPBACK || loopback) {
-		SOCK_DEBUG(sk, "SK %p: Loop back.\n", sk);
+		net_dbg_ratelimited("SK %p: Loop back.\n", sk);
 		/* loop back */
 		skb_orphan(skb);
 		if (ddp->deh_dnode == ATADDR_BCAST) {
@@ -1689,7 +1689,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 		}
 		ddp_dl->request(ddp_dl, skb, dev->dev_addr);
 	} else {
-		SOCK_DEBUG(sk, "SK %p: send out.\n", sk);
+		net_dbg_ratelimited("SK %p: send out.\n", sk);
 		if (rt->flags & RTF_GATEWAY) {
 		    gsat.sat_addr = rt->gateway;
 		    usat = &gsat;
@@ -1700,7 +1700,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 		 */
 		aarp_send_ddp(dev, skb, &usat->sat_addr, NULL);
 	}
-	SOCK_DEBUG(sk, "SK %p: Done write (%zd).\n", sk, len);
+	net_dbg_ratelimited("SK %p: Done write (%zd).\n", sk, len);
 
 out:
 	release_sock(sk);
@@ -1775,15 +1775,14 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		break;
 	}
 	case TIOCINQ: {
-		/*
-		 * These two are safe on a single CPU system as only
-		 * user tasks fiddle here
-		 */
-		struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
+		struct sk_buff *skb;
 		long amount = 0;
 
+		spin_lock_irq(&sk->sk_receive_queue.lock);
+		skb = skb_peek(&sk->sk_receive_queue);
 		if (skb)
 			amount = skb->len - sizeof(struct ddpehdr);
+		spin_unlock_irq(&sk->sk_receive_queue.lock);
 		rc = put_user(amount, (int __user *)argp);
 		break;
 	}
diff --git a/net/atm/common.c b/net/atm/common.c
index f7019df41c3e..2a1ec014e901 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -890,6 +890,7 @@ subsys_initcall(atm_init);
 
 module_exit(atm_exit);
 
+MODULE_DESCRIPTION("Asynchronous Transfer Mode (ATM) networking core");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_NETPROTO(PF_ATMPVC);
 MODULE_ALIAS_NETPROTO(PF_ATMSVC);
diff --git a/net/atm/ioctl.c b/net/atm/ioctl.c
index 838ebf0cabbf..f81f8d56f5c0 100644
--- a/net/atm/ioctl.c
+++ b/net/atm/ioctl.c
@@ -73,14 +73,17 @@ static int do_vcc_ioctl(struct socket *sock, unsigned int cmd,
 	case SIOCINQ:
 	{
 		struct sk_buff *skb;
+		int amount;
 
 		if (sock->state != SS_CONNECTED) {
 			error = -EINVAL;
 			goto done;
 		}
+		spin_lock_irq(&sk->sk_receive_queue.lock);
 		skb = skb_peek(&sk->sk_receive_queue);
-		error = put_user(skb ? skb->len : 0,
-				 (int __user *)argp) ? -EFAULT : 0;
+		amount = skb ? skb->len : 0;
+		spin_unlock_irq(&sk->sk_receive_queue.lock);
+		error = put_user(amount, (int __user *)argp) ? -EFAULT : 0;
 		goto done;
 	}
 	case ATM_SETSC:
diff --git a/net/atm/lec.c b/net/atm/lec.c
index 6257bf12e5a0..ffef658862db 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -2234,4 +2234,5 @@ out:
 	spin_unlock_irqrestore(&priv->lec_arp_lock, flags);
 }
 
+MODULE_DESCRIPTION("ATM LAN Emulation (LANE) support");
 MODULE_LICENSE("GPL");
diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile
index 3bd0760c76a2..b51d8b071b56 100644
--- a/net/batman-adv/Makefile
+++ b/net/batman-adv/Makefile
@@ -20,6 +20,7 @@ batman-adv-y += hash.o
 batman-adv-$(CONFIG_BATMAN_ADV_DEBUG) += log.o
 batman-adv-y += main.o
 batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast.o
+batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast_forw.o
 batman-adv-y += netlink.o
 batman-adv-$(CONFIG_BATMAN_ADV_NC) += network-coding.o
 batman-adv-y += originator.o
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index 37ce6cfb3520..5f46ca3d4bb8 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -20,7 +20,6 @@
 #include <linux/if_vlan.h>
 #include <linux/jhash.h>
 #include <linux/jiffies.h>
-#include <linux/kernel.h>
 #include <linux/kref.h>
 #include <linux/list.h>
 #include <linux/lockdep.h>
@@ -31,6 +30,7 @@
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/sprintf.h>
 #include <linux/stddef.h>
 #include <linux/string.h>
 #include <linux/workqueue.h>
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index c120c7c6d25f..757c084ac2d1 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -25,7 +25,6 @@
 
 #include "hard-interface.h"
 #include "originator.h"
-#include "routing.h"
 #include "send.h"
 
 /**
@@ -351,18 +350,14 @@ bool batadv_frag_skb_fwd(struct sk_buff *skb,
 			 struct batadv_orig_node *orig_node_src)
 {
 	struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface);
-	struct batadv_orig_node *orig_node_dst;
 	struct batadv_neigh_node *neigh_node = NULL;
 	struct batadv_frag_packet *packet;
 	u16 total_size;
 	bool ret = false;
 
 	packet = (struct batadv_frag_packet *)skb->data;
-	orig_node_dst = batadv_orig_hash_find(bat_priv, packet->dest);
-	if (!orig_node_dst)
-		goto out;
 
-	neigh_node = batadv_find_router(bat_priv, orig_node_dst, recv_if);
+	neigh_node = batadv_orig_to_router(bat_priv, packet->dest, recv_if);
 	if (!neigh_node)
 		goto out;
 
@@ -381,7 +376,6 @@ bool batadv_frag_skb_fwd(struct sk_buff *skb,
 	}
 
 out:
-	batadv_orig_node_put(orig_node_dst);
 	batadv_neigh_node_put(neigh_node);
 	return ret;
 }
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index d26124bc27e1..0ddd8b4b3f4c 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -18,7 +18,6 @@
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
-#include <linux/kernel.h>
 #include <linux/kref.h>
 #include <linux/list.h>
 #include <linux/lockdep.h>
@@ -29,6 +28,7 @@
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/sprintf.h>
 #include <linux/stddef.h>
 #include <linux/udp.h>
 #include <net/sock.h>
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index e8a449915566..5fc754b0b3f7 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -6,6 +6,7 @@
 
 #include "main.h"
 
+#include <linux/array_size.h>
 #include <linux/atomic.h>
 #include <linux/build_bug.h>
 #include <linux/byteorder/generic.h>
@@ -20,7 +21,6 @@
 #include <linux/init.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
-#include <linux/kernel.h>
 #include <linux/kobject.h>
 #include <linux/kref.h>
 #include <linux/list.h>
@@ -33,6 +33,7 @@
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/sprintf.h>
 #include <linux/stddef.h>
 #include <linux/string.h>
 #include <linux/workqueue.h>
@@ -532,6 +533,8 @@ static void batadv_recv_handler_init(void)
 
 	/* broadcast packet */
 	batadv_rx_handler[BATADV_BCAST] = batadv_recv_bcast_packet;
+	/* multicast packet */
+	batadv_rx_handler[BATADV_MCAST] = batadv_recv_mcast_packet;
 
 	/* unicast packets ... */
 	/* unicast with 4 addresses packet */
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 10007c5894a1..870dcd7f1786 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -13,7 +13,7 @@
 #define BATADV_DRIVER_DEVICE "batman-adv"
 
 #ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2023.3"
+#define BATADV_SOURCE_VERSION "2024.0"
 #endif
 
 /* B.A.T.M.A.N. parameters */
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index 315394f12c55..d982daea8329 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -25,7 +25,6 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/jiffies.h>
-#include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/lockdep.h>
 #include <linux/netdevice.h>
@@ -36,6 +35,7 @@
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/sprintf.h>
 #include <linux/stddef.h>
 #include <linux/string.h>
 #include <linux/types.h>
@@ -236,6 +236,37 @@ static u8 batadv_mcast_mla_rtr_flags_get(struct batadv_priv *bat_priv,
 }
 
 /**
+ * batadv_mcast_mla_forw_flags_get() - get multicast forwarding flags
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Checks if all active hard interfaces have an MTU larger or equal to 1280
+ * bytes (IPv6 minimum MTU).
+ *
+ * Return: BATADV_MCAST_HAVE_MC_PTYPE_CAPA if yes, BATADV_NO_FLAGS otherwise.
+ */
+static u8 batadv_mcast_mla_forw_flags_get(struct batadv_priv *bat_priv)
+{
+	const struct batadv_hard_iface *hard_iface;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
+		if (hard_iface->if_status != BATADV_IF_ACTIVE)
+			continue;
+
+		if (hard_iface->soft_iface != bat_priv->soft_iface)
+			continue;
+
+		if (hard_iface->net_dev->mtu < IPV6_MIN_MTU) {
+			rcu_read_unlock();
+			return BATADV_NO_FLAGS;
+		}
+	}
+	rcu_read_unlock();
+
+	return BATADV_MCAST_HAVE_MC_PTYPE_CAPA;
+}
+
+/**
  * batadv_mcast_mla_flags_get() - get the new multicast flags
  * @bat_priv: the bat priv with all the soft interface information
  *
@@ -256,6 +287,7 @@ batadv_mcast_mla_flags_get(struct batadv_priv *bat_priv)
 	mla_flags.enabled = 1;
 	mla_flags.tvlv_flags |= batadv_mcast_mla_rtr_flags_get(bat_priv,
 							       bridge);
+	mla_flags.tvlv_flags |= batadv_mcast_mla_forw_flags_get(bat_priv);
 
 	if (!bridge)
 		return mla_flags;
@@ -806,23 +838,25 @@ static void batadv_mcast_flags_log(struct batadv_priv *bat_priv, u8 flags)
 {
 	bool old_enabled = bat_priv->mcast.mla_flags.enabled;
 	u8 old_flags = bat_priv->mcast.mla_flags.tvlv_flags;
-	char str_old_flags[] = "[.... . ]";
+	char str_old_flags[] = "[.... . .]";
 
-	sprintf(str_old_flags, "[%c%c%c%s%s]",
+	sprintf(str_old_flags, "[%c%c%c%s%s%c]",
 		(old_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.',
 		(old_flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.',
 		(old_flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.',
 		!(old_flags & BATADV_MCAST_WANT_NO_RTR4) ? "R4" : ". ",
-		!(old_flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". ");
+		!(old_flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". ",
+		!(old_flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA) ? 'P' : '.');
 
 	batadv_dbg(BATADV_DBG_MCAST, bat_priv,
-		   "Changing multicast flags from '%s' to '[%c%c%c%s%s]'\n",
+		   "Changing multicast flags from '%s' to '[%c%c%c%s%s%c]'\n",
 		   old_enabled ? str_old_flags : "<undefined>",
 		   (flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.',
 		   (flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.',
 		   (flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.',
 		   !(flags & BATADV_MCAST_WANT_NO_RTR4) ? "R4" : ". ",
-		   !(flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". ");
+		   !(flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". ",
+		   !(flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA) ? 'P' : '.');
 }
 
 /**
@@ -1136,16 +1170,61 @@ static int batadv_mcast_forw_rtr_count(struct batadv_priv *bat_priv,
 }
 
 /**
+ * batadv_mcast_forw_mode_by_count() - get forwarding mode by count
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the multicast packet to check
+ * @vid: the vlan identifier
+ * @is_routable: stores whether the destination is routable
+ * @count: the number of originators the multicast packet need to be sent to
+ *
+ * For a multicast packet with multiple destination originators, checks which
+ * mode to use. For BATADV_FORW_MCAST it also encapsulates the packet with a
+ * complete batman-adv multicast header.
+ *
+ * Return:
+ *	BATADV_FORW_MCAST: If all nodes have multicast packet routing
+ *	capabilities and an MTU >= 1280 on all hard interfaces (including us)
+ *	and the encapsulated multicast packet with all destination addresses
+ *	would still fit into an 1280 bytes batman-adv multicast packet
+ *	(excluding the outer ethernet frame) and we could successfully push
+ *	the full batman-adv multicast packet header.
+ *	BATADV_FORW_UCASTS: If the packet cannot be sent in a batman-adv
+ *	multicast packet and the amount of batman-adv unicast packets needed
+ *	is smaller or equal to the configured multicast fanout.
+ *	BATADV_FORW_BCAST: Otherwise.
+ */
+static enum batadv_forw_mode
+batadv_mcast_forw_mode_by_count(struct batadv_priv *bat_priv,
+				struct sk_buff *skb, unsigned short vid,
+				int is_routable, int count)
+{
+	unsigned int mcast_hdrlen = batadv_mcast_forw_packet_hdrlen(count);
+	u8 own_tvlv_flags = bat_priv->mcast.mla_flags.tvlv_flags;
+
+	if (!atomic_read(&bat_priv->mcast.num_no_mc_ptype_capa) &&
+	    own_tvlv_flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA &&
+	    skb->len + mcast_hdrlen <= IPV6_MIN_MTU &&
+	    batadv_mcast_forw_push(bat_priv, skb, vid, is_routable, count))
+		return BATADV_FORW_MCAST;
+
+	if (count <= atomic_read(&bat_priv->multicast_fanout))
+		return BATADV_FORW_UCASTS;
+
+	return BATADV_FORW_BCAST;
+}
+
+/**
  * batadv_mcast_forw_mode() - check on how to forward a multicast packet
  * @bat_priv: the bat priv with all the soft interface information
  * @skb: the multicast packet to check
+ * @vid: the vlan identifier
  * @is_routable: stores whether the destination is routable
  *
  * Return: The forwarding mode as enum batadv_forw_mode.
  */
 enum batadv_forw_mode
 batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
-		       int *is_routable)
+		       unsigned short vid, int *is_routable)
 {
 	int ret, tt_count, ip_count, unsnoop_count, total_count;
 	bool is_unsnoopable = false;
@@ -1175,10 +1254,8 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
 	else if (unsnoop_count)
 		return BATADV_FORW_BCAST;
 
-	if (total_count <= atomic_read(&bat_priv->multicast_fanout))
-		return BATADV_FORW_UCASTS;
-
-	return BATADV_FORW_BCAST;
+	return batadv_mcast_forw_mode_by_count(bat_priv, skb, vid, *is_routable,
+					       total_count);
 }
 
 /**
@@ -1739,6 +1816,31 @@ static void batadv_mcast_want_rtr6_update(struct batadv_priv *bat_priv,
 }
 
 /**
+ * batadv_mcast_have_mc_ptype_update() - update multicast packet type counter
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig: the orig_node which multicast state might have changed of
+ * @mcast_flags: flags indicating the new multicast state
+ *
+ * If the BATADV_MCAST_HAVE_MC_PTYPE_CAPA flag of this originator, orig, has
+ * toggled then this method updates the counter accordingly.
+ */
+static void batadv_mcast_have_mc_ptype_update(struct batadv_priv *bat_priv,
+					      struct batadv_orig_node *orig,
+					      u8 mcast_flags)
+{
+	lockdep_assert_held(&orig->mcast_handler_lock);
+
+	/* switched from flag set to unset */
+	if (!(mcast_flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA) &&
+	    orig->mcast_flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA)
+		atomic_inc(&bat_priv->mcast.num_no_mc_ptype_capa);
+	/* switched from flag unset to set */
+	else if (mcast_flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA &&
+		 !(orig->mcast_flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA))
+		atomic_dec(&bat_priv->mcast.num_no_mc_ptype_capa);
+}
+
+/**
  * batadv_mcast_tvlv_flags_get() - get multicast flags from an OGM TVLV
  * @enabled: whether the originator has multicast TVLV support enabled
  * @tvlv_value: tvlv buffer containing the multicast flags
@@ -1806,6 +1908,7 @@ static void batadv_mcast_tvlv_ogm_handler(struct batadv_priv *bat_priv,
 	batadv_mcast_want_ipv6_update(bat_priv, orig, mcast_flags);
 	batadv_mcast_want_rtr4_update(bat_priv, orig, mcast_flags);
 	batadv_mcast_want_rtr6_update(bat_priv, orig, mcast_flags);
+	batadv_mcast_have_mc_ptype_update(bat_priv, orig, mcast_flags);
 
 	orig->mcast_flags = mcast_flags;
 	spin_unlock_bh(&orig->mcast_handler_lock);
@@ -1820,6 +1923,10 @@ void batadv_mcast_init(struct batadv_priv *bat_priv)
 	batadv_tvlv_handler_register(bat_priv, batadv_mcast_tvlv_ogm_handler,
 				     NULL, NULL, BATADV_TVLV_MCAST, 2,
 				     BATADV_TVLV_HANDLER_OGM_CIFNOTFND);
+	batadv_tvlv_handler_register(bat_priv, NULL, NULL,
+				     batadv_mcast_forw_tracker_tvlv_handler,
+				     BATADV_TVLV_MCAST_TRACKER, 1,
+				     BATADV_TVLV_HANDLER_OGM_CIFNOTFND);
 
 	INIT_DELAYED_WORK(&bat_priv->mcast.work, batadv_mcast_mla_update);
 	batadv_mcast_start_timer(bat_priv);
diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h
index a9770d8d6d36..d97ee51d26f2 100644
--- a/net/batman-adv/multicast.h
+++ b/net/batman-adv/multicast.h
@@ -11,6 +11,7 @@
 
 #include <linux/netlink.h>
 #include <linux/skbuff.h>
+#include <linux/types.h>
 
 /**
  * enum batadv_forw_mode - the way a packet should be forwarded as
@@ -28,6 +29,12 @@ enum batadv_forw_mode {
 	 */
 	BATADV_FORW_UCASTS,
 
+	/**
+	 * @BATADV_FORW_MCAST: forward the packet to some nodes via a
+	 *  batman-adv multicast packet
+	 */
+	BATADV_FORW_MCAST,
+
 	/** @BATADV_FORW_NONE: don't forward, drop it */
 	BATADV_FORW_NONE,
 };
@@ -36,7 +43,7 @@ enum batadv_forw_mode {
 
 enum batadv_forw_mode
 batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
-		       int *is_routable);
+		       unsigned short vid, int *is_routable);
 
 int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb,
 			   unsigned short vid, int is_routable);
@@ -52,11 +59,23 @@ void batadv_mcast_free(struct batadv_priv *bat_priv);
 
 void batadv_mcast_purge_orig(struct batadv_orig_node *orig_node);
 
+/* multicast_forw.c */
+
+int batadv_mcast_forw_tracker_tvlv_handler(struct batadv_priv *bat_priv,
+					   struct sk_buff *skb);
+
+unsigned int batadv_mcast_forw_packet_hdrlen(unsigned int num_dests);
+
+bool batadv_mcast_forw_push(struct batadv_priv *bat_priv, struct sk_buff *skb,
+			    unsigned short vid, int is_routable, int count);
+
+int batadv_mcast_forw_mcsend(struct batadv_priv *bat_priv, struct sk_buff *skb);
+
 #else
 
 static inline enum batadv_forw_mode
 batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
-		       int *is_routable)
+		       unsigned short vid, int *is_routable)
 {
 	return BATADV_FORW_BCAST;
 }
@@ -94,6 +113,13 @@ static inline void batadv_mcast_purge_orig(struct batadv_orig_node *orig_node)
 {
 }
 
+static inline int batadv_mcast_forw_mcsend(struct batadv_priv *bat_priv,
+					   struct sk_buff *skb)
+{
+	kfree_skb(skb);
+	return NET_XMIT_DROP;
+}
+
 #endif /* CONFIG_BATMAN_ADV_MCAST */
 
 #endif /* _NET_BATMAN_ADV_MULTICAST_H_ */
diff --git a/net/batman-adv/multicast_forw.c b/net/batman-adv/multicast_forw.c
new file mode 100644
index 000000000000..fafd6ba8c056
--- /dev/null
+++ b/net/batman-adv/multicast_forw.c
@@ -0,0 +1,1178 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) B.A.T.M.A.N. contributors:
+ *
+ * Linus Lüssing
+ */
+
+#include "multicast.h"
+#include "main.h"
+
+#include <linux/bug.h>
+#include <linux/build_bug.h>
+#include <linux/byteorder/generic.h>
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/etherdevice.h>
+#include <linux/gfp.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <linux/ipv6.h>
+#include <linux/limits.h>
+#include <linux/netdevice.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/skbuff.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <uapi/linux/batadv_packet.h>
+
+#include "bridge_loop_avoidance.h"
+#include "originator.h"
+#include "send.h"
+#include "translation-table.h"
+
+#define batadv_mcast_forw_tracker_for_each_dest(dest, num_dests) \
+	for (; num_dests; num_dests--, (dest) += ETH_ALEN)
+
+#define batadv_mcast_forw_tracker_for_each_dest2(dest1, dest2, num_dests) \
+	for (; num_dests; num_dests--, (dest1) += ETH_ALEN, (dest2) += ETH_ALEN)
+
+/**
+ * batadv_mcast_forw_skb_push() - skb_push and memorize amount of pushed bytes
+ * @skb: the skb to push onto
+ * @size: the amount of bytes to push
+ * @len: stores the total amount of bytes pushed
+ *
+ * Performs an skb_push() onto the given skb and adds the amount of pushed bytes
+ * to the given len pointer.
+ *
+ * Return: the return value of the skb_push() call.
+ */
+static void *batadv_mcast_forw_skb_push(struct sk_buff *skb, size_t size,
+					unsigned short *len)
+{
+	*len += size;
+	return skb_push(skb, size);
+}
+
+/**
+ * batadv_mcast_forw_push_padding() - push 2 padding bytes to skb's front
+ * @skb: the skb to push onto
+ * @tvlv_len: stores the amount of currently pushed TVLV bytes
+ *
+ * Pushes two padding bytes to the front of the given skb.
+ *
+ * Return: On success a pointer to the first byte of the two pushed padding
+ * bytes within the skb. NULL otherwise.
+ */
+static char *
+batadv_mcast_forw_push_padding(struct sk_buff *skb, unsigned short *tvlv_len)
+{
+	const int pad_len = 2;
+	char *padding;
+
+	if (skb_headroom(skb) < pad_len)
+		return NULL;
+
+	padding = batadv_mcast_forw_skb_push(skb, pad_len, tvlv_len);
+	memset(padding, 0, pad_len);
+
+	return padding;
+}
+
+/**
+ * batadv_mcast_forw_push_est_padding() - push padding bytes if necessary
+ * @skb: the skb to potentially push the padding onto
+ * @count: the (estimated) number of originators the multicast packet needs to
+ *  be sent to
+ * @tvlv_len: stores the amount of currently pushed TVLV bytes
+ *
+ * If the number of destination entries is even then this adds two
+ * padding bytes to the end of the tracker TVLV.
+ *
+ * Return: true on success or if no padding is needed, false otherwise.
+ */
+static bool
+batadv_mcast_forw_push_est_padding(struct sk_buff *skb, int count,
+				   unsigned short *tvlv_len)
+{
+	if (!(count % 2) && !batadv_mcast_forw_push_padding(skb, tvlv_len))
+		return false;
+
+	return true;
+}
+
+/**
+ * batadv_mcast_forw_orig_entry() - get orig_node from an hlist node
+ * @node: the hlist node to get the orig_node from
+ * @entry_offset: the offset of the hlist node within the orig_node struct
+ *
+ * Return: The orig_node containing the hlist node on success, NULL on error.
+ */
+static struct batadv_orig_node *
+batadv_mcast_forw_orig_entry(struct hlist_node *node,
+			     size_t entry_offset)
+{
+	/* sanity check */
+	switch (entry_offset) {
+	case offsetof(struct batadv_orig_node, mcast_want_all_ipv4_node):
+	case offsetof(struct batadv_orig_node, mcast_want_all_ipv6_node):
+	case offsetof(struct batadv_orig_node, mcast_want_all_rtr4_node):
+	case offsetof(struct batadv_orig_node, mcast_want_all_rtr6_node):
+		break;
+	default:
+		WARN_ON(1);
+		return NULL;
+	}
+
+	return (struct batadv_orig_node *)((void *)node - entry_offset);
+}
+
+/**
+ * batadv_mcast_forw_push_dest() - push an originator MAC address onto an skb
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the skb to push the destination address onto
+ * @vid: the vlan identifier
+ * @orig_node: the originator node to get the MAC address from
+ * @num_dests: a pointer to store the number of pushed addresses in
+ * @tvlv_len: stores the amount of currently pushed TVLV bytes
+ *
+ * If the orig_node is a BLA backbone gateway, if there is not enough skb
+ * headroom available or if num_dests is already at its maximum (65535) then
+ * neither the skb nor num_dests is changed. Otherwise the originator's MAC
+ * address is pushed onto the given skb and num_dests incremented by one.
+ *
+ * Return: true if the orig_node is a backbone gateway or if an orig address
+ *  was pushed successfully, false otherwise.
+ */
+static bool batadv_mcast_forw_push_dest(struct batadv_priv *bat_priv,
+					struct sk_buff *skb, unsigned short vid,
+					struct batadv_orig_node *orig_node,
+					unsigned short *num_dests,
+					unsigned short *tvlv_len)
+{
+	BUILD_BUG_ON(sizeof_field(struct batadv_tvlv_mcast_tracker, num_dests)
+		     != sizeof(__be16));
+
+	/* Avoid sending to other BLA gateways - they already got the frame from
+	 * the LAN side we share with them.
+	 * TODO: Refactor to take BLA into account earlier in mode check.
+	 */
+	if (batadv_bla_is_backbone_gw_orig(bat_priv, orig_node->orig, vid))
+		return true;
+
+	if (skb_headroom(skb) < ETH_ALEN || *num_dests == U16_MAX)
+		return false;
+
+	batadv_mcast_forw_skb_push(skb, ETH_ALEN, tvlv_len);
+	ether_addr_copy(skb->data, orig_node->orig);
+	(*num_dests)++;
+
+	return true;
+}
+
+/**
+ * batadv_mcast_forw_push_dests_list() - push originators from list onto an skb
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the skb to push the destination addresses onto
+ * @vid: the vlan identifier
+ * @head: the list to gather originators from
+ * @entry_offset: offset of an hlist node in an orig_node structure
+ * @num_dests: a pointer to store the number of pushed addresses in
+ * @tvlv_len: stores the amount of currently pushed TVLV bytes
+ *
+ * Push the MAC addresses of all originators in the given list onto the given
+ * skb.
+ *
+ * Return: true on success, false otherwise.
+ */
+static int batadv_mcast_forw_push_dests_list(struct batadv_priv *bat_priv,
+					     struct sk_buff *skb,
+					     unsigned short vid,
+					     struct hlist_head *head,
+					     size_t entry_offset,
+					     unsigned short *num_dests,
+					     unsigned short *tvlv_len)
+{
+	struct hlist_node *node;
+	struct batadv_orig_node *orig_node;
+
+	rcu_read_lock();
+	__hlist_for_each_rcu(node, head) {
+		orig_node = batadv_mcast_forw_orig_entry(node, entry_offset);
+		if (!orig_node ||
+		    !batadv_mcast_forw_push_dest(bat_priv, skb, vid, orig_node,
+						 num_dests, tvlv_len)) {
+			rcu_read_unlock();
+			return false;
+		}
+	}
+	rcu_read_unlock();
+
+	return true;
+}
+
+/**
+ * batadv_mcast_forw_push_tt() - push originators with interest through TT
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the skb to push the destination addresses onto
+ * @vid: the vlan identifier
+ * @num_dests: a pointer to store the number of pushed addresses in
+ * @tvlv_len: stores the amount of currently pushed TVLV bytes
+ *
+ * Push the MAC addresses of all originators which have indicated interest in
+ * this multicast packet through the translation table onto the given skb.
+ *
+ * Return: true on success, false otherwise.
+ */
+static bool
+batadv_mcast_forw_push_tt(struct batadv_priv *bat_priv, struct sk_buff *skb,
+			  unsigned short vid, unsigned short *num_dests,
+			  unsigned short *tvlv_len)
+{
+	struct batadv_tt_orig_list_entry *orig_entry;
+
+	struct batadv_tt_global_entry *tt_global;
+	const u8 *addr = eth_hdr(skb)->h_dest;
+
+	/* ok */
+	int ret = true;
+
+	tt_global = batadv_tt_global_hash_find(bat_priv, addr, vid);
+	if (!tt_global)
+		goto out;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(orig_entry, &tt_global->orig_list, list) {
+		if (!batadv_mcast_forw_push_dest(bat_priv, skb, vid,
+						 orig_entry->orig_node,
+						 num_dests, tvlv_len)) {
+			ret = false;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	batadv_tt_global_entry_put(tt_global);
+
+out:
+	return ret;
+}
+
+/**
+ * batadv_mcast_forw_push_want_all() - push originators with want-all flag
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the skb to push the destination addresses onto
+ * @vid: the vlan identifier
+ * @num_dests: a pointer to store the number of pushed addresses in
+ * @tvlv_len: stores the amount of currently pushed TVLV bytes
+ *
+ * Push the MAC addresses of all originators which have indicated interest in
+ * this multicast packet through the want-all flag onto the given skb.
+ *
+ * Return: true on success, false otherwise.
+ */
+static bool batadv_mcast_forw_push_want_all(struct batadv_priv *bat_priv,
+					    struct sk_buff *skb,
+					    unsigned short vid,
+					    unsigned short *num_dests,
+					    unsigned short *tvlv_len)
+{
+	struct hlist_head *head = NULL;
+	size_t offset;
+	int ret;
+
+	switch (eth_hdr(skb)->h_proto) {
+	case htons(ETH_P_IP):
+		head = &bat_priv->mcast.want_all_ipv4_list;
+		offset = offsetof(struct batadv_orig_node,
+				  mcast_want_all_ipv4_node);
+		break;
+	case htons(ETH_P_IPV6):
+		head = &bat_priv->mcast.want_all_ipv6_list;
+		offset = offsetof(struct batadv_orig_node,
+				  mcast_want_all_ipv6_node);
+		break;
+	default:
+		return false;
+	}
+
+	ret = batadv_mcast_forw_push_dests_list(bat_priv, skb, vid, head,
+						offset, num_dests, tvlv_len);
+	if (!ret)
+		return false;
+
+	return true;
+}
+
+/**
+ * batadv_mcast_forw_push_want_rtr() - push originators with want-router flag
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the skb to push the destination addresses onto
+ * @vid: the vlan identifier
+ * @num_dests: a pointer to store the number of pushed addresses in
+ * @tvlv_len: stores the amount of currently pushed TVLV bytes
+ *
+ * Push the MAC addresses of all originators which have indicated interest in
+ * this multicast packet through the want-all-rtr flag onto the given skb.
+ *
+ * Return: true on success, false otherwise.
+ */
+static bool batadv_mcast_forw_push_want_rtr(struct batadv_priv *bat_priv,
+					    struct sk_buff *skb,
+					    unsigned short vid,
+					    unsigned short *num_dests,
+					    unsigned short *tvlv_len)
+{
+	struct hlist_head *head = NULL;
+	size_t offset;
+	int ret;
+
+	switch (eth_hdr(skb)->h_proto) {
+	case htons(ETH_P_IP):
+		head = &bat_priv->mcast.want_all_rtr4_list;
+		offset = offsetof(struct batadv_orig_node,
+				  mcast_want_all_rtr4_node);
+		break;
+	case htons(ETH_P_IPV6):
+		head = &bat_priv->mcast.want_all_rtr6_list;
+		offset = offsetof(struct batadv_orig_node,
+				  mcast_want_all_rtr6_node);
+		break;
+	default:
+		return false;
+	}
+
+	ret = batadv_mcast_forw_push_dests_list(bat_priv, skb, vid, head,
+						offset, num_dests, tvlv_len);
+	if (!ret)
+		return false;
+
+	return true;
+}
+
+/**
+ * batadv_mcast_forw_scrape() - remove bytes within skb data
+ * @skb: the skb to remove bytes from
+ * @offset: the offset from the skb data from which to scrape
+ * @len: the amount of bytes to scrape starting from the offset
+ *
+ * Scrapes/removes len bytes from the given skb at the given offset from the
+ * skb data.
+ *
+ * Caller needs to ensure that the region from the skb data's start up
+ * to/including the to be removed bytes are linearized.
+ */
+static void batadv_mcast_forw_scrape(struct sk_buff *skb,
+				     unsigned short offset,
+				     unsigned short len)
+{
+	char *to, *from;
+
+	SKB_LINEAR_ASSERT(skb);
+
+	to = skb_pull(skb, len);
+	from = to - len;
+
+	memmove(to, from, offset);
+}
+
+/**
+ * batadv_mcast_forw_push_scrape_padding() - remove TVLV padding
+ * @skb: the skb to potentially adjust the TVLV's padding on
+ * @tvlv_len: stores the amount of currently pushed TVLV bytes
+ *
+ * Remove two padding bytes from the end of the multicast tracker TVLV,
+ * from before the payload data.
+ *
+ * Caller needs to ensure that the TVLV bytes are linearized.
+ */
+static void batadv_mcast_forw_push_scrape_padding(struct sk_buff *skb,
+						  unsigned short *tvlv_len)
+{
+	const int pad_len = 2;
+
+	batadv_mcast_forw_scrape(skb, *tvlv_len - pad_len, pad_len);
+	*tvlv_len -= pad_len;
+}
+
+/**
+ * batadv_mcast_forw_push_insert_padding() - insert TVLV padding
+ * @skb: the skb to potentially adjust the TVLV's padding on
+ * @tvlv_len: stores the amount of currently pushed TVLV bytes
+ *
+ * Inserts two padding bytes at the end of the multicast tracker TVLV,
+ * before the payload data in the given skb.
+ *
+ * Return: true on success, false otherwise.
+ */
+static bool batadv_mcast_forw_push_insert_padding(struct sk_buff *skb,
+						  unsigned short *tvlv_len)
+{
+	unsigned short offset =	*tvlv_len;
+	char *to, *from = skb->data;
+
+	to = batadv_mcast_forw_push_padding(skb, tvlv_len);
+	if (!to)
+		return false;
+
+	memmove(to, from, offset);
+	memset(to + offset, 0, *tvlv_len - offset);
+	return true;
+}
+
+/**
+ * batadv_mcast_forw_push_adjust_padding() - adjust padding if necessary
+ * @skb: the skb to potentially adjust the TVLV's padding on
+ * @count: the estimated number of originators the multicast packet needs to
+ *  be sent to
+ * @num_dests_pushed: the number of originators that were actually added to the
+ *  multicast packet's tracker TVLV
+ * @tvlv_len: stores the amount of currently pushed TVLV bytes
+ *
+ * Adjusts the padding in the multicast packet's tracker TVLV depending on the
+ * initially estimated amount of destinations versus the amount of destinations
+ * that were actually added to the tracker TVLV.
+ *
+ * If the initial estimate was correct or at least the oddness was the same then
+ * no padding adjustment is performed.
+ * If the initially estimated number was even, so padding was initially added,
+ * but it turned out to be odd then padding is removed.
+ * If the initially estimated number was odd, so no padding was initially added,
+ * but it turned out to be even then padding is added.
+ *
+ * Return: true if no padding adjustment is needed or the adjustment was
+ * successful, false otherwise.
+ */
+static bool
+batadv_mcast_forw_push_adjust_padding(struct sk_buff *skb, int *count,
+				      unsigned short num_dests_pushed,
+				      unsigned short *tvlv_len)
+{
+	int ret = true;
+
+	if (likely((num_dests_pushed % 2) == (*count % 2)))
+		goto out;
+
+	/**
+	 * estimated even number of destinations, but turned out to be odd
+	 * -> remove padding
+	 */
+	if (!(*count % 2) && (num_dests_pushed % 2))
+		batadv_mcast_forw_push_scrape_padding(skb, tvlv_len);
+	/**
+	 * estimated odd number of destinations, but turned out to be even
+	 * -> add padding
+	 */
+	else if ((*count % 2) && (!(num_dests_pushed % 2)))
+		ret = batadv_mcast_forw_push_insert_padding(skb, tvlv_len);
+
+out:
+	*count = num_dests_pushed;
+	return ret;
+}
+
+/**
+ * batadv_mcast_forw_push_dests() - push originator addresses onto an skb
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the skb to push the destination addresses onto
+ * @vid: the vlan identifier
+ * @is_routable: indicates whether the destination is routable
+ * @count: the number of originators the multicast packet needs to be sent to
+ * @tvlv_len: stores the amount of currently pushed TVLV bytes
+ *
+ * Push the MAC addresses of all originators which have indicated interest in
+ * this multicast packet onto the given skb.
+ *
+ * Return: -ENOMEM if there is not enough skb headroom available. Otherwise, on
+ * success 0.
+ */
+static int
+batadv_mcast_forw_push_dests(struct batadv_priv *bat_priv, struct sk_buff *skb,
+			     unsigned short vid, int is_routable, int *count,
+			     unsigned short *tvlv_len)
+{
+	unsigned short num_dests = 0;
+
+	if (!batadv_mcast_forw_push_est_padding(skb, *count, tvlv_len))
+		goto err;
+
+	if (!batadv_mcast_forw_push_tt(bat_priv, skb, vid, &num_dests,
+				       tvlv_len))
+		goto err;
+
+	if (!batadv_mcast_forw_push_want_all(bat_priv, skb, vid, &num_dests,
+					     tvlv_len))
+		goto err;
+
+	if (is_routable &&
+	    !batadv_mcast_forw_push_want_rtr(bat_priv, skb, vid, &num_dests,
+					     tvlv_len))
+		goto err;
+
+	if (!batadv_mcast_forw_push_adjust_padding(skb, count, num_dests,
+						   tvlv_len))
+		goto err;
+
+	return 0;
+err:
+	return -ENOMEM;
+}
+
+/**
+ * batadv_mcast_forw_push_tracker() - push a multicast tracker TVLV header
+ * @skb: the skb to push the tracker TVLV onto
+ * @num_dests: the number of destination addresses to set in the header
+ * @tvlv_len: stores the amount of currently pushed TVLV bytes
+ *
+ * Pushes a multicast tracker TVLV header onto the given skb, including the
+ * generic TVLV header but excluding the destination MAC addresses.
+ *
+ * The provided num_dests value is taken into consideration to set the
+ * num_dests field in the tracker header and to set the appropriate TVLV length
+ * value fields.
+ *
+ * Return: -ENOMEM if there is not enough skb headroom available. Otherwise, on
+ * success 0.
+ */
+static int batadv_mcast_forw_push_tracker(struct sk_buff *skb, int num_dests,
+					  unsigned short *tvlv_len)
+{
+	struct batadv_tvlv_mcast_tracker *mcast_tracker;
+	struct batadv_tvlv_hdr *tvlv_hdr;
+	unsigned int tvlv_value_len;
+
+	if (skb_headroom(skb) < sizeof(*mcast_tracker) + sizeof(*tvlv_hdr))
+		return -ENOMEM;
+
+	tvlv_value_len = sizeof(*mcast_tracker) + *tvlv_len;
+	if (tvlv_value_len + sizeof(*tvlv_hdr) > U16_MAX)
+		return -ENOMEM;
+
+	batadv_mcast_forw_skb_push(skb, sizeof(*mcast_tracker), tvlv_len);
+	mcast_tracker = (struct batadv_tvlv_mcast_tracker *)skb->data;
+	mcast_tracker->num_dests = htons(num_dests);
+
+	skb_reset_network_header(skb);
+
+	batadv_mcast_forw_skb_push(skb, sizeof(*tvlv_hdr), tvlv_len);
+	tvlv_hdr = (struct batadv_tvlv_hdr *)skb->data;
+	tvlv_hdr->type = BATADV_TVLV_MCAST_TRACKER;
+	tvlv_hdr->version = 1;
+	tvlv_hdr->len = htons(tvlv_value_len);
+
+	return 0;
+}
+
+/**
+ * batadv_mcast_forw_push_tvlvs() - push a multicast tracker TVLV onto an skb
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the skb to push the tracker TVLV onto
+ * @vid: the vlan identifier
+ * @is_routable: indicates whether the destination is routable
+ * @count: the number of originators the multicast packet needs to be sent to
+ * @tvlv_len: stores the amount of currently pushed TVLV bytes
+ *
+ * Pushes a multicast tracker TVLV onto the given skb, including the collected
+ * destination MAC addresses and the generic TVLV header.
+ *
+ * Return: -ENOMEM if there is not enough skb headroom available. Otherwise, on
+ * success 0.
+ */
+static int
+batadv_mcast_forw_push_tvlvs(struct batadv_priv *bat_priv, struct sk_buff *skb,
+			     unsigned short vid, int is_routable, int count,
+			     unsigned short *tvlv_len)
+{
+	int ret;
+
+	ret = batadv_mcast_forw_push_dests(bat_priv, skb, vid, is_routable,
+					   &count, tvlv_len);
+	if (ret < 0)
+		return ret;
+
+	ret = batadv_mcast_forw_push_tracker(skb, count, tvlv_len);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+/**
+ * batadv_mcast_forw_push_hdr() - push a multicast packet header onto an skb
+ * @skb: the skb to push the header onto
+ * @tvlv_len: the total TVLV length value to set in the header
+ *
+ * Pushes a batman-adv multicast packet header onto the given skb and sets
+ * the provided total TVLV length value in it.
+ *
+ * Caller needs to ensure enough skb headroom is available.
+ *
+ * Return: -ENOMEM if there is not enough skb headroom available. Otherwise, on
+ * success 0.
+ */
+static int
+batadv_mcast_forw_push_hdr(struct sk_buff *skb, unsigned short tvlv_len)
+{
+	struct batadv_mcast_packet *mcast_packet;
+
+	if (skb_headroom(skb) < sizeof(*mcast_packet))
+		return -ENOMEM;
+
+	skb_push(skb, sizeof(*mcast_packet));
+
+	mcast_packet = (struct batadv_mcast_packet *)skb->data;
+	mcast_packet->version = BATADV_COMPAT_VERSION;
+	mcast_packet->ttl = BATADV_TTL;
+	mcast_packet->packet_type = BATADV_MCAST;
+	mcast_packet->reserved = 0;
+	mcast_packet->tvlv_len = htons(tvlv_len);
+
+	return 0;
+}
+
+/**
+ * batadv_mcast_forw_scrub_dests() - scrub destinations in a tracker TVLV
+ * @bat_priv: the bat priv with all the soft interface information
+ * @comp_neigh: next hop neighbor to scrub+collect destinations for
+ * @dest: start MAC entry in original skb's tracker TVLV
+ * @next_dest: start MAC entry in to be sent skb's tracker TVLV
+ * @num_dests: number of remaining destination MAC entries to iterate over
+ *
+ * This sorts destination entries into either the original batman-adv
+ * multicast packet or the skb (copy) that is going to be sent to comp_neigh
+ * next.
+ *
+ * In preparation for the next, to be (unicast) transmitted batman-adv multicast
+ * packet skb to be sent to the given neighbor node, tries to collect all
+ * originator MAC addresses that have the given neighbor node as their next hop
+ * in the to be transmitted skb (copy), which next_dest points into. That is we
+ * zero all destination entries in next_dest which do not have comp_neigh as
+ * their next hop. And zero all destination entries in the original skb that
+ * would have comp_neigh as their next hop (to avoid redundant transmissions and
+ * duplicated payload later).
+ */
+static void
+batadv_mcast_forw_scrub_dests(struct batadv_priv *bat_priv,
+			      struct batadv_neigh_node *comp_neigh, u8 *dest,
+			      u8 *next_dest, u16 num_dests)
+{
+	struct batadv_neigh_node *next_neigh;
+
+	/* skip first entry, this is what we are comparing with */
+	eth_zero_addr(dest);
+	dest += ETH_ALEN;
+	next_dest += ETH_ALEN;
+	num_dests--;
+
+	batadv_mcast_forw_tracker_for_each_dest2(dest, next_dest, num_dests) {
+		if (is_zero_ether_addr(next_dest))
+			continue;
+
+		/* sanity check, we expect unicast destinations */
+		if (is_multicast_ether_addr(next_dest)) {
+			eth_zero_addr(dest);
+			eth_zero_addr(next_dest);
+			continue;
+		}
+
+		next_neigh = batadv_orig_to_router(bat_priv, next_dest, NULL);
+		if (!next_neigh) {
+			eth_zero_addr(next_dest);
+			continue;
+		}
+
+		if (!batadv_compare_eth(next_neigh->addr, comp_neigh->addr)) {
+			eth_zero_addr(next_dest);
+			batadv_neigh_node_put(next_neigh);
+			continue;
+		}
+
+		/* found an entry for our next packet to transmit, so remove it
+		 * from the original packet
+		 */
+		eth_zero_addr(dest);
+		batadv_neigh_node_put(next_neigh);
+	}
+}
+
+/**
+ * batadv_mcast_forw_shrink_fill() - swap slot with next non-zero destination
+ * @slot: the to be filled zero-MAC destination entry in a tracker TVLV
+ * @num_dests_slot: remaining entries in tracker TVLV from/including slot
+ *
+ * Searches for the next non-zero-MAC destination entry in a tracker TVLV after
+ * the given slot pointer. And if found, swaps it with the zero-MAC destination
+ * entry which the slot points to.
+ *
+ * Return: true if slot was swapped/filled successfully, false otherwise.
+ */
+static bool batadv_mcast_forw_shrink_fill(u8 *slot, u16 num_dests_slot)
+{
+	u16 num_dests_filler;
+	u8 *filler;
+
+	/* sanity check, should not happen */
+	if (!num_dests_slot)
+		return false;
+
+	num_dests_filler = num_dests_slot - 1;
+	filler = slot + ETH_ALEN;
+
+	/* find a candidate to fill the empty slot */
+	batadv_mcast_forw_tracker_for_each_dest(filler, num_dests_filler) {
+		if (is_zero_ether_addr(filler))
+			continue;
+
+		ether_addr_copy(slot, filler);
+		eth_zero_addr(filler);
+		return true;
+	}
+
+	return false;
+}
+
+/**
+ * batadv_mcast_forw_shrink_pack_dests() - pack destinations of a tracker TVLV
+ * @skb: the batman-adv multicast packet to compact destinations in
+ *
+ * Compacts the originator destination MAC addresses in the multicast tracker
+ * TVLV of the given multicast packet. This is done by moving all non-zero
+ * MAC addresses in direction of the skb head and all zero MAC addresses in skb
+ * tail direction, within the multicast tracker TVLV.
+ *
+ * Return: The number of consecutive zero MAC address destinations which are
+ * now at the end of the multicast tracker TVLV.
+ */
+static int batadv_mcast_forw_shrink_pack_dests(struct sk_buff *skb)
+{
+	struct batadv_tvlv_mcast_tracker *mcast_tracker;
+	unsigned char *skb_net_hdr;
+	u16 num_dests_slot;
+	u8 *slot;
+
+	skb_net_hdr = skb_network_header(skb);
+	mcast_tracker = (struct batadv_tvlv_mcast_tracker *)skb_net_hdr;
+	num_dests_slot = ntohs(mcast_tracker->num_dests);
+
+	slot = (u8 *)mcast_tracker + sizeof(*mcast_tracker);
+
+	batadv_mcast_forw_tracker_for_each_dest(slot, num_dests_slot) {
+		/* find an empty slot */
+		if (!is_zero_ether_addr(slot))
+			continue;
+
+		if (!batadv_mcast_forw_shrink_fill(slot, num_dests_slot))
+			/* could not find a filler, so we successfully packed
+			 * and can stop - and must not reduce num_dests_slot!
+			 */
+			break;
+	}
+
+	/* num_dests_slot is now the amount of reduced, zeroed
+	 * destinations at the end of the tracker TVLV
+	 */
+	return num_dests_slot;
+}
+
+/**
+ * batadv_mcast_forw_shrink_align_offset() - get new alignment offset
+ * @num_dests_old: the old, to be updated amount of destination nodes
+ * @num_dests_reduce: the number of destinations that were removed
+ *
+ * Calculates the amount of potential extra alignment offset that is needed to
+ * adjust the TVLV padding after the change in destination nodes.
+ *
+ * Return:
+ *	0: If no change to padding is needed.
+ *	2: If padding needs to be removed.
+ *	-2: If padding needs to be added.
+ */
+static short
+batadv_mcast_forw_shrink_align_offset(unsigned int num_dests_old,
+				      unsigned int num_dests_reduce)
+{
+	/* even amount of removed destinations -> no alignment change */
+	if (!(num_dests_reduce % 2))
+		return 0;
+
+	/* even to odd amount of destinations -> remove padding */
+	if (!(num_dests_old % 2))
+		return 2;
+
+	/* odd to even amount of destinations -> add padding */
+	return -2;
+}
+
+/**
+ * batadv_mcast_forw_shrink_update_headers() - update shrunk mc packet headers
+ * @skb: the batman-adv multicast packet to update headers of
+ * @num_dests_reduce: the number of destinations that were removed
+ *
+ * This updates any fields of a batman-adv multicast packet that are affected
+ * by the reduced number of destinations in the multicast tracket TVLV. In
+ * particular this updates:
+ *
+ * The num_dest field of the multicast tracker TVLV.
+ * The TVLV length field of the according generic TVLV header.
+ * The batman-adv multicast packet's total TVLV length field.
+ *
+ * Return: The offset in skb's tail direction at which the new batman-adv
+ * multicast packet header needs to start.
+ */
+static unsigned int
+batadv_mcast_forw_shrink_update_headers(struct sk_buff *skb,
+					unsigned int num_dests_reduce)
+{
+	struct batadv_tvlv_mcast_tracker *mcast_tracker;
+	struct batadv_mcast_packet *mcast_packet;
+	struct batadv_tvlv_hdr *tvlv_hdr;
+	unsigned char *skb_net_hdr;
+	unsigned int offset;
+	short align_offset;
+	u16 num_dests;
+
+	skb_net_hdr = skb_network_header(skb);
+	mcast_tracker = (struct batadv_tvlv_mcast_tracker *)skb_net_hdr;
+	num_dests = ntohs(mcast_tracker->num_dests);
+
+	align_offset = batadv_mcast_forw_shrink_align_offset(num_dests,
+							     num_dests_reduce);
+	offset = ETH_ALEN * num_dests_reduce + align_offset;
+	num_dests -= num_dests_reduce;
+
+	/* update tracker header */
+	mcast_tracker->num_dests = htons(num_dests);
+
+	/* update tracker's tvlv header's length field */
+	tvlv_hdr = (struct batadv_tvlv_hdr *)(skb_network_header(skb) -
+					      sizeof(*tvlv_hdr));
+	tvlv_hdr->len = htons(ntohs(tvlv_hdr->len) - offset);
+
+	/* update multicast packet header's tvlv length field */
+	mcast_packet = (struct batadv_mcast_packet *)skb->data;
+	mcast_packet->tvlv_len = htons(ntohs(mcast_packet->tvlv_len) - offset);
+
+	return offset;
+}
+
+/**
+ * batadv_mcast_forw_shrink_move_headers() - move multicast headers by offset
+ * @skb: the batman-adv multicast packet to move headers for
+ * @offset: a non-negative offset to move headers by, towards the skb tail
+ *
+ * Moves the batman-adv multicast packet header, its multicast tracker TVLV and
+ * any TVLVs in between by the given offset in direction towards the tail.
+ */
+static void
+batadv_mcast_forw_shrink_move_headers(struct sk_buff *skb, unsigned int offset)
+{
+	struct batadv_tvlv_mcast_tracker *mcast_tracker;
+	unsigned char *skb_net_hdr;
+	unsigned int len;
+	u16 num_dests;
+
+	skb_net_hdr = skb_network_header(skb);
+	mcast_tracker = (struct batadv_tvlv_mcast_tracker *)skb_net_hdr;
+	num_dests = ntohs(mcast_tracker->num_dests);
+	len = skb_network_offset(skb) + sizeof(*mcast_tracker);
+	len += num_dests * ETH_ALEN;
+
+	batadv_mcast_forw_scrape(skb, len, offset);
+}
+
+/**
+ * batadv_mcast_forw_shrink_tracker() - remove zero addresses in a tracker tvlv
+ * @skb: the batman-adv multicast packet to (potentially) shrink
+ *
+ * Removes all destinations with a zero MAC addresses (00:00:00:00:00:00) from
+ * the given batman-adv multicast packet's tracker TVLV and updates headers
+ * accordingly to maintain a valid batman-adv multicast packet.
+ */
+static void batadv_mcast_forw_shrink_tracker(struct sk_buff *skb)
+{
+	unsigned int offset;
+	u16 dests_reduced;
+
+	dests_reduced = batadv_mcast_forw_shrink_pack_dests(skb);
+	if (!dests_reduced)
+		return;
+
+	offset = batadv_mcast_forw_shrink_update_headers(skb, dests_reduced);
+	batadv_mcast_forw_shrink_move_headers(skb, offset);
+}
+
+/**
+ * batadv_mcast_forw_packet() - forward a batman-adv multicast packet
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the received or locally generated batman-adv multicast packet
+ * @local_xmit: indicates that the packet was locally generated and not received
+ *
+ * Parses the tracker TVLV of a batman-adv multicast packet and forwards the
+ * packet as indicated in this TVLV.
+ *
+ * Caller needs to set the skb network header to the start of the multicast
+ * tracker TVLV (excluding the generic TVLV header) and the skb transport header
+ * to the next byte after this multicast tracker TVLV.
+ *
+ * Caller needs to free the skb.
+ *
+ * Return: NET_RX_SUCCESS or NET_RX_DROP on success or a negative error
+ * code on failure. NET_RX_SUCCESS if the received packet is supposed to be
+ * decapsulated and forwarded to the own soft interface, NET_RX_DROP otherwise.
+ */
+static int batadv_mcast_forw_packet(struct batadv_priv *bat_priv,
+				    struct sk_buff *skb, bool local_xmit)
+{
+	struct batadv_tvlv_mcast_tracker *mcast_tracker;
+	struct batadv_neigh_node *neigh_node;
+	unsigned long offset, num_dests_off;
+	struct sk_buff *nexthop_skb;
+	unsigned char *skb_net_hdr;
+	bool local_recv = false;
+	unsigned int tvlv_len;
+	bool xmitted = false;
+	u8 *dest, *next_dest;
+	u16 num_dests;
+	int ret;
+
+	/* (at least) TVLV part needs to be linearized */
+	SKB_LINEAR_ASSERT(skb);
+
+	/* check if num_dests is within skb length */
+	num_dests_off = offsetof(struct batadv_tvlv_mcast_tracker, num_dests);
+	if (num_dests_off > skb_network_header_len(skb))
+		return -EINVAL;
+
+	skb_net_hdr = skb_network_header(skb);
+	mcast_tracker = (struct batadv_tvlv_mcast_tracker *)skb_net_hdr;
+	num_dests = ntohs(mcast_tracker->num_dests);
+
+	dest = (u8 *)mcast_tracker + sizeof(*mcast_tracker);
+
+	/* check if full tracker tvlv is within skb length */
+	tvlv_len = sizeof(*mcast_tracker) + ETH_ALEN * num_dests;
+	if (tvlv_len > skb_network_header_len(skb))
+		return -EINVAL;
+
+	/* invalidate checksum: */
+	skb->ip_summed = CHECKSUM_NONE;
+
+	batadv_mcast_forw_tracker_for_each_dest(dest, num_dests) {
+		if (is_zero_ether_addr(dest))
+			continue;
+
+		/* only unicast originator addresses supported */
+		if (is_multicast_ether_addr(dest)) {
+			eth_zero_addr(dest);
+			continue;
+		}
+
+		if (batadv_is_my_mac(bat_priv, dest)) {
+			eth_zero_addr(dest);
+			local_recv = true;
+			continue;
+		}
+
+		neigh_node = batadv_orig_to_router(bat_priv, dest, NULL);
+		if (!neigh_node) {
+			eth_zero_addr(dest);
+			continue;
+		}
+
+		nexthop_skb = skb_copy(skb, GFP_ATOMIC);
+		if (!nexthop_skb) {
+			batadv_neigh_node_put(neigh_node);
+			return -ENOMEM;
+		}
+
+		offset = dest - skb->data;
+		next_dest = nexthop_skb->data + offset;
+
+		batadv_mcast_forw_scrub_dests(bat_priv, neigh_node, dest,
+					      next_dest, num_dests);
+		batadv_mcast_forw_shrink_tracker(nexthop_skb);
+
+		batadv_inc_counter(bat_priv, BATADV_CNT_MCAST_TX);
+		batadv_add_counter(bat_priv, BATADV_CNT_MCAST_TX_BYTES,
+				   nexthop_skb->len + ETH_HLEN);
+		xmitted = true;
+		ret = batadv_send_unicast_skb(nexthop_skb, neigh_node);
+
+		batadv_neigh_node_put(neigh_node);
+
+		if (ret < 0)
+			return ret;
+	}
+
+	if (xmitted) {
+		if (local_xmit) {
+			batadv_inc_counter(bat_priv, BATADV_CNT_MCAST_TX_LOCAL);
+			batadv_add_counter(bat_priv,
+					   BATADV_CNT_MCAST_TX_LOCAL_BYTES,
+					   skb->len -
+					   skb_transport_offset(skb));
+		} else {
+			batadv_inc_counter(bat_priv, BATADV_CNT_MCAST_FWD);
+			batadv_add_counter(bat_priv, BATADV_CNT_MCAST_FWD_BYTES,
+					   skb->len + ETH_HLEN);
+		}
+	}
+
+	if (local_recv)
+		return NET_RX_SUCCESS;
+	else
+		return NET_RX_DROP;
+}
+
+/**
+ * batadv_mcast_forw_tracker_tvlv_handler() - handle an mcast tracker tvlv
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the received batman-adv multicast packet
+ *
+ * Parses the tracker TVLV of an incoming batman-adv multicast packet and
+ * forwards the packet as indicated in this TVLV.
+ *
+ * Caller needs to set the skb network header to the start of the multicast
+ * tracker TVLV (excluding the generic TVLV header) and the skb transport header
+ * to the next byte after this multicast tracker TVLV.
+ *
+ * Caller needs to free the skb.
+ *
+ * Return: NET_RX_SUCCESS or NET_RX_DROP on success or a negative error
+ * code on failure. NET_RX_SUCCESS if the received packet is supposed to be
+ * decapsulated and forwarded to the own soft interface, NET_RX_DROP otherwise.
+ */
+int batadv_mcast_forw_tracker_tvlv_handler(struct batadv_priv *bat_priv,
+					   struct sk_buff *skb)
+{
+	return batadv_mcast_forw_packet(bat_priv, skb, false);
+}
+
+/**
+ * batadv_mcast_forw_packet_hdrlen() - multicast packet header length
+ * @num_dests: number of destination nodes
+ *
+ * Calculates the total batman-adv multicast packet header length for a given
+ * number of destination nodes (excluding the outer ethernet frame).
+ *
+ * Return: The calculated total batman-adv multicast packet header length.
+ */
+unsigned int batadv_mcast_forw_packet_hdrlen(unsigned int num_dests)
+{
+	/**
+	 * If the number of destination entries is even then we need to add
+	 * two byte padding to the tracker TVLV.
+	 */
+	int padding = (!(num_dests % 2)) ? 2 : 0;
+
+	return padding + num_dests * ETH_ALEN +
+	       sizeof(struct batadv_tvlv_mcast_tracker) +
+	       sizeof(struct batadv_tvlv_hdr) +
+	       sizeof(struct batadv_mcast_packet);
+}
+
+/**
+ * batadv_mcast_forw_expand_head() - expand headroom for an mcast packet
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the multicast packet to send
+ *
+ * Tries to expand an skb's headroom so that its head to tail is 1298
+ * bytes (minimum IPv6 MTU + vlan ethernet header size) large.
+ *
+ * Return: -EINVAL if the given skb's length is too large or -ENOMEM on memory
+ * allocation failure. Otherwise, on success, zero is returned.
+ */
+static int batadv_mcast_forw_expand_head(struct batadv_priv *bat_priv,
+					 struct sk_buff *skb)
+{
+	int hdr_size = VLAN_ETH_HLEN + IPV6_MIN_MTU - skb->len;
+
+	 /* TODO: Could be tightened to actual number of destination nodes?
+	  * But it's tricky, number of destinations might have increased since
+	  * we last checked.
+	  */
+	if (hdr_size < 0) {
+		/* batadv_mcast_forw_mode_check_count() should ensure we do not
+		 * end up here
+		 */
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	if (skb_headroom(skb) < hdr_size &&
+	    pskb_expand_head(skb, hdr_size, 0, GFP_ATOMIC) < 0)
+		return -ENOMEM;
+
+	return 0;
+}
+
+/**
+ * batadv_mcast_forw_push() - encapsulate skb in a batman-adv multicast packet
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the multicast packet to encapsulate and send
+ * @vid: the vlan identifier
+ * @is_routable: indicates whether the destination is routable
+ * @count: the number of originators the multicast packet needs to be sent to
+ *
+ * Encapsulates the given multicast packet in a batman-adv multicast packet.
+ * A multicast tracker TVLV with destination originator addresses for any node
+ * that signaled interest in it, that is either via the translation table or the
+ * according want-all flags, is attached accordingly.
+ *
+ * Return: true on success, false otherwise.
+ */
+bool batadv_mcast_forw_push(struct batadv_priv *bat_priv, struct sk_buff *skb,
+			    unsigned short vid, int is_routable, int count)
+{
+	unsigned short tvlv_len = 0;
+	int ret;
+
+	if (batadv_mcast_forw_expand_head(bat_priv, skb) < 0)
+		goto err;
+
+	skb_reset_transport_header(skb);
+
+	ret = batadv_mcast_forw_push_tvlvs(bat_priv, skb, vid, is_routable,
+					   count, &tvlv_len);
+	if (ret < 0)
+		goto err;
+
+	ret = batadv_mcast_forw_push_hdr(skb, tvlv_len);
+	if (ret < 0)
+		goto err;
+
+	return true;
+
+err:
+	if (tvlv_len)
+		skb_pull(skb, tvlv_len);
+
+	return false;
+}
+
+/**
+ * batadv_mcast_forw_mcsend() - send a self prepared batman-adv multicast packet
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the multicast packet to encapsulate and send
+ *
+ * Transmits a batman-adv multicast packet that was locally prepared and
+ * consumes/frees it.
+ *
+ * Return: NET_XMIT_DROP on memory allocation failure. NET_XMIT_SUCCESS
+ * otherwise.
+ */
+int batadv_mcast_forw_mcsend(struct batadv_priv *bat_priv,
+			     struct sk_buff *skb)
+{
+	int ret = batadv_mcast_forw_packet(bat_priv, skb, true);
+
+	if (ret < 0) {
+		kfree_skb(skb);
+		return NET_XMIT_DROP;
+	}
+
+	consume_skb(skb);
+	return NET_XMIT_SUCCESS;
+}
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index 0c64d81a7761..1f7ed9d4f6fd 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -7,6 +7,7 @@
 #include "netlink.h"
 #include "main.h"
 
+#include <linux/array_size.h>
 #include <linux/atomic.h>
 #include <linux/bitops.h>
 #include <linux/bug.h>
@@ -20,7 +21,6 @@
 #include <linux/if_ether.h>
 #include <linux/if_vlan.h>
 #include <linux/init.h>
-#include <linux/kernel.h>
 #include <linux/limits.h>
 #include <linux/list.h>
 #include <linux/minmax.h>
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 34903df4fe93..71c143d4b6d0 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -312,6 +312,33 @@ batadv_orig_router_get(struct batadv_orig_node *orig_node,
 }
 
 /**
+ * batadv_orig_to_router() - get next hop neighbor to an orig address
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig_addr: the originator MAC address to search the best next hop router for
+ * @if_outgoing: the interface where the payload packet has been received or
+ *  the OGM should be sent to
+ *
+ * Return: A neighbor node which is the best router towards the given originator
+ * address.
+ */
+struct batadv_neigh_node *
+batadv_orig_to_router(struct batadv_priv *bat_priv, u8 *orig_addr,
+		      struct batadv_hard_iface *if_outgoing)
+{
+	struct batadv_neigh_node *neigh_node;
+	struct batadv_orig_node *orig_node;
+
+	orig_node = batadv_orig_hash_find(bat_priv, orig_addr);
+	if (!orig_node)
+		return NULL;
+
+	neigh_node = batadv_find_router(bat_priv, orig_node, if_outgoing);
+	batadv_orig_node_put(orig_node);
+
+	return neigh_node;
+}
+
+/**
  * batadv_orig_ifinfo_get() - find the ifinfo from an orig_node
  * @orig_node: the orig node to be queried
  * @if_outgoing: the interface for which the ifinfo should be acquired
@@ -942,6 +969,7 @@ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv,
 #ifdef CONFIG_BATMAN_ADV_MCAST
 	orig_node->mcast_flags = BATADV_MCAST_WANT_NO_RTR4;
 	orig_node->mcast_flags |= BATADV_MCAST_WANT_NO_RTR6;
+	orig_node->mcast_flags |= BATADV_MCAST_HAVE_MC_PTYPE_CAPA;
 	INIT_HLIST_NODE(&orig_node->mcast_want_all_unsnoopables_node);
 	INIT_HLIST_NODE(&orig_node->mcast_want_all_ipv4_node);
 	INIT_HLIST_NODE(&orig_node->mcast_want_all_ipv6_node);
diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h
index ea3d69e4e670..db0c55128170 100644
--- a/net/batman-adv/originator.h
+++ b/net/batman-adv/originator.h
@@ -36,6 +36,9 @@ void batadv_neigh_node_release(struct kref *ref);
 struct batadv_neigh_node *
 batadv_orig_router_get(struct batadv_orig_node *orig_node,
 		       const struct batadv_hard_iface *if_outgoing);
+struct batadv_neigh_node *
+batadv_orig_to_router(struct batadv_priv *bat_priv, u8 *orig_addr,
+		      struct batadv_hard_iface *if_outgoing);
 struct batadv_neigh_ifinfo *
 batadv_neigh_ifinfo_new(struct batadv_neigh_node *neigh,
 			struct batadv_hard_iface *if_outgoing);
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index 163cd43c4821..f1061985149f 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -1270,3 +1270,73 @@ out:
 	batadv_orig_node_put(orig_node);
 	return ret;
 }
+
+#ifdef CONFIG_BATMAN_ADV_MCAST
+/**
+ * batadv_recv_mcast_packet() - process received batman-adv multicast packet
+ * @skb: the received batman-adv multicast packet
+ * @recv_if: interface that the skb is received on
+ *
+ * Parses the given, received batman-adv multicast packet. Depending on the
+ * contents of its TVLV forwards it and/or decapsulates it to hand it to the
+ * soft interface.
+ *
+ * Return: NET_RX_DROP if the skb is not consumed, NET_RX_SUCCESS otherwise.
+ */
+int batadv_recv_mcast_packet(struct sk_buff *skb,
+			     struct batadv_hard_iface *recv_if)
+{
+	struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface);
+	struct batadv_mcast_packet *mcast_packet;
+	int hdr_size = sizeof(*mcast_packet);
+	unsigned char *tvlv_buff;
+	int ret = NET_RX_DROP;
+	u16 tvlv_buff_len;
+
+	if (batadv_check_unicast_packet(bat_priv, skb, hdr_size) < 0)
+		goto free_skb;
+
+	/* create a copy of the skb, if needed, to modify it. */
+	if (skb_cow(skb, ETH_HLEN) < 0)
+		goto free_skb;
+
+	/* packet needs to be linearized to access the tvlv content */
+	if (skb_linearize(skb) < 0)
+		goto free_skb;
+
+	mcast_packet = (struct batadv_mcast_packet *)skb->data;
+	if (mcast_packet->ttl-- < 2)
+		goto free_skb;
+
+	tvlv_buff = (unsigned char *)(skb->data + hdr_size);
+	tvlv_buff_len = ntohs(mcast_packet->tvlv_len);
+
+	if (tvlv_buff_len > skb->len - hdr_size)
+		goto free_skb;
+
+	ret = batadv_tvlv_containers_process(bat_priv, BATADV_MCAST, NULL, skb,
+					     tvlv_buff, tvlv_buff_len);
+	if (ret >= 0) {
+		batadv_inc_counter(bat_priv, BATADV_CNT_MCAST_RX);
+		batadv_add_counter(bat_priv, BATADV_CNT_MCAST_RX_BYTES,
+				   skb->len + ETH_HLEN);
+	}
+
+	hdr_size += tvlv_buff_len;
+
+	if (ret == NET_RX_SUCCESS && (skb->len - hdr_size >= ETH_HLEN)) {
+		batadv_inc_counter(bat_priv, BATADV_CNT_MCAST_RX_LOCAL);
+		batadv_add_counter(bat_priv, BATADV_CNT_MCAST_RX_LOCAL_BYTES,
+				   skb->len - hdr_size);
+
+		batadv_interface_rx(bat_priv->soft_iface, skb, hdr_size, NULL);
+		/* skb was consumed */
+		skb = NULL;
+	}
+
+free_skb:
+	kfree_skb(skb);
+
+	return ret;
+}
+#endif /* CONFIG_BATMAN_ADV_MCAST */
diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h
index afd15b3879f1..e9849f032a24 100644
--- a/net/batman-adv/routing.h
+++ b/net/batman-adv/routing.h
@@ -27,6 +27,17 @@ int batadv_recv_frag_packet(struct sk_buff *skb,
 			    struct batadv_hard_iface *iface);
 int batadv_recv_bcast_packet(struct sk_buff *skb,
 			     struct batadv_hard_iface *recv_if);
+#ifdef CONFIG_BATMAN_ADV_MCAST
+int batadv_recv_mcast_packet(struct sk_buff *skb,
+			     struct batadv_hard_iface *recv_if);
+#else
+static inline int batadv_recv_mcast_packet(struct sk_buff *skb,
+					   struct batadv_hard_iface *recv_if)
+{
+	kfree_skb(skb);
+	return NET_RX_DROP;
+}
+#endif
 int batadv_recv_unicast_tvlv(struct sk_buff *skb,
 			     struct batadv_hard_iface *recv_if);
 int batadv_recv_unhandled_unicast_packet(struct sk_buff *skb,
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 1bf1232a4f75..89c51b3cf430 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -301,12 +301,13 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb,
 
 send:
 		if (do_bcast && !is_broadcast_ether_addr(ethhdr->h_dest)) {
-			forw_mode = batadv_mcast_forw_mode(bat_priv, skb,
+			forw_mode = batadv_mcast_forw_mode(bat_priv, skb, vid,
 							   &mcast_is_routable);
 			switch (forw_mode) {
 			case BATADV_FORW_BCAST:
 				break;
 			case BATADV_FORW_UCASTS:
+			case BATADV_FORW_MCAST:
 				do_bcast = false;
 				break;
 			case BATADV_FORW_NONE:
@@ -365,6 +366,8 @@ send:
 		} else if (forw_mode == BATADV_FORW_UCASTS) {
 			ret = batadv_mcast_forw_send(bat_priv, skb, vid,
 						     mcast_is_routable);
+		} else if (forw_mode == BATADV_FORW_MCAST) {
+			ret = batadv_mcast_forw_mcsend(bat_priv, skb);
 		} else {
 			if (batadv_dat_snoop_outgoing_arp_request(bat_priv,
 								  skb))
@@ -762,6 +765,7 @@ static int batadv_softif_init_late(struct net_device *dev)
 	atomic_set(&bat_priv->mcast.num_want_all_unsnoopables, 0);
 	atomic_set(&bat_priv->mcast.num_want_all_ipv4, 0);
 	atomic_set(&bat_priv->mcast.num_want_all_ipv6, 0);
+	atomic_set(&bat_priv->mcast.num_no_mc_ptype_capa, 0);
 #endif
 	atomic_set(&bat_priv->gw.mode, BATADV_GW_MODE_OFF);
 	atomic_set(&bat_priv->gw.bandwidth_down, 100);
@@ -925,6 +929,18 @@ static const struct {
 	{ "tt_response_rx" },
 	{ "tt_roam_adv_tx" },
 	{ "tt_roam_adv_rx" },
+#ifdef CONFIG_BATMAN_ADV_MCAST
+	{ "mcast_tx" },
+	{ "mcast_tx_bytes" },
+	{ "mcast_tx_local" },
+	{ "mcast_tx_local_bytes" },
+	{ "mcast_rx" },
+	{ "mcast_rx_bytes" },
+	{ "mcast_rx_local" },
+	{ "mcast_rx_local_bytes" },
+	{ "mcast_fwd" },
+	{ "mcast_fwd_bytes" },
+#endif
 #ifdef CONFIG_BATMAN_ADV_DAT
 	{ "dat_get_tx" },
 	{ "dat_get_rx" },
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 17d5ea1d8e84..00840d5784fe 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -862,6 +862,70 @@ enum batadv_counters {
 	 */
 	BATADV_CNT_TT_ROAM_ADV_RX,
 
+#ifdef CONFIG_BATMAN_ADV_MCAST
+	/**
+	 * @BATADV_CNT_MCAST_TX: transmitted batman-adv multicast packets
+	 *  counter
+	 */
+	BATADV_CNT_MCAST_TX,
+
+	/**
+	 * @BATADV_CNT_MCAST_TX_BYTES: transmitted batman-adv multicast packets
+	 *  bytes counter
+	 */
+	BATADV_CNT_MCAST_TX_BYTES,
+
+	/**
+	 * @BATADV_CNT_MCAST_TX_LOCAL: counter for multicast packets which
+	 *  were locally encapsulated and transmitted as batman-adv multicast
+	 *  packets
+	 */
+	BATADV_CNT_MCAST_TX_LOCAL,
+
+	/**
+	 * @BATADV_CNT_MCAST_TX_LOCAL_BYTES: bytes counter for multicast packets
+	 *  which were locally encapsulated and transmitted as batman-adv
+	 *  multicast packets
+	 */
+	BATADV_CNT_MCAST_TX_LOCAL_BYTES,
+
+	/**
+	 * @BATADV_CNT_MCAST_RX: received batman-adv multicast packet counter
+	 */
+	BATADV_CNT_MCAST_RX,
+
+	/**
+	 * @BATADV_CNT_MCAST_RX_BYTES: received batman-adv multicast packet
+	 *  bytes counter
+	 */
+	BATADV_CNT_MCAST_RX_BYTES,
+
+	/**
+	 * @BATADV_CNT_MCAST_RX_LOCAL: counter for received batman-adv multicast
+	 *  packets which were forwarded to the local soft interface
+	 */
+	BATADV_CNT_MCAST_RX_LOCAL,
+
+	/**
+	 * @BATADV_CNT_MCAST_RX_LOCAL_BYTES: bytes counter for received
+	 *  batman-adv multicast packets which were forwarded to the local soft
+	 *  interface
+	 */
+	BATADV_CNT_MCAST_RX_LOCAL_BYTES,
+
+	/**
+	 * @BATADV_CNT_MCAST_FWD: counter for received batman-adv multicast
+	 *  packets which were forwarded to other, neighboring nodes
+	 */
+	BATADV_CNT_MCAST_FWD,
+
+	/**
+	 * @BATADV_CNT_MCAST_FWD_BYTES: bytes counter for received batman-adv
+	 *  multicast packets which were forwarded to other, neighboring nodes
+	 */
+	BATADV_CNT_MCAST_FWD_BYTES,
+#endif
+
 #ifdef CONFIG_BATMAN_ADV_DAT
 	/**
 	 * @BATADV_CNT_DAT_GET_TX: transmitted dht GET traffic packet counter
@@ -1279,6 +1343,12 @@ struct batadv_priv_mcast {
 	atomic_t num_want_all_rtr6;
 
 	/**
+	 * @num_no_mc_ptype_capa: counter for number of nodes without the
+	 *  BATADV_MCAST_HAVE_MC_PTYPE_CAPA flag
+	 */
+	atomic_t num_no_mc_ptype_capa;
+
+	/**
 	 * @want_lists_lock: lock for protecting modifications to mcasts
 	 *  want_all_{unsnoopables,ipv4,ipv6}_list (traversals are rcu-locked)
 	 */
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 336a76165454..b93464ac3517 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -309,11 +309,14 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	if (flags & MSG_OOB)
 		return -EOPNOTSUPP;
 
+	lock_sock(sk);
+
 	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb) {
 		if (sk->sk_shutdown & RCV_SHUTDOWN)
-			return 0;
+			err = 0;
 
+		release_sock(sk);
 		return err;
 	}
 
@@ -343,6 +346,8 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 	skb_free_datagram(sk, skb);
 
+	release_sock(sk);
+
 	if (flags & MSG_TRUNC)
 		copied = skblen;
 
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 2cee330188ce..a41d2693f4d8 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -300,6 +300,13 @@ static int configure_datapath_sync(struct hci_dev *hdev, struct bt_codec *codec)
 	__u8 vnd_len, *vnd_data = NULL;
 	struct hci_op_configure_data_path *cmd = NULL;
 
+	if (!codec->data_path || !hdev->get_codec_config_data)
+		return 0;
+
+	/* Do not take me as error */
+	if (!hdev->get_codec_config_data)
+		return 0;
+
 	err = hdev->get_codec_config_data(hdev, ESCO_LINK, codec, &vnd_len,
 					  &vnd_data);
 	if (err < 0)
@@ -345,9 +352,7 @@ static int hci_enhanced_setup_sync(struct hci_dev *hdev, void *data)
 
 	bt_dev_dbg(hdev, "hcon %p", conn);
 
-	/* for offload use case, codec needs to configured before opening SCO */
-	if (conn->codec.data_path)
-		configure_datapath_sync(hdev, &conn->codec);
+	configure_datapath_sync(hdev, &conn->codec);
 
 	conn->state = BT_CONNECT;
 	conn->out = true;
@@ -1086,8 +1091,9 @@ static void hci_conn_cleanup_child(struct hci_conn *conn, u8 reason)
 			hci_conn_failed(conn, reason);
 		break;
 	case ISO_LINK:
-		if (conn->state != BT_CONNECTED &&
-		    !test_bit(HCI_CONN_CREATE_CIS, &conn->flags))
+		if ((conn->state != BT_CONNECTED &&
+		    !test_bit(HCI_CONN_CREATE_CIS, &conn->flags)) ||
+		    test_bit(HCI_CONN_BIG_CREATED, &conn->flags))
 			hci_conn_failed(conn, reason);
 		break;
 	}
@@ -2228,7 +2234,17 @@ struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst,
 			      __u8 base_len, __u8 *base)
 {
 	struct hci_conn *conn;
+	struct hci_conn *parent;
 	__u8 eir[HCI_MAX_PER_AD_LENGTH];
+	struct hci_link *link;
+
+	/* Look for any BIS that is open for rebinding */
+	conn = hci_conn_hash_lookup_big_state(hdev, qos->bcast.big, BT_OPEN);
+	if (conn) {
+		memcpy(qos, &conn->iso_qos, sizeof(*qos));
+		conn->state = BT_CONNECTED;
+		return conn;
+	}
 
 	if (base_len && base)
 		base_len = eir_append_service_data(eir, 0,  0x1851,
@@ -2256,6 +2272,20 @@ struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst,
 	conn->iso_qos = *qos;
 	conn->state = BT_BOUND;
 
+	/* Link BISes together */
+	parent = hci_conn_hash_lookup_big(hdev,
+					  conn->iso_qos.bcast.big);
+	if (parent && parent != conn) {
+		link = hci_conn_link(parent, conn);
+		if (!link) {
+			hci_conn_drop(conn);
+			return ERR_PTR(-ENOLINK);
+		}
+
+		/* Link takes the refcount */
+		hci_conn_drop(conn);
+	}
+
 	return conn;
 }
 
@@ -2287,6 +2317,9 @@ struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst,
 	if (IS_ERR(conn))
 		return conn;
 
+	if (conn->state == BT_CONNECTED)
+		return conn;
+
 	data.big = qos->bcast.big;
 	data.bis = qos->bcast.bis;
 
@@ -2421,12 +2454,10 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type)
 		hci_send_cmd(conn->hdev, HCI_OP_AUTH_REQUESTED,
 			     sizeof(cp), &cp);
 
-		/* If we're already encrypted set the REAUTH_PEND flag,
-		 * otherwise set the ENCRYPT_PEND.
+		/* Set the ENCRYPT_PEND to trigger encryption after
+		 * authentication.
 		 */
-		if (test_bit(HCI_CONN_ENCRYPT, &conn->flags))
-			set_bit(HCI_CONN_REAUTH_PEND, &conn->flags);
-		else
+		if (!test_bit(HCI_CONN_ENCRYPT, &conn->flags))
 			set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
 	}
 
diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c
index 6b7741f6e95b..233453807b50 100644
--- a/net/bluetooth/hci_debugfs.c
+++ b/net/bluetooth/hci_debugfs.c
@@ -1046,10 +1046,12 @@ static int min_key_size_set(void *data, u64 val)
 {
 	struct hci_dev *hdev = data;
 
-	if (val > hdev->le_max_key_size || val < SMP_MIN_ENC_KEY_SIZE)
+	hci_dev_lock(hdev);
+	if (val > hdev->le_max_key_size || val < SMP_MIN_ENC_KEY_SIZE) {
+		hci_dev_unlock(hdev);
 		return -EINVAL;
+	}
 
-	hci_dev_lock(hdev);
 	hdev->le_min_key_size = val;
 	hci_dev_unlock(hdev);
 
@@ -1074,10 +1076,12 @@ static int max_key_size_set(void *data, u64 val)
 {
 	struct hci_dev *hdev = data;
 
-	if (val > SMP_MAX_ENC_KEY_SIZE || val < hdev->le_min_key_size)
+	hci_dev_lock(hdev);
+	if (val > SMP_MAX_ENC_KEY_SIZE || val < hdev->le_min_key_size) {
+		hci_dev_unlock(hdev);
 		return -EINVAL;
+	}
 
-	hci_dev_lock(hdev);
 	hdev->le_max_key_size = val;
 	hci_dev_unlock(hdev);
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 0849e0dafa95..ef8c3bed7361 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -516,6 +516,9 @@ static u8 hci_cc_read_class_of_dev(struct hci_dev *hdev, void *data,
 {
 	struct hci_rp_read_class_of_dev *rp = data;
 
+	if (WARN_ON(!hdev))
+		return HCI_ERROR_UNSPECIFIED;
+
 	bt_dev_dbg(hdev, "status 0x%2.2x", rp->status);
 
 	if (rp->status)
@@ -747,9 +750,23 @@ static u8 hci_cc_read_enc_key_size(struct hci_dev *hdev, void *data,
 	} else {
 		conn->enc_key_size = rp->key_size;
 		status = 0;
+
+		if (conn->enc_key_size < hdev->min_enc_key_size) {
+			/* As slave role, the conn->state has been set to
+			 * BT_CONNECTED and l2cap conn req might not be received
+			 * yet, at this moment the l2cap layer almost does
+			 * nothing with the non-zero status.
+			 * So we also clear encrypt related bits, and then the
+			 * handler of l2cap conn req will get the right secure
+			 * state at a later time.
+			 */
+			status = HCI_ERROR_AUTH_FAILURE;
+			clear_bit(HCI_CONN_ENCRYPT, &conn->flags);
+			clear_bit(HCI_CONN_AES_CCM, &conn->flags);
+		}
 	}
 
-	hci_encrypt_cfm(conn, 0);
+	hci_encrypt_cfm(conn, status);
 
 done:
 	hci_dev_unlock(hdev);
@@ -820,8 +837,6 @@ static u8 hci_cc_write_auth_payload_timeout(struct hci_dev *hdev, void *data,
 	if (!rp->status)
 		conn->auth_payload_timeout = get_unaligned_le16(sent + 2);
 
-	hci_encrypt_cfm(conn, 0);
-
 unlock:
 	hci_dev_unlock(hdev);
 
@@ -2304,7 +2319,8 @@ static void hci_cs_inquiry(struct hci_dev *hdev, __u8 status)
 		return;
 	}
 
-	set_bit(HCI_INQUIRY, &hdev->flags);
+	if (hci_sent_cmd_data(hdev, HCI_OP_INQUIRY))
+		set_bit(HCI_INQUIRY, &hdev->flags);
 }
 
 static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status)
@@ -3484,14 +3500,8 @@ static void hci_auth_complete_evt(struct hci_dev *hdev, void *data,
 
 	if (!ev->status) {
 		clear_bit(HCI_CONN_AUTH_FAILURE, &conn->flags);
-
-		if (!hci_conn_ssp_enabled(conn) &&
-		    test_bit(HCI_CONN_REAUTH_PEND, &conn->flags)) {
-			bt_dev_info(hdev, "re-auth of legacy device is not possible.");
-		} else {
-			set_bit(HCI_CONN_AUTH, &conn->flags);
-			conn->sec_level = conn->pending_sec_level;
-		}
+		set_bit(HCI_CONN_AUTH, &conn->flags);
+		conn->sec_level = conn->pending_sec_level;
 	} else {
 		if (ev->status == HCI_ERROR_PIN_OR_KEY_MISSING)
 			set_bit(HCI_CONN_AUTH_FAILURE, &conn->flags);
@@ -3500,7 +3510,6 @@ static void hci_auth_complete_evt(struct hci_dev *hdev, void *data,
 	}
 
 	clear_bit(HCI_CONN_AUTH_PEND, &conn->flags);
-	clear_bit(HCI_CONN_REAUTH_PEND, &conn->flags);
 
 	if (conn->state == BT_CONFIG) {
 		if (!ev->status && hci_conn_ssp_enabled(conn)) {
@@ -3683,12 +3692,8 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, void *data,
 		cp.handle = cpu_to_le16(conn->handle);
 		cp.timeout = cpu_to_le16(hdev->auth_payload_timeout);
 		if (hci_send_cmd(conn->hdev, HCI_OP_WRITE_AUTH_PAYLOAD_TO,
-				 sizeof(cp), &cp)) {
+				 sizeof(cp), &cp))
 			bt_dev_err(hdev, "write auth payload timeout failed");
-			goto notify;
-		}
-
-		goto unlock;
 	}
 
 notify:
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index d85a7091a116..a6fc8a2a5c67 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -348,8 +348,6 @@ static void le_scan_disable(struct work_struct *work)
 	if (!hci_dev_test_flag(hdev, HCI_LE_SCAN))
 		goto _return;
 
-	cancel_delayed_work(&hdev->le_scan_restart);
-
 	status = hci_cmd_sync_queue(hdev, scan_disable_sync, NULL, NULL);
 	if (status) {
 		bt_dev_err(hdev, "failed to disable LE scan: %d", status);
@@ -397,71 +395,6 @@ _return:
 
 static int hci_le_set_scan_enable_sync(struct hci_dev *hdev, u8 val,
 				       u8 filter_dup);
-static int hci_le_scan_restart_sync(struct hci_dev *hdev)
-{
-	/* If controller is not scanning we are done. */
-	if (!hci_dev_test_flag(hdev, HCI_LE_SCAN))
-		return 0;
-
-	if (hdev->scanning_paused) {
-		bt_dev_dbg(hdev, "Scanning is paused for suspend");
-		return 0;
-	}
-
-	hci_le_set_scan_enable_sync(hdev, LE_SCAN_DISABLE, 0x00);
-	return hci_le_set_scan_enable_sync(hdev, LE_SCAN_ENABLE,
-					   LE_SCAN_FILTER_DUP_ENABLE);
-}
-
-static void le_scan_restart(struct work_struct *work)
-{
-	struct hci_dev *hdev = container_of(work, struct hci_dev,
-					    le_scan_restart.work);
-	unsigned long timeout, duration, scan_start, now;
-	int status;
-
-	bt_dev_dbg(hdev, "");
-
-	status = hci_le_scan_restart_sync(hdev);
-	if (status) {
-		bt_dev_err(hdev, "failed to restart LE scan: status %d",
-			   status);
-		return;
-	}
-
-	hci_dev_lock(hdev);
-
-	if (!test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks) ||
-	    !hdev->discovery.scan_start)
-		goto unlock;
-
-	/* When the scan was started, hdev->le_scan_disable has been queued
-	 * after duration from scan_start. During scan restart this job
-	 * has been canceled, and we need to queue it again after proper
-	 * timeout, to make sure that scan does not run indefinitely.
-	 */
-	duration = hdev->discovery.scan_duration;
-	scan_start = hdev->discovery.scan_start;
-	now = jiffies;
-	if (now - scan_start <= duration) {
-		int elapsed;
-
-		if (now >= scan_start)
-			elapsed = now - scan_start;
-		else
-			elapsed = ULONG_MAX - scan_start + now;
-
-		timeout = duration - elapsed;
-	} else {
-		timeout = 0;
-	}
-
-	queue_delayed_work(hdev->req_workqueue,
-			   &hdev->le_scan_disable, timeout);
-
-unlock:
-	hci_dev_unlock(hdev);
-}
 
 static int reenable_adv_sync(struct hci_dev *hdev, void *data)
 {
@@ -630,7 +563,6 @@ void hci_cmd_sync_init(struct hci_dev *hdev)
 	INIT_WORK(&hdev->cmd_sync_cancel_work, hci_cmd_sync_cancel_work);
 	INIT_WORK(&hdev->reenable_adv_work, reenable_adv);
 	INIT_DELAYED_WORK(&hdev->le_scan_disable, le_scan_disable);
-	INIT_DELAYED_WORK(&hdev->le_scan_restart, le_scan_restart);
 	INIT_DELAYED_WORK(&hdev->adv_instance_expire, adv_timeout_expire);
 }
 
@@ -3800,12 +3732,14 @@ static int hci_set_event_mask_sync(struct hci_dev *hdev)
 	if (lmp_bredr_capable(hdev)) {
 		events[4] |= 0x01; /* Flow Specification Complete */
 
-		/* Don't set Disconnect Complete when suspended as that
-		 * would wakeup the host when disconnecting due to
-		 * suspend.
+		/* Don't set Disconnect Complete and mode change when
+		 * suspended as that would wakeup the host when disconnecting
+		 * due to suspend.
 		 */
-		if (hdev->suspended)
+		if (hdev->suspended) {
 			events[0] &= 0xef;
+			events[2] &= 0xf7;
+		}
 	} else {
 		/* Use a different default for LE-only devices */
 		memset(events, 0, sizeof(events));
@@ -4960,7 +4894,6 @@ int hci_dev_close_sync(struct hci_dev *hdev)
 	cancel_delayed_work(&hdev->power_off);
 	cancel_delayed_work(&hdev->ncmd_timer);
 	cancel_delayed_work(&hdev->le_scan_disable);
-	cancel_delayed_work(&hdev->le_scan_restart);
 
 	hci_request_cancel_all(hdev);
 
@@ -5178,7 +5111,6 @@ int hci_stop_discovery_sync(struct hci_dev *hdev)
 
 		if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) {
 			cancel_delayed_work(&hdev->le_scan_disable);
-			cancel_delayed_work(&hdev->le_scan_restart);
 
 			err = hci_scan_disable_sync(hdev);
 			if (err)
@@ -5686,19 +5618,18 @@ static int hci_active_scan_sync(struct hci_dev *hdev, uint16_t interval)
 	if (err < 0)
 		own_addr_type = ADDR_LE_DEV_PUBLIC;
 
-	if (hci_is_adv_monitoring(hdev)) {
+	if (hci_is_adv_monitoring(hdev) ||
+	    (test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks) &&
+	    hdev->discovery.result_filtering)) {
 		/* Duplicate filter should be disabled when some advertisement
 		 * monitor is activated, otherwise AdvMon can only receive one
 		 * advertisement for one peer(*) during active scanning, and
 		 * might report loss to these peers.
 		 *
-		 * Note that different controllers have different meanings of
-		 * |duplicate|. Some of them consider packets with the same
-		 * address as duplicate, and others consider packets with the
-		 * same address and the same RSSI as duplicate. Although in the
-		 * latter case we don't need to disable duplicate filter, but
-		 * it is common to have active scanning for a short period of
-		 * time, the power impact should be neglectable.
+		 * If controller does strict duplicate filtering and the
+		 * discovery requires result filtering disables controller based
+		 * filtering since that can cause reports that would match the
+		 * host filter to not be reported.
 		 */
 		filter_dup = LE_SCAN_FILTER_DUP_DISABLE;
 	}
@@ -5778,17 +5709,6 @@ int hci_start_discovery_sync(struct hci_dev *hdev)
 
 	bt_dev_dbg(hdev, "timeout %u ms", jiffies_to_msecs(timeout));
 
-	/* When service discovery is used and the controller has a
-	 * strict duplicate filter, it is important to remember the
-	 * start and duration of the scan. This is required for
-	 * restarting scanning during the discovery phase.
-	 */
-	if (test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks) &&
-	    hdev->discovery.result_filtering) {
-		hdev->discovery.scan_start = jiffies;
-		hdev->discovery.scan_duration = timeout;
-	}
-
 	queue_delayed_work(hdev->req_workqueue, &hdev->le_scan_disable,
 			   timeout);
 	return 0;
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 07b80e97aead..04f6572d35f1 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -54,6 +54,7 @@ static void iso_sock_kill(struct sock *sk);
 enum {
 	BT_SK_BIG_SYNC,
 	BT_SK_PA_SYNC,
+	BT_SK_PA_SYNC_TERM,
 };
 
 struct iso_pinfo {
@@ -82,6 +83,11 @@ static bool iso_match_sid(struct sock *sk, void *data);
 static bool iso_match_sync_handle(struct sock *sk, void *data);
 static void iso_sock_disconn(struct sock *sk);
 
+typedef bool (*iso_sock_match_t)(struct sock *sk, void *data);
+
+static struct sock *iso_get_sock_listen(bdaddr_t *src, bdaddr_t *dst,
+					iso_sock_match_t match, void *data);
+
 /* ---- ISO timers ---- */
 #define ISO_CONN_TIMEOUT	(HZ * 40)
 #define ISO_DISCONN_TIMEOUT	(HZ * 2)
@@ -190,10 +196,21 @@ static void iso_chan_del(struct sock *sk, int err)
 	sock_set_flag(sk, SOCK_ZAPPED);
 }
 
+static bool iso_match_conn_sync_handle(struct sock *sk, void *data)
+{
+	struct hci_conn *hcon = data;
+
+	if (test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags))
+		return false;
+
+	return hcon->sync_handle == iso_pi(sk)->sync_handle;
+}
+
 static void iso_conn_del(struct hci_conn *hcon, int err)
 {
 	struct iso_conn *conn = hcon->iso_data;
 	struct sock *sk;
+	struct sock *parent;
 
 	if (!conn)
 		return;
@@ -209,6 +226,25 @@ static void iso_conn_del(struct hci_conn *hcon, int err)
 
 	if (sk) {
 		lock_sock(sk);
+
+		/* While a PA sync hcon is in the process of closing,
+		 * mark parent socket with a flag, so that any residual
+		 * BIGInfo adv reports that arrive before PA sync is
+		 * terminated are not processed anymore.
+		 */
+		if (test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags)) {
+			parent = iso_get_sock_listen(&hcon->src,
+						     &hcon->dst,
+						     iso_match_conn_sync_handle,
+						     hcon);
+
+			if (parent) {
+				set_bit(BT_SK_PA_SYNC_TERM,
+					&iso_pi(parent)->flags);
+				sock_put(parent);
+			}
+		}
+
 		iso_sock_clear_timer(sk);
 		iso_chan_del(sk, err);
 		release_sock(sk);
@@ -545,8 +581,6 @@ static struct sock *__iso_get_sock_listen_by_sid(bdaddr_t *ba, bdaddr_t *bc,
 	return NULL;
 }
 
-typedef bool (*iso_sock_match_t)(struct sock *sk, void *data);
-
 /* Find socket listening:
  * source bdaddr (Unicast)
  * destination bdaddr (Broadcast only)
@@ -574,19 +608,68 @@ static struct sock *iso_get_sock_listen(bdaddr_t *src, bdaddr_t *dst,
 			continue;
 
 		/* Exact match. */
-		if (!bacmp(&iso_pi(sk)->src, src))
+		if (!bacmp(&iso_pi(sk)->src, src)) {
+			sock_hold(sk);
 			break;
+		}
 
 		/* Closest match */
-		if (!bacmp(&iso_pi(sk)->src, BDADDR_ANY))
+		if (!bacmp(&iso_pi(sk)->src, BDADDR_ANY)) {
+			if (sk1)
+				sock_put(sk1);
+
 			sk1 = sk;
+			sock_hold(sk1);
+		}
 	}
 
+	if (sk && sk1)
+		sock_put(sk1);
+
 	read_unlock(&iso_sk_list.lock);
 
 	return sk ? sk : sk1;
 }
 
+static struct sock *iso_get_sock_big(struct sock *match_sk, bdaddr_t *src,
+				     bdaddr_t *dst, uint8_t big)
+{
+	struct sock *sk = NULL;
+
+	read_lock(&iso_sk_list.lock);
+
+	sk_for_each(sk, &iso_sk_list.head) {
+		if (match_sk == sk)
+			continue;
+
+		/* Look for sockets that have already been
+		 * connected to the BIG
+		 */
+		if (sk->sk_state != BT_CONNECTED &&
+		    sk->sk_state != BT_CONNECT)
+			continue;
+
+		/* Match Broadcast destination */
+		if (bacmp(&iso_pi(sk)->dst, dst))
+			continue;
+
+		/* Match BIG handle */
+		if (iso_pi(sk)->qos.bcast.big != big)
+			continue;
+
+		/* Match source address */
+		if (bacmp(&iso_pi(sk)->src, src))
+			continue;
+
+		sock_hold(sk);
+		break;
+	}
+
+	read_unlock(&iso_sk_list.lock);
+
+	return sk;
+}
+
 static void iso_sock_destruct(struct sock *sk)
 {
 	BT_DBG("sk %p", sk);
@@ -639,6 +722,28 @@ static void iso_sock_kill(struct sock *sk)
 
 static void iso_sock_disconn(struct sock *sk)
 {
+	struct sock *bis_sk;
+	struct hci_conn *hcon = iso_pi(sk)->conn->hcon;
+
+	if (test_bit(HCI_CONN_BIG_CREATED, &hcon->flags)) {
+		bis_sk = iso_get_sock_big(sk, &iso_pi(sk)->src,
+					  &iso_pi(sk)->dst,
+					  iso_pi(sk)->qos.bcast.big);
+
+		/* If there are any other connected sockets for the
+		 * same BIG, just delete the sk and leave the bis
+		 * hcon active, in case later rebinding is needed.
+		 */
+		if (bis_sk) {
+			hcon->state = BT_OPEN;
+			iso_pi(sk)->conn->hcon = NULL;
+			iso_sock_clear_timer(sk);
+			iso_chan_del(sk, bt_to_errno(hcon->abort_reason));
+			sock_put(bis_sk);
+			return;
+		}
+	}
+
 	sk->sk_state = BT_DISCONN;
 	iso_sock_set_timer(sk, ISO_DISCONN_TIMEOUT);
 	iso_conn_lock(iso_pi(sk)->conn);
@@ -792,27 +897,75 @@ static int iso_sock_bind_bc(struct socket *sock, struct sockaddr *addr,
 	BT_DBG("sk %p bc_sid %u bc_num_bis %u", sk, sa->iso_bc->bc_sid,
 	       sa->iso_bc->bc_num_bis);
 
-	if (addr_len > sizeof(*sa) + sizeof(*sa->iso_bc))
+	if (addr_len != sizeof(*sa) + sizeof(*sa->iso_bc))
 		return -EINVAL;
 
 	bacpy(&iso_pi(sk)->dst, &sa->iso_bc->bc_bdaddr);
+
+	/* Check if the address type is of LE type */
+	if (!bdaddr_type_is_le(sa->iso_bc->bc_bdaddr_type))
+		return -EINVAL;
+
 	iso_pi(sk)->dst_type = sa->iso_bc->bc_bdaddr_type;
 	iso_pi(sk)->sync_handle = -1;
+
+	if (sa->iso_bc->bc_sid > 0x0f)
+		return -EINVAL;
+
 	iso_pi(sk)->bc_sid = sa->iso_bc->bc_sid;
+
+	if (sa->iso_bc->bc_num_bis > ISO_MAX_NUM_BIS)
+		return -EINVAL;
+
 	iso_pi(sk)->bc_num_bis = sa->iso_bc->bc_num_bis;
 
-	for (i = 0; i < iso_pi(sk)->bc_num_bis; i++) {
+	for (i = 0; i < iso_pi(sk)->bc_num_bis; i++)
 		if (sa->iso_bc->bc_bis[i] < 0x01 ||
 		    sa->iso_bc->bc_bis[i] > 0x1f)
 			return -EINVAL;
 
-		memcpy(iso_pi(sk)->bc_bis, sa->iso_bc->bc_bis,
-		       iso_pi(sk)->bc_num_bis);
-	}
+	memcpy(iso_pi(sk)->bc_bis, sa->iso_bc->bc_bis,
+	       iso_pi(sk)->bc_num_bis);
 
 	return 0;
 }
 
+static int iso_sock_bind_pa_sk(struct sock *sk, struct sockaddr_iso *sa,
+			       int addr_len)
+{
+	int err = 0;
+
+	if (sk->sk_type != SOCK_SEQPACKET) {
+		err = -EINVAL;
+		goto done;
+	}
+
+	if (addr_len != sizeof(*sa) + sizeof(*sa->iso_bc)) {
+		err = -EINVAL;
+		goto done;
+	}
+
+	if (sa->iso_bc->bc_num_bis > ISO_MAX_NUM_BIS) {
+		err = -EINVAL;
+		goto done;
+	}
+
+	iso_pi(sk)->bc_num_bis = sa->iso_bc->bc_num_bis;
+
+	for (int i = 0; i < iso_pi(sk)->bc_num_bis; i++)
+		if (sa->iso_bc->bc_bis[i] < 0x01 ||
+		    sa->iso_bc->bc_bis[i] > 0x1f) {
+			err = -EINVAL;
+			goto done;
+		}
+
+	memcpy(iso_pi(sk)->bc_bis, sa->iso_bc->bc_bis,
+	       iso_pi(sk)->bc_num_bis);
+
+done:
+	return err;
+}
+
 static int iso_sock_bind(struct socket *sock, struct sockaddr *addr,
 			 int addr_len)
 {
@@ -828,6 +981,15 @@ static int iso_sock_bind(struct socket *sock, struct sockaddr *addr,
 
 	lock_sock(sk);
 
+	/* Allow the user to bind a PA sync socket to a number
+	 * of BISes to sync to.
+	 */
+	if (sk->sk_state == BT_CONNECT2 &&
+	    test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags)) {
+		err = iso_sock_bind_pa_sk(sk, sa, addr_len);
+		goto done;
+	}
+
 	if (sk->sk_state != BT_OPEN) {
 		err = -EBADFD;
 		goto done;
@@ -1694,6 +1856,7 @@ static void iso_conn_ready(struct iso_conn *conn)
 		parent->sk_data_ready(parent);
 
 		release_sock(parent);
+		sock_put(parent);
 	}
 }
 
@@ -1759,9 +1922,20 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags)
 		/* Try to get PA sync listening socket, if it exists */
 		sk = iso_get_sock_listen(&hdev->bdaddr, bdaddr,
 						iso_match_pa_sync_flag, NULL);
-		if (!sk)
+
+		if (!sk) {
 			sk = iso_get_sock_listen(&hdev->bdaddr, bdaddr,
 						 iso_match_sync_handle, ev2);
+
+			/* If PA Sync is in process of terminating,
+			 * do not handle any more BIGInfo adv reports.
+			 */
+
+			if (sk && test_bit(BT_SK_PA_SYNC_TERM,
+					   &iso_pi(sk)->flags))
+				return lm;
+		}
+
 		if (sk) {
 			int err;
 
@@ -1778,6 +1952,7 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags)
 				if (err) {
 					bt_dev_err(hdev, "hci_le_big_create_sync: %d",
 						   err);
+					sock_put(sk);
 					sk = NULL;
 				}
 			}
@@ -1810,6 +1985,8 @@ done:
 	if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags))
 		*flags |= HCI_PROTO_DEFER;
 
+	sock_put(sk);
+
 	return lm;
 }
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 17ca13e8c044..60298975d5c4 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -6492,6 +6492,14 @@ drop:
 	kfree_skb(skb);
 }
 
+static inline void l2cap_sig_send_rej(struct l2cap_conn *conn, u16 ident)
+{
+	struct l2cap_cmd_rej_unk rej;
+
+	rej.reason = cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD);
+	l2cap_send_cmd(conn, ident, L2CAP_COMMAND_REJ, sizeof(rej), &rej);
+}
+
 static inline void l2cap_sig_channel(struct l2cap_conn *conn,
 				     struct sk_buff *skb)
 {
@@ -6517,23 +6525,25 @@ static inline void l2cap_sig_channel(struct l2cap_conn *conn,
 
 		if (len > skb->len || !cmd->ident) {
 			BT_DBG("corrupted command");
-			break;
+			l2cap_sig_send_rej(conn, cmd->ident);
+			skb_pull(skb, len > skb->len ? skb->len : len);
+			continue;
 		}
 
 		err = l2cap_bredr_sig_cmd(conn, cmd, len, skb->data);
 		if (err) {
-			struct l2cap_cmd_rej_unk rej;
-
 			BT_ERR("Wrong link type (%d)", err);
-
-			rej.reason = cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD);
-			l2cap_send_cmd(conn, cmd->ident, L2CAP_COMMAND_REJ,
-				       sizeof(rej), &rej);
+			l2cap_sig_send_rej(conn, cmd->ident);
 		}
 
 		skb_pull(skb, len);
 	}
 
+	if (skb->len > 0) {
+		BT_DBG("corrupted command");
+		l2cap_sig_send_rej(conn, 0);
+	}
+
 drop:
 	kfree_skb(skb);
 }
diff --git a/net/bluetooth/lib.c b/net/bluetooth/lib.c
index 53a796ac078c..43aa01fd07b9 100644
--- a/net/bluetooth/lib.c
+++ b/net/bluetooth/lib.c
@@ -30,6 +30,15 @@
 
 #include <net/bluetooth/bluetooth.h>
 
+/**
+ * baswap() - Swaps the order of a bd address
+ * @dst: Pointer to a bdaddr_t struct that will store the swapped
+ * 		 bd address.
+ * @src: Pointer to the bdaddr_t struct to be swapped.
+ *
+ * This function reverses the byte order of a Bluetooth device
+ * address.
+ */
 void baswap(bdaddr_t *dst, const bdaddr_t *src)
 {
 	const unsigned char *s = (const unsigned char *)src;
@@ -41,7 +50,19 @@ void baswap(bdaddr_t *dst, const bdaddr_t *src)
 }
 EXPORT_SYMBOL(baswap);
 
-/* Bluetooth error codes to Unix errno mapping */
+/**
+ * bt_to_errno() - Bluetooth error codes to standard errno
+ * @code: Bluetooth error code to be converted
+ *
+ * This function takes a Bluetooth error code as input and convets
+ * it to an equivalent Unix/standard errno value.
+ *
+ * Return:
+ *
+ * If the bt error code is known, an equivalent Unix errno value
+ * is returned.
+ * If the given bt error code is not known, ENOSYS is returned.
+ */
 int bt_to_errno(__u16 code)
 {
 	switch (code) {
@@ -135,10 +156,22 @@ int bt_to_errno(__u16 code)
 }
 EXPORT_SYMBOL(bt_to_errno);
 
-/* Unix errno to Bluetooth error codes mapping */
+/**
+ * bt_status() - Standard errno value to Bluetooth error code
+ * @err: Unix/standard errno value to be converted
+ *
+ * This function converts a standard/Unix errno value to an
+ * equivalent Bluetooth error code.
+ *
+ * Return: Bluetooth error code.
+ *
+ * If the given errno is not found, 0x1f is returned by default
+ * which indicates an unspecified error.
+ * For err >= 0, no conversion is performed, and the same value
+ * is immediately returned.
+ */
 __u8 bt_status(int err)
 {
-	/* Don't convert if already positive value */
 	if (err >= 0)
 		return err;
 
@@ -206,6 +239,10 @@ __u8 bt_status(int err)
 }
 EXPORT_SYMBOL(bt_status);
 
+/**
+ * bt_info() - Log Bluetooth information message
+ * @format: Message's format string
+ */
 void bt_info(const char *format, ...)
 {
 	struct va_format vaf;
@@ -222,6 +259,10 @@ void bt_info(const char *format, ...)
 }
 EXPORT_SYMBOL(bt_info);
 
+/**
+ * bt_warn() - Log Bluetooth warning message
+ * @format: Message's format string
+ */
 void bt_warn(const char *format, ...)
 {
 	struct va_format vaf;
@@ -238,6 +279,10 @@ void bt_warn(const char *format, ...)
 }
 EXPORT_SYMBOL(bt_warn);
 
+/**
+ * bt_err() - Log Bluetooth error message
+ * @format: Message's format string
+ */
 void bt_err(const char *format, ...)
 {
 	struct va_format vaf;
@@ -267,6 +312,10 @@ bool bt_dbg_get(void)
 	return debug_enable;
 }
 
+/**
+ * bt_dbg() - Log Bluetooth debugging message
+ * @format: Message's format string
+ */
 void bt_dbg(const char *format, ...)
 {
 	struct va_format vaf;
@@ -287,6 +336,13 @@ void bt_dbg(const char *format, ...)
 EXPORT_SYMBOL(bt_dbg);
 #endif
 
+/**
+ * bt_warn_ratelimited() - Log rate-limited Bluetooth warning message
+ * @format: Message's format string
+ *
+ * This functions works like bt_warn, but it uses rate limiting
+ * to prevent the message from being logged too often.
+ */
 void bt_warn_ratelimited(const char *format, ...)
 {
 	struct va_format vaf;
@@ -303,6 +359,13 @@ void bt_warn_ratelimited(const char *format, ...)
 }
 EXPORT_SYMBOL(bt_warn_ratelimited);
 
+/**
+ * bt_err_ratelimited() - Log rate-limited Bluetooth error message
+ * @format: Message's format string
+ *
+ * This functions works like bt_err, but it uses rate limiting
+ * to prevent the message from being logged too often.
+ */
 void bt_err_ratelimited(const char *format, ...)
 {
 	struct va_format vaf;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index ba2e00646e8e..bb72ff6eb22f 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2897,7 +2897,8 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data,
 	for (i = 0; i < key_count; i++) {
 		struct mgmt_link_key_info *key = &cp->keys[i];
 
-		if (key->addr.type != BDADDR_BREDR || key->type > 0x08)
+		/* Considering SMP over BREDR/LE, there is no need to check addr_type */
+		if (key->type > 0x08)
 			return mgmt_cmd_status(sk, hdev->id,
 					       MGMT_OP_LOAD_LINK_KEYS,
 					       MGMT_STATUS_INVALID_PARAMS);
@@ -7130,6 +7131,7 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data,
 
 	for (i = 0; i < irk_count; i++) {
 		struct mgmt_irk_info *irk = &cp->irks[i];
+		u8 addr_type = le_addr_type(irk->addr.type);
 
 		if (hci_is_blocked_key(hdev,
 				       HCI_BLOCKED_KEY_TYPE_IRK,
@@ -7139,8 +7141,12 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data,
 			continue;
 		}
 
+		/* When using SMP over BR/EDR, the addr type should be set to BREDR */
+		if (irk->addr.type == BDADDR_BREDR)
+			addr_type = BDADDR_BREDR;
+
 		hci_add_irk(hdev, &irk->addr.bdaddr,
-			    le_addr_type(irk->addr.type), irk->val,
+			    addr_type, irk->val,
 			    BDADDR_ANY);
 	}
 
@@ -7221,6 +7227,7 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 	for (i = 0; i < key_count; i++) {
 		struct mgmt_ltk_info *key = &cp->keys[i];
 		u8 type, authenticated;
+		u8 addr_type = le_addr_type(key->addr.type);
 
 		if (hci_is_blocked_key(hdev,
 				       HCI_BLOCKED_KEY_TYPE_LTK,
@@ -7255,8 +7262,12 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 			continue;
 		}
 
+		/* When using SMP over BR/EDR, the addr type should be set to BREDR */
+		if (key->addr.type == BDADDR_BREDR)
+			addr_type = BDADDR_BREDR;
+
 		hci_add_ltk(hdev, &key->addr.bdaddr,
-			    le_addr_type(key->addr.type), type, authenticated,
+			    addr_type, type, authenticated,
 			    key->val, key->enc_size, key->ediv, key->rand);
 	}
 
@@ -9523,7 +9534,7 @@ void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key,
 
 	ev.store_hint = persistent;
 	bacpy(&ev.key.addr.bdaddr, &key->bdaddr);
-	ev.key.addr.type = BDADDR_BREDR;
+	ev.key.addr.type = link_to_bdaddr(key->link_type, key->bdaddr_type);
 	ev.key.type = key->type;
 	memcpy(ev.key.val, key->val, HCI_LINK_KEY_SIZE);
 	ev.key.pin_len = key->pin_len;
@@ -9574,7 +9585,7 @@ void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent)
 		ev.store_hint = persistent;
 
 	bacpy(&ev.key.addr.bdaddr, &key->bdaddr);
-	ev.key.addr.type = link_to_bdaddr(LE_LINK, key->bdaddr_type);
+	ev.key.addr.type = link_to_bdaddr(key->link_type, key->bdaddr_type);
 	ev.key.type = mgmt_ltk_type(key);
 	ev.key.enc_size = key->enc_size;
 	ev.key.ediv = key->ediv;
@@ -9603,7 +9614,7 @@ void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk, bool persistent)
 
 	bacpy(&ev.rpa, &irk->rpa);
 	bacpy(&ev.irk.addr.bdaddr, &irk->bdaddr);
-	ev.irk.addr.type = link_to_bdaddr(LE_LINK, irk->addr_type);
+	ev.irk.addr.type = link_to_bdaddr(irk->link_type, irk->addr_type);
 	memcpy(ev.irk.val, irk->val, sizeof(irk->val));
 
 	mgmt_event(MGMT_EV_NEW_IRK, hdev, &ev, sizeof(ev), NULL);
@@ -9632,7 +9643,7 @@ void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk,
 		ev.store_hint = persistent;
 
 	bacpy(&ev.key.addr.bdaddr, &csrk->bdaddr);
-	ev.key.addr.type = link_to_bdaddr(LE_LINK, csrk->bdaddr_type);
+	ev.key.addr.type = link_to_bdaddr(csrk->link_type, csrk->bdaddr_type);
 	ev.key.type = csrk->type;
 	memcpy(ev.key.val, csrk->val, sizeof(csrk->val));
 
@@ -10134,21 +10145,6 @@ static bool eir_has_uuids(u8 *eir, u16 eir_len, u16 uuid_count, u8 (*uuids)[16])
 	return false;
 }
 
-static void restart_le_scan(struct hci_dev *hdev)
-{
-	/* If controller is not scanning we are done. */
-	if (!hci_dev_test_flag(hdev, HCI_LE_SCAN))
-		return;
-
-	if (time_after(jiffies + DISCOV_LE_RESTART_DELAY,
-		       hdev->discovery.scan_start +
-		       hdev->discovery.scan_duration))
-		return;
-
-	queue_delayed_work(hdev->req_workqueue, &hdev->le_scan_restart,
-			   DISCOV_LE_RESTART_DELAY);
-}
-
 static bool is_filter_match(struct hci_dev *hdev, s8 rssi, u8 *eir,
 			    u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len)
 {
@@ -10183,8 +10179,6 @@ static bool is_filter_match(struct hci_dev *hdev, s8 rssi, u8 *eir,
 	 * scanning to ensure updated result with updated RSSI values.
 	 */
 	if (test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks)) {
-		restart_le_scan(hdev);
-
 		/* Validate RSSI value against the RSSI threshold once more. */
 		if (hdev->discovery.rssi != HCI_RSSI_INVALID &&
 		    rssi < hdev->discovery.rssi)
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 5f2f97de295e..1e7ea3a4b7ef 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -1059,6 +1059,7 @@ static void smp_notify_keys(struct l2cap_conn *conn)
 	}
 
 	if (smp->remote_irk) {
+		smp->remote_irk->link_type = hcon->type;
 		mgmt_new_irk(hdev, smp->remote_irk, persistent);
 
 		/* Now that user space can be considered to know the
@@ -1078,24 +1079,28 @@ static void smp_notify_keys(struct l2cap_conn *conn)
 	}
 
 	if (smp->csrk) {
+		smp->csrk->link_type = hcon->type;
 		smp->csrk->bdaddr_type = hcon->dst_type;
 		bacpy(&smp->csrk->bdaddr, &hcon->dst);
 		mgmt_new_csrk(hdev, smp->csrk, persistent);
 	}
 
 	if (smp->responder_csrk) {
+		smp->responder_csrk->link_type = hcon->type;
 		smp->responder_csrk->bdaddr_type = hcon->dst_type;
 		bacpy(&smp->responder_csrk->bdaddr, &hcon->dst);
 		mgmt_new_csrk(hdev, smp->responder_csrk, persistent);
 	}
 
 	if (smp->ltk) {
+		smp->ltk->link_type = hcon->type;
 		smp->ltk->bdaddr_type = hcon->dst_type;
 		bacpy(&smp->ltk->bdaddr, &hcon->dst);
 		mgmt_new_ltk(hdev, smp->ltk, persistent);
 	}
 
 	if (smp->responder_ltk) {
+		smp->responder_ltk->link_type = hcon->type;
 		smp->responder_ltk->bdaddr_type = hcon->dst_type;
 		bacpy(&smp->responder_ltk->bdaddr, &hcon->dst);
 		mgmt_new_ltk(hdev, smp->responder_ltk, persistent);
@@ -1115,6 +1120,8 @@ static void smp_notify_keys(struct l2cap_conn *conn)
 		key = hci_add_link_key(hdev, smp->conn->hcon, &hcon->dst,
 				       smp->link_key, type, 0, &persistent);
 		if (key) {
+			key->link_type = hcon->type;
+			key->bdaddr_type = hcon->dst_type;
 			mgmt_new_link_key(hdev, key, persistent);
 
 			/* Don't keep debug keys around if the relevant
diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c
index 5918d1b32e19..8906f7bdf4a9 100644
--- a/net/bpf/bpf_dummy_struct_ops.c
+++ b/net/bpf/bpf_dummy_struct_ops.c
@@ -12,6 +12,11 @@ extern struct bpf_struct_ops bpf_bpf_dummy_ops;
 /* A common type for test_N with return value in bpf_dummy_ops */
 typedef int (*dummy_ops_test_ret_fn)(struct bpf_dummy_ops_state *state, ...);
 
+static int dummy_ops_test_ret_function(struct bpf_dummy_ops_state *state, ...)
+{
+	return 0;
+}
+
 struct bpf_dummy_ops_test_args {
 	u64 args[MAX_BPF_FUNC_ARGS];
 	struct bpf_dummy_ops_state state;
@@ -62,7 +67,7 @@ static int dummy_ops_copy_args(struct bpf_dummy_ops_test_args *args)
 
 static int dummy_ops_call_op(void *image, struct bpf_dummy_ops_test_args *args)
 {
-	dummy_ops_test_ret_fn test = (void *)image;
+	dummy_ops_test_ret_fn test = (void *)image + cfi_get_offset();
 	struct bpf_dummy_ops_state *state = NULL;
 
 	/* state needs to be NULL if args[0] is 0 */
@@ -101,12 +106,11 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 		goto out;
 	}
 
-	image = bpf_jit_alloc_exec(PAGE_SIZE);
+	image = arch_alloc_bpf_trampoline(PAGE_SIZE);
 	if (!image) {
 		err = -ENOMEM;
 		goto out;
 	}
-	set_vm_flush_reset_perms(image);
 
 	link = kzalloc(sizeof(*link), GFP_USER);
 	if (!link) {
@@ -120,11 +124,12 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 	op_idx = prog->expected_attach_type;
 	err = bpf_struct_ops_prepare_trampoline(tlinks, link,
 						&st_ops->func_models[op_idx],
+						&dummy_ops_test_ret_function,
 						image, image + PAGE_SIZE);
 	if (err < 0)
 		goto out;
 
-	set_memory_rox((long)image, 1);
+	arch_protect_bpf_trampoline(image, PAGE_SIZE);
 	prog_ret = dummy_ops_call_op(image, args);
 
 	err = dummy_ops_copy_args(args);
@@ -134,7 +139,7 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 		err = -EFAULT;
 out:
 	kfree(args);
-	bpf_jit_free_exec(image);
+	arch_free_bpf_trampoline(image, PAGE_SIZE);
 	if (link)
 		bpf_link_put(&link->link);
 	kfree(tlinks);
@@ -220,6 +225,28 @@ static void bpf_dummy_unreg(void *kdata)
 {
 }
 
+static int bpf_dummy_test_1(struct bpf_dummy_ops_state *cb)
+{
+	return 0;
+}
+
+static int bpf_dummy_test_2(struct bpf_dummy_ops_state *cb, int a1, unsigned short a2,
+			    char a3, unsigned long a4)
+{
+	return 0;
+}
+
+static int bpf_dummy_test_sleepable(struct bpf_dummy_ops_state *cb)
+{
+	return 0;
+}
+
+static struct bpf_dummy_ops __bpf_bpf_dummy_ops = {
+	.test_1 = bpf_dummy_test_1,
+	.test_2 = bpf_dummy_test_2,
+	.test_sleepable = bpf_dummy_test_sleepable,
+};
+
 struct bpf_struct_ops bpf_bpf_dummy_ops = {
 	.verifier_ops = &bpf_dummy_verifier_ops,
 	.init = bpf_dummy_init,
@@ -228,4 +255,5 @@ struct bpf_struct_ops bpf_bpf_dummy_ops = {
 	.reg = bpf_dummy_reg,
 	.unreg = bpf_dummy_unreg,
 	.name = "bpf_dummy_ops",
+	.cfi_stubs = &__bpf_bpf_dummy_ops,
 };
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index c9fdcc5cdce1..dfd919374017 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -542,7 +542,7 @@ struct bpf_fentry_test_t {
 
 int noinline bpf_fentry_test7(struct bpf_fentry_test_t *arg)
 {
-	asm volatile ("");
+	asm volatile ("": "+r"(arg));
 	return (long)arg;
 }
 
@@ -600,10 +600,21 @@ __bpf_kfunc void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p)
 	refcount_dec(&p->cnt);
 }
 
+__bpf_kfunc void bpf_kfunc_call_test_release_dtor(void *p)
+{
+	bpf_kfunc_call_test_release(p);
+}
+CFI_NOSEAL(bpf_kfunc_call_test_release_dtor);
+
 __bpf_kfunc void bpf_kfunc_call_memb_release(struct prog_test_member *p)
 {
 }
 
+__bpf_kfunc void bpf_kfunc_call_memb_release_dtor(void *p)
+{
+}
+CFI_NOSEAL(bpf_kfunc_call_memb_release_dtor);
+
 __bpf_kfunc_end_defs();
 
 BTF_SET8_START(bpf_test_modify_return_ids)
@@ -1671,9 +1682,9 @@ static const struct btf_kfunc_id_set bpf_prog_test_kfunc_set = {
 
 BTF_ID_LIST(bpf_prog_test_dtor_kfunc_ids)
 BTF_ID(struct, prog_test_ref_kfunc)
-BTF_ID(func, bpf_kfunc_call_test_release)
+BTF_ID(func, bpf_kfunc_call_test_release_dtor)
 BTF_ID(struct, prog_test_member)
-BTF_ID(func, bpf_kfunc_call_memb_release)
+BTF_ID(func, bpf_kfunc_call_memb_release_dtor)
 
 static int __init bpf_prog_test_run_init(void)
 {
diff --git a/net/bpfilter/Kconfig b/net/bpfilter/Kconfig
deleted file mode 100644
index 3d4a21462458..000000000000
--- a/net/bpfilter/Kconfig
+++ /dev/null
@@ -1,23 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-menuconfig BPFILTER
-	bool "BPF based packet filtering framework (BPFILTER)"
-	depends on BPF && INET
-	select USERMODE_DRIVER
-	help
-	  This builds experimental bpfilter framework that is aiming to
-	  provide netfilter compatible functionality via BPF
-
-if BPFILTER
-config BPFILTER_UMH
-	tristate "bpfilter kernel module with user mode helper"
-	depends on CC_CAN_LINK
-	depends on m || CC_CAN_LINK_STATIC
-	default m
-	help
-	  This builds bpfilter kernel module with embedded user mode helper
-
-	  Note: To compile this as built-in, your toolchain must support
-	  building static binaries, since rootfs isn't mounted at the time
-	  when __init functions are called and do_execv won't be able to find
-	  the elf interpreter.
-endif
diff --git a/net/bpfilter/Makefile b/net/bpfilter/Makefile
deleted file mode 100644
index cdac82b8c53a..000000000000
--- a/net/bpfilter/Makefile
+++ /dev/null
@@ -1,20 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile for the Linux BPFILTER layer.
-#
-
-userprogs := bpfilter_umh
-bpfilter_umh-objs := main.o
-userccflags += -I $(srctree)/tools/include/ -I $(srctree)/tools/include/uapi
-
-ifeq ($(CONFIG_BPFILTER_UMH), y)
-# builtin bpfilter_umh should be linked with -static
-# since rootfs isn't mounted at the time of __init
-# function is called and do_execv won't find elf interpreter
-userldflags += -static
-endif
-
-$(obj)/bpfilter_umh_blob.o: $(obj)/bpfilter_umh
-
-obj-$(CONFIG_BPFILTER_UMH) += bpfilter.o
-bpfilter-objs += bpfilter_kern.o bpfilter_umh_blob.o
diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c
deleted file mode 100644
index 97e129e3f31c..000000000000
--- a/net/bpfilter/bpfilter_kern.c
+++ /dev/null
@@ -1,136 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/umh.h>
-#include <linux/bpfilter.h>
-#include <linux/sched.h>
-#include <linux/sched/signal.h>
-#include <linux/fs.h>
-#include <linux/file.h>
-#include "msgfmt.h"
-
-extern char bpfilter_umh_start;
-extern char bpfilter_umh_end;
-
-static void shutdown_umh(void)
-{
-	struct umd_info *info = &bpfilter_ops.info;
-	struct pid *tgid = info->tgid;
-
-	if (tgid) {
-		kill_pid(tgid, SIGKILL, 1);
-		wait_event(tgid->wait_pidfd, thread_group_exited(tgid));
-		umd_cleanup_helper(info);
-	}
-}
-
-static void __stop_umh(void)
-{
-	if (IS_ENABLED(CONFIG_INET))
-		shutdown_umh();
-}
-
-static int bpfilter_send_req(struct mbox_request *req)
-{
-	struct mbox_reply reply;
-	loff_t pos = 0;
-	ssize_t n;
-
-	if (!bpfilter_ops.info.tgid)
-		return -EFAULT;
-	pos = 0;
-	n = kernel_write(bpfilter_ops.info.pipe_to_umh, req, sizeof(*req),
-			   &pos);
-	if (n != sizeof(*req)) {
-		pr_err("write fail %zd\n", n);
-		goto stop;
-	}
-	pos = 0;
-	n = kernel_read(bpfilter_ops.info.pipe_from_umh, &reply, sizeof(reply),
-			&pos);
-	if (n != sizeof(reply)) {
-		pr_err("read fail %zd\n", n);
-		goto stop;
-	}
-	return reply.status;
-stop:
-	__stop_umh();
-	return -EFAULT;
-}
-
-static int bpfilter_process_sockopt(struct sock *sk, int optname,
-				    sockptr_t optval, unsigned int optlen,
-				    bool is_set)
-{
-	struct mbox_request req = {
-		.is_set		= is_set,
-		.pid		= current->pid,
-		.cmd		= optname,
-		.addr		= (uintptr_t)optval.user,
-		.len		= optlen,
-	};
-	if (sockptr_is_kernel(optval)) {
-		pr_err("kernel access not supported\n");
-		return -EFAULT;
-	}
-	return bpfilter_send_req(&req);
-}
-
-static int start_umh(void)
-{
-	struct mbox_request req = { .pid = current->pid };
-	int err;
-
-	/* fork usermode process */
-	err = fork_usermode_driver(&bpfilter_ops.info);
-	if (err)
-		return err;
-	pr_info("Loaded bpfilter_umh pid %d\n", pid_nr(bpfilter_ops.info.tgid));
-
-	/* health check that usermode process started correctly */
-	if (bpfilter_send_req(&req) != 0) {
-		shutdown_umh();
-		return -EFAULT;
-	}
-
-	return 0;
-}
-
-static int __init load_umh(void)
-{
-	int err;
-
-	err = umd_load_blob(&bpfilter_ops.info,
-			    &bpfilter_umh_start,
-			    &bpfilter_umh_end - &bpfilter_umh_start);
-	if (err)
-		return err;
-
-	mutex_lock(&bpfilter_ops.lock);
-	err = start_umh();
-	if (!err && IS_ENABLED(CONFIG_INET)) {
-		bpfilter_ops.sockopt = &bpfilter_process_sockopt;
-		bpfilter_ops.start = &start_umh;
-	}
-	mutex_unlock(&bpfilter_ops.lock);
-	if (err)
-		umd_unload_blob(&bpfilter_ops.info);
-	return err;
-}
-
-static void __exit fini_umh(void)
-{
-	mutex_lock(&bpfilter_ops.lock);
-	if (IS_ENABLED(CONFIG_INET)) {
-		shutdown_umh();
-		bpfilter_ops.start = NULL;
-		bpfilter_ops.sockopt = NULL;
-	}
-	mutex_unlock(&bpfilter_ops.lock);
-
-	umd_unload_blob(&bpfilter_ops.info);
-}
-module_init(load_umh);
-module_exit(fini_umh);
-MODULE_LICENSE("GPL");
diff --git a/net/bpfilter/bpfilter_umh_blob.S b/net/bpfilter/bpfilter_umh_blob.S
deleted file mode 100644
index 40311d10d2f2..000000000000
--- a/net/bpfilter/bpfilter_umh_blob.S
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-	.section .init.rodata, "a"
-	.global bpfilter_umh_start
-bpfilter_umh_start:
-	.incbin "net/bpfilter/bpfilter_umh"
-	.global bpfilter_umh_end
-bpfilter_umh_end:
diff --git a/net/bpfilter/main.c b/net/bpfilter/main.c
deleted file mode 100644
index 291a92546246..000000000000
--- a/net/bpfilter/main.c
+++ /dev/null
@@ -1,64 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#define _GNU_SOURCE
-#include <sys/uio.h>
-#include <errno.h>
-#include <stdio.h>
-#include <sys/socket.h>
-#include <fcntl.h>
-#include <unistd.h>
-#include "../../include/uapi/linux/bpf.h"
-#include <asm/unistd.h>
-#include "msgfmt.h"
-
-FILE *debug_f;
-
-static int handle_get_cmd(struct mbox_request *cmd)
-{
-	switch (cmd->cmd) {
-	case 0:
-		return 0;
-	default:
-		break;
-	}
-	return -ENOPROTOOPT;
-}
-
-static int handle_set_cmd(struct mbox_request *cmd)
-{
-	return -ENOPROTOOPT;
-}
-
-static void loop(void)
-{
-	while (1) {
-		struct mbox_request req;
-		struct mbox_reply reply;
-		int n;
-
-		n = read(0, &req, sizeof(req));
-		if (n != sizeof(req)) {
-			fprintf(debug_f, "invalid request %d\n", n);
-			return;
-		}
-
-		reply.status = req.is_set ?
-			handle_set_cmd(&req) :
-			handle_get_cmd(&req);
-
-		n = write(1, &reply, sizeof(reply));
-		if (n != sizeof(reply)) {
-			fprintf(debug_f, "reply failed %d\n", n);
-			return;
-		}
-	}
-}
-
-int main(void)
-{
-	debug_f = fopen("/dev/kmsg", "w");
-	setvbuf(debug_f, 0, _IOLBF, 0);
-	fprintf(debug_f, "<5>Started bpfilter\n");
-	loop();
-	fclose(debug_f);
-	return 0;
-}
diff --git a/net/bpfilter/msgfmt.h b/net/bpfilter/msgfmt.h
deleted file mode 100644
index 98d121c62945..000000000000
--- a/net/bpfilter/msgfmt.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _NET_BPFILTER_MSGFMT_H
-#define _NET_BPFILTER_MSGFMT_H
-
-struct mbox_request {
-	__u64 addr;
-	__u32 len;
-	__u32 is_set;
-	__u32 cmd;
-	__u32 pid;
-};
-
-struct mbox_reply {
-	__u32 status;
-};
-
-#endif
diff --git a/net/bridge/br_cfm_netlink.c b/net/bridge/br_cfm_netlink.c
index 5c4c369f8536..2faab44652e7 100644
--- a/net/bridge/br_cfm_netlink.c
+++ b/net/bridge/br_cfm_netlink.c
@@ -362,7 +362,7 @@ static int br_cc_ccm_tx_parse(struct net_bridge *br, struct nlattr *attr,
 
 	memset(&tx_info, 0, sizeof(tx_info));
 
-	instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_RDI_INSTANCE]);
+	instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE]);
 	nla_memcpy(&tx_info.dmac.addr,
 		   tb[IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC],
 		   sizeof(tx_info.dmac.addr));
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 8f40de3af154..65cee0ad3c1b 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -471,6 +471,7 @@ static const struct net_device_ops br_netdev_ops = {
 	.ndo_fdb_get		 = br_fdb_get,
 	.ndo_mdb_add		 = br_mdb_add,
 	.ndo_mdb_del		 = br_mdb_del,
+	.ndo_mdb_del_bulk	 = br_mdb_del_bulk,
 	.ndo_mdb_dump		 = br_mdb_dump,
 	.ndo_mdb_get		 = br_mdb_get,
 	.ndo_bridge_getlink	 = br_getlink,
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 8cc526067bc2..bc37e47ad829 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -1412,6 +1412,139 @@ int br_mdb_del(struct net_device *dev, struct nlattr *tb[],
 	return err;
 }
 
+struct br_mdb_flush_desc {
+	u32 port_ifindex;
+	u16 vid;
+	u8 rt_protocol;
+	u8 state;
+	u8 state_mask;
+};
+
+static const struct nla_policy br_mdbe_attrs_del_bulk_pol[MDBE_ATTR_MAX + 1] = {
+	[MDBE_ATTR_RTPROT] = NLA_POLICY_MIN(NLA_U8, RTPROT_STATIC),
+	[MDBE_ATTR_STATE_MASK] = NLA_POLICY_MASK(NLA_U8, MDB_PERMANENT),
+};
+
+static int br_mdb_flush_desc_init(struct br_mdb_flush_desc *desc,
+				  struct nlattr *tb[],
+				  struct netlink_ext_ack *extack)
+{
+	struct br_mdb_entry *entry = nla_data(tb[MDBA_SET_ENTRY]);
+	struct nlattr *mdbe_attrs[MDBE_ATTR_MAX + 1];
+	int err;
+
+	desc->port_ifindex = entry->ifindex;
+	desc->vid = entry->vid;
+	desc->state = entry->state;
+
+	if (!tb[MDBA_SET_ENTRY_ATTRS])
+		return 0;
+
+	err = nla_parse_nested(mdbe_attrs, MDBE_ATTR_MAX,
+			       tb[MDBA_SET_ENTRY_ATTRS],
+			       br_mdbe_attrs_del_bulk_pol, extack);
+	if (err)
+		return err;
+
+	if (mdbe_attrs[MDBE_ATTR_STATE_MASK])
+		desc->state_mask = nla_get_u8(mdbe_attrs[MDBE_ATTR_STATE_MASK]);
+
+	if (mdbe_attrs[MDBE_ATTR_RTPROT])
+		desc->rt_protocol = nla_get_u8(mdbe_attrs[MDBE_ATTR_RTPROT]);
+
+	return 0;
+}
+
+static void br_mdb_flush_host(struct net_bridge *br,
+			      struct net_bridge_mdb_entry *mp,
+			      const struct br_mdb_flush_desc *desc)
+{
+	u8 state;
+
+	if (desc->port_ifindex && desc->port_ifindex != br->dev->ifindex)
+		return;
+
+	if (desc->rt_protocol)
+		return;
+
+	state = br_group_is_l2(&mp->addr) ? MDB_PERMANENT : 0;
+	if (desc->state_mask && (state & desc->state_mask) != desc->state)
+		return;
+
+	br_multicast_host_leave(mp, true);
+	if (!mp->ports && netif_running(br->dev))
+		mod_timer(&mp->timer, jiffies);
+}
+
+static void br_mdb_flush_pgs(struct net_bridge *br,
+			     struct net_bridge_mdb_entry *mp,
+			     const struct br_mdb_flush_desc *desc)
+{
+	struct net_bridge_port_group __rcu **pp;
+	struct net_bridge_port_group *p;
+
+	for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL;) {
+		u8 state;
+
+		if (desc->port_ifindex &&
+		    desc->port_ifindex != p->key.port->dev->ifindex) {
+			pp = &p->next;
+			continue;
+		}
+
+		if (desc->rt_protocol && desc->rt_protocol != p->rt_protocol) {
+			pp = &p->next;
+			continue;
+		}
+
+		state = p->flags & MDB_PG_FLAGS_PERMANENT ? MDB_PERMANENT : 0;
+		if (desc->state_mask &&
+		    (state & desc->state_mask) != desc->state) {
+			pp = &p->next;
+			continue;
+		}
+
+		br_multicast_del_pg(mp, p, pp);
+	}
+}
+
+static void br_mdb_flush(struct net_bridge *br,
+			 const struct br_mdb_flush_desc *desc)
+{
+	struct net_bridge_mdb_entry *mp;
+
+	spin_lock_bh(&br->multicast_lock);
+
+	/* Safe variant is not needed because entries are removed from the list
+	 * upon group timer expiration or bridge deletion.
+	 */
+	hlist_for_each_entry(mp, &br->mdb_list, mdb_node) {
+		if (desc->vid && desc->vid != mp->addr.vid)
+			continue;
+
+		br_mdb_flush_host(br, mp, desc);
+		br_mdb_flush_pgs(br, mp, desc);
+	}
+
+	spin_unlock_bh(&br->multicast_lock);
+}
+
+int br_mdb_del_bulk(struct net_device *dev, struct nlattr *tb[],
+		    struct netlink_ext_ack *extack)
+{
+	struct net_bridge *br = netdev_priv(dev);
+	struct br_mdb_flush_desc desc = {};
+	int err;
+
+	err = br_mdb_flush_desc_init(&desc, tb, extack);
+	if (err)
+		return err;
+
+	br_mdb_flush(br, &desc);
+
+	return 0;
+}
+
 static const struct nla_policy br_mdbe_attrs_get_pol[MDBE_ATTR_MAX + 1] = {
 	[MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY,
 					      sizeof(struct in_addr),
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 6b7f36769d03..b0a92c344722 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -186,6 +186,7 @@ enum {
  * struct net_bridge_vlan - per-vlan entry
  *
  * @vnode: rhashtable member
+ * @tnode: rhashtable member
  * @vid: VLAN id
  * @flags: bridge vlan flags
  * @priv_flags: private (in-kernel) bridge vlan flags
@@ -196,6 +197,7 @@ enum {
  * @refcnt: if MASTER flag set, this is bumped for each port referencing it
  * @brvlan: if MASTER flag unset, this points to the global per-VLAN context
  *          for this VLAN entry
+ * @tinfo: bridge tunnel info
  * @br_mcast_ctx: if MASTER flag set, this is the global vlan multicast context
  * @port_mcast_ctx: if MASTER flag unset, this is the per-port/vlan multicast
  *                  context
@@ -1020,6 +1022,8 @@ int br_mdb_add(struct net_device *dev, struct nlattr *tb[], u16 nlmsg_flags,
 	       struct netlink_ext_ack *extack);
 int br_mdb_del(struct net_device *dev, struct nlattr *tb[],
 	       struct netlink_ext_ack *extack);
+int br_mdb_del_bulk(struct net_device *dev, struct nlattr *tb[],
+		    struct netlink_ext_ack *extack);
 int br_mdb_dump(struct net_device *dev, struct sk_buff *skb,
 		struct netlink_callback *cb);
 int br_mdb_get(struct net_device *dev, struct nlattr *tb[], u32 portid, u32 seq,
@@ -1428,6 +1432,12 @@ static inline int br_mdb_del(struct net_device *dev, struct nlattr *tb[],
 	return -EOPNOTSUPP;
 }
 
+static inline int br_mdb_del_bulk(struct net_device *dev, struct nlattr *tb[],
+				  struct netlink_ext_ack *extack)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline int br_mdb_dump(struct net_device *dev, struct sk_buff *skb,
 			      struct netlink_callback *cb)
 {
diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index b5c406a6e765..abb090f94ed2 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -37,7 +37,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk,
 	ktime_t tstamp = skb->tstamp;
 	struct ip_frag_state state;
 	struct iphdr *iph;
-	int err;
+	int err = 0;
 
 	/* for offloaded checksums cleanup checksum before fragmentation */
 	if (skb->ip_summed == CHECKSUM_PARTIAL &&
diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c
index 6a0cba4fc29f..24e85c5487ef 100644
--- a/net/caif/caif_dev.c
+++ b/net/caif/caif_dev.c
@@ -27,6 +27,7 @@
 #include <net/caif/cfcnfg.h>
 #include <net/caif/cfserl.h>
 
+MODULE_DESCRIPTION("ST-Ericsson CAIF modem protocol support");
 MODULE_LICENSE("GPL");
 
 /* Used for local tracking of the CAIF net devices */
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 9c82698da4f5..039dfbd367c9 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -27,6 +27,7 @@
 #include <net/caif/caif_dev.h>
 #include <net/caif/cfpkt.h>
 
+MODULE_DESCRIPTION("ST-Ericsson CAIF modem protocol socket support (AF_CAIF)");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_NETPROTO(AF_CAIF);
 
diff --git a/net/caif/caif_usb.c b/net/caif/caif_usb.c
index bf61ea4b8132..5dc05a1e3178 100644
--- a/net/caif/caif_usb.c
+++ b/net/caif/caif_usb.c
@@ -20,6 +20,7 @@
 #include <net/caif/cfpkt.h>
 #include <net/caif/cfcnfg.h>
 
+MODULE_DESCRIPTION("ST-Ericsson CAIF modem protocol USB support");
 MODULE_LICENSE("GPL");
 
 #define CFUSB_PAD_DESCR_SZ 1	/* Alignment descriptor length */
diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index f35fc87c453a..47901bd4def1 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -31,6 +31,7 @@
 /*This list is protected by the rtnl lock. */
 static LIST_HEAD(chnl_net_list);
 
+MODULE_DESCRIPTION("ST-Ericsson CAIF modem protocol GPRS network device");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_RTNL_LINK("caif");
 
diff --git a/net/compat.c b/net/compat.c
index 6564720f32b7..485db8ee9b28 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -297,7 +297,7 @@ void scm_detach_fds_compat(struct msghdr *msg, struct scm_cookie *scm)
 	int err = 0, i;
 
 	for (i = 0; i < fdmax; i++) {
-		err = receive_fd_user(scm->fp->fp[i], cmsg_data + i, o_flags);
+		err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags);
 		if (err < 0)
 			break;
 	}
diff --git a/net/core/Makefile b/net/core/Makefile
index 0cb734cbc24b..821aec06abf1 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -18,7 +18,7 @@ obj-y		     += dev.o dev_addr_lists.o dst.o netevent.o \
 obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o
 
 obj-y += net-sysfs.o
-obj-$(CONFIG_PAGE_POOL) += page_pool.o
+obj-$(CONFIG_PAGE_POOL) += page_pool.o page_pool_user.o
 obj-$(CONFIG_PROC_FS) += net-procfs.o
 obj-$(CONFIG_NET_PKTGEN) += pktgen.o
 obj-$(CONFIG_NETPOLL) += netpoll.o
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index cca7594be92e..6c4d90b24d46 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -275,9 +275,10 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
 static int bpf_sk_storage_charge(struct bpf_local_storage_map *smap,
 				 void *owner, u32 size)
 {
-	int optmem_max = READ_ONCE(sysctl_optmem_max);
 	struct sock *sk = (struct sock *)owner;
+	int optmem_max;
 
+	optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max);
 	/* same check as in sock_kmalloc() */
 	if (size <= optmem_max &&
 	    atomic_read(&sk->sk_omem_alloc) + size < optmem_max) {
diff --git a/net/core/dev.c b/net/core/dev.c
index 0d548431f3fa..f01a9b858347 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -165,7 +165,6 @@ static int netif_rx_internal(struct sk_buff *skb);
 static int call_netdevice_notifiers_extack(unsigned long val,
 					   struct net_device *dev,
 					   struct netlink_ext_ack *extack);
-static struct napi_struct *napi_by_id(unsigned int napi_id);
 
 /*
  * The @dev_base_head list is protected by @dev_base_lock and the rtnl
@@ -1119,7 +1118,9 @@ static int __dev_alloc_name(struct net *net, const char *name, char *res)
 	if (i == max_netdevices)
 		return -ENFILE;
 
-	snprintf(res, IFNAMSIZ, name, i);
+	/* 'res' and 'name' could overlap, use 'buf' as an intermediate buffer */
+	strscpy(buf, name, IFNAMSIZ);
+	snprintf(res, IFNAMSIZ, buf, i);
 	return i;
 }
 
@@ -3470,6 +3471,9 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb,
 	if (gso_segs > READ_ONCE(dev->gso_max_segs))
 		return features & ~NETIF_F_GSO_MASK;
 
+	if (unlikely(skb->len >= READ_ONCE(dev->gso_max_size)))
+		return features & ~NETIF_F_GSO_MASK;
+
 	if (!skb_shinfo(skb)->gso_type) {
 		skb_warn_bad_offload(skb);
 		return features & ~NETIF_F_GSO_MASK;
@@ -3752,6 +3756,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 
 	qdisc_calculate_pkt_len(skb, q);
 
+	tcf_set_drop_reason(skb, SKB_DROP_REASON_QDISC_DROP);
+
 	if (q->flags & TCQ_F_NOLOCK) {
 		if (q->flags & TCQ_F_CAN_BYPASS && nolock_qdisc_is_empty(q) &&
 		    qdisc_run_begin(q)) {
@@ -3781,7 +3787,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 no_lock_out:
 		if (unlikely(to_free))
 			kfree_skb_list_reason(to_free,
-					      SKB_DROP_REASON_QDISC_DROP);
+					      tcf_get_drop_reason(to_free));
 		return rc;
 	}
 
@@ -3836,7 +3842,8 @@ no_lock_out:
 	}
 	spin_unlock(root_lock);
 	if (unlikely(to_free))
-		kfree_skb_list_reason(to_free, SKB_DROP_REASON_QDISC_DROP);
+		kfree_skb_list_reason(to_free,
+				      tcf_get_drop_reason(to_free));
 	if (unlikely(contended))
 		spin_unlock(&q->busylock);
 	return rc;
@@ -3922,14 +3929,14 @@ static int tc_run(struct tcx_entry *entry, struct sk_buff *skb,
 
 	tc_skb_cb(skb)->mru = 0;
 	tc_skb_cb(skb)->post_ct = false;
-	res.drop_reason = *drop_reason;
+	tcf_set_drop_reason(skb, *drop_reason);
 
 	mini_qdisc_bstats_cpu_update(miniq, skb);
 	ret = tcf_classify(skb, miniq->block, miniq->filter_list, &res, false);
 	/* Only tcf related quirks below. */
 	switch (ret) {
 	case TC_ACT_SHOT:
-		*drop_reason = res.drop_reason;
+		*drop_reason = tcf_get_drop_reason(skb);
 		mini_qdisc_qstats_cpu_drop(miniq);
 		break;
 	case TC_ACT_OK:
@@ -6137,7 +6144,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 EXPORT_SYMBOL(napi_complete_done);
 
 /* must be called under rcu_read_lock(), as we dont take a reference */
-static struct napi_struct *napi_by_id(unsigned int napi_id)
+struct napi_struct *napi_by_id(unsigned int napi_id)
 {
 	unsigned int hash = napi_id % HASH_SIZE(napi_hash);
 	struct napi_struct *napi;
@@ -6398,6 +6405,43 @@ int dev_set_threaded(struct net_device *dev, bool threaded)
 }
 EXPORT_SYMBOL(dev_set_threaded);
 
+/**
+ * netif_queue_set_napi - Associate queue with the napi
+ * @dev: device to which NAPI and queue belong
+ * @queue_index: Index of queue
+ * @type: queue type as RX or TX
+ * @napi: NAPI context, pass NULL to clear previously set NAPI
+ *
+ * Set queue with its corresponding napi context. This should be done after
+ * registering the NAPI handler for the queue-vector and the queues have been
+ * mapped to the corresponding interrupt vector.
+ */
+void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index,
+			  enum netdev_queue_type type, struct napi_struct *napi)
+{
+	struct netdev_rx_queue *rxq;
+	struct netdev_queue *txq;
+
+	if (WARN_ON_ONCE(napi && !napi->dev))
+		return;
+	if (dev->reg_state >= NETREG_REGISTERED)
+		ASSERT_RTNL();
+
+	switch (type) {
+	case NETDEV_QUEUE_TYPE_RX:
+		rxq = __netif_get_rx_queue(dev, queue_index);
+		rxq->napi = napi;
+		return;
+	case NETDEV_QUEUE_TYPE_TX:
+		txq = netdev_get_tx_queue(dev, queue_index);
+		txq->napi = napi;
+		return;
+	default:
+		return;
+	}
+}
+EXPORT_SYMBOL(netif_queue_set_napi);
+
 void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
 			   int (*poll)(struct napi_struct *, int), int weight)
 {
@@ -6433,6 +6477,7 @@ void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
 	 */
 	if (dev->threaded && napi_kthread_create(napi))
 		dev->threaded = 0;
+	netif_napi_set_irq(napi, -1);
 }
 EXPORT_SYMBOL(netif_napi_add_weight);
 
@@ -10049,6 +10094,54 @@ void netif_tx_stop_all_queues(struct net_device *dev)
 }
 EXPORT_SYMBOL(netif_tx_stop_all_queues);
 
+static int netdev_do_alloc_pcpu_stats(struct net_device *dev)
+{
+	void __percpu *v;
+
+	/* Drivers implementing ndo_get_peer_dev must support tstat
+	 * accounting, so that skb_do_redirect() can bump the dev's
+	 * RX stats upon network namespace switch.
+	 */
+	if (dev->netdev_ops->ndo_get_peer_dev &&
+	    dev->pcpu_stat_type != NETDEV_PCPU_STAT_TSTATS)
+		return -EOPNOTSUPP;
+
+	switch (dev->pcpu_stat_type) {
+	case NETDEV_PCPU_STAT_NONE:
+		return 0;
+	case NETDEV_PCPU_STAT_LSTATS:
+		v = dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats);
+		break;
+	case NETDEV_PCPU_STAT_TSTATS:
+		v = dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+		break;
+	case NETDEV_PCPU_STAT_DSTATS:
+		v = dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return v ? 0 : -ENOMEM;
+}
+
+static void netdev_do_free_pcpu_stats(struct net_device *dev)
+{
+	switch (dev->pcpu_stat_type) {
+	case NETDEV_PCPU_STAT_NONE:
+		return;
+	case NETDEV_PCPU_STAT_LSTATS:
+		free_percpu(dev->lstats);
+		break;
+	case NETDEV_PCPU_STAT_TSTATS:
+		free_percpu(dev->tstats);
+		break;
+	case NETDEV_PCPU_STAT_DSTATS:
+		free_percpu(dev->dstats);
+		break;
+	}
+}
+
 /**
  * register_netdevice() - register a network device
  * @dev: device to register
@@ -10109,9 +10202,13 @@ int register_netdevice(struct net_device *dev)
 		goto err_uninit;
 	}
 
+	ret = netdev_do_alloc_pcpu_stats(dev);
+	if (ret)
+		goto err_uninit;
+
 	ret = dev_index_reserve(net, dev->ifindex);
 	if (ret < 0)
-		goto err_uninit;
+		goto err_free_pcpu;
 	dev->ifindex = ret;
 
 	/* Transfer changeable features to wanted_features and enable
@@ -10217,6 +10314,8 @@ err_uninit_notify:
 	call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev);
 err_ifindex_release:
 	dev_index_release(net, dev->ifindex);
+err_free_pcpu:
+	netdev_do_free_pcpu_stats(dev);
 err_uninit:
 	if (dev->netdev_ops->ndo_uninit)
 		dev->netdev_ops->ndo_uninit(dev);
@@ -10455,7 +10554,7 @@ void netdev_run_todo(void)
 		write_lock(&dev_base_lock);
 		dev->reg_state = NETREG_UNREGISTERED;
 		write_unlock(&dev_base_lock);
-		linkwatch_forget_dev(dev);
+		linkwatch_sync_dev(dev);
 	}
 
 	while (!list_empty(&list)) {
@@ -10469,6 +10568,7 @@ void netdev_run_todo(void)
 		WARN_ON(rcu_access_pointer(dev->ip_ptr));
 		WARN_ON(rcu_access_pointer(dev->ip6_ptr));
 
+		netdev_do_free_pcpu_stats(dev);
 		if (dev->priv_destructor)
 			dev->priv_destructor(dev);
 		if (dev->needs_free_netdev)
@@ -11179,17 +11279,19 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
 	dev_net_set(dev, net);
 	dev->ifindex = new_ifindex;
 
-	/* Send a netdev-add uevent to the new namespace */
-	kobject_uevent(&dev->dev.kobj, KOBJ_ADD);
-	netdev_adjacent_add_links(dev);
-
 	if (new_name[0]) /* Rename the netdev to prepared name */
 		strscpy(dev->name, new_name, IFNAMSIZ);
 
 	/* Fixup kobjects */
+	dev_set_uevent_suppress(&dev->dev, 1);
 	err = device_rename(&dev->dev, dev->name);
+	dev_set_uevent_suppress(&dev->dev, 0);
 	WARN_ON(err);
 
+	/* Send a netdev-add uevent to the new namespace */
+	kobject_uevent(&dev->dev.kobj, KOBJ_ADD);
+	netdev_adjacent_add_links(dev);
+
 	/* Adapt owner in case owning user namespace of target network
 	 * namespace is different from the original one.
 	 */
@@ -11513,6 +11615,61 @@ static struct pernet_operations __net_initdata default_device_ops = {
 	.exit_batch = default_device_exit_batch,
 };
 
+static void __init net_dev_struct_check(void)
+{
+	/* TX read-mostly hotpath */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, priv_flags);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, netdev_ops);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, header_ops);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, _tx);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, real_num_tx_queues);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_size);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_ipv4_max_size);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_segs);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_partial_features);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, num_tc);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, mtu);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, needed_headroom);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, tc_to_txq);
+#ifdef CONFIG_XPS
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, xps_maps);
+#endif
+#ifdef CONFIG_NETFILTER_EGRESS
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, nf_hooks_egress);
+#endif
+#ifdef CONFIG_NET_XGRESS
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, tcx_egress);
+#endif
+	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_tx, 160);
+
+	/* TXRX read-mostly hotpath */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr);
+	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 30);
+
+	/* RX read-mostly hotpath */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ifindex);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, real_num_rx_queues);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, _rx);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_flush_timeout);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, napi_defer_hard_irqs);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_max_size);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_ipv4_max_size);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, rx_handler);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, rx_handler_data);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, nd_net);
+#ifdef CONFIG_NETPOLL
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, npinfo);
+#endif
+#ifdef CONFIG_NET_XGRESS
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, tcx_ingress);
+#endif
+	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_rx, 104);
+}
+
 /*
  *	Initialize the DEV module. At boot time this walks the device list and
  *	unhooks any devices that fail to initialise (normally hardware not
@@ -11530,6 +11687,8 @@ static int __init net_dev_init(void)
 
 	BUG_ON(!dev_boot_phase);
 
+	net_dev_struct_check();
+
 	if (dev_proc_init())
 		goto out;
 
diff --git a/net/core/dev.h b/net/core/dev.h
index 5aa45f0fd4ae..cf93e188785b 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -30,7 +30,6 @@ int __init dev_proc_init(void);
 #endif
 
 void linkwatch_init_dev(struct net_device *dev);
-void linkwatch_forget_dev(struct net_device *dev);
 void linkwatch_run_queue(void);
 
 void dev_addr_flush(struct net_device *dev);
@@ -145,4 +144,6 @@ void xdp_do_check_flushed(struct napi_struct *napi);
 #else
 static inline void xdp_do_check_flushed(struct napi_struct *napi) { }
 #endif
+
+struct napi_struct *napi_by_id(unsigned int napi_id);
 #endif
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index feeddf95f450..9a66cf5015f2 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -322,9 +322,9 @@ static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr)
  * frames and not forward them), it must set IFF_SEE_ALL_HWTSTAMP_REQUESTS in
  * dev->priv_flags.
  */
-static int dev_set_hwtstamp_phylib(struct net_device *dev,
-				   struct kernel_hwtstamp_config *cfg,
-				   struct netlink_ext_ack *extack)
+int dev_set_hwtstamp_phylib(struct net_device *dev,
+			    struct kernel_hwtstamp_config *cfg,
+			    struct netlink_ext_ack *extack)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 	bool phy_ts = phy_has_hwtstamp(dev->phydev);
@@ -363,6 +363,7 @@ static int dev_set_hwtstamp_phylib(struct net_device *dev,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(dev_set_hwtstamp_phylib);
 
 static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr)
 {
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index aff31cd944c2..b0f221d658be 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -183,7 +183,7 @@ out:
 }
 
 static const struct genl_multicast_group dropmon_mcgrps[] = {
-	{ .name = "events", },
+	{ .name = "events", .flags = GENL_MCAST_CAP_SYS_ADMIN, },
 };
 
 static void send_dm_alert(struct work_struct *work)
@@ -1619,11 +1619,13 @@ static const struct genl_small_ops dropmon_ops[] = {
 		.cmd = NET_DM_CMD_START,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = net_dm_cmd_trace,
+		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = NET_DM_CMD_STOP,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = net_dm_cmd_trace,
+		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = NET_DM_CMD_CONFIG_GET,
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 75282222e0b4..3f933ffcefc3 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -53,7 +53,7 @@ bool fib_rule_matchall(const struct fib_rule *rule)
 EXPORT_SYMBOL_GPL(fib_rule_matchall);
 
 int fib_default_rule_add(struct fib_rules_ops *ops,
-			 u32 pref, u32 table, u32 flags)
+			 u32 pref, u32 table)
 {
 	struct fib_rule *r;
 
@@ -65,7 +65,6 @@ int fib_default_rule_add(struct fib_rules_ops *ops,
 	r->action = FR_ACT_TO_TBL;
 	r->pref = pref;
 	r->table = table;
-	r->flags = flags;
 	r->proto = RTPROT_KERNEL;
 	r->fr_net = ops->fro_net;
 	r->uid_range = fib_kuid_range_unset;
@@ -594,7 +593,6 @@ static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (tb[FRA_TUN_ID])
 		nlrule->tun_id = nla_get_be64(tb[FRA_TUN_ID]);
 
-	err = -EINVAL;
 	if (tb[FRA_L3MDEV] &&
 	    fib_nl2rule_l3mdev(tb[FRA_L3MDEV], nlrule, extack) < 0)
 		goto errout_free;
diff --git a/net/core/filter.c b/net/core/filter.c
index 383f96b0a1c7..24061f29c9dd 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -81,6 +81,7 @@
 #include <net/xdp.h>
 #include <net/mptcp.h>
 #include <net/netfilter/nf_conntrack_bpf.h>
+#include <net/netkit.h>
 #include <linux/un.h>
 
 #include "dev.h"
@@ -202,7 +203,7 @@ BPF_CALL_3(bpf_skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x)
 		return 0;
 
 	nla = (struct nlattr *) &skb->data[a];
-	if (nla->nla_len > skb->len - a)
+	if (!nla_ok(nla, skb->len - a))
 		return 0;
 
 	nla = nla_find_nested(nla, x);
@@ -1218,8 +1219,8 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
  */
 static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
 {
+	int optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max);
 	u32 filter_size = bpf_prog_size(fp->prog->len);
-	int optmem_max = READ_ONCE(sysctl_optmem_max);
 
 	/* same check as in sock_kmalloc() */
 	if (filter_size <= optmem_max &&
@@ -1549,12 +1550,13 @@ EXPORT_SYMBOL_GPL(sk_attach_filter);
 int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 {
 	struct bpf_prog *prog = __get_filter(fprog, sk);
-	int err;
+	int err, optmem_max;
 
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max))
+	optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max);
+	if (bpf_prog_size(prog->len) > optmem_max)
 		err = -ENOMEM;
 	else
 		err = reuseport_attach_prog(sk, prog);
@@ -1593,7 +1595,7 @@ int sk_attach_bpf(u32 ufd, struct sock *sk)
 int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk)
 {
 	struct bpf_prog *prog;
-	int err;
+	int err, optmem_max;
 
 	if (sock_flag(sk, SOCK_FILTER_LOCKED))
 		return -EPERM;
@@ -1621,7 +1623,8 @@ int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk)
 		}
 	} else {
 		/* BPF_PROG_TYPE_SOCKET_FILTER */
-		if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max)) {
+		optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max);
+		if (bpf_prog_size(prog->len) > optmem_max) {
 			err = -ENOMEM;
 			goto err_prog_put;
 		}
@@ -2468,6 +2471,16 @@ static const struct bpf_func_proto bpf_clone_redirect_proto = {
 DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
 EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info);
 
+static struct net_device *skb_get_peer_dev(struct net_device *dev)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (likely(ops->ndo_get_peer_dev))
+		return INDIRECT_CALL_1(ops->ndo_get_peer_dev,
+				       netkit_peer_dev, dev);
+	return NULL;
+}
+
 int skb_do_redirect(struct sk_buff *skb)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
@@ -2481,17 +2494,15 @@ int skb_do_redirect(struct sk_buff *skb)
 	if (unlikely(!dev))
 		goto out_drop;
 	if (flags & BPF_F_PEER) {
-		const struct net_device_ops *ops = dev->netdev_ops;
-
-		if (unlikely(!ops->ndo_get_peer_dev ||
-			     !skb_at_tc_ingress(skb)))
+		if (unlikely(!skb_at_tc_ingress(skb)))
 			goto out_drop;
-		dev = ops->ndo_get_peer_dev(dev);
+		dev = skb_get_peer_dev(dev);
 		if (unlikely(!dev ||
 			     !(dev->flags & IFF_UP) ||
 			     net_eq(net, dev_net(dev))))
 			goto out_drop;
 		skb->dev = dev;
+		dev_sw_netstats_rx_add(dev, skb->len);
 		return -EAGAIN;
 	}
 	return flags & BPF_F_NEIGH ?
@@ -2593,6 +2604,22 @@ BPF_CALL_2(bpf_msg_cork_bytes, struct sk_msg *, msg, u32, bytes)
 	return 0;
 }
 
+static void sk_msg_reset_curr(struct sk_msg *msg)
+{
+	u32 i = msg->sg.start;
+	u32 len = 0;
+
+	do {
+		len += sk_msg_elem(msg, i)->length;
+		sk_msg_iter_var_next(i);
+		if (len >= msg->sg.size)
+			break;
+	} while (i != msg->sg.end);
+
+	msg->sg.curr = i;
+	msg->sg.copybreak = 0;
+}
+
 static const struct bpf_func_proto bpf_msg_cork_bytes_proto = {
 	.func           = bpf_msg_cork_bytes,
 	.gpl_only       = false,
@@ -2712,6 +2739,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start,
 		      msg->sg.end - shift + NR_MSG_FRAG_IDS :
 		      msg->sg.end - shift;
 out:
+	sk_msg_reset_curr(msg);
 	msg->data = sg_virt(&msg->sg.data[first_sge]) + start - offset;
 	msg->data_end = msg->data + bytes;
 	return 0;
@@ -2848,6 +2876,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
 		msg->sg.data[new] = rsge;
 	}
 
+	sk_msg_reset_curr(msg);
 	sk_msg_compute_data_pointers(msg);
 	return 0;
 }
@@ -3016,6 +3045,7 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
 
 	sk_mem_uncharge(msg->sk, len - pop);
 	msg->sg.size -= (len - pop);
+	sk_msg_reset_curr(msg);
 	sk_msg_compute_data_pointers(msg);
 	return 0;
 }
@@ -7229,7 +7259,6 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len
 	   struct tcphdr *, th, u32, th_len)
 {
 #ifdef CONFIG_SYN_COOKIES
-	u32 cookie;
 	int ret;
 
 	if (unlikely(!sk || th_len < sizeof(*th)))
@@ -7251,8 +7280,6 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len
 	if (tcp_synq_no_recent_overflow(sk))
 		return -ENOENT;
 
-	cookie = ntohl(th->ack_seq) - 1;
-
 	/* Both struct iphdr and struct ipv6hdr have the version field at the
 	 * same offset so we can cast to the shorter header (struct iphdr).
 	 */
@@ -7261,7 +7288,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len
 		if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk))
 			return -EINVAL;
 
-		ret = __cookie_v4_check((struct iphdr *)iph, th, cookie);
+		ret = __cookie_v4_check((struct iphdr *)iph, th);
 		break;
 
 #if IS_BUILTIN(CONFIG_IPV6)
@@ -7272,7 +7299,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len
 		if (sk->sk_family != AF_INET6)
 			return -EINVAL;
 
-		ret = __cookie_v6_check((struct ipv6hdr *)iph, th, cookie);
+		ret = __cookie_v6_check((struct ipv6hdr *)iph, th);
 		break;
 #endif /* CONFIG_IPV6 */
 
@@ -7725,9 +7752,7 @@ static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv6_proto = {
 BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv4, struct iphdr *, iph,
 	   struct tcphdr *, th)
 {
-	u32 cookie = ntohl(th->ack_seq) - 1;
-
-	if (__cookie_v4_check(iph, th, cookie) > 0)
+	if (__cookie_v4_check(iph, th) > 0)
 		return 0;
 
 	return -EACCES;
@@ -7748,9 +7773,7 @@ BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv6, struct ipv6hdr *, iph,
 	   struct tcphdr *, th)
 {
 #if IS_BUILTIN(CONFIG_IPV6)
-	u32 cookie = ntohl(th->ack_seq) - 1;
-
-	if (__cookie_v6_check(iph, th, cookie) > 0)
+	if (__cookie_v6_check(iph, th) > 0)
 		return 0;
 
 	return -EACCES;
diff --git a/net/core/gso_test.c b/net/core/gso_test.c
index ceb684be4cbf..4c2e77bd12f4 100644
--- a/net/core/gso_test.c
+++ b/net/core/gso_test.c
@@ -180,18 +180,17 @@ static void gso_test_func(struct kunit *test)
 	}
 
 	if (tcase->frag_skbs) {
-		unsigned int total_size = 0, total_true_size = 0, alloc_size = 0;
+		unsigned int total_size = 0, total_true_size = 0;
 		struct sk_buff *frag_skb, *prev = NULL;
 
-		page = alloc_page(GFP_KERNEL);
-		KUNIT_ASSERT_NOT_NULL(test, page);
-		page_ref_add(page, tcase->nr_frag_skbs - 1);
-
 		for (i = 0; i < tcase->nr_frag_skbs; i++) {
 			unsigned int frag_size;
 
+			page = alloc_page(GFP_KERNEL);
+			KUNIT_ASSERT_NOT_NULL(test, page);
+
 			frag_size = tcase->frag_skbs[i];
-			frag_skb = build_skb(page_address(page) + alloc_size,
+			frag_skb = build_skb(page_address(page),
 					     frag_size + shinfo_size);
 			KUNIT_ASSERT_NOT_NULL(test, frag_skb);
 			__skb_put(frag_skb, frag_size);
@@ -204,11 +203,8 @@ static void gso_test_func(struct kunit *test)
 
 			total_size += frag_size;
 			total_true_size += frag_skb->truesize;
-			alloc_size += frag_size + shinfo_size;
 		}
 
-		KUNIT_ASSERT_LE(test, alloc_size, PAGE_SIZE);
-
 		skb->len += total_size;
 		skb->data_len += total_size;
 		skb->truesize += total_true_size;
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index c469d1c4db5d..429571c258da 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -192,7 +192,10 @@ static void __linkwatch_run_queue(int urgent_only)
 #define MAX_DO_DEV_PER_LOOP	100
 
 	int do_dev = MAX_DO_DEV_PER_LOOP;
-	struct net_device *dev;
+	/* Use a local list here since we add non-urgent
+	 * events back to the global one when called with
+	 * urgent_only=1.
+	 */
 	LIST_HEAD(wrk);
 
 	/* Give urgent case more budget */
@@ -218,6 +221,7 @@ static void __linkwatch_run_queue(int urgent_only)
 	list_splice_init(&lweventlist, &wrk);
 
 	while (!list_empty(&wrk) && do_dev > 0) {
+		struct net_device *dev;
 
 		dev = list_first_entry(&wrk, struct net_device, link_watch_list);
 		list_del_init(&dev->link_watch_list);
@@ -245,7 +249,7 @@ static void __linkwatch_run_queue(int urgent_only)
 	spin_unlock_irq(&lweventlist_lock);
 }
 
-void linkwatch_forget_dev(struct net_device *dev)
+void linkwatch_sync_dev(struct net_device *dev)
 {
 	unsigned long flags;
 	int clean = 0;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index df81c1f0a570..552719c3bbc3 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -253,9 +253,11 @@ static int neigh_forced_gc(struct neigh_table *tbl)
 {
 	int max_clean = atomic_read(&tbl->gc_entries) -
 			READ_ONCE(tbl->gc_thresh2);
+	u64 tmax = ktime_get_ns() + NSEC_PER_MSEC;
 	unsigned long tref = jiffies - 5 * HZ;
 	struct neighbour *n, *tmp;
 	int shrunk = 0;
+	int loop = 0;
 
 	NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs);
 
@@ -278,11 +280,16 @@ static int neigh_forced_gc(struct neigh_table *tbl)
 				shrunk++;
 			if (shrunk >= max_clean)
 				break;
+			if (++loop == 16) {
+				if (ktime_get_ns() > tmax)
+					goto unlock;
+				loop = 0;
+			}
 		}
 	}
 
 	WRITE_ONCE(tbl->last_flush, jiffies);
-
+unlock:
 	write_unlock_bh(&tbl->lock);
 
 	return shrunk;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index fccaa5bac0ed..a09d507c5b03 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -193,11 +193,22 @@ static ssize_t carrier_show(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
 	struct net_device *netdev = to_net_dev(dev);
+	int ret = -EINVAL;
 
-	if (netif_running(netdev))
-		return sysfs_emit(buf, fmt_dec, !!netif_carrier_ok(netdev));
+	if (!rtnl_trylock())
+		return restart_syscall();
 
-	return -EINVAL;
+	if (netif_running(netdev)) {
+		/* Synchronize carrier state with link watch,
+		 * see also rtnl_getlink().
+		 */
+		linkwatch_sync_dev(netdev);
+
+		ret = sysfs_emit(buf, fmt_dec, !!netif_carrier_ok(netdev));
+	}
+	rtnl_unlock();
+
+	return ret;
 }
 static DEVICE_ATTR_RW(carrier);
 
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index f4183c4c1ec8..72799533426b 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -372,6 +372,10 @@ out_undo:
 static int __net_init net_defaults_init_net(struct net *net)
 {
 	net->core.sysctl_somaxconn = SOMAXCONN;
+	/* Limits per socket sk_omem_alloc usage.
+	 * TCP zerocopy regular usage needs 128 KB.
+	 */
+	net->core.sysctl_optmem_max = 128 * 1024;
 	net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED;
 
 	return 0;
@@ -1099,11 +1103,56 @@ out:
 	rtnl_set_sk_err(net, RTNLGRP_NSID, err);
 }
 
+#ifdef CONFIG_NET_NS
+static void __init netns_ipv4_struct_check(void)
+{
+	/* TX readonly hotpath cache lines */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_early_retrans);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_tso_win_divisor);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_tso_rtt_log);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_autocorking);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_min_snd_mss);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_notsent_lowat);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_limit_output_bytes);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_min_rtt_wlen);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_wmem);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_ip_fwd_use_pmtu);
+	CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_tx, 33);
+
+	/* TXRX readonly hotpath cache lines */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_txrx,
+				      sysctl_tcp_moderate_rcvbuf);
+	CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_txrx, 1);
+
+	/* RX readonly hotpath cache line */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx,
+				      sysctl_ip_early_demux);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx,
+				      sysctl_tcp_early_demux);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx,
+				      sysctl_tcp_reordering);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx,
+				      sysctl_tcp_rmem);
+	CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_rx, 18);
+}
+#endif
+
 void __init net_ns_init(void)
 {
 	struct net_generic *ng;
 
 #ifdef CONFIG_NET_NS
+	netns_ipv4_struct_check();
 	net_cachep = kmem_cache_create("net_namespace", sizeof(struct net),
 					SMP_CACHE_BYTES,
 					SLAB_PANIC|SLAB_ACCOUNT, NULL);
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index ea9231378aa6..be7f2ebd61b2 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -10,11 +10,64 @@
 
 #include <uapi/linux/netdev.h>
 
+/* Integer value ranges */
+static const struct netlink_range_validation netdev_a_page_pool_id_range = {
+	.min	= 1ULL,
+	.max	= 4294967295ULL,
+};
+
+static const struct netlink_range_validation netdev_a_page_pool_ifindex_range = {
+	.min	= 1ULL,
+	.max	= 2147483647ULL,
+};
+
+/* Common nested types */
+const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1] = {
+	[NETDEV_A_PAGE_POOL_ID] = NLA_POLICY_FULL_RANGE(NLA_UINT, &netdev_a_page_pool_id_range),
+	[NETDEV_A_PAGE_POOL_IFINDEX] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_page_pool_ifindex_range),
+};
+
 /* NETDEV_CMD_DEV_GET - do */
 static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1] = {
 	[NETDEV_A_DEV_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
 };
 
+/* NETDEV_CMD_PAGE_POOL_GET - do */
+#ifdef CONFIG_PAGE_POOL
+static const struct nla_policy netdev_page_pool_get_nl_policy[NETDEV_A_PAGE_POOL_ID + 1] = {
+	[NETDEV_A_PAGE_POOL_ID] = NLA_POLICY_FULL_RANGE(NLA_UINT, &netdev_a_page_pool_id_range),
+};
+#endif /* CONFIG_PAGE_POOL */
+
+/* NETDEV_CMD_PAGE_POOL_STATS_GET - do */
+#ifdef CONFIG_PAGE_POOL_STATS
+static const struct nla_policy netdev_page_pool_stats_get_nl_policy[NETDEV_A_PAGE_POOL_STATS_INFO + 1] = {
+	[NETDEV_A_PAGE_POOL_STATS_INFO] = NLA_POLICY_NESTED(netdev_page_pool_info_nl_policy),
+};
+#endif /* CONFIG_PAGE_POOL_STATS */
+
+/* NETDEV_CMD_QUEUE_GET - do */
+static const struct nla_policy netdev_queue_get_do_nl_policy[NETDEV_A_QUEUE_TYPE + 1] = {
+	[NETDEV_A_QUEUE_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
+	[NETDEV_A_QUEUE_TYPE] = NLA_POLICY_MAX(NLA_U32, 1),
+	[NETDEV_A_QUEUE_ID] = { .type = NLA_U32, },
+};
+
+/* NETDEV_CMD_QUEUE_GET - dump */
+static const struct nla_policy netdev_queue_get_dump_nl_policy[NETDEV_A_QUEUE_IFINDEX + 1] = {
+	[NETDEV_A_QUEUE_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
+};
+
+/* NETDEV_CMD_NAPI_GET - do */
+static const struct nla_policy netdev_napi_get_do_nl_policy[NETDEV_A_NAPI_ID + 1] = {
+	[NETDEV_A_NAPI_ID] = { .type = NLA_U32, },
+};
+
+/* NETDEV_CMD_NAPI_GET - dump */
+static const struct nla_policy netdev_napi_get_dump_nl_policy[NETDEV_A_NAPI_IFINDEX + 1] = {
+	[NETDEV_A_NAPI_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
+};
+
 /* Ops table for netdev */
 static const struct genl_split_ops netdev_nl_ops[] = {
 	{
@@ -29,10 +82,67 @@ static const struct genl_split_ops netdev_nl_ops[] = {
 		.dumpit	= netdev_nl_dev_get_dumpit,
 		.flags	= GENL_CMD_CAP_DUMP,
 	},
+#ifdef CONFIG_PAGE_POOL
+	{
+		.cmd		= NETDEV_CMD_PAGE_POOL_GET,
+		.doit		= netdev_nl_page_pool_get_doit,
+		.policy		= netdev_page_pool_get_nl_policy,
+		.maxattr	= NETDEV_A_PAGE_POOL_ID,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd	= NETDEV_CMD_PAGE_POOL_GET,
+		.dumpit	= netdev_nl_page_pool_get_dumpit,
+		.flags	= GENL_CMD_CAP_DUMP,
+	},
+#endif /* CONFIG_PAGE_POOL */
+#ifdef CONFIG_PAGE_POOL_STATS
+	{
+		.cmd		= NETDEV_CMD_PAGE_POOL_STATS_GET,
+		.doit		= netdev_nl_page_pool_stats_get_doit,
+		.policy		= netdev_page_pool_stats_get_nl_policy,
+		.maxattr	= NETDEV_A_PAGE_POOL_STATS_INFO,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd	= NETDEV_CMD_PAGE_POOL_STATS_GET,
+		.dumpit	= netdev_nl_page_pool_stats_get_dumpit,
+		.flags	= GENL_CMD_CAP_DUMP,
+	},
+#endif /* CONFIG_PAGE_POOL_STATS */
+	{
+		.cmd		= NETDEV_CMD_QUEUE_GET,
+		.doit		= netdev_nl_queue_get_doit,
+		.policy		= netdev_queue_get_do_nl_policy,
+		.maxattr	= NETDEV_A_QUEUE_TYPE,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= NETDEV_CMD_QUEUE_GET,
+		.dumpit		= netdev_nl_queue_get_dumpit,
+		.policy		= netdev_queue_get_dump_nl_policy,
+		.maxattr	= NETDEV_A_QUEUE_IFINDEX,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= NETDEV_CMD_NAPI_GET,
+		.doit		= netdev_nl_napi_get_doit,
+		.policy		= netdev_napi_get_do_nl_policy,
+		.maxattr	= NETDEV_A_NAPI_ID,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= NETDEV_CMD_NAPI_GET,
+		.dumpit		= netdev_nl_napi_get_dumpit,
+		.policy		= netdev_napi_get_dump_nl_policy,
+		.maxattr	= NETDEV_A_NAPI_IFINDEX,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
 };
 
 static const struct genl_multicast_group netdev_nl_mcgrps[] = {
 	[NETDEV_NLGRP_MGMT] = { "mgmt", },
+	[NETDEV_NLGRP_PAGE_POOL] = { "page-pool", },
 };
 
 struct genl_family netdev_nl_family __ro_after_init = {
diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h
index 7b370c073e7d..a47f2bcbe4fa 100644
--- a/net/core/netdev-genl-gen.h
+++ b/net/core/netdev-genl-gen.h
@@ -11,11 +11,27 @@
 
 #include <uapi/linux/netdev.h>
 
+/* Common nested types */
+extern const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1];
+
 int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info);
 int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+int netdev_nl_page_pool_get_doit(struct sk_buff *skb, struct genl_info *info);
+int netdev_nl_page_pool_get_dumpit(struct sk_buff *skb,
+				   struct netlink_callback *cb);
+int netdev_nl_page_pool_stats_get_doit(struct sk_buff *skb,
+				       struct genl_info *info);
+int netdev_nl_page_pool_stats_get_dumpit(struct sk_buff *skb,
+					 struct netlink_callback *cb);
+int netdev_nl_queue_get_doit(struct sk_buff *skb, struct genl_info *info);
+int netdev_nl_queue_get_dumpit(struct sk_buff *skb,
+			       struct netlink_callback *cb);
+int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info);
+int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 
 enum {
 	NETDEV_NLGRP_MGMT,
+	NETDEV_NLGRP_PAGE_POOL,
 };
 
 extern struct genl_family netdev_nl_family;
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index fe61f85bcf33..fd98936da3ae 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -6,13 +6,32 @@
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/xdp.h>
+#include <net/xdp_sock.h>
+#include <net/netdev_rx_queue.h>
+#include <net/busy_poll.h>
 
 #include "netdev-genl-gen.h"
+#include "dev.h"
+
+struct netdev_nl_dump_ctx {
+	unsigned long	ifindex;
+	unsigned int	rxq_idx;
+	unsigned int	txq_idx;
+	unsigned int	napi_id;
+};
+
+static struct netdev_nl_dump_ctx *netdev_dump_ctx(struct netlink_callback *cb)
+{
+	NL_ASSERT_DUMP_CTX_FITS(struct netdev_nl_dump_ctx);
+
+	return (struct netdev_nl_dump_ctx *)cb->ctx;
+}
 
 static int
 netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp,
 		   const struct genl_info *info)
 {
+	u64 xsk_features = 0;
 	u64 xdp_rx_meta = 0;
 	void *hdr;
 
@@ -26,11 +45,20 @@ netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp,
 XDP_METADATA_KFUNC_xxx
 #undef XDP_METADATA_KFUNC
 
+	if (netdev->xsk_tx_metadata_ops) {
+		if (netdev->xsk_tx_metadata_ops->tmo_fill_timestamp)
+			xsk_features |= NETDEV_XSK_FLAGS_TX_TIMESTAMP;
+		if (netdev->xsk_tx_metadata_ops->tmo_request_checksum)
+			xsk_features |= NETDEV_XSK_FLAGS_TX_CHECKSUM;
+	}
+
 	if (nla_put_u32(rsp, NETDEV_A_DEV_IFINDEX, netdev->ifindex) ||
 	    nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_FEATURES,
 			      netdev->xdp_features, NETDEV_A_DEV_PAD) ||
 	    nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_RX_METADATA_FEATURES,
-			      xdp_rx_meta, NETDEV_A_DEV_PAD)) {
+			      xdp_rx_meta, NETDEV_A_DEV_PAD) ||
+	    nla_put_u64_64bit(rsp, NETDEV_A_DEV_XSK_FEATURES,
+			      xsk_features, NETDEV_A_DEV_PAD)) {
 		genlmsg_cancel(rsp, hdr);
 		return -EINVAL;
 	}
@@ -111,12 +139,13 @@ err_free_msg:
 
 int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 {
+	struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb);
 	struct net *net = sock_net(skb->sk);
 	struct net_device *netdev;
 	int err = 0;
 
 	rtnl_lock();
-	for_each_netdev_dump(net, netdev, cb->args[0]) {
+	for_each_netdev_dump(net, netdev, ctx->ifindex) {
 		err = netdev_nl_dev_fill(netdev, skb, genl_info_dump(cb));
 		if (err < 0)
 			break;
@@ -129,6 +158,317 @@ int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
+static int
+netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi,
+			const struct genl_info *info)
+{
+	void *hdr;
+	pid_t pid;
+
+	if (WARN_ON_ONCE(!napi->dev))
+		return -EINVAL;
+	if (!(napi->dev->flags & IFF_UP))
+		return 0;
+
+	hdr = genlmsg_iput(rsp, info);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (napi->napi_id >= MIN_NAPI_ID &&
+	    nla_put_u32(rsp, NETDEV_A_NAPI_ID, napi->napi_id))
+		goto nla_put_failure;
+
+	if (nla_put_u32(rsp, NETDEV_A_NAPI_IFINDEX, napi->dev->ifindex))
+		goto nla_put_failure;
+
+	if (napi->irq >= 0 && nla_put_u32(rsp, NETDEV_A_NAPI_IRQ, napi->irq))
+		goto nla_put_failure;
+
+	if (napi->thread) {
+		pid = task_pid_nr(napi->thread);
+		if (nla_put_u32(rsp, NETDEV_A_NAPI_PID, pid))
+			goto nla_put_failure;
+	}
+
+	genlmsg_end(rsp, hdr);
+
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(rsp, hdr);
+	return -EMSGSIZE;
+}
+
+int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct napi_struct *napi;
+	struct sk_buff *rsp;
+	u32 napi_id;
+	int err;
+
+	if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_NAPI_ID))
+		return -EINVAL;
+
+	napi_id = nla_get_u32(info->attrs[NETDEV_A_NAPI_ID]);
+
+	rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!rsp)
+		return -ENOMEM;
+
+	rtnl_lock();
+
+	napi = napi_by_id(napi_id);
+	if (napi)
+		err = netdev_nl_napi_fill_one(rsp, napi, info);
+	else
+		err = -EINVAL;
+
+	rtnl_unlock();
+
+	if (err)
+		goto err_free_msg;
+
+	return genlmsg_reply(rsp, info);
+
+err_free_msg:
+	nlmsg_free(rsp);
+	return err;
+}
+
+static int
+netdev_nl_napi_dump_one(struct net_device *netdev, struct sk_buff *rsp,
+			const struct genl_info *info,
+			struct netdev_nl_dump_ctx *ctx)
+{
+	struct napi_struct *napi;
+	int err = 0;
+
+	if (!(netdev->flags & IFF_UP))
+		return err;
+
+	list_for_each_entry(napi, &netdev->napi_list, dev_list) {
+		if (ctx->napi_id && napi->napi_id >= ctx->napi_id)
+			continue;
+
+		err = netdev_nl_napi_fill_one(rsp, napi, info);
+		if (err)
+			return err;
+		ctx->napi_id = napi->napi_id;
+	}
+	return err;
+}
+
+int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb);
+	const struct genl_info *info = genl_info_dump(cb);
+	struct net *net = sock_net(skb->sk);
+	struct net_device *netdev;
+	u32 ifindex = 0;
+	int err = 0;
+
+	if (info->attrs[NETDEV_A_NAPI_IFINDEX])
+		ifindex = nla_get_u32(info->attrs[NETDEV_A_NAPI_IFINDEX]);
+
+	rtnl_lock();
+	if (ifindex) {
+		netdev = __dev_get_by_index(net, ifindex);
+		if (netdev)
+			err = netdev_nl_napi_dump_one(netdev, skb, info, ctx);
+		else
+			err = -ENODEV;
+	} else {
+		for_each_netdev_dump(net, netdev, ctx->ifindex) {
+			err = netdev_nl_napi_dump_one(netdev, skb, info, ctx);
+			if (err < 0)
+				break;
+			ctx->napi_id = 0;
+		}
+	}
+	rtnl_unlock();
+
+	if (err != -EMSGSIZE)
+		return err;
+
+	return skb->len;
+}
+
+static int
+netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
+			 u32 q_idx, u32 q_type, const struct genl_info *info)
+{
+	struct netdev_rx_queue *rxq;
+	struct netdev_queue *txq;
+	void *hdr;
+
+	hdr = genlmsg_iput(rsp, info);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(rsp, NETDEV_A_QUEUE_ID, q_idx) ||
+	    nla_put_u32(rsp, NETDEV_A_QUEUE_TYPE, q_type) ||
+	    nla_put_u32(rsp, NETDEV_A_QUEUE_IFINDEX, netdev->ifindex))
+		goto nla_put_failure;
+
+	switch (q_type) {
+	case NETDEV_QUEUE_TYPE_RX:
+		rxq = __netif_get_rx_queue(netdev, q_idx);
+		if (rxq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID,
+					     rxq->napi->napi_id))
+			goto nla_put_failure;
+		break;
+	case NETDEV_QUEUE_TYPE_TX:
+		txq = netdev_get_tx_queue(netdev, q_idx);
+		if (txq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID,
+					     txq->napi->napi_id))
+			goto nla_put_failure;
+	}
+
+	genlmsg_end(rsp, hdr);
+
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(rsp, hdr);
+	return -EMSGSIZE;
+}
+
+static int netdev_nl_queue_validate(struct net_device *netdev, u32 q_id,
+				    u32 q_type)
+{
+	switch (q_type) {
+	case NETDEV_QUEUE_TYPE_RX:
+		if (q_id >= netdev->real_num_rx_queues)
+			return -EINVAL;
+		return 0;
+	case NETDEV_QUEUE_TYPE_TX:
+		if (q_id >= netdev->real_num_tx_queues)
+			return -EINVAL;
+	}
+	return 0;
+}
+
+static int
+netdev_nl_queue_fill(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx,
+		     u32 q_type, const struct genl_info *info)
+{
+	int err = 0;
+
+	if (!(netdev->flags & IFF_UP))
+		return err;
+
+	err = netdev_nl_queue_validate(netdev, q_idx, q_type);
+	if (err)
+		return err;
+
+	return netdev_nl_queue_fill_one(rsp, netdev, q_idx, q_type, info);
+}
+
+int netdev_nl_queue_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	u32 q_id, q_type, ifindex;
+	struct net_device *netdev;
+	struct sk_buff *rsp;
+	int err;
+
+	if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_ID) ||
+	    GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_TYPE) ||
+	    GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_IFINDEX))
+		return -EINVAL;
+
+	q_id = nla_get_u32(info->attrs[NETDEV_A_QUEUE_ID]);
+	q_type = nla_get_u32(info->attrs[NETDEV_A_QUEUE_TYPE]);
+	ifindex = nla_get_u32(info->attrs[NETDEV_A_QUEUE_IFINDEX]);
+
+	rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!rsp)
+		return -ENOMEM;
+
+	rtnl_lock();
+
+	netdev = __dev_get_by_index(genl_info_net(info), ifindex);
+	if (netdev)
+		err = netdev_nl_queue_fill(rsp, netdev, q_id, q_type, info);
+	else
+		err = -ENODEV;
+
+	rtnl_unlock();
+
+	if (err)
+		goto err_free_msg;
+
+	return genlmsg_reply(rsp, info);
+
+err_free_msg:
+	nlmsg_free(rsp);
+	return err;
+}
+
+static int
+netdev_nl_queue_dump_one(struct net_device *netdev, struct sk_buff *rsp,
+			 const struct genl_info *info,
+			 struct netdev_nl_dump_ctx *ctx)
+{
+	int err = 0;
+	int i;
+
+	if (!(netdev->flags & IFF_UP))
+		return err;
+
+	for (i = ctx->rxq_idx; i < netdev->real_num_rx_queues;) {
+		err = netdev_nl_queue_fill_one(rsp, netdev, i,
+					       NETDEV_QUEUE_TYPE_RX, info);
+		if (err)
+			return err;
+		ctx->rxq_idx = i++;
+	}
+	for (i = ctx->txq_idx; i < netdev->real_num_tx_queues;) {
+		err = netdev_nl_queue_fill_one(rsp, netdev, i,
+					       NETDEV_QUEUE_TYPE_TX, info);
+		if (err)
+			return err;
+		ctx->txq_idx = i++;
+	}
+
+	return err;
+}
+
+int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb);
+	const struct genl_info *info = genl_info_dump(cb);
+	struct net *net = sock_net(skb->sk);
+	struct net_device *netdev;
+	u32 ifindex = 0;
+	int err = 0;
+
+	if (info->attrs[NETDEV_A_QUEUE_IFINDEX])
+		ifindex = nla_get_u32(info->attrs[NETDEV_A_QUEUE_IFINDEX]);
+
+	rtnl_lock();
+	if (ifindex) {
+		netdev = __dev_get_by_index(net, ifindex);
+		if (netdev)
+			err = netdev_nl_queue_dump_one(netdev, skb, info, ctx);
+		else
+			err = -ENODEV;
+	} else {
+		for_each_netdev_dump(net, netdev, ctx->ifindex) {
+			err = netdev_nl_queue_dump_one(netdev, skb, info, ctx);
+			if (err < 0)
+				break;
+			ctx->rxq_idx = 0;
+			ctx->txq_idx = 0;
+		}
+	}
+	rtnl_unlock();
+
+	if (err != -EMSGSIZE)
+		return err;
+
+	return skb->len;
+}
+
 static int netdev_genl_netdevice_event(struct notifier_block *nb,
 				       unsigned long event, void *ptr)
 {
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index dec544337236..4933762e5a6b 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -23,10 +23,12 @@
 
 #include <trace/events/page_pool.h>
 
+#include "page_pool_priv.h"
+
 #define DEFER_TIME (msecs_to_jiffies(1000))
 #define DEFER_WARN_INTERVAL (60 * HZ)
 
-#define BIAS_MAX	LONG_MAX
+#define BIAS_MAX	(LONG_MAX >> 1)
 
 #ifdef CONFIG_PAGE_POOL_STATS
 /* alloc_stat_inc is intended to be used in softirq context */
@@ -69,7 +71,7 @@ static const char pp_stats[][ETH_GSTRING_LEN] = {
  * is passed to this API which is filled in. The caller can then report
  * those stats to the user (perhaps via ethtool, debugfs, etc.).
  */
-bool page_pool_get_stats(struct page_pool *pool,
+bool page_pool_get_stats(const struct page_pool *pool,
 			 struct page_pool_stats *stats)
 {
 	int cpu = 0;
@@ -173,7 +175,8 @@ static int page_pool_init(struct page_pool *pool,
 {
 	unsigned int ring_qsize = 1024; /* Default */
 
-	memcpy(&pool->p, params, sizeof(pool->p));
+	memcpy(&pool->p, &params->fast, sizeof(pool->p));
+	memcpy(&pool->slow, &params->slow, sizeof(pool->slow));
 
 	/* Validate only known flags were used */
 	if (pool->p.flags & ~(PP_FLAG_ALL))
@@ -211,6 +214,8 @@ static int page_pool_init(struct page_pool *pool,
 		 */
 	}
 
+	pool->has_init_callback = !!pool->slow.init_callback;
+
 #ifdef CONFIG_PAGE_POOL_STATS
 	pool->recycle_stats = alloc_percpu(struct page_pool_recycle_stats);
 	if (!pool->recycle_stats)
@@ -235,6 +240,18 @@ static int page_pool_init(struct page_pool *pool,
 	return 0;
 }
 
+static void page_pool_uninit(struct page_pool *pool)
+{
+	ptr_ring_cleanup(&pool->ring, NULL);
+
+	if (pool->p.flags & PP_FLAG_DMA_MAP)
+		put_device(pool->p.dev);
+
+#ifdef CONFIG_PAGE_POOL_STATS
+	free_percpu(pool->recycle_stats);
+#endif
+}
+
 /**
  * page_pool_create() - create a page pool.
  * @params: parameters, see struct page_pool_params
@@ -249,13 +266,21 @@ struct page_pool *page_pool_create(const struct page_pool_params *params)
 		return ERR_PTR(-ENOMEM);
 
 	err = page_pool_init(pool, params);
-	if (err < 0) {
-		pr_warn("%s() gave up with errno %d\n", __func__, err);
-		kfree(pool);
-		return ERR_PTR(err);
-	}
+	if (err < 0)
+		goto err_free;
+
+	err = page_pool_list(pool);
+	if (err)
+		goto err_uninit;
 
 	return pool;
+
+err_uninit:
+	page_pool_uninit(pool);
+err_free:
+	pr_warn("%s() gave up with errno %d\n", __func__, err);
+	kfree(pool);
+	return ERR_PTR(err);
 }
 EXPORT_SYMBOL(page_pool_create);
 
@@ -388,8 +413,8 @@ static void page_pool_set_pp_info(struct page_pool *pool,
 	 * the overhead is negligible.
 	 */
 	page_pool_fragment_page(page, 1);
-	if (pool->p.init_callback)
-		pool->p.init_callback(page, pool->p.init_arg);
+	if (pool->has_init_callback)
+		pool->slow.init_callback(page, pool->slow.init_arg);
 }
 
 static void page_pool_clear_pp_info(struct page *page)
@@ -504,7 +529,7 @@ EXPORT_SYMBOL(page_pool_alloc_pages);
  */
 #define _distance(a, b)	(s32)((a) - (b))
 
-static s32 page_pool_inflight(struct page_pool *pool)
+s32 page_pool_inflight(const struct page_pool *pool, bool strict)
 {
 	u32 release_cnt = atomic_read(&pool->pages_state_release_cnt);
 	u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt);
@@ -512,27 +537,27 @@ static s32 page_pool_inflight(struct page_pool *pool)
 
 	inflight = _distance(hold_cnt, release_cnt);
 
-	trace_page_pool_release(pool, inflight, hold_cnt, release_cnt);
-	WARN(inflight < 0, "Negative(%d) inflight packet-pages", inflight);
+	if (strict) {
+		trace_page_pool_release(pool, inflight, hold_cnt, release_cnt);
+		WARN(inflight < 0, "Negative(%d) inflight packet-pages",
+		     inflight);
+	} else {
+		inflight = max(0, inflight);
+	}
 
 	return inflight;
 }
 
-/* Disconnects a page (from a page_pool).  API users can have a need
- * to disconnect a page (from a page_pool), to allow it to be used as
- * a regular page (that will eventually be returned to the normal
- * page-allocator via put_page).
- */
-static void page_pool_return_page(struct page_pool *pool, struct page *page)
+static __always_inline
+void __page_pool_release_page_dma(struct page_pool *pool, struct page *page)
 {
 	dma_addr_t dma;
-	int count;
 
 	if (!(pool->p.flags & PP_FLAG_DMA_MAP))
 		/* Always account for inflight pages, even if we didn't
 		 * map them
 		 */
-		goto skip_dma_unmap;
+		return;
 
 	dma = page_pool_get_dma_addr(page);
 
@@ -541,7 +566,19 @@ static void page_pool_return_page(struct page_pool *pool, struct page *page)
 			     PAGE_SIZE << pool->p.order, pool->p.dma_dir,
 			     DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
 	page_pool_set_dma_addr(page, 0);
-skip_dma_unmap:
+}
+
+/* Disconnects a page (from a page_pool).  API users can have a need
+ * to disconnect a page (from a page_pool), to allow it to be used as
+ * a regular page (that will eventually be returned to the normal
+ * page-allocator via put_page).
+ */
+void page_pool_return_page(struct page_pool *pool, struct page *page)
+{
+	int count;
+
+	__page_pool_release_page_dma(pool, page);
+
 	page_pool_clear_pp_info(page);
 
 	/* This may be the last page returned, releasing the pool, so
@@ -647,8 +684,8 @@ __page_pool_put_page(struct page_pool *pool, struct page *page,
 	return NULL;
 }
 
-void page_pool_put_defragged_page(struct page_pool *pool, struct page *page,
-				  unsigned int dma_sync_size, bool allow_direct)
+void page_pool_put_unrefed_page(struct page_pool *pool, struct page *page,
+				unsigned int dma_sync_size, bool allow_direct)
 {
 	page = __page_pool_put_page(pool, page, dma_sync_size, allow_direct);
 	if (page && !page_pool_recycle_in_ring(pool, page)) {
@@ -657,7 +694,7 @@ void page_pool_put_defragged_page(struct page_pool *pool, struct page *page,
 		page_pool_return_page(pool, page);
 	}
 }
-EXPORT_SYMBOL(page_pool_put_defragged_page);
+EXPORT_SYMBOL(page_pool_put_unrefed_page);
 
 /**
  * page_pool_put_page_bulk() - release references on multiple pages
@@ -684,7 +721,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data,
 		struct page *page = virt_to_head_page(data[i]);
 
 		/* It is not the last user for the page frag case */
-		if (!page_pool_is_last_frag(page))
+		if (!page_pool_is_last_ref(page))
 			continue;
 
 		page = __page_pool_put_page(pool, page, -1, false);
@@ -726,7 +763,7 @@ static struct page *page_pool_drain_frag(struct page_pool *pool,
 	long drain_count = BIAS_MAX - pool->frag_users;
 
 	/* Some user is still using the page frag */
-	if (likely(page_pool_defrag_page(page, drain_count)))
+	if (likely(page_pool_unref_page(page, drain_count)))
 		return NULL;
 
 	if (page_ref_count(page) == 1 && !page_is_pfmemalloc(page)) {
@@ -747,7 +784,7 @@ static void page_pool_free_frag(struct page_pool *pool)
 
 	pool->frag_page = NULL;
 
-	if (!page || page_pool_defrag_page(page, drain_count))
+	if (!page || page_pool_unref_page(page, drain_count))
 		return;
 
 	page_pool_return_page(pool, page);
@@ -818,14 +855,8 @@ static void __page_pool_destroy(struct page_pool *pool)
 	if (pool->disconnect)
 		pool->disconnect(pool);
 
-	ptr_ring_cleanup(&pool->ring, NULL);
-
-	if (pool->p.flags & PP_FLAG_DMA_MAP)
-		put_device(pool->p.dev);
-
-#ifdef CONFIG_PAGE_POOL_STATS
-	free_percpu(pool->recycle_stats);
-#endif
+	page_pool_unlist(pool);
+	page_pool_uninit(pool);
 	kfree(pool);
 }
 
@@ -862,7 +893,7 @@ static int page_pool_release(struct page_pool *pool)
 	int inflight;
 
 	page_pool_scrub(pool);
-	inflight = page_pool_inflight(pool);
+	inflight = page_pool_inflight(pool, true);
 	if (!inflight)
 		__page_pool_destroy(pool);
 
@@ -873,18 +904,21 @@ static void page_pool_release_retry(struct work_struct *wq)
 {
 	struct delayed_work *dwq = to_delayed_work(wq);
 	struct page_pool *pool = container_of(dwq, typeof(*pool), release_dw);
+	void *netdev;
 	int inflight;
 
 	inflight = page_pool_release(pool);
 	if (!inflight)
 		return;
 
-	/* Periodic warning */
-	if (time_after_eq(jiffies, pool->defer_warn)) {
+	/* Periodic warning for page pools the user can't see */
+	netdev = READ_ONCE(pool->slow.netdev);
+	if (time_after_eq(jiffies, pool->defer_warn) &&
+	    (!netdev || netdev == NET_PTR_POISON)) {
 		int sec = (s32)((u32)jiffies - (u32)pool->defer_start) / HZ;
 
-		pr_warn("%s() stalled pool shutdown %d inflight %d sec\n",
-			__func__, inflight, sec);
+		pr_warn("%s() stalled pool shutdown: id %u, %d inflight %d sec\n",
+			__func__, pool->user.id, inflight, sec);
 		pool->defer_warn = jiffies + DEFER_WARN_INTERVAL;
 	}
 
@@ -929,6 +963,7 @@ void page_pool_destroy(struct page_pool *pool)
 	if (!page_pool_release(pool))
 		return;
 
+	page_pool_detached(pool);
 	pool->defer_start = jiffies;
 	pool->defer_warn  = jiffies + DEFER_WARN_INTERVAL;
 
diff --git a/net/core/page_pool_priv.h b/net/core/page_pool_priv.h
new file mode 100644
index 000000000000..90665d40f1eb
--- /dev/null
+++ b/net/core/page_pool_priv.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __PAGE_POOL_PRIV_H
+#define __PAGE_POOL_PRIV_H
+
+s32 page_pool_inflight(const struct page_pool *pool, bool strict);
+
+int page_pool_list(struct page_pool *pool);
+void page_pool_detached(struct page_pool *pool);
+void page_pool_unlist(struct page_pool *pool);
+
+#endif
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
new file mode 100644
index 000000000000..ffe5244e5597
--- /dev/null
+++ b/net/core/page_pool_user.c
@@ -0,0 +1,410 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/mutex.h>
+#include <linux/netdevice.h>
+#include <linux/xarray.h>
+#include <net/net_debug.h>
+#include <net/page_pool/types.h>
+#include <net/page_pool/helpers.h>
+#include <net/sock.h>
+
+#include "page_pool_priv.h"
+#include "netdev-genl-gen.h"
+
+static DEFINE_XARRAY_FLAGS(page_pools, XA_FLAGS_ALLOC1);
+/* Protects: page_pools, netdevice->page_pools, pool->slow.netdev, pool->user.
+ * Ordering: inside rtnl_lock
+ */
+static DEFINE_MUTEX(page_pools_lock);
+
+/* Page pools are only reachable from user space (via netlink) if they are
+ * linked to a netdev at creation time. Following page pool "visibility"
+ * states are possible:
+ *  - normal
+ *    - user.list: linked to real netdev, netdev: real netdev
+ *  - orphaned - real netdev has disappeared
+ *    - user.list: linked to lo, netdev: lo
+ *  - invisible - either (a) created without netdev linking, (b) unlisted due
+ *      to error, or (c) the entire namespace which owned this pool disappeared
+ *    - user.list: unhashed, netdev: unknown
+ */
+
+typedef int (*pp_nl_fill_cb)(struct sk_buff *rsp, const struct page_pool *pool,
+			     const struct genl_info *info);
+
+static int
+netdev_nl_page_pool_get_do(struct genl_info *info, u32 id, pp_nl_fill_cb fill)
+{
+	struct page_pool *pool;
+	struct sk_buff *rsp;
+	int err;
+
+	mutex_lock(&page_pools_lock);
+	pool = xa_load(&page_pools, id);
+	if (!pool || hlist_unhashed(&pool->user.list) ||
+	    !net_eq(dev_net(pool->slow.netdev), genl_info_net(info))) {
+		err = -ENOENT;
+		goto err_unlock;
+	}
+
+	rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!rsp) {
+		err = -ENOMEM;
+		goto err_unlock;
+	}
+
+	err = fill(rsp, pool, info);
+	if (err)
+		goto err_free_msg;
+
+	mutex_unlock(&page_pools_lock);
+
+	return genlmsg_reply(rsp, info);
+
+err_free_msg:
+	nlmsg_free(rsp);
+err_unlock:
+	mutex_unlock(&page_pools_lock);
+	return err;
+}
+
+struct page_pool_dump_cb {
+	unsigned long ifindex;
+	u32 pp_id;
+};
+
+static int
+netdev_nl_page_pool_get_dump(struct sk_buff *skb, struct netlink_callback *cb,
+			     pp_nl_fill_cb fill)
+{
+	struct page_pool_dump_cb *state = (void *)cb->ctx;
+	const struct genl_info *info = genl_info_dump(cb);
+	struct net *net = sock_net(skb->sk);
+	struct net_device *netdev;
+	struct page_pool *pool;
+	int err = 0;
+
+	rtnl_lock();
+	mutex_lock(&page_pools_lock);
+	for_each_netdev_dump(net, netdev, state->ifindex) {
+		hlist_for_each_entry(pool, &netdev->page_pools, user.list) {
+			if (state->pp_id && state->pp_id < pool->user.id)
+				continue;
+
+			state->pp_id = pool->user.id;
+			err = fill(skb, pool, info);
+			if (err)
+				break;
+		}
+
+		state->pp_id = 0;
+	}
+	mutex_unlock(&page_pools_lock);
+	rtnl_unlock();
+
+	if (skb->len && err == -EMSGSIZE)
+		return skb->len;
+	return err;
+}
+
+static int
+page_pool_nl_stats_fill(struct sk_buff *rsp, const struct page_pool *pool,
+			const struct genl_info *info)
+{
+#ifdef CONFIG_PAGE_POOL_STATS
+	struct page_pool_stats stats = {};
+	struct nlattr *nest;
+	void *hdr;
+
+	if (!page_pool_get_stats(pool, &stats))
+		return 0;
+
+	hdr = genlmsg_iput(rsp, info);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	nest = nla_nest_start(rsp, NETDEV_A_PAGE_POOL_STATS_INFO);
+
+	if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_ID, pool->user.id) ||
+	    (pool->slow.netdev->ifindex != LOOPBACK_IFINDEX &&
+	     nla_put_u32(rsp, NETDEV_A_PAGE_POOL_IFINDEX,
+			 pool->slow.netdev->ifindex)))
+		goto err_cancel_nest;
+
+	nla_nest_end(rsp, nest);
+
+	if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST,
+			 stats.alloc_stats.fast) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW,
+			 stats.alloc_stats.slow) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER,
+			 stats.alloc_stats.slow_high_order) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY,
+			 stats.alloc_stats.empty) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL,
+			 stats.alloc_stats.refill) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE,
+			 stats.alloc_stats.waive) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED,
+			 stats.recycle_stats.cached) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL,
+			 stats.recycle_stats.cache_full) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING,
+			 stats.recycle_stats.ring) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL,
+			 stats.recycle_stats.ring_full) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT,
+			 stats.recycle_stats.released_refcnt))
+		goto err_cancel_msg;
+
+	genlmsg_end(rsp, hdr);
+
+	return 0;
+err_cancel_nest:
+	nla_nest_cancel(rsp, nest);
+err_cancel_msg:
+	genlmsg_cancel(rsp, hdr);
+	return -EMSGSIZE;
+#else
+	GENL_SET_ERR_MSG(info, "kernel built without CONFIG_PAGE_POOL_STATS");
+	return -EOPNOTSUPP;
+#endif
+}
+
+int netdev_nl_page_pool_stats_get_doit(struct sk_buff *skb,
+				       struct genl_info *info)
+{
+	struct nlattr *tb[ARRAY_SIZE(netdev_page_pool_info_nl_policy)];
+	struct nlattr *nest;
+	int err;
+	u32 id;
+
+	if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_PAGE_POOL_STATS_INFO))
+		return -EINVAL;
+
+	nest = info->attrs[NETDEV_A_PAGE_POOL_STATS_INFO];
+	err = nla_parse_nested(tb, ARRAY_SIZE(tb) - 1, nest,
+			       netdev_page_pool_info_nl_policy,
+			       info->extack);
+	if (err)
+		return err;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, nest, tb, NETDEV_A_PAGE_POOL_ID))
+		return -EINVAL;
+	if (tb[NETDEV_A_PAGE_POOL_IFINDEX]) {
+		NL_SET_ERR_MSG_ATTR(info->extack,
+				    tb[NETDEV_A_PAGE_POOL_IFINDEX],
+				    "selecting by ifindex not supported");
+		return -EINVAL;
+	}
+
+	id = nla_get_uint(tb[NETDEV_A_PAGE_POOL_ID]);
+
+	return netdev_nl_page_pool_get_do(info, id, page_pool_nl_stats_fill);
+}
+
+int netdev_nl_page_pool_stats_get_dumpit(struct sk_buff *skb,
+					 struct netlink_callback *cb)
+{
+	return netdev_nl_page_pool_get_dump(skb, cb, page_pool_nl_stats_fill);
+}
+
+static int
+page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
+		  const struct genl_info *info)
+{
+	size_t inflight, refsz;
+	void *hdr;
+
+	hdr = genlmsg_iput(rsp, info);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_ID, pool->user.id))
+		goto err_cancel;
+
+	if (pool->slow.netdev->ifindex != LOOPBACK_IFINDEX &&
+	    nla_put_u32(rsp, NETDEV_A_PAGE_POOL_IFINDEX,
+			pool->slow.netdev->ifindex))
+		goto err_cancel;
+	if (pool->user.napi_id &&
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, pool->user.napi_id))
+		goto err_cancel;
+
+	inflight = page_pool_inflight(pool, false);
+	refsz =	PAGE_SIZE << pool->p.order;
+	if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_INFLIGHT, inflight) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
+			 inflight * refsz))
+		goto err_cancel;
+	if (pool->user.detach_time &&
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_DETACH_TIME,
+			 pool->user.detach_time))
+		goto err_cancel;
+
+	genlmsg_end(rsp, hdr);
+
+	return 0;
+err_cancel:
+	genlmsg_cancel(rsp, hdr);
+	return -EMSGSIZE;
+}
+
+static void netdev_nl_page_pool_event(const struct page_pool *pool, u32 cmd)
+{
+	struct genl_info info;
+	struct sk_buff *ntf;
+	struct net *net;
+
+	lockdep_assert_held(&page_pools_lock);
+
+	/* 'invisible' page pools don't matter */
+	if (hlist_unhashed(&pool->user.list))
+		return;
+	net = dev_net(pool->slow.netdev);
+
+	if (!genl_has_listeners(&netdev_nl_family, net, NETDEV_NLGRP_PAGE_POOL))
+		return;
+
+	genl_info_init_ntf(&info, &netdev_nl_family, cmd);
+
+	ntf = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!ntf)
+		return;
+
+	if (page_pool_nl_fill(ntf, pool, &info)) {
+		nlmsg_free(ntf);
+		return;
+	}
+
+	genlmsg_multicast_netns(&netdev_nl_family, net, ntf,
+				0, NETDEV_NLGRP_PAGE_POOL, GFP_KERNEL);
+}
+
+int netdev_nl_page_pool_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	u32 id;
+
+	if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_PAGE_POOL_ID))
+		return -EINVAL;
+
+	id = nla_get_uint(info->attrs[NETDEV_A_PAGE_POOL_ID]);
+
+	return netdev_nl_page_pool_get_do(info, id, page_pool_nl_fill);
+}
+
+int netdev_nl_page_pool_get_dumpit(struct sk_buff *skb,
+				   struct netlink_callback *cb)
+{
+	return netdev_nl_page_pool_get_dump(skb, cb, page_pool_nl_fill);
+}
+
+int page_pool_list(struct page_pool *pool)
+{
+	static u32 id_alloc_next;
+	int err;
+
+	mutex_lock(&page_pools_lock);
+	err = xa_alloc_cyclic(&page_pools, &pool->user.id, pool, xa_limit_32b,
+			      &id_alloc_next, GFP_KERNEL);
+	if (err < 0)
+		goto err_unlock;
+
+	INIT_HLIST_NODE(&pool->user.list);
+	if (pool->slow.netdev) {
+		hlist_add_head(&pool->user.list,
+			       &pool->slow.netdev->page_pools);
+		pool->user.napi_id = pool->p.napi ? pool->p.napi->napi_id : 0;
+
+		netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_ADD_NTF);
+	}
+
+	mutex_unlock(&page_pools_lock);
+	return 0;
+
+err_unlock:
+	mutex_unlock(&page_pools_lock);
+	return err;
+}
+
+void page_pool_detached(struct page_pool *pool)
+{
+	mutex_lock(&page_pools_lock);
+	pool->user.detach_time = ktime_get_boottime_seconds();
+	netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_CHANGE_NTF);
+	mutex_unlock(&page_pools_lock);
+}
+
+void page_pool_unlist(struct page_pool *pool)
+{
+	mutex_lock(&page_pools_lock);
+	netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_DEL_NTF);
+	xa_erase(&page_pools, pool->user.id);
+	if (!hlist_unhashed(&pool->user.list))
+		hlist_del(&pool->user.list);
+	mutex_unlock(&page_pools_lock);
+}
+
+static void page_pool_unreg_netdev_wipe(struct net_device *netdev)
+{
+	struct page_pool *pool;
+	struct hlist_node *n;
+
+	mutex_lock(&page_pools_lock);
+	hlist_for_each_entry_safe(pool, n, &netdev->page_pools, user.list) {
+		hlist_del_init(&pool->user.list);
+		pool->slow.netdev = NET_PTR_POISON;
+	}
+	mutex_unlock(&page_pools_lock);
+}
+
+static void page_pool_unreg_netdev(struct net_device *netdev)
+{
+	struct page_pool *pool, *last;
+	struct net_device *lo;
+
+	lo = dev_net(netdev)->loopback_dev;
+
+	mutex_lock(&page_pools_lock);
+	last = NULL;
+	hlist_for_each_entry(pool, &netdev->page_pools, user.list) {
+		pool->slow.netdev = lo;
+		netdev_nl_page_pool_event(pool,
+					  NETDEV_CMD_PAGE_POOL_CHANGE_NTF);
+		last = pool;
+	}
+	if (last)
+		hlist_splice_init(&netdev->page_pools, &last->user.list,
+				  &lo->page_pools);
+	mutex_unlock(&page_pools_lock);
+}
+
+static int
+page_pool_netdevice_event(struct notifier_block *nb,
+			  unsigned long event, void *ptr)
+{
+	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+
+	if (event != NETDEV_UNREGISTER)
+		return NOTIFY_DONE;
+
+	if (hlist_empty(&netdev->page_pools))
+		return NOTIFY_OK;
+
+	if (netdev->ifindex != LOOPBACK_IFINDEX)
+		page_pool_unreg_netdev(netdev);
+	else
+		page_pool_unreg_netdev_wipe(netdev);
+	return NOTIFY_OK;
+}
+
+static struct notifier_block page_pool_netdevice_nb = {
+	.notifier_call = page_pool_netdevice_event,
+};
+
+static int __init page_pool_user_init(void)
+{
+	return register_netdevice_notifier(&page_pool_netdevice_nb);
+}
+
+subsys_initcall(page_pool_user_init);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 57cea67b7562..ea55a758a475 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3669,10 +3669,8 @@ static int pktgen_thread_worker(void *arg)
 		if (unlikely(!pkt_dev && t->control == 0)) {
 			if (t->net->pktgen_exiting)
 				break;
-			wait_event_interruptible_timeout(t->queue,
-							 t->control != 0,
-							 HZ/10);
-			try_to_freeze();
+			wait_event_freezable_timeout(t->queue,
+						     t->control != 0, HZ / 10);
 			continue;
 		}
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e8431c6c8490..5f6ed6da3cfc 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -342,8 +342,7 @@ int rtnl_unregister(int protocol, int msgtype)
 		return -ENOENT;
 	}
 
-	link = rtnl_dereference(tab[msgindex]);
-	RCU_INIT_POINTER(tab[msgindex], NULL);
+	link = rcu_replace_pointer_rtnl(tab[msgindex], NULL);
 	rtnl_unlock();
 
 	kfree_rcu(link, rcu);
@@ -368,18 +367,13 @@ void rtnl_unregister_all(int protocol)
 	BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
 
 	rtnl_lock();
-	tab = rtnl_dereference(rtnl_msg_handlers[protocol]);
+	tab = rcu_replace_pointer_rtnl(rtnl_msg_handlers[protocol], NULL);
 	if (!tab) {
 		rtnl_unlock();
 		return;
 	}
-	RCU_INIT_POINTER(rtnl_msg_handlers[protocol], NULL);
 	for (msgindex = 0; msgindex < RTM_NR_MSGTYPES; msgindex++) {
-		link = rtnl_dereference(tab[msgindex]);
-		if (!link)
-			continue;
-
-		RCU_INIT_POINTER(tab[msgindex], NULL);
+		link = rcu_replace_pointer_rtnl(tab[msgindex], NULL);
 		kfree_rcu(link, rcu);
 	}
 	rtnl_unlock();
@@ -3849,10 +3843,18 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto out;
 
 	err = -ENOBUFS;
-	nskb = nlmsg_new(if_nlmsg_size(dev, ext_filter_mask), GFP_KERNEL);
+	nskb = nlmsg_new_large(if_nlmsg_size(dev, ext_filter_mask));
 	if (nskb == NULL)
 		goto out;
 
+	/* Synchronize the carrier state so we don't report a state
+	 * that we're not actually going to honour immediately; if
+	 * the driver just did a carrier off->on transition, we can
+	 * only TX if link watch work has run, but without this we'd
+	 * already report carrier on, even if it doesn't work yet.
+	 */
+	linkwatch_sync_dev(dev);
+
 	err = rtnl_fill_ifinfo(nskb, dev, net,
 			       RTM_NEWLINK, NETLINK_CB(skb).portid,
 			       nlh->nlmsg_seq, 0, 0, ext_filter_mask,
@@ -6408,17 +6410,64 @@ static int rtnl_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 	return dev->netdev_ops->ndo_mdb_add(dev, tb, nlh->nlmsg_flags, extack);
 }
 
+static int rtnl_validate_mdb_entry_del_bulk(const struct nlattr *attr,
+					    struct netlink_ext_ack *extack)
+{
+	struct br_mdb_entry *entry = nla_data(attr);
+	struct br_mdb_entry zero_entry = {};
+
+	if (nla_len(attr) != sizeof(struct br_mdb_entry)) {
+		NL_SET_ERR_MSG_ATTR(extack, attr, "Invalid attribute length");
+		return -EINVAL;
+	}
+
+	if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY) {
+		NL_SET_ERR_MSG(extack, "Unknown entry state");
+		return -EINVAL;
+	}
+
+	if (entry->flags) {
+		NL_SET_ERR_MSG(extack, "Entry flags cannot be set");
+		return -EINVAL;
+	}
+
+	if (entry->vid >= VLAN_N_VID - 1) {
+		NL_SET_ERR_MSG(extack, "Invalid entry VLAN id");
+		return -EINVAL;
+	}
+
+	if (memcmp(&entry->addr, &zero_entry.addr, sizeof(entry->addr))) {
+		NL_SET_ERR_MSG(extack, "Entry address cannot be set");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct nla_policy mdba_del_bulk_policy[MDBA_SET_ENTRY_MAX + 1] = {
+	[MDBA_SET_ENTRY] = NLA_POLICY_VALIDATE_FN(NLA_BINARY,
+						  rtnl_validate_mdb_entry_del_bulk,
+						  sizeof(struct br_mdb_entry)),
+	[MDBA_SET_ENTRY_ATTRS] = { .type = NLA_NESTED },
+};
+
 static int rtnl_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 			struct netlink_ext_ack *extack)
 {
+	bool del_bulk = !!(nlh->nlmsg_flags & NLM_F_BULK);
 	struct nlattr *tb[MDBA_SET_ENTRY_MAX + 1];
 	struct net *net = sock_net(skb->sk);
 	struct br_port_msg *bpm;
 	struct net_device *dev;
 	int err;
 
-	err = nlmsg_parse_deprecated(nlh, sizeof(*bpm), tb,
-				     MDBA_SET_ENTRY_MAX, mdba_policy, extack);
+	if (!del_bulk)
+		err = nlmsg_parse_deprecated(nlh, sizeof(*bpm), tb,
+					     MDBA_SET_ENTRY_MAX, mdba_policy,
+					     extack);
+	else
+		err = nlmsg_parse(nlh, sizeof(*bpm), tb, MDBA_SET_ENTRY_MAX,
+				  mdba_del_bulk_policy, extack);
 	if (err)
 		return err;
 
@@ -6439,6 +6488,14 @@ static int rtnl_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return -EINVAL;
 	}
 
+	if (del_bulk) {
+		if (!dev->netdev_ops->ndo_mdb_del_bulk) {
+			NL_SET_ERR_MSG(extack, "Device does not support MDB bulk deletion");
+			return -EOPNOTSUPP;
+		}
+		return dev->netdev_ops->ndo_mdb_del_bulk(dev, tb, extack);
+	}
+
 	if (!dev->netdev_ops->ndo_mdb_del) {
 		NL_SET_ERR_MSG(extack, "Device does not support MDB operations");
 		return -EOPNOTSUPP;
@@ -6684,5 +6741,6 @@ void __init rtnetlink_init(void)
 
 	rtnl_register(PF_BRIDGE, RTM_GETMDB, rtnl_mdb_get, rtnl_mdb_dump, 0);
 	rtnl_register(PF_BRIDGE, RTM_NEWMDB, rtnl_mdb_add, NULL, 0);
-	rtnl_register(PF_BRIDGE, RTM_DELMDB, rtnl_mdb_del, NULL, 0);
+	rtnl_register(PF_BRIDGE, RTM_DELMDB, rtnl_mdb_del, NULL,
+		      RTNL_FLAG_BULK_DEL_SUPPORTED);
 }
diff --git a/net/core/scm.c b/net/core/scm.c
index 880027ecf516..d0e0852a24d5 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -26,6 +26,7 @@
 #include <linux/nsproxy.h>
 #include <linux/slab.h>
 #include <linux/errqueue.h>
+#include <linux/io_uring.h>
 
 #include <linux/uaccess.h>
 
@@ -103,6 +104,11 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp)
 
 		if (fd < 0 || !(file = fget_raw(fd)))
 			return -EBADF;
+		/* don't allow io_uring files */
+		if (io_is_uring_fops(file)) {
+			fput(file);
+			return -EINVAL;
+		}
 		*fpp++ = file;
 		fpl->count++;
 	}
@@ -319,7 +325,7 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
 	}
 
 	for (i = 0; i < fdmax; i++) {
-		err = receive_fd_user(scm->fp->fp[i], cmsg_data + i, o_flags);
+		err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags);
 		if (err < 0)
 			break;
 	}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b157efea5dea..edbbef563d4d 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -337,7 +337,7 @@ static struct sk_buff *napi_skb_cache_get(void)
 	}
 
 	skb = nc->skb_cache[--nc->skb_count];
-	kasan_unpoison_object_data(skbuff_cache, skb);
+	kasan_mempool_unpoison_object(skb, kmem_cache_size(skbuff_cache));
 
 	return skb;
 }
@@ -890,6 +890,11 @@ static void skb_clone_fraglist(struct sk_buff *skb)
 		skb_get(list);
 }
 
+static bool is_pp_page(struct page *page)
+{
+	return (page->pp_magic & ~0x3UL) == PP_SIGNATURE;
+}
+
 #if IS_ENABLED(CONFIG_PAGE_POOL)
 bool napi_pp_put_page(struct page *page, bool napi_safe)
 {
@@ -905,7 +910,7 @@ bool napi_pp_put_page(struct page *page, bool napi_safe)
 	 * and page_is_pfmemalloc() is checked in __page_pool_put_page()
 	 * to avoid recycling the pfmemalloc page.
 	 */
-	if (unlikely((page->pp_magic & ~0x3UL) != PP_SIGNATURE))
+	if (unlikely(!is_pp_page(page)))
 		return false;
 
 	pp = page->pp;
@@ -942,6 +947,37 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data, bool napi_safe)
 	return napi_pp_put_page(virt_to_page(data), napi_safe);
 }
 
+/**
+ * skb_pp_frag_ref() - Increase fragment references of a page pool aware skb
+ * @skb:	page pool aware skb
+ *
+ * Increase the fragment reference count (pp_ref_count) of a skb. This is
+ * intended to gain fragment references only for page pool aware skbs,
+ * i.e. when skb->pp_recycle is true, and not for fragments in a
+ * non-pp-recycling skb. It has a fallback to increase references on normal
+ * pages, as page pool aware skbs may also have normal page fragments.
+ */
+static int skb_pp_frag_ref(struct sk_buff *skb)
+{
+	struct skb_shared_info *shinfo;
+	struct page *head_page;
+	int i;
+
+	if (!skb->pp_recycle)
+		return -EINVAL;
+
+	shinfo = skb_shinfo(skb);
+
+	for (i = 0; i < shinfo->nr_frags; i++) {
+		head_page = compound_head(skb_frag_page(&shinfo->frags[i]));
+		if (likely(is_pp_page(head_page)))
+			page_pool_ref_page(head_page);
+		else
+			page_ref_inc(head_page);
+	}
+	return 0;
+}
+
 static void skb_kfree_head(void *head, unsigned int end_offset)
 {
 	if (end_offset == SKB_SMALL_HEAD_HEADROOM)
@@ -1309,13 +1345,15 @@ static void napi_skb_cache_put(struct sk_buff *skb)
 	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
 	u32 i;
 
-	kasan_poison_object_data(skbuff_cache, skb);
+	if (!kasan_mempool_poison_object(skb))
+		return;
+
 	nc->skb_cache[nc->skb_count++] = skb;
 
 	if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) {
 		for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++)
-			kasan_unpoison_object_data(skbuff_cache,
-						   nc->skb_cache[i]);
+			kasan_mempool_unpoison_object(nc->skb_cache[i],
+						kmem_cache_size(skbuff_cache));
 
 		kmem_cache_free_bulk(skbuff_cache, NAPI_SKB_CACHE_HALF,
 				     nc->skb_cache + NAPI_SKB_CACHE_HALF);
@@ -4522,8 +4560,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 		/* GSO partial only requires that we trim off any excess that
 		 * doesn't fit into an MSS sized block, so take care of that
 		 * now.
+		 * Cap len to not accidentally hit GSO_BY_FRAGS.
 		 */
-		partial_segs = len / mss;
+		partial_segs = min(len, GSO_BY_FRAGS - 1) / mss;
 		if (partial_segs > 1)
 			mss *= partial_segs;
 		else
@@ -4824,7 +4863,9 @@ static __always_inline unsigned int skb_ext_total_length(void)
 static void skb_extensions_init(void)
 {
 	BUILD_BUG_ON(SKB_EXT_NUM >= 8);
+#if !IS_ENABLED(CONFIG_KCOV_INSTRUMENT_ALL)
 	BUILD_BUG_ON(skb_ext_total_length() > 255);
+#endif
 
 	skbuff_ext_cache = kmem_cache_create("skbuff_ext_cache",
 					     SKB_EXT_ALIGN_VALUE * skb_ext_total_length(),
@@ -5764,17 +5805,12 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 		return false;
 
 	/* In general, avoid mixing page_pool and non-page_pool allocated
-	 * pages within the same SKB. Additionally avoid dealing with clones
-	 * with page_pool pages, in case the SKB is using page_pool fragment
-	 * references (page_pool_alloc_frag()). Since we only take full page
-	 * references for cloned SKBs at the moment that would result in
-	 * inconsistent reference counts.
-	 * In theory we could take full references if @from is cloned and
-	 * !@to->pp_recycle but its tricky (due to potential race with
-	 * the clone disappearing) and rare, so not worth dealing with.
+	 * pages within the same SKB. In theory we could take full
+	 * references if @from is cloned and !@to->pp_recycle but its
+	 * tricky (due to potential race with the clone disappearing) and
+	 * rare, so not worth dealing with.
 	 */
-	if (to->pp_recycle != from->pp_recycle ||
-	    (from->pp_recycle && skb_cloned(from)))
+	if (to->pp_recycle != from->pp_recycle)
 		return false;
 
 	if (len <= skb_tailroom(to)) {
@@ -5831,8 +5867,10 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 	/* if the skb is not cloned this does nothing
 	 * since we set nr_frags to 0.
 	 */
-	for (i = 0; i < from_shinfo->nr_frags; i++)
-		__skb_frag_ref(&from_shinfo->frags[i]);
+	if (skb_pp_frag_ref(from)) {
+		for (i = 0; i < from_shinfo->nr_frags; i++)
+			__skb_frag_ref(&from_shinfo->frags[i]);
+	}
 
 	to->truesize += delta;
 	to->len += len;
@@ -5959,6 +5997,31 @@ int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len)
 }
 EXPORT_SYMBOL(skb_ensure_writable);
 
+int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev)
+{
+	int needed_headroom = dev->needed_headroom;
+	int needed_tailroom = dev->needed_tailroom;
+
+	/* For tail taggers, we need to pad short frames ourselves, to ensure
+	 * that the tail tag does not fail at its role of being at the end of
+	 * the packet, once the conduit interface pads the frame. Account for
+	 * that pad length here, and pad later.
+	 */
+	if (unlikely(needed_tailroom && skb->len < ETH_ZLEN))
+		needed_tailroom += ETH_ZLEN - skb->len;
+	/* skb_headroom() returns unsigned int... */
+	needed_headroom = max_t(int, needed_headroom - skb_headroom(skb), 0);
+	needed_tailroom = max_t(int, needed_tailroom - skb_tailroom(skb), 0);
+
+	if (likely(!needed_headroom && !needed_tailroom && !skb_cloned(skb)))
+		/* No reallocation needed, yay! */
+		return 0;
+
+	return pskb_expand_head(skb, needed_headroom, needed_tailroom,
+				GFP_ATOMIC);
+}
+EXPORT_SYMBOL(skb_ensure_writable_head_tail);
+
 /* remove VLAN header from packet and update csum accordingly.
  * expects a non skb_vlan_tag_present skb with a vlan tag payload
  */
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 6c31eefbd777..93ecfceac1bc 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -826,6 +826,8 @@ static void sk_psock_destroy(struct work_struct *work)
 
 	if (psock->sk_redir)
 		sock_put(psock->sk_redir);
+	if (psock->sk_pair)
+		sock_put(psock->sk_pair);
 	sock_put(psock->sk);
 	kfree(psock);
 }
diff --git a/net/core/sock.c b/net/core/sock.c
index fef349dd72fa..158dbdebce6a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -283,10 +283,6 @@ EXPORT_SYMBOL(sysctl_rmem_max);
 __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX;
 __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
 
-/* Maximal space eaten by iovec or ancillary data plus some space */
-int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
-EXPORT_SYMBOL(sysctl_optmem_max);
-
 int sysctl_tstamp_allow_data __read_mostly = 1;
 
 DEFINE_STATIC_KEY_FALSE(memalloc_socks_key);
@@ -1711,9 +1707,16 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case SO_TIMESTAMPING_OLD:
+	case SO_TIMESTAMPING_NEW:
 		lv = sizeof(v.timestamping);
-		v.timestamping.flags = READ_ONCE(sk->sk_tsflags);
-		v.timestamping.bind_phc = READ_ONCE(sk->sk_bind_phc);
+		/* For the later-added case SO_TIMESTAMPING_NEW: Be strict about only
+		 * returning the flags when they were set through the same option.
+		 * Don't change the beviour for the old case SO_TIMESTAMPING_OLD.
+		 */
+		if (optname == SO_TIMESTAMPING_OLD || sock_flag(sk, SOCK_TSTAMP_NEW)) {
+			v.timestamping.flags = READ_ONCE(sk->sk_tsflags);
+			v.timestamping.bind_phc = READ_ONCE(sk->sk_bind_phc);
+		}
 		break;
 
 	case SO_RCVTIMEO_OLD:
@@ -2651,7 +2654,7 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
 
 	/* small safe race: SKB_TRUESIZE may differ from final skb->truesize */
 	if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) >
-	    READ_ONCE(sysctl_optmem_max))
+	    READ_ONCE(sock_net(sk)->core.sysctl_optmem_max))
 		return NULL;
 
 	skb = alloc_skb(size, priority);
@@ -2669,7 +2672,7 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
  */
 void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
 {
-	int optmem_max = READ_ONCE(sysctl_optmem_max);
+	int optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max);
 
 	if ((unsigned int)size <= optmem_max &&
 	    atomic_read(&sk->sk_omem_alloc) + size < optmem_max) {
@@ -2806,6 +2809,7 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
 		sockc->mark = *(u32 *)CMSG_DATA(cmsg);
 		break;
 	case SO_TIMESTAMPING_OLD:
+	case SO_TIMESTAMPING_NEW:
 		if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
 			return -EINVAL;
 
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 4292c2ed1828..27d733c0f65e 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -536,6 +536,8 @@ static bool sock_map_sk_state_allowed(const struct sock *sk)
 {
 	if (sk_is_tcp(sk))
 		return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN);
+	if (sk_is_stream_unix(sk))
+		return (1 << sk->sk_state) & TCPF_ESTABLISHED;
 	return true;
 }
 
diff --git a/net/core/stream.c b/net/core/stream.c
index 96fbcb9bbb30..b16dfa568a2d 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -79,7 +79,7 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p)
 		remove_wait_queue(sk_sleep(sk), &wait);
 		sk->sk_write_pending--;
 	} while (!done);
-	return 0;
+	return done < 0 ? done : 0;
 }
 EXPORT_SYMBOL(sk_stream_wait_connect);
 
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 03f1edb948d7..0f0cb1465e08 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -509,13 +509,6 @@ static struct ctl_table net_core_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 	{
-		.procname	= "optmem_max",
-		.data		= &sysctl_optmem_max,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
 		.procname	= "tstamp_allow_data",
 		.data		= &sysctl_tstamp_allow_data,
 		.maxlen		= sizeof(int),
@@ -674,6 +667,14 @@ static struct ctl_table netns_core_table[] = {
 		.proc_handler	= proc_dointvec_minmax
 	},
 	{
+		.procname	= "optmem_max",
+		.data		= &init_net.core.sysctl_optmem_max,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.extra1		= SYSCTL_ZERO,
+		.proc_handler	= proc_dointvec_minmax
+	},
+	{
 		.procname	= "txrehash",
 		.data		= &init_net.core.sysctl_txrehash,
 		.maxlen		= sizeof(u8),
diff --git a/net/core/xdp.c b/net/core/xdp.c
index b6f1d6dab3f2..4869c1c2d8f3 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -736,6 +736,39 @@ __bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash,
 	return -EOPNOTSUPP;
 }
 
+/**
+ * bpf_xdp_metadata_rx_vlan_tag - Get XDP packet outermost VLAN tag
+ * @ctx: XDP context pointer.
+ * @vlan_proto: Destination pointer for VLAN Tag protocol identifier (TPID).
+ * @vlan_tci: Destination pointer for VLAN TCI (VID + DEI + PCP)
+ *
+ * In case of success, ``vlan_proto`` contains *Tag protocol identifier (TPID)*,
+ * usually ``ETH_P_8021Q`` or ``ETH_P_8021AD``, but some networks can use
+ * custom TPIDs. ``vlan_proto`` is stored in **network byte order (BE)**
+ * and should be used as follows:
+ * ``if (vlan_proto == bpf_htons(ETH_P_8021Q)) do_something();``
+ *
+ * ``vlan_tci`` contains the remaining 16 bits of a VLAN tag.
+ * Driver is expected to provide those in **host byte order (usually LE)**,
+ * so the bpf program should not perform byte conversion.
+ * According to 802.1Q standard, *VLAN TCI (Tag control information)*
+ * is a bit field that contains:
+ * *VLAN identifier (VID)* that can be read with ``vlan_tci & 0xfff``,
+ * *Drop eligible indicator (DEI)* - 1 bit,
+ * *Priority code point (PCP)* - 3 bits.
+ * For detailed meaning of DEI and PCP, please refer to other sources.
+ *
+ * Return:
+ * * Returns 0 on success or ``-errno`` on error.
+ * * ``-EOPNOTSUPP`` : device driver doesn't implement kfunc
+ * * ``-ENODATA``    : VLAN tag was not stripped or is not available
+ */
+__bpf_kfunc int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx,
+					     __be16 *vlan_proto, u16 *vlan_tci)
+{
+	return -EOPNOTSUPP;
+}
+
 __bpf_kfunc_end_defs();
 
 BTF_SET8_START(xdp_metadata_kfunc_ids)
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 4550b680665a..ded07e09f813 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -669,7 +669,7 @@ discard:
 ipv6_pktoptions:
 	if (!((1 << sk->sk_state) & (DCCPF_CLOSED | DCCPF_LISTEN))) {
 		if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo)
-			np->mcast_oif = inet6_iif(opt_skb);
+			WRITE_ONCE(np->mcast_oif, inet6_iif(opt_skb));
 		if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim)
 			WRITE_ONCE(np->mcast_hops, ipv6_hdr(opt_skb)->hop_limit);
 		if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass)
@@ -889,7 +889,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 		u32 exthdrlen = icsk->icsk_ext_hdr_len;
 		struct sockaddr_in sin;
 
-		SOCK_DEBUG(sk, "connect: ipv4 mapped\n");
+		net_dbg_ratelimited("connect: ipv4 mapped\n");
 
 		if (ipv6_only_sock(sk))
 			return -ENETUNREACH;
diff --git a/net/devlink/core.c b/net/devlink/core.c
index 6984877e9f10..4275a2bc6d8e 100644
--- a/net/devlink/core.c
+++ b/net/devlink/core.c
@@ -503,14 +503,14 @@ static void __net_exit devlink_pernet_pre_exit(struct net *net)
 	 * all devlink instances from this namespace into init_net.
 	 */
 	devlinks_xa_for_each_registered_get(net, index, devlink) {
-		devl_lock(devlink);
+		devl_dev_lock(devlink, true);
 		err = 0;
 		if (devl_is_registered(devlink))
 			err = devlink_reload(devlink, &init_net,
 					     DEVLINK_RELOAD_ACTION_DRIVER_REINIT,
 					     DEVLINK_RELOAD_LIMIT_UNSPEC,
 					     &actions_performed, NULL);
-		devl_unlock(devlink);
+		devl_dev_unlock(devlink, true);
 		devlink_put(devlink);
 		if (err && err != -EOPNOTSUPP)
 			pr_warn("Failed to reload devlink instance into init_net\n");
diff --git a/net/devlink/dev.c b/net/devlink/dev.c
index 4fc7adb32663..19dbf540748a 100644
--- a/net/devlink/dev.c
+++ b/net/devlink/dev.c
@@ -4,6 +4,7 @@
  * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
  */
 
+#include <linux/device.h>
 #include <net/genetlink.h>
 #include <net/sock.h>
 #include "devl_internal.h"
@@ -201,7 +202,10 @@ static void devlink_notify(struct devlink *devlink, enum devlink_command cmd)
 	int err;
 
 	WARN_ON(cmd != DEVLINK_CMD_NEW && cmd != DEVLINK_CMD_DEL);
-	WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED));
+	WARN_ON(!devl_is_registered(devlink));
+
+	if (!devlink_nl_notify_need(devlink))
+		return;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
@@ -213,8 +217,7 @@ static void devlink_notify(struct devlink *devlink, enum devlink_command cmd)
 		return;
 	}
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
-				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_notify_send(devlink, msg);
 }
 
 int devlink_nl_get_doit(struct sk_buff *skb, struct genl_info *info)
@@ -424,6 +427,18 @@ static void devlink_reload_netns_change(struct devlink *devlink,
 	devlink_rel_nested_in_notify(devlink);
 }
 
+static void devlink_reload_reinit_sanity_check(struct devlink *devlink)
+{
+	WARN_ON(!list_empty(&devlink->trap_policer_list));
+	WARN_ON(!list_empty(&devlink->trap_group_list));
+	WARN_ON(!list_empty(&devlink->trap_list));
+	WARN_ON(!list_empty(&devlink->dpipe_table_list));
+	WARN_ON(!list_empty(&devlink->sb_list));
+	WARN_ON(!list_empty(&devlink->rate_list));
+	WARN_ON(!list_empty(&devlink->linecard_list));
+	WARN_ON(!xa_empty(&devlink->ports));
+}
+
 int devlink_reload(struct devlink *devlink, struct net *dest_net,
 		   enum devlink_reload_action action,
 		   enum devlink_reload_limit limit,
@@ -433,6 +448,13 @@ int devlink_reload(struct devlink *devlink, struct net *dest_net,
 	struct net *curr_net;
 	int err;
 
+	/* Make sure the reload operations are invoked with the device lock
+	 * held to allow drivers to trigger functionality that expects it
+	 * (e.g., PCI reset) and to close possible races between these
+	 * operations and probe/remove.
+	 */
+	device_lock_assert(devlink->dev);
+
 	memcpy(remote_reload_stats, devlink->stats.remote_reload_stats,
 	       sizeof(remote_reload_stats));
 
@@ -444,8 +466,10 @@ int devlink_reload(struct devlink *devlink, struct net *dest_net,
 	if (dest_net && !net_eq(dest_net, curr_net))
 		devlink_reload_netns_change(devlink, curr_net, dest_net);
 
-	if (action == DEVLINK_RELOAD_ACTION_DRIVER_REINIT)
+	if (action == DEVLINK_RELOAD_ACTION_DRIVER_REINIT) {
 		devlink_params_driverinit_load_new(devlink);
+		devlink_reload_reinit_sanity_check(devlink);
+	}
 
 	err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack);
 	devlink_reload_failed_set(devlink, !!err);
@@ -977,7 +1001,7 @@ static void __devlink_flash_update_notify(struct devlink *devlink,
 		cmd != DEVLINK_CMD_FLASH_UPDATE_END &&
 		cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS);
 
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+	if (!devl_is_registered(devlink) || !devlink_nl_notify_need(devlink))
 		return;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
@@ -988,8 +1012,7 @@ static void __devlink_flash_update_notify(struct devlink *devlink,
 	if (err)
 		goto out_free_msg;
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
-				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_notify_send(devlink, msg);
 	return;
 
 out_free_msg:
diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index 183dbe3807ab..c7a8e13f917c 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -3,6 +3,7 @@
  * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
  */
 
+#include <linux/device.h>
 #include <linux/etherdevice.h>
 #include <linux/mutex.h>
 #include <linux/netdevice.h>
@@ -90,10 +91,29 @@ extern struct genl_family devlink_nl_family;
 
 struct devlink *devlinks_xa_find_get(struct net *net, unsigned long *indexp);
 
+static inline bool __devl_is_registered(struct devlink *devlink)
+{
+	return xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED);
+}
+
 static inline bool devl_is_registered(struct devlink *devlink)
 {
 	devl_assert_locked(devlink);
-	return xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED);
+	return __devl_is_registered(devlink);
+}
+
+static inline void devl_dev_lock(struct devlink *devlink, bool dev_lock)
+{
+	if (dev_lock)
+		device_lock(devlink->dev);
+	devl_lock(devlink);
+}
+
+static inline void devl_dev_unlock(struct devlink *devlink, bool dev_lock)
+{
+	devl_unlock(devlink);
+	if (dev_lock)
+		device_unlock(devlink->dev);
 }
 
 typedef void devlink_rel_notify_cb_t(struct devlink *devlink, u32 obj_index);
@@ -111,9 +131,6 @@ int devlink_rel_devlink_handle_put(struct sk_buff *msg, struct devlink *devlink,
 				   bool *msg_updated);
 
 /* Netlink */
-#define DEVLINK_NL_FLAG_NEED_PORT		BIT(0)
-#define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT	BIT(1)
-
 enum devlink_multicast_groups {
 	DEVLINK_MCGRP_CONFIG,
 };
@@ -140,7 +157,8 @@ typedef int devlink_nl_dump_one_func_t(struct sk_buff *msg,
 				       int flags);
 
 struct devlink *
-devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs);
+devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs,
+			    bool dev_lock);
 
 int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb,
 		      devlink_nl_dump_one_func_t *dump_one);
@@ -167,6 +185,58 @@ int devlink_nl_put_nested_handle(struct sk_buff *msg, struct net *net,
 				 struct devlink *devlink, int attrtype);
 int devlink_nl_msg_reply_and_new(struct sk_buff **msg, struct genl_info *info);
 
+static inline bool devlink_nl_notify_need(struct devlink *devlink)
+{
+	return genl_has_listeners(&devlink_nl_family, devlink_net(devlink),
+				  DEVLINK_MCGRP_CONFIG);
+}
+
+struct devlink_obj_desc {
+	struct rcu_head rcu;
+	const char *bus_name;
+	const char *dev_name;
+	unsigned int port_index;
+	bool port_index_valid;
+	long data[];
+};
+
+static inline void devlink_nl_obj_desc_init(struct devlink_obj_desc *desc,
+					    struct devlink *devlink)
+{
+	memset(desc, 0, sizeof(*desc));
+	desc->bus_name = devlink->dev->bus->name;
+	desc->dev_name = dev_name(devlink->dev);
+}
+
+static inline void devlink_nl_obj_desc_port_set(struct devlink_obj_desc *desc,
+						struct devlink_port *devlink_port)
+{
+	desc->port_index = devlink_port->index;
+	desc->port_index_valid = true;
+}
+
+int devlink_nl_notify_filter(struct sock *dsk, struct sk_buff *skb, void *data);
+
+static inline void devlink_nl_notify_send_desc(struct devlink *devlink,
+					       struct sk_buff *msg,
+					       struct devlink_obj_desc *desc)
+{
+	genlmsg_multicast_netns_filtered(&devlink_nl_family,
+					 devlink_net(devlink),
+					 msg, 0, DEVLINK_MCGRP_CONFIG,
+					 GFP_KERNEL,
+					 devlink_nl_notify_filter, desc);
+}
+
+static inline void devlink_nl_notify_send(struct devlink *devlink,
+					  struct sk_buff *msg)
+{
+	struct devlink_obj_desc desc;
+
+	devlink_nl_obj_desc_init(&desc, devlink);
+	devlink_nl_notify_send_desc(devlink, msg, &desc);
+}
+
 /* Notify */
 void devlink_notify_register(struct devlink *devlink);
 void devlink_notify_unregister(struct devlink *devlink);
diff --git a/net/devlink/health.c b/net/devlink/health.c
index 695df61f8ac2..acb8c0e174bb 100644
--- a/net/devlink/health.c
+++ b/net/devlink/health.c
@@ -490,12 +490,16 @@ static void devlink_recover_notify(struct devlink_health_reporter *reporter,
 				   enum devlink_command cmd)
 {
 	struct devlink *devlink = reporter->devlink;
+	struct devlink_obj_desc desc;
 	struct sk_buff *msg;
 	int err;
 
 	WARN_ON(cmd != DEVLINK_CMD_HEALTH_REPORTER_RECOVER);
 	ASSERT_DEVLINK_REGISTERED(devlink);
 
+	if (!devlink_nl_notify_need(devlink))
+		return;
+
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
 		return;
@@ -506,8 +510,10 @@ static void devlink_recover_notify(struct devlink_health_reporter *reporter,
 		return;
 	}
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg,
-				0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_obj_desc_init(&desc, devlink);
+	if (reporter->devlink_port)
+		devlink_nl_obj_desc_port_set(&desc, reporter->devlink_port);
+	devlink_nl_notify_send_desc(devlink, msg, &desc);
 }
 
 void
@@ -1151,7 +1157,8 @@ devlink_health_reporter_get_from_cb_lock(struct netlink_callback *cb)
 	struct nlattr **attrs = info->attrs;
 	struct devlink *devlink;
 
-	devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs);
+	devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs,
+					      false);
 	if (IS_ERR(devlink))
 		return NULL;
 
diff --git a/net/devlink/linecard.c b/net/devlink/linecard.c
index 2f1c317b64cd..67f70a621d27 100644
--- a/net/devlink/linecard.c
+++ b/net/devlink/linecard.c
@@ -136,7 +136,7 @@ static void devlink_linecard_notify(struct devlink_linecard *linecard,
 	WARN_ON(cmd != DEVLINK_CMD_LINECARD_NEW &&
 		cmd != DEVLINK_CMD_LINECARD_DEL);
 
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+	if (!__devl_is_registered(devlink) || !devlink_nl_notify_need(devlink))
 		return;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
@@ -150,8 +150,7 @@ static void devlink_linecard_notify(struct devlink_linecard *linecard,
 		return;
 	}
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
-				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_notify_send(devlink, msg);
 }
 
 void devlink_linecards_notify_register(struct devlink *devlink)
diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c
index d0b90ebc8b15..499885c8b9ca 100644
--- a/net/devlink/netlink.c
+++ b/net/devlink/netlink.c
@@ -9,10 +9,127 @@
 
 #include "devl_internal.h"
 
+#define DEVLINK_NL_FLAG_NEED_PORT		BIT(0)
+#define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT	BIT(1)
+#define DEVLINK_NL_FLAG_NEED_DEV_LOCK		BIT(2)
+
 static const struct genl_multicast_group devlink_nl_mcgrps[] = {
 	[DEVLINK_MCGRP_CONFIG] = { .name = DEVLINK_GENL_MCGRP_CONFIG_NAME },
 };
 
+struct devlink_nl_sock_priv {
+	struct devlink_obj_desc __rcu *flt;
+	spinlock_t flt_lock; /* Protects flt. */
+};
+
+static void devlink_nl_sock_priv_init(void *priv)
+{
+	struct devlink_nl_sock_priv *sk_priv = priv;
+
+	spin_lock_init(&sk_priv->flt_lock);
+}
+
+static void devlink_nl_sock_priv_destroy(void *priv)
+{
+	struct devlink_nl_sock_priv *sk_priv = priv;
+	struct devlink_obj_desc *flt;
+
+	flt = rcu_dereference_protected(sk_priv->flt, true);
+	kfree_rcu(flt, rcu);
+}
+
+int devlink_nl_notify_filter_set_doit(struct sk_buff *skb,
+				      struct genl_info *info)
+{
+	struct devlink_nl_sock_priv *sk_priv;
+	struct nlattr **attrs = info->attrs;
+	struct devlink_obj_desc *flt;
+	size_t data_offset = 0;
+	size_t data_size = 0;
+	char *pos;
+
+	if (attrs[DEVLINK_ATTR_BUS_NAME])
+		data_size = size_add(data_size,
+				     nla_len(attrs[DEVLINK_ATTR_BUS_NAME]) + 1);
+	if (attrs[DEVLINK_ATTR_DEV_NAME])
+		data_size = size_add(data_size,
+				     nla_len(attrs[DEVLINK_ATTR_DEV_NAME]) + 1);
+
+	flt = kzalloc(size_add(sizeof(*flt), data_size), GFP_KERNEL);
+	if (!flt)
+		return -ENOMEM;
+
+	pos = (char *) flt->data;
+	if (attrs[DEVLINK_ATTR_BUS_NAME]) {
+		data_offset += nla_strscpy(pos,
+					   attrs[DEVLINK_ATTR_BUS_NAME],
+					   data_size) + 1;
+		flt->bus_name = pos;
+		pos += data_offset;
+	}
+	if (attrs[DEVLINK_ATTR_DEV_NAME]) {
+		nla_strscpy(pos, attrs[DEVLINK_ATTR_DEV_NAME],
+			    data_size - data_offset);
+		flt->dev_name = pos;
+	}
+
+	if (attrs[DEVLINK_ATTR_PORT_INDEX]) {
+		flt->port_index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]);
+		flt->port_index_valid = true;
+	}
+
+	/* Don't attach empty filter. */
+	if (!flt->bus_name && !flt->dev_name && !flt->port_index_valid) {
+		kfree(flt);
+		flt = NULL;
+	}
+
+	sk_priv = genl_sk_priv_get(&devlink_nl_family, NETLINK_CB(skb).sk);
+	if (IS_ERR(sk_priv)) {
+		kfree(flt);
+		return PTR_ERR(sk_priv);
+	}
+	spin_lock(&sk_priv->flt_lock);
+	flt = rcu_replace_pointer(sk_priv->flt, flt,
+				  lockdep_is_held(&sk_priv->flt_lock));
+	spin_unlock(&sk_priv->flt_lock);
+	kfree_rcu(flt, rcu);
+	return 0;
+}
+
+static bool devlink_obj_desc_match(const struct devlink_obj_desc *desc,
+				   const struct devlink_obj_desc *flt)
+{
+	if (desc->bus_name && flt->bus_name &&
+	    strcmp(desc->bus_name, flt->bus_name))
+		return false;
+	if (desc->dev_name && flt->dev_name &&
+	    strcmp(desc->dev_name, flt->dev_name))
+		return false;
+	if (desc->port_index_valid && flt->port_index_valid &&
+	    desc->port_index != flt->port_index)
+		return false;
+	return true;
+}
+
+int devlink_nl_notify_filter(struct sock *dsk, struct sk_buff *skb, void *data)
+{
+	struct devlink_obj_desc *desc = data;
+	struct devlink_nl_sock_priv *sk_priv;
+	struct devlink_obj_desc *flt;
+	int ret = 0;
+
+	rcu_read_lock();
+	sk_priv = __genl_sk_priv_get(&devlink_nl_family, dsk);
+	if (!IS_ERR_OR_NULL(sk_priv)) {
+		flt = rcu_dereference(sk_priv->flt);
+		if (flt)
+			ret = !devlink_obj_desc_match(desc, flt);
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
 int devlink_nl_put_nested_handle(struct sk_buff *msg, struct net *net,
 				 struct devlink *devlink, int attrtype)
 {
@@ -61,7 +178,8 @@ int devlink_nl_msg_reply_and_new(struct sk_buff **msg, struct genl_info *info)
 }
 
 struct devlink *
-devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs)
+devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs,
+			    bool dev_lock)
 {
 	struct devlink *devlink;
 	unsigned long index;
@@ -75,12 +193,12 @@ devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs)
 	devname = nla_data(attrs[DEVLINK_ATTR_DEV_NAME]);
 
 	devlinks_xa_for_each_registered_get(net, index, devlink) {
-		devl_lock(devlink);
+		devl_dev_lock(devlink, dev_lock);
 		if (devl_is_registered(devlink) &&
 		    strcmp(devlink->dev->bus->name, busname) == 0 &&
 		    strcmp(dev_name(devlink->dev), devname) == 0)
 			return devlink;
-		devl_unlock(devlink);
+		devl_dev_unlock(devlink, dev_lock);
 		devlink_put(devlink);
 	}
 
@@ -90,11 +208,13 @@ devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs)
 static int __devlink_nl_pre_doit(struct sk_buff *skb, struct genl_info *info,
 				 u8 flags)
 {
+	bool dev_lock = flags & DEVLINK_NL_FLAG_NEED_DEV_LOCK;
 	struct devlink_port *devlink_port;
 	struct devlink *devlink;
 	int err;
 
-	devlink = devlink_get_from_attrs_lock(genl_info_net(info), info->attrs);
+	devlink = devlink_get_from_attrs_lock(genl_info_net(info), info->attrs,
+					      dev_lock);
 	if (IS_ERR(devlink))
 		return PTR_ERR(devlink);
 
@@ -114,7 +234,7 @@ static int __devlink_nl_pre_doit(struct sk_buff *skb, struct genl_info *info,
 	return 0;
 
 unlock:
-	devl_unlock(devlink);
+	devl_dev_unlock(devlink, dev_lock);
 	devlink_put(devlink);
 	return err;
 }
@@ -131,6 +251,12 @@ int devlink_nl_pre_doit_port(const struct genl_split_ops *ops,
 	return __devlink_nl_pre_doit(skb, info, DEVLINK_NL_FLAG_NEED_PORT);
 }
 
+int devlink_nl_pre_doit_dev_lock(const struct genl_split_ops *ops,
+				 struct sk_buff *skb, struct genl_info *info)
+{
+	return __devlink_nl_pre_doit(skb, info, DEVLINK_NL_FLAG_NEED_DEV_LOCK);
+}
+
 int devlink_nl_pre_doit_port_optional(const struct genl_split_ops *ops,
 				      struct sk_buff *skb,
 				      struct genl_info *info)
@@ -138,16 +264,30 @@ int devlink_nl_pre_doit_port_optional(const struct genl_split_ops *ops,
 	return __devlink_nl_pre_doit(skb, info, DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT);
 }
 
-void devlink_nl_post_doit(const struct genl_split_ops *ops,
-			  struct sk_buff *skb, struct genl_info *info)
+static void __devlink_nl_post_doit(struct sk_buff *skb, struct genl_info *info,
+				   u8 flags)
 {
+	bool dev_lock = flags & DEVLINK_NL_FLAG_NEED_DEV_LOCK;
 	struct devlink *devlink;
 
 	devlink = info->user_ptr[0];
-	devl_unlock(devlink);
+	devl_dev_unlock(devlink, dev_lock);
 	devlink_put(devlink);
 }
 
+void devlink_nl_post_doit(const struct genl_split_ops *ops,
+			  struct sk_buff *skb, struct genl_info *info)
+{
+	__devlink_nl_post_doit(skb, info, 0);
+}
+
+void
+devlink_nl_post_doit_dev_lock(const struct genl_split_ops *ops,
+			      struct sk_buff *skb, struct genl_info *info)
+{
+	__devlink_nl_post_doit(skb, info, DEVLINK_NL_FLAG_NEED_DEV_LOCK);
+}
+
 static int devlink_nl_inst_single_dumpit(struct sk_buff *msg,
 					 struct netlink_callback *cb, int flags,
 					 devlink_nl_dump_one_func_t *dump_one,
@@ -156,7 +296,7 @@ static int devlink_nl_inst_single_dumpit(struct sk_buff *msg,
 	struct devlink *devlink;
 	int err;
 
-	devlink = devlink_get_from_attrs_lock(sock_net(msg->sk), attrs);
+	devlink = devlink_get_from_attrs_lock(sock_net(msg->sk), attrs, false);
 	if (IS_ERR(devlink))
 		return PTR_ERR(devlink);
 	err = dump_one(msg, devlink, cb, flags | NLM_F_DUMP_FILTERED);
@@ -229,4 +369,7 @@ struct genl_family devlink_nl_family __ro_after_init = {
 	.resv_start_op	= DEVLINK_CMD_SELFTESTS_RUN + 1,
 	.mcgrps		= devlink_nl_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(devlink_nl_mcgrps),
+	.sock_priv_size		= sizeof(struct devlink_nl_sock_priv),
+	.sock_priv_init		= devlink_nl_sock_priv_init,
+	.sock_priv_destroy	= devlink_nl_sock_priv_destroy,
 };
diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c
index 788dfdc498a9..c81cf2dd154f 100644
--- a/net/devlink/netlink_gen.c
+++ b/net/devlink/netlink_gen.c
@@ -560,8 +560,15 @@ static const struct nla_policy devlink_selftests_run_nl_policy[DEVLINK_ATTR_SELF
 	[DEVLINK_ATTR_SELFTESTS] = NLA_POLICY_NESTED(devlink_dl_selftest_id_nl_policy),
 };
 
+/* DEVLINK_CMD_NOTIFY_FILTER_SET - do */
+static const struct nla_policy devlink_notify_filter_set_nl_policy[DEVLINK_ATTR_PORT_INDEX + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+};
+
 /* Ops table for devlink */
-const struct genl_split_ops devlink_nl_ops[73] = {
+const struct genl_split_ops devlink_nl_ops[74] = {
 	{
 		.cmd		= DEVLINK_CMD_GET,
 		.validate	= GENL_DONT_VALIDATE_STRICT,
@@ -846,9 +853,9 @@ const struct genl_split_ops devlink_nl_ops[73] = {
 	{
 		.cmd		= DEVLINK_CMD_RELOAD,
 		.validate	= GENL_DONT_VALIDATE_STRICT,
-		.pre_doit	= devlink_nl_pre_doit,
+		.pre_doit	= devlink_nl_pre_doit_dev_lock,
 		.doit		= devlink_nl_reload_doit,
-		.post_doit	= devlink_nl_post_doit,
+		.post_doit	= devlink_nl_post_doit_dev_lock,
 		.policy		= devlink_reload_nl_policy,
 		.maxattr	= DEVLINK_ATTR_RELOAD_LIMITS,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
@@ -1233,4 +1240,11 @@ const struct genl_split_ops devlink_nl_ops[73] = {
 		.maxattr	= DEVLINK_ATTR_SELFTESTS,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
 	},
+	{
+		.cmd		= DEVLINK_CMD_NOTIFY_FILTER_SET,
+		.doit		= devlink_nl_notify_filter_set_doit,
+		.policy		= devlink_notify_filter_set_nl_policy,
+		.maxattr	= DEVLINK_ATTR_PORT_INDEX,
+		.flags		= GENL_CMD_CAP_DO,
+	},
 };
diff --git a/net/devlink/netlink_gen.h b/net/devlink/netlink_gen.h
index 0e9e89c31c31..8f2bd50ddf5e 100644
--- a/net/devlink/netlink_gen.h
+++ b/net/devlink/netlink_gen.h
@@ -16,18 +16,23 @@ extern const struct nla_policy devlink_dl_port_function_nl_policy[DEVLINK_PORT_F
 extern const struct nla_policy devlink_dl_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1];
 
 /* Ops table for devlink */
-extern const struct genl_split_ops devlink_nl_ops[73];
+extern const struct genl_split_ops devlink_nl_ops[74];
 
 int devlink_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 			struct genl_info *info);
 int devlink_nl_pre_doit_port(const struct genl_split_ops *ops,
 			     struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_pre_doit_dev_lock(const struct genl_split_ops *ops,
+				 struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_pre_doit_port_optional(const struct genl_split_ops *ops,
 				      struct sk_buff *skb,
 				      struct genl_info *info);
 void
 devlink_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 		     struct genl_info *info);
+void
+devlink_nl_post_doit_dev_lock(const struct genl_split_ops *ops,
+			      struct sk_buff *skb, struct genl_info *info);
 
 int devlink_nl_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
@@ -137,5 +142,7 @@ int devlink_nl_selftests_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_selftests_get_dumpit(struct sk_buff *skb,
 				    struct netlink_callback *cb);
 int devlink_nl_selftests_run_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_notify_filter_set_doit(struct sk_buff *skb,
+				      struct genl_info *info);
 
 #endif /* _LINUX_DEVLINK_GEN_H */
diff --git a/net/devlink/param.c b/net/devlink/param.c
index d74df09311a9..22bc3b500518 100644
--- a/net/devlink/param.c
+++ b/net/devlink/param.c
@@ -343,7 +343,7 @@ static void devlink_param_notify(struct devlink *devlink,
 	 * will replay the notifications if the params are added/removed
 	 * outside of the lifetime of the instance.
 	 */
-	if (!devl_is_registered(devlink))
+	if (!devl_is_registered(devlink) || !devlink_nl_notify_need(devlink))
 		return;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
@@ -356,8 +356,7 @@ static void devlink_param_notify(struct devlink *devlink,
 		return;
 	}
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
-				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_notify_send(devlink, msg);
 }
 
 static void devlink_params_notify(struct devlink *devlink,
diff --git a/net/devlink/port.c b/net/devlink/port.c
index 7634f187fa50..62e54e152ecf 100644
--- a/net/devlink/port.c
+++ b/net/devlink/port.c
@@ -507,12 +507,13 @@ static void devlink_port_notify(struct devlink_port *devlink_port,
 				enum devlink_command cmd)
 {
 	struct devlink *devlink = devlink_port->devlink;
+	struct devlink_obj_desc desc;
 	struct sk_buff *msg;
 	int err;
 
 	WARN_ON(cmd != DEVLINK_CMD_PORT_NEW && cmd != DEVLINK_CMD_PORT_DEL);
 
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+	if (!__devl_is_registered(devlink) || !devlink_nl_notify_need(devlink))
 		return;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
@@ -525,8 +526,9 @@ static void devlink_port_notify(struct devlink_port *devlink_port,
 		return;
 	}
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg,
-				0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_obj_desc_init(&desc, devlink);
+	devlink_nl_obj_desc_port_set(&desc, devlink_port);
+	devlink_nl_notify_send_desc(devlink, msg, &desc);
 }
 
 static void devlink_ports_notify(struct devlink *devlink,
diff --git a/net/devlink/rate.c b/net/devlink/rate.c
index 94b289b93ff2..7139e67e93ae 100644
--- a/net/devlink/rate.c
+++ b/net/devlink/rate.c
@@ -146,7 +146,7 @@ static void devlink_rate_notify(struct devlink_rate *devlink_rate,
 
 	WARN_ON(cmd != DEVLINK_CMD_RATE_NEW && cmd != DEVLINK_CMD_RATE_DEL);
 
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+	if (!devl_is_registered(devlink) || !devlink_nl_notify_need(devlink))
 		return;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
@@ -159,8 +159,7 @@ static void devlink_rate_notify(struct devlink_rate *devlink_rate,
 		return;
 	}
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg,
-				0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_notify_send(devlink, msg);
 }
 
 void devlink_rates_notify_register(struct devlink *devlink)
diff --git a/net/devlink/region.c b/net/devlink/region.c
index 0aab7b82d678..7319127c5913 100644
--- a/net/devlink/region.c
+++ b/net/devlink/region.c
@@ -234,15 +234,15 @@ static void devlink_nl_region_notify(struct devlink_region *region,
 	struct sk_buff *msg;
 
 	WARN_ON(cmd != DEVLINK_CMD_REGION_NEW && cmd != DEVLINK_CMD_REGION_DEL);
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+
+	if (!__devl_is_registered(devlink) || !devlink_nl_notify_need(devlink))
 		return;
 
 	msg = devlink_nl_region_notify_build(region, snapshot, cmd, 0, 0);
 	if (IS_ERR(msg))
 		return;
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg,
-				0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_notify_send(devlink, msg);
 }
 
 void devlink_regions_notify_register(struct devlink *devlink)
@@ -883,7 +883,8 @@ int devlink_nl_region_read_dumpit(struct sk_buff *skb,
 
 	start_offset = state->start_offset;
 
-	devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs);
+	devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs,
+					      false);
 	if (IS_ERR(devlink))
 		return PTR_ERR(devlink);
 
diff --git a/net/devlink/trap.c b/net/devlink/trap.c
index c26313e7ca08..5d18c7424df1 100644
--- a/net/devlink/trap.c
+++ b/net/devlink/trap.c
@@ -1173,7 +1173,8 @@ devlink_trap_group_notify(struct devlink *devlink,
 
 	WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_GROUP_NEW &&
 		     cmd != DEVLINK_CMD_TRAP_GROUP_DEL);
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+
+	if (!devl_is_registered(devlink) || !devlink_nl_notify_need(devlink))
 		return;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
@@ -1187,8 +1188,7 @@ devlink_trap_group_notify(struct devlink *devlink,
 		return;
 	}
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
-				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_notify_send(devlink, msg);
 }
 
 void devlink_trap_groups_notify_register(struct devlink *devlink)
@@ -1234,7 +1234,8 @@ static void devlink_trap_notify(struct devlink *devlink,
 
 	WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_NEW &&
 		     cmd != DEVLINK_CMD_TRAP_DEL);
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+
+	if (!devl_is_registered(devlink) || !devlink_nl_notify_need(devlink))
 		return;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
@@ -1247,8 +1248,7 @@ static void devlink_trap_notify(struct devlink *devlink,
 		return;
 	}
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
-				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_notify_send(devlink, msg);
 }
 
 void devlink_traps_notify_register(struct devlink *devlink)
@@ -1710,7 +1710,8 @@ devlink_trap_policer_notify(struct devlink *devlink,
 
 	WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_POLICER_NEW &&
 		     cmd != DEVLINK_CMD_TRAP_POLICER_DEL);
-	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+
+	if (!devl_is_registered(devlink) || !devlink_nl_notify_need(devlink))
 		return;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
@@ -1724,8 +1725,7 @@ devlink_trap_policer_notify(struct devlink *devlink,
 		return;
 	}
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
-				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	devlink_nl_notify_send(devlink, msg);
 }
 
 void devlink_trap_policers_notify_register(struct devlink *devlink)
diff --git a/net/dns_resolver/Kconfig b/net/dns_resolver/Kconfig
index 155b06163409..7c2dba273e35 100644
--- a/net/dns_resolver/Kconfig
+++ b/net/dns_resolver/Kconfig
@@ -23,6 +23,6 @@ config DNS_RESOLVER
 	  information.
 
 	  To compile this as a module, choose M here: the module will be called
-	  dnsresolver.
+	  dns_resolver.
 
 	  If unsure, say N.
diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
index 01e54b46ae0b..c42ddd85ff1f 100644
--- a/net/dns_resolver/dns_key.c
+++ b/net/dns_resolver/dns_key.c
@@ -91,7 +91,6 @@ const struct cred *dns_resolver_cache;
 static int
 dns_resolver_preparse(struct key_preparsed_payload *prep)
 {
-	const struct dns_payload_header *bin;
 	struct user_key_payload *upayload;
 	unsigned long derrno;
 	int ret;
@@ -102,26 +101,34 @@ dns_resolver_preparse(struct key_preparsed_payload *prep)
 		return -EINVAL;
 
 	if (data[0] == 0) {
+		const struct dns_server_list_v1_header *v1;
+
 		/* It may be a server list. */
-		if (datalen <= sizeof(*bin))
+		if (datalen < sizeof(*v1))
 			return -EINVAL;
 
-		bin = (const struct dns_payload_header *)data;
-		kenter("[%u,%u],%u", bin->content, bin->version, datalen);
-		if (bin->content != DNS_PAYLOAD_IS_SERVER_LIST) {
+		v1 = (const struct dns_server_list_v1_header *)data;
+		kenter("[%u,%u],%u", v1->hdr.content, v1->hdr.version, datalen);
+		if (v1->hdr.content != DNS_PAYLOAD_IS_SERVER_LIST) {
 			pr_warn_ratelimited(
 				"dns_resolver: Unsupported content type (%u)\n",
-				bin->content);
+				v1->hdr.content);
 			return -EINVAL;
 		}
 
-		if (bin->version != 1) {
+		if (v1->hdr.version != 1) {
 			pr_warn_ratelimited(
 				"dns_resolver: Unsupported server list version (%u)\n",
-				bin->version);
+				v1->hdr.version);
 			return -EINVAL;
 		}
 
+		if ((v1->status != DNS_LOOKUP_GOOD &&
+		     v1->status != DNS_LOOKUP_GOOD_WITH_BAD)) {
+			if (prep->expiry == TIME64_MAX)
+				prep->expiry = ktime_get_real_seconds() + 1;
+		}
+
 		result_len = datalen;
 		goto store_result;
 	}
@@ -314,7 +321,7 @@ static long dns_resolver_read(const struct key *key,
 
 struct key_type key_type_dns_resolver = {
 	.name		= "dns_resolver",
-	.flags		= KEY_TYPE_NET_DOMAIN,
+	.flags		= KEY_TYPE_NET_DOMAIN | KEY_TYPE_INSTANT_REAP,
 	.preparse	= dns_resolver_preparse,
 	.free_preparse	= dns_resolver_free_preparse,
 	.instantiate	= generic_key_instantiate,
diff --git a/net/dsa/tag_ar9331.c b/net/dsa/tag_ar9331.c
index 92ce67b93a58..cbb588ca73aa 100644
--- a/net/dsa/tag_ar9331.c
+++ b/net/dsa/tag_ar9331.c
@@ -89,6 +89,7 @@ static const struct dsa_device_ops ar9331_netdev_ops = {
 	.needed_headroom = AR9331_HDR_LEN,
 };
 
+MODULE_DESCRIPTION("DSA tag driver for Atheros AR9331 SoC with built-in switch");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_AR9331, AR9331_NAME);
 module_dsa_tag_driver(ar9331_netdev_ops);
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index 83d283a5d27e..8c3c068728e5 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -335,4 +335,5 @@ static struct dsa_tag_driver *dsa_tag_driver_array[] =	{
 
 module_dsa_tag_drivers(dsa_tag_driver_array);
 
+MODULE_DESCRIPTION("DSA tag driver for Broadcom switches using in-frame headers");
 MODULE_LICENSE("GPL");
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index 8ed52dd663ab..2a2c4fb61a65 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -406,4 +406,5 @@ static struct dsa_tag_driver *dsa_tag_drivers[] = {
 
 module_dsa_tag_drivers(dsa_tag_drivers);
 
+MODULE_DESCRIPTION("DSA tag driver for Marvell switches using DSA headers");
 MODULE_LICENSE("GPL");
diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c
index 3539141b5350..51a1f46a567f 100644
--- a/net/dsa/tag_gswip.c
+++ b/net/dsa/tag_gswip.c
@@ -107,6 +107,7 @@ static const struct dsa_device_ops gswip_netdev_ops = {
 	.needed_headroom = GSWIP_RX_HEADER_LEN,
 };
 
+MODULE_DESCRIPTION("DSA tag driver for Lantiq / Intel GSWIP switches");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_GSWIP, GSWIP_NAME);
 
diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c
index 6e233cd0aa38..663b25785d95 100644
--- a/net/dsa/tag_hellcreek.c
+++ b/net/dsa/tag_hellcreek.c
@@ -67,6 +67,7 @@ static const struct dsa_device_ops hellcreek_netdev_ops = {
 	.needed_tailroom = HELLCREEK_TAG_LEN,
 };
 
+MODULE_DESCRIPTION("DSA tag driver for Hirschmann Hellcreek TSN switches");
 MODULE_LICENSE("Dual MIT/GPL");
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_HELLCREEK, HELLCREEK_NAME);
 
diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index 9be341fa88f0..ee7b272ab715 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -459,4 +459,5 @@ static struct dsa_tag_driver *dsa_tag_driver_array[] = {
 
 module_dsa_tag_drivers(dsa_tag_driver_array);
 
+MODULE_DESCRIPTION("DSA tag driver for Microchip 8795/937x/9477/9893 families of switches");
 MODULE_LICENSE("GPL");
diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c
index 1ed8ee24855d..258e5d7dc5ef 100644
--- a/net/dsa/tag_lan9303.c
+++ b/net/dsa/tag_lan9303.c
@@ -119,6 +119,7 @@ static const struct dsa_device_ops lan9303_netdev_ops = {
 	.needed_headroom = LAN9303_TAG_LEN,
 };
 
+MODULE_DESCRIPTION("DSA tag driver for SMSC/Microchip LAN9303 family of switches");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_LAN9303, LAN9303_NAME);
 
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
index 2483785f6ab1..b670e3c53e91 100644
--- a/net/dsa/tag_mtk.c
+++ b/net/dsa/tag_mtk.c
@@ -102,6 +102,7 @@ static const struct dsa_device_ops mtk_netdev_ops = {
 	.needed_headroom = MTK_HDR_LEN,
 };
 
+MODULE_DESCRIPTION("DSA tag driver for Mediatek switches");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_MTK, MTK_NAME);
 
diff --git a/net/dsa/tag_none.c b/net/dsa/tag_none.c
index 9a473624db50..e9c9670a9c44 100644
--- a/net/dsa/tag_none.c
+++ b/net/dsa/tag_none.c
@@ -27,4 +27,5 @@ static const struct dsa_device_ops none_ops = {
 
 module_dsa_tag_driver(none_ops);
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_NONE, NONE_NAME);
+MODULE_DESCRIPTION("DSA no-op tag driver");
 MODULE_LICENSE("GPL");
diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c
index ef2f8fffb2c7..e0e4300bfbd3 100644
--- a/net/dsa/tag_ocelot.c
+++ b/net/dsa/tag_ocelot.c
@@ -217,4 +217,5 @@ static struct dsa_tag_driver *ocelot_tag_driver_array[] = {
 
 module_dsa_tag_drivers(ocelot_tag_driver_array);
 
+MODULE_DESCRIPTION("DSA tag driver for Ocelot family of switches, using NPI port");
 MODULE_LICENSE("GPL v2");
diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c
index 210039320888..b059381310fe 100644
--- a/net/dsa/tag_ocelot_8021q.c
+++ b/net/dsa/tag_ocelot_8021q.c
@@ -133,6 +133,7 @@ static const struct dsa_device_ops ocelot_8021q_netdev_ops = {
 	.promisc_on_conduit	= true,
 };
 
+MODULE_DESCRIPTION("DSA tag driver for Ocelot family of switches, using VLAN");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_OCELOT_8021Q, OCELOT_8021Q_NAME);
 
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index 6514aa7993ce..0cf61286b426 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -119,6 +119,7 @@ static const struct dsa_device_ops qca_netdev_ops = {
 	.promisc_on_conduit = true,
 };
 
+MODULE_DESCRIPTION("DSA tag driver for Qualcomm Atheros QCA8K switches");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_QCA, QCA_NAME);
 
diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c
index 4da5bad1a7aa..feaefa0e179b 100644
--- a/net/dsa/tag_rtl4_a.c
+++ b/net/dsa/tag_rtl4_a.c
@@ -23,7 +23,6 @@
 #define RTL4_A_NAME		"rtl4a"
 
 #define RTL4_A_HDR_LEN		4
-#define RTL4_A_ETHERTYPE	0x8899
 #define RTL4_A_PROTOCOL_SHIFT	12
 /*
  * 0x1 = Realtek Remote Control protocol (RRCP)
@@ -54,7 +53,7 @@ static struct sk_buff *rtl4a_tag_xmit(struct sk_buff *skb,
 
 	/* Set Ethertype */
 	p = (__be16 *)tag;
-	*p = htons(RTL4_A_ETHERTYPE);
+	*p = htons(ETH_P_REALTEK);
 
 	out = (RTL4_A_PROTOCOL_RTL8366RB << RTL4_A_PROTOCOL_SHIFT);
 	/* The lower bits indicate the port number */
@@ -82,7 +81,7 @@ static struct sk_buff *rtl4a_tag_rcv(struct sk_buff *skb,
 	tag = dsa_etype_header_pos_rx(skb);
 	p = (__be16 *)tag;
 	etype = ntohs(*p);
-	if (etype != RTL4_A_ETHERTYPE) {
+	if (etype != ETH_P_REALTEK) {
 		/* Not custom, just pass through */
 		netdev_dbg(dev, "non-realtek ethertype 0x%04x\n", etype);
 		return skb;
@@ -122,5 +121,6 @@ static const struct dsa_device_ops rtl4a_netdev_ops = {
 };
 module_dsa_tag_driver(rtl4a_netdev_ops);
 
+MODULE_DESCRIPTION("DSA tag driver for Realtek 4 byte protocol A tags");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_RTL4_A, RTL4_A_NAME);
diff --git a/net/dsa/tag_rtl8_4.c b/net/dsa/tag_rtl8_4.c
index 07e857debabf..15c2bae2b429 100644
--- a/net/dsa/tag_rtl8_4.c
+++ b/net/dsa/tag_rtl8_4.c
@@ -258,4 +258,5 @@ static struct dsa_tag_driver *dsa_tag_drivers[] = {
 };
 module_dsa_tag_drivers(dsa_tag_drivers);
 
+MODULE_DESCRIPTION("DSA tag driver for Realtek 8 byte protocol 4 tags");
 MODULE_LICENSE("GPL");
diff --git a/net/dsa/tag_rzn1_a5psw.c b/net/dsa/tag_rzn1_a5psw.c
index 2ce866b45615..69d51221b1e5 100644
--- a/net/dsa/tag_rzn1_a5psw.c
+++ b/net/dsa/tag_rzn1_a5psw.c
@@ -110,6 +110,7 @@ static const struct dsa_device_ops a5psw_netdev_ops = {
 	.needed_headroom = A5PSW_TAG_LEN,
 };
 
+MODULE_DESCRIPTION("DSA tag driver for Renesas RZ/N1 A5PSW switch");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_A5PSW, A5PSW_NAME);
 module_dsa_tag_driver(a5psw_netdev_ops);
diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c
index 1fffe8c2b589..2717e9d7b612 100644
--- a/net/dsa/tag_sja1105.c
+++ b/net/dsa/tag_sja1105.c
@@ -806,4 +806,5 @@ static struct dsa_tag_driver *sja1105_tag_driver_array[] = {
 
 module_dsa_tag_drivers(sja1105_tag_driver_array);
 
+MODULE_DESCRIPTION("DSA tag driver for NXP SJA1105 switches");
 MODULE_LICENSE("GPL v2");
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 1ebb25a8b140..22742a53d6f4 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -59,6 +59,7 @@ static const struct dsa_device_ops trailer_netdev_ops = {
 	.needed_tailroom = 4,
 };
 
+MODULE_DESCRIPTION("DSA tag driver for switches using a trailer tag");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_TRAILER, TRAILER_NAME);
 
diff --git a/net/dsa/tag_xrs700x.c b/net/dsa/tag_xrs700x.c
index c9c163598ef2..68d4633ddd5e 100644
--- a/net/dsa/tag_xrs700x.c
+++ b/net/dsa/tag_xrs700x.c
@@ -60,6 +60,7 @@ static const struct dsa_device_ops xrs700x_netdev_ops = {
 	.needed_tailroom = 1,
 };
 
+MODULE_DESCRIPTION("DSA tag driver for XRS700x switches");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_XRS700X, XRS700X_NAME);
 
diff --git a/net/dsa/user.c b/net/dsa/user.c
index d438884a4eb0..b738a466e2dc 100644
--- a/net/dsa/user.c
+++ b/net/dsa/user.c
@@ -920,30 +920,6 @@ netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev)
 }
 EXPORT_SYMBOL_GPL(dsa_enqueue_skb);
 
-static int dsa_realloc_skb(struct sk_buff *skb, struct net_device *dev)
-{
-	int needed_headroom = dev->needed_headroom;
-	int needed_tailroom = dev->needed_tailroom;
-
-	/* For tail taggers, we need to pad short frames ourselves, to ensure
-	 * that the tail tag does not fail at its role of being at the end of
-	 * the packet, once the conduit interface pads the frame. Account for
-	 * that pad length here, and pad later.
-	 */
-	if (unlikely(needed_tailroom && skb->len < ETH_ZLEN))
-		needed_tailroom += ETH_ZLEN - skb->len;
-	/* skb_headroom() returns unsigned int... */
-	needed_headroom = max_t(int, needed_headroom - skb_headroom(skb), 0);
-	needed_tailroom = max_t(int, needed_tailroom - skb_tailroom(skb), 0);
-
-	if (likely(!needed_headroom && !needed_tailroom && !skb_cloned(skb)))
-		/* No reallocation needed, yay! */
-		return 0;
-
-	return pskb_expand_head(skb, needed_headroom, needed_tailroom,
-				GFP_ATOMIC);
-}
-
 static netdev_tx_t dsa_user_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct dsa_user_priv *p = netdev_priv(dev);
@@ -956,13 +932,14 @@ static netdev_tx_t dsa_user_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Handle tx timestamp if any */
 	dsa_skb_tx_timestamp(p, skb);
 
-	if (dsa_realloc_skb(skb, dev)) {
+	if (skb_ensure_writable_head_tail(skb, dev)) {
 		dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
 	}
 
 	/* needed_tailroom should still be 'warm' in the cache line from
-	 * dsa_realloc_skb(), which has also ensured that padding is safe.
+	 * skb_ensure_writable_head_tail(), which has also ensured that
+	 * padding is safe.
 	 */
 	if (dev->needed_tailroom)
 		eth_skb_pad(skb);
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index b4419fb6df6a..6b2a360dcdf0 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -589,8 +589,8 @@ err_free_info:
 
 int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max)
 {
+	struct ethtool_rxfh_param rxfh = {};
 	u32 dev_size, current_max = 0;
-	u32 *indir;
 	int ret;
 
 	if (!dev->ethtool_ops->get_rxfh_indir_size ||
@@ -600,21 +600,21 @@ int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max)
 	if (dev_size == 0)
 		return -EOPNOTSUPP;
 
-	indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER);
-	if (!indir)
+	rxfh.indir = kcalloc(dev_size, sizeof(rxfh.indir[0]), GFP_USER);
+	if (!rxfh.indir)
 		return -ENOMEM;
 
-	ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL, NULL);
+	ret = dev->ethtool_ops->get_rxfh(dev, &rxfh);
 	if (ret)
 		goto out;
 
 	while (dev_size--)
-		current_max = max(current_max, indir[dev_size]);
+		current_max = max(current_max, rxfh.indir[dev_size]);
 
 	*max = current_max;
 
 out:
-	kfree(indir);
+	kfree(rxfh.indir);
 	return ret;
 }
 
@@ -661,6 +661,12 @@ int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index)
 }
 EXPORT_SYMBOL(ethtool_get_phc_vclocks);
 
+int ethtool_get_ts_info_by_layer(struct net_device *dev, struct ethtool_ts_info *info)
+{
+	return __ethtool_get_ts_info(dev, info);
+}
+EXPORT_SYMBOL(ethtool_get_ts_info_by_layer);
+
 const struct ethtool_phy_ops *ethtool_phy_ops;
 
 void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops)
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 0b0ce4f81c01..7519b0818b91 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -58,6 +58,9 @@ static struct devlink *netdev_to_devlink_get(struct net_device *dev)
 
 u32 ethtool_op_get_link(struct net_device *dev)
 {
+	/* Synchronize carrier state with link watch, see also rtnl_getlink() */
+	linkwatch_sync_dev(dev);
+
 	return netif_carrier_ok(dev) ? 1 : 0;
 }
 EXPORT_SYMBOL(ethtool_op_get_link);
@@ -969,18 +972,38 @@ static int ethtool_rxnfc_copy_to_user(void __user *useraddr,
 static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev,
 						u32 cmd, void __user *useraddr)
 {
+	const struct ethtool_ops *ops = dev->ethtool_ops;
 	struct ethtool_rxnfc info;
 	size_t info_size = sizeof(info);
 	int rc;
 
-	if (!dev->ethtool_ops->set_rxnfc)
+	if (!ops->set_rxnfc)
 		return -EOPNOTSUPP;
 
 	rc = ethtool_rxnfc_copy_struct(cmd, &info, &info_size, useraddr);
 	if (rc)
 		return rc;
 
-	rc = dev->ethtool_ops->set_rxnfc(dev, &info);
+	if (ops->get_rxfh) {
+		struct ethtool_rxfh_param rxfh = {};
+
+		rc = ops->get_rxfh(dev, &rxfh);
+		if (rc)
+			return rc;
+
+		/* Sanity check: if symmetric-xor is set, then:
+		 * 1 - no other fields besides IP src/dst and/or L4 src/dst
+		 * 2 - If src is set, dst must also be set
+		 */
+		if ((rxfh.input_xfrm & RXH_XFRM_SYM_XOR) &&
+		    ((info.data & ~(RXH_IP_SRC | RXH_IP_DST |
+				    RXH_L4_B_0_1 | RXH_L4_B_2_3)) ||
+		     (!!(info.data & RXH_IP_SRC) ^ !!(info.data & RXH_IP_DST)) ||
+		     (!!(info.data & RXH_L4_B_0_1) ^ !!(info.data & RXH_L4_B_2_3))))
+			return -EINVAL;
+	}
+
+	rc = ops->set_rxnfc(dev, &info);
 	if (rc)
 		return rc;
 
@@ -1058,15 +1081,15 @@ EXPORT_SYMBOL(netdev_rss_key_fill);
 static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
 						     void __user *useraddr)
 {
-	u32 user_size, dev_size;
-	u32 *indir;
+	struct ethtool_rxfh_param rxfh = {};
+	u32 user_size;
 	int ret;
 
 	if (!dev->ethtool_ops->get_rxfh_indir_size ||
 	    !dev->ethtool_ops->get_rxfh)
 		return -EOPNOTSUPP;
-	dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev);
-	if (dev_size == 0)
+	rxfh.indir_size = dev->ethtool_ops->get_rxfh_indir_size(dev);
+	if (rxfh.indir_size == 0)
 		return -EOPNOTSUPP;
 
 	if (copy_from_user(&user_size,
@@ -1075,41 +1098,41 @@ static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
 		return -EFAULT;
 
 	if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh_indir, size),
-			 &dev_size, sizeof(dev_size)))
+			 &rxfh.indir_size, sizeof(rxfh.indir_size)))
 		return -EFAULT;
 
 	/* If the user buffer size is 0, this is just a query for the
 	 * device table size.  Otherwise, if it's smaller than the
 	 * device table size it's an error.
 	 */
-	if (user_size < dev_size)
+	if (user_size < rxfh.indir_size)
 		return user_size == 0 ? 0 : -EINVAL;
 
-	indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER);
-	if (!indir)
+	rxfh.indir = kcalloc(rxfh.indir_size, sizeof(rxfh.indir[0]), GFP_USER);
+	if (!rxfh.indir)
 		return -ENOMEM;
 
-	ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL, NULL);
+	ret = dev->ethtool_ops->get_rxfh(dev, &rxfh);
 	if (ret)
 		goto out;
-
 	if (copy_to_user(useraddr +
 			 offsetof(struct ethtool_rxfh_indir, ring_index[0]),
-			 indir, dev_size * sizeof(indir[0])))
+			 rxfh.indir, rxfh.indir_size * sizeof(*rxfh.indir)))
 		ret = -EFAULT;
 
 out:
-	kfree(indir);
+	kfree(rxfh.indir);
 	return ret;
 }
 
 static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
 						     void __user *useraddr)
 {
-	struct ethtool_rxnfc rx_rings;
-	u32 user_size, dev_size, i;
-	u32 *indir;
 	const struct ethtool_ops *ops = dev->ethtool_ops;
+	struct ethtool_rxfh_param rxfh_dev = {};
+	struct netlink_ext_ack *extack = NULL;
+	struct ethtool_rxnfc rx_rings;
+	u32 user_size, i;
 	int ret;
 	u32 ringidx_offset = offsetof(struct ethtool_rxfh_indir, ring_index[0]);
 
@@ -1117,8 +1140,8 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
 	    !ops->get_rxnfc)
 		return -EOPNOTSUPP;
 
-	dev_size = ops->get_rxfh_indir_size(dev);
-	if (dev_size == 0)
+	rxfh_dev.indir_size = ops->get_rxfh_indir_size(dev);
+	if (rxfh_dev.indir_size == 0)
 		return -EOPNOTSUPP;
 
 	if (copy_from_user(&user_size,
@@ -1126,11 +1149,12 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
 			   sizeof(user_size)))
 		return -EFAULT;
 
-	if (user_size != 0 && user_size != dev_size)
+	if (user_size != 0 && user_size != rxfh_dev.indir_size)
 		return -EINVAL;
 
-	indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER);
-	if (!indir)
+	rxfh_dev.indir = kcalloc(rxfh_dev.indir_size,
+				 sizeof(rxfh_dev.indir[0]), GFP_USER);
+	if (!rxfh_dev.indir)
 		return -ENOMEM;
 
 	rx_rings.cmd = ETHTOOL_GRXRINGS;
@@ -1139,18 +1163,21 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
 		goto out;
 
 	if (user_size == 0) {
-		for (i = 0; i < dev_size; i++)
+		u32 *indir = rxfh_dev.indir;
+
+		for (i = 0; i < rxfh_dev.indir_size; i++)
 			indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data);
 	} else {
-		ret = ethtool_copy_validate_indir(indir,
+		ret = ethtool_copy_validate_indir(rxfh_dev.indir,
 						  useraddr + ringidx_offset,
 						  &rx_rings,
-						  dev_size);
+						  rxfh_dev.indir_size);
 		if (ret)
 			goto out;
 	}
 
-	ret = ops->set_rxfh(dev, indir, NULL, ETH_RSS_HASH_NO_CHANGE);
+	rxfh_dev.hfunc = ETH_RSS_HASH_NO_CHANGE;
+	ret = ops->set_rxfh(dev, &rxfh_dev, extack);
 	if (ret)
 		goto out;
 
@@ -1161,32 +1188,29 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
 		dev->priv_flags |= IFF_RXFH_CONFIGURED;
 
 out:
-	kfree(indir);
+	kfree(rxfh_dev.indir);
 	return ret;
 }
 
 static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
 					       void __user *useraddr)
 {
-	int ret;
 	const struct ethtool_ops *ops = dev->ethtool_ops;
+	struct ethtool_rxfh_param rxfh_dev = {};
 	u32 user_indir_size, user_key_size;
-	u32 dev_indir_size = 0, dev_key_size = 0;
 	struct ethtool_rxfh rxfh;
-	u32 total_size;
 	u32 indir_bytes;
-	u32 *indir = NULL;
-	u8 dev_hfunc = 0;
-	u8 *hkey = NULL;
 	u8 *rss_config;
+	u32 total_size;
+	int ret;
 
 	if (!ops->get_rxfh)
 		return -EOPNOTSUPP;
 
 	if (ops->get_rxfh_indir_size)
-		dev_indir_size = ops->get_rxfh_indir_size(dev);
+		rxfh_dev.indir_size = ops->get_rxfh_indir_size(dev);
 	if (ops->get_rxfh_key_size)
-		dev_key_size = ops->get_rxfh_key_size(dev);
+		rxfh_dev.key_size = ops->get_rxfh_key_size(dev);
 
 	if (copy_from_user(&rxfh, useraddr, sizeof(rxfh)))
 		return -EFAULT;
@@ -1194,44 +1218,46 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
 	user_key_size = rxfh.key_size;
 
 	/* Check that reserved fields are 0 for now */
-	if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd8[2] || rxfh.rsvd32)
+	if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd32)
 		return -EINVAL;
 	/* Most drivers don't handle rss_context, check it's 0 as well */
-	if (rxfh.rss_context && !ops->get_rxfh_context)
+	if (rxfh.rss_context && !ops->cap_rss_ctx_supported)
 		return -EOPNOTSUPP;
 
-	rxfh.indir_size = dev_indir_size;
-	rxfh.key_size = dev_key_size;
+	rxfh.indir_size = rxfh_dev.indir_size;
+	rxfh.key_size = rxfh_dev.key_size;
 	if (copy_to_user(useraddr, &rxfh, sizeof(rxfh)))
 		return -EFAULT;
 
-	if ((user_indir_size && (user_indir_size != dev_indir_size)) ||
-	    (user_key_size && (user_key_size != dev_key_size)))
+	if ((user_indir_size && user_indir_size != rxfh_dev.indir_size) ||
+	    (user_key_size && user_key_size != rxfh_dev.key_size))
 		return -EINVAL;
 
-	indir_bytes = user_indir_size * sizeof(indir[0]);
+	indir_bytes = user_indir_size * sizeof(rxfh_dev.indir[0]);
 	total_size = indir_bytes + user_key_size;
 	rss_config = kzalloc(total_size, GFP_USER);
 	if (!rss_config)
 		return -ENOMEM;
 
 	if (user_indir_size)
-		indir = (u32 *)rss_config;
+		rxfh_dev.indir = (u32 *)rss_config;
 
 	if (user_key_size)
-		hkey = rss_config + indir_bytes;
+		rxfh_dev.key = rss_config + indir_bytes;
 
-	if (rxfh.rss_context)
-		ret = dev->ethtool_ops->get_rxfh_context(dev, indir, hkey,
-							 &dev_hfunc,
-							 rxfh.rss_context);
-	else
-		ret = dev->ethtool_ops->get_rxfh(dev, indir, hkey, &dev_hfunc);
+	rxfh_dev.rss_context = rxfh.rss_context;
+
+	ret = dev->ethtool_ops->get_rxfh(dev, &rxfh_dev);
 	if (ret)
 		goto out;
 
 	if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, hfunc),
-			 &dev_hfunc, sizeof(rxfh.hfunc))) {
+			 &rxfh_dev.hfunc, sizeof(rxfh.hfunc))) {
+		ret = -EFAULT;
+	} else if (copy_to_user(useraddr +
+				offsetof(struct ethtool_rxfh, input_xfrm),
+				&rxfh_dev.input_xfrm,
+				sizeof(rxfh.input_xfrm))) {
 		ret = -EFAULT;
 	} else if (copy_to_user(useraddr +
 			      offsetof(struct ethtool_rxfh, rss_config[0]),
@@ -1247,16 +1273,16 @@ out:
 static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 					       void __user *useraddr)
 {
-	int ret;
+	u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]);
 	const struct ethtool_ops *ops = dev->ethtool_ops;
+	u32 dev_indir_size = 0, dev_key_size = 0, i;
+	struct ethtool_rxfh_param rxfh_dev = {};
+	struct netlink_ext_ack *extack = NULL;
 	struct ethtool_rxnfc rx_rings;
 	struct ethtool_rxfh rxfh;
-	u32 dev_indir_size = 0, dev_key_size = 0, i;
-	u32 *indir = NULL, indir_bytes = 0;
-	u8 *hkey = NULL;
+	u32 indir_bytes = 0;
 	u8 *rss_config;
-	u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]);
-	bool delete = false;
+	int ret;
 
 	if (!ops->get_rxnfc || !ops->set_rxfh)
 		return -EOPNOTSUPP;
@@ -1270,25 +1296,34 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 		return -EFAULT;
 
 	/* Check that reserved fields are 0 for now */
-	if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd8[2] || rxfh.rsvd32)
+	if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd32)
 		return -EINVAL;
 	/* Most drivers don't handle rss_context, check it's 0 as well */
-	if (rxfh.rss_context && !ops->set_rxfh_context)
+	if (rxfh.rss_context && !ops->cap_rss_ctx_supported)
+		return -EOPNOTSUPP;
+	/* Check input data transformation capabilities */
+	if (rxfh.input_xfrm && rxfh.input_xfrm != RXH_XFRM_SYM_XOR &&
+	    rxfh.input_xfrm != RXH_XFRM_NO_CHANGE)
+		return -EINVAL;
+	if ((rxfh.input_xfrm & RXH_XFRM_SYM_XOR) &&
+	    !ops->cap_rss_sym_xor_supported)
 		return -EOPNOTSUPP;
 
 	/* If either indir, hash key or function is valid, proceed further.
-	 * Must request at least one change: indir size, hash key or function.
+	 * Must request at least one change: indir size, hash key, function
+	 * or input transformation.
 	 */
 	if ((rxfh.indir_size &&
 	     rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE &&
 	     rxfh.indir_size != dev_indir_size) ||
 	    (rxfh.key_size && (rxfh.key_size != dev_key_size)) ||
 	    (rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE &&
-	     rxfh.key_size == 0 && rxfh.hfunc == ETH_RSS_HASH_NO_CHANGE))
+	     rxfh.key_size == 0 && rxfh.hfunc == ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh.input_xfrm == RXH_XFRM_NO_CHANGE))
 		return -EINVAL;
 
 	if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE)
-		indir_bytes = dev_indir_size * sizeof(indir[0]);
+		indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]);
 
 	rss_config = kzalloc(indir_bytes + rxfh.key_size, GFP_USER);
 	if (!rss_config)
@@ -1305,8 +1340,9 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 	 */
 	if (rxfh.indir_size &&
 	    rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) {
-		indir = (u32 *)rss_config;
-		ret = ethtool_copy_validate_indir(indir,
+		rxfh_dev.indir = (u32 *)rss_config;
+		rxfh_dev.indir_size = dev_indir_size;
+		ret = ethtool_copy_validate_indir(rxfh_dev.indir,
 						  useraddr + rss_cfg_offset,
 						  &rx_rings,
 						  rxfh.indir_size);
@@ -1314,17 +1350,22 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 			goto out;
 	} else if (rxfh.indir_size == 0) {
 		if (rxfh.rss_context == 0) {
-			indir = (u32 *)rss_config;
+			u32 *indir;
+
+			rxfh_dev.indir = (u32 *)rss_config;
+			rxfh_dev.indir_size = dev_indir_size;
+			indir = rxfh_dev.indir;
 			for (i = 0; i < dev_indir_size; i++)
 				indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data);
 		} else {
-			delete = true;
+			rxfh_dev.rss_delete = true;
 		}
 	}
 
 	if (rxfh.key_size) {
-		hkey = rss_config + indir_bytes;
-		if (copy_from_user(hkey,
+		rxfh_dev.key_size = dev_key_size;
+		rxfh_dev.key = rss_config + indir_bytes;
+		if (copy_from_user(rxfh_dev.key,
 				   useraddr + rss_cfg_offset + indir_bytes,
 				   rxfh.key_size)) {
 			ret = -EFAULT;
@@ -1332,19 +1373,19 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 		}
 	}
 
-	if (rxfh.rss_context)
-		ret = ops->set_rxfh_context(dev, indir, hkey, rxfh.hfunc,
-					    &rxfh.rss_context, delete);
-	else
-		ret = ops->set_rxfh(dev, indir, hkey, rxfh.hfunc);
+	rxfh_dev.hfunc = rxfh.hfunc;
+	rxfh_dev.rss_context = rxfh.rss_context;
+	rxfh_dev.input_xfrm = rxfh.input_xfrm;
+
+	ret = ops->set_rxfh(dev, &rxfh_dev, extack);
 	if (ret)
 		goto out;
 
 	if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, rss_context),
-			 &rxfh.rss_context, sizeof(rxfh.rss_context)))
+			 &rxfh_dev.rss_context, sizeof(rxfh_dev.rss_context)))
 		ret = -EFAULT;
 
-	if (!rxfh.rss_context) {
+	if (!rxfh_dev.rss_context) {
 		/* indicate whether rxfh was set to default */
 		if (rxfh.indir_size == 0)
 			dev->priv_flags &= ~IFF_RXFH_CONFIGURED;
@@ -1991,6 +2032,13 @@ __printf(2, 3) void ethtool_sprintf(u8 **data, const char *fmt, ...)
 }
 EXPORT_SYMBOL(ethtool_sprintf);
 
+void ethtool_puts(u8 **data, const char *str)
+{
+	strscpy(*data, str, ETH_GSTRING_LEN);
+	*data += ETH_GSTRING_LEN;
+}
+EXPORT_SYMBOL(ethtool_puts);
+
 static int ethtool_phys_id(struct net_device *dev, void __user *useraddr)
 {
 	struct ethtool_value id;
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 3bbd5afb7b31..fe3553f60bf3 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -505,6 +505,7 @@ static int ethnl_default_dumpit(struct sk_buff *skb,
 				ret = skb->len;
 			break;
 		}
+		ret = 0;
 	}
 	rtnl_unlock();
 
diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c
index fb09f774ea01..b7865a14fdf8 100644
--- a/net/ethtool/rings.c
+++ b/net/ethtool/rings.c
@@ -124,6 +124,8 @@ const struct nla_policy ethnl_rings_set_policy[] = {
 	[ETHTOOL_A_RINGS_RX_JUMBO]		= { .type = NLA_U32 },
 	[ETHTOOL_A_RINGS_TX]			= { .type = NLA_U32 },
 	[ETHTOOL_A_RINGS_RX_BUF_LEN]            = NLA_POLICY_MIN(NLA_U32, 1),
+	[ETHTOOL_A_RINGS_TCP_DATA_SPLIT]	=
+		NLA_POLICY_MAX(NLA_U8, ETHTOOL_TCP_DATA_SPLIT_ENABLED),
 	[ETHTOOL_A_RINGS_CQE_SIZE]		= NLA_POLICY_MIN(NLA_U32, 1),
 	[ETHTOOL_A_RINGS_TX_PUSH]		= NLA_POLICY_MAX(NLA_U8, 1),
 	[ETHTOOL_A_RINGS_RX_PUSH]		= NLA_POLICY_MAX(NLA_U8, 1),
@@ -145,6 +147,14 @@ ethnl_set_rings_validate(struct ethnl_req_info *req_info,
 		return -EOPNOTSUPP;
 	}
 
+	if (tb[ETHTOOL_A_RINGS_TCP_DATA_SPLIT] &&
+	    !(ops->supported_ring_params & ETHTOOL_RING_USE_TCP_DATA_SPLIT)) {
+		NL_SET_ERR_MSG_ATTR(info->extack,
+				    tb[ETHTOOL_A_RINGS_TCP_DATA_SPLIT],
+				    "setting TCP data split is not supported");
+		return -EOPNOTSUPP;
+	}
+
 	if (tb[ETHTOOL_A_RINGS_CQE_SIZE] &&
 	    !(ops->supported_ring_params & ETHTOOL_RING_USE_CQE_SIZE)) {
 		NL_SET_ERR_MSG_ATTR(info->extack,
@@ -202,6 +212,8 @@ ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info)
 	ethnl_update_u32(&ringparam.tx_pending, tb[ETHTOOL_A_RINGS_TX], &mod);
 	ethnl_update_u32(&kernel_ringparam.rx_buf_len,
 			 tb[ETHTOOL_A_RINGS_RX_BUF_LEN], &mod);
+	ethnl_update_u8(&kernel_ringparam.tcp_data_split,
+			tb[ETHTOOL_A_RINGS_TCP_DATA_SPLIT], &mod);
 	ethnl_update_u32(&kernel_ringparam.cqe_size,
 			 tb[ETHTOOL_A_RINGS_CQE_SIZE], &mod);
 	ethnl_update_u8(&kernel_ringparam.tx_push,
diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
index 5764202e6cb6..71679137eff2 100644
--- a/net/ethtool/rss.c
+++ b/net/ethtool/rss.c
@@ -13,6 +13,7 @@ struct rss_reply_data {
 	u32				indir_size;
 	u32				hkey_size;
 	u32				hfunc;
+	u32				input_xfrm;
 	u32				*indir_table;
 	u8				*hkey;
 };
@@ -48,9 +49,9 @@ rss_prepare_data(const struct ethnl_req_info *req_base,
 	struct rss_reply_data *data = RSS_REPDATA(reply_base);
 	struct rss_req_info *request = RSS_REQINFO(req_base);
 	struct net_device *dev = reply_base->dev;
+	struct ethtool_rxfh_param rxfh = {};
 	const struct ethtool_ops *ops;
 	u32 total_size, indir_bytes;
-	u8 dev_hfunc = 0;
 	u8 *rss_config;
 	int ret;
 
@@ -59,7 +60,7 @@ rss_prepare_data(const struct ethnl_req_info *req_base,
 		return -EOPNOTSUPP;
 
 	/* Some drivers don't handle rss_context */
-	if (request->rss_context && !ops->get_rxfh_context)
+	if (request->rss_context && !ops->cap_rss_ctx_supported)
 		return -EOPNOTSUPP;
 
 	ret = ethnl_ops_begin(dev);
@@ -83,21 +84,21 @@ rss_prepare_data(const struct ethnl_req_info *req_base,
 
 	if (data->indir_size)
 		data->indir_table = (u32 *)rss_config;
-
 	if (data->hkey_size)
 		data->hkey = rss_config + indir_bytes;
 
-	if (request->rss_context)
-		ret = ops->get_rxfh_context(dev, data->indir_table, data->hkey,
-					    &dev_hfunc, request->rss_context);
-	else
-		ret = ops->get_rxfh(dev, data->indir_table, data->hkey,
-				    &dev_hfunc);
+	rxfh.indir_size = data->indir_size;
+	rxfh.indir = data->indir_table;
+	rxfh.key_size = data->hkey_size;
+	rxfh.key = data->hkey;
+	rxfh.rss_context = request->rss_context;
 
+	ret = ops->get_rxfh(dev, &rxfh);
 	if (ret)
 		goto out_ops;
 
-	data->hfunc = dev_hfunc;
+	data->hfunc = rxfh.hfunc;
+	data->input_xfrm = rxfh.input_xfrm;
 out_ops:
 	ethnl_ops_complete(dev);
 	return ret;
@@ -111,6 +112,7 @@ rss_reply_size(const struct ethnl_req_info *req_base,
 	int len;
 
 	len = nla_total_size(sizeof(u32)) +	/* _RSS_HFUNC */
+	      nla_total_size(sizeof(u32)) +	/* _RSS_INPUT_XFRM */
 	      nla_total_size(sizeof(u32) * data->indir_size) + /* _RSS_INDIR */
 	      nla_total_size(data->hkey_size);	/* _RSS_HKEY */
 
@@ -125,6 +127,8 @@ rss_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base,
 
 	if ((data->hfunc &&
 	     nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc)) ||
+	    (data->input_xfrm &&
+	     nla_put_u32(skb, ETHTOOL_A_RSS_INPUT_XFRM, data->input_xfrm)) ||
 	    (data->indir_size &&
 	     nla_put(skb, ETHTOOL_A_RSS_INDIR,
 		     sizeof(u32) * data->indir_size, data->indir_table)) ||
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 306f942c3b28..7ceb9ac6e730 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -173,7 +173,24 @@ static int hsr_dev_open(struct net_device *dev)
 
 static int hsr_dev_close(struct net_device *dev)
 {
-	/* Nothing to do here. */
+	struct hsr_port *port;
+	struct hsr_priv *hsr;
+
+	hsr = netdev_priv(dev);
+	hsr_for_each_port(hsr, port) {
+		if (port->type == HSR_PT_MASTER)
+			continue;
+		switch (port->type) {
+		case HSR_PT_SLAVE_A:
+		case HSR_PT_SLAVE_B:
+			dev_uc_unsync(port->dev, dev);
+			dev_mc_unsync(port->dev, dev);
+			break;
+		default:
+			break;
+		}
+	}
+
 	return 0;
 }
 
@@ -404,12 +421,60 @@ void hsr_del_ports(struct hsr_priv *hsr)
 		hsr_del_port(port);
 }
 
+static void hsr_set_rx_mode(struct net_device *dev)
+{
+	struct hsr_port *port;
+	struct hsr_priv *hsr;
+
+	hsr = netdev_priv(dev);
+
+	hsr_for_each_port(hsr, port) {
+		if (port->type == HSR_PT_MASTER)
+			continue;
+		switch (port->type) {
+		case HSR_PT_SLAVE_A:
+		case HSR_PT_SLAVE_B:
+			dev_mc_sync_multiple(port->dev, dev);
+			dev_uc_sync_multiple(port->dev, dev);
+			break;
+		default:
+			break;
+		}
+	}
+}
+
+static void hsr_change_rx_flags(struct net_device *dev, int change)
+{
+	struct hsr_port *port;
+	struct hsr_priv *hsr;
+
+	hsr = netdev_priv(dev);
+
+	hsr_for_each_port(hsr, port) {
+		if (port->type == HSR_PT_MASTER)
+			continue;
+		switch (port->type) {
+		case HSR_PT_SLAVE_A:
+		case HSR_PT_SLAVE_B:
+			if (change & IFF_ALLMULTI)
+				dev_set_allmulti(port->dev,
+						 dev->flags &
+						 IFF_ALLMULTI ? 1 : -1);
+			break;
+		default:
+			break;
+		}
+	}
+}
+
 static const struct net_device_ops hsr_device_ops = {
 	.ndo_change_mtu = hsr_dev_change_mtu,
 	.ndo_open = hsr_dev_open,
 	.ndo_stop = hsr_dev_close,
 	.ndo_start_xmit = hsr_dev_xmit,
+	.ndo_change_rx_flags = hsr_change_rx_flags,
 	.ndo_fix_features = hsr_fix_features,
+	.ndo_set_rx_mode = hsr_set_rx_mode,
 };
 
 static struct device_type hsr_type = {
diff --git a/net/ieee802154/Makefile b/net/ieee802154/Makefile
index f05b7bdae2aa..7bce67673e83 100644
--- a/net/ieee802154/Makefile
+++ b/net/ieee802154/Makefile
@@ -4,7 +4,7 @@ obj-$(CONFIG_IEEE802154_SOCKET) += ieee802154_socket.o
 obj-y += 6lowpan/
 
 ieee802154-y := netlink.o nl-mac.o nl-phy.o nl_policy.o core.o \
-                header_ops.o sysfs.o nl802154.o trace.o
+                header_ops.o sysfs.o nl802154.o trace.o pan.o
 ieee802154_socket-y := socket.o
 
 CFLAGS_trace.o := -I$(src)
diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c
index 57546e07e06a..60e8fff1347e 100644
--- a/net/ieee802154/core.c
+++ b/net/ieee802154/core.c
@@ -198,6 +198,25 @@ void wpan_phy_free(struct wpan_phy *phy)
 }
 EXPORT_SYMBOL(wpan_phy_free);
 
+static void cfg802154_free_peer_structures(struct wpan_dev *wpan_dev)
+{
+	struct ieee802154_pan_device *child, *tmp;
+
+	mutex_lock(&wpan_dev->association_lock);
+
+	kfree(wpan_dev->parent);
+	wpan_dev->parent = NULL;
+
+	list_for_each_entry_safe(child, tmp, &wpan_dev->children, node) {
+		list_del(&child->node);
+		kfree(child);
+	}
+
+	wpan_dev->nchildren = 0;
+
+	mutex_unlock(&wpan_dev->association_lock);
+}
+
 int cfg802154_switch_netns(struct cfg802154_registered_device *rdev,
 			   struct net *net)
 {
@@ -276,6 +295,9 @@ static int cfg802154_netdev_notifier_call(struct notifier_block *nb,
 		wpan_dev->identifier = ++rdev->wpan_dev_id;
 		list_add_rcu(&wpan_dev->list, &rdev->wpan_dev_list);
 		rdev->devlist_generation++;
+		mutex_init(&wpan_dev->association_lock);
+		INIT_LIST_HEAD(&wpan_dev->children);
+		wpan_dev->max_associations = SZ_16K;
 
 		wpan_dev->netdev = dev;
 		break;
@@ -291,6 +313,8 @@ static int cfg802154_netdev_notifier_call(struct notifier_block *nb,
 		rdev->opencount++;
 		break;
 	case NETDEV_UNREGISTER:
+		cfg802154_free_peer_structures(wpan_dev);
+
 		/* It is possible to get NETDEV_UNREGISTER
 		 * multiple times. To detect that, check
 		 * that the interface is still on the list
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 1a265a421308..7eb37de3add2 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -234,6 +234,8 @@ static const struct nla_policy nl802154_policy[NL802154_ATTR_MAX+1] = {
 				 NL802154_SCAN_DONE_REASON_ABORTED),
 	[NL802154_ATTR_BEACON_INTERVAL] =
 		NLA_POLICY_MAX(NLA_U8, IEEE802154_ACTIVE_SCAN_DURATION),
+	[NL802154_ATTR_MAX_ASSOCIATIONS] = { .type = NLA_U32 },
+	[NL802154_ATTR_PEER] = { .type = NLA_NESTED },
 
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 	[NL802154_ATTR_SEC_ENABLED] = { .type = NLA_U8, },
@@ -248,7 +250,6 @@ static const struct nla_policy nl802154_policy[NL802154_ATTR_MAX+1] = {
 #endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */
 };
 
-#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 static int
 nl802154_prepare_wpan_dev_dump(struct sk_buff *skb,
 			       struct netlink_callback *cb,
@@ -307,7 +308,6 @@ nl802154_finish_wpan_dev_dump(struct cfg802154_registered_device *rdev)
 {
 	rtnl_unlock();
 }
-#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */
 
 /* message building helper */
 static inline void *nl802154hdr_put(struct sk_buff *skb, u32 portid, u32 seq,
@@ -1087,15 +1087,14 @@ static int nl802154_set_pan_id(struct sk_buff *skb, struct genl_info *info)
 
 	pan_id = nla_get_le16(info->attrs[NL802154_ATTR_PAN_ID]);
 
-	/* TODO
-	 * I am not sure about to check here on broadcast pan_id.
-	 * Broadcast is a valid setting, comment from 802.15.4:
-	 * If this value is 0xffff, the device is not associated.
-	 *
-	 * This could useful to simple deassociate an device.
+	/* Only allow changing the PAN ID when the device has no more
+	 * associations ongoing to avoid confusing peers.
 	 */
-	if (pan_id == cpu_to_le16(IEEE802154_PAN_ID_BROADCAST))
+	if (cfg802154_device_is_associated(wpan_dev)) {
+		NL_SET_ERR_MSG(info->extack,
+			       "Existing associations, changing PAN ID forbidden");
 		return -EINVAL;
+	}
 
 	return rdev_set_pan_id(rdev, wpan_dev, pan_id);
 }
@@ -1123,20 +1122,17 @@ static int nl802154_set_short_addr(struct sk_buff *skb, struct genl_info *info)
 
 	short_addr = nla_get_le16(info->attrs[NL802154_ATTR_SHORT_ADDR]);
 
-	/* TODO
-	 * I am not sure about to check here on broadcast short_addr.
-	 * Broadcast is a valid setting, comment from 802.15.4:
-	 * A value of 0xfffe indicates that the device has
-	 * associated but has not been allocated an address. A
-	 * value of 0xffff indicates that the device does not
-	 * have a short address.
-	 *
-	 * I think we should allow to set these settings but
-	 * don't allow to allow socket communication with it.
+	/* The short address only has a meaning when part of a PAN, after a
+	 * proper association procedure. However, we want to still offer the
+	 * possibility to create static networks so changing the short address
+	 * is only allowed when not already associated to other devices with
+	 * the official handshake.
 	 */
-	if (short_addr == cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC) ||
-	    short_addr == cpu_to_le16(IEEE802154_ADDR_SHORT_BROADCAST))
+	if (cfg802154_device_is_associated(wpan_dev)) {
+		NL_SET_ERR_MSG(info->extack,
+			       "Existing associations, changing short address forbidden");
 		return -EINVAL;
+	}
 
 	return rdev_set_short_addr(rdev, wpan_dev, short_addr);
 }
@@ -1638,6 +1634,189 @@ nl802154_stop_beacons(struct sk_buff *skb, struct genl_info *info)
 	return rdev_stop_beacons(rdev, wpan_dev);
 }
 
+static int nl802154_associate(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wpan_dev *wpan_dev;
+	struct wpan_phy *wpan_phy;
+	struct ieee802154_addr coord;
+	int err;
+
+	wpan_dev = dev->ieee802154_ptr;
+	wpan_phy = &rdev->wpan_phy;
+
+	if (wpan_phy->flags & WPAN_PHY_FLAG_DATAGRAMS_ONLY) {
+		NL_SET_ERR_MSG(info->extack, "PHY only supports datagrams");
+		return -EOPNOTSUPP;
+	}
+
+	if (!info->attrs[NL802154_ATTR_PAN_ID] ||
+	    !info->attrs[NL802154_ATTR_EXTENDED_ADDR])
+		return -EINVAL;
+
+	coord.pan_id = nla_get_le16(info->attrs[NL802154_ATTR_PAN_ID]);
+	coord.mode = IEEE802154_ADDR_LONG;
+	coord.extended_addr = nla_get_le64(info->attrs[NL802154_ATTR_EXTENDED_ADDR]);
+
+	mutex_lock(&wpan_dev->association_lock);
+	err = rdev_associate(rdev, wpan_dev, &coord);
+	mutex_unlock(&wpan_dev->association_lock);
+	if (err)
+		pr_err("Association with PAN ID 0x%x failed (%d)\n",
+		       le16_to_cpu(coord.pan_id), err);
+
+	return err;
+}
+
+static int nl802154_disassociate(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+	struct wpan_phy *wpan_phy = &rdev->wpan_phy;
+	struct ieee802154_addr target;
+
+	if (wpan_phy->flags & WPAN_PHY_FLAG_DATAGRAMS_ONLY) {
+		NL_SET_ERR_MSG(info->extack, "PHY only supports datagrams");
+		return -EOPNOTSUPP;
+	}
+
+	target.pan_id = wpan_dev->pan_id;
+
+	if (info->attrs[NL802154_ATTR_EXTENDED_ADDR]) {
+		target.mode = IEEE802154_ADDR_LONG;
+		target.extended_addr = nla_get_le64(info->attrs[NL802154_ATTR_EXTENDED_ADDR]);
+	} else if (info->attrs[NL802154_ATTR_SHORT_ADDR]) {
+		target.mode = IEEE802154_ADDR_SHORT;
+		target.short_addr = nla_get_le16(info->attrs[NL802154_ATTR_SHORT_ADDR]);
+	} else {
+		NL_SET_ERR_MSG(info->extack, "Device address is missing");
+		return -EINVAL;
+	}
+
+	mutex_lock(&wpan_dev->association_lock);
+	rdev_disassociate(rdev, wpan_dev, &target);
+	mutex_unlock(&wpan_dev->association_lock);
+
+	return 0;
+}
+
+static int nl802154_set_max_associations(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net_device *dev = info->user_ptr[1];
+	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+	unsigned int max_assoc;
+
+	if (!info->attrs[NL802154_ATTR_MAX_ASSOCIATIONS]) {
+		NL_SET_ERR_MSG(info->extack, "No maximum number of association given");
+		return -EINVAL;
+	}
+
+	max_assoc = nla_get_u32(info->attrs[NL802154_ATTR_MAX_ASSOCIATIONS]);
+
+	mutex_lock(&wpan_dev->association_lock);
+	cfg802154_set_max_associations(wpan_dev, max_assoc);
+	mutex_unlock(&wpan_dev->association_lock);
+
+	return 0;
+}
+
+static int nl802154_send_peer_info(struct sk_buff *msg,
+				   struct netlink_callback *cb,
+				   u32 seq, int flags,
+				   struct cfg802154_registered_device *rdev,
+				   struct wpan_dev *wpan_dev,
+				   struct ieee802154_pan_device *peer,
+				   enum nl802154_peer_type type)
+{
+	struct nlattr *nla;
+	void *hdr;
+
+	ASSERT_RTNL();
+
+	hdr = nl802154hdr_put(msg, NETLINK_CB(cb->skb).portid, seq, flags,
+			      NL802154_CMD_LIST_ASSOCIATIONS);
+	if (!hdr)
+		return -ENOBUFS;
+
+	genl_dump_check_consistent(cb, hdr);
+
+	nla = nla_nest_start_noflag(msg, NL802154_ATTR_PEER);
+	if (!nla)
+		goto nla_put_failure;
+
+	if (nla_put_u8(msg, NL802154_DEV_ADDR_ATTR_PEER_TYPE, type))
+		goto nla_put_failure;
+
+	if (nla_put_u8(msg, NL802154_DEV_ADDR_ATTR_MODE, peer->mode))
+		goto nla_put_failure;
+
+	if (nla_put(msg, NL802154_DEV_ADDR_ATTR_SHORT,
+		    IEEE802154_SHORT_ADDR_LEN, &peer->short_addr))
+		goto nla_put_failure;
+
+	if (nla_put(msg, NL802154_DEV_ADDR_ATTR_EXTENDED,
+		    IEEE802154_EXTENDED_ADDR_LEN, &peer->extended_addr))
+		goto nla_put_failure;
+
+	nla_nest_end(msg, nla);
+
+	genlmsg_end(msg, hdr);
+
+	return 0;
+
+ nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+static int nl802154_list_associations(struct sk_buff *skb,
+				      struct netlink_callback *cb)
+{
+	struct cfg802154_registered_device *rdev;
+	struct ieee802154_pan_device *child;
+	struct wpan_dev *wpan_dev;
+	int err;
+
+	err = nl802154_prepare_wpan_dev_dump(skb, cb, &rdev, &wpan_dev);
+	if (err)
+		return err;
+
+	mutex_lock(&wpan_dev->association_lock);
+
+	if (cb->args[2])
+		goto out;
+
+	if (wpan_dev->parent) {
+		err = nl802154_send_peer_info(skb, cb, cb->nlh->nlmsg_seq,
+					      NLM_F_MULTI, rdev, wpan_dev,
+					      wpan_dev->parent,
+					      NL802154_PEER_TYPE_PARENT);
+		if (err < 0)
+			goto out_err;
+	}
+
+	list_for_each_entry(child, &wpan_dev->children, node) {
+		err = nl802154_send_peer_info(skb, cb, cb->nlh->nlmsg_seq,
+					      NLM_F_MULTI, rdev, wpan_dev,
+					      child,
+					      NL802154_PEER_TYPE_CHILD);
+		if (err < 0)
+			goto out_err;
+	}
+
+	cb->args[2] = 1;
+out:
+	err = skb->len;
+out_err:
+	mutex_unlock(&wpan_dev->association_lock);
+
+	nl802154_finish_wpan_dev_dump(rdev);
+
+	return err;
+}
+
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 static const struct nla_policy nl802154_dev_addr_policy[NL802154_DEV_ADDR_ATTR_MAX + 1] = {
 	[NL802154_DEV_ADDR_ATTR_PAN_ID] = { .type = NLA_U16 },
@@ -2759,6 +2938,34 @@ static const struct genl_ops nl802154_ops[] = {
 				  NL802154_FLAG_CHECK_NETDEV_UP |
 				  NL802154_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL802154_CMD_ASSOCIATE,
+		.doit = nl802154_associate,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_NETDEV |
+				  NL802154_FLAG_CHECK_NETDEV_UP |
+				  NL802154_FLAG_NEED_RTNL,
+	},
+	{
+		.cmd = NL802154_CMD_DISASSOCIATE,
+		.doit = nl802154_disassociate,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_NETDEV |
+				  NL802154_FLAG_CHECK_NETDEV_UP |
+				  NL802154_FLAG_NEED_RTNL,
+	},
+	{
+		.cmd = NL802154_CMD_SET_MAX_ASSOCIATIONS,
+		.doit = nl802154_set_max_associations,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_NETDEV |
+				  NL802154_FLAG_NEED_RTNL,
+	},
+	{
+		.cmd = NL802154_CMD_LIST_ASSOCIATIONS,
+		.dumpit = nl802154_list_associations,
+		/* can be retrieved by unprivileged users */
+	},
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 	{
 		.cmd = NL802154_CMD_SET_SEC_PARAMS,
diff --git a/net/ieee802154/pan.c b/net/ieee802154/pan.c
new file mode 100644
index 000000000000..249df7364b3e
--- /dev/null
+++ b/net/ieee802154/pan.c
@@ -0,0 +1,109 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * IEEE 802.15.4 PAN management
+ *
+ * Copyright (C) 2023 Qorvo US, Inc
+ * Authors:
+ *   - David Girault <david.girault@qorvo.com>
+ *   - Miquel Raynal <miquel.raynal@bootlin.com>
+ */
+
+#include <linux/kernel.h>
+#include <net/cfg802154.h>
+#include <net/af_ieee802154.h>
+
+/* Checks whether a device address matches one from the PAN list.
+ * This helper is meant to be used only during PAN management, when we expect
+ * extended addresses to be used.
+ */
+static bool cfg802154_pan_device_is_matching(struct ieee802154_pan_device *pan_dev,
+					     struct ieee802154_addr *ext_dev)
+{
+	if (!pan_dev || !ext_dev)
+		return false;
+
+	if (ext_dev->mode == IEEE802154_ADDR_SHORT)
+		return false;
+
+	return pan_dev->extended_addr == ext_dev->extended_addr;
+}
+
+bool cfg802154_device_is_associated(struct wpan_dev *wpan_dev)
+{
+	bool is_assoc;
+
+	mutex_lock(&wpan_dev->association_lock);
+	is_assoc = !list_empty(&wpan_dev->children) || wpan_dev->parent;
+	mutex_unlock(&wpan_dev->association_lock);
+
+	return is_assoc;
+}
+
+bool cfg802154_device_is_parent(struct wpan_dev *wpan_dev,
+				struct ieee802154_addr *target)
+{
+	lockdep_assert_held(&wpan_dev->association_lock);
+
+	return cfg802154_pan_device_is_matching(wpan_dev->parent, target);
+}
+EXPORT_SYMBOL_GPL(cfg802154_device_is_parent);
+
+struct ieee802154_pan_device *
+cfg802154_device_is_child(struct wpan_dev *wpan_dev,
+			  struct ieee802154_addr *target)
+{
+	struct ieee802154_pan_device *child;
+
+	lockdep_assert_held(&wpan_dev->association_lock);
+
+	list_for_each_entry(child, &wpan_dev->children, node)
+		if (cfg802154_pan_device_is_matching(child, target))
+			return child;
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(cfg802154_device_is_child);
+
+__le16 cfg802154_get_free_short_addr(struct wpan_dev *wpan_dev)
+{
+	struct ieee802154_pan_device *child;
+	__le16 addr;
+
+	lockdep_assert_held(&wpan_dev->association_lock);
+
+	do {
+		get_random_bytes(&addr, 2);
+		if (addr == cpu_to_le16(IEEE802154_ADDR_SHORT_BROADCAST) ||
+		    addr == cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC))
+			continue;
+
+		if (wpan_dev->short_addr == addr)
+			continue;
+
+		if (wpan_dev->parent && wpan_dev->parent->short_addr == addr)
+			continue;
+
+		list_for_each_entry(child, &wpan_dev->children, node)
+			if (child->short_addr == addr)
+				continue;
+
+		break;
+	} while (1);
+
+	return addr;
+}
+EXPORT_SYMBOL_GPL(cfg802154_get_free_short_addr);
+
+unsigned int cfg802154_set_max_associations(struct wpan_dev *wpan_dev,
+					    unsigned int max)
+{
+	unsigned int old_max;
+
+	lockdep_assert_held(&wpan_dev->association_lock);
+
+	old_max = wpan_dev->max_associations;
+	wpan_dev->max_associations = max;
+
+	return old_max;
+}
+EXPORT_SYMBOL_GPL(cfg802154_set_max_associations);
diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h
index 5eaae15c610e..64071ef6f57b 100644
--- a/net/ieee802154/rdev-ops.h
+++ b/net/ieee802154/rdev-ops.h
@@ -265,6 +265,36 @@ static inline int rdev_stop_beacons(struct cfg802154_registered_device *rdev,
 	return ret;
 }
 
+static inline int rdev_associate(struct cfg802154_registered_device *rdev,
+				 struct wpan_dev *wpan_dev,
+				 struct ieee802154_addr *coord)
+{
+	int ret;
+
+	if (!rdev->ops->associate)
+		return -EOPNOTSUPP;
+
+	trace_802154_rdev_associate(&rdev->wpan_phy, wpan_dev, coord);
+	ret = rdev->ops->associate(&rdev->wpan_phy, wpan_dev, coord);
+	trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+	return ret;
+}
+
+static inline int rdev_disassociate(struct cfg802154_registered_device *rdev,
+				    struct wpan_dev *wpan_dev,
+				    struct ieee802154_addr *target)
+{
+	int ret;
+
+	if (!rdev->ops->disassociate)
+		return -EOPNOTSUPP;
+
+	trace_802154_rdev_disassociate(&rdev->wpan_phy, wpan_dev, target);
+	ret = rdev->ops->disassociate(&rdev->wpan_phy, wpan_dev, target);
+	trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+	return ret;
+}
+
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 /* TODO this is already a nl802154, so move into ieee802154 */
 static inline void
diff --git a/net/ieee802154/trace.h b/net/ieee802154/trace.h
index c16db0b326fa..62aa6465253a 100644
--- a/net/ieee802154/trace.h
+++ b/net/ieee802154/trace.h
@@ -356,6 +356,44 @@ DEFINE_EVENT(802154_wdev_template, 802154_rdev_stop_beacons,
 	TP_ARGS(wpan_phy, wpan_dev)
 );
 
+TRACE_EVENT(802154_rdev_associate,
+	TP_PROTO(struct wpan_phy *wpan_phy,
+		 struct wpan_dev *wpan_dev,
+		 struct ieee802154_addr *coord),
+	TP_ARGS(wpan_phy, wpan_dev, coord),
+	TP_STRUCT__entry(
+		WPAN_PHY_ENTRY
+		WPAN_DEV_ENTRY
+		__field(__le64, addr)
+	),
+	TP_fast_assign(
+		WPAN_PHY_ASSIGN;
+		WPAN_DEV_ASSIGN;
+		__entry->addr = coord->extended_addr;
+	),
+	TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT ", associating with: 0x%llx",
+		  WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG, __entry->addr)
+);
+
+TRACE_EVENT(802154_rdev_disassociate,
+	TP_PROTO(struct wpan_phy *wpan_phy,
+		 struct wpan_dev *wpan_dev,
+		 struct ieee802154_addr *target),
+	TP_ARGS(wpan_phy, wpan_dev, target),
+	TP_STRUCT__entry(
+		WPAN_PHY_ENTRY
+		WPAN_DEV_ENTRY
+		__field(__le64, addr)
+	),
+	TP_fast_assign(
+		WPAN_PHY_ASSIGN;
+		WPAN_DEV_ASSIGN;
+		__entry->addr = target->extended_addr;
+	),
+	TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT ", disassociating with: 0x%llx",
+		  WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG, __entry->addr)
+);
+
 TRACE_EVENT(802154_rdev_return_int,
 	TP_PROTO(struct wpan_phy *wpan_phy, int ret),
 	TP_ARGS(wpan_phy, ret),
diff --git a/net/ife/ife.c b/net/ife/ife.c
index 13bbf8cb6a39..be05b690b9ef 100644
--- a/net/ife/ife.c
+++ b/net/ife/ife.c
@@ -82,6 +82,7 @@ void *ife_decode(struct sk_buff *skb, u16 *metalen)
 	if (unlikely(!pskb_may_pull(skb, total_pull)))
 		return NULL;
 
+	ifehdr = (struct ifeheadr *)(skb->data + skb->dev->hard_header_len);
 	skb_set_mac_header(skb, total_pull);
 	__skb_pull(skb, total_pull);
 	*metalen = ifehdrln - IFE_METAHDRLEN;
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index e144a02a6a61..ec36d2ec059e 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -16,8 +16,6 @@ obj-y     := route.o inetpeer.o protocol.o \
 	     inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o \
 	     metrics.o netlink.o nexthop.o udp_tunnel_stub.o
 
-obj-$(CONFIG_BPFILTER) += bpfilter/
-
 obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
 obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
 obj-$(CONFIG_PROC_FS) += proc.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index fb81de10d332..835f4f9d98d2 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1633,6 +1633,7 @@ int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 #endif
 	return -EINVAL;
 }
+EXPORT_SYMBOL(inet_recv_error);
 
 int inet_gro_complete(struct sk_buff *skb, int nhoff)
 {
@@ -1847,9 +1848,7 @@ static __net_init int inet_init_net(struct net *net)
 	/*
 	 * Set defaults for local port range
 	 */
-	seqlock_init(&net->ipv4.ip_local_ports.lock);
-	net->ipv4.ip_local_ports.range[0] =  32768;
-	net->ipv4.ip_local_ports.range[1] =  60999;
+	net->ipv4.ip_local_ports.range = 60999u << 16 | 32768u;
 
 	seqlock_init(&net->ipv4.ping_group_range.lock);
 	/*
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 39dcccf0f174..ae8b15e6896f 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -271,6 +271,74 @@ static int bpf_tcp_ca_validate(void *kdata)
 	return tcp_validate_congestion_control(kdata);
 }
 
+static u32 bpf_tcp_ca_ssthresh(struct sock *sk)
+{
+	return 0;
+}
+
+static void bpf_tcp_ca_cong_avoid(struct sock *sk, u32 ack, u32 acked)
+{
+}
+
+static void bpf_tcp_ca_set_state(struct sock *sk, u8 new_state)
+{
+}
+
+static void bpf_tcp_ca_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
+{
+}
+
+static void bpf_tcp_ca_in_ack_event(struct sock *sk, u32 flags)
+{
+}
+
+static void bpf_tcp_ca_pkts_acked(struct sock *sk, const struct ack_sample *sample)
+{
+}
+
+static u32 bpf_tcp_ca_min_tso_segs(struct sock *sk)
+{
+	return 0;
+}
+
+static void bpf_tcp_ca_cong_control(struct sock *sk, const struct rate_sample *rs)
+{
+}
+
+static u32 bpf_tcp_ca_undo_cwnd(struct sock *sk)
+{
+	return 0;
+}
+
+static u32 bpf_tcp_ca_sndbuf_expand(struct sock *sk)
+{
+	return 0;
+}
+
+static void __bpf_tcp_ca_init(struct sock *sk)
+{
+}
+
+static void __bpf_tcp_ca_release(struct sock *sk)
+{
+}
+
+static struct tcp_congestion_ops __bpf_ops_tcp_congestion_ops = {
+	.ssthresh = bpf_tcp_ca_ssthresh,
+	.cong_avoid = bpf_tcp_ca_cong_avoid,
+	.set_state = bpf_tcp_ca_set_state,
+	.cwnd_event = bpf_tcp_ca_cwnd_event,
+	.in_ack_event = bpf_tcp_ca_in_ack_event,
+	.pkts_acked = bpf_tcp_ca_pkts_acked,
+	.min_tso_segs = bpf_tcp_ca_min_tso_segs,
+	.cong_control = bpf_tcp_ca_cong_control,
+	.undo_cwnd = bpf_tcp_ca_undo_cwnd,
+	.sndbuf_expand = bpf_tcp_ca_sndbuf_expand,
+
+	.init = __bpf_tcp_ca_init,
+	.release = __bpf_tcp_ca_release,
+};
+
 struct bpf_struct_ops bpf_tcp_congestion_ops = {
 	.verifier_ops = &bpf_tcp_ca_verifier_ops,
 	.reg = bpf_tcp_ca_reg,
@@ -281,6 +349,7 @@ struct bpf_struct_ops bpf_tcp_congestion_ops = {
 	.init = bpf_tcp_ca_init,
 	.validate = bpf_tcp_ca_validate,
 	.name = "tcp_congestion_ops",
+	.cfi_stubs = &__bpf_ops_tcp_congestion_ops,
 };
 
 static int __init bpf_tcp_ca_kfunc_init(void)
diff --git a/net/ipv4/bpfilter/Makefile b/net/ipv4/bpfilter/Makefile
deleted file mode 100644
index 00af5305e05a..000000000000
--- a/net/ipv4/bpfilter/Makefile
+++ /dev/null
@@ -1,2 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_BPFILTER) += sockopt.o
diff --git a/net/ipv4/bpfilter/sockopt.c b/net/ipv4/bpfilter/sockopt.c
deleted file mode 100644
index 193bcc2acccc..000000000000
--- a/net/ipv4/bpfilter/sockopt.c
+++ /dev/null
@@ -1,71 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/uaccess.h>
-#include <linux/bpfilter.h>
-#include <uapi/linux/bpf.h>
-#include <linux/wait.h>
-#include <linux/kmod.h>
-#include <linux/fs.h>
-#include <linux/file.h>
-
-struct bpfilter_umh_ops bpfilter_ops;
-EXPORT_SYMBOL_GPL(bpfilter_ops);
-
-static int bpfilter_mbox_request(struct sock *sk, int optname, sockptr_t optval,
-				 unsigned int optlen, bool is_set)
-{
-	int err;
-	mutex_lock(&bpfilter_ops.lock);
-	if (!bpfilter_ops.sockopt) {
-		mutex_unlock(&bpfilter_ops.lock);
-		request_module("bpfilter");
-		mutex_lock(&bpfilter_ops.lock);
-
-		if (!bpfilter_ops.sockopt) {
-			err = -ENOPROTOOPT;
-			goto out;
-		}
-	}
-	if (bpfilter_ops.info.tgid &&
-	    thread_group_exited(bpfilter_ops.info.tgid))
-		umd_cleanup_helper(&bpfilter_ops.info);
-
-	if (!bpfilter_ops.info.tgid) {
-		err = bpfilter_ops.start();
-		if (err)
-			goto out;
-	}
-	err = bpfilter_ops.sockopt(sk, optname, optval, optlen, is_set);
-out:
-	mutex_unlock(&bpfilter_ops.lock);
-	return err;
-}
-
-int bpfilter_ip_set_sockopt(struct sock *sk, int optname, sockptr_t optval,
-			    unsigned int optlen)
-{
-	return bpfilter_mbox_request(sk, optname, optval, optlen, true);
-}
-
-int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval,
-			    int __user *optlen)
-{
-	int len;
-
-	if (get_user(len, optlen))
-		return -EFAULT;
-
-	return bpfilter_mbox_request(sk, optname, USER_SOCKPTR(optval), len,
-				     false);
-}
-
-static int __init bpfilter_sockopt_init(void)
-{
-	mutex_init(&bpfilter_ops.lock);
-	bpfilter_ops.info.tgid = NULL;
-	bpfilter_ops.info.driver_name = "bpfilter_umh";
-
-	return 0;
-}
-device_initcall(bpfilter_sockopt_init);
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 513f475c6a53..5bdd1c016009 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -395,13 +395,13 @@ static int fib_default_rules_init(struct fib_rules_ops *ops)
 {
 	int err;
 
-	err = fib_default_rule_add(ops, 0, RT_TABLE_LOCAL, 0);
+	err = fib_default_rule_add(ops, 0, RT_TABLE_LOCAL);
 	if (err < 0)
 		return err;
-	err = fib_default_rule_add(ops, 0x7FFE, RT_TABLE_MAIN, 0);
+	err = fib_default_rule_add(ops, 0x7FFE, RT_TABLE_MAIN);
 	if (err < 0)
 		return err;
-	err = fib_default_rule_add(ops, 0x7FFF, RT_TABLE_DEFAULT, 0);
+	err = fib_default_rule_add(ops, 0x7FFF, RT_TABLE_DEFAULT);
 	if (err < 0)
 		return err;
 	return 0;
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 9bdfdab906fe..3ff35f811765 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -52,6 +52,7 @@
 #include <linux/if_arp.h>
 #include <linux/proc_fs.h>
 #include <linux/rcupdate.h>
+#include <linux/rcupdate_wait.h>
 #include <linux/skbuff.h>
 #include <linux/netlink.h>
 #include <linux/init.h>
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 76c3ea75b8dd..efeeca2b1328 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -216,8 +216,10 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay)
 	int tv = get_random_u32_below(max_delay);
 
 	im->tm_running = 1;
-	if (!mod_timer(&im->timer, jiffies+tv+2))
-		refcount_inc(&im->refcnt);
+	if (refcount_inc_not_zero(&im->refcnt)) {
+		if (mod_timer(&im->timer, jiffies + tv + 2))
+			ip_ma_put(im);
+	}
 }
 
 static void igmp_gq_start_timer(struct in_device *in_dev)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 394a498c2823..8e2eb1793685 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -117,37 +117,39 @@ bool inet_rcv_saddr_any(const struct sock *sk)
 	return !sk->sk_rcv_saddr;
 }
 
-void inet_get_local_port_range(const struct net *net, int *low, int *high)
-{
-	unsigned int seq;
-
-	do {
-		seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
-
-		*low = net->ipv4.ip_local_ports.range[0];
-		*high = net->ipv4.ip_local_ports.range[1];
-	} while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));
-}
-EXPORT_SYMBOL(inet_get_local_port_range);
-
-void inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high)
+/**
+ *	inet_sk_get_local_port_range - fetch ephemeral ports range
+ *	@sk: socket
+ *	@low: pointer to low port
+ *	@high: pointer to high port
+ *
+ *	Fetch netns port range (/proc/sys/net/ipv4/ip_local_port_range)
+ *	Range can be overridden if socket got IP_LOCAL_PORT_RANGE option.
+ *	Returns true if IP_LOCAL_PORT_RANGE was set on this socket.
+ */
+bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high)
 {
-	const struct inet_sock *inet = inet_sk(sk);
-	const struct net *net = sock_net(sk);
 	int lo, hi, sk_lo, sk_hi;
+	bool local_range = false;
+	u32 sk_range;
 
-	inet_get_local_port_range(net, &lo, &hi);
+	inet_get_local_port_range(sock_net(sk), &lo, &hi);
 
-	sk_lo = inet->local_port_range.lo;
-	sk_hi = inet->local_port_range.hi;
+	sk_range = READ_ONCE(inet_sk(sk)->local_port_range);
+	if (unlikely(sk_range)) {
+		sk_lo = sk_range & 0xffff;
+		sk_hi = sk_range >> 16;
 
-	if (unlikely(lo <= sk_lo && sk_lo <= hi))
-		lo = sk_lo;
-	if (unlikely(lo <= sk_hi && sk_hi <= hi))
-		hi = sk_hi;
+		if (lo <= sk_lo && sk_lo <= hi)
+			lo = sk_lo;
+		if (lo <= sk_hi && sk_hi <= hi)
+			hi = sk_hi;
+		local_range = true;
+	}
 
 	*low = lo;
 	*high = hi;
+	return local_range;
 }
 EXPORT_SYMBOL(inet_sk_get_local_port_range);
 
@@ -157,8 +159,11 @@ static bool inet_use_bhash2_on_bind(const struct sock *sk)
 	if (sk->sk_family == AF_INET6) {
 		int addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr);
 
-		return addr_type != IPV6_ADDR_ANY &&
-			addr_type != IPV6_ADDR_MAPPED;
+		if (addr_type == IPV6_ADDR_ANY)
+			return false;
+
+		if (addr_type != IPV6_ADDR_MAPPED)
+			return true;
 	}
 #endif
 	return sk->sk_rcv_saddr != htonl(INADDR_ANY);
@@ -211,18 +216,9 @@ static bool inet_bhash2_conflict(const struct sock *sk,
 				 bool relax, bool reuseport_cb_ok,
 				 bool reuseport_ok)
 {
-	struct inet_timewait_sock *tw2;
 	struct sock *sk2;
 
-	sk_for_each_bound_bhash2(sk2, &tb2->owners) {
-		if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax,
-					   reuseport_cb_ok, reuseport_ok))
-			return true;
-	}
-
-	twsk_for_each_bound_bhash2(tw2, &tb2->deathrow) {
-		sk2 = (struct sock *)tw2;
-
+	sk_for_each_bound(sk2, &tb2->owners) {
 		if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax,
 					   reuseport_cb_ok, reuseport_ok))
 			return true;
@@ -231,15 +227,20 @@ static bool inet_bhash2_conflict(const struct sock *sk,
 	return false;
 }
 
+#define sk_for_each_bound_bhash(__sk, __tb2, __tb)			\
+	hlist_for_each_entry(__tb2, &(__tb)->bhash2, bhash_node)	\
+		sk_for_each_bound(sk2, &(__tb2)->owners)
+
 /* This should be called only when the tb and tb2 hashbuckets' locks are held */
 static int inet_csk_bind_conflict(const struct sock *sk,
 				  const struct inet_bind_bucket *tb,
 				  const struct inet_bind2_bucket *tb2, /* may be null */
 				  bool relax, bool reuseport_ok)
 {
-	bool reuseport_cb_ok;
-	struct sock_reuseport *reuseport_cb;
 	kuid_t uid = sock_i_uid((struct sock *)sk);
+	struct sock_reuseport *reuseport_cb;
+	bool reuseport_cb_ok;
+	struct sock *sk2;
 
 	rcu_read_lock();
 	reuseport_cb = rcu_dereference(sk->sk_reuseport_cb);
@@ -247,32 +248,29 @@ static int inet_csk_bind_conflict(const struct sock *sk,
 	reuseport_cb_ok = !reuseport_cb || READ_ONCE(reuseport_cb->num_closed_socks);
 	rcu_read_unlock();
 
-	/*
-	 * Unlike other sk lookup places we do not check
+	/* Conflicts with an existing IPV6_ADDR_ANY (if ipv6) or INADDR_ANY (if
+	 * ipv4) should have been checked already. We need to do these two
+	 * checks separately because their spinlocks have to be acquired/released
+	 * independently of each other, to prevent possible deadlocks
+	 */
+	if (inet_use_bhash2_on_bind(sk))
+		return tb2 && inet_bhash2_conflict(sk, tb2, uid, relax,
+						   reuseport_cb_ok, reuseport_ok);
+
+	/* Unlike other sk lookup places we do not check
 	 * for sk_net here, since _all_ the socks listed
 	 * in tb->owners and tb2->owners list belong
 	 * to the same net - the one this bucket belongs to.
 	 */
+	sk_for_each_bound_bhash(sk2, tb2, tb) {
+		if (!inet_bind_conflict(sk, sk2, uid, relax, reuseport_cb_ok, reuseport_ok))
+			continue;
 
-	if (!inet_use_bhash2_on_bind(sk)) {
-		struct sock *sk2;
-
-		sk_for_each_bound(sk2, &tb->owners)
-			if (inet_bind_conflict(sk, sk2, uid, relax,
-					       reuseport_cb_ok, reuseport_ok) &&
-			    inet_rcv_saddr_equal(sk, sk2, true))
-				return true;
-
-		return false;
+		if (inet_rcv_saddr_equal(sk, sk2, true))
+			return true;
 	}
 
-	/* Conflicts with an existing IPV6_ADDR_ANY (if ipv6) or INADDR_ANY (if
-	 * ipv4) should have been checked already. We need to do these two
-	 * checks separately because their spinlocks have to be acquired/released
-	 * independently of each other, to prevent possible deadlocks
-	 */
-	return tb2 && inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok,
-					   reuseport_ok);
+	return false;
 }
 
 /* Determine if there is a bind conflict with an existing IPV6_ADDR_ANY (if ipv6) or
@@ -455,7 +453,7 @@ void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
 	kuid_t uid = sock_i_uid(sk);
 	bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN;
 
-	if (hlist_empty(&tb->owners)) {
+	if (hlist_empty(&tb->bhash2)) {
 		tb->fastreuse = reuse;
 		if (sk->sk_reuseport) {
 			tb->fastreuseport = FASTREUSEPORT_ANY;
@@ -547,7 +545,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 	}
 
 	if (!found_port) {
-		if (!hlist_empty(&tb->owners)) {
+		if (!hlist_empty(&tb->bhash2)) {
 			if (sk->sk_reuse == SK_FORCE_REUSE ||
 			    (tb->fastreuse > 0 && reuse) ||
 			    sk_reuseport_match(tb, sk))
@@ -567,7 +565,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 
 	if (!tb2) {
 		tb2 = inet_bind2_bucket_create(hinfo->bind2_bucket_cachep,
-					       net, head2, port, l3mdev, sk);
+					       net, head2, tb, sk);
 		if (!tb2)
 			goto fail_unlock;
 		bhash2_created = true;
@@ -589,11 +587,10 @@ success:
 
 fail_unlock:
 	if (ret) {
+		if (bhash2_created)
+			inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, tb2);
 		if (bhash_created)
 			inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb);
-		if (bhash2_created)
-			inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep,
-						  tb2);
 	}
 	if (head2_lock_acquired)
 		spin_unlock(&head2->lock);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index f01aee832aab..8e6b6aa0579e 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -1077,10 +1077,94 @@ skip_listen_ht:
 		s_i = num = s_num = 0;
 	}
 
+/* Process a maximum of SKARR_SZ sockets at a time when walking hash buckets
+ * with bh disabled.
+ */
+#define SKARR_SZ 16
+
+	/* Dump bound but inactive (not listening, connecting, etc.) sockets */
+	if (cb->args[0] == 1) {
+		if (!(idiag_states & TCPF_BOUND_INACTIVE))
+			goto skip_bind_ht;
+
+		for (i = s_i; i < hashinfo->bhash_size; i++) {
+			struct inet_bind_hashbucket *ibb;
+			struct inet_bind2_bucket *tb2;
+			struct sock *sk_arr[SKARR_SZ];
+			int num_arr[SKARR_SZ];
+			int idx, accum, res;
+
+resume_bind_walk:
+			num = 0;
+			accum = 0;
+			ibb = &hashinfo->bhash2[i];
+
+			spin_lock_bh(&ibb->lock);
+			inet_bind_bucket_for_each(tb2, &ibb->chain) {
+				if (!net_eq(ib2_net(tb2), net))
+					continue;
+
+				sk_for_each_bound(sk, &tb2->owners) {
+					struct inet_sock *inet = inet_sk(sk);
+
+					if (num < s_num)
+						goto next_bind;
+
+					if (sk->sk_state != TCP_CLOSE ||
+					    !inet->inet_num)
+						goto next_bind;
+
+					if (r->sdiag_family != AF_UNSPEC &&
+					    r->sdiag_family != sk->sk_family)
+						goto next_bind;
+
+					if (!inet_diag_bc_sk(bc, sk))
+						goto next_bind;
+
+					sock_hold(sk);
+					num_arr[accum] = num;
+					sk_arr[accum] = sk;
+					if (++accum == SKARR_SZ)
+						goto pause_bind_walk;
+next_bind:
+					num++;
+				}
+			}
+pause_bind_walk:
+			spin_unlock_bh(&ibb->lock);
+
+			res = 0;
+			for (idx = 0; idx < accum; idx++) {
+				if (res >= 0) {
+					res = inet_sk_diag_fill(sk_arr[idx],
+								NULL, skb, cb,
+								r, NLM_F_MULTI,
+								net_admin);
+					if (res < 0)
+						num = num_arr[idx];
+				}
+				sock_put(sk_arr[idx]);
+			}
+			if (res < 0)
+				goto done;
+
+			cond_resched();
+
+			if (accum == SKARR_SZ) {
+				s_num = num + 1;
+				goto resume_bind_walk;
+			}
+
+			s_num = 0;
+		}
+skip_bind_ht:
+		cb->args[0] = 2;
+		s_i = num = s_num = 0;
+	}
+
 	if (!(idiag_states & ~TCPF_LISTEN))
 		goto out;
 
-#define SKARR_SZ 16
 	for (i = s_i; i <= hashinfo->ehash_mask; i++) {
 		struct inet_ehash_bucket *head = &hashinfo->ehash[i];
 		spinlock_t *lock = inet_ehash_lockp(hashinfo, i);
@@ -1481,5 +1565,6 @@ static void __exit inet_diag_exit(void)
 module_init(inet_diag_init);
 module_exit(inet_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("INET/INET6: socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2 /* AF_INET */);
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 10 /* AF_INET6 */);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 598c1b114d2c..93e9193df544 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -76,7 +76,7 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
 		tb->port      = snum;
 		tb->fastreuse = 0;
 		tb->fastreuseport = 0;
-		INIT_HLIST_HEAD(&tb->owners);
+		INIT_HLIST_HEAD(&tb->bhash2);
 		hlist_add_head(&tb->node, &head->chain);
 	}
 	return tb;
@@ -87,7 +87,7 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
  */
 void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket *tb)
 {
-	if (hlist_empty(&tb->owners)) {
+	if (hlist_empty(&tb->bhash2)) {
 		__hlist_del(&tb->node);
 		kmem_cache_free(cachep, tb);
 	}
@@ -100,47 +100,52 @@ bool inet_bind_bucket_match(const struct inet_bind_bucket *tb, const struct net
 		tb->l3mdev == l3mdev;
 }
 
-static void inet_bind2_bucket_init(struct inet_bind2_bucket *tb,
+static void inet_bind2_bucket_init(struct inet_bind2_bucket *tb2,
 				   struct net *net,
 				   struct inet_bind_hashbucket *head,
-				   unsigned short port, int l3mdev,
+				   struct inet_bind_bucket *tb,
 				   const struct sock *sk)
 {
-	write_pnet(&tb->ib_net, net);
-	tb->l3mdev    = l3mdev;
-	tb->port      = port;
+	write_pnet(&tb2->ib_net, net);
+	tb2->l3mdev = tb->l3mdev;
+	tb2->port = tb->port;
 #if IS_ENABLED(CONFIG_IPV6)
-	tb->family    = sk->sk_family;
-	if (sk->sk_family == AF_INET6)
-		tb->v6_rcv_saddr = sk->sk_v6_rcv_saddr;
-	else
+	BUILD_BUG_ON(USHRT_MAX < (IPV6_ADDR_ANY | IPV6_ADDR_MAPPED));
+	if (sk->sk_family == AF_INET6) {
+		tb2->addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr);
+		tb2->v6_rcv_saddr = sk->sk_v6_rcv_saddr;
+	} else {
+		tb2->addr_type = IPV6_ADDR_MAPPED;
+		ipv6_addr_set_v4mapped(sk->sk_rcv_saddr, &tb2->v6_rcv_saddr);
+	}
+#else
+	tb2->rcv_saddr = sk->sk_rcv_saddr;
 #endif
-		tb->rcv_saddr = sk->sk_rcv_saddr;
-	INIT_HLIST_HEAD(&tb->owners);
-	INIT_HLIST_HEAD(&tb->deathrow);
-	hlist_add_head(&tb->node, &head->chain);
+	INIT_HLIST_HEAD(&tb2->owners);
+	hlist_add_head(&tb2->node, &head->chain);
+	hlist_add_head(&tb2->bhash_node, &tb->bhash2);
 }
 
 struct inet_bind2_bucket *inet_bind2_bucket_create(struct kmem_cache *cachep,
 						   struct net *net,
 						   struct inet_bind_hashbucket *head,
-						   unsigned short port,
-						   int l3mdev,
+						   struct inet_bind_bucket *tb,
 						   const struct sock *sk)
 {
-	struct inet_bind2_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC);
+	struct inet_bind2_bucket *tb2 = kmem_cache_alloc(cachep, GFP_ATOMIC);
 
-	if (tb)
-		inet_bind2_bucket_init(tb, net, head, port, l3mdev, sk);
+	if (tb2)
+		inet_bind2_bucket_init(tb2, net, head, tb, sk);
 
-	return tb;
+	return tb2;
 }
 
 /* Caller must hold hashbucket lock for this tb with local BH disabled */
 void inet_bind2_bucket_destroy(struct kmem_cache *cachep, struct inet_bind2_bucket *tb)
 {
-	if (hlist_empty(&tb->owners) && hlist_empty(&tb->deathrow)) {
+	if (hlist_empty(&tb->owners)) {
 		__hlist_del(&tb->node);
+		__hlist_del(&tb->bhash_node);
 		kmem_cache_free(cachep, tb);
 	}
 }
@@ -149,18 +154,11 @@ static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2,
 					 const struct sock *sk)
 {
 #if IS_ENABLED(CONFIG_IPV6)
-	if (sk->sk_family != tb2->family) {
-		if (sk->sk_family == AF_INET)
-			return ipv6_addr_v4mapped(&tb2->v6_rcv_saddr) &&
-				tb2->v6_rcv_saddr.s6_addr32[3] == sk->sk_rcv_saddr;
-
-		return ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr) &&
-			sk->sk_v6_rcv_saddr.s6_addr32[3] == tb2->rcv_saddr;
-	}
-
 	if (sk->sk_family == AF_INET6)
-		return ipv6_addr_equal(&tb2->v6_rcv_saddr,
-				       &sk->sk_v6_rcv_saddr);
+		return ipv6_addr_equal(&tb2->v6_rcv_saddr, &sk->sk_v6_rcv_saddr);
+
+	if (tb2->addr_type != IPV6_ADDR_MAPPED)
+		return false;
 #endif
 	return tb2->rcv_saddr == sk->sk_rcv_saddr;
 }
@@ -169,10 +167,9 @@ void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
 		    struct inet_bind2_bucket *tb2, unsigned short port)
 {
 	inet_sk(sk)->inet_num = port;
-	sk_add_bind_node(sk, &tb->owners);
 	inet_csk(sk)->icsk_bind_hash = tb;
-	sk_add_bind2_node(sk, &tb2->owners);
 	inet_csk(sk)->icsk_bind2_hash = tb2;
+	sk_add_bind_node(sk, &tb2->owners);
 }
 
 /*
@@ -192,21 +189,20 @@ static void __inet_put_port(struct sock *sk)
 
 	spin_lock(&head->lock);
 	tb = inet_csk(sk)->icsk_bind_hash;
-	__sk_del_bind_node(sk);
 	inet_csk(sk)->icsk_bind_hash = NULL;
 	inet_sk(sk)->inet_num = 0;
-	inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
 
 	spin_lock(&head2->lock);
 	if (inet_csk(sk)->icsk_bind2_hash) {
 		struct inet_bind2_bucket *tb2 = inet_csk(sk)->icsk_bind2_hash;
 
-		__sk_del_bind2_node(sk);
+		__sk_del_bind_node(sk);
 		inet_csk(sk)->icsk_bind2_hash = NULL;
 		inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2);
 	}
 	spin_unlock(&head2->lock);
 
+	inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
 	spin_unlock(&head->lock);
 }
 
@@ -275,8 +271,7 @@ bhash2_find:
 		tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, child);
 		if (!tb2) {
 			tb2 = inet_bind2_bucket_create(table->bind2_bucket_cachep,
-						       net, head2, port,
-						       l3mdev, child);
+						       net, head2, tb, child);
 			if (!tb2)
 				goto error;
 		}
@@ -751,12 +746,12 @@ int __inet_hash(struct sock *sk, struct sock *osk)
 		if (err)
 			goto unlock;
 	}
+	sock_set_flag(sk, SOCK_RCU_FREE);
 	if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
 		sk->sk_family == AF_INET6)
 		__sk_nulls_add_node_tail_rcu(sk, &ilb2->nulls_head);
 	else
 		__sk_nulls_add_node_rcu(sk, &ilb2->nulls_head);
-	sock_set_flag(sk, SOCK_RCU_FREE);
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
 unlock:
 	spin_unlock(&ilb2->lock);
@@ -836,16 +831,15 @@ bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const
 		return false;
 
 #if IS_ENABLED(CONFIG_IPV6)
-	if (sk->sk_family != tb->family) {
-		if (sk->sk_family == AF_INET)
-			return ipv6_addr_any(&tb->v6_rcv_saddr) ||
-				ipv6_addr_v4mapped_any(&tb->v6_rcv_saddr);
+	if (tb->addr_type == IPV6_ADDR_ANY)
+		return true;
 
+	if (tb->addr_type != IPV6_ADDR_MAPPED)
 		return false;
-	}
 
-	if (sk->sk_family == AF_INET6)
-		return ipv6_addr_any(&tb->v6_rcv_saddr);
+	if (sk->sk_family == AF_INET6 &&
+	    !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+		return false;
 #endif
 	return tb->rcv_saddr == 0;
 }
@@ -942,7 +936,7 @@ static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family,
 	spin_lock_bh(&head->lock);
 
 	spin_lock(&head2->lock);
-	__sk_del_bind2_node(sk);
+	__sk_del_bind_node(sk);
 	inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, inet_csk(sk)->icsk_bind2_hash);
 	spin_unlock(&head2->lock);
 
@@ -957,10 +951,10 @@ static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family,
 	tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk);
 	if (!tb2) {
 		tb2 = new_tb2;
-		inet_bind2_bucket_init(tb2, net, head2, port, l3mdev, sk);
+		inet_bind2_bucket_init(tb2, net, head2, inet_csk(sk)->icsk_bind_hash, sk);
 	}
-	sk_add_bind2_node(sk, &tb2->owners);
 	inet_csk(sk)->icsk_bind2_hash = tb2;
+	sk_add_bind_node(sk, &tb2->owners);
 	spin_unlock(&head2->lock);
 
 	spin_unlock_bh(&head->lock);
@@ -1012,7 +1006,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 	bool tb_created = false;
 	u32 remaining, offset;
 	int ret, i, low, high;
-	int l3mdev;
+	bool local_ports;
+	int step, l3mdev;
 	u32 index;
 
 	if (port) {
@@ -1024,10 +1019,12 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 
 	l3mdev = inet_sk_bound_l3mdev(sk);
 
-	inet_sk_get_local_port_range(sk, &low, &high);
+	local_ports = inet_sk_get_local_port_range(sk, &low, &high);
+	step = local_ports ? 1 : 2;
+
 	high++; /* [32768, 60999] -> [32768, 61000[ */
 	remaining = high - low;
-	if (likely(remaining > 1))
+	if (!local_ports && remaining > 1)
 		remaining &= ~1U;
 
 	get_random_sleepable_once(table_perturb,
@@ -1040,10 +1037,11 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 	/* In first pass we try ports of @low parity.
 	 * inet_csk_get_port() does the opposite choice.
 	 */
-	offset &= ~1U;
+	if (!local_ports)
+		offset &= ~1U;
 other_parity_scan:
 	port = low + offset;
-	for (i = 0; i < remaining; i += 2, port += 2) {
+	for (i = 0; i < remaining; i += step, port += step) {
 		if (unlikely(port >= high))
 			port -= remaining;
 		if (inet_is_local_reserved_port(net, port))
@@ -1060,7 +1058,7 @@ other_parity_scan:
 				if (tb->fastreuse >= 0 ||
 				    tb->fastreuseport >= 0)
 					goto next_port;
-				WARN_ON(hlist_empty(&tb->owners));
+				WARN_ON(hlist_empty(&tb->bhash2));
 				if (!check_established(death_row, sk,
 						       port, &tw))
 					goto ok;
@@ -1083,10 +1081,11 @@ next_port:
 		cond_resched();
 	}
 
-	offset++;
-	if ((offset & 1) && remaining > 1)
-		goto other_parity_scan;
-
+	if (!local_ports) {
+		offset++;
+		if ((offset & 1) && remaining > 1)
+			goto other_parity_scan;
+	}
 	return -EADDRNOTAVAIL;
 
 ok:
@@ -1099,7 +1098,7 @@ ok:
 	tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk);
 	if (!tb2) {
 		tb2 = inet_bind2_bucket_create(hinfo->bind2_bucket_cachep, net,
-					       head2, port, l3mdev, sk);
+					       head2, tb, sk);
 		if (!tb2)
 			goto error;
 	}
@@ -1109,8 +1108,8 @@ ok:
 	 * on low contention the randomness is maximal and on high contention
 	 * it may be inexistent.
 	 */
-	i = max_t(int, i, get_random_u32_below(8) * 2);
-	WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2);
+	i = max_t(int, i, get_random_u32_below(8) * step);
+	WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + step);
 
 	/* Head lock still held and bh's disabled */
 	inet_bind_hash(sk, tb, tb2, port);
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index dd37a5bf6881..5befa4de5b24 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -35,13 +35,11 @@ void inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
 	if (!tb)
 		return;
 
-	__hlist_del(&tw->tw_bind_node);
+	__sk_del_bind_node((struct sock *)tw);
 	tw->tw_tb = NULL;
-	inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
-
-	__hlist_del(&tw->tw_bind2_node);
 	tw->tw_tb2 = NULL;
 	inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2);
+	inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
 
 	__sock_put((struct sock *)tw);
 }
@@ -94,18 +92,6 @@ static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
 	hlist_nulls_add_head_rcu(&tw->tw_node, list);
 }
 
-static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
-				    struct hlist_head *list)
-{
-	hlist_add_head(&tw->tw_bind_node, list);
-}
-
-static void inet_twsk_add_bind2_node(struct inet_timewait_sock *tw,
-				     struct hlist_head *list)
-{
-	hlist_add_head(&tw->tw_bind2_node, list);
-}
-
 /*
  * Enter the time wait state. This is called with locally disabled BH.
  * Essentially we whip up a timewait bucket, copy the relevant info into it
@@ -133,11 +119,10 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 
 	tw->tw_tb = icsk->icsk_bind_hash;
 	WARN_ON(!icsk->icsk_bind_hash);
-	inet_twsk_add_bind_node(tw, &tw->tw_tb->owners);
 
 	tw->tw_tb2 = icsk->icsk_bind2_hash;
 	WARN_ON(!icsk->icsk_bind2_hash);
-	inet_twsk_add_bind2_node(tw, &tw->tw_tb2->deathrow);
+	sk_add_bind_node((struct sock *)tw, &tw->tw_tb2->owners);
 
 	spin_unlock(&bhead2->lock);
 	spin_unlock(&bhead->lock);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 22a26d1d29a0..5169c3c72cff 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -635,15 +635,18 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
 	}
 
 	if (dev->header_ops) {
+		int pull_len = tunnel->hlen + sizeof(struct iphdr);
+
 		if (skb_cow_head(skb, 0))
 			goto free_skb;
 
 		tnl_params = (const struct iphdr *)skb->data;
 
-		/* Pull skb since ip_tunnel_xmit() needs skb->data pointing
-		 * to gre header.
-		 */
-		skb_pull(skb, tunnel->hlen + sizeof(struct iphdr));
+		if (!pskb_network_may_pull(skb, pull_len))
+			goto free_skb;
+
+		/* ip_tunnel_xmit() needs skb->data pointing to gre header. */
+		skb_pull(skb, pull_len);
 		skb_reset_mac_header(skb);
 
 		if (skb->ip_summed == CHECKSUM_PARTIAL &&
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 2efc53526a38..7aa9dc0e6760 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -47,8 +47,6 @@
 #include <linux/errqueue.h>
 #include <linux/uaccess.h>
 
-#include <linux/bpfilter.h>
-
 /*
  *	SOL_IP control messages.
  */
@@ -775,7 +773,7 @@ static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen)
 
 	if (optlen < GROUP_FILTER_SIZE(0))
 		return -EINVAL;
-	if (optlen > READ_ONCE(sysctl_optmem_max))
+	if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max))
 		return -ENOBUFS;
 
 	gsf = memdup_sockptr(optval, optlen);
@@ -811,7 +809,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
 
 	if (optlen < size0)
 		return -EINVAL;
-	if (optlen > READ_ONCE(sysctl_optmem_max) - 4)
+	if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max) - 4)
 		return -ENOBUFS;
 
 	p = kmalloc(optlen + 4, GFP_KERNEL);
@@ -1055,6 +1053,19 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 	case IP_TOS:	/* This sets both TOS and Precedence */
 		ip_sock_set_tos(sk, val);
 		return 0;
+	case IP_LOCAL_PORT_RANGE:
+	{
+		u16 lo = val;
+		u16 hi = val >> 16;
+
+		if (optlen != sizeof(u32))
+			return -EINVAL;
+		if (lo != 0 && hi != 0 && lo > hi)
+			return -EINVAL;
+
+		WRITE_ONCE(inet->local_port_range, val);
+		return 0;
+	}
 	}
 
 	err = 0;
@@ -1241,7 +1252,7 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 
 		if (optlen < IP_MSFILTER_SIZE(0))
 			goto e_inval;
-		if (optlen > READ_ONCE(sysctl_optmem_max)) {
+		if (optlen > READ_ONCE(net->core.sysctl_optmem_max)) {
 			err = -ENOBUFS;
 			break;
 		}
@@ -1332,20 +1343,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 		err = xfrm_user_policy(sk, optname, optval, optlen);
 		break;
 
-	case IP_LOCAL_PORT_RANGE:
-	{
-		const __u16 lo = val;
-		const __u16 hi = val >> 16;
-
-		if (optlen != sizeof(__u32))
-			goto e_inval;
-		if (lo != 0 && hi != 0 && lo > hi)
-			goto e_inval;
-
-		inet->local_port_range.lo = lo;
-		inet->local_port_range.hi = hi;
-		break;
-	}
 	default:
 		err = -ENOPROTOOPT;
 		break;
@@ -1412,11 +1409,6 @@ int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		return -ENOPROTOOPT;
 
 	err = do_ip_setsockopt(sk, level, optname, optval, optlen);
-#if IS_ENABLED(CONFIG_BPFILTER_UMH)
-	if (optname >= BPFILTER_IPT_SO_SET_REPLACE &&
-	    optname < BPFILTER_IPT_SET_MAX)
-		err = bpfilter_ip_set_sockopt(sk, optname, optval, optlen);
-#endif
 #ifdef CONFIG_NETFILTER
 	/* we need to exclude all possible ENOPROTOOPTs except default case */
 	if (err == -ENOPROTOOPT && optname != IP_HDRINCL &&
@@ -1692,6 +1684,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 			return -EFAULT;
 		return 0;
 	}
+	case IP_LOCAL_PORT_RANGE:
+		val = READ_ONCE(inet->local_port_range);
+		goto copyval;
 	}
 
 	if (needs_rtnl)
@@ -1721,9 +1716,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 		else
 			err = ip_get_mcast_msfilter(sk, optval, optlen, len);
 		goto out;
-	case IP_LOCAL_PORT_RANGE:
-		val = inet->local_port_range.hi << 16 | inet->local_port_range.lo;
-		break;
 	case IP_PROTOCOL:
 		val = inet_sk(sk)->inet_num;
 		break;
@@ -1764,11 +1756,6 @@ int ip_getsockopt(struct sock *sk, int level,
 	err = do_ip_getsockopt(sk, level, optname,
 			       USER_SOCKPTR(optval), USER_SOCKPTR(optlen));
 
-#if IS_ENABLED(CONFIG_BPFILTER_UMH)
-	if (optname >= BPFILTER_IPT_SO_GET_INFO &&
-	    optname < BPFILTER_IPT_GET_MAX)
-		err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen);
-#endif
 #ifdef CONFIG_NETFILTER
 	/* we need to exclude all possible ENOPROTOOPTs except default case */
 	if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS &&
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 9e222a57bc2b..9d6f59531b3a 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -253,7 +253,7 @@ static int __net_init ipmr_rules_init(struct net *net)
 		goto err1;
 	}
 
-	err = fib_default_rule_add(ops, 0x7fff, RT_TABLE_DEFAULT, 0);
+	err = fib_default_rule_add(ops, 0x7fff, RT_TABLE_DEFAULT);
 	if (err < 0)
 		goto err2;
 
@@ -1025,6 +1025,10 @@ static int ipmr_cache_report(const struct mr_table *mrt,
 	struct sk_buff *skb;
 	int ret;
 
+	mroute_sk = rcu_dereference(mrt->mroute_sk);
+	if (!mroute_sk)
+		return -EINVAL;
+
 	if (assert == IGMPMSG_WHOLEPKT || assert == IGMPMSG_WRVIFWHOLE)
 		skb = skb_realloc_headroom(pkt, sizeof(struct iphdr));
 	else
@@ -1069,7 +1073,8 @@ static int ipmr_cache_report(const struct mr_table *mrt,
 		msg = (struct igmpmsg *)skb_network_header(skb);
 		msg->im_vif = vifi;
 		msg->im_vif_hi = vifi >> 8;
-		skb_dst_set(skb, dst_clone(skb_dst(pkt)));
+		ipv4_pktinfo_prepare(mroute_sk, pkt);
+		memcpy(skb->cb, pkt->cb, sizeof(skb->cb));
 		/* Add our header */
 		igmp = skb_put(skb, sizeof(struct igmphdr));
 		igmp->type = assert;
@@ -1079,12 +1084,6 @@ static int ipmr_cache_report(const struct mr_table *mrt,
 		skb->transport_header = skb->network_header;
 	}
 
-	mroute_sk = rcu_dereference(mrt->mroute_sk);
-	if (!mroute_sk) {
-		kfree_skb(skb);
-		return -EINVAL;
-	}
-
 	igmpmsg_netlink_event(mrt, skb);
 
 	/* Deliver to mrouted */
diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c
index 63a40e4b678f..fe2140c8375c 100644
--- a/net/ipv4/raw_diag.c
+++ b/net/ipv4/raw_diag.c
@@ -257,5 +257,6 @@ static void __exit raw_diag_exit(void)
 module_init(raw_diag_init);
 module_exit(raw_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("RAW socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-255 /* AF_INET - IPPROTO_RAW */);
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 10-255 /* AF_INET6 - IPPROTO_RAW */);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 3290a4442b4a..16615d107cf0 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -780,7 +780,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 			goto reject_redirect;
 	}
 
-	n = __ipv4_neigh_lookup(rt->dst.dev, new_gw);
+	n = __ipv4_neigh_lookup(rt->dst.dev, (__force u32)new_gw);
 	if (!n)
 		n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev);
 	if (!IS_ERR(n)) {
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index d37282c06e3d..61f1c96cfe63 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -189,12 +189,14 @@ __u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mssp)
  * Check if a ack sequence number is a valid syncookie.
  * Return the decoded mss if it is, or 0 if not.
  */
-int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
-		      u32 cookie)
+int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th)
 {
+	__u32 cookie = ntohl(th->ack_seq) - 1;
 	__u32 seq = ntohl(th->seq) - 1;
-	__u32 mssind = check_tcp_syn_cookie(cookie, iph->saddr, iph->daddr,
-					    th->source, th->dest, seq);
+	__u32 mssind;
+
+	mssind = check_tcp_syn_cookie(cookie, iph->saddr, iph->daddr,
+				      th->source, th->dest, seq);
 
 	return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0;
 }
@@ -202,7 +204,7 @@ EXPORT_SYMBOL_GPL(__cookie_v4_check);
 
 struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 				 struct request_sock *req,
-				 struct dst_entry *dst, u32 tsoff)
+				 struct dst_entry *dst)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct sock *child;
@@ -212,7 +214,6 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 						 NULL, &own_req);
 	if (child) {
 		refcount_set(&req->rsk_refcnt, 1);
-		tcp_sk(child)->tsoffset = tsoff;
 		sock_rps_save_rxhash(child, skb);
 
 		if (rsk_drop_req(req)) {
@@ -269,26 +270,46 @@ bool cookie_timestamp_decode(const struct net *net,
 }
 EXPORT_SYMBOL(cookie_timestamp_decode);
 
-bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt,
-		   const struct net *net, const struct dst_entry *dst)
+static int cookie_tcp_reqsk_init(struct sock *sk, struct sk_buff *skb,
+				 struct request_sock *req)
 {
-	bool ecn_ok = tcp_opt->rcv_tsecr & TS_OPT_ECN;
+	struct inet_request_sock *ireq = inet_rsk(req);
+	struct tcp_request_sock *treq = tcp_rsk(req);
+	const struct tcphdr *th = tcp_hdr(skb);
 
-	if (!ecn_ok)
-		return false;
+	req->num_retrans = 0;
 
-	if (READ_ONCE(net->ipv4.sysctl_tcp_ecn))
-		return true;
+	ireq->ir_num = ntohs(th->dest);
+	ireq->ir_rmt_port = th->source;
+	ireq->ir_iif = inet_request_bound_dev_if(sk, skb);
+	ireq->ir_mark = inet_request_mark(sk, skb);
+
+	if (IS_ENABLED(CONFIG_SMC))
+		ireq->smc_ok = 0;
 
-	return dst_feature(dst, RTAX_FEATURE_ECN);
+	treq->snt_synack = 0;
+	treq->tfo_listener = false;
+	treq->txhash = net_tx_rndhash();
+	treq->rcv_isn = ntohl(th->seq) - 1;
+	treq->snt_isn = ntohl(th->ack_seq) - 1;
+	treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield;
+	treq->req_usec_ts = false;
+
+#if IS_ENABLED(CONFIG_MPTCP)
+	treq->is_mptcp = sk_is_mptcp(sk);
+	if (treq->is_mptcp)
+		return mptcp_subflow_init_cookie_req(req, sk, skb);
+#endif
+
+	return 0;
 }
-EXPORT_SYMBOL(cookie_ecn_ok);
 
 struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
-					    const struct tcp_request_sock_ops *af_ops,
-					    struct sock *sk,
-					    struct sk_buff *skb)
+					    struct sock *sk, struct sk_buff *skb,
+					    struct tcp_options_received *tcp_opt,
+					    int mss, u32 tsoff)
 {
+	struct inet_request_sock *ireq;
 	struct tcp_request_sock *treq;
 	struct request_sock *req;
 
@@ -300,126 +321,109 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
 	if (!req)
 		return NULL;
 
-	treq = tcp_rsk(req);
+	if (cookie_tcp_reqsk_init(sk, skb, req)) {
+		reqsk_free(req);
+		return NULL;
+	}
 
-	/* treq->af_specific might be used to perform TCP_MD5 lookup */
-	treq->af_specific = af_ops;
+	ireq = inet_rsk(req);
+	treq = tcp_rsk(req);
 
-	treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield;
-	treq->req_usec_ts = false;
+	req->mss = mss;
+	req->ts_recent = tcp_opt->saw_tstamp ? tcp_opt->rcv_tsval : 0;
 
-#if IS_ENABLED(CONFIG_MPTCP)
-	treq->is_mptcp = sk_is_mptcp(sk);
-	if (treq->is_mptcp) {
-		int err = mptcp_subflow_init_cookie_req(req, sk, skb);
+	ireq->snd_wscale = tcp_opt->snd_wscale;
+	ireq->tstamp_ok = tcp_opt->saw_tstamp;
+	ireq->sack_ok = tcp_opt->sack_ok;
+	ireq->wscale_ok = tcp_opt->wscale_ok;
+	ireq->ecn_ok = !!(tcp_opt->rcv_tsecr & TS_OPT_ECN);
 
-		if (err) {
-			reqsk_free(req);
-			return NULL;
-		}
-	}
-#endif
+	treq->ts_off = tsoff;
 
 	return req;
 }
 EXPORT_SYMBOL_GPL(cookie_tcp_reqsk_alloc);
 
-/* On input, sk is a listener.
- * Output is listener if incoming packet would not create a child
- *           NULL if memory could not be allocated.
- */
-struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
+static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk,
+					     struct sk_buff *skb)
 {
-	struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
 	struct tcp_options_received tcp_opt;
-	struct inet_request_sock *ireq;
-	struct tcp_request_sock *treq;
-	struct tcp_sock *tp = tcp_sk(sk);
-	const struct tcphdr *th = tcp_hdr(skb);
-	__u32 cookie = ntohl(th->ack_seq) - 1;
-	struct sock *ret = sk;
-	struct request_sock *req;
-	int full_space, mss;
-	struct rtable *rt;
-	__u8 rcv_wscale;
-	struct flowi4 fl4;
 	u32 tsoff = 0;
-	int l3index;
-
-	if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) ||
-	    !th->ack || th->rst)
-		goto out;
+	int mss;
 
 	if (tcp_synq_no_recent_overflow(sk))
 		goto out;
 
-	mss = __cookie_v4_check(ip_hdr(skb), th, cookie);
-	if (mss == 0) {
-		__NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESFAILED);
+	mss = __cookie_v4_check(ip_hdr(skb), tcp_hdr(skb));
+	if (!mss) {
+		__NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESFAILED);
 		goto out;
 	}
 
-	__NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV);
+	__NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESRECV);
 
 	/* check for timestamp cookie support */
 	memset(&tcp_opt, 0, sizeof(tcp_opt));
-	tcp_parse_options(sock_net(sk), skb, &tcp_opt, 0, NULL);
+	tcp_parse_options(net, skb, &tcp_opt, 0, NULL);
 
 	if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) {
-		tsoff = secure_tcp_ts_off(sock_net(sk),
+		tsoff = secure_tcp_ts_off(net,
 					  ip_hdr(skb)->daddr,
 					  ip_hdr(skb)->saddr);
 		tcp_opt.rcv_tsecr -= tsoff;
 	}
 
-	if (!cookie_timestamp_decode(sock_net(sk), &tcp_opt))
+	if (!cookie_timestamp_decode(net, &tcp_opt))
 		goto out;
 
-	ret = NULL;
-	req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops,
-				     &tcp_request_sock_ipv4_ops, sk, skb);
-	if (!req)
+	return cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, sk, skb,
+				      &tcp_opt, mss, tsoff);
+out:
+	return ERR_PTR(-EINVAL);
+}
+
+/* On input, sk is a listener.
+ * Output is listener if incoming packet would not create a child
+ *           NULL if memory could not be allocated.
+ */
+struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
+{
+	struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
+	const struct tcphdr *th = tcp_hdr(skb);
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct inet_request_sock *ireq;
+	struct net *net = sock_net(sk);
+	struct request_sock *req;
+	struct sock *ret = sk;
+	struct flowi4 fl4;
+	struct rtable *rt;
+	__u8 rcv_wscale;
+	int full_space;
+
+	if (!READ_ONCE(net->ipv4.sysctl_tcp_syncookies) ||
+	    !th->ack || th->rst)
 		goto out;
 
+	req = cookie_tcp_check(net, sk, skb);
+	if (IS_ERR(req))
+		goto out;
+	if (!req)
+		goto out_drop;
+
 	ireq = inet_rsk(req);
-	treq = tcp_rsk(req);
-	treq->rcv_isn		= ntohl(th->seq) - 1;
-	treq->snt_isn		= cookie;
-	treq->ts_off		= 0;
-	treq->txhash		= net_tx_rndhash();
-	req->mss		= mss;
-	ireq->ir_num		= ntohs(th->dest);
-	ireq->ir_rmt_port	= th->source;
+
 	sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
 	sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
-	ireq->ir_mark		= inet_request_mark(sk, skb);
-	ireq->snd_wscale	= tcp_opt.snd_wscale;
-	ireq->sack_ok		= tcp_opt.sack_ok;
-	ireq->wscale_ok		= tcp_opt.wscale_ok;
-	ireq->tstamp_ok		= tcp_opt.saw_tstamp;
-	req->ts_recent		= tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
-	treq->snt_synack	= 0;
-	treq->tfo_listener	= false;
-
-	if (IS_ENABLED(CONFIG_SMC))
-		ireq->smc_ok = 0;
-
-	ireq->ir_iif = inet_request_bound_dev_if(sk, skb);
-
-	l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif);
-	tcp_ao_syncookie(sk, skb, treq, AF_INET, l3index);
 
 	/* We throwed the options of the initial SYN away, so we hope
 	 * the ACK carries the same options again (see RFC1122 4.2.3.8)
 	 */
-	RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(sock_net(sk), skb));
+	RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(net, skb));
 
-	if (security_inet_conn_request(sk, skb, req)) {
-		reqsk_free(req);
-		goto out;
-	}
+	if (security_inet_conn_request(sk, skb, req))
+		goto out_free;
 
-	req->num_retrans = 0;
+	tcp_ao_syncookie(sk, skb, req, AF_INET);
 
 	/*
 	 * We need to lookup the route here to get at the correct
@@ -433,11 +437,9 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 			   opt->srr ? opt->faddr : ireq->ir_rmt_addr,
 			   ireq->ir_loc_addr, th->source, th->dest, sk->sk_uid);
 	security_req_classify_flow(req, flowi4_to_flowi_common(&fl4));
-	rt = ip_route_output_key(sock_net(sk), &fl4);
-	if (IS_ERR(rt)) {
-		reqsk_free(req);
-		goto out;
-	}
+	rt = ip_route_output_key(net, &fl4);
+	if (IS_ERR(rt))
+		goto out_free;
 
 	/* Try to redo what tcp_v4_send_synack did. */
 	req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW);
@@ -453,13 +455,18 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 				  dst_metric(&rt->dst, RTAX_INITRWND));
 
 	ireq->rcv_wscale  = rcv_wscale;
-	ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), &rt->dst);
+	ireq->ecn_ok &= cookie_ecn_ok(net, &rt->dst);
 
-	ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst, tsoff);
+	ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst);
 	/* ip_queue_xmit() depends on our flow being setup
 	 * Normal sockets get it right from inet_csk_route_child_sock()
 	 */
 	if (ret)
 		inet_sk(ret)->cork.fl.u.ip4 = fl4;
-out:	return ret;
+out:
+	return ret;
+out_free:
+	reqsk_free(req);
+out_drop:
+	return NULL;
 }
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index f63a545a7374..7e4f16a7dcc1 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -50,26 +50,22 @@ static int tcp_plb_max_cong_thresh = 256;
 static int sysctl_tcp_low_latency __read_mostly;
 
 /* Update system visible IP port range */
-static void set_local_port_range(struct net *net, int range[2])
+static void set_local_port_range(struct net *net, unsigned int low, unsigned int high)
 {
-	bool same_parity = !((range[0] ^ range[1]) & 1);
+	bool same_parity = !((low ^ high) & 1);
 
-	write_seqlock_bh(&net->ipv4.ip_local_ports.lock);
 	if (same_parity && !net->ipv4.ip_local_ports.warned) {
 		net->ipv4.ip_local_ports.warned = true;
 		pr_err_ratelimited("ip_local_port_range: prefer different parity for start/end values.\n");
 	}
-	net->ipv4.ip_local_ports.range[0] = range[0];
-	net->ipv4.ip_local_ports.range[1] = range[1];
-	write_sequnlock_bh(&net->ipv4.ip_local_ports.lock);
+	WRITE_ONCE(net->ipv4.ip_local_ports.range, high << 16 | low);
 }
 
 /* Validate changes from /proc interface. */
 static int ipv4_local_port_range(struct ctl_table *table, int write,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {
-	struct net *net =
-		container_of(table->data, struct net, ipv4.ip_local_ports.range);
+	struct net *net = table->data;
 	int ret;
 	int range[2];
 	struct ctl_table tmp = {
@@ -93,7 +89,7 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
 		    (range[0] < READ_ONCE(net->ipv4.sysctl_ip_prot_sock)))
 			ret = -EINVAL;
 		else
-			set_local_port_range(net, range);
+			set_local_port_range(net, range[0], range[1]);
 	}
 
 	return ret;
@@ -733,8 +729,8 @@ static struct ctl_table ipv4_net_table[] = {
 	},
 	{
 		.procname	= "ip_local_port_range",
-		.maxlen		= sizeof(init_net.ipv4.ip_local_ports.range),
-		.data		= &init_net.ipv4.ip_local_ports.range,
+		.maxlen		= 0,
+		.data		= &init_net,
 		.mode		= 0644,
 		.proc_handler	= ipv4_local_port_range,
 	},
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 53bcc17c91e4..1baa484d2190 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1849,7 +1849,6 @@ static int receive_fallback_to_copy(struct sock *sk,
 {
 	unsigned long copy_address = (unsigned long)zc->copybuf_address;
 	struct msghdr msg = {};
-	struct iovec iov;
 	int err;
 
 	zc->length = 0;
@@ -1858,8 +1857,8 @@ static int receive_fallback_to_copy(struct sock *sk,
 	if (copy_address != zc->copybuf_address)
 		return -EINVAL;
 
-	err = import_single_range(ITER_DEST, (void __user *)copy_address,
-				  inq, &iov, &msg.msg_iter);
+	err = import_ubuf(ITER_DEST, (void __user *)copy_address, inq,
+			  &msg.msg_iter);
 	if (err)
 		return err;
 
@@ -1886,14 +1885,13 @@ static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc,
 {
 	unsigned long copy_address = (unsigned long)zc->copybuf_address;
 	struct msghdr msg = {};
-	struct iovec iov;
 	int err;
 
 	if (copy_address != zc->copybuf_address)
 		return -EINVAL;
 
-	err = import_single_range(ITER_DEST, (void __user *)copy_address,
-				  copylen, &iov, &msg.msg_iter);
+	err = import_ubuf(ITER_DEST, (void __user *)copy_address, copylen,
+			  &msg.msg_iter);
 	if (err)
 		return err;
 	err = skb_copy_datagram_msg(skb, *offset, &msg, copylen);
@@ -2605,6 +2603,7 @@ void tcp_set_state(struct sock *sk, int state)
 	BUILD_BUG_ON((int)BPF_TCP_LISTEN != (int)TCP_LISTEN);
 	BUILD_BUG_ON((int)BPF_TCP_CLOSING != (int)TCP_CLOSING);
 	BUILD_BUG_ON((int)BPF_TCP_NEW_SYN_RECV != (int)TCP_NEW_SYN_RECV);
+	BUILD_BUG_ON((int)BPF_TCP_BOUND_INACTIVE != (int)TCP_BOUND_INACTIVE);
 	BUILD_BUG_ON((int)BPF_TCP_MAX_STATES != (int)TCP_MAX_STATES);
 
 	/* bpf uapi header bpf.h defines an anonymous enum with values
@@ -3368,9 +3367,25 @@ int tcp_set_window_clamp(struct sock *sk, int val)
 			return -EINVAL;
 		tp->window_clamp = 0;
 	} else {
-		tp->window_clamp = val < SOCK_MIN_RCVBUF / 2 ?
-			SOCK_MIN_RCVBUF / 2 : val;
-		tp->rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp);
+		u32 new_rcv_ssthresh, old_window_clamp = tp->window_clamp;
+		u32 new_window_clamp = val < SOCK_MIN_RCVBUF / 2 ?
+						SOCK_MIN_RCVBUF / 2 : val;
+
+		if (new_window_clamp == old_window_clamp)
+			return 0;
+
+		tp->window_clamp = new_window_clamp;
+		if (new_window_clamp < old_window_clamp) {
+			/* need to apply the reserved mem provisioning only
+			 * when shrinking the window clamp
+			 */
+			__tcp_adjust_rcv_ssthresh(sk, tp->window_clamp);
+
+		} else {
+			new_rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp);
+			tp->rcv_ssthresh = max(new_rcv_ssthresh,
+					       tp->rcv_ssthresh);
+		}
 	}
 	return 0;
 }
@@ -3594,6 +3609,10 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case TCP_AO_REPAIR:
+		if (!tcp_can_repair_sock(sk)) {
+			err = -EPERM;
+			break;
+		}
 		err = tcp_ao_set_repair(sk, optval, optlen);
 		break;
 #ifdef CONFIG_TCP_AO
@@ -4293,6 +4312,8 @@ zerocopy_rcv_out:
 	}
 #endif
 	case TCP_AO_REPAIR:
+		if (!tcp_can_repair_sock(sk))
+			return -EPERM;
 		return tcp_ao_get_repair(sk, optval, optlen);
 	case TCP_AO_GET_KEYS:
 	case TCP_AO_INFO: {
@@ -4563,6 +4584,97 @@ static void __init tcp_init_mem(void)
 	sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2;	/* 9.37 % */
 }
 
+static void __init tcp_struct_check(void)
+{
+	/* TX read-mostly hotpath cache lines */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, max_window);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, rcv_ssthresh);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, reordering);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, notsent_lowat);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, gso_segs);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, lost_skb_hint);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, retransmit_skb_hint);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_tx, 40);
+
+	/* TXRX read-mostly hotpath cache lines */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, tsoffset);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, snd_wnd);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, mss_cache);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, snd_cwnd);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, prr_out);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, lost_out);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, sacked_out);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 31);
+
+	/* RX read-mostly hotpath cache lines */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, copied_seq);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rcv_tstamp);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, snd_wl1);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, tlp_high_seq);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rttvar_us);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, retrans_out);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, advmss);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, urg_data);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, lost);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rtt_min);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, out_of_order_queue);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, snd_ssthresh);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_rx, 69);
+
+	/* TX read-write hotpath cache lines */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, segs_out);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, data_segs_out);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, bytes_sent);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, snd_sml);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, chrono_start);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, chrono_stat);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, write_seq);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, pushed_seq);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, lsndtime);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, mdev_us);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_wstamp_ns);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_clock_cache);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_mstamp);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, rtt_seq);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tsorted_sent_queue);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, highest_sack);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, ecn_flags);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 113);
+
+	/* TXRX read-write hotpath cache lines */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, pred_flags);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_nxt);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_nxt);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_una);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, window_clamp);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, srtt_us);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, packets_out);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_up);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered_ce);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, app_limited);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_wnd);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rx_opt);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 76);
+
+	/* RX read-write hotpath cache lines */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_received);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, segs_in);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, data_segs_in);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_wup);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, max_packets_out);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, cwnd_usage_seq);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_delivered);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_interval_us);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_last_tsecr);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, first_tx_mstamp);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, delivered_mstamp);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_acked);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_est);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcvq_space);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_rx, 99);
+}
+
 void __init tcp_init(void)
 {
 	int max_rshare, max_wshare, cnt;
@@ -4573,6 +4685,8 @@ void __init tcp_init(void)
 	BUILD_BUG_ON(sizeof(struct tcp_skb_cb) >
 		     sizeof_field(struct sk_buff, cb));
 
+	tcp_struct_check();
+
 	percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL);
 
 	timer_setup(&tcp_orphan_timer, tcp_orphan_update, TIMER_DEFERRABLE);
diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
index 7696417d0640..87db432c6bb4 100644
--- a/net/ipv4/tcp_ao.c
+++ b/net/ipv4/tcp_ao.c
@@ -844,18 +844,30 @@ static struct tcp_ao_key *tcp_ao_inbound_lookup(unsigned short int family,
 }
 
 void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb,
-		      struct tcp_request_sock *treq,
-		      unsigned short int family, int l3index)
+		      struct request_sock *req, unsigned short int family)
 {
+	struct tcp_request_sock *treq = tcp_rsk(req);
 	const struct tcphdr *th = tcp_hdr(skb);
 	const struct tcp_ao_hdr *aoh;
 	struct tcp_ao_key *key;
+	int l3index;
 
-	treq->maclen = 0;
+	/* treq->af_specific is used to perform TCP_AO lookup
+	 * in tcp_create_openreq_child().
+	 */
+#if IS_ENABLED(CONFIG_IPV6)
+	if (family == AF_INET6)
+		treq->af_specific = &tcp_request_sock_ipv6_ops;
+	else
+#endif
+		treq->af_specific = &tcp_request_sock_ipv4_ops;
+
+	treq->used_tcp_ao = false;
 
 	if (tcp_parse_auth_options(th, NULL, &aoh) || !aoh)
 		return;
 
+	l3index = l3mdev_master_ifindex_by_index(sock_net(sk), inet_rsk(req)->ir_iif);
 	key = tcp_ao_inbound_lookup(family, sk, skb, -1, aoh->keyid, l3index);
 	if (!key)
 		/* Key not found, continue without TCP-AO */
@@ -863,7 +875,7 @@ void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb,
 
 	treq->ao_rcv_next = aoh->keyid;
 	treq->ao_keyid = aoh->rnext_keyid;
-	treq->maclen = tcp_ao_maclen(key);
+	treq->used_tcp_ao = true;
 }
 
 static enum skb_drop_reason
@@ -1100,7 +1112,7 @@ void tcp_ao_connect_init(struct sock *sk)
 			ao_info->current_key = key;
 		if (!ao_info->rnext_key)
 			ao_info->rnext_key = key;
-		tp->tcp_header_len += tcp_ao_len(key);
+		tp->tcp_header_len += tcp_ao_len_aligned(key);
 
 		ao_info->lisn = htonl(tp->write_seq);
 		ao_info->snd_sne = 0;
@@ -1346,7 +1358,7 @@ static int tcp_ao_parse_crypto(struct tcp_ao_add *cmd, struct tcp_ao_key *key)
 	syn_tcp_option_space -= TCPOLEN_MSS_ALIGNED;
 	syn_tcp_option_space -= TCPOLEN_TSTAMP_ALIGNED;
 	syn_tcp_option_space -= TCPOLEN_WSCALE_ALIGNED;
-	if (tcp_ao_len(key) > syn_tcp_option_space) {
+	if (tcp_ao_len_aligned(key) > syn_tcp_option_space) {
 		err = -EMSGSIZE;
 		goto err_kfree;
 	}
@@ -1608,6 +1620,15 @@ static int tcp_ao_add_cmd(struct sock *sk, unsigned short int family,
 		if (!dev || !l3index)
 			return -EINVAL;
 
+		if (!bound_dev_if || bound_dev_if != cmd.ifindex) {
+			/* tcp_ao_established_key() doesn't expect having
+			 * non peer-matching key on an established TCP-AO
+			 * connection.
+			 */
+			if (!((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)))
+				return -EINVAL;
+		}
+
 		/* It's still possible to bind after adding keys or even
 		 * re-bind to a different dev (with CAP_NET_RAW).
 		 * So, no reason to return error here, rather try to be
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index 01b50fa79189..4cbe4b44425a 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -247,4 +247,5 @@ static void __exit tcp_diag_exit(void)
 module_init(tcp_diag_init);
 module_exit(tcp_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("TCP socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-6 /* AF_INET - IPPROTO_TCP */);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index bcb55d98004c..df7b13f0e5e0 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -202,23 +202,17 @@ static void bpf_skops_established(struct sock *sk, int bpf_op,
 }
 #endif
 
-static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb,
-			     unsigned int len)
+static __cold void tcp_gro_dev_warn(const struct sock *sk, const struct sk_buff *skb,
+				    unsigned int len)
 {
-	static bool __once __read_mostly;
+	struct net_device *dev;
 
-	if (!__once) {
-		struct net_device *dev;
-
-		__once = true;
-
-		rcu_read_lock();
-		dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif);
-		if (!dev || len >= dev->mtu)
-			pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n",
-				dev ? dev->name : "Unknown driver");
-		rcu_read_unlock();
-	}
+	rcu_read_lock();
+	dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif);
+	if (!dev || len >= READ_ONCE(dev->mtu))
+		pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n",
+			dev ? dev->name : "Unknown driver");
+	rcu_read_unlock();
 }
 
 /* Adapt the MSS value used to make delayed ack decision to the
@@ -250,9 +244,8 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
 		icsk->icsk_ack.rcv_mss = min_t(unsigned int, len,
 					       tcp_sk(sk)->advmss);
 		/* Account for possibly-removed options */
-		if (unlikely(len > icsk->icsk_ack.rcv_mss +
-				   MAX_TCP_OPTION_SPACE))
-			tcp_gro_dev_warn(sk, skb, len);
+		DO_ONCE_LITE_IF(len > icsk->icsk_ack.rcv_mss + MAX_TCP_OPTION_SPACE,
+				tcp_gro_dev_warn, sk, skb, len);
 		/* If the skb has a len of exactly 1*MSS and has the PSH bit
 		 * set then it is likely the end of an application write. So
 		 * more data may not be arriving soon, and yet the data sender
@@ -3871,8 +3864,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	 * then we can probably ignore it.
 	 */
 	if (before(ack, prior_snd_una)) {
+		u32 max_window;
+
+		/* do not accept ACK for bytes we never sent. */
+		max_window = min_t(u64, tp->max_window, tp->bytes_acked);
 		/* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */
-		if (before(ack, prior_snd_una - tp->max_window)) {
+		if (before(ack, prior_snd_una - max_window)) {
 			if (!(flag & FLAG_NO_CHALLENGE_ACK))
 				tcp_send_challenge_ack(sk);
 			return -SKB_DROP_REASON_TCP_TOO_OLD_ACK;
@@ -4364,6 +4361,23 @@ EXPORT_SYMBOL(tcp_do_parse_auth_options);
  * up to bandwidth of 18Gigabit/sec. 8) ]
  */
 
+/* Estimates max number of increments of remote peer TSval in
+ * a replay window (based on our current RTO estimation).
+ */
+static u32 tcp_tsval_replay(const struct sock *sk)
+{
+	/* If we use usec TS resolution,
+	 * then expect the remote peer to use the same resolution.
+	 */
+	if (tcp_sk(sk)->tcp_usec_ts)
+		return inet_csk(sk)->icsk_rto * (USEC_PER_SEC / HZ);
+
+	/* RFC 7323 recommends a TSval clock between 1ms and 1sec.
+	 * We know that some OS (including old linux) can use 1200 Hz.
+	 */
+	return inet_csk(sk)->icsk_rto * 1200 / HZ;
+}
+
 static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
@@ -4371,7 +4385,7 @@ static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb)
 	u32 seq = TCP_SKB_CB(skb)->seq;
 	u32 ack = TCP_SKB_CB(skb)->ack_seq;
 
-	return (/* 1. Pure ACK with correct sequence number. */
+	return	/* 1. Pure ACK with correct sequence number. */
 		(th->ack && seq == TCP_SKB_CB(skb)->end_seq && seq == tp->rcv_nxt) &&
 
 		/* 2. ... and duplicate ACK. */
@@ -4381,7 +4395,8 @@ static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb)
 		!tcp_may_update_window(tp, ack, seq, ntohs(th->window) << tp->rx_opt.snd_wscale) &&
 
 		/* 4. ... and sits in replay window. */
-		(s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= (inet_csk(sk)->icsk_rto * 1024) / HZ);
+		(s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <=
+		tcp_tsval_replay(sk);
 }
 
 static inline bool tcp_paws_discard(const struct sock *sk,
@@ -7182,11 +7197,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh))
 		goto drop_and_release; /* Invalid TCP options */
 	if (aoh) {
-		tcp_rsk(req)->maclen = aoh->length - sizeof(struct tcp_ao_hdr);
+		tcp_rsk(req)->used_tcp_ao = true;
 		tcp_rsk(req)->ao_rcv_next = aoh->keyid;
 		tcp_rsk(req)->ao_keyid = aoh->rnext_keyid;
+
 	} else {
-		tcp_rsk(req)->maclen = 0;
+		tcp_rsk(req)->used_tcp_ao = false;
 	}
 #endif
 	tcp_rsk(req)->snt_isn = isn;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5f693bbd578d..0c50c5a32b84 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -690,7 +690,7 @@ static bool tcp_v4_ao_sign_reset(const struct sock *sk, struct sk_buff *skb,
 
 	reply_options[0] = htonl((TCPOPT_AO << 24) | (tcp_ao_len(key) << 16) |
 				 (aoh->rnext_keyid << 8) | keyid);
-	arg->iov[0].iov_len += round_up(tcp_ao_len(key), 4);
+	arg->iov[0].iov_len += tcp_ao_len_aligned(key);
 	reply->doff = arg->iov[0].iov_len / 4;
 
 	if (tcp_ao_hash_hdr(AF_INET, (char *)&reply_options[1],
@@ -978,7 +978,7 @@ static void tcp_v4_send_ack(const struct sock *sk,
 					  (tcp_ao_len(key->ao_key) << 16) |
 					  (key->ao_key->sndid << 8) |
 					  key->rcv_next);
-		arg.iov[0].iov_len += round_up(tcp_ao_len(key->ao_key), 4);
+		arg.iov[0].iov_len += tcp_ao_len_aligned(key->ao_key);
 		rep.th.doff = arg.iov[0].iov_len / 4;
 
 		tcp_ao_hash_hdr(AF_INET, (char *)&rep.opt[offset],
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index a9807eeb311c..9e85f2a0bddd 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -615,7 +615,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	ao_key = treq->af_specific->ao_lookup(sk, req,
 				tcp_rsk(req)->ao_keyid, -1);
 	if (ao_key)
-		newtp->tcp_header_len += tcp_ao_len(ao_key);
+		newtp->tcp_header_len += tcp_ao_len_aligned(ao_key);
  #endif
 	if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len)
 		newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index eb13a55d660c..e3167ad96567 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -825,7 +825,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 		timestamps = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps);
 		if (tcp_key_is_ao(key)) {
 			opts->options |= OPTION_AO;
-			remaining -= tcp_ao_len(key->ao_key);
+			remaining -= tcp_ao_len_aligned(key->ao_key);
 		}
 	}
 
@@ -915,7 +915,7 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 			ireq->tstamp_ok &= !ireq->sack_ok;
 	} else if (tcp_key_is_ao(key)) {
 		opts->options |= OPTION_AO;
-		remaining -= tcp_ao_len(key->ao_key);
+		remaining -= tcp_ao_len_aligned(key->ao_key);
 		ireq->tstamp_ok &= !ireq->sack_ok;
 	}
 
@@ -982,7 +982,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 		size += TCPOLEN_MD5SIG_ALIGNED;
 	} else if (tcp_key_is_ao(key)) {
 		opts->options |= OPTION_AO;
-		size += tcp_ao_len(key->ao_key);
+		size += tcp_ao_len_aligned(key->ao_key);
 	}
 
 	if (likely(tp->rx_opt.tstamp_ok)) {
@@ -3293,7 +3293,13 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 	if (skb_still_in_host_queue(sk, skb))
 		return -EBUSY;
 
+start:
 	if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
+		if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
+			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN;
+			TCP_SKB_CB(skb)->seq++;
+			goto start;
+		}
 		if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) {
 			WARN_ON_ONCE(1);
 			return -EINVAL;
@@ -3720,7 +3726,6 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	if (tcp_rsk_used_ao(req)) {
 #ifdef CONFIG_TCP_AO
 		struct tcp_ao_key *ao_key = NULL;
-		u8 maclen = tcp_rsk(req)->maclen;
 		u8 keyid = tcp_rsk(req)->ao_keyid;
 
 		ao_key = tcp_sk(sk)->af_specific->ao_lookup(sk, req_to_sk(req),
@@ -3730,13 +3735,11 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 		 * for another peer-matching key, but the peer has requested
 		 * ao_keyid (RFC5925 RNextKeyID), so let's keep it simple here.
 		 */
-		if (unlikely(!ao_key || tcp_ao_maclen(ao_key) != maclen)) {
-			u8 key_maclen = ao_key ? tcp_ao_maclen(ao_key) : 0;
-
+		if (unlikely(!ao_key)) {
 			rcu_read_unlock();
 			kfree_skb(skb);
-			net_warn_ratelimited("TCP-AO: the keyid %u with maclen %u|%u from SYN packet is not present - not sending SYNACK\n",
-					     keyid, maclen, key_maclen);
+			net_warn_ratelimited("TCP-AO: the keyid %u from SYN packet is not present - not sending SYNACK\n",
+					     keyid);
 			return NULL;
 		}
 		key.ao_key = ao_key;
diff --git a/net/ipv4/tcp_sigpool.c b/net/ipv4/tcp_sigpool.c
index 55b310a722c7..8512cb09ebc0 100644
--- a/net/ipv4/tcp_sigpool.c
+++ b/net/ipv4/tcp_sigpool.c
@@ -162,9 +162,8 @@ int tcp_sigpool_alloc_ahash(const char *alg, size_t scratch_size)
 		if (strcmp(cpool[i].alg, alg))
 			continue;
 
-		if (kref_read(&cpool[i].kref) > 0)
-			kref_get(&cpool[i].kref);
-		else
+		/* pairs with tcp_sigpool_release() */
+		if (!kref_get_unless_zero(&cpool[i].kref))
 			kref_init(&cpool[i].kref);
 		ret = i;
 		goto out;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 1f9f6c1c196b..d1ad20ce1c8c 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -626,7 +626,6 @@ void tcp_retransmit_timer(struct sock *sk)
 	 * implemented ftp to mars will work nicely. We will have to fix
 	 * the 120 second clamps though!
 	 */
-	icsk->icsk_backoff++;
 
 out_reset_timer:
 	/* If stream is thin, use linear timeouts. Since 'icsk_backoff' is
@@ -647,11 +646,12 @@ out_reset_timer:
 				       tcp_rto_min(sk),
 				       TCP_RTO_MAX);
 	} else if (sk->sk_state != TCP_SYN_SENT ||
-		   icsk->icsk_backoff >
+		   tp->total_rto >
 		   READ_ONCE(net->ipv4.sysctl_tcp_syn_linear_timeouts)) {
 		/* Use normal (exponential) backoff unless linear timeouts are
 		 * activated.
 		 */
+		icsk->icsk_backoff++;
 		icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
 	}
 	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index de3f2d31f510..dc41a22ee80e 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -296,5 +296,6 @@ static void __exit udp_diag_exit(void)
 module_init(udp_diag_init);
 module_exit(udp_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("UDP socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-17 /* AF_INET - IPPROTO_UDP */);
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-136 /* AF_INET - IPPROTO_UDPLITE */);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 3aaea56b5166..733ace18806c 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1407,23 +1407,15 @@ retry:
 
 	write_unlock_bh(&idev->lock);
 
-	/* From RFC 4941:
-	 *
-	 *     A temporary address is created only if this calculated Preferred
-	 *     Lifetime is greater than REGEN_ADVANCE time units.  In
-	 *     particular, an implementation must not create a temporary address
-	 *     with a zero Preferred Lifetime.
-	 *
-	 * Clamp the preferred lifetime to a minimum of regen_advance, unless
-	 * that would exceed valid_lft.
-	 *
+	/* A temporary address is created only if this calculated Preferred
+	 * Lifetime is greater than REGEN_ADVANCE time units.  In particular,
+	 * an implementation must not create a temporary address with a zero
+	 * Preferred Lifetime.
 	 * Use age calculation as in addrconf_verify to avoid unnecessary
 	 * temporary addresses being generated.
 	 */
 	age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
-	if (cfg.preferred_lft <= regen_advance + age)
-		cfg.preferred_lft = regen_advance + age + 1;
-	if (cfg.preferred_lft > cfg.valid_lft) {
+	if (cfg.preferred_lft <= regen_advance + age) {
 		in6_ifa_put(ifp);
 		in6_dev_put(idev);
 		ret = -1;
@@ -6149,11 +6141,7 @@ static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev,
 	pmsg->prefix_len = pinfo->prefix_len;
 	pmsg->prefix_type = pinfo->type;
 	pmsg->prefix_pad3 = 0;
-	pmsg->prefix_flags = 0;
-	if (pinfo->onlink)
-		pmsg->prefix_flags |= IF_PREFIX_ONLINK;
-	if (pinfo->autoconf)
-		pmsg->prefix_flags |= IF_PREFIX_AUTOCONF;
+	pmsg->prefix_flags = pinfo->flags;
 
 	if (nla_put(skb, PREFIX_ADDRESS, sizeof(pinfo->prefix), &pinfo->prefix))
 		goto nla_put_failure;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index cc6a502db39d..fff78496803d 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -60,9 +60,9 @@ static void ip6_datagram_flow_key_init(struct flowi6 *fl6,
 
 	if (!oif) {
 		if (ipv6_addr_is_multicast(&fl6->daddr))
-			oif = np->mcast_oif;
+			oif = READ_ONCE(np->mcast_oif);
 		else
-			oif = np->ucast_oif;
+			oif = READ_ONCE(np->ucast_oif);
 	}
 
 	fl6->flowi6_oif = oif;
@@ -229,7 +229,7 @@ ipv4_connected:
 		}
 
 		if (!sk->sk_bound_dev_if && (addr_type & IPV6_ADDR_MULTICAST))
-			WRITE_ONCE(sk->sk_bound_dev_if, np->mcast_oif);
+			WRITE_ONCE(sk->sk_bound_dev_if, READ_ONCE(np->mcast_oif));
 
 		/* Connect to link-local address requires an interface */
 		if (!sk->sk_bound_dev_if) {
diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c
index 06750d65d480..4c00398f4dca 100644
--- a/net/ipv6/exthdrs_offload.c
+++ b/net/ipv6/exthdrs_offload.c
@@ -16,6 +16,10 @@ static const struct net_offload dstopt_offload = {
 	.flags		=	INET6_PROTO_GSO_EXTHDR,
 };
 
+static const struct net_offload hbh_offload = {
+	.flags		=	INET6_PROTO_GSO_EXTHDR,
+};
+
 int __init ipv6_exthdrs_offload_init(void)
 {
 	int ret;
@@ -28,9 +32,16 @@ int __init ipv6_exthdrs_offload_init(void)
 	if (ret)
 		goto out_rt;
 
+	ret = inet6_add_offload(&hbh_offload, IPPROTO_HOPOPTS);
+	if (ret)
+		goto out_dstopts;
+
 out:
 	return ret;
 
+out_dstopts:
+	inet6_del_offload(&dstopt_offload, IPPROTO_DSTOPTS);
+
 out_rt:
 	inet6_del_offload(&rthdr_offload, IPPROTO_ROUTING);
 	goto out;
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 7c2003833010..7523c4baef35 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -475,11 +475,11 @@ static int __net_init fib6_rules_net_init(struct net *net)
 	if (IS_ERR(ops))
 		return PTR_ERR(ops);
 
-	err = fib_default_rule_add(ops, 0, RT6_TABLE_LOCAL, 0);
+	err = fib_default_rule_add(ops, 0, RT6_TABLE_LOCAL);
 	if (err)
 		goto out_fib6_rules_ops;
 
-	err = fib_default_rule_add(ops, 0x7FFE, RT6_TABLE_MAIN, 0);
+	err = fib_default_rule_add(ops, 0x7FFE, RT6_TABLE_MAIN);
 	if (err)
 		goto out_fib6_rules_ops;
 
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index f62427097126..1635da07285f 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -584,9 +584,9 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	tmp_hdr.icmp6_pointer = htonl(info);
 
 	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
-		fl6.flowi6_oif = np->mcast_oif;
+		fl6.flowi6_oif = READ_ONCE(np->mcast_oif);
 	else if (!fl6.flowi6_oif)
-		fl6.flowi6_oif = np->ucast_oif;
+		fl6.flowi6_oif = READ_ONCE(np->ucast_oif);
 
 	ipcm6_init_sk(&ipc6, sk);
 	ipc6.sockc.mark = mark;
@@ -770,9 +770,9 @@ static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb)
 	np = inet6_sk(sk);
 
 	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
-		fl6.flowi6_oif = np->mcast_oif;
+		fl6.flowi6_oif = READ_ONCE(np->mcast_oif);
 	else if (!fl6.flowi6_oif)
-		fl6.flowi6_oif = np->ucast_oif;
+		fl6.flowi6_oif = READ_ONCE(np->ucast_oif);
 
 	if (ip6_dst_lookup(net, sk, &dst, &fl6))
 		goto out;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 28b01a068412..4fc2cae0d116 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -160,8 +160,6 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh)
 	INIT_LIST_HEAD(&f6i->fib6_siblings);
 	refcount_set(&f6i->fib6_ref, 1);
 
-	INIT_HLIST_NODE(&f6i->gc_link);
-
 	return f6i;
 }
 
@@ -248,7 +246,6 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
 				   net->ipv6.fib6_null_entry);
 		table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
 		inet_peer_base_init(&table->tb6_peers);
-		INIT_HLIST_HEAD(&table->tb6_gc_hlist);
 	}
 
 	return table;
@@ -1060,8 +1057,6 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
 				    lockdep_is_held(&table->tb6_lock));
 		}
 	}
-
-	fib6_clean_expires_locked(rt);
 }
 
 /*
@@ -1123,10 +1118,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 				if (!(iter->fib6_flags & RTF_EXPIRES))
 					return -EEXIST;
 				if (!(rt->fib6_flags & RTF_EXPIRES))
-					fib6_clean_expires_locked(iter);
+					fib6_clean_expires(iter);
 				else
-					fib6_set_expires_locked(iter,
-								rt->expires);
+					fib6_set_expires(iter, rt->expires);
 
 				if (rt->fib6_pmtu)
 					fib6_metric_set(iter, RTAX_MTU,
@@ -1485,10 +1479,6 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
 		if (rt->nh)
 			list_add(&rt->nh_list, &rt->nh->f6i_list);
 		__fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net));
-
-		if (fib6_has_expires(rt))
-			hlist_add_head(&rt->gc_link, &table->tb6_gc_hlist);
-
 		fib6_start_gc(info->nl_net, rt);
 	}
 
@@ -1511,13 +1501,9 @@ out:
 			if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) {
 				pn_leaf = fib6_find_prefix(info->nl_net, table,
 							   pn);
-#if RT6_DEBUG >= 2
-				if (!pn_leaf) {
-					WARN_ON(!pn_leaf);
+				if (!pn_leaf)
 					pn_leaf =
 					    info->nl_net->ipv6.fib6_null_entry;
-				}
-#endif
 				fib6_info_hold(pn_leaf);
 				rcu_assign_pointer(pn->leaf, pn_leaf);
 			}
@@ -2295,8 +2281,9 @@ static void fib6_flush_trees(struct net *net)
  *	Garbage collection
  */
 
-static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args)
+static int fib6_age(struct fib6_info *rt, void *arg)
 {
+	struct fib6_gc_args *gc_args = arg;
 	unsigned long now = jiffies;
 
 	/*
@@ -2304,7 +2291,7 @@ static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args)
 	 *	Routes are expired even if they are in use.
 	 */
 
-	if (fib6_has_expires(rt) && rt->expires) {
+	if (rt->fib6_flags & RTF_EXPIRES && rt->expires) {
 		if (time_after(now, rt->expires)) {
 			RT6_TRACE("expiring %p\n", rt);
 			return -1;
@@ -2321,40 +2308,6 @@ static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args)
 	return 0;
 }
 
-static void fib6_gc_table(struct net *net,
-			  struct fib6_table *tb6,
-			  struct fib6_gc_args *gc_args)
-{
-	struct fib6_info *rt;
-	struct hlist_node *n;
-	struct nl_info info = {
-		.nl_net = net,
-		.skip_notify = false,
-	};
-
-	hlist_for_each_entry_safe(rt, n, &tb6->tb6_gc_hlist, gc_link)
-		if (fib6_age(rt, gc_args) == -1)
-			fib6_del(rt, &info);
-}
-
-static void fib6_gc_all(struct net *net, struct fib6_gc_args *gc_args)
-{
-	struct fib6_table *table;
-	struct hlist_head *head;
-	unsigned int h;
-
-	rcu_read_lock();
-	for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
-		head = &net->ipv6.fib_table_hash[h];
-		hlist_for_each_entry_rcu(table, head, tb6_hlist) {
-			spin_lock_bh(&table->tb6_lock);
-			fib6_gc_table(net, table, gc_args);
-			spin_unlock_bh(&table->tb6_lock);
-		}
-	}
-	rcu_read_unlock();
-}
-
 void fib6_run_gc(unsigned long expires, struct net *net, bool force)
 {
 	struct fib6_gc_args gc_args;
@@ -2370,7 +2323,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force)
 			  net->ipv6.sysctl.ip6_rt_gc_interval;
 	gc_args.more = 0;
 
-	fib6_gc_all(net, &gc_args);
+	fib6_clean_all(net, fib6_age, &gc_args);
 	now = jiffies;
 	net->ipv6.ip6_rt_last_gc = now;
 
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index d6314287338d..cca64c7809be 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -37,6 +37,40 @@
 		INDIRECT_CALL_L4(cb, f2, f1, head, skb);	\
 })
 
+static int ipv6_gro_pull_exthdrs(struct sk_buff *skb, int off, int proto)
+{
+	const struct net_offload *ops = NULL;
+	struct ipv6_opt_hdr *opth;
+
+	for (;;) {
+		int len;
+
+		ops = rcu_dereference(inet6_offloads[proto]);
+
+		if (unlikely(!ops))
+			break;
+
+		if (!(ops->flags & INET6_PROTO_GSO_EXTHDR))
+			break;
+
+		opth = skb_gro_header(skb, off + sizeof(*opth), off);
+		if (unlikely(!opth))
+			break;
+
+		len = ipv6_optlen(opth);
+
+		opth = skb_gro_header(skb, off + len, off);
+		if (unlikely(!opth))
+			break;
+		proto = opth->nexthdr;
+
+		off += len;
+	}
+
+	skb_gro_pull(skb, off - skb_network_offset(skb));
+	return proto;
+}
+
 static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto)
 {
 	const struct net_offload *ops = NULL;
@@ -45,15 +79,13 @@ static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto)
 		struct ipv6_opt_hdr *opth;
 		int len;
 
-		if (proto != NEXTHDR_HOP) {
-			ops = rcu_dereference(inet6_offloads[proto]);
+		ops = rcu_dereference(inet6_offloads[proto]);
 
-			if (unlikely(!ops))
-				break;
+		if (unlikely(!ops))
+			break;
 
-			if (!(ops->flags & INET6_PROTO_GSO_EXTHDR))
-				break;
-		}
+		if (!(ops->flags & INET6_PROTO_GSO_EXTHDR))
+			break;
 
 		if (unlikely(!pskb_may_pull(skb, 8)))
 			break;
@@ -171,13 +203,12 @@ static int ipv6_exthdrs_len(struct ipv6hdr *iph,
 
 	proto = iph->nexthdr;
 	for (;;) {
-		if (proto != NEXTHDR_HOP) {
-			*opps = rcu_dereference(inet6_offloads[proto]);
-			if (unlikely(!(*opps)))
-				break;
-			if (!((*opps)->flags & INET6_PROTO_GSO_EXTHDR))
-				break;
-		}
+		*opps = rcu_dereference(inet6_offloads[proto]);
+		if (unlikely(!(*opps)))
+			break;
+		if (!((*opps)->flags & INET6_PROTO_GSO_EXTHDR))
+			break;
+
 		opth = (void *)opth + optlen;
 		optlen = ipv6_optlen(opth);
 		len += optlen;
@@ -206,28 +237,25 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head,
 		goto out;
 
 	skb_set_network_header(skb, off);
-	skb_gro_pull(skb, sizeof(*iph));
-	skb_set_transport_header(skb, skb_gro_offset(skb));
 
-	flush += ntohs(iph->payload_len) != skb_gro_len(skb);
+	flush += ntohs(iph->payload_len) != skb->len - hlen;
 
 	proto = iph->nexthdr;
 	ops = rcu_dereference(inet6_offloads[proto]);
 	if (!ops || !ops->callbacks.gro_receive) {
-		pskb_pull(skb, skb_gro_offset(skb));
-		skb_gro_frag0_invalidate(skb);
-		proto = ipv6_gso_pull_exthdrs(skb, proto);
-		skb_gro_pull(skb, -skb_transport_offset(skb));
-		skb_reset_transport_header(skb);
-		__skb_push(skb, skb_gro_offset(skb));
+		proto = ipv6_gro_pull_exthdrs(skb, hlen, proto);
 
 		ops = rcu_dereference(inet6_offloads[proto]);
 		if (!ops || !ops->callbacks.gro_receive)
 			goto out;
 
-		iph = ipv6_hdr(skb);
+		iph = skb_gro_network_header(skb);
+	} else {
+		skb_gro_pull(skb, sizeof(*iph));
 	}
 
+	skb_set_transport_header(skb, skb_gro_offset(skb));
+
 	NAPI_GRO_CB(skb)->proto = proto;
 
 	flush--;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 5e80e517f071..46c19bd48990 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -399,7 +399,7 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)raw;
 	unsigned int nhoff = raw - skb->data;
 	unsigned int off = nhoff + sizeof(*ipv6h);
-	u8 next, nexthdr = ipv6h->nexthdr;
+	u8 nexthdr = ipv6h->nexthdr;
 
 	while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) {
 		struct ipv6_opt_hdr *hdr;
@@ -410,25 +410,25 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 
 		hdr = (struct ipv6_opt_hdr *)(skb->data + off);
 		if (nexthdr == NEXTHDR_FRAGMENT) {
-			struct frag_hdr *frag_hdr = (struct frag_hdr *) hdr;
-			if (frag_hdr->frag_off)
-				break;
 			optlen = 8;
 		} else if (nexthdr == NEXTHDR_AUTH) {
 			optlen = ipv6_authlen(hdr);
 		} else {
 			optlen = ipv6_optlen(hdr);
 		}
-		/* cache hdr->nexthdr, since pskb_may_pull() might
-		 * invalidate hdr
-		 */
-		next = hdr->nexthdr;
-		if (nexthdr == NEXTHDR_DEST) {
-			u16 i = 2;
 
-			/* Remember : hdr is no longer valid at this point. */
-			if (!pskb_may_pull(skb, off + optlen))
+		if (!pskb_may_pull(skb, off + optlen))
+			break;
+
+		hdr = (struct ipv6_opt_hdr *)(skb->data + off);
+		if (nexthdr == NEXTHDR_FRAGMENT) {
+			struct frag_hdr *frag_hdr = (struct frag_hdr *)hdr;
+
+			if (frag_hdr->frag_off)
 				break;
+		}
+		if (nexthdr == NEXTHDR_DEST) {
+			u16 i = 2;
 
 			while (1) {
 				struct ipv6_tlv_tnl_enc_lim *tel;
@@ -449,7 +449,7 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 					i++;
 			}
 		}
-		nexthdr = next;
+		nexthdr = hdr->nexthdr;
 		off += optlen;
 	}
 	return 0;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 30ca064b76ef..9782c180fee6 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -242,7 +242,7 @@ static int __net_init ip6mr_rules_init(struct net *net)
 		goto err1;
 	}
 
-	err = fib_default_rule_add(ops, 0x7fff, RT6_TABLE_DFLT, 0);
+	err = fib_default_rule_add(ops, 0x7fff, RT6_TABLE_DFLT);
 	if (err < 0)
 		goto err2;
 
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 7d661735cb9d..56c3c467f9de 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -210,7 +210,7 @@ static int ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
 
 	if (optlen < GROUP_FILTER_SIZE(0))
 		return -EINVAL;
-	if (optlen > READ_ONCE(sysctl_optmem_max))
+	if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max))
 		return -ENOBUFS;
 
 	gsf = memdup_sockptr(optval, optlen);
@@ -244,7 +244,7 @@ static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
 
 	if (optlen < size0)
 		return -EINVAL;
-	if (optlen > READ_ONCE(sysctl_optmem_max) - 4)
+	if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max) - 4)
 		return -ENOBUFS;
 
 	p = kmalloc(optlen + 4, GFP_KERNEL);
@@ -509,6 +509,59 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		if (optlen < sizeof(int))
 			return -EINVAL;
 		return ip6_sock_set_addr_preferences(sk, val);
+	case IPV6_MULTICAST_IF:
+		if (sk->sk_type == SOCK_STREAM)
+			return -ENOPROTOOPT;
+		if (optlen < sizeof(int))
+			return -EINVAL;
+		if (val) {
+			struct net_device *dev;
+			int bound_dev_if, midx;
+
+			rcu_read_lock();
+
+			dev = dev_get_by_index_rcu(net, val);
+			if (!dev) {
+				rcu_read_unlock();
+				return -ENODEV;
+			}
+			midx = l3mdev_master_ifindex_rcu(dev);
+
+			rcu_read_unlock();
+
+			bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
+			if (bound_dev_if &&
+			    bound_dev_if != val &&
+			    (!midx || midx != bound_dev_if))
+				return -EINVAL;
+		}
+		WRITE_ONCE(np->mcast_oif, val);
+		return 0;
+	case IPV6_UNICAST_IF:
+	{
+		struct net_device *dev;
+		int ifindex;
+
+		if (optlen != sizeof(int))
+			return -EINVAL;
+
+		ifindex = (__force int)ntohl((__force __be32)val);
+		if (!ifindex) {
+			WRITE_ONCE(np->ucast_oif, 0);
+			return 0;
+		}
+
+		dev = dev_get_by_index(net, ifindex);
+		if (!dev)
+			return -EADDRNOTAVAIL;
+		dev_put(dev);
+
+		if (READ_ONCE(sk->sk_bound_dev_if))
+			return -EINVAL;
+
+		WRITE_ONCE(np->ucast_oif, ifindex);
+		return 0;
+	}
 	}
 	if (needs_rtnl)
 		rtnl_lock();
@@ -829,67 +882,6 @@ done:
 		break;
 	}
 
-
-	case IPV6_UNICAST_IF:
-	{
-		struct net_device *dev = NULL;
-		int ifindex;
-
-		if (optlen != sizeof(int))
-			goto e_inval;
-
-		ifindex = (__force int)ntohl((__force __be32)val);
-		if (ifindex == 0) {
-			np->ucast_oif = 0;
-			retv = 0;
-			break;
-		}
-
-		dev = dev_get_by_index(net, ifindex);
-		retv = -EADDRNOTAVAIL;
-		if (!dev)
-			break;
-		dev_put(dev);
-
-		retv = -EINVAL;
-		if (sk->sk_bound_dev_if)
-			break;
-
-		np->ucast_oif = ifindex;
-		retv = 0;
-		break;
-	}
-
-	case IPV6_MULTICAST_IF:
-		if (sk->sk_type == SOCK_STREAM)
-			break;
-		if (optlen < sizeof(int))
-			goto e_inval;
-
-		if (val) {
-			struct net_device *dev;
-			int midx;
-
-			rcu_read_lock();
-
-			dev = dev_get_by_index_rcu(net, val);
-			if (!dev) {
-				rcu_read_unlock();
-				retv = -ENODEV;
-				break;
-			}
-			midx = l3mdev_master_ifindex_rcu(dev);
-
-			rcu_read_unlock();
-
-			if (sk->sk_bound_dev_if &&
-			    sk->sk_bound_dev_if != val &&
-			    (!midx || midx != sk->sk_bound_dev_if))
-				goto e_inval;
-		}
-		np->mcast_oif = val;
-		retv = 0;
-		break;
 	case IPV6_ADD_MEMBERSHIP:
 	case IPV6_DROP_MEMBERSHIP:
 	{
@@ -1161,10 +1153,12 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		sockopt_release_sock(sk);
 		if (!skb) {
 			if (np->rxopt.bits.rxinfo) {
+				int mcast_oif = READ_ONCE(np->mcast_oif);
 				struct in6_pktinfo src_info;
-				src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif :
+
+				src_info.ipi6_ifindex = mcast_oif ? :
 					np->sticky_pktinfo.ipi6_ifindex;
-				src_info.ipi6_addr = np->mcast_oif ? sk->sk_v6_daddr : np->sticky_pktinfo.ipi6_addr;
+				src_info.ipi6_addr = mcast_oif ? sk->sk_v6_daddr : np->sticky_pktinfo.ipi6_addr;
 				put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
 			}
 			if (np->rxopt.bits.rxhlim) {
@@ -1178,11 +1172,13 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 				put_cmsg(&msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass);
 			}
 			if (np->rxopt.bits.rxoinfo) {
+				int mcast_oif = READ_ONCE(np->mcast_oif);
 				struct in6_pktinfo src_info;
-				src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif :
+
+				src_info.ipi6_ifindex = mcast_oif ? :
 					np->sticky_pktinfo.ipi6_ifindex;
-				src_info.ipi6_addr = np->mcast_oif ? sk->sk_v6_daddr :
-								     np->sticky_pktinfo.ipi6_addr;
+				src_info.ipi6_addr = mcast_oif ? sk->sk_v6_daddr :
+								 np->sticky_pktinfo.ipi6_addr;
 				put_cmsg(&msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info);
 			}
 			if (np->rxopt.bits.rxohlim) {
@@ -1359,7 +1355,7 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case IPV6_MULTICAST_IF:
-		val = np->mcast_oif;
+		val = READ_ONCE(np->mcast_oif);
 		break;
 
 	case IPV6_MULTICAST_ALL:
@@ -1367,7 +1363,7 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case IPV6_UNICAST_IF:
-		val = (__force int)htonl((__u32) np->ucast_oif);
+		val = (__force int)htonl((__u32) READ_ONCE(np->ucast_oif));
 		break;
 
 	case IPV6_MTU_DISCOVER:
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index d2098dd4ceae..ef2059c88955 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -107,9 +107,9 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		oif = np->sticky_pktinfo.ipi6_ifindex;
 
 	if (!oif && ipv6_addr_is_multicast(daddr))
-		oif = np->mcast_oif;
+		oif = READ_ONCE(np->mcast_oif);
 	else if (!oif)
-		oif = np->ucast_oif;
+		oif = READ_ONCE(np->ucast_oif);
 
 	addr_type = ipv6_addr_type(daddr);
 	if ((__ipv6_addr_needs_scope_id(addr_type) && !oif) ||
@@ -157,9 +157,9 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	rt = (struct rt6_info *) dst;
 
 	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
-		fl6.flowi6_oif = np->mcast_oif;
+		fl6.flowi6_oif = READ_ONCE(np->mcast_oif);
 	else if (!fl6.flowi6_oif)
-		fl6.flowi6_oif = np->ucast_oif;
+		fl6.flowi6_oif = READ_ONCE(np->ucast_oif);
 
 	pfh.icmph.type = user_icmph.icmp6_type;
 	pfh.icmph.code = user_icmph.icmp6_code;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index dd0a4e73e602..03dbb874c363 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -876,9 +876,9 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	final_p = fl6_update_dst(&fl6, opt, &final);
 
 	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
-		fl6.flowi6_oif = np->mcast_oif;
+		fl6.flowi6_oif = READ_ONCE(np->mcast_oif);
 	else if (!fl6.flowi6_oif)
-		fl6.flowi6_oif = np->ucast_oif;
+		fl6.flowi6_oif = READ_ONCE(np->ucast_oif);
 	security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
 
 	if (hdrincl)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index b132feae3393..ea1dec8448fc 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3763,10 +3763,10 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 		rt->dst_nocount = true;
 
 	if (cfg->fc_flags & RTF_EXPIRES)
-		fib6_set_expires_locked(rt, jiffies +
-					clock_t_to_jiffies(cfg->fc_expires));
+		fib6_set_expires(rt, jiffies +
+				clock_t_to_jiffies(cfg->fc_expires));
 	else
-		fib6_clean_expires_locked(rt);
+		fib6_clean_expires(rt);
 
 	if (cfg->fc_protocol == RTPROT_UNSPEC)
 		cfg->fc_protocol = RTPROT_BOOT;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 12eedc6ca2cc..c8d2ca27220c 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -114,76 +114,82 @@ __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mssp)
 	return __cookie_v6_init_sequence(iph, th, mssp);
 }
 
-int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th,
-		      __u32 cookie)
+int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th)
 {
+	__u32 cookie = ntohl(th->ack_seq) - 1;
 	__u32 seq = ntohl(th->seq) - 1;
-	__u32 mssind = check_tcp_syn_cookie(cookie, &iph->saddr, &iph->daddr,
-					    th->source, th->dest, seq);
+	__u32 mssind;
+
+	mssind = check_tcp_syn_cookie(cookie, &iph->saddr, &iph->daddr,
+				      th->source, th->dest, seq);
 
 	return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0;
 }
 EXPORT_SYMBOL_GPL(__cookie_v6_check);
 
-struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
+static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk,
+					     struct sk_buff *skb)
 {
 	struct tcp_options_received tcp_opt;
-	struct inet_request_sock *ireq;
-	struct tcp_request_sock *treq;
-	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct tcp_sock *tp = tcp_sk(sk);
-	const struct tcphdr *th = tcp_hdr(skb);
-	__u32 cookie = ntohl(th->ack_seq) - 1;
-	struct sock *ret = sk;
-	struct request_sock *req;
-	int full_space, mss;
-	struct dst_entry *dst;
-	__u8 rcv_wscale;
 	u32 tsoff = 0;
-	int l3index;
-
-	if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) ||
-	    !th->ack || th->rst)
-		goto out;
+	int mss;
 
 	if (tcp_synq_no_recent_overflow(sk))
 		goto out;
 
-	mss = __cookie_v6_check(ipv6_hdr(skb), th, cookie);
-	if (mss == 0) {
-		__NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESFAILED);
+	mss = __cookie_v6_check(ipv6_hdr(skb), tcp_hdr(skb));
+	if (!mss) {
+		__NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESFAILED);
 		goto out;
 	}
 
-	__NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV);
+	__NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESRECV);
 
 	/* check for timestamp cookie support */
 	memset(&tcp_opt, 0, sizeof(tcp_opt));
-	tcp_parse_options(sock_net(sk), skb, &tcp_opt, 0, NULL);
+	tcp_parse_options(net, skb, &tcp_opt, 0, NULL);
 
 	if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) {
-		tsoff = secure_tcpv6_ts_off(sock_net(sk),
+		tsoff = secure_tcpv6_ts_off(net,
 					    ipv6_hdr(skb)->daddr.s6_addr32,
 					    ipv6_hdr(skb)->saddr.s6_addr32);
 		tcp_opt.rcv_tsecr -= tsoff;
 	}
 
-	if (!cookie_timestamp_decode(sock_net(sk), &tcp_opt))
+	if (!cookie_timestamp_decode(net, &tcp_opt))
 		goto out;
 
-	ret = NULL;
-	req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops,
-				     &tcp_request_sock_ipv6_ops, sk, skb);
-	if (!req)
+	return cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, sk, skb,
+				      &tcp_opt, mss, tsoff);
+out:
+	return ERR_PTR(-EINVAL);
+}
+
+struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
+{
+	const struct tcphdr *th = tcp_hdr(skb);
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct inet_request_sock *ireq;
+	struct net *net = sock_net(sk);
+	struct request_sock *req;
+	struct dst_entry *dst;
+	struct sock *ret = sk;
+	__u8 rcv_wscale;
+	int full_space;
+
+	if (!READ_ONCE(net->ipv4.sysctl_tcp_syncookies) ||
+	    !th->ack || th->rst)
 		goto out;
 
+	req = cookie_tcp_check(net, sk, skb);
+	if (IS_ERR(req))
+		goto out;
+	if (!req)
+		goto out_drop;
+
 	ireq = inet_rsk(req);
-	treq = tcp_rsk(req);
-	treq->tfo_listener = false;
 
-	req->mss = mss;
-	ireq->ir_rmt_port = th->source;
-	ireq->ir_num = ntohs(th->dest);
 	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
 	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
 
@@ -197,31 +203,12 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		ireq->pktopts = skb;
 	}
 
-	ireq->ir_iif = inet_request_bound_dev_if(sk, skb);
 	/* So that link locals have meaning */
 	if (!sk->sk_bound_dev_if &&
 	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
 		ireq->ir_iif = tcp_v6_iif(skb);
 
-	ireq->ir_mark = inet_request_mark(sk, skb);
-
-	req->num_retrans = 0;
-	ireq->snd_wscale	= tcp_opt.snd_wscale;
-	ireq->sack_ok		= tcp_opt.sack_ok;
-	ireq->wscale_ok		= tcp_opt.wscale_ok;
-	ireq->tstamp_ok		= tcp_opt.saw_tstamp;
-	req->ts_recent		= tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
-	treq->snt_synack	= 0;
-	treq->rcv_isn = ntohl(th->seq) - 1;
-	treq->snt_isn = cookie;
-	treq->ts_off = 0;
-	treq->txhash = net_tx_rndhash();
-
-	l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif);
-	tcp_ao_syncookie(sk, skb, treq, AF_INET6, l3index);
-
-	if (IS_ENABLED(CONFIG_SMC))
-		ireq->smc_ok = 0;
+	tcp_ao_syncookie(sk, skb, req, AF_INET6);
 
 	/*
 	 * We need to lookup the dst_entry to get the correct window size.
@@ -243,7 +230,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		fl6.flowi6_uid = sk->sk_uid;
 		security_req_classify_flow(req, flowi6_to_flowi_common(&fl6));
 
-		dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
+		dst = ip6_dst_lookup_flow(net, sk, &fl6, final_p);
 		if (IS_ERR(dst))
 			goto out_free;
 	}
@@ -261,12 +248,13 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 				  dst_metric(dst, RTAX_INITRWND));
 
 	ireq->rcv_wscale = rcv_wscale;
-	ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), dst);
+	ireq->ecn_ok &= cookie_ecn_ok(net, dst);
 
-	ret = tcp_get_cookie_sock(sk, skb, req, dst, tsoff);
+	ret = tcp_get_cookie_sock(sk, skb, req, dst);
 out:
 	return ret;
 out_free:
 	reqsk_free(req);
+out_drop:
 	return NULL;
 }
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 937a02c2e534..57b25b1fc9d9 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -881,7 +881,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	if (tcp_key_is_md5(key))
 		tot_len += TCPOLEN_MD5SIG_ALIGNED;
 	if (tcp_key_is_ao(key))
-		tot_len += tcp_ao_len(key->ao_key);
+		tot_len += tcp_ao_len_aligned(key->ao_key);
 
 #ifdef CONFIG_MPTCP
 	if (rst && !tcp_key_is_md5(key)) {
@@ -1699,7 +1699,7 @@ ipv6_pktoptions:
 	if (TCP_SKB_CB(opt_skb)->end_seq == tp->rcv_nxt &&
 	    !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) {
 		if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo)
-			np->mcast_oif = tcp_v6_iif(opt_skb);
+			WRITE_ONCE(np->mcast_oif, tcp_v6_iif(opt_skb));
 		if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim)
 			WRITE_ONCE(np->mcast_hops,
 				   ipv6_hdr(opt_skb)->hop_limit);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 622b10a549f7..594e3f23c129 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1541,10 +1541,10 @@ do_udp_sendmsg:
 		connected = false;
 
 	if (!fl6->flowi6_oif && ipv6_addr_is_multicast(&fl6->daddr)) {
-		fl6->flowi6_oif = np->mcast_oif;
+		fl6->flowi6_oif = READ_ONCE(np->mcast_oif);
 		connected = false;
 	} else if (!fl6->flowi6_oif)
-		fl6->flowi6_oif = np->ucast_oif;
+		fl6->flowi6_oif = READ_ONCE(np->ucast_oif);
 
 	security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6));
 
diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c
index 0ed6e34d6edd..6334f64f04d5 100644
--- a/net/iucv/iucv.c
+++ b/net/iucv/iucv.c
@@ -67,7 +67,7 @@ static int iucv_bus_match(struct device *dev, struct device_driver *drv)
 	return 0;
 }
 
-struct bus_type iucv_bus = {
+const struct bus_type iucv_bus = {
 	.name = "iucv",
 	.match = iucv_bus_match,
 };
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 65d1f6755f98..1184d40167b8 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -634,7 +634,7 @@ retry:
 
 		msize = 0;
 		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
-			msize += skb_shinfo(skb)->frags[i].bv_len;
+			msize += skb_frag_size(&skb_shinfo(skb)->frags[i]);
 
 		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE,
 			      skb_shinfo(skb)->frags, skb_shinfo(skb)->nr_frags,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index bb373e249237..dd3153966173 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -599,9 +599,9 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	final_p = fl6_update_dst(&fl6, opt, &final);
 
 	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
-		fl6.flowi6_oif = np->mcast_oif;
+		fl6.flowi6_oif = READ_ONCE(np->mcast_oif);
 	else if (!fl6.flowi6_oif)
-		fl6.flowi6_oif = np->ucast_oif;
+		fl6.flowi6_oif = READ_ONCE(np->ucast_oif);
 
 	security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
 
diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig
index 037ab74f5ade..cb0291decf2e 100644
--- a/net/mac80211/Kconfig
+++ b/net/mac80211/Kconfig
@@ -88,7 +88,7 @@ config MAC80211_LEDS
 
 config MAC80211_DEBUGFS
 	bool "Export mac80211 internals in DebugFS"
-	depends on MAC80211 && DEBUG_FS
+	depends on MAC80211 && CFG80211_DEBUGFS
 	help
 	  Select this to see extensive information about
 	  the internal state of mac80211 in debugfs.
diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile
index c9eb52768133..4406b4f8f3b9 100644
--- a/net/mac80211/Makefile
+++ b/net/mac80211/Makefile
@@ -67,4 +67,6 @@ mac80211-$(CONFIG_MAC80211_RC_MINSTREL) += $(rc80211_minstrel-y)
 
 obj-y += tests/
 
+mac80211-y += wbrf.o
+
 ccflags-y += -DDEBUG
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 606b1b2e4123..489dd97f5172 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1270,7 +1270,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 		return -EALREADY;
 
 	if (params->smps_mode != NL80211_SMPS_OFF)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	link->smps_mode = IEEE80211_SMPS_OFF;
 
@@ -1788,10 +1788,10 @@ static int sta_link_apply_parameters(struct ieee80211_local *local,
 					  lockdep_is_held(&local->hw.wiphy->mtx));
 
 	/*
-	 * If there are no changes, then accept a link that doesn't exist,
+	 * If there are no changes, then accept a link that exist,
 	 * unless it's a new link.
 	 */
-	if (params->link_id < 0 && !new_link &&
+	if (params->link_id >= 0 && !new_link &&
 	    !params->link_mac && !params->txpwr_set &&
 	    !params->supported_rates_len &&
 	    !params->ht_capa && !params->vht_capa &&
@@ -2556,7 +2556,7 @@ static int ieee80211_update_mesh_config(struct wiphy *wiphy,
 		 * devices that report signal in dBm.
 		 */
 		if (!ieee80211_hw_check(&sdata->local->hw, SIGNAL_DBM))
-			return -ENOTSUPP;
+			return -EOPNOTSUPP;
 		conf->rssi_threshold = nconf->rssi_threshold;
 	}
 	if (_chg_mesh_attr(NL80211_MESHCONF_HT_OPMODE, mask)) {
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index 1d928f29ad6f..ef4c2cebc080 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -507,11 +507,16 @@ static void _ieee80211_change_chanctx(struct ieee80211_local *local,
 
 	WARN_ON(!cfg80211_chandef_compatible(&ctx->conf.def, chandef));
 
+	ieee80211_remove_wbrf(local, &ctx->conf.def);
+
 	ctx->conf.def = *chandef;
 
 	/* check if min chanctx also changed */
 	changed = IEEE80211_CHANCTX_CHANGE_WIDTH |
 		  _ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for);
+
+	ieee80211_add_wbrf(local, &ctx->conf.def);
+
 	drv_change_chanctx(local, ctx, changed);
 
 	if (!local->use_chanctx) {
@@ -667,6 +672,8 @@ static int ieee80211_add_chanctx(struct ieee80211_local *local,
 
 	lockdep_assert_wiphy(local->hw.wiphy);
 
+	ieee80211_add_wbrf(local, &ctx->conf.def);
+
 	if (!local->use_chanctx)
 		local->hw.conf.radar_enabled = ctx->conf.radar_enabled;
 
@@ -746,6 +753,8 @@ static void ieee80211_del_chanctx(struct ieee80211_local *local,
 	}
 
 	ieee80211_recalc_idle(local);
+
+	ieee80211_remove_wbrf(local, &ctx->conf.def);
 }
 
 static void ieee80211_free_chanctx(struct ieee80211_local *local,
@@ -858,7 +867,7 @@ static int ieee80211_assign_link_chanctx(struct ieee80211_link_data *link,
 	int ret = 0;
 
 	if (WARN_ON(sdata->vif.type == NL80211_IFTYPE_NAN))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	conf = rcu_dereference_protected(link->conf->chanctx_conf,
 					 lockdep_is_held(&local->hw.wiphy->mtx));
@@ -1106,7 +1115,7 @@ int ieee80211_link_reserve_chanctx(struct ieee80211_link_data *link,
 
 	curr_ctx = ieee80211_link_get_chanctx(link);
 	if (curr_ctx && local->use_chanctx && !local->ops->switch_vif_chanctx)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	new_ctx = ieee80211_find_reservation_chanctx(local, chandef, mode);
 	if (!new_ctx) {
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index b575ae90e57f..74be49191e70 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -497,6 +497,7 @@ static const char *hw_flag_names[] = {
 	FLAG(SUPPORTS_CONC_MON_RX_DECAP),
 	FLAG(DETECTS_COLOR_COLLISION),
 	FLAG(MLO_MCAST_MULTI_LINK_TX),
+	FLAG(DISALLOW_PUNCTURING),
 #undef FLAG
 };
 
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index ec91e131b29e..dce5606ed66d 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -22,88 +22,148 @@
 #include "debugfs_netdev.h"
 #include "driver-ops.h"
 
+struct ieee80211_if_read_sdata_data {
+	ssize_t (*format)(const struct ieee80211_sub_if_data *, char *, int);
+	struct ieee80211_sub_if_data *sdata;
+};
+
+static ssize_t ieee80211_if_read_sdata_handler(struct wiphy *wiphy,
+					       struct file *file,
+					       char *buf,
+					       size_t bufsize,
+					       void *data)
+{
+	struct ieee80211_if_read_sdata_data *d = data;
+
+	return d->format(d->sdata, buf, bufsize);
+}
+
 static ssize_t ieee80211_if_read_sdata(
-	struct ieee80211_sub_if_data *sdata,
+	struct file *file,
 	char __user *userbuf,
 	size_t count, loff_t *ppos,
 	ssize_t (*format)(const struct ieee80211_sub_if_data *sdata, char *, int))
 {
+	struct ieee80211_sub_if_data *sdata = file->private_data;
+	struct ieee80211_if_read_sdata_data data = {
+		.format = format,
+		.sdata = sdata,
+	};
 	char buf[200];
-	ssize_t ret = -EINVAL;
 
-	wiphy_lock(sdata->local->hw.wiphy);
-	ret = (*format)(sdata, buf, sizeof(buf));
-	wiphy_unlock(sdata->local->hw.wiphy);
+	return wiphy_locked_debugfs_read(sdata->local->hw.wiphy,
+					 file, buf, sizeof(buf),
+					 userbuf, count, ppos,
+					 ieee80211_if_read_sdata_handler,
+					 &data);
+}
+
+struct ieee80211_if_write_sdata_data {
+	ssize_t (*write)(struct ieee80211_sub_if_data *, const char *, int);
+	struct ieee80211_sub_if_data *sdata;
+};
 
-	if (ret >= 0)
-		ret = simple_read_from_buffer(userbuf, count, ppos, buf, ret);
+static ssize_t ieee80211_if_write_sdata_handler(struct wiphy *wiphy,
+						struct file *file,
+						char *buf,
+						size_t count,
+						void *data)
+{
+	struct ieee80211_if_write_sdata_data *d = data;
 
-	return ret;
+	return d->write(d->sdata, buf, count);
 }
 
 static ssize_t ieee80211_if_write_sdata(
-	struct ieee80211_sub_if_data *sdata,
+	struct file *file,
 	const char __user *userbuf,
 	size_t count, loff_t *ppos,
 	ssize_t (*write)(struct ieee80211_sub_if_data *sdata, const char *, int))
 {
+	struct ieee80211_sub_if_data *sdata = file->private_data;
+	struct ieee80211_if_write_sdata_data data = {
+		.write = write,
+		.sdata = sdata,
+	};
 	char buf[64];
-	ssize_t ret;
 
-	if (count >= sizeof(buf))
-		return -E2BIG;
+	return wiphy_locked_debugfs_write(sdata->local->hw.wiphy,
+					  file, buf, sizeof(buf),
+					  userbuf, count,
+					  ieee80211_if_write_sdata_handler,
+					  &data);
+}
 
-	if (copy_from_user(buf, userbuf, count))
-		return -EFAULT;
-	buf[count] = '\0';
+struct ieee80211_if_read_link_data {
+	ssize_t (*format)(const struct ieee80211_link_data *, char *, int);
+	struct ieee80211_link_data *link;
+};
 
-	wiphy_lock(sdata->local->hw.wiphy);
-	ret = (*write)(sdata, buf, count);
-	wiphy_unlock(sdata->local->hw.wiphy);
+static ssize_t ieee80211_if_read_link_handler(struct wiphy *wiphy,
+					      struct file *file,
+					      char *buf,
+					      size_t bufsize,
+					      void *data)
+{
+	struct ieee80211_if_read_link_data *d = data;
 
-	return ret;
+	return d->format(d->link, buf, bufsize);
 }
 
 static ssize_t ieee80211_if_read_link(
-	struct ieee80211_link_data *link,
+	struct file *file,
 	char __user *userbuf,
 	size_t count, loff_t *ppos,
 	ssize_t (*format)(const struct ieee80211_link_data *link, char *, int))
 {
+	struct ieee80211_link_data *link = file->private_data;
+	struct ieee80211_if_read_link_data data = {
+		.format = format,
+		.link = link,
+	};
 	char buf[200];
-	ssize_t ret = -EINVAL;
 
-	wiphy_lock(link->sdata->local->hw.wiphy);
-	ret = (*format)(link, buf, sizeof(buf));
-	wiphy_unlock(link->sdata->local->hw.wiphy);
+	return wiphy_locked_debugfs_read(link->sdata->local->hw.wiphy,
+					 file, buf, sizeof(buf),
+					 userbuf, count, ppos,
+					 ieee80211_if_read_link_handler,
+					 &data);
+}
+
+struct ieee80211_if_write_link_data {
+	ssize_t (*write)(struct ieee80211_link_data *, const char *, int);
+	struct ieee80211_link_data *link;
+};
 
-	if (ret >= 0)
-		ret = simple_read_from_buffer(userbuf, count, ppos, buf, ret);
+static ssize_t ieee80211_if_write_link_handler(struct wiphy *wiphy,
+					       struct file *file,
+					       char *buf,
+					       size_t count,
+					       void *data)
+{
+	struct ieee80211_if_write_sdata_data *d = data;
 
-	return ret;
+	return d->write(d->sdata, buf, count);
 }
 
 static ssize_t ieee80211_if_write_link(
-	struct ieee80211_link_data *link,
+	struct file *file,
 	const char __user *userbuf,
 	size_t count, loff_t *ppos,
 	ssize_t (*write)(struct ieee80211_link_data *link, const char *, int))
 {
+	struct ieee80211_link_data *link = file->private_data;
+	struct ieee80211_if_write_link_data data = {
+		.write = write,
+		.link = link,
+	};
 	char buf[64];
-	ssize_t ret;
-
-	if (count >= sizeof(buf))
-		return -E2BIG;
 
-	if (copy_from_user(buf, userbuf, count))
-		return -EFAULT;
-	buf[count] = '\0';
-
-	wiphy_lock(link->sdata->local->hw.wiphy);
-	ret = (*write)(link, buf, count);
-	wiphy_unlock(link->sdata->local->hw.wiphy);
-
-	return ret;
+	return wiphy_locked_debugfs_write(link->sdata->local->hw.wiphy,
+					  file, buf, sizeof(buf),
+					  userbuf, count,
+					  ieee80211_if_write_link_handler,
+					  &data);
 }
 
 #define IEEE80211_IF_FMT(name, type, field, format_string)		\
@@ -173,7 +233,7 @@ static ssize_t ieee80211_if_read_##name(struct file *file,		\
 					char __user *userbuf,		\
 					size_t count, loff_t *ppos)	\
 {									\
-	return ieee80211_if_read_sdata(file->private_data,		\
+	return ieee80211_if_read_sdata(file,				\
 				       userbuf, count, ppos,		\
 				       ieee80211_if_fmt_##name);	\
 }
@@ -183,7 +243,7 @@ static ssize_t ieee80211_if_write_##name(struct file *file,		\
 					 const char __user *userbuf,	\
 					 size_t count, loff_t *ppos)	\
 {									\
-	return ieee80211_if_write_sdata(file->private_data, userbuf,	\
+	return ieee80211_if_write_sdata(file, userbuf,			\
 					count, ppos,			\
 					ieee80211_if_parse_##name);	\
 }
@@ -211,7 +271,7 @@ static ssize_t ieee80211_if_read_##name(struct file *file,		\
 					char __user *userbuf,		\
 					size_t count, loff_t *ppos)	\
 {									\
-	return ieee80211_if_read_link(file->private_data,		\
+	return ieee80211_if_read_link(file,				\
 				      userbuf, count, ppos,		\
 				      ieee80211_if_fmt_##name);	\
 }
@@ -221,7 +281,7 @@ static ssize_t ieee80211_if_write_##name(struct file *file,		\
 					 const char __user *userbuf,	\
 					 size_t count, loff_t *ppos)	\
 {									\
-	return ieee80211_if_write_link(file->private_data, userbuf,	\
+	return ieee80211_if_write_link(file, userbuf,			\
 				       count, ppos,			\
 				       ieee80211_if_parse_##name);	\
 }
@@ -983,9 +1043,12 @@ void ieee80211_debugfs_recreate_netdev(struct ieee80211_sub_if_data *sdata,
 {
 	ieee80211_debugfs_remove_netdev(sdata);
 	ieee80211_debugfs_add_netdev(sdata, mld_vif);
-	drv_vif_add_debugfs(sdata->local, sdata);
-	if (!mld_vif)
-		ieee80211_link_debugfs_drv_add(&sdata->deflink);
+
+	if (sdata->flags & IEEE80211_SDATA_IN_DRIVER) {
+		drv_vif_add_debugfs(sdata->local, sdata);
+		if (!mld_vif)
+			ieee80211_link_debugfs_drv_add(&sdata->deflink);
+	}
 }
 
 void ieee80211_link_debugfs_add(struct ieee80211_link_data *link)
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index 06e3613bf46b..1e9389c49a57 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -16,7 +16,7 @@
 #include "sta_info.h"
 #include "driver-ops.h"
 
-/* sta attributtes */
+/* sta attributes */
 
 #define STA_READ(name, field, format_string)				\
 static ssize_t sta_ ##name## _read(struct file *file,			\
@@ -312,23 +312,14 @@ static ssize_t sta_aql_write(struct file *file, const char __user *userbuf,
 STA_OPS_RW(aql);
 
 
-static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf,
-					size_t count, loff_t *ppos)
+static ssize_t sta_agg_status_do_read(struct wiphy *wiphy, struct file *file,
+				      char *buf, size_t bufsz, void *data)
 {
-	char *buf, *p;
-	ssize_t bufsz = 71 + IEEE80211_NUM_TIDS * 40;
+	struct sta_info *sta = data;
+	char *p = buf;
 	int i;
-	struct sta_info *sta = file->private_data;
 	struct tid_ampdu_rx *tid_rx;
 	struct tid_ampdu_tx *tid_tx;
-	ssize_t ret;
-
-	buf = kzalloc(bufsz, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-	p = buf;
-
-	rcu_read_lock();
 
 	p += scnprintf(p, bufsz + buf - p, "next dialog_token: %#02x\n",
 			sta->ampdu_mlme.dialog_token_allocator + 1);
@@ -338,8 +329,8 @@ static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf,
 	for (i = 0; i < IEEE80211_NUM_TIDS; i++) {
 		bool tid_rx_valid;
 
-		tid_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[i]);
-		tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[i]);
+		tid_rx = wiphy_dereference(wiphy, sta->ampdu_mlme.tid_rx[i]);
+		tid_tx = wiphy_dereference(wiphy, sta->ampdu_mlme.tid_tx[i]);
 		tid_rx_valid = test_bit(i, sta->ampdu_mlme.agg_session_valid);
 
 		p += scnprintf(p, bufsz + buf - p, "%02d", i);
@@ -358,31 +349,39 @@ static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf,
 				tid_tx ? skb_queue_len(&tid_tx->pending) : 0);
 		p += scnprintf(p, bufsz + buf - p, "\n");
 	}
-	rcu_read_unlock();
 
-	ret = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf);
+	return p - buf;
+}
+
+static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf,
+				   size_t count, loff_t *ppos)
+{
+	struct sta_info *sta = file->private_data;
+	struct wiphy *wiphy = sta->local->hw.wiphy;
+	size_t bufsz = 71 + IEEE80211_NUM_TIDS * 40;
+	char *buf = kmalloc(bufsz, GFP_KERNEL);
+	ssize_t ret;
+
+	if (!buf)
+		return -ENOMEM;
+
+	ret = wiphy_locked_debugfs_read(wiphy, file, buf, bufsz,
+					userbuf, count, ppos,
+					sta_agg_status_do_read, sta);
 	kfree(buf);
+
 	return ret;
 }
 
-static ssize_t sta_agg_status_write(struct file *file, const char __user *userbuf,
-				    size_t count, loff_t *ppos)
+static ssize_t sta_agg_status_do_write(struct wiphy *wiphy, struct file *file,
+				       char *buf, size_t count, void *data)
 {
-	char _buf[25] = {}, *buf = _buf;
-	struct sta_info *sta = file->private_data;
+	struct sta_info *sta = data;
 	bool start, tx;
 	unsigned long tid;
-	char *pos;
+	char *pos = buf;
 	int ret, timeout = 5000;
 
-	if (count > sizeof(_buf))
-		return -EINVAL;
-
-	if (copy_from_user(buf, userbuf, count))
-		return -EFAULT;
-
-	buf[sizeof(_buf) - 1] = '\0';
-	pos = buf;
 	buf = strsep(&pos, " ");
 	if (!buf)
 		return -EINVAL;
@@ -420,7 +419,6 @@ static ssize_t sta_agg_status_write(struct file *file, const char __user *userbu
 	if (ret || tid >= IEEE80211_NUM_TIDS)
 		return -EINVAL;
 
-	wiphy_lock(sta->local->hw.wiphy);
 	if (tx) {
 		if (start)
 			ret = ieee80211_start_tx_ba_session(&sta->sta, tid,
@@ -432,10 +430,22 @@ static ssize_t sta_agg_status_write(struct file *file, const char __user *userbu
 					       3, true);
 		ret = 0;
 	}
-	wiphy_unlock(sta->local->hw.wiphy);
 
 	return ret ?: count;
 }
+
+static ssize_t sta_agg_status_write(struct file *file,
+				    const char __user *userbuf,
+				    size_t count, loff_t *ppos)
+{
+	struct sta_info *sta = file->private_data;
+	struct wiphy *wiphy = sta->local->hw.wiphy;
+	char _buf[26];
+
+	return wiphy_locked_debugfs_write(wiphy, file, _buf, sizeof(_buf),
+					  userbuf, count,
+					  sta_agg_status_do_write, sta);
+}
 STA_OPS_RW(agg_status);
 
 /* link sta attributes */
diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c
index 7938ec87ef25..3b7f70073fc3 100644
--- a/net/mac80211/driver-ops.c
+++ b/net/mac80211/driver-ops.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2015 Intel Deutschland GmbH
- * Copyright (C) 2022 Intel Corporation
+ * Copyright (C) 2022-2023 Intel Corporation
  */
 #include <net/mac80211.h>
 #include "ieee80211_i.h"
@@ -75,9 +75,9 @@ int drv_add_interface(struct ieee80211_local *local,
 	if (ret)
 		return ret;
 
-	sdata->flags |= IEEE80211_SDATA_IN_DRIVER;
+	if (!(sdata->flags & IEEE80211_SDATA_IN_DRIVER)) {
+		sdata->flags |= IEEE80211_SDATA_IN_DRIVER;
 
-	if (!local->in_reconfig) {
 		drv_vif_add_debugfs(local, sdata);
 		/* initially vif is not MLD */
 		ieee80211_link_debugfs_drv_add(&sdata->deflink);
@@ -113,9 +113,13 @@ void drv_remove_interface(struct ieee80211_local *local,
 	if (!check_sdata_in_driver(sdata))
 		return;
 
+	sdata->flags &= ~IEEE80211_SDATA_IN_DRIVER;
+
+	/* Remove driver debugfs entries */
+	ieee80211_debugfs_recreate_netdev(sdata, sdata->vif.valid_links);
+
 	trace_drv_remove_interface(local, sdata);
 	local->ops->remove_interface(&local->hw, &sdata->vif);
-	sdata->flags &= ~IEEE80211_SDATA_IN_DRIVER;
 	trace_drv_return_void(local);
 }
 
@@ -534,7 +538,7 @@ int drv_change_vif_links(struct ieee80211_local *local,
 	if (ret)
 		return ret;
 
-	if (!local->in_reconfig) {
+	if (!local->in_reconfig && !local->resuming) {
 		for_each_set_bit(link_id, &links_to_add,
 				 IEEE80211_MLD_MAX_NUM_LINKS) {
 			link = rcu_access_pointer(sdata->link[link_id]);
@@ -589,6 +593,10 @@ int drv_change_sta_links(struct ieee80211_local *local,
 	if (ret)
 		return ret;
 
+	/* during reconfig don't add it to debugfs again */
+	if (local->in_reconfig || local->resuming)
+		return 0;
+
 	for_each_set_bit(link_id, &links_to_add, IEEE80211_MLD_MAX_NUM_LINKS) {
 		link_sta = rcu_dereference_protected(info->link[link_id],
 						     lockdep_is_held(&local->hw.wiphy->mtx));
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 568633b38c47..eb482fb8c3af 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -23,7 +23,7 @@
 static inline struct ieee80211_sub_if_data *
 get_bss_sdata(struct ieee80211_sub_if_data *sdata)
 {
-	if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+	if (sdata && sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
 		sdata = container_of(sdata->bss, struct ieee80211_sub_if_data,
 				     u.ap);
 
@@ -695,11 +695,14 @@ static inline void drv_flush(struct ieee80211_local *local,
 			     struct ieee80211_sub_if_data *sdata,
 			     u32 queues, bool drop)
 {
-	struct ieee80211_vif *vif = sdata ? &sdata->vif : NULL;
+	struct ieee80211_vif *vif;
 
 	might_sleep();
 	lockdep_assert_wiphy(local->hw.wiphy);
 
+	sdata = get_bss_sdata(sdata);
+	vif = sdata ? &sdata->vif : NULL;
+
 	if (sdata && !check_sdata_in_driver(sdata))
 		return;
 
@@ -716,6 +719,8 @@ static inline void drv_flush_sta(struct ieee80211_local *local,
 	might_sleep();
 	lockdep_assert_wiphy(local->hw.wiphy);
 
+	sdata = get_bss_sdata(sdata);
+
 	if (sdata && !check_sdata_in_driver(sdata))
 		return;
 
@@ -800,7 +805,7 @@ drv_cancel_remain_on_channel(struct ieee80211_local *local,
 static inline int drv_set_ringparam(struct ieee80211_local *local,
 				    u32 tx, u32 rx)
 {
-	int ret = -ENOTSUPP;
+	int ret = -EOPNOTSUPP;
 
 	might_sleep();
 	lockdep_assert_wiphy(local->hw.wiphy);
@@ -1661,6 +1666,26 @@ static inline int drv_net_setup_tc(struct ieee80211_local *local,
 	return ret;
 }
 
+static inline bool drv_can_activate_links(struct ieee80211_local *local,
+					  struct ieee80211_sub_if_data *sdata,
+					  u16 active_links)
+{
+	bool ret = true;
+
+	lockdep_assert_wiphy(local->hw.wiphy);
+
+	if (!check_sdata_in_driver(sdata))
+		return false;
+
+	trace_drv_can_activate_links(local, sdata, active_links);
+	if (local->ops->can_activate_links)
+		ret = local->ops->can_activate_links(&local->hw, &sdata->vif,
+						     active_links);
+	trace_drv_return_bool(local, ret);
+
+	return ret;
+}
+
 int drv_change_vif_links(struct ieee80211_local *local,
 			 struct ieee80211_sub_if_data *sdata,
 			 u16 old_links, u16 new_links,
diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c
index 68cea2685224..749f4ecab990 100644
--- a/net/mac80211/ht.c
+++ b/net/mac80211/ht.c
@@ -271,6 +271,7 @@ bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata,
 	case NL80211_CHAN_WIDTH_80:
 	case NL80211_CHAN_WIDTH_80P80:
 	case NL80211_CHAN_WIDTH_160:
+	case NL80211_CHAN_WIDTH_320:
 		bw = ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 ?
 				IEEE80211_STA_RX_BW_40 : IEEE80211_STA_RX_BW_20;
 		break;
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 8b1e02f2f9ae..8f2b445a5ec3 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -485,7 +485,7 @@ int ieee80211_ibss_csa_beacon(struct ieee80211_sub_if_data *sdata,
 				ifibss->ssid_len, IEEE80211_BSS_TYPE_IBSS,
 				IEEE80211_PRIVACY(ifibss->privacy));
 
-	if (WARN_ON(!cbss))
+	if (unlikely(!cbss))
 		return -EINVAL;
 
 	rcu_read_lock();
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 84df104f272b..0b2b53550bd9 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -92,11 +92,14 @@ enum ieee80211_status_data {
 	IEEE80211_STATUS_SUBDATA_MASK	= 0xff0,
 };
 
-/*
- * Keep a station's queues on the active list for deficit accounting purposes
- * if it was active or queued during the last 100ms
- */
-#define AIRTIME_ACTIVE_DURATION (HZ / 10)
+static inline bool
+ieee80211_sta_keep_active(struct sta_info *sta, u8 ac)
+{
+	/* Keep a station's queues on the active list for deficit accounting
+	 * purposes if it was active or queued during the last 100ms.
+	 */
+	return time_before_eq(jiffies, sta->airtime[ac].last_active + HZ / 10);
+}
 
 struct ieee80211_bss {
 	u32 device_ts_beacon, device_ts_presp;
@@ -436,6 +439,7 @@ struct ieee80211_mgd_assoc_data {
 	bool need_beacon;
 	bool synced;
 	bool timeout_started;
+	bool comeback; /* whether the AP has requested association comeback */
 	bool s1g;
 
 	unsigned int assoc_link_id;
@@ -1559,6 +1563,8 @@ struct ieee80211_local {
 
 	/* extended capabilities provided by mac80211 */
 	u8 ext_capa[8];
+
+	bool wbrf_supported;
 };
 
 static inline struct ieee80211_sub_if_data *
@@ -1770,10 +1776,7 @@ static inline bool txq_has_queue(struct ieee80211_txq *txq)
 static inline bool
 ieee80211_have_rx_timestamp(struct ieee80211_rx_status *status)
 {
-	WARN_ON_ONCE(status->flag & RX_FLAG_MACTIME_START &&
-		     status->flag & RX_FLAG_MACTIME_END);
-	return !!(status->flag & (RX_FLAG_MACTIME_START | RX_FLAG_MACTIME_END |
-				  RX_FLAG_MACTIME_PLCP_START));
+	return status->flag & RX_FLAG_MACTIME;
 }
 
 void ieee80211_vif_inc_num_mcast(struct ieee80211_sub_if_data *sdata);
@@ -2600,4 +2603,19 @@ ieee80211_eht_cap_ie_to_sta_eht_cap(struct ieee80211_sub_if_data *sdata,
 				    const struct ieee80211_eht_cap_elem *eht_cap_ie_elem,
 				    u8 eht_cap_len,
 				    struct link_sta_info *link_sta);
+
+void ieee80211_check_wbrf_support(struct ieee80211_local *local);
+void ieee80211_add_wbrf(struct ieee80211_local *local, struct cfg80211_chan_def *chandef);
+void ieee80211_remove_wbrf(struct ieee80211_local *local, struct cfg80211_chan_def *chandef);
+
+#if IS_ENABLED(CONFIG_MAC80211_KUNIT_TEST)
+#define EXPORT_SYMBOL_IF_MAC80211_KUNIT(sym) EXPORT_SYMBOL_IF_KUNIT(sym)
+#define VISIBLE_IF_MAC80211_KUNIT
+ieee80211_rx_result
+ieee80211_drop_unencrypted_mgmt(struct ieee80211_rx_data *rx);
+#else
+#define EXPORT_SYMBOL_IF_MAC80211_KUNIT(sym)
+#define VISIBLE_IF_MAC80211_KUNIT static
+#endif
+
 #endif /* IEEE80211_I_H */
diff --git a/net/mac80211/link.c b/net/mac80211/link.c
index bf7bd880d062..d4f86955afa6 100644
--- a/net/mac80211/link.c
+++ b/net/mac80211/link.c
@@ -444,6 +444,9 @@ int ieee80211_set_active_links(struct ieee80211_vif *vif, u16 active_links)
 
 	lockdep_assert_wiphy(local->hw.wiphy);
 
+	if (!drv_can_activate_links(local, sdata, active_links))
+		return -EINVAL;
+
 	old_active = sdata->vif.active_links;
 	if (old_active & active_links) {
 		/*
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 033a5261ac3a..f2ece7793573 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -1405,6 +1405,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	debugfs_hw_add(local);
 	rate_control_add_debugfs(local);
 
+	ieee80211_check_wbrf_support(local);
+
 	rtnl_lock();
 	wiphy_lock(hw->wiphy);
 
diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index 775d52561c54..024f48db6b05 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -151,7 +151,7 @@ static int mesh_path_sel_frame_tx(enum mpath_frame_type action, u8 flags,
 		break;
 	default:
 		kfree_skb(skb);
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 	*pos++ = ie_len;
 	*pos++ = flags;
diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c
index 8a3f44ce3e04..735edde1bd81 100644
--- a/net/mac80211/mesh_pathtbl.c
+++ b/net/mac80211/mesh_pathtbl.c
@@ -676,10 +676,10 @@ struct mesh_path *mesh_path_add(struct ieee80211_sub_if_data *sdata,
 
 	if (ether_addr_equal(dst, sdata->vif.addr))
 		/* never add ourselves as neighbours */
-		return ERR_PTR(-ENOTSUPP);
+		return ERR_PTR(-EOPNOTSUPP);
 
 	if (is_multicast_ether_addr(dst))
-		return ERR_PTR(-ENOTSUPP);
+		return ERR_PTR(-EOPNOTSUPP);
 
 	if (atomic_add_unless(&sdata->u.mesh.mpaths, 1, MESH_MAX_MPATHS) == 0)
 		return ERR_PTR(-ENOSPC);
@@ -719,10 +719,10 @@ int mpp_path_add(struct ieee80211_sub_if_data *sdata,
 
 	if (ether_addr_equal(dst, sdata->vif.addr))
 		/* never add ourselves as neighbours */
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (is_multicast_ether_addr(dst))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	new_mpath = mesh_path_new(sdata, dst, GFP_ATOMIC);
 
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index dbabeefe4515..28bf794f67f8 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -1068,8 +1068,8 @@ mesh_plink_get_event(struct ieee80211_sub_if_data *sdata,
 	case WLAN_SP_MESH_PEERING_OPEN:
 		if (!matches_local)
 			event = OPN_RJCT;
-		if (!mesh_plink_free_count(sdata) ||
-		    (sta->mesh->plid && sta->mesh->plid != plid))
+		else if (!mesh_plink_free_count(sdata) ||
+			 (sta->mesh->plid && sta->mesh->plid != plid))
 			event = OPN_IGNR;
 		else
 			event = OPN_ACPT;
@@ -1077,9 +1077,9 @@ mesh_plink_get_event(struct ieee80211_sub_if_data *sdata,
 	case WLAN_SP_MESH_PEERING_CONFIRM:
 		if (!matches_local)
 			event = CNF_RJCT;
-		if (!mesh_plink_free_count(sdata) ||
-		    sta->mesh->llid != llid ||
-		    (sta->mesh->plid && sta->mesh->plid != plid))
+		else if (!mesh_plink_free_count(sdata) ||
+			 sta->mesh->llid != llid ||
+			 (sta->mesh->plid && sta->mesh->plid != plid))
 			event = CNF_IGNR;
 		else
 			event = CNF_ACPT;
@@ -1247,6 +1247,8 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata,
 			return;
 	}
 	elems = ieee802_11_parse_elems(baseaddr, len - baselen, true, NULL);
-	mesh_process_plink_frame(sdata, mgmt, elems, rx_status);
-	kfree(elems);
+	if (elems) {
+		mesh_process_plink_frame(sdata, mgmt, elems, rx_status);
+		kfree(elems);
+	}
 }
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 887b496f2b81..073105deb424 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -43,6 +43,9 @@
 #define IEEE80211_ASSOC_TIMEOUT_SHORT	(HZ / 10)
 #define IEEE80211_ASSOC_MAX_TRIES	3
 
+#define IEEE80211_ADV_TTLM_SAFETY_BUFFER_MS msecs_to_jiffies(100)
+#define IEEE80211_ADV_TTLM_ST_UNDERFLOW 0xff00
+
 static int max_nullfunc_tries = 2;
 module_param(max_nullfunc_tries, int, 0644);
 MODULE_PARM_DESC(max_nullfunc_tries,
@@ -135,6 +138,7 @@ ieee80211_handle_puncturing_bitmap(struct ieee80211_link_data *link,
 				   u16 bitmap, u64 *changed)
 {
 	struct cfg80211_chan_def *chandef = &link->conf->chandef;
+	struct ieee80211_local *local = link->sdata->local;
 	u16 extracted;
 	u64 _changed = 0;
 
@@ -147,7 +151,9 @@ ieee80211_handle_puncturing_bitmap(struct ieee80211_link_data *link,
 							 bitmap);
 
 		if (cfg80211_valid_disable_subchannel_bitmap(&bitmap,
-							     chandef))
+							     chandef) &&
+		    !(bitmap && ieee80211_hw_check(&local->hw,
+						   DISALLOW_PUNCTURING)))
 			break;
 		link->u.mgd.conn_flags |=
 			ieee80211_chandef_downgrade(chandef);
@@ -595,6 +601,7 @@ static int ieee80211_config_bw(struct ieee80211_link_data *link,
 		return ret;
 	}
 
+	cfg80211_schedule_channels_check(&sdata->wdev);
 	return 0;
 }
 
@@ -1382,7 +1389,7 @@ static int ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 	struct ieee80211_mgmt *mgmt;
 	u8 *pos, qos_info, *ie_start;
 	size_t offset, noffset;
-	u16 capab = WLAN_CAPABILITY_ESS, link_capab;
+	u16 capab = 0, link_capab;
 	__le16 listen_int;
 	struct element *ext_capa = NULL;
 	enum nl80211_iftype iftype = ieee80211_vif_type_p2p(&sdata->vif);
@@ -1529,6 +1536,17 @@ static int ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 	*pos++ = assoc_data->ssid_len;
 	memcpy(pos, assoc_data->ssid, assoc_data->ssid_len);
 
+	/*
+	 * This bit is technically reserved, so it shouldn't matter for either
+	 * the AP or us, but it also means we shouldn't set it. However, we've
+	 * always set it in the past, and apparently some EHT APs check that
+	 * we don't set it. To avoid interoperability issues with old APs that
+	 * for some reason check it and want it to be set, set the bit for all
+	 * pre-EHT connections as we used to do.
+	 */
+	if (link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_EHT)
+		capab |= WLAN_CAPABILITY_ESS;
+
 	/* add the elements for the assoc (main) link */
 	link_capab = capab;
 	offset = ieee80211_assoc_link_elems(sdata, skb, &link_capab,
@@ -5367,6 +5385,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 			   assoc_data->ap_addr, tu, ms);
 		assoc_data->timeout = jiffies + msecs_to_jiffies(ms);
 		assoc_data->timeout_started = true;
+		assoc_data->comeback = true;
 		if (ms > IEEE80211_ASSOC_TIMEOUT)
 			run_again(sdata, assoc_data->timeout);
 		goto notify_driver;
@@ -5388,33 +5407,24 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 		}
 
 		if (ieee80211_vif_is_mld(&sdata->vif)) {
+			struct ieee80211_mle_basic_common_info *common;
+
 			if (!elems->ml_basic) {
 				sdata_info(sdata,
-					   "MLO association with %pM but no multi-link element in response!\n",
+					   "MLO association with %pM but no (basic) multi-link element in response!\n",
 					   assoc_data->ap_addr);
 				goto abandon_assoc;
 			}
 
-			if (le16_get_bits(elems->ml_basic->control,
-					  IEEE80211_ML_CONTROL_TYPE) !=
-					IEEE80211_ML_CONTROL_TYPE_BASIC) {
+			common = (void *)elems->ml_basic->variable;
+
+			if (memcmp(assoc_data->ap_addr,
+				   common->mld_mac_addr, ETH_ALEN)) {
 				sdata_info(sdata,
-					   "bad multi-link element (control=0x%x)\n",
-					   le16_to_cpu(elems->ml_basic->control));
+					   "AP MLD MAC address mismatch: got %pM expected %pM\n",
+					   common->mld_mac_addr,
+					   assoc_data->ap_addr);
 				goto abandon_assoc;
-			} else {
-				struct ieee80211_mle_basic_common_info *common;
-
-				common = (void *)elems->ml_basic->variable;
-
-				if (memcmp(assoc_data->ap_addr,
-					   common->mld_mac_addr, ETH_ALEN)) {
-					sdata_info(sdata,
-						   "AP MLD MAC address mismatch: got %pM expected %pM\n",
-						   common->mld_mac_addr,
-						   assoc_data->ap_addr);
-					goto abandon_assoc;
-				}
 			}
 		}
 
@@ -5682,6 +5692,7 @@ static bool ieee80211_config_puncturing(struct ieee80211_link_data *link,
 					const struct ieee80211_eht_operation *eht_oper,
 					u64 *changed)
 {
+	struct ieee80211_local *local = link->sdata->local;
 	u16 bitmap = 0, extracted;
 
 	if ((eht_oper->params & IEEE80211_EHT_OPER_INFO_PRESENT) &&
@@ -5713,6 +5724,9 @@ static bool ieee80211_config_puncturing(struct ieee80211_link_data *link,
 		return false;
 	}
 
+	if (bitmap && ieee80211_hw_check(&local->hw, DISALLOW_PUNCTURING))
+		return false;
+
 	ieee80211_handle_puncturing_bitmap(link, eht_oper, bitmap, changed);
 	return true;
 }
@@ -5782,7 +5796,7 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata,
 {
 	const struct ieee80211_multi_link_elem *ml;
 	const struct element *sub;
-	size_t ml_len;
+	ssize_t ml_len;
 	unsigned long removed_links = 0;
 	u16 link_removal_timeout[IEEE80211_MLD_MAX_NUM_LINKS] = {};
 	u8 link_id;
@@ -5798,6 +5812,8 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata,
 					     elems->scratch + elems->scratch_len -
 					     elems->scratch_pos,
 					     WLAN_EID_FRAGMENT);
+	if (ml_len < 0)
+		return;
 
 	elems->ml_reconf = (const void *)elems->scratch_pos;
 	elems->ml_reconf_len = ml_len;
@@ -5944,6 +5960,13 @@ ieee80211_parse_adv_t2l(struct ieee80211_sub_if_data *sdata,
 	pos++;
 
 	ttlm_info->switch_time = get_unaligned_le16(pos);
+
+	/* Since ttlm_info->switch_time == 0 means no switch time, bump it
+	 * by 1.
+	 */
+	if (!ttlm_info->switch_time)
+		ttlm_info->switch_time = 1;
+
 	pos += 2;
 
 	if (control & IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT) {
@@ -6038,25 +6061,46 @@ static void ieee80211_process_adv_ttlm(struct ieee80211_sub_if_data *sdata,
 		}
 
 		if (ttlm_info.switch_time) {
-			u32 st_us, delay = 0;
-			u32 ts_l26 = beacon_ts & GENMASK(25, 0);
+			u16 beacon_ts_tu, st_tu, delay;
+			u32 delay_jiffies;
+			u64 mask;
 
 			/* The t2l map switch time is indicated with a partial
-			 * TSF value, convert it to TSF and calc the delay
-			 * to the start time.
+			 * TSF value (bits 10 to 25), get the partial beacon TS
+			 * as well, and calc the delay to the start time.
 			 */
-			st_us = ieee80211_tu_to_usec(ttlm_info.switch_time);
-			if (st_us > ts_l26)
-				delay = st_us - ts_l26;
+			mask = GENMASK_ULL(25, 10);
+			beacon_ts_tu = (beacon_ts & mask) >> 10;
+			st_tu = ttlm_info.switch_time;
+			delay = st_tu - beacon_ts_tu;
+
+			/*
+			 * If the switch time is far in the future, then it
+			 * could also be the previous switch still being
+			 * announced.
+			 * We can simply ignore it for now, if it is a future
+			 * switch the AP will continue to announce it anyway.
+			 */
+			if (delay > IEEE80211_ADV_TTLM_ST_UNDERFLOW)
+				return;
+
+			delay_jiffies = TU_TO_JIFFIES(delay);
+
+			/* Link switching can take time, so schedule it
+			 * 100ms before to be ready on time
+			 */
+			if (delay_jiffies > IEEE80211_ADV_TTLM_SAFETY_BUFFER_MS)
+				delay_jiffies -=
+					IEEE80211_ADV_TTLM_SAFETY_BUFFER_MS;
 			else
-				continue;
+				delay_jiffies = 0;
 
 			sdata->u.mgd.ttlm_info = ttlm_info;
 			wiphy_delayed_work_cancel(sdata->local->hw.wiphy,
 						  &sdata->u.mgd.ttlm_work);
 			wiphy_delayed_work_queue(sdata->local->hw.wiphy,
 						 &sdata->u.mgd.ttlm_work,
-						 usecs_to_jiffies(delay));
+						 delay_jiffies);
 			return;
 		}
 	}
@@ -6700,8 +6744,18 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata)
 			}
 			ifmgd->auth_data->timeout_started = true;
 		} else if (ifmgd->assoc_data &&
+			   !ifmgd->assoc_data->comeback &&
 			   (ieee80211_is_assoc_req(fc) ||
 			    ieee80211_is_reassoc_req(fc))) {
+			/*
+			 * Update association timeout based on the TX status
+			 * for the (Re)Association Request frame. Skip this if
+			 * we have already processed a (Re)Association Response
+			 * frame that indicated need for association comeback
+			 * at a specific time in the future. This could happen
+			 * if the TX status information is delayed enough for
+			 * the response to be received and processed first.
+			 */
 			if (status_acked) {
 				ifmgd->assoc_data->timeout =
 					jiffies + IEEE80211_ASSOC_TIMEOUT_SHORT;
@@ -7584,7 +7638,8 @@ ieee80211_setup_assoc_link(struct ieee80211_sub_if_data *sdata,
 
 			bitmap = get_unaligned_le16(disable_subchannel_bitmap);
 			if (cfg80211_valid_disable_subchannel_bitmap(&bitmap,
-								     &link->conf->chandef))
+								     &link->conf->chandef) &&
+			    !(bitmap && ieee80211_hw_check(&local->hw, DISALLOW_PUNCTURING)))
 				ieee80211_handle_puncturing_bitmap(link,
 								   eht_oper,
 								   bitmap,
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 64352e4e6d00..0bf72928ccfc 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -19,6 +19,7 @@
 #include <linux/export.h>
 #include <linux/kcov.h>
 #include <linux/bitops.h>
+#include <kunit/visibility.h>
 #include <net/mac80211.h>
 #include <net/ieee80211_radiotap.h>
 #include <asm/unaligned.h>
@@ -566,7 +567,8 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 
 	if (local->hw.radiotap_timestamp.units_pos >= 0) {
 		u16 accuracy = 0;
-		u8 flags = IEEE80211_RADIOTAP_TIMESTAMP_FLAG_32BIT;
+		u8 flags;
+		u64 ts;
 
 		rthdr->it_present |=
 			cpu_to_le32(BIT(IEEE80211_RADIOTAP_TIMESTAMP));
@@ -575,7 +577,15 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 		while ((pos - (u8 *)rthdr) & 7)
 			pos++;
 
-		put_unaligned_le64(status->device_timestamp, pos);
+		if (status->flag & RX_FLAG_MACTIME_IS_RTAP_TS64) {
+			flags = IEEE80211_RADIOTAP_TIMESTAMP_FLAG_64BIT;
+			ts = status->mactime;
+		} else {
+			flags = IEEE80211_RADIOTAP_TIMESTAMP_FLAG_32BIT;
+			ts = status->device_timestamp;
+		}
+
+		put_unaligned_le64(ts, pos);
 		pos += sizeof(u64);
 
 		if (local->hw.radiotap_timestamp.accuracy >= 0) {
@@ -920,7 +930,7 @@ static void ieee80211_parse_qos(struct ieee80211_rx_data *rx)
  * Drivers always need to pass packets that are aligned to two-byte boundaries
  * to the stack.
  *
- * Additionally, should, if possible, align the payload data in a way that
+ * Additionally, they should, if possible, align the payload data in a way that
  * guarantees that the contained IP header is aligned to a four-byte
  * boundary. In the case of regular frames, this simply means aligning the
  * payload to a four-byte boundary (because either the IP header is directly
@@ -936,7 +946,7 @@ static void ieee80211_parse_qos(struct ieee80211_rx_data *rx)
  * subframe to a length that is a multiple of four.
  *
  * Padding like Atheros hardware adds which is between the 802.11 header and
- * the payload is not supported, the driver is required to move the 802.11
+ * the payload is not supported; the driver is required to move the 802.11
  * header to be directly in front of the payload in that case.
  */
 static void ieee80211_verify_alignment(struct ieee80211_rx_data *rx)
@@ -2405,7 +2415,7 @@ static int ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc)
 	return 0;
 }
 
-static ieee80211_rx_result
+VISIBLE_IF_MAC80211_KUNIT ieee80211_rx_result
 ieee80211_drop_unencrypted_mgmt(struct ieee80211_rx_data *rx)
 {
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb);
@@ -2484,6 +2494,7 @@ ieee80211_drop_unencrypted_mgmt(struct ieee80211_rx_data *rx)
 
 	return RX_CONTINUE;
 }
+EXPORT_SYMBOL_IF_MAC80211_KUNIT(ieee80211_drop_unencrypted_mgmt);
 
 static ieee80211_rx_result
 __ieee80211_data_to_8023(struct ieee80211_rx_data *rx, bool *port_control)
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 24fa06105378..645355e5f1bc 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -194,11 +194,32 @@ ieee80211_bss_info_update(struct ieee80211_local *local,
 	if (scan_sdata && scan_sdata->vif.type == NL80211_IFTYPE_STATION &&
 	    scan_sdata->vif.cfg.assoc &&
 	    ieee80211_have_rx_timestamp(rx_status)) {
-		bss_meta.parent_tsf =
-			ieee80211_calculate_rx_timestamp(local, rx_status,
-							 len + FCS_LEN, 24);
-		ether_addr_copy(bss_meta.parent_bssid,
-				scan_sdata->vif.bss_conf.bssid);
+		struct ieee80211_bss_conf *link_conf = NULL;
+
+		/* for an MLO connection, set the TSF data only in case we have
+		 * an indication on which of the links the frame was received
+		 */
+		if (ieee80211_vif_is_mld(&scan_sdata->vif)) {
+			if (rx_status->link_valid) {
+				s8 link_id = rx_status->link_id;
+
+				link_conf =
+					rcu_dereference(scan_sdata->vif.link_conf[link_id]);
+			}
+		} else {
+			link_conf = &scan_sdata->vif.bss_conf;
+		}
+
+		if (link_conf) {
+			bss_meta.parent_tsf =
+				ieee80211_calculate_rx_timestamp(local,
+								 rx_status,
+								 len + FCS_LEN,
+								 24);
+
+			ether_addr_copy(bss_meta.parent_bssid,
+					link_conf->bssid);
+		}
 	}
 	rcu_read_unlock();
 
@@ -666,6 +687,21 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 	if (local->scan_req)
 		return -EBUSY;
 
+	/* For an MLO connection, if a link ID was specified, validate that it
+	 * is indeed active. If no link ID was specified, select one of the
+	 * active links.
+	 */
+	if (ieee80211_vif_is_mld(&sdata->vif)) {
+		if (req->tsf_report_link_id >= 0) {
+			if (!(sdata->vif.active_links &
+			      BIT(req->tsf_report_link_id)))
+				return -EINVAL;
+		} else {
+			req->tsf_report_link_id =
+				__ffs(sdata->vif.active_links);
+		}
+	}
+
 	if (!__ieee80211_can_leave_ch(sdata))
 		return -EBUSY;
 
@@ -714,6 +750,8 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 		local->hw_scan_req->req.duration = req->duration;
 		local->hw_scan_req->req.duration_mandatory =
 			req->duration_mandatory;
+		local->hw_scan_req->req.tsf_report_link_id =
+			req->tsf_report_link_id;
 
 		local->hw_scan_band = 0;
 		local->hw_scan_req->req.n_6ghz_params = req->n_6ghz_params;
@@ -1251,7 +1289,7 @@ int __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata,
 	iebufsz = local->scan_ies_len + req->ie_len;
 
 	if (!local->ops->sched_scan_start)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	for (i = 0; i < NUM_NL80211_BANDS; i++) {
 		if (local->hw.wiphy->bands[i]) {
@@ -1316,7 +1354,7 @@ int ieee80211_request_sched_scan_stop(struct ieee80211_local *local)
 	lockdep_assert_wiphy(local->hw.wiphy);
 
 	if (!local->ops->sched_scan_stop)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	/* We don't want to restart sched scan anymore. */
 	RCU_INIT_POINTER(local->sched_scan_req, NULL);
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 0ba613dd1cc4..bf1adcd96b41 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -40,7 +40,7 @@
  * either sta_info_insert() or sta_info_insert_rcu(); only in the latter
  * case (which acquires an rcu read section but must not be called from
  * within one) will the pointer still be valid after the call. Note that
- * the caller may not do much with the STA info before inserting it, in
+ * the caller may not do much with the STA info before inserting it; in
  * particular, it may not start any mesh peer link management or add
  * encryption keys.
  *
@@ -58,7 +58,7 @@
  * In order to remove a STA info structure, various sta_info_destroy_*()
  * calls are available.
  *
- * There is no concept of ownership on a STA entry, each structure is
+ * There is no concept of ownership on a STA entry; each structure is
  * owned by the global hash table/list until it is removed. All users of
  * the structure need to be RCU protected so that the structure won't be
  * freed before they are done using it.
@@ -2268,7 +2268,6 @@ void ieee80211_sta_register_airtime(struct ieee80211_sta *pubsta, u8 tid,
 	struct ieee80211_local *local = sta->sdata->local;
 	u8 ac = ieee80211_ac_from_tid(tid);
 	u32 airtime = 0;
-	u32 diff;
 
 	if (sta->local->airtime_flags & AIRTIME_USE_TX)
 		airtime += tx_airtime;
@@ -2279,8 +2278,7 @@ void ieee80211_sta_register_airtime(struct ieee80211_sta *pubsta, u8 tid,
 	sta->airtime[ac].tx_airtime += tx_airtime;
 	sta->airtime[ac].rx_airtime += rx_airtime;
 
-	diff = (u32)jiffies - sta->airtime[ac].last_active;
-	if (diff <= AIRTIME_ACTIVE_DURATION)
+	if (ieee80211_sta_keep_active(sta, ac))
 		sta->airtime[ac].deficit -= airtime;
 
 	spin_unlock_bh(&local->active_txq_lock[ac]);
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index 7acf2223e47a..5ef1554f991f 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -138,7 +138,7 @@ enum ieee80211_agg_stop_reason {
 struct airtime_info {
 	u64 rx_airtime;
 	u64 tx_airtime;
-	u32 last_active;
+	unsigned long last_active;
 	s32 deficit;
 	atomic_t aql_tx_pending; /* Estimated airtime for frames pending */
 	u32 aql_limit_low;
diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c
index 05a7dff69fe9..49730b424141 100644
--- a/net/mac80211/tdls.c
+++ b/net/mac80211/tdls.c
@@ -1001,7 +1001,7 @@ ieee80211_tdls_build_mgmt_packet_data(struct ieee80211_sub_if_data *sdata,
 						 skb);
 		break;
 	default:
-		ret = -ENOTSUPP;
+		ret = -EOPNOTSUPP;
 		break;
 	}
 
@@ -1071,7 +1071,7 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev,
 		/* any value is ok */
 		break;
 	default:
-		ret = -ENOTSUPP;
+		ret = -EOPNOTSUPP;
 		break;
 	}
 
@@ -1177,7 +1177,7 @@ ieee80211_tdls_mgmt_setup(struct wiphy *wiphy, struct net_device *dev,
 	    smps_mode != IEEE80211_SMPS_OFF) {
 		tdls_dbg(sdata, "Aborting TDLS setup due to SMPS mode %d\n",
 			 smps_mode);
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 
 	lockdep_assert_wiphy(local->hw.wiphy);
@@ -1289,7 +1289,7 @@ int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev,
 	int ret;
 
 	if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	/* make sure we are in managed mode, and associated */
 	if (sdata->vif.type != NL80211_IFTYPE_STATION ||
@@ -1446,7 +1446,7 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev,
 	lockdep_assert_wiphy(local->hw.wiphy);
 
 	if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (sdata->vif.type != NL80211_IFTYPE_STATION)
 		return -EINVAL;
@@ -1459,7 +1459,7 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev,
 	case NL80211_TDLS_SETUP:
 	case NL80211_TDLS_DISCOVERY_REQ:
 		/* We don't support in-driver setup/teardown/discovery */
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 
 	/* protect possible bss_conf changes and avoid concurrency in
@@ -1510,7 +1510,7 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev,
 			return ret;
 		break;
 	default:
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 
 	if (ether_addr_equal(sdata->u.mgd.tdls_peer, peer)) {
@@ -1673,7 +1673,7 @@ ieee80211_tdls_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 	if (!test_sta_flag(sta, WLAN_STA_TDLS_CHAN_SWITCH)) {
 		tdls_dbg(sdata, "TDLS channel switch unsupported by %pM\n",
 			 addr);
-		ret = -ENOTSUPP;
+		ret = -EOPNOTSUPP;
 		goto out;
 	}
 
@@ -1993,7 +1993,7 @@ ieee80211_process_tdls_channel_switch_req(struct ieee80211_sub_if_data *sdata,
 	if (!sta->sta.deflink.ht_cap.ht_supported && elems->sec_chan_offs &&
 	    elems->sec_chan_offs->sec_chan_offs) {
 		tdls_dbg(sdata, "TDLS chan switch - wide chan unsupported\n");
-		ret = -ENOTSUPP;
+		ret = -EOPNOTSUPP;
 		goto out;
 	}
 
diff --git a/net/mac80211/tests/Makefile b/net/mac80211/tests/Makefile
index 4814584f8a14..4fdaf3feaca3 100644
--- a/net/mac80211/tests/Makefile
+++ b/net/mac80211/tests/Makefile
@@ -1,3 +1,3 @@
-mac80211-tests-y += module.o elems.o
+mac80211-tests-y += module.o elems.o mfp.o
 
 obj-$(CONFIG_MAC80211_KUNIT_TEST) += mac80211-tests.o
diff --git a/net/mac80211/tests/mfp.c b/net/mac80211/tests/mfp.c
new file mode 100644
index 000000000000..a8dc1601da60
--- /dev/null
+++ b/net/mac80211/tests/mfp.c
@@ -0,0 +1,286 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * KUnit tests for management frame acceptance
+ *
+ * Copyright (C) 2023 Intel Corporation
+ */
+#include <kunit/test.h>
+#include <kunit/skbuff.h>
+#include "../ieee80211_i.h"
+#include "../sta_info.h"
+
+MODULE_IMPORT_NS(EXPORTED_FOR_KUNIT_TESTING);
+
+static const struct mfp_test_case {
+	const char *desc;
+	bool sta, mfp, decrypted, unicast, assoc;
+	u8 category;
+	u8 stype;
+	u8 action;
+	ieee80211_rx_result result;
+} accept_mfp_cases[] = {
+	/* regular public action */
+	{
+		.desc = "public action: accept unicast from unknown peer",
+		.stype = IEEE80211_STYPE_ACTION,
+		.category = WLAN_CATEGORY_PUBLIC,
+		.action = WLAN_PUB_ACTION_DSE_ENABLEMENT,
+		.unicast = true,
+		.result = RX_CONTINUE,
+	},
+	{
+		.desc = "public action: accept multicast from unknown peer",
+		.stype = IEEE80211_STYPE_ACTION,
+		.category = WLAN_CATEGORY_PUBLIC,
+		.action = WLAN_PUB_ACTION_DSE_ENABLEMENT,
+		.unicast = false,
+		.result = RX_CONTINUE,
+	},
+	{
+		.desc = "public action: accept unicast without MFP",
+		.stype = IEEE80211_STYPE_ACTION,
+		.category = WLAN_CATEGORY_PUBLIC,
+		.action = WLAN_PUB_ACTION_DSE_ENABLEMENT,
+		.unicast = true,
+		.sta = true,
+		.result = RX_CONTINUE,
+	},
+	{
+		.desc = "public action: accept multicast without MFP",
+		.stype = IEEE80211_STYPE_ACTION,
+		.category = WLAN_CATEGORY_PUBLIC,
+		.action = WLAN_PUB_ACTION_DSE_ENABLEMENT,
+		.unicast = false,
+		.sta = true,
+		.result = RX_CONTINUE,
+	},
+	{
+		.desc = "public action: drop unicast with MFP",
+		.stype = IEEE80211_STYPE_ACTION,
+		.category = WLAN_CATEGORY_PUBLIC,
+		.action = WLAN_PUB_ACTION_DSE_ENABLEMENT,
+		.unicast = true,
+		.sta = true,
+		.mfp = true,
+		.result = RX_DROP_U_UNPROT_UNICAST_PUB_ACTION,
+	},
+	{
+		.desc = "public action: accept multicast with MFP",
+		.stype = IEEE80211_STYPE_ACTION,
+		.category = WLAN_CATEGORY_PUBLIC,
+		.action = WLAN_PUB_ACTION_DSE_ENABLEMENT,
+		.unicast = false,
+		.sta = true,
+		.mfp = true,
+		.result = RX_CONTINUE,
+	},
+	/* protected dual of public action */
+	{
+		.desc = "protected dual: drop unicast from unknown peer",
+		.stype = IEEE80211_STYPE_ACTION,
+		.category = WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION,
+		.action = WLAN_PUB_ACTION_DSE_ENABLEMENT,
+		.unicast = true,
+		.result = RX_DROP_U_UNPROT_DUAL,
+	},
+	{
+		.desc = "protected dual: drop multicast from unknown peer",
+		.stype = IEEE80211_STYPE_ACTION,
+		.category = WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION,
+		.action = WLAN_PUB_ACTION_DSE_ENABLEMENT,
+		.unicast = false,
+		.result = RX_DROP_U_UNPROT_DUAL,
+	},
+	{
+		.desc = "protected dual: drop unicast without MFP",
+		.stype = IEEE80211_STYPE_ACTION,
+		.category = WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION,
+		.action = WLAN_PUB_ACTION_DSE_ENABLEMENT,
+		.unicast = true,
+		.sta = true,
+		.result = RX_DROP_U_UNPROT_DUAL,
+	},
+	{
+		.desc = "protected dual: drop multicast without MFP",
+		.stype = IEEE80211_STYPE_ACTION,
+		.category = WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION,
+		.action = WLAN_PUB_ACTION_DSE_ENABLEMENT,
+		.unicast = false,
+		.sta = true,
+		.result = RX_DROP_U_UNPROT_DUAL,
+	},
+	{
+		.desc = "protected dual: drop undecrypted unicast with MFP",
+		.stype = IEEE80211_STYPE_ACTION,
+		.category = WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION,
+		.action = WLAN_PUB_ACTION_DSE_ENABLEMENT,
+		.unicast = true,
+		.sta = true,
+		.mfp = true,
+		.result = RX_DROP_U_UNPROT_DUAL,
+	},
+	{
+		.desc = "protected dual: drop undecrypted multicast with MFP",
+		.stype = IEEE80211_STYPE_ACTION,
+		.category = WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION,
+		.action = WLAN_PUB_ACTION_DSE_ENABLEMENT,
+		.unicast = false,
+		.sta = true,
+		.mfp = true,
+		.result = RX_DROP_U_UNPROT_DUAL,
+	},
+	{
+		.desc = "protected dual: accept unicast with MFP",
+		.stype = IEEE80211_STYPE_ACTION,
+		.category = WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION,
+		.action = WLAN_PUB_ACTION_DSE_ENABLEMENT,
+		.decrypted = true,
+		.unicast = true,
+		.sta = true,
+		.mfp = true,
+		.result = RX_CONTINUE,
+	},
+	{
+		.desc = "protected dual: accept multicast with MFP",
+		.stype = IEEE80211_STYPE_ACTION,
+		.category = WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION,
+		.action = WLAN_PUB_ACTION_DSE_ENABLEMENT,
+		.decrypted = true,
+		.unicast = false,
+		.sta = true,
+		.mfp = true,
+		.result = RX_CONTINUE,
+	},
+	/* deauth/disassoc before keys are set */
+	{
+		.desc = "deauth: accept unicast with MFP but w/o key",
+		.stype = IEEE80211_STYPE_DEAUTH,
+		.sta = true,
+		.mfp = true,
+		.unicast = true,
+		.result = RX_CONTINUE,
+	},
+	{
+		.desc = "disassoc: accept unicast with MFP but w/o key",
+		.stype = IEEE80211_STYPE_DEAUTH,
+		.sta = true,
+		.mfp = true,
+		.unicast = true,
+		.result = RX_CONTINUE,
+	},
+	/* non-public robust action frame ... */
+	{
+		.desc = "BA action: drop unicast before assoc",
+		.stype = IEEE80211_STYPE_ACTION,
+		.category = WLAN_CATEGORY_BACK,
+		.unicast = true,
+		.sta = true,
+		.result = RX_DROP_U_UNPROT_ROBUST_ACTION,
+	},
+	{
+		.desc = "BA action: drop unprotected after assoc",
+		.stype = IEEE80211_STYPE_ACTION,
+		.category = WLAN_CATEGORY_BACK,
+		.unicast = true,
+		.sta = true,
+		.mfp = true,
+		.result = RX_DROP_U_UNPROT_UCAST_MGMT,
+	},
+	{
+		.desc = "BA action: accept unprotected without MFP",
+		.stype = IEEE80211_STYPE_ACTION,
+		.category = WLAN_CATEGORY_BACK,
+		.unicast = true,
+		.sta = true,
+		.assoc = true,
+		.mfp = false,
+		.result = RX_CONTINUE,
+	},
+	{
+		.desc = "BA action: drop unprotected with MFP",
+		.stype = IEEE80211_STYPE_ACTION,
+		.category = WLAN_CATEGORY_BACK,
+		.unicast = true,
+		.sta = true,
+		.mfp = true,
+		.result = RX_DROP_U_UNPROT_UCAST_MGMT,
+	},
+};
+
+KUNIT_ARRAY_PARAM_DESC(accept_mfp, accept_mfp_cases, desc);
+
+static void accept_mfp(struct kunit *test)
+{
+	static struct sta_info sta;
+	const struct mfp_test_case *params = test->param_value;
+	struct ieee80211_rx_data rx = {
+		.sta = params->sta ? &sta : NULL,
+	};
+	struct ieee80211_rx_status *status;
+	struct ieee80211_hdr_3addr hdr = {
+		.frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
+					     params->stype),
+		.addr1 = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff },
+		.addr2 = { 0x12, 0x22, 0x33, 0x44, 0x55, 0x66 },
+		/* A3/BSSID doesn't matter here */
+	};
+
+	memset(&sta, 0, sizeof(sta));
+
+	if (!params->sta) {
+		KUNIT_ASSERT_FALSE(test, params->mfp);
+		KUNIT_ASSERT_FALSE(test, params->decrypted);
+	}
+
+	if (params->mfp)
+		set_sta_flag(&sta, WLAN_STA_MFP);
+
+	if (params->assoc)
+		set_bit(WLAN_STA_ASSOC, &sta._flags);
+
+	rx.skb = kunit_zalloc_skb(test, 128, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_NULL(test, rx.skb);
+	status = IEEE80211_SKB_RXCB(rx.skb);
+
+	if (params->decrypted) {
+		status->flag |= RX_FLAG_DECRYPTED;
+		if (params->unicast)
+			hdr.frame_control |=
+				cpu_to_le16(IEEE80211_FCTL_PROTECTED);
+	}
+
+	if (params->unicast)
+		hdr.addr1[0] = 0x02;
+
+	skb_put_data(rx.skb, &hdr, sizeof(hdr));
+
+	switch (params->stype) {
+	case IEEE80211_STYPE_ACTION:
+		skb_put_u8(rx.skb, params->category);
+		skb_put_u8(rx.skb, params->action);
+		break;
+	case IEEE80211_STYPE_DEAUTH:
+	case IEEE80211_STYPE_DISASSOC: {
+		__le16 reason = cpu_to_le16(WLAN_REASON_UNSPECIFIED);
+
+		skb_put_data(rx.skb, &reason, sizeof(reason));
+		}
+		break;
+	}
+
+	KUNIT_EXPECT_EQ(test,
+			(__force u32)ieee80211_drop_unencrypted_mgmt(&rx),
+			(__force u32)params->result);
+}
+
+static struct kunit_case mfp_test_cases[] = {
+	KUNIT_CASE_PARAM(accept_mfp, accept_mfp_gen_params),
+	{}
+};
+
+static struct kunit_suite mfp = {
+	.name = "mac80211-mfp",
+	.test_cases = mfp_test_cases,
+};
+
+kunit_test_suite(mfp);
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 032718d5b298..06835ed4c44f 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -2512,6 +2512,31 @@ TRACE_EVENT(drv_net_setup_tc,
 	)
 );
 
+TRACE_EVENT(drv_can_activate_links,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 u16 active_links),
+
+	TP_ARGS(local, sdata, active_links),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		VIF_ENTRY
+		__field(u16, active_links)
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		__entry->active_links = active_links;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT VIF_PR_FMT " requested active_links:0x%04x\n",
+		LOCAL_PR_ARG, VIF_PR_ARG, __entry->active_links
+	)
+);
+
 TRACE_EVENT(drv_change_vif_links,
 	TP_PROTO(struct ieee80211_local *local,
 		 struct ieee80211_sub_if_data *sdata,
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index ed4fdf655343..314998fdb1a5 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -4013,14 +4013,13 @@ ieee80211_txq_set_active(struct txq_info *txqi)
 		return;
 
 	sta = container_of(txqi->txq.sta, struct sta_info, sta);
-	sta->airtime[txqi->txq.ac].last_active = (u32)jiffies;
+	sta->airtime[txqi->txq.ac].last_active = jiffies;
 }
 
 static bool
 ieee80211_txq_keep_active(struct txq_info *txqi)
 {
 	struct sta_info *sta;
-	u32 diff;
 
 	if (!txqi->txq.sta)
 		return false;
@@ -4029,9 +4028,7 @@ ieee80211_txq_keep_active(struct txq_info *txqi)
 	if (ieee80211_sta_deficit(sta, txqi->txq.ac) >= 0)
 		return false;
 
-	diff = (u32)jiffies - sta->airtime[txqi->txq.ac].last_active;
-
-	return diff <= AIRTIME_ACTIVE_DURATION;
+	return ieee80211_sta_keep_active(sta, txqi->txq.ac);
 }
 
 struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac)
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index ed680120d5a7..643c54855be6 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -4176,6 +4176,7 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 				     unsigned int mpdu_offset)
 {
 	u64 ts = status->mactime;
+	bool mactime_plcp_start;
 	struct rate_info ri;
 	u16 rate;
 	u8 n_ltf;
@@ -4183,6 +4184,9 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 	if (WARN_ON(!ieee80211_have_rx_timestamp(status)))
 		return 0;
 
+	mactime_plcp_start = (status->flag & RX_FLAG_MACTIME) ==
+				RX_FLAG_MACTIME_PLCP_START;
+
 	memset(&ri, 0, sizeof(ri));
 
 	ri.bw = status->bw;
@@ -4197,7 +4201,7 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 		if (status->enc_flags & RX_ENC_FLAG_SHORT_GI)
 			ri.flags |= RATE_INFO_FLAGS_SHORT_GI;
 		/* TODO/FIXME: is this right? handle other PPDUs */
-		if (status->flag & RX_FLAG_MACTIME_PLCP_START) {
+		if (mactime_plcp_start) {
 			mpdu_offset += 2;
 			ts += 36;
 		}
@@ -4214,7 +4218,7 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 		 * See P802.11ax_D6.0, section 27.3.4 for
 		 * VHT PPDU format.
 		 */
-		if (status->flag & RX_FLAG_MACTIME_PLCP_START) {
+		if (mactime_plcp_start) {
 			mpdu_offset += 2;
 			ts += 36;
 
@@ -4238,7 +4242,7 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 		 * See P802.11REVmd_D3.0, section 19.3.2 for
 		 * HT PPDU format.
 		 */
-		if (status->flag & RX_FLAG_MACTIME_PLCP_START) {
+		if (mactime_plcp_start) {
 			mpdu_offset += 2;
 			if (status->enc_flags & RX_ENC_FLAG_HT_GF)
 				ts += 24;
@@ -4266,7 +4270,7 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 		 * See P802.11REVmd_D3.0, section 21.3.2 for
 		 * VHT PPDU format.
 		 */
-		if (status->flag & RX_FLAG_MACTIME_PLCP_START) {
+		if (mactime_plcp_start) {
 			mpdu_offset += 2;
 			ts += 36;
 
@@ -4288,7 +4292,7 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 		sband = local->hw.wiphy->bands[status->band];
 		ri.legacy = sband->bitrates[status->rate_idx].bitrate;
 
-		if (status->flag & RX_FLAG_MACTIME_PLCP_START) {
+		if (mactime_plcp_start) {
 			if (status->band == NL80211_BAND_5GHZ) {
 				ts += 20;
 				mpdu_offset += 2;
@@ -4310,7 +4314,7 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 		return 0;
 
 	/* rewind from end of MPDU */
-	if (status->flag & RX_FLAG_MACTIME_END)
+	if ((status->flag & RX_FLAG_MACTIME) == RX_FLAG_MACTIME_END)
 		ts -= mpdu_len * 8 * 10 / rate;
 
 	ts += mpdu_offset * 8 * 10 / rate;
diff --git a/net/mac80211/wbrf.c b/net/mac80211/wbrf.c
new file mode 100644
index 000000000000..a05c5b971789
--- /dev/null
+++ b/net/mac80211/wbrf.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Wifi Band Exclusion Interface for WLAN
+ * Copyright (C) 2023 Advanced Micro Devices
+ *
+ */
+
+#include <linux/acpi_amd_wbrf.h>
+#include <linux/units.h>
+#include <net/cfg80211.h>
+#include "ieee80211_i.h"
+
+void ieee80211_check_wbrf_support(struct ieee80211_local *local)
+{
+	struct wiphy *wiphy = local->hw.wiphy;
+	struct device *dev;
+
+	if (!wiphy)
+		return;
+
+	dev = wiphy->dev.parent;
+	if (!dev)
+		return;
+
+	local->wbrf_supported = acpi_amd_wbrf_supported_producer(dev);
+	dev_dbg(dev, "WBRF is %s supported\n",
+		local->wbrf_supported ? "" : "not");
+}
+
+static void get_chan_freq_boundary(u32 center_freq, u32 bandwidth, u64 *start, u64 *end)
+{
+	bandwidth *= KHZ_PER_MHZ;
+	center_freq *= KHZ_PER_MHZ;
+
+	*start = center_freq - bandwidth / 2;
+	*end = center_freq + bandwidth / 2;
+
+	/* Frequency in Hz is expected */
+	*start = *start * HZ_PER_KHZ;
+	*end = *end * HZ_PER_KHZ;
+}
+
+static void get_ranges_from_chandef(struct cfg80211_chan_def *chandef,
+				    struct wbrf_ranges_in_out *ranges_in)
+{
+	u64 start_freq1, end_freq1;
+	u64 start_freq2, end_freq2;
+	int bandwidth;
+
+	bandwidth = nl80211_chan_width_to_mhz(chandef->width);
+
+	get_chan_freq_boundary(chandef->center_freq1, bandwidth, &start_freq1, &end_freq1);
+
+	ranges_in->band_list[0].start = start_freq1;
+	ranges_in->band_list[0].end = end_freq1;
+	ranges_in->num_of_ranges = 1;
+
+	if (chandef->width == NL80211_CHAN_WIDTH_80P80) {
+		get_chan_freq_boundary(chandef->center_freq2, bandwidth, &start_freq2, &end_freq2);
+
+		ranges_in->band_list[1].start = start_freq2;
+		ranges_in->band_list[1].end = end_freq2;
+		ranges_in->num_of_ranges++;
+	}
+}
+
+void ieee80211_add_wbrf(struct ieee80211_local *local, struct cfg80211_chan_def *chandef)
+{
+	struct wbrf_ranges_in_out ranges_in = {0};
+	struct device *dev;
+
+	if (!local->wbrf_supported)
+		return;
+
+	dev = local->hw.wiphy->dev.parent;
+
+	get_ranges_from_chandef(chandef, &ranges_in);
+
+	acpi_amd_wbrf_add_remove(dev, WBRF_RECORD_ADD, &ranges_in);
+}
+
+void ieee80211_remove_wbrf(struct ieee80211_local *local, struct cfg80211_chan_def *chandef)
+{
+	struct wbrf_ranges_in_out ranges_in = {0};
+	struct device *dev;
+
+	if (!local->wbrf_supported)
+		return;
+
+	dev = local->hw.wiphy->dev.parent;
+
+	get_ranges_from_chandef(chandef, &ranges_in);
+
+	acpi_amd_wbrf_add_remove(dev, WBRF_RECORD_REMOVE, &ranges_in);
+}
diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c
index 5c3cb019f751..ef7f23af043f 100644
--- a/net/mac802154/cfg.c
+++ b/net/mac802154/cfg.c
@@ -315,6 +315,179 @@ static int mac802154_stop_beacons(struct wpan_phy *wpan_phy,
 	return mac802154_stop_beacons_locked(local, sdata);
 }
 
+static int mac802154_associate(struct wpan_phy *wpan_phy,
+			       struct wpan_dev *wpan_dev,
+			       struct ieee802154_addr *coord)
+{
+	struct ieee802154_local *local = wpan_phy_priv(wpan_phy);
+	u64 ceaddr = swab64((__force u64)coord->extended_addr);
+	struct ieee802154_sub_if_data *sdata;
+	struct ieee802154_pan_device *parent;
+	__le16 short_addr;
+	int ret;
+
+	ASSERT_RTNL();
+
+	sdata = IEEE802154_WPAN_DEV_TO_SUB_IF(wpan_dev);
+
+	if (wpan_dev->parent) {
+		dev_err(&sdata->dev->dev,
+			"Device %8phC is already associated\n", &ceaddr);
+		return -EPERM;
+	}
+
+	if (coord->mode == IEEE802154_SHORT_ADDRESSING)
+		return -EINVAL;
+
+	parent = kzalloc(sizeof(*parent), GFP_KERNEL);
+	if (!parent)
+		return -ENOMEM;
+
+	parent->pan_id = coord->pan_id;
+	parent->mode = coord->mode;
+	parent->extended_addr = coord->extended_addr;
+	parent->short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_BROADCAST);
+
+	/* Set the PAN ID hardware address filter beforehand to avoid dropping
+	 * the association response with a destination PAN ID field set to the
+	 * "new" PAN ID.
+	 */
+	if (local->hw.flags & IEEE802154_HW_AFILT) {
+		ret = drv_set_pan_id(local, coord->pan_id);
+		if (ret < 0)
+			goto free_parent;
+	}
+
+	ret = mac802154_perform_association(sdata, parent, &short_addr);
+	if (ret)
+		goto reset_panid;
+
+	if (local->hw.flags & IEEE802154_HW_AFILT) {
+		ret = drv_set_short_addr(local, short_addr);
+		if (ret < 0)
+			goto reset_panid;
+	}
+
+	wpan_dev->pan_id = coord->pan_id;
+	wpan_dev->short_addr = short_addr;
+	wpan_dev->parent = parent;
+
+	return 0;
+
+reset_panid:
+	if (local->hw.flags & IEEE802154_HW_AFILT)
+		drv_set_pan_id(local, cpu_to_le16(IEEE802154_PAN_ID_BROADCAST));
+
+free_parent:
+	kfree(parent);
+	return ret;
+}
+
+static int mac802154_disassociate_from_parent(struct wpan_phy *wpan_phy,
+					      struct wpan_dev *wpan_dev)
+{
+	struct ieee802154_local *local = wpan_phy_priv(wpan_phy);
+	struct ieee802154_pan_device *child, *tmp;
+	struct ieee802154_sub_if_data *sdata;
+	unsigned int max_assoc;
+	u64 eaddr;
+	int ret;
+
+	sdata = IEEE802154_WPAN_DEV_TO_SUB_IF(wpan_dev);
+
+	/* Start by disassociating all the children and preventing new ones to
+	 * attempt associations.
+	 */
+	max_assoc = cfg802154_set_max_associations(wpan_dev, 0);
+	list_for_each_entry_safe(child, tmp, &wpan_dev->children, node) {
+		ret = mac802154_send_disassociation_notif(sdata, child,
+							  IEEE802154_COORD_WISHES_DEVICE_TO_LEAVE);
+		if (ret) {
+			eaddr = swab64((__force u64)child->extended_addr);
+			dev_err(&sdata->dev->dev,
+				"Disassociation with %8phC may have failed (%d)\n",
+				&eaddr, ret);
+		}
+
+		list_del(&child->node);
+	}
+
+	ret = mac802154_send_disassociation_notif(sdata, wpan_dev->parent,
+						  IEEE802154_DEVICE_WISHES_TO_LEAVE);
+	if (ret) {
+		eaddr = swab64((__force u64)wpan_dev->parent->extended_addr);
+		dev_err(&sdata->dev->dev,
+			"Disassociation from %8phC may have failed (%d)\n",
+			&eaddr, ret);
+	}
+
+	ret = 0;
+
+	kfree(wpan_dev->parent);
+	wpan_dev->parent = NULL;
+	wpan_dev->pan_id = cpu_to_le16(IEEE802154_PAN_ID_BROADCAST);
+	wpan_dev->short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_BROADCAST);
+
+	if (local->hw.flags & IEEE802154_HW_AFILT) {
+		ret = drv_set_pan_id(local, wpan_dev->pan_id);
+		if (ret < 0)
+			goto reset_mac_assoc;
+
+		ret = drv_set_short_addr(local, wpan_dev->short_addr);
+		if (ret < 0)
+			goto reset_mac_assoc;
+	}
+
+reset_mac_assoc:
+	cfg802154_set_max_associations(wpan_dev, max_assoc);
+
+	return ret;
+}
+
+static int mac802154_disassociate_child(struct wpan_phy *wpan_phy,
+					struct wpan_dev *wpan_dev,
+					struct ieee802154_pan_device *child)
+{
+	struct ieee802154_sub_if_data *sdata;
+	int ret;
+
+	sdata = IEEE802154_WPAN_DEV_TO_SUB_IF(wpan_dev);
+
+	ret = mac802154_send_disassociation_notif(sdata, child,
+						  IEEE802154_COORD_WISHES_DEVICE_TO_LEAVE);
+	if (ret)
+		return ret;
+
+	list_del(&child->node);
+	wpan_dev->nchildren--;
+	kfree(child);
+
+	return 0;
+}
+
+static int mac802154_disassociate(struct wpan_phy *wpan_phy,
+				  struct wpan_dev *wpan_dev,
+				  struct ieee802154_addr *target)
+{
+	u64 teaddr = swab64((__force u64)target->extended_addr);
+	struct ieee802154_pan_device *pan_device;
+
+	ASSERT_RTNL();
+
+	if (cfg802154_device_is_parent(wpan_dev, target))
+		return mac802154_disassociate_from_parent(wpan_phy, wpan_dev);
+
+	pan_device = cfg802154_device_is_child(wpan_dev, target);
+	if (pan_device)
+		return mac802154_disassociate_child(wpan_phy, wpan_dev,
+						    pan_device);
+
+	dev_err(&wpan_dev->netdev->dev,
+		"Device %8phC is not associated with us\n", &teaddr);
+
+	return -EINVAL;
+}
+
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 static void
 ieee802154_get_llsec_table(struct wpan_phy *wpan_phy,
@@ -526,6 +699,8 @@ const struct cfg802154_ops mac802154_config_ops = {
 	.abort_scan = mac802154_abort_scan,
 	.send_beacons = mac802154_send_beacons,
 	.stop_beacons = mac802154_stop_beacons,
+	.associate = mac802154_associate,
+	.disassociate = mac802154_disassociate,
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 	.get_llsec_table = ieee802154_get_llsec_table,
 	.lock_llsec_table = ieee802154_lock_llsec_table,
diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h
index c347ec9ff8c9..08dd521a51a5 100644
--- a/net/mac802154/ieee802154_i.h
+++ b/net/mac802154/ieee802154_i.h
@@ -24,6 +24,7 @@
 enum ieee802154_ongoing {
 	IEEE802154_IS_SCANNING = BIT(0),
 	IEEE802154_IS_BEACONING = BIT(1),
+	IEEE802154_IS_ASSOCIATING = BIT(2),
 };
 
 /* mac802154 device private data */
@@ -74,6 +75,13 @@ struct ieee802154_local {
 	struct list_head rx_mac_cmd_list;
 	struct work_struct rx_mac_cmd_work;
 
+	/* Association */
+	struct ieee802154_pan_device *assoc_dev;
+	struct completion assoc_done;
+	__le16 assoc_addr;
+	u8 assoc_status;
+	struct work_struct assoc_work;
+
 	bool started;
 	bool suspended;
 	unsigned long ongoing;
@@ -296,6 +304,25 @@ static inline bool mac802154_is_beaconing(struct ieee802154_local *local)
 
 void mac802154_rx_mac_cmd_worker(struct work_struct *work);
 
+int mac802154_perform_association(struct ieee802154_sub_if_data *sdata,
+				  struct ieee802154_pan_device *coord,
+				  __le16 *short_addr);
+int mac802154_process_association_resp(struct ieee802154_sub_if_data *sdata,
+				       struct sk_buff *skb);
+
+static inline bool mac802154_is_associating(struct ieee802154_local *local)
+{
+	return test_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing);
+}
+
+int mac802154_send_disassociation_notif(struct ieee802154_sub_if_data *sdata,
+					struct ieee802154_pan_device *target,
+					u8 reason);
+int mac802154_process_disassociation_notif(struct ieee802154_sub_if_data *sdata,
+					   struct sk_buff *skb);
+int mac802154_process_association_req(struct ieee802154_sub_if_data *sdata,
+				      struct sk_buff *skb);
+
 /* interface handling */
 int ieee802154_iface_init(void);
 void ieee802154_iface_exit(void);
diff --git a/net/mac802154/main.c b/net/mac802154/main.c
index 357ece67432b..9ab7396668d2 100644
--- a/net/mac802154/main.c
+++ b/net/mac802154/main.c
@@ -103,6 +103,8 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops)
 	INIT_DELAYED_WORK(&local->beacon_work, mac802154_beacon_worker);
 	INIT_WORK(&local->rx_mac_cmd_work, mac802154_rx_mac_cmd_worker);
 
+	init_completion(&local->assoc_done);
+
 	/* init supported flags with 802.15.4 default ranges */
 	phy->supported.max_minbe = 8;
 	phy->supported.min_maxbe = 3;
diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c
index e2434b4fe514..e40a988d6c80 100644
--- a/net/mac802154/rx.c
+++ b/net/mac802154/rx.c
@@ -93,6 +93,31 @@ void mac802154_rx_mac_cmd_worker(struct work_struct *work)
 
 		queue_delayed_work(local->mac_wq, &local->beacon_work, 0);
 		break;
+
+	case IEEE802154_CMD_ASSOCIATION_RESP:
+		dev_dbg(&mac_pkt->sdata->dev->dev, "processing ASSOC RESP\n");
+		if (!mac802154_is_associating(local))
+			break;
+
+		mac802154_process_association_resp(mac_pkt->sdata, mac_pkt->skb);
+		break;
+
+	case IEEE802154_CMD_ASSOCIATION_REQ:
+		dev_dbg(&mac_pkt->sdata->dev->dev, "processing ASSOC REQ\n");
+		if (mac_pkt->sdata->wpan_dev.iftype != NL802154_IFTYPE_COORD)
+			break;
+
+		mac802154_process_association_req(mac_pkt->sdata, mac_pkt->skb);
+		break;
+
+	case IEEE802154_CMD_DISASSOCIATION_NOTIFY:
+		dev_dbg(&mac_pkt->sdata->dev->dev, "processing DISASSOC NOTIF\n");
+		if (mac_pkt->sdata->wpan_dev.iftype != NL802154_IFTYPE_COORD)
+			break;
+
+		mac802154_process_disassociation_notif(mac_pkt->sdata, mac_pkt->skb);
+		break;
+
 	default:
 		break;
 	}
@@ -131,12 +156,15 @@ ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata,
 
 	switch (mac_cb(skb)->dest.mode) {
 	case IEEE802154_ADDR_NONE:
-		if (hdr->source.mode != IEEE802154_ADDR_NONE)
-			/* FIXME: check if we are PAN coordinator */
-			skb->pkt_type = PACKET_OTHERHOST;
-		else
+		if (hdr->source.mode == IEEE802154_ADDR_NONE)
 			/* ACK comes with both addresses empty */
 			skb->pkt_type = PACKET_HOST;
+		else if (!wpan_dev->parent)
+			/* No dest means PAN coordinator is the recipient */
+			skb->pkt_type = PACKET_HOST;
+		else
+			/* We are not the PAN coordinator, just relaying */
+			skb->pkt_type = PACKET_OTHERHOST;
 		break;
 	case IEEE802154_ADDR_LONG:
 		if (mac_cb(skb)->dest.pan_id != span &&
diff --git a/net/mac802154/scan.c b/net/mac802154/scan.c
index d9658f2c4ae6..1c0eeaa76560 100644
--- a/net/mac802154/scan.c
+++ b/net/mac802154/scan.c
@@ -466,6 +466,7 @@ int mac802154_send_beacons_locked(struct ieee802154_sub_if_data *sdata,
 				  struct cfg802154_beacon_request *request)
 {
 	struct ieee802154_local *local = sdata->local;
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
 
 	ASSERT_RTNL();
 
@@ -495,8 +496,7 @@ int mac802154_send_beacons_locked(struct ieee802154_sub_if_data *sdata,
 		local->beacon.mac_pl.superframe_order = request->interval;
 	local->beacon.mac_pl.final_cap_slot = 0xf;
 	local->beacon.mac_pl.battery_life_ext = 0;
-	/* TODO: Fill this field with the coordinator situation in the network */
-	local->beacon.mac_pl.pan_coordinator = 1;
+	local->beacon.mac_pl.pan_coordinator = !wpan_dev->parent;
 	local->beacon.mac_pl.assoc_permit = 1;
 
 	if (request->interval == IEEE802154_ACTIVE_SCAN_DURATION)
@@ -510,3 +510,406 @@ int mac802154_send_beacons_locked(struct ieee802154_sub_if_data *sdata,
 
 	return 0;
 }
+
+int mac802154_perform_association(struct ieee802154_sub_if_data *sdata,
+				  struct ieee802154_pan_device *coord,
+				  __le16 *short_addr)
+{
+	u64 ceaddr = swab64((__force u64)coord->extended_addr);
+	struct ieee802154_association_req_frame frame = {};
+	struct ieee802154_local *local = sdata->local;
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
+	struct sk_buff *skb;
+	int ret;
+
+	frame.mhr.fc.type = IEEE802154_FC_TYPE_MAC_CMD;
+	frame.mhr.fc.security_enabled = 0;
+	frame.mhr.fc.frame_pending = 0;
+	frame.mhr.fc.ack_request = 1; /* We always expect an ack here */
+	frame.mhr.fc.intra_pan = 0;
+	frame.mhr.fc.dest_addr_mode = (coord->mode == IEEE802154_ADDR_LONG) ?
+		IEEE802154_EXTENDED_ADDRESSING : IEEE802154_SHORT_ADDRESSING;
+	frame.mhr.fc.version = IEEE802154_2003_STD;
+	frame.mhr.fc.source_addr_mode = IEEE802154_EXTENDED_ADDRESSING;
+	frame.mhr.source.mode = IEEE802154_ADDR_LONG;
+	frame.mhr.source.pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST);
+	frame.mhr.source.extended_addr = wpan_dev->extended_addr;
+	frame.mhr.dest.mode = coord->mode;
+	frame.mhr.dest.pan_id = coord->pan_id;
+	if (coord->mode == IEEE802154_ADDR_LONG)
+		frame.mhr.dest.extended_addr = coord->extended_addr;
+	else
+		frame.mhr.dest.short_addr = coord->short_addr;
+	frame.mhr.seq = atomic_inc_return(&wpan_dev->dsn) & 0xFF;
+	frame.mac_pl.cmd_id = IEEE802154_CMD_ASSOCIATION_REQ;
+	frame.assoc_req_pl.device_type = 1;
+	frame.assoc_req_pl.power_source = 1;
+	frame.assoc_req_pl.rx_on_when_idle = 1;
+	frame.assoc_req_pl.alloc_addr = 1;
+
+	skb = alloc_skb(IEEE802154_MAC_CMD_SKB_SZ + sizeof(frame.assoc_req_pl),
+			GFP_KERNEL);
+	if (!skb)
+		return -ENOBUFS;
+
+	skb->dev = sdata->dev;
+
+	ret = ieee802154_mac_cmd_push(skb, &frame, &frame.assoc_req_pl,
+				      sizeof(frame.assoc_req_pl));
+	if (ret) {
+		kfree_skb(skb);
+		return ret;
+	}
+
+	local->assoc_dev = coord;
+	reinit_completion(&local->assoc_done);
+	set_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing);
+
+	ret = ieee802154_mlme_tx_one_locked(local, sdata, skb);
+	if (ret) {
+		if (ret > 0)
+			ret = (ret == IEEE802154_NO_ACK) ? -EREMOTEIO : -EIO;
+		dev_warn(&sdata->dev->dev,
+			 "No ASSOC REQ ACK received from %8phC\n", &ceaddr);
+		goto clear_assoc;
+	}
+
+	ret = wait_for_completion_killable_timeout(&local->assoc_done, 10 * HZ);
+	if (ret <= 0) {
+		dev_warn(&sdata->dev->dev,
+			 "No ASSOC RESP received from %8phC\n", &ceaddr);
+		ret = -ETIMEDOUT;
+		goto clear_assoc;
+	}
+
+	if (local->assoc_status != IEEE802154_ASSOCIATION_SUCCESSFUL) {
+		if (local->assoc_status == IEEE802154_PAN_AT_CAPACITY)
+			ret = -ERANGE;
+		else
+			ret = -EPERM;
+
+		dev_warn(&sdata->dev->dev,
+			 "Negative ASSOC RESP received from %8phC: %s\n", &ceaddr,
+			 local->assoc_status == IEEE802154_PAN_AT_CAPACITY ?
+			 "PAN at capacity" : "access denied");
+	}
+
+	ret = 0;
+	*short_addr = local->assoc_addr;
+
+clear_assoc:
+	clear_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing);
+	local->assoc_dev = NULL;
+
+	return ret;
+}
+
+int mac802154_process_association_resp(struct ieee802154_sub_if_data *sdata,
+				       struct sk_buff *skb)
+{
+	struct ieee802154_addr *src = &mac_cb(skb)->source;
+	struct ieee802154_addr *dest = &mac_cb(skb)->dest;
+	u64 deaddr = swab64((__force u64)dest->extended_addr);
+	struct ieee802154_local *local = sdata->local;
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
+	struct ieee802154_assoc_resp_pl resp_pl = {};
+
+	if (skb->len != sizeof(resp_pl))
+		return -EINVAL;
+
+	if (unlikely(src->mode != IEEE802154_EXTENDED_ADDRESSING ||
+		     dest->mode != IEEE802154_EXTENDED_ADDRESSING))
+		return -EINVAL;
+
+	if (unlikely(dest->extended_addr != wpan_dev->extended_addr ||
+		     src->extended_addr != local->assoc_dev->extended_addr))
+		return -ENODEV;
+
+	memcpy(&resp_pl, skb->data, sizeof(resp_pl));
+	local->assoc_addr = resp_pl.short_addr;
+	local->assoc_status = resp_pl.status;
+
+	dev_dbg(&skb->dev->dev,
+		"ASSOC RESP 0x%x received from %8phC, getting short address %04x\n",
+		local->assoc_status, &deaddr, local->assoc_addr);
+
+	complete(&local->assoc_done);
+
+	return 0;
+}
+
+int mac802154_send_disassociation_notif(struct ieee802154_sub_if_data *sdata,
+					struct ieee802154_pan_device *target,
+					u8 reason)
+{
+	struct ieee802154_disassociation_notif_frame frame = {};
+	u64 teaddr = swab64((__force u64)target->extended_addr);
+	struct ieee802154_local *local = sdata->local;
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
+	struct sk_buff *skb;
+	int ret;
+
+	frame.mhr.fc.type = IEEE802154_FC_TYPE_MAC_CMD;
+	frame.mhr.fc.security_enabled = 0;
+	frame.mhr.fc.frame_pending = 0;
+	frame.mhr.fc.ack_request = 1;
+	frame.mhr.fc.intra_pan = 1;
+	frame.mhr.fc.dest_addr_mode = (target->mode == IEEE802154_ADDR_LONG) ?
+		IEEE802154_EXTENDED_ADDRESSING : IEEE802154_SHORT_ADDRESSING;
+	frame.mhr.fc.version = IEEE802154_2003_STD;
+	frame.mhr.fc.source_addr_mode = IEEE802154_EXTENDED_ADDRESSING;
+	frame.mhr.source.mode = IEEE802154_ADDR_LONG;
+	frame.mhr.source.pan_id = wpan_dev->pan_id;
+	frame.mhr.source.extended_addr = wpan_dev->extended_addr;
+	frame.mhr.dest.mode = target->mode;
+	frame.mhr.dest.pan_id = wpan_dev->pan_id;
+	if (target->mode == IEEE802154_ADDR_LONG)
+		frame.mhr.dest.extended_addr = target->extended_addr;
+	else
+		frame.mhr.dest.short_addr = target->short_addr;
+	frame.mhr.seq = atomic_inc_return(&wpan_dev->dsn) & 0xFF;
+	frame.mac_pl.cmd_id = IEEE802154_CMD_DISASSOCIATION_NOTIFY;
+	frame.disassoc_pl = reason;
+
+	skb = alloc_skb(IEEE802154_MAC_CMD_SKB_SZ + sizeof(frame.disassoc_pl),
+			GFP_KERNEL);
+	if (!skb)
+		return -ENOBUFS;
+
+	skb->dev = sdata->dev;
+
+	ret = ieee802154_mac_cmd_push(skb, &frame, &frame.disassoc_pl,
+				      sizeof(frame.disassoc_pl));
+	if (ret) {
+		kfree_skb(skb);
+		return ret;
+	}
+
+	ret = ieee802154_mlme_tx_one_locked(local, sdata, skb);
+	if (ret) {
+		dev_warn(&sdata->dev->dev,
+			 "No DISASSOC ACK received from %8phC\n", &teaddr);
+		if (ret > 0)
+			ret = (ret == IEEE802154_NO_ACK) ? -EREMOTEIO : -EIO;
+		return ret;
+	}
+
+	dev_dbg(&sdata->dev->dev, "DISASSOC ACK received from %8phC\n", &teaddr);
+	return 0;
+}
+
+static int
+mac802154_send_association_resp_locked(struct ieee802154_sub_if_data *sdata,
+				       struct ieee802154_pan_device *target,
+				       struct ieee802154_assoc_resp_pl *assoc_resp_pl)
+{
+	u64 teaddr = swab64((__force u64)target->extended_addr);
+	struct ieee802154_association_resp_frame frame = {};
+	struct ieee802154_local *local = sdata->local;
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
+	struct sk_buff *skb;
+	int ret;
+
+	frame.mhr.fc.type = IEEE802154_FC_TYPE_MAC_CMD;
+	frame.mhr.fc.security_enabled = 0;
+	frame.mhr.fc.frame_pending = 0;
+	frame.mhr.fc.ack_request = 1; /* We always expect an ack here */
+	frame.mhr.fc.intra_pan = 1;
+	frame.mhr.fc.dest_addr_mode = IEEE802154_EXTENDED_ADDRESSING;
+	frame.mhr.fc.version = IEEE802154_2003_STD;
+	frame.mhr.fc.source_addr_mode = IEEE802154_EXTENDED_ADDRESSING;
+	frame.mhr.source.mode = IEEE802154_ADDR_LONG;
+	frame.mhr.source.extended_addr = wpan_dev->extended_addr;
+	frame.mhr.dest.mode = IEEE802154_ADDR_LONG;
+	frame.mhr.dest.pan_id = wpan_dev->pan_id;
+	frame.mhr.dest.extended_addr = target->extended_addr;
+	frame.mhr.seq = atomic_inc_return(&wpan_dev->dsn) & 0xFF;
+	frame.mac_pl.cmd_id = IEEE802154_CMD_ASSOCIATION_RESP;
+
+	skb = alloc_skb(IEEE802154_MAC_CMD_SKB_SZ + sizeof(*assoc_resp_pl),
+			GFP_KERNEL);
+	if (!skb)
+		return -ENOBUFS;
+
+	skb->dev = sdata->dev;
+
+	ret = ieee802154_mac_cmd_push(skb, &frame, assoc_resp_pl,
+				      sizeof(*assoc_resp_pl));
+	if (ret) {
+		kfree_skb(skb);
+		return ret;
+	}
+
+	ret = ieee802154_mlme_tx_locked(local, sdata, skb);
+	if (ret) {
+		dev_warn(&sdata->dev->dev,
+			 "No ASSOC RESP ACK received from %8phC\n", &teaddr);
+		if (ret > 0)
+			ret = (ret == IEEE802154_NO_ACK) ? -EREMOTEIO : -EIO;
+		return ret;
+	}
+
+	return 0;
+}
+
+int mac802154_process_association_req(struct ieee802154_sub_if_data *sdata,
+				      struct sk_buff *skb)
+{
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
+	struct ieee802154_addr *src = &mac_cb(skb)->source;
+	struct ieee802154_addr *dest = &mac_cb(skb)->dest;
+	struct ieee802154_assoc_resp_pl assoc_resp_pl = {};
+	struct ieee802154_assoc_req_pl assoc_req_pl;
+	struct ieee802154_pan_device *child, *exchild;
+	struct ieee802154_addr tmp = {};
+	u64 ceaddr;
+	int ret;
+
+	if (skb->len != sizeof(assoc_req_pl))
+		return -EINVAL;
+
+	if (unlikely(src->mode != IEEE802154_EXTENDED_ADDRESSING))
+		return -EINVAL;
+
+	if (unlikely(dest->pan_id != wpan_dev->pan_id))
+		return -ENODEV;
+
+	if (dest->mode == IEEE802154_EXTENDED_ADDRESSING &&
+	    unlikely(dest->extended_addr != wpan_dev->extended_addr))
+		return -ENODEV;
+	else if (dest->mode == IEEE802154_SHORT_ADDRESSING &&
+		 unlikely(dest->short_addr != wpan_dev->short_addr))
+		return -ENODEV;
+
+	if (wpan_dev->parent) {
+		dev_dbg(&sdata->dev->dev,
+			"Ignoring ASSOC REQ, not the PAN coordinator\n");
+		return -ENODEV;
+	}
+
+	mutex_lock(&wpan_dev->association_lock);
+
+	memcpy(&assoc_req_pl, skb->data, sizeof(assoc_req_pl));
+	if (assoc_req_pl.assoc_type) {
+		dev_err(&skb->dev->dev, "Fast associations not supported yet\n");
+		ret = -EOPNOTSUPP;
+		goto unlock;
+	}
+
+	child = kzalloc(sizeof(*child), GFP_KERNEL);
+	if (!child) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	child->extended_addr = src->extended_addr;
+	child->mode = IEEE802154_EXTENDED_ADDRESSING;
+	ceaddr = swab64((__force u64)child->extended_addr);
+
+	if (wpan_dev->nchildren >= wpan_dev->max_associations) {
+		if (!wpan_dev->max_associations)
+			assoc_resp_pl.status = IEEE802154_PAN_ACCESS_DENIED;
+		else
+			assoc_resp_pl.status = IEEE802154_PAN_AT_CAPACITY;
+		assoc_resp_pl.short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_BROADCAST);
+		dev_dbg(&sdata->dev->dev,
+			"Refusing ASSOC REQ from child %8phC, %s\n", &ceaddr,
+			assoc_resp_pl.status == IEEE802154_PAN_ACCESS_DENIED ?
+			"access denied" : "too many children");
+	} else {
+		assoc_resp_pl.status = IEEE802154_ASSOCIATION_SUCCESSFUL;
+		if (assoc_req_pl.alloc_addr) {
+			assoc_resp_pl.short_addr = cfg802154_get_free_short_addr(wpan_dev);
+			child->mode = IEEE802154_SHORT_ADDRESSING;
+		} else {
+			assoc_resp_pl.short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC);
+		}
+		child->short_addr = assoc_resp_pl.short_addr;
+		dev_dbg(&sdata->dev->dev,
+			"Accepting ASSOC REQ from child %8phC, providing short address 0x%04x\n",
+			&ceaddr, le16_to_cpu(child->short_addr));
+	}
+
+	ret = mac802154_send_association_resp_locked(sdata, child, &assoc_resp_pl);
+	if (ret || assoc_resp_pl.status != IEEE802154_ASSOCIATION_SUCCESSFUL) {
+		kfree(child);
+		goto unlock;
+	}
+
+	dev_dbg(&sdata->dev->dev,
+		"Successful association with new child %8phC\n", &ceaddr);
+
+	/* Ensure this child is not already associated (might happen due to
+	 * retransmissions), in this case drop the ex structure.
+	 */
+	tmp.mode = child->mode;
+	tmp.extended_addr = child->extended_addr;
+	exchild = cfg802154_device_is_child(wpan_dev, &tmp);
+	if (exchild) {
+		dev_dbg(&sdata->dev->dev,
+			"Child %8phC was already known\n", &ceaddr);
+		list_del(&exchild->node);
+	}
+
+	list_add(&child->node, &wpan_dev->children);
+	wpan_dev->nchildren++;
+
+unlock:
+	mutex_unlock(&wpan_dev->association_lock);
+	return ret;
+}
+
+int mac802154_process_disassociation_notif(struct ieee802154_sub_if_data *sdata,
+					   struct sk_buff *skb)
+{
+	struct ieee802154_addr *src = &mac_cb(skb)->source;
+	struct ieee802154_addr *dest = &mac_cb(skb)->dest;
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
+	struct ieee802154_pan_device *child;
+	struct ieee802154_addr target;
+	bool parent;
+	u64 teaddr;
+
+	if (skb->len != sizeof(u8))
+		return -EINVAL;
+
+	if (unlikely(src->mode != IEEE802154_EXTENDED_ADDRESSING))
+		return -EINVAL;
+
+	if (dest->mode == IEEE802154_EXTENDED_ADDRESSING &&
+	    unlikely(dest->extended_addr != wpan_dev->extended_addr))
+		return -ENODEV;
+	else if (dest->mode == IEEE802154_SHORT_ADDRESSING &&
+		 unlikely(dest->short_addr != wpan_dev->short_addr))
+		return -ENODEV;
+
+	if (dest->pan_id != wpan_dev->pan_id)
+		return -ENODEV;
+
+	target.mode = IEEE802154_EXTENDED_ADDRESSING;
+	target.extended_addr = src->extended_addr;
+	teaddr = swab64((__force u64)target.extended_addr);
+	dev_dbg(&skb->dev->dev, "Processing DISASSOC NOTIF from %8phC\n", &teaddr);
+
+	mutex_lock(&wpan_dev->association_lock);
+	parent = cfg802154_device_is_parent(wpan_dev, &target);
+	if (!parent)
+		child = cfg802154_device_is_child(wpan_dev, &target);
+	if (!parent && !child) {
+		mutex_unlock(&wpan_dev->association_lock);
+		return -EINVAL;
+	}
+
+	if (parent) {
+		kfree(wpan_dev->parent);
+		wpan_dev->parent = NULL;
+	} else {
+		list_del(&child->node);
+		kfree(child);
+		wpan_dev->nchildren--;
+	}
+
+	mutex_unlock(&wpan_dev->association_lock);
+
+	return 0;
+}
diff --git a/net/mptcp/crypto_test.c b/net/mptcp/crypto_test.c
index 017248dea038..220414e5c850 100644
--- a/net/mptcp/crypto_test.c
+++ b/net/mptcp/crypto_test.c
@@ -70,3 +70,4 @@ static struct kunit_suite mptcp_crypto_suite = {
 kunit_test_suite(mptcp_crypto_suite);
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("KUnit tests for MPTCP Crypto");
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index a0990c365a2e..c30405e76833 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -66,6 +66,7 @@ static const struct snmp_mib mptcp_snmp_list[] = {
 	SNMP_MIB_ITEM("RcvWndShared", MPTCP_MIB_RCVWNDSHARED),
 	SNMP_MIB_ITEM("RcvWndConflictUpdate", MPTCP_MIB_RCVWNDCONFLICTUPDATE),
 	SNMP_MIB_ITEM("RcvWndConflict", MPTCP_MIB_RCVWNDCONFLICT),
+	SNMP_MIB_ITEM("MPCurrEstab", MPTCP_MIB_CURRESTAB),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index cae71d947252..dd7fd1f246b5 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -65,6 +65,7 @@ enum linux_mptcp_mib_field {
 					 * conflict with another subflow while updating msk rcv wnd
 					 */
 	MPTCP_MIB_RCVWNDCONFLICT,	/* Conflict with while updating msk rcv wnd */
+	MPTCP_MIB_CURRESTAB,		/* Current established MPTCP connections */
 	__MPTCP_MIB_MAX
 };
 
@@ -95,4 +96,11 @@ static inline void __MPTCP_INC_STATS(struct net *net,
 		__SNMP_INC_STATS(net->mib.mptcp_statistics, field);
 }
 
+static inline void MPTCP_DEC_STATS(struct net *net,
+				   enum linux_mptcp_mib_field field)
+{
+	if (likely(net->mib.mptcp_statistics))
+		SNMP_DEC_STATS(net->mib.mptcp_statistics, field);
+}
+
 bool mptcp_mib_alloc(struct net *net);
diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c
index 8df1bdb647e2..5409c2ea3f57 100644
--- a/net/mptcp/mptcp_diag.c
+++ b/net/mptcp/mptcp_diag.c
@@ -245,4 +245,5 @@ static void __exit mptcp_diag_exit(void)
 module_init(mptcp_diag_init);
 module_exit(mptcp_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MPTCP socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-262 /* AF_INET - IPPROTO_MPTCP */);
diff --git a/net/mptcp/mptcp_pm_gen.c b/net/mptcp/mptcp_pm_gen.c
index a2325e70ddab..670da7822e6c 100644
--- a/net/mptcp/mptcp_pm_gen.c
+++ b/net/mptcp/mptcp_pm_gen.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
 /* Do not edit directly, auto-generated from: */
-/*	Documentation/netlink/specs/mptcp.yaml */
+/*	Documentation/netlink/specs/mptcp_pm.yaml */
 /* YNL-GEN kernel source */
 
 #include <net/netlink.h>
diff --git a/net/mptcp/mptcp_pm_gen.h b/net/mptcp/mptcp_pm_gen.h
index 10579d184587..ac9fc7225b6a 100644
--- a/net/mptcp/mptcp_pm_gen.h
+++ b/net/mptcp/mptcp_pm_gen.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
 /* Do not edit directly, auto-generated from: */
-/*	Documentation/netlink/specs/mptcp.yaml */
+/*	Documentation/netlink/specs/mptcp_pm.yaml */
 /* YNL-GEN kernel header */
 
 #ifndef _LINUX_MPTCP_PM_GEN_H
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index cd15ec73073e..c53914012d01 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -108,6 +108,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 			mp_opt->suboptions |= OPTION_MPTCP_DSS;
 			mp_opt->use_map = 1;
 			mp_opt->mpc_map = 1;
+			mp_opt->use_ack = 0;
 			mp_opt->data_len = get_unaligned_be16(ptr);
 			ptr += 2;
 		}
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 1529ec358815..287a60381eae 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1048,6 +1048,11 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
 	if (err)
 		return err;
 
+	/* We don't use mptcp_set_state() here because it needs to be called
+	 * under the msk socket lock. For the moment, that will not bring
+	 * anything more than only calling inet_sk_state_store(), because the
+	 * old status is known (TCP_CLOSE).
+	 */
 	inet_sk_state_store(newsk, TCP_LISTEN);
 	lock_sock(ssk);
 	err = __inet_listen_sk(ssk, backlog);
@@ -1100,7 +1105,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc
 static const struct genl_multicast_group mptcp_pm_mcgrps[] = {
 	[MPTCP_PM_CMD_GRP_OFFSET]	= { .name = MPTCP_PM_CMD_GRP_NAME, },
 	[MPTCP_PM_EV_GRP_OFFSET]        = { .name = MPTCP_PM_EV_GRP_NAME,
-					    .flags = GENL_UNS_ADMIN_PERM,
+					    .flags = GENL_MCAST_CAP_NET_ADMIN,
 					  },
 };
 
@@ -1515,8 +1520,9 @@ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list)
 	struct mptcp_pm_addr_entry *entry;
 
 	list_for_each_entry(entry, rm_list, list) {
-		remove_anno_list_by_saddr(msk, &entry->addr);
-		if (alist.nr < MPTCP_RM_IDS_MAX)
+		if ((remove_anno_list_by_saddr(msk, &entry->addr) ||
+		     lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) &&
+		    alist.nr < MPTCP_RM_IDS_MAX)
 			alist.ids[alist.nr++] = entry->addr.id;
 	}
 
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 5c01b9bc619a..efecbe3cf415 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -276,12 +276,12 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info)
 
 	if (!mptcp_pm_is_userspace(msk)) {
 		GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected");
-		goto remove_err;
+		goto out;
 	}
 
 	if (id_val == 0) {
 		err = mptcp_userspace_pm_remove_id_zero_address(msk, info);
-		goto remove_err;
+		goto out;
 	}
 
 	lock_sock(sk);
@@ -296,7 +296,7 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info)
 	if (!match) {
 		GENL_SET_ERR_MSG(info, "address with specified id not found");
 		release_sock(sk);
-		goto remove_err;
+		goto out;
 	}
 
 	list_move(&match->list, &free_list);
@@ -310,7 +310,7 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	err = 0;
- remove_err:
+out:
 	sock_put(sk);
 	return err;
 }
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index a0b8356cd8c5..3ed4709a7509 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -55,28 +55,14 @@ static u64 mptcp_wnd_end(const struct mptcp_sock *msk)
 	return READ_ONCE(msk->wnd_end);
 }
 
-static bool mptcp_is_tcpsk(struct sock *sk)
+static const struct proto_ops *mptcp_fallback_tcp_ops(const struct sock *sk)
 {
-	struct socket *sock = sk->sk_socket;
-
-	if (unlikely(sk->sk_prot == &tcp_prot)) {
-		/* we are being invoked after mptcp_accept() has
-		 * accepted a non-mp-capable flow: sk is a tcp_sk,
-		 * not an mptcp one.
-		 *
-		 * Hand the socket over to tcp so all further socket ops
-		 * bypass mptcp.
-		 */
-		WRITE_ONCE(sock->ops, &inet_stream_ops);
-		return true;
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
-	} else if (unlikely(sk->sk_prot == &tcpv6_prot)) {
-		WRITE_ONCE(sock->ops, &inet6_stream_ops);
-		return true;
+	if (sk->sk_prot == &tcpv6_prot)
+		return &inet6_stream_ops;
 #endif
-	}
-
-	return false;
+	WARN_ON_ONCE(sk->sk_prot != &tcp_prot);
+	return &inet_stream_ops;
 }
 
 static int __mptcp_socket_create(struct mptcp_sock *msk)
@@ -443,11 +429,11 @@ static void mptcp_check_data_fin_ack(struct sock *sk)
 
 		switch (sk->sk_state) {
 		case TCP_FIN_WAIT1:
-			inet_sk_state_store(sk, TCP_FIN_WAIT2);
+			mptcp_set_state(sk, TCP_FIN_WAIT2);
 			break;
 		case TCP_CLOSING:
 		case TCP_LAST_ACK:
-			inet_sk_state_store(sk, TCP_CLOSE);
+			mptcp_set_state(sk, TCP_CLOSE);
 			break;
 		}
 
@@ -608,13 +594,13 @@ static bool mptcp_check_data_fin(struct sock *sk)
 
 		switch (sk->sk_state) {
 		case TCP_ESTABLISHED:
-			inet_sk_state_store(sk, TCP_CLOSE_WAIT);
+			mptcp_set_state(sk, TCP_CLOSE_WAIT);
 			break;
 		case TCP_FIN_WAIT1:
-			inet_sk_state_store(sk, TCP_CLOSING);
+			mptcp_set_state(sk, TCP_CLOSING);
 			break;
 		case TCP_FIN_WAIT2:
-			inet_sk_state_store(sk, TCP_CLOSE);
+			mptcp_set_state(sk, TCP_CLOSE);
 			break;
 		default:
 			/* Other states not expected */
@@ -789,7 +775,7 @@ static bool __mptcp_subflow_error_report(struct sock *sk, struct sock *ssk)
 	 */
 	ssk_state = inet_sk_state_load(ssk);
 	if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD))
-		inet_sk_state_store(sk, ssk_state);
+		mptcp_set_state(sk, ssk_state);
 	WRITE_ONCE(sk->sk_err, -err);
 
 	/* This barrier is coupled with smp_rmb() in mptcp_poll() */
@@ -1230,6 +1216,8 @@ static void mptcp_update_infinite_map(struct mptcp_sock *msk,
 	mptcp_do_fallback(ssk);
 }
 
+#define MPTCP_MAX_GSO_SIZE (GSO_LEGACY_MAX_SIZE - (MAX_TCP_HEADER + 1))
+
 static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 			      struct mptcp_data_frag *dfrag,
 			      struct mptcp_sendmsg_info *info)
@@ -1256,6 +1244,8 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 		return -EAGAIN;
 
 	/* compute send limit */
+	if (unlikely(ssk->sk_gso_max_size > MPTCP_MAX_GSO_SIZE))
+		ssk->sk_gso_max_size = MPTCP_MAX_GSO_SIZE;
 	info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags);
 	copy = info->size_goal;
 
@@ -2473,7 +2463,7 @@ out:
 	    inet_sk_state_load(msk->first) == TCP_CLOSE) {
 		if (sk->sk_state != TCP_ESTABLISHED ||
 		    msk->in_accept_queue || sock_flag(sk, SOCK_DEAD)) {
-			inet_sk_state_store(sk, TCP_CLOSE);
+			mptcp_set_state(sk, TCP_CLOSE);
 			mptcp_close_wake_up(sk);
 		} else {
 			mptcp_start_tout_timer(sk);
@@ -2568,7 +2558,7 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
 		WRITE_ONCE(sk->sk_err, ECONNRESET);
 	}
 
-	inet_sk_state_store(sk, TCP_CLOSE);
+	mptcp_set_state(sk, TCP_CLOSE);
 	WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
 	smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
 	set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags);
@@ -2703,7 +2693,7 @@ static void mptcp_do_fastclose(struct sock *sk)
 	struct mptcp_subflow_context *subflow, *tmp;
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	inet_sk_state_store(sk, TCP_CLOSE);
+	mptcp_set_state(sk, TCP_CLOSE);
 	mptcp_for_each_subflow_safe(msk, subflow, tmp)
 		__mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow),
 				  subflow, MPTCP_CF_FASTCLOSE);
@@ -2881,6 +2871,24 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
 	release_sock(ssk);
 }
 
+void mptcp_set_state(struct sock *sk, int state)
+{
+	int oldstate = sk->sk_state;
+
+	switch (state) {
+	case TCP_ESTABLISHED:
+		if (oldstate != TCP_ESTABLISHED)
+			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB);
+		break;
+
+	default:
+		if (oldstate == TCP_ESTABLISHED)
+			MPTCP_DEC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB);
+	}
+
+	inet_sk_state_store(sk, state);
+}
+
 static const unsigned char new_state[16] = {
 	/* current state:     new state:      action:	*/
 	[0 /* (Invalid) */] = TCP_CLOSE,
@@ -2903,7 +2911,7 @@ static int mptcp_close_state(struct sock *sk)
 	int next = (int)new_state[sk->sk_state];
 	int ns = next & TCP_STATE_MASK;
 
-	inet_sk_state_store(sk, ns);
+	mptcp_set_state(sk, ns);
 
 	return next & TCP_ACTION_FIN;
 }
@@ -3014,7 +3022,7 @@ bool __mptcp_close(struct sock *sk, long timeout)
 
 	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) {
 		mptcp_check_listen_stop(sk);
-		inet_sk_state_store(sk, TCP_CLOSE);
+		mptcp_set_state(sk, TCP_CLOSE);
 		goto cleanup;
 	}
 
@@ -3057,7 +3065,7 @@ cleanup:
 	 * state, let's not keep resources busy for no reasons
 	 */
 	if (subflows_alive == 0)
-		inet_sk_state_store(sk, TCP_CLOSE);
+		mptcp_set_state(sk, TCP_CLOSE);
 
 	sock_hold(sk);
 	pr_debug("msk=%p state=%d", sk, sk->sk_state);
@@ -3123,7 +3131,7 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 		return -EBUSY;
 
 	mptcp_check_listen_stop(sk);
-	inet_sk_state_store(sk, TCP_CLOSE);
+	mptcp_set_state(sk, TCP_CLOSE);
 
 	mptcp_stop_rtx_timer(sk);
 	mptcp_stop_tout_timer(sk);
@@ -3211,7 +3219,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 	/* this can't race with mptcp_close(), as the msk is
 	 * not yet exposted to user-space
 	 */
-	inet_sk_state_store(nsk, TCP_ESTABLISHED);
+	mptcp_set_state(nsk, TCP_ESTABLISHED);
 
 	/* The msk maintain a ref to each subflow in the connections list */
 	WRITE_ONCE(msk->first, ssk);
@@ -3254,44 +3262,6 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
 	WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd);
 }
 
-static struct sock *mptcp_accept(struct sock *ssk, int flags, int *err,
-				 bool kern)
-{
-	struct sock *newsk;
-
-	pr_debug("ssk=%p, listener=%p", ssk, mptcp_subflow_ctx(ssk));
-	newsk = inet_csk_accept(ssk, flags, err, kern);
-	if (!newsk)
-		return NULL;
-
-	pr_debug("newsk=%p, subflow is mptcp=%d", newsk, sk_is_mptcp(newsk));
-	if (sk_is_mptcp(newsk)) {
-		struct mptcp_subflow_context *subflow;
-		struct sock *new_mptcp_sock;
-
-		subflow = mptcp_subflow_ctx(newsk);
-		new_mptcp_sock = subflow->conn;
-
-		/* is_mptcp should be false if subflow->conn is missing, see
-		 * subflow_syn_recv_sock()
-		 */
-		if (WARN_ON_ONCE(!new_mptcp_sock)) {
-			tcp_sk(newsk)->is_mptcp = 0;
-			goto out;
-		}
-
-		newsk = new_mptcp_sock;
-		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
-	} else {
-		MPTCP_INC_STATS(sock_net(ssk),
-				MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
-	}
-
-out:
-	newsk->sk_kern_sock = kern;
-	return newsk;
-}
-
 void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags)
 {
 	struct mptcp_subflow_context *subflow, *tmp;
@@ -3398,11 +3368,12 @@ static void mptcp_release_cb(struct sock *sk)
 	if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags))
 		__mptcp_clean_una_wakeup(sk);
 	if (unlikely(msk->cb_flags)) {
-		/* be sure to set the current sk state before tacking actions
-		 * depending on sk_state, that is processing MPTCP_ERROR_REPORT
+		/* be sure to sync the msk state before taking actions
+		 * depending on sk_state (MPTCP_ERROR_REPORT)
+		 * On sk release avoid actions depending on the first subflow
 		 */
-		if (__test_and_clear_bit(MPTCP_CONNECTED, &msk->cb_flags))
-			__mptcp_set_connected(sk);
+		if (__test_and_clear_bit(MPTCP_SYNC_STATE, &msk->cb_flags) && msk->first)
+			__mptcp_sync_state(sk, msk->pending_state);
 		if (__test_and_clear_bit(MPTCP_ERROR_REPORT, &msk->cb_flags))
 			__mptcp_error_report(sk);
 		if (__test_and_clear_bit(MPTCP_SYNC_SNDBUF, &msk->cb_flags))
@@ -3669,7 +3640,7 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (IS_ERR(ssk))
 		return PTR_ERR(ssk);
 
-	inet_sk_state_store(sk, TCP_SYN_SENT);
+	mptcp_set_state(sk, TCP_SYN_SENT);
 	subflow = mptcp_subflow_ctx(ssk);
 #ifdef CONFIG_TCP_MD5SIG
 	/* no MPTCP if MD5SIG is enabled on this socket or we may run out of
@@ -3719,7 +3690,7 @@ out:
 	if (unlikely(err)) {
 		/* avoid leaving a dangling token in an unconnected socket */
 		mptcp_token_destroy(msk);
-		inet_sk_state_store(sk, TCP_CLOSE);
+		mptcp_set_state(sk, TCP_CLOSE);
 		return err;
 	}
 
@@ -3734,7 +3705,6 @@ static struct proto mptcp_prot = {
 	.connect	= mptcp_connect,
 	.disconnect	= mptcp_disconnect,
 	.close		= mptcp_close,
-	.accept		= mptcp_accept,
 	.setsockopt	= mptcp_setsockopt,
 	.getsockopt	= mptcp_getsockopt,
 	.shutdown	= mptcp_shutdown,
@@ -3809,13 +3779,13 @@ static int mptcp_listen(struct socket *sock, int backlog)
 		goto unlock;
 	}
 
-	inet_sk_state_store(sk, TCP_LISTEN);
+	mptcp_set_state(sk, TCP_LISTEN);
 	sock_set_flag(sk, SOCK_RCU_FREE);
 
 	lock_sock(ssk);
 	err = __inet_listen_sk(ssk, backlog);
 	release_sock(ssk);
-	inet_sk_state_store(sk, inet_sk_state_load(ssk));
+	mptcp_set_state(sk, inet_sk_state_load(ssk));
 
 	if (!err) {
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
@@ -3844,18 +3814,36 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 	if (!ssk)
 		return -EINVAL;
 
-	newsk = mptcp_accept(ssk, flags, &err, kern);
+	pr_debug("ssk=%p, listener=%p", ssk, mptcp_subflow_ctx(ssk));
+	newsk = inet_csk_accept(ssk, flags, &err, kern);
 	if (!newsk)
 		return err;
 
-	lock_sock(newsk);
-
-	__inet_accept(sock, newsock, newsk);
-	if (!mptcp_is_tcpsk(newsock->sk)) {
-		struct mptcp_sock *msk = mptcp_sk(newsk);
+	pr_debug("newsk=%p, subflow is mptcp=%d", newsk, sk_is_mptcp(newsk));
+	if (sk_is_mptcp(newsk)) {
 		struct mptcp_subflow_context *subflow;
+		struct sock *new_mptcp_sock;
+
+		subflow = mptcp_subflow_ctx(newsk);
+		new_mptcp_sock = subflow->conn;
+
+		/* is_mptcp should be false if subflow->conn is missing, see
+		 * subflow_syn_recv_sock()
+		 */
+		if (WARN_ON_ONCE(!new_mptcp_sock)) {
+			tcp_sk(newsk)->is_mptcp = 0;
+			goto tcpfallback;
+		}
+
+		newsk = new_mptcp_sock;
+		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
+
+		newsk->sk_kern_sock = kern;
+		lock_sock(newsk);
+		__inet_accept(sock, newsock, newsk);
 
 		set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags);
+		msk = mptcp_sk(newsk);
 		msk->in_accept_queue = 0;
 
 		/* set ssk->sk_socket of accept()ed flows to mptcp socket.
@@ -3875,8 +3863,23 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 			__mptcp_close_ssk(newsk, msk->first,
 					  mptcp_subflow_ctx(msk->first), 0);
 			if (unlikely(list_is_singular(&msk->conn_list)))
-				inet_sk_state_store(newsk, TCP_CLOSE);
+				mptcp_set_state(newsk, TCP_CLOSE);
 		}
+	} else {
+		MPTCP_INC_STATS(sock_net(ssk),
+				MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
+tcpfallback:
+		newsk->sk_kern_sock = kern;
+		lock_sock(newsk);
+		__inet_accept(sock, newsock, newsk);
+		/* we are being invoked after accepting a non-mp-capable
+		 * flow: sk is a tcp_sk, not an mptcp one.
+		 *
+		 * Hand the socket over to tcp so all further socket ops
+		 * bypass mptcp.
+		 */
+		WRITE_ONCE(newsock->sk->sk_socket->ops,
+			   mptcp_fallback_tcp_ops(newsock->sk));
 	}
 	release_sock(newsk);
 
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index fe6f2d399ee8..3517f2d24a22 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -124,7 +124,7 @@
 #define MPTCP_ERROR_REPORT	3
 #define MPTCP_RETRANSMIT	4
 #define MPTCP_FLUSH_JOIN_LIST	5
-#define MPTCP_CONNECTED		6
+#define MPTCP_SYNC_STATE	6
 #define MPTCP_SYNC_SNDBUF	7
 
 struct mptcp_skb_cb {
@@ -296,6 +296,9 @@ struct mptcp_sock {
 	bool		use_64bit_ack; /* Set when we received a 64-bit DSN */
 	bool		csum_enabled;
 	bool		allow_infinite_fallback;
+	u8		pending_state; /* A subflow asked to set this sk_state,
+					* protected by the msk data lock
+					*/
 	u8		mpc_endpoint_id;
 	u8		recvmsg_inq:1,
 			cork:1,
@@ -638,6 +641,7 @@ bool __mptcp_close(struct sock *sk, long timeout);
 void mptcp_cancel_work(struct sock *sk);
 void __mptcp_unaccepted_force_close(struct sock *sk);
 void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk);
+void mptcp_set_state(struct sock *sk, int state);
 
 bool mptcp_addresses_equal(const struct mptcp_addr_info *a,
 			   const struct mptcp_addr_info *b, bool use_port);
@@ -728,7 +732,7 @@ void mptcp_get_options(const struct sk_buff *skb,
 		       struct mptcp_options_received *mp_opt);
 
 void mptcp_finish_connect(struct sock *sk);
-void __mptcp_set_connected(struct sock *sk);
+void __mptcp_sync_state(struct sock *sk, int state);
 void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout);
 
 static inline void mptcp_stop_tout_timer(struct sock *sk)
@@ -1072,6 +1076,15 @@ static inline void __mptcp_do_fallback(struct mptcp_sock *msk)
 	set_bit(MPTCP_FALLBACK_DONE, &msk->flags);
 }
 
+static inline bool __mptcp_has_initial_subflow(const struct mptcp_sock *msk)
+{
+	struct sock *ssk = READ_ONCE(msk->first);
+
+	return ssk && ((1 << inet_sk_state_load(ssk)) &
+		       (TCPF_ESTABLISHED | TCPF_SYN_SENT |
+			TCPF_SYN_RECV | TCPF_LISTEN));
+}
+
 static inline void mptcp_do_fallback(struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
@@ -1115,7 +1128,7 @@ static inline bool subflow_simultaneous_connect(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 
-	return sk->sk_state == TCP_ESTABLISHED &&
+	return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1) &&
 	       is_active_ssk(subflow) &&
 	       !subflow->conn_finished;
 }
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 77f5e8932abf..c40f1428e602 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -440,6 +440,8 @@ static bool mptcp_supported_sockopt(int level, int optname)
 		/* should work fine */
 		case IP_FREEBIND:
 		case IP_TRANSPARENT:
+		case IP_BIND_ADDRESS_NO_PORT:
+		case IP_LOCAL_PORT_RANGE:
 
 		/* the following are control cmsg related */
 		case IP_PKTINFO:
@@ -455,7 +457,6 @@ static bool mptcp_supported_sockopt(int level, int optname)
 		/* common stuff that need some love */
 		case IP_TOS:
 		case IP_TTL:
-		case IP_BIND_ADDRESS_NO_PORT:
 		case IP_MTU_DISCOVER:
 		case IP_RECVERR:
 
@@ -683,8 +684,8 @@ static int mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, sockptr_t op
 	return 0;
 }
 
-static int mptcp_setsockopt_sol_ip_set_transparent(struct mptcp_sock *msk, int optname,
-						   sockptr_t optval, unsigned int optlen)
+static int mptcp_setsockopt_sol_ip_set(struct mptcp_sock *msk, int optname,
+				       sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = (struct sock *)msk;
 	struct sock *ssk;
@@ -710,6 +711,14 @@ static int mptcp_setsockopt_sol_ip_set_transparent(struct mptcp_sock *msk, int o
 		inet_assign_bit(TRANSPARENT, ssk,
 				inet_test_bit(TRANSPARENT, sk));
 		break;
+	case IP_BIND_ADDRESS_NO_PORT:
+		inet_assign_bit(BIND_ADDRESS_NO_PORT, ssk,
+				inet_test_bit(BIND_ADDRESS_NO_PORT, sk));
+		break;
+	case IP_LOCAL_PORT_RANGE:
+		WRITE_ONCE(inet_sk(ssk)->local_port_range,
+			   READ_ONCE(inet_sk(sk)->local_port_range));
+		break;
 	default:
 		release_sock(sk);
 		WARN_ON_ONCE(1);
@@ -738,8 +747,11 @@ static int mptcp_setsockopt_v4_set_tos(struct mptcp_sock *msk, int optname,
 	val = READ_ONCE(inet_sk(sk)->tos);
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		bool slow;
 
+		slow = lock_sock_fast(ssk);
 		__ip_sock_set_tos(ssk, val);
+		unlock_sock_fast(ssk, slow);
 	}
 	release_sock(sk);
 
@@ -752,7 +764,9 @@ static int mptcp_setsockopt_v4(struct mptcp_sock *msk, int optname,
 	switch (optname) {
 	case IP_FREEBIND:
 	case IP_TRANSPARENT:
-		return mptcp_setsockopt_sol_ip_set_transparent(msk, optname, optval, optlen);
+	case IP_BIND_ADDRESS_NO_PORT:
+	case IP_LOCAL_PORT_RANGE:
+		return mptcp_setsockopt_sol_ip_set(msk, optname, optval, optlen);
 	case IP_TOS:
 		return mptcp_setsockopt_v4_set_tos(msk, optname, optval, optlen);
 	}
@@ -935,6 +949,8 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
 	info->mptcpi_bytes_sent = msk->bytes_sent;
 	info->mptcpi_bytes_received = msk->bytes_received;
 	info->mptcpi_bytes_retrans = msk->bytes_retrans;
+	info->mptcpi_subflows_total = info->mptcpi_subflows +
+		__mptcp_has_initial_subflow(msk);
 	unlock_sock_fast(sk, slow);
 }
 EXPORT_SYMBOL_GPL(mptcp_diag_fill_info);
@@ -1345,6 +1361,12 @@ static int mptcp_getsockopt_v4(struct mptcp_sock *msk, int optname,
 	switch (optname) {
 	case IP_TOS:
 		return mptcp_put_int_option(msk, optval, optlen, READ_ONCE(inet_sk(sk)->tos));
+	case IP_BIND_ADDRESS_NO_PORT:
+		return mptcp_put_int_option(msk, optval, optlen,
+				inet_test_bit(BIND_ADDRESS_NO_PORT, sk));
+	case IP_LOCAL_PORT_RANGE:
+		return mptcp_put_int_option(msk, optval, optlen,
+				READ_ONCE(inet_sk(sk)->local_port_range));
 	}
 
 	return -EOPNOTSUPP;
@@ -1445,6 +1467,8 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
 
 	inet_assign_bit(TRANSPARENT, ssk, inet_test_bit(TRANSPARENT, sk));
 	inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk));
+	inet_assign_bit(BIND_ADDRESS_NO_PORT, ssk, inet_test_bit(BIND_ADDRESS_NO_PORT, sk));
+	WRITE_ONCE(inet_sk(ssk)->local_port_range, READ_ONCE(inet_sk(sk)->local_port_range));
 }
 
 void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk)
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index a4f3c27f0309..3eacd04e7099 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -419,22 +419,28 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc
 	return inet_sk(sk)->inet_dport != inet_sk((struct sock *)msk)->inet_dport;
 }
 
-void __mptcp_set_connected(struct sock *sk)
+void __mptcp_sync_state(struct sock *sk, int state)
 {
-	__mptcp_propagate_sndbuf(sk, mptcp_sk(sk)->first);
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	__mptcp_propagate_sndbuf(sk, msk->first);
 	if (sk->sk_state == TCP_SYN_SENT) {
-		inet_sk_state_store(sk, TCP_ESTABLISHED);
+		mptcp_set_state(sk, state);
 		sk->sk_state_change(sk);
 	}
 }
 
-static void mptcp_set_connected(struct sock *sk)
+static void mptcp_propagate_state(struct sock *sk, struct sock *ssk)
 {
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
 	mptcp_data_lock(sk);
-	if (!sock_owned_by_user(sk))
-		__mptcp_set_connected(sk);
-	else
-		__set_bit(MPTCP_CONNECTED, &mptcp_sk(sk)->cb_flags);
+	if (!sock_owned_by_user(sk)) {
+		__mptcp_sync_state(sk, ssk->sk_state);
+	} else {
+		msk->pending_state = ssk->sk_state;
+		__set_bit(MPTCP_SYNC_STATE, &msk->cb_flags);
+	}
 	mptcp_data_unlock(sk);
 }
 
@@ -496,7 +502,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		subflow_set_remote_key(msk, subflow, &mp_opt);
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK);
 		mptcp_finish_connect(sk);
-		mptcp_set_connected(parent);
+		mptcp_propagate_state(parent, sk);
 	} else if (subflow->request_join) {
 		u8 hmac[SHA256_DIGEST_SIZE];
 
@@ -540,7 +546,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 	} else if (mptcp_check_fallback(sk)) {
 fallback:
 		mptcp_rcv_space_init(msk, sk);
-		mptcp_set_connected(parent);
+		mptcp_propagate_state(parent, sk);
 	}
 	return;
 
@@ -1740,7 +1746,7 @@ static void subflow_state_change(struct sock *sk)
 		mptcp_rcv_space_init(msk, sk);
 		pr_fallback(msk);
 		subflow->conn_finished = 1;
-		mptcp_set_connected(parent);
+		mptcp_propagate_state(parent, sk);
 	}
 
 	/* as recvmsg() does not acquire the subflow socket for ssk selection
@@ -1976,6 +1982,17 @@ static void tcp_release_cb_override(struct sock *ssk)
 	tcp_release_cb(ssk);
 }
 
+static int tcp_abort_override(struct sock *ssk, int err)
+{
+	/* closing a listener subflow requires a great deal of care.
+	 * keep it simple and just prevent such operation
+	 */
+	if (inet_sk_state_load(ssk) == TCP_LISTEN)
+		return -EINVAL;
+
+	return tcp_abort(ssk, err);
+}
+
 static struct tcp_ulp_ops subflow_ulp_ops __read_mostly = {
 	.name		= "mptcp",
 	.owner		= THIS_MODULE,
@@ -2020,6 +2037,7 @@ void __init mptcp_subflow_init(void)
 
 	tcp_prot_override = tcp_prot;
 	tcp_prot_override.release_cb = tcp_release_cb_override;
+	tcp_prot_override.diag_destroy = tcp_abort_override;
 
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 	/* In struct mptcp_subflow_request_sock, we assume the TCP request sock
@@ -2055,6 +2073,7 @@ void __init mptcp_subflow_init(void)
 
 	tcpv6_prot_override = tcpv6_prot;
 	tcpv6_prot_override.release_cb = tcp_release_cb_override;
+	tcpv6_prot_override.diag_destroy = tcp_abort_override;
 #endif
 
 	mptcp_diag_subflow_init(&subflow_ulp_ops);
diff --git a/net/mptcp/token_test.c b/net/mptcp/token_test.c
index 0758865ab658..bfff53e668da 100644
--- a/net/mptcp/token_test.c
+++ b/net/mptcp/token_test.c
@@ -143,3 +143,4 @@ static struct kunit_suite mptcp_token_suite = {
 kunit_test_suite(mptcp_token_suite);
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("KUnit tests for MPTCP Token");
diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h
index 03757e76bb6b..374412ed780b 100644
--- a/net/ncsi/internal.h
+++ b/net/ncsi/internal.h
@@ -105,8 +105,11 @@ enum {
 
 
 struct ncsi_channel_version {
-	u32 version;		/* Supported BCD encoded NCSI version */
-	u32 alpha2;		/* Supported BCD encoded NCSI version */
+	u8   major;		/* NCSI version major */
+	u8   minor;		/* NCSI version minor */
+	u8   update;		/* NCSI version update */
+	char alpha1;		/* NCSI version alpha1 */
+	char alpha2;		/* NCSI version alpha2 */
 	u8  fw_name[12];	/* Firmware name string                */
 	u32 fw_version;		/* Firmware version                   */
 	u16 pci_ids[4];		/* PCI identification                 */
diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c
index f8854bff286c..62fb1031763d 100644
--- a/net/ncsi/ncsi-aen.c
+++ b/net/ncsi/ncsi-aen.c
@@ -89,11 +89,6 @@ static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp,
 	if ((had_link == has_link) || chained)
 		return 0;
 
-	if (had_link)
-		netif_carrier_off(ndp->ndev.dev);
-	else
-		netif_carrier_on(ndp->ndev.dev);
-
 	if (!ndp->multi_package && !nc->package->multi_channel) {
 		if (had_link) {
 			ndp->flags |= NCSI_DEV_RESHUFFLE;
diff --git a/net/ncsi/ncsi-cmd.c b/net/ncsi/ncsi-cmd.c
index fd2236ee9a79..b3ff37a181d7 100644
--- a/net/ncsi/ncsi-cmd.c
+++ b/net/ncsi/ncsi-cmd.c
@@ -270,7 +270,8 @@ static struct ncsi_cmd_handler {
 	{ NCSI_PKT_CMD_GPS,    0, ncsi_cmd_handler_default },
 	{ NCSI_PKT_CMD_OEM,   -1, ncsi_cmd_handler_oem     },
 	{ NCSI_PKT_CMD_PLDM,   0, NULL                     },
-	{ NCSI_PKT_CMD_GPUUID, 0, ncsi_cmd_handler_default }
+	{ NCSI_PKT_CMD_GPUUID, 0, ncsi_cmd_handler_default },
+	{ NCSI_PKT_CMD_GMCMA,  0, ncsi_cmd_handler_default }
 };
 
 static struct ncsi_request *ncsi_alloc_command(struct ncsi_cmd_arg *nca)
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index d9da942ad53d..745c788f1d1d 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -689,8 +689,6 @@ static int set_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc,
 	return 0;
 }
 
-#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY)
-
 static int ncsi_oem_keep_phy_intel(struct ncsi_cmd_arg *nca)
 {
 	unsigned char data[NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN];
@@ -716,10 +714,6 @@ static int ncsi_oem_keep_phy_intel(struct ncsi_cmd_arg *nca)
 	return ret;
 }
 
-#endif
-
-#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC)
-
 /* NCSI OEM Command APIs */
 static int ncsi_oem_gma_handler_bcm(struct ncsi_cmd_arg *nca)
 {
@@ -856,8 +850,6 @@ static int ncsi_gma_handler(struct ncsi_cmd_arg *nca, unsigned int mf_id)
 	return nch->handler(nca);
 }
 
-#endif /* CONFIG_NCSI_OEM_CMD_GET_MAC */
-
 /* Determine if a given channel from the channel_queue should be used for Tx */
 static bool ncsi_channel_is_tx(struct ncsi_dev_priv *ndp,
 			       struct ncsi_channel *nc)
@@ -1039,20 +1031,23 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
 			goto error;
 		}
 
-		nd->state = ncsi_dev_state_config_oem_gma;
+		nd->state = IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC)
+			  ? ncsi_dev_state_config_oem_gma
+			  : ncsi_dev_state_config_clear_vids;
 		break;
 	case ncsi_dev_state_config_oem_gma:
 		nd->state = ncsi_dev_state_config_clear_vids;
-		ret = -1;
 
-#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC)
-		nca.type = NCSI_PKT_CMD_OEM;
 		nca.package = np->id;
 		nca.channel = nc->id;
 		ndp->pending_req_num = 1;
-		ret = ncsi_gma_handler(&nca, nc->version.mf_id);
-#endif /* CONFIG_NCSI_OEM_CMD_GET_MAC */
-
+		if (nc->version.major >= 1 && nc->version.minor >= 2) {
+			nca.type = NCSI_PKT_CMD_GMCMA;
+			ret = ncsi_xmit_cmd(&nca);
+		} else {
+			nca.type = NCSI_PKT_CMD_OEM;
+			ret = ncsi_gma_handler(&nca, nc->version.mf_id);
+		}
 		if (ret < 0)
 			schedule_work(&ndp->work);
 
@@ -1404,7 +1399,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp)
 
 		schedule_work(&ndp->work);
 		break;
-#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC)
 	case ncsi_dev_state_probe_mlx_gma:
 		ndp->pending_req_num = 1;
 
@@ -1429,7 +1423,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp)
 
 		nd->state = ncsi_dev_state_probe_cis;
 		break;
-#endif /* CONFIG_NCSI_OEM_CMD_GET_MAC */
 	case ncsi_dev_state_probe_cis:
 		ndp->pending_req_num = NCSI_RESERVED_CHANNEL;
 
@@ -1447,7 +1440,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp)
 		if (IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY))
 			nd->state = ncsi_dev_state_probe_keep_phy;
 		break;
-#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY)
 	case ncsi_dev_state_probe_keep_phy:
 		ndp->pending_req_num = 1;
 
@@ -1460,7 +1452,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp)
 
 		nd->state = ncsi_dev_state_probe_gvi;
 		break;
-#endif /* CONFIG_NCSI_OEM_CMD_KEEP_PHY */
 	case ncsi_dev_state_probe_gvi:
 	case ncsi_dev_state_probe_gc:
 	case ncsi_dev_state_probe_gls:
diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c
index a3a6753a1db7..2f872d064396 100644
--- a/net/ncsi/ncsi-netlink.c
+++ b/net/ncsi/ncsi-netlink.c
@@ -71,8 +71,8 @@ static int ncsi_write_channel_info(struct sk_buff *skb,
 	if (nc == nc->package->preferred_channel)
 		nla_put_flag(skb, NCSI_CHANNEL_ATTR_FORCED);
 
-	nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MAJOR, nc->version.version);
-	nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MINOR, nc->version.alpha2);
+	nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MAJOR, nc->version.major);
+	nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MINOR, nc->version.minor);
 	nla_put_string(skb, NCSI_CHANNEL_ATTR_VERSION_STR, nc->version.fw_name);
 
 	vid_nest = nla_nest_start_noflag(skb, NCSI_CHANNEL_ATTR_VLAN_LIST);
diff --git a/net/ncsi/ncsi-pkt.h b/net/ncsi/ncsi-pkt.h
index ba66c7dc3a21..f2f3b5c1b941 100644
--- a/net/ncsi/ncsi-pkt.h
+++ b/net/ncsi/ncsi-pkt.h
@@ -197,9 +197,12 @@ struct ncsi_rsp_gls_pkt {
 /* Get Version ID */
 struct ncsi_rsp_gvi_pkt {
 	struct ncsi_rsp_pkt_hdr rsp;          /* Response header */
-	__be32                  ncsi_version; /* NCSI version    */
+	unsigned char           major;        /* NCSI version major */
+	unsigned char           minor;        /* NCSI version minor */
+	unsigned char           update;       /* NCSI version update */
+	unsigned char           alpha1;       /* NCSI version alpha1 */
 	unsigned char           reserved[3];  /* Reserved        */
-	unsigned char           alpha2;       /* NCSI version    */
+	unsigned char           alpha2;       /* NCSI version alpha2 */
 	unsigned char           fw_name[12];  /* f/w name string */
 	__be32                  fw_version;   /* f/w version     */
 	__be16                  pci_ids[4];   /* PCI IDs         */
@@ -335,6 +338,14 @@ struct ncsi_rsp_gpuuid_pkt {
 	__be32                  checksum;
 };
 
+/* Get MC MAC Address */
+struct ncsi_rsp_gmcma_pkt {
+	struct ncsi_rsp_pkt_hdr rsp;
+	unsigned char           address_count;
+	unsigned char           reserved[3];
+	unsigned char           addresses[][ETH_ALEN];
+};
+
 /* AEN: Link State Change */
 struct ncsi_aen_lsc_pkt {
 	struct ncsi_aen_pkt_hdr aen;        /* AEN header      */
@@ -395,6 +406,7 @@ struct ncsi_aen_hncdsc_pkt {
 #define NCSI_PKT_CMD_GPUUID	0x52 /* Get package UUID                 */
 #define NCSI_PKT_CMD_QPNPR	0x56 /* Query Pending NC PLDM request */
 #define NCSI_PKT_CMD_SNPR	0x57 /* Send NC PLDM Reply  */
+#define NCSI_PKT_CMD_GMCMA	0x58 /* Get MC MAC Address */
 
 
 /* NCSI packet responses */
@@ -430,6 +442,7 @@ struct ncsi_aen_hncdsc_pkt {
 #define NCSI_PKT_RSP_GPUUID	(NCSI_PKT_CMD_GPUUID + 0x80)
 #define NCSI_PKT_RSP_QPNPR	(NCSI_PKT_CMD_QPNPR   + 0x80)
 #define NCSI_PKT_RSP_SNPR	(NCSI_PKT_CMD_SNPR   + 0x80)
+#define NCSI_PKT_RSP_GMCMA	(NCSI_PKT_CMD_GMCMA  + 0x80)
 
 /* NCSI response code/reason */
 #define NCSI_PKT_RSP_C_COMPLETED	0x0000 /* Command Completed        */
diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c
index 069c2659074b..bee290d0f48b 100644
--- a/net/ncsi/ncsi-rsp.c
+++ b/net/ncsi/ncsi-rsp.c
@@ -19,6 +19,19 @@
 #include "ncsi-pkt.h"
 #include "ncsi-netlink.h"
 
+/* Nibbles within [0xA, 0xF] add zero "0" to the returned value.
+ * Optional fields (encoded as 0xFF) will default to zero.
+ */
+static u8 decode_bcd_u8(u8 x)
+{
+	int lo = x & 0xF;
+	int hi = x >> 4;
+
+	lo = lo < 0xA ? lo : 0;
+	hi = hi < 0xA ? hi : 0;
+	return lo + hi * 10;
+}
+
 static int ncsi_validate_rsp_pkt(struct ncsi_request *nr,
 				 unsigned short payload)
 {
@@ -755,9 +768,18 @@ static int ncsi_rsp_handler_gvi(struct ncsi_request *nr)
 	if (!nc)
 		return -ENODEV;
 
-	/* Update to channel's version info */
+	/* Update channel's version info
+	 *
+	 * Major, minor, and update fields are supposed to be
+	 * unsigned integers encoded as packed BCD.
+	 *
+	 * Alpha1 and alpha2 are ISO/IEC 8859-1 characters.
+	 */
 	ncv = &nc->version;
-	ncv->version = ntohl(rsp->ncsi_version);
+	ncv->major = decode_bcd_u8(rsp->major);
+	ncv->minor = decode_bcd_u8(rsp->minor);
+	ncv->update = decode_bcd_u8(rsp->update);
+	ncv->alpha1 = rsp->alpha1;
 	ncv->alpha2 = rsp->alpha2;
 	memcpy(ncv->fw_name, rsp->fw_name, 12);
 	ncv->fw_version = ntohl(rsp->fw_version);
@@ -1069,6 +1091,44 @@ static int ncsi_rsp_handler_netlink(struct ncsi_request *nr)
 	return ret;
 }
 
+static int ncsi_rsp_handler_gmcma(struct ncsi_request *nr)
+{
+	struct ncsi_dev_priv *ndp = nr->ndp;
+	struct net_device *ndev = ndp->ndev.dev;
+	struct ncsi_rsp_gmcma_pkt *rsp;
+	struct sockaddr saddr;
+	int ret = -1;
+	int i;
+
+	rsp = (struct ncsi_rsp_gmcma_pkt *)skb_network_header(nr->rsp);
+	saddr.sa_family = ndev->type;
+	ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+
+	netdev_info(ndev, "NCSI: Received %d provisioned MAC addresses\n",
+		    rsp->address_count);
+	for (i = 0; i < rsp->address_count; i++) {
+		netdev_info(ndev, "NCSI: MAC address %d: %02x:%02x:%02x:%02x:%02x:%02x\n",
+			    i, rsp->addresses[i][0], rsp->addresses[i][1],
+			    rsp->addresses[i][2], rsp->addresses[i][3],
+			    rsp->addresses[i][4], rsp->addresses[i][5]);
+	}
+
+	for (i = 0; i < rsp->address_count; i++) {
+		memcpy(saddr.sa_data, &rsp->addresses[i], ETH_ALEN);
+		ret = ndev->netdev_ops->ndo_set_mac_address(ndev, &saddr);
+		if (ret < 0) {
+			netdev_warn(ndev, "NCSI: Unable to assign %pM to device\n",
+				    saddr.sa_data);
+			continue;
+		}
+		netdev_warn(ndev, "NCSI: Set MAC address to %pM\n", saddr.sa_data);
+		break;
+	}
+
+	ndp->gma_flag = ret == 0;
+	return ret;
+}
+
 static struct ncsi_rsp_handler {
 	unsigned char	type;
 	int             payload;
@@ -1105,7 +1165,8 @@ static struct ncsi_rsp_handler {
 	{ NCSI_PKT_RSP_PLDM,   -1, ncsi_rsp_handler_pldm    },
 	{ NCSI_PKT_RSP_GPUUID, 20, ncsi_rsp_handler_gpuuid  },
 	{ NCSI_PKT_RSP_QPNPR,  -1, ncsi_rsp_handler_pldm    },
-	{ NCSI_PKT_RSP_SNPR,   -1, ncsi_rsp_handler_pldm    }
+	{ NCSI_PKT_RSP_SNPR,   -1, ncsi_rsp_handler_pldm    },
+	{ NCSI_PKT_RSP_GMCMA,  -1, ncsi_rsp_handler_gmcma   },
 };
 
 int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev,
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index 26ab0e9612d8..21f7860e8fa1 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -4,6 +4,8 @@
 #ifndef __IP_SET_BITMAP_IP_GEN_H
 #define __IP_SET_BITMAP_IP_GEN_H
 
+#include <linux/rcupdate_wait.h>
+
 #define mtype_do_test		IPSET_TOKEN(MTYPE, _do_test)
 #define mtype_gc_test		IPSET_TOKEN(MTYPE, _gc_test)
 #define mtype_is_filled		IPSET_TOKEN(MTYPE, _is_filled)
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 35d2f9c9ada0..4c133e06be1d 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -61,6 +61,8 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET);
 	ip_set_dereference((inst)->ip_set_list)[id]
 #define ip_set_ref_netlink(inst,id)	\
 	rcu_dereference_raw((inst)->ip_set_list)[id]
+#define ip_set_dereference_nfnl(p)	\
+	rcu_dereference_check(p, lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET))
 
 /* The set types are implemented in modules and registered set types
  * can be found in ip_set_type_list. Adding/deleting types is
@@ -708,15 +710,10 @@ __ip_set_put_netlink(struct ip_set *set)
 static struct ip_set *
 ip_set_rcu_get(struct net *net, ip_set_id_t index)
 {
-	struct ip_set *set;
 	struct ip_set_net *inst = ip_set_pernet(net);
 
-	rcu_read_lock();
-	/* ip_set_list itself needs to be protected */
-	set = rcu_dereference(inst->ip_set_list)[index];
-	rcu_read_unlock();
-
-	return set;
+	/* ip_set_list and the set pointer need to be protected */
+	return ip_set_dereference_nfnl(inst->ip_set_list)[index];
 }
 
 static inline void
@@ -1397,6 +1394,9 @@ static int ip_set_swap(struct sk_buff *skb, const struct nfnl_info *info,
 	ip_set(inst, to_id) = from;
 	write_unlock_bh(&ip_set_ref_lock);
 
+	/* Make sure all readers of the old set pointers are completed. */
+	synchronize_rcu();
+
 	return 0;
 }
 
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 7c2399541771..cbf80da9a01c 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -5,6 +5,7 @@
 #define _IP_SET_HASH_GEN_H
 
 #include <linux/rcupdate.h>
+#include <linux/rcupdate_wait.h>
 #include <linux/jhash.h>
 #include <linux/types.h>
 #include <linux/netfilter/nfnetlink.h>
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 9065da3cdd12..a743db073887 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -31,6 +31,7 @@
 #include <linux/seq_file.h>
 #include <linux/jhash.h>
 #include <linux/random.h>
+#include <linux/rcupdate_wait.h>
 
 #include <net/net_namespace.h>
 #include <net/ip_vs.h>
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index c5970ba416ae..f821ad2e19b3 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -21,6 +21,7 @@
 #include <linux/interrupt.h>
 #include <linux/sysctl.h>
 #include <linux/list.h>
+#include <linux/rcupdate_wait.h>
 
 #include <net/ip_vs.h>
 
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index eaf9f2ed0067..be74c0906dda 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1365,7 +1365,7 @@ static int set_mcast_if(struct sock *sk, struct net_device *dev)
 		struct ipv6_pinfo *np = inet6_sk(sk);
 
 		/* IPV6_MULTICAST_IF */
-		np->mcast_oif = dev->ifindex;
+		WRITE_ONCE(np->mcast_oif, dev->ifindex);
 	}
 #endif
 	release_sock(sk);
diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c
index e502ec00b2fe..0e4beae421f8 100644
--- a/net/netfilter/nf_bpf_link.c
+++ b/net/netfilter/nf_bpf_link.c
@@ -31,7 +31,7 @@ struct bpf_nf_link {
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) || IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 static const struct nf_defrag_hook *
 get_proto_defrag_hook(struct bpf_nf_link *link,
-		      const struct nf_defrag_hook __rcu *global_hook,
+		      const struct nf_defrag_hook __rcu **ptr_global_hook,
 		      const char *mod)
 {
 	const struct nf_defrag_hook *hook;
@@ -39,7 +39,7 @@ get_proto_defrag_hook(struct bpf_nf_link *link,
 
 	/* RCU protects us from races against module unloading */
 	rcu_read_lock();
-	hook = rcu_dereference(global_hook);
+	hook = rcu_dereference(*ptr_global_hook);
 	if (!hook) {
 		rcu_read_unlock();
 		err = request_module(mod);
@@ -47,7 +47,7 @@ get_proto_defrag_hook(struct bpf_nf_link *link,
 			return ERR_PTR(err < 0 ? err : -EINVAL);
 
 		rcu_read_lock();
-		hook = rcu_dereference(global_hook);
+		hook = rcu_dereference(*ptr_global_hook);
 	}
 
 	if (hook && try_module_get(hook->owner)) {
@@ -78,7 +78,7 @@ static int bpf_nf_enable_defrag(struct bpf_nf_link *link)
 	switch (link->hook_ops.pf) {
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
 	case NFPROTO_IPV4:
-		hook = get_proto_defrag_hook(link, nf_defrag_v4_hook, "nf_defrag_ipv4");
+		hook = get_proto_defrag_hook(link, &nf_defrag_v4_hook, "nf_defrag_ipv4");
 		if (IS_ERR(hook))
 			return PTR_ERR(hook);
 
@@ -87,7 +87,7 @@ static int bpf_nf_enable_defrag(struct bpf_nf_link *link)
 #endif
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 	case NFPROTO_IPV6:
-		hook = get_proto_defrag_hook(link, nf_defrag_v6_hook, "nf_defrag_ipv6");
+		hook = get_proto_defrag_hook(link, &nf_defrag_v6_hook, "nf_defrag_ipv6");
 		if (IS_ERR(hook))
 			return PTR_ERR(hook);
 
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index fb0ae15e96df..0c22a02c2035 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -992,13 +992,13 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family)
 	if (err)
 		goto err_filter;
 
-	if (!cda[CTA_FILTER])
-		return filter;
-
 	err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone);
 	if (err < 0)
 		goto err_filter;
 
+	if (!cda[CTA_FILTER])
+		return filter;
+
 	err = ctnetlink_parse_filter(cda[CTA_FILTER], filter);
 	if (err < 0)
 		goto err_filter;
@@ -1043,7 +1043,7 @@ err_filter:
 
 static bool ctnetlink_needs_filter(u8 family, const struct nlattr * const *cda)
 {
-	return family || cda[CTA_MARK] || cda[CTA_FILTER] || cda[CTA_STATUS];
+	return family || cda[CTA_MARK] || cda[CTA_FILTER] || cda[CTA_STATUS] || cda[CTA_ZONE];
 }
 
 static int ctnetlink_start(struct netlink_callback *cb)
@@ -1148,6 +1148,10 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data)
 	if (filter->family && nf_ct_l3num(ct) != filter->family)
 		goto ignore_entry;
 
+	if (filter->zone.id != NF_CT_DEFAULT_ZONE_ID &&
+	    !nf_ct_zone_equal_any(ct, &filter->zone))
+		goto ignore_entry;
+
 	if (filter->orig_flags) {
 		tuple = nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL);
 		if (!ctnetlink_filter_match_tuple(&filter->orig, tuple,
diff --git a/net/netfilter/nf_nat_ovs.c b/net/netfilter/nf_nat_ovs.c
index 551abd2da614..0f9a559f6207 100644
--- a/net/netfilter/nf_nat_ovs.c
+++ b/net/netfilter/nf_nat_ovs.c
@@ -75,9 +75,10 @@ static int nf_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
 	}
 
 	err = nf_nat_packet(ct, ctinfo, hooknum, skb);
+out:
 	if (err == NF_ACCEPT)
 		*action |= BIT(maniptype);
-out:
+
 	return err;
 }
 
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 467671f2d42f..fbbc4fd37349 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -617,7 +617,7 @@ synproxy_recv_client_ack(struct net *net,
 	struct synproxy_net *snet = synproxy_pernet(net);
 	int mss;
 
-	mss = __cookie_v4_check(ip_hdr(skb), th, ntohl(th->ack_seq) - 1);
+	mss = __cookie_v4_check(ip_hdr(skb), th);
 	if (mss == 0) {
 		this_cpu_inc(snet->stats->cookie_invalid);
 		return false;
@@ -1034,7 +1034,7 @@ synproxy_recv_client_ack_ipv6(struct net *net,
 	struct synproxy_net *snet = synproxy_pernet(net);
 	int mss;
 
-	mss = nf_cookie_v6_check(ipv6_hdr(skb), th, ntohl(th->ack_seq) - 1);
+	mss = nf_cookie_v6_check(ipv6_hdr(skb), th);
 	if (mss == 0) {
 		this_cpu_inc(snet->stats->cookie_invalid);
 		return false;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index a761ee6796f6..8438a8922e4a 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -803,7 +803,7 @@ static struct nft_table *nft_table_lookup(const struct net *net,
 
 static struct nft_table *nft_table_lookup_byhandle(const struct net *net,
 						   const struct nlattr *nla,
-						   u8 genmask, u32 nlpid)
+						   int family, u8 genmask, u32 nlpid)
 {
 	struct nftables_pernet *nft_net;
 	struct nft_table *table;
@@ -811,6 +811,7 @@ static struct nft_table *nft_table_lookup_byhandle(const struct net *net,
 	nft_net = nft_pernet(net);
 	list_for_each_entry(table, &nft_net->tables, list) {
 		if (be64_to_cpu(nla_get_be64(nla)) == table->handle &&
+		    table->family == family &&
 		    nft_active_genmask(table, genmask)) {
 			if (nft_table_has_owner(table) &&
 			    nlpid && table->nlpid != nlpid)
@@ -1544,7 +1545,7 @@ static int nf_tables_deltable(struct sk_buff *skb, const struct nfnl_info *info,
 
 	if (nla[NFTA_TABLE_HANDLE]) {
 		attr = nla[NFTA_TABLE_HANDLE];
-		table = nft_table_lookup_byhandle(net, attr, genmask,
+		table = nft_table_lookup_byhandle(net, attr, family, genmask,
 						  NETLINK_CB(skb).portid);
 	} else {
 		attr = nla[NFTA_TABLE_NAME];
@@ -2260,7 +2261,16 @@ static int nft_chain_parse_hook(struct net *net,
 				return -EOPNOTSUPP;
 		}
 
-		type = basechain->type;
+		if (nla[NFTA_CHAIN_TYPE]) {
+			type = __nf_tables_chain_type_lookup(nla[NFTA_CHAIN_TYPE],
+							     family);
+			if (!type) {
+				NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TYPE]);
+				return -ENOENT;
+			}
+		} else {
+			type = basechain->type;
+		}
 	}
 
 	if (!try_module_get(type->owner)) {
@@ -5816,10 +5826,6 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 	nla_nest_end(skb, nest);
 	nlmsg_end(skb, nlh);
 
-	if (dump_ctx->reset && args.iter.count > args.iter.skip)
-		audit_log_nft_set_reset(table, cb->seq,
-					args.iter.count - args.iter.skip);
-
 	rcu_read_unlock();
 
 	if (args.iter.err && args.iter.err != -EMSGSIZE)
@@ -5835,6 +5841,26 @@ nla_put_failure:
 	return -ENOSPC;
 }
 
+static int nf_tables_dumpreset_set(struct sk_buff *skb,
+				   struct netlink_callback *cb)
+{
+	struct nftables_pernet *nft_net = nft_pernet(sock_net(skb->sk));
+	struct nft_set_dump_ctx *dump_ctx = cb->data;
+	int ret, skip = cb->args[0];
+
+	mutex_lock(&nft_net->commit_mutex);
+
+	ret = nf_tables_dump_set(skb, cb);
+
+	if (cb->args[0] > skip)
+		audit_log_nft_set_reset(dump_ctx->ctx.table, cb->seq,
+					cb->args[0] - skip);
+
+	mutex_unlock(&nft_net->commit_mutex);
+
+	return ret;
+}
+
 static int nf_tables_dump_set_start(struct netlink_callback *cb)
 {
 	struct nft_set_dump_ctx *dump_ctx = cb->data;
@@ -5909,7 +5935,7 @@ static int nft_setelem_parse_flags(const struct nft_set *set,
 	return 0;
 }
 
-static int nft_setelem_parse_key(struct nft_ctx *ctx, struct nft_set *set,
+static int nft_setelem_parse_key(struct nft_ctx *ctx, const struct nft_set *set,
 				 struct nft_data *key, struct nlattr *attr)
 {
 	struct nft_data_desc desc = {
@@ -5962,7 +5988,7 @@ static void *nft_setelem_catchall_get(const struct net *net,
 	return priv;
 }
 
-static int nft_setelem_get(struct nft_ctx *ctx, struct nft_set *set,
+static int nft_setelem_get(struct nft_ctx *ctx, const struct nft_set *set,
 			   struct nft_set_elem *elem, u32 flags)
 {
 	void *priv;
@@ -5981,7 +6007,7 @@ static int nft_setelem_get(struct nft_ctx *ctx, struct nft_set *set,
 	return 0;
 }
 
-static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set,
+static int nft_get_set_elem(struct nft_ctx *ctx, const struct nft_set *set,
 			    const struct nlattr *attr, bool reset)
 {
 	struct nlattr *nla[NFTA_SET_ELEM_MAX + 1];
@@ -6038,21 +6064,18 @@ err_fill_setelem:
 	return err;
 }
 
-/* called with rcu_read_lock held */
-static int nf_tables_getsetelem(struct sk_buff *skb,
-				const struct nfnl_info *info,
-				const struct nlattr * const nla[])
+static int nft_set_dump_ctx_init(struct nft_set_dump_ctx *dump_ctx,
+				 const struct sk_buff *skb,
+				 const struct nfnl_info *info,
+				 const struct nlattr * const nla[],
+				 bool reset)
 {
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_cur(info->net);
 	u8 family = info->nfmsg->nfgen_family;
-	int rem, err = 0, nelems = 0;
 	struct net *net = info->net;
 	struct nft_table *table;
 	struct nft_set *set;
-	struct nlattr *attr;
-	struct nft_ctx ctx;
-	bool reset = false;
 
 	table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family,
 				 genmask, 0);
@@ -6067,10 +6090,22 @@ static int nf_tables_getsetelem(struct sk_buff *skb,
 		return PTR_ERR(set);
 	}
 
-	nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla);
+	nft_ctx_init(&dump_ctx->ctx, net, skb,
+		     info->nlh, family, table, NULL, nla);
+	dump_ctx->set = set;
+	dump_ctx->reset = reset;
+	return 0;
+}
 
-	if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETSETELEM_RESET)
-		reset = true;
+/* called with rcu_read_lock held */
+static int nf_tables_getsetelem(struct sk_buff *skb,
+				const struct nfnl_info *info,
+				const struct nlattr * const nla[])
+{
+	struct netlink_ext_ack *extack = info->extack;
+	struct nft_set_dump_ctx dump_ctx;
+	struct nlattr *attr;
+	int rem, err = 0;
 
 	if (info->nlh->nlmsg_flags & NLM_F_DUMP) {
 		struct netlink_dump_control c = {
@@ -6079,12 +6114,55 @@ static int nf_tables_getsetelem(struct sk_buff *skb,
 			.done = nf_tables_dump_set_done,
 			.module = THIS_MODULE,
 		};
-		struct nft_set_dump_ctx dump_ctx = {
-			.set = set,
-			.ctx = ctx,
-			.reset = reset,
+
+		err = nft_set_dump_ctx_init(&dump_ctx, skb, info, nla, false);
+		if (err)
+			return err;
+
+		c.data = &dump_ctx;
+		return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c);
+	}
+
+	if (!nla[NFTA_SET_ELEM_LIST_ELEMENTS])
+		return -EINVAL;
+
+	err = nft_set_dump_ctx_init(&dump_ctx, skb, info, nla, false);
+	if (err)
+		return err;
+
+	nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) {
+		err = nft_get_set_elem(&dump_ctx.ctx, dump_ctx.set, attr, false);
+		if (err < 0) {
+			NL_SET_BAD_ATTR(extack, attr);
+			break;
+		}
+	}
+
+	return err;
+}
+
+static int nf_tables_getsetelem_reset(struct sk_buff *skb,
+				      const struct nfnl_info *info,
+				      const struct nlattr * const nla[])
+{
+	struct nftables_pernet *nft_net = nft_pernet(info->net);
+	struct netlink_ext_ack *extack = info->extack;
+	struct nft_set_dump_ctx dump_ctx;
+	int rem, err = 0, nelems = 0;
+	struct nlattr *attr;
+
+	if (info->nlh->nlmsg_flags & NLM_F_DUMP) {
+		struct netlink_dump_control c = {
+			.start = nf_tables_dump_set_start,
+			.dump = nf_tables_dumpreset_set,
+			.done = nf_tables_dump_set_done,
+			.module = THIS_MODULE,
 		};
 
+		err = nft_set_dump_ctx_init(&dump_ctx, skb, info, nla, true);
+		if (err)
+			return err;
+
 		c.data = &dump_ctx;
 		return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c);
 	}
@@ -6092,18 +6170,31 @@ static int nf_tables_getsetelem(struct sk_buff *skb,
 	if (!nla[NFTA_SET_ELEM_LIST_ELEMENTS])
 		return -EINVAL;
 
+	if (!try_module_get(THIS_MODULE))
+		return -EINVAL;
+	rcu_read_unlock();
+	mutex_lock(&nft_net->commit_mutex);
+	rcu_read_lock();
+
+	err = nft_set_dump_ctx_init(&dump_ctx, skb, info, nla, true);
+	if (err)
+		goto out_unlock;
+
 	nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) {
-		err = nft_get_set_elem(&ctx, set, attr, reset);
+		err = nft_get_set_elem(&dump_ctx.ctx, dump_ctx.set, attr, true);
 		if (err < 0) {
 			NL_SET_BAD_ATTR(extack, attr);
 			break;
 		}
 		nelems++;
 	}
+	audit_log_nft_set_reset(dump_ctx.ctx.table, nft_net->base_seq, nelems);
 
-	if (reset)
-		audit_log_nft_set_reset(table, nft_pernet(net)->base_seq,
-					nelems);
+out_unlock:
+	rcu_read_unlock();
+	mutex_unlock(&nft_net->commit_mutex);
+	rcu_read_lock();
+	module_put(THIS_MODULE);
 
 	return err;
 }
@@ -7263,10 +7354,11 @@ static int nf_tables_delsetelem(struct sk_buff *skb,
 
 		if (err < 0) {
 			NL_SET_BAD_ATTR(extack, attr);
-			break;
+			return err;
 		}
 	}
-	return err;
+
+	return 0;
 }
 
 /*
@@ -9076,7 +9168,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
 		.policy		= nft_set_elem_list_policy,
 	},
 	[NFT_MSG_GETSETELEM_RESET] = {
-		.call		= nf_tables_getsetelem,
+		.call		= nf_tables_getsetelem_reset,
 		.type		= NFNL_CB_RCU,
 		.attr_count	= NFTA_SET_ELEM_LIST_MAX,
 		.policy		= nft_set_elem_list_policy,
@@ -9679,16 +9771,14 @@ void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans)
 	call_rcu(&trans->rcu, nft_trans_gc_trans_free);
 }
 
-static struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc,
-						  unsigned int gc_seq,
-						  bool sync)
+struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc,
+						 unsigned int gc_seq)
 {
-	struct nft_set_elem_catchall *catchall, *next;
+	struct nft_set_elem_catchall *catchall;
 	const struct nft_set *set = gc->set;
-	struct nft_elem_priv *elem_priv;
 	struct nft_set_ext *ext;
 
-	list_for_each_entry_safe(catchall, next, &set->catchall_list, list) {
+	list_for_each_entry_rcu(catchall, &set->catchall_list, list) {
 		ext = nft_set_elem_ext(set, catchall->elem);
 
 		if (!nft_set_elem_expired(ext))
@@ -9698,35 +9788,42 @@ static struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc,
 
 		nft_set_elem_dead(ext);
 dead_elem:
-		if (sync)
-			gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC);
-		else
-			gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC);
-
+		gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC);
 		if (!gc)
 			return NULL;
 
-		elem_priv = catchall->elem;
-		if (sync) {
-			nft_setelem_data_deactivate(gc->net, gc->set, elem_priv);
-			nft_setelem_catchall_destroy(catchall);
-		}
-
-		nft_trans_gc_elem_add(gc, elem_priv);
+		nft_trans_gc_elem_add(gc, catchall->elem);
 	}
 
 	return gc;
 }
 
-struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc,
-						 unsigned int gc_seq)
-{
-	return nft_trans_gc_catchall(gc, gc_seq, false);
-}
-
 struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc)
 {
-	return nft_trans_gc_catchall(gc, 0, true);
+	struct nft_set_elem_catchall *catchall, *next;
+	const struct nft_set *set = gc->set;
+	struct nft_elem_priv *elem_priv;
+	struct nft_set_ext *ext;
+
+	WARN_ON_ONCE(!lockdep_commit_lock_is_held(gc->net));
+
+	list_for_each_entry_safe(catchall, next, &set->catchall_list, list) {
+		ext = nft_set_elem_ext(set, catchall->elem);
+
+		if (!nft_set_elem_expired(ext))
+			continue;
+
+		gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);
+		if (!gc)
+			return NULL;
+
+		elem_priv = catchall->elem;
+		nft_setelem_data_deactivate(gc->net, gc->set, elem_priv);
+		nft_setelem_catchall_destroy(catchall);
+		nft_trans_gc_elem_add(gc, elem_priv);
+	}
+
+	return gc;
 }
 
 static void nf_tables_module_autoload_cleanup(struct net *net)
@@ -9880,7 +9977,7 @@ static void nft_set_commit_update(struct list_head *set_update_list)
 	list_for_each_entry_safe(set, next, set_update_list, pending_update) {
 		list_del_init(&set->pending_update);
 
-		if (!set->ops->commit)
+		if (!set->ops->commit || set->dead)
 			continue;
 
 		set->ops->commit(set);
@@ -10376,6 +10473,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 				nft_trans_destroy(trans);
 				break;
 			}
+			nft_trans_set(trans)->dead = 1;
 			list_del_rcu(&nft_trans_set(trans)->list);
 			break;
 		case NFT_MSG_DELSET:
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 8b536d7ef6c2..c3e635364701 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -158,7 +158,7 @@ static bool nft_payload_fast_eval(const struct nft_expr *expr,
 	else {
 		if (!(pkt->flags & NFT_PKTINFO_L4PROTO))
 			return false;
-		ptr = skb_network_header(skb) + nft_thoff(pkt);
+		ptr = skb->data + nft_thoff(pkt);
 	}
 
 	ptr += priv->offset;
diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c
index e596d1a842f7..f6e791a68101 100644
--- a/net/netfilter/nft_byteorder.c
+++ b/net/netfilter/nft_byteorder.c
@@ -38,13 +38,14 @@ void nft_byteorder_eval(const struct nft_expr *expr,
 
 	switch (priv->size) {
 	case 8: {
+		u64 *dst64 = (void *)dst;
 		u64 src64;
 
 		switch (priv->op) {
 		case NFT_BYTEORDER_NTOH:
 			for (i = 0; i < priv->len / 8; i++) {
 				src64 = nft_reg_load64(&src[i]);
-				nft_reg_store64(&dst[i],
+				nft_reg_store64(&dst64[i],
 						be64_to_cpu((__force __be64)src64));
 			}
 			break;
@@ -52,7 +53,7 @@ void nft_byteorder_eval(const struct nft_expr *expr,
 			for (i = 0; i < priv->len / 8; i++) {
 				src64 = (__force __u64)
 					cpu_to_be64(nft_reg_load64(&src[i]));
-				nft_reg_store64(&dst[i], src64);
+				nft_reg_store64(&dst64[i], src64);
 			}
 			break;
 		}
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index b18a79039125..c09dba57354c 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -280,10 +280,15 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 			priv->expr_array[i] = dynset_expr;
 			priv->num_exprs++;
 
-			if (set->num_exprs &&
-			    dynset_expr->ops != set->exprs[i]->ops) {
-				err = -EOPNOTSUPP;
-				goto err_expr_free;
+			if (set->num_exprs) {
+				if (i >= set->num_exprs) {
+					err = -EINVAL;
+					goto err_expr_free;
+				}
+				if (dynset_expr->ops != set->exprs[i]->ops) {
+					err = -EOPNOTSUPP;
+					goto err_expr_free;
+				}
 			}
 			i++;
 		}
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index 3fbaa7bf41f9..6eb571d0c3fd 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -214,7 +214,7 @@ static void nft_exthdr_tcp_eval(const struct nft_expr *expr,
 
 		offset = i + priv->offset;
 		if (priv->flags & NFT_EXTHDR_F_PRESENT) {
-			*dest = 1;
+			nft_reg_store8(dest, 1);
 		} else {
 			if (priv->len % NFT_REG32_SIZE)
 				dest[priv->len / NFT_REG32_SIZE] = 0;
@@ -461,7 +461,7 @@ static void nft_exthdr_dccp_eval(const struct nft_expr *expr,
 		type = bufp[0];
 
 		if (type == priv->type) {
-			*dest = 1;
+			nft_reg_store8(dest, 1);
 			return;
 		}
 
diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c
index 1bfe258018da..37cfe6dd712d 100644
--- a/net/netfilter/nft_fib.c
+++ b/net/netfilter/nft_fib.c
@@ -145,11 +145,15 @@ void nft_fib_store_result(void *reg, const struct nft_fib *priv,
 	switch (priv->result) {
 	case NFT_FIB_RESULT_OIF:
 		index = dev ? dev->ifindex : 0;
-		*dreg = (priv->flags & NFTA_FIB_F_PRESENT) ? !!index : index;
+		if (priv->flags & NFTA_FIB_F_PRESENT)
+			nft_reg_store8(dreg, !!index);
+		else
+			*dreg = index;
+
 		break;
 	case NFT_FIB_RESULT_OIFNAME:
 		if (priv->flags & NFTA_FIB_F_PRESENT)
-			*dreg = !!dev;
+			nft_reg_store8(dreg, !!dev);
 		else
 			strscpy_pad(reg, dev ? dev->name : "", IFNAMSIZ);
 		break;
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index fccb3cf7749c..6475c7abc1fe 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -78,7 +78,7 @@ static int nft_immediate_init(const struct nft_ctx *ctx,
 		case NFT_GOTO:
 			err = nf_tables_bind_chain(ctx, chain);
 			if (err < 0)
-				return err;
+				goto err1;
 			break;
 		default:
 			break;
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index f7da7c43333b..ba0d3683a45d 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -63,7 +63,7 @@ nft_meta_get_eval_time(enum nft_meta_keys key,
 {
 	switch (key) {
 	case NFT_META_TIME_NS:
-		nft_reg_store64(dest, ktime_get_real_ns());
+		nft_reg_store64((u64 *)dest, ktime_get_real_ns());
 		break;
 	case NFT_META_TIME_DAY:
 		nft_reg_store8(dest, nft_meta_weekday());
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 701977af3ee8..efd523496be4 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -1597,7 +1597,7 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m)
 		if (nft_set_elem_expired(&e->ext)) {
 			priv->dirty = true;
 
-			gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC);
+			gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);
 			if (!gc)
 				return;
 
@@ -2043,6 +2043,9 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set,
 
 		e = f->mt[r].e;
 
+		if (!nft_set_elem_active(&e->ext, iter->genmask))
+			goto cont;
+
 		iter->err = iter->fn(ctx, set, iter, &e->priv);
 		if (iter->err < 0)
 			goto out;
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 6f1186abd47b..baa3fea4fe65 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -624,14 +624,12 @@ static void nft_rbtree_gc(struct nft_set *set)
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_rbtree_elem *rbe, *rbe_end = NULL;
-	struct nftables_pernet *nft_net;
 	struct rb_node *node, *next;
 	struct nft_trans_gc *gc;
 	struct net *net;
 
 	set  = nft_set_container_of(priv);
 	net  = read_pnet(&set->net);
-	nft_net = nft_pernet(net);
 
 	gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL);
 	if (!gc)
diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c
index e85ce69924ae..50332888c8d2 100644
--- a/net/netfilter/xt_owner.c
+++ b/net/netfilter/xt_owner.c
@@ -76,18 +76,23 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par)
 		 */
 		return false;
 
-	filp = sk->sk_socket->file;
-	if (filp == NULL)
+	read_lock_bh(&sk->sk_callback_lock);
+	filp = sk->sk_socket ? sk->sk_socket->file : NULL;
+	if (filp == NULL) {
+		read_unlock_bh(&sk->sk_callback_lock);
 		return ((info->match ^ info->invert) &
 		       (XT_OWNER_UID | XT_OWNER_GID)) == 0;
+	}
 
 	if (info->match & XT_OWNER_UID) {
 		kuid_t uid_min = make_kuid(net->user_ns, info->uid_min);
 		kuid_t uid_max = make_kuid(net->user_ns, info->uid_max);
 		if ((uid_gte(filp->f_cred->fsuid, uid_min) &&
 		     uid_lte(filp->f_cred->fsuid, uid_max)) ^
-		    !(info->invert & XT_OWNER_UID))
+		    !(info->invert & XT_OWNER_UID)) {
+			read_unlock_bh(&sk->sk_callback_lock);
 			return false;
+		}
 	}
 
 	if (info->match & XT_OWNER_GID) {
@@ -112,10 +117,13 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par)
 			}
 		}
 
-		if (match ^ !(info->invert & XT_OWNER_GID))
+		if (match ^ !(info->invert & XT_OWNER_GID)) {
+			read_unlock_bh(&sk->sk_callback_lock);
 			return false;
+		}
 	}
 
+	read_unlock_bh(&sk->sk_callback_lock);
 	return true;
 }
 
diff --git a/net/netlabel/netlabel_calipso.c b/net/netlabel/netlabel_calipso.c
index f1d5b8465217..a07c2216d28b 100644
--- a/net/netlabel/netlabel_calipso.c
+++ b/net/netlabel/netlabel_calipso.c
@@ -54,6 +54,28 @@ static const struct nla_policy calipso_genl_policy[NLBL_CALIPSO_A_MAX + 1] = {
 	[NLBL_CALIPSO_A_MTYPE] = { .type = NLA_U32 },
 };
 
+static const struct netlbl_calipso_ops *calipso_ops;
+
+/**
+ * netlbl_calipso_ops_register - Register the CALIPSO operations
+ * @ops: ops to register
+ *
+ * Description:
+ * Register the CALIPSO packet engine operations.
+ *
+ */
+const struct netlbl_calipso_ops *
+netlbl_calipso_ops_register(const struct netlbl_calipso_ops *ops)
+{
+	return xchg(&calipso_ops, ops);
+}
+EXPORT_SYMBOL(netlbl_calipso_ops_register);
+
+static const struct netlbl_calipso_ops *netlbl_calipso_ops_get(void)
+{
+	return READ_ONCE(calipso_ops);
+}
+
 /* NetLabel Command Handlers
  */
 /**
@@ -96,15 +118,18 @@ static int netlbl_calipso_add_pass(struct genl_info *info,
  *
  */
 static int netlbl_calipso_add(struct sk_buff *skb, struct genl_info *info)
-
 {
 	int ret_val = -EINVAL;
 	struct netlbl_audit audit_info;
+	const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get();
 
 	if (!info->attrs[NLBL_CALIPSO_A_DOI] ||
 	    !info->attrs[NLBL_CALIPSO_A_MTYPE])
 		return -EINVAL;
 
+	if (!ops)
+		return -EOPNOTSUPP;
+
 	netlbl_netlink_auditinfo(&audit_info);
 	switch (nla_get_u32(info->attrs[NLBL_CALIPSO_A_MTYPE])) {
 	case CALIPSO_MAP_PASS:
@@ -363,28 +388,6 @@ int __init netlbl_calipso_genl_init(void)
 	return genl_register_family(&netlbl_calipso_gnl_family);
 }
 
-static const struct netlbl_calipso_ops *calipso_ops;
-
-/**
- * netlbl_calipso_ops_register - Register the CALIPSO operations
- * @ops: ops to register
- *
- * Description:
- * Register the CALIPSO packet engine operations.
- *
- */
-const struct netlbl_calipso_ops *
-netlbl_calipso_ops_register(const struct netlbl_calipso_ops *ops)
-{
-	return xchg(&calipso_ops, ops);
-}
-EXPORT_SYMBOL(netlbl_calipso_ops_register);
-
-static const struct netlbl_calipso_ops *netlbl_calipso_ops_get(void)
-{
-	return READ_ONCE(calipso_ops);
-}
-
 /**
  * calipso_doi_add - Add a new DOI to the CALIPSO protocol engine
  * @doi_def: the DOI structure
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index eb086b06d60d..4ed8ffd58ff3 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1204,8 +1204,7 @@ struct sock *netlink_getsockbyfilp(struct file *filp)
 	return sock;
 }
 
-static struct sk_buff *netlink_alloc_large_skb(unsigned int size,
-					       int broadcast)
+struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast)
 {
 	struct sk_buff *skb;
 	void *data;
@@ -1520,8 +1519,7 @@ out:
 int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb,
 			       u32 portid,
 			       u32 group, gfp_t allocation,
-			       int (*filter)(struct sock *dsk,
-					     struct sk_buff *skb, void *data),
+			       netlink_filter_fn filter,
 			       void *filter_data)
 {
 	struct net *net = sock_net(ssk);
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 92ef5ed2e7b0..8c7af02f8454 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -631,6 +631,138 @@ static int genl_validate_ops(const struct genl_family *family)
 	return 0;
 }
 
+static void *genl_sk_priv_alloc(struct genl_family *family)
+{
+	void *priv;
+
+	priv = kzalloc(family->sock_priv_size, GFP_KERNEL);
+	if (!priv)
+		return ERR_PTR(-ENOMEM);
+
+	if (family->sock_priv_init)
+		family->sock_priv_init(priv);
+
+	return priv;
+}
+
+static void genl_sk_priv_free(const struct genl_family *family, void *priv)
+{
+	if (family->sock_priv_destroy)
+		family->sock_priv_destroy(priv);
+	kfree(priv);
+}
+
+static int genl_sk_privs_alloc(struct genl_family *family)
+{
+	if (!family->sock_priv_size)
+		return 0;
+
+	family->sock_privs = kzalloc(sizeof(*family->sock_privs), GFP_KERNEL);
+	if (!family->sock_privs)
+		return -ENOMEM;
+	xa_init(family->sock_privs);
+	return 0;
+}
+
+static void genl_sk_privs_free(const struct genl_family *family)
+{
+	unsigned long id;
+	void *priv;
+
+	if (!family->sock_priv_size)
+		return;
+
+	xa_for_each(family->sock_privs, id, priv)
+		genl_sk_priv_free(family, priv);
+
+	xa_destroy(family->sock_privs);
+	kfree(family->sock_privs);
+}
+
+static void genl_sk_priv_free_by_sock(struct genl_family *family,
+				      struct sock *sk)
+{
+	void *priv;
+
+	if (!family->sock_priv_size)
+		return;
+	priv = xa_erase(family->sock_privs, (unsigned long) sk);
+	if (!priv)
+		return;
+	genl_sk_priv_free(family, priv);
+}
+
+static void genl_release(struct sock *sk, unsigned long *groups)
+{
+	struct genl_family *family;
+	unsigned int id;
+
+	down_read(&cb_lock);
+
+	idr_for_each_entry(&genl_fam_idr, family, id)
+		genl_sk_priv_free_by_sock(family, sk);
+
+	up_read(&cb_lock);
+}
+
+/**
+ * __genl_sk_priv_get - Get family private pointer for socket, if exists
+ *
+ * @family: family
+ * @sk: socket
+ *
+ * Lookup a private memory for a Generic netlink family and specified socket.
+ *
+ * Caller should make sure this is called in RCU read locked section.
+ *
+ * Return: valid pointer on success, otherwise negative error value
+ * encoded by ERR_PTR(), NULL in case priv does not exist.
+ */
+void *__genl_sk_priv_get(struct genl_family *family, struct sock *sk)
+{
+	if (WARN_ON_ONCE(!family->sock_privs))
+		return ERR_PTR(-EINVAL);
+	return xa_load(family->sock_privs, (unsigned long) sk);
+}
+
+/**
+ * genl_sk_priv_get - Get family private pointer for socket
+ *
+ * @family: family
+ * @sk: socket
+ *
+ * Lookup a private memory for a Generic netlink family and specified socket.
+ * Allocate the private memory in case it was not already done.
+ *
+ * Return: valid pointer on success, otherwise negative error value
+ * encoded by ERR_PTR().
+ */
+void *genl_sk_priv_get(struct genl_family *family, struct sock *sk)
+{
+	void *priv, *old_priv;
+
+	priv = __genl_sk_priv_get(family, sk);
+	if (priv)
+		return priv;
+
+	/* priv for the family does not exist so far, create it. */
+
+	priv = genl_sk_priv_alloc(family);
+	if (IS_ERR(priv))
+		return ERR_CAST(priv);
+
+	old_priv = xa_cmpxchg(family->sock_privs, (unsigned long) sk, NULL,
+			      priv, GFP_KERNEL);
+	if (old_priv) {
+		genl_sk_priv_free(family, priv);
+		if (xa_is_err(old_priv))
+			return ERR_PTR(xa_err(old_priv));
+		/* Race happened, priv for the socket was already inserted. */
+		return old_priv;
+	}
+	return priv;
+}
+
 /**
  * genl_register_family - register a generic netlink family
  * @family: generic netlink family
@@ -659,6 +791,10 @@ int genl_register_family(struct genl_family *family)
 		goto errout_locked;
 	}
 
+	err = genl_sk_privs_alloc(family);
+	if (err)
+		goto errout_locked;
+
 	/*
 	 * Sadly, a few cases need to be special-cased
 	 * due to them having previously abused the API
@@ -679,7 +815,7 @@ int genl_register_family(struct genl_family *family)
 				      start, end + 1, GFP_KERNEL);
 	if (family->id < 0) {
 		err = family->id;
-		goto errout_locked;
+		goto errout_sk_privs_free;
 	}
 
 	err = genl_validate_assign_mc_groups(family);
@@ -698,6 +834,8 @@ int genl_register_family(struct genl_family *family)
 
 errout_remove:
 	idr_remove(&genl_fam_idr, family->id);
+errout_sk_privs_free:
+	genl_sk_privs_free(family);
 errout_locked:
 	genl_unlock_all();
 	return err;
@@ -728,6 +866,9 @@ int genl_unregister_family(const struct genl_family *family)
 	up_write(&cb_lock);
 	wait_event(genl_sk_destructing_waitq,
 		   atomic_read(&genl_sk_destructing_cnt) == 0);
+
+	genl_sk_privs_free(family);
+
 	genl_unlock();
 
 	genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL, 0);
@@ -1688,9 +1829,12 @@ static int genl_bind(struct net *net, int group)
 			continue;
 
 		grp = &family->mcgrps[i];
-		if ((grp->flags & GENL_UNS_ADMIN_PERM) &&
+		if ((grp->flags & GENL_MCAST_CAP_NET_ADMIN) &&
 		    !ns_capable(net->user_ns, CAP_NET_ADMIN))
 			ret = -EPERM;
+		if ((grp->flags & GENL_MCAST_CAP_SYS_ADMIN) &&
+		    !ns_capable(net->user_ns, CAP_SYS_ADMIN))
+			ret = -EPERM;
 
 		break;
 	}
@@ -1705,6 +1849,7 @@ static int __net_init genl_pernet_init(struct net *net)
 		.input		= genl_rcv,
 		.flags		= NL_CFG_F_NONROOT_RECV,
 		.bind		= genl_bind,
+		.release	= genl_release,
 	};
 
 	/* we'll bump the group number right afterwards */
diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c
index 1dac28136e6a..18be13fb9b75 100644
--- a/net/nfc/llcp_core.c
+++ b/net/nfc/llcp_core.c
@@ -145,6 +145,13 @@ static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool device,
 
 static struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local)
 {
+	/* Since using nfc_llcp_local may result in usage of nfc_dev, whenever
+	 * we hold a reference to local, we also need to hold a reference to
+	 * the device to avoid UAF.
+	 */
+	if (!nfc_get_device(local->dev->idx))
+		return NULL;
+
 	kref_get(&local->ref);
 
 	return local;
@@ -177,10 +184,18 @@ static void local_release(struct kref *ref)
 
 int nfc_llcp_local_put(struct nfc_llcp_local *local)
 {
+	struct nfc_dev *dev;
+	int ret;
+
 	if (local == NULL)
 		return 0;
 
-	return kref_put(&local->ref, local_release);
+	dev = local->dev;
+
+	ret = kref_put(&local->ref, local_release);
+	nfc_put_device(dev);
+
+	return ret;
 }
 
 static struct nfc_llcp_sock *nfc_llcp_sock_get(struct nfc_llcp_local *local,
@@ -959,8 +974,17 @@ static void nfc_llcp_recv_connect(struct nfc_llcp_local *local,
 	}
 
 	new_sock = nfc_llcp_sock(new_sk);
-	new_sock->dev = local->dev;
+
 	new_sock->local = nfc_llcp_local_get(local);
+	if (!new_sock->local) {
+		reason = LLCP_DM_REJ;
+		sock_put(&new_sock->sk);
+		release_sock(&sock->sk);
+		sock_put(&sock->sk);
+		goto fail;
+	}
+
+	new_sock->dev = local->dev;
 	new_sock->rw = sock->rw;
 	new_sock->miux = sock->miux;
 	new_sock->nfc_protocol = sock->nfc_protocol;
@@ -1597,7 +1621,16 @@ int nfc_llcp_register_device(struct nfc_dev *ndev)
 	if (local == NULL)
 		return -ENOMEM;
 
-	local->dev = ndev;
+	/* As we are going to initialize local's refcount, we need to get the
+	 * nfc_dev to avoid UAF, otherwise there is no point in continuing.
+	 * See nfc_llcp_local_get().
+	 */
+	local->dev = nfc_get_device(ndev->idx);
+	if (!local->dev) {
+		kfree(local);
+		return -ENODEV;
+	}
+
 	INIT_LIST_HEAD(&local->list);
 	kref_init(&local->ref);
 	mutex_init(&local->sdp_lock);
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 645677f84dba..819157bbb5a2 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -796,6 +796,11 @@ static int llcp_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 	}
 
 	if (sk->sk_type == SOCK_DGRAM) {
+		if (sk->sk_state != LLCP_BOUND) {
+			release_sock(sk);
+			return -ENOTCONN;
+		}
+
 		DECLARE_SOCKADDR(struct sockaddr_nfc_llcp *, addr,
 				 msg->msg_name);
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index a84e00b5904b..c9bbc2686690 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2121,13 +2121,13 @@ static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb,
 static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
 		      struct packet_type *pt, struct net_device *orig_dev)
 {
+	enum skb_drop_reason drop_reason = SKB_CONSUMED;
 	struct sock *sk;
 	struct sockaddr_ll *sll;
 	struct packet_sock *po;
 	u8 *skb_head = skb->data;
 	int skb_len = skb->len;
 	unsigned int snaplen, res;
-	bool is_drop_n_account = false;
 
 	if (skb->pkt_type == PACKET_LOOPBACK)
 		goto drop;
@@ -2217,9 +2217,9 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
 	return 0;
 
 drop_n_acct:
-	is_drop_n_account = true;
 	atomic_inc(&po->tp_drops);
 	atomic_inc(&sk->sk_drops);
+	drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR;
 
 drop_n_restore:
 	if (skb_head != skb->data && skb_shared(skb)) {
@@ -2227,16 +2227,14 @@ drop_n_restore:
 		skb->len = skb_len;
 	}
 drop:
-	if (!is_drop_n_account)
-		consume_skb(skb);
-	else
-		kfree_skb(skb);
+	kfree_skb_reason(skb, drop_reason);
 	return 0;
 }
 
 static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		       struct packet_type *pt, struct net_device *orig_dev)
 {
+	enum skb_drop_reason drop_reason = SKB_CONSUMED;
 	struct sock *sk;
 	struct packet_sock *po;
 	struct sockaddr_ll *sll;
@@ -2250,7 +2248,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	struct sk_buff *copy_skb = NULL;
 	struct timespec64 ts;
 	__u32 ts_status;
-	bool is_drop_n_account = false;
 	unsigned int slot_id = 0;
 	int vnet_hdr_sz = 0;
 
@@ -2498,19 +2495,16 @@ drop_n_restore:
 		skb->len = skb_len;
 	}
 drop:
-	if (!is_drop_n_account)
-		consume_skb(skb);
-	else
-		kfree_skb(skb);
+	kfree_skb_reason(skb, drop_reason);
 	return 0;
 
 drop_n_account:
 	spin_unlock(&sk->sk_receive_queue.lock);
 	atomic_inc(&po->tp_drops);
-	is_drop_n_account = true;
+	drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR;
 
 	sk->sk_data_ready(sk);
-	kfree_skb(copy_skb);
+	kfree_skb_reason(copy_skb, drop_reason);
 	goto drop_n_restore;
 }
 
@@ -4300,7 +4294,7 @@ static void packet_mm_open(struct vm_area_struct *vma)
 	struct sock *sk = sock->sk;
 
 	if (sk)
-		atomic_inc(&pkt_sk(sk)->mapped);
+		atomic_long_inc(&pkt_sk(sk)->mapped);
 }
 
 static void packet_mm_close(struct vm_area_struct *vma)
@@ -4310,7 +4304,7 @@ static void packet_mm_close(struct vm_area_struct *vma)
 	struct sock *sk = sock->sk;
 
 	if (sk)
-		atomic_dec(&pkt_sk(sk)->mapped);
+		atomic_long_dec(&pkt_sk(sk)->mapped);
 }
 
 static const struct vm_operations_struct packet_mmap_ops = {
@@ -4405,7 +4399,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 
 	err = -EBUSY;
 	if (!closing) {
-		if (atomic_read(&po->mapped))
+		if (atomic_long_read(&po->mapped))
 			goto out;
 		if (packet_read_pending(rb))
 			goto out;
@@ -4508,7 +4502,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 
 	err = -EBUSY;
 	mutex_lock(&po->pg_vec_lock);
-	if (closing || atomic_read(&po->mapped) == 0) {
+	if (closing || atomic_long_read(&po->mapped) == 0) {
 		err = 0;
 		spin_lock_bh(&rb_queue->lock);
 		swap(rb->pg_vec, pg_vec);
@@ -4526,9 +4520,9 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		po->prot_hook.func = (po->rx_ring.pg_vec) ?
 						tpacket_rcv : packet_rcv;
 		skb_queue_purge(rb_queue);
-		if (atomic_read(&po->mapped))
-			pr_err("packet_mmap: vma is busy: %d\n",
-			       atomic_read(&po->mapped));
+		if (atomic_long_read(&po->mapped))
+			pr_err("packet_mmap: vma is busy: %ld\n",
+			       atomic_long_read(&po->mapped));
 	}
 	mutex_unlock(&po->pg_vec_lock);
 
@@ -4606,7 +4600,7 @@ static int packet_mmap(struct file *file, struct socket *sock,
 		}
 	}
 
-	atomic_inc(&po->mapped);
+	atomic_long_inc(&po->mapped);
 	vma->vm_ops = &packet_mmap_ops;
 	err = 0;
 
@@ -4787,5 +4781,6 @@ out:
 
 module_init(packet_init);
 module_exit(packet_exit);
+MODULE_DESCRIPTION("Packet socket support (AF_PACKET)");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_NETPROTO(PF_PACKET);
diff --git a/net/packet/diag.c b/net/packet/diag.c
index f6b200cb3c06..9a7980e3309d 100644
--- a/net/packet/diag.c
+++ b/net/packet/diag.c
@@ -262,4 +262,5 @@ static void __exit packet_diag_exit(void)
 module_init(packet_diag_init);
 module_exit(packet_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("PACKET socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 17 /* AF_PACKET */);
diff --git a/net/packet/internal.h b/net/packet/internal.h
index d29c94c45159..d5d70712007a 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -122,7 +122,7 @@ struct packet_sock {
 	__be16			num;
 	struct packet_rollover	*rollover;
 	struct packet_mclist	*mclist;
-	atomic_t		mapped;
+	atomic_long_t		mapped;
 	enum tpacket_versions	tp_version;
 	unsigned int		tp_hdrlen;
 	unsigned int		tp_reserve;
diff --git a/net/psample/psample.c b/net/psample/psample.c
index 81a794e36f53..ddd211a151d0 100644
--- a/net/psample/psample.c
+++ b/net/psample/psample.c
@@ -31,7 +31,8 @@ enum psample_nl_multicast_groups {
 
 static const struct genl_multicast_group psample_nl_mcgrps[] = {
 	[PSAMPLE_NL_MCGRP_CONFIG] = { .name = PSAMPLE_NL_MCGRP_CONFIG_NAME },
-	[PSAMPLE_NL_MCGRP_SAMPLE] = { .name = PSAMPLE_NL_MCGRP_SAMPLE_NAME },
+	[PSAMPLE_NL_MCGRP_SAMPLE] = { .name = PSAMPLE_NL_MCGRP_SAMPLE_NAME,
+				      .flags = GENL_MCAST_CAP_NET_ADMIN, },
 };
 
 static struct genl_family psample_nl_family __ro_after_init;
diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c
index b1db0b519179..abb0c70ffc8b 100644
--- a/net/qrtr/ns.c
+++ b/net/qrtr/ns.c
@@ -512,7 +512,9 @@ static int ctrl_cmd_del_server(struct sockaddr_qrtr *from,
 	if (!node)
 		return -ENOENT;
 
-	return server_del(node, port, true);
+	server_del(node, port, true);
+
+	return 0;
 }
 
 static int ctrl_cmd_new_lookup(struct sockaddr_qrtr *from,
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 53b3535a1e4a..05008ce5c421 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -165,7 +165,7 @@ int rds_tcp_accept_one(struct socket *sock)
 		struct ipv6_pinfo *inet6;
 
 		inet6 = inet6_sk(new_sock->sk);
-		dev_if = inet6->mcast_oif;
+		dev_if = READ_ONCE(inet6->mcast_oif);
 	} else {
 		dev_if = new_sock->sk->sk_bound_dev_if;
 	}
diff --git a/net/rfkill/core.c b/net/rfkill/core.c
index 14cc8fe8584b..c3feb4f49d09 100644
--- a/net/rfkill/core.c
+++ b/net/rfkill/core.c
@@ -1351,11 +1351,11 @@ static long rfkill_fop_ioctl(struct file *file, unsigned int cmd,
 			     unsigned long arg)
 {
 	struct rfkill_data *data = file->private_data;
-	int ret = -ENOSYS;
+	int ret = -ENOTTY;
 	u32 size;
 
 	if (_IOC_TYPE(cmd) != RFKILL_IOC_MAGIC)
-		return -ENOSYS;
+		return -ENOTTY;
 
 	mutex_lock(&data->mtx);
 	switch (_IOC_NR(cmd)) {
diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c
index 5a81505fba9a..4e32d659524e 100644
--- a/net/rfkill/rfkill-gpio.c
+++ b/net/rfkill/rfkill-gpio.c
@@ -126,6 +126,14 @@ static int rfkill_gpio_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
+	ret = gpiod_direction_output(rfkill->reset_gpio, true);
+	if (ret)
+		return ret;
+
+	ret = gpiod_direction_output(rfkill->shutdown_gpio, true);
+	if (ret)
+		return ret;
+
 	rfkill->rfkill_dev = rfkill_alloc(rfkill->name, &pdev->dev,
 					  rfkill->type, &rfkill_gpio_ops,
 					  rfkill);
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 0cc5a4e19900..ef81d019b20f 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -182,21 +182,47 @@ void rose_kill_by_neigh(struct rose_neigh *neigh)
  */
 static void rose_kill_by_device(struct net_device *dev)
 {
-	struct sock *s;
+	struct sock *sk, *array[16];
+	struct rose_sock *rose;
+	bool rescan;
+	int i, cnt;
 
+start:
+	rescan = false;
+	cnt = 0;
 	spin_lock_bh(&rose_list_lock);
-	sk_for_each(s, &rose_list) {
-		struct rose_sock *rose = rose_sk(s);
+	sk_for_each(sk, &rose_list) {
+		rose = rose_sk(sk);
+		if (rose->device == dev) {
+			if (cnt == ARRAY_SIZE(array)) {
+				rescan = true;
+				break;
+			}
+			sock_hold(sk);
+			array[cnt++] = sk;
+		}
+	}
+	spin_unlock_bh(&rose_list_lock);
 
+	for (i = 0; i < cnt; i++) {
+		sk = array[cnt];
+		rose = rose_sk(sk);
+		lock_sock(sk);
+		spin_lock_bh(&rose_list_lock);
 		if (rose->device == dev) {
-			rose_disconnect(s, ENETUNREACH, ROSE_OUT_OF_ORDER, 0);
+			rose_disconnect(sk, ENETUNREACH, ROSE_OUT_OF_ORDER, 0);
 			if (rose->neighbour)
 				rose->neighbour->use--;
 			netdev_put(rose->device, &rose->dev_tracker);
 			rose->device = NULL;
 		}
+		spin_unlock_bh(&rose_list_lock);
+		release_sock(sk);
+		sock_put(sk);
+		cond_resched();
 	}
-	spin_unlock_bh(&rose_list_lock);
+	if (rescan)
+		goto start;
 }
 
 /*
@@ -656,7 +682,10 @@ static int rose_release(struct socket *sock)
 		break;
 	}
 
+	spin_lock_bh(&rose_list_lock);
 	netdev_put(rose->device, &rose->dev_tracker);
+	rose->device = NULL;
+	spin_unlock_bh(&rose_list_lock);
 	sock->sk = NULL;
 	release_sock(sk);
 	sock_put(sk);
@@ -1315,9 +1344,11 @@ static int rose_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	case TIOCINQ: {
 		struct sk_buff *skb;
 		long amount = 0L;
-		/* These two are safe on a single CPU system as only user tasks fiddle here */
+
+		spin_lock_irq(&sk->sk_receive_queue.lock);
 		if ((skb = skb_peek(&sk->sk_receive_queue)) != NULL)
 			amount = skb->len;
+		spin_unlock_irq(&sk->sk_receive_queue.lock);
 		return put_user(amount, (unsigned int __user *) argp);
 	}
 
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index fa8aec78f63d..465bfe5eb061 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -259,15 +259,61 @@ static int rxrpc_listen(struct socket *sock, int backlog)
 }
 
 /**
+ * rxrpc_kernel_lookup_peer - Obtain remote transport endpoint for an address
+ * @sock: The socket through which it will be accessed
+ * @srx: The network address
+ * @gfp: Allocation flags
+ *
+ * Lookup or create a remote transport endpoint record for the specified
+ * address and return it with a ref held.
+ */
+struct rxrpc_peer *rxrpc_kernel_lookup_peer(struct socket *sock,
+					    struct sockaddr_rxrpc *srx, gfp_t gfp)
+{
+	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
+	int ret;
+
+	ret = rxrpc_validate_address(rx, srx, sizeof(*srx));
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	return rxrpc_lookup_peer(rx->local, srx, gfp);
+}
+EXPORT_SYMBOL(rxrpc_kernel_lookup_peer);
+
+/**
+ * rxrpc_kernel_get_peer - Get a reference on a peer
+ * @peer: The peer to get a reference on.
+ *
+ * Get a record for the remote peer in a call.
+ */
+struct rxrpc_peer *rxrpc_kernel_get_peer(struct rxrpc_peer *peer)
+{
+	return peer ? rxrpc_get_peer(peer, rxrpc_peer_get_application) : NULL;
+}
+EXPORT_SYMBOL(rxrpc_kernel_get_peer);
+
+/**
+ * rxrpc_kernel_put_peer - Allow a kernel app to drop a peer reference
+ * @peer: The peer to drop a ref on
+ */
+void rxrpc_kernel_put_peer(struct rxrpc_peer *peer)
+{
+	rxrpc_put_peer(peer, rxrpc_peer_put_application);
+}
+EXPORT_SYMBOL(rxrpc_kernel_put_peer);
+
+/**
  * rxrpc_kernel_begin_call - Allow a kernel service to begin a call
  * @sock: The socket on which to make the call
- * @srx: The address of the peer to contact
+ * @peer: The peer to contact
  * @key: The security context to use (defaults to socket setting)
  * @user_call_ID: The ID to use
  * @tx_total_len: Total length of data to transmit during the call (or -1)
  * @hard_timeout: The maximum lifespan of the call in sec
  * @gfp: The allocation constraints
  * @notify_rx: Where to send notifications instead of socket queue
+ * @service_id: The ID of the service to contact
  * @upgrade: Request service upgrade for call
  * @interruptibility: The call is interruptible, or can be canceled.
  * @debug_id: The debug ID for tracing to be assigned to the call
@@ -280,13 +326,14 @@ static int rxrpc_listen(struct socket *sock, int backlog)
  * supplying @srx and @key.
  */
 struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
-					   struct sockaddr_rxrpc *srx,
+					   struct rxrpc_peer *peer,
 					   struct key *key,
 					   unsigned long user_call_ID,
 					   s64 tx_total_len,
 					   u32 hard_timeout,
 					   gfp_t gfp,
 					   rxrpc_notify_rx_t notify_rx,
+					   u16 service_id,
 					   bool upgrade,
 					   enum rxrpc_interruptibility interruptibility,
 					   unsigned int debug_id)
@@ -295,13 +342,11 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 	struct rxrpc_call_params p;
 	struct rxrpc_call *call;
 	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
-	int ret;
 
 	_enter(",,%x,%lx", key_serial(key), user_call_ID);
 
-	ret = rxrpc_validate_address(rx, srx, sizeof(*srx));
-	if (ret < 0)
-		return ERR_PTR(ret);
+	if (WARN_ON_ONCE(peer->local != rx->local))
+		return ERR_PTR(-EIO);
 
 	lock_sock(&rx->sk);
 
@@ -319,12 +364,13 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 
 	memset(&cp, 0, sizeof(cp));
 	cp.local		= rx->local;
+	cp.peer			= peer;
 	cp.key			= key;
 	cp.security_level	= rx->min_sec_level;
 	cp.exclusive		= false;
 	cp.upgrade		= upgrade;
-	cp.service_id		= srx->srx_service;
-	call = rxrpc_new_client_call(rx, &cp, srx, &p, gfp, debug_id);
+	cp.service_id		= service_id;
+	call = rxrpc_new_client_call(rx, &cp, &p, gfp, debug_id);
 	/* The socket has been unlocked. */
 	if (!IS_ERR(call)) {
 		call->notify_rx = notify_rx;
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index e8e14c6f904d..2f8b39a614c3 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -68,6 +68,7 @@ struct rxrpc_net {
 	atomic_t		nr_calls;	/* Count of allocated calls */
 
 	atomic_t		nr_conns;
+	struct list_head	bundle_proc_list; /* List of bundles for proc */
 	struct list_head	conn_proc_list;	/* List of conns in this namespace for proc */
 	struct list_head	service_conns;	/* Service conns in this namespace */
 	rwlock_t		conn_lock;	/* Lock for ->conn_proc_list, ->service_conns */
@@ -364,6 +365,7 @@ struct rxrpc_conn_proto {
 
 struct rxrpc_conn_parameters {
 	struct rxrpc_local	*local;		/* Representation of local endpoint */
+	struct rxrpc_peer	*peer;		/* Representation of remote endpoint */
 	struct key		*key;		/* Security details */
 	bool			exclusive;	/* T if conn is exclusive */
 	bool			upgrade;	/* T if service ID can be upgraded */
@@ -431,6 +433,7 @@ struct rxrpc_bundle {
 	struct rxrpc_local	*local;		/* Representation of local endpoint */
 	struct rxrpc_peer	*peer;		/* Remote endpoint */
 	struct key		*key;		/* Security details */
+	struct list_head	proc_link;	/* Link in net->bundle_proc_list */
 	const struct rxrpc_security *security;	/* applied security module */
 	refcount_t		ref;
 	atomic_t		active;		/* Number of active users */
@@ -444,6 +447,7 @@ struct rxrpc_bundle {
 	struct rb_node		local_node;	/* Node in local->client_conns */
 	struct list_head	waiting_calls;	/* Calls waiting for channels */
 	unsigned long		avail_chans;	/* Mask of available channels */
+	unsigned int		conn_ids[4];	/* Connection IDs. */
 	struct rxrpc_connection	*conns[4];	/* The connections in the bundle (max 4) */
 };
 
@@ -867,7 +871,6 @@ struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *, unsigned long
 struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *, gfp_t, unsigned int);
 struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *,
 					 struct rxrpc_conn_parameters *,
-					 struct sockaddr_rxrpc *,
 					 struct rxrpc_call_params *, gfp_t,
 					 unsigned int);
 void rxrpc_start_call_timer(struct rxrpc_call *call);
@@ -1167,6 +1170,7 @@ void rxrpc_put_peer(struct rxrpc_peer *, enum rxrpc_peer_trace);
  */
 extern const struct seq_operations rxrpc_call_seq_ops;
 extern const struct seq_operations rxrpc_connection_seq_ops;
+extern const struct seq_operations rxrpc_bundle_seq_ops;
 extern const struct seq_operations rxrpc_peer_seq_ops;
 extern const struct seq_operations rxrpc_local_seq_ops;
 
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 773eecd1e979..0943e54370ba 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -193,7 +193,6 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp,
  * Allocate a new client call.
  */
 static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx,
-						  struct sockaddr_rxrpc *srx,
 						  struct rxrpc_conn_parameters *cp,
 						  struct rxrpc_call_params *p,
 						  gfp_t gfp,
@@ -211,10 +210,12 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx,
 	now = ktime_get_real();
 	call->acks_latest_ts	= now;
 	call->cong_tstamp	= now;
-	call->dest_srx		= *srx;
+	call->dest_srx		= cp->peer->srx;
+	call->dest_srx.srx_service = cp->service_id;
 	call->interruptibility	= p->interruptibility;
 	call->tx_total_len	= p->tx_total_len;
 	call->key		= key_get(cp->key);
+	call->peer		= rxrpc_get_peer(cp->peer, rxrpc_peer_get_call);
 	call->local		= rxrpc_get_local(cp->local, rxrpc_local_get_call);
 	call->security_level	= cp->security_level;
 	if (p->kernel)
@@ -306,10 +307,6 @@ static int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp)
 
 	_enter("{%d,%lx},", call->debug_id, call->user_call_ID);
 
-	call->peer = rxrpc_lookup_peer(local, &call->dest_srx, gfp);
-	if (!call->peer)
-		goto error;
-
 	ret = rxrpc_look_up_bundle(call, gfp);
 	if (ret < 0)
 		goto error;
@@ -334,7 +331,6 @@ error:
  */
 struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 					 struct rxrpc_conn_parameters *cp,
-					 struct sockaddr_rxrpc *srx,
 					 struct rxrpc_call_params *p,
 					 gfp_t gfp,
 					 unsigned int debug_id)
@@ -349,13 +345,18 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 
 	_enter("%p,%lx", rx, p->user_call_ID);
 
+	if (WARN_ON_ONCE(!cp->peer)) {
+		release_sock(&rx->sk);
+		return ERR_PTR(-EIO);
+	}
+
 	limiter = rxrpc_get_call_slot(p, gfp);
 	if (!limiter) {
 		release_sock(&rx->sk);
 		return ERR_PTR(-ERESTARTSYS);
 	}
 
-	call = rxrpc_alloc_client_call(rx, srx, cp, p, gfp, debug_id);
+	call = rxrpc_alloc_client_call(rx, cp, p, gfp, debug_id);
 	if (IS_ERR(call)) {
 		release_sock(&rx->sk);
 		up(limiter);
@@ -545,8 +546,8 @@ void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace why)
  */
 static void rxrpc_cleanup_ring(struct rxrpc_call *call)
 {
-	skb_queue_purge(&call->recvmsg_queue);
-	skb_queue_purge(&call->rx_oos_queue);
+	rxrpc_purge_queue(&call->recvmsg_queue);
+	rxrpc_purge_queue(&call->rx_oos_queue);
 }
 
 /*
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 981ca5b98bcb..3b9b267a4431 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -73,6 +73,7 @@ static void rxrpc_destroy_client_conn_ids(struct rxrpc_local *local)
 static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_call *call,
 					       gfp_t gfp)
 {
+	static atomic_t rxrpc_bundle_id;
 	struct rxrpc_bundle *bundle;
 
 	bundle = kzalloc(sizeof(*bundle), gfp);
@@ -85,10 +86,15 @@ static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_call *call,
 		bundle->upgrade		= test_bit(RXRPC_CALL_UPGRADE, &call->flags);
 		bundle->service_id	= call->dest_srx.srx_service;
 		bundle->security_level	= call->security_level;
+		bundle->debug_id	= atomic_inc_return(&rxrpc_bundle_id);
 		refcount_set(&bundle->ref, 1);
 		atomic_set(&bundle->active, 1);
 		INIT_LIST_HEAD(&bundle->waiting_calls);
 		trace_rxrpc_bundle(bundle->debug_id, 1, rxrpc_bundle_new);
+
+		write_lock(&bundle->local->rxnet->conn_lock);
+		list_add_tail(&bundle->proc_link, &bundle->local->rxnet->bundle_proc_list);
+		write_unlock(&bundle->local->rxnet->conn_lock);
 	}
 	return bundle;
 }
@@ -105,7 +111,11 @@ struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *bundle,
 
 static void rxrpc_free_bundle(struct rxrpc_bundle *bundle)
 {
-	trace_rxrpc_bundle(bundle->debug_id, 1, rxrpc_bundle_free);
+	trace_rxrpc_bundle(bundle->debug_id, refcount_read(&bundle->ref),
+			   rxrpc_bundle_free);
+	write_lock(&bundle->local->rxnet->conn_lock);
+	list_del(&bundle->proc_link);
+	write_unlock(&bundle->local->rxnet->conn_lock);
 	rxrpc_put_peer(bundle->peer, rxrpc_peer_put_bundle);
 	key_put(bundle->key);
 	kfree(bundle);
@@ -239,7 +249,6 @@ dont_reuse:
  */
 int rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp)
 {
-	static atomic_t rxrpc_bundle_id;
 	struct rxrpc_bundle *bundle, *candidate;
 	struct rxrpc_local *local = call->local;
 	struct rb_node *p, **pp, *parent;
@@ -306,7 +315,6 @@ int rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp)
 	}
 
 	_debug("new bundle");
-	candidate->debug_id = atomic_inc_return(&rxrpc_bundle_id);
 	rb_link_node(&candidate->local_node, parent, pp);
 	rb_insert_color(&candidate->local_node, &local->client_bundles);
 	call->bundle = rxrpc_get_bundle(candidate, rxrpc_bundle_get_client_call);
@@ -337,6 +345,7 @@ static bool rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle,
 	old = bundle->conns[slot];
 	if (old) {
 		bundle->conns[slot] = NULL;
+		bundle->conn_ids[slot] = 0;
 		trace_rxrpc_client(old, -1, rxrpc_client_replace);
 		rxrpc_put_connection(old, rxrpc_conn_put_noreuse);
 	}
@@ -350,6 +359,7 @@ static bool rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle,
 	rxrpc_activate_bundle(bundle);
 	conn->bundle_shift = shift;
 	bundle->conns[slot] = conn;
+	bundle->conn_ids[slot] = conn->debug_id;
 	for (i = 0; i < RXRPC_MAXCALLS; i++)
 		set_bit(shift + i, &bundle->avail_chans);
 	return true;
@@ -670,6 +680,7 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn)
 	if (bundle->conns[bindex] == conn) {
 		_debug("clear slot %u", bindex);
 		bundle->conns[bindex] = NULL;
+		bundle->conn_ids[bindex] = 0;
 		for (i = 0; i < RXRPC_MAXCALLS; i++)
 			clear_bit(conn->bundle_shift + i, &bundle->avail_chans);
 		rxrpc_put_client_connection_id(bundle->local, conn);
diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c
index 89ac05a711a4..39c908a3ca6e 100644
--- a/net/rxrpc/conn_service.c
+++ b/net/rxrpc/conn_service.c
@@ -25,7 +25,7 @@ struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *peer,
 	struct rxrpc_conn_proto k;
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	struct rb_node *p;
-	unsigned int seq = 0;
+	unsigned int seq = 1;
 
 	k.epoch	= sp->hdr.epoch;
 	k.cid	= sp->hdr.cid & RXRPC_CIDMASK;
@@ -35,6 +35,7 @@ struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *peer,
 		 * under just the RCU read lock, so we have to check for
 		 * changes.
 		 */
+		seq++; /* 2 on the 1st/lockless path, otherwise odd */
 		read_seqbegin_or_lock(&peer->service_conn_lock, &seq);
 
 		p = rcu_dereference_raw(peer->service_conns.rb_node);
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 030d64f282f3..92495e73b869 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -643,12 +643,8 @@ static void rxrpc_complete_rtt_probe(struct rxrpc_call *call,
 			clear_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail);
 			smp_mb(); /* Read data before setting avail bit */
 			set_bit(i, &call->rtt_avail);
-			if (type != rxrpc_rtt_rx_cancel)
-				rxrpc_peer_add_rtt(call, type, i, acked_serial, ack_serial,
-						   sent_at, resp_time);
-			else
-				trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_cancel, i,
-						   orig_serial, acked_serial, 0, 0);
+			rxrpc_peer_add_rtt(call, type, i, acked_serial, ack_serial,
+					   sent_at, resp_time);
 			matched = true;
 		}
 
@@ -801,28 +797,21 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 			   summary.ack_reason, nr_acks);
 	rxrpc_inc_stat(call->rxnet, stat_rx_acks[ack.reason]);
 
-	switch (ack.reason) {
-	case RXRPC_ACK_PING_RESPONSE:
-		rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial,
-					 rxrpc_rtt_rx_ping_response);
-		break;
-	case RXRPC_ACK_REQUESTED:
-		rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial,
-					 rxrpc_rtt_rx_requested_ack);
-		break;
-	default:
-		if (acked_serial != 0)
+	if (acked_serial != 0) {
+		switch (ack.reason) {
+		case RXRPC_ACK_PING_RESPONSE:
 			rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial,
-						 rxrpc_rtt_rx_cancel);
-		break;
-	}
-
-	if (ack.reason == RXRPC_ACK_PING) {
-		rxrpc_send_ACK(call, RXRPC_ACK_PING_RESPONSE, ack_serial,
-			       rxrpc_propose_ack_respond_to_ping);
-	} else if (sp->hdr.flags & RXRPC_REQUEST_ACK) {
-		rxrpc_send_ACK(call, RXRPC_ACK_REQUESTED, ack_serial,
-			       rxrpc_propose_ack_respond_to_ack);
+						 rxrpc_rtt_rx_ping_response);
+			break;
+		case RXRPC_ACK_REQUESTED:
+			rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial,
+						 rxrpc_rtt_rx_requested_ack);
+			break;
+		default:
+			rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial,
+						 rxrpc_rtt_rx_other_ack);
+			break;
+		}
 	}
 
 	/* If we get an EXCEEDS_WINDOW ACK from the server, it probably
@@ -835,7 +824,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	    rxrpc_is_client_call(call)) {
 		rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED,
 					  0, -ENETRESET);
-		return;
+		goto send_response;
 	}
 
 	/* If we get an OUT_OF_SEQUENCE ACK from the server, that can also
@@ -849,7 +838,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	    rxrpc_is_client_call(call)) {
 		rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED,
 					  0, -ENETRESET);
-		return;
+		goto send_response;
 	}
 
 	/* Discard any out-of-order or duplicate ACKs (outside lock). */
@@ -857,7 +846,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 		trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial,
 					   first_soft_ack, call->acks_first_seq,
 					   prev_pkt, call->acks_prev_seq);
-		return;
+		goto send_response;
 	}
 
 	info.rxMTU = 0;
@@ -897,7 +886,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	case RXRPC_CALL_SERVER_AWAIT_ACK:
 		break;
 	default:
-		return;
+		goto send_response;
 	}
 
 	if (before(hard_ack, call->acks_hard_ack) ||
@@ -909,7 +898,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	if (after(hard_ack, call->acks_hard_ack)) {
 		if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) {
 			rxrpc_end_tx_phase(call, false, rxrpc_eproto_unexpected_ack);
-			return;
+			goto send_response;
 		}
 	}
 
@@ -927,6 +916,14 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 				   rxrpc_propose_ack_ping_for_lost_reply);
 
 	rxrpc_congestion_management(call, skb, &summary, acked_serial);
+
+send_response:
+	if (ack.reason == RXRPC_ACK_PING)
+		rxrpc_send_ACK(call, RXRPC_ACK_PING_RESPONSE, ack_serial,
+			       rxrpc_propose_ack_respond_to_ping);
+	else if (sp->hdr.flags & RXRPC_REQUEST_ACK)
+		rxrpc_send_ACK(call, RXRPC_ACK_REQUESTED, ack_serial,
+			       rxrpc_propose_ack_respond_to_ack);
 }
 
 /*
diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c
index a0319c040c25..a4c135d0fbcc 100644
--- a/net/rxrpc/net_ns.c
+++ b/net/rxrpc/net_ns.c
@@ -45,6 +45,7 @@ static __net_init int rxrpc_init_net(struct net *net)
 	atomic_set(&rxnet->nr_calls, 1);
 
 	atomic_set(&rxnet->nr_conns, 1);
+	INIT_LIST_HEAD(&rxnet->bundle_proc_list);
 	INIT_LIST_HEAD(&rxnet->conn_proc_list);
 	INIT_LIST_HEAD(&rxnet->service_conns);
 	rwlock_init(&rxnet->conn_lock);
@@ -78,6 +79,9 @@ static __net_init int rxrpc_init_net(struct net *net)
 	proc_create_net("conns", 0444, rxnet->proc_net,
 			&rxrpc_connection_seq_ops,
 			sizeof(struct seq_net_private));
+	proc_create_net("bundles", 0444, rxnet->proc_net,
+			&rxrpc_bundle_seq_ops,
+			sizeof(struct seq_net_private));
 	proc_create_net("peers", 0444, rxnet->proc_net,
 			&rxrpc_peer_seq_ops,
 			sizeof(struct seq_net_private));
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 8d7a715a0bb1..49dcda67a0d5 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -22,6 +22,8 @@
 #include <net/ip6_route.h>
 #include "ar-internal.h"
 
+static const struct sockaddr_rxrpc rxrpc_null_addr;
+
 /*
  * Hash a peer key.
  */
@@ -457,39 +459,53 @@ void rxrpc_destroy_all_peers(struct rxrpc_net *rxnet)
 }
 
 /**
- * rxrpc_kernel_get_peer - Get the peer address of a call
+ * rxrpc_kernel_get_call_peer - Get the peer address of a call
  * @sock: The socket on which the call is in progress.
  * @call: The call to query
- * @_srx: Where to place the result
  *
- * Get the address of the remote peer in a call.
+ * Get a record for the remote peer in a call.
  */
-void rxrpc_kernel_get_peer(struct socket *sock, struct rxrpc_call *call,
-			   struct sockaddr_rxrpc *_srx)
+struct rxrpc_peer *rxrpc_kernel_get_call_peer(struct socket *sock, struct rxrpc_call *call)
 {
-	*_srx = call->peer->srx;
+	return call->peer;
 }
-EXPORT_SYMBOL(rxrpc_kernel_get_peer);
+EXPORT_SYMBOL(rxrpc_kernel_get_call_peer);
 
 /**
  * rxrpc_kernel_get_srtt - Get a call's peer smoothed RTT
- * @sock: The socket on which the call is in progress.
- * @call: The call to query
- * @_srtt: Where to store the SRTT value.
+ * @peer: The peer to query
  *
- * Get the call's peer smoothed RTT in uS.
+ * Get the call's peer smoothed RTT in uS or UINT_MAX if we have no samples.
  */
-bool rxrpc_kernel_get_srtt(struct socket *sock, struct rxrpc_call *call,
-			   u32 *_srtt)
+unsigned int rxrpc_kernel_get_srtt(const struct rxrpc_peer *peer)
 {
-	struct rxrpc_peer *peer = call->peer;
+	return peer->rtt_count > 0 ? peer->srtt_us >> 3 : UINT_MAX;
+}
+EXPORT_SYMBOL(rxrpc_kernel_get_srtt);
 
-	if (peer->rtt_count == 0) {
-		*_srtt = 1000000; /* 1S */
-		return false;
-	}
+/**
+ * rxrpc_kernel_remote_srx - Get the address of a peer
+ * @peer: The peer to query
+ *
+ * Get a pointer to the address from a peer record.  The caller is responsible
+ * for making sure that the address is not deallocated.
+ */
+const struct sockaddr_rxrpc *rxrpc_kernel_remote_srx(const struct rxrpc_peer *peer)
+{
+	return peer ? &peer->srx : &rxrpc_null_addr;
+}
+EXPORT_SYMBOL(rxrpc_kernel_remote_srx);
 
-	*_srtt = call->peer->srtt_us >> 3;
-	return true;
+/**
+ * rxrpc_kernel_remote_addr - Get the peer transport address of a call
+ * @peer: The peer to query
+ *
+ * Get a pointer to the transport address from a peer record.  The caller is
+ * responsible for making sure that the address is not deallocated.
+ */
+const struct sockaddr *rxrpc_kernel_remote_addr(const struct rxrpc_peer *peer)
+{
+	return (const struct sockaddr *)
+		(peer ? &peer->srx.transport : &rxrpc_null_addr.transport);
 }
-EXPORT_SYMBOL(rxrpc_kernel_get_srtt);
+EXPORT_SYMBOL(rxrpc_kernel_remote_addr);
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index 682636d3b060..6c86cbb98d1d 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -199,6 +199,82 @@ const struct seq_operations rxrpc_connection_seq_ops = {
 };
 
 /*
+ * generate a list of extant virtual bundles in /proc/net/rxrpc/bundles
+ */
+static void *rxrpc_bundle_seq_start(struct seq_file *seq, loff_t *_pos)
+	__acquires(rxnet->conn_lock)
+{
+	struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
+
+	read_lock(&rxnet->conn_lock);
+	return seq_list_start_head(&rxnet->bundle_proc_list, *_pos);
+}
+
+static void *rxrpc_bundle_seq_next(struct seq_file *seq, void *v,
+				       loff_t *pos)
+{
+	struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
+
+	return seq_list_next(v, &rxnet->bundle_proc_list, pos);
+}
+
+static void rxrpc_bundle_seq_stop(struct seq_file *seq, void *v)
+	__releases(rxnet->conn_lock)
+{
+	struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
+
+	read_unlock(&rxnet->conn_lock);
+}
+
+static int rxrpc_bundle_seq_show(struct seq_file *seq, void *v)
+{
+	struct rxrpc_bundle *bundle;
+	struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
+	char lbuff[50], rbuff[50];
+
+	if (v == &rxnet->bundle_proc_list) {
+		seq_puts(seq,
+			 "Proto Local                                          "
+			 " Remote                                         "
+			 " SvID Ref Act Flg Key      |"
+			 " Bundle   Conn_0   Conn_1   Conn_2   Conn_3\n"
+			 );
+		return 0;
+	}
+
+	bundle = list_entry(v, struct rxrpc_bundle, proc_link);
+
+	sprintf(lbuff, "%pISpc", &bundle->local->srx.transport);
+	sprintf(rbuff, "%pISpc", &bundle->peer->srx.transport);
+	seq_printf(seq,
+		   "UDP   %-47.47s %-47.47s %4x %3u %3d"
+		   " %c%c%c %08x | %08x %08x %08x %08x %08x\n",
+		   lbuff,
+		   rbuff,
+		   bundle->service_id,
+		   refcount_read(&bundle->ref),
+		   atomic_read(&bundle->active),
+		   bundle->try_upgrade ? 'U' : '-',
+		   bundle->exclusive ? 'e' : '-',
+		   bundle->upgrade ? 'u' : '-',
+		   key_serial(bundle->key),
+		   bundle->debug_id,
+		   bundle->conn_ids[0],
+		   bundle->conn_ids[1],
+		   bundle->conn_ids[2],
+		   bundle->conn_ids[3]);
+
+	return 0;
+}
+
+const struct seq_operations rxrpc_bundle_seq_ops = {
+	.start  = rxrpc_bundle_seq_start,
+	.next   = rxrpc_bundle_seq_next,
+	.stop   = rxrpc_bundle_seq_stop,
+	.show   = rxrpc_bundle_seq_show,
+};
+
+/*
  * generate a list of extant virtual peers in /proc/net/rxrpc/peers
  */
 static int rxrpc_peer_seq_show(struct seq_file *seq, void *v)
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 8e0b94714e84..5677d5690a02 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -572,6 +572,7 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
 	__acquires(&call->user_mutex)
 {
 	struct rxrpc_conn_parameters cp;
+	struct rxrpc_peer *peer;
 	struct rxrpc_call *call;
 	struct key *key;
 
@@ -584,21 +585,29 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
 		return ERR_PTR(-EDESTADDRREQ);
 	}
 
+	peer = rxrpc_lookup_peer(rx->local, srx, GFP_KERNEL);
+	if (!peer) {
+		release_sock(&rx->sk);
+		return ERR_PTR(-ENOMEM);
+	}
+
 	key = rx->key;
 	if (key && !rx->key->payload.data[0])
 		key = NULL;
 
 	memset(&cp, 0, sizeof(cp));
 	cp.local		= rx->local;
+	cp.peer			= peer;
 	cp.key			= rx->key;
 	cp.security_level	= rx->min_sec_level;
 	cp.exclusive		= rx->exclusive | p->exclusive;
 	cp.upgrade		= p->upgrade;
 	cp.service_id		= srx->srx_service;
-	call = rxrpc_new_client_call(rx, &cp, srx, &p->call, GFP_KERNEL,
+	call = rxrpc_new_client_call(rx, &cp, &p->call, GFP_KERNEL,
 				     atomic_inc_return(&rxrpc_debug_id));
 	/* The socket is now unlocked */
 
+	rxrpc_put_peer(peer, rxrpc_peer_put_application);
 	_leave(" = %p\n", call);
 	return call;
 }
diff --git a/net/sched/Makefile b/net/sched/Makefile
index b5fd49641d91..82c3f78ca486 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -13,7 +13,6 @@ obj-$(CONFIG_NET_ACT_POLICE)	+= act_police.o
 obj-$(CONFIG_NET_ACT_GACT)	+= act_gact.o
 obj-$(CONFIG_NET_ACT_MIRRED)	+= act_mirred.o
 obj-$(CONFIG_NET_ACT_SAMPLE)	+= act_sample.o
-obj-$(CONFIG_NET_ACT_IPT)	+= act_ipt.o
 obj-$(CONFIG_NET_ACT_NAT)	+= act_nat.o
 obj-$(CONFIG_NET_ACT_PEDIT)	+= act_pedit.o
 obj-$(CONFIG_NET_ACT_SIMP)	+= act_simple.o
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index c39252d61ebb..3e30d7260493 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -816,6 +816,9 @@ EXPORT_SYMBOL(tcf_idr_cleanup);
  * its reference and bind counters, and return 1. Otherwise insert temporary
  * error pointer (to prevent concurrent users from inserting actions with same
  * index) and return 0.
+ *
+ * May return -EAGAIN for binding actions in case of a parallel add/delete on
+ * the requested index.
  */
 
 int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
@@ -824,43 +827,61 @@ int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
 	struct tcf_idrinfo *idrinfo = tn->idrinfo;
 	struct tc_action *p;
 	int ret;
+	u32 max;
 
-again:
-	mutex_lock(&idrinfo->lock);
 	if (*index) {
+again:
+		rcu_read_lock();
 		p = idr_find(&idrinfo->action_idr, *index);
+
 		if (IS_ERR(p)) {
 			/* This means that another process allocated
 			 * index but did not assign the pointer yet.
 			 */
-			mutex_unlock(&idrinfo->lock);
+			rcu_read_unlock();
 			goto again;
 		}
 
-		if (p) {
-			refcount_inc(&p->tcfa_refcnt);
-			if (bind)
-				atomic_inc(&p->tcfa_bindcnt);
-			*a = p;
-			ret = 1;
-		} else {
-			*a = NULL;
-			ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index,
-					    *index, GFP_KERNEL);
-			if (!ret)
-				idr_replace(&idrinfo->action_idr,
-					    ERR_PTR(-EBUSY), *index);
+		if (!p) {
+			/* Empty slot, try to allocate it */
+			max = *index;
+			rcu_read_unlock();
+			goto new;
+		}
+
+		if (!refcount_inc_not_zero(&p->tcfa_refcnt)) {
+			/* Action was deleted in parallel */
+			rcu_read_unlock();
+			return -EAGAIN;
 		}
+
+		if (bind)
+			atomic_inc(&p->tcfa_bindcnt);
+		*a = p;
+
+		rcu_read_unlock();
+
+		return 1;
 	} else {
+		/* Find a slot */
 		*index = 1;
-		*a = NULL;
-		ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index,
-				    UINT_MAX, GFP_KERNEL);
-		if (!ret)
-			idr_replace(&idrinfo->action_idr, ERR_PTR(-EBUSY),
-				    *index);
+		max = UINT_MAX;
 	}
+
+new:
+	*a = NULL;
+
+	mutex_lock(&idrinfo->lock);
+	ret = idr_alloc_u32(&idrinfo->action_idr, ERR_PTR(-EBUSY), index, max,
+			    GFP_KERNEL);
 	mutex_unlock(&idrinfo->lock);
+
+	/* N binds raced for action allocation,
+	 * retry for all the ones that failed.
+	 */
+	if (ret == -ENOSPC && *index == max)
+		ret = -EAGAIN;
+
 	return ret;
 }
 EXPORT_SYMBOL(tcf_idr_check_alloc);
@@ -1098,7 +1119,8 @@ repeat:
 			}
 		} else if (TC_ACT_EXT_CMP(ret, TC_ACT_GOTO_CHAIN)) {
 			if (unlikely(!rcu_access_pointer(a->goto_chain))) {
-				tcf_set_drop_reason(res, SKB_DROP_REASON_TC_ERROR);
+				tcf_set_drop_reason(skb,
+						    SKB_DROP_REASON_TC_CHAIN_NOTFOUND);
 				return TC_ACT_SHOT;
 			}
 			tcf_action_goto_chain_exec(a, res);
@@ -1118,8 +1140,7 @@ int tcf_action_destroy(struct tc_action *actions[], int bind)
 	struct tc_action *a;
 	int ret = 0, i;
 
-	for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) {
-		a = actions[i];
+	tcf_act_for_each_action(i, a, actions) {
 		actions[i] = NULL;
 		ops = a->ops;
 		ret = __tcf_idr_release(a, bind, true);
@@ -1136,18 +1157,29 @@ static int tcf_action_put(struct tc_action *p)
 	return __tcf_action_put(p, false);
 }
 
-/* Put all actions in this array, skip those NULL's. */
 static void tcf_action_put_many(struct tc_action *actions[])
 {
+	struct tc_action *a;
+	int i;
+
+	tcf_act_for_each_action(i, a, actions) {
+		const struct tc_action_ops *ops = a->ops;
+		if (tcf_action_put(a))
+			module_put(ops->owner);
+	}
+}
+
+static void tca_put_bound_many(struct tc_action *actions[], int init_res[])
+{
+	struct tc_action *a;
 	int i;
 
-	for (i = 0; i < TCA_ACT_MAX_PRIO; i++) {
-		struct tc_action *a = actions[i];
-		const struct tc_action_ops *ops;
+	tcf_act_for_each_action(i, a, actions) {
+		const struct tc_action_ops *ops = a->ops;
 
-		if (!a)
+		if (init_res[i] == ACT_P_CREATED)
 			continue;
-		ops = a->ops;
+
 		if (tcf_action_put(a))
 			module_put(ops->owner);
 	}
@@ -1211,8 +1243,7 @@ int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[],
 	int err = -EINVAL, i;
 	struct nlattr *nest;
 
-	for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) {
-		a = actions[i];
+	tcf_act_for_each_action(i, a, actions) {
 		nest = nla_nest_start_noflag(skb, i + 1);
 		if (nest == NULL)
 			goto nla_put_failure;
@@ -1274,30 +1305,29 @@ static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = {
 	[TCA_ACT_HW_STATS]	= NLA_POLICY_BITFIELD32(TCA_ACT_HW_STATS_ANY),
 };
 
-void tcf_idr_insert_many(struct tc_action *actions[])
+void tcf_idr_insert_many(struct tc_action *actions[], int init_res[])
 {
+	struct tc_action *a;
 	int i;
 
-	for (i = 0; i < TCA_ACT_MAX_PRIO; i++) {
-		struct tc_action *a = actions[i];
+	tcf_act_for_each_action(i, a, actions) {
 		struct tcf_idrinfo *idrinfo;
 
-		if (!a)
+		if (init_res[i] == ACT_P_BOUND)
 			continue;
+
 		idrinfo = a->idrinfo;
 		mutex_lock(&idrinfo->lock);
-		/* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc if
-		 * it is just created, otherwise this is just a nop.
-		 */
+		/* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */
 		idr_replace(&idrinfo->action_idr, a, a->tcfa_index);
 		mutex_unlock(&idrinfo->lock);
 	}
 }
 
-struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, bool police,
-					 bool rtnl_held,
+struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, u32 flags,
 					 struct netlink_ext_ack *extack)
 {
+	bool police = flags & TCA_ACT_FLAGS_POLICE;
 	struct nlattr *tb[TCA_ACT_MAX + 1];
 	struct tc_action_ops *a_o;
 	char act_name[IFNAMSIZ];
@@ -1329,6 +1359,8 @@ struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, bool police,
 	a_o = tc_lookup_action_n(act_name);
 	if (a_o == NULL) {
 #ifdef CONFIG_MODULES
+		bool rtnl_held = !(flags & TCA_ACT_FLAGS_NO_RTNL);
+
 		if (rtnl_held)
 			rtnl_unlock();
 		request_module("act_%s", act_name);
@@ -1445,9 +1477,7 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 	for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
 		struct tc_action_ops *a_o;
 
-		a_o = tc_action_load_ops(tb[i], flags & TCA_ACT_FLAGS_POLICE,
-					 !(flags & TCA_ACT_FLAGS_NO_RTNL),
-					 extack);
+		a_o = tc_action_load_ops(tb[i], flags, extack);
 		if (IS_ERR(a_o)) {
 			err = PTR_ERR(a_o);
 			goto err_mod;
@@ -1488,7 +1518,7 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 	/* We have to commit them all together, because if any error happened in
 	 * between, we could not handle the failure gracefully.
 	 */
-	tcf_idr_insert_many(actions);
+	tcf_idr_insert_many(actions, init_res);
 
 	*attr_size = tcf_action_full_attrs_size(sz);
 	err = i - 1;
@@ -1497,10 +1527,8 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 err:
 	tcf_action_destroy(actions, flags & TCA_ACT_FLAGS_BIND);
 err_mod:
-	for (i = 0; i < TCA_ACT_MAX_PRIO; i++) {
-		if (ops[i])
-			module_put(ops[i]->owner);
-	}
+	for (i = 0; i < TCA_ACT_MAX_PRIO && ops[i]; i++)
+		module_put(ops[i]->owner);
 	return err;
 }
 
@@ -1753,10 +1781,10 @@ err_out:
 
 static int tcf_action_delete(struct net *net, struct tc_action *actions[])
 {
+	struct tc_action *a;
 	int i;
 
-	for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) {
-		struct tc_action *a = actions[i];
+	tcf_act_for_each_action(i, a, actions) {
 		const struct tc_action_ops *ops = a->ops;
 		/* Actions can be deleted concurrently so we must save their
 		 * type and id to search again after reference is released.
@@ -1768,7 +1796,7 @@ static int tcf_action_delete(struct net *net, struct tc_action *actions[])
 		if (tcf_action_put(a)) {
 			/* last reference, action was deleted concurrently */
 			module_put(ops->owner);
-		} else  {
+		} else {
 			int ret;
 
 			/* now do the delete */
@@ -1780,31 +1808,45 @@ static int tcf_action_delete(struct net *net, struct tc_action *actions[])
 	return 0;
 }
 
-static int
-tcf_reoffload_del_notify(struct net *net, struct tc_action *action)
+static struct sk_buff *tcf_reoffload_del_notify_msg(struct net *net,
+						    struct tc_action *action)
 {
 	size_t attr_size = tcf_action_fill_size(action);
 	struct tc_action *actions[TCA_ACT_MAX_PRIO] = {
 		[0] = action,
 	};
-	const struct tc_action_ops *ops = action->ops;
 	struct sk_buff *skb;
-	int ret;
 
-	skb = alloc_skb(attr_size <= NLMSG_GOODSIZE ? NLMSG_GOODSIZE : attr_size,
-			GFP_KERNEL);
+	skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL);
 	if (!skb)
-		return -ENOBUFS;
+		return ERR_PTR(-ENOBUFS);
 
 	if (tca_get_fill(skb, actions, 0, 0, 0, RTM_DELACTION, 0, 1, NULL) <= 0) {
 		kfree_skb(skb);
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
+	}
+
+	return skb;
+}
+
+static int tcf_reoffload_del_notify(struct net *net, struct tc_action *action)
+{
+	const struct tc_action_ops *ops = action->ops;
+	struct sk_buff *skb;
+	int ret;
+
+	if (!rtnl_notify_needed(net, 0, RTNLGRP_TC)) {
+		skb = NULL;
+	} else {
+		skb = tcf_reoffload_del_notify_msg(net, action);
+		if (IS_ERR(skb))
+			return PTR_ERR(skb);
 	}
 
 	ret = tcf_idr_release_unsafe(action);
 	if (ret == ACT_P_DELETED) {
 		module_put(ops->owner);
-		ret = rtnetlink_send(skb, net, 0, RTNLGRP_TC, 0);
+		ret = rtnetlink_maybe_send(skb, net, 0, RTNLGRP_TC, 0);
 	} else {
 		kfree_skb(skb);
 	}
@@ -1870,23 +1912,41 @@ int tcf_action_reoffload_cb(flow_indr_block_bind_cb_t *cb,
 	return 0;
 }
 
-static int
-tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[],
-	       u32 portid, size_t attr_size, struct netlink_ext_ack *extack)
+static struct sk_buff *tcf_del_notify_msg(struct net *net, struct nlmsghdr *n,
+					  struct tc_action *actions[],
+					  u32 portid, size_t attr_size,
+					  struct netlink_ext_ack *extack)
 {
-	int ret;
 	struct sk_buff *skb;
 
-	skb = alloc_skb(attr_size <= NLMSG_GOODSIZE ? NLMSG_GOODSIZE : attr_size,
-			GFP_KERNEL);
+	skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL);
 	if (!skb)
-		return -ENOBUFS;
+		return ERR_PTR(-ENOBUFS);
 
 	if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, RTM_DELACTION,
 			 0, 2, extack) <= 0) {
 		NL_SET_ERR_MSG(extack, "Failed to fill netlink TC action attributes");
 		kfree_skb(skb);
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
+	}
+
+	return skb;
+}
+
+static int tcf_del_notify(struct net *net, struct nlmsghdr *n,
+			  struct tc_action *actions[], u32 portid,
+			  size_t attr_size, struct netlink_ext_ack *extack)
+{
+	struct sk_buff *skb;
+	int ret;
+
+	if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) {
+		skb = NULL;
+	} else {
+		skb = tcf_del_notify_msg(net, n, actions, portid, attr_size,
+					 extack);
+		if (IS_ERR(skb))
+			return PTR_ERR(skb);
 	}
 
 	/* now do the delete */
@@ -1897,9 +1957,8 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[],
 		return ret;
 	}
 
-	ret = rtnetlink_send(skb, net, portid, RTNLGRP_TC,
-			     n->nlmsg_flags & NLM_F_ECHO);
-	return ret;
+	return rtnetlink_maybe_send(skb, net, portid, RTNLGRP_TC,
+				    n->nlmsg_flags & NLM_F_ECHO);
 }
 
 static int
@@ -1950,26 +2009,44 @@ err:
 	return ret;
 }
 
-static int
-tcf_add_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[],
-	       u32 portid, size_t attr_size, struct netlink_ext_ack *extack)
+static struct sk_buff *tcf_add_notify_msg(struct net *net, struct nlmsghdr *n,
+					  struct tc_action *actions[],
+					  u32 portid, size_t attr_size,
+					  struct netlink_ext_ack *extack)
 {
 	struct sk_buff *skb;
 
-	skb = alloc_skb(attr_size <= NLMSG_GOODSIZE ? NLMSG_GOODSIZE : attr_size,
-			GFP_KERNEL);
+	skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL);
 	if (!skb)
-		return -ENOBUFS;
+		return ERR_PTR(-ENOBUFS);
 
 	if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, n->nlmsg_flags,
 			 RTM_NEWACTION, 0, 0, extack) <= 0) {
 		NL_SET_ERR_MSG(extack, "Failed to fill netlink attributes while adding TC action");
 		kfree_skb(skb);
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 	}
 
-	return rtnetlink_send(skb, net, portid, RTNLGRP_TC,
-			      n->nlmsg_flags & NLM_F_ECHO);
+	return skb;
+}
+
+static int tcf_add_notify(struct net *net, struct nlmsghdr *n,
+			  struct tc_action *actions[], u32 portid,
+			  size_t attr_size, struct netlink_ext_ack *extack)
+{
+	struct sk_buff *skb;
+
+	if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) {
+		skb = NULL;
+	} else {
+		skb = tcf_add_notify_msg(net, n, actions, portid, attr_size,
+					 extack);
+		if (IS_ERR(skb))
+			return PTR_ERR(skb);
+	}
+
+	return rtnetlink_maybe_send(skb, net, portid, RTNLGRP_TC,
+				    n->nlmsg_flags & NLM_F_ECHO);
 }
 
 static int tcf_action_add(struct net *net, struct nlattr *nla,
@@ -1977,7 +2054,7 @@ static int tcf_action_add(struct net *net, struct nlattr *nla,
 			  struct netlink_ext_ack *extack)
 {
 	size_t attr_size = 0;
-	int loop, ret, i;
+	int loop, ret;
 	struct tc_action *actions[TCA_ACT_MAX_PRIO] = {};
 	int init_res[TCA_ACT_MAX_PRIO] = {};
 
@@ -1990,13 +2067,11 @@ static int tcf_action_add(struct net *net, struct nlattr *nla,
 
 	if (ret < 0)
 		return ret;
+
 	ret = tcf_add_notify(net, n, actions, portid, attr_size, extack);
 
-	/* only put existing actions */
-	for (i = 0; i < TCA_ACT_MAX_PRIO; i++)
-		if (init_res[i] == ACT_P_CREATED)
-			actions[i] = NULL;
-	tcf_action_put_many(actions);
+	/* only put bound actions */
+	tca_put_bound_many(actions, init_res);
 
 	return ret;
 }
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index b0455fda7d0b..6cfee6658103 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -318,7 +318,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 	} else if (ret > 0) {
 		/* Don't override defaults. */
 		if (bind)
-			return 0;
+			return ACT_P_BOUND;
 
 		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
 			tcf_idr_release(*act, bind);
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 0d7aee8933c5..f8762756657d 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -146,7 +146,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 	} else if (ret > 0) {
 		ci = to_connmark(*a);
 		if (bind) {
-			err = 0;
+			err = ACT_P_BOUND;
 			goto out_free;
 		}
 		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 8ed285023a40..7f8b1f2f2ed9 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -77,8 +77,8 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 		}
 		ret = ACT_P_CREATED;
 	} else if (err > 0) {
-		if (bind)/* dont override defaults */
-			return 0;
+		if (bind) /* dont override defaults */
+			return ACT_P_BOUND;
 		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
 			tcf_idr_release(*a, bind);
 			return -EEXIST;
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 0db0ecf1d110..6124d8b128d1 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -286,9 +286,31 @@ static bool tcf_ct_flow_is_outdated(const struct flow_offload *flow)
 	       !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags);
 }
 
+static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft);
+
+static void tcf_ct_nf_get(struct nf_flowtable *ft)
+{
+	struct tcf_ct_flow_table *ct_ft =
+		container_of(ft, struct tcf_ct_flow_table, nf_ft);
+
+	tcf_ct_flow_table_get_ref(ct_ft);
+}
+
+static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft);
+
+static void tcf_ct_nf_put(struct nf_flowtable *ft)
+{
+	struct tcf_ct_flow_table *ct_ft =
+		container_of(ft, struct tcf_ct_flow_table, nf_ft);
+
+	tcf_ct_flow_table_put(ct_ft);
+}
+
 static struct nf_flowtable_type flowtable_ct = {
 	.gc		= tcf_ct_flow_is_outdated,
 	.action		= tcf_ct_flow_table_fill_actions,
+	.get		= tcf_ct_nf_get,
+	.put		= tcf_ct_nf_put,
 	.owner		= THIS_MODULE,
 };
 
@@ -337,9 +359,13 @@ err_alloc:
 	return err;
 }
 
+static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft)
+{
+	refcount_inc(&ct_ft->ref);
+}
+
 static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
 {
-	struct flow_block_cb *block_cb, *tmp_cb;
 	struct tcf_ct_flow_table *ct_ft;
 	struct flow_block *block;
 
@@ -347,13 +373,9 @@ static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
 			     rwork);
 	nf_flow_table_free(&ct_ft->nf_ft);
 
-	/* Remove any remaining callbacks before cleanup */
 	block = &ct_ft->nf_ft.flow_block;
 	down_write(&ct_ft->nf_ft.flow_block_lock);
-	list_for_each_entry_safe(block_cb, tmp_cb, &block->cb_list, list) {
-		list_del(&block_cb->list);
-		flow_block_cb_free(block_cb);
-	}
+	WARN_ON(!list_empty(&block->cb_list));
 	up_write(&ct_ft->nf_ft.flow_block_lock);
 	kfree(ct_ft);
 
@@ -828,7 +850,6 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 	if (err || !frag)
 		return err;
 
-	skb_get(skb);
 	err = nf_ct_handle_fragments(net, skb, zone, family, &proto, &mru);
 	if (err)
 		return err;
@@ -977,12 +998,8 @@ TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
 	nh_ofs = skb_network_offset(skb);
 	skb_pull_rcsum(skb, nh_ofs);
 	err = tcf_ct_handle_fragments(net, skb, family, p->zone, &defrag);
-	if (err == -EINPROGRESS) {
-		retval = TC_ACT_STOLEN;
-		goto out_clear;
-	}
 	if (err)
-		goto drop;
+		goto out_frag;
 
 	err = nf_ct_skb_network_trim(skb, family);
 	if (err)
@@ -1069,6 +1086,11 @@ out_clear:
 		qdisc_skb_cb(skb)->pkt_len = skb->len;
 	return retval;
 
+out_frag:
+	if (err != -EINPROGRESS)
+		tcf_action_inc_drop_qstats(&c->common);
+	return TC_ACT_CONSUMED;
+
 drop:
 	tcf_action_inc_drop_qstats(&c->common);
 	return TC_ACT_SHOT;
@@ -1327,7 +1349,7 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla,
 		res = ACT_P_CREATED;
 	} else {
 		if (bind)
-			return 0;
+			return ACT_P_BOUND;
 
 		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
 			tcf_idr_release(*a, bind);
@@ -1549,6 +1571,9 @@ static int tcf_ct_offload_act_setup(struct tc_action *act, void *entry_data,
 	if (bind) {
 		struct flow_action_entry *entry = entry_data;
 
+		if (tcf_ct_helper(act))
+			return -EOPNOTSUPP;
+
 		entry->id = FLOW_ACTION_CT;
 		entry->ct.action = tcf_ct_action(act);
 		entry->ct.zone = tcf_ct_zone(act);
diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c
index 4d15b6a6169c..e620f9a84afe 100644
--- a/net/sched/act_ctinfo.c
+++ b/net/sched/act_ctinfo.c
@@ -221,7 +221,7 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla,
 		ret = ACT_P_CREATED;
 	} else if (err > 0) {
 		if (bind) /* don't override defaults */
-			return 0;
+			return ACT_P_BOUND;
 		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
 			tcf_idr_release(*a, bind);
 			return -EEXIST;
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 904ab3d457ef..4af3b7ec249f 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -108,7 +108,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 		ret = ACT_P_CREATED;
 	} else if (err > 0) {
 		if (bind)/* dont override defaults */
-			return 0;
+			return ACT_P_BOUND;
 		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
 			tcf_idr_release(*a, bind);
 			return -EEXIST;
diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c
index 393b78729216..c681cd011afd 100644
--- a/net/sched/act_gate.c
+++ b/net/sched/act_gate.c
@@ -356,7 +356,7 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
 		return err;
 
 	if (err && bind)
-		return 0;
+		return ACT_P_BOUND;
 
 	if (!err) {
 		ret = tcf_idr_create_from_flags(tn, index, est, a,
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index bc7611b0744c..0e867d13beb5 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -548,7 +548,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	exists = err;
 	if (exists && bind) {
 		kfree(p);
-		return 0;
+		return ACT_P_BOUND;
 	}
 
 	if (!exists) {
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
deleted file mode 100644
index 598d6e299152..000000000000
--- a/net/sched/act_ipt.c
+++ /dev/null
@@ -1,464 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * net/sched/act_ipt.c		iptables target interface
- *
- *TODO: Add other tables. For now we only support the ipv4 table targets
- *
- * Copyright:	Jamal Hadi Salim (2002-13)
- */
-
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/skbuff.h>
-#include <linux/rtnetlink.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <net/netlink.h>
-#include <net/pkt_sched.h>
-#include <linux/tc_act/tc_ipt.h>
-#include <net/tc_act/tc_ipt.h>
-#include <net/tc_wrapper.h>
-#include <net/ip.h>
-
-#include <linux/netfilter_ipv4/ip_tables.h>
-
-
-static struct tc_action_ops act_ipt_ops;
-static struct tc_action_ops act_xt_ops;
-
-static int ipt_init_target(struct net *net, struct xt_entry_target *t,
-			   char *table, unsigned int hook)
-{
-	struct xt_tgchk_param par;
-	struct xt_target *target;
-	struct ipt_entry e = {};
-	int ret = 0;
-
-	target = xt_request_find_target(AF_INET, t->u.user.name,
-					t->u.user.revision);
-	if (IS_ERR(target))
-		return PTR_ERR(target);
-
-	t->u.kernel.target = target;
-	memset(&par, 0, sizeof(par));
-	par.net       = net;
-	par.table     = table;
-	par.entryinfo = &e;
-	par.target    = target;
-	par.targinfo  = t->data;
-	par.hook_mask = 1 << hook;
-	par.family    = NFPROTO_IPV4;
-
-	ret = xt_check_target(&par, t->u.target_size - sizeof(*t), 0, false);
-	if (ret < 0) {
-		module_put(t->u.kernel.target->me);
-		return ret;
-	}
-	return 0;
-}
-
-static void ipt_destroy_target(struct xt_entry_target *t, struct net *net)
-{
-	struct xt_tgdtor_param par = {
-		.target   = t->u.kernel.target,
-		.targinfo = t->data,
-		.family   = NFPROTO_IPV4,
-		.net      = net,
-	};
-	if (par.target->destroy != NULL)
-		par.target->destroy(&par);
-	module_put(par.target->me);
-}
-
-static void tcf_ipt_release(struct tc_action *a)
-{
-	struct tcf_ipt *ipt = to_ipt(a);
-
-	if (ipt->tcfi_t) {
-		ipt_destroy_target(ipt->tcfi_t, a->idrinfo->net);
-		kfree(ipt->tcfi_t);
-	}
-	kfree(ipt->tcfi_tname);
-}
-
-static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = {
-	[TCA_IPT_TABLE]	= { .type = NLA_STRING, .len = IFNAMSIZ },
-	[TCA_IPT_HOOK]	= NLA_POLICY_RANGE(NLA_U32, NF_INET_PRE_ROUTING,
-					   NF_INET_NUMHOOKS),
-	[TCA_IPT_INDEX]	= { .type = NLA_U32 },
-	[TCA_IPT_TARG]	= { .len = sizeof(struct xt_entry_target) },
-};
-
-static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
-			  struct nlattr *est, struct tc_action **a,
-			  const struct tc_action_ops *ops,
-			  struct tcf_proto *tp, u32 flags)
-{
-	struct tc_action_net *tn = net_generic(net, id);
-	bool bind = flags & TCA_ACT_FLAGS_BIND;
-	struct nlattr *tb[TCA_IPT_MAX + 1];
-	struct tcf_ipt *ipt;
-	struct xt_entry_target *td, *t;
-	char *tname;
-	bool exists = false;
-	int ret = 0, err;
-	u32 hook = 0;
-	u32 index = 0;
-
-	if (nla == NULL)
-		return -EINVAL;
-
-	err = nla_parse_nested_deprecated(tb, TCA_IPT_MAX, nla, ipt_policy,
-					  NULL);
-	if (err < 0)
-		return err;
-
-	if (tb[TCA_IPT_INDEX] != NULL)
-		index = nla_get_u32(tb[TCA_IPT_INDEX]);
-
-	err = tcf_idr_check_alloc(tn, &index, a, bind);
-	if (err < 0)
-		return err;
-	exists = err;
-	if (exists && bind)
-		return 0;
-
-	if (tb[TCA_IPT_HOOK] == NULL || tb[TCA_IPT_TARG] == NULL) {
-		if (exists)
-			tcf_idr_release(*a, bind);
-		else
-			tcf_idr_cleanup(tn, index);
-		return -EINVAL;
-	}
-
-	td = (struct xt_entry_target *)nla_data(tb[TCA_IPT_TARG]);
-	if (nla_len(tb[TCA_IPT_TARG]) != td->u.target_size) {
-		if (exists)
-			tcf_idr_release(*a, bind);
-		else
-			tcf_idr_cleanup(tn, index);
-		return -EINVAL;
-	}
-
-	if (!exists) {
-		ret = tcf_idr_create(tn, index, est, a, ops, bind,
-				     false, flags);
-		if (ret) {
-			tcf_idr_cleanup(tn, index);
-			return ret;
-		}
-		ret = ACT_P_CREATED;
-	} else {
-		if (bind)/* dont override defaults */
-			return 0;
-
-		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
-			tcf_idr_release(*a, bind);
-			return -EEXIST;
-		}
-	}
-
-	err = -EINVAL;
-	hook = nla_get_u32(tb[TCA_IPT_HOOK]);
-	switch (hook) {
-	case NF_INET_PRE_ROUTING:
-		break;
-	case NF_INET_POST_ROUTING:
-		break;
-	default:
-		goto err1;
-	}
-
-	if (tb[TCA_IPT_TABLE]) {
-		/* mangle only for now */
-		if (nla_strcmp(tb[TCA_IPT_TABLE], "mangle"))
-			goto err1;
-	}
-
-	tname = kstrdup("mangle", GFP_KERNEL);
-	if (unlikely(!tname))
-		goto err1;
-
-	t = kmemdup(td, td->u.target_size, GFP_KERNEL);
-	if (unlikely(!t))
-		goto err2;
-
-	err = ipt_init_target(net, t, tname, hook);
-	if (err < 0)
-		goto err3;
-
-	ipt = to_ipt(*a);
-
-	spin_lock_bh(&ipt->tcf_lock);
-	if (ret != ACT_P_CREATED) {
-		ipt_destroy_target(ipt->tcfi_t, net);
-		kfree(ipt->tcfi_tname);
-		kfree(ipt->tcfi_t);
-	}
-	ipt->tcfi_tname = tname;
-	ipt->tcfi_t     = t;
-	ipt->tcfi_hook  = hook;
-	spin_unlock_bh(&ipt->tcf_lock);
-	return ret;
-
-err3:
-	kfree(t);
-err2:
-	kfree(tname);
-err1:
-	tcf_idr_release(*a, bind);
-	return err;
-}
-
-static int tcf_ipt_init(struct net *net, struct nlattr *nla,
-			struct nlattr *est, struct tc_action **a,
-			struct tcf_proto *tp,
-			u32 flags, struct netlink_ext_ack *extack)
-{
-	return __tcf_ipt_init(net, act_ipt_ops.net_id, nla, est,
-			      a, &act_ipt_ops, tp, flags);
-}
-
-static int tcf_xt_init(struct net *net, struct nlattr *nla,
-		       struct nlattr *est, struct tc_action **a,
-		       struct tcf_proto *tp,
-		       u32 flags, struct netlink_ext_ack *extack)
-{
-	return __tcf_ipt_init(net, act_xt_ops.net_id, nla, est,
-			      a, &act_xt_ops, tp, flags);
-}
-
-static bool tcf_ipt_act_check(struct sk_buff *skb)
-{
-	const struct iphdr *iph;
-	unsigned int nhoff, len;
-
-	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
-		return false;
-
-	nhoff = skb_network_offset(skb);
-	iph = ip_hdr(skb);
-	if (iph->ihl < 5 || iph->version != 4)
-		return false;
-
-	len = skb_ip_totlen(skb);
-	if (skb->len < nhoff + len || len < (iph->ihl * 4u))
-		return false;
-
-	return pskb_may_pull(skb, iph->ihl * 4u);
-}
-
-TC_INDIRECT_SCOPE int tcf_ipt_act(struct sk_buff *skb,
-				  const struct tc_action *a,
-				  struct tcf_result *res)
-{
-	char saved_cb[sizeof_field(struct sk_buff, cb)];
-	int ret = 0, result = 0;
-	struct tcf_ipt *ipt = to_ipt(a);
-	struct xt_action_param par;
-	struct nf_hook_state state = {
-		.net	= dev_net(skb->dev),
-		.in	= skb->dev,
-		.hook	= ipt->tcfi_hook,
-		.pf	= NFPROTO_IPV4,
-	};
-
-	if (skb_protocol(skb, false) != htons(ETH_P_IP))
-		return TC_ACT_UNSPEC;
-
-	if (skb_unclone(skb, GFP_ATOMIC))
-		return TC_ACT_UNSPEC;
-
-	if (!tcf_ipt_act_check(skb))
-		return TC_ACT_UNSPEC;
-
-	if (state.hook == NF_INET_POST_ROUTING) {
-		if (!skb_dst(skb))
-			return TC_ACT_UNSPEC;
-
-		state.out = skb->dev;
-	}
-
-	memcpy(saved_cb, skb->cb, sizeof(saved_cb));
-
-	spin_lock(&ipt->tcf_lock);
-
-	tcf_lastuse_update(&ipt->tcf_tm);
-	bstats_update(&ipt->tcf_bstats, skb);
-
-	/* yes, we have to worry about both in and out dev
-	 * worry later - danger - this API seems to have changed
-	 * from earlier kernels
-	 */
-	par.state    = &state;
-	par.target   = ipt->tcfi_t->u.kernel.target;
-	par.targinfo = ipt->tcfi_t->data;
-
-	memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
-
-	ret = par.target->target(skb, &par);
-
-	switch (ret) {
-	case NF_ACCEPT:
-		result = TC_ACT_OK;
-		break;
-	case NF_DROP:
-		result = TC_ACT_SHOT;
-		ipt->tcf_qstats.drops++;
-		break;
-	case XT_CONTINUE:
-		result = TC_ACT_PIPE;
-		break;
-	default:
-		net_notice_ratelimited("tc filter: Bogus netfilter code %d assume ACCEPT\n",
-				       ret);
-		result = TC_ACT_OK;
-		break;
-	}
-	spin_unlock(&ipt->tcf_lock);
-
-	memcpy(skb->cb, saved_cb, sizeof(skb->cb));
-
-	return result;
-
-}
-
-static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind,
-			int ref)
-{
-	unsigned char *b = skb_tail_pointer(skb);
-	struct tcf_ipt *ipt = to_ipt(a);
-	struct xt_entry_target *t;
-	struct tcf_t tm;
-	struct tc_cnt c;
-
-	/* for simple targets kernel size == user size
-	 * user name = target name
-	 * for foolproof you need to not assume this
-	 */
-
-	spin_lock_bh(&ipt->tcf_lock);
-	t = kmemdup(ipt->tcfi_t, ipt->tcfi_t->u.user.target_size, GFP_ATOMIC);
-	if (unlikely(!t))
-		goto nla_put_failure;
-
-	c.bindcnt = atomic_read(&ipt->tcf_bindcnt) - bind;
-	c.refcnt = refcount_read(&ipt->tcf_refcnt) - ref;
-	strcpy(t->u.user.name, ipt->tcfi_t->u.kernel.target->name);
-
-	if (nla_put(skb, TCA_IPT_TARG, ipt->tcfi_t->u.user.target_size, t) ||
-	    nla_put_u32(skb, TCA_IPT_INDEX, ipt->tcf_index) ||
-	    nla_put_u32(skb, TCA_IPT_HOOK, ipt->tcfi_hook) ||
-	    nla_put(skb, TCA_IPT_CNT, sizeof(struct tc_cnt), &c) ||
-	    nla_put_string(skb, TCA_IPT_TABLE, ipt->tcfi_tname))
-		goto nla_put_failure;
-
-	tcf_tm_dump(&tm, &ipt->tcf_tm);
-	if (nla_put_64bit(skb, TCA_IPT_TM, sizeof(tm), &tm, TCA_IPT_PAD))
-		goto nla_put_failure;
-
-	spin_unlock_bh(&ipt->tcf_lock);
-	kfree(t);
-	return skb->len;
-
-nla_put_failure:
-	spin_unlock_bh(&ipt->tcf_lock);
-	nlmsg_trim(skb, b);
-	kfree(t);
-	return -1;
-}
-
-static struct tc_action_ops act_ipt_ops = {
-	.kind		=	"ipt",
-	.id		=	TCA_ID_IPT,
-	.owner		=	THIS_MODULE,
-	.act		=	tcf_ipt_act,
-	.dump		=	tcf_ipt_dump,
-	.cleanup	=	tcf_ipt_release,
-	.init		=	tcf_ipt_init,
-	.size		=	sizeof(struct tcf_ipt),
-};
-
-static __net_init int ipt_init_net(struct net *net)
-{
-	struct tc_action_net *tn = net_generic(net, act_ipt_ops.net_id);
-
-	return tc_action_net_init(net, tn, &act_ipt_ops);
-}
-
-static void __net_exit ipt_exit_net(struct list_head *net_list)
-{
-	tc_action_net_exit(net_list, act_ipt_ops.net_id);
-}
-
-static struct pernet_operations ipt_net_ops = {
-	.init = ipt_init_net,
-	.exit_batch = ipt_exit_net,
-	.id   = &act_ipt_ops.net_id,
-	.size = sizeof(struct tc_action_net),
-};
-
-static struct tc_action_ops act_xt_ops = {
-	.kind		=	"xt",
-	.id		=	TCA_ID_XT,
-	.owner		=	THIS_MODULE,
-	.act		=	tcf_ipt_act,
-	.dump		=	tcf_ipt_dump,
-	.cleanup	=	tcf_ipt_release,
-	.init		=	tcf_xt_init,
-	.size		=	sizeof(struct tcf_ipt),
-};
-
-static __net_init int xt_init_net(struct net *net)
-{
-	struct tc_action_net *tn = net_generic(net, act_xt_ops.net_id);
-
-	return tc_action_net_init(net, tn, &act_xt_ops);
-}
-
-static void __net_exit xt_exit_net(struct list_head *net_list)
-{
-	tc_action_net_exit(net_list, act_xt_ops.net_id);
-}
-
-static struct pernet_operations xt_net_ops = {
-	.init = xt_init_net,
-	.exit_batch = xt_exit_net,
-	.id   = &act_xt_ops.net_id,
-	.size = sizeof(struct tc_action_net),
-};
-
-MODULE_AUTHOR("Jamal Hadi Salim(2002-13)");
-MODULE_DESCRIPTION("Iptables target actions");
-MODULE_LICENSE("GPL");
-MODULE_ALIAS("act_xt");
-
-static int __init ipt_init_module(void)
-{
-	int ret1, ret2;
-
-	ret1 = tcf_register_action(&act_xt_ops, &xt_net_ops);
-	if (ret1 < 0)
-		pr_err("Failed to load xt action\n");
-
-	ret2 = tcf_register_action(&act_ipt_ops, &ipt_net_ops);
-	if (ret2 < 0)
-		pr_err("Failed to load ipt action\n");
-
-	if (ret1 < 0 && ret2 < 0) {
-		return ret1;
-	} else
-		return 0;
-}
-
-static void __exit ipt_cleanup_module(void)
-{
-	tcf_unregister_action(&act_ipt_ops, &ipt_net_ops);
-	tcf_unregister_action(&act_xt_ops, &xt_net_ops);
-}
-
-module_init(ipt_init_module);
-module_exit(ipt_cleanup_module);
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 0a711c184c29..12386f590b0f 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -85,10 +85,21 @@ static void tcf_mirred_release(struct tc_action *a)
 
 static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = {
 	[TCA_MIRRED_PARMS]	= { .len = sizeof(struct tc_mirred) },
+	[TCA_MIRRED_BLOCKID]	= NLA_POLICY_MIN(NLA_U32, 1),
 };
 
 static struct tc_action_ops act_mirred_ops;
 
+static void tcf_mirred_replace_dev(struct tcf_mirred *m,
+				   struct net_device *ndev)
+{
+	struct net_device *odev;
+
+	odev = rcu_replace_pointer(m->tcfm_dev, ndev,
+				   lockdep_is_held(&m->tcf_lock));
+	netdev_put(odev, &m->tcfm_dev_tracker);
+}
+
 static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 			   struct nlattr *est, struct tc_action **a,
 			   struct tcf_proto *tp,
@@ -124,7 +135,18 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 		return err;
 	exists = err;
 	if (exists && bind)
-		return 0;
+		return ACT_P_BOUND;
+
+	if (tb[TCA_MIRRED_BLOCKID] && parm->ifindex) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot specify Block ID and dev simultaneously");
+		if (exists)
+			tcf_idr_release(*a, bind);
+		else
+			tcf_idr_cleanup(tn, index);
+
+		return -EINVAL;
+	}
 
 	switch (parm->eaction) {
 	case TCA_EGRESS_MIRROR:
@@ -142,9 +164,10 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	}
 
 	if (!exists) {
-		if (!parm->ifindex) {
+		if (!parm->ifindex && !tb[TCA_MIRRED_BLOCKID]) {
 			tcf_idr_cleanup(tn, index);
-			NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist");
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Must specify device or block");
 			return -EINVAL;
 		}
 		ret = tcf_idr_create_from_flags(tn, index, est, a,
@@ -170,7 +193,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	spin_lock_bh(&m->tcf_lock);
 
 	if (parm->ifindex) {
-		struct net_device *odev, *ndev;
+		struct net_device *ndev;
 
 		ndev = dev_get_by_index(net, parm->ifindex);
 		if (!ndev) {
@@ -179,11 +202,14 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 			goto put_chain;
 		}
 		mac_header_xmit = dev_is_mac_header_xmit(ndev);
-		odev = rcu_replace_pointer(m->tcfm_dev, ndev,
-					  lockdep_is_held(&m->tcf_lock));
-		netdev_put(odev, &m->tcfm_dev_tracker);
+		tcf_mirred_replace_dev(m, ndev);
 		netdev_tracker_alloc(ndev, &m->tcfm_dev_tracker, GFP_ATOMIC);
 		m->tcfm_mac_header_xmit = mac_header_xmit;
+		m->tcfm_blockid = 0;
+	} else if (tb[TCA_MIRRED_BLOCKID]) {
+		tcf_mirred_replace_dev(m, NULL);
+		m->tcfm_mac_header_xmit = false;
+		m->tcfm_blockid = nla_get_u32(tb[TCA_MIRRED_BLOCKID]);
 	}
 	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 	m->tcfm_eaction = parm->eaction;
@@ -225,48 +251,26 @@ static int tcf_mirred_forward(bool want_ingress, struct sk_buff *skb)
 	return err;
 }
 
-TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb,
-				     const struct tc_action *a,
-				     struct tcf_result *res)
+static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m,
+			     struct net_device *dev,
+			     const bool m_mac_header_xmit, int m_eaction,
+			     int retval)
 {
-	struct tcf_mirred *m = to_mirred(a);
-	struct sk_buff *skb2 = skb;
-	bool m_mac_header_xmit;
-	struct net_device *dev;
-	unsigned int nest_level;
-	int retval, err = 0;
-	bool use_reinsert;
+	struct sk_buff *skb_to_send = skb;
 	bool want_ingress;
 	bool is_redirect;
 	bool expects_nh;
 	bool at_ingress;
-	int m_eaction;
+	bool dont_clone;
 	int mac_len;
 	bool at_nh;
+	int err;
 
-	nest_level = __this_cpu_inc_return(mirred_nest_level);
-	if (unlikely(nest_level > MIRRED_NEST_LIMIT)) {
-		net_warn_ratelimited("Packet exceeded mirred recursion limit on dev %s\n",
-				     netdev_name(skb->dev));
-		__this_cpu_dec(mirred_nest_level);
-		return TC_ACT_SHOT;
-	}
-
-	tcf_lastuse_update(&m->tcf_tm);
-	tcf_action_update_bstats(&m->common, skb);
-
-	m_mac_header_xmit = READ_ONCE(m->tcfm_mac_header_xmit);
-	m_eaction = READ_ONCE(m->tcfm_eaction);
-	retval = READ_ONCE(m->tcf_action);
-	dev = rcu_dereference_bh(m->tcfm_dev);
-	if (unlikely(!dev)) {
-		pr_notice_once("tc mirred: target device is gone\n");
-		goto out;
-	}
-
+	is_redirect = tcf_mirred_is_act_redirect(m_eaction);
 	if (unlikely(!(dev->flags & IFF_UP)) || !netif_carrier_ok(dev)) {
 		net_notice_ratelimited("tc mirred to Houston: device %s is down\n",
 				       dev->name);
+		err = -ENODEV;
 		goto out;
 	}
 
@@ -274,61 +278,188 @@ TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb,
 	 * since we can't easily detect the clsact caller, skip clone only for
 	 * ingress - that covers the TC S/W datapath.
 	 */
-	is_redirect = tcf_mirred_is_act_redirect(m_eaction);
 	at_ingress = skb_at_tc_ingress(skb);
-	use_reinsert = at_ingress && is_redirect &&
-		       tcf_mirred_can_reinsert(retval);
-	if (!use_reinsert) {
-		skb2 = skb_clone(skb, GFP_ATOMIC);
-		if (!skb2)
+	dont_clone = skb_at_tc_ingress(skb) && is_redirect &&
+		tcf_mirred_can_reinsert(retval);
+	if (!dont_clone) {
+		skb_to_send = skb_clone(skb, GFP_ATOMIC);
+		if (!skb_to_send) {
+			err =  -ENOMEM;
 			goto out;
+		}
 	}
 
 	want_ingress = tcf_mirred_act_wants_ingress(m_eaction);
 
 	/* All mirred/redirected skbs should clear previous ct info */
-	nf_reset_ct(skb2);
+	nf_reset_ct(skb_to_send);
 	if (want_ingress && !at_ingress) /* drop dst for egress -> ingress */
-		skb_dst_drop(skb2);
+		skb_dst_drop(skb_to_send);
 
 	expects_nh = want_ingress || !m_mac_header_xmit;
 	at_nh = skb->data == skb_network_header(skb);
 	if (at_nh != expects_nh) {
-		mac_len = skb_at_tc_ingress(skb) ? skb->mac_len :
+		mac_len = at_ingress ? skb->mac_len :
 			  skb_network_offset(skb);
 		if (expects_nh) {
 			/* target device/action expect data at nh */
-			skb_pull_rcsum(skb2, mac_len);
+			skb_pull_rcsum(skb_to_send, mac_len);
 		} else {
 			/* target device/action expect data at mac */
-			skb_push_rcsum(skb2, mac_len);
+			skb_push_rcsum(skb_to_send, mac_len);
 		}
 	}
 
-	skb2->skb_iif = skb->dev->ifindex;
-	skb2->dev = dev;
+	skb_to_send->skb_iif = skb->dev->ifindex;
+	skb_to_send->dev = dev;
 
-	/* mirror is always swallowed */
 	if (is_redirect) {
-		skb_set_redirected(skb2, skb2->tc_at_ingress);
-
-		/* let's the caller reinsert the packet, if possible */
-		if (use_reinsert) {
-			err = tcf_mirred_forward(want_ingress, skb);
-			if (err)
-				tcf_action_inc_overlimit_qstats(&m->common);
-			__this_cpu_dec(mirred_nest_level);
-			return TC_ACT_CONSUMED;
-		}
+		if (skb == skb_to_send)
+			retval = TC_ACT_CONSUMED;
+
+		skb_set_redirected(skb_to_send, skb_to_send->tc_at_ingress);
+
+		err = tcf_mirred_forward(want_ingress, skb_to_send);
+	} else {
+		err = tcf_mirred_forward(want_ingress, skb_to_send);
 	}
 
-	err = tcf_mirred_forward(want_ingress, skb2);
 	if (err) {
 out:
 		tcf_action_inc_overlimit_qstats(&m->common);
-		if (tcf_mirred_is_act_redirect(m_eaction))
+		if (is_redirect)
 			retval = TC_ACT_SHOT;
 	}
+
+	return retval;
+}
+
+static int tcf_blockcast_redir(struct sk_buff *skb, struct tcf_mirred *m,
+			       struct tcf_block *block, int m_eaction,
+			       const u32 exception_ifindex, int retval)
+{
+	struct net_device *dev_prev = NULL;
+	struct net_device *dev = NULL;
+	unsigned long index;
+	int mirred_eaction;
+
+	mirred_eaction = tcf_mirred_act_wants_ingress(m_eaction) ?
+		TCA_INGRESS_MIRROR : TCA_EGRESS_MIRROR;
+
+	xa_for_each(&block->ports, index, dev) {
+		if (index == exception_ifindex)
+			continue;
+
+		if (!dev_prev)
+			goto assign_prev;
+
+		tcf_mirred_to_dev(skb, m, dev_prev,
+				  dev_is_mac_header_xmit(dev),
+				  mirred_eaction, retval);
+assign_prev:
+		dev_prev = dev;
+	}
+
+	if (dev_prev)
+		return tcf_mirred_to_dev(skb, m, dev_prev,
+					 dev_is_mac_header_xmit(dev_prev),
+					 m_eaction, retval);
+
+	return retval;
+}
+
+static int tcf_blockcast_mirror(struct sk_buff *skb, struct tcf_mirred *m,
+				struct tcf_block *block, int m_eaction,
+				const u32 exception_ifindex, int retval)
+{
+	struct net_device *dev = NULL;
+	unsigned long index;
+
+	xa_for_each(&block->ports, index, dev) {
+		if (index == exception_ifindex)
+			continue;
+
+		tcf_mirred_to_dev(skb, m, dev,
+				  dev_is_mac_header_xmit(dev),
+				  m_eaction, retval);
+	}
+
+	return retval;
+}
+
+static int tcf_blockcast(struct sk_buff *skb, struct tcf_mirred *m,
+			 const u32 blockid, struct tcf_result *res,
+			 int retval)
+{
+	const u32 exception_ifindex = skb->dev->ifindex;
+	struct tcf_block *block;
+	bool is_redirect;
+	int m_eaction;
+
+	m_eaction = READ_ONCE(m->tcfm_eaction);
+	is_redirect = tcf_mirred_is_act_redirect(m_eaction);
+
+	/* we are already under rcu protection, so can call block lookup
+	 * directly.
+	 */
+	block = tcf_block_lookup(dev_net(skb->dev), blockid);
+	if (!block || xa_empty(&block->ports)) {
+		tcf_action_inc_overlimit_qstats(&m->common);
+		return retval;
+	}
+
+	if (is_redirect)
+		return tcf_blockcast_redir(skb, m, block, m_eaction,
+					   exception_ifindex, retval);
+
+	/* If it's not redirect, it is mirror */
+	return tcf_blockcast_mirror(skb, m, block, m_eaction, exception_ifindex,
+				    retval);
+}
+
+TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb,
+				     const struct tc_action *a,
+				     struct tcf_result *res)
+{
+	struct tcf_mirred *m = to_mirred(a);
+	int retval = READ_ONCE(m->tcf_action);
+	unsigned int nest_level;
+	bool m_mac_header_xmit;
+	struct net_device *dev;
+	int m_eaction;
+	u32 blockid;
+
+	nest_level = __this_cpu_inc_return(mirred_nest_level);
+	if (unlikely(nest_level > MIRRED_NEST_LIMIT)) {
+		net_warn_ratelimited("Packet exceeded mirred recursion limit on dev %s\n",
+				     netdev_name(skb->dev));
+		retval = TC_ACT_SHOT;
+		goto dec_nest_level;
+	}
+
+	tcf_lastuse_update(&m->tcf_tm);
+	tcf_action_update_bstats(&m->common, skb);
+
+	blockid = READ_ONCE(m->tcfm_blockid);
+	if (blockid) {
+		retval = tcf_blockcast(skb, m, blockid, res, retval);
+		goto dec_nest_level;
+	}
+
+	dev = rcu_dereference_bh(m->tcfm_dev);
+	if (unlikely(!dev)) {
+		pr_notice_once("tc mirred: target device is gone\n");
+		tcf_action_inc_overlimit_qstats(&m->common);
+		goto dec_nest_level;
+	}
+
+	m_mac_header_xmit = READ_ONCE(m->tcfm_mac_header_xmit);
+	m_eaction = READ_ONCE(m->tcfm_eaction);
+
+	retval = tcf_mirred_to_dev(skb, m, dev, m_mac_header_xmit, m_eaction,
+				   retval);
+
+dec_nest_level:
 	__this_cpu_dec(mirred_nest_level);
 
 	return retval;
@@ -356,6 +487,7 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 	};
 	struct net_device *dev;
 	struct tcf_t t;
+	u32 blockid;
 
 	spin_lock_bh(&m->tcf_lock);
 	opt.action = m->tcf_action;
@@ -367,6 +499,10 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 	if (nla_put(skb, TCA_MIRRED_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
 
+	blockid = m->tcfm_blockid;
+	if (blockid && nla_put_u32(skb, TCA_MIRRED_BLOCKID, blockid))
+		goto nla_put_failure;
+
 	tcf_tm_dump(&t, &m->tcf_tm);
 	if (nla_put_64bit(skb, TCA_MIRRED_TM, sizeof(t), &t, TCA_MIRRED_PAD))
 		goto nla_put_failure;
@@ -397,6 +533,8 @@ static int mirred_device_event(struct notifier_block *unused,
 				 * net_device are already rcu protected.
 				 */
 				RCU_INIT_POINTER(m->tcfm_dev, NULL);
+			} else if (m->tcfm_blockid) {
+				m->tcfm_blockid = 0;
 			}
 			spin_unlock_bh(&m->tcf_lock);
 		}
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index 1010dc632874..34b8edb6cc77 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -195,7 +195,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla,
 		return err;
 	exists = err;
 	if (exists && bind)
-		return 0;
+		return ACT_P_BOUND;
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, est, a, &act_mpls_ops, bind,
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 4184af5abbf3..a180e724634e 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -69,7 +69,7 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 		ret = ACT_P_CREATED;
 	} else if (err > 0) {
 		if (bind)
-			return 0;
+			return ACT_P_BOUND;
 		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
 			tcf_idr_release(*a, bind);
 			return -EEXIST;
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 1ef8fcfa9997..2ef22969f274 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -202,7 +202,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 		ret = ACT_P_CREATED;
 	} else if (err > 0) {
 		if (bind)
-			return 0;
+			return ACT_P_BOUND;
 		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
 			ret = -EEXIST;
 			goto out_release;
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index f3121c5a85e9..e119b4a3db9f 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -77,7 +77,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 		return err;
 	exists = err;
 	if (exists && bind)
-		return 0;
+		return ACT_P_BOUND;
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, NULL, a,
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 4c670e7568dc..c5c61efe6db4 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -66,7 +66,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 		return err;
 	exists = err;
 	if (exists && bind)
-		return 0;
+		return ACT_P_BOUND;
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, est, a,
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 4b84514534f3..0a3e92888295 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -118,7 +118,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 		return err;
 	exists = err;
 	if (exists && bind)
-		return 0;
+		return ACT_P_BOUND;
 
 	if (tb[TCA_DEF_DATA] == NULL) {
 		if (exists)
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index ce7008cf291c..754f78b35bb8 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -209,7 +209,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 		return err;
 	exists = err;
 	if (exists && bind)
-		return 0;
+		return ACT_P_BOUND;
 
 	if (!flags) {
 		if (exists)
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index dffa990a9629..bcb673ab0008 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -157,7 +157,7 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 		return err;
 	exists = err;
 	if (exists && bind)
-		return 0;
+		return ACT_P_BOUND;
 
 	if (!lflags) {
 		if (exists)
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 0c8aa7e686ea..300b08aa8283 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -401,7 +401,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 		return err;
 	exists = err;
 	if (exists && bind)
-		return 0;
+		return ACT_P_BOUND;
 
 	switch (parm->t_action) {
 	case TCA_TUNNEL_KEY_ACT_RELEASE:
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 0251442f5f29..836183011a7c 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -151,7 +151,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 		return err;
 	exists = err;
 	if (exists && bind)
-		return 0;
+		return ACT_P_BOUND;
 
 	switch (parm->v_action) {
 	case TCA_VLAN_ACT_POP:
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 1976bd163986..e3236a3169c3 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -531,6 +531,7 @@ static void tcf_block_destroy(struct tcf_block *block)
 {
 	mutex_destroy(&block->lock);
 	mutex_destroy(&block->proto_destroy_lock);
+	xa_destroy(&block->ports);
 	kfree_rcu(block, rcu);
 }
 
@@ -650,7 +651,7 @@ static void tc_chain_tmplt_del(const struct tcf_proto_ops *tmplt_ops,
 static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops,
 				  void *tmplt_priv, u32 chain_index,
 				  struct tcf_block *block, struct sk_buff *oskb,
-				  u32 seq, u16 flags, bool unicast);
+				  u32 seq, u16 flags);
 
 static void __tcf_chain_put(struct tcf_chain *chain, bool by_act,
 			    bool explicitly_created)
@@ -685,8 +686,7 @@ static void __tcf_chain_put(struct tcf_chain *chain, bool by_act,
 	if (non_act_refcnt == chain->explicitly_created && !by_act) {
 		if (non_act_refcnt == 0)
 			tc_chain_notify_delete(tmplt_ops, tmplt_priv,
-					       chain->index, block, NULL, 0, 0,
-					       false);
+					       chain->index, block, NULL, 0, 0);
 		/* Last reference to chain, no need to lock. */
 		chain->flushing = false;
 	}
@@ -1003,6 +1003,7 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q,
 	refcount_set(&block->refcnt, 1);
 	block->net = net;
 	block->index = block_index;
+	xa_init(&block->ports);
 
 	/* Don't store q pointer for blocks which are shared */
 	if (!tcf_block_shared(block))
@@ -1010,12 +1011,13 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q,
 	return block;
 }
 
-static struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index)
+struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index)
 {
 	struct tcf_net *tn = net_generic(net, tcf_net_id);
 
 	return idr_find(&tn->idr, block_index);
 }
+EXPORT_SYMBOL(tcf_block_lookup);
 
 static struct tcf_block *tcf_block_refcnt_get(struct net *net, u32 block_index)
 {
@@ -1426,6 +1428,7 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
 		      struct tcf_block_ext_info *ei,
 		      struct netlink_ext_ack *extack)
 {
+	struct net_device *dev = qdisc_dev(q);
 	struct net *net = qdisc_net(q);
 	struct tcf_block *block = NULL;
 	int err;
@@ -1459,9 +1462,18 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
 	if (err)
 		goto err_block_offload_bind;
 
+	if (tcf_block_shared(block)) {
+		err = xa_insert(&block->ports, dev->ifindex, dev, GFP_KERNEL);
+		if (err) {
+			NL_SET_ERR_MSG(extack, "block dev insert failed");
+			goto err_dev_insert;
+		}
+	}
+
 	*p_block = block;
 	return 0;
 
+err_dev_insert:
 err_block_offload_bind:
 	tcf_chain0_head_change_cb_del(block, ei);
 err_chain0_head_change_cb_add:
@@ -1500,8 +1512,12 @@ EXPORT_SYMBOL(tcf_block_get);
 void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
 		       struct tcf_block_ext_info *ei)
 {
+	struct net_device *dev = qdisc_dev(q);
+
 	if (!block)
 		return;
+	if (tcf_block_shared(block))
+		xa_erase(&block->ports, dev->ifindex);
 	tcf_chain0_head_change_cb_del(block, ei);
 	tcf_block_owner_del(block, q, ei->binder_type);
 
@@ -1658,7 +1674,6 @@ static inline int __tcf_classify(struct sk_buff *skb,
 				 int act_index,
 				 u32 *last_executed_chain)
 {
-	u32 orig_reason = res->drop_reason;
 #ifdef CONFIG_NET_CLS_ACT
 	const int max_reclassify_loop = 16;
 	const struct tcf_proto *first_tp;
@@ -1683,13 +1698,15 @@ reclassify:
 			 */
 			if (unlikely(n->tp != tp || n->tp->chain != n->chain ||
 				     !tp->ops->get_exts)) {
-				tcf_set_drop_reason(res, SKB_DROP_REASON_TC_ERROR);
+				tcf_set_drop_reason(skb,
+						    SKB_DROP_REASON_TC_COOKIE_ERROR);
 				return TC_ACT_SHOT;
 			}
 
 			exts = tp->ops->get_exts(tp, n->handle);
 			if (unlikely(!exts || n->exts != exts)) {
-				tcf_set_drop_reason(res, SKB_DROP_REASON_TC_ERROR);
+				tcf_set_drop_reason(skb,
+						    SKB_DROP_REASON_TC_COOKIE_ERROR);
 				return TC_ACT_SHOT;
 			}
 
@@ -1713,18 +1730,13 @@ reclassify:
 			goto reset;
 		}
 #endif
-		if (err >= 0) {
-			/* Policy drop or drop reason is over-written by
-			 * classifiers with a bogus value(0) */
-			if (err == TC_ACT_SHOT &&
-			    res->drop_reason == SKB_NOT_DROPPED_YET)
-				tcf_set_drop_reason(res, orig_reason);
+		if (err >= 0)
 			return err;
-		}
 	}
 
 	if (unlikely(n)) {
-		tcf_set_drop_reason(res, SKB_DROP_REASON_TC_ERROR);
+		tcf_set_drop_reason(skb,
+				    SKB_DROP_REASON_TC_COOKIE_ERROR);
 		return TC_ACT_SHOT;
 	}
 
@@ -1736,7 +1748,8 @@ reset:
 				       tp->chain->block->index,
 				       tp->prio & 0xffff,
 				       ntohs(tp->protocol));
-		tcf_set_drop_reason(res, SKB_DROP_REASON_TC_ERROR);
+		tcf_set_drop_reason(skb,
+				    SKB_DROP_REASON_TC_RECLASSIFY_LOOP);
 		return TC_ACT_SHOT;
 	}
 
@@ -1774,7 +1787,8 @@ int tcf_classify(struct sk_buff *skb,
 				n = tcf_exts_miss_cookie_lookup(ext->act_miss_cookie,
 								&act_index);
 				if (!n) {
-					tcf_set_drop_reason(res, SKB_DROP_REASON_TC_ERROR);
+					tcf_set_drop_reason(skb,
+							    SKB_DROP_REASON_TC_COOKIE_ERROR);
 					return TC_ACT_SHOT;
 				}
 
@@ -1785,7 +1799,9 @@ int tcf_classify(struct sk_buff *skb,
 
 			fchain = tcf_chain_lookup_rcu(block, chain);
 			if (!fchain) {
-				tcf_set_drop_reason(res, SKB_DROP_REASON_TC_ERROR);
+				tcf_set_drop_reason(skb,
+						    SKB_DROP_REASON_TC_CHAIN_NOTFOUND);
+
 				return TC_ACT_SHOT;
 			}
 
@@ -1807,10 +1823,9 @@ int tcf_classify(struct sk_buff *skb,
 
 			ext = tc_skb_ext_alloc(skb);
 			if (WARN_ON_ONCE(!ext)) {
-				tcf_set_drop_reason(res, SKB_DROP_REASON_TC_ERROR);
+				tcf_set_drop_reason(skb, SKB_DROP_REASON_NOMEM);
 				return TC_ACT_SHOT;
 			}
-
 			ext->chain = last_executed_chain;
 			ext->mru = cb->mru;
 			ext->post_ct = cb->post_ct;
@@ -2053,6 +2068,9 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb,
 	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
 	int err = 0;
 
+	if (!unicast && !rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC))
+		return 0;
+
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb)
 		return -ENOBUFS;
@@ -2075,13 +2093,16 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb,
 static int tfilter_del_notify(struct net *net, struct sk_buff *oskb,
 			      struct nlmsghdr *n, struct tcf_proto *tp,
 			      struct tcf_block *block, struct Qdisc *q,
-			      u32 parent, void *fh, bool unicast, bool *last,
-			      bool rtnl_held, struct netlink_ext_ack *extack)
+			      u32 parent, void *fh, bool *last, bool rtnl_held,
+			      struct netlink_ext_ack *extack)
 {
 	struct sk_buff *skb;
 	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
 	int err;
 
+	if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC))
+		return tp->ops->delete(tp, fh, last, rtnl_held, extack);
+
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb)
 		return -ENOBUFS;
@@ -2100,11 +2121,8 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb,
 		return err;
 	}
 
-	if (unicast)
-		err = rtnl_unicast(skb, net, portid);
-	else
-		err = rtnetlink_send(skb, net, portid, RTNLGRP_TC,
-				     n->nlmsg_flags & NLM_F_ECHO);
+	err = rtnetlink_send(skb, net, portid, RTNLGRP_TC,
+			     n->nlmsg_flags & NLM_F_ECHO);
 	if (err < 0)
 		NL_SET_ERR_MSG(extack, "Failed to send filter delete notification");
 
@@ -2499,9 +2517,8 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 	} else {
 		bool last;
 
-		err = tfilter_del_notify(net, skb, n, tp, block,
-					 q, parent, fh, false, &last,
-					 rtnl_held, extack);
+		err = tfilter_del_notify(net, skb, n, tp, block, q, parent, fh,
+					 &last, rtnl_held, extack);
 
 		if (err)
 			goto errout;
@@ -2732,6 +2749,7 @@ errout:
 }
 
 static const struct nla_policy tcf_tfilter_dump_policy[TCA_MAX + 1] = {
+	[TCA_CHAIN]      = { .type = NLA_U32 },
 	[TCA_DUMP_FLAGS] = NLA_POLICY_BITFIELD32(TCA_DUMP_FLAGS_TERSE),
 };
 
@@ -2906,6 +2924,9 @@ static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb,
 	struct sk_buff *skb;
 	int err = 0;
 
+	if (!unicast && !rtnl_notify_needed(net, flags, RTNLGRP_TC))
+		return 0;
+
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb)
 		return -ENOBUFS;
@@ -2929,12 +2950,15 @@ static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb,
 static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops,
 				  void *tmplt_priv, u32 chain_index,
 				  struct tcf_block *block, struct sk_buff *oskb,
-				  u32 seq, u16 flags, bool unicast)
+				  u32 seq, u16 flags)
 {
 	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
 	struct net *net = block->net;
 	struct sk_buff *skb;
 
+	if (!rtnl_notify_needed(net, flags, RTNLGRP_TC))
+		return 0;
+
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb)
 		return -ENOBUFS;
@@ -2945,9 +2969,6 @@ static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops,
 		return -EINVAL;
 	}
 
-	if (unicast)
-		return rtnl_unicast(skb, net, portid);
-
 	return rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO);
 }
 
@@ -3293,12 +3314,11 @@ int tcf_exts_validate_ex(struct net *net, struct tcf_proto *tp, struct nlattr **
 		if (exts->police && tb[exts->police]) {
 			struct tc_action_ops *a_o;
 
-			a_o = tc_action_load_ops(tb[exts->police], true,
-						 !(flags & TCA_ACT_FLAGS_NO_RTNL),
+			flags |= TCA_ACT_FLAGS_POLICE | TCA_ACT_FLAGS_BIND;
+			a_o = tc_action_load_ops(tb[exts->police], flags,
 						 extack);
 			if (IS_ERR(a_o))
 				return PTR_ERR(a_o);
-			flags |= TCA_ACT_FLAGS_POLICE | TCA_ACT_FLAGS_BIND;
 			act = tcf_action_init_1(net, tp, tb[exts->police],
 						rate_tlv, a_o, init_res, flags,
 						extack);
@@ -3309,7 +3329,7 @@ int tcf_exts_validate_ex(struct net *net, struct tcf_proto *tp, struct nlattr **
 			act->type = exts->type = TCA_OLD_COMPAT;
 			exts->actions[0] = act;
 			exts->nr_actions = 1;
-			tcf_idr_insert_many(exts->actions);
+			tcf_idr_insert_many(exts->actions, init_res);
 		} else if (exts->action && tb[exts->action]) {
 			int err;
 
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index d5bdfd4a7655..289e1755c26b 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -71,7 +71,7 @@ struct tc_u_hnode {
 	struct tc_u_hnode __rcu	*next;
 	u32			handle;
 	u32			prio;
-	int			refcnt;
+	refcount_t		refcnt;
 	unsigned int		divisor;
 	struct idr		handle_idr;
 	bool			is_root;
@@ -86,7 +86,7 @@ struct tc_u_hnode {
 struct tc_u_common {
 	struct tc_u_hnode __rcu	*hlist;
 	void			*ptr;
-	int			refcnt;
+	refcount_t		refcnt;
 	struct idr		handle_idr;
 	struct hlist_node	hnode;
 	long			knodes;
@@ -359,7 +359,7 @@ static int u32_init(struct tcf_proto *tp)
 	if (root_ht == NULL)
 		return -ENOBUFS;
 
-	root_ht->refcnt++;
+	refcount_set(&root_ht->refcnt, 1);
 	root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : 0x80000000;
 	root_ht->prio = tp->prio;
 	root_ht->is_root = true;
@@ -371,18 +371,20 @@ static int u32_init(struct tcf_proto *tp)
 			kfree(root_ht);
 			return -ENOBUFS;
 		}
+		refcount_set(&tp_c->refcnt, 1);
 		tp_c->ptr = key;
 		INIT_HLIST_NODE(&tp_c->hnode);
 		idr_init(&tp_c->handle_idr);
 
 		hlist_add_head(&tp_c->hnode, tc_u_hash(key));
+	} else {
+		refcount_inc(&tp_c->refcnt);
 	}
 
-	tp_c->refcnt++;
 	RCU_INIT_POINTER(root_ht->next, tp_c->hlist);
 	rcu_assign_pointer(tp_c->hlist, root_ht);
 
-	root_ht->refcnt++;
+	/* root_ht must be destroyed when tcf_proto is destroyed */
 	rcu_assign_pointer(tp->root, root_ht);
 	tp->data = tp_c;
 	return 0;
@@ -393,7 +395,7 @@ static void __u32_destroy_key(struct tc_u_knode *n)
 	struct tc_u_hnode *ht = rtnl_dereference(n->ht_down);
 
 	tcf_exts_destroy(&n->exts);
-	if (ht && --ht->refcnt == 0)
+	if (ht && refcount_dec_and_test(&ht->refcnt))
 		kfree(ht);
 	kfree(n);
 }
@@ -601,8 +603,6 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht,
 	struct tc_u_hnode __rcu **hn;
 	struct tc_u_hnode *phn;
 
-	WARN_ON(--ht->refcnt);
-
 	u32_clear_hnode(tp, ht, extack);
 
 	hn = &tp_c->hlist;
@@ -630,10 +630,10 @@ static void u32_destroy(struct tcf_proto *tp, bool rtnl_held,
 
 	WARN_ON(root_ht == NULL);
 
-	if (root_ht && --root_ht->refcnt == 1)
+	if (root_ht && refcount_dec_and_test(&root_ht->refcnt))
 		u32_destroy_hnode(tp, root_ht, extack);
 
-	if (--tp_c->refcnt == 0) {
+	if (refcount_dec_and_test(&tp_c->refcnt)) {
 		struct tc_u_hnode *ht;
 
 		hlist_del(&tp_c->hnode);
@@ -645,7 +645,7 @@ static void u32_destroy(struct tcf_proto *tp, bool rtnl_held,
 			/* u32_destroy_key() will later free ht for us, if it's
 			 * still referenced by some knode
 			 */
-			if (--ht->refcnt == 0)
+			if (refcount_dec_and_test(&ht->refcnt))
 				kfree_rcu(ht, rcu);
 		}
 
@@ -674,7 +674,7 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last,
 		return -EINVAL;
 	}
 
-	if (ht->refcnt == 1) {
+	if (refcount_dec_if_one(&ht->refcnt)) {
 		u32_destroy_hnode(tp, ht, extack);
 	} else {
 		NL_SET_ERR_MSG_MOD(extack, "Can not delete in-use filter");
@@ -682,7 +682,7 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last,
 	}
 
 out:
-	*last = tp_c->refcnt == 1 && tp_c->knodes == 0;
+	*last = refcount_read(&tp_c->refcnt) == 1 && tp_c->knodes == 0;
 	return ret;
 }
 
@@ -766,14 +766,14 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp,
 				NL_SET_ERR_MSG_MOD(extack, "Not linking to root node");
 				return -EINVAL;
 			}
-			ht_down->refcnt++;
+			refcount_inc(&ht_down->refcnt);
 		}
 
 		ht_old = rtnl_dereference(n->ht_down);
 		rcu_assign_pointer(n->ht_down, ht_down);
 
 		if (ht_old)
-			ht_old->refcnt--;
+			refcount_dec(&ht_old->refcnt);
 	}
 
 	if (ifindex >= 0)
@@ -852,7 +852,7 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp,
 
 	/* bump reference count as long as we hold pointer to structure */
 	if (ht)
-		ht->refcnt++;
+		refcount_inc(&ht->refcnt);
 
 	return new;
 }
@@ -932,7 +932,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 
 				ht_old = rtnl_dereference(n->ht_down);
 				if (ht_old)
-					ht_old->refcnt++;
+					refcount_inc(&ht_old->refcnt);
 			}
 			__u32_destroy_key(new);
 			return err;
@@ -980,7 +980,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 				return err;
 			}
 		}
-		ht->refcnt = 1;
+		refcount_set(&ht->refcnt, 1);
 		ht->divisor = divisor;
 		ht->handle = handle;
 		ht->prio = tp->prio;
diff --git a/net/sched/em_text.c b/net/sched/em_text.c
index 6f3c1fb2fb44..f176afb70559 100644
--- a/net/sched/em_text.c
+++ b/net/sched/em_text.c
@@ -97,8 +97,10 @@ retry:
 
 static void em_text_destroy(struct tcf_ematch *m)
 {
-	if (EM_TEXT_PRIV(m) && EM_TEXT_PRIV(m)->config)
+	if (EM_TEXT_PRIV(m) && EM_TEXT_PRIV(m)->config) {
 		textsearch_destroy(EM_TEXT_PRIV(m)->config);
+		kfree(EM_TEXT_PRIV(m));
+	}
 }
 
 static int em_text_dump(struct sk_buff *skb, struct tcf_ematch *m)
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index e9eaf637220e..36b025cc4fd2 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1003,6 +1003,32 @@ static bool tc_qdisc_dump_ignore(struct Qdisc *q, bool dump_invisible)
 	return false;
 }
 
+static int qdisc_get_notify(struct net *net, struct sk_buff *oskb,
+			    struct nlmsghdr *n, u32 clid, struct Qdisc *q,
+			    struct netlink_ext_ack *extack)
+{
+	struct sk_buff *skb;
+	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
+
+	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!skb)
+		return -ENOBUFS;
+
+	if (!tc_qdisc_dump_ignore(q, false)) {
+		if (tc_fill_qdisc(skb, q, clid, portid, n->nlmsg_seq, 0,
+				  RTM_NEWQDISC, extack) < 0)
+			goto err_out;
+	}
+
+	if (skb->len)
+		return rtnetlink_send(skb, net, portid, RTNLGRP_TC,
+				      n->nlmsg_flags & NLM_F_ECHO);
+
+err_out:
+	kfree_skb(skb);
+	return -EINVAL;
+}
+
 static int qdisc_notify(struct net *net, struct sk_buff *oskb,
 			struct nlmsghdr *n, u32 clid,
 			struct Qdisc *old, struct Qdisc *new,
@@ -1011,6 +1037,9 @@ static int qdisc_notify(struct net *net, struct sk_buff *oskb,
 	struct sk_buff *skb;
 	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
 
+	if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC))
+		return 0;
+
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb)
 		return -ENOBUFS;
@@ -1542,7 +1571,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
 		if (err != 0)
 			return err;
 	} else {
-		qdisc_notify(net, skb, n, clid, NULL, q, NULL);
+		qdisc_get_notify(net, skb, n, clid, q, NULL);
 	}
 	return 0;
 }
@@ -1936,6 +1965,9 @@ static int tclass_notify(struct net *net, struct sk_buff *oskb,
 	struct sk_buff *skb;
 	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
 
+	if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC))
+		return 0;
+
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb)
 		return -ENOBUFS;
@@ -1949,6 +1981,27 @@ static int tclass_notify(struct net *net, struct sk_buff *oskb,
 			      n->nlmsg_flags & NLM_F_ECHO);
 }
 
+static int tclass_get_notify(struct net *net, struct sk_buff *oskb,
+			     struct nlmsghdr *n, struct Qdisc *q,
+			     unsigned long cl, struct netlink_ext_ack *extack)
+{
+	struct sk_buff *skb;
+	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
+
+	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!skb)
+		return -ENOBUFS;
+
+	if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, RTM_NEWTCLASS,
+			   extack) < 0) {
+		kfree_skb(skb);
+		return -EINVAL;
+	}
+
+	return rtnetlink_send(skb, net, portid, RTNLGRP_TC,
+			      n->nlmsg_flags & NLM_F_ECHO);
+}
+
 static int tclass_del_notify(struct net *net,
 			     const struct Qdisc_class_ops *cops,
 			     struct sk_buff *oskb, struct nlmsghdr *n,
@@ -1962,14 +2015,18 @@ static int tclass_del_notify(struct net *net,
 	if (!cops->delete)
 		return -EOPNOTSUPP;
 
-	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
-	if (!skb)
-		return -ENOBUFS;
+	if (rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) {
+		skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+		if (!skb)
+			return -ENOBUFS;
 
-	if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0,
-			   RTM_DELTCLASS, extack) < 0) {
-		kfree_skb(skb);
-		return -EINVAL;
+		if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0,
+				   RTM_DELTCLASS, extack) < 0) {
+			kfree_skb(skb);
+			return -EINVAL;
+		}
+	} else {
+		skb = NULL;
 	}
 
 	err = cops->delete(q, cl, extack);
@@ -1978,8 +2035,8 @@ static int tclass_del_notify(struct net *net,
 		return err;
 	}
 
-	err = rtnetlink_send(skb, net, portid, RTNLGRP_TC,
-			     n->nlmsg_flags & NLM_F_ECHO);
+	err = rtnetlink_maybe_send(skb, net, portid, RTNLGRP_TC,
+				   n->nlmsg_flags & NLM_F_ECHO);
 	return err;
 }
 
@@ -2174,7 +2231,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n,
 			tc_bind_tclass(q, portid, clid, 0);
 			goto out;
 		case RTM_GETTCLASS:
-			err = tclass_notify(net, skb, n, q, cl, RTM_NEWTCLASS, extack);
+			err = tclass_get_notify(net, skb, n, q, cl, extack);
 			goto out;
 		default:
 			err = -EINVAL;
diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index 9a0b85190a2c..beece8e82c23 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -57,6 +57,8 @@
 #include <linux/string.h>
 #include <linux/errno.h>
 #include <linux/skbuff.h>
+#include <linux/units.h>
+
 #include <net/netevent.h>
 #include <net/netlink.h>
 #include <net/sch_generic.h>
@@ -65,8 +67,6 @@
 static LIST_HEAD(cbs_list);
 static DEFINE_SPINLOCK(cbs_list_lock);
 
-#define BYTES_PER_KBIT (1000LL / 8)
-
 struct cbs_sched_data {
 	bool offload;
 	int queue;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 4195a4bc26ca..9b3e9262040b 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -522,8 +522,9 @@ static void dev_watchdog(struct timer_list *t)
 
 			if (unlikely(timedout_ms)) {
 				trace_net_dev_xmit_timeout(dev, i);
-				WARN_ONCE(1, "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out %u ms\n",
-					  dev->name, netdev_drivername(dev), i, timedout_ms);
+				netdev_crit(dev, "NETDEV WATCHDOG: CPU: %d: transmit queue %u timed out %u ms\n",
+					    raw_smp_processor_id(),
+					    i, timedout_ms);
 				netif_freeze_queues(dev);
 				dev->netdev_ops->ndo_tx_timeout(dev, i);
 				netif_unfreeze_queues(dev);
@@ -1050,6 +1051,7 @@ static void qdisc_free_cb(struct rcu_head *head)
 static void __qdisc_destroy(struct Qdisc *qdisc)
 {
 	const struct Qdisc_ops  *ops = qdisc->ops;
+	struct net_device *dev = qdisc_dev(qdisc);
 
 #ifdef CONFIG_NET_SCHED
 	qdisc_hash_del(qdisc);
@@ -1060,11 +1062,12 @@ static void __qdisc_destroy(struct Qdisc *qdisc)
 
 	qdisc_reset(qdisc);
 
+
 	if (ops->destroy)
 		ops->destroy(qdisc);
 
 	module_put(ops->owner);
-	netdev_put(qdisc_dev(qdisc), &qdisc->dev_tracker);
+	netdev_put(dev, &qdisc->dev_tracker);
 
 	trace_qdisc_destroy(qdisc);
 
diff --git a/net/sctp/diag.c b/net/sctp/diag.c
index c3d6b92dd386..eb05131ff1dd 100644
--- a/net/sctp/diag.c
+++ b/net/sctp/diag.c
@@ -527,4 +527,5 @@ static void __exit sctp_diag_exit(void)
 module_init(sctp_diag_init);
 module_exit(sctp_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SCTP socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-132);
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 7f89e43154c0..6b9fcdb0952a 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -2099,6 +2099,13 @@ static int sctp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	pr_debug("%s: sk:%p, msghdr:%p, len:%zd, flags:0x%x, addr_len:%p)\n",
 		 __func__, sk, msg, len, flags, addr_len);
 
+	if (unlikely(flags & MSG_ERRQUEUE))
+		return inet_recv_error(sk, msg, len, addr_len);
+
+	if (sk_can_busy_loop(sk) &&
+	    skb_queue_empty_lockless(&sk->sk_receive_queue))
+		sk_busy_loop(sk, flags & MSG_DONTWAIT);
+
 	lock_sock(sk);
 
 	if (sctp_style(sk, TCP) && !sctp_sstate(sk, ESTABLISHED) &&
@@ -9043,12 +9050,6 @@ struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags, int *err)
 		if (sk->sk_shutdown & RCV_SHUTDOWN)
 			break;
 
-		if (sk_can_busy_loop(sk)) {
-			sk_busy_loop(sk, flags & MSG_DONTWAIT);
-
-			if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
-				continue;
-		}
 
 		/* User doesn't want to wait.  */
 		error = -EAGAIN;
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index da97f946b79b..a2cb30af46cb 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -598,8 +598,12 @@ static int smcr_clnt_conf_first_link(struct smc_sock *smc)
 	struct smc_llc_qentry *qentry;
 	int rc;
 
-	/* receive CONFIRM LINK request from server over RoCE fabric */
-	qentry = smc_llc_wait(link->lgr, NULL, SMC_LLC_WAIT_TIME,
+	/* Receive CONFIRM LINK request from server over RoCE fabric.
+	 * Increasing the client's timeout by twice as much as the server's
+	 * timeout by default can temporarily avoid decline messages of
+	 * both sides crossing or colliding
+	 */
+	qentry = smc_llc_wait(link->lgr, NULL, 2 * SMC_LLC_WAIT_TIME,
 			      SMC_LLC_CONFIRM_LINK);
 	if (!qentry) {
 		struct smc_clc_msg_decline dclc;
@@ -673,8 +677,6 @@ static bool smc_isascii(char *hostname)
 static void smc_conn_save_peer_info_fce(struct smc_sock *smc,
 					struct smc_clc_msg_accept_confirm *clc)
 {
-	struct smc_clc_msg_accept_confirm_v2 *clc_v2 =
-		(struct smc_clc_msg_accept_confirm_v2 *)clc;
 	struct smc_clc_first_contact_ext *fce;
 	int clc_v2_len;
 
@@ -683,17 +685,15 @@ static void smc_conn_save_peer_info_fce(struct smc_sock *smc,
 		return;
 
 	if (smc->conn.lgr->is_smcd) {
-		memcpy(smc->conn.lgr->negotiated_eid, clc_v2->d1.eid,
+		memcpy(smc->conn.lgr->negotiated_eid, clc->d1.eid,
 		       SMC_MAX_EID_LEN);
-		clc_v2_len = offsetofend(struct smc_clc_msg_accept_confirm_v2,
-					 d1);
+		clc_v2_len = offsetofend(struct smc_clc_msg_accept_confirm, d1);
 	} else {
-		memcpy(smc->conn.lgr->negotiated_eid, clc_v2->r1.eid,
+		memcpy(smc->conn.lgr->negotiated_eid, clc->r1.eid,
 		       SMC_MAX_EID_LEN);
-		clc_v2_len = offsetofend(struct smc_clc_msg_accept_confirm_v2,
-					 r1);
+		clc_v2_len = offsetofend(struct smc_clc_msg_accept_confirm, r1);
 	}
-	fce = (struct smc_clc_first_contact_ext *)(((u8 *)clc_v2) + clc_v2_len);
+	fce = (struct smc_clc_first_contact_ext *)(((u8 *)clc) + clc_v2_len);
 	smc->conn.lgr->peer_os = fce->os_type;
 	smc->conn.lgr->peer_smc_release = fce->release;
 	if (smc_isascii(fce->hostname))
@@ -719,7 +719,7 @@ static void smcd_conn_save_peer_info(struct smc_sock *smc,
 	int bufsize = smc_uncompress_bufsize(clc->d0.dmbe_size);
 
 	smc->conn.peer_rmbe_idx = clc->d0.dmbe_idx;
-	smc->conn.peer_token = clc->d0.token;
+	smc->conn.peer_token = ntohll(clc->d0.token);
 	/* msg header takes up space in the buffer */
 	smc->conn.peer_rmbe_size = bufsize - sizeof(struct smcd_cdc_msg);
 	atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size);
@@ -1044,7 +1044,8 @@ static int smc_find_ism_v2_device_clnt(struct smc_sock *smc,
 {
 	int rc = SMC_CLC_DECL_NOSMCDDEV;
 	struct smcd_dev *smcd;
-	int i = 1;
+	int i = 1, entry = 1;
+	bool is_virtual;
 	u16 chid;
 
 	if (smcd_indicated(ini->smc_type_v1))
@@ -1056,14 +1057,23 @@ static int smc_find_ism_v2_device_clnt(struct smc_sock *smc,
 		chid = smc_ism_get_chid(smcd);
 		if (!smc_find_ism_v2_is_unique_chid(chid, ini, i))
 			continue;
+		is_virtual = __smc_ism_is_virtual(chid);
 		if (!smc_pnet_is_pnetid_set(smcd->pnetid) ||
 		    smc_pnet_is_ndev_pnetid(sock_net(&smc->sk), smcd->pnetid)) {
+			if (is_virtual && entry == SMCD_CLC_MAX_V2_GID_ENTRIES)
+				/* It's the last GID-CHID entry left in CLC
+				 * Proposal SMC-Dv2 extension, but a virtual
+				 * ISM device will take two entries. So give
+				 * up it and try the next potential ISM device.
+				 */
+				continue;
 			ini->ism_dev[i] = smcd;
 			ini->ism_chid[i] = chid;
 			ini->is_smcd = true;
 			rc = 0;
 			i++;
-			if (i > SMC_MAX_ISM_DEVS)
+			entry = is_virtual ? entry + 2 : entry + 1;
+			if (entry > SMCD_CLC_MAX_V2_GID_ENTRIES)
 				break;
 		}
 	}
@@ -1145,13 +1155,13 @@ static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc,
 }
 
 #define SMC_CLC_MAX_ACCEPT_LEN \
-	(sizeof(struct smc_clc_msg_accept_confirm_v2) + \
+	(sizeof(struct smc_clc_msg_accept_confirm) + \
 	 sizeof(struct smc_clc_first_contact_ext_v2x) + \
 	 sizeof(struct smc_clc_msg_trail))
 
 /* CLC handshake during connect */
 static int smc_connect_clc(struct smc_sock *smc,
-			   struct smc_clc_msg_accept_confirm_v2 *aclc2,
+			   struct smc_clc_msg_accept_confirm *aclc,
 			   struct smc_init_info *ini)
 {
 	int rc = 0;
@@ -1161,7 +1171,7 @@ static int smc_connect_clc(struct smc_sock *smc,
 	if (rc)
 		return rc;
 	/* receive SMC Accept CLC message */
-	return smc_clc_wait_msg(smc, aclc2, SMC_CLC_MAX_ACCEPT_LEN,
+	return smc_clc_wait_msg(smc, aclc, SMC_CLC_MAX_ACCEPT_LEN,
 				SMC_CLC_ACCEPT, CLC_WAIT_TIME);
 }
 
@@ -1197,10 +1207,8 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc,
 				       struct smc_clc_msg_accept_confirm *aclc,
 				       struct smc_init_info *ini)
 {
-	struct smc_clc_msg_accept_confirm_v2 *clc_v2 =
-		(struct smc_clc_msg_accept_confirm_v2 *)aclc;
 	struct smc_clc_first_contact_ext *fce =
-		smc_get_clc_first_contact_ext(clc_v2, false);
+		smc_get_clc_first_contact_ext(aclc, false);
 	struct net *net = sock_net(&smc->sk);
 	int rc;
 
@@ -1323,10 +1331,7 @@ static int smc_connect_rdma(struct smc_sock *smc,
 	}
 
 	if (aclc->hdr.version > SMC_V1) {
-		struct smc_clc_msg_accept_confirm_v2 *clc_v2 =
-			(struct smc_clc_msg_accept_confirm_v2 *)aclc;
-
-		eid = clc_v2->r1.eid;
+		eid = aclc->r1.eid;
 		if (ini->first_contact_local)
 			smc_fill_gid_list(link->lgr, &ini->smcrv2.gidlist,
 					  link->smcibdev, link->gid);
@@ -1367,7 +1372,7 @@ connect_abort:
  * Determine from the CHID of the received CLC ACCEPT the ISM device chosen.
  */
 static int
-smc_v2_determine_accepted_chid(struct smc_clc_msg_accept_confirm_v2 *aclc,
+smc_v2_determine_accepted_chid(struct smc_clc_msg_accept_confirm *aclc,
 			       struct smc_init_info *ini)
 {
 	int i;
@@ -1394,12 +1399,9 @@ static int smc_connect_ism(struct smc_sock *smc,
 	ini->first_contact_peer = aclc->hdr.typev2 & SMC_FIRST_CONTACT_MASK;
 
 	if (aclc->hdr.version == SMC_V2) {
-		struct smc_clc_msg_accept_confirm_v2 *aclc_v2 =
-			(struct smc_clc_msg_accept_confirm_v2 *)aclc;
-
 		if (ini->first_contact_peer) {
 			struct smc_clc_first_contact_ext *fce =
-				smc_get_clc_first_contact_ext(aclc_v2, true);
+				smc_get_clc_first_contact_ext(aclc, true);
 
 			ini->release_nr = fce->release;
 			rc = smc_clc_clnt_v2x_features_validate(fce, ini);
@@ -1407,11 +1409,16 @@ static int smc_connect_ism(struct smc_sock *smc,
 				return rc;
 		}
 
-		rc = smc_v2_determine_accepted_chid(aclc_v2, ini);
+		rc = smc_v2_determine_accepted_chid(aclc, ini);
 		if (rc)
 			return rc;
+
+		if (__smc_ism_is_virtual(ini->ism_chid[ini->ism_selected]))
+			ini->ism_peer_gid[ini->ism_selected].gid_ext =
+						ntohll(aclc->d1.gid_ext);
+		/* for non-virtual ISM devices, peer gid_ext remains 0. */
 	}
-	ini->ism_peer_gid[ini->ism_selected] = aclc->d0.gid;
+	ini->ism_peer_gid[ini->ism_selected].gid = ntohll(aclc->d0.gid);
 
 	/* there is only one lgr role for SMC-D; use server lock */
 	mutex_lock(&smc_server_lgr_pending);
@@ -1433,12 +1440,8 @@ static int smc_connect_ism(struct smc_sock *smc,
 	smc_rx_init(smc);
 	smc_tx_init(smc);
 
-	if (aclc->hdr.version > SMC_V1) {
-		struct smc_clc_msg_accept_confirm_v2 *clc_v2 =
-			(struct smc_clc_msg_accept_confirm_v2 *)aclc;
-
-		eid = clc_v2->d1.eid;
-	}
+	if (aclc->hdr.version > SMC_V1)
+		eid = aclc->d1.eid;
 
 	rc = smc_clc_send_confirm(smc, ini->first_contact_local,
 				  aclc->hdr.version, eid, ini);
@@ -1489,7 +1492,6 @@ static int smc_connect_check_aclc(struct smc_init_info *ini,
 static int __smc_connect(struct smc_sock *smc)
 {
 	u8 version = smc_ism_is_v2_capable() ? SMC_V2 : SMC_V1;
-	struct smc_clc_msg_accept_confirm_v2 *aclc2;
 	struct smc_clc_msg_accept_confirm *aclc;
 	struct smc_init_info *ini = NULL;
 	u8 *buf = NULL;
@@ -1537,11 +1539,10 @@ static int __smc_connect(struct smc_sock *smc)
 		rc = SMC_CLC_DECL_MEM;
 		goto fallback;
 	}
-	aclc2 = (struct smc_clc_msg_accept_confirm_v2 *)buf;
-	aclc = (struct smc_clc_msg_accept_confirm *)aclc2;
+	aclc = (struct smc_clc_msg_accept_confirm *)buf;
 
 	/* perform CLC handshake */
-	rc = smc_connect_clc(smc, aclc2, ini);
+	rc = smc_connect_clc(smc, aclc, ini);
 	if (rc) {
 		/* -EAGAIN on timeout, see tcp_recvmsg() */
 		if (rc == -EAGAIN) {
@@ -2102,7 +2103,8 @@ static bool smc_is_already_selected(struct smcd_dev *smcd,
 
 /* check for ISM devices matching proposed ISM devices */
 static void smc_check_ism_v2_match(struct smc_init_info *ini,
-				   u16 proposed_chid, u64 proposed_gid,
+				   u16 proposed_chid,
+				   struct smcd_gid *proposed_gid,
 				   unsigned int *matches)
 {
 	struct smcd_dev *smcd;
@@ -2114,7 +2116,11 @@ static void smc_check_ism_v2_match(struct smc_init_info *ini,
 			continue;
 		if (smc_ism_get_chid(smcd) == proposed_chid &&
 		    !smc_ism_cantalk(proposed_gid, ISM_RESERVED_VLANID, smcd)) {
-			ini->ism_peer_gid[*matches] = proposed_gid;
+			ini->ism_peer_gid[*matches].gid = proposed_gid->gid;
+			if (__smc_ism_is_virtual(proposed_chid))
+				ini->ism_peer_gid[*matches].gid_ext =
+							proposed_gid->gid_ext;
+				/* non-virtual ISM's peer gid_ext remains 0. */
 			ini->ism_dev[*matches] = smcd;
 			(*matches)++;
 			break;
@@ -2136,9 +2142,11 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc,
 	struct smc_clc_v2_extension *smc_v2_ext;
 	struct smc_clc_msg_smcd *pclc_smcd;
 	unsigned int matches = 0;
+	struct smcd_gid smcd_gid;
 	u8 smcd_version;
 	u8 *eid = NULL;
 	int i, rc;
+	u16 chid;
 
 	if (!(ini->smcd_version & SMC_V2) || !smcd_indicated(ini->smc_type_v2))
 		goto not_found;
@@ -2148,18 +2156,35 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc,
 	smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext);
 
 	mutex_lock(&smcd_dev_list.mutex);
-	if (pclc_smcd->ism.chid)
+	if (pclc_smcd->ism.chid) {
 		/* check for ISM device matching proposed native ISM device */
+		smcd_gid.gid = ntohll(pclc_smcd->ism.gid);
+		smcd_gid.gid_ext = 0;
 		smc_check_ism_v2_match(ini, ntohs(pclc_smcd->ism.chid),
-				       ntohll(pclc_smcd->ism.gid), &matches);
-	for (i = 1; i <= smc_v2_ext->hdr.ism_gid_cnt; i++) {
+				       &smcd_gid, &matches);
+	}
+	for (i = 0; i < smc_v2_ext->hdr.ism_gid_cnt; i++) {
 		/* check for ISM devices matching proposed non-native ISM
 		 * devices
 		 */
-		smc_check_ism_v2_match(ini,
-				       ntohs(smcd_v2_ext->gidchid[i - 1].chid),
-				       ntohll(smcd_v2_ext->gidchid[i - 1].gid),
-				       &matches);
+		smcd_gid.gid = ntohll(smcd_v2_ext->gidchid[i].gid);
+		smcd_gid.gid_ext = 0;
+		chid = ntohs(smcd_v2_ext->gidchid[i].chid);
+		if (__smc_ism_is_virtual(chid)) {
+			if ((i + 1) == smc_v2_ext->hdr.ism_gid_cnt ||
+			    chid != ntohs(smcd_v2_ext->gidchid[i + 1].chid))
+				/* each virtual ISM device takes two GID-CHID
+				 * entries and CHID of the second entry repeats
+				 * that of the first entry.
+				 *
+				 * So check if the next GID-CHID entry exists
+				 * and both two entries' CHIDs are the same.
+				 */
+				continue;
+			smcd_gid.gid_ext =
+				ntohll(smcd_v2_ext->gidchid[++i].gid);
+		}
+		smc_check_ism_v2_match(ini, chid, &smcd_gid, &matches);
 	}
 	mutex_unlock(&smcd_dev_list.mutex);
 
@@ -2208,7 +2233,8 @@ static void smc_find_ism_v1_device_serv(struct smc_sock *new_smc,
 	if (!(ini->smcd_version & SMC_V1) || !smcd_indicated(ini->smc_type_v1))
 		goto not_found;
 	ini->is_smcd = true; /* prepare ISM check */
-	ini->ism_peer_gid[0] = ntohll(pclc_smcd->ism.gid);
+	ini->ism_peer_gid[0].gid = ntohll(pclc_smcd->ism.gid);
+	ini->ism_peer_gid[0].gid_ext = 0;
 	rc = smc_find_ism_device(new_smc, ini);
 	if (rc)
 		goto not_found;
@@ -2457,7 +2483,7 @@ static void smc_listen_work(struct work_struct *work)
 	if (rc)
 		goto out_decl;
 
-	rc = smc_clc_srv_v2x_features_validate(pclc, ini);
+	rc = smc_clc_srv_v2x_features_validate(new_smc, pclc, ini);
 	if (rc)
 		goto out_decl;
 
diff --git a/net/smc/smc.h b/net/smc/smc.h
index e377980b8414..df64efd2dee8 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -29,9 +29,6 @@
 #define SMCPROTO_SMC		0	/* SMC protocol, IPv4 */
 #define SMCPROTO_SMC6		1	/* SMC protocol, IPv6 */
 
-#define SMC_MAX_ISM_DEVS	8	/* max # of proposed non-native ISM
-					 * devices
-					 */
 #define SMC_AUTOCORKING_DEFAULT_SIZE	0x10000	/* 64K by default */
 
 extern struct proto smc_proto;
@@ -58,6 +55,13 @@ enum smc_state {		/* possible states of an SMC socket */
 	SMC_PROCESSABORT	= 27,
 };
 
+enum smc_supplemental_features {
+	SMC_SPF_VIRT_ISM_DEV	= 0,
+};
+
+#define SMC_FEATURE_MASK \
+	(BIT(SMC_SPF_VIRT_ISM_DEV))
+
 struct smc_link_group;
 
 struct smc_wr_rx_hdr {	/* common prefix part of LLC and CDC to demultiplex */
@@ -196,7 +200,6 @@ struct smc_connection {
 						 * - dec on polled tx cqe
 						 */
 	wait_queue_head_t	cdc_pend_tx_wq; /* wakeup on no cdc_pend_tx_wr*/
-	atomic_t		tx_pushing;     /* nr_threads trying tx push */
 	struct delayed_work	tx_work;	/* retry of smc_cdc_msg_send */
 	u32			tx_off;		/* base offset in peer rmb */
 
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 8deb46c28f1d..9a13709bea1c 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -155,10 +155,12 @@ static int smc_clc_ueid_remove(char *ueid)
 			rc = 0;
 		}
 	}
+#if IS_ENABLED(CONFIG_S390)
 	if (!rc && !smc_clc_eid_table.ueid_cnt) {
 		smc_clc_eid_table.seid_enabled = 1;
 		rc = -EAGAIN;	/* indicate success and enabling of seid */
 	}
+#endif
 	write_unlock(&smc_clc_eid_table.lock);
 	return rc;
 }
@@ -273,22 +275,30 @@ err:
 
 int smc_nl_enable_seid(struct sk_buff *skb, struct genl_info *info)
 {
+#if IS_ENABLED(CONFIG_S390)
 	write_lock(&smc_clc_eid_table.lock);
 	smc_clc_eid_table.seid_enabled = 1;
 	write_unlock(&smc_clc_eid_table.lock);
 	return 0;
+#else
+	return -EOPNOTSUPP;
+#endif
 }
 
 int smc_nl_disable_seid(struct sk_buff *skb, struct genl_info *info)
 {
 	int rc = 0;
 
+#if IS_ENABLED(CONFIG_S390)
 	write_lock(&smc_clc_eid_table.lock);
 	if (!smc_clc_eid_table.ueid_cnt)
 		rc = -ENOENT;
 	else
 		smc_clc_eid_table.seid_enabled = 0;
 	write_unlock(&smc_clc_eid_table.lock);
+#else
+	rc = -EOPNOTSUPP;
+#endif
 	return rc;
 }
 
@@ -377,9 +387,9 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc)
 
 /* check arriving CLC accept or confirm */
 static bool
-smc_clc_msg_acc_conf_valid(struct smc_clc_msg_accept_confirm_v2 *clc_v2)
+smc_clc_msg_acc_conf_valid(struct smc_clc_msg_accept_confirm *clc)
 {
-	struct smc_clc_msg_hdr *hdr = &clc_v2->hdr;
+	struct smc_clc_msg_hdr *hdr = &clc->hdr;
 
 	if (hdr->typev1 != SMC_TYPE_R && hdr->typev1 != SMC_TYPE_D)
 		return false;
@@ -418,15 +428,16 @@ smc_clc_msg_decl_valid(struct smc_clc_msg_decline *dclc)
 	return true;
 }
 
-static int smc_clc_fill_fce(struct smc_clc_first_contact_ext_v2x *fce,
-			    struct smc_init_info *ini)
+static int smc_clc_fill_fce_v2x(struct smc_clc_first_contact_ext_v2x *fce_v2x,
+				struct smc_init_info *ini)
 {
-	int ret = sizeof(*fce);
+	int ret = sizeof(*fce_v2x);
 
-	memset(fce, 0, sizeof(*fce));
-	fce->fce_v2_base.os_type = SMC_CLC_OS_LINUX;
-	fce->fce_v2_base.release = ini->release_nr;
-	memcpy(fce->fce_v2_base.hostname, smc_hostname, sizeof(smc_hostname));
+	memset(fce_v2x, 0, sizeof(*fce_v2x));
+	fce_v2x->fce_v2_base.os_type = SMC_CLC_OS_LINUX;
+	fce_v2x->fce_v2_base.release = ini->release_nr;
+	memcpy(fce_v2x->fce_v2_base.hostname,
+	       smc_hostname, sizeof(smc_hostname));
 	if (ini->is_smcd && ini->release_nr < SMC_RELEASE_1) {
 		ret = sizeof(struct smc_clc_first_contact_ext);
 		goto out;
@@ -434,9 +445,10 @@ static int smc_clc_fill_fce(struct smc_clc_first_contact_ext_v2x *fce,
 
 	if (ini->release_nr >= SMC_RELEASE_1) {
 		if (!ini->is_smcd) {
-			fce->max_conns = ini->max_conns;
-			fce->max_links = ini->max_links;
+			fce_v2x->max_conns = ini->max_conns;
+			fce_v2x->max_links = ini->max_links;
 		}
+		fce_v2x->feature_mask = htons(ini->feature_mask);
 	}
 
 out:
@@ -448,7 +460,7 @@ out:
  */
 static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm, bool check_trl)
 {
-	struct smc_clc_msg_accept_confirm_v2 *clc_v2;
+	struct smc_clc_msg_accept_confirm *clc;
 	struct smc_clc_msg_proposal *pclc;
 	struct smc_clc_msg_decline *dclc;
 	struct smc_clc_msg_trail *trl;
@@ -466,12 +478,11 @@ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm, bool check_trl)
 		break;
 	case SMC_CLC_ACCEPT:
 	case SMC_CLC_CONFIRM:
-		clc_v2 = (struct smc_clc_msg_accept_confirm_v2 *)clcm;
-		if (!smc_clc_msg_acc_conf_valid(clc_v2))
+		clc = (struct smc_clc_msg_accept_confirm *)clcm;
+		if (!smc_clc_msg_acc_conf_valid(clc))
 			return false;
 		trl = (struct smc_clc_msg_trail *)
-			((u8 *)clc_v2 + ntohs(clc_v2->hdr.length) -
-							sizeof(*trl));
+			((u8 *)clc + ntohs(clc->hdr.length) - sizeof(*trl));
 		break;
 	case SMC_CLC_DECLINE:
 		dclc = (struct smc_clc_msg_decline *)clcm;
@@ -824,6 +835,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
 	struct smc_clc_smcd_gid_chid *gidchids;
 	struct smc_clc_msg_proposal_area *pclc;
 	struct smc_clc_ipv6_prefix *ipv6_prfx;
+	struct net *net = sock_net(&smc->sk);
 	struct smc_clc_v2_extension *v2_ext;
 	struct smc_clc_msg_smcd *pclc_smcd;
 	struct smc_clc_msg_trail *trl;
@@ -881,11 +893,13 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
 		       ETH_ALEN);
 	}
 	if (smcd_indicated(ini->smc_type_v1)) {
+		struct smcd_gid smcd_gid;
+
 		/* add SMC-D specifics */
 		if (ini->ism_dev[0]) {
 			smcd = ini->ism_dev[0];
-			pclc_smcd->ism.gid =
-				htonll(smcd->ops->get_local_gid(smcd));
+			smcd->ops->get_local_gid(smcd, &smcd_gid);
+			pclc_smcd->ism.gid = htonll(smcd_gid.gid);
 			pclc_smcd->ism.chid =
 				htons(smc_ism_get_chid(ini->ism_dev[0]));
 		}
@@ -906,6 +920,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
 		pclc_smcd->v2_ext_offset = htons(v2_ext_offset);
 		plen += sizeof(*v2_ext);
 
+		v2_ext->feature_mask = htons(SMC_FEATURE_MASK);
 		read_lock(&smc_clc_eid_table.lock);
 		v2_ext->hdr.eid_cnt = smc_clc_eid_table.ueid_cnt;
 		plen += smc_clc_eid_table.ueid_cnt * SMC_MAX_EID_LEN;
@@ -917,10 +932,11 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
 		read_unlock(&smc_clc_eid_table.lock);
 	}
 	if (smcd_indicated(ini->smc_type_v2)) {
+		struct smcd_gid smcd_gid;
 		u8 *eid = NULL;
+		int entry = 0;
 
 		v2_ext->hdr.flag.seid = smc_clc_eid_table.seid_enabled;
-		v2_ext->hdr.ism_gid_cnt = ini->ism_offered_cnt;
 		v2_ext->hdr.smcd_v2_ext_offset = htons(sizeof(*v2_ext) -
 				offsetofend(struct smc_clnt_opts_area_hdr,
 					    smcd_v2_ext_offset) +
@@ -932,19 +948,31 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
 		if (ini->ism_offered_cnt) {
 			for (i = 1; i <= ini->ism_offered_cnt; i++) {
 				smcd = ini->ism_dev[i];
-				gidchids[i - 1].gid =
-					htonll(smcd->ops->get_local_gid(smcd));
-				gidchids[i - 1].chid =
+				smcd->ops->get_local_gid(smcd, &smcd_gid);
+				gidchids[entry].chid =
 					htons(smc_ism_get_chid(ini->ism_dev[i]));
+				gidchids[entry].gid = htonll(smcd_gid.gid);
+				if (smc_ism_is_virtual(smcd)) {
+					/* a virtual ISM device takes two
+					 * entries. CHID of the second entry
+					 * repeats that of the first entry.
+					 */
+					gidchids[entry + 1].chid =
+						gidchids[entry].chid;
+					gidchids[entry + 1].gid =
+						htonll(smcd_gid.gid_ext);
+					entry++;
+				}
+				entry++;
 			}
-			plen += ini->ism_offered_cnt *
-				sizeof(struct smc_clc_smcd_gid_chid);
+			plen += entry * sizeof(struct smc_clc_smcd_gid_chid);
 		}
+		v2_ext->hdr.ism_gid_cnt = entry;
 	}
 	if (smcr_indicated(ini->smc_type_v2)) {
 		memcpy(v2_ext->roce, ini->smcrv2.ib_gid_v2, SMC_GID_SIZE);
-		v2_ext->max_conns = SMC_CONN_PER_LGR_PREFER;
-		v2_ext->max_links = SMC_LINKS_PER_LGR_MAX_PREFER;
+		v2_ext->max_conns = net->smc.sysctl_max_conns_per_lgr;
+		v2_ext->max_links = net->smc.sysctl_max_links_per_lgr;
 	}
 
 	pclc_base->hdr.length = htons(plen);
@@ -975,7 +1003,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
 			vec[i++].iov_len = sizeof(*smcd_v2_ext);
 			if (ini->ism_offered_cnt) {
 				vec[i].iov_base = gidchids;
-				vec[i++].iov_len = ini->ism_offered_cnt *
+				vec[i++].iov_len = v2_ext->hdr.ism_gid_cnt *
 					sizeof(struct smc_clc_smcd_gid_chid);
 			}
 		}
@@ -996,110 +1024,143 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
 	return reason_code;
 }
 
+static void
+smcd_clc_prep_confirm_accept(struct smc_connection *conn,
+			     struct smc_clc_msg_accept_confirm *clc,
+			     int first_contact, u8 version,
+			     u8 *eid, struct smc_init_info *ini,
+			     int *fce_len,
+			     struct smc_clc_first_contact_ext_v2x *fce_v2x,
+			     struct smc_clc_msg_trail *trl)
+{
+	struct smcd_dev *smcd = conn->lgr->smcd;
+	struct smcd_gid smcd_gid;
+	u16 chid;
+	int len;
+
+	/* SMC-D specific settings */
+	memcpy(clc->hdr.eyecatcher, SMCD_EYECATCHER,
+	       sizeof(SMCD_EYECATCHER));
+	smcd->ops->get_local_gid(smcd, &smcd_gid);
+	clc->hdr.typev1 = SMC_TYPE_D;
+	clc->d0.gid = htonll(smcd_gid.gid);
+	clc->d0.token = htonll(conn->rmb_desc->token);
+	clc->d0.dmbe_size = conn->rmbe_size_comp;
+	clc->d0.dmbe_idx = 0;
+	memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE);
+	if (version == SMC_V1) {
+		clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN);
+	} else {
+		chid = smc_ism_get_chid(smcd);
+		clc->d1.chid = htons(chid);
+		if (eid && eid[0])
+			memcpy(clc->d1.eid, eid, SMC_MAX_EID_LEN);
+		if (__smc_ism_is_virtual(chid))
+			clc->d1.gid_ext = htonll(smcd_gid.gid_ext);
+		len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2;
+		if (first_contact) {
+			*fce_len = smc_clc_fill_fce_v2x(fce_v2x, ini);
+			len += *fce_len;
+		}
+		clc->hdr.length = htons(len);
+	}
+	memcpy(trl->eyecatcher, SMCD_EYECATCHER,
+	       sizeof(SMCD_EYECATCHER));
+}
+
+static void
+smcr_clc_prep_confirm_accept(struct smc_connection *conn,
+			     struct smc_clc_msg_accept_confirm *clc,
+			     int first_contact, u8 version,
+			     u8 *eid, struct smc_init_info *ini,
+			     int *fce_len,
+			     struct smc_clc_first_contact_ext_v2x *fce_v2x,
+			     struct smc_clc_fce_gid_ext *gle,
+			     struct smc_clc_msg_trail *trl)
+{
+	struct smc_link *link = conn->lnk;
+	int len;
+
+	/* SMC-R specific settings */
+	memcpy(clc->hdr.eyecatcher, SMC_EYECATCHER,
+	       sizeof(SMC_EYECATCHER));
+	clc->hdr.typev1 = SMC_TYPE_R;
+	memcpy(clc->r0.lcl.id_for_peer, local_systemid,
+	       sizeof(local_systemid));
+	memcpy(&clc->r0.lcl.gid, link->gid, SMC_GID_SIZE);
+	memcpy(&clc->r0.lcl.mac, &link->smcibdev->mac[link->ibport - 1],
+	       ETH_ALEN);
+	hton24(clc->r0.qpn, link->roce_qp->qp_num);
+	clc->r0.rmb_rkey =
+		htonl(conn->rmb_desc->mr[link->link_idx]->rkey);
+	clc->r0.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */
+	clc->r0.rmbe_alert_token = htonl(conn->alert_token_local);
+	switch (clc->hdr.type) {
+	case SMC_CLC_ACCEPT:
+		clc->r0.qp_mtu = link->path_mtu;
+		break;
+	case SMC_CLC_CONFIRM:
+		clc->r0.qp_mtu = min(link->path_mtu, link->peer_mtu);
+		break;
+	}
+	clc->r0.rmbe_size = conn->rmbe_size_comp;
+	clc->r0.rmb_dma_addr = conn->rmb_desc->is_vm ?
+		cpu_to_be64((uintptr_t)conn->rmb_desc->cpu_addr) :
+		cpu_to_be64((u64)sg_dma_address
+			    (conn->rmb_desc->sgt[link->link_idx].sgl));
+	hton24(clc->r0.psn, link->psn_initial);
+	if (version == SMC_V1) {
+		clc->hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN);
+	} else {
+		if (eid && eid[0])
+			memcpy(clc->r1.eid, eid, SMC_MAX_EID_LEN);
+		len = SMCR_CLC_ACCEPT_CONFIRM_LEN_V2;
+		if (first_contact) {
+			*fce_len = smc_clc_fill_fce_v2x(fce_v2x, ini);
+			len += *fce_len;
+			fce_v2x->fce_v2_base.v2_direct =
+				!link->lgr->uses_gateway;
+			if (clc->hdr.type == SMC_CLC_CONFIRM) {
+				memset(gle, 0, sizeof(*gle));
+				gle->gid_cnt = ini->smcrv2.gidlist.len;
+				len += sizeof(*gle);
+				len += gle->gid_cnt * sizeof(gle->gid[0]);
+			}
+		}
+		clc->hdr.length = htons(len);
+	}
+	memcpy(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
+}
+
 /* build and send CLC CONFIRM / ACCEPT message */
 static int smc_clc_send_confirm_accept(struct smc_sock *smc,
-				       struct smc_clc_msg_accept_confirm_v2 *clc_v2,
+				       struct smc_clc_msg_accept_confirm *clc,
 				       int first_contact, u8 version,
 				       u8 *eid, struct smc_init_info *ini)
 {
+	struct smc_clc_first_contact_ext_v2x fce_v2x;
 	struct smc_connection *conn = &smc->conn;
-	struct smc_clc_first_contact_ext_v2x fce;
-	struct smc_clc_msg_accept_confirm *clc;
 	struct smc_clc_fce_gid_ext gle;
 	struct smc_clc_msg_trail trl;
-	int i, len, fce_len;
+	int i, fce_len;
 	struct kvec vec[5];
 	struct msghdr msg;
 
 	/* send SMC Confirm CLC msg */
-	clc = (struct smc_clc_msg_accept_confirm *)clc_v2;
 	clc->hdr.version = version;	/* SMC version */
 	if (first_contact)
 		clc->hdr.typev2 |= SMC_FIRST_CONTACT_MASK;
-	if (conn->lgr->is_smcd) {
-		/* SMC-D specific settings */
-		memcpy(clc->hdr.eyecatcher, SMCD_EYECATCHER,
-		       sizeof(SMCD_EYECATCHER));
-		clc->hdr.typev1 = SMC_TYPE_D;
-		clc->d0.gid =
-			conn->lgr->smcd->ops->get_local_gid(conn->lgr->smcd);
-		clc->d0.token = conn->rmb_desc->token;
-		clc->d0.dmbe_size = conn->rmbe_size_comp;
-		clc->d0.dmbe_idx = 0;
-		memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE);
-		if (version == SMC_V1) {
-			clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN);
-		} else {
-			clc_v2->d1.chid =
-				htons(smc_ism_get_chid(conn->lgr->smcd));
-			if (eid && eid[0])
-				memcpy(clc_v2->d1.eid, eid, SMC_MAX_EID_LEN);
-			len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2;
-			if (first_contact) {
-				fce_len = smc_clc_fill_fce(&fce, ini);
-				len += fce_len;
-			}
-			clc_v2->hdr.length = htons(len);
-		}
-		memcpy(trl.eyecatcher, SMCD_EYECATCHER,
-		       sizeof(SMCD_EYECATCHER));
-	} else {
-		struct smc_link *link = conn->lnk;
-
-		/* SMC-R specific settings */
-		memcpy(clc->hdr.eyecatcher, SMC_EYECATCHER,
-		       sizeof(SMC_EYECATCHER));
-		clc->hdr.typev1 = SMC_TYPE_R;
-		clc->hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN);
-		memcpy(clc->r0.lcl.id_for_peer, local_systemid,
-		       sizeof(local_systemid));
-		memcpy(&clc->r0.lcl.gid, link->gid, SMC_GID_SIZE);
-		memcpy(&clc->r0.lcl.mac, &link->smcibdev->mac[link->ibport - 1],
-		       ETH_ALEN);
-		hton24(clc->r0.qpn, link->roce_qp->qp_num);
-		clc->r0.rmb_rkey =
-			htonl(conn->rmb_desc->mr[link->link_idx]->rkey);
-		clc->r0.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */
-		clc->r0.rmbe_alert_token = htonl(conn->alert_token_local);
-		switch (clc->hdr.type) {
-		case SMC_CLC_ACCEPT:
-			clc->r0.qp_mtu = link->path_mtu;
-			break;
-		case SMC_CLC_CONFIRM:
-			clc->r0.qp_mtu = min(link->path_mtu, link->peer_mtu);
-			break;
-		}
-		clc->r0.rmbe_size = conn->rmbe_size_comp;
-		clc->r0.rmb_dma_addr = conn->rmb_desc->is_vm ?
-			cpu_to_be64((uintptr_t)conn->rmb_desc->cpu_addr) :
-			cpu_to_be64((u64)sg_dma_address
-				    (conn->rmb_desc->sgt[link->link_idx].sgl));
-		hton24(clc->r0.psn, link->psn_initial);
-		if (version == SMC_V1) {
-			clc->hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN);
-		} else {
-			if (eid && eid[0])
-				memcpy(clc_v2->r1.eid, eid, SMC_MAX_EID_LEN);
-			len = SMCR_CLC_ACCEPT_CONFIRM_LEN_V2;
-			if (first_contact) {
-				fce_len = smc_clc_fill_fce(&fce, ini);
-				len += fce_len;
-				fce.fce_v2_base.v2_direct = !link->lgr->uses_gateway;
-				if (clc->hdr.type == SMC_CLC_CONFIRM) {
-					memset(&gle, 0, sizeof(gle));
-					gle.gid_cnt = ini->smcrv2.gidlist.len;
-					len += sizeof(gle);
-					len += gle.gid_cnt * sizeof(gle.gid[0]);
-				}
-			}
-			clc_v2->hdr.length = htons(len);
-		}
-		memcpy(trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
-	}
-
+	if (conn->lgr->is_smcd)
+		smcd_clc_prep_confirm_accept(conn, clc, first_contact,
+					     version, eid, ini, &fce_len,
+					     &fce_v2x, &trl);
+	else
+		smcr_clc_prep_confirm_accept(conn, clc, first_contact,
+					     version, eid, ini, &fce_len,
+					     &fce_v2x, &gle, &trl);
 	memset(&msg, 0, sizeof(msg));
 	i = 0;
-	vec[i].iov_base = clc_v2;
+	vec[i].iov_base = clc;
 	if (version > SMC_V1)
 		vec[i++].iov_len = (clc->hdr.typev1 == SMC_TYPE_D ?
 					SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 :
@@ -1111,7 +1172,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
 						SMCR_CLC_ACCEPT_CONFIRM_LEN) -
 				   sizeof(trl);
 	if (version > SMC_V1 && first_contact) {
-		vec[i].iov_base = &fce;
+		vec[i].iov_base = &fce_v2x;
 		vec[i++].iov_len = fce_len;
 		if (!conn->lgr->is_smcd) {
 			if (clc->hdr.type == SMC_CLC_CONFIRM) {
@@ -1133,16 +1194,16 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
 int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact,
 			 u8 version, u8 *eid, struct smc_init_info *ini)
 {
-	struct smc_clc_msg_accept_confirm_v2 cclc_v2;
+	struct smc_clc_msg_accept_confirm cclc;
 	int reason_code = 0;
 	int len;
 
 	/* send SMC Confirm CLC msg */
-	memset(&cclc_v2, 0, sizeof(cclc_v2));
-	cclc_v2.hdr.type = SMC_CLC_CONFIRM;
-	len = smc_clc_send_confirm_accept(smc, &cclc_v2, clnt_first_contact,
+	memset(&cclc, 0, sizeof(cclc));
+	cclc.hdr.type = SMC_CLC_CONFIRM;
+	len = smc_clc_send_confirm_accept(smc, &cclc, clnt_first_contact,
 					  version, eid, ini);
-	if (len < ntohs(cclc_v2.hdr.length)) {
+	if (len < ntohs(cclc.hdr.length)) {
 		if (len >= 0) {
 			reason_code = -ENETUNREACH;
 			smc->sk.sk_err = -reason_code;
@@ -1158,26 +1219,29 @@ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact,
 int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact,
 			u8 version, u8 *negotiated_eid, struct smc_init_info *ini)
 {
-	struct smc_clc_msg_accept_confirm_v2 aclc_v2;
+	struct smc_clc_msg_accept_confirm aclc;
 	int len;
 
-	memset(&aclc_v2, 0, sizeof(aclc_v2));
-	aclc_v2.hdr.type = SMC_CLC_ACCEPT;
-	len = smc_clc_send_confirm_accept(new_smc, &aclc_v2, srv_first_contact,
+	memset(&aclc, 0, sizeof(aclc));
+	aclc.hdr.type = SMC_CLC_ACCEPT;
+	len = smc_clc_send_confirm_accept(new_smc, &aclc, srv_first_contact,
 					  version, negotiated_eid, ini);
-	if (len < ntohs(aclc_v2.hdr.length))
+	if (len < ntohs(aclc.hdr.length))
 		len = len >= 0 ? -EPROTO : -new_smc->clcsock->sk->sk_err;
 
 	return len > 0 ? 0 : len;
 }
 
-int smc_clc_srv_v2x_features_validate(struct smc_clc_msg_proposal *pclc,
+int smc_clc_srv_v2x_features_validate(struct smc_sock *smc,
+				      struct smc_clc_msg_proposal *pclc,
 				      struct smc_init_info *ini)
 {
 	struct smc_clc_v2_extension *pclc_v2_ext;
+	struct net *net = sock_net(&smc->sk);
 
 	ini->max_conns = SMC_CONN_PER_LGR_MAX;
 	ini->max_links = SMC_LINKS_ADD_LNK_MAX;
+	ini->feature_mask = SMC_FEATURE_MASK;
 
 	if ((!(ini->smcd_version & SMC_V2) && !(ini->smcr_version & SMC_V2)) ||
 	    ini->release_nr < SMC_RELEASE_1)
@@ -1188,11 +1252,13 @@ int smc_clc_srv_v2x_features_validate(struct smc_clc_msg_proposal *pclc,
 		return SMC_CLC_DECL_NOV2EXT;
 
 	if (ini->smcr_version & SMC_V2) {
-		ini->max_conns = min_t(u8, pclc_v2_ext->max_conns, SMC_CONN_PER_LGR_PREFER);
+		ini->max_conns = min_t(u8, pclc_v2_ext->max_conns,
+				       net->smc.sysctl_max_conns_per_lgr);
 		if (ini->max_conns < SMC_CONN_PER_LGR_MIN)
 			return SMC_CLC_DECL_MAXCONNERR;
 
-		ini->max_links = min_t(u8, pclc_v2_ext->max_links, SMC_LINKS_PER_LGR_MAX_PREFER);
+		ini->max_links = min_t(u8, pclc_v2_ext->max_links,
+				       net->smc.sysctl_max_links_per_lgr);
 		if (ini->max_links < SMC_LINKS_ADD_LNK_MIN)
 			return SMC_CLC_DECL_MAXLINKERR;
 	}
@@ -1219,6 +1285,8 @@ int smc_clc_clnt_v2x_features_validate(struct smc_clc_first_contact_ext *fce,
 			return SMC_CLC_DECL_MAXLINKERR;
 		ini->max_links = fce_v2x->max_links;
 	}
+	/* common supplemental features of server and client */
+	ini->feature_mask = ntohs(fce_v2x->feature_mask) & SMC_FEATURE_MASK;
 
 	return 0;
 }
@@ -1226,10 +1294,8 @@ int smc_clc_clnt_v2x_features_validate(struct smc_clc_first_contact_ext *fce,
 int smc_clc_v2x_features_confirm_check(struct smc_clc_msg_accept_confirm *cclc,
 				       struct smc_init_info *ini)
 {
-	struct smc_clc_msg_accept_confirm_v2 *clc_v2 =
-		(struct smc_clc_msg_accept_confirm_v2 *)cclc;
 	struct smc_clc_first_contact_ext *fce =
-		smc_get_clc_first_contact_ext(clc_v2, ini->is_smcd);
+		smc_get_clc_first_contact_ext(cclc, ini->is_smcd);
 	struct smc_clc_first_contact_ext_v2x *fce_v2x =
 		(struct smc_clc_first_contact_ext_v2x *)fce;
 
@@ -1249,6 +1315,8 @@ int smc_clc_v2x_features_confirm_check(struct smc_clc_msg_accept_confirm *cclc,
 		if (fce_v2x->max_links != ini->max_links)
 			return SMC_CLC_DECL_MAXLINKERR;
 	}
+	/* common supplemental features returned by client */
+	ini->feature_mask = ntohs(fce_v2x->feature_mask);
 
 	return 0;
 }
@@ -1270,7 +1338,11 @@ void __init smc_clc_init(void)
 	INIT_LIST_HEAD(&smc_clc_eid_table.list);
 	rwlock_init(&smc_clc_eid_table.lock);
 	smc_clc_eid_table.ueid_cnt = 0;
+#if IS_ENABLED(CONFIG_S390)
 	smc_clc_eid_table.seid_enabled = 1;
+#else
+	smc_clc_eid_table.seid_enabled = 0;
+#endif
 }
 
 void smc_clc_exit(void)
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index c5c8e7db775a..a9f9bdd26dcd 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -138,7 +138,8 @@ struct smc_clc_v2_extension {
 	u8 roce[16];		/* RoCEv2 GID */
 	u8 max_conns;
 	u8 max_links;
-	u8 reserved[14];
+	__be16 feature_mask;
+	u8 reserved[12];
 	u8 user_eids[][SMC_MAX_EID_LEN];
 };
 
@@ -171,6 +172,11 @@ struct smc_clc_msg_proposal {	/* clc proposal message sent by Linux */
 
 #define SMC_CLC_MAX_V6_PREFIX		8
 #define SMC_CLC_MAX_UEID		8
+#define SMCD_CLC_MAX_V2_GID_ENTRIES	8 /* max # of CHID-GID entries in CLC
+					   * proposal SMC-Dv2 extension.
+					   * each ISM device takes one entry and
+					   * each virtual ISM takes two entries.
+					   */
 
 struct smc_clc_msg_proposal_area {
 	struct smc_clc_msg_proposal		pclc_base;
@@ -180,7 +186,8 @@ struct smc_clc_msg_proposal_area {
 	struct smc_clc_v2_extension		pclc_v2_ext;
 	u8			user_eids[SMC_CLC_MAX_UEID][SMC_MAX_EID_LEN];
 	struct smc_clc_smcd_v2_extension	pclc_smcd_v2_ext;
-	struct smc_clc_smcd_gid_chid		pclc_gidchids[SMC_MAX_ISM_DEVS];
+	struct smc_clc_smcd_gid_chid
+				pclc_gidchids[SMCD_CLC_MAX_V2_GID_ENTRIES];
 	struct smc_clc_msg_trail		pclc_trl;
 };
 
@@ -204,8 +211,8 @@ struct smcr_clc_msg_accept_confirm {	/* SMCR accept/confirm */
 } __packed;
 
 struct smcd_clc_msg_accept_confirm_common {	/* SMCD accept/confirm */
-	u64 gid;		/* Sender GID */
-	u64 token;		/* DMB token */
+	__be64 gid;		/* Sender GID */
+	__be64 token;		/* DMB token */
 	u8 dmbe_idx;		/* DMBE index */
 #if defined(__BIG_ENDIAN_BITFIELD)
 	u8 dmbe_size : 4,	/* buf size (compressed) */
@@ -240,9 +247,14 @@ struct smc_clc_first_contact_ext {
 
 struct smc_clc_first_contact_ext_v2x {
 	struct smc_clc_first_contact_ext fce_v2_base;
-	u8 max_conns; /* for SMC-R only */
-	u8 max_links; /* for SMC-R only */
-	u8 reserved3[2];
+	union {
+		struct {
+			u8 max_conns; /* for SMC-R only */
+			u8 max_links; /* for SMC-R only */
+		};
+		u8 reserved3[2];	/* for SMC-D only */
+	};
+	__be16 feature_mask;
 	__be32 vendor_exp_options;
 	u8 reserved4[8];
 } __packed;		/* format defined in
@@ -259,28 +271,21 @@ struct smc_clc_fce_gid_ext {
 struct smc_clc_msg_accept_confirm {	/* clc accept / confirm message */
 	struct smc_clc_msg_hdr hdr;
 	union {
-		struct smcr_clc_msg_accept_confirm r0; /* SMC-R */
-		struct { /* SMC-D */
-			struct smcd_clc_msg_accept_confirm_common d0;
-			u32 reserved5[3];
-		};
-	};
-} __packed;			/* format defined in RFC7609 */
-
-struct smc_clc_msg_accept_confirm_v2 {	/* clc accept / confirm message */
-	struct smc_clc_msg_hdr hdr;
-	union {
 		struct { /* SMC-R */
 			struct smcr_clc_msg_accept_confirm r0;
-			u8 eid[SMC_MAX_EID_LEN];
-			u8 reserved6[8];
-		} r1;
+			struct { /* v2 only */
+				u8 eid[SMC_MAX_EID_LEN];
+				u8 reserved6[8];
+			} __packed r1;
+		};
 		struct { /* SMC-D */
 			struct smcd_clc_msg_accept_confirm_common d0;
-			__be16 chid;
-			u8 eid[SMC_MAX_EID_LEN];
-			u8 reserved5[8];
-		} d1;
+			struct { /* v2 only, but 12 bytes reserved in v1 */
+				__be16 chid;
+				u8 eid[SMC_MAX_EID_LEN];
+				__be64 gid_ext;
+			} __packed d1;
+		};
 	};
 };
 
@@ -389,24 +394,23 @@ smc_get_clc_smcd_v2_ext(struct smc_clc_v2_extension *prop_v2ext)
 }
 
 static inline struct smc_clc_first_contact_ext *
-smc_get_clc_first_contact_ext(struct smc_clc_msg_accept_confirm_v2 *clc_v2,
+smc_get_clc_first_contact_ext(struct smc_clc_msg_accept_confirm *clc,
 			      bool is_smcd)
 {
 	int clc_v2_len;
 
-	if (clc_v2->hdr.version == SMC_V1 ||
-	    !(clc_v2->hdr.typev2 & SMC_FIRST_CONTACT_MASK))
+	if (clc->hdr.version == SMC_V1 ||
+	    !(clc->hdr.typev2 & SMC_FIRST_CONTACT_MASK))
 		return NULL;
 
 	if (is_smcd)
 		clc_v2_len =
-			offsetofend(struct smc_clc_msg_accept_confirm_v2, d1);
+			offsetofend(struct smc_clc_msg_accept_confirm, d1);
 	else
 		clc_v2_len =
-			offsetofend(struct smc_clc_msg_accept_confirm_v2, r1);
+			offsetofend(struct smc_clc_msg_accept_confirm, r1);
 
-	return (struct smc_clc_first_contact_ext *)(((u8 *)clc_v2) +
-						    clc_v2_len);
+	return (struct smc_clc_first_contact_ext *)(((u8 *)clc) + clc_v2_len);
 }
 
 struct smcd_dev;
@@ -422,7 +426,8 @@ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact,
 			 u8 version, u8 *eid, struct smc_init_info *ini);
 int smc_clc_send_accept(struct smc_sock *smc, bool srv_first_contact,
 			u8 version, u8 *negotiated_eid, struct smc_init_info *ini);
-int smc_clc_srv_v2x_features_validate(struct smc_clc_msg_proposal *pclc,
+int smc_clc_srv_v2x_features_validate(struct smc_sock *smc,
+				      struct smc_clc_msg_proposal *pclc,
 				      struct smc_init_info *ini);
 int smc_clc_clnt_v2x_features_validate(struct smc_clc_first_contact_ext *fce,
 				       struct smc_init_info *ini);
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index d520ee62c8ec..95cc95458e2d 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -506,6 +506,7 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr,
 {
 	char smc_pnet[SMC_MAX_PNETID_LEN + 1];
 	struct smcd_dev *smcd = lgr->smcd;
+	struct smcd_gid smcd_gid;
 	struct nlattr *attrs;
 	void *nlh;
 
@@ -521,13 +522,19 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr,
 
 	if (nla_put_u32(skb, SMC_NLA_LGR_D_ID, *((u32 *)&lgr->id)))
 		goto errattr;
+	smcd->ops->get_local_gid(smcd, &smcd_gid);
 	if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_GID,
-			      smcd->ops->get_local_gid(smcd),
-				  SMC_NLA_LGR_D_PAD))
+			      smcd_gid.gid, SMC_NLA_LGR_D_PAD))
 		goto errattr;
-	if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_GID, lgr->peer_gid,
+	if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_EXT_GID,
+			      smcd_gid.gid_ext, SMC_NLA_LGR_D_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_GID, lgr->peer_gid.gid,
 			      SMC_NLA_LGR_D_PAD))
 		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_EXT_GID,
+			      lgr->peer_gid.gid_ext, SMC_NLA_LGR_D_PAD))
+		goto errattr;
 	if (nla_put_u8(skb, SMC_NLA_LGR_D_VLAN_ID, lgr->vlan_id))
 		goto errattr;
 	if (nla_put_u32(skb, SMC_NLA_LGR_D_CONNS_NUM, lgr->conns_num))
@@ -876,7 +883,10 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini)
 		/* SMC-D specific settings */
 		smcd = ini->ism_dev[ini->ism_selected];
 		get_device(smcd->ops->get_dev(smcd));
-		lgr->peer_gid = ini->ism_peer_gid[ini->ism_selected];
+		lgr->peer_gid.gid =
+			ini->ism_peer_gid[ini->ism_selected].gid;
+		lgr->peer_gid.gid_ext =
+			ini->ism_peer_gid[ini->ism_selected].gid_ext;
 		lgr->smcd = ini->ism_dev[ini->ism_selected];
 		lgr_list = &ini->ism_dev[ini->ism_selected]->lgr_list;
 		lgr_lock = &lgr->smcd->lgr_lock;
@@ -1514,7 +1524,8 @@ void smc_lgr_terminate_sched(struct smc_link_group *lgr)
 }
 
 /* Called when peer lgr shutdown (regularly or abnormally) is received */
-void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, unsigned short vlan)
+void smc_smcd_terminate(struct smcd_dev *dev, struct smcd_gid *peer_gid,
+			unsigned short vlan)
 {
 	struct smc_link_group *lgr, *l;
 	LIST_HEAD(lgr_free_list);
@@ -1522,9 +1533,12 @@ void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, unsigned short vlan)
 	/* run common cleanup function and build free list */
 	spin_lock_bh(&dev->lgr_lock);
 	list_for_each_entry_safe(lgr, l, &dev->lgr_list, list) {
-		if ((!peer_gid || lgr->peer_gid == peer_gid) &&
+		if ((!peer_gid->gid ||
+		     (lgr->peer_gid.gid == peer_gid->gid &&
+		      !smc_ism_is_virtual(dev) ? 1 :
+		      lgr->peer_gid.gid_ext == peer_gid->gid_ext)) &&
 		    (vlan == VLAN_VID_MASK || lgr->vlan_id == vlan)) {
-			if (peer_gid) /* peer triggered termination */
+			if (peer_gid->gid) /* peer triggered termination */
 				lgr->peer_shutdown = 1;
 			list_move(&lgr->list, &lgr_free_list);
 			lgr->freeing = 1;
@@ -1860,9 +1874,12 @@ static bool smcr_lgr_match(struct smc_link_group *lgr, u8 smcr_version,
 }
 
 static bool smcd_lgr_match(struct smc_link_group *lgr,
-			   struct smcd_dev *smcismdev, u64 peer_gid)
+			   struct smcd_dev *smcismdev,
+			   struct smcd_gid *peer_gid)
 {
-	return lgr->peer_gid == peer_gid && lgr->smcd == smcismdev;
+	return lgr->peer_gid.gid == peer_gid->gid && lgr->smcd == smcismdev &&
+		smc_ism_is_virtual(smcismdev) ?
+		(lgr->peer_gid.gid_ext == peer_gid->gid_ext) : 1;
 }
 
 /* create a new SMC connection (and a new link group if necessary) */
@@ -1892,7 +1909,7 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
 		write_lock_bh(&lgr->conns_lock);
 		if ((ini->is_smcd ?
 		     smcd_lgr_match(lgr, ini->ism_dev[ini->ism_selected],
-				    ini->ism_peer_gid[ini->ism_selected]) :
+				    &ini->ism_peer_gid[ini->ism_selected]) :
 		     smcr_lgr_match(lgr, ini->smcr_version,
 				    ini->peer_systemid,
 				    ini->peer_gid, ini->peer_mac, role,
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 120027d40469..1f175376037b 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -17,9 +17,11 @@
 #include <linux/pci.h>
 #include <rdma/ib_verbs.h>
 #include <net/genetlink.h>
+#include <net/smc.h>
 
 #include "smc.h"
 #include "smc_ib.h"
+#include "smc_clc.h"
 
 #define SMC_RMBS_PER_LGR_MAX	255	/* max. # of RMBs per link group */
 #define SMC_CONN_PER_LGR_MIN	16	/* min. # of connections per link group */
@@ -355,7 +357,7 @@ struct smc_link_group {
 						/* max links can be added in lgr */
 		};
 		struct { /* SMC-D */
-			u64			peer_gid;
+			struct smcd_gid		peer_gid;
 						/* Peer GID (remote) */
 			struct smcd_dev		*smcd;
 						/* ISM device for VLAN reg. */
@@ -392,6 +394,11 @@ struct smc_init_info_smcrv2 {
 	struct smc_gidlist	gidlist;
 };
 
+#define SMC_MAX_V2_ISM_DEVS	SMCD_CLC_MAX_V2_GID_ENTRIES
+				/* max # of proposed non-native ISM devices,
+				 * which can't exceed the max # of CHID-GID
+				 * entries in CLC proposal SMC-Dv2 extension.
+				 */
 struct smc_init_info {
 	u8			is_smcd;
 	u8			smc_type_v1;
@@ -401,6 +408,7 @@ struct smc_init_info {
 	u8			max_links;
 	u8			first_contact_peer;
 	u8			first_contact_local;
+	u16			feature_mask;
 	unsigned short		vlan_id;
 	u32			rc;
 	u8			negotiated_eid[SMC_MAX_EID_LEN];
@@ -416,9 +424,9 @@ struct smc_init_info {
 	u32			ib_clcqpn;
 	struct smc_init_info_smcrv2 smcrv2;
 	/* SMC-D */
-	u64			ism_peer_gid[SMC_MAX_ISM_DEVS + 1];
-	struct smcd_dev		*ism_dev[SMC_MAX_ISM_DEVS + 1];
-	u16			ism_chid[SMC_MAX_ISM_DEVS + 1];
+	struct smcd_gid		ism_peer_gid[SMC_MAX_V2_ISM_DEVS + 1];
+	struct smcd_dev		*ism_dev[SMC_MAX_V2_ISM_DEVS + 1];
+	u16			ism_chid[SMC_MAX_V2_ISM_DEVS + 1];
 	u8			ism_offered_cnt; /* # of ISM devices offered */
 	u8			ism_selected;    /* index of selected ISM dev*/
 	u8			smcd_version;
@@ -544,7 +552,7 @@ void smc_lgr_hold(struct smc_link_group *lgr);
 void smc_lgr_put(struct smc_link_group *lgr);
 void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport);
 void smcr_port_err(struct smc_ib_device *smcibdev, u8 ibport);
-void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid,
+void smc_smcd_terminate(struct smcd_dev *dev, struct smcd_gid *peer_gid,
 			unsigned short vlan);
 void smc_smcd_terminate_all(struct smcd_dev *dev);
 void smc_smcr_terminate_all(struct smc_ib_device *smcibdev);
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index 7ff2152971a5..52f7c4f1e767 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -21,6 +21,7 @@
 
 #include "smc.h"
 #include "smc_core.h"
+#include "smc_ism.h"
 
 struct smc_diag_dump_ctx {
 	int pos[2];
@@ -153,8 +154,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 			.lnk[0].link_id = link->link_id,
 		};
 
-		memcpy(linfo.lnk[0].ibname,
-		       smc->conn.lgr->lnk[0].smcibdev->ibdev->name,
+		memcpy(linfo.lnk[0].ibname, link->smcibdev->ibdev->name,
 		       sizeof(link->smcibdev->ibdev->name));
 		smc_gid_be16_convert(linfo.lnk[0].gid, link->gid);
 		smc_gid_be16_convert(linfo.lnk[0].peer_gid, link->peer_gid);
@@ -168,12 +168,16 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 		struct smc_connection *conn = &smc->conn;
 		struct smcd_diag_dmbinfo dinfo;
 		struct smcd_dev *smcd = conn->lgr->smcd;
+		struct smcd_gid smcd_gid;
 
 		memset(&dinfo, 0, sizeof(dinfo));
 
 		dinfo.linkid = *((u32 *)conn->lgr->id);
-		dinfo.peer_gid = conn->lgr->peer_gid;
-		dinfo.my_gid = smcd->ops->get_local_gid(smcd);
+		dinfo.peer_gid = conn->lgr->peer_gid.gid;
+		dinfo.peer_gid_ext = conn->lgr->peer_gid.gid_ext;
+		smcd->ops->get_local_gid(smcd, &smcd_gid);
+		dinfo.my_gid = smcd_gid.gid;
+		dinfo.my_gid_ext = smcd_gid.gid_ext;
 		dinfo.token = conn->rmb_desc->token;
 		dinfo.peer_token = conn->peer_token;
 
@@ -268,5 +272,6 @@ static void __exit smc_diag_exit(void)
 module_init(smc_diag_init);
 module_exit(smc_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SMC socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 43 /* AF_SMC */);
 MODULE_ALIAS_GENL_FAMILY(SMCR_GENL_FAMILY_NAME);
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index 89981dbe46c9..97704a9e84c7 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -844,7 +844,7 @@ long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev)
 		goto out;
 	/* the calculated number of cq entries fits to mlx5 cq allocation */
 	cqe_size_order = cache_line_size() == 128 ? 7 : 6;
-	smc_order = MAX_ORDER - cqe_size_order;
+	smc_order = MAX_PAGE_ORDER - cqe_size_order;
 	if (SMC_MAX_CQE + 2 > (0x00000001 << smc_order) * PAGE_SIZE)
 		cqattr.cqe = (0x00000001 << smc_order) * PAGE_SIZE - 2;
 	smcibdev->roce_cq_send = ib_create_cq(smcibdev->ibdev,
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index fbee2493091f..ac88de2a06a0 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -43,8 +43,30 @@ static struct ism_client smc_ism_client = {
 };
 #endif
 
+static void smc_ism_create_system_eid(void)
+{
+	struct smc_ism_seid *seid =
+		(struct smc_ism_seid *)smc_ism_v2_system_eid;
+#if IS_ENABLED(CONFIG_S390)
+	struct cpuid id;
+	u16 ident_tail;
+	char tmp[5];
+
+	memcpy(seid->seid_string, "IBM-SYSZ-ISMSEID00000000", 24);
+	get_cpu_id(&id);
+	ident_tail = (u16)(id.ident & SMC_ISM_IDENT_MASK);
+	snprintf(tmp, 5, "%04X", ident_tail);
+	memcpy(seid->serial_number, tmp, 4);
+	snprintf(tmp, 5, "%04X", id.machine);
+	memcpy(seid->type, tmp, 4);
+#else
+	memset(seid, 0, SMC_MAX_EID_LEN);
+#endif
+}
+
 /* Test if an ISM communication is possible - same CPC */
-int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *smcd)
+int smc_ism_cantalk(struct smcd_gid *peer_gid, unsigned short vlan_id,
+		    struct smcd_dev *smcd)
 {
 	return smcd->ops->query_remote_gid(smcd, peer_gid, vlan_id ? 1 : 0,
 					   vlan_id);
@@ -208,7 +230,7 @@ int smc_ism_register_dmb(struct smc_link_group *lgr, int dmb_len,
 	dmb.dmb_len = dmb_len;
 	dmb.sba_idx = dmb_desc->sba_idx;
 	dmb.vlan_id = lgr->vlan_id;
-	dmb.rgid = lgr->peer_gid;
+	dmb.rgid = lgr->peer_gid.gid;
 	rc = lgr->smcd->ops->register_dmb(lgr->smcd, &dmb, &smc_ism_client);
 	if (!rc) {
 		dmb_desc->sba_idx = dmb.sba_idx;
@@ -340,18 +362,20 @@ union smcd_sw_event_info {
 
 static void smcd_handle_sw_event(struct smc_ism_event_work *wrk)
 {
+	struct smcd_gid peer_gid = { .gid = wrk->event.tok,
+				     .gid_ext = 0 };
 	union smcd_sw_event_info ev_info;
 
 	ev_info.info = wrk->event.info;
 	switch (wrk->event.code) {
 	case ISM_EVENT_CODE_SHUTDOWN:	/* Peer shut down DMBs */
-		smc_smcd_terminate(wrk->smcd, wrk->event.tok, ev_info.vlan_id);
+		smc_smcd_terminate(wrk->smcd, &peer_gid, ev_info.vlan_id);
 		break;
 	case ISM_EVENT_CODE_TESTLINK:	/* Activity timer */
 		if (ev_info.code == ISM_EVENT_REQUEST) {
 			ev_info.code = ISM_EVENT_RESPONSE;
 			wrk->smcd->ops->signal_event(wrk->smcd,
-						     wrk->event.tok,
+						     &peer_gid,
 						     ISM_EVENT_REQUEST_IR,
 						     ISM_EVENT_CODE_TESTLINK,
 						     ev_info.info);
@@ -365,10 +389,12 @@ static void smc_ism_event_work(struct work_struct *work)
 {
 	struct smc_ism_event_work *wrk =
 		container_of(work, struct smc_ism_event_work, work);
+	struct smcd_gid smcd_gid = { .gid = wrk->event.tok,
+				     .gid_ext = 0 };
 
 	switch (wrk->event.type) {
 	case ISM_EVENT_GID:	/* GID event, token is peer GID */
-		smc_smcd_terminate(wrk->smcd, wrk->event.tok, VLAN_VID_MASK);
+		smc_smcd_terminate(wrk->smcd, &smcd_gid, VLAN_VID_MASK);
 		break;
 	case ISM_EVENT_DMB:
 		break;
@@ -426,14 +452,8 @@ static void smcd_register_dev(struct ism_dev *ism)
 
 	mutex_lock(&smcd_dev_list.mutex);
 	if (list_empty(&smcd_dev_list.list)) {
-		u8 *system_eid = NULL;
-
-		system_eid = smcd->ops->get_system_eid();
-		if (smcd->ops->supports_v2()) {
+		if (smcd->ops->supports_v2())
 			smc_ism_v2_capable = true;
-			memcpy(smc_ism_v2_system_eid, system_eid,
-			       SMC_MAX_EID_LEN);
-		}
 	}
 	/* sort list: devices without pnetid before devices with pnetid */
 	if (smcd->pnetid[0])
@@ -525,7 +545,7 @@ int smc_ism_signal_shutdown(struct smc_link_group *lgr)
 	memcpy(ev_info.uid, lgr->id, SMC_LGR_ID_SIZE);
 	ev_info.vlan_id = lgr->vlan_id;
 	ev_info.code = ISM_EVENT_REQUEST;
-	rc = lgr->smcd->ops->signal_event(lgr->smcd, lgr->peer_gid,
+	rc = lgr->smcd->ops->signal_event(lgr->smcd, &lgr->peer_gid,
 					  ISM_EVENT_REQUEST_IR,
 					  ISM_EVENT_CODE_SHUTDOWN,
 					  ev_info.info);
@@ -537,10 +557,10 @@ int smc_ism_init(void)
 {
 	int rc = 0;
 
-#if IS_ENABLED(CONFIG_ISM)
 	smc_ism_v2_capable = false;
-	memset(smc_ism_v2_system_eid, 0, SMC_MAX_EID_LEN);
+	smc_ism_create_system_eid();
 
+#if IS_ENABLED(CONFIG_ISM)
 	rc = ism_register_client(&smc_ism_client);
 #endif
 	return rc;
diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h
index 832b2f42d79f..ffff40c30a06 100644
--- a/net/smc/smc_ism.h
+++ b/net/smc/smc_ism.h
@@ -15,6 +15,9 @@
 
 #include "smc.h"
 
+#define SMC_VIRTUAL_ISM_CHID_MASK	0xFF00
+#define SMC_ISM_IDENT_MASK		0x00FFFF
+
 struct smcd_dev_list {	/* List of SMCD devices */
 	struct list_head list;
 	struct mutex mutex;	/* Protects list of devices */
@@ -28,9 +31,16 @@ struct smc_ism_vlanid {			/* VLAN id set on ISM device */
 	refcount_t refcnt;		/* Reference count */
 };
 
+struct smc_ism_seid {
+	u8 seid_string[24];
+	u8 serial_number[4];
+	u8 type[4];
+};
+
 struct smcd_dev;
 
-int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *dev);
+int smc_ism_cantalk(struct smcd_gid *peer_gid, unsigned short vlan_id,
+		    struct smcd_dev *dev);
 void smc_ism_set_conn(struct smc_connection *conn);
 void smc_ism_unset_conn(struct smc_connection *conn);
 int smc_ism_get_vlan(struct smcd_dev *dev, unsigned short vlan_id);
@@ -56,4 +66,22 @@ static inline int smc_ism_write(struct smcd_dev *smcd, u64 dmb_tok,
 	return rc < 0 ? rc : 0;
 }
 
+static inline bool __smc_ism_is_virtual(u16 chid)
+{
+	/* CHIDs in range of 0xFF00 to 0xFFFF are reserved
+	 * for virtual ISM device.
+	 *
+	 * loopback-ism:	0xFFFF
+	 * virtio-ism:		0xFF00 ~ 0xFFFE
+	 */
+	return ((chid & 0xFF00) == 0xFF00);
+}
+
+static inline bool smc_ism_is_virtual(struct smcd_dev *smcd)
+{
+	u16 chid = smcd->ops->get_chid(smcd);
+
+	return __smc_ism_is_virtual(chid);
+}
+
 #endif
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 11775401df68..9f2c58c5a86b 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -1103,8 +1103,8 @@ static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev,
 	list_for_each_entry(ismdev, &smcd_dev_list.list, list) {
 		if (smc_pnet_match(ismdev->pnetid, ndev_pnetid) &&
 		    !ismdev->going_away &&
-		    (!ini->ism_peer_gid[0] ||
-		     !smc_ism_cantalk(ini->ism_peer_gid[0], ini->vlan_id,
+		    (!ini->ism_peer_gid[0].gid ||
+		     !smc_ism_cantalk(&ini->ism_peer_gid[0], ini->vlan_id,
 				      ismdev))) {
 			ini->ism_dev[0] = ismdev;
 			break;
diff --git a/net/smc/smc_sysctl.c b/net/smc/smc_sysctl.c
index 5cbc18c6e62b..a5946d1b9d60 100644
--- a/net/smc/smc_sysctl.c
+++ b/net/smc/smc_sysctl.c
@@ -25,6 +25,10 @@ static int max_sndbuf = INT_MAX / 2;
 static int max_rcvbuf = INT_MAX / 2;
 static const int net_smc_wmem_init = (64 * 1024);
 static const int net_smc_rmem_init = (64 * 1024);
+static int links_per_lgr_min = SMC_LINKS_ADD_LNK_MIN;
+static int links_per_lgr_max = SMC_LINKS_ADD_LNK_MAX;
+static int conns_per_lgr_min = SMC_CONN_PER_LGR_MIN;
+static int conns_per_lgr_max = SMC_CONN_PER_LGR_MAX;
 
 static struct ctl_table smc_table[] = {
 	{
@@ -68,6 +72,24 @@ static struct ctl_table smc_table[] = {
 		.extra1		= &min_rcvbuf,
 		.extra2		= &max_rcvbuf,
 	},
+	{
+		.procname	= "smcr_max_links_per_lgr",
+		.data		= &init_net.smc.sysctl_max_links_per_lgr,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &links_per_lgr_min,
+		.extra2		= &links_per_lgr_max,
+	},
+	{
+		.procname	= "smcr_max_conns_per_lgr",
+		.data		= &init_net.smc.sysctl_max_conns_per_lgr,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &conns_per_lgr_min,
+		.extra2		= &conns_per_lgr_max,
+	},
 	{  }
 };
 
@@ -97,6 +119,8 @@ int __net_init smc_sysctl_net_init(struct net *net)
 	net->smc.sysctl_smcr_testlink_time = SMC_LLC_TESTLINK_DEFAULT_TIME;
 	WRITE_ONCE(net->smc.sysctl_wmem, net_smc_wmem_init);
 	WRITE_ONCE(net->smc.sysctl_rmem, net_smc_rmem_init);
+	net->smc.sysctl_max_links_per_lgr = SMC_LINKS_PER_LGR_MAX_PREFER;
+	net->smc.sysctl_max_conns_per_lgr = SMC_CONN_PER_LGR_PREFER;
 
 	return 0;
 
diff --git a/net/smc/smc_sysctl.h b/net/smc/smc_sysctl.h
index 0becc11bd2f4..eb2465ae1e15 100644
--- a/net/smc/smc_sysctl.h
+++ b/net/smc/smc_sysctl.h
@@ -23,6 +23,8 @@ void __net_exit smc_sysctl_net_exit(struct net *net);
 static inline int smc_sysctl_net_init(struct net *net)
 {
 	net->smc.sysctl_autocorking_size = SMC_AUTOCORKING_DEFAULT_SIZE;
+	net->smc.sysctl_max_links_per_lgr = SMC_LINKS_PER_LGR_MAX_PREFER;
+	net->smc.sysctl_max_conns_per_lgr = SMC_CONN_PER_LGR_PREFER;
 	return 0;
 }
 
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index 3b0ff3b589c7..214ac3cbcf9a 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -621,7 +621,7 @@ static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn)
 	return rc;
 }
 
-static int __smc_tx_sndbuf_nonempty(struct smc_connection *conn)
+int smc_tx_sndbuf_nonempty(struct smc_connection *conn)
 {
 	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
 	int rc = 0;
@@ -655,34 +655,6 @@ out:
 	return rc;
 }
 
-int smc_tx_sndbuf_nonempty(struct smc_connection *conn)
-{
-	int rc;
-
-	/* This make sure only one can send simultaneously to prevent wasting
-	 * of CPU and CDC slot.
-	 * Record whether someone has tried to push while we are pushing.
-	 */
-	if (atomic_inc_return(&conn->tx_pushing) > 1)
-		return 0;
-
-again:
-	atomic_set(&conn->tx_pushing, 1);
-	smp_wmb(); /* Make sure tx_pushing is 1 before real send */
-	rc = __smc_tx_sndbuf_nonempty(conn);
-
-	/* We need to check whether someone else have added some data into
-	 * the send queue and tried to push but failed after the atomic_set()
-	 * when we are pushing.
-	 * If so, we need to push again to prevent those data hang in the send
-	 * queue.
-	 */
-	if (unlikely(!atomic_dec_and_test(&conn->tx_pushing)))
-		goto again;
-
-	return rc;
-}
-
 /* Wakeup sndbuf consumers from process context
  * since there is more data to transmit. The caller
  * must hold sock lock.
diff --git a/net/socket.c b/net/socket.c
index 3379c64217a4..ed3df2f749bf 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -757,6 +757,7 @@ int sock_sendmsg(struct socket *sock, struct msghdr *msg)
 {
 	struct sockaddr_storage *save_addr = (struct sockaddr_storage *)msg->msg_name;
 	struct sockaddr_storage address;
+	int save_len = msg->msg_namelen;
 	int ret;
 
 	if (msg->msg_name) {
@@ -766,6 +767,7 @@ int sock_sendmsg(struct socket *sock, struct msghdr *msg)
 
 	ret = __sock_sendmsg(sock, msg);
 	msg->msg_name = save_addr;
+	msg->msg_namelen = save_len;
 
 	return ret;
 }
@@ -2161,10 +2163,9 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags,
 	struct sockaddr_storage address;
 	int err;
 	struct msghdr msg;
-	struct iovec iov;
 	int fput_needed;
 
-	err = import_single_range(ITER_SOURCE, buff, len, &iov, &msg.msg_iter);
+	err = import_ubuf(ITER_SOURCE, buff, len, &msg.msg_iter);
 	if (unlikely(err))
 		return err;
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
@@ -2226,11 +2227,10 @@ int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags,
 		.msg_name = addr ? (struct sockaddr *)&address : NULL,
 	};
 	struct socket *sock;
-	struct iovec iov;
 	int err, err2;
 	int fput_needed;
 
-	err = import_single_range(ITER_DEST, ubuf, size, &iov, &msg.msg_iter);
+	err = import_ubuf(ITER_DEST, ubuf, size, &msg.msg_iter);
 	if (unlikely(err))
 		return err;
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 7bfe7d9a32aa..04534ea537c8 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -40,9 +40,6 @@ static unsigned long number_cred_unused;
 
 static struct cred machine_cred = {
 	.usage = ATOMIC_INIT(1),
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	.magic = CRED_MAGIC,
-#endif
 };
 
 /*
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 18734e70c5dd..24de94184700 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -866,14 +866,6 @@ svcauth_gss_unwrap_integ(struct svc_rqst *rqstp, u32 seq, struct gss_ctx *ctx)
 	struct xdr_buf databody_integ;
 	struct xdr_netobj checksum;
 
-	/* NFS READ normally uses splice to send data in-place. However
-	 * the data in cache can change after the reply's MIC is computed
-	 * but before the RPC reply is sent. To prevent the client from
-	 * rejecting the server-computed MIC in this somewhat rare case,
-	 * do not use splice with the GSS integrity service.
-	 */
-	clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
-
 	/* Did we already verify the signature on the original pass through? */
 	if (rqstp->rq_deferred)
 		return 0;
@@ -948,8 +940,6 @@ svcauth_gss_unwrap_priv(struct svc_rqst *rqstp, u32 seq, struct gss_ctx *ctx)
 	struct xdr_buf *buf = xdr->buf;
 	unsigned int saved_len;
 
-	clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
-
 	if (xdr_stream_decode_u32(xdr, &len) < 0)
 		goto unwrap_failed;
 	if (rqstp->rq_deferred) {
@@ -2014,6 +2004,11 @@ svcauth_gss_domain_release(struct auth_domain *dom)
 	call_rcu(&dom->rcu_head, svcauth_gss_domain_release_rcu);
 }
 
+static rpc_authflavor_t svcauth_gss_pseudoflavor(struct svc_rqst *rqstp)
+{
+	return svcauth_gss_flavor(rqstp->rq_gssclient);
+}
+
 static struct auth_ops svcauthops_gss = {
 	.name		= "rpcsec_gss",
 	.owner		= THIS_MODULE,
@@ -2022,6 +2017,7 @@ static struct auth_ops svcauthops_gss = {
 	.release	= svcauth_gss_release,
 	.domain_release = svcauth_gss_domain_release,
 	.set_client	= svcauth_gss_set_client,
+	.pseudoflavor	= svcauth_gss_pseudoflavor,
 };
 
 static int rsi_cache_create_net(struct net *net)
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index daa9582ec861..cda0935a68c9 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -287,8 +287,14 @@ static struct rpc_xprt *rpc_clnt_set_transport(struct rpc_clnt *clnt,
 
 static void rpc_clnt_set_nodename(struct rpc_clnt *clnt, const char *nodename)
 {
-	clnt->cl_nodelen = strlcpy(clnt->cl_nodename,
-			nodename, sizeof(clnt->cl_nodename));
+	ssize_t copied;
+
+	copied = strscpy(clnt->cl_nodename,
+			 nodename, sizeof(clnt->cl_nodename));
+
+	clnt->cl_nodelen = copied < 0
+				? sizeof(clnt->cl_nodename) - 1
+				: copied;
 }
 
 static int rpc_client_register(struct rpc_clnt *clnt,
@@ -797,15 +803,24 @@ out_revert:
 }
 EXPORT_SYMBOL_GPL(rpc_switch_client_transport);
 
-static
-int _rpc_clnt_xprt_iter_init(struct rpc_clnt *clnt, struct rpc_xprt_iter *xpi,
-			     void func(struct rpc_xprt_iter *xpi, struct rpc_xprt_switch *xps))
+static struct rpc_xprt_switch *rpc_clnt_xprt_switch_get(struct rpc_clnt *clnt)
 {
 	struct rpc_xprt_switch *xps;
 
 	rcu_read_lock();
 	xps = xprt_switch_get(rcu_dereference(clnt->cl_xpi.xpi_xpswitch));
 	rcu_read_unlock();
+
+	return xps;
+}
+
+static
+int _rpc_clnt_xprt_iter_init(struct rpc_clnt *clnt, struct rpc_xprt_iter *xpi,
+			     void func(struct rpc_xprt_iter *xpi, struct rpc_xprt_switch *xps))
+{
+	struct rpc_xprt_switch *xps;
+
+	xps = rpc_clnt_xprt_switch_get(clnt);
 	if (xps == NULL)
 		return -EAGAIN;
 	func(xpi, xps);
@@ -1302,8 +1317,10 @@ static void call_bc_encode(struct rpc_task *task);
  * rpc_run_bc_task - Allocate a new RPC task for backchannel use, then run
  * rpc_execute against it
  * @req: RPC request
+ * @timeout: timeout values to use for this task
  */
-struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req)
+struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req,
+		struct rpc_timeout *timeout)
 {
 	struct rpc_task *task;
 	struct rpc_task_setup task_setup_data = {
@@ -1322,7 +1339,7 @@ struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req)
 		return task;
 	}
 
-	xprt_init_bc_request(req, task);
+	xprt_init_bc_request(req, task, timeout);
 
 	task->tk_action = call_bc_encode;
 	atomic_inc(&task->tk_count);
@@ -2206,9 +2223,7 @@ call_connect_status(struct rpc_task *task)
 			struct rpc_xprt *saved = task->tk_xprt;
 			struct rpc_xprt_switch *xps;
 
-			rcu_read_lock();
-			xps = xprt_switch_get(rcu_dereference(clnt->cl_xpi.xpi_xpswitch));
-			rcu_read_unlock();
+			xps = rpc_clnt_xprt_switch_get(clnt);
 			if (xps->xps_nxprts > 1) {
 				long value;
 
@@ -3116,7 +3131,6 @@ static int rpc_xprt_probe_trunked(struct rpc_clnt *clnt,
 				  struct rpc_xprt *xprt,
 				  struct rpc_add_xprt_test *data)
 {
-	struct rpc_xprt_switch *xps;
 	struct rpc_xprt *main_xprt;
 	int status = 0;
 
@@ -3124,7 +3138,6 @@ static int rpc_xprt_probe_trunked(struct rpc_clnt *clnt,
 
 	rcu_read_lock();
 	main_xprt = xprt_get(rcu_dereference(clnt->cl_xprt));
-	xps = xprt_switch_get(rcu_dereference(clnt->cl_xpi.xpi_xpswitch));
 	status = rpc_cmp_addr_port((struct sockaddr *)&xprt->addr,
 				   (struct sockaddr *)&main_xprt->addr);
 	rcu_read_unlock();
@@ -3135,7 +3148,6 @@ static int rpc_xprt_probe_trunked(struct rpc_clnt *clnt,
 	status = rpc_clnt_add_xprt_helper(clnt, xprt, data);
 out:
 	xprt_put(xprt);
-	xprt_switch_put(xps);
 	return status;
 }
 
@@ -3250,34 +3262,27 @@ rpc_set_connect_timeout(struct rpc_clnt *clnt,
 }
 EXPORT_SYMBOL_GPL(rpc_set_connect_timeout);
 
-void rpc_clnt_xprt_switch_put(struct rpc_clnt *clnt)
-{
-	rcu_read_lock();
-	xprt_switch_put(rcu_dereference(clnt->cl_xpi.xpi_xpswitch));
-	rcu_read_unlock();
-}
-EXPORT_SYMBOL_GPL(rpc_clnt_xprt_switch_put);
-
 void rpc_clnt_xprt_set_online(struct rpc_clnt *clnt, struct rpc_xprt *xprt)
 {
 	struct rpc_xprt_switch *xps;
 
-	rcu_read_lock();
-	xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch);
-	rcu_read_unlock();
+	xps = rpc_clnt_xprt_switch_get(clnt);
 	xprt_set_online_locked(xprt, xps);
+	xprt_switch_put(xps);
 }
 
 void rpc_clnt_xprt_switch_add_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt)
 {
+	struct rpc_xprt_switch *xps;
+
 	if (rpc_clnt_xprt_switch_has_addr(clnt,
 		(const struct sockaddr *)&xprt->addr)) {
 		return rpc_clnt_xprt_set_online(clnt, xprt);
 	}
-	rcu_read_lock();
-	rpc_xprt_switch_add_xprt(rcu_dereference(clnt->cl_xpi.xpi_xpswitch),
-				 xprt);
-	rcu_read_unlock();
+
+	xps = rpc_clnt_xprt_switch_get(clnt);
+	rpc_xprt_switch_add_xprt(xps, xprt);
+	xprt_switch_put(xps);
 }
 EXPORT_SYMBOL_GPL(rpc_clnt_xprt_switch_add_xprt);
 
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 3f2ea7a0496f..f60c93e5a25d 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -463,7 +463,6 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
 		return NULL;
 	serv->sv_name      = prog->pg_name;
 	serv->sv_program   = prog;
-	kref_init(&serv->sv_refcnt);
 	serv->sv_stats     = prog->pg_stats;
 	if (bufsize > RPCSVC_MAXPAYLOAD)
 		bufsize = RPCSVC_MAXPAYLOAD;
@@ -564,11 +563,13 @@ EXPORT_SYMBOL_GPL(svc_create_pooled);
  * protect sv_permsocks and sv_tempsocks.
  */
 void
-svc_destroy(struct kref *ref)
+svc_destroy(struct svc_serv **servp)
 {
-	struct svc_serv *serv = container_of(ref, struct svc_serv, sv_refcnt);
+	struct svc_serv *serv = *servp;
 	unsigned int i;
 
+	*servp = NULL;
+
 	dprintk("svc: svc_destroy(%s)\n", serv->sv_program->pg_name);
 	timer_shutdown_sync(&serv->sv_temptimer);
 
@@ -675,7 +676,6 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
 	if (!rqstp)
 		return ERR_PTR(-ENOMEM);
 
-	svc_get(serv);
 	spin_lock_bh(&serv->sv_lock);
 	serv->sv_nrthreads += 1;
 	spin_unlock_bh(&serv->sv_lock);
@@ -935,11 +935,6 @@ svc_exit_thread(struct svc_rqst *rqstp)
 
 	svc_rqst_free(rqstp);
 
-	svc_put(serv);
-	/* That svc_put() cannot be the last, because the thread
-	 * waiting for SP_VICTIM_REMAINS to clear must hold
-	 * a reference. So it is still safe to access pool.
-	 */
 	clear_and_wake_up_bit(SP_VICTIM_REMAINS, &pool->sp_flags);
 }
 EXPORT_SYMBOL_GPL(svc_exit_thread);
@@ -1305,8 +1300,6 @@ svc_process_common(struct svc_rqst *rqstp)
 	int			rc;
 	__be32			*p;
 
-	/* Will be turned off by GSS integrity and privacy services */
-	set_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
 	/* Will be turned off only when NFSv4 Sessions are used */
 	set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
 	clear_bit(RQ_DROPME, &rqstp->rq_flags);
@@ -1557,6 +1550,7 @@ void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp)
 {
 	struct rpc_task *task;
 	int proc_error;
+	struct rpc_timeout timeout;
 
 	/* Build the svc_rqst used by the common processing routine */
 	rqstp->rq_xid = req->rq_xid;
@@ -1602,8 +1596,16 @@ void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp)
 		return;
 	}
 	/* Finally, send the reply synchronously */
+	if (rqstp->bc_to_initval > 0) {
+		timeout.to_initval = rqstp->bc_to_initval;
+		timeout.to_retries = rqstp->bc_to_initval;
+	} else {
+		timeout.to_initval = req->rq_xprt->timeout->to_initval;
+		timeout.to_initval = req->rq_xprt->timeout->to_retries;
+	}
 	memcpy(&req->rq_snd_buf, &rqstp->rq_res, sizeof(req->rq_snd_buf));
-	task = rpc_run_bc_task(req);
+	task = rpc_run_bc_task(req, &timeout);
+
 	if (IS_ERR(task))
 		return;
 
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index fee83d1024bc..b4a85a227bd7 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -654,9 +654,8 @@ static bool svc_alloc_arg(struct svc_rqst *rqstp)
 	}
 
 	for (filled = 0; filled < pages; filled = ret) {
-		ret = alloc_pages_bulk_array_node(GFP_KERNEL,
-						  rqstp->rq_pool->sp_id,
-						  pages, rqstp->rq_pages);
+		ret = alloc_pages_bulk_array(GFP_KERNEL, pages,
+					     rqstp->rq_pages);
 		if (ret > filled)
 			/* Made progress, don't sleep yet */
 			continue;
@@ -1363,29 +1362,36 @@ int svc_xprt_names(struct svc_serv *serv, char *buf, const int buflen)
 }
 EXPORT_SYMBOL_GPL(svc_xprt_names);
 
-
 /*----------------------------------------------------------------------------*/
 
 static void *svc_pool_stats_start(struct seq_file *m, loff_t *pos)
 {
 	unsigned int pidx = (unsigned int)*pos;
-	struct svc_serv *serv = m->private;
+	struct svc_info *si = m->private;
 
 	dprintk("svc_pool_stats_start, *pidx=%u\n", pidx);
 
+	mutex_lock(si->mutex);
+
 	if (!pidx)
 		return SEQ_START_TOKEN;
-	return (pidx > serv->sv_nrpools ? NULL : &serv->sv_pools[pidx-1]);
+	if (!si->serv)
+		return NULL;
+	return pidx > si->serv->sv_nrpools ? NULL
+		: &si->serv->sv_pools[pidx - 1];
 }
 
 static void *svc_pool_stats_next(struct seq_file *m, void *p, loff_t *pos)
 {
 	struct svc_pool *pool = p;
-	struct svc_serv *serv = m->private;
+	struct svc_info *si = m->private;
+	struct svc_serv *serv = si->serv;
 
 	dprintk("svc_pool_stats_next, *pos=%llu\n", *pos);
 
-	if (p == SEQ_START_TOKEN) {
+	if (!serv) {
+		pool = NULL;
+	} else if (p == SEQ_START_TOKEN) {
 		pool = &serv->sv_pools[0];
 	} else {
 		unsigned int pidx = (pool - &serv->sv_pools[0]);
@@ -1400,6 +1406,9 @@ static void *svc_pool_stats_next(struct seq_file *m, void *p, loff_t *pos)
 
 static void svc_pool_stats_stop(struct seq_file *m, void *p)
 {
+	struct svc_info *si = m->private;
+
+	mutex_unlock(si->mutex);
 }
 
 static int svc_pool_stats_show(struct seq_file *m, void *p)
@@ -1427,14 +1436,18 @@ static const struct seq_operations svc_pool_stats_seq_ops = {
 	.show	= svc_pool_stats_show,
 };
 
-int svc_pool_stats_open(struct svc_serv *serv, struct file *file)
+int svc_pool_stats_open(struct svc_info *info, struct file *file)
 {
+	struct seq_file *seq;
 	int err;
 
 	err = seq_open(file, &svc_pool_stats_seq_ops);
-	if (!err)
-		((struct seq_file *) file->private_data)->private = serv;
-	return err;
+	if (err)
+		return err;
+	seq = file->private_data;
+	seq->private = info;
+
+	return 0;
 }
 EXPORT_SYMBOL(svc_pool_stats_open);
 
diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c
index aa4429d0b810..1619211f0960 100644
--- a/net/sunrpc/svcauth.c
+++ b/net/sunrpc/svcauth.c
@@ -160,6 +160,22 @@ svc_auth_unregister(rpc_authflavor_t flavor)
 }
 EXPORT_SYMBOL_GPL(svc_auth_unregister);
 
+/**
+ * svc_auth_flavor - return RPC transaction's RPC_AUTH flavor
+ * @rqstp: RPC transaction context
+ *
+ * Returns an RPC flavor or GSS pseudoflavor.
+ */
+rpc_authflavor_t svc_auth_flavor(struct svc_rqst *rqstp)
+{
+	struct auth_ops *aops = rqstp->rq_authop;
+
+	if (!aops->pseudoflavor)
+		return aops->flavour;
+	return aops->pseudoflavor(rqstp);
+}
+EXPORT_SYMBOL_GPL(svc_auth_flavor);
+
 /**************************************************
  * 'auth_domains' are stored in a hash table indexed by name.
  * When the last reference to an 'auth_domain' is dropped,
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 998687421fa6..bfb2f78523a8 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1049,18 +1049,14 @@ static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp)
 	struct rpc_rqst *req = NULL;
 	struct kvec *src, *dst;
 	__be32 *p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
-	__be32 xid;
-	__be32 calldir;
-
-	xid = *p++;
-	calldir = *p;
+	__be32 xid = *p;
 
 	if (!bc_xprt)
 		return -EAGAIN;
 	spin_lock(&bc_xprt->queue_lock);
 	req = xprt_lookup_rqst(bc_xprt, xid);
 	if (!req)
-		goto unlock_notfound;
+		goto unlock_eagain;
 
 	memcpy(&req->rq_private_buf, &req->rq_rcv_buf, sizeof(struct xdr_buf));
 	/*
@@ -1077,12 +1073,6 @@ static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp)
 	rqstp->rq_arg.len = 0;
 	spin_unlock(&bc_xprt->queue_lock);
 	return 0;
-unlock_notfound:
-	printk(KERN_NOTICE
-		"%s: Got unrecognized reply: "
-		"calldir 0x%x xpt_bc_xprt %p xid %08x\n",
-		__func__, ntohl(calldir),
-		bc_xprt, ntohl(xid));
 unlock_eagain:
 	spin_unlock(&bc_xprt->queue_lock);
 	return -EAGAIN;
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 2364c485540c..af13fdfa6672 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -651,9 +651,9 @@ static unsigned long xprt_abs_ktime_to_jiffies(ktime_t abstime)
 		jiffies + nsecs_to_jiffies(-delta);
 }
 
-static unsigned long xprt_calc_majortimeo(struct rpc_rqst *req)
+static unsigned long xprt_calc_majortimeo(struct rpc_rqst *req,
+		const struct rpc_timeout *to)
 {
-	const struct rpc_timeout *to = req->rq_task->tk_client->cl_timeout;
 	unsigned long majortimeo = req->rq_timeout;
 
 	if (to->to_exponential)
@@ -665,9 +665,10 @@ static unsigned long xprt_calc_majortimeo(struct rpc_rqst *req)
 	return majortimeo;
 }
 
-static void xprt_reset_majortimeo(struct rpc_rqst *req)
+static void xprt_reset_majortimeo(struct rpc_rqst *req,
+		const struct rpc_timeout *to)
 {
-	req->rq_majortimeo += xprt_calc_majortimeo(req);
+	req->rq_majortimeo += xprt_calc_majortimeo(req, to);
 }
 
 static void xprt_reset_minortimeo(struct rpc_rqst *req)
@@ -675,7 +676,8 @@ static void xprt_reset_minortimeo(struct rpc_rqst *req)
 	req->rq_minortimeo += req->rq_timeout;
 }
 
-static void xprt_init_majortimeo(struct rpc_task *task, struct rpc_rqst *req)
+static void xprt_init_majortimeo(struct rpc_task *task, struct rpc_rqst *req,
+		const struct rpc_timeout *to)
 {
 	unsigned long time_init;
 	struct rpc_xprt *xprt = req->rq_xprt;
@@ -684,8 +686,9 @@ static void xprt_init_majortimeo(struct rpc_task *task, struct rpc_rqst *req)
 		time_init = jiffies;
 	else
 		time_init = xprt_abs_ktime_to_jiffies(task->tk_start);
-	req->rq_timeout = task->tk_client->cl_timeout->to_initval;
-	req->rq_majortimeo = time_init + xprt_calc_majortimeo(req);
+
+	req->rq_timeout = to->to_initval;
+	req->rq_majortimeo = time_init + xprt_calc_majortimeo(req, to);
 	req->rq_minortimeo = time_init + req->rq_timeout;
 }
 
@@ -713,7 +716,7 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
 	} else {
 		req->rq_timeout = to->to_initval;
 		req->rq_retries = 0;
-		xprt_reset_majortimeo(req);
+		xprt_reset_majortimeo(req, to);
 		/* Reset the RTT counters == "slow start" */
 		spin_lock(&xprt->transport_lock);
 		rpc_init_rtt(req->rq_task->tk_client->cl_rtt, to->to_initval);
@@ -1886,7 +1889,7 @@ xprt_request_init(struct rpc_task *task)
 	req->rq_snd_buf.bvec = NULL;
 	req->rq_rcv_buf.bvec = NULL;
 	req->rq_release_snd_buf = NULL;
-	xprt_init_majortimeo(task, req);
+	xprt_init_majortimeo(task, req, task->tk_client->cl_timeout);
 
 	trace_xprt_reserve(req);
 }
@@ -1983,7 +1986,8 @@ void xprt_release(struct rpc_task *task)
 
 #ifdef CONFIG_SUNRPC_BACKCHANNEL
 void
-xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task)
+xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task,
+		const struct rpc_timeout *to)
 {
 	struct xdr_buf *xbufp = &req->rq_snd_buf;
 
@@ -1996,6 +2000,13 @@ xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task)
 	 */
 	xbufp->len = xbufp->head[0].iov_len + xbufp->page_len +
 		xbufp->tail[0].iov_len;
+	/*
+	 * Backchannel Replies are sent with !RPC_TASK_SOFT and
+	 * RPC_TASK_NO_RETRANS_TIMEOUT. The major timeout setting
+	 * affects only how long each Reply waits to be sent when
+	 * a transport connection cannot be established.
+	 */
+	xprt_init_majortimeo(task, req, to);
 }
 #endif
 
diff --git a/net/sunrpc/xprtmultipath.c b/net/sunrpc/xprtmultipath.c
index 701250b305db..720d3ba742ec 100644
--- a/net/sunrpc/xprtmultipath.c
+++ b/net/sunrpc/xprtmultipath.c
@@ -284,7 +284,7 @@ struct rpc_xprt *_xprt_switch_find_current_entry(struct list_head *head,
 		if (cur == pos)
 			found = true;
 		if (found && ((find_active && xprt_is_active(pos)) ||
-			      (!find_active && xprt_is_active(pos))))
+			      (!find_active && !xprt_is_active(pos))))
 			return pos;
 	}
 	return NULL;
@@ -336,8 +336,9 @@ struct rpc_xprt *xprt_iter_current_entry_offline(struct rpc_xprt_iter *xpi)
 			xprt_switch_find_current_entry_offline);
 }
 
-bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps,
-			      const struct sockaddr *sap)
+static
+bool __rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps,
+				const struct sockaddr *sap)
 {
 	struct list_head *head;
 	struct rpc_xprt *pos;
@@ -356,6 +357,18 @@ bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps,
 	return false;
 }
 
+bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps,
+			      const struct sockaddr *sap)
+{
+	bool res;
+
+	rcu_read_lock();
+	res = __rpc_xprt_switch_has_addr(xps, sap);
+	rcu_read_unlock();
+
+	return res;
+}
+
 static
 struct rpc_xprt *xprt_switch_find_next_entry(struct list_head *head,
 		const struct rpc_xprt *cur, bool check_active)
diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c
index f0d5eeed4c88..f86970733eb0 100644
--- a/net/sunrpc/xprtrdma/svc_rdma.c
+++ b/net/sunrpc/xprtrdma/svc_rdma.c
@@ -256,28 +256,44 @@ out_err:
 	return rc;
 }
 
+struct workqueue_struct *svcrdma_wq;
+
 void svc_rdma_cleanup(void)
 {
-	dprintk("SVCRDMA Module Removed, deregister RPC RDMA transport\n");
 	svc_unreg_xprt_class(&svc_rdma_class);
 	svc_rdma_proc_cleanup();
+	if (svcrdma_wq) {
+		struct workqueue_struct *wq = svcrdma_wq;
+
+		svcrdma_wq = NULL;
+		destroy_workqueue(wq);
+	}
+
+	dprintk("SVCRDMA Module Removed, deregister RPC RDMA transport\n");
 }
 
 int svc_rdma_init(void)
 {
+	struct workqueue_struct *wq;
 	int rc;
 
-	dprintk("SVCRDMA Module Init, register RPC RDMA transport\n");
-	dprintk("\tsvcrdma_ord      : %d\n", svcrdma_ord);
-	dprintk("\tmax_requests     : %u\n", svcrdma_max_requests);
-	dprintk("\tmax_bc_requests  : %u\n", svcrdma_max_bc_requests);
-	dprintk("\tmax_inline       : %d\n", svcrdma_max_req_size);
+	wq = alloc_workqueue("svcrdma", WQ_UNBOUND, 0);
+	if (!wq)
+		return -ENOMEM;
 
 	rc = svc_rdma_proc_init();
-	if (rc)
+	if (rc) {
+		destroy_workqueue(wq);
 		return rc;
+	}
 
-	/* Register RDMA with the SVC transport switch */
+	svcrdma_wq = wq;
 	svc_reg_xprt_class(&svc_rdma_class);
+
+	dprintk("SVCRDMA Module Init, register RPC RDMA transport\n");
+	dprintk("\tsvcrdma_ord      : %d\n", svcrdma_ord);
+	dprintk("\tmax_requests     : %u\n", svcrdma_max_requests);
+	dprintk("\tmax_bc_requests  : %u\n", svcrdma_max_bc_requests);
+	dprintk("\tmax_inline       : %d\n", svcrdma_max_req_size);
 	return 0;
 }
diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index 7420a2c990c7..c9be6778643b 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -76,15 +76,12 @@ static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma,
 			      struct rpc_rqst *rqst,
 			      struct svc_rdma_send_ctxt *sctxt)
 {
-	struct svc_rdma_recv_ctxt *rctxt;
+	struct svc_rdma_pcl empty_pcl;
 	int ret;
 
-	rctxt = svc_rdma_recv_ctxt_get(rdma);
-	if (!rctxt)
-		return -EIO;
-
-	ret = svc_rdma_map_reply_msg(rdma, sctxt, rctxt, &rqst->rq_snd_buf);
-	svc_rdma_recv_ctxt_put(rdma, rctxt);
+	pcl_init(&empty_pcl);
+	ret = svc_rdma_map_reply_msg(rdma, sctxt, &empty_pcl, &empty_pcl,
+				     &rqst->rq_snd_buf);
 	if (ret < 0)
 		return -EIO;
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 3b05f90a3e50..d72953f29258 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -115,13 +115,6 @@ svc_rdma_next_recv_ctxt(struct list_head *list)
 					rc_list);
 }
 
-static void svc_rdma_recv_cid_init(struct svcxprt_rdma *rdma,
-				   struct rpc_rdma_cid *cid)
-{
-	cid->ci_queue_id = rdma->sc_rq_cq->res.id;
-	cid->ci_completion_id = atomic_inc_return(&rdma->sc_completion_ids);
-}
-
 static struct svc_rdma_recv_ctxt *
 svc_rdma_recv_ctxt_alloc(struct svcxprt_rdma *rdma)
 {
@@ -130,7 +123,7 @@ svc_rdma_recv_ctxt_alloc(struct svcxprt_rdma *rdma)
 	dma_addr_t addr;
 	void *buffer;
 
-	ctxt = kmalloc_node(sizeof(*ctxt), GFP_KERNEL, node);
+	ctxt = kzalloc_node(sizeof(*ctxt), GFP_KERNEL, node);
 	if (!ctxt)
 		goto fail0;
 	buffer = kmalloc_node(rdma->sc_max_req_size, GFP_KERNEL, node);
@@ -156,6 +149,7 @@ svc_rdma_recv_ctxt_alloc(struct svcxprt_rdma *rdma)
 	ctxt->rc_recv_sge.length = rdma->sc_max_req_size;
 	ctxt->rc_recv_sge.lkey = rdma->sc_pd->local_dma_lkey;
 	ctxt->rc_recv_buf = buffer;
+	svc_rdma_cc_init(rdma, &ctxt->rc_cc);
 	return ctxt;
 
 fail2:
@@ -204,18 +198,11 @@ struct svc_rdma_recv_ctxt *svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma)
 
 	node = llist_del_first(&rdma->sc_recv_ctxts);
 	if (!node)
-		goto out_empty;
-	ctxt = llist_entry(node, struct svc_rdma_recv_ctxt, rc_node);
+		return NULL;
 
-out:
+	ctxt = llist_entry(node, struct svc_rdma_recv_ctxt, rc_node);
 	ctxt->rc_page_count = 0;
 	return ctxt;
-
-out_empty:
-	ctxt = svc_rdma_recv_ctxt_alloc(rdma);
-	if (!ctxt)
-		return NULL;
-	goto out;
 }
 
 /**
@@ -227,6 +214,13 @@ out_empty:
 void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma,
 			    struct svc_rdma_recv_ctxt *ctxt)
 {
+	svc_rdma_cc_release(rdma, &ctxt->rc_cc, DMA_FROM_DEVICE);
+
+	/* @rc_page_count is normally zero here, but error flows
+	 * can leave pages in @rc_pages.
+	 */
+	release_pages(ctxt->rc_pages, ctxt->rc_page_count);
+
 	pcl_free(&ctxt->rc_call_pcl);
 	pcl_free(&ctxt->rc_read_pcl);
 	pcl_free(&ctxt->rc_write_pcl);
@@ -271,13 +265,13 @@ static bool svc_rdma_refresh_recvs(struct svcxprt_rdma *rdma,
 		if (!ctxt)
 			break;
 
-		trace_svcrdma_post_recv(ctxt);
+		trace_svcrdma_post_recv(&ctxt->rc_cid);
 		ctxt->rc_recv_wr.next = recv_chain;
 		recv_chain = &ctxt->rc_recv_wr;
 		rdma->sc_pending_recvs++;
 	}
 	if (!recv_chain)
-		return false;
+		return true;
 
 	ret = ib_post_recv(rdma->sc_qp, recv_chain, &bad_wr);
 	if (ret)
@@ -301,10 +295,27 @@ err_free:
  * svc_rdma_post_recvs - Post initial set of Recv WRs
  * @rdma: fresh svcxprt_rdma
  *
- * Returns true if successful, otherwise false.
+ * Return values:
+ *   %true: Receive Queue initialization successful
+ *   %false: memory allocation or DMA error
  */
 bool svc_rdma_post_recvs(struct svcxprt_rdma *rdma)
 {
+	unsigned int total;
+
+	/* For each credit, allocate enough recv_ctxts for one
+	 * posted Receive and one RPC in process.
+	 */
+	total = (rdma->sc_max_requests * 2) + rdma->sc_recv_batch;
+	while (total--) {
+		struct svc_rdma_recv_ctxt *ctxt;
+
+		ctxt = svc_rdma_recv_ctxt_alloc(rdma);
+		if (!ctxt)
+			return false;
+		llist_add(&ctxt->rc_node, &rdma->sc_recv_ctxts);
+	}
+
 	return svc_rdma_refresh_recvs(rdma, rdma->sc_max_requests);
 }
 
@@ -373,6 +384,10 @@ void svc_rdma_flush_recv_queues(struct svcxprt_rdma *rdma)
 {
 	struct svc_rdma_recv_ctxt *ctxt;
 
+	while ((ctxt = svc_rdma_next_recv_ctxt(&rdma->sc_read_complete_q))) {
+		list_del(&ctxt->rc_list);
+		svc_rdma_recv_ctxt_put(rdma, ctxt);
+	}
 	while ((ctxt = svc_rdma_next_recv_ctxt(&rdma->sc_rq_dto_q))) {
 		list_del(&ctxt->rc_list);
 		svc_rdma_recv_ctxt_put(rdma, ctxt);
@@ -754,6 +769,122 @@ static bool svc_rdma_is_reverse_direction_reply(struct svc_xprt *xprt,
 	return true;
 }
 
+/* Finish constructing the RPC Call message in rqstp::rq_arg.
+ *
+ * The incoming RPC/RDMA message is an RDMA_MSG type message
+ * with a single Read chunk (only the upper layer data payload
+ * was conveyed via RDMA Read).
+ */
+static void svc_rdma_read_complete_one(struct svc_rqst *rqstp,
+				       struct svc_rdma_recv_ctxt *ctxt)
+{
+	struct svc_rdma_chunk *chunk = pcl_first_chunk(&ctxt->rc_read_pcl);
+	struct xdr_buf *buf = &rqstp->rq_arg;
+	unsigned int length;
+
+	/* Split the Receive buffer between the head and tail
+	 * buffers at Read chunk's position. XDR roundup of the
+	 * chunk is not included in either the pagelist or in
+	 * the tail.
+	 */
+	buf->tail[0].iov_base = buf->head[0].iov_base + chunk->ch_position;
+	buf->tail[0].iov_len = buf->head[0].iov_len - chunk->ch_position;
+	buf->head[0].iov_len = chunk->ch_position;
+
+	/* Read chunk may need XDR roundup (see RFC 8166, s. 3.4.5.2).
+	 *
+	 * If the client already rounded up the chunk length, the
+	 * length does not change. Otherwise, the length of the page
+	 * list is increased to include XDR round-up.
+	 *
+	 * Currently these chunks always start at page offset 0,
+	 * thus the rounded-up length never crosses a page boundary.
+	 */
+	buf->pages = &rqstp->rq_pages[0];
+	length = xdr_align_size(chunk->ch_length);
+	buf->page_len = length;
+	buf->len += length;
+	buf->buflen += length;
+}
+
+/* Finish constructing the RPC Call message in rqstp::rq_arg.
+ *
+ * The incoming RPC/RDMA message is an RDMA_MSG type message
+ * with payload in multiple Read chunks and no PZRC.
+ */
+static void svc_rdma_read_complete_multiple(struct svc_rqst *rqstp,
+					    struct svc_rdma_recv_ctxt *ctxt)
+{
+	struct xdr_buf *buf = &rqstp->rq_arg;
+
+	buf->len += ctxt->rc_readbytes;
+	buf->buflen += ctxt->rc_readbytes;
+
+	buf->head[0].iov_base = page_address(rqstp->rq_pages[0]);
+	buf->head[0].iov_len = min_t(size_t, PAGE_SIZE, ctxt->rc_readbytes);
+	buf->pages = &rqstp->rq_pages[1];
+	buf->page_len = ctxt->rc_readbytes - buf->head[0].iov_len;
+}
+
+/* Finish constructing the RPC Call message in rqstp::rq_arg.
+ *
+ * The incoming RPC/RDMA message is an RDMA_NOMSG type message
+ * (the RPC message body was conveyed via RDMA Read).
+ */
+static void svc_rdma_read_complete_pzrc(struct svc_rqst *rqstp,
+					struct svc_rdma_recv_ctxt *ctxt)
+{
+	struct xdr_buf *buf = &rqstp->rq_arg;
+
+	buf->len += ctxt->rc_readbytes;
+	buf->buflen += ctxt->rc_readbytes;
+
+	buf->head[0].iov_base = page_address(rqstp->rq_pages[0]);
+	buf->head[0].iov_len = min_t(size_t, PAGE_SIZE, ctxt->rc_readbytes);
+	buf->pages = &rqstp->rq_pages[1];
+	buf->page_len = ctxt->rc_readbytes - buf->head[0].iov_len;
+}
+
+static noinline void svc_rdma_read_complete(struct svc_rqst *rqstp,
+					    struct svc_rdma_recv_ctxt *ctxt)
+{
+	unsigned int i;
+
+	/* Transfer the Read chunk pages into @rqstp.rq_pages, replacing
+	 * the rq_pages that were already allocated for this rqstp.
+	 */
+	release_pages(rqstp->rq_respages, ctxt->rc_page_count);
+	for (i = 0; i < ctxt->rc_page_count; i++)
+		rqstp->rq_pages[i] = ctxt->rc_pages[i];
+
+	/* Update @rqstp's result send buffer to start after the
+	 * last page in the RDMA Read payload.
+	 */
+	rqstp->rq_respages = &rqstp->rq_pages[ctxt->rc_page_count];
+	rqstp->rq_next_page = rqstp->rq_respages + 1;
+
+	/* Prevent svc_rdma_recv_ctxt_put() from releasing the
+	 * pages in ctxt::rc_pages a second time.
+	 */
+	ctxt->rc_page_count = 0;
+
+	/* Finish constructing the RPC Call message. The exact
+	 * procedure for that depends on what kind of RPC/RDMA
+	 * chunks were provided by the client.
+	 */
+	rqstp->rq_arg = ctxt->rc_saved_arg;
+	if (pcl_is_empty(&ctxt->rc_call_pcl)) {
+		if (ctxt->rc_read_pcl.cl_count == 1)
+			svc_rdma_read_complete_one(rqstp, ctxt);
+		else
+			svc_rdma_read_complete_multiple(rqstp, ctxt);
+	} else {
+		svc_rdma_read_complete_pzrc(rqstp, ctxt);
+	}
+
+	trace_svcrdma_read_finished(&ctxt->rc_cid);
+}
+
 /**
  * svc_rdma_recvfrom - Receive an RPC call
  * @rqstp: request structure into which to receive an RPC Call
@@ -798,8 +929,15 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 
 	rqstp->rq_xprt_ctxt = NULL;
 
-	ctxt = NULL;
 	spin_lock(&rdma_xprt->sc_rq_dto_lock);
+	ctxt = svc_rdma_next_recv_ctxt(&rdma_xprt->sc_read_complete_q);
+	if (ctxt) {
+		list_del(&ctxt->rc_list);
+		spin_unlock(&rdma_xprt->sc_rq_dto_lock);
+		svc_xprt_received(xprt);
+		svc_rdma_read_complete(rqstp, ctxt);
+		goto complete;
+	}
 	ctxt = svc_rdma_next_recv_ctxt(&rdma_xprt->sc_rq_dto_q);
 	if (ctxt)
 		list_del(&ctxt->rc_list);
@@ -831,12 +969,10 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 	svc_rdma_get_inv_rkey(rdma_xprt, ctxt);
 
 	if (!pcl_is_empty(&ctxt->rc_read_pcl) ||
-	    !pcl_is_empty(&ctxt->rc_call_pcl)) {
-		ret = svc_rdma_process_read_list(rdma_xprt, rqstp, ctxt);
-		if (ret < 0)
-			goto out_readfail;
-	}
+	    !pcl_is_empty(&ctxt->rc_call_pcl))
+		goto out_readlist;
 
+complete:
 	rqstp->rq_xprt_ctxt = ctxt;
 	rqstp->rq_prot = IPPROTO_MAX;
 	svc_xprt_copy_addrs(rqstp, xprt);
@@ -848,12 +984,23 @@ out_err:
 	svc_rdma_recv_ctxt_put(rdma_xprt, ctxt);
 	return 0;
 
-out_readfail:
-	if (ret == -EINVAL)
-		svc_rdma_send_error(rdma_xprt, ctxt, ret);
-	svc_rdma_recv_ctxt_put(rdma_xprt, ctxt);
-	svc_xprt_deferred_close(xprt);
-	return -ENOTCONN;
+out_readlist:
+	/* This @rqstp is about to be recycled. Save the work
+	 * already done constructing the Call message in rq_arg
+	 * so it can be restored when the RDMA Reads have
+	 * completed.
+	 */
+	ctxt->rc_saved_arg = rqstp->rq_arg;
+
+	ret = svc_rdma_process_read_list(rdma_xprt, rqstp, ctxt);
+	if (ret < 0) {
+		if (ret == -EINVAL)
+			svc_rdma_send_error(rdma_xprt, ctxt, ret);
+		svc_rdma_recv_ctxt_put(rdma_xprt, ctxt);
+		svc_xprt_deferred_close(xprt);
+		return ret;
+	}
+	return 0;
 
 out_backchannel:
 	svc_rdma_handle_bc_reply(rqstp, ctxt);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index e460e25a1d6d..c00fcce61d1e 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -39,6 +39,7 @@ struct svc_rdma_rw_ctxt {
 	struct list_head	rw_list;
 	struct rdma_rw_ctx	rw_ctx;
 	unsigned int		rw_nents;
+	unsigned int		rw_first_sgl_nents;
 	struct sg_table		rw_sg_table;
 	struct scatterlist	rw_first_sgl[];
 };
@@ -53,6 +54,8 @@ svc_rdma_next_ctxt(struct list_head *list)
 static struct svc_rdma_rw_ctxt *
 svc_rdma_get_rw_ctxt(struct svcxprt_rdma *rdma, unsigned int sges)
 {
+	struct ib_device *dev = rdma->sc_cm_id->device;
+	unsigned int first_sgl_nents = dev->attrs.max_send_sge;
 	struct svc_rdma_rw_ctxt *ctxt;
 	struct llist_node *node;
 
@@ -62,32 +65,33 @@ svc_rdma_get_rw_ctxt(struct svcxprt_rdma *rdma, unsigned int sges)
 	if (node) {
 		ctxt = llist_entry(node, struct svc_rdma_rw_ctxt, rw_node);
 	} else {
-		ctxt = kmalloc_node(struct_size(ctxt, rw_first_sgl, SG_CHUNK_SIZE),
-				    GFP_KERNEL, ibdev_to_node(rdma->sc_cm_id->device));
+		ctxt = kmalloc_node(struct_size(ctxt, rw_first_sgl, first_sgl_nents),
+				    GFP_KERNEL, ibdev_to_node(dev));
 		if (!ctxt)
 			goto out_noctx;
 
 		INIT_LIST_HEAD(&ctxt->rw_list);
+		ctxt->rw_first_sgl_nents = first_sgl_nents;
 	}
 
 	ctxt->rw_sg_table.sgl = ctxt->rw_first_sgl;
 	if (sg_alloc_table_chained(&ctxt->rw_sg_table, sges,
 				   ctxt->rw_sg_table.sgl,
-				   SG_CHUNK_SIZE))
+				   first_sgl_nents))
 		goto out_free;
 	return ctxt;
 
 out_free:
 	kfree(ctxt);
 out_noctx:
-	trace_svcrdma_no_rwctx_err(rdma, sges);
+	trace_svcrdma_rwctx_empty(rdma, sges);
 	return NULL;
 }
 
 static void __svc_rdma_put_rw_ctxt(struct svc_rdma_rw_ctxt *ctxt,
 				   struct llist_head *list)
 {
-	sg_free_table_chained(&ctxt->rw_sg_table, SG_CHUNK_SIZE);
+	sg_free_table_chained(&ctxt->rw_sg_table, ctxt->rw_first_sgl_nents);
 	llist_add(&ctxt->rw_node, list);
 }
 
@@ -135,57 +139,40 @@ static int svc_rdma_rw_ctx_init(struct svcxprt_rdma *rdma,
 			       ctxt->rw_sg_table.sgl, ctxt->rw_nents,
 			       0, offset, handle, direction);
 	if (unlikely(ret < 0)) {
+		trace_svcrdma_dma_map_rw_err(rdma, offset, handle,
+					     ctxt->rw_nents, ret);
 		svc_rdma_put_rw_ctxt(rdma, ctxt);
-		trace_svcrdma_dma_map_rw_err(rdma, ctxt->rw_nents, ret);
 	}
 	return ret;
 }
 
-/* A chunk context tracks all I/O for moving one Read or Write
- * chunk. This is a set of rdma_rw's that handle data movement
- * for all segments of one chunk.
- *
- * These are small, acquired with a single allocator call, and
- * no more than one is needed per chunk. They are allocated on
- * demand, and not cached.
+/**
+ * svc_rdma_cc_init - Initialize an svc_rdma_chunk_ctxt
+ * @rdma: controlling transport instance
+ * @cc: svc_rdma_chunk_ctxt to be initialized
  */
-struct svc_rdma_chunk_ctxt {
-	struct rpc_rdma_cid	cc_cid;
-	struct ib_cqe		cc_cqe;
-	struct svcxprt_rdma	*cc_rdma;
-	struct list_head	cc_rwctxts;
-	ktime_t			cc_posttime;
-	int			cc_sqecount;
-	enum ib_wc_status	cc_status;
-	struct completion	cc_done;
-};
-
-static void svc_rdma_cc_cid_init(struct svcxprt_rdma *rdma,
-				 struct rpc_rdma_cid *cid)
+void svc_rdma_cc_init(struct svcxprt_rdma *rdma,
+		      struct svc_rdma_chunk_ctxt *cc)
 {
-	cid->ci_queue_id = rdma->sc_sq_cq->res.id;
-	cid->ci_completion_id = atomic_inc_return(&rdma->sc_completion_ids);
-}
+	struct rpc_rdma_cid *cid = &cc->cc_cid;
 
-static void svc_rdma_cc_init(struct svcxprt_rdma *rdma,
-			     struct svc_rdma_chunk_ctxt *cc)
-{
-	svc_rdma_cc_cid_init(rdma, &cc->cc_cid);
-	cc->cc_rdma = rdma;
+	if (unlikely(!cid->ci_completion_id))
+		svc_rdma_send_cid_init(rdma, cid);
 
 	INIT_LIST_HEAD(&cc->cc_rwctxts);
 	cc->cc_sqecount = 0;
 }
 
-/*
- * The consumed rw_ctx's are cleaned and placed on a local llist so
- * that only one atomic llist operation is needed to put them all
- * back on the free list.
+/**
+ * svc_rdma_cc_release - Release resources held by a svc_rdma_chunk_ctxt
+ * @rdma: controlling transport instance
+ * @cc: svc_rdma_chunk_ctxt to be released
+ * @dir: DMA direction
  */
-static void svc_rdma_cc_release(struct svc_rdma_chunk_ctxt *cc,
-				enum dma_data_direction dir)
+void svc_rdma_cc_release(struct svcxprt_rdma *rdma,
+			 struct svc_rdma_chunk_ctxt *cc,
+			 enum dma_data_direction dir)
 {
-	struct svcxprt_rdma *rdma = cc->cc_rdma;
 	struct llist_node *first, *last;
 	struct svc_rdma_rw_ctxt *ctxt;
 	LLIST_HEAD(free);
@@ -215,6 +202,8 @@ static void svc_rdma_cc_release(struct svc_rdma_chunk_ctxt *cc,
  *  - Stores arguments for the SGL constructor functions
  */
 struct svc_rdma_write_info {
+	struct svcxprt_rdma	*wi_rdma;
+
 	const struct svc_rdma_chunk	*wi_chunk;
 
 	/* write state of this chunk */
@@ -227,6 +216,7 @@ struct svc_rdma_write_info {
 	unsigned int		wi_next_off;
 
 	struct svc_rdma_chunk_ctxt	wi_cc;
+	struct work_struct	wi_work;
 };
 
 static struct svc_rdma_write_info *
@@ -235,25 +225,33 @@ svc_rdma_write_info_alloc(struct svcxprt_rdma *rdma,
 {
 	struct svc_rdma_write_info *info;
 
-	info = kmalloc_node(sizeof(*info), GFP_KERNEL,
+	info = kzalloc_node(sizeof(*info), GFP_KERNEL,
 			    ibdev_to_node(rdma->sc_cm_id->device));
 	if (!info)
 		return info;
 
+	info->wi_rdma = rdma;
 	info->wi_chunk = chunk;
-	info->wi_seg_off = 0;
-	info->wi_seg_no = 0;
 	svc_rdma_cc_init(rdma, &info->wi_cc);
 	info->wi_cc.cc_cqe.done = svc_rdma_write_done;
 	return info;
 }
 
-static void svc_rdma_write_info_free(struct svc_rdma_write_info *info)
+static void svc_rdma_write_info_free_async(struct work_struct *work)
 {
-	svc_rdma_cc_release(&info->wi_cc, DMA_TO_DEVICE);
+	struct svc_rdma_write_info *info;
+
+	info = container_of(work, struct svc_rdma_write_info, wi_work);
+	svc_rdma_cc_release(info->wi_rdma, &info->wi_cc, DMA_TO_DEVICE);
 	kfree(info);
 }
 
+static void svc_rdma_write_info_free(struct svc_rdma_write_info *info)
+{
+	INIT_WORK(&info->wi_work, svc_rdma_write_info_free_async);
+	queue_work(svcrdma_wq, &info->wi_work);
+}
+
 /**
  * svc_rdma_write_done - Write chunk completion
  * @cq: controlling Completion Queue
@@ -263,16 +261,16 @@ static void svc_rdma_write_info_free(struct svc_rdma_write_info *info)
  */
 static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc)
 {
+	struct svcxprt_rdma *rdma = cq->cq_context;
 	struct ib_cqe *cqe = wc->wr_cqe;
 	struct svc_rdma_chunk_ctxt *cc =
 			container_of(cqe, struct svc_rdma_chunk_ctxt, cc_cqe);
-	struct svcxprt_rdma *rdma = cc->cc_rdma;
 	struct svc_rdma_write_info *info =
 			container_of(cc, struct svc_rdma_write_info, wi_cc);
 
 	switch (wc->status) {
 	case IB_WC_SUCCESS:
-		trace_svcrdma_wc_write(wc, &cc->cc_cid);
+		trace_svcrdma_wc_write(&cc->cc_cid);
 		break;
 	case IB_WC_WR_FLUSH_ERR:
 		trace_svcrdma_wc_write_flush(wc, &cc->cc_cid);
@@ -289,39 +287,6 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc)
 	svc_rdma_write_info_free(info);
 }
 
-/* State for pulling a Read chunk.
- */
-struct svc_rdma_read_info {
-	struct svc_rqst			*ri_rqst;
-	struct svc_rdma_recv_ctxt	*ri_readctxt;
-	unsigned int			ri_pageno;
-	unsigned int			ri_pageoff;
-	unsigned int			ri_totalbytes;
-
-	struct svc_rdma_chunk_ctxt	ri_cc;
-};
-
-static struct svc_rdma_read_info *
-svc_rdma_read_info_alloc(struct svcxprt_rdma *rdma)
-{
-	struct svc_rdma_read_info *info;
-
-	info = kmalloc_node(sizeof(*info), GFP_KERNEL,
-			    ibdev_to_node(rdma->sc_cm_id->device));
-	if (!info)
-		return info;
-
-	svc_rdma_cc_init(rdma, &info->ri_cc);
-	info->ri_cc.cc_cqe.done = svc_rdma_wc_read_done;
-	return info;
-}
-
-static void svc_rdma_read_info_free(struct svc_rdma_read_info *info)
-{
-	svc_rdma_cc_release(&info->ri_cc, DMA_FROM_DEVICE);
-	kfree(info);
-}
-
 /**
  * svc_rdma_wc_read_done - Handle completion of an RDMA Read ctx
  * @cq: controlling Completion Queue
@@ -330,17 +295,27 @@ static void svc_rdma_read_info_free(struct svc_rdma_read_info *info)
  */
 static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc)
 {
+	struct svcxprt_rdma *rdma = cq->cq_context;
 	struct ib_cqe *cqe = wc->wr_cqe;
 	struct svc_rdma_chunk_ctxt *cc =
 			container_of(cqe, struct svc_rdma_chunk_ctxt, cc_cqe);
-	struct svc_rdma_read_info *info;
+	struct svc_rdma_recv_ctxt *ctxt;
 
+	svc_rdma_wake_send_waiters(rdma, cc->cc_sqecount);
+
+	ctxt = container_of(cc, struct svc_rdma_recv_ctxt, rc_cc);
 	switch (wc->status) {
 	case IB_WC_SUCCESS:
-		info = container_of(cc, struct svc_rdma_read_info, ri_cc);
-		trace_svcrdma_wc_read(wc, &cc->cc_cid, info->ri_totalbytes,
+		trace_svcrdma_wc_read(wc, &cc->cc_cid, ctxt->rc_readbytes,
 				      cc->cc_posttime);
-		break;
+
+		spin_lock(&rdma->sc_rq_dto_lock);
+		list_add_tail(&ctxt->rc_list, &rdma->sc_read_complete_q);
+		/* the unlock pairs with the smp_rmb in svc_xprt_ready */
+		set_bit(XPT_DATA, &rdma->sc_xprt.xpt_flags);
+		spin_unlock(&rdma->sc_rq_dto_lock);
+		svc_xprt_enqueue(&rdma->sc_xprt);
+		return;
 	case IB_WC_WR_FLUSH_ERR:
 		trace_svcrdma_wc_read_flush(wc, &cc->cc_cid);
 		break;
@@ -348,10 +323,13 @@ static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc)
 		trace_svcrdma_wc_read_err(wc, &cc->cc_cid);
 	}
 
-	svc_rdma_wake_send_waiters(cc->cc_rdma, cc->cc_sqecount);
-	cc->cc_status = wc->status;
-	complete(&cc->cc_done);
-	return;
+	/* The RDMA Read has flushed, so the incoming RPC message
+	 * cannot be constructed and must be dropped. Signal the
+	 * loss to the client by closing the connection.
+	 */
+	svc_rdma_cc_release(rdma, cc, DMA_FROM_DEVICE);
+	svc_rdma_recv_ctxt_put(rdma, ctxt);
+	svc_xprt_deferred_close(&rdma->sc_xprt);
 }
 
 /*
@@ -360,9 +338,9 @@ static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc)
  *   even if one or more WRs are flushed. This is true when posting
  *   an rdma_rw_ctx or when posting a single signaled WR.
  */
-static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc)
+static int svc_rdma_post_chunk_ctxt(struct svcxprt_rdma *rdma,
+				    struct svc_rdma_chunk_ctxt *cc)
 {
-	struct svcxprt_rdma *rdma = cc->cc_rdma;
 	struct ib_send_wr *first_wr;
 	const struct ib_send_wr *bad_wr;
 	struct list_head *tmp;
@@ -396,14 +374,14 @@ static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc)
 		}
 
 		percpu_counter_inc(&svcrdma_stat_sq_starve);
-		trace_svcrdma_sq_full(rdma);
+		trace_svcrdma_sq_full(rdma, &cc->cc_cid);
 		atomic_add(cc->cc_sqecount, &rdma->sc_sq_avail);
 		wait_event(rdma->sc_send_wait,
 			   atomic_read(&rdma->sc_sq_avail) > cc->cc_sqecount);
-		trace_svcrdma_sq_retry(rdma);
+		trace_svcrdma_sq_retry(rdma, &cc->cc_cid);
 	} while (1);
 
-	trace_svcrdma_sq_post_err(rdma, ret);
+	trace_svcrdma_sq_post_err(rdma, &cc->cc_cid, ret);
 	svc_xprt_deferred_close(&rdma->sc_xprt);
 
 	/* If even one was posted, there will be a completion. */
@@ -473,7 +451,7 @@ svc_rdma_build_writes(struct svc_rdma_write_info *info,
 		      unsigned int remaining)
 {
 	struct svc_rdma_chunk_ctxt *cc = &info->wi_cc;
-	struct svcxprt_rdma *rdma = cc->cc_rdma;
+	struct svcxprt_rdma *rdma = info->wi_rdma;
 	const struct svc_rdma_segment *seg;
 	struct svc_rdma_rw_ctxt *ctxt;
 	int ret;
@@ -516,7 +494,7 @@ svc_rdma_build_writes(struct svc_rdma_write_info *info,
 	return 0;
 
 out_overflow:
-	trace_svcrdma_small_wrch_err(rdma, remaining, info->wi_seg_no,
+	trace_svcrdma_small_wrch_err(&cc->cc_cid, remaining, info->wi_seg_no,
 				     info->wi_chunk->ch_segcount);
 	return -E2BIG;
 }
@@ -633,7 +611,7 @@ int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
 		goto out_err;
 
 	trace_svcrdma_post_write_chunk(&cc->cc_cid, cc->cc_sqecount);
-	ret = svc_rdma_post_chunk_ctxt(cc);
+	ret = svc_rdma_post_chunk_ctxt(rdma, cc);
 	if (ret < 0)
 		goto out_err;
 	return xdr->len;
@@ -680,7 +658,7 @@ int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma,
 		goto out_err;
 
 	trace_svcrdma_post_reply_chunk(&cc->cc_cid, cc->cc_sqecount);
-	ret = svc_rdma_post_chunk_ctxt(cc);
+	ret = svc_rdma_post_chunk_ctxt(rdma, cc);
 	if (ret < 0)
 		goto out_err;
 
@@ -693,7 +671,8 @@ out_err:
 
 /**
  * svc_rdma_build_read_segment - Build RDMA Read WQEs to pull one RDMA segment
- * @info: context for ongoing I/O
+ * @rqstp: RPC transaction context
+ * @head: context for ongoing I/O
  * @segment: co-ordinates of remote memory to be read
  *
  * Returns:
@@ -702,20 +681,20 @@ out_err:
  *   %-ENOMEM: allocating a local resources failed
  *   %-EIO: a DMA mapping error occurred
  */
-static int svc_rdma_build_read_segment(struct svc_rdma_read_info *info,
+static int svc_rdma_build_read_segment(struct svc_rqst *rqstp,
+				       struct svc_rdma_recv_ctxt *head,
 				       const struct svc_rdma_segment *segment)
 {
-	struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
-	struct svc_rdma_chunk_ctxt *cc = &info->ri_cc;
-	struct svc_rqst *rqstp = info->ri_rqst;
+	struct svcxprt_rdma *rdma = svc_rdma_rqst_rdma(rqstp);
+	struct svc_rdma_chunk_ctxt *cc = &head->rc_cc;
 	unsigned int sge_no, seg_len, len;
 	struct svc_rdma_rw_ctxt *ctxt;
 	struct scatterlist *sg;
 	int ret;
 
 	len = segment->rs_length;
-	sge_no = PAGE_ALIGN(info->ri_pageoff + len) >> PAGE_SHIFT;
-	ctxt = svc_rdma_get_rw_ctxt(cc->cc_rdma, sge_no);
+	sge_no = PAGE_ALIGN(head->rc_pageoff + len) >> PAGE_SHIFT;
+	ctxt = svc_rdma_get_rw_ctxt(rdma, sge_no);
 	if (!ctxt)
 		return -ENOMEM;
 	ctxt->rw_nents = sge_no;
@@ -723,29 +702,27 @@ static int svc_rdma_build_read_segment(struct svc_rdma_read_info *info,
 	sg = ctxt->rw_sg_table.sgl;
 	for (sge_no = 0; sge_no < ctxt->rw_nents; sge_no++) {
 		seg_len = min_t(unsigned int, len,
-				PAGE_SIZE - info->ri_pageoff);
+				PAGE_SIZE - head->rc_pageoff);
 
-		if (!info->ri_pageoff)
+		if (!head->rc_pageoff)
 			head->rc_page_count++;
 
-		sg_set_page(sg, rqstp->rq_pages[info->ri_pageno],
-			    seg_len, info->ri_pageoff);
+		sg_set_page(sg, rqstp->rq_pages[head->rc_curpage],
+			    seg_len, head->rc_pageoff);
 		sg = sg_next(sg);
 
-		info->ri_pageoff += seg_len;
-		if (info->ri_pageoff == PAGE_SIZE) {
-			info->ri_pageno++;
-			info->ri_pageoff = 0;
+		head->rc_pageoff += seg_len;
+		if (head->rc_pageoff == PAGE_SIZE) {
+			head->rc_curpage++;
+			head->rc_pageoff = 0;
 		}
 		len -= seg_len;
 
-		/* Safety check */
-		if (len &&
-		    &rqstp->rq_pages[info->ri_pageno + 1] > rqstp->rq_page_end)
+		if (len && ((head->rc_curpage + 1) > ARRAY_SIZE(rqstp->rq_pages)))
 			goto out_overrun;
 	}
 
-	ret = svc_rdma_rw_ctx_init(cc->cc_rdma, ctxt, segment->rs_offset,
+	ret = svc_rdma_rw_ctx_init(rdma, ctxt, segment->rs_offset,
 				   segment->rs_handle, DMA_FROM_DEVICE);
 	if (ret < 0)
 		return -EIO;
@@ -756,13 +733,14 @@ static int svc_rdma_build_read_segment(struct svc_rdma_read_info *info,
 	return 0;
 
 out_overrun:
-	trace_svcrdma_page_overrun_err(cc->cc_rdma, rqstp, info->ri_pageno);
+	trace_svcrdma_page_overrun_err(&cc->cc_cid, head->rc_curpage);
 	return -EINVAL;
 }
 
 /**
  * svc_rdma_build_read_chunk - Build RDMA Read WQEs to pull one RDMA chunk
- * @info: context for ongoing I/O
+ * @rqstp: RPC transaction context
+ * @head: context for ongoing I/O
  * @chunk: Read chunk to pull
  *
  * Return values:
@@ -771,7 +749,8 @@ out_overrun:
  *   %-ENOMEM: allocating a local resources failed
  *   %-EIO: a DMA mapping error occurred
  */
-static int svc_rdma_build_read_chunk(struct svc_rdma_read_info *info,
+static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp,
+				     struct svc_rdma_recv_ctxt *head,
 				     const struct svc_rdma_chunk *chunk)
 {
 	const struct svc_rdma_segment *segment;
@@ -779,56 +758,56 @@ static int svc_rdma_build_read_chunk(struct svc_rdma_read_info *info,
 
 	ret = -EINVAL;
 	pcl_for_each_segment(segment, chunk) {
-		ret = svc_rdma_build_read_segment(info, segment);
+		ret = svc_rdma_build_read_segment(rqstp, head, segment);
 		if (ret < 0)
 			break;
-		info->ri_totalbytes += segment->rs_length;
+		head->rc_readbytes += segment->rs_length;
 	}
 	return ret;
 }
 
 /**
  * svc_rdma_copy_inline_range - Copy part of the inline content into pages
- * @info: context for RDMA Reads
+ * @rqstp: RPC transaction context
+ * @head: context for ongoing I/O
  * @offset: offset into the Receive buffer of region to copy
  * @remaining: length of region to copy
  *
  * Take a page at a time from rqstp->rq_pages and copy the inline
  * content from the Receive buffer into that page. Update
- * info->ri_pageno and info->ri_pageoff so that the next RDMA Read
+ * head->rc_curpage and head->rc_pageoff so that the next RDMA Read
  * result will land contiguously with the copied content.
  *
  * Return values:
  *   %0: Inline content was successfully copied
  *   %-EINVAL: offset or length was incorrect
  */
-static int svc_rdma_copy_inline_range(struct svc_rdma_read_info *info,
+static int svc_rdma_copy_inline_range(struct svc_rqst *rqstp,
+				      struct svc_rdma_recv_ctxt *head,
 				      unsigned int offset,
 				      unsigned int remaining)
 {
-	struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
 	unsigned char *dst, *src = head->rc_recv_buf;
-	struct svc_rqst *rqstp = info->ri_rqst;
 	unsigned int page_no, numpages;
 
-	numpages = PAGE_ALIGN(info->ri_pageoff + remaining) >> PAGE_SHIFT;
+	numpages = PAGE_ALIGN(head->rc_pageoff + remaining) >> PAGE_SHIFT;
 	for (page_no = 0; page_no < numpages; page_no++) {
 		unsigned int page_len;
 
 		page_len = min_t(unsigned int, remaining,
-				 PAGE_SIZE - info->ri_pageoff);
+				 PAGE_SIZE - head->rc_pageoff);
 
-		if (!info->ri_pageoff)
+		if (!head->rc_pageoff)
 			head->rc_page_count++;
 
-		dst = page_address(rqstp->rq_pages[info->ri_pageno]);
-		memcpy(dst + info->ri_pageno, src + offset, page_len);
+		dst = page_address(rqstp->rq_pages[head->rc_curpage]);
+		memcpy(dst + head->rc_curpage, src + offset, page_len);
 
-		info->ri_totalbytes += page_len;
-		info->ri_pageoff += page_len;
-		if (info->ri_pageoff == PAGE_SIZE) {
-			info->ri_pageno++;
-			info->ri_pageoff = 0;
+		head->rc_readbytes += page_len;
+		head->rc_pageoff += page_len;
+		if (head->rc_pageoff == PAGE_SIZE) {
+			head->rc_curpage++;
+			head->rc_pageoff = 0;
 		}
 		remaining -= page_len;
 		offset += page_len;
@@ -839,7 +818,8 @@ static int svc_rdma_copy_inline_range(struct svc_rdma_read_info *info,
 
 /**
  * svc_rdma_read_multiple_chunks - Construct RDMA Reads to pull data item Read chunks
- * @info: context for RDMA Reads
+ * @rqstp: RPC transaction context
+ * @head: context for ongoing I/O
  *
  * The chunk data lands in rqstp->rq_arg as a series of contiguous pages,
  * like an incoming TCP call.
@@ -851,11 +831,11 @@ static int svc_rdma_copy_inline_range(struct svc_rdma_read_info *info,
  *   %-ENOTCONN: posting failed (connection is lost),
  *   %-EIO: rdma_rw initialization failed (DMA mapping, etc).
  */
-static noinline int svc_rdma_read_multiple_chunks(struct svc_rdma_read_info *info)
+static noinline int
+svc_rdma_read_multiple_chunks(struct svc_rqst *rqstp,
+			      struct svc_rdma_recv_ctxt *head)
 {
-	struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
 	const struct svc_rdma_pcl *pcl = &head->rc_read_pcl;
-	struct xdr_buf *buf = &info->ri_rqst->rq_arg;
 	struct svc_rdma_chunk *chunk, *next;
 	unsigned int start, length;
 	int ret;
@@ -863,12 +843,12 @@ static noinline int svc_rdma_read_multiple_chunks(struct svc_rdma_read_info *inf
 	start = 0;
 	chunk = pcl_first_chunk(pcl);
 	length = chunk->ch_position;
-	ret = svc_rdma_copy_inline_range(info, start, length);
+	ret = svc_rdma_copy_inline_range(rqstp, head, start, length);
 	if (ret < 0)
 		return ret;
 
 	pcl_for_each_chunk(chunk, pcl) {
-		ret = svc_rdma_build_read_chunk(info, chunk);
+		ret = svc_rdma_build_read_chunk(rqstp, head, chunk);
 		if (ret < 0)
 			return ret;
 
@@ -877,31 +857,21 @@ static noinline int svc_rdma_read_multiple_chunks(struct svc_rdma_read_info *inf
 			break;
 
 		start += length;
-		length = next->ch_position - info->ri_totalbytes;
-		ret = svc_rdma_copy_inline_range(info, start, length);
+		length = next->ch_position - head->rc_readbytes;
+		ret = svc_rdma_copy_inline_range(rqstp, head, start, length);
 		if (ret < 0)
 			return ret;
 	}
 
 	start += length;
 	length = head->rc_byte_len - start;
-	ret = svc_rdma_copy_inline_range(info, start, length);
-	if (ret < 0)
-		return ret;
-
-	buf->len += info->ri_totalbytes;
-	buf->buflen += info->ri_totalbytes;
-
-	buf->head[0].iov_base = page_address(info->ri_rqst->rq_pages[0]);
-	buf->head[0].iov_len = min_t(size_t, PAGE_SIZE, info->ri_totalbytes);
-	buf->pages = &info->ri_rqst->rq_pages[1];
-	buf->page_len = info->ri_totalbytes - buf->head[0].iov_len;
-	return 0;
+	return svc_rdma_copy_inline_range(rqstp, head, start, length);
 }
 
 /**
  * svc_rdma_read_data_item - Construct RDMA Reads to pull data item Read chunks
- * @info: context for RDMA Reads
+ * @rqstp: RPC transaction context
+ * @head: context for ongoing I/O
  *
  * The chunk data lands in the page list of rqstp->rq_arg.pages.
  *
@@ -916,50 +886,17 @@ static noinline int svc_rdma_read_multiple_chunks(struct svc_rdma_read_info *inf
  *   %-ENOTCONN: posting failed (connection is lost),
  *   %-EIO: rdma_rw initialization failed (DMA mapping, etc).
  */
-static int svc_rdma_read_data_item(struct svc_rdma_read_info *info)
+static int svc_rdma_read_data_item(struct svc_rqst *rqstp,
+				   struct svc_rdma_recv_ctxt *head)
 {
-	struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
-	struct xdr_buf *buf = &info->ri_rqst->rq_arg;
-	struct svc_rdma_chunk *chunk;
-	unsigned int length;
-	int ret;
-
-	chunk = pcl_first_chunk(&head->rc_read_pcl);
-	ret = svc_rdma_build_read_chunk(info, chunk);
-	if (ret < 0)
-		goto out;
-
-	/* Split the Receive buffer between the head and tail
-	 * buffers at Read chunk's position. XDR roundup of the
-	 * chunk is not included in either the pagelist or in
-	 * the tail.
-	 */
-	buf->tail[0].iov_base = buf->head[0].iov_base + chunk->ch_position;
-	buf->tail[0].iov_len = buf->head[0].iov_len - chunk->ch_position;
-	buf->head[0].iov_len = chunk->ch_position;
-
-	/* Read chunk may need XDR roundup (see RFC 8166, s. 3.4.5.2).
-	 *
-	 * If the client already rounded up the chunk length, the
-	 * length does not change. Otherwise, the length of the page
-	 * list is increased to include XDR round-up.
-	 *
-	 * Currently these chunks always start at page offset 0,
-	 * thus the rounded-up length never crosses a page boundary.
-	 */
-	buf->pages = &info->ri_rqst->rq_pages[0];
-	length = xdr_align_size(chunk->ch_length);
-	buf->page_len = length;
-	buf->len += length;
-	buf->buflen += length;
-
-out:
-	return ret;
+	return svc_rdma_build_read_chunk(rqstp, head,
+					 pcl_first_chunk(&head->rc_read_pcl));
 }
 
 /**
- * svc_rdma_read_chunk_range - Build RDMA Read WQEs for portion of a chunk
- * @info: context for RDMA Reads
+ * svc_rdma_read_chunk_range - Build RDMA Read WRs for portion of a chunk
+ * @rqstp: RPC transaction context
+ * @head: context for ongoing I/O
  * @chunk: parsed Call chunk to pull
  * @offset: offset of region to pull
  * @length: length of region to pull
@@ -971,7 +908,8 @@ out:
  *   %-ENOTCONN: posting failed (connection is lost),
  *   %-EIO: rdma_rw initialization failed (DMA mapping, etc).
  */
-static int svc_rdma_read_chunk_range(struct svc_rdma_read_info *info,
+static int svc_rdma_read_chunk_range(struct svc_rqst *rqstp,
+				     struct svc_rdma_recv_ctxt *head,
 				     const struct svc_rdma_chunk *chunk,
 				     unsigned int offset, unsigned int length)
 {
@@ -991,11 +929,11 @@ static int svc_rdma_read_chunk_range(struct svc_rdma_read_info *info,
 		dummy.rs_length = min_t(u32, length, segment->rs_length) - offset;
 		dummy.rs_offset = segment->rs_offset + offset;
 
-		ret = svc_rdma_build_read_segment(info, &dummy);
+		ret = svc_rdma_build_read_segment(rqstp, head, &dummy);
 		if (ret < 0)
 			break;
 
-		info->ri_totalbytes += dummy.rs_length;
+		head->rc_readbytes += dummy.rs_length;
 		length -= dummy.rs_length;
 		offset = 0;
 	}
@@ -1004,7 +942,8 @@ static int svc_rdma_read_chunk_range(struct svc_rdma_read_info *info,
 
 /**
  * svc_rdma_read_call_chunk - Build RDMA Read WQEs to pull a Long Message
- * @info: context for RDMA Reads
+ * @rqstp: RPC transaction context
+ * @head: context for ongoing I/O
  *
  * Return values:
  *   %0: RDMA Read WQEs were successfully built
@@ -1013,9 +952,9 @@ static int svc_rdma_read_chunk_range(struct svc_rdma_read_info *info,
  *   %-ENOTCONN: posting failed (connection is lost),
  *   %-EIO: rdma_rw initialization failed (DMA mapping, etc).
  */
-static int svc_rdma_read_call_chunk(struct svc_rdma_read_info *info)
+static int svc_rdma_read_call_chunk(struct svc_rqst *rqstp,
+				    struct svc_rdma_recv_ctxt *head)
 {
-	struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
 	const struct svc_rdma_chunk *call_chunk =
 			pcl_first_chunk(&head->rc_call_pcl);
 	const struct svc_rdma_pcl *pcl = &head->rc_read_pcl;
@@ -1024,17 +963,18 @@ static int svc_rdma_read_call_chunk(struct svc_rdma_read_info *info)
 	int ret;
 
 	if (pcl_is_empty(pcl))
-		return svc_rdma_build_read_chunk(info, call_chunk);
+		return svc_rdma_build_read_chunk(rqstp, head, call_chunk);
 
 	start = 0;
 	chunk = pcl_first_chunk(pcl);
 	length = chunk->ch_position;
-	ret = svc_rdma_read_chunk_range(info, call_chunk, start, length);
+	ret = svc_rdma_read_chunk_range(rqstp, head, call_chunk,
+					start, length);
 	if (ret < 0)
 		return ret;
 
 	pcl_for_each_chunk(chunk, pcl) {
-		ret = svc_rdma_build_read_chunk(info, chunk);
+		ret = svc_rdma_build_read_chunk(rqstp, head, chunk);
 		if (ret < 0)
 			return ret;
 
@@ -1043,8 +983,8 @@ static int svc_rdma_read_call_chunk(struct svc_rdma_read_info *info)
 			break;
 
 		start += length;
-		length = next->ch_position - info->ri_totalbytes;
-		ret = svc_rdma_read_chunk_range(info, call_chunk,
+		length = next->ch_position - head->rc_readbytes;
+		ret = svc_rdma_read_chunk_range(rqstp, head, call_chunk,
 						start, length);
 		if (ret < 0)
 			return ret;
@@ -1052,12 +992,14 @@ static int svc_rdma_read_call_chunk(struct svc_rdma_read_info *info)
 
 	start += length;
 	length = call_chunk->ch_length - start;
-	return svc_rdma_read_chunk_range(info, call_chunk, start, length);
+	return svc_rdma_read_chunk_range(rqstp, head, call_chunk,
+					 start, length);
 }
 
 /**
  * svc_rdma_read_special - Build RDMA Read WQEs to pull a Long Message
- * @info: context for RDMA Reads
+ * @rqstp: RPC transaction context
+ * @head: context for ongoing I/O
  *
  * The start of the data lands in the first page just after the
  * Transport header, and the rest lands in rqstp->rq_arg.pages.
@@ -1073,25 +1015,31 @@ static int svc_rdma_read_call_chunk(struct svc_rdma_read_info *info)
  *   %-ENOTCONN: posting failed (connection is lost),
  *   %-EIO: rdma_rw initialization failed (DMA mapping, etc).
  */
-static noinline int svc_rdma_read_special(struct svc_rdma_read_info *info)
+static noinline int svc_rdma_read_special(struct svc_rqst *rqstp,
+					  struct svc_rdma_recv_ctxt *head)
 {
-	struct xdr_buf *buf = &info->ri_rqst->rq_arg;
-	int ret;
-
-	ret = svc_rdma_read_call_chunk(info);
-	if (ret < 0)
-		goto out;
-
-	buf->len += info->ri_totalbytes;
-	buf->buflen += info->ri_totalbytes;
+	return svc_rdma_read_call_chunk(rqstp, head);
+}
 
-	buf->head[0].iov_base = page_address(info->ri_rqst->rq_pages[0]);
-	buf->head[0].iov_len = min_t(size_t, PAGE_SIZE, info->ri_totalbytes);
-	buf->pages = &info->ri_rqst->rq_pages[1];
-	buf->page_len = info->ri_totalbytes - buf->head[0].iov_len;
+/* Pages under I/O have been copied to head->rc_pages. Ensure that
+ * svc_xprt_release() does not put them when svc_rdma_recvfrom()
+ * returns. This has to be done after all Read WRs are constructed
+ * to properly handle a page that happens to be part of I/O on behalf
+ * of two different RDMA segments.
+ *
+ * Note: if the subsequent post_send fails, these pages have already
+ * been moved to head->rc_pages and thus will be cleaned up by
+ * svc_rdma_recv_ctxt_put().
+ */
+static void svc_rdma_clear_rqst_pages(struct svc_rqst *rqstp,
+				      struct svc_rdma_recv_ctxt *head)
+{
+	unsigned int i;
 
-out:
-	return ret;
+	for (i = 0; i < head->rc_page_count; i++) {
+		head->rc_pages[i] = rqstp->rq_pages[i];
+		rqstp->rq_pages[i] = NULL;
+	}
 }
 
 /**
@@ -1121,49 +1069,27 @@ int svc_rdma_process_read_list(struct svcxprt_rdma *rdma,
 			       struct svc_rqst *rqstp,
 			       struct svc_rdma_recv_ctxt *head)
 {
-	struct svc_rdma_read_info *info;
-	struct svc_rdma_chunk_ctxt *cc;
+	struct svc_rdma_chunk_ctxt *cc = &head->rc_cc;
 	int ret;
 
-	info = svc_rdma_read_info_alloc(rdma);
-	if (!info)
-		return -ENOMEM;
-	cc = &info->ri_cc;
-	info->ri_rqst = rqstp;
-	info->ri_readctxt = head;
-	info->ri_pageno = 0;
-	info->ri_pageoff = 0;
-	info->ri_totalbytes = 0;
+	cc->cc_cqe.done = svc_rdma_wc_read_done;
+	cc->cc_sqecount = 0;
+	head->rc_pageoff = 0;
+	head->rc_curpage = 0;
+	head->rc_readbytes = 0;
 
 	if (pcl_is_empty(&head->rc_call_pcl)) {
 		if (head->rc_read_pcl.cl_count == 1)
-			ret = svc_rdma_read_data_item(info);
+			ret = svc_rdma_read_data_item(rqstp, head);
 		else
-			ret = svc_rdma_read_multiple_chunks(info);
+			ret = svc_rdma_read_multiple_chunks(rqstp, head);
 	} else
-		ret = svc_rdma_read_special(info);
+		ret = svc_rdma_read_special(rqstp, head);
+	svc_rdma_clear_rqst_pages(rqstp, head);
 	if (ret < 0)
-		goto out_err;
+		return ret;
 
 	trace_svcrdma_post_read_chunk(&cc->cc_cid, cc->cc_sqecount);
-	init_completion(&cc->cc_done);
-	ret = svc_rdma_post_chunk_ctxt(cc);
-	if (ret < 0)
-		goto out_err;
-
-	ret = 1;
-	wait_for_completion(&cc->cc_done);
-	if (cc->cc_status != IB_WC_SUCCESS)
-		ret = -EIO;
-
-	/* rq_respages starts after the last arg page */
-	rqstp->rq_respages = &rqstp->rq_pages[head->rc_page_count];
-	rqstp->rq_next_page = rqstp->rq_respages + 1;
-
-	/* Ensure svc_rdma_recv_ctxt_put() does not try to release pages */
-	head->rc_page_count = 0;
-
-out_err:
-	svc_rdma_read_info_free(info);
-	return ret;
+	ret = svc_rdma_post_chunk_ctxt(rdma, cc);
+	return ret < 0 ? ret : 1;
 }
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index c6644cca52c5..1a49b7f02041 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -113,13 +113,6 @@
 
 static void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc);
 
-static void svc_rdma_send_cid_init(struct svcxprt_rdma *rdma,
-				   struct rpc_rdma_cid *cid)
-{
-	cid->ci_queue_id = rdma->sc_sq_cq->res.id;
-	cid->ci_completion_id = atomic_inc_return(&rdma->sc_completion_ids);
-}
-
 static struct svc_rdma_send_ctxt *
 svc_rdma_send_ctxt_alloc(struct svcxprt_rdma *rdma)
 {
@@ -129,7 +122,7 @@ svc_rdma_send_ctxt_alloc(struct svcxprt_rdma *rdma)
 	void *buffer;
 	int i;
 
-	ctxt = kmalloc_node(struct_size(ctxt, sc_sges, rdma->sc_max_send_sges),
+	ctxt = kzalloc_node(struct_size(ctxt, sc_sges, rdma->sc_max_send_sges),
 			    GFP_KERNEL, node);
 	if (!ctxt)
 		goto fail0;
@@ -143,6 +136,7 @@ svc_rdma_send_ctxt_alloc(struct svcxprt_rdma *rdma)
 
 	svc_rdma_send_cid_init(rdma, &ctxt->sc_cid);
 
+	ctxt->sc_rdma = rdma;
 	ctxt->sc_send_wr.next = NULL;
 	ctxt->sc_send_wr.wr_cqe = &ctxt->sc_cqe;
 	ctxt->sc_send_wr.sg_list = ctxt->sc_sges;
@@ -200,10 +194,11 @@ struct svc_rdma_send_ctxt *svc_rdma_send_ctxt_get(struct svcxprt_rdma *rdma)
 
 	spin_lock(&rdma->sc_send_lock);
 	node = llist_del_first(&rdma->sc_send_ctxts);
+	spin_unlock(&rdma->sc_send_lock);
 	if (!node)
 		goto out_empty;
+
 	ctxt = llist_entry(node, struct svc_rdma_send_ctxt, sc_node);
-	spin_unlock(&rdma->sc_send_lock);
 
 out:
 	rpcrdma_set_xdrlen(&ctxt->sc_hdrbuf, 0);
@@ -216,22 +211,14 @@ out:
 	return ctxt;
 
 out_empty:
-	spin_unlock(&rdma->sc_send_lock);
 	ctxt = svc_rdma_send_ctxt_alloc(rdma);
 	if (!ctxt)
 		return NULL;
 	goto out;
 }
 
-/**
- * svc_rdma_send_ctxt_put - Return send_ctxt to free list
- * @rdma: controlling svcxprt_rdma
- * @ctxt: object to return to the free list
- *
- * Pages left in sc_pages are DMA unmapped and released.
- */
-void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma,
-			    struct svc_rdma_send_ctxt *ctxt)
+static void svc_rdma_send_ctxt_release(struct svcxprt_rdma *rdma,
+				       struct svc_rdma_send_ctxt *ctxt)
 {
 	struct ib_device *device = rdma->sc_cm_id->device;
 	unsigned int i;
@@ -243,18 +230,40 @@ void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma,
 	 * remains mapped until @ctxt is destroyed.
 	 */
 	for (i = 1; i < ctxt->sc_send_wr.num_sge; i++) {
+		trace_svcrdma_dma_unmap_page(&ctxt->sc_cid,
+					     ctxt->sc_sges[i].addr,
+					     ctxt->sc_sges[i].length);
 		ib_dma_unmap_page(device,
 				  ctxt->sc_sges[i].addr,
 				  ctxt->sc_sges[i].length,
 				  DMA_TO_DEVICE);
-		trace_svcrdma_dma_unmap_page(rdma,
-					     ctxt->sc_sges[i].addr,
-					     ctxt->sc_sges[i].length);
 	}
 
 	llist_add(&ctxt->sc_node, &rdma->sc_send_ctxts);
 }
 
+static void svc_rdma_send_ctxt_put_async(struct work_struct *work)
+{
+	struct svc_rdma_send_ctxt *ctxt;
+
+	ctxt = container_of(work, struct svc_rdma_send_ctxt, sc_work);
+	svc_rdma_send_ctxt_release(ctxt->sc_rdma, ctxt);
+}
+
+/**
+ * svc_rdma_send_ctxt_put - Return send_ctxt to free list
+ * @rdma: controlling svcxprt_rdma
+ * @ctxt: object to return to the free list
+ *
+ * Pages left in sc_pages are DMA unmapped and released.
+ */
+void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma,
+			    struct svc_rdma_send_ctxt *ctxt)
+{
+	INIT_WORK(&ctxt->sc_work, svc_rdma_send_ctxt_put_async);
+	queue_work(svcrdma_wq, &ctxt->sc_work);
+}
+
 /**
  * svc_rdma_wake_send_waiters - manage Send Queue accounting
  * @rdma: controlling transport
@@ -289,7 +298,7 @@ static void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc)
 	if (unlikely(wc->status != IB_WC_SUCCESS))
 		goto flushed;
 
-	trace_svcrdma_wc_send(wc, &ctxt->sc_cid);
+	trace_svcrdma_wc_send(&ctxt->sc_cid);
 	svc_rdma_send_ctxt_put(rdma, ctxt);
 	return;
 
@@ -327,13 +336,13 @@ int svc_rdma_send(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt)
 	while (1) {
 		if ((atomic_dec_return(&rdma->sc_sq_avail) < 0)) {
 			percpu_counter_inc(&svcrdma_stat_sq_starve);
-			trace_svcrdma_sq_full(rdma);
+			trace_svcrdma_sq_full(rdma, &ctxt->sc_cid);
 			atomic_inc(&rdma->sc_sq_avail);
 			wait_event(rdma->sc_send_wait,
 				   atomic_read(&rdma->sc_sq_avail) > 1);
 			if (test_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags))
 				return -ENOTCONN;
-			trace_svcrdma_sq_retry(rdma);
+			trace_svcrdma_sq_retry(rdma, &ctxt->sc_cid);
 			continue;
 		}
 
@@ -344,7 +353,7 @@ int svc_rdma_send(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt)
 		return 0;
 	}
 
-	trace_svcrdma_sq_post_err(rdma, ret);
+	trace_svcrdma_sq_post_err(rdma, &ctxt->sc_cid, ret);
 	svc_xprt_deferred_close(&rdma->sc_xprt);
 	wake_up(&rdma->sc_send_wait);
 	return ret;
@@ -534,14 +543,14 @@ static int svc_rdma_page_dma_map(void *data, struct page *page,
 	if (ib_dma_mapping_error(dev, dma_addr))
 		goto out_maperr;
 
-	trace_svcrdma_dma_map_page(rdma, dma_addr, len);
+	trace_svcrdma_dma_map_page(&ctxt->sc_cid, dma_addr, len);
 	ctxt->sc_sges[ctxt->sc_cur_sge_no].addr = dma_addr;
 	ctxt->sc_sges[ctxt->sc_cur_sge_no].length = len;
 	ctxt->sc_send_wr.num_sge++;
 	return 0;
 
 out_maperr:
-	trace_svcrdma_dma_map_err(rdma, dma_addr, len);
+	trace_svcrdma_dma_map_err(&ctxt->sc_cid, dma_addr, len);
 	return -EIO;
 }
 
@@ -653,7 +662,7 @@ static int svc_rdma_xb_count_sges(const struct xdr_buf *xdr,
  * svc_rdma_pull_up_needed - Determine whether to use pull-up
  * @rdma: controlling transport
  * @sctxt: send_ctxt for the Send WR
- * @rctxt: Write and Reply chunks provided by client
+ * @write_pcl: Write chunk list provided by client
  * @xdr: xdr_buf containing RPC message to transmit
  *
  * Returns:
@@ -662,7 +671,7 @@ static int svc_rdma_xb_count_sges(const struct xdr_buf *xdr,
  */
 static bool svc_rdma_pull_up_needed(const struct svcxprt_rdma *rdma,
 				    const struct svc_rdma_send_ctxt *sctxt,
-				    const struct svc_rdma_recv_ctxt *rctxt,
+				    const struct svc_rdma_pcl *write_pcl,
 				    const struct xdr_buf *xdr)
 {
 	/* Resources needed for the transport header */
@@ -672,7 +681,7 @@ static bool svc_rdma_pull_up_needed(const struct svcxprt_rdma *rdma,
 	};
 	int ret;
 
-	ret = pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr,
+	ret = pcl_process_nonpayloads(write_pcl, xdr,
 				      svc_rdma_xb_count_sges, &args);
 	if (ret < 0)
 		return false;
@@ -728,7 +737,7 @@ static int svc_rdma_xb_linearize(const struct xdr_buf *xdr,
  * svc_rdma_pull_up_reply_msg - Copy Reply into a single buffer
  * @rdma: controlling transport
  * @sctxt: send_ctxt for the Send WR; xprt hdr is already prepared
- * @rctxt: Write and Reply chunks provided by client
+ * @write_pcl: Write chunk list provided by client
  * @xdr: prepared xdr_buf containing RPC message
  *
  * The device is not capable of sending the reply directly.
@@ -743,7 +752,7 @@ static int svc_rdma_xb_linearize(const struct xdr_buf *xdr,
  */
 static int svc_rdma_pull_up_reply_msg(const struct svcxprt_rdma *rdma,
 				      struct svc_rdma_send_ctxt *sctxt,
-				      const struct svc_rdma_recv_ctxt *rctxt,
+				      const struct svc_rdma_pcl *write_pcl,
 				      const struct xdr_buf *xdr)
 {
 	struct svc_rdma_pullup_data args = {
@@ -751,7 +760,7 @@ static int svc_rdma_pull_up_reply_msg(const struct svcxprt_rdma *rdma,
 	};
 	int ret;
 
-	ret = pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr,
+	ret = pcl_process_nonpayloads(write_pcl, xdr,
 				      svc_rdma_xb_linearize, &args);
 	if (ret < 0)
 		return ret;
@@ -764,7 +773,8 @@ static int svc_rdma_pull_up_reply_msg(const struct svcxprt_rdma *rdma,
 /* svc_rdma_map_reply_msg - DMA map the buffer holding RPC message
  * @rdma: controlling transport
  * @sctxt: send_ctxt for the Send WR
- * @rctxt: Write and Reply chunks provided by client
+ * @write_pcl: Write chunk list provided by client
+ * @reply_pcl: Reply chunk provided by client
  * @xdr: prepared xdr_buf containing RPC message
  *
  * Returns:
@@ -776,7 +786,8 @@ static int svc_rdma_pull_up_reply_msg(const struct svcxprt_rdma *rdma,
  */
 int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 			   struct svc_rdma_send_ctxt *sctxt,
-			   const struct svc_rdma_recv_ctxt *rctxt,
+			   const struct svc_rdma_pcl *write_pcl,
+			   const struct svc_rdma_pcl *reply_pcl,
 			   const struct xdr_buf *xdr)
 {
 	struct svc_rdma_map_data args = {
@@ -789,18 +800,18 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 	sctxt->sc_sges[0].length = sctxt->sc_hdrbuf.len;
 
 	/* If there is a Reply chunk, nothing follows the transport
-	 * header, and we're done here.
+	 * header, so there is nothing to map.
 	 */
-	if (!pcl_is_empty(&rctxt->rc_reply_pcl))
+	if (!pcl_is_empty(reply_pcl))
 		return 0;
 
 	/* For pull-up, svc_rdma_send() will sync the transport header.
 	 * No additional DMA mapping is necessary.
 	 */
-	if (svc_rdma_pull_up_needed(rdma, sctxt, rctxt, xdr))
-		return svc_rdma_pull_up_reply_msg(rdma, sctxt, rctxt, xdr);
+	if (svc_rdma_pull_up_needed(rdma, sctxt, write_pcl, xdr))
+		return svc_rdma_pull_up_reply_msg(rdma, sctxt, write_pcl, xdr);
 
-	return pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr,
+	return pcl_process_nonpayloads(write_pcl, xdr,
 				       svc_rdma_xb_dma_map, &args);
 }
 
@@ -848,7 +859,8 @@ static int svc_rdma_send_reply_msg(struct svcxprt_rdma *rdma,
 {
 	int ret;
 
-	ret = svc_rdma_map_reply_msg(rdma, sctxt, rctxt, &rqstp->rq_res);
+	ret = svc_rdma_map_reply_msg(rdma, sctxt, &rctxt->rc_write_pcl,
+				     &rctxt->rc_reply_pcl, &rqstp->rq_res);
 	if (ret < 0)
 		return ret;
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 2abd895046ee..4f27325ace4a 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -125,6 +125,9 @@ static void qp_event_handler(struct ib_event *event, void *context)
 static struct svcxprt_rdma *svc_rdma_create_xprt(struct svc_serv *serv,
 						 struct net *net, int node)
 {
+	static struct lock_class_key svcrdma_rwctx_lock;
+	static struct lock_class_key svcrdma_sctx_lock;
+	static struct lock_class_key svcrdma_dto_lock;
 	struct svcxprt_rdma *cma_xprt;
 
 	cma_xprt = kzalloc_node(sizeof(*cma_xprt), GFP_KERNEL, node);
@@ -134,6 +137,7 @@ static struct svcxprt_rdma *svc_rdma_create_xprt(struct svc_serv *serv,
 	svc_xprt_init(net, &svc_rdma_class, &cma_xprt->sc_xprt, serv);
 	INIT_LIST_HEAD(&cma_xprt->sc_accept_q);
 	INIT_LIST_HEAD(&cma_xprt->sc_rq_dto_q);
+	INIT_LIST_HEAD(&cma_xprt->sc_read_complete_q);
 	init_llist_head(&cma_xprt->sc_send_ctxts);
 	init_llist_head(&cma_xprt->sc_recv_ctxts);
 	init_llist_head(&cma_xprt->sc_rw_ctxts);
@@ -141,8 +145,11 @@ static struct svcxprt_rdma *svc_rdma_create_xprt(struct svc_serv *serv,
 
 	spin_lock_init(&cma_xprt->sc_lock);
 	spin_lock_init(&cma_xprt->sc_rq_dto_lock);
+	lockdep_set_class(&cma_xprt->sc_rq_dto_lock, &svcrdma_dto_lock);
 	spin_lock_init(&cma_xprt->sc_send_lock);
+	lockdep_set_class(&cma_xprt->sc_send_lock, &svcrdma_sctx_lock);
 	spin_lock_init(&cma_xprt->sc_rw_ctxt_lock);
+	lockdep_set_class(&cma_xprt->sc_rw_ctxt_lock, &svcrdma_rwctx_lock);
 
 	/*
 	 * Note that this implies that the underlying transport support
@@ -391,37 +398,35 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	dev = newxprt->sc_cm_id->device;
 	newxprt->sc_port_num = newxprt->sc_cm_id->port_num;
 
-	/* Qualify the transport resource defaults with the
-	 * capabilities of this particular device */
+	newxprt->sc_max_req_size = svcrdma_max_req_size;
+	newxprt->sc_max_requests = svcrdma_max_requests;
+	newxprt->sc_max_bc_requests = svcrdma_max_bc_requests;
+	newxprt->sc_recv_batch = RPCRDMA_MAX_RECV_BATCH;
+	newxprt->sc_fc_credits = cpu_to_be32(newxprt->sc_max_requests);
+
+	/* Qualify the transport's resource defaults with the
+	 * capabilities of this particular device.
+	 */
+
 	/* Transport header, head iovec, tail iovec */
 	newxprt->sc_max_send_sges = 3;
 	/* Add one SGE per page list entry */
 	newxprt->sc_max_send_sges += (svcrdma_max_req_size / PAGE_SIZE) + 1;
 	if (newxprt->sc_max_send_sges > dev->attrs.max_send_sge)
 		newxprt->sc_max_send_sges = dev->attrs.max_send_sge;
-	newxprt->sc_max_req_size = svcrdma_max_req_size;
-	newxprt->sc_max_requests = svcrdma_max_requests;
-	newxprt->sc_max_bc_requests = svcrdma_max_bc_requests;
-	newxprt->sc_recv_batch = RPCRDMA_MAX_RECV_BATCH;
 	rq_depth = newxprt->sc_max_requests + newxprt->sc_max_bc_requests +
 		   newxprt->sc_recv_batch;
 	if (rq_depth > dev->attrs.max_qp_wr) {
-		pr_warn("svcrdma: reducing receive depth to %d\n",
-			dev->attrs.max_qp_wr);
 		rq_depth = dev->attrs.max_qp_wr;
 		newxprt->sc_recv_batch = 1;
 		newxprt->sc_max_requests = rq_depth - 2;
 		newxprt->sc_max_bc_requests = 2;
 	}
-	newxprt->sc_fc_credits = cpu_to_be32(newxprt->sc_max_requests);
 	ctxts = rdma_rw_mr_factor(dev, newxprt->sc_port_num, RPCSVC_MAXPAGES);
 	ctxts *= newxprt->sc_max_requests;
 	newxprt->sc_sq_depth = rq_depth + ctxts;
-	if (newxprt->sc_sq_depth > dev->attrs.max_qp_wr) {
-		pr_warn("svcrdma: reducing send depth to %d\n",
-			dev->attrs.max_qp_wr);
+	if (newxprt->sc_sq_depth > dev->attrs.max_qp_wr)
 		newxprt->sc_sq_depth = dev->attrs.max_qp_wr;
-	}
 	atomic_set(&newxprt->sc_sq_avail, newxprt->sc_sq_depth);
 
 	newxprt->sc_pd = ib_alloc_pd(dev, 0);
@@ -451,8 +456,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	qp_attr.qp_type = IB_QPT_RC;
 	qp_attr.send_cq = newxprt->sc_sq_cq;
 	qp_attr.recv_cq = newxprt->sc_rq_cq;
-	dprintk("svcrdma: newxprt->sc_cm_id=%p, newxprt->sc_pd=%p\n",
-		newxprt->sc_cm_id, newxprt->sc_pd);
 	dprintk("    cap.max_send_wr = %d, cap.max_recv_wr = %d\n",
 		qp_attr.cap.max_send_wr, qp_attr.cap.max_recv_wr);
 	dprintk("    cap.max_send_sge = %d, cap.max_recv_sge = %d\n",
@@ -506,7 +509,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	}
 
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
-	dprintk("svcrdma: new connection %p accepted:\n", newxprt);
+	dprintk("svcrdma: new connection accepted on device %s:\n", dev->name);
 	sap = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.src_addr;
 	dprintk("    local address   : %pIS:%u\n", sap, rpc_get_port(sap));
 	sap = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.dst_addr;
@@ -547,6 +550,7 @@ static void __svc_rdma_free(struct work_struct *work)
 	/* This blocks until the Completion Queues are empty */
 	if (rdma->sc_qp && !IS_ERR(rdma->sc_qp))
 		ib_drain_qp(rdma->sc_qp);
+	flush_workqueue(svcrdma_wq);
 
 	svc_rdma_flush_recv_queues(rdma);
 
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 28c0771c4e8c..4f8d7efa469f 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -1364,7 +1364,7 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed, bool temp)
 		}
 
 		rep->rr_cid.ci_queue_id = ep->re_attr.recv_cq->res.id;
-		trace_xprtrdma_post_recv(rep);
+		trace_xprtrdma_post_recv(&rep->rr_cid);
 		rep->rr_recv_wr.next = wr;
 		wr = &rep->rr_recv_wr;
 		--needed;
diff --git a/net/tipc/diag.c b/net/tipc/diag.c
index 73137f4aeb68..18733451c9e0 100644
--- a/net/tipc/diag.c
+++ b/net/tipc/diag.c
@@ -113,4 +113,5 @@ module_init(tipc_diag_init);
 module_exit(tipc_diag_exit);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("TIPC socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, AF_TIPC);
diff --git a/net/tipc/link.c b/net/tipc/link.c
index d0143823658d..0716eb5c8a31 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -82,10 +82,7 @@ struct tipc_stats {
  * struct tipc_link - TIPC link data structure
  * @addr: network address of link's peer node
  * @name: link name character string
- * @media_addr: media address to use when sending messages over link
- * @timer: link timer
  * @net: pointer to namespace struct
- * @refcnt: reference counter for permanent references (owner node & timer)
  * @peer_session: link session # being used by peer end of link
  * @peer_bearer_id: bearer id used by link's peer endpoint
  * @bearer_id: local bearer id used by link
@@ -94,31 +91,19 @@ struct tipc_stats {
  * @state: current state of link FSM
  * @peer_caps: bitmap describing capabilities of peer node
  * @silent_intv_cnt: # of timer intervals without any reception from peer
- * @proto_msg: template for control messages generated by link
- * @pmsg: convenience pointer to "proto_msg" field
  * @priority: current link priority
  * @net_plane: current link network plane ('A' through 'H')
  * @mon_state: cookie with information needed by link monitor
- * @backlog_limit: backlog queue congestion thresholds (indexed by importance)
- * @exp_msg_count: # of tunnelled messages expected during link changeover
- * @reset_rcv_checkpt: seq # of last acknowledged message at time of link reset
  * @mtu: current maximum packet size for this link
  * @advertised_mtu: advertised own mtu when link is being established
- * @transmitq: queue for sent, non-acked messages
  * @backlogq: queue for messages waiting to be sent
- * @snt_nxt: next sequence number to use for outbound messages
  * @ackers: # of peers that needs to ack each packet before it can be released
  * @acked: # last packet acked by a certain peer. Used for broadcast.
  * @rcv_nxt: next sequence number to expect for inbound messages
- * @deferred_queue: deferred queue saved OOS b'cast message received from node
- * @unacked_window: # of inbound messages rx'd without ack'ing back to peer
  * @inputq: buffer queue for messages to be delivered upwards
  * @namedq: buffer queue for name table messages to be delivered upwards
- * @next_out: ptr to first unsent outbound message in queue
  * @wakeupq: linked list of wakeup msgs waiting for link congestion to abate
- * @long_msg_seq_no: next identifier to use for outbound fragmented messages
  * @reasm_buf: head of partially reassembled inbound message fragments
- * @bc_rcvr: marks that this is a broadcast receiver link
  * @stats: collects statistics regarding link activity
  * @session: session to be used by link
  * @snd_nxt_state: next send seq number
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 5bc076f2fa74..079aebb16ed8 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -102,6 +102,7 @@ static int tipc_add_tlv(struct sk_buff *skb, u16 type, void *data, u16 len)
 		return -EMSGSIZE;
 
 	skb_put(skb, TLV_SPACE(len));
+	memset(tlv, 0, TLV_SPACE(len));
 	tlv->tlv_type = htons(type);
 	tlv->tlv_len = htons(TLV_LENGTH(len));
 	if (len && data)
@@ -167,7 +168,7 @@ static struct sk_buff *tipc_get_err_tlv(char *str)
 	int str_len = strlen(str) + 1;
 	struct sk_buff *buf;
 
-	buf = tipc_tlv_alloc(TLV_SPACE(str_len));
+	buf = tipc_tlv_alloc(str_len);
 	if (buf)
 		tipc_add_tlv(buf, TIPC_TLV_ERROR_STRING, str, str_len);
 
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index a78e8e722409..e37b4d2e2acd 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -952,6 +952,8 @@ static int tls_sw_sendmsg_splice(struct sock *sk, struct msghdr *msg,
 		}
 
 		sk_msg_page_add(msg_pl, page, part, off);
+		msg_pl->sg.copybreak = 0;
+		msg_pl->sg.curr = msg_pl->sg.end;
 		sk_mem_charge(sk, part);
 		*copied += part;
 		try_to_copy -= part;
@@ -1232,11 +1234,14 @@ void tls_sw_splice_eof(struct socket *sock)
 	lock_sock(sk);
 
 retry:
+	/* same checks as in tls_sw_push_pending_record() */
 	rec = ctx->open_rec;
 	if (!rec)
 		goto unlock;
 
 	msg_pl = &rec->msg_plaintext;
+	if (msg_pl->sg.size == 0)
+		goto unlock;
 
 	/* Check the BPF advisor and perform transmission. */
 	ret = bpf_exec_tx_verdict(msg_pl, sk, false, TLS_RECORD_TYPE_DATA,
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 45506a95b25f..ac1f2bc18fc9 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -213,8 +213,6 @@ static inline bool unix_secdata_eq(struct scm_cookie *scm, struct sk_buff *skb)
 }
 #endif /* CONFIG_SECURITY_NETWORK */
 
-#define unix_peer(sk) (unix_sk(sk)->peer)
-
 static inline int unix_our_peer(struct sock *sk, struct sock *osk)
 {
 	return unix_peer(osk) == sk;
@@ -2581,15 +2579,16 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 
 	if (!(state->flags & MSG_PEEK))
 		WRITE_ONCE(u->oob_skb, NULL);
-
+	else
+		skb_get(oob_skb);
 	unix_state_unlock(sk);
 
 	chunk = state->recv_actor(oob_skb, 0, chunk, state);
 
-	if (!(state->flags & MSG_PEEK)) {
+	if (!(state->flags & MSG_PEEK))
 		UNIXCB(oob_skb).consumed += 1;
-		kfree_skb(oob_skb);
-	}
+
+	consume_skb(oob_skb);
 
 	mutex_unlock(&u->iolock);
 
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 616b55c5b890..bec09a3a1d44 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -339,4 +339,5 @@ static void __exit unix_diag_exit(void)
 module_init(unix_diag_init);
 module_exit(unix_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("UNIX socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 1 /* AF_LOCAL */);
diff --git a/net/unix/scm.c b/net/unix/scm.c
index 6ff628f2349f..822ce0d0d791 100644
--- a/net/unix/scm.c
+++ b/net/unix/scm.c
@@ -35,10 +35,8 @@ struct sock *unix_get_socket(struct file *filp)
 		/* PF_UNIX ? */
 		if (s && ops && ops->family == PF_UNIX)
 			u_sock = s;
-	} else {
-		/* Could be an io_uring instance */
-		u_sock = io_uring_get_socket(filp);
 	}
+
 	return u_sock;
 }
 EXPORT_SYMBOL(unix_get_socket);
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index 2f9d8271c6ec..bd84785bf8d6 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -159,12 +159,32 @@ int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool re
 
 int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
 {
+	struct sock *sk_pair;
+
+	/* Restore does not decrement the sk_pair reference yet because we must
+	 * keep the a reference to the socket until after an RCU grace period
+	 * and any pending sends have completed.
+	 */
 	if (restore) {
 		sk->sk_write_space = psock->saved_write_space;
 		sock_replace_proto(sk, psock->sk_proto);
 		return 0;
 	}
 
+	/* psock_update_sk_prot can be called multiple times if psock is
+	 * added to multiple maps and/or slots in the same map. There is
+	 * also an edge case where replacing a psock with itself can trigger
+	 * an extra psock_update_sk_prot during the insert process. So it
+	 * must be safe to do multiple calls. Here we need to ensure we don't
+	 * increment the refcnt through sock_hold many times. There will only
+	 * be a single matching destroy operation.
+	 */
+	if (!psock->sk_pair) {
+		sk_pair = unix_peer(sk);
+		sock_hold(sk_pair);
+		psock->sk_pair = sk_pair;
+	}
+
 	unix_stream_bpf_check_needs_rebuild(psock->sk_proto);
 	sock_replace_proto(sk, &unix_stream_bpf_prot);
 	return 0;
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 816725af281f..54ba7316f808 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -2264,8 +2264,13 @@ static int vsock_set_rcvlowat(struct sock *sk, int val)
 
 	transport = vsk->transport;
 
-	if (transport && transport->set_rcvlowat)
-		return transport->set_rcvlowat(vsk, val);
+	if (transport && transport->notify_set_rcvlowat) {
+		int err;
+
+		err = transport->notify_set_rcvlowat(vsk, val);
+		if (err)
+			return err;
+	}
 
 	WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
 	return 0;
diff --git a/net/vmw_vsock/diag.c b/net/vmw_vsock/diag.c
index a2823b1c5e28..2e29994f92ff 100644
--- a/net/vmw_vsock/diag.c
+++ b/net/vmw_vsock/diag.c
@@ -174,5 +174,6 @@ static void __exit vsock_diag_exit(void)
 module_init(vsock_diag_init);
 module_exit(vsock_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("VMware Virtual Sockets monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG,
 			       40 /* AF_VSOCK */);
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index 7cb1a9d2cdb4..e2157e387217 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -816,7 +816,7 @@ int hvs_notify_send_post_enqueue(struct vsock_sock *vsk, ssize_t written,
 }
 
 static
-int hvs_set_rcvlowat(struct vsock_sock *vsk, int val)
+int hvs_notify_set_rcvlowat(struct vsock_sock *vsk, int val)
 {
 	return -EOPNOTSUPP;
 }
@@ -856,7 +856,7 @@ static struct vsock_transport hvs_transport = {
 	.notify_send_pre_enqueue  = hvs_notify_send_pre_enqueue,
 	.notify_send_post_enqueue = hvs_notify_send_post_enqueue,
 
-	.set_rcvlowat             = hvs_set_rcvlowat
+	.notify_set_rcvlowat      = hvs_notify_set_rcvlowat
 };
 
 static bool hvs_check_transport(struct vsock_sock *vsk)
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index af5bab1acee1..1748268e0694 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -153,10 +153,10 @@ virtio_transport_send_pkt_work(struct work_struct *work)
 				 * 'virt_to_phys()' later to fill the buffer descriptor.
 				 * We don't touch memory at "virtual" address of this page.
 				 */
-				va = page_to_virt(skb_frag->bv_page);
+				va = page_to_virt(skb_frag_page(skb_frag));
 				sg_init_one(sgs[out_sg],
-					    va + skb_frag->bv_offset,
-					    skb_frag->bv_len);
+					    va + skb_frag_off(skb_frag),
+					    skb_frag_size(skb_frag));
 				out_sg++;
 			}
 		}
@@ -537,6 +537,7 @@ static struct virtio_transport virtio_transport = {
 		.notify_send_pre_enqueue  = virtio_transport_notify_send_pre_enqueue,
 		.notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
 		.notify_buffer_size       = virtio_transport_notify_buffer_size,
+		.notify_set_rcvlowat      = virtio_transport_notify_set_rcvlowat,
 
 		.read_skb = virtio_transport_read_skb,
 	},
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index f6dc896bf44c..16ff976a86e3 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -59,8 +59,7 @@ static bool virtio_transport_can_zcopy(const struct virtio_transport *t_ops,
 	t_ops = virtio_transport_get_ops(info->vsk);
 
 	if (t_ops->can_msgzerocopy) {
-		int pages_in_iov = iov_iter_npages(iov_iter, MAX_SKB_FRAGS);
-		int pages_to_send = min(pages_in_iov, MAX_SKB_FRAGS);
+		int pages_to_send = iov_iter_npages(iov_iter, MAX_SKB_FRAGS);
 
 		/* +1 is for packet header. */
 		return t_ops->can_msgzerocopy(pages_to_send + 1);
@@ -558,6 +557,8 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
 	struct virtio_vsock_sock *vvs = vsk->trans;
 	size_t bytes, total = 0;
 	struct sk_buff *skb;
+	u32 fwd_cnt_delta;
+	bool low_rx_bytes;
 	int err = -EFAULT;
 	u32 free_space;
 
@@ -601,7 +602,10 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
 		}
 	}
 
-	free_space = vvs->buf_alloc - (vvs->fwd_cnt - vvs->last_fwd_cnt);
+	fwd_cnt_delta = vvs->fwd_cnt - vvs->last_fwd_cnt;
+	free_space = vvs->buf_alloc - fwd_cnt_delta;
+	low_rx_bytes = (vvs->rx_bytes <
+			sock_rcvlowat(sk_vsock(vsk), 0, INT_MAX));
 
 	spin_unlock_bh(&vvs->rx_lock);
 
@@ -611,9 +615,11 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
 	 * too high causes extra messages. Too low causes transmitter
 	 * stalls. As stalls are in theory more expensive than extra
 	 * messages, we set the limit to a high value. TODO: experiment
-	 * with different values.
+	 * with different values. Also send credit update message when
+	 * number of bytes in rx queue is not enough to wake up reader.
 	 */
-	if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE)
+	if (fwd_cnt_delta &&
+	    (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE || low_rx_bytes))
 		virtio_transport_send_credit_update(vsk);
 
 	return total;
@@ -844,7 +850,7 @@ static s64 virtio_transport_has_space(struct vsock_sock *vsk)
 	struct virtio_vsock_sock *vvs = vsk->trans;
 	s64 bytes;
 
-	bytes = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt);
+	bytes = (s64)vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt);
 	if (bytes < 0)
 		bytes = 0;
 
@@ -1684,6 +1690,36 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto
 }
 EXPORT_SYMBOL_GPL(virtio_transport_read_skb);
 
+int virtio_transport_notify_set_rcvlowat(struct vsock_sock *vsk, int val)
+{
+	struct virtio_vsock_sock *vvs = vsk->trans;
+	bool send_update;
+
+	spin_lock_bh(&vvs->rx_lock);
+
+	/* If number of available bytes is less than new SO_RCVLOWAT value,
+	 * kick sender to send more data, because sender may sleep in its
+	 * 'send()' syscall waiting for enough space at our side. Also
+	 * don't send credit update when peer already knows actual value -
+	 * such transmission will be useless.
+	 */
+	send_update = (vvs->rx_bytes < val) &&
+		      (vvs->fwd_cnt != vvs->last_fwd_cnt);
+
+	spin_unlock_bh(&vvs->rx_lock);
+
+	if (send_update) {
+		int err;
+
+		err = virtio_transport_send_credit_update(vsk);
+		if (err < 0)
+			return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_notify_set_rcvlowat);
+
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Asias He");
 MODULE_DESCRIPTION("common code for virtio vsock");
diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c
index 048640167411..6dea6119f5b2 100644
--- a/net/vmw_vsock/vsock_loopback.c
+++ b/net/vmw_vsock/vsock_loopback.c
@@ -96,6 +96,7 @@ static struct virtio_transport loopback_transport = {
 		.notify_send_pre_enqueue  = virtio_transport_notify_send_pre_enqueue,
 		.notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
 		.notify_buffer_size       = virtio_transport_notify_buffer_size,
+		.notify_set_rcvlowat      = virtio_transport_notify_set_rcvlowat,
 
 		.read_skb = virtio_transport_read_skb,
 	},
diff --git a/net/wireless/Makefile b/net/wireless/Makefile
index 089c841528c8..72074fd36df4 100644
--- a/net/wireless/Makefile
+++ b/net/wireless/Makefile
@@ -25,7 +25,7 @@ ifneq ($(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR),)
 cfg80211-y += extra-certs.o
 endif
 
-$(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.hex)
+$(obj)/shipped-certs.c: $(sort $(wildcard $(srctree)/$(src)/certs/*.hex))
 	@$(kecho) "  GEN     $@"
 	$(Q)(echo '#include "reg.h"'; \
 	  echo 'const u8 shipped_regdb_certs[] = {'; \
@@ -35,7 +35,7 @@ $(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.hex)
 	 ) > $@
 
 $(obj)/extra-certs.c: $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR) \
-		      $(wildcard $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR)/*.x509)
+		      $(sort $(wildcard $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR)/*.x509))
 	@$(kecho) "  GEN     $@"
 	$(Q)(set -e; \
 	  allf=""; \
diff --git a/net/wireless/certs/wens.hex b/net/wireless/certs/wens.hex
new file mode 100644
index 000000000000..0d50369bede9
--- /dev/null
+++ b/net/wireless/certs/wens.hex
@@ -0,0 +1,87 @@
+/* Chen-Yu Tsai's regdb certificate */
+0x30, 0x82, 0x02, 0xa7, 0x30, 0x82, 0x01, 0x8f,
+0x02, 0x14, 0x61, 0xc0, 0x38, 0x65, 0x1a, 0xab,
+0xdc, 0xf9, 0x4b, 0xd0, 0xac, 0x7f, 0xf0, 0x6c,
+0x72, 0x48, 0xdb, 0x18, 0xc6, 0x00, 0x30, 0x0d,
+0x06, 0x09, 0x2a, 0x86, 0x48, 0x86, 0xf7, 0x0d,
+0x01, 0x01, 0x0b, 0x05, 0x00, 0x30, 0x0f, 0x31,
+0x0d, 0x30, 0x0b, 0x06, 0x03, 0x55, 0x04, 0x03,
+0x0c, 0x04, 0x77, 0x65, 0x6e, 0x73, 0x30, 0x20,
+0x17, 0x0d, 0x32, 0x33, 0x31, 0x32, 0x30, 0x31,
+0x30, 0x37, 0x34, 0x31, 0x31, 0x34, 0x5a, 0x18,
+0x0f, 0x32, 0x31, 0x32, 0x33, 0x31, 0x31, 0x30,
+0x37, 0x30, 0x37, 0x34, 0x31, 0x31, 0x34, 0x5a,
+0x30, 0x0f, 0x31, 0x0d, 0x30, 0x0b, 0x06, 0x03,
+0x55, 0x04, 0x03, 0x0c, 0x04, 0x77, 0x65, 0x6e,
+0x73, 0x30, 0x82, 0x01, 0x22, 0x30, 0x0d, 0x06,
+0x09, 0x2a, 0x86, 0x48, 0x86, 0xf7, 0x0d, 0x01,
+0x01, 0x01, 0x05, 0x00, 0x03, 0x82, 0x01, 0x0f,
+0x00, 0x30, 0x82, 0x01, 0x0a, 0x02, 0x82, 0x01,
+0x01, 0x00, 0xa9, 0x7a, 0x2c, 0x78, 0x4d, 0xa7,
+0x19, 0x2d, 0x32, 0x52, 0xa0, 0x2e, 0x6c, 0xef,
+0x88, 0x7f, 0x15, 0xc5, 0xb6, 0x69, 0x54, 0x16,
+0x43, 0x14, 0x79, 0x53, 0xb7, 0xae, 0x88, 0xfe,
+0xc0, 0xb7, 0x5d, 0x47, 0x8e, 0x1a, 0xe1, 0xef,
+0xb3, 0x90, 0x86, 0xda, 0xd3, 0x64, 0x81, 0x1f,
+0xce, 0x5d, 0x9e, 0x4b, 0x6e, 0x58, 0x02, 0x3e,
+0xb2, 0x6f, 0x5e, 0x42, 0x47, 0x41, 0xf4, 0x2c,
+0xb8, 0xa8, 0xd4, 0xaa, 0xc0, 0x0e, 0xe6, 0x48,
+0xf0, 0xa8, 0xce, 0xcb, 0x08, 0xae, 0x37, 0xaf,
+0xf6, 0x40, 0x39, 0xcb, 0x55, 0x6f, 0x5b, 0x4f,
+0x85, 0x34, 0xe6, 0x69, 0x10, 0x50, 0x72, 0x5e,
+0x4e, 0x9d, 0x4c, 0xba, 0x38, 0x36, 0x0d, 0xce,
+0x73, 0x38, 0xd7, 0x27, 0x02, 0x2a, 0x79, 0x03,
+0xe1, 0xac, 0xcf, 0xb0, 0x27, 0x85, 0x86, 0x93,
+0x17, 0xab, 0xec, 0x42, 0x77, 0x37, 0x65, 0x8a,
+0x44, 0xcb, 0xd6, 0x42, 0x93, 0x92, 0x13, 0xe3,
+0x39, 0x45, 0xc5, 0x6e, 0x00, 0x4a, 0x7f, 0xcb,
+0x42, 0x17, 0x2b, 0x25, 0x8c, 0xb8, 0x17, 0x3b,
+0x15, 0x36, 0x59, 0xde, 0x42, 0xce, 0x21, 0xe6,
+0xb6, 0xc7, 0x6e, 0x5e, 0x26, 0x1f, 0xf7, 0x8a,
+0x57, 0x9e, 0xa5, 0x96, 0x72, 0xb7, 0x02, 0x32,
+0xeb, 0x07, 0x2b, 0x73, 0xe2, 0x4f, 0x66, 0x58,
+0x9a, 0xeb, 0x0f, 0x07, 0xb6, 0xab, 0x50, 0x8b,
+0xc3, 0x8f, 0x17, 0xfa, 0x0a, 0x99, 0xc2, 0x16,
+0x25, 0xbf, 0x2d, 0x6b, 0x1a, 0xaa, 0xe6, 0x3e,
+0x5f, 0xeb, 0x6d, 0x9b, 0x5d, 0x4d, 0x42, 0x83,
+0x2d, 0x39, 0xb8, 0xc9, 0xac, 0xdb, 0x3a, 0x91,
+0x50, 0xdf, 0xbb, 0xb1, 0x76, 0x6d, 0x15, 0x73,
+0xfd, 0xc6, 0xe6, 0x6b, 0x71, 0x9e, 0x67, 0x36,
+0x22, 0x83, 0x79, 0xb1, 0xd6, 0xb8, 0x84, 0x52,
+0xaf, 0x96, 0x5b, 0xc3, 0x63, 0x02, 0x4e, 0x78,
+0x70, 0x57, 0x02, 0x03, 0x01, 0x00, 0x01, 0x30,
+0x0d, 0x06, 0x09, 0x2a, 0x86, 0x48, 0x86, 0xf7,
+0x0d, 0x01, 0x01, 0x0b, 0x05, 0x00, 0x03, 0x82,
+0x01, 0x01, 0x00, 0x24, 0x28, 0xee, 0x22, 0x74,
+0x7f, 0x7c, 0xfa, 0x6c, 0x1f, 0xb3, 0x18, 0xd1,
+0xc2, 0x3d, 0x7d, 0x29, 0x42, 0x88, 0xad, 0x82,
+0xa5, 0xb1, 0x8a, 0x05, 0xd0, 0xec, 0x5c, 0x91,
+0x20, 0xf6, 0x82, 0xfd, 0xd5, 0x67, 0x60, 0x5f,
+0x31, 0xf5, 0xbd, 0x88, 0x91, 0x70, 0xbd, 0xb8,
+0xb9, 0x8c, 0x88, 0xfe, 0x53, 0xc9, 0x54, 0x9b,
+0x43, 0xc4, 0x7a, 0x43, 0x74, 0x6b, 0xdd, 0xb0,
+0xb1, 0x3b, 0x33, 0x45, 0x46, 0x78, 0xa3, 0x1c,
+0xef, 0x54, 0x68, 0xf7, 0x85, 0x9c, 0xe4, 0x51,
+0x6f, 0x06, 0xaf, 0x81, 0xdb, 0x2a, 0x7b, 0x7b,
+0x6f, 0xa8, 0x9c, 0x67, 0xd8, 0xcb, 0xc9, 0x91,
+0x40, 0x00, 0xae, 0xd9, 0xa1, 0x9f, 0xdd, 0xa6,
+0x43, 0x0e, 0x28, 0x7b, 0xaa, 0x1b, 0xe9, 0x84,
+0xdb, 0x76, 0x64, 0x42, 0x70, 0xc9, 0xc0, 0xeb,
+0xae, 0x84, 0x11, 0x16, 0x68, 0x4e, 0x84, 0x9e,
+0x7e, 0x92, 0x36, 0xee, 0x1c, 0x3b, 0x08, 0x63,
+0xeb, 0x79, 0x84, 0x15, 0x08, 0x9d, 0xaf, 0xc8,
+0x9a, 0xc7, 0x34, 0xd3, 0x94, 0x4b, 0xd1, 0x28,
+0x97, 0xbe, 0xd1, 0x45, 0x75, 0xdc, 0x35, 0x62,
+0xac, 0x1d, 0x1f, 0xb7, 0xb7, 0x15, 0x87, 0xc8,
+0x98, 0xc0, 0x24, 0x31, 0x56, 0x8d, 0xed, 0xdb,
+0x06, 0xc6, 0x46, 0xbf, 0x4b, 0x6d, 0xa6, 0xd5,
+0xab, 0xcc, 0x60, 0xfc, 0xe5, 0x37, 0xb6, 0x53,
+0x7d, 0x58, 0x95, 0xa9, 0x56, 0xc7, 0xf7, 0xee,
+0xc3, 0xa0, 0x76, 0xf7, 0x65, 0x4d, 0x53, 0xfa,
+0xff, 0x5f, 0x76, 0x33, 0x5a, 0x08, 0xfa, 0x86,
+0x92, 0x5a, 0x13, 0xfa, 0x1a, 0xfc, 0xf2, 0x1b,
+0x8c, 0x7f, 0x42, 0x6d, 0xb7, 0x7e, 0xb7, 0xb4,
+0xf0, 0xc7, 0x83, 0xbb, 0xa2, 0x81, 0x03, 0x2d,
+0xd4, 0x2a, 0x63, 0x3f, 0xf7, 0x31, 0x2e, 0x40,
+0x33, 0x5c, 0x46, 0xbc, 0x9b, 0xc1, 0x05, 0xa5,
+0x45, 0x4e, 0xc3,
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 2d21e423abdb..ceb9174c5c3d 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -141,7 +141,7 @@ static bool cfg80211_edmg_chandef_valid(const struct cfg80211_chan_def *chandef)
 	return true;
 }
 
-static int nl80211_chan_width_to_mhz(enum nl80211_chan_width chan_width)
+int nl80211_chan_width_to_mhz(enum nl80211_chan_width chan_width)
 {
 	int mhz;
 
@@ -190,6 +190,7 @@ static int nl80211_chan_width_to_mhz(enum nl80211_chan_width chan_width)
 	}
 	return mhz;
 }
+EXPORT_SYMBOL(nl80211_chan_width_to_mhz);
 
 static int cfg80211_chandef_get_width(const struct cfg80211_chan_def *c)
 {
@@ -514,9 +515,83 @@ static u32 cfg80211_get_end_freq(u32 center_freq,
 	return end_freq;
 }
 
+static bool
+cfg80211_dfs_permissive_check_wdev(struct cfg80211_registered_device *rdev,
+				   enum nl80211_iftype iftype,
+				   struct wireless_dev *wdev,
+				   struct ieee80211_channel *chan)
+{
+	unsigned int link_id;
+
+	for_each_valid_link(wdev, link_id) {
+		struct ieee80211_channel *other_chan = NULL;
+		struct cfg80211_chan_def chandef = {};
+		int ret;
+
+		/* In order to avoid daisy chaining only allow BSS STA */
+		if (wdev->iftype != NL80211_IFTYPE_STATION ||
+		    !wdev->links[link_id].client.current_bss)
+			continue;
+
+		other_chan =
+			wdev->links[link_id].client.current_bss->pub.channel;
+
+		if (!other_chan)
+			continue;
+
+		if (chan == other_chan)
+			return true;
+
+		/* continue if we can't get the channel */
+		ret = rdev_get_channel(rdev, wdev, link_id, &chandef);
+		if (ret)
+			continue;
+
+		if (cfg80211_is_sub_chan(&chandef, chan, false))
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * Check if P2P GO is allowed to operate on a DFS channel
+ */
+static bool cfg80211_dfs_permissive_chan(struct wiphy *wiphy,
+					 enum nl80211_iftype iftype,
+					 struct ieee80211_channel *chan)
+{
+	struct wireless_dev *wdev;
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
+
+	lockdep_assert_held(&rdev->wiphy.mtx);
+
+	if (!wiphy_ext_feature_isset(&rdev->wiphy,
+				     NL80211_EXT_FEATURE_DFS_CONCURRENT) ||
+	    !(chan->flags & IEEE80211_CHAN_DFS_CONCURRENT))
+		return false;
+
+	/* only valid for P2P GO */
+	if (iftype != NL80211_IFTYPE_P2P_GO)
+		return false;
+
+	/*
+	 * Allow only if there's a concurrent BSS
+	 */
+	list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) {
+		bool ret = cfg80211_dfs_permissive_check_wdev(rdev, iftype,
+							      wdev, chan);
+		if (ret)
+			return ret;
+	}
+
+	return false;
+}
+
 static int cfg80211_get_chans_dfs_required(struct wiphy *wiphy,
 					    u32 center_freq,
-					    u32 bandwidth)
+					    u32 bandwidth,
+					    enum nl80211_iftype iftype)
 {
 	struct ieee80211_channel *c;
 	u32 freq, start_freq, end_freq;
@@ -529,9 +604,11 @@ static int cfg80211_get_chans_dfs_required(struct wiphy *wiphy,
 		if (!c)
 			return -EINVAL;
 
-		if (c->flags & IEEE80211_CHAN_RADAR)
+		if (c->flags & IEEE80211_CHAN_RADAR &&
+		    !cfg80211_dfs_permissive_chan(wiphy, iftype, c))
 			return 1;
 	}
+
 	return 0;
 }
 
@@ -557,7 +634,7 @@ int cfg80211_chandef_dfs_required(struct wiphy *wiphy,
 
 		ret = cfg80211_get_chans_dfs_required(wiphy,
 					ieee80211_chandef_to_khz(chandef),
-					width);
+					width, iftype);
 		if (ret < 0)
 			return ret;
 		else if (ret > 0)
@@ -568,7 +645,7 @@ int cfg80211_chandef_dfs_required(struct wiphy *wiphy,
 
 		ret = cfg80211_get_chans_dfs_required(wiphy,
 					MHZ_TO_KHZ(chandef->center_freq2),
-					width);
+					width, iftype);
 		if (ret < 0)
 			return ret;
 		else if (ret > 0)
@@ -1336,15 +1413,19 @@ static bool _cfg80211_reg_can_beacon(struct wiphy *wiphy,
 				     bool check_no_ir)
 {
 	bool res;
-	u32 prohibited_flags = IEEE80211_CHAN_DISABLED |
-			       IEEE80211_CHAN_RADAR;
+	u32 prohibited_flags = IEEE80211_CHAN_DISABLED;
+	int dfs_required;
 
 	trace_cfg80211_reg_can_beacon(wiphy, chandef, iftype, check_no_ir);
 
 	if (check_no_ir)
 		prohibited_flags |= IEEE80211_CHAN_NO_IR;
 
-	if (cfg80211_chandef_dfs_required(wiphy, chandef, iftype) > 0 &&
+	dfs_required = cfg80211_chandef_dfs_required(wiphy, chandef, iftype);
+	if (dfs_required != 0)
+		prohibited_flags |= IEEE80211_CHAN_RADAR;
+
+	if (dfs_required > 0 &&
 	    cfg80211_chandef_dfs_available(wiphy, chandef)) {
 		/* We can skip IEEE80211_CHAN_NO_IR if chandef dfs available */
 		prohibited_flags = IEEE80211_CHAN_DISABLED;
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 758c9a2a12c0..409d74c57ca0 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -191,13 +191,13 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev,
 		return err;
 	}
 
+	wiphy_lock(&rdev->wiphy);
 	list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) {
 		if (!wdev->netdev)
 			continue;
 		nl80211_notify_iface(rdev, wdev, NL80211_CMD_DEL_INTERFACE);
 	}
 
-	wiphy_lock(&rdev->wiphy);
 	nl80211_notify_wiphy(rdev, NL80211_CMD_DEL_WIPHY);
 
 	wiphy_net_set(&rdev->wiphy, net);
@@ -206,13 +206,13 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev,
 	WARN_ON(err);
 
 	nl80211_notify_wiphy(rdev, NL80211_CMD_NEW_WIPHY);
-	wiphy_unlock(&rdev->wiphy);
 
 	list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) {
 		if (!wdev->netdev)
 			continue;
 		nl80211_notify_iface(rdev, wdev, NL80211_CMD_NEW_INTERFACE);
 	}
+	wiphy_unlock(&rdev->wiphy);
 
 	return 0;
 }
@@ -221,7 +221,9 @@ static void cfg80211_rfkill_poll(struct rfkill *rfkill, void *data)
 {
 	struct cfg80211_registered_device *rdev = data;
 
+	wiphy_lock(&rdev->wiphy);
 	rdev_rfkill_poll(rdev);
+	wiphy_unlock(&rdev->wiphy);
 }
 
 void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev,
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 4c692c7faf30..13657a85cf61 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -3,7 +3,7 @@
  * Wireless configuration interface internals.
  *
  * Copyright 2006-2010	Johannes Berg <johannes@sipsolutions.net>
- * Copyright (C) 2018-2022 Intel Corporation
+ * Copyright (C) 2018-2023 Intel Corporation
  */
 #ifndef __NET_WIRELESS_CORE_H
 #define __NET_WIRELESS_CORE_H
@@ -293,6 +293,7 @@ struct cfg80211_cqm_config {
 	u32 rssi_hyst;
 	s32 last_rssi_event_value;
 	enum nl80211_cqm_rssi_threshold_event last_rssi_event_type;
+	bool use_range_api;
 	int n_rssi_thresholds;
 	s32 rssi_thresholds[] __counted_by(n_rssi_thresholds);
 };
@@ -457,6 +458,9 @@ int cfg80211_scan(struct cfg80211_registered_device *rdev);
 
 extern struct work_struct cfg80211_disconnect_work;
 
+#define NL80211_BSS_USE_FOR_ALL	(NL80211_BSS_USE_FOR_NORMAL | \
+				 NL80211_BSS_USE_FOR_MLD_LINK)
+
 void cfg80211_set_dfs_state(struct wiphy *wiphy,
 			    const struct cfg80211_chan_def *chandef,
 			    enum nl80211_dfs_state dfs_state);
@@ -545,4 +549,15 @@ int cfg80211_remove_virtual_intf(struct cfg80211_registered_device *rdev,
 				 struct wireless_dev *wdev);
 void cfg80211_wdev_release_link_bsses(struct wireless_dev *wdev, u16 link_mask);
 
+#if IS_ENABLED(CONFIG_CFG80211_KUNIT_TEST)
+#define EXPORT_SYMBOL_IF_CFG80211_KUNIT(sym) EXPORT_SYMBOL_IF_KUNIT(sym)
+#define VISIBLE_IF_CFG80211_KUNIT
+size_t cfg80211_gen_new_ie(const u8 *ie, size_t ielen,
+			   const u8 *subie, size_t subie_len,
+			   u8 *new_ie, size_t new_ie_len);
+#else
+#define EXPORT_SYMBOL_IF_CFG80211_KUNIT(sym)
+#define VISIBLE_IF_CFG80211_KUNIT static
+#endif /* IS_ENABLED(CONFIG_CFG80211_KUNIT_TEST) */
+
 #endif /* __NET_WIRELESS_CORE_H */
diff --git a/net/wireless/debugfs.c b/net/wireless/debugfs.c
index 0878b162890a..40e49074e2ee 100644
--- a/net/wireless/debugfs.c
+++ b/net/wireless/debugfs.c
@@ -4,6 +4,7 @@
  *
  * Copyright 2009	Luis R. Rodriguez <lrodriguez@atheros.com>
  * Copyright 2007	Johannes Berg <johannes@sipsolutions.net>
+ * Copyright (C) 2023 Intel Corporation
  */
 
 #include <linux/slab.h>
@@ -109,3 +110,162 @@ void cfg80211_debugfs_rdev_add(struct cfg80211_registered_device *rdev)
 	DEBUGFS_ADD(long_retry_limit);
 	DEBUGFS_ADD(ht40allow_map);
 }
+
+struct debugfs_read_work {
+	struct wiphy_work work;
+	ssize_t (*handler)(struct wiphy *wiphy,
+			   struct file *file,
+			   char *buf,
+			   size_t count,
+			   void *data);
+	struct wiphy *wiphy;
+	struct file *file;
+	char *buf;
+	size_t bufsize;
+	void *data;
+	ssize_t ret;
+	struct completion completion;
+};
+
+static void wiphy_locked_debugfs_read_work(struct wiphy *wiphy,
+					   struct wiphy_work *work)
+{
+	struct debugfs_read_work *w = container_of(work, typeof(*w), work);
+
+	w->ret = w->handler(w->wiphy, w->file, w->buf, w->bufsize, w->data);
+	complete(&w->completion);
+}
+
+static void wiphy_locked_debugfs_read_cancel(struct dentry *dentry,
+					     void *data)
+{
+	struct debugfs_read_work *w = data;
+
+	wiphy_work_cancel(w->wiphy, &w->work);
+	complete(&w->completion);
+}
+
+ssize_t wiphy_locked_debugfs_read(struct wiphy *wiphy, struct file *file,
+				  char *buf, size_t bufsize,
+				  char __user *userbuf, size_t count,
+				  loff_t *ppos,
+				  ssize_t (*handler)(struct wiphy *wiphy,
+						     struct file *file,
+						     char *buf,
+						     size_t bufsize,
+						     void *data),
+				  void *data)
+{
+	struct debugfs_read_work work = {
+		.handler = handler,
+		.wiphy = wiphy,
+		.file = file,
+		.buf = buf,
+		.bufsize = bufsize,
+		.data = data,
+		.ret = -ENODEV,
+		.completion = COMPLETION_INITIALIZER_ONSTACK(work.completion),
+	};
+	struct debugfs_cancellation cancellation = {
+		.cancel = wiphy_locked_debugfs_read_cancel,
+		.cancel_data = &work,
+	};
+
+	/* don't leak stack data or whatever */
+	memset(buf, 0, bufsize);
+
+	wiphy_work_init(&work.work, wiphy_locked_debugfs_read_work);
+	wiphy_work_queue(wiphy, &work.work);
+
+	debugfs_enter_cancellation(file, &cancellation);
+	wait_for_completion(&work.completion);
+	debugfs_leave_cancellation(file, &cancellation);
+
+	if (work.ret < 0)
+		return work.ret;
+
+	if (WARN_ON(work.ret > bufsize))
+		return -EINVAL;
+
+	return simple_read_from_buffer(userbuf, count, ppos, buf, work.ret);
+}
+EXPORT_SYMBOL_GPL(wiphy_locked_debugfs_read);
+
+struct debugfs_write_work {
+	struct wiphy_work work;
+	ssize_t (*handler)(struct wiphy *wiphy,
+			   struct file *file,
+			   char *buf,
+			   size_t count,
+			   void *data);
+	struct wiphy *wiphy;
+	struct file *file;
+	char *buf;
+	size_t count;
+	void *data;
+	ssize_t ret;
+	struct completion completion;
+};
+
+static void wiphy_locked_debugfs_write_work(struct wiphy *wiphy,
+					    struct wiphy_work *work)
+{
+	struct debugfs_write_work *w = container_of(work, typeof(*w), work);
+
+	w->ret = w->handler(w->wiphy, w->file, w->buf, w->count, w->data);
+	complete(&w->completion);
+}
+
+static void wiphy_locked_debugfs_write_cancel(struct dentry *dentry,
+					      void *data)
+{
+	struct debugfs_write_work *w = data;
+
+	wiphy_work_cancel(w->wiphy, &w->work);
+	complete(&w->completion);
+}
+
+ssize_t wiphy_locked_debugfs_write(struct wiphy *wiphy,
+				   struct file *file, char *buf, size_t bufsize,
+				   const char __user *userbuf, size_t count,
+				   ssize_t (*handler)(struct wiphy *wiphy,
+						      struct file *file,
+						      char *buf,
+						      size_t count,
+						      void *data),
+				   void *data)
+{
+	struct debugfs_write_work work = {
+		.handler = handler,
+		.wiphy = wiphy,
+		.file = file,
+		.buf = buf,
+		.count = count,
+		.data = data,
+		.ret = -ENODEV,
+		.completion = COMPLETION_INITIALIZER_ONSTACK(work.completion),
+	};
+	struct debugfs_cancellation cancellation = {
+		.cancel = wiphy_locked_debugfs_write_cancel,
+		.cancel_data = &work,
+	};
+
+	/* mostly used for strings so enforce NUL-termination for safety */
+	if (count >= bufsize)
+		return -EINVAL;
+
+	memset(buf, 0, bufsize);
+
+	if (copy_from_user(buf, userbuf, count))
+		return -EFAULT;
+
+	wiphy_work_init(&work.work, wiphy_locked_debugfs_write_work);
+	wiphy_work_queue(wiphy, &work.work);
+
+	debugfs_enter_cancellation(file, &cancellation);
+	wait_for_completion(&work.completion);
+	debugfs_leave_cancellation(file, &cancellation);
+
+	return work.ret;
+}
+EXPORT_SYMBOL_GPL(wiphy_locked_debugfs_write);
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index bad9e4fd842f..f635a8b6ca2e 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -22,7 +22,7 @@
 
 
 void cfg80211_rx_assoc_resp(struct net_device *dev,
-			    struct cfg80211_rx_assoc_resp_data *data)
+			    const struct cfg80211_rx_assoc_resp_data *data)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 569234bc2be6..60877b532993 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -818,6 +818,9 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_HW_TIMESTAMP_ENABLED] = { .type = NLA_FLAG },
 	[NL80211_ATTR_EMA_RNR_ELEMS] = { .type = NLA_NESTED },
 	[NL80211_ATTR_MLO_LINK_DISABLED] = { .type = NLA_FLAG },
+	[NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA] = { .type = NLA_FLAG },
+	[NL80211_ATTR_MLO_TTLM_DLINK] = NLA_POLICY_EXACT_LEN(sizeof(u16) * 8),
+	[NL80211_ATTR_MLO_TTLM_ULINK] = NLA_POLICY_EXACT_LEN(sizeof(u16) * 8),
 };
 
 /* policy for the key attributes */
@@ -1198,6 +1201,15 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy,
 		if ((chan->flags & IEEE80211_CHAN_NO_EHT) &&
 		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_EHT))
 			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_DFS_CONCURRENT) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_DFS_CONCURRENT))
+			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_NO_UHB_VLP_CLIENT) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_UHB_VLP_CLIENT))
+			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_NO_UHB_AFC_CLIENT) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_UHB_AFC_CLIENT))
+			goto nla_put_failure;
 	}
 
 	if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER,
@@ -3822,6 +3834,8 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag
 	struct net_device *dev = wdev->netdev;
 	void *hdr;
 
+	lockdep_assert_wiphy(&rdev->wiphy);
+
 	WARN_ON(cmd != NL80211_CMD_NEW_INTERFACE &&
 		cmd != NL80211_CMD_DEL_INTERFACE &&
 		cmd != NL80211_CMD_SET_INTERFACE);
@@ -3989,6 +4003,7 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback *
 
 		if_idx = 0;
 
+		wiphy_lock(&rdev->wiphy);
 		list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) {
 			if (if_idx < if_start) {
 				if_idx++;
@@ -3998,10 +4013,12 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback *
 					       cb->nlh->nlmsg_seq, NLM_F_MULTI,
 					       rdev, wdev,
 					       NL80211_CMD_NEW_INTERFACE) < 0) {
+				wiphy_unlock(&rdev->wiphy);
 				goto out;
 			}
 			if_idx++;
 		}
+		wiphy_unlock(&rdev->wiphy);
 
 		wp_idx++;
 	}
@@ -4850,7 +4867,7 @@ static struct cfg80211_acl_data *parse_acl_data(struct wiphy *wiphy,
 		return ERR_PTR(n_entries);
 
 	if (n_entries > wiphy->max_acl_mac_addrs)
-		return ERR_PTR(-ENOTSUPP);
+		return ERR_PTR(-EOPNOTSUPP);
 
 	acl = kzalloc(struct_size(acl, mac_addrs, n_entries), GFP_KERNEL);
 	if (!acl)
@@ -9337,6 +9354,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 	else
 		eth_broadcast_addr(request->bssid);
 
+	request->tsf_report_link_id = nl80211_link_id_or_invalid(info->attrs);
 	request->wdev = wdev;
 	request->wiphy = &rdev->wiphy;
 	request->scan_start = jiffies;
@@ -10404,6 +10422,15 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb,
 		break;
 	}
 
+	if (nla_put_u32(msg, NL80211_BSS_USE_FOR, res->use_for))
+		goto nla_put_failure;
+
+	if (res->cannot_use_reasons &&
+	    nla_put_u64_64bit(msg, NL80211_BSS_CANNOT_USE_REASONS,
+			      res->cannot_use_reasons,
+			      NL80211_BSS_PAD))
+		goto nla_put_failure;
+
 	nla_nest_end(msg, bss);
 
 	genlmsg_end(msg, hdr);
@@ -10421,15 +10448,27 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb)
 	struct cfg80211_registered_device *rdev;
 	struct cfg80211_internal_bss *scan;
 	struct wireless_dev *wdev;
+	struct nlattr **attrbuf;
 	int start = cb->args[2], idx = 0;
+	bool dump_include_use_data;
 	int err;
 
-	err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, NULL);
-	if (err)
+	attrbuf = kcalloc(NUM_NL80211_ATTR, sizeof(*attrbuf), GFP_KERNEL);
+	if (!attrbuf)
+		return -ENOMEM;
+
+	err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, attrbuf);
+	if (err) {
+		kfree(attrbuf);
 		return err;
+	}
 	/* nl80211_prepare_wdev_dump acquired it in the successful case */
 	__acquire(&rdev->wiphy.mtx);
 
+	dump_include_use_data =
+		attrbuf[NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA];
+	kfree(attrbuf);
+
 	spin_lock_bh(&rdev->bss_lock);
 
 	/*
@@ -10446,6 +10485,9 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb)
 	list_for_each_entry(scan, &rdev->bss_list, list) {
 		if (++idx <= start)
 			continue;
+		if (!dump_include_use_data &&
+		    !(scan->pub.use_for & NL80211_BSS_USE_FOR_NORMAL))
+			continue;
 		if (nl80211_send_bss(skb, cb,
 				cb->nlh->nlmsg_seq, NLM_F_MULTI,
 				rdev, wdev, scan) < 0) {
@@ -10897,12 +10939,13 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev,
 
 static struct cfg80211_bss *nl80211_assoc_bss(struct cfg80211_registered_device *rdev,
 					      const u8 *ssid, int ssid_len,
-					      struct nlattr **attrs)
+					      struct nlattr **attrs,
+					      int assoc_link_id, int link_id)
 {
 	struct ieee80211_channel *chan;
 	struct cfg80211_bss *bss;
 	const u8 *bssid;
-	u32 freq;
+	u32 freq, use_for = 0;
 
 	if (!attrs[NL80211_ATTR_MAC] || !attrs[NL80211_ATTR_WIPHY_FREQ])
 		return ERR_PTR(-EINVAL);
@@ -10917,10 +10960,16 @@ static struct cfg80211_bss *nl80211_assoc_bss(struct cfg80211_registered_device
 	if (!chan)
 		return ERR_PTR(-EINVAL);
 
-	bss = cfg80211_get_bss(&rdev->wiphy, chan, bssid,
-			       ssid, ssid_len,
-			       IEEE80211_BSS_TYPE_ESS,
-			       IEEE80211_PRIVACY_ANY);
+	if (assoc_link_id >= 0)
+		use_for = NL80211_BSS_USE_FOR_MLD_LINK;
+	if (assoc_link_id == link_id)
+		use_for |= NL80211_BSS_USE_FOR_NORMAL;
+
+	bss = __cfg80211_get_bss(&rdev->wiphy, chan, bssid,
+				 ssid, ssid_len,
+				 IEEE80211_BSS_TYPE_ESS,
+				 IEEE80211_PRIVACY_ANY,
+				 use_for);
 	if (!bss)
 		return ERR_PTR(-ENOENT);
 
@@ -11099,7 +11148,8 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info)
 				goto free;
 			}
 			req.links[link_id].bss =
-				nl80211_assoc_bss(rdev, ssid, ssid_len, attrs);
+				nl80211_assoc_bss(rdev, ssid, ssid_len, attrs,
+						  req.link_id, link_id);
 			if (IS_ERR(req.links[link_id].bss)) {
 				err = PTR_ERR(req.links[link_id].bss);
 				req.links[link_id].bss = NULL;
@@ -11164,7 +11214,8 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info)
 		if (req.link_id >= 0)
 			return -EINVAL;
 
-		req.bss = nl80211_assoc_bss(rdev, ssid, ssid_len, info->attrs);
+		req.bss = nl80211_assoc_bss(rdev, ssid, ssid_len, info->attrs,
+					    -1, -1);
 		if (IS_ERR(req.bss))
 			return PTR_ERR(req.bss);
 		ap_addr = req.bss->bssid;
@@ -12173,16 +12224,18 @@ static int nl80211_wiphy_netns(struct sk_buff *skb, struct genl_info *info)
 	return err;
 }
 
-static int nl80211_setdel_pmksa(struct sk_buff *skb, struct genl_info *info)
+static int nl80211_set_pmksa(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
-	int (*rdev_ops)(struct wiphy *wiphy, struct net_device *dev,
-			struct cfg80211_pmksa *pmksa) = NULL;
 	struct net_device *dev = info->user_ptr[1];
 	struct cfg80211_pmksa pmksa;
+	bool ap_pmksa_caching_support = false;
 
 	memset(&pmksa, 0, sizeof(struct cfg80211_pmksa));
 
+	ap_pmksa_caching_support = wiphy_ext_feature_isset(&rdev->wiphy,
+		NL80211_EXT_FEATURE_AP_PMKSA_CACHING);
+
 	if (!info->attrs[NL80211_ATTR_PMKID])
 		return -EINVAL;
 
@@ -12191,16 +12244,15 @@ static int nl80211_setdel_pmksa(struct sk_buff *skb, struct genl_info *info)
 	if (info->attrs[NL80211_ATTR_MAC]) {
 		pmksa.bssid = nla_data(info->attrs[NL80211_ATTR_MAC]);
 	} else if (info->attrs[NL80211_ATTR_SSID] &&
-		   info->attrs[NL80211_ATTR_FILS_CACHE_ID] &&
-		   (info->genlhdr->cmd == NL80211_CMD_DEL_PMKSA ||
-		    info->attrs[NL80211_ATTR_PMK])) {
+	           info->attrs[NL80211_ATTR_FILS_CACHE_ID] &&
+	           info->attrs[NL80211_ATTR_PMK]) {
 		pmksa.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]);
 		pmksa.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]);
-		pmksa.cache_id =
-			nla_data(info->attrs[NL80211_ATTR_FILS_CACHE_ID]);
+		pmksa.cache_id = nla_data(info->attrs[NL80211_ATTR_FILS_CACHE_ID]);
 	} else {
 		return -EINVAL;
 	}
+
 	if (info->attrs[NL80211_ATTR_PMK]) {
 		pmksa.pmk = nla_data(info->attrs[NL80211_ATTR_PMK]);
 		pmksa.pmk_len = nla_len(info->attrs[NL80211_ATTR_PMK]);
@@ -12212,32 +12264,71 @@ static int nl80211_setdel_pmksa(struct sk_buff *skb, struct genl_info *info)
 
 	if (info->attrs[NL80211_ATTR_PMK_REAUTH_THRESHOLD])
 		pmksa.pmk_reauth_threshold =
-			nla_get_u8(
-				info->attrs[NL80211_ATTR_PMK_REAUTH_THRESHOLD]);
+			nla_get_u8(info->attrs[NL80211_ATTR_PMK_REAUTH_THRESHOLD]);
 
 	if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION &&
 	    dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT &&
-	    !(dev->ieee80211_ptr->iftype == NL80211_IFTYPE_AP &&
-	      wiphy_ext_feature_isset(&rdev->wiphy,
-				      NL80211_EXT_FEATURE_AP_PMKSA_CACHING)))
+	    !((dev->ieee80211_ptr->iftype == NL80211_IFTYPE_AP ||
+	       dev->ieee80211_ptr->iftype == NL80211_IFTYPE_P2P_GO) &&
+	       ap_pmksa_caching_support))
 		return -EOPNOTSUPP;
 
-	switch (info->genlhdr->cmd) {
-	case NL80211_CMD_SET_PMKSA:
-		rdev_ops = rdev->ops->set_pmksa;
-		break;
-	case NL80211_CMD_DEL_PMKSA:
-		rdev_ops = rdev->ops->del_pmksa;
-		break;
-	default:
-		WARN_ON(1);
-		break;
+	if (!rdev->ops->set_pmksa)
+		return -EOPNOTSUPP;
+
+	return rdev_set_pmksa(rdev, dev, &pmksa);
+}
+
+static int nl80211_del_pmksa(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct cfg80211_pmksa pmksa;
+	bool sae_offload_support = false;
+	bool owe_offload_support = false;
+	bool ap_pmksa_caching_support = false;
+
+	memset(&pmksa, 0, sizeof(struct cfg80211_pmksa));
+
+	sae_offload_support = wiphy_ext_feature_isset(&rdev->wiphy,
+		NL80211_EXT_FEATURE_SAE_OFFLOAD);
+	owe_offload_support = wiphy_ext_feature_isset(&rdev->wiphy,
+		NL80211_EXT_FEATURE_OWE_OFFLOAD);
+	ap_pmksa_caching_support = wiphy_ext_feature_isset(&rdev->wiphy,
+		NL80211_EXT_FEATURE_AP_PMKSA_CACHING);
+
+	if (info->attrs[NL80211_ATTR_PMKID])
+		pmksa.pmkid = nla_data(info->attrs[NL80211_ATTR_PMKID]);
+
+	if (info->attrs[NL80211_ATTR_MAC]) {
+		pmksa.bssid = nla_data(info->attrs[NL80211_ATTR_MAC]);
+	} else if (info->attrs[NL80211_ATTR_SSID]) {
+		/* SSID based pmksa flush suppported only for FILS,
+		 * OWE/SAE OFFLOAD cases
+		 */
+		if (info->attrs[NL80211_ATTR_FILS_CACHE_ID] &&
+		    info->attrs[NL80211_ATTR_PMK]) {
+			pmksa.cache_id = nla_data(info->attrs[NL80211_ATTR_FILS_CACHE_ID]);
+		} else if (!sae_offload_support && !owe_offload_support) {
+			return -EINVAL;
+		}
+		pmksa.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]);
+		pmksa.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]);
+	} else {
+		return -EINVAL;
 	}
 
-	if (!rdev_ops)
+	if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION &&
+	    dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT &&
+	    !((dev->ieee80211_ptr->iftype == NL80211_IFTYPE_AP ||
+	       dev->ieee80211_ptr->iftype == NL80211_IFTYPE_P2P_GO) &&
+	       ap_pmksa_caching_support))
+		return -EOPNOTSUPP;
+
+	if (!rdev->ops->del_pmksa)
 		return -EOPNOTSUPP;
 
-	return rdev_ops(&rdev->wiphy, dev, &pmksa);
+	return rdev_del_pmksa(rdev, dev, &pmksa);
 }
 
 static int nl80211_flush_pmksa(struct sk_buff *skb, struct genl_info *info)
@@ -12787,10 +12878,6 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev,
 	int i, n, low_index;
 	int err;
 
-	/* RSSI reporting disabled? */
-	if (!cqm_config)
-		return rdev_set_cqm_rssi_range_config(rdev, dev, 0, 0);
-
 	/*
 	 * Obtain current RSSI value if possible, if not and no RSSI threshold
 	 * event has been received yet, we should receive an event after a
@@ -12865,23 +12952,25 @@ static int nl80211_set_cqm_rssi(struct genl_info *info,
 	    wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)
 		return -EOPNOTSUPP;
 
-	if (n_thresholds <= 1 && rdev->ops->set_cqm_rssi_config) {
-		if (n_thresholds == 0 || thresholds[0] == 0) /* Disabling */
-			return rdev_set_cqm_rssi_config(rdev, dev, 0, 0);
-
-		return rdev_set_cqm_rssi_config(rdev, dev,
-						thresholds[0], hysteresis);
-	}
-
-	if (!wiphy_ext_feature_isset(&rdev->wiphy,
-				     NL80211_EXT_FEATURE_CQM_RSSI_LIST))
-		return -EOPNOTSUPP;
-
 	if (n_thresholds == 1 && thresholds[0] == 0) /* Disabling */
 		n_thresholds = 0;
 
 	old = wiphy_dereference(wdev->wiphy, wdev->cqm_config);
 
+	/* if already disabled just succeed */
+	if (!n_thresholds && !old)
+		return 0;
+
+	if (n_thresholds > 1) {
+		if (!wiphy_ext_feature_isset(&rdev->wiphy,
+					     NL80211_EXT_FEATURE_CQM_RSSI_LIST) ||
+		    !rdev->ops->set_cqm_rssi_range_config)
+			return -EOPNOTSUPP;
+	} else {
+		if (!rdev->ops->set_cqm_rssi_config)
+			return -EOPNOTSUPP;
+	}
+
 	if (n_thresholds) {
 		cqm_config = kzalloc(struct_size(cqm_config, rssi_thresholds,
 						 n_thresholds),
@@ -12894,13 +12983,26 @@ static int nl80211_set_cqm_rssi(struct genl_info *info,
 		memcpy(cqm_config->rssi_thresholds, thresholds,
 		       flex_array_size(cqm_config, rssi_thresholds,
 				       n_thresholds));
+		cqm_config->use_range_api = n_thresholds > 1 ||
+					    !rdev->ops->set_cqm_rssi_config;
 
 		rcu_assign_pointer(wdev->cqm_config, cqm_config);
+
+		if (cqm_config->use_range_api)
+			err = cfg80211_cqm_rssi_update(rdev, dev, cqm_config);
+		else
+			err = rdev_set_cqm_rssi_config(rdev, dev,
+						       thresholds[0],
+						       hysteresis);
 	} else {
 		RCU_INIT_POINTER(wdev->cqm_config, NULL);
+		/* if enabled as range also disable via range */
+		if (old->use_range_api)
+			err = rdev_set_cqm_rssi_range_config(rdev, dev, 0, 0);
+		else
+			err = rdev_set_cqm_rssi_config(rdev, dev, 0, 0);
 	}
 
-	err = cfg80211_cqm_rssi_update(rdev, dev, cqm_config);
 	if (err) {
 		rcu_assign_pointer(wdev->cqm_config, old);
 		kfree_rcu(cqm_config, rcu_head);
@@ -15830,7 +15932,7 @@ static int parse_tid_conf(struct cfg80211_registered_device *rdev,
 
 	if (tid_conf->mask & ~mask) {
 		NL_SET_ERR_MSG(extack, "unsupported TID configuration");
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 
 	return 0;
@@ -16223,6 +16325,35 @@ static int nl80211_set_hw_timestamp(struct sk_buff *skb,
 	return rdev_set_hw_timestamp(rdev, dev, &hwts);
 }
 
+static int
+nl80211_set_ttlm(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg80211_ttlm_params params = {};
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+
+	if (wdev->iftype != NL80211_IFTYPE_STATION &&
+	    wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)
+		return -EOPNOTSUPP;
+
+	if (!wdev->connected)
+		return -ENOLINK;
+
+	if (!info->attrs[NL80211_ATTR_MLO_TTLM_DLINK] ||
+	    !info->attrs[NL80211_ATTR_MLO_TTLM_ULINK])
+		return -EINVAL;
+
+	nla_memcpy(params.dlink,
+		   info->attrs[NL80211_ATTR_MLO_TTLM_DLINK],
+		   sizeof(params.dlink));
+	nla_memcpy(params.ulink,
+		   info->attrs[NL80211_ATTR_MLO_TTLM_ULINK],
+		   sizeof(params.ulink));
+
+	return rdev_set_ttlm(rdev, dev, &params);
+}
+
 #define NL80211_FLAG_NEED_WIPHY		0x01
 #define NL80211_FLAG_NEED_NETDEV	0x02
 #define NL80211_FLAG_NEED_RTNL		0x04
@@ -16911,7 +17042,7 @@ static const struct genl_small_ops nl80211_small_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_PMKSA,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = nl80211_setdel_pmksa,
+		.doit = nl80211_set_pmksa,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP |
 					 NL80211_FLAG_CLEAR_SKB),
@@ -16919,7 +17050,7 @@ static const struct genl_small_ops nl80211_small_ops[] = {
 	{
 		.cmd = NL80211_CMD_DEL_PMKSA,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = nl80211_setdel_pmksa,
+		.doit = nl80211_del_pmksa,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP),
 	},
@@ -17404,6 +17535,12 @@ static const struct genl_small_ops nl80211_small_ops[] = {
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP),
 	},
+	{
+		.cmd = NL80211_CMD_SET_TID_TO_LINK_MAPPING,
+		.doit = nl80211_set_ttlm,
+		.flags = GENL_UNS_ADMIN_PERM,
+		.internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP),
+	},
 };
 
 static struct genl_family nl80211_fam __ro_after_init = {
@@ -17735,21 +17872,29 @@ nla_put_failure:
 	nlmsg_free(msg);
 }
 
+struct nl80211_mlme_event {
+	enum nl80211_commands cmd;
+	const u8 *buf;
+	size_t buf_len;
+	int uapsd_queues;
+	const u8 *req_ies;
+	size_t req_ies_len;
+	bool reconnect;
+};
+
 static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev,
 				    struct net_device *netdev,
-				    const u8 *buf, size_t len,
-				    enum nl80211_commands cmd, gfp_t gfp,
-				    int uapsd_queues, const u8 *req_ies,
-				    size_t req_ies_len, bool reconnect)
+				    const struct nl80211_mlme_event *event,
+				    gfp_t gfp)
 {
 	struct sk_buff *msg;
 	void *hdr;
 
-	msg = nlmsg_new(100 + len + req_ies_len, gfp);
+	msg = nlmsg_new(100 + event->buf_len + event->req_ies_len, gfp);
 	if (!msg)
 		return;
 
-	hdr = nl80211hdr_put(msg, 0, 0, 0, cmd);
+	hdr = nl80211hdr_put(msg, 0, 0, 0, event->cmd);
 	if (!hdr) {
 		nlmsg_free(msg);
 		return;
@@ -17757,22 +17902,24 @@ static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev,
 
 	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
 	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) ||
-	    nla_put(msg, NL80211_ATTR_FRAME, len, buf) ||
-	    (req_ies &&
-	     nla_put(msg, NL80211_ATTR_REQ_IE, req_ies_len, req_ies)))
+	    nla_put(msg, NL80211_ATTR_FRAME, event->buf_len, event->buf) ||
+	    (event->req_ies &&
+	     nla_put(msg, NL80211_ATTR_REQ_IE, event->req_ies_len,
+		     event->req_ies)))
 		goto nla_put_failure;
 
-	if (reconnect && nla_put_flag(msg, NL80211_ATTR_RECONNECT_REQUESTED))
+	if (event->reconnect &&
+	    nla_put_flag(msg, NL80211_ATTR_RECONNECT_REQUESTED))
 		goto nla_put_failure;
 
-	if (uapsd_queues >= 0) {
+	if (event->uapsd_queues >= 0) {
 		struct nlattr *nla_wmm =
 			nla_nest_start_noflag(msg, NL80211_ATTR_STA_WME);
 		if (!nla_wmm)
 			goto nla_put_failure;
 
 		if (nla_put_u8(msg, NL80211_STA_WME_UAPSD_QUEUES,
-			       uapsd_queues))
+			       event->uapsd_queues))
 			goto nla_put_failure;
 
 		nla_nest_end(msg, nla_wmm);
@@ -17792,37 +17939,60 @@ void nl80211_send_rx_auth(struct cfg80211_registered_device *rdev,
 			  struct net_device *netdev, const u8 *buf,
 			  size_t len, gfp_t gfp)
 {
-	nl80211_send_mlme_event(rdev, netdev, buf, len,
-				NL80211_CMD_AUTHENTICATE, gfp, -1, NULL, 0,
-				false);
+	struct nl80211_mlme_event event = {
+		.cmd = NL80211_CMD_AUTHENTICATE,
+		.buf = buf,
+		.buf_len = len,
+		.uapsd_queues = -1,
+	};
+
+	nl80211_send_mlme_event(rdev, netdev, &event, gfp);
 }
 
 void nl80211_send_rx_assoc(struct cfg80211_registered_device *rdev,
 			   struct net_device *netdev,
-			   struct cfg80211_rx_assoc_resp_data *data)
+			   const struct cfg80211_rx_assoc_resp_data *data)
 {
-	nl80211_send_mlme_event(rdev, netdev, data->buf, data->len,
-				NL80211_CMD_ASSOCIATE, GFP_KERNEL,
-				data->uapsd_queues,
-				data->req_ies, data->req_ies_len, false);
+	struct nl80211_mlme_event event = {
+		.cmd = NL80211_CMD_ASSOCIATE,
+		.buf = data->buf,
+		.buf_len = data->len,
+		.uapsd_queues = data->uapsd_queues,
+		.req_ies = data->req_ies,
+		.req_ies_len = data->req_ies_len,
+	};
+
+	nl80211_send_mlme_event(rdev, netdev, &event, GFP_KERNEL);
 }
 
 void nl80211_send_deauth(struct cfg80211_registered_device *rdev,
 			 struct net_device *netdev, const u8 *buf,
 			 size_t len, bool reconnect, gfp_t gfp)
 {
-	nl80211_send_mlme_event(rdev, netdev, buf, len,
-				NL80211_CMD_DEAUTHENTICATE, gfp, -1, NULL, 0,
-				reconnect);
+	struct nl80211_mlme_event event = {
+		.cmd = NL80211_CMD_DEAUTHENTICATE,
+		.buf = buf,
+		.buf_len = len,
+		.reconnect = reconnect,
+		.uapsd_queues = -1,
+	};
+
+	nl80211_send_mlme_event(rdev, netdev, &event, gfp);
 }
 
 void nl80211_send_disassoc(struct cfg80211_registered_device *rdev,
 			   struct net_device *netdev, const u8 *buf,
 			   size_t len, bool reconnect, gfp_t gfp)
 {
-	nl80211_send_mlme_event(rdev, netdev, buf, len,
-				NL80211_CMD_DISASSOCIATE, gfp, -1, NULL, 0,
-				reconnect);
+	struct nl80211_mlme_event event = {
+		.cmd = NL80211_CMD_DISASSOCIATE,
+		.buf = buf,
+		.buf_len = len,
+		.reconnect = reconnect,
+		.uapsd_queues = -1,
+	};
+
+	nl80211_send_mlme_event(rdev, netdev, &event, gfp);
 }
 
 void cfg80211_rx_unprot_mlme_mgmt(struct net_device *dev, const u8 *buf,
@@ -17832,28 +18002,31 @@ void cfg80211_rx_unprot_mlme_mgmt(struct net_device *dev, const u8 *buf,
 	struct wiphy *wiphy = wdev->wiphy;
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	const struct ieee80211_mgmt *mgmt = (void *)buf;
-	u32 cmd;
+	struct nl80211_mlme_event event = {
+		.buf = buf,
+		.buf_len = len,
+		.uapsd_queues = -1,
+	};
 
 	if (WARN_ON(len < 2))
 		return;
 
 	if (ieee80211_is_deauth(mgmt->frame_control)) {
-		cmd = NL80211_CMD_UNPROT_DEAUTHENTICATE;
+		event.cmd = NL80211_CMD_UNPROT_DEAUTHENTICATE;
 	} else if (ieee80211_is_disassoc(mgmt->frame_control)) {
-		cmd = NL80211_CMD_UNPROT_DISASSOCIATE;
+		event.cmd = NL80211_CMD_UNPROT_DISASSOCIATE;
 	} else if (ieee80211_is_beacon(mgmt->frame_control)) {
 		if (wdev->unprot_beacon_reported &&
 		    elapsed_jiffies_msecs(wdev->unprot_beacon_reported) < 10000)
 			return;
-		cmd = NL80211_CMD_UNPROT_BEACON;
+		event.cmd = NL80211_CMD_UNPROT_BEACON;
 		wdev->unprot_beacon_reported = jiffies;
 	} else {
 		return;
 	}
 
 	trace_cfg80211_rx_unprot_mlme_mgmt(dev, buf, len);
-	nl80211_send_mlme_event(rdev, dev, buf, len, cmd, GFP_ATOMIC, -1,
-				NULL, 0, false);
+	nl80211_send_mlme_event(rdev, dev, &event, GFP_ATOMIC);
 }
 EXPORT_SYMBOL(cfg80211_rx_unprot_mlme_mgmt);
 
@@ -19009,10 +19182,11 @@ void cfg80211_cqm_rssi_notify_work(struct wiphy *wiphy, struct wiphy_work *work)
 	s32 rssi_level;
 
 	cqm_config = wiphy_dereference(wdev->wiphy, wdev->cqm_config);
-	if (!wdev->cqm_config)
+	if (!cqm_config)
 		return;
 
-	cfg80211_cqm_rssi_update(rdev, wdev->netdev, cqm_config);
+	if (cqm_config->use_range_api)
+		cfg80211_cqm_rssi_update(rdev, wdev->netdev, cqm_config);
 
 	rssi_level = cqm_config->last_rssi_event_value;
 	rssi_event = cqm_config->last_rssi_event_type;
@@ -19306,6 +19480,7 @@ void cfg80211_ch_switch_notify(struct net_device *dev,
 		break;
 	}
 
+	cfg80211_schedule_channels_check(wdev);
 	cfg80211_sched_dfs_chan_update(rdev);
 
 	nl80211_ch_switch_notify(rdev, dev, link_id, chandef, GFP_KERNEL,
@@ -20063,6 +20238,20 @@ nla_put_failure:
 }
 EXPORT_SYMBOL(cfg80211_update_owe_info_event);
 
+void cfg80211_schedule_channels_check(struct wireless_dev *wdev)
+{
+	struct wiphy *wiphy = wdev->wiphy;
+
+	/* Schedule channels check if NO_IR or DFS relaxations are supported */
+	if (wdev->iftype == NL80211_IFTYPE_STATION &&
+	    (wiphy_ext_feature_isset(wiphy,
+				     NL80211_EXT_FEATURE_DFS_CONCURRENT) ||
+	    (IS_ENABLED(CONFIG_CFG80211_REG_RELAX_NO_IR) &&
+	     wiphy->regulatory_flags & REGULATORY_ENABLE_RELAX_NO_IR)))
+		reg_check_channels();
+}
+EXPORT_SYMBOL(cfg80211_schedule_channels_check);
+
 /* initialisation/exit functions */
 
 int __init nl80211_init(void)
diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h
index aad40240d9cb..6376f3a87f8a 100644
--- a/net/wireless/nl80211.h
+++ b/net/wireless/nl80211.h
@@ -60,7 +60,7 @@ void nl80211_send_rx_auth(struct cfg80211_registered_device *rdev,
 			  const u8 *buf, size_t len, gfp_t gfp);
 void nl80211_send_rx_assoc(struct cfg80211_registered_device *rdev,
 			   struct net_device *netdev,
-			   struct cfg80211_rx_assoc_resp_data *data);
+			   const struct cfg80211_rx_assoc_resp_data *data);
 void nl80211_send_deauth(struct cfg80211_registered_device *rdev,
 			 struct net_device *netdev,
 			 const u8 *buf, size_t len,
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index 2214a90cf101..43897a5269b6 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -1046,7 +1046,7 @@ rdev_nan_change_conf(struct cfg80211_registered_device *rdev,
 		ret = rdev->ops->nan_change_conf(&rdev->wiphy, wdev, conf,
 						 changes);
 	else
-		ret = -ENOTSUPP;
+		ret = -EOPNOTSUPP;
 	trace_rdev_return_int(&rdev->wiphy, ret);
 	return ret;
 }
@@ -1200,7 +1200,7 @@ rdev_start_radar_detection(struct cfg80211_registered_device *rdev,
 			   struct cfg80211_chan_def *chandef,
 			   u32 cac_time_ms)
 {
-	int ret = -ENOTSUPP;
+	int ret = -EOPNOTSUPP;
 
 	trace_rdev_start_radar_detection(&rdev->wiphy, dev, chandef,
 					 cac_time_ms);
@@ -1226,7 +1226,7 @@ rdev_set_mcast_rate(struct cfg80211_registered_device *rdev,
 		    struct net_device *dev,
 		    int mcast_rate[NUM_NL80211_BANDS])
 {
-	int ret = -ENOTSUPP;
+	int ret = -EOPNOTSUPP;
 
 	trace_rdev_set_mcast_rate(&rdev->wiphy, dev, mcast_rate);
 	if (rdev->ops->set_mcast_rate)
@@ -1239,7 +1239,7 @@ static inline int
 rdev_set_coalesce(struct cfg80211_registered_device *rdev,
 		  struct cfg80211_coalesce *coalesce)
 {
-	int ret = -ENOTSUPP;
+	int ret = -EOPNOTSUPP;
 
 	trace_rdev_set_coalesce(&rdev->wiphy, coalesce);
 	if (rdev->ops->set_coalesce)
@@ -1524,4 +1524,22 @@ rdev_set_hw_timestamp(struct cfg80211_registered_device *rdev,
 
 	return ret;
 }
+
+static inline int
+rdev_set_ttlm(struct cfg80211_registered_device *rdev,
+	      struct net_device *dev,
+	      struct cfg80211_ttlm_params *params)
+{
+	struct wiphy *wiphy = &rdev->wiphy;
+	int ret;
+
+	if (!rdev->ops->set_ttlm)
+		return -EOPNOTSUPP;
+
+	trace_rdev_set_ttlm(wiphy, dev, params);
+	ret = rdev->ops->set_ttlm(wiphy, dev, params);
+	trace_rdev_return_int(wiphy, ret);
+
+	return ret;
+}
 #endif /* __CFG80211_RDEV_OPS */
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 2ef4f6cc7a32..2741b626919a 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -1593,6 +1593,12 @@ static u32 map_regdom_flags(u32 rd_flags)
 		channel_flags |= IEEE80211_CHAN_NO_320MHZ;
 	if (rd_flags & NL80211_RRF_NO_EHT)
 		channel_flags |= IEEE80211_CHAN_NO_EHT;
+	if (rd_flags & NL80211_RRF_DFS_CONCURRENT)
+		channel_flags |= IEEE80211_CHAN_DFS_CONCURRENT;
+	if (rd_flags & NL80211_RRF_NO_UHB_VLP_CLIENT)
+		channel_flags |= IEEE80211_CHAN_NO_UHB_VLP_CLIENT;
+	if (rd_flags & NL80211_RRF_NO_UHB_AFC_CLIENT)
+		channel_flags |= IEEE80211_CHAN_NO_UHB_AFC_CLIENT;
 	if (rd_flags & NL80211_RRF_PSD)
 		channel_flags |= IEEE80211_CHAN_PSD;
 	return channel_flags;
@@ -2478,7 +2484,7 @@ static void reg_check_chans_work(struct work_struct *work)
 	rtnl_unlock();
 }
 
-static void reg_check_channels(void)
+void reg_check_channels(void)
 {
 	/*
 	 * Give usermode a chance to do something nicer (move to another
diff --git a/net/wireless/reg.h b/net/wireless/reg.h
index a703e53c23ee..a02ef5609f52 100644
--- a/net/wireless/reg.h
+++ b/net/wireless/reg.h
@@ -181,6 +181,11 @@ bool reg_dfs_domain_same(struct wiphy *wiphy1, struct wiphy *wiphy2);
  */
 int reg_reload_regdb(void);
 
+/**
+ * reg_check_channels - schedule regulatory enforcement
+ */
+void reg_check_channels(void);
+
 extern const u8 shipped_regdb_certs[];
 extern unsigned int shipped_regdb_certs_len;
 extern const u8 extra_regdb_certs[];
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 9e5ccffd6868..2249b1a89d1c 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -20,6 +20,7 @@
 #include <net/cfg80211.h>
 #include <net/cfg80211-wext.h>
 #include <net/iw_handler.h>
+#include <kunit/visibility.h>
 #include "core.h"
 #include "nl80211.h"
 #include "wext-compat.h"
@@ -303,9 +304,10 @@ static size_t cfg80211_copy_elem_with_frags(const struct element *elem,
 	return *pos - buf;
 }
 
-static size_t cfg80211_gen_new_ie(const u8 *ie, size_t ielen,
-				  const u8 *subie, size_t subie_len,
-				  u8 *new_ie, size_t new_ie_len)
+VISIBLE_IF_CFG80211_KUNIT size_t
+cfg80211_gen_new_ie(const u8 *ie, size_t ielen,
+		    const u8 *subie, size_t subie_len,
+		    u8 *new_ie, size_t new_ie_len)
 {
 	const struct element *non_inherit_elem, *parent, *sub;
 	u8 *pos = new_ie;
@@ -413,6 +415,7 @@ static size_t cfg80211_gen_new_ie(const u8 *ie, size_t ielen,
 
 	return pos - new_ie;
 }
+EXPORT_SYMBOL_IF_CFG80211_KUNIT(cfg80211_gen_new_ie);
 
 static bool is_bss(struct cfg80211_bss *a, const u8 *bssid,
 		   const u8 *ssid, size_t ssid_len)
@@ -1535,12 +1538,13 @@ static bool cfg80211_bss_type_match(u16 capability,
 }
 
 /* Returned bss is reference counted and must be cleaned up appropriately. */
-struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy,
-				      struct ieee80211_channel *channel,
-				      const u8 *bssid,
-				      const u8 *ssid, size_t ssid_len,
-				      enum ieee80211_bss_type bss_type,
-				      enum ieee80211_privacy privacy)
+struct cfg80211_bss *__cfg80211_get_bss(struct wiphy *wiphy,
+					struct ieee80211_channel *channel,
+					const u8 *bssid,
+					const u8 *ssid, size_t ssid_len,
+					enum ieee80211_bss_type bss_type,
+					enum ieee80211_privacy privacy,
+					u32 use_for)
 {
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct cfg80211_internal_bss *bss, *res = NULL;
@@ -1565,6 +1569,8 @@ struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy,
 			continue;
 		if (!is_valid_ether_addr(bss->pub.bssid))
 			continue;
+		if ((bss->pub.use_for & use_for) != use_for)
+			continue;
 		/* Don't get expired BSS structs */
 		if (time_after(now, bss->ts + IEEE80211_SCAN_RESULT_EXPIRE) &&
 		    !atomic_read(&bss->hold))
@@ -1582,7 +1588,7 @@ struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy,
 	trace_cfg80211_return_bss(&res->pub);
 	return &res->pub;
 }
-EXPORT_SYMBOL(cfg80211_get_bss);
+EXPORT_SYMBOL(__cfg80211_get_bss);
 
 static void rb_insert_bss(struct cfg80211_registered_device *rdev,
 			  struct cfg80211_internal_bss *bss)
@@ -1746,7 +1752,9 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev,
 				   new->pub.proberesp_ies);
 		if (old)
 			kfree_rcu((struct cfg80211_bss_ies *)old, rcu_head);
-	} else if (rcu_access_pointer(new->pub.beacon_ies)) {
+	}
+
+	if (rcu_access_pointer(new->pub.beacon_ies)) {
 		const struct cfg80211_bss_ies *old;
 
 		if (known->pub.hidden_beacon_bss &&
@@ -1800,6 +1808,8 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev,
 	ether_addr_copy(known->parent_bssid, new->parent_bssid);
 	known->pub.max_bssid_indicator = new->pub.max_bssid_indicator;
 	known->pub.bssid_index = new->pub.bssid_index;
+	known->pub.use_for &= new->pub.use_for;
+	known->pub.cannot_use_reasons = new->pub.cannot_use_reasons;
 
 	return true;
 }
@@ -1811,15 +1821,15 @@ __cfg80211_bss_update(struct cfg80211_registered_device *rdev,
 		      bool signal_valid, unsigned long ts)
 {
 	struct cfg80211_internal_bss *found = NULL;
+	struct cfg80211_bss_ies *ies;
 
 	if (WARN_ON(!tmp->pub.channel))
-		return NULL;
+		goto free_ies;
 
 	tmp->ts = ts;
 
-	if (WARN_ON(!rcu_access_pointer(tmp->pub.ies))) {
-		return NULL;
-	}
+	if (WARN_ON(!rcu_access_pointer(tmp->pub.ies)))
+		goto free_ies;
 
 	found = rb_find_bss(rdev, tmp, BSS_CMP_REGULAR);
 
@@ -1829,7 +1839,6 @@ __cfg80211_bss_update(struct cfg80211_registered_device *rdev,
 	} else {
 		struct cfg80211_internal_bss *new;
 		struct cfg80211_internal_bss *hidden;
-		struct cfg80211_bss_ies *ies;
 
 		/*
 		 * create a copy -- the "res" variable that is passed in
@@ -1838,15 +1847,8 @@ __cfg80211_bss_update(struct cfg80211_registered_device *rdev,
 		 */
 		new = kzalloc(sizeof(*new) + rdev->wiphy.bss_priv_size,
 			      GFP_ATOMIC);
-		if (!new) {
-			ies = (void *)rcu_dereference(tmp->pub.beacon_ies);
-			if (ies)
-				kfree_rcu(ies, rcu_head);
-			ies = (void *)rcu_dereference(tmp->pub.proberesp_ies);
-			if (ies)
-				kfree_rcu(ies, rcu_head);
-			return NULL;
-		}
+		if (!new)
+			goto free_ies;
 		memcpy(new, tmp, sizeof(*new));
 		new->refcount = 1;
 		INIT_LIST_HEAD(&new->hidden_list);
@@ -1864,8 +1866,12 @@ __cfg80211_bss_update(struct cfg80211_registered_device *rdev,
 				list_add(&new->hidden_list,
 					 &hidden->hidden_list);
 				hidden->refcount++;
+
+				ies = (void *)rcu_access_pointer(new->pub.beacon_ies);
 				rcu_assign_pointer(new->pub.beacon_ies,
 						   hidden->pub.beacon_ies);
+				if (ies)
+					kfree_rcu(ies, rcu_head);
 			}
 		} else {
 			/*
@@ -1902,6 +1908,16 @@ __cfg80211_bss_update(struct cfg80211_registered_device *rdev,
 	bss_ref_get(rdev, found);
 
 	return found;
+
+free_ies:
+	ies = (void *)rcu_dereference(tmp->pub.beacon_ies);
+	if (ies)
+		kfree_rcu(ies, rcu_head);
+	ies = (void *)rcu_dereference(tmp->pub.proberesp_ies);
+	if (ies)
+		kfree_rcu(ies, rcu_head);
+
+	return NULL;
 }
 
 struct cfg80211_internal_bss *
@@ -2044,6 +2060,9 @@ struct cfg80211_inform_single_bss_data {
 	struct cfg80211_bss *source_bss;
 	u8 max_bssid_indicator;
 	u8 bssid_index;
+
+	u8 use_for;
+	u64 cannot_use_reasons;
 };
 
 /* Returned bss is reference counted and must be cleaned up appropriately. */
@@ -2089,6 +2108,8 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy,
 	tmp.ts_boottime = drv_data->boottime_ns;
 	tmp.parent_tsf = drv_data->parent_tsf;
 	ether_addr_copy(tmp.parent_bssid, drv_data->parent_bssid);
+	tmp.pub.use_for = data->use_for;
+	tmp.pub.cannot_use_reasons = data->cannot_use_reasons;
 
 	if (data->bss_source != BSS_SOURCE_DIRECT) {
 		tmp.pub.transmitted_bss = data->source_bss;
@@ -2259,6 +2280,8 @@ cfg80211_parse_mbssid_data(struct wiphy *wiphy,
 		.beacon_interval = tx_data->beacon_interval,
 		.source_bss = source_bss,
 		.bss_source = BSS_SOURCE_MBSSID,
+		.use_for = tx_data->use_for,
+		.cannot_use_reasons = tx_data->cannot_use_reasons,
 	};
 	const u8 *mbssid_index_ie;
 	const struct element *elem, *sub;
@@ -2521,7 +2544,7 @@ error:
 	return NULL;
 }
 
-static bool
+static u8
 cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id,
 			      const struct ieee80211_neighbor_ap_info **ap_info,
 			      const u8 **tbtt_info)
@@ -2540,6 +2563,7 @@ cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id,
 			u16 params;
 			u8 length, i, count, mld_params_offset;
 			u8 type, lid;
+			u32 use_for;
 
 			info = (void *)pos;
 			count = u8_get_bits(info->tbtt_info_hdr,
@@ -2549,20 +2573,22 @@ cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id,
 			pos += sizeof(*info);
 
 			if (count * length > end - pos)
-				return false;
+				return 0;
 
 			type = u8_get_bits(info->tbtt_info_hdr,
 					   IEEE80211_AP_INFO_TBTT_HDR_TYPE);
 
-			/* Only accept full TBTT information. NSTR mobile APs
-			 * use the shortened version, but we ignore them here.
-			 */
 			if (type == IEEE80211_TBTT_INFO_TYPE_TBTT &&
 			    length >=
 			    offsetofend(struct ieee80211_tbtt_info_ge_11,
 					mld_params)) {
 				mld_params_offset =
 					offsetof(struct ieee80211_tbtt_info_ge_11, mld_params);
+				use_for = NL80211_BSS_USE_FOR_ALL;
+			} else if (type == IEEE80211_TBTT_INFO_TYPE_MLD &&
+				   length >= sizeof(struct ieee80211_rnr_mld_params)) {
+				mld_params_offset = 0;
+				use_for = NL80211_BSS_USE_FOR_MLD_LINK;
 			} else {
 				pos += count * length;
 				continue;
@@ -2580,7 +2606,7 @@ cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id,
 					*ap_info = info;
 					*tbtt_info = pos;
 
-					return true;
+					return use_for;
 				}
 
 				pos += length;
@@ -2588,13 +2614,15 @@ cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id,
 		}
 	}
 
-	return false;
+	return 0;
 }
 
-static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy,
-				       struct cfg80211_inform_single_bss_data *tx_data,
-				       struct cfg80211_bss *source_bss,
-				       gfp_t gfp)
+static void
+cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy,
+				struct cfg80211_inform_single_bss_data *tx_data,
+				struct cfg80211_bss *source_bss,
+				const struct element *elem,
+				gfp_t gfp)
 {
 	struct cfg80211_inform_single_bss_data data = {
 		.drv_data = tx_data->drv_data,
@@ -2603,9 +2631,9 @@ static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy,
 		.bss_source = BSS_SOURCE_STA_PROFILE,
 	};
 	struct ieee80211_multi_link_elem *ml_elem;
-	const struct element *elem;
 	struct cfg80211_mle *mle;
 	u16 control;
+	u8 ml_common_len;
 	u8 *new_ie;
 	struct cfg80211_bss *bss;
 	int mld_id;
@@ -2613,15 +2641,7 @@ static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy,
 	const u8 *pos;
 	u8 i;
 
-	if (!source_bss)
-		return;
-
-	if (tx_data->ftype != CFG80211_BSS_FTYPE_PRESP)
-		return;
-
-	elem = cfg80211_find_ext_elem(WLAN_EID_EXT_EHT_MULTI_LINK,
-				      tx_data->ie, tx_data->ielen);
-	if (!elem || !ieee80211_mle_size_ok(elem->data + 1, elem->datalen - 1))
+	if (!ieee80211_mle_size_ok(elem->data + 1, elem->datalen - 1))
 		return;
 
 	ml_elem = (void *)elem->data + 1;
@@ -2636,6 +2656,8 @@ static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy,
 	    !(control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP))
 		return;
 
+	ml_common_len = ml_elem->variable[0];
+
 	/* length + MLD MAC address + link ID info + BSS Params Change Count */
 	pos = ml_elem->variable + 1 + 6 + 1 + 1;
 
@@ -2647,8 +2669,11 @@ static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy,
 	/* MLD capabilities and operations */
 	pos += 2;
 
-	/* Not included when the (nontransmitted) AP is responding itself,
-	 * but defined to zero then (Draft P802.11be_D3.0, 9.4.2.170.2)
+	/*
+	 * The MLD ID of the reporting AP is always zero. It is set if the AP
+	 * is part of an MBSSID set and will be non-zero for ML Elements
+	 * relating to a nontransmitted BSS (matching the Multi-BSSID Index,
+	 * Draft P802.11be_D3.2, 35.3.4.2)
 	 */
 	if (u16_get_bits(control, IEEE80211_MLC_BASIC_PRES_MLD_ID)) {
 		mld_id = *pos;
@@ -2676,7 +2701,7 @@ static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy,
 		const u8 *profile;
 		const u8 *tbtt_info;
 		ssize_t profile_len;
-		u8 link_id;
+		u8 link_id, use_for;
 
 		if (!ieee80211_mle_basic_sta_prof_size_ok((u8 *)mle->sta_prof[i],
 							  mle->sta_prof_len[i]))
@@ -2718,9 +2743,11 @@ static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy,
 		profile_len -= 2;
 
 		/* Find in RNR to look up channel information */
-		if (!cfg80211_tbtt_info_for_mld_ap(tx_data->ie, tx_data->ielen,
-						   mld_id, link_id,
-						   &ap_info, &tbtt_info))
+		use_for = cfg80211_tbtt_info_for_mld_ap(tx_data->ie,
+							tx_data->ielen,
+							mld_id, link_id,
+							&ap_info, &tbtt_info);
+		if (!use_for)
 			continue;
 
 		/* We could sanity check the BSSID is included */
@@ -2732,6 +2759,14 @@ static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy,
 		freq = ieee80211_channel_to_freq_khz(ap_info->channel, band);
 		data.channel = ieee80211_get_channel_khz(wiphy, freq);
 
+		if (use_for == NL80211_BSS_USE_FOR_MLD_LINK &&
+		    !(wiphy->flags & WIPHY_FLAG_SUPPORTS_NSTR_NONPRIMARY)) {
+			use_for = 0;
+			data.cannot_use_reasons =
+				NL80211_BSS_CANNOT_USE_NSTR_NONPRIMARY;
+		}
+		data.use_for = use_for;
+
 		/* Generate new elements */
 		memset(new_ie, 0, IEEE80211_MAX_DATA_LEN);
 		data.ie = new_ie;
@@ -2742,6 +2777,34 @@ static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy,
 		if (!data.ielen)
 			continue;
 
+		/* The generated elements do not contain:
+		 *  - Basic ML element
+		 *  - A TBTT entry in the RNR for the transmitting AP
+		 *
+		 * This information is needed both internally and in userspace
+		 * as such, we should append it here.
+		 */
+		if (data.ielen + 3 + sizeof(*ml_elem) + ml_common_len >
+		    IEEE80211_MAX_DATA_LEN)
+			continue;
+
+		/* Copy the Basic Multi-Link element including the common
+		 * information, and then fix up the link ID.
+		 * Note that the ML element length has been verified and we
+		 * also checked that it contains the link ID.
+		 */
+		new_ie[data.ielen++] = WLAN_EID_EXTENSION;
+		new_ie[data.ielen++] = 1 + sizeof(*ml_elem) + ml_common_len;
+		new_ie[data.ielen++] = WLAN_EID_EXT_EHT_MULTI_LINK;
+		memcpy(new_ie + data.ielen, ml_elem,
+		       sizeof(*ml_elem) + ml_common_len);
+
+		new_ie[data.ielen + sizeof(*ml_elem) + 1 + ETH_ALEN] = link_id;
+
+		data.ielen += sizeof(*ml_elem) + ml_common_len;
+
+		/* TODO: Add an RNR containing only the reporting AP */
+
 		bss = cfg80211_inform_single_bss_data(wiphy, &data, gfp);
 		if (!bss)
 			break;
@@ -2753,6 +2816,25 @@ out:
 	kfree(mle);
 }
 
+static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy,
+				       struct cfg80211_inform_single_bss_data *tx_data,
+				       struct cfg80211_bss *source_bss,
+				       gfp_t gfp)
+{
+	const struct element *elem;
+
+	if (!source_bss)
+		return;
+
+	if (tx_data->ftype != CFG80211_BSS_FTYPE_PRESP)
+		return;
+
+	for_each_element_extid(elem, WLAN_EID_EXT_EHT_MULTI_LINK,
+			       tx_data->ie, tx_data->ielen)
+		cfg80211_parse_ml_elem_sta_data(wiphy, tx_data, source_bss,
+						elem, gfp);
+}
+
 struct cfg80211_bss *
 cfg80211_inform_bss_data(struct wiphy *wiphy,
 			 struct cfg80211_inform_bss *data,
@@ -2769,6 +2851,10 @@ cfg80211_inform_bss_data(struct wiphy *wiphy,
 		.beacon_interval = beacon_interval,
 		.ie = ie,
 		.ielen = ielen,
+		.use_for = data->restrict_use ?
+				data->use_for :
+				NL80211_BSS_USE_FOR_ALL,
+		.cannot_use_reasons = data->cannot_use_reasons,
 	};
 	struct cfg80211_bss *res;
 
@@ -2786,6 +2872,36 @@ cfg80211_inform_bss_data(struct wiphy *wiphy,
 }
 EXPORT_SYMBOL(cfg80211_inform_bss_data);
 
+static bool cfg80211_uhb_power_type_valid(const u8 *ie,
+					  size_t ielen,
+					  const u32 flags)
+{
+	const struct element *tmp;
+	struct ieee80211_he_operation *he_oper;
+
+	tmp = cfg80211_find_ext_elem(WLAN_EID_EXT_HE_OPERATION, ie, ielen);
+	if (tmp && tmp->datalen >= sizeof(*he_oper) + 1) {
+		const struct ieee80211_he_6ghz_oper *he_6ghz_oper;
+
+		he_oper = (void *)&tmp->data[1];
+		he_6ghz_oper = ieee80211_he_6ghz_oper(he_oper);
+
+		if (!he_6ghz_oper)
+			return false;
+
+		switch (u8_get_bits(he_6ghz_oper->control,
+				    IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO)) {
+		case IEEE80211_6GHZ_CTRL_REG_LPI_AP:
+			return true;
+		case IEEE80211_6GHZ_CTRL_REG_SP_AP:
+			return !(flags & IEEE80211_CHAN_NO_UHB_AFC_CLIENT);
+		case IEEE80211_6GHZ_CTRL_REG_VLP_AP:
+			return !(flags & IEEE80211_CHAN_NO_UHB_VLP_CLIENT);
+		}
+	}
+	return false;
+}
+
 /* cfg80211_inform_bss_width_frame helper */
 static struct cfg80211_bss *
 cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
@@ -2844,6 +2960,14 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
 	if (!channel)
 		return NULL;
 
+	if (channel->band == NL80211_BAND_6GHZ &&
+	    !cfg80211_uhb_power_type_valid(variable, ielen, channel->flags)) {
+		data->restrict_use = 1;
+		data->use_for = 0;
+		data->cannot_use_reasons =
+			NL80211_BSS_CANNOT_USE_UHB_PWR_MISMATCH;
+	}
+
 	if (ext) {
 		const struct ieee80211_s1g_bcn_compat_ie *compat;
 		const struct element *elem;
@@ -2899,6 +3023,10 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
 	tmp.pub.chains = data->chains;
 	memcpy(tmp.pub.chain_signal, data->chain_signal, IEEE80211_MAX_CHAINS);
 	ether_addr_copy(tmp.parent_bssid, data->parent_bssid);
+	tmp.pub.use_for = data->restrict_use ?
+				data->use_for :
+				NL80211_BSS_USE_FOR_ALL;
+	tmp.pub.cannot_use_reasons = data->cannot_use_reasons;
 
 	signal_valid = data->chan == channel;
 	spin_lock_bh(&rdev->bss_lock);
@@ -2930,6 +3058,10 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy,
 		.ie = mgmt->u.probe_resp.variable,
 		.ielen = len - offsetof(struct ieee80211_mgmt,
 					u.probe_resp.variable),
+		.use_for = data->restrict_use ?
+				data->use_for :
+				NL80211_BSS_USE_FOR_ALL,
+		.cannot_use_reasons = data->cannot_use_reasons,
 	};
 	struct cfg80211_bss *res;
 
@@ -3080,10 +3212,9 @@ void cfg80211_update_assoc_bss_entry(struct wireless_dev *wdev,
 
 	if (new) {
 		/* to save time, update IEs for transmitting bss only */
-		if (cfg80211_update_known_bss(rdev, cbss, new, false)) {
-			new->pub.proberesp_ies = NULL;
-			new->pub.beacon_ies = NULL;
-		}
+		cfg80211_update_known_bss(rdev, cbss, new, false);
+		new->pub.proberesp_ies = NULL;
+		new->pub.beacon_ies = NULL;
 
 		list_for_each_entry_safe(nontrans_bss, tmp,
 					 &new->pub.nontrans_list,
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index acfe66da7109..195c8532734b 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -1394,6 +1394,8 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie,
 #endif
 
 	schedule_work(&cfg80211_disconnect_work);
+
+	cfg80211_schedule_channels_check(wdev);
 }
 
 void cfg80211_disconnected(struct net_device *dev, u16 reason,
diff --git a/net/wireless/tests/Makefile b/net/wireless/tests/Makefile
index fa8e297bbc5e..1f6622fcb758 100644
--- a/net/wireless/tests/Makefile
+++ b/net/wireless/tests/Makefile
@@ -1,3 +1,3 @@
-cfg80211-tests-y += module.o fragmentation.o
+cfg80211-tests-y += module.o fragmentation.o scan.o util.o
 
 obj-$(CONFIG_CFG80211_KUNIT_TEST) += cfg80211-tests.o
diff --git a/net/wireless/tests/scan.c b/net/wireless/tests/scan.c
new file mode 100644
index 000000000000..77854161cd22
--- /dev/null
+++ b/net/wireless/tests/scan.c
@@ -0,0 +1,625 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * KUnit tests for inform_bss functions
+ *
+ * Copyright (C) 2023 Intel Corporation
+ */
+#include <linux/ieee80211.h>
+#include <net/cfg80211.h>
+#include <kunit/test.h>
+#include <kunit/skbuff.h>
+#include "../core.h"
+#include "util.h"
+
+/* mac80211 helpers for element building */
+#include "../../mac80211/ieee80211_i.h"
+
+MODULE_IMPORT_NS(EXPORTED_FOR_KUNIT_TESTING);
+
+struct test_elem {
+	u8 id;
+	u8 len;
+	union {
+		u8 data[255];
+		struct {
+			u8 eid;
+			u8 edata[254];
+		};
+	};
+};
+
+static struct gen_new_ie_case {
+	const char *desc;
+	struct test_elem parent_ies[16];
+	struct test_elem child_ies[16];
+	struct test_elem result_ies[16];
+} gen_new_ie_cases[] = {
+	{
+		.desc = "ML not inherited",
+		.parent_ies = {
+			{ .id = WLAN_EID_EXTENSION, .len = 255,
+			  .eid = WLAN_EID_EXT_EHT_MULTI_LINK },
+		},
+		.child_ies = {
+			{ .id = WLAN_EID_SSID, .len = 2 },
+		},
+		.result_ies = {
+			{ .id = WLAN_EID_SSID, .len = 2 },
+		},
+	},
+	{
+		.desc = "fragments are ignored if previous len not 255",
+		.parent_ies = {
+			{ .id = WLAN_EID_REDUCED_NEIGHBOR_REPORT, .len = 254, },
+			{ .id = WLAN_EID_FRAGMENT, .len = 125, },
+		},
+		.child_ies = {
+			{ .id = WLAN_EID_SSID, .len = 2 },
+			{ .id = WLAN_EID_FRAGMENT, .len = 125, },
+		},
+		.result_ies = {
+			{ .id = WLAN_EID_REDUCED_NEIGHBOR_REPORT, .len = 254, },
+			{ .id = WLAN_EID_SSID, .len = 2 },
+		},
+	},
+	{
+		.desc = "fragments inherited",
+		.parent_ies = {
+			{ .id = WLAN_EID_REDUCED_NEIGHBOR_REPORT, .len = 255, },
+			{ .id = WLAN_EID_FRAGMENT, .len = 125, },
+		},
+		.child_ies = {
+			{ .id = WLAN_EID_SSID, .len = 2 },
+		},
+		.result_ies = {
+			{ .id = WLAN_EID_REDUCED_NEIGHBOR_REPORT, .len = 255, },
+			{ .id = WLAN_EID_FRAGMENT, .len = 125, },
+			{ .id = WLAN_EID_SSID, .len = 2 },
+		},
+	},
+	{
+		.desc = "fragments copied",
+		.parent_ies = {
+			{ .id = WLAN_EID_REDUCED_NEIGHBOR_REPORT, .len = 255, },
+			{ .id = WLAN_EID_FRAGMENT, .len = 125, },
+		},
+		.child_ies = {
+			{ .id = WLAN_EID_SSID, .len = 2 },
+		},
+		.result_ies = {
+			{ .id = WLAN_EID_REDUCED_NEIGHBOR_REPORT, .len = 255, },
+			{ .id = WLAN_EID_FRAGMENT, .len = 125, },
+			{ .id = WLAN_EID_SSID, .len = 2 },
+		},
+	},
+	{
+		.desc = "multiple elements inherit",
+		.parent_ies = {
+			{ .id = WLAN_EID_REDUCED_NEIGHBOR_REPORT, .len = 255, },
+			{ .id = WLAN_EID_FRAGMENT, .len = 125, },
+			{ .id = WLAN_EID_REDUCED_NEIGHBOR_REPORT, .len = 123, },
+		},
+		.child_ies = {
+			{ .id = WLAN_EID_SSID, .len = 2 },
+		},
+		.result_ies = {
+			{ .id = WLAN_EID_REDUCED_NEIGHBOR_REPORT, .len = 255, },
+			{ .id = WLAN_EID_FRAGMENT, .len = 125, },
+			{ .id = WLAN_EID_REDUCED_NEIGHBOR_REPORT, .len = 123, },
+			{ .id = WLAN_EID_SSID, .len = 2 },
+		},
+	},
+	{
+		.desc = "one child element overrides",
+		.parent_ies = {
+			{ .id = WLAN_EID_REDUCED_NEIGHBOR_REPORT, .len = 255, },
+			{ .id = WLAN_EID_FRAGMENT, .len = 125, },
+			{ .id = WLAN_EID_REDUCED_NEIGHBOR_REPORT, .len = 123, },
+		},
+		.child_ies = {
+			{ .id = WLAN_EID_REDUCED_NEIGHBOR_REPORT, .len = 127, },
+			{ .id = WLAN_EID_SSID, .len = 2 },
+		},
+		.result_ies = {
+			{ .id = WLAN_EID_REDUCED_NEIGHBOR_REPORT, .len = 127, },
+			{ .id = WLAN_EID_SSID, .len = 2 },
+		},
+	},
+	{
+		.desc = "empty elements from parent",
+		.parent_ies = {
+			{ .id = 0x1, .len = 0, },
+			{ .id = WLAN_EID_EXTENSION, .len = 1, .eid = 0x10 },
+		},
+		.child_ies = {
+		},
+		.result_ies = {
+			{ .id = 0x1, .len = 0, },
+			{ .id = WLAN_EID_EXTENSION, .len = 1, .eid = 0x10 },
+		},
+	},
+	{
+		.desc = "empty elements from child",
+		.parent_ies = {
+		},
+		.child_ies = {
+			{ .id = 0x1, .len = 0, },
+			{ .id = WLAN_EID_EXTENSION, .len = 1, .eid = 0x10 },
+		},
+		.result_ies = {
+			{ .id = 0x1, .len = 0, },
+			{ .id = WLAN_EID_EXTENSION, .len = 1, .eid = 0x10 },
+		},
+	},
+	{
+		.desc = "invalid extended elements ignored",
+		.parent_ies = {
+			{ .id = WLAN_EID_EXTENSION, .len = 0 },
+		},
+		.child_ies = {
+			{ .id = WLAN_EID_EXTENSION, .len = 0 },
+		},
+		.result_ies = {
+		},
+	},
+	{
+		.desc = "multiple extended elements",
+		.parent_ies = {
+			{ .id = WLAN_EID_EXTENSION, .len = 3,
+			  .eid = WLAN_EID_EXT_HE_CAPABILITY },
+			{ .id = WLAN_EID_EXTENSION, .len = 5,
+			  .eid = WLAN_EID_EXT_ASSOC_DELAY_INFO },
+			{ .id = WLAN_EID_EXTENSION, .len = 7,
+			  .eid = WLAN_EID_EXT_HE_OPERATION },
+			{ .id = WLAN_EID_EXTENSION, .len = 11,
+			  .eid = WLAN_EID_EXT_FILS_REQ_PARAMS },
+		},
+		.child_ies = {
+			{ .id = WLAN_EID_SSID, .len = 13 },
+			{ .id = WLAN_EID_EXTENSION, .len = 17,
+			  .eid = WLAN_EID_EXT_HE_CAPABILITY },
+			{ .id = WLAN_EID_EXTENSION, .len = 11,
+			  .eid = WLAN_EID_EXT_FILS_KEY_CONFIRM },
+			{ .id = WLAN_EID_EXTENSION, .len = 19,
+			  .eid = WLAN_EID_EXT_HE_OPERATION },
+		},
+		.result_ies = {
+			{ .id = WLAN_EID_EXTENSION, .len = 17,
+			  .eid = WLAN_EID_EXT_HE_CAPABILITY },
+			{ .id = WLAN_EID_EXTENSION, .len = 5,
+			  .eid = WLAN_EID_EXT_ASSOC_DELAY_INFO },
+			{ .id = WLAN_EID_EXTENSION, .len = 19,
+			  .eid = WLAN_EID_EXT_HE_OPERATION },
+			{ .id = WLAN_EID_EXTENSION, .len = 11,
+			  .eid = WLAN_EID_EXT_FILS_REQ_PARAMS },
+			{ .id = WLAN_EID_SSID, .len = 13 },
+			{ .id = WLAN_EID_EXTENSION, .len = 11,
+			  .eid = WLAN_EID_EXT_FILS_KEY_CONFIRM },
+		},
+	},
+	{
+		.desc = "non-inherit element",
+		.parent_ies = {
+			{ .id = 0x1, .len = 7, },
+			{ .id = 0x2, .len = 11, },
+			{ .id = 0x3, .len = 13, },
+			{ .id = WLAN_EID_EXTENSION, .len = 17, .eid = 0x10 },
+			{ .id = WLAN_EID_EXTENSION, .len = 19, .eid = 0x11 },
+			{ .id = WLAN_EID_EXTENSION, .len = 23, .eid = 0x12 },
+			{ .id = WLAN_EID_EXTENSION, .len = 29, .eid = 0x14 },
+		},
+		.child_ies = {
+			{ .id = WLAN_EID_EXTENSION,
+			  .eid = WLAN_EID_EXT_NON_INHERITANCE,
+			  .len = 10,
+			  .edata = { 0x3, 0x1, 0x2, 0x3,
+				     0x4, 0x10, 0x11, 0x13, 0x14 } },
+			{ .id = WLAN_EID_SSID, .len = 2 },
+		},
+		.result_ies = {
+			{ .id = WLAN_EID_EXTENSION, .len = 23, .eid = 0x12 },
+			{ .id = WLAN_EID_SSID, .len = 2 },
+		},
+	},
+};
+KUNIT_ARRAY_PARAM_DESC(gen_new_ie, gen_new_ie_cases, desc)
+
+static void test_gen_new_ie(struct kunit *test)
+{
+	const struct gen_new_ie_case *params = test->param_value;
+	struct sk_buff *parent = kunit_zalloc_skb(test, 1024, GFP_KERNEL);
+	struct sk_buff *child = kunit_zalloc_skb(test, 1024, GFP_KERNEL);
+	struct sk_buff *reference = kunit_zalloc_skb(test, 1024, GFP_KERNEL);
+	u8 *out = kunit_kzalloc(test, IEEE80211_MAX_DATA_LEN, GFP_KERNEL);
+	size_t len;
+	int i;
+
+	KUNIT_ASSERT_NOT_NULL(test, parent);
+	KUNIT_ASSERT_NOT_NULL(test, child);
+	KUNIT_ASSERT_NOT_NULL(test, reference);
+	KUNIT_ASSERT_NOT_NULL(test, out);
+
+	for (i = 0; i < ARRAY_SIZE(params->parent_ies); i++) {
+		if (params->parent_ies[i].len != 0) {
+			skb_put_u8(parent, params->parent_ies[i].id);
+			skb_put_u8(parent, params->parent_ies[i].len);
+			skb_put_data(parent, params->parent_ies[i].data,
+				     params->parent_ies[i].len);
+		}
+
+		if (params->child_ies[i].len != 0) {
+			skb_put_u8(child, params->child_ies[i].id);
+			skb_put_u8(child, params->child_ies[i].len);
+			skb_put_data(child, params->child_ies[i].data,
+				     params->child_ies[i].len);
+		}
+
+		if (params->result_ies[i].len != 0) {
+			skb_put_u8(reference, params->result_ies[i].id);
+			skb_put_u8(reference, params->result_ies[i].len);
+			skb_put_data(reference, params->result_ies[i].data,
+				     params->result_ies[i].len);
+		}
+	}
+
+	len = cfg80211_gen_new_ie(parent->data, parent->len,
+				  child->data, child->len,
+				  out, IEEE80211_MAX_DATA_LEN);
+	KUNIT_EXPECT_EQ(test, len, reference->len);
+	KUNIT_EXPECT_MEMEQ(test, out, reference->data, reference->len);
+	memset(out, 0, IEEE80211_MAX_DATA_LEN);
+
+	/* Exactly enough space */
+	len = cfg80211_gen_new_ie(parent->data, parent->len,
+				  child->data, child->len,
+				  out, reference->len);
+	KUNIT_EXPECT_EQ(test, len, reference->len);
+	KUNIT_EXPECT_MEMEQ(test, out, reference->data, reference->len);
+	memset(out, 0, IEEE80211_MAX_DATA_LEN);
+
+	/* Not enough space (or expected zero length) */
+	len = cfg80211_gen_new_ie(parent->data, parent->len,
+				  child->data, child->len,
+				  out, reference->len - 1);
+	KUNIT_EXPECT_EQ(test, len, 0);
+}
+
+static void test_gen_new_ie_malformed(struct kunit *test)
+{
+	struct sk_buff *malformed = kunit_zalloc_skb(test, 1024, GFP_KERNEL);
+	u8 *out = kunit_kzalloc(test, IEEE80211_MAX_DATA_LEN, GFP_KERNEL);
+	size_t len;
+
+	KUNIT_ASSERT_NOT_NULL(test, malformed);
+	KUNIT_ASSERT_NOT_NULL(test, out);
+
+	skb_put_u8(malformed, WLAN_EID_SSID);
+	skb_put_u8(malformed, 3);
+	skb_put(malformed, 3);
+	skb_put_u8(malformed, WLAN_EID_REDUCED_NEIGHBOR_REPORT);
+	skb_put_u8(malformed, 10);
+	skb_put(malformed, 9);
+
+	len = cfg80211_gen_new_ie(malformed->data, malformed->len,
+				  out, 0,
+				  out, IEEE80211_MAX_DATA_LEN);
+	KUNIT_EXPECT_EQ(test, len, 5);
+
+	len = cfg80211_gen_new_ie(out, 0,
+				  malformed->data, malformed->len,
+				  out, IEEE80211_MAX_DATA_LEN);
+	KUNIT_EXPECT_EQ(test, len, 5);
+}
+
+struct inform_bss {
+	struct kunit *test;
+
+	int inform_bss_count;
+};
+
+static void inform_bss_inc_counter(struct wiphy *wiphy,
+				   struct cfg80211_bss *bss,
+				   const struct cfg80211_bss_ies *ies,
+				   void *drv_data)
+{
+	struct inform_bss *ctx = t_wiphy_ctx(wiphy);
+
+	ctx->inform_bss_count++;
+
+	rcu_read_lock();
+	KUNIT_EXPECT_PTR_EQ(ctx->test, drv_data, ctx);
+	KUNIT_EXPECT_PTR_EQ(ctx->test, ies, rcu_dereference(bss->ies));
+	rcu_read_unlock();
+}
+
+static void test_inform_bss_ssid_only(struct kunit *test)
+{
+	struct inform_bss ctx = {
+		.test = test,
+	};
+	struct wiphy *wiphy = T_WIPHY(test, ctx);
+	struct t_wiphy_priv *w_priv = wiphy_priv(wiphy);
+	struct cfg80211_inform_bss inform_bss = {
+		.signal = 50,
+		.drv_data = &ctx,
+	};
+	const u8 bssid[ETH_ALEN] = { 0x10, 0x22, 0x33, 0x44, 0x55, 0x66 };
+	u64 tsf = 0x1000000000000000ULL;
+	int beacon_int = 100;
+	u16 capability = 0x1234;
+	static const u8 input[] = {
+		[0] = WLAN_EID_SSID,
+		[1] = 4,
+		[2] = 'T', 'E', 'S', 'T'
+	};
+	struct cfg80211_bss *bss, *other;
+	const struct cfg80211_bss_ies *ies;
+
+	w_priv->ops->inform_bss = inform_bss_inc_counter;
+
+	inform_bss.chan = ieee80211_get_channel_khz(wiphy, MHZ_TO_KHZ(2412));
+	KUNIT_ASSERT_NOT_NULL(test, inform_bss.chan);
+
+	bss = cfg80211_inform_bss_data(wiphy, &inform_bss,
+				       CFG80211_BSS_FTYPE_PRESP, bssid, tsf,
+				       capability, beacon_int,
+				       input, sizeof(input),
+				       GFP_KERNEL);
+	KUNIT_EXPECT_NOT_NULL(test, bss);
+	KUNIT_EXPECT_EQ(test, ctx.inform_bss_count, 1);
+
+	/* Check values in returned bss are correct */
+	KUNIT_EXPECT_EQ(test, bss->signal, inform_bss.signal);
+	KUNIT_EXPECT_EQ(test, bss->beacon_interval, beacon_int);
+	KUNIT_EXPECT_EQ(test, bss->capability, capability);
+	KUNIT_EXPECT_EQ(test, bss->bssid_index, 0);
+	KUNIT_EXPECT_PTR_EQ(test, bss->channel, inform_bss.chan);
+	KUNIT_EXPECT_MEMEQ(test, bssid, bss->bssid, sizeof(bssid));
+
+	/* Check the IEs have the expected value */
+	rcu_read_lock();
+	ies = rcu_dereference(bss->ies);
+	KUNIT_EXPECT_NOT_NULL(test, ies);
+	KUNIT_EXPECT_EQ(test, ies->tsf, tsf);
+	KUNIT_EXPECT_EQ(test, ies->len, sizeof(input));
+	KUNIT_EXPECT_MEMEQ(test, ies->data, input, sizeof(input));
+	rcu_read_unlock();
+
+	/* Check we can look up the BSS - by SSID */
+	other = cfg80211_get_bss(wiphy, NULL, NULL, "TEST", 4,
+				 IEEE80211_BSS_TYPE_ANY,
+				 IEEE80211_PRIVACY_ANY);
+	KUNIT_EXPECT_PTR_EQ(test, bss, other);
+	cfg80211_put_bss(wiphy, other);
+
+	/* Check we can look up the BSS - by BSSID */
+	other = cfg80211_get_bss(wiphy, NULL, bssid, NULL, 0,
+				 IEEE80211_BSS_TYPE_ANY,
+				 IEEE80211_PRIVACY_ANY);
+	KUNIT_EXPECT_PTR_EQ(test, bss, other);
+	cfg80211_put_bss(wiphy, other);
+
+	cfg80211_put_bss(wiphy, bss);
+}
+
+static struct inform_bss_ml_sta_case {
+	const char *desc;
+	int mld_id;
+	bool sta_prof_vendor_elems;
+} inform_bss_ml_sta_cases[] = {
+	{ .desc = "no_mld_id", .mld_id = 0, .sta_prof_vendor_elems = false },
+	{ .desc = "mld_id_eq_1", .mld_id = 1, .sta_prof_vendor_elems = true },
+};
+KUNIT_ARRAY_PARAM_DESC(inform_bss_ml_sta, inform_bss_ml_sta_cases, desc)
+
+static void test_inform_bss_ml_sta(struct kunit *test)
+{
+	const struct inform_bss_ml_sta_case *params = test->param_value;
+	struct inform_bss ctx = {
+		.test = test,
+	};
+	struct wiphy *wiphy = T_WIPHY(test, ctx);
+	struct t_wiphy_priv *w_priv = wiphy_priv(wiphy);
+	struct cfg80211_inform_bss inform_bss = {
+		.signal = 50,
+		.drv_data = &ctx,
+	};
+	struct cfg80211_bss *bss, *link_bss;
+	const struct cfg80211_bss_ies *ies;
+
+	/* sending station */
+	const u8 bssid[ETH_ALEN] = { 0x10, 0x22, 0x33, 0x44, 0x55, 0x66 };
+	u64 tsf = 0x1000000000000000ULL;
+	int beacon_int = 100;
+	u16 capability = 0x1234;
+
+	/* Building the frame *************************************************/
+	struct sk_buff *input = kunit_zalloc_skb(test, 1024, GFP_KERNEL);
+	u8 *len_mle, *len_prof;
+	u8 link_id = 2;
+	struct {
+		struct ieee80211_neighbor_ap_info info;
+		struct ieee80211_tbtt_info_ge_11 ap;
+	} __packed rnr = {
+		.info = {
+			.tbtt_info_hdr = u8_encode_bits(0, IEEE80211_AP_INFO_TBTT_HDR_COUNT),
+			.tbtt_info_len = sizeof(struct ieee80211_tbtt_info_ge_11),
+			.op_class = 81,
+			.channel = 11,
+		},
+		.ap = {
+			.tbtt_offset = 0xff,
+			.bssid = { 0x10, 0x22, 0x33, 0x44, 0x55, 0x67 },
+			.short_ssid = 0, /* unused */
+			.bss_params = 0,
+			.psd_20 = 0,
+			.mld_params.mld_id = params->mld_id,
+			.mld_params.params =
+				le16_encode_bits(link_id,
+						 IEEE80211_RNR_MLD_PARAMS_LINK_ID),
+		}
+	};
+	struct {
+		__le16 control;
+		u8 var_len;
+		u8 mld_mac_addr[ETH_ALEN];
+		u8 link_id_info;
+		u8 params_change_count;
+		__le16 mld_caps_and_ops;
+		u8 mld_id;
+		__le16 ext_mld_caps_and_ops;
+	} __packed mle_basic_common_info = {
+		.control =
+			cpu_to_le16(IEEE80211_ML_CONTROL_TYPE_BASIC |
+				    IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT |
+				    IEEE80211_MLC_BASIC_PRES_LINK_ID |
+				    (params->mld_id ? IEEE80211_MLC_BASIC_PRES_MLD_ID : 0) |
+				    IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP),
+		.mld_id = params->mld_id,
+		.mld_caps_and_ops = cpu_to_le16(0x0102),
+		.ext_mld_caps_and_ops = cpu_to_le16(0x0304),
+		.var_len = sizeof(mle_basic_common_info) - 2 -
+			   (params->mld_id ? 0 : 1),
+		.mld_mac_addr = { 0x10, 0x22, 0x33, 0x44, 0x55, 0x60 },
+	};
+	struct {
+		__le16 control;
+		u8 var_len;
+		u8 bssid[ETH_ALEN];
+		__le16 beacon_int;
+		__le64 tsf_offset;
+		__le16 capabilities; /* already part of payload */
+	} __packed sta_prof = {
+		.control =
+			cpu_to_le16(IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE |
+				    IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT |
+				    IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT |
+				    IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT |
+				    u16_encode_bits(link_id,
+						    IEEE80211_MLE_STA_CONTROL_LINK_ID)),
+		.var_len = sizeof(sta_prof) - 2 - 2,
+		.bssid = { *rnr.ap.bssid },
+		.beacon_int = cpu_to_le16(101),
+		.tsf_offset = cpu_to_le64(-123ll),
+		.capabilities = cpu_to_le16(0xdead),
+	};
+
+	KUNIT_ASSERT_NOT_NULL(test, input);
+
+	w_priv->ops->inform_bss = inform_bss_inc_counter;
+
+	inform_bss.chan = ieee80211_get_channel_khz(wiphy, MHZ_TO_KHZ(2412));
+	KUNIT_ASSERT_NOT_NULL(test, inform_bss.chan);
+
+	skb_put_u8(input, WLAN_EID_SSID);
+	skb_put_u8(input, 4);
+	skb_put_data(input, "TEST", 4);
+
+	skb_put_u8(input, WLAN_EID_REDUCED_NEIGHBOR_REPORT);
+	skb_put_u8(input, sizeof(rnr));
+	skb_put_data(input, &rnr, sizeof(rnr));
+
+	/* build a multi-link element */
+	skb_put_u8(input, WLAN_EID_EXTENSION);
+	len_mle = skb_put(input, 1);
+	skb_put_u8(input, WLAN_EID_EXT_EHT_MULTI_LINK);
+	skb_put_data(input, &mle_basic_common_info, sizeof(mle_basic_common_info));
+	if (!params->mld_id)
+		t_skb_remove_member(input, typeof(mle_basic_common_info), mld_id);
+	/* with a STA profile inside */
+	skb_put_u8(input, IEEE80211_MLE_SUBELEM_PER_STA_PROFILE);
+	len_prof = skb_put(input, 1);
+	skb_put_data(input, &sta_prof, sizeof(sta_prof));
+
+	if (params->sta_prof_vendor_elems) {
+		/* Put two (vendor) element into sta_prof */
+		skb_put_u8(input, WLAN_EID_VENDOR_SPECIFIC);
+		skb_put_u8(input, 160);
+		skb_put(input, 160);
+
+		skb_put_u8(input, WLAN_EID_VENDOR_SPECIFIC);
+		skb_put_u8(input, 165);
+		skb_put(input, 165);
+	}
+
+	/* fragment STA profile */
+	ieee80211_fragment_element(input, len_prof,
+				   IEEE80211_MLE_SUBELEM_FRAGMENT);
+	/* fragment MLE */
+	ieee80211_fragment_element(input, len_mle, WLAN_EID_FRAGMENT);
+
+	/* Put a (vendor) element after the ML element */
+	skb_put_u8(input, WLAN_EID_VENDOR_SPECIFIC);
+	skb_put_u8(input, 155);
+	skb_put(input, 155);
+
+	/* Submit *************************************************************/
+	bss = cfg80211_inform_bss_data(wiphy, &inform_bss,
+				       CFG80211_BSS_FTYPE_PRESP, bssid, tsf,
+				       capability, beacon_int,
+				       input->data, input->len,
+				       GFP_KERNEL);
+	KUNIT_EXPECT_NOT_NULL(test, bss);
+	KUNIT_EXPECT_EQ(test, ctx.inform_bss_count, 2);
+
+	/* Check link_bss *****************************************************/
+	link_bss = cfg80211_get_bss(wiphy, NULL, sta_prof.bssid, NULL, 0,
+				    IEEE80211_BSS_TYPE_ANY,
+				    IEEE80211_PRIVACY_ANY);
+	KUNIT_ASSERT_NOT_NULL(test, link_bss);
+	KUNIT_EXPECT_EQ(test, link_bss->signal, 0);
+	KUNIT_EXPECT_EQ(test, link_bss->beacon_interval,
+			      le16_to_cpu(sta_prof.beacon_int));
+	KUNIT_EXPECT_EQ(test, link_bss->capability,
+			      le16_to_cpu(sta_prof.capabilities));
+	KUNIT_EXPECT_EQ(test, link_bss->bssid_index, 0);
+	KUNIT_EXPECT_PTR_EQ(test, link_bss->channel,
+			    ieee80211_get_channel_khz(wiphy, MHZ_TO_KHZ(2462)));
+
+	rcu_read_lock();
+	ies = rcu_dereference(link_bss->ies);
+	KUNIT_EXPECT_NOT_NULL(test, ies);
+	KUNIT_EXPECT_EQ(test, ies->tsf, tsf + le64_to_cpu(sta_prof.tsf_offset));
+	/* Resulting length should be:
+	 * SSID (inherited) + RNR (inherited) + vendor element(s) +
+	 * MLE common info + MLE header and control
+	 */
+	if (params->sta_prof_vendor_elems)
+		KUNIT_EXPECT_EQ(test, ies->len,
+				6 + 2 + sizeof(rnr) + 2 + 160 + 2 + 165 +
+				mle_basic_common_info.var_len + 5);
+	else
+		KUNIT_EXPECT_EQ(test, ies->len,
+				6 + 2 + sizeof(rnr) + 2 + 155 +
+				mle_basic_common_info.var_len + 5);
+	rcu_read_unlock();
+
+	cfg80211_put_bss(wiphy, bss);
+	cfg80211_put_bss(wiphy, link_bss);
+}
+
+static struct kunit_case gen_new_ie_test_cases[] = {
+	KUNIT_CASE_PARAM(test_gen_new_ie, gen_new_ie_gen_params),
+	KUNIT_CASE(test_gen_new_ie_malformed),
+	{}
+};
+
+static struct kunit_suite gen_new_ie = {
+	.name = "cfg80211-ie-generation",
+	.test_cases = gen_new_ie_test_cases,
+};
+
+kunit_test_suite(gen_new_ie);
+
+static struct kunit_case inform_bss_test_cases[] = {
+	KUNIT_CASE(test_inform_bss_ssid_only),
+	KUNIT_CASE_PARAM(test_inform_bss_ml_sta, inform_bss_ml_sta_gen_params),
+	{}
+};
+
+static struct kunit_suite inform_bss = {
+	.name = "cfg80211-inform-bss",
+	.test_cases = inform_bss_test_cases,
+};
+
+kunit_test_suite(inform_bss);
diff --git a/net/wireless/tests/util.c b/net/wireless/tests/util.c
new file mode 100644
index 000000000000..8abdaeb820ce
--- /dev/null
+++ b/net/wireless/tests/util.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * KUnit fixture to have a (configurable) wiphy
+ *
+ * Copyright (C) 2023 Intel Corporation
+ */
+#include <linux/ieee80211.h>
+#include <net/cfg80211.h>
+#include <kunit/test.h>
+#include <kunit/test-bug.h>
+#include "util.h"
+
+int t_wiphy_init(struct kunit_resource *resource, void *ctx)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct cfg80211_ops *ops;
+	struct wiphy *wiphy;
+	struct t_wiphy_priv *priv;
+
+	ops = kzalloc(sizeof(*ops), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_NULL(test, ops);
+
+	wiphy = wiphy_new_nm(ops, sizeof(*priv), "kunit");
+	KUNIT_ASSERT_NOT_NULL(test, wiphy);
+
+	priv = wiphy_priv(wiphy);
+	priv->ctx = ctx;
+	priv->ops = ops;
+
+	/* Initialize channels, feel free to add more here channels/bands */
+	memcpy(priv->channels_2ghz, channels_2ghz, sizeof(channels_2ghz));
+	wiphy->bands[NL80211_BAND_2GHZ] = &priv->band_2ghz;
+	priv->band_2ghz.channels = priv->channels_2ghz;
+	priv->band_2ghz.n_channels = ARRAY_SIZE(channels_2ghz);
+
+	resource->data = wiphy;
+	resource->name = "wiphy";
+
+	return 0;
+}
+
+void t_wiphy_exit(struct kunit_resource *resource)
+{
+	struct t_wiphy_priv *priv;
+	struct cfg80211_ops *ops;
+
+	priv = wiphy_priv(resource->data);
+	ops = priv->ops;
+
+	/* Should we ensure anything about the state here?
+	 * e.g. full destruction or no calls to any ops on destruction?
+	 */
+
+	wiphy_free(resource->data);
+	kfree(ops);
+}
diff --git a/net/wireless/tests/util.h b/net/wireless/tests/util.h
new file mode 100644
index 000000000000..6de712e0d432
--- /dev/null
+++ b/net/wireless/tests/util.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Utilities for cfg80211 unit testing
+ *
+ * Copyright (C) 2023 Intel Corporation
+ */
+#ifndef __CFG80211_UTILS_H
+#define __CFG80211_UTILS_H
+
+#define CHAN2G(_freq)  { \
+	.band = NL80211_BAND_2GHZ, \
+	.center_freq = (_freq), \
+	.hw_value = (_freq), \
+}
+
+static const struct ieee80211_channel channels_2ghz[] = {
+	CHAN2G(2412), /* Channel 1 */
+	CHAN2G(2417), /* Channel 2 */
+	CHAN2G(2422), /* Channel 3 */
+	CHAN2G(2427), /* Channel 4 */
+	CHAN2G(2432), /* Channel 5 */
+	CHAN2G(2437), /* Channel 6 */
+	CHAN2G(2442), /* Channel 7 */
+	CHAN2G(2447), /* Channel 8 */
+	CHAN2G(2452), /* Channel 9 */
+	CHAN2G(2457), /* Channel 10 */
+	CHAN2G(2462), /* Channel 11 */
+	CHAN2G(2467), /* Channel 12 */
+	CHAN2G(2472), /* Channel 13 */
+	CHAN2G(2484), /* Channel 14 */
+};
+
+struct t_wiphy_priv {
+	struct kunit *test;
+	struct cfg80211_ops *ops;
+
+	void *ctx;
+
+	struct ieee80211_supported_band band_2ghz;
+	struct ieee80211_channel channels_2ghz[ARRAY_SIZE(channels_2ghz)];
+};
+
+#define T_WIPHY(test, ctx) ({						\
+		struct wiphy *__wiphy =					\
+			kunit_alloc_resource(test, t_wiphy_init,	\
+					     t_wiphy_exit,		\
+					     GFP_KERNEL, &(ctx));	\
+									\
+		KUNIT_ASSERT_NOT_NULL(test, __wiphy);			\
+		__wiphy;						\
+	})
+#define t_wiphy_ctx(wiphy) (((struct t_wiphy_priv *)wiphy_priv(wiphy))->ctx)
+
+int t_wiphy_init(struct kunit_resource *resource, void *data);
+void t_wiphy_exit(struct kunit_resource *resource);
+
+#define t_skb_remove_member(skb, type, member)	do {				\
+		memmove((skb)->data + (skb)->len - sizeof(type) +		\
+			offsetof(type, member),					\
+			(skb)->data + (skb)->len - sizeof(type) +		\
+			offsetofend(type, member),				\
+			offsetofend(type, member));				\
+		skb_trim(skb, (skb)->len - sizeof_field(type, member));		\
+	} while (0)
+
+#endif /* __CFG80211_UTILS_H */
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 30cd1bd58aac..1f374c8a17a5 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -2928,7 +2928,7 @@ DEFINE_EVENT(netdev_evt_only, cfg80211_send_rx_auth,
 
 TRACE_EVENT(cfg80211_send_rx_assoc,
 	TP_PROTO(struct net_device *netdev,
-		 struct cfg80211_rx_assoc_resp_data *data),
+		 const struct cfg80211_rx_assoc_resp_data *data),
 	TP_ARGS(netdev, data),
 	TP_STRUCT__entry(
 		NETDEV_ENTRY
@@ -3979,6 +3979,26 @@ TRACE_EVENT(cfg80211_links_removed,
 		  __entry->link_mask)
 );
 
+TRACE_EVENT(rdev_set_ttlm,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 struct cfg80211_ttlm_params *params),
+	TP_ARGS(wiphy, netdev, params),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		__array(u8, dlink, sizeof(u16) * 8)
+		__array(u8, ulink, sizeof(u16) * 8)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		memcpy(__entry->dlink, params->dlink, sizeof(params->dlink));
+		memcpy(__entry->ulink, params->ulink, sizeof(params->ulink));
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT,
+		  WIPHY_PR_ARG, NETDEV_PR_ARG)
+);
+
 #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 626b858b4b35..d1ce3bee2797 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -980,7 +980,63 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb,
 		}
 	}
 
+	/* The default mapping as defined Section 2.3 in RFC8325: The three
+	 * Most Significant Bits (MSBs) of the DSCP are used as the
+	 * corresponding L2 markings.
+	 */
 	ret = dscp >> 5;
+
+	/* Handle specific DSCP values for which the default mapping (as
+	 * described above) doesn't adhere to the intended usage of the DSCP
+	 * value. See section 4 in RFC8325. Specifically, for the following
+	 * Diffserv Service Classes no update is needed:
+	 * - Standard: DF
+	 * - Low Priority Data: CS1
+	 * - Multimedia Streaming: AF31, AF32, AF33
+	 * - Multimedia Conferencing: AF41, AF42, AF43
+	 * - Network Control Traffic: CS7
+	 * - Real-Time Interactive: CS4
+	 */
+	switch (dscp >> 2) {
+	case 10:
+	case 12:
+	case 14:
+		/* High throughput data: AF11, AF12, AF13 */
+		ret = 0;
+		break;
+	case 16:
+		/* Operations, Administration, and Maintenance and Provisioning:
+		 * CS2
+		 */
+		ret = 0;
+		break;
+	case 18:
+	case 20:
+	case 22:
+		/* Low latency data: AF21, AF22, AF23 */
+		ret = 3;
+		break;
+	case 24:
+		/* Broadcasting video: CS3 */
+		ret = 4;
+		break;
+	case 40:
+		/* Signaling: CS5 */
+		ret = 5;
+		break;
+	case 44:
+		/* Voice Admit: VA */
+		ret = 6;
+		break;
+	case 46:
+		/* Telephony traffic: EF */
+		ret = 6;
+		break;
+	case 48:
+		/* Network Control Traffic: CS6 */
+		ret = 7;
+		break;
+	}
 out:
 	return array_index_nospec(ret, IEEE80211_NUM_TIDS);
 }
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index aad8ffeaee04..f7a7c7798c3b 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -704,7 +704,7 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		rc = -EINVAL;
 	}
 	release_sock(sk);
-	SOCK_DEBUG(sk, "x25_bind: socket is bound\n");
+	net_dbg_ratelimited("x25_bind: socket is bound\n");
 out:
 	return rc;
 }
@@ -1165,10 +1165,10 @@ static int x25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 		goto out;
 	}
 
-	SOCK_DEBUG(sk, "x25_sendmsg: sendto: Addresses built.\n");
+	net_dbg_ratelimited("x25_sendmsg: sendto: Addresses built.\n");
 
 	/* Build a packet */
-	SOCK_DEBUG(sk, "x25_sendmsg: sendto: building packet.\n");
+	net_dbg_ratelimited("x25_sendmsg: sendto: building packet.\n");
 
 	if ((msg->msg_flags & MSG_OOB) && len > 32)
 		len = 32;
@@ -1187,7 +1187,7 @@ static int x25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	/*
 	 *	Put the data on the end
 	 */
-	SOCK_DEBUG(sk, "x25_sendmsg: Copying user data\n");
+	net_dbg_ratelimited("x25_sendmsg: Copying user data\n");
 
 	skb_reset_transport_header(skb);
 	skb_put(skb, len);
@@ -1211,7 +1211,7 @@ static int x25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	/*
 	 *	Push down the X.25 header
 	 */
-	SOCK_DEBUG(sk, "x25_sendmsg: Building X.25 Header.\n");
+	net_dbg_ratelimited("x25_sendmsg: Building X.25 Header.\n");
 
 	if (msg->msg_flags & MSG_OOB) {
 		if (x25->neighbour->extended) {
@@ -1245,8 +1245,8 @@ static int x25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 			skb->data[0] |= X25_Q_BIT;
 	}
 
-	SOCK_DEBUG(sk, "x25_sendmsg: Built header.\n");
-	SOCK_DEBUG(sk, "x25_sendmsg: Transmitting buffer\n");
+	net_dbg_ratelimited("x25_sendmsg: Built header.\n");
+	net_dbg_ratelimited("x25_sendmsg: Transmitting buffer\n");
 
 	rc = -ENOTCONN;
 	if (sk->sk_state != TCP_ESTABLISHED)
diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c
index 8e1a49b0c0dc..6dadb217e101 100644
--- a/net/x25/x25_facilities.c
+++ b/net/x25/x25_facilities.c
@@ -282,7 +282,7 @@ int x25_negotiate_facilities(struct sk_buff *skb, struct sock *sk,
 	 *	They want reverse charging, we won't accept it.
 	 */
 	if ((theirs.reverse & 0x01 ) && (ours->reverse & 0x01)) {
-		SOCK_DEBUG(sk, "X.25: rejecting reverse charging request\n");
+		net_dbg_ratelimited("X.25: rejecting reverse charging request\n");
 		return -1;
 	}
 
@@ -294,11 +294,11 @@ int x25_negotiate_facilities(struct sk_buff *skb, struct sock *sk,
 		int ours_in  = ours->throughput & 0x0f;
 		int ours_out = ours->throughput & 0xf0;
 		if (!ours_in || theirs_in < ours_in) {
-			SOCK_DEBUG(sk, "X.25: inbound throughput negotiated\n");
+			net_dbg_ratelimited("X.25: inbound throughput negotiated\n");
 			new->throughput = (new->throughput & 0xf0) | theirs_in;
 		}
 		if (!ours_out || theirs_out < ours_out) {
-			SOCK_DEBUG(sk,
+			net_dbg_ratelimited(
 				"X.25: outbound throughput negotiated\n");
 			new->throughput = (new->throughput & 0x0f) | theirs_out;
 		}
@@ -306,22 +306,22 @@ int x25_negotiate_facilities(struct sk_buff *skb, struct sock *sk,
 
 	if (theirs.pacsize_in && theirs.pacsize_out) {
 		if (theirs.pacsize_in < ours->pacsize_in) {
-			SOCK_DEBUG(sk, "X.25: packet size inwards negotiated down\n");
+			net_dbg_ratelimited("X.25: packet size inwards negotiated down\n");
 			new->pacsize_in = theirs.pacsize_in;
 		}
 		if (theirs.pacsize_out < ours->pacsize_out) {
-			SOCK_DEBUG(sk, "X.25: packet size outwards negotiated down\n");
+			net_dbg_ratelimited("X.25: packet size outwards negotiated down\n");
 			new->pacsize_out = theirs.pacsize_out;
 		}
 	}
 
 	if (theirs.winsize_in && theirs.winsize_out) {
 		if (theirs.winsize_in < ours->winsize_in) {
-			SOCK_DEBUG(sk, "X.25: window size inwards negotiated down\n");
+			net_dbg_ratelimited("X.25: window size inwards negotiated down\n");
 			new->winsize_in = theirs.winsize_in;
 		}
 		if (theirs.winsize_out < ours->winsize_out) {
-			SOCK_DEBUG(sk, "X.25: window size outwards negotiated down\n");
+			net_dbg_ratelimited("X.25: window size outwards negotiated down\n");
 			new->winsize_out = theirs.winsize_out;
 		}
 	}
diff --git a/net/x25/x25_out.c b/net/x25/x25_out.c
index dbc0940bf35f..f8922b0e23a4 100644
--- a/net/x25/x25_out.c
+++ b/net/x25/x25_out.c
@@ -72,7 +72,7 @@ int x25_output(struct sock *sk, struct sk_buff *skb)
 					kfree_skb(skb);
 					return sent;
 				}
-				SOCK_DEBUG(sk, "x25_output: fragment alloc"
+				net_dbg_ratelimited("x25_output: fragment alloc"
 					       " failed, err=%d, %d bytes "
 					       "sent\n", err, sent);
 				return err;
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 06cead2b8e34..caa340134b0e 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -148,6 +148,11 @@ static int xdp_umem_account_pages(struct xdp_umem *umem)
 	return 0;
 }
 
+#define XDP_UMEM_FLAGS_VALID ( \
+		XDP_UMEM_UNALIGNED_CHUNK_FLAG | \
+		XDP_UMEM_TX_SW_CSUM | \
+	0)
+
 static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 {
 	bool unaligned_chunks = mr->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG;
@@ -167,7 +172,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 		return -EINVAL;
 	}
 
-	if (mr->flags & ~XDP_UMEM_UNALIGNED_CHUNK_FLAG)
+	if (mr->flags & ~XDP_UMEM_FLAGS_VALID)
 		return -EINVAL;
 
 	if (!unaligned_chunks && !is_power_of_2(chunk_size))
@@ -199,6 +204,9 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	if (headroom >= chunk_size - XDP_PACKET_HEADROOM)
 		return -EINVAL;
 
+	if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8)
+		return -EINVAL;
+
 	umem->size = size;
 	umem->headroom = headroom;
 	umem->chunk_size = chunk_size;
@@ -207,6 +215,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	umem->pgs = NULL;
 	umem->user = NULL;
 	umem->flags = mr->flags;
+	umem->tx_metadata_len = mr->tx_metadata_len;
 
 	INIT_LIST_HEAD(&umem->xsk_dma_list);
 	refcount_set(&umem->users, 1);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index ae9f8cb611f6..9f13aa3353e3 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -571,6 +571,13 @@ static u32 xsk_get_num_desc(struct sk_buff *skb)
 
 static void xsk_destruct_skb(struct sk_buff *skb)
 {
+	struct xsk_tx_metadata_compl *compl = &skb_shinfo(skb)->xsk_meta;
+
+	if (compl->tx_timestamp) {
+		/* sw completion timestamp, not a real one */
+		*compl->tx_timestamp = ktime_get_tai_fast_ns();
+	}
+
 	xsk_cq_submit_locked(xdp_sk(skb->sk), xsk_get_num_desc(skb));
 	sock_wfree(skb);
 }
@@ -655,8 +662,10 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
 static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 				     struct xdp_desc *desc)
 {
+	struct xsk_tx_metadata *meta = NULL;
 	struct net_device *dev = xs->dev;
 	struct sk_buff *skb = xs->skb;
+	bool first_frag = false;
 	int err;
 
 	if (dev->priv_flags & IFF_TX_SKB_NO_LINEAR) {
@@ -687,6 +696,8 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 				kfree_skb(skb);
 				goto free_err;
 			}
+
+			first_frag = true;
 		} else {
 			int nr_frags = skb_shinfo(skb)->nr_frags;
 			struct page *page;
@@ -709,12 +720,45 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 
 			skb_add_rx_frag(skb, nr_frags, page, 0, len, 0);
 		}
+
+		if (first_frag && desc->options & XDP_TX_METADATA) {
+			if (unlikely(xs->pool->tx_metadata_len == 0)) {
+				err = -EINVAL;
+				goto free_err;
+			}
+
+			meta = buffer - xs->pool->tx_metadata_len;
+			if (unlikely(!xsk_buff_valid_tx_metadata(meta))) {
+				err = -EINVAL;
+				goto free_err;
+			}
+
+			if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) {
+				if (unlikely(meta->request.csum_start +
+					     meta->request.csum_offset +
+					     sizeof(__sum16) > len)) {
+					err = -EINVAL;
+					goto free_err;
+				}
+
+				skb->csum_start = hr + meta->request.csum_start;
+				skb->csum_offset = meta->request.csum_offset;
+				skb->ip_summed = CHECKSUM_PARTIAL;
+
+				if (unlikely(xs->pool->tx_sw_csum)) {
+					err = skb_checksum_help(skb);
+					if (err)
+						goto free_err;
+				}
+			}
+		}
 	}
 
 	skb->dev = dev;
 	skb->priority = READ_ONCE(xs->sk.sk_priority);
 	skb->mark = READ_ONCE(xs->sk.sk_mark);
 	skb->destructor = xsk_destruct_skb;
+	xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta);
 	xsk_set_destructor_arg(skb);
 
 	return skb;
@@ -947,7 +991,7 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock,
 
 	rcu_read_lock();
 	if (xsk_check_common(xs))
-		goto skip_tx;
+		goto out;
 
 	pool = xs->pool;
 
@@ -959,12 +1003,11 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock,
 			xsk_generic_xmit(sk);
 	}
 
-skip_tx:
 	if (xs->rx && !xskq_prod_is_empty(xs->rx))
 		mask |= EPOLLIN | EPOLLRDNORM;
 	if (xs->tx && xsk_tx_writeable(xs))
 		mask |= EPOLLOUT | EPOLLWRNORM;
-
+out:
 	rcu_read_unlock();
 	return mask;
 }
@@ -1283,6 +1326,14 @@ struct xdp_umem_reg_v1 {
 	__u32 headroom;
 };
 
+struct xdp_umem_reg_v2 {
+	__u64 addr; /* Start of packet data area */
+	__u64 len; /* Length of packet data area */
+	__u32 chunk_size;
+	__u32 headroom;
+	__u32 flags;
+};
+
 static int xsk_setsockopt(struct socket *sock, int level, int optname,
 			  sockptr_t optval, unsigned int optlen)
 {
@@ -1326,8 +1377,10 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
 
 		if (optlen < sizeof(struct xdp_umem_reg_v1))
 			return -EINVAL;
-		else if (optlen < sizeof(mr))
+		else if (optlen < sizeof(struct xdp_umem_reg_v2))
 			mr_size = sizeof(struct xdp_umem_reg_v1);
+		else if (optlen < sizeof(mr))
+			mr_size = sizeof(struct xdp_umem_reg_v2);
 
 		if (copy_from_sockptr(&mr, optval, mr_size))
 			return -EFAULT;
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 49cb9f9a09be..28711cc44ced 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -85,6 +85,8 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 		XDP_PACKET_HEADROOM;
 	pool->umem = umem;
 	pool->addrs = umem->addrs;
+	pool->tx_metadata_len = umem->tx_metadata_len;
+	pool->tx_sw_csum = umem->flags & XDP_UMEM_TX_SW_CSUM;
 	INIT_LIST_HEAD(&pool->free_list);
 	INIT_LIST_HEAD(&pool->xskb_list);
 	INIT_LIST_HEAD(&pool->xsk_tx_list);
@@ -123,6 +125,18 @@ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq)
 }
 EXPORT_SYMBOL(xp_set_rxq_info);
 
+void xp_fill_cb(struct xsk_buff_pool *pool, struct xsk_cb_desc *desc)
+{
+	u32 i;
+
+	for (i = 0; i < pool->heads_cnt; i++) {
+		struct xdp_buff_xsk *xskb = &pool->heads[i];
+
+		memcpy(xskb->cb + desc->off, desc->src, desc->bytes);
+	}
+}
+EXPORT_SYMBOL(xp_fill_cb);
+
 static void xp_disable_drv_zc(struct xsk_buff_pool *pool)
 {
 	struct netdev_bpf bpf;
diff --git a/net/xdp/xsk_diag.c b/net/xdp/xsk_diag.c
index 22b36c8143cf..9f8955367275 100644
--- a/net/xdp/xsk_diag.c
+++ b/net/xdp/xsk_diag.c
@@ -211,4 +211,5 @@ static void __exit xsk_diag_exit(void)
 module_init(xsk_diag_init);
 module_exit(xsk_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("XDP socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, AF_XDP);
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 13354a1e4280..6f2d1621c992 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -137,21 +137,23 @@ static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr)
 
 static inline bool xp_unused_options_set(u32 options)
 {
-	return options & ~XDP_PKT_CONTD;
+	return options & ~(XDP_PKT_CONTD | XDP_TX_METADATA);
 }
 
 static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
 					    struct xdp_desc *desc)
 {
-	u64 offset = desc->addr & (pool->chunk_size - 1);
+	u64 addr = desc->addr - pool->tx_metadata_len;
+	u64 len = desc->len + pool->tx_metadata_len;
+	u64 offset = addr & (pool->chunk_size - 1);
 
 	if (!desc->len)
 		return false;
 
-	if (offset + desc->len > pool->chunk_size)
+	if (offset + len > pool->chunk_size)
 		return false;
 
-	if (desc->addr >= pool->addrs_cnt)
+	if (addr >= pool->addrs_cnt)
 		return false;
 
 	if (xp_unused_options_set(desc->options))
@@ -162,16 +164,17 @@ static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
 static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool,
 					      struct xdp_desc *desc)
 {
-	u64 addr = xp_unaligned_add_offset_to_addr(desc->addr);
+	u64 addr = xp_unaligned_add_offset_to_addr(desc->addr) - pool->tx_metadata_len;
+	u64 len = desc->len + pool->tx_metadata_len;
 
 	if (!desc->len)
 		return false;
 
-	if (desc->len > pool->chunk_size)
+	if (len > pool->chunk_size)
 		return false;
 
-	if (addr >= pool->addrs_cnt || addr + desc->len > pool->addrs_cnt ||
-	    xp_desc_crosses_non_contig_pg(pool, addr, desc->len))
+	if (addr >= pool->addrs_cnt || addr + len > pool->addrs_cnt ||
+	    xp_desc_crosses_non_contig_pg(pool, addr, len))
 		return false;
 
 	if (xp_unused_options_set(desc->options))
diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile
index cd47f88921f5..547cec77ba03 100644
--- a/net/xfrm/Makefile
+++ b/net/xfrm/Makefile
@@ -21,3 +21,4 @@ obj-$(CONFIG_XFRM_USER_COMPAT) += xfrm_compat.o
 obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o
 obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o
 obj-$(CONFIG_XFRM_ESPINTCP) += espintcp.o
+obj-$(CONFIG_DEBUG_INFO_BTF) += xfrm_state_bpf.o
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index c13dc3ef7910..1b7e75159727 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -4218,6 +4218,8 @@ void __init xfrm_init(void)
 #ifdef CONFIG_XFRM_ESPINTCP
 	espintcp_init();
 #endif
+
+	register_xfrm_state_bpf();
 }
 
 #ifdef CONFIG_AUDITSYSCALL
diff --git a/net/xfrm/xfrm_state_bpf.c b/net/xfrm/xfrm_state_bpf.c
new file mode 100644
index 000000000000..9e20d4a377f7
--- /dev/null
+++ b/net/xfrm/xfrm_state_bpf.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Unstable XFRM state BPF helpers.
+ *
+ * Note that it is allowed to break compatibility for these functions since the
+ * interface they are exposed through to BPF programs is explicitly unstable.
+ */
+
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/btf_ids.h>
+#include <net/xdp.h>
+#include <net/xfrm.h>
+
+/* bpf_xfrm_state_opts - Options for XFRM state lookup helpers
+ *
+ * Members:
+ * @error      - Out parameter, set for any errors encountered
+ *		 Values:
+ *		   -EINVAL - netns_id is less than -1
+ *		   -EINVAL - opts__sz isn't BPF_XFRM_STATE_OPTS_SZ
+ *		   -ENONET - No network namespace found for netns_id
+ *		   -ENOENT - No xfrm_state found
+ * @netns_id	- Specify the network namespace for lookup
+ *		 Values:
+ *		   BPF_F_CURRENT_NETNS (-1)
+ *		     Use namespace associated with ctx
+ *		   [0, S32_MAX]
+ *		     Network Namespace ID
+ * @mark	- XFRM mark to match on
+ * @daddr	- Destination address to match on
+ * @spi		- Security parameter index to match on
+ * @proto	- IP protocol to match on (eg. IPPROTO_ESP)
+ * @family	- Protocol family to match on (AF_INET/AF_INET6)
+ */
+struct bpf_xfrm_state_opts {
+	s32 error;
+	s32 netns_id;
+	u32 mark;
+	xfrm_address_t daddr;
+	__be32 spi;
+	u8 proto;
+	u16 family;
+};
+
+enum {
+	BPF_XFRM_STATE_OPTS_SZ = sizeof(struct bpf_xfrm_state_opts),
+};
+
+__bpf_kfunc_start_defs();
+
+/* bpf_xdp_get_xfrm_state - Get XFRM state
+ *
+ * A `struct xfrm_state *`, if found, must be released with a corresponding
+ * bpf_xdp_xfrm_state_release.
+ *
+ * Parameters:
+ * @ctx	- Pointer to ctx (xdp_md) in XDP program
+ *		    Cannot be NULL
+ * @opts	- Options for lookup (documented above)
+ *		    Cannot be NULL
+ * @opts__sz	- Length of the bpf_xfrm_state_opts structure
+ *		    Must be BPF_XFRM_STATE_OPTS_SZ
+ */
+__bpf_kfunc struct xfrm_state *
+bpf_xdp_get_xfrm_state(struct xdp_md *ctx, struct bpf_xfrm_state_opts *opts, u32 opts__sz)
+{
+	struct xdp_buff *xdp = (struct xdp_buff *)ctx;
+	struct net *net = dev_net(xdp->rxq->dev);
+	struct xfrm_state *x;
+
+	if (!opts || opts__sz < sizeof(opts->error))
+		return NULL;
+
+	if (opts__sz != BPF_XFRM_STATE_OPTS_SZ) {
+		opts->error = -EINVAL;
+		return NULL;
+	}
+
+	if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS)) {
+		opts->error = -EINVAL;
+		return NULL;
+	}
+
+	if (opts->netns_id >= 0) {
+		net = get_net_ns_by_id(net, opts->netns_id);
+		if (unlikely(!net)) {
+			opts->error = -ENONET;
+			return NULL;
+		}
+	}
+
+	x = xfrm_state_lookup(net, opts->mark, &opts->daddr, opts->spi,
+			      opts->proto, opts->family);
+
+	if (opts->netns_id >= 0)
+		put_net(net);
+	if (!x)
+		opts->error = -ENOENT;
+
+	return x;
+}
+
+/* bpf_xdp_xfrm_state_release - Release acquired xfrm_state object
+ *
+ * This must be invoked for referenced PTR_TO_BTF_ID, and the verifier rejects
+ * the program if any references remain in the program in all of the explored
+ * states.
+ *
+ * Parameters:
+ * @x		- Pointer to referenced xfrm_state object, obtained using
+ *		  bpf_xdp_get_xfrm_state.
+ */
+__bpf_kfunc void bpf_xdp_xfrm_state_release(struct xfrm_state *x)
+{
+	xfrm_state_put(x);
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_SET8_START(xfrm_state_kfunc_set)
+BTF_ID_FLAGS(func, bpf_xdp_get_xfrm_state, KF_RET_NULL | KF_ACQUIRE)
+BTF_ID_FLAGS(func, bpf_xdp_xfrm_state_release, KF_RELEASE)
+BTF_SET8_END(xfrm_state_kfunc_set)
+
+static const struct btf_kfunc_id_set xfrm_state_xdp_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set   = &xfrm_state_kfunc_set,
+};
+
+int __init register_xfrm_state_bpf(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP,
+					 &xfrm_state_xdp_kfunc_set);
+}
diff --git a/rust/Makefile b/rust/Makefile
index 543b37f6c77f..9d2a16cc91cb 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -78,6 +78,7 @@ quiet_cmd_rustdoc = RUSTDOC $(if $(rustdoc_host),H, ) $<
 		$(rustc_target_flags) -L$(objtree)/$(obj) \
 		--output $(rustdoc_output) \
 		--crate-name $(subst rustdoc-,,$@) \
+		$(if $(rustdoc_host),,--sysroot=/dev/null) \
 		@$(objtree)/include/generated/rustc_cfg $<
 
 # The `html_logo_url` and `html_favicon_url` forms of the `doc` attribute
@@ -98,7 +99,8 @@ rustdoc: rustdoc-core rustdoc-macros rustdoc-compiler_builtins \
 	$(Q)find $(rustdoc_output) -name '*.html' -type f -print0 | xargs -0 sed -Ei \
 		-e 's:rust-logo-[0-9a-f]+\.svg:logo.svg:g' \
 		-e 's:favicon-[0-9a-f]+\.svg:logo.svg:g' \
-		-e 's:<link rel="alternate icon" type="image/png" href="[/.]+/static\.files/favicon-(16x16|32x32)-[0-9a-f]+\.png">::g'
+		-e 's:<link rel="alternate icon" type="image/png" href="[/.]+/static\.files/favicon-(16x16|32x32)-[0-9a-f]+\.png">::g' \
+		-e 's:<a href="srctree/([^"]+)">:<a href="$(abs_srctree)/\1">:g'
 	$(Q)for f in $(rustdoc_output)/static.files/rustdoc-*.css; do \
 		echo ".logo-container > img { object-fit: contain; }" >> $$f; done
 
@@ -178,6 +180,7 @@ quiet_cmd_rustdoc_test_kernel = RUSTDOC TK $<
 		--extern build_error --extern macros \
 		--extern bindings --extern uapi \
 		--no-run --crate-name kernel -Zunstable-options \
+		--sysroot=/dev/null \
 		--test-builder $(objtree)/scripts/rustdoc_test_builder \
 		$< $(rustdoc_test_kernel_quiet); \
 	$(objtree)/scripts/rustdoc_test_gen
@@ -337,6 +340,8 @@ quiet_cmd_bindgen = BINDGEN $@
 
 $(obj)/bindings/bindings_generated.rs: private bindgen_target_flags = \
     $(shell grep -Ev '^#|^$$' $(srctree)/$(src)/bindgen_parameters)
+$(obj)/bindings/bindings_generated.rs: private bindgen_target_extra = ; \
+    sed -Ei 's/pub const RUST_CONST_HELPER_([a-zA-Z0-9_]*)/pub const \1/g' $@
 $(obj)/bindings/bindings_generated.rs: $(src)/bindings/bindings_helper.h \
     $(src)/bindgen_parameters FORCE
 	$(call if_changed_dep,bindgen)
@@ -402,6 +407,7 @@ quiet_cmd_rustc_library = $(if $(skip_clippy),RUSTC,$(RUSTC_OR_CLIPPY_QUIET)) L
 		--emit=metadata=$(dir $@)$(patsubst %.o,lib%.rmeta,$(notdir $@)) \
 		--crate-type rlib -L$(objtree)/$(obj) \
 		--crate-name $(patsubst %.o,%,$(notdir $@)) $< \
+		--sysroot=/dev/null \
 	$(if $(rustc_objcopy),;$(OBJCOPY) $(rustc_objcopy) $@)
 
 rust-analyzer:
diff --git a/rust/alloc/alloc.rs b/rust/alloc/alloc.rs
index 8cb4a31cf6e5..150e13750ff7 100644
--- a/rust/alloc/alloc.rs
+++ b/rust/alloc/alloc.rs
@@ -345,18 +345,31 @@ extern "Rust" {
     fn __rust_alloc_error_handler(size: usize, align: usize) -> !;
 }
 
-/// Abort on memory allocation error or failure.
+/// Signal a memory allocation error.
 ///
-/// Callers of memory allocation APIs wishing to abort computation
+/// Callers of memory allocation APIs wishing to cease execution
 /// in response to an allocation error are encouraged to call this function,
-/// rather than directly invoking `panic!` or similar.
+/// rather than directly invoking [`panic!`] or similar.
 ///
-/// The default behavior of this function is to print a message to standard error
-/// and abort the process.
-/// It can be replaced with [`set_alloc_error_hook`] and [`take_alloc_error_hook`].
+/// This function is guaranteed to diverge (not return normally with a value), but depending on
+/// global configuration, it may either panic (resulting in unwinding or aborting as per
+/// configuration for all panics), or abort the process (with no unwinding).
+///
+/// The default behavior is:
+///
+///  * If the binary links against `std` (typically the case), then
+///   print a message to standard error and abort the process.
+///   This behavior can be replaced with [`set_alloc_error_hook`] and [`take_alloc_error_hook`].
+///   Future versions of Rust may panic by default instead.
+///
+/// * If the binary does not link against `std` (all of its crates are marked
+///   [`#![no_std]`][no_std]), then call [`panic!`] with a message.
+///   [The panic handler] applies as to any panic.
 ///
 /// [`set_alloc_error_hook`]: ../../std/alloc/fn.set_alloc_error_hook.html
 /// [`take_alloc_error_hook`]: ../../std/alloc/fn.take_alloc_error_hook.html
+/// [The panic handler]: https://doc.rust-lang.org/reference/runtime.html#the-panic_handler-attribute
+/// [no_std]: https://doc.rust-lang.org/reference/names/preludes.html#the-no_std-attribute
 #[stable(feature = "global_alloc", since = "1.28.0")]
 #[rustc_const_unstable(feature = "const_alloc_error", issue = "92523")]
 #[cfg(all(not(no_global_oom_handling), not(test)))]
@@ -397,9 +410,10 @@ pub mod __alloc_error_handler {
         if unsafe { __rust_alloc_error_handler_should_panic != 0 } {
             panic!("memory allocation of {size} bytes failed")
         } else {
-            core::panicking::panic_nounwind_fmt(format_args!(
-                "memory allocation of {size} bytes failed"
-            ))
+            core::panicking::panic_nounwind_fmt(
+                format_args!("memory allocation of {size} bytes failed"),
+                /* force_no_backtrace */ false,
+            )
         }
     }
 }
diff --git a/rust/alloc/lib.rs b/rust/alloc/lib.rs
index 73b9ffd845d9..9c7ea73da108 100644
--- a/rust/alloc/lib.rs
+++ b/rust/alloc/lib.rs
@@ -90,8 +90,8 @@
 #![warn(missing_docs)]
 #![allow(explicit_outlives_requirements)]
 #![warn(multiple_supertrait_upcastable)]
-#![cfg_attr(not(bootstrap), allow(internal_features))]
-#![cfg_attr(not(bootstrap), allow(rustdoc::redundant_explicit_links))]
+#![allow(internal_features)]
+#![allow(rustdoc::redundant_explicit_links)]
 //
 // Library features:
 // tidy-alphabetical-start
@@ -122,6 +122,7 @@
 #![feature(const_waker)]
 #![feature(core_intrinsics)]
 #![feature(core_panic)]
+#![feature(deprecated_suggestion)]
 #![feature(dispatch_from_dyn)]
 #![feature(error_generic_member_access)]
 #![feature(error_in_core)]
@@ -145,7 +146,6 @@
 #![feature(ptr_metadata)]
 #![feature(ptr_sub_ptr)]
 #![feature(receiver_trait)]
-#![feature(saturating_int_impl)]
 #![feature(set_ptr_value)]
 #![feature(sized_type_properties)]
 #![feature(slice_from_ptr_range)]
diff --git a/rust/alloc/slice.rs b/rust/alloc/slice.rs
index 6ac463bd3edc..1181836da5f4 100644
--- a/rust/alloc/slice.rs
+++ b/rust/alloc/slice.rs
@@ -594,7 +594,7 @@ impl<T> [T] {
     /// ```
     #[rustc_allow_incoherent_impl]
     #[stable(feature = "rust1", since = "1.0.0")]
-    #[deprecated(since = "1.3.0", note = "renamed to join")]
+    #[deprecated(since = "1.3.0", note = "renamed to join", suggestion = "join")]
     pub fn connect<Separator>(&self, sep: Separator) -> <Self as Join<Separator>>::Output
     where
         Self: Join<Separator>,
diff --git a/rust/alloc/vec/mod.rs b/rust/alloc/vec/mod.rs
index 209a88cfe598..41ca71805ef0 100644
--- a/rust/alloc/vec/mod.rs
+++ b/rust/alloc/vec/mod.rs
@@ -1228,8 +1228,8 @@ impl<T, A: Allocator> Vec<T, A> {
     /// Shortens the vector, keeping the first `len` elements and dropping
     /// the rest.
     ///
-    /// If `len` is greater than the vector's current length, this has no
-    /// effect.
+    /// If `len` is greater or equal to the vector's current length, this has
+    /// no effect.
     ///
     /// The [`drain`] method can emulate `truncate`, but causes the excess
     /// elements to be returned instead of dropped.
@@ -1336,6 +1336,15 @@ impl<T, A: Allocator> Vec<T, A> {
     /// is never written to (except inside an `UnsafeCell`) using this pointer or any pointer
     /// derived from it. If you need to mutate the contents of the slice, use [`as_mut_ptr`].
     ///
+    /// This method guarantees that for the purpose of the aliasing model, this method
+    /// does not materialize a reference to the underlying slice, and thus the returned pointer
+    /// will remain valid when mixed with other calls to [`as_ptr`] and [`as_mut_ptr`].
+    /// Note that calling other methods that materialize mutable references to the slice,
+    /// or mutable references to specific elements you are planning on accessing through this pointer,
+    /// as well as writing to those elements, may still invalidate this pointer.
+    /// See the second example below for how this guarantee can be used.
+    ///
+    ///
     /// # Examples
     ///
     /// ```
@@ -1349,8 +1358,25 @@ impl<T, A: Allocator> Vec<T, A> {
     /// }
     /// ```
     ///
+    /// Due to the aliasing guarantee, the following code is legal:
+    ///
+    /// ```rust
+    /// unsafe {
+    ///     let mut v = vec![0, 1, 2];
+    ///     let ptr1 = v.as_ptr();
+    ///     let _ = ptr1.read();
+    ///     let ptr2 = v.as_mut_ptr().offset(2);
+    ///     ptr2.write(2);
+    ///     // Notably, the write to `ptr2` did *not* invalidate `ptr1`
+    ///     // because it mutated a different element:
+    ///     let _ = ptr1.read();
+    /// }
+    /// ```
+    ///
     /// [`as_mut_ptr`]: Vec::as_mut_ptr
+    /// [`as_ptr`]: Vec::as_ptr
     #[stable(feature = "vec_as_ptr", since = "1.37.0")]
+    #[cfg_attr(not(bootstrap), rustc_never_returns_null_ptr)]
     #[inline]
     pub fn as_ptr(&self) -> *const T {
         // We shadow the slice method of the same name to avoid going through
@@ -1366,6 +1392,15 @@ impl<T, A: Allocator> Vec<T, A> {
     /// Modifying the vector may cause its buffer to be reallocated,
     /// which would also make any pointers to it invalid.
     ///
+    /// This method guarantees that for the purpose of the aliasing model, this method
+    /// does not materialize a reference to the underlying slice, and thus the returned pointer
+    /// will remain valid when mixed with other calls to [`as_ptr`] and [`as_mut_ptr`].
+    /// Note that calling other methods that materialize references to the slice,
+    /// or references to specific elements you are planning on accessing through this pointer,
+    /// may still invalidate this pointer.
+    /// See the second example below for how this guarantee can be used.
+    ///
+    ///
     /// # Examples
     ///
     /// ```
@@ -1383,7 +1418,25 @@ impl<T, A: Allocator> Vec<T, A> {
     /// }
     /// assert_eq!(&*x, &[0, 1, 2, 3]);
     /// ```
+    ///
+    /// Due to the aliasing guarantee, the following code is legal:
+    ///
+    /// ```rust
+    /// unsafe {
+    ///     let mut v = vec![0];
+    ///     let ptr1 = v.as_mut_ptr();
+    ///     ptr1.write(1);
+    ///     let ptr2 = v.as_mut_ptr();
+    ///     ptr2.write(2);
+    ///     // Notably, the write to `ptr2` did *not* invalidate `ptr1`:
+    ///     ptr1.write(3);
+    /// }
+    /// ```
+    ///
+    /// [`as_mut_ptr`]: Vec::as_mut_ptr
+    /// [`as_ptr`]: Vec::as_ptr
     #[stable(feature = "vec_as_ptr", since = "1.37.0")]
+    #[cfg_attr(not(bootstrap), rustc_never_returns_null_ptr)]
     #[inline]
     pub fn as_mut_ptr(&mut self) -> *mut T {
         // We shadow the slice method of the same name to avoid going through
@@ -3404,6 +3457,36 @@ impl<T: Clone> From<&mut [T]> for Vec<T> {
 }
 
 #[cfg(not(no_global_oom_handling))]
+#[stable(feature = "vec_from_array_ref", since = "1.74.0")]
+impl<T: Clone, const N: usize> From<&[T; N]> for Vec<T> {
+    /// Allocate a `Vec<T>` and fill it by cloning `s`'s items.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// assert_eq!(Vec::from(&[1, 2, 3]), vec![1, 2, 3]);
+    /// ```
+    fn from(s: &[T; N]) -> Vec<T> {
+        Self::from(s.as_slice())
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "vec_from_array_ref", since = "1.74.0")]
+impl<T: Clone, const N: usize> From<&mut [T; N]> for Vec<T> {
+    /// Allocate a `Vec<T>` and fill it by cloning `s`'s items.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// assert_eq!(Vec::from(&mut [1, 2, 3]), vec![1, 2, 3]);
+    /// ```
+    fn from(s: &mut [T; N]) -> Vec<T> {
+        Self::from(s.as_mut_slice())
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
 #[stable(feature = "vec_from_array", since = "1.44.0")]
 impl<T, const N: usize> From<[T; N]> for Vec<T> {
     /// Allocate a `Vec<T>` and move `s`'s items into it.
diff --git a/rust/bindgen_parameters b/rust/bindgen_parameters
index 552d9a85925b..a721d466bee4 100644
--- a/rust/bindgen_parameters
+++ b/rust/bindgen_parameters
@@ -20,3 +20,7 @@
 
 # `seccomp`'s comment gets understood as a doctest
 --no-doc-comments
+
+# These functions use the `__preserve_most` calling convention, which neither bindgen
+# nor Rust currently understand, and which Clang currently declares to be unstable.
+--blocklist-function __list_.*_report
diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h
index 85f013ed4ca4..c0cb4b05b918 100644
--- a/rust/bindings/bindings_helper.h
+++ b/rust/bindings/bindings_helper.h
@@ -8,6 +8,9 @@
 
 #include <kunit/test.h>
 #include <linux/errname.h>
+#include <linux/ethtool.h>
+#include <linux/mdio.h>
+#include <linux/phy.h>
 #include <linux/slab.h>
 #include <linux/refcount.h>
 #include <linux/wait.h>
@@ -15,6 +18,6 @@
 #include <linux/workqueue.h>
 
 /* `bindgen` gets confused at certain things. */
-const size_t BINDINGS_ARCH_SLAB_MINALIGN = ARCH_SLAB_MINALIGN;
-const gfp_t BINDINGS_GFP_KERNEL = GFP_KERNEL;
-const gfp_t BINDINGS___GFP_ZERO = __GFP_ZERO;
+const size_t RUST_CONST_HELPER_ARCH_SLAB_MINALIGN = ARCH_SLAB_MINALIGN;
+const gfp_t RUST_CONST_HELPER_GFP_KERNEL = GFP_KERNEL;
+const gfp_t RUST_CONST_HELPER___GFP_ZERO = __GFP_ZERO;
diff --git a/rust/bindings/lib.rs b/rust/bindings/lib.rs
index 9bcbea04dac3..40ddaee50d8b 100644
--- a/rust/bindings/lib.rs
+++ b/rust/bindings/lib.rs
@@ -48,6 +48,3 @@ mod bindings_helper {
 }
 
 pub use bindings_raw::*;
-
-pub const GFP_KERNEL: gfp_t = BINDINGS_GFP_KERNEL;
-pub const __GFP_ZERO: gfp_t = BINDINGS___GFP_ZERO;
diff --git a/rust/exports.c b/rust/exports.c
index 83e2a7070cae..3803c21d1403 100644
--- a/rust/exports.c
+++ b/rust/exports.c
@@ -11,7 +11,7 @@
  * accidentally exposed.
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 
 #define EXPORT_SYMBOL_RUST_GPL(sym) extern int sym; EXPORT_SYMBOL_GPL(sym)
 
diff --git a/rust/kernel/allocator.rs b/rust/kernel/allocator.rs
index a8f3d5be1af1..4b057e837358 100644
--- a/rust/kernel/allocator.rs
+++ b/rust/kernel/allocator.rs
@@ -21,7 +21,7 @@ unsafe fn krealloc_aligned(ptr: *mut u8, new_layout: Layout, flags: bindings::gf
 
     let mut size = layout.size();
 
-    if layout.align() > bindings::BINDINGS_ARCH_SLAB_MINALIGN {
+    if layout.align() > bindings::ARCH_SLAB_MINALIGN {
         // The alignment requirement exceeds the slab guarantee, thus try to enlarge the size
         // to use the "power-of-two" size/alignment guarantee (see comments in `kmalloc()` for
         // more information).
diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs
index 032b64543953..4f0c1edd63b7 100644
--- a/rust/kernel/error.rs
+++ b/rust/kernel/error.rs
@@ -2,7 +2,7 @@
 
 //! Kernel errors.
 //!
-//! C header: [`include/uapi/asm-generic/errno-base.h`](../../../include/uapi/asm-generic/errno-base.h)
+//! C header: [`include/uapi/asm-generic/errno-base.h`](srctree/include/uapi/asm-generic/errno-base.h)
 
 use crate::str::CStr;
 
@@ -335,3 +335,7 @@ where
         Err(e) => T::from(e.to_errno() as i16),
     }
 }
+
+/// Error message for calling a default function of a [`#[vtable]`](macros::vtable) trait.
+pub const VTABLE_DEFAULT_ERROR: &str =
+    "This function must not be called, see the #[vtable] documentation.";
diff --git a/rust/kernel/ioctl.rs b/rust/kernel/ioctl.rs
index c49e1a8d3fd0..f1d42ab69972 100644
--- a/rust/kernel/ioctl.rs
+++ b/rust/kernel/ioctl.rs
@@ -2,7 +2,7 @@
 
 //! ioctl() number definitions
 //!
-//! C header: [`include/asm-generic/ioctl.h`](../../../../include/asm-generic/ioctl.h)
+//! C header: [`include/asm-generic/ioctl.h`](srctree/include/asm-generic/ioctl.h)
 
 #![allow(non_snake_case)]
 
diff --git a/rust/kernel/kunit.rs b/rust/kernel/kunit.rs
index 722655b2d62d..0ba77276ae7e 100644
--- a/rust/kernel/kunit.rs
+++ b/rust/kernel/kunit.rs
@@ -2,7 +2,7 @@
 
 //! KUnit-based macros for Rust unit tests.
 //!
-//! C header: [`include/kunit/test.h`](../../../../../include/kunit/test.h)
+//! C header: [`include/kunit/test.h`](srctree/include/kunit/test.h)
 //!
 //! Reference: <https://docs.kernel.org/dev-tools/kunit/index.html>
 
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index e6aff80b521f..7ac39874aeac 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -14,6 +14,7 @@
 #![no_std]
 #![feature(allocator_api)]
 #![feature(coerce_unsized)]
+#![feature(const_maybe_uninit_zeroed)]
 #![feature(dispatch_from_dyn)]
 #![feature(new_uninit)]
 #![feature(offset_of)]
@@ -38,6 +39,8 @@ pub mod init;
 pub mod ioctl;
 #[cfg(CONFIG_KUNIT)]
 pub mod kunit;
+#[cfg(CONFIG_NET)]
+pub mod net;
 pub mod prelude;
 pub mod print;
 mod static_assert;
diff --git a/rust/kernel/net.rs b/rust/kernel/net.rs
new file mode 100644
index 000000000000..fe415cb369d3
--- /dev/null
+++ b/rust/kernel/net.rs
@@ -0,0 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Networking.
+
+#[cfg(CONFIG_RUST_PHYLIB_ABSTRACTIONS)]
+pub mod phy;
diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs
new file mode 100644
index 000000000000..e457b3c7cb2f
--- /dev/null
+++ b/rust/kernel/net/phy.rs
@@ -0,0 +1,901 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2023 FUJITA Tomonori <fujita.tomonori@gmail.com>
+
+//! Network PHY device.
+//!
+//! C headers: [`include/linux/phy.h`](../../../../../../../include/linux/phy.h).
+
+use crate::{bindings, error::*, prelude::*, str::CStr, types::Opaque};
+
+use core::marker::PhantomData;
+
+/// PHY state machine states.
+///
+/// Corresponds to the kernel's [`enum phy_state`].
+///
+/// Some of PHY drivers access to the state of PHY's software state machine.
+///
+/// [`enum phy_state`]: ../../../../../../../include/linux/phy.h
+#[derive(PartialEq, Eq)]
+pub enum DeviceState {
+    /// PHY device and driver are not ready for anything.
+    Down,
+    /// PHY is ready to send and receive packets.
+    Ready,
+    /// PHY is up, but no polling or interrupts are done.
+    Halted,
+    /// PHY is up, but is in an error state.
+    Error,
+    /// PHY and attached device are ready to do work.
+    Up,
+    /// PHY is currently running.
+    Running,
+    /// PHY is up, but not currently plugged in.
+    NoLink,
+    /// PHY is performing a cable test.
+    CableTest,
+}
+
+/// A mode of Ethernet communication.
+///
+/// PHY drivers get duplex information from hardware and update the current state.
+pub enum DuplexMode {
+    /// PHY is in full-duplex mode.
+    Full,
+    /// PHY is in half-duplex mode.
+    Half,
+    /// PHY is in unknown duplex mode.
+    Unknown,
+}
+
+/// An instance of a PHY device.
+///
+/// Wraps the kernel's [`struct phy_device`].
+///
+/// A [`Device`] instance is created when a callback in [`Driver`] is executed. A PHY driver
+/// executes [`Driver`]'s methods during the callback.
+///
+/// # Invariants
+///
+/// Referencing a `phy_device` using this struct asserts that you are in
+/// a context where all methods defined on this struct are safe to call.
+///
+/// [`struct phy_device`]: ../../../../../../../include/linux/phy.h
+// During the calls to most functions in [`Driver`], the C side (`PHYLIB`) holds a lock that is
+// unique for every instance of [`Device`]. `PHYLIB` uses a different serialization technique for
+// [`Driver::resume`] and [`Driver::suspend`]: `PHYLIB` updates `phy_device`'s state with
+// the lock held, thus guaranteeing that [`Driver::resume`] has exclusive access to the instance.
+// [`Driver::resume`] and [`Driver::suspend`] also are called where only one thread can access
+// to the instance.
+#[repr(transparent)]
+pub struct Device(Opaque<bindings::phy_device>);
+
+impl Device {
+    /// Creates a new [`Device`] instance from a raw pointer.
+    ///
+    /// # Safety
+    ///
+    /// For the duration of 'a, the pointer must point at a valid `phy_device`,
+    /// and the caller must be in a context where all methods defined on this struct
+    /// are safe to call.
+    unsafe fn from_raw<'a>(ptr: *mut bindings::phy_device) -> &'a mut Self {
+        // CAST: `Self` is a `repr(transparent)` wrapper around `bindings::phy_device`.
+        let ptr = ptr.cast::<Self>();
+        // SAFETY: by the function requirements the pointer is valid and we have unique access for
+        // the duration of `'a`.
+        unsafe { &mut *ptr }
+    }
+
+    /// Gets the id of the PHY.
+    pub fn phy_id(&self) -> u32 {
+        let phydev = self.0.get();
+        // SAFETY: The struct invariant ensures that we may access
+        // this field without additional synchronization.
+        unsafe { (*phydev).phy_id }
+    }
+
+    /// Gets the state of PHY state machine states.
+    pub fn state(&self) -> DeviceState {
+        let phydev = self.0.get();
+        // SAFETY: The struct invariant ensures that we may access
+        // this field without additional synchronization.
+        let state = unsafe { (*phydev).state };
+        // TODO: this conversion code will be replaced with automatically generated code by bindgen
+        // when it becomes possible.
+        match state {
+            bindings::phy_state_PHY_DOWN => DeviceState::Down,
+            bindings::phy_state_PHY_READY => DeviceState::Ready,
+            bindings::phy_state_PHY_HALTED => DeviceState::Halted,
+            bindings::phy_state_PHY_ERROR => DeviceState::Error,
+            bindings::phy_state_PHY_UP => DeviceState::Up,
+            bindings::phy_state_PHY_RUNNING => DeviceState::Running,
+            bindings::phy_state_PHY_NOLINK => DeviceState::NoLink,
+            bindings::phy_state_PHY_CABLETEST => DeviceState::CableTest,
+            _ => DeviceState::Error,
+        }
+    }
+
+    /// Gets the current link state.
+    ///
+    /// It returns true if the link is up.
+    pub fn is_link_up(&self) -> bool {
+        const LINK_IS_UP: u64 = 1;
+        // TODO: the code to access to the bit field will be replaced with automatically
+        // generated code by bindgen when it becomes possible.
+        // SAFETY: The struct invariant ensures that we may access
+        // this field without additional synchronization.
+        let bit_field = unsafe { &(*self.0.get())._bitfield_1 };
+        bit_field.get(14, 1) == LINK_IS_UP
+    }
+
+    /// Gets the current auto-negotiation configuration.
+    ///
+    /// It returns true if auto-negotiation is enabled.
+    pub fn is_autoneg_enabled(&self) -> bool {
+        // TODO: the code to access to the bit field will be replaced with automatically
+        // generated code by bindgen when it becomes possible.
+        // SAFETY: The struct invariant ensures that we may access
+        // this field without additional synchronization.
+        let bit_field = unsafe { &(*self.0.get())._bitfield_1 };
+        bit_field.get(13, 1) == bindings::AUTONEG_ENABLE as u64
+    }
+
+    /// Gets the current auto-negotiation state.
+    ///
+    /// It returns true if auto-negotiation is completed.
+    pub fn is_autoneg_completed(&self) -> bool {
+        const AUTONEG_COMPLETED: u64 = 1;
+        // TODO: the code to access to the bit field will be replaced with automatically
+        // generated code by bindgen when it becomes possible.
+        // SAFETY: The struct invariant ensures that we may access
+        // this field without additional synchronization.
+        let bit_field = unsafe { &(*self.0.get())._bitfield_1 };
+        bit_field.get(15, 1) == AUTONEG_COMPLETED
+    }
+
+    /// Sets the speed of the PHY.
+    pub fn set_speed(&mut self, speed: u32) {
+        let phydev = self.0.get();
+        // SAFETY: The struct invariant ensures that we may access
+        // this field without additional synchronization.
+        unsafe { (*phydev).speed = speed as i32 };
+    }
+
+    /// Sets duplex mode.
+    pub fn set_duplex(&mut self, mode: DuplexMode) {
+        let phydev = self.0.get();
+        let v = match mode {
+            DuplexMode::Full => bindings::DUPLEX_FULL as i32,
+            DuplexMode::Half => bindings::DUPLEX_HALF as i32,
+            DuplexMode::Unknown => bindings::DUPLEX_UNKNOWN as i32,
+        };
+        // SAFETY: The struct invariant ensures that we may access
+        // this field without additional synchronization.
+        unsafe { (*phydev).duplex = v };
+    }
+
+    /// Reads a given C22 PHY register.
+    // This function reads a hardware register and updates the stats so takes `&mut self`.
+    pub fn read(&mut self, regnum: u16) -> Result<u16> {
+        let phydev = self.0.get();
+        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Self`.
+        // So it's just an FFI call, open code of `phy_read()` with a valid `phy_device` pointer
+        // `phydev`.
+        let ret = unsafe {
+            bindings::mdiobus_read((*phydev).mdio.bus, (*phydev).mdio.addr, regnum.into())
+        };
+        if ret < 0 {
+            Err(Error::from_errno(ret))
+        } else {
+            Ok(ret as u16)
+        }
+    }
+
+    /// Writes a given C22 PHY register.
+    pub fn write(&mut self, regnum: u16, val: u16) -> Result {
+        let phydev = self.0.get();
+        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Self`.
+        // So it's just an FFI call, open code of `phy_write()` with a valid `phy_device` pointer
+        // `phydev`.
+        to_result(unsafe {
+            bindings::mdiobus_write((*phydev).mdio.bus, (*phydev).mdio.addr, regnum.into(), val)
+        })
+    }
+
+    /// Reads a paged register.
+    pub fn read_paged(&mut self, page: u16, regnum: u16) -> Result<u16> {
+        let phydev = self.0.get();
+        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Self`.
+        // So it's just an FFI call.
+        let ret = unsafe { bindings::phy_read_paged(phydev, page.into(), regnum.into()) };
+        if ret < 0 {
+            Err(Error::from_errno(ret))
+        } else {
+            Ok(ret as u16)
+        }
+    }
+
+    /// Resolves the advertisements into PHY settings.
+    pub fn resolve_aneg_linkmode(&mut self) {
+        let phydev = self.0.get();
+        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Self`.
+        // So it's just an FFI call.
+        unsafe { bindings::phy_resolve_aneg_linkmode(phydev) };
+    }
+
+    /// Executes software reset the PHY via `BMCR_RESET` bit.
+    pub fn genphy_soft_reset(&mut self) -> Result {
+        let phydev = self.0.get();
+        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Self`.
+        // So it's just an FFI call.
+        to_result(unsafe { bindings::genphy_soft_reset(phydev) })
+    }
+
+    /// Initializes the PHY.
+    pub fn init_hw(&mut self) -> Result {
+        let phydev = self.0.get();
+        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Self`.
+        // So it's just an FFI call.
+        to_result(unsafe { bindings::phy_init_hw(phydev) })
+    }
+
+    /// Starts auto-negotiation.
+    pub fn start_aneg(&mut self) -> Result {
+        let phydev = self.0.get();
+        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Self`.
+        // So it's just an FFI call.
+        to_result(unsafe { bindings::_phy_start_aneg(phydev) })
+    }
+
+    /// Resumes the PHY via `BMCR_PDOWN` bit.
+    pub fn genphy_resume(&mut self) -> Result {
+        let phydev = self.0.get();
+        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Self`.
+        // So it's just an FFI call.
+        to_result(unsafe { bindings::genphy_resume(phydev) })
+    }
+
+    /// Suspends the PHY via `BMCR_PDOWN` bit.
+    pub fn genphy_suspend(&mut self) -> Result {
+        let phydev = self.0.get();
+        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Self`.
+        // So it's just an FFI call.
+        to_result(unsafe { bindings::genphy_suspend(phydev) })
+    }
+
+    /// Checks the link status and updates current link state.
+    pub fn genphy_read_status(&mut self) -> Result<u16> {
+        let phydev = self.0.get();
+        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Self`.
+        // So it's just an FFI call.
+        let ret = unsafe { bindings::genphy_read_status(phydev) };
+        if ret < 0 {
+            Err(Error::from_errno(ret))
+        } else {
+            Ok(ret as u16)
+        }
+    }
+
+    /// Updates the link status.
+    pub fn genphy_update_link(&mut self) -> Result {
+        let phydev = self.0.get();
+        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Self`.
+        // So it's just an FFI call.
+        to_result(unsafe { bindings::genphy_update_link(phydev) })
+    }
+
+    /// Reads link partner ability.
+    pub fn genphy_read_lpa(&mut self) -> Result {
+        let phydev = self.0.get();
+        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Self`.
+        // So it's just an FFI call.
+        to_result(unsafe { bindings::genphy_read_lpa(phydev) })
+    }
+
+    /// Reads PHY abilities.
+    pub fn genphy_read_abilities(&mut self) -> Result {
+        let phydev = self.0.get();
+        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Self`.
+        // So it's just an FFI call.
+        to_result(unsafe { bindings::genphy_read_abilities(phydev) })
+    }
+}
+
+/// Defines certain other features this PHY supports (like interrupts).
+///
+/// These flag values are used in [`Driver::FLAGS`].
+pub mod flags {
+    /// PHY is internal.
+    pub const IS_INTERNAL: u32 = bindings::PHY_IS_INTERNAL;
+    /// PHY needs to be reset after the refclk is enabled.
+    pub const RST_AFTER_CLK_EN: u32 = bindings::PHY_RST_AFTER_CLK_EN;
+    /// Polling is used to detect PHY status changes.
+    pub const POLL_CABLE_TEST: u32 = bindings::PHY_POLL_CABLE_TEST;
+    /// Don't suspend.
+    pub const ALWAYS_CALL_SUSPEND: u32 = bindings::PHY_ALWAYS_CALL_SUSPEND;
+}
+
+/// An adapter for the registration of a PHY driver.
+struct Adapter<T: Driver> {
+    _p: PhantomData<T>,
+}
+
+impl<T: Driver> Adapter<T> {
+    /// # Safety
+    ///
+    /// `phydev` must be passed by the corresponding callback in `phy_driver`.
+    unsafe extern "C" fn soft_reset_callback(
+        phydev: *mut bindings::phy_device,
+    ) -> core::ffi::c_int {
+        from_result(|| {
+            // SAFETY: This callback is called only in contexts
+            // where we hold `phy_device->lock`, so the accessors on
+            // `Device` are okay to call.
+            let dev = unsafe { Device::from_raw(phydev) };
+            T::soft_reset(dev)?;
+            Ok(0)
+        })
+    }
+
+    /// # Safety
+    ///
+    /// `phydev` must be passed by the corresponding callback in `phy_driver`.
+    unsafe extern "C" fn get_features_callback(
+        phydev: *mut bindings::phy_device,
+    ) -> core::ffi::c_int {
+        from_result(|| {
+            // SAFETY: This callback is called only in contexts
+            // where we hold `phy_device->lock`, so the accessors on
+            // `Device` are okay to call.
+            let dev = unsafe { Device::from_raw(phydev) };
+            T::get_features(dev)?;
+            Ok(0)
+        })
+    }
+
+    /// # Safety
+    ///
+    /// `phydev` must be passed by the corresponding callback in `phy_driver`.
+    unsafe extern "C" fn suspend_callback(phydev: *mut bindings::phy_device) -> core::ffi::c_int {
+        from_result(|| {
+            // SAFETY: The C core code ensures that the accessors on
+            // `Device` are okay to call even though `phy_device->lock`
+            // might not be held.
+            let dev = unsafe { Device::from_raw(phydev) };
+            T::suspend(dev)?;
+            Ok(0)
+        })
+    }
+
+    /// # Safety
+    ///
+    /// `phydev` must be passed by the corresponding callback in `phy_driver`.
+    unsafe extern "C" fn resume_callback(phydev: *mut bindings::phy_device) -> core::ffi::c_int {
+        from_result(|| {
+            // SAFETY: The C core code ensures that the accessors on
+            // `Device` are okay to call even though `phy_device->lock`
+            // might not be held.
+            let dev = unsafe { Device::from_raw(phydev) };
+            T::resume(dev)?;
+            Ok(0)
+        })
+    }
+
+    /// # Safety
+    ///
+    /// `phydev` must be passed by the corresponding callback in `phy_driver`.
+    unsafe extern "C" fn config_aneg_callback(
+        phydev: *mut bindings::phy_device,
+    ) -> core::ffi::c_int {
+        from_result(|| {
+            // SAFETY: This callback is called only in contexts
+            // where we hold `phy_device->lock`, so the accessors on
+            // `Device` are okay to call.
+            let dev = unsafe { Device::from_raw(phydev) };
+            T::config_aneg(dev)?;
+            Ok(0)
+        })
+    }
+
+    /// # Safety
+    ///
+    /// `phydev` must be passed by the corresponding callback in `phy_driver`.
+    unsafe extern "C" fn read_status_callback(
+        phydev: *mut bindings::phy_device,
+    ) -> core::ffi::c_int {
+        from_result(|| {
+            // SAFETY: This callback is called only in contexts
+            // where we hold `phy_device->lock`, so the accessors on
+            // `Device` are okay to call.
+            let dev = unsafe { Device::from_raw(phydev) };
+            T::read_status(dev)?;
+            Ok(0)
+        })
+    }
+
+    /// # Safety
+    ///
+    /// `phydev` must be passed by the corresponding callback in `phy_driver`.
+    unsafe extern "C" fn match_phy_device_callback(
+        phydev: *mut bindings::phy_device,
+    ) -> core::ffi::c_int {
+        // SAFETY: This callback is called only in contexts
+        // where we hold `phy_device->lock`, so the accessors on
+        // `Device` are okay to call.
+        let dev = unsafe { Device::from_raw(phydev) };
+        T::match_phy_device(dev) as i32
+    }
+
+    /// # Safety
+    ///
+    /// `phydev` must be passed by the corresponding callback in `phy_driver`.
+    unsafe extern "C" fn read_mmd_callback(
+        phydev: *mut bindings::phy_device,
+        devnum: i32,
+        regnum: u16,
+    ) -> i32 {
+        from_result(|| {
+            // SAFETY: This callback is called only in contexts
+            // where we hold `phy_device->lock`, so the accessors on
+            // `Device` are okay to call.
+            let dev = unsafe { Device::from_raw(phydev) };
+            // CAST: the C side verifies devnum < 32.
+            let ret = T::read_mmd(dev, devnum as u8, regnum)?;
+            Ok(ret.into())
+        })
+    }
+
+    /// # Safety
+    ///
+    /// `phydev` must be passed by the corresponding callback in `phy_driver`.
+    unsafe extern "C" fn write_mmd_callback(
+        phydev: *mut bindings::phy_device,
+        devnum: i32,
+        regnum: u16,
+        val: u16,
+    ) -> i32 {
+        from_result(|| {
+            // SAFETY: This callback is called only in contexts
+            // where we hold `phy_device->lock`, so the accessors on
+            // `Device` are okay to call.
+            let dev = unsafe { Device::from_raw(phydev) };
+            T::write_mmd(dev, devnum as u8, regnum, val)?;
+            Ok(0)
+        })
+    }
+
+    /// # Safety
+    ///
+    /// `phydev` must be passed by the corresponding callback in `phy_driver`.
+    unsafe extern "C" fn link_change_notify_callback(phydev: *mut bindings::phy_device) {
+        // SAFETY: This callback is called only in contexts
+        // where we hold `phy_device->lock`, so the accessors on
+        // `Device` are okay to call.
+        let dev = unsafe { Device::from_raw(phydev) };
+        T::link_change_notify(dev);
+    }
+}
+
+/// Driver structure for a particular PHY type.
+///
+/// Wraps the kernel's [`struct phy_driver`].
+/// This is used to register a driver for a particular PHY type with the kernel.
+///
+/// # Invariants
+///
+/// `self.0` is always in a valid state.
+///
+/// [`struct phy_driver`]: ../../../../../../../include/linux/phy.h
+#[repr(transparent)]
+pub struct DriverVTable(Opaque<bindings::phy_driver>);
+
+// SAFETY: `DriverVTable` doesn't expose any &self method to access internal data, so it's safe to
+// share `&DriverVTable` across execution context boundries.
+unsafe impl Sync for DriverVTable {}
+
+/// Creates a [`DriverVTable`] instance from [`Driver`].
+///
+/// This is used by [`module_phy_driver`] macro to create a static array of `phy_driver`.
+///
+/// [`module_phy_driver`]: crate::module_phy_driver
+pub const fn create_phy_driver<T: Driver>() -> DriverVTable {
+    // INVARIANT: All the fields of `struct phy_driver` are initialized properly.
+    DriverVTable(Opaque::new(bindings::phy_driver {
+        name: T::NAME.as_char_ptr().cast_mut(),
+        flags: T::FLAGS,
+        phy_id: T::PHY_DEVICE_ID.id,
+        phy_id_mask: T::PHY_DEVICE_ID.mask_as_int(),
+        soft_reset: if T::HAS_SOFT_RESET {
+            Some(Adapter::<T>::soft_reset_callback)
+        } else {
+            None
+        },
+        get_features: if T::HAS_GET_FEATURES {
+            Some(Adapter::<T>::get_features_callback)
+        } else {
+            None
+        },
+        match_phy_device: if T::HAS_MATCH_PHY_DEVICE {
+            Some(Adapter::<T>::match_phy_device_callback)
+        } else {
+            None
+        },
+        suspend: if T::HAS_SUSPEND {
+            Some(Adapter::<T>::suspend_callback)
+        } else {
+            None
+        },
+        resume: if T::HAS_RESUME {
+            Some(Adapter::<T>::resume_callback)
+        } else {
+            None
+        },
+        config_aneg: if T::HAS_CONFIG_ANEG {
+            Some(Adapter::<T>::config_aneg_callback)
+        } else {
+            None
+        },
+        read_status: if T::HAS_READ_STATUS {
+            Some(Adapter::<T>::read_status_callback)
+        } else {
+            None
+        },
+        read_mmd: if T::HAS_READ_MMD {
+            Some(Adapter::<T>::read_mmd_callback)
+        } else {
+            None
+        },
+        write_mmd: if T::HAS_WRITE_MMD {
+            Some(Adapter::<T>::write_mmd_callback)
+        } else {
+            None
+        },
+        link_change_notify: if T::HAS_LINK_CHANGE_NOTIFY {
+            Some(Adapter::<T>::link_change_notify_callback)
+        } else {
+            None
+        },
+        // SAFETY: The rest is zeroed out to initialize `struct phy_driver`,
+        // sets `Option<&F>` to be `None`.
+        ..unsafe { core::mem::MaybeUninit::<bindings::phy_driver>::zeroed().assume_init() }
+    }))
+}
+
+/// Driver implementation for a particular PHY type.
+///
+/// This trait is used to create a [`DriverVTable`].
+#[vtable]
+pub trait Driver {
+    /// Defines certain other features this PHY supports.
+    /// It is a combination of the flags in the [`flags`] module.
+    const FLAGS: u32 = 0;
+
+    /// The friendly name of this PHY type.
+    const NAME: &'static CStr;
+
+    /// This driver only works for PHYs with IDs which match this field.
+    /// The default id and mask are zero.
+    const PHY_DEVICE_ID: DeviceId = DeviceId::new_with_custom_mask(0, 0);
+
+    /// Issues a PHY software reset.
+    fn soft_reset(_dev: &mut Device) -> Result {
+        Err(code::ENOTSUPP)
+    }
+
+    /// Probes the hardware to determine what abilities it has.
+    fn get_features(_dev: &mut Device) -> Result {
+        Err(code::ENOTSUPP)
+    }
+
+    /// Returns true if this is a suitable driver for the given phydev.
+    /// If not implemented, matching is based on [`Driver::PHY_DEVICE_ID`].
+    fn match_phy_device(_dev: &Device) -> bool {
+        false
+    }
+
+    /// Configures the advertisement and resets auto-negotiation
+    /// if auto-negotiation is enabled.
+    fn config_aneg(_dev: &mut Device) -> Result {
+        Err(code::ENOTSUPP)
+    }
+
+    /// Determines the negotiated speed and duplex.
+    fn read_status(_dev: &mut Device) -> Result<u16> {
+        Err(code::ENOTSUPP)
+    }
+
+    /// Suspends the hardware, saving state if needed.
+    fn suspend(_dev: &mut Device) -> Result {
+        Err(code::ENOTSUPP)
+    }
+
+    /// Resumes the hardware, restoring state if needed.
+    fn resume(_dev: &mut Device) -> Result {
+        Err(code::ENOTSUPP)
+    }
+
+    /// Overrides the default MMD read function for reading a MMD register.
+    fn read_mmd(_dev: &mut Device, _devnum: u8, _regnum: u16) -> Result<u16> {
+        Err(code::ENOTSUPP)
+    }
+
+    /// Overrides the default MMD write function for writing a MMD register.
+    fn write_mmd(_dev: &mut Device, _devnum: u8, _regnum: u16, _val: u16) -> Result {
+        Err(code::ENOTSUPP)
+    }
+
+    /// Callback for notification of link change.
+    fn link_change_notify(_dev: &mut Device) {}
+}
+
+/// Registration structure for PHY drivers.
+///
+/// Registers [`DriverVTable`] instances with the kernel. They will be unregistered when dropped.
+///
+/// # Invariants
+///
+/// The `drivers` slice are currently registered to the kernel via `phy_drivers_register`.
+pub struct Registration {
+    drivers: Pin<&'static mut [DriverVTable]>,
+}
+
+impl Registration {
+    /// Registers a PHY driver.
+    pub fn register(
+        module: &'static crate::ThisModule,
+        drivers: Pin<&'static mut [DriverVTable]>,
+    ) -> Result<Self> {
+        if drivers.is_empty() {
+            return Err(code::EINVAL);
+        }
+        // SAFETY: The type invariants of [`DriverVTable`] ensure that all elements of
+        // the `drivers` slice are initialized properly. `drivers` will not be moved.
+        // So it's just an FFI call.
+        to_result(unsafe {
+            bindings::phy_drivers_register(drivers[0].0.get(), drivers.len().try_into()?, module.0)
+        })?;
+        // INVARIANT: The `drivers` slice is successfully registered to the kernel via `phy_drivers_register`.
+        Ok(Registration { drivers })
+    }
+}
+
+impl Drop for Registration {
+    fn drop(&mut self) {
+        // SAFETY: The type invariants guarantee that `self.drivers` is valid.
+        // So it's just an FFI call.
+        unsafe {
+            bindings::phy_drivers_unregister(self.drivers[0].0.get(), self.drivers.len() as i32)
+        };
+    }
+}
+
+/// An identifier for PHY devices on an MDIO/MII bus.
+///
+/// Represents the kernel's `struct mdio_device_id`. This is used to find an appropriate
+/// PHY driver.
+pub struct DeviceId {
+    id: u32,
+    mask: DeviceMask,
+}
+
+impl DeviceId {
+    /// Creates a new instance with the exact match mask.
+    pub const fn new_with_exact_mask(id: u32) -> Self {
+        DeviceId {
+            id,
+            mask: DeviceMask::Exact,
+        }
+    }
+
+    /// Creates a new instance with the model match mask.
+    pub const fn new_with_model_mask(id: u32) -> Self {
+        DeviceId {
+            id,
+            mask: DeviceMask::Model,
+        }
+    }
+
+    /// Creates a new instance with the vendor match mask.
+    pub const fn new_with_vendor_mask(id: u32) -> Self {
+        DeviceId {
+            id,
+            mask: DeviceMask::Vendor,
+        }
+    }
+
+    /// Creates a new instance with a custom match mask.
+    pub const fn new_with_custom_mask(id: u32, mask: u32) -> Self {
+        DeviceId {
+            id,
+            mask: DeviceMask::Custom(mask),
+        }
+    }
+
+    /// Creates a new instance from [`Driver`].
+    pub const fn new_with_driver<T: Driver>() -> Self {
+        T::PHY_DEVICE_ID
+    }
+
+    /// Get a `mask` as u32.
+    pub const fn mask_as_int(&self) -> u32 {
+        self.mask.as_int()
+    }
+
+    // macro use only
+    #[doc(hidden)]
+    pub const fn mdio_device_id(&self) -> bindings::mdio_device_id {
+        bindings::mdio_device_id {
+            phy_id: self.id,
+            phy_id_mask: self.mask.as_int(),
+        }
+    }
+}
+
+enum DeviceMask {
+    Exact,
+    Model,
+    Vendor,
+    Custom(u32),
+}
+
+impl DeviceMask {
+    const MASK_EXACT: u32 = !0;
+    const MASK_MODEL: u32 = !0 << 4;
+    const MASK_VENDOR: u32 = !0 << 10;
+
+    const fn as_int(&self) -> u32 {
+        match self {
+            DeviceMask::Exact => Self::MASK_EXACT,
+            DeviceMask::Model => Self::MASK_MODEL,
+            DeviceMask::Vendor => Self::MASK_VENDOR,
+            DeviceMask::Custom(mask) => *mask,
+        }
+    }
+}
+
+/// Declares a kernel module for PHYs drivers.
+///
+/// This creates a static array of kernel's `struct phy_driver` and registers it.
+/// This also corresponds to the kernel's `MODULE_DEVICE_TABLE` macro, which embeds the information
+/// for module loading into the module binary file. Every driver needs an entry in `device_table`.
+///
+/// # Examples
+///
+/// ```
+/// # mod module_phy_driver_sample {
+/// use kernel::c_str;
+/// use kernel::net::phy::{self, DeviceId};
+/// use kernel::prelude::*;
+///
+/// kernel::module_phy_driver! {
+///     drivers: [PhySample],
+///     device_table: [
+///         DeviceId::new_with_driver::<PhySample>()
+///     ],
+///     name: "rust_sample_phy",
+///     author: "Rust for Linux Contributors",
+///     description: "Rust sample PHYs driver",
+///     license: "GPL",
+/// }
+///
+/// struct PhySample;
+///
+/// #[vtable]
+/// impl phy::Driver for PhySample {
+///     const NAME: &'static CStr = c_str!("PhySample");
+///     const PHY_DEVICE_ID: phy::DeviceId = phy::DeviceId::new_with_exact_mask(0x00000001);
+/// }
+/// # }
+/// ```
+///
+/// This expands to the following code:
+///
+/// ```ignore
+/// use kernel::c_str;
+/// use kernel::net::phy::{self, DeviceId};
+/// use kernel::prelude::*;
+///
+/// struct Module {
+///     _reg: ::kernel::net::phy::Registration,
+/// }
+///
+/// module! {
+///     type: Module,
+///     name: "rust_sample_phy",
+///     author: "Rust for Linux Contributors",
+///     description: "Rust sample PHYs driver",
+///     license: "GPL",
+/// }
+///
+/// struct PhySample;
+///
+/// #[vtable]
+/// impl phy::Driver for PhySample {
+///     const NAME: &'static CStr = c_str!("PhySample");
+///     const PHY_DEVICE_ID: phy::DeviceId = phy::DeviceId::new_with_exact_mask(0x00000001);
+/// }
+///
+/// const _: () = {
+///     static mut DRIVERS: [::kernel::net::phy::DriverVTable; 1] =
+///         [::kernel::net::phy::create_phy_driver::<PhySample>()];
+///
+///     impl ::kernel::Module for Module {
+///         fn init(module: &'static ThisModule) -> Result<Self> {
+///             let drivers = unsafe { &mut DRIVERS };
+///             let mut reg = ::kernel::net::phy::Registration::register(
+///                 module,
+///                 ::core::pin::Pin::static_mut(drivers),
+///             )?;
+///             Ok(Module { _reg: reg })
+///         }
+///     }
+/// };
+///
+/// #[cfg(MODULE)]
+/// #[no_mangle]
+/// static __mod_mdio__phydev_device_table: [::kernel::bindings::mdio_device_id; 2] = [
+///     ::kernel::bindings::mdio_device_id {
+///         phy_id: 0x00000001,
+///         phy_id_mask: 0xffffffff,
+///     },
+///     ::kernel::bindings::mdio_device_id {
+///         phy_id: 0,
+///         phy_id_mask: 0,
+///     },
+/// ];
+/// ```
+#[macro_export]
+macro_rules! module_phy_driver {
+    (@replace_expr $_t:tt $sub:expr) => {$sub};
+
+    (@count_devices $($x:expr),*) => {
+        0usize $(+ $crate::module_phy_driver!(@replace_expr $x 1usize))*
+    };
+
+    (@device_table [$($dev:expr),+]) => {
+        // SAFETY: C will not read off the end of this constant since the last element is zero.
+        #[cfg(MODULE)]
+        #[no_mangle]
+        static __mod_mdio__phydev_device_table: [$crate::bindings::mdio_device_id;
+            $crate::module_phy_driver!(@count_devices $($dev),+) + 1] = [
+            $($dev.mdio_device_id()),+,
+            $crate::bindings::mdio_device_id {
+                phy_id: 0,
+                phy_id_mask: 0
+            }
+        ];
+    };
+
+    (drivers: [$($driver:ident),+ $(,)?], device_table: [$($dev:expr),+ $(,)?], $($f:tt)*) => {
+        struct Module {
+            _reg: $crate::net::phy::Registration,
+        }
+
+        $crate::prelude::module! {
+            type: Module,
+            $($f)*
+        }
+
+        const _: () = {
+            static mut DRIVERS: [$crate::net::phy::DriverVTable;
+                $crate::module_phy_driver!(@count_devices $($driver),+)] =
+                [$($crate::net::phy::create_phy_driver::<$driver>()),+];
+
+            impl $crate::Module for Module {
+                fn init(module: &'static ThisModule) -> Result<Self> {
+                    // SAFETY: The anonymous constant guarantees that nobody else can access
+                    // the `DRIVERS` static. The array is used only in the C side.
+                    let drivers = unsafe { &mut DRIVERS };
+                    let mut reg = $crate::net::phy::Registration::register(
+                        module,
+                        ::core::pin::Pin::static_mut(drivers),
+                    )?;
+                    Ok(Module { _reg: reg })
+                }
+            }
+        };
+
+        $crate::module_phy_driver!(@device_table [$($dev),+]);
+    }
+}
diff --git a/rust/kernel/print.rs b/rust/kernel/print.rs
index f48926e3e9fe..9b13aca832c2 100644
--- a/rust/kernel/print.rs
+++ b/rust/kernel/print.rs
@@ -2,7 +2,7 @@
 
 //! Printing facilities.
 //!
-//! C header: [`include/linux/printk.h`](../../../../include/linux/printk.h)
+//! C header: [`include/linux/printk.h`](srctree/include/linux/printk.h)
 //!
 //! Reference: <https://www.kernel.org/doc/html/latest/core-api/printk-basics.html>
 
@@ -48,7 +48,7 @@ pub mod format_strings {
     /// The format string is always the same for a given level, i.e. for a
     /// given `prefix`, which are the kernel's `KERN_*` constants.
     ///
-    /// [`_printk`]: ../../../../include/linux/printk.h
+    /// [`_printk`]: srctree/include/linux/printk.h
     const fn generate(is_cont: bool, prefix: &[u8; 3]) -> [u8; LENGTH] {
         // Ensure the `KERN_*` macros are what we expect.
         assert!(prefix[0] == b'\x01');
@@ -97,7 +97,7 @@ pub mod format_strings {
 /// The format string must be one of the ones in [`format_strings`], and
 /// the module name must be null-terminated.
 ///
-/// [`_printk`]: ../../../../include/linux/_printk.h
+/// [`_printk`]: srctree/include/linux/_printk.h
 #[doc(hidden)]
 #[cfg_attr(not(CONFIG_PRINTK), allow(unused_variables))]
 pub unsafe fn call_printk(
@@ -120,7 +120,7 @@ pub unsafe fn call_printk(
 ///
 /// Public but hidden since it should only be used from public macros.
 ///
-/// [`_printk`]: ../../../../include/linux/printk.h
+/// [`_printk`]: srctree/include/linux/printk.h
 #[doc(hidden)]
 #[cfg_attr(not(CONFIG_PRINTK), allow(unused_variables))]
 pub fn call_printk_cont(args: fmt::Arguments<'_>) {
diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs
index c41607b2e4fe..7d848b83add4 100644
--- a/rust/kernel/str.rs
+++ b/rust/kernel/str.rs
@@ -608,6 +608,12 @@ impl<'a> TryFrom<&'a CStr> for CString {
     }
 }
 
+impl fmt::Debug for CString {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        fmt::Debug::fmt(&**self, f)
+    }
+}
+
 /// A convenience alias for [`core::format_args`].
 #[macro_export]
 macro_rules! fmt {
diff --git a/rust/kernel/sync/condvar.rs b/rust/kernel/sync/condvar.rs
index b679b6f6dbeb..f65e19d5a37c 100644
--- a/rust/kernel/sync/condvar.rs
+++ b/rust/kernel/sync/condvar.rs
@@ -50,7 +50,7 @@ macro_rules! new_condvar {
 /// fn wait_for_value(e: &Example, v: u32) {
 ///     let mut guard = e.value.lock();
 ///     while *guard != v {
-///         e.value_changed.wait_uninterruptible(&mut guard);
+///         e.value_changed.wait(&mut guard);
 ///     }
 /// }
 ///
@@ -69,7 +69,7 @@ macro_rules! new_condvar {
 /// }
 /// ```
 ///
-/// [`struct wait_queue_head`]: ../../../include/linux/wait.h
+/// [`struct wait_queue_head`]: srctree/include/linux/wait.h
 #[pin_data]
 pub struct CondVar {
     #[pin]
@@ -120,28 +120,28 @@ impl CondVar {
         unsafe { bindings::finish_wait(self.wait_list.get(), wait.get()) };
     }
 
-    /// Releases the lock and waits for a notification in interruptible mode.
+    /// Releases the lock and waits for a notification in uninterruptible mode.
     ///
     /// Atomically releases the given lock (whose ownership is proven by the guard) and puts the
     /// thread to sleep, reacquiring the lock on wake up. It wakes up when notified by
-    /// [`CondVar::notify_one`] or [`CondVar::notify_all`], or when the thread receives a signal.
-    /// It may also wake up spuriously.
+    /// [`CondVar::notify_one`] or [`CondVar::notify_all`]. Note that it may also wake up
+    /// spuriously.
+    pub fn wait<T: ?Sized, B: Backend>(&self, guard: &mut Guard<'_, T, B>) {
+        self.wait_internal(bindings::TASK_UNINTERRUPTIBLE, guard);
+    }
+
+    /// Releases the lock and waits for a notification in interruptible mode.
+    ///
+    /// Similar to [`CondVar::wait`], except that the wait is interruptible. That is, the thread may
+    /// wake up due to signals. It may also wake up spuriously.
     ///
     /// Returns whether there is a signal pending.
-    #[must_use = "wait returns if a signal is pending, so the caller must check the return value"]
-    pub fn wait<T: ?Sized, B: Backend>(&self, guard: &mut Guard<'_, T, B>) -> bool {
+    #[must_use = "wait_interruptible returns if a signal is pending, so the caller must check the return value"]
+    pub fn wait_interruptible<T: ?Sized, B: Backend>(&self, guard: &mut Guard<'_, T, B>) -> bool {
         self.wait_internal(bindings::TASK_INTERRUPTIBLE, guard);
         crate::current!().signal_pending()
     }
 
-    /// Releases the lock and waits for a notification in uninterruptible mode.
-    ///
-    /// Similar to [`CondVar::wait`], except that the wait is not interruptible. That is, the
-    /// thread won't wake up due to signals. It may, however, wake up supirously.
-    pub fn wait_uninterruptible<T: ?Sized, B: Backend>(&self, guard: &mut Guard<'_, T, B>) {
-        self.wait_internal(bindings::TASK_UNINTERRUPTIBLE, guard)
-    }
-
     /// Calls the kernel function to notify the appropriate number of threads with the given flags.
     fn notify(&self, count: i32, flags: u32) {
         // SAFETY: `wait_list` points to valid memory.
diff --git a/rust/kernel/sync/lock/mutex.rs b/rust/kernel/sync/lock/mutex.rs
index 09276fedc091..8c524a3ec45a 100644
--- a/rust/kernel/sync/lock/mutex.rs
+++ b/rust/kernel/sync/lock/mutex.rs
@@ -84,7 +84,7 @@ macro_rules! new_mutex {
 /// }
 /// ```
 ///
-/// [`struct mutex`]: ../../../../include/linux/mutex.h
+/// [`struct mutex`]: srctree/include/linux/mutex.h
 pub type Mutex<T> = super::Lock<T, MutexBackend>;
 
 /// A kernel `struct mutex` lock backend.
diff --git a/rust/kernel/sync/lock/spinlock.rs b/rust/kernel/sync/lock/spinlock.rs
index 91eb2c9e9123..068535ce1b29 100644
--- a/rust/kernel/sync/lock/spinlock.rs
+++ b/rust/kernel/sync/lock/spinlock.rs
@@ -82,7 +82,7 @@ macro_rules! new_spinlock {
 /// }
 /// ```
 ///
-/// [`spinlock_t`]: ../../../../include/linux/spinlock.h
+/// [`spinlock_t`]: srctree/include/linux/spinlock.h
 pub type SpinLock<T> = super::Lock<T, SpinLockBackend>;
 
 /// A kernel `spinlock_t` lock backend.
diff --git a/rust/kernel/task.rs b/rust/kernel/task.rs
index b2299bc7ac1f..9451932d5d86 100644
--- a/rust/kernel/task.rs
+++ b/rust/kernel/task.rs
@@ -2,7 +2,7 @@
 
 //! Tasks (threads and processes).
 //!
-//! C header: [`include/linux/sched.h`](../../../../include/linux/sched.h).
+//! C header: [`include/linux/sched.h`](srctree/include/linux/sched.h).
 
 use crate::{bindings, types::Opaque};
 use core::{marker::PhantomData, ops::Deref, ptr};
diff --git a/rust/kernel/workqueue.rs b/rust/kernel/workqueue.rs
index b67fb1ba168e..498397877376 100644
--- a/rust/kernel/workqueue.rs
+++ b/rust/kernel/workqueue.rs
@@ -132,7 +132,7 @@
 //! }
 //! ```
 //!
-//! C header: [`include/linux/workqueue.h`](../../../../include/linux/workqueue.h)
+//! C header: [`include/linux/workqueue.h`](srctree/include/linux/workqueue.h)
 
 use crate::{bindings, prelude::*, sync::Arc, sync::LockClassKey, types::Opaque};
 use alloc::alloc::AllocError;
diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs
index c42105c2ff96..f489f3157383 100644
--- a/rust/macros/lib.rs
+++ b/rust/macros/lib.rs
@@ -20,7 +20,7 @@ use proc_macro::TokenStream;
 /// The `type` argument should be a type which implements the [`Module`]
 /// trait. Also accepts various forms of kernel metadata.
 ///
-/// C header: [`include/linux/moduleparam.h`](../../../include/linux/moduleparam.h)
+/// C header: [`include/linux/moduleparam.h`](srctree/include/linux/moduleparam.h)
 ///
 /// [`Module`]: ../kernel/trait.Module.html
 ///
@@ -87,27 +87,49 @@ pub fn module(ts: TokenStream) -> TokenStream {
 /// implementation could just return `Error::EINVAL`); Linux typically use C
 /// `NULL` pointers to represent these functions.
 ///
-/// This attribute is intended to close the gap. Traits can be declared and
-/// implemented with the `#[vtable]` attribute, and a `HAS_*` associated constant
-/// will be generated for each method in the trait, indicating if the implementor
-/// has overridden a method.
+/// This attribute closes that gap. A trait can be annotated with the
+/// `#[vtable]` attribute. Implementers of the trait will then also have to
+/// annotate the trait with `#[vtable]`. This attribute generates a `HAS_*`
+/// associated constant bool for each method in the trait that is set to true if
+/// the implementer has overridden the associated method.
+///
+/// For a trait method to be optional, it must have a default implementation.
+/// This is also the case for traits annotated with `#[vtable]`, but in this
+/// case the default implementation will never be executed. The reason for this
+/// is that the functions will be called through function pointers installed in
+/// C side vtables. When an optional method is not implemented on a `#[vtable]`
+/// trait, a NULL entry is installed in the vtable. Thus the default
+/// implementation is never called. Since these traits are not designed to be
+/// used on the Rust side, it should not be possible to call the default
+/// implementation. This is done to ensure that we call the vtable methods
+/// through the C vtable, and not through the Rust vtable. Therefore, the
+/// default implementation should call `kernel::build_error`, which prevents
+/// calls to this function at compile time:
+///
+/// ```compile_fail
+/// # use kernel::error::VTABLE_DEFAULT_ERROR;
+/// kernel::build_error(VTABLE_DEFAULT_ERROR)
+/// ```
+///
+/// Note that you might need to import [`kernel::error::VTABLE_DEFAULT_ERROR`].
 ///
-/// This attribute is not needed if all methods are required.
+/// This macro should not be used when all functions are required.
 ///
 /// # Examples
 ///
 /// ```ignore
+/// use kernel::error::VTABLE_DEFAULT_ERROR;
 /// use kernel::prelude::*;
 ///
 /// // Declares a `#[vtable]` trait
 /// #[vtable]
 /// pub trait Operations: Send + Sync + Sized {
 ///     fn foo(&self) -> Result<()> {
-///         Err(EINVAL)
+///         kernel::build_error(VTABLE_DEFAULT_ERROR)
 ///     }
 ///
 ///     fn bar(&self) -> Result<()> {
-///         Err(EINVAL)
+///         kernel::build_error(VTABLE_DEFAULT_ERROR)
 ///     }
 /// }
 ///
@@ -125,6 +147,8 @@ pub fn module(ts: TokenStream) -> TokenStream {
 /// assert_eq!(<Foo as Operations>::HAS_FOO, true);
 /// assert_eq!(<Foo as Operations>::HAS_BAR, false);
 /// ```
+///
+/// [`kernel::error::VTABLE_DEFAULT_ERROR`]: ../kernel/error/constant.VTABLE_DEFAULT_ERROR.html
 #[proc_macro_attribute]
 pub fn vtable(attr: TokenStream, ts: TokenStream) -> TokenStream {
     vtable::vtable(attr, ts)
@@ -254,8 +278,8 @@ pub fn pinned_drop(args: TokenStream, input: TokenStream) -> TokenStream {
 /// Within the `paste!` macro, identifiers inside `[<` and `>]` are concatenated together to form a
 /// single identifier.
 ///
-/// This is similar to the [`paste`] crate, but with pasting feature limited to identifiers
-/// (literals, lifetimes and documentation strings are not supported). There is a difference in
+/// This is similar to the [`paste`] crate, but with pasting feature limited to identifiers and
+/// literals (lifetimes and documentation strings are not supported). There is a difference in
 /// supported modifiers as well.
 ///
 /// # Example
@@ -337,6 +361,24 @@ pub fn pinned_drop(args: TokenStream, input: TokenStream) -> TokenStream {
 /// assert_eq!(br_ok(), binder_driver_return_protocol_BR_OK);
 /// ```
 ///
+/// # Literals
+///
+/// Literals can also be concatenated with other identifiers:
+///
+/// ```ignore
+/// macro_rules! create_numbered_fn {
+///     ($name:literal, $val:literal) => {
+///         kernel::macros::paste! {
+///             fn [<some_ $name _fn $val>]() -> u32 { $val }
+///         }
+///     };
+/// }
+///
+/// create_numbered_fn!("foo", 100);
+///
+/// assert_eq!(some_foo_fn100(), 100)
+/// ```
+///
 /// [`paste`]: https://docs.rs/paste/
 #[proc_macro]
 pub fn paste(input: TokenStream) -> TokenStream {
diff --git a/rust/macros/paste.rs b/rust/macros/paste.rs
index 385a78434224..f40d42b35b58 100644
--- a/rust/macros/paste.rs
+++ b/rust/macros/paste.rs
@@ -9,7 +9,15 @@ fn concat(tokens: &[TokenTree], group_span: Span) -> TokenTree {
     loop {
         match tokens.next() {
             None => break,
-            Some(TokenTree::Literal(lit)) => segments.push((lit.to_string(), lit.span())),
+            Some(TokenTree::Literal(lit)) => {
+                // Allow us to concat string literals by stripping quotes
+                let mut value = lit.to_string();
+                if value.starts_with('"') && value.ends_with('"') {
+                    value.remove(0);
+                    value.pop();
+                }
+                segments.push((value, lit.span()));
+            }
             Some(TokenTree::Ident(ident)) => {
                 let mut value = ident.to_string();
                 if value.starts_with("r#") {
diff --git a/rust/uapi/uapi_helper.h b/rust/uapi/uapi_helper.h
index 301f5207f023..08f5e9334c9e 100644
--- a/rust/uapi/uapi_helper.h
+++ b/rust/uapi/uapi_helper.h
@@ -7,3 +7,5 @@
  */
 
 #include <uapi/asm-generic/ioctl.h>
+#include <uapi/linux/mii.h>
+#include <uapi/linux/ethtool.h>
diff --git a/samples/Kconfig b/samples/Kconfig
index b0ddf5f36738..b288d9991d27 100644
--- a/samples/Kconfig
+++ b/samples/Kconfig
@@ -285,6 +285,12 @@ config SAMPLE_KMEMLEAK
           Build a sample program which have explicitly leaks memory to test
           kmemleak
 
+config SAMPLE_CGROUP
+	bool "Build cgroup sample code"
+	depends on CGROUPS && CC_CAN_LINK && HEADERS_INSTALL
+	help
+	  Build samples that demonstrate the usage of the cgroup API.
+
 source "samples/rust/Kconfig"
 
 endif # SAMPLES
diff --git a/samples/Makefile b/samples/Makefile
index 0a551c2b33f4..b85fa64390c5 100644
--- a/samples/Makefile
+++ b/samples/Makefile
@@ -3,6 +3,7 @@
 
 subdir-$(CONFIG_SAMPLE_AUXDISPLAY)	+= auxdisplay
 subdir-$(CONFIG_SAMPLE_ANDROID_BINDERFS) += binderfs
+subdir-$(CONFIG_SAMPLE_CGROUP) += cgroup
 obj-$(CONFIG_SAMPLE_CONFIGFS)		+= configfs/
 obj-$(CONFIG_SAMPLE_CONNECTOR)		+= connector/
 obj-$(CONFIG_SAMPLE_FANOTIFY_ERROR)	+= fanotify/
diff --git a/samples/bpf/cpustat_user.c b/samples/bpf/cpustat_user.c
index ab90bb08a2b4..356f756cba0d 100644
--- a/samples/bpf/cpustat_user.c
+++ b/samples/bpf/cpustat_user.c
@@ -66,10 +66,10 @@ static void cpu_stat_print(void)
 
 		printf("CPU-%-6d ", j);
 		for (i = 0; i < MAX_CSTATE_ENTRIES; i++)
-			printf("%-11ld ", data->cstate[i] / 1000000);
+			printf("%-11lu ", data->cstate[i] / 1000000);
 
 		for (i = 0; i < MAX_PSTATE_ENTRIES; i++)
-			printf("%-11ld ", data->pstate[i] / 1000000);
+			printf("%-11lu ", data->pstate[i] / 1000000);
 
 		printf("\n");
 	}
diff --git a/samples/cgroup/Makefile b/samples/cgroup/Makefile
new file mode 100644
index 000000000000..526c8569707c
--- /dev/null
+++ b/samples/cgroup/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+
+userprogs-always-y += cgroup_event_listener memcg_event_listener
+
+userccflags += -I usr/include
diff --git a/tools/cgroup/cgroup_event_listener.c b/samples/cgroup/cgroup_event_listener.c
index 3d70dc831a76..3d70dc831a76 100644
--- a/tools/cgroup/cgroup_event_listener.c
+++ b/samples/cgroup/cgroup_event_listener.c
diff --git a/samples/cgroup/memcg_event_listener.c b/samples/cgroup/memcg_event_listener.c
new file mode 100644
index 000000000000..a1667fe2489a
--- /dev/null
+++ b/samples/cgroup/memcg_event_listener.c
@@ -0,0 +1,330 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * memcg_event_listener.c - Simple listener of memcg memory.events
+ *
+ * Copyright (c) 2023, SaluteDevices. All Rights Reserved.
+ *
+ * Author: Dmitry Rokosov <ddrokosov@salutedevices.com>
+ */
+
+#include <err.h>
+#include <errno.h>
+#include <limits.h>
+#include <poll.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/inotify.h>
+#include <unistd.h>
+
+#define MEMCG_EVENTS "memory.events"
+
+/* Size of buffer to use when reading inotify events */
+#define INOTIFY_BUFFER_SIZE 8192
+
+#define INOTIFY_EVENT_NEXT(event, length) ({         \
+	(length) -= sizeof(*(event)) + (event)->len; \
+	(event)++;                                   \
+})
+
+#define INOTIFY_EVENT_OK(event, length) ((length) >= (ssize_t)sizeof(*(event)))
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(arr[0]))
+
+struct memcg_counters {
+	long low;
+	long high;
+	long max;
+	long oom;
+	long oom_kill;
+	long oom_group_kill;
+};
+
+struct memcg_events {
+	struct memcg_counters counters;
+	char path[PATH_MAX];
+	int inotify_fd;
+	int inotify_wd;
+};
+
+static void print_memcg_counters(const struct memcg_counters *counters)
+{
+	printf("MEMCG events:\n");
+	printf("\tlow: %ld\n", counters->low);
+	printf("\thigh: %ld\n", counters->high);
+	printf("\tmax: %ld\n", counters->max);
+	printf("\toom: %ld\n", counters->oom);
+	printf("\toom_kill: %ld\n", counters->oom_kill);
+	printf("\toom_group_kill: %ld\n", counters->oom_group_kill);
+}
+
+static int get_memcg_counter(char *line, const char *name, long *counter)
+{
+	size_t len = strlen(name);
+	char *endptr;
+	long tmp;
+
+	if (memcmp(line, name, len)) {
+		warnx("Counter line %s has wrong name, %s is expected",
+		      line, name);
+		return -EINVAL;
+	}
+
+	/* skip the whitespace delimiter */
+	len += 1;
+
+	errno = 0;
+	tmp = strtol(&line[len], &endptr, 10);
+	if (((tmp == LONG_MAX || tmp == LONG_MIN) && errno == ERANGE) ||
+	    (errno && !tmp)) {
+		warnx("Failed to parse: %s", &line[len]);
+		return -ERANGE;
+	}
+
+	if (endptr == &line[len]) {
+		warnx("Not digits were found in line %s", &line[len]);
+		return -EINVAL;
+	}
+
+	if (!(*endptr == '\0' || (*endptr == '\n' && *++endptr == '\0'))) {
+		warnx("Further characters after number: %s", endptr);
+		return -EINVAL;
+	}
+
+	*counter = tmp;
+
+	return 0;
+}
+
+static int read_memcg_events(struct memcg_events *events, bool show_diff)
+{
+	FILE *fp = fopen(events->path, "re");
+	size_t i;
+	int ret = 0;
+	bool any_new_events = false;
+	char *line = NULL;
+	size_t len = 0;
+	struct memcg_counters new_counters;
+	struct memcg_counters *counters = &events->counters;
+	struct {
+		const char *name;
+		long *new;
+		long *old;
+	} map[] = {
+		{
+			.name = "low",
+			.new = &new_counters.low,
+			.old = &counters->low,
+		},
+		{
+			.name = "high",
+			.new = &new_counters.high,
+			.old = &counters->high,
+		},
+		{
+			.name = "max",
+			.new = &new_counters.max,
+			.old = &counters->max,
+		},
+		{
+			.name = "oom",
+			.new = &new_counters.oom,
+			.old = &counters->oom,
+		},
+		{
+			.name = "oom_kill",
+			.new = &new_counters.oom_kill,
+			.old = &counters->oom_kill,
+		},
+		{
+			.name = "oom_group_kill",
+			.new = &new_counters.oom_group_kill,
+			.old = &counters->oom_group_kill,
+		},
+	};
+
+	if (!fp) {
+		warn("Failed to open memcg events file %s", events->path);
+		return -EBADF;
+	}
+
+	/* Read new values for memcg counters */
+	for (i = 0; i < ARRAY_SIZE(map); ++i) {
+		ssize_t nread;
+
+		errno = 0;
+		nread = getline(&line, &len, fp);
+		if (nread == -1) {
+			if (errno) {
+				warn("Failed to read line for counter %s",
+				     map[i].name);
+				ret = -EIO;
+				goto exit;
+			}
+
+			break;
+		}
+
+		ret = get_memcg_counter(line, map[i].name, map[i].new);
+		if (ret) {
+			warnx("Failed to get counter value from line %s", line);
+			goto exit;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(map); ++i) {
+		long diff;
+
+		if (*map[i].new > *map[i].old) {
+			diff = *map[i].new - *map[i].old;
+
+			if (show_diff)
+				printf("*** %ld MEMCG %s event%s, "
+				       "change counter %ld => %ld\n",
+				       diff, map[i].name,
+				       (diff == 1) ? "" : "s",
+				       *map[i].old, *map[i].new);
+
+			*map[i].old += diff;
+			any_new_events = true;
+		}
+	}
+
+	if (show_diff && !any_new_events)
+		printf("*** No new untracked memcg events available\n");
+
+exit:
+	free(line);
+	fclose(fp);
+
+	return ret;
+}
+
+static void process_memcg_events(struct memcg_events *events,
+				 struct inotify_event *event)
+{
+	int ret;
+
+	if (events->inotify_wd != event->wd) {
+		warnx("Unknown inotify event %d, should be %d", event->wd,
+		      events->inotify_wd);
+		return;
+	}
+
+	printf("Received event in %s:\n", events->path);
+
+	if (!(event->mask & IN_MODIFY)) {
+		warnx("No IN_MODIFY event, skip it");
+		return;
+	}
+
+	ret = read_memcg_events(events, /* show_diff = */true);
+	if (ret)
+		warnx("Can't read memcg events");
+}
+
+static void monitor_events(struct memcg_events *events)
+{
+	struct pollfd fds[1];
+	int ret;
+
+	printf("Started monitoring memory events from '%s'...\n", events->path);
+
+	fds[0].fd = events->inotify_fd;
+	fds[0].events = POLLIN;
+
+	for (;;) {
+		ret = poll(fds, ARRAY_SIZE(fds), -1);
+		if (ret < 0 && errno != EAGAIN)
+			err(EXIT_FAILURE, "Can't poll memcg events (%d)", ret);
+
+		if (fds[0].revents & POLLERR)
+			err(EXIT_FAILURE, "Got POLLERR during monitor events");
+
+		if (fds[0].revents & POLLIN) {
+			struct inotify_event *event;
+			char buffer[INOTIFY_BUFFER_SIZE];
+			ssize_t length;
+
+			length = read(fds[0].fd, buffer, INOTIFY_BUFFER_SIZE);
+			if (length <= 0)
+				continue;
+
+			event = (struct inotify_event *)buffer;
+			while (INOTIFY_EVENT_OK(event, length)) {
+				process_memcg_events(events, event);
+				event = INOTIFY_EVENT_NEXT(event, length);
+			}
+		}
+	}
+}
+
+static int initialize_memcg_events(struct memcg_events *events,
+				   const char *cgroup)
+{
+	int ret;
+
+	memset(events, 0, sizeof(struct memcg_events));
+
+	ret = snprintf(events->path, PATH_MAX,
+		       "/sys/fs/cgroup/%s/memory.events", cgroup);
+	if (ret >= PATH_MAX) {
+		warnx("Path to cgroup memory.events is too long");
+		return -EMSGSIZE;
+	} else if (ret < 0) {
+		warn("Can't generate cgroup event full name");
+		return ret;
+	}
+
+	ret = read_memcg_events(events, /* show_diff = */false);
+	if (ret) {
+		warnx("Failed to read initial memcg events state (%d)", ret);
+		return ret;
+	}
+
+	events->inotify_fd = inotify_init();
+	if (events->inotify_fd < 0) {
+		warn("Failed to setup new inotify device");
+		return -EMFILE;
+	}
+
+	events->inotify_wd = inotify_add_watch(events->inotify_fd,
+					       events->path, IN_MODIFY);
+	if (events->inotify_wd < 0) {
+		warn("Couldn't add monitor in dir %s", events->path);
+		return -EIO;
+	}
+
+	printf("Initialized MEMCG events with counters:\n");
+	print_memcg_counters(&events->counters);
+
+	return 0;
+}
+
+static void cleanup_memcg_events(struct memcg_events *events)
+{
+	inotify_rm_watch(events->inotify_fd, events->inotify_wd);
+	close(events->inotify_fd);
+}
+
+int main(int argc, const char **argv)
+{
+	struct memcg_events events;
+	ssize_t ret;
+
+	if (argc != 2)
+		errx(EXIT_FAILURE, "Usage: %s <cgroup>", argv[0]);
+
+	ret = initialize_memcg_events(&events, argv[1]);
+	if (ret)
+		errx(EXIT_FAILURE, "Can't initialize memcg events (%zd)", ret);
+
+	monitor_events(&events);
+
+	cleanup_memcg_events(&events);
+
+	printf("Exiting memcg event listener...\n");
+
+	return EXIT_SUCCESS;
+}
diff --git a/samples/trace_events/trace-events-sample.h b/samples/trace_events/trace-events-sample.h
index 1c6b843b8c4e..23f923ccd529 100644
--- a/samples/trace_events/trace-events-sample.h
+++ b/samples/trace_events/trace-events-sample.h
@@ -305,7 +305,7 @@ TRACE_EVENT(foo_bar,
 	),
 
 	TP_fast_assign(
-		strlcpy(__entry->foo, foo, 10);
+		strscpy(__entry->foo, foo, 10);
 		__entry->bar	= bar;
 		memcpy(__get_dynamic_array(list), lst,
 		       __length_of(lst) * sizeof(int));
diff --git a/samples/v4l/v4l2-pci-skeleton.c b/samples/v4l/v4l2-pci-skeleton.c
index a61f94db18d9..69ef788d9e3b 100644
--- a/samples/v4l/v4l2-pci-skeleton.c
+++ b/samples/v4l/v4l2-pci-skeleton.c
@@ -291,8 +291,8 @@ static int skeleton_querycap(struct file *file, void *priv,
 {
 	struct skeleton *skel = video_drvdata(file);
 
-	strlcpy(cap->driver, KBUILD_MODNAME, sizeof(cap->driver));
-	strlcpy(cap->card, "V4L2 PCI Skeleton", sizeof(cap->card));
+	strscpy(cap->driver, KBUILD_MODNAME, sizeof(cap->driver));
+	strscpy(cap->card, "V4L2 PCI Skeleton", sizeof(cap->card));
 	snprintf(cap->bus_info, sizeof(cap->bus_info), "PCI:%s",
 		 pci_name(skel->pdev));
 	return 0;
@@ -597,11 +597,11 @@ static int skeleton_enum_input(struct file *file, void *priv,
 	i->type = V4L2_INPUT_TYPE_CAMERA;
 	if (i->index == 0) {
 		i->std = SKEL_TVNORMS;
-		strlcpy(i->name, "S-Video", sizeof(i->name));
+		strscpy(i->name, "S-Video", sizeof(i->name));
 		i->capabilities = V4L2_IN_CAP_STD;
 	} else {
 		i->std = 0;
-		strlcpy(i->name, "HDMI", sizeof(i->name));
+		strscpy(i->name, "HDMI", sizeof(i->name));
 		i->capabilities = V4L2_IN_CAP_DV_TIMINGS;
 	}
 	return 0;
@@ -845,7 +845,7 @@ static int skeleton_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* Initialize the video_device structure */
 	vdev = &skel->vdev;
-	strlcpy(vdev->name, KBUILD_MODNAME, sizeof(vdev->name));
+	strscpy(vdev->name, KBUILD_MODNAME, sizeof(vdev->name));
 	/*
 	 * There is nothing to clean up, so release is set to an empty release
 	 * function. The release callback must be non-NULL.
diff --git a/samples/vfio-mdev/mtty.c b/samples/vfio-mdev/mtty.c
index 69ba0281f9e0..2284b3751240 100644
--- a/samples/vfio-mdev/mtty.c
+++ b/samples/vfio-mdev/mtty.c
@@ -234,10 +234,10 @@ static void mtty_trigger_interrupt(struct mdev_state *mdev_state)
 
 	if (is_msi(mdev_state)) {
 		if (mdev_state->msi_evtfd)
-			eventfd_signal(mdev_state->msi_evtfd, 1);
+			eventfd_signal(mdev_state->msi_evtfd);
 	} else if (is_intx(mdev_state)) {
 		if (mdev_state->intx_evtfd && !mdev_state->intx_mask) {
-			eventfd_signal(mdev_state->intx_evtfd, 1);
+			eventfd_signal(mdev_state->intx_evtfd);
 			mdev_state->intx_mask = true;
 		}
 	}
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 9a3063735e71..dae447a1ad30 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -275,6 +275,7 @@ rust_common_cmd = \
 	--extern alloc --extern kernel \
 	--crate-type rlib -L $(objtree)/rust/ \
 	--crate-name $(basename $(notdir $@)) \
+	--sysroot=/dev/null \
 	--out-dir $(dir $@) --emit=dep-info=$(depfile)
 
 # `--emit=obj`, `--emit=asm` and `--emit=llvm-ir` imply a single codegen unit
diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn
index 2fe6f2828d37..c9725685aa76 100644
--- a/scripts/Makefile.extrawarn
+++ b/scripts/Makefile.extrawarn
@@ -17,6 +17,8 @@ KBUILD_CFLAGS += -Wno-format-security
 KBUILD_CFLAGS += -Wno-trigraphs
 KBUILD_CFLAGS += $(call cc-disable-warning,frame-address,)
 KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
+KBUILD_CFLAGS += -Wmissing-declarations
+KBUILD_CFLAGS += -Wmissing-prototypes
 
 ifneq ($(CONFIG_FRAME_WARN),0)
 KBUILD_CFLAGS += -Wframe-larger-than=$(CONFIG_FRAME_WARN)
@@ -95,10 +97,8 @@ export KBUILD_EXTRA_WARN
 ifneq ($(findstring 1, $(KBUILD_EXTRA_WARN)),)
 
 KBUILD_CFLAGS += -Wextra -Wunused -Wno-unused-parameter
-KBUILD_CFLAGS += -Wmissing-declarations
 KBUILD_CFLAGS += $(call cc-option, -Wrestrict)
 KBUILD_CFLAGS += -Wmissing-format-attribute
-KBUILD_CFLAGS += -Wmissing-prototypes
 KBUILD_CFLAGS += -Wold-style-definition
 KBUILD_CFLAGS += -Wmissing-include-dirs
 KBUILD_CFLAGS += $(call cc-option, -Wunused-but-set-variable)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 68d0134bdbf9..1a965fe68e01 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -487,14 +487,14 @@ UIMAGE_OPTS-y ?=
 UIMAGE_TYPE ?= kernel
 UIMAGE_LOADADDR ?= arch_must_set_this
 UIMAGE_ENTRYADDR ?= $(UIMAGE_LOADADDR)
-UIMAGE_NAME ?= 'Linux-$(KERNELRELEASE)'
+UIMAGE_NAME ?= Linux-$(KERNELRELEASE)
 
 quiet_cmd_uimage = UIMAGE  $@
       cmd_uimage = $(BASH) $(MKIMAGE) -A $(UIMAGE_ARCH) -O linux \
 			-C $(UIMAGE_COMPRESSION) $(UIMAGE_OPTS-y) \
 			-T $(UIMAGE_TYPE) \
 			-a $(UIMAGE_LOADADDR) -e $(UIMAGE_ENTRYADDR) \
-			-n $(UIMAGE_NAME) -d $< $@
+			-n '$(UIMAGE_NAME)' -d $< $@
 
 # XZ
 # ---------------------------------------------------------------------------
diff --git a/scripts/Makefile.vdsoinst b/scripts/Makefile.vdsoinst
index 1022d9fdd976..c477d17b0aa5 100644
--- a/scripts/Makefile.vdsoinst
+++ b/scripts/Makefile.vdsoinst
@@ -22,7 +22,7 @@ $$(dest): $$(src) FORCE
 
 # Some architectures create .build-id symlinks
 ifneq ($(filter arm sparc x86, $(SRCARCH)),)
-link := $(install-dir)/.build-id/$$(shell $(READELF) -n $$(src) | sed -n 's@^.*Build ID: \(..\)\(.*\)@\1/\2@p')
+link := $(install-dir)/.build-id/$$(shell $(READELF) -n $$(src) | sed -n 's@^.*Build ID: \(..\)\(.*\)@\1/\2@p').debug
 
 __default: $$(link)
 $$(link): $$(dest) FORCE
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 25fdb7fda112..f8343b34a28b 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -4054,7 +4054,7 @@ sub process {
 		if ($prevline =~ /^[\+ ]};?\s*$/ &&
 		    $line =~ /^\+/ &&
 		    !($line =~ /^\+\s*$/ ||
-		      $line =~ /^\+\s*(?:EXPORT_SYMBOL|early_param)/ ||
+		      $line =~ /^\+\s*(?:EXPORT_SYMBOL|early_param|ALLOW_ERROR_INJECTION)/ ||
 		      $line =~ /^\+\s*MODULE_/i ||
 		      $line =~ /^\+\s*\#\s*(?:end|elif|else)/ ||
 		      $line =~ /^\+[a-z_]*init/ ||
@@ -7011,6 +7011,25 @@ sub process {
 			     "Prefer strscpy, strscpy_pad, or __nonstring over strncpy - see: https://github.com/KSPP/linux/issues/90\n" . $herecurr);
 		}
 
+# ethtool_sprintf uses that should likely be ethtool_puts
+		if ($line =~ /\bethtool_sprintf\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\)/) {
+			if (WARN("PREFER_ETHTOOL_PUTS",
+				 "Prefer ethtool_puts over ethtool_sprintf with only two arguments\n" . $herecurr) &&
+			    $fix) {
+				$fixed[$fixlinenr] =~ s/\bethtool_sprintf\s*\(\s*($FuncArg)\s*,\s*($FuncArg)/ethtool_puts($1, $7)/;
+			}
+		}
+
+		# use $rawline because $line loses %s via sanitization and thus we can't match against it.
+		if ($rawline =~ /\bethtool_sprintf\s*\(\s*$FuncArg\s*,\s*\"\%s\"\s*,\s*$FuncArg\s*\)/) {
+			if (WARN("PREFER_ETHTOOL_PUTS",
+				 "Prefer ethtool_puts over ethtool_sprintf with standalone \"%s\" specifier\n" . $herecurr) &&
+			    $fix) {
+				$fixed[$fixlinenr] =~ s/\bethtool_sprintf\s*\(\s*($FuncArg)\s*,\s*"\%s"\s*,\s*($FuncArg)/ethtool_puts($1, $7)/;
+			}
+		}
+
+
 # typecasts on min/max could be min_t/max_t
 		if ($perl_version_ok &&
 		    defined $stat &&
diff --git a/scripts/checkstack.pl b/scripts/checkstack.pl
index 84f5fb7f1cec..14ce31f732ee 100755
--- a/scripts/checkstack.pl
+++ b/scripts/checkstack.pl
@@ -8,7 +8,6 @@
 #	Original idea maybe from Keith Owens
 #	s390 port and big speedup by Arnd Bergmann <arnd@bergmann-dalldorf.de>
 #	Mips port by Juan Quintela <quintela@mandrakesoft.com>
-#	IA64 port via Andreas Dilger
 #	Arm port by Holger Schurig
 #	Random bits by Matt Mackall <mpm@selenic.com>
 #	M68k port by Geert Uytterhoeven and Andreas Schwab
@@ -16,9 +15,10 @@
 #	sparc port by Martin Habets <errandir_news@mph.eclipse.co.uk>
 #	ppc64le port by Breno Leitao <leitao@debian.org>
 #	riscv port by Wadim Mueller <wafgo01@gmail.com>
+#	loongarch port by Youling Tang <tangyouling@kylinos.cn>
 #
 #	Usage:
-#	objdump -d vmlinux | scripts/checkstack.pl [arch]
+#	objdump -d vmlinux | scripts/checkstack.pl [arch] [min_stack]
 #
 #	TODO :	Port to all architectures (one regex per arch)
 
@@ -47,7 +47,7 @@ my (@stack, $re, $dre, $sub, $x, $xs, $funcre, $min_stack);
 
 	$min_stack = shift;
 	if ($min_stack eq "" || $min_stack !~ /^\d+$/) {
-		$min_stack = 100;
+		$min_stack = 512;
 	}
 
 	$x	= "[0-9a-f]";	# hex character
@@ -56,7 +56,7 @@ my (@stack, $re, $dre, $sub, $x, $xs, $funcre, $min_stack);
 	if ($arch =~ '^(aarch|arm)64$') {
 		#ffffffc0006325cc:       a9bb7bfd        stp     x29, x30, [sp, #-80]!
 		#a110:       d11643ff        sub     sp, sp, #0x590
-		$re = qr/^.*stp.*sp, \#-([0-9]{1,8})\]\!/o;
+		$re = qr/^.*stp.*sp, ?\#-([0-9]{1,8})\]\!/o;
 		$dre = qr/^.*sub.*sp, sp, #(0x$x{1,8})/o;
 	} elsif ($arch eq 'arm') {
 		#c0008ffc:	e24dd064	sub	sp, sp, #100	; 0x64
@@ -68,25 +68,22 @@ my (@stack, $re, $dre, $sub, $x, $xs, $funcre, $min_stack);
 		#    2f60:    48 81 ec e8 05 00 00       sub    $0x5e8,%rsp
 		$re = qr/^.*[as][du][db]    \$(0x$x{1,8}),\%(e|r)sp$/o;
 		$dre = qr/^.*[as][du][db]    (%.*),\%(e|r)sp$/o;
-	} elsif ($arch eq 'ia64') {
-		#e0000000044011fc:       01 0f fc 8c     adds r12=-384,r12
-		$re = qr/.*adds.*r12=-(([0-9]{2}|[3-9])[0-9]{2}),r12/o;
 	} elsif ($arch eq 'm68k') {
 		#    2b6c:       4e56 fb70       linkw %fp,#-1168
 		#  1df770:       defc ffe4       addaw #-28,%sp
 		$re = qr/.*(?:linkw %fp,|addaw )#-([0-9]{1,4})(?:,%sp)?$/o;
 	} elsif ($arch eq 'mips64') {
 		#8800402c:       67bdfff0        daddiu  sp,sp,-16
-		$re = qr/.*daddiu.*sp,sp,-(([0-9]{2}|[3-9])[0-9]{2})/o;
+		$re = qr/.*daddiu.*sp,sp,-([0-9]{1,8})/o;
 	} elsif ($arch eq 'mips') {
 		#88003254:       27bdffe0        addiu   sp,sp,-32
-		$re = qr/.*addiu.*sp,sp,-(([0-9]{2}|[3-9])[0-9]{2})/o;
+		$re = qr/.*addiu.*sp,sp,-([0-9]{1,8})/o;
 	} elsif ($arch eq 'nios2') {
 		#25a8:	defffb04 	addi	sp,sp,-20
-		$re = qr/.*addi.*sp,sp,-(([0-9]{2}|[3-9])[0-9]{2})/o;
+		$re = qr/.*addi.*sp,sp,-([0-9]{1,8})/o;
 	} elsif ($arch eq 'openrisc') {
 		# c000043c:       9c 21 fe f0     l.addi r1,r1,-272
-		$re = qr/.*l\.addi.*r1,r1,-(([0-9]{2}|[3-9])[0-9]{2})/o;
+		$re = qr/.*l\.addi.*r1,r1,-([0-9]{1,8})/o;
 	} elsif ($arch eq 'parisc' || $arch eq 'parisc64') {
 		$re = qr/.*ldo ($x{1,8})\(sp\),sp/o;
 	} elsif ($arch eq 'powerpc' || $arch =~ /^ppc(64)?(le)?$/ ) {
@@ -97,14 +94,16 @@ my (@stack, $re, $dre, $sub, $x, $xs, $funcre, $min_stack);
 		#   11160:       a7 fb ff 60             aghi   %r15,-160
 		# or
 		#  100092:	 e3 f0 ff c8 ff 71	 lay	 %r15,-56(%r15)
-		$re = qr/.*(?:lay|ag?hi).*\%r15,-(([0-9]{2}|[3-9])[0-9]{2})
-		      (?:\(\%r15\))?$/ox;
+		$re = qr/.*(?:lay|ag?hi).*\%r15,-([0-9]+)(?:\(\%r15\))?$/o;
 	} elsif ($arch eq 'sparc' || $arch eq 'sparc64') {
 		# f0019d10:       9d e3 bf 90     save  %sp, -112, %sp
-		$re = qr/.*save.*%sp, -(([0-9]{2}|[3-9])[0-9]{2}), %sp/o;
+		$re = qr/.*save.*%sp, -([0-9]{1,8}), %sp/o;
 	} elsif ($arch =~ /^riscv(64)?$/) {
 		#ffffffff8036e868:	c2010113          	addi	sp,sp,-992
-		$re = qr/.*addi.*sp,sp,-(([0-9]{2}|[3-9])[0-9]{2})/o;
+		$re = qr/.*addi.*sp,sp,-([0-9]{1,8})/o;
+	} elsif ($arch =~ /^loongarch(32|64)?$/) {
+		#9000000000224708:	02ff4063		addi.d  $sp, $sp, -48(0xfd0)
+		$re = qr/.*addi\..*sp, .*sp, -([0-9]{1,8}).*/o;
 	} else {
 		print("wrong or unknown architecture \"$arch\"\n");
 		exit
@@ -139,15 +138,11 @@ $total_size = 0;
 while (my $line = <STDIN>) {
 	if ($line =~ m/$funcre/) {
 		$func = $1;
-		next if $line !~ m/^($xs*)/;
+		next if $line !~ m/^($x*)/;
 		if ($total_size > $min_stack) {
 			push @stack, "$intro$total_size\n";
 		}
-
-		$addr = $1;
-		$addr =~ s/ /0/g;
-		$addr = "0x$addr";
-
+		$addr = "0x$1";
 		$intro = "$addr $func [$file]:";
 		my $padlen = 56 - length($intro);
 		while ($padlen > 0) {
@@ -194,5 +189,20 @@ if ($total_size > $min_stack) {
 	push @stack, "$intro$total_size\n";
 }
 
-# Sort output by size (last field)
-print sort { ($b =~ /:\t*(\d+)$/)[0] <=> ($a =~ /:\t*(\d+)$/)[0] } @stack;
+# Sort output by size (last field) and function name if size is the same
+sub sort_lines {
+	my ($a, $b) = @_;
+
+	my $num_a = $1 if $a =~ /:\t*(\d+)$/;
+	my $num_b = $1 if $b =~ /:\t*(\d+)$/;
+	my $func_a = $1 if $a =~ / (.*):/;
+	my $func_b = $1 if $b =~ / (.*):/;
+
+	if ($num_a != $num_b) {
+		return $num_b <=> $num_a;
+	} else {
+		return $func_a cmp $func_b;
+	}
+}
+
+print sort { sort_lines($a, $b) } @stack;
diff --git a/scripts/clang-tools/gen_compile_commands.py b/scripts/clang-tools/gen_compile_commands.py
index 180952fb91c1..5dea4479240b 100755
--- a/scripts/clang-tools/gen_compile_commands.py
+++ b/scripts/clang-tools/gen_compile_commands.py
@@ -64,7 +64,7 @@ def parse_arguments():
     args = parser.parse_args()
 
     return (args.log_level,
-            os.path.abspath(args.directory),
+            os.path.realpath(args.directory),
             args.output,
             args.ar,
             args.paths if len(args.paths) > 0 else [args.directory])
@@ -172,8 +172,8 @@ def process_line(root_directory, command_prefix, file_path):
     # by Make, so this code replaces the escaped version with '#'.
     prefix = command_prefix.replace('\#', '#').replace('$(pound)', '#')
 
-    # Use os.path.abspath() to normalize the path resolving '.' and '..' .
-    abs_path = os.path.abspath(os.path.join(root_directory, file_path))
+    # Return the canonical path, eliminating any symbolic links encountered in the path.
+    abs_path = os.path.realpath(os.path.join(root_directory, file_path))
     if not os.path.exists(abs_path):
         raise ValueError('File %s not found' % abs_path)
     return {
diff --git a/scripts/decode_stacktrace.sh b/scripts/decode_stacktrace.sh
index 564c5632e1a2..cb980b144ca1 100755
--- a/scripts/decode_stacktrace.sh
+++ b/scripts/decode_stacktrace.sh
@@ -291,6 +291,9 @@ handle_line() {
 }
 
 while read line; do
+	# Strip unexpected carriage return at end of line
+	line=${line%$'\r'}
+
 	# Let's see if we have an address in the line
 	if [[ $line =~ \[\<([^]]+)\>\] ]] ||
 	   [[ $line =~ [^+\ ]+\+0x[0-9a-f]+/0x[0-9a-f]+ ]]; then
diff --git a/scripts/decodecode b/scripts/decodecode
index 8fe71c292381..6364218b2178 100755
--- a/scripts/decodecode
+++ b/scripts/decodecode
@@ -67,6 +67,7 @@ if [ -z "$ARCH" ]; then
     case `uname -m` in
 	aarch64*) ARCH=arm64 ;;
 	arm*) ARCH=arm ;;
+	loongarch*) ARCH=loongarch ;;
     esac
 fi
 
@@ -98,6 +99,10 @@ disas() {
 		${CROSS_COMPILE}strip $t.o
 	fi
 
+	if [ "$ARCH" = "loongarch" ]; then
+		${CROSS_COMPILE}strip $t.o
+	fi
+
 	if [ $pc_sub -ne 0 ]; then
 		if [ $PC ]; then
 			adj_vma=$(( $PC - $pc_sub ))
diff --git a/scripts/dtc/dt-extract-compatibles b/scripts/dtc/dt-extract-compatibles
index bd07477dd144..5ffb2364409b 100755
--- a/scripts/dtc/dt-extract-compatibles
+++ b/scripts/dtc/dt-extract-compatibles
@@ -1,8 +1,8 @@
 #!/usr/bin/env python3
 # SPDX-License-Identifier: GPL-2.0-only
 
+import fnmatch
 import os
-import glob
 import re
 import argparse
 
@@ -81,10 +81,20 @@ def print_compat(filename, compatibles):
 	else:
 		print(*compatibles, sep='\n')
 
+def glob_without_symlinks(root, glob):
+	for path, dirs, files in os.walk(root):
+		# Ignore hidden directories
+		for d in dirs:
+			if fnmatch.fnmatch(d, ".*"):
+				dirs.remove(d)
+		for f in files:
+			if fnmatch.fnmatch(f, glob):
+				yield os.path.join(path, f)
+
 def files_to_parse(path_args):
 	for f in path_args:
 		if os.path.isdir(f):
-			for filename in glob.iglob(f + "/**/*.c", recursive=True):
+			for filename in glob_without_symlinks(f, "*.c"):
 				yield filename
 		else:
 			yield f
diff --git a/scripts/gcc-plugins/latent_entropy_plugin.c b/scripts/gcc-plugins/latent_entropy_plugin.c
index 39e86be60dd2..ff0b192be91f 100644
--- a/scripts/gcc-plugins/latent_entropy_plugin.c
+++ b/scripts/gcc-plugins/latent_entropy_plugin.c
@@ -17,7 +17,7 @@
  *	if (argc <= 1)
  *		printf("%s: no command arguments :(\n", *argv);
  *	else
- *		printf("%s: %d command arguments!\n", *argv, args - 1);
+ *		printf("%s: %d command arguments!\n", *argv, argc - 1);
  * }
  *
  * after:
@@ -47,7 +47,7 @@
  *		// perturb_local_entropy()
  *	} else {
  *		local_entropy ^= 3896280633962944730;
- *		printf("%s: %d command arguments!\n", *argv, args - 1);
+ *		printf("%s: %d command arguments!\n", *argv, argc - 1);
  *	}
  *
  *	// latent_entropy_execute() 4.
diff --git a/scripts/gcc-plugins/randomize_layout_plugin.c b/scripts/gcc-plugins/randomize_layout_plugin.c
index 366395cab490..746ff2d272f2 100644
--- a/scripts/gcc-plugins/randomize_layout_plugin.c
+++ b/scripts/gcc-plugins/randomize_layout_plugin.c
@@ -278,8 +278,6 @@ static bool is_flexible_array(const_tree field)
 {
 	const_tree fieldtype;
 	const_tree typesize;
-	const_tree elemtype;
-	const_tree elemsize;
 
 	fieldtype = TREE_TYPE(field);
 	typesize = TYPE_SIZE(fieldtype);
@@ -287,20 +285,12 @@ static bool is_flexible_array(const_tree field)
 	if (TREE_CODE(fieldtype) != ARRAY_TYPE)
 		return false;
 
-	elemtype = TREE_TYPE(fieldtype);
-	elemsize = TYPE_SIZE(elemtype);
-
 	/* size of type is represented in bits */
 
 	if (typesize == NULL_TREE && TYPE_DOMAIN(fieldtype) != NULL_TREE &&
 	    TYPE_MAX_VALUE(TYPE_DOMAIN(fieldtype)) == NULL_TREE)
 		return true;
 
-	if (typesize != NULL_TREE &&
-	    (TREE_CONSTANT(typesize) && (!tree_to_uhwi(typesize) ||
-	     tree_to_uhwi(typesize) == tree_to_uhwi(elemsize))))
-		return true;
-
 	return false;
 }
 
@@ -349,8 +339,7 @@ static int relayout_struct(tree type)
 
 	/*
 	 * enforce that we don't randomize the layout of the last
-	 * element of a struct if it's a 0 or 1-length array
-	 * or a proper flexible array
+	 * element of a struct if it's a proper flexible array
 	 */
 	if (is_flexible_array(newtree[num_fields - 1])) {
 		has_flexarray = true;
diff --git a/scripts/gdb/linux/device.py b/scripts/gdb/linux/device.py
index 16376c5cfec6..0eabc5f4f8ca 100644
--- a/scripts/gdb/linux/device.py
+++ b/scripts/gdb/linux/device.py
@@ -36,26 +36,26 @@ def for_each_bus():
     for kobj in kset_for_each_object(gdb.parse_and_eval('bus_kset')):
         subsys = container_of(kobj, kset_type.get_type().pointer(), 'kobj')
         subsys_priv = container_of(subsys, subsys_private_type.get_type().pointer(), 'subsys')
-        yield subsys_priv['bus']
+        yield subsys_priv
 
 
 def for_each_class():
     for kobj in kset_for_each_object(gdb.parse_and_eval('class_kset')):
         subsys = container_of(kobj, kset_type.get_type().pointer(), 'kobj')
         subsys_priv = container_of(subsys, subsys_private_type.get_type().pointer(), 'subsys')
-        yield subsys_priv['class']
+        yield subsys_priv
 
 
 def get_bus_by_name(name):
     for item in for_each_bus():
-        if item['name'].string() == name:
+        if item['bus']['name'].string() == name:
             return item
     raise gdb.GdbError("Can't find bus type {!r}".format(name))
 
 
 def get_class_by_name(name):
     for item in for_each_class():
-        if item['name'].string() == name:
+        if item['class']['name'].string() == name:
             return item
     raise gdb.GdbError("Can't find device class {!r}".format(name))
 
@@ -70,13 +70,13 @@ def klist_for_each(klist):
 
 
 def bus_for_each_device(bus):
-    for kn in klist_for_each(bus['p']['klist_devices']):
+    for kn in klist_for_each(bus['klist_devices']):
         dp = container_of(kn, device_private_type.get_type().pointer(), 'knode_bus')
         yield dp['device']
 
 
 def class_for_each_device(cls):
-    for kn in klist_for_each(cls['p']['klist_devices']):
+    for kn in klist_for_each(cls['klist_devices']):
         dp = container_of(kn, device_private_type.get_type().pointer(), 'knode_class')
         yield dp['device']
 
@@ -103,7 +103,7 @@ class LxDeviceListBus(gdb.Command):
     def invoke(self, arg, from_tty):
         if not arg:
             for bus in for_each_bus():
-                gdb.write('bus {}:\t{}\n'.format(bus['name'].string(), bus))
+                gdb.write('bus {}:\t{}\n'.format(bus['bus']['name'].string(), bus))
                 for dev in bus_for_each_device(bus):
                     _show_device(dev, level=1)
         else:
@@ -123,7 +123,7 @@ class LxDeviceListClass(gdb.Command):
     def invoke(self, arg, from_tty):
         if not arg:
             for cls in for_each_class():
-                gdb.write("class {}:\t{}\n".format(cls['name'].string(), cls))
+                gdb.write("class {}:\t{}\n".format(cls['class']['name'].string(), cls))
                 for dev in class_for_each_device(cls):
                     _show_device(dev, level=1)
         else:
diff --git a/scripts/gdb/linux/page_owner.py b/scripts/gdb/linux/page_owner.py
index 844fd5d0c912..8e713a09cfe7 100644
--- a/scripts/gdb/linux/page_owner.py
+++ b/scripts/gdb/linux/page_owner.py
@@ -122,27 +122,24 @@ class DumpPageOwner(gdb.Command):
         if not (page_ext['flags'] & (1 << PAGE_EXT_OWNER_ALLOCATED)):
             gdb.write("page_owner is not allocated\n")
 
-        try:
-            page_owner = self.get_page_owner(page_ext)
-            gdb.write("Page last allocated via order %d, gfp_mask: 0x%x, pid: %d, tgid: %d (%s), ts %u ns, free_ts %u ns\n" %\
-                    (page_owner["order"], page_owner["gfp_mask"],\
-                    page_owner["pid"], page_owner["tgid"], page_owner["comm"],\
-                    page_owner["ts_nsec"], page_owner["free_ts_nsec"]))
-            gdb.write("PFN: %d, Flags: 0x%x\n" % (pfn, page['flags']))
-            if page_owner["handle"] == 0:
-                gdb.write('page_owner allocation stack trace missing\n')
-            else:
-                stackdepot.stack_depot_print(page_owner["handle"])
+        page_owner = self.get_page_owner(page_ext)
+        gdb.write("Page last allocated via order %d, gfp_mask: 0x%x, pid: %d, tgid: %d (%s), ts %u ns, free_ts %u ns\n" %\
+                (page_owner["order"], page_owner["gfp_mask"],\
+                page_owner["pid"], page_owner["tgid"], page_owner["comm"].string(),\
+                page_owner["ts_nsec"], page_owner["free_ts_nsec"]))
+        gdb.write("PFN: %d, Flags: 0x%x\n" % (pfn, page['flags']))
+        if page_owner["handle"] == 0:
+            gdb.write('page_owner allocation stack trace missing\n')
+        else:
+            stackdepot.stack_depot_print(page_owner["handle"])
 
-            if page_owner["free_handle"] == 0:
-                gdb.write('page_owner free stack trace missing\n')
-            else:
-                gdb.write('page last free stack trace:\n')
-                stackdepot.stack_depot_print(page_owner["free_handle"])
-            if page_owner['last_migrate_reason'] != -1:
-                gdb.write('page has been migrated, last migrate reason: %s\n' % self.migrate_reason_names[page_owner['last_migrate_reason']])
-        except:
-            gdb.write("\n")
+        if page_owner["free_handle"] == 0:
+            gdb.write('page_owner free stack trace missing\n')
+        else:
+            gdb.write('page last free stack trace:\n')
+            stackdepot.stack_depot_print(page_owner["free_handle"])
+        if page_owner['last_migrate_reason'] != -1:
+            gdb.write('page has been migrated, last migrate reason: %s\n' % self.migrate_reason_names[page_owner['last_migrate_reason']])
 
     def read_page_owner(self):
         pfn = self.min_pfn
@@ -173,18 +170,13 @@ class DumpPageOwner(gdb.Command):
                 pfn += 1
                 continue
 
-            try:
-                page_owner = self.get_page_owner(page_ext)
-                gdb.write("Page allocated via order %d, gfp_mask: 0x%x, pid: %d, tgid: %d (%s), ts %u ns, free_ts %u ns\n" %\
-                        (page_owner["order"], page_owner["gfp_mask"],\
-                        page_owner["pid"], page_owner["tgid"], page_owner["comm"],\
-                        page_owner["ts_nsec"], page_owner["free_ts_nsec"]))
-                gdb.write("PFN: %d, Flags: 0x%x\n" % (pfn, page['flags']))
-                stackdepot.stack_depot_print(page_owner["handle"])
-                pfn += (1 << page_owner["order"])
-                continue
-            except:
-                gdb.write("\n")
-            pfn += 1
+            page_owner = self.get_page_owner(page_ext)
+            gdb.write("Page allocated via order %d, gfp_mask: 0x%x, pid: %d, tgid: %d (%s), ts %u ns, free_ts %u ns\n" %\
+                    (page_owner["order"], page_owner["gfp_mask"],\
+                    page_owner["pid"], page_owner["tgid"], page_owner["comm"].string(),\
+                    page_owner["ts_nsec"], page_owner["free_ts_nsec"]))
+            gdb.write("PFN: %d, Flags: 0x%x\n" % (pfn, page['flags']))
+            stackdepot.stack_depot_print(page_owner["handle"])
+            pfn += (1 << page_owner["order"])
 
 DumpPageOwner()
diff --git a/scripts/gdb/linux/slab.py b/scripts/gdb/linux/slab.py
index f012ba38c7d9..0e2d93867fe2 100644
--- a/scripts/gdb/linux/slab.py
+++ b/scripts/gdb/linux/slab.py
@@ -228,8 +228,7 @@ def slabtrace(alloc, cache_name):
             nr_cpu = gdb.parse_and_eval('__num_online_cpus')['counter']
             if nr_cpu > 1:
                 gdb.write(" cpus=")
-                for i in loc['cpus']:
-                    gdb.write("%d," % i)
+                gdb.write(','.join(str(cpu) for cpu in loc['cpus']))
         gdb.write("\n")
         if constants.LX_CONFIG_STACKDEPOT:
             if loc['handle']:
diff --git a/scripts/gdb/linux/stackdepot.py b/scripts/gdb/linux/stackdepot.py
index 047d329a6a12..0281d9de4b7c 100644
--- a/scripts/gdb/linux/stackdepot.py
+++ b/scripts/gdb/linux/stackdepot.py
@@ -25,10 +25,10 @@ def stack_depot_fetch(handle):
     handle_parts_t = gdb.lookup_type("union handle_parts")
     parts = handle.cast(handle_parts_t)
     offset = parts['offset'] << DEPOT_STACK_ALIGN
-    pool_index_cached = gdb.parse_and_eval('pool_index')
+    pools_num = gdb.parse_and_eval('pools_num')
 
-    if parts['pool_index'] > pool_index_cached:
-        gdb.write("pool index %d out of bounds (%d) for stack id 0x%08x\n" % (parts['pool_index'], pool_index_cached, handle))
+    if parts['pool_index'] > pools_num:
+        gdb.write("pool index %d out of bounds (%d) for stack id 0x%08x\n" % (parts['pool_index'], pools_num, handle))
         return gdb.Value(0), 0
 
     stack_pools = gdb.parse_and_eval('stack_pools')
diff --git a/scripts/gdb/linux/tasks.py b/scripts/gdb/linux/tasks.py
index 17ec19e9b5bf..aa5ab6251f76 100644
--- a/scripts/gdb/linux/tasks.py
+++ b/scripts/gdb/linux/tasks.py
@@ -13,7 +13,7 @@
 
 import gdb
 
-from linux import utils
+from linux import utils, lists
 
 
 task_type = utils.CachedType("struct task_struct")
@@ -22,19 +22,15 @@ task_type = utils.CachedType("struct task_struct")
 def task_lists():
     task_ptr_type = task_type.get_type().pointer()
     init_task = gdb.parse_and_eval("init_task").address
-    t = g = init_task
+    t = init_task
 
     while True:
-        while True:
-            yield t
+        thread_head = t['signal']['thread_head']
+        for thread in lists.list_for_each_entry(thread_head, task_ptr_type, 'thread_node'):
+            yield thread
 
-            t = utils.container_of(t['thread_group']['next'],
-                                   task_ptr_type, "thread_group")
-            if t == g:
-                break
-
-        t = g = utils.container_of(g['tasks']['next'],
-                                   task_ptr_type, "tasks")
+        t = utils.container_of(t['tasks']['next'],
+                               task_ptr_type, "tasks")
         if t == init_task:
             return
 
diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl
index 16d8ac6005b6..ee1aed7e090c 100755
--- a/scripts/get_maintainer.pl
+++ b/scripts/get_maintainer.pl
@@ -20,6 +20,7 @@ use Getopt::Long qw(:config no_auto_abbrev);
 use Cwd;
 use File::Find;
 use File::Spec::Functions;
+use open qw(:std :encoding(UTF-8));
 
 my $cur_path = fastgetcwd() . '/';
 my $lk_path = "./";
@@ -445,7 +446,7 @@ sub maintainers_in_file {
 	my $text = do { local($/) ; <$f> };
 	close($f);
 
-	my @poss_addr = $text =~ m$[A-Za-zÀ-ÿ\"\' \,\.\+-]*\s*[\,]*\s*[\(\<\{]{0,1}[A-Za-z0-9_\.\+-]+\@[A-Za-z0-9\.-]+\.[A-Za-z0-9]+[\)\>\}]{0,1}$g;
+	my @poss_addr = $text =~ m$[\p{L}\"\' \,\.\+-]*\s*[\,]*\s*[\(\<\{]{0,1}[A-Za-z0-9_\.\+-]+\@[A-Za-z0-9\.-]+\.[A-Za-z0-9]+[\)\>\}]{0,1}$g;
 	push(@file_emails, clean_file_emails(@poss_addr));
     }
 }
@@ -1152,6 +1153,17 @@ sub top_of_kernel_tree {
     return 0;
 }
 
+sub escape_name {
+    my ($name) = @_;
+
+    if ($name =~ /[^\w \-]/ai) {  	 ##has "must quote" chars
+	$name =~ s/(?<!\\)"/\\"/g;       ##escape quotes
+	$name = "\"$name\"";
+    }
+
+    return $name;
+}
+
 sub parse_email {
     my ($formatted_email) = @_;
 
@@ -1169,13 +1181,9 @@ sub parse_email {
 
     $name =~ s/^\s+|\s+$//g;
     $name =~ s/^\"|\"$//g;
+    $name = escape_name($name);
     $address =~ s/^\s+|\s+$//g;
 
-    if ($name =~ /[^\w \-]/i) {  	 ##has "must quote" chars
-	$name =~ s/(?<!\\)"/\\"/g;       ##escape quotes
-	$name = "\"$name\"";
-    }
-
     return ($name, $address);
 }
 
@@ -1186,13 +1194,9 @@ sub format_email {
 
     $name =~ s/^\s+|\s+$//g;
     $name =~ s/^\"|\"$//g;
+    $name = escape_name($name);
     $address =~ s/^\s+|\s+$//g;
 
-    if ($name =~ /[^\w \-]/i) {          ##has "must quote" chars
-	$name =~ s/(?<!\\)"/\\"/g;       ##escape quotes
-	$name = "\"$name\"";
-    }
-
     if ($usename) {
 	if ("$name" eq "") {
 	    $formatted_email = "$address";
@@ -2458,17 +2462,23 @@ sub clean_file_emails {
     foreach my $email (@file_emails) {
 	$email =~ s/[\(\<\{]{0,1}([A-Za-z0-9_\.\+-]+\@[A-Za-z0-9\.-]+)[\)\>\}]{0,1}/\<$1\>/g;
 	my ($name, $address) = parse_email($email);
-	if ($name eq '"[,\.]"') {
-	    $name = "";
-	}
 
-	my @nw = split(/[^A-Za-zÀ-ÿ\'\,\.\+-]/, $name);
+	# Strip quotes for easier processing, format_email will add them back
+	$name =~ s/^"(.*)"$/$1/;
+
+	# Split into name-like parts and remove stray punctuation particles
+	my @nw = split(/[^\p{L}\'\,\.\+-]/, $name);
+	@nw = grep(!/^[\'\,\.\+-]$/, @nw);
+
+	# Make a best effort to extract the name, and only the name, by taking
+	# only the last two names, or in the case of obvious initials, the last
+	# three names.
 	if (@nw > 2) {
 	    my $first = $nw[@nw - 3];
 	    my $middle = $nw[@nw - 2];
 	    my $last = $nw[@nw - 1];
 
-	    if (((length($first) == 1 && $first =~ m/[A-Za-z]/) ||
+	    if (((length($first) == 1 && $first =~ m/\p{L}/) ||
 		 (length($first) == 2 && substr($first, -1) eq ".")) ||
 		(length($middle) == 1 ||
 		 (length($middle) == 2 && substr($middle, -1) eq "."))) {
@@ -2476,18 +2486,16 @@ sub clean_file_emails {
 	    } else {
 		$name = "$middle $last";
 	    }
+	} else {
+	    $name = "@nw";
 	}
 
 	if (substr($name, -1) =~ /[,\.]/) {
 	    $name = substr($name, 0, length($name) - 1);
-	} elsif (substr($name, -2) =~ /[,\.]"/) {
-	    $name = substr($name, 0, length($name) - 2) . '"';
 	}
 
 	if (substr($name, 0, 1) =~ /[,\.]/) {
 	    $name = substr($name, 1, length($name) - 1);
-	} elsif (substr($name, 0, 2) =~ /"[,\.]/) {
-	    $name = '"' . substr($name, 2, length($name) - 2);
 	}
 
 	my $fmt_email = format_email($name, $address, $email_usename);
diff --git a/scripts/headers_install.sh b/scripts/headers_install.sh
index c3064ac31003..f7d9b114de8f 100755
--- a/scripts/headers_install.sh
+++ b/scripts/headers_install.sh
@@ -74,7 +74,6 @@ arch/arc/include/uapi/asm/page.h:CONFIG_ARC_PAGE_SIZE_16K
 arch/arc/include/uapi/asm/page.h:CONFIG_ARC_PAGE_SIZE_4K
 arch/arc/include/uapi/asm/swab.h:CONFIG_ARC_HAS_SWAPE
 arch/arm/include/uapi/asm/ptrace.h:CONFIG_CPU_ENDIAN_BE8
-arch/hexagon/include/uapi/asm/user.h:CONFIG_HEXAGON_ARCH_VERSION
 arch/m68k/include/uapi/asm/ptrace.h:CONFIG_COLDFIRE
 arch/nios2/include/uapi/asm/swab.h:CONFIG_NIOS2_CI_SWAB_NO
 arch/nios2/include/uapi/asm/swab.h:CONFIG_NIOS2_CI_SWAB_SUPPORT
diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index 0572330bf8a7..a76925b46ce6 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -122,9 +122,9 @@ static long long sym_get_range_val(struct symbol *sym, int base)
 static void sym_validate_range(struct symbol *sym)
 {
 	struct property *prop;
+	struct symbol *range_sym;
 	int base;
 	long long val, val2;
-	char str[64];
 
 	switch (sym->type) {
 	case S_INT:
@@ -140,17 +140,15 @@ static void sym_validate_range(struct symbol *sym)
 	if (!prop)
 		return;
 	val = strtoll(sym->curr.val, NULL, base);
-	val2 = sym_get_range_val(prop->expr->left.sym, base);
+	range_sym = prop->expr->left.sym;
+	val2 = sym_get_range_val(range_sym, base);
 	if (val >= val2) {
-		val2 = sym_get_range_val(prop->expr->right.sym, base);
+		range_sym = prop->expr->right.sym;
+		val2 = sym_get_range_val(range_sym, base);
 		if (val <= val2)
 			return;
 	}
-	if (sym->type == S_INT)
-		sprintf(str, "%lld", val2);
-	else
-		sprintf(str, "0x%llx", val2);
-	sym->curr.val = xstrdup(str);
+	sym->curr.val = range_sym->curr.val;
 }
 
 static void sym_set_changed(struct symbol *sym)
diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index 3ecdab5ca612..e8aefd258a29 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -1593,6 +1593,11 @@ sub push_parameter($$$$$) {
 		$parameterdescs{$param} = "anonymous\n";
 		$anon_struct_union = 1;
 	}
+	elsif ($param =~ "__cacheline_group" )
+	# handle cache group enforcing variables: they do not need be described in header files
+	{
+		return; # ignore __cacheline_group_begin and __cacheline_group_end
+	}
 
 	# warn if parameter has no description
 	# (but ignore ones starting with # as these are not parameters
diff --git a/scripts/min-tool-version.sh b/scripts/min-tool-version.sh
index fd5ffdb81bab..c62066825f53 100755
--- a/scripts/min-tool-version.sh
+++ b/scripts/min-tool-version.sh
@@ -31,7 +31,7 @@ llvm)
 	fi
 	;;
 rustc)
-	echo 1.73.0
+	echo 1.74.1
 	;;
 bindgen)
 	echo 0.65.1
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 973b5e5ae2dd..cb6406f485a9 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -1383,13 +1383,15 @@ static void section_rela(struct module *mod, struct elf_info *elf,
 	const Elf_Rela *rela;
 
 	for (rela = start; rela < stop; rela++) {
+		Elf_Sym *tsym;
 		Elf_Addr taddr, r_offset;
 		unsigned int r_type, r_sym;
 
 		r_offset = TO_NATIVE(rela->r_offset);
 		get_rel_type_and_sym(elf, rela->r_info, &r_type, &r_sym);
 
-		taddr = TO_NATIVE(rela->r_addend);
+		tsym = elf->symtab_start + r_sym;
+		taddr = tsym->st_value + TO_NATIVE(rela->r_addend);
 
 		switch (elf->hdr->e_machine) {
 		case EM_RISCV:
@@ -1404,7 +1406,7 @@ static void section_rela(struct module *mod, struct elf_info *elf,
 			break;
 		}
 
-		check_section_mismatch(mod, elf, elf->symtab_start + r_sym,
+		check_section_mismatch(mod, elf, tsym,
 				       fsecndx, fromsec, r_offset, taddr);
 	}
 }
diff --git a/scripts/sign-file.c b/scripts/sign-file.c
index 598ef5465f82..3edb156ae52c 100644
--- a/scripts/sign-file.c
+++ b/scripts/sign-file.c
@@ -322,7 +322,7 @@ int main(int argc, char **argv)
 				     CMS_NOSMIMECAP | use_keyid |
 				     use_signed_attrs),
 		    "CMS_add1_signer");
-		ERR(CMS_final(cms, bm, NULL, CMS_NOCERTS | CMS_BINARY) < 0,
+		ERR(CMS_final(cms, bm, NULL, CMS_NOCERTS | CMS_BINARY) != 1,
 		    "CMS_final");
 
 #else
@@ -341,10 +341,10 @@ int main(int argc, char **argv)
 			b = BIO_new_file(sig_file_name, "wb");
 			ERR(!b, "%s", sig_file_name);
 #ifndef USE_PKCS7
-			ERR(i2d_CMS_bio_stream(b, cms, NULL, 0) < 0,
+			ERR(i2d_CMS_bio_stream(b, cms, NULL, 0) != 1,
 			    "%s", sig_file_name);
 #else
-			ERR(i2d_PKCS7_bio(b, pkcs7) < 0,
+			ERR(i2d_PKCS7_bio(b, pkcs7) != 1,
 			    "%s", sig_file_name);
 #endif
 			BIO_free(b);
@@ -374,9 +374,9 @@ int main(int argc, char **argv)
 
 	if (!raw_sig) {
 #ifndef USE_PKCS7
-		ERR(i2d_CMS_bio_stream(bd, cms, NULL, 0) < 0, "%s", dest_name);
+		ERR(i2d_CMS_bio_stream(bd, cms, NULL, 0) != 1, "%s", dest_name);
 #else
-		ERR(i2d_PKCS7_bio(bd, pkcs7) < 0, "%s", dest_name);
+		ERR(i2d_PKCS7_bio(bd, pkcs7) != 1, "%s", dest_name);
 #endif
 	} else {
 		BIO *b;
@@ -396,7 +396,7 @@ int main(int argc, char **argv)
 	ERR(BIO_write(bd, &sig_info, sizeof(sig_info)) < 0, "%s", dest_name);
 	ERR(BIO_write(bd, magic_number, sizeof(magic_number) - 1) < 0, "%s", dest_name);
 
-	ERR(BIO_free(bd) < 0, "%s", dest_name);
+	ERR(BIO_free(bd) != 1, "%s", dest_name);
 
 	/* Finally, if we're signing in place, replace the original. */
 	if (replace_orig)
diff --git a/scripts/spelling.txt b/scripts/spelling.txt
index 855c4863124b..edec60d39bbf 100644
--- a/scripts/spelling.txt
+++ b/scripts/spelling.txt
@@ -26,6 +26,7 @@ accelaration||acceleration
 accelearion||acceleration
 acceleratoin||acceleration
 accelleration||acceleration
+accelrometer||accelerometer
 accesing||accessing
 accesnt||accent
 accessable||accessible
@@ -137,6 +138,7 @@ anniversery||anniversary
 annoucement||announcement
 anomolies||anomalies
 anomoly||anomaly
+anonynous||anonymous
 anway||anyway
 aplication||application
 appearence||appearance
@@ -267,6 +269,7 @@ cadidate||candidate
 cahces||caches
 calender||calendar
 calescing||coalescing
+calibraiton||calibration
 calle||called
 callibration||calibration
 callled||called
@@ -288,6 +291,7 @@ capabitilies||capabilities
 capablity||capability
 capatibilities||capabilities
 capapbilities||capabilities
+captuer||capture
 caputure||capture
 carefuly||carefully
 cariage||carriage
@@ -340,6 +344,7 @@ comminucation||communication
 commited||committed
 commiting||committing
 committ||commit
+commmand||command
 commnunication||communication
 commoditiy||commodity
 comsume||consume
@@ -406,6 +411,7 @@ continious||continuous
 continous||continuous
 continously||continuously
 continueing||continuing
+contiuous||continuous
 contraints||constraints
 contruct||construct
 contol||control
@@ -757,6 +763,7 @@ hardward||hardware
 havind||having
 heirarchically||hierarchically
 heirarchy||hierarchy
+heirachy||hierarchy
 helpfull||helpful
 hearbeat||heartbeat
 heterogenous||heterogeneous
@@ -1199,6 +1206,7 @@ priting||printing
 privilaged||privileged
 privilage||privilege
 priviledge||privilege
+priviledged||privileged
 priviledges||privileges
 privleges||privileges
 probaly||probably
@@ -1251,6 +1259,7 @@ purgable||purgeable
 pwoer||power
 queing||queuing
 quering||querying
+querrying||querying
 queus||queues
 randomally||randomly
 raoming||roaming
@@ -1324,6 +1333,7 @@ reseting||resetting
 reseved||reserved
 reseverd||reserved
 resizeable||resizable
+resonable||reasonable
 resotre||restore
 resouce||resource
 resouces||resources
@@ -1427,6 +1437,7 @@ sliped||slipped
 softwade||software
 softwares||software
 soley||solely
+soluation||solution
 souce||source
 speach||speech
 specfic||specific
@@ -1458,6 +1469,7 @@ standart||standard
 standy||standby
 stardard||standard
 staticly||statically
+statisitcs||statistics
 statuss||status
 stoped||stopped
 stoping||stopping
@@ -1548,6 +1560,7 @@ threds||threads
 threee||three
 threshhold||threshold
 thresold||threshold
+throtting||throttling
 throught||through
 tansition||transition
 trackling||tracking
@@ -1571,6 +1584,7 @@ tranasction||transaction
 tranceiver||transceiver
 tranfer||transfer
 tranmission||transmission
+tranport||transport
 transcevier||transceiver
 transciever||transceiver
 transferd||transferred
diff --git a/security/Makefile b/security/Makefile
index 18121f8f85cd..59f238490665 100644
--- a/security/Makefile
+++ b/security/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_KEYS)			+= keys/
 
 # always enable default capabilities
 obj-y					+= commoncap.o
+obj-$(CONFIG_SECURITY) 			+= lsm_syscalls.o
 obj-$(CONFIG_MMU)			+= min_addr.o
 
 # Object file lists
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index 38650e52ef57..2d9f2a4b4519 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -2373,6 +2373,7 @@ static struct aa_sfs_entry aa_sfs_entry_policy[] = {
 
 static struct aa_sfs_entry aa_sfs_entry_mount[] = {
 	AA_SFS_FILE_STRING("mask", "mount umount pivot_root"),
+	AA_SFS_FILE_STRING("move_mount", "detached"),
 	{ }
 };
 
diff --git a/security/apparmor/include/procattr.h b/security/apparmor/include/procattr.h
index 31689437e0e1..03dbfdb2f2c0 100644
--- a/security/apparmor/include/procattr.h
+++ b/security/apparmor/include/procattr.h
@@ -11,7 +11,7 @@
 #ifndef __AA_PROCATTR_H
 #define __AA_PROCATTR_H
 
-int aa_getprocattr(struct aa_label *label, char **string);
+int aa_getprocattr(struct aa_label *label, char **string, bool newline);
 int aa_setprocattr_changehat(char *args, size_t size, int flags);
 
 #endif /* __AA_PROCATTR_H */
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 4981bdf02993..e490a7000408 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -24,6 +24,7 @@
 #include <linux/zstd.h>
 #include <net/sock.h>
 #include <uapi/linux/mount.h>
+#include <uapi/linux/lsm.h>
 
 #include "include/apparmor.h"
 #include "include/apparmorfs.h"
@@ -775,6 +776,46 @@ static int apparmor_sb_pivotroot(const struct path *old_path,
 	return error;
 }
 
+static int apparmor_getselfattr(unsigned int attr, struct lsm_ctx __user *lx,
+				size_t *size, u32 flags)
+{
+	int error = -ENOENT;
+	struct aa_task_ctx *ctx = task_ctx(current);
+	struct aa_label *label = NULL;
+	char *value;
+
+	switch (attr) {
+	case LSM_ATTR_CURRENT:
+		label = aa_get_newest_label(cred_label(current_cred()));
+		break;
+	case LSM_ATTR_PREV:
+		if (ctx->previous)
+			label = aa_get_newest_label(ctx->previous);
+		break;
+	case LSM_ATTR_EXEC:
+		if (ctx->onexec)
+			label = aa_get_newest_label(ctx->onexec);
+		break;
+	default:
+		error = -EOPNOTSUPP;
+		break;
+	}
+
+	if (label) {
+		error = aa_getprocattr(label, &value, false);
+		if (error > 0)
+			error = lsm_fill_user_ctx(lx, size, value, error,
+						  LSM_ID_APPARMOR, 0);
+		kfree(value);
+	}
+
+	aa_put_label(label);
+
+	if (error < 0)
+		return error;
+	return 1;
+}
+
 static int apparmor_getprocattr(struct task_struct *task, const char *name,
 				char **value)
 {
@@ -794,7 +835,7 @@ static int apparmor_getprocattr(struct task_struct *task, const char *name,
 		error = -EINVAL;
 
 	if (label)
-		error = aa_getprocattr(label, value);
+		error = aa_getprocattr(label, value, true);
 
 	aa_put_label(label);
 	put_cred(cred);
@@ -802,8 +843,7 @@ static int apparmor_getprocattr(struct task_struct *task, const char *name,
 	return error;
 }
 
-static int apparmor_setprocattr(const char *name, void *value,
-				size_t size)
+static int do_setattr(u64 attr, void *value, size_t size)
 {
 	char *command, *largs = NULL, *args = value;
 	size_t arg_size;
@@ -834,7 +874,7 @@ static int apparmor_setprocattr(const char *name, void *value,
 		goto out;
 
 	arg_size = size - (args - (largs ? largs : (char *) value));
-	if (strcmp(name, "current") == 0) {
+	if (attr == LSM_ATTR_CURRENT) {
 		if (strcmp(command, "changehat") == 0) {
 			error = aa_setprocattr_changehat(args, arg_size,
 							 AA_CHANGE_NOFLAGS);
@@ -849,7 +889,7 @@ static int apparmor_setprocattr(const char *name, void *value,
 			error = aa_change_profile(args, AA_CHANGE_STACK);
 		} else
 			goto fail;
-	} else if (strcmp(name, "exec") == 0) {
+	} else if (attr == LSM_ATTR_EXEC) {
 		if (strcmp(command, "exec") == 0)
 			error = aa_change_profile(args, AA_CHANGE_ONEXEC);
 		else if (strcmp(command, "stack") == 0)
@@ -869,13 +909,42 @@ out:
 
 fail:
 	ad.subj_label = begin_current_label_crit_section();
-	ad.info = name;
+	if (attr == LSM_ATTR_CURRENT)
+		ad.info = "current";
+	else if (attr == LSM_ATTR_EXEC)
+		ad.info = "exec";
+	else
+		ad.info = "invalid";
 	ad.error = error = -EINVAL;
 	aa_audit_msg(AUDIT_APPARMOR_DENIED, &ad, NULL);
 	end_current_label_crit_section(ad.subj_label);
 	goto out;
 }
 
+static int apparmor_setselfattr(unsigned int attr, struct lsm_ctx *ctx,
+				size_t size, u32 flags)
+{
+	int rc;
+
+	if (attr != LSM_ATTR_CURRENT && attr != LSM_ATTR_EXEC)
+		return -EOPNOTSUPP;
+
+	rc = do_setattr(attr, ctx->ctx, ctx->ctx_len);
+	if (rc > 0)
+		return 0;
+	return rc;
+}
+
+static int apparmor_setprocattr(const char *name, void *value,
+				size_t size)
+{
+	int attr = lsm_name_to_attr(name);
+
+	if (attr)
+		return do_setattr(attr, value, size);
+	return -EINVAL;
+}
+
 /**
  * apparmor_bprm_committing_creds - do task cleanup on committing new creds
  * @bprm: binprm for the exec  (NOT NULL)
@@ -1385,6 +1454,11 @@ struct lsm_blob_sizes apparmor_blob_sizes __ro_after_init = {
 	.lbs_task = sizeof(struct aa_task_ctx),
 };
 
+static const struct lsm_id apparmor_lsmid = {
+	.name = "apparmor",
+	.id = LSM_ID_APPARMOR,
+};
+
 static struct security_hook_list apparmor_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(ptrace_access_check, apparmor_ptrace_access_check),
 	LSM_HOOK_INIT(ptrace_traceme, apparmor_ptrace_traceme),
@@ -1418,6 +1492,8 @@ static struct security_hook_list apparmor_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(file_lock, apparmor_file_lock),
 	LSM_HOOK_INIT(file_truncate, apparmor_file_truncate),
 
+	LSM_HOOK_INIT(getselfattr, apparmor_getselfattr),
+	LSM_HOOK_INIT(setselfattr, apparmor_setselfattr),
 	LSM_HOOK_INIT(getprocattr, apparmor_getprocattr),
 	LSM_HOOK_INIT(setprocattr, apparmor_setprocattr),
 
@@ -2202,7 +2278,7 @@ static int __init apparmor_init(void)
 		goto buffers_out;
 	}
 	security_add_hooks(apparmor_hooks, ARRAY_SIZE(apparmor_hooks),
-				"apparmor");
+				&apparmor_lsmid);
 
 	/* Report that AppArmor successfully initialized */
 	apparmor_initialized = 1;
diff --git a/security/apparmor/mount.c b/security/apparmor/mount.c
index fb30204c761a..49fe8da6fea4 100644
--- a/security/apparmor/mount.c
+++ b/security/apparmor/mount.c
@@ -499,6 +499,10 @@ int aa_move_mount(const struct cred *subj_cred,
 	error = -ENOMEM;
 	if (!to_buffer || !from_buffer)
 		goto out;
+
+	if (!our_mnt(from_path->mnt))
+		/* moving a mount detached from the namespace */
+		from_path = NULL;
 	error = fn_for_each_confined(label, profile,
 			match_mnt(subj_cred, profile, to_path, to_buffer,
 				  from_path, from_buffer,
diff --git a/security/apparmor/procattr.c b/security/apparmor/procattr.c
index 197d41f9c32b..e3857e3d7c6c 100644
--- a/security/apparmor/procattr.c
+++ b/security/apparmor/procattr.c
@@ -20,6 +20,7 @@
  * aa_getprocattr - Return the label information for @label
  * @label: the label to print label info about  (NOT NULL)
  * @string: Returns - string containing the label info (NOT NULL)
+ * @newline: indicates that a newline should be added
  *
  * Requires: label != NULL && string != NULL
  *
@@ -27,7 +28,7 @@
  *
  * Returns: size of string placed in @string else error code on failure
  */
-int aa_getprocattr(struct aa_label *label, char **string)
+int aa_getprocattr(struct aa_label *label, char **string, bool newline)
 {
 	struct aa_ns *ns = labels_ns(label);
 	struct aa_ns *current_ns = aa_get_current_ns();
@@ -57,11 +58,12 @@ int aa_getprocattr(struct aa_label *label, char **string)
 		return len;
 	}
 
-	(*string)[len] = '\n';
-	(*string)[len + 1] = 0;
+	if (newline)
+		(*string)[len++] = '\n';
+	(*string)[len] = 0;
 
 	aa_put_ns(current_ns);
-	return len + 1;
+	return len;
 }
 
 /**
diff --git a/security/bpf/hooks.c b/security/bpf/hooks.c
index cfaf1d0e6a5f..57b9ffd53c98 100644
--- a/security/bpf/hooks.c
+++ b/security/bpf/hooks.c
@@ -5,6 +5,7 @@
  */
 #include <linux/lsm_hooks.h>
 #include <linux/bpf_lsm.h>
+#include <uapi/linux/lsm.h>
 
 static struct security_hook_list bpf_lsm_hooks[] __ro_after_init = {
 	#define LSM_HOOK(RET, DEFAULT, NAME, ...) \
@@ -15,9 +16,15 @@ static struct security_hook_list bpf_lsm_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(task_free, bpf_task_storage_free),
 };
 
+static const struct lsm_id bpf_lsmid = {
+	.name = "bpf",
+	.id = LSM_ID_BPF,
+};
+
 static int __init bpf_lsm_init(void)
 {
-	security_add_hooks(bpf_lsm_hooks, ARRAY_SIZE(bpf_lsm_hooks), "bpf");
+	security_add_hooks(bpf_lsm_hooks, ARRAY_SIZE(bpf_lsm_hooks),
+			   &bpf_lsmid);
 	pr_info("LSM support for eBPF active\n");
 	return 0;
 }
diff --git a/security/commoncap.c b/security/commoncap.c
index 8e8c630ce204..162d96b3a676 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -25,6 +25,7 @@
 #include <linux/binfmts.h>
 #include <linux/personality.h>
 #include <linux/mnt_idmapping.h>
+#include <uapi/linux/lsm.h>
 
 /*
  * If a non-root user executes a setuid-root binary in
@@ -1440,6 +1441,11 @@ int cap_mmap_file(struct file *file, unsigned long reqprot,
 
 #ifdef CONFIG_SECURITY
 
+static const struct lsm_id capability_lsmid = {
+	.name = "capability",
+	.id = LSM_ID_CAPABILITY,
+};
+
 static struct security_hook_list capability_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(capable, cap_capable),
 	LSM_HOOK_INIT(settime, cap_settime),
@@ -1464,7 +1470,7 @@ static struct security_hook_list capability_hooks[] __ro_after_init = {
 static int __init capability_init(void)
 {
 	security_add_hooks(capability_hooks, ARRAY_SIZE(capability_hooks),
-				"capability");
+			   &capability_lsmid);
 	return 0;
 }
 
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index 894570fe39bc..cc7956d7878b 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -151,6 +151,17 @@ static int evm_find_protected_xattrs(struct dentry *dentry)
 	return count;
 }
 
+static int is_unsupported_fs(struct dentry *dentry)
+{
+	struct inode *inode = d_backing_inode(dentry);
+
+	if (inode->i_sb->s_iflags & SB_I_EVM_UNSUPPORTED) {
+		pr_info_once("%s not supported\n", inode->i_sb->s_type->name);
+		return 1;
+	}
+	return 0;
+}
+
 /*
  * evm_verify_hmac - calculate and compare the HMAC with the EVM xattr
  *
@@ -181,6 +192,9 @@ static enum integrity_status evm_verify_hmac(struct dentry *dentry,
 		     iint->evm_status == INTEGRITY_PASS_IMMUTABLE))
 		return iint->evm_status;
 
+	if (is_unsupported_fs(dentry))
+		return INTEGRITY_UNKNOWN;
+
 	/* if status is not PASS, try to check again - against -ENOMEM */
 
 	/* first need to know the sig type */
@@ -408,6 +422,9 @@ enum integrity_status evm_verifyxattr(struct dentry *dentry,
 	if (!evm_key_loaded() || !evm_protected_xattr(xattr_name))
 		return INTEGRITY_UNKNOWN;
 
+	if (is_unsupported_fs(dentry))
+		return INTEGRITY_UNKNOWN;
+
 	if (!iint) {
 		iint = integrity_iint_find(d_backing_inode(dentry));
 		if (!iint)
@@ -491,15 +508,21 @@ static int evm_protect_xattr(struct mnt_idmap *idmap,
 	if (strcmp(xattr_name, XATTR_NAME_EVM) == 0) {
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
+		if (is_unsupported_fs(dentry))
+			return -EPERM;
 	} else if (!evm_protected_xattr(xattr_name)) {
 		if (!posix_xattr_acl(xattr_name))
 			return 0;
+		if (is_unsupported_fs(dentry))
+			return 0;
+
 		evm_status = evm_verify_current_integrity(dentry);
 		if ((evm_status == INTEGRITY_PASS) ||
 		    (evm_status == INTEGRITY_NOXATTRS))
 			return 0;
 		goto out;
-	}
+	} else if (is_unsupported_fs(dentry))
+		return 0;
 
 	evm_status = evm_verify_current_integrity(dentry);
 	if (evm_status == INTEGRITY_NOXATTRS) {
@@ -750,6 +773,9 @@ void evm_inode_post_setxattr(struct dentry *dentry, const char *xattr_name,
 	if (!(evm_initialized & EVM_INIT_HMAC))
 		return;
 
+	if (is_unsupported_fs(dentry))
+		return;
+
 	evm_update_evmxattr(dentry, xattr_name, xattr_value, xattr_value_len);
 }
 
@@ -814,8 +840,12 @@ int evm_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	if (evm_initialized & EVM_ALLOW_METADATA_WRITES)
 		return 0;
 
+	if (is_unsupported_fs(dentry))
+		return 0;
+
 	if (!(ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)))
 		return 0;
+
 	evm_status = evm_verify_current_integrity(dentry);
 	/*
 	 * Writing attrs is safe for portable signatures, as portable signatures
@@ -859,10 +889,20 @@ void evm_inode_post_setattr(struct dentry *dentry, int ia_valid)
 	if (!(evm_initialized & EVM_INIT_HMAC))
 		return;
 
+	if (is_unsupported_fs(dentry))
+		return;
+
 	if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
 		evm_update_evmxattr(dentry, NULL, NULL, 0);
 }
 
+int evm_inode_copy_up_xattr(const char *name)
+{
+	if (strcmp(name, XATTR_NAME_EVM) == 0)
+		return 1; /* Discard */
+	return -EOPNOTSUPP;
+}
+
 /*
  * evm_inode_init_security - initializes security.evm HMAC value
  */
diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig
index a6bd817efc1a..b98bfe9efd0c 100644
--- a/security/integrity/ima/Kconfig
+++ b/security/integrity/ima/Kconfig
@@ -243,7 +243,7 @@ config IMA_APPRAISE_MODSIG
 	   to accept such signatures.
 
 config IMA_KEYRINGS_PERMIT_SIGNED_BY_BUILTIN_OR_SECONDARY
-	bool "Permit keys validly signed by a built-in or secondary CA cert (EXPERIMENTAL)"
+	bool "Permit keys validly signed by a built-in, machine (if configured) or secondary"
 	depends on SYSTEM_TRUSTED_KEYRING
 	depends on SECONDARY_TRUSTED_KEYRING
 	depends on INTEGRITY_ASYMMETRIC_KEYS
@@ -251,14 +251,14 @@ config IMA_KEYRINGS_PERMIT_SIGNED_BY_BUILTIN_OR_SECONDARY
 	default n
 	help
 	  Keys may be added to the IMA or IMA blacklist keyrings, if the
-	  key is validly signed by a CA cert in the system built-in or
-	  secondary trusted keyrings. The key must also have the
-	  digitalSignature usage set.
+	  key is validly signed by a CA cert in the system built-in,
+	  machine (if configured), or secondary trusted keyrings. The
+	  key must also have the digitalSignature usage set.
 
 	  Intermediate keys between those the kernel has compiled in and the
 	  IMA keys to be added may be added to the system secondary keyring,
 	  provided they are validly signed by a key already resident in the
-	  built-in or secondary trusted keyrings.
+	  built-in, machine (if configured) or secondary trusted keyrings.
 
 config IMA_BLACKLIST_KEYRING
 	bool "Create IMA machine owner blacklist keyrings (EXPERIMENTAL)"
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index 51ad29940f05..f3738b2c8bcd 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -38,7 +38,7 @@ static int param_set_bufsize(const char *val, const struct kernel_param *kp)
 
 	size = memparse(val, NULL);
 	order = get_order(size);
-	if (order > MAX_ORDER)
+	if (order > MAX_PAGE_ORDER)
 		return -EINVAL;
 	ima_maxorder = order;
 	ima_bufsize = PAGE_SIZE << order;
diff --git a/security/integrity/ima/ima_kexec.c b/security/integrity/ima/ima_kexec.c
index ad133fe120db..dadc1d138118 100644
--- a/security/integrity/ima/ima_kexec.c
+++ b/security/integrity/ima/ima_kexec.c
@@ -129,8 +129,8 @@ void ima_add_kexec_buffer(struct kimage *image)
 	image->ima_buffer_size = kexec_segment_size;
 	image->ima_buffer = kexec_buffer;
 
-	pr_debug("kexec measurement buffer for the loaded kernel at 0x%lx.\n",
-		 kbuf.mem);
+	kexec_dprintk("kexec measurement buffer for the loaded kernel at 0x%lx.\n",
+		      kbuf.mem);
 }
 #endif /* IMA_KEXEC */
 
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index 8af2136069d2..76f55dd13cb8 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -237,6 +237,10 @@ static int datablob_parse(char *datablob, const char **format,
 			break;
 		}
 		*decrypted_data = strsep(&datablob, " \t");
+		if (!*decrypted_data) {
+			pr_info("encrypted_key: decrypted_data is missing\n");
+			break;
+		}
 		ret = 0;
 		break;
 	case Opt_load:
diff --git a/security/keys/gc.c b/security/keys/gc.c
index 3c90807476eb..eaddaceda14e 100644
--- a/security/keys/gc.c
+++ b/security/keys/gc.c
@@ -67,6 +67,19 @@ void key_schedule_gc(time64_t gc_at)
 }
 
 /*
+ * Set the expiration time on a key.
+ */
+void key_set_expiry(struct key *key, time64_t expiry)
+{
+	key->expiry = expiry;
+	if (expiry != TIME64_MAX) {
+		if (!(key->type->flags & KEY_TYPE_INSTANT_REAP))
+			expiry += key_gc_delay;
+		key_schedule_gc(expiry);
+	}
+}
+
+/*
  * Schedule a dead links collection run.
  */
 void key_schedule_gc_links(void)
@@ -176,7 +189,6 @@ static void key_garbage_collector(struct work_struct *work)
 	static u8 gc_state;		/* Internal persistent state */
 #define KEY_GC_REAP_AGAIN	0x01	/* - Need another cycle */
 #define KEY_GC_REAPING_LINKS	0x02	/* - We need to reap links */
-#define KEY_GC_SET_TIMER	0x04	/* - We need to restart the timer */
 #define KEY_GC_REAPING_DEAD_1	0x10	/* - We need to mark dead keys */
 #define KEY_GC_REAPING_DEAD_2	0x20	/* - We need to reap dead key links */
 #define KEY_GC_REAPING_DEAD_3	0x40	/* - We need to reap dead keys */
@@ -184,21 +196,17 @@ static void key_garbage_collector(struct work_struct *work)
 
 	struct rb_node *cursor;
 	struct key *key;
-	time64_t new_timer, limit;
+	time64_t new_timer, limit, expiry;
 
 	kenter("[%lx,%x]", key_gc_flags, gc_state);
 
 	limit = ktime_get_real_seconds();
-	if (limit > key_gc_delay)
-		limit -= key_gc_delay;
-	else
-		limit = key_gc_delay;
 
 	/* Work out what we're going to be doing in this pass */
 	gc_state &= KEY_GC_REAPING_DEAD_1 | KEY_GC_REAPING_DEAD_2;
 	gc_state <<= 1;
 	if (test_and_clear_bit(KEY_GC_KEY_EXPIRED, &key_gc_flags))
-		gc_state |= KEY_GC_REAPING_LINKS | KEY_GC_SET_TIMER;
+		gc_state |= KEY_GC_REAPING_LINKS;
 
 	if (test_and_clear_bit(KEY_GC_REAP_KEYTYPE, &key_gc_flags))
 		gc_state |= KEY_GC_REAPING_DEAD_1;
@@ -233,8 +241,11 @@ continue_scanning:
 			}
 		}
 
-		if (gc_state & KEY_GC_SET_TIMER) {
-			if (key->expiry > limit && key->expiry < new_timer) {
+		expiry = key->expiry;
+		if (expiry != TIME64_MAX) {
+			if (!(key->type->flags & KEY_TYPE_INSTANT_REAP))
+				expiry += key_gc_delay;
+			if (expiry > limit && expiry < new_timer) {
 				kdebug("will expire %x in %lld",
 				       key_serial(key), key->expiry - limit);
 				new_timer = key->expiry;
@@ -276,7 +287,7 @@ maybe_resched:
 	 */
 	kdebug("pass complete");
 
-	if (gc_state & KEY_GC_SET_TIMER && new_timer != (time64_t)TIME64_MAX) {
+	if (new_timer != TIME64_MAX) {
 		new_timer += key_gc_delay;
 		key_schedule_gc(new_timer);
 	}
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 471cf36dedc0..2cffa6dc8255 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -167,6 +167,7 @@ extern unsigned key_gc_delay;
 extern void keyring_gc(struct key *keyring, time64_t limit);
 extern void keyring_restriction_gc(struct key *keyring,
 				   struct key_type *dead_type);
+void key_set_expiry(struct key *key, time64_t expiry);
 extern void key_schedule_gc(time64_t gc_at);
 extern void key_schedule_gc_links(void);
 extern void key_gc_keytype(struct key_type *ktype);
@@ -215,10 +216,18 @@ extern struct key *key_get_instantiation_authkey(key_serial_t target_id);
  */
 static inline bool key_is_dead(const struct key *key, time64_t limit)
 {
+	time64_t expiry = key->expiry;
+
+	if (expiry != TIME64_MAX) {
+		if (!(key->type->flags & KEY_TYPE_INSTANT_REAP))
+			expiry += key_gc_delay;
+		if (expiry <= limit)
+			return true;
+	}
+
 	return
 		key->flags & ((1 << KEY_FLAG_DEAD) |
 			      (1 << KEY_FLAG_INVALIDATED)) ||
-		(key->expiry > 0 && key->expiry <= limit) ||
 		key->domain_tag->removed;
 }
 
diff --git a/security/keys/key.c b/security/keys/key.c
index 0260a1902922..5b10641debd5 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -294,6 +294,7 @@ struct key *key_alloc(struct key_type *type, const char *desc,
 	key->uid = uid;
 	key->gid = gid;
 	key->perm = perm;
+	key->expiry = TIME64_MAX;
 	key->restrict_link = restrict_link;
 	key->last_used_at = ktime_get_real_seconds();
 
@@ -463,10 +464,7 @@ static int __key_instantiate_and_link(struct key *key,
 			if (authkey)
 				key_invalidate(authkey);
 
-			if (prep->expiry != TIME64_MAX) {
-				key->expiry = prep->expiry;
-				key_schedule_gc(prep->expiry + key_gc_delay);
-			}
+			key_set_expiry(key, prep->expiry);
 		}
 	}
 
@@ -606,8 +604,7 @@ int key_reject_and_link(struct key *key,
 		atomic_inc(&key->user->nikeys);
 		mark_key_instantiated(key, -error);
 		notify_key(key, NOTIFY_KEY_INSTANTIATED, -error);
-		key->expiry = ktime_get_real_seconds() + timeout;
-		key_schedule_gc(key->expiry + key_gc_delay);
+		key_set_expiry(key, ktime_get_real_seconds() + timeout);
 
 		if (test_and_clear_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags))
 			awaken = 1;
@@ -723,16 +720,14 @@ found_kernel_type:
 
 void key_set_timeout(struct key *key, unsigned timeout)
 {
-	time64_t expiry = 0;
+	time64_t expiry = TIME64_MAX;
 
 	/* make the changes with the locks held to prevent races */
 	down_write(&key->sem);
 
 	if (timeout > 0)
 		expiry = ktime_get_real_seconds() + timeout;
-
-	key->expiry = expiry;
-	key_schedule_gc(key->expiry + key_gc_delay);
+	key_set_expiry(key, expiry);
 
 	up_write(&key->sem);
 }
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index 19be69fa4d05..10ba439968f7 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -1252,12 +1252,11 @@ long keyctl_instantiate_key(key_serial_t id,
 			    key_serial_t ringid)
 {
 	if (_payload && plen) {
-		struct iovec iov;
 		struct iov_iter from;
 		int ret;
 
-		ret = import_single_range(ITER_SOURCE, (void __user *)_payload, plen,
-					  &iov, &from);
+		ret = import_ubuf(ITER_SOURCE, (void __user *)_payload, plen,
+				  &from);
 		if (unlikely(ret))
 			return ret;
 
diff --git a/security/keys/proc.c b/security/keys/proc.c
index d0cde6685627..4f4e2c1824f1 100644
--- a/security/keys/proc.c
+++ b/security/keys/proc.c
@@ -198,7 +198,7 @@ static int proc_keys_show(struct seq_file *m, void *v)
 
 	/* come up with a suitable timeout value */
 	expiry = READ_ONCE(key->expiry);
-	if (expiry == 0) {
+	if (expiry == TIME64_MAX) {
 		memcpy(xbuf, "perm", 5);
 	} else if (now >= expiry) {
 		memcpy(xbuf, "expd", 5);
diff --git a/security/landlock/cred.c b/security/landlock/cred.c
index 13dff2a31545..786af18c4a1c 100644
--- a/security/landlock/cred.c
+++ b/security/landlock/cred.c
@@ -42,5 +42,5 @@ static struct security_hook_list landlock_hooks[] __ro_after_init = {
 __init void landlock_add_cred_hooks(void)
 {
 	security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks),
-			   LANDLOCK_NAME);
+			   &landlock_lsmid);
 }
diff --git a/security/landlock/fs.c b/security/landlock/fs.c
index bc7c126deea2..fc520a06f9af 100644
--- a/security/landlock/fs.c
+++ b/security/landlock/fs.c
@@ -193,7 +193,7 @@ int landlock_append_fs_rule(struct landlock_ruleset *const ruleset,
  *
  * Returns NULL if no rule is found or if @dentry is negative.
  */
-static inline const struct landlock_rule *
+static const struct landlock_rule *
 find_rule(const struct landlock_ruleset *const domain,
 	  const struct dentry *const dentry)
 {
@@ -220,7 +220,7 @@ find_rule(const struct landlock_ruleset *const domain,
  * sockfs, pipefs), but can still be reachable through
  * /proc/<pid>/fd/<file-descriptor>
  */
-static inline bool is_nouser_or_private(const struct dentry *dentry)
+static bool is_nouser_or_private(const struct dentry *dentry)
 {
 	return (dentry->d_sb->s_flags & SB_NOUSER) ||
 	       (d_is_positive(dentry) &&
@@ -264,7 +264,7 @@ static const struct landlock_ruleset *get_current_fs_domain(void)
  *
  * @layer_masks_child2: Optional child masks.
  */
-static inline bool no_more_access(
+static bool no_more_access(
 	const layer_mask_t (*const layer_masks_parent1)[LANDLOCK_NUM_ACCESS_FS],
 	const layer_mask_t (*const layer_masks_child1)[LANDLOCK_NUM_ACCESS_FS],
 	const bool child1_is_directory,
@@ -316,7 +316,7 @@ static inline bool no_more_access(
  *
  * Returns true if the request is allowed, false otherwise.
  */
-static inline bool
+static bool
 scope_to_request(const access_mask_t access_request,
 		 layer_mask_t (*const layer_masks)[LANDLOCK_NUM_ACCESS_FS])
 {
@@ -335,7 +335,7 @@ scope_to_request(const access_mask_t access_request,
  * Returns true if there is at least one access right different than
  * LANDLOCK_ACCESS_FS_REFER.
  */
-static inline bool
+static bool
 is_eacces(const layer_mask_t (*const layer_masks)[LANDLOCK_NUM_ACCESS_FS],
 	  const access_mask_t access_request)
 {
@@ -551,9 +551,9 @@ jump_up:
 	return allowed_parent1 && allowed_parent2;
 }
 
-static inline int check_access_path(const struct landlock_ruleset *const domain,
-				    const struct path *const path,
-				    access_mask_t access_request)
+static int check_access_path(const struct landlock_ruleset *const domain,
+			     const struct path *const path,
+			     access_mask_t access_request)
 {
 	layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = {};
 
@@ -565,8 +565,8 @@ static inline int check_access_path(const struct landlock_ruleset *const domain,
 	return -EACCES;
 }
 
-static inline int current_check_access_path(const struct path *const path,
-					    const access_mask_t access_request)
+static int current_check_access_path(const struct path *const path,
+				     const access_mask_t access_request)
 {
 	const struct landlock_ruleset *const dom = get_current_fs_domain();
 
@@ -575,7 +575,7 @@ static inline int current_check_access_path(const struct path *const path,
 	return check_access_path(dom, path, access_request);
 }
 
-static inline access_mask_t get_mode_access(const umode_t mode)
+static access_mask_t get_mode_access(const umode_t mode)
 {
 	switch (mode & S_IFMT) {
 	case S_IFLNK:
@@ -600,7 +600,7 @@ static inline access_mask_t get_mode_access(const umode_t mode)
 	}
 }
 
-static inline access_mask_t maybe_remove(const struct dentry *const dentry)
+static access_mask_t maybe_remove(const struct dentry *const dentry)
 {
 	if (d_is_negative(dentry))
 		return 0;
@@ -1086,7 +1086,7 @@ static int hook_path_truncate(const struct path *const path)
  * Returns the access rights that are required for opening the given file,
  * depending on the file type and open mode.
  */
-static inline access_mask_t
+static access_mask_t
 get_required_file_open_access(const struct file *const file)
 {
 	access_mask_t access = 0;
@@ -1223,5 +1223,5 @@ static struct security_hook_list landlock_hooks[] __ro_after_init = {
 __init void landlock_add_fs_hooks(void)
 {
 	security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks),
-			   LANDLOCK_NAME);
+			   &landlock_lsmid);
 }
diff --git a/security/landlock/net.c b/security/landlock/net.c
index aaa92c2b1f08..efa1b644a4af 100644
--- a/security/landlock/net.c
+++ b/security/landlock/net.c
@@ -196,5 +196,5 @@ static struct security_hook_list landlock_hooks[] __ro_after_init = {
 __init void landlock_add_net_hooks(void)
 {
 	security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks),
-			   LANDLOCK_NAME);
+			   &landlock_lsmid);
 }
diff --git a/security/landlock/ptrace.c b/security/landlock/ptrace.c
index 8a06d6c492bf..2bfc533d36e4 100644
--- a/security/landlock/ptrace.c
+++ b/security/landlock/ptrace.c
@@ -116,5 +116,5 @@ static struct security_hook_list landlock_hooks[] __ro_after_init = {
 __init void landlock_add_ptrace_hooks(void)
 {
 	security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks),
-			   LANDLOCK_NAME);
+			   &landlock_lsmid);
 }
diff --git a/security/landlock/ruleset.c b/security/landlock/ruleset.c
index ffedc99f2b68..e0a5fbf9201a 100644
--- a/security/landlock/ruleset.c
+++ b/security/landlock/ruleset.c
@@ -305,7 +305,7 @@ int landlock_insert_rule(struct landlock_ruleset *const ruleset,
 	return insert_rule(ruleset, id, &layers, ARRAY_SIZE(layers));
 }
 
-static inline void get_hierarchy(struct landlock_hierarchy *const hierarchy)
+static void get_hierarchy(struct landlock_hierarchy *const hierarchy)
 {
 	if (hierarchy)
 		refcount_inc(&hierarchy->usage);
@@ -723,11 +723,12 @@ landlock_init_layer_masks(const struct landlock_ruleset *const domain,
 	/* Saves all handled accesses per layer. */
 	for (layer_level = 0; layer_level < domain->num_layers; layer_level++) {
 		const unsigned long access_req = access_request;
+		const access_mask_t access_mask =
+			get_access_mask(domain, layer_level);
 		unsigned long access_bit;
 
 		for_each_set_bit(access_bit, &access_req, num_access) {
-			if (BIT_ULL(access_bit) &
-			    get_access_mask(domain, layer_level)) {
+			if (BIT_ULL(access_bit) & access_mask) {
 				(*layer_masks)[access_bit] |=
 					BIT_ULL(layer_level);
 				handled_accesses |= BIT_ULL(access_bit);
diff --git a/security/landlock/setup.c b/security/landlock/setup.c
index 3e11d303542f..f6dd33143b7f 100644
--- a/security/landlock/setup.c
+++ b/security/landlock/setup.c
@@ -8,6 +8,7 @@
 
 #include <linux/init.h>
 #include <linux/lsm_hooks.h>
+#include <uapi/linux/lsm.h>
 
 #include "common.h"
 #include "cred.h"
@@ -25,6 +26,11 @@ struct lsm_blob_sizes landlock_blob_sizes __ro_after_init = {
 	.lbs_superblock = sizeof(struct landlock_superblock_security),
 };
 
+const struct lsm_id landlock_lsmid = {
+	.name = LANDLOCK_NAME,
+	.id = LSM_ID_LANDLOCK,
+};
+
 static int __init landlock_init(void)
 {
 	landlock_add_cred_hooks();
diff --git a/security/landlock/setup.h b/security/landlock/setup.h
index 1daffab1ab4b..c4252d46d49d 100644
--- a/security/landlock/setup.h
+++ b/security/landlock/setup.h
@@ -14,5 +14,6 @@
 extern bool landlock_initialized;
 
 extern struct lsm_blob_sizes landlock_blob_sizes;
+extern const struct lsm_id landlock_lsmid;
 
 #endif /* _SECURITY_LANDLOCK_SETUP_H */
diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c
index a9d40456a064..8e93cda130f1 100644
--- a/security/loadpin/loadpin.c
+++ b/security/loadpin/loadpin.c
@@ -20,6 +20,7 @@
 #include <linux/string_helpers.h>
 #include <linux/dm-verity-loadpin.h>
 #include <uapi/linux/loadpin.h>
+#include <uapi/linux/lsm.h>
 
 #define VERITY_DIGEST_FILE_HEADER "# LOADPIN_TRUSTED_VERITY_ROOT_DIGESTS"
 
@@ -208,6 +209,11 @@ static int loadpin_load_data(enum kernel_load_data_id id, bool contents)
 	return loadpin_check(NULL, (enum kernel_read_file_id) id);
 }
 
+static const struct lsm_id loadpin_lsmid = {
+	.name = "loadpin",
+	.id = LSM_ID_LOADPIN,
+};
+
 static struct security_hook_list loadpin_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(sb_free_security, loadpin_sb_free_security),
 	LSM_HOOK_INIT(kernel_read_file, loadpin_read_file),
@@ -259,7 +265,8 @@ static int __init loadpin_init(void)
 	if (!register_sysctl("kernel/loadpin", loadpin_sysctl_table))
 		pr_notice("sysctl registration failed!\n");
 #endif
-	security_add_hooks(loadpin_hooks, ARRAY_SIZE(loadpin_hooks), "loadpin");
+	security_add_hooks(loadpin_hooks, ARRAY_SIZE(loadpin_hooks),
+			   &loadpin_lsmid);
 
 	return 0;
 }
diff --git a/security/lockdown/lockdown.c b/security/lockdown/lockdown.c
index 68d19632aeb7..cd84d8ea1dfb 100644
--- a/security/lockdown/lockdown.c
+++ b/security/lockdown/lockdown.c
@@ -13,6 +13,7 @@
 #include <linux/security.h>
 #include <linux/export.h>
 #include <linux/lsm_hooks.h>
+#include <uapi/linux/lsm.h>
 
 static enum lockdown_reason kernel_locked_down;
 
@@ -75,6 +76,11 @@ static struct security_hook_list lockdown_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(locked_down, lockdown_is_locked_down),
 };
 
+const struct lsm_id lockdown_lsmid = {
+	.name = "lockdown",
+	.id = LSM_ID_LOCKDOWN,
+};
+
 static int __init lockdown_lsm_init(void)
 {
 #if defined(CONFIG_LOCK_DOWN_KERNEL_FORCE_INTEGRITY)
@@ -83,7 +89,7 @@ static int __init lockdown_lsm_init(void)
 	lock_kernel_down("Kernel configuration", LOCKDOWN_CONFIDENTIALITY_MAX);
 #endif
 	security_add_hooks(lockdown_hooks, ARRAY_SIZE(lockdown_hooks),
-			   "lockdown");
+			   &lockdown_lsmid);
 	return 0;
 }
 
diff --git a/security/lsm_syscalls.c b/security/lsm_syscalls.c
new file mode 100644
index 000000000000..5d391b1f7e69
--- /dev/null
+++ b/security/lsm_syscalls.c
@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * System calls implementing the Linux Security Module API.
+ *
+ *  Copyright (C) 2022 Casey Schaufler <casey@schaufler-ca.com>
+ *  Copyright (C) 2022 Intel Corporation
+ */
+
+#include <asm/current.h>
+#include <linux/compiler_types.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/security.h>
+#include <linux/stddef.h>
+#include <linux/syscalls.h>
+#include <linux/types.h>
+#include <linux/lsm_hooks.h>
+#include <uapi/linux/lsm.h>
+
+/**
+ * lsm_name_to_attr - map an LSM attribute name to its ID
+ * @name: name of the attribute
+ *
+ * Returns the LSM attribute value associated with @name, or 0 if
+ * there is no mapping.
+ */
+u64 lsm_name_to_attr(const char *name)
+{
+	if (!strcmp(name, "current"))
+		return LSM_ATTR_CURRENT;
+	if (!strcmp(name, "exec"))
+		return LSM_ATTR_EXEC;
+	if (!strcmp(name, "fscreate"))
+		return LSM_ATTR_FSCREATE;
+	if (!strcmp(name, "keycreate"))
+		return LSM_ATTR_KEYCREATE;
+	if (!strcmp(name, "prev"))
+		return LSM_ATTR_PREV;
+	if (!strcmp(name, "sockcreate"))
+		return LSM_ATTR_SOCKCREATE;
+	return LSM_ATTR_UNDEF;
+}
+
+/**
+ * sys_lsm_set_self_attr - Set current task's security module attribute
+ * @attr: which attribute to set
+ * @ctx: the LSM contexts
+ * @size: size of @ctx
+ * @flags: reserved for future use
+ *
+ * Sets the calling task's LSM context. On success this function
+ * returns 0. If the attribute specified cannot be set a negative
+ * value indicating the reason for the error is returned.
+ */
+SYSCALL_DEFINE4(lsm_set_self_attr, unsigned int, attr, struct lsm_ctx __user *,
+		ctx, size_t, size, u32, flags)
+{
+	return security_setselfattr(attr, ctx, size, flags);
+}
+
+/**
+ * sys_lsm_get_self_attr - Return current task's security module attributes
+ * @attr: which attribute to return
+ * @ctx: the user-space destination for the information, or NULL
+ * @size: pointer to the size of space available to receive the data
+ * @flags: special handling options. LSM_FLAG_SINGLE indicates that only
+ * attributes associated with the LSM identified in the passed @ctx be
+ * reported.
+ *
+ * Returns the calling task's LSM contexts. On success this
+ * function returns the number of @ctx array elements. This value
+ * may be zero if there are no LSM contexts assigned. If @size is
+ * insufficient to contain the return data -E2BIG is returned and
+ * @size is set to the minimum required size. In all other cases
+ * a negative value indicating the error is returned.
+ */
+SYSCALL_DEFINE4(lsm_get_self_attr, unsigned int, attr, struct lsm_ctx __user *,
+		ctx, size_t __user *, size, u32, flags)
+{
+	return security_getselfattr(attr, ctx, size, flags);
+}
+
+/**
+ * sys_lsm_list_modules - Return a list of the active security modules
+ * @ids: the LSM module ids
+ * @size: pointer to size of @ids, updated on return
+ * @flags: reserved for future use, must be zero
+ *
+ * Returns a list of the active LSM ids. On success this function
+ * returns the number of @ids array elements. This value may be zero
+ * if there are no LSMs active. If @size is insufficient to contain
+ * the return data -E2BIG is returned and @size is set to the minimum
+ * required size. In all other cases a negative value indicating the
+ * error is returned.
+ */
+SYSCALL_DEFINE3(lsm_list_modules, u64 __user *, ids, size_t __user *, size,
+		u32, flags)
+{
+	size_t total_size = lsm_active_cnt * sizeof(*ids);
+	size_t usize;
+	int i;
+
+	if (flags)
+		return -EINVAL;
+
+	if (get_user(usize, size))
+		return -EFAULT;
+
+	if (put_user(total_size, size) != 0)
+		return -EFAULT;
+
+	if (usize < total_size)
+		return -E2BIG;
+
+	for (i = 0; i < lsm_active_cnt; i++)
+		if (put_user(lsm_idlist[i]->id, ids++))
+			return -EFAULT;
+
+	return lsm_active_cnt;
+}
diff --git a/security/safesetid/lsm.c b/security/safesetid/lsm.c
index 5be5894aa0ea..1ba564f097f5 100644
--- a/security/safesetid/lsm.c
+++ b/security/safesetid/lsm.c
@@ -19,6 +19,7 @@
 #include <linux/ptrace.h>
 #include <linux/sched/task_stack.h>
 #include <linux/security.h>
+#include <uapi/linux/lsm.h>
 #include "lsm.h"
 
 /* Flag indicating whether initialization completed */
@@ -261,6 +262,11 @@ static int safesetid_task_fix_setgroups(struct cred *new, const struct cred *old
 	return 0;
 }
 
+static const struct lsm_id safesetid_lsmid = {
+	.name = "safesetid",
+	.id = LSM_ID_SAFESETID,
+};
+
 static struct security_hook_list safesetid_security_hooks[] = {
 	LSM_HOOK_INIT(task_fix_setuid, safesetid_task_fix_setuid),
 	LSM_HOOK_INIT(task_fix_setgid, safesetid_task_fix_setgid),
@@ -271,7 +277,8 @@ static struct security_hook_list safesetid_security_hooks[] = {
 static int __init safesetid_security_init(void)
 {
 	security_add_hooks(safesetid_security_hooks,
-			   ARRAY_SIZE(safesetid_security_hooks), "safesetid");
+			   ARRAY_SIZE(safesetid_security_hooks),
+			   &safesetid_lsmid);
 
 	/* Report that SafeSetID successfully initialized */
 	safesetid_initialized = 1;
diff --git a/security/security.c b/security/security.c
index dcb3e7014f9b..0144a98d3712 100644
--- a/security/security.c
+++ b/security/security.c
@@ -35,6 +35,24 @@
 #define LSM_COUNT (__end_lsm_info - __start_lsm_info)
 
 /*
+ * How many LSMs are built into the kernel as determined at
+ * build time. Used to determine fixed array sizes.
+ * The capability module is accounted for by CONFIG_SECURITY
+ */
+#define LSM_CONFIG_COUNT ( \
+	(IS_ENABLED(CONFIG_SECURITY) ? 1 : 0) + \
+	(IS_ENABLED(CONFIG_SECURITY_SELINUX) ? 1 : 0) + \
+	(IS_ENABLED(CONFIG_SECURITY_SMACK) ? 1 : 0) + \
+	(IS_ENABLED(CONFIG_SECURITY_TOMOYO) ? 1 : 0) + \
+	(IS_ENABLED(CONFIG_SECURITY_APPARMOR) ? 1 : 0) + \
+	(IS_ENABLED(CONFIG_SECURITY_YAMA) ? 1 : 0) + \
+	(IS_ENABLED(CONFIG_SECURITY_LOADPIN) ? 1 : 0) + \
+	(IS_ENABLED(CONFIG_SECURITY_SAFESETID) ? 1 : 0) + \
+	(IS_ENABLED(CONFIG_SECURITY_LOCKDOWN_LSM) ? 1 : 0) + \
+	(IS_ENABLED(CONFIG_BPF_LSM) ? 1 : 0) + \
+	(IS_ENABLED(CONFIG_SECURITY_LANDLOCK) ? 1 : 0))
+
+/*
  * These are descriptions of the reasons that can be passed to the
  * security_locked_down() LSM hook. Placing this array here allows
  * all security modules to use the same descriptions for auditing
@@ -245,6 +263,12 @@ static void __init initialize_lsm(struct lsm_info *lsm)
 	}
 }
 
+/*
+ * Current index to use while initializing the lsm id list.
+ */
+u32 lsm_active_cnt __ro_after_init;
+const struct lsm_id *lsm_idlist[LSM_CONFIG_COUNT];
+
 /* Populate ordered LSMs list from comma-separated LSM name list. */
 static void __init ordered_lsm_parse(const char *order, const char *origin)
 {
@@ -513,17 +537,29 @@ static int lsm_append(const char *new, char **result)
  * security_add_hooks - Add a modules hooks to the hook lists.
  * @hooks: the hooks to add
  * @count: the number of hooks to add
- * @lsm: the name of the security module
+ * @lsmid: the identification information for the security module
  *
  * Each LSM has to register its hooks with the infrastructure.
  */
 void __init security_add_hooks(struct security_hook_list *hooks, int count,
-			       const char *lsm)
+			       const struct lsm_id *lsmid)
 {
 	int i;
 
+	/*
+	 * A security module may call security_add_hooks() more
+	 * than once during initialization, and LSM initialization
+	 * is serialized. Landlock is one such case.
+	 * Look at the previous entry, if there is one, for duplication.
+	 */
+	if (lsm_active_cnt == 0 || lsm_idlist[lsm_active_cnt - 1] != lsmid) {
+		if (lsm_active_cnt >= LSM_CONFIG_COUNT)
+			panic("%s Too many LSMs registered.\n", __func__);
+		lsm_idlist[lsm_active_cnt++] = lsmid;
+	}
+
 	for (i = 0; i < count; i++) {
-		hooks[i].lsm = lsm;
+		hooks[i].lsmid = lsmid;
 		hlist_add_tail_rcu(&hooks[i].list, hooks[i].head);
 	}
 
@@ -532,7 +568,7 @@ void __init security_add_hooks(struct security_hook_list *hooks, int count,
 	 * and fix this up afterwards.
 	 */
 	if (slab_is_available()) {
-		if (lsm_append(lsm, &lsm_names) < 0)
+		if (lsm_append(lsmid->name, &lsm_names) < 0)
 			panic("%s - Cannot get early memory.\n", __func__);
 	}
 }
@@ -734,6 +770,54 @@ static int lsm_superblock_alloc(struct super_block *sb)
 	return 0;
 }
 
+/**
+ * lsm_fill_user_ctx - Fill a user space lsm_ctx structure
+ * @uctx: a userspace LSM context to be filled
+ * @uctx_len: available uctx size (input), used uctx size (output)
+ * @val: the new LSM context value
+ * @val_len: the size of the new LSM context value
+ * @id: LSM id
+ * @flags: LSM defined flags
+ *
+ * Fill all of the fields in a userspace lsm_ctx structure.
+ *
+ * Returns 0 on success, -E2BIG if userspace buffer is not large enough,
+ * -EFAULT on a copyout error, -ENOMEM if memory can't be allocated.
+ */
+int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, size_t *uctx_len,
+		      void *val, size_t val_len,
+		      u64 id, u64 flags)
+{
+	struct lsm_ctx *nctx = NULL;
+	size_t nctx_len;
+	int rc = 0;
+
+	nctx_len = ALIGN(struct_size(nctx, ctx, val_len), sizeof(void *));
+	if (nctx_len > *uctx_len) {
+		rc = -E2BIG;
+		goto out;
+	}
+
+	nctx = kzalloc(nctx_len, GFP_KERNEL);
+	if (nctx == NULL) {
+		rc = -ENOMEM;
+		goto out;
+	}
+	nctx->id = id;
+	nctx->flags = flags;
+	nctx->len = nctx_len;
+	nctx->ctx_len = val_len;
+	memcpy(nctx->ctx, val, val_len);
+
+	if (copy_to_user(uctx, nctx, nctx_len))
+		rc = -EFAULT;
+
+out:
+	kfree(nctx);
+	*uctx_len = nctx_len;
+	return rc;
+}
+
 /*
  * The default value of the LSM hook is defined in linux/lsm_hook_defs.h and
  * can be accessed with:
@@ -2539,7 +2623,7 @@ int security_inode_copy_up_xattr(const char *name)
 			return rc;
 	}
 
-	return LSM_RET_DEFAULT(inode_copy_up_xattr);
+	return evm_inode_copy_up_xattr(name);
 }
 EXPORT_SYMBOL(security_inode_copy_up_xattr);
 
@@ -2580,13 +2664,7 @@ int security_kernfs_init_security(struct kernfs_node *kn_dir,
  */
 int security_file_permission(struct file *file, int mask)
 {
-	int ret;
-
-	ret = call_int_hook(file_permission, 0, file, mask);
-	if (ret)
-		return ret;
-
-	return fsnotify_perm(file, mask);
+	return call_int_hook(file_permission, 0, file, mask);
 }
 
 /**
@@ -2648,6 +2726,24 @@ int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 }
 EXPORT_SYMBOL_GPL(security_file_ioctl);
 
+/**
+ * security_file_ioctl_compat() - Check if an ioctl is allowed in compat mode
+ * @file: associated file
+ * @cmd: ioctl cmd
+ * @arg: ioctl arguments
+ *
+ * Compat version of security_file_ioctl() that correctly handles 32-bit
+ * processes running on 64-bit kernels.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_file_ioctl_compat(struct file *file, unsigned int cmd,
+			       unsigned long arg)
+{
+	return call_int_hook(file_ioctl_compat, 0, file, cmd, arg);
+}
+EXPORT_SYMBOL_GPL(security_file_ioctl_compat);
+
 static inline unsigned long mmap_prot(struct file *file, unsigned long prot)
 {
 	/*
@@ -2837,7 +2933,7 @@ int security_file_open(struct file *file)
 	if (ret)
 		return ret;
 
-	return fsnotify_perm(file, MAY_OPEN);
+	return fsnotify_open_perm(file);
 }
 
 /**
@@ -3800,10 +3896,158 @@ void security_d_instantiate(struct dentry *dentry, struct inode *inode)
 }
 EXPORT_SYMBOL(security_d_instantiate);
 
+/*
+ * Please keep this in sync with it's counterpart in security/lsm_syscalls.c
+ */
+
+/**
+ * security_getselfattr - Read an LSM attribute of the current process.
+ * @attr: which attribute to return
+ * @uctx: the user-space destination for the information, or NULL
+ * @size: pointer to the size of space available to receive the data
+ * @flags: special handling options. LSM_FLAG_SINGLE indicates that only
+ * attributes associated with the LSM identified in the passed @ctx be
+ * reported.
+ *
+ * A NULL value for @uctx can be used to get both the number of attributes
+ * and the size of the data.
+ *
+ * Returns the number of attributes found on success, negative value
+ * on error. @size is reset to the total size of the data.
+ * If @size is insufficient to contain the data -E2BIG is returned.
+ */
+int security_getselfattr(unsigned int attr, struct lsm_ctx __user *uctx,
+			 size_t __user *size, u32 flags)
+{
+	struct security_hook_list *hp;
+	struct lsm_ctx lctx = { .id = LSM_ID_UNDEF, };
+	u8 __user *base = (u8 __user *)uctx;
+	size_t total = 0;
+	size_t entrysize;
+	size_t left;
+	bool toobig = false;
+	bool single = false;
+	int count = 0;
+	int rc;
+
+	if (attr == LSM_ATTR_UNDEF)
+		return -EINVAL;
+	if (size == NULL)
+		return -EINVAL;
+	if (get_user(left, size))
+		return -EFAULT;
+
+	if (flags) {
+		/*
+		 * Only flag supported is LSM_FLAG_SINGLE
+		 */
+		if (flags != LSM_FLAG_SINGLE || !uctx)
+			return -EINVAL;
+		if (copy_from_user(&lctx, uctx, sizeof(lctx)))
+			return -EFAULT;
+		/*
+		 * If the LSM ID isn't specified it is an error.
+		 */
+		if (lctx.id == LSM_ID_UNDEF)
+			return -EINVAL;
+		single = true;
+	}
+
+	/*
+	 * In the usual case gather all the data from the LSMs.
+	 * In the single case only get the data from the LSM specified.
+	 */
+	hlist_for_each_entry(hp, &security_hook_heads.getselfattr, list) {
+		if (single && lctx.id != hp->lsmid->id)
+			continue;
+		entrysize = left;
+		if (base)
+			uctx = (struct lsm_ctx __user *)(base + total);
+		rc = hp->hook.getselfattr(attr, uctx, &entrysize, flags);
+		if (rc == -EOPNOTSUPP) {
+			rc = 0;
+			continue;
+		}
+		if (rc == -E2BIG) {
+			rc = 0;
+			left = 0;
+			toobig = true;
+		} else if (rc < 0)
+			return rc;
+		else
+			left -= entrysize;
+
+		total += entrysize;
+		count += rc;
+		if (single)
+			break;
+	}
+	if (put_user(total, size))
+		return -EFAULT;
+	if (toobig)
+		return -E2BIG;
+	if (count == 0)
+		return LSM_RET_DEFAULT(getselfattr);
+	return count;
+}
+
+/*
+ * Please keep this in sync with it's counterpart in security/lsm_syscalls.c
+ */
+
+/**
+ * security_setselfattr - Set an LSM attribute on the current process.
+ * @attr: which attribute to set
+ * @uctx: the user-space source for the information
+ * @size: the size of the data
+ * @flags: reserved for future use, must be 0
+ *
+ * Set an LSM attribute for the current process. The LSM, attribute
+ * and new value are included in @uctx.
+ *
+ * Returns 0 on success, -EINVAL if the input is inconsistent, -EFAULT
+ * if the user buffer is inaccessible, E2BIG if size is too big, or an
+ * LSM specific failure.
+ */
+int security_setselfattr(unsigned int attr, struct lsm_ctx __user *uctx,
+			 size_t size, u32 flags)
+{
+	struct security_hook_list *hp;
+	struct lsm_ctx *lctx;
+	int rc = LSM_RET_DEFAULT(setselfattr);
+
+	if (flags)
+		return -EINVAL;
+	if (size < sizeof(*lctx))
+		return -EINVAL;
+	if (size > PAGE_SIZE)
+		return -E2BIG;
+
+	lctx = memdup_user(uctx, size);
+	if (IS_ERR(lctx))
+		return PTR_ERR(lctx);
+
+	if (size < lctx->len || size < lctx->ctx_len + sizeof(*lctx) ||
+	    lctx->len < lctx->ctx_len + sizeof(*lctx)) {
+		rc = -EINVAL;
+		goto free_out;
+	}
+
+	hlist_for_each_entry(hp, &security_hook_heads.setselfattr, list)
+		if ((hp->lsmid->id) == lctx->id) {
+			rc = hp->hook.setselfattr(attr, lctx, size, flags);
+			break;
+		}
+
+free_out:
+	kfree(lctx);
+	return rc;
+}
+
 /**
  * security_getprocattr() - Read an attribute for a task
  * @p: the task
- * @lsm: LSM name
+ * @lsmid: LSM identification
  * @name: attribute name
  * @value: attribute value
  *
@@ -3811,13 +4055,13 @@ EXPORT_SYMBOL(security_d_instantiate);
  *
  * Return: Returns the length of @value on success, a negative value otherwise.
  */
-int security_getprocattr(struct task_struct *p, const char *lsm,
-			 const char *name, char **value)
+int security_getprocattr(struct task_struct *p, int lsmid, const char *name,
+			 char **value)
 {
 	struct security_hook_list *hp;
 
 	hlist_for_each_entry(hp, &security_hook_heads.getprocattr, list) {
-		if (lsm != NULL && strcmp(lsm, hp->lsm))
+		if (lsmid != 0 && lsmid != hp->lsmid->id)
 			continue;
 		return hp->hook.getprocattr(p, name, value);
 	}
@@ -3826,7 +4070,7 @@ int security_getprocattr(struct task_struct *p, const char *lsm,
 
 /**
  * security_setprocattr() - Set an attribute for a task
- * @lsm: LSM name
+ * @lsmid: LSM identification
  * @name: attribute name
  * @value: attribute value
  * @size: attribute value size
@@ -3836,13 +4080,12 @@ int security_getprocattr(struct task_struct *p, const char *lsm,
  *
  * Return: Returns bytes written on success, a negative value otherwise.
  */
-int security_setprocattr(const char *lsm, const char *name, void *value,
-			 size_t size)
+int security_setprocattr(int lsmid, const char *name, void *value, size_t size)
 {
 	struct security_hook_list *hp;
 
 	hlist_for_each_entry(hp, &security_hook_heads.setprocattr, list) {
-		if (lsm != NULL && strcmp(lsm, hp->lsm))
+		if (lsmid != 0 && lsmid != hp->lsmid->id)
 			continue;
 		return hp->hook.setprocattr(name, value, size);
 	}
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index feda711c6b7b..a6bf90ace84c 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -85,13 +85,15 @@
 #include <linux/export.h>
 #include <linux/msg.h>
 #include <linux/shm.h>
+#include <uapi/linux/shm.h>
 #include <linux/bpf.h>
 #include <linux/kernfs.h>
 #include <linux/stringhash.h>	/* for hashlen_string() */
 #include <uapi/linux/mount.h>
 #include <linux/fsnotify.h>
 #include <linux/fanotify.h>
-#include <linux/io_uring.h>
+#include <linux/io_uring/cmd.h>
+#include <uapi/linux/lsm.h>
 
 #include "avc.h"
 #include "objsec.h"
@@ -1660,8 +1662,6 @@ static int inode_has_perm(const struct cred *cred,
 	struct inode_security_struct *isec;
 	u32 sid;
 
-	validate_creds(cred);
-
 	if (unlikely(IS_PRIVATE(inode)))
 		return 0;
 
@@ -2315,6 +2315,19 @@ static int selinux_bprm_creds_for_exec(struct linux_binprm *bprm)
 	new_tsec->keycreate_sid = 0;
 	new_tsec->sockcreate_sid = 0;
 
+	/*
+	 * Before policy is loaded, label any task outside kernel space
+	 * as SECINITSID_INIT, so that any userspace tasks surviving from
+	 * early boot end up with a label different from SECINITSID_KERNEL
+	 * (if the policy chooses to set SECINITSID_INIT != SECINITSID_KERNEL).
+	 */
+	if (!selinux_initialized()) {
+		new_tsec->sid = SECINITSID_INIT;
+		/* also clear the exec_sid just in case */
+		new_tsec->exec_sid = 0;
+		return 0;
+	}
+
 	if (old_tsec->exec_sid) {
 		new_tsec->sid = old_tsec->exec_sid;
 		/* Reset exec SID on execve. */
@@ -3056,8 +3069,6 @@ static int selinux_inode_follow_link(struct dentry *dentry, struct inode *inode,
 	struct inode_security_struct *isec;
 	u32 sid;
 
-	validate_creds(cred);
-
 	ad.type = LSM_AUDIT_DATA_DENTRY;
 	ad.u.dentry = dentry;
 	sid = cred_sid(cred);
@@ -3101,8 +3112,6 @@ static int selinux_inode_permission(struct inode *inode, int mask)
 	if (!mask)
 		return 0;
 
-	validate_creds(cred);
-
 	if (unlikely(IS_PRIVATE(inode)))
 		return 0;
 
@@ -3731,6 +3740,33 @@ static int selinux_file_ioctl(struct file *file, unsigned int cmd,
 	return error;
 }
 
+static int selinux_file_ioctl_compat(struct file *file, unsigned int cmd,
+			      unsigned long arg)
+{
+	/*
+	 * If we are in a 64-bit kernel running 32-bit userspace, we need to
+	 * make sure we don't compare 32-bit flags to 64-bit flags.
+	 */
+	switch (cmd) {
+	case FS_IOC32_GETFLAGS:
+		cmd = FS_IOC_GETFLAGS;
+		break;
+	case FS_IOC32_SETFLAGS:
+		cmd = FS_IOC_SETFLAGS;
+		break;
+	case FS_IOC32_GETVERSION:
+		cmd = FS_IOC_GETVERSION;
+		break;
+	case FS_IOC32_SETVERSION:
+		cmd = FS_IOC_SETVERSION;
+		break;
+	default:
+		break;
+	}
+
+	return selinux_file_ioctl(file, cmd, arg);
+}
+
 static int default_noexec __ro_after_init;
 
 static int file_map_prot_check(struct file *file, unsigned long prot, int shared)
@@ -4553,6 +4589,21 @@ static int sock_has_perm(struct sock *sk, u32 perms)
 	if (sksec->sid == SECINITSID_KERNEL)
 		return 0;
 
+	/*
+	 * Before POLICYDB_CAP_USERSPACE_INITIAL_CONTEXT, sockets that
+	 * inherited the kernel context from early boot used to be skipped
+	 * here, so preserve that behavior unless the capability is set.
+	 *
+	 * By setting the capability the policy signals that it is ready
+	 * for this quirk to be fixed. Note that sockets created by a kernel
+	 * thread or a usermode helper executed without a transition will
+	 * still be skipped in this check regardless of the policycap
+	 * setting.
+	 */
+	if (!selinux_policycap_userspace_initial_context() &&
+	    sksec->sid == SECINITSID_INIT)
+		return 0;
+
 	ad_net_init_from_sk(&ad, &net, sk);
 
 	return avc_has_perm(current_sid(), sksec->sid, sksec->sclass, perms,
@@ -4667,6 +4718,13 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
 				return -EINVAL;
 			addr4 = (struct sockaddr_in *)address;
 			if (family_sa == AF_UNSPEC) {
+				if (family == PF_INET6) {
+					/* Length check from inet6_bind_sk() */
+					if (addrlen < SIN6_LEN_RFC2133)
+						return -EINVAL;
+					/* Family check from __inet6_bind() */
+					goto err_af;
+				}
 				/* see __inet_bind(), we only want to allow
 				 * AF_UNSPEC if the address is INADDR_ANY
 				 */
@@ -6284,8 +6342,8 @@ static void selinux_d_instantiate(struct dentry *dentry, struct inode *inode)
 		inode_doinit_with_dentry(inode, dentry);
 }
 
-static int selinux_getprocattr(struct task_struct *p,
-			       const char *name, char **value)
+static int selinux_lsm_getattr(unsigned int attr, struct task_struct *p,
+			       char **value)
 {
 	const struct task_security_struct *__tsec;
 	u32 sid;
@@ -6302,20 +6360,27 @@ static int selinux_getprocattr(struct task_struct *p,
 			goto bad;
 	}
 
-	if (!strcmp(name, "current"))
+	switch (attr) {
+	case LSM_ATTR_CURRENT:
 		sid = __tsec->sid;
-	else if (!strcmp(name, "prev"))
+		break;
+	case LSM_ATTR_PREV:
 		sid = __tsec->osid;
-	else if (!strcmp(name, "exec"))
+		break;
+	case LSM_ATTR_EXEC:
 		sid = __tsec->exec_sid;
-	else if (!strcmp(name, "fscreate"))
+		break;
+	case LSM_ATTR_FSCREATE:
 		sid = __tsec->create_sid;
-	else if (!strcmp(name, "keycreate"))
+		break;
+	case LSM_ATTR_KEYCREATE:
 		sid = __tsec->keycreate_sid;
-	else if (!strcmp(name, "sockcreate"))
+		break;
+	case LSM_ATTR_SOCKCREATE:
 		sid = __tsec->sockcreate_sid;
-	else {
-		error = -EINVAL;
+		break;
+	default:
+		error = -EOPNOTSUPP;
 		goto bad;
 	}
 	rcu_read_unlock();
@@ -6333,7 +6398,7 @@ bad:
 	return error;
 }
 
-static int selinux_setprocattr(const char *name, void *value, size_t size)
+static int selinux_lsm_setattr(u64 attr, void *value, size_t size)
 {
 	struct task_security_struct *tsec;
 	struct cred *new;
@@ -6344,23 +6409,31 @@ static int selinux_setprocattr(const char *name, void *value, size_t size)
 	/*
 	 * Basic control over ability to set these attributes at all.
 	 */
-	if (!strcmp(name, "exec"))
+	switch (attr) {
+	case LSM_ATTR_EXEC:
 		error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS,
 				     PROCESS__SETEXEC, NULL);
-	else if (!strcmp(name, "fscreate"))
+		break;
+	case LSM_ATTR_FSCREATE:
 		error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS,
 				     PROCESS__SETFSCREATE, NULL);
-	else if (!strcmp(name, "keycreate"))
+		break;
+	case LSM_ATTR_KEYCREATE:
 		error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS,
 				     PROCESS__SETKEYCREATE, NULL);
-	else if (!strcmp(name, "sockcreate"))
+		break;
+	case LSM_ATTR_SOCKCREATE:
 		error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS,
 				     PROCESS__SETSOCKCREATE, NULL);
-	else if (!strcmp(name, "current"))
+		break;
+	case LSM_ATTR_CURRENT:
 		error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS,
 				     PROCESS__SETCURRENT, NULL);
-	else
-		error = -EINVAL;
+		break;
+	default:
+		error = -EOPNOTSUPP;
+		break;
+	}
 	if (error)
 		return error;
 
@@ -6372,13 +6445,14 @@ static int selinux_setprocattr(const char *name, void *value, size_t size)
 		}
 		error = security_context_to_sid(value, size,
 						&sid, GFP_KERNEL);
-		if (error == -EINVAL && !strcmp(name, "fscreate")) {
+		if (error == -EINVAL && attr == LSM_ATTR_FSCREATE) {
 			if (!has_cap_mac_admin(true)) {
 				struct audit_buffer *ab;
 				size_t audit_size;
 
-				/* We strip a nul only if it is at the end, otherwise the
-				 * context contains a nul and we should audit that */
+				/* We strip a nul only if it is at the end,
+				 * otherwise the context contains a nul and
+				 * we should audit that */
 				if (str[size - 1] == '\0')
 					audit_size = size - 1;
 				else
@@ -6389,7 +6463,8 @@ static int selinux_setprocattr(const char *name, void *value, size_t size)
 				if (!ab)
 					return error;
 				audit_log_format(ab, "op=fscreate invalid_context=");
-				audit_log_n_untrustedstring(ab, value, audit_size);
+				audit_log_n_untrustedstring(ab, value,
+							    audit_size);
 				audit_log_end(ab);
 
 				return error;
@@ -6412,11 +6487,11 @@ static int selinux_setprocattr(const char *name, void *value, size_t size)
 	   checks and may_create for the file creation checks. The
 	   operation will then fail if the context is not permitted. */
 	tsec = selinux_cred(new);
-	if (!strcmp(name, "exec")) {
+	if (attr == LSM_ATTR_EXEC) {
 		tsec->exec_sid = sid;
-	} else if (!strcmp(name, "fscreate")) {
+	} else if (attr == LSM_ATTR_FSCREATE) {
 		tsec->create_sid = sid;
-	} else if (!strcmp(name, "keycreate")) {
+	} else if (attr == LSM_ATTR_KEYCREATE) {
 		if (sid) {
 			error = avc_has_perm(mysid, sid,
 					     SECCLASS_KEY, KEY__CREATE, NULL);
@@ -6424,14 +6499,13 @@ static int selinux_setprocattr(const char *name, void *value, size_t size)
 				goto abort_change;
 		}
 		tsec->keycreate_sid = sid;
-	} else if (!strcmp(name, "sockcreate")) {
+	} else if (attr == LSM_ATTR_SOCKCREATE) {
 		tsec->sockcreate_sid = sid;
-	} else if (!strcmp(name, "current")) {
+	} else if (attr == LSM_ATTR_CURRENT) {
 		error = -EINVAL;
 		if (sid == 0)
 			goto abort_change;
 
-		/* Only allow single threaded processes to change context */
 		if (!current_is_single_threaded()) {
 			error = security_bounded_transition(tsec->sid, sid);
 			if (error)
@@ -6468,6 +6542,69 @@ abort_change:
 	return error;
 }
 
+/**
+ * selinux_getselfattr - Get SELinux current task attributes
+ * @attr: the requested attribute
+ * @ctx: buffer to receive the result
+ * @size: buffer size (input), buffer size used (output)
+ * @flags: unused
+ *
+ * Fill the passed user space @ctx with the details of the requested
+ * attribute.
+ *
+ * Returns the number of attributes on success, an error code otherwise.
+ * There will only ever be one attribute.
+ */
+static int selinux_getselfattr(unsigned int attr, struct lsm_ctx __user *ctx,
+			       size_t *size, u32 flags)
+{
+	int rc;
+	char *val;
+	int val_len;
+
+	val_len = selinux_lsm_getattr(attr, current, &val);
+	if (val_len < 0)
+		return val_len;
+	rc = lsm_fill_user_ctx(ctx, size, val, val_len, LSM_ID_SELINUX, 0);
+	kfree(val);
+	return (!rc ? 1 : rc);
+}
+
+static int selinux_setselfattr(unsigned int attr, struct lsm_ctx *ctx,
+			       size_t size, u32 flags)
+{
+	int rc;
+
+	rc = selinux_lsm_setattr(attr, ctx->ctx, ctx->ctx_len);
+	if (rc > 0)
+		return 0;
+	return rc;
+}
+
+static int selinux_getprocattr(struct task_struct *p,
+			       const char *name, char **value)
+{
+	unsigned int attr = lsm_name_to_attr(name);
+	int rc;
+
+	if (attr) {
+		rc = selinux_lsm_getattr(attr, p, value);
+		if (rc != -EOPNOTSUPP)
+			return rc;
+	}
+
+	return -EINVAL;
+}
+
+static int selinux_setprocattr(const char *name, void *value, size_t size)
+{
+	int attr = lsm_name_to_attr(name);
+
+	if (attr)
+		return selinux_lsm_setattr(attr, value, size);
+	return -EINVAL;
+}
+
 static int selinux_ismaclabel(const char *name)
 {
 	return (strcmp(name, XATTR_SELINUX_SUFFIX) == 0);
@@ -6950,6 +7087,11 @@ static int selinux_uring_cmd(struct io_uring_cmd *ioucmd)
 }
 #endif /* CONFIG_IO_URING */
 
+static const struct lsm_id selinux_lsmid = {
+	.name = "selinux",
+	.id = LSM_ID_SELINUX,
+};
+
 /*
  * IMPORTANT NOTE: When adding new hooks, please be careful to keep this order:
  * 1. any hooks that don't belong to (2.) or (3.) below,
@@ -7036,6 +7178,7 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(file_permission, selinux_file_permission),
 	LSM_HOOK_INIT(file_alloc_security, selinux_file_alloc_security),
 	LSM_HOOK_INIT(file_ioctl, selinux_file_ioctl),
+	LSM_HOOK_INIT(file_ioctl_compat, selinux_file_ioctl_compat),
 	LSM_HOOK_INIT(mmap_file, selinux_mmap_file),
 	LSM_HOOK_INIT(mmap_addr, selinux_mmap_addr),
 	LSM_HOOK_INIT(file_mprotect, selinux_file_mprotect),
@@ -7091,6 +7234,8 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = {
 
 	LSM_HOOK_INIT(d_instantiate, selinux_d_instantiate),
 
+	LSM_HOOK_INIT(getselfattr, selinux_getselfattr),
+	LSM_HOOK_INIT(setselfattr, selinux_setselfattr),
 	LSM_HOOK_INIT(getprocattr, selinux_getprocattr),
 	LSM_HOOK_INIT(setprocattr, selinux_setprocattr),
 
@@ -7270,7 +7415,8 @@ static __init int selinux_init(void)
 
 	hashtab_cache_init();
 
-	security_add_hooks(selinux_hooks, ARRAY_SIZE(selinux_hooks), "selinux");
+	security_add_hooks(selinux_hooks, ARRAY_SIZE(selinux_hooks),
+			   &selinux_lsmid);
 
 	if (avc_add_callback(selinux_netcache_avc_callback, AVC_CALLBACK_RESET))
 		panic("SELinux: Unable to register AVC netcache callback\n");
diff --git a/security/selinux/include/audit.h b/security/selinux/include/audit.h
index d5495134a5b9..52aca71210b4 100644
--- a/security/selinux/include/audit.h
+++ b/security/selinux/include/audit.h
@@ -57,4 +57,3 @@ int selinux_audit_rule_match(u32 sid, u32 field, u32 op, void *rule);
 int selinux_audit_rule_known(struct audit_krule *rule);
 
 #endif /* _SELINUX_AUDIT_H */
-
diff --git a/security/selinux/include/avc.h b/security/selinux/include/avc.h
index 8f0aa66ccb13..96a614d47df8 100644
--- a/security/selinux/include/avc.h
+++ b/security/selinux/include/avc.h
@@ -4,6 +4,7 @@
  *
  * Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
  */
+
 #ifndef _SELINUX_AVC_H_
 #define _SELINUX_AVC_H_
 
@@ -60,11 +61,8 @@ struct selinux_audit_data {
 
 void __init avc_init(void);
 
-static inline u32 avc_audit_required(u32 requested,
-			      struct av_decision *avd,
-			      int result,
-			      u32 auditdeny,
-			      u32 *deniedp)
+static inline u32 avc_audit_required(u32 requested, struct av_decision *avd,
+				     int result, u32 auditdeny, u32 *deniedp)
 {
 	u32 denied, audited;
 	denied = requested & ~avd->allowed;
@@ -96,9 +94,8 @@ static inline u32 avc_audit_required(u32 requested,
 	return audited;
 }
 
-int slow_avc_audit(u32 ssid, u32 tsid, u16 tclass,
-		   u32 requested, u32 audited, u32 denied, int result,
-		   struct common_audit_data *a);
+int slow_avc_audit(u32 ssid, u32 tsid, u16 tclass, u32 requested, u32 audited,
+		   u32 denied, int result, struct common_audit_data *a);
 
 /**
  * avc_audit - Audit the granting or denial of permissions.
@@ -119,36 +116,29 @@ int slow_avc_audit(u32 ssid, u32 tsid, u16 tclass,
  * be performed under a lock, to allow the lock to be released
  * before calling the auditing code.
  */
-static inline int avc_audit(u32 ssid, u32 tsid,
-			    u16 tclass, u32 requested,
-			    struct av_decision *avd,
-			    int result,
+static inline int avc_audit(u32 ssid, u32 tsid, u16 tclass, u32 requested,
+			    struct av_decision *avd, int result,
 			    struct common_audit_data *a)
 {
 	u32 audited, denied;
 	audited = avc_audit_required(requested, avd, result, 0, &denied);
 	if (likely(!audited))
 		return 0;
-	return slow_avc_audit(ssid, tsid, tclass,
-			      requested, audited, denied, result,
-			      a);
+	return slow_avc_audit(ssid, tsid, tclass, requested, audited, denied,
+			      result, a);
 }
 
-#define AVC_STRICT 1 /* Ignore permissive mode. */
-#define AVC_EXTENDED_PERMS 2	/* update extended permissions */
-int avc_has_perm_noaudit(u32 ssid, u32 tsid,
-			 u16 tclass, u32 requested,
-			 unsigned flags,
-			 struct av_decision *avd);
+#define AVC_STRICT	   1 /* Ignore permissive mode. */
+#define AVC_EXTENDED_PERMS 2 /* update extended permissions */
+int avc_has_perm_noaudit(u32 ssid, u32 tsid, u16 tclass, u32 requested,
+			 unsigned int flags, struct av_decision *avd);
 
-int avc_has_perm(u32 ssid, u32 tsid,
-		 u16 tclass, u32 requested,
+int avc_has_perm(u32 ssid, u32 tsid, u16 tclass, u32 requested,
 		 struct common_audit_data *auditdata);
 
 int avc_has_extended_perms(u32 ssid, u32 tsid, u16 tclass, u32 requested,
 			   u8 driver, u8 perm, struct common_audit_data *ad);
 
-
 u32 avc_policy_seqno(void);
 
 #define AVC_CALLBACK_GRANT		1
@@ -156,7 +146,7 @@ u32 avc_policy_seqno(void);
 #define AVC_CALLBACK_REVOKE		4
 #define AVC_CALLBACK_RESET		8
 #define AVC_CALLBACK_AUDITALLOW_ENABLE	16
-#define AVC_CALLBACK_AUDITALLOW_DISABLE	32
+#define AVC_CALLBACK_AUDITALLOW_DISABLE 32
 #define AVC_CALLBACK_AUDITDENY_ENABLE	64
 #define AVC_CALLBACK_AUDITDENY_DISABLE	128
 #define AVC_CALLBACK_ADD_XPERMS		256
@@ -173,4 +163,3 @@ DECLARE_PER_CPU(struct avc_cache_stats, avc_cache_stats);
 #endif
 
 #endif /* _SELINUX_AVC_H_ */
-
diff --git a/security/selinux/include/avc_ss.h b/security/selinux/include/avc_ss.h
index 88b139e086c4..48ad64d54032 100644
--- a/security/selinux/include/avc_ss.h
+++ b/security/selinux/include/avc_ss.h
@@ -4,6 +4,7 @@
  *
  * Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
  */
+
 #ifndef _SELINUX_AVC_SS_H_
 #define _SELINUX_AVC_SS_H_
 
@@ -20,4 +21,3 @@ struct security_class_mapping {
 extern const struct security_class_mapping secclass_map[];
 
 #endif /* _SELINUX_AVC_SS_H_ */
-
diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h
index a3c380775d41..7229c9bf6c27 100644
--- a/security/selinux/include/classmap.h
+++ b/security/selinux/include/classmap.h
@@ -1,34 +1,40 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+
 #include <linux/capability.h>
 #include <linux/socket.h>
 
-#define COMMON_FILE_SOCK_PERMS "ioctl", "read", "write", "create", \
-    "getattr", "setattr", "lock", "relabelfrom", "relabelto", "append", "map"
+#define COMMON_FILE_SOCK_PERMS                                            \
+	"ioctl", "read", "write", "create", "getattr", "setattr", "lock", \
+		"relabelfrom", "relabelto", "append", "map"
 
-#define COMMON_FILE_PERMS COMMON_FILE_SOCK_PERMS, "unlink", "link", \
-    "rename", "execute", "quotaon", "mounton", "audit_access", \
-	"open", "execmod", "watch", "watch_mount", "watch_sb", \
-	"watch_with_perm", "watch_reads"
+#define COMMON_FILE_PERMS                                                \
+	COMMON_FILE_SOCK_PERMS, "unlink", "link", "rename", "execute",   \
+		"quotaon", "mounton", "audit_access", "open", "execmod", \
+		"watch", "watch_mount", "watch_sb", "watch_with_perm",   \
+		"watch_reads"
 
-#define COMMON_SOCK_PERMS COMMON_FILE_SOCK_PERMS, "bind", "connect", \
-    "listen", "accept", "getopt", "setopt", "shutdown", "recvfrom",  \
-    "sendto", "name_bind"
+#define COMMON_SOCK_PERMS                                              \
+	COMMON_FILE_SOCK_PERMS, "bind", "connect", "listen", "accept", \
+		"getopt", "setopt", "shutdown", "recvfrom", "sendto",  \
+		"name_bind"
 
-#define COMMON_IPC_PERMS "create", "destroy", "getattr", "setattr", "read", \
-	    "write", "associate", "unix_read", "unix_write"
+#define COMMON_IPC_PERMS                                            \
+	"create", "destroy", "getattr", "setattr", "read", "write", \
+		"associate", "unix_read", "unix_write"
 
-#define COMMON_CAP_PERMS  "chown", "dac_override", "dac_read_search", \
-	    "fowner", "fsetid", "kill", "setgid", "setuid", "setpcap", \
-	    "linux_immutable", "net_bind_service", "net_broadcast", \
-	    "net_admin", "net_raw", "ipc_lock", "ipc_owner", "sys_module", \
-	    "sys_rawio", "sys_chroot", "sys_ptrace", "sys_pacct", "sys_admin", \
-	    "sys_boot", "sys_nice", "sys_resource", "sys_time", \
-	    "sys_tty_config", "mknod", "lease", "audit_write", \
-	    "audit_control", "setfcap"
+#define COMMON_CAP_PERMS                                                     \
+	"chown", "dac_override", "dac_read_search", "fowner", "fsetid",      \
+		"kill", "setgid", "setuid", "setpcap", "linux_immutable",    \
+		"net_bind_service", "net_broadcast", "net_admin", "net_raw", \
+		"ipc_lock", "ipc_owner", "sys_module", "sys_rawio",          \
+		"sys_chroot", "sys_ptrace", "sys_pacct", "sys_admin",        \
+		"sys_boot", "sys_nice", "sys_resource", "sys_time",          \
+		"sys_tty_config", "mknod", "lease", "audit_write",           \
+		"audit_control", "setfcap"
 
-#define COMMON_CAP2_PERMS  "mac_override", "mac_admin", "syslog", \
-		"wake_alarm", "block_suspend", "audit_read", "perfmon", "bpf", \
-		"checkpoint_restore"
+#define COMMON_CAP2_PERMS                                                     \
+	"mac_override", "mac_admin", "syslog", "wake_alarm", "block_suspend", \
+		"audit_read", "perfmon", "bpf", "checkpoint_restore"
 
 #if CAP_LAST_CAP > CAP_CHECKPOINT_RESTORE
 #error New capability defined, please update COMMON_CAP2_PERMS.
@@ -40,224 +46,140 @@
  */
 const struct security_class_mapping secclass_map[] = {
 	{ "security",
-	  { "compute_av", "compute_create", "compute_member",
-	    "check_context", "load_policy", "compute_relabel",
-	    "compute_user", "setenforce", "setbool", "setsecparam",
-	    "setcheckreqprot", "read_policy", "validate_trans", NULL } },
+	  { "compute_av", "compute_create", "compute_member", "check_context",
+	    "load_policy", "compute_relabel", "compute_user", "setenforce",
+	    "setbool", "setsecparam", "setcheckreqprot", "read_policy",
+	    "validate_trans", NULL } },
 	{ "process",
-	  { "fork", "transition", "sigchld", "sigkill",
-	    "sigstop", "signull", "signal", "ptrace", "getsched", "setsched",
-	    "getsession", "getpgid", "setpgid", "getcap", "setcap", "share",
-	    "getattr", "setexec", "setfscreate", "noatsecure", "siginh",
-	    "setrlimit", "rlimitinh", "dyntransition", "setcurrent",
-	    "execmem", "execstack", "execheap", "setkeycreate",
-	    "setsockcreate", "getrlimit", NULL } },
-	{ "process2",
-	  { "nnp_transition", "nosuid_transition", NULL } },
+	  { "fork",	    "transition",    "sigchld",	    "sigkill",
+	    "sigstop",	    "signull",	     "signal",	    "ptrace",
+	    "getsched",	    "setsched",	     "getsession",  "getpgid",
+	    "setpgid",	    "getcap",	     "setcap",	    "share",
+	    "getattr",	    "setexec",	     "setfscreate", "noatsecure",
+	    "siginh",	    "setrlimit",     "rlimitinh",   "dyntransition",
+	    "setcurrent",   "execmem",	     "execstack",   "execheap",
+	    "setkeycreate", "setsockcreate", "getrlimit",   NULL } },
+	{ "process2", { "nnp_transition", "nosuid_transition", NULL } },
 	{ "system",
-	  { "ipc_info", "syslog_read", "syslog_mod",
-	    "syslog_console", "module_request", "module_load", NULL } },
-	{ "capability",
-	  { COMMON_CAP_PERMS, NULL } },
+	  { "ipc_info", "syslog_read", "syslog_mod", "syslog_console",
+	    "module_request", "module_load", NULL } },
+	{ "capability", { COMMON_CAP_PERMS, NULL } },
 	{ "filesystem",
-	  { "mount", "remount", "unmount", "getattr",
-	    "relabelfrom", "relabelto", "associate", "quotamod",
-	    "quotaget", "watch", NULL } },
+	  { "mount", "remount", "unmount", "getattr", "relabelfrom",
+	    "relabelto", "associate", "quotamod", "quotaget", "watch", NULL } },
 	{ "file",
-	  { COMMON_FILE_PERMS,
-	    "execute_no_trans", "entrypoint", NULL } },
+	  { COMMON_FILE_PERMS, "execute_no_trans", "entrypoint", NULL } },
 	{ "dir",
-	  { COMMON_FILE_PERMS, "add_name", "remove_name",
-	    "reparent", "search", "rmdir", NULL } },
+	  { COMMON_FILE_PERMS, "add_name", "remove_name", "reparent", "search",
+	    "rmdir", NULL } },
 	{ "fd", { "use", NULL } },
-	{ "lnk_file",
-	  { COMMON_FILE_PERMS, NULL } },
-	{ "chr_file",
-	  { COMMON_FILE_PERMS, NULL } },
-	{ "blk_file",
-	  { COMMON_FILE_PERMS, NULL } },
-	{ "sock_file",
-	  { COMMON_FILE_PERMS, NULL } },
-	{ "fifo_file",
-	  { COMMON_FILE_PERMS, NULL } },
-	{ "socket",
-	  { COMMON_SOCK_PERMS, NULL } },
+	{ "lnk_file", { COMMON_FILE_PERMS, NULL } },
+	{ "chr_file", { COMMON_FILE_PERMS, NULL } },
+	{ "blk_file", { COMMON_FILE_PERMS, NULL } },
+	{ "sock_file", { COMMON_FILE_PERMS, NULL } },
+	{ "fifo_file", { COMMON_FILE_PERMS, NULL } },
+	{ "socket", { COMMON_SOCK_PERMS, NULL } },
 	{ "tcp_socket",
-	  { COMMON_SOCK_PERMS,
-	    "node_bind", "name_connect",
-	    NULL } },
-	{ "udp_socket",
-	  { COMMON_SOCK_PERMS,
-	    "node_bind", NULL } },
-	{ "rawip_socket",
-	  { COMMON_SOCK_PERMS,
-	    "node_bind", NULL } },
-	{ "node",
-	  { "recvfrom", "sendto", NULL } },
-	{ "netif",
-	  { "ingress", "egress", NULL } },
-	{ "netlink_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "packet_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "key_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "unix_stream_socket",
-	  { COMMON_SOCK_PERMS, "connectto", NULL } },
-	{ "unix_dgram_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "sem",
-	  { COMMON_IPC_PERMS, NULL } },
+	  { COMMON_SOCK_PERMS, "node_bind", "name_connect", NULL } },
+	{ "udp_socket", { COMMON_SOCK_PERMS, "node_bind", NULL } },
+	{ "rawip_socket", { COMMON_SOCK_PERMS, "node_bind", NULL } },
+	{ "node", { "recvfrom", "sendto", NULL } },
+	{ "netif", { "ingress", "egress", NULL } },
+	{ "netlink_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "packet_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "key_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "unix_stream_socket", { COMMON_SOCK_PERMS, "connectto", NULL } },
+	{ "unix_dgram_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "sem", { COMMON_IPC_PERMS, NULL } },
 	{ "msg", { "send", "receive", NULL } },
-	{ "msgq",
-	  { COMMON_IPC_PERMS, "enqueue", NULL } },
-	{ "shm",
-	  { COMMON_IPC_PERMS, "lock", NULL } },
-	{ "ipc",
-	  { COMMON_IPC_PERMS, NULL } },
+	{ "msgq", { COMMON_IPC_PERMS, "enqueue", NULL } },
+	{ "shm", { COMMON_IPC_PERMS, "lock", NULL } },
+	{ "ipc", { COMMON_IPC_PERMS, NULL } },
 	{ "netlink_route_socket",
-	  { COMMON_SOCK_PERMS,
-	    "nlmsg_read", "nlmsg_write", NULL } },
+	  { COMMON_SOCK_PERMS, "nlmsg_read", "nlmsg_write", NULL } },
 	{ "netlink_tcpdiag_socket",
-	  { COMMON_SOCK_PERMS,
-	    "nlmsg_read", "nlmsg_write", NULL } },
-	{ "netlink_nflog_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
+	  { COMMON_SOCK_PERMS, "nlmsg_read", "nlmsg_write", NULL } },
+	{ "netlink_nflog_socket", { COMMON_SOCK_PERMS, NULL } },
 	{ "netlink_xfrm_socket",
-	  { COMMON_SOCK_PERMS,
-	    "nlmsg_read", "nlmsg_write", NULL } },
-	{ "netlink_selinux_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "netlink_iscsi_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
+	  { COMMON_SOCK_PERMS, "nlmsg_read", "nlmsg_write", NULL } },
+	{ "netlink_selinux_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "netlink_iscsi_socket", { COMMON_SOCK_PERMS, NULL } },
 	{ "netlink_audit_socket",
-	  { COMMON_SOCK_PERMS,
-	    "nlmsg_read", "nlmsg_write", "nlmsg_relay", "nlmsg_readpriv",
-	    "nlmsg_tty_audit", NULL } },
-	{ "netlink_fib_lookup_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "netlink_connector_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "netlink_netfilter_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "netlink_dnrt_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
+	  { COMMON_SOCK_PERMS, "nlmsg_read", "nlmsg_write", "nlmsg_relay",
+	    "nlmsg_readpriv", "nlmsg_tty_audit", NULL } },
+	{ "netlink_fib_lookup_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "netlink_connector_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "netlink_netfilter_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "netlink_dnrt_socket", { COMMON_SOCK_PERMS, NULL } },
 	{ "association",
 	  { "sendto", "recvfrom", "setcontext", "polmatch", NULL } },
-	{ "netlink_kobject_uevent_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "netlink_generic_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "netlink_scsitransport_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "netlink_rdma_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "netlink_crypto_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "appletalk_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
+	{ "netlink_kobject_uevent_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "netlink_generic_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "netlink_scsitransport_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "netlink_rdma_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "netlink_crypto_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "appletalk_socket", { COMMON_SOCK_PERMS, NULL } },
 	{ "packet",
 	  { "send", "recv", "relabelto", "forward_in", "forward_out", NULL } },
 	{ "key",
 	  { "view", "read", "write", "search", "link", "setattr", "create",
 	    NULL } },
 	{ "dccp_socket",
-	  { COMMON_SOCK_PERMS,
-	    "node_bind", "name_connect", NULL } },
+	  { COMMON_SOCK_PERMS, "node_bind", "name_connect", NULL } },
 	{ "memprotect", { "mmap_zero", NULL } },
 	{ "peer", { "recv", NULL } },
-	{ "capability2",
-	  { COMMON_CAP2_PERMS, NULL } },
+	{ "capability2", { COMMON_CAP2_PERMS, NULL } },
 	{ "kernel_service", { "use_as_override", "create_files_as", NULL } },
-	{ "tun_socket",
-	  { COMMON_SOCK_PERMS, "attach_queue", NULL } },
-	{ "binder", { "impersonate", "call", "set_context_mgr", "transfer",
-		      NULL } },
-	{ "cap_userns",
-	  { COMMON_CAP_PERMS, NULL } },
-	{ "cap2_userns",
-	  { COMMON_CAP2_PERMS, NULL } },
+	{ "tun_socket", { COMMON_SOCK_PERMS, "attach_queue", NULL } },
+	{ "binder",
+	  { "impersonate", "call", "set_context_mgr", "transfer", NULL } },
+	{ "cap_userns", { COMMON_CAP_PERMS, NULL } },
+	{ "cap2_userns", { COMMON_CAP2_PERMS, NULL } },
 	{ "sctp_socket",
-	  { COMMON_SOCK_PERMS,
-	    "node_bind", "name_connect", "association", NULL } },
-	{ "icmp_socket",
-	  { COMMON_SOCK_PERMS,
-	    "node_bind", NULL } },
-	{ "ax25_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "ipx_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "netrom_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "atmpvc_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "x25_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "rose_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "decnet_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "atmsvc_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "rds_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "irda_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "pppox_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "llc_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "can_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "tipc_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "bluetooth_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "iucv_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "rxrpc_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "isdn_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "phonet_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "ieee802154_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "caif_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "alg_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "nfc_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "vsock_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "kcm_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "qipcrtr_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "smc_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "infiniband_pkey",
-	  { "access", NULL } },
-	{ "infiniband_endport",
-	  { "manage_subnet", NULL } },
+	  { COMMON_SOCK_PERMS, "node_bind", "name_connect", "association",
+	    NULL } },
+	{ "icmp_socket", { COMMON_SOCK_PERMS, "node_bind", NULL } },
+	{ "ax25_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "ipx_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "netrom_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "atmpvc_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "x25_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "rose_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "decnet_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "atmsvc_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "rds_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "irda_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "pppox_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "llc_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "can_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "tipc_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "bluetooth_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "iucv_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "rxrpc_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "isdn_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "phonet_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "ieee802154_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "caif_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "alg_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "nfc_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "vsock_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "kcm_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "qipcrtr_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "smc_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "infiniband_pkey", { "access", NULL } },
+	{ "infiniband_endport", { "manage_subnet", NULL } },
 	{ "bpf",
 	  { "map_create", "map_read", "map_write", "prog_load", "prog_run",
 	    NULL } },
-	{ "xdp_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
-	{ "mctp_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
+	{ "xdp_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "mctp_socket", { COMMON_SOCK_PERMS, NULL } },
 	{ "perf_event",
 	  { "open", "cpu", "kernel", "tracepoint", "read", "write", NULL } },
-	{ "anon_inode",
-	  { COMMON_FILE_PERMS, NULL } },
-	{ "io_uring",
-	  { "override_creds", "sqpoll", "cmd", NULL } },
-	{ "user_namespace",
-	  { "create", NULL } },
+	{ "anon_inode", { COMMON_FILE_PERMS, NULL } },
+	{ "io_uring", { "override_creds", "sqpoll", "cmd", NULL } },
+	{ "user_namespace", { "create", NULL } },
 	{ NULL }
-  };
+};
 
 #if PF_MAX > 46
 #error New address family defined, please update secclass_map.
diff --git a/security/selinux/include/conditional.h b/security/selinux/include/conditional.h
index 693a654714eb..5910bb7c2eca 100644
--- a/security/selinux/include/conditional.h
+++ b/security/selinux/include/conditional.h
@@ -13,8 +13,8 @@
 
 #include "security.h"
 
-int security_get_bools(struct selinux_policy *policy,
-		       u32 *len, char ***names, int **values);
+int security_get_bools(struct selinux_policy *policy, u32 *len, char ***names,
+		       int **values);
 
 int security_set_bools(u32 len, int *values);
 
diff --git a/security/selinux/include/ima.h b/security/selinux/include/ima.h
index 93c05e97eb7f..38ab302f5946 100644
--- a/security/selinux/include/ima.h
+++ b/security/selinux/include/ima.h
@@ -25,4 +25,4 @@ static inline void selinux_ima_measure_state_locked(void)
 }
 #endif
 
-#endif	/* _SELINUX_IMA_H_ */
+#endif /* _SELINUX_IMA_H_ */
diff --git a/security/selinux/include/initial_sid_to_string.h b/security/selinux/include/initial_sid_to_string.h
index ecc6e74fa09b..99b353b2abb4 100644
--- a/security/selinux/include/initial_sid_to_string.h
+++ b/security/selinux/include/initial_sid_to_string.h
@@ -3,33 +3,32 @@
 #include <linux/stddef.h>
 
 static const char *const initial_sid_to_string[] = {
-	NULL,
-	"kernel",
-	"security",
-	"unlabeled",
-	NULL,
-	"file",
-	NULL,
-	NULL,
-	"any_socket",
-	"port",
-	"netif",
-	"netmsg",
-	"node",
-	NULL,
-	NULL,
-	NULL,
-	NULL,
-	NULL,
-	NULL,
-	NULL,
-	NULL,
-	NULL,
-	NULL,
-	NULL,
-	NULL,
-	NULL,
-	NULL,
-	"devnull",
+	NULL, /* zero placeholder, not used */
+	"kernel", /* kernel / SECINITSID_KERNEL */
+	"security", /* security / SECINITSID_SECURITY */
+	"unlabeled", /* unlabeled / SECINITSID_UNLABELED */
+	NULL, /* fs */
+	"file", /* file / SECINITSID_FILE */
+	NULL, /* file_labels */
+	"init", /* init / SECINITSID_INIT */
+	"any_socket", /* any_socket / SECINITSID_ANY_SOCKET */
+	"port", /* port / SECINITSID_PORT */
+	"netif", /* netif / SECINITSID_NETIF */
+	"netmsg", /* netmsg / SECINITSID_NETMSG */
+	"node", /* node / SECINITSID_NODE */
+	NULL, /* igmp_packet */
+	NULL, /* icmp_socket */
+	NULL, /* tcp_socket */
+	NULL, /* sysctl_modprobe */
+	NULL, /* sysctl */
+	NULL, /* sysctl_fs */
+	NULL, /* sysctl_kernel */
+	NULL, /* sysctl_net */
+	NULL, /* sysctl_net_unix */
+	NULL, /* sysctl_vm */
+	NULL, /* sysctl_dev */
+	NULL, /* kmod */
+	NULL, /* policy */
+	NULL, /* scmp_packet */
+	"devnull", /* devnull / SECINITSID_DEVNULL */
 };
-
diff --git a/security/selinux/include/netif.h b/security/selinux/include/netif.h
index 85ec30d11144..2838bdc170dd 100644
--- a/security/selinux/include/netif.h
+++ b/security/selinux/include/netif.h
@@ -11,6 +11,7 @@
  * Copyright (C) 2007 Hewlett-Packard Development Company, L.P.
  *                    Paul Moore <paul@paul-moore.com>
  */
+
 #ifndef _SELINUX_NETIF_H_
 #define _SELINUX_NETIF_H_
 
@@ -20,5 +21,4 @@ void sel_netif_flush(void);
 
 int sel_netif_sid(struct net *ns, int ifindex, u32 *sid);
 
-#endif	/* _SELINUX_NETIF_H_ */
-
+#endif /* _SELINUX_NETIF_H_ */
diff --git a/security/selinux/include/netlabel.h b/security/selinux/include/netlabel.h
index 4d0456d3d459..5731c0dcd3e8 100644
--- a/security/selinux/include/netlabel.h
+++ b/security/selinux/include/netlabel.h
@@ -32,25 +32,19 @@ void selinux_netlbl_err(struct sk_buff *skb, u16 family, int error,
 void selinux_netlbl_sk_security_free(struct sk_security_struct *sksec);
 void selinux_netlbl_sk_security_reset(struct sk_security_struct *sksec);
 
-int selinux_netlbl_skbuff_getsid(struct sk_buff *skb,
-				 u16 family,
-				 u32 *type,
+int selinux_netlbl_skbuff_getsid(struct sk_buff *skb, u16 family, u32 *type,
 				 u32 *sid);
-int selinux_netlbl_skbuff_setsid(struct sk_buff *skb,
-				 u16 family,
-				 u32 sid);
+int selinux_netlbl_skbuff_setsid(struct sk_buff *skb, u16 family, u32 sid);
 int selinux_netlbl_sctp_assoc_request(struct sctp_association *asoc,
-				     struct sk_buff *skb);
+				      struct sk_buff *skb);
 int selinux_netlbl_inet_conn_request(struct request_sock *req, u16 family);
 void selinux_netlbl_inet_csk_clone(struct sock *sk, u16 family);
 void selinux_netlbl_sctp_sk_clone(struct sock *sk, struct sock *newsk);
 int selinux_netlbl_socket_post_create(struct sock *sk, u16 family);
 int selinux_netlbl_sock_rcv_skb(struct sk_security_struct *sksec,
-				struct sk_buff *skb,
-				u16 family,
+				struct sk_buff *skb, u16 family,
 				struct common_audit_data *ad);
-int selinux_netlbl_socket_setsockopt(struct socket *sock,
-				     int level,
+int selinux_netlbl_socket_setsockopt(struct socket *sock, int level,
 				     int optname);
 int selinux_netlbl_socket_connect(struct sock *sk, struct sockaddr *addr);
 int selinux_netlbl_socket_connect_locked(struct sock *sk,
@@ -62,44 +56,40 @@ static inline void selinux_netlbl_cache_invalidate(void)
 	return;
 }
 
-static inline void selinux_netlbl_err(struct sk_buff *skb,
-				      u16 family,
-				      int error,
-				      int gateway)
+static inline void selinux_netlbl_err(struct sk_buff *skb, u16 family,
+				      int error, int gateway)
 {
 	return;
 }
 
-static inline void selinux_netlbl_sk_security_free(
-					       struct sk_security_struct *sksec)
+static inline void
+selinux_netlbl_sk_security_free(struct sk_security_struct *sksec)
 {
 	return;
 }
 
-static inline void selinux_netlbl_sk_security_reset(
-					       struct sk_security_struct *sksec)
+static inline void
+selinux_netlbl_sk_security_reset(struct sk_security_struct *sksec)
 {
 	return;
 }
 
-static inline int selinux_netlbl_skbuff_getsid(struct sk_buff *skb,
-					       u16 family,
-					       u32 *type,
-					       u32 *sid)
+static inline int selinux_netlbl_skbuff_getsid(struct sk_buff *skb, u16 family,
+					       u32 *type, u32 *sid)
 {
 	*type = NETLBL_NLTYPE_NONE;
 	*sid = SECSID_NULL;
 	return 0;
 }
-static inline int selinux_netlbl_skbuff_setsid(struct sk_buff *skb,
-					       u16 family,
+static inline int selinux_netlbl_skbuff_setsid(struct sk_buff *skb, u16 family,
 					       u32 sid)
 {
 	return 0;
 }
 
-static inline int selinux_netlbl_sctp_assoc_request(struct sctp_association *asoc,
-						    struct sk_buff *skb)
+static inline int
+selinux_netlbl_sctp_assoc_request(struct sctp_association *asoc,
+				  struct sk_buff *skb)
 {
 	return 0;
 }
@@ -117,21 +107,18 @@ static inline void selinux_netlbl_sctp_sk_clone(struct sock *sk,
 {
 	return;
 }
-static inline int selinux_netlbl_socket_post_create(struct sock *sk,
-						    u16 family)
+static inline int selinux_netlbl_socket_post_create(struct sock *sk, u16 family)
 {
 	return 0;
 }
 static inline int selinux_netlbl_sock_rcv_skb(struct sk_security_struct *sksec,
-					      struct sk_buff *skb,
-					      u16 family,
+					      struct sk_buff *skb, u16 family,
 					      struct common_audit_data *ad)
 {
 	return 0;
 }
 static inline int selinux_netlbl_socket_setsockopt(struct socket *sock,
-						   int level,
-						   int optname)
+						   int level, int optname)
 {
 	return 0;
 }
diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h
index 8159fd53c3de..dea1d6f3ed2d 100644
--- a/security/selinux/include/objsec.h
+++ b/security/selinux/include/objsec.h
@@ -13,6 +13,7 @@
  *  Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com>
  *  Copyright (C) 2016 Mellanox Technologies
  */
+
 #ifndef _SELINUX_OBJSEC_H_
 #define _SELINUX_OBJSEC_H_
 
@@ -29,122 +30,122 @@
 #include "avc.h"
 
 struct task_security_struct {
-	u32 osid;		/* SID prior to last execve */
-	u32 sid;		/* current SID */
-	u32 exec_sid;		/* exec SID */
-	u32 create_sid;		/* fscreate SID */
-	u32 keycreate_sid;	/* keycreate SID */
-	u32 sockcreate_sid;	/* fscreate SID */
+	u32 osid; /* SID prior to last execve */
+	u32 sid; /* current SID */
+	u32 exec_sid; /* exec SID */
+	u32 create_sid; /* fscreate SID */
+	u32 keycreate_sid; /* keycreate SID */
+	u32 sockcreate_sid; /* fscreate SID */
 } __randomize_layout;
 
 enum label_initialized {
-	LABEL_INVALID,		/* invalid or not initialized */
-	LABEL_INITIALIZED,	/* initialized */
+	LABEL_INVALID, /* invalid or not initialized */
+	LABEL_INITIALIZED, /* initialized */
 	LABEL_PENDING
 };
 
 struct inode_security_struct {
-	struct inode *inode;	/* back pointer to inode object */
-	struct list_head list;	/* list of inode_security_struct */
-	u32 task_sid;		/* SID of creating task */
-	u32 sid;		/* SID of this object */
-	u16 sclass;		/* security class of this object */
-	unsigned char initialized;	/* initialization flag */
+	struct inode *inode; /* back pointer to inode object */
+	struct list_head list; /* list of inode_security_struct */
+	u32 task_sid; /* SID of creating task */
+	u32 sid; /* SID of this object */
+	u16 sclass; /* security class of this object */
+	unsigned char initialized; /* initialization flag */
 	spinlock_t lock;
 };
 
 struct file_security_struct {
-	u32 sid;		/* SID of open file description */
-	u32 fown_sid;		/* SID of file owner (for SIGIO) */
-	u32 isid;		/* SID of inode at the time of file open */
-	u32 pseqno;		/* Policy seqno at the time of file open */
+	u32 sid; /* SID of open file description */
+	u32 fown_sid; /* SID of file owner (for SIGIO) */
+	u32 isid; /* SID of inode at the time of file open */
+	u32 pseqno; /* Policy seqno at the time of file open */
 };
 
 struct superblock_security_struct {
-	u32 sid;			/* SID of file system superblock */
-	u32 def_sid;			/* default SID for labeling */
-	u32 mntpoint_sid;		/* SECURITY_FS_USE_MNTPOINT context for files */
-	unsigned short behavior;	/* labeling behavior */
-	unsigned short flags;		/* which mount options were specified */
+	u32 sid; /* SID of file system superblock */
+	u32 def_sid; /* default SID for labeling */
+	u32 mntpoint_sid; /* SECURITY_FS_USE_MNTPOINT context for files */
+	unsigned short behavior; /* labeling behavior */
+	unsigned short flags; /* which mount options were specified */
 	struct mutex lock;
 	struct list_head isec_head;
 	spinlock_t isec_lock;
 };
 
 struct msg_security_struct {
-	u32 sid;	/* SID of message */
+	u32 sid; /* SID of message */
 };
 
 struct ipc_security_struct {
-	u16 sclass;	/* security class of this object */
-	u32 sid;	/* SID of IPC resource */
+	u16 sclass; /* security class of this object */
+	u32 sid; /* SID of IPC resource */
 };
 
 struct netif_security_struct {
-	struct net *ns;			/* network namespace */
-	int ifindex;			/* device index */
-	u32 sid;			/* SID for this interface */
+	struct net *ns; /* network namespace */
+	int ifindex; /* device index */
+	u32 sid; /* SID for this interface */
 };
 
 struct netnode_security_struct {
 	union {
-		__be32 ipv4;		/* IPv4 node address */
-		struct in6_addr ipv6;	/* IPv6 node address */
+		__be32 ipv4; /* IPv4 node address */
+		struct in6_addr ipv6; /* IPv6 node address */
 	} addr;
-	u32 sid;			/* SID for this node */
-	u16 family;			/* address family */
+	u32 sid; /* SID for this node */
+	u16 family; /* address family */
 };
 
 struct netport_security_struct {
-	u32 sid;			/* SID for this node */
-	u16 port;			/* port number */
-	u8 protocol;			/* transport protocol */
+	u32 sid; /* SID for this node */
+	u16 port; /* port number */
+	u8 protocol; /* transport protocol */
 };
 
 struct sk_security_struct {
 #ifdef CONFIG_NETLABEL
-	enum {				/* NetLabel state */
-		NLBL_UNSET = 0,
-		NLBL_REQUIRE,
-		NLBL_LABELED,
-		NLBL_REQSKB,
-		NLBL_CONNLABELED,
+	enum { /* NetLabel state */
+	       NLBL_UNSET = 0,
+	       NLBL_REQUIRE,
+	       NLBL_LABELED,
+	       NLBL_REQSKB,
+	       NLBL_CONNLABELED,
 	} nlbl_state;
 	struct netlbl_lsm_secattr *nlbl_secattr; /* NetLabel sec attributes */
 #endif
-	u32 sid;			/* SID of this object */
-	u32 peer_sid;			/* SID of peer */
-	u16 sclass;			/* sock security class */
-	enum {				/* SCTP association state */
-		SCTP_ASSOC_UNSET = 0,
-		SCTP_ASSOC_SET,
+	u32 sid; /* SID of this object */
+	u32 peer_sid; /* SID of peer */
+	u16 sclass; /* sock security class */
+	enum { /* SCTP association state */
+	       SCTP_ASSOC_UNSET = 0,
+	       SCTP_ASSOC_SET,
 	} sctp_assoc_state;
 };
 
 struct tun_security_struct {
-	u32 sid;			/* SID for the tun device sockets */
+	u32 sid; /* SID for the tun device sockets */
 };
 
 struct key_security_struct {
-	u32 sid;	/* SID of key */
+	u32 sid; /* SID of key */
 };
 
 struct ib_security_struct {
-	u32 sid;        /* SID of the queue pair or MAD agent */
+	u32 sid; /* SID of the queue pair or MAD agent */
 };
 
 struct pkey_security_struct {
-	u64	subnet_prefix; /* Port subnet prefix */
-	u16	pkey;	/* PKey number */
-	u32	sid;	/* SID of pkey */
+	u64 subnet_prefix; /* Port subnet prefix */
+	u16 pkey; /* PKey number */
+	u32 sid; /* SID of pkey */
 };
 
 struct bpf_security_struct {
-	u32 sid;  /* SID of bpf obj creator */
+	u32 sid; /* SID of bpf obj creator */
 };
 
 struct perf_event_security_struct {
-	u32 sid;  /* SID of perf_event obj creator */
+	u32 sid; /* SID of perf_event obj creator */
 };
 
 extern struct lsm_blob_sizes selinux_blob_sizes;
@@ -158,22 +159,22 @@ static inline struct file_security_struct *selinux_file(const struct file *file)
 	return file->f_security + selinux_blob_sizes.lbs_file;
 }
 
-static inline struct inode_security_struct *selinux_inode(
-						const struct inode *inode)
+static inline struct inode_security_struct *
+selinux_inode(const struct inode *inode)
 {
 	if (unlikely(!inode->i_security))
 		return NULL;
 	return inode->i_security + selinux_blob_sizes.lbs_inode;
 }
 
-static inline struct msg_security_struct *selinux_msg_msg(
-						const struct msg_msg *msg_msg)
+static inline struct msg_security_struct *
+selinux_msg_msg(const struct msg_msg *msg_msg)
 {
 	return msg_msg->security + selinux_blob_sizes.lbs_msg_msg;
 }
 
-static inline struct ipc_security_struct *selinux_ipc(
-						const struct kern_ipc_perm *ipc)
+static inline struct ipc_security_struct *
+selinux_ipc(const struct kern_ipc_perm *ipc)
 {
 	return ipc->security + selinux_blob_sizes.lbs_ipc;
 }
@@ -188,8 +189,8 @@ static inline u32 current_sid(void)
 	return tsec->sid;
 }
 
-static inline struct superblock_security_struct *selinux_superblock(
-					const struct super_block *superblock)
+static inline struct superblock_security_struct *
+selinux_superblock(const struct super_block *superblock)
 {
 	return superblock->s_security + selinux_blob_sizes.lbs_superblock;
 }
diff --git a/security/selinux/include/policycap.h b/security/selinux/include/policycap.h
index f35d3458e71d..dc3674eb29c1 100644
--- a/security/selinux/include/policycap.h
+++ b/security/selinux/include/policycap.h
@@ -1,4 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+
 #ifndef _SELINUX_POLICYCAP_H_
 #define _SELINUX_POLICYCAP_H_
 
@@ -12,6 +13,7 @@ enum {
 	POLICYDB_CAP_NNP_NOSUID_TRANSITION,
 	POLICYDB_CAP_GENFS_SECLABEL_SYMLINKS,
 	POLICYDB_CAP_IOCTL_SKIP_CLOEXEC,
+	POLICYDB_CAP_USERSPACE_INITIAL_CONTEXT,
 	__POLICYDB_CAP_MAX
 };
 #define POLICYDB_CAP_MAX (__POLICYDB_CAP_MAX - 1)
diff --git a/security/selinux/include/policycap_names.h b/security/selinux/include/policycap_names.h
index 49bbe120d173..2cffcc1ce851 100644
--- a/security/selinux/include/policycap_names.h
+++ b/security/selinux/include/policycap_names.h
@@ -1,9 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+
 #ifndef _SELINUX_POLICYCAP_NAMES_H_
 #define _SELINUX_POLICYCAP_NAMES_H_
 
 #include "policycap.h"
 
+/* clang-format off */
 /* Policy capability names */
 const char *const selinux_policycap_names[__POLICYDB_CAP_MAX] = {
 	"network_peer_controls",
@@ -14,6 +16,8 @@ const char *const selinux_policycap_names[__POLICYDB_CAP_MAX] = {
 	"nnp_nosuid_transition",
 	"genfs_seclabel_symlinks",
 	"ioctl_skip_cloexec",
+	"userspace_initial_context",
 };
+/* clang-format on */
 
 #endif /* _SELINUX_POLICYCAP_NAMES_H_ */
diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h
index a9de89af8fdc..289bf9233f71 100644
--- a/security/selinux/include/security.h
+++ b/security/selinux/include/security.h
@@ -21,57 +21,57 @@
 #include "flask.h"
 #include "policycap.h"
 
-#define SECSID_NULL			0x00000000 /* unspecified SID */
-#define SECSID_WILD			0xffffffff /* wildcard SID */
-#define SECCLASS_NULL			0x0000 /* no class */
+#define SECSID_NULL   0x00000000 /* unspecified SID */
+#define SECSID_WILD   0xffffffff /* wildcard SID */
+#define SECCLASS_NULL 0x0000 /* no class */
 
 /* Identify specific policy version changes */
-#define POLICYDB_VERSION_BASE		15
-#define POLICYDB_VERSION_BOOL		16
-#define POLICYDB_VERSION_IPV6		17
-#define POLICYDB_VERSION_NLCLASS	18
-#define POLICYDB_VERSION_VALIDATETRANS	19
-#define POLICYDB_VERSION_MLS		19
-#define POLICYDB_VERSION_AVTAB		20
-#define POLICYDB_VERSION_RANGETRANS	21
-#define POLICYDB_VERSION_POLCAP		22
-#define POLICYDB_VERSION_PERMISSIVE	23
-#define POLICYDB_VERSION_BOUNDARY	24
-#define POLICYDB_VERSION_FILENAME_TRANS	25
-#define POLICYDB_VERSION_ROLETRANS	26
-#define POLICYDB_VERSION_NEW_OBJECT_DEFAULTS	27
-#define POLICYDB_VERSION_DEFAULT_TYPE	28
-#define POLICYDB_VERSION_CONSTRAINT_NAMES	29
-#define POLICYDB_VERSION_XPERMS_IOCTL	30
-#define POLICYDB_VERSION_INFINIBAND		31
-#define POLICYDB_VERSION_GLBLUB		32
-#define POLICYDB_VERSION_COMP_FTRANS	33 /* compressed filename transitions */
+#define POLICYDB_VERSION_BASE		     15
+#define POLICYDB_VERSION_BOOL		     16
+#define POLICYDB_VERSION_IPV6		     17
+#define POLICYDB_VERSION_NLCLASS	     18
+#define POLICYDB_VERSION_VALIDATETRANS	     19
+#define POLICYDB_VERSION_MLS		     19
+#define POLICYDB_VERSION_AVTAB		     20
+#define POLICYDB_VERSION_RANGETRANS	     21
+#define POLICYDB_VERSION_POLCAP		     22
+#define POLICYDB_VERSION_PERMISSIVE	     23
+#define POLICYDB_VERSION_BOUNDARY	     24
+#define POLICYDB_VERSION_FILENAME_TRANS	     25
+#define POLICYDB_VERSION_ROLETRANS	     26
+#define POLICYDB_VERSION_NEW_OBJECT_DEFAULTS 27
+#define POLICYDB_VERSION_DEFAULT_TYPE	     28
+#define POLICYDB_VERSION_CONSTRAINT_NAMES    29
+#define POLICYDB_VERSION_XPERMS_IOCTL	     30
+#define POLICYDB_VERSION_INFINIBAND	     31
+#define POLICYDB_VERSION_GLBLUB		     32
+#define POLICYDB_VERSION_COMP_FTRANS	     33 /* compressed filename transitions */
 
 /* Range of policy versions we understand*/
-#define POLICYDB_VERSION_MIN   POLICYDB_VERSION_BASE
-#define POLICYDB_VERSION_MAX   POLICYDB_VERSION_COMP_FTRANS
+#define POLICYDB_VERSION_MIN POLICYDB_VERSION_BASE
+#define POLICYDB_VERSION_MAX POLICYDB_VERSION_COMP_FTRANS
 
 /* Mask for just the mount related flags */
-#define SE_MNTMASK	0x0f
+#define SE_MNTMASK 0x0f
 /* Super block security struct flags for mount options */
 /* BE CAREFUL, these need to be the low order bits for selinux_get_mnt_opts */
 #define CONTEXT_MNT	0x01
 #define FSCONTEXT_MNT	0x02
-#define ROOTCONTEXT_MNT	0x04
+#define ROOTCONTEXT_MNT 0x04
 #define DEFCONTEXT_MNT	0x08
 #define SBLABEL_MNT	0x10
 /* Non-mount related flags */
-#define SE_SBINITIALIZED	0x0100
-#define SE_SBPROC		0x0200
-#define SE_SBGENFS		0x0400
-#define SE_SBGENFS_XATTR	0x0800
-#define SE_SBNATIVE		0x1000
+#define SE_SBINITIALIZED 0x0100
+#define SE_SBPROC	 0x0200
+#define SE_SBGENFS	 0x0400
+#define SE_SBGENFS_XATTR 0x0800
+#define SE_SBNATIVE	 0x1000
 
 #define CONTEXT_STR	"context"
 #define FSCONTEXT_STR	"fscontext"
-#define ROOTCONTEXT_STR	"rootcontext"
+#define ROOTCONTEXT_STR "rootcontext"
 #define DEFCONTEXT_STR	"defcontext"
-#define SECLABEL_STR "seclabel"
+#define SECLABEL_STR	"seclabel"
 
 struct netlbl_lsm_secattr;
 
@@ -81,11 +81,11 @@ extern int selinux_enabled_boot;
  * type_datum properties
  * available at the kernel policy version >= POLICYDB_VERSION_BOUNDARY
  */
-#define TYPEDATUM_PROPERTY_PRIMARY	0x0001
-#define TYPEDATUM_PROPERTY_ATTRIBUTE	0x0002
+#define TYPEDATUM_PROPERTY_PRIMARY   0x0001
+#define TYPEDATUM_PROPERTY_ATTRIBUTE 0x0002
 
 /* limitation of boundary depth  */
-#define POLICYDB_BOUNDS_MAXDEPTH	4
+#define POLICYDB_BOUNDS_MAXDEPTH 4
 
 struct selinux_policy;
 
@@ -189,6 +189,12 @@ static inline bool selinux_policycap_ioctl_skip_cloexec(void)
 		selinux_state.policycap[POLICYDB_CAP_IOCTL_SKIP_CLOEXEC]);
 }
 
+static inline bool selinux_policycap_userspace_initial_context(void)
+{
+	return READ_ONCE(
+		selinux_state.policycap[POLICYDB_CAP_USERSPACE_INITIAL_CONTEXT]);
+}
+
 struct selinux_policy_convert_data;
 
 struct selinux_load_state {
@@ -214,12 +220,12 @@ struct av_decision {
 	u32 flags;
 };
 
-#define XPERMS_ALLOWED 1
+#define XPERMS_ALLOWED	  1
 #define XPERMS_AUDITALLOW 2
-#define XPERMS_DONTAUDIT 4
+#define XPERMS_DONTAUDIT  4
 
-#define security_xperm_set(perms, x) ((perms)[(x) >> 5] |= 1 << ((x) & 0x1f))
-#define security_xperm_test(perms, x) (1 & ((perms)[(x) >> 5] >> ((x) & 0x1f)))
+#define security_xperm_set(perms, x)  ((perms)[(x) >> 5] |= 1 << ((x)&0x1f))
+#define security_xperm_test(perms, x) (1 & ((perms)[(x) >> 5] >> ((x)&0x1f)))
 struct extended_perms_data {
 	u32 p[8];
 };
@@ -233,23 +239,22 @@ struct extended_perms_decision {
 };
 
 struct extended_perms {
-	u16 len;	/* length associated decision chain */
+	u16 len; /* length associated decision chain */
 	struct extended_perms_data drivers; /* flag drivers that are used */
 };
 
 /* definitions of av_decision.flags */
-#define AVD_FLAGS_PERMISSIVE	0x0001
+#define AVD_FLAGS_PERMISSIVE 0x0001
 
-void security_compute_av(u32 ssid, u32 tsid,
-			 u16 tclass, struct av_decision *avd,
+void security_compute_av(u32 ssid, u32 tsid, u16 tclass,
+			 struct av_decision *avd,
 			 struct extended_perms *xperms);
 
-void security_compute_xperms_decision(u32 ssid, u32 tsid, u16 tclass,
-				      u8 driver,
+void security_compute_xperms_decision(u32 ssid, u32 tsid, u16 tclass, u8 driver,
 				      struct extended_perms_decision *xpermd);
 
-void security_compute_av_user(u32 ssid, u32 tsid,
-			      u16 tclass, struct av_decision *avd);
+void security_compute_av_user(u32 ssid, u32 tsid, u16 tclass,
+			      struct av_decision *avd);
 
 int security_transition_sid(u32 ssid, u32 tsid, u16 tclass,
 			    const struct qstr *qstr, u32 *out_sid);
@@ -288,8 +293,7 @@ int security_ib_endport_sid(const char *dev_name, u8 port_num, u32 *out_sid);
 
 int security_netif_sid(char *name, u32 *if_sid);
 
-int security_node_sid(u16 domain, void *addr, u32 addrlen,
-		      u32 *out_sid);
+int security_node_sid(u16 domain, void *addr, u32 addrlen, u32 *out_sid);
 
 int security_validate_transition(u32 oldsid, u32 newsid, u32 tasksid,
 				 u16 tclass);
@@ -301,50 +305,47 @@ int security_bounded_transition(u32 oldsid, u32 newsid);
 
 int security_sid_mls_copy(u32 sid, u32 mls_sid, u32 *new_sid);
 
-int security_net_peersid_resolve(u32 nlbl_sid, u32 nlbl_type,
-				 u32 xfrm_sid,
+int security_net_peersid_resolve(u32 nlbl_sid, u32 nlbl_type, u32 xfrm_sid,
 				 u32 *peer_sid);
 
-int security_get_classes(struct selinux_policy *policy,
-			 char ***classes, u32 *nclasses);
-int security_get_permissions(struct selinux_policy *policy,
-			     const char *class, char ***perms, u32 *nperms);
+int security_get_classes(struct selinux_policy *policy, char ***classes,
+			 u32 *nclasses);
+int security_get_permissions(struct selinux_policy *policy, const char *class,
+			     char ***perms, u32 *nperms);
 int security_get_reject_unknown(void);
 int security_get_allow_unknown(void);
 
-#define SECURITY_FS_USE_XATTR		1 /* use xattr */
-#define SECURITY_FS_USE_TRANS		2 /* use transition SIDs, e.g. devpts/tmpfs */
-#define SECURITY_FS_USE_TASK		3 /* use task SIDs, e.g. pipefs/sockfs */
-#define SECURITY_FS_USE_GENFS		4 /* use the genfs support */
-#define SECURITY_FS_USE_NONE		5 /* no labeling support */
-#define SECURITY_FS_USE_MNTPOINT	6 /* use mountpoint labeling */
-#define SECURITY_FS_USE_NATIVE		7 /* use native label support */
-#define SECURITY_FS_USE_MAX		7 /* Highest SECURITY_FS_USE_XXX */
+#define SECURITY_FS_USE_XATTR	 1 /* use xattr */
+#define SECURITY_FS_USE_TRANS	 2 /* use transition SIDs, e.g. devpts/tmpfs */
+#define SECURITY_FS_USE_TASK	 3 /* use task SIDs, e.g. pipefs/sockfs */
+#define SECURITY_FS_USE_GENFS	 4 /* use the genfs support */
+#define SECURITY_FS_USE_NONE	 5 /* no labeling support */
+#define SECURITY_FS_USE_MNTPOINT 6 /* use mountpoint labeling */
+#define SECURITY_FS_USE_NATIVE	 7 /* use native label support */
+#define SECURITY_FS_USE_MAX	 7 /* Highest SECURITY_FS_USE_XXX */
 
 int security_fs_use(struct super_block *sb);
 
 int security_genfs_sid(const char *fstype, const char *path, u16 sclass,
 		       u32 *sid);
 
-int selinux_policy_genfs_sid(struct selinux_policy *policy,
-		       const char *fstype, const char *path, u16 sclass,
-		       u32 *sid);
+int selinux_policy_genfs_sid(struct selinux_policy *policy, const char *fstype,
+			     const char *path, u16 sclass, u32 *sid);
 
 #ifdef CONFIG_NETLABEL
 int security_netlbl_secattr_to_sid(struct netlbl_lsm_secattr *secattr,
 				   u32 *sid);
 
-int security_netlbl_sid_to_secattr(u32 sid,
-				   struct netlbl_lsm_secattr *secattr);
+int security_netlbl_sid_to_secattr(u32 sid, struct netlbl_lsm_secattr *secattr);
 #else
-static inline int security_netlbl_secattr_to_sid(struct netlbl_lsm_secattr *secattr,
-					    u32 *sid)
+static inline int
+security_netlbl_secattr_to_sid(struct netlbl_lsm_secattr *secattr, u32 *sid)
 {
 	return -EIDRM;
 }
 
-static inline int security_netlbl_sid_to_secattr(u32 sid,
-					 struct netlbl_lsm_secattr *secattr)
+static inline int
+security_netlbl_sid_to_secattr(u32 sid, struct netlbl_lsm_secattr *secattr)
 {
 	return -ENOENT;
 }
@@ -357,13 +358,13 @@ const char *security_get_initial_sid_context(u32 sid);
  */
 extern struct page *selinux_kernel_status_page(void);
 
-#define SELINUX_KERNEL_STATUS_VERSION	1
+#define SELINUX_KERNEL_STATUS_VERSION 1
 struct selinux_kernel_status {
-	u32	version;	/* version number of the structure */
-	u32	sequence;	/* sequence number of seqlock logic */
-	u32	enforcing;	/* current setting of enforcing mode */
-	u32	policyload;	/* times of policy reloaded */
-	u32	deny_unknown;	/* current setting of deny_unknown */
+	u32 version; /* version number of the structure */
+	u32 sequence; /* sequence number of seqlock logic */
+	u32 enforcing; /* current setting of enforcing mode */
+	u32 policyload; /* times of policy reloaded */
+	u32 deny_unknown; /* current setting of deny_unknown */
 	/*
 	 * The version > 0 supports above members.
 	 */
diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h
index c75839860200..de485556ae29 100644
--- a/security/selinux/include/xfrm.h
+++ b/security/selinux/include/xfrm.h
@@ -5,6 +5,7 @@
  * Author : Trent Jaeger, <jaegert@us.ibm.com>
  * Updated : Venkat Yekkirala, <vyekkirala@TrustedCS.com>
  */
+
 #ifndef _SELINUX_XFRM_H_
 #define _SELINUX_XFRM_H_
 
@@ -13,8 +14,7 @@
 #include <net/xfrm.h>
 
 int selinux_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
-			      struct xfrm_user_sec_ctx *uctx,
-			      gfp_t gfp);
+			      struct xfrm_user_sec_ctx *uctx, gfp_t gfp);
 int selinux_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx,
 			      struct xfrm_sec_ctx **new_ctxp);
 void selinux_xfrm_policy_free(struct xfrm_sec_ctx *ctx);
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index 6c596ae7fef9..0619a1cbbfbe 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -336,12 +336,9 @@ static struct dentry *sel_make_dir(struct dentry *dir, const char *name,
 			unsigned long *ino);
 
 /* declaration for sel_make_policy_nodes */
-static struct dentry *sel_make_disconnected_dir(struct super_block *sb,
+static struct dentry *sel_make_swapover_dir(struct super_block *sb,
 						unsigned long *ino);
 
-/* declaration for sel_make_policy_nodes */
-static void sel_remove_entries(struct dentry *de);
-
 static ssize_t sel_read_mls(struct file *filp, char __user *buf,
 				size_t count, loff_t *ppos)
 {
@@ -508,13 +505,13 @@ static int sel_make_policy_nodes(struct selinux_fs_info *fsi,
 				struct selinux_policy *newpolicy)
 {
 	int ret = 0;
-	struct dentry *tmp_parent, *tmp_bool_dir, *tmp_class_dir, *old_dentry;
-	unsigned int tmp_bool_num, old_bool_num;
-	char **tmp_bool_names, **old_bool_names;
-	int *tmp_bool_values, *old_bool_values;
+	struct dentry *tmp_parent, *tmp_bool_dir, *tmp_class_dir;
+	unsigned int bool_num = 0;
+	char **bool_names = NULL;
+	int *bool_values = NULL;
 	unsigned long tmp_ino = fsi->last_ino; /* Don't increment last_ino in this function */
 
-	tmp_parent = sel_make_disconnected_dir(fsi->sb, &tmp_ino);
+	tmp_parent = sel_make_swapover_dir(fsi->sb, &tmp_ino);
 	if (IS_ERR(tmp_parent))
 		return PTR_ERR(tmp_parent);
 
@@ -532,8 +529,8 @@ static int sel_make_policy_nodes(struct selinux_fs_info *fsi,
 		goto out;
 	}
 
-	ret = sel_make_bools(newpolicy, tmp_bool_dir, &tmp_bool_num,
-			     &tmp_bool_names, &tmp_bool_values);
+	ret = sel_make_bools(newpolicy, tmp_bool_dir, &bool_num,
+			     &bool_names, &bool_values);
 	if (ret)
 		goto out;
 
@@ -542,38 +539,30 @@ static int sel_make_policy_nodes(struct selinux_fs_info *fsi,
 	if (ret)
 		goto out;
 
+	lock_rename(tmp_parent, fsi->sb->s_root);
+
 	/* booleans */
-	old_dentry = fsi->bool_dir;
-	lock_rename(tmp_bool_dir, old_dentry);
 	d_exchange(tmp_bool_dir, fsi->bool_dir);
 
-	old_bool_num = fsi->bool_num;
-	old_bool_names = fsi->bool_pending_names;
-	old_bool_values = fsi->bool_pending_values;
-
-	fsi->bool_num = tmp_bool_num;
-	fsi->bool_pending_names = tmp_bool_names;
-	fsi->bool_pending_values = tmp_bool_values;
-
-	sel_remove_old_bool_data(old_bool_num, old_bool_names, old_bool_values);
+	swap(fsi->bool_num, bool_num);
+	swap(fsi->bool_pending_names, bool_names);
+	swap(fsi->bool_pending_values, bool_values);
 
 	fsi->bool_dir = tmp_bool_dir;
-	unlock_rename(tmp_bool_dir, old_dentry);
 
 	/* classes */
-	old_dentry = fsi->class_dir;
-	lock_rename(tmp_class_dir, old_dentry);
 	d_exchange(tmp_class_dir, fsi->class_dir);
 	fsi->class_dir = tmp_class_dir;
-	unlock_rename(tmp_class_dir, old_dentry);
+
+	unlock_rename(tmp_parent, fsi->sb->s_root);
 
 out:
+	sel_remove_old_bool_data(bool_num, bool_names, bool_values);
 	/* Since the other temporary dirs are children of tmp_parent
 	 * this will handle all the cleanup in the case of a failure before
 	 * the swapover
 	 */
-	sel_remove_entries(tmp_parent);
-	dput(tmp_parent); /* d_genocide() only handles the children */
+	simple_recursive_removal(tmp_parent, NULL);
 
 	return ret;
 }
@@ -1351,54 +1340,48 @@ static const struct file_operations sel_commit_bools_ops = {
 	.llseek		= generic_file_llseek,
 };
 
-static void sel_remove_entries(struct dentry *de)
-{
-	d_genocide(de);
-	shrink_dcache_parent(de);
-}
-
 static int sel_make_bools(struct selinux_policy *newpolicy, struct dentry *bool_dir,
 			  unsigned int *bool_num, char ***bool_pending_names,
 			  int **bool_pending_values)
 {
 	int ret;
-	ssize_t len;
-	struct dentry *dentry = NULL;
-	struct inode *inode = NULL;
-	struct inode_security_struct *isec;
-	char **names = NULL, *page;
+	char **names, *page;
 	u32 i, num;
-	int *values = NULL;
-	u32 sid;
 
-	ret = -ENOMEM;
 	page = (char *)get_zeroed_page(GFP_KERNEL);
 	if (!page)
-		goto out;
+		return -ENOMEM;
 
-	ret = security_get_bools(newpolicy, &num, &names, &values);
+	ret = security_get_bools(newpolicy, &num, &names, bool_pending_values);
 	if (ret)
 		goto out;
 
+	*bool_num = num;
+	*bool_pending_names = names;
+
 	for (i = 0; i < num; i++) {
-		ret = -ENOMEM;
+		struct dentry *dentry;
+		struct inode *inode;
+		struct inode_security_struct *isec;
+		ssize_t len;
+		u32 sid;
+
+		len = snprintf(page, PAGE_SIZE, "/%s/%s", BOOL_DIR_NAME, names[i]);
+		if (len >= PAGE_SIZE) {
+			ret = -ENAMETOOLONG;
+			break;
+		}
 		dentry = d_alloc_name(bool_dir, names[i]);
-		if (!dentry)
-			goto out;
+		if (!dentry) {
+			ret = -ENOMEM;
+			break;
+		}
 
-		ret = -ENOMEM;
 		inode = sel_make_inode(bool_dir->d_sb, S_IFREG | S_IRUGO | S_IWUSR);
 		if (!inode) {
 			dput(dentry);
-			goto out;
-		}
-
-		ret = -ENAMETOOLONG;
-		len = snprintf(page, PAGE_SIZE, "/%s/%s", BOOL_DIR_NAME, names[i]);
-		if (len >= PAGE_SIZE) {
-			dput(dentry);
-			iput(inode);
-			goto out;
+			ret = -ENOMEM;
+			break;
 		}
 
 		isec = selinux_inode(inode);
@@ -1416,23 +1399,8 @@ static int sel_make_bools(struct selinux_policy *newpolicy, struct dentry *bool_
 		inode->i_ino = i|SEL_BOOL_INO_OFFSET;
 		d_add(dentry, inode);
 	}
-	*bool_num = num;
-	*bool_pending_names = names;
-	*bool_pending_values = values;
-
-	free_page((unsigned long)page);
-	return 0;
 out:
 	free_page((unsigned long)page);
-
-	if (names) {
-		for (i = 0; i < num; i++)
-			kfree(names[i]);
-		kfree(names);
-	}
-	kfree(values);
-	sel_remove_entries(bool_dir);
-
 	return ret;
 }
 
@@ -1961,20 +1929,40 @@ static struct dentry *sel_make_dir(struct dentry *dir, const char *name,
 	return dentry;
 }
 
-static struct dentry *sel_make_disconnected_dir(struct super_block *sb,
+static int reject_all(struct mnt_idmap *idmap, struct inode *inode, int mask)
+{
+	return -EPERM;	// no access for anyone, root or no root.
+}
+
+static const struct inode_operations swapover_dir_inode_operations = {
+	.lookup		= simple_lookup,
+	.permission	= reject_all,
+};
+
+static struct dentry *sel_make_swapover_dir(struct super_block *sb,
 						unsigned long *ino)
 {
-	struct inode *inode = sel_make_inode(sb, S_IFDIR | S_IRUGO | S_IXUGO);
+	struct dentry *dentry = d_alloc_name(sb->s_root, ".swapover");
+	struct inode *inode;
 
-	if (!inode)
+	if (!dentry)
 		return ERR_PTR(-ENOMEM);
 
-	inode->i_op = &simple_dir_inode_operations;
-	inode->i_fop = &simple_dir_operations;
+	inode = sel_make_inode(sb, S_IFDIR);
+	if (!inode) {
+		dput(dentry);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	inode->i_op = &swapover_dir_inode_operations;
 	inode->i_ino = ++(*ino);
 	/* directory inodes start off with i_nlink == 2 (for "." entry) */
 	inc_nlink(inode);
-	return d_obtain_alias(inode);
+	inode_lock(sb->s_root->d_inode);
+	d_add(dentry, inode);
+	inc_nlink(sb->s_root->d_inode);
+	inode_unlock(sb->s_root->d_inode);
+	return dentry;
 }
 
 #define NULL_FILE_NAME "null"
diff --git a/security/selinux/ss/avtab.c b/security/selinux/ss/avtab.c
index 8751a602ead2..697eb4352439 100644
--- a/security/selinux/ss/avtab.c
+++ b/security/selinux/ss/avtab.c
@@ -96,12 +96,34 @@ avtab_insert_node(struct avtab *h, struct avtab_node **dst,
 	return newnode;
 }
 
+static int avtab_node_cmp(const struct avtab_key *key1,
+			  const struct avtab_key *key2)
+{
+	u16 specified = key1->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD);
+
+	if (key1->source_type == key2->source_type &&
+	    key1->target_type == key2->target_type &&
+	    key1->target_class == key2->target_class &&
+	    (specified & key2->specified))
+		return 0;
+	if (key1->source_type < key2->source_type)
+		return -1;
+	if (key1->source_type == key2->source_type &&
+	    key1->target_type < key2->target_type)
+		return -1;
+	if (key1->source_type == key2->source_type &&
+	    key1->target_type == key2->target_type &&
+	    key1->target_class < key2->target_class)
+		return -1;
+	return 1;
+}
+
 static int avtab_insert(struct avtab *h, const struct avtab_key *key,
 			const struct avtab_datum *datum)
 {
 	u32 hvalue;
 	struct avtab_node *prev, *cur, *newnode;
-	u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD);
+	int cmp;
 
 	if (!h || !h->nslot || h->nel == U32_MAX)
 		return -EINVAL;
@@ -110,23 +132,11 @@ static int avtab_insert(struct avtab *h, const struct avtab_key *key,
 	for (prev = NULL, cur = h->htable[hvalue];
 	     cur;
 	     prev = cur, cur = cur->next) {
-		if (key->source_type == cur->key.source_type &&
-		    key->target_type == cur->key.target_type &&
-		    key->target_class == cur->key.target_class &&
-		    (specified & cur->key.specified)) {
-			/* extended perms may not be unique */
-			if (specified & AVTAB_XPERMS)
-				break;
+		cmp = avtab_node_cmp(key, &cur->key);
+		/* extended perms may not be unique */
+		if (cmp == 0 && !(key->specified & AVTAB_XPERMS))
 			return -EEXIST;
-		}
-		if (key->source_type < cur->key.source_type)
-			break;
-		if (key->source_type == cur->key.source_type &&
-		    key->target_type < cur->key.target_type)
-			break;
-		if (key->source_type == cur->key.source_type &&
-		    key->target_type == cur->key.target_type &&
-		    key->target_class < cur->key.target_class)
+		if (cmp <= 0)
 			break;
 	}
 
@@ -148,7 +158,7 @@ struct avtab_node *avtab_insert_nonunique(struct avtab *h,
 {
 	u32 hvalue;
 	struct avtab_node *prev, *cur;
-	u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD);
+	int cmp;
 
 	if (!h || !h->nslot || h->nel == U32_MAX)
 		return NULL;
@@ -156,19 +166,8 @@ struct avtab_node *avtab_insert_nonunique(struct avtab *h,
 	for (prev = NULL, cur = h->htable[hvalue];
 	     cur;
 	     prev = cur, cur = cur->next) {
-		if (key->source_type == cur->key.source_type &&
-		    key->target_type == cur->key.target_type &&
-		    key->target_class == cur->key.target_class &&
-		    (specified & cur->key.specified))
-			break;
-		if (key->source_type < cur->key.source_type)
-			break;
-		if (key->source_type == cur->key.source_type &&
-		    key->target_type < cur->key.target_type)
-			break;
-		if (key->source_type == cur->key.source_type &&
-		    key->target_type == cur->key.target_type &&
-		    key->target_class < cur->key.target_class)
+		cmp = avtab_node_cmp(key, &cur->key);
+		if (cmp <= 0)
 			break;
 	}
 	return avtab_insert_node(h, prev ? &prev->next : &h->htable[hvalue],
@@ -183,7 +182,7 @@ struct avtab_node *avtab_search_node(struct avtab *h,
 {
 	u32 hvalue;
 	struct avtab_node *cur;
-	u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD);
+	int cmp;
 
 	if (!h || !h->nslot)
 		return NULL;
@@ -191,20 +190,10 @@ struct avtab_node *avtab_search_node(struct avtab *h,
 	hvalue = avtab_hash(key, h->mask);
 	for (cur = h->htable[hvalue]; cur;
 	     cur = cur->next) {
-		if (key->source_type == cur->key.source_type &&
-		    key->target_type == cur->key.target_type &&
-		    key->target_class == cur->key.target_class &&
-		    (specified & cur->key.specified))
+		cmp = avtab_node_cmp(key, &cur->key);
+		if (cmp == 0)
 			return cur;
-
-		if (key->source_type < cur->key.source_type)
-			break;
-		if (key->source_type == cur->key.source_type &&
-		    key->target_type < cur->key.target_type)
-			break;
-		if (key->source_type == cur->key.source_type &&
-		    key->target_type == cur->key.target_type &&
-		    key->target_class < cur->key.target_class)
+		if (cmp < 0)
 			break;
 	}
 	return NULL;
@@ -213,27 +202,19 @@ struct avtab_node *avtab_search_node(struct avtab *h,
 struct avtab_node*
 avtab_search_node_next(struct avtab_node *node, u16 specified)
 {
+	struct avtab_key tmp_key;
 	struct avtab_node *cur;
+	int cmp;
 
 	if (!node)
 		return NULL;
-
-	specified &= ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD);
+	tmp_key = node->key;
+	tmp_key.specified = specified;
 	for (cur = node->next; cur; cur = cur->next) {
-		if (node->key.source_type == cur->key.source_type &&
-		    node->key.target_type == cur->key.target_type &&
-		    node->key.target_class == cur->key.target_class &&
-		    (specified & cur->key.specified))
+		cmp = avtab_node_cmp(&tmp_key, &cur->key);
+		if (cmp == 0)
 			return cur;
-
-		if (node->key.source_type < cur->key.source_type)
-			break;
-		if (node->key.source_type == cur->key.source_type &&
-		    node->key.target_type < cur->key.target_type)
-			break;
-		if (node->key.source_type == cur->key.source_type &&
-		    node->key.target_type == cur->key.target_type &&
-		    node->key.target_class < cur->key.target_class)
+		if (cmp < 0)
 			break;
 	}
 	return NULL;
diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index 595a435ea9c8..3b19ad28c922 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -409,16 +409,9 @@ out:
 static u32 filenametr_hash(const void *k)
 {
 	const struct filename_trans_key *ft = k;
-	unsigned long hash;
-	unsigned int byte_num;
-	unsigned char focus;
+	unsigned long salt = ft->ttype ^ ft->tclass;
 
-	hash = ft->ttype ^ ft->tclass;
-
-	byte_num = 0;
-	while ((focus = ft->name[byte_num++]))
-		hash = partial_name_hash(focus, hash);
-	return hash;
+	return full_name_hash((void *)salt, ft->name, strlen(ft->name));
 }
 
 static int filenametr_cmp(const void *k1, const void *k2)
@@ -864,6 +857,8 @@ void policydb_destroy(struct policydb *p)
 int policydb_load_isids(struct policydb *p, struct sidtab *s)
 {
 	struct ocontext *head, *c;
+	bool isid_init_supported = ebitmap_get_bit(&p->policycaps,
+						   POLICYDB_CAP_USERSPACE_INITIAL_CONTEXT);
 	int rc;
 
 	rc = sidtab_init(s);
@@ -887,6 +882,13 @@ int policydb_load_isids(struct policydb *p, struct sidtab *s)
 		if (!name)
 			continue;
 
+		/*
+		 * Also ignore SECINITSID_INIT if the policy doesn't declare
+		 * support for it
+		 */
+		if (sid == SECINITSID_INIT && !isid_init_supported)
+			continue;
+
 		rc = sidtab_set_initial(s, sid, &c->context[0]);
 		if (rc) {
 			pr_err("SELinux:  unable to load initial SID %s.\n",
@@ -894,6 +896,24 @@ int policydb_load_isids(struct policydb *p, struct sidtab *s)
 			sidtab_destroy(s);
 			return rc;
 		}
+
+		/*
+		 * If the policy doesn't support the "userspace_initial_context"
+		 * capability, set SECINITSID_INIT to the same context as
+		 * SECINITSID_KERNEL. This ensures the same behavior as before
+		 * the reintroduction of SECINITSID_INIT, where all tasks
+		 * started before policy load would initially get the context
+		 * corresponding to SECINITSID_KERNEL.
+		 */
+		if (sid == SECINITSID_KERNEL && !isid_init_supported) {
+			rc = sidtab_set_initial(s, SECINITSID_INIT, &c->context[0]);
+			if (rc) {
+				pr_err("SELinux:  unable to load initial SID %s.\n",
+				       name);
+				sidtab_destroy(s);
+				return rc;
+			}
+		}
 	}
 	return 0;
 }
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index 1eeffc66ea7d..e88b1b6c4adb 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -1322,8 +1322,19 @@ static int security_sid_to_context_core(u32 sid, char **scontext,
 	if (!selinux_initialized()) {
 		if (sid <= SECINITSID_NUM) {
 			char *scontextp;
-			const char *s = initial_sid_to_string[sid];
+			const char *s;
 
+			/*
+			 * Before the policy is loaded, translate
+			 * SECINITSID_INIT to "kernel", because systemd and
+			 * libselinux < 2.6 take a getcon_raw() result that is
+			 * both non-null and not "kernel" to mean that a policy
+			 * is already loaded.
+			 */
+			if (sid == SECINITSID_INIT)
+				sid = SECINITSID_KERNEL;
+
+			s = initial_sid_to_string[sid];
 			if (!s)
 				return -EINVAL;
 			*scontext_len = strlen(s) + 1;
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 65130a791f57..0fdbf04cc258 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -37,12 +37,14 @@
 #include <linux/personality.h>
 #include <linux/msg.h>
 #include <linux/shm.h>
+#include <uapi/linux/shm.h>
 #include <linux/binfmts.h>
 #include <linux/parser.h>
 #include <linux/fs_context.h>
 #include <linux/fs_parser.h>
 #include <linux/watch_queue.h>
-#include <linux/io_uring.h>
+#include <linux/io_uring/cmd.h>
+#include <uapi/linux/lsm.h>
 #include "smack.h"
 
 #define TRANS_TRUE	"TRUE"
@@ -3626,6 +3628,35 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode)
 }
 
 /**
+ * smack_getselfattr - Smack current process attribute
+ * @attr: which attribute to fetch
+ * @ctx: buffer to receive the result
+ * @size: available size in, actual size out
+ * @flags: unused
+ *
+ * Fill the passed user space @ctx with the details of the requested
+ * attribute.
+ *
+ * Returns the number of attributes on success, an error code otherwise.
+ * There will only ever be one attribute.
+ */
+static int smack_getselfattr(unsigned int attr, struct lsm_ctx __user *ctx,
+			     size_t *size, u32 flags)
+{
+	int rc;
+	struct smack_known *skp;
+
+	if (attr != LSM_ATTR_CURRENT)
+		return -EOPNOTSUPP;
+
+	skp = smk_of_current();
+	rc = lsm_fill_user_ctx(ctx, size,
+			       skp->smk_known, strlen(skp->smk_known) + 1,
+			       LSM_ID_SMACK, 0);
+	return (!rc ? 1 : rc);
+}
+
+/**
  * smack_getprocattr - Smack process attribute access
  * @p: the object task
  * @name: the name of the attribute in /proc/.../attr
@@ -3654,8 +3685,8 @@ static int smack_getprocattr(struct task_struct *p, const char *name, char **val
 }
 
 /**
- * smack_setprocattr - Smack process attribute setting
- * @name: the name of the attribute in /proc/.../attr
+ * do_setattr - Smack process attribute setting
+ * @attr: the ID of the attribute
  * @value: the value to set
  * @size: the size of the value
  *
@@ -3664,7 +3695,7 @@ static int smack_getprocattr(struct task_struct *p, const char *name, char **val
  *
  * Returns the length of the smack label or an error code
  */
-static int smack_setprocattr(const char *name, void *value, size_t size)
+static int do_setattr(u64 attr, void *value, size_t size)
 {
 	struct task_smack *tsp = smack_cred(current_cred());
 	struct cred *new;
@@ -3678,8 +3709,8 @@ static int smack_setprocattr(const char *name, void *value, size_t size)
 	if (value == NULL || size == 0 || size >= SMK_LONGLABEL)
 		return -EINVAL;
 
-	if (strcmp(name, "current") != 0)
-		return -EINVAL;
+	if (attr != LSM_ATTR_CURRENT)
+		return -EOPNOTSUPP;
 
 	skp = smk_import_entry(value, size);
 	if (IS_ERR(skp))
@@ -3719,6 +3750,49 @@ static int smack_setprocattr(const char *name, void *value, size_t size)
 }
 
 /**
+ * smack_setselfattr - Set a Smack process attribute
+ * @attr: which attribute to set
+ * @ctx: buffer containing the data
+ * @size: size of @ctx
+ * @flags: unused
+ *
+ * Fill the passed user space @ctx with the details of the requested
+ * attribute.
+ *
+ * Returns 0 on success, an error code otherwise.
+ */
+static int smack_setselfattr(unsigned int attr, struct lsm_ctx *ctx,
+			     size_t size, u32 flags)
+{
+	int rc;
+
+	rc = do_setattr(attr, ctx->ctx, ctx->ctx_len);
+	if (rc > 0)
+		return 0;
+	return rc;
+}
+
+/**
+ * smack_setprocattr - Smack process attribute setting
+ * @name: the name of the attribute in /proc/.../attr
+ * @value: the value to set
+ * @size: the size of the value
+ *
+ * Sets the Smack value of the task. Only setting self
+ * is permitted and only with privilege
+ *
+ * Returns the length of the smack label or an error code
+ */
+static int smack_setprocattr(const char *name, void *value, size_t size)
+{
+	int attr = lsm_name_to_attr(name);
+
+	if (attr != LSM_ATTR_UNDEF)
+		return do_setattr(attr, value, size);
+	return -EINVAL;
+}
+
+/**
  * smack_unix_stream_connect - Smack access on UDS
  * @sock: one sock
  * @other: the other sock
@@ -4933,6 +5007,11 @@ struct lsm_blob_sizes smack_blob_sizes __ro_after_init = {
 	.lbs_xattr_count = SMACK_INODE_INIT_XATTRS,
 };
 
+static const struct lsm_id smack_lsmid = {
+	.name = "smack",
+	.id = LSM_ID_SMACK,
+};
+
 static struct security_hook_list smack_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(ptrace_access_check, smack_ptrace_access_check),
 	LSM_HOOK_INIT(ptrace_traceme, smack_ptrace_traceme),
@@ -4973,6 +5052,7 @@ static struct security_hook_list smack_hooks[] __ro_after_init = {
 
 	LSM_HOOK_INIT(file_alloc_security, smack_file_alloc_security),
 	LSM_HOOK_INIT(file_ioctl, smack_file_ioctl),
+	LSM_HOOK_INIT(file_ioctl_compat, smack_file_ioctl),
 	LSM_HOOK_INIT(file_lock, smack_file_lock),
 	LSM_HOOK_INIT(file_fcntl, smack_file_fcntl),
 	LSM_HOOK_INIT(mmap_file, smack_mmap_file),
@@ -5027,6 +5107,8 @@ static struct security_hook_list smack_hooks[] __ro_after_init = {
 
 	LSM_HOOK_INIT(d_instantiate, smack_d_instantiate),
 
+	LSM_HOOK_INIT(getselfattr, smack_getselfattr),
+	LSM_HOOK_INIT(setselfattr, smack_setselfattr),
 	LSM_HOOK_INIT(getprocattr, smack_getprocattr),
 	LSM_HOOK_INIT(setprocattr, smack_setprocattr),
 
@@ -5140,7 +5222,7 @@ static __init int smack_init(void)
 	/*
 	 * Register with LSM
 	 */
-	security_add_hooks(smack_hooks, ARRAY_SIZE(smack_hooks), "smack");
+	security_add_hooks(smack_hooks, ARRAY_SIZE(smack_hooks), &smack_lsmid);
 	smack_enabled = 1;
 
 	pr_info("Smack:  Initializing.\n");
diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c
index 255f1b470295..3c3af149bf1c 100644
--- a/security/tomoyo/tomoyo.c
+++ b/security/tomoyo/tomoyo.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/lsm_hooks.h>
+#include <uapi/linux/lsm.h>
 #include "common.h"
 
 /**
@@ -542,6 +543,11 @@ static void tomoyo_task_free(struct task_struct *task)
 	}
 }
 
+static const struct lsm_id tomoyo_lsmid = {
+	.name = "tomoyo",
+	.id = LSM_ID_TOMOYO,
+};
+
 /*
  * tomoyo_security_ops is a "struct security_operations" which is used for
  * registering TOMOYO.
@@ -568,6 +574,7 @@ static struct security_hook_list tomoyo_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(path_rename, tomoyo_path_rename),
 	LSM_HOOK_INIT(inode_getattr, tomoyo_inode_getattr),
 	LSM_HOOK_INIT(file_ioctl, tomoyo_file_ioctl),
+	LSM_HOOK_INIT(file_ioctl_compat, tomoyo_file_ioctl),
 	LSM_HOOK_INIT(path_chmod, tomoyo_path_chmod),
 	LSM_HOOK_INIT(path_chown, tomoyo_path_chown),
 	LSM_HOOK_INIT(path_chroot, tomoyo_path_chroot),
@@ -595,7 +602,8 @@ static int __init tomoyo_init(void)
 	struct tomoyo_task *s = tomoyo_task(current);
 
 	/* register ourselves with the security framework */
-	security_add_hooks(tomoyo_hooks, ARRAY_SIZE(tomoyo_hooks), "tomoyo");
+	security_add_hooks(tomoyo_hooks, ARRAY_SIZE(tomoyo_hooks),
+			   &tomoyo_lsmid);
 	pr_info("TOMOYO Linux initialized\n");
 	s->domain_info = &tomoyo_kernel_domain;
 	atomic_inc(&tomoyo_kernel_domain.users);
diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c
index 2503cf153d4a..49dc52b454ef 100644
--- a/security/yama/yama_lsm.c
+++ b/security/yama/yama_lsm.c
@@ -18,6 +18,7 @@
 #include <linux/task_work.h>
 #include <linux/sched.h>
 #include <linux/spinlock.h>
+#include <uapi/linux/lsm.h>
 
 #define YAMA_SCOPE_DISABLED	0
 #define YAMA_SCOPE_RELATIONAL	1
@@ -421,6 +422,11 @@ static int yama_ptrace_traceme(struct task_struct *parent)
 	return rc;
 }
 
+static const struct lsm_id yama_lsmid = {
+	.name = "yama",
+	.id = LSM_ID_YAMA,
+};
+
 static struct security_hook_list yama_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(ptrace_access_check, yama_ptrace_access_check),
 	LSM_HOOK_INIT(ptrace_traceme, yama_ptrace_traceme),
@@ -471,7 +477,7 @@ static inline void yama_init_sysctl(void) { }
 static int __init yama_init(void)
 {
 	pr_info("Yama: becoming mindful.\n");
-	security_add_hooks(yama_hooks, ARRAY_SIZE(yama_hooks), "yama");
+	security_add_hooks(yama_hooks, ARRAY_SIZE(yama_hooks), &yama_lsmid);
 	yama_init_sysctl();
 	return 0;
 }
diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index 20bb2d7c8d4b..6d0c9c37796c 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -253,6 +253,7 @@ static const char * const snd_pcm_state_names[] = {
 	STATE(DRAINING),
 	STATE(PAUSED),
 	STATE(SUSPENDED),
+	STATE(DISCONNECTED),
 };
 
 static const char * const snd_pcm_access_names[] = {
diff --git a/sound/drivers/pcmtest.c b/sound/drivers/pcmtest.c
index b59b78a09224..b8bff5522bce 100644
--- a/sound/drivers/pcmtest.c
+++ b/sound/drivers/pcmtest.c
@@ -397,7 +397,6 @@ static int snd_pcmtst_pcm_close(struct snd_pcm_substream *substream)
 	struct pcmtst_buf_iter *v_iter = substream->runtime->private_data;
 
 	timer_shutdown_sync(&v_iter->timer_instance);
-	v_iter->substream = NULL;
 	playback_capture_test = !v_iter->is_buf_corrupted;
 	kfree(v_iter);
 	return 0;
@@ -435,6 +434,7 @@ static int snd_pcmtst_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
 		// We can't call timer_shutdown_sync here, as it is forbidden to sleep here
 		v_iter->suspend = true;
+		timer_delete(&v_iter->timer_instance);
 		break;
 	}
 
@@ -512,12 +512,22 @@ static int snd_pcmtst_ioctl(struct snd_pcm_substream *substream, unsigned int cm
 	return snd_pcm_lib_ioctl(substream, cmd, arg);
 }
 
+static int snd_pcmtst_sync_stop(struct snd_pcm_substream *substream)
+{
+	struct pcmtst_buf_iter *v_iter = substream->runtime->private_data;
+
+	timer_delete_sync(&v_iter->timer_instance);
+
+	return 0;
+}
+
 static const struct snd_pcm_ops snd_pcmtst_playback_ops = {
 	.open =		snd_pcmtst_pcm_open,
 	.close =	snd_pcmtst_pcm_close,
 	.trigger =	snd_pcmtst_pcm_trigger,
 	.hw_params =	snd_pcmtst_pcm_hw_params,
 	.ioctl =	snd_pcmtst_ioctl,
+	.sync_stop =	snd_pcmtst_sync_stop,
 	.hw_free =	snd_pcmtst_pcm_hw_free,
 	.prepare =	snd_pcmtst_pcm_prepare,
 	.pointer =	snd_pcmtst_pcm_pointer,
@@ -530,6 +540,7 @@ static const struct snd_pcm_ops snd_pcmtst_capture_ops = {
 	.hw_params =	snd_pcmtst_pcm_hw_params,
 	.hw_free =	snd_pcmtst_pcm_hw_free,
 	.ioctl =	snd_pcmtst_ioctl,
+	.sync_stop =	snd_pcmtst_sync_stop,
 	.prepare =	snd_pcmtst_pcm_prepare,
 	.pointer =	snd_pcmtst_pcm_pointer,
 };
diff --git a/sound/hda/intel-nhlt.c b/sound/hda/intel-nhlt.c
index 2c4dfc0b7e34..696a958d93e9 100644
--- a/sound/hda/intel-nhlt.c
+++ b/sound/hda/intel-nhlt.c
@@ -238,7 +238,7 @@ EXPORT_SYMBOL(intel_nhlt_ssp_mclk_mask);
 
 static struct nhlt_specific_cfg *
 nhlt_get_specific_cfg(struct device *dev, struct nhlt_fmt *fmt, u8 num_ch,
-		      u32 rate, u8 vbps, u8 bps)
+		      u32 rate, u8 vbps, u8 bps, bool ignore_vbps)
 {
 	struct nhlt_fmt_cfg *cfg = fmt->fmt_config;
 	struct wav_fmt *wfmt;
@@ -255,8 +255,12 @@ nhlt_get_specific_cfg(struct device *dev, struct nhlt_fmt *fmt, u8 num_ch,
 		dev_dbg(dev, "Endpoint format: ch=%d fmt=%d/%d rate=%d\n",
 			wfmt->channels, _vbps, _bps, wfmt->samples_per_sec);
 
+		/*
+		 * When looking for exact match of configuration ignore the vbps
+		 * from NHLT table when ignore_vbps is true
+		 */
 		if (wfmt->channels == num_ch && wfmt->samples_per_sec == rate &&
-		    vbps == _vbps && bps == _bps)
+		    (ignore_vbps || vbps == _vbps) && bps == _bps)
 			return &cfg->config;
 
 		cfg = (struct nhlt_fmt_cfg *)(cfg->config.caps + cfg->config.size);
@@ -289,6 +293,7 @@ intel_nhlt_get_endpoint_blob(struct device *dev, struct nhlt_acpi_table *nhlt,
 {
 	struct nhlt_specific_cfg *cfg;
 	struct nhlt_endpoint *epnt;
+	bool ignore_vbps = false;
 	struct nhlt_fmt *fmt;
 	int i;
 
@@ -298,7 +303,26 @@ intel_nhlt_get_endpoint_blob(struct device *dev, struct nhlt_acpi_table *nhlt,
 	dev_dbg(dev, "Looking for configuration:\n");
 	dev_dbg(dev, "  vbus_id=%d link_type=%d dir=%d, dev_type=%d\n",
 		bus_id, link_type, dir, dev_type);
-	dev_dbg(dev, "  ch=%d fmt=%d/%d rate=%d\n", num_ch, vbps, bps, rate);
+	if (link_type == NHLT_LINK_DMIC && bps == 32 && (vbps == 24 || vbps == 32)) {
+		/*
+		 * The DMIC hardware supports only one type of 32 bits sample
+		 * size, which is 24 bit sampling on the MSB side and bits[1:0]
+		 * are used for indicating the channel number.
+		 * It has been observed that some NHLT tables have the vbps
+		 * specified as 32 while some uses 24.
+		 * The format these variations describe are identical, the
+		 * hardware is configured and behaves the same way.
+		 * Note: when the samples assumed to be vbps=32 then the 'noise'
+		 * introduced by the lower two bits (channel number) have no
+		 * real life implication on audio quality.
+		 */
+		dev_dbg(dev,
+			"  ch=%d fmt=%d rate=%d (vbps is ignored for DMIC 32bit format)\n",
+			num_ch, bps, rate);
+		ignore_vbps = true;
+	} else {
+		dev_dbg(dev, "  ch=%d fmt=%d/%d rate=%d\n", num_ch, vbps, bps, rate);
+	}
 	dev_dbg(dev, "Endpoint count=%d\n", nhlt->endpoint_count);
 
 	epnt = (struct nhlt_endpoint *)nhlt->desc;
@@ -307,7 +331,8 @@ intel_nhlt_get_endpoint_blob(struct device *dev, struct nhlt_acpi_table *nhlt,
 		if (nhlt_check_ep_match(dev, epnt, bus_id, link_type, dir, dev_type)) {
 			fmt = (struct nhlt_fmt *)(epnt->config.caps + epnt->config.size);
 
-			cfg = nhlt_get_specific_cfg(dev, fmt, num_ch, rate, vbps, bps);
+			cfg = nhlt_get_specific_cfg(dev, fmt, num_ch, rate,
+						    vbps, bps, ignore_vbps);
 			if (cfg)
 				return cfg;
 		}
diff --git a/sound/pci/hda/cs35l41_hda.c b/sound/pci/hda/cs35l41_hda.c
index b2db8091f0ed..92ca2b3b6c92 100644
--- a/sound/pci/hda/cs35l41_hda.c
+++ b/sound/pci/hda/cs35l41_hda.c
@@ -504,7 +504,6 @@ static void cs35l41_shutdown_dsp(struct cs35l41_hda *cs35l41)
 
 	cs_dsp_stop(dsp);
 	cs_dsp_power_down(dsp);
-	cs35l41->firmware_running = false;
 	dev_dbg(cs35l41->dev, "Unloaded Firmware\n");
 }
 
@@ -550,7 +549,7 @@ static void cs35l41_hda_play_start(struct device *dev)
 
 	cs35l41->playback_started = true;
 
-	if (cs35l41->firmware_running) {
+	if (cs35l41->cs_dsp.running) {
 		regmap_multi_reg_write(reg, cs35l41_hda_config_dsp,
 				       ARRAY_SIZE(cs35l41_hda_config_dsp));
 		regmap_update_bits(reg, CS35L41_PWR_CTRL2,
@@ -580,7 +579,7 @@ static void cs35l41_mute(struct device *dev, bool mute)
 			regmap_multi_reg_write(reg, cs35l41_hda_mute, ARRAY_SIZE(cs35l41_hda_mute));
 		} else {
 			dev_dbg(dev, "Unmuting\n");
-			if (cs35l41->firmware_running) {
+			if (cs35l41->cs_dsp.running) {
 				regmap_multi_reg_write(reg, cs35l41_hda_unmute_dsp,
 						ARRAY_SIZE(cs35l41_hda_unmute_dsp));
 			} else {
@@ -599,7 +598,7 @@ static void cs35l41_hda_play_done(struct device *dev)
 	dev_dbg(dev, "Play (Complete)\n");
 
 	cs35l41_global_enable(dev, reg, cs35l41->hw_cfg.bst_type, 1,
-			      cs35l41->firmware_running);
+			      &cs35l41->cs_dsp);
 	cs35l41_mute(dev, false);
 }
 
@@ -612,7 +611,7 @@ static void cs35l41_hda_pause_start(struct device *dev)
 
 	cs35l41_mute(dev, true);
 	cs35l41_global_enable(dev, reg, cs35l41->hw_cfg.bst_type, 0,
-			      cs35l41->firmware_running);
+			      &cs35l41->cs_dsp);
 }
 
 static void cs35l41_hda_pause_done(struct device *dev)
@@ -625,7 +624,7 @@ static void cs35l41_hda_pause_done(struct device *dev)
 	regmap_update_bits(reg, CS35L41_PWR_CTRL2, CS35L41_AMP_EN_MASK, 0 << CS35L41_AMP_EN_SHIFT);
 	if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST)
 		regmap_write(reg, CS35L41_GPIO1_CTRL1, 0x00000001);
-	if (cs35l41->firmware_running) {
+	if (cs35l41->cs_dsp.running) {
 		cs35l41_set_cspl_mbox_cmd(dev, reg, CSPL_MBOX_CMD_PAUSE);
 		regmap_update_bits(reg, CS35L41_PWR_CTRL2,
 				   CS35L41_VMON_EN_MASK | CS35L41_IMON_EN_MASK,
@@ -675,7 +674,7 @@ static void cs35l41_hda_playback_hook(struct device *dev, int action)
 		break;
 	case HDA_GEN_PCM_ACT_CLOSE:
 		mutex_lock(&cs35l41->fw_mutex);
-		if (!cs35l41->firmware_running && cs35l41->request_fw_load &&
+		if (!cs35l41->cs_dsp.running && cs35l41->request_fw_load &&
 		    !cs35l41->fw_request_ongoing) {
 			dev_info(dev, "Requesting Firmware Load after HDA_GEN_PCM_ACT_CLOSE\n");
 			cs35l41->fw_request_ongoing = true;
@@ -761,10 +760,9 @@ static int cs35l41_verify_id(struct cs35l41_hda *cs35l41, unsigned int *regid, u
 static int cs35l41_ready_for_reset(struct cs35l41_hda *cs35l41)
 {
 	mutex_lock(&cs35l41->fw_mutex);
-	if (cs35l41->firmware_running) {
+	if (cs35l41->cs_dsp.running) {
 		cs35l41->cs_dsp.running = false;
 		cs35l41->cs_dsp.booted = false;
-		cs35l41->firmware_running = false;
 	}
 	regcache_mark_dirty(cs35l41->regmap);
 	mutex_unlock(&cs35l41->fw_mutex);
@@ -925,7 +923,7 @@ static int cs35l41_runtime_suspend(struct device *dev)
 
 	mutex_lock(&cs35l41->fw_mutex);
 
-	if (cs35l41->firmware_running) {
+	if (cs35l41->cs_dsp.running) {
 		ret = cs35l41_enter_hibernate(cs35l41->dev, cs35l41->regmap,
 					      cs35l41->hw_cfg.bst_type);
 		if (ret)
@@ -960,7 +958,7 @@ static int cs35l41_runtime_resume(struct device *dev)
 
 	regcache_cache_only(cs35l41->regmap, false);
 
-	if (cs35l41->firmware_running)	{
+	if (cs35l41->cs_dsp.running)	{
 		ret = cs35l41_exit_hibernate(cs35l41->dev, cs35l41->regmap);
 		if (ret) {
 			dev_warn(cs35l41->dev, "Unable to exit Hibernate.");
@@ -1052,8 +1050,6 @@ static int cs35l41_smart_amp(struct cs35l41_hda *cs35l41)
 		goto clean_dsp;
 	}
 
-	cs35l41->firmware_running = true;
-
 	return 0;
 
 clean_dsp:
@@ -1063,10 +1059,10 @@ clean_dsp:
 
 static void cs35l41_load_firmware(struct cs35l41_hda *cs35l41, bool load)
 {
-	if (cs35l41->firmware_running && !load) {
+	if (cs35l41->cs_dsp.running && !load) {
 		dev_dbg(cs35l41->dev, "Unloading Firmware\n");
 		cs35l41_shutdown_dsp(cs35l41);
-	} else if (!cs35l41->firmware_running && load) {
+	} else if (!cs35l41->cs_dsp.running && load) {
 		dev_dbg(cs35l41->dev, "Loading Firmware\n");
 		cs35l41_smart_amp(cs35l41);
 	} else {
@@ -1346,7 +1342,7 @@ static int cs35l41_hda_bind(struct device *dev, struct device *master, void *mas
 		 cs35l41->acpi_subsystem_id, cs35l41->hw_cfg.bst_type,
 		 cs35l41->hw_cfg.gpio1.func == CS35l41_VSPK_SWITCH,
 		 cs35l41->hw_cfg.spk_pos ? 'R' : 'L',
-		 cs35l41->firmware_running, cs35l41->speaker_id);
+		 cs35l41->cs_dsp.running, cs35l41->speaker_id);
 
 	return ret;
 }
@@ -1830,6 +1826,7 @@ err:
 	if (cs35l41_safe_reset(cs35l41->regmap, cs35l41->hw_cfg.bst_type))
 		gpiod_set_value_cansleep(cs35l41->reset_gpio, 0);
 	gpiod_put(cs35l41->reset_gpio);
+	gpiod_put(cs35l41->cs_gpio);
 	acpi_dev_put(cs35l41->dacpi);
 	kfree(cs35l41->acpi_subsystem_id);
 
@@ -1857,6 +1854,7 @@ void cs35l41_hda_remove(struct device *dev)
 	if (cs35l41_safe_reset(cs35l41->regmap, cs35l41->hw_cfg.bst_type))
 		gpiod_set_value_cansleep(cs35l41->reset_gpio, 0);
 	gpiod_put(cs35l41->reset_gpio);
+	gpiod_put(cs35l41->cs_gpio);
 	kfree(cs35l41->acpi_subsystem_id);
 }
 EXPORT_SYMBOL_NS_GPL(cs35l41_hda_remove, SND_HDA_SCODEC_CS35L41);
diff --git a/sound/pci/hda/cs35l41_hda.h b/sound/pci/hda/cs35l41_hda.h
index ce3f2bb6ffd0..3d925d677213 100644
--- a/sound/pci/hda/cs35l41_hda.h
+++ b/sound/pci/hda/cs35l41_hda.h
@@ -35,8 +35,8 @@ struct cs35l41_amp_efi_data {
 } __packed;
 
 enum cs35l41_hda_spk_pos {
-	CS35l41_LEFT,
-	CS35l41_RIGHT,
+	CS35L41_LEFT,
+	CS35L41_RIGHT,
 };
 
 enum cs35l41_hda_gpio_function {
@@ -50,6 +50,7 @@ struct cs35l41_hda {
 	struct device *dev;
 	struct regmap *regmap;
 	struct gpio_desc *reset_gpio;
+	struct gpio_desc *cs_gpio;
 	struct cs35l41_hw_cfg hw_cfg;
 	struct hda_codec *codec;
 
diff --git a/sound/pci/hda/cs35l41_hda_property.c b/sound/pci/hda/cs35l41_hda_property.c
index c83328971728..c1afb721b4c6 100644
--- a/sound/pci/hda/cs35l41_hda_property.c
+++ b/sound/pci/hda/cs35l41_hda_property.c
@@ -6,9 +6,301 @@
 //
 // Author: Stefan Binding <sbinding@opensource.cirrus.com>
 
+#include <linux/acpi.h>
 #include <linux/gpio/consumer.h>
 #include <linux/string.h>
 #include "cs35l41_hda_property.h"
+#include <linux/spi/spi.h>
+
+#define MAX_AMPS 4
+
+struct cs35l41_config {
+	const char *ssid;
+	enum {
+		SPI,
+		I2C
+	} bus;
+	int num_amps;
+	enum {
+		INTERNAL,
+		EXTERNAL
+	} boost_type;
+	u8 channel[MAX_AMPS];
+	int reset_gpio_index; /* -1 if no reset gpio */
+	int spkid_gpio_index; /* -1 if no spkid gpio */
+	int cs_gpio_index; /* -1 if no cs gpio, or cs-gpios already exists, max num amps == 2 */
+	int boost_ind_nanohenry; /* Required if boost_type == Internal */
+	int boost_peak_milliamp; /* Required if boost_type == Internal */
+	int boost_cap_microfarad; /* Required if boost_type == Internal */
+};
+
+static const struct cs35l41_config cs35l41_config_table[] = {
+/*
+ * Device 103C89C6 does have _DSD, however it is setup to use the wrong boost type.
+ * We can override the _DSD to correct the boost type here.
+ * Since this laptop has valid ACPI, we do not need to handle cs-gpios, since that already exists
+ * in the ACPI. The Reset GPIO is also valid, so we can use the Reset defined in _DSD.
+ */
+	{ "103C89C6", SPI, 2, INTERNAL, { CS35L41_RIGHT, CS35L41_LEFT, 0, 0 }, -1, -1, -1, 1000, 4500, 24 },
+	{ "104312AF", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
+	{ "10431433", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
+	{ "10431463", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
+	{ "10431473", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 1000, 4500, 24 },
+	{ "10431483", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 1000, 4500, 24 },
+	{ "10431493", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
+	{ "104314D3", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
+	{ "104314E3", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
+	{ "10431503", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
+	{ "10431533", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
+	{ "10431573", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
+	{ "10431663", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 1000, 4500, 24 },
+	{ "104316D3", SPI, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
+	{ "104316F3", SPI, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
+	{ "104317F3", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
+	{ "10431863", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
+	{ "104318D3", I2C, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
+	{ "10431C9F", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
+	{ "10431CAF", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
+	{ "10431CCF", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
+	{ "10431CDF", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
+	{ "10431CEF", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
+	{ "10431D1F", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
+	{ "10431DA2", SPI, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
+	{ "10431E02", SPI, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
+	{ "10431EE2", I2C, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, -1, -1, 0, 0, 0 },
+	{ "10431F12", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
+	{ "10431F1F", SPI, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 0, 0, 0 },
+	{ "10431F62", SPI, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
+	{}
+};
+
+static int cs35l41_add_gpios(struct cs35l41_hda *cs35l41, struct device *physdev, int reset_gpio,
+			     int spkid_gpio, int cs_gpio_index, int num_amps)
+{
+	struct acpi_gpio_mapping *gpio_mapping = NULL;
+	struct acpi_gpio_params *reset_gpio_params = NULL;
+	struct acpi_gpio_params *spkid_gpio_params = NULL;
+	struct acpi_gpio_params *cs_gpio_params = NULL;
+	unsigned int num_entries = 0;
+	unsigned int reset_index, spkid_index, csgpio_index;
+	int i;
+
+	/*
+	 * GPIO Mapping only needs to be done once, since it would be available for subsequent amps
+	 */
+	if (cs35l41->dacpi->driver_gpios)
+		return 0;
+
+	if (reset_gpio >= 0) {
+		reset_index = num_entries;
+		num_entries++;
+	}
+
+	if (spkid_gpio >= 0) {
+		spkid_index = num_entries;
+		num_entries++;
+	}
+
+	if ((cs_gpio_index >= 0)  && (num_amps == 2)) {
+		csgpio_index = num_entries;
+		num_entries++;
+	}
+
+	if (!num_entries)
+		return 0;
+
+	/* must include termination entry */
+	num_entries++;
+
+	gpio_mapping = devm_kcalloc(physdev, num_entries, sizeof(struct acpi_gpio_mapping),
+				    GFP_KERNEL);
+
+	if (!gpio_mapping)
+		goto err;
+
+	if (reset_gpio >= 0) {
+		gpio_mapping[reset_index].name = "reset-gpios";
+		reset_gpio_params = devm_kcalloc(physdev, num_amps, sizeof(struct acpi_gpio_params),
+						 GFP_KERNEL);
+		if (!reset_gpio_params)
+			goto err;
+
+		for (i = 0; i < num_amps; i++)
+			reset_gpio_params[i].crs_entry_index = reset_gpio;
+
+		gpio_mapping[reset_index].data = reset_gpio_params;
+		gpio_mapping[reset_index].size = num_amps;
+	}
+
+	if (spkid_gpio >= 0) {
+		gpio_mapping[spkid_index].name = "spk-id-gpios";
+		spkid_gpio_params = devm_kcalloc(physdev, num_amps, sizeof(struct acpi_gpio_params),
+						 GFP_KERNEL);
+		if (!spkid_gpio_params)
+			goto err;
+
+		for (i = 0; i < num_amps; i++)
+			spkid_gpio_params[i].crs_entry_index = spkid_gpio;
+
+		gpio_mapping[spkid_index].data = spkid_gpio_params;
+		gpio_mapping[spkid_index].size = num_amps;
+	}
+
+	if ((cs_gpio_index >= 0) && (num_amps == 2)) {
+		gpio_mapping[csgpio_index].name = "cs-gpios";
+		/* only one GPIO CS is supported without using _DSD, obtained using index 0 */
+		cs_gpio_params = devm_kzalloc(physdev, sizeof(struct acpi_gpio_params), GFP_KERNEL);
+		if (!cs_gpio_params)
+			goto err;
+
+		cs_gpio_params->crs_entry_index = cs_gpio_index;
+
+		gpio_mapping[csgpio_index].data = cs_gpio_params;
+		gpio_mapping[csgpio_index].size = 1;
+	}
+
+	return devm_acpi_dev_add_driver_gpios(physdev, gpio_mapping);
+err:
+	devm_kfree(physdev, gpio_mapping);
+	devm_kfree(physdev, reset_gpio_params);
+	devm_kfree(physdev, spkid_gpio_params);
+	devm_kfree(physdev, cs_gpio_params);
+	return -ENOMEM;
+}
+
+static int generic_dsd_config(struct cs35l41_hda *cs35l41, struct device *physdev, int id,
+			      const char *hid)
+{
+	struct cs35l41_hw_cfg *hw_cfg = &cs35l41->hw_cfg;
+	const struct cs35l41_config *cfg;
+	struct gpio_desc *cs_gpiod;
+	struct spi_device *spi;
+	bool dsd_found;
+	int ret;
+
+	for (cfg = cs35l41_config_table; cfg->ssid; cfg++) {
+		if (!strcasecmp(cfg->ssid, cs35l41->acpi_subsystem_id))
+			break;
+	}
+
+	if (!cfg->ssid)
+		return -ENOENT;
+
+	if (!cs35l41->dacpi || cs35l41->dacpi != ACPI_COMPANION(physdev)) {
+		dev_err(cs35l41->dev, "ACPI Device does not match, cannot override _DSD.\n");
+		return -ENODEV;
+	}
+
+	dev_info(cs35l41->dev, "Adding DSD properties for %s\n", cs35l41->acpi_subsystem_id);
+
+	dsd_found = acpi_dev_has_props(cs35l41->dacpi);
+
+	if (!dsd_found) {
+		ret = cs35l41_add_gpios(cs35l41, physdev, cfg->reset_gpio_index,
+						 cfg->spkid_gpio_index, cfg->cs_gpio_index,
+						 cfg->num_amps);
+		if (ret) {
+			dev_err(cs35l41->dev, "Error adding GPIO mapping: %d\n", ret);
+			return ret;
+		}
+	} else if (cfg->reset_gpio_index >= 0 || cfg->spkid_gpio_index >= 0) {
+		dev_warn(cs35l41->dev, "Cannot add Reset/Speaker ID/SPI CS GPIO Mapping, "
+			 "_DSD already exists.\n");
+	}
+
+	if (cfg->bus == SPI) {
+		cs35l41->index = id;
+
+		/*
+		 * Manually set the Chip Select for the second amp <cs_gpio_index> in the node.
+		 * This is only supported for systems with 2 amps, since we cannot expand the
+		 * default number of chip selects without using cs-gpios
+		 * The CS GPIO must be set high prior to communicating with the first amp (which
+		 * uses a native chip select), to ensure the second amp does not clash with the
+		 * first.
+		 */
+		if (IS_ENABLED(CONFIG_SPI) && cfg->cs_gpio_index >= 0) {
+			spi = to_spi_device(cs35l41->dev);
+
+			if (cfg->num_amps != 2) {
+				dev_warn(cs35l41->dev,
+					 "Cannot update SPI CS, Number of Amps (%d) != 2\n",
+					 cfg->num_amps);
+			} else if (dsd_found) {
+				dev_warn(cs35l41->dev,
+					"Cannot update SPI CS, _DSD already exists.\n");
+			} else {
+				/*
+				 * This is obtained using driver_gpios, since only one GPIO for CS
+				 * exists, this can be obtained using index 0.
+				 */
+				cs_gpiod = gpiod_get_index(physdev, "cs", 0, GPIOD_OUT_LOW);
+				if (IS_ERR(cs_gpiod)) {
+					dev_err(cs35l41->dev,
+						"Unable to get Chip Select GPIO descriptor\n");
+					return PTR_ERR(cs_gpiod);
+				}
+				if (id == 1) {
+					spi_set_csgpiod(spi, 0, cs_gpiod);
+					cs35l41->cs_gpio = cs_gpiod;
+				} else {
+					gpiod_set_value_cansleep(cs_gpiod, true);
+					gpiod_put(cs_gpiod);
+				}
+				spi_setup(spi);
+			}
+		}
+	} else {
+		if (cfg->num_amps > 2)
+			/*
+			 * i2c addresses for 3/4 amps are used in order: 0x40, 0x41, 0x42, 0x43,
+			 * subtracting 0x40 would give zero-based index
+			 */
+			cs35l41->index = id - 0x40;
+		else
+			/* i2c addr 0x40 for first amp (always), 0x41/0x42 for 2nd amp */
+			cs35l41->index = id == 0x40 ? 0 : 1;
+	}
+
+	if (cfg->num_amps == 3)
+		/* 3 amps means a center channel, so no duplicate channels */
+		cs35l41->channel_index = 0;
+	else
+		/*
+		 * if 4 amps, there are duplicate channels, so they need different indexes
+		 * if 2 amps, no duplicate channels, channel_index would be 0
+		 */
+		cs35l41->channel_index = cs35l41->index / 2;
+
+	cs35l41->reset_gpio = fwnode_gpiod_get_index(acpi_fwnode_handle(cs35l41->dacpi), "reset",
+						     cs35l41->index, GPIOD_OUT_LOW,
+						     "cs35l41-reset");
+	cs35l41->speaker_id = cs35l41_get_speaker_id(physdev, cs35l41->index, cfg->num_amps, -1);
+
+	hw_cfg->spk_pos = cfg->channel[cs35l41->index];
+
+	if (cfg->boost_type == INTERNAL) {
+		hw_cfg->bst_type = CS35L41_INT_BOOST;
+		hw_cfg->bst_ind = cfg->boost_ind_nanohenry;
+		hw_cfg->bst_ipk = cfg->boost_peak_milliamp;
+		hw_cfg->bst_cap = cfg->boost_cap_microfarad;
+		hw_cfg->gpio1.func = CS35L41_NOT_USED;
+		hw_cfg->gpio1.valid = true;
+	} else {
+		hw_cfg->bst_type = CS35L41_EXT_BOOST;
+		hw_cfg->bst_ind = -1;
+		hw_cfg->bst_ipk = -1;
+		hw_cfg->bst_cap = -1;
+		hw_cfg->gpio1.func = CS35l41_VSPK_SWITCH;
+		hw_cfg->gpio1.valid = true;
+	}
+
+	hw_cfg->gpio2.func = CS35L41_INTERRUPT;
+	hw_cfg->gpio2.valid = true;
+	hw_cfg->valid = true;
+
+	return 0;
+}
 
 /*
  * Device CLSA010(0/1) doesn't have _DSD so a gpiod_get by the label reset won't work.
@@ -43,44 +335,6 @@ static int lenovo_legion_no_acpi(struct cs35l41_hda *cs35l41, struct device *phy
 	return 0;
 }
 
-/*
- * Device 103C89C6 does have _DSD, however it is setup to use the wrong boost type.
- * We can override the _DSD to correct the boost type here.
- * Since this laptop has valid ACPI, we do not need to handle cs-gpios, since that already exists
- * in the ACPI.
- */
-static int hp_vision_acpi_fix(struct cs35l41_hda *cs35l41, struct device *physdev, int id,
-			      const char *hid)
-{
-	struct cs35l41_hw_cfg *hw_cfg = &cs35l41->hw_cfg;
-
-	dev_info(cs35l41->dev, "Adding DSD properties for %s\n", cs35l41->acpi_subsystem_id);
-
-	cs35l41->index = id;
-	cs35l41->channel_index = 0;
-
-	/*
-	 * This system has _DSD, it just contains an error, so we can still get the reset using
-	 * the "reset" label.
-	 */
-	cs35l41->reset_gpio = fwnode_gpiod_get_index(acpi_fwnode_handle(cs35l41->dacpi), "reset",
-						     cs35l41->index, GPIOD_OUT_LOW,
-						     "cs35l41-reset");
-	cs35l41->speaker_id = -ENOENT;
-	hw_cfg->spk_pos = cs35l41->index ? 0 : 1; // right:left
-	hw_cfg->gpio1.func = CS35L41_NOT_USED;
-	hw_cfg->gpio1.valid = true;
-	hw_cfg->gpio2.func = CS35L41_INTERRUPT;
-	hw_cfg->gpio2.valid = true;
-	hw_cfg->bst_type = CS35L41_INT_BOOST;
-	hw_cfg->bst_ind = 1000;
-	hw_cfg->bst_ipk = 4500;
-	hw_cfg->bst_cap = 24;
-	hw_cfg->valid = true;
-
-	return 0;
-}
-
 struct cs35l41_prop_model {
 	const char *hid;
 	const char *ssid;
@@ -91,7 +345,36 @@ struct cs35l41_prop_model {
 static const struct cs35l41_prop_model cs35l41_prop_model_table[] = {
 	{ "CLSA0100", NULL, lenovo_legion_no_acpi },
 	{ "CLSA0101", NULL, lenovo_legion_no_acpi },
-	{ "CSC3551", "103C89C6", hp_vision_acpi_fix },
+	{ "CSC3551", "103C89C6", generic_dsd_config },
+	{ "CSC3551", "104312AF", generic_dsd_config },
+	{ "CSC3551", "10431433", generic_dsd_config },
+	{ "CSC3551", "10431463", generic_dsd_config },
+	{ "CSC3551", "10431473", generic_dsd_config },
+	{ "CSC3551", "10431483", generic_dsd_config },
+	{ "CSC3551", "10431493", generic_dsd_config },
+	{ "CSC3551", "104314D3", generic_dsd_config },
+	{ "CSC3551", "104314E3", generic_dsd_config },
+	{ "CSC3551", "10431503", generic_dsd_config },
+	{ "CSC3551", "10431533", generic_dsd_config },
+	{ "CSC3551", "10431573", generic_dsd_config },
+	{ "CSC3551", "10431663", generic_dsd_config },
+	{ "CSC3551", "104316D3", generic_dsd_config },
+	{ "CSC3551", "104316F3", generic_dsd_config },
+	{ "CSC3551", "104317F3", generic_dsd_config },
+	{ "CSC3551", "10431863", generic_dsd_config },
+	{ "CSC3551", "104318D3", generic_dsd_config },
+	{ "CSC3551", "10431C9F", generic_dsd_config },
+	{ "CSC3551", "10431CAF", generic_dsd_config },
+	{ "CSC3551", "10431CCF", generic_dsd_config },
+	{ "CSC3551", "10431CDF", generic_dsd_config },
+	{ "CSC3551", "10431CEF", generic_dsd_config },
+	{ "CSC3551", "10431D1F", generic_dsd_config },
+	{ "CSC3551", "10431DA2", generic_dsd_config },
+	{ "CSC3551", "10431E02", generic_dsd_config },
+	{ "CSC3551", "10431EE2", generic_dsd_config },
+	{ "CSC3551", "10431F12", generic_dsd_config },
+	{ "CSC3551", "10431F1F", generic_dsd_config },
+	{ "CSC3551", "10431F62", generic_dsd_config },
 	{}
 };
 
@@ -104,7 +387,7 @@ int cs35l41_add_dsd_properties(struct cs35l41_hda *cs35l41, struct device *physd
 		if (!strcmp(model->hid, hid) &&
 		    (!model->ssid ||
 		     (cs35l41->acpi_subsystem_id &&
-		      !strcmp(model->ssid, cs35l41->acpi_subsystem_id))))
+		      !strcasecmp(model->ssid, cs35l41->acpi_subsystem_id))))
 			return model->add_prop(cs35l41, physdev, id, hid);
 	}
 
diff --git a/sound/pci/hda/cs35l56_hda_i2c.c b/sound/pci/hda/cs35l56_hda_i2c.c
index 757a4d193e0f..a9ef6d86de83 100644
--- a/sound/pci/hda/cs35l56_hda_i2c.c
+++ b/sound/pci/hda/cs35l56_hda_i2c.c
@@ -21,6 +21,10 @@ static int cs35l56_hda_i2c_probe(struct i2c_client *clt)
 		return -ENOMEM;
 
 	cs35l56->base.dev = &clt->dev;
+
+#ifdef CS35L56_WAKE_HOLD_TIME_US
+	cs35l56->base.can_hibernate = true;
+#endif
 	cs35l56->base.regmap = devm_regmap_init_i2c(clt, &cs35l56_regmap_i2c);
 	if (IS_ERR(cs35l56->base.regmap)) {
 		ret = PTR_ERR(cs35l56->base.regmap);
diff --git a/sound/pci/hda/cs35l56_hda_spi.c b/sound/pci/hda/cs35l56_hda_spi.c
index 756aec342eab..080426de9083 100644
--- a/sound/pci/hda/cs35l56_hda_spi.c
+++ b/sound/pci/hda/cs35l56_hda_spi.c
@@ -21,6 +21,10 @@ static int cs35l56_hda_spi_probe(struct spi_device *spi)
 		return -ENOMEM;
 
 	cs35l56->base.dev = &spi->dev;
+
+#ifdef CS35L56_WAKE_HOLD_TIME_US
+	cs35l56->base.can_hibernate = true;
+#endif
 	cs35l56->base.regmap = devm_regmap_init_spi(spi, &cs35l56_regmap_spi);
 	if (IS_ERR(cs35l56->base.regmap)) {
 		ret = PTR_ERR(cs35l56->base.regmap);
@@ -29,7 +33,7 @@ static int cs35l56_hda_spi_probe(struct spi_device *spi)
 		return ret;
 	}
 
-	ret = cs35l56_hda_common_probe(cs35l56, spi->chip_select);
+	ret = cs35l56_hda_common_probe(cs35l56, spi_get_chipselect(spi, 0));
 	if (ret)
 		return ret;
 	ret = cs35l56_irq_request(&cs35l56->base, spi->irq);
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 03264915c618..2d1df3654424 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2135,6 +2135,9 @@ static int azx_probe(struct pci_dev *pci,
 	if (chip->driver_caps & AZX_DCAPS_I915_COMPONENT) {
 		err = snd_hdac_i915_init(azx_bus(chip));
 		if (err < 0) {
+			if (err == -EPROBE_DEFER)
+				goto out_free;
+
 			/* if the controller is bound only with HDMI/DP
 			 * (for HSW and BDW), we need to abort the probe;
 			 * for other chips, still continue probing as other
@@ -2239,6 +2242,8 @@ static const struct snd_pci_quirk power_save_denylist[] = {
 	SND_PCI_QUIRK(0x17aa, 0x36a7, "Lenovo C50 All in one", 0),
 	/* https://bugs.launchpad.net/bugs/1821663 */
 	SND_PCI_QUIRK(0x1631, 0xe017, "Packard Bell NEC IMEDIA 5204", 0),
+	/* KONTRON SinglePC may cause a stall at runtime resume */
+	SND_PCI_QUIRK(0x1734, 0x1232, "KONTRON SinglePC", 0),
 	{}
 };
 #endif /* CONFIG_PM */
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 1cde2a69bdb4..78cee53fee02 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -1993,7 +1993,10 @@ static const struct snd_pci_quirk force_connect_list[] = {
 	SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1),
 	SND_PCI_QUIRK(0x103c, 0x8711, "HP", 1),
 	SND_PCI_QUIRK(0x103c, 0x8715, "HP", 1),
+	SND_PCI_QUIRK(0x1043, 0x86ae, "ASUS", 1),  /* Z170 PRO */
+	SND_PCI_QUIRK(0x1043, 0x86c7, "ASUS", 1),  /* Z170M PLUS */
 	SND_PCI_QUIRK(0x1462, 0xec94, "MS-7C94", 1),
+	SND_PCI_QUIRK(0x8086, 0x2060, "Intel NUC5CPYB", 1),
 	SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", 1),
 	{}
 };
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 669ae3d6e447..70b17b08d4ff 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -1987,6 +1987,7 @@ enum {
 	ALC887_FIXUP_ASUS_AUDIO,
 	ALC887_FIXUP_ASUS_HMIC,
 	ALCS1200A_FIXUP_MIC_VREF,
+	ALC888VD_FIXUP_MIC_100VREF,
 };
 
 static void alc889_fixup_coef(struct hda_codec *codec,
@@ -2540,6 +2541,13 @@ static const struct hda_fixup alc882_fixups[] = {
 			{}
 		}
 	},
+	[ALC888VD_FIXUP_MIC_100VREF] = {
+		.type = HDA_FIXUP_PINCTLS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x18, PIN_VREF100 }, /* headset mic */
+			{}
+		}
+	},
 };
 
 static const struct snd_pci_quirk alc882_fixup_tbl[] = {
@@ -2609,6 +2617,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x106b, 0x4a00, "Macbook 5,2", ALC889_FIXUP_MBA11_VREF),
 
 	SND_PCI_QUIRK(0x1071, 0x8258, "Evesham Voyaeger", ALC882_FIXUP_EAPD),
+	SND_PCI_QUIRK(0x10ec, 0x12d8, "iBase Elo Touch", ALC888VD_FIXUP_MIC_100VREF),
 	SND_PCI_QUIRK(0x13fe, 0x1009, "Advantech MIT-W101", ALC886_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x1458, 0xa002, "Gigabyte EP45-DS3/Z87X-UD3H", ALC889_FIXUP_FRONT_HP_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1458, 0xa0b8, "Gigabyte AZ370-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS),
@@ -3256,6 +3265,7 @@ static void alc_disable_headset_jack_key(struct hda_codec *codec)
 	case 0x10ec0230:
 	case 0x10ec0236:
 	case 0x10ec0256:
+	case 0x10ec0257:
 	case 0x19e58326:
 		alc_write_coef_idx(codec, 0x48, 0x0);
 		alc_update_coef_idx(codec, 0x49, 0x0045, 0x0);
@@ -3285,6 +3295,7 @@ static void alc_enable_headset_jack_key(struct hda_codec *codec)
 	case 0x10ec0230:
 	case 0x10ec0236:
 	case 0x10ec0256:
+	case 0x10ec0257:
 	case 0x19e58326:
 		alc_write_coef_idx(codec, 0x48, 0xd011);
 		alc_update_coef_idx(codec, 0x49, 0x007f, 0x0045);
@@ -6496,6 +6507,7 @@ static void alc_combo_jack_hp_jd_restart(struct hda_codec *codec)
 	case 0x10ec0236:
 	case 0x10ec0255:
 	case 0x10ec0256:
+	case 0x10ec0257:
 	case 0x19e58326:
 		alc_update_coef_idx(codec, 0x1b, 0x8000, 1 << 15); /* Reset HP JD */
 		alc_update_coef_idx(codec, 0x1b, 0x8000, 0 << 15);
@@ -7249,6 +7261,7 @@ enum {
 	ALC290_FIXUP_SUBWOOFER_HSJACK,
 	ALC269_FIXUP_THINKPAD_ACPI,
 	ALC269_FIXUP_DMIC_THINKPAD_ACPI,
+	ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO,
 	ALC255_FIXUP_ACER_MIC_NO_PRESENCE,
 	ALC255_FIXUP_ASUS_MIC_NO_PRESENCE,
 	ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
@@ -7601,6 +7614,14 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc269_fixup_pincfg_U7x7_headset_mic,
 	},
+	[ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x18, 0x03a19020 }, /* headset mic */
+			{ 0x1b, 0x90170150 }, /* speaker */
+			{ }
+		},
+	},
 	[ALC269_FIXUP_AMIC] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -9684,6 +9705,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x0b1a, "Dell Precision 5570", ALC289_FIXUP_DUAL_SPK),
 	SND_PCI_QUIRK(0x1028, 0x0b37, "Dell Inspiron 16 Plus 7620 2-in-1", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS),
 	SND_PCI_QUIRK(0x1028, 0x0b71, "Dell Inspiron 16 Plus 7620", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS),
+	SND_PCI_QUIRK(0x1028, 0x0beb, "Dell XPS 15 9530 (2023)", ALC289_FIXUP_DELL_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1028, 0x0c03, "Dell Precision 5340", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0c19, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
 	SND_PCI_QUIRK(0x1028, 0x0c1a, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
@@ -9773,9 +9795,11 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x83b9, "HP Spectre x360", ALC269_FIXUP_HP_MUTE_LED_MIC3),
 	SND_PCI_QUIRK(0x103c, 0x841c, "HP Pavilion 15-CK0xx", ALC269_FIXUP_HP_MUTE_LED_MIC3),
 	SND_PCI_QUIRK(0x103c, 0x8497, "HP Envy x360", ALC269_FIXUP_HP_MUTE_LED_MIC3),
+	SND_PCI_QUIRK(0x103c, 0x84ae, "HP 15-db0403ng", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x84da, "HP OMEN dc0019-ur", ALC295_FIXUP_HP_OMEN),
 	SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3),
 	SND_PCI_QUIRK(0x103c, 0x8519, "HP Spectre x360 15-df0xxx", ALC285_FIXUP_HP_SPECTRE_X360),
+	SND_PCI_QUIRK(0x103c, 0x8537, "HP ProBook 440 G6", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x860f, "HP ZBook 15 G6", ALC285_FIXUP_HP_GPIO_AMP_INIT),
 	SND_PCI_QUIRK(0x103c, 0x861f, "HP Elite Dragonfly G1", ALC285_FIXUP_HP_GPIO_AMP_INIT),
 	SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED),
@@ -9832,6 +9856,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8898, "HP EliteBook 845 G8 Notebook PC", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x103c, 0x88d0, "HP Pavilion 15-eh1xxx (mainboard 88D0)", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8902, "HP OMEN 16", ALC285_FIXUP_HP_MUTE_LED),
+	SND_PCI_QUIRK(0x103c, 0x890e, "HP 255 G8 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x8919, "HP Pavilion Aero Laptop 13-be0xxx", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x896d, "HP ZBook Firefly 16 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x896e, "HP EliteBook x360 830 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
@@ -9857,6 +9882,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x89c6, "Zbook Fury 17 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x89ca, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x89d3, "HP EliteBook 645 G9 (MB 89D2)", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
+	SND_PCI_QUIRK(0x103c, 0x8a0f, "HP Pavilion 14-ec1xxx", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8a20, "HP Laptop 15s-fq5xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x8a25, "HP Victus 16-d1xxx (MB 8A25)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT),
 	SND_PCI_QUIRK(0x103c, 0x8a78, "HP Dev One", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST),
@@ -9867,6 +9893,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8b2f, "HP 255 15.6 inch G10 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x8b42, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8b43, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8b44, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
@@ -9900,12 +9927,17 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8c70, "HP EliteBook 835 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8c71, "HP EliteBook 845 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8c72, "HP EliteBook 865 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8c96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
+	SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x1043, 0x10a1, "ASUS UX391UA", ALC294_FIXUP_ASUS_SPK),
 	SND_PCI_QUIRK(0x1043, 0x10c0, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x10d0, "ASUS X540LA/X540LJ", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1043, 0x10d3, "ASUS K6500ZC", ALC294_FIXUP_ASUS_SPK),
 	SND_PCI_QUIRK(0x1043, 0x115d, "Asus 1015E", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x1043, 0x11c0, "ASUS X556UR", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x125e, "ASUS Q524UQK", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
@@ -9919,23 +9951,31 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1313, "Asus K42JZ", ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK),
-	SND_PCI_QUIRK(0x1043, 0x1433, "ASUS GX650P", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC),
-	SND_PCI_QUIRK(0x1043, 0x1463, "Asus GA402X", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC),
-	SND_PCI_QUIRK(0x1043, 0x1473, "ASUS GU604V", ALC285_FIXUP_ASUS_HEADSET_MIC),
-	SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603V", ALC285_FIXUP_ASUS_HEADSET_MIC),
-	SND_PCI_QUIRK(0x1043, 0x1493, "ASUS GV601V", ALC285_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1433, "ASUS GX650PY/PZ/PV/PU/PYV/PZV/PIV/PVV", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1463, "Asus GA402X/GA402N", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1473, "ASUS GU604VI/VC/VE/VG/VJ/VQ/VU/VV/VY/VZ", ALC285_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603VQ/VU/VV/VJ/VI", ALC285_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1493, "ASUS GV601VV/VU/VJ/VQ/VI", ALC285_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x14d3, "ASUS G614JY/JZ/JG", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x14e3, "ASUS G513PI/PU/PV", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x1503, "ASUS G733PY/PZ/PZV/PYV", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A),
-	SND_PCI_QUIRK(0x1043, 0x1573, "ASUS GZ301V", ALC285_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1533, "ASUS GV302XA/XJ/XQ/XU/XV/XI", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x1573, "ASUS GZ301VV/VQ/VU/VJ/VA/VC/VE/VVC/VQC/VUC/VJC/VEC/VCC", ALC285_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK),
-	SND_PCI_QUIRK(0x1043, 0x1663, "ASUS GU603ZV", ALC285_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1663, "ASUS GU603ZI/ZJ/ZQ/ZU/ZV", ALC285_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1683, "ASUS UM3402YAR", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x16b2, "ASUS GU603", ALC289_FIXUP_ASUS_GA401),
+	SND_PCI_QUIRK(0x1043, 0x16d3, "ASUS UX5304VA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC),
+	SND_PCI_QUIRK(0x1043, 0x16f3, "ASUS UX7602VI/BZ", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1740, "ASUS UX430UA", ALC295_FIXUP_ASUS_DACS),
 	SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_DUAL_SPK),
-	SND_PCI_QUIRK(0x1043, 0x17f3, "ROG Ally RC71L_RC71L", ALC294_FIXUP_ASUS_ALLY),
+	SND_PCI_QUIRK(0x1043, 0x17f3, "ROG Ally NR2301L/X", ALC294_FIXUP_ASUS_ALLY),
+	SND_PCI_QUIRK(0x1043, 0x1863, "ASUS UX6404VI/VV", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1881, "ASUS Zephyrus S/M", ALC294_FIXUP_ASUS_GX502_PINS),
 	SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x18d3, "ASUS UM3504DA", ALC294_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x18f1, "Asus FX505DT", ALC256_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x194e, "ASUS UX563FD", ALC294_FIXUP_ASUS_HPE),
 	SND_PCI_QUIRK(0x1043, 0x1970, "ASUS UX550VE", ALC289_FIXUP_ASUS_GA401),
@@ -9944,32 +9984,43 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x19e1, "ASUS UX581LV", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW),
 	SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1a63, "ASUS UX3405MA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1a83, "ASUS UM5302LA", ALC294_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1a8f, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1b11, "ASUS UX431DA", ALC294_FIXUP_ASUS_COEF_1B),
 	SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x1b93, "ASUS G614JVR/JIR", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1043, 0x1c03, "ASUS UM3406HA", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x1043, 0x1c33, "ASUS UX5304MA", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x1c43, "ASUS UX8406MA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1c62, "ASUS GU603", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS),
-	SND_PCI_QUIRK(0x1043, 0x1c9f, "ASUS G614JI", ALC285_FIXUP_ASUS_HEADSET_MIC),
-	SND_PCI_QUIRK(0x1043, 0x1caf, "ASUS G634JYR/JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
+	SND_PCI_QUIRK(0x1043, 0x1c9f, "ASUS G614JU/JV/JI", ALC285_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1caf, "ASUS G634JY/JZ/JI/JG", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC),
-	SND_PCI_QUIRK(0x1043, 0x1d1f, "ASUS ROG Strix G17 2023 (G713PV)", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x1ccf, "ASUS G814JU/JV/JI", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x1cdf, "ASUS G814JY/JZ/JG", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x1cef, "ASUS G834JY/JZ/JI/JG", ALC285_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1d1f, "ASUS G713PI/PU/PV/PVN", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE),
+	SND_PCI_QUIRK(0x1043, 0x1da2, "ASUS UP6502ZA/ZD", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1e02, "ASUS UX3402ZA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x16a3, "ASUS UX3402VA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1f62, "ASUS UX7602ZM", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502),
-	SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM6702RA/RC", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS),
 	SND_PCI_QUIRK(0x1043, 0x1e5e, "ASUS ROG Strix G513", ALC294_FIXUP_ASUS_G513_PINS),
 	SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401),
+	SND_PCI_QUIRK(0x1043, 0x1ee2, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1c52, "ASUS Zephyrus G15 2022", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1f12, "ASUS UM5302", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x1f1f, "ASUS H7604JI/JV/J3D", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x1f62, "ASUS UX7602ZM", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1f92, "ASUS ROG Flow X16", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),
 	SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC245_FIXUP_CS35L41_SPI_2),
@@ -10173,6 +10224,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x387d, "Yoga S780-16 pro Quad AAC", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x387e, "Yoga S780-16 pro Quad YC", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x3881, "YB9 dual power mode2 YC", ALC287_FIXUP_TAS2781_I2C),
+	SND_PCI_QUIRK(0x17aa, 0x3882, "Lenovo Yoga Pro 7 14APH8", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x3884, "Y780 YG DUAL", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x3886, "Y780 VECO DUAL", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x38a7, "Y780P AMD YG dual", ALC287_FIXUP_TAS2781_I2C),
@@ -10234,11 +10286,14 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1d72, 0x1945, "Redmi G", ALC256_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
+	SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO),
 	SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC),
 	SND_PCI_QUIRK(0x8086, 0x2080, "Intel NUC 8 Rugged", ALC256_FIXUP_INTEL_NUC8_RUGGED),
 	SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", ALC256_FIXUP_INTEL_NUC10),
 	SND_PCI_QUIRK(0x8086, 0x3038, "Intel NUC 13", ALC295_FIXUP_CHROME_BOOK),
 	SND_PCI_QUIRK(0xf111, 0x0001, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0xf111, 0x0005, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0xf111, 0x0006, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE),
 
 #if 0
 	/* Below is a quirk table taken from the old code.
@@ -10821,22 +10876,6 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x12, 0x90a60130},
 		{0x17, 0x90170110},
 		{0x21, 0x03211020}),
-	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,
-		{0x14, 0x90170110},
-		{0x21, 0x04211020}),
-	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,
-		{0x14, 0x90170110},
-		{0x21, 0x04211030}),
-	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
-		ALC295_STANDARD_PINS,
-		{0x17, 0x21014020},
-		{0x18, 0x21a19030}),
-	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
-		ALC295_STANDARD_PINS,
-		{0x17, 0x21014040},
-		{0x18, 0x21a19050}),
-	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
-		ALC295_STANDARD_PINS),
 	SND_HDA_PIN_QUIRK(0x10ec0298, 0x1028, "Dell", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC298_STANDARD_PINS,
 		{0x17, 0x90170110}),
@@ -10880,6 +10919,9 @@ static const struct snd_hda_pin_quirk alc269_fallback_pin_fixup_tbl[] = {
 	SND_HDA_PIN_QUIRK(0x10ec0289, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,
 		{0x19, 0x40000000},
 		{0x1b, 0x40000000}),
+	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,
+		{0x19, 0x40000000},
+		{0x1b, 0x40000000}),
 	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x19, 0x40000000},
 		{0x1a, 0x40000000}),
@@ -12177,6 +12219,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x32f7, "Lenovo ThinkCentre M90", ALC897_FIXUP_HEADSET_MIC_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x3321, "Lenovo ThinkCentre M70 Gen4", ALC897_FIXUP_HEADSET_MIC_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x331b, "Lenovo ThinkCentre M90 Gen4", ALC897_FIXUP_HEADSET_MIC_PIN),
+	SND_PCI_QUIRK(0x17aa, 0x3364, "Lenovo ThinkCentre M90 Gen5", ALC897_FIXUP_HEADSET_MIC_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x3742, "Lenovo TianYi510Pro-14IOB", ALC897_FIXUP_HEADSET_MIC_PIN2),
 	SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo Ideapad Y550P", ALC662_FIXUP_IDEAPAD),
 	SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Ideapad Y550", ALC662_FIXUP_IDEAPAD),
diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c
index fb802802939e..dfe281b57aa6 100644
--- a/sound/pci/hda/tas2781_hda_i2c.c
+++ b/sound/pci/hda/tas2781_hda_i2c.c
@@ -65,6 +65,15 @@ enum calib_data {
 	CALIB_MAX
 };
 
+struct tas2781_hda {
+	struct device *dev;
+	struct tasdevice_priv *priv;
+	struct snd_kcontrol *dsp_prog_ctl;
+	struct snd_kcontrol *dsp_conf_ctl;
+	struct snd_kcontrol *prof_ctl;
+	struct snd_kcontrol *snd_ctls[3];
+};
+
 static int tas2781_get_i2c_res(struct acpi_resource *ares, void *data)
 {
 	struct tasdevice_priv *tas_priv = data;
@@ -125,26 +134,26 @@ err:
 
 static void tas2781_hda_playback_hook(struct device *dev, int action)
 {
-	struct tasdevice_priv *tas_priv = dev_get_drvdata(dev);
+	struct tas2781_hda *tas_hda = dev_get_drvdata(dev);
 
-	dev_dbg(tas_priv->dev, "%s: action = %d\n", __func__, action);
+	dev_dbg(tas_hda->dev, "%s: action = %d\n", __func__, action);
 	switch (action) {
 	case HDA_GEN_PCM_ACT_OPEN:
 		pm_runtime_get_sync(dev);
-		mutex_lock(&tas_priv->codec_lock);
-		tasdevice_tuning_switch(tas_priv, 0);
-		mutex_unlock(&tas_priv->codec_lock);
+		mutex_lock(&tas_hda->priv->codec_lock);
+		tasdevice_tuning_switch(tas_hda->priv, 0);
+		mutex_unlock(&tas_hda->priv->codec_lock);
 		break;
 	case HDA_GEN_PCM_ACT_CLOSE:
-		mutex_lock(&tas_priv->codec_lock);
-		tasdevice_tuning_switch(tas_priv, 1);
-		mutex_unlock(&tas_priv->codec_lock);
+		mutex_lock(&tas_hda->priv->codec_lock);
+		tasdevice_tuning_switch(tas_hda->priv, 1);
+		mutex_unlock(&tas_hda->priv->codec_lock);
 
 		pm_runtime_mark_last_busy(dev);
 		pm_runtime_put_autosuspend(dev);
 		break;
 	default:
-		dev_dbg(tas_priv->dev, "Playback action not supported: %d\n",
+		dev_dbg(tas_hda->dev, "Playback action not supported: %d\n",
 			action);
 		break;
 	}
@@ -421,9 +430,9 @@ static void tas2781_apply_calib(struct tasdevice_priv *tas_priv)
 	}
 }
 
-/* Update the calibrate data, including speaker impedance, f0, etc, into algo.
+/* Update the calibration data, including speaker impedance, f0, etc, into algo.
  * Calibrate data is done by manufacturer in the factory. These data are used
- * by Algo for calucating the speaker temperature, speaker membrance excursion
+ * by Algo for calculating the speaker temperature, speaker membrane excursion
  * and f0 in real time during playback.
  */
 static int tas2781_save_calibration(struct tasdevice_priv *tas_priv)
@@ -455,9 +464,9 @@ static int tas2781_save_calibration(struct tasdevice_priv *tas_priv)
 		status = efi.get_variable(efi_name, &efi_guid, &attr,
 			&tas_priv->cali_data.total_sz,
 			tas_priv->cali_data.data);
-		if (status != EFI_SUCCESS)
-			return -EINVAL;
 	}
+	if (status != EFI_SUCCESS)
+		return -EINVAL;
 
 	tmp_val = (unsigned int *)tas_priv->cali_data.data;
 
@@ -477,9 +486,28 @@ static int tas2781_save_calibration(struct tasdevice_priv *tas_priv)
 	return 0;
 }
 
+static void tas2781_hda_remove_controls(struct tas2781_hda *tas_hda)
+{
+	struct hda_codec *codec = tas_hda->priv->codec;
+
+	if (tas_hda->dsp_prog_ctl)
+		snd_ctl_remove(codec->card, tas_hda->dsp_prog_ctl);
+
+	if (tas_hda->dsp_conf_ctl)
+		snd_ctl_remove(codec->card, tas_hda->dsp_conf_ctl);
+
+	for (int i = ARRAY_SIZE(tas_hda->snd_ctls) - 1; i >= 0; i--)
+		if (tas_hda->snd_ctls[i])
+			snd_ctl_remove(codec->card, tas_hda->snd_ctls[i]);
+
+	if (tas_hda->prof_ctl)
+		snd_ctl_remove(codec->card, tas_hda->prof_ctl);
+}
+
 static void tasdev_fw_ready(const struct firmware *fmw, void *context)
 {
 	struct tasdevice_priv *tas_priv = context;
+	struct tas2781_hda *tas_hda = dev_get_drvdata(tas_priv->dev);
 	struct hda_codec *codec = tas_priv->codec;
 	int i, ret;
 
@@ -490,8 +518,8 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context)
 	if (ret)
 		goto out;
 
-	ret = snd_ctl_add(codec->card,
-		snd_ctl_new1(&tas2781_prof_ctrl, tas_priv));
+	tas_hda->prof_ctl = snd_ctl_new1(&tas2781_prof_ctrl, tas_priv);
+	ret = snd_ctl_add(codec->card, tas_hda->prof_ctl);
 	if (ret) {
 		dev_err(tas_priv->dev,
 			"Failed to add KControl %s = %d\n",
@@ -500,8 +528,9 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context)
 	}
 
 	for (i = 0; i < ARRAY_SIZE(tas2781_snd_controls); i++) {
-		ret = snd_ctl_add(codec->card,
-			snd_ctl_new1(&tas2781_snd_controls[i], tas_priv));
+		tas_hda->snd_ctls[i] = snd_ctl_new1(&tas2781_snd_controls[i],
+			tas_priv);
+		ret = snd_ctl_add(codec->card, tas_hda->snd_ctls[i]);
 		if (ret) {
 			dev_err(tas_priv->dev,
 				"Failed to add KControl %s = %d\n",
@@ -523,8 +552,9 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context)
 		goto out;
 	}
 
-	ret = snd_ctl_add(codec->card,
-		snd_ctl_new1(&tas2781_dsp_prog_ctrl, tas_priv));
+	tas_hda->dsp_prog_ctl = snd_ctl_new1(&tas2781_dsp_prog_ctrl,
+		tas_priv);
+	ret = snd_ctl_add(codec->card, tas_hda->dsp_prog_ctl);
 	if (ret) {
 		dev_err(tas_priv->dev,
 			"Failed to add KControl %s = %d\n",
@@ -532,8 +562,9 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context)
 		goto out;
 	}
 
-	ret = snd_ctl_add(codec->card,
-		snd_ctl_new1(&tas2781_dsp_conf_ctrl, tas_priv));
+	tas_hda->dsp_conf_ctl = snd_ctl_new1(&tas2781_dsp_conf_ctrl,
+		tas_priv);
+	ret = snd_ctl_add(codec->card, tas_hda->dsp_conf_ctl);
 	if (ret) {
 		dev_err(tas_priv->dev,
 			"Failed to add KControl %s = %d\n",
@@ -543,6 +574,10 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context)
 
 	tas_priv->fw_state = TASDEVICE_DSP_FW_ALL_OK;
 	tasdevice_prmg_load(tas_priv, 0);
+	if (tas_priv->fmw->nr_programs > 0)
+		tas_priv->cur_prog = 0;
+	if (tas_priv->fmw->nr_configurations > 0)
+		tas_priv->cur_conf = 0;
 
 	/* If calibrated data occurs error, dsp will still works with default
 	 * calibrated data inside algo.
@@ -550,32 +585,27 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context)
 	tas2781_save_calibration(tas_priv);
 
 out:
-	if (tas_priv->fw_state == TASDEVICE_DSP_FW_FAIL) {
-		/*If DSP FW fail, kcontrol won't be created */
-		tasdevice_config_info_remove(tas_priv);
-		tasdevice_dsp_remove(tas_priv);
-	}
-	mutex_unlock(&tas_priv->codec_lock);
+	mutex_unlock(&tas_hda->priv->codec_lock);
 	if (fmw)
 		release_firmware(fmw);
-	pm_runtime_mark_last_busy(tas_priv->dev);
-	pm_runtime_put_autosuspend(tas_priv->dev);
+	pm_runtime_mark_last_busy(tas_hda->dev);
+	pm_runtime_put_autosuspend(tas_hda->dev);
 }
 
 static int tas2781_hda_bind(struct device *dev, struct device *master,
 	void *master_data)
 {
-	struct tasdevice_priv *tas_priv = dev_get_drvdata(dev);
+	struct tas2781_hda *tas_hda = dev_get_drvdata(dev);
 	struct hda_component *comps = master_data;
 	struct hda_codec *codec;
 	unsigned int subid;
 	int ret;
 
-	if (!comps || tas_priv->index < 0 ||
-		tas_priv->index >= HDA_MAX_COMPONENTS)
+	if (!comps || tas_hda->priv->index < 0 ||
+		tas_hda->priv->index >= HDA_MAX_COMPONENTS)
 		return -EINVAL;
 
-	comps = &comps[tas_priv->index];
+	comps = &comps[tas_hda->priv->index];
 	if (comps->dev)
 		return -EBUSY;
 
@@ -584,10 +614,10 @@ static int tas2781_hda_bind(struct device *dev, struct device *master,
 
 	switch (subid) {
 	case 0x17aa:
-		tas_priv->catlog_id = LENOVO;
+		tas_hda->priv->catlog_id = LENOVO;
 		break;
 	default:
-		tas_priv->catlog_id = OTHERS;
+		tas_hda->priv->catlog_id = OTHERS;
 		break;
 	}
 
@@ -597,7 +627,7 @@ static int tas2781_hda_bind(struct device *dev, struct device *master,
 
 	strscpy(comps->name, dev_name(dev), sizeof(comps->name));
 
-	ret = tascodec_init(tas_priv, codec, tasdev_fw_ready);
+	ret = tascodec_init(tas_hda->priv, codec, tasdev_fw_ready);
 	if (!ret)
 		comps->playback_hook = tas2781_hda_playback_hook;
 
@@ -610,16 +640,22 @@ static int tas2781_hda_bind(struct device *dev, struct device *master,
 static void tas2781_hda_unbind(struct device *dev,
 	struct device *master, void *master_data)
 {
-	struct tasdevice_priv *tas_priv = dev_get_drvdata(dev);
+	struct tas2781_hda *tas_hda = dev_get_drvdata(dev);
 	struct hda_component *comps = master_data;
+	comps = &comps[tas_hda->priv->index];
 
-	if (comps[tas_priv->index].dev == dev)
-		memset(&comps[tas_priv->index], 0, sizeof(*comps));
+	if (comps->dev == dev) {
+		comps->dev = NULL;
+		memset(comps->name, 0, sizeof(comps->name));
+		comps->playback_hook = NULL;
+	}
 
-	tasdevice_config_info_remove(tas_priv);
-	tasdevice_dsp_remove(tas_priv);
+	tas2781_hda_remove_controls(tas_hda);
 
-	tas_priv->fw_state = TASDEVICE_DSP_FW_PENDING;
+	tasdevice_config_info_remove(tas_hda->priv);
+	tasdevice_dsp_remove(tas_hda->priv);
+
+	tas_hda->priv->fw_state = TASDEVICE_DSP_FW_PENDING;
 }
 
 static const struct component_ops tas2781_hda_comp_ops = {
@@ -629,21 +665,21 @@ static const struct component_ops tas2781_hda_comp_ops = {
 
 static void tas2781_hda_remove(struct device *dev)
 {
-	struct tasdevice_priv *tas_priv = dev_get_drvdata(dev);
+	struct tas2781_hda *tas_hda = dev_get_drvdata(dev);
 
-	pm_runtime_get_sync(tas_priv->dev);
-	pm_runtime_disable(tas_priv->dev);
+	pm_runtime_get_sync(tas_hda->dev);
+	pm_runtime_disable(tas_hda->dev);
 
-	component_del(tas_priv->dev, &tas2781_hda_comp_ops);
+	component_del(tas_hda->dev, &tas2781_hda_comp_ops);
 
-	pm_runtime_put_noidle(tas_priv->dev);
+	pm_runtime_put_noidle(tas_hda->dev);
 
-	tasdevice_remove(tas_priv);
+	tasdevice_remove(tas_hda->priv);
 }
 
 static int tas2781_hda_i2c_probe(struct i2c_client *clt)
 {
-	struct tasdevice_priv *tas_priv;
+	struct tas2781_hda *tas_hda;
 	const char *device_name;
 	int ret;
 
@@ -652,37 +688,44 @@ static int tas2781_hda_i2c_probe(struct i2c_client *clt)
 	else
 		return -ENODEV;
 
-	tas_priv = tasdevice_kzalloc(clt);
-	if (!tas_priv)
+	tas_hda = devm_kzalloc(&clt->dev, sizeof(*tas_hda), GFP_KERNEL);
+	if (!tas_hda)
+		return -ENOMEM;
+
+	dev_set_drvdata(&clt->dev, tas_hda);
+	tas_hda->dev = &clt->dev;
+
+	tas_hda->priv = tasdevice_kzalloc(clt);
+	if (!tas_hda->priv)
 		return -ENOMEM;
 
-	tas_priv->irq_info.irq = clt->irq;
-	ret = tas2781_read_acpi(tas_priv, device_name);
+	tas_hda->priv->irq_info.irq = clt->irq;
+	ret = tas2781_read_acpi(tas_hda->priv, device_name);
 	if (ret)
-		return dev_err_probe(tas_priv->dev, ret,
+		return dev_err_probe(tas_hda->dev, ret,
 			"Platform not supported\n");
 
-	ret = tasdevice_init(tas_priv);
+	ret = tasdevice_init(tas_hda->priv);
 	if (ret)
 		goto err;
 
-	pm_runtime_set_autosuspend_delay(tas_priv->dev, 3000);
-	pm_runtime_use_autosuspend(tas_priv->dev);
-	pm_runtime_mark_last_busy(tas_priv->dev);
-	pm_runtime_set_active(tas_priv->dev);
-	pm_runtime_get_noresume(tas_priv->dev);
-	pm_runtime_enable(tas_priv->dev);
+	pm_runtime_set_autosuspend_delay(tas_hda->dev, 3000);
+	pm_runtime_use_autosuspend(tas_hda->dev);
+	pm_runtime_mark_last_busy(tas_hda->dev);
+	pm_runtime_set_active(tas_hda->dev);
+	pm_runtime_get_noresume(tas_hda->dev);
+	pm_runtime_enable(tas_hda->dev);
 
-	pm_runtime_put_autosuspend(tas_priv->dev);
+	pm_runtime_put_autosuspend(tas_hda->dev);
 
-	ret = component_add(tas_priv->dev, &tas2781_hda_comp_ops);
+	tas2781_reset(tas_hda->priv);
+
+	ret = component_add(tas_hda->dev, &tas2781_hda_comp_ops);
 	if (ret) {
-		dev_err(tas_priv->dev, "Register component failed: %d\n", ret);
-		pm_runtime_disable(tas_priv->dev);
-		goto err;
+		dev_err(tas_hda->dev, "Register component failed: %d\n", ret);
+		pm_runtime_disable(tas_hda->dev);
 	}
 
-	tas2781_reset(tas_priv);
 err:
 	if (ret)
 		tas2781_hda_remove(&clt->dev);
@@ -696,81 +739,65 @@ static void tas2781_hda_i2c_remove(struct i2c_client *clt)
 
 static int tas2781_runtime_suspend(struct device *dev)
 {
-	struct tasdevice_priv *tas_priv = dev_get_drvdata(dev);
+	struct tas2781_hda *tas_hda = dev_get_drvdata(dev);
 	int i;
 
-	dev_dbg(tas_priv->dev, "Runtime Suspend\n");
+	dev_dbg(tas_hda->dev, "Runtime Suspend\n");
 
-	mutex_lock(&tas_priv->codec_lock);
+	mutex_lock(&tas_hda->priv->codec_lock);
 
-	if (tas_priv->playback_started) {
-		tasdevice_tuning_switch(tas_priv, 1);
-		tas_priv->playback_started = false;
+	if (tas_hda->priv->playback_started) {
+		tasdevice_tuning_switch(tas_hda->priv, 1);
+		tas_hda->priv->playback_started = false;
 	}
 
-	for (i = 0; i < tas_priv->ndev; i++) {
-		tas_priv->tasdevice[i].cur_book = -1;
-		tas_priv->tasdevice[i].cur_prog = -1;
-		tas_priv->tasdevice[i].cur_conf = -1;
+	for (i = 0; i < tas_hda->priv->ndev; i++) {
+		tas_hda->priv->tasdevice[i].cur_book = -1;
+		tas_hda->priv->tasdevice[i].cur_prog = -1;
+		tas_hda->priv->tasdevice[i].cur_conf = -1;
 	}
 
-	regcache_cache_only(tas_priv->regmap, true);
-	regcache_mark_dirty(tas_priv->regmap);
-
-	mutex_unlock(&tas_priv->codec_lock);
+	mutex_unlock(&tas_hda->priv->codec_lock);
 
 	return 0;
 }
 
 static int tas2781_runtime_resume(struct device *dev)
 {
-	struct tasdevice_priv *tas_priv = dev_get_drvdata(dev);
+	struct tas2781_hda *tas_hda = dev_get_drvdata(dev);
 	unsigned long calib_data_sz =
-		tas_priv->ndev * TASDEVICE_SPEAKER_CALIBRATION_SIZE;
-	int ret;
+		tas_hda->priv->ndev * TASDEVICE_SPEAKER_CALIBRATION_SIZE;
 
-	dev_dbg(tas_priv->dev, "Runtime Resume\n");
+	dev_dbg(tas_hda->dev, "Runtime Resume\n");
 
-	mutex_lock(&tas_priv->codec_lock);
+	mutex_lock(&tas_hda->priv->codec_lock);
 
-	regcache_cache_only(tas_priv->regmap, false);
-	ret = regcache_sync(tas_priv->regmap);
-	if (ret) {
-		dev_err(tas_priv->dev,
-			"Failed to restore register cache: %d\n", ret);
-		goto out;
-	}
-
-	tasdevice_prmg_load(tas_priv, tas_priv->cur_prog);
+	tasdevice_prmg_load(tas_hda->priv, tas_hda->priv->cur_prog);
 
 	/* If calibrated data occurs error, dsp will still works with default
 	 * calibrated data inside algo.
 	 */
-	if (tas_priv->cali_data.total_sz > calib_data_sz)
-		tas2781_apply_calib(tas_priv);
+	if (tas_hda->priv->cali_data.total_sz > calib_data_sz)
+		tas2781_apply_calib(tas_hda->priv);
 
-out:
-	mutex_unlock(&tas_priv->codec_lock);
+	mutex_unlock(&tas_hda->priv->codec_lock);
 
-	return ret;
+	return 0;
 }
 
 static int tas2781_system_suspend(struct device *dev)
 {
-	struct tasdevice_priv *tas_priv = dev_get_drvdata(dev);
+	struct tas2781_hda *tas_hda = dev_get_drvdata(dev);
 	int ret;
 
-	dev_dbg(tas_priv->dev, "System Suspend\n");
+	dev_dbg(tas_hda->priv->dev, "System Suspend\n");
 
 	ret = pm_runtime_force_suspend(dev);
 	if (ret)
 		return ret;
 
 	/* Shutdown chip before system suspend */
-	regcache_cache_only(tas_priv->regmap, false);
-	tasdevice_tuning_switch(tas_priv, 1);
-	regcache_cache_only(tas_priv->regmap, true);
-	regcache_mark_dirty(tas_priv->regmap);
+	tasdevice_tuning_switch(tas_hda->priv, 1);
 
 	/*
 	 * Reset GPIO may be shared, so cannot reset here.
@@ -781,33 +808,33 @@ static int tas2781_system_suspend(struct device *dev)
 
 static int tas2781_system_resume(struct device *dev)
 {
-	struct tasdevice_priv *tas_priv = dev_get_drvdata(dev);
+	struct tas2781_hda *tas_hda = dev_get_drvdata(dev);
 	unsigned long calib_data_sz =
-		tas_priv->ndev * TASDEVICE_SPEAKER_CALIBRATION_SIZE;
+		tas_hda->priv->ndev * TASDEVICE_SPEAKER_CALIBRATION_SIZE;
 	int i, ret;
 
-	dev_dbg(tas_priv->dev, "System Resume\n");
+	dev_info(tas_hda->priv->dev, "System Resume\n");
 
 	ret = pm_runtime_force_resume(dev);
 	if (ret)
 		return ret;
 
-	mutex_lock(&tas_priv->codec_lock);
+	mutex_lock(&tas_hda->priv->codec_lock);
 
-	for (i = 0; i < tas_priv->ndev; i++) {
-		tas_priv->tasdevice[i].cur_book = -1;
-		tas_priv->tasdevice[i].cur_prog = -1;
-		tas_priv->tasdevice[i].cur_conf = -1;
+	for (i = 0; i < tas_hda->priv->ndev; i++) {
+		tas_hda->priv->tasdevice[i].cur_book = -1;
+		tas_hda->priv->tasdevice[i].cur_prog = -1;
+		tas_hda->priv->tasdevice[i].cur_conf = -1;
 	}
-	tas2781_reset(tas_priv);
-	tasdevice_prmg_load(tas_priv, tas_priv->cur_prog);
+	tas2781_reset(tas_hda->priv);
+	tasdevice_prmg_load(tas_hda->priv, tas_hda->priv->cur_prog);
 
 	/* If calibrated data occurs error, dsp will still work with default
 	 * calibrated data inside algo.
 	 */
-	if (tas_priv->cali_data.total_sz > calib_data_sz)
-		tas2781_apply_calib(tas_priv);
-	mutex_unlock(&tas_priv->codec_lock);
+	if (tas_hda->priv->cali_data.total_sz > calib_data_sz)
+		tas2781_apply_calib(tas_hda->priv);
+	mutex_unlock(&tas_hda->priv->codec_lock);
 
 	return 0;
 }
diff --git a/sound/soc/amd/acp-config.c b/sound/soc/amd/acp-config.c
index 20cee7104c2b..3bc4b2e41650 100644
--- a/sound/soc/amd/acp-config.c
+++ b/sound/soc/amd/acp-config.c
@@ -111,6 +111,20 @@ static const struct config_entry config_table[] = {
 				.matches = {
 					DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "HUAWEI"),
 					DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "HVY-WXX9"),
+					DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "M1010"),
+				},
+			},
+			{}
+		},
+	},
+	{
+		.flags = FLAG_AMD_LEGACY,
+		.device = ACP_PCI_DEV_ID,
+		.dmi_table = (const struct dmi_system_id []) {
+			{
+				.matches = {
+					DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "HUAWEI"),
+					DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "HVY-WXX9"),
 					DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "M1020"),
 				},
 			},
diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index 15a864dcd7bd..d83cb6e4c62a 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -286,6 +286,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 	{
 		.driver_data = &acp6x_card,
 		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "E1504FA"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Bravo 15 B7ED"),
 		}
@@ -370,6 +377,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 	{
 		.driver_data = &acp6x_card,
 		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "HP"),
+			DMI_MATCH(DMI_BOARD_NAME, "8B2F"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "MECHREVO"),
 			DMI_MATCH(DMI_BOARD_NAME, "MRID6"),
 		}
@@ -381,6 +395,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 			DMI_MATCH(DMI_PRODUCT_VERSION, "pang12"),
 		}
 	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "System76"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "pang13"),
+		}
+	},
 	{}
 };
 
diff --git a/sound/soc/codecs/cs35l41-lib.c b/sound/soc/codecs/cs35l41-lib.c
index 4569e4f7cf7e..e9993a39f7d0 100644
--- a/sound/soc/codecs/cs35l41-lib.c
+++ b/sound/soc/codecs/cs35l41-lib.c
@@ -16,6 +16,8 @@
 
 #include <sound/cs35l41.h>
 
+#define CS35L41_FIRMWARE_OLD_VERSION 0x001C00 /* v0.28.0 */
+
 static const struct reg_default cs35l41_reg[] = {
 	{ CS35L41_PWR_CTRL1,			0x00000000 },
 	{ CS35L41_PWR_CTRL2,			0x00000000 },
@@ -1214,7 +1216,7 @@ EXPORT_SYMBOL_GPL(cs35l41_safe_reset);
  * the PLL Lock interrupt, in the IRQ handler.
  */
 int cs35l41_global_enable(struct device *dev, struct regmap *regmap, enum cs35l41_boost_type b_type,
-			  int enable, bool firmware_running)
+			  int enable, struct cs_dsp *dsp)
 {
 	int ret;
 	unsigned int gpio1_func, pad_control, pwr_ctrl1, pwr_ctrl3, int_status, pup_pdn_mask;
@@ -1309,7 +1311,7 @@ int cs35l41_global_enable(struct device *dev, struct regmap *regmap, enum cs35l4
 			}
 			regmap_write(regmap, CS35L41_IRQ1_STATUS1, CS35L41_PUP_DONE_MASK);
 
-			if (firmware_running)
+			if (dsp->running && dsp->fw_id_version > CS35L41_FIRMWARE_OLD_VERSION)
 				ret = cs35l41_set_cspl_mbox_cmd(dev, regmap,
 								CSPL_MBOX_CMD_SPK_OUT_ENABLE);
 			else
diff --git a/sound/soc/codecs/cs35l41.c b/sound/soc/codecs/cs35l41.c
index d0e9128ac6d0..dfb4ce53491b 100644
--- a/sound/soc/codecs/cs35l41.c
+++ b/sound/soc/codecs/cs35l41.c
@@ -519,11 +519,11 @@ static int cs35l41_main_amp_event(struct snd_soc_dapm_widget *w,
 						ARRAY_SIZE(cs35l41_pup_patch));
 
 		ret = cs35l41_global_enable(cs35l41->dev, cs35l41->regmap, cs35l41->hw_cfg.bst_type,
-					    1, cs35l41->dsp.cs_dsp.running);
+					    1, &cs35l41->dsp.cs_dsp);
 		break;
 	case SND_SOC_DAPM_POST_PMD:
 		ret = cs35l41_global_enable(cs35l41->dev, cs35l41->regmap, cs35l41->hw_cfg.bst_type,
-					    0, cs35l41->dsp.cs_dsp.running);
+					    0, &cs35l41->dsp.cs_dsp);
 
 		regmap_multi_reg_write_bypassed(cs35l41->regmap,
 						cs35l41_pdn_patch,
diff --git a/sound/soc/codecs/cs35l45-i2c.c b/sound/soc/codecs/cs35l45-i2c.c
index 77e0f8750f37..bc2af1ed0fe9 100644
--- a/sound/soc/codecs/cs35l45-i2c.c
+++ b/sound/soc/codecs/cs35l45-i2c.c
@@ -62,7 +62,7 @@ static struct i2c_driver cs35l45_i2c_driver = {
 	.driver = {
 		.name		= "cs35l45",
 		.of_match_table = cs35l45_of_match,
-		.pm		= &cs35l45_pm_ops,
+		.pm		= pm_ptr(&cs35l45_pm_ops),
 	},
 	.id_table	= cs35l45_id_i2c,
 	.probe		= cs35l45_i2c_probe,
diff --git a/sound/soc/codecs/cs35l45-spi.c b/sound/soc/codecs/cs35l45-spi.c
index 5efb77530cc3..39e203a5f060 100644
--- a/sound/soc/codecs/cs35l45-spi.c
+++ b/sound/soc/codecs/cs35l45-spi.c
@@ -64,7 +64,7 @@ static struct spi_driver cs35l45_spi_driver = {
 	.driver = {
 		.name		= "cs35l45",
 		.of_match_table = cs35l45_of_match,
-		.pm		= &cs35l45_pm_ops,
+		.pm		= pm_ptr(&cs35l45_pm_ops),
 	},
 	.id_table	= cs35l45_id_spi,
 	.probe		= cs35l45_spi_probe,
diff --git a/sound/soc/codecs/cs35l45.c b/sound/soc/codecs/cs35l45.c
index b68853e42fd1..44c221745c3b 100644
--- a/sound/soc/codecs/cs35l45.c
+++ b/sound/soc/codecs/cs35l45.c
@@ -947,6 +947,8 @@ static int cs35l45_enter_hibernate(struct cs35l45_private *cs35l45)
 
 	cs35l45_setup_hibernate(cs35l45);
 
+	regmap_set_bits(cs35l45->regmap, CS35L45_IRQ1_MASK_2, CS35L45_DSP_VIRT2_MBOX_MASK);
+
 	// Don't wait for ACK since bus activity would wake the device
 	regmap_write(cs35l45->regmap, CS35L45_DSP_VIRT1_MBOX_1, CSPL_MBOX_CMD_HIBERNATE);
 
@@ -967,6 +969,8 @@ static int cs35l45_exit_hibernate(struct cs35l45_private *cs35l45)
 					  CSPL_MBOX_CMD_OUT_OF_HIBERNATE);
 			if (!ret) {
 				dev_dbg(cs35l45->dev, "Wake success at cycle: %d\n", j);
+				regmap_clear_bits(cs35l45->regmap, CS35L45_IRQ1_MASK_2,
+						 CS35L45_DSP_VIRT2_MBOX_MASK);
 				return 0;
 			}
 			usleep_range(100, 200);
@@ -982,7 +986,7 @@ static int cs35l45_exit_hibernate(struct cs35l45_private *cs35l45)
 	return -ETIMEDOUT;
 }
 
-static int __maybe_unused cs35l45_runtime_suspend(struct device *dev)
+static int cs35l45_runtime_suspend(struct device *dev)
 {
 	struct cs35l45_private *cs35l45 = dev_get_drvdata(dev);
 
@@ -999,7 +1003,7 @@ static int __maybe_unused cs35l45_runtime_suspend(struct device *dev)
 	return 0;
 }
 
-static int __maybe_unused cs35l45_runtime_resume(struct device *dev)
+static int cs35l45_runtime_resume(struct device *dev)
 {
 	struct cs35l45_private *cs35l45 = dev_get_drvdata(dev);
 	int ret;
@@ -1026,6 +1030,46 @@ static int __maybe_unused cs35l45_runtime_resume(struct device *dev)
 	return ret;
 }
 
+static int cs35l45_sys_suspend(struct device *dev)
+{
+	struct cs35l45_private *cs35l45 = dev_get_drvdata(dev);
+
+	dev_dbg(cs35l45->dev, "System suspend, disabling IRQ\n");
+	disable_irq(cs35l45->irq);
+
+	return 0;
+}
+
+static int cs35l45_sys_suspend_noirq(struct device *dev)
+{
+	struct cs35l45_private *cs35l45 = dev_get_drvdata(dev);
+
+	dev_dbg(cs35l45->dev, "Late system suspend, reenabling IRQ\n");
+	enable_irq(cs35l45->irq);
+
+	return 0;
+}
+
+static int cs35l45_sys_resume_noirq(struct device *dev)
+{
+	struct cs35l45_private *cs35l45 = dev_get_drvdata(dev);
+
+	dev_dbg(cs35l45->dev, "Early system resume, disabling IRQ\n");
+	disable_irq(cs35l45->irq);
+
+	return 0;
+}
+
+static int cs35l45_sys_resume(struct device *dev)
+{
+	struct cs35l45_private *cs35l45 = dev_get_drvdata(dev);
+
+	dev_dbg(cs35l45->dev, "System resume, reenabling IRQ\n");
+	enable_irq(cs35l45->irq);
+
+	return 0;
+}
+
 static int cs35l45_apply_property_config(struct cs35l45_private *cs35l45)
 {
 	struct device_node *node = cs35l45->dev->of_node;
@@ -1466,10 +1510,12 @@ void cs35l45_remove(struct cs35l45_private *cs35l45)
 }
 EXPORT_SYMBOL_NS_GPL(cs35l45_remove, SND_SOC_CS35L45);
 
-const struct dev_pm_ops cs35l45_pm_ops = {
-	SET_RUNTIME_PM_OPS(cs35l45_runtime_suspend, cs35l45_runtime_resume, NULL)
+EXPORT_GPL_DEV_PM_OPS(cs35l45_pm_ops) = {
+	RUNTIME_PM_OPS(cs35l45_runtime_suspend, cs35l45_runtime_resume, NULL)
+
+	SYSTEM_SLEEP_PM_OPS(cs35l45_sys_suspend, cs35l45_sys_resume)
+	NOIRQ_SYSTEM_SLEEP_PM_OPS(cs35l45_sys_suspend_noirq, cs35l45_sys_resume_noirq)
 };
-EXPORT_SYMBOL_NS_GPL(cs35l45_pm_ops, SND_SOC_CS35L45);
 
 MODULE_DESCRIPTION("ASoC CS35L45 driver");
 MODULE_AUTHOR("James Schulman, Cirrus Logic Inc, <james.schulman@cirrus.com>");
diff --git a/sound/soc/codecs/cs42l43-jack.c b/sound/soc/codecs/cs42l43-jack.c
index 73454de068cf..54a3ea606443 100644
--- a/sound/soc/codecs/cs42l43-jack.c
+++ b/sound/soc/codecs/cs42l43-jack.c
@@ -237,7 +237,7 @@ error:
 	return ret;
 }
 
-static void cs42l43_start_hs_bias(struct cs42l43_codec *priv, bool force_high)
+static void cs42l43_start_hs_bias(struct cs42l43_codec *priv, bool type_detect)
 {
 	struct cs42l43 *cs42l43 = priv->core;
 	unsigned int val = 0x3 << CS42L43_HSBIAS_MODE_SHIFT;
@@ -247,16 +247,17 @@ static void cs42l43_start_hs_bias(struct cs42l43_codec *priv, bool force_high)
 	regmap_update_bits(cs42l43->regmap, CS42L43_HS2,
 			   CS42L43_HS_CLAMP_DISABLE_MASK, CS42L43_HS_CLAMP_DISABLE_MASK);
 
-	if (!force_high && priv->bias_low)
-		val = 0x2 << CS42L43_HSBIAS_MODE_SHIFT;
-
-	if (priv->bias_sense_ua) {
-		regmap_update_bits(cs42l43->regmap,
-				   CS42L43_HS_BIAS_SENSE_AND_CLAMP_AUTOCONTROL,
-				   CS42L43_HSBIAS_SENSE_EN_MASK |
-				   CS42L43_AUTO_HSBIAS_CLAMP_EN_MASK,
-				   CS42L43_HSBIAS_SENSE_EN_MASK |
-				   CS42L43_AUTO_HSBIAS_CLAMP_EN_MASK);
+	if (!type_detect) {
+		if (priv->bias_low)
+			val = 0x2 << CS42L43_HSBIAS_MODE_SHIFT;
+
+		if (priv->bias_sense_ua)
+			regmap_update_bits(cs42l43->regmap,
+					   CS42L43_HS_BIAS_SENSE_AND_CLAMP_AUTOCONTROL,
+					   CS42L43_HSBIAS_SENSE_EN_MASK |
+					   CS42L43_AUTO_HSBIAS_CLAMP_EN_MASK,
+					   CS42L43_HSBIAS_SENSE_EN_MASK |
+					   CS42L43_AUTO_HSBIAS_CLAMP_EN_MASK);
 	}
 
 	regmap_update_bits(cs42l43->regmap, CS42L43_MIC_DETECT_CONTROL_1,
diff --git a/sound/soc/codecs/cs43130.c b/sound/soc/codecs/cs43130.c
index 0b40fdfb1825..d8ec325b9cc9 100644
--- a/sound/soc/codecs/cs43130.c
+++ b/sound/soc/codecs/cs43130.c
@@ -578,7 +578,7 @@ static int cs43130_set_sp_fmt(int dai_id, unsigned int bitwidth_sclk,
 		break;
 	case SND_SOC_DAIFMT_LEFT_J:
 		hi_size = bitwidth_sclk;
-		frm_delay = 2;
+		frm_delay = 0;
 		frm_phase = 1;
 		break;
 	case SND_SOC_DAIFMT_DSP_A:
@@ -1682,7 +1682,7 @@ static ssize_t hpload_dc_r_show(struct device *dev,
 	return cs43130_show_dc(dev, buf, HP_RIGHT);
 }
 
-static u16 const cs43130_ac_freq[CS43130_AC_FREQ] = {
+static const u16 cs43130_ac_freq[CS43130_AC_FREQ] = {
 	24,
 	43,
 	93,
@@ -2362,7 +2362,7 @@ static const struct regmap_config cs43130_regmap = {
 	.use_single_write	= true,
 };
 
-static u16 const cs43130_dc_threshold[CS43130_DC_THRESHOLD] = {
+static const u16 cs43130_dc_threshold[CS43130_DC_THRESHOLD] = {
 	50,
 	120,
 };
diff --git a/sound/soc/codecs/da7219-aad.c b/sound/soc/codecs/da7219-aad.c
index 4c4405942779..6bc068cdcbe2 100644
--- a/sound/soc/codecs/da7219-aad.c
+++ b/sound/soc/codecs/da7219-aad.c
@@ -696,7 +696,7 @@ static struct da7219_aad_pdata *da7219_aad_fw_to_pdata(struct device *dev)
 		aad_pdata->mic_det_thr =
 			da7219_aad_fw_mic_det_thr(dev, fw_val32);
 	else
-		aad_pdata->mic_det_thr = DA7219_AAD_MIC_DET_THR_500_OHMS;
+		aad_pdata->mic_det_thr = DA7219_AAD_MIC_DET_THR_200_OHMS;
 
 	if (fwnode_property_read_u32(aad_np, "dlg,jack-ins-deb", &fw_val32) >= 0)
 		aad_pdata->jack_ins_deb =
diff --git a/sound/soc/codecs/hdac_hda.c b/sound/soc/codecs/hdac_hda.c
index 355f30779a34..b075689db2dc 100644
--- a/sound/soc/codecs/hdac_hda.c
+++ b/sound/soc/codecs/hdac_hda.c
@@ -132,6 +132,9 @@ static struct snd_soc_dai_driver hdac_hda_dais[] = {
 		.sig_bits = 24,
 	},
 },
+};
+
+static struct snd_soc_dai_driver hdac_hda_hdmi_dais[] = {
 {
 	.id = HDAC_HDMI_0_DAI_ID,
 	.name = "intel-hdmi-hifi1",
@@ -607,8 +610,16 @@ static const struct snd_soc_component_driver hdac_hda_codec = {
 	.endianness		= 1,
 };
 
+static const struct snd_soc_component_driver hdac_hda_hdmi_codec = {
+	.probe			= hdac_hda_codec_probe,
+	.remove			= hdac_hda_codec_remove,
+	.idle_bias_on		= false,
+	.endianness		= 1,
+};
+
 static int hdac_hda_dev_probe(struct hdac_device *hdev)
 {
+	struct hdac_hda_priv *hda_pvt = dev_get_drvdata(&hdev->dev);
 	struct hdac_ext_link *hlink;
 	int ret;
 
@@ -621,9 +632,15 @@ static int hdac_hda_dev_probe(struct hdac_device *hdev)
 	snd_hdac_ext_bus_link_get(hdev->bus, hlink);
 
 	/* ASoC specific initialization */
-	ret = devm_snd_soc_register_component(&hdev->dev,
-					 &hdac_hda_codec, hdac_hda_dais,
-					 ARRAY_SIZE(hdac_hda_dais));
+	if (hda_pvt->need_display_power)
+		ret = devm_snd_soc_register_component(&hdev->dev,
+						&hdac_hda_hdmi_codec, hdac_hda_hdmi_dais,
+						ARRAY_SIZE(hdac_hda_hdmi_dais));
+	else
+		ret = devm_snd_soc_register_component(&hdev->dev,
+						&hdac_hda_codec, hdac_hda_dais,
+						ARRAY_SIZE(hdac_hda_dais));
+
 	if (ret < 0) {
 		dev_err(&hdev->dev, "failed to register HDA codec %d\n", ret);
 		return ret;
diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c
index 20da1eaa4f1c..0938671700c6 100644
--- a/sound/soc/codecs/hdmi-codec.c
+++ b/sound/soc/codecs/hdmi-codec.c
@@ -850,8 +850,9 @@ static int hdmi_dai_probe(struct snd_soc_dai *dai)
 static void hdmi_codec_jack_report(struct hdmi_codec_priv *hcp,
 				   unsigned int jack_status)
 {
-	if (hcp->jack && jack_status != hcp->jack_status) {
-		snd_soc_jack_report(hcp->jack, jack_status, SND_JACK_LINEOUT);
+	if (jack_status != hcp->jack_status) {
+		if (hcp->jack)
+			snd_soc_jack_report(hcp->jack, jack_status, SND_JACK_LINEOUT);
 		hcp->jack_status = jack_status;
 	}
 }
@@ -880,6 +881,13 @@ static int hdmi_codec_set_jack(struct snd_soc_component *component,
 
 	if (hcp->hcd.ops->hook_plugged_cb) {
 		hcp->jack = jack;
+
+		/*
+		 * Report the initial jack status which may have been provided
+		 * by the parent hdmi driver while the hpd hook was registered.
+		 */
+		snd_soc_jack_report(jack, hcp->jack_status, SND_JACK_LINEOUT);
+
 		return 0;
 	}
 
diff --git a/sound/soc/codecs/lpass-tx-macro.c b/sound/soc/codecs/lpass-tx-macro.c
index 82f9873ffada..124c2e144f33 100644
--- a/sound/soc/codecs/lpass-tx-macro.c
+++ b/sound/soc/codecs/lpass-tx-macro.c
@@ -2021,6 +2021,11 @@ static int tx_macro_probe(struct platform_device *pdev)
 
 	tx->dev = dev;
 
+	/* Set active_decimator default value */
+	tx->active_decimator[TX_MACRO_AIF1_CAP] = -1;
+	tx->active_decimator[TX_MACRO_AIF2_CAP] = -1;
+	tx->active_decimator[TX_MACRO_AIF3_CAP] = -1;
+
 	/* set MCLK and NPL rates */
 	clk_set_rate(tx->mclk, MCLK_FREQ);
 	clk_set_rate(tx->npl, MCLK_FREQ);
diff --git a/sound/soc/codecs/nau8822.c b/sound/soc/codecs/nau8822.c
index ff3024899f45..7199d734c79f 100644
--- a/sound/soc/codecs/nau8822.c
+++ b/sound/soc/codecs/nau8822.c
@@ -184,6 +184,7 @@ static int nau8822_eq_get(struct snd_kcontrol *kcontrol,
 	struct soc_bytes_ext *params = (void *)kcontrol->private_value;
 	int i, reg;
 	u16 reg_val, *val;
+	__be16 tmp;
 
 	val = (u16 *)ucontrol->value.bytes.data;
 	reg = NAU8822_REG_EQ1;
@@ -192,8 +193,8 @@ static int nau8822_eq_get(struct snd_kcontrol *kcontrol,
 		/* conversion of 16-bit integers between native CPU format
 		 * and big endian format
 		 */
-		reg_val = cpu_to_be16(reg_val);
-		memcpy(val + i, &reg_val, sizeof(reg_val));
+		tmp = cpu_to_be16(reg_val);
+		memcpy(val + i, &tmp, sizeof(tmp));
 	}
 
 	return 0;
@@ -216,6 +217,7 @@ static int nau8822_eq_put(struct snd_kcontrol *kcontrol,
 	void *data;
 	u16 *val, value;
 	int i, reg, ret;
+	__be16 *tmp;
 
 	data = kmemdup(ucontrol->value.bytes.data,
 		params->max, GFP_KERNEL | GFP_DMA);
@@ -228,7 +230,8 @@ static int nau8822_eq_put(struct snd_kcontrol *kcontrol,
 		/* conversion of 16-bit integers between native CPU format
 		 * and big endian format
 		 */
-		value = be16_to_cpu(*(val + i));
+		tmp = (__be16 *)(val + i);
+		value = be16_to_cpup(tmp);
 		ret = snd_soc_component_write(component, reg + i, value);
 		if (ret) {
 			dev_err(component->dev,
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index 7938b52d741d..a0d01d71d8b5 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -448,6 +448,7 @@ struct rt5645_priv {
 	struct regulator_bulk_data supplies[ARRAY_SIZE(rt5645_supply_names)];
 	struct rt5645_eq_param_s *eq_param;
 	struct timer_list btn_check_timer;
+	struct mutex jd_mutex;
 
 	int codec_type;
 	int sysclk;
@@ -3193,6 +3194,8 @@ static int rt5645_jack_detect(struct snd_soc_component *component, int jack_inse
 				rt5645_enable_push_button_irq(component, true);
 			}
 		} else {
+			if (rt5645->en_button_func)
+				rt5645_enable_push_button_irq(component, false);
 			snd_soc_dapm_disable_pin(dapm, "Mic Det Power");
 			snd_soc_dapm_sync(dapm);
 			rt5645->jack_type = SND_JACK_HEADPHONE;
@@ -3295,6 +3298,8 @@ static void rt5645_jack_detect_work(struct work_struct *work)
 	if (!rt5645->component)
 		return;
 
+	mutex_lock(&rt5645->jd_mutex);
+
 	switch (rt5645->pdata.jd_mode) {
 	case 0: /* Not using rt5645 JD */
 		if (rt5645->gpiod_hp_det) {
@@ -3321,7 +3326,7 @@ static void rt5645_jack_detect_work(struct work_struct *work)
 
 	if (!val && (rt5645->jack_type == 0)) { /* jack in */
 		report = rt5645_jack_detect(rt5645->component, 1);
-	} else if (!val && rt5645->jack_type != 0) {
+	} else if (!val && rt5645->jack_type == SND_JACK_HEADSET) {
 		/* for push button and jack out */
 		btn_type = 0;
 		if (snd_soc_component_read(rt5645->component, RT5645_INT_IRQ_ST) & 0x4) {
@@ -3377,6 +3382,8 @@ static void rt5645_jack_detect_work(struct work_struct *work)
 		rt5645_jack_detect(rt5645->component, 0);
 	}
 
+	mutex_unlock(&rt5645->jd_mutex);
+
 	snd_soc_jack_report(rt5645->hp_jack, report, SND_JACK_HEADPHONE);
 	snd_soc_jack_report(rt5645->mic_jack, report, SND_JACK_MICROPHONE);
 	if (rt5645->en_button_func)
@@ -4150,6 +4157,7 @@ static int rt5645_i2c_probe(struct i2c_client *i2c)
 	}
 	timer_setup(&rt5645->btn_check_timer, rt5645_btn_check_callback, 0);
 
+	mutex_init(&rt5645->jd_mutex);
 	INIT_DELAYED_WORK(&rt5645->jack_detect_work, rt5645_jack_detect_work);
 	INIT_DELAYED_WORK(&rt5645->rcclock_work, rt5645_rcclock_work);
 
diff --git a/sound/soc/codecs/tas2781-comlib.c b/sound/soc/codecs/tas2781-comlib.c
index ffb26e4a7e2f..00e35169ae49 100644
--- a/sound/soc/codecs/tas2781-comlib.c
+++ b/sound/soc/codecs/tas2781-comlib.c
@@ -39,7 +39,7 @@ static const struct regmap_range_cfg tasdevice_ranges[] = {
 static const struct regmap_config tasdevice_regmap = {
 	.reg_bits = 8,
 	.val_bits = 8,
-	.cache_type = REGCACHE_RBTREE,
+	.cache_type = REGCACHE_NONE,
 	.ranges = tasdevice_ranges,
 	.num_ranges = ARRAY_SIZE(tasdevice_ranges),
 	.max_register = 256 * 128,
@@ -316,8 +316,6 @@ int tasdevice_init(struct tasdevice_priv *tas_priv)
 		tas_priv->tasdevice[i].cur_conf = -1;
 	}
 
-	dev_set_drvdata(tas_priv->dev, tas_priv);
-
 	mutex_init(&tas_priv->codec_lock);
 
 out:
diff --git a/sound/soc/codecs/tas2781-fmwlib.c b/sound/soc/codecs/tas2781-fmwlib.c
index 4efe95b60aaa..5c09e441a936 100644
--- a/sound/soc/codecs/tas2781-fmwlib.c
+++ b/sound/soc/codecs/tas2781-fmwlib.c
@@ -2189,11 +2189,11 @@ int tasdevice_select_tuningprm_cfg(void *context, int prm_no,
 		goto out;
 	}
 
-	conf = &(tas_fmw->configs[cfg_no]);
 	for (i = 0, prog_status = 0; i < tas_priv->ndev; i++) {
 		if (cfg_info[rca_conf_no]->active_dev & (1 << i)) {
-			if (tas_priv->tasdevice[i].cur_prog != prm_no
-				|| tas_priv->force_fwload_status) {
+			if (prm_no >= 0
+				&& (tas_priv->tasdevice[i].cur_prog != prm_no
+				|| tas_priv->force_fwload_status)) {
 				tas_priv->tasdevice[i].cur_conf = -1;
 				tas_priv->tasdevice[i].is_loading = true;
 				prog_status++;
@@ -2228,7 +2228,8 @@ int tasdevice_select_tuningprm_cfg(void *context, int prm_no,
 	}
 
 	for (i = 0, status = 0; i < tas_priv->ndev; i++) {
-		if (tas_priv->tasdevice[i].cur_conf != cfg_no
+		if (cfg_no >= 0
+			&& tas_priv->tasdevice[i].cur_conf != cfg_no
 			&& (cfg_info[rca_conf_no]->active_dev & (1 << i))
 			&& (tas_priv->tasdevice[i].is_loaderr == false)) {
 			status++;
@@ -2238,6 +2239,7 @@ int tasdevice_select_tuningprm_cfg(void *context, int prm_no,
 	}
 
 	if (status) {
+		conf = &(tas_fmw->configs[cfg_no]);
 		status = 0;
 		tasdevice_load_data(tas_priv, &(conf->dev_data));
 		for (i = 0; i < tas_priv->ndev; i++) {
@@ -2281,7 +2283,7 @@ int tasdevice_prmg_load(void *context, int prm_no)
 	}
 
 	for (i = 0, prog_status = 0; i < tas_priv->ndev; i++) {
-		if (tas_priv->tasdevice[i].cur_prog != prm_no) {
+		if (prm_no >= 0 && tas_priv->tasdevice[i].cur_prog != prm_no) {
 			tas_priv->tasdevice[i].cur_conf = -1;
 			tas_priv->tasdevice[i].is_loading = true;
 			prog_status++;
@@ -2326,7 +2328,7 @@ int tasdevice_prmg_calibdata_load(void *context, int prm_no)
 	}
 
 	for (i = 0, prog_status = 0; i < tas_priv->ndev; i++) {
-		if (tas_priv->tasdevice[i].cur_prog != prm_no) {
+		if (prm_no >= 0 && tas_priv->tasdevice[i].cur_prog != prm_no) {
 			tas_priv->tasdevice[i].cur_conf = -1;
 			tas_priv->tasdevice[i].is_loading = true;
 			prog_status++;
diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c
index 55cd5e3c23a5..917b1c15f71d 100644
--- a/sound/soc/codecs/tas2781-i2c.c
+++ b/sound/soc/codecs/tas2781-i2c.c
@@ -689,6 +689,8 @@ static int tasdevice_i2c_probe(struct i2c_client *i2c)
 	if (!tas_priv)
 		return -ENOMEM;
 
+	dev_set_drvdata(&i2c->dev, tas_priv);
+
 	if (ACPI_HANDLE(&i2c->dev)) {
 		acpi_id = acpi_match_device(i2c->dev.driver->acpi_match_table,
 				&i2c->dev);
diff --git a/sound/soc/codecs/wm8974.c b/sound/soc/codecs/wm8974.c
index 044b6f604c09..260bac695b20 100644
--- a/sound/soc/codecs/wm8974.c
+++ b/sound/soc/codecs/wm8974.c
@@ -186,7 +186,7 @@ SOC_DAPM_SINGLE("PCM Playback Switch", WM8974_MONOMIX, 0, 1, 0),
 
 /* Boost mixer */
 static const struct snd_kcontrol_new wm8974_boost_mixer[] = {
-SOC_DAPM_SINGLE("Aux Switch", WM8974_INPPGA, 6, 1, 1),
+SOC_DAPM_SINGLE("PGA Switch", WM8974_INPPGA, 6, 1, 1),
 };
 
 /* Input PGA */
@@ -246,8 +246,8 @@ static const struct snd_soc_dapm_route wm8974_dapm_routes[] = {
 
 	/* Boost Mixer */
 	{"ADC", NULL, "Boost Mixer"},
-	{"Boost Mixer", "Aux Switch", "Aux Input"},
-	{"Boost Mixer", NULL, "Input PGA"},
+	{"Boost Mixer", NULL, "Aux Input"},
+	{"Boost Mixer", "PGA Switch", "Input PGA"},
 	{"Boost Mixer", NULL, "MICP"},
 
 	/* Input PGA */
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 236b12b69ae5..c01e31175015 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -1451,12 +1451,12 @@ static int wm_adsp_buffer_populate(struct wm_adsp_compr_buf *buf)
 		ret = wm_adsp_buffer_read(buf, caps->region_defs[i].base_offset,
 					  &region->base_addr);
 		if (ret < 0)
-			return ret;
+			goto err;
 
 		ret = wm_adsp_buffer_read(buf, caps->region_defs[i].size_offset,
 					  &offset);
 		if (ret < 0)
-			return ret;
+			goto err;
 
 		region->cumulative_size = offset;
 
@@ -1467,6 +1467,10 @@ static int wm_adsp_buffer_populate(struct wm_adsp_compr_buf *buf)
 	}
 
 	return 0;
+
+err:
+	kfree(buf->regions);
+	return ret;
 }
 
 static void wm_adsp_buffer_clear(struct wm_adsp_compr_buf *buf)
diff --git a/sound/soc/fsl/Kconfig b/sound/soc/fsl/Kconfig
index 725c530a3636..be342ee03fb9 100644
--- a/sound/soc/fsl/Kconfig
+++ b/sound/soc/fsl/Kconfig
@@ -360,6 +360,7 @@ config SND_SOC_IMX_HDMI
 config SND_SOC_IMX_RPMSG
 	tristate "SoC Audio support for i.MX boards with rpmsg"
 	depends on RPMSG
+	depends on OF && I2C
 	select SND_SOC_IMX_PCM_RPMSG
 	select SND_SOC_IMX_AUDIO_RPMSG
 	help
diff --git a/sound/soc/fsl/fsl_qmc_audio.c b/sound/soc/fsl/fsl_qmc_audio.c
index 56d6b0b039a2..bfaaa451735b 100644
--- a/sound/soc/fsl/fsl_qmc_audio.c
+++ b/sound/soc/fsl/fsl_qmc_audio.c
@@ -99,7 +99,7 @@ static void qmc_audio_pcm_write_complete(void *context)
 	snd_pcm_period_elapsed(prtd->substream);
 }
 
-static void qmc_audio_pcm_read_complete(void *context, size_t length)
+static void qmc_audio_pcm_read_complete(void *context, size_t length, unsigned int flags)
 {
 	struct qmc_dai_prtd *prtd = context;
 	int ret;
diff --git a/sound/soc/fsl/fsl_rpmsg.c b/sound/soc/fsl/fsl_rpmsg.c
index 5c5c04ce9db7..00852f174a69 100644
--- a/sound/soc/fsl/fsl_rpmsg.c
+++ b/sound/soc/fsl/fsl_rpmsg.c
@@ -238,7 +238,7 @@ static int fsl_rpmsg_probe(struct platform_device *pdev)
 	ret = devm_snd_soc_register_component(&pdev->dev, &fsl_component,
 					      &fsl_rpmsg_dai, 1);
 	if (ret)
-		return ret;
+		goto err_pm_disable;
 
 	rpmsg->card_pdev = platform_device_register_data(&pdev->dev,
 							 "imx-audio-rpmsg",
@@ -248,16 +248,22 @@ static int fsl_rpmsg_probe(struct platform_device *pdev)
 	if (IS_ERR(rpmsg->card_pdev)) {
 		dev_err(&pdev->dev, "failed to register rpmsg card\n");
 		ret = PTR_ERR(rpmsg->card_pdev);
-		return ret;
+		goto err_pm_disable;
 	}
 
 	return 0;
+
+err_pm_disable:
+	pm_runtime_disable(&pdev->dev);
+	return ret;
 }
 
 static void fsl_rpmsg_remove(struct platform_device *pdev)
 {
 	struct fsl_rpmsg *rpmsg = platform_get_drvdata(pdev);
 
+	pm_runtime_disable(&pdev->dev);
+
 	if (rpmsg->card_pdev)
 		platform_device_unregister(rpmsg->card_pdev);
 }
diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c
index 79e7c6b98a75..546bd4e333b5 100644
--- a/sound/soc/fsl/fsl_sai.c
+++ b/sound/soc/fsl/fsl_sai.c
@@ -673,6 +673,20 @@ static int fsl_sai_hw_params(struct snd_pcm_substream *substream,
 			   FSL_SAI_CR3_TRCE_MASK,
 			   FSL_SAI_CR3_TRCE((dl_cfg[dl_cfg_idx].mask[tx] & trce_mask)));
 
+	/*
+	 * When the TERE and FSD_MSTR enabled before configuring the word width
+	 * There will be no frame sync clock issue, because word width impact
+	 * the generation of frame sync clock.
+	 *
+	 * TERE enabled earlier only for i.MX8MP case for the hardware limitation,
+	 * We need to disable FSD_MSTR before configuring word width, then enable
+	 * FSD_MSTR bit for this specific case.
+	 */
+	if (sai->soc_data->mclk_with_tere && sai->mclk_direction_output &&
+	    !sai->is_consumer_mode)
+		regmap_update_bits(sai->regmap, FSL_SAI_xCR4(tx, ofs),
+				   FSL_SAI_CR4_FSD_MSTR, 0);
+
 	regmap_update_bits(sai->regmap, FSL_SAI_xCR4(tx, ofs),
 			   FSL_SAI_CR4_SYWD_MASK | FSL_SAI_CR4_FRSZ_MASK |
 			   FSL_SAI_CR4_CHMOD_MASK,
@@ -680,6 +694,13 @@ static int fsl_sai_hw_params(struct snd_pcm_substream *substream,
 	regmap_update_bits(sai->regmap, FSL_SAI_xCR5(tx, ofs),
 			   FSL_SAI_CR5_WNW_MASK | FSL_SAI_CR5_W0W_MASK |
 			   FSL_SAI_CR5_FBT_MASK, val_cr5);
+
+	/* Enable FSD_MSTR after configuring word width */
+	if (sai->soc_data->mclk_with_tere && sai->mclk_direction_output &&
+	    !sai->is_consumer_mode)
+		regmap_update_bits(sai->regmap, FSL_SAI_xCR4(tx, ofs),
+				   FSL_SAI_CR4_FSD_MSTR, FSL_SAI_CR4_FSD_MSTR);
+
 	regmap_write(sai->regmap, FSL_SAI_xMR(tx),
 		     ~0UL - ((1 << min(channels, slots)) - 1));
 
@@ -693,6 +714,9 @@ static int fsl_sai_hw_free(struct snd_pcm_substream *substream,
 	bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK;
 	unsigned int ofs = sai->soc_data->reg_offset;
 
+	/* Clear xMR to avoid channel swap with mclk_with_tere enabled case */
+	regmap_write(sai->regmap, FSL_SAI_xMR(tx), 0);
+
 	regmap_update_bits(sai->regmap, FSL_SAI_xCR3(tx, ofs),
 			   FSL_SAI_CR3_TRCE_MASK, 0);
 
diff --git a/sound/soc/fsl/fsl_xcvr.c b/sound/soc/fsl/fsl_xcvr.c
index fa0a15263c66..f0fb33d719c2 100644
--- a/sound/soc/fsl/fsl_xcvr.c
+++ b/sound/soc/fsl/fsl_xcvr.c
@@ -358,7 +358,7 @@ static int fsl_xcvr_en_aud_pll(struct fsl_xcvr *xcvr, u32 freq)
 	struct device *dev = &xcvr->pdev->dev;
 	int ret;
 
-	freq = xcvr->soc_data->spdif_only ? freq / 10 : freq;
+	freq = xcvr->soc_data->spdif_only ? freq / 5 : freq;
 	clk_disable_unprepare(xcvr->phy_clk);
 	ret = clk_set_rate(xcvr->phy_clk, freq);
 	if (ret < 0) {
@@ -409,11 +409,21 @@ static int fsl_xcvr_prepare(struct snd_pcm_substream *substream,
 	bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK;
 	u32 m_ctl = 0, v_ctl = 0;
 	u32 r = substream->runtime->rate, ch = substream->runtime->channels;
-	u32 fout = 32 * r * ch * 10 * 2;
+	u32 fout = 32 * r * ch * 10;
 	int ret = 0;
 
 	switch (xcvr->mode) {
 	case FSL_XCVR_MODE_SPDIF:
+		if (xcvr->soc_data->spdif_only && tx) {
+			ret = regmap_update_bits(xcvr->regmap, FSL_XCVR_TX_DPTH_CTRL_SET,
+						 FSL_XCVR_TX_DPTH_CTRL_BYPASS_FEM,
+						 FSL_XCVR_TX_DPTH_CTRL_BYPASS_FEM);
+			if (ret < 0) {
+				dev_err(dai->dev, "Failed to set bypass fem: %d\n", ret);
+				return ret;
+			}
+		}
+		fallthrough;
 	case FSL_XCVR_MODE_ARC:
 		if (tx) {
 			ret = fsl_xcvr_en_aud_pll(xcvr, fout);
diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index ed14d9e4aa53..42466b4b1ca4 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -83,6 +83,7 @@ enum {
 #define BYT_RT5640_HSMIC2_ON_IN1	BIT(27)
 #define BYT_RT5640_JD_HP_ELITEP_1000G2	BIT(28)
 #define BYT_RT5640_USE_AMCR0F28		BIT(29)
+#define BYT_RT5640_SWAPPED_SPEAKERS	BIT(30)
 
 #define BYTCR_INPUT_DEFAULTS				\
 	(BYT_RT5640_IN3_MAP |				\
@@ -157,6 +158,8 @@ static void log_quirks(struct device *dev)
 		dev_info(dev, "quirk MONO_SPEAKER enabled\n");
 	if (byt_rt5640_quirk & BYT_RT5640_NO_SPEAKERS)
 		dev_info(dev, "quirk NO_SPEAKERS enabled\n");
+	if (byt_rt5640_quirk & BYT_RT5640_SWAPPED_SPEAKERS)
+		dev_info(dev, "quirk SWAPPED_SPEAKERS enabled\n");
 	if (byt_rt5640_quirk & BYT_RT5640_LINEOUT)
 		dev_info(dev, "quirk LINEOUT enabled\n");
 	if (byt_rt5640_quirk & BYT_RT5640_LINEOUT_AS_HP2)
@@ -894,6 +897,19 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 					BYT_RT5640_SSP0_AIF1 |
 					BYT_RT5640_MCLK_EN),
 	},
+	{
+		/* Medion Lifetab S10346 */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
+			DMI_MATCH(DMI_BOARD_NAME, "Aptio CRB"),
+			/* Above strings are much too generic, also match on BIOS date */
+			DMI_MATCH(DMI_BIOS_DATE, "10/22/2015"),
+		},
+		.driver_data = (void *)(BYTCR_INPUT_DEFAULTS |
+					BYT_RT5640_SWAPPED_SPEAKERS |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
 	{	/* Mele PCG03 Mini PC */
 		.matches = {
 			DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "Mini PC"),
@@ -1619,11 +1635,11 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev)
 	const char *platform_name;
 	struct acpi_device *adev;
 	struct device *codec_dev;
+	const char *cfg_spk;
 	bool sof_parent;
 	int ret_val = 0;
 	int dai_index = 0;
-	int i, cfg_spk;
-	int aif;
+	int i, aif;
 
 	is_bytcr = false;
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
@@ -1783,13 +1799,16 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev)
 	}
 
 	if (byt_rt5640_quirk & BYT_RT5640_NO_SPEAKERS) {
-		cfg_spk = 0;
+		cfg_spk = "0";
 		spk_type = "none";
 	} else if (byt_rt5640_quirk & BYT_RT5640_MONO_SPEAKER) {
-		cfg_spk = 1;
+		cfg_spk = "1";
 		spk_type = "mono";
+	} else if (byt_rt5640_quirk & BYT_RT5640_SWAPPED_SPEAKERS) {
+		cfg_spk = "swapped";
+		spk_type = "swapped";
 	} else {
-		cfg_spk = 2;
+		cfg_spk = "2";
 		spk_type = "stereo";
 	}
 
@@ -1804,7 +1823,7 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev)
 		headset2_string = " cfg-hs2:in1";
 
 	snprintf(byt_rt5640_components, sizeof(byt_rt5640_components),
-		 "cfg-spk:%d cfg-mic:%s aif:%d%s%s", cfg_spk,
+		 "cfg-spk:%s cfg-mic:%s aif:%d%s%s", cfg_spk,
 		 map_name[BYT_RT5640_MAP(byt_rt5640_quirk)], aif,
 		 lineout_string, headset2_string);
 	byt_rt5640_card.components = byt_rt5640_components;
diff --git a/sound/soc/intel/boards/skl_hda_dsp_generic.c b/sound/soc/intel/boards/skl_hda_dsp_generic.c
index 6c6ef63cd5d9..6e172719c979 100644
--- a/sound/soc/intel/boards/skl_hda_dsp_generic.c
+++ b/sound/soc/intel/boards/skl_hda_dsp_generic.c
@@ -154,6 +154,8 @@ static int skl_hda_fill_card_info(struct snd_soc_acpi_mach_params *mach_params)
 		card->dapm_widgets = skl_hda_widgets;
 		card->num_dapm_widgets = ARRAY_SIZE(skl_hda_widgets);
 		if (!ctx->idisp_codec) {
+			card->dapm_routes = &skl_hda_map[IDISP_ROUTE_COUNT];
+			num_route -= IDISP_ROUTE_COUNT;
 			for (i = 0; i < IDISP_DAI_COUNT; i++) {
 				skl_hda_be_dai_links[i].codecs = &snd_soc_dummy_dlc;
 				skl_hda_be_dai_links[i].num_codecs = 1;
diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c
index 3312ad8a563b..4e4284729773 100644
--- a/sound/soc/intel/boards/sof_sdw.c
+++ b/sound/soc/intel/boards/sof_sdw.c
@@ -1546,7 +1546,7 @@ static int sof_card_dai_links_create(struct snd_soc_card *card)
 {
 	struct device *dev = card->dev;
 	struct snd_soc_acpi_mach *mach = dev_get_platdata(card->dev);
-	int sdw_be_num = 0, ssp_num = 0, dmic_num = 0, hdmi_num = 0, bt_num = 0;
+	int sdw_be_num = 0, ssp_num = 0, dmic_num = 0, bt_num = 0;
 	struct mc_private *ctx = snd_soc_card_get_drvdata(card);
 	struct snd_soc_acpi_mach_params *mach_params = &mach->mach_params;
 	const struct snd_soc_acpi_link_adr *adr_link = mach_params->links;
@@ -1564,6 +1564,7 @@ static int sof_card_dai_links_create(struct snd_soc_card *card)
 	char *codec_name, *codec_dai_name;
 	int i, j, be_id = 0;
 	int codec_index;
+	int hdmi_num;
 	int ret;
 
 	ret = get_dailink_info(dev, adr_link, &sdw_be_num, &codec_conf_num);
@@ -1584,14 +1585,13 @@ static int sof_card_dai_links_create(struct snd_soc_card *card)
 		ssp_num = hweight_long(ssp_mask);
 	}
 
-	if (mach_params->codec_mask & IDISP_CODEC_MASK) {
+	if (mach_params->codec_mask & IDISP_CODEC_MASK)
 		ctx->hdmi.idisp_codec = true;
 
-		if (sof_sdw_quirk & SOF_SDW_TGL_HDMI)
-			hdmi_num = SOF_TGL_HDMI_COUNT;
-		else
-			hdmi_num = SOF_PRE_TGL_HDMI_COUNT;
-	}
+	if (sof_sdw_quirk & SOF_SDW_TGL_HDMI)
+		hdmi_num = SOF_TGL_HDMI_COUNT;
+	else
+		hdmi_num = SOF_PRE_TGL_HDMI_COUNT;
 
 	/* enable dmic01 & dmic16k */
 	if (sof_sdw_quirk & SOF_SDW_PCH_DMIC || mach_params->dmic_num)
@@ -1601,7 +1601,8 @@ static int sof_card_dai_links_create(struct snd_soc_card *card)
 		bt_num = 1;
 
 	dev_dbg(dev, "sdw %d, ssp %d, dmic %d, hdmi %d, bt: %d\n",
-		sdw_be_num, ssp_num, dmic_num, hdmi_num, bt_num);
+		sdw_be_num, ssp_num, dmic_num,
+		ctx->hdmi.idisp_codec ? hdmi_num : 0, bt_num);
 
 	/* allocate BE dailinks */
 	num_links = sdw_be_num + ssp_num + dmic_num + hdmi_num + bt_num;
diff --git a/sound/soc/intel/common/soc-acpi-intel-mtl-match.c b/sound/soc/intel/common/soc-acpi-intel-mtl-match.c
index 301b8142d554..9008b6768205 100644
--- a/sound/soc/intel/common/soc-acpi-intel-mtl-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-mtl-match.c
@@ -306,13 +306,13 @@ static const struct snd_soc_acpi_adr_device cs35l56_1_adr[] = {
 		.adr = 0x00013701FA355601ull,
 		.num_endpoints = 1,
 		.endpoints = &spk_r_endpoint,
-		.name_prefix = "cs35l56-8"
+		.name_prefix = "AMP8"
 	},
 	{
 		.adr = 0x00013601FA355601ull,
 		.num_endpoints = 1,
 		.endpoints = &spk_3_endpoint,
-		.name_prefix = "cs35l56-7"
+		.name_prefix = "AMP7"
 	}
 };
 
@@ -321,13 +321,13 @@ static const struct snd_soc_acpi_adr_device cs35l56_2_adr[] = {
 		.adr = 0x00023301FA355601ull,
 		.num_endpoints = 1,
 		.endpoints = &spk_l_endpoint,
-		.name_prefix = "cs35l56-1"
+		.name_prefix = "AMP1"
 	},
 	{
 		.adr = 0x00023201FA355601ull,
 		.num_endpoints = 1,
 		.endpoints = &spk_2_endpoint,
-		.name_prefix = "cs35l56-2"
+		.name_prefix = "AMP2"
 	}
 };
 
diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c
index d0c02e8a6785..174aae6e0398 100644
--- a/sound/soc/intel/skylake/skl-pcm.c
+++ b/sound/soc/intel/skylake/skl-pcm.c
@@ -240,8 +240,10 @@ static int skl_pcm_open(struct snd_pcm_substream *substream,
 	snd_pcm_set_sync(substream);
 
 	mconfig = skl_tplg_fe_get_cpr_module(dai, substream->stream);
-	if (!mconfig)
+	if (!mconfig) {
+		kfree(dma_params);
 		return -EINVAL;
+	}
 
 	skl_tplg_d0i3_get(skl, mconfig->d0i3_caps);
 
@@ -1462,6 +1464,7 @@ int skl_platform_register(struct device *dev)
 		dais = krealloc(skl->dais, sizeof(skl_fe_dai) +
 				sizeof(skl_platform_dai), GFP_KERNEL);
 		if (!dais) {
+			kfree(skl->dais);
 			ret = -ENOMEM;
 			goto err;
 		}
@@ -1474,8 +1477,10 @@ int skl_platform_register(struct device *dev)
 
 	ret = devm_snd_soc_register_component(dev, &skl_component,
 					 skl->dais, num_dais);
-	if (ret)
+	if (ret) {
+		kfree(skl->dais);
 		dev_err(dev, "soc component registration failed %d\n", ret);
+	}
 err:
 	return ret;
 }
diff --git a/sound/soc/intel/skylake/skl-sst-ipc.c b/sound/soc/intel/skylake/skl-sst-ipc.c
index 7a425271b08b..fd9624ad5f72 100644
--- a/sound/soc/intel/skylake/skl-sst-ipc.c
+++ b/sound/soc/intel/skylake/skl-sst-ipc.c
@@ -1003,8 +1003,10 @@ int skl_ipc_get_large_config(struct sst_generic_ipc *ipc,
 
 	reply.size = (reply.header >> 32) & IPC_DATA_OFFSET_SZ_MASK;
 	buf = krealloc(reply.data, reply.size, GFP_KERNEL);
-	if (!buf)
+	if (!buf) {
+		kfree(reply.data);
 		return -ENOMEM;
+	}
 	*payload = buf;
 	*bytes = reply.size;
 
diff --git a/sound/soc/mediatek/mt8186/mt8186-dai-adda.c b/sound/soc/mediatek/mt8186/mt8186-dai-adda.c
index 85ae3f76d951..ad6d4b5cf697 100644
--- a/sound/soc/mediatek/mt8186/mt8186-dai-adda.c
+++ b/sound/soc/mediatek/mt8186/mt8186-dai-adda.c
@@ -499,7 +499,7 @@ static const struct snd_soc_dapm_widget mtk_dai_adda_widgets[] = {
 			      SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
 
 	SND_SOC_DAPM_SUPPLY_S("AUD_PAD_TOP", SUPPLY_SEQ_ADDA_AUD_PAD_TOP,
-			      0, 0, 0,
+			      AFE_AUD_PAD_TOP, RG_RX_FIFO_ON_SFT, 0,
 			      mtk_adda_pad_top_event,
 			      SND_SOC_DAPM_PRE_PMU),
 	SND_SOC_DAPM_SUPPLY_S("ADDA_MTKAIF_CFG", SUPPLY_SEQ_ADDA_MTKAIF_CFG,
diff --git a/sound/soc/meson/g12a-toacodec.c b/sound/soc/meson/g12a-toacodec.c
index 6c4503766fdc..531bb8707a3e 100644
--- a/sound/soc/meson/g12a-toacodec.c
+++ b/sound/soc/meson/g12a-toacodec.c
@@ -71,6 +71,9 @@ static int g12a_toacodec_mux_put_enum(struct snd_kcontrol *kcontrol,
 	struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
 	unsigned int mux, reg;
 
+	if (ucontrol->value.enumerated.item[0] >= e->items)
+		return -EINVAL;
+
 	mux = snd_soc_enum_item_to_val(e, ucontrol->value.enumerated.item[0]);
 	regmap_field_read(priv->field_dat_sel, &reg);
 
@@ -101,7 +104,7 @@ static int g12a_toacodec_mux_put_enum(struct snd_kcontrol *kcontrol,
 
 	snd_soc_dapm_mux_update_power(dapm, kcontrol, mux, e, NULL);
 
-	return 0;
+	return 1;
 }
 
 static SOC_ENUM_SINGLE_DECL(g12a_toacodec_mux_enum, TOACODEC_CTRL0,
diff --git a/sound/soc/meson/g12a-tohdmitx.c b/sound/soc/meson/g12a-tohdmitx.c
index f7ef9aa1eed8..b92434125fac 100644
--- a/sound/soc/meson/g12a-tohdmitx.c
+++ b/sound/soc/meson/g12a-tohdmitx.c
@@ -45,6 +45,9 @@ static int g12a_tohdmitx_i2s_mux_put_enum(struct snd_kcontrol *kcontrol,
 	struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
 	unsigned int mux, changed;
 
+	if (ucontrol->value.enumerated.item[0] >= e->items)
+		return -EINVAL;
+
 	mux = snd_soc_enum_item_to_val(e, ucontrol->value.enumerated.item[0]);
 	changed = snd_soc_component_test_bits(component, e->reg,
 					      CTRL0_I2S_DAT_SEL,
@@ -93,6 +96,9 @@ static int g12a_tohdmitx_spdif_mux_put_enum(struct snd_kcontrol *kcontrol,
 	struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
 	unsigned int mux, changed;
 
+	if (ucontrol->value.enumerated.item[0] >= e->items)
+		return -EINVAL;
+
 	mux = snd_soc_enum_item_to_val(e, ucontrol->value.enumerated.item[0]);
 	changed = snd_soc_component_test_bits(component, TOHDMITX_CTRL0,
 					      CTRL0_SPDIF_SEL,
@@ -112,7 +118,7 @@ static int g12a_tohdmitx_spdif_mux_put_enum(struct snd_kcontrol *kcontrol,
 
 	snd_soc_dapm_mux_update_power(dapm, kcontrol, mux, e, NULL);
 
-	return 0;
+	return 1;
 }
 
 static SOC_ENUM_SINGLE_DECL(g12a_tohdmitx_spdif_mux_enum, TOHDMITX_CTRL0,
diff --git a/sound/soc/qcom/sc8280xp.c b/sound/soc/qcom/sc8280xp.c
index d93b18f07be5..39cb0b889aff 100644
--- a/sound/soc/qcom/sc8280xp.c
+++ b/sound/soc/qcom/sc8280xp.c
@@ -27,6 +27,23 @@ struct sc8280xp_snd_data {
 static int sc8280xp_snd_init(struct snd_soc_pcm_runtime *rtd)
 {
 	struct sc8280xp_snd_data *data = snd_soc_card_get_drvdata(rtd->card);
+	struct snd_soc_dai *cpu_dai = snd_soc_rtd_to_cpu(rtd, 0);
+	struct snd_soc_card *card = rtd->card;
+
+	switch (cpu_dai->id) {
+	case WSA_CODEC_DMA_RX_0:
+	case WSA_CODEC_DMA_RX_1:
+		/*
+		 * set limit of 0dB on Digital Volume for Speakers,
+		 * this can prevent damage of speakers to some extent without
+		 * active speaker protection
+		 */
+		snd_soc_limit_volume(card, "WSA_RX0 Digital Volume", 84);
+		snd_soc_limit_volume(card, "WSA_RX1 Digital Volume", 84);
+		break;
+	default:
+		break;
+	}
 
 	return qcom_snd_wcd_jack_setup(rtd, &data->jack, &data->jack_setup);
 }
diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c
index 55b009d3c681..2d25748ca706 100644
--- a/sound/soc/soc-ops.c
+++ b/sound/soc/soc-ops.c
@@ -661,7 +661,7 @@ int snd_soc_limit_volume(struct snd_soc_card *card,
 	kctl = snd_soc_card_get_kcontrol(card, name);
 	if (kctl) {
 		struct soc_mixer_control *mc = (struct soc_mixer_control *)kctl->private_value;
-		if (max <= mc->max) {
+		if (max <= mc->max - mc->min) {
 			mc->platform_max = max;
 			ret = 0;
 		}
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 323e4d7b6adf..f6d1b2e11795 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -704,11 +704,6 @@ static int soc_pcm_clean(struct snd_soc_pcm_runtime *rtd,
 			if (snd_soc_dai_active(dai) == 0 &&
 			    (dai->rate || dai->channels || dai->sample_bits))
 				soc_pcm_set_dai_params(dai, NULL);
-
-			if (snd_soc_dai_stream_active(dai, substream->stream) ==  0) {
-				if (dai->driver->ops && !dai->driver->ops->mute_unmute_on_trigger)
-					snd_soc_dai_digital_mute(dai, 1, substream->stream);
-			}
 		}
 	}
 
@@ -947,8 +942,10 @@ static int soc_pcm_hw_clean(struct snd_soc_pcm_runtime *rtd,
 		if (snd_soc_dai_active(dai) == 1)
 			soc_pcm_set_dai_params(dai, NULL);
 
-		if (snd_soc_dai_stream_active(dai, substream->stream) == 1)
-			snd_soc_dai_digital_mute(dai, 1, substream->stream);
+		if (snd_soc_dai_stream_active(dai, substream->stream) == 1) {
+			if (dai->driver->ops && !dai->driver->ops->mute_unmute_on_trigger)
+				snd_soc_dai_digital_mute(dai, 1, substream->stream);
+		}
 	}
 
 	/* run the stream event */
diff --git a/sound/soc/soc-topology-test.c b/sound/soc/soc-topology-test.c
index 2cd3540cec04..70cbccc42a42 100644
--- a/sound/soc/soc-topology-test.c
+++ b/sound/soc/soc-topology-test.c
@@ -9,6 +9,7 @@
 #include <sound/core.h>
 #include <sound/soc.h>
 #include <sound/soc-topology.h>
+#include <kunit/device.h>
 #include <kunit/test.h>
 
 /* ===== HELPER FUNCTIONS =================================================== */
@@ -21,26 +22,19 @@
  */
 static struct device *test_dev;
 
-static struct device_driver test_drv = {
-	.name = "sound-soc-topology-test-driver",
-};
-
 static int snd_soc_tplg_test_init(struct kunit *test)
 {
-	test_dev = root_device_register("sound-soc-topology-test");
+	test_dev = kunit_device_register(test, "sound-soc-topology-test");
 	test_dev = get_device(test_dev);
 	if (!test_dev)
 		return -ENODEV;
 
-	test_dev->driver = &test_drv;
-
 	return 0;
 }
 
 static void snd_soc_tplg_test_exit(struct kunit *test)
 {
 	put_device(test_dev);
-	root_device_unregister(test_dev);
 }
 
 /*
diff --git a/sound/soc/sof/intel/hda-codec.c b/sound/soc/sof/intel/hda-codec.c
index 28ecbebb4b84..9f84b0d287a5 100644
--- a/sound/soc/sof/intel/hda-codec.c
+++ b/sound/soc/sof/intel/hda-codec.c
@@ -54,8 +54,16 @@ static int request_codec_module(struct hda_codec *codec)
 
 static int hda_codec_load_module(struct hda_codec *codec)
 {
-	int ret = request_codec_module(codec);
+	int ret;
+
+	ret = snd_hdac_device_register(&codec->core);
+	if (ret) {
+		dev_err(&codec->core.dev, "failed to register hdac device\n");
+		put_device(&codec->core.dev);
+		return ret;
+	}
 
+	ret = request_codec_module(codec);
 	if (ret <= 0) {
 		codec->probe_id = HDA_CODEC_ID_GENERIC;
 		ret = request_codec_module(codec);
@@ -116,7 +124,6 @@ EXPORT_SYMBOL_NS_GPL(hda_codec_jack_check, SND_SOC_SOF_HDA_AUDIO_CODEC);
 static struct hda_codec *hda_codec_device_init(struct hdac_bus *bus, int addr, int type)
 {
 	struct hda_codec *codec;
-	int ret;
 
 	codec = snd_hda_codec_device_init(to_hda_bus(bus), addr, "ehdaudio%dD%d", bus->idx, addr);
 	if (IS_ERR(codec)) {
@@ -126,13 +133,6 @@ static struct hda_codec *hda_codec_device_init(struct hdac_bus *bus, int addr, i
 
 	codec->core.type = type;
 
-	ret = snd_hdac_device_register(&codec->core);
-	if (ret) {
-		dev_err(bus->dev, "failed to register hdac device\n");
-		put_device(&codec->core.dev);
-		return ERR_PTR(ret);
-	}
-
 	return codec;
 }
 
diff --git a/sound/soc/sof/ipc3-topology.c b/sound/soc/sof/ipc3-topology.c
index ba4ef290b634..2c7a5e7a364c 100644
--- a/sound/soc/sof/ipc3-topology.c
+++ b/sound/soc/sof/ipc3-topology.c
@@ -493,6 +493,7 @@ static int sof_ipc3_widget_setup_comp_mixer(struct snd_sof_widget *swidget)
 static int sof_ipc3_widget_setup_comp_pipeline(struct snd_sof_widget *swidget)
 {
 	struct snd_soc_component *scomp = swidget->scomp;
+	struct snd_sof_pipeline *spipe = swidget->spipe;
 	struct sof_ipc_pipe_new *pipeline;
 	struct snd_sof_widget *comp_swidget;
 	int ret;
@@ -545,6 +546,7 @@ static int sof_ipc3_widget_setup_comp_pipeline(struct snd_sof_widget *swidget)
 		swidget->dynamic_pipeline_widget);
 
 	swidget->core = pipeline->core;
+	spipe->core_mask |= BIT(pipeline->core);
 
 	return 0;
 
diff --git a/sound/soc/sof/ipc4-control.c b/sound/soc/sof/ipc4-control.c
index 938efaceb81c..b4cdcec33e12 100644
--- a/sound/soc/sof/ipc4-control.c
+++ b/sound/soc/sof/ipc4-control.c
@@ -89,7 +89,7 @@ sof_ipc4_set_volume_data(struct snd_sof_dev *sdev, struct snd_sof_widget *swidge
 	struct sof_ipc4_control_data *cdata = scontrol->ipc_control_data;
 	struct sof_ipc4_gain *gain = swidget->private;
 	struct sof_ipc4_msg *msg = &cdata->msg;
-	struct sof_ipc4_gain_data data;
+	struct sof_ipc4_gain_params params;
 	bool all_channels_equal = true;
 	u32 value;
 	int ret, i;
@@ -109,20 +109,20 @@ sof_ipc4_set_volume_data(struct snd_sof_dev *sdev, struct snd_sof_widget *swidge
 	 */
 	for (i = 0; i < scontrol->num_channels; i++) {
 		if (all_channels_equal) {
-			data.channels = SOF_IPC4_GAIN_ALL_CHANNELS_MASK;
-			data.init_val = cdata->chanv[0].value;
+			params.channels = SOF_IPC4_GAIN_ALL_CHANNELS_MASK;
+			params.init_val = cdata->chanv[0].value;
 		} else {
-			data.channels = cdata->chanv[i].channel;
-			data.init_val = cdata->chanv[i].value;
+			params.channels = cdata->chanv[i].channel;
+			params.init_val = cdata->chanv[i].value;
 		}
 
 		/* set curve type and duration from topology */
-		data.curve_duration_l = gain->data.curve_duration_l;
-		data.curve_duration_h = gain->data.curve_duration_h;
-		data.curve_type = gain->data.curve_type;
+		params.curve_duration_l = gain->data.params.curve_duration_l;
+		params.curve_duration_h = gain->data.params.curve_duration_h;
+		params.curve_type = gain->data.params.curve_type;
 
-		msg->data_ptr = &data;
-		msg->data_size = sizeof(data);
+		msg->data_ptr = &params;
+		msg->data_size = sizeof(params);
 
 		ret = sof_ipc4_set_get_kcontrol_data(scontrol, true, lock);
 		msg->data_ptr = NULL;
diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c
index b24a64377f68..e012b6e166ac 100644
--- a/sound/soc/sof/ipc4-topology.c
+++ b/sound/soc/sof/ipc4-topology.c
@@ -130,18 +130,18 @@ static const struct sof_topology_token comp_ext_tokens[] = {
 
 static const struct sof_topology_token gain_tokens[] = {
 	{SOF_TKN_GAIN_RAMP_TYPE, SND_SOC_TPLG_TUPLE_TYPE_WORD,
-		get_token_u32, offsetof(struct sof_ipc4_gain_data, curve_type)},
+		get_token_u32, offsetof(struct sof_ipc4_gain_params, curve_type)},
 	{SOF_TKN_GAIN_RAMP_DURATION,
 		SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32,
-		offsetof(struct sof_ipc4_gain_data, curve_duration_l)},
+		offsetof(struct sof_ipc4_gain_params, curve_duration_l)},
 	{SOF_TKN_GAIN_VAL, SND_SOC_TPLG_TUPLE_TYPE_WORD,
-		get_token_u32, offsetof(struct sof_ipc4_gain_data, init_val)},
+		get_token_u32, offsetof(struct sof_ipc4_gain_params, init_val)},
 };
 
 /* SRC */
 static const struct sof_topology_token src_tokens[] = {
 	{SOF_TKN_SRC_RATE_OUT, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32,
-		offsetof(struct sof_ipc4_src, sink_rate)},
+		offsetof(struct sof_ipc4_src_data, sink_rate)},
 };
 
 static const struct sof_token_info ipc4_token_list[SOF_TOKEN_COUNT] = {
@@ -656,6 +656,7 @@ static int sof_ipc4_widget_setup_comp_pipeline(struct snd_sof_widget *swidget)
 {
 	struct snd_soc_component *scomp = swidget->scomp;
 	struct sof_ipc4_pipeline *pipeline;
+	struct snd_sof_pipeline *spipe = swidget->spipe;
 	int ret;
 
 	pipeline = kzalloc(sizeof(*pipeline), GFP_KERNEL);
@@ -670,6 +671,7 @@ static int sof_ipc4_widget_setup_comp_pipeline(struct snd_sof_widget *swidget)
 	}
 
 	swidget->core = pipeline->core_id;
+	spipe->core_mask |= BIT(pipeline->core_id);
 
 	if (pipeline->use_chain_dma) {
 		dev_dbg(scomp->dev, "Set up chain DMA for %s\n", swidget->widget->name);
@@ -718,15 +720,15 @@ static int sof_ipc4_widget_setup_comp_pga(struct snd_sof_widget *swidget)
 
 	swidget->private = gain;
 
-	gain->data.channels = SOF_IPC4_GAIN_ALL_CHANNELS_MASK;
-	gain->data.init_val = SOF_IPC4_VOL_ZERO_DB;
+	gain->data.params.channels = SOF_IPC4_GAIN_ALL_CHANNELS_MASK;
+	gain->data.params.init_val = SOF_IPC4_VOL_ZERO_DB;
 
-	ret = sof_ipc4_get_audio_fmt(scomp, swidget, &gain->available_fmt, &gain->base_config);
+	ret = sof_ipc4_get_audio_fmt(scomp, swidget, &gain->available_fmt, &gain->data.base_config);
 	if (ret)
 		goto err;
 
-	ret = sof_update_ipc_object(scomp, &gain->data, SOF_GAIN_TOKENS, swidget->tuples,
-				    swidget->num_tuples, sizeof(gain->data), 1);
+	ret = sof_update_ipc_object(scomp, &gain->data.params, SOF_GAIN_TOKENS,
+				    swidget->tuples, swidget->num_tuples, sizeof(gain->data), 1);
 	if (ret) {
 		dev_err(scomp->dev, "Parsing gain tokens failed\n");
 		goto err;
@@ -734,8 +736,8 @@ static int sof_ipc4_widget_setup_comp_pga(struct snd_sof_widget *swidget)
 
 	dev_dbg(scomp->dev,
 		"pga widget %s: ramp type: %d, ramp duration %d, initial gain value: %#x\n",
-		swidget->widget->name, gain->data.curve_type, gain->data.curve_duration_l,
-		gain->data.init_val);
+		swidget->widget->name, gain->data.params.curve_type,
+		gain->data.params.curve_duration_l, gain->data.params.init_val);
 
 	ret = sof_ipc4_widget_setup_msg(swidget, &gain->msg);
 	if (ret)
@@ -797,6 +799,7 @@ err:
 static int sof_ipc4_widget_setup_comp_src(struct snd_sof_widget *swidget)
 {
 	struct snd_soc_component *scomp = swidget->scomp;
+	struct snd_sof_pipeline *spipe = swidget->spipe;
 	struct sof_ipc4_src *src;
 	int ret;
 
@@ -808,18 +811,21 @@ static int sof_ipc4_widget_setup_comp_src(struct snd_sof_widget *swidget)
 
 	swidget->private = src;
 
-	ret = sof_ipc4_get_audio_fmt(scomp, swidget, &src->available_fmt, &src->base_config);
+	ret = sof_ipc4_get_audio_fmt(scomp, swidget, &src->available_fmt,
+				     &src->data.base_config);
 	if (ret)
 		goto err;
 
-	ret = sof_update_ipc_object(scomp, src, SOF_SRC_TOKENS, swidget->tuples,
+	ret = sof_update_ipc_object(scomp, &src->data, SOF_SRC_TOKENS, swidget->tuples,
 				    swidget->num_tuples, sizeof(*src), 1);
 	if (ret) {
 		dev_err(scomp->dev, "Parsing SRC tokens failed\n");
 		goto err;
 	}
 
-	dev_dbg(scomp->dev, "SRC sink rate %d\n", src->sink_rate);
+	spipe->core_mask |= BIT(swidget->core);
+
+	dev_dbg(scomp->dev, "SRC sink rate %d\n", src->data.sink_rate);
 
 	ret = sof_ipc4_widget_setup_msg(swidget, &src->msg);
 	if (ret)
@@ -864,6 +870,7 @@ static int sof_ipc4_widget_setup_comp_process(struct snd_sof_widget *swidget)
 {
 	struct snd_soc_component *scomp = swidget->scomp;
 	struct sof_ipc4_fw_module *fw_module;
+	struct snd_sof_pipeline *spipe = swidget->spipe;
 	struct sof_ipc4_process *process;
 	void *cfg;
 	int ret;
@@ -920,6 +927,9 @@ static int sof_ipc4_widget_setup_comp_process(struct snd_sof_widget *swidget)
 
 	sof_ipc4_widget_update_kcontrol_module_id(swidget);
 
+	/* set pipeline core mask to keep track of the core the module is scheduled to run on */
+	spipe->core_mask |= BIT(swidget->core);
+
 	return 0;
 free_base_cfg_ext:
 	kfree(process->base_config_ext);
@@ -1816,7 +1826,7 @@ static int sof_ipc4_prepare_gain_module(struct snd_sof_widget *swidget,
 	u32 out_ref_rate, out_ref_channels, out_ref_valid_bits;
 	int ret;
 
-	ret = sof_ipc4_init_input_audio_fmt(sdev, swidget, &gain->base_config,
+	ret = sof_ipc4_init_input_audio_fmt(sdev, swidget, &gain->data.base_config,
 					    pipeline_params, available_fmt);
 	if (ret < 0)
 		return ret;
@@ -1826,7 +1836,7 @@ static int sof_ipc4_prepare_gain_module(struct snd_sof_widget *swidget,
 	out_ref_channels = SOF_IPC4_AUDIO_FORMAT_CFG_CHANNELS_COUNT(in_fmt->fmt_cfg);
 	out_ref_valid_bits = SOF_IPC4_AUDIO_FORMAT_CFG_V_BIT_DEPTH(in_fmt->fmt_cfg);
 
-	ret = sof_ipc4_init_output_audio_fmt(sdev, &gain->base_config, available_fmt,
+	ret = sof_ipc4_init_output_audio_fmt(sdev, &gain->data.base_config, available_fmt,
 					     out_ref_rate, out_ref_channels, out_ref_valid_bits);
 	if (ret < 0) {
 		dev_err(sdev->dev, "Failed to initialize output format for %s",
@@ -1835,7 +1845,7 @@ static int sof_ipc4_prepare_gain_module(struct snd_sof_widget *swidget,
 	}
 
 	/* update pipeline memory usage */
-	sof_ipc4_update_resource_usage(sdev, swidget, &gain->base_config);
+	sof_ipc4_update_resource_usage(sdev, swidget, &gain->data.base_config);
 
 	return 0;
 }
@@ -1891,7 +1901,7 @@ static int sof_ipc4_prepare_src_module(struct snd_sof_widget *swidget,
 	u32 out_ref_rate, out_ref_channels, out_ref_valid_bits;
 	int output_format_index, input_format_index;
 
-	input_format_index = sof_ipc4_init_input_audio_fmt(sdev, swidget, &src->base_config,
+	input_format_index = sof_ipc4_init_input_audio_fmt(sdev, swidget, &src->data.base_config,
 							   pipeline_params, available_fmt);
 	if (input_format_index < 0)
 		return input_format_index;
@@ -1921,7 +1931,7 @@ static int sof_ipc4_prepare_src_module(struct snd_sof_widget *swidget,
 	 */
 	out_ref_rate = params_rate(fe_params);
 
-	output_format_index = sof_ipc4_init_output_audio_fmt(sdev, &src->base_config,
+	output_format_index = sof_ipc4_init_output_audio_fmt(sdev, &src->data.base_config,
 							     available_fmt, out_ref_rate,
 							     out_ref_channels, out_ref_valid_bits);
 	if (output_format_index < 0) {
@@ -1931,10 +1941,10 @@ static int sof_ipc4_prepare_src_module(struct snd_sof_widget *swidget,
 	}
 
 	/* update pipeline memory usage */
-	sof_ipc4_update_resource_usage(sdev, swidget, &src->base_config);
+	sof_ipc4_update_resource_usage(sdev, swidget, &src->data.base_config);
 
 	out_audio_fmt = &available_fmt->output_pin_fmts[output_format_index].audio_fmt;
-	src->sink_rate = out_audio_fmt->sampling_frequency;
+	src->data.sink_rate = out_audio_fmt->sampling_frequency;
 
 	/* update pipeline_params for sink widgets */
 	return sof_ipc4_update_hw_params(sdev, pipeline_params, out_audio_fmt);
@@ -2314,9 +2324,8 @@ static int sof_ipc4_widget_setup(struct snd_sof_dev *sdev, struct snd_sof_widget
 	{
 		struct sof_ipc4_gain *gain = swidget->private;
 
-		ipc_size = sizeof(struct sof_ipc4_base_module_cfg) +
-			   sizeof(struct sof_ipc4_gain_data);
-		ipc_data = gain;
+		ipc_size = sizeof(gain->data);
+		ipc_data = &gain->data;
 
 		msg = &gain->msg;
 		break;
@@ -2335,8 +2344,8 @@ static int sof_ipc4_widget_setup(struct snd_sof_dev *sdev, struct snd_sof_widget
 	{
 		struct sof_ipc4_src *src = swidget->private;
 
-		ipc_size = sizeof(struct sof_ipc4_base_module_cfg) + sizeof(src->sink_rate);
-		ipc_data = src;
+		ipc_size = sizeof(src->data);
+		ipc_data = &src->data;
 
 		msg = &src->msg;
 		break;
diff --git a/sound/soc/sof/ipc4-topology.h b/sound/soc/sof/ipc4-topology.h
index 0a57b8ab3e08..dce174a190dd 100644
--- a/sound/soc/sof/ipc4-topology.h
+++ b/sound/soc/sof/ipc4-topology.h
@@ -361,7 +361,7 @@ struct sof_ipc4_control_msg_payload {
 } __packed;
 
 /**
- * struct sof_ipc4_gain_data - IPC gain blob
+ * struct sof_ipc4_gain_params - IPC gain parameters
  * @channels: Channels
  * @init_val: Initial value
  * @curve_type: Curve type
@@ -369,24 +369,32 @@ struct sof_ipc4_control_msg_payload {
  * @curve_duration_l: Curve duration low part
  * @curve_duration_h: Curve duration high part
  */
-struct sof_ipc4_gain_data {
+struct sof_ipc4_gain_params {
 	uint32_t channels;
 	uint32_t init_val;
 	uint32_t curve_type;
 	uint32_t reserved;
 	uint32_t curve_duration_l;
 	uint32_t curve_duration_h;
-} __aligned(8);
+} __packed __aligned(4);
 
 /**
- * struct sof_ipc4_gain - gain config data
+ * struct sof_ipc4_gain_data - IPC gain init blob
  * @base_config: IPC base config data
+ * @params: Initial parameters for the gain module
+ */
+struct sof_ipc4_gain_data {
+	struct sof_ipc4_base_module_cfg base_config;
+	struct sof_ipc4_gain_params params;
+} __packed __aligned(4);
+
+/**
+ * struct sof_ipc4_gain - gain config data
  * @data: IPC gain blob
  * @available_fmt: Available audio format
  * @msg: message structure for gain
  */
 struct sof_ipc4_gain {
-	struct sof_ipc4_base_module_cfg base_config;
 	struct sof_ipc4_gain_data data;
 	struct sof_ipc4_available_audio_format available_fmt;
 	struct sof_ipc4_msg msg;
@@ -404,16 +412,24 @@ struct sof_ipc4_mixer {
 	struct sof_ipc4_msg msg;
 };
 
-/**
- * struct sof_ipc4_src SRC config data
+/*
+ * struct sof_ipc4_src_data - IPC data for SRC
  * @base_config: IPC base config data
  * @sink_rate: Output rate for sink module
+ */
+struct sof_ipc4_src_data {
+	struct sof_ipc4_base_module_cfg base_config;
+	uint32_t sink_rate;
+} __packed __aligned(4);
+
+/**
+ * struct sof_ipc4_src - SRC config data
+ * @data: IPC base config data
  * @available_fmt: Available audio format
  * @msg: IPC4 message struct containing header and data info
  */
 struct sof_ipc4_src {
-	struct sof_ipc4_base_module_cfg base_config;
-	uint32_t sink_rate;
+	struct sof_ipc4_src_data data;
 	struct sof_ipc4_available_audio_format available_fmt;
 	struct sof_ipc4_msg msg;
 };
diff --git a/sound/soc/sof/sof-audio.c b/sound/soc/sof/sof-audio.c
index 563fe6f7789f..77cc64ac7113 100644
--- a/sound/soc/sof/sof-audio.c
+++ b/sound/soc/sof/sof-audio.c
@@ -46,6 +46,7 @@ static int sof_widget_free_unlocked(struct snd_sof_dev *sdev,
 				    struct snd_sof_widget *swidget)
 {
 	const struct sof_ipc_tplg_ops *tplg_ops = sof_ipc_get_ops(sdev, tplg);
+	struct snd_sof_pipeline *spipe = swidget->spipe;
 	struct snd_sof_widget *pipe_widget;
 	int err = 0;
 	int ret;
@@ -87,15 +88,22 @@ static int sof_widget_free_unlocked(struct snd_sof_dev *sdev,
 	}
 
 	/*
-	 * disable widget core. continue to route setup status and complete flag
-	 * even if this fails and return the appropriate error
+	 * decrement ref count for cores associated with all modules in the pipeline and clear
+	 * the complete flag
 	 */
-	ret = snd_sof_dsp_core_put(sdev, swidget->core);
-	if (ret < 0) {
-		dev_err(sdev->dev, "error: failed to disable target core: %d for widget %s\n",
-			swidget->core, swidget->widget->name);
-		if (!err)
-			err = ret;
+	if (swidget->id == snd_soc_dapm_scheduler) {
+		int i;
+
+		for_each_set_bit(i, &spipe->core_mask, sdev->num_cores) {
+			ret = snd_sof_dsp_core_put(sdev, i);
+			if (ret < 0) {
+				dev_err(sdev->dev, "failed to disable target core: %d for pipeline %s\n",
+					i, swidget->widget->name);
+				if (!err)
+					err = ret;
+			}
+		}
+		swidget->spipe->complete = 0;
 	}
 
 	/*
@@ -108,10 +116,6 @@ static int sof_widget_free_unlocked(struct snd_sof_dev *sdev,
 			err = ret;
 	}
 
-	/* clear pipeline complete */
-	if (swidget->id == snd_soc_dapm_scheduler)
-		swidget->spipe->complete = 0;
-
 	if (!err)
 		dev_dbg(sdev->dev, "widget %s freed\n", swidget->widget->name);
 
@@ -134,8 +138,10 @@ static int sof_widget_setup_unlocked(struct snd_sof_dev *sdev,
 				     struct snd_sof_widget *swidget)
 {
 	const struct sof_ipc_tplg_ops *tplg_ops = sof_ipc_get_ops(sdev, tplg);
+	struct snd_sof_pipeline *spipe = swidget->spipe;
 	bool use_count_decremented = false;
 	int ret;
+	int i;
 
 	/* skip if there is no private data */
 	if (!swidget->private)
@@ -166,19 +172,23 @@ static int sof_widget_setup_unlocked(struct snd_sof_dev *sdev,
 			goto use_count_dec;
 	}
 
-	/* enable widget core */
-	ret = snd_sof_dsp_core_get(sdev, swidget->core);
-	if (ret < 0) {
-		dev_err(sdev->dev, "error: failed to enable target core for widget %s\n",
-			swidget->widget->name);
-		goto pipe_widget_free;
+	/* update ref count for cores associated with all modules in the pipeline */
+	if (swidget->id == snd_soc_dapm_scheduler) {
+		for_each_set_bit(i, &spipe->core_mask, sdev->num_cores) {
+			ret = snd_sof_dsp_core_get(sdev, i);
+			if (ret < 0) {
+				dev_err(sdev->dev, "failed to enable target core %d for pipeline %s\n",
+					i, swidget->widget->name);
+				goto pipe_widget_free;
+			}
+		}
 	}
 
 	/* setup widget in the DSP */
 	if (tplg_ops && tplg_ops->widget_setup) {
 		ret = tplg_ops->widget_setup(sdev, swidget);
 		if (ret < 0)
-			goto core_put;
+			goto pipe_widget_free;
 	}
 
 	/* send config for DAI components */
@@ -208,15 +218,22 @@ static int sof_widget_setup_unlocked(struct snd_sof_dev *sdev,
 	return 0;
 
 widget_free:
-	/* widget use_count and core ref_count will both be decremented by sof_widget_free() */
+	/* widget use_count will be decremented by sof_widget_free() */
 	sof_widget_free_unlocked(sdev, swidget);
 	use_count_decremented = true;
-core_put:
-	if (!use_count_decremented)
-		snd_sof_dsp_core_put(sdev, swidget->core);
 pipe_widget_free:
-	if (swidget->id != snd_soc_dapm_scheduler)
+	if (swidget->id != snd_soc_dapm_scheduler) {
 		sof_widget_free_unlocked(sdev, swidget->spipe->pipe_widget);
+	} else {
+		int j;
+
+		/* decrement ref count for all cores that were updated previously */
+		for_each_set_bit(j, &spipe->core_mask, sdev->num_cores) {
+			if (j >= i)
+				break;
+			snd_sof_dsp_core_put(sdev, j);
+		}
+	}
 use_count_dec:
 	if (!use_count_decremented)
 		swidget->use_count--;
diff --git a/sound/soc/sof/sof-audio.h b/sound/soc/sof/sof-audio.h
index 5d5eeb1a1a6f..a6d6bcd00cee 100644
--- a/sound/soc/sof/sof-audio.h
+++ b/sound/soc/sof/sof-audio.h
@@ -480,6 +480,7 @@ struct snd_sof_widget {
  * @paused_count: Count of number of PCM's that have started and have currently paused this
 		  pipeline
  * @complete: flag used to indicate that pipeline set up is complete.
+ * @core_mask: Mask containing target cores for all modules in the pipeline
  * @list: List item in sdev pipeline_list
  */
 struct snd_sof_pipeline {
@@ -487,6 +488,7 @@ struct snd_sof_pipeline {
 	int started_count;
 	int paused_count;
 	int complete;
+	unsigned long core_mask;
 	struct list_head list;
 };
 
diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c
index a3a3af252259..37ec671a2d76 100644
--- a/sound/soc/sof/topology.c
+++ b/sound/soc/sof/topology.c
@@ -1736,8 +1736,10 @@ static int sof_dai_load(struct snd_soc_component *scomp, int index,
 	/* perform pcm set op */
 	if (ipc_pcm_ops && ipc_pcm_ops->pcm_setup) {
 		ret = ipc_pcm_ops->pcm_setup(sdev, spcm);
-		if (ret < 0)
+		if (ret < 0) {
+			kfree(spcm);
 			return ret;
+		}
 	}
 
 	dai_drv->dobj.private = spcm;
diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c
index 898bc3baca7b..c8d48566e175 100644
--- a/sound/usb/mixer_quirks.c
+++ b/sound/usb/mixer_quirks.c
@@ -2978,6 +2978,7 @@ static int snd_bbfpro_controls_create(struct usb_mixer_interface *mixer)
 #define SND_DJM_850_IDX		0x2
 #define SND_DJM_900NXS2_IDX	0x3
 #define SND_DJM_750MK2_IDX	0x4
+#define SND_DJM_450_IDX		0x5
 
 
 #define SND_DJM_CTL(_name, suffix, _default_value, _windex) { \
@@ -3108,6 +3109,31 @@ static const struct snd_djm_ctl snd_djm_ctls_250mk2[] = {
 };
 
 
+// DJM-450
+static const u16 snd_djm_opts_450_cap1[] = {
+	0x0103, 0x0100, 0x0106, 0x0107, 0x0108, 0x0109, 0x010d, 0x010a };
+
+static const u16 snd_djm_opts_450_cap2[] = {
+	0x0203, 0x0200, 0x0206, 0x0207, 0x0208, 0x0209, 0x020d, 0x020a };
+
+static const u16 snd_djm_opts_450_cap3[] = {
+	0x030a, 0x0311, 0x0312, 0x0307, 0x0308, 0x0309, 0x030d };
+
+static const u16 snd_djm_opts_450_pb1[] = { 0x0100, 0x0101, 0x0104 };
+static const u16 snd_djm_opts_450_pb2[] = { 0x0200, 0x0201, 0x0204 };
+static const u16 snd_djm_opts_450_pb3[] = { 0x0300, 0x0301, 0x0304 };
+
+static const struct snd_djm_ctl snd_djm_ctls_450[] = {
+	SND_DJM_CTL("Capture Level", cap_level, 0, SND_DJM_WINDEX_CAPLVL),
+	SND_DJM_CTL("Ch1 Input",   450_cap1, 2, SND_DJM_WINDEX_CAP),
+	SND_DJM_CTL("Ch2 Input",   450_cap2, 2, SND_DJM_WINDEX_CAP),
+	SND_DJM_CTL("Ch3 Input",   450_cap3, 0, SND_DJM_WINDEX_CAP),
+	SND_DJM_CTL("Ch1 Output",   450_pb1, 0, SND_DJM_WINDEX_PB),
+	SND_DJM_CTL("Ch2 Output",   450_pb2, 1, SND_DJM_WINDEX_PB),
+	SND_DJM_CTL("Ch3 Output",   450_pb3, 2, SND_DJM_WINDEX_PB)
+};
+
+
 // DJM-750
 static const u16 snd_djm_opts_750_cap1[] = {
 	0x0101, 0x0103, 0x0106, 0x0107, 0x0108, 0x0109, 0x010a, 0x010f };
@@ -3203,6 +3229,7 @@ static const struct snd_djm_device snd_djm_devices[] = {
 	[SND_DJM_850_IDX] = SND_DJM_DEVICE(850),
 	[SND_DJM_900NXS2_IDX] = SND_DJM_DEVICE(900nxs2),
 	[SND_DJM_750MK2_IDX] = SND_DJM_DEVICE(750mk2),
+	[SND_DJM_450_IDX] = SND_DJM_DEVICE(450),
 };
 
 
@@ -3454,6 +3481,9 @@ int snd_usb_mixer_apply_create_quirk(struct usb_mixer_interface *mixer)
 	case USB_ID(0x2b73, 0x0017): /* Pioneer DJ DJM-250MK2 */
 		err = snd_djm_controls_create(mixer, SND_DJM_250MK2_IDX);
 		break;
+	case USB_ID(0x2b73, 0x0013): /* Pioneer DJ DJM-450 */
+		err = snd_djm_controls_create(mixer, SND_DJM_450_IDX);
+		break;
 	case USB_ID(0x08e4, 0x017f): /* Pioneer DJ DJM-750 */
 		err = snd_djm_controls_create(mixer, SND_DJM_750_IDX);
 		break;
diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c
index f7c57a2c3028..33a3d1161885 100644
--- a/sound/usb/mixer_scarlett2.c
+++ b/sound/usb/mixer_scarlett2.c
@@ -1966,7 +1966,7 @@ static int scarlett2_usb_get_meter_levels(struct usb_mixer_interface *mixer,
 		__le16 num_meters;
 		__le32 magic;
 	} __packed req;
-	u32 resp[SCARLETT2_MAX_METERS];
+	__le32 resp[SCARLETT2_MAX_METERS];
 	int i, err;
 
 	req.pad = 0;
@@ -1979,7 +1979,7 @@ static int scarlett2_usb_get_meter_levels(struct usb_mixer_interface *mixer,
 
 	/* copy, convert to u16 */
 	for (i = 0; i < num_meters; i++)
-		levels[i] = resp[i];
+		levels[i] = le32_to_cpu(resp[i]);
 
 	return 0;
 }
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index ab2b938502eb..07cc6a201579 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1387,7 +1387,7 @@ free_buf:
 
 static int snd_usb_motu_m_series_boot_quirk(struct usb_device *dev)
 {
-	msleep(2000);
+	msleep(4000);
 
 	return 0;
 }
@@ -1630,7 +1630,7 @@ int snd_usb_apply_boot_quirk_once(struct usb_device *dev,
 				  unsigned int id)
 {
 	switch (id) {
-	case USB_ID(0x07fd, 0x0008): /* MOTU M Series */
+	case USB_ID(0x07fd, 0x0008): /* MOTU M Series, 1st hardware version */
 		return snd_usb_motu_m_series_boot_quirk(dev);
 	}
 
diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h
index 5f6f84837a49..7c7493cb571f 100644
--- a/tools/arch/arm64/include/asm/cputype.h
+++ b/tools/arch/arm64/include/asm/cputype.h
@@ -79,13 +79,15 @@
 #define ARM_CPU_PART_CORTEX_A78AE	0xD42
 #define ARM_CPU_PART_CORTEX_X1		0xD44
 #define ARM_CPU_PART_CORTEX_A510	0xD46
+#define ARM_CPU_PART_CORTEX_A520	0xD80
 #define ARM_CPU_PART_CORTEX_A710	0xD47
 #define ARM_CPU_PART_CORTEX_A715	0xD4D
 #define ARM_CPU_PART_CORTEX_X2		0xD48
 #define ARM_CPU_PART_NEOVERSE_N2	0xD49
 #define ARM_CPU_PART_CORTEX_A78C	0xD4B
 
-#define APM_CPU_PART_POTENZA		0x000
+#define APM_CPU_PART_XGENE		0x000
+#define APM_CPU_VAR_POTENZA		0x00
 
 #define CAVIUM_CPU_PART_THUNDERX	0x0A1
 #define CAVIUM_CPU_PART_THUNDERX_81XX	0x0A2
@@ -148,6 +150,7 @@
 #define MIDR_CORTEX_A78AE	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE)
 #define MIDR_CORTEX_X1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
 #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
+#define MIDR_CORTEX_A520 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A520)
 #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
 #define MIDR_CORTEX_A715 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A715)
 #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2)
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index f7ddd73a8c0f..89d2fc872d9f 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -505,6 +505,38 @@ struct kvm_smccc_filter {
 #define KVM_HYPERCALL_EXIT_SMC		(1U << 0)
 #define KVM_HYPERCALL_EXIT_16BIT	(1U << 1)
 
+/*
+ * Get feature ID registers userspace writable mask.
+ *
+ * From DDI0487J.a, D19.2.66 ("ID_AA64MMFR2_EL1, AArch64 Memory Model
+ * Feature Register 2"):
+ *
+ * "The Feature ID space is defined as the System register space in
+ * AArch64 with op0==3, op1=={0, 1, 3}, CRn==0, CRm=={0-7},
+ * op2=={0-7}."
+ *
+ * This covers all currently known R/O registers that indicate
+ * anything useful feature wise, including the ID registers.
+ *
+ * If we ever need to introduce a new range, it will be described as
+ * such in the range field.
+ */
+#define KVM_ARM_FEATURE_ID_RANGE_IDX(op0, op1, crn, crm, op2)		\
+	({								\
+		__u64 __op1 = (op1) & 3;				\
+		__op1 -= (__op1 == 3);					\
+		(__op1 << 6 | ((crm) & 7) << 3 | (op2));		\
+	})
+
+#define KVM_ARM_FEATURE_ID_RANGE	0
+#define KVM_ARM_FEATURE_ID_RANGE_SIZE	(3 * 8 * 8)
+
+struct reg_mask_range {
+	__u64 addr;		/* Pointer to mask array */
+	__u32 range;		/* Requested range */
+	__u32 reserved[13];
+};
+
 #endif
 
 #endif /* __ARM_KVM_H__ */
diff --git a/tools/arch/arm64/include/uapi/asm/perf_regs.h b/tools/arch/arm64/include/uapi/asm/perf_regs.h
index fd157f46727e..86e556429e0e 100644
--- a/tools/arch/arm64/include/uapi/asm/perf_regs.h
+++ b/tools/arch/arm64/include/uapi/asm/perf_regs.h
@@ -36,11 +36,13 @@ enum perf_event_arm_regs {
 	PERF_REG_ARM64_LR,
 	PERF_REG_ARM64_SP,
 	PERF_REG_ARM64_PC,
+	PERF_REG_ARM64_MAX,
 
 	/* Extended/pseudo registers */
-	PERF_REG_ARM64_VG = 46, // SVE Vector Granule
-
-	PERF_REG_ARM64_MAX = PERF_REG_ARM64_PC + 1,
-	PERF_REG_ARM64_EXTENDED_MAX = PERF_REG_ARM64_VG + 1
+	PERF_REG_ARM64_VG = 46,				/* SVE Vector Granule */
+	PERF_REG_ARM64_EXTENDED_MAX
 };
+
+#define PERF_REG_EXTENDED_MASK	(1ULL << PERF_REG_ARM64_VG)
+
 #endif /* _ASM_ARM64_PERF_REGS_H */
diff --git a/tools/arch/arm64/tools/Makefile b/tools/arch/arm64/tools/Makefile
index 7f64b8bb5107..7b42feedf647 100644
--- a/tools/arch/arm64/tools/Makefile
+++ b/tools/arch/arm64/tools/Makefile
@@ -22,7 +22,7 @@ endif
 arm64_tools_dir = $(top_srcdir)/arch/arm64/tools
 arm64_sysreg_tbl = $(arm64_tools_dir)/sysreg
 arm64_gen_sysreg = $(arm64_tools_dir)/gen-sysreg.awk
-arm64_generated_dir = $(top_srcdir)/tools/arch/arm64/include/generated
+arm64_generated_dir = $(OUTPUT)arch/arm64/include/generated
 arm64_sysreg_defs = $(arm64_generated_dir)/asm/sysreg-defs.h
 
 all: $(arm64_sysreg_defs)
diff --git a/tools/arch/parisc/include/uapi/asm/errno.h b/tools/arch/parisc/include/uapi/asm/errno.h
index 87245c584784..8d94739d75c6 100644
--- a/tools/arch/parisc/include/uapi/asm/errno.h
+++ b/tools/arch/parisc/include/uapi/asm/errno.h
@@ -75,7 +75,6 @@
 
 /* We now return you to your regularly scheduled HPUX. */
 
-#define ENOSYM		215	/* symbol does not exist in executable */
 #define	ENOTSOCK	216	/* Socket operation on non-socket */
 #define	EDESTADDRREQ	217	/* Destination address required */
 #define	EMSGSIZE	218	/* Message too long */
@@ -101,7 +100,6 @@
 #define	ETIMEDOUT	238	/* Connection timed out */
 #define	ECONNREFUSED	239	/* Connection refused */
 #define	EREFUSED	ECONNREFUSED	/* for HP's NFS apparently */
-#define	EREMOTERELEASE	240	/* Remote peer released connection */
 #define	EHOSTDOWN	241	/* Host is down */
 #define	EHOSTUNREACH	242	/* No route to host */
 
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index a73cf01a1606..abe926d43cbe 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -159,6 +159,22 @@ struct kvm_s390_vm_cpu_subfunc {
 	__u8 reserved[1728];
 };
 
+#define KVM_S390_VM_CPU_PROCESSOR_UV_FEAT_GUEST	6
+#define KVM_S390_VM_CPU_MACHINE_UV_FEAT_GUEST	7
+
+#define KVM_S390_VM_CPU_UV_FEAT_NR_BITS	64
+struct kvm_s390_vm_cpu_uv_feat {
+	union {
+		struct {
+			__u64 : 4;
+			__u64 ap : 1;		/* bit 4 */
+			__u64 ap_intr : 1;	/* bit 5 */
+			__u64 : 58;
+		};
+		__u64 feat;
+	};
+};
+
 /* kvm attributes for crypto */
 #define KVM_S390_VM_CRYPTO_ENABLE_AES_KW	0
 #define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW	1
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 798e60b5454b..f4542d2718f4 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -198,7 +198,6 @@
 #define X86_FEATURE_CAT_L3		( 7*32+ 4) /* Cache Allocation Technology L3 */
 #define X86_FEATURE_CAT_L2		( 7*32+ 5) /* Cache Allocation Technology L2 */
 #define X86_FEATURE_CDP_L3		( 7*32+ 6) /* Code and Data Prioritization L3 */
-#define X86_FEATURE_INVPCID_SINGLE	( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
 #define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_XCOMPACTED		( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */
@@ -219,7 +218,7 @@
 #define X86_FEATURE_IBRS		( 7*32+25) /* Indirect Branch Restricted Speculation */
 #define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
 #define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
-#define X86_FEATURE_ZEN			(7*32+28) /* "" CPU based on Zen microarchitecture */
+#define X86_FEATURE_ZEN			( 7*32+28) /* "" Generic flag for all Zen and newer */
 #define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* "" L1TF workaround PTE inversion */
 #define X86_FEATURE_IBRS_ENHANCED	( 7*32+30) /* Enhanced IBRS */
 #define X86_FEATURE_MSR_IA32_FEAT_CTL	( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */
@@ -308,6 +307,11 @@
 #define X86_FEATURE_MSR_TSX_CTRL	(11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */
 #define X86_FEATURE_SMBA		(11*32+21) /* "" Slow Memory Bandwidth Allocation */
 #define X86_FEATURE_BMEC		(11*32+22) /* "" Bandwidth Monitoring Event Configuration */
+#define X86_FEATURE_USER_SHSTK		(11*32+23) /* Shadow stack support for user mode applications */
+
+#define X86_FEATURE_SRSO		(11*32+24) /* "" AMD BTB untrain RETs */
+#define X86_FEATURE_SRSO_ALIAS		(11*32+25) /* "" AMD BTB untrain RETs through aliasing */
+#define X86_FEATURE_IBPB_ON_VMEXIT	(11*32+26) /* "" Issue an IBPB only on VMEXIT */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
@@ -380,6 +384,7 @@
 #define X86_FEATURE_OSPKE		(16*32+ 4) /* OS Protection Keys Enable */
 #define X86_FEATURE_WAITPKG		(16*32+ 5) /* UMONITOR/UMWAIT/TPAUSE Instructions */
 #define X86_FEATURE_AVX512_VBMI2	(16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */
+#define X86_FEATURE_SHSTK		(16*32+ 7) /* "" Shadow stack */
 #define X86_FEATURE_GFNI		(16*32+ 8) /* Galois Field New Instructions */
 #define X86_FEATURE_VAES		(16*32+ 9) /* Vector AES */
 #define X86_FEATURE_VPCLMULQDQ		(16*32+10) /* Carry-Less Multiplication Double Quadword */
@@ -438,11 +443,16 @@
 
 /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */
 #define X86_FEATURE_NO_NESTED_DATA_BP	(20*32+ 0) /* "" No Nested Data Breakpoints */
+#define X86_FEATURE_WRMSR_XX_BASE_NS	(20*32+ 1) /* "" WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */
 #define X86_FEATURE_LFENCE_RDTSC	(20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */
 #define X86_FEATURE_NULL_SEL_CLR_BASE	(20*32+ 6) /* "" Null Selector Clears Base */
 #define X86_FEATURE_AUTOIBRS		(20*32+ 8) /* "" Automatic IBRS */
 #define X86_FEATURE_NO_SMM_CTL_MSR	(20*32+ 9) /* "" SMM_CTL MSR is not present */
 
+#define X86_FEATURE_SBPB		(20*32+27) /* "" Selective Branch Prediction Barrier */
+#define X86_FEATURE_IBPB_BRTYPE		(20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */
+#define X86_FEATURE_SRSO_NO		(20*32+29) /* "" CPU is not affected by SRSO */
+
 /*
  * BUG word(s)
  */
@@ -484,5 +494,9 @@
 #define X86_BUG_RETBLEED		X86_BUG(27) /* CPU is affected by RETBleed */
 #define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
 #define X86_BUG_SMT_RSB			X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */
+#define X86_BUG_GDS			X86_BUG(30) /* CPU is affected by Gather Data Sampling */
 
+/* BUG word 2 */
+#define X86_BUG_SRSO			X86_BUG(1*32 + 0) /* AMD SRSO bug */
+#define X86_BUG_DIV0			X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index fafe9be7a6f4..702d93fdd10e 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -105,6 +105,18 @@
 # define DISABLE_TDX_GUEST	(1 << (X86_FEATURE_TDX_GUEST & 31))
 #endif
 
+#ifdef CONFIG_X86_USER_SHADOW_STACK
+#define DISABLE_USER_SHSTK	0
+#else
+#define DISABLE_USER_SHSTK	(1 << (X86_FEATURE_USER_SHSTK & 31))
+#endif
+
+#ifdef CONFIG_X86_KERNEL_IBT
+#define DISABLE_IBT	0
+#else
+#define DISABLE_IBT	(1 << (X86_FEATURE_IBT & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -120,7 +132,7 @@
 #define DISABLED_MASK9	(DISABLE_SGX)
 #define DISABLED_MASK10	0
 #define DISABLED_MASK11	(DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \
-			 DISABLE_CALL_DEPTH_TRACKING)
+			 DISABLE_CALL_DEPTH_TRACKING|DISABLE_USER_SHSTK)
 #define DISABLED_MASK12	(DISABLE_LAM)
 #define DISABLED_MASK13	0
 #define DISABLED_MASK14	0
@@ -128,7 +140,7 @@
 #define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP| \
 			 DISABLE_ENQCMD)
 #define DISABLED_MASK17	0
-#define DISABLED_MASK18	0
+#define DISABLED_MASK18	(DISABLE_IBT)
 #define DISABLED_MASK19	0
 #define DISABLED_MASK20	0
 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 1d111350197f..1d51e1850ed0 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -222,6 +222,7 @@
 #define MSR_INTEGRITY_CAPS_ARRAY_BIST          BIT(MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT)
 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT	4
 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST	BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT)
+#define MSR_INTEGRITY_CAPS_SAF_GEN_MASK	GENMASK_ULL(10, 9)
 
 #define MSR_LBR_NHM_FROM		0x00000680
 #define MSR_LBR_NHM_TO			0x000006c0
@@ -553,6 +554,7 @@
 #define MSR_AMD64_CPUID_FN_1		0xc0011004
 #define MSR_AMD64_LS_CFG		0xc0011020
 #define MSR_AMD64_DC_CFG		0xc0011022
+#define MSR_AMD64_TW_CFG		0xc0011023
 
 #define MSR_AMD64_DE_CFG		0xc0011029
 #define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT	 1
@@ -637,12 +639,21 @@
 /* AMD Last Branch Record MSRs */
 #define MSR_AMD64_LBR_SELECT			0xc000010e
 
+/* Zen4 */
+#define MSR_ZEN4_BP_CFG                 0xc001102e
+#define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5
+
+/* Fam 19h MSRs */
+#define MSR_F19H_UMC_PERF_CTL           0xc0010800
+#define MSR_F19H_UMC_PERF_CTR           0xc0010801
+
+/* Zen 2 */
+#define MSR_ZEN2_SPECTRAL_CHICKEN       0xc00110e3
+#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT   BIT_ULL(1)
+
 /* Fam 17h MSRs */
 #define MSR_F17H_IRPERF			0xc00000e9
 
-#define MSR_ZEN2_SPECTRAL_CHICKEN	0xc00110e3
-#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT	BIT_ULL(1)
-
 /* Fam 16h MSRs */
 #define MSR_F16H_L2I_PERF_CTL		0xc0010230
 #define MSR_F16H_L2I_PERF_CTR		0xc0010231
@@ -1112,12 +1123,16 @@
 #define MSR_IA32_VMX_MISC_INTEL_PT                 (1ULL << 14)
 #define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29)
 #define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE   0x1F
-/* AMD-V MSRs */
 
+/* AMD-V MSRs */
 #define MSR_VM_CR                       0xc0010114
 #define MSR_VM_IGNNE                    0xc0010115
 #define MSR_VM_HSAVE_PA                 0xc0010117
 
+#define SVM_VM_CR_VALID_MASK		0x001fULL
+#define SVM_VM_CR_SVM_LOCK_MASK		0x0008ULL
+#define SVM_VM_CR_SVM_DIS_MASK		0x0010ULL
+
 /* Hardware Feedback Interface */
 #define MSR_IA32_HW_FEEDBACK_PTR        0x17d0
 #define MSR_IA32_HW_FEEDBACK_CONFIG     0x17d1
diff --git a/tools/arch/x86/include/uapi/asm/prctl.h b/tools/arch/x86/include/uapi/asm/prctl.h
index e8d7ebbca1a4..384e2cc6ac19 100644
--- a/tools/arch/x86/include/uapi/asm/prctl.h
+++ b/tools/arch/x86/include/uapi/asm/prctl.h
@@ -23,9 +23,21 @@
 #define ARCH_MAP_VDSO_32		0x2002
 #define ARCH_MAP_VDSO_64		0x2003
 
+/* Don't use 0x3001-0x3004 because of old glibcs */
+
 #define ARCH_GET_UNTAG_MASK		0x4001
 #define ARCH_ENABLE_TAGGED_ADDR		0x4002
 #define ARCH_GET_MAX_TAG_BITS		0x4003
 #define ARCH_FORCE_TAGGED_SVA		0x4004
 
+#define ARCH_SHSTK_ENABLE		0x5001
+#define ARCH_SHSTK_DISABLE		0x5002
+#define ARCH_SHSTK_LOCK			0x5003
+#define ARCH_SHSTK_UNLOCK		0x5004
+#define ARCH_SHSTK_STATUS		0x5005
+
+/* ARCH_SHSTK_ features bits */
+#define ARCH_SHSTK_SHSTK		(1ULL <<  0)
+#define ARCH_SHSTK_WRSS			(1ULL <<  1)
+
 #endif /* _ASM_X86_PRCTL_H */
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
index 6965c94dfdaf..09e4f2ff5658 100644
--- a/tools/bpf/bpftool/Documentation/bpftool.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -20,7 +20,7 @@ SYNOPSIS
 
 	**bpftool** **version**
 
-	*OBJECT* := { **map** | **program** | **link** | **cgroup** | **perf** | **net** | **feature** |
+	*OBJECT* := { **map** | **prog** | **link** | **cgroup** | **perf** | **net** | **feature** |
 	**btf** | **gen** | **struct_ops** | **iter** }
 
 	*OPTIONS* := { { **-V** | **--version** } | |COMMON_OPTIONS| }
diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c
index edda4fc2c4d0..708733b0ea06 100644
--- a/tools/bpf/bpftool/feature.c
+++ b/tools/bpf/bpftool/feature.c
@@ -426,10 +426,6 @@ static void probe_kernel_image_config(const char *define_prefix)
 		{ "CONFIG_BPF_STREAM_PARSER", },
 		/* xt_bpf module for passing BPF programs to netfilter  */
 		{ "CONFIG_NETFILTER_XT_MATCH_BPF", },
-		/* bpfilter back-end for iptables */
-		{ "CONFIG_BPFILTER", },
-		/* bpftilter module with "user mode helper" */
-		{ "CONFIG_BPFILTER_UMH", },
 
 		/* test_bpf module for BPF tests */
 		{ "CONFIG_TEST_BPF", },
diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index a1528cde81ab..cb46667a6b2e 100644
--- a/tools/bpf/bpftool/link.c
+++ b/tools/bpf/bpftool/link.c
@@ -294,6 +294,37 @@ show_kprobe_multi_json(struct bpf_link_info *info, json_writer_t *wtr)
 	jsonw_end_array(json_wtr);
 }
 
+static __u64 *u64_to_arr(__u64 val)
+{
+	return (__u64 *) u64_to_ptr(val);
+}
+
+static void
+show_uprobe_multi_json(struct bpf_link_info *info, json_writer_t *wtr)
+{
+	__u32 i;
+
+	jsonw_bool_field(json_wtr, "retprobe",
+			 info->uprobe_multi.flags & BPF_F_UPROBE_MULTI_RETURN);
+	jsonw_string_field(json_wtr, "path", (char *) u64_to_ptr(info->uprobe_multi.path));
+	jsonw_uint_field(json_wtr, "func_cnt", info->uprobe_multi.count);
+	jsonw_int_field(json_wtr, "pid", (int) info->uprobe_multi.pid);
+	jsonw_name(json_wtr, "funcs");
+	jsonw_start_array(json_wtr);
+
+	for (i = 0; i < info->uprobe_multi.count; i++) {
+		jsonw_start_object(json_wtr);
+		jsonw_uint_field(json_wtr, "offset",
+				 u64_to_arr(info->uprobe_multi.offsets)[i]);
+		jsonw_uint_field(json_wtr, "ref_ctr_offset",
+				 u64_to_arr(info->uprobe_multi.ref_ctr_offsets)[i]);
+		jsonw_uint_field(json_wtr, "cookie",
+				 u64_to_arr(info->uprobe_multi.cookies)[i]);
+		jsonw_end_object(json_wtr);
+	}
+	jsonw_end_array(json_wtr);
+}
+
 static void
 show_perf_event_kprobe_json(struct bpf_link_info *info, json_writer_t *wtr)
 {
@@ -465,6 +496,9 @@ static int show_link_close_json(int fd, struct bpf_link_info *info)
 	case BPF_LINK_TYPE_KPROBE_MULTI:
 		show_kprobe_multi_json(info, json_wtr);
 		break;
+	case BPF_LINK_TYPE_UPROBE_MULTI:
+		show_uprobe_multi_json(info, json_wtr);
+		break;
 	case BPF_LINK_TYPE_PERF_EVENT:
 		switch (info->perf_event.type) {
 		case BPF_PERF_EVENT_EVENT:
@@ -674,6 +708,33 @@ static void show_kprobe_multi_plain(struct bpf_link_info *info)
 	}
 }
 
+static void show_uprobe_multi_plain(struct bpf_link_info *info)
+{
+	__u32 i;
+
+	if (!info->uprobe_multi.count)
+		return;
+
+	if (info->uprobe_multi.flags & BPF_F_UPROBE_MULTI_RETURN)
+		printf("\n\turetprobe.multi  ");
+	else
+		printf("\n\tuprobe.multi  ");
+
+	printf("path %s  ", (char *) u64_to_ptr(info->uprobe_multi.path));
+	printf("func_cnt %u  ", info->uprobe_multi.count);
+
+	if (info->uprobe_multi.pid)
+		printf("pid %d  ", info->uprobe_multi.pid);
+
+	printf("\n\t%-16s   %-16s   %-16s", "offset", "ref_ctr_offset", "cookies");
+	for (i = 0; i < info->uprobe_multi.count; i++) {
+		printf("\n\t0x%-16llx 0x%-16llx 0x%-16llx",
+			u64_to_arr(info->uprobe_multi.offsets)[i],
+			u64_to_arr(info->uprobe_multi.ref_ctr_offsets)[i],
+			u64_to_arr(info->uprobe_multi.cookies)[i]);
+	}
+}
+
 static void show_perf_event_kprobe_plain(struct bpf_link_info *info)
 {
 	const char *buf;
@@ -807,6 +868,9 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
 	case BPF_LINK_TYPE_KPROBE_MULTI:
 		show_kprobe_multi_plain(info);
 		break;
+	case BPF_LINK_TYPE_UPROBE_MULTI:
+		show_uprobe_multi_plain(info);
+		break;
 	case BPF_LINK_TYPE_PERF_EVENT:
 		switch (info->perf_event.type) {
 		case BPF_PERF_EVENT_EVENT:
@@ -846,8 +910,10 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
 
 static int do_show_link(int fd)
 {
+	__u64 *ref_ctr_offsets = NULL, *offsets = NULL, *cookies = NULL;
 	struct bpf_link_info info;
 	__u32 len = sizeof(info);
+	char path_buf[PATH_MAX];
 	__u64 *addrs = NULL;
 	char buf[PATH_MAX];
 	int count;
@@ -889,6 +955,39 @@ again:
 			goto again;
 		}
 	}
+	if (info.type == BPF_LINK_TYPE_UPROBE_MULTI &&
+	    !info.uprobe_multi.offsets) {
+		count = info.uprobe_multi.count;
+		if (count) {
+			offsets = calloc(count, sizeof(__u64));
+			if (!offsets) {
+				p_err("mem alloc failed");
+				close(fd);
+				return -ENOMEM;
+			}
+			info.uprobe_multi.offsets = ptr_to_u64(offsets);
+			ref_ctr_offsets = calloc(count, sizeof(__u64));
+			if (!ref_ctr_offsets) {
+				p_err("mem alloc failed");
+				free(offsets);
+				close(fd);
+				return -ENOMEM;
+			}
+			info.uprobe_multi.ref_ctr_offsets = ptr_to_u64(ref_ctr_offsets);
+			cookies = calloc(count, sizeof(__u64));
+			if (!cookies) {
+				p_err("mem alloc failed");
+				free(cookies);
+				free(offsets);
+				close(fd);
+				return -ENOMEM;
+			}
+			info.uprobe_multi.cookies = ptr_to_u64(cookies);
+			info.uprobe_multi.path = ptr_to_u64(path_buf);
+			info.uprobe_multi.path_size = sizeof(path_buf);
+			goto again;
+		}
+	}
 	if (info.type == BPF_LINK_TYPE_PERF_EVENT) {
 		switch (info.perf_event.type) {
 		case BPF_PERF_EVENT_TRACEPOINT:
@@ -924,8 +1023,10 @@ again:
 	else
 		show_link_close_plain(fd, &info);
 
-	if (addrs)
-		free(addrs);
+	free(ref_ctr_offsets);
+	free(cookies);
+	free(offsets);
+	free(addrs);
 	close(fd);
 	return 0;
 }
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 7ec4f5671e7a..feb8e305804f 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -442,7 +442,7 @@ static void print_prog_header_json(struct bpf_prog_info *info, int fd)
 		jsonw_uint_field(json_wtr, "recursion_misses", info->recursion_misses);
 }
 
-static void print_prog_json(struct bpf_prog_info *info, int fd)
+static void print_prog_json(struct bpf_prog_info *info, int fd, bool orphaned)
 {
 	char *memlock;
 
@@ -461,6 +461,7 @@ static void print_prog_json(struct bpf_prog_info *info, int fd)
 		jsonw_uint_field(json_wtr, "uid", info->created_by_uid);
 	}
 
+	jsonw_bool_field(json_wtr, "orphaned", orphaned);
 	jsonw_uint_field(json_wtr, "bytes_xlated", info->xlated_prog_len);
 
 	if (info->jited_prog_len) {
@@ -527,7 +528,7 @@ static void print_prog_header_plain(struct bpf_prog_info *info, int fd)
 	printf("\n");
 }
 
-static void print_prog_plain(struct bpf_prog_info *info, int fd)
+static void print_prog_plain(struct bpf_prog_info *info, int fd, bool orphaned)
 {
 	char *memlock;
 
@@ -554,6 +555,9 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd)
 		printf("  memlock %sB", memlock);
 	free(memlock);
 
+	if (orphaned)
+		printf("  orphaned");
+
 	if (info->nr_map_ids)
 		show_prog_maps(fd, info->nr_map_ids);
 
@@ -581,15 +585,15 @@ static int show_prog(int fd)
 	int err;
 
 	err = bpf_prog_get_info_by_fd(fd, &info, &len);
-	if (err) {
+	if (err && err != -ENODEV) {
 		p_err("can't get prog info: %s", strerror(errno));
 		return -1;
 	}
 
 	if (json_output)
-		print_prog_json(&info, fd);
+		print_prog_json(&info, fd, err == -ENODEV);
 	else
-		print_prog_plain(&info, fd);
+		print_prog_plain(&info, fd, err == -ENODEV);
 
 	return 0;
 }
diff --git a/tools/cgroup/Makefile b/tools/cgroup/Makefile
deleted file mode 100644
index ffca068e4a76..000000000000
--- a/tools/cgroup/Makefile
+++ /dev/null
@@ -1,11 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-# Makefile for cgroup tools
-
-CFLAGS = -Wall -Wextra
-
-all: cgroup_event_listener
-%: %.c
-	$(CC) $(CFLAGS) -o $@ $^
-
-clean:
-	$(RM) cgroup_event_listener
diff --git a/tools/crypto/tcrypt/tcrypt_speed_compare.py b/tools/crypto/tcrypt/tcrypt_speed_compare.py
new file mode 100755
index 000000000000..f3f5783cdc06
--- /dev/null
+++ b/tools/crypto/tcrypt/tcrypt_speed_compare.py
@@ -0,0 +1,190 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) xFusion Digital Technologies Co., Ltd., 2023
+#
+# Author: Wang Jinchao <wangjinchao@xfusion.com>
+#
+"""
+A tool for comparing tcrypt speed test logs.
+
+Please note that for such a comparison, stability depends
+on whether we allow frequency to float or pin the frequency.
+
+Both support tests for operations within one second and
+cycles of operation.
+For example, use it in the bash script below.
+
+```bash
+#!/bin/bash
+
+# log file prefix
+seq_num=0
+
+# When sec=0, it will perform cycle tests;
+# otherwise, it indicates the duration of a single test
+sec=0
+num_mb=8
+mode=211
+
+# base speed test
+lsmod | grep pcrypt && modprobe -r pcrypt
+dmesg -C
+modprobe tcrypt alg="pcrypt(rfc4106(gcm(aes)))" type=3
+modprobe tcrypt mode=${mode} sec=${sec} num_mb=${num_mb}
+dmesg > ${seq_num}_base_dmesg.log
+
+# new speed test
+lsmod | grep pcrypt && modprobe -r pcrypt
+dmesg -C
+modprobe tcrypt alg="pcrypt(rfc4106(gcm(aes)))" type=3
+modprobe tcrypt mode=${mode} sec=${sec} num_mb=${num_mb}
+dmesg > ${seq_num}_new_dmesg.log
+lsmod | grep pcrypt && modprobe -r pcrypt
+
+tools/crypto/tcrypt/tcrypt_speed_compare.py \
+    ${seq_num}_base_dmesg.log \
+    ${seq_num}_new_dmesg.log  \
+        >${seq_num}_compare.log
+grep 'average' -A2 -B0 --group-separator="" ${seq_num}_compare.log
+```
+"""
+
+import sys
+import re
+
+
+def parse_title(line):
+    pattern = r'tcrypt: testing speed of (.*?) (encryption|decryption)'
+    match = re.search(pattern, line)
+    if match:
+        alg = match.group(1)
+        op = match.group(2)
+        return alg, op
+    else:
+        return "", ""
+
+
+def parse_item(line):
+    pattern_operations = r'\((\d+) bit key, (\d+) byte blocks\): (\d+) operations'
+    pattern_cycles = r'\((\d+) bit key, (\d+) byte blocks\): 1 operation in (\d+) cycles'
+    match = re.search(pattern_operations, line)
+    if match:
+        res = {
+            "bit_key": int(match.group(1)),
+            "byte_blocks": int(match.group(2)),
+            "operations": int(match.group(3)),
+        }
+        return res
+
+    match = re.search(pattern_cycles, line)
+    if match:
+        res = {
+            "bit_key": int(match.group(1)),
+            "byte_blocks": int(match.group(2)),
+            "cycles": int(match.group(3)),
+        }
+        return res
+
+    return None
+
+
+def parse(filepath):
+    result = {}
+    alg, op = "", ""
+    with open(filepath, 'r') as file:
+        for line in file:
+            if not line:
+                continue
+            _alg, _op = parse_title(line)
+            if _alg:
+                alg, op = _alg, _op
+                if alg not in result:
+                    result[alg] = {}
+                if op not in result[alg]:
+                    result[alg][op] = []
+                continue
+            parsed_result = parse_item(line)
+            if parsed_result:
+                result[alg][op].append(parsed_result)
+    return result
+
+
+def merge(base, new):
+    merged = {}
+    for alg in base.keys():
+        merged[alg] = {}
+        for op in base[alg].keys():
+            if op not in merged[alg]:
+                merged[alg][op] = []
+            for index in range(len(base[alg][op])):
+                merged_item = {
+                    "bit_key": base[alg][op][index]["bit_key"],
+                    "byte_blocks": base[alg][op][index]["byte_blocks"],
+                }
+                if "operations" in base[alg][op][index].keys():
+                    merged_item["base_ops"] = base[alg][op][index]["operations"]
+                    merged_item["new_ops"] = new[alg][op][index]["operations"]
+                else:
+                    merged_item["base_cycles"] = base[alg][op][index]["cycles"]
+                    merged_item["new_cycles"] = new[alg][op][index]["cycles"]
+
+                merged[alg][op].append(merged_item)
+    return merged
+
+
+def format(merged):
+    for alg in merged.keys():
+        for op in merged[alg].keys():
+            base_sum = 0
+            new_sum = 0
+            differ_sum = 0
+            differ_cnt = 0
+            print()
+            hlen = 80
+            print("="*hlen)
+            print(f"{alg}")
+            print(f"{' '*(len(alg)//3) + op}")
+            print("-"*hlen)
+            key = ""
+            if "base_ops" in merged[alg][op][0]:
+                key = "ops"
+                print(f"bit key | byte blocks | base ops    | new ops     | differ(%)")
+            else:
+                key = "cycles"
+                print(f"bit key | byte blocks | base cycles | new cycles  | differ(%)")
+            for index in range(len(merged[alg][op])):
+                item = merged[alg][op][index]
+                base_cnt = item[f"base_{key}"]
+                new_cnt = item[f"new_{key}"]
+                base_sum += base_cnt
+                new_sum += new_cnt
+                differ = round((new_cnt - base_cnt)*100/base_cnt, 2)
+                differ_sum += differ
+                differ_cnt += 1
+                bit_key = item["bit_key"]
+                byte_blocks = item["byte_blocks"]
+                print(
+                    f"{bit_key:<7} | {byte_blocks:<11} | {base_cnt:<11} | {new_cnt:<11} | {differ:<8}")
+            average_speed_up = "{:.2f}".format(differ_sum/differ_cnt)
+            ops_total_speed_up = "{:.2f}".format(
+                (base_sum - new_sum) * 100 / base_sum)
+            print('-'*hlen)
+            print(f"average differ(%s)    | total_differ(%)")
+            print('-'*hlen)
+            print(f"{average_speed_up:<21} | {ops_total_speed_up:<10}")
+            print('='*hlen)
+
+
+def main(base_log, new_log):
+    base = parse(base_log)
+    new = parse(new_log)
+    merged = merge(base, new)
+    format(merged)
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 3:
+        print(f"usage: {sys.argv[0]} base_log new_log")
+        exit(-1)
+    main(sys.argv[1], sys.argv[2])
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index 264eeb9c46a9..318e2dad27e0 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -1421,7 +1421,7 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val)
 	if (error)
 		goto setval_error;
 
-	if (new_val->addr_family == ADDR_FAMILY_IPV6) {
+	if (new_val->addr_family & ADDR_FAMILY_IPV6) {
 		error = fprintf(nmfile, "\n[ipv6]\n");
 		if (error < 0)
 			goto setval_error;
@@ -1455,14 +1455,18 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val)
 	if (error < 0)
 		goto setval_error;
 
-	error = fprintf(nmfile, "gateway=%s\n", (char *)new_val->gate_way);
-	if (error < 0)
-		goto setval_error;
-
-	error = fprintf(nmfile, "dns=%s\n", (char *)new_val->dns_addr);
-	if (error < 0)
-		goto setval_error;
+	/* we do not want ipv4 addresses in ipv6 section and vice versa */
+	if (is_ipv6 != is_ipv4((char *)new_val->gate_way)) {
+		error = fprintf(nmfile, "gateway=%s\n", (char *)new_val->gate_way);
+		if (error < 0)
+			goto setval_error;
+	}
 
+	if (is_ipv6 != is_ipv4((char *)new_val->dns_addr)) {
+		error = fprintf(nmfile, "dns=%s\n", (char *)new_val->dns_addr);
+		if (error < 0)
+			goto setval_error;
+	}
 	fclose(nmfile);
 	fclose(ifcfg_file);
 
diff --git a/tools/hv/hv_set_ifconfig.sh b/tools/hv/hv_set_ifconfig.sh
index ae5a7a8249a2..440a91b35823 100755
--- a/tools/hv/hv_set_ifconfig.sh
+++ b/tools/hv/hv_set_ifconfig.sh
@@ -53,7 +53,7 @@
 #                       or "manual" if no boot-time protocol should be used)
 #
 # address1=ipaddr1/plen
-# address=ipaddr2/plen
+# address2=ipaddr2/plen
 #
 # gateway=gateway1;gateway2
 #
@@ -61,7 +61,7 @@
 #
 # [ipv6]
 # address1=ipaddr1/plen
-# address2=ipaddr1/plen
+# address2=ipaddr2/plen
 #
 # gateway=gateway1;gateway2
 #
diff --git a/tools/include/asm-generic/unaligned.h b/tools/include/asm-generic/unaligned.h
index 156743d399ae..2fd551915c20 100644
--- a/tools/include/asm-generic/unaligned.h
+++ b/tools/include/asm-generic/unaligned.h
@@ -8,6 +8,7 @@
  */
 #pragma GCC diagnostic push
 #pragma GCC diagnostic ignored "-Wpacked"
+#pragma GCC diagnostic ignored "-Wattributes"
 
 #define __get_unaligned_t(type, ptr) ({						\
 	const struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr);	\
diff --git a/tools/include/linux/rwsem.h b/tools/include/linux/rwsem.h
index 83971b3cbfce..f8bffd4a987c 100644
--- a/tools/include/linux/rwsem.h
+++ b/tools/include/linux/rwsem.h
@@ -37,4 +37,8 @@ static inline int up_write(struct rw_semaphore *sem)
 {
 	return pthread_rwlock_unlock(&sem->lock);
 }
+
+#define down_read_nested(sem, subclass)		down_read(sem)
+#define down_write_nested(sem, subclass)	down_write(sem)
+
 #endif /* _TOOLS_RWSEM_H */
diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h
index 622266b197d0..a6cdf25b6b9d 100644
--- a/tools/include/linux/spinlock.h
+++ b/tools/include/linux/spinlock.h
@@ -11,6 +11,7 @@
 #define spin_lock_init(x)	pthread_mutex_init(x, NULL)
 
 #define spin_lock(x)			pthread_mutex_lock(x)
+#define spin_lock_nested(x, subclass)	pthread_mutex_lock(x)
 #define spin_unlock(x)			pthread_mutex_unlock(x)
 #define spin_lock_bh(x)			pthread_mutex_lock(x)
 #define spin_unlock_bh(x)		pthread_mutex_unlock(x)
diff --git a/tools/include/nolibc/arch-mips.h b/tools/include/nolibc/arch-mips.h
index 4ab6fa54beee..62cc50ef3288 100644
--- a/tools/include/nolibc/arch-mips.h
+++ b/tools/include/nolibc/arch-mips.h
@@ -10,6 +10,10 @@
 #include "compiler.h"
 #include "crt.h"
 
+#if !defined(_ABIO32)
+#error Unsupported MIPS ABI
+#endif
+
 /* Syscalls for MIPS ABI O32 :
  *   - WARNING! there's always a delayed slot!
  *   - WARNING again, the syntax is different, registers take a '$' and numbers
@@ -180,8 +184,13 @@ void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_
 	__asm__ volatile (
 		".set push\n"
 		".set noreorder\n"
-		".option pic0\n"
+		"bal 1f\n"               /* prime $ra for .cpload                            */
+		"nop\n"
+		"1:\n"
+		".cpload $ra\n"
 		"move  $a0, $sp\n"       /* save stack pointer to $a0, as arg1 of _start_c */
+		"addiu $sp, $sp, -4\n"   /* space for .cprestore to store $gp              */
+		".cprestore 0\n"
 		"li    $t0, -8\n"
 		"and   $sp, $sp, $t0\n"  /* $sp must be 8-byte aligned                     */
 		"addiu $sp, $sp, -16\n"  /* the callee expects to save a0..a3 there        */
diff --git a/tools/include/nolibc/arch.h b/tools/include/nolibc/arch.h
index e276fb0680af..c8f4e5d3add9 100644
--- a/tools/include/nolibc/arch.h
+++ b/tools/include/nolibc/arch.h
@@ -23,7 +23,7 @@
 #include "arch-arm.h"
 #elif defined(__aarch64__)
 #include "arch-aarch64.h"
-#elif defined(__mips__) && defined(_ABIO32)
+#elif defined(__mips__)
 #include "arch-mips.h"
 #elif defined(__powerpc__)
 #include "arch-powerpc.h"
@@ -33,6 +33,8 @@
 #include "arch-s390.h"
 #elif defined(__loongarch__)
 #include "arch-loongarch.h"
+#else
+#error Unsupported Architecture
 #endif
 
 #endif /* _NOLIBC_ARCH_H */
diff --git a/tools/include/nolibc/stdio.h b/tools/include/nolibc/stdio.h
index d7ef43973916..16cd4d807251 100644
--- a/tools/include/nolibc/stdio.h
+++ b/tools/include/nolibc/stdio.h
@@ -212,7 +212,7 @@ char *fgets(char *s, int size, FILE *stream)
  *  - %s
  *  - unknown modifiers are ignored.
  */
-static __attribute__((unused))
+static __attribute__((unused, format(printf, 2, 0)))
 int vfprintf(FILE *stream, const char *fmt, va_list args)
 {
 	char escape, lpref, c;
@@ -318,7 +318,7 @@ int vfprintf(FILE *stream, const char *fmt, va_list args)
 	return written;
 }
 
-static __attribute__((unused))
+static __attribute__((unused, format(printf, 1, 0)))
 int vprintf(const char *fmt, va_list args)
 {
 	return vfprintf(stdout, fmt, args);
diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h
index 2f359cb03d10..dda9dffd1d74 100644
--- a/tools/include/nolibc/sys.h
+++ b/tools/include/nolibc/sys.h
@@ -21,6 +21,7 @@
 #include <linux/fcntl.h> /* for O_* and AT_* */
 #include <linux/stat.h>  /* for statx() */
 #include <linux/prctl.h>
+#include <linux/resource.h>
 
 #include "arch.h"
 #include "errno.h"
@@ -899,6 +900,43 @@ int reboot(int cmd)
 
 
 /*
+ * int getrlimit(int resource, struct rlimit *rlim);
+ * int setrlimit(int resource, const struct rlimit *rlim);
+ */
+
+static __attribute__((unused))
+int sys_prlimit64(pid_t pid, int resource,
+		  const struct rlimit64 *new_limit, struct rlimit64 *old_limit)
+{
+	return my_syscall4(__NR_prlimit64, pid, resource, new_limit, old_limit);
+}
+
+static __attribute__((unused))
+int getrlimit(int resource, struct rlimit *rlim)
+{
+	struct rlimit64 rlim64;
+	int ret;
+
+	ret = __sysret(sys_prlimit64(0, resource, NULL, &rlim64));
+	rlim->rlim_cur = rlim64.rlim_cur;
+	rlim->rlim_max = rlim64.rlim_max;
+
+	return ret;
+}
+
+static __attribute__((unused))
+int setrlimit(int resource, const struct rlimit *rlim)
+{
+	struct rlimit64 rlim64 = {
+		.rlim_cur = rlim->rlim_cur,
+		.rlim_max = rlim->rlim_max,
+	};
+
+	return __sysret(sys_prlimit64(0, resource, &rlim64, NULL));
+}
+
+
+/*
  * int sched_yield(void);
  */
 
diff --git a/tools/include/nolibc/types.h b/tools/include/nolibc/types.h
index 8cfc4c860fa4..b26a5d0c417c 100644
--- a/tools/include/nolibc/types.h
+++ b/tools/include/nolibc/types.h
@@ -12,6 +12,8 @@
 #include <linux/reboot.h> /* for LINUX_REBOOT_* */
 #include <linux/stat.h>
 #include <linux/time.h>
+#include <linux/wait.h>
+#include <linux/resource.h>
 
 
 /* Only the generic macros and types may be defined here. The arch-specific
@@ -108,9 +110,6 @@
 #define WTERMSIG(status)    ((status) & 0x7f)
 #define WIFSIGNALED(status) ((status) - 1 < 0xff)
 
-/* waitpid() flags */
-#define WNOHANG      1
-
 /* standard exit() codes */
 #define EXIT_SUCCESS 0
 #define EXIT_FAILURE 1
@@ -180,26 +179,6 @@ struct linux_dirent64 {
 	char           d_name[];
 };
 
-/* needed by wait4() */
-struct rusage {
-	struct timeval ru_utime;
-	struct timeval ru_stime;
-	long   ru_maxrss;
-	long   ru_ixrss;
-	long   ru_idrss;
-	long   ru_isrss;
-	long   ru_minflt;
-	long   ru_majflt;
-	long   ru_nswap;
-	long   ru_inblock;
-	long   ru_oublock;
-	long   ru_msgsnd;
-	long   ru_msgrcv;
-	long   ru_nsignals;
-	long   ru_nvcsw;
-	long   ru_nivcsw;
-};
-
 /* The format of the struct as returned by the libc to the application, which
  * significantly differs from the format returned by the stat() syscall flavours.
  */
diff --git a/tools/include/perf/arm_pmuv3.h b/tools/include/perf/arm_pmuv3.h
index e822d49fb5b8..1e397d55384e 100644
--- a/tools/include/perf/arm_pmuv3.h
+++ b/tools/include/perf/arm_pmuv3.h
@@ -218,45 +218,54 @@
 #define ARMV8_PMU_PMCR_DP	(1 << 5) /* Disable CCNT if non-invasive debug*/
 #define ARMV8_PMU_PMCR_LC	(1 << 6) /* Overflow on 64 bit cycle counter */
 #define ARMV8_PMU_PMCR_LP	(1 << 7) /* Long event counter enable */
-#define ARMV8_PMU_PMCR_N_SHIFT	11  /* Number of counters supported */
-#define ARMV8_PMU_PMCR_N_MASK	0x1f
-#define ARMV8_PMU_PMCR_MASK	0xff    /* Mask for writable bits */
+#define ARMV8_PMU_PMCR_N	GENMASK(15, 11) /* Number of counters supported */
+/* Mask for writable bits */
+#define ARMV8_PMU_PMCR_MASK	(ARMV8_PMU_PMCR_E | ARMV8_PMU_PMCR_P | \
+				 ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_D | \
+				 ARMV8_PMU_PMCR_X | ARMV8_PMU_PMCR_DP | \
+				 ARMV8_PMU_PMCR_LC | ARMV8_PMU_PMCR_LP)
 
 /*
  * PMOVSR: counters overflow flag status reg
  */
-#define ARMV8_PMU_OVSR_MASK		0xffffffff	/* Mask for writable bits */
-#define ARMV8_PMU_OVERFLOWED_MASK	ARMV8_PMU_OVSR_MASK
+#define ARMV8_PMU_OVSR_P		GENMASK(30, 0)
+#define ARMV8_PMU_OVSR_C		BIT(31)
+/* Mask for writable bits is both P and C fields */
+#define ARMV8_PMU_OVERFLOWED_MASK	(ARMV8_PMU_OVSR_P | ARMV8_PMU_OVSR_C)
 
 /*
  * PMXEVTYPER: Event selection reg
  */
-#define ARMV8_PMU_EVTYPE_MASK	0xc800ffff	/* Mask for writable bits */
-#define ARMV8_PMU_EVTYPE_EVENT	0xffff		/* Mask for EVENT bits */
+#define ARMV8_PMU_EVTYPE_EVENT	GENMASK(15, 0)	/* Mask for EVENT bits */
+#define ARMV8_PMU_EVTYPE_TH	GENMASK(43, 32)
+#define ARMV8_PMU_EVTYPE_TC	GENMASK(63, 61)
 
 /*
  * Event filters for PMUv3
  */
-#define ARMV8_PMU_EXCLUDE_EL1	(1U << 31)
-#define ARMV8_PMU_EXCLUDE_EL0	(1U << 30)
-#define ARMV8_PMU_INCLUDE_EL2	(1U << 27)
+#define ARMV8_PMU_EXCLUDE_EL1		(1U << 31)
+#define ARMV8_PMU_EXCLUDE_EL0		(1U << 30)
+#define ARMV8_PMU_EXCLUDE_NS_EL1	(1U << 29)
+#define ARMV8_PMU_EXCLUDE_NS_EL0	(1U << 28)
+#define ARMV8_PMU_INCLUDE_EL2		(1U << 27)
+#define ARMV8_PMU_EXCLUDE_EL3		(1U << 26)
 
 /*
  * PMUSERENR: user enable reg
  */
-#define ARMV8_PMU_USERENR_MASK	0xf		/* Mask for writable bits */
 #define ARMV8_PMU_USERENR_EN	(1 << 0) /* PMU regs can be accessed at EL0 */
 #define ARMV8_PMU_USERENR_SW	(1 << 1) /* PMSWINC can be written at EL0 */
 #define ARMV8_PMU_USERENR_CR	(1 << 2) /* Cycle counter can be read at EL0 */
 #define ARMV8_PMU_USERENR_ER	(1 << 3) /* Event counter can be read at EL0 */
+/* Mask for writable bits */
+#define ARMV8_PMU_USERENR_MASK	(ARMV8_PMU_USERENR_EN | ARMV8_PMU_USERENR_SW | \
+				 ARMV8_PMU_USERENR_CR | ARMV8_PMU_USERENR_ER)
 
 /* PMMIR_EL1.SLOTS mask */
-#define ARMV8_PMU_SLOTS_MASK	0xff
-
-#define ARMV8_PMU_BUS_SLOTS_SHIFT 8
-#define ARMV8_PMU_BUS_SLOTS_MASK 0xff
-#define ARMV8_PMU_BUS_WIDTH_SHIFT 16
-#define ARMV8_PMU_BUS_WIDTH_MASK 0xf
+#define ARMV8_PMU_SLOTS		GENMASK(7, 0)
+#define ARMV8_PMU_BUS_SLOTS	GENMASK(15, 8)
+#define ARMV8_PMU_BUS_WIDTH	GENMASK(19, 16)
+#define ARMV8_PMU_THWIDTH	GENMASK(23, 20)
 
 /*
  * This code is really good
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 76d946445391..756b013fb832 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -816,15 +816,21 @@ __SYSCALL(__NR_process_mrelease, sys_process_mrelease)
 __SYSCALL(__NR_futex_waitv, sys_futex_waitv)
 #define __NR_set_mempolicy_home_node 450
 __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
-
 #define __NR_cachestat 451
 __SYSCALL(__NR_cachestat, sys_cachestat)
-
 #define __NR_fchmodat2 452
 __SYSCALL(__NR_fchmodat2, sys_fchmodat2)
+#define __NR_map_shadow_stack 453
+__SYSCALL(__NR_map_shadow_stack, sys_map_shadow_stack)
+#define __NR_futex_wake 454
+__SYSCALL(__NR_futex_wake, sys_futex_wake)
+#define __NR_futex_wait 455
+__SYSCALL(__NR_futex_wait, sys_futex_wait)
+#define __NR_futex_requeue 456
+__SYSCALL(__NR_futex_requeue, sys_futex_requeue)
 
 #undef __NR_syscalls
-#define __NR_syscalls 453
+#define __NR_syscalls 457
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 794c1d857677..de723566c5ae 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -1134,6 +1134,26 @@ extern "C" {
 #define DRM_IOCTL_MODE_PAGE_FLIP	DRM_IOWR(0xB0, struct drm_mode_crtc_page_flip)
 #define DRM_IOCTL_MODE_DIRTYFB		DRM_IOWR(0xB1, struct drm_mode_fb_dirty_cmd)
 
+/**
+ * DRM_IOCTL_MODE_CREATE_DUMB - Create a new dumb buffer object.
+ *
+ * KMS dumb buffers provide a very primitive way to allocate a buffer object
+ * suitable for scanout and map it for software rendering. KMS dumb buffers are
+ * not suitable for hardware-accelerated rendering nor video decoding. KMS dumb
+ * buffers are not suitable to be displayed on any other device than the KMS
+ * device where they were allocated from. Also see
+ * :ref:`kms_dumb_buffer_objects`.
+ *
+ * The IOCTL argument is a struct drm_mode_create_dumb.
+ *
+ * User-space is expected to create a KMS dumb buffer via this IOCTL, then add
+ * it as a KMS framebuffer via &DRM_IOCTL_MODE_ADDFB and map it via
+ * &DRM_IOCTL_MODE_MAP_DUMB.
+ *
+ * &DRM_CAP_DUMB_BUFFER indicates whether this IOCTL is supported.
+ * &DRM_CAP_DUMB_PREFERRED_DEPTH and &DRM_CAP_DUMB_PREFER_SHADOW indicate
+ * driver preferences for dumb buffers.
+ */
 #define DRM_IOCTL_MODE_CREATE_DUMB DRM_IOWR(0xB2, struct drm_mode_create_dumb)
 #define DRM_IOCTL_MODE_MAP_DUMB    DRM_IOWR(0xB3, struct drm_mode_map_dumb)
 #define DRM_IOCTL_MODE_DESTROY_DUMB    DRM_IOWR(0xB4, struct drm_mode_destroy_dumb)
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 7000e5910a1d..218edb0a96f8 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -38,13 +38,13 @@ extern "C" {
  */
 
 /**
- * DOC: uevents generated by i915 on it's device node
+ * DOC: uevents generated by i915 on its device node
  *
  * I915_L3_PARITY_UEVENT - Generated when the driver receives a parity mismatch
- *	event from the gpu l3 cache. Additional information supplied is ROW,
+ *	event from the GPU L3 cache. Additional information supplied is ROW,
  *	BANK, SUBBANK, SLICE of the affected cacheline. Userspace should keep
- *	track of these events and if a specific cache-line seems to have a
- *	persistent error remap it with the l3 remapping tool supplied in
+ *	track of these events, and if a specific cache-line seems to have a
+ *	persistent error, remap it with the L3 remapping tool supplied in
  *	intel-gpu-tools.  The value supplied with the event is always 1.
  *
  * I915_ERROR_UEVENT - Generated upon error detection, currently only via
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0f6cdf52b1da..7f24d898efbb 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1074,9 +1074,11 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_TCX = 11,
 	BPF_LINK_TYPE_UPROBE_MULTI = 12,
 	BPF_LINK_TYPE_NETKIT = 13,
-	MAX_BPF_LINK_TYPE,
+	__MAX_BPF_LINK_TYPE,
 };
 
+#define MAX_BPF_LINK_TYPE __MAX_BPF_LINK_TYPE
+
 enum bpf_perf_event_type {
 	BPF_PERF_EVENT_UNSPEC = 0,
 	BPF_PERF_EVENT_UPROBE = 1,
@@ -1200,6 +1202,9 @@ enum bpf_perf_event_type {
  */
 #define BPF_F_XDP_DEV_BOUND_ONLY	(1U << 6)
 
+/* The verifier internal test flag. Behavior is undefined */
+#define BPF_F_TEST_REG_INVARIANTS	(1U << 7)
+
 /* link_create.kprobe_multi.flags used in LINK_CREATE command for
  * BPF_TRACE_KPROBE_MULTI attach type to create return probe.
  */
@@ -4517,6 +4522,8 @@ union bpf_attr {
  * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags)
  *	Description
  *		Return a user or a kernel stack in bpf program provided buffer.
+ *		Note: the user stack will only be populated if the *task* is
+ *		the current task; all other tasks will return -EOPNOTSUPP.
  *		To achieve this, the helper needs *task*, which is a valid
  *		pointer to **struct task_struct**. To store the stacktrace, the
  *		bpf program provides *buf* with a nonnegative *size*.
@@ -4528,6 +4535,7 @@ union bpf_attr {
  *
  *		**BPF_F_USER_STACK**
  *			Collect a user space stack instead of a kernel stack.
+ *			The *task* must be the current task.
  *		**BPF_F_USER_BUILD_ID**
  *			Collect buildid+offset instead of ips for user stack,
  *			only valid if **BPF_F_USER_STACK** is also specified.
@@ -6557,6 +6565,16 @@ struct bpf_link_info {
 			__u64 missed;
 		} kprobe_multi;
 		struct {
+			__aligned_u64 path;
+			__aligned_u64 offsets;
+			__aligned_u64 ref_ctr_offsets;
+			__aligned_u64 cookies;
+			__u32 path_size; /* in/out: real path size on success, including zero byte */
+			__u32 count; /* in/out: uprobe_multi offsets/ref_ctr_offsets/cookies count */
+			__u32 flags;
+			__u32 pid;
+		} uprobe_multi;
+		struct {
 			__u32 type; /* enum bpf_perf_event_type */
 			__u32 :32;
 			union {
@@ -7151,40 +7169,31 @@ struct bpf_spin_lock {
 };
 
 struct bpf_timer {
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[2];
 } __attribute__((aligned(8)));
 
 struct bpf_dynptr {
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[2];
 } __attribute__((aligned(8)));
 
 struct bpf_list_head {
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[2];
 } __attribute__((aligned(8)));
 
 struct bpf_list_node {
-	__u64 :64;
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[3];
 } __attribute__((aligned(8)));
 
 struct bpf_rb_root {
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[2];
 } __attribute__((aligned(8)));
 
 struct bpf_rb_node {
-	__u64 :64;
-	__u64 :64;
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[4];
 } __attribute__((aligned(8)));
 
 struct bpf_refcount {
-	__u32 :32;
+	__u32 __opaque[1];
 } __attribute__((aligned(4)));
 
 struct bpf_sysctl {
diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
index da43810b7485..48ad69f7722e 100644
--- a/tools/include/uapi/linux/fs.h
+++ b/tools/include/uapi/linux/fs.h
@@ -316,6 +316,7 @@ typedef int __bitwise __kernel_rwf_t;
 #define PAGE_IS_SWAPPED		(1 << 4)
 #define PAGE_IS_PFNZERO		(1 << 5)
 #define PAGE_IS_HUGE		(1 << 6)
+#define PAGE_IS_SOFT_DIRTY	(1 << 7)
 
 /*
  * struct page_region - Page region with flags
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
index fd1fb0d5389d..7a8f4c290187 100644
--- a/tools/include/uapi/linux/fscrypt.h
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -71,7 +71,8 @@ struct fscrypt_policy_v2 {
 	__u8 contents_encryption_mode;
 	__u8 filenames_encryption_mode;
 	__u8 flags;
-	__u8 __reserved[4];
+	__u8 log2_data_unit_size;
+	__u8 __reserved[3];
 	__u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
 };
 
diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h
index 73a47da885dc..638c606dfa74 100644
--- a/tools/include/uapi/linux/if_xdp.h
+++ b/tools/include/uapi/linux/if_xdp.h
@@ -26,14 +26,20 @@
  */
 #define XDP_USE_NEED_WAKEUP (1 << 3)
 /* By setting this option, userspace application indicates that it can
- * handle multiple descriptors per packet thus enabling xsk core to split
+ * handle multiple descriptors per packet thus enabling AF_XDP to split
  * multi-buffer XDP frames into multiple Rx descriptors. Without this set
- * such frames will be dropped by xsk.
+ * such frames will be dropped.
  */
-#define XDP_USE_SG     (1 << 4)
+#define XDP_USE_SG	(1 << 4)
 
 /* Flags for xsk_umem_config flags */
-#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
+#define XDP_UMEM_UNALIGNED_CHUNK_FLAG	(1 << 0)
+
+/* Force checksum calculation in software. Can be used for testing or
+ * working around potential HW issues. This option causes performance
+ * degradation and only works in XDP_COPY mode.
+ */
+#define XDP_UMEM_TX_SW_CSUM		(1 << 1)
 
 struct sockaddr_xdp {
 	__u16 sxdp_family;
@@ -76,6 +82,7 @@ struct xdp_umem_reg {
 	__u32 chunk_size;
 	__u32 headroom;
 	__u32 flags;
+	__u32 tx_metadata_len;
 };
 
 struct xdp_statistics {
@@ -105,6 +112,41 @@ struct xdp_options {
 #define XSK_UNALIGNED_BUF_ADDR_MASK \
 	((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1)
 
+/* Request transmit timestamp. Upon completion, put it into tx_timestamp
+ * field of union xsk_tx_metadata.
+ */
+#define XDP_TXMD_FLAGS_TIMESTAMP		(1 << 0)
+
+/* Request transmit checksum offload. Checksum start position and offset
+ * are communicated via csum_start and csum_offset fields of union
+ * xsk_tx_metadata.
+ */
+#define XDP_TXMD_FLAGS_CHECKSUM			(1 << 1)
+
+/* AF_XDP offloads request. 'request' union member is consumed by the driver
+ * when the packet is being transmitted. 'completion' union member is
+ * filled by the driver when the transmit completion arrives.
+ */
+struct xsk_tx_metadata {
+	__u64 flags;
+
+	union {
+		struct {
+			/* XDP_TXMD_FLAGS_CHECKSUM */
+
+			/* Offset from desc->addr where checksumming should start. */
+			__u16 csum_start;
+			/* Offset from csum_start where checksum should be stored. */
+			__u16 csum_offset;
+		} request;
+
+		struct {
+			/* XDP_TXMD_FLAGS_TIMESTAMP */
+			__u64 tx_timestamp;
+		} completion;
+	};
+};
+
 /* Rx/Tx descriptor */
 struct xdp_desc {
 	__u64 addr;
@@ -112,9 +154,16 @@ struct xdp_desc {
 	__u32 options;
 };
 
-/* Flag indicating packet constitutes of multiple buffers*/
+/* UMEM descriptor is __u64 */
+
+/* Flag indicating that the packet continues with the buffer pointed out by the
+ * next frame in the ring. The end of the packet is signalled by setting this
+ * bit to zero. For single buffer packets, every descriptor has 'options' set
+ * to 0 and this maintains backward compatibility.
+ */
 #define XDP_PKT_CONTD (1 << 0)
 
-/* UMEM descriptor is __u64 */
+/* TX packet carries valid metadata. */
+#define XDP_TX_METADATA (1 << 1)
 
 #endif /* _LINUX_IF_XDP_H */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index f089ab290978..211b86de35ac 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -264,6 +264,7 @@ struct kvm_xen_exit {
 #define KVM_EXIT_RISCV_SBI        35
 #define KVM_EXIT_RISCV_CSR        36
 #define KVM_EXIT_NOTIFY           37
+#define KVM_EXIT_LOONGARCH_IOCSR  38
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -336,6 +337,13 @@ struct kvm_run {
 			__u32 len;
 			__u8  is_write;
 		} mmio;
+		/* KVM_EXIT_LOONGARCH_IOCSR */
+		struct {
+			__u64 phys_addr;
+			__u8  data[8];
+			__u32 len;
+			__u8  is_write;
+		} iocsr_io;
 		/* KVM_EXIT_HYPERCALL */
 		struct {
 			__u64 nr;
@@ -1192,6 +1200,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_COUNTER_OFFSET 227
 #define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228
 #define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
+#define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1362,6 +1371,7 @@ struct kvm_dirty_tlb {
 #define KVM_REG_ARM64		0x6000000000000000ULL
 #define KVM_REG_MIPS		0x7000000000000000ULL
 #define KVM_REG_RISCV		0x8000000000000000ULL
+#define KVM_REG_LOONGARCH	0x9000000000000000ULL
 
 #define KVM_REG_SIZE_SHIFT	52
 #define KVM_REG_SIZE_MASK	0x00f0000000000000ULL
@@ -1418,9 +1428,16 @@ struct kvm_device_attr {
 	__u64	addr;		/* userspace address of attr data */
 };
 
-#define  KVM_DEV_VFIO_GROUP			1
-#define   KVM_DEV_VFIO_GROUP_ADD			1
-#define   KVM_DEV_VFIO_GROUP_DEL			2
+#define  KVM_DEV_VFIO_FILE			1
+
+#define   KVM_DEV_VFIO_FILE_ADD			1
+#define   KVM_DEV_VFIO_FILE_DEL			2
+
+/* KVM_DEV_VFIO_GROUP aliases are for compile time uapi compatibility */
+#define  KVM_DEV_VFIO_GROUP	KVM_DEV_VFIO_FILE
+
+#define   KVM_DEV_VFIO_GROUP_ADD	KVM_DEV_VFIO_FILE_ADD
+#define   KVM_DEV_VFIO_GROUP_DEL	KVM_DEV_VFIO_FILE_DEL
 #define   KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE		3
 
 enum kvm_device_type {
@@ -1555,6 +1572,7 @@ struct kvm_s390_ucas_mapping {
 #define KVM_ARM_MTE_COPY_TAGS	  _IOR(KVMIO,  0xb4, struct kvm_arm_copy_mte_tags)
 /* Available with KVM_CAP_COUNTER_OFFSET */
 #define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO,  0xb5, struct kvm_arm_counter_offset)
+#define KVM_ARM_GET_REG_WRITABLE_MASKS _IOR(KVMIO,  0xb6, struct reg_mask_range)
 
 /* ioctl for vm fd */
 #define KVM_CREATE_DEVICE	  _IOWR(KVMIO,  0xe0, struct kvm_create_device)
diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h
index 8eb0d7b758d2..bb242fdcfe6b 100644
--- a/tools/include/uapi/linux/mount.h
+++ b/tools/include/uapi/linux/mount.h
@@ -100,8 +100,9 @@ enum fsconfig_command {
 	FSCONFIG_SET_PATH	= 3,	/* Set parameter, supplying an object by path */
 	FSCONFIG_SET_PATH_EMPTY	= 4,	/* Set parameter, supplying an object by (empty) path */
 	FSCONFIG_SET_FD		= 5,	/* Set parameter, supplying an object by fd */
-	FSCONFIG_CMD_CREATE	= 6,	/* Invoke superblock creation */
+	FSCONFIG_CMD_CREATE	= 6,	/* Create new or reuse existing superblock */
 	FSCONFIG_CMD_RECONFIGURE = 7,	/* Invoke superblock reconfiguration */
+	FSCONFIG_CMD_CREATE_EXCL = 8,	/* Create new superblock, fail if reusing existing superblock */
 };
 
 /*
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 2943a151d4f1..93cb411adf72 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -44,13 +44,30 @@ enum netdev_xdp_act {
  *   timestamp via bpf_xdp_metadata_rx_timestamp().
  * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet
  *   hash via bpf_xdp_metadata_rx_hash().
+ * @NETDEV_XDP_RX_METADATA_VLAN_TAG: Device is capable of exposing receive
+ *   packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag().
  */
 enum netdev_xdp_rx_metadata {
 	NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
 	NETDEV_XDP_RX_METADATA_HASH = 2,
+	NETDEV_XDP_RX_METADATA_VLAN_TAG = 4,
+};
 
-	/* private: */
-	NETDEV_XDP_RX_METADATA_MASK = 3,
+/**
+ * enum netdev_xsk_flags
+ * @NETDEV_XSK_FLAGS_TX_TIMESTAMP: HW timestamping egress packets is supported
+ *   by the driver.
+ * @NETDEV_XSK_FLAGS_TX_CHECKSUM: L3 checksum HW offload is supported by the
+ *   driver.
+ */
+enum netdev_xsk_flags {
+	NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1,
+	NETDEV_XSK_FLAGS_TX_CHECKSUM = 2,
+};
+
+enum netdev_queue_type {
+	NETDEV_QUEUE_TYPE_RX,
+	NETDEV_QUEUE_TYPE_TX,
 };
 
 enum {
@@ -59,21 +76,80 @@ enum {
 	NETDEV_A_DEV_XDP_FEATURES,
 	NETDEV_A_DEV_XDP_ZC_MAX_SEGS,
 	NETDEV_A_DEV_XDP_RX_METADATA_FEATURES,
+	NETDEV_A_DEV_XSK_FEATURES,
 
 	__NETDEV_A_DEV_MAX,
 	NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
 };
 
 enum {
+	NETDEV_A_PAGE_POOL_ID = 1,
+	NETDEV_A_PAGE_POOL_IFINDEX,
+	NETDEV_A_PAGE_POOL_NAPI_ID,
+	NETDEV_A_PAGE_POOL_INFLIGHT,
+	NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
+	NETDEV_A_PAGE_POOL_DETACH_TIME,
+
+	__NETDEV_A_PAGE_POOL_MAX,
+	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)
+};
+
+enum {
+	NETDEV_A_PAGE_POOL_STATS_INFO = 1,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST = 8,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT,
+
+	__NETDEV_A_PAGE_POOL_STATS_MAX,
+	NETDEV_A_PAGE_POOL_STATS_MAX = (__NETDEV_A_PAGE_POOL_STATS_MAX - 1)
+};
+
+enum {
+	NETDEV_A_NAPI_IFINDEX = 1,
+	NETDEV_A_NAPI_ID,
+	NETDEV_A_NAPI_IRQ,
+	NETDEV_A_NAPI_PID,
+
+	__NETDEV_A_NAPI_MAX,
+	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
+};
+
+enum {
+	NETDEV_A_QUEUE_ID = 1,
+	NETDEV_A_QUEUE_IFINDEX,
+	NETDEV_A_QUEUE_TYPE,
+	NETDEV_A_QUEUE_NAPI_ID,
+
+	__NETDEV_A_QUEUE_MAX,
+	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
+};
+
+enum {
 	NETDEV_CMD_DEV_GET = 1,
 	NETDEV_CMD_DEV_ADD_NTF,
 	NETDEV_CMD_DEV_DEL_NTF,
 	NETDEV_CMD_DEV_CHANGE_NTF,
+	NETDEV_CMD_PAGE_POOL_GET,
+	NETDEV_CMD_PAGE_POOL_ADD_NTF,
+	NETDEV_CMD_PAGE_POOL_DEL_NTF,
+	NETDEV_CMD_PAGE_POOL_CHANGE_NTF,
+	NETDEV_CMD_PAGE_POOL_STATS_GET,
+	NETDEV_CMD_QUEUE_GET,
+	NETDEV_CMD_NAPI_GET,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
 };
 
 #define NETDEV_MCGRP_MGMT	"mgmt"
+#define NETDEV_MCGRP_PAGE_POOL	"page-pool"
 
 #endif /* _UAPI_LINUX_NETDEV_H */
diff --git a/tools/include/uapi/linux/pkt_cls.h b/tools/include/uapi/linux/pkt_cls.h
index 3faee0199a9b..bd4b227ab4ba 100644
--- a/tools/include/uapi/linux/pkt_cls.h
+++ b/tools/include/uapi/linux/pkt_cls.h
@@ -204,37 +204,6 @@ struct tc_u32_pcnt {
 
 #define TC_U32_MAXDEPTH 8
 
-
-/* RSVP filter */
-
-enum {
-	TCA_RSVP_UNSPEC,
-	TCA_RSVP_CLASSID,
-	TCA_RSVP_DST,
-	TCA_RSVP_SRC,
-	TCA_RSVP_PINFO,
-	TCA_RSVP_POLICE,
-	TCA_RSVP_ACT,
-	__TCA_RSVP_MAX
-};
-
-#define TCA_RSVP_MAX (__TCA_RSVP_MAX - 1 )
-
-struct tc_rsvp_gpi {
-	__u32	key;
-	__u32	mask;
-	int	offset;
-};
-
-struct tc_rsvp_pinfo {
-	struct tc_rsvp_gpi dpi;
-	struct tc_rsvp_gpi spi;
-	__u8	protocol;
-	__u8	tunnelid;
-	__u8	tunnelhdr;
-	__u8	pad;
-};
-
 /* ROUTE filter */
 
 enum {
@@ -265,22 +234,6 @@ enum {
 
 #define TCA_FW_MAX (__TCA_FW_MAX - 1)
 
-/* TC index filter */
-
-enum {
-	TCA_TCINDEX_UNSPEC,
-	TCA_TCINDEX_HASH,
-	TCA_TCINDEX_MASK,
-	TCA_TCINDEX_SHIFT,
-	TCA_TCINDEX_FALL_THROUGH,
-	TCA_TCINDEX_CLASSID,
-	TCA_TCINDEX_POLICE,
-	TCA_TCINDEX_ACT,
-	__TCA_TCINDEX_MAX
-};
-
-#define TCA_TCINDEX_MAX     (__TCA_TCINDEX_MAX - 1)
-
 /* Flow filter */
 
 enum {
diff --git a/tools/include/uapi/linux/pkt_sched.h b/tools/include/uapi/linux/pkt_sched.h
index 5c903abc9fa5..587481a19433 100644
--- a/tools/include/uapi/linux/pkt_sched.h
+++ b/tools/include/uapi/linux/pkt_sched.h
@@ -457,115 +457,6 @@ enum {
 
 #define TCA_HFSC_MAX (__TCA_HFSC_MAX - 1)
 
-
-/* CBQ section */
-
-#define TC_CBQ_MAXPRIO		8
-#define TC_CBQ_MAXLEVEL		8
-#define TC_CBQ_DEF_EWMA		5
-
-struct tc_cbq_lssopt {
-	unsigned char	change;
-	unsigned char	flags;
-#define TCF_CBQ_LSS_BOUNDED	1
-#define TCF_CBQ_LSS_ISOLATED	2
-	unsigned char  	ewma_log;
-	unsigned char  	level;
-#define TCF_CBQ_LSS_FLAGS	1
-#define TCF_CBQ_LSS_EWMA	2
-#define TCF_CBQ_LSS_MAXIDLE	4
-#define TCF_CBQ_LSS_MINIDLE	8
-#define TCF_CBQ_LSS_OFFTIME	0x10
-#define TCF_CBQ_LSS_AVPKT	0x20
-	__u32		maxidle;
-	__u32		minidle;
-	__u32		offtime;
-	__u32		avpkt;
-};
-
-struct tc_cbq_wrropt {
-	unsigned char	flags;
-	unsigned char	priority;
-	unsigned char	cpriority;
-	unsigned char	__reserved;
-	__u32		allot;
-	__u32		weight;
-};
-
-struct tc_cbq_ovl {
-	unsigned char	strategy;
-#define	TC_CBQ_OVL_CLASSIC	0
-#define	TC_CBQ_OVL_DELAY	1
-#define	TC_CBQ_OVL_LOWPRIO	2
-#define	TC_CBQ_OVL_DROP		3
-#define	TC_CBQ_OVL_RCLASSIC	4
-	unsigned char	priority2;
-	__u16		pad;
-	__u32		penalty;
-};
-
-struct tc_cbq_police {
-	unsigned char	police;
-	unsigned char	__res1;
-	unsigned short	__res2;
-};
-
-struct tc_cbq_fopt {
-	__u32		split;
-	__u32		defmap;
-	__u32		defchange;
-};
-
-struct tc_cbq_xstats {
-	__u32		borrows;
-	__u32		overactions;
-	__s32		avgidle;
-	__s32		undertime;
-};
-
-enum {
-	TCA_CBQ_UNSPEC,
-	TCA_CBQ_LSSOPT,
-	TCA_CBQ_WRROPT,
-	TCA_CBQ_FOPT,
-	TCA_CBQ_OVL_STRATEGY,
-	TCA_CBQ_RATE,
-	TCA_CBQ_RTAB,
-	TCA_CBQ_POLICE,
-	__TCA_CBQ_MAX,
-};
-
-#define TCA_CBQ_MAX	(__TCA_CBQ_MAX - 1)
-
-/* dsmark section */
-
-enum {
-	TCA_DSMARK_UNSPEC,
-	TCA_DSMARK_INDICES,
-	TCA_DSMARK_DEFAULT_INDEX,
-	TCA_DSMARK_SET_TC_INDEX,
-	TCA_DSMARK_MASK,
-	TCA_DSMARK_VALUE,
-	__TCA_DSMARK_MAX,
-};
-
-#define TCA_DSMARK_MAX (__TCA_DSMARK_MAX - 1)
-
-/* ATM  section */
-
-enum {
-	TCA_ATM_UNSPEC,
-	TCA_ATM_FD,		/* file/socket descriptor */
-	TCA_ATM_PTR,		/* pointer to descriptor - later */
-	TCA_ATM_HDR,		/* LL header */
-	TCA_ATM_EXCESS,		/* excess traffic class (0 for CLP)  */
-	TCA_ATM_ADDR,		/* PVC address (for output only) */
-	TCA_ATM_STATE,		/* VC state (ATM_VS_*; for output only) */
-	__TCA_ATM_MAX,
-};
-
-#define TCA_ATM_MAX	(__TCA_ATM_MAX - 1)
-
 /* Network emulator */
 
 enum {
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index f5c48b61ab62..649560c685f1 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -219,4 +219,12 @@
  */
 #define VHOST_VDPA_RESUME		_IO(VHOST_VIRTIO, 0x7E)
 
+/* Get the group for the descriptor table including driver & device areas
+ * of a virtqueue: read index, write group in num.
+ * The virtqueue index is stored in the index field of vhost_vring_state.
+ * The group ID of the descriptor table for this specific virtqueue
+ * is returned via num field of vhost_vring_state.
+ */
+#define VHOST_VDPA_GET_VRING_DESC_GROUP	_IOWR(VHOST_VIRTIO, 0x7F,	\
+					      struct vhost_vring_state)
 #endif
diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h
index 1ac57bb7ac55..7325a12692a3 100644
--- a/tools/lib/bpf/bpf_core_read.h
+++ b/tools/lib/bpf/bpf_core_read.h
@@ -111,6 +111,38 @@ enum bpf_enum_value_kind {
 	val;								      \
 })
 
+/*
+ * Write to a bitfield, identified by s->field.
+ * This is the inverse of BPF_CORE_WRITE_BITFIELD().
+ */
+#define BPF_CORE_WRITE_BITFIELD(s, field, new_val) ({			\
+	void *p = (void *)s + __CORE_RELO(s, field, BYTE_OFFSET);	\
+	unsigned int byte_size = __CORE_RELO(s, field, BYTE_SIZE);	\
+	unsigned int lshift = __CORE_RELO(s, field, LSHIFT_U64);	\
+	unsigned int rshift = __CORE_RELO(s, field, RSHIFT_U64);	\
+	unsigned long long mask, val, nval = new_val;			\
+	unsigned int rpad = rshift - lshift;				\
+									\
+	asm volatile("" : "+r"(p));					\
+									\
+	switch (byte_size) {						\
+	case 1: val = *(unsigned char *)p; break;			\
+	case 2: val = *(unsigned short *)p; break;			\
+	case 4: val = *(unsigned int *)p; break;			\
+	case 8: val = *(unsigned long long *)p; break;			\
+	}								\
+									\
+	mask = (~0ULL << rshift) >> lshift;				\
+	val = (val & ~mask) | ((nval << rpad) & mask);			\
+									\
+	switch (byte_size) {						\
+	case 1: *(unsigned char *)p      = val; break;			\
+	case 2: *(unsigned short *)p     = val; break;			\
+	case 4: *(unsigned int *)p       = val; break;			\
+	case 8: *(unsigned long long *)p = val; break;			\
+	}								\
+})
+
 #define ___bpf_field_ref1(field)	(field)
 #define ___bpf_field_ref2(type, field)	(((typeof(type) *)0)->field)
 #define ___bpf_field_ref(args...)					    \
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index 77ceea575dc7..2324cc42b017 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -188,6 +188,9 @@ enum libbpf_tristate {
 	!!sym;											\
 })
 
+#define __arg_ctx __attribute__((btf_decl_tag("arg:ctx")))
+#define __arg_nonnull __attribute((btf_decl_tag("arg:nonnull")))
+
 #ifndef ___bpf_concat
 #define ___bpf_concat(a, b) a ## b
 #endif
diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c
index 2a62bf411bb3..b02faec748a5 100644
--- a/tools/lib/bpf/elf.c
+++ b/tools/lib/bpf/elf.c
@@ -407,7 +407,8 @@ static int symbol_cmp(const void *a, const void *b)
  * size, that needs to be released by the caller.
  */
 int elf_resolve_syms_offsets(const char *binary_path, int cnt,
-			     const char **syms, unsigned long **poffsets)
+			     const char **syms, unsigned long **poffsets,
+			     int st_type)
 {
 	int sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB };
 	int err = 0, i, cnt_done = 0;
@@ -438,7 +439,7 @@ int elf_resolve_syms_offsets(const char *binary_path, int cnt,
 		struct elf_sym_iter iter;
 		struct elf_sym *sym;
 
-		err = elf_sym_iter_new(&iter, elf_fd.elf, binary_path, sh_types[i], STT_FUNC);
+		err = elf_sym_iter_new(&iter, elf_fd.elf, binary_path, sh_types[i], st_type);
 		if (err == -ENOENT)
 			continue;
 		if (err)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e067be95da3c..c5a42ac309fd 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1503,6 +1503,16 @@ static Elf64_Sym *find_elf_var_sym(const struct bpf_object *obj, const char *nam
 	return ERR_PTR(-ENOENT);
 }
 
+static int create_placeholder_fd(void)
+{
+	int fd;
+
+	fd = ensure_good_fd(memfd_create("libbpf-placeholder-fd", MFD_CLOEXEC));
+	if (fd < 0)
+		return -errno;
+	return fd;
+}
+
 static struct bpf_map *bpf_object__add_map(struct bpf_object *obj)
 {
 	struct bpf_map *map;
@@ -1515,7 +1525,21 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj)
 
 	map = &obj->maps[obj->nr_maps++];
 	map->obj = obj;
-	map->fd = -1;
+	/* Preallocate map FD without actually creating BPF map just yet.
+	 * These map FD "placeholders" will be reused later without changing
+	 * FD value when map is actually created in the kernel.
+	 *
+	 * This is useful to be able to perform BPF program relocations
+	 * without having to create BPF maps before that step. This allows us
+	 * to finalize and load BTF very late in BPF object's loading phase,
+	 * right before BPF maps have to be created and BPF programs have to
+	 * be loaded. By having these map FD placeholders we can perform all
+	 * the sanitizations, relocations, and any other adjustments before we
+	 * start creating actual BPF kernel objects (BTF, maps, progs).
+	 */
+	map->fd = create_placeholder_fd();
+	if (map->fd < 0)
+		return ERR_PTR(map->fd);
 	map->inner_map_fd = -1;
 	map->autocreate = true;
 
@@ -2607,7 +2631,9 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 		map->inner_map = calloc(1, sizeof(*map->inner_map));
 		if (!map->inner_map)
 			return -ENOMEM;
-		map->inner_map->fd = -1;
+		map->inner_map->fd = create_placeholder_fd();
+		if (map->inner_map->fd < 0)
+			return map->inner_map->fd;
 		map->inner_map->sec_idx = sec_idx;
 		map->inner_map->name = malloc(strlen(map_name) + sizeof(".inner") + 1);
 		if (!map->inner_map->name)
@@ -3054,9 +3080,15 @@ static bool prog_needs_vmlinux_btf(struct bpf_program *prog)
 	return false;
 }
 
+static bool map_needs_vmlinux_btf(struct bpf_map *map)
+{
+	return bpf_map__is_struct_ops(map);
+}
+
 static bool obj_needs_vmlinux_btf(const struct bpf_object *obj)
 {
 	struct bpf_program *prog;
+	struct bpf_map *map;
 	int i;
 
 	/* CO-RE relocations need kernel BTF, only when btf_custom_path
@@ -3081,6 +3113,11 @@ static bool obj_needs_vmlinux_btf(const struct bpf_object *obj)
 			return true;
 	}
 
+	bpf_object__for_each_map(map, obj) {
+		if (map_needs_vmlinux_btf(map))
+			return true;
+	}
+
 	return false;
 }
 
@@ -3155,86 +3192,6 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 		}
 	}
 
-	if (!kernel_supports(obj, FEAT_BTF_DECL_TAG))
-		goto skip_exception_cb;
-	for (i = 0; i < obj->nr_programs; i++) {
-		struct bpf_program *prog = &obj->programs[i];
-		int j, k, n;
-
-		if (prog_is_subprog(obj, prog))
-			continue;
-		n = btf__type_cnt(obj->btf);
-		for (j = 1; j < n; j++) {
-			const char *str = "exception_callback:", *name;
-			size_t len = strlen(str);
-			struct btf_type *t;
-
-			t = btf_type_by_id(obj->btf, j);
-			if (!btf_is_decl_tag(t) || btf_decl_tag(t)->component_idx != -1)
-				continue;
-
-			name = btf__str_by_offset(obj->btf, t->name_off);
-			if (strncmp(name, str, len))
-				continue;
-
-			t = btf_type_by_id(obj->btf, t->type);
-			if (!btf_is_func(t) || btf_func_linkage(t) != BTF_FUNC_GLOBAL) {
-				pr_warn("prog '%s': exception_callback:<value> decl tag not applied to the main program\n",
-					prog->name);
-				return -EINVAL;
-			}
-			if (strcmp(prog->name, btf__str_by_offset(obj->btf, t->name_off)))
-				continue;
-			/* Multiple callbacks are specified for the same prog,
-			 * the verifier will eventually return an error for this
-			 * case, hence simply skip appending a subprog.
-			 */
-			if (prog->exception_cb_idx >= 0) {
-				prog->exception_cb_idx = -1;
-				break;
-			}
-
-			name += len;
-			if (str_is_empty(name)) {
-				pr_warn("prog '%s': exception_callback:<value> decl tag contains empty value\n",
-					prog->name);
-				return -EINVAL;
-			}
-
-			for (k = 0; k < obj->nr_programs; k++) {
-				struct bpf_program *subprog = &obj->programs[k];
-
-				if (!prog_is_subprog(obj, subprog))
-					continue;
-				if (strcmp(name, subprog->name))
-					continue;
-				/* Enforce non-hidden, as from verifier point of
-				 * view it expects global functions, whereas the
-				 * mark_btf_static fixes up linkage as static.
-				 */
-				if (!subprog->sym_global || subprog->mark_btf_static) {
-					pr_warn("prog '%s': exception callback %s must be a global non-hidden function\n",
-						prog->name, subprog->name);
-					return -EINVAL;
-				}
-				/* Let's see if we already saw a static exception callback with the same name */
-				if (prog->exception_cb_idx >= 0) {
-					pr_warn("prog '%s': multiple subprogs with same name as exception callback '%s'\n",
-					        prog->name, subprog->name);
-					return -EINVAL;
-				}
-				prog->exception_cb_idx = k;
-				break;
-			}
-
-			if (prog->exception_cb_idx >= 0)
-				continue;
-			pr_warn("prog '%s': cannot find exception callback '%s'\n", prog->name, name);
-			return -ENOENT;
-		}
-	}
-skip_exception_cb:
-
 	sanitize = btf_needs_sanitization(obj);
 	if (sanitize) {
 		const void *raw_data;
@@ -4344,6 +4301,8 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, Elf64_Shdr *shdr, Elf_Dat
 
 	scn = elf_sec_by_idx(obj, sec_idx);
 	scn_data = elf_sec_data(obj, scn);
+	if (!scn_data)
+		return -LIBBPF_ERRNO__FORMAT;
 
 	relo_sec_name = elf_sec_str(obj, shdr->sh_name);
 	sec_name = elf_sec_name(obj, scn);
@@ -4536,14 +4495,12 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd)
 		goto err_free_new_name;
 	}
 
-	err = zclose(map->fd);
-	if (err) {
-		err = -errno;
-		goto err_close_new_fd;
-	}
+	err = reuse_fd(map->fd, new_fd);
+	if (err)
+		goto err_free_new_name;
+
 	free(map->name);
 
-	map->fd = new_fd;
 	map->name = new_name;
 	map->def.type = info.type;
 	map->def.key_size = info.key_size;
@@ -4557,8 +4514,6 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd)
 
 	return 0;
 
-err_close_new_fd:
-	close(new_fd);
 err_free_new_name:
 	free(new_name);
 	return libbpf_err(err);
@@ -5187,12 +5142,17 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
 
 static void bpf_map__destroy(struct bpf_map *map);
 
+static bool map_is_created(const struct bpf_map *map)
+{
+	return map->obj->loaded || map->reused;
+}
+
 static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, bool is_inner)
 {
 	LIBBPF_OPTS(bpf_map_create_opts, create_attr);
 	struct bpf_map_def *def = &map->def;
 	const char *map_name = NULL;
-	int err = 0;
+	int err = 0, map_fd;
 
 	if (kernel_supports(obj, FEAT_PROG_NAME))
 		map_name = map->name;
@@ -5218,7 +5178,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 					map->name, err);
 				return err;
 			}
-			map->inner_map_fd = bpf_map__fd(map->inner_map);
+			map->inner_map_fd = map->inner_map->fd;
 		}
 		if (map->inner_map_fd >= 0)
 			create_attr.inner_map_fd = map->inner_map_fd;
@@ -5251,17 +5211,19 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 		bpf_gen__map_create(obj->gen_loader, def->type, map_name,
 				    def->key_size, def->value_size, def->max_entries,
 				    &create_attr, is_inner ? -1 : map - obj->maps);
-		/* Pretend to have valid FD to pass various fd >= 0 checks.
-		 * This fd == 0 will not be used with any syscall and will be reset to -1 eventually.
+		/* We keep pretenting we have valid FD to pass various fd >= 0
+		 * checks by just keeping original placeholder FDs in place.
+		 * See bpf_object__add_map() comment.
+		 * This placeholder fd will not be used with any syscall and
+		 * will be reset to -1 eventually.
 		 */
-		map->fd = 0;
+		map_fd = map->fd;
 	} else {
-		map->fd = bpf_map_create(def->type, map_name,
-					 def->key_size, def->value_size,
-					 def->max_entries, &create_attr);
+		map_fd = bpf_map_create(def->type, map_name,
+					def->key_size, def->value_size,
+					def->max_entries, &create_attr);
 	}
-	if (map->fd < 0 && (create_attr.btf_key_type_id ||
-			    create_attr.btf_value_type_id)) {
+	if (map_fd < 0 && (create_attr.btf_key_type_id || create_attr.btf_value_type_id)) {
 		char *cp, errmsg[STRERR_BUFSIZE];
 
 		err = -errno;
@@ -5273,13 +5235,11 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 		create_attr.btf_value_type_id = 0;
 		map->btf_key_type_id = 0;
 		map->btf_value_type_id = 0;
-		map->fd = bpf_map_create(def->type, map_name,
-					 def->key_size, def->value_size,
-					 def->max_entries, &create_attr);
+		map_fd = bpf_map_create(def->type, map_name,
+					def->key_size, def->value_size,
+					def->max_entries, &create_attr);
 	}
 
-	err = map->fd < 0 ? -errno : 0;
-
 	if (bpf_map_type__is_map_in_map(def->type) && map->inner_map) {
 		if (obj->gen_loader)
 			map->inner_map->fd = -1;
@@ -5287,7 +5247,19 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 		zfree(&map->inner_map);
 	}
 
-	return err;
+	if (map_fd < 0)
+		return map_fd;
+
+	/* obj->gen_loader case, prevent reuse_fd() from closing map_fd */
+	if (map->fd == map_fd)
+		return 0;
+
+	/* Keep placeholder FD value but now point it to the BPF map object.
+	 * This way everything that relied on this map's FD (e.g., relocated
+	 * ldimm64 instructions) will stay valid and won't need adjustments.
+	 * map->fd stays valid but now point to what map_fd points to.
+	 */
+	return reuse_fd(map->fd, map_fd);
 }
 
 static int init_map_in_map_slots(struct bpf_object *obj, struct bpf_map *map)
@@ -5301,7 +5273,7 @@ static int init_map_in_map_slots(struct bpf_object *obj, struct bpf_map *map)
 			continue;
 
 		targ_map = map->init_slots[i];
-		fd = bpf_map__fd(targ_map);
+		fd = targ_map->fd;
 
 		if (obj->gen_loader) {
 			bpf_gen__populate_outer_map(obj->gen_loader,
@@ -5371,10 +5343,8 @@ static int bpf_object_init_prog_arrays(struct bpf_object *obj)
 			continue;
 
 		err = init_prog_array_slots(obj, map);
-		if (err < 0) {
-			zclose(map->fd);
+		if (err < 0)
 			return err;
-		}
 	}
 	return 0;
 }
@@ -5452,7 +5422,7 @@ retry:
 			}
 		}
 
-		if (map->fd >= 0) {
+		if (map->reused) {
 			pr_debug("map '%s': skipping creation (preset fd=%d)\n",
 				 map->name, map->fd);
 		} else {
@@ -5465,25 +5435,20 @@ retry:
 
 			if (bpf_map__is_internal(map)) {
 				err = bpf_object__populate_internal_map(obj, map);
-				if (err < 0) {
-					zclose(map->fd);
+				if (err < 0)
 					goto err_out;
-				}
 			}
 
 			if (map->init_slots_sz && map->def.type != BPF_MAP_TYPE_PROG_ARRAY) {
 				err = init_map_in_map_slots(obj, map);
-				if (err < 0) {
-					zclose(map->fd);
+				if (err < 0)
 					goto err_out;
-				}
 			}
 		}
 
 		if (map->pin_path && !map->pinned) {
 			err = bpf_map__pin(map, NULL);
 			if (err) {
-				zclose(map->fd);
 				if (!retried && err == -EEXIST) {
 					retried = true;
 					goto retry;
@@ -6216,7 +6181,7 @@ reloc_prog_func_and_line_info(const struct bpf_object *obj,
 	int err;
 
 	/* no .BTF.ext relocation if .BTF.ext is missing or kernel doesn't
-	 * supprot func/line info
+	 * support func/line info
 	 */
 	if (!obj->btf_ext || !kernel_supports(obj, FEAT_BTF_FUNC))
 		return 0;
@@ -6616,8 +6581,329 @@ static void bpf_object__sort_relos(struct bpf_object *obj)
 	}
 }
 
-static int
-bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
+static int bpf_prog_assign_exc_cb(struct bpf_object *obj, struct bpf_program *prog)
+{
+	const char *str = "exception_callback:";
+	size_t pfx_len = strlen(str);
+	int i, j, n;
+
+	if (!obj->btf || !kernel_supports(obj, FEAT_BTF_DECL_TAG))
+		return 0;
+
+	n = btf__type_cnt(obj->btf);
+	for (i = 1; i < n; i++) {
+		const char *name;
+		struct btf_type *t;
+
+		t = btf_type_by_id(obj->btf, i);
+		if (!btf_is_decl_tag(t) || btf_decl_tag(t)->component_idx != -1)
+			continue;
+
+		name = btf__str_by_offset(obj->btf, t->name_off);
+		if (strncmp(name, str, pfx_len) != 0)
+			continue;
+
+		t = btf_type_by_id(obj->btf, t->type);
+		if (!btf_is_func(t) || btf_func_linkage(t) != BTF_FUNC_GLOBAL) {
+			pr_warn("prog '%s': exception_callback:<value> decl tag not applied to the main program\n",
+				prog->name);
+			return -EINVAL;
+		}
+		if (strcmp(prog->name, btf__str_by_offset(obj->btf, t->name_off)) != 0)
+			continue;
+		/* Multiple callbacks are specified for the same prog,
+		 * the verifier will eventually return an error for this
+		 * case, hence simply skip appending a subprog.
+		 */
+		if (prog->exception_cb_idx >= 0) {
+			prog->exception_cb_idx = -1;
+			break;
+		}
+
+		name += pfx_len;
+		if (str_is_empty(name)) {
+			pr_warn("prog '%s': exception_callback:<value> decl tag contains empty value\n",
+				prog->name);
+			return -EINVAL;
+		}
+
+		for (j = 0; j < obj->nr_programs; j++) {
+			struct bpf_program *subprog = &obj->programs[j];
+
+			if (!prog_is_subprog(obj, subprog))
+				continue;
+			if (strcmp(name, subprog->name) != 0)
+				continue;
+			/* Enforce non-hidden, as from verifier point of
+			 * view it expects global functions, whereas the
+			 * mark_btf_static fixes up linkage as static.
+			 */
+			if (!subprog->sym_global || subprog->mark_btf_static) {
+				pr_warn("prog '%s': exception callback %s must be a global non-hidden function\n",
+					prog->name, subprog->name);
+				return -EINVAL;
+			}
+			/* Let's see if we already saw a static exception callback with the same name */
+			if (prog->exception_cb_idx >= 0) {
+				pr_warn("prog '%s': multiple subprogs with same name as exception callback '%s'\n",
+					prog->name, subprog->name);
+				return -EINVAL;
+			}
+			prog->exception_cb_idx = j;
+			break;
+		}
+
+		if (prog->exception_cb_idx >= 0)
+			continue;
+
+		pr_warn("prog '%s': cannot find exception callback '%s'\n", prog->name, name);
+		return -ENOENT;
+	}
+
+	return 0;
+}
+
+static struct {
+	enum bpf_prog_type prog_type;
+	const char *ctx_name;
+} global_ctx_map[] = {
+	{ BPF_PROG_TYPE_CGROUP_DEVICE,           "bpf_cgroup_dev_ctx" },
+	{ BPF_PROG_TYPE_CGROUP_SKB,              "__sk_buff" },
+	{ BPF_PROG_TYPE_CGROUP_SOCK,             "bpf_sock" },
+	{ BPF_PROG_TYPE_CGROUP_SOCK_ADDR,        "bpf_sock_addr" },
+	{ BPF_PROG_TYPE_CGROUP_SOCKOPT,          "bpf_sockopt" },
+	{ BPF_PROG_TYPE_CGROUP_SYSCTL,           "bpf_sysctl" },
+	{ BPF_PROG_TYPE_FLOW_DISSECTOR,          "__sk_buff" },
+	{ BPF_PROG_TYPE_KPROBE,                  "bpf_user_pt_regs_t" },
+	{ BPF_PROG_TYPE_LWT_IN,                  "__sk_buff" },
+	{ BPF_PROG_TYPE_LWT_OUT,                 "__sk_buff" },
+	{ BPF_PROG_TYPE_LWT_SEG6LOCAL,           "__sk_buff" },
+	{ BPF_PROG_TYPE_LWT_XMIT,                "__sk_buff" },
+	{ BPF_PROG_TYPE_NETFILTER,               "bpf_nf_ctx" },
+	{ BPF_PROG_TYPE_PERF_EVENT,              "bpf_perf_event_data" },
+	{ BPF_PROG_TYPE_RAW_TRACEPOINT,          "bpf_raw_tracepoint_args" },
+	{ BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, "bpf_raw_tracepoint_args" },
+	{ BPF_PROG_TYPE_SCHED_ACT,               "__sk_buff" },
+	{ BPF_PROG_TYPE_SCHED_CLS,               "__sk_buff" },
+	{ BPF_PROG_TYPE_SK_LOOKUP,               "bpf_sk_lookup" },
+	{ BPF_PROG_TYPE_SK_MSG,                  "sk_msg_md" },
+	{ BPF_PROG_TYPE_SK_REUSEPORT,            "sk_reuseport_md" },
+	{ BPF_PROG_TYPE_SK_SKB,                  "__sk_buff" },
+	{ BPF_PROG_TYPE_SOCK_OPS,                "bpf_sock_ops" },
+	{ BPF_PROG_TYPE_SOCKET_FILTER,           "__sk_buff" },
+	{ BPF_PROG_TYPE_XDP,                     "xdp_md" },
+	/* all other program types don't have "named" context structs */
+};
+
+static int clone_func_btf_info(struct btf *btf, int orig_fn_id, struct bpf_program *prog)
+{
+	int fn_id, fn_proto_id, ret_type_id, orig_proto_id;
+	int i, err, arg_cnt, fn_name_off, linkage;
+	struct btf_type *fn_t, *fn_proto_t, *t;
+	struct btf_param *p;
+
+	/* caller already validated FUNC -> FUNC_PROTO validity */
+	fn_t = btf_type_by_id(btf, orig_fn_id);
+	fn_proto_t = btf_type_by_id(btf, fn_t->type);
+
+	/* Note that each btf__add_xxx() operation invalidates
+	 * all btf_type and string pointers, so we need to be
+	 * very careful when cloning BTF types. BTF type
+	 * pointers have to be always refetched. And to avoid
+	 * problems with invalidated string pointers, we
+	 * add empty strings initially, then just fix up
+	 * name_off offsets in place. Offsets are stable for
+	 * existing strings, so that works out.
+	 */
+	fn_name_off = fn_t->name_off; /* we are about to invalidate fn_t */
+	linkage = btf_func_linkage(fn_t);
+	orig_proto_id = fn_t->type; /* original FUNC_PROTO ID */
+	ret_type_id = fn_proto_t->type; /* fn_proto_t will be invalidated */
+	arg_cnt = btf_vlen(fn_proto_t);
+
+	/* clone FUNC_PROTO and its params */
+	fn_proto_id = btf__add_func_proto(btf, ret_type_id);
+	if (fn_proto_id < 0)
+		return -EINVAL;
+
+	for (i = 0; i < arg_cnt; i++) {
+		int name_off;
+
+		/* copy original parameter data */
+		t = btf_type_by_id(btf, orig_proto_id);
+		p = &btf_params(t)[i];
+		name_off = p->name_off;
+
+		err = btf__add_func_param(btf, "", p->type);
+		if (err)
+			return err;
+
+		fn_proto_t = btf_type_by_id(btf, fn_proto_id);
+		p = &btf_params(fn_proto_t)[i];
+		p->name_off = name_off; /* use remembered str offset */
+	}
+
+	/* clone FUNC now, btf__add_func() enforces non-empty name, so use
+	 * entry program's name as a placeholder, which we replace immediately
+	 * with original name_off
+	 */
+	fn_id = btf__add_func(btf, prog->name, linkage, fn_proto_id);
+	if (fn_id < 0)
+		return -EINVAL;
+
+	fn_t = btf_type_by_id(btf, fn_id);
+	fn_t->name_off = fn_name_off; /* reuse original string */
+
+	return fn_id;
+}
+
+/* Check if main program or global subprog's function prototype has `arg:ctx`
+ * argument tags, and, if necessary, substitute correct type to match what BPF
+ * verifier would expect, taking into account specific program type. This
+ * allows to support __arg_ctx tag transparently on old kernels that don't yet
+ * have a native support for it in the verifier, making user's life much
+ * easier.
+ */
+static int bpf_program_fixup_func_info(struct bpf_object *obj, struct bpf_program *prog)
+{
+	const char *ctx_name = NULL, *ctx_tag = "arg:ctx";
+	struct bpf_func_info_min *func_rec;
+	struct btf_type *fn_t, *fn_proto_t;
+	struct btf *btf = obj->btf;
+	const struct btf_type *t;
+	struct btf_param *p;
+	int ptr_id = 0, struct_id, tag_id, orig_fn_id;
+	int i, n, arg_idx, arg_cnt, err, rec_idx;
+	int *orig_ids;
+
+	/* no .BTF.ext, no problem */
+	if (!obj->btf_ext || !prog->func_info)
+		return 0;
+
+	/* some BPF program types just don't have named context structs, so
+	 * this fallback mechanism doesn't work for them
+	 */
+	for (i = 0; i < ARRAY_SIZE(global_ctx_map); i++) {
+		if (global_ctx_map[i].prog_type != prog->type)
+			continue;
+		ctx_name = global_ctx_map[i].ctx_name;
+		break;
+	}
+	if (!ctx_name)
+		return 0;
+
+	/* remember original func BTF IDs to detect if we already cloned them */
+	orig_ids = calloc(prog->func_info_cnt, sizeof(*orig_ids));
+	if (!orig_ids)
+		return -ENOMEM;
+	for (i = 0; i < prog->func_info_cnt; i++) {
+		func_rec = prog->func_info + prog->func_info_rec_size * i;
+		orig_ids[i] = func_rec->type_id;
+	}
+
+	/* go through each DECL_TAG with "arg:ctx" and see if it points to one
+	 * of our subprogs; if yes and subprog is global and needs adjustment,
+	 * clone and adjust FUNC -> FUNC_PROTO combo
+	 */
+	for (i = 1, n = btf__type_cnt(btf); i < n; i++) {
+		/* only DECL_TAG with "arg:ctx" value are interesting */
+		t = btf__type_by_id(btf, i);
+		if (!btf_is_decl_tag(t))
+			continue;
+		if (strcmp(btf__str_by_offset(btf, t->name_off), ctx_tag) != 0)
+			continue;
+
+		/* only global funcs need adjustment, if at all */
+		orig_fn_id = t->type;
+		fn_t = btf_type_by_id(btf, orig_fn_id);
+		if (!btf_is_func(fn_t) || btf_func_linkage(fn_t) != BTF_FUNC_GLOBAL)
+			continue;
+
+		/* sanity check FUNC -> FUNC_PROTO chain, just in case */
+		fn_proto_t = btf_type_by_id(btf, fn_t->type);
+		if (!fn_proto_t || !btf_is_func_proto(fn_proto_t))
+			continue;
+
+		/* find corresponding func_info record */
+		func_rec = NULL;
+		for (rec_idx = 0; rec_idx < prog->func_info_cnt; rec_idx++) {
+			if (orig_ids[rec_idx] == t->type) {
+				func_rec = prog->func_info + prog->func_info_rec_size * rec_idx;
+				break;
+			}
+		}
+		/* current main program doesn't call into this subprog */
+		if (!func_rec)
+			continue;
+
+		/* some more sanity checking of DECL_TAG */
+		arg_cnt = btf_vlen(fn_proto_t);
+		arg_idx = btf_decl_tag(t)->component_idx;
+		if (arg_idx < 0 || arg_idx >= arg_cnt)
+			continue;
+
+		/* check if existing parameter already matches verifier expectations */
+		p = &btf_params(fn_proto_t)[arg_idx];
+		t = skip_mods_and_typedefs(btf, p->type, NULL);
+		if (btf_is_ptr(t) &&
+		    (t = skip_mods_and_typedefs(btf, t->type, NULL)) &&
+		    btf_is_struct(t) &&
+		    strcmp(btf__str_by_offset(btf, t->name_off), ctx_name) == 0) {
+			continue; /* no need for fix up */
+		}
+
+		/* clone fn/fn_proto, unless we already did it for another arg */
+		if (func_rec->type_id == orig_fn_id) {
+			int fn_id;
+
+			fn_id = clone_func_btf_info(btf, orig_fn_id, prog);
+			if (fn_id < 0) {
+				err = fn_id;
+				goto err_out;
+			}
+
+			/* point func_info record to a cloned FUNC type */
+			func_rec->type_id = fn_id;
+		}
+
+		/* create PTR -> STRUCT type chain to mark PTR_TO_CTX argument;
+		 * we do it just once per main BPF program, as all global
+		 * funcs share the same program type, so need only PTR ->
+		 * STRUCT type chain
+		 */
+		if (ptr_id == 0) {
+			struct_id = btf__add_struct(btf, ctx_name, 0);
+			ptr_id = btf__add_ptr(btf, struct_id);
+			if (ptr_id < 0 || struct_id < 0) {
+				err = -EINVAL;
+				goto err_out;
+			}
+		}
+
+		/* for completeness, clone DECL_TAG and point it to cloned param */
+		tag_id = btf__add_decl_tag(btf, ctx_tag, func_rec->type_id, arg_idx);
+		if (tag_id < 0) {
+			err = -EINVAL;
+			goto err_out;
+		}
+
+		/* all the BTF manipulations invalidated pointers, refetch them */
+		fn_t = btf_type_by_id(btf, func_rec->type_id);
+		fn_proto_t = btf_type_by_id(btf, fn_t->type);
+
+		/* fix up type ID pointed to by param */
+		p = &btf_params(fn_proto_t)[arg_idx];
+		p->type = ptr_id;
+	}
+
+	free(orig_ids);
+	return 0;
+err_out:
+	free(orig_ids);
+	return err;
+}
+
+static int bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 {
 	struct bpf_program *prog;
 	size_t i, j;
@@ -6676,6 +6962,9 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 			return err;
 		}
 
+		err = bpf_prog_assign_exc_cb(obj, prog);
+		if (err)
+			return err;
 		/* Now, also append exception callback if it has not been done already. */
 		if (prog->exception_cb_idx >= 0) {
 			struct bpf_program *subprog = &obj->programs[prog->exception_cb_idx];
@@ -6695,19 +6984,28 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 			}
 		}
 	}
-	/* Process data relos for main programs */
 	for (i = 0; i < obj->nr_programs; i++) {
 		prog = &obj->programs[i];
 		if (prog_is_subprog(obj, prog))
 			continue;
 		if (!prog->autoload)
 			continue;
+
+		/* Process data relos for main programs */
 		err = bpf_object__relocate_data(obj, prog);
 		if (err) {
 			pr_warn("prog '%s': failed to relocate data references: %d\n",
 				prog->name, err);
 			return err;
 		}
+
+		/* Fix up .BTF.ext information, if necessary */
+		err = bpf_program_fixup_func_info(obj, prog);
+		if (err) {
+			pr_warn("prog '%s': failed to perform .BTF.ext fix ups: %d\n",
+				prog->name, err);
+			return err;
+		}
 	}
 
 	return 0;
@@ -7037,7 +7335,7 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog
 	load_attr.prog_ifindex = prog->prog_ifindex;
 
 	/* specify func_info/line_info only if kernel supports them */
-	btf_fd = bpf_object__btf_fd(obj);
+	btf_fd = btf__fd(obj->btf);
 	if (btf_fd >= 0 && kernel_supports(obj, FEAT_BTF_FUNC)) {
 		load_attr.prog_btf_fd = btf_fd;
 		load_attr.func_info = prog->func_info;
@@ -7122,7 +7420,7 @@ retry_load:
 				if (map->libbpf_type != LIBBPF_MAP_RODATA)
 					continue;
 
-				if (bpf_prog_bind_map(ret, bpf_map__fd(map), NULL)) {
+				if (bpf_prog_bind_map(ret, map->fd, NULL)) {
 					cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 					pr_warn("prog '%s': failed to bind map '%s': %s\n",
 						prog->name, map->real_name, cp);
@@ -8054,11 +8352,11 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch
 	err = bpf_object__probe_loading(obj);
 	err = err ? : bpf_object__load_vmlinux_btf(obj, false);
 	err = err ? : bpf_object__resolve_externs(obj, obj->kconfig);
-	err = err ? : bpf_object__sanitize_and_load_btf(obj);
 	err = err ? : bpf_object__sanitize_maps(obj);
 	err = err ? : bpf_object__init_kern_struct_ops_maps(obj);
-	err = err ? : bpf_object__create_maps(obj);
 	err = err ? : bpf_object__relocate(obj, obj->btf_custom_path ? : target_btf_path);
+	err = err ? : bpf_object__sanitize_and_load_btf(obj);
+	err = err ? : bpf_object__create_maps(obj);
 	err = err ? : bpf_object__load_progs(obj, extra_log_level);
 	err = err ? : bpf_object_init_prog_arrays(obj);
 	err = err ? : bpf_object_prepare_struct_ops(obj);
@@ -8067,8 +8365,6 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch
 		/* reset FDs */
 		if (obj->btf)
 			btf__set_fd(obj->btf, -1);
-		for (i = 0; i < obj->nr_maps; i++)
-			obj->maps[i].fd = -1;
 		if (!err)
 			err = bpf_gen__finish(obj->gen_loader, obj->nr_programs, obj->nr_maps);
 	}
@@ -9588,7 +9884,11 @@ int libbpf_attach_type_by_name(const char *name,
 
 int bpf_map__fd(const struct bpf_map *map)
 {
-	return map ? map->fd : libbpf_err(-EINVAL);
+	if (!map)
+		return libbpf_err(-EINVAL);
+	if (!map_is_created(map))
+		return -1;
+	return map->fd;
 }
 
 static bool map_uses_real_name(const struct bpf_map *map)
@@ -9624,7 +9924,7 @@ enum bpf_map_type bpf_map__type(const struct bpf_map *map)
 
 int bpf_map__set_type(struct bpf_map *map, enum bpf_map_type type)
 {
-	if (map->fd >= 0)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 	map->def.type = type;
 	return 0;
@@ -9637,7 +9937,7 @@ __u32 bpf_map__map_flags(const struct bpf_map *map)
 
 int bpf_map__set_map_flags(struct bpf_map *map, __u32 flags)
 {
-	if (map->fd >= 0)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 	map->def.map_flags = flags;
 	return 0;
@@ -9650,7 +9950,7 @@ __u64 bpf_map__map_extra(const struct bpf_map *map)
 
 int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra)
 {
-	if (map->fd >= 0)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 	map->map_extra = map_extra;
 	return 0;
@@ -9663,7 +9963,7 @@ __u32 bpf_map__numa_node(const struct bpf_map *map)
 
 int bpf_map__set_numa_node(struct bpf_map *map, __u32 numa_node)
 {
-	if (map->fd >= 0)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 	map->numa_node = numa_node;
 	return 0;
@@ -9676,7 +9976,7 @@ __u32 bpf_map__key_size(const struct bpf_map *map)
 
 int bpf_map__set_key_size(struct bpf_map *map, __u32 size)
 {
-	if (map->fd >= 0)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 	map->def.key_size = size;
 	return 0;
@@ -9760,7 +10060,7 @@ static int map_btf_datasec_resize(struct bpf_map *map, __u32 size)
 
 int bpf_map__set_value_size(struct bpf_map *map, __u32 size)
 {
-	if (map->fd >= 0)
+	if (map->obj->loaded || map->reused)
 		return libbpf_err(-EBUSY);
 
 	if (map->mmaped) {
@@ -9801,8 +10101,11 @@ __u32 bpf_map__btf_value_type_id(const struct bpf_map *map)
 int bpf_map__set_initial_value(struct bpf_map *map,
 			       const void *data, size_t size)
 {
+	if (map->obj->loaded || map->reused)
+		return libbpf_err(-EBUSY);
+
 	if (!map->mmaped || map->libbpf_type == LIBBPF_MAP_KCONFIG ||
-	    size != map->def.value_size || map->fd >= 0)
+	    size != map->def.value_size)
 		return libbpf_err(-EINVAL);
 
 	memcpy(map->mmaped, data, size);
@@ -9829,7 +10132,7 @@ __u32 bpf_map__ifindex(const struct bpf_map *map)
 
 int bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
 {
-	if (map->fd >= 0)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 	map->map_ifindex = ifindex;
 	return 0;
@@ -9934,7 +10237,7 @@ bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name)
 static int validate_map_op(const struct bpf_map *map, size_t key_sz,
 			   size_t value_sz, bool check_value_sz)
 {
-	if (map->fd <= 0)
+	if (!map_is_created(map)) /* map is not yet created */
 		return -ENOENT;
 
 	if (map->def.key_size != key_sz) {
@@ -11447,7 +11750,7 @@ bpf_program__attach_uprobe_multi(const struct bpf_program *prog,
 			return libbpf_err_ptr(err);
 		offsets = resolved_offsets;
 	} else if (syms) {
-		err = elf_resolve_syms_offsets(path, cnt, syms, &resolved_offsets);
+		err = elf_resolve_syms_offsets(path, cnt, syms, &resolved_offsets, STT_FUNC);
 		if (err < 0)
 			return libbpf_err_ptr(err);
 		offsets = resolved_offsets;
@@ -12387,7 +12690,7 @@ int bpf_link__update_map(struct bpf_link *link, const struct bpf_map *map)
 	__u32 zero = 0;
 	int err;
 
-	if (!bpf_map__is_struct_ops(map) || map->fd < 0)
+	if (!bpf_map__is_struct_ops(map) || !map_is_created(map))
 		return -EINVAL;
 
 	st_ops_link = container_of(link, struct bpf_link_struct_ops, link);
@@ -13291,7 +13594,7 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s)
 	for (i = 0; i < s->map_cnt; i++) {
 		struct bpf_map *map = *s->maps[i].map;
 		size_t mmap_sz = bpf_map_mmap_sz(map->def.value_size, map->def.max_entries);
-		int prot, map_fd = bpf_map__fd(map);
+		int prot, map_fd = map->fd;
 		void **mmaped = s->maps[i].mmaped;
 
 		if (!mmaped)
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index b52dc28dc8af..91c5aef7dae7 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -409,3 +409,6 @@ LIBBPF_1.3.0 {
 		ring__size;
 		ring_buffer__ring;
 } LIBBPF_1.2.0;
+
+LIBBPF_1.4.0 {
+} LIBBPF_1.3.0;
diff --git a/tools/lib/bpf/libbpf_common.h b/tools/lib/bpf/libbpf_common.h
index b7060f254486..8fe248e14eb6 100644
--- a/tools/lib/bpf/libbpf_common.h
+++ b/tools/lib/bpf/libbpf_common.h
@@ -79,11 +79,14 @@
  */
 #define LIBBPF_OPTS_RESET(NAME, ...)					    \
 	do {								    \
-		memset(&NAME, 0, sizeof(NAME));				    \
-		NAME = (typeof(NAME)) {					    \
-			.sz = sizeof(NAME),				    \
-			__VA_ARGS__					    \
-		};							    \
+		typeof(NAME) ___##NAME = ({ 				    \
+			memset(&___##NAME, 0, sizeof(NAME));		    \
+			(typeof(NAME)) {				    \
+				.sz = sizeof(NAME),			    \
+				__VA_ARGS__				    \
+			};						    \
+		});							    \
+		memcpy(&NAME, &___##NAME, sizeof(NAME));		    \
 	} while (0)
 
 #endif /* __LIBBPF_LIBBPF_COMMON_H */
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index f0f08635adb0..27e4e320e1a6 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -555,6 +555,20 @@ static inline int ensure_good_fd(int fd)
 	return fd;
 }
 
+/* Point *fixed_fd* to the same file that *tmp_fd* points to.
+ * Regardless of success, *tmp_fd* is closed.
+ * Whatever *fixed_fd* pointed to is closed silently.
+ */
+static inline int reuse_fd(int fixed_fd, int tmp_fd)
+{
+	int err;
+
+	err = dup2(tmp_fd, fixed_fd);
+	err = err < 0 ? -errno : 0;
+	close(tmp_fd); /* clean up temporary FD */
+	return err;
+}
+
 /* The following two functions are exposed to bpftool */
 int bpf_core_add_cands(struct bpf_core_cand *local_cand,
 		       size_t local_essent_len,
@@ -594,7 +608,8 @@ int elf_open(const char *binary_path, struct elf_fd *elf_fd);
 void elf_close(struct elf_fd *elf_fd);
 
 int elf_resolve_syms_offsets(const char *binary_path, int cnt,
-			     const char **syms, unsigned long **poffsets);
+			     const char **syms, unsigned long **poffsets,
+			     int st_type);
 int elf_resolve_pattern_offsets(const char *binary_path, const char *pattern,
 				 unsigned long **poffsets, size_t *pcnt);
 
diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h
index 290411ddb39e..e783a47da815 100644
--- a/tools/lib/bpf/libbpf_version.h
+++ b/tools/lib/bpf/libbpf_version.h
@@ -4,6 +4,6 @@
 #define __LIBBPF_VERSION_H
 
 #define LIBBPF_MAJOR_VERSION 1
-#define LIBBPF_MINOR_VERSION 3
+#define LIBBPF_MINOR_VERSION 4
 
 #endif /* __LIBBPF_VERSION_H */
diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
index 5ced96d99f8c..16bca56002ab 100644
--- a/tools/lib/bpf/linker.c
+++ b/tools/lib/bpf/linker.c
@@ -719,13 +719,28 @@ static int linker_sanity_check_elf(struct src_obj *obj)
 			return -EINVAL;
 		}
 
-		if (sec->shdr->sh_addralign && !is_pow_of_2(sec->shdr->sh_addralign))
+		if (is_dwarf_sec_name(sec->sec_name))
+			continue;
+
+		if (sec->shdr->sh_addralign && !is_pow_of_2(sec->shdr->sh_addralign)) {
+			pr_warn("ELF section #%zu alignment %llu is non pow-of-2 alignment in %s\n",
+				sec->sec_idx, (long long unsigned)sec->shdr->sh_addralign,
+				obj->filename);
 			return -EINVAL;
-		if (sec->shdr->sh_addralign != sec->data->d_align)
+		}
+		if (sec->shdr->sh_addralign != sec->data->d_align) {
+			pr_warn("ELF section #%zu has inconsistent alignment addr=%llu != d=%llu in %s\n",
+				sec->sec_idx, (long long unsigned)sec->shdr->sh_addralign,
+				(long long unsigned)sec->data->d_align, obj->filename);
 			return -EINVAL;
+		}
 
-		if (sec->shdr->sh_size != sec->data->d_size)
+		if (sec->shdr->sh_size != sec->data->d_size) {
+			pr_warn("ELF section #%zu has inconsistent section size sh=%llu != d=%llu in %s\n",
+				sec->sec_idx, (long long unsigned)sec->shdr->sh_size,
+				(long long unsigned)sec->data->d_size, obj->filename);
 			return -EINVAL;
+		}
 
 		switch (sec->shdr->sh_type) {
 		case SHT_SYMTAB:
@@ -737,8 +752,12 @@ static int linker_sanity_check_elf(struct src_obj *obj)
 			break;
 		case SHT_PROGBITS:
 			if (sec->shdr->sh_flags & SHF_EXECINSTR) {
-				if (sec->shdr->sh_size % sizeof(struct bpf_insn) != 0)
+				if (sec->shdr->sh_size % sizeof(struct bpf_insn) != 0) {
+					pr_warn("ELF section #%zu has unexpected size alignment %llu in %s\n",
+						sec->sec_idx, (long long unsigned)sec->shdr->sh_size,
+						obj->filename);
 					return -EINVAL;
+				}
 			}
 			break;
 		case SHT_NOBITS:
diff --git a/tools/net/ynl/Makefile b/tools/net/ynl/Makefile
index d664b36deb5b..da1aa10bbcc3 100644
--- a/tools/net/ynl/Makefile
+++ b/tools/net/ynl/Makefile
@@ -4,6 +4,8 @@ SUBDIRS = lib generated samples
 
 all: $(SUBDIRS)
 
+samples: | lib generated
+
 $(SUBDIRS):
 	@if [ -f "$@/Makefile" ] ; then \
 		$(MAKE) -C $@ ; \
diff --git a/tools/net/ynl/Makefile.deps b/tools/net/ynl/Makefile.deps
index 64d139400db1..3110f84dd029 100644
--- a/tools/net/ynl/Makefile.deps
+++ b/tools/net/ynl/Makefile.deps
@@ -18,4 +18,4 @@ CFLAGS_devlink:=$(call get_hdr_inc,_LINUX_DEVLINK_H_,devlink.h)
 CFLAGS_ethtool:=$(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_H_,ethtool_netlink.h)
 CFLAGS_handshake:=$(call get_hdr_inc,_LINUX_HANDSHAKE_H,handshake.h)
 CFLAGS_netdev:=$(call get_hdr_inc,_LINUX_NETDEV_H,netdev.h)
-CFLAGS_nfsd:=$(call get_hdr_inc,_LINUX_NFSD_H,nfsd.h)
+CFLAGS_nfsd:=$(call get_hdr_inc,_LINUX_NFSD_NETLINK_H,nfsd_netlink.h)
diff --git a/tools/net/ynl/generated/.gitignore b/tools/net/ynl/generated/.gitignore
new file mode 100644
index 000000000000..ade488626d26
--- /dev/null
+++ b/tools/net/ynl/generated/.gitignore
@@ -0,0 +1,2 @@
+*-user.c
+*-user.h
diff --git a/tools/net/ynl/generated/devlink-user.c b/tools/net/ynl/generated/devlink-user.c
deleted file mode 100644
index bc5065bd99b2..000000000000
--- a/tools/net/ynl/generated/devlink-user.c
+++ /dev/null
@@ -1,6835 +0,0 @@
-// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
-/* Do not edit directly, auto-generated from: */
-/*	Documentation/netlink/specs/devlink.yaml */
-/* YNL-GEN user source */
-
-#include <stdlib.h>
-#include <string.h>
-#include "devlink-user.h"
-#include "ynl.h"
-#include <linux/devlink.h>
-
-#include <libmnl/libmnl.h>
-#include <linux/genetlink.h>
-
-/* Enums */
-static const char * const devlink_op_strmap[] = {
-	[3] = "get",
-	[7] = "port-get",
-	[DEVLINK_CMD_PORT_NEW] = "port-new",
-	[13] = "sb-get",
-	[17] = "sb-pool-get",
-	[21] = "sb-port-pool-get",
-	[25] = "sb-tc-pool-bind-get",
-	[DEVLINK_CMD_ESWITCH_GET] = "eswitch-get",
-	[DEVLINK_CMD_DPIPE_TABLE_GET] = "dpipe-table-get",
-	[DEVLINK_CMD_DPIPE_ENTRIES_GET] = "dpipe-entries-get",
-	[DEVLINK_CMD_DPIPE_HEADERS_GET] = "dpipe-headers-get",
-	[DEVLINK_CMD_RESOURCE_DUMP] = "resource-dump",
-	[DEVLINK_CMD_RELOAD] = "reload",
-	[DEVLINK_CMD_PARAM_GET] = "param-get",
-	[DEVLINK_CMD_REGION_GET] = "region-get",
-	[DEVLINK_CMD_REGION_NEW] = "region-new",
-	[DEVLINK_CMD_REGION_READ] = "region-read",
-	[DEVLINK_CMD_PORT_PARAM_GET] = "port-param-get",
-	[DEVLINK_CMD_INFO_GET] = "info-get",
-	[DEVLINK_CMD_HEALTH_REPORTER_GET] = "health-reporter-get",
-	[DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET] = "health-reporter-dump-get",
-	[63] = "trap-get",
-	[67] = "trap-group-get",
-	[71] = "trap-policer-get",
-	[76] = "rate-get",
-	[80] = "linecard-get",
-	[DEVLINK_CMD_SELFTESTS_GET] = "selftests-get",
-};
-
-const char *devlink_op_str(int op)
-{
-	if (op < 0 || op >= (int)MNL_ARRAY_SIZE(devlink_op_strmap))
-		return NULL;
-	return devlink_op_strmap[op];
-}
-
-static const char * const devlink_sb_pool_type_strmap[] = {
-	[0] = "ingress",
-	[1] = "egress",
-};
-
-const char *devlink_sb_pool_type_str(enum devlink_sb_pool_type value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_sb_pool_type_strmap))
-		return NULL;
-	return devlink_sb_pool_type_strmap[value];
-}
-
-static const char * const devlink_port_type_strmap[] = {
-	[0] = "notset",
-	[1] = "auto",
-	[2] = "eth",
-	[3] = "ib",
-};
-
-const char *devlink_port_type_str(enum devlink_port_type value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_port_type_strmap))
-		return NULL;
-	return devlink_port_type_strmap[value];
-}
-
-static const char * const devlink_port_flavour_strmap[] = {
-	[0] = "physical",
-	[1] = "cpu",
-	[2] = "dsa",
-	[3] = "pci_pf",
-	[4] = "pci_vf",
-	[5] = "virtual",
-	[6] = "unused",
-	[7] = "pci_sf",
-};
-
-const char *devlink_port_flavour_str(enum devlink_port_flavour value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_port_flavour_strmap))
-		return NULL;
-	return devlink_port_flavour_strmap[value];
-}
-
-static const char * const devlink_port_fn_state_strmap[] = {
-	[0] = "inactive",
-	[1] = "active",
-};
-
-const char *devlink_port_fn_state_str(enum devlink_port_fn_state value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_port_fn_state_strmap))
-		return NULL;
-	return devlink_port_fn_state_strmap[value];
-}
-
-static const char * const devlink_port_fn_opstate_strmap[] = {
-	[0] = "detached",
-	[1] = "attached",
-};
-
-const char *devlink_port_fn_opstate_str(enum devlink_port_fn_opstate value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_port_fn_opstate_strmap))
-		return NULL;
-	return devlink_port_fn_opstate_strmap[value];
-}
-
-static const char * const devlink_port_fn_attr_cap_strmap[] = {
-	[0] = "roce-bit",
-	[1] = "migratable-bit",
-	[2] = "ipsec-crypto-bit",
-	[3] = "ipsec-packet-bit",
-};
-
-const char *devlink_port_fn_attr_cap_str(enum devlink_port_fn_attr_cap value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_port_fn_attr_cap_strmap))
-		return NULL;
-	return devlink_port_fn_attr_cap_strmap[value];
-}
-
-static const char * const devlink_sb_threshold_type_strmap[] = {
-	[0] = "static",
-	[1] = "dynamic",
-};
-
-const char *devlink_sb_threshold_type_str(enum devlink_sb_threshold_type value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_sb_threshold_type_strmap))
-		return NULL;
-	return devlink_sb_threshold_type_strmap[value];
-}
-
-static const char * const devlink_eswitch_mode_strmap[] = {
-	[0] = "legacy",
-	[1] = "switchdev",
-};
-
-const char *devlink_eswitch_mode_str(enum devlink_eswitch_mode value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_eswitch_mode_strmap))
-		return NULL;
-	return devlink_eswitch_mode_strmap[value];
-}
-
-static const char * const devlink_eswitch_inline_mode_strmap[] = {
-	[0] = "none",
-	[1] = "link",
-	[2] = "network",
-	[3] = "transport",
-};
-
-const char *
-devlink_eswitch_inline_mode_str(enum devlink_eswitch_inline_mode value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_eswitch_inline_mode_strmap))
-		return NULL;
-	return devlink_eswitch_inline_mode_strmap[value];
-}
-
-static const char * const devlink_eswitch_encap_mode_strmap[] = {
-	[0] = "none",
-	[1] = "basic",
-};
-
-const char *
-devlink_eswitch_encap_mode_str(enum devlink_eswitch_encap_mode value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_eswitch_encap_mode_strmap))
-		return NULL;
-	return devlink_eswitch_encap_mode_strmap[value];
-}
-
-static const char * const devlink_dpipe_match_type_strmap[] = {
-	[0] = "field-exact",
-};
-
-const char *devlink_dpipe_match_type_str(enum devlink_dpipe_match_type value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_dpipe_match_type_strmap))
-		return NULL;
-	return devlink_dpipe_match_type_strmap[value];
-}
-
-static const char * const devlink_dpipe_action_type_strmap[] = {
-	[0] = "field-modify",
-};
-
-const char *devlink_dpipe_action_type_str(enum devlink_dpipe_action_type value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_dpipe_action_type_strmap))
-		return NULL;
-	return devlink_dpipe_action_type_strmap[value];
-}
-
-static const char * const devlink_dpipe_field_mapping_type_strmap[] = {
-	[0] = "none",
-	[1] = "ifindex",
-};
-
-const char *
-devlink_dpipe_field_mapping_type_str(enum devlink_dpipe_field_mapping_type value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_dpipe_field_mapping_type_strmap))
-		return NULL;
-	return devlink_dpipe_field_mapping_type_strmap[value];
-}
-
-static const char * const devlink_resource_unit_strmap[] = {
-	[0] = "entry",
-};
-
-const char *devlink_resource_unit_str(enum devlink_resource_unit value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_resource_unit_strmap))
-		return NULL;
-	return devlink_resource_unit_strmap[value];
-}
-
-static const char * const devlink_reload_action_strmap[] = {
-	[1] = "driver-reinit",
-	[2] = "fw-activate",
-};
-
-const char *devlink_reload_action_str(enum devlink_reload_action value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_reload_action_strmap))
-		return NULL;
-	return devlink_reload_action_strmap[value];
-}
-
-static const char * const devlink_param_cmode_strmap[] = {
-	[0] = "runtime",
-	[1] = "driverinit",
-	[2] = "permanent",
-};
-
-const char *devlink_param_cmode_str(enum devlink_param_cmode value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_param_cmode_strmap))
-		return NULL;
-	return devlink_param_cmode_strmap[value];
-}
-
-static const char * const devlink_flash_overwrite_strmap[] = {
-	[0] = "settings-bit",
-	[1] = "identifiers-bit",
-};
-
-const char *devlink_flash_overwrite_str(enum devlink_flash_overwrite value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_flash_overwrite_strmap))
-		return NULL;
-	return devlink_flash_overwrite_strmap[value];
-}
-
-static const char * const devlink_trap_action_strmap[] = {
-	[0] = "drop",
-	[1] = "trap",
-	[2] = "mirror",
-};
-
-const char *devlink_trap_action_str(enum devlink_trap_action value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_trap_action_strmap))
-		return NULL;
-	return devlink_trap_action_strmap[value];
-}
-
-/* Policies */
-struct ynl_policy_attr devlink_dl_dpipe_match_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_DPIPE_MATCH_TYPE] = { .name = "dpipe-match-type", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_DPIPE_HEADER_ID] = { .name = "dpipe-header-id", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_DPIPE_HEADER_GLOBAL] = { .name = "dpipe-header-global", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_DPIPE_HEADER_INDEX] = { .name = "dpipe-header-index", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_DPIPE_FIELD_ID] = { .name = "dpipe-field-id", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest devlink_dl_dpipe_match_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_dpipe_match_policy,
-};
-
-struct ynl_policy_attr devlink_dl_dpipe_match_value_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_DPIPE_MATCH] = { .name = "dpipe-match", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_match_nest, },
-	[DEVLINK_ATTR_DPIPE_VALUE] = { .name = "dpipe-value", .type = YNL_PT_BINARY,},
-	[DEVLINK_ATTR_DPIPE_VALUE_MASK] = { .name = "dpipe-value-mask", .type = YNL_PT_BINARY,},
-	[DEVLINK_ATTR_DPIPE_VALUE_MAPPING] = { .name = "dpipe-value-mapping", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest devlink_dl_dpipe_match_value_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_dpipe_match_value_policy,
-};
-
-struct ynl_policy_attr devlink_dl_dpipe_action_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_DPIPE_ACTION_TYPE] = { .name = "dpipe-action-type", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_DPIPE_HEADER_ID] = { .name = "dpipe-header-id", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_DPIPE_HEADER_GLOBAL] = { .name = "dpipe-header-global", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_DPIPE_HEADER_INDEX] = { .name = "dpipe-header-index", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_DPIPE_FIELD_ID] = { .name = "dpipe-field-id", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest devlink_dl_dpipe_action_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_dpipe_action_policy,
-};
-
-struct ynl_policy_attr devlink_dl_dpipe_action_value_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_DPIPE_ACTION] = { .name = "dpipe-action", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_action_nest, },
-	[DEVLINK_ATTR_DPIPE_VALUE] = { .name = "dpipe-value", .type = YNL_PT_BINARY,},
-	[DEVLINK_ATTR_DPIPE_VALUE_MASK] = { .name = "dpipe-value-mask", .type = YNL_PT_BINARY,},
-	[DEVLINK_ATTR_DPIPE_VALUE_MAPPING] = { .name = "dpipe-value-mapping", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest devlink_dl_dpipe_action_value_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_dpipe_action_value_policy,
-};
-
-struct ynl_policy_attr devlink_dl_dpipe_field_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_DPIPE_FIELD_NAME] = { .name = "dpipe-field-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_DPIPE_FIELD_ID] = { .name = "dpipe-field-id", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH] = { .name = "dpipe-field-bitwidth", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE] = { .name = "dpipe-field-mapping-type", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest devlink_dl_dpipe_field_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_dpipe_field_policy,
-};
-
-struct ynl_policy_attr devlink_dl_resource_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_RESOURCE_NAME] = { .name = "resource-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_RESOURCE_ID] = { .name = "resource-id", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_RESOURCE_SIZE] = { .name = "resource-size", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_RESOURCE_SIZE_NEW] = { .name = "resource-size-new", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_RESOURCE_SIZE_VALID] = { .name = "resource-size-valid", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_RESOURCE_SIZE_MIN] = { .name = "resource-size-min", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_RESOURCE_SIZE_MAX] = { .name = "resource-size-max", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_RESOURCE_SIZE_GRAN] = { .name = "resource-size-gran", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_RESOURCE_UNIT] = { .name = "resource-unit", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_RESOURCE_OCC] = { .name = "resource-occ", .type = YNL_PT_U64, },
-};
-
-struct ynl_policy_nest devlink_dl_resource_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_resource_policy,
-};
-
-struct ynl_policy_attr devlink_dl_info_version_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_INFO_VERSION_NAME] = { .name = "info-version-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_INFO_VERSION_VALUE] = { .name = "info-version-value", .type = YNL_PT_NUL_STR, },
-};
-
-struct ynl_policy_nest devlink_dl_info_version_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_info_version_policy,
-};
-
-struct ynl_policy_attr devlink_dl_fmsg_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_FMSG_OBJ_NEST_START] = { .name = "fmsg-obj-nest-start", .type = YNL_PT_FLAG, },
-	[DEVLINK_ATTR_FMSG_PAIR_NEST_START] = { .name = "fmsg-pair-nest-start", .type = YNL_PT_FLAG, },
-	[DEVLINK_ATTR_FMSG_ARR_NEST_START] = { .name = "fmsg-arr-nest-start", .type = YNL_PT_FLAG, },
-	[DEVLINK_ATTR_FMSG_NEST_END] = { .name = "fmsg-nest-end", .type = YNL_PT_FLAG, },
-	[DEVLINK_ATTR_FMSG_OBJ_NAME] = { .name = "fmsg-obj-name", .type = YNL_PT_NUL_STR, },
-};
-
-struct ynl_policy_nest devlink_dl_fmsg_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_fmsg_policy,
-};
-
-struct ynl_policy_attr devlink_dl_port_function_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = {
-	[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .name = "hw-addr", .type = YNL_PT_BINARY,},
-	[DEVLINK_PORT_FN_ATTR_STATE] = { .name = "state", .type = YNL_PT_U8, },
-	[DEVLINK_PORT_FN_ATTR_OPSTATE] = { .name = "opstate", .type = YNL_PT_U8, },
-	[DEVLINK_PORT_FN_ATTR_CAPS] = { .name = "caps", .type = YNL_PT_BITFIELD32, },
-};
-
-struct ynl_policy_nest devlink_dl_port_function_nest = {
-	.max_attr = DEVLINK_PORT_FUNCTION_ATTR_MAX,
-	.table = devlink_dl_port_function_policy,
-};
-
-struct ynl_policy_attr devlink_dl_reload_stats_entry_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_RELOAD_STATS_LIMIT] = { .name = "reload-stats-limit", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_RELOAD_STATS_VALUE] = { .name = "reload-stats-value", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest devlink_dl_reload_stats_entry_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_reload_stats_entry_policy,
-};
-
-struct ynl_policy_attr devlink_dl_reload_act_stats_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_RELOAD_STATS_ENTRY] = { .name = "reload-stats-entry", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_entry_nest, },
-};
-
-struct ynl_policy_nest devlink_dl_reload_act_stats_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_reload_act_stats_policy,
-};
-
-struct ynl_policy_attr devlink_dl_selftest_id_policy[DEVLINK_ATTR_SELFTEST_ID_MAX + 1] = {
-	[DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .name = "flash", .type = YNL_PT_FLAG, },
-};
-
-struct ynl_policy_nest devlink_dl_selftest_id_nest = {
-	.max_attr = DEVLINK_ATTR_SELFTEST_ID_MAX,
-	.table = devlink_dl_selftest_id_policy,
-};
-
-struct ynl_policy_attr devlink_dl_dpipe_table_matches_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_DPIPE_MATCH] = { .name = "dpipe-match", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_match_nest, },
-};
-
-struct ynl_policy_nest devlink_dl_dpipe_table_matches_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_dpipe_table_matches_policy,
-};
-
-struct ynl_policy_attr devlink_dl_dpipe_table_actions_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_DPIPE_ACTION] = { .name = "dpipe-action", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_action_nest, },
-};
-
-struct ynl_policy_nest devlink_dl_dpipe_table_actions_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_dpipe_table_actions_policy,
-};
-
-struct ynl_policy_attr devlink_dl_dpipe_entry_match_values_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_DPIPE_MATCH_VALUE] = { .name = "dpipe-match-value", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_match_value_nest, },
-};
-
-struct ynl_policy_nest devlink_dl_dpipe_entry_match_values_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_dpipe_entry_match_values_policy,
-};
-
-struct ynl_policy_attr devlink_dl_dpipe_entry_action_values_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_DPIPE_ACTION_VALUE] = { .name = "dpipe-action-value", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_action_value_nest, },
-};
-
-struct ynl_policy_nest devlink_dl_dpipe_entry_action_values_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_dpipe_entry_action_values_policy,
-};
-
-struct ynl_policy_attr devlink_dl_dpipe_header_fields_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_DPIPE_FIELD] = { .name = "dpipe-field", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_field_nest, },
-};
-
-struct ynl_policy_nest devlink_dl_dpipe_header_fields_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_dpipe_header_fields_policy,
-};
-
-struct ynl_policy_attr devlink_dl_resource_list_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_RESOURCE] = { .name = "resource", .type = YNL_PT_NEST, .nest = &devlink_dl_resource_nest, },
-};
-
-struct ynl_policy_nest devlink_dl_resource_list_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_resource_list_policy,
-};
-
-struct ynl_policy_attr devlink_dl_reload_act_info_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_RELOAD_ACTION] = { .name = "reload-action", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_RELOAD_ACTION_STATS] = { .name = "reload-action-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_stats_nest, },
-};
-
-struct ynl_policy_nest devlink_dl_reload_act_info_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_reload_act_info_policy,
-};
-
-struct ynl_policy_attr devlink_dl_dpipe_table_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .name = "dpipe-table-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_DPIPE_TABLE_SIZE] = { .name = "dpipe-table-size", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_DPIPE_TABLE_MATCHES] = { .name = "dpipe-table-matches", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_table_matches_nest, },
-	[DEVLINK_ATTR_DPIPE_TABLE_ACTIONS] = { .name = "dpipe-table-actions", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_table_actions_nest, },
-	[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .name = "dpipe-table-counters-enabled", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID] = { .name = "dpipe-table-resource-id", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS] = { .name = "dpipe-table-resource-units", .type = YNL_PT_U64, },
-};
-
-struct ynl_policy_nest devlink_dl_dpipe_table_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_dpipe_table_policy,
-};
-
-struct ynl_policy_attr devlink_dl_dpipe_entry_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_DPIPE_ENTRY_INDEX] = { .name = "dpipe-entry-index", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES] = { .name = "dpipe-entry-match-values", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_entry_match_values_nest, },
-	[DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES] = { .name = "dpipe-entry-action-values", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_entry_action_values_nest, },
-	[DEVLINK_ATTR_DPIPE_ENTRY_COUNTER] = { .name = "dpipe-entry-counter", .type = YNL_PT_U64, },
-};
-
-struct ynl_policy_nest devlink_dl_dpipe_entry_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_dpipe_entry_policy,
-};
-
-struct ynl_policy_attr devlink_dl_dpipe_header_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_DPIPE_HEADER_NAME] = { .name = "dpipe-header-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_DPIPE_HEADER_ID] = { .name = "dpipe-header-id", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_DPIPE_HEADER_GLOBAL] = { .name = "dpipe-header-global", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_DPIPE_HEADER_FIELDS] = { .name = "dpipe-header-fields", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_header_fields_nest, },
-};
-
-struct ynl_policy_nest devlink_dl_dpipe_header_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_dpipe_header_policy,
-};
-
-struct ynl_policy_attr devlink_dl_reload_stats_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_RELOAD_ACTION_INFO] = { .name = "reload-action-info", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_info_nest, },
-};
-
-struct ynl_policy_nest devlink_dl_reload_stats_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_reload_stats_policy,
-};
-
-struct ynl_policy_attr devlink_dl_dpipe_tables_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_DPIPE_TABLE] = { .name = "dpipe-table", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_table_nest, },
-};
-
-struct ynl_policy_nest devlink_dl_dpipe_tables_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_dpipe_tables_policy,
-};
-
-struct ynl_policy_attr devlink_dl_dpipe_entries_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_DPIPE_ENTRY] = { .name = "dpipe-entry", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_entry_nest, },
-};
-
-struct ynl_policy_nest devlink_dl_dpipe_entries_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_dpipe_entries_policy,
-};
-
-struct ynl_policy_attr devlink_dl_dpipe_headers_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_DPIPE_HEADER] = { .name = "dpipe-header", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_header_nest, },
-};
-
-struct ynl_policy_nest devlink_dl_dpipe_headers_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_dpipe_headers_policy,
-};
-
-struct ynl_policy_attr devlink_dl_dev_stats_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_RELOAD_STATS] = { .name = "reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, },
-	[DEVLINK_ATTR_REMOTE_RELOAD_STATS] = { .name = "remote-reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, },
-};
-
-struct ynl_policy_nest devlink_dl_dev_stats_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_dl_dev_stats_policy,
-};
-
-struct ynl_policy_attr devlink_policy[DEVLINK_ATTR_MAX + 1] = {
-	[DEVLINK_ATTR_BUS_NAME] = { .name = "bus-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_DEV_NAME] = { .name = "dev-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_PORT_INDEX] = { .name = "port-index", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_PORT_TYPE] = { .name = "port-type", .type = YNL_PT_U16, },
-	[DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .name = "port-split-count", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_SB_INDEX] = { .name = "sb-index", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_SB_POOL_INDEX] = { .name = "sb-pool-index", .type = YNL_PT_U16, },
-	[DEVLINK_ATTR_SB_POOL_TYPE] = { .name = "sb-pool-type", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_SB_POOL_SIZE] = { .name = "sb-pool-size", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = { .name = "sb-pool-threshold-type", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_SB_THRESHOLD] = { .name = "sb-threshold", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_SB_TC_INDEX] = { .name = "sb-tc-index", .type = YNL_PT_U16, },
-	[DEVLINK_ATTR_ESWITCH_MODE] = { .name = "eswitch-mode", .type = YNL_PT_U16, },
-	[DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .name = "eswitch-inline-mode", .type = YNL_PT_U16, },
-	[DEVLINK_ATTR_DPIPE_TABLES] = { .name = "dpipe-tables", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_tables_nest, },
-	[DEVLINK_ATTR_DPIPE_TABLE] = { .name = "dpipe-table", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_table_nest, },
-	[DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .name = "dpipe-table-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_DPIPE_TABLE_SIZE] = { .name = "dpipe-table-size", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_DPIPE_TABLE_MATCHES] = { .name = "dpipe-table-matches", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_table_matches_nest, },
-	[DEVLINK_ATTR_DPIPE_TABLE_ACTIONS] = { .name = "dpipe-table-actions", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_table_actions_nest, },
-	[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .name = "dpipe-table-counters-enabled", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_DPIPE_ENTRIES] = { .name = "dpipe-entries", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_entries_nest, },
-	[DEVLINK_ATTR_DPIPE_ENTRY] = { .name = "dpipe-entry", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_entry_nest, },
-	[DEVLINK_ATTR_DPIPE_ENTRY_INDEX] = { .name = "dpipe-entry-index", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES] = { .name = "dpipe-entry-match-values", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_entry_match_values_nest, },
-	[DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES] = { .name = "dpipe-entry-action-values", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_entry_action_values_nest, },
-	[DEVLINK_ATTR_DPIPE_ENTRY_COUNTER] = { .name = "dpipe-entry-counter", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_DPIPE_MATCH] = { .name = "dpipe-match", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_match_nest, },
-	[DEVLINK_ATTR_DPIPE_MATCH_VALUE] = { .name = "dpipe-match-value", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_match_value_nest, },
-	[DEVLINK_ATTR_DPIPE_MATCH_TYPE] = { .name = "dpipe-match-type", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_DPIPE_ACTION] = { .name = "dpipe-action", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_action_nest, },
-	[DEVLINK_ATTR_DPIPE_ACTION_VALUE] = { .name = "dpipe-action-value", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_action_value_nest, },
-	[DEVLINK_ATTR_DPIPE_ACTION_TYPE] = { .name = "dpipe-action-type", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_DPIPE_VALUE] = { .name = "dpipe-value", .type = YNL_PT_BINARY,},
-	[DEVLINK_ATTR_DPIPE_VALUE_MASK] = { .name = "dpipe-value-mask", .type = YNL_PT_BINARY,},
-	[DEVLINK_ATTR_DPIPE_VALUE_MAPPING] = { .name = "dpipe-value-mapping", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_DPIPE_HEADERS] = { .name = "dpipe-headers", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_headers_nest, },
-	[DEVLINK_ATTR_DPIPE_HEADER] = { .name = "dpipe-header", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_header_nest, },
-	[DEVLINK_ATTR_DPIPE_HEADER_NAME] = { .name = "dpipe-header-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_DPIPE_HEADER_ID] = { .name = "dpipe-header-id", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_DPIPE_HEADER_FIELDS] = { .name = "dpipe-header-fields", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_header_fields_nest, },
-	[DEVLINK_ATTR_DPIPE_HEADER_GLOBAL] = { .name = "dpipe-header-global", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_DPIPE_HEADER_INDEX] = { .name = "dpipe-header-index", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_DPIPE_FIELD] = { .name = "dpipe-field", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_field_nest, },
-	[DEVLINK_ATTR_DPIPE_FIELD_NAME] = { .name = "dpipe-field-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_DPIPE_FIELD_ID] = { .name = "dpipe-field-id", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH] = { .name = "dpipe-field-bitwidth", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE] = { .name = "dpipe-field-mapping-type", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_PAD] = { .name = "pad", .type = YNL_PT_IGNORE, },
-	[DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = { .name = "eswitch-encap-mode", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_RESOURCE_LIST] = { .name = "resource-list", .type = YNL_PT_NEST, .nest = &devlink_dl_resource_list_nest, },
-	[DEVLINK_ATTR_RESOURCE] = { .name = "resource", .type = YNL_PT_NEST, .nest = &devlink_dl_resource_nest, },
-	[DEVLINK_ATTR_RESOURCE_NAME] = { .name = "resource-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_RESOURCE_ID] = { .name = "resource-id", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_RESOURCE_SIZE] = { .name = "resource-size", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_RESOURCE_SIZE_NEW] = { .name = "resource-size-new", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_RESOURCE_SIZE_VALID] = { .name = "resource-size-valid", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_RESOURCE_SIZE_MIN] = { .name = "resource-size-min", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_RESOURCE_SIZE_MAX] = { .name = "resource-size-max", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_RESOURCE_SIZE_GRAN] = { .name = "resource-size-gran", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_RESOURCE_UNIT] = { .name = "resource-unit", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_RESOURCE_OCC] = { .name = "resource-occ", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID] = { .name = "dpipe-table-resource-id", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS] = { .name = "dpipe-table-resource-units", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_PORT_FLAVOUR] = { .name = "port-flavour", .type = YNL_PT_U16, },
-	[DEVLINK_ATTR_PARAM_NAME] = { .name = "param-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_PARAM_TYPE] = { .name = "param-type", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .name = "param-value-cmode", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_REGION_NAME] = { .name = "region-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .name = "region-snapshot-id", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_REGION_CHUNK_ADDR] = { .name = "region-chunk-addr", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_REGION_CHUNK_LEN] = { .name = "region-chunk-len", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_INFO_DRIVER_NAME] = { .name = "info-driver-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_INFO_SERIAL_NUMBER] = { .name = "info-serial-number", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_INFO_VERSION_FIXED] = { .name = "info-version-fixed", .type = YNL_PT_NEST, .nest = &devlink_dl_info_version_nest, },
-	[DEVLINK_ATTR_INFO_VERSION_RUNNING] = { .name = "info-version-running", .type = YNL_PT_NEST, .nest = &devlink_dl_info_version_nest, },
-	[DEVLINK_ATTR_INFO_VERSION_STORED] = { .name = "info-version-stored", .type = YNL_PT_NEST, .nest = &devlink_dl_info_version_nest, },
-	[DEVLINK_ATTR_INFO_VERSION_NAME] = { .name = "info-version-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_INFO_VERSION_VALUE] = { .name = "info-version-value", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_FMSG] = { .name = "fmsg", .type = YNL_PT_NEST, .nest = &devlink_dl_fmsg_nest, },
-	[DEVLINK_ATTR_FMSG_OBJ_NEST_START] = { .name = "fmsg-obj-nest-start", .type = YNL_PT_FLAG, },
-	[DEVLINK_ATTR_FMSG_PAIR_NEST_START] = { .name = "fmsg-pair-nest-start", .type = YNL_PT_FLAG, },
-	[DEVLINK_ATTR_FMSG_ARR_NEST_START] = { .name = "fmsg-arr-nest-start", .type = YNL_PT_FLAG, },
-	[DEVLINK_ATTR_FMSG_NEST_END] = { .name = "fmsg-nest-end", .type = YNL_PT_FLAG, },
-	[DEVLINK_ATTR_FMSG_OBJ_NAME] = { .name = "fmsg-obj-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .name = "health-reporter-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .name = "health-reporter-graceful-period", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .name = "health-reporter-auto-recover", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .name = "flash-update-file-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .name = "flash-update-component", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .name = "port-pci-pf-number", .type = YNL_PT_U16, },
-	[DEVLINK_ATTR_TRAP_NAME] = { .name = "trap-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_TRAP_ACTION] = { .name = "trap-action", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_TRAP_GROUP_NAME] = { .name = "trap-group-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_RELOAD_FAILED] = { .name = "reload-failed", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_NETNS_FD] = { .name = "netns-fd", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_NETNS_PID] = { .name = "netns-pid", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_NETNS_ID] = { .name = "netns-id", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP] = { .name = "health-reporter-auto-dump", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_TRAP_POLICER_ID] = { .name = "trap-policer-id", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_TRAP_POLICER_RATE] = { .name = "trap-policer-rate", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_TRAP_POLICER_BURST] = { .name = "trap-policer-burst", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_PORT_FUNCTION] = { .name = "port-function", .type = YNL_PT_NEST, .nest = &devlink_dl_port_function_nest, },
-	[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .name = "port-controller-number", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK] = { .name = "flash-update-overwrite-mask", .type = YNL_PT_BITFIELD32, },
-	[DEVLINK_ATTR_RELOAD_ACTION] = { .name = "reload-action", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED] = { .name = "reload-actions-performed", .type = YNL_PT_BITFIELD32, },
-	[DEVLINK_ATTR_RELOAD_LIMITS] = { .name = "reload-limits", .type = YNL_PT_BITFIELD32, },
-	[DEVLINK_ATTR_DEV_STATS] = { .name = "dev-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_dev_stats_nest, },
-	[DEVLINK_ATTR_RELOAD_STATS] = { .name = "reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, },
-	[DEVLINK_ATTR_RELOAD_STATS_ENTRY] = { .name = "reload-stats-entry", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_entry_nest, },
-	[DEVLINK_ATTR_RELOAD_STATS_LIMIT] = { .name = "reload-stats-limit", .type = YNL_PT_U8, },
-	[DEVLINK_ATTR_RELOAD_STATS_VALUE] = { .name = "reload-stats-value", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_REMOTE_RELOAD_STATS] = { .name = "remote-reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, },
-	[DEVLINK_ATTR_RELOAD_ACTION_INFO] = { .name = "reload-action-info", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_info_nest, },
-	[DEVLINK_ATTR_RELOAD_ACTION_STATS] = { .name = "reload-action-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_stats_nest, },
-	[DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .name = "port-pci-sf-number", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_RATE_TX_SHARE] = { .name = "rate-tx-share", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_RATE_TX_MAX] = { .name = "rate-tx-max", .type = YNL_PT_U64, },
-	[DEVLINK_ATTR_RATE_NODE_NAME] = { .name = "rate-node-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .name = "rate-parent-node-name", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_LINECARD_INDEX] = { .name = "linecard-index", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_LINECARD_TYPE] = { .name = "linecard-type", .type = YNL_PT_NUL_STR, },
-	[DEVLINK_ATTR_SELFTESTS] = { .name = "selftests", .type = YNL_PT_NEST, .nest = &devlink_dl_selftest_id_nest, },
-	[DEVLINK_ATTR_RATE_TX_PRIORITY] = { .name = "rate-tx-priority", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_RATE_TX_WEIGHT] = { .name = "rate-tx-weight", .type = YNL_PT_U32, },
-	[DEVLINK_ATTR_REGION_DIRECT] = { .name = "region-direct", .type = YNL_PT_FLAG, },
-};
-
-struct ynl_policy_nest devlink_nest = {
-	.max_attr = DEVLINK_ATTR_MAX,
-	.table = devlink_policy,
-};
-
-/* Common nested types */
-void devlink_dl_dpipe_match_free(struct devlink_dl_dpipe_match *obj)
-{
-}
-
-int devlink_dl_dpipe_match_parse(struct ynl_parse_arg *yarg,
-				 const struct nlattr *nested)
-{
-	struct devlink_dl_dpipe_match *dst = yarg->data;
-	const struct nlattr *attr;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_DPIPE_MATCH_TYPE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_match_type = 1;
-			dst->dpipe_match_type = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_DPIPE_HEADER_ID) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_header_id = 1;
-			dst->dpipe_header_id = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_DPIPE_HEADER_GLOBAL) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_header_global = 1;
-			dst->dpipe_header_global = mnl_attr_get_u8(attr);
-		} else if (type == DEVLINK_ATTR_DPIPE_HEADER_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_header_index = 1;
-			dst->dpipe_header_index = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_DPIPE_FIELD_ID) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_field_id = 1;
-			dst->dpipe_field_id = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return 0;
-}
-
-void
-devlink_dl_dpipe_match_value_free(struct devlink_dl_dpipe_match_value *obj)
-{
-	unsigned int i;
-
-	for (i = 0; i < obj->n_dpipe_match; i++)
-		devlink_dl_dpipe_match_free(&obj->dpipe_match[i]);
-	free(obj->dpipe_match);
-	free(obj->dpipe_value);
-	free(obj->dpipe_value_mask);
-}
-
-int devlink_dl_dpipe_match_value_parse(struct ynl_parse_arg *yarg,
-				       const struct nlattr *nested)
-{
-	struct devlink_dl_dpipe_match_value *dst = yarg->data;
-	unsigned int n_dpipe_match = 0;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	int i;
-
-	parg.ys = yarg->ys;
-
-	if (dst->dpipe_match)
-		return ynl_error_parse(yarg, "attribute already present (dl-dpipe-match-value.dpipe-match)");
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_DPIPE_MATCH) {
-			n_dpipe_match++;
-		} else if (type == DEVLINK_ATTR_DPIPE_VALUE) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = mnl_attr_get_payload_len(attr);
-			dst->_present.dpipe_value_len = len;
-			dst->dpipe_value = malloc(len);
-			memcpy(dst->dpipe_value, mnl_attr_get_payload(attr), len);
-		} else if (type == DEVLINK_ATTR_DPIPE_VALUE_MASK) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = mnl_attr_get_payload_len(attr);
-			dst->_present.dpipe_value_mask_len = len;
-			dst->dpipe_value_mask = malloc(len);
-			memcpy(dst->dpipe_value_mask, mnl_attr_get_payload(attr), len);
-		} else if (type == DEVLINK_ATTR_DPIPE_VALUE_MAPPING) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_value_mapping = 1;
-			dst->dpipe_value_mapping = mnl_attr_get_u32(attr);
-		}
-	}
-
-	if (n_dpipe_match) {
-		dst->dpipe_match = calloc(n_dpipe_match, sizeof(*dst->dpipe_match));
-		dst->n_dpipe_match = n_dpipe_match;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_dpipe_match_nest;
-		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_MATCH) {
-				parg.data = &dst->dpipe_match[i];
-				if (devlink_dl_dpipe_match_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-
-	return 0;
-}
-
-void devlink_dl_dpipe_action_free(struct devlink_dl_dpipe_action *obj)
-{
-}
-
-int devlink_dl_dpipe_action_parse(struct ynl_parse_arg *yarg,
-				  const struct nlattr *nested)
-{
-	struct devlink_dl_dpipe_action *dst = yarg->data;
-	const struct nlattr *attr;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_DPIPE_ACTION_TYPE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_action_type = 1;
-			dst->dpipe_action_type = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_DPIPE_HEADER_ID) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_header_id = 1;
-			dst->dpipe_header_id = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_DPIPE_HEADER_GLOBAL) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_header_global = 1;
-			dst->dpipe_header_global = mnl_attr_get_u8(attr);
-		} else if (type == DEVLINK_ATTR_DPIPE_HEADER_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_header_index = 1;
-			dst->dpipe_header_index = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_DPIPE_FIELD_ID) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_field_id = 1;
-			dst->dpipe_field_id = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return 0;
-}
-
-void
-devlink_dl_dpipe_action_value_free(struct devlink_dl_dpipe_action_value *obj)
-{
-	unsigned int i;
-
-	for (i = 0; i < obj->n_dpipe_action; i++)
-		devlink_dl_dpipe_action_free(&obj->dpipe_action[i]);
-	free(obj->dpipe_action);
-	free(obj->dpipe_value);
-	free(obj->dpipe_value_mask);
-}
-
-int devlink_dl_dpipe_action_value_parse(struct ynl_parse_arg *yarg,
-					const struct nlattr *nested)
-{
-	struct devlink_dl_dpipe_action_value *dst = yarg->data;
-	unsigned int n_dpipe_action = 0;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	int i;
-
-	parg.ys = yarg->ys;
-
-	if (dst->dpipe_action)
-		return ynl_error_parse(yarg, "attribute already present (dl-dpipe-action-value.dpipe-action)");
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_DPIPE_ACTION) {
-			n_dpipe_action++;
-		} else if (type == DEVLINK_ATTR_DPIPE_VALUE) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = mnl_attr_get_payload_len(attr);
-			dst->_present.dpipe_value_len = len;
-			dst->dpipe_value = malloc(len);
-			memcpy(dst->dpipe_value, mnl_attr_get_payload(attr), len);
-		} else if (type == DEVLINK_ATTR_DPIPE_VALUE_MASK) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = mnl_attr_get_payload_len(attr);
-			dst->_present.dpipe_value_mask_len = len;
-			dst->dpipe_value_mask = malloc(len);
-			memcpy(dst->dpipe_value_mask, mnl_attr_get_payload(attr), len);
-		} else if (type == DEVLINK_ATTR_DPIPE_VALUE_MAPPING) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_value_mapping = 1;
-			dst->dpipe_value_mapping = mnl_attr_get_u32(attr);
-		}
-	}
-
-	if (n_dpipe_action) {
-		dst->dpipe_action = calloc(n_dpipe_action, sizeof(*dst->dpipe_action));
-		dst->n_dpipe_action = n_dpipe_action;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_dpipe_action_nest;
-		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_ACTION) {
-				parg.data = &dst->dpipe_action[i];
-				if (devlink_dl_dpipe_action_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-
-	return 0;
-}
-
-void devlink_dl_dpipe_field_free(struct devlink_dl_dpipe_field *obj)
-{
-	free(obj->dpipe_field_name);
-}
-
-int devlink_dl_dpipe_field_parse(struct ynl_parse_arg *yarg,
-				 const struct nlattr *nested)
-{
-	struct devlink_dl_dpipe_field *dst = yarg->data;
-	const struct nlattr *attr;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_DPIPE_FIELD_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dpipe_field_name_len = len;
-			dst->dpipe_field_name = malloc(len + 1);
-			memcpy(dst->dpipe_field_name, mnl_attr_get_str(attr), len);
-			dst->dpipe_field_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DPIPE_FIELD_ID) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_field_id = 1;
-			dst->dpipe_field_id = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_field_bitwidth = 1;
-			dst->dpipe_field_bitwidth = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_field_mapping_type = 1;
-			dst->dpipe_field_mapping_type = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return 0;
-}
-
-void devlink_dl_resource_free(struct devlink_dl_resource *obj)
-{
-	free(obj->resource_name);
-}
-
-int devlink_dl_resource_parse(struct ynl_parse_arg *yarg,
-			      const struct nlattr *nested)
-{
-	struct devlink_dl_resource *dst = yarg->data;
-	const struct nlattr *attr;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_RESOURCE_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.resource_name_len = len;
-			dst->resource_name = malloc(len + 1);
-			memcpy(dst->resource_name, mnl_attr_get_str(attr), len);
-			dst->resource_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_RESOURCE_ID) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.resource_id = 1;
-			dst->resource_id = mnl_attr_get_u64(attr);
-		} else if (type == DEVLINK_ATTR_RESOURCE_SIZE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.resource_size = 1;
-			dst->resource_size = mnl_attr_get_u64(attr);
-		} else if (type == DEVLINK_ATTR_RESOURCE_SIZE_NEW) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.resource_size_new = 1;
-			dst->resource_size_new = mnl_attr_get_u64(attr);
-		} else if (type == DEVLINK_ATTR_RESOURCE_SIZE_VALID) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.resource_size_valid = 1;
-			dst->resource_size_valid = mnl_attr_get_u8(attr);
-		} else if (type == DEVLINK_ATTR_RESOURCE_SIZE_MIN) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.resource_size_min = 1;
-			dst->resource_size_min = mnl_attr_get_u64(attr);
-		} else if (type == DEVLINK_ATTR_RESOURCE_SIZE_MAX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.resource_size_max = 1;
-			dst->resource_size_max = mnl_attr_get_u64(attr);
-		} else if (type == DEVLINK_ATTR_RESOURCE_SIZE_GRAN) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.resource_size_gran = 1;
-			dst->resource_size_gran = mnl_attr_get_u64(attr);
-		} else if (type == DEVLINK_ATTR_RESOURCE_UNIT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.resource_unit = 1;
-			dst->resource_unit = mnl_attr_get_u8(attr);
-		} else if (type == DEVLINK_ATTR_RESOURCE_OCC) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.resource_occ = 1;
-			dst->resource_occ = mnl_attr_get_u64(attr);
-		}
-	}
-
-	return 0;
-}
-
-void devlink_dl_info_version_free(struct devlink_dl_info_version *obj)
-{
-	free(obj->info_version_name);
-	free(obj->info_version_value);
-}
-
-int devlink_dl_info_version_parse(struct ynl_parse_arg *yarg,
-				  const struct nlattr *nested)
-{
-	struct devlink_dl_info_version *dst = yarg->data;
-	const struct nlattr *attr;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_INFO_VERSION_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.info_version_name_len = len;
-			dst->info_version_name = malloc(len + 1);
-			memcpy(dst->info_version_name, mnl_attr_get_str(attr), len);
-			dst->info_version_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_INFO_VERSION_VALUE) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.info_version_value_len = len;
-			dst->info_version_value = malloc(len + 1);
-			memcpy(dst->info_version_value, mnl_attr_get_str(attr), len);
-			dst->info_version_value[len] = 0;
-		}
-	}
-
-	return 0;
-}
-
-void devlink_dl_fmsg_free(struct devlink_dl_fmsg *obj)
-{
-	free(obj->fmsg_obj_name);
-}
-
-int devlink_dl_fmsg_parse(struct ynl_parse_arg *yarg,
-			  const struct nlattr *nested)
-{
-	struct devlink_dl_fmsg *dst = yarg->data;
-	const struct nlattr *attr;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_FMSG_OBJ_NEST_START) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.fmsg_obj_nest_start = 1;
-		} else if (type == DEVLINK_ATTR_FMSG_PAIR_NEST_START) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.fmsg_pair_nest_start = 1;
-		} else if (type == DEVLINK_ATTR_FMSG_ARR_NEST_START) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.fmsg_arr_nest_start = 1;
-		} else if (type == DEVLINK_ATTR_FMSG_NEST_END) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.fmsg_nest_end = 1;
-		} else if (type == DEVLINK_ATTR_FMSG_OBJ_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.fmsg_obj_name_len = len;
-			dst->fmsg_obj_name = malloc(len + 1);
-			memcpy(dst->fmsg_obj_name, mnl_attr_get_str(attr), len);
-			dst->fmsg_obj_name[len] = 0;
-		}
-	}
-
-	return 0;
-}
-
-void devlink_dl_port_function_free(struct devlink_dl_port_function *obj)
-{
-	free(obj->hw_addr);
-}
-
-int devlink_dl_port_function_put(struct nlmsghdr *nlh, unsigned int attr_type,
-				 struct devlink_dl_port_function *obj)
-{
-	struct nlattr *nest;
-
-	nest = mnl_attr_nest_start(nlh, attr_type);
-	if (obj->_present.hw_addr_len)
-		mnl_attr_put(nlh, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, obj->_present.hw_addr_len, obj->hw_addr);
-	if (obj->_present.state)
-		mnl_attr_put_u8(nlh, DEVLINK_PORT_FN_ATTR_STATE, obj->state);
-	if (obj->_present.opstate)
-		mnl_attr_put_u8(nlh, DEVLINK_PORT_FN_ATTR_OPSTATE, obj->opstate);
-	if (obj->_present.caps)
-		mnl_attr_put(nlh, DEVLINK_PORT_FN_ATTR_CAPS, sizeof(struct nla_bitfield32), &obj->caps);
-	mnl_attr_nest_end(nlh, nest);
-
-	return 0;
-}
-
-void
-devlink_dl_reload_stats_entry_free(struct devlink_dl_reload_stats_entry *obj)
-{
-}
-
-int devlink_dl_reload_stats_entry_parse(struct ynl_parse_arg *yarg,
-					const struct nlattr *nested)
-{
-	struct devlink_dl_reload_stats_entry *dst = yarg->data;
-	const struct nlattr *attr;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_RELOAD_STATS_LIMIT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.reload_stats_limit = 1;
-			dst->reload_stats_limit = mnl_attr_get_u8(attr);
-		} else if (type == DEVLINK_ATTR_RELOAD_STATS_VALUE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.reload_stats_value = 1;
-			dst->reload_stats_value = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return 0;
-}
-
-void devlink_dl_reload_act_stats_free(struct devlink_dl_reload_act_stats *obj)
-{
-	unsigned int i;
-
-	for (i = 0; i < obj->n_reload_stats_entry; i++)
-		devlink_dl_reload_stats_entry_free(&obj->reload_stats_entry[i]);
-	free(obj->reload_stats_entry);
-}
-
-int devlink_dl_reload_act_stats_parse(struct ynl_parse_arg *yarg,
-				      const struct nlattr *nested)
-{
-	struct devlink_dl_reload_act_stats *dst = yarg->data;
-	unsigned int n_reload_stats_entry = 0;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	int i;
-
-	parg.ys = yarg->ys;
-
-	if (dst->reload_stats_entry)
-		return ynl_error_parse(yarg, "attribute already present (dl-reload-act-stats.reload-stats-entry)");
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_RELOAD_STATS_ENTRY) {
-			n_reload_stats_entry++;
-		}
-	}
-
-	if (n_reload_stats_entry) {
-		dst->reload_stats_entry = calloc(n_reload_stats_entry, sizeof(*dst->reload_stats_entry));
-		dst->n_reload_stats_entry = n_reload_stats_entry;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_reload_stats_entry_nest;
-		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_RELOAD_STATS_ENTRY) {
-				parg.data = &dst->reload_stats_entry[i];
-				if (devlink_dl_reload_stats_entry_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-
-	return 0;
-}
-
-void devlink_dl_selftest_id_free(struct devlink_dl_selftest_id *obj)
-{
-}
-
-int devlink_dl_selftest_id_put(struct nlmsghdr *nlh, unsigned int attr_type,
-			       struct devlink_dl_selftest_id *obj)
-{
-	struct nlattr *nest;
-
-	nest = mnl_attr_nest_start(nlh, attr_type);
-	if (obj->_present.flash)
-		mnl_attr_put(nlh, DEVLINK_ATTR_SELFTEST_ID_FLASH, 0, NULL);
-	mnl_attr_nest_end(nlh, nest);
-
-	return 0;
-}
-
-void
-devlink_dl_dpipe_table_matches_free(struct devlink_dl_dpipe_table_matches *obj)
-{
-	unsigned int i;
-
-	for (i = 0; i < obj->n_dpipe_match; i++)
-		devlink_dl_dpipe_match_free(&obj->dpipe_match[i]);
-	free(obj->dpipe_match);
-}
-
-int devlink_dl_dpipe_table_matches_parse(struct ynl_parse_arg *yarg,
-					 const struct nlattr *nested)
-{
-	struct devlink_dl_dpipe_table_matches *dst = yarg->data;
-	unsigned int n_dpipe_match = 0;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	int i;
-
-	parg.ys = yarg->ys;
-
-	if (dst->dpipe_match)
-		return ynl_error_parse(yarg, "attribute already present (dl-dpipe-table-matches.dpipe-match)");
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_DPIPE_MATCH) {
-			n_dpipe_match++;
-		}
-	}
-
-	if (n_dpipe_match) {
-		dst->dpipe_match = calloc(n_dpipe_match, sizeof(*dst->dpipe_match));
-		dst->n_dpipe_match = n_dpipe_match;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_dpipe_match_nest;
-		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_MATCH) {
-				parg.data = &dst->dpipe_match[i];
-				if (devlink_dl_dpipe_match_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-
-	return 0;
-}
-
-void
-devlink_dl_dpipe_table_actions_free(struct devlink_dl_dpipe_table_actions *obj)
-{
-	unsigned int i;
-
-	for (i = 0; i < obj->n_dpipe_action; i++)
-		devlink_dl_dpipe_action_free(&obj->dpipe_action[i]);
-	free(obj->dpipe_action);
-}
-
-int devlink_dl_dpipe_table_actions_parse(struct ynl_parse_arg *yarg,
-					 const struct nlattr *nested)
-{
-	struct devlink_dl_dpipe_table_actions *dst = yarg->data;
-	unsigned int n_dpipe_action = 0;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	int i;
-
-	parg.ys = yarg->ys;
-
-	if (dst->dpipe_action)
-		return ynl_error_parse(yarg, "attribute already present (dl-dpipe-table-actions.dpipe-action)");
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_DPIPE_ACTION) {
-			n_dpipe_action++;
-		}
-	}
-
-	if (n_dpipe_action) {
-		dst->dpipe_action = calloc(n_dpipe_action, sizeof(*dst->dpipe_action));
-		dst->n_dpipe_action = n_dpipe_action;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_dpipe_action_nest;
-		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_ACTION) {
-				parg.data = &dst->dpipe_action[i];
-				if (devlink_dl_dpipe_action_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-
-	return 0;
-}
-
-void
-devlink_dl_dpipe_entry_match_values_free(struct devlink_dl_dpipe_entry_match_values *obj)
-{
-	unsigned int i;
-
-	for (i = 0; i < obj->n_dpipe_match_value; i++)
-		devlink_dl_dpipe_match_value_free(&obj->dpipe_match_value[i]);
-	free(obj->dpipe_match_value);
-}
-
-int devlink_dl_dpipe_entry_match_values_parse(struct ynl_parse_arg *yarg,
-					      const struct nlattr *nested)
-{
-	struct devlink_dl_dpipe_entry_match_values *dst = yarg->data;
-	unsigned int n_dpipe_match_value = 0;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	int i;
-
-	parg.ys = yarg->ys;
-
-	if (dst->dpipe_match_value)
-		return ynl_error_parse(yarg, "attribute already present (dl-dpipe-entry-match-values.dpipe-match-value)");
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_DPIPE_MATCH_VALUE) {
-			n_dpipe_match_value++;
-		}
-	}
-
-	if (n_dpipe_match_value) {
-		dst->dpipe_match_value = calloc(n_dpipe_match_value, sizeof(*dst->dpipe_match_value));
-		dst->n_dpipe_match_value = n_dpipe_match_value;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_dpipe_match_value_nest;
-		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_MATCH_VALUE) {
-				parg.data = &dst->dpipe_match_value[i];
-				if (devlink_dl_dpipe_match_value_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-
-	return 0;
-}
-
-void
-devlink_dl_dpipe_entry_action_values_free(struct devlink_dl_dpipe_entry_action_values *obj)
-{
-	unsigned int i;
-
-	for (i = 0; i < obj->n_dpipe_action_value; i++)
-		devlink_dl_dpipe_action_value_free(&obj->dpipe_action_value[i]);
-	free(obj->dpipe_action_value);
-}
-
-int devlink_dl_dpipe_entry_action_values_parse(struct ynl_parse_arg *yarg,
-					       const struct nlattr *nested)
-{
-	struct devlink_dl_dpipe_entry_action_values *dst = yarg->data;
-	unsigned int n_dpipe_action_value = 0;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	int i;
-
-	parg.ys = yarg->ys;
-
-	if (dst->dpipe_action_value)
-		return ynl_error_parse(yarg, "attribute already present (dl-dpipe-entry-action-values.dpipe-action-value)");
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_DPIPE_ACTION_VALUE) {
-			n_dpipe_action_value++;
-		}
-	}
-
-	if (n_dpipe_action_value) {
-		dst->dpipe_action_value = calloc(n_dpipe_action_value, sizeof(*dst->dpipe_action_value));
-		dst->n_dpipe_action_value = n_dpipe_action_value;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_dpipe_action_value_nest;
-		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_ACTION_VALUE) {
-				parg.data = &dst->dpipe_action_value[i];
-				if (devlink_dl_dpipe_action_value_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-
-	return 0;
-}
-
-void
-devlink_dl_dpipe_header_fields_free(struct devlink_dl_dpipe_header_fields *obj)
-{
-	unsigned int i;
-
-	for (i = 0; i < obj->n_dpipe_field; i++)
-		devlink_dl_dpipe_field_free(&obj->dpipe_field[i]);
-	free(obj->dpipe_field);
-}
-
-int devlink_dl_dpipe_header_fields_parse(struct ynl_parse_arg *yarg,
-					 const struct nlattr *nested)
-{
-	struct devlink_dl_dpipe_header_fields *dst = yarg->data;
-	unsigned int n_dpipe_field = 0;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	int i;
-
-	parg.ys = yarg->ys;
-
-	if (dst->dpipe_field)
-		return ynl_error_parse(yarg, "attribute already present (dl-dpipe-header-fields.dpipe-field)");
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_DPIPE_FIELD) {
-			n_dpipe_field++;
-		}
-	}
-
-	if (n_dpipe_field) {
-		dst->dpipe_field = calloc(n_dpipe_field, sizeof(*dst->dpipe_field));
-		dst->n_dpipe_field = n_dpipe_field;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_dpipe_field_nest;
-		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_FIELD) {
-				parg.data = &dst->dpipe_field[i];
-				if (devlink_dl_dpipe_field_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-
-	return 0;
-}
-
-void devlink_dl_resource_list_free(struct devlink_dl_resource_list *obj)
-{
-	unsigned int i;
-
-	for (i = 0; i < obj->n_resource; i++)
-		devlink_dl_resource_free(&obj->resource[i]);
-	free(obj->resource);
-}
-
-int devlink_dl_resource_list_parse(struct ynl_parse_arg *yarg,
-				   const struct nlattr *nested)
-{
-	struct devlink_dl_resource_list *dst = yarg->data;
-	unsigned int n_resource = 0;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	int i;
-
-	parg.ys = yarg->ys;
-
-	if (dst->resource)
-		return ynl_error_parse(yarg, "attribute already present (dl-resource-list.resource)");
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_RESOURCE) {
-			n_resource++;
-		}
-	}
-
-	if (n_resource) {
-		dst->resource = calloc(n_resource, sizeof(*dst->resource));
-		dst->n_resource = n_resource;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_resource_nest;
-		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_RESOURCE) {
-				parg.data = &dst->resource[i];
-				if (devlink_dl_resource_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-
-	return 0;
-}
-
-void devlink_dl_reload_act_info_free(struct devlink_dl_reload_act_info *obj)
-{
-	unsigned int i;
-
-	for (i = 0; i < obj->n_reload_action_stats; i++)
-		devlink_dl_reload_act_stats_free(&obj->reload_action_stats[i]);
-	free(obj->reload_action_stats);
-}
-
-int devlink_dl_reload_act_info_parse(struct ynl_parse_arg *yarg,
-				     const struct nlattr *nested)
-{
-	struct devlink_dl_reload_act_info *dst = yarg->data;
-	unsigned int n_reload_action_stats = 0;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	int i;
-
-	parg.ys = yarg->ys;
-
-	if (dst->reload_action_stats)
-		return ynl_error_parse(yarg, "attribute already present (dl-reload-act-info.reload-action-stats)");
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_RELOAD_ACTION) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.reload_action = 1;
-			dst->reload_action = mnl_attr_get_u8(attr);
-		} else if (type == DEVLINK_ATTR_RELOAD_ACTION_STATS) {
-			n_reload_action_stats++;
-		}
-	}
-
-	if (n_reload_action_stats) {
-		dst->reload_action_stats = calloc(n_reload_action_stats, sizeof(*dst->reload_action_stats));
-		dst->n_reload_action_stats = n_reload_action_stats;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_reload_act_stats_nest;
-		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_RELOAD_ACTION_STATS) {
-				parg.data = &dst->reload_action_stats[i];
-				if (devlink_dl_reload_act_stats_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-
-	return 0;
-}
-
-void devlink_dl_dpipe_table_free(struct devlink_dl_dpipe_table *obj)
-{
-	free(obj->dpipe_table_name);
-	devlink_dl_dpipe_table_matches_free(&obj->dpipe_table_matches);
-	devlink_dl_dpipe_table_actions_free(&obj->dpipe_table_actions);
-}
-
-int devlink_dl_dpipe_table_parse(struct ynl_parse_arg *yarg,
-				 const struct nlattr *nested)
-{
-	struct devlink_dl_dpipe_table *dst = yarg->data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_DPIPE_TABLE_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dpipe_table_name_len = len;
-			dst->dpipe_table_name = malloc(len + 1);
-			memcpy(dst->dpipe_table_name, mnl_attr_get_str(attr), len);
-			dst->dpipe_table_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DPIPE_TABLE_SIZE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_table_size = 1;
-			dst->dpipe_table_size = mnl_attr_get_u64(attr);
-		} else if (type == DEVLINK_ATTR_DPIPE_TABLE_MATCHES) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_table_matches = 1;
-
-			parg.rsp_policy = &devlink_dl_dpipe_table_matches_nest;
-			parg.data = &dst->dpipe_table_matches;
-			if (devlink_dl_dpipe_table_matches_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == DEVLINK_ATTR_DPIPE_TABLE_ACTIONS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_table_actions = 1;
-
-			parg.rsp_policy = &devlink_dl_dpipe_table_actions_nest;
-			parg.data = &dst->dpipe_table_actions;
-			if (devlink_dl_dpipe_table_actions_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_table_counters_enabled = 1;
-			dst->dpipe_table_counters_enabled = mnl_attr_get_u8(attr);
-		} else if (type == DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_table_resource_id = 1;
-			dst->dpipe_table_resource_id = mnl_attr_get_u64(attr);
-		} else if (type == DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_table_resource_units = 1;
-			dst->dpipe_table_resource_units = mnl_attr_get_u64(attr);
-		}
-	}
-
-	return 0;
-}
-
-void devlink_dl_dpipe_entry_free(struct devlink_dl_dpipe_entry *obj)
-{
-	devlink_dl_dpipe_entry_match_values_free(&obj->dpipe_entry_match_values);
-	devlink_dl_dpipe_entry_action_values_free(&obj->dpipe_entry_action_values);
-}
-
-int devlink_dl_dpipe_entry_parse(struct ynl_parse_arg *yarg,
-				 const struct nlattr *nested)
-{
-	struct devlink_dl_dpipe_entry *dst = yarg->data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_DPIPE_ENTRY_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_entry_index = 1;
-			dst->dpipe_entry_index = mnl_attr_get_u64(attr);
-		} else if (type == DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_entry_match_values = 1;
-
-			parg.rsp_policy = &devlink_dl_dpipe_entry_match_values_nest;
-			parg.data = &dst->dpipe_entry_match_values;
-			if (devlink_dl_dpipe_entry_match_values_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_entry_action_values = 1;
-
-			parg.rsp_policy = &devlink_dl_dpipe_entry_action_values_nest;
-			parg.data = &dst->dpipe_entry_action_values;
-			if (devlink_dl_dpipe_entry_action_values_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == DEVLINK_ATTR_DPIPE_ENTRY_COUNTER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_entry_counter = 1;
-			dst->dpipe_entry_counter = mnl_attr_get_u64(attr);
-		}
-	}
-
-	return 0;
-}
-
-void devlink_dl_dpipe_header_free(struct devlink_dl_dpipe_header *obj)
-{
-	free(obj->dpipe_header_name);
-	devlink_dl_dpipe_header_fields_free(&obj->dpipe_header_fields);
-}
-
-int devlink_dl_dpipe_header_parse(struct ynl_parse_arg *yarg,
-				  const struct nlattr *nested)
-{
-	struct devlink_dl_dpipe_header *dst = yarg->data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_DPIPE_HEADER_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dpipe_header_name_len = len;
-			dst->dpipe_header_name = malloc(len + 1);
-			memcpy(dst->dpipe_header_name, mnl_attr_get_str(attr), len);
-			dst->dpipe_header_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DPIPE_HEADER_ID) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_header_id = 1;
-			dst->dpipe_header_id = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_DPIPE_HEADER_GLOBAL) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_header_global = 1;
-			dst->dpipe_header_global = mnl_attr_get_u8(attr);
-		} else if (type == DEVLINK_ATTR_DPIPE_HEADER_FIELDS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_header_fields = 1;
-
-			parg.rsp_policy = &devlink_dl_dpipe_header_fields_nest;
-			parg.data = &dst->dpipe_header_fields;
-			if (devlink_dl_dpipe_header_fields_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		}
-	}
-
-	return 0;
-}
-
-void devlink_dl_reload_stats_free(struct devlink_dl_reload_stats *obj)
-{
-	unsigned int i;
-
-	for (i = 0; i < obj->n_reload_action_info; i++)
-		devlink_dl_reload_act_info_free(&obj->reload_action_info[i]);
-	free(obj->reload_action_info);
-}
-
-int devlink_dl_reload_stats_parse(struct ynl_parse_arg *yarg,
-				  const struct nlattr *nested)
-{
-	struct devlink_dl_reload_stats *dst = yarg->data;
-	unsigned int n_reload_action_info = 0;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	int i;
-
-	parg.ys = yarg->ys;
-
-	if (dst->reload_action_info)
-		return ynl_error_parse(yarg, "attribute already present (dl-reload-stats.reload-action-info)");
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_RELOAD_ACTION_INFO) {
-			n_reload_action_info++;
-		}
-	}
-
-	if (n_reload_action_info) {
-		dst->reload_action_info = calloc(n_reload_action_info, sizeof(*dst->reload_action_info));
-		dst->n_reload_action_info = n_reload_action_info;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_reload_act_info_nest;
-		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_RELOAD_ACTION_INFO) {
-				parg.data = &dst->reload_action_info[i];
-				if (devlink_dl_reload_act_info_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-
-	return 0;
-}
-
-void devlink_dl_dpipe_tables_free(struct devlink_dl_dpipe_tables *obj)
-{
-	unsigned int i;
-
-	for (i = 0; i < obj->n_dpipe_table; i++)
-		devlink_dl_dpipe_table_free(&obj->dpipe_table[i]);
-	free(obj->dpipe_table);
-}
-
-int devlink_dl_dpipe_tables_parse(struct ynl_parse_arg *yarg,
-				  const struct nlattr *nested)
-{
-	struct devlink_dl_dpipe_tables *dst = yarg->data;
-	unsigned int n_dpipe_table = 0;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	int i;
-
-	parg.ys = yarg->ys;
-
-	if (dst->dpipe_table)
-		return ynl_error_parse(yarg, "attribute already present (dl-dpipe-tables.dpipe-table)");
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_DPIPE_TABLE) {
-			n_dpipe_table++;
-		}
-	}
-
-	if (n_dpipe_table) {
-		dst->dpipe_table = calloc(n_dpipe_table, sizeof(*dst->dpipe_table));
-		dst->n_dpipe_table = n_dpipe_table;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_dpipe_table_nest;
-		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_TABLE) {
-				parg.data = &dst->dpipe_table[i];
-				if (devlink_dl_dpipe_table_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-
-	return 0;
-}
-
-void devlink_dl_dpipe_entries_free(struct devlink_dl_dpipe_entries *obj)
-{
-	unsigned int i;
-
-	for (i = 0; i < obj->n_dpipe_entry; i++)
-		devlink_dl_dpipe_entry_free(&obj->dpipe_entry[i]);
-	free(obj->dpipe_entry);
-}
-
-int devlink_dl_dpipe_entries_parse(struct ynl_parse_arg *yarg,
-				   const struct nlattr *nested)
-{
-	struct devlink_dl_dpipe_entries *dst = yarg->data;
-	unsigned int n_dpipe_entry = 0;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	int i;
-
-	parg.ys = yarg->ys;
-
-	if (dst->dpipe_entry)
-		return ynl_error_parse(yarg, "attribute already present (dl-dpipe-entries.dpipe-entry)");
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_DPIPE_ENTRY) {
-			n_dpipe_entry++;
-		}
-	}
-
-	if (n_dpipe_entry) {
-		dst->dpipe_entry = calloc(n_dpipe_entry, sizeof(*dst->dpipe_entry));
-		dst->n_dpipe_entry = n_dpipe_entry;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_dpipe_entry_nest;
-		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_ENTRY) {
-				parg.data = &dst->dpipe_entry[i];
-				if (devlink_dl_dpipe_entry_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-
-	return 0;
-}
-
-void devlink_dl_dpipe_headers_free(struct devlink_dl_dpipe_headers *obj)
-{
-	unsigned int i;
-
-	for (i = 0; i < obj->n_dpipe_header; i++)
-		devlink_dl_dpipe_header_free(&obj->dpipe_header[i]);
-	free(obj->dpipe_header);
-}
-
-int devlink_dl_dpipe_headers_parse(struct ynl_parse_arg *yarg,
-				   const struct nlattr *nested)
-{
-	struct devlink_dl_dpipe_headers *dst = yarg->data;
-	unsigned int n_dpipe_header = 0;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	int i;
-
-	parg.ys = yarg->ys;
-
-	if (dst->dpipe_header)
-		return ynl_error_parse(yarg, "attribute already present (dl-dpipe-headers.dpipe-header)");
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_DPIPE_HEADER) {
-			n_dpipe_header++;
-		}
-	}
-
-	if (n_dpipe_header) {
-		dst->dpipe_header = calloc(n_dpipe_header, sizeof(*dst->dpipe_header));
-		dst->n_dpipe_header = n_dpipe_header;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_dpipe_header_nest;
-		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_HEADER) {
-				parg.data = &dst->dpipe_header[i];
-				if (devlink_dl_dpipe_header_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-
-	return 0;
-}
-
-void devlink_dl_dev_stats_free(struct devlink_dl_dev_stats *obj)
-{
-	devlink_dl_reload_stats_free(&obj->reload_stats);
-	devlink_dl_reload_stats_free(&obj->remote_reload_stats);
-}
-
-int devlink_dl_dev_stats_parse(struct ynl_parse_arg *yarg,
-			       const struct nlattr *nested)
-{
-	struct devlink_dl_dev_stats *dst = yarg->data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_RELOAD_STATS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.reload_stats = 1;
-
-			parg.rsp_policy = &devlink_dl_reload_stats_nest;
-			parg.data = &dst->reload_stats;
-			if (devlink_dl_reload_stats_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == DEVLINK_ATTR_REMOTE_RELOAD_STATS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.remote_reload_stats = 1;
-
-			parg.rsp_policy = &devlink_dl_reload_stats_nest;
-			parg.data = &dst->remote_reload_stats;
-			if (devlink_dl_reload_stats_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		}
-	}
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_GET ============== */
-/* DEVLINK_CMD_GET - do */
-void devlink_get_req_free(struct devlink_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-void devlink_get_rsp_free(struct devlink_get_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	devlink_dl_dev_stats_free(&rsp->dev_stats);
-	free(rsp);
-}
-
-int devlink_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ynl_parse_arg *yarg = data;
-	struct devlink_get_rsp *dst;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_RELOAD_FAILED) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.reload_failed = 1;
-			dst->reload_failed = mnl_attr_get_u8(attr);
-		} else if (type == DEVLINK_ATTR_DEV_STATS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dev_stats = 1;
-
-			parg.rsp_policy = &devlink_dl_dev_stats_nest;
-			parg.data = &dst->dev_stats;
-			if (devlink_dl_dev_stats_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_get_rsp *
-devlink_get(struct ynl_sock *ys, struct devlink_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_get_rsp_parse;
-	yrs.rsp_cmd = 3;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* DEVLINK_CMD_GET - dump */
-void devlink_get_list_free(struct devlink_get_list *rsp)
-{
-	struct devlink_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		devlink_dl_dev_stats_free(&rsp->obj.dev_stats);
-		free(rsp);
-	}
-}
-
-struct devlink_get_list *devlink_get_dump(struct ynl_sock *ys)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_get_list);
-	yds.cb = devlink_get_rsp_parse;
-	yds.rsp_cmd = 3;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_GET, 1);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	devlink_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_PORT_GET ============== */
-/* DEVLINK_CMD_PORT_GET - do */
-void devlink_port_get_req_free(struct devlink_port_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-void devlink_port_get_rsp_free(struct devlink_port_get_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	free(rsp);
-}
-
-int devlink_port_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ynl_parse_arg *yarg = data;
-	struct devlink_port_get_rsp *dst;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.port_index = 1;
-			dst->port_index = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_port_get_rsp *
-devlink_port_get(struct ynl_sock *ys, struct devlink_port_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_port_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_port_get_rsp_parse;
-	yrs.rsp_cmd = 7;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_port_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* DEVLINK_CMD_PORT_GET - dump */
-int devlink_port_get_rsp_dump_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct devlink_port_get_rsp_dump *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.port_index = 1;
-			dst->port_index = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-void devlink_port_get_rsp_list_free(struct devlink_port_get_rsp_list *rsp)
-{
-	struct devlink_port_get_rsp_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		free(rsp);
-	}
-}
-
-struct devlink_port_get_rsp_list *
-devlink_port_get_dump(struct ynl_sock *ys,
-		      struct devlink_port_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_port_get_rsp_list);
-	yds.cb = devlink_port_get_rsp_dump_parse;
-	yds.rsp_cmd = 7;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_PORT_GET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	devlink_port_get_rsp_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_PORT_SET ============== */
-/* DEVLINK_CMD_PORT_SET - do */
-void devlink_port_set_req_free(struct devlink_port_set_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	devlink_dl_port_function_free(&req->port_function);
-	free(req);
-}
-
-int devlink_port_set(struct ynl_sock *ys, struct devlink_port_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_SET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.port_type)
-		mnl_attr_put_u16(nlh, DEVLINK_ATTR_PORT_TYPE, req->port_type);
-	if (req->_present.port_function)
-		devlink_dl_port_function_put(nlh, DEVLINK_ATTR_PORT_FUNCTION, &req->port_function);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_PORT_NEW ============== */
-/* DEVLINK_CMD_PORT_NEW - do */
-void devlink_port_new_req_free(struct devlink_port_new_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-void devlink_port_new_rsp_free(struct devlink_port_new_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	free(rsp);
-}
-
-int devlink_port_new_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ynl_parse_arg *yarg = data;
-	struct devlink_port_new_rsp *dst;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.port_index = 1;
-			dst->port_index = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_port_new_rsp *
-devlink_port_new(struct ynl_sock *ys, struct devlink_port_new_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_port_new_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_NEW, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.port_flavour)
-		mnl_attr_put_u16(nlh, DEVLINK_ATTR_PORT_FLAVOUR, req->port_flavour);
-	if (req->_present.port_pci_pf_number)
-		mnl_attr_put_u16(nlh, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, req->port_pci_pf_number);
-	if (req->_present.port_pci_sf_number)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_PCI_SF_NUMBER, req->port_pci_sf_number);
-	if (req->_present.port_controller_number)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, req->port_controller_number);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_port_new_rsp_parse;
-	yrs.rsp_cmd = DEVLINK_CMD_PORT_NEW;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_port_new_rsp_free(rsp);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_PORT_DEL ============== */
-/* DEVLINK_CMD_PORT_DEL - do */
-void devlink_port_del_req_free(struct devlink_port_del_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-int devlink_port_del(struct ynl_sock *ys, struct devlink_port_del_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_DEL, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_PORT_SPLIT ============== */
-/* DEVLINK_CMD_PORT_SPLIT - do */
-void devlink_port_split_req_free(struct devlink_port_split_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-int devlink_port_split(struct ynl_sock *ys, struct devlink_port_split_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_SPLIT, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.port_split_count)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_SPLIT_COUNT, req->port_split_count);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_PORT_UNSPLIT ============== */
-/* DEVLINK_CMD_PORT_UNSPLIT - do */
-void devlink_port_unsplit_req_free(struct devlink_port_unsplit_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-int devlink_port_unsplit(struct ynl_sock *ys,
-			 struct devlink_port_unsplit_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_UNSPLIT, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_SB_GET ============== */
-/* DEVLINK_CMD_SB_GET - do */
-void devlink_sb_get_req_free(struct devlink_sb_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-void devlink_sb_get_rsp_free(struct devlink_sb_get_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	free(rsp);
-}
-
-int devlink_sb_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ynl_parse_arg *yarg = data;
-	struct devlink_sb_get_rsp *dst;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_SB_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.sb_index = 1;
-			dst->sb_index = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_sb_get_rsp *
-devlink_sb_get(struct ynl_sock *ys, struct devlink_sb_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_sb_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.sb_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_sb_get_rsp_parse;
-	yrs.rsp_cmd = 13;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_sb_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* DEVLINK_CMD_SB_GET - dump */
-void devlink_sb_get_list_free(struct devlink_sb_get_list *rsp)
-{
-	struct devlink_sb_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		free(rsp);
-	}
-}
-
-struct devlink_sb_get_list *
-devlink_sb_get_dump(struct ynl_sock *ys, struct devlink_sb_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_sb_get_list);
-	yds.cb = devlink_sb_get_rsp_parse;
-	yds.rsp_cmd = 13;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_GET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	devlink_sb_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_SB_POOL_GET ============== */
-/* DEVLINK_CMD_SB_POOL_GET - do */
-void devlink_sb_pool_get_req_free(struct devlink_sb_pool_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-void devlink_sb_pool_get_rsp_free(struct devlink_sb_pool_get_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	free(rsp);
-}
-
-int devlink_sb_pool_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct devlink_sb_pool_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_SB_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.sb_index = 1;
-			dst->sb_index = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_SB_POOL_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.sb_pool_index = 1;
-			dst->sb_pool_index = mnl_attr_get_u16(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_sb_pool_get_rsp *
-devlink_sb_pool_get(struct ynl_sock *ys, struct devlink_sb_pool_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_sb_pool_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_POOL_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.sb_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
-	if (req->_present.sb_pool_index)
-		mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_POOL_INDEX, req->sb_pool_index);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_sb_pool_get_rsp_parse;
-	yrs.rsp_cmd = 17;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_sb_pool_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* DEVLINK_CMD_SB_POOL_GET - dump */
-void devlink_sb_pool_get_list_free(struct devlink_sb_pool_get_list *rsp)
-{
-	struct devlink_sb_pool_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		free(rsp);
-	}
-}
-
-struct devlink_sb_pool_get_list *
-devlink_sb_pool_get_dump(struct ynl_sock *ys,
-			 struct devlink_sb_pool_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_sb_pool_get_list);
-	yds.cb = devlink_sb_pool_get_rsp_parse;
-	yds.rsp_cmd = 17;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_POOL_GET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	devlink_sb_pool_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_SB_POOL_SET ============== */
-/* DEVLINK_CMD_SB_POOL_SET - do */
-void devlink_sb_pool_set_req_free(struct devlink_sb_pool_set_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-int devlink_sb_pool_set(struct ynl_sock *ys,
-			struct devlink_sb_pool_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_POOL_SET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.sb_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
-	if (req->_present.sb_pool_index)
-		mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_POOL_INDEX, req->sb_pool_index);
-	if (req->_present.sb_pool_threshold_type)
-		mnl_attr_put_u8(nlh, DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE, req->sb_pool_threshold_type);
-	if (req->_present.sb_pool_size)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_POOL_SIZE, req->sb_pool_size);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_SB_PORT_POOL_GET ============== */
-/* DEVLINK_CMD_SB_PORT_POOL_GET - do */
-void
-devlink_sb_port_pool_get_req_free(struct devlink_sb_port_pool_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-void
-devlink_sb_port_pool_get_rsp_free(struct devlink_sb_port_pool_get_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	free(rsp);
-}
-
-int devlink_sb_port_pool_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct devlink_sb_port_pool_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.port_index = 1;
-			dst->port_index = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_SB_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.sb_index = 1;
-			dst->sb_index = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_SB_POOL_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.sb_pool_index = 1;
-			dst->sb_pool_index = mnl_attr_get_u16(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_sb_port_pool_get_rsp *
-devlink_sb_port_pool_get(struct ynl_sock *ys,
-			 struct devlink_sb_port_pool_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_sb_port_pool_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_PORT_POOL_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.sb_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
-	if (req->_present.sb_pool_index)
-		mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_POOL_INDEX, req->sb_pool_index);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_sb_port_pool_get_rsp_parse;
-	yrs.rsp_cmd = 21;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_sb_port_pool_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* DEVLINK_CMD_SB_PORT_POOL_GET - dump */
-void
-devlink_sb_port_pool_get_list_free(struct devlink_sb_port_pool_get_list *rsp)
-{
-	struct devlink_sb_port_pool_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		free(rsp);
-	}
-}
-
-struct devlink_sb_port_pool_get_list *
-devlink_sb_port_pool_get_dump(struct ynl_sock *ys,
-			      struct devlink_sb_port_pool_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_sb_port_pool_get_list);
-	yds.cb = devlink_sb_port_pool_get_rsp_parse;
-	yds.rsp_cmd = 21;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_PORT_POOL_GET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	devlink_sb_port_pool_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_SB_PORT_POOL_SET ============== */
-/* DEVLINK_CMD_SB_PORT_POOL_SET - do */
-void
-devlink_sb_port_pool_set_req_free(struct devlink_sb_port_pool_set_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-int devlink_sb_port_pool_set(struct ynl_sock *ys,
-			     struct devlink_sb_port_pool_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_PORT_POOL_SET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.sb_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
-	if (req->_present.sb_pool_index)
-		mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_POOL_INDEX, req->sb_pool_index);
-	if (req->_present.sb_threshold)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_THRESHOLD, req->sb_threshold);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_SB_TC_POOL_BIND_GET ============== */
-/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - do */
-void
-devlink_sb_tc_pool_bind_get_req_free(struct devlink_sb_tc_pool_bind_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-void
-devlink_sb_tc_pool_bind_get_rsp_free(struct devlink_sb_tc_pool_bind_get_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	free(rsp);
-}
-
-int devlink_sb_tc_pool_bind_get_rsp_parse(const struct nlmsghdr *nlh,
-					  void *data)
-{
-	struct devlink_sb_tc_pool_bind_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.port_index = 1;
-			dst->port_index = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_SB_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.sb_index = 1;
-			dst->sb_index = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_SB_POOL_TYPE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.sb_pool_type = 1;
-			dst->sb_pool_type = mnl_attr_get_u8(attr);
-		} else if (type == DEVLINK_ATTR_SB_TC_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.sb_tc_index = 1;
-			dst->sb_tc_index = mnl_attr_get_u16(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_sb_tc_pool_bind_get_rsp *
-devlink_sb_tc_pool_bind_get(struct ynl_sock *ys,
-			    struct devlink_sb_tc_pool_bind_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_sb_tc_pool_bind_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_TC_POOL_BIND_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.sb_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
-	if (req->_present.sb_pool_type)
-		mnl_attr_put_u8(nlh, DEVLINK_ATTR_SB_POOL_TYPE, req->sb_pool_type);
-	if (req->_present.sb_tc_index)
-		mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_TC_INDEX, req->sb_tc_index);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_sb_tc_pool_bind_get_rsp_parse;
-	yrs.rsp_cmd = 25;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_sb_tc_pool_bind_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - dump */
-void
-devlink_sb_tc_pool_bind_get_list_free(struct devlink_sb_tc_pool_bind_get_list *rsp)
-{
-	struct devlink_sb_tc_pool_bind_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		free(rsp);
-	}
-}
-
-struct devlink_sb_tc_pool_bind_get_list *
-devlink_sb_tc_pool_bind_get_dump(struct ynl_sock *ys,
-				 struct devlink_sb_tc_pool_bind_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_sb_tc_pool_bind_get_list);
-	yds.cb = devlink_sb_tc_pool_bind_get_rsp_parse;
-	yds.rsp_cmd = 25;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_TC_POOL_BIND_GET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	devlink_sb_tc_pool_bind_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_SB_TC_POOL_BIND_SET ============== */
-/* DEVLINK_CMD_SB_TC_POOL_BIND_SET - do */
-void
-devlink_sb_tc_pool_bind_set_req_free(struct devlink_sb_tc_pool_bind_set_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-int devlink_sb_tc_pool_bind_set(struct ynl_sock *ys,
-				struct devlink_sb_tc_pool_bind_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_TC_POOL_BIND_SET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.sb_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
-	if (req->_present.sb_pool_index)
-		mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_POOL_INDEX, req->sb_pool_index);
-	if (req->_present.sb_pool_type)
-		mnl_attr_put_u8(nlh, DEVLINK_ATTR_SB_POOL_TYPE, req->sb_pool_type);
-	if (req->_present.sb_tc_index)
-		mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_TC_INDEX, req->sb_tc_index);
-	if (req->_present.sb_threshold)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_THRESHOLD, req->sb_threshold);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_SB_OCC_SNAPSHOT ============== */
-/* DEVLINK_CMD_SB_OCC_SNAPSHOT - do */
-void devlink_sb_occ_snapshot_req_free(struct devlink_sb_occ_snapshot_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-int devlink_sb_occ_snapshot(struct ynl_sock *ys,
-			    struct devlink_sb_occ_snapshot_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_OCC_SNAPSHOT, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.sb_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_SB_OCC_MAX_CLEAR ============== */
-/* DEVLINK_CMD_SB_OCC_MAX_CLEAR - do */
-void
-devlink_sb_occ_max_clear_req_free(struct devlink_sb_occ_max_clear_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-int devlink_sb_occ_max_clear(struct ynl_sock *ys,
-			     struct devlink_sb_occ_max_clear_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_OCC_MAX_CLEAR, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.sb_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_ESWITCH_GET ============== */
-/* DEVLINK_CMD_ESWITCH_GET - do */
-void devlink_eswitch_get_req_free(struct devlink_eswitch_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-void devlink_eswitch_get_rsp_free(struct devlink_eswitch_get_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	free(rsp);
-}
-
-int devlink_eswitch_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct devlink_eswitch_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_ESWITCH_MODE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.eswitch_mode = 1;
-			dst->eswitch_mode = mnl_attr_get_u16(attr);
-		} else if (type == DEVLINK_ATTR_ESWITCH_INLINE_MODE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.eswitch_inline_mode = 1;
-			dst->eswitch_inline_mode = mnl_attr_get_u16(attr);
-		} else if (type == DEVLINK_ATTR_ESWITCH_ENCAP_MODE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.eswitch_encap_mode = 1;
-			dst->eswitch_encap_mode = mnl_attr_get_u8(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_eswitch_get_rsp *
-devlink_eswitch_get(struct ynl_sock *ys, struct devlink_eswitch_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_eswitch_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_ESWITCH_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_eswitch_get_rsp_parse;
-	yrs.rsp_cmd = DEVLINK_CMD_ESWITCH_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_eswitch_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_ESWITCH_SET ============== */
-/* DEVLINK_CMD_ESWITCH_SET - do */
-void devlink_eswitch_set_req_free(struct devlink_eswitch_set_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-int devlink_eswitch_set(struct ynl_sock *ys,
-			struct devlink_eswitch_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_ESWITCH_SET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.eswitch_mode)
-		mnl_attr_put_u16(nlh, DEVLINK_ATTR_ESWITCH_MODE, req->eswitch_mode);
-	if (req->_present.eswitch_inline_mode)
-		mnl_attr_put_u16(nlh, DEVLINK_ATTR_ESWITCH_INLINE_MODE, req->eswitch_inline_mode);
-	if (req->_present.eswitch_encap_mode)
-		mnl_attr_put_u8(nlh, DEVLINK_ATTR_ESWITCH_ENCAP_MODE, req->eswitch_encap_mode);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_DPIPE_TABLE_GET ============== */
-/* DEVLINK_CMD_DPIPE_TABLE_GET - do */
-void devlink_dpipe_table_get_req_free(struct devlink_dpipe_table_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->dpipe_table_name);
-	free(req);
-}
-
-void devlink_dpipe_table_get_rsp_free(struct devlink_dpipe_table_get_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	devlink_dl_dpipe_tables_free(&rsp->dpipe_tables);
-	free(rsp);
-}
-
-int devlink_dpipe_table_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct devlink_dpipe_table_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DPIPE_TABLES) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_tables = 1;
-
-			parg.rsp_policy = &devlink_dl_dpipe_tables_nest;
-			parg.data = &dst->dpipe_tables;
-			if (devlink_dl_dpipe_tables_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_dpipe_table_get_rsp *
-devlink_dpipe_table_get(struct ynl_sock *ys,
-			struct devlink_dpipe_table_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_dpipe_table_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_DPIPE_TABLE_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.dpipe_table_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DPIPE_TABLE_NAME, req->dpipe_table_name);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_dpipe_table_get_rsp_parse;
-	yrs.rsp_cmd = DEVLINK_CMD_DPIPE_TABLE_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_dpipe_table_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_DPIPE_ENTRIES_GET ============== */
-/* DEVLINK_CMD_DPIPE_ENTRIES_GET - do */
-void
-devlink_dpipe_entries_get_req_free(struct devlink_dpipe_entries_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->dpipe_table_name);
-	free(req);
-}
-
-void
-devlink_dpipe_entries_get_rsp_free(struct devlink_dpipe_entries_get_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	devlink_dl_dpipe_entries_free(&rsp->dpipe_entries);
-	free(rsp);
-}
-
-int devlink_dpipe_entries_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct devlink_dpipe_entries_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DPIPE_ENTRIES) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_entries = 1;
-
-			parg.rsp_policy = &devlink_dl_dpipe_entries_nest;
-			parg.data = &dst->dpipe_entries;
-			if (devlink_dl_dpipe_entries_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_dpipe_entries_get_rsp *
-devlink_dpipe_entries_get(struct ynl_sock *ys,
-			  struct devlink_dpipe_entries_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_dpipe_entries_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_DPIPE_ENTRIES_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.dpipe_table_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DPIPE_TABLE_NAME, req->dpipe_table_name);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_dpipe_entries_get_rsp_parse;
-	yrs.rsp_cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_dpipe_entries_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_DPIPE_HEADERS_GET ============== */
-/* DEVLINK_CMD_DPIPE_HEADERS_GET - do */
-void
-devlink_dpipe_headers_get_req_free(struct devlink_dpipe_headers_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-void
-devlink_dpipe_headers_get_rsp_free(struct devlink_dpipe_headers_get_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	devlink_dl_dpipe_headers_free(&rsp->dpipe_headers);
-	free(rsp);
-}
-
-int devlink_dpipe_headers_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct devlink_dpipe_headers_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DPIPE_HEADERS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dpipe_headers = 1;
-
-			parg.rsp_policy = &devlink_dl_dpipe_headers_nest;
-			parg.data = &dst->dpipe_headers;
-			if (devlink_dl_dpipe_headers_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_dpipe_headers_get_rsp *
-devlink_dpipe_headers_get(struct ynl_sock *ys,
-			  struct devlink_dpipe_headers_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_dpipe_headers_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_DPIPE_HEADERS_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_dpipe_headers_get_rsp_parse;
-	yrs.rsp_cmd = DEVLINK_CMD_DPIPE_HEADERS_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_dpipe_headers_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET ============== */
-/* DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET - do */
-void
-devlink_dpipe_table_counters_set_req_free(struct devlink_dpipe_table_counters_set_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->dpipe_table_name);
-	free(req);
-}
-
-int devlink_dpipe_table_counters_set(struct ynl_sock *ys,
-				     struct devlink_dpipe_table_counters_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.dpipe_table_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DPIPE_TABLE_NAME, req->dpipe_table_name);
-	if (req->_present.dpipe_table_counters_enabled)
-		mnl_attr_put_u8(nlh, DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED, req->dpipe_table_counters_enabled);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_RESOURCE_SET ============== */
-/* DEVLINK_CMD_RESOURCE_SET - do */
-void devlink_resource_set_req_free(struct devlink_resource_set_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-int devlink_resource_set(struct ynl_sock *ys,
-			 struct devlink_resource_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RESOURCE_SET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.resource_id)
-		mnl_attr_put_u64(nlh, DEVLINK_ATTR_RESOURCE_ID, req->resource_id);
-	if (req->_present.resource_size)
-		mnl_attr_put_u64(nlh, DEVLINK_ATTR_RESOURCE_SIZE, req->resource_size);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_RESOURCE_DUMP ============== */
-/* DEVLINK_CMD_RESOURCE_DUMP - do */
-void devlink_resource_dump_req_free(struct devlink_resource_dump_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-void devlink_resource_dump_rsp_free(struct devlink_resource_dump_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	devlink_dl_resource_list_free(&rsp->resource_list);
-	free(rsp);
-}
-
-int devlink_resource_dump_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct devlink_resource_dump_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_RESOURCE_LIST) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.resource_list = 1;
-
-			parg.rsp_policy = &devlink_dl_resource_list_nest;
-			parg.data = &dst->resource_list;
-			if (devlink_dl_resource_list_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_resource_dump_rsp *
-devlink_resource_dump(struct ynl_sock *ys,
-		      struct devlink_resource_dump_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_resource_dump_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RESOURCE_DUMP, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_resource_dump_rsp_parse;
-	yrs.rsp_cmd = DEVLINK_CMD_RESOURCE_DUMP;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_resource_dump_rsp_free(rsp);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_RELOAD ============== */
-/* DEVLINK_CMD_RELOAD - do */
-void devlink_reload_req_free(struct devlink_reload_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-void devlink_reload_rsp_free(struct devlink_reload_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	free(rsp);
-}
-
-int devlink_reload_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ynl_parse_arg *yarg = data;
-	struct devlink_reload_rsp *dst;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.reload_actions_performed = 1;
-			memcpy(&dst->reload_actions_performed, mnl_attr_get_payload(attr), sizeof(struct nla_bitfield32));
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_reload_rsp *
-devlink_reload(struct ynl_sock *ys, struct devlink_reload_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_reload_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RELOAD, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.reload_action)
-		mnl_attr_put_u8(nlh, DEVLINK_ATTR_RELOAD_ACTION, req->reload_action);
-	if (req->_present.reload_limits)
-		mnl_attr_put(nlh, DEVLINK_ATTR_RELOAD_LIMITS, sizeof(struct nla_bitfield32), &req->reload_limits);
-	if (req->_present.netns_pid)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_NETNS_PID, req->netns_pid);
-	if (req->_present.netns_fd)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_NETNS_FD, req->netns_fd);
-	if (req->_present.netns_id)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_NETNS_ID, req->netns_id);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_reload_rsp_parse;
-	yrs.rsp_cmd = DEVLINK_CMD_RELOAD;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_reload_rsp_free(rsp);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_PARAM_GET ============== */
-/* DEVLINK_CMD_PARAM_GET - do */
-void devlink_param_get_req_free(struct devlink_param_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->param_name);
-	free(req);
-}
-
-void devlink_param_get_rsp_free(struct devlink_param_get_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	free(rsp->param_name);
-	free(rsp);
-}
-
-int devlink_param_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct devlink_param_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_PARAM_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.param_name_len = len;
-			dst->param_name = malloc(len + 1);
-			memcpy(dst->param_name, mnl_attr_get_str(attr), len);
-			dst->param_name[len] = 0;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_param_get_rsp *
-devlink_param_get(struct ynl_sock *ys, struct devlink_param_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_param_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PARAM_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.param_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_PARAM_NAME, req->param_name);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_param_get_rsp_parse;
-	yrs.rsp_cmd = DEVLINK_CMD_PARAM_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_param_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* DEVLINK_CMD_PARAM_GET - dump */
-void devlink_param_get_list_free(struct devlink_param_get_list *rsp)
-{
-	struct devlink_param_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		free(rsp->obj.param_name);
-		free(rsp);
-	}
-}
-
-struct devlink_param_get_list *
-devlink_param_get_dump(struct ynl_sock *ys,
-		       struct devlink_param_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_param_get_list);
-	yds.cb = devlink_param_get_rsp_parse;
-	yds.rsp_cmd = DEVLINK_CMD_PARAM_GET;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_PARAM_GET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	devlink_param_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_PARAM_SET ============== */
-/* DEVLINK_CMD_PARAM_SET - do */
-void devlink_param_set_req_free(struct devlink_param_set_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->param_name);
-	free(req);
-}
-
-int devlink_param_set(struct ynl_sock *ys, struct devlink_param_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PARAM_SET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.param_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_PARAM_NAME, req->param_name);
-	if (req->_present.param_type)
-		mnl_attr_put_u8(nlh, DEVLINK_ATTR_PARAM_TYPE, req->param_type);
-	if (req->_present.param_value_cmode)
-		mnl_attr_put_u8(nlh, DEVLINK_ATTR_PARAM_VALUE_CMODE, req->param_value_cmode);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_REGION_GET ============== */
-/* DEVLINK_CMD_REGION_GET - do */
-void devlink_region_get_req_free(struct devlink_region_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->region_name);
-	free(req);
-}
-
-void devlink_region_get_rsp_free(struct devlink_region_get_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	free(rsp->region_name);
-	free(rsp);
-}
-
-int devlink_region_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct devlink_region_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.port_index = 1;
-			dst->port_index = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_REGION_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.region_name_len = len;
-			dst->region_name = malloc(len + 1);
-			memcpy(dst->region_name, mnl_attr_get_str(attr), len);
-			dst->region_name[len] = 0;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_region_get_rsp *
-devlink_region_get(struct ynl_sock *ys, struct devlink_region_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_region_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_REGION_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.region_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_REGION_NAME, req->region_name);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_region_get_rsp_parse;
-	yrs.rsp_cmd = DEVLINK_CMD_REGION_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_region_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* DEVLINK_CMD_REGION_GET - dump */
-void devlink_region_get_list_free(struct devlink_region_get_list *rsp)
-{
-	struct devlink_region_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		free(rsp->obj.region_name);
-		free(rsp);
-	}
-}
-
-struct devlink_region_get_list *
-devlink_region_get_dump(struct ynl_sock *ys,
-			struct devlink_region_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_region_get_list);
-	yds.cb = devlink_region_get_rsp_parse;
-	yds.rsp_cmd = DEVLINK_CMD_REGION_GET;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_REGION_GET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	devlink_region_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_REGION_NEW ============== */
-/* DEVLINK_CMD_REGION_NEW - do */
-void devlink_region_new_req_free(struct devlink_region_new_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->region_name);
-	free(req);
-}
-
-void devlink_region_new_rsp_free(struct devlink_region_new_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	free(rsp->region_name);
-	free(rsp);
-}
-
-int devlink_region_new_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct devlink_region_new_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.port_index = 1;
-			dst->port_index = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_REGION_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.region_name_len = len;
-			dst->region_name = malloc(len + 1);
-			memcpy(dst->region_name, mnl_attr_get_str(attr), len);
-			dst->region_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_REGION_SNAPSHOT_ID) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.region_snapshot_id = 1;
-			dst->region_snapshot_id = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_region_new_rsp *
-devlink_region_new(struct ynl_sock *ys, struct devlink_region_new_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_region_new_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_REGION_NEW, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.region_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_REGION_NAME, req->region_name);
-	if (req->_present.region_snapshot_id)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_REGION_SNAPSHOT_ID, req->region_snapshot_id);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_region_new_rsp_parse;
-	yrs.rsp_cmd = DEVLINK_CMD_REGION_NEW;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_region_new_rsp_free(rsp);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_REGION_DEL ============== */
-/* DEVLINK_CMD_REGION_DEL - do */
-void devlink_region_del_req_free(struct devlink_region_del_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->region_name);
-	free(req);
-}
-
-int devlink_region_del(struct ynl_sock *ys, struct devlink_region_del_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_REGION_DEL, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.region_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_REGION_NAME, req->region_name);
-	if (req->_present.region_snapshot_id)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_REGION_SNAPSHOT_ID, req->region_snapshot_id);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_REGION_READ ============== */
-/* DEVLINK_CMD_REGION_READ - dump */
-int devlink_region_read_rsp_dump_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct devlink_region_read_rsp_dump *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.port_index = 1;
-			dst->port_index = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_REGION_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.region_name_len = len;
-			dst->region_name = malloc(len + 1);
-			memcpy(dst->region_name, mnl_attr_get_str(attr), len);
-			dst->region_name[len] = 0;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-void
-devlink_region_read_rsp_list_free(struct devlink_region_read_rsp_list *rsp)
-{
-	struct devlink_region_read_rsp_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		free(rsp->obj.region_name);
-		free(rsp);
-	}
-}
-
-struct devlink_region_read_rsp_list *
-devlink_region_read_dump(struct ynl_sock *ys,
-			 struct devlink_region_read_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_region_read_rsp_list);
-	yds.cb = devlink_region_read_rsp_dump_parse;
-	yds.rsp_cmd = DEVLINK_CMD_REGION_READ;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_REGION_READ, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.region_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_REGION_NAME, req->region_name);
-	if (req->_present.region_snapshot_id)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_REGION_SNAPSHOT_ID, req->region_snapshot_id);
-	if (req->_present.region_direct)
-		mnl_attr_put(nlh, DEVLINK_ATTR_REGION_DIRECT, 0, NULL);
-	if (req->_present.region_chunk_addr)
-		mnl_attr_put_u64(nlh, DEVLINK_ATTR_REGION_CHUNK_ADDR, req->region_chunk_addr);
-	if (req->_present.region_chunk_len)
-		mnl_attr_put_u64(nlh, DEVLINK_ATTR_REGION_CHUNK_LEN, req->region_chunk_len);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	devlink_region_read_rsp_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_PORT_PARAM_GET ============== */
-/* DEVLINK_CMD_PORT_PARAM_GET - do */
-void devlink_port_param_get_req_free(struct devlink_port_param_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-void devlink_port_param_get_rsp_free(struct devlink_port_param_get_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	free(rsp);
-}
-
-int devlink_port_param_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct devlink_port_param_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.port_index = 1;
-			dst->port_index = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_port_param_get_rsp *
-devlink_port_param_get(struct ynl_sock *ys,
-		       struct devlink_port_param_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_port_param_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_PARAM_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_port_param_get_rsp_parse;
-	yrs.rsp_cmd = DEVLINK_CMD_PORT_PARAM_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_port_param_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* DEVLINK_CMD_PORT_PARAM_GET - dump */
-void devlink_port_param_get_list_free(struct devlink_port_param_get_list *rsp)
-{
-	struct devlink_port_param_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		free(rsp);
-	}
-}
-
-struct devlink_port_param_get_list *
-devlink_port_param_get_dump(struct ynl_sock *ys)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_port_param_get_list);
-	yds.cb = devlink_port_param_get_rsp_parse;
-	yds.rsp_cmd = DEVLINK_CMD_PORT_PARAM_GET;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_PORT_PARAM_GET, 1);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	devlink_port_param_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_PORT_PARAM_SET ============== */
-/* DEVLINK_CMD_PORT_PARAM_SET - do */
-void devlink_port_param_set_req_free(struct devlink_port_param_set_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-int devlink_port_param_set(struct ynl_sock *ys,
-			   struct devlink_port_param_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_PARAM_SET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_INFO_GET ============== */
-/* DEVLINK_CMD_INFO_GET - do */
-void devlink_info_get_req_free(struct devlink_info_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-void devlink_info_get_rsp_free(struct devlink_info_get_rsp *rsp)
-{
-	unsigned int i;
-
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	free(rsp->info_driver_name);
-	free(rsp->info_serial_number);
-	for (i = 0; i < rsp->n_info_version_fixed; i++)
-		devlink_dl_info_version_free(&rsp->info_version_fixed[i]);
-	free(rsp->info_version_fixed);
-	for (i = 0; i < rsp->n_info_version_running; i++)
-		devlink_dl_info_version_free(&rsp->info_version_running[i]);
-	free(rsp->info_version_running);
-	for (i = 0; i < rsp->n_info_version_stored; i++)
-		devlink_dl_info_version_free(&rsp->info_version_stored[i]);
-	free(rsp->info_version_stored);
-	free(rsp);
-}
-
-int devlink_info_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	unsigned int n_info_version_running = 0;
-	unsigned int n_info_version_stored = 0;
-	unsigned int n_info_version_fixed = 0;
-	struct ynl_parse_arg *yarg = data;
-	struct devlink_info_get_rsp *dst;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	int i;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	if (dst->info_version_fixed)
-		return ynl_error_parse(yarg, "attribute already present (devlink.info-version-fixed)");
-	if (dst->info_version_running)
-		return ynl_error_parse(yarg, "attribute already present (devlink.info-version-running)");
-	if (dst->info_version_stored)
-		return ynl_error_parse(yarg, "attribute already present (devlink.info-version-stored)");
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_INFO_DRIVER_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.info_driver_name_len = len;
-			dst->info_driver_name = malloc(len + 1);
-			memcpy(dst->info_driver_name, mnl_attr_get_str(attr), len);
-			dst->info_driver_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_INFO_SERIAL_NUMBER) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.info_serial_number_len = len;
-			dst->info_serial_number = malloc(len + 1);
-			memcpy(dst->info_serial_number, mnl_attr_get_str(attr), len);
-			dst->info_serial_number[len] = 0;
-		} else if (type == DEVLINK_ATTR_INFO_VERSION_FIXED) {
-			n_info_version_fixed++;
-		} else if (type == DEVLINK_ATTR_INFO_VERSION_RUNNING) {
-			n_info_version_running++;
-		} else if (type == DEVLINK_ATTR_INFO_VERSION_STORED) {
-			n_info_version_stored++;
-		}
-	}
-
-	if (n_info_version_fixed) {
-		dst->info_version_fixed = calloc(n_info_version_fixed, sizeof(*dst->info_version_fixed));
-		dst->n_info_version_fixed = n_info_version_fixed;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_info_version_nest;
-		mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_INFO_VERSION_FIXED) {
-				parg.data = &dst->info_version_fixed[i];
-				if (devlink_dl_info_version_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-	if (n_info_version_running) {
-		dst->info_version_running = calloc(n_info_version_running, sizeof(*dst->info_version_running));
-		dst->n_info_version_running = n_info_version_running;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_info_version_nest;
-		mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_INFO_VERSION_RUNNING) {
-				parg.data = &dst->info_version_running[i];
-				if (devlink_dl_info_version_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-	if (n_info_version_stored) {
-		dst->info_version_stored = calloc(n_info_version_stored, sizeof(*dst->info_version_stored));
-		dst->n_info_version_stored = n_info_version_stored;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_info_version_nest;
-		mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_INFO_VERSION_STORED) {
-				parg.data = &dst->info_version_stored[i];
-				if (devlink_dl_info_version_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_info_get_rsp *
-devlink_info_get(struct ynl_sock *ys, struct devlink_info_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_info_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_INFO_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_info_get_rsp_parse;
-	yrs.rsp_cmd = DEVLINK_CMD_INFO_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_info_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* DEVLINK_CMD_INFO_GET - dump */
-void devlink_info_get_list_free(struct devlink_info_get_list *rsp)
-{
-	struct devlink_info_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		unsigned int i;
-
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		free(rsp->obj.info_driver_name);
-		free(rsp->obj.info_serial_number);
-		for (i = 0; i < rsp->obj.n_info_version_fixed; i++)
-			devlink_dl_info_version_free(&rsp->obj.info_version_fixed[i]);
-		free(rsp->obj.info_version_fixed);
-		for (i = 0; i < rsp->obj.n_info_version_running; i++)
-			devlink_dl_info_version_free(&rsp->obj.info_version_running[i]);
-		free(rsp->obj.info_version_running);
-		for (i = 0; i < rsp->obj.n_info_version_stored; i++)
-			devlink_dl_info_version_free(&rsp->obj.info_version_stored[i]);
-		free(rsp->obj.info_version_stored);
-		free(rsp);
-	}
-}
-
-struct devlink_info_get_list *devlink_info_get_dump(struct ynl_sock *ys)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_info_get_list);
-	yds.cb = devlink_info_get_rsp_parse;
-	yds.rsp_cmd = DEVLINK_CMD_INFO_GET;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_INFO_GET, 1);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	devlink_info_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_HEALTH_REPORTER_GET ============== */
-/* DEVLINK_CMD_HEALTH_REPORTER_GET - do */
-void
-devlink_health_reporter_get_req_free(struct devlink_health_reporter_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->health_reporter_name);
-	free(req);
-}
-
-void
-devlink_health_reporter_get_rsp_free(struct devlink_health_reporter_get_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	free(rsp->health_reporter_name);
-	free(rsp);
-}
-
-int devlink_health_reporter_get_rsp_parse(const struct nlmsghdr *nlh,
-					  void *data)
-{
-	struct devlink_health_reporter_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.port_index = 1;
-			dst->port_index = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_HEALTH_REPORTER_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.health_reporter_name_len = len;
-			dst->health_reporter_name = malloc(len + 1);
-			memcpy(dst->health_reporter_name, mnl_attr_get_str(attr), len);
-			dst->health_reporter_name[len] = 0;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_health_reporter_get_rsp *
-devlink_health_reporter_get(struct ynl_sock *ys,
-			    struct devlink_health_reporter_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_health_reporter_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.health_reporter_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_health_reporter_get_rsp_parse;
-	yrs.rsp_cmd = DEVLINK_CMD_HEALTH_REPORTER_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_health_reporter_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* DEVLINK_CMD_HEALTH_REPORTER_GET - dump */
-void
-devlink_health_reporter_get_list_free(struct devlink_health_reporter_get_list *rsp)
-{
-	struct devlink_health_reporter_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		free(rsp->obj.health_reporter_name);
-		free(rsp);
-	}
-}
-
-struct devlink_health_reporter_get_list *
-devlink_health_reporter_get_dump(struct ynl_sock *ys,
-				 struct devlink_health_reporter_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_health_reporter_get_list);
-	yds.cb = devlink_health_reporter_get_rsp_parse;
-	yds.rsp_cmd = DEVLINK_CMD_HEALTH_REPORTER_GET;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_GET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	devlink_health_reporter_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_HEALTH_REPORTER_SET ============== */
-/* DEVLINK_CMD_HEALTH_REPORTER_SET - do */
-void
-devlink_health_reporter_set_req_free(struct devlink_health_reporter_set_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->health_reporter_name);
-	free(req);
-}
-
-int devlink_health_reporter_set(struct ynl_sock *ys,
-				struct devlink_health_reporter_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_SET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.health_reporter_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name);
-	if (req->_present.health_reporter_graceful_period)
-		mnl_attr_put_u64(nlh, DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD, req->health_reporter_graceful_period);
-	if (req->_present.health_reporter_auto_recover)
-		mnl_attr_put_u8(nlh, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER, req->health_reporter_auto_recover);
-	if (req->_present.health_reporter_auto_dump)
-		mnl_attr_put_u8(nlh, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP, req->health_reporter_auto_dump);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_HEALTH_REPORTER_RECOVER ============== */
-/* DEVLINK_CMD_HEALTH_REPORTER_RECOVER - do */
-void
-devlink_health_reporter_recover_req_free(struct devlink_health_reporter_recover_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->health_reporter_name);
-	free(req);
-}
-
-int devlink_health_reporter_recover(struct ynl_sock *ys,
-				    struct devlink_health_reporter_recover_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_RECOVER, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.health_reporter_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE ============== */
-/* DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE - do */
-void
-devlink_health_reporter_diagnose_req_free(struct devlink_health_reporter_diagnose_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->health_reporter_name);
-	free(req);
-}
-
-int devlink_health_reporter_diagnose(struct ynl_sock *ys,
-				     struct devlink_health_reporter_diagnose_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.health_reporter_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET ============== */
-/* DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET - dump */
-int devlink_health_reporter_dump_get_rsp_dump_parse(const struct nlmsghdr *nlh,
-						    void *data)
-{
-	struct devlink_health_reporter_dump_get_rsp_dump *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_FMSG) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.fmsg = 1;
-
-			parg.rsp_policy = &devlink_dl_fmsg_nest;
-			parg.data = &dst->fmsg;
-			if (devlink_dl_fmsg_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-void
-devlink_health_reporter_dump_get_rsp_list_free(struct devlink_health_reporter_dump_get_rsp_list *rsp)
-{
-	struct devlink_health_reporter_dump_get_rsp_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		devlink_dl_fmsg_free(&rsp->obj.fmsg);
-		free(rsp);
-	}
-}
-
-struct devlink_health_reporter_dump_get_rsp_list *
-devlink_health_reporter_dump_get_dump(struct ynl_sock *ys,
-				      struct devlink_health_reporter_dump_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_health_reporter_dump_get_rsp_list);
-	yds.cb = devlink_health_reporter_dump_get_rsp_dump_parse;
-	yds.rsp_cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.health_reporter_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	devlink_health_reporter_dump_get_rsp_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR ============== */
-/* DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR - do */
-void
-devlink_health_reporter_dump_clear_req_free(struct devlink_health_reporter_dump_clear_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->health_reporter_name);
-	free(req);
-}
-
-int devlink_health_reporter_dump_clear(struct ynl_sock *ys,
-				       struct devlink_health_reporter_dump_clear_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.health_reporter_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_FLASH_UPDATE ============== */
-/* DEVLINK_CMD_FLASH_UPDATE - do */
-void devlink_flash_update_req_free(struct devlink_flash_update_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->flash_update_file_name);
-	free(req->flash_update_component);
-	free(req);
-}
-
-int devlink_flash_update(struct ynl_sock *ys,
-			 struct devlink_flash_update_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_FLASH_UPDATE, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.flash_update_file_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME, req->flash_update_file_name);
-	if (req->_present.flash_update_component_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_FLASH_UPDATE_COMPONENT, req->flash_update_component);
-	if (req->_present.flash_update_overwrite_mask)
-		mnl_attr_put(nlh, DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK, sizeof(struct nla_bitfield32), &req->flash_update_overwrite_mask);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_TRAP_GET ============== */
-/* DEVLINK_CMD_TRAP_GET - do */
-void devlink_trap_get_req_free(struct devlink_trap_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->trap_name);
-	free(req);
-}
-
-void devlink_trap_get_rsp_free(struct devlink_trap_get_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	free(rsp->trap_name);
-	free(rsp);
-}
-
-int devlink_trap_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ynl_parse_arg *yarg = data;
-	struct devlink_trap_get_rsp *dst;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_TRAP_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.trap_name_len = len;
-			dst->trap_name = malloc(len + 1);
-			memcpy(dst->trap_name, mnl_attr_get_str(attr), len);
-			dst->trap_name[len] = 0;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_trap_get_rsp *
-devlink_trap_get(struct ynl_sock *ys, struct devlink_trap_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_trap_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_TRAP_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.trap_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_TRAP_NAME, req->trap_name);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_trap_get_rsp_parse;
-	yrs.rsp_cmd = 63;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_trap_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* DEVLINK_CMD_TRAP_GET - dump */
-void devlink_trap_get_list_free(struct devlink_trap_get_list *rsp)
-{
-	struct devlink_trap_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		free(rsp->obj.trap_name);
-		free(rsp);
-	}
-}
-
-struct devlink_trap_get_list *
-devlink_trap_get_dump(struct ynl_sock *ys,
-		      struct devlink_trap_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_trap_get_list);
-	yds.cb = devlink_trap_get_rsp_parse;
-	yds.rsp_cmd = 63;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_TRAP_GET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	devlink_trap_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_TRAP_SET ============== */
-/* DEVLINK_CMD_TRAP_SET - do */
-void devlink_trap_set_req_free(struct devlink_trap_set_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->trap_name);
-	free(req);
-}
-
-int devlink_trap_set(struct ynl_sock *ys, struct devlink_trap_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_TRAP_SET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.trap_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_TRAP_NAME, req->trap_name);
-	if (req->_present.trap_action)
-		mnl_attr_put_u8(nlh, DEVLINK_ATTR_TRAP_ACTION, req->trap_action);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_TRAP_GROUP_GET ============== */
-/* DEVLINK_CMD_TRAP_GROUP_GET - do */
-void devlink_trap_group_get_req_free(struct devlink_trap_group_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->trap_group_name);
-	free(req);
-}
-
-void devlink_trap_group_get_rsp_free(struct devlink_trap_group_get_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	free(rsp->trap_group_name);
-	free(rsp);
-}
-
-int devlink_trap_group_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct devlink_trap_group_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_TRAP_GROUP_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.trap_group_name_len = len;
-			dst->trap_group_name = malloc(len + 1);
-			memcpy(dst->trap_group_name, mnl_attr_get_str(attr), len);
-			dst->trap_group_name[len] = 0;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_trap_group_get_rsp *
-devlink_trap_group_get(struct ynl_sock *ys,
-		       struct devlink_trap_group_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_trap_group_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_TRAP_GROUP_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.trap_group_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_TRAP_GROUP_NAME, req->trap_group_name);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_trap_group_get_rsp_parse;
-	yrs.rsp_cmd = 67;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_trap_group_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* DEVLINK_CMD_TRAP_GROUP_GET - dump */
-void devlink_trap_group_get_list_free(struct devlink_trap_group_get_list *rsp)
-{
-	struct devlink_trap_group_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		free(rsp->obj.trap_group_name);
-		free(rsp);
-	}
-}
-
-struct devlink_trap_group_get_list *
-devlink_trap_group_get_dump(struct ynl_sock *ys,
-			    struct devlink_trap_group_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_trap_group_get_list);
-	yds.cb = devlink_trap_group_get_rsp_parse;
-	yds.rsp_cmd = 67;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_TRAP_GROUP_GET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	devlink_trap_group_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_TRAP_GROUP_SET ============== */
-/* DEVLINK_CMD_TRAP_GROUP_SET - do */
-void devlink_trap_group_set_req_free(struct devlink_trap_group_set_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->trap_group_name);
-	free(req);
-}
-
-int devlink_trap_group_set(struct ynl_sock *ys,
-			   struct devlink_trap_group_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_TRAP_GROUP_SET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.trap_group_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_TRAP_GROUP_NAME, req->trap_group_name);
-	if (req->_present.trap_action)
-		mnl_attr_put_u8(nlh, DEVLINK_ATTR_TRAP_ACTION, req->trap_action);
-	if (req->_present.trap_policer_id)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_TRAP_POLICER_ID, req->trap_policer_id);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_TRAP_POLICER_GET ============== */
-/* DEVLINK_CMD_TRAP_POLICER_GET - do */
-void
-devlink_trap_policer_get_req_free(struct devlink_trap_policer_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-void
-devlink_trap_policer_get_rsp_free(struct devlink_trap_policer_get_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	free(rsp);
-}
-
-int devlink_trap_policer_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct devlink_trap_policer_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_TRAP_POLICER_ID) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.trap_policer_id = 1;
-			dst->trap_policer_id = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_trap_policer_get_rsp *
-devlink_trap_policer_get(struct ynl_sock *ys,
-			 struct devlink_trap_policer_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_trap_policer_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_TRAP_POLICER_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.trap_policer_id)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_TRAP_POLICER_ID, req->trap_policer_id);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_trap_policer_get_rsp_parse;
-	yrs.rsp_cmd = 71;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_trap_policer_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* DEVLINK_CMD_TRAP_POLICER_GET - dump */
-void
-devlink_trap_policer_get_list_free(struct devlink_trap_policer_get_list *rsp)
-{
-	struct devlink_trap_policer_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		free(rsp);
-	}
-}
-
-struct devlink_trap_policer_get_list *
-devlink_trap_policer_get_dump(struct ynl_sock *ys,
-			      struct devlink_trap_policer_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_trap_policer_get_list);
-	yds.cb = devlink_trap_policer_get_rsp_parse;
-	yds.rsp_cmd = 71;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_TRAP_POLICER_GET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	devlink_trap_policer_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_TRAP_POLICER_SET ============== */
-/* DEVLINK_CMD_TRAP_POLICER_SET - do */
-void
-devlink_trap_policer_set_req_free(struct devlink_trap_policer_set_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-int devlink_trap_policer_set(struct ynl_sock *ys,
-			     struct devlink_trap_policer_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_TRAP_POLICER_SET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.trap_policer_id)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_TRAP_POLICER_ID, req->trap_policer_id);
-	if (req->_present.trap_policer_rate)
-		mnl_attr_put_u64(nlh, DEVLINK_ATTR_TRAP_POLICER_RATE, req->trap_policer_rate);
-	if (req->_present.trap_policer_burst)
-		mnl_attr_put_u64(nlh, DEVLINK_ATTR_TRAP_POLICER_BURST, req->trap_policer_burst);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_HEALTH_REPORTER_TEST ============== */
-/* DEVLINK_CMD_HEALTH_REPORTER_TEST - do */
-void
-devlink_health_reporter_test_req_free(struct devlink_health_reporter_test_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->health_reporter_name);
-	free(req);
-}
-
-int devlink_health_reporter_test(struct ynl_sock *ys,
-				 struct devlink_health_reporter_test_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_TEST, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.health_reporter_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_RATE_GET ============== */
-/* DEVLINK_CMD_RATE_GET - do */
-void devlink_rate_get_req_free(struct devlink_rate_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->rate_node_name);
-	free(req);
-}
-
-void devlink_rate_get_rsp_free(struct devlink_rate_get_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	free(rsp->rate_node_name);
-	free(rsp);
-}
-
-int devlink_rate_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ynl_parse_arg *yarg = data;
-	struct devlink_rate_get_rsp *dst;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.port_index = 1;
-			dst->port_index = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_RATE_NODE_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.rate_node_name_len = len;
-			dst->rate_node_name = malloc(len + 1);
-			memcpy(dst->rate_node_name, mnl_attr_get_str(attr), len);
-			dst->rate_node_name[len] = 0;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_rate_get_rsp *
-devlink_rate_get(struct ynl_sock *ys, struct devlink_rate_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_rate_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RATE_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.rate_node_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_NODE_NAME, req->rate_node_name);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_rate_get_rsp_parse;
-	yrs.rsp_cmd = 76;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_rate_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* DEVLINK_CMD_RATE_GET - dump */
-void devlink_rate_get_list_free(struct devlink_rate_get_list *rsp)
-{
-	struct devlink_rate_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		free(rsp->obj.rate_node_name);
-		free(rsp);
-	}
-}
-
-struct devlink_rate_get_list *
-devlink_rate_get_dump(struct ynl_sock *ys,
-		      struct devlink_rate_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_rate_get_list);
-	yds.cb = devlink_rate_get_rsp_parse;
-	yds.rsp_cmd = 76;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_RATE_GET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	devlink_rate_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_RATE_SET ============== */
-/* DEVLINK_CMD_RATE_SET - do */
-void devlink_rate_set_req_free(struct devlink_rate_set_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->rate_node_name);
-	free(req->rate_parent_node_name);
-	free(req);
-}
-
-int devlink_rate_set(struct ynl_sock *ys, struct devlink_rate_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RATE_SET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.rate_node_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_NODE_NAME, req->rate_node_name);
-	if (req->_present.rate_tx_share)
-		mnl_attr_put_u64(nlh, DEVLINK_ATTR_RATE_TX_SHARE, req->rate_tx_share);
-	if (req->_present.rate_tx_max)
-		mnl_attr_put_u64(nlh, DEVLINK_ATTR_RATE_TX_MAX, req->rate_tx_max);
-	if (req->_present.rate_tx_priority)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_RATE_TX_PRIORITY, req->rate_tx_priority);
-	if (req->_present.rate_tx_weight)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_RATE_TX_WEIGHT, req->rate_tx_weight);
-	if (req->_present.rate_parent_node_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_PARENT_NODE_NAME, req->rate_parent_node_name);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_RATE_NEW ============== */
-/* DEVLINK_CMD_RATE_NEW - do */
-void devlink_rate_new_req_free(struct devlink_rate_new_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->rate_node_name);
-	free(req->rate_parent_node_name);
-	free(req);
-}
-
-int devlink_rate_new(struct ynl_sock *ys, struct devlink_rate_new_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RATE_NEW, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.rate_node_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_NODE_NAME, req->rate_node_name);
-	if (req->_present.rate_tx_share)
-		mnl_attr_put_u64(nlh, DEVLINK_ATTR_RATE_TX_SHARE, req->rate_tx_share);
-	if (req->_present.rate_tx_max)
-		mnl_attr_put_u64(nlh, DEVLINK_ATTR_RATE_TX_MAX, req->rate_tx_max);
-	if (req->_present.rate_tx_priority)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_RATE_TX_PRIORITY, req->rate_tx_priority);
-	if (req->_present.rate_tx_weight)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_RATE_TX_WEIGHT, req->rate_tx_weight);
-	if (req->_present.rate_parent_node_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_PARENT_NODE_NAME, req->rate_parent_node_name);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_RATE_DEL ============== */
-/* DEVLINK_CMD_RATE_DEL - do */
-void devlink_rate_del_req_free(struct devlink_rate_del_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->rate_node_name);
-	free(req);
-}
-
-int devlink_rate_del(struct ynl_sock *ys, struct devlink_rate_del_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RATE_DEL, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.rate_node_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_NODE_NAME, req->rate_node_name);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_LINECARD_GET ============== */
-/* DEVLINK_CMD_LINECARD_GET - do */
-void devlink_linecard_get_req_free(struct devlink_linecard_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-void devlink_linecard_get_rsp_free(struct devlink_linecard_get_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	free(rsp);
-}
-
-int devlink_linecard_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct devlink_linecard_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_LINECARD_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.linecard_index = 1;
-			dst->linecard_index = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_linecard_get_rsp *
-devlink_linecard_get(struct ynl_sock *ys, struct devlink_linecard_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_linecard_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_LINECARD_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.linecard_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_LINECARD_INDEX, req->linecard_index);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_linecard_get_rsp_parse;
-	yrs.rsp_cmd = 80;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_linecard_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* DEVLINK_CMD_LINECARD_GET - dump */
-void devlink_linecard_get_list_free(struct devlink_linecard_get_list *rsp)
-{
-	struct devlink_linecard_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		free(rsp);
-	}
-}
-
-struct devlink_linecard_get_list *
-devlink_linecard_get_dump(struct ynl_sock *ys,
-			  struct devlink_linecard_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_linecard_get_list);
-	yds.cb = devlink_linecard_get_rsp_parse;
-	yds.rsp_cmd = 80;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_LINECARD_GET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	devlink_linecard_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_LINECARD_SET ============== */
-/* DEVLINK_CMD_LINECARD_SET - do */
-void devlink_linecard_set_req_free(struct devlink_linecard_set_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->linecard_type);
-	free(req);
-}
-
-int devlink_linecard_set(struct ynl_sock *ys,
-			 struct devlink_linecard_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_LINECARD_SET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.linecard_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_LINECARD_INDEX, req->linecard_index);
-	if (req->_present.linecard_type_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_LINECARD_TYPE, req->linecard_type);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== DEVLINK_CMD_SELFTESTS_GET ============== */
-/* DEVLINK_CMD_SELFTESTS_GET - do */
-void devlink_selftests_get_req_free(struct devlink_selftests_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req);
-}
-
-void devlink_selftests_get_rsp_free(struct devlink_selftests_get_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	free(rsp);
-}
-
-int devlink_selftests_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct devlink_selftests_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == DEVLINK_ATTR_BUS_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.bus_name_len = len;
-			dst->bus_name = malloc(len + 1);
-			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
-			dst->bus_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct devlink_selftests_get_rsp *
-devlink_selftests_get(struct ynl_sock *ys,
-		      struct devlink_selftests_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_selftests_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SELFTESTS_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_selftests_get_rsp_parse;
-	yrs.rsp_cmd = DEVLINK_CMD_SELFTESTS_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_selftests_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* DEVLINK_CMD_SELFTESTS_GET - dump */
-void devlink_selftests_get_list_free(struct devlink_selftests_get_list *rsp)
-{
-	struct devlink_selftests_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		free(rsp);
-	}
-}
-
-struct devlink_selftests_get_list *
-devlink_selftests_get_dump(struct ynl_sock *ys)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_selftests_get_list);
-	yds.cb = devlink_selftests_get_rsp_parse;
-	yds.rsp_cmd = DEVLINK_CMD_SELFTESTS_GET;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SELFTESTS_GET, 1);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	devlink_selftests_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_SELFTESTS_RUN ============== */
-/* DEVLINK_CMD_SELFTESTS_RUN - do */
-void devlink_selftests_run_req_free(struct devlink_selftests_run_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	devlink_dl_selftest_id_free(&req->selftests);
-	free(req);
-}
-
-int devlink_selftests_run(struct ynl_sock *ys,
-			  struct devlink_selftests_run_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SELFTESTS_RUN, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.selftests)
-		devlink_dl_selftest_id_put(nlh, DEVLINK_ATTR_SELFTESTS, &req->selftests);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-const struct ynl_family ynl_devlink_family =  {
-	.name		= "devlink",
-};
diff --git a/tools/net/ynl/generated/devlink-user.h b/tools/net/ynl/generated/devlink-user.h
deleted file mode 100644
index 1db4edc36eaa..000000000000
--- a/tools/net/ynl/generated/devlink-user.h
+++ /dev/null
@@ -1,5255 +0,0 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
-/* Do not edit directly, auto-generated from: */
-/*	Documentation/netlink/specs/devlink.yaml */
-/* YNL-GEN user header */
-
-#ifndef _LINUX_DEVLINK_GEN_H
-#define _LINUX_DEVLINK_GEN_H
-
-#include <stdlib.h>
-#include <string.h>
-#include <linux/types.h>
-#include <linux/netlink.h>
-#include <linux/devlink.h>
-
-struct ynl_sock;
-
-extern const struct ynl_family ynl_devlink_family;
-
-/* Enums */
-const char *devlink_op_str(int op);
-const char *devlink_sb_pool_type_str(enum devlink_sb_pool_type value);
-const char *devlink_port_type_str(enum devlink_port_type value);
-const char *devlink_port_flavour_str(enum devlink_port_flavour value);
-const char *devlink_port_fn_state_str(enum devlink_port_fn_state value);
-const char *devlink_port_fn_opstate_str(enum devlink_port_fn_opstate value);
-const char *devlink_port_fn_attr_cap_str(enum devlink_port_fn_attr_cap value);
-const char *
-devlink_sb_threshold_type_str(enum devlink_sb_threshold_type value);
-const char *devlink_eswitch_mode_str(enum devlink_eswitch_mode value);
-const char *
-devlink_eswitch_inline_mode_str(enum devlink_eswitch_inline_mode value);
-const char *
-devlink_eswitch_encap_mode_str(enum devlink_eswitch_encap_mode value);
-const char *devlink_dpipe_match_type_str(enum devlink_dpipe_match_type value);
-const char *
-devlink_dpipe_action_type_str(enum devlink_dpipe_action_type value);
-const char *
-devlink_dpipe_field_mapping_type_str(enum devlink_dpipe_field_mapping_type value);
-const char *devlink_resource_unit_str(enum devlink_resource_unit value);
-const char *devlink_reload_action_str(enum devlink_reload_action value);
-const char *devlink_param_cmode_str(enum devlink_param_cmode value);
-const char *devlink_flash_overwrite_str(enum devlink_flash_overwrite value);
-const char *devlink_trap_action_str(enum devlink_trap_action value);
-
-/* Common nested types */
-struct devlink_dl_dpipe_match {
-	struct {
-		__u32 dpipe_match_type:1;
-		__u32 dpipe_header_id:1;
-		__u32 dpipe_header_global:1;
-		__u32 dpipe_header_index:1;
-		__u32 dpipe_field_id:1;
-	} _present;
-
-	enum devlink_dpipe_match_type dpipe_match_type;
-	__u32 dpipe_header_id;
-	__u8 dpipe_header_global;
-	__u32 dpipe_header_index;
-	__u32 dpipe_field_id;
-};
-
-struct devlink_dl_dpipe_match_value {
-	struct {
-		__u32 dpipe_value_len;
-		__u32 dpipe_value_mask_len;
-		__u32 dpipe_value_mapping:1;
-	} _present;
-
-	unsigned int n_dpipe_match;
-	struct devlink_dl_dpipe_match *dpipe_match;
-	void *dpipe_value;
-	void *dpipe_value_mask;
-	__u32 dpipe_value_mapping;
-};
-
-struct devlink_dl_dpipe_action {
-	struct {
-		__u32 dpipe_action_type:1;
-		__u32 dpipe_header_id:1;
-		__u32 dpipe_header_global:1;
-		__u32 dpipe_header_index:1;
-		__u32 dpipe_field_id:1;
-	} _present;
-
-	enum devlink_dpipe_action_type dpipe_action_type;
-	__u32 dpipe_header_id;
-	__u8 dpipe_header_global;
-	__u32 dpipe_header_index;
-	__u32 dpipe_field_id;
-};
-
-struct devlink_dl_dpipe_action_value {
-	struct {
-		__u32 dpipe_value_len;
-		__u32 dpipe_value_mask_len;
-		__u32 dpipe_value_mapping:1;
-	} _present;
-
-	unsigned int n_dpipe_action;
-	struct devlink_dl_dpipe_action *dpipe_action;
-	void *dpipe_value;
-	void *dpipe_value_mask;
-	__u32 dpipe_value_mapping;
-};
-
-struct devlink_dl_dpipe_field {
-	struct {
-		__u32 dpipe_field_name_len;
-		__u32 dpipe_field_id:1;
-		__u32 dpipe_field_bitwidth:1;
-		__u32 dpipe_field_mapping_type:1;
-	} _present;
-
-	char *dpipe_field_name;
-	__u32 dpipe_field_id;
-	__u32 dpipe_field_bitwidth;
-	enum devlink_dpipe_field_mapping_type dpipe_field_mapping_type;
-};
-
-struct devlink_dl_resource {
-	struct {
-		__u32 resource_name_len;
-		__u32 resource_id:1;
-		__u32 resource_size:1;
-		__u32 resource_size_new:1;
-		__u32 resource_size_valid:1;
-		__u32 resource_size_min:1;
-		__u32 resource_size_max:1;
-		__u32 resource_size_gran:1;
-		__u32 resource_unit:1;
-		__u32 resource_occ:1;
-	} _present;
-
-	char *resource_name;
-	__u64 resource_id;
-	__u64 resource_size;
-	__u64 resource_size_new;
-	__u8 resource_size_valid;
-	__u64 resource_size_min;
-	__u64 resource_size_max;
-	__u64 resource_size_gran;
-	enum devlink_resource_unit resource_unit;
-	__u64 resource_occ;
-};
-
-struct devlink_dl_info_version {
-	struct {
-		__u32 info_version_name_len;
-		__u32 info_version_value_len;
-	} _present;
-
-	char *info_version_name;
-	char *info_version_value;
-};
-
-struct devlink_dl_fmsg {
-	struct {
-		__u32 fmsg_obj_nest_start:1;
-		__u32 fmsg_pair_nest_start:1;
-		__u32 fmsg_arr_nest_start:1;
-		__u32 fmsg_nest_end:1;
-		__u32 fmsg_obj_name_len;
-	} _present;
-
-	char *fmsg_obj_name;
-};
-
-struct devlink_dl_port_function {
-	struct {
-		__u32 hw_addr_len;
-		__u32 state:1;
-		__u32 opstate:1;
-		__u32 caps:1;
-	} _present;
-
-	void *hw_addr;
-	enum devlink_port_fn_state state;
-	enum devlink_port_fn_opstate opstate;
-	struct nla_bitfield32 caps;
-};
-
-struct devlink_dl_reload_stats_entry {
-	struct {
-		__u32 reload_stats_limit:1;
-		__u32 reload_stats_value:1;
-	} _present;
-
-	__u8 reload_stats_limit;
-	__u32 reload_stats_value;
-};
-
-struct devlink_dl_reload_act_stats {
-	unsigned int n_reload_stats_entry;
-	struct devlink_dl_reload_stats_entry *reload_stats_entry;
-};
-
-struct devlink_dl_selftest_id {
-	struct {
-		__u32 flash:1;
-	} _present;
-};
-
-struct devlink_dl_dpipe_table_matches {
-	unsigned int n_dpipe_match;
-	struct devlink_dl_dpipe_match *dpipe_match;
-};
-
-struct devlink_dl_dpipe_table_actions {
-	unsigned int n_dpipe_action;
-	struct devlink_dl_dpipe_action *dpipe_action;
-};
-
-struct devlink_dl_dpipe_entry_match_values {
-	unsigned int n_dpipe_match_value;
-	struct devlink_dl_dpipe_match_value *dpipe_match_value;
-};
-
-struct devlink_dl_dpipe_entry_action_values {
-	unsigned int n_dpipe_action_value;
-	struct devlink_dl_dpipe_action_value *dpipe_action_value;
-};
-
-struct devlink_dl_dpipe_header_fields {
-	unsigned int n_dpipe_field;
-	struct devlink_dl_dpipe_field *dpipe_field;
-};
-
-struct devlink_dl_resource_list {
-	unsigned int n_resource;
-	struct devlink_dl_resource *resource;
-};
-
-struct devlink_dl_reload_act_info {
-	struct {
-		__u32 reload_action:1;
-	} _present;
-
-	enum devlink_reload_action reload_action;
-	unsigned int n_reload_action_stats;
-	struct devlink_dl_reload_act_stats *reload_action_stats;
-};
-
-struct devlink_dl_dpipe_table {
-	struct {
-		__u32 dpipe_table_name_len;
-		__u32 dpipe_table_size:1;
-		__u32 dpipe_table_matches:1;
-		__u32 dpipe_table_actions:1;
-		__u32 dpipe_table_counters_enabled:1;
-		__u32 dpipe_table_resource_id:1;
-		__u32 dpipe_table_resource_units:1;
-	} _present;
-
-	char *dpipe_table_name;
-	__u64 dpipe_table_size;
-	struct devlink_dl_dpipe_table_matches dpipe_table_matches;
-	struct devlink_dl_dpipe_table_actions dpipe_table_actions;
-	__u8 dpipe_table_counters_enabled;
-	__u64 dpipe_table_resource_id;
-	__u64 dpipe_table_resource_units;
-};
-
-struct devlink_dl_dpipe_entry {
-	struct {
-		__u32 dpipe_entry_index:1;
-		__u32 dpipe_entry_match_values:1;
-		__u32 dpipe_entry_action_values:1;
-		__u32 dpipe_entry_counter:1;
-	} _present;
-
-	__u64 dpipe_entry_index;
-	struct devlink_dl_dpipe_entry_match_values dpipe_entry_match_values;
-	struct devlink_dl_dpipe_entry_action_values dpipe_entry_action_values;
-	__u64 dpipe_entry_counter;
-};
-
-struct devlink_dl_dpipe_header {
-	struct {
-		__u32 dpipe_header_name_len;
-		__u32 dpipe_header_id:1;
-		__u32 dpipe_header_global:1;
-		__u32 dpipe_header_fields:1;
-	} _present;
-
-	char *dpipe_header_name;
-	__u32 dpipe_header_id;
-	__u8 dpipe_header_global;
-	struct devlink_dl_dpipe_header_fields dpipe_header_fields;
-};
-
-struct devlink_dl_reload_stats {
-	unsigned int n_reload_action_info;
-	struct devlink_dl_reload_act_info *reload_action_info;
-};
-
-struct devlink_dl_dpipe_tables {
-	unsigned int n_dpipe_table;
-	struct devlink_dl_dpipe_table *dpipe_table;
-};
-
-struct devlink_dl_dpipe_entries {
-	unsigned int n_dpipe_entry;
-	struct devlink_dl_dpipe_entry *dpipe_entry;
-};
-
-struct devlink_dl_dpipe_headers {
-	unsigned int n_dpipe_header;
-	struct devlink_dl_dpipe_header *dpipe_header;
-};
-
-struct devlink_dl_dev_stats {
-	struct {
-		__u32 reload_stats:1;
-		__u32 remote_reload_stats:1;
-	} _present;
-
-	struct devlink_dl_reload_stats reload_stats;
-	struct devlink_dl_reload_stats remote_reload_stats;
-};
-
-/* ============== DEVLINK_CMD_GET ============== */
-/* DEVLINK_CMD_GET - do */
-struct devlink_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-};
-
-static inline struct devlink_get_req *devlink_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_get_req));
-}
-void devlink_get_req_free(struct devlink_get_req *req);
-
-static inline void
-devlink_get_req_set_bus_name(struct devlink_get_req *req, const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_get_req_set_dev_name(struct devlink_get_req *req, const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-
-struct devlink_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 reload_failed:1;
-		__u32 dev_stats:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u8 reload_failed;
-	struct devlink_dl_dev_stats dev_stats;
-};
-
-void devlink_get_rsp_free(struct devlink_get_rsp *rsp);
-
-/*
- * Get devlink instances.
- */
-struct devlink_get_rsp *
-devlink_get(struct ynl_sock *ys, struct devlink_get_req *req);
-
-/* DEVLINK_CMD_GET - dump */
-struct devlink_get_list {
-	struct devlink_get_list *next;
-	struct devlink_get_rsp obj __attribute__((aligned(8)));
-};
-
-void devlink_get_list_free(struct devlink_get_list *rsp);
-
-struct devlink_get_list *devlink_get_dump(struct ynl_sock *ys);
-
-/* ============== DEVLINK_CMD_PORT_GET ============== */
-/* DEVLINK_CMD_PORT_GET - do */
-struct devlink_port_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-};
-
-static inline struct devlink_port_get_req *devlink_port_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_port_get_req));
-}
-void devlink_port_get_req_free(struct devlink_port_get_req *req);
-
-static inline void
-devlink_port_get_req_set_bus_name(struct devlink_port_get_req *req,
-				  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_port_get_req_set_dev_name(struct devlink_port_get_req *req,
-				  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_port_get_req_set_port_index(struct devlink_port_get_req *req,
-				    __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-
-struct devlink_port_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-};
-
-void devlink_port_get_rsp_free(struct devlink_port_get_rsp *rsp);
-
-/*
- * Get devlink port instances.
- */
-struct devlink_port_get_rsp *
-devlink_port_get(struct ynl_sock *ys, struct devlink_port_get_req *req);
-
-/* DEVLINK_CMD_PORT_GET - dump */
-struct devlink_port_get_req_dump {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-};
-
-static inline struct devlink_port_get_req_dump *
-devlink_port_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_port_get_req_dump));
-}
-void devlink_port_get_req_dump_free(struct devlink_port_get_req_dump *req);
-
-static inline void
-devlink_port_get_req_dump_set_bus_name(struct devlink_port_get_req_dump *req,
-				       const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_port_get_req_dump_set_dev_name(struct devlink_port_get_req_dump *req,
-				       const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-
-struct devlink_port_get_rsp_dump {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-};
-
-struct devlink_port_get_rsp_list {
-	struct devlink_port_get_rsp_list *next;
-	struct devlink_port_get_rsp_dump obj __attribute__((aligned(8)));
-};
-
-void devlink_port_get_rsp_list_free(struct devlink_port_get_rsp_list *rsp);
-
-struct devlink_port_get_rsp_list *
-devlink_port_get_dump(struct ynl_sock *ys,
-		      struct devlink_port_get_req_dump *req);
-
-/* ============== DEVLINK_CMD_PORT_SET ============== */
-/* DEVLINK_CMD_PORT_SET - do */
-struct devlink_port_set_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 port_type:1;
-		__u32 port_function:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	enum devlink_port_type port_type;
-	struct devlink_dl_port_function port_function;
-};
-
-static inline struct devlink_port_set_req *devlink_port_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_port_set_req));
-}
-void devlink_port_set_req_free(struct devlink_port_set_req *req);
-
-static inline void
-devlink_port_set_req_set_bus_name(struct devlink_port_set_req *req,
-				  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_port_set_req_set_dev_name(struct devlink_port_set_req *req,
-				  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_port_set_req_set_port_index(struct devlink_port_set_req *req,
-				    __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-static inline void
-devlink_port_set_req_set_port_type(struct devlink_port_set_req *req,
-				   enum devlink_port_type port_type)
-{
-	req->_present.port_type = 1;
-	req->port_type = port_type;
-}
-static inline void
-devlink_port_set_req_set_port_function_hw_addr(struct devlink_port_set_req *req,
-					       const void *hw_addr, size_t len)
-{
-	free(req->port_function.hw_addr);
-	req->port_function._present.hw_addr_len = len;
-	req->port_function.hw_addr = malloc(req->port_function._present.hw_addr_len);
-	memcpy(req->port_function.hw_addr, hw_addr, req->port_function._present.hw_addr_len);
-}
-static inline void
-devlink_port_set_req_set_port_function_state(struct devlink_port_set_req *req,
-					     enum devlink_port_fn_state state)
-{
-	req->_present.port_function = 1;
-	req->port_function._present.state = 1;
-	req->port_function.state = state;
-}
-static inline void
-devlink_port_set_req_set_port_function_opstate(struct devlink_port_set_req *req,
-					       enum devlink_port_fn_opstate opstate)
-{
-	req->_present.port_function = 1;
-	req->port_function._present.opstate = 1;
-	req->port_function.opstate = opstate;
-}
-static inline void
-devlink_port_set_req_set_port_function_caps(struct devlink_port_set_req *req,
-					    struct nla_bitfield32 *caps)
-{
-	req->_present.port_function = 1;
-	req->port_function._present.caps = 1;
-	memcpy(&req->port_function.caps, caps, sizeof(struct nla_bitfield32));
-}
-
-/*
- * Set devlink port instances.
- */
-int devlink_port_set(struct ynl_sock *ys, struct devlink_port_set_req *req);
-
-/* ============== DEVLINK_CMD_PORT_NEW ============== */
-/* DEVLINK_CMD_PORT_NEW - do */
-struct devlink_port_new_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 port_flavour:1;
-		__u32 port_pci_pf_number:1;
-		__u32 port_pci_sf_number:1;
-		__u32 port_controller_number:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	enum devlink_port_flavour port_flavour;
-	__u16 port_pci_pf_number;
-	__u32 port_pci_sf_number;
-	__u32 port_controller_number;
-};
-
-static inline struct devlink_port_new_req *devlink_port_new_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_port_new_req));
-}
-void devlink_port_new_req_free(struct devlink_port_new_req *req);
-
-static inline void
-devlink_port_new_req_set_bus_name(struct devlink_port_new_req *req,
-				  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_port_new_req_set_dev_name(struct devlink_port_new_req *req,
-				  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_port_new_req_set_port_index(struct devlink_port_new_req *req,
-				    __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-static inline void
-devlink_port_new_req_set_port_flavour(struct devlink_port_new_req *req,
-				      enum devlink_port_flavour port_flavour)
-{
-	req->_present.port_flavour = 1;
-	req->port_flavour = port_flavour;
-}
-static inline void
-devlink_port_new_req_set_port_pci_pf_number(struct devlink_port_new_req *req,
-					    __u16 port_pci_pf_number)
-{
-	req->_present.port_pci_pf_number = 1;
-	req->port_pci_pf_number = port_pci_pf_number;
-}
-static inline void
-devlink_port_new_req_set_port_pci_sf_number(struct devlink_port_new_req *req,
-					    __u32 port_pci_sf_number)
-{
-	req->_present.port_pci_sf_number = 1;
-	req->port_pci_sf_number = port_pci_sf_number;
-}
-static inline void
-devlink_port_new_req_set_port_controller_number(struct devlink_port_new_req *req,
-						__u32 port_controller_number)
-{
-	req->_present.port_controller_number = 1;
-	req->port_controller_number = port_controller_number;
-}
-
-struct devlink_port_new_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-};
-
-void devlink_port_new_rsp_free(struct devlink_port_new_rsp *rsp);
-
-/*
- * Create devlink port instances.
- */
-struct devlink_port_new_rsp *
-devlink_port_new(struct ynl_sock *ys, struct devlink_port_new_req *req);
-
-/* ============== DEVLINK_CMD_PORT_DEL ============== */
-/* DEVLINK_CMD_PORT_DEL - do */
-struct devlink_port_del_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-};
-
-static inline struct devlink_port_del_req *devlink_port_del_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_port_del_req));
-}
-void devlink_port_del_req_free(struct devlink_port_del_req *req);
-
-static inline void
-devlink_port_del_req_set_bus_name(struct devlink_port_del_req *req,
-				  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_port_del_req_set_dev_name(struct devlink_port_del_req *req,
-				  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_port_del_req_set_port_index(struct devlink_port_del_req *req,
-				    __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-
-/*
- * Delete devlink port instances.
- */
-int devlink_port_del(struct ynl_sock *ys, struct devlink_port_del_req *req);
-
-/* ============== DEVLINK_CMD_PORT_SPLIT ============== */
-/* DEVLINK_CMD_PORT_SPLIT - do */
-struct devlink_port_split_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 port_split_count:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	__u32 port_split_count;
-};
-
-static inline struct devlink_port_split_req *devlink_port_split_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_port_split_req));
-}
-void devlink_port_split_req_free(struct devlink_port_split_req *req);
-
-static inline void
-devlink_port_split_req_set_bus_name(struct devlink_port_split_req *req,
-				    const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_port_split_req_set_dev_name(struct devlink_port_split_req *req,
-				    const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_port_split_req_set_port_index(struct devlink_port_split_req *req,
-				      __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-static inline void
-devlink_port_split_req_set_port_split_count(struct devlink_port_split_req *req,
-					    __u32 port_split_count)
-{
-	req->_present.port_split_count = 1;
-	req->port_split_count = port_split_count;
-}
-
-/*
- * Split devlink port instances.
- */
-int devlink_port_split(struct ynl_sock *ys, struct devlink_port_split_req *req);
-
-/* ============== DEVLINK_CMD_PORT_UNSPLIT ============== */
-/* DEVLINK_CMD_PORT_UNSPLIT - do */
-struct devlink_port_unsplit_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-};
-
-static inline struct devlink_port_unsplit_req *
-devlink_port_unsplit_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_port_unsplit_req));
-}
-void devlink_port_unsplit_req_free(struct devlink_port_unsplit_req *req);
-
-static inline void
-devlink_port_unsplit_req_set_bus_name(struct devlink_port_unsplit_req *req,
-				      const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_port_unsplit_req_set_dev_name(struct devlink_port_unsplit_req *req,
-				      const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_port_unsplit_req_set_port_index(struct devlink_port_unsplit_req *req,
-					__u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-
-/*
- * Unplit devlink port instances.
- */
-int devlink_port_unsplit(struct ynl_sock *ys,
-			 struct devlink_port_unsplit_req *req);
-
-/* ============== DEVLINK_CMD_SB_GET ============== */
-/* DEVLINK_CMD_SB_GET - do */
-struct devlink_sb_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 sb_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 sb_index;
-};
-
-static inline struct devlink_sb_get_req *devlink_sb_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_sb_get_req));
-}
-void devlink_sb_get_req_free(struct devlink_sb_get_req *req);
-
-static inline void
-devlink_sb_get_req_set_bus_name(struct devlink_sb_get_req *req,
-				const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_sb_get_req_set_dev_name(struct devlink_sb_get_req *req,
-				const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_sb_get_req_set_sb_index(struct devlink_sb_get_req *req, __u32 sb_index)
-{
-	req->_present.sb_index = 1;
-	req->sb_index = sb_index;
-}
-
-struct devlink_sb_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 sb_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 sb_index;
-};
-
-void devlink_sb_get_rsp_free(struct devlink_sb_get_rsp *rsp);
-
-/*
- * Get shared buffer instances.
- */
-struct devlink_sb_get_rsp *
-devlink_sb_get(struct ynl_sock *ys, struct devlink_sb_get_req *req);
-
-/* DEVLINK_CMD_SB_GET - dump */
-struct devlink_sb_get_req_dump {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-};
-
-static inline struct devlink_sb_get_req_dump *
-devlink_sb_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_sb_get_req_dump));
-}
-void devlink_sb_get_req_dump_free(struct devlink_sb_get_req_dump *req);
-
-static inline void
-devlink_sb_get_req_dump_set_bus_name(struct devlink_sb_get_req_dump *req,
-				     const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_sb_get_req_dump_set_dev_name(struct devlink_sb_get_req_dump *req,
-				     const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-
-struct devlink_sb_get_list {
-	struct devlink_sb_get_list *next;
-	struct devlink_sb_get_rsp obj __attribute__((aligned(8)));
-};
-
-void devlink_sb_get_list_free(struct devlink_sb_get_list *rsp);
-
-struct devlink_sb_get_list *
-devlink_sb_get_dump(struct ynl_sock *ys, struct devlink_sb_get_req_dump *req);
-
-/* ============== DEVLINK_CMD_SB_POOL_GET ============== */
-/* DEVLINK_CMD_SB_POOL_GET - do */
-struct devlink_sb_pool_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 sb_index:1;
-		__u32 sb_pool_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 sb_index;
-	__u16 sb_pool_index;
-};
-
-static inline struct devlink_sb_pool_get_req *
-devlink_sb_pool_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_sb_pool_get_req));
-}
-void devlink_sb_pool_get_req_free(struct devlink_sb_pool_get_req *req);
-
-static inline void
-devlink_sb_pool_get_req_set_bus_name(struct devlink_sb_pool_get_req *req,
-				     const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_sb_pool_get_req_set_dev_name(struct devlink_sb_pool_get_req *req,
-				     const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_sb_pool_get_req_set_sb_index(struct devlink_sb_pool_get_req *req,
-				     __u32 sb_index)
-{
-	req->_present.sb_index = 1;
-	req->sb_index = sb_index;
-}
-static inline void
-devlink_sb_pool_get_req_set_sb_pool_index(struct devlink_sb_pool_get_req *req,
-					  __u16 sb_pool_index)
-{
-	req->_present.sb_pool_index = 1;
-	req->sb_pool_index = sb_pool_index;
-}
-
-struct devlink_sb_pool_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 sb_index:1;
-		__u32 sb_pool_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 sb_index;
-	__u16 sb_pool_index;
-};
-
-void devlink_sb_pool_get_rsp_free(struct devlink_sb_pool_get_rsp *rsp);
-
-/*
- * Get shared buffer pool instances.
- */
-struct devlink_sb_pool_get_rsp *
-devlink_sb_pool_get(struct ynl_sock *ys, struct devlink_sb_pool_get_req *req);
-
-/* DEVLINK_CMD_SB_POOL_GET - dump */
-struct devlink_sb_pool_get_req_dump {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-};
-
-static inline struct devlink_sb_pool_get_req_dump *
-devlink_sb_pool_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_sb_pool_get_req_dump));
-}
-void
-devlink_sb_pool_get_req_dump_free(struct devlink_sb_pool_get_req_dump *req);
-
-static inline void
-devlink_sb_pool_get_req_dump_set_bus_name(struct devlink_sb_pool_get_req_dump *req,
-					  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_sb_pool_get_req_dump_set_dev_name(struct devlink_sb_pool_get_req_dump *req,
-					  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-
-struct devlink_sb_pool_get_list {
-	struct devlink_sb_pool_get_list *next;
-	struct devlink_sb_pool_get_rsp obj __attribute__((aligned(8)));
-};
-
-void devlink_sb_pool_get_list_free(struct devlink_sb_pool_get_list *rsp);
-
-struct devlink_sb_pool_get_list *
-devlink_sb_pool_get_dump(struct ynl_sock *ys,
-			 struct devlink_sb_pool_get_req_dump *req);
-
-/* ============== DEVLINK_CMD_SB_POOL_SET ============== */
-/* DEVLINK_CMD_SB_POOL_SET - do */
-struct devlink_sb_pool_set_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 sb_index:1;
-		__u32 sb_pool_index:1;
-		__u32 sb_pool_threshold_type:1;
-		__u32 sb_pool_size:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 sb_index;
-	__u16 sb_pool_index;
-	enum devlink_sb_threshold_type sb_pool_threshold_type;
-	__u32 sb_pool_size;
-};
-
-static inline struct devlink_sb_pool_set_req *
-devlink_sb_pool_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_sb_pool_set_req));
-}
-void devlink_sb_pool_set_req_free(struct devlink_sb_pool_set_req *req);
-
-static inline void
-devlink_sb_pool_set_req_set_bus_name(struct devlink_sb_pool_set_req *req,
-				     const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_sb_pool_set_req_set_dev_name(struct devlink_sb_pool_set_req *req,
-				     const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_sb_pool_set_req_set_sb_index(struct devlink_sb_pool_set_req *req,
-				     __u32 sb_index)
-{
-	req->_present.sb_index = 1;
-	req->sb_index = sb_index;
-}
-static inline void
-devlink_sb_pool_set_req_set_sb_pool_index(struct devlink_sb_pool_set_req *req,
-					  __u16 sb_pool_index)
-{
-	req->_present.sb_pool_index = 1;
-	req->sb_pool_index = sb_pool_index;
-}
-static inline void
-devlink_sb_pool_set_req_set_sb_pool_threshold_type(struct devlink_sb_pool_set_req *req,
-						   enum devlink_sb_threshold_type sb_pool_threshold_type)
-{
-	req->_present.sb_pool_threshold_type = 1;
-	req->sb_pool_threshold_type = sb_pool_threshold_type;
-}
-static inline void
-devlink_sb_pool_set_req_set_sb_pool_size(struct devlink_sb_pool_set_req *req,
-					 __u32 sb_pool_size)
-{
-	req->_present.sb_pool_size = 1;
-	req->sb_pool_size = sb_pool_size;
-}
-
-/*
- * Set shared buffer pool instances.
- */
-int devlink_sb_pool_set(struct ynl_sock *ys,
-			struct devlink_sb_pool_set_req *req);
-
-/* ============== DEVLINK_CMD_SB_PORT_POOL_GET ============== */
-/* DEVLINK_CMD_SB_PORT_POOL_GET - do */
-struct devlink_sb_port_pool_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 sb_index:1;
-		__u32 sb_pool_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	__u32 sb_index;
-	__u16 sb_pool_index;
-};
-
-static inline struct devlink_sb_port_pool_get_req *
-devlink_sb_port_pool_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_sb_port_pool_get_req));
-}
-void
-devlink_sb_port_pool_get_req_free(struct devlink_sb_port_pool_get_req *req);
-
-static inline void
-devlink_sb_port_pool_get_req_set_bus_name(struct devlink_sb_port_pool_get_req *req,
-					  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_sb_port_pool_get_req_set_dev_name(struct devlink_sb_port_pool_get_req *req,
-					  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_sb_port_pool_get_req_set_port_index(struct devlink_sb_port_pool_get_req *req,
-					    __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-static inline void
-devlink_sb_port_pool_get_req_set_sb_index(struct devlink_sb_port_pool_get_req *req,
-					  __u32 sb_index)
-{
-	req->_present.sb_index = 1;
-	req->sb_index = sb_index;
-}
-static inline void
-devlink_sb_port_pool_get_req_set_sb_pool_index(struct devlink_sb_port_pool_get_req *req,
-					       __u16 sb_pool_index)
-{
-	req->_present.sb_pool_index = 1;
-	req->sb_pool_index = sb_pool_index;
-}
-
-struct devlink_sb_port_pool_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 sb_index:1;
-		__u32 sb_pool_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	__u32 sb_index;
-	__u16 sb_pool_index;
-};
-
-void
-devlink_sb_port_pool_get_rsp_free(struct devlink_sb_port_pool_get_rsp *rsp);
-
-/*
- * Get shared buffer port-pool combinations and threshold.
- */
-struct devlink_sb_port_pool_get_rsp *
-devlink_sb_port_pool_get(struct ynl_sock *ys,
-			 struct devlink_sb_port_pool_get_req *req);
-
-/* DEVLINK_CMD_SB_PORT_POOL_GET - dump */
-struct devlink_sb_port_pool_get_req_dump {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-};
-
-static inline struct devlink_sb_port_pool_get_req_dump *
-devlink_sb_port_pool_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_sb_port_pool_get_req_dump));
-}
-void
-devlink_sb_port_pool_get_req_dump_free(struct devlink_sb_port_pool_get_req_dump *req);
-
-static inline void
-devlink_sb_port_pool_get_req_dump_set_bus_name(struct devlink_sb_port_pool_get_req_dump *req,
-					       const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_sb_port_pool_get_req_dump_set_dev_name(struct devlink_sb_port_pool_get_req_dump *req,
-					       const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-
-struct devlink_sb_port_pool_get_list {
-	struct devlink_sb_port_pool_get_list *next;
-	struct devlink_sb_port_pool_get_rsp obj __attribute__((aligned(8)));
-};
-
-void
-devlink_sb_port_pool_get_list_free(struct devlink_sb_port_pool_get_list *rsp);
-
-struct devlink_sb_port_pool_get_list *
-devlink_sb_port_pool_get_dump(struct ynl_sock *ys,
-			      struct devlink_sb_port_pool_get_req_dump *req);
-
-/* ============== DEVLINK_CMD_SB_PORT_POOL_SET ============== */
-/* DEVLINK_CMD_SB_PORT_POOL_SET - do */
-struct devlink_sb_port_pool_set_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 sb_index:1;
-		__u32 sb_pool_index:1;
-		__u32 sb_threshold:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	__u32 sb_index;
-	__u16 sb_pool_index;
-	__u32 sb_threshold;
-};
-
-static inline struct devlink_sb_port_pool_set_req *
-devlink_sb_port_pool_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_sb_port_pool_set_req));
-}
-void
-devlink_sb_port_pool_set_req_free(struct devlink_sb_port_pool_set_req *req);
-
-static inline void
-devlink_sb_port_pool_set_req_set_bus_name(struct devlink_sb_port_pool_set_req *req,
-					  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_sb_port_pool_set_req_set_dev_name(struct devlink_sb_port_pool_set_req *req,
-					  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_sb_port_pool_set_req_set_port_index(struct devlink_sb_port_pool_set_req *req,
-					    __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-static inline void
-devlink_sb_port_pool_set_req_set_sb_index(struct devlink_sb_port_pool_set_req *req,
-					  __u32 sb_index)
-{
-	req->_present.sb_index = 1;
-	req->sb_index = sb_index;
-}
-static inline void
-devlink_sb_port_pool_set_req_set_sb_pool_index(struct devlink_sb_port_pool_set_req *req,
-					       __u16 sb_pool_index)
-{
-	req->_present.sb_pool_index = 1;
-	req->sb_pool_index = sb_pool_index;
-}
-static inline void
-devlink_sb_port_pool_set_req_set_sb_threshold(struct devlink_sb_port_pool_set_req *req,
-					      __u32 sb_threshold)
-{
-	req->_present.sb_threshold = 1;
-	req->sb_threshold = sb_threshold;
-}
-
-/*
- * Set shared buffer port-pool combinations and threshold.
- */
-int devlink_sb_port_pool_set(struct ynl_sock *ys,
-			     struct devlink_sb_port_pool_set_req *req);
-
-/* ============== DEVLINK_CMD_SB_TC_POOL_BIND_GET ============== */
-/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - do */
-struct devlink_sb_tc_pool_bind_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 sb_index:1;
-		__u32 sb_pool_type:1;
-		__u32 sb_tc_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	__u32 sb_index;
-	enum devlink_sb_pool_type sb_pool_type;
-	__u16 sb_tc_index;
-};
-
-static inline struct devlink_sb_tc_pool_bind_get_req *
-devlink_sb_tc_pool_bind_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_sb_tc_pool_bind_get_req));
-}
-void
-devlink_sb_tc_pool_bind_get_req_free(struct devlink_sb_tc_pool_bind_get_req *req);
-
-static inline void
-devlink_sb_tc_pool_bind_get_req_set_bus_name(struct devlink_sb_tc_pool_bind_get_req *req,
-					     const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_sb_tc_pool_bind_get_req_set_dev_name(struct devlink_sb_tc_pool_bind_get_req *req,
-					     const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_sb_tc_pool_bind_get_req_set_port_index(struct devlink_sb_tc_pool_bind_get_req *req,
-					       __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-static inline void
-devlink_sb_tc_pool_bind_get_req_set_sb_index(struct devlink_sb_tc_pool_bind_get_req *req,
-					     __u32 sb_index)
-{
-	req->_present.sb_index = 1;
-	req->sb_index = sb_index;
-}
-static inline void
-devlink_sb_tc_pool_bind_get_req_set_sb_pool_type(struct devlink_sb_tc_pool_bind_get_req *req,
-						 enum devlink_sb_pool_type sb_pool_type)
-{
-	req->_present.sb_pool_type = 1;
-	req->sb_pool_type = sb_pool_type;
-}
-static inline void
-devlink_sb_tc_pool_bind_get_req_set_sb_tc_index(struct devlink_sb_tc_pool_bind_get_req *req,
-						__u16 sb_tc_index)
-{
-	req->_present.sb_tc_index = 1;
-	req->sb_tc_index = sb_tc_index;
-}
-
-struct devlink_sb_tc_pool_bind_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 sb_index:1;
-		__u32 sb_pool_type:1;
-		__u32 sb_tc_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	__u32 sb_index;
-	enum devlink_sb_pool_type sb_pool_type;
-	__u16 sb_tc_index;
-};
-
-void
-devlink_sb_tc_pool_bind_get_rsp_free(struct devlink_sb_tc_pool_bind_get_rsp *rsp);
-
-/*
- * Get shared buffer port-TC to pool bindings and threshold.
- */
-struct devlink_sb_tc_pool_bind_get_rsp *
-devlink_sb_tc_pool_bind_get(struct ynl_sock *ys,
-			    struct devlink_sb_tc_pool_bind_get_req *req);
-
-/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - dump */
-struct devlink_sb_tc_pool_bind_get_req_dump {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-};
-
-static inline struct devlink_sb_tc_pool_bind_get_req_dump *
-devlink_sb_tc_pool_bind_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_sb_tc_pool_bind_get_req_dump));
-}
-void
-devlink_sb_tc_pool_bind_get_req_dump_free(struct devlink_sb_tc_pool_bind_get_req_dump *req);
-
-static inline void
-devlink_sb_tc_pool_bind_get_req_dump_set_bus_name(struct devlink_sb_tc_pool_bind_get_req_dump *req,
-						  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_sb_tc_pool_bind_get_req_dump_set_dev_name(struct devlink_sb_tc_pool_bind_get_req_dump *req,
-						  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-
-struct devlink_sb_tc_pool_bind_get_list {
-	struct devlink_sb_tc_pool_bind_get_list *next;
-	struct devlink_sb_tc_pool_bind_get_rsp obj __attribute__((aligned(8)));
-};
-
-void
-devlink_sb_tc_pool_bind_get_list_free(struct devlink_sb_tc_pool_bind_get_list *rsp);
-
-struct devlink_sb_tc_pool_bind_get_list *
-devlink_sb_tc_pool_bind_get_dump(struct ynl_sock *ys,
-				 struct devlink_sb_tc_pool_bind_get_req_dump *req);
-
-/* ============== DEVLINK_CMD_SB_TC_POOL_BIND_SET ============== */
-/* DEVLINK_CMD_SB_TC_POOL_BIND_SET - do */
-struct devlink_sb_tc_pool_bind_set_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 sb_index:1;
-		__u32 sb_pool_index:1;
-		__u32 sb_pool_type:1;
-		__u32 sb_tc_index:1;
-		__u32 sb_threshold:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	__u32 sb_index;
-	__u16 sb_pool_index;
-	enum devlink_sb_pool_type sb_pool_type;
-	__u16 sb_tc_index;
-	__u32 sb_threshold;
-};
-
-static inline struct devlink_sb_tc_pool_bind_set_req *
-devlink_sb_tc_pool_bind_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_sb_tc_pool_bind_set_req));
-}
-void
-devlink_sb_tc_pool_bind_set_req_free(struct devlink_sb_tc_pool_bind_set_req *req);
-
-static inline void
-devlink_sb_tc_pool_bind_set_req_set_bus_name(struct devlink_sb_tc_pool_bind_set_req *req,
-					     const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_sb_tc_pool_bind_set_req_set_dev_name(struct devlink_sb_tc_pool_bind_set_req *req,
-					     const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_sb_tc_pool_bind_set_req_set_port_index(struct devlink_sb_tc_pool_bind_set_req *req,
-					       __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-static inline void
-devlink_sb_tc_pool_bind_set_req_set_sb_index(struct devlink_sb_tc_pool_bind_set_req *req,
-					     __u32 sb_index)
-{
-	req->_present.sb_index = 1;
-	req->sb_index = sb_index;
-}
-static inline void
-devlink_sb_tc_pool_bind_set_req_set_sb_pool_index(struct devlink_sb_tc_pool_bind_set_req *req,
-						  __u16 sb_pool_index)
-{
-	req->_present.sb_pool_index = 1;
-	req->sb_pool_index = sb_pool_index;
-}
-static inline void
-devlink_sb_tc_pool_bind_set_req_set_sb_pool_type(struct devlink_sb_tc_pool_bind_set_req *req,
-						 enum devlink_sb_pool_type sb_pool_type)
-{
-	req->_present.sb_pool_type = 1;
-	req->sb_pool_type = sb_pool_type;
-}
-static inline void
-devlink_sb_tc_pool_bind_set_req_set_sb_tc_index(struct devlink_sb_tc_pool_bind_set_req *req,
-						__u16 sb_tc_index)
-{
-	req->_present.sb_tc_index = 1;
-	req->sb_tc_index = sb_tc_index;
-}
-static inline void
-devlink_sb_tc_pool_bind_set_req_set_sb_threshold(struct devlink_sb_tc_pool_bind_set_req *req,
-						 __u32 sb_threshold)
-{
-	req->_present.sb_threshold = 1;
-	req->sb_threshold = sb_threshold;
-}
-
-/*
- * Set shared buffer port-TC to pool bindings and threshold.
- */
-int devlink_sb_tc_pool_bind_set(struct ynl_sock *ys,
-				struct devlink_sb_tc_pool_bind_set_req *req);
-
-/* ============== DEVLINK_CMD_SB_OCC_SNAPSHOT ============== */
-/* DEVLINK_CMD_SB_OCC_SNAPSHOT - do */
-struct devlink_sb_occ_snapshot_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 sb_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 sb_index;
-};
-
-static inline struct devlink_sb_occ_snapshot_req *
-devlink_sb_occ_snapshot_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_sb_occ_snapshot_req));
-}
-void devlink_sb_occ_snapshot_req_free(struct devlink_sb_occ_snapshot_req *req);
-
-static inline void
-devlink_sb_occ_snapshot_req_set_bus_name(struct devlink_sb_occ_snapshot_req *req,
-					 const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_sb_occ_snapshot_req_set_dev_name(struct devlink_sb_occ_snapshot_req *req,
-					 const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_sb_occ_snapshot_req_set_sb_index(struct devlink_sb_occ_snapshot_req *req,
-					 __u32 sb_index)
-{
-	req->_present.sb_index = 1;
-	req->sb_index = sb_index;
-}
-
-/*
- * Take occupancy snapshot of shared buffer.
- */
-int devlink_sb_occ_snapshot(struct ynl_sock *ys,
-			    struct devlink_sb_occ_snapshot_req *req);
-
-/* ============== DEVLINK_CMD_SB_OCC_MAX_CLEAR ============== */
-/* DEVLINK_CMD_SB_OCC_MAX_CLEAR - do */
-struct devlink_sb_occ_max_clear_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 sb_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 sb_index;
-};
-
-static inline struct devlink_sb_occ_max_clear_req *
-devlink_sb_occ_max_clear_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_sb_occ_max_clear_req));
-}
-void
-devlink_sb_occ_max_clear_req_free(struct devlink_sb_occ_max_clear_req *req);
-
-static inline void
-devlink_sb_occ_max_clear_req_set_bus_name(struct devlink_sb_occ_max_clear_req *req,
-					  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_sb_occ_max_clear_req_set_dev_name(struct devlink_sb_occ_max_clear_req *req,
-					  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_sb_occ_max_clear_req_set_sb_index(struct devlink_sb_occ_max_clear_req *req,
-					  __u32 sb_index)
-{
-	req->_present.sb_index = 1;
-	req->sb_index = sb_index;
-}
-
-/*
- * Clear occupancy watermarks of shared buffer.
- */
-int devlink_sb_occ_max_clear(struct ynl_sock *ys,
-			     struct devlink_sb_occ_max_clear_req *req);
-
-/* ============== DEVLINK_CMD_ESWITCH_GET ============== */
-/* DEVLINK_CMD_ESWITCH_GET - do */
-struct devlink_eswitch_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-};
-
-static inline struct devlink_eswitch_get_req *
-devlink_eswitch_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_eswitch_get_req));
-}
-void devlink_eswitch_get_req_free(struct devlink_eswitch_get_req *req);
-
-static inline void
-devlink_eswitch_get_req_set_bus_name(struct devlink_eswitch_get_req *req,
-				     const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_eswitch_get_req_set_dev_name(struct devlink_eswitch_get_req *req,
-				     const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-
-struct devlink_eswitch_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 eswitch_mode:1;
-		__u32 eswitch_inline_mode:1;
-		__u32 eswitch_encap_mode:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	enum devlink_eswitch_mode eswitch_mode;
-	enum devlink_eswitch_inline_mode eswitch_inline_mode;
-	enum devlink_eswitch_encap_mode eswitch_encap_mode;
-};
-
-void devlink_eswitch_get_rsp_free(struct devlink_eswitch_get_rsp *rsp);
-
-/*
- * Get eswitch attributes.
- */
-struct devlink_eswitch_get_rsp *
-devlink_eswitch_get(struct ynl_sock *ys, struct devlink_eswitch_get_req *req);
-
-/* ============== DEVLINK_CMD_ESWITCH_SET ============== */
-/* DEVLINK_CMD_ESWITCH_SET - do */
-struct devlink_eswitch_set_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 eswitch_mode:1;
-		__u32 eswitch_inline_mode:1;
-		__u32 eswitch_encap_mode:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	enum devlink_eswitch_mode eswitch_mode;
-	enum devlink_eswitch_inline_mode eswitch_inline_mode;
-	enum devlink_eswitch_encap_mode eswitch_encap_mode;
-};
-
-static inline struct devlink_eswitch_set_req *
-devlink_eswitch_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_eswitch_set_req));
-}
-void devlink_eswitch_set_req_free(struct devlink_eswitch_set_req *req);
-
-static inline void
-devlink_eswitch_set_req_set_bus_name(struct devlink_eswitch_set_req *req,
-				     const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_eswitch_set_req_set_dev_name(struct devlink_eswitch_set_req *req,
-				     const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_eswitch_set_req_set_eswitch_mode(struct devlink_eswitch_set_req *req,
-					 enum devlink_eswitch_mode eswitch_mode)
-{
-	req->_present.eswitch_mode = 1;
-	req->eswitch_mode = eswitch_mode;
-}
-static inline void
-devlink_eswitch_set_req_set_eswitch_inline_mode(struct devlink_eswitch_set_req *req,
-						enum devlink_eswitch_inline_mode eswitch_inline_mode)
-{
-	req->_present.eswitch_inline_mode = 1;
-	req->eswitch_inline_mode = eswitch_inline_mode;
-}
-static inline void
-devlink_eswitch_set_req_set_eswitch_encap_mode(struct devlink_eswitch_set_req *req,
-					       enum devlink_eswitch_encap_mode eswitch_encap_mode)
-{
-	req->_present.eswitch_encap_mode = 1;
-	req->eswitch_encap_mode = eswitch_encap_mode;
-}
-
-/*
- * Set eswitch attributes.
- */
-int devlink_eswitch_set(struct ynl_sock *ys,
-			struct devlink_eswitch_set_req *req);
-
-/* ============== DEVLINK_CMD_DPIPE_TABLE_GET ============== */
-/* DEVLINK_CMD_DPIPE_TABLE_GET - do */
-struct devlink_dpipe_table_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 dpipe_table_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	char *dpipe_table_name;
-};
-
-static inline struct devlink_dpipe_table_get_req *
-devlink_dpipe_table_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_dpipe_table_get_req));
-}
-void devlink_dpipe_table_get_req_free(struct devlink_dpipe_table_get_req *req);
-
-static inline void
-devlink_dpipe_table_get_req_set_bus_name(struct devlink_dpipe_table_get_req *req,
-					 const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_dpipe_table_get_req_set_dev_name(struct devlink_dpipe_table_get_req *req,
-					 const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_dpipe_table_get_req_set_dpipe_table_name(struct devlink_dpipe_table_get_req *req,
-						 const char *dpipe_table_name)
-{
-	free(req->dpipe_table_name);
-	req->_present.dpipe_table_name_len = strlen(dpipe_table_name);
-	req->dpipe_table_name = malloc(req->_present.dpipe_table_name_len + 1);
-	memcpy(req->dpipe_table_name, dpipe_table_name, req->_present.dpipe_table_name_len);
-	req->dpipe_table_name[req->_present.dpipe_table_name_len] = 0;
-}
-
-struct devlink_dpipe_table_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 dpipe_tables:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	struct devlink_dl_dpipe_tables dpipe_tables;
-};
-
-void devlink_dpipe_table_get_rsp_free(struct devlink_dpipe_table_get_rsp *rsp);
-
-/*
- * Get dpipe table attributes.
- */
-struct devlink_dpipe_table_get_rsp *
-devlink_dpipe_table_get(struct ynl_sock *ys,
-			struct devlink_dpipe_table_get_req *req);
-
-/* ============== DEVLINK_CMD_DPIPE_ENTRIES_GET ============== */
-/* DEVLINK_CMD_DPIPE_ENTRIES_GET - do */
-struct devlink_dpipe_entries_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 dpipe_table_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	char *dpipe_table_name;
-};
-
-static inline struct devlink_dpipe_entries_get_req *
-devlink_dpipe_entries_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_dpipe_entries_get_req));
-}
-void
-devlink_dpipe_entries_get_req_free(struct devlink_dpipe_entries_get_req *req);
-
-static inline void
-devlink_dpipe_entries_get_req_set_bus_name(struct devlink_dpipe_entries_get_req *req,
-					   const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_dpipe_entries_get_req_set_dev_name(struct devlink_dpipe_entries_get_req *req,
-					   const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_dpipe_entries_get_req_set_dpipe_table_name(struct devlink_dpipe_entries_get_req *req,
-						   const char *dpipe_table_name)
-{
-	free(req->dpipe_table_name);
-	req->_present.dpipe_table_name_len = strlen(dpipe_table_name);
-	req->dpipe_table_name = malloc(req->_present.dpipe_table_name_len + 1);
-	memcpy(req->dpipe_table_name, dpipe_table_name, req->_present.dpipe_table_name_len);
-	req->dpipe_table_name[req->_present.dpipe_table_name_len] = 0;
-}
-
-struct devlink_dpipe_entries_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 dpipe_entries:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	struct devlink_dl_dpipe_entries dpipe_entries;
-};
-
-void
-devlink_dpipe_entries_get_rsp_free(struct devlink_dpipe_entries_get_rsp *rsp);
-
-/*
- * Get dpipe entries attributes.
- */
-struct devlink_dpipe_entries_get_rsp *
-devlink_dpipe_entries_get(struct ynl_sock *ys,
-			  struct devlink_dpipe_entries_get_req *req);
-
-/* ============== DEVLINK_CMD_DPIPE_HEADERS_GET ============== */
-/* DEVLINK_CMD_DPIPE_HEADERS_GET - do */
-struct devlink_dpipe_headers_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-};
-
-static inline struct devlink_dpipe_headers_get_req *
-devlink_dpipe_headers_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_dpipe_headers_get_req));
-}
-void
-devlink_dpipe_headers_get_req_free(struct devlink_dpipe_headers_get_req *req);
-
-static inline void
-devlink_dpipe_headers_get_req_set_bus_name(struct devlink_dpipe_headers_get_req *req,
-					   const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_dpipe_headers_get_req_set_dev_name(struct devlink_dpipe_headers_get_req *req,
-					   const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-
-struct devlink_dpipe_headers_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 dpipe_headers:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	struct devlink_dl_dpipe_headers dpipe_headers;
-};
-
-void
-devlink_dpipe_headers_get_rsp_free(struct devlink_dpipe_headers_get_rsp *rsp);
-
-/*
- * Get dpipe headers attributes.
- */
-struct devlink_dpipe_headers_get_rsp *
-devlink_dpipe_headers_get(struct ynl_sock *ys,
-			  struct devlink_dpipe_headers_get_req *req);
-
-/* ============== DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET ============== */
-/* DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET - do */
-struct devlink_dpipe_table_counters_set_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 dpipe_table_name_len;
-		__u32 dpipe_table_counters_enabled:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	char *dpipe_table_name;
-	__u8 dpipe_table_counters_enabled;
-};
-
-static inline struct devlink_dpipe_table_counters_set_req *
-devlink_dpipe_table_counters_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_dpipe_table_counters_set_req));
-}
-void
-devlink_dpipe_table_counters_set_req_free(struct devlink_dpipe_table_counters_set_req *req);
-
-static inline void
-devlink_dpipe_table_counters_set_req_set_bus_name(struct devlink_dpipe_table_counters_set_req *req,
-						  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_dpipe_table_counters_set_req_set_dev_name(struct devlink_dpipe_table_counters_set_req *req,
-						  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_dpipe_table_counters_set_req_set_dpipe_table_name(struct devlink_dpipe_table_counters_set_req *req,
-							  const char *dpipe_table_name)
-{
-	free(req->dpipe_table_name);
-	req->_present.dpipe_table_name_len = strlen(dpipe_table_name);
-	req->dpipe_table_name = malloc(req->_present.dpipe_table_name_len + 1);
-	memcpy(req->dpipe_table_name, dpipe_table_name, req->_present.dpipe_table_name_len);
-	req->dpipe_table_name[req->_present.dpipe_table_name_len] = 0;
-}
-static inline void
-devlink_dpipe_table_counters_set_req_set_dpipe_table_counters_enabled(struct devlink_dpipe_table_counters_set_req *req,
-								      __u8 dpipe_table_counters_enabled)
-{
-	req->_present.dpipe_table_counters_enabled = 1;
-	req->dpipe_table_counters_enabled = dpipe_table_counters_enabled;
-}
-
-/*
- * Set dpipe counter attributes.
- */
-int devlink_dpipe_table_counters_set(struct ynl_sock *ys,
-				     struct devlink_dpipe_table_counters_set_req *req);
-
-/* ============== DEVLINK_CMD_RESOURCE_SET ============== */
-/* DEVLINK_CMD_RESOURCE_SET - do */
-struct devlink_resource_set_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 resource_id:1;
-		__u32 resource_size:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u64 resource_id;
-	__u64 resource_size;
-};
-
-static inline struct devlink_resource_set_req *
-devlink_resource_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_resource_set_req));
-}
-void devlink_resource_set_req_free(struct devlink_resource_set_req *req);
-
-static inline void
-devlink_resource_set_req_set_bus_name(struct devlink_resource_set_req *req,
-				      const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_resource_set_req_set_dev_name(struct devlink_resource_set_req *req,
-				      const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_resource_set_req_set_resource_id(struct devlink_resource_set_req *req,
-					 __u64 resource_id)
-{
-	req->_present.resource_id = 1;
-	req->resource_id = resource_id;
-}
-static inline void
-devlink_resource_set_req_set_resource_size(struct devlink_resource_set_req *req,
-					   __u64 resource_size)
-{
-	req->_present.resource_size = 1;
-	req->resource_size = resource_size;
-}
-
-/*
- * Set resource attributes.
- */
-int devlink_resource_set(struct ynl_sock *ys,
-			 struct devlink_resource_set_req *req);
-
-/* ============== DEVLINK_CMD_RESOURCE_DUMP ============== */
-/* DEVLINK_CMD_RESOURCE_DUMP - do */
-struct devlink_resource_dump_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-};
-
-static inline struct devlink_resource_dump_req *
-devlink_resource_dump_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_resource_dump_req));
-}
-void devlink_resource_dump_req_free(struct devlink_resource_dump_req *req);
-
-static inline void
-devlink_resource_dump_req_set_bus_name(struct devlink_resource_dump_req *req,
-				       const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_resource_dump_req_set_dev_name(struct devlink_resource_dump_req *req,
-				       const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-
-struct devlink_resource_dump_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 resource_list:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	struct devlink_dl_resource_list resource_list;
-};
-
-void devlink_resource_dump_rsp_free(struct devlink_resource_dump_rsp *rsp);
-
-/*
- * Get resource attributes.
- */
-struct devlink_resource_dump_rsp *
-devlink_resource_dump(struct ynl_sock *ys,
-		      struct devlink_resource_dump_req *req);
-
-/* ============== DEVLINK_CMD_RELOAD ============== */
-/* DEVLINK_CMD_RELOAD - do */
-struct devlink_reload_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 reload_action:1;
-		__u32 reload_limits:1;
-		__u32 netns_pid:1;
-		__u32 netns_fd:1;
-		__u32 netns_id:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	enum devlink_reload_action reload_action;
-	struct nla_bitfield32 reload_limits;
-	__u32 netns_pid;
-	__u32 netns_fd;
-	__u32 netns_id;
-};
-
-static inline struct devlink_reload_req *devlink_reload_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_reload_req));
-}
-void devlink_reload_req_free(struct devlink_reload_req *req);
-
-static inline void
-devlink_reload_req_set_bus_name(struct devlink_reload_req *req,
-				const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_reload_req_set_dev_name(struct devlink_reload_req *req,
-				const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_reload_req_set_reload_action(struct devlink_reload_req *req,
-				     enum devlink_reload_action reload_action)
-{
-	req->_present.reload_action = 1;
-	req->reload_action = reload_action;
-}
-static inline void
-devlink_reload_req_set_reload_limits(struct devlink_reload_req *req,
-				     struct nla_bitfield32 *reload_limits)
-{
-	req->_present.reload_limits = 1;
-	memcpy(&req->reload_limits, reload_limits, sizeof(struct nla_bitfield32));
-}
-static inline void
-devlink_reload_req_set_netns_pid(struct devlink_reload_req *req,
-				 __u32 netns_pid)
-{
-	req->_present.netns_pid = 1;
-	req->netns_pid = netns_pid;
-}
-static inline void
-devlink_reload_req_set_netns_fd(struct devlink_reload_req *req, __u32 netns_fd)
-{
-	req->_present.netns_fd = 1;
-	req->netns_fd = netns_fd;
-}
-static inline void
-devlink_reload_req_set_netns_id(struct devlink_reload_req *req, __u32 netns_id)
-{
-	req->_present.netns_id = 1;
-	req->netns_id = netns_id;
-}
-
-struct devlink_reload_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 reload_actions_performed:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	struct nla_bitfield32 reload_actions_performed;
-};
-
-void devlink_reload_rsp_free(struct devlink_reload_rsp *rsp);
-
-/*
- * Reload devlink.
- */
-struct devlink_reload_rsp *
-devlink_reload(struct ynl_sock *ys, struct devlink_reload_req *req);
-
-/* ============== DEVLINK_CMD_PARAM_GET ============== */
-/* DEVLINK_CMD_PARAM_GET - do */
-struct devlink_param_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 param_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	char *param_name;
-};
-
-static inline struct devlink_param_get_req *devlink_param_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_param_get_req));
-}
-void devlink_param_get_req_free(struct devlink_param_get_req *req);
-
-static inline void
-devlink_param_get_req_set_bus_name(struct devlink_param_get_req *req,
-				   const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_param_get_req_set_dev_name(struct devlink_param_get_req *req,
-				   const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_param_get_req_set_param_name(struct devlink_param_get_req *req,
-				     const char *param_name)
-{
-	free(req->param_name);
-	req->_present.param_name_len = strlen(param_name);
-	req->param_name = malloc(req->_present.param_name_len + 1);
-	memcpy(req->param_name, param_name, req->_present.param_name_len);
-	req->param_name[req->_present.param_name_len] = 0;
-}
-
-struct devlink_param_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 param_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	char *param_name;
-};
-
-void devlink_param_get_rsp_free(struct devlink_param_get_rsp *rsp);
-
-/*
- * Get param instances.
- */
-struct devlink_param_get_rsp *
-devlink_param_get(struct ynl_sock *ys, struct devlink_param_get_req *req);
-
-/* DEVLINK_CMD_PARAM_GET - dump */
-struct devlink_param_get_req_dump {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-};
-
-static inline struct devlink_param_get_req_dump *
-devlink_param_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_param_get_req_dump));
-}
-void devlink_param_get_req_dump_free(struct devlink_param_get_req_dump *req);
-
-static inline void
-devlink_param_get_req_dump_set_bus_name(struct devlink_param_get_req_dump *req,
-					const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_param_get_req_dump_set_dev_name(struct devlink_param_get_req_dump *req,
-					const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-
-struct devlink_param_get_list {
-	struct devlink_param_get_list *next;
-	struct devlink_param_get_rsp obj __attribute__((aligned(8)));
-};
-
-void devlink_param_get_list_free(struct devlink_param_get_list *rsp);
-
-struct devlink_param_get_list *
-devlink_param_get_dump(struct ynl_sock *ys,
-		       struct devlink_param_get_req_dump *req);
-
-/* ============== DEVLINK_CMD_PARAM_SET ============== */
-/* DEVLINK_CMD_PARAM_SET - do */
-struct devlink_param_set_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 param_name_len;
-		__u32 param_type:1;
-		__u32 param_value_cmode:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	char *param_name;
-	__u8 param_type;
-	enum devlink_param_cmode param_value_cmode;
-};
-
-static inline struct devlink_param_set_req *devlink_param_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_param_set_req));
-}
-void devlink_param_set_req_free(struct devlink_param_set_req *req);
-
-static inline void
-devlink_param_set_req_set_bus_name(struct devlink_param_set_req *req,
-				   const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_param_set_req_set_dev_name(struct devlink_param_set_req *req,
-				   const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_param_set_req_set_param_name(struct devlink_param_set_req *req,
-				     const char *param_name)
-{
-	free(req->param_name);
-	req->_present.param_name_len = strlen(param_name);
-	req->param_name = malloc(req->_present.param_name_len + 1);
-	memcpy(req->param_name, param_name, req->_present.param_name_len);
-	req->param_name[req->_present.param_name_len] = 0;
-}
-static inline void
-devlink_param_set_req_set_param_type(struct devlink_param_set_req *req,
-				     __u8 param_type)
-{
-	req->_present.param_type = 1;
-	req->param_type = param_type;
-}
-static inline void
-devlink_param_set_req_set_param_value_cmode(struct devlink_param_set_req *req,
-					    enum devlink_param_cmode param_value_cmode)
-{
-	req->_present.param_value_cmode = 1;
-	req->param_value_cmode = param_value_cmode;
-}
-
-/*
- * Set param instances.
- */
-int devlink_param_set(struct ynl_sock *ys, struct devlink_param_set_req *req);
-
-/* ============== DEVLINK_CMD_REGION_GET ============== */
-/* DEVLINK_CMD_REGION_GET - do */
-struct devlink_region_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 region_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	char *region_name;
-};
-
-static inline struct devlink_region_get_req *devlink_region_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_region_get_req));
-}
-void devlink_region_get_req_free(struct devlink_region_get_req *req);
-
-static inline void
-devlink_region_get_req_set_bus_name(struct devlink_region_get_req *req,
-				    const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_region_get_req_set_dev_name(struct devlink_region_get_req *req,
-				    const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_region_get_req_set_port_index(struct devlink_region_get_req *req,
-				      __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-static inline void
-devlink_region_get_req_set_region_name(struct devlink_region_get_req *req,
-				       const char *region_name)
-{
-	free(req->region_name);
-	req->_present.region_name_len = strlen(region_name);
-	req->region_name = malloc(req->_present.region_name_len + 1);
-	memcpy(req->region_name, region_name, req->_present.region_name_len);
-	req->region_name[req->_present.region_name_len] = 0;
-}
-
-struct devlink_region_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 region_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	char *region_name;
-};
-
-void devlink_region_get_rsp_free(struct devlink_region_get_rsp *rsp);
-
-/*
- * Get region instances.
- */
-struct devlink_region_get_rsp *
-devlink_region_get(struct ynl_sock *ys, struct devlink_region_get_req *req);
-
-/* DEVLINK_CMD_REGION_GET - dump */
-struct devlink_region_get_req_dump {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-};
-
-static inline struct devlink_region_get_req_dump *
-devlink_region_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_region_get_req_dump));
-}
-void devlink_region_get_req_dump_free(struct devlink_region_get_req_dump *req);
-
-static inline void
-devlink_region_get_req_dump_set_bus_name(struct devlink_region_get_req_dump *req,
-					 const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_region_get_req_dump_set_dev_name(struct devlink_region_get_req_dump *req,
-					 const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-
-struct devlink_region_get_list {
-	struct devlink_region_get_list *next;
-	struct devlink_region_get_rsp obj __attribute__((aligned(8)));
-};
-
-void devlink_region_get_list_free(struct devlink_region_get_list *rsp);
-
-struct devlink_region_get_list *
-devlink_region_get_dump(struct ynl_sock *ys,
-			struct devlink_region_get_req_dump *req);
-
-/* ============== DEVLINK_CMD_REGION_NEW ============== */
-/* DEVLINK_CMD_REGION_NEW - do */
-struct devlink_region_new_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 region_name_len;
-		__u32 region_snapshot_id:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	char *region_name;
-	__u32 region_snapshot_id;
-};
-
-static inline struct devlink_region_new_req *devlink_region_new_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_region_new_req));
-}
-void devlink_region_new_req_free(struct devlink_region_new_req *req);
-
-static inline void
-devlink_region_new_req_set_bus_name(struct devlink_region_new_req *req,
-				    const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_region_new_req_set_dev_name(struct devlink_region_new_req *req,
-				    const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_region_new_req_set_port_index(struct devlink_region_new_req *req,
-				      __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-static inline void
-devlink_region_new_req_set_region_name(struct devlink_region_new_req *req,
-				       const char *region_name)
-{
-	free(req->region_name);
-	req->_present.region_name_len = strlen(region_name);
-	req->region_name = malloc(req->_present.region_name_len + 1);
-	memcpy(req->region_name, region_name, req->_present.region_name_len);
-	req->region_name[req->_present.region_name_len] = 0;
-}
-static inline void
-devlink_region_new_req_set_region_snapshot_id(struct devlink_region_new_req *req,
-					      __u32 region_snapshot_id)
-{
-	req->_present.region_snapshot_id = 1;
-	req->region_snapshot_id = region_snapshot_id;
-}
-
-struct devlink_region_new_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 region_name_len;
-		__u32 region_snapshot_id:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	char *region_name;
-	__u32 region_snapshot_id;
-};
-
-void devlink_region_new_rsp_free(struct devlink_region_new_rsp *rsp);
-
-/*
- * Create region snapshot.
- */
-struct devlink_region_new_rsp *
-devlink_region_new(struct ynl_sock *ys, struct devlink_region_new_req *req);
-
-/* ============== DEVLINK_CMD_REGION_DEL ============== */
-/* DEVLINK_CMD_REGION_DEL - do */
-struct devlink_region_del_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 region_name_len;
-		__u32 region_snapshot_id:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	char *region_name;
-	__u32 region_snapshot_id;
-};
-
-static inline struct devlink_region_del_req *devlink_region_del_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_region_del_req));
-}
-void devlink_region_del_req_free(struct devlink_region_del_req *req);
-
-static inline void
-devlink_region_del_req_set_bus_name(struct devlink_region_del_req *req,
-				    const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_region_del_req_set_dev_name(struct devlink_region_del_req *req,
-				    const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_region_del_req_set_port_index(struct devlink_region_del_req *req,
-				      __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-static inline void
-devlink_region_del_req_set_region_name(struct devlink_region_del_req *req,
-				       const char *region_name)
-{
-	free(req->region_name);
-	req->_present.region_name_len = strlen(region_name);
-	req->region_name = malloc(req->_present.region_name_len + 1);
-	memcpy(req->region_name, region_name, req->_present.region_name_len);
-	req->region_name[req->_present.region_name_len] = 0;
-}
-static inline void
-devlink_region_del_req_set_region_snapshot_id(struct devlink_region_del_req *req,
-					      __u32 region_snapshot_id)
-{
-	req->_present.region_snapshot_id = 1;
-	req->region_snapshot_id = region_snapshot_id;
-}
-
-/*
- * Delete region snapshot.
- */
-int devlink_region_del(struct ynl_sock *ys, struct devlink_region_del_req *req);
-
-/* ============== DEVLINK_CMD_REGION_READ ============== */
-/* DEVLINK_CMD_REGION_READ - dump */
-struct devlink_region_read_req_dump {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 region_name_len;
-		__u32 region_snapshot_id:1;
-		__u32 region_direct:1;
-		__u32 region_chunk_addr:1;
-		__u32 region_chunk_len:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	char *region_name;
-	__u32 region_snapshot_id;
-	__u64 region_chunk_addr;
-	__u64 region_chunk_len;
-};
-
-static inline struct devlink_region_read_req_dump *
-devlink_region_read_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_region_read_req_dump));
-}
-void
-devlink_region_read_req_dump_free(struct devlink_region_read_req_dump *req);
-
-static inline void
-devlink_region_read_req_dump_set_bus_name(struct devlink_region_read_req_dump *req,
-					  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_region_read_req_dump_set_dev_name(struct devlink_region_read_req_dump *req,
-					  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_region_read_req_dump_set_port_index(struct devlink_region_read_req_dump *req,
-					    __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-static inline void
-devlink_region_read_req_dump_set_region_name(struct devlink_region_read_req_dump *req,
-					     const char *region_name)
-{
-	free(req->region_name);
-	req->_present.region_name_len = strlen(region_name);
-	req->region_name = malloc(req->_present.region_name_len + 1);
-	memcpy(req->region_name, region_name, req->_present.region_name_len);
-	req->region_name[req->_present.region_name_len] = 0;
-}
-static inline void
-devlink_region_read_req_dump_set_region_snapshot_id(struct devlink_region_read_req_dump *req,
-						    __u32 region_snapshot_id)
-{
-	req->_present.region_snapshot_id = 1;
-	req->region_snapshot_id = region_snapshot_id;
-}
-static inline void
-devlink_region_read_req_dump_set_region_direct(struct devlink_region_read_req_dump *req)
-{
-	req->_present.region_direct = 1;
-}
-static inline void
-devlink_region_read_req_dump_set_region_chunk_addr(struct devlink_region_read_req_dump *req,
-						   __u64 region_chunk_addr)
-{
-	req->_present.region_chunk_addr = 1;
-	req->region_chunk_addr = region_chunk_addr;
-}
-static inline void
-devlink_region_read_req_dump_set_region_chunk_len(struct devlink_region_read_req_dump *req,
-						  __u64 region_chunk_len)
-{
-	req->_present.region_chunk_len = 1;
-	req->region_chunk_len = region_chunk_len;
-}
-
-struct devlink_region_read_rsp_dump {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 region_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	char *region_name;
-};
-
-struct devlink_region_read_rsp_list {
-	struct devlink_region_read_rsp_list *next;
-	struct devlink_region_read_rsp_dump obj __attribute__((aligned(8)));
-};
-
-void
-devlink_region_read_rsp_list_free(struct devlink_region_read_rsp_list *rsp);
-
-struct devlink_region_read_rsp_list *
-devlink_region_read_dump(struct ynl_sock *ys,
-			 struct devlink_region_read_req_dump *req);
-
-/* ============== DEVLINK_CMD_PORT_PARAM_GET ============== */
-/* DEVLINK_CMD_PORT_PARAM_GET - do */
-struct devlink_port_param_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-};
-
-static inline struct devlink_port_param_get_req *
-devlink_port_param_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_port_param_get_req));
-}
-void devlink_port_param_get_req_free(struct devlink_port_param_get_req *req);
-
-static inline void
-devlink_port_param_get_req_set_bus_name(struct devlink_port_param_get_req *req,
-					const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_port_param_get_req_set_dev_name(struct devlink_port_param_get_req *req,
-					const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_port_param_get_req_set_port_index(struct devlink_port_param_get_req *req,
-					  __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-
-struct devlink_port_param_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-};
-
-void devlink_port_param_get_rsp_free(struct devlink_port_param_get_rsp *rsp);
-
-/*
- * Get port param instances.
- */
-struct devlink_port_param_get_rsp *
-devlink_port_param_get(struct ynl_sock *ys,
-		       struct devlink_port_param_get_req *req);
-
-/* DEVLINK_CMD_PORT_PARAM_GET - dump */
-struct devlink_port_param_get_list {
-	struct devlink_port_param_get_list *next;
-	struct devlink_port_param_get_rsp obj __attribute__((aligned(8)));
-};
-
-void devlink_port_param_get_list_free(struct devlink_port_param_get_list *rsp);
-
-struct devlink_port_param_get_list *
-devlink_port_param_get_dump(struct ynl_sock *ys);
-
-/* ============== DEVLINK_CMD_PORT_PARAM_SET ============== */
-/* DEVLINK_CMD_PORT_PARAM_SET - do */
-struct devlink_port_param_set_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-};
-
-static inline struct devlink_port_param_set_req *
-devlink_port_param_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_port_param_set_req));
-}
-void devlink_port_param_set_req_free(struct devlink_port_param_set_req *req);
-
-static inline void
-devlink_port_param_set_req_set_bus_name(struct devlink_port_param_set_req *req,
-					const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_port_param_set_req_set_dev_name(struct devlink_port_param_set_req *req,
-					const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_port_param_set_req_set_port_index(struct devlink_port_param_set_req *req,
-					  __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-
-/*
- * Set port param instances.
- */
-int devlink_port_param_set(struct ynl_sock *ys,
-			   struct devlink_port_param_set_req *req);
-
-/* ============== DEVLINK_CMD_INFO_GET ============== */
-/* DEVLINK_CMD_INFO_GET - do */
-struct devlink_info_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-};
-
-static inline struct devlink_info_get_req *devlink_info_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_info_get_req));
-}
-void devlink_info_get_req_free(struct devlink_info_get_req *req);
-
-static inline void
-devlink_info_get_req_set_bus_name(struct devlink_info_get_req *req,
-				  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_info_get_req_set_dev_name(struct devlink_info_get_req *req,
-				  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-
-struct devlink_info_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 info_driver_name_len;
-		__u32 info_serial_number_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	char *info_driver_name;
-	char *info_serial_number;
-	unsigned int n_info_version_fixed;
-	struct devlink_dl_info_version *info_version_fixed;
-	unsigned int n_info_version_running;
-	struct devlink_dl_info_version *info_version_running;
-	unsigned int n_info_version_stored;
-	struct devlink_dl_info_version *info_version_stored;
-};
-
-void devlink_info_get_rsp_free(struct devlink_info_get_rsp *rsp);
-
-/*
- * Get device information, like driver name, hardware and firmware versions etc.
- */
-struct devlink_info_get_rsp *
-devlink_info_get(struct ynl_sock *ys, struct devlink_info_get_req *req);
-
-/* DEVLINK_CMD_INFO_GET - dump */
-struct devlink_info_get_list {
-	struct devlink_info_get_list *next;
-	struct devlink_info_get_rsp obj __attribute__((aligned(8)));
-};
-
-void devlink_info_get_list_free(struct devlink_info_get_list *rsp);
-
-struct devlink_info_get_list *devlink_info_get_dump(struct ynl_sock *ys);
-
-/* ============== DEVLINK_CMD_HEALTH_REPORTER_GET ============== */
-/* DEVLINK_CMD_HEALTH_REPORTER_GET - do */
-struct devlink_health_reporter_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 health_reporter_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	char *health_reporter_name;
-};
-
-static inline struct devlink_health_reporter_get_req *
-devlink_health_reporter_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_health_reporter_get_req));
-}
-void
-devlink_health_reporter_get_req_free(struct devlink_health_reporter_get_req *req);
-
-static inline void
-devlink_health_reporter_get_req_set_bus_name(struct devlink_health_reporter_get_req *req,
-					     const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_health_reporter_get_req_set_dev_name(struct devlink_health_reporter_get_req *req,
-					     const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_health_reporter_get_req_set_port_index(struct devlink_health_reporter_get_req *req,
-					       __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-static inline void
-devlink_health_reporter_get_req_set_health_reporter_name(struct devlink_health_reporter_get_req *req,
-							 const char *health_reporter_name)
-{
-	free(req->health_reporter_name);
-	req->_present.health_reporter_name_len = strlen(health_reporter_name);
-	req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1);
-	memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len);
-	req->health_reporter_name[req->_present.health_reporter_name_len] = 0;
-}
-
-struct devlink_health_reporter_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 health_reporter_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	char *health_reporter_name;
-};
-
-void
-devlink_health_reporter_get_rsp_free(struct devlink_health_reporter_get_rsp *rsp);
-
-/*
- * Get health reporter instances.
- */
-struct devlink_health_reporter_get_rsp *
-devlink_health_reporter_get(struct ynl_sock *ys,
-			    struct devlink_health_reporter_get_req *req);
-
-/* DEVLINK_CMD_HEALTH_REPORTER_GET - dump */
-struct devlink_health_reporter_get_req_dump {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-};
-
-static inline struct devlink_health_reporter_get_req_dump *
-devlink_health_reporter_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_health_reporter_get_req_dump));
-}
-void
-devlink_health_reporter_get_req_dump_free(struct devlink_health_reporter_get_req_dump *req);
-
-static inline void
-devlink_health_reporter_get_req_dump_set_bus_name(struct devlink_health_reporter_get_req_dump *req,
-						  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_health_reporter_get_req_dump_set_dev_name(struct devlink_health_reporter_get_req_dump *req,
-						  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_health_reporter_get_req_dump_set_port_index(struct devlink_health_reporter_get_req_dump *req,
-						    __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-
-struct devlink_health_reporter_get_list {
-	struct devlink_health_reporter_get_list *next;
-	struct devlink_health_reporter_get_rsp obj __attribute__((aligned(8)));
-};
-
-void
-devlink_health_reporter_get_list_free(struct devlink_health_reporter_get_list *rsp);
-
-struct devlink_health_reporter_get_list *
-devlink_health_reporter_get_dump(struct ynl_sock *ys,
-				 struct devlink_health_reporter_get_req_dump *req);
-
-/* ============== DEVLINK_CMD_HEALTH_REPORTER_SET ============== */
-/* DEVLINK_CMD_HEALTH_REPORTER_SET - do */
-struct devlink_health_reporter_set_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 health_reporter_name_len;
-		__u32 health_reporter_graceful_period:1;
-		__u32 health_reporter_auto_recover:1;
-		__u32 health_reporter_auto_dump:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	char *health_reporter_name;
-	__u64 health_reporter_graceful_period;
-	__u8 health_reporter_auto_recover;
-	__u8 health_reporter_auto_dump;
-};
-
-static inline struct devlink_health_reporter_set_req *
-devlink_health_reporter_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_health_reporter_set_req));
-}
-void
-devlink_health_reporter_set_req_free(struct devlink_health_reporter_set_req *req);
-
-static inline void
-devlink_health_reporter_set_req_set_bus_name(struct devlink_health_reporter_set_req *req,
-					     const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_health_reporter_set_req_set_dev_name(struct devlink_health_reporter_set_req *req,
-					     const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_health_reporter_set_req_set_port_index(struct devlink_health_reporter_set_req *req,
-					       __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-static inline void
-devlink_health_reporter_set_req_set_health_reporter_name(struct devlink_health_reporter_set_req *req,
-							 const char *health_reporter_name)
-{
-	free(req->health_reporter_name);
-	req->_present.health_reporter_name_len = strlen(health_reporter_name);
-	req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1);
-	memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len);
-	req->health_reporter_name[req->_present.health_reporter_name_len] = 0;
-}
-static inline void
-devlink_health_reporter_set_req_set_health_reporter_graceful_period(struct devlink_health_reporter_set_req *req,
-								    __u64 health_reporter_graceful_period)
-{
-	req->_present.health_reporter_graceful_period = 1;
-	req->health_reporter_graceful_period = health_reporter_graceful_period;
-}
-static inline void
-devlink_health_reporter_set_req_set_health_reporter_auto_recover(struct devlink_health_reporter_set_req *req,
-								 __u8 health_reporter_auto_recover)
-{
-	req->_present.health_reporter_auto_recover = 1;
-	req->health_reporter_auto_recover = health_reporter_auto_recover;
-}
-static inline void
-devlink_health_reporter_set_req_set_health_reporter_auto_dump(struct devlink_health_reporter_set_req *req,
-							      __u8 health_reporter_auto_dump)
-{
-	req->_present.health_reporter_auto_dump = 1;
-	req->health_reporter_auto_dump = health_reporter_auto_dump;
-}
-
-/*
- * Set health reporter instances.
- */
-int devlink_health_reporter_set(struct ynl_sock *ys,
-				struct devlink_health_reporter_set_req *req);
-
-/* ============== DEVLINK_CMD_HEALTH_REPORTER_RECOVER ============== */
-/* DEVLINK_CMD_HEALTH_REPORTER_RECOVER - do */
-struct devlink_health_reporter_recover_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 health_reporter_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	char *health_reporter_name;
-};
-
-static inline struct devlink_health_reporter_recover_req *
-devlink_health_reporter_recover_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_health_reporter_recover_req));
-}
-void
-devlink_health_reporter_recover_req_free(struct devlink_health_reporter_recover_req *req);
-
-static inline void
-devlink_health_reporter_recover_req_set_bus_name(struct devlink_health_reporter_recover_req *req,
-						 const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_health_reporter_recover_req_set_dev_name(struct devlink_health_reporter_recover_req *req,
-						 const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_health_reporter_recover_req_set_port_index(struct devlink_health_reporter_recover_req *req,
-						   __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-static inline void
-devlink_health_reporter_recover_req_set_health_reporter_name(struct devlink_health_reporter_recover_req *req,
-							     const char *health_reporter_name)
-{
-	free(req->health_reporter_name);
-	req->_present.health_reporter_name_len = strlen(health_reporter_name);
-	req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1);
-	memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len);
-	req->health_reporter_name[req->_present.health_reporter_name_len] = 0;
-}
-
-/*
- * Recover health reporter instances.
- */
-int devlink_health_reporter_recover(struct ynl_sock *ys,
-				    struct devlink_health_reporter_recover_req *req);
-
-/* ============== DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE ============== */
-/* DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE - do */
-struct devlink_health_reporter_diagnose_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 health_reporter_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	char *health_reporter_name;
-};
-
-static inline struct devlink_health_reporter_diagnose_req *
-devlink_health_reporter_diagnose_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_health_reporter_diagnose_req));
-}
-void
-devlink_health_reporter_diagnose_req_free(struct devlink_health_reporter_diagnose_req *req);
-
-static inline void
-devlink_health_reporter_diagnose_req_set_bus_name(struct devlink_health_reporter_diagnose_req *req,
-						  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_health_reporter_diagnose_req_set_dev_name(struct devlink_health_reporter_diagnose_req *req,
-						  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_health_reporter_diagnose_req_set_port_index(struct devlink_health_reporter_diagnose_req *req,
-						    __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-static inline void
-devlink_health_reporter_diagnose_req_set_health_reporter_name(struct devlink_health_reporter_diagnose_req *req,
-							      const char *health_reporter_name)
-{
-	free(req->health_reporter_name);
-	req->_present.health_reporter_name_len = strlen(health_reporter_name);
-	req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1);
-	memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len);
-	req->health_reporter_name[req->_present.health_reporter_name_len] = 0;
-}
-
-/*
- * Diagnose health reporter instances.
- */
-int devlink_health_reporter_diagnose(struct ynl_sock *ys,
-				     struct devlink_health_reporter_diagnose_req *req);
-
-/* ============== DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET ============== */
-/* DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET - dump */
-struct devlink_health_reporter_dump_get_req_dump {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 health_reporter_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	char *health_reporter_name;
-};
-
-static inline struct devlink_health_reporter_dump_get_req_dump *
-devlink_health_reporter_dump_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_health_reporter_dump_get_req_dump));
-}
-void
-devlink_health_reporter_dump_get_req_dump_free(struct devlink_health_reporter_dump_get_req_dump *req);
-
-static inline void
-devlink_health_reporter_dump_get_req_dump_set_bus_name(struct devlink_health_reporter_dump_get_req_dump *req,
-						       const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_health_reporter_dump_get_req_dump_set_dev_name(struct devlink_health_reporter_dump_get_req_dump *req,
-						       const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_health_reporter_dump_get_req_dump_set_port_index(struct devlink_health_reporter_dump_get_req_dump *req,
-							 __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-static inline void
-devlink_health_reporter_dump_get_req_dump_set_health_reporter_name(struct devlink_health_reporter_dump_get_req_dump *req,
-								   const char *health_reporter_name)
-{
-	free(req->health_reporter_name);
-	req->_present.health_reporter_name_len = strlen(health_reporter_name);
-	req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1);
-	memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len);
-	req->health_reporter_name[req->_present.health_reporter_name_len] = 0;
-}
-
-struct devlink_health_reporter_dump_get_rsp_dump {
-	struct {
-		__u32 fmsg:1;
-	} _present;
-
-	struct devlink_dl_fmsg fmsg;
-};
-
-struct devlink_health_reporter_dump_get_rsp_list {
-	struct devlink_health_reporter_dump_get_rsp_list *next;
-	struct devlink_health_reporter_dump_get_rsp_dump obj __attribute__((aligned(8)));
-};
-
-void
-devlink_health_reporter_dump_get_rsp_list_free(struct devlink_health_reporter_dump_get_rsp_list *rsp);
-
-struct devlink_health_reporter_dump_get_rsp_list *
-devlink_health_reporter_dump_get_dump(struct ynl_sock *ys,
-				      struct devlink_health_reporter_dump_get_req_dump *req);
-
-/* ============== DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR ============== */
-/* DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR - do */
-struct devlink_health_reporter_dump_clear_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 health_reporter_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	char *health_reporter_name;
-};
-
-static inline struct devlink_health_reporter_dump_clear_req *
-devlink_health_reporter_dump_clear_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_health_reporter_dump_clear_req));
-}
-void
-devlink_health_reporter_dump_clear_req_free(struct devlink_health_reporter_dump_clear_req *req);
-
-static inline void
-devlink_health_reporter_dump_clear_req_set_bus_name(struct devlink_health_reporter_dump_clear_req *req,
-						    const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_health_reporter_dump_clear_req_set_dev_name(struct devlink_health_reporter_dump_clear_req *req,
-						    const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_health_reporter_dump_clear_req_set_port_index(struct devlink_health_reporter_dump_clear_req *req,
-						      __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-static inline void
-devlink_health_reporter_dump_clear_req_set_health_reporter_name(struct devlink_health_reporter_dump_clear_req *req,
-								const char *health_reporter_name)
-{
-	free(req->health_reporter_name);
-	req->_present.health_reporter_name_len = strlen(health_reporter_name);
-	req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1);
-	memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len);
-	req->health_reporter_name[req->_present.health_reporter_name_len] = 0;
-}
-
-/*
- * Clear dump of health reporter instances.
- */
-int devlink_health_reporter_dump_clear(struct ynl_sock *ys,
-				       struct devlink_health_reporter_dump_clear_req *req);
-
-/* ============== DEVLINK_CMD_FLASH_UPDATE ============== */
-/* DEVLINK_CMD_FLASH_UPDATE - do */
-struct devlink_flash_update_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 flash_update_file_name_len;
-		__u32 flash_update_component_len;
-		__u32 flash_update_overwrite_mask:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	char *flash_update_file_name;
-	char *flash_update_component;
-	struct nla_bitfield32 flash_update_overwrite_mask;
-};
-
-static inline struct devlink_flash_update_req *
-devlink_flash_update_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_flash_update_req));
-}
-void devlink_flash_update_req_free(struct devlink_flash_update_req *req);
-
-static inline void
-devlink_flash_update_req_set_bus_name(struct devlink_flash_update_req *req,
-				      const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_flash_update_req_set_dev_name(struct devlink_flash_update_req *req,
-				      const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_flash_update_req_set_flash_update_file_name(struct devlink_flash_update_req *req,
-						    const char *flash_update_file_name)
-{
-	free(req->flash_update_file_name);
-	req->_present.flash_update_file_name_len = strlen(flash_update_file_name);
-	req->flash_update_file_name = malloc(req->_present.flash_update_file_name_len + 1);
-	memcpy(req->flash_update_file_name, flash_update_file_name, req->_present.flash_update_file_name_len);
-	req->flash_update_file_name[req->_present.flash_update_file_name_len] = 0;
-}
-static inline void
-devlink_flash_update_req_set_flash_update_component(struct devlink_flash_update_req *req,
-						    const char *flash_update_component)
-{
-	free(req->flash_update_component);
-	req->_present.flash_update_component_len = strlen(flash_update_component);
-	req->flash_update_component = malloc(req->_present.flash_update_component_len + 1);
-	memcpy(req->flash_update_component, flash_update_component, req->_present.flash_update_component_len);
-	req->flash_update_component[req->_present.flash_update_component_len] = 0;
-}
-static inline void
-devlink_flash_update_req_set_flash_update_overwrite_mask(struct devlink_flash_update_req *req,
-							 struct nla_bitfield32 *flash_update_overwrite_mask)
-{
-	req->_present.flash_update_overwrite_mask = 1;
-	memcpy(&req->flash_update_overwrite_mask, flash_update_overwrite_mask, sizeof(struct nla_bitfield32));
-}
-
-/*
- * Flash update devlink instances.
- */
-int devlink_flash_update(struct ynl_sock *ys,
-			 struct devlink_flash_update_req *req);
-
-/* ============== DEVLINK_CMD_TRAP_GET ============== */
-/* DEVLINK_CMD_TRAP_GET - do */
-struct devlink_trap_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 trap_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	char *trap_name;
-};
-
-static inline struct devlink_trap_get_req *devlink_trap_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_trap_get_req));
-}
-void devlink_trap_get_req_free(struct devlink_trap_get_req *req);
-
-static inline void
-devlink_trap_get_req_set_bus_name(struct devlink_trap_get_req *req,
-				  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_trap_get_req_set_dev_name(struct devlink_trap_get_req *req,
-				  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_trap_get_req_set_trap_name(struct devlink_trap_get_req *req,
-				   const char *trap_name)
-{
-	free(req->trap_name);
-	req->_present.trap_name_len = strlen(trap_name);
-	req->trap_name = malloc(req->_present.trap_name_len + 1);
-	memcpy(req->trap_name, trap_name, req->_present.trap_name_len);
-	req->trap_name[req->_present.trap_name_len] = 0;
-}
-
-struct devlink_trap_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 trap_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	char *trap_name;
-};
-
-void devlink_trap_get_rsp_free(struct devlink_trap_get_rsp *rsp);
-
-/*
- * Get trap instances.
- */
-struct devlink_trap_get_rsp *
-devlink_trap_get(struct ynl_sock *ys, struct devlink_trap_get_req *req);
-
-/* DEVLINK_CMD_TRAP_GET - dump */
-struct devlink_trap_get_req_dump {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-};
-
-static inline struct devlink_trap_get_req_dump *
-devlink_trap_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_trap_get_req_dump));
-}
-void devlink_trap_get_req_dump_free(struct devlink_trap_get_req_dump *req);
-
-static inline void
-devlink_trap_get_req_dump_set_bus_name(struct devlink_trap_get_req_dump *req,
-				       const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_trap_get_req_dump_set_dev_name(struct devlink_trap_get_req_dump *req,
-				       const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-
-struct devlink_trap_get_list {
-	struct devlink_trap_get_list *next;
-	struct devlink_trap_get_rsp obj __attribute__((aligned(8)));
-};
-
-void devlink_trap_get_list_free(struct devlink_trap_get_list *rsp);
-
-struct devlink_trap_get_list *
-devlink_trap_get_dump(struct ynl_sock *ys,
-		      struct devlink_trap_get_req_dump *req);
-
-/* ============== DEVLINK_CMD_TRAP_SET ============== */
-/* DEVLINK_CMD_TRAP_SET - do */
-struct devlink_trap_set_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 trap_name_len;
-		__u32 trap_action:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	char *trap_name;
-	enum devlink_trap_action trap_action;
-};
-
-static inline struct devlink_trap_set_req *devlink_trap_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_trap_set_req));
-}
-void devlink_trap_set_req_free(struct devlink_trap_set_req *req);
-
-static inline void
-devlink_trap_set_req_set_bus_name(struct devlink_trap_set_req *req,
-				  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_trap_set_req_set_dev_name(struct devlink_trap_set_req *req,
-				  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_trap_set_req_set_trap_name(struct devlink_trap_set_req *req,
-				   const char *trap_name)
-{
-	free(req->trap_name);
-	req->_present.trap_name_len = strlen(trap_name);
-	req->trap_name = malloc(req->_present.trap_name_len + 1);
-	memcpy(req->trap_name, trap_name, req->_present.trap_name_len);
-	req->trap_name[req->_present.trap_name_len] = 0;
-}
-static inline void
-devlink_trap_set_req_set_trap_action(struct devlink_trap_set_req *req,
-				     enum devlink_trap_action trap_action)
-{
-	req->_present.trap_action = 1;
-	req->trap_action = trap_action;
-}
-
-/*
- * Set trap instances.
- */
-int devlink_trap_set(struct ynl_sock *ys, struct devlink_trap_set_req *req);
-
-/* ============== DEVLINK_CMD_TRAP_GROUP_GET ============== */
-/* DEVLINK_CMD_TRAP_GROUP_GET - do */
-struct devlink_trap_group_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 trap_group_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	char *trap_group_name;
-};
-
-static inline struct devlink_trap_group_get_req *
-devlink_trap_group_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_trap_group_get_req));
-}
-void devlink_trap_group_get_req_free(struct devlink_trap_group_get_req *req);
-
-static inline void
-devlink_trap_group_get_req_set_bus_name(struct devlink_trap_group_get_req *req,
-					const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_trap_group_get_req_set_dev_name(struct devlink_trap_group_get_req *req,
-					const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_trap_group_get_req_set_trap_group_name(struct devlink_trap_group_get_req *req,
-					       const char *trap_group_name)
-{
-	free(req->trap_group_name);
-	req->_present.trap_group_name_len = strlen(trap_group_name);
-	req->trap_group_name = malloc(req->_present.trap_group_name_len + 1);
-	memcpy(req->trap_group_name, trap_group_name, req->_present.trap_group_name_len);
-	req->trap_group_name[req->_present.trap_group_name_len] = 0;
-}
-
-struct devlink_trap_group_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 trap_group_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	char *trap_group_name;
-};
-
-void devlink_trap_group_get_rsp_free(struct devlink_trap_group_get_rsp *rsp);
-
-/*
- * Get trap group instances.
- */
-struct devlink_trap_group_get_rsp *
-devlink_trap_group_get(struct ynl_sock *ys,
-		       struct devlink_trap_group_get_req *req);
-
-/* DEVLINK_CMD_TRAP_GROUP_GET - dump */
-struct devlink_trap_group_get_req_dump {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-};
-
-static inline struct devlink_trap_group_get_req_dump *
-devlink_trap_group_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_trap_group_get_req_dump));
-}
-void
-devlink_trap_group_get_req_dump_free(struct devlink_trap_group_get_req_dump *req);
-
-static inline void
-devlink_trap_group_get_req_dump_set_bus_name(struct devlink_trap_group_get_req_dump *req,
-					     const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_trap_group_get_req_dump_set_dev_name(struct devlink_trap_group_get_req_dump *req,
-					     const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-
-struct devlink_trap_group_get_list {
-	struct devlink_trap_group_get_list *next;
-	struct devlink_trap_group_get_rsp obj __attribute__((aligned(8)));
-};
-
-void devlink_trap_group_get_list_free(struct devlink_trap_group_get_list *rsp);
-
-struct devlink_trap_group_get_list *
-devlink_trap_group_get_dump(struct ynl_sock *ys,
-			    struct devlink_trap_group_get_req_dump *req);
-
-/* ============== DEVLINK_CMD_TRAP_GROUP_SET ============== */
-/* DEVLINK_CMD_TRAP_GROUP_SET - do */
-struct devlink_trap_group_set_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 trap_group_name_len;
-		__u32 trap_action:1;
-		__u32 trap_policer_id:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	char *trap_group_name;
-	enum devlink_trap_action trap_action;
-	__u32 trap_policer_id;
-};
-
-static inline struct devlink_trap_group_set_req *
-devlink_trap_group_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_trap_group_set_req));
-}
-void devlink_trap_group_set_req_free(struct devlink_trap_group_set_req *req);
-
-static inline void
-devlink_trap_group_set_req_set_bus_name(struct devlink_trap_group_set_req *req,
-					const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_trap_group_set_req_set_dev_name(struct devlink_trap_group_set_req *req,
-					const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_trap_group_set_req_set_trap_group_name(struct devlink_trap_group_set_req *req,
-					       const char *trap_group_name)
-{
-	free(req->trap_group_name);
-	req->_present.trap_group_name_len = strlen(trap_group_name);
-	req->trap_group_name = malloc(req->_present.trap_group_name_len + 1);
-	memcpy(req->trap_group_name, trap_group_name, req->_present.trap_group_name_len);
-	req->trap_group_name[req->_present.trap_group_name_len] = 0;
-}
-static inline void
-devlink_trap_group_set_req_set_trap_action(struct devlink_trap_group_set_req *req,
-					   enum devlink_trap_action trap_action)
-{
-	req->_present.trap_action = 1;
-	req->trap_action = trap_action;
-}
-static inline void
-devlink_trap_group_set_req_set_trap_policer_id(struct devlink_trap_group_set_req *req,
-					       __u32 trap_policer_id)
-{
-	req->_present.trap_policer_id = 1;
-	req->trap_policer_id = trap_policer_id;
-}
-
-/*
- * Set trap group instances.
- */
-int devlink_trap_group_set(struct ynl_sock *ys,
-			   struct devlink_trap_group_set_req *req);
-
-/* ============== DEVLINK_CMD_TRAP_POLICER_GET ============== */
-/* DEVLINK_CMD_TRAP_POLICER_GET - do */
-struct devlink_trap_policer_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 trap_policer_id:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 trap_policer_id;
-};
-
-static inline struct devlink_trap_policer_get_req *
-devlink_trap_policer_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_trap_policer_get_req));
-}
-void
-devlink_trap_policer_get_req_free(struct devlink_trap_policer_get_req *req);
-
-static inline void
-devlink_trap_policer_get_req_set_bus_name(struct devlink_trap_policer_get_req *req,
-					  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_trap_policer_get_req_set_dev_name(struct devlink_trap_policer_get_req *req,
-					  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_trap_policer_get_req_set_trap_policer_id(struct devlink_trap_policer_get_req *req,
-						 __u32 trap_policer_id)
-{
-	req->_present.trap_policer_id = 1;
-	req->trap_policer_id = trap_policer_id;
-}
-
-struct devlink_trap_policer_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 trap_policer_id:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 trap_policer_id;
-};
-
-void
-devlink_trap_policer_get_rsp_free(struct devlink_trap_policer_get_rsp *rsp);
-
-/*
- * Get trap policer instances.
- */
-struct devlink_trap_policer_get_rsp *
-devlink_trap_policer_get(struct ynl_sock *ys,
-			 struct devlink_trap_policer_get_req *req);
-
-/* DEVLINK_CMD_TRAP_POLICER_GET - dump */
-struct devlink_trap_policer_get_req_dump {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-};
-
-static inline struct devlink_trap_policer_get_req_dump *
-devlink_trap_policer_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_trap_policer_get_req_dump));
-}
-void
-devlink_trap_policer_get_req_dump_free(struct devlink_trap_policer_get_req_dump *req);
-
-static inline void
-devlink_trap_policer_get_req_dump_set_bus_name(struct devlink_trap_policer_get_req_dump *req,
-					       const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_trap_policer_get_req_dump_set_dev_name(struct devlink_trap_policer_get_req_dump *req,
-					       const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-
-struct devlink_trap_policer_get_list {
-	struct devlink_trap_policer_get_list *next;
-	struct devlink_trap_policer_get_rsp obj __attribute__((aligned(8)));
-};
-
-void
-devlink_trap_policer_get_list_free(struct devlink_trap_policer_get_list *rsp);
-
-struct devlink_trap_policer_get_list *
-devlink_trap_policer_get_dump(struct ynl_sock *ys,
-			      struct devlink_trap_policer_get_req_dump *req);
-
-/* ============== DEVLINK_CMD_TRAP_POLICER_SET ============== */
-/* DEVLINK_CMD_TRAP_POLICER_SET - do */
-struct devlink_trap_policer_set_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 trap_policer_id:1;
-		__u32 trap_policer_rate:1;
-		__u32 trap_policer_burst:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 trap_policer_id;
-	__u64 trap_policer_rate;
-	__u64 trap_policer_burst;
-};
-
-static inline struct devlink_trap_policer_set_req *
-devlink_trap_policer_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_trap_policer_set_req));
-}
-void
-devlink_trap_policer_set_req_free(struct devlink_trap_policer_set_req *req);
-
-static inline void
-devlink_trap_policer_set_req_set_bus_name(struct devlink_trap_policer_set_req *req,
-					  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_trap_policer_set_req_set_dev_name(struct devlink_trap_policer_set_req *req,
-					  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_trap_policer_set_req_set_trap_policer_id(struct devlink_trap_policer_set_req *req,
-						 __u32 trap_policer_id)
-{
-	req->_present.trap_policer_id = 1;
-	req->trap_policer_id = trap_policer_id;
-}
-static inline void
-devlink_trap_policer_set_req_set_trap_policer_rate(struct devlink_trap_policer_set_req *req,
-						   __u64 trap_policer_rate)
-{
-	req->_present.trap_policer_rate = 1;
-	req->trap_policer_rate = trap_policer_rate;
-}
-static inline void
-devlink_trap_policer_set_req_set_trap_policer_burst(struct devlink_trap_policer_set_req *req,
-						    __u64 trap_policer_burst)
-{
-	req->_present.trap_policer_burst = 1;
-	req->trap_policer_burst = trap_policer_burst;
-}
-
-/*
- * Get trap policer instances.
- */
-int devlink_trap_policer_set(struct ynl_sock *ys,
-			     struct devlink_trap_policer_set_req *req);
-
-/* ============== DEVLINK_CMD_HEALTH_REPORTER_TEST ============== */
-/* DEVLINK_CMD_HEALTH_REPORTER_TEST - do */
-struct devlink_health_reporter_test_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 health_reporter_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	char *health_reporter_name;
-};
-
-static inline struct devlink_health_reporter_test_req *
-devlink_health_reporter_test_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_health_reporter_test_req));
-}
-void
-devlink_health_reporter_test_req_free(struct devlink_health_reporter_test_req *req);
-
-static inline void
-devlink_health_reporter_test_req_set_bus_name(struct devlink_health_reporter_test_req *req,
-					      const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_health_reporter_test_req_set_dev_name(struct devlink_health_reporter_test_req *req,
-					      const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_health_reporter_test_req_set_port_index(struct devlink_health_reporter_test_req *req,
-						__u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-static inline void
-devlink_health_reporter_test_req_set_health_reporter_name(struct devlink_health_reporter_test_req *req,
-							  const char *health_reporter_name)
-{
-	free(req->health_reporter_name);
-	req->_present.health_reporter_name_len = strlen(health_reporter_name);
-	req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1);
-	memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len);
-	req->health_reporter_name[req->_present.health_reporter_name_len] = 0;
-}
-
-/*
- * Test health reporter instances.
- */
-int devlink_health_reporter_test(struct ynl_sock *ys,
-				 struct devlink_health_reporter_test_req *req);
-
-/* ============== DEVLINK_CMD_RATE_GET ============== */
-/* DEVLINK_CMD_RATE_GET - do */
-struct devlink_rate_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 rate_node_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	char *rate_node_name;
-};
-
-static inline struct devlink_rate_get_req *devlink_rate_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_rate_get_req));
-}
-void devlink_rate_get_req_free(struct devlink_rate_get_req *req);
-
-static inline void
-devlink_rate_get_req_set_bus_name(struct devlink_rate_get_req *req,
-				  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_rate_get_req_set_dev_name(struct devlink_rate_get_req *req,
-				  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_rate_get_req_set_port_index(struct devlink_rate_get_req *req,
-				    __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-static inline void
-devlink_rate_get_req_set_rate_node_name(struct devlink_rate_get_req *req,
-					const char *rate_node_name)
-{
-	free(req->rate_node_name);
-	req->_present.rate_node_name_len = strlen(rate_node_name);
-	req->rate_node_name = malloc(req->_present.rate_node_name_len + 1);
-	memcpy(req->rate_node_name, rate_node_name, req->_present.rate_node_name_len);
-	req->rate_node_name[req->_present.rate_node_name_len] = 0;
-}
-
-struct devlink_rate_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 rate_node_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	char *rate_node_name;
-};
-
-void devlink_rate_get_rsp_free(struct devlink_rate_get_rsp *rsp);
-
-/*
- * Get rate instances.
- */
-struct devlink_rate_get_rsp *
-devlink_rate_get(struct ynl_sock *ys, struct devlink_rate_get_req *req);
-
-/* DEVLINK_CMD_RATE_GET - dump */
-struct devlink_rate_get_req_dump {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-};
-
-static inline struct devlink_rate_get_req_dump *
-devlink_rate_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_rate_get_req_dump));
-}
-void devlink_rate_get_req_dump_free(struct devlink_rate_get_req_dump *req);
-
-static inline void
-devlink_rate_get_req_dump_set_bus_name(struct devlink_rate_get_req_dump *req,
-				       const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_rate_get_req_dump_set_dev_name(struct devlink_rate_get_req_dump *req,
-				       const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-
-struct devlink_rate_get_list {
-	struct devlink_rate_get_list *next;
-	struct devlink_rate_get_rsp obj __attribute__((aligned(8)));
-};
-
-void devlink_rate_get_list_free(struct devlink_rate_get_list *rsp);
-
-struct devlink_rate_get_list *
-devlink_rate_get_dump(struct ynl_sock *ys,
-		      struct devlink_rate_get_req_dump *req);
-
-/* ============== DEVLINK_CMD_RATE_SET ============== */
-/* DEVLINK_CMD_RATE_SET - do */
-struct devlink_rate_set_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 rate_node_name_len;
-		__u32 rate_tx_share:1;
-		__u32 rate_tx_max:1;
-		__u32 rate_tx_priority:1;
-		__u32 rate_tx_weight:1;
-		__u32 rate_parent_node_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	char *rate_node_name;
-	__u64 rate_tx_share;
-	__u64 rate_tx_max;
-	__u32 rate_tx_priority;
-	__u32 rate_tx_weight;
-	char *rate_parent_node_name;
-};
-
-static inline struct devlink_rate_set_req *devlink_rate_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_rate_set_req));
-}
-void devlink_rate_set_req_free(struct devlink_rate_set_req *req);
-
-static inline void
-devlink_rate_set_req_set_bus_name(struct devlink_rate_set_req *req,
-				  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_rate_set_req_set_dev_name(struct devlink_rate_set_req *req,
-				  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_rate_set_req_set_rate_node_name(struct devlink_rate_set_req *req,
-					const char *rate_node_name)
-{
-	free(req->rate_node_name);
-	req->_present.rate_node_name_len = strlen(rate_node_name);
-	req->rate_node_name = malloc(req->_present.rate_node_name_len + 1);
-	memcpy(req->rate_node_name, rate_node_name, req->_present.rate_node_name_len);
-	req->rate_node_name[req->_present.rate_node_name_len] = 0;
-}
-static inline void
-devlink_rate_set_req_set_rate_tx_share(struct devlink_rate_set_req *req,
-				       __u64 rate_tx_share)
-{
-	req->_present.rate_tx_share = 1;
-	req->rate_tx_share = rate_tx_share;
-}
-static inline void
-devlink_rate_set_req_set_rate_tx_max(struct devlink_rate_set_req *req,
-				     __u64 rate_tx_max)
-{
-	req->_present.rate_tx_max = 1;
-	req->rate_tx_max = rate_tx_max;
-}
-static inline void
-devlink_rate_set_req_set_rate_tx_priority(struct devlink_rate_set_req *req,
-					  __u32 rate_tx_priority)
-{
-	req->_present.rate_tx_priority = 1;
-	req->rate_tx_priority = rate_tx_priority;
-}
-static inline void
-devlink_rate_set_req_set_rate_tx_weight(struct devlink_rate_set_req *req,
-					__u32 rate_tx_weight)
-{
-	req->_present.rate_tx_weight = 1;
-	req->rate_tx_weight = rate_tx_weight;
-}
-static inline void
-devlink_rate_set_req_set_rate_parent_node_name(struct devlink_rate_set_req *req,
-					       const char *rate_parent_node_name)
-{
-	free(req->rate_parent_node_name);
-	req->_present.rate_parent_node_name_len = strlen(rate_parent_node_name);
-	req->rate_parent_node_name = malloc(req->_present.rate_parent_node_name_len + 1);
-	memcpy(req->rate_parent_node_name, rate_parent_node_name, req->_present.rate_parent_node_name_len);
-	req->rate_parent_node_name[req->_present.rate_parent_node_name_len] = 0;
-}
-
-/*
- * Set rate instances.
- */
-int devlink_rate_set(struct ynl_sock *ys, struct devlink_rate_set_req *req);
-
-/* ============== DEVLINK_CMD_RATE_NEW ============== */
-/* DEVLINK_CMD_RATE_NEW - do */
-struct devlink_rate_new_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 rate_node_name_len;
-		__u32 rate_tx_share:1;
-		__u32 rate_tx_max:1;
-		__u32 rate_tx_priority:1;
-		__u32 rate_tx_weight:1;
-		__u32 rate_parent_node_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	char *rate_node_name;
-	__u64 rate_tx_share;
-	__u64 rate_tx_max;
-	__u32 rate_tx_priority;
-	__u32 rate_tx_weight;
-	char *rate_parent_node_name;
-};
-
-static inline struct devlink_rate_new_req *devlink_rate_new_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_rate_new_req));
-}
-void devlink_rate_new_req_free(struct devlink_rate_new_req *req);
-
-static inline void
-devlink_rate_new_req_set_bus_name(struct devlink_rate_new_req *req,
-				  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_rate_new_req_set_dev_name(struct devlink_rate_new_req *req,
-				  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_rate_new_req_set_rate_node_name(struct devlink_rate_new_req *req,
-					const char *rate_node_name)
-{
-	free(req->rate_node_name);
-	req->_present.rate_node_name_len = strlen(rate_node_name);
-	req->rate_node_name = malloc(req->_present.rate_node_name_len + 1);
-	memcpy(req->rate_node_name, rate_node_name, req->_present.rate_node_name_len);
-	req->rate_node_name[req->_present.rate_node_name_len] = 0;
-}
-static inline void
-devlink_rate_new_req_set_rate_tx_share(struct devlink_rate_new_req *req,
-				       __u64 rate_tx_share)
-{
-	req->_present.rate_tx_share = 1;
-	req->rate_tx_share = rate_tx_share;
-}
-static inline void
-devlink_rate_new_req_set_rate_tx_max(struct devlink_rate_new_req *req,
-				     __u64 rate_tx_max)
-{
-	req->_present.rate_tx_max = 1;
-	req->rate_tx_max = rate_tx_max;
-}
-static inline void
-devlink_rate_new_req_set_rate_tx_priority(struct devlink_rate_new_req *req,
-					  __u32 rate_tx_priority)
-{
-	req->_present.rate_tx_priority = 1;
-	req->rate_tx_priority = rate_tx_priority;
-}
-static inline void
-devlink_rate_new_req_set_rate_tx_weight(struct devlink_rate_new_req *req,
-					__u32 rate_tx_weight)
-{
-	req->_present.rate_tx_weight = 1;
-	req->rate_tx_weight = rate_tx_weight;
-}
-static inline void
-devlink_rate_new_req_set_rate_parent_node_name(struct devlink_rate_new_req *req,
-					       const char *rate_parent_node_name)
-{
-	free(req->rate_parent_node_name);
-	req->_present.rate_parent_node_name_len = strlen(rate_parent_node_name);
-	req->rate_parent_node_name = malloc(req->_present.rate_parent_node_name_len + 1);
-	memcpy(req->rate_parent_node_name, rate_parent_node_name, req->_present.rate_parent_node_name_len);
-	req->rate_parent_node_name[req->_present.rate_parent_node_name_len] = 0;
-}
-
-/*
- * Create rate instances.
- */
-int devlink_rate_new(struct ynl_sock *ys, struct devlink_rate_new_req *req);
-
-/* ============== DEVLINK_CMD_RATE_DEL ============== */
-/* DEVLINK_CMD_RATE_DEL - do */
-struct devlink_rate_del_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 rate_node_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	char *rate_node_name;
-};
-
-static inline struct devlink_rate_del_req *devlink_rate_del_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_rate_del_req));
-}
-void devlink_rate_del_req_free(struct devlink_rate_del_req *req);
-
-static inline void
-devlink_rate_del_req_set_bus_name(struct devlink_rate_del_req *req,
-				  const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_rate_del_req_set_dev_name(struct devlink_rate_del_req *req,
-				  const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_rate_del_req_set_rate_node_name(struct devlink_rate_del_req *req,
-					const char *rate_node_name)
-{
-	free(req->rate_node_name);
-	req->_present.rate_node_name_len = strlen(rate_node_name);
-	req->rate_node_name = malloc(req->_present.rate_node_name_len + 1);
-	memcpy(req->rate_node_name, rate_node_name, req->_present.rate_node_name_len);
-	req->rate_node_name[req->_present.rate_node_name_len] = 0;
-}
-
-/*
- * Delete rate instances.
- */
-int devlink_rate_del(struct ynl_sock *ys, struct devlink_rate_del_req *req);
-
-/* ============== DEVLINK_CMD_LINECARD_GET ============== */
-/* DEVLINK_CMD_LINECARD_GET - do */
-struct devlink_linecard_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 linecard_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 linecard_index;
-};
-
-static inline struct devlink_linecard_get_req *
-devlink_linecard_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_linecard_get_req));
-}
-void devlink_linecard_get_req_free(struct devlink_linecard_get_req *req);
-
-static inline void
-devlink_linecard_get_req_set_bus_name(struct devlink_linecard_get_req *req,
-				      const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_linecard_get_req_set_dev_name(struct devlink_linecard_get_req *req,
-				      const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_linecard_get_req_set_linecard_index(struct devlink_linecard_get_req *req,
-					    __u32 linecard_index)
-{
-	req->_present.linecard_index = 1;
-	req->linecard_index = linecard_index;
-}
-
-struct devlink_linecard_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 linecard_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 linecard_index;
-};
-
-void devlink_linecard_get_rsp_free(struct devlink_linecard_get_rsp *rsp);
-
-/*
- * Get line card instances.
- */
-struct devlink_linecard_get_rsp *
-devlink_linecard_get(struct ynl_sock *ys, struct devlink_linecard_get_req *req);
-
-/* DEVLINK_CMD_LINECARD_GET - dump */
-struct devlink_linecard_get_req_dump {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-};
-
-static inline struct devlink_linecard_get_req_dump *
-devlink_linecard_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_linecard_get_req_dump));
-}
-void
-devlink_linecard_get_req_dump_free(struct devlink_linecard_get_req_dump *req);
-
-static inline void
-devlink_linecard_get_req_dump_set_bus_name(struct devlink_linecard_get_req_dump *req,
-					   const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_linecard_get_req_dump_set_dev_name(struct devlink_linecard_get_req_dump *req,
-					   const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-
-struct devlink_linecard_get_list {
-	struct devlink_linecard_get_list *next;
-	struct devlink_linecard_get_rsp obj __attribute__((aligned(8)));
-};
-
-void devlink_linecard_get_list_free(struct devlink_linecard_get_list *rsp);
-
-struct devlink_linecard_get_list *
-devlink_linecard_get_dump(struct ynl_sock *ys,
-			  struct devlink_linecard_get_req_dump *req);
-
-/* ============== DEVLINK_CMD_LINECARD_SET ============== */
-/* DEVLINK_CMD_LINECARD_SET - do */
-struct devlink_linecard_set_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 linecard_index:1;
-		__u32 linecard_type_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 linecard_index;
-	char *linecard_type;
-};
-
-static inline struct devlink_linecard_set_req *
-devlink_linecard_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_linecard_set_req));
-}
-void devlink_linecard_set_req_free(struct devlink_linecard_set_req *req);
-
-static inline void
-devlink_linecard_set_req_set_bus_name(struct devlink_linecard_set_req *req,
-				      const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_linecard_set_req_set_dev_name(struct devlink_linecard_set_req *req,
-				      const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_linecard_set_req_set_linecard_index(struct devlink_linecard_set_req *req,
-					    __u32 linecard_index)
-{
-	req->_present.linecard_index = 1;
-	req->linecard_index = linecard_index;
-}
-static inline void
-devlink_linecard_set_req_set_linecard_type(struct devlink_linecard_set_req *req,
-					   const char *linecard_type)
-{
-	free(req->linecard_type);
-	req->_present.linecard_type_len = strlen(linecard_type);
-	req->linecard_type = malloc(req->_present.linecard_type_len + 1);
-	memcpy(req->linecard_type, linecard_type, req->_present.linecard_type_len);
-	req->linecard_type[req->_present.linecard_type_len] = 0;
-}
-
-/*
- * Set line card instances.
- */
-int devlink_linecard_set(struct ynl_sock *ys,
-			 struct devlink_linecard_set_req *req);
-
-/* ============== DEVLINK_CMD_SELFTESTS_GET ============== */
-/* DEVLINK_CMD_SELFTESTS_GET - do */
-struct devlink_selftests_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-};
-
-static inline struct devlink_selftests_get_req *
-devlink_selftests_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_selftests_get_req));
-}
-void devlink_selftests_get_req_free(struct devlink_selftests_get_req *req);
-
-static inline void
-devlink_selftests_get_req_set_bus_name(struct devlink_selftests_get_req *req,
-				       const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_selftests_get_req_set_dev_name(struct devlink_selftests_get_req *req,
-				       const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-
-struct devlink_selftests_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-};
-
-void devlink_selftests_get_rsp_free(struct devlink_selftests_get_rsp *rsp);
-
-/*
- * Get device selftest instances.
- */
-struct devlink_selftests_get_rsp *
-devlink_selftests_get(struct ynl_sock *ys,
-		      struct devlink_selftests_get_req *req);
-
-/* DEVLINK_CMD_SELFTESTS_GET - dump */
-struct devlink_selftests_get_list {
-	struct devlink_selftests_get_list *next;
-	struct devlink_selftests_get_rsp obj __attribute__((aligned(8)));
-};
-
-void devlink_selftests_get_list_free(struct devlink_selftests_get_list *rsp);
-
-struct devlink_selftests_get_list *
-devlink_selftests_get_dump(struct ynl_sock *ys);
-
-/* ============== DEVLINK_CMD_SELFTESTS_RUN ============== */
-/* DEVLINK_CMD_SELFTESTS_RUN - do */
-struct devlink_selftests_run_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 selftests:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	struct devlink_dl_selftest_id selftests;
-};
-
-static inline struct devlink_selftests_run_req *
-devlink_selftests_run_req_alloc(void)
-{
-	return calloc(1, sizeof(struct devlink_selftests_run_req));
-}
-void devlink_selftests_run_req_free(struct devlink_selftests_run_req *req);
-
-static inline void
-devlink_selftests_run_req_set_bus_name(struct devlink_selftests_run_req *req,
-				       const char *bus_name)
-{
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
-}
-static inline void
-devlink_selftests_run_req_set_dev_name(struct devlink_selftests_run_req *req,
-				       const char *dev_name)
-{
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
-}
-static inline void
-devlink_selftests_run_req_set_selftests_flash(struct devlink_selftests_run_req *req)
-{
-	req->_present.selftests = 1;
-	req->selftests._present.flash = 1;
-}
-
-/*
- * Run device selftest instances.
- */
-int devlink_selftests_run(struct ynl_sock *ys,
-			  struct devlink_selftests_run_req *req);
-
-#endif /* _LINUX_DEVLINK_GEN_H */
diff --git a/tools/net/ynl/generated/ethtool-user.c b/tools/net/ynl/generated/ethtool-user.c
deleted file mode 100644
index 74b883a14958..000000000000
--- a/tools/net/ynl/generated/ethtool-user.c
+++ /dev/null
@@ -1,6353 +0,0 @@
-// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
-/* Do not edit directly, auto-generated from: */
-/*	Documentation/netlink/specs/ethtool.yaml */
-/* YNL-GEN user source */
-/* YNL-ARG --user-header linux/ethtool_netlink.h --exclude-op stats-get */
-
-#include <stdlib.h>
-#include <string.h>
-#include "ethtool-user.h"
-#include "ynl.h"
-#include <linux/ethtool.h>
-
-#include <libmnl/libmnl.h>
-#include <linux/genetlink.h>
-
-#include "linux/ethtool_netlink.h"
-
-/* Enums */
-static const char * const ethtool_op_strmap[] = {
-	[ETHTOOL_MSG_STRSET_GET] = "strset-get",
-	[ETHTOOL_MSG_LINKINFO_GET] = "linkinfo-get",
-	[3] = "linkinfo-ntf",
-	[ETHTOOL_MSG_LINKMODES_GET] = "linkmodes-get",
-	[5] = "linkmodes-ntf",
-	[ETHTOOL_MSG_LINKSTATE_GET] = "linkstate-get",
-	[ETHTOOL_MSG_DEBUG_GET] = "debug-get",
-	[8] = "debug-ntf",
-	[ETHTOOL_MSG_WOL_GET] = "wol-get",
-	[10] = "wol-ntf",
-	[ETHTOOL_MSG_FEATURES_GET] = "features-get",
-	[ETHTOOL_MSG_FEATURES_SET] = "features-set",
-	[13] = "features-ntf",
-	[14] = "privflags-get",
-	[15] = "privflags-ntf",
-	[16] = "rings-get",
-	[17] = "rings-ntf",
-	[18] = "channels-get",
-	[19] = "channels-ntf",
-	[20] = "coalesce-get",
-	[21] = "coalesce-ntf",
-	[22] = "pause-get",
-	[23] = "pause-ntf",
-	[24] = "eee-get",
-	[25] = "eee-ntf",
-	[26] = "tsinfo-get",
-	[27] = "cable-test-ntf",
-	[28] = "cable-test-tdr-ntf",
-	[29] = "tunnel-info-get",
-	[30] = "fec-get",
-	[31] = "fec-ntf",
-	[32] = "module-eeprom-get",
-	[34] = "phc-vclocks-get",
-	[35] = "module-get",
-	[36] = "module-ntf",
-	[37] = "pse-get",
-	[ETHTOOL_MSG_RSS_GET] = "rss-get",
-	[ETHTOOL_MSG_PLCA_GET_CFG] = "plca-get-cfg",
-	[40] = "plca-get-status",
-	[41] = "plca-ntf",
-	[ETHTOOL_MSG_MM_GET] = "mm-get",
-	[43] = "mm-ntf",
-};
-
-const char *ethtool_op_str(int op)
-{
-	if (op < 0 || op >= (int)MNL_ARRAY_SIZE(ethtool_op_strmap))
-		return NULL;
-	return ethtool_op_strmap[op];
-}
-
-static const char * const ethtool_udp_tunnel_type_strmap[] = {
-	[0] = "vxlan",
-	[1] = "geneve",
-	[2] = "vxlan-gpe",
-};
-
-const char *ethtool_udp_tunnel_type_str(int value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(ethtool_udp_tunnel_type_strmap))
-		return NULL;
-	return ethtool_udp_tunnel_type_strmap[value];
-}
-
-static const char * const ethtool_stringset_strmap[] = {
-};
-
-const char *ethtool_stringset_str(enum ethtool_stringset value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(ethtool_stringset_strmap))
-		return NULL;
-	return ethtool_stringset_strmap[value];
-}
-
-/* Policies */
-struct ynl_policy_attr ethtool_header_policy[ETHTOOL_A_HEADER_MAX + 1] = {
-	[ETHTOOL_A_HEADER_DEV_INDEX] = { .name = "dev-index", .type = YNL_PT_U32, },
-	[ETHTOOL_A_HEADER_DEV_NAME] = { .name = "dev-name", .type = YNL_PT_NUL_STR, },
-	[ETHTOOL_A_HEADER_FLAGS] = { .name = "flags", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest ethtool_header_nest = {
-	.max_attr = ETHTOOL_A_HEADER_MAX,
-	.table = ethtool_header_policy,
-};
-
-struct ynl_policy_attr ethtool_pause_stat_policy[ETHTOOL_A_PAUSE_STAT_MAX + 1] = {
-	[ETHTOOL_A_PAUSE_STAT_PAD] = { .name = "pad", .type = YNL_PT_IGNORE, },
-	[ETHTOOL_A_PAUSE_STAT_TX_FRAMES] = { .name = "tx-frames", .type = YNL_PT_U64, },
-	[ETHTOOL_A_PAUSE_STAT_RX_FRAMES] = { .name = "rx-frames", .type = YNL_PT_U64, },
-};
-
-struct ynl_policy_nest ethtool_pause_stat_nest = {
-	.max_attr = ETHTOOL_A_PAUSE_STAT_MAX,
-	.table = ethtool_pause_stat_policy,
-};
-
-struct ynl_policy_attr ethtool_cable_test_tdr_cfg_policy[ETHTOOL_A_CABLE_TEST_TDR_CFG_MAX + 1] = {
-	[ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST] = { .name = "first", .type = YNL_PT_U32, },
-	[ETHTOOL_A_CABLE_TEST_TDR_CFG_LAST] = { .name = "last", .type = YNL_PT_U32, },
-	[ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP] = { .name = "step", .type = YNL_PT_U32, },
-	[ETHTOOL_A_CABLE_TEST_TDR_CFG_PAIR] = { .name = "pair", .type = YNL_PT_U8, },
-};
-
-struct ynl_policy_nest ethtool_cable_test_tdr_cfg_nest = {
-	.max_attr = ETHTOOL_A_CABLE_TEST_TDR_CFG_MAX,
-	.table = ethtool_cable_test_tdr_cfg_policy,
-};
-
-struct ynl_policy_attr ethtool_fec_stat_policy[ETHTOOL_A_FEC_STAT_MAX + 1] = {
-	[ETHTOOL_A_FEC_STAT_PAD] = { .name = "pad", .type = YNL_PT_IGNORE, },
-	[ETHTOOL_A_FEC_STAT_CORRECTED] = { .name = "corrected", .type = YNL_PT_BINARY,},
-	[ETHTOOL_A_FEC_STAT_UNCORR] = { .name = "uncorr", .type = YNL_PT_BINARY,},
-	[ETHTOOL_A_FEC_STAT_CORR_BITS] = { .name = "corr-bits", .type = YNL_PT_BINARY,},
-};
-
-struct ynl_policy_nest ethtool_fec_stat_nest = {
-	.max_attr = ETHTOOL_A_FEC_STAT_MAX,
-	.table = ethtool_fec_stat_policy,
-};
-
-struct ynl_policy_attr ethtool_mm_stat_policy[ETHTOOL_A_MM_STAT_MAX + 1] = {
-	[ETHTOOL_A_MM_STAT_PAD] = { .name = "pad", .type = YNL_PT_IGNORE, },
-	[ETHTOOL_A_MM_STAT_REASSEMBLY_ERRORS] = { .name = "reassembly-errors", .type = YNL_PT_U64, },
-	[ETHTOOL_A_MM_STAT_SMD_ERRORS] = { .name = "smd-errors", .type = YNL_PT_U64, },
-	[ETHTOOL_A_MM_STAT_REASSEMBLY_OK] = { .name = "reassembly-ok", .type = YNL_PT_U64, },
-	[ETHTOOL_A_MM_STAT_RX_FRAG_COUNT] = { .name = "rx-frag-count", .type = YNL_PT_U64, },
-	[ETHTOOL_A_MM_STAT_TX_FRAG_COUNT] = { .name = "tx-frag-count", .type = YNL_PT_U64, },
-	[ETHTOOL_A_MM_STAT_HOLD_COUNT] = { .name = "hold-count", .type = YNL_PT_U64, },
-};
-
-struct ynl_policy_nest ethtool_mm_stat_nest = {
-	.max_attr = ETHTOOL_A_MM_STAT_MAX,
-	.table = ethtool_mm_stat_policy,
-};
-
-struct ynl_policy_attr ethtool_cable_result_policy[ETHTOOL_A_CABLE_RESULT_MAX + 1] = {
-	[ETHTOOL_A_CABLE_RESULT_PAIR] = { .name = "pair", .type = YNL_PT_U8, },
-	[ETHTOOL_A_CABLE_RESULT_CODE] = { .name = "code", .type = YNL_PT_U8, },
-};
-
-struct ynl_policy_nest ethtool_cable_result_nest = {
-	.max_attr = ETHTOOL_A_CABLE_RESULT_MAX,
-	.table = ethtool_cable_result_policy,
-};
-
-struct ynl_policy_attr ethtool_cable_fault_length_policy[ETHTOOL_A_CABLE_FAULT_LENGTH_MAX + 1] = {
-	[ETHTOOL_A_CABLE_FAULT_LENGTH_PAIR] = { .name = "pair", .type = YNL_PT_U8, },
-	[ETHTOOL_A_CABLE_FAULT_LENGTH_CM] = { .name = "cm", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest ethtool_cable_fault_length_nest = {
-	.max_attr = ETHTOOL_A_CABLE_FAULT_LENGTH_MAX,
-	.table = ethtool_cable_fault_length_policy,
-};
-
-struct ynl_policy_attr ethtool_bitset_bit_policy[ETHTOOL_A_BITSET_BIT_MAX + 1] = {
-	[ETHTOOL_A_BITSET_BIT_INDEX] = { .name = "index", .type = YNL_PT_U32, },
-	[ETHTOOL_A_BITSET_BIT_NAME] = { .name = "name", .type = YNL_PT_NUL_STR, },
-	[ETHTOOL_A_BITSET_BIT_VALUE] = { .name = "value", .type = YNL_PT_FLAG, },
-};
-
-struct ynl_policy_nest ethtool_bitset_bit_nest = {
-	.max_attr = ETHTOOL_A_BITSET_BIT_MAX,
-	.table = ethtool_bitset_bit_policy,
-};
-
-struct ynl_policy_attr ethtool_tunnel_udp_entry_policy[ETHTOOL_A_TUNNEL_UDP_ENTRY_MAX + 1] = {
-	[ETHTOOL_A_TUNNEL_UDP_ENTRY_PORT] = { .name = "port", .type = YNL_PT_U16, },
-	[ETHTOOL_A_TUNNEL_UDP_ENTRY_TYPE] = { .name = "type", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest ethtool_tunnel_udp_entry_nest = {
-	.max_attr = ETHTOOL_A_TUNNEL_UDP_ENTRY_MAX,
-	.table = ethtool_tunnel_udp_entry_policy,
-};
-
-struct ynl_policy_attr ethtool_string_policy[ETHTOOL_A_STRING_MAX + 1] = {
-	[ETHTOOL_A_STRING_INDEX] = { .name = "index", .type = YNL_PT_U32, },
-	[ETHTOOL_A_STRING_VALUE] = { .name = "value", .type = YNL_PT_NUL_STR, },
-};
-
-struct ynl_policy_nest ethtool_string_nest = {
-	.max_attr = ETHTOOL_A_STRING_MAX,
-	.table = ethtool_string_policy,
-};
-
-struct ynl_policy_attr ethtool_cable_nest_policy[ETHTOOL_A_CABLE_NEST_MAX + 1] = {
-	[ETHTOOL_A_CABLE_NEST_RESULT] = { .name = "result", .type = YNL_PT_NEST, .nest = &ethtool_cable_result_nest, },
-	[ETHTOOL_A_CABLE_NEST_FAULT_LENGTH] = { .name = "fault-length", .type = YNL_PT_NEST, .nest = &ethtool_cable_fault_length_nest, },
-};
-
-struct ynl_policy_nest ethtool_cable_nest_nest = {
-	.max_attr = ETHTOOL_A_CABLE_NEST_MAX,
-	.table = ethtool_cable_nest_policy,
-};
-
-struct ynl_policy_attr ethtool_bitset_bits_policy[ETHTOOL_A_BITSET_BITS_MAX + 1] = {
-	[ETHTOOL_A_BITSET_BITS_BIT] = { .name = "bit", .type = YNL_PT_NEST, .nest = &ethtool_bitset_bit_nest, },
-};
-
-struct ynl_policy_nest ethtool_bitset_bits_nest = {
-	.max_attr = ETHTOOL_A_BITSET_BITS_MAX,
-	.table = ethtool_bitset_bits_policy,
-};
-
-struct ynl_policy_attr ethtool_strings_policy[ETHTOOL_A_STRINGS_MAX + 1] = {
-	[ETHTOOL_A_STRINGS_STRING] = { .name = "string", .type = YNL_PT_NEST, .nest = &ethtool_string_nest, },
-};
-
-struct ynl_policy_nest ethtool_strings_nest = {
-	.max_attr = ETHTOOL_A_STRINGS_MAX,
-	.table = ethtool_strings_policy,
-};
-
-struct ynl_policy_attr ethtool_bitset_policy[ETHTOOL_A_BITSET_MAX + 1] = {
-	[ETHTOOL_A_BITSET_NOMASK] = { .name = "nomask", .type = YNL_PT_FLAG, },
-	[ETHTOOL_A_BITSET_SIZE] = { .name = "size", .type = YNL_PT_U32, },
-	[ETHTOOL_A_BITSET_BITS] = { .name = "bits", .type = YNL_PT_NEST, .nest = &ethtool_bitset_bits_nest, },
-};
-
-struct ynl_policy_nest ethtool_bitset_nest = {
-	.max_attr = ETHTOOL_A_BITSET_MAX,
-	.table = ethtool_bitset_policy,
-};
-
-struct ynl_policy_attr ethtool_stringset_policy[ETHTOOL_A_STRINGSET_MAX + 1] = {
-	[ETHTOOL_A_STRINGSET_ID] = { .name = "id", .type = YNL_PT_U32, },
-	[ETHTOOL_A_STRINGSET_COUNT] = { .name = "count", .type = YNL_PT_U32, },
-	[ETHTOOL_A_STRINGSET_STRINGS] = { .name = "strings", .type = YNL_PT_NEST, .nest = &ethtool_strings_nest, },
-};
-
-struct ynl_policy_nest ethtool_stringset_nest = {
-	.max_attr = ETHTOOL_A_STRINGSET_MAX,
-	.table = ethtool_stringset_policy,
-};
-
-struct ynl_policy_attr ethtool_tunnel_udp_table_policy[ETHTOOL_A_TUNNEL_UDP_TABLE_MAX + 1] = {
-	[ETHTOOL_A_TUNNEL_UDP_TABLE_SIZE] = { .name = "size", .type = YNL_PT_U32, },
-	[ETHTOOL_A_TUNNEL_UDP_TABLE_TYPES] = { .name = "types", .type = YNL_PT_NEST, .nest = &ethtool_bitset_nest, },
-	[ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY] = { .name = "entry", .type = YNL_PT_NEST, .nest = &ethtool_tunnel_udp_entry_nest, },
-};
-
-struct ynl_policy_nest ethtool_tunnel_udp_table_nest = {
-	.max_attr = ETHTOOL_A_TUNNEL_UDP_TABLE_MAX,
-	.table = ethtool_tunnel_udp_table_policy,
-};
-
-struct ynl_policy_attr ethtool_stringsets_policy[ETHTOOL_A_STRINGSETS_MAX + 1] = {
-	[ETHTOOL_A_STRINGSETS_STRINGSET] = { .name = "stringset", .type = YNL_PT_NEST, .nest = &ethtool_stringset_nest, },
-};
-
-struct ynl_policy_nest ethtool_stringsets_nest = {
-	.max_attr = ETHTOOL_A_STRINGSETS_MAX,
-	.table = ethtool_stringsets_policy,
-};
-
-struct ynl_policy_attr ethtool_tunnel_udp_policy[ETHTOOL_A_TUNNEL_UDP_MAX + 1] = {
-	[ETHTOOL_A_TUNNEL_UDP_TABLE] = { .name = "table", .type = YNL_PT_NEST, .nest = &ethtool_tunnel_udp_table_nest, },
-};
-
-struct ynl_policy_nest ethtool_tunnel_udp_nest = {
-	.max_attr = ETHTOOL_A_TUNNEL_UDP_MAX,
-	.table = ethtool_tunnel_udp_policy,
-};
-
-struct ynl_policy_attr ethtool_strset_policy[ETHTOOL_A_STRSET_MAX + 1] = {
-	[ETHTOOL_A_STRSET_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_STRSET_STRINGSETS] = { .name = "stringsets", .type = YNL_PT_NEST, .nest = &ethtool_stringsets_nest, },
-	[ETHTOOL_A_STRSET_COUNTS_ONLY] = { .name = "counts-only", .type = YNL_PT_FLAG, },
-};
-
-struct ynl_policy_nest ethtool_strset_nest = {
-	.max_attr = ETHTOOL_A_STRSET_MAX,
-	.table = ethtool_strset_policy,
-};
-
-struct ynl_policy_attr ethtool_linkinfo_policy[ETHTOOL_A_LINKINFO_MAX + 1] = {
-	[ETHTOOL_A_LINKINFO_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_LINKINFO_PORT] = { .name = "port", .type = YNL_PT_U8, },
-	[ETHTOOL_A_LINKINFO_PHYADDR] = { .name = "phyaddr", .type = YNL_PT_U8, },
-	[ETHTOOL_A_LINKINFO_TP_MDIX] = { .name = "tp-mdix", .type = YNL_PT_U8, },
-	[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL] = { .name = "tp-mdix-ctrl", .type = YNL_PT_U8, },
-	[ETHTOOL_A_LINKINFO_TRANSCEIVER] = { .name = "transceiver", .type = YNL_PT_U8, },
-};
-
-struct ynl_policy_nest ethtool_linkinfo_nest = {
-	.max_attr = ETHTOOL_A_LINKINFO_MAX,
-	.table = ethtool_linkinfo_policy,
-};
-
-struct ynl_policy_attr ethtool_linkmodes_policy[ETHTOOL_A_LINKMODES_MAX + 1] = {
-	[ETHTOOL_A_LINKMODES_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_LINKMODES_AUTONEG] = { .name = "autoneg", .type = YNL_PT_U8, },
-	[ETHTOOL_A_LINKMODES_OURS] = { .name = "ours", .type = YNL_PT_NEST, .nest = &ethtool_bitset_nest, },
-	[ETHTOOL_A_LINKMODES_PEER] = { .name = "peer", .type = YNL_PT_NEST, .nest = &ethtool_bitset_nest, },
-	[ETHTOOL_A_LINKMODES_SPEED] = { .name = "speed", .type = YNL_PT_U32, },
-	[ETHTOOL_A_LINKMODES_DUPLEX] = { .name = "duplex", .type = YNL_PT_U8, },
-	[ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG] = { .name = "master-slave-cfg", .type = YNL_PT_U8, },
-	[ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE] = { .name = "master-slave-state", .type = YNL_PT_U8, },
-	[ETHTOOL_A_LINKMODES_LANES] = { .name = "lanes", .type = YNL_PT_U32, },
-	[ETHTOOL_A_LINKMODES_RATE_MATCHING] = { .name = "rate-matching", .type = YNL_PT_U8, },
-};
-
-struct ynl_policy_nest ethtool_linkmodes_nest = {
-	.max_attr = ETHTOOL_A_LINKMODES_MAX,
-	.table = ethtool_linkmodes_policy,
-};
-
-struct ynl_policy_attr ethtool_linkstate_policy[ETHTOOL_A_LINKSTATE_MAX + 1] = {
-	[ETHTOOL_A_LINKSTATE_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_LINKSTATE_LINK] = { .name = "link", .type = YNL_PT_U8, },
-	[ETHTOOL_A_LINKSTATE_SQI] = { .name = "sqi", .type = YNL_PT_U32, },
-	[ETHTOOL_A_LINKSTATE_SQI_MAX] = { .name = "sqi-max", .type = YNL_PT_U32, },
-	[ETHTOOL_A_LINKSTATE_EXT_STATE] = { .name = "ext-state", .type = YNL_PT_U8, },
-	[ETHTOOL_A_LINKSTATE_EXT_SUBSTATE] = { .name = "ext-substate", .type = YNL_PT_U8, },
-	[ETHTOOL_A_LINKSTATE_EXT_DOWN_CNT] = { .name = "ext-down-cnt", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest ethtool_linkstate_nest = {
-	.max_attr = ETHTOOL_A_LINKSTATE_MAX,
-	.table = ethtool_linkstate_policy,
-};
-
-struct ynl_policy_attr ethtool_debug_policy[ETHTOOL_A_DEBUG_MAX + 1] = {
-	[ETHTOOL_A_DEBUG_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_DEBUG_MSGMASK] = { .name = "msgmask", .type = YNL_PT_NEST, .nest = &ethtool_bitset_nest, },
-};
-
-struct ynl_policy_nest ethtool_debug_nest = {
-	.max_attr = ETHTOOL_A_DEBUG_MAX,
-	.table = ethtool_debug_policy,
-};
-
-struct ynl_policy_attr ethtool_wol_policy[ETHTOOL_A_WOL_MAX + 1] = {
-	[ETHTOOL_A_WOL_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_WOL_MODES] = { .name = "modes", .type = YNL_PT_NEST, .nest = &ethtool_bitset_nest, },
-	[ETHTOOL_A_WOL_SOPASS] = { .name = "sopass", .type = YNL_PT_BINARY,},
-};
-
-struct ynl_policy_nest ethtool_wol_nest = {
-	.max_attr = ETHTOOL_A_WOL_MAX,
-	.table = ethtool_wol_policy,
-};
-
-struct ynl_policy_attr ethtool_features_policy[ETHTOOL_A_FEATURES_MAX + 1] = {
-	[ETHTOOL_A_FEATURES_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_FEATURES_HW] = { .name = "hw", .type = YNL_PT_NEST, .nest = &ethtool_bitset_nest, },
-	[ETHTOOL_A_FEATURES_WANTED] = { .name = "wanted", .type = YNL_PT_NEST, .nest = &ethtool_bitset_nest, },
-	[ETHTOOL_A_FEATURES_ACTIVE] = { .name = "active", .type = YNL_PT_NEST, .nest = &ethtool_bitset_nest, },
-	[ETHTOOL_A_FEATURES_NOCHANGE] = { .name = "nochange", .type = YNL_PT_NEST, .nest = &ethtool_bitset_nest, },
-};
-
-struct ynl_policy_nest ethtool_features_nest = {
-	.max_attr = ETHTOOL_A_FEATURES_MAX,
-	.table = ethtool_features_policy,
-};
-
-struct ynl_policy_attr ethtool_privflags_policy[ETHTOOL_A_PRIVFLAGS_MAX + 1] = {
-	[ETHTOOL_A_PRIVFLAGS_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_PRIVFLAGS_FLAGS] = { .name = "flags", .type = YNL_PT_NEST, .nest = &ethtool_bitset_nest, },
-};
-
-struct ynl_policy_nest ethtool_privflags_nest = {
-	.max_attr = ETHTOOL_A_PRIVFLAGS_MAX,
-	.table = ethtool_privflags_policy,
-};
-
-struct ynl_policy_attr ethtool_rings_policy[ETHTOOL_A_RINGS_MAX + 1] = {
-	[ETHTOOL_A_RINGS_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_RINGS_RX_MAX] = { .name = "rx-max", .type = YNL_PT_U32, },
-	[ETHTOOL_A_RINGS_RX_MINI_MAX] = { .name = "rx-mini-max", .type = YNL_PT_U32, },
-	[ETHTOOL_A_RINGS_RX_JUMBO_MAX] = { .name = "rx-jumbo-max", .type = YNL_PT_U32, },
-	[ETHTOOL_A_RINGS_TX_MAX] = { .name = "tx-max", .type = YNL_PT_U32, },
-	[ETHTOOL_A_RINGS_RX] = { .name = "rx", .type = YNL_PT_U32, },
-	[ETHTOOL_A_RINGS_RX_MINI] = { .name = "rx-mini", .type = YNL_PT_U32, },
-	[ETHTOOL_A_RINGS_RX_JUMBO] = { .name = "rx-jumbo", .type = YNL_PT_U32, },
-	[ETHTOOL_A_RINGS_TX] = { .name = "tx", .type = YNL_PT_U32, },
-	[ETHTOOL_A_RINGS_RX_BUF_LEN] = { .name = "rx-buf-len", .type = YNL_PT_U32, },
-	[ETHTOOL_A_RINGS_TCP_DATA_SPLIT] = { .name = "tcp-data-split", .type = YNL_PT_U8, },
-	[ETHTOOL_A_RINGS_CQE_SIZE] = { .name = "cqe-size", .type = YNL_PT_U32, },
-	[ETHTOOL_A_RINGS_TX_PUSH] = { .name = "tx-push", .type = YNL_PT_U8, },
-	[ETHTOOL_A_RINGS_RX_PUSH] = { .name = "rx-push", .type = YNL_PT_U8, },
-	[ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN] = { .name = "tx-push-buf-len", .type = YNL_PT_U32, },
-	[ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN_MAX] = { .name = "tx-push-buf-len-max", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest ethtool_rings_nest = {
-	.max_attr = ETHTOOL_A_RINGS_MAX,
-	.table = ethtool_rings_policy,
-};
-
-struct ynl_policy_attr ethtool_channels_policy[ETHTOOL_A_CHANNELS_MAX + 1] = {
-	[ETHTOOL_A_CHANNELS_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_CHANNELS_RX_MAX] = { .name = "rx-max", .type = YNL_PT_U32, },
-	[ETHTOOL_A_CHANNELS_TX_MAX] = { .name = "tx-max", .type = YNL_PT_U32, },
-	[ETHTOOL_A_CHANNELS_OTHER_MAX] = { .name = "other-max", .type = YNL_PT_U32, },
-	[ETHTOOL_A_CHANNELS_COMBINED_MAX] = { .name = "combined-max", .type = YNL_PT_U32, },
-	[ETHTOOL_A_CHANNELS_RX_COUNT] = { .name = "rx-count", .type = YNL_PT_U32, },
-	[ETHTOOL_A_CHANNELS_TX_COUNT] = { .name = "tx-count", .type = YNL_PT_U32, },
-	[ETHTOOL_A_CHANNELS_OTHER_COUNT] = { .name = "other-count", .type = YNL_PT_U32, },
-	[ETHTOOL_A_CHANNELS_COMBINED_COUNT] = { .name = "combined-count", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest ethtool_channels_nest = {
-	.max_attr = ETHTOOL_A_CHANNELS_MAX,
-	.table = ethtool_channels_policy,
-};
-
-struct ynl_policy_attr ethtool_coalesce_policy[ETHTOOL_A_COALESCE_MAX + 1] = {
-	[ETHTOOL_A_COALESCE_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_COALESCE_RX_USECS] = { .name = "rx-usecs", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_RX_MAX_FRAMES] = { .name = "rx-max-frames", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_RX_USECS_IRQ] = { .name = "rx-usecs-irq", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ] = { .name = "rx-max-frames-irq", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_TX_USECS] = { .name = "tx-usecs", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_TX_MAX_FRAMES] = { .name = "tx-max-frames", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_TX_USECS_IRQ] = { .name = "tx-usecs-irq", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ] = { .name = "tx-max-frames-irq", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_STATS_BLOCK_USECS] = { .name = "stats-block-usecs", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX] = { .name = "use-adaptive-rx", .type = YNL_PT_U8, },
-	[ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX] = { .name = "use-adaptive-tx", .type = YNL_PT_U8, },
-	[ETHTOOL_A_COALESCE_PKT_RATE_LOW] = { .name = "pkt-rate-low", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_RX_USECS_LOW] = { .name = "rx-usecs-low", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW] = { .name = "rx-max-frames-low", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_TX_USECS_LOW] = { .name = "tx-usecs-low", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW] = { .name = "tx-max-frames-low", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_PKT_RATE_HIGH] = { .name = "pkt-rate-high", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_RX_USECS_HIGH] = { .name = "rx-usecs-high", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH] = { .name = "rx-max-frames-high", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_TX_USECS_HIGH] = { .name = "tx-usecs-high", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH] = { .name = "tx-max-frames-high", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL] = { .name = "rate-sample-interval", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_USE_CQE_MODE_TX] = { .name = "use-cqe-mode-tx", .type = YNL_PT_U8, },
-	[ETHTOOL_A_COALESCE_USE_CQE_MODE_RX] = { .name = "use-cqe-mode-rx", .type = YNL_PT_U8, },
-	[ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES] = { .name = "tx-aggr-max-bytes", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES] = { .name = "tx-aggr-max-frames", .type = YNL_PT_U32, },
-	[ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS] = { .name = "tx-aggr-time-usecs", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest ethtool_coalesce_nest = {
-	.max_attr = ETHTOOL_A_COALESCE_MAX,
-	.table = ethtool_coalesce_policy,
-};
-
-struct ynl_policy_attr ethtool_pause_policy[ETHTOOL_A_PAUSE_MAX + 1] = {
-	[ETHTOOL_A_PAUSE_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_PAUSE_AUTONEG] = { .name = "autoneg", .type = YNL_PT_U8, },
-	[ETHTOOL_A_PAUSE_RX] = { .name = "rx", .type = YNL_PT_U8, },
-	[ETHTOOL_A_PAUSE_TX] = { .name = "tx", .type = YNL_PT_U8, },
-	[ETHTOOL_A_PAUSE_STATS] = { .name = "stats", .type = YNL_PT_NEST, .nest = &ethtool_pause_stat_nest, },
-	[ETHTOOL_A_PAUSE_STATS_SRC] = { .name = "stats-src", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest ethtool_pause_nest = {
-	.max_attr = ETHTOOL_A_PAUSE_MAX,
-	.table = ethtool_pause_policy,
-};
-
-struct ynl_policy_attr ethtool_eee_policy[ETHTOOL_A_EEE_MAX + 1] = {
-	[ETHTOOL_A_EEE_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_EEE_MODES_OURS] = { .name = "modes-ours", .type = YNL_PT_NEST, .nest = &ethtool_bitset_nest, },
-	[ETHTOOL_A_EEE_MODES_PEER] = { .name = "modes-peer", .type = YNL_PT_NEST, .nest = &ethtool_bitset_nest, },
-	[ETHTOOL_A_EEE_ACTIVE] = { .name = "active", .type = YNL_PT_U8, },
-	[ETHTOOL_A_EEE_ENABLED] = { .name = "enabled", .type = YNL_PT_U8, },
-	[ETHTOOL_A_EEE_TX_LPI_ENABLED] = { .name = "tx-lpi-enabled", .type = YNL_PT_U8, },
-	[ETHTOOL_A_EEE_TX_LPI_TIMER] = { .name = "tx-lpi-timer", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest ethtool_eee_nest = {
-	.max_attr = ETHTOOL_A_EEE_MAX,
-	.table = ethtool_eee_policy,
-};
-
-struct ynl_policy_attr ethtool_tsinfo_policy[ETHTOOL_A_TSINFO_MAX + 1] = {
-	[ETHTOOL_A_TSINFO_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_TSINFO_TIMESTAMPING] = { .name = "timestamping", .type = YNL_PT_NEST, .nest = &ethtool_bitset_nest, },
-	[ETHTOOL_A_TSINFO_TX_TYPES] = { .name = "tx-types", .type = YNL_PT_NEST, .nest = &ethtool_bitset_nest, },
-	[ETHTOOL_A_TSINFO_RX_FILTERS] = { .name = "rx-filters", .type = YNL_PT_NEST, .nest = &ethtool_bitset_nest, },
-	[ETHTOOL_A_TSINFO_PHC_INDEX] = { .name = "phc-index", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest ethtool_tsinfo_nest = {
-	.max_attr = ETHTOOL_A_TSINFO_MAX,
-	.table = ethtool_tsinfo_policy,
-};
-
-struct ynl_policy_attr ethtool_cable_test_policy[ETHTOOL_A_CABLE_TEST_MAX + 1] = {
-	[ETHTOOL_A_CABLE_TEST_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-};
-
-struct ynl_policy_nest ethtool_cable_test_nest = {
-	.max_attr = ETHTOOL_A_CABLE_TEST_MAX,
-	.table = ethtool_cable_test_policy,
-};
-
-struct ynl_policy_attr ethtool_cable_test_ntf_policy[ETHTOOL_A_CABLE_TEST_NTF_MAX + 1] = {
-	[ETHTOOL_A_CABLE_TEST_NTF_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_CABLE_TEST_NTF_STATUS] = { .name = "status", .type = YNL_PT_U8, },
-	[ETHTOOL_A_CABLE_TEST_NTF_NEST] = { .name = "nest", .type = YNL_PT_NEST, .nest = &ethtool_cable_nest_nest, },
-};
-
-struct ynl_policy_nest ethtool_cable_test_ntf_nest = {
-	.max_attr = ETHTOOL_A_CABLE_TEST_NTF_MAX,
-	.table = ethtool_cable_test_ntf_policy,
-};
-
-struct ynl_policy_attr ethtool_cable_test_tdr_policy[ETHTOOL_A_CABLE_TEST_TDR_MAX + 1] = {
-	[ETHTOOL_A_CABLE_TEST_TDR_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_CABLE_TEST_TDR_CFG] = { .name = "cfg", .type = YNL_PT_NEST, .nest = &ethtool_cable_test_tdr_cfg_nest, },
-};
-
-struct ynl_policy_nest ethtool_cable_test_tdr_nest = {
-	.max_attr = ETHTOOL_A_CABLE_TEST_TDR_MAX,
-	.table = ethtool_cable_test_tdr_policy,
-};
-
-struct ynl_policy_attr ethtool_cable_test_tdr_ntf_policy[ETHTOOL_A_CABLE_TEST_TDR_NTF_MAX + 1] = {
-	[ETHTOOL_A_CABLE_TEST_TDR_NTF_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_CABLE_TEST_TDR_NTF_STATUS] = { .name = "status", .type = YNL_PT_U8, },
-	[ETHTOOL_A_CABLE_TEST_TDR_NTF_NEST] = { .name = "nest", .type = YNL_PT_NEST, .nest = &ethtool_cable_nest_nest, },
-};
-
-struct ynl_policy_nest ethtool_cable_test_tdr_ntf_nest = {
-	.max_attr = ETHTOOL_A_CABLE_TEST_TDR_NTF_MAX,
-	.table = ethtool_cable_test_tdr_ntf_policy,
-};
-
-struct ynl_policy_attr ethtool_tunnel_info_policy[ETHTOOL_A_TUNNEL_INFO_MAX + 1] = {
-	[ETHTOOL_A_TUNNEL_INFO_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_TUNNEL_INFO_UDP_PORTS] = { .name = "udp-ports", .type = YNL_PT_NEST, .nest = &ethtool_tunnel_udp_nest, },
-};
-
-struct ynl_policy_nest ethtool_tunnel_info_nest = {
-	.max_attr = ETHTOOL_A_TUNNEL_INFO_MAX,
-	.table = ethtool_tunnel_info_policy,
-};
-
-struct ynl_policy_attr ethtool_fec_policy[ETHTOOL_A_FEC_MAX + 1] = {
-	[ETHTOOL_A_FEC_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_FEC_MODES] = { .name = "modes", .type = YNL_PT_NEST, .nest = &ethtool_bitset_nest, },
-	[ETHTOOL_A_FEC_AUTO] = { .name = "auto", .type = YNL_PT_U8, },
-	[ETHTOOL_A_FEC_ACTIVE] = { .name = "active", .type = YNL_PT_U32, },
-	[ETHTOOL_A_FEC_STATS] = { .name = "stats", .type = YNL_PT_NEST, .nest = &ethtool_fec_stat_nest, },
-};
-
-struct ynl_policy_nest ethtool_fec_nest = {
-	.max_attr = ETHTOOL_A_FEC_MAX,
-	.table = ethtool_fec_policy,
-};
-
-struct ynl_policy_attr ethtool_module_eeprom_policy[ETHTOOL_A_MODULE_EEPROM_MAX + 1] = {
-	[ETHTOOL_A_MODULE_EEPROM_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_MODULE_EEPROM_OFFSET] = { .name = "offset", .type = YNL_PT_U32, },
-	[ETHTOOL_A_MODULE_EEPROM_LENGTH] = { .name = "length", .type = YNL_PT_U32, },
-	[ETHTOOL_A_MODULE_EEPROM_PAGE] = { .name = "page", .type = YNL_PT_U8, },
-	[ETHTOOL_A_MODULE_EEPROM_BANK] = { .name = "bank", .type = YNL_PT_U8, },
-	[ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS] = { .name = "i2c-address", .type = YNL_PT_U8, },
-	[ETHTOOL_A_MODULE_EEPROM_DATA] = { .name = "data", .type = YNL_PT_BINARY,},
-};
-
-struct ynl_policy_nest ethtool_module_eeprom_nest = {
-	.max_attr = ETHTOOL_A_MODULE_EEPROM_MAX,
-	.table = ethtool_module_eeprom_policy,
-};
-
-struct ynl_policy_attr ethtool_phc_vclocks_policy[ETHTOOL_A_PHC_VCLOCKS_MAX + 1] = {
-	[ETHTOOL_A_PHC_VCLOCKS_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_PHC_VCLOCKS_NUM] = { .name = "num", .type = YNL_PT_U32, },
-	[ETHTOOL_A_PHC_VCLOCKS_INDEX] = { .name = "index", .type = YNL_PT_BINARY,},
-};
-
-struct ynl_policy_nest ethtool_phc_vclocks_nest = {
-	.max_attr = ETHTOOL_A_PHC_VCLOCKS_MAX,
-	.table = ethtool_phc_vclocks_policy,
-};
-
-struct ynl_policy_attr ethtool_module_policy[ETHTOOL_A_MODULE_MAX + 1] = {
-	[ETHTOOL_A_MODULE_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_MODULE_POWER_MODE_POLICY] = { .name = "power-mode-policy", .type = YNL_PT_U8, },
-	[ETHTOOL_A_MODULE_POWER_MODE] = { .name = "power-mode", .type = YNL_PT_U8, },
-};
-
-struct ynl_policy_nest ethtool_module_nest = {
-	.max_attr = ETHTOOL_A_MODULE_MAX,
-	.table = ethtool_module_policy,
-};
-
-struct ynl_policy_attr ethtool_pse_policy[ETHTOOL_A_PSE_MAX + 1] = {
-	[ETHTOOL_A_PSE_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_PODL_PSE_ADMIN_STATE] = { .name = "admin-state", .type = YNL_PT_U32, },
-	[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL] = { .name = "admin-control", .type = YNL_PT_U32, },
-	[ETHTOOL_A_PODL_PSE_PW_D_STATUS] = { .name = "pw-d-status", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest ethtool_pse_nest = {
-	.max_attr = ETHTOOL_A_PSE_MAX,
-	.table = ethtool_pse_policy,
-};
-
-struct ynl_policy_attr ethtool_rss_policy[ETHTOOL_A_RSS_MAX + 1] = {
-	[ETHTOOL_A_RSS_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_RSS_CONTEXT] = { .name = "context", .type = YNL_PT_U32, },
-	[ETHTOOL_A_RSS_HFUNC] = { .name = "hfunc", .type = YNL_PT_U32, },
-	[ETHTOOL_A_RSS_INDIR] = { .name = "indir", .type = YNL_PT_BINARY,},
-	[ETHTOOL_A_RSS_HKEY] = { .name = "hkey", .type = YNL_PT_BINARY,},
-};
-
-struct ynl_policy_nest ethtool_rss_nest = {
-	.max_attr = ETHTOOL_A_RSS_MAX,
-	.table = ethtool_rss_policy,
-};
-
-struct ynl_policy_attr ethtool_plca_policy[ETHTOOL_A_PLCA_MAX + 1] = {
-	[ETHTOOL_A_PLCA_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_PLCA_VERSION] = { .name = "version", .type = YNL_PT_U16, },
-	[ETHTOOL_A_PLCA_ENABLED] = { .name = "enabled", .type = YNL_PT_U8, },
-	[ETHTOOL_A_PLCA_STATUS] = { .name = "status", .type = YNL_PT_U8, },
-	[ETHTOOL_A_PLCA_NODE_CNT] = { .name = "node-cnt", .type = YNL_PT_U32, },
-	[ETHTOOL_A_PLCA_NODE_ID] = { .name = "node-id", .type = YNL_PT_U32, },
-	[ETHTOOL_A_PLCA_TO_TMR] = { .name = "to-tmr", .type = YNL_PT_U32, },
-	[ETHTOOL_A_PLCA_BURST_CNT] = { .name = "burst-cnt", .type = YNL_PT_U32, },
-	[ETHTOOL_A_PLCA_BURST_TMR] = { .name = "burst-tmr", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest ethtool_plca_nest = {
-	.max_attr = ETHTOOL_A_PLCA_MAX,
-	.table = ethtool_plca_policy,
-};
-
-struct ynl_policy_attr ethtool_mm_policy[ETHTOOL_A_MM_MAX + 1] = {
-	[ETHTOOL_A_MM_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = &ethtool_header_nest, },
-	[ETHTOOL_A_MM_PMAC_ENABLED] = { .name = "pmac-enabled", .type = YNL_PT_U8, },
-	[ETHTOOL_A_MM_TX_ENABLED] = { .name = "tx-enabled", .type = YNL_PT_U8, },
-	[ETHTOOL_A_MM_TX_ACTIVE] = { .name = "tx-active", .type = YNL_PT_U8, },
-	[ETHTOOL_A_MM_TX_MIN_FRAG_SIZE] = { .name = "tx-min-frag-size", .type = YNL_PT_U32, },
-	[ETHTOOL_A_MM_RX_MIN_FRAG_SIZE] = { .name = "rx-min-frag-size", .type = YNL_PT_U32, },
-	[ETHTOOL_A_MM_VERIFY_ENABLED] = { .name = "verify-enabled", .type = YNL_PT_U8, },
-	[ETHTOOL_A_MM_VERIFY_STATUS] = { .name = "verify-status", .type = YNL_PT_U8, },
-	[ETHTOOL_A_MM_VERIFY_TIME] = { .name = "verify-time", .type = YNL_PT_U32, },
-	[ETHTOOL_A_MM_MAX_VERIFY_TIME] = { .name = "max-verify-time", .type = YNL_PT_U32, },
-	[ETHTOOL_A_MM_STATS] = { .name = "stats", .type = YNL_PT_NEST, .nest = &ethtool_mm_stat_nest, },
-};
-
-struct ynl_policy_nest ethtool_mm_nest = {
-	.max_attr = ETHTOOL_A_MM_MAX,
-	.table = ethtool_mm_policy,
-};
-
-/* Common nested types */
-void ethtool_header_free(struct ethtool_header *obj)
-{
-	free(obj->dev_name);
-}
-
-int ethtool_header_put(struct nlmsghdr *nlh, unsigned int attr_type,
-		       struct ethtool_header *obj)
-{
-	struct nlattr *nest;
-
-	nest = mnl_attr_nest_start(nlh, attr_type);
-	if (obj->_present.dev_index)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_HEADER_DEV_INDEX, obj->dev_index);
-	if (obj->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, ETHTOOL_A_HEADER_DEV_NAME, obj->dev_name);
-	if (obj->_present.flags)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_HEADER_FLAGS, obj->flags);
-	mnl_attr_nest_end(nlh, nest);
-
-	return 0;
-}
-
-int ethtool_header_parse(struct ynl_parse_arg *yarg,
-			 const struct nlattr *nested)
-{
-	struct ethtool_header *dst = yarg->data;
-	const struct nlattr *attr;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_HEADER_DEV_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dev_index = 1;
-			dst->dev_index = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_HEADER_DEV_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.dev_name_len = len;
-			dst->dev_name = malloc(len + 1);
-			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
-			dst->dev_name[len] = 0;
-		} else if (type == ETHTOOL_A_HEADER_FLAGS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.flags = 1;
-			dst->flags = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return 0;
-}
-
-void ethtool_pause_stat_free(struct ethtool_pause_stat *obj)
-{
-}
-
-int ethtool_pause_stat_put(struct nlmsghdr *nlh, unsigned int attr_type,
-			   struct ethtool_pause_stat *obj)
-{
-	struct nlattr *nest;
-
-	nest = mnl_attr_nest_start(nlh, attr_type);
-	if (obj->_present.tx_frames)
-		mnl_attr_put_u64(nlh, ETHTOOL_A_PAUSE_STAT_TX_FRAMES, obj->tx_frames);
-	if (obj->_present.rx_frames)
-		mnl_attr_put_u64(nlh, ETHTOOL_A_PAUSE_STAT_RX_FRAMES, obj->rx_frames);
-	mnl_attr_nest_end(nlh, nest);
-
-	return 0;
-}
-
-int ethtool_pause_stat_parse(struct ynl_parse_arg *yarg,
-			     const struct nlattr *nested)
-{
-	struct ethtool_pause_stat *dst = yarg->data;
-	const struct nlattr *attr;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_PAUSE_STAT_TX_FRAMES) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_frames = 1;
-			dst->tx_frames = mnl_attr_get_u64(attr);
-		} else if (type == ETHTOOL_A_PAUSE_STAT_RX_FRAMES) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx_frames = 1;
-			dst->rx_frames = mnl_attr_get_u64(attr);
-		}
-	}
-
-	return 0;
-}
-
-void ethtool_cable_test_tdr_cfg_free(struct ethtool_cable_test_tdr_cfg *obj)
-{
-}
-
-void ethtool_fec_stat_free(struct ethtool_fec_stat *obj)
-{
-	free(obj->corrected);
-	free(obj->uncorr);
-	free(obj->corr_bits);
-}
-
-int ethtool_fec_stat_put(struct nlmsghdr *nlh, unsigned int attr_type,
-			 struct ethtool_fec_stat *obj)
-{
-	struct nlattr *nest;
-
-	nest = mnl_attr_nest_start(nlh, attr_type);
-	if (obj->_present.corrected_len)
-		mnl_attr_put(nlh, ETHTOOL_A_FEC_STAT_CORRECTED, obj->_present.corrected_len, obj->corrected);
-	if (obj->_present.uncorr_len)
-		mnl_attr_put(nlh, ETHTOOL_A_FEC_STAT_UNCORR, obj->_present.uncorr_len, obj->uncorr);
-	if (obj->_present.corr_bits_len)
-		mnl_attr_put(nlh, ETHTOOL_A_FEC_STAT_CORR_BITS, obj->_present.corr_bits_len, obj->corr_bits);
-	mnl_attr_nest_end(nlh, nest);
-
-	return 0;
-}
-
-int ethtool_fec_stat_parse(struct ynl_parse_arg *yarg,
-			   const struct nlattr *nested)
-{
-	struct ethtool_fec_stat *dst = yarg->data;
-	const struct nlattr *attr;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_FEC_STAT_CORRECTED) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = mnl_attr_get_payload_len(attr);
-			dst->_present.corrected_len = len;
-			dst->corrected = malloc(len);
-			memcpy(dst->corrected, mnl_attr_get_payload(attr), len);
-		} else if (type == ETHTOOL_A_FEC_STAT_UNCORR) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = mnl_attr_get_payload_len(attr);
-			dst->_present.uncorr_len = len;
-			dst->uncorr = malloc(len);
-			memcpy(dst->uncorr, mnl_attr_get_payload(attr), len);
-		} else if (type == ETHTOOL_A_FEC_STAT_CORR_BITS) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = mnl_attr_get_payload_len(attr);
-			dst->_present.corr_bits_len = len;
-			dst->corr_bits = malloc(len);
-			memcpy(dst->corr_bits, mnl_attr_get_payload(attr), len);
-		}
-	}
-
-	return 0;
-}
-
-void ethtool_mm_stat_free(struct ethtool_mm_stat *obj)
-{
-}
-
-int ethtool_mm_stat_parse(struct ynl_parse_arg *yarg,
-			  const struct nlattr *nested)
-{
-	struct ethtool_mm_stat *dst = yarg->data;
-	const struct nlattr *attr;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_MM_STAT_REASSEMBLY_ERRORS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.reassembly_errors = 1;
-			dst->reassembly_errors = mnl_attr_get_u64(attr);
-		} else if (type == ETHTOOL_A_MM_STAT_SMD_ERRORS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.smd_errors = 1;
-			dst->smd_errors = mnl_attr_get_u64(attr);
-		} else if (type == ETHTOOL_A_MM_STAT_REASSEMBLY_OK) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.reassembly_ok = 1;
-			dst->reassembly_ok = mnl_attr_get_u64(attr);
-		} else if (type == ETHTOOL_A_MM_STAT_RX_FRAG_COUNT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx_frag_count = 1;
-			dst->rx_frag_count = mnl_attr_get_u64(attr);
-		} else if (type == ETHTOOL_A_MM_STAT_TX_FRAG_COUNT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_frag_count = 1;
-			dst->tx_frag_count = mnl_attr_get_u64(attr);
-		} else if (type == ETHTOOL_A_MM_STAT_HOLD_COUNT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.hold_count = 1;
-			dst->hold_count = mnl_attr_get_u64(attr);
-		}
-	}
-
-	return 0;
-}
-
-void ethtool_cable_result_free(struct ethtool_cable_result *obj)
-{
-}
-
-int ethtool_cable_result_parse(struct ynl_parse_arg *yarg,
-			       const struct nlattr *nested)
-{
-	struct ethtool_cable_result *dst = yarg->data;
-	const struct nlattr *attr;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_CABLE_RESULT_PAIR) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.pair = 1;
-			dst->pair = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_CABLE_RESULT_CODE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.code = 1;
-			dst->code = mnl_attr_get_u8(attr);
-		}
-	}
-
-	return 0;
-}
-
-void ethtool_cable_fault_length_free(struct ethtool_cable_fault_length *obj)
-{
-}
-
-int ethtool_cable_fault_length_parse(struct ynl_parse_arg *yarg,
-				     const struct nlattr *nested)
-{
-	struct ethtool_cable_fault_length *dst = yarg->data;
-	const struct nlattr *attr;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_CABLE_FAULT_LENGTH_PAIR) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.pair = 1;
-			dst->pair = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_CABLE_FAULT_LENGTH_CM) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.cm = 1;
-			dst->cm = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return 0;
-}
-
-void ethtool_bitset_bit_free(struct ethtool_bitset_bit *obj)
-{
-	free(obj->name);
-}
-
-int ethtool_bitset_bit_put(struct nlmsghdr *nlh, unsigned int attr_type,
-			   struct ethtool_bitset_bit *obj)
-{
-	struct nlattr *nest;
-
-	nest = mnl_attr_nest_start(nlh, attr_type);
-	if (obj->_present.index)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_BITSET_BIT_INDEX, obj->index);
-	if (obj->_present.name_len)
-		mnl_attr_put_strz(nlh, ETHTOOL_A_BITSET_BIT_NAME, obj->name);
-	if (obj->_present.value)
-		mnl_attr_put(nlh, ETHTOOL_A_BITSET_BIT_VALUE, 0, NULL);
-	mnl_attr_nest_end(nlh, nest);
-
-	return 0;
-}
-
-int ethtool_bitset_bit_parse(struct ynl_parse_arg *yarg,
-			     const struct nlattr *nested)
-{
-	struct ethtool_bitset_bit *dst = yarg->data;
-	const struct nlattr *attr;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_BITSET_BIT_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.index = 1;
-			dst->index = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_BITSET_BIT_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.name_len = len;
-			dst->name = malloc(len + 1);
-			memcpy(dst->name, mnl_attr_get_str(attr), len);
-			dst->name[len] = 0;
-		} else if (type == ETHTOOL_A_BITSET_BIT_VALUE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.value = 1;
-		}
-	}
-
-	return 0;
-}
-
-void ethtool_tunnel_udp_entry_free(struct ethtool_tunnel_udp_entry *obj)
-{
-}
-
-int ethtool_tunnel_udp_entry_parse(struct ynl_parse_arg *yarg,
-				   const struct nlattr *nested)
-{
-	struct ethtool_tunnel_udp_entry *dst = yarg->data;
-	const struct nlattr *attr;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_TUNNEL_UDP_ENTRY_PORT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.port = 1;
-			dst->port = mnl_attr_get_u16(attr);
-		} else if (type == ETHTOOL_A_TUNNEL_UDP_ENTRY_TYPE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.type = 1;
-			dst->type = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return 0;
-}
-
-void ethtool_string_free(struct ethtool_string *obj)
-{
-	free(obj->value);
-}
-
-int ethtool_string_put(struct nlmsghdr *nlh, unsigned int attr_type,
-		       struct ethtool_string *obj)
-{
-	struct nlattr *nest;
-
-	nest = mnl_attr_nest_start(nlh, attr_type);
-	if (obj->_present.index)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_STRING_INDEX, obj->index);
-	if (obj->_present.value_len)
-		mnl_attr_put_strz(nlh, ETHTOOL_A_STRING_VALUE, obj->value);
-	mnl_attr_nest_end(nlh, nest);
-
-	return 0;
-}
-
-int ethtool_string_parse(struct ynl_parse_arg *yarg,
-			 const struct nlattr *nested)
-{
-	struct ethtool_string *dst = yarg->data;
-	const struct nlattr *attr;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_STRING_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.index = 1;
-			dst->index = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_STRING_VALUE) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.value_len = len;
-			dst->value = malloc(len + 1);
-			memcpy(dst->value, mnl_attr_get_str(attr), len);
-			dst->value[len] = 0;
-		}
-	}
-
-	return 0;
-}
-
-void ethtool_cable_nest_free(struct ethtool_cable_nest *obj)
-{
-	ethtool_cable_result_free(&obj->result);
-	ethtool_cable_fault_length_free(&obj->fault_length);
-}
-
-int ethtool_cable_nest_parse(struct ynl_parse_arg *yarg,
-			     const struct nlattr *nested)
-{
-	struct ethtool_cable_nest *dst = yarg->data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_CABLE_NEST_RESULT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.result = 1;
-
-			parg.rsp_policy = &ethtool_cable_result_nest;
-			parg.data = &dst->result;
-			if (ethtool_cable_result_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_CABLE_NEST_FAULT_LENGTH) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.fault_length = 1;
-
-			parg.rsp_policy = &ethtool_cable_fault_length_nest;
-			parg.data = &dst->fault_length;
-			if (ethtool_cable_fault_length_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		}
-	}
-
-	return 0;
-}
-
-void ethtool_bitset_bits_free(struct ethtool_bitset_bits *obj)
-{
-	unsigned int i;
-
-	for (i = 0; i < obj->n_bit; i++)
-		ethtool_bitset_bit_free(&obj->bit[i]);
-	free(obj->bit);
-}
-
-int ethtool_bitset_bits_put(struct nlmsghdr *nlh, unsigned int attr_type,
-			    struct ethtool_bitset_bits *obj)
-{
-	struct nlattr *nest;
-
-	nest = mnl_attr_nest_start(nlh, attr_type);
-	for (unsigned int i = 0; i < obj->n_bit; i++)
-		ethtool_bitset_bit_put(nlh, ETHTOOL_A_BITSET_BITS_BIT, &obj->bit[i]);
-	mnl_attr_nest_end(nlh, nest);
-
-	return 0;
-}
-
-int ethtool_bitset_bits_parse(struct ynl_parse_arg *yarg,
-			      const struct nlattr *nested)
-{
-	struct ethtool_bitset_bits *dst = yarg->data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	unsigned int n_bit = 0;
-	int i;
-
-	parg.ys = yarg->ys;
-
-	if (dst->bit)
-		return ynl_error_parse(yarg, "attribute already present (bitset-bits.bit)");
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_BITSET_BITS_BIT) {
-			n_bit++;
-		}
-	}
-
-	if (n_bit) {
-		dst->bit = calloc(n_bit, sizeof(*dst->bit));
-		dst->n_bit = n_bit;
-		i = 0;
-		parg.rsp_policy = &ethtool_bitset_bit_nest;
-		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == ETHTOOL_A_BITSET_BITS_BIT) {
-				parg.data = &dst->bit[i];
-				if (ethtool_bitset_bit_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-
-	return 0;
-}
-
-void ethtool_strings_free(struct ethtool_strings *obj)
-{
-	unsigned int i;
-
-	for (i = 0; i < obj->n_string; i++)
-		ethtool_string_free(&obj->string[i]);
-	free(obj->string);
-}
-
-int ethtool_strings_put(struct nlmsghdr *nlh, unsigned int attr_type,
-			struct ethtool_strings *obj)
-{
-	struct nlattr *nest;
-
-	nest = mnl_attr_nest_start(nlh, attr_type);
-	for (unsigned int i = 0; i < obj->n_string; i++)
-		ethtool_string_put(nlh, ETHTOOL_A_STRINGS_STRING, &obj->string[i]);
-	mnl_attr_nest_end(nlh, nest);
-
-	return 0;
-}
-
-int ethtool_strings_parse(struct ynl_parse_arg *yarg,
-			  const struct nlattr *nested)
-{
-	struct ethtool_strings *dst = yarg->data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	unsigned int n_string = 0;
-	int i;
-
-	parg.ys = yarg->ys;
-
-	if (dst->string)
-		return ynl_error_parse(yarg, "attribute already present (strings.string)");
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_STRINGS_STRING) {
-			n_string++;
-		}
-	}
-
-	if (n_string) {
-		dst->string = calloc(n_string, sizeof(*dst->string));
-		dst->n_string = n_string;
-		i = 0;
-		parg.rsp_policy = &ethtool_string_nest;
-		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == ETHTOOL_A_STRINGS_STRING) {
-				parg.data = &dst->string[i];
-				if (ethtool_string_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-
-	return 0;
-}
-
-void ethtool_bitset_free(struct ethtool_bitset *obj)
-{
-	ethtool_bitset_bits_free(&obj->bits);
-}
-
-int ethtool_bitset_put(struct nlmsghdr *nlh, unsigned int attr_type,
-		       struct ethtool_bitset *obj)
-{
-	struct nlattr *nest;
-
-	nest = mnl_attr_nest_start(nlh, attr_type);
-	if (obj->_present.nomask)
-		mnl_attr_put(nlh, ETHTOOL_A_BITSET_NOMASK, 0, NULL);
-	if (obj->_present.size)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_BITSET_SIZE, obj->size);
-	if (obj->_present.bits)
-		ethtool_bitset_bits_put(nlh, ETHTOOL_A_BITSET_BITS, &obj->bits);
-	mnl_attr_nest_end(nlh, nest);
-
-	return 0;
-}
-
-int ethtool_bitset_parse(struct ynl_parse_arg *yarg,
-			 const struct nlattr *nested)
-{
-	struct ethtool_bitset *dst = yarg->data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_BITSET_NOMASK) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.nomask = 1;
-		} else if (type == ETHTOOL_A_BITSET_SIZE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.size = 1;
-			dst->size = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_BITSET_BITS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.bits = 1;
-
-			parg.rsp_policy = &ethtool_bitset_bits_nest;
-			parg.data = &dst->bits;
-			if (ethtool_bitset_bits_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		}
-	}
-
-	return 0;
-}
-
-void ethtool_stringset_free(struct ethtool_stringset_ *obj)
-{
-	unsigned int i;
-
-	for (i = 0; i < obj->n_strings; i++)
-		ethtool_strings_free(&obj->strings[i]);
-	free(obj->strings);
-}
-
-int ethtool_stringset_put(struct nlmsghdr *nlh, unsigned int attr_type,
-			  struct ethtool_stringset_ *obj)
-{
-	struct nlattr *nest;
-
-	nest = mnl_attr_nest_start(nlh, attr_type);
-	if (obj->_present.id)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_STRINGSET_ID, obj->id);
-	if (obj->_present.count)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_STRINGSET_COUNT, obj->count);
-	for (unsigned int i = 0; i < obj->n_strings; i++)
-		ethtool_strings_put(nlh, ETHTOOL_A_STRINGSET_STRINGS, &obj->strings[i]);
-	mnl_attr_nest_end(nlh, nest);
-
-	return 0;
-}
-
-int ethtool_stringset_parse(struct ynl_parse_arg *yarg,
-			    const struct nlattr *nested)
-{
-	struct ethtool_stringset_ *dst = yarg->data;
-	unsigned int n_strings = 0;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	int i;
-
-	parg.ys = yarg->ys;
-
-	if (dst->strings)
-		return ynl_error_parse(yarg, "attribute already present (stringset.strings)");
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_STRINGSET_ID) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.id = 1;
-			dst->id = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_STRINGSET_COUNT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.count = 1;
-			dst->count = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_STRINGSET_STRINGS) {
-			n_strings++;
-		}
-	}
-
-	if (n_strings) {
-		dst->strings = calloc(n_strings, sizeof(*dst->strings));
-		dst->n_strings = n_strings;
-		i = 0;
-		parg.rsp_policy = &ethtool_strings_nest;
-		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == ETHTOOL_A_STRINGSET_STRINGS) {
-				parg.data = &dst->strings[i];
-				if (ethtool_strings_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-
-	return 0;
-}
-
-void ethtool_tunnel_udp_table_free(struct ethtool_tunnel_udp_table *obj)
-{
-	unsigned int i;
-
-	ethtool_bitset_free(&obj->types);
-	for (i = 0; i < obj->n_entry; i++)
-		ethtool_tunnel_udp_entry_free(&obj->entry[i]);
-	free(obj->entry);
-}
-
-int ethtool_tunnel_udp_table_parse(struct ynl_parse_arg *yarg,
-				   const struct nlattr *nested)
-{
-	struct ethtool_tunnel_udp_table *dst = yarg->data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	unsigned int n_entry = 0;
-	int i;
-
-	parg.ys = yarg->ys;
-
-	if (dst->entry)
-		return ynl_error_parse(yarg, "attribute already present (tunnel-udp-table.entry)");
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_TUNNEL_UDP_TABLE_SIZE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.size = 1;
-			dst->size = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_TUNNEL_UDP_TABLE_TYPES) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.types = 1;
-
-			parg.rsp_policy = &ethtool_bitset_nest;
-			parg.data = &dst->types;
-			if (ethtool_bitset_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY) {
-			n_entry++;
-		}
-	}
-
-	if (n_entry) {
-		dst->entry = calloc(n_entry, sizeof(*dst->entry));
-		dst->n_entry = n_entry;
-		i = 0;
-		parg.rsp_policy = &ethtool_tunnel_udp_entry_nest;
-		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY) {
-				parg.data = &dst->entry[i];
-				if (ethtool_tunnel_udp_entry_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-
-	return 0;
-}
-
-void ethtool_stringsets_free(struct ethtool_stringsets *obj)
-{
-	unsigned int i;
-
-	for (i = 0; i < obj->n_stringset; i++)
-		ethtool_stringset_free(&obj->stringset[i]);
-	free(obj->stringset);
-}
-
-int ethtool_stringsets_put(struct nlmsghdr *nlh, unsigned int attr_type,
-			   struct ethtool_stringsets *obj)
-{
-	struct nlattr *nest;
-
-	nest = mnl_attr_nest_start(nlh, attr_type);
-	for (unsigned int i = 0; i < obj->n_stringset; i++)
-		ethtool_stringset_put(nlh, ETHTOOL_A_STRINGSETS_STRINGSET, &obj->stringset[i]);
-	mnl_attr_nest_end(nlh, nest);
-
-	return 0;
-}
-
-int ethtool_stringsets_parse(struct ynl_parse_arg *yarg,
-			     const struct nlattr *nested)
-{
-	struct ethtool_stringsets *dst = yarg->data;
-	unsigned int n_stringset = 0;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	int i;
-
-	parg.ys = yarg->ys;
-
-	if (dst->stringset)
-		return ynl_error_parse(yarg, "attribute already present (stringsets.stringset)");
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_STRINGSETS_STRINGSET) {
-			n_stringset++;
-		}
-	}
-
-	if (n_stringset) {
-		dst->stringset = calloc(n_stringset, sizeof(*dst->stringset));
-		dst->n_stringset = n_stringset;
-		i = 0;
-		parg.rsp_policy = &ethtool_stringset_nest;
-		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == ETHTOOL_A_STRINGSETS_STRINGSET) {
-				parg.data = &dst->stringset[i];
-				if (ethtool_stringset_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-
-	return 0;
-}
-
-void ethtool_tunnel_udp_free(struct ethtool_tunnel_udp *obj)
-{
-	ethtool_tunnel_udp_table_free(&obj->table);
-}
-
-int ethtool_tunnel_udp_parse(struct ynl_parse_arg *yarg,
-			     const struct nlattr *nested)
-{
-	struct ethtool_tunnel_udp *dst = yarg->data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_TUNNEL_UDP_TABLE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.table = 1;
-
-			parg.rsp_policy = &ethtool_tunnel_udp_table_nest;
-			parg.data = &dst->table;
-			if (ethtool_tunnel_udp_table_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		}
-	}
-
-	return 0;
-}
-
-/* ============== ETHTOOL_MSG_STRSET_GET ============== */
-/* ETHTOOL_MSG_STRSET_GET - do */
-void ethtool_strset_get_req_free(struct ethtool_strset_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	ethtool_stringsets_free(&req->stringsets);
-	free(req);
-}
-
-void ethtool_strset_get_rsp_free(struct ethtool_strset_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	ethtool_stringsets_free(&rsp->stringsets);
-	free(rsp);
-}
-
-int ethtool_strset_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ethtool_strset_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_STRSET_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_STRSET_STRINGSETS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.stringsets = 1;
-
-			parg.rsp_policy = &ethtool_stringsets_nest;
-			parg.data = &dst->stringsets;
-			if (ethtool_stringsets_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_strset_get_rsp *
-ethtool_strset_get(struct ynl_sock *ys, struct ethtool_strset_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_strset_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_STRSET_GET, 1);
-	ys->req_policy = &ethtool_strset_nest;
-	yrs.yarg.rsp_policy = &ethtool_strset_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_STRSET_HEADER, &req->header);
-	if (req->_present.stringsets)
-		ethtool_stringsets_put(nlh, ETHTOOL_A_STRSET_STRINGSETS, &req->stringsets);
-	if (req->_present.counts_only)
-		mnl_attr_put(nlh, ETHTOOL_A_STRSET_COUNTS_ONLY, 0, NULL);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_strset_get_rsp_parse;
-	yrs.rsp_cmd = ETHTOOL_MSG_STRSET_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_strset_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_STRSET_GET - dump */
-void ethtool_strset_get_list_free(struct ethtool_strset_get_list *rsp)
-{
-	struct ethtool_strset_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		ethtool_stringsets_free(&rsp->obj.stringsets);
-		free(rsp);
-	}
-}
-
-struct ethtool_strset_get_list *
-ethtool_strset_get_dump(struct ynl_sock *ys,
-			struct ethtool_strset_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_strset_get_list);
-	yds.cb = ethtool_strset_get_rsp_parse;
-	yds.rsp_cmd = ETHTOOL_MSG_STRSET_GET;
-	yds.rsp_policy = &ethtool_strset_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_STRSET_GET, 1);
-	ys->req_policy = &ethtool_strset_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_STRSET_HEADER, &req->header);
-	if (req->_present.stringsets)
-		ethtool_stringsets_put(nlh, ETHTOOL_A_STRSET_STRINGSETS, &req->stringsets);
-	if (req->_present.counts_only)
-		mnl_attr_put(nlh, ETHTOOL_A_STRSET_COUNTS_ONLY, 0, NULL);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_strset_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== ETHTOOL_MSG_LINKINFO_GET ============== */
-/* ETHTOOL_MSG_LINKINFO_GET - do */
-void ethtool_linkinfo_get_req_free(struct ethtool_linkinfo_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_linkinfo_get_rsp_free(struct ethtool_linkinfo_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	free(rsp);
-}
-
-int ethtool_linkinfo_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ethtool_linkinfo_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_LINKINFO_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_LINKINFO_PORT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.port = 1;
-			dst->port = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_LINKINFO_PHYADDR) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.phyaddr = 1;
-			dst->phyaddr = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_LINKINFO_TP_MDIX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tp_mdix = 1;
-			dst->tp_mdix = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_LINKINFO_TP_MDIX_CTRL) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tp_mdix_ctrl = 1;
-			dst->tp_mdix_ctrl = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_LINKINFO_TRANSCEIVER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.transceiver = 1;
-			dst->transceiver = mnl_attr_get_u8(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_linkinfo_get_rsp *
-ethtool_linkinfo_get(struct ynl_sock *ys, struct ethtool_linkinfo_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_linkinfo_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_LINKINFO_GET, 1);
-	ys->req_policy = &ethtool_linkinfo_nest;
-	yrs.yarg.rsp_policy = &ethtool_linkinfo_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_LINKINFO_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_linkinfo_get_rsp_parse;
-	yrs.rsp_cmd = ETHTOOL_MSG_LINKINFO_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_linkinfo_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_LINKINFO_GET - dump */
-void ethtool_linkinfo_get_list_free(struct ethtool_linkinfo_get_list *rsp)
-{
-	struct ethtool_linkinfo_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		free(rsp);
-	}
-}
-
-struct ethtool_linkinfo_get_list *
-ethtool_linkinfo_get_dump(struct ynl_sock *ys,
-			  struct ethtool_linkinfo_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_linkinfo_get_list);
-	yds.cb = ethtool_linkinfo_get_rsp_parse;
-	yds.rsp_cmd = ETHTOOL_MSG_LINKINFO_GET;
-	yds.rsp_policy = &ethtool_linkinfo_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_LINKINFO_GET, 1);
-	ys->req_policy = &ethtool_linkinfo_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_LINKINFO_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_linkinfo_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_LINKINFO_GET - notify */
-void ethtool_linkinfo_get_ntf_free(struct ethtool_linkinfo_get_ntf *rsp)
-{
-	ethtool_header_free(&rsp->obj.header);
-	free(rsp);
-}
-
-/* ============== ETHTOOL_MSG_LINKINFO_SET ============== */
-/* ETHTOOL_MSG_LINKINFO_SET - do */
-void ethtool_linkinfo_set_req_free(struct ethtool_linkinfo_set_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-int ethtool_linkinfo_set(struct ynl_sock *ys,
-			 struct ethtool_linkinfo_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_LINKINFO_SET, 1);
-	ys->req_policy = &ethtool_linkinfo_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_LINKINFO_HEADER, &req->header);
-	if (req->_present.port)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_LINKINFO_PORT, req->port);
-	if (req->_present.phyaddr)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_LINKINFO_PHYADDR, req->phyaddr);
-	if (req->_present.tp_mdix)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_LINKINFO_TP_MDIX, req->tp_mdix);
-	if (req->_present.tp_mdix_ctrl)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_LINKINFO_TP_MDIX_CTRL, req->tp_mdix_ctrl);
-	if (req->_present.transceiver)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_LINKINFO_TRANSCEIVER, req->transceiver);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== ETHTOOL_MSG_LINKMODES_GET ============== */
-/* ETHTOOL_MSG_LINKMODES_GET - do */
-void ethtool_linkmodes_get_req_free(struct ethtool_linkmodes_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_linkmodes_get_rsp_free(struct ethtool_linkmodes_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	ethtool_bitset_free(&rsp->ours);
-	ethtool_bitset_free(&rsp->peer);
-	free(rsp);
-}
-
-int ethtool_linkmodes_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ethtool_linkmodes_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_LINKMODES_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_LINKMODES_AUTONEG) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.autoneg = 1;
-			dst->autoneg = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_LINKMODES_OURS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.ours = 1;
-
-			parg.rsp_policy = &ethtool_bitset_nest;
-			parg.data = &dst->ours;
-			if (ethtool_bitset_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_LINKMODES_PEER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.peer = 1;
-
-			parg.rsp_policy = &ethtool_bitset_nest;
-			parg.data = &dst->peer;
-			if (ethtool_bitset_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_LINKMODES_SPEED) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.speed = 1;
-			dst->speed = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_LINKMODES_DUPLEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.duplex = 1;
-			dst->duplex = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.master_slave_cfg = 1;
-			dst->master_slave_cfg = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.master_slave_state = 1;
-			dst->master_slave_state = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_LINKMODES_LANES) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.lanes = 1;
-			dst->lanes = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_LINKMODES_RATE_MATCHING) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rate_matching = 1;
-			dst->rate_matching = mnl_attr_get_u8(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_linkmodes_get_rsp *
-ethtool_linkmodes_get(struct ynl_sock *ys,
-		      struct ethtool_linkmodes_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_linkmodes_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_LINKMODES_GET, 1);
-	ys->req_policy = &ethtool_linkmodes_nest;
-	yrs.yarg.rsp_policy = &ethtool_linkmodes_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_LINKMODES_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_linkmodes_get_rsp_parse;
-	yrs.rsp_cmd = ETHTOOL_MSG_LINKMODES_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_linkmodes_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_LINKMODES_GET - dump */
-void ethtool_linkmodes_get_list_free(struct ethtool_linkmodes_get_list *rsp)
-{
-	struct ethtool_linkmodes_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		ethtool_bitset_free(&rsp->obj.ours);
-		ethtool_bitset_free(&rsp->obj.peer);
-		free(rsp);
-	}
-}
-
-struct ethtool_linkmodes_get_list *
-ethtool_linkmodes_get_dump(struct ynl_sock *ys,
-			   struct ethtool_linkmodes_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_linkmodes_get_list);
-	yds.cb = ethtool_linkmodes_get_rsp_parse;
-	yds.rsp_cmd = ETHTOOL_MSG_LINKMODES_GET;
-	yds.rsp_policy = &ethtool_linkmodes_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_LINKMODES_GET, 1);
-	ys->req_policy = &ethtool_linkmodes_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_LINKMODES_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_linkmodes_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_LINKMODES_GET - notify */
-void ethtool_linkmodes_get_ntf_free(struct ethtool_linkmodes_get_ntf *rsp)
-{
-	ethtool_header_free(&rsp->obj.header);
-	ethtool_bitset_free(&rsp->obj.ours);
-	ethtool_bitset_free(&rsp->obj.peer);
-	free(rsp);
-}
-
-/* ============== ETHTOOL_MSG_LINKMODES_SET ============== */
-/* ETHTOOL_MSG_LINKMODES_SET - do */
-void ethtool_linkmodes_set_req_free(struct ethtool_linkmodes_set_req *req)
-{
-	ethtool_header_free(&req->header);
-	ethtool_bitset_free(&req->ours);
-	ethtool_bitset_free(&req->peer);
-	free(req);
-}
-
-int ethtool_linkmodes_set(struct ynl_sock *ys,
-			  struct ethtool_linkmodes_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_LINKMODES_SET, 1);
-	ys->req_policy = &ethtool_linkmodes_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_LINKMODES_HEADER, &req->header);
-	if (req->_present.autoneg)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_LINKMODES_AUTONEG, req->autoneg);
-	if (req->_present.ours)
-		ethtool_bitset_put(nlh, ETHTOOL_A_LINKMODES_OURS, &req->ours);
-	if (req->_present.peer)
-		ethtool_bitset_put(nlh, ETHTOOL_A_LINKMODES_PEER, &req->peer);
-	if (req->_present.speed)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_LINKMODES_SPEED, req->speed);
-	if (req->_present.duplex)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_LINKMODES_DUPLEX, req->duplex);
-	if (req->_present.master_slave_cfg)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG, req->master_slave_cfg);
-	if (req->_present.master_slave_state)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE, req->master_slave_state);
-	if (req->_present.lanes)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_LINKMODES_LANES, req->lanes);
-	if (req->_present.rate_matching)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_LINKMODES_RATE_MATCHING, req->rate_matching);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== ETHTOOL_MSG_LINKSTATE_GET ============== */
-/* ETHTOOL_MSG_LINKSTATE_GET - do */
-void ethtool_linkstate_get_req_free(struct ethtool_linkstate_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_linkstate_get_rsp_free(struct ethtool_linkstate_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	free(rsp);
-}
-
-int ethtool_linkstate_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ethtool_linkstate_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_LINKSTATE_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_LINKSTATE_LINK) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.link = 1;
-			dst->link = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_LINKSTATE_SQI) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.sqi = 1;
-			dst->sqi = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_LINKSTATE_SQI_MAX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.sqi_max = 1;
-			dst->sqi_max = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_LINKSTATE_EXT_STATE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.ext_state = 1;
-			dst->ext_state = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_LINKSTATE_EXT_SUBSTATE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.ext_substate = 1;
-			dst->ext_substate = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_LINKSTATE_EXT_DOWN_CNT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.ext_down_cnt = 1;
-			dst->ext_down_cnt = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_linkstate_get_rsp *
-ethtool_linkstate_get(struct ynl_sock *ys,
-		      struct ethtool_linkstate_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_linkstate_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_LINKSTATE_GET, 1);
-	ys->req_policy = &ethtool_linkstate_nest;
-	yrs.yarg.rsp_policy = &ethtool_linkstate_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_LINKSTATE_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_linkstate_get_rsp_parse;
-	yrs.rsp_cmd = ETHTOOL_MSG_LINKSTATE_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_linkstate_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_LINKSTATE_GET - dump */
-void ethtool_linkstate_get_list_free(struct ethtool_linkstate_get_list *rsp)
-{
-	struct ethtool_linkstate_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		free(rsp);
-	}
-}
-
-struct ethtool_linkstate_get_list *
-ethtool_linkstate_get_dump(struct ynl_sock *ys,
-			   struct ethtool_linkstate_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_linkstate_get_list);
-	yds.cb = ethtool_linkstate_get_rsp_parse;
-	yds.rsp_cmd = ETHTOOL_MSG_LINKSTATE_GET;
-	yds.rsp_policy = &ethtool_linkstate_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_LINKSTATE_GET, 1);
-	ys->req_policy = &ethtool_linkstate_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_LINKSTATE_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_linkstate_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== ETHTOOL_MSG_DEBUG_GET ============== */
-/* ETHTOOL_MSG_DEBUG_GET - do */
-void ethtool_debug_get_req_free(struct ethtool_debug_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_debug_get_rsp_free(struct ethtool_debug_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	ethtool_bitset_free(&rsp->msgmask);
-	free(rsp);
-}
-
-int ethtool_debug_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ethtool_debug_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_DEBUG_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_DEBUG_MSGMASK) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.msgmask = 1;
-
-			parg.rsp_policy = &ethtool_bitset_nest;
-			parg.data = &dst->msgmask;
-			if (ethtool_bitset_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_debug_get_rsp *
-ethtool_debug_get(struct ynl_sock *ys, struct ethtool_debug_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_debug_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_DEBUG_GET, 1);
-	ys->req_policy = &ethtool_debug_nest;
-	yrs.yarg.rsp_policy = &ethtool_debug_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_DEBUG_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_debug_get_rsp_parse;
-	yrs.rsp_cmd = ETHTOOL_MSG_DEBUG_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_debug_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_DEBUG_GET - dump */
-void ethtool_debug_get_list_free(struct ethtool_debug_get_list *rsp)
-{
-	struct ethtool_debug_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		ethtool_bitset_free(&rsp->obj.msgmask);
-		free(rsp);
-	}
-}
-
-struct ethtool_debug_get_list *
-ethtool_debug_get_dump(struct ynl_sock *ys,
-		       struct ethtool_debug_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_debug_get_list);
-	yds.cb = ethtool_debug_get_rsp_parse;
-	yds.rsp_cmd = ETHTOOL_MSG_DEBUG_GET;
-	yds.rsp_policy = &ethtool_debug_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_DEBUG_GET, 1);
-	ys->req_policy = &ethtool_debug_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_DEBUG_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_debug_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_DEBUG_GET - notify */
-void ethtool_debug_get_ntf_free(struct ethtool_debug_get_ntf *rsp)
-{
-	ethtool_header_free(&rsp->obj.header);
-	ethtool_bitset_free(&rsp->obj.msgmask);
-	free(rsp);
-}
-
-/* ============== ETHTOOL_MSG_DEBUG_SET ============== */
-/* ETHTOOL_MSG_DEBUG_SET - do */
-void ethtool_debug_set_req_free(struct ethtool_debug_set_req *req)
-{
-	ethtool_header_free(&req->header);
-	ethtool_bitset_free(&req->msgmask);
-	free(req);
-}
-
-int ethtool_debug_set(struct ynl_sock *ys, struct ethtool_debug_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_DEBUG_SET, 1);
-	ys->req_policy = &ethtool_debug_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_DEBUG_HEADER, &req->header);
-	if (req->_present.msgmask)
-		ethtool_bitset_put(nlh, ETHTOOL_A_DEBUG_MSGMASK, &req->msgmask);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== ETHTOOL_MSG_WOL_GET ============== */
-/* ETHTOOL_MSG_WOL_GET - do */
-void ethtool_wol_get_req_free(struct ethtool_wol_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_wol_get_rsp_free(struct ethtool_wol_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	ethtool_bitset_free(&rsp->modes);
-	free(rsp->sopass);
-	free(rsp);
-}
-
-int ethtool_wol_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ynl_parse_arg *yarg = data;
-	struct ethtool_wol_get_rsp *dst;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_WOL_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_WOL_MODES) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.modes = 1;
-
-			parg.rsp_policy = &ethtool_bitset_nest;
-			parg.data = &dst->modes;
-			if (ethtool_bitset_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_WOL_SOPASS) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = mnl_attr_get_payload_len(attr);
-			dst->_present.sopass_len = len;
-			dst->sopass = malloc(len);
-			memcpy(dst->sopass, mnl_attr_get_payload(attr), len);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_wol_get_rsp *
-ethtool_wol_get(struct ynl_sock *ys, struct ethtool_wol_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_wol_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_WOL_GET, 1);
-	ys->req_policy = &ethtool_wol_nest;
-	yrs.yarg.rsp_policy = &ethtool_wol_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_WOL_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_wol_get_rsp_parse;
-	yrs.rsp_cmd = ETHTOOL_MSG_WOL_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_wol_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_WOL_GET - dump */
-void ethtool_wol_get_list_free(struct ethtool_wol_get_list *rsp)
-{
-	struct ethtool_wol_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		ethtool_bitset_free(&rsp->obj.modes);
-		free(rsp->obj.sopass);
-		free(rsp);
-	}
-}
-
-struct ethtool_wol_get_list *
-ethtool_wol_get_dump(struct ynl_sock *ys, struct ethtool_wol_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_wol_get_list);
-	yds.cb = ethtool_wol_get_rsp_parse;
-	yds.rsp_cmd = ETHTOOL_MSG_WOL_GET;
-	yds.rsp_policy = &ethtool_wol_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_WOL_GET, 1);
-	ys->req_policy = &ethtool_wol_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_WOL_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_wol_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_WOL_GET - notify */
-void ethtool_wol_get_ntf_free(struct ethtool_wol_get_ntf *rsp)
-{
-	ethtool_header_free(&rsp->obj.header);
-	ethtool_bitset_free(&rsp->obj.modes);
-	free(rsp->obj.sopass);
-	free(rsp);
-}
-
-/* ============== ETHTOOL_MSG_WOL_SET ============== */
-/* ETHTOOL_MSG_WOL_SET - do */
-void ethtool_wol_set_req_free(struct ethtool_wol_set_req *req)
-{
-	ethtool_header_free(&req->header);
-	ethtool_bitset_free(&req->modes);
-	free(req->sopass);
-	free(req);
-}
-
-int ethtool_wol_set(struct ynl_sock *ys, struct ethtool_wol_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_WOL_SET, 1);
-	ys->req_policy = &ethtool_wol_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_WOL_HEADER, &req->header);
-	if (req->_present.modes)
-		ethtool_bitset_put(nlh, ETHTOOL_A_WOL_MODES, &req->modes);
-	if (req->_present.sopass_len)
-		mnl_attr_put(nlh, ETHTOOL_A_WOL_SOPASS, req->_present.sopass_len, req->sopass);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== ETHTOOL_MSG_FEATURES_GET ============== */
-/* ETHTOOL_MSG_FEATURES_GET - do */
-void ethtool_features_get_req_free(struct ethtool_features_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_features_get_rsp_free(struct ethtool_features_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	ethtool_bitset_free(&rsp->hw);
-	ethtool_bitset_free(&rsp->wanted);
-	ethtool_bitset_free(&rsp->active);
-	ethtool_bitset_free(&rsp->nochange);
-	free(rsp);
-}
-
-int ethtool_features_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ethtool_features_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_FEATURES_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_FEATURES_HW) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.hw = 1;
-
-			parg.rsp_policy = &ethtool_bitset_nest;
-			parg.data = &dst->hw;
-			if (ethtool_bitset_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_FEATURES_WANTED) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.wanted = 1;
-
-			parg.rsp_policy = &ethtool_bitset_nest;
-			parg.data = &dst->wanted;
-			if (ethtool_bitset_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_FEATURES_ACTIVE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.active = 1;
-
-			parg.rsp_policy = &ethtool_bitset_nest;
-			parg.data = &dst->active;
-			if (ethtool_bitset_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_FEATURES_NOCHANGE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.nochange = 1;
-
-			parg.rsp_policy = &ethtool_bitset_nest;
-			parg.data = &dst->nochange;
-			if (ethtool_bitset_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_features_get_rsp *
-ethtool_features_get(struct ynl_sock *ys, struct ethtool_features_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_features_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_FEATURES_GET, 1);
-	ys->req_policy = &ethtool_features_nest;
-	yrs.yarg.rsp_policy = &ethtool_features_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_FEATURES_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_features_get_rsp_parse;
-	yrs.rsp_cmd = ETHTOOL_MSG_FEATURES_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_features_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_FEATURES_GET - dump */
-void ethtool_features_get_list_free(struct ethtool_features_get_list *rsp)
-{
-	struct ethtool_features_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		ethtool_bitset_free(&rsp->obj.hw);
-		ethtool_bitset_free(&rsp->obj.wanted);
-		ethtool_bitset_free(&rsp->obj.active);
-		ethtool_bitset_free(&rsp->obj.nochange);
-		free(rsp);
-	}
-}
-
-struct ethtool_features_get_list *
-ethtool_features_get_dump(struct ynl_sock *ys,
-			  struct ethtool_features_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_features_get_list);
-	yds.cb = ethtool_features_get_rsp_parse;
-	yds.rsp_cmd = ETHTOOL_MSG_FEATURES_GET;
-	yds.rsp_policy = &ethtool_features_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_FEATURES_GET, 1);
-	ys->req_policy = &ethtool_features_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_FEATURES_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_features_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_FEATURES_GET - notify */
-void ethtool_features_get_ntf_free(struct ethtool_features_get_ntf *rsp)
-{
-	ethtool_header_free(&rsp->obj.header);
-	ethtool_bitset_free(&rsp->obj.hw);
-	ethtool_bitset_free(&rsp->obj.wanted);
-	ethtool_bitset_free(&rsp->obj.active);
-	ethtool_bitset_free(&rsp->obj.nochange);
-	free(rsp);
-}
-
-/* ============== ETHTOOL_MSG_FEATURES_SET ============== */
-/* ETHTOOL_MSG_FEATURES_SET - do */
-void ethtool_features_set_req_free(struct ethtool_features_set_req *req)
-{
-	ethtool_header_free(&req->header);
-	ethtool_bitset_free(&req->hw);
-	ethtool_bitset_free(&req->wanted);
-	ethtool_bitset_free(&req->active);
-	ethtool_bitset_free(&req->nochange);
-	free(req);
-}
-
-void ethtool_features_set_rsp_free(struct ethtool_features_set_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	ethtool_bitset_free(&rsp->hw);
-	ethtool_bitset_free(&rsp->wanted);
-	ethtool_bitset_free(&rsp->active);
-	ethtool_bitset_free(&rsp->nochange);
-	free(rsp);
-}
-
-int ethtool_features_set_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ethtool_features_set_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_FEATURES_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_FEATURES_HW) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.hw = 1;
-
-			parg.rsp_policy = &ethtool_bitset_nest;
-			parg.data = &dst->hw;
-			if (ethtool_bitset_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_FEATURES_WANTED) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.wanted = 1;
-
-			parg.rsp_policy = &ethtool_bitset_nest;
-			parg.data = &dst->wanted;
-			if (ethtool_bitset_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_FEATURES_ACTIVE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.active = 1;
-
-			parg.rsp_policy = &ethtool_bitset_nest;
-			parg.data = &dst->active;
-			if (ethtool_bitset_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_FEATURES_NOCHANGE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.nochange = 1;
-
-			parg.rsp_policy = &ethtool_bitset_nest;
-			parg.data = &dst->nochange;
-			if (ethtool_bitset_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_features_set_rsp *
-ethtool_features_set(struct ynl_sock *ys, struct ethtool_features_set_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_features_set_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_FEATURES_SET, 1);
-	ys->req_policy = &ethtool_features_nest;
-	yrs.yarg.rsp_policy = &ethtool_features_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_FEATURES_HEADER, &req->header);
-	if (req->_present.hw)
-		ethtool_bitset_put(nlh, ETHTOOL_A_FEATURES_HW, &req->hw);
-	if (req->_present.wanted)
-		ethtool_bitset_put(nlh, ETHTOOL_A_FEATURES_WANTED, &req->wanted);
-	if (req->_present.active)
-		ethtool_bitset_put(nlh, ETHTOOL_A_FEATURES_ACTIVE, &req->active);
-	if (req->_present.nochange)
-		ethtool_bitset_put(nlh, ETHTOOL_A_FEATURES_NOCHANGE, &req->nochange);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_features_set_rsp_parse;
-	yrs.rsp_cmd = ETHTOOL_MSG_FEATURES_SET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_features_set_rsp_free(rsp);
-	return NULL;
-}
-
-/* ============== ETHTOOL_MSG_PRIVFLAGS_GET ============== */
-/* ETHTOOL_MSG_PRIVFLAGS_GET - do */
-void ethtool_privflags_get_req_free(struct ethtool_privflags_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_privflags_get_rsp_free(struct ethtool_privflags_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	ethtool_bitset_free(&rsp->flags);
-	free(rsp);
-}
-
-int ethtool_privflags_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ethtool_privflags_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_PRIVFLAGS_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_PRIVFLAGS_FLAGS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.flags = 1;
-
-			parg.rsp_policy = &ethtool_bitset_nest;
-			parg.data = &dst->flags;
-			if (ethtool_bitset_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_privflags_get_rsp *
-ethtool_privflags_get(struct ynl_sock *ys,
-		      struct ethtool_privflags_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_privflags_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_PRIVFLAGS_GET, 1);
-	ys->req_policy = &ethtool_privflags_nest;
-	yrs.yarg.rsp_policy = &ethtool_privflags_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_PRIVFLAGS_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_privflags_get_rsp_parse;
-	yrs.rsp_cmd = 14;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_privflags_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_PRIVFLAGS_GET - dump */
-void ethtool_privflags_get_list_free(struct ethtool_privflags_get_list *rsp)
-{
-	struct ethtool_privflags_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		ethtool_bitset_free(&rsp->obj.flags);
-		free(rsp);
-	}
-}
-
-struct ethtool_privflags_get_list *
-ethtool_privflags_get_dump(struct ynl_sock *ys,
-			   struct ethtool_privflags_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_privflags_get_list);
-	yds.cb = ethtool_privflags_get_rsp_parse;
-	yds.rsp_cmd = 14;
-	yds.rsp_policy = &ethtool_privflags_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_PRIVFLAGS_GET, 1);
-	ys->req_policy = &ethtool_privflags_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_PRIVFLAGS_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_privflags_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_PRIVFLAGS_GET - notify */
-void ethtool_privflags_get_ntf_free(struct ethtool_privflags_get_ntf *rsp)
-{
-	ethtool_header_free(&rsp->obj.header);
-	ethtool_bitset_free(&rsp->obj.flags);
-	free(rsp);
-}
-
-/* ============== ETHTOOL_MSG_PRIVFLAGS_SET ============== */
-/* ETHTOOL_MSG_PRIVFLAGS_SET - do */
-void ethtool_privflags_set_req_free(struct ethtool_privflags_set_req *req)
-{
-	ethtool_header_free(&req->header);
-	ethtool_bitset_free(&req->flags);
-	free(req);
-}
-
-int ethtool_privflags_set(struct ynl_sock *ys,
-			  struct ethtool_privflags_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_PRIVFLAGS_SET, 1);
-	ys->req_policy = &ethtool_privflags_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_PRIVFLAGS_HEADER, &req->header);
-	if (req->_present.flags)
-		ethtool_bitset_put(nlh, ETHTOOL_A_PRIVFLAGS_FLAGS, &req->flags);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== ETHTOOL_MSG_RINGS_GET ============== */
-/* ETHTOOL_MSG_RINGS_GET - do */
-void ethtool_rings_get_req_free(struct ethtool_rings_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_rings_get_rsp_free(struct ethtool_rings_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	free(rsp);
-}
-
-int ethtool_rings_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ethtool_rings_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_RINGS_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_RINGS_RX_MAX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx_max = 1;
-			dst->rx_max = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_RINGS_RX_MINI_MAX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx_mini_max = 1;
-			dst->rx_mini_max = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_RINGS_RX_JUMBO_MAX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx_jumbo_max = 1;
-			dst->rx_jumbo_max = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_RINGS_TX_MAX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_max = 1;
-			dst->tx_max = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_RINGS_RX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx = 1;
-			dst->rx = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_RINGS_RX_MINI) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx_mini = 1;
-			dst->rx_mini = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_RINGS_RX_JUMBO) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx_jumbo = 1;
-			dst->rx_jumbo = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_RINGS_TX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx = 1;
-			dst->tx = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_RINGS_RX_BUF_LEN) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx_buf_len = 1;
-			dst->rx_buf_len = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_RINGS_TCP_DATA_SPLIT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tcp_data_split = 1;
-			dst->tcp_data_split = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_RINGS_CQE_SIZE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.cqe_size = 1;
-			dst->cqe_size = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_RINGS_TX_PUSH) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_push = 1;
-			dst->tx_push = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_RINGS_RX_PUSH) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx_push = 1;
-			dst->rx_push = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_push_buf_len = 1;
-			dst->tx_push_buf_len = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN_MAX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_push_buf_len_max = 1;
-			dst->tx_push_buf_len_max = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_rings_get_rsp *
-ethtool_rings_get(struct ynl_sock *ys, struct ethtool_rings_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_rings_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_RINGS_GET, 1);
-	ys->req_policy = &ethtool_rings_nest;
-	yrs.yarg.rsp_policy = &ethtool_rings_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_RINGS_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_rings_get_rsp_parse;
-	yrs.rsp_cmd = 16;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_rings_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_RINGS_GET - dump */
-void ethtool_rings_get_list_free(struct ethtool_rings_get_list *rsp)
-{
-	struct ethtool_rings_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		free(rsp);
-	}
-}
-
-struct ethtool_rings_get_list *
-ethtool_rings_get_dump(struct ynl_sock *ys,
-		       struct ethtool_rings_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_rings_get_list);
-	yds.cb = ethtool_rings_get_rsp_parse;
-	yds.rsp_cmd = 16;
-	yds.rsp_policy = &ethtool_rings_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_RINGS_GET, 1);
-	ys->req_policy = &ethtool_rings_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_RINGS_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_rings_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_RINGS_GET - notify */
-void ethtool_rings_get_ntf_free(struct ethtool_rings_get_ntf *rsp)
-{
-	ethtool_header_free(&rsp->obj.header);
-	free(rsp);
-}
-
-/* ============== ETHTOOL_MSG_RINGS_SET ============== */
-/* ETHTOOL_MSG_RINGS_SET - do */
-void ethtool_rings_set_req_free(struct ethtool_rings_set_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-int ethtool_rings_set(struct ynl_sock *ys, struct ethtool_rings_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_RINGS_SET, 1);
-	ys->req_policy = &ethtool_rings_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_RINGS_HEADER, &req->header);
-	if (req->_present.rx_max)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_RX_MAX, req->rx_max);
-	if (req->_present.rx_mini_max)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_RX_MINI_MAX, req->rx_mini_max);
-	if (req->_present.rx_jumbo_max)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_RX_JUMBO_MAX, req->rx_jumbo_max);
-	if (req->_present.tx_max)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_TX_MAX, req->tx_max);
-	if (req->_present.rx)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_RX, req->rx);
-	if (req->_present.rx_mini)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_RX_MINI, req->rx_mini);
-	if (req->_present.rx_jumbo)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_RX_JUMBO, req->rx_jumbo);
-	if (req->_present.tx)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_TX, req->tx);
-	if (req->_present.rx_buf_len)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_RX_BUF_LEN, req->rx_buf_len);
-	if (req->_present.tcp_data_split)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_RINGS_TCP_DATA_SPLIT, req->tcp_data_split);
-	if (req->_present.cqe_size)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_CQE_SIZE, req->cqe_size);
-	if (req->_present.tx_push)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_RINGS_TX_PUSH, req->tx_push);
-	if (req->_present.rx_push)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_RINGS_RX_PUSH, req->rx_push);
-	if (req->_present.tx_push_buf_len)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN, req->tx_push_buf_len);
-	if (req->_present.tx_push_buf_len_max)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN_MAX, req->tx_push_buf_len_max);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== ETHTOOL_MSG_CHANNELS_GET ============== */
-/* ETHTOOL_MSG_CHANNELS_GET - do */
-void ethtool_channels_get_req_free(struct ethtool_channels_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_channels_get_rsp_free(struct ethtool_channels_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	free(rsp);
-}
-
-int ethtool_channels_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ethtool_channels_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_CHANNELS_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_CHANNELS_RX_MAX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx_max = 1;
-			dst->rx_max = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_CHANNELS_TX_MAX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_max = 1;
-			dst->tx_max = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_CHANNELS_OTHER_MAX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.other_max = 1;
-			dst->other_max = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_CHANNELS_COMBINED_MAX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.combined_max = 1;
-			dst->combined_max = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_CHANNELS_RX_COUNT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx_count = 1;
-			dst->rx_count = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_CHANNELS_TX_COUNT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_count = 1;
-			dst->tx_count = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_CHANNELS_OTHER_COUNT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.other_count = 1;
-			dst->other_count = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_CHANNELS_COMBINED_COUNT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.combined_count = 1;
-			dst->combined_count = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_channels_get_rsp *
-ethtool_channels_get(struct ynl_sock *ys, struct ethtool_channels_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_channels_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_CHANNELS_GET, 1);
-	ys->req_policy = &ethtool_channels_nest;
-	yrs.yarg.rsp_policy = &ethtool_channels_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_CHANNELS_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_channels_get_rsp_parse;
-	yrs.rsp_cmd = 18;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_channels_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_CHANNELS_GET - dump */
-void ethtool_channels_get_list_free(struct ethtool_channels_get_list *rsp)
-{
-	struct ethtool_channels_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		free(rsp);
-	}
-}
-
-struct ethtool_channels_get_list *
-ethtool_channels_get_dump(struct ynl_sock *ys,
-			  struct ethtool_channels_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_channels_get_list);
-	yds.cb = ethtool_channels_get_rsp_parse;
-	yds.rsp_cmd = 18;
-	yds.rsp_policy = &ethtool_channels_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_CHANNELS_GET, 1);
-	ys->req_policy = &ethtool_channels_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_CHANNELS_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_channels_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_CHANNELS_GET - notify */
-void ethtool_channels_get_ntf_free(struct ethtool_channels_get_ntf *rsp)
-{
-	ethtool_header_free(&rsp->obj.header);
-	free(rsp);
-}
-
-/* ============== ETHTOOL_MSG_CHANNELS_SET ============== */
-/* ETHTOOL_MSG_CHANNELS_SET - do */
-void ethtool_channels_set_req_free(struct ethtool_channels_set_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-int ethtool_channels_set(struct ynl_sock *ys,
-			 struct ethtool_channels_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_CHANNELS_SET, 1);
-	ys->req_policy = &ethtool_channels_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_CHANNELS_HEADER, &req->header);
-	if (req->_present.rx_max)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_CHANNELS_RX_MAX, req->rx_max);
-	if (req->_present.tx_max)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_CHANNELS_TX_MAX, req->tx_max);
-	if (req->_present.other_max)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_CHANNELS_OTHER_MAX, req->other_max);
-	if (req->_present.combined_max)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_CHANNELS_COMBINED_MAX, req->combined_max);
-	if (req->_present.rx_count)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_CHANNELS_RX_COUNT, req->rx_count);
-	if (req->_present.tx_count)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_CHANNELS_TX_COUNT, req->tx_count);
-	if (req->_present.other_count)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_CHANNELS_OTHER_COUNT, req->other_count);
-	if (req->_present.combined_count)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_CHANNELS_COMBINED_COUNT, req->combined_count);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== ETHTOOL_MSG_COALESCE_GET ============== */
-/* ETHTOOL_MSG_COALESCE_GET - do */
-void ethtool_coalesce_get_req_free(struct ethtool_coalesce_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_coalesce_get_rsp_free(struct ethtool_coalesce_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	free(rsp);
-}
-
-int ethtool_coalesce_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ethtool_coalesce_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_COALESCE_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_COALESCE_RX_USECS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx_usecs = 1;
-			dst->rx_usecs = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_RX_MAX_FRAMES) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx_max_frames = 1;
-			dst->rx_max_frames = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_RX_USECS_IRQ) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx_usecs_irq = 1;
-			dst->rx_usecs_irq = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx_max_frames_irq = 1;
-			dst->rx_max_frames_irq = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_TX_USECS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_usecs = 1;
-			dst->tx_usecs = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_TX_MAX_FRAMES) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_max_frames = 1;
-			dst->tx_max_frames = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_TX_USECS_IRQ) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_usecs_irq = 1;
-			dst->tx_usecs_irq = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_max_frames_irq = 1;
-			dst->tx_max_frames_irq = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_STATS_BLOCK_USECS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.stats_block_usecs = 1;
-			dst->stats_block_usecs = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.use_adaptive_rx = 1;
-			dst->use_adaptive_rx = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.use_adaptive_tx = 1;
-			dst->use_adaptive_tx = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_COALESCE_PKT_RATE_LOW) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.pkt_rate_low = 1;
-			dst->pkt_rate_low = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_RX_USECS_LOW) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx_usecs_low = 1;
-			dst->rx_usecs_low = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx_max_frames_low = 1;
-			dst->rx_max_frames_low = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_TX_USECS_LOW) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_usecs_low = 1;
-			dst->tx_usecs_low = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_max_frames_low = 1;
-			dst->tx_max_frames_low = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_PKT_RATE_HIGH) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.pkt_rate_high = 1;
-			dst->pkt_rate_high = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_RX_USECS_HIGH) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx_usecs_high = 1;
-			dst->rx_usecs_high = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx_max_frames_high = 1;
-			dst->rx_max_frames_high = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_TX_USECS_HIGH) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_usecs_high = 1;
-			dst->tx_usecs_high = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_max_frames_high = 1;
-			dst->tx_max_frames_high = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rate_sample_interval = 1;
-			dst->rate_sample_interval = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_USE_CQE_MODE_TX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.use_cqe_mode_tx = 1;
-			dst->use_cqe_mode_tx = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_COALESCE_USE_CQE_MODE_RX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.use_cqe_mode_rx = 1;
-			dst->use_cqe_mode_rx = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_aggr_max_bytes = 1;
-			dst->tx_aggr_max_bytes = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_aggr_max_frames = 1;
-			dst->tx_aggr_max_frames = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_aggr_time_usecs = 1;
-			dst->tx_aggr_time_usecs = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_coalesce_get_rsp *
-ethtool_coalesce_get(struct ynl_sock *ys, struct ethtool_coalesce_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_coalesce_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_COALESCE_GET, 1);
-	ys->req_policy = &ethtool_coalesce_nest;
-	yrs.yarg.rsp_policy = &ethtool_coalesce_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_COALESCE_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_coalesce_get_rsp_parse;
-	yrs.rsp_cmd = 20;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_coalesce_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_COALESCE_GET - dump */
-void ethtool_coalesce_get_list_free(struct ethtool_coalesce_get_list *rsp)
-{
-	struct ethtool_coalesce_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		free(rsp);
-	}
-}
-
-struct ethtool_coalesce_get_list *
-ethtool_coalesce_get_dump(struct ynl_sock *ys,
-			  struct ethtool_coalesce_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_coalesce_get_list);
-	yds.cb = ethtool_coalesce_get_rsp_parse;
-	yds.rsp_cmd = 20;
-	yds.rsp_policy = &ethtool_coalesce_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_COALESCE_GET, 1);
-	ys->req_policy = &ethtool_coalesce_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_COALESCE_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_coalesce_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_COALESCE_GET - notify */
-void ethtool_coalesce_get_ntf_free(struct ethtool_coalesce_get_ntf *rsp)
-{
-	ethtool_header_free(&rsp->obj.header);
-	free(rsp);
-}
-
-/* ============== ETHTOOL_MSG_COALESCE_SET ============== */
-/* ETHTOOL_MSG_COALESCE_SET - do */
-void ethtool_coalesce_set_req_free(struct ethtool_coalesce_set_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-int ethtool_coalesce_set(struct ynl_sock *ys,
-			 struct ethtool_coalesce_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_COALESCE_SET, 1);
-	ys->req_policy = &ethtool_coalesce_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_COALESCE_HEADER, &req->header);
-	if (req->_present.rx_usecs)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_RX_USECS, req->rx_usecs);
-	if (req->_present.rx_max_frames)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_RX_MAX_FRAMES, req->rx_max_frames);
-	if (req->_present.rx_usecs_irq)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_RX_USECS_IRQ, req->rx_usecs_irq);
-	if (req->_present.rx_max_frames_irq)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ, req->rx_max_frames_irq);
-	if (req->_present.tx_usecs)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_USECS, req->tx_usecs);
-	if (req->_present.tx_max_frames)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_MAX_FRAMES, req->tx_max_frames);
-	if (req->_present.tx_usecs_irq)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_USECS_IRQ, req->tx_usecs_irq);
-	if (req->_present.tx_max_frames_irq)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ, req->tx_max_frames_irq);
-	if (req->_present.stats_block_usecs)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_STATS_BLOCK_USECS, req->stats_block_usecs);
-	if (req->_present.use_adaptive_rx)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX, req->use_adaptive_rx);
-	if (req->_present.use_adaptive_tx)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX, req->use_adaptive_tx);
-	if (req->_present.pkt_rate_low)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_PKT_RATE_LOW, req->pkt_rate_low);
-	if (req->_present.rx_usecs_low)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_RX_USECS_LOW, req->rx_usecs_low);
-	if (req->_present.rx_max_frames_low)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW, req->rx_max_frames_low);
-	if (req->_present.tx_usecs_low)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_USECS_LOW, req->tx_usecs_low);
-	if (req->_present.tx_max_frames_low)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW, req->tx_max_frames_low);
-	if (req->_present.pkt_rate_high)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_PKT_RATE_HIGH, req->pkt_rate_high);
-	if (req->_present.rx_usecs_high)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_RX_USECS_HIGH, req->rx_usecs_high);
-	if (req->_present.rx_max_frames_high)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH, req->rx_max_frames_high);
-	if (req->_present.tx_usecs_high)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_USECS_HIGH, req->tx_usecs_high);
-	if (req->_present.tx_max_frames_high)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH, req->tx_max_frames_high);
-	if (req->_present.rate_sample_interval)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL, req->rate_sample_interval);
-	if (req->_present.use_cqe_mode_tx)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_COALESCE_USE_CQE_MODE_TX, req->use_cqe_mode_tx);
-	if (req->_present.use_cqe_mode_rx)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_COALESCE_USE_CQE_MODE_RX, req->use_cqe_mode_rx);
-	if (req->_present.tx_aggr_max_bytes)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES, req->tx_aggr_max_bytes);
-	if (req->_present.tx_aggr_max_frames)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES, req->tx_aggr_max_frames);
-	if (req->_present.tx_aggr_time_usecs)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS, req->tx_aggr_time_usecs);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== ETHTOOL_MSG_PAUSE_GET ============== */
-/* ETHTOOL_MSG_PAUSE_GET - do */
-void ethtool_pause_get_req_free(struct ethtool_pause_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_pause_get_rsp_free(struct ethtool_pause_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	ethtool_pause_stat_free(&rsp->stats);
-	free(rsp);
-}
-
-int ethtool_pause_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ethtool_pause_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_PAUSE_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_PAUSE_AUTONEG) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.autoneg = 1;
-			dst->autoneg = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_PAUSE_RX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx = 1;
-			dst->rx = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_PAUSE_TX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx = 1;
-			dst->tx = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_PAUSE_STATS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.stats = 1;
-
-			parg.rsp_policy = &ethtool_pause_stat_nest;
-			parg.data = &dst->stats;
-			if (ethtool_pause_stat_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_PAUSE_STATS_SRC) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.stats_src = 1;
-			dst->stats_src = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_pause_get_rsp *
-ethtool_pause_get(struct ynl_sock *ys, struct ethtool_pause_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_pause_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_PAUSE_GET, 1);
-	ys->req_policy = &ethtool_pause_nest;
-	yrs.yarg.rsp_policy = &ethtool_pause_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_PAUSE_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_pause_get_rsp_parse;
-	yrs.rsp_cmd = 22;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_pause_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_PAUSE_GET - dump */
-void ethtool_pause_get_list_free(struct ethtool_pause_get_list *rsp)
-{
-	struct ethtool_pause_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		ethtool_pause_stat_free(&rsp->obj.stats);
-		free(rsp);
-	}
-}
-
-struct ethtool_pause_get_list *
-ethtool_pause_get_dump(struct ynl_sock *ys,
-		       struct ethtool_pause_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_pause_get_list);
-	yds.cb = ethtool_pause_get_rsp_parse;
-	yds.rsp_cmd = 22;
-	yds.rsp_policy = &ethtool_pause_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_PAUSE_GET, 1);
-	ys->req_policy = &ethtool_pause_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_PAUSE_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_pause_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_PAUSE_GET - notify */
-void ethtool_pause_get_ntf_free(struct ethtool_pause_get_ntf *rsp)
-{
-	ethtool_header_free(&rsp->obj.header);
-	ethtool_pause_stat_free(&rsp->obj.stats);
-	free(rsp);
-}
-
-/* ============== ETHTOOL_MSG_PAUSE_SET ============== */
-/* ETHTOOL_MSG_PAUSE_SET - do */
-void ethtool_pause_set_req_free(struct ethtool_pause_set_req *req)
-{
-	ethtool_header_free(&req->header);
-	ethtool_pause_stat_free(&req->stats);
-	free(req);
-}
-
-int ethtool_pause_set(struct ynl_sock *ys, struct ethtool_pause_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_PAUSE_SET, 1);
-	ys->req_policy = &ethtool_pause_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_PAUSE_HEADER, &req->header);
-	if (req->_present.autoneg)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_PAUSE_AUTONEG, req->autoneg);
-	if (req->_present.rx)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_PAUSE_RX, req->rx);
-	if (req->_present.tx)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_PAUSE_TX, req->tx);
-	if (req->_present.stats)
-		ethtool_pause_stat_put(nlh, ETHTOOL_A_PAUSE_STATS, &req->stats);
-	if (req->_present.stats_src)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_PAUSE_STATS_SRC, req->stats_src);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== ETHTOOL_MSG_EEE_GET ============== */
-/* ETHTOOL_MSG_EEE_GET - do */
-void ethtool_eee_get_req_free(struct ethtool_eee_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_eee_get_rsp_free(struct ethtool_eee_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	ethtool_bitset_free(&rsp->modes_ours);
-	ethtool_bitset_free(&rsp->modes_peer);
-	free(rsp);
-}
-
-int ethtool_eee_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ynl_parse_arg *yarg = data;
-	struct ethtool_eee_get_rsp *dst;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_EEE_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_EEE_MODES_OURS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.modes_ours = 1;
-
-			parg.rsp_policy = &ethtool_bitset_nest;
-			parg.data = &dst->modes_ours;
-			if (ethtool_bitset_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_EEE_MODES_PEER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.modes_peer = 1;
-
-			parg.rsp_policy = &ethtool_bitset_nest;
-			parg.data = &dst->modes_peer;
-			if (ethtool_bitset_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_EEE_ACTIVE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.active = 1;
-			dst->active = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_EEE_ENABLED) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.enabled = 1;
-			dst->enabled = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_EEE_TX_LPI_ENABLED) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_lpi_enabled = 1;
-			dst->tx_lpi_enabled = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_EEE_TX_LPI_TIMER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_lpi_timer = 1;
-			dst->tx_lpi_timer = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_eee_get_rsp *
-ethtool_eee_get(struct ynl_sock *ys, struct ethtool_eee_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_eee_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_EEE_GET, 1);
-	ys->req_policy = &ethtool_eee_nest;
-	yrs.yarg.rsp_policy = &ethtool_eee_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_EEE_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_eee_get_rsp_parse;
-	yrs.rsp_cmd = 24;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_eee_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_EEE_GET - dump */
-void ethtool_eee_get_list_free(struct ethtool_eee_get_list *rsp)
-{
-	struct ethtool_eee_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		ethtool_bitset_free(&rsp->obj.modes_ours);
-		ethtool_bitset_free(&rsp->obj.modes_peer);
-		free(rsp);
-	}
-}
-
-struct ethtool_eee_get_list *
-ethtool_eee_get_dump(struct ynl_sock *ys, struct ethtool_eee_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_eee_get_list);
-	yds.cb = ethtool_eee_get_rsp_parse;
-	yds.rsp_cmd = 24;
-	yds.rsp_policy = &ethtool_eee_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_EEE_GET, 1);
-	ys->req_policy = &ethtool_eee_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_EEE_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_eee_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_EEE_GET - notify */
-void ethtool_eee_get_ntf_free(struct ethtool_eee_get_ntf *rsp)
-{
-	ethtool_header_free(&rsp->obj.header);
-	ethtool_bitset_free(&rsp->obj.modes_ours);
-	ethtool_bitset_free(&rsp->obj.modes_peer);
-	free(rsp);
-}
-
-/* ============== ETHTOOL_MSG_EEE_SET ============== */
-/* ETHTOOL_MSG_EEE_SET - do */
-void ethtool_eee_set_req_free(struct ethtool_eee_set_req *req)
-{
-	ethtool_header_free(&req->header);
-	ethtool_bitset_free(&req->modes_ours);
-	ethtool_bitset_free(&req->modes_peer);
-	free(req);
-}
-
-int ethtool_eee_set(struct ynl_sock *ys, struct ethtool_eee_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_EEE_SET, 1);
-	ys->req_policy = &ethtool_eee_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_EEE_HEADER, &req->header);
-	if (req->_present.modes_ours)
-		ethtool_bitset_put(nlh, ETHTOOL_A_EEE_MODES_OURS, &req->modes_ours);
-	if (req->_present.modes_peer)
-		ethtool_bitset_put(nlh, ETHTOOL_A_EEE_MODES_PEER, &req->modes_peer);
-	if (req->_present.active)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_EEE_ACTIVE, req->active);
-	if (req->_present.enabled)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_EEE_ENABLED, req->enabled);
-	if (req->_present.tx_lpi_enabled)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_EEE_TX_LPI_ENABLED, req->tx_lpi_enabled);
-	if (req->_present.tx_lpi_timer)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_EEE_TX_LPI_TIMER, req->tx_lpi_timer);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== ETHTOOL_MSG_TSINFO_GET ============== */
-/* ETHTOOL_MSG_TSINFO_GET - do */
-void ethtool_tsinfo_get_req_free(struct ethtool_tsinfo_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_tsinfo_get_rsp_free(struct ethtool_tsinfo_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	ethtool_bitset_free(&rsp->timestamping);
-	ethtool_bitset_free(&rsp->tx_types);
-	ethtool_bitset_free(&rsp->rx_filters);
-	free(rsp);
-}
-
-int ethtool_tsinfo_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ethtool_tsinfo_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_TSINFO_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_TSINFO_TIMESTAMPING) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.timestamping = 1;
-
-			parg.rsp_policy = &ethtool_bitset_nest;
-			parg.data = &dst->timestamping;
-			if (ethtool_bitset_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_TSINFO_TX_TYPES) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_types = 1;
-
-			parg.rsp_policy = &ethtool_bitset_nest;
-			parg.data = &dst->tx_types;
-			if (ethtool_bitset_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_TSINFO_RX_FILTERS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx_filters = 1;
-
-			parg.rsp_policy = &ethtool_bitset_nest;
-			parg.data = &dst->rx_filters;
-			if (ethtool_bitset_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_TSINFO_PHC_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.phc_index = 1;
-			dst->phc_index = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_tsinfo_get_rsp *
-ethtool_tsinfo_get(struct ynl_sock *ys, struct ethtool_tsinfo_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_tsinfo_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_TSINFO_GET, 1);
-	ys->req_policy = &ethtool_tsinfo_nest;
-	yrs.yarg.rsp_policy = &ethtool_tsinfo_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_TSINFO_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_tsinfo_get_rsp_parse;
-	yrs.rsp_cmd = 26;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_tsinfo_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_TSINFO_GET - dump */
-void ethtool_tsinfo_get_list_free(struct ethtool_tsinfo_get_list *rsp)
-{
-	struct ethtool_tsinfo_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		ethtool_bitset_free(&rsp->obj.timestamping);
-		ethtool_bitset_free(&rsp->obj.tx_types);
-		ethtool_bitset_free(&rsp->obj.rx_filters);
-		free(rsp);
-	}
-}
-
-struct ethtool_tsinfo_get_list *
-ethtool_tsinfo_get_dump(struct ynl_sock *ys,
-			struct ethtool_tsinfo_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_tsinfo_get_list);
-	yds.cb = ethtool_tsinfo_get_rsp_parse;
-	yds.rsp_cmd = 26;
-	yds.rsp_policy = &ethtool_tsinfo_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_TSINFO_GET, 1);
-	ys->req_policy = &ethtool_tsinfo_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_TSINFO_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_tsinfo_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== ETHTOOL_MSG_CABLE_TEST_ACT ============== */
-/* ETHTOOL_MSG_CABLE_TEST_ACT - do */
-void ethtool_cable_test_act_req_free(struct ethtool_cable_test_act_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-int ethtool_cable_test_act(struct ynl_sock *ys,
-			   struct ethtool_cable_test_act_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_CABLE_TEST_ACT, 1);
-	ys->req_policy = &ethtool_cable_test_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_CABLE_TEST_HEADER, &req->header);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== ETHTOOL_MSG_CABLE_TEST_TDR_ACT ============== */
-/* ETHTOOL_MSG_CABLE_TEST_TDR_ACT - do */
-void
-ethtool_cable_test_tdr_act_req_free(struct ethtool_cable_test_tdr_act_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-int ethtool_cable_test_tdr_act(struct ynl_sock *ys,
-			       struct ethtool_cable_test_tdr_act_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_CABLE_TEST_TDR_ACT, 1);
-	ys->req_policy = &ethtool_cable_test_tdr_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_CABLE_TEST_TDR_HEADER, &req->header);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== ETHTOOL_MSG_TUNNEL_INFO_GET ============== */
-/* ETHTOOL_MSG_TUNNEL_INFO_GET - do */
-void ethtool_tunnel_info_get_req_free(struct ethtool_tunnel_info_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_tunnel_info_get_rsp_free(struct ethtool_tunnel_info_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	ethtool_tunnel_udp_free(&rsp->udp_ports);
-	free(rsp);
-}
-
-int ethtool_tunnel_info_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ethtool_tunnel_info_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_TUNNEL_INFO_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_TUNNEL_INFO_UDP_PORTS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.udp_ports = 1;
-
-			parg.rsp_policy = &ethtool_tunnel_udp_nest;
-			parg.data = &dst->udp_ports;
-			if (ethtool_tunnel_udp_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_tunnel_info_get_rsp *
-ethtool_tunnel_info_get(struct ynl_sock *ys,
-			struct ethtool_tunnel_info_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_tunnel_info_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_TUNNEL_INFO_GET, 1);
-	ys->req_policy = &ethtool_tunnel_info_nest;
-	yrs.yarg.rsp_policy = &ethtool_tunnel_info_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_TUNNEL_INFO_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_tunnel_info_get_rsp_parse;
-	yrs.rsp_cmd = 29;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_tunnel_info_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_TUNNEL_INFO_GET - dump */
-void
-ethtool_tunnel_info_get_list_free(struct ethtool_tunnel_info_get_list *rsp)
-{
-	struct ethtool_tunnel_info_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		ethtool_tunnel_udp_free(&rsp->obj.udp_ports);
-		free(rsp);
-	}
-}
-
-struct ethtool_tunnel_info_get_list *
-ethtool_tunnel_info_get_dump(struct ynl_sock *ys,
-			     struct ethtool_tunnel_info_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_tunnel_info_get_list);
-	yds.cb = ethtool_tunnel_info_get_rsp_parse;
-	yds.rsp_cmd = 29;
-	yds.rsp_policy = &ethtool_tunnel_info_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_TUNNEL_INFO_GET, 1);
-	ys->req_policy = &ethtool_tunnel_info_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_TUNNEL_INFO_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_tunnel_info_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== ETHTOOL_MSG_FEC_GET ============== */
-/* ETHTOOL_MSG_FEC_GET - do */
-void ethtool_fec_get_req_free(struct ethtool_fec_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_fec_get_rsp_free(struct ethtool_fec_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	ethtool_bitset_free(&rsp->modes);
-	ethtool_fec_stat_free(&rsp->stats);
-	free(rsp);
-}
-
-int ethtool_fec_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ynl_parse_arg *yarg = data;
-	struct ethtool_fec_get_rsp *dst;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_FEC_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_FEC_MODES) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.modes = 1;
-
-			parg.rsp_policy = &ethtool_bitset_nest;
-			parg.data = &dst->modes;
-			if (ethtool_bitset_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_FEC_AUTO) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.auto_ = 1;
-			dst->auto_ = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_FEC_ACTIVE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.active = 1;
-			dst->active = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_FEC_STATS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.stats = 1;
-
-			parg.rsp_policy = &ethtool_fec_stat_nest;
-			parg.data = &dst->stats;
-			if (ethtool_fec_stat_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_fec_get_rsp *
-ethtool_fec_get(struct ynl_sock *ys, struct ethtool_fec_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_fec_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_FEC_GET, 1);
-	ys->req_policy = &ethtool_fec_nest;
-	yrs.yarg.rsp_policy = &ethtool_fec_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_FEC_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_fec_get_rsp_parse;
-	yrs.rsp_cmd = 30;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_fec_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_FEC_GET - dump */
-void ethtool_fec_get_list_free(struct ethtool_fec_get_list *rsp)
-{
-	struct ethtool_fec_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		ethtool_bitset_free(&rsp->obj.modes);
-		ethtool_fec_stat_free(&rsp->obj.stats);
-		free(rsp);
-	}
-}
-
-struct ethtool_fec_get_list *
-ethtool_fec_get_dump(struct ynl_sock *ys, struct ethtool_fec_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_fec_get_list);
-	yds.cb = ethtool_fec_get_rsp_parse;
-	yds.rsp_cmd = 30;
-	yds.rsp_policy = &ethtool_fec_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_FEC_GET, 1);
-	ys->req_policy = &ethtool_fec_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_FEC_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_fec_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_FEC_GET - notify */
-void ethtool_fec_get_ntf_free(struct ethtool_fec_get_ntf *rsp)
-{
-	ethtool_header_free(&rsp->obj.header);
-	ethtool_bitset_free(&rsp->obj.modes);
-	ethtool_fec_stat_free(&rsp->obj.stats);
-	free(rsp);
-}
-
-/* ============== ETHTOOL_MSG_FEC_SET ============== */
-/* ETHTOOL_MSG_FEC_SET - do */
-void ethtool_fec_set_req_free(struct ethtool_fec_set_req *req)
-{
-	ethtool_header_free(&req->header);
-	ethtool_bitset_free(&req->modes);
-	ethtool_fec_stat_free(&req->stats);
-	free(req);
-}
-
-int ethtool_fec_set(struct ynl_sock *ys, struct ethtool_fec_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_FEC_SET, 1);
-	ys->req_policy = &ethtool_fec_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_FEC_HEADER, &req->header);
-	if (req->_present.modes)
-		ethtool_bitset_put(nlh, ETHTOOL_A_FEC_MODES, &req->modes);
-	if (req->_present.auto_)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_FEC_AUTO, req->auto_);
-	if (req->_present.active)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_FEC_ACTIVE, req->active);
-	if (req->_present.stats)
-		ethtool_fec_stat_put(nlh, ETHTOOL_A_FEC_STATS, &req->stats);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== ETHTOOL_MSG_MODULE_EEPROM_GET ============== */
-/* ETHTOOL_MSG_MODULE_EEPROM_GET - do */
-void
-ethtool_module_eeprom_get_req_free(struct ethtool_module_eeprom_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void
-ethtool_module_eeprom_get_rsp_free(struct ethtool_module_eeprom_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	free(rsp->data);
-	free(rsp);
-}
-
-int ethtool_module_eeprom_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ethtool_module_eeprom_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_MODULE_EEPROM_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_MODULE_EEPROM_OFFSET) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.offset = 1;
-			dst->offset = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_MODULE_EEPROM_LENGTH) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.length = 1;
-			dst->length = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_MODULE_EEPROM_PAGE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.page = 1;
-			dst->page = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_MODULE_EEPROM_BANK) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.bank = 1;
-			dst->bank = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.i2c_address = 1;
-			dst->i2c_address = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_MODULE_EEPROM_DATA) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = mnl_attr_get_payload_len(attr);
-			dst->_present.data_len = len;
-			dst->data = malloc(len);
-			memcpy(dst->data, mnl_attr_get_payload(attr), len);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_module_eeprom_get_rsp *
-ethtool_module_eeprom_get(struct ynl_sock *ys,
-			  struct ethtool_module_eeprom_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_module_eeprom_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_MODULE_EEPROM_GET, 1);
-	ys->req_policy = &ethtool_module_eeprom_nest;
-	yrs.yarg.rsp_policy = &ethtool_module_eeprom_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_MODULE_EEPROM_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_module_eeprom_get_rsp_parse;
-	yrs.rsp_cmd = 32;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_module_eeprom_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_MODULE_EEPROM_GET - dump */
-void
-ethtool_module_eeprom_get_list_free(struct ethtool_module_eeprom_get_list *rsp)
-{
-	struct ethtool_module_eeprom_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		free(rsp->obj.data);
-		free(rsp);
-	}
-}
-
-struct ethtool_module_eeprom_get_list *
-ethtool_module_eeprom_get_dump(struct ynl_sock *ys,
-			       struct ethtool_module_eeprom_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_module_eeprom_get_list);
-	yds.cb = ethtool_module_eeprom_get_rsp_parse;
-	yds.rsp_cmd = 32;
-	yds.rsp_policy = &ethtool_module_eeprom_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_MODULE_EEPROM_GET, 1);
-	ys->req_policy = &ethtool_module_eeprom_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_MODULE_EEPROM_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_module_eeprom_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== ETHTOOL_MSG_PHC_VCLOCKS_GET ============== */
-/* ETHTOOL_MSG_PHC_VCLOCKS_GET - do */
-void ethtool_phc_vclocks_get_req_free(struct ethtool_phc_vclocks_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_phc_vclocks_get_rsp_free(struct ethtool_phc_vclocks_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	free(rsp);
-}
-
-int ethtool_phc_vclocks_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ethtool_phc_vclocks_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_PHC_VCLOCKS_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_PHC_VCLOCKS_NUM) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.num = 1;
-			dst->num = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_phc_vclocks_get_rsp *
-ethtool_phc_vclocks_get(struct ynl_sock *ys,
-			struct ethtool_phc_vclocks_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_phc_vclocks_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_PHC_VCLOCKS_GET, 1);
-	ys->req_policy = &ethtool_phc_vclocks_nest;
-	yrs.yarg.rsp_policy = &ethtool_phc_vclocks_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_PHC_VCLOCKS_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_phc_vclocks_get_rsp_parse;
-	yrs.rsp_cmd = 34;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_phc_vclocks_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_PHC_VCLOCKS_GET - dump */
-void
-ethtool_phc_vclocks_get_list_free(struct ethtool_phc_vclocks_get_list *rsp)
-{
-	struct ethtool_phc_vclocks_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		free(rsp);
-	}
-}
-
-struct ethtool_phc_vclocks_get_list *
-ethtool_phc_vclocks_get_dump(struct ynl_sock *ys,
-			     struct ethtool_phc_vclocks_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_phc_vclocks_get_list);
-	yds.cb = ethtool_phc_vclocks_get_rsp_parse;
-	yds.rsp_cmd = 34;
-	yds.rsp_policy = &ethtool_phc_vclocks_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_PHC_VCLOCKS_GET, 1);
-	ys->req_policy = &ethtool_phc_vclocks_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_PHC_VCLOCKS_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_phc_vclocks_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== ETHTOOL_MSG_MODULE_GET ============== */
-/* ETHTOOL_MSG_MODULE_GET - do */
-void ethtool_module_get_req_free(struct ethtool_module_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_module_get_rsp_free(struct ethtool_module_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	free(rsp);
-}
-
-int ethtool_module_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ethtool_module_get_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_MODULE_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_MODULE_POWER_MODE_POLICY) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.power_mode_policy = 1;
-			dst->power_mode_policy = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_MODULE_POWER_MODE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.power_mode = 1;
-			dst->power_mode = mnl_attr_get_u8(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_module_get_rsp *
-ethtool_module_get(struct ynl_sock *ys, struct ethtool_module_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_module_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_MODULE_GET, 1);
-	ys->req_policy = &ethtool_module_nest;
-	yrs.yarg.rsp_policy = &ethtool_module_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_MODULE_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_module_get_rsp_parse;
-	yrs.rsp_cmd = 35;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_module_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_MODULE_GET - dump */
-void ethtool_module_get_list_free(struct ethtool_module_get_list *rsp)
-{
-	struct ethtool_module_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		free(rsp);
-	}
-}
-
-struct ethtool_module_get_list *
-ethtool_module_get_dump(struct ynl_sock *ys,
-			struct ethtool_module_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_module_get_list);
-	yds.cb = ethtool_module_get_rsp_parse;
-	yds.rsp_cmd = 35;
-	yds.rsp_policy = &ethtool_module_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_MODULE_GET, 1);
-	ys->req_policy = &ethtool_module_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_MODULE_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_module_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_MODULE_GET - notify */
-void ethtool_module_get_ntf_free(struct ethtool_module_get_ntf *rsp)
-{
-	ethtool_header_free(&rsp->obj.header);
-	free(rsp);
-}
-
-/* ============== ETHTOOL_MSG_MODULE_SET ============== */
-/* ETHTOOL_MSG_MODULE_SET - do */
-void ethtool_module_set_req_free(struct ethtool_module_set_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-int ethtool_module_set(struct ynl_sock *ys, struct ethtool_module_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_MODULE_SET, 1);
-	ys->req_policy = &ethtool_module_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_MODULE_HEADER, &req->header);
-	if (req->_present.power_mode_policy)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_MODULE_POWER_MODE_POLICY, req->power_mode_policy);
-	if (req->_present.power_mode)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_MODULE_POWER_MODE, req->power_mode);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== ETHTOOL_MSG_PSE_GET ============== */
-/* ETHTOOL_MSG_PSE_GET - do */
-void ethtool_pse_get_req_free(struct ethtool_pse_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_pse_get_rsp_free(struct ethtool_pse_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	free(rsp);
-}
-
-int ethtool_pse_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ynl_parse_arg *yarg = data;
-	struct ethtool_pse_get_rsp *dst;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_PSE_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_PODL_PSE_ADMIN_STATE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.admin_state = 1;
-			dst->admin_state = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_PODL_PSE_ADMIN_CONTROL) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.admin_control = 1;
-			dst->admin_control = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_PODL_PSE_PW_D_STATUS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.pw_d_status = 1;
-			dst->pw_d_status = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_pse_get_rsp *
-ethtool_pse_get(struct ynl_sock *ys, struct ethtool_pse_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_pse_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_PSE_GET, 1);
-	ys->req_policy = &ethtool_pse_nest;
-	yrs.yarg.rsp_policy = &ethtool_pse_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_PSE_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_pse_get_rsp_parse;
-	yrs.rsp_cmd = 37;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_pse_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_PSE_GET - dump */
-void ethtool_pse_get_list_free(struct ethtool_pse_get_list *rsp)
-{
-	struct ethtool_pse_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		free(rsp);
-	}
-}
-
-struct ethtool_pse_get_list *
-ethtool_pse_get_dump(struct ynl_sock *ys, struct ethtool_pse_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_pse_get_list);
-	yds.cb = ethtool_pse_get_rsp_parse;
-	yds.rsp_cmd = 37;
-	yds.rsp_policy = &ethtool_pse_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_PSE_GET, 1);
-	ys->req_policy = &ethtool_pse_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_PSE_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_pse_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== ETHTOOL_MSG_PSE_SET ============== */
-/* ETHTOOL_MSG_PSE_SET - do */
-void ethtool_pse_set_req_free(struct ethtool_pse_set_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-int ethtool_pse_set(struct ynl_sock *ys, struct ethtool_pse_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_PSE_SET, 1);
-	ys->req_policy = &ethtool_pse_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_PSE_HEADER, &req->header);
-	if (req->_present.admin_state)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_PODL_PSE_ADMIN_STATE, req->admin_state);
-	if (req->_present.admin_control)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_PODL_PSE_ADMIN_CONTROL, req->admin_control);
-	if (req->_present.pw_d_status)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_PODL_PSE_PW_D_STATUS, req->pw_d_status);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== ETHTOOL_MSG_RSS_GET ============== */
-/* ETHTOOL_MSG_RSS_GET - do */
-void ethtool_rss_get_req_free(struct ethtool_rss_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_rss_get_rsp_free(struct ethtool_rss_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	free(rsp->indir);
-	free(rsp->hkey);
-	free(rsp);
-}
-
-int ethtool_rss_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ynl_parse_arg *yarg = data;
-	struct ethtool_rss_get_rsp *dst;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_RSS_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_RSS_CONTEXT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.context = 1;
-			dst->context = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_RSS_HFUNC) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.hfunc = 1;
-			dst->hfunc = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_RSS_INDIR) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = mnl_attr_get_payload_len(attr);
-			dst->_present.indir_len = len;
-			dst->indir = malloc(len);
-			memcpy(dst->indir, mnl_attr_get_payload(attr), len);
-		} else if (type == ETHTOOL_A_RSS_HKEY) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = mnl_attr_get_payload_len(attr);
-			dst->_present.hkey_len = len;
-			dst->hkey = malloc(len);
-			memcpy(dst->hkey, mnl_attr_get_payload(attr), len);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_rss_get_rsp *
-ethtool_rss_get(struct ynl_sock *ys, struct ethtool_rss_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_rss_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_RSS_GET, 1);
-	ys->req_policy = &ethtool_rss_nest;
-	yrs.yarg.rsp_policy = &ethtool_rss_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_RSS_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_rss_get_rsp_parse;
-	yrs.rsp_cmd = ETHTOOL_MSG_RSS_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_rss_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_RSS_GET - dump */
-void ethtool_rss_get_list_free(struct ethtool_rss_get_list *rsp)
-{
-	struct ethtool_rss_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		free(rsp->obj.indir);
-		free(rsp->obj.hkey);
-		free(rsp);
-	}
-}
-
-struct ethtool_rss_get_list *
-ethtool_rss_get_dump(struct ynl_sock *ys, struct ethtool_rss_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_rss_get_list);
-	yds.cb = ethtool_rss_get_rsp_parse;
-	yds.rsp_cmd = ETHTOOL_MSG_RSS_GET;
-	yds.rsp_policy = &ethtool_rss_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_RSS_GET, 1);
-	ys->req_policy = &ethtool_rss_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_RSS_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_rss_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== ETHTOOL_MSG_PLCA_GET_CFG ============== */
-/* ETHTOOL_MSG_PLCA_GET_CFG - do */
-void ethtool_plca_get_cfg_req_free(struct ethtool_plca_get_cfg_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_plca_get_cfg_rsp_free(struct ethtool_plca_get_cfg_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	free(rsp);
-}
-
-int ethtool_plca_get_cfg_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ethtool_plca_get_cfg_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_PLCA_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_PLCA_VERSION) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.version = 1;
-			dst->version = mnl_attr_get_u16(attr);
-		} else if (type == ETHTOOL_A_PLCA_ENABLED) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.enabled = 1;
-			dst->enabled = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_PLCA_STATUS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.status = 1;
-			dst->status = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_PLCA_NODE_CNT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.node_cnt = 1;
-			dst->node_cnt = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_PLCA_NODE_ID) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.node_id = 1;
-			dst->node_id = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_PLCA_TO_TMR) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.to_tmr = 1;
-			dst->to_tmr = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_PLCA_BURST_CNT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.burst_cnt = 1;
-			dst->burst_cnt = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_PLCA_BURST_TMR) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.burst_tmr = 1;
-			dst->burst_tmr = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_plca_get_cfg_rsp *
-ethtool_plca_get_cfg(struct ynl_sock *ys, struct ethtool_plca_get_cfg_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_plca_get_cfg_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_PLCA_GET_CFG, 1);
-	ys->req_policy = &ethtool_plca_nest;
-	yrs.yarg.rsp_policy = &ethtool_plca_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_PLCA_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_plca_get_cfg_rsp_parse;
-	yrs.rsp_cmd = ETHTOOL_MSG_PLCA_GET_CFG;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_plca_get_cfg_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_PLCA_GET_CFG - dump */
-void ethtool_plca_get_cfg_list_free(struct ethtool_plca_get_cfg_list *rsp)
-{
-	struct ethtool_plca_get_cfg_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		free(rsp);
-	}
-}
-
-struct ethtool_plca_get_cfg_list *
-ethtool_plca_get_cfg_dump(struct ynl_sock *ys,
-			  struct ethtool_plca_get_cfg_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_plca_get_cfg_list);
-	yds.cb = ethtool_plca_get_cfg_rsp_parse;
-	yds.rsp_cmd = ETHTOOL_MSG_PLCA_GET_CFG;
-	yds.rsp_policy = &ethtool_plca_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_PLCA_GET_CFG, 1);
-	ys->req_policy = &ethtool_plca_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_PLCA_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_plca_get_cfg_list_free(yds.first);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_PLCA_GET_CFG - notify */
-void ethtool_plca_get_cfg_ntf_free(struct ethtool_plca_get_cfg_ntf *rsp)
-{
-	ethtool_header_free(&rsp->obj.header);
-	free(rsp);
-}
-
-/* ============== ETHTOOL_MSG_PLCA_SET_CFG ============== */
-/* ETHTOOL_MSG_PLCA_SET_CFG - do */
-void ethtool_plca_set_cfg_req_free(struct ethtool_plca_set_cfg_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-int ethtool_plca_set_cfg(struct ynl_sock *ys,
-			 struct ethtool_plca_set_cfg_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_PLCA_SET_CFG, 1);
-	ys->req_policy = &ethtool_plca_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_PLCA_HEADER, &req->header);
-	if (req->_present.version)
-		mnl_attr_put_u16(nlh, ETHTOOL_A_PLCA_VERSION, req->version);
-	if (req->_present.enabled)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_PLCA_ENABLED, req->enabled);
-	if (req->_present.status)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_PLCA_STATUS, req->status);
-	if (req->_present.node_cnt)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_PLCA_NODE_CNT, req->node_cnt);
-	if (req->_present.node_id)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_PLCA_NODE_ID, req->node_id);
-	if (req->_present.to_tmr)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_PLCA_TO_TMR, req->to_tmr);
-	if (req->_present.burst_cnt)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_PLCA_BURST_CNT, req->burst_cnt);
-	if (req->_present.burst_tmr)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_PLCA_BURST_TMR, req->burst_tmr);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== ETHTOOL_MSG_PLCA_GET_STATUS ============== */
-/* ETHTOOL_MSG_PLCA_GET_STATUS - do */
-void ethtool_plca_get_status_req_free(struct ethtool_plca_get_status_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_plca_get_status_rsp_free(struct ethtool_plca_get_status_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	free(rsp);
-}
-
-int ethtool_plca_get_status_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ethtool_plca_get_status_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_PLCA_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_PLCA_VERSION) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.version = 1;
-			dst->version = mnl_attr_get_u16(attr);
-		} else if (type == ETHTOOL_A_PLCA_ENABLED) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.enabled = 1;
-			dst->enabled = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_PLCA_STATUS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.status = 1;
-			dst->status = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_PLCA_NODE_CNT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.node_cnt = 1;
-			dst->node_cnt = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_PLCA_NODE_ID) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.node_id = 1;
-			dst->node_id = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_PLCA_TO_TMR) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.to_tmr = 1;
-			dst->to_tmr = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_PLCA_BURST_CNT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.burst_cnt = 1;
-			dst->burst_cnt = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_PLCA_BURST_TMR) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.burst_tmr = 1;
-			dst->burst_tmr = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_plca_get_status_rsp *
-ethtool_plca_get_status(struct ynl_sock *ys,
-			struct ethtool_plca_get_status_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_plca_get_status_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_PLCA_GET_STATUS, 1);
-	ys->req_policy = &ethtool_plca_nest;
-	yrs.yarg.rsp_policy = &ethtool_plca_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_PLCA_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_plca_get_status_rsp_parse;
-	yrs.rsp_cmd = 40;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_plca_get_status_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_PLCA_GET_STATUS - dump */
-void
-ethtool_plca_get_status_list_free(struct ethtool_plca_get_status_list *rsp)
-{
-	struct ethtool_plca_get_status_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		free(rsp);
-	}
-}
-
-struct ethtool_plca_get_status_list *
-ethtool_plca_get_status_dump(struct ynl_sock *ys,
-			     struct ethtool_plca_get_status_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_plca_get_status_list);
-	yds.cb = ethtool_plca_get_status_rsp_parse;
-	yds.rsp_cmd = 40;
-	yds.rsp_policy = &ethtool_plca_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_PLCA_GET_STATUS, 1);
-	ys->req_policy = &ethtool_plca_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_PLCA_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_plca_get_status_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== ETHTOOL_MSG_MM_GET ============== */
-/* ETHTOOL_MSG_MM_GET - do */
-void ethtool_mm_get_req_free(struct ethtool_mm_get_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-void ethtool_mm_get_rsp_free(struct ethtool_mm_get_rsp *rsp)
-{
-	ethtool_header_free(&rsp->header);
-	ethtool_mm_stat_free(&rsp->stats);
-	free(rsp);
-}
-
-int ethtool_mm_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ynl_parse_arg *yarg = data;
-	struct ethtool_mm_get_rsp *dst;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_MM_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_MM_PMAC_ENABLED) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.pmac_enabled = 1;
-			dst->pmac_enabled = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_MM_TX_ENABLED) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_enabled = 1;
-			dst->tx_enabled = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_MM_TX_ACTIVE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_active = 1;
-			dst->tx_active = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_MM_TX_MIN_FRAG_SIZE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.tx_min_frag_size = 1;
-			dst->tx_min_frag_size = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_MM_RX_MIN_FRAG_SIZE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.rx_min_frag_size = 1;
-			dst->rx_min_frag_size = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_MM_VERIFY_ENABLED) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.verify_enabled = 1;
-			dst->verify_enabled = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_MM_VERIFY_TIME) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.verify_time = 1;
-			dst->verify_time = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_MM_MAX_VERIFY_TIME) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.max_verify_time = 1;
-			dst->max_verify_time = mnl_attr_get_u32(attr);
-		} else if (type == ETHTOOL_A_MM_STATS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.stats = 1;
-
-			parg.rsp_policy = &ethtool_mm_stat_nest;
-			parg.data = &dst->stats;
-			if (ethtool_mm_stat_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct ethtool_mm_get_rsp *
-ethtool_mm_get(struct ynl_sock *ys, struct ethtool_mm_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct ethtool_mm_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_MM_GET, 1);
-	ys->req_policy = &ethtool_mm_nest;
-	yrs.yarg.rsp_policy = &ethtool_mm_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_MM_HEADER, &req->header);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = ethtool_mm_get_rsp_parse;
-	yrs.rsp_cmd = ETHTOOL_MSG_MM_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	ethtool_mm_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_MM_GET - dump */
-void ethtool_mm_get_list_free(struct ethtool_mm_get_list *rsp)
-{
-	struct ethtool_mm_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		ethtool_header_free(&rsp->obj.header);
-		ethtool_mm_stat_free(&rsp->obj.stats);
-		free(rsp);
-	}
-}
-
-struct ethtool_mm_get_list *
-ethtool_mm_get_dump(struct ynl_sock *ys, struct ethtool_mm_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct ethtool_mm_get_list);
-	yds.cb = ethtool_mm_get_rsp_parse;
-	yds.rsp_cmd = ETHTOOL_MSG_MM_GET;
-	yds.rsp_policy = &ethtool_mm_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_MM_GET, 1);
-	ys->req_policy = &ethtool_mm_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_MM_HEADER, &req->header);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	ethtool_mm_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ETHTOOL_MSG_MM_GET - notify */
-void ethtool_mm_get_ntf_free(struct ethtool_mm_get_ntf *rsp)
-{
-	ethtool_header_free(&rsp->obj.header);
-	ethtool_mm_stat_free(&rsp->obj.stats);
-	free(rsp);
-}
-
-/* ============== ETHTOOL_MSG_MM_SET ============== */
-/* ETHTOOL_MSG_MM_SET - do */
-void ethtool_mm_set_req_free(struct ethtool_mm_set_req *req)
-{
-	ethtool_header_free(&req->header);
-	free(req);
-}
-
-int ethtool_mm_set(struct ynl_sock *ys, struct ethtool_mm_set_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_MM_SET, 1);
-	ys->req_policy = &ethtool_mm_nest;
-
-	if (req->_present.header)
-		ethtool_header_put(nlh, ETHTOOL_A_MM_HEADER, &req->header);
-	if (req->_present.verify_enabled)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_MM_VERIFY_ENABLED, req->verify_enabled);
-	if (req->_present.verify_time)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_MM_VERIFY_TIME, req->verify_time);
-	if (req->_present.tx_enabled)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_MM_TX_ENABLED, req->tx_enabled);
-	if (req->_present.pmac_enabled)
-		mnl_attr_put_u8(nlh, ETHTOOL_A_MM_PMAC_ENABLED, req->pmac_enabled);
-	if (req->_present.tx_min_frag_size)
-		mnl_attr_put_u32(nlh, ETHTOOL_A_MM_TX_MIN_FRAG_SIZE, req->tx_min_frag_size);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ETHTOOL_MSG_CABLE_TEST_NTF - event */
-int ethtool_cable_test_ntf_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ethtool_cable_test_ntf_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_CABLE_TEST_NTF_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_CABLE_TEST_NTF_STATUS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.status = 1;
-			dst->status = mnl_attr_get_u8(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-void ethtool_cable_test_ntf_free(struct ethtool_cable_test_ntf *rsp)
-{
-	ethtool_header_free(&rsp->obj.header);
-	free(rsp);
-}
-
-/* ETHTOOL_MSG_CABLE_TEST_TDR_NTF - event */
-int ethtool_cable_test_tdr_ntf_rsp_parse(const struct nlmsghdr *nlh,
-					 void *data)
-{
-	struct ethtool_cable_test_tdr_ntf_rsp *dst;
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == ETHTOOL_A_CABLE_TEST_TDR_NTF_HEADER) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.header = 1;
-
-			parg.rsp_policy = &ethtool_header_nest;
-			parg.data = &dst->header;
-			if (ethtool_header_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == ETHTOOL_A_CABLE_TEST_TDR_NTF_STATUS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.status = 1;
-			dst->status = mnl_attr_get_u8(attr);
-		} else if (type == ETHTOOL_A_CABLE_TEST_TDR_NTF_NEST) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.nest = 1;
-
-			parg.rsp_policy = &ethtool_cable_nest_nest;
-			parg.data = &dst->nest;
-			if (ethtool_cable_nest_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-void ethtool_cable_test_tdr_ntf_free(struct ethtool_cable_test_tdr_ntf *rsp)
-{
-	ethtool_header_free(&rsp->obj.header);
-	ethtool_cable_nest_free(&rsp->obj.nest);
-	free(rsp);
-}
-
-static const struct ynl_ntf_info ethtool_ntf_info[] =  {
-	[ETHTOOL_MSG_LINKINFO_NTF] =  {
-		.alloc_sz	= sizeof(struct ethtool_linkinfo_get_ntf),
-		.cb		= ethtool_linkinfo_get_rsp_parse,
-		.policy		= &ethtool_linkinfo_nest,
-		.free		= (void *)ethtool_linkinfo_get_ntf_free,
-	},
-	[ETHTOOL_MSG_LINKMODES_NTF] =  {
-		.alloc_sz	= sizeof(struct ethtool_linkmodes_get_ntf),
-		.cb		= ethtool_linkmodes_get_rsp_parse,
-		.policy		= &ethtool_linkmodes_nest,
-		.free		= (void *)ethtool_linkmodes_get_ntf_free,
-	},
-	[ETHTOOL_MSG_DEBUG_NTF] =  {
-		.alloc_sz	= sizeof(struct ethtool_debug_get_ntf),
-		.cb		= ethtool_debug_get_rsp_parse,
-		.policy		= &ethtool_debug_nest,
-		.free		= (void *)ethtool_debug_get_ntf_free,
-	},
-	[ETHTOOL_MSG_WOL_NTF] =  {
-		.alloc_sz	= sizeof(struct ethtool_wol_get_ntf),
-		.cb		= ethtool_wol_get_rsp_parse,
-		.policy		= &ethtool_wol_nest,
-		.free		= (void *)ethtool_wol_get_ntf_free,
-	},
-	[ETHTOOL_MSG_FEATURES_NTF] =  {
-		.alloc_sz	= sizeof(struct ethtool_features_get_ntf),
-		.cb		= ethtool_features_get_rsp_parse,
-		.policy		= &ethtool_features_nest,
-		.free		= (void *)ethtool_features_get_ntf_free,
-	},
-	[ETHTOOL_MSG_PRIVFLAGS_NTF] =  {
-		.alloc_sz	= sizeof(struct ethtool_privflags_get_ntf),
-		.cb		= ethtool_privflags_get_rsp_parse,
-		.policy		= &ethtool_privflags_nest,
-		.free		= (void *)ethtool_privflags_get_ntf_free,
-	},
-	[ETHTOOL_MSG_RINGS_NTF] =  {
-		.alloc_sz	= sizeof(struct ethtool_rings_get_ntf),
-		.cb		= ethtool_rings_get_rsp_parse,
-		.policy		= &ethtool_rings_nest,
-		.free		= (void *)ethtool_rings_get_ntf_free,
-	},
-	[ETHTOOL_MSG_CHANNELS_NTF] =  {
-		.alloc_sz	= sizeof(struct ethtool_channels_get_ntf),
-		.cb		= ethtool_channels_get_rsp_parse,
-		.policy		= &ethtool_channels_nest,
-		.free		= (void *)ethtool_channels_get_ntf_free,
-	},
-	[ETHTOOL_MSG_COALESCE_NTF] =  {
-		.alloc_sz	= sizeof(struct ethtool_coalesce_get_ntf),
-		.cb		= ethtool_coalesce_get_rsp_parse,
-		.policy		= &ethtool_coalesce_nest,
-		.free		= (void *)ethtool_coalesce_get_ntf_free,
-	},
-	[ETHTOOL_MSG_PAUSE_NTF] =  {
-		.alloc_sz	= sizeof(struct ethtool_pause_get_ntf),
-		.cb		= ethtool_pause_get_rsp_parse,
-		.policy		= &ethtool_pause_nest,
-		.free		= (void *)ethtool_pause_get_ntf_free,
-	},
-	[ETHTOOL_MSG_EEE_NTF] =  {
-		.alloc_sz	= sizeof(struct ethtool_eee_get_ntf),
-		.cb		= ethtool_eee_get_rsp_parse,
-		.policy		= &ethtool_eee_nest,
-		.free		= (void *)ethtool_eee_get_ntf_free,
-	},
-	[ETHTOOL_MSG_CABLE_TEST_NTF] =  {
-		.alloc_sz	= sizeof(struct ethtool_cable_test_ntf),
-		.cb		= ethtool_cable_test_ntf_rsp_parse,
-		.policy		= &ethtool_cable_test_ntf_nest,
-		.free		= (void *)ethtool_cable_test_ntf_free,
-	},
-	[ETHTOOL_MSG_CABLE_TEST_TDR_NTF] =  {
-		.alloc_sz	= sizeof(struct ethtool_cable_test_tdr_ntf),
-		.cb		= ethtool_cable_test_tdr_ntf_rsp_parse,
-		.policy		= &ethtool_cable_test_tdr_ntf_nest,
-		.free		= (void *)ethtool_cable_test_tdr_ntf_free,
-	},
-	[ETHTOOL_MSG_FEC_NTF] =  {
-		.alloc_sz	= sizeof(struct ethtool_fec_get_ntf),
-		.cb		= ethtool_fec_get_rsp_parse,
-		.policy		= &ethtool_fec_nest,
-		.free		= (void *)ethtool_fec_get_ntf_free,
-	},
-	[ETHTOOL_MSG_MODULE_NTF] =  {
-		.alloc_sz	= sizeof(struct ethtool_module_get_ntf),
-		.cb		= ethtool_module_get_rsp_parse,
-		.policy		= &ethtool_module_nest,
-		.free		= (void *)ethtool_module_get_ntf_free,
-	},
-	[ETHTOOL_MSG_PLCA_NTF] =  {
-		.alloc_sz	= sizeof(struct ethtool_plca_get_cfg_ntf),
-		.cb		= ethtool_plca_get_cfg_rsp_parse,
-		.policy		= &ethtool_plca_nest,
-		.free		= (void *)ethtool_plca_get_cfg_ntf_free,
-	},
-	[ETHTOOL_MSG_MM_NTF] =  {
-		.alloc_sz	= sizeof(struct ethtool_mm_get_ntf),
-		.cb		= ethtool_mm_get_rsp_parse,
-		.policy		= &ethtool_mm_nest,
-		.free		= (void *)ethtool_mm_get_ntf_free,
-	},
-};
-
-const struct ynl_family ynl_ethtool_family =  {
-	.name		= "ethtool",
-	.ntf_info	= ethtool_ntf_info,
-	.ntf_info_size	= MNL_ARRAY_SIZE(ethtool_ntf_info),
-};
diff --git a/tools/net/ynl/generated/ethtool-user.h b/tools/net/ynl/generated/ethtool-user.h
deleted file mode 100644
index ca0ec5fd7798..000000000000
--- a/tools/net/ynl/generated/ethtool-user.h
+++ /dev/null
@@ -1,5535 +0,0 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
-/* Do not edit directly, auto-generated from: */
-/*	Documentation/netlink/specs/ethtool.yaml */
-/* YNL-GEN user header */
-/* YNL-ARG --user-header linux/ethtool_netlink.h --exclude-op stats-get */
-
-#ifndef _LINUX_ETHTOOL_GEN_H
-#define _LINUX_ETHTOOL_GEN_H
-
-#include <stdlib.h>
-#include <string.h>
-#include <linux/types.h>
-#include <linux/ethtool.h>
-
-struct ynl_sock;
-
-extern const struct ynl_family ynl_ethtool_family;
-
-/* Enums */
-const char *ethtool_op_str(int op);
-const char *ethtool_udp_tunnel_type_str(int value);
-const char *ethtool_stringset_str(enum ethtool_stringset value);
-
-/* Common nested types */
-struct ethtool_header {
-	struct {
-		__u32 dev_index:1;
-		__u32 dev_name_len;
-		__u32 flags:1;
-	} _present;
-
-	__u32 dev_index;
-	char *dev_name;
-	__u32 flags;
-};
-
-struct ethtool_pause_stat {
-	struct {
-		__u32 tx_frames:1;
-		__u32 rx_frames:1;
-	} _present;
-
-	__u64 tx_frames;
-	__u64 rx_frames;
-};
-
-struct ethtool_cable_test_tdr_cfg {
-	struct {
-		__u32 first:1;
-		__u32 last:1;
-		__u32 step:1;
-		__u32 pair:1;
-	} _present;
-
-	__u32 first;
-	__u32 last;
-	__u32 step;
-	__u8 pair;
-};
-
-struct ethtool_fec_stat {
-	struct {
-		__u32 corrected_len;
-		__u32 uncorr_len;
-		__u32 corr_bits_len;
-	} _present;
-
-	void *corrected;
-	void *uncorr;
-	void *corr_bits;
-};
-
-struct ethtool_mm_stat {
-	struct {
-		__u32 reassembly_errors:1;
-		__u32 smd_errors:1;
-		__u32 reassembly_ok:1;
-		__u32 rx_frag_count:1;
-		__u32 tx_frag_count:1;
-		__u32 hold_count:1;
-	} _present;
-
-	__u64 reassembly_errors;
-	__u64 smd_errors;
-	__u64 reassembly_ok;
-	__u64 rx_frag_count;
-	__u64 tx_frag_count;
-	__u64 hold_count;
-};
-
-struct ethtool_cable_result {
-	struct {
-		__u32 pair:1;
-		__u32 code:1;
-	} _present;
-
-	__u8 pair;
-	__u8 code;
-};
-
-struct ethtool_cable_fault_length {
-	struct {
-		__u32 pair:1;
-		__u32 cm:1;
-	} _present;
-
-	__u8 pair;
-	__u32 cm;
-};
-
-struct ethtool_bitset_bit {
-	struct {
-		__u32 index:1;
-		__u32 name_len;
-		__u32 value:1;
-	} _present;
-
-	__u32 index;
-	char *name;
-};
-
-struct ethtool_tunnel_udp_entry {
-	struct {
-		__u32 port:1;
-		__u32 type:1;
-	} _present;
-
-	__u16 port /* big-endian */;
-	__u32 type;
-};
-
-struct ethtool_string {
-	struct {
-		__u32 index:1;
-		__u32 value_len;
-	} _present;
-
-	__u32 index;
-	char *value;
-};
-
-struct ethtool_cable_nest {
-	struct {
-		__u32 result:1;
-		__u32 fault_length:1;
-	} _present;
-
-	struct ethtool_cable_result result;
-	struct ethtool_cable_fault_length fault_length;
-};
-
-struct ethtool_bitset_bits {
-	unsigned int n_bit;
-	struct ethtool_bitset_bit *bit;
-};
-
-struct ethtool_strings {
-	unsigned int n_string;
-	struct ethtool_string *string;
-};
-
-struct ethtool_bitset {
-	struct {
-		__u32 nomask:1;
-		__u32 size:1;
-		__u32 bits:1;
-	} _present;
-
-	__u32 size;
-	struct ethtool_bitset_bits bits;
-};
-
-struct ethtool_stringset_ {
-	struct {
-		__u32 id:1;
-		__u32 count:1;
-	} _present;
-
-	__u32 id;
-	__u32 count;
-	unsigned int n_strings;
-	struct ethtool_strings *strings;
-};
-
-struct ethtool_tunnel_udp_table {
-	struct {
-		__u32 size:1;
-		__u32 types:1;
-	} _present;
-
-	__u32 size;
-	struct ethtool_bitset types;
-	unsigned int n_entry;
-	struct ethtool_tunnel_udp_entry *entry;
-};
-
-struct ethtool_stringsets {
-	unsigned int n_stringset;
-	struct ethtool_stringset_ *stringset;
-};
-
-struct ethtool_tunnel_udp {
-	struct {
-		__u32 table:1;
-	} _present;
-
-	struct ethtool_tunnel_udp_table table;
-};
-
-/* ============== ETHTOOL_MSG_STRSET_GET ============== */
-/* ETHTOOL_MSG_STRSET_GET - do */
-struct ethtool_strset_get_req {
-	struct {
-		__u32 header:1;
-		__u32 stringsets:1;
-		__u32 counts_only:1;
-	} _present;
-
-	struct ethtool_header header;
-	struct ethtool_stringsets stringsets;
-};
-
-static inline struct ethtool_strset_get_req *ethtool_strset_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_strset_get_req));
-}
-void ethtool_strset_get_req_free(struct ethtool_strset_get_req *req);
-
-static inline void
-ethtool_strset_get_req_set_header_dev_index(struct ethtool_strset_get_req *req,
-					    __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_strset_get_req_set_header_dev_name(struct ethtool_strset_get_req *req,
-					   const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_strset_get_req_set_header_flags(struct ethtool_strset_get_req *req,
-					__u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-static inline void
-__ethtool_strset_get_req_set_stringsets_stringset(struct ethtool_strset_get_req *req,
-						  struct ethtool_stringset_ *stringset,
-						  unsigned int n_stringset)
-{
-	free(req->stringsets.stringset);
-	req->stringsets.stringset = stringset;
-	req->stringsets.n_stringset = n_stringset;
-}
-static inline void
-ethtool_strset_get_req_set_counts_only(struct ethtool_strset_get_req *req)
-{
-	req->_present.counts_only = 1;
-}
-
-struct ethtool_strset_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 stringsets:1;
-	} _present;
-
-	struct ethtool_header header;
-	struct ethtool_stringsets stringsets;
-};
-
-void ethtool_strset_get_rsp_free(struct ethtool_strset_get_rsp *rsp);
-
-/*
- * Get string set from the kernel.
- */
-struct ethtool_strset_get_rsp *
-ethtool_strset_get(struct ynl_sock *ys, struct ethtool_strset_get_req *req);
-
-/* ETHTOOL_MSG_STRSET_GET - dump */
-struct ethtool_strset_get_req_dump {
-	struct {
-		__u32 header:1;
-		__u32 stringsets:1;
-		__u32 counts_only:1;
-	} _present;
-
-	struct ethtool_header header;
-	struct ethtool_stringsets stringsets;
-};
-
-static inline struct ethtool_strset_get_req_dump *
-ethtool_strset_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_strset_get_req_dump));
-}
-void ethtool_strset_get_req_dump_free(struct ethtool_strset_get_req_dump *req);
-
-static inline void
-ethtool_strset_get_req_dump_set_header_dev_index(struct ethtool_strset_get_req_dump *req,
-						 __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_strset_get_req_dump_set_header_dev_name(struct ethtool_strset_get_req_dump *req,
-						const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_strset_get_req_dump_set_header_flags(struct ethtool_strset_get_req_dump *req,
-					     __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-static inline void
-__ethtool_strset_get_req_dump_set_stringsets_stringset(struct ethtool_strset_get_req_dump *req,
-						       struct ethtool_stringset_ *stringset,
-						       unsigned int n_stringset)
-{
-	free(req->stringsets.stringset);
-	req->stringsets.stringset = stringset;
-	req->stringsets.n_stringset = n_stringset;
-}
-static inline void
-ethtool_strset_get_req_dump_set_counts_only(struct ethtool_strset_get_req_dump *req)
-{
-	req->_present.counts_only = 1;
-}
-
-struct ethtool_strset_get_list {
-	struct ethtool_strset_get_list *next;
-	struct ethtool_strset_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_strset_get_list_free(struct ethtool_strset_get_list *rsp);
-
-struct ethtool_strset_get_list *
-ethtool_strset_get_dump(struct ynl_sock *ys,
-			struct ethtool_strset_get_req_dump *req);
-
-/* ============== ETHTOOL_MSG_LINKINFO_GET ============== */
-/* ETHTOOL_MSG_LINKINFO_GET - do */
-struct ethtool_linkinfo_get_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_linkinfo_get_req *
-ethtool_linkinfo_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_linkinfo_get_req));
-}
-void ethtool_linkinfo_get_req_free(struct ethtool_linkinfo_get_req *req);
-
-static inline void
-ethtool_linkinfo_get_req_set_header_dev_index(struct ethtool_linkinfo_get_req *req,
-					      __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_linkinfo_get_req_set_header_dev_name(struct ethtool_linkinfo_get_req *req,
-					     const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_linkinfo_get_req_set_header_flags(struct ethtool_linkinfo_get_req *req,
-					  __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_linkinfo_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 port:1;
-		__u32 phyaddr:1;
-		__u32 tp_mdix:1;
-		__u32 tp_mdix_ctrl:1;
-		__u32 transceiver:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u8 port;
-	__u8 phyaddr;
-	__u8 tp_mdix;
-	__u8 tp_mdix_ctrl;
-	__u8 transceiver;
-};
-
-void ethtool_linkinfo_get_rsp_free(struct ethtool_linkinfo_get_rsp *rsp);
-
-/*
- * Get link info.
- */
-struct ethtool_linkinfo_get_rsp *
-ethtool_linkinfo_get(struct ynl_sock *ys, struct ethtool_linkinfo_get_req *req);
-
-/* ETHTOOL_MSG_LINKINFO_GET - dump */
-struct ethtool_linkinfo_get_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_linkinfo_get_req_dump *
-ethtool_linkinfo_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_linkinfo_get_req_dump));
-}
-void
-ethtool_linkinfo_get_req_dump_free(struct ethtool_linkinfo_get_req_dump *req);
-
-static inline void
-ethtool_linkinfo_get_req_dump_set_header_dev_index(struct ethtool_linkinfo_get_req_dump *req,
-						   __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_linkinfo_get_req_dump_set_header_dev_name(struct ethtool_linkinfo_get_req_dump *req,
-						  const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_linkinfo_get_req_dump_set_header_flags(struct ethtool_linkinfo_get_req_dump *req,
-					       __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_linkinfo_get_list {
-	struct ethtool_linkinfo_get_list *next;
-	struct ethtool_linkinfo_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_linkinfo_get_list_free(struct ethtool_linkinfo_get_list *rsp);
-
-struct ethtool_linkinfo_get_list *
-ethtool_linkinfo_get_dump(struct ynl_sock *ys,
-			  struct ethtool_linkinfo_get_req_dump *req);
-
-/* ETHTOOL_MSG_LINKINFO_GET - notify */
-struct ethtool_linkinfo_get_ntf {
-	__u16 family;
-	__u8 cmd;
-	struct ynl_ntf_base_type *next;
-	void (*free)(struct ethtool_linkinfo_get_ntf *ntf);
-	struct ethtool_linkinfo_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_linkinfo_get_ntf_free(struct ethtool_linkinfo_get_ntf *rsp);
-
-/* ============== ETHTOOL_MSG_LINKINFO_SET ============== */
-/* ETHTOOL_MSG_LINKINFO_SET - do */
-struct ethtool_linkinfo_set_req {
-	struct {
-		__u32 header:1;
-		__u32 port:1;
-		__u32 phyaddr:1;
-		__u32 tp_mdix:1;
-		__u32 tp_mdix_ctrl:1;
-		__u32 transceiver:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u8 port;
-	__u8 phyaddr;
-	__u8 tp_mdix;
-	__u8 tp_mdix_ctrl;
-	__u8 transceiver;
-};
-
-static inline struct ethtool_linkinfo_set_req *
-ethtool_linkinfo_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_linkinfo_set_req));
-}
-void ethtool_linkinfo_set_req_free(struct ethtool_linkinfo_set_req *req);
-
-static inline void
-ethtool_linkinfo_set_req_set_header_dev_index(struct ethtool_linkinfo_set_req *req,
-					      __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_linkinfo_set_req_set_header_dev_name(struct ethtool_linkinfo_set_req *req,
-					     const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_linkinfo_set_req_set_header_flags(struct ethtool_linkinfo_set_req *req,
-					  __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-static inline void
-ethtool_linkinfo_set_req_set_port(struct ethtool_linkinfo_set_req *req,
-				  __u8 port)
-{
-	req->_present.port = 1;
-	req->port = port;
-}
-static inline void
-ethtool_linkinfo_set_req_set_phyaddr(struct ethtool_linkinfo_set_req *req,
-				     __u8 phyaddr)
-{
-	req->_present.phyaddr = 1;
-	req->phyaddr = phyaddr;
-}
-static inline void
-ethtool_linkinfo_set_req_set_tp_mdix(struct ethtool_linkinfo_set_req *req,
-				     __u8 tp_mdix)
-{
-	req->_present.tp_mdix = 1;
-	req->tp_mdix = tp_mdix;
-}
-static inline void
-ethtool_linkinfo_set_req_set_tp_mdix_ctrl(struct ethtool_linkinfo_set_req *req,
-					  __u8 tp_mdix_ctrl)
-{
-	req->_present.tp_mdix_ctrl = 1;
-	req->tp_mdix_ctrl = tp_mdix_ctrl;
-}
-static inline void
-ethtool_linkinfo_set_req_set_transceiver(struct ethtool_linkinfo_set_req *req,
-					 __u8 transceiver)
-{
-	req->_present.transceiver = 1;
-	req->transceiver = transceiver;
-}
-
-/*
- * Set link info.
- */
-int ethtool_linkinfo_set(struct ynl_sock *ys,
-			 struct ethtool_linkinfo_set_req *req);
-
-/* ============== ETHTOOL_MSG_LINKMODES_GET ============== */
-/* ETHTOOL_MSG_LINKMODES_GET - do */
-struct ethtool_linkmodes_get_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_linkmodes_get_req *
-ethtool_linkmodes_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_linkmodes_get_req));
-}
-void ethtool_linkmodes_get_req_free(struct ethtool_linkmodes_get_req *req);
-
-static inline void
-ethtool_linkmodes_get_req_set_header_dev_index(struct ethtool_linkmodes_get_req *req,
-					       __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_linkmodes_get_req_set_header_dev_name(struct ethtool_linkmodes_get_req *req,
-					      const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_linkmodes_get_req_set_header_flags(struct ethtool_linkmodes_get_req *req,
-					   __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_linkmodes_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 autoneg:1;
-		__u32 ours:1;
-		__u32 peer:1;
-		__u32 speed:1;
-		__u32 duplex:1;
-		__u32 master_slave_cfg:1;
-		__u32 master_slave_state:1;
-		__u32 lanes:1;
-		__u32 rate_matching:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u8 autoneg;
-	struct ethtool_bitset ours;
-	struct ethtool_bitset peer;
-	__u32 speed;
-	__u8 duplex;
-	__u8 master_slave_cfg;
-	__u8 master_slave_state;
-	__u32 lanes;
-	__u8 rate_matching;
-};
-
-void ethtool_linkmodes_get_rsp_free(struct ethtool_linkmodes_get_rsp *rsp);
-
-/*
- * Get link modes.
- */
-struct ethtool_linkmodes_get_rsp *
-ethtool_linkmodes_get(struct ynl_sock *ys,
-		      struct ethtool_linkmodes_get_req *req);
-
-/* ETHTOOL_MSG_LINKMODES_GET - dump */
-struct ethtool_linkmodes_get_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_linkmodes_get_req_dump *
-ethtool_linkmodes_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_linkmodes_get_req_dump));
-}
-void
-ethtool_linkmodes_get_req_dump_free(struct ethtool_linkmodes_get_req_dump *req);
-
-static inline void
-ethtool_linkmodes_get_req_dump_set_header_dev_index(struct ethtool_linkmodes_get_req_dump *req,
-						    __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_linkmodes_get_req_dump_set_header_dev_name(struct ethtool_linkmodes_get_req_dump *req,
-						   const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_linkmodes_get_req_dump_set_header_flags(struct ethtool_linkmodes_get_req_dump *req,
-						__u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_linkmodes_get_list {
-	struct ethtool_linkmodes_get_list *next;
-	struct ethtool_linkmodes_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_linkmodes_get_list_free(struct ethtool_linkmodes_get_list *rsp);
-
-struct ethtool_linkmodes_get_list *
-ethtool_linkmodes_get_dump(struct ynl_sock *ys,
-			   struct ethtool_linkmodes_get_req_dump *req);
-
-/* ETHTOOL_MSG_LINKMODES_GET - notify */
-struct ethtool_linkmodes_get_ntf {
-	__u16 family;
-	__u8 cmd;
-	struct ynl_ntf_base_type *next;
-	void (*free)(struct ethtool_linkmodes_get_ntf *ntf);
-	struct ethtool_linkmodes_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_linkmodes_get_ntf_free(struct ethtool_linkmodes_get_ntf *rsp);
-
-/* ============== ETHTOOL_MSG_LINKMODES_SET ============== */
-/* ETHTOOL_MSG_LINKMODES_SET - do */
-struct ethtool_linkmodes_set_req {
-	struct {
-		__u32 header:1;
-		__u32 autoneg:1;
-		__u32 ours:1;
-		__u32 peer:1;
-		__u32 speed:1;
-		__u32 duplex:1;
-		__u32 master_slave_cfg:1;
-		__u32 master_slave_state:1;
-		__u32 lanes:1;
-		__u32 rate_matching:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u8 autoneg;
-	struct ethtool_bitset ours;
-	struct ethtool_bitset peer;
-	__u32 speed;
-	__u8 duplex;
-	__u8 master_slave_cfg;
-	__u8 master_slave_state;
-	__u32 lanes;
-	__u8 rate_matching;
-};
-
-static inline struct ethtool_linkmodes_set_req *
-ethtool_linkmodes_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_linkmodes_set_req));
-}
-void ethtool_linkmodes_set_req_free(struct ethtool_linkmodes_set_req *req);
-
-static inline void
-ethtool_linkmodes_set_req_set_header_dev_index(struct ethtool_linkmodes_set_req *req,
-					       __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_linkmodes_set_req_set_header_dev_name(struct ethtool_linkmodes_set_req *req,
-					      const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_linkmodes_set_req_set_header_flags(struct ethtool_linkmodes_set_req *req,
-					   __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-static inline void
-ethtool_linkmodes_set_req_set_autoneg(struct ethtool_linkmodes_set_req *req,
-				      __u8 autoneg)
-{
-	req->_present.autoneg = 1;
-	req->autoneg = autoneg;
-}
-static inline void
-ethtool_linkmodes_set_req_set_ours_nomask(struct ethtool_linkmodes_set_req *req)
-{
-	req->_present.ours = 1;
-	req->ours._present.nomask = 1;
-}
-static inline void
-ethtool_linkmodes_set_req_set_ours_size(struct ethtool_linkmodes_set_req *req,
-					__u32 size)
-{
-	req->_present.ours = 1;
-	req->ours._present.size = 1;
-	req->ours.size = size;
-}
-static inline void
-__ethtool_linkmodes_set_req_set_ours_bits_bit(struct ethtool_linkmodes_set_req *req,
-					      struct ethtool_bitset_bit *bit,
-					      unsigned int n_bit)
-{
-	free(req->ours.bits.bit);
-	req->ours.bits.bit = bit;
-	req->ours.bits.n_bit = n_bit;
-}
-static inline void
-ethtool_linkmodes_set_req_set_peer_nomask(struct ethtool_linkmodes_set_req *req)
-{
-	req->_present.peer = 1;
-	req->peer._present.nomask = 1;
-}
-static inline void
-ethtool_linkmodes_set_req_set_peer_size(struct ethtool_linkmodes_set_req *req,
-					__u32 size)
-{
-	req->_present.peer = 1;
-	req->peer._present.size = 1;
-	req->peer.size = size;
-}
-static inline void
-__ethtool_linkmodes_set_req_set_peer_bits_bit(struct ethtool_linkmodes_set_req *req,
-					      struct ethtool_bitset_bit *bit,
-					      unsigned int n_bit)
-{
-	free(req->peer.bits.bit);
-	req->peer.bits.bit = bit;
-	req->peer.bits.n_bit = n_bit;
-}
-static inline void
-ethtool_linkmodes_set_req_set_speed(struct ethtool_linkmodes_set_req *req,
-				    __u32 speed)
-{
-	req->_present.speed = 1;
-	req->speed = speed;
-}
-static inline void
-ethtool_linkmodes_set_req_set_duplex(struct ethtool_linkmodes_set_req *req,
-				     __u8 duplex)
-{
-	req->_present.duplex = 1;
-	req->duplex = duplex;
-}
-static inline void
-ethtool_linkmodes_set_req_set_master_slave_cfg(struct ethtool_linkmodes_set_req *req,
-					       __u8 master_slave_cfg)
-{
-	req->_present.master_slave_cfg = 1;
-	req->master_slave_cfg = master_slave_cfg;
-}
-static inline void
-ethtool_linkmodes_set_req_set_master_slave_state(struct ethtool_linkmodes_set_req *req,
-						 __u8 master_slave_state)
-{
-	req->_present.master_slave_state = 1;
-	req->master_slave_state = master_slave_state;
-}
-static inline void
-ethtool_linkmodes_set_req_set_lanes(struct ethtool_linkmodes_set_req *req,
-				    __u32 lanes)
-{
-	req->_present.lanes = 1;
-	req->lanes = lanes;
-}
-static inline void
-ethtool_linkmodes_set_req_set_rate_matching(struct ethtool_linkmodes_set_req *req,
-					    __u8 rate_matching)
-{
-	req->_present.rate_matching = 1;
-	req->rate_matching = rate_matching;
-}
-
-/*
- * Set link modes.
- */
-int ethtool_linkmodes_set(struct ynl_sock *ys,
-			  struct ethtool_linkmodes_set_req *req);
-
-/* ============== ETHTOOL_MSG_LINKSTATE_GET ============== */
-/* ETHTOOL_MSG_LINKSTATE_GET - do */
-struct ethtool_linkstate_get_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_linkstate_get_req *
-ethtool_linkstate_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_linkstate_get_req));
-}
-void ethtool_linkstate_get_req_free(struct ethtool_linkstate_get_req *req);
-
-static inline void
-ethtool_linkstate_get_req_set_header_dev_index(struct ethtool_linkstate_get_req *req,
-					       __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_linkstate_get_req_set_header_dev_name(struct ethtool_linkstate_get_req *req,
-					      const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_linkstate_get_req_set_header_flags(struct ethtool_linkstate_get_req *req,
-					   __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_linkstate_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 link:1;
-		__u32 sqi:1;
-		__u32 sqi_max:1;
-		__u32 ext_state:1;
-		__u32 ext_substate:1;
-		__u32 ext_down_cnt:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u8 link;
-	__u32 sqi;
-	__u32 sqi_max;
-	__u8 ext_state;
-	__u8 ext_substate;
-	__u32 ext_down_cnt;
-};
-
-void ethtool_linkstate_get_rsp_free(struct ethtool_linkstate_get_rsp *rsp);
-
-/*
- * Get link state.
- */
-struct ethtool_linkstate_get_rsp *
-ethtool_linkstate_get(struct ynl_sock *ys,
-		      struct ethtool_linkstate_get_req *req);
-
-/* ETHTOOL_MSG_LINKSTATE_GET - dump */
-struct ethtool_linkstate_get_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_linkstate_get_req_dump *
-ethtool_linkstate_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_linkstate_get_req_dump));
-}
-void
-ethtool_linkstate_get_req_dump_free(struct ethtool_linkstate_get_req_dump *req);
-
-static inline void
-ethtool_linkstate_get_req_dump_set_header_dev_index(struct ethtool_linkstate_get_req_dump *req,
-						    __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_linkstate_get_req_dump_set_header_dev_name(struct ethtool_linkstate_get_req_dump *req,
-						   const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_linkstate_get_req_dump_set_header_flags(struct ethtool_linkstate_get_req_dump *req,
-						__u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_linkstate_get_list {
-	struct ethtool_linkstate_get_list *next;
-	struct ethtool_linkstate_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_linkstate_get_list_free(struct ethtool_linkstate_get_list *rsp);
-
-struct ethtool_linkstate_get_list *
-ethtool_linkstate_get_dump(struct ynl_sock *ys,
-			   struct ethtool_linkstate_get_req_dump *req);
-
-/* ============== ETHTOOL_MSG_DEBUG_GET ============== */
-/* ETHTOOL_MSG_DEBUG_GET - do */
-struct ethtool_debug_get_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_debug_get_req *ethtool_debug_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_debug_get_req));
-}
-void ethtool_debug_get_req_free(struct ethtool_debug_get_req *req);
-
-static inline void
-ethtool_debug_get_req_set_header_dev_index(struct ethtool_debug_get_req *req,
-					   __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_debug_get_req_set_header_dev_name(struct ethtool_debug_get_req *req,
-					  const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_debug_get_req_set_header_flags(struct ethtool_debug_get_req *req,
-				       __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_debug_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 msgmask:1;
-	} _present;
-
-	struct ethtool_header header;
-	struct ethtool_bitset msgmask;
-};
-
-void ethtool_debug_get_rsp_free(struct ethtool_debug_get_rsp *rsp);
-
-/*
- * Get debug message mask.
- */
-struct ethtool_debug_get_rsp *
-ethtool_debug_get(struct ynl_sock *ys, struct ethtool_debug_get_req *req);
-
-/* ETHTOOL_MSG_DEBUG_GET - dump */
-struct ethtool_debug_get_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_debug_get_req_dump *
-ethtool_debug_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_debug_get_req_dump));
-}
-void ethtool_debug_get_req_dump_free(struct ethtool_debug_get_req_dump *req);
-
-static inline void
-ethtool_debug_get_req_dump_set_header_dev_index(struct ethtool_debug_get_req_dump *req,
-						__u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_debug_get_req_dump_set_header_dev_name(struct ethtool_debug_get_req_dump *req,
-					       const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_debug_get_req_dump_set_header_flags(struct ethtool_debug_get_req_dump *req,
-					    __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_debug_get_list {
-	struct ethtool_debug_get_list *next;
-	struct ethtool_debug_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_debug_get_list_free(struct ethtool_debug_get_list *rsp);
-
-struct ethtool_debug_get_list *
-ethtool_debug_get_dump(struct ynl_sock *ys,
-		       struct ethtool_debug_get_req_dump *req);
-
-/* ETHTOOL_MSG_DEBUG_GET - notify */
-struct ethtool_debug_get_ntf {
-	__u16 family;
-	__u8 cmd;
-	struct ynl_ntf_base_type *next;
-	void (*free)(struct ethtool_debug_get_ntf *ntf);
-	struct ethtool_debug_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_debug_get_ntf_free(struct ethtool_debug_get_ntf *rsp);
-
-/* ============== ETHTOOL_MSG_DEBUG_SET ============== */
-/* ETHTOOL_MSG_DEBUG_SET - do */
-struct ethtool_debug_set_req {
-	struct {
-		__u32 header:1;
-		__u32 msgmask:1;
-	} _present;
-
-	struct ethtool_header header;
-	struct ethtool_bitset msgmask;
-};
-
-static inline struct ethtool_debug_set_req *ethtool_debug_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_debug_set_req));
-}
-void ethtool_debug_set_req_free(struct ethtool_debug_set_req *req);
-
-static inline void
-ethtool_debug_set_req_set_header_dev_index(struct ethtool_debug_set_req *req,
-					   __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_debug_set_req_set_header_dev_name(struct ethtool_debug_set_req *req,
-					  const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_debug_set_req_set_header_flags(struct ethtool_debug_set_req *req,
-				       __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-static inline void
-ethtool_debug_set_req_set_msgmask_nomask(struct ethtool_debug_set_req *req)
-{
-	req->_present.msgmask = 1;
-	req->msgmask._present.nomask = 1;
-}
-static inline void
-ethtool_debug_set_req_set_msgmask_size(struct ethtool_debug_set_req *req,
-				       __u32 size)
-{
-	req->_present.msgmask = 1;
-	req->msgmask._present.size = 1;
-	req->msgmask.size = size;
-}
-static inline void
-__ethtool_debug_set_req_set_msgmask_bits_bit(struct ethtool_debug_set_req *req,
-					     struct ethtool_bitset_bit *bit,
-					     unsigned int n_bit)
-{
-	free(req->msgmask.bits.bit);
-	req->msgmask.bits.bit = bit;
-	req->msgmask.bits.n_bit = n_bit;
-}
-
-/*
- * Set debug message mask.
- */
-int ethtool_debug_set(struct ynl_sock *ys, struct ethtool_debug_set_req *req);
-
-/* ============== ETHTOOL_MSG_WOL_GET ============== */
-/* ETHTOOL_MSG_WOL_GET - do */
-struct ethtool_wol_get_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_wol_get_req *ethtool_wol_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_wol_get_req));
-}
-void ethtool_wol_get_req_free(struct ethtool_wol_get_req *req);
-
-static inline void
-ethtool_wol_get_req_set_header_dev_index(struct ethtool_wol_get_req *req,
-					 __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_wol_get_req_set_header_dev_name(struct ethtool_wol_get_req *req,
-					const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_wol_get_req_set_header_flags(struct ethtool_wol_get_req *req,
-				     __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_wol_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 modes:1;
-		__u32 sopass_len;
-	} _present;
-
-	struct ethtool_header header;
-	struct ethtool_bitset modes;
-	void *sopass;
-};
-
-void ethtool_wol_get_rsp_free(struct ethtool_wol_get_rsp *rsp);
-
-/*
- * Get WOL params.
- */
-struct ethtool_wol_get_rsp *
-ethtool_wol_get(struct ynl_sock *ys, struct ethtool_wol_get_req *req);
-
-/* ETHTOOL_MSG_WOL_GET - dump */
-struct ethtool_wol_get_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_wol_get_req_dump *
-ethtool_wol_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_wol_get_req_dump));
-}
-void ethtool_wol_get_req_dump_free(struct ethtool_wol_get_req_dump *req);
-
-static inline void
-ethtool_wol_get_req_dump_set_header_dev_index(struct ethtool_wol_get_req_dump *req,
-					      __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_wol_get_req_dump_set_header_dev_name(struct ethtool_wol_get_req_dump *req,
-					     const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_wol_get_req_dump_set_header_flags(struct ethtool_wol_get_req_dump *req,
-					  __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_wol_get_list {
-	struct ethtool_wol_get_list *next;
-	struct ethtool_wol_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_wol_get_list_free(struct ethtool_wol_get_list *rsp);
-
-struct ethtool_wol_get_list *
-ethtool_wol_get_dump(struct ynl_sock *ys, struct ethtool_wol_get_req_dump *req);
-
-/* ETHTOOL_MSG_WOL_GET - notify */
-struct ethtool_wol_get_ntf {
-	__u16 family;
-	__u8 cmd;
-	struct ynl_ntf_base_type *next;
-	void (*free)(struct ethtool_wol_get_ntf *ntf);
-	struct ethtool_wol_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_wol_get_ntf_free(struct ethtool_wol_get_ntf *rsp);
-
-/* ============== ETHTOOL_MSG_WOL_SET ============== */
-/* ETHTOOL_MSG_WOL_SET - do */
-struct ethtool_wol_set_req {
-	struct {
-		__u32 header:1;
-		__u32 modes:1;
-		__u32 sopass_len;
-	} _present;
-
-	struct ethtool_header header;
-	struct ethtool_bitset modes;
-	void *sopass;
-};
-
-static inline struct ethtool_wol_set_req *ethtool_wol_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_wol_set_req));
-}
-void ethtool_wol_set_req_free(struct ethtool_wol_set_req *req);
-
-static inline void
-ethtool_wol_set_req_set_header_dev_index(struct ethtool_wol_set_req *req,
-					 __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_wol_set_req_set_header_dev_name(struct ethtool_wol_set_req *req,
-					const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_wol_set_req_set_header_flags(struct ethtool_wol_set_req *req,
-				     __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-static inline void
-ethtool_wol_set_req_set_modes_nomask(struct ethtool_wol_set_req *req)
-{
-	req->_present.modes = 1;
-	req->modes._present.nomask = 1;
-}
-static inline void
-ethtool_wol_set_req_set_modes_size(struct ethtool_wol_set_req *req, __u32 size)
-{
-	req->_present.modes = 1;
-	req->modes._present.size = 1;
-	req->modes.size = size;
-}
-static inline void
-__ethtool_wol_set_req_set_modes_bits_bit(struct ethtool_wol_set_req *req,
-					 struct ethtool_bitset_bit *bit,
-					 unsigned int n_bit)
-{
-	free(req->modes.bits.bit);
-	req->modes.bits.bit = bit;
-	req->modes.bits.n_bit = n_bit;
-}
-static inline void
-ethtool_wol_set_req_set_sopass(struct ethtool_wol_set_req *req,
-			       const void *sopass, size_t len)
-{
-	free(req->sopass);
-	req->_present.sopass_len = len;
-	req->sopass = malloc(req->_present.sopass_len);
-	memcpy(req->sopass, sopass, req->_present.sopass_len);
-}
-
-/*
- * Set WOL params.
- */
-int ethtool_wol_set(struct ynl_sock *ys, struct ethtool_wol_set_req *req);
-
-/* ============== ETHTOOL_MSG_FEATURES_GET ============== */
-/* ETHTOOL_MSG_FEATURES_GET - do */
-struct ethtool_features_get_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_features_get_req *
-ethtool_features_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_features_get_req));
-}
-void ethtool_features_get_req_free(struct ethtool_features_get_req *req);
-
-static inline void
-ethtool_features_get_req_set_header_dev_index(struct ethtool_features_get_req *req,
-					      __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_features_get_req_set_header_dev_name(struct ethtool_features_get_req *req,
-					     const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_features_get_req_set_header_flags(struct ethtool_features_get_req *req,
-					  __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_features_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 hw:1;
-		__u32 wanted:1;
-		__u32 active:1;
-		__u32 nochange:1;
-	} _present;
-
-	struct ethtool_header header;
-	struct ethtool_bitset hw;
-	struct ethtool_bitset wanted;
-	struct ethtool_bitset active;
-	struct ethtool_bitset nochange;
-};
-
-void ethtool_features_get_rsp_free(struct ethtool_features_get_rsp *rsp);
-
-/*
- * Get features.
- */
-struct ethtool_features_get_rsp *
-ethtool_features_get(struct ynl_sock *ys, struct ethtool_features_get_req *req);
-
-/* ETHTOOL_MSG_FEATURES_GET - dump */
-struct ethtool_features_get_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_features_get_req_dump *
-ethtool_features_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_features_get_req_dump));
-}
-void
-ethtool_features_get_req_dump_free(struct ethtool_features_get_req_dump *req);
-
-static inline void
-ethtool_features_get_req_dump_set_header_dev_index(struct ethtool_features_get_req_dump *req,
-						   __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_features_get_req_dump_set_header_dev_name(struct ethtool_features_get_req_dump *req,
-						  const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_features_get_req_dump_set_header_flags(struct ethtool_features_get_req_dump *req,
-					       __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_features_get_list {
-	struct ethtool_features_get_list *next;
-	struct ethtool_features_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_features_get_list_free(struct ethtool_features_get_list *rsp);
-
-struct ethtool_features_get_list *
-ethtool_features_get_dump(struct ynl_sock *ys,
-			  struct ethtool_features_get_req_dump *req);
-
-/* ETHTOOL_MSG_FEATURES_GET - notify */
-struct ethtool_features_get_ntf {
-	__u16 family;
-	__u8 cmd;
-	struct ynl_ntf_base_type *next;
-	void (*free)(struct ethtool_features_get_ntf *ntf);
-	struct ethtool_features_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_features_get_ntf_free(struct ethtool_features_get_ntf *rsp);
-
-/* ============== ETHTOOL_MSG_FEATURES_SET ============== */
-/* ETHTOOL_MSG_FEATURES_SET - do */
-struct ethtool_features_set_req {
-	struct {
-		__u32 header:1;
-		__u32 hw:1;
-		__u32 wanted:1;
-		__u32 active:1;
-		__u32 nochange:1;
-	} _present;
-
-	struct ethtool_header header;
-	struct ethtool_bitset hw;
-	struct ethtool_bitset wanted;
-	struct ethtool_bitset active;
-	struct ethtool_bitset nochange;
-};
-
-static inline struct ethtool_features_set_req *
-ethtool_features_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_features_set_req));
-}
-void ethtool_features_set_req_free(struct ethtool_features_set_req *req);
-
-static inline void
-ethtool_features_set_req_set_header_dev_index(struct ethtool_features_set_req *req,
-					      __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_features_set_req_set_header_dev_name(struct ethtool_features_set_req *req,
-					     const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_features_set_req_set_header_flags(struct ethtool_features_set_req *req,
-					  __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-static inline void
-ethtool_features_set_req_set_hw_nomask(struct ethtool_features_set_req *req)
-{
-	req->_present.hw = 1;
-	req->hw._present.nomask = 1;
-}
-static inline void
-ethtool_features_set_req_set_hw_size(struct ethtool_features_set_req *req,
-				     __u32 size)
-{
-	req->_present.hw = 1;
-	req->hw._present.size = 1;
-	req->hw.size = size;
-}
-static inline void
-__ethtool_features_set_req_set_hw_bits_bit(struct ethtool_features_set_req *req,
-					   struct ethtool_bitset_bit *bit,
-					   unsigned int n_bit)
-{
-	free(req->hw.bits.bit);
-	req->hw.bits.bit = bit;
-	req->hw.bits.n_bit = n_bit;
-}
-static inline void
-ethtool_features_set_req_set_wanted_nomask(struct ethtool_features_set_req *req)
-{
-	req->_present.wanted = 1;
-	req->wanted._present.nomask = 1;
-}
-static inline void
-ethtool_features_set_req_set_wanted_size(struct ethtool_features_set_req *req,
-					 __u32 size)
-{
-	req->_present.wanted = 1;
-	req->wanted._present.size = 1;
-	req->wanted.size = size;
-}
-static inline void
-__ethtool_features_set_req_set_wanted_bits_bit(struct ethtool_features_set_req *req,
-					       struct ethtool_bitset_bit *bit,
-					       unsigned int n_bit)
-{
-	free(req->wanted.bits.bit);
-	req->wanted.bits.bit = bit;
-	req->wanted.bits.n_bit = n_bit;
-}
-static inline void
-ethtool_features_set_req_set_active_nomask(struct ethtool_features_set_req *req)
-{
-	req->_present.active = 1;
-	req->active._present.nomask = 1;
-}
-static inline void
-ethtool_features_set_req_set_active_size(struct ethtool_features_set_req *req,
-					 __u32 size)
-{
-	req->_present.active = 1;
-	req->active._present.size = 1;
-	req->active.size = size;
-}
-static inline void
-__ethtool_features_set_req_set_active_bits_bit(struct ethtool_features_set_req *req,
-					       struct ethtool_bitset_bit *bit,
-					       unsigned int n_bit)
-{
-	free(req->active.bits.bit);
-	req->active.bits.bit = bit;
-	req->active.bits.n_bit = n_bit;
-}
-static inline void
-ethtool_features_set_req_set_nochange_nomask(struct ethtool_features_set_req *req)
-{
-	req->_present.nochange = 1;
-	req->nochange._present.nomask = 1;
-}
-static inline void
-ethtool_features_set_req_set_nochange_size(struct ethtool_features_set_req *req,
-					   __u32 size)
-{
-	req->_present.nochange = 1;
-	req->nochange._present.size = 1;
-	req->nochange.size = size;
-}
-static inline void
-__ethtool_features_set_req_set_nochange_bits_bit(struct ethtool_features_set_req *req,
-						 struct ethtool_bitset_bit *bit,
-						 unsigned int n_bit)
-{
-	free(req->nochange.bits.bit);
-	req->nochange.bits.bit = bit;
-	req->nochange.bits.n_bit = n_bit;
-}
-
-struct ethtool_features_set_rsp {
-	struct {
-		__u32 header:1;
-		__u32 hw:1;
-		__u32 wanted:1;
-		__u32 active:1;
-		__u32 nochange:1;
-	} _present;
-
-	struct ethtool_header header;
-	struct ethtool_bitset hw;
-	struct ethtool_bitset wanted;
-	struct ethtool_bitset active;
-	struct ethtool_bitset nochange;
-};
-
-void ethtool_features_set_rsp_free(struct ethtool_features_set_rsp *rsp);
-
-/*
- * Set features.
- */
-struct ethtool_features_set_rsp *
-ethtool_features_set(struct ynl_sock *ys, struct ethtool_features_set_req *req);
-
-/* ============== ETHTOOL_MSG_PRIVFLAGS_GET ============== */
-/* ETHTOOL_MSG_PRIVFLAGS_GET - do */
-struct ethtool_privflags_get_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_privflags_get_req *
-ethtool_privflags_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_privflags_get_req));
-}
-void ethtool_privflags_get_req_free(struct ethtool_privflags_get_req *req);
-
-static inline void
-ethtool_privflags_get_req_set_header_dev_index(struct ethtool_privflags_get_req *req,
-					       __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_privflags_get_req_set_header_dev_name(struct ethtool_privflags_get_req *req,
-					      const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_privflags_get_req_set_header_flags(struct ethtool_privflags_get_req *req,
-					   __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_privflags_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 flags:1;
-	} _present;
-
-	struct ethtool_header header;
-	struct ethtool_bitset flags;
-};
-
-void ethtool_privflags_get_rsp_free(struct ethtool_privflags_get_rsp *rsp);
-
-/*
- * Get device private flags.
- */
-struct ethtool_privflags_get_rsp *
-ethtool_privflags_get(struct ynl_sock *ys,
-		      struct ethtool_privflags_get_req *req);
-
-/* ETHTOOL_MSG_PRIVFLAGS_GET - dump */
-struct ethtool_privflags_get_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_privflags_get_req_dump *
-ethtool_privflags_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_privflags_get_req_dump));
-}
-void
-ethtool_privflags_get_req_dump_free(struct ethtool_privflags_get_req_dump *req);
-
-static inline void
-ethtool_privflags_get_req_dump_set_header_dev_index(struct ethtool_privflags_get_req_dump *req,
-						    __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_privflags_get_req_dump_set_header_dev_name(struct ethtool_privflags_get_req_dump *req,
-						   const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_privflags_get_req_dump_set_header_flags(struct ethtool_privflags_get_req_dump *req,
-						__u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_privflags_get_list {
-	struct ethtool_privflags_get_list *next;
-	struct ethtool_privflags_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_privflags_get_list_free(struct ethtool_privflags_get_list *rsp);
-
-struct ethtool_privflags_get_list *
-ethtool_privflags_get_dump(struct ynl_sock *ys,
-			   struct ethtool_privflags_get_req_dump *req);
-
-/* ETHTOOL_MSG_PRIVFLAGS_GET - notify */
-struct ethtool_privflags_get_ntf {
-	__u16 family;
-	__u8 cmd;
-	struct ynl_ntf_base_type *next;
-	void (*free)(struct ethtool_privflags_get_ntf *ntf);
-	struct ethtool_privflags_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_privflags_get_ntf_free(struct ethtool_privflags_get_ntf *rsp);
-
-/* ============== ETHTOOL_MSG_PRIVFLAGS_SET ============== */
-/* ETHTOOL_MSG_PRIVFLAGS_SET - do */
-struct ethtool_privflags_set_req {
-	struct {
-		__u32 header:1;
-		__u32 flags:1;
-	} _present;
-
-	struct ethtool_header header;
-	struct ethtool_bitset flags;
-};
-
-static inline struct ethtool_privflags_set_req *
-ethtool_privflags_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_privflags_set_req));
-}
-void ethtool_privflags_set_req_free(struct ethtool_privflags_set_req *req);
-
-static inline void
-ethtool_privflags_set_req_set_header_dev_index(struct ethtool_privflags_set_req *req,
-					       __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_privflags_set_req_set_header_dev_name(struct ethtool_privflags_set_req *req,
-					      const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_privflags_set_req_set_header_flags(struct ethtool_privflags_set_req *req,
-					   __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-static inline void
-ethtool_privflags_set_req_set_flags_nomask(struct ethtool_privflags_set_req *req)
-{
-	req->_present.flags = 1;
-	req->flags._present.nomask = 1;
-}
-static inline void
-ethtool_privflags_set_req_set_flags_size(struct ethtool_privflags_set_req *req,
-					 __u32 size)
-{
-	req->_present.flags = 1;
-	req->flags._present.size = 1;
-	req->flags.size = size;
-}
-static inline void
-__ethtool_privflags_set_req_set_flags_bits_bit(struct ethtool_privflags_set_req *req,
-					       struct ethtool_bitset_bit *bit,
-					       unsigned int n_bit)
-{
-	free(req->flags.bits.bit);
-	req->flags.bits.bit = bit;
-	req->flags.bits.n_bit = n_bit;
-}
-
-/*
- * Set device private flags.
- */
-int ethtool_privflags_set(struct ynl_sock *ys,
-			  struct ethtool_privflags_set_req *req);
-
-/* ============== ETHTOOL_MSG_RINGS_GET ============== */
-/* ETHTOOL_MSG_RINGS_GET - do */
-struct ethtool_rings_get_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_rings_get_req *ethtool_rings_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_rings_get_req));
-}
-void ethtool_rings_get_req_free(struct ethtool_rings_get_req *req);
-
-static inline void
-ethtool_rings_get_req_set_header_dev_index(struct ethtool_rings_get_req *req,
-					   __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_rings_get_req_set_header_dev_name(struct ethtool_rings_get_req *req,
-					  const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_rings_get_req_set_header_flags(struct ethtool_rings_get_req *req,
-				       __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_rings_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 rx_max:1;
-		__u32 rx_mini_max:1;
-		__u32 rx_jumbo_max:1;
-		__u32 tx_max:1;
-		__u32 rx:1;
-		__u32 rx_mini:1;
-		__u32 rx_jumbo:1;
-		__u32 tx:1;
-		__u32 rx_buf_len:1;
-		__u32 tcp_data_split:1;
-		__u32 cqe_size:1;
-		__u32 tx_push:1;
-		__u32 rx_push:1;
-		__u32 tx_push_buf_len:1;
-		__u32 tx_push_buf_len_max:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u32 rx_max;
-	__u32 rx_mini_max;
-	__u32 rx_jumbo_max;
-	__u32 tx_max;
-	__u32 rx;
-	__u32 rx_mini;
-	__u32 rx_jumbo;
-	__u32 tx;
-	__u32 rx_buf_len;
-	__u8 tcp_data_split;
-	__u32 cqe_size;
-	__u8 tx_push;
-	__u8 rx_push;
-	__u32 tx_push_buf_len;
-	__u32 tx_push_buf_len_max;
-};
-
-void ethtool_rings_get_rsp_free(struct ethtool_rings_get_rsp *rsp);
-
-/*
- * Get ring params.
- */
-struct ethtool_rings_get_rsp *
-ethtool_rings_get(struct ynl_sock *ys, struct ethtool_rings_get_req *req);
-
-/* ETHTOOL_MSG_RINGS_GET - dump */
-struct ethtool_rings_get_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_rings_get_req_dump *
-ethtool_rings_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_rings_get_req_dump));
-}
-void ethtool_rings_get_req_dump_free(struct ethtool_rings_get_req_dump *req);
-
-static inline void
-ethtool_rings_get_req_dump_set_header_dev_index(struct ethtool_rings_get_req_dump *req,
-						__u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_rings_get_req_dump_set_header_dev_name(struct ethtool_rings_get_req_dump *req,
-					       const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_rings_get_req_dump_set_header_flags(struct ethtool_rings_get_req_dump *req,
-					    __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_rings_get_list {
-	struct ethtool_rings_get_list *next;
-	struct ethtool_rings_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_rings_get_list_free(struct ethtool_rings_get_list *rsp);
-
-struct ethtool_rings_get_list *
-ethtool_rings_get_dump(struct ynl_sock *ys,
-		       struct ethtool_rings_get_req_dump *req);
-
-/* ETHTOOL_MSG_RINGS_GET - notify */
-struct ethtool_rings_get_ntf {
-	__u16 family;
-	__u8 cmd;
-	struct ynl_ntf_base_type *next;
-	void (*free)(struct ethtool_rings_get_ntf *ntf);
-	struct ethtool_rings_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_rings_get_ntf_free(struct ethtool_rings_get_ntf *rsp);
-
-/* ============== ETHTOOL_MSG_RINGS_SET ============== */
-/* ETHTOOL_MSG_RINGS_SET - do */
-struct ethtool_rings_set_req {
-	struct {
-		__u32 header:1;
-		__u32 rx_max:1;
-		__u32 rx_mini_max:1;
-		__u32 rx_jumbo_max:1;
-		__u32 tx_max:1;
-		__u32 rx:1;
-		__u32 rx_mini:1;
-		__u32 rx_jumbo:1;
-		__u32 tx:1;
-		__u32 rx_buf_len:1;
-		__u32 tcp_data_split:1;
-		__u32 cqe_size:1;
-		__u32 tx_push:1;
-		__u32 rx_push:1;
-		__u32 tx_push_buf_len:1;
-		__u32 tx_push_buf_len_max:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u32 rx_max;
-	__u32 rx_mini_max;
-	__u32 rx_jumbo_max;
-	__u32 tx_max;
-	__u32 rx;
-	__u32 rx_mini;
-	__u32 rx_jumbo;
-	__u32 tx;
-	__u32 rx_buf_len;
-	__u8 tcp_data_split;
-	__u32 cqe_size;
-	__u8 tx_push;
-	__u8 rx_push;
-	__u32 tx_push_buf_len;
-	__u32 tx_push_buf_len_max;
-};
-
-static inline struct ethtool_rings_set_req *ethtool_rings_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_rings_set_req));
-}
-void ethtool_rings_set_req_free(struct ethtool_rings_set_req *req);
-
-static inline void
-ethtool_rings_set_req_set_header_dev_index(struct ethtool_rings_set_req *req,
-					   __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_rings_set_req_set_header_dev_name(struct ethtool_rings_set_req *req,
-					  const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_rings_set_req_set_header_flags(struct ethtool_rings_set_req *req,
-				       __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-static inline void
-ethtool_rings_set_req_set_rx_max(struct ethtool_rings_set_req *req,
-				 __u32 rx_max)
-{
-	req->_present.rx_max = 1;
-	req->rx_max = rx_max;
-}
-static inline void
-ethtool_rings_set_req_set_rx_mini_max(struct ethtool_rings_set_req *req,
-				      __u32 rx_mini_max)
-{
-	req->_present.rx_mini_max = 1;
-	req->rx_mini_max = rx_mini_max;
-}
-static inline void
-ethtool_rings_set_req_set_rx_jumbo_max(struct ethtool_rings_set_req *req,
-				       __u32 rx_jumbo_max)
-{
-	req->_present.rx_jumbo_max = 1;
-	req->rx_jumbo_max = rx_jumbo_max;
-}
-static inline void
-ethtool_rings_set_req_set_tx_max(struct ethtool_rings_set_req *req,
-				 __u32 tx_max)
-{
-	req->_present.tx_max = 1;
-	req->tx_max = tx_max;
-}
-static inline void
-ethtool_rings_set_req_set_rx(struct ethtool_rings_set_req *req, __u32 rx)
-{
-	req->_present.rx = 1;
-	req->rx = rx;
-}
-static inline void
-ethtool_rings_set_req_set_rx_mini(struct ethtool_rings_set_req *req,
-				  __u32 rx_mini)
-{
-	req->_present.rx_mini = 1;
-	req->rx_mini = rx_mini;
-}
-static inline void
-ethtool_rings_set_req_set_rx_jumbo(struct ethtool_rings_set_req *req,
-				   __u32 rx_jumbo)
-{
-	req->_present.rx_jumbo = 1;
-	req->rx_jumbo = rx_jumbo;
-}
-static inline void
-ethtool_rings_set_req_set_tx(struct ethtool_rings_set_req *req, __u32 tx)
-{
-	req->_present.tx = 1;
-	req->tx = tx;
-}
-static inline void
-ethtool_rings_set_req_set_rx_buf_len(struct ethtool_rings_set_req *req,
-				     __u32 rx_buf_len)
-{
-	req->_present.rx_buf_len = 1;
-	req->rx_buf_len = rx_buf_len;
-}
-static inline void
-ethtool_rings_set_req_set_tcp_data_split(struct ethtool_rings_set_req *req,
-					 __u8 tcp_data_split)
-{
-	req->_present.tcp_data_split = 1;
-	req->tcp_data_split = tcp_data_split;
-}
-static inline void
-ethtool_rings_set_req_set_cqe_size(struct ethtool_rings_set_req *req,
-				   __u32 cqe_size)
-{
-	req->_present.cqe_size = 1;
-	req->cqe_size = cqe_size;
-}
-static inline void
-ethtool_rings_set_req_set_tx_push(struct ethtool_rings_set_req *req,
-				  __u8 tx_push)
-{
-	req->_present.tx_push = 1;
-	req->tx_push = tx_push;
-}
-static inline void
-ethtool_rings_set_req_set_rx_push(struct ethtool_rings_set_req *req,
-				  __u8 rx_push)
-{
-	req->_present.rx_push = 1;
-	req->rx_push = rx_push;
-}
-static inline void
-ethtool_rings_set_req_set_tx_push_buf_len(struct ethtool_rings_set_req *req,
-					  __u32 tx_push_buf_len)
-{
-	req->_present.tx_push_buf_len = 1;
-	req->tx_push_buf_len = tx_push_buf_len;
-}
-static inline void
-ethtool_rings_set_req_set_tx_push_buf_len_max(struct ethtool_rings_set_req *req,
-					      __u32 tx_push_buf_len_max)
-{
-	req->_present.tx_push_buf_len_max = 1;
-	req->tx_push_buf_len_max = tx_push_buf_len_max;
-}
-
-/*
- * Set ring params.
- */
-int ethtool_rings_set(struct ynl_sock *ys, struct ethtool_rings_set_req *req);
-
-/* ============== ETHTOOL_MSG_CHANNELS_GET ============== */
-/* ETHTOOL_MSG_CHANNELS_GET - do */
-struct ethtool_channels_get_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_channels_get_req *
-ethtool_channels_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_channels_get_req));
-}
-void ethtool_channels_get_req_free(struct ethtool_channels_get_req *req);
-
-static inline void
-ethtool_channels_get_req_set_header_dev_index(struct ethtool_channels_get_req *req,
-					      __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_channels_get_req_set_header_dev_name(struct ethtool_channels_get_req *req,
-					     const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_channels_get_req_set_header_flags(struct ethtool_channels_get_req *req,
-					  __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_channels_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 rx_max:1;
-		__u32 tx_max:1;
-		__u32 other_max:1;
-		__u32 combined_max:1;
-		__u32 rx_count:1;
-		__u32 tx_count:1;
-		__u32 other_count:1;
-		__u32 combined_count:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u32 rx_max;
-	__u32 tx_max;
-	__u32 other_max;
-	__u32 combined_max;
-	__u32 rx_count;
-	__u32 tx_count;
-	__u32 other_count;
-	__u32 combined_count;
-};
-
-void ethtool_channels_get_rsp_free(struct ethtool_channels_get_rsp *rsp);
-
-/*
- * Get channel params.
- */
-struct ethtool_channels_get_rsp *
-ethtool_channels_get(struct ynl_sock *ys, struct ethtool_channels_get_req *req);
-
-/* ETHTOOL_MSG_CHANNELS_GET - dump */
-struct ethtool_channels_get_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_channels_get_req_dump *
-ethtool_channels_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_channels_get_req_dump));
-}
-void
-ethtool_channels_get_req_dump_free(struct ethtool_channels_get_req_dump *req);
-
-static inline void
-ethtool_channels_get_req_dump_set_header_dev_index(struct ethtool_channels_get_req_dump *req,
-						   __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_channels_get_req_dump_set_header_dev_name(struct ethtool_channels_get_req_dump *req,
-						  const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_channels_get_req_dump_set_header_flags(struct ethtool_channels_get_req_dump *req,
-					       __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_channels_get_list {
-	struct ethtool_channels_get_list *next;
-	struct ethtool_channels_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_channels_get_list_free(struct ethtool_channels_get_list *rsp);
-
-struct ethtool_channels_get_list *
-ethtool_channels_get_dump(struct ynl_sock *ys,
-			  struct ethtool_channels_get_req_dump *req);
-
-/* ETHTOOL_MSG_CHANNELS_GET - notify */
-struct ethtool_channels_get_ntf {
-	__u16 family;
-	__u8 cmd;
-	struct ynl_ntf_base_type *next;
-	void (*free)(struct ethtool_channels_get_ntf *ntf);
-	struct ethtool_channels_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_channels_get_ntf_free(struct ethtool_channels_get_ntf *rsp);
-
-/* ============== ETHTOOL_MSG_CHANNELS_SET ============== */
-/* ETHTOOL_MSG_CHANNELS_SET - do */
-struct ethtool_channels_set_req {
-	struct {
-		__u32 header:1;
-		__u32 rx_max:1;
-		__u32 tx_max:1;
-		__u32 other_max:1;
-		__u32 combined_max:1;
-		__u32 rx_count:1;
-		__u32 tx_count:1;
-		__u32 other_count:1;
-		__u32 combined_count:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u32 rx_max;
-	__u32 tx_max;
-	__u32 other_max;
-	__u32 combined_max;
-	__u32 rx_count;
-	__u32 tx_count;
-	__u32 other_count;
-	__u32 combined_count;
-};
-
-static inline struct ethtool_channels_set_req *
-ethtool_channels_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_channels_set_req));
-}
-void ethtool_channels_set_req_free(struct ethtool_channels_set_req *req);
-
-static inline void
-ethtool_channels_set_req_set_header_dev_index(struct ethtool_channels_set_req *req,
-					      __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_channels_set_req_set_header_dev_name(struct ethtool_channels_set_req *req,
-					     const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_channels_set_req_set_header_flags(struct ethtool_channels_set_req *req,
-					  __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-static inline void
-ethtool_channels_set_req_set_rx_max(struct ethtool_channels_set_req *req,
-				    __u32 rx_max)
-{
-	req->_present.rx_max = 1;
-	req->rx_max = rx_max;
-}
-static inline void
-ethtool_channels_set_req_set_tx_max(struct ethtool_channels_set_req *req,
-				    __u32 tx_max)
-{
-	req->_present.tx_max = 1;
-	req->tx_max = tx_max;
-}
-static inline void
-ethtool_channels_set_req_set_other_max(struct ethtool_channels_set_req *req,
-				       __u32 other_max)
-{
-	req->_present.other_max = 1;
-	req->other_max = other_max;
-}
-static inline void
-ethtool_channels_set_req_set_combined_max(struct ethtool_channels_set_req *req,
-					  __u32 combined_max)
-{
-	req->_present.combined_max = 1;
-	req->combined_max = combined_max;
-}
-static inline void
-ethtool_channels_set_req_set_rx_count(struct ethtool_channels_set_req *req,
-				      __u32 rx_count)
-{
-	req->_present.rx_count = 1;
-	req->rx_count = rx_count;
-}
-static inline void
-ethtool_channels_set_req_set_tx_count(struct ethtool_channels_set_req *req,
-				      __u32 tx_count)
-{
-	req->_present.tx_count = 1;
-	req->tx_count = tx_count;
-}
-static inline void
-ethtool_channels_set_req_set_other_count(struct ethtool_channels_set_req *req,
-					 __u32 other_count)
-{
-	req->_present.other_count = 1;
-	req->other_count = other_count;
-}
-static inline void
-ethtool_channels_set_req_set_combined_count(struct ethtool_channels_set_req *req,
-					    __u32 combined_count)
-{
-	req->_present.combined_count = 1;
-	req->combined_count = combined_count;
-}
-
-/*
- * Set channel params.
- */
-int ethtool_channels_set(struct ynl_sock *ys,
-			 struct ethtool_channels_set_req *req);
-
-/* ============== ETHTOOL_MSG_COALESCE_GET ============== */
-/* ETHTOOL_MSG_COALESCE_GET - do */
-struct ethtool_coalesce_get_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_coalesce_get_req *
-ethtool_coalesce_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_coalesce_get_req));
-}
-void ethtool_coalesce_get_req_free(struct ethtool_coalesce_get_req *req);
-
-static inline void
-ethtool_coalesce_get_req_set_header_dev_index(struct ethtool_coalesce_get_req *req,
-					      __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_coalesce_get_req_set_header_dev_name(struct ethtool_coalesce_get_req *req,
-					     const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_coalesce_get_req_set_header_flags(struct ethtool_coalesce_get_req *req,
-					  __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_coalesce_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 rx_usecs:1;
-		__u32 rx_max_frames:1;
-		__u32 rx_usecs_irq:1;
-		__u32 rx_max_frames_irq:1;
-		__u32 tx_usecs:1;
-		__u32 tx_max_frames:1;
-		__u32 tx_usecs_irq:1;
-		__u32 tx_max_frames_irq:1;
-		__u32 stats_block_usecs:1;
-		__u32 use_adaptive_rx:1;
-		__u32 use_adaptive_tx:1;
-		__u32 pkt_rate_low:1;
-		__u32 rx_usecs_low:1;
-		__u32 rx_max_frames_low:1;
-		__u32 tx_usecs_low:1;
-		__u32 tx_max_frames_low:1;
-		__u32 pkt_rate_high:1;
-		__u32 rx_usecs_high:1;
-		__u32 rx_max_frames_high:1;
-		__u32 tx_usecs_high:1;
-		__u32 tx_max_frames_high:1;
-		__u32 rate_sample_interval:1;
-		__u32 use_cqe_mode_tx:1;
-		__u32 use_cqe_mode_rx:1;
-		__u32 tx_aggr_max_bytes:1;
-		__u32 tx_aggr_max_frames:1;
-		__u32 tx_aggr_time_usecs:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u32 rx_usecs;
-	__u32 rx_max_frames;
-	__u32 rx_usecs_irq;
-	__u32 rx_max_frames_irq;
-	__u32 tx_usecs;
-	__u32 tx_max_frames;
-	__u32 tx_usecs_irq;
-	__u32 tx_max_frames_irq;
-	__u32 stats_block_usecs;
-	__u8 use_adaptive_rx;
-	__u8 use_adaptive_tx;
-	__u32 pkt_rate_low;
-	__u32 rx_usecs_low;
-	__u32 rx_max_frames_low;
-	__u32 tx_usecs_low;
-	__u32 tx_max_frames_low;
-	__u32 pkt_rate_high;
-	__u32 rx_usecs_high;
-	__u32 rx_max_frames_high;
-	__u32 tx_usecs_high;
-	__u32 tx_max_frames_high;
-	__u32 rate_sample_interval;
-	__u8 use_cqe_mode_tx;
-	__u8 use_cqe_mode_rx;
-	__u32 tx_aggr_max_bytes;
-	__u32 tx_aggr_max_frames;
-	__u32 tx_aggr_time_usecs;
-};
-
-void ethtool_coalesce_get_rsp_free(struct ethtool_coalesce_get_rsp *rsp);
-
-/*
- * Get coalesce params.
- */
-struct ethtool_coalesce_get_rsp *
-ethtool_coalesce_get(struct ynl_sock *ys, struct ethtool_coalesce_get_req *req);
-
-/* ETHTOOL_MSG_COALESCE_GET - dump */
-struct ethtool_coalesce_get_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_coalesce_get_req_dump *
-ethtool_coalesce_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_coalesce_get_req_dump));
-}
-void
-ethtool_coalesce_get_req_dump_free(struct ethtool_coalesce_get_req_dump *req);
-
-static inline void
-ethtool_coalesce_get_req_dump_set_header_dev_index(struct ethtool_coalesce_get_req_dump *req,
-						   __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_coalesce_get_req_dump_set_header_dev_name(struct ethtool_coalesce_get_req_dump *req,
-						  const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_coalesce_get_req_dump_set_header_flags(struct ethtool_coalesce_get_req_dump *req,
-					       __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_coalesce_get_list {
-	struct ethtool_coalesce_get_list *next;
-	struct ethtool_coalesce_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_coalesce_get_list_free(struct ethtool_coalesce_get_list *rsp);
-
-struct ethtool_coalesce_get_list *
-ethtool_coalesce_get_dump(struct ynl_sock *ys,
-			  struct ethtool_coalesce_get_req_dump *req);
-
-/* ETHTOOL_MSG_COALESCE_GET - notify */
-struct ethtool_coalesce_get_ntf {
-	__u16 family;
-	__u8 cmd;
-	struct ynl_ntf_base_type *next;
-	void (*free)(struct ethtool_coalesce_get_ntf *ntf);
-	struct ethtool_coalesce_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_coalesce_get_ntf_free(struct ethtool_coalesce_get_ntf *rsp);
-
-/* ============== ETHTOOL_MSG_COALESCE_SET ============== */
-/* ETHTOOL_MSG_COALESCE_SET - do */
-struct ethtool_coalesce_set_req {
-	struct {
-		__u32 header:1;
-		__u32 rx_usecs:1;
-		__u32 rx_max_frames:1;
-		__u32 rx_usecs_irq:1;
-		__u32 rx_max_frames_irq:1;
-		__u32 tx_usecs:1;
-		__u32 tx_max_frames:1;
-		__u32 tx_usecs_irq:1;
-		__u32 tx_max_frames_irq:1;
-		__u32 stats_block_usecs:1;
-		__u32 use_adaptive_rx:1;
-		__u32 use_adaptive_tx:1;
-		__u32 pkt_rate_low:1;
-		__u32 rx_usecs_low:1;
-		__u32 rx_max_frames_low:1;
-		__u32 tx_usecs_low:1;
-		__u32 tx_max_frames_low:1;
-		__u32 pkt_rate_high:1;
-		__u32 rx_usecs_high:1;
-		__u32 rx_max_frames_high:1;
-		__u32 tx_usecs_high:1;
-		__u32 tx_max_frames_high:1;
-		__u32 rate_sample_interval:1;
-		__u32 use_cqe_mode_tx:1;
-		__u32 use_cqe_mode_rx:1;
-		__u32 tx_aggr_max_bytes:1;
-		__u32 tx_aggr_max_frames:1;
-		__u32 tx_aggr_time_usecs:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u32 rx_usecs;
-	__u32 rx_max_frames;
-	__u32 rx_usecs_irq;
-	__u32 rx_max_frames_irq;
-	__u32 tx_usecs;
-	__u32 tx_max_frames;
-	__u32 tx_usecs_irq;
-	__u32 tx_max_frames_irq;
-	__u32 stats_block_usecs;
-	__u8 use_adaptive_rx;
-	__u8 use_adaptive_tx;
-	__u32 pkt_rate_low;
-	__u32 rx_usecs_low;
-	__u32 rx_max_frames_low;
-	__u32 tx_usecs_low;
-	__u32 tx_max_frames_low;
-	__u32 pkt_rate_high;
-	__u32 rx_usecs_high;
-	__u32 rx_max_frames_high;
-	__u32 tx_usecs_high;
-	__u32 tx_max_frames_high;
-	__u32 rate_sample_interval;
-	__u8 use_cqe_mode_tx;
-	__u8 use_cqe_mode_rx;
-	__u32 tx_aggr_max_bytes;
-	__u32 tx_aggr_max_frames;
-	__u32 tx_aggr_time_usecs;
-};
-
-static inline struct ethtool_coalesce_set_req *
-ethtool_coalesce_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_coalesce_set_req));
-}
-void ethtool_coalesce_set_req_free(struct ethtool_coalesce_set_req *req);
-
-static inline void
-ethtool_coalesce_set_req_set_header_dev_index(struct ethtool_coalesce_set_req *req,
-					      __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_coalesce_set_req_set_header_dev_name(struct ethtool_coalesce_set_req *req,
-					     const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_coalesce_set_req_set_header_flags(struct ethtool_coalesce_set_req *req,
-					  __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-static inline void
-ethtool_coalesce_set_req_set_rx_usecs(struct ethtool_coalesce_set_req *req,
-				      __u32 rx_usecs)
-{
-	req->_present.rx_usecs = 1;
-	req->rx_usecs = rx_usecs;
-}
-static inline void
-ethtool_coalesce_set_req_set_rx_max_frames(struct ethtool_coalesce_set_req *req,
-					   __u32 rx_max_frames)
-{
-	req->_present.rx_max_frames = 1;
-	req->rx_max_frames = rx_max_frames;
-}
-static inline void
-ethtool_coalesce_set_req_set_rx_usecs_irq(struct ethtool_coalesce_set_req *req,
-					  __u32 rx_usecs_irq)
-{
-	req->_present.rx_usecs_irq = 1;
-	req->rx_usecs_irq = rx_usecs_irq;
-}
-static inline void
-ethtool_coalesce_set_req_set_rx_max_frames_irq(struct ethtool_coalesce_set_req *req,
-					       __u32 rx_max_frames_irq)
-{
-	req->_present.rx_max_frames_irq = 1;
-	req->rx_max_frames_irq = rx_max_frames_irq;
-}
-static inline void
-ethtool_coalesce_set_req_set_tx_usecs(struct ethtool_coalesce_set_req *req,
-				      __u32 tx_usecs)
-{
-	req->_present.tx_usecs = 1;
-	req->tx_usecs = tx_usecs;
-}
-static inline void
-ethtool_coalesce_set_req_set_tx_max_frames(struct ethtool_coalesce_set_req *req,
-					   __u32 tx_max_frames)
-{
-	req->_present.tx_max_frames = 1;
-	req->tx_max_frames = tx_max_frames;
-}
-static inline void
-ethtool_coalesce_set_req_set_tx_usecs_irq(struct ethtool_coalesce_set_req *req,
-					  __u32 tx_usecs_irq)
-{
-	req->_present.tx_usecs_irq = 1;
-	req->tx_usecs_irq = tx_usecs_irq;
-}
-static inline void
-ethtool_coalesce_set_req_set_tx_max_frames_irq(struct ethtool_coalesce_set_req *req,
-					       __u32 tx_max_frames_irq)
-{
-	req->_present.tx_max_frames_irq = 1;
-	req->tx_max_frames_irq = tx_max_frames_irq;
-}
-static inline void
-ethtool_coalesce_set_req_set_stats_block_usecs(struct ethtool_coalesce_set_req *req,
-					       __u32 stats_block_usecs)
-{
-	req->_present.stats_block_usecs = 1;
-	req->stats_block_usecs = stats_block_usecs;
-}
-static inline void
-ethtool_coalesce_set_req_set_use_adaptive_rx(struct ethtool_coalesce_set_req *req,
-					     __u8 use_adaptive_rx)
-{
-	req->_present.use_adaptive_rx = 1;
-	req->use_adaptive_rx = use_adaptive_rx;
-}
-static inline void
-ethtool_coalesce_set_req_set_use_adaptive_tx(struct ethtool_coalesce_set_req *req,
-					     __u8 use_adaptive_tx)
-{
-	req->_present.use_adaptive_tx = 1;
-	req->use_adaptive_tx = use_adaptive_tx;
-}
-static inline void
-ethtool_coalesce_set_req_set_pkt_rate_low(struct ethtool_coalesce_set_req *req,
-					  __u32 pkt_rate_low)
-{
-	req->_present.pkt_rate_low = 1;
-	req->pkt_rate_low = pkt_rate_low;
-}
-static inline void
-ethtool_coalesce_set_req_set_rx_usecs_low(struct ethtool_coalesce_set_req *req,
-					  __u32 rx_usecs_low)
-{
-	req->_present.rx_usecs_low = 1;
-	req->rx_usecs_low = rx_usecs_low;
-}
-static inline void
-ethtool_coalesce_set_req_set_rx_max_frames_low(struct ethtool_coalesce_set_req *req,
-					       __u32 rx_max_frames_low)
-{
-	req->_present.rx_max_frames_low = 1;
-	req->rx_max_frames_low = rx_max_frames_low;
-}
-static inline void
-ethtool_coalesce_set_req_set_tx_usecs_low(struct ethtool_coalesce_set_req *req,
-					  __u32 tx_usecs_low)
-{
-	req->_present.tx_usecs_low = 1;
-	req->tx_usecs_low = tx_usecs_low;
-}
-static inline void
-ethtool_coalesce_set_req_set_tx_max_frames_low(struct ethtool_coalesce_set_req *req,
-					       __u32 tx_max_frames_low)
-{
-	req->_present.tx_max_frames_low = 1;
-	req->tx_max_frames_low = tx_max_frames_low;
-}
-static inline void
-ethtool_coalesce_set_req_set_pkt_rate_high(struct ethtool_coalesce_set_req *req,
-					   __u32 pkt_rate_high)
-{
-	req->_present.pkt_rate_high = 1;
-	req->pkt_rate_high = pkt_rate_high;
-}
-static inline void
-ethtool_coalesce_set_req_set_rx_usecs_high(struct ethtool_coalesce_set_req *req,
-					   __u32 rx_usecs_high)
-{
-	req->_present.rx_usecs_high = 1;
-	req->rx_usecs_high = rx_usecs_high;
-}
-static inline void
-ethtool_coalesce_set_req_set_rx_max_frames_high(struct ethtool_coalesce_set_req *req,
-						__u32 rx_max_frames_high)
-{
-	req->_present.rx_max_frames_high = 1;
-	req->rx_max_frames_high = rx_max_frames_high;
-}
-static inline void
-ethtool_coalesce_set_req_set_tx_usecs_high(struct ethtool_coalesce_set_req *req,
-					   __u32 tx_usecs_high)
-{
-	req->_present.tx_usecs_high = 1;
-	req->tx_usecs_high = tx_usecs_high;
-}
-static inline void
-ethtool_coalesce_set_req_set_tx_max_frames_high(struct ethtool_coalesce_set_req *req,
-						__u32 tx_max_frames_high)
-{
-	req->_present.tx_max_frames_high = 1;
-	req->tx_max_frames_high = tx_max_frames_high;
-}
-static inline void
-ethtool_coalesce_set_req_set_rate_sample_interval(struct ethtool_coalesce_set_req *req,
-						  __u32 rate_sample_interval)
-{
-	req->_present.rate_sample_interval = 1;
-	req->rate_sample_interval = rate_sample_interval;
-}
-static inline void
-ethtool_coalesce_set_req_set_use_cqe_mode_tx(struct ethtool_coalesce_set_req *req,
-					     __u8 use_cqe_mode_tx)
-{
-	req->_present.use_cqe_mode_tx = 1;
-	req->use_cqe_mode_tx = use_cqe_mode_tx;
-}
-static inline void
-ethtool_coalesce_set_req_set_use_cqe_mode_rx(struct ethtool_coalesce_set_req *req,
-					     __u8 use_cqe_mode_rx)
-{
-	req->_present.use_cqe_mode_rx = 1;
-	req->use_cqe_mode_rx = use_cqe_mode_rx;
-}
-static inline void
-ethtool_coalesce_set_req_set_tx_aggr_max_bytes(struct ethtool_coalesce_set_req *req,
-					       __u32 tx_aggr_max_bytes)
-{
-	req->_present.tx_aggr_max_bytes = 1;
-	req->tx_aggr_max_bytes = tx_aggr_max_bytes;
-}
-static inline void
-ethtool_coalesce_set_req_set_tx_aggr_max_frames(struct ethtool_coalesce_set_req *req,
-						__u32 tx_aggr_max_frames)
-{
-	req->_present.tx_aggr_max_frames = 1;
-	req->tx_aggr_max_frames = tx_aggr_max_frames;
-}
-static inline void
-ethtool_coalesce_set_req_set_tx_aggr_time_usecs(struct ethtool_coalesce_set_req *req,
-						__u32 tx_aggr_time_usecs)
-{
-	req->_present.tx_aggr_time_usecs = 1;
-	req->tx_aggr_time_usecs = tx_aggr_time_usecs;
-}
-
-/*
- * Set coalesce params.
- */
-int ethtool_coalesce_set(struct ynl_sock *ys,
-			 struct ethtool_coalesce_set_req *req);
-
-/* ============== ETHTOOL_MSG_PAUSE_GET ============== */
-/* ETHTOOL_MSG_PAUSE_GET - do */
-struct ethtool_pause_get_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_pause_get_req *ethtool_pause_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_pause_get_req));
-}
-void ethtool_pause_get_req_free(struct ethtool_pause_get_req *req);
-
-static inline void
-ethtool_pause_get_req_set_header_dev_index(struct ethtool_pause_get_req *req,
-					   __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_pause_get_req_set_header_dev_name(struct ethtool_pause_get_req *req,
-					  const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_pause_get_req_set_header_flags(struct ethtool_pause_get_req *req,
-				       __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_pause_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 autoneg:1;
-		__u32 rx:1;
-		__u32 tx:1;
-		__u32 stats:1;
-		__u32 stats_src:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u8 autoneg;
-	__u8 rx;
-	__u8 tx;
-	struct ethtool_pause_stat stats;
-	__u32 stats_src;
-};
-
-void ethtool_pause_get_rsp_free(struct ethtool_pause_get_rsp *rsp);
-
-/*
- * Get pause params.
- */
-struct ethtool_pause_get_rsp *
-ethtool_pause_get(struct ynl_sock *ys, struct ethtool_pause_get_req *req);
-
-/* ETHTOOL_MSG_PAUSE_GET - dump */
-struct ethtool_pause_get_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_pause_get_req_dump *
-ethtool_pause_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_pause_get_req_dump));
-}
-void ethtool_pause_get_req_dump_free(struct ethtool_pause_get_req_dump *req);
-
-static inline void
-ethtool_pause_get_req_dump_set_header_dev_index(struct ethtool_pause_get_req_dump *req,
-						__u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_pause_get_req_dump_set_header_dev_name(struct ethtool_pause_get_req_dump *req,
-					       const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_pause_get_req_dump_set_header_flags(struct ethtool_pause_get_req_dump *req,
-					    __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_pause_get_list {
-	struct ethtool_pause_get_list *next;
-	struct ethtool_pause_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_pause_get_list_free(struct ethtool_pause_get_list *rsp);
-
-struct ethtool_pause_get_list *
-ethtool_pause_get_dump(struct ynl_sock *ys,
-		       struct ethtool_pause_get_req_dump *req);
-
-/* ETHTOOL_MSG_PAUSE_GET - notify */
-struct ethtool_pause_get_ntf {
-	__u16 family;
-	__u8 cmd;
-	struct ynl_ntf_base_type *next;
-	void (*free)(struct ethtool_pause_get_ntf *ntf);
-	struct ethtool_pause_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_pause_get_ntf_free(struct ethtool_pause_get_ntf *rsp);
-
-/* ============== ETHTOOL_MSG_PAUSE_SET ============== */
-/* ETHTOOL_MSG_PAUSE_SET - do */
-struct ethtool_pause_set_req {
-	struct {
-		__u32 header:1;
-		__u32 autoneg:1;
-		__u32 rx:1;
-		__u32 tx:1;
-		__u32 stats:1;
-		__u32 stats_src:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u8 autoneg;
-	__u8 rx;
-	__u8 tx;
-	struct ethtool_pause_stat stats;
-	__u32 stats_src;
-};
-
-static inline struct ethtool_pause_set_req *ethtool_pause_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_pause_set_req));
-}
-void ethtool_pause_set_req_free(struct ethtool_pause_set_req *req);
-
-static inline void
-ethtool_pause_set_req_set_header_dev_index(struct ethtool_pause_set_req *req,
-					   __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_pause_set_req_set_header_dev_name(struct ethtool_pause_set_req *req,
-					  const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_pause_set_req_set_header_flags(struct ethtool_pause_set_req *req,
-				       __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-static inline void
-ethtool_pause_set_req_set_autoneg(struct ethtool_pause_set_req *req,
-				  __u8 autoneg)
-{
-	req->_present.autoneg = 1;
-	req->autoneg = autoneg;
-}
-static inline void
-ethtool_pause_set_req_set_rx(struct ethtool_pause_set_req *req, __u8 rx)
-{
-	req->_present.rx = 1;
-	req->rx = rx;
-}
-static inline void
-ethtool_pause_set_req_set_tx(struct ethtool_pause_set_req *req, __u8 tx)
-{
-	req->_present.tx = 1;
-	req->tx = tx;
-}
-static inline void
-ethtool_pause_set_req_set_stats_tx_frames(struct ethtool_pause_set_req *req,
-					  __u64 tx_frames)
-{
-	req->_present.stats = 1;
-	req->stats._present.tx_frames = 1;
-	req->stats.tx_frames = tx_frames;
-}
-static inline void
-ethtool_pause_set_req_set_stats_rx_frames(struct ethtool_pause_set_req *req,
-					  __u64 rx_frames)
-{
-	req->_present.stats = 1;
-	req->stats._present.rx_frames = 1;
-	req->stats.rx_frames = rx_frames;
-}
-static inline void
-ethtool_pause_set_req_set_stats_src(struct ethtool_pause_set_req *req,
-				    __u32 stats_src)
-{
-	req->_present.stats_src = 1;
-	req->stats_src = stats_src;
-}
-
-/*
- * Set pause params.
- */
-int ethtool_pause_set(struct ynl_sock *ys, struct ethtool_pause_set_req *req);
-
-/* ============== ETHTOOL_MSG_EEE_GET ============== */
-/* ETHTOOL_MSG_EEE_GET - do */
-struct ethtool_eee_get_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_eee_get_req *ethtool_eee_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_eee_get_req));
-}
-void ethtool_eee_get_req_free(struct ethtool_eee_get_req *req);
-
-static inline void
-ethtool_eee_get_req_set_header_dev_index(struct ethtool_eee_get_req *req,
-					 __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_eee_get_req_set_header_dev_name(struct ethtool_eee_get_req *req,
-					const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_eee_get_req_set_header_flags(struct ethtool_eee_get_req *req,
-				     __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_eee_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 modes_ours:1;
-		__u32 modes_peer:1;
-		__u32 active:1;
-		__u32 enabled:1;
-		__u32 tx_lpi_enabled:1;
-		__u32 tx_lpi_timer:1;
-	} _present;
-
-	struct ethtool_header header;
-	struct ethtool_bitset modes_ours;
-	struct ethtool_bitset modes_peer;
-	__u8 active;
-	__u8 enabled;
-	__u8 tx_lpi_enabled;
-	__u32 tx_lpi_timer;
-};
-
-void ethtool_eee_get_rsp_free(struct ethtool_eee_get_rsp *rsp);
-
-/*
- * Get eee params.
- */
-struct ethtool_eee_get_rsp *
-ethtool_eee_get(struct ynl_sock *ys, struct ethtool_eee_get_req *req);
-
-/* ETHTOOL_MSG_EEE_GET - dump */
-struct ethtool_eee_get_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_eee_get_req_dump *
-ethtool_eee_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_eee_get_req_dump));
-}
-void ethtool_eee_get_req_dump_free(struct ethtool_eee_get_req_dump *req);
-
-static inline void
-ethtool_eee_get_req_dump_set_header_dev_index(struct ethtool_eee_get_req_dump *req,
-					      __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_eee_get_req_dump_set_header_dev_name(struct ethtool_eee_get_req_dump *req,
-					     const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_eee_get_req_dump_set_header_flags(struct ethtool_eee_get_req_dump *req,
-					  __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_eee_get_list {
-	struct ethtool_eee_get_list *next;
-	struct ethtool_eee_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_eee_get_list_free(struct ethtool_eee_get_list *rsp);
-
-struct ethtool_eee_get_list *
-ethtool_eee_get_dump(struct ynl_sock *ys, struct ethtool_eee_get_req_dump *req);
-
-/* ETHTOOL_MSG_EEE_GET - notify */
-struct ethtool_eee_get_ntf {
-	__u16 family;
-	__u8 cmd;
-	struct ynl_ntf_base_type *next;
-	void (*free)(struct ethtool_eee_get_ntf *ntf);
-	struct ethtool_eee_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_eee_get_ntf_free(struct ethtool_eee_get_ntf *rsp);
-
-/* ============== ETHTOOL_MSG_EEE_SET ============== */
-/* ETHTOOL_MSG_EEE_SET - do */
-struct ethtool_eee_set_req {
-	struct {
-		__u32 header:1;
-		__u32 modes_ours:1;
-		__u32 modes_peer:1;
-		__u32 active:1;
-		__u32 enabled:1;
-		__u32 tx_lpi_enabled:1;
-		__u32 tx_lpi_timer:1;
-	} _present;
-
-	struct ethtool_header header;
-	struct ethtool_bitset modes_ours;
-	struct ethtool_bitset modes_peer;
-	__u8 active;
-	__u8 enabled;
-	__u8 tx_lpi_enabled;
-	__u32 tx_lpi_timer;
-};
-
-static inline struct ethtool_eee_set_req *ethtool_eee_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_eee_set_req));
-}
-void ethtool_eee_set_req_free(struct ethtool_eee_set_req *req);
-
-static inline void
-ethtool_eee_set_req_set_header_dev_index(struct ethtool_eee_set_req *req,
-					 __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_eee_set_req_set_header_dev_name(struct ethtool_eee_set_req *req,
-					const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_eee_set_req_set_header_flags(struct ethtool_eee_set_req *req,
-				     __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-static inline void
-ethtool_eee_set_req_set_modes_ours_nomask(struct ethtool_eee_set_req *req)
-{
-	req->_present.modes_ours = 1;
-	req->modes_ours._present.nomask = 1;
-}
-static inline void
-ethtool_eee_set_req_set_modes_ours_size(struct ethtool_eee_set_req *req,
-					__u32 size)
-{
-	req->_present.modes_ours = 1;
-	req->modes_ours._present.size = 1;
-	req->modes_ours.size = size;
-}
-static inline void
-__ethtool_eee_set_req_set_modes_ours_bits_bit(struct ethtool_eee_set_req *req,
-					      struct ethtool_bitset_bit *bit,
-					      unsigned int n_bit)
-{
-	free(req->modes_ours.bits.bit);
-	req->modes_ours.bits.bit = bit;
-	req->modes_ours.bits.n_bit = n_bit;
-}
-static inline void
-ethtool_eee_set_req_set_modes_peer_nomask(struct ethtool_eee_set_req *req)
-{
-	req->_present.modes_peer = 1;
-	req->modes_peer._present.nomask = 1;
-}
-static inline void
-ethtool_eee_set_req_set_modes_peer_size(struct ethtool_eee_set_req *req,
-					__u32 size)
-{
-	req->_present.modes_peer = 1;
-	req->modes_peer._present.size = 1;
-	req->modes_peer.size = size;
-}
-static inline void
-__ethtool_eee_set_req_set_modes_peer_bits_bit(struct ethtool_eee_set_req *req,
-					      struct ethtool_bitset_bit *bit,
-					      unsigned int n_bit)
-{
-	free(req->modes_peer.bits.bit);
-	req->modes_peer.bits.bit = bit;
-	req->modes_peer.bits.n_bit = n_bit;
-}
-static inline void
-ethtool_eee_set_req_set_active(struct ethtool_eee_set_req *req, __u8 active)
-{
-	req->_present.active = 1;
-	req->active = active;
-}
-static inline void
-ethtool_eee_set_req_set_enabled(struct ethtool_eee_set_req *req, __u8 enabled)
-{
-	req->_present.enabled = 1;
-	req->enabled = enabled;
-}
-static inline void
-ethtool_eee_set_req_set_tx_lpi_enabled(struct ethtool_eee_set_req *req,
-				       __u8 tx_lpi_enabled)
-{
-	req->_present.tx_lpi_enabled = 1;
-	req->tx_lpi_enabled = tx_lpi_enabled;
-}
-static inline void
-ethtool_eee_set_req_set_tx_lpi_timer(struct ethtool_eee_set_req *req,
-				     __u32 tx_lpi_timer)
-{
-	req->_present.tx_lpi_timer = 1;
-	req->tx_lpi_timer = tx_lpi_timer;
-}
-
-/*
- * Set eee params.
- */
-int ethtool_eee_set(struct ynl_sock *ys, struct ethtool_eee_set_req *req);
-
-/* ============== ETHTOOL_MSG_TSINFO_GET ============== */
-/* ETHTOOL_MSG_TSINFO_GET - do */
-struct ethtool_tsinfo_get_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_tsinfo_get_req *ethtool_tsinfo_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_tsinfo_get_req));
-}
-void ethtool_tsinfo_get_req_free(struct ethtool_tsinfo_get_req *req);
-
-static inline void
-ethtool_tsinfo_get_req_set_header_dev_index(struct ethtool_tsinfo_get_req *req,
-					    __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_tsinfo_get_req_set_header_dev_name(struct ethtool_tsinfo_get_req *req,
-					   const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_tsinfo_get_req_set_header_flags(struct ethtool_tsinfo_get_req *req,
-					__u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_tsinfo_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 timestamping:1;
-		__u32 tx_types:1;
-		__u32 rx_filters:1;
-		__u32 phc_index:1;
-	} _present;
-
-	struct ethtool_header header;
-	struct ethtool_bitset timestamping;
-	struct ethtool_bitset tx_types;
-	struct ethtool_bitset rx_filters;
-	__u32 phc_index;
-};
-
-void ethtool_tsinfo_get_rsp_free(struct ethtool_tsinfo_get_rsp *rsp);
-
-/*
- * Get tsinfo params.
- */
-struct ethtool_tsinfo_get_rsp *
-ethtool_tsinfo_get(struct ynl_sock *ys, struct ethtool_tsinfo_get_req *req);
-
-/* ETHTOOL_MSG_TSINFO_GET - dump */
-struct ethtool_tsinfo_get_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_tsinfo_get_req_dump *
-ethtool_tsinfo_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_tsinfo_get_req_dump));
-}
-void ethtool_tsinfo_get_req_dump_free(struct ethtool_tsinfo_get_req_dump *req);
-
-static inline void
-ethtool_tsinfo_get_req_dump_set_header_dev_index(struct ethtool_tsinfo_get_req_dump *req,
-						 __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_tsinfo_get_req_dump_set_header_dev_name(struct ethtool_tsinfo_get_req_dump *req,
-						const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_tsinfo_get_req_dump_set_header_flags(struct ethtool_tsinfo_get_req_dump *req,
-					     __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_tsinfo_get_list {
-	struct ethtool_tsinfo_get_list *next;
-	struct ethtool_tsinfo_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_tsinfo_get_list_free(struct ethtool_tsinfo_get_list *rsp);
-
-struct ethtool_tsinfo_get_list *
-ethtool_tsinfo_get_dump(struct ynl_sock *ys,
-			struct ethtool_tsinfo_get_req_dump *req);
-
-/* ============== ETHTOOL_MSG_CABLE_TEST_ACT ============== */
-/* ETHTOOL_MSG_CABLE_TEST_ACT - do */
-struct ethtool_cable_test_act_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_cable_test_act_req *
-ethtool_cable_test_act_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_cable_test_act_req));
-}
-void ethtool_cable_test_act_req_free(struct ethtool_cable_test_act_req *req);
-
-static inline void
-ethtool_cable_test_act_req_set_header_dev_index(struct ethtool_cable_test_act_req *req,
-						__u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_cable_test_act_req_set_header_dev_name(struct ethtool_cable_test_act_req *req,
-					       const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_cable_test_act_req_set_header_flags(struct ethtool_cable_test_act_req *req,
-					    __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-/*
- * Cable test.
- */
-int ethtool_cable_test_act(struct ynl_sock *ys,
-			   struct ethtool_cable_test_act_req *req);
-
-/* ============== ETHTOOL_MSG_CABLE_TEST_TDR_ACT ============== */
-/* ETHTOOL_MSG_CABLE_TEST_TDR_ACT - do */
-struct ethtool_cable_test_tdr_act_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_cable_test_tdr_act_req *
-ethtool_cable_test_tdr_act_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_cable_test_tdr_act_req));
-}
-void
-ethtool_cable_test_tdr_act_req_free(struct ethtool_cable_test_tdr_act_req *req);
-
-static inline void
-ethtool_cable_test_tdr_act_req_set_header_dev_index(struct ethtool_cable_test_tdr_act_req *req,
-						    __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_cable_test_tdr_act_req_set_header_dev_name(struct ethtool_cable_test_tdr_act_req *req,
-						   const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_cable_test_tdr_act_req_set_header_flags(struct ethtool_cable_test_tdr_act_req *req,
-						__u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-/*
- * Cable test TDR.
- */
-int ethtool_cable_test_tdr_act(struct ynl_sock *ys,
-			       struct ethtool_cable_test_tdr_act_req *req);
-
-/* ============== ETHTOOL_MSG_TUNNEL_INFO_GET ============== */
-/* ETHTOOL_MSG_TUNNEL_INFO_GET - do */
-struct ethtool_tunnel_info_get_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_tunnel_info_get_req *
-ethtool_tunnel_info_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_tunnel_info_get_req));
-}
-void ethtool_tunnel_info_get_req_free(struct ethtool_tunnel_info_get_req *req);
-
-static inline void
-ethtool_tunnel_info_get_req_set_header_dev_index(struct ethtool_tunnel_info_get_req *req,
-						 __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_tunnel_info_get_req_set_header_dev_name(struct ethtool_tunnel_info_get_req *req,
-						const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_tunnel_info_get_req_set_header_flags(struct ethtool_tunnel_info_get_req *req,
-					     __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_tunnel_info_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 udp_ports:1;
-	} _present;
-
-	struct ethtool_header header;
-	struct ethtool_tunnel_udp udp_ports;
-};
-
-void ethtool_tunnel_info_get_rsp_free(struct ethtool_tunnel_info_get_rsp *rsp);
-
-/*
- * Get tsinfo params.
- */
-struct ethtool_tunnel_info_get_rsp *
-ethtool_tunnel_info_get(struct ynl_sock *ys,
-			struct ethtool_tunnel_info_get_req *req);
-
-/* ETHTOOL_MSG_TUNNEL_INFO_GET - dump */
-struct ethtool_tunnel_info_get_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_tunnel_info_get_req_dump *
-ethtool_tunnel_info_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_tunnel_info_get_req_dump));
-}
-void
-ethtool_tunnel_info_get_req_dump_free(struct ethtool_tunnel_info_get_req_dump *req);
-
-static inline void
-ethtool_tunnel_info_get_req_dump_set_header_dev_index(struct ethtool_tunnel_info_get_req_dump *req,
-						      __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_tunnel_info_get_req_dump_set_header_dev_name(struct ethtool_tunnel_info_get_req_dump *req,
-						     const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_tunnel_info_get_req_dump_set_header_flags(struct ethtool_tunnel_info_get_req_dump *req,
-						  __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_tunnel_info_get_list {
-	struct ethtool_tunnel_info_get_list *next;
-	struct ethtool_tunnel_info_get_rsp obj __attribute__((aligned(8)));
-};
-
-void
-ethtool_tunnel_info_get_list_free(struct ethtool_tunnel_info_get_list *rsp);
-
-struct ethtool_tunnel_info_get_list *
-ethtool_tunnel_info_get_dump(struct ynl_sock *ys,
-			     struct ethtool_tunnel_info_get_req_dump *req);
-
-/* ============== ETHTOOL_MSG_FEC_GET ============== */
-/* ETHTOOL_MSG_FEC_GET - do */
-struct ethtool_fec_get_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_fec_get_req *ethtool_fec_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_fec_get_req));
-}
-void ethtool_fec_get_req_free(struct ethtool_fec_get_req *req);
-
-static inline void
-ethtool_fec_get_req_set_header_dev_index(struct ethtool_fec_get_req *req,
-					 __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_fec_get_req_set_header_dev_name(struct ethtool_fec_get_req *req,
-					const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_fec_get_req_set_header_flags(struct ethtool_fec_get_req *req,
-				     __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_fec_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 modes:1;
-		__u32 auto_:1;
-		__u32 active:1;
-		__u32 stats:1;
-	} _present;
-
-	struct ethtool_header header;
-	struct ethtool_bitset modes;
-	__u8 auto_;
-	__u32 active;
-	struct ethtool_fec_stat stats;
-};
-
-void ethtool_fec_get_rsp_free(struct ethtool_fec_get_rsp *rsp);
-
-/*
- * Get FEC params.
- */
-struct ethtool_fec_get_rsp *
-ethtool_fec_get(struct ynl_sock *ys, struct ethtool_fec_get_req *req);
-
-/* ETHTOOL_MSG_FEC_GET - dump */
-struct ethtool_fec_get_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_fec_get_req_dump *
-ethtool_fec_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_fec_get_req_dump));
-}
-void ethtool_fec_get_req_dump_free(struct ethtool_fec_get_req_dump *req);
-
-static inline void
-ethtool_fec_get_req_dump_set_header_dev_index(struct ethtool_fec_get_req_dump *req,
-					      __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_fec_get_req_dump_set_header_dev_name(struct ethtool_fec_get_req_dump *req,
-					     const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_fec_get_req_dump_set_header_flags(struct ethtool_fec_get_req_dump *req,
-					  __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_fec_get_list {
-	struct ethtool_fec_get_list *next;
-	struct ethtool_fec_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_fec_get_list_free(struct ethtool_fec_get_list *rsp);
-
-struct ethtool_fec_get_list *
-ethtool_fec_get_dump(struct ynl_sock *ys, struct ethtool_fec_get_req_dump *req);
-
-/* ETHTOOL_MSG_FEC_GET - notify */
-struct ethtool_fec_get_ntf {
-	__u16 family;
-	__u8 cmd;
-	struct ynl_ntf_base_type *next;
-	void (*free)(struct ethtool_fec_get_ntf *ntf);
-	struct ethtool_fec_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_fec_get_ntf_free(struct ethtool_fec_get_ntf *rsp);
-
-/* ============== ETHTOOL_MSG_FEC_SET ============== */
-/* ETHTOOL_MSG_FEC_SET - do */
-struct ethtool_fec_set_req {
-	struct {
-		__u32 header:1;
-		__u32 modes:1;
-		__u32 auto_:1;
-		__u32 active:1;
-		__u32 stats:1;
-	} _present;
-
-	struct ethtool_header header;
-	struct ethtool_bitset modes;
-	__u8 auto_;
-	__u32 active;
-	struct ethtool_fec_stat stats;
-};
-
-static inline struct ethtool_fec_set_req *ethtool_fec_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_fec_set_req));
-}
-void ethtool_fec_set_req_free(struct ethtool_fec_set_req *req);
-
-static inline void
-ethtool_fec_set_req_set_header_dev_index(struct ethtool_fec_set_req *req,
-					 __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_fec_set_req_set_header_dev_name(struct ethtool_fec_set_req *req,
-					const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_fec_set_req_set_header_flags(struct ethtool_fec_set_req *req,
-				     __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-static inline void
-ethtool_fec_set_req_set_modes_nomask(struct ethtool_fec_set_req *req)
-{
-	req->_present.modes = 1;
-	req->modes._present.nomask = 1;
-}
-static inline void
-ethtool_fec_set_req_set_modes_size(struct ethtool_fec_set_req *req, __u32 size)
-{
-	req->_present.modes = 1;
-	req->modes._present.size = 1;
-	req->modes.size = size;
-}
-static inline void
-__ethtool_fec_set_req_set_modes_bits_bit(struct ethtool_fec_set_req *req,
-					 struct ethtool_bitset_bit *bit,
-					 unsigned int n_bit)
-{
-	free(req->modes.bits.bit);
-	req->modes.bits.bit = bit;
-	req->modes.bits.n_bit = n_bit;
-}
-static inline void
-ethtool_fec_set_req_set_auto_(struct ethtool_fec_set_req *req, __u8 auto_)
-{
-	req->_present.auto_ = 1;
-	req->auto_ = auto_;
-}
-static inline void
-ethtool_fec_set_req_set_active(struct ethtool_fec_set_req *req, __u32 active)
-{
-	req->_present.active = 1;
-	req->active = active;
-}
-static inline void
-ethtool_fec_set_req_set_stats_corrected(struct ethtool_fec_set_req *req,
-					const void *corrected, size_t len)
-{
-	free(req->stats.corrected);
-	req->stats._present.corrected_len = len;
-	req->stats.corrected = malloc(req->stats._present.corrected_len);
-	memcpy(req->stats.corrected, corrected, req->stats._present.corrected_len);
-}
-static inline void
-ethtool_fec_set_req_set_stats_uncorr(struct ethtool_fec_set_req *req,
-				     const void *uncorr, size_t len)
-{
-	free(req->stats.uncorr);
-	req->stats._present.uncorr_len = len;
-	req->stats.uncorr = malloc(req->stats._present.uncorr_len);
-	memcpy(req->stats.uncorr, uncorr, req->stats._present.uncorr_len);
-}
-static inline void
-ethtool_fec_set_req_set_stats_corr_bits(struct ethtool_fec_set_req *req,
-					const void *corr_bits, size_t len)
-{
-	free(req->stats.corr_bits);
-	req->stats._present.corr_bits_len = len;
-	req->stats.corr_bits = malloc(req->stats._present.corr_bits_len);
-	memcpy(req->stats.corr_bits, corr_bits, req->stats._present.corr_bits_len);
-}
-
-/*
- * Set FEC params.
- */
-int ethtool_fec_set(struct ynl_sock *ys, struct ethtool_fec_set_req *req);
-
-/* ============== ETHTOOL_MSG_MODULE_EEPROM_GET ============== */
-/* ETHTOOL_MSG_MODULE_EEPROM_GET - do */
-struct ethtool_module_eeprom_get_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_module_eeprom_get_req *
-ethtool_module_eeprom_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_module_eeprom_get_req));
-}
-void
-ethtool_module_eeprom_get_req_free(struct ethtool_module_eeprom_get_req *req);
-
-static inline void
-ethtool_module_eeprom_get_req_set_header_dev_index(struct ethtool_module_eeprom_get_req *req,
-						   __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_module_eeprom_get_req_set_header_dev_name(struct ethtool_module_eeprom_get_req *req,
-						  const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_module_eeprom_get_req_set_header_flags(struct ethtool_module_eeprom_get_req *req,
-					       __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_module_eeprom_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 offset:1;
-		__u32 length:1;
-		__u32 page:1;
-		__u32 bank:1;
-		__u32 i2c_address:1;
-		__u32 data_len;
-	} _present;
-
-	struct ethtool_header header;
-	__u32 offset;
-	__u32 length;
-	__u8 page;
-	__u8 bank;
-	__u8 i2c_address;
-	void *data;
-};
-
-void
-ethtool_module_eeprom_get_rsp_free(struct ethtool_module_eeprom_get_rsp *rsp);
-
-/*
- * Get module EEPROM params.
- */
-struct ethtool_module_eeprom_get_rsp *
-ethtool_module_eeprom_get(struct ynl_sock *ys,
-			  struct ethtool_module_eeprom_get_req *req);
-
-/* ETHTOOL_MSG_MODULE_EEPROM_GET - dump */
-struct ethtool_module_eeprom_get_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_module_eeprom_get_req_dump *
-ethtool_module_eeprom_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_module_eeprom_get_req_dump));
-}
-void
-ethtool_module_eeprom_get_req_dump_free(struct ethtool_module_eeprom_get_req_dump *req);
-
-static inline void
-ethtool_module_eeprom_get_req_dump_set_header_dev_index(struct ethtool_module_eeprom_get_req_dump *req,
-							__u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_module_eeprom_get_req_dump_set_header_dev_name(struct ethtool_module_eeprom_get_req_dump *req,
-						       const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_module_eeprom_get_req_dump_set_header_flags(struct ethtool_module_eeprom_get_req_dump *req,
-						    __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_module_eeprom_get_list {
-	struct ethtool_module_eeprom_get_list *next;
-	struct ethtool_module_eeprom_get_rsp obj __attribute__((aligned(8)));
-};
-
-void
-ethtool_module_eeprom_get_list_free(struct ethtool_module_eeprom_get_list *rsp);
-
-struct ethtool_module_eeprom_get_list *
-ethtool_module_eeprom_get_dump(struct ynl_sock *ys,
-			       struct ethtool_module_eeprom_get_req_dump *req);
-
-/* ============== ETHTOOL_MSG_PHC_VCLOCKS_GET ============== */
-/* ETHTOOL_MSG_PHC_VCLOCKS_GET - do */
-struct ethtool_phc_vclocks_get_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_phc_vclocks_get_req *
-ethtool_phc_vclocks_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_phc_vclocks_get_req));
-}
-void ethtool_phc_vclocks_get_req_free(struct ethtool_phc_vclocks_get_req *req);
-
-static inline void
-ethtool_phc_vclocks_get_req_set_header_dev_index(struct ethtool_phc_vclocks_get_req *req,
-						 __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_phc_vclocks_get_req_set_header_dev_name(struct ethtool_phc_vclocks_get_req *req,
-						const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_phc_vclocks_get_req_set_header_flags(struct ethtool_phc_vclocks_get_req *req,
-					     __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_phc_vclocks_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 num:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u32 num;
-};
-
-void ethtool_phc_vclocks_get_rsp_free(struct ethtool_phc_vclocks_get_rsp *rsp);
-
-/*
- * Get PHC VCLOCKs.
- */
-struct ethtool_phc_vclocks_get_rsp *
-ethtool_phc_vclocks_get(struct ynl_sock *ys,
-			struct ethtool_phc_vclocks_get_req *req);
-
-/* ETHTOOL_MSG_PHC_VCLOCKS_GET - dump */
-struct ethtool_phc_vclocks_get_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_phc_vclocks_get_req_dump *
-ethtool_phc_vclocks_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_phc_vclocks_get_req_dump));
-}
-void
-ethtool_phc_vclocks_get_req_dump_free(struct ethtool_phc_vclocks_get_req_dump *req);
-
-static inline void
-ethtool_phc_vclocks_get_req_dump_set_header_dev_index(struct ethtool_phc_vclocks_get_req_dump *req,
-						      __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_phc_vclocks_get_req_dump_set_header_dev_name(struct ethtool_phc_vclocks_get_req_dump *req,
-						     const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_phc_vclocks_get_req_dump_set_header_flags(struct ethtool_phc_vclocks_get_req_dump *req,
-						  __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_phc_vclocks_get_list {
-	struct ethtool_phc_vclocks_get_list *next;
-	struct ethtool_phc_vclocks_get_rsp obj __attribute__((aligned(8)));
-};
-
-void
-ethtool_phc_vclocks_get_list_free(struct ethtool_phc_vclocks_get_list *rsp);
-
-struct ethtool_phc_vclocks_get_list *
-ethtool_phc_vclocks_get_dump(struct ynl_sock *ys,
-			     struct ethtool_phc_vclocks_get_req_dump *req);
-
-/* ============== ETHTOOL_MSG_MODULE_GET ============== */
-/* ETHTOOL_MSG_MODULE_GET - do */
-struct ethtool_module_get_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_module_get_req *ethtool_module_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_module_get_req));
-}
-void ethtool_module_get_req_free(struct ethtool_module_get_req *req);
-
-static inline void
-ethtool_module_get_req_set_header_dev_index(struct ethtool_module_get_req *req,
-					    __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_module_get_req_set_header_dev_name(struct ethtool_module_get_req *req,
-					   const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_module_get_req_set_header_flags(struct ethtool_module_get_req *req,
-					__u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_module_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 power_mode_policy:1;
-		__u32 power_mode:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u8 power_mode_policy;
-	__u8 power_mode;
-};
-
-void ethtool_module_get_rsp_free(struct ethtool_module_get_rsp *rsp);
-
-/*
- * Get module params.
- */
-struct ethtool_module_get_rsp *
-ethtool_module_get(struct ynl_sock *ys, struct ethtool_module_get_req *req);
-
-/* ETHTOOL_MSG_MODULE_GET - dump */
-struct ethtool_module_get_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_module_get_req_dump *
-ethtool_module_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_module_get_req_dump));
-}
-void ethtool_module_get_req_dump_free(struct ethtool_module_get_req_dump *req);
-
-static inline void
-ethtool_module_get_req_dump_set_header_dev_index(struct ethtool_module_get_req_dump *req,
-						 __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_module_get_req_dump_set_header_dev_name(struct ethtool_module_get_req_dump *req,
-						const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_module_get_req_dump_set_header_flags(struct ethtool_module_get_req_dump *req,
-					     __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_module_get_list {
-	struct ethtool_module_get_list *next;
-	struct ethtool_module_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_module_get_list_free(struct ethtool_module_get_list *rsp);
-
-struct ethtool_module_get_list *
-ethtool_module_get_dump(struct ynl_sock *ys,
-			struct ethtool_module_get_req_dump *req);
-
-/* ETHTOOL_MSG_MODULE_GET - notify */
-struct ethtool_module_get_ntf {
-	__u16 family;
-	__u8 cmd;
-	struct ynl_ntf_base_type *next;
-	void (*free)(struct ethtool_module_get_ntf *ntf);
-	struct ethtool_module_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_module_get_ntf_free(struct ethtool_module_get_ntf *rsp);
-
-/* ============== ETHTOOL_MSG_MODULE_SET ============== */
-/* ETHTOOL_MSG_MODULE_SET - do */
-struct ethtool_module_set_req {
-	struct {
-		__u32 header:1;
-		__u32 power_mode_policy:1;
-		__u32 power_mode:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u8 power_mode_policy;
-	__u8 power_mode;
-};
-
-static inline struct ethtool_module_set_req *ethtool_module_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_module_set_req));
-}
-void ethtool_module_set_req_free(struct ethtool_module_set_req *req);
-
-static inline void
-ethtool_module_set_req_set_header_dev_index(struct ethtool_module_set_req *req,
-					    __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_module_set_req_set_header_dev_name(struct ethtool_module_set_req *req,
-					   const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_module_set_req_set_header_flags(struct ethtool_module_set_req *req,
-					__u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-static inline void
-ethtool_module_set_req_set_power_mode_policy(struct ethtool_module_set_req *req,
-					     __u8 power_mode_policy)
-{
-	req->_present.power_mode_policy = 1;
-	req->power_mode_policy = power_mode_policy;
-}
-static inline void
-ethtool_module_set_req_set_power_mode(struct ethtool_module_set_req *req,
-				      __u8 power_mode)
-{
-	req->_present.power_mode = 1;
-	req->power_mode = power_mode;
-}
-
-/*
- * Set module params.
- */
-int ethtool_module_set(struct ynl_sock *ys, struct ethtool_module_set_req *req);
-
-/* ============== ETHTOOL_MSG_PSE_GET ============== */
-/* ETHTOOL_MSG_PSE_GET - do */
-struct ethtool_pse_get_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_pse_get_req *ethtool_pse_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_pse_get_req));
-}
-void ethtool_pse_get_req_free(struct ethtool_pse_get_req *req);
-
-static inline void
-ethtool_pse_get_req_set_header_dev_index(struct ethtool_pse_get_req *req,
-					 __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_pse_get_req_set_header_dev_name(struct ethtool_pse_get_req *req,
-					const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_pse_get_req_set_header_flags(struct ethtool_pse_get_req *req,
-				     __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_pse_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 admin_state:1;
-		__u32 admin_control:1;
-		__u32 pw_d_status:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u32 admin_state;
-	__u32 admin_control;
-	__u32 pw_d_status;
-};
-
-void ethtool_pse_get_rsp_free(struct ethtool_pse_get_rsp *rsp);
-
-/*
- * Get Power Sourcing Equipment params.
- */
-struct ethtool_pse_get_rsp *
-ethtool_pse_get(struct ynl_sock *ys, struct ethtool_pse_get_req *req);
-
-/* ETHTOOL_MSG_PSE_GET - dump */
-struct ethtool_pse_get_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_pse_get_req_dump *
-ethtool_pse_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_pse_get_req_dump));
-}
-void ethtool_pse_get_req_dump_free(struct ethtool_pse_get_req_dump *req);
-
-static inline void
-ethtool_pse_get_req_dump_set_header_dev_index(struct ethtool_pse_get_req_dump *req,
-					      __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_pse_get_req_dump_set_header_dev_name(struct ethtool_pse_get_req_dump *req,
-					     const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_pse_get_req_dump_set_header_flags(struct ethtool_pse_get_req_dump *req,
-					  __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_pse_get_list {
-	struct ethtool_pse_get_list *next;
-	struct ethtool_pse_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_pse_get_list_free(struct ethtool_pse_get_list *rsp);
-
-struct ethtool_pse_get_list *
-ethtool_pse_get_dump(struct ynl_sock *ys, struct ethtool_pse_get_req_dump *req);
-
-/* ============== ETHTOOL_MSG_PSE_SET ============== */
-/* ETHTOOL_MSG_PSE_SET - do */
-struct ethtool_pse_set_req {
-	struct {
-		__u32 header:1;
-		__u32 admin_state:1;
-		__u32 admin_control:1;
-		__u32 pw_d_status:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u32 admin_state;
-	__u32 admin_control;
-	__u32 pw_d_status;
-};
-
-static inline struct ethtool_pse_set_req *ethtool_pse_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_pse_set_req));
-}
-void ethtool_pse_set_req_free(struct ethtool_pse_set_req *req);
-
-static inline void
-ethtool_pse_set_req_set_header_dev_index(struct ethtool_pse_set_req *req,
-					 __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_pse_set_req_set_header_dev_name(struct ethtool_pse_set_req *req,
-					const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_pse_set_req_set_header_flags(struct ethtool_pse_set_req *req,
-				     __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-static inline void
-ethtool_pse_set_req_set_admin_state(struct ethtool_pse_set_req *req,
-				    __u32 admin_state)
-{
-	req->_present.admin_state = 1;
-	req->admin_state = admin_state;
-}
-static inline void
-ethtool_pse_set_req_set_admin_control(struct ethtool_pse_set_req *req,
-				      __u32 admin_control)
-{
-	req->_present.admin_control = 1;
-	req->admin_control = admin_control;
-}
-static inline void
-ethtool_pse_set_req_set_pw_d_status(struct ethtool_pse_set_req *req,
-				    __u32 pw_d_status)
-{
-	req->_present.pw_d_status = 1;
-	req->pw_d_status = pw_d_status;
-}
-
-/*
- * Set Power Sourcing Equipment params.
- */
-int ethtool_pse_set(struct ynl_sock *ys, struct ethtool_pse_set_req *req);
-
-/* ============== ETHTOOL_MSG_RSS_GET ============== */
-/* ETHTOOL_MSG_RSS_GET - do */
-struct ethtool_rss_get_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_rss_get_req *ethtool_rss_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_rss_get_req));
-}
-void ethtool_rss_get_req_free(struct ethtool_rss_get_req *req);
-
-static inline void
-ethtool_rss_get_req_set_header_dev_index(struct ethtool_rss_get_req *req,
-					 __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_rss_get_req_set_header_dev_name(struct ethtool_rss_get_req *req,
-					const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_rss_get_req_set_header_flags(struct ethtool_rss_get_req *req,
-				     __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_rss_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 context:1;
-		__u32 hfunc:1;
-		__u32 indir_len;
-		__u32 hkey_len;
-	} _present;
-
-	struct ethtool_header header;
-	__u32 context;
-	__u32 hfunc;
-	void *indir;
-	void *hkey;
-};
-
-void ethtool_rss_get_rsp_free(struct ethtool_rss_get_rsp *rsp);
-
-/*
- * Get RSS params.
- */
-struct ethtool_rss_get_rsp *
-ethtool_rss_get(struct ynl_sock *ys, struct ethtool_rss_get_req *req);
-
-/* ETHTOOL_MSG_RSS_GET - dump */
-struct ethtool_rss_get_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_rss_get_req_dump *
-ethtool_rss_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_rss_get_req_dump));
-}
-void ethtool_rss_get_req_dump_free(struct ethtool_rss_get_req_dump *req);
-
-static inline void
-ethtool_rss_get_req_dump_set_header_dev_index(struct ethtool_rss_get_req_dump *req,
-					      __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_rss_get_req_dump_set_header_dev_name(struct ethtool_rss_get_req_dump *req,
-					     const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_rss_get_req_dump_set_header_flags(struct ethtool_rss_get_req_dump *req,
-					  __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_rss_get_list {
-	struct ethtool_rss_get_list *next;
-	struct ethtool_rss_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_rss_get_list_free(struct ethtool_rss_get_list *rsp);
-
-struct ethtool_rss_get_list *
-ethtool_rss_get_dump(struct ynl_sock *ys, struct ethtool_rss_get_req_dump *req);
-
-/* ============== ETHTOOL_MSG_PLCA_GET_CFG ============== */
-/* ETHTOOL_MSG_PLCA_GET_CFG - do */
-struct ethtool_plca_get_cfg_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_plca_get_cfg_req *
-ethtool_plca_get_cfg_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_plca_get_cfg_req));
-}
-void ethtool_plca_get_cfg_req_free(struct ethtool_plca_get_cfg_req *req);
-
-static inline void
-ethtool_plca_get_cfg_req_set_header_dev_index(struct ethtool_plca_get_cfg_req *req,
-					      __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_plca_get_cfg_req_set_header_dev_name(struct ethtool_plca_get_cfg_req *req,
-					     const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_plca_get_cfg_req_set_header_flags(struct ethtool_plca_get_cfg_req *req,
-					  __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_plca_get_cfg_rsp {
-	struct {
-		__u32 header:1;
-		__u32 version:1;
-		__u32 enabled:1;
-		__u32 status:1;
-		__u32 node_cnt:1;
-		__u32 node_id:1;
-		__u32 to_tmr:1;
-		__u32 burst_cnt:1;
-		__u32 burst_tmr:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u16 version;
-	__u8 enabled;
-	__u8 status;
-	__u32 node_cnt;
-	__u32 node_id;
-	__u32 to_tmr;
-	__u32 burst_cnt;
-	__u32 burst_tmr;
-};
-
-void ethtool_plca_get_cfg_rsp_free(struct ethtool_plca_get_cfg_rsp *rsp);
-
-/*
- * Get PLCA params.
- */
-struct ethtool_plca_get_cfg_rsp *
-ethtool_plca_get_cfg(struct ynl_sock *ys, struct ethtool_plca_get_cfg_req *req);
-
-/* ETHTOOL_MSG_PLCA_GET_CFG - dump */
-struct ethtool_plca_get_cfg_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_plca_get_cfg_req_dump *
-ethtool_plca_get_cfg_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_plca_get_cfg_req_dump));
-}
-void
-ethtool_plca_get_cfg_req_dump_free(struct ethtool_plca_get_cfg_req_dump *req);
-
-static inline void
-ethtool_plca_get_cfg_req_dump_set_header_dev_index(struct ethtool_plca_get_cfg_req_dump *req,
-						   __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_plca_get_cfg_req_dump_set_header_dev_name(struct ethtool_plca_get_cfg_req_dump *req,
-						  const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_plca_get_cfg_req_dump_set_header_flags(struct ethtool_plca_get_cfg_req_dump *req,
-					       __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_plca_get_cfg_list {
-	struct ethtool_plca_get_cfg_list *next;
-	struct ethtool_plca_get_cfg_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_plca_get_cfg_list_free(struct ethtool_plca_get_cfg_list *rsp);
-
-struct ethtool_plca_get_cfg_list *
-ethtool_plca_get_cfg_dump(struct ynl_sock *ys,
-			  struct ethtool_plca_get_cfg_req_dump *req);
-
-/* ETHTOOL_MSG_PLCA_GET_CFG - notify */
-struct ethtool_plca_get_cfg_ntf {
-	__u16 family;
-	__u8 cmd;
-	struct ynl_ntf_base_type *next;
-	void (*free)(struct ethtool_plca_get_cfg_ntf *ntf);
-	struct ethtool_plca_get_cfg_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_plca_get_cfg_ntf_free(struct ethtool_plca_get_cfg_ntf *rsp);
-
-/* ============== ETHTOOL_MSG_PLCA_SET_CFG ============== */
-/* ETHTOOL_MSG_PLCA_SET_CFG - do */
-struct ethtool_plca_set_cfg_req {
-	struct {
-		__u32 header:1;
-		__u32 version:1;
-		__u32 enabled:1;
-		__u32 status:1;
-		__u32 node_cnt:1;
-		__u32 node_id:1;
-		__u32 to_tmr:1;
-		__u32 burst_cnt:1;
-		__u32 burst_tmr:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u16 version;
-	__u8 enabled;
-	__u8 status;
-	__u32 node_cnt;
-	__u32 node_id;
-	__u32 to_tmr;
-	__u32 burst_cnt;
-	__u32 burst_tmr;
-};
-
-static inline struct ethtool_plca_set_cfg_req *
-ethtool_plca_set_cfg_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_plca_set_cfg_req));
-}
-void ethtool_plca_set_cfg_req_free(struct ethtool_plca_set_cfg_req *req);
-
-static inline void
-ethtool_plca_set_cfg_req_set_header_dev_index(struct ethtool_plca_set_cfg_req *req,
-					      __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_plca_set_cfg_req_set_header_dev_name(struct ethtool_plca_set_cfg_req *req,
-					     const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_plca_set_cfg_req_set_header_flags(struct ethtool_plca_set_cfg_req *req,
-					  __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-static inline void
-ethtool_plca_set_cfg_req_set_version(struct ethtool_plca_set_cfg_req *req,
-				     __u16 version)
-{
-	req->_present.version = 1;
-	req->version = version;
-}
-static inline void
-ethtool_plca_set_cfg_req_set_enabled(struct ethtool_plca_set_cfg_req *req,
-				     __u8 enabled)
-{
-	req->_present.enabled = 1;
-	req->enabled = enabled;
-}
-static inline void
-ethtool_plca_set_cfg_req_set_status(struct ethtool_plca_set_cfg_req *req,
-				    __u8 status)
-{
-	req->_present.status = 1;
-	req->status = status;
-}
-static inline void
-ethtool_plca_set_cfg_req_set_node_cnt(struct ethtool_plca_set_cfg_req *req,
-				      __u32 node_cnt)
-{
-	req->_present.node_cnt = 1;
-	req->node_cnt = node_cnt;
-}
-static inline void
-ethtool_plca_set_cfg_req_set_node_id(struct ethtool_plca_set_cfg_req *req,
-				     __u32 node_id)
-{
-	req->_present.node_id = 1;
-	req->node_id = node_id;
-}
-static inline void
-ethtool_plca_set_cfg_req_set_to_tmr(struct ethtool_plca_set_cfg_req *req,
-				    __u32 to_tmr)
-{
-	req->_present.to_tmr = 1;
-	req->to_tmr = to_tmr;
-}
-static inline void
-ethtool_plca_set_cfg_req_set_burst_cnt(struct ethtool_plca_set_cfg_req *req,
-				       __u32 burst_cnt)
-{
-	req->_present.burst_cnt = 1;
-	req->burst_cnt = burst_cnt;
-}
-static inline void
-ethtool_plca_set_cfg_req_set_burst_tmr(struct ethtool_plca_set_cfg_req *req,
-				       __u32 burst_tmr)
-{
-	req->_present.burst_tmr = 1;
-	req->burst_tmr = burst_tmr;
-}
-
-/*
- * Set PLCA params.
- */
-int ethtool_plca_set_cfg(struct ynl_sock *ys,
-			 struct ethtool_plca_set_cfg_req *req);
-
-/* ============== ETHTOOL_MSG_PLCA_GET_STATUS ============== */
-/* ETHTOOL_MSG_PLCA_GET_STATUS - do */
-struct ethtool_plca_get_status_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_plca_get_status_req *
-ethtool_plca_get_status_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_plca_get_status_req));
-}
-void ethtool_plca_get_status_req_free(struct ethtool_plca_get_status_req *req);
-
-static inline void
-ethtool_plca_get_status_req_set_header_dev_index(struct ethtool_plca_get_status_req *req,
-						 __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_plca_get_status_req_set_header_dev_name(struct ethtool_plca_get_status_req *req,
-						const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_plca_get_status_req_set_header_flags(struct ethtool_plca_get_status_req *req,
-					     __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_plca_get_status_rsp {
-	struct {
-		__u32 header:1;
-		__u32 version:1;
-		__u32 enabled:1;
-		__u32 status:1;
-		__u32 node_cnt:1;
-		__u32 node_id:1;
-		__u32 to_tmr:1;
-		__u32 burst_cnt:1;
-		__u32 burst_tmr:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u16 version;
-	__u8 enabled;
-	__u8 status;
-	__u32 node_cnt;
-	__u32 node_id;
-	__u32 to_tmr;
-	__u32 burst_cnt;
-	__u32 burst_tmr;
-};
-
-void ethtool_plca_get_status_rsp_free(struct ethtool_plca_get_status_rsp *rsp);
-
-/*
- * Get PLCA status params.
- */
-struct ethtool_plca_get_status_rsp *
-ethtool_plca_get_status(struct ynl_sock *ys,
-			struct ethtool_plca_get_status_req *req);
-
-/* ETHTOOL_MSG_PLCA_GET_STATUS - dump */
-struct ethtool_plca_get_status_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_plca_get_status_req_dump *
-ethtool_plca_get_status_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_plca_get_status_req_dump));
-}
-void
-ethtool_plca_get_status_req_dump_free(struct ethtool_plca_get_status_req_dump *req);
-
-static inline void
-ethtool_plca_get_status_req_dump_set_header_dev_index(struct ethtool_plca_get_status_req_dump *req,
-						      __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_plca_get_status_req_dump_set_header_dev_name(struct ethtool_plca_get_status_req_dump *req,
-						     const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_plca_get_status_req_dump_set_header_flags(struct ethtool_plca_get_status_req_dump *req,
-						  __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_plca_get_status_list {
-	struct ethtool_plca_get_status_list *next;
-	struct ethtool_plca_get_status_rsp obj __attribute__((aligned(8)));
-};
-
-void
-ethtool_plca_get_status_list_free(struct ethtool_plca_get_status_list *rsp);
-
-struct ethtool_plca_get_status_list *
-ethtool_plca_get_status_dump(struct ynl_sock *ys,
-			     struct ethtool_plca_get_status_req_dump *req);
-
-/* ============== ETHTOOL_MSG_MM_GET ============== */
-/* ETHTOOL_MSG_MM_GET - do */
-struct ethtool_mm_get_req {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_mm_get_req *ethtool_mm_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_mm_get_req));
-}
-void ethtool_mm_get_req_free(struct ethtool_mm_get_req *req);
-
-static inline void
-ethtool_mm_get_req_set_header_dev_index(struct ethtool_mm_get_req *req,
-					__u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_mm_get_req_set_header_dev_name(struct ethtool_mm_get_req *req,
-				       const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_mm_get_req_set_header_flags(struct ethtool_mm_get_req *req,
-				    __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_mm_get_rsp {
-	struct {
-		__u32 header:1;
-		__u32 pmac_enabled:1;
-		__u32 tx_enabled:1;
-		__u32 tx_active:1;
-		__u32 tx_min_frag_size:1;
-		__u32 rx_min_frag_size:1;
-		__u32 verify_enabled:1;
-		__u32 verify_time:1;
-		__u32 max_verify_time:1;
-		__u32 stats:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u8 pmac_enabled;
-	__u8 tx_enabled;
-	__u8 tx_active;
-	__u32 tx_min_frag_size;
-	__u32 rx_min_frag_size;
-	__u8 verify_enabled;
-	__u32 verify_time;
-	__u32 max_verify_time;
-	struct ethtool_mm_stat stats;
-};
-
-void ethtool_mm_get_rsp_free(struct ethtool_mm_get_rsp *rsp);
-
-/*
- * Get MAC Merge configuration and state
- */
-struct ethtool_mm_get_rsp *
-ethtool_mm_get(struct ynl_sock *ys, struct ethtool_mm_get_req *req);
-
-/* ETHTOOL_MSG_MM_GET - dump */
-struct ethtool_mm_get_req_dump {
-	struct {
-		__u32 header:1;
-	} _present;
-
-	struct ethtool_header header;
-};
-
-static inline struct ethtool_mm_get_req_dump *
-ethtool_mm_get_req_dump_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_mm_get_req_dump));
-}
-void ethtool_mm_get_req_dump_free(struct ethtool_mm_get_req_dump *req);
-
-static inline void
-ethtool_mm_get_req_dump_set_header_dev_index(struct ethtool_mm_get_req_dump *req,
-					     __u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_mm_get_req_dump_set_header_dev_name(struct ethtool_mm_get_req_dump *req,
-					    const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_mm_get_req_dump_set_header_flags(struct ethtool_mm_get_req_dump *req,
-					 __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-
-struct ethtool_mm_get_list {
-	struct ethtool_mm_get_list *next;
-	struct ethtool_mm_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_mm_get_list_free(struct ethtool_mm_get_list *rsp);
-
-struct ethtool_mm_get_list *
-ethtool_mm_get_dump(struct ynl_sock *ys, struct ethtool_mm_get_req_dump *req);
-
-/* ETHTOOL_MSG_MM_GET - notify */
-struct ethtool_mm_get_ntf {
-	__u16 family;
-	__u8 cmd;
-	struct ynl_ntf_base_type *next;
-	void (*free)(struct ethtool_mm_get_ntf *ntf);
-	struct ethtool_mm_get_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_mm_get_ntf_free(struct ethtool_mm_get_ntf *rsp);
-
-/* ============== ETHTOOL_MSG_MM_SET ============== */
-/* ETHTOOL_MSG_MM_SET - do */
-struct ethtool_mm_set_req {
-	struct {
-		__u32 header:1;
-		__u32 verify_enabled:1;
-		__u32 verify_time:1;
-		__u32 tx_enabled:1;
-		__u32 pmac_enabled:1;
-		__u32 tx_min_frag_size:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u8 verify_enabled;
-	__u32 verify_time;
-	__u8 tx_enabled;
-	__u8 pmac_enabled;
-	__u32 tx_min_frag_size;
-};
-
-static inline struct ethtool_mm_set_req *ethtool_mm_set_req_alloc(void)
-{
-	return calloc(1, sizeof(struct ethtool_mm_set_req));
-}
-void ethtool_mm_set_req_free(struct ethtool_mm_set_req *req);
-
-static inline void
-ethtool_mm_set_req_set_header_dev_index(struct ethtool_mm_set_req *req,
-					__u32 dev_index)
-{
-	req->_present.header = 1;
-	req->header._present.dev_index = 1;
-	req->header.dev_index = dev_index;
-}
-static inline void
-ethtool_mm_set_req_set_header_dev_name(struct ethtool_mm_set_req *req,
-				       const char *dev_name)
-{
-	free(req->header.dev_name);
-	req->header._present.dev_name_len = strlen(dev_name);
-	req->header.dev_name = malloc(req->header._present.dev_name_len + 1);
-	memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len);
-	req->header.dev_name[req->header._present.dev_name_len] = 0;
-}
-static inline void
-ethtool_mm_set_req_set_header_flags(struct ethtool_mm_set_req *req,
-				    __u32 flags)
-{
-	req->_present.header = 1;
-	req->header._present.flags = 1;
-	req->header.flags = flags;
-}
-static inline void
-ethtool_mm_set_req_set_verify_enabled(struct ethtool_mm_set_req *req,
-				      __u8 verify_enabled)
-{
-	req->_present.verify_enabled = 1;
-	req->verify_enabled = verify_enabled;
-}
-static inline void
-ethtool_mm_set_req_set_verify_time(struct ethtool_mm_set_req *req,
-				   __u32 verify_time)
-{
-	req->_present.verify_time = 1;
-	req->verify_time = verify_time;
-}
-static inline void
-ethtool_mm_set_req_set_tx_enabled(struct ethtool_mm_set_req *req,
-				  __u8 tx_enabled)
-{
-	req->_present.tx_enabled = 1;
-	req->tx_enabled = tx_enabled;
-}
-static inline void
-ethtool_mm_set_req_set_pmac_enabled(struct ethtool_mm_set_req *req,
-				    __u8 pmac_enabled)
-{
-	req->_present.pmac_enabled = 1;
-	req->pmac_enabled = pmac_enabled;
-}
-static inline void
-ethtool_mm_set_req_set_tx_min_frag_size(struct ethtool_mm_set_req *req,
-					__u32 tx_min_frag_size)
-{
-	req->_present.tx_min_frag_size = 1;
-	req->tx_min_frag_size = tx_min_frag_size;
-}
-
-/*
- * Set MAC Merge configuration
- */
-int ethtool_mm_set(struct ynl_sock *ys, struct ethtool_mm_set_req *req);
-
-/* ETHTOOL_MSG_CABLE_TEST_NTF - event */
-struct ethtool_cable_test_ntf_rsp {
-	struct {
-		__u32 header:1;
-		__u32 status:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u8 status;
-};
-
-struct ethtool_cable_test_ntf {
-	__u16 family;
-	__u8 cmd;
-	struct ynl_ntf_base_type *next;
-	void (*free)(struct ethtool_cable_test_ntf *ntf);
-	struct ethtool_cable_test_ntf_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_cable_test_ntf_free(struct ethtool_cable_test_ntf *rsp);
-
-/* ETHTOOL_MSG_CABLE_TEST_TDR_NTF - event */
-struct ethtool_cable_test_tdr_ntf_rsp {
-	struct {
-		__u32 header:1;
-		__u32 status:1;
-		__u32 nest:1;
-	} _present;
-
-	struct ethtool_header header;
-	__u8 status;
-	struct ethtool_cable_nest nest;
-};
-
-struct ethtool_cable_test_tdr_ntf {
-	__u16 family;
-	__u8 cmd;
-	struct ynl_ntf_base_type *next;
-	void (*free)(struct ethtool_cable_test_tdr_ntf *ntf);
-	struct ethtool_cable_test_tdr_ntf_rsp obj __attribute__((aligned(8)));
-};
-
-void ethtool_cable_test_tdr_ntf_free(struct ethtool_cable_test_tdr_ntf *rsp);
-
-#endif /* _LINUX_ETHTOOL_GEN_H */
diff --git a/tools/net/ynl/generated/fou-user.c b/tools/net/ynl/generated/fou-user.c
deleted file mode 100644
index 4271b5d43c58..000000000000
--- a/tools/net/ynl/generated/fou-user.c
+++ /dev/null
@@ -1,328 +0,0 @@
-// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
-/* Do not edit directly, auto-generated from: */
-/*	Documentation/netlink/specs/fou.yaml */
-/* YNL-GEN user source */
-
-#include <stdlib.h>
-#include <string.h>
-#include "fou-user.h"
-#include "ynl.h"
-#include <linux/fou.h>
-
-#include <libmnl/libmnl.h>
-#include <linux/genetlink.h>
-
-/* Enums */
-static const char * const fou_op_strmap[] = {
-	[FOU_CMD_ADD] = "add",
-	[FOU_CMD_DEL] = "del",
-	[FOU_CMD_GET] = "get",
-};
-
-const char *fou_op_str(int op)
-{
-	if (op < 0 || op >= (int)MNL_ARRAY_SIZE(fou_op_strmap))
-		return NULL;
-	return fou_op_strmap[op];
-}
-
-static const char * const fou_encap_type_strmap[] = {
-	[0] = "unspec",
-	[1] = "direct",
-	[2] = "gue",
-};
-
-const char *fou_encap_type_str(int value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(fou_encap_type_strmap))
-		return NULL;
-	return fou_encap_type_strmap[value];
-}
-
-/* Policies */
-struct ynl_policy_attr fou_policy[FOU_ATTR_MAX + 1] = {
-	[FOU_ATTR_UNSPEC] = { .name = "unspec", .type = YNL_PT_REJECT, },
-	[FOU_ATTR_PORT] = { .name = "port", .type = YNL_PT_U16, },
-	[FOU_ATTR_AF] = { .name = "af", .type = YNL_PT_U8, },
-	[FOU_ATTR_IPPROTO] = { .name = "ipproto", .type = YNL_PT_U8, },
-	[FOU_ATTR_TYPE] = { .name = "type", .type = YNL_PT_U8, },
-	[FOU_ATTR_REMCSUM_NOPARTIAL] = { .name = "remcsum_nopartial", .type = YNL_PT_FLAG, },
-	[FOU_ATTR_LOCAL_V4] = { .name = "local_v4", .type = YNL_PT_U32, },
-	[FOU_ATTR_LOCAL_V6] = { .name = "local_v6", .type = YNL_PT_BINARY,},
-	[FOU_ATTR_PEER_V4] = { .name = "peer_v4", .type = YNL_PT_U32, },
-	[FOU_ATTR_PEER_V6] = { .name = "peer_v6", .type = YNL_PT_BINARY,},
-	[FOU_ATTR_PEER_PORT] = { .name = "peer_port", .type = YNL_PT_U16, },
-	[FOU_ATTR_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest fou_nest = {
-	.max_attr = FOU_ATTR_MAX,
-	.table = fou_policy,
-};
-
-/* Common nested types */
-/* ============== FOU_CMD_ADD ============== */
-/* FOU_CMD_ADD - do */
-void fou_add_req_free(struct fou_add_req *req)
-{
-	free(req->local_v6);
-	free(req->peer_v6);
-	free(req);
-}
-
-int fou_add(struct ynl_sock *ys, struct fou_add_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, FOU_CMD_ADD, 1);
-	ys->req_policy = &fou_nest;
-
-	if (req->_present.port)
-		mnl_attr_put_u16(nlh, FOU_ATTR_PORT, req->port);
-	if (req->_present.ipproto)
-		mnl_attr_put_u8(nlh, FOU_ATTR_IPPROTO, req->ipproto);
-	if (req->_present.type)
-		mnl_attr_put_u8(nlh, FOU_ATTR_TYPE, req->type);
-	if (req->_present.remcsum_nopartial)
-		mnl_attr_put(nlh, FOU_ATTR_REMCSUM_NOPARTIAL, 0, NULL);
-	if (req->_present.local_v4)
-		mnl_attr_put_u32(nlh, FOU_ATTR_LOCAL_V4, req->local_v4);
-	if (req->_present.peer_v4)
-		mnl_attr_put_u32(nlh, FOU_ATTR_PEER_V4, req->peer_v4);
-	if (req->_present.local_v6_len)
-		mnl_attr_put(nlh, FOU_ATTR_LOCAL_V6, req->_present.local_v6_len, req->local_v6);
-	if (req->_present.peer_v6_len)
-		mnl_attr_put(nlh, FOU_ATTR_PEER_V6, req->_present.peer_v6_len, req->peer_v6);
-	if (req->_present.peer_port)
-		mnl_attr_put_u16(nlh, FOU_ATTR_PEER_PORT, req->peer_port);
-	if (req->_present.ifindex)
-		mnl_attr_put_u32(nlh, FOU_ATTR_IFINDEX, req->ifindex);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== FOU_CMD_DEL ============== */
-/* FOU_CMD_DEL - do */
-void fou_del_req_free(struct fou_del_req *req)
-{
-	free(req->local_v6);
-	free(req->peer_v6);
-	free(req);
-}
-
-int fou_del(struct ynl_sock *ys, struct fou_del_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, FOU_CMD_DEL, 1);
-	ys->req_policy = &fou_nest;
-
-	if (req->_present.af)
-		mnl_attr_put_u8(nlh, FOU_ATTR_AF, req->af);
-	if (req->_present.ifindex)
-		mnl_attr_put_u32(nlh, FOU_ATTR_IFINDEX, req->ifindex);
-	if (req->_present.port)
-		mnl_attr_put_u16(nlh, FOU_ATTR_PORT, req->port);
-	if (req->_present.peer_port)
-		mnl_attr_put_u16(nlh, FOU_ATTR_PEER_PORT, req->peer_port);
-	if (req->_present.local_v4)
-		mnl_attr_put_u32(nlh, FOU_ATTR_LOCAL_V4, req->local_v4);
-	if (req->_present.peer_v4)
-		mnl_attr_put_u32(nlh, FOU_ATTR_PEER_V4, req->peer_v4);
-	if (req->_present.local_v6_len)
-		mnl_attr_put(nlh, FOU_ATTR_LOCAL_V6, req->_present.local_v6_len, req->local_v6);
-	if (req->_present.peer_v6_len)
-		mnl_attr_put(nlh, FOU_ATTR_PEER_V6, req->_present.peer_v6_len, req->peer_v6);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-/* ============== FOU_CMD_GET ============== */
-/* FOU_CMD_GET - do */
-void fou_get_req_free(struct fou_get_req *req)
-{
-	free(req->local_v6);
-	free(req->peer_v6);
-	free(req);
-}
-
-void fou_get_rsp_free(struct fou_get_rsp *rsp)
-{
-	free(rsp->local_v6);
-	free(rsp->peer_v6);
-	free(rsp);
-}
-
-int fou_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ynl_parse_arg *yarg = data;
-	const struct nlattr *attr;
-	struct fou_get_rsp *dst;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == FOU_ATTR_PORT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.port = 1;
-			dst->port = mnl_attr_get_u16(attr);
-		} else if (type == FOU_ATTR_IPPROTO) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.ipproto = 1;
-			dst->ipproto = mnl_attr_get_u8(attr);
-		} else if (type == FOU_ATTR_TYPE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.type = 1;
-			dst->type = mnl_attr_get_u8(attr);
-		} else if (type == FOU_ATTR_REMCSUM_NOPARTIAL) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.remcsum_nopartial = 1;
-		} else if (type == FOU_ATTR_LOCAL_V4) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.local_v4 = 1;
-			dst->local_v4 = mnl_attr_get_u32(attr);
-		} else if (type == FOU_ATTR_PEER_V4) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.peer_v4 = 1;
-			dst->peer_v4 = mnl_attr_get_u32(attr);
-		} else if (type == FOU_ATTR_LOCAL_V6) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = mnl_attr_get_payload_len(attr);
-			dst->_present.local_v6_len = len;
-			dst->local_v6 = malloc(len);
-			memcpy(dst->local_v6, mnl_attr_get_payload(attr), len);
-		} else if (type == FOU_ATTR_PEER_V6) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = mnl_attr_get_payload_len(attr);
-			dst->_present.peer_v6_len = len;
-			dst->peer_v6 = malloc(len);
-			memcpy(dst->peer_v6, mnl_attr_get_payload(attr), len);
-		} else if (type == FOU_ATTR_PEER_PORT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.peer_port = 1;
-			dst->peer_port = mnl_attr_get_u16(attr);
-		} else if (type == FOU_ATTR_IFINDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.ifindex = 1;
-			dst->ifindex = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct fou_get_rsp *fou_get(struct ynl_sock *ys, struct fou_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct fou_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, FOU_CMD_GET, 1);
-	ys->req_policy = &fou_nest;
-	yrs.yarg.rsp_policy = &fou_nest;
-
-	if (req->_present.af)
-		mnl_attr_put_u8(nlh, FOU_ATTR_AF, req->af);
-	if (req->_present.ifindex)
-		mnl_attr_put_u32(nlh, FOU_ATTR_IFINDEX, req->ifindex);
-	if (req->_present.port)
-		mnl_attr_put_u16(nlh, FOU_ATTR_PORT, req->port);
-	if (req->_present.peer_port)
-		mnl_attr_put_u16(nlh, FOU_ATTR_PEER_PORT, req->peer_port);
-	if (req->_present.local_v4)
-		mnl_attr_put_u32(nlh, FOU_ATTR_LOCAL_V4, req->local_v4);
-	if (req->_present.peer_v4)
-		mnl_attr_put_u32(nlh, FOU_ATTR_PEER_V4, req->peer_v4);
-	if (req->_present.local_v6_len)
-		mnl_attr_put(nlh, FOU_ATTR_LOCAL_V6, req->_present.local_v6_len, req->local_v6);
-	if (req->_present.peer_v6_len)
-		mnl_attr_put(nlh, FOU_ATTR_PEER_V6, req->_present.peer_v6_len, req->peer_v6);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = fou_get_rsp_parse;
-	yrs.rsp_cmd = FOU_CMD_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	fou_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* FOU_CMD_GET - dump */
-void fou_get_list_free(struct fou_get_list *rsp)
-{
-	struct fou_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.local_v6);
-		free(rsp->obj.peer_v6);
-		free(rsp);
-	}
-}
-
-struct fou_get_list *fou_get_dump(struct ynl_sock *ys)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct fou_get_list);
-	yds.cb = fou_get_rsp_parse;
-	yds.rsp_cmd = FOU_CMD_GET;
-	yds.rsp_policy = &fou_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, FOU_CMD_GET, 1);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	fou_get_list_free(yds.first);
-	return NULL;
-}
-
-const struct ynl_family ynl_fou_family =  {
-	.name		= "fou",
-};
diff --git a/tools/net/ynl/generated/fou-user.h b/tools/net/ynl/generated/fou-user.h
deleted file mode 100644
index fd566716ddd6..000000000000
--- a/tools/net/ynl/generated/fou-user.h
+++ /dev/null
@@ -1,343 +0,0 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
-/* Do not edit directly, auto-generated from: */
-/*	Documentation/netlink/specs/fou.yaml */
-/* YNL-GEN user header */
-
-#ifndef _LINUX_FOU_GEN_H
-#define _LINUX_FOU_GEN_H
-
-#include <stdlib.h>
-#include <string.h>
-#include <linux/types.h>
-#include <linux/fou.h>
-
-struct ynl_sock;
-
-extern const struct ynl_family ynl_fou_family;
-
-/* Enums */
-const char *fou_op_str(int op);
-const char *fou_encap_type_str(int value);
-
-/* Common nested types */
-/* ============== FOU_CMD_ADD ============== */
-/* FOU_CMD_ADD - do */
-struct fou_add_req {
-	struct {
-		__u32 port:1;
-		__u32 ipproto:1;
-		__u32 type:1;
-		__u32 remcsum_nopartial:1;
-		__u32 local_v4:1;
-		__u32 peer_v4:1;
-		__u32 local_v6_len;
-		__u32 peer_v6_len;
-		__u32 peer_port:1;
-		__u32 ifindex:1;
-	} _present;
-
-	__u16 port /* big-endian */;
-	__u8 ipproto;
-	__u8 type;
-	__u32 local_v4;
-	__u32 peer_v4;
-	void *local_v6;
-	void *peer_v6;
-	__u16 peer_port /* big-endian */;
-	__s32 ifindex;
-};
-
-static inline struct fou_add_req *fou_add_req_alloc(void)
-{
-	return calloc(1, sizeof(struct fou_add_req));
-}
-void fou_add_req_free(struct fou_add_req *req);
-
-static inline void
-fou_add_req_set_port(struct fou_add_req *req, __u16 port /* big-endian */)
-{
-	req->_present.port = 1;
-	req->port = port;
-}
-static inline void
-fou_add_req_set_ipproto(struct fou_add_req *req, __u8 ipproto)
-{
-	req->_present.ipproto = 1;
-	req->ipproto = ipproto;
-}
-static inline void fou_add_req_set_type(struct fou_add_req *req, __u8 type)
-{
-	req->_present.type = 1;
-	req->type = type;
-}
-static inline void fou_add_req_set_remcsum_nopartial(struct fou_add_req *req)
-{
-	req->_present.remcsum_nopartial = 1;
-}
-static inline void
-fou_add_req_set_local_v4(struct fou_add_req *req, __u32 local_v4)
-{
-	req->_present.local_v4 = 1;
-	req->local_v4 = local_v4;
-}
-static inline void
-fou_add_req_set_peer_v4(struct fou_add_req *req, __u32 peer_v4)
-{
-	req->_present.peer_v4 = 1;
-	req->peer_v4 = peer_v4;
-}
-static inline void
-fou_add_req_set_local_v6(struct fou_add_req *req, const void *local_v6,
-			 size_t len)
-{
-	free(req->local_v6);
-	req->_present.local_v6_len = len;
-	req->local_v6 = malloc(req->_present.local_v6_len);
-	memcpy(req->local_v6, local_v6, req->_present.local_v6_len);
-}
-static inline void
-fou_add_req_set_peer_v6(struct fou_add_req *req, const void *peer_v6,
-			size_t len)
-{
-	free(req->peer_v6);
-	req->_present.peer_v6_len = len;
-	req->peer_v6 = malloc(req->_present.peer_v6_len);
-	memcpy(req->peer_v6, peer_v6, req->_present.peer_v6_len);
-}
-static inline void
-fou_add_req_set_peer_port(struct fou_add_req *req,
-			  __u16 peer_port /* big-endian */)
-{
-	req->_present.peer_port = 1;
-	req->peer_port = peer_port;
-}
-static inline void
-fou_add_req_set_ifindex(struct fou_add_req *req, __s32 ifindex)
-{
-	req->_present.ifindex = 1;
-	req->ifindex = ifindex;
-}
-
-/*
- * Add port.
- */
-int fou_add(struct ynl_sock *ys, struct fou_add_req *req);
-
-/* ============== FOU_CMD_DEL ============== */
-/* FOU_CMD_DEL - do */
-struct fou_del_req {
-	struct {
-		__u32 af:1;
-		__u32 ifindex:1;
-		__u32 port:1;
-		__u32 peer_port:1;
-		__u32 local_v4:1;
-		__u32 peer_v4:1;
-		__u32 local_v6_len;
-		__u32 peer_v6_len;
-	} _present;
-
-	__u8 af;
-	__s32 ifindex;
-	__u16 port /* big-endian */;
-	__u16 peer_port /* big-endian */;
-	__u32 local_v4;
-	__u32 peer_v4;
-	void *local_v6;
-	void *peer_v6;
-};
-
-static inline struct fou_del_req *fou_del_req_alloc(void)
-{
-	return calloc(1, sizeof(struct fou_del_req));
-}
-void fou_del_req_free(struct fou_del_req *req);
-
-static inline void fou_del_req_set_af(struct fou_del_req *req, __u8 af)
-{
-	req->_present.af = 1;
-	req->af = af;
-}
-static inline void
-fou_del_req_set_ifindex(struct fou_del_req *req, __s32 ifindex)
-{
-	req->_present.ifindex = 1;
-	req->ifindex = ifindex;
-}
-static inline void
-fou_del_req_set_port(struct fou_del_req *req, __u16 port /* big-endian */)
-{
-	req->_present.port = 1;
-	req->port = port;
-}
-static inline void
-fou_del_req_set_peer_port(struct fou_del_req *req,
-			  __u16 peer_port /* big-endian */)
-{
-	req->_present.peer_port = 1;
-	req->peer_port = peer_port;
-}
-static inline void
-fou_del_req_set_local_v4(struct fou_del_req *req, __u32 local_v4)
-{
-	req->_present.local_v4 = 1;
-	req->local_v4 = local_v4;
-}
-static inline void
-fou_del_req_set_peer_v4(struct fou_del_req *req, __u32 peer_v4)
-{
-	req->_present.peer_v4 = 1;
-	req->peer_v4 = peer_v4;
-}
-static inline void
-fou_del_req_set_local_v6(struct fou_del_req *req, const void *local_v6,
-			 size_t len)
-{
-	free(req->local_v6);
-	req->_present.local_v6_len = len;
-	req->local_v6 = malloc(req->_present.local_v6_len);
-	memcpy(req->local_v6, local_v6, req->_present.local_v6_len);
-}
-static inline void
-fou_del_req_set_peer_v6(struct fou_del_req *req, const void *peer_v6,
-			size_t len)
-{
-	free(req->peer_v6);
-	req->_present.peer_v6_len = len;
-	req->peer_v6 = malloc(req->_present.peer_v6_len);
-	memcpy(req->peer_v6, peer_v6, req->_present.peer_v6_len);
-}
-
-/*
- * Delete port.
- */
-int fou_del(struct ynl_sock *ys, struct fou_del_req *req);
-
-/* ============== FOU_CMD_GET ============== */
-/* FOU_CMD_GET - do */
-struct fou_get_req {
-	struct {
-		__u32 af:1;
-		__u32 ifindex:1;
-		__u32 port:1;
-		__u32 peer_port:1;
-		__u32 local_v4:1;
-		__u32 peer_v4:1;
-		__u32 local_v6_len;
-		__u32 peer_v6_len;
-	} _present;
-
-	__u8 af;
-	__s32 ifindex;
-	__u16 port /* big-endian */;
-	__u16 peer_port /* big-endian */;
-	__u32 local_v4;
-	__u32 peer_v4;
-	void *local_v6;
-	void *peer_v6;
-};
-
-static inline struct fou_get_req *fou_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct fou_get_req));
-}
-void fou_get_req_free(struct fou_get_req *req);
-
-static inline void fou_get_req_set_af(struct fou_get_req *req, __u8 af)
-{
-	req->_present.af = 1;
-	req->af = af;
-}
-static inline void
-fou_get_req_set_ifindex(struct fou_get_req *req, __s32 ifindex)
-{
-	req->_present.ifindex = 1;
-	req->ifindex = ifindex;
-}
-static inline void
-fou_get_req_set_port(struct fou_get_req *req, __u16 port /* big-endian */)
-{
-	req->_present.port = 1;
-	req->port = port;
-}
-static inline void
-fou_get_req_set_peer_port(struct fou_get_req *req,
-			  __u16 peer_port /* big-endian */)
-{
-	req->_present.peer_port = 1;
-	req->peer_port = peer_port;
-}
-static inline void
-fou_get_req_set_local_v4(struct fou_get_req *req, __u32 local_v4)
-{
-	req->_present.local_v4 = 1;
-	req->local_v4 = local_v4;
-}
-static inline void
-fou_get_req_set_peer_v4(struct fou_get_req *req, __u32 peer_v4)
-{
-	req->_present.peer_v4 = 1;
-	req->peer_v4 = peer_v4;
-}
-static inline void
-fou_get_req_set_local_v6(struct fou_get_req *req, const void *local_v6,
-			 size_t len)
-{
-	free(req->local_v6);
-	req->_present.local_v6_len = len;
-	req->local_v6 = malloc(req->_present.local_v6_len);
-	memcpy(req->local_v6, local_v6, req->_present.local_v6_len);
-}
-static inline void
-fou_get_req_set_peer_v6(struct fou_get_req *req, const void *peer_v6,
-			size_t len)
-{
-	free(req->peer_v6);
-	req->_present.peer_v6_len = len;
-	req->peer_v6 = malloc(req->_present.peer_v6_len);
-	memcpy(req->peer_v6, peer_v6, req->_present.peer_v6_len);
-}
-
-struct fou_get_rsp {
-	struct {
-		__u32 port:1;
-		__u32 ipproto:1;
-		__u32 type:1;
-		__u32 remcsum_nopartial:1;
-		__u32 local_v4:1;
-		__u32 peer_v4:1;
-		__u32 local_v6_len;
-		__u32 peer_v6_len;
-		__u32 peer_port:1;
-		__u32 ifindex:1;
-	} _present;
-
-	__u16 port /* big-endian */;
-	__u8 ipproto;
-	__u8 type;
-	__u32 local_v4;
-	__u32 peer_v4;
-	void *local_v6;
-	void *peer_v6;
-	__u16 peer_port /* big-endian */;
-	__s32 ifindex;
-};
-
-void fou_get_rsp_free(struct fou_get_rsp *rsp);
-
-/*
- * Get tunnel info.
- */
-struct fou_get_rsp *fou_get(struct ynl_sock *ys, struct fou_get_req *req);
-
-/* FOU_CMD_GET - dump */
-struct fou_get_list {
-	struct fou_get_list *next;
-	struct fou_get_rsp obj __attribute__((aligned(8)));
-};
-
-void fou_get_list_free(struct fou_get_list *rsp);
-
-struct fou_get_list *fou_get_dump(struct ynl_sock *ys);
-
-#endif /* _LINUX_FOU_GEN_H */
diff --git a/tools/net/ynl/generated/handshake-user.c b/tools/net/ynl/generated/handshake-user.c
deleted file mode 100644
index 7c67765daf90..000000000000
--- a/tools/net/ynl/generated/handshake-user.c
+++ /dev/null
@@ -1,331 +0,0 @@
-// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
-/* Do not edit directly, auto-generated from: */
-/*	Documentation/netlink/specs/handshake.yaml */
-/* YNL-GEN user source */
-
-#include <stdlib.h>
-#include <string.h>
-#include "handshake-user.h"
-#include "ynl.h"
-#include <linux/handshake.h>
-
-#include <libmnl/libmnl.h>
-#include <linux/genetlink.h>
-
-/* Enums */
-static const char * const handshake_op_strmap[] = {
-	[HANDSHAKE_CMD_READY] = "ready",
-	[HANDSHAKE_CMD_ACCEPT] = "accept",
-	[HANDSHAKE_CMD_DONE] = "done",
-};
-
-const char *handshake_op_str(int op)
-{
-	if (op < 0 || op >= (int)MNL_ARRAY_SIZE(handshake_op_strmap))
-		return NULL;
-	return handshake_op_strmap[op];
-}
-
-static const char * const handshake_handler_class_strmap[] = {
-	[0] = "none",
-	[1] = "tlshd",
-	[2] = "max",
-};
-
-const char *handshake_handler_class_str(enum handshake_handler_class value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(handshake_handler_class_strmap))
-		return NULL;
-	return handshake_handler_class_strmap[value];
-}
-
-static const char * const handshake_msg_type_strmap[] = {
-	[0] = "unspec",
-	[1] = "clienthello",
-	[2] = "serverhello",
-};
-
-const char *handshake_msg_type_str(enum handshake_msg_type value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(handshake_msg_type_strmap))
-		return NULL;
-	return handshake_msg_type_strmap[value];
-}
-
-static const char * const handshake_auth_strmap[] = {
-	[0] = "unspec",
-	[1] = "unauth",
-	[2] = "psk",
-	[3] = "x509",
-};
-
-const char *handshake_auth_str(enum handshake_auth value)
-{
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(handshake_auth_strmap))
-		return NULL;
-	return handshake_auth_strmap[value];
-}
-
-/* Policies */
-struct ynl_policy_attr handshake_x509_policy[HANDSHAKE_A_X509_MAX + 1] = {
-	[HANDSHAKE_A_X509_CERT] = { .name = "cert", .type = YNL_PT_U32, },
-	[HANDSHAKE_A_X509_PRIVKEY] = { .name = "privkey", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest handshake_x509_nest = {
-	.max_attr = HANDSHAKE_A_X509_MAX,
-	.table = handshake_x509_policy,
-};
-
-struct ynl_policy_attr handshake_accept_policy[HANDSHAKE_A_ACCEPT_MAX + 1] = {
-	[HANDSHAKE_A_ACCEPT_SOCKFD] = { .name = "sockfd", .type = YNL_PT_U32, },
-	[HANDSHAKE_A_ACCEPT_HANDLER_CLASS] = { .name = "handler-class", .type = YNL_PT_U32, },
-	[HANDSHAKE_A_ACCEPT_MESSAGE_TYPE] = { .name = "message-type", .type = YNL_PT_U32, },
-	[HANDSHAKE_A_ACCEPT_TIMEOUT] = { .name = "timeout", .type = YNL_PT_U32, },
-	[HANDSHAKE_A_ACCEPT_AUTH_MODE] = { .name = "auth-mode", .type = YNL_PT_U32, },
-	[HANDSHAKE_A_ACCEPT_PEER_IDENTITY] = { .name = "peer-identity", .type = YNL_PT_U32, },
-	[HANDSHAKE_A_ACCEPT_CERTIFICATE] = { .name = "certificate", .type = YNL_PT_NEST, .nest = &handshake_x509_nest, },
-	[HANDSHAKE_A_ACCEPT_PEERNAME] = { .name = "peername", .type = YNL_PT_NUL_STR, },
-};
-
-struct ynl_policy_nest handshake_accept_nest = {
-	.max_attr = HANDSHAKE_A_ACCEPT_MAX,
-	.table = handshake_accept_policy,
-};
-
-struct ynl_policy_attr handshake_done_policy[HANDSHAKE_A_DONE_MAX + 1] = {
-	[HANDSHAKE_A_DONE_STATUS] = { .name = "status", .type = YNL_PT_U32, },
-	[HANDSHAKE_A_DONE_SOCKFD] = { .name = "sockfd", .type = YNL_PT_U32, },
-	[HANDSHAKE_A_DONE_REMOTE_AUTH] = { .name = "remote-auth", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest handshake_done_nest = {
-	.max_attr = HANDSHAKE_A_DONE_MAX,
-	.table = handshake_done_policy,
-};
-
-/* Common nested types */
-void handshake_x509_free(struct handshake_x509 *obj)
-{
-}
-
-int handshake_x509_parse(struct ynl_parse_arg *yarg,
-			 const struct nlattr *nested)
-{
-	struct handshake_x509 *dst = yarg->data;
-	const struct nlattr *attr;
-
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == HANDSHAKE_A_X509_CERT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.cert = 1;
-			dst->cert = mnl_attr_get_u32(attr);
-		} else if (type == HANDSHAKE_A_X509_PRIVKEY) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.privkey = 1;
-			dst->privkey = mnl_attr_get_u32(attr);
-		}
-	}
-
-	return 0;
-}
-
-/* ============== HANDSHAKE_CMD_ACCEPT ============== */
-/* HANDSHAKE_CMD_ACCEPT - do */
-void handshake_accept_req_free(struct handshake_accept_req *req)
-{
-	free(req);
-}
-
-void handshake_accept_rsp_free(struct handshake_accept_rsp *rsp)
-{
-	unsigned int i;
-
-	free(rsp->peer_identity);
-	for (i = 0; i < rsp->n_certificate; i++)
-		handshake_x509_free(&rsp->certificate[i]);
-	free(rsp->certificate);
-	free(rsp->peername);
-	free(rsp);
-}
-
-int handshake_accept_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ynl_parse_arg *yarg = data;
-	struct handshake_accept_rsp *dst;
-	unsigned int n_peer_identity = 0;
-	unsigned int n_certificate = 0;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	int i;
-
-	dst = yarg->data;
-	parg.ys = yarg->ys;
-
-	if (dst->certificate)
-		return ynl_error_parse(yarg, "attribute already present (accept.certificate)");
-	if (dst->peer_identity)
-		return ynl_error_parse(yarg, "attribute already present (accept.peer-identity)");
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == HANDSHAKE_A_ACCEPT_SOCKFD) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.sockfd = 1;
-			dst->sockfd = mnl_attr_get_u32(attr);
-		} else if (type == HANDSHAKE_A_ACCEPT_MESSAGE_TYPE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.message_type = 1;
-			dst->message_type = mnl_attr_get_u32(attr);
-		} else if (type == HANDSHAKE_A_ACCEPT_TIMEOUT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.timeout = 1;
-			dst->timeout = mnl_attr_get_u32(attr);
-		} else if (type == HANDSHAKE_A_ACCEPT_AUTH_MODE) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.auth_mode = 1;
-			dst->auth_mode = mnl_attr_get_u32(attr);
-		} else if (type == HANDSHAKE_A_ACCEPT_PEER_IDENTITY) {
-			n_peer_identity++;
-		} else if (type == HANDSHAKE_A_ACCEPT_CERTIFICATE) {
-			n_certificate++;
-		} else if (type == HANDSHAKE_A_ACCEPT_PEERNAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.peername_len = len;
-			dst->peername = malloc(len + 1);
-			memcpy(dst->peername, mnl_attr_get_str(attr), len);
-			dst->peername[len] = 0;
-		}
-	}
-
-	if (n_certificate) {
-		dst->certificate = calloc(n_certificate, sizeof(*dst->certificate));
-		dst->n_certificate = n_certificate;
-		i = 0;
-		parg.rsp_policy = &handshake_x509_nest;
-		mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-			if (mnl_attr_get_type(attr) == HANDSHAKE_A_ACCEPT_CERTIFICATE) {
-				parg.data = &dst->certificate[i];
-				if (handshake_x509_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
-		}
-	}
-	if (n_peer_identity) {
-		dst->peer_identity = calloc(n_peer_identity, sizeof(*dst->peer_identity));
-		dst->n_peer_identity = n_peer_identity;
-		i = 0;
-		mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-			if (mnl_attr_get_type(attr) == HANDSHAKE_A_ACCEPT_PEER_IDENTITY) {
-				dst->peer_identity[i] = mnl_attr_get_u32(attr);
-				i++;
-			}
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct handshake_accept_rsp *
-handshake_accept(struct ynl_sock *ys, struct handshake_accept_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct handshake_accept_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, HANDSHAKE_CMD_ACCEPT, 1);
-	ys->req_policy = &handshake_accept_nest;
-	yrs.yarg.rsp_policy = &handshake_accept_nest;
-
-	if (req->_present.handler_class)
-		mnl_attr_put_u32(nlh, HANDSHAKE_A_ACCEPT_HANDLER_CLASS, req->handler_class);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = handshake_accept_rsp_parse;
-	yrs.rsp_cmd = HANDSHAKE_CMD_ACCEPT;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	handshake_accept_rsp_free(rsp);
-	return NULL;
-}
-
-/* HANDSHAKE_CMD_ACCEPT - notify */
-void handshake_accept_ntf_free(struct handshake_accept_ntf *rsp)
-{
-	unsigned int i;
-
-	free(rsp->obj.peer_identity);
-	for (i = 0; i < rsp->obj.n_certificate; i++)
-		handshake_x509_free(&rsp->obj.certificate[i]);
-	free(rsp->obj.certificate);
-	free(rsp->obj.peername);
-	free(rsp);
-}
-
-/* ============== HANDSHAKE_CMD_DONE ============== */
-/* HANDSHAKE_CMD_DONE - do */
-void handshake_done_req_free(struct handshake_done_req *req)
-{
-	free(req->remote_auth);
-	free(req);
-}
-
-int handshake_done(struct ynl_sock *ys, struct handshake_done_req *req)
-{
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, HANDSHAKE_CMD_DONE, 1);
-	ys->req_policy = &handshake_done_nest;
-
-	if (req->_present.status)
-		mnl_attr_put_u32(nlh, HANDSHAKE_A_DONE_STATUS, req->status);
-	if (req->_present.sockfd)
-		mnl_attr_put_u32(nlh, HANDSHAKE_A_DONE_SOCKFD, req->sockfd);
-	for (unsigned int i = 0; i < req->n_remote_auth; i++)
-		mnl_attr_put_u32(nlh, HANDSHAKE_A_DONE_REMOTE_AUTH, req->remote_auth[i]);
-
-	err = ynl_exec(ys, nlh, NULL);
-	if (err < 0)
-		return -1;
-
-	return 0;
-}
-
-static const struct ynl_ntf_info handshake_ntf_info[] =  {
-	[HANDSHAKE_CMD_READY] =  {
-		.alloc_sz	= sizeof(struct handshake_accept_ntf),
-		.cb		= handshake_accept_rsp_parse,
-		.policy		= &handshake_accept_nest,
-		.free		= (void *)handshake_accept_ntf_free,
-	},
-};
-
-const struct ynl_family ynl_handshake_family =  {
-	.name		= "handshake",
-	.ntf_info	= handshake_ntf_info,
-	.ntf_info_size	= MNL_ARRAY_SIZE(handshake_ntf_info),
-};
diff --git a/tools/net/ynl/generated/handshake-user.h b/tools/net/ynl/generated/handshake-user.h
deleted file mode 100644
index bce537d8b8cc..000000000000
--- a/tools/net/ynl/generated/handshake-user.h
+++ /dev/null
@@ -1,145 +0,0 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
-/* Do not edit directly, auto-generated from: */
-/*	Documentation/netlink/specs/handshake.yaml */
-/* YNL-GEN user header */
-
-#ifndef _LINUX_HANDSHAKE_GEN_H
-#define _LINUX_HANDSHAKE_GEN_H
-
-#include <stdlib.h>
-#include <string.h>
-#include <linux/types.h>
-#include <linux/handshake.h>
-
-struct ynl_sock;
-
-extern const struct ynl_family ynl_handshake_family;
-
-/* Enums */
-const char *handshake_op_str(int op);
-const char *handshake_handler_class_str(enum handshake_handler_class value);
-const char *handshake_msg_type_str(enum handshake_msg_type value);
-const char *handshake_auth_str(enum handshake_auth value);
-
-/* Common nested types */
-struct handshake_x509 {
-	struct {
-		__u32 cert:1;
-		__u32 privkey:1;
-	} _present;
-
-	__s32 cert;
-	__s32 privkey;
-};
-
-/* ============== HANDSHAKE_CMD_ACCEPT ============== */
-/* HANDSHAKE_CMD_ACCEPT - do */
-struct handshake_accept_req {
-	struct {
-		__u32 handler_class:1;
-	} _present;
-
-	enum handshake_handler_class handler_class;
-};
-
-static inline struct handshake_accept_req *handshake_accept_req_alloc(void)
-{
-	return calloc(1, sizeof(struct handshake_accept_req));
-}
-void handshake_accept_req_free(struct handshake_accept_req *req);
-
-static inline void
-handshake_accept_req_set_handler_class(struct handshake_accept_req *req,
-				       enum handshake_handler_class handler_class)
-{
-	req->_present.handler_class = 1;
-	req->handler_class = handler_class;
-}
-
-struct handshake_accept_rsp {
-	struct {
-		__u32 sockfd:1;
-		__u32 message_type:1;
-		__u32 timeout:1;
-		__u32 auth_mode:1;
-		__u32 peername_len;
-	} _present;
-
-	__s32 sockfd;
-	enum handshake_msg_type message_type;
-	__u32 timeout;
-	enum handshake_auth auth_mode;
-	unsigned int n_peer_identity;
-	__u32 *peer_identity;
-	unsigned int n_certificate;
-	struct handshake_x509 *certificate;
-	char *peername;
-};
-
-void handshake_accept_rsp_free(struct handshake_accept_rsp *rsp);
-
-/*
- * Handler retrieves next queued handshake request
- */
-struct handshake_accept_rsp *
-handshake_accept(struct ynl_sock *ys, struct handshake_accept_req *req);
-
-/* HANDSHAKE_CMD_ACCEPT - notify */
-struct handshake_accept_ntf {
-	__u16 family;
-	__u8 cmd;
-	struct ynl_ntf_base_type *next;
-	void (*free)(struct handshake_accept_ntf *ntf);
-	struct handshake_accept_rsp obj __attribute__((aligned(8)));
-};
-
-void handshake_accept_ntf_free(struct handshake_accept_ntf *rsp);
-
-/* ============== HANDSHAKE_CMD_DONE ============== */
-/* HANDSHAKE_CMD_DONE - do */
-struct handshake_done_req {
-	struct {
-		__u32 status:1;
-		__u32 sockfd:1;
-	} _present;
-
-	__u32 status;
-	__s32 sockfd;
-	unsigned int n_remote_auth;
-	__u32 *remote_auth;
-};
-
-static inline struct handshake_done_req *handshake_done_req_alloc(void)
-{
-	return calloc(1, sizeof(struct handshake_done_req));
-}
-void handshake_done_req_free(struct handshake_done_req *req);
-
-static inline void
-handshake_done_req_set_status(struct handshake_done_req *req, __u32 status)
-{
-	req->_present.status = 1;
-	req->status = status;
-}
-static inline void
-handshake_done_req_set_sockfd(struct handshake_done_req *req, __s32 sockfd)
-{
-	req->_present.sockfd = 1;
-	req->sockfd = sockfd;
-}
-static inline void
-__handshake_done_req_set_remote_auth(struct handshake_done_req *req,
-				     __u32 *remote_auth,
-				     unsigned int n_remote_auth)
-{
-	free(req->remote_auth);
-	req->remote_auth = remote_auth;
-	req->n_remote_auth = n_remote_auth;
-}
-
-/*
- * Handler reports handshake completion
- */
-int handshake_done(struct ynl_sock *ys, struct handshake_done_req *req);
-
-#endif /* _LINUX_HANDSHAKE_GEN_H */
diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c
deleted file mode 100644
index b5ffe8cd1144..000000000000
--- a/tools/net/ynl/generated/netdev-user.c
+++ /dev/null
@@ -1,225 +0,0 @@
-// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
-/* Do not edit directly, auto-generated from: */
-/*	Documentation/netlink/specs/netdev.yaml */
-/* YNL-GEN user source */
-
-#include <stdlib.h>
-#include <string.h>
-#include "netdev-user.h"
-#include "ynl.h"
-#include <linux/netdev.h>
-
-#include <libmnl/libmnl.h>
-#include <linux/genetlink.h>
-
-/* Enums */
-static const char * const netdev_op_strmap[] = {
-	[NETDEV_CMD_DEV_GET] = "dev-get",
-	[NETDEV_CMD_DEV_ADD_NTF] = "dev-add-ntf",
-	[NETDEV_CMD_DEV_DEL_NTF] = "dev-del-ntf",
-	[NETDEV_CMD_DEV_CHANGE_NTF] = "dev-change-ntf",
-};
-
-const char *netdev_op_str(int op)
-{
-	if (op < 0 || op >= (int)MNL_ARRAY_SIZE(netdev_op_strmap))
-		return NULL;
-	return netdev_op_strmap[op];
-}
-
-static const char * const netdev_xdp_act_strmap[] = {
-	[0] = "basic",
-	[1] = "redirect",
-	[2] = "ndo-xmit",
-	[3] = "xsk-zerocopy",
-	[4] = "hw-offload",
-	[5] = "rx-sg",
-	[6] = "ndo-xmit-sg",
-};
-
-const char *netdev_xdp_act_str(enum netdev_xdp_act value)
-{
-	value = ffs(value) - 1;
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(netdev_xdp_act_strmap))
-		return NULL;
-	return netdev_xdp_act_strmap[value];
-}
-
-static const char * const netdev_xdp_rx_metadata_strmap[] = {
-	[0] = "timestamp",
-	[1] = "hash",
-};
-
-const char *netdev_xdp_rx_metadata_str(enum netdev_xdp_rx_metadata value)
-{
-	value = ffs(value) - 1;
-	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(netdev_xdp_rx_metadata_strmap))
-		return NULL;
-	return netdev_xdp_rx_metadata_strmap[value];
-}
-
-/* Policies */
-struct ynl_policy_attr netdev_dev_policy[NETDEV_A_DEV_MAX + 1] = {
-	[NETDEV_A_DEV_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, },
-	[NETDEV_A_DEV_PAD] = { .name = "pad", .type = YNL_PT_IGNORE, },
-	[NETDEV_A_DEV_XDP_FEATURES] = { .name = "xdp-features", .type = YNL_PT_U64, },
-	[NETDEV_A_DEV_XDP_ZC_MAX_SEGS] = { .name = "xdp-zc-max-segs", .type = YNL_PT_U32, },
-	[NETDEV_A_DEV_XDP_RX_METADATA_FEATURES] = { .name = "xdp-rx-metadata-features", .type = YNL_PT_U64, },
-};
-
-struct ynl_policy_nest netdev_dev_nest = {
-	.max_attr = NETDEV_A_DEV_MAX,
-	.table = netdev_dev_policy,
-};
-
-/* Common nested types */
-/* ============== NETDEV_CMD_DEV_GET ============== */
-/* NETDEV_CMD_DEV_GET - do */
-void netdev_dev_get_req_free(struct netdev_dev_get_req *req)
-{
-	free(req);
-}
-
-void netdev_dev_get_rsp_free(struct netdev_dev_get_rsp *rsp)
-{
-	free(rsp);
-}
-
-int netdev_dev_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct ynl_parse_arg *yarg = data;
-	struct netdev_dev_get_rsp *dst;
-	const struct nlattr *attr;
-
-	dst = yarg->data;
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == NETDEV_A_DEV_IFINDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.ifindex = 1;
-			dst->ifindex = mnl_attr_get_u32(attr);
-		} else if (type == NETDEV_A_DEV_XDP_FEATURES) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.xdp_features = 1;
-			dst->xdp_features = mnl_attr_get_u64(attr);
-		} else if (type == NETDEV_A_DEV_XDP_ZC_MAX_SEGS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.xdp_zc_max_segs = 1;
-			dst->xdp_zc_max_segs = mnl_attr_get_u32(attr);
-		} else if (type == NETDEV_A_DEV_XDP_RX_METADATA_FEATURES) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.xdp_rx_metadata_features = 1;
-			dst->xdp_rx_metadata_features = mnl_attr_get_u64(attr);
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-struct netdev_dev_get_rsp *
-netdev_dev_get(struct ynl_sock *ys, struct netdev_dev_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct netdev_dev_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, NETDEV_CMD_DEV_GET, 1);
-	ys->req_policy = &netdev_dev_nest;
-	yrs.yarg.rsp_policy = &netdev_dev_nest;
-
-	if (req->_present.ifindex)
-		mnl_attr_put_u32(nlh, NETDEV_A_DEV_IFINDEX, req->ifindex);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = netdev_dev_get_rsp_parse;
-	yrs.rsp_cmd = NETDEV_CMD_DEV_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	netdev_dev_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* NETDEV_CMD_DEV_GET - dump */
-void netdev_dev_get_list_free(struct netdev_dev_get_list *rsp)
-{
-	struct netdev_dev_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp);
-	}
-}
-
-struct netdev_dev_get_list *netdev_dev_get_dump(struct ynl_sock *ys)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct netdev_dev_get_list);
-	yds.cb = netdev_dev_get_rsp_parse;
-	yds.rsp_cmd = NETDEV_CMD_DEV_GET;
-	yds.rsp_policy = &netdev_dev_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, NETDEV_CMD_DEV_GET, 1);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	netdev_dev_get_list_free(yds.first);
-	return NULL;
-}
-
-/* NETDEV_CMD_DEV_GET - notify */
-void netdev_dev_get_ntf_free(struct netdev_dev_get_ntf *rsp)
-{
-	free(rsp);
-}
-
-static const struct ynl_ntf_info netdev_ntf_info[] =  {
-	[NETDEV_CMD_DEV_ADD_NTF] =  {
-		.alloc_sz	= sizeof(struct netdev_dev_get_ntf),
-		.cb		= netdev_dev_get_rsp_parse,
-		.policy		= &netdev_dev_nest,
-		.free		= (void *)netdev_dev_get_ntf_free,
-	},
-	[NETDEV_CMD_DEV_DEL_NTF] =  {
-		.alloc_sz	= sizeof(struct netdev_dev_get_ntf),
-		.cb		= netdev_dev_get_rsp_parse,
-		.policy		= &netdev_dev_nest,
-		.free		= (void *)netdev_dev_get_ntf_free,
-	},
-	[NETDEV_CMD_DEV_CHANGE_NTF] =  {
-		.alloc_sz	= sizeof(struct netdev_dev_get_ntf),
-		.cb		= netdev_dev_get_rsp_parse,
-		.policy		= &netdev_dev_nest,
-		.free		= (void *)netdev_dev_get_ntf_free,
-	},
-};
-
-const struct ynl_family ynl_netdev_family =  {
-	.name		= "netdev",
-	.ntf_info	= netdev_ntf_info,
-	.ntf_info_size	= MNL_ARRAY_SIZE(netdev_ntf_info),
-};
diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h
deleted file mode 100644
index 4fafac879df3..000000000000
--- a/tools/net/ynl/generated/netdev-user.h
+++ /dev/null
@@ -1,90 +0,0 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
-/* Do not edit directly, auto-generated from: */
-/*	Documentation/netlink/specs/netdev.yaml */
-/* YNL-GEN user header */
-
-#ifndef _LINUX_NETDEV_GEN_H
-#define _LINUX_NETDEV_GEN_H
-
-#include <stdlib.h>
-#include <string.h>
-#include <linux/types.h>
-#include <linux/netdev.h>
-
-struct ynl_sock;
-
-extern const struct ynl_family ynl_netdev_family;
-
-/* Enums */
-const char *netdev_op_str(int op);
-const char *netdev_xdp_act_str(enum netdev_xdp_act value);
-const char *netdev_xdp_rx_metadata_str(enum netdev_xdp_rx_metadata value);
-
-/* Common nested types */
-/* ============== NETDEV_CMD_DEV_GET ============== */
-/* NETDEV_CMD_DEV_GET - do */
-struct netdev_dev_get_req {
-	struct {
-		__u32 ifindex:1;
-	} _present;
-
-	__u32 ifindex;
-};
-
-static inline struct netdev_dev_get_req *netdev_dev_get_req_alloc(void)
-{
-	return calloc(1, sizeof(struct netdev_dev_get_req));
-}
-void netdev_dev_get_req_free(struct netdev_dev_get_req *req);
-
-static inline void
-netdev_dev_get_req_set_ifindex(struct netdev_dev_get_req *req, __u32 ifindex)
-{
-	req->_present.ifindex = 1;
-	req->ifindex = ifindex;
-}
-
-struct netdev_dev_get_rsp {
-	struct {
-		__u32 ifindex:1;
-		__u32 xdp_features:1;
-		__u32 xdp_zc_max_segs:1;
-		__u32 xdp_rx_metadata_features:1;
-	} _present;
-
-	__u32 ifindex;
-	__u64 xdp_features;
-	__u32 xdp_zc_max_segs;
-	__u64 xdp_rx_metadata_features;
-};
-
-void netdev_dev_get_rsp_free(struct netdev_dev_get_rsp *rsp);
-
-/*
- * Get / dump information about a netdev.
- */
-struct netdev_dev_get_rsp *
-netdev_dev_get(struct ynl_sock *ys, struct netdev_dev_get_req *req);
-
-/* NETDEV_CMD_DEV_GET - dump */
-struct netdev_dev_get_list {
-	struct netdev_dev_get_list *next;
-	struct netdev_dev_get_rsp obj __attribute__((aligned(8)));
-};
-
-void netdev_dev_get_list_free(struct netdev_dev_get_list *rsp);
-
-struct netdev_dev_get_list *netdev_dev_get_dump(struct ynl_sock *ys);
-
-/* NETDEV_CMD_DEV_GET - notify */
-struct netdev_dev_get_ntf {
-	__u16 family;
-	__u8 cmd;
-	struct ynl_ntf_base_type *next;
-	void (*free)(struct netdev_dev_get_ntf *ntf);
-	struct netdev_dev_get_rsp obj __attribute__((aligned(8)));
-};
-
-void netdev_dev_get_ntf_free(struct netdev_dev_get_ntf *rsp);
-
-#endif /* _LINUX_NETDEV_GEN_H */
diff --git a/tools/net/ynl/generated/nfsd-user.c b/tools/net/ynl/generated/nfsd-user.c
deleted file mode 100644
index 360b6448c6e9..000000000000
--- a/tools/net/ynl/generated/nfsd-user.c
+++ /dev/null
@@ -1,203 +0,0 @@
-// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
-/* Do not edit directly, auto-generated from: */
-/*	Documentation/netlink/specs/nfsd.yaml */
-/* YNL-GEN user source */
-
-#include <stdlib.h>
-#include <string.h>
-#include "nfsd-user.h"
-#include "ynl.h"
-#include <linux/nfsd_netlink.h>
-
-#include <libmnl/libmnl.h>
-#include <linux/genetlink.h>
-
-/* Enums */
-static const char * const nfsd_op_strmap[] = {
-	[NFSD_CMD_RPC_STATUS_GET] = "rpc-status-get",
-};
-
-const char *nfsd_op_str(int op)
-{
-	if (op < 0 || op >= (int)MNL_ARRAY_SIZE(nfsd_op_strmap))
-		return NULL;
-	return nfsd_op_strmap[op];
-}
-
-/* Policies */
-struct ynl_policy_attr nfsd_rpc_status_policy[NFSD_A_RPC_STATUS_MAX + 1] = {
-	[NFSD_A_RPC_STATUS_XID] = { .name = "xid", .type = YNL_PT_U32, },
-	[NFSD_A_RPC_STATUS_FLAGS] = { .name = "flags", .type = YNL_PT_U32, },
-	[NFSD_A_RPC_STATUS_PROG] = { .name = "prog", .type = YNL_PT_U32, },
-	[NFSD_A_RPC_STATUS_VERSION] = { .name = "version", .type = YNL_PT_U8, },
-	[NFSD_A_RPC_STATUS_PROC] = { .name = "proc", .type = YNL_PT_U32, },
-	[NFSD_A_RPC_STATUS_SERVICE_TIME] = { .name = "service_time", .type = YNL_PT_U64, },
-	[NFSD_A_RPC_STATUS_PAD] = { .name = "pad", .type = YNL_PT_IGNORE, },
-	[NFSD_A_RPC_STATUS_SADDR4] = { .name = "saddr4", .type = YNL_PT_U32, },
-	[NFSD_A_RPC_STATUS_DADDR4] = { .name = "daddr4", .type = YNL_PT_U32, },
-	[NFSD_A_RPC_STATUS_SADDR6] = { .name = "saddr6", .type = YNL_PT_BINARY,},
-	[NFSD_A_RPC_STATUS_DADDR6] = { .name = "daddr6", .type = YNL_PT_BINARY,},
-	[NFSD_A_RPC_STATUS_SPORT] = { .name = "sport", .type = YNL_PT_U16, },
-	[NFSD_A_RPC_STATUS_DPORT] = { .name = "dport", .type = YNL_PT_U16, },
-	[NFSD_A_RPC_STATUS_COMPOUND_OPS] = { .name = "compound-ops", .type = YNL_PT_U32, },
-};
-
-struct ynl_policy_nest nfsd_rpc_status_nest = {
-	.max_attr = NFSD_A_RPC_STATUS_MAX,
-	.table = nfsd_rpc_status_policy,
-};
-
-/* Common nested types */
-/* ============== NFSD_CMD_RPC_STATUS_GET ============== */
-/* NFSD_CMD_RPC_STATUS_GET - dump */
-int nfsd_rpc_status_get_rsp_dump_parse(const struct nlmsghdr *nlh, void *data)
-{
-	struct nfsd_rpc_status_get_rsp_dump *dst;
-	struct ynl_parse_arg *yarg = data;
-	unsigned int n_compound_ops = 0;
-	const struct nlattr *attr;
-	int i;
-
-	dst = yarg->data;
-
-	if (dst->compound_ops)
-		return ynl_error_parse(yarg, "attribute already present (rpc-status.compound-ops)");
-
-	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-		unsigned int type = mnl_attr_get_type(attr);
-
-		if (type == NFSD_A_RPC_STATUS_XID) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.xid = 1;
-			dst->xid = mnl_attr_get_u32(attr);
-		} else if (type == NFSD_A_RPC_STATUS_FLAGS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.flags = 1;
-			dst->flags = mnl_attr_get_u32(attr);
-		} else if (type == NFSD_A_RPC_STATUS_PROG) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.prog = 1;
-			dst->prog = mnl_attr_get_u32(attr);
-		} else if (type == NFSD_A_RPC_STATUS_VERSION) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.version = 1;
-			dst->version = mnl_attr_get_u8(attr);
-		} else if (type == NFSD_A_RPC_STATUS_PROC) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.proc = 1;
-			dst->proc = mnl_attr_get_u32(attr);
-		} else if (type == NFSD_A_RPC_STATUS_SERVICE_TIME) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.service_time = 1;
-			dst->service_time = mnl_attr_get_u64(attr);
-		} else if (type == NFSD_A_RPC_STATUS_SADDR4) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.saddr4 = 1;
-			dst->saddr4 = mnl_attr_get_u32(attr);
-		} else if (type == NFSD_A_RPC_STATUS_DADDR4) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.daddr4 = 1;
-			dst->daddr4 = mnl_attr_get_u32(attr);
-		} else if (type == NFSD_A_RPC_STATUS_SADDR6) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = mnl_attr_get_payload_len(attr);
-			dst->_present.saddr6_len = len;
-			dst->saddr6 = malloc(len);
-			memcpy(dst->saddr6, mnl_attr_get_payload(attr), len);
-		} else if (type == NFSD_A_RPC_STATUS_DADDR6) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = mnl_attr_get_payload_len(attr);
-			dst->_present.daddr6_len = len;
-			dst->daddr6 = malloc(len);
-			memcpy(dst->daddr6, mnl_attr_get_payload(attr), len);
-		} else if (type == NFSD_A_RPC_STATUS_SPORT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.sport = 1;
-			dst->sport = mnl_attr_get_u16(attr);
-		} else if (type == NFSD_A_RPC_STATUS_DPORT) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dport = 1;
-			dst->dport = mnl_attr_get_u16(attr);
-		} else if (type == NFSD_A_RPC_STATUS_COMPOUND_OPS) {
-			n_compound_ops++;
-		}
-	}
-
-	if (n_compound_ops) {
-		dst->compound_ops = calloc(n_compound_ops, sizeof(*dst->compound_ops));
-		dst->n_compound_ops = n_compound_ops;
-		i = 0;
-		mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
-			if (mnl_attr_get_type(attr) == NFSD_A_RPC_STATUS_COMPOUND_OPS) {
-				dst->compound_ops[i] = mnl_attr_get_u32(attr);
-				i++;
-			}
-		}
-	}
-
-	return MNL_CB_OK;
-}
-
-void
-nfsd_rpc_status_get_rsp_list_free(struct nfsd_rpc_status_get_rsp_list *rsp)
-{
-	struct nfsd_rpc_status_get_rsp_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.saddr6);
-		free(rsp->obj.daddr6);
-		free(rsp->obj.compound_ops);
-		free(rsp);
-	}
-}
-
-struct nfsd_rpc_status_get_rsp_list *
-nfsd_rpc_status_get_dump(struct ynl_sock *ys)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct nfsd_rpc_status_get_rsp_list);
-	yds.cb = nfsd_rpc_status_get_rsp_dump_parse;
-	yds.rsp_cmd = NFSD_CMD_RPC_STATUS_GET;
-	yds.rsp_policy = &nfsd_rpc_status_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, NFSD_CMD_RPC_STATUS_GET, 1);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	nfsd_rpc_status_get_rsp_list_free(yds.first);
-	return NULL;
-}
-
-const struct ynl_family ynl_nfsd_family =  {
-	.name		= "nfsd",
-};
diff --git a/tools/net/ynl/generated/nfsd-user.h b/tools/net/ynl/generated/nfsd-user.h
deleted file mode 100644
index 989c6e209ced..000000000000
--- a/tools/net/ynl/generated/nfsd-user.h
+++ /dev/null
@@ -1,67 +0,0 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
-/* Do not edit directly, auto-generated from: */
-/*	Documentation/netlink/specs/nfsd.yaml */
-/* YNL-GEN user header */
-
-#ifndef _LINUX_NFSD_GEN_H
-#define _LINUX_NFSD_GEN_H
-
-#include <stdlib.h>
-#include <string.h>
-#include <linux/types.h>
-#include <linux/nfsd_netlink.h>
-
-struct ynl_sock;
-
-extern const struct ynl_family ynl_nfsd_family;
-
-/* Enums */
-const char *nfsd_op_str(int op);
-
-/* Common nested types */
-/* ============== NFSD_CMD_RPC_STATUS_GET ============== */
-/* NFSD_CMD_RPC_STATUS_GET - dump */
-struct nfsd_rpc_status_get_rsp_dump {
-	struct {
-		__u32 xid:1;
-		__u32 flags:1;
-		__u32 prog:1;
-		__u32 version:1;
-		__u32 proc:1;
-		__u32 service_time:1;
-		__u32 saddr4:1;
-		__u32 daddr4:1;
-		__u32 saddr6_len;
-		__u32 daddr6_len;
-		__u32 sport:1;
-		__u32 dport:1;
-	} _present;
-
-	__u32 xid /* big-endian */;
-	__u32 flags;
-	__u32 prog;
-	__u8 version;
-	__u32 proc;
-	__s64 service_time;
-	__u32 saddr4 /* big-endian */;
-	__u32 daddr4 /* big-endian */;
-	void *saddr6;
-	void *daddr6;
-	__u16 sport /* big-endian */;
-	__u16 dport /* big-endian */;
-	unsigned int n_compound_ops;
-	__u32 *compound_ops;
-};
-
-struct nfsd_rpc_status_get_rsp_list {
-	struct nfsd_rpc_status_get_rsp_list *next;
-	struct nfsd_rpc_status_get_rsp_dump obj __attribute__((aligned(8)));
-};
-
-void
-nfsd_rpc_status_get_rsp_list_free(struct nfsd_rpc_status_get_rsp_list *rsp);
-
-struct nfsd_rpc_status_get_rsp_list *
-nfsd_rpc_status_get_dump(struct ynl_sock *ys);
-
-#endif /* _LINUX_NFSD_GEN_H */
diff --git a/tools/net/ynl/lib/nlspec.py b/tools/net/ynl/lib/nlspec.py
index 92889298b197..44f13e383e8a 100644
--- a/tools/net/ynl/lib/nlspec.py
+++ b/tools/net/ynl/lib/nlspec.py
@@ -158,6 +158,9 @@ class SpecAttr(SpecElement):
         len           integer, optional byte length of binary types
         display_hint  string, hint to help choose format specifier
                       when displaying the value
+        sub_message   string, name of sub message type
+        selector      string, name of attribute used to select
+                      sub-message type
 
         is_auto_scalar bool, attr is a variable-size scalar
     """
@@ -173,6 +176,8 @@ class SpecAttr(SpecElement):
         self.byte_order = yaml.get('byte-order')
         self.len = yaml.get('len')
         self.display_hint = yaml.get('display-hint')
+        self.sub_message = yaml.get('sub-message')
+        self.selector = yaml.get('selector')
 
         self.is_auto_scalar = self.type == "sint" or self.type == "uint"
 
@@ -278,6 +283,47 @@ class SpecStruct(SpecElement):
         return self.members.items()
 
 
+class SpecSubMessage(SpecElement):
+    """ Netlink sub-message definition
+
+    Represents a set of sub-message formats for polymorphic nlattrs
+    that contain type-specific sub messages.
+
+    Attributes:
+        name     string, name of sub-message definition
+        formats  dict of sub-message formats indexed by match value
+    """
+    def __init__(self, family, yaml):
+        super().__init__(family, yaml)
+
+        self.formats = collections.OrderedDict()
+        for elem in self.yaml['formats']:
+            format = self.new_format(family, elem)
+            self.formats[format.value] = format
+
+    def new_format(self, family, format):
+        return SpecSubMessageFormat(family, format)
+
+
+class SpecSubMessageFormat(SpecElement):
+    """ Netlink sub-message definition
+
+    Represents a set of sub-message formats for polymorphic nlattrs
+    that contain type-specific sub messages.
+
+    Attributes:
+        value         attribute value to match against type selector
+        fixed_header  string, name of fixed header, or None
+        attr_set      string, name of attribute set, or None
+    """
+    def __init__(self, family, yaml):
+        super().__init__(family, yaml)
+
+        self.value = yaml.get('value')
+        self.fixed_header = yaml.get('fixed-header')
+        self.attr_set = yaml.get('attribute-set')
+
+
 class SpecOperation(SpecElement):
     """Netlink Operation
 
@@ -365,6 +411,7 @@ class SpecFamily(SpecElement):
 
         attr_sets  dict of attribute sets
         msgs       dict of all messages (index by name)
+        sub_msgs   dict of all sub messages (index by name)
         ops        dict of all valid requests / responses
         ntfs       dict of all async events
         consts     dict of all constants/enums
@@ -405,6 +452,7 @@ class SpecFamily(SpecElement):
             jsonschema.validate(self.yaml, schema)
 
         self.attr_sets = collections.OrderedDict()
+        self.sub_msgs = collections.OrderedDict()
         self.msgs = collections.OrderedDict()
         self.req_by_value = collections.OrderedDict()
         self.rsp_by_value = collections.OrderedDict()
@@ -441,6 +489,9 @@ class SpecFamily(SpecElement):
     def new_struct(self, elem):
         return SpecStruct(self, elem)
 
+    def new_sub_message(self, elem):
+        return SpecSubMessage(self, elem);
+
     def new_operation(self, elem, req_val, rsp_val):
         return SpecOperation(self, elem, req_val, rsp_val)
 
@@ -529,6 +580,10 @@ class SpecFamily(SpecElement):
             attr_set = self.new_attr_set(elem)
             self.attr_sets[elem['name']] = attr_set
 
+        for elem in self.yaml.get('sub-messages', []):
+            sub_message = self.new_sub_message(elem)
+            self.sub_msgs[sub_message.name] = sub_message
+
         if self.msg_id_model == 'unified':
             self._dictify_ops_unified()
         elif self.msg_id_model == 'directional':
diff --git a/tools/net/ynl/lib/ynl-priv.h b/tools/net/ynl/lib/ynl-priv.h
new file mode 100644
index 000000000000..7491da8e7555
--- /dev/null
+++ b/tools/net/ynl/lib/ynl-priv.h
@@ -0,0 +1,144 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+#ifndef __YNL_C_PRIV_H
+#define __YNL_C_PRIV_H 1
+
+#include <stddef.h>
+#include <libmnl/libmnl.h>
+#include <linux/types.h>
+
+/*
+ * YNL internals / low level stuff
+ */
+
+/* Generic mnl helper code */
+
+enum ynl_policy_type {
+	YNL_PT_REJECT = 1,
+	YNL_PT_IGNORE,
+	YNL_PT_NEST,
+	YNL_PT_FLAG,
+	YNL_PT_BINARY,
+	YNL_PT_U8,
+	YNL_PT_U16,
+	YNL_PT_U32,
+	YNL_PT_U64,
+	YNL_PT_UINT,
+	YNL_PT_NUL_STR,
+	YNL_PT_BITFIELD32,
+};
+
+struct ynl_policy_attr {
+	enum ynl_policy_type type;
+	unsigned int len;
+	const char *name;
+	struct ynl_policy_nest *nest;
+};
+
+struct ynl_policy_nest {
+	unsigned int max_attr;
+	struct ynl_policy_attr *table;
+};
+
+struct ynl_parse_arg {
+	struct ynl_sock *ys;
+	struct ynl_policy_nest *rsp_policy;
+	void *data;
+};
+
+struct ynl_dump_list_type {
+	struct ynl_dump_list_type *next;
+	unsigned char data[] __attribute__((aligned(8)));
+};
+extern struct ynl_dump_list_type *YNL_LIST_END;
+
+static inline bool ynl_dump_obj_is_last(void *obj)
+{
+	unsigned long uptr = (unsigned long)obj;
+
+	uptr -= offsetof(struct ynl_dump_list_type, data);
+	return uptr == (unsigned long)YNL_LIST_END;
+}
+
+static inline void *ynl_dump_obj_next(void *obj)
+{
+	unsigned long uptr = (unsigned long)obj;
+	struct ynl_dump_list_type *list;
+
+	uptr -= offsetof(struct ynl_dump_list_type, data);
+	list = (void *)uptr;
+	uptr = (unsigned long)list->next;
+	uptr += offsetof(struct ynl_dump_list_type, data);
+
+	return (void *)uptr;
+}
+
+struct ynl_ntf_base_type {
+	__u16 family;
+	__u8 cmd;
+	struct ynl_ntf_base_type *next;
+	void (*free)(struct ynl_ntf_base_type *ntf);
+	unsigned char data[] __attribute__((aligned(8)));
+};
+
+extern mnl_cb_t ynl_cb_array[NLMSG_MIN_TYPE];
+
+struct nlmsghdr *
+ynl_gemsg_start_req(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version);
+struct nlmsghdr *
+ynl_gemsg_start_dump(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version);
+
+int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr);
+
+int ynl_recv_ack(struct ynl_sock *ys, int ret);
+int ynl_cb_null(const struct nlmsghdr *nlh, void *data);
+
+/* YNL specific helpers used by the auto-generated code */
+
+struct ynl_req_state {
+	struct ynl_parse_arg yarg;
+	mnl_cb_t cb;
+	__u32 rsp_cmd;
+};
+
+struct ynl_dump_state {
+	struct ynl_sock *ys;
+	struct ynl_policy_nest *rsp_policy;
+	void *first;
+	struct ynl_dump_list_type *last;
+	size_t alloc_sz;
+	mnl_cb_t cb;
+	__u32 rsp_cmd;
+};
+
+struct ynl_ntf_info {
+	struct ynl_policy_nest *policy;
+	mnl_cb_t cb;
+	size_t alloc_sz;
+	void (*free)(struct ynl_ntf_base_type *ntf);
+};
+
+int ynl_exec(struct ynl_sock *ys, struct nlmsghdr *req_nlh,
+	     struct ynl_req_state *yrs);
+int ynl_exec_dump(struct ynl_sock *ys, struct nlmsghdr *req_nlh,
+		  struct ynl_dump_state *yds);
+
+void ynl_error_unknown_notification(struct ynl_sock *ys, __u8 cmd);
+int ynl_error_parse(struct ynl_parse_arg *yarg, const char *msg);
+
+#ifndef MNL_HAS_AUTO_SCALARS
+static inline uint64_t mnl_attr_get_uint(const struct nlattr *attr)
+{
+	if (mnl_attr_get_payload_len(attr) == 4)
+		return mnl_attr_get_u32(attr);
+	return mnl_attr_get_u64(attr);
+}
+
+static inline void
+mnl_attr_put_uint(struct nlmsghdr *nlh, uint16_t type, uint64_t data)
+{
+	if ((uint32_t)data == (uint64_t)data)
+		return mnl_attr_put_u32(nlh, type, data);
+	return mnl_attr_put_u64(nlh, type, data);
+}
+#endif
+#endif
diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c
index 830d25097009..c82a7f41b31c 100644
--- a/tools/net/ynl/lib/ynl.c
+++ b/tools/net/ynl/lib/ynl.c
@@ -145,8 +145,10 @@ ynl_ext_ack_check(struct ynl_sock *ys, const struct nlmsghdr *nlh,
 	const struct nlattr *attr;
 	const char *str = NULL;
 
-	if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS))
+	if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS)) {
+		yerr_msg(ys, "%s", strerror(ys->err.code));
 		return MNL_CB_OK;
+	}
 
 	mnl_attr_for_each(attr, nlh, hlen) {
 		unsigned int len, type;
@@ -189,12 +191,12 @@ ynl_ext_ack_check(struct ynl_sock *ys, const struct nlmsghdr *nlh,
 			     str ? " (" : "");
 
 		start = mnl_nlmsg_get_payload_offset(ys->nlh,
-						     sizeof(struct genlmsghdr));
+						     ys->family->hdr_len);
 		end = mnl_nlmsg_get_payload_tail(ys->nlh);
 
 		off = ys->err.attr_offs;
 		off -= sizeof(struct nlmsghdr);
-		off -= sizeof(struct genlmsghdr);
+		off -= ys->family->hdr_len;
 
 		n += ynl_err_walk(ys, start, end, off, ys->req_policy,
 				  &bad_attr[n], sizeof(bad_attr) - n, NULL);
@@ -215,14 +217,14 @@ ynl_ext_ack_check(struct ynl_sock *ys, const struct nlmsghdr *nlh,
 			     bad_attr[0] ? ", " : (str ? " (" : ""));
 
 		start = mnl_nlmsg_get_payload_offset(ys->nlh,
-						     sizeof(struct genlmsghdr));
+						     ys->family->hdr_len);
 		end = mnl_nlmsg_get_payload_tail(ys->nlh);
 
 		nest_pol = ys->req_policy;
 		if (tb[NLMSGERR_ATTR_MISS_NEST]) {
 			off = mnl_attr_get_u32(tb[NLMSGERR_ATTR_MISS_NEST]);
 			off -= sizeof(struct nlmsghdr);
-			off -= sizeof(struct genlmsghdr);
+			off -= ys->family->hdr_len;
 
 			n += ynl_err_walk(ys, start, end, off, ys->req_policy,
 					  &miss_attr[n], sizeof(miss_attr) - n,
@@ -249,6 +251,8 @@ ynl_ext_ack_check(struct ynl_sock *ys, const struct nlmsghdr *nlh,
 		yerr_msg(ys, "Kernel %s: %s%s",
 			 ys->err.code ? "error" : "warning",
 			 bad_attr, miss_attr);
+	else
+		yerr_msg(ys, "%s", strerror(ys->err.code));
 
 	return MNL_CB_OK;
 }
diff --git a/tools/net/ynl/lib/ynl.h b/tools/net/ynl/lib/ynl.h
index e974378e3b8c..ce77a6d76ce0 100644
--- a/tools/net/ynl/lib/ynl.h
+++ b/tools/net/ynl/lib/ynl.h
@@ -3,20 +3,10 @@
 #define __YNL_C_H 1
 
 #include <stddef.h>
-#include <libmnl/libmnl.h>
 #include <linux/genetlink.h>
 #include <linux/types.h>
 
-struct mnl_socket;
-struct nlmsghdr;
-
-/*
- * User facing code
- */
-
-struct ynl_ntf_base_type;
-struct ynl_ntf_info;
-struct ynl_sock;
+#include "ynl-priv.h"
 
 enum ynl_error_code {
 	YNL_ERROR_NONE = 0,
@@ -54,6 +44,7 @@ struct ynl_error {
 struct ynl_family {
 /* private: */
 	const char *name;
+	size_t hdr_len;
 	const struct ynl_ntf_info *ntf_info;
 	unsigned int ntf_info_size;
 };
@@ -116,140 +107,4 @@ static inline bool ynl_has_ntf(struct ynl_sock *ys)
 struct ynl_ntf_base_type *ynl_ntf_dequeue(struct ynl_sock *ys);
 
 void ynl_ntf_free(struct ynl_ntf_base_type *ntf);
-
-/*
- * YNL internals / low level stuff
- */
-
-/* Generic mnl helper code */
-
-enum ynl_policy_type {
-	YNL_PT_REJECT = 1,
-	YNL_PT_IGNORE,
-	YNL_PT_NEST,
-	YNL_PT_FLAG,
-	YNL_PT_BINARY,
-	YNL_PT_U8,
-	YNL_PT_U16,
-	YNL_PT_U32,
-	YNL_PT_U64,
-	YNL_PT_UINT,
-	YNL_PT_NUL_STR,
-	YNL_PT_BITFIELD32,
-};
-
-struct ynl_policy_attr {
-	enum ynl_policy_type type;
-	unsigned int len;
-	const char *name;
-	struct ynl_policy_nest *nest;
-};
-
-struct ynl_policy_nest {
-	unsigned int max_attr;
-	struct ynl_policy_attr *table;
-};
-
-struct ynl_parse_arg {
-	struct ynl_sock *ys;
-	struct ynl_policy_nest *rsp_policy;
-	void *data;
-};
-
-struct ynl_dump_list_type {
-	struct ynl_dump_list_type *next;
-	unsigned char data[] __attribute__((aligned(8)));
-};
-extern struct ynl_dump_list_type *YNL_LIST_END;
-
-static inline bool ynl_dump_obj_is_last(void *obj)
-{
-	unsigned long uptr = (unsigned long)obj;
-
-	uptr -= offsetof(struct ynl_dump_list_type, data);
-	return uptr == (unsigned long)YNL_LIST_END;
-}
-
-static inline void *ynl_dump_obj_next(void *obj)
-{
-	unsigned long uptr = (unsigned long)obj;
-	struct ynl_dump_list_type *list;
-
-	uptr -= offsetof(struct ynl_dump_list_type, data);
-	list = (void *)uptr;
-	uptr = (unsigned long)list->next;
-	uptr += offsetof(struct ynl_dump_list_type, data);
-
-	return (void *)uptr;
-}
-
-struct ynl_ntf_base_type {
-	__u16 family;
-	__u8 cmd;
-	struct ynl_ntf_base_type *next;
-	void (*free)(struct ynl_ntf_base_type *ntf);
-	unsigned char data[] __attribute__((aligned(8)));
-};
-
-extern mnl_cb_t ynl_cb_array[NLMSG_MIN_TYPE];
-
-struct nlmsghdr *
-ynl_gemsg_start_req(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version);
-struct nlmsghdr *
-ynl_gemsg_start_dump(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version);
-
-int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr);
-
-int ynl_recv_ack(struct ynl_sock *ys, int ret);
-int ynl_cb_null(const struct nlmsghdr *nlh, void *data);
-
-/* YNL specific helpers used by the auto-generated code */
-
-struct ynl_req_state {
-	struct ynl_parse_arg yarg;
-	mnl_cb_t cb;
-	__u32 rsp_cmd;
-};
-
-struct ynl_dump_state {
-	struct ynl_sock *ys;
-	struct ynl_policy_nest *rsp_policy;
-	void *first;
-	struct ynl_dump_list_type *last;
-	size_t alloc_sz;
-	mnl_cb_t cb;
-	__u32 rsp_cmd;
-};
-
-struct ynl_ntf_info {
-	struct ynl_policy_nest *policy;
-	mnl_cb_t cb;
-	size_t alloc_sz;
-	void (*free)(struct ynl_ntf_base_type *ntf);
-};
-
-int ynl_exec(struct ynl_sock *ys, struct nlmsghdr *req_nlh,
-	     struct ynl_req_state *yrs);
-int ynl_exec_dump(struct ynl_sock *ys, struct nlmsghdr *req_nlh,
-		  struct ynl_dump_state *yds);
-
-void ynl_error_unknown_notification(struct ynl_sock *ys, __u8 cmd);
-int ynl_error_parse(struct ynl_parse_arg *yarg, const char *msg);
-
-#ifndef MNL_HAS_AUTO_SCALARS
-static inline uint64_t mnl_attr_get_uint(const struct nlattr *attr)
-{
-	if (mnl_attr_get_len(attr) == 4)
-		return mnl_attr_get_u32(attr);
-	return mnl_attr_get_u64(attr);
-}
-
-static inline void
-mnl_attr_put_uint(struct nlmsghdr *nlh, uint16_t type, uint64_t data)
-{
-	if ((uint32_t)data == (uint64_t)data)
-		return mnl_attr_put_u32(nlh, type, data);
-	return mnl_attr_put_u64(nlh, type, data);
-}
-#endif
 #endif
diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py
index 92995bca14e1..1e10512b2117 100644
--- a/tools/net/ynl/lib/ynl.py
+++ b/tools/net/ynl/lib/ynl.py
@@ -98,12 +98,12 @@ class NlAttr:
     }
 
     def __init__(self, raw, offset):
-        self._len, self._type = struct.unpack("HH", raw[offset:offset + 4])
+        self._len, self._type = struct.unpack("HH", raw[offset : offset + 4])
         self.type = self._type & ~Netlink.NLA_TYPE_MASK
         self.is_nest = self._type & Netlink.NLA_F_NESTED
         self.payload_len = self._len
         self.full_len = (self.payload_len + 3) & ~3
-        self.raw = raw[offset + 4:offset + self.payload_len]
+        self.raw = raw[offset + 4 : offset + self.payload_len]
 
     @classmethod
     def get_format(cls, attr_type, byte_order=None):
@@ -154,7 +154,7 @@ class NlAttr:
         for m in members:
             # TODO: handle non-scalar members
             if m.type == 'binary':
-                decoded = self.raw[offset:offset+m['len']]
+                decoded = self.raw[offset : offset + m['len']]
                 offset += m['len']
             elif m.type in NlAttr.type_formats:
                 format = self.get_format(m.type, m.byte_order)
@@ -170,10 +170,9 @@ class NlAttr:
 
 
 class NlAttrs:
-    def __init__(self, msg):
+    def __init__(self, msg, offset=0):
         self.attrs = []
 
-        offset = 0
         while offset < len(msg):
             attr = NlAttr(msg, offset)
             offset += attr.full_len
@@ -193,12 +192,12 @@ class NlAttrs:
 
 class NlMsg:
     def __init__(self, msg, offset, attr_space=None):
-        self.hdr = msg[offset:offset + 16]
+        self.hdr = msg[offset : offset + 16]
 
         self.nl_len, self.nl_type, self.nl_flags, self.nl_seq, self.nl_portid = \
             struct.unpack("IHHII", self.hdr)
 
-        self.raw = msg[offset + 16:offset + self.nl_len]
+        self.raw = msg[offset + 16 : offset + self.nl_len]
 
         self.error = 0
         self.done = 0
@@ -371,8 +370,8 @@ class NetlinkProtocol:
         fixed_header_size = 0
         if ynl:
             op = ynl.rsp_by_value[msg.cmd()]
-            fixed_header_size = ynl._fixed_header_size(op)
-        msg.raw_attrs = NlAttrs(msg.raw[fixed_header_size:])
+            fixed_header_size = ynl._fixed_header_size(op.fixed_header)
+        msg.raw_attrs = NlAttrs(msg.raw, fixed_header_size)
         return msg
 
     def get_mcast_id(self, mcast_name, mcast_groups):
@@ -549,6 +548,37 @@ class YnlFamily(SpecFamily):
         else:
             rsp[name] = [decoded]
 
+    def _resolve_selector(self, attr_spec, vals):
+        sub_msg = attr_spec.sub_message
+        if sub_msg not in self.sub_msgs:
+            raise Exception(f"No sub-message spec named {sub_msg} for {attr_spec.name}")
+        sub_msg_spec = self.sub_msgs[sub_msg]
+
+        selector = attr_spec.selector
+        if selector not in vals:
+            raise Exception(f"There is no value for {selector} to resolve '{attr_spec.name}'")
+        value = vals[selector]
+        if value not in sub_msg_spec.formats:
+            raise Exception(f"No message format for '{value}' in sub-message spec '{sub_msg}'")
+
+        spec = sub_msg_spec.formats[value]
+        return spec
+
+    def _decode_sub_msg(self, attr, attr_spec, rsp):
+        msg_format = self._resolve_selector(attr_spec, rsp)
+        decoded = {}
+        offset = 0
+        if msg_format.fixed_header:
+            decoded.update(self._decode_fixed_header(attr, msg_format.fixed_header));
+            offset = self._fixed_header_size(msg_format.fixed_header)
+        if msg_format.attr_set:
+            if msg_format.attr_set in self.attr_sets:
+                subdict = self._decode(NlAttrs(attr.raw, offset), msg_format.attr_set)
+                decoded.update(subdict)
+            else:
+                raise Exception(f"Unknown attribute-set '{attr_space}' when decoding '{attr_spec.name}'")
+        return decoded
+
     def _decode(self, attrs, space):
         if space:
             attr_space = self.attr_sets[space]
@@ -586,6 +616,8 @@ class YnlFamily(SpecFamily):
                     value = self._decode_enum(value, attr_spec)
                     selector = self._decode_enum(selector, attr_spec)
                 decoded = {"value": value, "selector": selector}
+            elif attr_spec["type"] == 'sub-message':
+                decoded = self._decode_sub_msg(attr, attr_spec, rsp)
             else:
                 if not self.process_unknown:
                     raise Exception(f'Unknown {attr_spec["type"]} with name {attr_spec["name"]}')
@@ -626,20 +658,23 @@ class YnlFamily(SpecFamily):
             return
 
         msg = self.nlproto.decode(self, NlMsg(request, 0, op.attr_set))
-        offset = 20 + self._fixed_header_size(op)
+        offset = 20 + self._fixed_header_size(op.fixed_header)
         path = self._decode_extack_path(msg.raw_attrs, op.attr_set, offset,
                                         extack['bad-attr-offs'])
         if path:
             del extack['bad-attr-offs']
             extack['bad-attr'] = path
 
-    def _fixed_header_size(self, op):
-        if op.fixed_header:
-            fixed_header_members = self.consts[op.fixed_header].members
+    def _fixed_header_size(self, name):
+        if name:
+            fixed_header_members = self.consts[name].members
             size = 0
             for m in fixed_header_members:
-                format = NlAttr.get_format(m.type, m.byte_order)
-                size += format.size
+                if m.type in ['pad', 'binary']:
+                    size += m.len
+                else:
+                    format = NlAttr.get_format(m.type, m.byte_order)
+                    size += format.size
             return size
         else:
             return 0
@@ -649,12 +684,20 @@ class YnlFamily(SpecFamily):
         fixed_header_attrs = dict()
         offset = 0
         for m in fixed_header_members:
-            format = NlAttr.get_format(m.type, m.byte_order)
-            [ value ] = format.unpack_from(msg.raw, offset)
-            offset += format.size
-            if m.enum:
-                value = self._decode_enum(value, m)
-            fixed_header_attrs[m.name] = value
+            value = None
+            if m.type == 'pad':
+                offset += m.len
+            elif m.type == 'binary':
+                value = msg.raw[offset : offset + m.len]
+                offset += m.len
+            else:
+                format = NlAttr.get_format(m.type, m.byte_order)
+                [ value ] = format.unpack_from(msg.raw, offset)
+                offset += format.size
+            if value is not None:
+                if m.enum:
+                    value = self._decode_enum(value, m)
+                fixed_header_attrs[m.name] = value
         return fixed_header_attrs
 
     def handle_ntf(self, decoded):
@@ -705,7 +748,7 @@ class YnlFamily(SpecFamily):
 
       return op['do']['request']['attributes'].copy()
 
-    def _op(self, method, vals, flags, dump=False):
+    def _op(self, method, vals, flags=None, dump=False):
         op = self.ops[method]
 
         nl_flags = Netlink.NLM_F_REQUEST | Netlink.NLM_F_ACK
@@ -721,8 +764,13 @@ class YnlFamily(SpecFamily):
             fixed_header_members = self.consts[op.fixed_header].members
             for m in fixed_header_members:
                 value = vals.pop(m.name) if m.name in vals else 0
-                format = NlAttr.get_format(m.type, m.byte_order)
-                msg += format.pack(value)
+                if m.type == 'pad':
+                    msg += bytearray(m.len)
+                elif m.type == 'binary':
+                    msg += bytes.fromhex(value)
+                else:
+                    format = NlAttr.get_format(m.type, m.byte_order)
+                    msg += format.pack(value)
         for name, value in vals.items():
             msg += self._add_attr(op.attr_set.name, name, value)
         msg = _genl_msg_finalize(msg)
@@ -769,7 +817,7 @@ class YnlFamily(SpecFamily):
             return rsp[0]
         return rsp
 
-    def do(self, method, vals, flags):
+    def do(self, method, vals, flags=None):
         return self._op(method, vals, flags)
 
     def dump(self, method, vals):
diff --git a/tools/net/ynl/samples/.gitignore b/tools/net/ynl/samples/.gitignore
index 2aae60c4829f..49637b26c482 100644
--- a/tools/net/ynl/samples/.gitignore
+++ b/tools/net/ynl/samples/.gitignore
@@ -1,3 +1,4 @@
 ethtool
 devlink
 netdev
+page-pool
\ No newline at end of file
diff --git a/tools/net/ynl/samples/Makefile b/tools/net/ynl/samples/Makefile
index 3dbb106e87d9..28bdb1557a54 100644
--- a/tools/net/ynl/samples/Makefile
+++ b/tools/net/ynl/samples/Makefile
@@ -18,7 +18,9 @@ include $(wildcard *.d)
 
 all: $(BINS)
 
-$(BINS): ../lib/ynl.a ../generated/protos.a
+CFLAGS_page-pool=$(CFLAGS_netdev)
+
+$(BINS): ../lib/ynl.a ../generated/protos.a $(SRCS)
 	@echo -e '\tCC sample $@'
 	@$(COMPILE.c) $(CFLAGS_$@) $@.c -o $@.o
 	@$(LINK.c) $@.o -o $@  $(LDLIBS)
diff --git a/tools/net/ynl/samples/netdev.c b/tools/net/ynl/samples/netdev.c
index b828225daad0..591b90e21890 100644
--- a/tools/net/ynl/samples/netdev.c
+++ b/tools/net/ynl/samples/netdev.c
@@ -33,17 +33,23 @@ static void netdev_print_device(struct netdev_dev_get_rsp *d, unsigned int op)
 		return;
 
 	printf("xdp-features (%llx):", d->xdp_features);
-	for (int i = 0; d->xdp_features > 1U << i; i++) {
+	for (int i = 0; d->xdp_features >= 1U << i; i++) {
 		if (d->xdp_features & (1U << i))
 			printf(" %s", netdev_xdp_act_str(1 << i));
 	}
 
 	printf(" xdp-rx-metadata-features (%llx):", d->xdp_rx_metadata_features);
-	for (int i = 0; d->xdp_rx_metadata_features > 1U << i; i++) {
+	for (int i = 0; d->xdp_rx_metadata_features >= 1U << i; i++) {
 		if (d->xdp_rx_metadata_features & (1U << i))
 			printf(" %s", netdev_xdp_rx_metadata_str(1 << i));
 	}
 
+	printf(" xsk-features (%llx):", d->xsk_features);
+	for (int i = 0; d->xsk_features >= 1U << i; i++) {
+		if (d->xsk_features & (1U << i))
+			printf(" %s", netdev_xsk_flags_str(1 << i));
+	}
+
 	printf(" xdp-zc-max-segs=%u", d->xdp_zc_max_segs);
 
 	name = netdev_op_str(op);
diff --git a/tools/net/ynl/samples/page-pool.c b/tools/net/ynl/samples/page-pool.c
new file mode 100644
index 000000000000..098b5190d0e5
--- /dev/null
+++ b/tools/net/ynl/samples/page-pool.c
@@ -0,0 +1,147 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <string.h>
+
+#include <ynl.h>
+
+#include <net/if.h>
+
+#include "netdev-user.h"
+
+struct stat {
+	unsigned int ifc;
+
+	struct {
+		unsigned int cnt;
+		size_t refs, bytes;
+	} live[2];
+
+	size_t alloc_slow, alloc_fast, recycle_ring, recycle_cache;
+};
+
+struct stats_array {
+	unsigned int i, max;
+	struct stat *s;
+};
+
+static struct stat *find_ifc(struct stats_array *a, unsigned int ifindex)
+{
+	unsigned int i;
+
+	for (i = 0; i < a->i; i++) {
+		if (a->s[i].ifc == ifindex)
+			return &a->s[i];
+	}
+
+	a->i++;
+	if (a->i == a->max) {
+		a->max *= 2;
+		a->s = reallocarray(a->s, a->max, sizeof(*a->s));
+	}
+	a->s[i].ifc = ifindex;
+	return &a->s[i];
+}
+
+static void count(struct stat *s, unsigned int l,
+		  struct netdev_page_pool_get_rsp *pp)
+{
+	s->live[l].cnt++;
+	if (pp->_present.inflight)
+		s->live[l].refs += pp->inflight;
+	if (pp->_present.inflight_mem)
+		s->live[l].bytes += pp->inflight_mem;
+}
+
+int main(int argc, char **argv)
+{
+	struct netdev_page_pool_stats_get_list *pp_stats;
+	struct netdev_page_pool_get_list *pools;
+	struct stats_array a = {};
+	struct ynl_error yerr;
+	struct ynl_sock *ys;
+
+	ys = ynl_sock_create(&ynl_netdev_family, &yerr);
+	if (!ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return 1;
+	}
+
+	a.max = 128;
+	a.s = calloc(a.max, sizeof(*a.s));
+	if (!a.s)
+		goto err_close;
+
+	pools = netdev_page_pool_get_dump(ys);
+	if (!pools)
+		goto err_free;
+
+	ynl_dump_foreach(pools, pp) {
+		struct stat *s = find_ifc(&a, pp->ifindex);
+
+		count(s, 1, pp);
+		if (pp->_present.detach_time)
+			count(s, 0, pp);
+	}
+	netdev_page_pool_get_list_free(pools);
+
+	pp_stats = netdev_page_pool_stats_get_dump(ys);
+	if (!pp_stats)
+		goto err_free;
+
+	ynl_dump_foreach(pp_stats, pp) {
+		struct stat *s = find_ifc(&a, pp->info.ifindex);
+
+		if (pp->_present.alloc_fast)
+			s->alloc_fast += pp->alloc_fast;
+		if (pp->_present.alloc_slow)
+			s->alloc_slow += pp->alloc_slow;
+		if (pp->_present.recycle_ring)
+			s->recycle_ring += pp->recycle_ring;
+		if (pp->_present.recycle_cached)
+			s->recycle_cache += pp->recycle_cached;
+	}
+	netdev_page_pool_stats_get_list_free(pp_stats);
+
+	for (unsigned int i = 0; i < a.i; i++) {
+		char ifname[IF_NAMESIZE];
+		struct stat *s = &a.s[i];
+		const char *name;
+		double recycle;
+
+		if (!s->ifc) {
+			name = "<orphan>\t";
+		} else {
+			name = if_indextoname(s->ifc, ifname);
+			if (name)
+				printf("%8s", name);
+			printf("[%d]\t", s->ifc);
+		}
+
+		printf("page pools: %u (zombies: %u)\n",
+		       s->live[1].cnt, s->live[0].cnt);
+		printf("\t\trefs: %zu bytes: %zu (refs: %zu bytes: %zu)\n",
+		       s->live[1].refs, s->live[1].bytes,
+		       s->live[0].refs, s->live[0].bytes);
+
+		/* We don't know how many pages are sitting in cache and ring
+		 * so we will under-count the recycling rate a bit.
+		 */
+		recycle = (double)(s->recycle_ring + s->recycle_cache) /
+			(s->alloc_fast + s->alloc_slow) * 100;
+		printf("\t\trecycling: %.1lf%% (alloc: %zu:%zu recycle: %zu:%zu)\n",
+		       recycle, s->alloc_slow, s->alloc_fast,
+		       s->recycle_ring, s->recycle_cache);
+	}
+
+	ynl_sock_destroy(ys);
+	return 0;
+
+err_free:
+	free(a.s);
+err_close:
+	fprintf(stderr, "YNL: %s\n", ys->err.msg);
+	ynl_sock_destroy(ys);
+	return 2;
+}
diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index c4003a83cd5d..7fc1aa788f6f 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -67,9 +67,9 @@ class Type(SpecAttr):
         if 'nested-attributes' in attr:
             self.nested_attrs = attr['nested-attributes']
             if self.nested_attrs == family.name:
-                self.nested_render_name = f"{family.name}"
+                self.nested_render_name = c_lower(f"{family.name}")
             else:
-                self.nested_render_name = f"{family.name}_{c_lower(self.nested_attrs)}"
+                self.nested_render_name = c_lower(f"{family.name}_{self.nested_attrs}")
 
             if self.nested_attrs in self.family.consts:
                 self.nested_struct_type = 'struct ' + self.nested_render_name + '_'
@@ -105,6 +105,12 @@ class Type(SpecAttr):
     def is_scalar(self):
         return self.type in {'u8', 'u16', 'u32', 'u64', 's32', 's64'}
 
+    def is_recursive(self):
+        return False
+
+    def is_recursive_for_op(self, ri):
+        return self.is_recursive() and not ri.op
+
     def presence_type(self):
         return 'bit'
 
@@ -145,6 +151,8 @@ class Type(SpecAttr):
         member = self._complex_member_type(ri)
         if member:
             ptr = '*' if self.is_multi_val() else ''
+            if self.is_recursive_for_op(ri):
+                ptr = '*'
             ri.cw.p(f"{member} {ptr}{self.c_name};")
             return
         members = self.arg_member(ri)
@@ -264,6 +272,15 @@ class TypeUnused(Type):
     def attr_policy(self, cw):
         pass
 
+    def attr_put(self, ri, var):
+        pass
+
+    def attr_get(self, ri, var, first):
+        pass
+
+    def setter(self, ri, space, direction, deref=False, ref=None):
+        pass
+
 
 class TypePad(Type):
     def presence_type(self):
@@ -333,9 +350,8 @@ class TypeScalar(Type):
         else:
             self.is_bitfield = False
 
-        maybe_enum = not self.is_bitfield and 'enum' in self.attr
-        if maybe_enum and self.family.consts[self.attr['enum']].enum_name:
-            self.type_name = f"enum {self.family.name}_{c_lower(self.attr['enum'])}"
+        if not self.is_bitfield and 'enum' in self.attr:
+            self.type_name = self.family.consts[self.attr['enum']].user_type
         elif self.is_auto_scalar:
             self.type_name = '__' + self.type[0] + '64'
         else:
@@ -521,11 +537,18 @@ class TypeBitfield32(Type):
 
 
 class TypeNest(Type):
+    def is_recursive(self):
+        return self.family.pure_nested_structs[self.nested_attrs].recursive
+
     def _complex_member_type(self, ri):
         return self.nested_struct_type
 
     def free(self, ri, var, ref):
-        ri.cw.p(f'{self.nested_render_name}_free(&{var}->{ref}{self.c_name});')
+        at = '&'
+        if self.is_recursive_for_op(ri):
+            at = ''
+            ri.cw.p(f'if ({var}->{ref}{self.c_name})')
+        ri.cw.p(f'{self.nested_render_name}_free({at}{var}->{ref}{self.c_name});')
 
     def _attr_typol(self):
         return f'.type = YNL_PT_NEST, .nest = &{self.nested_render_name}_nest, '
@@ -534,8 +557,9 @@ class TypeNest(Type):
         return 'NLA_POLICY_NESTED(' + self.nested_render_name + '_nl_policy)'
 
     def attr_put(self, ri, var):
+        at = '' if self.is_recursive_for_op(ri) else '&'
         self._attr_put_line(ri, var, f"{self.nested_render_name}_put(nlh, " +
-                            f"{self.enum_name}, &{var}->{self.c_name})")
+                            f"{self.enum_name}, {at}{var}->{self.c_name})")
 
     def _attr_get(self, ri, var):
         get_lines = [f"if ({self.nested_render_name}_parse(&parg, attr))",
@@ -548,6 +572,8 @@ class TypeNest(Type):
         ref = (ref if ref else []) + [self.c_name]
 
         for _, attr in ri.family.pure_nested_structs[self.nested_attrs].member_list():
+            if attr.is_recursive():
+                continue
             attr.setter(ri, self.nested_attrs, direction, deref=deref, ref=ref)
 
 
@@ -685,16 +711,19 @@ class Struct:
 
         self.nested = type_list is None
         if family.name == c_lower(space_name):
-            self.render_name = f"{family.name}"
+            self.render_name = c_lower(family.name)
         else:
-            self.render_name = f"{family.name}_{c_lower(space_name)}"
+            self.render_name = c_lower(family.name + '-' + space_name)
         self.struct_name = 'struct ' + self.render_name
         if self.nested and space_name in family.consts:
             self.struct_name += '_'
         self.ptr_name = self.struct_name + ' *'
+        # All attr sets this one contains, directly or multiple levels down
+        self.child_nests = set()
 
         self.request = False
         self.reply = False
+        self.recursive = False
 
         self.attr_list = []
         self.attrs = dict()
@@ -755,11 +784,17 @@ class EnumSet(SpecEnumSet):
         if 'enum-name' in yaml:
             if yaml['enum-name']:
                 self.enum_name = 'enum ' + c_lower(yaml['enum-name'])
+                self.user_type = self.enum_name
             else:
                 self.enum_name = None
         else:
             self.enum_name = 'enum ' + self.render_name
 
+        if self.enum_name:
+            self.user_type = self.enum_name
+        else:
+            self.user_type = 'int'
+
         self.value_pfx = yaml.get('name-prefix', f"{family.name}-{yaml['name']}-")
 
         super().__init__(family, yaml)
@@ -841,7 +876,7 @@ class Operation(SpecOperation):
     def __init__(self, family, yaml, req_value, rsp_value):
         super().__init__(family, yaml, req_value, rsp_value)
 
-        self.render_name = family.name + '_' + c_lower(self.name)
+        self.render_name = c_lower(family.name + '_' + self.name)
 
         self.dual_policy = ('do' in yaml and 'request' in yaml['do']) and \
                          ('dump' in yaml and 'request' in yaml['dump'])
@@ -985,6 +1020,33 @@ class Family(SpecFamily):
                 self.root_sets[op['attribute-set']]['request'].update(req_attrs)
                 self.root_sets[op['attribute-set']]['reply'].update(rsp_attrs)
 
+    def _sort_pure_types(self):
+        # Try to reorder according to dependencies
+        pns_key_list = list(self.pure_nested_structs.keys())
+        pns_key_seen = set()
+        rounds = len(pns_key_list) ** 2  # it's basically bubble sort
+        for _ in range(rounds):
+            if len(pns_key_list) == 0:
+                break
+            name = pns_key_list.pop(0)
+            finished = True
+            for _, spec in self.attr_sets[name].items():
+                if 'nested-attributes' in spec:
+                    nested = spec['nested-attributes']
+                    # If the unknown nest we hit is recursive it's fine, it'll be a pointer
+                    if self.pure_nested_structs[nested].recursive:
+                        continue
+                    if nested not in pns_key_seen:
+                        # Dicts are sorted, this will make struct last
+                        struct = self.pure_nested_structs.pop(name)
+                        self.pure_nested_structs[name] = struct
+                        finished = False
+                        break
+            if finished:
+                pns_key_seen.add(name)
+            else:
+                pns_key_list.append(name)
+
     def _load_nested_sets(self):
         attr_set_queue = list(self.root_sets.keys())
         attr_set_seen = set(self.root_sets.keys())
@@ -1024,35 +1086,24 @@ class Family(SpecFamily):
                     if attr in rs_members['reply']:
                         self.pure_nested_structs[nested].reply = True
 
-        # Try to reorder according to dependencies
-        pns_key_list = list(self.pure_nested_structs.keys())
-        pns_key_seen = set()
-        rounds = len(pns_key_list)**2  # it's basically bubble sort
-        for _ in range(rounds):
-            if len(pns_key_list) == 0:
-                break
-            name = pns_key_list.pop(0)
-            finished = True
-            for _, spec in self.attr_sets[name].items():
-                if 'nested-attributes' in spec:
-                    if spec['nested-attributes'] not in pns_key_seen:
-                        # Dicts are sorted, this will make struct last
-                        struct = self.pure_nested_structs.pop(name)
-                        self.pure_nested_structs[name] = struct
-                        finished = False
-                        break
-            if finished:
-                pns_key_seen.add(name)
-            else:
-                pns_key_list.append(name)
-        # Propagate the request / reply
+        self._sort_pure_types()
+
+        # Propagate the request / reply / recursive
         for attr_set, struct in reversed(self.pure_nested_structs.items()):
             for _, spec in self.attr_sets[attr_set].items():
                 if 'nested-attributes' in spec:
-                    child = self.pure_nested_structs.get(spec['nested-attributes'])
+                    child_name = spec['nested-attributes']
+                    struct.child_nests.add(child_name)
+                    child = self.pure_nested_structs.get(child_name)
                     if child:
+                        if not child.recursive:
+                            struct.child_nests.update(child.child_nests)
                         child.request |= struct.request
                         child.reply |= struct.reply
+                if attr_set in struct.child_nests:
+                    struct.recursive = True
+
+        self._sort_pure_types()
 
     def _load_attr_use(self):
         for _, struct in self.pure_nested_structs.items():
@@ -1119,6 +1170,10 @@ class RenderInfo:
         self.op_mode = op_mode
         self.op = op
 
+        self.fixed_hdr = None
+        if op and op.fixed_header:
+            self.fixed_hdr = 'struct ' + c_lower(op.fixed_header)
+
         # 'do' and 'dump' response parsing is identical
         self.type_consistent = True
         if op_mode != 'do' and 'dump' in op:
@@ -1158,8 +1213,9 @@ class RenderInfo:
 
 
 class CodeWriter:
-    def __init__(self, nlib, out_file=None):
+    def __init__(self, nlib, out_file=None, overwrite=True):
         self.nlib = nlib
+        self._overwrite = overwrite
 
         self._nl = False
         self._block_end = False
@@ -1180,8 +1236,9 @@ class CodeWriter:
             return
         # Avoid modifying the file if contents didn't change
         self._out.flush()
-        if os.path.isfile(self._out_file) and filecmp.cmp(self._out.name, self._out_file, shallow=False):
-            return
+        if not self._overwrite and os.path.isfile(self._out_file):
+            if filecmp.cmp(self._out.name, self._out_file, shallow=False):
+                return
         with open(self._out_file, 'w+') as out_file:
             self._out.seek(0)
             shutil.copyfileobj(self._out, out_file)
@@ -1431,7 +1488,7 @@ def op_prefix(ri, direction, deref=False):
                 suffix += '_rsp'
                 suffix += '_dump' if deref else '_list'
 
-    return f"{ri.family['name']}{suffix}"
+    return f"{ri.family.c_name}{suffix}"
 
 
 def type_name(ri, direction, deref=False):
@@ -1464,6 +1521,10 @@ def print_dump_prototype(ri):
     print_prototype(ri, "request")
 
 
+def put_typol_fwd(cw, struct):
+    cw.p(f'extern struct ynl_policy_nest {struct.render_name}_nest;')
+
+
 def put_typol(cw, struct):
     type_max = struct.attr_set.max_name
     cw.block_start(line=f'struct ynl_policy_attr {struct.render_name}_policy[{type_max} + 1] =')
@@ -1483,8 +1544,8 @@ def put_typol(cw, struct):
 
 def _put_enum_to_str_helper(cw, render_name, map_name, arg_name, enum=None):
     args = [f'int {arg_name}']
-    if enum and not ('enum-name' in enum and not enum['enum-name']):
-        args = [f'enum {render_name} {arg_name}']
+    if enum:
+        args = [enum.user_type + ' ' + arg_name]
     cw.write_func_prot('const char *', f'{render_name}_str', args)
     cw.block_start()
     if enum and enum.type == 'flags':
@@ -1497,14 +1558,20 @@ def _put_enum_to_str_helper(cw, render_name, map_name, arg_name, enum=None):
 
 
 def put_op_name_fwd(family, cw):
-    cw.write_func_prot('const char *', f'{family.name}_op_str', ['int op'], suffix=';')
+    cw.write_func_prot('const char *', f'{family.c_name}_op_str', ['int op'], suffix=';')
 
 
 def put_op_name(family, cw):
-    map_name = f'{family.name}_op_strmap'
+    map_name = f'{family.c_name}_op_strmap'
     cw.block_start(line=f"static const char * const {map_name}[] =")
     for op_name, op in family.msgs.items():
         if op.rsp_value:
+            # Make sure we don't add duplicated entries, if multiple commands
+            # produce the same response in legacy families.
+            if family.rsp_by_value[op.rsp_value] != op:
+                cw.p(f'// skip "{op_name}", duplicate reply value')
+                continue
+
             if op.req_value == op.rsp_value:
                 cw.p(f'[{op.enum_name}] = "{op_name}",')
             else:
@@ -1512,13 +1579,11 @@ def put_op_name(family, cw):
     cw.block_end(line=';')
     cw.nl()
 
-    _put_enum_to_str_helper(cw, family.name + '_op', map_name, 'op')
+    _put_enum_to_str_helper(cw, family.c_name + '_op', map_name, 'op')
 
 
 def put_enum_to_str_fwd(family, cw, enum):
-    args = [f'enum {enum.render_name} value']
-    if 'enum-name' in enum and not enum['enum-name']:
-        args = ['int value']
+    args = [enum.user_type + ' value']
     cw.write_func_prot('const char *', f'{enum.render_name}_str', args, suffix=';')
 
 
@@ -1533,12 +1598,17 @@ def put_enum_to_str(family, cw, enum):
     _put_enum_to_str_helper(cw, enum.render_name, map_name, 'value', enum=enum)
 
 
-def put_req_nested(ri, struct):
+def put_req_nested_prototype(ri, struct, suffix=';'):
     func_args = ['struct nlmsghdr *nlh',
                  'unsigned int attr_type',
                  f'{struct.ptr_name}obj']
 
-    ri.cw.write_func_prot('int', f'{struct.render_name}_put', func_args)
+    ri.cw.write_func_prot('int', f'{struct.render_name}_put', func_args,
+                          suffix=suffix)
+
+
+def put_req_nested(ri, struct):
+    put_req_nested_prototype(ri, struct, suffix='')
     ri.cw.block_start()
     ri.cw.write_func_lvar('struct nlattr *nest;')
 
@@ -1559,7 +1629,9 @@ def _multi_parse(ri, struct, init_lines, local_vars):
     if struct.nested:
         iter_line = "mnl_attr_for_each_nested(attr, nested)"
     else:
-        iter_line = "mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr))"
+        if ri.fixed_hdr:
+            local_vars += ['void *hdr;']
+        iter_line = "mnl_attr_for_each(attr, nlh, yarg->ys->family->hdr_len)"
 
     array_nests = set()
     multi_attrs = set()
@@ -1592,6 +1664,9 @@ def _multi_parse(ri, struct, init_lines, local_vars):
     for arg in struct.inherited:
         ri.cw.p(f'dst->{arg} = {arg};')
 
+    if ri.fixed_hdr:
+        ri.cw.p('hdr = mnl_nlmsg_get_payload_offset(nlh, sizeof(struct genlmsghdr));')
+        ri.cw.p(f"memcpy(&dst->_hdr, hdr, sizeof({ri.fixed_hdr}));")
     for anest in sorted(all_multi):
         aspec = struct[anest]
         ri.cw.p(f"if (dst->{aspec.c_name})")
@@ -1660,18 +1735,23 @@ def _multi_parse(ri, struct, init_lines, local_vars):
     ri.cw.nl()
 
 
-def parse_rsp_nested(ri, struct):
+def parse_rsp_nested_prototype(ri, struct, suffix=';'):
     func_args = ['struct ynl_parse_arg *yarg',
                  'const struct nlattr *nested']
     for arg in struct.inherited:
         func_args.append('__u32 ' + arg)
 
+    ri.cw.write_func_prot('int', f'{struct.render_name}_parse', func_args,
+                          suffix=suffix)
+
+
+def parse_rsp_nested(ri, struct):
+    parse_rsp_nested_prototype(ri, struct, suffix='')
+
     local_vars = ['const struct nlattr *attr;',
                   f'{struct.ptr_name}dst = yarg->data;']
     init_lines = []
 
-    ri.cw.write_func_prot('int', f'{struct.render_name}_parse', func_args)
-
     _multi_parse(ri, struct, init_lines, local_vars)
 
 
@@ -1703,14 +1783,18 @@ def print_req(ri):
     ret_ok = '0'
     ret_err = '-1'
     direction = "request"
-    local_vars = ['struct nlmsghdr *nlh;',
+    local_vars = ['struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };',
+                  'struct nlmsghdr *nlh;',
                   'int err;']
 
     if 'reply' in ri.op[ri.op_mode]:
         ret_ok = 'rsp'
         ret_err = 'NULL'
-        local_vars += [f'{type_name(ri, rdir(direction))} *rsp;',
-                       'struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };']
+        local_vars += [f'{type_name(ri, rdir(direction))} *rsp;']
+
+    if ri.fixed_hdr:
+        local_vars += ['size_t hdr_len;',
+                       'void *hdr;']
 
     print_prototype(ri, direction, terminate=False)
     ri.cw.block_start()
@@ -1722,11 +1806,17 @@ def print_req(ri):
     if 'reply' in ri.op[ri.op_mode]:
         ri.cw.p(f"yrs.yarg.rsp_policy = &{ri.struct['reply'].render_name}_nest;")
     ri.cw.nl()
+
+    if ri.fixed_hdr:
+        ri.cw.p("hdr_len = sizeof(req->_hdr);")
+        ri.cw.p("hdr = mnl_nlmsg_put_extra_header(nlh, hdr_len);")
+        ri.cw.p("memcpy(hdr, &req->_hdr, hdr_len);")
+        ri.cw.nl()
+
     for _, attr in ri.struct["request"].member_list():
         attr.attr_put(ri, "req")
     ri.cw.nl()
 
-    parse_arg = "NULL"
     if 'reply' in ri.op[ri.op_mode]:
         ri.cw.p('rsp = calloc(1, sizeof(*rsp));')
         ri.cw.p('yrs.yarg.data = rsp;')
@@ -1736,8 +1826,7 @@ def print_req(ri):
         else:
             ri.cw.p(f'yrs.rsp_cmd = {ri.op.rsp_value};')
         ri.cw.nl()
-        parse_arg = '&yrs'
-    ri.cw.p(f"err = ynl_exec(ys, nlh, {parse_arg});")
+    ri.cw.p("err = ynl_exec(ys, nlh, &yrs);")
     ri.cw.p('if (err < 0)')
     if 'reply' in ri.op[ri.op_mode]:
         ri.cw.p('goto err_free;')
@@ -1764,9 +1853,11 @@ def print_dump(ri):
                   'struct nlmsghdr *nlh;',
                   'int err;']
 
-    for var in local_vars:
-        ri.cw.p(f'{var}')
-    ri.cw.nl()
+    if ri.fixed_hdr:
+        local_vars += ['size_t hdr_len;',
+                       'void *hdr;']
+
+    ri.cw.write_func_lvar(local_vars)
 
     ri.cw.p('yds.ys = ys;')
     ri.cw.p(f"yds.alloc_sz = sizeof({type_name(ri, rdir(direction))});")
@@ -1779,6 +1870,12 @@ def print_dump(ri):
     ri.cw.nl()
     ri.cw.p(f"nlh = ynl_gemsg_start_dump(ys, {ri.nl.get_family_id()}, {ri.op.enum_name}, 1);")
 
+    if ri.fixed_hdr:
+        ri.cw.p("hdr_len = sizeof(req->_hdr);")
+        ri.cw.p("hdr = mnl_nlmsg_put_extra_header(nlh, hdr_len);")
+        ri.cw.p("memcpy(hdr, &req->_hdr, hdr_len);")
+        ri.cw.nl()
+
     if "request" in ri.op[ri.op_mode]:
         ri.cw.p(f"ys->req_policy = &{ri.struct['request'].render_name}_nest;")
         ri.cw.nl()
@@ -1834,7 +1931,11 @@ def _print_type(ri, direction, struct):
     if ri.op_mode == 'dump':
         suffix += '_dump'
 
-    ri.cw.block_start(line=f"struct {ri.family['name']}{suffix}")
+    ri.cw.block_start(line=f"struct {ri.family.c_name}{suffix}")
+
+    if ri.fixed_hdr:
+        ri.cw.p(ri.fixed_hdr + ' _hdr;')
+        ri.cw.nl()
 
     meta_started = False
     for _, attr in struct.member_list():
@@ -1964,6 +2065,10 @@ def _free_type(ri, direction, struct):
     ri.cw.nl()
 
 
+def free_rsp_nested_prototype(ri):
+        print_free_prototype(ri, "")
+
+
 def free_rsp_nested(ri, struct):
     _free_type(ri, "", struct)
 
@@ -2064,12 +2169,13 @@ def print_kernel_policy_ranges(family, cw):
                 first = False
 
             sign = '' if attr.type[0] == 'u' else '_signed'
+            suffix = 'ULL' if attr.type[0] == 'u' else 'LL'
             cw.block_start(line=f'static const struct netlink_range_validation{sign} {c_lower(attr.enum_name)}_range =')
             members = []
             if 'min' in attr.checks:
-                members.append(('min', attr.get_limit('min')))
+                members.append(('min', str(attr.get_limit('min')) + suffix))
             if 'max' in attr.checks:
-                members.append(('max', attr.get_limit('max')))
+                members.append(('max', str(attr.get_limit('max')) + suffix))
             cw.write_struct_init(members)
             cw.block_end(line=';')
             cw.nl()
@@ -2099,7 +2205,7 @@ def print_kernel_op_table_fwd(family, cw, terminate):
             cnt = len(family.ops)
 
         qual = 'static const' if not exported else 'const'
-        line = f"{qual} struct {struct_type} {family.name}_nl_ops[{cnt}]"
+        line = f"{qual} struct {struct_type} {family.c_name}_nl_ops[{cnt}]"
         if terminate:
             cw.p(f"extern {line};")
         else:
@@ -2242,7 +2348,7 @@ def print_kernel_mcgrp_src(family, cw):
     if not family.mcgrps['list']:
         return
 
-    cw.block_start('static const struct genl_multicast_group ' + family.name + '_nl_mcgrps[] =')
+    cw.block_start('static const struct genl_multicast_group ' + family.c_name + '_nl_mcgrps[] =')
     for grp in family.mcgrps['list']:
         name = grp['name']
         grp_id = c_upper(f"{family.name}-nlgrp-{name}")
@@ -2255,7 +2361,7 @@ def print_kernel_family_struct_hdr(family, cw):
     if not kernel_can_gen_family_struct(family):
         return
 
-    cw.p(f"extern struct genl_family {family.name}_nl_family;")
+    cw.p(f"extern struct genl_family {family.c_name}_nl_family;")
     cw.nl()
 
 
@@ -2270,14 +2376,14 @@ def print_kernel_family_struct_src(family, cw):
     cw.p('.parallel_ops\t= true,')
     cw.p('.module\t\t= THIS_MODULE,')
     if family.kernel_policy == 'per-op':
-        cw.p(f'.ops\t\t= {family.name}_nl_ops,')
-        cw.p(f'.n_ops\t\t= ARRAY_SIZE({family.name}_nl_ops),')
+        cw.p(f'.ops\t\t= {family.c_name}_nl_ops,')
+        cw.p(f'.n_ops\t\t= ARRAY_SIZE({family.c_name}_nl_ops),')
     elif family.kernel_policy == 'split':
-        cw.p(f'.split_ops\t= {family.name}_nl_ops,')
-        cw.p(f'.n_split_ops\t= ARRAY_SIZE({family.name}_nl_ops),')
+        cw.p(f'.split_ops\t= {family.c_name}_nl_ops,')
+        cw.p(f'.n_split_ops\t= ARRAY_SIZE({family.c_name}_nl_ops),')
     if family.mcgrps['list']:
-        cw.p(f'.mcgrps\t\t= {family.name}_nl_mcgrps,')
-        cw.p(f'.n_mcgrps\t= ARRAY_SIZE({family.name}_nl_mcgrps),')
+        cw.p(f'.mcgrps\t\t= {family.c_name}_nl_mcgrps,')
+        cw.p(f'.n_mcgrps\t= ARRAY_SIZE({family.c_name}_nl_mcgrps),')
     cw.block_end(';')
 
 
@@ -2287,7 +2393,7 @@ def uapi_enum_start(family, cw, obj, ckey='', enum_name='enum-name'):
         if obj[enum_name]:
             start_line = 'enum ' + c_lower(obj[enum_name])
     elif ckey and ckey in obj:
-        start_line = 'enum ' + family.name + '_' + c_lower(obj[ckey])
+        start_line = 'enum ' + family.c_name + '_' + c_lower(obj[ckey])
     cw.block_start(line=start_line)
 
 
@@ -2471,7 +2577,11 @@ def render_user_family(family, cw, prototype):
         cw.nl()
 
     cw.block_start(f'{symbol} = ')
-    cw.p(f'.name\t\t= "{family.name}",')
+    cw.p(f'.name\t\t= "{family.c_name}",')
+    if family.fixed_header:
+        cw.p(f'.hdr_len\t= sizeof(struct genlmsghdr) + sizeof(struct {c_lower(family.fixed_header)}),')
+    else:
+        cw.p('.hdr_len\t= sizeof(struct genlmsghdr),')
     if family.ntfs:
         cw.p(f".ntf_info\t= {family['name']}_ntf_info,")
         cw.p(f".ntf_info_size\t= MNL_ARRAY_SIZE({family['name']}_ntf_info),")
@@ -2505,6 +2615,8 @@ def main():
     parser.add_argument('--header', dest='header', action='store_true', default=None)
     parser.add_argument('--source', dest='header', action='store_false')
     parser.add_argument('--user-header', nargs='+', default=[])
+    parser.add_argument('--cmp-out', action='store_true', default=None,
+                        help='Do not overwrite the output file if the new output is identical to the old')
     parser.add_argument('--exclude-op', action='append', default=[])
     parser.add_argument('-o', dest='out_file', type=str, default=None)
     args = parser.parse_args()
@@ -2532,7 +2644,7 @@ def main():
         print(f'Message enum-model {parsed.msg_id_model} not supported for {args.mode} generation')
         os.sys.exit(1)
 
-    cw = CodeWriter(BaseNlLib(), args.out_file)
+    cw = CodeWriter(BaseNlLib(), args.out_file, overwrite=(not args.cmp_out))
 
     _, spec_kernel = find_kernel_root(args.spec)
     if args.mode == 'uapi' or args.header:
@@ -2553,7 +2665,7 @@ def main():
         render_uapi(parsed, cw)
         return
 
-    hdr_prot = f"_LINUX_{parsed.name.upper()}_GEN_H"
+    hdr_prot = f"_LINUX_{parsed.c_name.upper()}_GEN_H"
     if args.header:
         cw.p('#ifndef ' + hdr_prot)
         cw.p('#define ' + hdr_prot)
@@ -2724,7 +2836,14 @@ def main():
                     put_enum_to_str(parsed, cw, const)
             cw.nl()
 
+            has_recursive_nests = False
             cw.p('/* Policies */')
+            for struct in parsed.pure_nested_structs.values():
+                if struct.recursive:
+                    put_typol_fwd(cw, struct)
+                    has_recursive_nests = True
+            if has_recursive_nests:
+                cw.nl()
             for name in parsed.pure_nested_structs:
                 struct = Struct(parsed, name)
                 put_typol(cw, struct)
@@ -2733,6 +2852,15 @@ def main():
                 put_typol(cw, struct)
 
             cw.p('/* Common nested types */')
+            if has_recursive_nests:
+                for attr_set, struct in parsed.pure_nested_structs.items():
+                    ri = RenderInfo(cw, parsed, args.mode, "", "", attr_set)
+                    free_rsp_nested_prototype(ri)
+                    if struct.request:
+                        put_req_nested_prototype(ri, struct)
+                    if struct.reply:
+                        parse_rsp_nested_prototype(ri, struct)
+                cw.nl()
             for attr_set, struct in parsed.pure_nested_structs.items():
                 ri = RenderInfo(cw, parsed, args.mode, "", "", attr_set)
 
@@ -2758,6 +2886,7 @@ def main():
                     ri = RenderInfo(cw, parsed, args.mode, op, "dump")
                     if not ri.type_consistent:
                         parse_rsp_msg(ri, deref=True)
+                    print_req_free(ri)
                     print_dump_type_free(ri)
                     print_dump(ri)
                     cw.nl()
diff --git a/tools/net/ynl/ynl-gen-rst.py b/tools/net/ynl/ynl-gen-rst.py
new file mode 100755
index 000000000000..262d88f88696
--- /dev/null
+++ b/tools/net/ynl/ynl-gen-rst.py
@@ -0,0 +1,417 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+# -*- coding: utf-8; mode: python -*-
+
+"""
+    Script to auto generate the documentation for Netlink specifications.
+
+    :copyright:  Copyright (C) 2023  Breno Leitao <leitao@debian.org>
+    :license:    GPL Version 2, June 1991 see linux/COPYING for details.
+
+    This script performs extensive parsing to the Linux kernel's netlink YAML
+    spec files, in an effort to avoid needing to heavily mark up the original
+    YAML file.
+
+    This code is split in three big parts:
+        1) RST formatters: Use to convert a string to a RST output
+        2) Parser helpers: Functions to parse the YAML data structure
+        3) Main function and small helpers
+"""
+
+from typing import Any, Dict, List
+import os.path
+import sys
+import argparse
+import logging
+import yaml
+
+
+SPACE_PER_LEVEL = 4
+
+
+# RST Formatters
+# ==============
+def headroom(level: int) -> str:
+    """Return space to format"""
+    return " " * (level * SPACE_PER_LEVEL)
+
+
+def bold(text: str) -> str:
+    """Format bold text"""
+    return f"**{text}**"
+
+
+def inline(text: str) -> str:
+    """Format inline text"""
+    return f"``{text}``"
+
+
+def sanitize(text: str) -> str:
+    """Remove newlines and multiple spaces"""
+    # This is useful for some fields that are spread across multiple lines
+    return str(text).replace("\n", "").strip()
+
+
+def rst_fields(key: str, value: str, level: int = 0) -> str:
+    """Return a RST formatted field"""
+    return headroom(level) + f":{key}: {value}"
+
+
+def rst_definition(key: str, value: Any, level: int = 0) -> str:
+    """Format a single rst definition"""
+    return headroom(level) + key + "\n" + headroom(level + 1) + str(value)
+
+
+def rst_paragraph(paragraph: str, level: int = 0) -> str:
+    """Return a formatted paragraph"""
+    return headroom(level) + paragraph
+
+
+def rst_bullet(item: str, level: int = 0) -> str:
+    """Return a formatted a bullet"""
+    return headroom(level) + f"- {item}"
+
+
+def rst_subsection(title: str) -> str:
+    """Add a sub-section to the document"""
+    return f"{title}\n" + "-" * len(title)
+
+
+def rst_subsubsection(title: str) -> str:
+    """Add a sub-sub-section to the document"""
+    return f"{title}\n" + "~" * len(title)
+
+
+def rst_section(title: str) -> str:
+    """Add a section to the document"""
+    return f"\n{title}\n" + "=" * len(title)
+
+
+def rst_subtitle(title: str) -> str:
+    """Add a subtitle to the document"""
+    return "\n" + "-" * len(title) + f"\n{title}\n" + "-" * len(title) + "\n\n"
+
+
+def rst_title(title: str) -> str:
+    """Add a title to the document"""
+    return "=" * len(title) + f"\n{title}\n" + "=" * len(title) + "\n\n"
+
+
+def rst_list_inline(list_: List[str], level: int = 0) -> str:
+    """Format a list using inlines"""
+    return headroom(level) + "[" + ", ".join(inline(i) for i in list_) + "]"
+
+
+def rst_header() -> str:
+    """The headers for all the auto generated RST files"""
+    lines = []
+
+    lines.append(rst_paragraph(".. SPDX-License-Identifier: GPL-2.0"))
+    lines.append(rst_paragraph(".. NOTE: This document was auto-generated.\n\n"))
+
+    return "\n".join(lines)
+
+
+def rst_toctree(maxdepth: int = 2) -> str:
+    """Generate a toctree RST primitive"""
+    lines = []
+
+    lines.append(".. toctree::")
+    lines.append(f"   :maxdepth: {maxdepth}\n\n")
+
+    return "\n".join(lines)
+
+
+def rst_label(title: str) -> str:
+    """Return a formatted label"""
+    return f".. _{title}:\n\n"
+
+
+# Parsers
+# =======
+
+
+def parse_mcast_group(mcast_group: List[Dict[str, Any]]) -> str:
+    """Parse 'multicast' group list and return a formatted string"""
+    lines = []
+    for group in mcast_group:
+        lines.append(rst_bullet(group["name"]))
+
+    return "\n".join(lines)
+
+
+def parse_do(do_dict: Dict[str, Any], level: int = 0) -> str:
+    """Parse 'do' section and return a formatted string"""
+    lines = []
+    for key in do_dict.keys():
+        lines.append(rst_paragraph(bold(key), level + 1))
+        lines.append(parse_do_attributes(do_dict[key], level + 1) + "\n")
+
+    return "\n".join(lines)
+
+
+def parse_do_attributes(attrs: Dict[str, Any], level: int = 0) -> str:
+    """Parse 'attributes' section"""
+    if "attributes" not in attrs:
+        return ""
+    lines = [rst_fields("attributes", rst_list_inline(attrs["attributes"]), level + 1)]
+
+    return "\n".join(lines)
+
+
+def parse_operations(operations: List[Dict[str, Any]]) -> str:
+    """Parse operations block"""
+    preprocessed = ["name", "doc", "title", "do", "dump"]
+    lines = []
+
+    for operation in operations:
+        lines.append(rst_section(operation["name"]))
+        lines.append(rst_paragraph(sanitize(operation["doc"])) + "\n")
+
+        for key in operation.keys():
+            if key in preprocessed:
+                # Skip the special fields
+                continue
+            lines.append(rst_fields(key, operation[key], 0))
+
+        if "do" in operation:
+            lines.append(rst_paragraph(":do:", 0))
+            lines.append(parse_do(operation["do"], 0))
+        if "dump" in operation:
+            lines.append(rst_paragraph(":dump:", 0))
+            lines.append(parse_do(operation["dump"], 0))
+
+        # New line after fields
+        lines.append("\n")
+
+    return "\n".join(lines)
+
+
+def parse_entries(entries: List[Dict[str, Any]], level: int) -> str:
+    """Parse a list of entries"""
+    lines = []
+    for entry in entries:
+        if isinstance(entry, dict):
+            # entries could be a list or a dictionary
+            lines.append(
+                rst_fields(entry.get("name", ""), sanitize(entry.get("doc", "")), level)
+            )
+        elif isinstance(entry, list):
+            lines.append(rst_list_inline(entry, level))
+        else:
+            lines.append(rst_bullet(inline(sanitize(entry)), level))
+
+    lines.append("\n")
+    return "\n".join(lines)
+
+
+def parse_definitions(defs: Dict[str, Any]) -> str:
+    """Parse definitions section"""
+    preprocessed = ["name", "entries", "members"]
+    ignored = ["render-max"]  # This is not printed
+    lines = []
+
+    for definition in defs:
+        lines.append(rst_section(definition["name"]))
+        for k in definition.keys():
+            if k in preprocessed + ignored:
+                continue
+            lines.append(rst_fields(k, sanitize(definition[k]), 0))
+
+        # Field list needs to finish with a new line
+        lines.append("\n")
+        if "entries" in definition:
+            lines.append(rst_paragraph(":entries:", 0))
+            lines.append(parse_entries(definition["entries"], 1))
+        if "members" in definition:
+            lines.append(rst_paragraph(":members:", 0))
+            lines.append(parse_entries(definition["members"], 1))
+
+    return "\n".join(lines)
+
+
+def parse_attr_sets(entries: List[Dict[str, Any]]) -> str:
+    """Parse attribute from attribute-set"""
+    preprocessed = ["name", "type"]
+    ignored = ["checks"]
+    lines = []
+
+    for entry in entries:
+        lines.append(rst_section(entry["name"]))
+        for attr in entry["attributes"]:
+            type_ = attr.get("type")
+            attr_line = attr["name"]
+            if type_:
+                # Add the attribute type in the same line
+                attr_line += f" ({inline(type_)})"
+
+            lines.append(rst_subsubsection(attr_line))
+
+            for k in attr.keys():
+                if k in preprocessed + ignored:
+                    continue
+                lines.append(rst_fields(k, sanitize(attr[k]), 0))
+            lines.append("\n")
+
+    return "\n".join(lines)
+
+
+def parse_sub_messages(entries: List[Dict[str, Any]]) -> str:
+    """Parse sub-message definitions"""
+    lines = []
+
+    for entry in entries:
+        lines.append(rst_section(entry["name"]))
+        for fmt in entry["formats"]:
+            value = fmt["value"]
+
+            lines.append(rst_bullet(bold(value)))
+            for attr in ['fixed-header', 'attribute-set']:
+                if attr in fmt:
+                    lines.append(rst_fields(attr, fmt[attr], 1))
+            lines.append("\n")
+
+    return "\n".join(lines)
+
+
+def parse_yaml(obj: Dict[str, Any]) -> str:
+    """Format the whole YAML into a RST string"""
+    lines = []
+
+    # Main header
+
+    lines.append(rst_header())
+
+    title = f"Family ``{obj['name']}`` netlink specification"
+    lines.append(rst_title(title))
+    lines.append(rst_paragraph(".. contents::\n"))
+
+    if "doc" in obj:
+        lines.append(rst_subtitle("Summary"))
+        lines.append(rst_paragraph(obj["doc"], 0))
+
+    # Operations
+    if "operations" in obj:
+        lines.append(rst_subtitle("Operations"))
+        lines.append(parse_operations(obj["operations"]["list"]))
+
+    # Multicast groups
+    if "mcast-groups" in obj:
+        lines.append(rst_subtitle("Multicast groups"))
+        lines.append(parse_mcast_group(obj["mcast-groups"]["list"]))
+
+    # Definitions
+    if "definitions" in obj:
+        lines.append(rst_subtitle("Definitions"))
+        lines.append(parse_definitions(obj["definitions"]))
+
+    # Attributes set
+    if "attribute-sets" in obj:
+        lines.append(rst_subtitle("Attribute sets"))
+        lines.append(parse_attr_sets(obj["attribute-sets"]))
+
+    # Sub-messages
+    if "sub-messages" in obj:
+        lines.append(rst_subtitle("Sub-messages"))
+        lines.append(parse_sub_messages(obj["sub-messages"]))
+
+    return "\n".join(lines)
+
+
+# Main functions
+# ==============
+
+
+def parse_arguments() -> argparse.Namespace:
+    """Parse arguments from user"""
+    parser = argparse.ArgumentParser(description="Netlink RST generator")
+
+    parser.add_argument("-v", "--verbose", action="store_true")
+    parser.add_argument("-o", "--output", help="Output file name")
+
+    # Index and input are mutually exclusive
+    group = parser.add_mutually_exclusive_group()
+    group.add_argument(
+        "-x", "--index", action="store_true", help="Generate the index page"
+    )
+    group.add_argument("-i", "--input", help="YAML file name")
+
+    args = parser.parse_args()
+
+    if args.verbose:
+        logging.basicConfig(level=logging.DEBUG)
+
+    if args.input and not os.path.isfile(args.input):
+        logging.warning("%s is not a valid file.", args.input)
+        sys.exit(-1)
+
+    if not args.output:
+        logging.error("No output file specified.")
+        sys.exit(-1)
+
+    if os.path.isfile(args.output):
+        logging.debug("%s already exists. Overwriting it.", args.output)
+
+    return args
+
+
+def parse_yaml_file(filename: str) -> str:
+    """Transform the YAML specified by filename into a rst-formmated string"""
+    with open(filename, "r", encoding="utf-8") as spec_file:
+        yaml_data = yaml.safe_load(spec_file)
+        content = parse_yaml(yaml_data)
+
+    return content
+
+
+def write_to_rstfile(content: str, filename: str) -> None:
+    """Write the generated content into an RST file"""
+    logging.debug("Saving RST file to %s", filename)
+
+    with open(filename, "w", encoding="utf-8") as rst_file:
+        rst_file.write(content)
+
+
+def generate_main_index_rst(output: str) -> None:
+    """Generate the `networking_spec/index` content and write to the file"""
+    lines = []
+
+    lines.append(rst_header())
+    lines.append(rst_label("specs"))
+    lines.append(rst_title("Netlink Family Specifications"))
+    lines.append(rst_toctree(1))
+
+    index_dir = os.path.dirname(output)
+    logging.debug("Looking for .rst files in %s", index_dir)
+    for filename in sorted(os.listdir(index_dir)):
+        if not filename.endswith(".rst") or filename == "index.rst":
+            continue
+        lines.append(f"   {filename.replace('.rst', '')}\n")
+
+    logging.debug("Writing an index file at %s", output)
+    write_to_rstfile("".join(lines), output)
+
+
+def main() -> None:
+    """Main function that reads the YAML files and generates the RST files"""
+
+    args = parse_arguments()
+
+    if args.input:
+        logging.debug("Parsing %s", args.input)
+        try:
+            content = parse_yaml_file(os.path.join(args.input))
+        except Exception as exception:
+            logging.warning("Failed to parse %s.", args.input)
+            logging.warning(exception)
+            sys.exit(-1)
+
+        write_to_rstfile(content, args.output)
+
+    if args.index:
+        # Generate the index RST file
+        generate_main_index_rst(args.output)
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/net/ynl/ynl-regen.sh b/tools/net/ynl/ynl-regen.sh
index bdba24066cf1..a37304dcc88e 100755
--- a/tools/net/ynl/ynl-regen.sh
+++ b/tools/net/ynl/ynl-regen.sh
@@ -30,8 +30,8 @@ for f in $files; do
     fi
 
     echo -e "\tGEN ${params[2]}\t$f"
-    $TOOL --mode ${params[2]} --${params[3]} --spec $KDIR/${params[0]} \
-	  $args -o $f
+    $TOOL --cmp-out --mode ${params[2]} --${params[3]} \
+	  --spec $KDIR/${params[0]} $args -o $f
 done
 
 popd >>/dev/null
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index e94756e09ca9..548ec3cd7c00 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -291,7 +291,7 @@ static void init_insn_state(struct objtool_file *file, struct insn_state *state,
 
 static struct cfi_state *cfi_alloc(void)
 {
-	struct cfi_state *cfi = calloc(sizeof(struct cfi_state), 1);
+	struct cfi_state *cfi = calloc(1, sizeof(struct cfi_state));
 	if (!cfi) {
 		WARN("calloc failed");
 		exit(1);
diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h
index 649ebdef9c3f..1685d7ea6a9f 100644
--- a/tools/objtool/noreturns.h
+++ b/tools/objtool/noreturns.h
@@ -6,7 +6,6 @@
  *
  * Yes, this is unfortunate.  A better solution is in the works.
  */
-NORETURN(__invalid_creds)
 NORETURN(__kunit_abort)
 NORETURN(__module_put_and_kthread_exit)
 NORETURN(__reiserfs_panic)
diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt
index 4c90cc176f81..2109690b0d5f 100644
--- a/tools/perf/Documentation/perf-intel-pt.txt
+++ b/tools/perf/Documentation/perf-intel-pt.txt
@@ -683,7 +683,7 @@ Buffer handling
 ~~~~~~~~~~~~~~~
 
 There may be buffer limitations (i.e. single ToPa entry) which means that actual
-buffer sizes are limited to powers of 2 up to 4MiB (MAX_ORDER).  In order to
+buffer sizes are limited to powers of 2 up to 4MiB (MAX_PAGE_ORDER).  In order to
 provide other sizes, and in particular an arbitrarily large size, multiple
 buffers are logically concatenated.  However an interrupt must be used to switch
 between buffers.  That has two potential problems:
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 1da7f4b91b4f..dc42de1785ce 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -1,3 +1,5 @@
+arch/arm64/tools/gen-sysreg.awk
+arch/arm64/tools/sysreg
 tools/perf
 tools/arch
 tools/scripts
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index d88da787e815..058c9aecf608 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -434,6 +434,21 @@ export INSTALL SHELL_PATH
 
 SHELL = $(SHELL_PATH)
 
+arm64_gen_sysreg_dir := $(srctree)/tools/arch/arm64/tools
+ifneq ($(OUTPUT),)
+  arm64_gen_sysreg_outdir := $(OUTPUT)
+else
+  arm64_gen_sysreg_outdir := $(CURDIR)
+endif
+
+arm64-sysreg-defs: FORCE
+	$(Q)$(MAKE) -C $(arm64_gen_sysreg_dir) O=$(arm64_gen_sysreg_outdir)
+
+arm64-sysreg-defs-clean:
+	$(call QUIET_CLEAN,arm64-sysreg-defs)
+	$(Q)$(MAKE) -C $(arm64_gen_sysreg_dir) O=$(arm64_gen_sysreg_outdir) \
+		clean > /dev/null
+
 beauty_linux_dir := $(srctree)/tools/perf/trace/beauty/include/linux/
 linux_uapi_dir := $(srctree)/tools/include/uapi/linux
 asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic
@@ -450,15 +465,6 @@ drm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/drm_ioctl.sh
 # Create output directory if not already present
 _dummy := $(shell [ -d '$(beauty_ioctl_outdir)' ] || mkdir -p '$(beauty_ioctl_outdir)')
 
-arm64_gen_sysreg_dir := $(srctree)/tools/arch/arm64/tools
-
-arm64-sysreg-defs: FORCE
-	$(Q)$(MAKE) -C $(arm64_gen_sysreg_dir)
-
-arm64-sysreg-defs-clean:
-	$(call QUIET_CLEAN,arm64-sysreg-defs)
-	$(Q)$(MAKE) -C $(arm64_gen_sysreg_dir) clean > /dev/null
-
 $(drm_ioctl_array): $(drm_hdr_dir)/drm.h $(drm_hdr_dir)/i915_drm.h $(drm_ioctl_tbl)
 	$(Q)$(SHELL) '$(drm_ioctl_tbl)' $(drm_hdr_dir) > $@
 
diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index 80be0e98ea0c..532b855df589 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -367,3 +367,12 @@
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	n64	cachestat			sys_cachestat
 452	n64	fchmodat2			sys_fchmodat2
+453	n64	map_shadow_stack		sys_map_shadow_stack
+454	n64	futex_wake			sys_futex_wake
+455	n64	futex_wait			sys_futex_wait
+456	n64	futex_requeue			sys_futex_requeue
+457	n64	statmount			sys_statmount
+458	n64	listmount			sys_listmount
+459	n64	lsm_get_self_attr		sys_lsm_get_self_attr
+460	n64	lsm_set_self_attr		sys_lsm_set_self_attr
+461	n64	lsm_list_modules		sys_lsm_list_modules
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index e1412519b4ad..17173b82ca21 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -539,3 +539,12 @@
 450 	nospu	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	cachestat			sys_cachestat
 452	common	fchmodat2			sys_fchmodat2
+453	common	map_shadow_stack		sys_ni_syscall
+454	common	futex_wake			sys_futex_wake
+455	common	futex_wait			sys_futex_wait
+456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount
+459	common	lsm_get_self_attr		sys_lsm_get_self_attr
+460	common	lsm_set_self_attr		sys_lsm_set_self_attr
+461	common	lsm_list_modules		sys_lsm_list_modules
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index cc0bc144b661..095bb86339a7 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -455,3 +455,12 @@
 450  common	set_mempolicy_home_node	sys_set_mempolicy_home_node	sys_set_mempolicy_home_node
 451  common	cachestat		sys_cachestat			sys_cachestat
 452  common	fchmodat2		sys_fchmodat2			sys_fchmodat2
+453  common	map_shadow_stack	sys_map_shadow_stack		sys_map_shadow_stack
+454  common	futex_wake		sys_futex_wake			sys_futex_wake
+455  common	futex_wait		sys_futex_wait			sys_futex_wait
+456  common	futex_requeue		sys_futex_requeue		sys_futex_requeue
+457  common	statmount		sys_statmount			sys_statmount
+458  common	listmount		sys_listmount			sys_listmount
+459  common	lsm_get_self_attr	sys_lsm_get_self_attr		sys_lsm_get_self_attr
+460  common	lsm_set_self_attr	sys_lsm_set_self_attr		sys_lsm_set_self_attr
+461  common	lsm_list_modules	sys_lsm_list_modules		sys_lsm_list_modules
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 2a62eaf30d69..7e8d46f4147f 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -375,6 +375,14 @@
 451	common	cachestat		sys_cachestat
 452	common	fchmodat2		sys_fchmodat2
 453	64	map_shadow_stack	sys_map_shadow_stack
+454	common	futex_wake		sys_futex_wake
+455	common	futex_wait		sys_futex_wait
+456	common	futex_requeue		sys_futex_requeue
+457	common	statmount		sys_statmount
+458	common	listmount		sys_listmount
+459	common	lsm_get_self_attr	sys_lsm_get_self_attr
+460	common	lsm_set_self_attr	sys_lsm_set_self_attr
+461	common	lsm_list_modules	sys_lsm_list_modules
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/tools/perf/builtin-kwork.c b/tools/perf/builtin-kwork.c
index f007a9b27065..0092b9b39611 100644
--- a/tools/perf/builtin-kwork.c
+++ b/tools/perf/builtin-kwork.c
@@ -1643,7 +1643,7 @@ static int top_print_work(struct perf_kwork *kwork __maybe_unused, struct kwork_
 	/*
 	 * pid
 	 */
-	ret += printf(" %*ld ", PRINT_PID_WIDTH, work->id);
+	ret += printf(" %*" PRIu64 " ", PRINT_PID_WIDTH, work->id);
 
 	/*
 	 * tgid
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index a343823c8ddf..61c2c96cc070 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -434,6 +434,11 @@ static void json_print_metric(void *ps __maybe_unused, const char *group,
 	strbuf_release(&buf);
 }
 
+static bool json_skip_duplicate_pmus(void *ps __maybe_unused)
+{
+	return false;
+}
+
 static bool default_skip_duplicate_pmus(void *ps)
 {
 	struct print_state *print_state = ps;
@@ -503,6 +508,7 @@ int cmd_list(int argc, const char **argv)
 			.print_end = json_print_end,
 			.print_event = json_print_event,
 			.print_metric = json_print_metric,
+			.skip_duplicate_pmus = json_skip_duplicate_pmus,
 		};
 		ps = &json_ps;
 	} else {
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json
index e2848a9d4848..afcdad58ef89 100644
--- a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json
@@ -231,6 +231,7 @@
         "MetricName": "slots_lost_misspeculation_fraction",
         "MetricExpr": "100 * ((OP_SPEC - OP_RETIRED) / (CPU_CYCLES * #slots))",
         "BriefDescription": "Fraction of slots lost due to misspeculation",
+        "DefaultMetricgroupName": "TopdownL1",
         "MetricGroup": "Default;TopdownL1",
         "ScaleUnit": "1percent of slots"
     },
@@ -238,6 +239,7 @@
         "MetricName": "retired_fraction",
         "MetricExpr": "100 * (OP_RETIRED / (CPU_CYCLES * #slots))",
         "BriefDescription": "Fraction of slots retiring, useful work",
+        "DefaultMetricgroupName": "TopdownL1",
         "MetricGroup": "Default;TopdownL1",
 	"ScaleUnit": "1percent of slots"
     },
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
index 39b74d83c7c4..cfcb7e2c3813 100644
--- a/tools/perf/trace/beauty/include/linux/socket.h
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -383,6 +383,7 @@ struct ucred {
 #define SOL_MPTCP	284
 #define SOL_MCTP	285
 #define SOL_SMC		286
+#define SOL_VSOCK	287
 
 /* IPX options */
 #define IPX_TYPE	1
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index fb661c48992f..988473bf907a 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -347,7 +347,7 @@ CFLAGS_rbtree.o        += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ET
 CFLAGS_libstring.o     += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_hweight.o       += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_header.o        += -include $(OUTPUT)PERF-VERSION-FILE
-CFLAGS_arm-spe.o       += -I$(srctree)/tools/arch/arm64/include/ -I$(srctree)/tools/arch/arm64/include/generated/
+CFLAGS_arm-spe.o       += -I$(srctree)/tools/arch/arm64/include/ -I$(OUTPUT)arch/arm64/include/generated/
 
 $(OUTPUT)util/argv_split.o: ../lib/argv_split.c FORCE
 	$(call rule_mkdir)
diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c
index e105245eb905..f1716c089c99 100644
--- a/tools/perf/util/bpf_lock_contention.c
+++ b/tools/perf/util/bpf_lock_contention.c
@@ -12,6 +12,7 @@
 #include <linux/zalloc.h>
 #include <linux/string.h>
 #include <bpf/bpf.h>
+#include <inttypes.h>
 
 #include "bpf_skel/lock_contention.skel.h"
 #include "bpf_skel/lock_data.h"
@@ -250,7 +251,7 @@ static const char *lock_contention_get_name(struct lock_contention *con,
 		if (cgrp)
 			return cgrp->name;
 
-		snprintf(name_buf, sizeof(name_buf), "cgroup:%lu", cgrp_id);
+		snprintf(name_buf, sizeof(name_buf), "cgroup:%" PRIu64 "", cgrp_id);
 		return name_buf;
 	}
 
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 0484736d9fe4..ca3e0404f187 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -225,7 +225,7 @@ static struct metric *metric__new(const struct pmu_metric *pm,
 
 	m->pmu = pm->pmu ?: "cpu";
 	m->metric_name = pm->metric_name;
-	m->default_metricgroup_name = pm->default_metricgroup_name;
+	m->default_metricgroup_name = pm->default_metricgroup_name ?: "";
 	m->modifier = NULL;
 	if (modifier) {
 		m->modifier = strdup(modifier);
diff --git a/tools/power/pm-graph/sleepgraph.py b/tools/power/pm-graph/sleepgraph.py
index 4a356a706785..40ad221e8881 100755
--- a/tools/power/pm-graph/sleepgraph.py
+++ b/tools/power/pm-graph/sleepgraph.py
@@ -4151,7 +4151,7 @@ def parseKernelLog(data):
 			elif(re.match('Enabling non-boot CPUs .*', msg)):
 				# start of first cpu resume
 				cpu_start = ktime
-			elif(re.match('smpboot: CPU (?P<cpu>[0-9]*) is now offline', msg)) \
+			elif(re.match('smpboot: CPU (?P<cpu>[0-9]*) is now offline', msg) \
 				or re.match('psci: CPU(?P<cpu>[0-9]*) killed.*', msg)):
 				# end of a cpu suspend, start of the next
 				m = re.match('smpboot: CPU (?P<cpu>[0-9]*) is now offline', msg)
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 9a10512e3407..7a334377f92b 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -211,9 +211,6 @@ int *fd_instr_count_percpu;
 struct timeval interval_tv = { 5, 0 };
 struct timespec interval_ts = { 5, 0 };
 
-/* Save original CPU model */
-unsigned int model_orig;
-
 unsigned int num_iterations;
 unsigned int header_iterations;
 unsigned int debug;
@@ -224,24 +221,16 @@ unsigned int rapl_joules;
 unsigned int summary_only;
 unsigned int list_header_only;
 unsigned int dump_only;
-unsigned int do_snb_cstates;
-unsigned int do_knl_cstates;
-unsigned int do_slm_cstates;
-unsigned int use_c1_residency_msr;
 unsigned int has_aperf;
 unsigned int has_epb;
 unsigned int has_turbo;
 unsigned int is_hybrid;
-unsigned int do_irtl_snb;
-unsigned int do_irtl_hsw;
 unsigned int units = 1000000;	/* MHz etc */
 unsigned int genuine_intel;
 unsigned int authentic_amd;
 unsigned int hygon_genuine;
 unsigned int max_level, max_extended_level;
 unsigned int has_invariant_tsc;
-unsigned int do_nhm_platform_info;
-unsigned int no_MSR_MISC_PWR_MGMT;
 unsigned int aperf_mperf_multiplier = 1;
 double bclk;
 double base_hz;
@@ -250,7 +239,6 @@ double tsc_tweak = 1.0;
 unsigned int show_pkg_only;
 unsigned int show_core_only;
 char *output_buffer, *outp;
-unsigned int do_rapl;
 unsigned int do_dts;
 unsigned int do_ptm;
 unsigned int do_ipc;
@@ -261,65 +249,686 @@ unsigned int gfx_cur_mhz;
 unsigned int gfx_act_mhz;
 unsigned int tj_max;
 unsigned int tj_max_override;
-int tcc_offset_bits;
 double rapl_power_units, rapl_time_units;
 double rapl_dram_energy_units, rapl_energy_units;
 double rapl_joule_counter_range;
-unsigned int do_core_perf_limit_reasons;
-unsigned int has_automatic_cstate_conversion;
-unsigned int dis_cstate_prewake;
-unsigned int do_gfx_perf_limit_reasons;
-unsigned int do_ring_perf_limit_reasons;
 unsigned int crystal_hz;
 unsigned long long tsc_hz;
 int base_cpu;
-double discover_bclk(unsigned int family, unsigned int model);
 unsigned int has_hwp;		/* IA32_PM_ENABLE, IA32_HWP_CAPABILITIES */
 			/* IA32_HWP_REQUEST, IA32_HWP_STATUS */
 unsigned int has_hwp_notify;	/* IA32_HWP_INTERRUPT */
 unsigned int has_hwp_activity_window;	/* IA32_HWP_REQUEST[bits 41:32] */
 unsigned int has_hwp_epp;	/* IA32_HWP_REQUEST[bits 31:24] */
 unsigned int has_hwp_pkg;	/* IA32_HWP_REQUEST_PKG */
-unsigned int has_misc_feature_control;
 unsigned int first_counter_read = 1;
 int ignore_stdin;
 
-#define RAPL_PKG		(1 << 0)
-					/* 0x610 MSR_PKG_POWER_LIMIT */
-					/* 0x611 MSR_PKG_ENERGY_STATUS */
-#define RAPL_PKG_PERF_STATUS	(1 << 1)
-					/* 0x613 MSR_PKG_PERF_STATUS */
-#define RAPL_PKG_POWER_INFO	(1 << 2)
-					/* 0x614 MSR_PKG_POWER_INFO */
-
-#define RAPL_DRAM		(1 << 3)
-					/* 0x618 MSR_DRAM_POWER_LIMIT */
-					/* 0x619 MSR_DRAM_ENERGY_STATUS */
-#define RAPL_DRAM_PERF_STATUS	(1 << 4)
-					/* 0x61b MSR_DRAM_PERF_STATUS */
-#define RAPL_DRAM_POWER_INFO	(1 << 5)
-					/* 0x61c MSR_DRAM_POWER_INFO */
-
-#define RAPL_CORES_POWER_LIMIT	(1 << 6)
-					/* 0x638 MSR_PP0_POWER_LIMIT */
-#define RAPL_CORE_POLICY	(1 << 7)
-					/* 0x63a MSR_PP0_POLICY */
-
-#define RAPL_GFX		(1 << 8)
-					/* 0x640 MSR_PP1_POWER_LIMIT */
-					/* 0x641 MSR_PP1_ENERGY_STATUS */
-					/* 0x642 MSR_PP1_POLICY */
-
-#define RAPL_CORES_ENERGY_STATUS	(1 << 9)
-					/* 0x639 MSR_PP0_ENERGY_STATUS */
-#define RAPL_PER_CORE_ENERGY	(1 << 10)
-					/* Indicates cores energy collection is per-core,
-					 * not per-package. */
-#define RAPL_AMD_F17H		(1 << 11)
-					/* 0xc0010299 MSR_RAPL_PWR_UNIT */
-					/* 0xc001029a MSR_CORE_ENERGY_STAT */
-					/* 0xc001029b MSR_PKG_ENERGY_STAT */
-#define RAPL_CORES (RAPL_CORES_ENERGY_STATUS | RAPL_CORES_POWER_LIMIT)
+int get_msr(int cpu, off_t offset, unsigned long long *msr);
+
+/* Model specific support Start */
+
+/* List of features that may diverge among different platforms */
+struct platform_features {
+	bool has_msr_misc_feature_control;	/* MSR_MISC_FEATURE_CONTROL */
+	bool has_msr_misc_pwr_mgmt;	/* MSR_MISC_PWR_MGMT */
+	bool has_nhm_msrs;	/* MSR_PLATFORM_INFO, MSR_IA32_TEMPERATURE_TARGET, MSR_SMI_COUNT, MSR_PKG_CST_CONFIG_CONTROL, MSR_IA32_POWER_CTL, TRL MSRs */
+	bool has_config_tdp;	/* MSR_CONFIG_TDP_NOMINAL/LEVEL_1/LEVEL_2/CONTROL, MSR_TURBO_ACTIVATION_RATIO */
+	int bclk_freq;		/* CPU base clock */
+	int crystal_freq;	/* Crystal clock to use when not available from CPUID.15 */
+	int supported_cstates;	/* Core cstates and Package cstates supported */
+	int cst_limit;		/* MSR_PKG_CST_CONFIG_CONTROL */
+	bool has_cst_auto_convension;	/* AUTOMATIC_CSTATE_CONVERSION bit in MSR_PKG_CST_CONFIG_CONTROL */
+	bool has_irtl_msrs;	/* MSR_PKGC3/PKGC6/PKGC7/PKGC8/PKGC9/PKGC10_IRTL */
+	bool has_msr_core_c1_res;	/* MSR_CORE_C1_RES */
+	bool has_msr_module_c6_res_ms;	/* MSR_MODULE_C6_RES_MS */
+	bool has_msr_c6_demotion_policy_config;	/* MSR_CC6_DEMOTION_POLICY_CONFIG/MSR_MC6_DEMOTION_POLICY_CONFIG */
+	bool has_msr_atom_pkg_c6_residency;	/* MSR_ATOM_PKG_C6_RESIDENCY */
+	bool has_msr_knl_core_c6_residency;	/* MSR_KNL_CORE_C6_RESIDENCY */
+	bool has_ext_cst_msrs;	/* MSR_PKG_WEIGHTED_CORE_C0_RES/MSR_PKG_ANY_CORE_C0_RES/MSR_PKG_ANY_GFXE_C0_RES/MSR_PKG_BOTH_CORE_GFXE_C0_RES */
+	bool has_cst_prewake_bit;	/* Cstate prewake bit in MSR_IA32_POWER_CTL */
+	int trl_msrs;		/* MSR_TURBO_RATIO_LIMIT/LIMIT1/LIMIT2/SECONDARY, Atom TRL MSRs */
+	int plr_msrs;		/* MSR_CORE/GFX/RING_PERF_LIMIT_REASONS */
+	int rapl_msrs;		/* RAPL PKG/DRAM/CORE/GFX MSRs, AMD RAPL MSRs */
+	bool has_per_core_rapl;	/* Indicates cores energy collection is per-core, not per-package. AMD specific for now */
+	bool has_rapl_divisor;	/* Divisor for Energy unit raw value from MSR_RAPL_POWER_UNIT */
+	bool has_fixed_rapl_unit;	/* Fixed Energy Unit used for DRAM RAPL Domain */
+	int rapl_quirk_tdp;	/* Hardcoded TDP value when cannot be retrieved from hardware */
+	int tcc_offset_bits;	/* TCC Offset bits in MSR_IA32_TEMPERATURE_TARGET */
+	bool enable_tsc_tweak;	/* Use CPU Base freq instead of TSC freq for aperf/mperf counter */
+	bool need_perf_multiplier;	/* mperf/aperf multiplier */
+};
+
+struct platform_data {
+	unsigned int model;
+	const struct platform_features *features;
+};
+
+/* For BCLK */
+enum bclk_freq {
+	BCLK_100MHZ = 1,
+	BCLK_133MHZ,
+	BCLK_SLV,
+};
+
+#define SLM_BCLK_FREQS 5
+double slm_freq_table[SLM_BCLK_FREQS] = { 83.3, 100.0, 133.3, 116.7, 80.0 };
+
+double slm_bclk(void)
+{
+	unsigned long long msr = 3;
+	unsigned int i;
+	double freq;
+
+	if (get_msr(base_cpu, MSR_FSB_FREQ, &msr))
+		fprintf(outf, "SLM BCLK: unknown\n");
+
+	i = msr & 0xf;
+	if (i >= SLM_BCLK_FREQS) {
+		fprintf(outf, "SLM BCLK[%d] invalid\n", i);
+		i = 3;
+	}
+	freq = slm_freq_table[i];
+
+	if (!quiet)
+		fprintf(outf, "SLM BCLK: %.1f Mhz\n", freq);
+
+	return freq;
+}
+
+/* For Package cstate limit */
+enum package_cstate_limit {
+	CST_LIMIT_NHM = 1,
+	CST_LIMIT_SNB,
+	CST_LIMIT_HSW,
+	CST_LIMIT_SKX,
+	CST_LIMIT_ICX,
+	CST_LIMIT_SLV,
+	CST_LIMIT_AMT,
+	CST_LIMIT_KNL,
+	CST_LIMIT_GMT,
+};
+
+/* For Turbo Ratio Limit MSRs */
+enum turbo_ratio_limit_msrs {
+	TRL_BASE = BIT(0),
+	TRL_LIMIT1 = BIT(1),
+	TRL_LIMIT2 = BIT(2),
+	TRL_ATOM = BIT(3),
+	TRL_KNL = BIT(4),
+	TRL_CORECOUNT = BIT(5),
+};
+
+/* For Perf Limit Reason MSRs */
+enum perf_limit_reason_msrs {
+	PLR_CORE = BIT(0),
+	PLR_GFX = BIT(1),
+	PLR_RING = BIT(2),
+};
+
+/* For RAPL MSRs */
+enum rapl_msrs {
+	RAPL_PKG_POWER_LIMIT = BIT(0),	/* 0x610 MSR_PKG_POWER_LIMIT */
+	RAPL_PKG_ENERGY_STATUS = BIT(1),	/* 0x611 MSR_PKG_ENERGY_STATUS */
+	RAPL_PKG_PERF_STATUS = BIT(2),	/* 0x613 MSR_PKG_PERF_STATUS */
+	RAPL_PKG_POWER_INFO = BIT(3),	/* 0x614 MSR_PKG_POWER_INFO */
+	RAPL_DRAM_POWER_LIMIT = BIT(4),	/* 0x618 MSR_DRAM_POWER_LIMIT */
+	RAPL_DRAM_ENERGY_STATUS = BIT(5),	/* 0x619 MSR_DRAM_ENERGY_STATUS */
+	RAPL_DRAM_PERF_STATUS = BIT(6),	/* 0x61b MSR_DRAM_PERF_STATUS */
+	RAPL_DRAM_POWER_INFO = BIT(7),	/* 0x61c MSR_DRAM_POWER_INFO */
+	RAPL_CORE_POWER_LIMIT = BIT(8),	/* 0x638 MSR_PP0_POWER_LIMIT */
+	RAPL_CORE_ENERGY_STATUS = BIT(9),	/* 0x639 MSR_PP0_ENERGY_STATUS */
+	RAPL_CORE_POLICY = BIT(10),	/* 0x63a MSR_PP0_POLICY */
+	RAPL_GFX_POWER_LIMIT = BIT(11),	/* 0x640 MSR_PP1_POWER_LIMIT */
+	RAPL_GFX_ENERGY_STATUS = BIT(12),	/* 0x641 MSR_PP1_ENERGY_STATUS */
+	RAPL_GFX_POLICY = BIT(13),	/* 0x642 MSR_PP1_POLICY */
+	RAPL_AMD_PWR_UNIT = BIT(14),	/* 0xc0010299 MSR_AMD_RAPL_POWER_UNIT */
+	RAPL_AMD_CORE_ENERGY_STAT = BIT(15),	/* 0xc001029a MSR_AMD_CORE_ENERGY_STATUS */
+	RAPL_AMD_PKG_ENERGY_STAT = BIT(16),	/* 0xc001029b MSR_AMD_PKG_ENERGY_STATUS */
+};
+
+#define RAPL_PKG	(RAPL_PKG_ENERGY_STATUS | RAPL_PKG_POWER_LIMIT)
+#define RAPL_DRAM	(RAPL_DRAM_ENERGY_STATUS | RAPL_DRAM_POWER_LIMIT)
+#define RAPL_CORE	(RAPL_CORE_ENERGY_STATUS | RAPL_CORE_POWER_LIMIT)
+#define RAPL_GFX	(RAPL_GFX_POWER_LIMIT | RAPL_GFX_ENERGY_STATUS)
+
+#define RAPL_PKG_ALL	(RAPL_PKG | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO)
+#define RAPL_DRAM_ALL	(RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_DRAM_POWER_INFO)
+#define RAPL_CORE_ALL	(RAPL_CORE | RAPL_CORE_POLICY)
+#define RAPL_GFX_ALL	(RAPL_GFX | RAPL_GFX_POLIGY)
+
+#define RAPL_AMD_F17H	(RAPL_AMD_PWR_UNIT | RAPL_AMD_CORE_ENERGY_STAT | RAPL_AMD_PKG_ENERGY_STAT)
+
+/* For Cstates */
+enum cstates {
+	CC1 = BIT(0),
+	CC3 = BIT(1),
+	CC6 = BIT(2),
+	CC7 = BIT(3),
+	PC2 = BIT(4),
+	PC3 = BIT(5),
+	PC6 = BIT(6),
+	PC7 = BIT(7),
+	PC8 = BIT(8),
+	PC9 = BIT(9),
+	PC10 = BIT(10),
+};
+
+static const struct platform_features nhm_features = {
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_133MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | PC3 | PC6,
+	.cst_limit = CST_LIMIT_NHM,
+	.trl_msrs = TRL_BASE,
+};
+
+static const struct platform_features nhx_features = {
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_133MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | PC3 | PC6,
+	.cst_limit = CST_LIMIT_NHM,
+};
+
+static const struct platform_features snb_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7,
+	.cst_limit = CST_LIMIT_SNB,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.rapl_msrs = RAPL_PKG | RAPL_CORE_ALL | RAPL_GFX | RAPL_PKG_POWER_INFO,
+};
+
+static const struct platform_features snx_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7,
+	.cst_limit = CST_LIMIT_SNB,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM_ALL,
+};
+
+static const struct platform_features ivb_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7,
+	.cst_limit = CST_LIMIT_SNB,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.rapl_msrs = RAPL_PKG | RAPL_CORE_ALL | RAPL_GFX | RAPL_PKG_POWER_INFO,
+};
+
+static const struct platform_features ivx_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7,
+	.cst_limit = CST_LIMIT_SNB,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE | TRL_LIMIT1,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM_ALL,
+};
+
+static const struct platform_features hsw_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7,
+	.cst_limit = CST_LIMIT_HSW,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.plr_msrs = PLR_CORE | PLR_GFX | PLR_RING,
+	.rapl_msrs = RAPL_PKG | RAPL_CORE_ALL | RAPL_GFX | RAPL_PKG_POWER_INFO,
+};
+
+static const struct platform_features hsx_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7,
+	.cst_limit = CST_LIMIT_HSW,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE | TRL_LIMIT1 | TRL_LIMIT2,
+	.plr_msrs = PLR_CORE | PLR_RING,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL,
+	.has_fixed_rapl_unit = 1,
+};
+
+static const struct platform_features hswl_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7 | PC8 | PC9 | PC10,
+	.cst_limit = CST_LIMIT_HSW,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.plr_msrs = PLR_CORE | PLR_GFX | PLR_RING,
+	.rapl_msrs = RAPL_PKG | RAPL_CORE_ALL | RAPL_GFX | RAPL_PKG_POWER_INFO,
+};
+
+static const struct platform_features hswg_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7,
+	.cst_limit = CST_LIMIT_HSW,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.plr_msrs = PLR_CORE | PLR_GFX | PLR_RING,
+	.rapl_msrs = RAPL_PKG | RAPL_CORE_ALL | RAPL_GFX | RAPL_PKG_POWER_INFO,
+};
+
+static const struct platform_features bdw_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7 | PC8 | PC9 | PC10,
+	.cst_limit = CST_LIMIT_HSW,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.rapl_msrs = RAPL_PKG | RAPL_CORE_ALL | RAPL_GFX | RAPL_PKG_POWER_INFO,
+};
+
+static const struct platform_features bdwg_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7,
+	.cst_limit = CST_LIMIT_HSW,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.rapl_msrs = RAPL_PKG | RAPL_CORE_ALL | RAPL_GFX | RAPL_PKG_POWER_INFO,
+};
+
+static const struct platform_features bdx_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | PC2 | PC3 | PC6,
+	.cst_limit = CST_LIMIT_HSW,
+	.has_irtl_msrs = 1,
+	.has_cst_auto_convension = 1,
+	.trl_msrs = TRL_BASE,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL,
+	.has_fixed_rapl_unit = 1,
+};
+
+static const struct platform_features skl_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.crystal_freq = 24000000,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7 | PC8 | PC9 | PC10,
+	.cst_limit = CST_LIMIT_HSW,
+	.has_irtl_msrs = 1,
+	.has_ext_cst_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.tcc_offset_bits = 6,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX,
+	.enable_tsc_tweak = 1,
+};
+
+static const struct platform_features cnl_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7 | PC8 | PC9 | PC10,
+	.cst_limit = CST_LIMIT_HSW,
+	.has_irtl_msrs = 1,
+	.has_msr_core_c1_res = 1,
+	.has_ext_cst_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.tcc_offset_bits = 6,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX,
+	.enable_tsc_tweak = 1,
+};
+
+static const struct platform_features adl_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC6 | CC7 | PC2 | PC3 | PC6 | PC8 | PC10,
+	.cst_limit = CST_LIMIT_HSW,
+	.has_irtl_msrs = 1,
+	.has_msr_core_c1_res = 1,
+	.has_ext_cst_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.tcc_offset_bits = 6,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX,
+	.enable_tsc_tweak = 1,
+};
+
+static const struct platform_features skx_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC6 | PC2 | PC6,
+	.cst_limit = CST_LIMIT_SKX,
+	.has_irtl_msrs = 1,
+	.has_cst_auto_convension = 1,
+	.trl_msrs = TRL_BASE | TRL_CORECOUNT,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL,
+	.has_fixed_rapl_unit = 1,
+};
+
+static const struct platform_features icx_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC6 | PC2 | PC6,
+	.cst_limit = CST_LIMIT_ICX,
+	.has_irtl_msrs = 1,
+	.has_cst_prewake_bit = 1,
+	.trl_msrs = TRL_BASE | TRL_CORECOUNT,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL,
+	.has_fixed_rapl_unit = 1,
+};
+
+static const struct platform_features spr_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC6 | PC2 | PC6,
+	.cst_limit = CST_LIMIT_SKX,
+	.has_msr_core_c1_res = 1,
+	.has_irtl_msrs = 1,
+	.has_cst_prewake_bit = 1,
+	.trl_msrs = TRL_BASE | TRL_CORECOUNT,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL,
+};
+
+static const struct platform_features srf_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC6 | PC2 | PC6,
+	.cst_limit = CST_LIMIT_SKX,
+	.has_msr_core_c1_res = 1,
+	.has_msr_module_c6_res_ms = 1,
+	.has_irtl_msrs = 1,
+	.has_cst_prewake_bit = 1,
+	.trl_msrs = TRL_BASE | TRL_CORECOUNT,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL,
+};
+
+static const struct platform_features grr_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC6,
+	.cst_limit = CST_LIMIT_SKX,
+	.has_msr_core_c1_res = 1,
+	.has_msr_module_c6_res_ms = 1,
+	.has_irtl_msrs = 1,
+	.has_cst_prewake_bit = 1,
+	.trl_msrs = TRL_BASE | TRL_CORECOUNT,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL,
+};
+
+static const struct platform_features slv_features = {
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_SLV,
+	.supported_cstates = CC1 | CC6 | PC6,
+	.cst_limit = CST_LIMIT_SLV,
+	.has_msr_core_c1_res = 1,
+	.has_msr_module_c6_res_ms = 1,
+	.has_msr_c6_demotion_policy_config = 1,
+	.has_msr_atom_pkg_c6_residency = 1,
+	.trl_msrs = TRL_ATOM,
+	.rapl_msrs = RAPL_PKG | RAPL_CORE,
+	.has_rapl_divisor = 1,
+	.rapl_quirk_tdp = 30,
+};
+
+static const struct platform_features slvd_features = {
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_SLV,
+	.supported_cstates = CC1 | CC6 | PC3 | PC6,
+	.cst_limit = CST_LIMIT_SLV,
+	.has_msr_atom_pkg_c6_residency = 1,
+	.trl_msrs = TRL_BASE,
+	.rapl_msrs = RAPL_PKG | RAPL_CORE,
+	.rapl_quirk_tdp = 30,
+};
+
+static const struct platform_features amt_features = {
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_133MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | PC3 | PC6,
+	.cst_limit = CST_LIMIT_AMT,
+	.trl_msrs = TRL_BASE,
+};
+
+static const struct platform_features gmt_features = {
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.crystal_freq = 19200000,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7 | PC8 | PC9 | PC10,
+	.cst_limit = CST_LIMIT_GMT,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE | TRL_CORECOUNT,
+	.rapl_msrs = RAPL_PKG | RAPL_PKG_POWER_INFO,
+};
+
+static const struct platform_features gmtd_features = {
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.crystal_freq = 25000000,
+	.supported_cstates = CC1 | CC6 | PC2 | PC6,
+	.cst_limit = CST_LIMIT_GMT,
+	.has_irtl_msrs = 1,
+	.has_msr_core_c1_res = 1,
+	.trl_msrs = TRL_BASE | TRL_CORECOUNT,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL | RAPL_CORE_ENERGY_STATUS,
+};
+
+static const struct platform_features gmtp_features = {
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.crystal_freq = 19200000,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7 | PC8 | PC9 | PC10,
+	.cst_limit = CST_LIMIT_GMT,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.rapl_msrs = RAPL_PKG | RAPL_PKG_POWER_INFO,
+};
+
+static const struct platform_features tmt_features = {
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7 | PC8 | PC9 | PC10,
+	.cst_limit = CST_LIMIT_GMT,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX,
+	.enable_tsc_tweak = 1,
+};
+
+static const struct platform_features tmtd_features = {
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC6,
+	.cst_limit = CST_LIMIT_GMT,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE | TRL_CORECOUNT,
+	.rapl_msrs = RAPL_PKG_ALL,
+};
+
+static const struct platform_features knl_features = {
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC6 | PC3 | PC6,
+	.cst_limit = CST_LIMIT_KNL,
+	.has_msr_knl_core_c6_residency = 1,
+	.trl_msrs = TRL_KNL,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL,
+	.has_fixed_rapl_unit = 1,
+	.need_perf_multiplier = 1,
+};
+
+static const struct platform_features default_features = {
+};
+
+static const struct platform_features amd_features_with_rapl = {
+	.rapl_msrs = RAPL_AMD_F17H,
+	.has_per_core_rapl = 1,
+	.rapl_quirk_tdp = 280,	/* This is the max stock TDP of HEDT/Server Fam17h+ chips */
+};
+
+static const struct platform_data turbostat_pdata[] = {
+	{ INTEL_FAM6_NEHALEM, &nhm_features },
+	{ INTEL_FAM6_NEHALEM_G, &nhm_features },
+	{ INTEL_FAM6_NEHALEM_EP, &nhm_features },
+	{ INTEL_FAM6_NEHALEM_EX, &nhx_features },
+	{ INTEL_FAM6_WESTMERE, &nhm_features },
+	{ INTEL_FAM6_WESTMERE_EP, &nhm_features },
+	{ INTEL_FAM6_WESTMERE_EX, &nhx_features },
+	{ INTEL_FAM6_SANDYBRIDGE, &snb_features },
+	{ INTEL_FAM6_SANDYBRIDGE_X, &snx_features },
+	{ INTEL_FAM6_IVYBRIDGE, &ivb_features },
+	{ INTEL_FAM6_IVYBRIDGE_X, &ivx_features },
+	{ INTEL_FAM6_HASWELL, &hsw_features },
+	{ INTEL_FAM6_HASWELL_X, &hsx_features },
+	{ INTEL_FAM6_HASWELL_L, &hswl_features },
+	{ INTEL_FAM6_HASWELL_G, &hswg_features },
+	{ INTEL_FAM6_BROADWELL, &bdw_features },
+	{ INTEL_FAM6_BROADWELL_G, &bdwg_features },
+	{ INTEL_FAM6_BROADWELL_X, &bdx_features },
+	{ INTEL_FAM6_BROADWELL_D, &bdx_features },
+	{ INTEL_FAM6_SKYLAKE_L, &skl_features },
+	{ INTEL_FAM6_SKYLAKE, &skl_features },
+	{ INTEL_FAM6_SKYLAKE_X, &skx_features },
+	{ INTEL_FAM6_KABYLAKE_L, &skl_features },
+	{ INTEL_FAM6_KABYLAKE, &skl_features },
+	{ INTEL_FAM6_COMETLAKE, &skl_features },
+	{ INTEL_FAM6_COMETLAKE_L, &skl_features },
+	{ INTEL_FAM6_CANNONLAKE_L, &cnl_features },
+	{ INTEL_FAM6_ICELAKE_X, &icx_features },
+	{ INTEL_FAM6_ICELAKE_D, &icx_features },
+	{ INTEL_FAM6_ICELAKE_L, &cnl_features },
+	{ INTEL_FAM6_ICELAKE_NNPI, &cnl_features },
+	{ INTEL_FAM6_ROCKETLAKE, &cnl_features },
+	{ INTEL_FAM6_TIGERLAKE_L, &cnl_features },
+	{ INTEL_FAM6_TIGERLAKE, &cnl_features },
+	{ INTEL_FAM6_SAPPHIRERAPIDS_X, &spr_features },
+	{ INTEL_FAM6_EMERALDRAPIDS_X, &spr_features },
+	{ INTEL_FAM6_GRANITERAPIDS_X, &spr_features },
+	{ INTEL_FAM6_LAKEFIELD, &cnl_features },
+	{ INTEL_FAM6_ALDERLAKE, &adl_features },
+	{ INTEL_FAM6_ALDERLAKE_L, &adl_features },
+	{ INTEL_FAM6_RAPTORLAKE, &adl_features },
+	{ INTEL_FAM6_RAPTORLAKE_P, &adl_features },
+	{ INTEL_FAM6_RAPTORLAKE_S, &adl_features },
+	{ INTEL_FAM6_METEORLAKE, &cnl_features },
+	{ INTEL_FAM6_METEORLAKE_L, &cnl_features },
+	{ INTEL_FAM6_ARROWLAKE, &cnl_features },
+	{ INTEL_FAM6_LUNARLAKE_M, &cnl_features },
+	{ INTEL_FAM6_ATOM_SILVERMONT, &slv_features },
+	{ INTEL_FAM6_ATOM_SILVERMONT_D, &slvd_features },
+	{ INTEL_FAM6_ATOM_AIRMONT, &amt_features },
+	{ INTEL_FAM6_ATOM_GOLDMONT, &gmt_features },
+	{ INTEL_FAM6_ATOM_GOLDMONT_D, &gmtd_features },
+	{ INTEL_FAM6_ATOM_GOLDMONT_PLUS, &gmtp_features },
+	{ INTEL_FAM6_ATOM_TREMONT_D, &tmtd_features },
+	{ INTEL_FAM6_ATOM_TREMONT, &tmt_features },
+	{ INTEL_FAM6_ATOM_TREMONT_L, &tmt_features },
+	{ INTEL_FAM6_ATOM_GRACEMONT, &adl_features },
+	{ INTEL_FAM6_ATOM_CRESTMONT_X, &srf_features },
+	{ INTEL_FAM6_ATOM_CRESTMONT, &grr_features },
+	{ INTEL_FAM6_XEON_PHI_KNL, &knl_features },
+	{ INTEL_FAM6_XEON_PHI_KNM, &knl_features },
+	/*
+	 * Missing support for
+	 * INTEL_FAM6_ICELAKE
+	 * INTEL_FAM6_ATOM_SILVERMONT_MID
+	 * INTEL_FAM6_ATOM_AIRMONT_MID
+	 * INTEL_FAM6_ATOM_AIRMONT_NP
+	 */
+	{ 0, NULL },
+};
+
+static const struct platform_features *platform;
+
+void probe_platform_features(unsigned int family, unsigned int model)
+{
+	int i;
+
+	platform = &default_features;
+
+	if (authentic_amd || hygon_genuine) {
+		if (max_extended_level >= 0x80000007) {
+			unsigned int eax, ebx, ecx, edx;
+
+			__cpuid(0x80000007, eax, ebx, ecx, edx);
+			/* RAPL (Fam 17h+) */
+			if ((edx & (1 << 14)) && family >= 0x17)
+				platform = &amd_features_with_rapl;
+		}
+		return;
+	}
+
+	if (!genuine_intel || family != 6)
+		return;
+
+	for (i = 0; turbostat_pdata[i].features; i++) {
+		if (turbostat_pdata[i].model == model) {
+			platform = turbostat_pdata[i].features;
+			return;
+		}
+	}
+}
+
+/* Model specific support End */
+
 #define	TJMAX_DEFAULT	100
 
 /* MSRs that are not yet in the kernel-provided header. */
@@ -333,8 +942,8 @@ int backwards_count;
 char *progname;
 
 #define CPU_SUBSET_MAXCPUS	1024	/* need to use before probe... */
-cpu_set_t *cpu_present_set, *cpu_affinity_set, *cpu_subset;
-size_t cpu_present_setsize, cpu_affinity_setsize, cpu_subset_size;
+cpu_set_t *cpu_present_set, *cpu_effective_set, *cpu_allowed_set, *cpu_affinity_set, *cpu_subset;
+size_t cpu_present_setsize, cpu_effective_setsize, cpu_allowed_setsize, cpu_affinity_setsize, cpu_subset_size;
 #define MAX_ADDED_COUNTERS 8
 #define MAX_ADDED_THREAD_COUNTERS 24
 #define BITMASK_SIZE 32
@@ -355,12 +964,11 @@ struct thread_data {
 	unsigned int x2apic_id;
 	unsigned int flags;
 	bool is_atom;
-#define CPU_IS_FIRST_THREAD_IN_CORE	0x2
-#define CPU_IS_FIRST_CORE_IN_PACKAGE	0x4
 	unsigned long long counter[MAX_ADDED_THREAD_COUNTERS];
 } *thread_even, *thread_odd;
 
 struct core_data {
+	int base_cpu;
 	unsigned long long c3;
 	unsigned long long c6;
 	unsigned long long c7;
@@ -373,6 +981,7 @@ struct core_data {
 } *core_even, *core_odd;
 
 struct pkg_data {
+	int base_cpu;
 	unsigned long long pc2;
 	unsigned long long pc3;
 	unsigned long long pc6;
@@ -456,7 +1065,7 @@ off_t idx_to_offset(int idx)
 
 	switch (idx) {
 	case IDX_PKG_ENERGY:
-		if (do_rapl & RAPL_AMD_F17H)
+		if (platform->rapl_msrs & RAPL_AMD_F17H)
 			offset = MSR_PKG_ENERGY_STAT;
 		else
 			offset = MSR_PKG_ENERGY_STATUS;
@@ -516,17 +1125,17 @@ int idx_valid(int idx)
 {
 	switch (idx) {
 	case IDX_PKG_ENERGY:
-		return do_rapl & (RAPL_PKG | RAPL_AMD_F17H);
+		return platform->rapl_msrs & (RAPL_PKG | RAPL_AMD_F17H);
 	case IDX_DRAM_ENERGY:
-		return do_rapl & RAPL_DRAM;
+		return platform->rapl_msrs & RAPL_DRAM;
 	case IDX_PP0_ENERGY:
-		return do_rapl & RAPL_CORES_ENERGY_STATUS;
+		return platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS;
 	case IDX_PP1_ENERGY:
-		return do_rapl & RAPL_GFX;
+		return platform->rapl_msrs & RAPL_GFX;
 	case IDX_PKG_PERF:
-		return do_rapl & RAPL_PKG_PERF_STATUS;
+		return platform->rapl_msrs & RAPL_PKG_PERF_STATUS;
 	case IDX_DRAM_PERF:
-		return do_rapl & RAPL_DRAM_PERF_STATUS;
+		return platform->rapl_msrs & RAPL_DRAM_PERF_STATUS;
 	default:
 		return 0;
 	}
@@ -563,6 +1172,9 @@ struct topo_params {
 	int num_die;
 	int num_cpus;
 	int num_cores;
+	int allowed_packages;
+	int allowed_cpus;
+	int allowed_cores;
 	int max_cpu_num;
 	int max_node_num;
 	int nodes_per_pkg;
@@ -575,7 +1187,7 @@ struct timeval tv_even, tv_odd, tv_delta;
 int *irq_column_2_cpu;		/* /proc/interrupts column numbers */
 int *irqs_per_cpu;		/* indexed by cpu_num */
 
-void setup_all_buffers(void);
+void setup_all_buffers(bool startup);
 
 char *sys_lpi_file;
 char *sys_lpi_file_sysfs = "/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us";
@@ -586,6 +1198,11 @@ int cpu_is_not_present(int cpu)
 	return !CPU_ISSET_S(cpu, cpu_present_setsize, cpu_present_set);
 }
 
+int cpu_is_not_allowed(int cpu)
+{
+	return !CPU_ISSET_S(cpu, cpu_allowed_setsize, cpu_allowed_set);
+}
+
 /*
  * run func(thread, core, package) in topology order
  * skip non-present cpus
@@ -603,10 +1220,9 @@ int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pk
 					struct thread_data *t;
 					struct core_data *c;
 					struct pkg_data *p;
-
 					t = GET_THREAD(thread_base, thread_no, core_no, node_no, pkg_no);
 
-					if (cpu_is_not_present(t->cpu_id))
+					if (cpu_is_not_allowed(t->cpu_id))
 						continue;
 
 					c = GET_CORE(core_base, core_no, node_no, pkg_no);
@@ -622,6 +1238,25 @@ int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pk
 	return 0;
 }
 
+int is_cpu_first_thread_in_core(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+	UNUSED(p);
+
+	return ((int)t->cpu_id == c->base_cpu || c->base_cpu < 0);
+}
+
+int is_cpu_first_core_in_package(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+	UNUSED(c);
+
+	return ((int)t->cpu_id == p->base_cpu || p->base_cpu < 0);
+}
+
+int is_cpu_first_thread_in_package(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+	return is_cpu_first_thread_in_core(t, c, p) && is_cpu_first_core_in_package(t, c, p);
+}
+
 int cpu_migrate(int cpu)
 {
 	CPU_ZERO_S(cpu_affinity_setsize, cpu_affinity_set);
@@ -904,11 +1539,11 @@ void print_header(char *delim)
 	if (DO_BIC(BIC_CORE_THROT_CNT))
 		outp += sprintf(outp, "%sCoreThr", (printed++ ? delim : ""));
 
-	if (do_rapl && !rapl_joules) {
-		if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY))
+	if (platform->rapl_msrs && !rapl_joules) {
+		if (DO_BIC(BIC_CorWatt) && platform->has_per_core_rapl)
 			outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : ""));
-	} else if (do_rapl && rapl_joules) {
-		if (DO_BIC(BIC_Cor_J) && (do_rapl & RAPL_PER_CORE_ENERGY))
+	} else if (platform->rapl_msrs && rapl_joules) {
+		if (DO_BIC(BIC_Cor_J) && platform->has_per_core_rapl)
 			outp += sprintf(outp, "%sCor_J", (printed++ ? delim : ""));
 	}
 
@@ -966,10 +1601,10 @@ void print_header(char *delim)
 	if (DO_BIC(BIC_SYS_LPI))
 		outp += sprintf(outp, "%sSYS%%LPI", (printed++ ? delim : ""));
 
-	if (do_rapl && !rapl_joules) {
+	if (platform->rapl_msrs && !rapl_joules) {
 		if (DO_BIC(BIC_PkgWatt))
 			outp += sprintf(outp, "%sPkgWatt", (printed++ ? delim : ""));
-		if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY))
+		if (DO_BIC(BIC_CorWatt) && !platform->has_per_core_rapl)
 			outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_GFXWatt))
 			outp += sprintf(outp, "%sGFXWatt", (printed++ ? delim : ""));
@@ -979,10 +1614,10 @@ void print_header(char *delim)
 			outp += sprintf(outp, "%sPKG_%%", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_RAM__))
 			outp += sprintf(outp, "%sRAM_%%", (printed++ ? delim : ""));
-	} else if (do_rapl && rapl_joules) {
+	} else if (platform->rapl_msrs && rapl_joules) {
 		if (DO_BIC(BIC_Pkg_J))
 			outp += sprintf(outp, "%sPkg_J", (printed++ ? delim : ""));
-		if (DO_BIC(BIC_Cor_J) && !(do_rapl & RAPL_PER_CORE_ENERGY))
+		if (DO_BIC(BIC_Cor_J) && !platform->has_per_core_rapl)
 			outp += sprintf(outp, "%sCor_J", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_GFX_J))
 			outp += sprintf(outp, "%sGFX_J", (printed++ ? delim : ""));
@@ -1106,11 +1741,11 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	int printed = 0;
 
 	/* if showing only 1st thread in core and this isn't one, bail out */
-	if (show_core_only && !(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
+	if (show_core_only && !is_cpu_first_thread_in_core(t, c, p))
 		return 0;
 
 	/* if showing only 1st thread in pkg and this isn't one, bail out */
-	if (show_pkg_only && !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+	if (show_pkg_only && !is_cpu_first_core_in_package(t, c, p))
 		return 0;
 
 	/*if not summary line and --cpu is used */
@@ -1244,7 +1879,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * t->c1 / tsc);
 
 	/* print per-core data only for 1st thread in core */
-	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
+	if (!is_cpu_first_thread_in_core(t, c, p))
 		goto done;
 
 	if (DO_BIC(BIC_CPU_c3))
@@ -1284,14 +1919,14 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 
 	fmt8 = "%s%.2f";
 
-	if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY))
+	if (DO_BIC(BIC_CorWatt) && platform->has_per_core_rapl)
 		outp +=
 		    sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float);
-	if (DO_BIC(BIC_Cor_J) && (do_rapl & RAPL_PER_CORE_ENERGY))
+	if (DO_BIC(BIC_Cor_J) && platform->has_per_core_rapl)
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units);
 
 	/* print per-package data only for 1st core in package */
-	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+	if (!is_cpu_first_core_in_package(t, c, p))
 		goto done;
 
 	/* PkgTmp */
@@ -1352,7 +1987,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 		outp +=
 		    sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units / interval_float);
 
-	if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY))
+	if (DO_BIC(BIC_CorWatt) && !platform->has_per_core_rapl)
 		outp +=
 		    sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units / interval_float);
 	if (DO_BIC(BIC_GFXWatt))
@@ -1364,7 +1999,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 			    p->energy_dram * rapl_dram_energy_units / interval_float);
 	if (DO_BIC(BIC_Pkg_J))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units);
-	if (DO_BIC(BIC_Cor_J) && !(do_rapl & RAPL_PER_CORE_ENERGY))
+	if (DO_BIC(BIC_Cor_J) && !platform->has_per_core_rapl)
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units);
 	if (DO_BIC(BIC_GFX_J))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units);
@@ -1527,7 +2162,7 @@ void delta_core(struct core_data *new, struct core_data *old)
 
 int soft_c1_residency_display(int bic)
 {
-	if (!DO_BIC(BIC_CPU_c1) || use_c1_residency_msr)
+	if (!DO_BIC(BIC_CPU_c1) || platform->has_msr_core_c1_res)
 		return 0;
 
 	return DO_BIC_READ(bic);
@@ -1567,7 +2202,8 @@ int delta_thread(struct thread_data *new, struct thread_data *old, struct core_d
 
 	old->c1 = new->c1 - old->c1;
 
-	if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || soft_c1_residency_display(BIC_Avg_MHz)) {
+	if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || DO_BIC(BIC_IPC)
+	    || soft_c1_residency_display(BIC_Avg_MHz)) {
 		if ((new->aperf > old->aperf) && (new->mperf > old->mperf)) {
 			old->aperf = new->aperf - old->aperf;
 			old->mperf = new->mperf - old->mperf;
@@ -1576,7 +2212,7 @@ int delta_thread(struct thread_data *new, struct thread_data *old, struct core_d
 		}
 	}
 
-	if (use_c1_residency_msr) {
+	if (platform->has_msr_core_c1_res) {
 		/*
 		 * Some models have a dedicated C1 residency MSR,
 		 * which should be more accurate than the derivation below.
@@ -1626,7 +2262,7 @@ int delta_cpu(struct thread_data *t, struct core_data *c,
 	int retval = 0;
 
 	/* calculate core delta only for 1st thread in core */
-	if (t->flags & CPU_IS_FIRST_THREAD_IN_CORE)
+	if (is_cpu_first_thread_in_core(t, c, p))
 		delta_core(c, c2);
 
 	/* always calculate thread delta */
@@ -1635,7 +2271,7 @@ int delta_cpu(struct thread_data *t, struct core_data *c,
 		return retval;
 
 	/* calculate package delta only for 1st core in package */
-	if (t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)
+	if (is_cpu_first_core_in_package(t, c, p))
 		retval = delta_package(p, p2);
 
 	return retval;
@@ -1663,9 +2299,6 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	t->irq_count = 0;
 	t->smi_count = 0;
 
-	/* tells format_counters to dump all fields from this set */
-	t->flags = CPU_IS_FIRST_THREAD_IN_CORE | CPU_IS_FIRST_CORE_IN_PACKAGE;
-
 	c->c3 = 0;
 	c->c6 = 0;
 	c->c7 = 0;
@@ -1749,7 +2382,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	}
 
 	/* sum per-core values only for 1st thread in core */
-	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
+	if (!is_cpu_first_thread_in_core(t, c, p))
 		return 0;
 
 	average.cores.c3 += c->c3;
@@ -1769,7 +2402,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	}
 
 	/* sum per-pkg values only for 1st core in pkg */
-	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+	if (!is_cpu_first_core_in_package(t, c, p))
 		return 0;
 
 	if (DO_BIC(BIC_Totl_c0))
@@ -1834,40 +2467,40 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data
 	/* Use the global time delta for the average. */
 	average.threads.tv_delta = tv_delta;
 
-	average.threads.tsc /= topo.num_cpus;
-	average.threads.aperf /= topo.num_cpus;
-	average.threads.mperf /= topo.num_cpus;
-	average.threads.instr_count /= topo.num_cpus;
-	average.threads.c1 /= topo.num_cpus;
+	average.threads.tsc /= topo.allowed_cpus;
+	average.threads.aperf /= topo.allowed_cpus;
+	average.threads.mperf /= topo.allowed_cpus;
+	average.threads.instr_count /= topo.allowed_cpus;
+	average.threads.c1 /= topo.allowed_cpus;
 
 	if (average.threads.irq_count > 9999999)
 		sums_need_wide_columns = 1;
 
-	average.cores.c3 /= topo.num_cores;
-	average.cores.c6 /= topo.num_cores;
-	average.cores.c7 /= topo.num_cores;
-	average.cores.mc6_us /= topo.num_cores;
+	average.cores.c3 /= topo.allowed_cores;
+	average.cores.c6 /= topo.allowed_cores;
+	average.cores.c7 /= topo.allowed_cores;
+	average.cores.mc6_us /= topo.allowed_cores;
 
 	if (DO_BIC(BIC_Totl_c0))
-		average.packages.pkg_wtd_core_c0 /= topo.num_packages;
+		average.packages.pkg_wtd_core_c0 /= topo.allowed_packages;
 	if (DO_BIC(BIC_Any_c0))
-		average.packages.pkg_any_core_c0 /= topo.num_packages;
+		average.packages.pkg_any_core_c0 /= topo.allowed_packages;
 	if (DO_BIC(BIC_GFX_c0))
-		average.packages.pkg_any_gfxe_c0 /= topo.num_packages;
+		average.packages.pkg_any_gfxe_c0 /= topo.allowed_packages;
 	if (DO_BIC(BIC_CPUGFX))
-		average.packages.pkg_both_core_gfxe_c0 /= topo.num_packages;
+		average.packages.pkg_both_core_gfxe_c0 /= topo.allowed_packages;
 
-	average.packages.pc2 /= topo.num_packages;
+	average.packages.pc2 /= topo.allowed_packages;
 	if (DO_BIC(BIC_Pkgpc3))
-		average.packages.pc3 /= topo.num_packages;
+		average.packages.pc3 /= topo.allowed_packages;
 	if (DO_BIC(BIC_Pkgpc6))
-		average.packages.pc6 /= topo.num_packages;
+		average.packages.pc6 /= topo.allowed_packages;
 	if (DO_BIC(BIC_Pkgpc7))
-		average.packages.pc7 /= topo.num_packages;
+		average.packages.pc7 /= topo.allowed_packages;
 
-	average.packages.pc8 /= topo.num_packages;
-	average.packages.pc9 /= topo.num_packages;
-	average.packages.pc10 /= topo.num_packages;
+	average.packages.pc8 /= topo.allowed_packages;
+	average.packages.pc9 /= topo.allowed_packages;
+	average.packages.pc10 /= topo.allowed_packages;
 
 	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
@@ -1877,7 +2510,7 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data
 				sums_need_wide_columns = 1;
 			continue;
 		}
-		average.threads.counter[i] /= topo.num_cpus;
+		average.threads.counter[i] /= topo.allowed_cpus;
 	}
 	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
@@ -1886,7 +2519,7 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data
 			if (average.cores.counter[i] > 9999999)
 				sums_need_wide_columns = 1;
 		}
-		average.cores.counter[i] /= topo.num_cores;
+		average.cores.counter[i] /= topo.allowed_cores;
 	}
 	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
@@ -1895,7 +2528,7 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data
 			if (average.packages.counter[i] > 9999999)
 				sums_need_wide_columns = 1;
 		}
-		average.packages.counter[i] /= topo.num_packages;
+		average.packages.counter[i] /= topo.allowed_packages;
 	}
 }
 
@@ -2092,7 +2725,8 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 retry:
 	t->tsc = rdtsc();	/* we are running on local CPU of interest */
 
-	if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || soft_c1_residency_display(BIC_Avg_MHz)) {
+	if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || DO_BIC(BIC_IPC)
+	    || soft_c1_residency_display(BIC_Avg_MHz)) {
 		unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time;
 
 		/*
@@ -2158,7 +2792,7 @@ retry:
 			return -5;
 		t->smi_count = msr & 0xFFFFFFFF;
 	}
-	if (DO_BIC(BIC_CPU_c1) && use_c1_residency_msr) {
+	if (DO_BIC(BIC_CPU_c1) && platform->has_msr_core_c1_res) {
 		if (get_msr(cpu, MSR_CORE_C1_RES, &t->c1))
 			return -6;
 	}
@@ -2169,7 +2803,7 @@ retry:
 	}
 
 	/* collect core counters only for 1st thread in core */
-	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
+	if (!is_cpu_first_thread_in_core(t, c, p))
 		goto done;
 
 	if (DO_BIC(BIC_CPU_c3) || soft_c1_residency_display(BIC_CPU_c3)) {
@@ -2177,10 +2811,10 @@ retry:
 			return -6;
 	}
 
-	if ((DO_BIC(BIC_CPU_c6) || soft_c1_residency_display(BIC_CPU_c6)) && !do_knl_cstates) {
+	if ((DO_BIC(BIC_CPU_c6) || soft_c1_residency_display(BIC_CPU_c6)) && !platform->has_msr_knl_core_c6_residency) {
 		if (get_msr(cpu, MSR_CORE_C6_RESIDENCY, &c->c6))
 			return -7;
-	} else if (do_knl_cstates || soft_c1_residency_display(BIC_CPU_c6)) {
+	} else if (platform->has_msr_knl_core_c6_residency && soft_c1_residency_display(BIC_CPU_c6)) {
 		if (get_msr(cpu, MSR_KNL_CORE_C6_RESIDENCY, &c->c6))
 			return -7;
 	}
@@ -2212,7 +2846,7 @@ retry:
 	if (DO_BIC(BIC_CORE_THROT_CNT))
 		get_core_throt_cnt(cpu, &c->core_throt_cnt);
 
-	if (do_rapl & RAPL_AMD_F17H) {
+	if (platform->rapl_msrs & RAPL_AMD_F17H) {
 		if (get_msr(cpu, MSR_CORE_ENERGY_STAT, &msr))
 			return -14;
 		c->core_energy = msr & 0xFFFFFFFF;
@@ -2224,7 +2858,7 @@ retry:
 	}
 
 	/* collect package counters only for 1st core in package */
-	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+	if (!is_cpu_first_core_in_package(t, c, p))
 		goto done;
 
 	if (DO_BIC(BIC_Totl_c0)) {
@@ -2247,7 +2881,7 @@ retry:
 		if (get_msr(cpu, MSR_PKG_C3_RESIDENCY, &p->pc3))
 			return -9;
 	if (DO_BIC(BIC_Pkgpc6)) {
-		if (do_slm_cstates) {
+		if (platform->has_msr_atom_pkg_c6_residency) {
 			if (get_msr(cpu, MSR_ATOM_PKG_C6_RESIDENCY, &p->pc6))
 				return -10;
 		} else {
@@ -2277,37 +2911,37 @@ retry:
 	if (DO_BIC(BIC_SYS_LPI))
 		p->sys_lpi = cpuidle_cur_sys_lpi_us;
 
-	if (do_rapl & RAPL_PKG) {
+	if (platform->rapl_msrs & RAPL_PKG) {
 		if (get_msr_sum(cpu, MSR_PKG_ENERGY_STATUS, &msr))
 			return -13;
 		p->energy_pkg = msr;
 	}
-	if (do_rapl & RAPL_CORES_ENERGY_STATUS) {
+	if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS) {
 		if (get_msr_sum(cpu, MSR_PP0_ENERGY_STATUS, &msr))
 			return -14;
 		p->energy_cores = msr;
 	}
-	if (do_rapl & RAPL_DRAM) {
+	if (platform->rapl_msrs & RAPL_DRAM) {
 		if (get_msr_sum(cpu, MSR_DRAM_ENERGY_STATUS, &msr))
 			return -15;
 		p->energy_dram = msr;
 	}
-	if (do_rapl & RAPL_GFX) {
+	if (platform->rapl_msrs & RAPL_GFX) {
 		if (get_msr_sum(cpu, MSR_PP1_ENERGY_STATUS, &msr))
 			return -16;
 		p->energy_gfx = msr;
 	}
-	if (do_rapl & RAPL_PKG_PERF_STATUS) {
+	if (platform->rapl_msrs & RAPL_PKG_PERF_STATUS) {
 		if (get_msr_sum(cpu, MSR_PKG_PERF_STATUS, &msr))
 			return -16;
 		p->rapl_pkg_perf_status = msr;
 	}
-	if (do_rapl & RAPL_DRAM_PERF_STATUS) {
+	if (platform->rapl_msrs & RAPL_DRAM_PERF_STATUS) {
 		if (get_msr_sum(cpu, MSR_DRAM_PERF_STATUS, &msr))
 			return -16;
 		p->rapl_dram_perf_status = msr;
 	}
-	if (do_rapl & RAPL_AMD_F17H) {
+	if (platform->rapl_msrs & RAPL_AMD_F17H) {
 		if (get_msr_sum(cpu, MSR_PKG_ENERGY_STAT, &msr))
 			return -13;
 		p->energy_pkg = msr;
@@ -2414,18 +3048,58 @@ int icx_pkg_cstate_limits[16] =
 	PCLRSV, PCLRSV
 };
 
-static void calculate_tsc_tweak()
+void probe_cst_limit(void)
 {
-	tsc_tweak = base_hz / tsc_hz;
-}
+	unsigned long long msr;
+	int *pkg_cstate_limits;
+
+	if (!platform->has_nhm_msrs)
+		return;
+
+	switch (platform->cst_limit) {
+	case CST_LIMIT_NHM:
+		pkg_cstate_limits = nhm_pkg_cstate_limits;
+		break;
+	case CST_LIMIT_SNB:
+		pkg_cstate_limits = snb_pkg_cstate_limits;
+		break;
+	case CST_LIMIT_HSW:
+		pkg_cstate_limits = hsw_pkg_cstate_limits;
+		break;
+	case CST_LIMIT_SKX:
+		pkg_cstate_limits = skx_pkg_cstate_limits;
+		break;
+	case CST_LIMIT_ICX:
+		pkg_cstate_limits = icx_pkg_cstate_limits;
+		break;
+	case CST_LIMIT_SLV:
+		pkg_cstate_limits = slv_pkg_cstate_limits;
+		break;
+	case CST_LIMIT_AMT:
+		pkg_cstate_limits = amt_pkg_cstate_limits;
+		break;
+	case CST_LIMIT_KNL:
+		pkg_cstate_limits = phi_pkg_cstate_limits;
+		break;
+	case CST_LIMIT_GMT:
+		pkg_cstate_limits = glm_pkg_cstate_limits;
+		break;
+	default:
+		return;
+	}
 
-void prewake_cstate_probe(unsigned int family, unsigned int model);
+	get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr);
+	pkg_cstate_limit = pkg_cstate_limits[msr & 0xF];
+}
 
-static void dump_nhm_platform_info(void)
+static void dump_platform_info(void)
 {
 	unsigned long long msr;
 	unsigned int ratio;
 
+	if (!platform->has_nhm_msrs)
+		return;
+
 	get_msr(base_cpu, MSR_PLATFORM_INFO, &msr);
 
 	fprintf(outf, "cpu%d: MSR_PLATFORM_INFO: 0x%08llx\n", base_cpu, msr);
@@ -2435,19 +3109,27 @@ static void dump_nhm_platform_info(void)
 
 	ratio = (msr >> 8) & 0xFF;
 	fprintf(outf, "%d * %.1f = %.1f MHz base frequency\n", ratio, bclk, ratio * bclk);
+}
+
+static void dump_power_ctl(void)
+{
+	unsigned long long msr;
+
+	if (!platform->has_nhm_msrs)
+		return;
 
 	get_msr(base_cpu, MSR_IA32_POWER_CTL, &msr);
 	fprintf(outf, "cpu%d: MSR_IA32_POWER_CTL: 0x%08llx (C1E auto-promotion: %sabled)\n",
 		base_cpu, msr, msr & 0x2 ? "EN" : "DIS");
 
 	/* C-state Pre-wake Disable (CSTATE_PREWAKE_DISABLE) */
-	if (dis_cstate_prewake)
+	if (platform->has_cst_prewake_bit)
 		fprintf(outf, "C-state Pre-wake: %sabled\n", msr & 0x40000000 ? "DIS" : "EN");
 
 	return;
 }
 
-static void dump_hsw_turbo_ratio_limits(void)
+static void dump_turbo_ratio_limit2(void)
 {
 	unsigned long long msr;
 	unsigned int ratio;
@@ -2466,7 +3148,7 @@ static void dump_hsw_turbo_ratio_limits(void)
 	return;
 }
 
-static void dump_ivt_turbo_ratio_limits(void)
+static void dump_turbo_ratio_limit1(void)
 {
 	unsigned long long msr;
 	unsigned int ratio;
@@ -2509,29 +3191,7 @@ static void dump_ivt_turbo_ratio_limits(void)
 	return;
 }
 
-int has_turbo_ratio_group_limits(int family, int model)
-{
-
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_ATOM_GOLDMONT:
-	case INTEL_FAM6_SKYLAKE_X:
-	case INTEL_FAM6_ICELAKE_X:
-	case INTEL_FAM6_SAPPHIRERAPIDS_X:
-	case INTEL_FAM6_ATOM_GOLDMONT_D:
-	case INTEL_FAM6_ATOM_TREMONT_D:
-		return 1;
-	default:
-		return 0;
-	}
-}
-
-static void dump_turbo_ratio_limits(int trl_msr_offset, int family, int model)
+static void dump_turbo_ratio_limits(int trl_msr_offset)
 {
 	unsigned long long msr, core_counts;
 	int shift;
@@ -2540,7 +3200,7 @@ static void dump_turbo_ratio_limits(int trl_msr_offset, int family, int model)
 	fprintf(outf, "cpu%d: MSR_%sTURBO_RATIO_LIMIT: 0x%08llx\n",
 		base_cpu, trl_msr_offset == MSR_SECONDARY_TURBO_RATIO_LIMIT ? "SECONDARY_" : "", msr);
 
-	if (has_turbo_ratio_group_limits(family, model)) {
+	if (platform->trl_msrs & TRL_CORECOUNT) {
 		get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT1, &core_counts);
 		fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT1: 0x%08llx\n", base_cpu, core_counts);
 	} else {
@@ -2657,10 +3317,13 @@ static void dump_knl_turbo_ratio_limits(void)
 				ratio[i], bclk, ratio[i] * bclk, cores[i]);
 }
 
-static void dump_nhm_cst_cfg(void)
+static void dump_cst_cfg(void)
 {
 	unsigned long long msr;
 
+	if (!platform->has_nhm_msrs)
+		return;
+
 	get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr);
 
 	fprintf(outf, "cpu%d: MSR_PKG_CST_CONFIG_CONTROL: 0x%08llx", base_cpu, msr);
@@ -2673,7 +3336,7 @@ static void dump_nhm_cst_cfg(void)
 		(msr & (1 << 15)) ? "" : "UN", (unsigned int)msr & 0xF, pkg_cstate_limit_strings[pkg_cstate_limit]);
 
 #define AUTOMATIC_CSTATE_CONVERSION		(1UL << 16)
-	if (has_automatic_cstate_conversion) {
+	if (platform->has_cst_auto_convension) {
 		fprintf(outf, ", automatic c-state conversion=%s", (msr & AUTOMATIC_CSTATE_CONVERSION) ? "on" : "off");
 	}
 
@@ -2730,39 +3393,50 @@ void print_irtl(void)
 {
 	unsigned long long msr;
 
-	get_msr(base_cpu, MSR_PKGC3_IRTL, &msr);
-	fprintf(outf, "cpu%d: MSR_PKGC3_IRTL: 0x%08llx (", base_cpu, msr);
-	fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
-		(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
-
-	get_msr(base_cpu, MSR_PKGC6_IRTL, &msr);
-	fprintf(outf, "cpu%d: MSR_PKGC6_IRTL: 0x%08llx (", base_cpu, msr);
-	fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
-		(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	if (!platform->has_irtl_msrs)
+		return;
 
-	get_msr(base_cpu, MSR_PKGC7_IRTL, &msr);
-	fprintf(outf, "cpu%d: MSR_PKGC7_IRTL: 0x%08llx (", base_cpu, msr);
-	fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
-		(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	if (platform->supported_cstates & PC3) {
+		get_msr(base_cpu, MSR_PKGC3_IRTL, &msr);
+		fprintf(outf, "cpu%d: MSR_PKGC3_IRTL: 0x%08llx (", base_cpu, msr);
+		fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+			(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	}
 
-	if (!do_irtl_hsw)
-		return;
+	if (platform->supported_cstates & PC6) {
+		get_msr(base_cpu, MSR_PKGC6_IRTL, &msr);
+		fprintf(outf, "cpu%d: MSR_PKGC6_IRTL: 0x%08llx (", base_cpu, msr);
+		fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+			(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	}
 
-	get_msr(base_cpu, MSR_PKGC8_IRTL, &msr);
-	fprintf(outf, "cpu%d: MSR_PKGC8_IRTL: 0x%08llx (", base_cpu, msr);
-	fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
-		(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	if (platform->supported_cstates & PC7) {
+		get_msr(base_cpu, MSR_PKGC7_IRTL, &msr);
+		fprintf(outf, "cpu%d: MSR_PKGC7_IRTL: 0x%08llx (", base_cpu, msr);
+		fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+			(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	}
 
-	get_msr(base_cpu, MSR_PKGC9_IRTL, &msr);
-	fprintf(outf, "cpu%d: MSR_PKGC9_IRTL: 0x%08llx (", base_cpu, msr);
-	fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
-		(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	if (platform->supported_cstates & PC8) {
+		get_msr(base_cpu, MSR_PKGC8_IRTL, &msr);
+		fprintf(outf, "cpu%d: MSR_PKGC8_IRTL: 0x%08llx (", base_cpu, msr);
+		fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+			(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	}
 
-	get_msr(base_cpu, MSR_PKGC10_IRTL, &msr);
-	fprintf(outf, "cpu%d: MSR_PKGC10_IRTL: 0x%08llx (", base_cpu, msr);
-	fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
-		(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	if (platform->supported_cstates & PC9) {
+		get_msr(base_cpu, MSR_PKGC9_IRTL, &msr);
+		fprintf(outf, "cpu%d: MSR_PKGC9_IRTL: 0x%08llx (", base_cpu, msr);
+		fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+			(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	}
 
+	if (platform->supported_cstates & PC10) {
+		get_msr(base_cpu, MSR_PKGC10_IRTL, &msr);
+		fprintf(outf, "cpu%d: MSR_PKGC10_IRTL: 0x%08llx (", base_cpu, msr);
+		fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+			(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	}
 }
 
 void free_fd_percpu(void)
@@ -2785,6 +3459,14 @@ void free_all_buffers(void)
 	cpu_present_set = NULL;
 	cpu_present_setsize = 0;
 
+	CPU_FREE(cpu_effective_set);
+	cpu_effective_set = NULL;
+	cpu_effective_setsize = 0;
+
+	CPU_FREE(cpu_allowed_set);
+	cpu_allowed_set = NULL;
+	cpu_allowed_setsize = 0;
+
 	CPU_FREE(cpu_affinity_set);
 	cpu_affinity_set = NULL;
 	cpu_affinity_setsize = 0;
@@ -2927,6 +3609,59 @@ int get_physical_node_id(struct cpu_topology *thiscpu)
 	return -1;
 }
 
+static int parse_cpu_str(char *cpu_str, cpu_set_t *cpu_set, int cpu_set_size)
+{
+	unsigned int start, end;
+	char *next = cpu_str;
+
+	while (next && *next) {
+
+		if (*next == '-')	/* no negative cpu numbers */
+			return 1;
+
+		start = strtoul(next, &next, 10);
+
+		if (start >= CPU_SUBSET_MAXCPUS)
+			return 1;
+		CPU_SET_S(start, cpu_set_size, cpu_set);
+
+		if (*next == '\0' || *next == '\n')
+			break;
+
+		if (*next == ',') {
+			next += 1;
+			continue;
+		}
+
+		if (*next == '-') {
+			next += 1;	/* start range */
+		} else if (*next == '.') {
+			next += 1;
+			if (*next == '.')
+				next += 1;	/* start range */
+			else
+				return 1;
+		}
+
+		end = strtoul(next, &next, 10);
+		if (end <= start)
+			return 1;
+
+		while (++start <= end) {
+			if (start >= CPU_SUBSET_MAXCPUS)
+				return 1;
+			CPU_SET_S(start, cpu_set_size, cpu_set);
+		}
+
+		if (*next == ',')
+			next += 1;
+		else if (*next != '\0' && *next != '\n')
+			return 1;
+	}
+
+	return 0;
+}
+
 int get_thread_siblings(struct cpu_topology *thiscpu)
 {
 	char path[80], character;
@@ -2998,7 +3733,7 @@ int for_all_cpus_2(int (func) (struct thread_data *, struct core_data *,
 
 					t = GET_THREAD(thread_base, thread_no, core_no, node_no, pkg_no);
 
-					if (cpu_is_not_present(t->cpu_id))
+					if (cpu_is_not_allowed(t->cpu_id))
 						continue;
 
 					t2 = GET_THREAD(thread_base2, thread_no, core_no, node_no, pkg_no);
@@ -3050,11 +3785,51 @@ int for_all_proc_cpus(int (func) (int))
 	return 0;
 }
 
+#define PATH_EFFECTIVE_CPUS	"/sys/fs/cgroup/cpuset.cpus.effective"
+
+static char cpu_effective_str[1024];
+
+static int update_effective_str(bool startup)
+{
+	FILE *fp;
+	char *pos;
+	char buf[1024];
+	int ret;
+
+	if (cpu_effective_str[0] == '\0' && !startup)
+		return 0;
+
+	fp = fopen(PATH_EFFECTIVE_CPUS, "r");
+	if (!fp)
+		return 0;
+
+	pos = fgets(buf, 1024, fp);
+	if (!pos)
+		err(1, "%s: file read failed\n", PATH_EFFECTIVE_CPUS);
+
+	fclose(fp);
+
+	ret = strncmp(cpu_effective_str, buf, 1024);
+	if (!ret)
+		return 0;
+
+	strncpy(cpu_effective_str, buf, 1024);
+	return 1;
+}
+
+static void update_effective_set(bool startup)
+{
+	update_effective_str(startup);
+
+	if (parse_cpu_str(cpu_effective_str, cpu_effective_set, cpu_effective_setsize))
+		err(1, "%s: cpu str malformat %s\n", PATH_EFFECTIVE_CPUS, cpu_effective_str);
+}
+
 void re_initialize(void)
 {
 	free_all_buffers();
-	setup_all_buffers();
-	fprintf(outf, "turbostat: re-initialized with num_cpus %d\n", topo.num_cpus);
+	setup_all_buffers(false);
+	fprintf(outf, "turbostat: re-initialized with num_cpus %d, allowed_cpus %d\n", topo.num_cpus, topo.allowed_cpus);
 }
 
 void set_max_cpu_num(void)
@@ -3191,8 +3966,8 @@ int snapshot_gfx_rc6_ms(void)
 /*
  * snapshot_gfx_mhz()
  *
- * record snapshot of
- * /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz
+ * fall back to /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz
+ * when /sys/class/drm/card0/gt_cur_freq_mhz is not available.
  *
  * return 1 if config change requires a restart, else return 0
  */
@@ -3201,9 +3976,11 @@ int snapshot_gfx_mhz(void)
 	static FILE *fp;
 	int retval;
 
-	if (fp == NULL)
-		fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", "r");
-	else {
+	if (fp == NULL) {
+		fp = fopen("/sys/class/drm/card0/gt_cur_freq_mhz", "r");
+		if (!fp)
+			fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", "r");
+	} else {
 		rewind(fp);
 		fflush(fp);
 	}
@@ -3218,8 +3995,8 @@ int snapshot_gfx_mhz(void)
 /*
  * snapshot_gfx_cur_mhz()
  *
- * record snapshot of
- * /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz
+ * fall back to /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz
+ * when /sys/class/drm/card0/gt_act_freq_mhz is not available.
  *
  * return 1 if config change requires a restart, else return 0
  */
@@ -3228,9 +4005,11 @@ int snapshot_gfx_act_mhz(void)
 	static FILE *fp;
 	int retval;
 
-	if (fp == NULL)
-		fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", "r");
-	else {
+	if (fp == NULL) {
+		fp = fopen("/sys/class/drm/card0/gt_act_freq_mhz", "r");
+		if (!fp)
+			fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", "r");
+	} else {
 		rewind(fp);
 		fflush(fp);
 	}
@@ -3562,6 +4341,10 @@ restart:
 			re_initialize();
 			goto restart;
 		}
+		if (update_effective_str(false)) {
+			re_initialize();
+			goto restart;
+		}
 		do_sleep();
 		if (snapshot_proc_sysfs_files())
 			goto restart;
@@ -3674,395 +4457,31 @@ void check_permissions(void)
 		exit(-6);
 }
 
-/*
- * NHM adds support for additional MSRs:
- *
- * MSR_SMI_COUNT                   0x00000034
- *
- * MSR_PLATFORM_INFO               0x000000ce
- * MSR_PKG_CST_CONFIG_CONTROL     0x000000e2
- *
- * MSR_MISC_PWR_MGMT               0x000001aa
- *
- * MSR_PKG_C3_RESIDENCY            0x000003f8
- * MSR_PKG_C6_RESIDENCY            0x000003f9
- * MSR_CORE_C3_RESIDENCY           0x000003fc
- * MSR_CORE_C6_RESIDENCY           0x000003fd
- *
- * Side effect:
- * sets global pkg_cstate_limit to decode MSR_PKG_CST_CONFIG_CONTROL
- * sets has_misc_feature_control
- */
-int probe_nhm_msrs(unsigned int family, unsigned int model)
+void probe_bclk(void)
 {
 	unsigned long long msr;
 	unsigned int base_ratio;
-	int *pkg_cstate_limits;
 
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	bclk = discover_bclk(family, model);
+	if (!platform->has_nhm_msrs)
+		return;
 
-	switch (model) {
-	case INTEL_FAM6_NEHALEM:	/* Core i7 and i5 Processor - Clarksfield, Lynnfield, Jasper Forest */
-	case INTEL_FAM6_NEHALEM_EX:	/* Nehalem-EX Xeon - Beckton */
-		pkg_cstate_limits = nhm_pkg_cstate_limits;
-		break;
-	case INTEL_FAM6_SANDYBRIDGE:	/* SNB */
-	case INTEL_FAM6_SANDYBRIDGE_X:	/* SNB Xeon */
-	case INTEL_FAM6_IVYBRIDGE:	/* IVB */
-	case INTEL_FAM6_IVYBRIDGE_X:	/* IVB Xeon */
-		pkg_cstate_limits = snb_pkg_cstate_limits;
-		has_misc_feature_control = 1;
-		break;
-	case INTEL_FAM6_HASWELL:	/* HSW */
-	case INTEL_FAM6_HASWELL_G:	/* HSW */
-	case INTEL_FAM6_HASWELL_X:	/* HSX */
-	case INTEL_FAM6_HASWELL_L:	/* HSW */
-	case INTEL_FAM6_BROADWELL:	/* BDW */
-	case INTEL_FAM6_BROADWELL_G:	/* BDW */
-	case INTEL_FAM6_BROADWELL_X:	/* BDX */
-	case INTEL_FAM6_SKYLAKE_L:	/* SKL */
-	case INTEL_FAM6_CANNONLAKE_L:	/* CNL */
-		pkg_cstate_limits = hsw_pkg_cstate_limits;
-		has_misc_feature_control = 1;
-		break;
-	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
-	case INTEL_FAM6_SAPPHIRERAPIDS_X:	/* SPR */
-		pkg_cstate_limits = skx_pkg_cstate_limits;
-		has_misc_feature_control = 1;
-		break;
-	case INTEL_FAM6_ICELAKE_X:	/* ICX */
-		pkg_cstate_limits = icx_pkg_cstate_limits;
-		has_misc_feature_control = 1;
-		break;
-	case INTEL_FAM6_ATOM_SILVERMONT:	/* BYT */
-		no_MSR_MISC_PWR_MGMT = 1;
-		/* FALLTHRU */
-	case INTEL_FAM6_ATOM_SILVERMONT_D:	/* AVN */
-		pkg_cstate_limits = slv_pkg_cstate_limits;
-		break;
-	case INTEL_FAM6_ATOM_AIRMONT:	/* AMT */
-		pkg_cstate_limits = amt_pkg_cstate_limits;
-		no_MSR_MISC_PWR_MGMT = 1;
-		break;
-	case INTEL_FAM6_XEON_PHI_KNL:	/* PHI */
-		pkg_cstate_limits = phi_pkg_cstate_limits;
-		break;
-	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
-	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
-	case INTEL_FAM6_ATOM_GOLDMONT_D:	/* DNV */
-	case INTEL_FAM6_ATOM_TREMONT:	/* EHL */
-	case INTEL_FAM6_ATOM_TREMONT_D:	/* JVL */
-		pkg_cstate_limits = glm_pkg_cstate_limits;
-		break;
-	default:
-		return 0;
-	}
-	get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr);
-	pkg_cstate_limit = pkg_cstate_limits[msr & 0xF];
+	if (platform->bclk_freq == BCLK_100MHZ)
+		bclk = 100.00;
+	else if (platform->bclk_freq == BCLK_133MHZ)
+		bclk = 133.33;
+	else if (platform->bclk_freq == BCLK_SLV)
+		bclk = slm_bclk();
+	else
+		return;
 
 	get_msr(base_cpu, MSR_PLATFORM_INFO, &msr);
 	base_ratio = (msr >> 8) & 0xFF;
 
 	base_hz = base_ratio * bclk * 1000000;
 	has_base_hz = 1;
-	return 1;
-}
-
-/*
- * SLV client has support for unique MSRs:
- *
- * MSR_CC6_DEMOTION_POLICY_CONFIG
- * MSR_MC6_DEMOTION_POLICY_CONFIG
- */
-
-int has_slv_msrs(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_ATOM_SILVERMONT:
-	case INTEL_FAM6_ATOM_SILVERMONT_MID:
-	case INTEL_FAM6_ATOM_AIRMONT_MID:
-		return 1;
-	}
-	return 0;
-}
-
-int is_dnv(unsigned int family, unsigned int model)
-{
-
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_ATOM_GOLDMONT_D:
-		return 1;
-	}
-	return 0;
-}
-
-int is_bdx(unsigned int family, unsigned int model)
-{
-
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_BROADWELL_X:
-		return 1;
-	}
-	return 0;
-}
-
-int is_skx(unsigned int family, unsigned int model)
-{
-
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_SKYLAKE_X:
-		return 1;
-	}
-	return 0;
-}
-
-int is_icx(unsigned int family, unsigned int model)
-{
-
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_ICELAKE_X:
-		return 1;
-	}
-	return 0;
-}
-
-int is_spr(unsigned int family, unsigned int model)
-{
-
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_SAPPHIRERAPIDS_X:
-		return 1;
-	}
-	return 0;
-}
-
-int is_ehl(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_ATOM_TREMONT:
-		return 1;
-	}
-	return 0;
-}
-
-int is_jvl(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_ATOM_TREMONT_D:
-		return 1;
-	}
-	return 0;
-}
-
-int has_turbo_ratio_limit(unsigned int family, unsigned int model)
-{
-	if (has_slv_msrs(family, model))
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-		/* Nehalem compatible, but do not include turbo-ratio limit support */
-	case INTEL_FAM6_NEHALEM_EX:	/* Nehalem-EX Xeon - Beckton */
-	case INTEL_FAM6_XEON_PHI_KNL:	/* PHI - Knights Landing (different MSR definition) */
-		return 0;
-	default:
-		return 1;
-	}
-}
-
-int has_atom_turbo_ratio_limit(unsigned int family, unsigned int model)
-{
-	if (has_slv_msrs(family, model))
-		return 1;
-
-	return 0;
-}
-
-int has_ivt_turbo_ratio_limit(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
 
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_IVYBRIDGE_X:	/* IVB Xeon */
-	case INTEL_FAM6_HASWELL_X:	/* HSW Xeon */
-		return 1;
-	default:
-		return 0;
-	}
-}
-
-int has_hsw_turbo_ratio_limit(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_HASWELL_X:	/* HSW Xeon */
-		return 1;
-	default:
-		return 0;
-	}
-}
-
-int has_knl_turbo_ratio_limit(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_XEON_PHI_KNL:	/* Knights Landing */
-		return 1;
-	default:
-		return 0;
-	}
-}
-
-int has_glm_turbo_ratio_limit(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_ATOM_GOLDMONT:
-	case INTEL_FAM6_SKYLAKE_X:
-	case INTEL_FAM6_ICELAKE_X:
-	case INTEL_FAM6_SAPPHIRERAPIDS_X:
-		return 1;
-	default:
-		return 0;
-	}
-}
-
-int has_config_tdp(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_IVYBRIDGE:	/* IVB */
-	case INTEL_FAM6_HASWELL:	/* HSW */
-	case INTEL_FAM6_HASWELL_X:	/* HSX */
-	case INTEL_FAM6_HASWELL_L:	/* HSW */
-	case INTEL_FAM6_HASWELL_G:	/* HSW */
-	case INTEL_FAM6_BROADWELL:	/* BDW */
-	case INTEL_FAM6_BROADWELL_G:	/* BDW */
-	case INTEL_FAM6_BROADWELL_X:	/* BDX */
-	case INTEL_FAM6_SKYLAKE_L:	/* SKL */
-	case INTEL_FAM6_CANNONLAKE_L:	/* CNL */
-	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
-	case INTEL_FAM6_ICELAKE_X:	/* ICX */
-	case INTEL_FAM6_SAPPHIRERAPIDS_X:	/* SPR */
-	case INTEL_FAM6_XEON_PHI_KNL:	/* Knights Landing */
-		return 1;
-	default:
-		return 0;
-	}
-}
-
-/*
- * tcc_offset_bits:
- * 0: Tcc Offset not supported (Default)
- * 6: Bit 29:24 of MSR_PLATFORM_INFO
- * 4: Bit 27:24 of MSR_PLATFORM_INFO
- */
-void check_tcc_offset(int model)
-{
-	unsigned long long msr;
-
-	if (!genuine_intel)
-		return;
-
-	switch (model) {
-	case INTEL_FAM6_SKYLAKE_L:
-	case INTEL_FAM6_SKYLAKE:
-	case INTEL_FAM6_KABYLAKE_L:
-	case INTEL_FAM6_KABYLAKE:
-	case INTEL_FAM6_ICELAKE_L:
-	case INTEL_FAM6_ICELAKE:
-	case INTEL_FAM6_TIGERLAKE_L:
-	case INTEL_FAM6_TIGERLAKE:
-	case INTEL_FAM6_COMETLAKE:
-		if (!get_msr(base_cpu, MSR_PLATFORM_INFO, &msr)) {
-			msr = (msr >> 30) & 1;
-			if (msr)
-				tcc_offset_bits = 6;
-		}
-		return;
-	default:
-		return;
-	}
+	if (platform->enable_tsc_tweak)
+		tsc_tweak = base_hz / tsc_hz;
 }
 
 static void remove_underbar(char *s)
@@ -4078,44 +4497,37 @@ static void remove_underbar(char *s)
 	*to = 0;
 }
 
-static void dump_turbo_ratio_info(unsigned int family, unsigned int model)
+static void dump_turbo_ratio_info(void)
 {
 	if (!has_turbo)
 		return;
 
-	if (has_hsw_turbo_ratio_limit(family, model))
-		dump_hsw_turbo_ratio_limits();
+	if (!platform->has_nhm_msrs)
+		return;
+
+	if (platform->trl_msrs & TRL_LIMIT2)
+		dump_turbo_ratio_limit2();
 
-	if (has_ivt_turbo_ratio_limit(family, model))
-		dump_ivt_turbo_ratio_limits();
+	if (platform->trl_msrs & TRL_LIMIT1)
+		dump_turbo_ratio_limit1();
 
-	if (has_turbo_ratio_limit(family, model)) {
-		dump_turbo_ratio_limits(MSR_TURBO_RATIO_LIMIT, family, model);
+	if (platform->trl_msrs & TRL_BASE) {
+		dump_turbo_ratio_limits(MSR_TURBO_RATIO_LIMIT);
 
 		if (is_hybrid)
-			dump_turbo_ratio_limits(MSR_SECONDARY_TURBO_RATIO_LIMIT, family, model);
+			dump_turbo_ratio_limits(MSR_SECONDARY_TURBO_RATIO_LIMIT);
 	}
 
-	if (has_atom_turbo_ratio_limit(family, model))
+	if (platform->trl_msrs & TRL_ATOM)
 		dump_atom_turbo_ratio_limits();
 
-	if (has_knl_turbo_ratio_limit(family, model))
+	if (platform->trl_msrs & TRL_KNL)
 		dump_knl_turbo_ratio_limits();
 
-	if (has_config_tdp(family, model))
+	if (platform->has_config_tdp)
 		dump_config_tdp();
 }
 
-static void dump_cstate_pstate_config_info(unsigned int family, unsigned int model)
-{
-	if (!do_nhm_platform_info)
-		return;
-
-	dump_nhm_platform_info();
-	dump_turbo_ratio_info(family, model);
-	dump_nhm_cst_cfg();
-}
-
 static int read_sysfs_int(char *path)
 {
 	FILE *input;
@@ -4152,7 +4564,7 @@ static void dump_sysfs_file(char *path)
 	fprintf(outf, "%s: %s", strrchr(path, '/') + 1, cpuidle_buf);
 }
 
-static void intel_uncore_frequency_probe(void)
+static void probe_intel_uncore_frequency(void)
 {
 	int i, j;
 	char path[128];
@@ -4163,6 +4575,10 @@ static void intel_uncore_frequency_probe(void)
 	if (access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00", R_OK))
 		return;
 
+	/* Cluster level sysfs not supported yet. */
+	if (!access("/sys/devices/system/cpu/intel_uncore_frequency/uncore00", R_OK))
+		return;
+
 	if (!access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00/current_freq_khz", R_OK))
 		BIC_PRESENT(BIC_UNCORE_MHZ);
 
@@ -4194,6 +4610,20 @@ static void intel_uncore_frequency_probe(void)
 	}
 }
 
+static void probe_graphics(void)
+{
+	if (!access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK))
+		BIC_PRESENT(BIC_GFX_rc6);
+
+	if (!access("/sys/class/drm/card0/gt_cur_freq_mhz", R_OK) ||
+	    !access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK))
+		BIC_PRESENT(BIC_GFXMHz);
+
+	if (!access("/sys/class/drm/card0/gt_act_freq_mhz", R_OK) ||
+	    !access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK))
+		BIC_PRESENT(BIC_GFXACTMHz);
+}
+
 static void dump_sysfs_cstate_config(void)
 {
 	char path[64];
@@ -4310,7 +4740,7 @@ int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	cpu = t->cpu_id;
 
 	/* EPB is per-package */
-	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+	if (!is_cpu_first_thread_in_package(t, c, p))
 		return 0;
 
 	if (cpu_migrate(cpu)) {
@@ -4359,7 +4789,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	cpu = t->cpu_id;
 
 	/* MSR_HWP_CAPABILITIES is per-package */
-	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+	if (!is_cpu_first_thread_in_package(t, c, p))
 		return 0;
 
 	if (cpu_migrate(cpu)) {
@@ -4442,7 +4872,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 	cpu = t->cpu_id;
 
 	/* per-package */
-	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+	if (!is_cpu_first_thread_in_package(t, c, p))
 		return 0;
 
 	if (cpu_migrate(cpu)) {
@@ -4450,7 +4880,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 		return -1;
 	}
 
-	if (do_core_perf_limit_reasons) {
+	if (platform->plr_msrs & PLR_CORE) {
 		get_msr(cpu, MSR_CORE_PERF_LIMIT_REASONS, &msr);
 		fprintf(outf, "cpu%d: MSR_CORE_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
 		fprintf(outf, " (Active: %s%s%s%s%s%s%s%s%s%s%s%s%s%s)",
@@ -4483,7 +4913,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 			(msr & 1 << 17) ? "ThermStatus, " : "", (msr & 1 << 16) ? "PROCHOT, " : "");
 
 	}
-	if (do_gfx_perf_limit_reasons) {
+	if (platform->plr_msrs & PLR_GFX) {
 		get_msr(cpu, MSR_GFX_PERF_LIMIT_REASONS, &msr);
 		fprintf(outf, "cpu%d: MSR_GFX_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
 		fprintf(outf, " (Active: %s%s%s%s%s%s%s%s)",
@@ -4503,7 +4933,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 			(msr & 1 << 25) ? "GFXPwr, " : "",
 			(msr & 1 << 26) ? "PkgPwrL1, " : "", (msr & 1 << 27) ? "PkgPwrL2, " : "");
 	}
-	if (do_ring_perf_limit_reasons) {
+	if (platform->plr_msrs & PLR_RING) {
 		get_msr(cpu, MSR_RING_PERF_LIMIT_REASONS, &msr);
 		fprintf(outf, "cpu%d: MSR_RING_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
 		fprintf(outf, " (Active: %s%s%s%s%s%s)",
@@ -4525,208 +4955,74 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 #define	RAPL_POWER_GRANULARITY	0x7FFF	/* 15 bit power granularity */
 #define	RAPL_TIME_GRANULARITY	0x3F	/* 6 bit time granularity */
 
-double get_tdp_intel(unsigned int model)
+double get_quirk_tdp(void)
 {
-	unsigned long long msr;
+	if (platform->rapl_quirk_tdp)
+		return platform->rapl_quirk_tdp;
 
-	if (do_rapl & RAPL_PKG_POWER_INFO)
-		if (!get_msr(base_cpu, MSR_PKG_POWER_INFO, &msr))
-			return ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units;
-
-	switch (model) {
-	case INTEL_FAM6_ATOM_SILVERMONT:
-	case INTEL_FAM6_ATOM_SILVERMONT_D:
-		return 30.0;
-	default:
-		return 135.0;
-	}
+	return 135.0;
 }
 
-double get_tdp_amd(unsigned int family)
+double get_tdp_intel(void)
 {
-	UNUSED(family);
+	unsigned long long msr;
 
-	/* This is the max stock TDP of HEDT/Server Fam17h+ chips */
-	return 280.0;
+	if (platform->rapl_msrs & RAPL_PKG_POWER_INFO)
+		if (!get_msr(base_cpu, MSR_PKG_POWER_INFO, &msr))
+			return ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units;
+	return get_quirk_tdp();
 }
 
-/*
- * rapl_dram_energy_units_probe()
- * Energy units are either hard-coded, or come from RAPL Energy Unit MSR.
- */
-static double rapl_dram_energy_units_probe(int model, double rapl_energy_units)
+double get_tdp_amd(void)
 {
-	/* only called for genuine_intel, family 6 */
-
-	switch (model) {
-	case INTEL_FAM6_HASWELL_X:	/* HSX */
-	case INTEL_FAM6_BROADWELL_X:	/* BDX */
-	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
-	case INTEL_FAM6_XEON_PHI_KNL:	/* KNL */
-	case INTEL_FAM6_ICELAKE_X:	/* ICX */
-		return (rapl_dram_energy_units = 15.3 / 1000000);
-	default:
-		return (rapl_energy_units);
-	}
+	return get_quirk_tdp();
 }
 
-void rapl_probe_intel(unsigned int family, unsigned int model)
+void rapl_probe_intel(void)
 {
 	unsigned long long msr;
 	unsigned int time_unit;
 	double tdp;
 
-	if (family != 6)
-		return;
-
-	switch (model) {
-	case INTEL_FAM6_SANDYBRIDGE:
-	case INTEL_FAM6_IVYBRIDGE:
-	case INTEL_FAM6_HASWELL:	/* HSW */
-	case INTEL_FAM6_HASWELL_L:	/* HSW */
-	case INTEL_FAM6_HASWELL_G:	/* HSW */
-	case INTEL_FAM6_BROADWELL:	/* BDW */
-	case INTEL_FAM6_BROADWELL_G:	/* BDW */
-		do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_GFX | RAPL_PKG_POWER_INFO;
-		if (rapl_joules) {
-			BIC_PRESENT(BIC_Pkg_J);
-			BIC_PRESENT(BIC_Cor_J);
-			BIC_PRESENT(BIC_GFX_J);
-		} else {
-			BIC_PRESENT(BIC_PkgWatt);
-			BIC_PRESENT(BIC_CorWatt);
-			BIC_PRESENT(BIC_GFXWatt);
-		}
-		break;
-	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
-	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
-		do_rapl = RAPL_PKG | RAPL_PKG_POWER_INFO;
-		if (rapl_joules)
-			BIC_PRESENT(BIC_Pkg_J);
-		else
-			BIC_PRESENT(BIC_PkgWatt);
-		break;
-	case INTEL_FAM6_ATOM_TREMONT:	/* EHL */
-		do_rapl =
-		    RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS
-		    | RAPL_GFX | RAPL_PKG_POWER_INFO;
-		if (rapl_joules) {
-			BIC_PRESENT(BIC_Pkg_J);
-			BIC_PRESENT(BIC_Cor_J);
-			BIC_PRESENT(BIC_RAM_J);
-			BIC_PRESENT(BIC_GFX_J);
-		} else {
-			BIC_PRESENT(BIC_PkgWatt);
-			BIC_PRESENT(BIC_CorWatt);
-			BIC_PRESENT(BIC_RAMWatt);
-			BIC_PRESENT(BIC_GFXWatt);
-		}
-		break;
-	case INTEL_FAM6_ATOM_TREMONT_D:	/* JVL */
-		do_rapl = RAPL_PKG | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
-		BIC_PRESENT(BIC_PKG__);
-		if (rapl_joules)
-			BIC_PRESENT(BIC_Pkg_J);
-		else
-			BIC_PRESENT(BIC_PkgWatt);
-		break;
-	case INTEL_FAM6_SKYLAKE_L:	/* SKL */
-	case INTEL_FAM6_CANNONLAKE_L:	/* CNL */
-		do_rapl =
-		    RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS
-		    | RAPL_GFX | RAPL_PKG_POWER_INFO;
-		BIC_PRESENT(BIC_PKG__);
-		BIC_PRESENT(BIC_RAM__);
-		if (rapl_joules) {
+	if (rapl_joules) {
+		if (platform->rapl_msrs & RAPL_PKG_ENERGY_STATUS)
 			BIC_PRESENT(BIC_Pkg_J);
+		if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS)
 			BIC_PRESENT(BIC_Cor_J);
+		if (platform->rapl_msrs & RAPL_DRAM_ENERGY_STATUS)
 			BIC_PRESENT(BIC_RAM_J);
+		if (platform->rapl_msrs & RAPL_GFX_ENERGY_STATUS)
 			BIC_PRESENT(BIC_GFX_J);
-		} else {
+	} else {
+		if (platform->rapl_msrs & RAPL_PKG_ENERGY_STATUS)
 			BIC_PRESENT(BIC_PkgWatt);
+		if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS)
 			BIC_PRESENT(BIC_CorWatt);
+		if (platform->rapl_msrs & RAPL_DRAM_ENERGY_STATUS)
 			BIC_PRESENT(BIC_RAMWatt);
+		if (platform->rapl_msrs & RAPL_GFX_ENERGY_STATUS)
 			BIC_PRESENT(BIC_GFXWatt);
-		}
-		break;
-	case INTEL_FAM6_HASWELL_X:	/* HSX */
-	case INTEL_FAM6_BROADWELL_X:	/* BDX */
-	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
-	case INTEL_FAM6_ICELAKE_X:	/* ICX */
-	case INTEL_FAM6_SAPPHIRERAPIDS_X:	/* SPR */
-	case INTEL_FAM6_XEON_PHI_KNL:	/* KNL */
-		do_rapl =
-		    RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS |
-		    RAPL_PKG_POWER_INFO;
-		BIC_PRESENT(BIC_PKG__);
-		BIC_PRESENT(BIC_RAM__);
-		if (rapl_joules) {
-			BIC_PRESENT(BIC_Pkg_J);
-			BIC_PRESENT(BIC_RAM_J);
-		} else {
-			BIC_PRESENT(BIC_PkgWatt);
-			BIC_PRESENT(BIC_RAMWatt);
-		}
-		break;
-	case INTEL_FAM6_SANDYBRIDGE_X:
-	case INTEL_FAM6_IVYBRIDGE_X:
-		do_rapl =
-		    RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_PKG_PERF_STATUS |
-		    RAPL_DRAM_PERF_STATUS | RAPL_PKG_POWER_INFO;
-		BIC_PRESENT(BIC_PKG__);
-		BIC_PRESENT(BIC_RAM__);
-		if (rapl_joules) {
-			BIC_PRESENT(BIC_Pkg_J);
-			BIC_PRESENT(BIC_Cor_J);
-			BIC_PRESENT(BIC_RAM_J);
-		} else {
-			BIC_PRESENT(BIC_PkgWatt);
-			BIC_PRESENT(BIC_CorWatt);
-			BIC_PRESENT(BIC_RAMWatt);
-		}
-		break;
-	case INTEL_FAM6_ATOM_SILVERMONT:	/* BYT */
-	case INTEL_FAM6_ATOM_SILVERMONT_D:	/* AVN */
-		do_rapl = RAPL_PKG | RAPL_CORES;
-		if (rapl_joules) {
-			BIC_PRESENT(BIC_Pkg_J);
-			BIC_PRESENT(BIC_Cor_J);
-		} else {
-			BIC_PRESENT(BIC_PkgWatt);
-			BIC_PRESENT(BIC_CorWatt);
-		}
-		break;
-	case INTEL_FAM6_ATOM_GOLDMONT_D:	/* DNV */
-		do_rapl =
-		    RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS |
-		    RAPL_PKG_POWER_INFO | RAPL_CORES_ENERGY_STATUS;
+	}
+
+	if (platform->rapl_msrs & RAPL_PKG_PERF_STATUS)
 		BIC_PRESENT(BIC_PKG__);
+	if (platform->rapl_msrs & RAPL_DRAM_PERF_STATUS)
 		BIC_PRESENT(BIC_RAM__);
-		if (rapl_joules) {
-			BIC_PRESENT(BIC_Pkg_J);
-			BIC_PRESENT(BIC_Cor_J);
-			BIC_PRESENT(BIC_RAM_J);
-		} else {
-			BIC_PRESENT(BIC_PkgWatt);
-			BIC_PRESENT(BIC_CorWatt);
-			BIC_PRESENT(BIC_RAMWatt);
-		}
-		break;
-	default:
-		return;
-	}
 
 	/* units on package 0, verify later other packages match */
 	if (get_msr(base_cpu, MSR_RAPL_POWER_UNIT, &msr))
 		return;
 
 	rapl_power_units = 1.0 / (1 << (msr & 0xF));
-	if (model == INTEL_FAM6_ATOM_SILVERMONT)
+	if (platform->has_rapl_divisor)
 		rapl_energy_units = 1.0 * (1 << (msr >> 8 & 0x1F)) / 1000000;
 	else
 		rapl_energy_units = 1.0 / (1 << (msr >> 8 & 0x1F));
 
-	rapl_dram_energy_units = rapl_dram_energy_units_probe(model, rapl_energy_units);
+	if (platform->has_fixed_rapl_unit)
+		rapl_dram_energy_units = (15.3 / 1000000);
+	else
+		rapl_dram_energy_units = rapl_energy_units;
 
 	time_unit = msr >> 16 & 0xF;
 	if (time_unit == 0)
@@ -4734,32 +5030,18 @@ void rapl_probe_intel(unsigned int family, unsigned int model)
 
 	rapl_time_units = 1.0 / (1 << (time_unit));
 
-	tdp = get_tdp_intel(model);
+	tdp = get_tdp_intel();
 
 	rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
 	if (!quiet)
 		fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp);
 }
 
-void rapl_probe_amd(unsigned int family, unsigned int model)
+void rapl_probe_amd(void)
 {
 	unsigned long long msr;
-	unsigned int eax, ebx, ecx, edx;
-	unsigned int has_rapl = 0;
 	double tdp;
 
-	UNUSED(model);
-
-	if (max_extended_level >= 0x80000007) {
-		__cpuid(0x80000007, eax, ebx, ecx, edx);
-		/* RAPL (Fam 17h+) */
-		has_rapl = edx & (1 << 14);
-	}
-
-	if (!has_rapl || family < 0x17)
-		return;
-
-	do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY;
 	if (rapl_joules) {
 		BIC_PRESENT(BIC_Pkg_J);
 		BIC_PRESENT(BIC_Cor_J);
@@ -4775,128 +5057,13 @@ void rapl_probe_amd(unsigned int family, unsigned int model)
 	rapl_energy_units = ldexp(1.0, -(msr >> 8 & 0x1f));
 	rapl_power_units = ldexp(1.0, -(msr & 0xf));
 
-	tdp = get_tdp_amd(family);
+	tdp = get_tdp_amd();
 
 	rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
 	if (!quiet)
 		fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp);
 }
 
-/*
- * rapl_probe()
- *
- * sets do_rapl, rapl_power_units, rapl_energy_units, rapl_time_units
- */
-void rapl_probe(unsigned int family, unsigned int model)
-{
-	if (genuine_intel)
-		rapl_probe_intel(family, model);
-	if (authentic_amd || hygon_genuine)
-		rapl_probe_amd(family, model);
-}
-
-void perf_limit_reasons_probe(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return;
-
-	if (family != 6)
-		return;
-
-	switch (model) {
-	case INTEL_FAM6_HASWELL:	/* HSW */
-	case INTEL_FAM6_HASWELL_L:	/* HSW */
-	case INTEL_FAM6_HASWELL_G:	/* HSW */
-		do_gfx_perf_limit_reasons = 1;
-		/* FALLTHRU */
-	case INTEL_FAM6_HASWELL_X:	/* HSX */
-		do_core_perf_limit_reasons = 1;
-		do_ring_perf_limit_reasons = 1;
-	default:
-		return;
-	}
-}
-
-void automatic_cstate_conversion_probe(unsigned int family, unsigned int model)
-{
-	if (family != 6)
-		return;
-
-	switch (model) {
-	case INTEL_FAM6_BROADWELL_X:
-	case INTEL_FAM6_SKYLAKE_X:
-		has_automatic_cstate_conversion = 1;
-	}
-}
-
-void prewake_cstate_probe(unsigned int family, unsigned int model)
-{
-	if (is_icx(family, model) || is_spr(family, model))
-		dis_cstate_prewake = 1;
-}
-
-int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p)
-{
-	unsigned long long msr;
-	unsigned int dts, dts2;
-	int cpu;
-
-	UNUSED(c);
-	UNUSED(p);
-
-	if (!(do_dts || do_ptm))
-		return 0;
-
-	cpu = t->cpu_id;
-
-	/* DTS is per-core, no need to print for each thread */
-	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
-		return 0;
-
-	if (cpu_migrate(cpu)) {
-		fprintf(outf, "print_thermal: Could not migrate to CPU %d\n", cpu);
-		return -1;
-	}
-
-	if (do_ptm && (t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) {
-		if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr))
-			return 0;
-
-		dts = (msr >> 16) & 0x7F;
-		fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_STATUS: 0x%08llx (%d C)\n", cpu, msr, tj_max - dts);
-
-		if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, &msr))
-			return 0;
-
-		dts = (msr >> 16) & 0x7F;
-		dts2 = (msr >> 8) & 0x7F;
-		fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
-			cpu, msr, tj_max - dts, tj_max - dts2);
-	}
-
-	if (do_dts && debug) {
-		unsigned int resolution;
-
-		if (get_msr(cpu, MSR_IA32_THERM_STATUS, &msr))
-			return 0;
-
-		dts = (msr >> 16) & 0x7F;
-		resolution = (msr >> 27) & 0xF;
-		fprintf(outf, "cpu%d: MSR_IA32_THERM_STATUS: 0x%08llx (%d C +/- %d)\n",
-			cpu, msr, tj_max - dts, resolution);
-
-		if (get_msr(cpu, MSR_IA32_THERM_INTERRUPT, &msr))
-			return 0;
-
-		dts = (msr >> 16) & 0x7F;
-		dts2 = (msr >> 8) & 0x7F;
-		fprintf(outf, "cpu%d: MSR_IA32_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
-			cpu, msr, tj_max - dts, tj_max - dts2);
-	}
-
-	return 0;
-}
-
 void print_power_limit_msr(int cpu, unsigned long long msr, char *label)
 {
 	fprintf(outf, "cpu%d: %s: %sabled (%0.3f Watts, %f sec, clamp %sabled)\n",
@@ -4918,11 +5085,11 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	UNUSED(c);
 	UNUSED(p);
 
-	if (!do_rapl)
+	if (!platform->rapl_msrs)
 		return 0;
 
 	/* RAPL counters are per package, so print only for 1st thread/package */
-	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+	if (!is_cpu_first_thread_in_package(t, c, p))
 		return 0;
 
 	cpu = t->cpu_id;
@@ -4931,7 +5098,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		return -1;
 	}
 
-	if (do_rapl & RAPL_AMD_F17H) {
+	if (platform->rapl_msrs & RAPL_AMD_F17H) {
 		msr_name = "MSR_RAPL_PWR_UNIT";
 		if (get_msr(cpu, MSR_RAPL_PWR_UNIT, &msr))
 			return -1;
@@ -4944,7 +5111,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	fprintf(outf, "cpu%d: %s: 0x%08llx (%f Watts, %f Joules, %f sec.)\n", cpu, msr_name, msr,
 		rapl_power_units, rapl_energy_units, rapl_time_units);
 
-	if (do_rapl & RAPL_PKG_POWER_INFO) {
+	if (platform->rapl_msrs & RAPL_PKG_POWER_INFO) {
 
 		if (get_msr(cpu, MSR_PKG_POWER_INFO, &msr))
 			return -5;
@@ -4957,7 +5124,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			((msr >> 48) & RAPL_TIME_GRANULARITY) * rapl_time_units);
 
 	}
-	if (do_rapl & RAPL_PKG) {
+	if (platform->rapl_msrs & RAPL_PKG) {
 
 		if (get_msr(cpu, MSR_PKG_POWER_LIMIT, &msr))
 			return -9;
@@ -4981,7 +5148,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			cpu, ((msr >> 0) & 0x1FFF) * rapl_power_units, (msr >> 31) & 1 ? "" : "UN");
 	}
 
-	if (do_rapl & RAPL_DRAM_POWER_INFO) {
+	if (platform->rapl_msrs & RAPL_DRAM_POWER_INFO) {
 		if (get_msr(cpu, MSR_DRAM_POWER_INFO, &msr))
 			return -6;
 
@@ -4992,7 +5159,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			((msr >> 32) & RAPL_POWER_GRANULARITY) * rapl_power_units,
 			((msr >> 48) & RAPL_TIME_GRANULARITY) * rapl_time_units);
 	}
-	if (do_rapl & RAPL_DRAM) {
+	if (platform->rapl_msrs & RAPL_DRAM) {
 		if (get_msr(cpu, MSR_DRAM_POWER_LIMIT, &msr))
 			return -9;
 		fprintf(outf, "cpu%d: MSR_DRAM_POWER_LIMIT: 0x%08llx (%slocked)\n",
@@ -5000,20 +5167,20 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 
 		print_power_limit_msr(cpu, msr, "DRAM Limit");
 	}
-	if (do_rapl & RAPL_CORE_POLICY) {
+	if (platform->rapl_msrs & RAPL_CORE_POLICY) {
 		if (get_msr(cpu, MSR_PP0_POLICY, &msr))
 			return -7;
 
 		fprintf(outf, "cpu%d: MSR_PP0_POLICY: %lld\n", cpu, msr & 0xF);
 	}
-	if (do_rapl & RAPL_CORES_POWER_LIMIT) {
+	if (platform->rapl_msrs & RAPL_CORE_POWER_LIMIT) {
 		if (get_msr(cpu, MSR_PP0_POWER_LIMIT, &msr))
 			return -9;
 		fprintf(outf, "cpu%d: MSR_PP0_POWER_LIMIT: 0x%08llx (%slocked)\n",
 			cpu, msr, (msr >> 31) & 1 ? "" : "UN");
 		print_power_limit_msr(cpu, msr, "Cores Limit");
 	}
-	if (do_rapl & RAPL_GFX) {
+	if (platform->rapl_msrs & RAPL_GFX) {
 		if (get_msr(cpu, MSR_PP1_POLICY, &msr))
 			return -8;
 
@@ -5029,217 +5196,24 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 }
 
 /*
- * SNB adds support for additional MSRs:
+ * probe_rapl()
  *
- * MSR_PKG_C7_RESIDENCY            0x000003fa
- * MSR_CORE_C7_RESIDENCY           0x000003fe
- * MSR_PKG_C2_RESIDENCY            0x0000060d
+ * sets rapl_power_units, rapl_energy_units, rapl_time_units
  */
-
-int has_snb_msrs(unsigned int family, unsigned int model)
+void probe_rapl(void)
 {
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_SANDYBRIDGE:
-	case INTEL_FAM6_SANDYBRIDGE_X:
-	case INTEL_FAM6_IVYBRIDGE:	/* IVB */
-	case INTEL_FAM6_IVYBRIDGE_X:	/* IVB Xeon */
-	case INTEL_FAM6_HASWELL:	/* HSW */
-	case INTEL_FAM6_HASWELL_X:	/* HSW */
-	case INTEL_FAM6_HASWELL_L:	/* HSW */
-	case INTEL_FAM6_HASWELL_G:	/* HSW */
-	case INTEL_FAM6_BROADWELL:	/* BDW */
-	case INTEL_FAM6_BROADWELL_G:	/* BDW */
-	case INTEL_FAM6_BROADWELL_X:	/* BDX */
-	case INTEL_FAM6_SKYLAKE_L:	/* SKL */
-	case INTEL_FAM6_CANNONLAKE_L:	/* CNL */
-	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
-	case INTEL_FAM6_ICELAKE_X:	/* ICX */
-	case INTEL_FAM6_SAPPHIRERAPIDS_X:	/* SPR */
-	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
-	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
-	case INTEL_FAM6_ATOM_GOLDMONT_D:	/* DNV */
-	case INTEL_FAM6_ATOM_TREMONT:	/* EHL */
-	case INTEL_FAM6_ATOM_TREMONT_D:	/* JVL */
-		return 1;
-	}
-	return 0;
-}
-
-/*
- * HSW ULT added support for C8/C9/C10 MSRs:
- *
- * MSR_PKG_C8_RESIDENCY		0x00000630
- * MSR_PKG_C9_RESIDENCY		0x00000631
- * MSR_PKG_C10_RESIDENCY	0x00000632
- *
- * MSR_PKGC8_IRTL		0x00000633
- * MSR_PKGC9_IRTL		0x00000634
- * MSR_PKGC10_IRTL		0x00000635
- *
- */
-int has_c8910_msrs(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_HASWELL_L:	/* HSW */
-	case INTEL_FAM6_BROADWELL:	/* BDW */
-	case INTEL_FAM6_SKYLAKE_L:	/* SKL */
-	case INTEL_FAM6_CANNONLAKE_L:	/* CNL */
-	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
-	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
-	case INTEL_FAM6_ATOM_TREMONT:	/* EHL */
-		return 1;
-	}
-	return 0;
-}
-
-/*
- * SKL adds support for additional MSRS:
- *
- * MSR_PKG_WEIGHTED_CORE_C0_RES    0x00000658
- * MSR_PKG_ANY_CORE_C0_RES         0x00000659
- * MSR_PKG_ANY_GFXE_C0_RES         0x0000065A
- * MSR_PKG_BOTH_CORE_GFXE_C0_RES   0x0000065B
- */
-int has_skl_msrs(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_SKYLAKE_L:	/* SKL */
-	case INTEL_FAM6_CANNONLAKE_L:	/* CNL */
-		return 1;
-	}
-	return 0;
-}
-
-int is_slm(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_ATOM_SILVERMONT:	/* BYT */
-	case INTEL_FAM6_ATOM_SILVERMONT_D:	/* AVN */
-		return 1;
-	}
-	return 0;
-}
-
-int is_knl(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_XEON_PHI_KNL:	/* KNL */
-		return 1;
-	}
-	return 0;
-}
-
-int is_cnl(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_CANNONLAKE_L:	/* CNL */
-		return 1;
-	}
-
-	return 0;
-}
-
-unsigned int get_aperf_mperf_multiplier(unsigned int family, unsigned int model)
-{
-	if (is_knl(family, model))
-		return 1024;
-	return 1;
-}
-
-#define SLM_BCLK_FREQS 5
-double slm_freq_table[SLM_BCLK_FREQS] = { 83.3, 100.0, 133.3, 116.7, 80.0 };
-
-double slm_bclk(void)
-{
-	unsigned long long msr = 3;
-	unsigned int i;
-	double freq;
-
-	if (get_msr(base_cpu, MSR_FSB_FREQ, &msr))
-		fprintf(outf, "SLM BCLK: unknown\n");
-
-	i = msr & 0xf;
-	if (i >= SLM_BCLK_FREQS) {
-		fprintf(outf, "SLM BCLK[%d] invalid\n", i);
-		i = 3;
-	}
-	freq = slm_freq_table[i];
-
-	if (!quiet)
-		fprintf(outf, "SLM BCLK: %.1f Mhz\n", freq);
-
-	return freq;
-}
-
-double discover_bclk(unsigned int family, unsigned int model)
-{
-	if (has_snb_msrs(family, model) || is_knl(family, model))
-		return 100.00;
-	else if (is_slm(family, model))
-		return slm_bclk();
-	else
-		return 133.33;
-}
-
-int get_cpu_type(struct thread_data *t, struct core_data *c, struct pkg_data *p)
-{
-	unsigned int eax, ebx, ecx, edx;
-
-	UNUSED(c);
-	UNUSED(p);
-
-	if (!genuine_intel)
-		return 0;
+	if (!platform->rapl_msrs)
+		return;
 
-	if (cpu_migrate(t->cpu_id)) {
-		fprintf(outf, "Could not migrate to CPU %d\n", t->cpu_id);
-		return -1;
-	}
+	if (genuine_intel)
+		rapl_probe_intel();
+	if (authentic_amd || hygon_genuine)
+		rapl_probe_amd();
 
-	if (max_level < 0x1a)
-		return 0;
+	if (quiet)
+		return;
 
-	__cpuid(0x1a, eax, ebx, ecx, edx);
-	eax = (eax >> 24) & 0xFF;
-	if (eax == 0x20)
-		t->is_atom = true;
-	return 0;
+	for_all_cpus(print_rapl, ODD_COUNTERS);
 }
 
 /*
@@ -5268,7 +5242,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk
 		return 0;
 
 	/* this is a per-package concept */
-	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+	if (!is_cpu_first_thread_in_package(t, c, p))
 		return 0;
 
 	cpu = t->cpu_id;
@@ -5284,7 +5258,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk
 	}
 
 	/* Temperature Target MSR is Nehalem and newer only */
-	if (!do_nhm_platform_info)
+	if (!platform->has_nhm_msrs)
 		goto guess;
 
 	if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr))
@@ -5293,20 +5267,18 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk
 	tcc_default = (msr >> 16) & 0xFF;
 
 	if (!quiet) {
-		switch (tcc_offset_bits) {
-		case 4:
-			tcc_offset = (msr >> 24) & 0xF;
-			fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C) (%d default - %d offset)\n",
-				cpu, msr, tcc_default - tcc_offset, tcc_default, tcc_offset);
-			break;
-		case 6:
-			tcc_offset = (msr >> 24) & 0x3F;
+		int bits = platform->tcc_offset_bits;
+		unsigned long long enabled = 0;
+
+		if (bits && !get_msr(base_cpu, MSR_PLATFORM_INFO, &enabled))
+			enabled = (enabled >> 30) & 1;
+
+		if (bits && enabled) {
+			tcc_offset = (msr >> 24) & GENMASK(bits - 1, 0);
 			fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C) (%d default - %d offset)\n",
 				cpu, msr, tcc_default - tcc_offset, tcc_default, tcc_offset);
-			break;
-		default:
+		} else {
 			fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n", cpu, msr, tcc_default);
-			break;
 		}
 	}
 
@@ -5324,6 +5296,108 @@ guess:
 	return 0;
 }
 
+int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+	unsigned long long msr;
+	unsigned int dts, dts2;
+	int cpu;
+
+	UNUSED(c);
+	UNUSED(p);
+
+	if (!(do_dts || do_ptm))
+		return 0;
+
+	cpu = t->cpu_id;
+
+	/* DTS is per-core, no need to print for each thread */
+	if (!is_cpu_first_thread_in_core(t, c, p))
+		return 0;
+
+	if (cpu_migrate(cpu)) {
+		fprintf(outf, "print_thermal: Could not migrate to CPU %d\n", cpu);
+		return -1;
+	}
+
+	if (do_ptm && is_cpu_first_core_in_package(t, c, p)) {
+		if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr))
+			return 0;
+
+		dts = (msr >> 16) & 0x7F;
+		fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_STATUS: 0x%08llx (%d C)\n", cpu, msr, tj_max - dts);
+
+		if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, &msr))
+			return 0;
+
+		dts = (msr >> 16) & 0x7F;
+		dts2 = (msr >> 8) & 0x7F;
+		fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
+			cpu, msr, tj_max - dts, tj_max - dts2);
+	}
+
+	if (do_dts && debug) {
+		unsigned int resolution;
+
+		if (get_msr(cpu, MSR_IA32_THERM_STATUS, &msr))
+			return 0;
+
+		dts = (msr >> 16) & 0x7F;
+		resolution = (msr >> 27) & 0xF;
+		fprintf(outf, "cpu%d: MSR_IA32_THERM_STATUS: 0x%08llx (%d C +/- %d)\n",
+			cpu, msr, tj_max - dts, resolution);
+
+		if (get_msr(cpu, MSR_IA32_THERM_INTERRUPT, &msr))
+			return 0;
+
+		dts = (msr >> 16) & 0x7F;
+		dts2 = (msr >> 8) & 0x7F;
+		fprintf(outf, "cpu%d: MSR_IA32_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
+			cpu, msr, tj_max - dts, tj_max - dts2);
+	}
+
+	return 0;
+}
+
+void probe_thermal(void)
+{
+	if (!access("/sys/devices/system/cpu/cpu0/thermal_throttle/core_throttle_count", R_OK))
+		BIC_PRESENT(BIC_CORE_THROT_CNT);
+	else
+		BIC_NOT_PRESENT(BIC_CORE_THROT_CNT);
+
+	for_all_cpus(set_temperature_target, ODD_COUNTERS);
+
+	if (quiet)
+		return;
+
+	for_all_cpus(print_thermal, ODD_COUNTERS);
+}
+
+int get_cpu_type(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+	unsigned int eax, ebx, ecx, edx;
+
+	UNUSED(c);
+	UNUSED(p);
+
+	if (!genuine_intel)
+		return 0;
+
+	if (cpu_migrate(t->cpu_id)) {
+		fprintf(outf, "Could not migrate to CPU %d\n", t->cpu_id);
+		return -1;
+	}
+
+	if (max_level < 0x1a)
+		return 0;
+
+	__cpuid(0x1a, eax, ebx, ecx, edx);
+	eax = (eax >> 24) & 0xFF;
+	if (eax == 0x20)
+		t->is_atom = true;
+	return 0;
+}
+
 void decode_feature_control_msr(void)
 {
 	unsigned long long msr;
@@ -5354,7 +5428,7 @@ void decode_misc_feature_control(void)
 {
 	unsigned long long msr;
 
-	if (!has_misc_feature_control)
+	if (!platform->has_msr_misc_feature_control)
 		return;
 
 	if (!get_msr(base_cpu, MSR_MISC_FEATURE_CONTROL, &msr))
@@ -5375,10 +5449,7 @@ void decode_misc_pwr_mgmt_msr(void)
 {
 	unsigned long long msr;
 
-	if (!do_nhm_platform_info)
-		return;
-
-	if (no_MSR_MISC_PWR_MGMT)
+	if (!platform->has_msr_misc_pwr_mgmt)
 		return;
 
 	if (!get_msr(base_cpu, MSR_MISC_PWR_MGMT, &msr))
@@ -5397,6 +5468,9 @@ void decode_c6_demotion_policy_msr(void)
 {
 	unsigned long long msr;
 
+	if (!platform->has_msr_c6_demotion_policy_config)
+		return;
+
 	if (!get_msr(base_cpu, MSR_CC6_DEMOTION_POLICY_CONFIG, &msr))
 		fprintf(outf, "cpu%d: MSR_CC6_DEMOTION_POLICY_CONFIG: 0x%08llx (%sable-CC6-Demotion)\n",
 			base_cpu, msr, msr & (1 << 0) ? "EN" : "DIS");
@@ -5406,67 +5480,6 @@ void decode_c6_demotion_policy_msr(void)
 			base_cpu, msr, msr & (1 << 0) ? "EN" : "DIS");
 }
 
-/*
- * When models are the same, for the purpose of turbostat, reuse
- */
-unsigned int intel_model_duplicates(unsigned int model)
-{
-
-	switch (model) {
-	case INTEL_FAM6_NEHALEM_EP:	/* Core i7, Xeon 5500 series - Bloomfield, Gainstown NHM-EP */
-	case INTEL_FAM6_NEHALEM:	/* Core i7 and i5 Processor - Clarksfield, Lynnfield, Jasper Forest */
-	case 0x1F:		/* Core i7 and i5 Processor - Nehalem */
-	case INTEL_FAM6_WESTMERE:	/* Westmere Client - Clarkdale, Arrandale */
-	case INTEL_FAM6_WESTMERE_EP:	/* Westmere EP - Gulftown */
-		return INTEL_FAM6_NEHALEM;
-
-	case INTEL_FAM6_NEHALEM_EX:	/* Nehalem-EX Xeon - Beckton */
-	case INTEL_FAM6_WESTMERE_EX:	/* Westmere-EX Xeon - Eagleton */
-		return INTEL_FAM6_NEHALEM_EX;
-
-	case INTEL_FAM6_XEON_PHI_KNM:
-		return INTEL_FAM6_XEON_PHI_KNL;
-
-	case INTEL_FAM6_BROADWELL_X:
-	case INTEL_FAM6_BROADWELL_D:	/* BDX-DE */
-		return INTEL_FAM6_BROADWELL_X;
-
-	case INTEL_FAM6_SKYLAKE_L:
-	case INTEL_FAM6_SKYLAKE:
-	case INTEL_FAM6_KABYLAKE_L:
-	case INTEL_FAM6_KABYLAKE:
-	case INTEL_FAM6_COMETLAKE_L:
-	case INTEL_FAM6_COMETLAKE:
-		return INTEL_FAM6_SKYLAKE_L;
-
-	case INTEL_FAM6_ICELAKE_L:
-	case INTEL_FAM6_ICELAKE_NNPI:
-	case INTEL_FAM6_TIGERLAKE_L:
-	case INTEL_FAM6_TIGERLAKE:
-	case INTEL_FAM6_ROCKETLAKE:
-	case INTEL_FAM6_LAKEFIELD:
-	case INTEL_FAM6_ALDERLAKE:
-	case INTEL_FAM6_ALDERLAKE_L:
-	case INTEL_FAM6_ATOM_GRACEMONT:
-	case INTEL_FAM6_RAPTORLAKE:
-	case INTEL_FAM6_RAPTORLAKE_P:
-	case INTEL_FAM6_RAPTORLAKE_S:
-	case INTEL_FAM6_METEORLAKE:
-	case INTEL_FAM6_METEORLAKE_L:
-		return INTEL_FAM6_CANNONLAKE_L;
-
-	case INTEL_FAM6_ATOM_TREMONT_L:
-		return INTEL_FAM6_ATOM_TREMONT;
-
-	case INTEL_FAM6_ICELAKE_D:
-		return INTEL_FAM6_ICELAKE_X;
-
-	case INTEL_FAM6_EMERALDRAPIDS_X:
-		return INTEL_FAM6_SAPPHIRERAPIDS_X;
-	}
-	return model;
-}
-
 void print_dev_latency(void)
 {
 	char *path = "/dev/cpu_dma_latency";
@@ -5510,6 +5523,101 @@ void linux_perf_init(void)
 	BIC_PRESENT(BIC_IPC);
 }
 
+void probe_cstates(void)
+{
+	probe_cst_limit();
+
+	if (platform->supported_cstates & CC1)
+		BIC_PRESENT(BIC_CPU_c1);
+
+	if (platform->supported_cstates & CC3)
+		BIC_PRESENT(BIC_CPU_c3);
+
+	if (platform->supported_cstates & CC6)
+		BIC_PRESENT(BIC_CPU_c6);
+
+	if (platform->supported_cstates & CC7)
+		BIC_PRESENT(BIC_CPU_c7);
+
+	if (platform->supported_cstates & PC2 && (pkg_cstate_limit >= PCL__2))
+		BIC_PRESENT(BIC_Pkgpc2);
+
+	if (platform->supported_cstates & PC3 && (pkg_cstate_limit >= PCL__3))
+		BIC_PRESENT(BIC_Pkgpc3);
+
+	if (platform->supported_cstates & PC6 && (pkg_cstate_limit >= PCL__6))
+		BIC_PRESENT(BIC_Pkgpc6);
+
+	if (platform->supported_cstates & PC7 && (pkg_cstate_limit >= PCL__7))
+		BIC_PRESENT(BIC_Pkgpc7);
+
+	if (platform->supported_cstates & PC8 && (pkg_cstate_limit >= PCL__8))
+		BIC_PRESENT(BIC_Pkgpc8);
+
+	if (platform->supported_cstates & PC9 && (pkg_cstate_limit >= PCL__9))
+		BIC_PRESENT(BIC_Pkgpc9);
+
+	if (platform->supported_cstates & PC10 && (pkg_cstate_limit >= PCL_10))
+		BIC_PRESENT(BIC_Pkgpc10);
+
+	if (platform->has_msr_module_c6_res_ms)
+		BIC_PRESENT(BIC_Mod_c6);
+
+	if (platform->has_ext_cst_msrs) {
+		BIC_PRESENT(BIC_Totl_c0);
+		BIC_PRESENT(BIC_Any_c0);
+		BIC_PRESENT(BIC_GFX_c0);
+		BIC_PRESENT(BIC_CPUGFX);
+	}
+
+	if (quiet)
+		return;
+
+	dump_power_ctl();
+	dump_cst_cfg();
+	decode_c6_demotion_policy_msr();
+	print_dev_latency();
+	dump_sysfs_cstate_config();
+	print_irtl();
+}
+
+void probe_lpi(void)
+{
+	if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", R_OK))
+		BIC_PRESENT(BIC_CPU_LPI);
+	else
+		BIC_NOT_PRESENT(BIC_CPU_LPI);
+
+	if (!access(sys_lpi_file_sysfs, R_OK)) {
+		sys_lpi_file = sys_lpi_file_sysfs;
+		BIC_PRESENT(BIC_SYS_LPI);
+	} else if (!access(sys_lpi_file_debugfs, R_OK)) {
+		sys_lpi_file = sys_lpi_file_debugfs;
+		BIC_PRESENT(BIC_SYS_LPI);
+	} else {
+		sys_lpi_file_sysfs = NULL;
+		BIC_NOT_PRESENT(BIC_SYS_LPI);
+	}
+
+}
+
+void probe_pstates(void)
+{
+	probe_bclk();
+
+	if (quiet)
+		return;
+
+	dump_platform_info();
+	dump_turbo_ratio_info();
+	dump_sysfs_pstate_config();
+	decode_misc_pwr_mgmt_msr();
+
+	for_all_cpus(print_hwp, ODD_COUNTERS);
+	for_all_cpus(print_epb, ODD_COUNTERS);
+	for_all_cpus(print_perf_limit, ODD_COUNTERS);
+}
+
 void process_cpuid()
 {
 	unsigned int eax, ebx, ecx, edx;
@@ -5569,10 +5677,8 @@ void process_cpuid()
 			edx_flags & (1 << 22) ? "ACPI-TM" : "-",
 			edx_flags & (1 << 28) ? "HT" : "-", edx_flags & (1 << 29) ? "TM" : "-");
 	}
-	if (genuine_intel) {
-		model_orig = model;
-		model = intel_model_duplicates(model);
-	}
+
+	probe_platform_features(family, model);
 
 	if (!(edx_flags & (1 << 5)))
 		errx(1, "CPUID: no MSR");
@@ -5656,26 +5762,12 @@ void process_cpuid()
 		__cpuid(0x15, eax_crystal, ebx_tsc, crystal_hz, edx);
 
 		if (ebx_tsc != 0) {
-
 			if (!quiet && (ebx != 0))
 				fprintf(outf, "CPUID(0x15): eax_crystal: %d ebx_tsc: %d ecx_crystal_hz: %d\n",
 					eax_crystal, ebx_tsc, crystal_hz);
 
 			if (crystal_hz == 0)
-				switch (model) {
-				case INTEL_FAM6_SKYLAKE_L:	/* SKL */
-					crystal_hz = 24000000;	/* 24.0 MHz */
-					break;
-				case INTEL_FAM6_ATOM_GOLDMONT_D:	/* DNV */
-					crystal_hz = 25000000;	/* 25.0 MHz */
-					break;
-				case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
-				case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
-					crystal_hz = 19200000;	/* 19.2 MHz */
-					break;
-				default:
-					crystal_hz = 0;
-				}
+				crystal_hz = platform->crystal_freq;
 
 			if (crystal_hz) {
 				tsc_hz = (unsigned long long)crystal_hz *ebx_tsc / eax_crystal;
@@ -5700,147 +5792,33 @@ void process_cpuid()
 	}
 
 	if (has_aperf)
-		aperf_mperf_multiplier = get_aperf_mperf_multiplier(family, model);
+		aperf_mperf_multiplier = platform->need_perf_multiplier ? 1024 : 1;
 
 	BIC_PRESENT(BIC_IRQ);
 	BIC_PRESENT(BIC_TSC_MHz);
+}
 
-	if (probe_nhm_msrs(family, model)) {
-		do_nhm_platform_info = 1;
-		BIC_PRESENT(BIC_CPU_c1);
-		BIC_PRESENT(BIC_CPU_c3);
-		BIC_PRESENT(BIC_CPU_c6);
-		BIC_PRESENT(BIC_SMI);
-	}
-	do_snb_cstates = has_snb_msrs(family, model);
-
-	if (do_snb_cstates)
-		BIC_PRESENT(BIC_CPU_c7);
-
-	do_irtl_snb = has_snb_msrs(family, model);
-	if (do_snb_cstates && (pkg_cstate_limit >= PCL__2))
-		BIC_PRESENT(BIC_Pkgpc2);
-	if (pkg_cstate_limit >= PCL__3)
-		BIC_PRESENT(BIC_Pkgpc3);
-	if (pkg_cstate_limit >= PCL__6)
-		BIC_PRESENT(BIC_Pkgpc6);
-	if (do_snb_cstates && (pkg_cstate_limit >= PCL__7))
-		BIC_PRESENT(BIC_Pkgpc7);
-	if (has_slv_msrs(family, model)) {
-		BIC_NOT_PRESENT(BIC_Pkgpc2);
-		BIC_NOT_PRESENT(BIC_Pkgpc3);
-		BIC_PRESENT(BIC_Pkgpc6);
-		BIC_NOT_PRESENT(BIC_Pkgpc7);
-		BIC_PRESENT(BIC_Mod_c6);
-		use_c1_residency_msr = 1;
-	}
-	if (is_jvl(family, model)) {
-		BIC_NOT_PRESENT(BIC_CPU_c3);
-		BIC_NOT_PRESENT(BIC_CPU_c7);
-		BIC_NOT_PRESENT(BIC_Pkgpc2);
-		BIC_NOT_PRESENT(BIC_Pkgpc3);
-		BIC_NOT_PRESENT(BIC_Pkgpc6);
-		BIC_NOT_PRESENT(BIC_Pkgpc7);
-	}
-	if (is_dnv(family, model)) {
-		BIC_PRESENT(BIC_CPU_c1);
-		BIC_NOT_PRESENT(BIC_CPU_c3);
-		BIC_NOT_PRESENT(BIC_Pkgpc3);
-		BIC_NOT_PRESENT(BIC_CPU_c7);
-		BIC_NOT_PRESENT(BIC_Pkgpc7);
-		use_c1_residency_msr = 1;
-	}
-	if (is_skx(family, model) || is_icx(family, model) || is_spr(family, model)) {
-		BIC_NOT_PRESENT(BIC_CPU_c3);
-		BIC_NOT_PRESENT(BIC_Pkgpc3);
-		BIC_NOT_PRESENT(BIC_CPU_c7);
-		BIC_NOT_PRESENT(BIC_Pkgpc7);
-	}
-	if (is_bdx(family, model)) {
-		BIC_NOT_PRESENT(BIC_CPU_c7);
-		BIC_NOT_PRESENT(BIC_Pkgpc7);
-	}
-	if (has_c8910_msrs(family, model)) {
-		if (pkg_cstate_limit >= PCL__8)
-			BIC_PRESENT(BIC_Pkgpc8);
-		if (pkg_cstate_limit >= PCL__9)
-			BIC_PRESENT(BIC_Pkgpc9);
-		if (pkg_cstate_limit >= PCL_10)
-			BIC_PRESENT(BIC_Pkgpc10);
-	}
-	do_irtl_hsw = has_c8910_msrs(family, model);
-	if (has_skl_msrs(family, model)) {
-		BIC_PRESENT(BIC_Totl_c0);
-		BIC_PRESENT(BIC_Any_c0);
-		BIC_PRESENT(BIC_GFX_c0);
-		BIC_PRESENT(BIC_CPUGFX);
-	}
-	do_slm_cstates = is_slm(family, model);
-	do_knl_cstates = is_knl(family, model);
-
-	if (do_slm_cstates || do_knl_cstates || is_cnl(family, model) || is_ehl(family, model))
-		BIC_NOT_PRESENT(BIC_CPU_c3);
-
-	if (!quiet)
-		decode_misc_pwr_mgmt_msr();
-
-	if (!quiet && has_slv_msrs(family, model))
-		decode_c6_demotion_policy_msr();
-
-	rapl_probe(family, model);
-	perf_limit_reasons_probe(family, model);
-	automatic_cstate_conversion_probe(family, model);
-
-	check_tcc_offset(model_orig);
-
-	if (!quiet)
-		dump_cstate_pstate_config_info(family, model);
-	intel_uncore_frequency_probe();
-
-	if (!quiet)
-		print_dev_latency();
-	if (!quiet)
-		dump_sysfs_cstate_config();
-	if (!quiet)
-		dump_sysfs_pstate_config();
+void probe_pm_features(void)
+{
+	probe_pstates();
 
-	if (has_skl_msrs(family, model) || is_ehl(family, model))
-		calculate_tsc_tweak();
+	probe_cstates();
 
-	if (!access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK))
-		BIC_PRESENT(BIC_GFX_rc6);
+	probe_lpi();
 
-	if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK))
-		BIC_PRESENT(BIC_GFXMHz);
+	probe_intel_uncore_frequency();
 
-	if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK))
-		BIC_PRESENT(BIC_GFXACTMHz);
+	probe_graphics();
 
-	if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", R_OK))
-		BIC_PRESENT(BIC_CPU_LPI);
-	else
-		BIC_NOT_PRESENT(BIC_CPU_LPI);
+	probe_rapl();
 
-	if (!access("/sys/devices/system/cpu/cpu0/thermal_throttle/core_throttle_count", R_OK))
-		BIC_PRESENT(BIC_CORE_THROT_CNT);
-	else
-		BIC_NOT_PRESENT(BIC_CORE_THROT_CNT);
+	probe_thermal();
 
-	if (!access(sys_lpi_file_sysfs, R_OK)) {
-		sys_lpi_file = sys_lpi_file_sysfs;
-		BIC_PRESENT(BIC_SYS_LPI);
-	} else if (!access(sys_lpi_file_debugfs, R_OK)) {
-		sys_lpi_file = sys_lpi_file_debugfs;
-		BIC_PRESENT(BIC_SYS_LPI);
-	} else {
-		sys_lpi_file_sysfs = NULL;
-		BIC_NOT_PRESENT(BIC_SYS_LPI);
-	}
+	if (platform->has_nhm_msrs)
+		BIC_PRESENT(BIC_SMI);
 
 	if (!quiet)
 		decode_misc_feature_control();
-
-	return;
 }
 
 /*
@@ -5855,7 +5833,7 @@ int dir_filter(const struct dirent *dirp)
 		return 0;
 }
 
-void topology_probe()
+void topology_probe(bool startup)
 {
 	int i;
 	int max_core_id = 0;
@@ -5888,14 +5866,62 @@ void topology_probe()
 	for_all_proc_cpus(mark_cpu_present);
 
 	/*
-	 * Validate that all cpus in cpu_subset are also in cpu_present_set
+	 * Allocate and initialize cpu_effective_set
+	 */
+	cpu_effective_set = CPU_ALLOC((topo.max_cpu_num + 1));
+	if (cpu_effective_set == NULL)
+		err(3, "CPU_ALLOC");
+	cpu_effective_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1));
+	CPU_ZERO_S(cpu_effective_setsize, cpu_effective_set);
+	update_effective_set(startup);
+
+	/*
+	 * Allocate and initialize cpu_allowed_set
+	 */
+	cpu_allowed_set = CPU_ALLOC((topo.max_cpu_num + 1));
+	if (cpu_allowed_set == NULL)
+		err(3, "CPU_ALLOC");
+	cpu_allowed_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1));
+	CPU_ZERO_S(cpu_allowed_setsize, cpu_allowed_set);
+
+	/*
+	 * Validate and update cpu_allowed_set.
+	 *
+	 * Make sure all cpus in cpu_subset are also in cpu_present_set during startup.
+	 * Give a warning when cpus in cpu_subset become unavailable at runtime.
+	 * Give a warning when cpus are not effective because of cgroup setting.
+	 *
+	 * cpu_allowed_set is the intersection of cpu_present_set/cpu_effective_set/cpu_subset.
 	 */
 	for (i = 0; i < CPU_SUBSET_MAXCPUS; ++i) {
-		if (CPU_ISSET_S(i, cpu_subset_size, cpu_subset))
-			if (!CPU_ISSET_S(i, cpu_present_setsize, cpu_present_set))
-				err(1, "cpu%d not present", i);
+		if (cpu_subset && !CPU_ISSET_S(i, cpu_subset_size, cpu_subset))
+			continue;
+
+		if (!CPU_ISSET_S(i, cpu_present_setsize, cpu_present_set)) {
+			if (cpu_subset) {
+				/* cpus in cpu_subset must be in cpu_present_set during startup */
+				if (startup)
+					err(1, "cpu%d not present", i);
+				else
+					fprintf(stderr, "cpu%d not present\n", i);
+			}
+			continue;
+		}
+
+		if (CPU_COUNT_S(cpu_effective_setsize, cpu_effective_set)) {
+			if (!CPU_ISSET_S(i, cpu_effective_setsize, cpu_effective_set)) {
+				fprintf(stderr, "cpu%d not effective\n", i);
+				continue;
+			}
+		}
+
+		CPU_SET_S(i, cpu_allowed_setsize, cpu_allowed_set);
 	}
 
+	if (!CPU_COUNT_S(cpu_allowed_setsize, cpu_allowed_set))
+		err(-ENODEV, "No valid cpus found");
+	sched_setaffinity(0, cpu_allowed_setsize, cpu_allowed_set);
+
 	/*
 	 * Allocate and initialize cpu_affinity_set
 	 */
@@ -6009,15 +6035,19 @@ void allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_
 	if (*c == NULL)
 		goto error;
 
-	for (i = 0; i < num_cores; i++)
+	for (i = 0; i < num_cores; i++) {
 		(*c)[i].core_id = -1;
+		(*c)[i].base_cpu = -1;
+	}
 
 	*p = calloc(topo.num_packages, sizeof(struct pkg_data));
 	if (*p == NULL)
 		goto error;
 
-	for (i = 0; i < topo.num_packages; i++)
+	for (i = 0; i < topo.num_packages; i++) {
 		(*p)[i].package_id = i;
+		(*p)[i].base_cpu = -1;
+	}
 
 	return;
 error:
@@ -6050,10 +6080,11 @@ void init_counter(struct thread_data *thread_base, struct core_data *core_base,
 	p = GET_PKG(pkg_base, pkg_id);
 
 	t->cpu_id = cpu_id;
-	if (thread_id == 0) {
-		t->flags |= CPU_IS_FIRST_THREAD_IN_CORE;
-		if (cpu_is_first_core_in_package(cpu_id))
-			t->flags |= CPU_IS_FIRST_CORE_IN_PACKAGE;
+	if (!cpu_is_not_allowed(cpu_id)) {
+		if (c->base_cpu < 0)
+			c->base_cpu = t->cpu_id;
+		if (p->base_cpu < 0)
+			p->base_cpu = t->cpu_id;
 	}
 
 	c->core_id = core_id;
@@ -6093,59 +6124,64 @@ void allocate_irq_buffers(void)
 		err(-1, "calloc %d", topo.max_cpu_num + 1);
 }
 
-void setup_all_buffers(void)
+int update_topo(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+	topo.allowed_cpus++;
+	if ((int)t->cpu_id == c->base_cpu)
+		topo.allowed_cores++;
+	if ((int)t->cpu_id == p->base_cpu)
+		topo.allowed_packages++;
+
+	return 0;
+}
+
+void topology_update(void)
 {
-	topology_probe();
+	topo.allowed_cpus = 0;
+	topo.allowed_cores = 0;
+	topo.allowed_packages = 0;
+	for_all_cpus(update_topo, ODD_COUNTERS);
+}
+void setup_all_buffers(bool startup)
+{
+	topology_probe(startup);
 	allocate_irq_buffers();
 	allocate_fd_percpu();
 	allocate_counters(&thread_even, &core_even, &package_even);
 	allocate_counters(&thread_odd, &core_odd, &package_odd);
 	allocate_output_buffer();
 	for_all_proc_cpus(initialize_counters);
+	topology_update();
 }
 
 void set_base_cpu(void)
 {
-	base_cpu = sched_getcpu();
-	if (base_cpu < 0)
-		err(-ENODEV, "No valid cpus found");
+	int i;
 
-	if (debug > 1)
-		fprintf(outf, "base_cpu = %d\n", base_cpu);
+	for (i = 0; i < topo.max_cpu_num + 1; ++i) {
+		if (cpu_is_not_allowed(i))
+			continue;
+		base_cpu = i;
+		if (debug > 1)
+			fprintf(outf, "base_cpu = %d\n", base_cpu);
+		return;
+	}
+	err(-ENODEV, "No valid cpus found");
 }
 
 void turbostat_init()
 {
-	setup_all_buffers();
+	setup_all_buffers(true);
 	set_base_cpu();
 	check_dev_msr();
 	check_permissions();
 	process_cpuid();
+	probe_pm_features();
 	linux_perf_init();
 
-	if (!quiet)
-		for_all_cpus(print_hwp, ODD_COUNTERS);
-
-	if (!quiet)
-		for_all_cpus(print_epb, ODD_COUNTERS);
-
-	if (!quiet)
-		for_all_cpus(print_perf_limit, ODD_COUNTERS);
-
-	if (!quiet)
-		for_all_cpus(print_rapl, ODD_COUNTERS);
-
-	for_all_cpus(set_temperature_target, ODD_COUNTERS);
-
 	for_all_cpus(get_cpu_type, ODD_COUNTERS);
 	for_all_cpus(get_cpu_type, EVEN_COUNTERS);
 
-	if (!quiet)
-		for_all_cpus(print_thermal, ODD_COUNTERS);
-
-	if (!quiet && do_irtl_snb)
-		print_irtl();
-
 	if (DO_BIC(BIC_IPC))
 		(void)get_instr_count_fd(base_cpu);
 }
@@ -6160,8 +6196,6 @@ int fork_it(char **argv)
 	first_counter_read = 0;
 	if (status)
 		exit(status);
-	/* clear affinity side-effect of get_counters() */
-	sched_setaffinity(0, cpu_present_setsize, cpu_present_set);
 	gettimeofday(&tv_even, (struct timezone *)NULL);
 
 	child_pid = fork();
@@ -6225,7 +6259,7 @@ int get_and_dump_counters(void)
 
 void print_version()
 {
-	fprintf(outf, "turbostat version 2023.03.17 - Len Brown <lenb@kernel.org>\n");
+	fprintf(outf, "turbostat version 2023.11.07 - Len Brown <lenb@kernel.org>\n");
 }
 
 #define COMMAND_LINE_SIZE 2048
@@ -6508,9 +6542,6 @@ void probe_sysfs(void)
  */
 void parse_cpu_command(char *optarg)
 {
-	unsigned int start, end;
-	char *next;
-
 	if (!strcmp(optarg, "core")) {
 		if (cpu_subset)
 			goto error;
@@ -6533,52 +6564,8 @@ void parse_cpu_command(char *optarg)
 
 	CPU_ZERO_S(cpu_subset_size, cpu_subset);
 
-	next = optarg;
-
-	while (next && *next) {
-
-		if (*next == '-')	/* no negative cpu numbers */
-			goto error;
-
-		start = strtoul(next, &next, 10);
-
-		if (start >= CPU_SUBSET_MAXCPUS)
-			goto error;
-		CPU_SET_S(start, cpu_subset_size, cpu_subset);
-
-		if (*next == '\0')
-			break;
-
-		if (*next == ',') {
-			next += 1;
-			continue;
-		}
-
-		if (*next == '-') {
-			next += 1;	/* start range */
-		} else if (*next == '.') {
-			next += 1;
-			if (*next == '.')
-				next += 1;	/* start range */
-			else
-				goto error;
-		}
-
-		end = strtoul(next, &next, 10);
-		if (end <= start)
-			goto error;
-
-		while (++start <= end) {
-			if (start >= CPU_SUBSET_MAXCPUS)
-				goto error;
-			CPU_SET_S(start, cpu_subset_size, cpu_subset);
-		}
-
-		if (*next == ',')
-			next += 1;
-		else if (*next != '\0')
-			goto error;
-	}
+	if (parse_cpu_str(optarg, cpu_subset, cpu_subset_size))
+		goto error;
 
 	return;
 
@@ -6719,6 +6706,19 @@ void cmdline(int argc, char **argv)
 
 int main(int argc, char **argv)
 {
+	int fd, ret;
+
+	fd = open("/sys/fs/cgroup/cgroup.procs", O_WRONLY);
+	if (fd < 0)
+		goto skip_cgroup_setting;
+
+	ret = write(fd, "0\n", 2);
+	if (ret == -1)
+		perror("Can't update cgroup\n");
+
+	close(fd);
+
+skip_cgroup_setting:
 	outf = stderr;
 	cmdline(argc, argv);
 
diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild
index 90f3c9802ffb..95dc58b94178 100644
--- a/tools/testing/cxl/Kbuild
+++ b/tools/testing/cxl/Kbuild
@@ -62,5 +62,6 @@ cxl_core-$(CONFIG_TRACING) += $(CXL_CORE_SRC)/trace.o
 cxl_core-$(CONFIG_CXL_REGION) += $(CXL_CORE_SRC)/region.o
 cxl_core-y += config_check.o
 cxl_core-y += cxl_core_test.o
+cxl_core-y += cxl_core_exports.o
 
 obj-m += test/
diff --git a/tools/testing/cxl/cxl_core_exports.c b/tools/testing/cxl/cxl_core_exports.c
new file mode 100644
index 000000000000..077e6883921d
--- /dev/null
+++ b/tools/testing/cxl/cxl_core_exports.c
@@ -0,0 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2022 Intel Corporation. All rights reserved. */
+
+#include "cxl.h"
+
+/* Exporting of cxl_core symbols that are only used by cxl_test */
+EXPORT_SYMBOL_NS_GPL(cxl_num_decoders_committed, CXL);
diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c
index b88546299902..f4e517a0c774 100644
--- a/tools/testing/cxl/test/cxl.c
+++ b/tools/testing/cxl/test/cxl.c
@@ -669,10 +669,11 @@ static int mock_decoder_commit(struct cxl_decoder *cxld)
 		return 0;
 
 	dev_dbg(&port->dev, "%s commit\n", dev_name(&cxld->dev));
-	if (port->commit_end + 1 != id) {
+	if (cxl_num_decoders_committed(port) != id) {
 		dev_dbg(&port->dev,
 			"%s: out of order commit, expected decoder%d.%d\n",
-			dev_name(&cxld->dev), port->id, port->commit_end + 1);
+			dev_name(&cxld->dev), port->id,
+			cxl_num_decoders_committed(port));
 		return -EBUSY;
 	}
 
diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py
index 79d8832c862a..ce34be15c929 100644
--- a/tools/testing/kunit/kunit_parser.py
+++ b/tools/testing/kunit/kunit_parser.py
@@ -450,7 +450,7 @@ def parse_diagnostic(lines: LineStream) -> List[str]:
 	Log of diagnostic lines
 	"""
 	log = []  # type: List[str]
-	non_diagnostic_lines = [TEST_RESULT, TEST_HEADER, KTAP_START, TAP_START]
+	non_diagnostic_lines = [TEST_RESULT, TEST_HEADER, KTAP_START, TAP_START, TEST_PLAN]
 	while lines and not any(re.match(lines.peek())
 			for re in non_diagnostic_lines):
 		log.append(lines.pop())
@@ -726,6 +726,7 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest:
 		# test plan
 		test.name = "main"
 		ktap_line = parse_ktap_header(lines, test)
+		test.log.extend(parse_diagnostic(lines))
 		parse_test_plan(lines, test)
 		parent_test = True
 	else:
@@ -737,6 +738,7 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest:
 		if parent_test:
 			# If KTAP version line and/or subtest header is found, attempt
 			# to parse test plan and print test header
+			test.log.extend(parse_diagnostic(lines))
 			parse_test_plan(lines, test)
 			print_test_header(test)
 	expected_count = test.expected_count
diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py
index b28c1510be2e..2beb7327e53f 100755
--- a/tools/testing/kunit/kunit_tool_test.py
+++ b/tools/testing/kunit/kunit_tool_test.py
@@ -331,6 +331,22 @@ class KUnitParserTest(unittest.TestCase):
 			kunit_parser.parse_run_tests(file.readlines())
 		self.print_mock.assert_any_call(StrContains('suite (1 subtest)'))
 
+	def test_parse_attributes(self):
+		ktap_log = test_data_path('test_parse_attributes.log')
+		with open(ktap_log) as file:
+			result = kunit_parser.parse_run_tests(file.readlines())
+
+		# Test should pass with no errors
+		self.assertEqual(result.counts, kunit_parser.TestCounts(passed=1, errors=0))
+		self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status)
+
+		# Ensure suite header is parsed correctly
+		self.print_mock.assert_any_call(StrContains('suite (1 subtest)'))
+
+		# Ensure attributes in correct test log
+		self.assertContains('# module: example', result.subtests[0].log)
+		self.assertContains('# test.speed: slow', result.subtests[0].subtests[0].log)
+
 	def test_show_test_output_on_failure(self):
 		output = """
 		KTAP version 1
diff --git a/tools/testing/kunit/test_data/test_parse_attributes.log b/tools/testing/kunit/test_data/test_parse_attributes.log
new file mode 100644
index 000000000000..1a13c371fe9d
--- /dev/null
+++ b/tools/testing/kunit/test_data/test_parse_attributes.log
@@ -0,0 +1,9 @@
+KTAP version 1
+1..1
+  KTAP version 1
+  # Subtest: suite
+  # module: example
+  1..1
+  # test.speed: slow
+  ok 1 test
+ok 1 suite
\ No newline at end of file
diff --git a/tools/testing/memblock/linux/mmzone.h b/tools/testing/memblock/linux/mmzone.h
index 134f8eab0768..71546e15bdd3 100644
--- a/tools/testing/memblock/linux/mmzone.h
+++ b/tools/testing/memblock/linux/mmzone.h
@@ -17,10 +17,10 @@ enum zone_type {
 };
 
 #define MAX_NR_ZONES __MAX_NR_ZONES
-#define MAX_ORDER 10
-#define MAX_ORDER_NR_PAGES (1 << MAX_ORDER)
+#define MAX_PAGE_ORDER 10
+#define MAX_ORDER_NR_PAGES (1 << MAX_PAGE_ORDER)
 
-#define pageblock_order		MAX_ORDER
+#define pageblock_order		MAX_PAGE_ORDER
 #define pageblock_nr_pages	BIT(pageblock_order)
 #define pageblock_align(pfn)	ALIGN((pfn), pageblock_nr_pages)
 #define pageblock_start_pfn(pfn)	ALIGN_DOWN((pfn), pageblock_nr_pages)
diff --git a/tools/testing/nvdimm/test/ndtest.c b/tools/testing/nvdimm/test/ndtest.c
index fd26189d53be..b8419f460368 100644
--- a/tools/testing/nvdimm/test/ndtest.c
+++ b/tools/testing/nvdimm/test/ndtest.c
@@ -924,7 +924,7 @@ static __init int ndtest_init(void)
 
 	nfit_test_setup(ndtest_resource_lookup, NULL);
 
-	rc = class_regster(&ndtest_dimm_class);
+	rc = class_register(&ndtest_dimm_class);
 	if (rc)
 		goto err_register;
 
diff --git a/tools/testing/radix-tree/linux.c b/tools/testing/radix-tree/linux.c
index 61fe2601cb3a..4eb442206d01 100644
--- a/tools/testing/radix-tree/linux.c
+++ b/tools/testing/radix-tree/linux.c
@@ -93,13 +93,9 @@ void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru,
 	return p;
 }
 
-void kmem_cache_free_locked(struct kmem_cache *cachep, void *objp)
+void __kmem_cache_free_locked(struct kmem_cache *cachep, void *objp)
 {
 	assert(objp);
-	uatomic_dec(&nr_allocated);
-	uatomic_dec(&cachep->nr_allocated);
-	if (kmalloc_verbose)
-		printf("Freeing %p to slab\n", objp);
 	if (cachep->nr_objs > 10 || cachep->align) {
 		memset(objp, POISON_FREE, cachep->size);
 		free(objp);
@@ -111,6 +107,15 @@ void kmem_cache_free_locked(struct kmem_cache *cachep, void *objp)
 	}
 }
 
+void kmem_cache_free_locked(struct kmem_cache *cachep, void *objp)
+{
+	uatomic_dec(&nr_allocated);
+	uatomic_dec(&cachep->nr_allocated);
+	if (kmalloc_verbose)
+		printf("Freeing %p to slab\n", objp);
+	__kmem_cache_free_locked(cachep, objp);
+}
+
 void kmem_cache_free(struct kmem_cache *cachep, void *objp)
 {
 	pthread_mutex_lock(&cachep->lock);
@@ -141,18 +146,17 @@ int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size,
 	if (kmalloc_verbose)
 		pr_debug("Bulk alloc %lu\n", size);
 
-	if (!(gfp & __GFP_DIRECT_RECLAIM)) {
-		if (cachep->non_kernel < size)
-			return 0;
-
-		cachep->non_kernel -= size;
-	}
-
 	pthread_mutex_lock(&cachep->lock);
 	if (cachep->nr_objs >= size) {
 		struct radix_tree_node *node;
 
 		for (i = 0; i < size; i++) {
+			if (!(gfp & __GFP_DIRECT_RECLAIM)) {
+				if (!cachep->non_kernel)
+					break;
+				cachep->non_kernel--;
+			}
+
 			node = cachep->objs;
 			cachep->nr_objs--;
 			cachep->objs = node->parent;
@@ -163,11 +167,19 @@ int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size,
 	} else {
 		pthread_mutex_unlock(&cachep->lock);
 		for (i = 0; i < size; i++) {
+			if (!(gfp & __GFP_DIRECT_RECLAIM)) {
+				if (!cachep->non_kernel)
+					break;
+				cachep->non_kernel--;
+			}
+
 			if (cachep->align) {
 				posix_memalign(&p[i], cachep->align,
 					       cachep->size);
 			} else {
 				p[i] = malloc(cachep->size);
+				if (!p[i])
+					break;
 			}
 			if (cachep->ctor)
 				cachep->ctor(p[i]);
@@ -176,6 +188,15 @@ int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size,
 		}
 	}
 
+	if (i < size) {
+		size = i;
+		pthread_mutex_lock(&cachep->lock);
+		for (i = 0; i < size; i++)
+			__kmem_cache_free_locked(cachep, p[i]);
+		pthread_mutex_unlock(&cachep->lock);
+		return 0;
+	}
+
 	for (i = 0; i < size; i++) {
 		uatomic_inc(&nr_allocated);
 		uatomic_inc(&cachep->nr_allocated);
diff --git a/tools/testing/radix-tree/linux/maple_tree.h b/tools/testing/radix-tree/linux/maple_tree.h
index 7d8d1f445b89..06c89bdcc515 100644
--- a/tools/testing/radix-tree/linux/maple_tree.h
+++ b/tools/testing/radix-tree/linux/maple_tree.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0+ */
 #define atomic_t int32_t
-#include "../../../../include/linux/maple_tree.h"
 #define atomic_inc(x) uatomic_inc(x)
 #define atomic_read(x) uatomic_read(x)
 #define atomic_set(x, y) do {} while (0)
 #define U8_MAX UCHAR_MAX
+#include "../../../../include/linux/maple_tree.h"
diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c
index e5da1cad70ba..f1caf4bcf937 100644
--- a/tools/testing/radix-tree/maple.c
+++ b/tools/testing/radix-tree/maple.c
@@ -118,6 +118,7 @@ static noinline void __init check_new_node(struct maple_tree *mt)
 	MT_BUG_ON(mt, mas.alloc == NULL);
 	MT_BUG_ON(mt, mas.alloc->slot[0] == NULL);
 	mas_push_node(&mas, mn);
+	mas_reset(&mas);
 	mas_nomem(&mas, GFP_KERNEL); /* free */
 	mtree_unlock(mt);
 
@@ -141,7 +142,7 @@ static noinline void __init check_new_node(struct maple_tree *mt)
 
 	mn->parent = ma_parent_ptr(mn);
 	ma_free_rcu(mn);
-	mas.node = MAS_START;
+	mas.status = ma_start;
 	mas_nomem(&mas, GFP_KERNEL);
 	/* Allocate 3 nodes, will fail. */
 	mas_node_count(&mas, 3);
@@ -158,6 +159,7 @@ static noinline void __init check_new_node(struct maple_tree *mt)
 	/* Ensure we counted 3. */
 	MT_BUG_ON(mt, mas_allocated(&mas) != 3);
 	/* Free. */
+	mas_reset(&mas);
 	mas_nomem(&mas, GFP_KERNEL);
 
 	/* Set allocation request to 1. */
@@ -272,6 +274,7 @@ static noinline void __init check_new_node(struct maple_tree *mt)
 			ma_free_rcu(mn);
 			MT_BUG_ON(mt, mas_allocated(&mas) != i - j - 1);
 		}
+		mas_reset(&mas);
 		MT_BUG_ON(mt, mas_nomem(&mas, GFP_KERNEL));
 
 	}
@@ -294,6 +297,7 @@ static noinline void __init check_new_node(struct maple_tree *mt)
 		smn = smn->slot[0]; /* next. */
 	}
 	MT_BUG_ON(mt, mas_allocated(&mas) != total);
+	mas_reset(&mas);
 	mas_nomem(&mas, GFP_KERNEL); /* Free. */
 
 	MT_BUG_ON(mt, mas_allocated(&mas) != 0);
@@ -441,7 +445,7 @@ static noinline void __init check_new_node(struct maple_tree *mt)
 	mas.node = MA_ERROR(-ENOMEM);
 	mas_node_count(&mas, 10); /* Request */
 	mas_nomem(&mas, GFP_KERNEL); /* Fill request */
-	mas.node = MAS_START;
+	mas.status = ma_start;
 	MT_BUG_ON(mt, mas_allocated(&mas) != 10);
 	mas_destroy(&mas);
 
@@ -452,7 +456,7 @@ static noinline void __init check_new_node(struct maple_tree *mt)
 	mas.node = MA_ERROR(-ENOMEM);
 	mas_node_count(&mas, 10 + MAPLE_ALLOC_SLOTS - 1); /* Request */
 	mas_nomem(&mas, GFP_KERNEL); /* Fill request */
-	mas.node = MAS_START;
+	mas.status = ma_start;
 	MT_BUG_ON(mt, mas_allocated(&mas) != 10 + MAPLE_ALLOC_SLOTS - 1);
 	mas_destroy(&mas);
 
@@ -941,10 +945,11 @@ retry:
 
 	ret = mas_descend_walk(mas, range_min, range_max);
 	if (unlikely(mte_dead_node(mas->node))) {
-		mas->node = MAS_START;
+		mas->status = ma_start;
 		goto retry;
 	}
 
+	mas->end = mas_data_end(mas);
 	return ret;
 
 not_found:
@@ -960,17 +965,19 @@ static inline void *mas_range_load(struct ma_state *mas,
 	unsigned long index = mas->index;
 
 	if (mas_is_none(mas) || mas_is_paused(mas))
-		mas->node = MAS_START;
+		mas->status = ma_start;
 retry:
 	if (mas_tree_walk(mas, range_min, range_max))
-		if (unlikely(mas->node == MAS_ROOT))
+		if (unlikely(mas->status == ma_root))
 			return mas_root(mas);
 
 	if (likely(mas->offset != MAPLE_NODE_SLOTS))
 		entry = mas_get_slot(mas, mas->offset);
 
-	if (mas_dead_node(mas, index))
+	if (mas_is_active(mas) && mte_dead_node(mas->node)) {
+		mas_set(mas, index);
 		goto retry;
+	}
 
 	return entry;
 }
@@ -34132,7 +34139,7 @@ STORE, 140501948112896, 140501948116991,
 	mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE);
 	check_erase2_testset(mt, set27, ARRAY_SIZE(set27));
 	rcu_barrier();
-	MT_BUG_ON(mt, 0 != mtree_load(mt, 140415537422336));
+	MT_BUG_ON(mt, NULL != mtree_load(mt, 140415537422336));
 	mt_set_non_kernel(0);
 	mt_validate(mt);
 	mtree_destroy(mt);
@@ -34256,7 +34263,7 @@ STORE, 140501948112896, 140501948116991,
 	mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE);
 	check_erase2_testset(mt, set37, ARRAY_SIZE(set37));
 	rcu_barrier();
-	MT_BUG_ON(mt, 0 != mtree_load(mt, 94637033459712));
+	MT_BUG_ON(mt, NULL != mtree_load(mt, 94637033459712));
 	mt_validate(mt);
 	mtree_destroy(mt);
 
@@ -34264,7 +34271,7 @@ STORE, 140501948112896, 140501948116991,
 	mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE);
 	check_erase2_testset(mt, set38, ARRAY_SIZE(set38));
 	rcu_barrier();
-	MT_BUG_ON(mt, 0 != mtree_load(mt, 94637033459712));
+	MT_BUG_ON(mt, NULL != mtree_load(mt, 94637033459712));
 	mt_validate(mt);
 	mtree_destroy(mt);
 
@@ -35336,7 +35343,7 @@ static void mas_dfs_preorder(struct ma_state *mas)
 	unsigned char end, slot = 0;
 	unsigned long *pivots;
 
-	if (mas->node == MAS_START) {
+	if (mas->status == ma_start) {
 		mas_start(mas);
 		return;
 	}
@@ -35373,7 +35380,7 @@ walk_up:
 
 	return;
 done:
-	mas->node = MAS_NONE;
+	mas->status = ma_none;
 }
 
 
@@ -35538,7 +35545,7 @@ static noinline void __init check_prealloc(struct maple_tree *mt)
 	MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0);
 	allocated = mas_allocated(&mas);
 	height = mas_mt_height(&mas);
-	MT_BUG_ON(mt, allocated != 1);
+	MT_BUG_ON(mt, allocated != 0);
 	mas_store_prealloc(&mas, ptr);
 	MT_BUG_ON(mt, mas_allocated(&mas) != 0);
 
@@ -35832,7 +35839,7 @@ static noinline void __init check_nomem(struct maple_tree *mt)
 	mas_store(&ms, &ms); /* insert 1 -> &ms, fails. */
 	MT_BUG_ON(mt, ms.node != MA_ERROR(-ENOMEM));
 	mas_nomem(&ms, GFP_KERNEL); /* Node allocated in here. */
-	MT_BUG_ON(mt, ms.node != MAS_START);
+	MT_BUG_ON(mt, ms.status != ma_start);
 	mtree_unlock(mt);
 	MT_BUG_ON(mt, mtree_insert(mt, 2, mt, GFP_KERNEL) != 0);
 	mtree_lock(mt);
@@ -35857,6 +35864,363 @@ static noinline void __init check_locky(struct maple_tree *mt)
 	mt_clear_in_rcu(mt);
 }
 
+/*
+ * Compares two nodes except for the addresses stored in the nodes.
+ * Returns zero if they are the same, otherwise returns non-zero.
+ */
+static int __init compare_node(struct maple_enode *enode_a,
+			       struct maple_enode *enode_b)
+{
+	struct maple_node *node_a, *node_b;
+	struct maple_node a, b;
+	void **slots_a, **slots_b; /* Do not use the rcu tag. */
+	enum maple_type type;
+	int i;
+
+	if (((unsigned long)enode_a & MAPLE_NODE_MASK) !=
+	    ((unsigned long)enode_b & MAPLE_NODE_MASK)) {
+		pr_err("The lower 8 bits of enode are different.\n");
+		return -1;
+	}
+
+	type = mte_node_type(enode_a);
+	node_a = mte_to_node(enode_a);
+	node_b = mte_to_node(enode_b);
+	a = *node_a;
+	b = *node_b;
+
+	/* Do not compare addresses. */
+	if (ma_is_root(node_a) || ma_is_root(node_b)) {
+		a.parent = (struct maple_pnode *)((unsigned long)a.parent &
+						  MA_ROOT_PARENT);
+		b.parent = (struct maple_pnode *)((unsigned long)b.parent &
+						  MA_ROOT_PARENT);
+	} else {
+		a.parent = (struct maple_pnode *)((unsigned long)a.parent &
+						  MAPLE_NODE_MASK);
+		b.parent = (struct maple_pnode *)((unsigned long)b.parent &
+						  MAPLE_NODE_MASK);
+	}
+
+	if (a.parent != b.parent) {
+		pr_err("The lower 8 bits of parents are different. %p %p\n",
+			a.parent, b.parent);
+		return -1;
+	}
+
+	/*
+	 * If it is a leaf node, the slots do not contain the node address, and
+	 * no special processing of slots is required.
+	 */
+	if (ma_is_leaf(type))
+		goto cmp;
+
+	slots_a = ma_slots(&a, type);
+	slots_b = ma_slots(&b, type);
+
+	for (i = 0; i < mt_slots[type]; i++) {
+		if (!slots_a[i] && !slots_b[i])
+			break;
+
+		if (!slots_a[i] || !slots_b[i]) {
+			pr_err("The number of slots is different.\n");
+			return -1;
+		}
+
+		/* Do not compare addresses in slots. */
+		((unsigned long *)slots_a)[i] &= MAPLE_NODE_MASK;
+		((unsigned long *)slots_b)[i] &= MAPLE_NODE_MASK;
+	}
+
+cmp:
+	/*
+	 * Compare all contents of two nodes, including parent (except address),
+	 * slots (except address), pivots, gaps and metadata.
+	 */
+	return memcmp(&a, &b, sizeof(struct maple_node));
+}
+
+/*
+ * Compare two trees and return 0 if they are the same, non-zero otherwise.
+ */
+static int __init compare_tree(struct maple_tree *mt_a, struct maple_tree *mt_b)
+{
+	MA_STATE(mas_a, mt_a, 0, 0);
+	MA_STATE(mas_b, mt_b, 0, 0);
+
+	if (mt_a->ma_flags != mt_b->ma_flags) {
+		pr_err("The flags of the two trees are different.\n");
+		return -1;
+	}
+
+	mas_dfs_preorder(&mas_a);
+	mas_dfs_preorder(&mas_b);
+
+	if (mas_is_ptr(&mas_a) || mas_is_ptr(&mas_b)) {
+		if (!(mas_is_ptr(&mas_a) && mas_is_ptr(&mas_b))) {
+			pr_err("One is ma_root and the other is not.\n");
+			return -1;
+		}
+		return 0;
+	}
+
+	while (!mas_is_none(&mas_a) || !mas_is_none(&mas_b)) {
+
+		if (mas_is_none(&mas_a) || mas_is_none(&mas_b)) {
+			pr_err("One is ma_none and the other is not.\n");
+			return -1;
+		}
+
+		if (mas_a.min != mas_b.min ||
+		    mas_a.max != mas_b.max) {
+			pr_err("mas->min, mas->max do not match.\n");
+			return -1;
+		}
+
+		if (compare_node(mas_a.node, mas_b.node)) {
+			pr_err("The contents of nodes %p and %p are different.\n",
+			       mas_a.node, mas_b.node);
+			mt_dump(mt_a, mt_dump_dec);
+			mt_dump(mt_b, mt_dump_dec);
+			return -1;
+		}
+
+		mas_dfs_preorder(&mas_a);
+		mas_dfs_preorder(&mas_b);
+	}
+
+	return 0;
+}
+
+static __init void mas_subtree_max_range(struct ma_state *mas)
+{
+	unsigned long limit = mas->max;
+	MA_STATE(newmas, mas->tree, 0, 0);
+	void *entry;
+
+	mas_for_each(mas, entry, limit) {
+		if (mas->last - mas->index >=
+		    newmas.last - newmas.index) {
+			newmas = *mas;
+		}
+	}
+
+	*mas = newmas;
+}
+
+/*
+ * build_full_tree() - Build a full tree.
+ * @mt: The tree to build.
+ * @flags: Use @flags to build the tree.
+ * @height: The height of the tree to build.
+ *
+ * Build a tree with full leaf nodes and internal nodes. Note that the height
+ * should not exceed 3, otherwise it will take a long time to build.
+ * Return: zero if the build is successful, non-zero if it fails.
+ */
+static __init int build_full_tree(struct maple_tree *mt, unsigned int flags,
+		int height)
+{
+	MA_STATE(mas, mt, 0, 0);
+	unsigned long step;
+	int ret = 0, cnt = 1;
+	enum maple_type type;
+
+	mt_init_flags(mt, flags);
+	mtree_insert_range(mt, 0, ULONG_MAX, xa_mk_value(5), GFP_KERNEL);
+
+	mtree_lock(mt);
+
+	while (1) {
+		mas_set(&mas, 0);
+		if (mt_height(mt) < height) {
+			mas.max = ULONG_MAX;
+			goto store;
+		}
+
+		while (1) {
+			mas_dfs_preorder(&mas);
+			if (mas_is_none(&mas))
+				goto unlock;
+
+			type = mte_node_type(mas.node);
+			if (mas_data_end(&mas) + 1 < mt_slots[type]) {
+				mas_set(&mas, mas.min);
+				goto store;
+			}
+		}
+store:
+		mas_subtree_max_range(&mas);
+		step = mas.last - mas.index;
+		if (step < 1) {
+			ret = -1;
+			goto unlock;
+		}
+
+		step /= 2;
+		mas.last = mas.index + step;
+		mas_store_gfp(&mas, xa_mk_value(5),
+				GFP_KERNEL);
+		++cnt;
+	}
+unlock:
+	mtree_unlock(mt);
+
+	MT_BUG_ON(mt, mt_height(mt) != height);
+	/* pr_info("height:%u number of elements:%d\n", mt_height(mt), cnt); */
+	return ret;
+}
+
+static noinline void __init check_mtree_dup(struct maple_tree *mt)
+{
+	DEFINE_MTREE(new);
+	int i, j, ret, count = 0;
+	unsigned int rand_seed = 17, rand;
+
+	/* store a value at [0, 0] */
+	mt_init_flags(mt, 0);
+	mtree_store_range(mt, 0, 0, xa_mk_value(0), GFP_KERNEL);
+	ret = mtree_dup(mt, &new, GFP_KERNEL);
+	MT_BUG_ON(&new, ret);
+	mt_validate(&new);
+	if (compare_tree(mt, &new))
+		MT_BUG_ON(&new, 1);
+
+	mtree_destroy(mt);
+	mtree_destroy(&new);
+
+	/* The two trees have different attributes. */
+	mt_init_flags(mt, 0);
+	mt_init_flags(&new, MT_FLAGS_ALLOC_RANGE);
+	ret = mtree_dup(mt, &new, GFP_KERNEL);
+	MT_BUG_ON(&new, ret != -EINVAL);
+	mtree_destroy(mt);
+	mtree_destroy(&new);
+
+	/* The new tree is not empty */
+	mt_init_flags(mt, 0);
+	mt_init_flags(&new, 0);
+	mtree_store(&new, 5, xa_mk_value(5), GFP_KERNEL);
+	ret = mtree_dup(mt, &new, GFP_KERNEL);
+	MT_BUG_ON(&new, ret != -EINVAL);
+	mtree_destroy(mt);
+	mtree_destroy(&new);
+
+	/* Test for duplicating full trees. */
+	for (i = 1; i <= 3; i++) {
+		ret = build_full_tree(mt, 0, i);
+		MT_BUG_ON(mt, ret);
+		mt_init_flags(&new, 0);
+
+		ret = mtree_dup(mt, &new, GFP_KERNEL);
+		MT_BUG_ON(&new, ret);
+		mt_validate(&new);
+		if (compare_tree(mt, &new))
+			MT_BUG_ON(&new, 1);
+
+		mtree_destroy(mt);
+		mtree_destroy(&new);
+	}
+
+	for (i = 1; i <= 3; i++) {
+		ret = build_full_tree(mt, MT_FLAGS_ALLOC_RANGE, i);
+		MT_BUG_ON(mt, ret);
+		mt_init_flags(&new, MT_FLAGS_ALLOC_RANGE);
+
+		ret = mtree_dup(mt, &new, GFP_KERNEL);
+		MT_BUG_ON(&new, ret);
+		mt_validate(&new);
+		if (compare_tree(mt, &new))
+			MT_BUG_ON(&new, 1);
+
+		mtree_destroy(mt);
+		mtree_destroy(&new);
+	}
+
+	/* Test for normal duplicating. */
+	for (i = 0; i < 1000; i += 3) {
+		if (i & 1) {
+			mt_init_flags(mt, 0);
+			mt_init_flags(&new, 0);
+		} else {
+			mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE);
+			mt_init_flags(&new, MT_FLAGS_ALLOC_RANGE);
+		}
+
+		for (j = 0; j < i; j++) {
+			mtree_store_range(mt, j * 10, j * 10 + 5,
+					  xa_mk_value(j), GFP_KERNEL);
+		}
+
+		ret = mtree_dup(mt, &new, GFP_KERNEL);
+		MT_BUG_ON(&new, ret);
+		mt_validate(&new);
+		if (compare_tree(mt, &new))
+			MT_BUG_ON(&new, 1);
+
+		mtree_destroy(mt);
+		mtree_destroy(&new);
+	}
+
+	/* Test memory allocation failed. */
+	mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE);
+	for (i = 0; i < 30; i += 3) {
+		mtree_store_range(mt, j * 10, j * 10 + 5,
+					  xa_mk_value(j), GFP_KERNEL);
+	}
+
+	/* Failed at the first node. */
+	mt_init_flags(&new, MT_FLAGS_ALLOC_RANGE);
+	mt_set_non_kernel(0);
+	ret = mtree_dup(mt, &new, GFP_NOWAIT);
+	mt_set_non_kernel(0);
+	MT_BUG_ON(&new, ret != -ENOMEM);
+	mtree_destroy(mt);
+	mtree_destroy(&new);
+
+	/* Random maple tree fails at a random node. */
+	for (i = 0; i < 1000; i += 3) {
+		if (i & 1) {
+			mt_init_flags(mt, 0);
+			mt_init_flags(&new, 0);
+		} else {
+			mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE);
+			mt_init_flags(&new, MT_FLAGS_ALLOC_RANGE);
+		}
+
+		for (j = 0; j < i; j++) {
+			mtree_store_range(mt, j * 10, j * 10 + 5,
+					  xa_mk_value(j), GFP_KERNEL);
+		}
+		/*
+		 * The rand() library function is not used, so we can generate
+		 * the same random numbers on any platform.
+		 */
+		rand_seed = rand_seed * 1103515245 + 12345;
+		rand = rand_seed / 65536 % 128;
+		mt_set_non_kernel(rand);
+
+		ret = mtree_dup(mt, &new, GFP_NOWAIT);
+		mt_set_non_kernel(0);
+		if (ret != 0) {
+			MT_BUG_ON(&new, ret != -ENOMEM);
+			count++;
+			mtree_destroy(mt);
+			continue;
+		}
+
+		mt_validate(&new);
+		if (compare_tree(mt, &new))
+			MT_BUG_ON(&new, 1);
+
+		mtree_destroy(mt);
+		mtree_destroy(&new);
+	}
+
+	/* pr_info("mtree_dup() fail %d times\n", count); */
+	BUG_ON(!count);
+}
+
 extern void test_kmem_cache_bulk(void);
 
 void farmer_tests(void)
@@ -35904,6 +36268,10 @@ void farmer_tests(void)
 	check_null_expand(&tree);
 	mtree_destroy(&tree);
 
+	mt_init_flags(&tree, 0);
+	check_mtree_dup(&tree);
+	mtree_destroy(&tree);
+
 	/* RCU testing */
 	mt_init_flags(&tree, 0);
 	check_erase_testset(&tree);
@@ -35938,7 +36306,9 @@ void farmer_tests(void)
 
 void maple_tree_tests(void)
 {
+#if !defined(BENCH)
 	farmer_tests();
+#endif
 	maple_tree_seed();
 	maple_tree_harvest();
 }
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 3b2061d1c1a5..15b6a111c3be 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -26,6 +26,8 @@ TARGETS += filesystems
 TARGETS += filesystems/binderfs
 TARGETS += filesystems/epoll
 TARGETS += filesystems/fat
+TARGETS += filesystems/overlayfs
+TARGETS += filesystems/statmount
 TARGETS += firmware
 TARGETS += fpu
 TARGETS += ftrace
@@ -43,6 +45,7 @@ TARGETS += landlock
 TARGETS += lib
 TARGETS += livepatch
 TARGETS += lkdtm
+TARGETS += lsm
 TARGETS += membarrier
 TARGETS += memfd
 TARGETS += memory-hotplug
@@ -58,6 +61,7 @@ TARGETS += net/forwarding
 TARGETS += net/hsr
 TARGETS += net/mptcp
 TARGETS += net/openvswitch
+TARGETS += net/tcp_ao
 TARGETS += netfilter
 TARGETS += nsfs
 TARGETS += perf_events
@@ -155,12 +159,10 @@ ifneq ($(KBUILD_OUTPUT),)
   abs_objtree := $(realpath $(abs_objtree))
   BUILD := $(abs_objtree)/kselftest
   KHDR_INCLUDES := -isystem ${abs_objtree}/usr/include
-  KHDR_DIR := ${abs_objtree}/usr/include
 else
   BUILD := $(CURDIR)
   abs_srctree := $(shell cd $(top_srcdir) && pwd)
   KHDR_INCLUDES := -isystem ${abs_srctree}/usr/include
-  KHDR_DIR := ${abs_srctree}/usr/include
   DEFAULT_INSTALL_HDR_PATH := 1
 endif
 
@@ -174,7 +176,7 @@ export KHDR_INCLUDES
 # all isn't the first target in the file.
 .DEFAULT_GOAL := all
 
-all: kernel_header_files
+all:
 	@ret=1;							\
 	for TARGET in $(TARGETS); do				\
 		BUILD_TARGET=$$BUILD/$$TARGET;			\
@@ -185,23 +187,6 @@ all: kernel_header_files
 		ret=$$((ret * $$?));				\
 	done; exit $$ret;
 
-kernel_header_files:
-	@ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null;                          \
-	if [ $$? -ne 0 ]; then                                                     \
-            RED='\033[1;31m';                                                  \
-            NOCOLOR='\033[0m';                                                 \
-            echo;                                                              \
-            echo -e "$${RED}error$${NOCOLOR}: missing kernel header files.";   \
-            echo "Please run this and try again:";                             \
-            echo;                                                              \
-            echo "    cd $(top_srcdir)";                                       \
-            echo "    make headers";                                           \
-            echo;                                                              \
-	    exit 1;                                                                \
-	fi
-
-.PHONY: kernel_header_files
-
 run_tests: all
 	@for TARGET in $(TARGETS); do \
 		BUILD_TARGET=$$BUILD/$$TARGET;	\
diff --git a/tools/testing/selftests/alsa/mixer-test.c b/tools/testing/selftests/alsa/mixer-test.c
index 21e482b23f50..23df154fcdd7 100644
--- a/tools/testing/selftests/alsa/mixer-test.c
+++ b/tools/testing/selftests/alsa/mixer-test.c
@@ -138,7 +138,7 @@ static void find_controls(void)
 			err = snd_ctl_elem_info(card_data->handle,
 						ctl_data->info);
 			if (err < 0) {
-				ksft_print_msg("%s getting info for %d\n",
+				ksft_print_msg("%s getting info for %s\n",
 					       snd_strerror(err),
 					       ctl_data->name);
 			}
diff --git a/tools/testing/selftests/arm64/abi/tpidr2.c b/tools/testing/selftests/arm64/abi/tpidr2.c
index 351a098b503a..02ee3a91b780 100644
--- a/tools/testing/selftests/arm64/abi/tpidr2.c
+++ b/tools/testing/selftests/arm64/abi/tpidr2.c
@@ -254,6 +254,12 @@ static int write_clone_read(void)
 	putnum(++tests_run);		     \
 	putstr(" " #name "\n");
 
+#define skip_test(name)			     \
+	tests_skipped++;		     \
+	putstr("ok ");			     \
+	putnum(++tests_run);		     \
+	putstr(" # SKIP " #name "\n");
+
 int main(int argc, char **argv)
 {
 	int ret, i;
@@ -283,13 +289,11 @@ int main(int argc, char **argv)
 	} else {
 		putstr("# SME support not present\n");
 
-		for (i = 0; i < EXPECTED_TESTS; i++) {
-			putstr("ok ");
-			putnum(i);
-			putstr(" skipped, TPIDR2 not supported\n");
-		}
-
-		tests_skipped += EXPECTED_TESTS;
+		skip_test(default_value);
+		skip_test(write_read);
+		skip_test(write_sleep_read);
+		skip_test(write_fork_read);
+		skip_test(write_clone_read);
 	}
 
 	print_summary();
diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S
index 547d077e3517..fff60e2a25ad 100644
--- a/tools/testing/selftests/arm64/fp/sve-test.S
+++ b/tools/testing/selftests/arm64/fp/sve-test.S
@@ -515,6 +515,10 @@ function barf
 	mov	x11, x1	// actual data
 	mov	x12, x2	// data size
 
+#ifdef SSVE
+	mrs	x13, S3_3_C4_C2_2
+#endif
+
 	puts	"Mismatch: PID="
 	mov	x0, x20
 	bl	putdec
@@ -534,6 +538,12 @@ function barf
 	bl	dumphex
 	puts	"]\n"
 
+#ifdef SSVE
+	puts	"\tSVCR: "
+	mov	x0, x13
+	bl	putdecn
+#endif
+
 	mov	x8, #__NR_getpid
 	svc	#0
 // fpsimd.c acitivty log dump hack
diff --git a/tools/testing/selftests/arm64/fp/vec-syscfg.c b/tools/testing/selftests/arm64/fp/vec-syscfg.c
index 5f648b97a06f..ea9c7d47790f 100644
--- a/tools/testing/selftests/arm64/fp/vec-syscfg.c
+++ b/tools/testing/selftests/arm64/fp/vec-syscfg.c
@@ -66,6 +66,11 @@ static struct vec_data vec_data[] = {
 	},
 };
 
+static bool vec_type_supported(struct vec_data *data)
+{
+	return getauxval(data->hwcap_type) & data->hwcap;
+}
+
 static int stdio_read_integer(FILE *f, const char *what, int *val)
 {
 	int n = 0;
@@ -564,8 +569,11 @@ static void prctl_set_all_vqs(struct vec_data *data)
 		return;
 	}
 
-	for (i = 0; i < ARRAY_SIZE(vec_data); i++)
+	for (i = 0; i < ARRAY_SIZE(vec_data); i++) {
+		if (!vec_type_supported(&vec_data[i]))
+			continue;
 		orig_vls[i] = vec_data[i].rdvl();
+	}
 
 	for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) {
 		vl = sve_vl_from_vq(vq);
@@ -594,7 +602,7 @@ static void prctl_set_all_vqs(struct vec_data *data)
 			if (&vec_data[i] == data)
 				continue;
 
-			if (!(getauxval(vec_data[i].hwcap_type) & vec_data[i].hwcap))
+			if (!vec_type_supported(&vec_data[i]))
 				continue;
 
 			if (vec_data[i].rdvl() != orig_vls[i]) {
@@ -765,7 +773,7 @@ int main(void)
 		struct vec_data *data = &vec_data[i];
 		unsigned long supported;
 
-		supported = getauxval(data->hwcap_type) & data->hwcap;
+		supported = vec_type_supported(data);
 		if (!supported)
 			all_supported = false;
 
diff --git a/tools/testing/selftests/arm64/fp/za-fork.c b/tools/testing/selftests/arm64/fp/za-fork.c
index b86cb1049497..587b94648222 100644
--- a/tools/testing/selftests/arm64/fp/za-fork.c
+++ b/tools/testing/selftests/arm64/fp/za-fork.c
@@ -85,7 +85,7 @@ int main(int argc, char **argv)
 	 */
 	ret = open("/proc/sys/abi/sme_default_vector_length", O_RDONLY, 0);
 	if (ret >= 0) {
-		ksft_test_result(fork_test(), "fork_test");
+		ksft_test_result(fork_test(), "fork_test\n");
 
 	} else {
 		ksft_print_msg("SME not supported\n");
diff --git a/tools/testing/selftests/arm64/fp/za-test.S b/tools/testing/selftests/arm64/fp/za-test.S
index 9dcd70911397..095b45531640 100644
--- a/tools/testing/selftests/arm64/fp/za-test.S
+++ b/tools/testing/selftests/arm64/fp/za-test.S
@@ -333,6 +333,9 @@ function barf
 //	mov	w8, #__NR_exit
 //	svc	#0
 // end hack
+
+	mrs	x13, S3_3_C4_C2_2
+
 	smstop
 	mov	x10, x0	// expected data
 	mov	x11, x1	// actual data
@@ -356,6 +359,9 @@ function barf
 	mov	x1, x12
 	bl	dumphex
 	puts	"]\n"
+	puts	"\tSVCR: "
+	mov	x0, x13
+	bl	putdecn
 
 	mov	x8, #__NR_getpid
 	svc	#0
diff --git a/tools/testing/selftests/arm64/fp/zt-test.S b/tools/testing/selftests/arm64/fp/zt-test.S
index d63286397638..b5c81e81a379 100644
--- a/tools/testing/selftests/arm64/fp/zt-test.S
+++ b/tools/testing/selftests/arm64/fp/zt-test.S
@@ -267,6 +267,8 @@ function barf
 //	mov	w8, #__NR_exit
 //	svc	#0
 // end hack
+
+	mrs	x13, S3_3_C4_C2_2
 	smstop
 	mov	x10, x0	// expected data
 	mov	x11, x1	// actual data
@@ -287,6 +289,9 @@ function barf
 	mov	x1, x12
 	bl	dumphex
 	puts	"]\n"
+	puts	"\tSVCR: "
+	mov	x0, x13
+	bl	putdecn
 
 	mov	x8, #__NR_getpid
 	svc	#0
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 9c27b67bc7b1..fd15017ed3b1 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -18,7 +18,7 @@ else
 GENDIR := $(abspath ../../../../include/generated)
 endif
 GENHDR := $(GENDIR)/autoconf.h
-HOSTPKG_CONFIG := pkg-config
+PKG_CONFIG ?= $(CROSS_COMPILE)pkg-config
 
 ifneq ($(wildcard $(GENHDR)),)
   GENFLAGS := -DHAVE_GENHDR
@@ -29,13 +29,17 @@ SAN_CFLAGS	?=
 SAN_LDFLAGS	?= $(SAN_CFLAGS)
 RELEASE		?=
 OPT_FLAGS	?= $(if $(RELEASE),-O2,-O0)
+
+LIBELF_CFLAGS	:= $(shell $(PKG_CONFIG) libelf --cflags 2>/dev/null)
+LIBELF_LIBS	:= $(shell $(PKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf)
+
 CFLAGS += -g $(OPT_FLAGS) -rdynamic					\
 	  -Wall -Werror 						\
-	  $(GENFLAGS) $(SAN_CFLAGS)					\
+	  $(GENFLAGS) $(SAN_CFLAGS) $(LIBELF_CFLAGS)			\
 	  -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR)		\
 	  -I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT)
 LDFLAGS += $(SAN_LDFLAGS)
-LDLIBS += -lelf -lz -lrt -lpthread
+LDLIBS += $(LIBELF_LIBS) -lz -lrt -lpthread
 
 ifneq ($(LLVM),)
 # Silence some warnings when compiled with clang
@@ -219,9 +223,9 @@ $(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_r
 
 $(OUTPUT)/sign-file: ../../../../scripts/sign-file.c
 	$(call msg,SIGN-FILE,,$@)
-	$(Q)$(CC) $(shell $(HOSTPKG_CONFIG) --cflags libcrypto 2> /dev/null) \
+	$(Q)$(CC) $(shell $(PKG_CONFIG) --cflags libcrypto 2> /dev/null) \
 		  $< -o $@ \
-		  $(shell $(HOSTPKG_CONFIG) --libs libcrypto 2> /dev/null || echo -lcrypto)
+		  $(shell $(PKG_CONFIG) --libs libcrypto 2> /dev/null || echo -lcrypto)
 
 $(OUTPUT)/bpf_testmod.ko: $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard bpf_testmod/Makefile bpf_testmod/*.[ch])
 	$(call msg,MOD,,$@)
@@ -379,6 +383,7 @@ CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH))
 BPF_CFLAGS = -g -Wall -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN)	\
 	     -I$(INCLUDE_DIR) -I$(CURDIR) -I$(APIDIR)			\
 	     -I$(abspath $(OUTPUT)/../usr/include)
+# TODO: enable me -Wsign-compare
 
 CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \
 	       -Wno-compare-distinct-pointer-types
diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst
index cb9b95702ac6..9af79c7a9b58 100644
--- a/tools/testing/selftests/bpf/README.rst
+++ b/tools/testing/selftests/bpf/README.rst
@@ -77,7 +77,7 @@ In case of linker errors when running selftests, try using static linking:
 
 .. code-block:: console
 
-  $ LDLIBS=-static vmtest.sh
+  $ LDLIBS=-static PKG_CONFIG='pkg-config --static' vmtest.sh
 
 .. note:: Some distros may not support static linking.
 
diff --git a/tools/testing/selftests/bpf/benchs/bench_htab_mem.c b/tools/testing/selftests/bpf/benchs/bench_htab_mem.c
index 9146d3f414d2..926ee822143e 100644
--- a/tools/testing/selftests/bpf/benchs/bench_htab_mem.c
+++ b/tools/testing/selftests/bpf/benchs/bench_htab_mem.c
@@ -335,6 +335,7 @@ static void htab_mem_report_final(struct bench_res res[], int res_cnt)
 	       " peak memory usage %7.2lfMiB\n",
 	       loop_mean, loop_stddev, mem_mean, mem_stddev, peak_mem / 1048576.0);
 
+	close(ctx.fd);
 	cleanup_cgroup_environment();
 }
 
diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index 1386baf9ae4a..f44875f8b367 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -254,173 +254,97 @@ extern void bpf_throw(u64 cookie) __ksym;
 		}									\
 	 })
 
-/* Description
- *	Assert that a conditional expression is true.
- * Returns
- *	Void.
- * Throws
- *	An exception with the value zero when the assertion fails.
- */
-#define bpf_assert(cond) if (!(cond)) bpf_throw(0);
-
-/* Description
- *	Assert that a conditional expression is true.
- * Returns
- *	Void.
- * Throws
- *	An exception with the specified value when the assertion fails.
- */
-#define bpf_assert_with(cond, value) if (!(cond)) bpf_throw(value);
-
-/* Description
- *	Assert that LHS is equal to RHS. This statement updates the known value
- *	of LHS during verification. Note that RHS must be a constant value, and
- *	must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the value zero when the assertion fails.
- */
-#define bpf_assert_eq(LHS, RHS)						\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, ==, RHS, 0, true);			\
-	})
-
-/* Description
- *	Assert that LHS is equal to RHS. This statement updates the known value
- *	of LHS during verification. Note that RHS must be a constant value, and
- *	must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the specified value when the assertion fails.
- */
-#define bpf_assert_eq_with(LHS, RHS, value)				\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, ==, RHS, value, true);		\
-	})
-
-/* Description
- *	Assert that LHS is less than RHS. This statement updates the known
- *	bounds of LHS during verification. Note that RHS must be a constant
- *	value, and must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the value zero when the assertion fails.
- */
-#define bpf_assert_lt(LHS, RHS)						\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, <, RHS, 0, false);			\
-	})
-
-/* Description
- *	Assert that LHS is less than RHS. This statement updates the known
- *	bounds of LHS during verification. Note that RHS must be a constant
- *	value, and must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the specified value when the assertion fails.
- */
-#define bpf_assert_lt_with(LHS, RHS, value)				\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, <, RHS, value, false);		\
-	})
+#define __cmp_cannot_be_signed(x) \
+	__builtin_strcmp(#x, "==") == 0 || __builtin_strcmp(#x, "!=") == 0 || \
+	__builtin_strcmp(#x, "&") == 0
 
-/* Description
- *	Assert that LHS is greater than RHS. This statement updates the known
- *	bounds of LHS during verification. Note that RHS must be a constant
- *	value, and must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the value zero when the assertion fails.
- */
-#define bpf_assert_gt(LHS, RHS)						\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, >, RHS, 0, false);			\
-	})
+#define __is_signed_type(type) (((type)(-1)) < (type)1)
 
-/* Description
- *	Assert that LHS is greater than RHS. This statement updates the known
- *	bounds of LHS during verification. Note that RHS must be a constant
- *	value, and must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the specified value when the assertion fails.
+#define __bpf_cmp(LHS, OP, SIGN, PRED, RHS, DEFAULT)						\
+	({											\
+		__label__ l_true;								\
+		bool ret = DEFAULT;								\
+		asm volatile goto("if %[lhs] " SIGN #OP " %[rhs] goto %l[l_true]"		\
+				  :: [lhs] "r"((short)LHS), [rhs] PRED (RHS) :: l_true);	\
+		ret = !DEFAULT;									\
+l_true:												\
+		ret;										\
+       })
+
+/* C type conversions coupled with comparison operator are tricky.
+ * Make sure BPF program is compiled with -Wsign-compare then
+ * __lhs OP __rhs below will catch the mistake.
+ * Be aware that we check only __lhs to figure out the sign of compare.
  */
-#define bpf_assert_gt_with(LHS, RHS, value)				\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, >, RHS, value, false);		\
-	})
+#define _bpf_cmp(LHS, OP, RHS, NOFLIP)								\
+	({											\
+		typeof(LHS) __lhs = (LHS);							\
+		typeof(RHS) __rhs = (RHS);							\
+		bool ret;									\
+		_Static_assert(sizeof(&(LHS)), "1st argument must be an lvalue expression");	\
+		(void)(__lhs OP __rhs);								\
+		if (__cmp_cannot_be_signed(OP) || !__is_signed_type(typeof(__lhs))) {		\
+			if (sizeof(__rhs) == 8)							\
+				ret = __bpf_cmp(__lhs, OP, "", "r", __rhs, NOFLIP);		\
+			else									\
+				ret = __bpf_cmp(__lhs, OP, "", "i", __rhs, NOFLIP);		\
+		} else {									\
+			if (sizeof(__rhs) == 8)							\
+				ret = __bpf_cmp(__lhs, OP, "s", "r", __rhs, NOFLIP);		\
+			else									\
+				ret = __bpf_cmp(__lhs, OP, "s", "i", __rhs, NOFLIP);		\
+		}										\
+		ret;										\
+       })
+
+#ifndef bpf_cmp_unlikely
+#define bpf_cmp_unlikely(LHS, OP, RHS) _bpf_cmp(LHS, OP, RHS, true)
+#endif
 
-/* Description
- *	Assert that LHS is less than or equal to RHS. This statement updates the
- *	known bounds of LHS during verification. Note that RHS must be a
- *	constant value, and must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the value zero when the assertion fails.
- */
-#define bpf_assert_le(LHS, RHS)						\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, <=, RHS, 0, false);		\
-	})
+#ifndef bpf_cmp_likely
+#define bpf_cmp_likely(LHS, OP, RHS)								\
+	({											\
+		bool ret;									\
+		if (__builtin_strcmp(#OP, "==") == 0)						\
+			ret = _bpf_cmp(LHS, !=, RHS, false);					\
+		else if (__builtin_strcmp(#OP, "!=") == 0)					\
+			ret = _bpf_cmp(LHS, ==, RHS, false);					\
+		else if (__builtin_strcmp(#OP, "<=") == 0)					\
+			ret = _bpf_cmp(LHS, >, RHS, false);					\
+		else if (__builtin_strcmp(#OP, "<") == 0)					\
+			ret = _bpf_cmp(LHS, >=, RHS, false);					\
+		else if (__builtin_strcmp(#OP, ">") == 0)					\
+			ret = _bpf_cmp(LHS, <=, RHS, false);					\
+		else if (__builtin_strcmp(#OP, ">=") == 0)					\
+			ret = _bpf_cmp(LHS, <, RHS, false);					\
+		else										\
+			(void) "bug";								\
+		ret;										\
+       })
+#endif
 
-/* Description
- *	Assert that LHS is less than or equal to RHS. This statement updates the
- *	known bounds of LHS during verification. Note that RHS must be a
- *	constant value, and must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the specified value when the assertion fails.
- */
-#define bpf_assert_le_with(LHS, RHS, value)				\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, <=, RHS, value, false);		\
-	})
+#ifndef bpf_nop_mov
+#define bpf_nop_mov(var) \
+	asm volatile("%[reg]=%[reg]"::[reg]"r"((short)var))
+#endif
 
 /* Description
- *	Assert that LHS is greater than or equal to RHS. This statement updates
- *	the known bounds of LHS during verification. Note that RHS must be a
- *	constant value, and must fit within the data type of LHS.
+ *	Assert that a conditional expression is true.
  * Returns
  *	Void.
  * Throws
  *	An exception with the value zero when the assertion fails.
  */
-#define bpf_assert_ge(LHS, RHS)						\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, >=, RHS, 0, false);		\
-	})
+#define bpf_assert(cond) if (!(cond)) bpf_throw(0);
 
 /* Description
- *	Assert that LHS is greater than or equal to RHS. This statement updates
- *	the known bounds of LHS during verification. Note that RHS must be a
- *	constant value, and must fit within the data type of LHS.
+ *	Assert that a conditional expression is true.
  * Returns
  *	Void.
  * Throws
  *	An exception with the specified value when the assertion fails.
  */
-#define bpf_assert_ge_with(LHS, RHS, value)				\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, >=, RHS, value, false);		\
-	})
+#define bpf_assert_with(cond, value) if (!(cond)) bpf_throw(value);
 
 /* Description
  *	Assert that LHS is in the range [BEG, END] (inclusive of both). This
diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h
index 5ca68ff0b59f..b4e78c1eb37b 100644
--- a/tools/testing/selftests/bpf/bpf_kfuncs.h
+++ b/tools/testing/selftests/bpf/bpf_kfuncs.h
@@ -55,4 +55,14 @@ void *bpf_cast_to_kern_ctx(void *) __ksym;
 
 void *bpf_rdonly_cast(void *obj, __u32 btf_id) __ksym;
 
+extern int bpf_get_file_xattr(struct file *file, const char *name,
+			      struct bpf_dynptr *value_ptr) __ksym;
+extern int bpf_get_fsverity_digest(struct file *file, struct bpf_dynptr *digest_ptr) __ksym;
+
+extern struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym;
+extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym;
+extern void bpf_key_put(struct bpf_key *key) __ksym;
+extern int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_ptr,
+				      struct bpf_dynptr *sig_ptr,
+				      struct bpf_key *trusted_keyring) __ksym;
 #endif
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index 5b1da2a32ea7..19be9c63d5e8 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -45,9 +45,12 @@
 #define format_parent_cgroup_path(buf, path) \
 	format_cgroup_path_pid(buf, path, getppid())
 
-#define format_classid_path(buf)				\
-	snprintf(buf, sizeof(buf), "%s%s", NETCLS_MOUNT_PATH,	\
-		 CGROUP_WORK_DIR)
+#define format_classid_path_pid(buf, pid)				\
+	snprintf(buf, sizeof(buf), "%s%s%d", NETCLS_MOUNT_PATH,	\
+		 CGROUP_WORK_DIR, pid)
+
+#define format_classid_path(buf)	\
+	format_classid_path_pid(buf, getpid())
 
 static __thread bool cgroup_workdir_mounted;
 
@@ -419,26 +422,23 @@ int create_and_get_cgroup(const char *relative_path)
 }
 
 /**
- * get_cgroup_id() - Get cgroup id for a particular cgroup path
- * @relative_path: The cgroup path, relative to the workdir, to join
+ * get_cgroup_id_from_path - Get cgroup id for a particular cgroup path
+ * @cgroup_workdir: The absolute cgroup path
  *
  * On success, it returns the cgroup id. On failure it returns 0,
  * which is an invalid cgroup id.
  * If there is a failure, it prints the error to stderr.
  */
-unsigned long long get_cgroup_id(const char *relative_path)
+unsigned long long get_cgroup_id_from_path(const char *cgroup_workdir)
 {
 	int dirfd, err, flags, mount_id, fhsize;
 	union {
 		unsigned long long cgid;
 		unsigned char raw_bytes[8];
 	} id;
-	char cgroup_workdir[PATH_MAX + 1];
 	struct file_handle *fhp, *fhp2;
 	unsigned long long ret = 0;
 
-	format_cgroup_path(cgroup_workdir, relative_path);
-
 	dirfd = AT_FDCWD;
 	flags = 0;
 	fhsize = sizeof(*fhp);
@@ -474,6 +474,14 @@ free_mem:
 	return ret;
 }
 
+unsigned long long get_cgroup_id(const char *relative_path)
+{
+	char cgroup_workdir[PATH_MAX + 1];
+
+	format_cgroup_path(cgroup_workdir, relative_path);
+	return get_cgroup_id_from_path(cgroup_workdir);
+}
+
 int cgroup_setup_and_join(const char *path) {
 	int cg_fd;
 
@@ -523,10 +531,20 @@ int setup_classid_environment(void)
 		return 1;
 	}
 
-	if (mount("net_cls", NETCLS_MOUNT_PATH, "cgroup", 0, "net_cls") &&
-	    errno != EBUSY) {
-		log_err("mount cgroup net_cls");
-		return 1;
+	if (mount("net_cls", NETCLS_MOUNT_PATH, "cgroup", 0, "net_cls")) {
+		if (errno != EBUSY) {
+			log_err("mount cgroup net_cls");
+			return 1;
+		}
+
+		if (rmdir(NETCLS_MOUNT_PATH)) {
+			log_err("rmdir cgroup net_cls");
+			return 1;
+		}
+		if (umount(CGROUP_MOUNT_DFLT)) {
+			log_err("umount cgroup base");
+			return 1;
+		}
 	}
 
 	cleanup_classid_environment();
@@ -541,15 +559,16 @@ int setup_classid_environment(void)
 
 /**
  * set_classid() - Set a cgroupv1 net_cls classid
- * @id: the numeric classid
  *
- * Writes the passed classid into the cgroup work dir's net_cls.classid
+ * Writes the classid into the cgroup work dir's net_cls.classid
  * file in order to later on trigger socket tagging.
  *
+ * We leverage the current pid as the classid, ensuring unique identification.
+ *
  * On success, it returns 0, otherwise on failure it returns 1. If there
  * is a failure, it prints the error to stderr.
  */
-int set_classid(unsigned int id)
+int set_classid(void)
 {
 	char cgroup_workdir[PATH_MAX - 42];
 	char cgroup_classid_path[PATH_MAX + 1];
@@ -565,7 +584,7 @@ int set_classid(unsigned int id)
 		return 1;
 	}
 
-	if (dprintf(fd, "%u\n", id) < 0) {
+	if (dprintf(fd, "%u\n", getpid()) < 0) {
 		log_err("Setting cgroup classid");
 		rc = 1;
 	}
@@ -607,3 +626,82 @@ void cleanup_classid_environment(void)
 	join_cgroup_from_top(NETCLS_MOUNT_PATH);
 	nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT);
 }
+
+/**
+ * get_classid_cgroup_id - Get the cgroup id of a net_cls cgroup
+ */
+unsigned long long get_classid_cgroup_id(void)
+{
+	char cgroup_workdir[PATH_MAX + 1];
+
+	format_classid_path(cgroup_workdir);
+	return get_cgroup_id_from_path(cgroup_workdir);
+}
+
+/**
+ * get_cgroup1_hierarchy_id - Retrieves the ID of a cgroup1 hierarchy from the cgroup1 subsys name.
+ * @subsys_name: The cgroup1 subsys name, which can be retrieved from /proc/self/cgroup. It can be
+ * a named cgroup like "name=systemd", a controller name like "net_cls", or multi-contollers like
+ * "net_cls,net_prio".
+ */
+int get_cgroup1_hierarchy_id(const char *subsys_name)
+{
+	char *c, *c2, *c3, *c4;
+	bool found = false;
+	char line[1024];
+	FILE *file;
+	int i, id;
+
+	if (!subsys_name)
+		return -1;
+
+	file = fopen("/proc/self/cgroup", "r");
+	if (!file) {
+		log_err("fopen /proc/self/cgroup");
+		return -1;
+	}
+
+	while (fgets(line, 1024, file)) {
+		i = 0;
+		for (c = strtok_r(line, ":", &c2); c && i < 2; c = strtok_r(NULL, ":", &c2)) {
+			if (i == 0) {
+				id = strtol(c, NULL, 10);
+			} else if (i == 1) {
+				if (!strcmp(c, subsys_name)) {
+					found = true;
+					break;
+				}
+
+				/* Multiple subsystems may share one single mount point */
+				for (c3 = strtok_r(c, ",", &c4); c3;
+				     c3 = strtok_r(NULL, ",", &c4)) {
+					if (!strcmp(c, subsys_name)) {
+						found = true;
+						break;
+					}
+				}
+			}
+			i++;
+		}
+		if (found)
+			break;
+	}
+	fclose(file);
+	return found ? id : -1;
+}
+
+/**
+ * open_classid() - Open a cgroupv1 net_cls classid
+ *
+ * This function expects the cgroup work dir to be already created, as we
+ * open it here.
+ *
+ * On success, it returns the file descriptor. On failure it returns -1.
+ */
+int open_classid(void)
+{
+	char cgroup_workdir[PATH_MAX + 1];
+
+	format_classid_path(cgroup_workdir);
+	return open(cgroup_workdir, O_RDONLY);
+}
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h
index 5c2cb9c8b546..502845160d88 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.h
+++ b/tools/testing/selftests/bpf/cgroup_helpers.h
@@ -20,6 +20,7 @@ int get_root_cgroup(void);
 int create_and_get_cgroup(const char *relative_path);
 void remove_cgroup(const char *relative_path);
 unsigned long long get_cgroup_id(const char *relative_path);
+int get_cgroup1_hierarchy_id(const char *subsys_name);
 
 int join_cgroup(const char *relative_path);
 int join_root_cgroup(void);
@@ -29,8 +30,10 @@ int setup_cgroup_environment(void);
 void cleanup_cgroup_environment(void);
 
 /* cgroupv1 related */
-int set_classid(unsigned int id);
+int set_classid(void);
 int join_classid(void);
+unsigned long long get_classid_cgroup_id(void);
+int open_classid(void);
 
 int setup_classid_environment(void);
 void cleanup_classid_environment(void);
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 3ec5927ec3e5..c125c441abc7 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -23,6 +23,7 @@ CONFIG_FPROBE=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_FUNCTION_ERROR_INJECTION=y
 CONFIG_FUNCTION_TRACER=y
+CONFIG_FS_VERITY=y
 CONFIG_GENEVE=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
@@ -82,7 +83,7 @@ CONFIG_SECURITY=y
 CONFIG_SECURITYFS=y
 CONFIG_TEST_BPF=m
 CONFIG_USERFAULTFD=y
+CONFIG_VSOCKETS=y
 CONFIG_VXLAN=y
 CONFIG_XDP_SOCKETS=y
 CONFIG_XFRM_INTERFACE=y
-CONFIG_VSOCKETS=y
diff --git a/tools/testing/selftests/bpf/config.aarch64 b/tools/testing/selftests/bpf/config.aarch64
index 253821494884..3720b7611523 100644
--- a/tools/testing/selftests/bpf/config.aarch64
+++ b/tools/testing/selftests/bpf/config.aarch64
@@ -1,4 +1,3 @@
-CONFIG_9P_FS=y
 CONFIG_ARCH_VEXPRESS=y
 CONFIG_ARCH_WANT_DEFAULT_BPF_JIT=y
 CONFIG_ARM_SMMU_V3=y
@@ -12,7 +11,6 @@ CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_BONDING=y
-CONFIG_BPFILTER=y
 CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_JIT_DEFAULT_ON=y
 CONFIG_BPF_PRELOAD_UMD=y
@@ -37,6 +35,7 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=y
 CONFIG_DEBUG_ATOMIC_SLEEP=y
 CONFIG_DEBUG_INFO_BTF=y
 CONFIG_DEBUG_INFO_DWARF4=y
+CONFIG_DEBUG_INFO_REDUCED=n
 CONFIG_DEBUG_LIST=y
 CONFIG_DEBUG_LOCKDEP=y
 CONFIG_DEBUG_NOTIFIERS=y
@@ -46,7 +45,6 @@ CONFIG_DEBUG_SG=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_DEVTMPFS=y
-CONFIG_DRM_VIRTIO_GPU=y
 CONFIG_DRM=y
 CONFIG_DUMMY=y
 CONFIG_EXPERT=y
@@ -67,7 +65,6 @@ CONFIG_HAVE_KRETPROBES=y
 CONFIG_HEADERS_INSTALL=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_HUGETLBFS=y
-CONFIG_HW_RANDOM_VIRTIO=y
 CONFIG_HW_RANDOM=y
 CONFIG_HZ_100=y
 CONFIG_IDLE_PAGE_TRACKING=y
@@ -99,8 +96,6 @@ CONFIG_MEMCG=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_NAMESPACES=y
-CONFIG_NET_9P_VIRTIO=y
-CONFIG_NET_9P=y
 CONFIG_NET_ACT_BPF=y
 CONFIG_NET_ACT_GACT=y
 CONFIG_NETDEVICES=y
@@ -140,7 +135,6 @@ CONFIG_SCHED_TRACER=y
 CONFIG_SCSI_CONSTANTS=y
 CONFIG_SCSI_LOGGING=y
 CONFIG_SCSI_SCAN_ASYNC=y
-CONFIG_SCSI_VIRTIO=y
 CONFIG_SCSI=y
 CONFIG_SECURITY_NETWORK=y
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
@@ -167,16 +161,6 @@ CONFIG_UPROBES=y
 CONFIG_USELIB=y
 CONFIG_USER_NS=y
 CONFIG_VETH=y
-CONFIG_VIRTIO_BALLOON=y
-CONFIG_VIRTIO_BLK=y
-CONFIG_VIRTIO_CONSOLE=y
-CONFIG_VIRTIO_FS=y
-CONFIG_VIRTIO_INPUT=y
-CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
-CONFIG_VIRTIO_MMIO=y
-CONFIG_VIRTIO_NET=y
-CONFIG_VIRTIO_PCI=y
-CONFIG_VIRTIO_VSOCKETS_COMMON=y
 CONFIG_VLAN_8021Q=y
 CONFIG_VSOCKETS=y
 CONFIG_VSOCKETS_LOOPBACK=y
diff --git a/tools/testing/selftests/bpf/config.s390x b/tools/testing/selftests/bpf/config.s390x
index 2ba92167be35..706931a8c2c6 100644
--- a/tools/testing/selftests/bpf/config.s390x
+++ b/tools/testing/selftests/bpf/config.s390x
@@ -1,4 +1,3 @@
-CONFIG_9P_FS=y
 CONFIG_ARCH_WANT_DEFAULT_BPF_JIT=y
 CONFIG_AUDIT=y
 CONFIG_BLK_CGROUP=y
@@ -10,7 +9,6 @@ CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_JIT_DEFAULT_ON=y
 CONFIG_BPF_PRELOAD=y
 CONFIG_BPF_PRELOAD_UMD=y
-CONFIG_BPFILTER=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_FREEZER=y
@@ -84,8 +82,6 @@ CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_NAMESPACES=y
 CONFIG_NET=y
-CONFIG_NET_9P=y
-CONFIG_NET_9P_VIRTIO=y
 CONFIG_NET_ACT_BPF=y
 CONFIG_NET_ACT_GACT=y
 CONFIG_NET_KEY=y
@@ -114,7 +110,6 @@ CONFIG_SAMPLE_SECCOMP=y
 CONFIG_SAMPLES=y
 CONFIG_SCHED_TRACER=y
 CONFIG_SCSI=y
-CONFIG_SCSI_VIRTIO=y
 CONFIG_SECURITY_NETWORK=y
 CONFIG_STACK_TRACER=y
 CONFIG_STATIC_KEYS_SELFTEST=y
@@ -136,11 +131,6 @@ CONFIG_UPROBES=y
 CONFIG_USELIB=y
 CONFIG_USER_NS=y
 CONFIG_VETH=y
-CONFIG_VIRTIO_BALLOON=y
-CONFIG_VIRTIO_BLK=y
-CONFIG_VIRTIO_NET=y
-CONFIG_VIRTIO_PCI=y
-CONFIG_VIRTIO_VSOCKETS_COMMON=y
 CONFIG_VLAN_8021Q=y
 CONFIG_VSOCKETS=y
 CONFIG_VSOCKETS_LOOPBACK=y
diff --git a/tools/testing/selftests/bpf/config.vm b/tools/testing/selftests/bpf/config.vm
new file mode 100644
index 000000000000..a9746ca78777
--- /dev/null
+++ b/tools/testing/selftests/bpf/config.vm
@@ -0,0 +1,12 @@
+CONFIG_9P_FS=y
+CONFIG_9P_FS_POSIX_ACL=y
+CONFIG_9P_FS_SECURITY=y
+CONFIG_CRYPTO_DEV_VIRTIO=y
+CONFIG_NET_9P=y
+CONFIG_NET_9P_VIRTIO=y
+CONFIG_VIRTIO_BALLOON=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_VIRTIO_CONSOLE=y
+CONFIG_VIRTIO_NET=y
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_VSOCKETS_COMMON=y
diff --git a/tools/testing/selftests/bpf/config.x86_64 b/tools/testing/selftests/bpf/config.x86_64
index 2e70a6048278..5680befae8c6 100644
--- a/tools/testing/selftests/bpf/config.x86_64
+++ b/tools/testing/selftests/bpf/config.x86_64
@@ -1,6 +1,3 @@
-CONFIG_9P_FS=y
-CONFIG_9P_FS_POSIX_ACL=y
-CONFIG_9P_FS_SECURITY=y
 CONFIG_AGP=y
 CONFIG_AGP_AMD64=y
 CONFIG_AGP_INTEL=y
@@ -22,7 +19,6 @@ CONFIG_BOOTTIME_TRACING=y
 CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_PRELOAD=y
 CONFIG_BPF_PRELOAD_UMD=y
-CONFIG_BPFILTER=y
 CONFIG_BSD_DISKLABEL=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_CFS_BANDWIDTH=y
@@ -45,12 +41,10 @@ CONFIG_CPU_IDLE_GOV_LADDER=y
 CONFIG_CPUSETS=y
 CONFIG_CRC_T10DIF=y
 CONFIG_CRYPTO_BLAKE2B=y
-CONFIG_CRYPTO_DEV_VIRTIO=y
 CONFIG_CRYPTO_SEQIV=y
 CONFIG_CRYPTO_XXHASH=y
 CONFIG_DCB=y
 CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_DEBUG_CREDENTIALS=y
 CONFIG_DEBUG_INFO_BTF=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_DEBUG_MEMORY_INIT=y
@@ -145,8 +139,6 @@ CONFIG_MEMORY_FAILURE=y
 CONFIG_MINIX_SUBPARTITION=y
 CONFIG_NAMESPACES=y
 CONFIG_NET=y
-CONFIG_NET_9P=y
-CONFIG_NET_9P_VIRTIO=y
 CONFIG_NET_ACT_BPF=y
 CONFIG_NET_CLS_CGROUP=y
 CONFIG_NET_EMATCH=y
@@ -228,12 +220,6 @@ CONFIG_USER_NS=y
 CONFIG_VALIDATE_FS_PARSER=y
 CONFIG_VETH=y
 CONFIG_VIRT_DRIVERS=y
-CONFIG_VIRTIO_BALLOON=y
-CONFIG_VIRTIO_BLK=y
-CONFIG_VIRTIO_CONSOLE=y
-CONFIG_VIRTIO_NET=y
-CONFIG_VIRTIO_PCI=y
-CONFIG_VIRTIO_VSOCKETS_COMMON=y
 CONFIG_VLAN_8021Q=y
 CONFIG_VSOCKETS=y
 CONFIG_VSOCKETS_LOOPBACK=y
diff --git a/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c b/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
index 8bf497a9843e..2ea36408816b 100644
--- a/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
+++ b/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
@@ -131,10 +131,17 @@ static bool is_lru(__u32 map_type)
 	       map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
 }
 
+static bool is_percpu(__u32 map_type)
+{
+	return map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+	       map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
+}
+
 struct upsert_opts {
 	__u32 map_type;
 	int map_fd;
 	__u32 n;
+	bool retry_for_nomem;
 };
 
 static int create_small_hash(void)
@@ -148,19 +155,38 @@ static int create_small_hash(void)
 	return map_fd;
 }
 
+static bool retry_for_nomem_fn(int err)
+{
+	return err == ENOMEM;
+}
+
 static void *patch_map_thread(void *arg)
 {
+	/* 8KB is enough for 1024 CPUs. And it is shared between N_THREADS. */
+	static __u8 blob[8 << 10];
 	struct upsert_opts *opts = arg;
+	void *val_ptr;
 	int val;
 	int ret;
 	int i;
 
 	for (i = 0; i < opts->n; i++) {
-		if (opts->map_type == BPF_MAP_TYPE_HASH_OF_MAPS)
+		if (opts->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
 			val = create_small_hash();
-		else
+			val_ptr = &val;
+		} else if (is_percpu(opts->map_type)) {
+			val_ptr = blob;
+		} else {
 			val = rand();
-		ret = bpf_map_update_elem(opts->map_fd, &i, &val, 0);
+			val_ptr = &val;
+		}
+
+		/* 2 seconds may be enough ? */
+		if (opts->retry_for_nomem)
+			ret = map_update_retriable(opts->map_fd, &i, val_ptr, 0,
+						   40, retry_for_nomem_fn);
+		else
+			ret = bpf_map_update_elem(opts->map_fd, &i, val_ptr, 0);
 		CHECK(ret < 0, "bpf_map_update_elem", "key=%d error: %s\n", i, strerror(errno));
 
 		if (opts->map_type == BPF_MAP_TYPE_HASH_OF_MAPS)
@@ -281,6 +307,13 @@ static void __test(int map_fd)
 	else
 		opts.n /= 2;
 
+	/* per-cpu bpf memory allocator may not be able to allocate per-cpu
+	 * pointer successfully and it can not refill free llist timely, and
+	 * bpf_map_update_elem() will return -ENOMEM. so just retry to mitigate
+	 * the problem temporarily.
+	 */
+	opts.retry_for_nomem = is_percpu(opts.map_type) && (info.map_flags & BPF_F_NO_PREALLOC);
+
 	/*
 	 * Upsert keys [0, n) under some competition: with random values from
 	 * N_THREADS threads. Check values, then delete all elements and check
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index 34f1200a781b..94b9be24e39b 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -71,4 +71,47 @@ struct nstoken;
  */
 struct nstoken *open_netns(const char *name);
 void close_netns(struct nstoken *token);
+
+static __u16 csum_fold(__u32 csum)
+{
+	csum = (csum & 0xffff) + (csum >> 16);
+	csum = (csum & 0xffff) + (csum >> 16);
+
+	return (__u16)~csum;
+}
+
+static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
+					__u32 len, __u8 proto,
+					__wsum csum)
+{
+	__u64 s = csum;
+
+	s += (__u32)saddr;
+	s += (__u32)daddr;
+	s += htons(proto + len);
+	s = (s & 0xffffffff) + (s >> 32);
+	s = (s & 0xffffffff) + (s >> 32);
+
+	return csum_fold((__u32)s);
+}
+
+static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+				      const struct in6_addr *daddr,
+					__u32 len, __u8 proto,
+					__wsum csum)
+{
+	__u64 s = csum;
+	int i;
+
+	for (i = 0; i < 4; i++)
+		s += (__u32)saddr->s6_addr32[i];
+	for (i = 0; i < 4; i++)
+		s += (__u32)daddr->s6_addr32[i];
+	s += htons(proto + len);
+	s = (s & 0xffffffff) + (s >> 32);
+	s = (s & 0xffffffff) + (s >> 32);
+
+	return csum_fold((__u32)s);
+}
+
 #endif
diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c
index 465c1c3a3d3c..4ebd0da898f5 100644
--- a/tools/testing/selftests/bpf/prog_tests/align.c
+++ b/tools/testing/selftests/bpf/prog_tests/align.c
@@ -40,7 +40,7 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{0, "R1", "ctx(off=0,imm=0)"},
+			{0, "R1", "ctx()"},
 			{0, "R10", "fp0"},
 			{0, "R3_w", "2"},
 			{1, "R3_w", "4"},
@@ -68,7 +68,7 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{0, "R1", "ctx(off=0,imm=0)"},
+			{0, "R1", "ctx()"},
 			{0, "R10", "fp0"},
 			{0, "R3_w", "1"},
 			{1, "R3_w", "2"},
@@ -97,7 +97,7 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{0, "R1", "ctx(off=0,imm=0)"},
+			{0, "R1", "ctx()"},
 			{0, "R10", "fp0"},
 			{0, "R3_w", "4"},
 			{1, "R3_w", "8"},
@@ -119,7 +119,7 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{0, "R1", "ctx(off=0,imm=0)"},
+			{0, "R1", "ctx()"},
 			{0, "R10", "fp0"},
 			{0, "R3_w", "7"},
 			{1, "R3_w", "7"},
@@ -162,13 +162,13 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{6, "R0_w", "pkt(off=8,r=8,imm=0)"},
+			{6, "R0_w", "pkt(off=8,r=8)"},
 			{6, "R3_w", "var_off=(0x0; 0xff)"},
 			{7, "R3_w", "var_off=(0x0; 0x1fe)"},
 			{8, "R3_w", "var_off=(0x0; 0x3fc)"},
 			{9, "R3_w", "var_off=(0x0; 0x7f8)"},
 			{10, "R3_w", "var_off=(0x0; 0xff0)"},
-			{12, "R3_w", "pkt_end(off=0,imm=0)"},
+			{12, "R3_w", "pkt_end()"},
 			{17, "R4_w", "var_off=(0x0; 0xff)"},
 			{18, "R4_w", "var_off=(0x0; 0x1fe0)"},
 			{19, "R4_w", "var_off=(0x0; 0xff0)"},
@@ -235,11 +235,11 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{2, "R5_w", "pkt(off=0,r=0,imm=0)"},
-			{4, "R5_w", "pkt(off=14,r=0,imm=0)"},
-			{5, "R4_w", "pkt(off=14,r=0,imm=0)"},
-			{9, "R2", "pkt(off=0,r=18,imm=0)"},
-			{10, "R5", "pkt(off=14,r=18,imm=0)"},
+			{2, "R5_w", "pkt(r=0)"},
+			{4, "R5_w", "pkt(off=14,r=0)"},
+			{5, "R4_w", "pkt(off=14,r=0)"},
+			{9, "R2", "pkt(r=18)"},
+			{10, "R5", "pkt(off=14,r=18)"},
 			{10, "R4_w", "var_off=(0x0; 0xff)"},
 			{13, "R4_w", "var_off=(0x0; 0xffff)"},
 			{14, "R4_w", "var_off=(0x0; 0xffff)"},
@@ -299,7 +299,7 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{6, "R2_w", "pkt(off=0,r=8,imm=0)"},
+			{6, "R2_w", "pkt(r=8)"},
 			{7, "R6_w", "var_off=(0x0; 0x3fc)"},
 			/* Offset is added to packet pointer R5, resulting in
 			 * known fixed offset, and variable offset from R6.
@@ -337,7 +337,7 @@ static struct bpf_align_test tests[] = {
 			/* Constant offset is added to R5 packet pointer,
 			 * resulting in reg->off value of 14.
 			 */
-			{26, "R5_w", "pkt(off=14,r=8,"},
+			{26, "R5_w", "pkt(off=14,r=8)"},
 			/* Variable offset is added to R5, resulting in a
 			 * variable offset of (4n). See comment for insn #18
 			 * for R4 = R5 trick.
@@ -397,7 +397,7 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{6, "R2_w", "pkt(off=0,r=8,imm=0)"},
+			{6, "R2_w", "pkt(r=8)"},
 			{7, "R6_w", "var_off=(0x0; 0x3fc)"},
 			/* Adding 14 makes R6 be (4n+2) */
 			{8, "R6_w", "var_off=(0x2; 0x7fc)"},
@@ -459,7 +459,7 @@ static struct bpf_align_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = REJECT,
 		.matches = {
-			{3, "R5_w", "pkt_end(off=0,imm=0)"},
+			{3, "R5_w", "pkt_end()"},
 			/* (ptr - ptr) << 2 == unknown, (4n) */
 			{5, "R5_w", "var_off=(0x0; 0xfffffffffffffffc)"},
 			/* (4n) + 14 == (4n+2).  We blow our bounds, because
@@ -513,7 +513,7 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{6, "R2_w", "pkt(off=0,r=8,imm=0)"},
+			{6, "R2_w", "pkt(r=8)"},
 			{8, "R6_w", "var_off=(0x0; 0x3fc)"},
 			/* Adding 14 makes R6 be (4n+2) */
 			{9, "R6_w", "var_off=(0x2; 0x7fc)"},
@@ -566,7 +566,7 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{6, "R2_w", "pkt(off=0,r=8,imm=0)"},
+			{6, "R2_w", "pkt(r=8)"},
 			{9, "R6_w", "var_off=(0x0; 0x3c)"},
 			/* Adding 14 makes R6 be (4n+2) */
 			{10, "R6_w", "var_off=(0x2; 0x7c)"},
@@ -659,14 +659,14 @@ static int do_test_single(struct bpf_align_test *test)
 			/* Check the next line as well in case the previous line
 			 * did not have a corresponding bpf insn. Example:
 			 * func#0 @0
-			 * 0: R1=ctx(off=0,imm=0) R10=fp0
+			 * 0: R1=ctx() R10=fp0
 			 * 0: (b7) r3 = 2                 ; R3_w=2
 			 *
 			 * Sometimes it's actually two lines below, e.g. when
 			 * searching for "6: R3_w=scalar(umax=255,var_off=(0x0; 0xff))":
-			 *   from 4 to 6: R0_w=pkt(off=8,r=8,imm=0) R1=ctx(off=0,imm=0) R2_w=pkt(off=0,r=8,imm=0) R3_w=pkt_end(off=0,imm=0) R10=fp0
-			 *   6: R0_w=pkt(off=8,r=8,imm=0) R1=ctx(off=0,imm=0) R2_w=pkt(off=0,r=8,imm=0) R3_w=pkt_end(off=0,imm=0) R10=fp0
-			 *   6: (71) r3 = *(u8 *)(r2 +0)           ; R2_w=pkt(off=0,r=8,imm=0) R3_w=scalar(umax=255,var_off=(0x0; 0xff))
+			 *   from 4 to 6: R0_w=pkt(off=8,r=8) R1=ctx() R2_w=pkt(r=8) R3_w=pkt_end() R10=fp0
+			 *   6: R0_w=pkt(off=8,r=8) R1=ctx() R2_w=pkt(r=8) R3_w=pkt_end() R10=fp0
+			 *   6: (71) r3 = *(u8 *)(r2 +0)           ; R2_w=pkt(r=8) R3_w=scalar(umax=255,var_off=(0x0; 0xff))
 			 */
 			while (!(p = strstr(line_ptr, m.reg)) || !strstr(p, m.match)) {
 				cur_line = -1;
diff --git a/tools/testing/selftests/bpf/prog_tests/bind_perm.c b/tools/testing/selftests/bpf/prog_tests/bind_perm.c
index a1766a298bb7..f7cd129cb82b 100644
--- a/tools/testing/selftests/bpf/prog_tests/bind_perm.c
+++ b/tools/testing/selftests/bpf/prog_tests/bind_perm.c
@@ -9,8 +9,6 @@
 #include "cap_helpers.h"
 #include "bind_perm.skel.h"
 
-static int duration;
-
 static int create_netns(void)
 {
 	if (!ASSERT_OK(unshare(CLONE_NEWNET), "create netns"))
@@ -27,7 +25,7 @@ void try_bind(int family, int port, int expected_errno)
 	int fd = -1;
 
 	fd = socket(family, SOCK_STREAM, 0);
-	if (CHECK(fd < 0, "fd", "errno %d", errno))
+	if (!ASSERT_GE(fd, 0, "socket"))
 		goto close_socket;
 
 	if (family == AF_INET) {
@@ -60,7 +58,7 @@ void test_bind_perm(void)
 		return;
 
 	cgroup_fd = test__join_cgroup("/bind_perm");
-	if (CHECK(cgroup_fd < 0, "cg-join", "errno %d", errno))
+	if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup"))
 		return;
 
 	skel = bind_perm__open_and_load();
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index e3498f607b49..618af9dfae9b 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -34,8 +34,6 @@
 #include "bpf_iter_ksym.skel.h"
 #include "bpf_iter_sockmap.skel.h"
 
-static int duration;
-
 static void test_btf_id_or_null(void)
 {
 	struct bpf_iter_test_kern3 *skel;
@@ -64,7 +62,7 @@ static void do_dummy_read_opts(struct bpf_program *prog, struct bpf_iter_attach_
 	/* not check contents, but ensure read() ends without error */
 	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
 		;
-	CHECK(len < 0, "read", "read failed: %s\n", strerror(errno));
+	ASSERT_GE(len, 0, "read");
 
 	close(iter_fd);
 
@@ -334,6 +332,8 @@ static void test_task_stack(void)
 	do_dummy_read(skel->progs.dump_task_stack);
 	do_dummy_read(skel->progs.get_task_user_stacks);
 
+	ASSERT_EQ(skel->bss->num_user_stacks, 1, "num_user_stacks");
+
 	bpf_iter_task_stack__destroy(skel);
 }
 
@@ -413,7 +413,7 @@ static int do_btf_read(struct bpf_iter_task_btf *skel)
 		goto free_link;
 	}
 
-	if (CHECK(err < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(err, 0, "read"))
 		goto free_link;
 
 	ASSERT_HAS_SUBSTR(taskbuf, "(struct task_struct)",
@@ -526,11 +526,11 @@ static int do_read_with_fd(int iter_fd, const char *expected,
 	start = 0;
 	while ((len = read(iter_fd, buf + start, read_buf_len)) > 0) {
 		start += len;
-		if (CHECK(start >= 16, "read", "read len %d\n", len))
+		if (!ASSERT_LT(start, 16, "read"))
 			return -1;
 		read_buf_len = read_one_char ? 1 : 16 - start;
 	}
-	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(len, 0, "read"))
 		return -1;
 
 	if (!ASSERT_STREQ(buf, expected, "read"))
@@ -571,8 +571,7 @@ static int do_read(const char *path, const char *expected)
 	int err, iter_fd;
 
 	iter_fd = open(path, O_RDONLY);
-	if (CHECK(iter_fd < 0, "open", "open %s failed: %s\n",
-		  path, strerror(errno)))
+	if (!ASSERT_GE(iter_fd, 0, "open"))
 		return -1;
 
 	err = do_read_with_fd(iter_fd, expected, false);
@@ -600,7 +599,7 @@ static void test_file_iter(void)
 	unlink(path);
 
 	err = bpf_link__pin(link, path);
-	if (CHECK(err, "pin_iter", "pin_iter to %s failed: %d\n", path, err))
+	if (!ASSERT_OK(err, "pin_iter"))
 		goto free_link;
 
 	err = do_read(path, "abcd");
@@ -651,12 +650,10 @@ static void test_overflow(bool test_e2big_overflow, bool ret1)
 	 * overflow and needs restart.
 	 */
 	map1_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 8, 1, NULL);
-	if (CHECK(map1_fd < 0, "bpf_map_create",
-		  "map_creation failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(map1_fd, 0, "bpf_map_create"))
 		goto out;
 	map2_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 8, 1, NULL);
-	if (CHECK(map2_fd < 0, "bpf_map_create",
-		  "map_creation failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(map2_fd, 0, "bpf_map_create"))
 		goto free_map1;
 
 	/* bpf_seq_printf kernel buffer is 8 pages, so one map
@@ -685,14 +682,12 @@ static void test_overflow(bool test_e2big_overflow, bool ret1)
 	/* setup filtering map_id in bpf program */
 	map_info_len = sizeof(map_info);
 	err = bpf_map_get_info_by_fd(map1_fd, &map_info, &map_info_len);
-	if (CHECK(err, "get_map_info", "get map info failed: %s\n",
-		  strerror(errno)))
+	if (!ASSERT_OK(err, "get_map_info"))
 		goto free_map2;
 	skel->bss->map1_id = map_info.id;
 
 	err = bpf_map_get_info_by_fd(map2_fd, &map_info, &map_info_len);
-	if (CHECK(err, "get_map_info", "get map info failed: %s\n",
-		  strerror(errno)))
+	if (!ASSERT_OK(err, "get_map_info"))
 		goto free_map2;
 	skel->bss->map2_id = map_info.id;
 
@@ -705,7 +700,7 @@ static void test_overflow(bool test_e2big_overflow, bool ret1)
 		goto free_link;
 
 	buf = malloc(expected_read_len);
-	if (!buf)
+	if (!ASSERT_OK_PTR(buf, "malloc"))
 		goto close_iter;
 
 	/* do read */
@@ -714,16 +709,14 @@ static void test_overflow(bool test_e2big_overflow, bool ret1)
 		while ((len = read(iter_fd, buf, expected_read_len)) > 0)
 			total_read_len += len;
 
-		CHECK(len != -1 || errno != E2BIG, "read",
-		      "expected ret -1, errno E2BIG, but get ret %d, error %s\n",
-			  len, strerror(errno));
+		ASSERT_EQ(len, -1, "read");
+		ASSERT_EQ(errno, E2BIG, "read");
 		goto free_buf;
 	} else if (!ret1) {
 		while ((len = read(iter_fd, buf, expected_read_len)) > 0)
 			total_read_len += len;
 
-		if (CHECK(len < 0, "read", "read failed: %s\n",
-			  strerror(errno)))
+		if (!ASSERT_GE(len, 0, "read"))
 			goto free_buf;
 	} else {
 		do {
@@ -732,8 +725,7 @@ static void test_overflow(bool test_e2big_overflow, bool ret1)
 				total_read_len += len;
 		} while (len > 0 || len == -EAGAIN);
 
-		if (CHECK(len < 0, "read", "read failed: %s\n",
-			  strerror(errno)))
+		if (!ASSERT_GE(len, 0, "read"))
 			goto free_buf;
 	}
 
@@ -836,7 +828,7 @@ static void test_bpf_hash_map(void)
 	/* do some tests */
 	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
 		;
-	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(len, 0, "read"))
 		goto close_iter;
 
 	/* test results */
@@ -878,6 +870,8 @@ static void test_bpf_percpu_hash_map(void)
 
 	skel->rodata->num_cpus = bpf_num_possible_cpus();
 	val = malloc(8 * bpf_num_possible_cpus());
+	if (!ASSERT_OK_PTR(val, "malloc"))
+		goto out;
 
 	err = bpf_iter_bpf_percpu_hash_map__load(skel);
 	if (!ASSERT_OK_PTR(skel, "bpf_iter_bpf_percpu_hash_map__load"))
@@ -917,7 +911,7 @@ static void test_bpf_percpu_hash_map(void)
 	/* do some tests */
 	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
 		;
-	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(len, 0, "read"))
 		goto close_iter;
 
 	/* test results */
@@ -983,17 +977,14 @@ static void test_bpf_array_map(void)
 	start = 0;
 	while ((len = read(iter_fd, buf + start, sizeof(buf) - start)) > 0)
 		start += len;
-	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(len, 0, "read"))
 		goto close_iter;
 
 	/* test results */
 	res_first_key = *(__u32 *)buf;
 	res_first_val = *(__u64 *)(buf + sizeof(__u32));
-	if (CHECK(res_first_key != 0 || res_first_val != first_val,
-		  "bpf_seq_write",
-		  "seq_write failure: first key %u vs expected 0, "
-		  " first value %llu vs expected %llu\n",
-		  res_first_key, res_first_val, first_val))
+	if (!ASSERT_EQ(res_first_key, 0, "bpf_seq_write") ||
+			!ASSERT_EQ(res_first_val, first_val, "bpf_seq_write"))
 		goto close_iter;
 
 	if (!ASSERT_EQ(skel->bss->key_sum, expected_key, "key_sum"))
@@ -1057,6 +1048,8 @@ static void test_bpf_percpu_array_map(void)
 
 	skel->rodata->num_cpus = bpf_num_possible_cpus();
 	val = malloc(8 * bpf_num_possible_cpus());
+	if (!ASSERT_OK_PTR(val, "malloc"))
+		goto out;
 
 	err = bpf_iter_bpf_percpu_array_map__load(skel);
 	if (!ASSERT_OK_PTR(skel, "bpf_iter_bpf_percpu_array_map__load"))
@@ -1092,7 +1085,7 @@ static void test_bpf_percpu_array_map(void)
 	/* do some tests */
 	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
 		;
-	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(len, 0, "read"))
 		goto close_iter;
 
 	/* test results */
@@ -1131,6 +1124,7 @@ static void test_bpf_sk_storage_delete(void)
 	sock_fd = socket(AF_INET6, SOCK_STREAM, 0);
 	if (!ASSERT_GE(sock_fd, 0, "socket"))
 		goto out;
+
 	err = bpf_map_update_elem(map_fd, &sock_fd, &val, BPF_NOEXIST);
 	if (!ASSERT_OK(err, "map_update"))
 		goto out;
@@ -1151,14 +1145,19 @@ static void test_bpf_sk_storage_delete(void)
 	/* do some tests */
 	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
 		;
-	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(len, 0, "read"))
 		goto close_iter;
 
 	/* test results */
 	err = bpf_map_lookup_elem(map_fd, &sock_fd, &val);
-	if (CHECK(!err || errno != ENOENT, "bpf_map_lookup_elem",
-		  "map value wasn't deleted (err=%d, errno=%d)\n", err, errno))
-		goto close_iter;
+
+	 /* Note: The following assertions serve to ensure
+	  * the value was deleted. It does so by asserting
+	  * that bpf_map_lookup_elem has failed. This might
+	  * seem counterintuitive at first.
+	  */
+	ASSERT_ERR(err, "bpf_map_lookup_elem");
+	ASSERT_EQ(errno, ENOENT, "bpf_map_lookup_elem");
 
 close_iter:
 	close(iter_fd);
@@ -1203,17 +1202,15 @@ static void test_bpf_sk_storage_get(void)
 	do_dummy_read(skel->progs.fill_socket_owner);
 
 	err = bpf_map_lookup_elem(map_fd, &sock_fd, &val);
-	if (CHECK(err || val != getpid(), "bpf_map_lookup_elem",
-	    "map value wasn't set correctly (expected %d, got %d, err=%d)\n",
-	    getpid(), val, err))
+	if (!ASSERT_OK(err, "bpf_map_lookup_elem") ||
+			!ASSERT_EQ(val, getpid(), "bpf_map_lookup_elem"))
 		goto close_socket;
 
 	do_dummy_read(skel->progs.negate_socket_local_storage);
 
 	err = bpf_map_lookup_elem(map_fd, &sock_fd, &val);
-	CHECK(err || val != -getpid(), "bpf_map_lookup_elem",
-	      "map value wasn't set correctly (expected %d, got %d, err=%d)\n",
-	      -getpid(), val, err);
+	ASSERT_OK(err, "bpf_map_lookup_elem");
+	ASSERT_EQ(val, -getpid(), "bpf_map_lookup_elem");
 
 close_socket:
 	close(sock_fd);
@@ -1290,7 +1287,7 @@ static void test_bpf_sk_storage_map(void)
 	/* do some tests */
 	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
 		;
-	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(len, 0, "read"))
 		goto close_iter;
 
 	/* test results */
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
index 675b90b15280..f09d6ac2ef09 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
@@ -25,7 +25,7 @@ void serial_test_bpf_obj_id(void)
 	 */
 	__u32 map_ids[nr_iters + 1];
 	char jited_insns[128], xlated_insns[128], zeros[128], tp_name[128];
-	__u32 i, next_id, info_len, nr_id_found, duration = 0;
+	__u32 i, next_id, info_len, nr_id_found;
 	struct timespec real_time_ts, boot_time_ts;
 	int err = 0;
 	__u64 array_value;
@@ -33,16 +33,16 @@ void serial_test_bpf_obj_id(void)
 	time_t now, load_time;
 
 	err = bpf_prog_get_fd_by_id(0);
-	CHECK(err >= 0 || errno != ENOENT,
-	      "get-fd-by-notexist-prog-id", "err %d errno %d\n", err, errno);
+	ASSERT_LT(err, 0, "bpf_prog_get_fd_by_id");
+	ASSERT_EQ(errno, ENOENT, "bpf_prog_get_fd_by_id");
 
 	err = bpf_map_get_fd_by_id(0);
-	CHECK(err >= 0 || errno != ENOENT,
-	      "get-fd-by-notexist-map-id", "err %d errno %d\n", err, errno);
+	ASSERT_LT(err, 0, "bpf_map_get_fd_by_id");
+	ASSERT_EQ(errno, ENOENT, "bpf_map_get_fd_by_id");
 
 	err = bpf_link_get_fd_by_id(0);
-	CHECK(err >= 0 || errno != ENOENT,
-	      "get-fd-by-notexist-link-id", "err %d errno %d\n", err, errno);
+	ASSERT_LT(err, 0, "bpf_map_get_fd_by_id");
+	ASSERT_EQ(errno, ENOENT, "bpf_map_get_fd_by_id");
 
 	/* Check bpf_map_get_info_by_fd() */
 	bzero(zeros, sizeof(zeros));
@@ -53,25 +53,26 @@ void serial_test_bpf_obj_id(void)
 		/* test_obj_id.o is a dumb prog. It should never fail
 		 * to load.
 		 */
-		if (CHECK_FAIL(err))
+		if (!ASSERT_OK(err, "bpf_prog_test_load"))
 			continue;
 
 		/* Insert a magic value to the map */
 		map_fds[i] = bpf_find_map(__func__, objs[i], "test_map_id");
-		if (CHECK_FAIL(map_fds[i] < 0))
+		if (!ASSERT_GE(map_fds[i], 0, "bpf_find_map"))
 			goto done;
+
 		err = bpf_map_update_elem(map_fds[i], &array_key,
 					  &array_magic_value, 0);
-		if (CHECK_FAIL(err))
+		if (!ASSERT_OK(err, "bpf_map_update_elem"))
 			goto done;
 
-		prog = bpf_object__find_program_by_name(objs[i],
-							"test_obj_id");
-		if (CHECK_FAIL(!prog))
+		prog = bpf_object__find_program_by_name(objs[i], "test_obj_id");
+		if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
 			goto done;
+
 		links[i] = bpf_program__attach(prog);
 		err = libbpf_get_error(links[i]);
-		if (CHECK(err, "prog_attach", "prog #%d, err %d\n", i, err)) {
+		if (!ASSERT_OK(err, "bpf_program__attach")) {
 			links[i] = NULL;
 			goto done;
 		}
@@ -81,24 +82,14 @@ void serial_test_bpf_obj_id(void)
 		bzero(&map_infos[i], info_len);
 		err = bpf_map_get_info_by_fd(map_fds[i], &map_infos[i],
 					     &info_len);
-		if (CHECK(err ||
-			  map_infos[i].type != BPF_MAP_TYPE_ARRAY ||
-			  map_infos[i].key_size != sizeof(__u32) ||
-			  map_infos[i].value_size != sizeof(__u64) ||
-			  map_infos[i].max_entries != 1 ||
-			  map_infos[i].map_flags != 0 ||
-			  info_len != sizeof(struct bpf_map_info) ||
-			  strcmp((char *)map_infos[i].name, expected_map_name),
-			  "get-map-info(fd)",
-			  "err %d errno %d type %d(%d) info_len %u(%zu) key_size %u value_size %u max_entries %u map_flags %X name %s(%s)\n",
-			  err, errno,
-			  map_infos[i].type, BPF_MAP_TYPE_ARRAY,
-			  info_len, sizeof(struct bpf_map_info),
-			  map_infos[i].key_size,
-			  map_infos[i].value_size,
-			  map_infos[i].max_entries,
-			  map_infos[i].map_flags,
-			  map_infos[i].name, expected_map_name))
+		if (!ASSERT_OK(err, "bpf_map_get_info_by_fd") ||
+				!ASSERT_EQ(map_infos[i].type, BPF_MAP_TYPE_ARRAY, "map_type") ||
+				!ASSERT_EQ(map_infos[i].key_size, sizeof(__u32), "key_size") ||
+				!ASSERT_EQ(map_infos[i].value_size, sizeof(__u64), "value_size") ||
+				!ASSERT_EQ(map_infos[i].max_entries, 1, "max_entries") ||
+				!ASSERT_EQ(map_infos[i].map_flags, 0, "map_flags") ||
+				!ASSERT_EQ(info_len, sizeof(struct bpf_map_info), "map_info_len") ||
+				!ASSERT_STREQ((char *)map_infos[i].name, expected_map_name, "map_name"))
 			goto done;
 
 		/* Check getting prog info */
@@ -112,48 +103,34 @@ void serial_test_bpf_obj_id(void)
 		prog_infos[i].xlated_prog_len = sizeof(xlated_insns);
 		prog_infos[i].map_ids = ptr_to_u64(map_ids + i);
 		prog_infos[i].nr_map_ids = 2;
+
 		err = clock_gettime(CLOCK_REALTIME, &real_time_ts);
-		if (CHECK_FAIL(err))
+		if (!ASSERT_OK(err, "clock_gettime"))
 			goto done;
+
 		err = clock_gettime(CLOCK_BOOTTIME, &boot_time_ts);
-		if (CHECK_FAIL(err))
+		if (!ASSERT_OK(err, "clock_gettime"))
 			goto done;
+
 		err = bpf_prog_get_info_by_fd(prog_fds[i], &prog_infos[i],
 					      &info_len);
 		load_time = (real_time_ts.tv_sec - boot_time_ts.tv_sec)
 			+ (prog_infos[i].load_time / nsec_per_sec);
-		if (CHECK(err ||
-			  prog_infos[i].type != BPF_PROG_TYPE_RAW_TRACEPOINT ||
-			  info_len != sizeof(struct bpf_prog_info) ||
-			  (env.jit_enabled && !prog_infos[i].jited_prog_len) ||
-			  (env.jit_enabled &&
-			   !memcmp(jited_insns, zeros, sizeof(zeros))) ||
-			  !prog_infos[i].xlated_prog_len ||
-			  !memcmp(xlated_insns, zeros, sizeof(zeros)) ||
-			  load_time < now - 60 || load_time > now + 60 ||
-			  prog_infos[i].created_by_uid != my_uid ||
-			  prog_infos[i].nr_map_ids != 1 ||
-			  *(int *)(long)prog_infos[i].map_ids != map_infos[i].id ||
-			  strcmp((char *)prog_infos[i].name, expected_prog_name),
-			  "get-prog-info(fd)",
-			  "err %d errno %d i %d type %d(%d) info_len %u(%zu) "
-			  "jit_enabled %d jited_prog_len %u xlated_prog_len %u "
-			  "jited_prog %d xlated_prog %d load_time %lu(%lu) "
-			  "uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) "
-			  "name %s(%s)\n",
-			  err, errno, i,
-			  prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER,
-			  info_len, sizeof(struct bpf_prog_info),
-			  env.jit_enabled,
-			  prog_infos[i].jited_prog_len,
-			  prog_infos[i].xlated_prog_len,
-			  !!memcmp(jited_insns, zeros, sizeof(zeros)),
-			  !!memcmp(xlated_insns, zeros, sizeof(zeros)),
-			  load_time, now,
-			  prog_infos[i].created_by_uid, my_uid,
-			  prog_infos[i].nr_map_ids, 1,
-			  *(int *)(long)prog_infos[i].map_ids, map_infos[i].id,
-			  prog_infos[i].name, expected_prog_name))
+
+		if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd") ||
+				!ASSERT_EQ(prog_infos[i].type, BPF_PROG_TYPE_RAW_TRACEPOINT, "prog_type") ||
+				!ASSERT_EQ(info_len, sizeof(struct bpf_prog_info), "prog_info_len") ||
+				!ASSERT_FALSE((env.jit_enabled && !prog_infos[i].jited_prog_len), "jited_prog_len") ||
+				!ASSERT_FALSE((env.jit_enabled && !memcmp(jited_insns, zeros, sizeof(zeros))),
+					"jited_insns") ||
+				!ASSERT_NEQ(prog_infos[i].xlated_prog_len, 0, "xlated_prog_len") ||
+				!ASSERT_NEQ(memcmp(xlated_insns, zeros, sizeof(zeros)), 0, "xlated_insns") ||
+				!ASSERT_GE(load_time, (now - 60), "load_time") ||
+				!ASSERT_LE(load_time, (now + 60), "load_time") ||
+				!ASSERT_EQ(prog_infos[i].created_by_uid, my_uid, "created_by_uid") ||
+				!ASSERT_EQ(prog_infos[i].nr_map_ids, 1, "nr_map_ids") ||
+				!ASSERT_EQ(*(int *)(long)prog_infos[i].map_ids, map_infos[i].id, "map_ids") ||
+				!ASSERT_STREQ((char *)prog_infos[i].name, expected_prog_name, "prog_name"))
 			goto done;
 
 		/* Check getting link info */
@@ -163,25 +140,12 @@ void serial_test_bpf_obj_id(void)
 		link_infos[i].raw_tracepoint.tp_name_len = sizeof(tp_name);
 		err = bpf_link_get_info_by_fd(bpf_link__fd(links[i]),
 					      &link_infos[i], &info_len);
-		if (CHECK(err ||
-			  link_infos[i].type != BPF_LINK_TYPE_RAW_TRACEPOINT ||
-			  link_infos[i].prog_id != prog_infos[i].id ||
-			  link_infos[i].raw_tracepoint.tp_name != ptr_to_u64(&tp_name) ||
-			  strcmp(u64_to_ptr(link_infos[i].raw_tracepoint.tp_name),
-				 "sys_enter") ||
-			  info_len != sizeof(struct bpf_link_info),
-			  "get-link-info(fd)",
-			  "err %d errno %d info_len %u(%zu) type %d(%d) id %d "
-			  "prog_id %d (%d) tp_name %s(%s)\n",
-			  err, errno,
-			  info_len, sizeof(struct bpf_link_info),
-			  link_infos[i].type, BPF_LINK_TYPE_RAW_TRACEPOINT,
-			  link_infos[i].id,
-			  link_infos[i].prog_id, prog_infos[i].id,
-			  (const char *)u64_to_ptr(link_infos[i].raw_tracepoint.tp_name),
-			  "sys_enter"))
+		if (!ASSERT_OK(err, "bpf_link_get_info_by_fd") ||
+				!ASSERT_EQ(link_infos[i].type, BPF_LINK_TYPE_RAW_TRACEPOINT, "link_type") ||
+				!ASSERT_EQ(link_infos[i].prog_id, prog_infos[i].id, "prog_id") ||
+				!ASSERT_EQ(link_infos[i].raw_tracepoint.tp_name, ptr_to_u64(&tp_name), "&tp_name") ||
+				!ASSERT_STREQ(u64_to_ptr(link_infos[i].raw_tracepoint.tp_name), "sys_enter", "tp_name"))
 			goto done;
-
 	}
 
 	/* Check bpf_prog_get_next_id() */
@@ -190,7 +154,7 @@ void serial_test_bpf_obj_id(void)
 	while (!bpf_prog_get_next_id(next_id, &next_id)) {
 		struct bpf_prog_info prog_info = {};
 		__u32 saved_map_id;
-		int prog_fd;
+		int prog_fd, cmp_res;
 
 		info_len = sizeof(prog_info);
 
@@ -198,9 +162,7 @@ void serial_test_bpf_obj_id(void)
 		if (prog_fd < 0 && errno == ENOENT)
 			/* The bpf_prog is in the dead row */
 			continue;
-		if (CHECK(prog_fd < 0, "get-prog-fd(next_id)",
-			  "prog_fd %d next_id %d errno %d\n",
-			  prog_fd, next_id, errno))
+		if (!ASSERT_GE(prog_fd, 0, "bpf_prog_get_fd_by_id"))
 			break;
 
 		for (i = 0; i < nr_iters; i++)
@@ -218,9 +180,8 @@ void serial_test_bpf_obj_id(void)
 		 */
 		prog_info.nr_map_ids = 1;
 		err = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &info_len);
-		if (CHECK(!err || errno != EFAULT,
-			  "get-prog-fd-bad-nr-map-ids", "err %d errno %d(%d)",
-			  err, errno, EFAULT))
+		if (!ASSERT_ERR(err, "bpf_prog_get_info_by_fd") ||
+				!ASSERT_EQ(errno, EFAULT, "bpf_prog_get_info_by_fd"))
 			break;
 		bzero(&prog_info, sizeof(prog_info));
 		info_len = sizeof(prog_info);
@@ -231,27 +192,22 @@ void serial_test_bpf_obj_id(void)
 		err = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &info_len);
 		prog_infos[i].jited_prog_insns = 0;
 		prog_infos[i].xlated_prog_insns = 0;
-		CHECK(err || info_len != sizeof(struct bpf_prog_info) ||
-		      memcmp(&prog_info, &prog_infos[i], info_len) ||
-		      *(int *)(long)prog_info.map_ids != saved_map_id,
-		      "get-prog-info(next_id->fd)",
-		      "err %d errno %d info_len %u(%zu) memcmp %d map_id %u(%u)\n",
-		      err, errno, info_len, sizeof(struct bpf_prog_info),
-		      memcmp(&prog_info, &prog_infos[i], info_len),
-		      *(int *)(long)prog_info.map_ids, saved_map_id);
+		cmp_res = memcmp(&prog_info, &prog_infos[i], info_len);
+
+		ASSERT_OK(err, "bpf_prog_get_info_by_fd");
+		ASSERT_EQ(info_len, sizeof(struct bpf_prog_info), "prog_info_len");
+		ASSERT_OK(cmp_res, "memcmp");
+		ASSERT_EQ(*(int *)(long)prog_info.map_ids, saved_map_id, "map_id");
 		close(prog_fd);
 	}
-	CHECK(nr_id_found != nr_iters,
-	      "check total prog id found by get_next_id",
-	      "nr_id_found %u(%u)\n",
-	      nr_id_found, nr_iters);
+	ASSERT_EQ(nr_id_found, nr_iters, "prog_nr_id_found");
 
 	/* Check bpf_map_get_next_id() */
 	nr_id_found = 0;
 	next_id = 0;
 	while (!bpf_map_get_next_id(next_id, &next_id)) {
 		struct bpf_map_info map_info = {};
-		int map_fd;
+		int map_fd, cmp_res;
 
 		info_len = sizeof(map_info);
 
@@ -259,9 +215,7 @@ void serial_test_bpf_obj_id(void)
 		if (map_fd < 0 && errno == ENOENT)
 			/* The bpf_map is in the dead row */
 			continue;
-		if (CHECK(map_fd < 0, "get-map-fd(next_id)",
-			  "map_fd %d next_id %u errno %d\n",
-			  map_fd, next_id, errno))
+		if (!ASSERT_GE(map_fd, 0, "bpf_map_get_fd_by_id"))
 			break;
 
 		for (i = 0; i < nr_iters; i++)
@@ -274,25 +228,19 @@ void serial_test_bpf_obj_id(void)
 		nr_id_found++;
 
 		err = bpf_map_lookup_elem(map_fd, &array_key, &array_value);
-		if (CHECK_FAIL(err))
+		if (!ASSERT_OK(err, "bpf_map_lookup_elem"))
 			goto done;
 
 		err = bpf_map_get_info_by_fd(map_fd, &map_info, &info_len);
-		CHECK(err || info_len != sizeof(struct bpf_map_info) ||
-		      memcmp(&map_info, &map_infos[i], info_len) ||
-		      array_value != array_magic_value,
-		      "check get-map-info(next_id->fd)",
-		      "err %d errno %d info_len %u(%zu) memcmp %d array_value %llu(%llu)\n",
-		      err, errno, info_len, sizeof(struct bpf_map_info),
-		      memcmp(&map_info, &map_infos[i], info_len),
-		      array_value, array_magic_value);
+		cmp_res = memcmp(&map_info, &map_infos[i], info_len);
+		ASSERT_OK(err, "bpf_map_get_info_by_fd");
+		ASSERT_EQ(info_len, sizeof(struct bpf_map_info), "info_len");
+		ASSERT_OK(cmp_res, "memcmp");
+		ASSERT_EQ(array_value, array_magic_value, "array_value");
 
 		close(map_fd);
 	}
-	CHECK(nr_id_found != nr_iters,
-	      "check total map id found by get_next_id",
-	      "nr_id_found %u(%u)\n",
-	      nr_id_found, nr_iters);
+	ASSERT_EQ(nr_id_found, nr_iters, "map_nr_id_found");
 
 	/* Check bpf_link_get_next_id() */
 	nr_id_found = 0;
@@ -308,9 +256,7 @@ void serial_test_bpf_obj_id(void)
 		if (link_fd < 0 && errno == ENOENT)
 			/* The bpf_link is in the dead row */
 			continue;
-		if (CHECK(link_fd < 0, "get-link-fd(next_id)",
-			  "link_fd %d next_id %u errno %d\n",
-			  link_fd, next_id, errno))
+		if (!ASSERT_GE(link_fd, 0, "bpf_link_get_fd_by_id"))
 			break;
 
 		for (i = 0; i < nr_iters; i++)
@@ -325,17 +271,13 @@ void serial_test_bpf_obj_id(void)
 		err = bpf_link_get_info_by_fd(link_fd, &link_info, &info_len);
 		cmp_res = memcmp(&link_info, &link_infos[i],
 				offsetof(struct bpf_link_info, raw_tracepoint));
-		CHECK(err || info_len != sizeof(link_info) || cmp_res,
-		      "check get-link-info(next_id->fd)",
-		      "err %d errno %d info_len %u(%zu) memcmp %d\n",
-		      err, errno, info_len, sizeof(struct bpf_link_info),
-		      cmp_res);
+		ASSERT_OK(err, "bpf_link_get_info_by_fd");
+		ASSERT_EQ(info_len, sizeof(link_info), "info_len");
+		ASSERT_OK(cmp_res, "memcmp");
 
 		close(link_fd);
 	}
-	CHECK(nr_id_found != nr_iters,
-	      "check total link id found by get_next_id",
-	      "nr_id_found %u(%u)\n", nr_id_found, nr_iters);
+	ASSERT_EQ(nr_id_found, nr_iters, "link_nr_id_found");
 
 done:
 	for (i = 0; i < nr_iters; i++) {
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index 4aabeaa525d4..a88e6e07e4f5 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -20,15 +20,14 @@
 
 static const unsigned int total_bytes = 10 * 1024 * 1024;
 static int expected_stg = 0xeB9F;
-static int stop, duration;
+static int stop;
 
 static int settcpca(int fd, const char *tcp_ca)
 {
 	int err;
 
 	err = setsockopt(fd, IPPROTO_TCP, TCP_CONGESTION, tcp_ca, strlen(tcp_ca));
-	if (CHECK(err == -1, "setsockopt(fd, TCP_CONGESTION)", "errno:%d\n",
-		  errno))
+	if (!ASSERT_NEQ(err, -1, "setsockopt"))
 		return -1;
 
 	return 0;
@@ -65,8 +64,7 @@ static void *server(void *arg)
 		bytes += nr_sent;
 	}
 
-	CHECK(bytes != total_bytes, "send", "%zd != %u nr_sent:%zd errno:%d\n",
-	      bytes, total_bytes, nr_sent, errno);
+	ASSERT_EQ(bytes, total_bytes, "send");
 
 done:
 	if (fd >= 0)
@@ -92,10 +90,11 @@ static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map)
 	WRITE_ONCE(stop, 0);
 
 	lfd = socket(AF_INET6, SOCK_STREAM, 0);
-	if (CHECK(lfd == -1, "socket", "errno:%d\n", errno))
+	if (!ASSERT_NEQ(lfd, -1, "socket"))
 		return;
+
 	fd = socket(AF_INET6, SOCK_STREAM, 0);
-	if (CHECK(fd == -1, "socket", "errno:%d\n", errno)) {
+	if (!ASSERT_NEQ(fd, -1, "socket")) {
 		close(lfd);
 		return;
 	}
@@ -108,26 +107,27 @@ static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map)
 	sa6.sin6_family = AF_INET6;
 	sa6.sin6_addr = in6addr_loopback;
 	err = bind(lfd, (struct sockaddr *)&sa6, addrlen);
-	if (CHECK(err == -1, "bind", "errno:%d\n", errno))
+	if (!ASSERT_NEQ(err, -1, "bind"))
 		goto done;
+
 	err = getsockname(lfd, (struct sockaddr *)&sa6, &addrlen);
-	if (CHECK(err == -1, "getsockname", "errno:%d\n", errno))
+	if (!ASSERT_NEQ(err, -1, "getsockname"))
 		goto done;
+
 	err = listen(lfd, 1);
-	if (CHECK(err == -1, "listen", "errno:%d\n", errno))
+	if (!ASSERT_NEQ(err, -1, "listen"))
 		goto done;
 
 	if (sk_stg_map) {
 		err = bpf_map_update_elem(bpf_map__fd(sk_stg_map), &fd,
 					  &expected_stg, BPF_NOEXIST);
-		if (CHECK(err, "bpf_map_update_elem(sk_stg_map)",
-			  "err:%d errno:%d\n", err, errno))
+		if (!ASSERT_OK(err, "bpf_map_update_elem(sk_stg_map)"))
 			goto done;
 	}
 
 	/* connect to server */
 	err = connect(fd, (struct sockaddr *)&sa6, addrlen);
-	if (CHECK(err == -1, "connect", "errno:%d\n", errno))
+	if (!ASSERT_NEQ(err, -1, "connect"))
 		goto done;
 
 	if (sk_stg_map) {
@@ -135,14 +135,13 @@ static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map)
 
 		err = bpf_map_lookup_elem(bpf_map__fd(sk_stg_map), &fd,
 					  &tmp_stg);
-		if (CHECK(!err || errno != ENOENT,
-			  "bpf_map_lookup_elem(sk_stg_map)",
-			  "err:%d errno:%d\n", err, errno))
+		if (!ASSERT_ERR(err, "bpf_map_lookup_elem(sk_stg_map)") ||
+				!ASSERT_EQ(errno, ENOENT, "bpf_map_lookup_elem(sk_stg_map)"))
 			goto done;
 	}
 
 	err = pthread_create(&srv_thread, NULL, server, (void *)(long)lfd);
-	if (CHECK(err != 0, "pthread_create", "err:%d errno:%d\n", err, errno))
+	if (!ASSERT_OK(err, "pthread_create"))
 		goto done;
 
 	/* recv total_bytes */
@@ -156,13 +155,12 @@ static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map)
 		bytes += nr_recv;
 	}
 
-	CHECK(bytes != total_bytes, "recv", "%zd != %u nr_recv:%zd errno:%d\n",
-	      bytes, total_bytes, nr_recv, errno);
+	ASSERT_EQ(bytes, total_bytes, "recv");
 
 	WRITE_ONCE(stop, 1);
 	pthread_join(srv_thread, &thread_ret);
-	CHECK(IS_ERR(thread_ret), "pthread_join", "thread_ret:%ld",
-	      PTR_ERR(thread_ret));
+	ASSERT_OK(IS_ERR(thread_ret), "thread_ret");
+
 done:
 	close(lfd);
 	close(fd);
@@ -174,7 +172,7 @@ static void test_cubic(void)
 	struct bpf_link *link;
 
 	cubic_skel = bpf_cubic__open_and_load();
-	if (CHECK(!cubic_skel, "bpf_cubic__open_and_load", "failed\n"))
+	if (!ASSERT_OK_PTR(cubic_skel, "bpf_cubic__open_and_load"))
 		return;
 
 	link = bpf_map__attach_struct_ops(cubic_skel->maps.cubic);
@@ -197,7 +195,7 @@ static void test_dctcp(void)
 	struct bpf_link *link;
 
 	dctcp_skel = bpf_dctcp__open_and_load();
-	if (CHECK(!dctcp_skel, "bpf_dctcp__open_and_load", "failed\n"))
+	if (!ASSERT_OK_PTR(dctcp_skel, "bpf_dctcp__open_and_load"))
 		return;
 
 	link = bpf_map__attach_struct_ops(dctcp_skel->maps.dctcp);
@@ -207,9 +205,7 @@ static void test_dctcp(void)
 	}
 
 	do_test("bpf_dctcp", dctcp_skel->maps.sk_stg_map);
-	CHECK(dctcp_skel->bss->stg_result != expected_stg,
-	      "Unexpected stg_result", "stg_result (%x) != expected_stg (%x)\n",
-	      dctcp_skel->bss->stg_result, expected_stg);
+	ASSERT_EQ(dctcp_skel->bss->stg_result, expected_stg, "stg_result");
 
 	bpf_link__destroy(link);
 	bpf_dctcp__destroy(dctcp_skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
index 731c343897d8..e770912fc1d2 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
@@ -35,7 +35,7 @@ static int check_load(const char *file, enum bpf_prog_type type)
 	}
 
 	bpf_program__set_type(prog, type);
-	bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32);
+	bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS);
 	bpf_program__set_log_level(prog, 4 | extra_prog_load_log_flags);
 
 	err = bpf_object__load(obj);
diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index 92d51f377fe5..816145bcb647 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -4630,11 +4630,6 @@ static int test_btf_id(unsigned int test_num)
 	/* The map holds the last ref to BTF and its btf_id */
 	close(map_fd);
 	map_fd = -1;
-	btf_fd[0] = bpf_btf_get_fd_by_id(map_info.btf_id);
-	if (CHECK(btf_fd[0] >= 0, "BTF lingers")) {
-		err = -1;
-		goto done;
-	}
 
 	fprintf(stderr, "OK");
 
@@ -5265,6 +5260,7 @@ static size_t get_pprint_mapv_size(enum pprint_mapv_kind_t mapv_kind)
 #endif
 
 	assert(0);
+	return 0;
 }
 
 static void set_pprint_mapv(enum pprint_mapv_kind_t mapv_kind,
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c b/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c
new file mode 100644
index 000000000000..74d6d7546f40
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */
+
+#include <sys/types.h>
+#include <unistd.h>
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+#include "test_cgroup1_hierarchy.skel.h"
+
+static void bpf_cgroup1(struct test_cgroup1_hierarchy *skel)
+{
+	struct bpf_link *lsm_link, *fentry_link;
+	int err;
+
+	/* Attach LSM prog first */
+	lsm_link = bpf_program__attach_lsm(skel->progs.lsm_run);
+	if (!ASSERT_OK_PTR(lsm_link, "lsm_attach"))
+		return;
+
+	/* LSM prog will be triggered when attaching fentry */
+	fentry_link = bpf_program__attach_trace(skel->progs.fentry_run);
+	ASSERT_NULL(fentry_link, "fentry_attach_fail");
+
+	err = bpf_link__destroy(lsm_link);
+	ASSERT_OK(err, "destroy_lsm");
+}
+
+static void bpf_cgroup1_sleepable(struct test_cgroup1_hierarchy *skel)
+{
+	struct bpf_link *lsm_link, *fentry_link;
+	int err;
+
+	/* Attach LSM prog first */
+	lsm_link = bpf_program__attach_lsm(skel->progs.lsm_s_run);
+	if (!ASSERT_OK_PTR(lsm_link, "lsm_attach"))
+		return;
+
+	/* LSM prog will be triggered when attaching fentry */
+	fentry_link = bpf_program__attach_trace(skel->progs.fentry_run);
+	ASSERT_NULL(fentry_link, "fentry_attach_fail");
+
+	err = bpf_link__destroy(lsm_link);
+	ASSERT_OK(err, "destroy_lsm");
+}
+
+static void bpf_cgroup1_invalid_id(struct test_cgroup1_hierarchy *skel)
+{
+	struct bpf_link *lsm_link, *fentry_link;
+	int err;
+
+	/* Attach LSM prog first */
+	lsm_link = bpf_program__attach_lsm(skel->progs.lsm_run);
+	if (!ASSERT_OK_PTR(lsm_link, "lsm_attach"))
+		return;
+
+	/* LSM prog will be triggered when attaching fentry */
+	fentry_link = bpf_program__attach_trace(skel->progs.fentry_run);
+	if (!ASSERT_OK_PTR(fentry_link, "fentry_attach_success"))
+		goto cleanup;
+
+	err = bpf_link__destroy(fentry_link);
+	ASSERT_OK(err, "destroy_lsm");
+
+cleanup:
+	err = bpf_link__destroy(lsm_link);
+	ASSERT_OK(err, "destroy_fentry");
+}
+
+void test_cgroup1_hierarchy(void)
+{
+	struct test_cgroup1_hierarchy *skel;
+	__u64 current_cgid;
+	int hid, err;
+
+	skel = test_cgroup1_hierarchy__open();
+	if (!ASSERT_OK_PTR(skel, "open"))
+		return;
+
+	skel->bss->target_pid = getpid();
+
+	err = bpf_program__set_attach_target(skel->progs.fentry_run, 0, "bpf_fentry_test1");
+	if (!ASSERT_OK(err, "fentry_set_target"))
+		goto destroy;
+
+	err = test_cgroup1_hierarchy__load(skel);
+	if (!ASSERT_OK(err, "load"))
+		goto destroy;
+
+	/* Setup cgroup1 hierarchy */
+	err = setup_classid_environment();
+	if (!ASSERT_OK(err, "setup_classid_environment"))
+		goto destroy;
+
+	err = join_classid();
+	if (!ASSERT_OK(err, "join_cgroup1"))
+		goto cleanup;
+
+	current_cgid = get_classid_cgroup_id();
+	if (!ASSERT_GE(current_cgid, 0, "cgroup1 id"))
+		goto cleanup;
+
+	hid = get_cgroup1_hierarchy_id("net_cls");
+	if (!ASSERT_GE(hid, 0, "cgroup1 id"))
+		goto cleanup;
+	skel->bss->target_hid = hid;
+
+	if (test__start_subtest("test_cgroup1_hierarchy")) {
+		skel->bss->target_ancestor_cgid = current_cgid;
+		bpf_cgroup1(skel);
+	}
+
+	if (test__start_subtest("test_root_cgid")) {
+		skel->bss->target_ancestor_cgid = 1;
+		skel->bss->target_ancestor_level = 0;
+		bpf_cgroup1(skel);
+	}
+
+	if (test__start_subtest("test_invalid_level")) {
+		skel->bss->target_ancestor_cgid = 1;
+		skel->bss->target_ancestor_level = 1;
+		bpf_cgroup1_invalid_id(skel);
+	}
+
+	if (test__start_subtest("test_invalid_cgid")) {
+		skel->bss->target_ancestor_cgid = 0;
+		bpf_cgroup1_invalid_id(skel);
+	}
+
+	if (test__start_subtest("test_invalid_hid")) {
+		skel->bss->target_ancestor_cgid = 1;
+		skel->bss->target_ancestor_level = 0;
+		skel->bss->target_hid = -1;
+		bpf_cgroup1_invalid_id(skel);
+	}
+
+	if (test__start_subtest("test_invalid_cgrp_name")) {
+		skel->bss->target_hid = get_cgroup1_hierarchy_id("net_cl");
+		skel->bss->target_ancestor_cgid = current_cgid;
+		bpf_cgroup1_invalid_id(skel);
+	}
+
+	if (test__start_subtest("test_invalid_cgrp_name2")) {
+		skel->bss->target_hid = get_cgroup1_hierarchy_id("net_cls,");
+		skel->bss->target_ancestor_cgid = current_cgid;
+		bpf_cgroup1_invalid_id(skel);
+	}
+
+	if (test__start_subtest("test_sleepable_prog")) {
+		skel->bss->target_hid = hid;
+		skel->bss->target_ancestor_cgid = current_cgid;
+		bpf_cgroup1_sleepable(skel);
+	}
+
+cleanup:
+	cleanup_classid_environment();
+destroy:
+	test_cgroup1_hierarchy__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
index 9026b42914d3..addf720428f7 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
@@ -71,7 +71,7 @@ void test_cgroup_v1v2(void)
 	}
 	ASSERT_OK(run_test(cgroup_fd, server_fd, false), "cgroup-v2-only");
 	setup_classid_environment();
-	set_classid(42);
+	set_classid();
 	ASSERT_OK(run_test(cgroup_fd, server_fd, true), "cgroup-v1v2");
 	cleanup_classid_environment();
 	close(server_fd);
diff --git a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c
index 63e776f4176e..747761572098 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c
@@ -19,6 +19,21 @@ struct socket_cookie {
 	__u64 cookie_value;
 };
 
+static bool is_cgroup1;
+static int target_hid;
+
+#define CGROUP_MODE_SET(skel)			\
+{						\
+	skel->bss->is_cgroup1 = is_cgroup1;	\
+	skel->bss->target_hid = target_hid;	\
+}
+
+static void cgroup_mode_value_init(bool cgroup, int hid)
+{
+	is_cgroup1 = cgroup;
+	target_hid = hid;
+}
+
 static void test_tp_btf(int cgroup_fd)
 {
 	struct cgrp_ls_tp_btf *skel;
@@ -29,6 +44,8 @@ static void test_tp_btf(int cgroup_fd)
 	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
 		return;
 
+	CGROUP_MODE_SET(skel);
+
 	/* populate a value in map_b */
 	err = bpf_map_update_elem(bpf_map__fd(skel->maps.map_b), &cgroup_fd, &val1, BPF_ANY);
 	if (!ASSERT_OK(err, "map_update_elem"))
@@ -130,6 +147,8 @@ static void test_recursion(int cgroup_fd)
 	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
 		return;
 
+	CGROUP_MODE_SET(skel);
+
 	err = cgrp_ls_recursion__attach(skel);
 	if (!ASSERT_OK(err, "skel_attach"))
 		goto out;
@@ -165,6 +184,8 @@ static void test_cgroup_iter_sleepable(int cgroup_fd, __u64 cgroup_id)
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
 		return;
 
+	CGROUP_MODE_SET(skel);
+
 	bpf_program__set_autoload(skel->progs.cgroup_iter, true);
 	err = cgrp_ls_sleepable__load(skel);
 	if (!ASSERT_OK(err, "skel_load"))
@@ -202,6 +223,7 @@ static void test_yes_rcu_lock(__u64 cgroup_id)
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
 		return;
 
+	CGROUP_MODE_SET(skel);
 	skel->bss->target_pid = syscall(SYS_gettid);
 
 	bpf_program__set_autoload(skel->progs.yes_rcu_lock, true);
@@ -229,6 +251,8 @@ static void test_no_rcu_lock(void)
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
 		return;
 
+	CGROUP_MODE_SET(skel);
+
 	bpf_program__set_autoload(skel->progs.no_rcu_lock, true);
 	err = cgrp_ls_sleepable__load(skel);
 	ASSERT_ERR(err, "skel_load");
@@ -236,7 +260,25 @@ static void test_no_rcu_lock(void)
 	cgrp_ls_sleepable__destroy(skel);
 }
 
-void test_cgrp_local_storage(void)
+static void test_cgrp1_no_rcu_lock(void)
+{
+	struct cgrp_ls_sleepable *skel;
+	int err;
+
+	skel = cgrp_ls_sleepable__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	CGROUP_MODE_SET(skel);
+
+	bpf_program__set_autoload(skel->progs.cgrp1_no_rcu_lock, true);
+	err = cgrp_ls_sleepable__load(skel);
+	ASSERT_OK(err, "skel_load");
+
+	cgrp_ls_sleepable__destroy(skel);
+}
+
+static void cgrp2_local_storage(void)
 {
 	__u64 cgroup_id;
 	int cgroup_fd;
@@ -245,6 +287,8 @@ void test_cgrp_local_storage(void)
 	if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup /cgrp_local_storage"))
 		return;
 
+	cgroup_mode_value_init(0, -1);
+
 	cgroup_id = get_cgroup_id("/cgrp_local_storage");
 	if (test__start_subtest("tp_btf"))
 		test_tp_btf(cgroup_fd);
@@ -263,3 +307,55 @@ void test_cgrp_local_storage(void)
 
 	close(cgroup_fd);
 }
+
+static void cgrp1_local_storage(void)
+{
+	int cgrp1_fd, cgrp1_hid, cgrp1_id, err;
+
+	/* Setup cgroup1 hierarchy */
+	err = setup_classid_environment();
+	if (!ASSERT_OK(err, "setup_classid_environment"))
+		return;
+
+	err = join_classid();
+	if (!ASSERT_OK(err, "join_cgroup1"))
+		goto cleanup;
+
+	cgrp1_fd = open_classid();
+	if (!ASSERT_GE(cgrp1_fd, 0, "cgroup1 fd"))
+		goto cleanup;
+
+	cgrp1_id = get_classid_cgroup_id();
+	if (!ASSERT_GE(cgrp1_id, 0, "cgroup1 id"))
+		goto close_fd;
+
+	cgrp1_hid = get_cgroup1_hierarchy_id("net_cls");
+	if (!ASSERT_GE(cgrp1_hid, 0, "cgroup1 hid"))
+		goto close_fd;
+
+	cgroup_mode_value_init(1, cgrp1_hid);
+
+	if (test__start_subtest("cgrp1_tp_btf"))
+		test_tp_btf(cgrp1_fd);
+	if (test__start_subtest("cgrp1_recursion"))
+		test_recursion(cgrp1_fd);
+	if (test__start_subtest("cgrp1_negative"))
+		test_negative();
+	if (test__start_subtest("cgrp1_iter_sleepable"))
+		test_cgroup_iter_sleepable(cgrp1_fd, cgrp1_id);
+	if (test__start_subtest("cgrp1_yes_rcu_lock"))
+		test_yes_rcu_lock(cgrp1_id);
+	if (test__start_subtest("cgrp1_no_rcu_lock"))
+		test_cgrp1_no_rcu_lock();
+
+close_fd:
+	close(cgrp1_fd);
+cleanup:
+	cleanup_classid_environment();
+}
+
+void test_cgrp_local_storage(void)
+{
+	cgrp2_local_storage();
+	cgrp1_local_storage();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cpumask.c b/tools/testing/selftests/bpf/prog_tests/cpumask.c
index 756ea8b590b6..c2e886399e3c 100644
--- a/tools/testing/selftests/bpf/prog_tests/cpumask.c
+++ b/tools/testing/selftests/bpf/prog_tests/cpumask.c
@@ -18,6 +18,7 @@ static const char * const cpumask_success_testcases[] = {
 	"test_insert_leave",
 	"test_insert_remove_release",
 	"test_global_mask_rcu",
+	"test_cpumask_weight",
 };
 
 static void verify_success(const char *prog_name)
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
index 8ec73fdfcdab..f29fc789c14b 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -348,7 +348,8 @@ static void test_func_sockmap_update(void)
 }
 
 static void test_obj_load_failure_common(const char *obj_file,
-					 const char *target_obj_file)
+					 const char *target_obj_file,
+					 const char *exp_msg)
 {
 	/*
 	 * standalone test that asserts failure to load freplace prog
@@ -356,6 +357,7 @@ static void test_obj_load_failure_common(const char *obj_file,
 	 */
 	struct bpf_object *obj = NULL, *pkt_obj;
 	struct bpf_program *prog;
+	char log_buf[64 * 1024];
 	int err, pkt_fd;
 	__u32 duration = 0;
 
@@ -374,11 +376,21 @@ static void test_obj_load_failure_common(const char *obj_file,
 	err = bpf_program__set_attach_target(prog, pkt_fd, NULL);
 	ASSERT_OK(err, "set_attach_target");
 
+	log_buf[0] = '\0';
+	if (exp_msg)
+		bpf_program__set_log_buf(prog, log_buf, sizeof(log_buf));
+	if (env.verbosity > VERBOSE_NONE)
+		bpf_program__set_log_level(prog, 2);
+
 	/* It should fail to load the program */
 	err = bpf_object__load(obj);
+	if (env.verbosity > VERBOSE_NONE && exp_msg) /* we overtook log */
+		printf("VERIFIER LOG:\n================\n%s\n================\n", log_buf);
 	if (CHECK(!err, "bpf_obj_load should fail", "err %d\n", err))
 		goto close_prog;
 
+	if (exp_msg)
+		ASSERT_HAS_SUBSTR(log_buf, exp_msg, "fail_msg");
 close_prog:
 	bpf_object__close(obj);
 	bpf_object__close(pkt_obj);
@@ -388,14 +400,24 @@ static void test_func_replace_return_code(void)
 {
 	/* test invalid return code in the replaced program */
 	test_obj_load_failure_common("./freplace_connect_v4_prog.bpf.o",
-				     "./connect4_prog.bpf.o");
+				     "./connect4_prog.bpf.o", NULL);
 }
 
 static void test_func_map_prog_compatibility(void)
 {
 	/* test with spin lock map value in the replaced program */
 	test_obj_load_failure_common("./freplace_attach_probe.bpf.o",
-				     "./test_attach_probe.bpf.o");
+				     "./test_attach_probe.bpf.o", NULL);
+}
+
+static void test_func_replace_unreliable(void)
+{
+	/* freplace'ing unreliable main prog should fail with error
+	 * "Cannot replace static functions"
+	 */
+	test_obj_load_failure_common("freplace_unreliable_prog.bpf.o",
+				     "./verifier_btf_unreliable_prog.bpf.o",
+				     "Cannot replace static functions");
 }
 
 static void test_func_replace_global_func(void)
@@ -563,6 +585,8 @@ void serial_test_fexit_bpf2bpf(void)
 		test_func_replace_return_code();
 	if (test__start_subtest("func_map_prog_compatibility"))
 		test_func_map_prog_compatibility();
+	if (test__start_subtest("func_replace_unreliable"))
+		test_func_replace_unreliable();
 	if (test__start_subtest("func_replace_multi"))
 		test_func_replace_multi();
 	if (test__start_subtest("fmod_ret_freplace"))
diff --git a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
index 97142a4db374..d4b1901f7879 100644
--- a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
+++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
@@ -7,6 +7,7 @@
 #include <test_progs.h>
 #include "trace_helpers.h"
 #include "test_fill_link_info.skel.h"
+#include "bpf/libbpf_internal.h"
 
 #define TP_CAT "sched"
 #define TP_NAME "sched_switch"
@@ -140,14 +141,14 @@ static void test_kprobe_fill_link_info(struct test_fill_link_info *skel,
 		.retprobe = type == BPF_PERF_EVENT_KRETPROBE,
 	);
 	ssize_t entry_offset = 0;
+	struct bpf_link *link;
 	int link_fd, err;
 
-	skel->links.kprobe_run = bpf_program__attach_kprobe_opts(skel->progs.kprobe_run,
-								 KPROBE_FUNC, &opts);
-	if (!ASSERT_OK_PTR(skel->links.kprobe_run, "attach_kprobe"))
+	link = bpf_program__attach_kprobe_opts(skel->progs.kprobe_run, KPROBE_FUNC, &opts);
+	if (!ASSERT_OK_PTR(link, "attach_kprobe"))
 		return;
 
-	link_fd = bpf_link__fd(skel->links.kprobe_run);
+	link_fd = bpf_link__fd(link);
 	if (!invalid) {
 		/* See also arch_adjust_kprobe_addr(). */
 		if (skel->kconfig->CONFIG_X86_KERNEL_IBT)
@@ -157,39 +158,41 @@ static void test_kprobe_fill_link_info(struct test_fill_link_info *skel,
 	} else {
 		kprobe_fill_invalid_user_buffer(link_fd);
 	}
-	bpf_link__detach(skel->links.kprobe_run);
+	bpf_link__destroy(link);
 }
 
 static void test_tp_fill_link_info(struct test_fill_link_info *skel)
 {
+	struct bpf_link *link;
 	int link_fd, err;
 
-	skel->links.tp_run = bpf_program__attach_tracepoint(skel->progs.tp_run, TP_CAT, TP_NAME);
-	if (!ASSERT_OK_PTR(skel->links.tp_run, "attach_tp"))
+	link = bpf_program__attach_tracepoint(skel->progs.tp_run, TP_CAT, TP_NAME);
+	if (!ASSERT_OK_PTR(link, "attach_tp"))
 		return;
 
-	link_fd = bpf_link__fd(skel->links.tp_run);
+	link_fd = bpf_link__fd(link);
 	err = verify_perf_link_info(link_fd, BPF_PERF_EVENT_TRACEPOINT, 0, 0, 0);
 	ASSERT_OK(err, "verify_perf_link_info");
-	bpf_link__detach(skel->links.tp_run);
+	bpf_link__destroy(link);
 }
 
 static void test_uprobe_fill_link_info(struct test_fill_link_info *skel,
 				       enum bpf_perf_event_type type)
 {
+	struct bpf_link *link;
 	int link_fd, err;
 
-	skel->links.uprobe_run = bpf_program__attach_uprobe(skel->progs.uprobe_run,
-							    type == BPF_PERF_EVENT_URETPROBE,
-							    0, /* self pid */
-							    UPROBE_FILE, uprobe_offset);
-	if (!ASSERT_OK_PTR(skel->links.uprobe_run, "attach_uprobe"))
+	link = bpf_program__attach_uprobe(skel->progs.uprobe_run,
+					  type == BPF_PERF_EVENT_URETPROBE,
+					  0, /* self pid */
+					  UPROBE_FILE, uprobe_offset);
+	if (!ASSERT_OK_PTR(link, "attach_uprobe"))
 		return;
 
-	link_fd = bpf_link__fd(skel->links.uprobe_run);
+	link_fd = bpf_link__fd(link);
 	err = verify_perf_link_info(link_fd, type, 0, uprobe_offset, 0);
 	ASSERT_OK(err, "verify_perf_link_info");
-	bpf_link__detach(skel->links.uprobe_run);
+	bpf_link__destroy(link);
 }
 
 static int verify_kmulti_link_info(int fd, bool retprobe)
@@ -278,24 +281,214 @@ static void test_kprobe_multi_fill_link_info(struct test_fill_link_info *skel,
 					     bool retprobe, bool invalid)
 {
 	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
+	struct bpf_link *link;
 	int link_fd, err;
 
 	opts.syms = kmulti_syms;
 	opts.cnt = KMULTI_CNT;
 	opts.retprobe = retprobe;
-	skel->links.kmulti_run = bpf_program__attach_kprobe_multi_opts(skel->progs.kmulti_run,
-								       NULL, &opts);
-	if (!ASSERT_OK_PTR(skel->links.kmulti_run, "attach_kprobe_multi"))
+	link = bpf_program__attach_kprobe_multi_opts(skel->progs.kmulti_run, NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "attach_kprobe_multi"))
 		return;
 
-	link_fd = bpf_link__fd(skel->links.kmulti_run);
+	link_fd = bpf_link__fd(link);
 	if (!invalid) {
 		err = verify_kmulti_link_info(link_fd, retprobe);
 		ASSERT_OK(err, "verify_kmulti_link_info");
 	} else {
 		verify_kmulti_invalid_user_buffer(link_fd);
 	}
-	bpf_link__detach(skel->links.kmulti_run);
+	bpf_link__destroy(link);
+}
+
+#define SEC(name) __attribute__((section(name), used))
+
+static short uprobe_link_info_sema_1 SEC(".probes");
+static short uprobe_link_info_sema_2 SEC(".probes");
+static short uprobe_link_info_sema_3 SEC(".probes");
+
+noinline void uprobe_link_info_func_1(void)
+{
+	asm volatile ("");
+	uprobe_link_info_sema_1++;
+}
+
+noinline void uprobe_link_info_func_2(void)
+{
+	asm volatile ("");
+	uprobe_link_info_sema_2++;
+}
+
+noinline void uprobe_link_info_func_3(void)
+{
+	asm volatile ("");
+	uprobe_link_info_sema_3++;
+}
+
+static int
+verify_umulti_link_info(int fd, bool retprobe, __u64 *offsets,
+			__u64 *cookies, __u64 *ref_ctr_offsets)
+{
+	char path[PATH_MAX], path_buf[PATH_MAX];
+	struct bpf_link_info info;
+	__u32 len = sizeof(info);
+	__u64 ref_ctr_offsets_buf[3];
+	__u64 offsets_buf[3];
+	__u64 cookies_buf[3];
+	int i, err, bit;
+	__u32 count = 0;
+
+	memset(path, 0, sizeof(path));
+	err = readlink("/proc/self/exe", path, sizeof(path));
+	if (!ASSERT_NEQ(err, -1, "readlink"))
+		return -1;
+
+	for (bit = 0; bit < 8; bit++) {
+		memset(&info, 0, sizeof(info));
+		info.uprobe_multi.path = ptr_to_u64(path_buf);
+		info.uprobe_multi.path_size = sizeof(path_buf);
+		info.uprobe_multi.count = count;
+
+		if (bit & 0x1)
+			info.uprobe_multi.offsets = ptr_to_u64(offsets_buf);
+		if (bit & 0x2)
+			info.uprobe_multi.cookies = ptr_to_u64(cookies_buf);
+		if (bit & 0x4)
+			info.uprobe_multi.ref_ctr_offsets = ptr_to_u64(ref_ctr_offsets_buf);
+
+		err = bpf_link_get_info_by_fd(fd, &info, &len);
+		if (!ASSERT_OK(err, "bpf_link_get_info_by_fd"))
+			return -1;
+
+		if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_UPROBE_MULTI, "info.type"))
+			return -1;
+
+		ASSERT_EQ(info.uprobe_multi.pid, getpid(), "info.uprobe_multi.pid");
+		ASSERT_EQ(info.uprobe_multi.count, 3, "info.uprobe_multi.count");
+		ASSERT_EQ(info.uprobe_multi.flags & BPF_F_KPROBE_MULTI_RETURN,
+			  retprobe, "info.uprobe_multi.flags.retprobe");
+		ASSERT_EQ(info.uprobe_multi.path_size, strlen(path) + 1, "info.uprobe_multi.path_size");
+		ASSERT_STREQ(path_buf, path, "info.uprobe_multi.path");
+
+		for (i = 0; i < info.uprobe_multi.count; i++) {
+			if (info.uprobe_multi.offsets)
+				ASSERT_EQ(offsets_buf[i], offsets[i], "info.uprobe_multi.offsets");
+			if (info.uprobe_multi.cookies)
+				ASSERT_EQ(cookies_buf[i], cookies[i], "info.uprobe_multi.cookies");
+			if (info.uprobe_multi.ref_ctr_offsets) {
+				ASSERT_EQ(ref_ctr_offsets_buf[i], ref_ctr_offsets[i],
+					  "info.uprobe_multi.ref_ctr_offsets");
+			}
+		}
+		count = count ?: info.uprobe_multi.count;
+	}
+
+	return 0;
+}
+
+static void verify_umulti_invalid_user_buffer(int fd)
+{
+	struct bpf_link_info info;
+	__u32 len = sizeof(info);
+	__u64 buf[3];
+	int err;
+
+	/* upath_size defined, not path */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.path_size = 3;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EINVAL, "failed_upath_size");
+
+	/* path defined, but small */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.path = ptr_to_u64(buf);
+	info.uprobe_multi.path_size = 3;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_LT(err, 0, "failed_upath_small");
+
+	/* path has wrong pointer */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.path_size = PATH_MAX;
+	info.uprobe_multi.path = 123;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EFAULT, "failed_bad_path_ptr");
+
+	/* count zero, with offsets */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.offsets = ptr_to_u64(buf);
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EINVAL, "failed_count");
+
+	/* offsets not big enough */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.offsets = ptr_to_u64(buf);
+	info.uprobe_multi.count = 2;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -ENOSPC, "failed_small_count");
+
+	/* offsets has wrong pointer */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.offsets = 123;
+	info.uprobe_multi.count = 3;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EFAULT, "failed_wrong_offsets");
+}
+
+static void test_uprobe_multi_fill_link_info(struct test_fill_link_info *skel,
+					     bool retprobe, bool invalid)
+{
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts,
+		.retprobe = retprobe,
+	);
+	const char *syms[3] = {
+		"uprobe_link_info_func_1",
+		"uprobe_link_info_func_2",
+		"uprobe_link_info_func_3",
+	};
+	__u64 cookies[3] = {
+		0xdead,
+		0xbeef,
+		0xcafe,
+	};
+	const char *sema[3] = {
+		"uprobe_link_info_sema_1",
+		"uprobe_link_info_sema_2",
+		"uprobe_link_info_sema_3",
+	};
+	__u64 *offsets = NULL, *ref_ctr_offsets;
+	struct bpf_link *link;
+	int link_fd, err;
+
+	err = elf_resolve_syms_offsets("/proc/self/exe", 3, sema,
+				       (unsigned long **) &ref_ctr_offsets, STT_OBJECT);
+	if (!ASSERT_OK(err, "elf_resolve_syms_offsets_object"))
+		return;
+
+	err = elf_resolve_syms_offsets("/proc/self/exe", 3, syms,
+				       (unsigned long **) &offsets, STT_FUNC);
+	if (!ASSERT_OK(err, "elf_resolve_syms_offsets_func"))
+		goto out;
+
+	opts.syms = syms;
+	opts.cookies = &cookies[0];
+	opts.ref_ctr_offsets = (unsigned long *) &ref_ctr_offsets[0];
+	opts.cnt = ARRAY_SIZE(syms);
+
+	link = bpf_program__attach_uprobe_multi(skel->progs.umulti_run, 0,
+						"/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto out;
+
+	link_fd = bpf_link__fd(link);
+	if (invalid)
+		verify_umulti_invalid_user_buffer(link_fd);
+	else
+		verify_umulti_link_info(link_fd, retprobe, offsets, cookies, ref_ctr_offsets);
+
+	bpf_link__destroy(link);
+out:
+	free(ref_ctr_offsets);
+	free(offsets);
 }
 
 void test_fill_link_info(void)
@@ -337,6 +530,13 @@ void test_fill_link_info(void)
 	if (test__start_subtest("kprobe_multi_invalid_ubuff"))
 		test_kprobe_multi_fill_link_info(skel, true, true);
 
+	if (test__start_subtest("uprobe_multi_link_info"))
+		test_uprobe_multi_fill_link_info(skel, false, false);
+	if (test__start_subtest("uretprobe_multi_link_info"))
+		test_uprobe_multi_fill_link_info(skel, true, false);
+	if (test__start_subtest("uprobe_multi_invalid"))
+		test_uprobe_multi_fill_link_info(skel, false, true);
+
 cleanup:
 	test_fill_link_info__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c b/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c
new file mode 100644
index 000000000000..37056ba73847
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c
@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/xattr.h>
+#include <linux/fsverity.h>
+#include <unistd.h>
+#include <test_progs.h>
+#include "test_get_xattr.skel.h"
+#include "test_fsverity.skel.h"
+
+static const char testfile[] = "/tmp/test_progs_fs_kfuncs";
+
+static void test_xattr(void)
+{
+	struct test_get_xattr *skel = NULL;
+	int fd = -1, err;
+
+	fd = open(testfile, O_CREAT | O_RDONLY, 0644);
+	if (!ASSERT_GE(fd, 0, "create_file"))
+		return;
+
+	close(fd);
+	fd = -1;
+
+	err = setxattr(testfile, "user.kfuncs", "hello", sizeof("hello"), 0);
+	if (err && errno == EOPNOTSUPP) {
+		printf("%s:SKIP:local fs doesn't support xattr (%d)\n"
+		       "To run this test, make sure /tmp filesystem supports xattr.\n",
+		       __func__, errno);
+		test__skip();
+		goto out;
+	}
+
+	if (!ASSERT_OK(err, "setxattr"))
+		goto out;
+
+	skel = test_get_xattr__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_get_xattr__open_and_load"))
+		goto out;
+
+	skel->bss->monitored_pid = getpid();
+	err = test_get_xattr__attach(skel);
+
+	if (!ASSERT_OK(err, "test_get_xattr__attach"))
+		goto out;
+
+	fd = open(testfile, O_RDONLY, 0644);
+	if (!ASSERT_GE(fd, 0, "open_file"))
+		goto out;
+
+	ASSERT_EQ(skel->bss->found_xattr, 1, "found_xattr");
+
+out:
+	close(fd);
+	test_get_xattr__destroy(skel);
+	remove(testfile);
+}
+
+#ifndef SHA256_DIGEST_SIZE
+#define SHA256_DIGEST_SIZE      32
+#endif
+
+static void test_fsverity(void)
+{
+	struct fsverity_enable_arg arg = {0};
+	struct test_fsverity *skel = NULL;
+	struct fsverity_digest *d;
+	int fd, err;
+	char buffer[4096];
+
+	fd = open(testfile, O_CREAT | O_RDWR, 0644);
+	if (!ASSERT_GE(fd, 0, "create_file"))
+		return;
+
+	/* Write random buffer, so the file is not empty */
+	err = write(fd, buffer, 4096);
+	if (!ASSERT_EQ(err, 4096, "write_file"))
+		goto out;
+	close(fd);
+
+	/* Reopen read-only, otherwise FS_IOC_ENABLE_VERITY will fail */
+	fd = open(testfile, O_RDONLY, 0644);
+	if (!ASSERT_GE(fd, 0, "open_file1"))
+		return;
+
+	/* Enable fsverity for the file.
+	 * If the file system doesn't support verity, this will fail. Skip
+	 * the test in such case.
+	 */
+	arg.version = 1;
+	arg.hash_algorithm = FS_VERITY_HASH_ALG_SHA256;
+	arg.block_size = 4096;
+	err = ioctl(fd, FS_IOC_ENABLE_VERITY, &arg);
+	if (err) {
+		printf("%s:SKIP:local fs doesn't support fsverity (%d)\n"
+		       "To run this test, try enable CONFIG_FS_VERITY and enable FSVerity for the filesystem.\n",
+		       __func__, errno);
+		test__skip();
+		goto out;
+	}
+
+	skel = test_fsverity__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_fsverity__open_and_load"))
+		goto out;
+
+	/* Get fsverity_digest from ioctl */
+	d = (struct fsverity_digest *)skel->bss->expected_digest;
+	d->digest_algorithm = FS_VERITY_HASH_ALG_SHA256;
+	d->digest_size = SHA256_DIGEST_SIZE;
+	err = ioctl(fd, FS_IOC_MEASURE_VERITY, skel->bss->expected_digest);
+	if (!ASSERT_OK(err, "ioctl_FS_IOC_MEASURE_VERITY"))
+		goto out;
+
+	skel->bss->monitored_pid = getpid();
+	err = test_fsverity__attach(skel);
+	if (!ASSERT_OK(err, "test_fsverity__attach"))
+		goto out;
+
+	/* Reopen the file to trigger the program */
+	close(fd);
+	fd = open(testfile, O_RDONLY);
+	if (!ASSERT_GE(fd, 0, "open_file2"))
+		goto out;
+
+	ASSERT_EQ(skel->bss->got_fsverity, 1, "got_fsverity");
+	ASSERT_EQ(skel->bss->digest_matches, 1, "digest_matches");
+out:
+	close(fd);
+	test_fsverity__destroy(skel);
+	remove(testfile);
+}
+
+void test_fs_kfuncs(void)
+{
+	if (test__start_subtest("xattr"))
+		test_xattr();
+
+	if (test__start_subtest("fsverity"))
+		test_fsverity();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/global_func_dead_code.c b/tools/testing/selftests/bpf/prog_tests/global_func_dead_code.c
new file mode 100644
index 000000000000..65309894b27a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/global_func_dead_code.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <test_progs.h>
+#include "verifier_global_subprogs.skel.h"
+#include "freplace_dead_global_func.skel.h"
+
+void test_global_func_dead_code(void)
+{
+	struct verifier_global_subprogs *tgt_skel = NULL;
+	struct freplace_dead_global_func *skel = NULL;
+	char log_buf[4096];
+	int err, tgt_fd;
+
+	/* first, try to load target with good global subprog */
+	tgt_skel = verifier_global_subprogs__open();
+	if (!ASSERT_OK_PTR(tgt_skel, "tgt_skel_good_open"))
+		return;
+
+	bpf_program__set_autoload(tgt_skel->progs.chained_global_func_calls_success, true);
+
+	err = verifier_global_subprogs__load(tgt_skel);
+	if (!ASSERT_OK(err, "tgt_skel_good_load"))
+		goto out;
+
+	tgt_fd = bpf_program__fd(tgt_skel->progs.chained_global_func_calls_success);
+
+	/* Attach to good non-eliminated subprog */
+	skel = freplace_dead_global_func__open();
+	if (!ASSERT_OK_PTR(skel, "skel_good_open"))
+		goto out;
+
+	err = bpf_program__set_attach_target(skel->progs.freplace_prog, tgt_fd, "global_good");
+	ASSERT_OK(err, "attach_target_good");
+
+	err = freplace_dead_global_func__load(skel);
+	if (!ASSERT_OK(err, "skel_good_load"))
+		goto out;
+
+	freplace_dead_global_func__destroy(skel);
+
+	/* Try attaching to dead code-eliminated subprog */
+	skel = freplace_dead_global_func__open();
+	if (!ASSERT_OK_PTR(skel, "skel_dead_open"))
+		goto out;
+
+	bpf_program__set_log_buf(skel->progs.freplace_prog, log_buf, sizeof(log_buf));
+	err = bpf_program__set_attach_target(skel->progs.freplace_prog, tgt_fd, "global_dead");
+	ASSERT_OK(err, "attach_target_dead");
+
+	err = freplace_dead_global_func__load(skel);
+	if (!ASSERT_ERR(err, "skel_dead_load"))
+		goto out;
+
+	ASSERT_HAS_SUBSTR(log_buf, "Subprog global_dead doesn't exist", "dead_subprog_missing_msg");
+
+out:
+	verifier_global_subprogs__destroy(tgt_skel);
+	freplace_dead_global_func__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
index 4041cfa670eb..05000810e28e 100644
--- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
@@ -222,6 +222,7 @@ static void test_attach_api_fails(void)
 		"bpf_fentry_test2",
 	};
 	__u64 cookies[2];
+	int saved_error;
 
 	addrs[0] = ksym_get_addr("bpf_fentry_test1");
 	addrs[1] = ksym_get_addr("bpf_fentry_test2");
@@ -238,10 +239,11 @@ static void test_attach_api_fails(void)
 	/* fail_1 - pattern and opts NULL */
 	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
 						     NULL, NULL);
+	saved_error = -errno;
 	if (!ASSERT_ERR_PTR(link, "fail_1"))
 		goto cleanup;
 
-	if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_1_error"))
+	if (!ASSERT_EQ(saved_error, -EINVAL, "fail_1_error"))
 		goto cleanup;
 
 	/* fail_2 - both addrs and syms set */
@@ -252,10 +254,11 @@ static void test_attach_api_fails(void)
 
 	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
 						     NULL, &opts);
+	saved_error = -errno;
 	if (!ASSERT_ERR_PTR(link, "fail_2"))
 		goto cleanup;
 
-	if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_2_error"))
+	if (!ASSERT_EQ(saved_error, -EINVAL, "fail_2_error"))
 		goto cleanup;
 
 	/* fail_3 - pattern and addrs set */
@@ -266,10 +269,11 @@ static void test_attach_api_fails(void)
 
 	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
 						     "ksys_*", &opts);
+	saved_error = -errno;
 	if (!ASSERT_ERR_PTR(link, "fail_3"))
 		goto cleanup;
 
-	if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_3_error"))
+	if (!ASSERT_EQ(saved_error, -EINVAL, "fail_3_error"))
 		goto cleanup;
 
 	/* fail_4 - pattern and cnt set */
@@ -280,10 +284,11 @@ static void test_attach_api_fails(void)
 
 	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
 						     "ksys_*", &opts);
+	saved_error = -errno;
 	if (!ASSERT_ERR_PTR(link, "fail_4"))
 		goto cleanup;
 
-	if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_4_error"))
+	if (!ASSERT_EQ(saved_error, -EINVAL, "fail_4_error"))
 		goto cleanup;
 
 	/* fail_5 - pattern and cookies */
@@ -294,10 +299,26 @@ static void test_attach_api_fails(void)
 
 	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
 						     "ksys_*", &opts);
+	saved_error = -errno;
 	if (!ASSERT_ERR_PTR(link, "fail_5"))
 		goto cleanup;
 
-	if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_5_error"))
+	if (!ASSERT_EQ(saved_error, -EINVAL, "fail_5_error"))
+		goto cleanup;
+
+	/* fail_6 - abnormal cnt */
+	opts.addrs = (const unsigned long *) addrs;
+	opts.syms = NULL;
+	opts.cnt = INT_MAX;
+	opts.cookies = NULL;
+
+	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
+						     NULL, &opts);
+	saved_error = -errno;
+	if (!ASSERT_ERR_PTR(link, "fail_6"))
+		goto cleanup;
+
+	if (!ASSERT_EQ(saved_error, -E2BIG, "fail_6_error"))
 		goto cleanup;
 
 cleanup:
diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
index c440ea3311ed..eb34d612d6f8 100644
--- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
+++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
@@ -87,7 +87,7 @@ static void test_libbpf_bpf_link_type_str(void)
 		const char *link_type_str;
 		char buf[256];
 
-		if (link_type == MAX_BPF_LINK_TYPE)
+		if (link_type == __MAX_BPF_LINK_TYPE)
 			continue;
 
 		link_type_name = btf__str_by_offset(btf, e->name_off);
diff --git a/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c b/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c
index b25b870f87ba..827e713f6cf1 100644
--- a/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c
+++ b/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c
@@ -48,6 +48,27 @@ static void test_local_kptr_stash_plain(void)
 	local_kptr_stash__destroy(skel);
 }
 
+static void test_local_kptr_stash_local_with_root(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+	struct local_kptr_stash *skel;
+	int ret;
+
+	skel = local_kptr_stash__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "local_kptr_stash__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.stash_local_with_root), &opts);
+	ASSERT_OK(ret, "local_kptr_stash_add_local_with_root run");
+	ASSERT_OK(opts.retval, "local_kptr_stash_add_local_with_root retval");
+
+	local_kptr_stash__destroy(skel);
+}
+
 static void test_local_kptr_stash_unstash(void)
 {
 	LIBBPF_OPTS(bpf_test_run_opts, opts,
@@ -73,6 +94,37 @@ static void test_local_kptr_stash_unstash(void)
 	local_kptr_stash__destroy(skel);
 }
 
+static void test_refcount_acquire_without_unstash(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+	struct local_kptr_stash *skel;
+	int ret;
+
+	skel = local_kptr_stash__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "local_kptr_stash__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.refcount_acquire_without_unstash),
+				     &opts);
+	ASSERT_OK(ret, "refcount_acquire_without_unstash run");
+	ASSERT_EQ(opts.retval, 2, "refcount_acquire_without_unstash retval");
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.stash_refcounted_node), &opts);
+	ASSERT_OK(ret, "stash_refcounted_node run");
+	ASSERT_OK(opts.retval, "stash_refcounted_node retval");
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.refcount_acquire_without_unstash),
+				     &opts);
+	ASSERT_OK(ret, "refcount_acquire_without_unstash (2) run");
+	ASSERT_EQ(opts.retval, 42, "refcount_acquire_without_unstash (2) retval");
+
+	local_kptr_stash__destroy(skel);
+}
+
 static void test_local_kptr_stash_fail(void)
 {
 	RUN_TESTS(local_kptr_stash_fail);
@@ -84,8 +136,12 @@ void test_local_kptr_stash(void)
 		test_local_kptr_stash_simple();
 	if (test__start_subtest("local_kptr_stash_plain"))
 		test_local_kptr_stash_plain();
+	if (test__start_subtest("local_kptr_stash_local_with_root"))
+		test_local_kptr_stash_local_with_root();
 	if (test__start_subtest("local_kptr_stash_unstash"))
 		test_local_kptr_stash_unstash();
+	if (test__start_subtest("refcount_acquire_without_unstash"))
+		test_refcount_acquire_without_unstash();
 	if (test__start_subtest("local_kptr_stash_fail"))
 		test_local_kptr_stash_fail();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/log_buf.c b/tools/testing/selftests/bpf/prog_tests/log_buf.c
index fe9a23e65ef4..0f7ea4d7d9f6 100644
--- a/tools/testing/selftests/bpf/prog_tests/log_buf.c
+++ b/tools/testing/selftests/bpf/prog_tests/log_buf.c
@@ -78,7 +78,7 @@ static void obj_load_log_buf(void)
 	ASSERT_OK_PTR(strstr(libbpf_log_buf, "prog 'bad_prog': BPF program load failed"),
 		      "libbpf_log_not_empty");
 	ASSERT_OK_PTR(strstr(obj_log_buf, "DATASEC license"), "obj_log_not_empty");
-	ASSERT_OK_PTR(strstr(good_log_buf, "0: R1=ctx(off=0,imm=0) R10=fp0"),
+	ASSERT_OK_PTR(strstr(good_log_buf, "0: R1=ctx() R10=fp0"),
 		      "good_log_verbose");
 	ASSERT_OK_PTR(strstr(bad_log_buf, "invalid access to map value, value_size=16 off=16000 size=4"),
 		      "bad_log_not_empty");
@@ -175,7 +175,7 @@ static void bpf_prog_load_log_buf(void)
 	opts.log_level = 2;
 	fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "good_prog", "GPL",
 			   good_prog_insns, good_prog_insn_cnt, &opts);
-	ASSERT_OK_PTR(strstr(log_buf, "0: R1=ctx(off=0,imm=0) R10=fp0"), "good_log_2");
+	ASSERT_OK_PTR(strstr(log_buf, "0: R1=ctx() R10=fp0"), "good_log_2");
 	ASSERT_GE(fd, 0, "good_fd2");
 	if (fd >= 0)
 		close(fd);
diff --git a/tools/testing/selftests/bpf/prog_tests/log_fixup.c b/tools/testing/selftests/bpf/prog_tests/log_fixup.c
index effd78b2a657..7a3fa2ff567b 100644
--- a/tools/testing/selftests/bpf/prog_tests/log_fixup.c
+++ b/tools/testing/selftests/bpf/prog_tests/log_fixup.c
@@ -169,9 +169,9 @@ void test_log_fixup(void)
 	if (test__start_subtest("bad_core_relo_trunc_none"))
 		bad_core_relo(0, TRUNC_NONE /* full buf */);
 	if (test__start_subtest("bad_core_relo_trunc_partial"))
-		bad_core_relo(300, TRUNC_PARTIAL /* truncate original log a bit */);
+		bad_core_relo(280, TRUNC_PARTIAL /* truncate original log a bit */);
 	if (test__start_subtest("bad_core_relo_trunc_full"))
-		bad_core_relo(210, TRUNC_FULL  /* truncate also libbpf's message patch */);
+		bad_core_relo(220, TRUNC_FULL  /* truncate also libbpf's message patch */);
 	if (test__start_subtest("bad_core_relo_subprog"))
 		bad_core_relo_subprog();
 	if (test__start_subtest("missing_map"))
diff --git a/tools/testing/selftests/bpf/prog_tests/map_btf.c b/tools/testing/selftests/bpf/prog_tests/map_btf.c
new file mode 100644
index 000000000000..2c4ef6037573
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/map_btf.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <test_progs.h>
+
+#include "normal_map_btf.skel.h"
+#include "map_in_map_btf.skel.h"
+
+static void do_test_normal_map_btf(void)
+{
+	struct normal_map_btf *skel;
+	int i, err, new_fd = -1;
+	int map_fd_arr[64];
+
+	skel = normal_map_btf__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_load"))
+		return;
+
+	err = normal_map_btf__attach(skel);
+	if (!ASSERT_OK(err, "attach"))
+		goto out;
+
+	skel->bss->pid = getpid();
+	usleep(1);
+	ASSERT_TRUE(skel->bss->done, "done");
+
+	/* Use percpu_array to slow bpf_map_free_deferred() down.
+	 * The memory allocation may fail, so doesn't check the returned fd.
+	 */
+	for (i = 0; i < ARRAY_SIZE(map_fd_arr); i++)
+		map_fd_arr[i] = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, NULL, 4, 4, 256, NULL);
+
+	/* Close array fd later */
+	new_fd = dup(bpf_map__fd(skel->maps.array));
+out:
+	normal_map_btf__destroy(skel);
+	if (new_fd < 0)
+		return;
+	/* Use kern_sync_rcu() to wait for the start of the free of the bpf
+	 * program and use an assumed delay to wait for the release of the map
+	 * btf which is held by other maps (e.g, bss). After that, array map
+	 * holds the last reference of map btf.
+	 */
+	kern_sync_rcu();
+	usleep(4000);
+	/* Spawn multiple kworkers to delay the invocation of
+	 * bpf_map_free_deferred() for array map.
+	 */
+	for (i = 0; i < ARRAY_SIZE(map_fd_arr); i++) {
+		if (map_fd_arr[i] < 0)
+			continue;
+		close(map_fd_arr[i]);
+	}
+	close(new_fd);
+}
+
+static void do_test_map_in_map_btf(void)
+{
+	int err, zero = 0, new_fd = -1;
+	struct map_in_map_btf *skel;
+
+	skel = map_in_map_btf__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_load"))
+		return;
+
+	err = map_in_map_btf__attach(skel);
+	if (!ASSERT_OK(err, "attach"))
+		goto out;
+
+	skel->bss->pid = getpid();
+	usleep(1);
+	ASSERT_TRUE(skel->bss->done, "done");
+
+	/* Close inner_array fd later */
+	new_fd = dup(bpf_map__fd(skel->maps.inner_array));
+	/* Defer the free of inner_array */
+	err = bpf_map__delete_elem(skel->maps.outer_array, &zero, sizeof(zero), 0);
+	ASSERT_OK(err, "delete inner map");
+out:
+	map_in_map_btf__destroy(skel);
+	if (new_fd < 0)
+		return;
+	/* Use kern_sync_rcu() to wait for the start of the free of the bpf
+	 * program and use an assumed delay to wait for the free of the outer
+	 * map and the release of map btf. After that, inner map holds the last
+	 * reference of map btf.
+	 */
+	kern_sync_rcu();
+	usleep(10000);
+	close(new_fd);
+}
+
+void test_map_btf(void)
+{
+	if (test__start_subtest("array_btf"))
+		do_test_normal_map_btf();
+	if (test__start_subtest("inner_array_btf"))
+		do_test_map_in_map_btf();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/map_in_map.c b/tools/testing/selftests/bpf/prog_tests/map_in_map.c
new file mode 100644
index 000000000000..d2a10eb4e5b5
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/map_in_map.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#define _GNU_SOURCE
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <test_progs.h>
+#include <bpf/btf.h>
+#include "access_map_in_map.skel.h"
+
+struct thread_ctx {
+	pthread_barrier_t barrier;
+	int outer_map_fd;
+	int start, abort;
+	int loop, err;
+};
+
+static int wait_for_start_or_abort(struct thread_ctx *ctx)
+{
+	while (!ctx->start && !ctx->abort)
+		usleep(1);
+	return ctx->abort ? -1 : 0;
+}
+
+static void *update_map_fn(void *data)
+{
+	struct thread_ctx *ctx = data;
+	int loop = ctx->loop, err = 0;
+
+	if (wait_for_start_or_abort(ctx) < 0)
+		return NULL;
+	pthread_barrier_wait(&ctx->barrier);
+
+	while (loop-- > 0) {
+		int fd, zero = 0;
+
+		fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 4, 1, NULL);
+		if (fd < 0) {
+			err |= 1;
+			pthread_barrier_wait(&ctx->barrier);
+			continue;
+		}
+
+		/* Remove the old inner map */
+		if (bpf_map_update_elem(ctx->outer_map_fd, &zero, &fd, 0) < 0)
+			err |= 2;
+		close(fd);
+		pthread_barrier_wait(&ctx->barrier);
+	}
+
+	ctx->err = err;
+
+	return NULL;
+}
+
+static void *access_map_fn(void *data)
+{
+	struct thread_ctx *ctx = data;
+	int loop = ctx->loop;
+
+	if (wait_for_start_or_abort(ctx) < 0)
+		return NULL;
+	pthread_barrier_wait(&ctx->barrier);
+
+	while (loop-- > 0) {
+		/* Access the old inner map */
+		syscall(SYS_getpgid);
+		pthread_barrier_wait(&ctx->barrier);
+	}
+
+	return NULL;
+}
+
+static void test_map_in_map_access(const char *prog_name, const char *map_name)
+{
+	struct access_map_in_map *skel;
+	struct bpf_map *outer_map;
+	struct bpf_program *prog;
+	struct thread_ctx ctx;
+	pthread_t tid[2];
+	int err;
+
+	skel = access_map_in_map__open();
+	if (!ASSERT_OK_PTR(skel, "access_map_in_map open"))
+		return;
+
+	prog = bpf_object__find_program_by_name(skel->obj, prog_name);
+	if (!ASSERT_OK_PTR(prog, "find program"))
+		goto out;
+	bpf_program__set_autoload(prog, true);
+
+	outer_map = bpf_object__find_map_by_name(skel->obj, map_name);
+	if (!ASSERT_OK_PTR(outer_map, "find map"))
+		goto out;
+
+	err = access_map_in_map__load(skel);
+	if (!ASSERT_OK(err, "access_map_in_map load"))
+		goto out;
+
+	err = access_map_in_map__attach(skel);
+	if (!ASSERT_OK(err, "access_map_in_map attach"))
+		goto out;
+
+	skel->bss->tgid = getpid();
+
+	memset(&ctx, 0, sizeof(ctx));
+	pthread_barrier_init(&ctx.barrier, NULL, 2);
+	ctx.outer_map_fd = bpf_map__fd(outer_map);
+	ctx.loop = 4;
+
+	err = pthread_create(&tid[0], NULL, update_map_fn, &ctx);
+	if (!ASSERT_OK(err, "close_thread"))
+		goto out;
+
+	err = pthread_create(&tid[1], NULL, access_map_fn, &ctx);
+	if (!ASSERT_OK(err, "read_thread")) {
+		ctx.abort = 1;
+		pthread_join(tid[0], NULL);
+		goto out;
+	}
+
+	ctx.start = 1;
+	pthread_join(tid[0], NULL);
+	pthread_join(tid[1], NULL);
+
+	ASSERT_OK(ctx.err, "err");
+out:
+	access_map_in_map__destroy(skel);
+}
+
+void test_map_in_map(void)
+{
+	if (test__start_subtest("acc_map_in_array"))
+		test_map_in_map_access("access_map_in_array", "outer_array_map");
+	if (test__start_subtest("sleepable_acc_map_in_array"))
+		test_map_in_map_access("sleepable_access_map_in_array", "outer_array_map");
+	if (test__start_subtest("acc_map_in_htab"))
+		test_map_in_map_access("access_map_in_htab", "outer_htab_map");
+	if (test__start_subtest("sleepable_acc_map_in_htab"))
+		test_map_in_map_access("sleepable_access_map_in_htab", "outer_htab_map");
+}
+
diff --git a/tools/testing/selftests/bpf/prog_tests/recursive_attach.c b/tools/testing/selftests/bpf/prog_tests/recursive_attach.c
new file mode 100644
index 000000000000..8100509e561b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/recursive_attach.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Red Hat, Inc. */
+#include <test_progs.h>
+#include "fentry_recursive.skel.h"
+#include "fentry_recursive_target.skel.h"
+#include <bpf/btf.h>
+#include "bpf/libbpf_internal.h"
+
+/* Test recursive attachment of tracing progs with more than one nesting level
+ * is not possible. Create a chain of attachment, verify that the last prog
+ * will fail. Depending on the arguments, following cases are tested:
+ *
+ * - Recursive loading of tracing progs, without attaching (attach = false,
+ *   detach = false). The chain looks like this:
+ *       load target
+ *       load fentry1 -> target
+ *       load fentry2 -> fentry1 (fail)
+ *
+ * - Recursive attach of tracing progs (attach = true, detach = false). The
+ *   chain looks like this:
+ *       load target
+ *       load fentry1 -> target
+ *       attach fentry1 -> target
+ *       load fentry2 -> fentry1 (fail)
+ *
+ * - Recursive attach and detach of tracing progs (attach = true, detach =
+ *   true). This validates that attach_tracing_prog flag will be set throughout
+ *   the whole lifecycle of an fentry prog, independently from whether it's
+ *   detached. The chain looks like this:
+ *       load target
+ *       load fentry1 -> target
+ *       attach fentry1 -> target
+ *       detach fentry1
+ *       load fentry2 -> fentry1 (fail)
+ */
+static void test_recursive_fentry_chain(bool attach, bool detach)
+{
+	struct fentry_recursive_target *target_skel = NULL;
+	struct fentry_recursive *tracing_chain[2] = {};
+	struct bpf_program *prog;
+	int prev_fd, err;
+
+	target_skel = fentry_recursive_target__open_and_load();
+	if (!ASSERT_OK_PTR(target_skel, "fentry_recursive_target__open_and_load"))
+		return;
+
+	/* Create an attachment chain with two fentry progs */
+	for (int i = 0; i < 2; i++) {
+		tracing_chain[i] = fentry_recursive__open();
+		if (!ASSERT_OK_PTR(tracing_chain[i], "fentry_recursive__open"))
+			goto close_prog;
+
+		/* The first prog in the chain is going to be attached to the target
+		 * fentry program, the second one to the previous in the chain.
+		 */
+		prog = tracing_chain[i]->progs.recursive_attach;
+		if (i == 0) {
+			prev_fd = bpf_program__fd(target_skel->progs.test1);
+			err = bpf_program__set_attach_target(prog, prev_fd, "test1");
+		} else {
+			prev_fd = bpf_program__fd(tracing_chain[i-1]->progs.recursive_attach);
+			err = bpf_program__set_attach_target(prog, prev_fd, "recursive_attach");
+		}
+
+		if (!ASSERT_OK(err, "bpf_program__set_attach_target"))
+			goto close_prog;
+
+		err = fentry_recursive__load(tracing_chain[i]);
+		/* The first attach should succeed, the second fail */
+		if (i == 0) {
+			if (!ASSERT_OK(err, "fentry_recursive__load"))
+				goto close_prog;
+
+			if (attach) {
+				err = fentry_recursive__attach(tracing_chain[i]);
+				if (!ASSERT_OK(err, "fentry_recursive__attach"))
+					goto close_prog;
+			}
+
+			if (detach) {
+				/* Flag attach_tracing_prog should still be set, preventing
+				 * attachment of the following prog.
+				 */
+				fentry_recursive__detach(tracing_chain[i]);
+			}
+		} else {
+			if (!ASSERT_ERR(err, "fentry_recursive__load"))
+				goto close_prog;
+		}
+	}
+
+close_prog:
+	fentry_recursive_target__destroy(target_skel);
+	for (int i = 0; i < 2; i++) {
+		fentry_recursive__destroy(tracing_chain[i]);
+	}
+}
+
+void test_recursive_fentry(void)
+{
+	if (test__start_subtest("attach"))
+		test_recursive_fentry_chain(true, false);
+	if (test__start_subtest("load"))
+		test_recursive_fentry_chain(false, false);
+	if (test__start_subtest("detach"))
+		test_recursive_fentry_chain(true, true);
+}
+
+/* Test that a tracing prog reattachment (when we land in
+ * "prog->aux->dst_trampoline and tgt_prog is NULL" branch in
+ * bpf_tracing_prog_attach) does not lead to a crash due to missing attach_btf
+ */
+void test_fentry_attach_btf_presence(void)
+{
+	struct fentry_recursive_target *target_skel = NULL;
+	struct fentry_recursive *tracing_skel = NULL;
+	struct bpf_program *prog;
+	int err, link_fd, tgt_prog_fd;
+
+	target_skel = fentry_recursive_target__open_and_load();
+	if (!ASSERT_OK_PTR(target_skel, "fentry_recursive_target__open_and_load"))
+		goto close_prog;
+
+	tracing_skel = fentry_recursive__open();
+	if (!ASSERT_OK_PTR(tracing_skel, "fentry_recursive__open"))
+		goto close_prog;
+
+	prog = tracing_skel->progs.recursive_attach;
+	tgt_prog_fd = bpf_program__fd(target_skel->progs.fentry_target);
+	err = bpf_program__set_attach_target(prog, tgt_prog_fd, "fentry_target");
+	if (!ASSERT_OK(err, "bpf_program__set_attach_target"))
+		goto close_prog;
+
+	err = fentry_recursive__load(tracing_skel);
+	if (!ASSERT_OK(err, "fentry_recursive__load"))
+		goto close_prog;
+
+	tgt_prog_fd = bpf_program__fd(tracing_skel->progs.recursive_attach);
+	link_fd = bpf_link_create(tgt_prog_fd, 0, BPF_TRACE_FENTRY, NULL);
+	if (!ASSERT_GE(link_fd, 0, "link_fd"))
+		goto close_prog;
+
+	fentry_recursive__detach(tracing_skel);
+
+	err = fentry_recursive__attach(tracing_skel);
+	ASSERT_ERR(err, "fentry_recursive__attach");
+
+close_prog:
+	fentry_recursive_target__destroy(target_skel);
+	fentry_recursive__destroy(tracing_skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
new file mode 100644
index 000000000000..820d0bcfc474
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
@@ -0,0 +1,2131 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#define _GNU_SOURCE
+#include <limits.h>
+#include <test_progs.h>
+#include <linux/filter.h>
+#include <linux/bpf.h>
+
+/* =================================
+ * SHORT AND CONSISTENT NUMBER TYPES
+ * =================================
+ */
+#define U64_MAX ((u64)UINT64_MAX)
+#define U32_MAX ((u32)UINT_MAX)
+#define U16_MAX ((u32)UINT_MAX)
+#define S64_MIN ((s64)INT64_MIN)
+#define S64_MAX ((s64)INT64_MAX)
+#define S32_MIN ((s32)INT_MIN)
+#define S32_MAX ((s32)INT_MAX)
+#define S16_MIN ((s16)0x80000000)
+#define S16_MAX ((s16)0x7fffffff)
+
+typedef unsigned long long ___u64;
+typedef unsigned int ___u32;
+typedef long long ___s64;
+typedef int ___s32;
+
+/* avoid conflicts with already defined types in kernel headers */
+#define u64 ___u64
+#define u32 ___u32
+#define s64 ___s64
+#define s32 ___s32
+
+/* ==================================
+ * STRING BUF ABSTRACTION AND HELPERS
+ * ==================================
+ */
+struct strbuf {
+	size_t buf_sz;
+	int pos;
+	char buf[0];
+};
+
+#define DEFINE_STRBUF(name, N)						\
+	struct { struct strbuf buf; char data[(N)]; } ___##name;	\
+	struct strbuf *name = (___##name.buf.buf_sz = (N), ___##name.buf.pos = 0, &___##name.buf)
+
+__printf(2, 3)
+static inline void snappendf(struct strbuf *s, const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	s->pos += vsnprintf(s->buf + s->pos,
+			    s->pos < s->buf_sz ? s->buf_sz - s->pos : 0,
+			    fmt, args);
+	va_end(args);
+}
+
+/* ==================================
+ * GENERIC NUMBER TYPE AND OPERATIONS
+ * ==================================
+ */
+enum num_t { U64, first_t = U64, U32, S64, S32, last_t = S32 };
+
+static __always_inline u64 min_t(enum num_t t, u64 x, u64 y)
+{
+	switch (t) {
+	case U64: return (u64)x < (u64)y ? (u64)x : (u64)y;
+	case U32: return (u32)x < (u32)y ? (u32)x : (u32)y;
+	case S64: return (s64)x < (s64)y ? (s64)x : (s64)y;
+	case S32: return (s32)x < (s32)y ? (s32)x : (s32)y;
+	default: printf("min_t!\n"); exit(1);
+	}
+}
+
+static __always_inline u64 max_t(enum num_t t, u64 x, u64 y)
+{
+	switch (t) {
+	case U64: return (u64)x > (u64)y ? (u64)x : (u64)y;
+	case U32: return (u32)x > (u32)y ? (u32)x : (u32)y;
+	case S64: return (s64)x > (s64)y ? (s64)x : (s64)y;
+	case S32: return (s32)x > (s32)y ? (u32)(s32)x : (u32)(s32)y;
+	default: printf("max_t!\n"); exit(1);
+	}
+}
+
+static __always_inline u64 cast_t(enum num_t t, u64 x)
+{
+	switch (t) {
+	case U64: return (u64)x;
+	case U32: return (u32)x;
+	case S64: return (s64)x;
+	case S32: return (u32)(s32)x;
+	default: printf("cast_t!\n"); exit(1);
+	}
+}
+
+static const char *t_str(enum num_t t)
+{
+	switch (t) {
+	case U64: return "u64";
+	case U32: return "u32";
+	case S64: return "s64";
+	case S32: return "s32";
+	default: printf("t_str!\n"); exit(1);
+	}
+}
+
+static enum num_t t_is_32(enum num_t t)
+{
+	switch (t) {
+	case U64: return false;
+	case U32: return true;
+	case S64: return false;
+	case S32: return true;
+	default: printf("t_is_32!\n"); exit(1);
+	}
+}
+
+static enum num_t t_signed(enum num_t t)
+{
+	switch (t) {
+	case U64: return S64;
+	case U32: return S32;
+	case S64: return S64;
+	case S32: return S32;
+	default: printf("t_signed!\n"); exit(1);
+	}
+}
+
+static enum num_t t_unsigned(enum num_t t)
+{
+	switch (t) {
+	case U64: return U64;
+	case U32: return U32;
+	case S64: return U64;
+	case S32: return U32;
+	default: printf("t_unsigned!\n"); exit(1);
+	}
+}
+
+#define UNUM_MAX_DECIMAL U16_MAX
+#define SNUM_MAX_DECIMAL S16_MAX
+#define SNUM_MIN_DECIMAL S16_MIN
+
+static bool num_is_small(enum num_t t, u64 x)
+{
+	switch (t) {
+	case U64: return (u64)x <= UNUM_MAX_DECIMAL;
+	case U32: return (u32)x <= UNUM_MAX_DECIMAL;
+	case S64: return (s64)x >= SNUM_MIN_DECIMAL && (s64)x <= SNUM_MAX_DECIMAL;
+	case S32: return (s32)x >= SNUM_MIN_DECIMAL && (s32)x <= SNUM_MAX_DECIMAL;
+	default: printf("num_is_small!\n"); exit(1);
+	}
+}
+
+static void snprintf_num(enum num_t t, struct strbuf *sb, u64 x)
+{
+	bool is_small = num_is_small(t, x);
+
+	if (is_small) {
+		switch (t) {
+		case U64: return snappendf(sb, "%llu", (u64)x);
+		case U32: return snappendf(sb, "%u", (u32)x);
+		case S64: return snappendf(sb, "%lld", (s64)x);
+		case S32: return snappendf(sb, "%d", (s32)x);
+		default: printf("snprintf_num!\n"); exit(1);
+		}
+	} else {
+		switch (t) {
+		case U64:
+			if (x == U64_MAX)
+				return snappendf(sb, "U64_MAX");
+			else if (x >= U64_MAX - 256)
+				return snappendf(sb, "U64_MAX-%llu", U64_MAX - x);
+			else
+				return snappendf(sb, "%#llx", (u64)x);
+		case U32:
+			if ((u32)x == U32_MAX)
+				return snappendf(sb, "U32_MAX");
+			else if ((u32)x >= U32_MAX - 256)
+				return snappendf(sb, "U32_MAX-%u", U32_MAX - (u32)x);
+			else
+				return snappendf(sb, "%#x", (u32)x);
+		case S64:
+			if ((s64)x == S64_MAX)
+				return snappendf(sb, "S64_MAX");
+			else if ((s64)x >= S64_MAX - 256)
+				return snappendf(sb, "S64_MAX-%lld", S64_MAX - (s64)x);
+			else if ((s64)x == S64_MIN)
+				return snappendf(sb, "S64_MIN");
+			else if ((s64)x <= S64_MIN + 256)
+				return snappendf(sb, "S64_MIN+%lld", (s64)x - S64_MIN);
+			else
+				return snappendf(sb, "%#llx", (s64)x);
+		case S32:
+			if ((s32)x == S32_MAX)
+				return snappendf(sb, "S32_MAX");
+			else if ((s32)x >= S32_MAX - 256)
+				return snappendf(sb, "S32_MAX-%d", S32_MAX - (s32)x);
+			else if ((s32)x == S32_MIN)
+				return snappendf(sb, "S32_MIN");
+			else if ((s32)x <= S32_MIN + 256)
+				return snappendf(sb, "S32_MIN+%d", (s32)x - S32_MIN);
+			else
+				return snappendf(sb, "%#x", (s32)x);
+		default: printf("snprintf_num!\n"); exit(1);
+		}
+	}
+}
+
+/* ===================================
+ * GENERIC RANGE STRUCT AND OPERATIONS
+ * ===================================
+ */
+struct range {
+	u64 a, b;
+};
+
+static void snprintf_range(enum num_t t, struct strbuf *sb, struct range x)
+{
+	if (x.a == x.b)
+		return snprintf_num(t, sb, x.a);
+
+	snappendf(sb, "[");
+	snprintf_num(t, sb, x.a);
+	snappendf(sb, "; ");
+	snprintf_num(t, sb, x.b);
+	snappendf(sb, "]");
+}
+
+static void print_range(enum num_t t, struct range x, const char *sfx)
+{
+	DEFINE_STRBUF(sb, 128);
+
+	snprintf_range(t, sb, x);
+	printf("%s%s", sb->buf, sfx);
+}
+
+static const struct range unkn[] = {
+	[U64] = { 0, U64_MAX },
+	[U32] = { 0, U32_MAX },
+	[S64] = { (u64)S64_MIN, (u64)S64_MAX },
+	[S32] = { (u64)(u32)S32_MIN, (u64)(u32)S32_MAX },
+};
+
+static struct range unkn_subreg(enum num_t t)
+{
+	switch (t) {
+	case U64: return unkn[U32];
+	case U32: return unkn[U32];
+	case S64: return unkn[U32];
+	case S32: return unkn[S32];
+	default: printf("unkn_subreg!\n"); exit(1);
+	}
+}
+
+static struct range range(enum num_t t, u64 a, u64 b)
+{
+	switch (t) {
+	case U64: return (struct range){ (u64)a, (u64)b };
+	case U32: return (struct range){ (u32)a, (u32)b };
+	case S64: return (struct range){ (s64)a, (s64)b };
+	case S32: return (struct range){ (u32)(s32)a, (u32)(s32)b };
+	default: printf("range!\n"); exit(1);
+	}
+}
+
+static __always_inline u32 sign64(u64 x) { return (x >> 63) & 1; }
+static __always_inline u32 sign32(u64 x) { return ((u32)x >> 31) & 1; }
+static __always_inline u32 upper32(u64 x) { return (u32)(x >> 32); }
+static __always_inline u64 swap_low32(u64 x, u32 y) { return (x & 0xffffffff00000000ULL) | y; }
+
+static bool range_eq(struct range x, struct range y)
+{
+	return x.a == y.a && x.b == y.b;
+}
+
+static struct range range_cast_to_s32(struct range x)
+{
+	u64 a = x.a, b = x.b;
+
+	/* if upper 32 bits are constant, lower 32 bits should form a proper
+	 * s32 range to be correct
+	 */
+	if (upper32(a) == upper32(b) && (s32)a <= (s32)b)
+		return range(S32, a, b);
+
+	/* Special case where upper bits form a small sequence of two
+	 * sequential numbers (in 32-bit unsigned space, so 0xffffffff to
+	 * 0x00000000 is also valid), while lower bits form a proper s32 range
+	 * going from negative numbers to positive numbers.
+	 *
+	 * E.g.: [0xfffffff0ffffff00; 0xfffffff100000010]. Iterating
+	 * over full 64-bit numbers range will form a proper [-16, 16]
+	 * ([0xffffff00; 0x00000010]) range in its lower 32 bits.
+	 */
+	if (upper32(a) + 1 == upper32(b) && (s32)a < 0 && (s32)b >= 0)
+		return range(S32, a, b);
+
+	/* otherwise we can't derive much meaningful information */
+	return unkn[S32];
+}
+
+static struct range range_cast_u64(enum num_t to_t, struct range x)
+{
+	u64 a = (u64)x.a, b = (u64)x.b;
+
+	switch (to_t) {
+	case U64:
+		return x;
+	case U32:
+		if (upper32(a) != upper32(b))
+			return unkn[U32];
+		return range(U32, a, b);
+	case S64:
+		if (sign64(a) != sign64(b))
+			return unkn[S64];
+		return range(S64, a, b);
+	case S32:
+		return range_cast_to_s32(x);
+	default: printf("range_cast_u64!\n"); exit(1);
+	}
+}
+
+static struct range range_cast_s64(enum num_t to_t, struct range x)
+{
+	s64 a = (s64)x.a, b = (s64)x.b;
+
+	switch (to_t) {
+	case U64:
+		/* equivalent to (s64)a <= (s64)b check */
+		if (sign64(a) != sign64(b))
+			return unkn[U64];
+		return range(U64, a, b);
+	case U32:
+		if (upper32(a) != upper32(b) || sign32(a) != sign32(b))
+			return unkn[U32];
+		return range(U32, a, b);
+	case S64:
+		return x;
+	case S32:
+		return range_cast_to_s32(x);
+	default: printf("range_cast_s64!\n"); exit(1);
+	}
+}
+
+static struct range range_cast_u32(enum num_t to_t, struct range x)
+{
+	u32 a = (u32)x.a, b = (u32)x.b;
+
+	switch (to_t) {
+	case U64:
+	case S64:
+		/* u32 is always a valid zero-extended u64/s64 */
+		return range(to_t, a, b);
+	case U32:
+		return x;
+	case S32:
+		return range_cast_to_s32(range(U32, a, b));
+	default: printf("range_cast_u32!\n"); exit(1);
+	}
+}
+
+static struct range range_cast_s32(enum num_t to_t, struct range x)
+{
+	s32 a = (s32)x.a, b = (s32)x.b;
+
+	switch (to_t) {
+	case U64:
+	case U32:
+	case S64:
+		if (sign32(a) != sign32(b))
+			return unkn[to_t];
+		return range(to_t, a, b);
+	case S32:
+		return x;
+	default: printf("range_cast_s32!\n"); exit(1);
+	}
+}
+
+/* Reinterpret range in *from_t* domain as a range in *to_t* domain preserving
+ * all possible information. Worst case, it will be unknown range within
+ * *to_t* domain, if nothing more specific can be guaranteed during the
+ * conversion
+ */
+static struct range range_cast(enum num_t from_t, enum num_t to_t, struct range from)
+{
+	switch (from_t) {
+	case U64: return range_cast_u64(to_t, from);
+	case U32: return range_cast_u32(to_t, from);
+	case S64: return range_cast_s64(to_t, from);
+	case S32: return range_cast_s32(to_t, from);
+	default: printf("range_cast!\n"); exit(1);
+	}
+}
+
+static bool is_valid_num(enum num_t t, u64 x)
+{
+	switch (t) {
+	case U64: return true;
+	case U32: return upper32(x) == 0;
+	case S64: return true;
+	case S32: return upper32(x) == 0;
+	default: printf("is_valid_num!\n"); exit(1);
+	}
+}
+
+static bool is_valid_range(enum num_t t, struct range x)
+{
+	if (!is_valid_num(t, x.a) || !is_valid_num(t, x.b))
+		return false;
+
+	switch (t) {
+	case U64: return (u64)x.a <= (u64)x.b;
+	case U32: return (u32)x.a <= (u32)x.b;
+	case S64: return (s64)x.a <= (s64)x.b;
+	case S32: return (s32)x.a <= (s32)x.b;
+	default: printf("is_valid_range!\n"); exit(1);
+	}
+}
+
+static struct range range_improve(enum num_t t, struct range old, struct range new)
+{
+	return range(t, max_t(t, old.a, new.a), min_t(t, old.b, new.b));
+}
+
+static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t, struct range y)
+{
+	struct range y_cast;
+
+	y_cast = range_cast(y_t, x_t, y);
+
+	/* the case when new range knowledge, *y*, is a 32-bit subregister
+	 * range, while previous range knowledge, *x*, is a full register
+	 * 64-bit range, needs special treatment to take into account upper 32
+	 * bits of full register range
+	 */
+	if (t_is_32(y_t) && !t_is_32(x_t)) {
+		struct range x_swap;
+
+		/* some combinations of upper 32 bits and sign bit can lead to
+		 * invalid ranges, in such cases it's easier to detect them
+		 * after cast/swap than try to enumerate all the conditions
+		 * under which transformation and knowledge transfer is valid
+		 */
+		x_swap = range(x_t, swap_low32(x.a, y_cast.a), swap_low32(x.b, y_cast.b));
+		if (!is_valid_range(x_t, x_swap))
+			return x;
+		return range_improve(x_t, x, x_swap);
+	}
+
+	/* otherwise, plain range cast and intersection works */
+	return range_improve(x_t, x, y_cast);
+}
+
+/* =======================
+ * GENERIC CONDITIONAL OPS
+ * =======================
+ */
+enum op { OP_LT, OP_LE, OP_GT, OP_GE, OP_EQ, OP_NE, first_op = OP_LT, last_op = OP_NE };
+
+static enum op complement_op(enum op op)
+{
+	switch (op) {
+	case OP_LT: return OP_GE;
+	case OP_LE: return OP_GT;
+	case OP_GT: return OP_LE;
+	case OP_GE: return OP_LT;
+	case OP_EQ: return OP_NE;
+	case OP_NE: return OP_EQ;
+	default: printf("complement_op!\n"); exit(1);
+	}
+}
+
+static const char *op_str(enum op op)
+{
+	switch (op) {
+	case OP_LT: return "<";
+	case OP_LE: return "<=";
+	case OP_GT: return ">";
+	case OP_GE: return ">=";
+	case OP_EQ: return "==";
+	case OP_NE: return "!=";
+	default: printf("op_str!\n"); exit(1);
+	}
+}
+
+/* Can register with range [x.a, x.b] *EVER* satisfy
+ * OP (<, <=, >, >=, ==, !=) relation to
+ * a regsiter with range [y.a, y.b]
+ * _in *num_t* domain_
+ */
+static bool range_canbe_op(enum num_t t, struct range x, struct range y, enum op op)
+{
+#define range_canbe(T) do {									\
+	switch (op) {										\
+	case OP_LT: return (T)x.a < (T)y.b;							\
+	case OP_LE: return (T)x.a <= (T)y.b;							\
+	case OP_GT: return (T)x.b > (T)y.a;							\
+	case OP_GE: return (T)x.b >= (T)y.a;							\
+	case OP_EQ: return (T)max_t(t, x.a, y.a) <= (T)min_t(t, x.b, y.b);			\
+	case OP_NE: return !((T)x.a == (T)x.b && (T)y.a == (T)y.b && (T)x.a == (T)y.a);		\
+	default: printf("range_canbe op %d\n", op); exit(1);					\
+	}											\
+} while (0)
+
+	switch (t) {
+	case U64: { range_canbe(u64); }
+	case U32: { range_canbe(u32); }
+	case S64: { range_canbe(s64); }
+	case S32: { range_canbe(s32); }
+	default: printf("range_canbe!\n"); exit(1);
+	}
+#undef range_canbe
+}
+
+/* Does register with range [x.a, x.b] *ALWAYS* satisfy
+ * OP (<, <=, >, >=, ==, !=) relation to
+ * a regsiter with range [y.a, y.b]
+ * _in *num_t* domain_
+ */
+static bool range_always_op(enum num_t t, struct range x, struct range y, enum op op)
+{
+	/* always op <=> ! canbe complement(op) */
+	return !range_canbe_op(t, x, y, complement_op(op));
+}
+
+/* Does register with range [x.a, x.b] *NEVER* satisfy
+ * OP (<, <=, >, >=, ==, !=) relation to
+ * a regsiter with range [y.a, y.b]
+ * _in *num_t* domain_
+ */
+static bool range_never_op(enum num_t t, struct range x, struct range y, enum op op)
+{
+	return !range_canbe_op(t, x, y, op);
+}
+
+/* similar to verifier's is_branch_taken():
+ *    1 - always taken;
+ *    0 - never taken,
+ *   -1 - unsure.
+ */
+static int range_branch_taken_op(enum num_t t, struct range x, struct range y, enum op op)
+{
+	if (range_always_op(t, x, y, op))
+		return 1;
+	if (range_never_op(t, x, y, op))
+		return 0;
+	return -1;
+}
+
+/* What would be the new estimates for register x and y ranges assuming truthful
+ * OP comparison between them. I.e., (x OP y == true) => x <- newx, y <- newy.
+ *
+ * We assume "interesting" cases where ranges overlap. Cases where it's
+ * obvious that (x OP y) is either always true or false should be filtered with
+ * range_never and range_always checks.
+ */
+static void range_cond(enum num_t t, struct range x, struct range y,
+		       enum op op, struct range *newx, struct range *newy)
+{
+	if (!range_canbe_op(t, x, y, op)) {
+		/* nothing to adjust, can't happen, return original values */
+		*newx = x;
+		*newy = y;
+		return;
+	}
+	switch (op) {
+	case OP_LT:
+		*newx = range(t, x.a, min_t(t, x.b, y.b - 1));
+		*newy = range(t, max_t(t, x.a + 1, y.a), y.b);
+		break;
+	case OP_LE:
+		*newx = range(t, x.a, min_t(t, x.b, y.b));
+		*newy = range(t, max_t(t, x.a, y.a), y.b);
+		break;
+	case OP_GT:
+		*newx = range(t, max_t(t, x.a, y.a + 1), x.b);
+		*newy = range(t, y.a, min_t(t, x.b - 1, y.b));
+		break;
+	case OP_GE:
+		*newx = range(t, max_t(t, x.a, y.a), x.b);
+		*newy = range(t, y.a, min_t(t, x.b, y.b));
+		break;
+	case OP_EQ:
+		*newx = range(t, max_t(t, x.a, y.a), min_t(t, x.b, y.b));
+		*newy = range(t, max_t(t, x.a, y.a), min_t(t, x.b, y.b));
+		break;
+	case OP_NE:
+		/* below logic is supported by the verifier now */
+		if (x.a == x.b && x.a == y.a) {
+			/* X is a constant matching left side of Y */
+			*newx = range(t, x.a, x.b);
+			*newy = range(t, y.a + 1, y.b);
+		} else if (x.a == x.b && x.b == y.b) {
+			/* X is a constant matching rigth side of Y */
+			*newx = range(t, x.a, x.b);
+			*newy = range(t, y.a, y.b - 1);
+		} else if (y.a == y.b && x.a == y.a) {
+			/* Y is a constant matching left side of X */
+			*newx = range(t, x.a + 1, x.b);
+			*newy = range(t, y.a, y.b);
+		} else if (y.a == y.b && x.b == y.b) {
+			/* Y is a constant matching rigth side of X */
+			*newx = range(t, x.a, x.b - 1);
+			*newy = range(t, y.a, y.b);
+		} else {
+			/* generic case, can't derive more information */
+			*newx = range(t, x.a, x.b);
+			*newy = range(t, y.a, y.b);
+		}
+
+		break;
+	default:
+		break;
+	}
+}
+
+/* =======================
+ * REGISTER STATE HANDLING
+ * =======================
+ */
+struct reg_state {
+	struct range r[4]; /* indexed by enum num_t: U64, U32, S64, S32 */
+	bool valid;
+};
+
+static void print_reg_state(struct reg_state *r, const char *sfx)
+{
+	DEFINE_STRBUF(sb, 512);
+	enum num_t t;
+	int cnt = 0;
+
+	if (!r->valid) {
+		printf("<not found>%s", sfx);
+		return;
+	}
+
+	snappendf(sb, "scalar(");
+	for (t = first_t; t <= last_t; t++) {
+		snappendf(sb, "%s%s=", cnt++ ? "," : "", t_str(t));
+		snprintf_range(t, sb, r->r[t]);
+	}
+	snappendf(sb, ")");
+
+	printf("%s%s", sb->buf, sfx);
+}
+
+static void print_refinement(enum num_t s_t, struct range src,
+			     enum num_t d_t, struct range old, struct range new,
+			     const char *ctx)
+{
+	printf("REFINING (%s) (%s)SRC=", ctx, t_str(s_t));
+	print_range(s_t, src, "");
+	printf(" (%s)DST_OLD=", t_str(d_t));
+	print_range(d_t, old, "");
+	printf(" (%s)DST_NEW=", t_str(d_t));
+	print_range(d_t, new, "\n");
+}
+
+static void reg_state_refine(struct reg_state *r, enum num_t t, struct range x, const char *ctx)
+{
+	enum num_t d_t, s_t;
+	struct range old;
+	bool keep_going = false;
+
+again:
+	/* try to derive new knowledge from just learned range x of type t */
+	for (d_t = first_t; d_t <= last_t; d_t++) {
+		old = r->r[d_t];
+		r->r[d_t] = range_refine(d_t, r->r[d_t], t, x);
+		if (!range_eq(r->r[d_t], old)) {
+			keep_going = true;
+			if (env.verbosity >= VERBOSE_VERY)
+				print_refinement(t, x, d_t, old, r->r[d_t], ctx);
+		}
+	}
+
+	/* now see if we can derive anything new from updated reg_state's ranges */
+	for (s_t = first_t; s_t <= last_t; s_t++) {
+		for (d_t = first_t; d_t <= last_t; d_t++) {
+			old = r->r[d_t];
+			r->r[d_t] = range_refine(d_t, r->r[d_t], s_t, r->r[s_t]);
+			if (!range_eq(r->r[d_t], old)) {
+				keep_going = true;
+				if (env.verbosity >= VERBOSE_VERY)
+					print_refinement(s_t, r->r[s_t], d_t, old, r->r[d_t], ctx);
+			}
+		}
+	}
+
+	/* keep refining until we converge */
+	if (keep_going) {
+		keep_going = false;
+		goto again;
+	}
+}
+
+static void reg_state_set_const(struct reg_state *rs, enum num_t t, u64 val)
+{
+	enum num_t tt;
+
+	rs->valid = true;
+	for (tt = first_t; tt <= last_t; tt++)
+		rs->r[tt] = tt == t ? range(t, val, val) : unkn[tt];
+
+	reg_state_refine(rs, t, rs->r[t], "CONST");
+}
+
+static void reg_state_cond(enum num_t t, struct reg_state *x, struct reg_state *y, enum op op,
+			   struct reg_state *newx, struct reg_state *newy, const char *ctx)
+{
+	char buf[32];
+	enum num_t ts[2];
+	struct reg_state xx = *x, yy = *y;
+	int i, t_cnt;
+	struct range z1, z2;
+
+	if (op == OP_EQ || op == OP_NE) {
+		/* OP_EQ and OP_NE are sign-agnostic, so we need to process
+		 * both signed and unsigned domains at the same time
+		 */
+		ts[0] = t_unsigned(t);
+		ts[1] = t_signed(t);
+		t_cnt = 2;
+	} else {
+		ts[0] = t;
+		t_cnt = 1;
+	}
+
+	for (i = 0; i < t_cnt; i++) {
+		t = ts[i];
+		z1 = x->r[t];
+		z2 = y->r[t];
+
+		range_cond(t, z1, z2, op, &z1, &z2);
+
+		if (newx) {
+			snprintf(buf, sizeof(buf), "%s R1", ctx);
+			reg_state_refine(&xx, t, z1, buf);
+		}
+		if (newy) {
+			snprintf(buf, sizeof(buf), "%s R2", ctx);
+			reg_state_refine(&yy, t, z2, buf);
+		}
+	}
+
+	if (newx)
+		*newx = xx;
+	if (newy)
+		*newy = yy;
+}
+
+static int reg_state_branch_taken_op(enum num_t t, struct reg_state *x, struct reg_state *y,
+				     enum op op)
+{
+	if (op == OP_EQ || op == OP_NE) {
+		/* OP_EQ and OP_NE are sign-agnostic */
+		enum num_t tu = t_unsigned(t);
+		enum num_t ts = t_signed(t);
+		int br_u, br_s, br;
+
+		br_u = range_branch_taken_op(tu, x->r[tu], y->r[tu], op);
+		br_s = range_branch_taken_op(ts, x->r[ts], y->r[ts], op);
+
+		if (br_u >= 0 && br_s >= 0 && br_u != br_s)
+			ASSERT_FALSE(true, "branch taken inconsistency!\n");
+
+		/* if 64-bit ranges are indecisive, use 32-bit subranges to
+		 * eliminate always/never taken branches, if possible
+		 */
+		if (br_u == -1 && (t == U64 || t == S64)) {
+			br = range_branch_taken_op(U32, x->r[U32], y->r[U32], op);
+			/* we can only reject for OP_EQ, never take branch
+			 * based on lower 32 bits
+			 */
+			if (op == OP_EQ && br == 0)
+				return 0;
+			/* for OP_NEQ we can be conclusive only if lower 32 bits
+			 * differ and thus inequality branch is always taken
+			 */
+			if (op == OP_NE && br == 1)
+				return 1;
+
+			br = range_branch_taken_op(S32, x->r[S32], y->r[S32], op);
+			if (op == OP_EQ && br == 0)
+				return 0;
+			if (op == OP_NE && br == 1)
+				return 1;
+		}
+
+		return br_u >= 0 ? br_u : br_s;
+	}
+	return range_branch_taken_op(t, x->r[t], y->r[t], op);
+}
+
+/* =====================================
+ * BPF PROGS GENERATION AND VERIFICATION
+ * =====================================
+ */
+struct case_spec {
+	/* whether to init full register (r1) or sub-register (w1) */
+	bool init_subregs;
+	/* whether to establish initial value range on full register (r1) or
+	 * sub-register (w1)
+	 */
+	bool setup_subregs;
+	/* whether to establish initial value range using signed or unsigned
+	 * comparisons (i.e., initialize umin/umax or smin/smax directly)
+	 */
+	bool setup_signed;
+	/* whether to perform comparison on full registers or sub-registers */
+	bool compare_subregs;
+	/* whether to perform comparison using signed or unsigned operations */
+	bool compare_signed;
+};
+
+/* Generate test BPF program based on provided test ranges, operation, and
+ * specifications about register bitness and signedness.
+ */
+static int load_range_cmp_prog(struct range x, struct range y, enum op op,
+			       int branch_taken, struct case_spec spec,
+			       char *log_buf, size_t log_sz,
+			       int *false_pos, int *true_pos)
+{
+#define emit(insn) ({							\
+	struct bpf_insn __insns[] = { insn };				\
+	int __i;							\
+	for (__i = 0; __i < ARRAY_SIZE(__insns); __i++)			\
+		insns[cur_pos + __i] = __insns[__i];			\
+	cur_pos += __i;							\
+})
+#define JMP_TO(target) (target - cur_pos - 1)
+	int cur_pos = 0, exit_pos, fd, op_code;
+	struct bpf_insn insns[64];
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		.log_level = 2,
+		.log_buf = log_buf,
+		.log_size = log_sz,
+		.prog_flags = BPF_F_TEST_REG_INVARIANTS,
+	);
+
+	/* ; skip exit block below
+	 * goto +2;
+	 */
+	emit(BPF_JMP_A(2));
+	exit_pos = cur_pos;
+	/* ; exit block for all the preparatory conditionals
+	 * out:
+	 * r0 = 0;
+	 * exit;
+	 */
+	emit(BPF_MOV64_IMM(BPF_REG_0, 0));
+	emit(BPF_EXIT_INSN());
+	/*
+	 * ; assign r6/w6 and r7/w7 unpredictable u64/u32 value
+	 * call bpf_get_current_pid_tgid;
+	 * r6 = r0;               | w6 = w0;
+	 * call bpf_get_current_pid_tgid;
+	 * r7 = r0;               | w7 = w0;
+	 */
+	emit(BPF_EMIT_CALL(BPF_FUNC_get_current_pid_tgid));
+	if (spec.init_subregs)
+		emit(BPF_MOV32_REG(BPF_REG_6, BPF_REG_0));
+	else
+		emit(BPF_MOV64_REG(BPF_REG_6, BPF_REG_0));
+	emit(BPF_EMIT_CALL(BPF_FUNC_get_current_pid_tgid));
+	if (spec.init_subregs)
+		emit(BPF_MOV32_REG(BPF_REG_7, BPF_REG_0));
+	else
+		emit(BPF_MOV64_REG(BPF_REG_7, BPF_REG_0));
+	/* ; setup initial r6/w6 possible value range ([x.a, x.b])
+	 * r1 = %[x.a] ll;        | w1 = %[x.a];
+	 * r2 = %[x.b] ll;        | w2 = %[x.b];
+	 * if r6 < r1 goto out;   | if w6 < w1 goto out;
+	 * if r6 > r2 goto out;   | if w6 > w2 goto out;
+	 */
+	if (spec.setup_subregs) {
+		emit(BPF_MOV32_IMM(BPF_REG_1, (s32)x.a));
+		emit(BPF_MOV32_IMM(BPF_REG_2, (s32)x.b));
+		emit(BPF_JMP32_REG(spec.setup_signed ? BPF_JSLT : BPF_JLT,
+				   BPF_REG_6, BPF_REG_1, JMP_TO(exit_pos)));
+		emit(BPF_JMP32_REG(spec.setup_signed ? BPF_JSGT : BPF_JGT,
+				   BPF_REG_6, BPF_REG_2, JMP_TO(exit_pos)));
+	} else {
+		emit(BPF_LD_IMM64(BPF_REG_1, x.a));
+		emit(BPF_LD_IMM64(BPF_REG_2, x.b));
+		emit(BPF_JMP_REG(spec.setup_signed ? BPF_JSLT : BPF_JLT,
+				 BPF_REG_6, BPF_REG_1, JMP_TO(exit_pos)));
+		emit(BPF_JMP_REG(spec.setup_signed ? BPF_JSGT : BPF_JGT,
+				 BPF_REG_6, BPF_REG_2, JMP_TO(exit_pos)));
+	}
+	/* ; setup initial r7/w7 possible value range ([y.a, y.b])
+	 * r1 = %[y.a] ll;        | w1 = %[y.a];
+	 * r2 = %[y.b] ll;        | w2 = %[y.b];
+	 * if r7 < r1 goto out;   | if w7 < w1 goto out;
+	 * if r7 > r2 goto out;   | if w7 > w2 goto out;
+	 */
+	if (spec.setup_subregs) {
+		emit(BPF_MOV32_IMM(BPF_REG_1, (s32)y.a));
+		emit(BPF_MOV32_IMM(BPF_REG_2, (s32)y.b));
+		emit(BPF_JMP32_REG(spec.setup_signed ? BPF_JSLT : BPF_JLT,
+				   BPF_REG_7, BPF_REG_1, JMP_TO(exit_pos)));
+		emit(BPF_JMP32_REG(spec.setup_signed ? BPF_JSGT : BPF_JGT,
+				   BPF_REG_7, BPF_REG_2, JMP_TO(exit_pos)));
+	} else {
+		emit(BPF_LD_IMM64(BPF_REG_1, y.a));
+		emit(BPF_LD_IMM64(BPF_REG_2, y.b));
+		emit(BPF_JMP_REG(spec.setup_signed ? BPF_JSLT : BPF_JLT,
+				 BPF_REG_7, BPF_REG_1, JMP_TO(exit_pos)));
+		emit(BPF_JMP_REG(spec.setup_signed ? BPF_JSGT : BPF_JGT,
+				 BPF_REG_7, BPF_REG_2, JMP_TO(exit_pos)));
+	}
+	/* ; range test instruction
+	 * if r6 <op> r7 goto +3; | if w6 <op> w7 goto +3;
+	 */
+	switch (op) {
+	case OP_LT: op_code = spec.compare_signed ? BPF_JSLT : BPF_JLT; break;
+	case OP_LE: op_code = spec.compare_signed ? BPF_JSLE : BPF_JLE; break;
+	case OP_GT: op_code = spec.compare_signed ? BPF_JSGT : BPF_JGT; break;
+	case OP_GE: op_code = spec.compare_signed ? BPF_JSGE : BPF_JGE; break;
+	case OP_EQ: op_code = BPF_JEQ; break;
+	case OP_NE: op_code = BPF_JNE; break;
+	default:
+		printf("unrecognized op %d\n", op);
+		return -ENOTSUP;
+	}
+	/* ; BEFORE conditional, r0/w0 = {r6/w6,r7/w7} is to extract verifier state reliably
+	 * ; this is used for debugging, as verifier doesn't always print
+	 * ; registers states as of condition jump instruction (e.g., when
+	 * ; precision marking happens)
+	 * r0 = r6;               | w0 = w6;
+	 * r0 = r7;               | w0 = w7;
+	 */
+	if (spec.compare_subregs) {
+		emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_6));
+		emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_7));
+	} else {
+		emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_6));
+		emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_7));
+	}
+	if (spec.compare_subregs)
+		emit(BPF_JMP32_REG(op_code, BPF_REG_6, BPF_REG_7, 3));
+	else
+		emit(BPF_JMP_REG(op_code, BPF_REG_6, BPF_REG_7, 3));
+	/* ; FALSE branch, r0/w0 = {r6/w6,r7/w7} is to extract verifier state reliably
+	 * r0 = r6;               | w0 = w6;
+	 * r0 = r7;               | w0 = w7;
+	 * exit;
+	 */
+	*false_pos = cur_pos;
+	if (spec.compare_subregs) {
+		emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_6));
+		emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_7));
+	} else {
+		emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_6));
+		emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_7));
+	}
+	if (branch_taken == 1) /* false branch is never taken */
+		emit(BPF_EMIT_CALL(0xDEAD)); /* poison this branch */
+	else
+		emit(BPF_EXIT_INSN());
+	/* ; TRUE branch, r0/w0 = {r6/w6,r7/w7} is to extract verifier state reliably
+	 * r0 = r6;               | w0 = w6;
+	 * r0 = r7;               | w0 = w7;
+	 * exit;
+	 */
+	*true_pos = cur_pos;
+	if (spec.compare_subregs) {
+		emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_6));
+		emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_7));
+	} else {
+		emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_6));
+		emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_7));
+	}
+	if (branch_taken == 0) /* true branch is never taken */
+		emit(BPF_EMIT_CALL(0xDEAD)); /* poison this branch */
+	emit(BPF_EXIT_INSN()); /* last instruction has to be exit */
+
+	fd = bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT, "reg_bounds_test",
+			   "GPL", insns, cur_pos, &opts);
+	if (fd < 0)
+		return fd;
+
+	close(fd);
+	return 0;
+#undef emit
+#undef JMP_TO
+}
+
+#define str_has_pfx(str, pfx) (strncmp(str, pfx, strlen(pfx)) == 0)
+
+/* Parse register state from verifier log.
+ * `s` should point to the start of "Rx = ..." substring in the verifier log.
+ */
+static int parse_reg_state(const char *s, struct reg_state *reg)
+{
+	/* There are two generic forms for SCALAR register:
+	 * - known constant: R6_rwD=P%lld
+	 * - range: R6_rwD=scalar(id=1,...), where "..." is a comma-separated
+	 *   list of optional range specifiers:
+	 *     - umin=%llu, if missing, assumed 0;
+	 *     - umax=%llu, if missing, assumed U64_MAX;
+	 *     - smin=%lld, if missing, assumed S64_MIN;
+	 *     - smax=%lld, if missing, assummed S64_MAX;
+	 *     - umin32=%d, if missing, assumed 0;
+	 *     - umax32=%d, if missing, assumed U32_MAX;
+	 *     - smin32=%d, if missing, assumed S32_MIN;
+	 *     - smax32=%d, if missing, assummed S32_MAX;
+	 *     - var_off=(%#llx; %#llx), tnum part, we don't care about it.
+	 *
+	 * If some of the values are equal, they will be grouped (but min/max
+	 * are not mixed together, and similarly negative values are not
+	 * grouped with non-negative ones). E.g.:
+	 *
+	 *   R6_w=Pscalar(smin=smin32=0, smax=umax=umax32=1000)
+	 *
+	 * _rwD part is optional (and any of the letters can be missing).
+	 * P (precision mark) is optional as well.
+	 *
+	 * Anything inside scalar() is optional, including id, of course.
+	 */
+	struct {
+		const char *pfx;
+		u64 *dst, def;
+		bool is_32, is_set;
+	} *f, fields[8] = {
+		{"smin=", &reg->r[S64].a, S64_MIN},
+		{"smax=", &reg->r[S64].b, S64_MAX},
+		{"umin=", &reg->r[U64].a, 0},
+		{"umax=", &reg->r[U64].b, U64_MAX},
+		{"smin32=", &reg->r[S32].a, (u32)S32_MIN, true},
+		{"smax32=", &reg->r[S32].b, (u32)S32_MAX, true},
+		{"umin32=", &reg->r[U32].a, 0,            true},
+		{"umax32=", &reg->r[U32].b, U32_MAX,      true},
+	};
+	const char *p;
+	int i;
+
+	p = strchr(s, '=');
+	if (!p)
+		return -EINVAL;
+	p++;
+	if (*p == 'P')
+		p++;
+
+	if (!str_has_pfx(p, "scalar(")) {
+		long long sval;
+		enum num_t t;
+
+		if (p[0] == '0' && p[1] == 'x') {
+			if (sscanf(p, "%llx", &sval) != 1)
+				return -EINVAL;
+		} else {
+			if (sscanf(p, "%lld", &sval) != 1)
+				return -EINVAL;
+		}
+
+		reg->valid = true;
+		for (t = first_t; t <= last_t; t++) {
+			reg->r[t] = range(t, sval, sval);
+		}
+		return 0;
+	}
+
+	p += sizeof("scalar");
+	while (p) {
+		int midxs[ARRAY_SIZE(fields)], mcnt = 0;
+		u64 val;
+
+		for (i = 0; i < ARRAY_SIZE(fields); i++) {
+			f = &fields[i];
+			if (!str_has_pfx(p, f->pfx))
+				continue;
+			midxs[mcnt++] = i;
+			p += strlen(f->pfx);
+		}
+
+		if (mcnt) {
+			/* populate all matched fields */
+			if (p[0] == '0' && p[1] == 'x') {
+				if (sscanf(p, "%llx", &val) != 1)
+					return -EINVAL;
+			} else {
+				if (sscanf(p, "%lld", &val) != 1)
+					return -EINVAL;
+			}
+
+			for (i = 0; i < mcnt; i++) {
+				f = &fields[midxs[i]];
+				f->is_set = true;
+				*f->dst = f->is_32 ? (u64)(u32)val : val;
+			}
+		} else if (str_has_pfx(p, "var_off")) {
+			/* skip "var_off=(0x0; 0x3f)" part completely */
+			p = strchr(p, ')');
+			if (!p)
+				return -EINVAL;
+			p++;
+		}
+
+		p = strpbrk(p, ",)");
+		if (*p == ')')
+			break;
+		if (p)
+			p++;
+	}
+
+	reg->valid = true;
+
+	for (i = 0; i < ARRAY_SIZE(fields); i++) {
+		f = &fields[i];
+		if (!f->is_set)
+			*f->dst = f->def;
+	}
+
+	return 0;
+}
+
+
+/* Parse all register states (TRUE/FALSE branches and DST/SRC registers)
+ * out of the verifier log for a corresponding test case BPF program.
+ */
+static int parse_range_cmp_log(const char *log_buf, struct case_spec spec,
+			       int false_pos, int true_pos,
+			       struct reg_state *false1_reg, struct reg_state *false2_reg,
+			       struct reg_state *true1_reg, struct reg_state *true2_reg)
+{
+	struct {
+		int insn_idx;
+		int reg_idx;
+		const char *reg_upper;
+		struct reg_state *state;
+	} specs[] = {
+		{false_pos,     6, "R6=", false1_reg},
+		{false_pos + 1, 7, "R7=", false2_reg},
+		{true_pos,      6, "R6=", true1_reg},
+		{true_pos + 1,  7, "R7=", true2_reg},
+	};
+	char buf[32];
+	const char *p = log_buf, *q;
+	int i, err;
+
+	for (i = 0; i < 4; i++) {
+		sprintf(buf, "%d: (%s) %s = %s%d", specs[i].insn_idx,
+			spec.compare_subregs ? "bc" : "bf",
+			spec.compare_subregs ? "w0" : "r0",
+			spec.compare_subregs ? "w" : "r", specs[i].reg_idx);
+
+		q = strstr(p, buf);
+		if (!q) {
+			*specs[i].state = (struct reg_state){.valid = false};
+			continue;
+		}
+		p = strstr(q, specs[i].reg_upper);
+		if (!p)
+			return -EINVAL;
+		err = parse_reg_state(p, specs[i].state);
+		if (err)
+			return -EINVAL;
+	}
+	return 0;
+}
+
+/* Validate ranges match, and print details if they don't */
+static bool assert_range_eq(enum num_t t, struct range x, struct range y,
+			    const char *ctx1, const char *ctx2)
+{
+	DEFINE_STRBUF(sb, 512);
+
+	if (range_eq(x, y))
+		return true;
+
+	snappendf(sb, "MISMATCH %s.%s: ", ctx1, ctx2);
+	snprintf_range(t, sb, x);
+	snappendf(sb, " != ");
+	snprintf_range(t, sb, y);
+
+	printf("%s\n", sb->buf);
+
+	return false;
+}
+
+/* Validate that register states match, and print details if they don't */
+static bool assert_reg_state_eq(struct reg_state *r, struct reg_state *e, const char *ctx)
+{
+	bool ok = true;
+	enum num_t t;
+
+	if (r->valid != e->valid) {
+		printf("MISMATCH %s: actual %s != expected %s\n", ctx,
+		       r->valid ? "<valid>" : "<invalid>",
+		       e->valid ? "<valid>" : "<invalid>");
+		return false;
+	}
+
+	if (!r->valid)
+		return true;
+
+	for (t = first_t; t <= last_t; t++) {
+		if (!assert_range_eq(t, r->r[t], e->r[t], ctx, t_str(t)))
+			ok = false;
+	}
+
+	return ok;
+}
+
+/* Printf verifier log, filtering out irrelevant noise */
+static void print_verifier_log(const char *buf)
+{
+	const char *p;
+
+	while (buf[0]) {
+		p = strchrnul(buf, '\n');
+
+		/* filter out irrelevant precision backtracking logs */
+		if (str_has_pfx(buf, "mark_precise: "))
+			goto skip_line;
+
+		printf("%.*s\n", (int)(p - buf), buf);
+
+skip_line:
+		buf = *p == '\0' ? p : p + 1;
+	}
+}
+
+/* Simulate provided test case purely with our own range-based logic.
+ * This is done to set up expectations for verifier's branch_taken logic and
+ * verifier's register states in the verifier log.
+ */
+static void sim_case(enum num_t init_t, enum num_t cond_t,
+		     struct range x, struct range y, enum op op,
+		     struct reg_state *fr1, struct reg_state *fr2,
+		     struct reg_state *tr1, struct reg_state *tr2,
+		     int *branch_taken)
+{
+	const u64 A = x.a;
+	const u64 B = x.b;
+	const u64 C = y.a;
+	const u64 D = y.b;
+	struct reg_state rc;
+	enum op rev_op = complement_op(op);
+	enum num_t t;
+
+	fr1->valid = fr2->valid = true;
+	tr1->valid = tr2->valid = true;
+	for (t = first_t; t <= last_t; t++) {
+		/* if we are initializing using 32-bit subregisters,
+		 * full registers get upper 32 bits zeroed automatically
+		 */
+		struct range z = t_is_32(init_t) ? unkn_subreg(t) : unkn[t];
+
+		fr1->r[t] = fr2->r[t] = tr1->r[t] = tr2->r[t] = z;
+	}
+
+	/* step 1: r1 >= A, r2 >= C */
+	reg_state_set_const(&rc, init_t, A);
+	reg_state_cond(init_t, fr1, &rc, OP_GE, fr1, NULL, "r1>=A");
+	reg_state_set_const(&rc, init_t, C);
+	reg_state_cond(init_t, fr2, &rc, OP_GE, fr2, NULL, "r2>=C");
+	*tr1 = *fr1;
+	*tr2 = *fr2;
+	if (env.verbosity >= VERBOSE_VERY) {
+		printf("STEP1 (%s) R1: ", t_str(init_t)); print_reg_state(fr1, "\n");
+		printf("STEP1 (%s) R2: ", t_str(init_t)); print_reg_state(fr2, "\n");
+	}
+
+	/* step 2: r1 <= B, r2 <= D */
+	reg_state_set_const(&rc, init_t, B);
+	reg_state_cond(init_t, fr1, &rc, OP_LE, fr1, NULL, "r1<=B");
+	reg_state_set_const(&rc, init_t, D);
+	reg_state_cond(init_t, fr2, &rc, OP_LE, fr2, NULL, "r2<=D");
+	*tr1 = *fr1;
+	*tr2 = *fr2;
+	if (env.verbosity >= VERBOSE_VERY) {
+		printf("STEP2 (%s) R1: ", t_str(init_t)); print_reg_state(fr1, "\n");
+		printf("STEP2 (%s) R2: ", t_str(init_t)); print_reg_state(fr2, "\n");
+	}
+
+	/* step 3: r1 <op> r2 */
+	*branch_taken = reg_state_branch_taken_op(cond_t, fr1, fr2, op);
+	fr1->valid = fr2->valid = false;
+	tr1->valid = tr2->valid = false;
+	if (*branch_taken != 1) { /* FALSE is possible */
+		fr1->valid = fr2->valid = true;
+		reg_state_cond(cond_t, fr1, fr2, rev_op, fr1, fr2, "FALSE");
+	}
+	if (*branch_taken != 0) { /* TRUE is possible */
+		tr1->valid = tr2->valid = true;
+		reg_state_cond(cond_t, tr1, tr2, op, tr1, tr2, "TRUE");
+	}
+	if (env.verbosity >= VERBOSE_VERY) {
+		printf("STEP3 (%s) FALSE R1:", t_str(cond_t)); print_reg_state(fr1, "\n");
+		printf("STEP3 (%s) FALSE R2:", t_str(cond_t)); print_reg_state(fr2, "\n");
+		printf("STEP3 (%s) TRUE  R1:", t_str(cond_t)); print_reg_state(tr1, "\n");
+		printf("STEP3 (%s) TRUE  R2:", t_str(cond_t)); print_reg_state(tr2, "\n");
+	}
+}
+
+/* ===============================
+ * HIGH-LEVEL TEST CASE VALIDATION
+ * ===============================
+ */
+static u32 upper_seeds[] = {
+	0,
+	1,
+	U32_MAX,
+	U32_MAX - 1,
+	S32_MAX,
+	(u32)S32_MIN,
+};
+
+static u32 lower_seeds[] = {
+	0,
+	1,
+	2, (u32)-2,
+	255, (u32)-255,
+	UINT_MAX,
+	UINT_MAX - 1,
+	INT_MAX,
+	(u32)INT_MIN,
+};
+
+struct ctx {
+	int val_cnt, subval_cnt, range_cnt, subrange_cnt;
+	u64 uvals[ARRAY_SIZE(upper_seeds) * ARRAY_SIZE(lower_seeds)];
+	s64 svals[ARRAY_SIZE(upper_seeds) * ARRAY_SIZE(lower_seeds)];
+	u32 usubvals[ARRAY_SIZE(lower_seeds)];
+	s32 ssubvals[ARRAY_SIZE(lower_seeds)];
+	struct range *uranges, *sranges;
+	struct range *usubranges, *ssubranges;
+	int max_failure_cnt, cur_failure_cnt;
+	int total_case_cnt, case_cnt;
+	int rand_case_cnt;
+	unsigned rand_seed;
+	__u64 start_ns;
+	char progress_ctx[64];
+};
+
+static void cleanup_ctx(struct ctx *ctx)
+{
+	free(ctx->uranges);
+	free(ctx->sranges);
+	free(ctx->usubranges);
+	free(ctx->ssubranges);
+}
+
+struct subtest_case {
+	enum num_t init_t;
+	enum num_t cond_t;
+	struct range x;
+	struct range y;
+	enum op op;
+};
+
+static void subtest_case_str(struct strbuf *sb, struct subtest_case *t, bool use_op)
+{
+	snappendf(sb, "(%s)", t_str(t->init_t));
+	snprintf_range(t->init_t, sb, t->x);
+	snappendf(sb, " (%s)%s ", t_str(t->cond_t), use_op ? op_str(t->op) : "<op>");
+	snprintf_range(t->init_t, sb, t->y);
+}
+
+/* Generate and validate test case based on specific combination of setup
+ * register ranges (including their expected num_t domain), and conditional
+ * operation to perform (including num_t domain in which it has to be
+ * performed)
+ */
+static int verify_case_op(enum num_t init_t, enum num_t cond_t,
+			  struct range x, struct range y, enum op op)
+{
+	char log_buf[256 * 1024];
+	size_t log_sz = sizeof(log_buf);
+	int err, false_pos = 0, true_pos = 0, branch_taken;
+	struct reg_state fr1, fr2, tr1, tr2;
+	struct reg_state fe1, fe2, te1, te2;
+	bool failed = false;
+	struct case_spec spec = {
+		.init_subregs = (init_t == U32 || init_t == S32),
+		.setup_subregs = (init_t == U32 || init_t == S32),
+		.setup_signed = (init_t == S64 || init_t == S32),
+		.compare_subregs = (cond_t == U32 || cond_t == S32),
+		.compare_signed = (cond_t == S64 || cond_t == S32),
+	};
+
+	log_buf[0] = '\0';
+
+	sim_case(init_t, cond_t, x, y, op, &fe1, &fe2, &te1, &te2, &branch_taken);
+
+	err = load_range_cmp_prog(x, y, op, branch_taken, spec,
+				  log_buf, log_sz, &false_pos, &true_pos);
+	if (err) {
+		ASSERT_OK(err, "load_range_cmp_prog");
+		failed = true;
+	}
+
+	err = parse_range_cmp_log(log_buf, spec, false_pos, true_pos,
+				  &fr1, &fr2, &tr1, &tr2);
+	if (err) {
+		ASSERT_OK(err, "parse_range_cmp_log");
+		failed = true;
+	}
+
+	if (!assert_reg_state_eq(&fr1, &fe1, "false_reg1") ||
+	    !assert_reg_state_eq(&fr2, &fe2, "false_reg2") ||
+	    !assert_reg_state_eq(&tr1, &te1, "true_reg1") ||
+	    !assert_reg_state_eq(&tr2, &te2, "true_reg2")) {
+		failed = true;
+	}
+
+	if (failed || env.verbosity >= VERBOSE_NORMAL) {
+		if (failed || env.verbosity >= VERBOSE_VERY) {
+			printf("VERIFIER LOG:\n========================\n");
+			print_verifier_log(log_buf);
+			printf("=====================\n");
+		}
+		printf("ACTUAL   FALSE1: "); print_reg_state(&fr1, "\n");
+		printf("EXPECTED FALSE1: "); print_reg_state(&fe1, "\n");
+		printf("ACTUAL   FALSE2: "); print_reg_state(&fr2, "\n");
+		printf("EXPECTED FALSE2: "); print_reg_state(&fe2, "\n");
+		printf("ACTUAL   TRUE1:  "); print_reg_state(&tr1, "\n");
+		printf("EXPECTED TRUE1:  "); print_reg_state(&te1, "\n");
+		printf("ACTUAL   TRUE2:  "); print_reg_state(&tr2, "\n");
+		printf("EXPECTED TRUE2:  "); print_reg_state(&te2, "\n");
+
+		return failed ? -EINVAL : 0;
+	}
+
+	return 0;
+}
+
+/* Given setup ranges and number types, go over all supported operations,
+ * generating individual subtest for each allowed combination
+ */
+static int verify_case_opt(struct ctx *ctx, enum num_t init_t, enum num_t cond_t,
+			   struct range x, struct range y, bool is_subtest)
+{
+	DEFINE_STRBUF(sb, 256);
+	int err;
+	struct subtest_case sub = {
+		.init_t = init_t,
+		.cond_t = cond_t,
+		.x = x,
+		.y = y,
+	};
+
+	sb->pos = 0; /* reset position in strbuf */
+	subtest_case_str(sb, &sub, false /* ignore op */);
+	if (is_subtest && !test__start_subtest(sb->buf))
+		return 0;
+
+	for (sub.op = first_op; sub.op <= last_op; sub.op++) {
+		sb->pos = 0; /* reset position in strbuf */
+		subtest_case_str(sb, &sub, true /* print op */);
+
+		if (env.verbosity >= VERBOSE_NORMAL) /* this speeds up debugging */
+			printf("TEST CASE: %s\n", sb->buf);
+
+		err = verify_case_op(init_t, cond_t, x, y, sub.op);
+		if (err || env.verbosity >= VERBOSE_NORMAL)
+			ASSERT_OK(err, sb->buf);
+		if (err) {
+			ctx->cur_failure_cnt++;
+			if (ctx->cur_failure_cnt > ctx->max_failure_cnt)
+				return err;
+			return 0; /* keep testing other cases */
+		}
+		ctx->case_cnt++;
+		if ((ctx->case_cnt % 10000) == 0) {
+			double progress = (ctx->case_cnt + 0.0) / ctx->total_case_cnt;
+			u64 elapsed_ns = get_time_ns() - ctx->start_ns;
+			double remain_ns = elapsed_ns / progress * (1 - progress);
+
+			fprintf(env.stderr, "PROGRESS (%s): %d/%d (%.2lf%%), "
+					    "elapsed %llu mins (%.2lf hrs), "
+					    "ETA %.0lf mins (%.2lf hrs)\n",
+				ctx->progress_ctx,
+				ctx->case_cnt, ctx->total_case_cnt, 100.0 * progress,
+				elapsed_ns / 1000000000 / 60,
+				elapsed_ns / 1000000000.0 / 3600,
+				remain_ns / 1000000000.0 / 60,
+				remain_ns / 1000000000.0 / 3600);
+		}
+	}
+
+	return 0;
+}
+
+static int verify_case(struct ctx *ctx, enum num_t init_t, enum num_t cond_t,
+		       struct range x, struct range y)
+{
+	return verify_case_opt(ctx, init_t, cond_t, x, y, true /* is_subtest */);
+}
+
+/* ================================
+ * GENERATED CASES FROM SEED VALUES
+ * ================================
+ */
+static int u64_cmp(const void *p1, const void *p2)
+{
+	u64 x1 = *(const u64 *)p1, x2 = *(const u64 *)p2;
+
+	return x1 != x2 ? (x1 < x2 ? -1 : 1) : 0;
+}
+
+static int u32_cmp(const void *p1, const void *p2)
+{
+	u32 x1 = *(const u32 *)p1, x2 = *(const u32 *)p2;
+
+	return x1 != x2 ? (x1 < x2 ? -1 : 1) : 0;
+}
+
+static int s64_cmp(const void *p1, const void *p2)
+{
+	s64 x1 = *(const s64 *)p1, x2 = *(const s64 *)p2;
+
+	return x1 != x2 ? (x1 < x2 ? -1 : 1) : 0;
+}
+
+static int s32_cmp(const void *p1, const void *p2)
+{
+	s32 x1 = *(const s32 *)p1, x2 = *(const s32 *)p2;
+
+	return x1 != x2 ? (x1 < x2 ? -1 : 1) : 0;
+}
+
+/* Generate valid unique constants from seeds, both signed and unsigned */
+static void gen_vals(struct ctx *ctx)
+{
+	int i, j, cnt = 0;
+
+	for (i = 0; i < ARRAY_SIZE(upper_seeds); i++) {
+		for (j = 0; j < ARRAY_SIZE(lower_seeds); j++) {
+			ctx->uvals[cnt++] = (((u64)upper_seeds[i]) << 32) | lower_seeds[j];
+		}
+	}
+
+	/* sort and compact uvals (i.e., it's `sort | uniq`) */
+	qsort(ctx->uvals, cnt, sizeof(*ctx->uvals), u64_cmp);
+	for (i = 1, j = 0; i < cnt; i++) {
+		if (ctx->uvals[j] == ctx->uvals[i])
+			continue;
+		j++;
+		ctx->uvals[j] = ctx->uvals[i];
+	}
+	ctx->val_cnt = j + 1;
+
+	/* we have exactly the same number of s64 values, they are just in
+	 * a different order than u64s, so just sort them differently
+	 */
+	for (i = 0; i < ctx->val_cnt; i++)
+		ctx->svals[i] = ctx->uvals[i];
+	qsort(ctx->svals, ctx->val_cnt, sizeof(*ctx->svals), s64_cmp);
+
+	if (env.verbosity >= VERBOSE_SUPER) {
+		DEFINE_STRBUF(sb1, 256);
+		DEFINE_STRBUF(sb2, 256);
+
+		for (i = 0; i < ctx->val_cnt; i++) {
+			sb1->pos = sb2->pos = 0;
+			snprintf_num(U64, sb1, ctx->uvals[i]);
+			snprintf_num(S64, sb2, ctx->svals[i]);
+			printf("SEED #%d: u64=%-20s s64=%-20s\n", i, sb1->buf, sb2->buf);
+		}
+	}
+
+	/* 32-bit values are generated separately */
+	cnt = 0;
+	for (i = 0; i < ARRAY_SIZE(lower_seeds); i++) {
+		ctx->usubvals[cnt++] = lower_seeds[i];
+	}
+
+	/* sort and compact usubvals (i.e., it's `sort | uniq`) */
+	qsort(ctx->usubvals, cnt, sizeof(*ctx->usubvals), u32_cmp);
+	for (i = 1, j = 0; i < cnt; i++) {
+		if (ctx->usubvals[j] == ctx->usubvals[i])
+			continue;
+		j++;
+		ctx->usubvals[j] = ctx->usubvals[i];
+	}
+	ctx->subval_cnt = j + 1;
+
+	for (i = 0; i < ctx->subval_cnt; i++)
+		ctx->ssubvals[i] = ctx->usubvals[i];
+	qsort(ctx->ssubvals, ctx->subval_cnt, sizeof(*ctx->ssubvals), s32_cmp);
+
+	if (env.verbosity >= VERBOSE_SUPER) {
+		DEFINE_STRBUF(sb1, 256);
+		DEFINE_STRBUF(sb2, 256);
+
+		for (i = 0; i < ctx->subval_cnt; i++) {
+			sb1->pos = sb2->pos = 0;
+			snprintf_num(U32, sb1, ctx->usubvals[i]);
+			snprintf_num(S32, sb2, ctx->ssubvals[i]);
+			printf("SUBSEED #%d: u32=%-10s s32=%-10s\n", i, sb1->buf, sb2->buf);
+		}
+	}
+}
+
+/* Generate valid ranges from upper/lower seeds */
+static int gen_ranges(struct ctx *ctx)
+{
+	int i, j, cnt = 0;
+
+	for (i = 0; i < ctx->val_cnt; i++) {
+		for (j = i; j < ctx->val_cnt; j++) {
+			if (env.verbosity >= VERBOSE_SUPER) {
+				DEFINE_STRBUF(sb1, 256);
+				DEFINE_STRBUF(sb2, 256);
+
+				sb1->pos = sb2->pos = 0;
+				snprintf_range(U64, sb1, range(U64, ctx->uvals[i], ctx->uvals[j]));
+				snprintf_range(S64, sb2, range(S64, ctx->svals[i], ctx->svals[j]));
+				printf("RANGE #%d: u64=%-40s s64=%-40s\n", cnt, sb1->buf, sb2->buf);
+			}
+			cnt++;
+		}
+	}
+	ctx->range_cnt = cnt;
+
+	ctx->uranges = calloc(ctx->range_cnt, sizeof(*ctx->uranges));
+	if (!ASSERT_OK_PTR(ctx->uranges, "uranges_calloc"))
+		return -EINVAL;
+	ctx->sranges = calloc(ctx->range_cnt, sizeof(*ctx->sranges));
+	if (!ASSERT_OK_PTR(ctx->sranges, "sranges_calloc"))
+		return -EINVAL;
+
+	cnt = 0;
+	for (i = 0; i < ctx->val_cnt; i++) {
+		for (j = i; j < ctx->val_cnt; j++) {
+			ctx->uranges[cnt] = range(U64, ctx->uvals[i], ctx->uvals[j]);
+			ctx->sranges[cnt] = range(S64, ctx->svals[i], ctx->svals[j]);
+			cnt++;
+		}
+	}
+
+	cnt = 0;
+	for (i = 0; i < ctx->subval_cnt; i++) {
+		for (j = i; j < ctx->subval_cnt; j++) {
+			if (env.verbosity >= VERBOSE_SUPER) {
+				DEFINE_STRBUF(sb1, 256);
+				DEFINE_STRBUF(sb2, 256);
+
+				sb1->pos = sb2->pos = 0;
+				snprintf_range(U32, sb1, range(U32, ctx->usubvals[i], ctx->usubvals[j]));
+				snprintf_range(S32, sb2, range(S32, ctx->ssubvals[i], ctx->ssubvals[j]));
+				printf("SUBRANGE #%d: u32=%-20s s32=%-20s\n", cnt, sb1->buf, sb2->buf);
+			}
+			cnt++;
+		}
+	}
+	ctx->subrange_cnt = cnt;
+
+	ctx->usubranges = calloc(ctx->subrange_cnt, sizeof(*ctx->usubranges));
+	if (!ASSERT_OK_PTR(ctx->usubranges, "usubranges_calloc"))
+		return -EINVAL;
+	ctx->ssubranges = calloc(ctx->subrange_cnt, sizeof(*ctx->ssubranges));
+	if (!ASSERT_OK_PTR(ctx->ssubranges, "ssubranges_calloc"))
+		return -EINVAL;
+
+	cnt = 0;
+	for (i = 0; i < ctx->subval_cnt; i++) {
+		for (j = i; j < ctx->subval_cnt; j++) {
+			ctx->usubranges[cnt] = range(U32, ctx->usubvals[i], ctx->usubvals[j]);
+			ctx->ssubranges[cnt] = range(S32, ctx->ssubvals[i], ctx->ssubvals[j]);
+			cnt++;
+		}
+	}
+
+	return 0;
+}
+
+static int parse_env_vars(struct ctx *ctx)
+{
+	const char *s;
+
+	if ((s = getenv("REG_BOUNDS_MAX_FAILURE_CNT"))) {
+		errno = 0;
+		ctx->max_failure_cnt = strtol(s, NULL, 10);
+		if (errno || ctx->max_failure_cnt < 0) {
+			ASSERT_OK(-errno, "REG_BOUNDS_MAX_FAILURE_CNT");
+			return -EINVAL;
+		}
+	}
+
+	if ((s = getenv("REG_BOUNDS_RAND_CASE_CNT"))) {
+		errno = 0;
+		ctx->rand_case_cnt = strtol(s, NULL, 10);
+		if (errno || ctx->rand_case_cnt < 0) {
+			ASSERT_OK(-errno, "REG_BOUNDS_RAND_CASE_CNT");
+			return -EINVAL;
+		}
+	}
+
+	if ((s = getenv("REG_BOUNDS_RAND_SEED"))) {
+		errno = 0;
+		ctx->rand_seed = strtoul(s, NULL, 10);
+		if (errno) {
+			ASSERT_OK(-errno, "REG_BOUNDS_RAND_SEED");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int prepare_gen_tests(struct ctx *ctx)
+{
+	const char *s;
+	int err;
+
+	if (!(s = getenv("SLOW_TESTS")) || strcmp(s, "1") != 0) {
+		test__skip();
+		return -ENOTSUP;
+	}
+
+	err = parse_env_vars(ctx);
+	if (err)
+		return err;
+
+	gen_vals(ctx);
+	err = gen_ranges(ctx);
+	if (err) {
+		ASSERT_OK(err, "gen_ranges");
+		return err;
+	}
+
+	return 0;
+}
+
+/* Go over generated constants and ranges and validate various supported
+ * combinations of them
+ */
+static void validate_gen_range_vs_const_64(enum num_t init_t, enum num_t cond_t)
+{
+	struct ctx ctx;
+	struct range rconst;
+	const struct range *ranges;
+	const u64 *vals;
+	int i, j;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	if (prepare_gen_tests(&ctx))
+		goto cleanup;
+
+	ranges = init_t == U64 ? ctx.uranges : ctx.sranges;
+	vals = init_t == U64 ? ctx.uvals : (const u64 *)ctx.svals;
+
+	ctx.total_case_cnt = (last_op - first_op + 1) * (2 * ctx.range_cnt * ctx.val_cnt);
+	ctx.start_ns = get_time_ns();
+	snprintf(ctx.progress_ctx, sizeof(ctx.progress_ctx),
+		 "RANGE x CONST, %s -> %s",
+		 t_str(init_t), t_str(cond_t));
+
+	for (i = 0; i < ctx.val_cnt; i++) {
+		for (j = 0; j < ctx.range_cnt; j++) {
+			rconst = range(init_t, vals[i], vals[i]);
+
+			/* (u64|s64)(<range> x <const>) */
+			if (verify_case(&ctx, init_t, cond_t, ranges[j], rconst))
+				goto cleanup;
+			/* (u64|s64)(<const> x <range>) */
+			if (verify_case(&ctx, init_t, cond_t, rconst, ranges[j]))
+				goto cleanup;
+		}
+	}
+
+cleanup:
+	cleanup_ctx(&ctx);
+}
+
+static void validate_gen_range_vs_const_32(enum num_t init_t, enum num_t cond_t)
+{
+	struct ctx ctx;
+	struct range rconst;
+	const struct range *ranges;
+	const u32 *vals;
+	int i, j;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	if (prepare_gen_tests(&ctx))
+		goto cleanup;
+
+	ranges = init_t == U32 ? ctx.usubranges : ctx.ssubranges;
+	vals = init_t == U32 ? ctx.usubvals : (const u32 *)ctx.ssubvals;
+
+	ctx.total_case_cnt = (last_op - first_op + 1) * (2 * ctx.subrange_cnt * ctx.subval_cnt);
+	ctx.start_ns = get_time_ns();
+	snprintf(ctx.progress_ctx, sizeof(ctx.progress_ctx),
+		 "RANGE x CONST, %s -> %s",
+		 t_str(init_t), t_str(cond_t));
+
+	for (i = 0; i < ctx.subval_cnt; i++) {
+		for (j = 0; j < ctx.subrange_cnt; j++) {
+			rconst = range(init_t, vals[i], vals[i]);
+
+			/* (u32|s32)(<range> x <const>) */
+			if (verify_case(&ctx, init_t, cond_t, ranges[j], rconst))
+				goto cleanup;
+			/* (u32|s32)(<const> x <range>) */
+			if (verify_case(&ctx, init_t, cond_t, rconst, ranges[j]))
+				goto cleanup;
+		}
+	}
+
+cleanup:
+	cleanup_ctx(&ctx);
+}
+
+static void validate_gen_range_vs_range(enum num_t init_t, enum num_t cond_t)
+{
+	struct ctx ctx;
+	const struct range *ranges;
+	int i, j, rcnt;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	if (prepare_gen_tests(&ctx))
+		goto cleanup;
+
+	switch (init_t)
+	{
+	case U64:
+		ranges = ctx.uranges;
+		rcnt = ctx.range_cnt;
+		break;
+	case U32:
+		ranges = ctx.usubranges;
+		rcnt = ctx.subrange_cnt;
+		break;
+	case S64:
+		ranges = ctx.sranges;
+		rcnt = ctx.range_cnt;
+		break;
+	case S32:
+		ranges = ctx.ssubranges;
+		rcnt = ctx.subrange_cnt;
+		break;
+	default:
+		printf("validate_gen_range_vs_range!\n");
+		exit(1);
+	}
+
+	ctx.total_case_cnt = (last_op - first_op + 1) * (2 * rcnt * (rcnt + 1) / 2);
+	ctx.start_ns = get_time_ns();
+	snprintf(ctx.progress_ctx, sizeof(ctx.progress_ctx),
+		 "RANGE x RANGE, %s -> %s",
+		 t_str(init_t), t_str(cond_t));
+
+	for (i = 0; i < rcnt; i++) {
+		for (j = i; j < rcnt; j++) {
+			/* (<range> x <range>) */
+			if (verify_case(&ctx, init_t, cond_t, ranges[i], ranges[j]))
+				goto cleanup;
+			if (verify_case(&ctx, init_t, cond_t, ranges[j], ranges[i]))
+				goto cleanup;
+		}
+	}
+
+cleanup:
+	cleanup_ctx(&ctx);
+}
+
+/* Go over thousands of test cases generated from initial seed values.
+ * Given this take a long time, guard this begind SLOW_TESTS=1 envvar. If
+ * envvar is not set, this test is skipped during test_progs testing.
+ *
+ * We split this up into smaller subsets based on initialization and
+ * conditiona numeric domains to get an easy parallelization with test_progs'
+ * -j argument.
+ */
+
+/* RANGE x CONST, U64 initial range */
+void test_reg_bounds_gen_consts_u64_u64(void) { validate_gen_range_vs_const_64(U64, U64); }
+void test_reg_bounds_gen_consts_u64_s64(void) { validate_gen_range_vs_const_64(U64, S64); }
+void test_reg_bounds_gen_consts_u64_u32(void) { validate_gen_range_vs_const_64(U64, U32); }
+void test_reg_bounds_gen_consts_u64_s32(void) { validate_gen_range_vs_const_64(U64, S32); }
+/* RANGE x CONST, S64 initial range */
+void test_reg_bounds_gen_consts_s64_u64(void) { validate_gen_range_vs_const_64(S64, U64); }
+void test_reg_bounds_gen_consts_s64_s64(void) { validate_gen_range_vs_const_64(S64, S64); }
+void test_reg_bounds_gen_consts_s64_u32(void) { validate_gen_range_vs_const_64(S64, U32); }
+void test_reg_bounds_gen_consts_s64_s32(void) { validate_gen_range_vs_const_64(S64, S32); }
+/* RANGE x CONST, U32 initial range */
+void test_reg_bounds_gen_consts_u32_u64(void) { validate_gen_range_vs_const_32(U32, U64); }
+void test_reg_bounds_gen_consts_u32_s64(void) { validate_gen_range_vs_const_32(U32, S64); }
+void test_reg_bounds_gen_consts_u32_u32(void) { validate_gen_range_vs_const_32(U32, U32); }
+void test_reg_bounds_gen_consts_u32_s32(void) { validate_gen_range_vs_const_32(U32, S32); }
+/* RANGE x CONST, S32 initial range */
+void test_reg_bounds_gen_consts_s32_u64(void) { validate_gen_range_vs_const_32(S32, U64); }
+void test_reg_bounds_gen_consts_s32_s64(void) { validate_gen_range_vs_const_32(S32, S64); }
+void test_reg_bounds_gen_consts_s32_u32(void) { validate_gen_range_vs_const_32(S32, U32); }
+void test_reg_bounds_gen_consts_s32_s32(void) { validate_gen_range_vs_const_32(S32, S32); }
+
+/* RANGE x RANGE, U64 initial range */
+void test_reg_bounds_gen_ranges_u64_u64(void) { validate_gen_range_vs_range(U64, U64); }
+void test_reg_bounds_gen_ranges_u64_s64(void) { validate_gen_range_vs_range(U64, S64); }
+void test_reg_bounds_gen_ranges_u64_u32(void) { validate_gen_range_vs_range(U64, U32); }
+void test_reg_bounds_gen_ranges_u64_s32(void) { validate_gen_range_vs_range(U64, S32); }
+/* RANGE x RANGE, S64 initial range */
+void test_reg_bounds_gen_ranges_s64_u64(void) { validate_gen_range_vs_range(S64, U64); }
+void test_reg_bounds_gen_ranges_s64_s64(void) { validate_gen_range_vs_range(S64, S64); }
+void test_reg_bounds_gen_ranges_s64_u32(void) { validate_gen_range_vs_range(S64, U32); }
+void test_reg_bounds_gen_ranges_s64_s32(void) { validate_gen_range_vs_range(S64, S32); }
+/* RANGE x RANGE, U32 initial range */
+void test_reg_bounds_gen_ranges_u32_u64(void) { validate_gen_range_vs_range(U32, U64); }
+void test_reg_bounds_gen_ranges_u32_s64(void) { validate_gen_range_vs_range(U32, S64); }
+void test_reg_bounds_gen_ranges_u32_u32(void) { validate_gen_range_vs_range(U32, U32); }
+void test_reg_bounds_gen_ranges_u32_s32(void) { validate_gen_range_vs_range(U32, S32); }
+/* RANGE x RANGE, S32 initial range */
+void test_reg_bounds_gen_ranges_s32_u64(void) { validate_gen_range_vs_range(S32, U64); }
+void test_reg_bounds_gen_ranges_s32_s64(void) { validate_gen_range_vs_range(S32, S64); }
+void test_reg_bounds_gen_ranges_s32_u32(void) { validate_gen_range_vs_range(S32, U32); }
+void test_reg_bounds_gen_ranges_s32_s32(void) { validate_gen_range_vs_range(S32, S32); }
+
+#define DEFAULT_RAND_CASE_CNT 100
+
+#define RAND_21BIT_MASK ((1 << 22) - 1)
+
+static u64 rand_u64()
+{
+	/* RAND_MAX is guaranteed to be at least 1<<15, but in practice it
+	 * seems to be 1<<31, so we need to call it thrice to get full u64;
+	 * we'll use rougly equal split: 22 + 21 + 21 bits
+	 */
+	return ((u64)random() << 42) |
+	       (((u64)random() & RAND_21BIT_MASK) << 21) |
+	       (random() & RAND_21BIT_MASK);
+}
+
+static u64 rand_const(enum num_t t)
+{
+	return cast_t(t, rand_u64());
+}
+
+static struct range rand_range(enum num_t t)
+{
+	u64 x = rand_const(t), y = rand_const(t);
+
+	return range(t, min_t(t, x, y), max_t(t, x, y));
+}
+
+static void validate_rand_ranges(enum num_t init_t, enum num_t cond_t, bool const_range)
+{
+	struct ctx ctx;
+	struct range range1, range2;
+	int err, i;
+	u64 t;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	err = parse_env_vars(&ctx);
+	if (err) {
+		ASSERT_OK(err, "parse_env_vars");
+		return;
+	}
+
+	if (ctx.rand_case_cnt == 0)
+		ctx.rand_case_cnt = DEFAULT_RAND_CASE_CNT;
+	if (ctx.rand_seed == 0)
+		ctx.rand_seed = (unsigned)get_time_ns();
+
+	srandom(ctx.rand_seed);
+
+	ctx.total_case_cnt = (last_op - first_op + 1) * (2 * ctx.rand_case_cnt);
+	ctx.start_ns = get_time_ns();
+	snprintf(ctx.progress_ctx, sizeof(ctx.progress_ctx),
+		 "[RANDOM SEED %u] RANGE x %s, %s -> %s",
+		 ctx.rand_seed, const_range ? "CONST" : "RANGE",
+		 t_str(init_t), t_str(cond_t));
+
+	for (i = 0; i < ctx.rand_case_cnt; i++) {
+		range1 = rand_range(init_t);
+		if (const_range) {
+			t = rand_const(init_t);
+			range2 = range(init_t, t, t);
+		} else {
+			range2 = rand_range(init_t);
+		}
+
+		/* <range1> x <range2> */
+		if (verify_case_opt(&ctx, init_t, cond_t, range1, range2, false /* !is_subtest */))
+			goto cleanup;
+		/* <range2> x <range1> */
+		if (verify_case_opt(&ctx, init_t, cond_t, range2, range1, false /* !is_subtest */))
+			goto cleanup;
+	}
+
+cleanup:
+	/* make sure we report random seed for reproducing */
+	ASSERT_TRUE(true, ctx.progress_ctx);
+	cleanup_ctx(&ctx);
+}
+
+/* [RANDOM] RANGE x CONST, U64 initial range */
+void test_reg_bounds_rand_consts_u64_u64(void) { validate_rand_ranges(U64, U64, true /* const */); }
+void test_reg_bounds_rand_consts_u64_s64(void) { validate_rand_ranges(U64, S64, true /* const */); }
+void test_reg_bounds_rand_consts_u64_u32(void) { validate_rand_ranges(U64, U32, true /* const */); }
+void test_reg_bounds_rand_consts_u64_s32(void) { validate_rand_ranges(U64, S32, true /* const */); }
+/* [RANDOM] RANGE x CONST, S64 initial range */
+void test_reg_bounds_rand_consts_s64_u64(void) { validate_rand_ranges(S64, U64, true /* const */); }
+void test_reg_bounds_rand_consts_s64_s64(void) { validate_rand_ranges(S64, S64, true /* const */); }
+void test_reg_bounds_rand_consts_s64_u32(void) { validate_rand_ranges(S64, U32, true /* const */); }
+void test_reg_bounds_rand_consts_s64_s32(void) { validate_rand_ranges(S64, S32, true /* const */); }
+/* [RANDOM] RANGE x CONST, U32 initial range */
+void test_reg_bounds_rand_consts_u32_u64(void) { validate_rand_ranges(U32, U64, true /* const */); }
+void test_reg_bounds_rand_consts_u32_s64(void) { validate_rand_ranges(U32, S64, true /* const */); }
+void test_reg_bounds_rand_consts_u32_u32(void) { validate_rand_ranges(U32, U32, true /* const */); }
+void test_reg_bounds_rand_consts_u32_s32(void) { validate_rand_ranges(U32, S32, true /* const */); }
+/* [RANDOM] RANGE x CONST, S32 initial range */
+void test_reg_bounds_rand_consts_s32_u64(void) { validate_rand_ranges(S32, U64, true /* const */); }
+void test_reg_bounds_rand_consts_s32_s64(void) { validate_rand_ranges(S32, S64, true /* const */); }
+void test_reg_bounds_rand_consts_s32_u32(void) { validate_rand_ranges(S32, U32, true /* const */); }
+void test_reg_bounds_rand_consts_s32_s32(void) { validate_rand_ranges(S32, S32, true /* const */); }
+
+/* [RANDOM] RANGE x RANGE, U64 initial range */
+void test_reg_bounds_rand_ranges_u64_u64(void) { validate_rand_ranges(U64, U64, false /* range */); }
+void test_reg_bounds_rand_ranges_u64_s64(void) { validate_rand_ranges(U64, S64, false /* range */); }
+void test_reg_bounds_rand_ranges_u64_u32(void) { validate_rand_ranges(U64, U32, false /* range */); }
+void test_reg_bounds_rand_ranges_u64_s32(void) { validate_rand_ranges(U64, S32, false /* range */); }
+/* [RANDOM] RANGE x RANGE, S64 initial range */
+void test_reg_bounds_rand_ranges_s64_u64(void) { validate_rand_ranges(S64, U64, false /* range */); }
+void test_reg_bounds_rand_ranges_s64_s64(void) { validate_rand_ranges(S64, S64, false /* range */); }
+void test_reg_bounds_rand_ranges_s64_u32(void) { validate_rand_ranges(S64, U32, false /* range */); }
+void test_reg_bounds_rand_ranges_s64_s32(void) { validate_rand_ranges(S64, S32, false /* range */); }
+/* [RANDOM] RANGE x RANGE, U32 initial range */
+void test_reg_bounds_rand_ranges_u32_u64(void) { validate_rand_ranges(U32, U64, false /* range */); }
+void test_reg_bounds_rand_ranges_u32_s64(void) { validate_rand_ranges(U32, S64, false /* range */); }
+void test_reg_bounds_rand_ranges_u32_u32(void) { validate_rand_ranges(U32, U32, false /* range */); }
+void test_reg_bounds_rand_ranges_u32_s32(void) { validate_rand_ranges(U32, S32, false /* range */); }
+/* [RANDOM] RANGE x RANGE, S32 initial range */
+void test_reg_bounds_rand_ranges_s32_u64(void) { validate_rand_ranges(S32, U64, false /* range */); }
+void test_reg_bounds_rand_ranges_s32_s64(void) { validate_rand_ranges(S32, S64, false /* range */); }
+void test_reg_bounds_rand_ranges_s32_u32(void) { validate_rand_ranges(S32, U32, false /* range */); }
+void test_reg_bounds_rand_ranges_s32_s32(void) { validate_rand_ranges(S32, S32, false /* range */); }
+
+/* A set of hard-coded "interesting" cases to validate as part of normal
+ * test_progs test runs
+ */
+static struct subtest_case crafted_cases[] = {
+	{U64, U64, {0, 0xffffffff}, {0, 0}},
+	{U64, U64, {0, 0x80000000}, {0, 0}},
+	{U64, U64, {0x100000000ULL, 0x100000100ULL}, {0, 0}},
+	{U64, U64, {0x100000000ULL, 0x180000000ULL}, {0, 0}},
+	{U64, U64, {0x100000000ULL, 0x1ffffff00ULL}, {0, 0}},
+	{U64, U64, {0x100000000ULL, 0x1ffffff01ULL}, {0, 0}},
+	{U64, U64, {0x100000000ULL, 0x1fffffffeULL}, {0, 0}},
+	{U64, U64, {0x100000001ULL, 0x1000000ffULL}, {0, 0}},
+
+	/* single point overlap, interesting BPF_EQ and BPF_NE interactions */
+	{U64, U64, {0, 1}, {1, 0x80000000}},
+	{U64, S64, {0, 1}, {1, 0x80000000}},
+	{U64, U32, {0, 1}, {1, 0x80000000}},
+	{U64, S32, {0, 1}, {1, 0x80000000}},
+
+	{U64, S64, {0, 0xffffffff00000000ULL}, {0, 0}},
+	{U64, S64, {0x7fffffffffffffffULL, 0xffffffff00000000ULL}, {0, 0}},
+	{U64, S64, {0x7fffffff00000001ULL, 0xffffffff00000000ULL}, {0, 0}},
+	{U64, S64, {0, 0xffffffffULL}, {1, 1}},
+	{U64, S64, {0, 0xffffffffULL}, {0x7fffffff, 0x7fffffff}},
+
+	{U64, U32, {0, 0x100000000}, {0, 0}},
+	{U64, U32, {0xfffffffe, 0x100000000}, {0x80000000, 0x80000000}},
+
+	{U64, S32, {0, 0xffffffff00000000ULL}, {0, 0}},
+	/* these are tricky cases where lower 32 bits allow to tighten 64
+	 * bit boundaries based on tightened lower 32 bit boundaries
+	 */
+	{U64, S32, {0, 0x0ffffffffULL}, {0, 0}},
+	{U64, S32, {0, 0x100000000ULL}, {0, 0}},
+	{U64, S32, {0, 0x100000001ULL}, {0, 0}},
+	{U64, S32, {0, 0x180000000ULL}, {0, 0}},
+	{U64, S32, {0, 0x17fffffffULL}, {0, 0}},
+	{U64, S32, {0, 0x180000001ULL}, {0, 0}},
+
+	/* verifier knows about [-1, 0] range for s32 for this case already */
+	{S64, S64, {0xffffffffffffffffULL, 0}, {0xffffffff00000000ULL, 0xffffffff00000000ULL}},
+	/* but didn't know about these cases initially */
+	{U64, U64, {0xffffffff, 0x100000000ULL}, {0, 0}}, /* s32: [-1, 0] */
+	{U64, U64, {0xffffffff, 0x100000001ULL}, {0, 0}}, /* s32: [-1, 1] */
+
+	/* longer convergence case: learning from u64 -> s64 -> u64 -> u32,
+	 * arriving at u32: [1, U32_MAX] (instead of more pessimistic [0, U32_MAX])
+	 */
+	{S64, U64, {0xffffffff00000001ULL, 0}, {0xffffffff00000000ULL, 0xffffffff00000000ULL}},
+
+	{U32, U32, {1, U32_MAX}, {0, 0}},
+
+	{U32, S32, {0, U32_MAX}, {U32_MAX, U32_MAX}},
+
+	{S32, U64, {(u32)S32_MIN, (u32)S32_MIN}, {(u32)(s32)-255, 0}},
+	{S32, S64, {(u32)S32_MIN, (u32)(s32)-255}, {(u32)(s32)-2, 0}},
+	{S32, S64, {0, 1}, {(u32)S32_MIN, (u32)S32_MIN}},
+	{S32, U32, {(u32)S32_MIN, (u32)S32_MIN}, {(u32)S32_MIN, (u32)S32_MIN}},
+
+	/* edge overlap testings for BPF_NE */
+	{U64, U64, {0, U64_MAX}, {U64_MAX, U64_MAX}},
+	{U64, U64, {0, U64_MAX}, {0, 0}},
+	{S64, U64, {S64_MIN, 0}, {S64_MIN, S64_MIN}},
+	{S64, U64, {S64_MIN, 0}, {0, 0}},
+	{S64, U64, {S64_MIN, S64_MAX}, {S64_MAX, S64_MAX}},
+	{U32, U32, {0, U32_MAX}, {0, 0}},
+	{U32, U32, {0, U32_MAX}, {U32_MAX, U32_MAX}},
+	{S32, U32, {(u32)S32_MIN, 0}, {0, 0}},
+	{S32, U32, {(u32)S32_MIN, 0}, {(u32)S32_MIN, (u32)S32_MIN}},
+	{S32, U32, {(u32)S32_MIN, S32_MAX}, {S32_MAX, S32_MAX}},
+};
+
+/* Go over crafted hard-coded cases. This is fast, so we do it as part of
+ * normal test_progs run.
+ */
+void test_reg_bounds_crafted(void)
+{
+	struct ctx ctx;
+	int i;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	for (i = 0; i < ARRAY_SIZE(crafted_cases); i++) {
+		struct subtest_case *c = &crafted_cases[i];
+
+		verify_case(&ctx, c->init_t, c->cond_t, c->x, c->y);
+		verify_case(&ctx, c->init_t, c->cond_t, c->y, c->x);
+	}
+
+	cleanup_ctx(&ctx);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index f75f84d0b3d7..77e26ecffa9d 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -524,6 +524,244 @@ out:
 	test_sockmap_pass_prog__destroy(pass);
 }
 
+static void test_sockmap_unconnected_unix(void)
+{
+	int err, map, stream = 0, dgram = 0, zero = 0;
+	struct test_sockmap_pass_prog *skel;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	map = bpf_map__fd(skel->maps.sock_map_rx);
+
+	stream = xsocket(AF_UNIX, SOCK_STREAM, 0);
+	if (stream < 0)
+		return;
+
+	dgram = xsocket(AF_UNIX, SOCK_DGRAM, 0);
+	if (dgram < 0) {
+		close(stream);
+		return;
+	}
+
+	err = bpf_map_update_elem(map, &zero, &stream, BPF_ANY);
+	ASSERT_ERR(err, "bpf_map_update_elem(stream)");
+
+	err = bpf_map_update_elem(map, &zero, &dgram, BPF_ANY);
+	ASSERT_OK(err, "bpf_map_update_elem(dgram)");
+
+	close(stream);
+	close(dgram);
+}
+
+static void test_sockmap_many_socket(void)
+{
+	struct test_sockmap_pass_prog *skel;
+	int stream[2], dgram, udp, tcp;
+	int i, err, map, entry = 0;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	map = bpf_map__fd(skel->maps.sock_map_rx);
+
+	dgram = xsocket(AF_UNIX, SOCK_DGRAM, 0);
+	if (dgram < 0) {
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	tcp = connected_socket_v4();
+	if (!ASSERT_GE(tcp, 0, "connected_socket_v4")) {
+		close(dgram);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0);
+	if (udp < 0) {
+		close(dgram);
+		close(tcp);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	err = socketpair(AF_UNIX, SOCK_STREAM, 0, stream);
+	ASSERT_OK(err, "socketpair(af_unix, sock_stream)");
+	if (err)
+		goto out;
+
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map, &entry, &stream[0], BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(stream)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map, &entry, &dgram, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(dgram)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map, &entry, &udp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(udp)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map, &entry, &tcp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(tcp)");
+	}
+	for (entry--; entry >= 0; entry--) {
+		err = bpf_map_delete_elem(map, &entry);
+		ASSERT_OK(err, "bpf_map_delete_elem(entry)");
+	}
+
+	close(stream[0]);
+	close(stream[1]);
+out:
+	close(dgram);
+	close(tcp);
+	close(udp);
+	test_sockmap_pass_prog__destroy(skel);
+}
+
+static void test_sockmap_many_maps(void)
+{
+	struct test_sockmap_pass_prog *skel;
+	int stream[2], dgram, udp, tcp;
+	int i, err, map[2], entry = 0;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	map[0] = bpf_map__fd(skel->maps.sock_map_rx);
+	map[1] = bpf_map__fd(skel->maps.sock_map_tx);
+
+	dgram = xsocket(AF_UNIX, SOCK_DGRAM, 0);
+	if (dgram < 0) {
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	tcp = connected_socket_v4();
+	if (!ASSERT_GE(tcp, 0, "connected_socket_v4")) {
+		close(dgram);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0);
+	if (udp < 0) {
+		close(dgram);
+		close(tcp);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	err = socketpair(AF_UNIX, SOCK_STREAM, 0, stream);
+	ASSERT_OK(err, "socketpair(af_unix, sock_stream)");
+	if (err)
+		goto out;
+
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map[i], &entry, &stream[0], BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(stream)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map[i], &entry, &dgram, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(dgram)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map[i], &entry, &udp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(udp)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map[i], &entry, &tcp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(tcp)");
+	}
+	for (entry--; entry >= 0; entry--) {
+		err = bpf_map_delete_elem(map[1], &entry);
+		entry--;
+		ASSERT_OK(err, "bpf_map_delete_elem(entry)");
+		err = bpf_map_delete_elem(map[0], &entry);
+		ASSERT_OK(err, "bpf_map_delete_elem(entry)");
+	}
+
+	close(stream[0]);
+	close(stream[1]);
+out:
+	close(dgram);
+	close(tcp);
+	close(udp);
+	test_sockmap_pass_prog__destroy(skel);
+}
+
+static void test_sockmap_same_sock(void)
+{
+	struct test_sockmap_pass_prog *skel;
+	int stream[2], dgram, udp, tcp;
+	int i, err, map, zero = 0;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	map = bpf_map__fd(skel->maps.sock_map_rx);
+
+	dgram = xsocket(AF_UNIX, SOCK_DGRAM, 0);
+	if (dgram < 0) {
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	tcp = connected_socket_v4();
+	if (!ASSERT_GE(tcp, 0, "connected_socket_v4")) {
+		close(dgram);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0);
+	if (udp < 0) {
+		close(dgram);
+		close(tcp);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	err = socketpair(AF_UNIX, SOCK_STREAM, 0, stream);
+	ASSERT_OK(err, "socketpair(af_unix, sock_stream)");
+	if (err)
+		goto out;
+
+	for (i = 0; i < 2; i++) {
+		err = bpf_map_update_elem(map, &zero, &stream[0], BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(stream)");
+	}
+	for (i = 0; i < 2; i++) {
+		err = bpf_map_update_elem(map, &zero, &dgram, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(dgram)");
+	}
+	for (i = 0; i < 2; i++) {
+		err = bpf_map_update_elem(map, &zero, &udp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(udp)");
+	}
+	for (i = 0; i < 2; i++) {
+		err = bpf_map_update_elem(map, &zero, &tcp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(tcp)");
+	}
+
+	err = bpf_map_delete_elem(map, &zero);
+	ASSERT_OK(err, "bpf_map_delete_elem(entry)");
+
+	close(stream[0]);
+	close(stream[1]);
+out:
+	close(dgram);
+	close(tcp);
+	close(udp);
+	test_sockmap_pass_prog__destroy(skel);
+}
+
 void test_sockmap_basic(void)
 {
 	if (test__start_subtest("sockmap create_update_free"))
@@ -566,4 +804,12 @@ void test_sockmap_basic(void)
 		test_sockmap_skb_verdict_fionread(false);
 	if (test__start_subtest("sockmap skb_verdict msg_f_peek"))
 		test_sockmap_skb_verdict_peek();
+	if (test__start_subtest("sockmap unconnected af_unix"))
+		test_sockmap_unconnected_unix();
+	if (test__start_subtest("sockmap one socket to many map entries"))
+		test_sockmap_many_socket();
+	if (test__start_subtest("sockmap one socket to many maps"))
+		test_sockmap_many_maps();
+	if (test__start_subtest("sockmap same socket replace"))
+		test_sockmap_same_sock();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index a934d430c20c..a92807bfcd13 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -1337,7 +1337,8 @@ static void test_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
 }
 
 static void pairs_redir_to_connected(int cli0, int peer0, int cli1, int peer1,
-				     int sock_mapfd, int verd_mapfd, enum redir_mode mode)
+				     int sock_mapfd, int nop_mapfd,
+				     int verd_mapfd, enum redir_mode mode)
 {
 	const char *log_prefix = redir_mode_str(mode);
 	unsigned int pass;
@@ -1351,6 +1352,12 @@ static void pairs_redir_to_connected(int cli0, int peer0, int cli1, int peer1,
 	if (err)
 		return;
 
+	if (nop_mapfd >= 0) {
+		err = add_to_sockmap(nop_mapfd, cli0, cli1);
+		if (err)
+			return;
+	}
+
 	n = write(cli1, "a", 1);
 	if (n < 0)
 		FAIL_ERRNO("%s: write", log_prefix);
@@ -1387,7 +1394,7 @@ static void unix_redir_to_connected(int sotype, int sock_mapfd,
 		goto close0;
 	c1 = sfd[0], p1 = sfd[1];
 
-	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, verd_mapfd, mode);
+	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, -1, verd_mapfd, mode);
 
 	xclose(c1);
 	xclose(p1);
@@ -1677,7 +1684,7 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd,
 	if (err)
 		goto close_cli0;
 
-	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, verd_mapfd, mode);
+	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, -1, verd_mapfd, mode);
 
 	xclose(c1);
 	xclose(p1);
@@ -1735,7 +1742,7 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd,
 	if (err)
 		goto close;
 
-	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, verd_mapfd, mode);
+	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, -1, verd_mapfd, mode);
 
 	xclose(c1);
 	xclose(p1);
@@ -1770,8 +1777,10 @@ static void inet_unix_skb_redir_to_connected(struct test_sockmap_listen *skel,
 	xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
 }
 
-static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd,
-					int verd_mapfd, enum redir_mode mode)
+static void unix_inet_redir_to_connected(int family, int type,
+					int sock_mapfd, int nop_mapfd,
+					int verd_mapfd,
+					enum redir_mode mode)
 {
 	int c0, c1, p0, p1;
 	int sfd[2];
@@ -1785,7 +1794,8 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd,
 		goto close_cli0;
 	c1 = sfd[0], p1 = sfd[1];
 
-	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, verd_mapfd, mode);
+	pairs_redir_to_connected(c0, p0, c1, p1,
+				 sock_mapfd, nop_mapfd, verd_mapfd, mode);
 
 	xclose(c1);
 	xclose(p1);
@@ -1799,6 +1809,7 @@ static void unix_inet_skb_redir_to_connected(struct test_sockmap_listen *skel,
 					    struct bpf_map *inner_map, int family)
 {
 	int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+	int nop_map = bpf_map__fd(skel->maps.nop_map);
 	int verdict_map = bpf_map__fd(skel->maps.verdict_map);
 	int sock_map = bpf_map__fd(inner_map);
 	int err;
@@ -1808,14 +1819,32 @@ static void unix_inet_skb_redir_to_connected(struct test_sockmap_listen *skel,
 		return;
 
 	skel->bss->test_ingress = false;
-	unix_inet_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
+	unix_inet_redir_to_connected(family, SOCK_DGRAM,
+				     sock_map, -1, verdict_map,
 				     REDIR_EGRESS);
-	unix_inet_redir_to_connected(family, SOCK_STREAM, sock_map, verdict_map,
+	unix_inet_redir_to_connected(family, SOCK_DGRAM,
+				     sock_map, -1, verdict_map,
+				     REDIR_EGRESS);
+
+	unix_inet_redir_to_connected(family, SOCK_DGRAM,
+				     sock_map, nop_map, verdict_map,
+				     REDIR_EGRESS);
+	unix_inet_redir_to_connected(family, SOCK_STREAM,
+				     sock_map, nop_map, verdict_map,
 				     REDIR_EGRESS);
 	skel->bss->test_ingress = true;
-	unix_inet_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
+	unix_inet_redir_to_connected(family, SOCK_DGRAM,
+				     sock_map, -1, verdict_map,
+				     REDIR_INGRESS);
+	unix_inet_redir_to_connected(family, SOCK_STREAM,
+				     sock_map, -1, verdict_map,
+				     REDIR_INGRESS);
+
+	unix_inet_redir_to_connected(family, SOCK_DGRAM,
+				     sock_map, nop_map, verdict_map,
 				     REDIR_INGRESS);
-	unix_inet_redir_to_connected(family, SOCK_STREAM, sock_map, verdict_map,
+	unix_inet_redir_to_connected(family, SOCK_STREAM,
+				     sock_map, nop_map, verdict_map,
 				     REDIR_INGRESS);
 
 	xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
diff --git a/tools/testing/selftests/bpf/prog_tests/spin_lock.c b/tools/testing/selftests/bpf/prog_tests/spin_lock.c
index f29c08d93beb..18d451be57c8 100644
--- a/tools/testing/selftests/bpf/prog_tests/spin_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/spin_lock.c
@@ -13,22 +13,22 @@ static struct {
 	const char *err_msg;
 } spin_lock_fail_tests[] = {
 	{ "lock_id_kptr_preserve",
-	  "5: (bf) r1 = r0                       ; R0_w=ptr_foo(id=2,ref_obj_id=2,off=0,imm=0) "
-	  "R1_w=ptr_foo(id=2,ref_obj_id=2,off=0,imm=0) refs=2\n6: (85) call bpf_this_cpu_ptr#154\n"
+	  "5: (bf) r1 = r0                       ; R0_w=ptr_foo(id=2,ref_obj_id=2) "
+	  "R1_w=ptr_foo(id=2,ref_obj_id=2) refs=2\n6: (85) call bpf_this_cpu_ptr#154\n"
 	  "R1 type=ptr_ expected=percpu_ptr_" },
 	{ "lock_id_global_zero",
-	  "; R1_w=map_value(off=0,ks=4,vs=4,imm=0)\n2: (85) call bpf_this_cpu_ptr#154\n"
+	  "; R1_w=map_value(map=.data.A,ks=4,vs=4)\n2: (85) call bpf_this_cpu_ptr#154\n"
 	  "R1 type=map_value expected=percpu_ptr_" },
 	{ "lock_id_mapval_preserve",
 	  "[0-9]\\+: (bf) r1 = r0                       ;"
-	  " R0_w=map_value(id=1,off=0,ks=4,vs=8,imm=0)"
-	  " R1_w=map_value(id=1,off=0,ks=4,vs=8,imm=0)\n"
+	  " R0_w=map_value(id=1,map=array_map,ks=4,vs=8)"
+	  " R1_w=map_value(id=1,map=array_map,ks=4,vs=8)\n"
 	  "[0-9]\\+: (85) call bpf_this_cpu_ptr#154\n"
 	  "R1 type=map_value expected=percpu_ptr_" },
 	{ "lock_id_innermapval_preserve",
 	  "[0-9]\\+: (bf) r1 = r0                      ;"
-	  " R0=map_value(id=2,off=0,ks=4,vs=8,imm=0)"
-	  " R1_w=map_value(id=2,off=0,ks=4,vs=8,imm=0)\n"
+	  " R0=map_value(id=2,ks=4,vs=8)"
+	  " R1_w=map_value(id=2,ks=4,vs=8)\n"
 	  "[0-9]\\+: (85) call bpf_this_cpu_ptr#154\n"
 	  "R1 type=map_value expected=percpu_ptr_" },
 	{ "lock_id_mismatch_kptr_kptr", "bpf_spin_unlock of different lock" },
diff --git a/tools/testing/selftests/bpf/prog_tests/syscall.c b/tools/testing/selftests/bpf/prog_tests/syscall.c
index f4d40001155a..0be8301c0ffd 100644
--- a/tools/testing/selftests/bpf/prog_tests/syscall.c
+++ b/tools/testing/selftests/bpf/prog_tests/syscall.c
@@ -12,7 +12,7 @@ struct args {
 	int btf_fd;
 };
 
-void test_syscall(void)
+static void test_syscall_load_prog(void)
 {
 	static char verifier_log[8192];
 	struct args ctx = {
@@ -32,7 +32,7 @@ void test_syscall(void)
 	if (!ASSERT_OK_PTR(skel, "skel_load"))
 		goto cleanup;
 
-	prog_fd = bpf_program__fd(skel->progs.bpf_prog);
+	prog_fd = bpf_program__fd(skel->progs.load_prog);
 	err = bpf_prog_test_run_opts(prog_fd, &tattr);
 	ASSERT_EQ(err, 0, "err");
 	ASSERT_EQ(tattr.retval, 1, "retval");
@@ -53,3 +53,29 @@ cleanup:
 	if (ctx.btf_fd > 0)
 		close(ctx.btf_fd);
 }
+
+static void test_syscall_update_outer_map(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	struct syscall *skel;
+	int err, prog_fd;
+
+	skel = syscall__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	prog_fd = bpf_program__fd(skel->progs.update_outer_map);
+	err = bpf_prog_test_run_opts(prog_fd, &opts);
+	ASSERT_EQ(err, 0, "err");
+	ASSERT_EQ(opts.retval, 1, "retval");
+cleanup:
+	syscall__destroy(skel);
+}
+
+void test_syscall(void)
+{
+	if (test__start_subtest("load_prog"))
+		test_syscall_load_prog();
+	if (test__start_subtest("update_outer_map"))
+		test_syscall_update_outer_map();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
index fc6b2954e8f5..59993fc9c0d7 100644
--- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c
+++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
@@ -1,6 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <unistd.h>
 #include <test_progs.h>
 #include <network_helpers.h>
+#include "tailcall_poke.skel.h"
+
 
 /* test_tailcall_1 checks basic functionality by patching multiple locations
  * in a single program for a single tail call slot with nop->jmp, jmp->nop
@@ -1105,6 +1108,85 @@ out:
 	bpf_object__close(tgt_obj);
 }
 
+#define JMP_TABLE "/sys/fs/bpf/jmp_table"
+
+static int poke_thread_exit;
+
+static void *poke_update(void *arg)
+{
+	__u32 zero = 0, prog1_fd, prog2_fd, map_fd;
+	struct tailcall_poke *call = arg;
+
+	map_fd = bpf_map__fd(call->maps.jmp_table);
+	prog1_fd = bpf_program__fd(call->progs.call1);
+	prog2_fd = bpf_program__fd(call->progs.call2);
+
+	while (!poke_thread_exit) {
+		bpf_map_update_elem(map_fd, &zero, &prog1_fd, BPF_ANY);
+		bpf_map_update_elem(map_fd, &zero, &prog2_fd, BPF_ANY);
+	}
+
+	return NULL;
+}
+
+/*
+ * We are trying to hit prog array update during another program load
+ * that shares the same prog array map.
+ *
+ * For that we share the jmp_table map between two skeleton instances
+ * by pinning the jmp_table to same path. Then first skeleton instance
+ * periodically updates jmp_table in 'poke update' thread while we load
+ * the second skeleton instance in the main thread.
+ */
+static void test_tailcall_poke(void)
+{
+	struct tailcall_poke *call, *test;
+	int err, cnt = 10;
+	pthread_t thread;
+
+	unlink(JMP_TABLE);
+
+	call = tailcall_poke__open_and_load();
+	if (!ASSERT_OK_PTR(call, "tailcall_poke__open"))
+		return;
+
+	err = bpf_map__pin(call->maps.jmp_table, JMP_TABLE);
+	if (!ASSERT_OK(err, "bpf_map__pin"))
+		goto out;
+
+	err = pthread_create(&thread, NULL, poke_update, call);
+	if (!ASSERT_OK(err, "new toggler"))
+		goto out;
+
+	while (cnt--) {
+		test = tailcall_poke__open();
+		if (!ASSERT_OK_PTR(test, "tailcall_poke__open"))
+			break;
+
+		err = bpf_map__set_pin_path(test->maps.jmp_table, JMP_TABLE);
+		if (!ASSERT_OK(err, "bpf_map__pin")) {
+			tailcall_poke__destroy(test);
+			break;
+		}
+
+		bpf_program__set_autoload(test->progs.test, true);
+		bpf_program__set_autoload(test->progs.call1, false);
+		bpf_program__set_autoload(test->progs.call2, false);
+
+		err = tailcall_poke__load(test);
+		tailcall_poke__destroy(test);
+		if (!ASSERT_OK(err, "tailcall_poke__load"))
+			break;
+	}
+
+	poke_thread_exit = 1;
+	ASSERT_OK(pthread_join(thread, NULL), "pthread_join");
+
+out:
+	bpf_map__unpin(call->maps.jmp_table, JMP_TABLE);
+	tailcall_poke__destroy(call);
+}
+
 void test_tailcalls(void)
 {
 	if (test__start_subtest("tailcall_1"))
@@ -1139,4 +1221,6 @@ void test_tailcalls(void)
 		test_tailcall_bpf2bpf_fentry_fexit();
 	if (test__start_subtest("tailcall_bpf2bpf_fentry_entry"))
 		test_tailcall_bpf2bpf_fentry_entry();
+	if (test__start_subtest("tailcall_poke"))
+		test_tailcall_poke();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_opts.c b/tools/testing/selftests/bpf/prog_tests/tc_opts.c
index 51883ccb8020..196abf223465 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_opts.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_opts.c
@@ -2387,12 +2387,9 @@ static int generate_dummy_prog(void)
 	const size_t prog_insn_cnt = sizeof(prog_insns) / sizeof(struct bpf_insn);
 	LIBBPF_OPTS(bpf_prog_load_opts, opts);
 	const size_t log_buf_sz = 256;
-	char *log_buf;
+	char log_buf[log_buf_sz];
 	int fd = -1;
 
-	log_buf = malloc(log_buf_sz);
-	if (!ASSERT_OK_PTR(log_buf, "log_buf_alloc"))
-		return fd;
 	opts.log_buf = log_buf;
 	opts.log_size = log_buf_sz;
 
@@ -2402,7 +2399,6 @@ static int generate_dummy_prog(void)
 			   prog_insns, prog_insn_cnt, &opts);
 	ASSERT_STREQ(log_buf, "", "log_0");
 	ASSERT_GE(fd, 0, "prog_fd");
-	free(log_buf);
 	return fd;
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
index 6ee22c3b251a..518f143c5b0f 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
@@ -24,6 +24,7 @@
 
 #include "test_progs.h"
 #include "network_helpers.h"
+#include "netlink_helpers.h"
 #include "test_tc_neigh_fib.skel.h"
 #include "test_tc_neigh.skel.h"
 #include "test_tc_peer.skel.h"
@@ -110,11 +111,17 @@ static void netns_setup_namespaces_nofail(const char *verb)
 	}
 }
 
+enum dev_mode {
+	MODE_VETH,
+	MODE_NETKIT,
+};
+
 struct netns_setup_result {
-	int ifindex_veth_src;
-	int ifindex_veth_src_fwd;
-	int ifindex_veth_dst;
-	int ifindex_veth_dst_fwd;
+	enum dev_mode dev_mode;
+	int ifindex_src;
+	int ifindex_src_fwd;
+	int ifindex_dst;
+	int ifindex_dst_fwd;
 };
 
 static int get_ifaddr(const char *name, char *ifaddr)
@@ -137,58 +144,110 @@ static int get_ifaddr(const char *name, char *ifaddr)
 	return 0;
 }
 
+static int create_netkit(int mode, char *prim, char *peer)
+{
+	struct rtattr *linkinfo, *data, *peer_info;
+	struct rtnl_handle rth = { .fd = -1 };
+	const char *type = "netkit";
+	struct {
+		struct nlmsghdr n;
+		struct ifinfomsg i;
+		char buf[1024];
+	} req = {};
+	int err;
+
+	err = rtnl_open(&rth, 0);
+	if (!ASSERT_OK(err, "open_rtnetlink"))
+		return err;
+
+	memset(&req, 0, sizeof(req));
+	req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+	req.n.nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE | NLM_F_EXCL;
+	req.n.nlmsg_type = RTM_NEWLINK;
+	req.i.ifi_family = AF_UNSPEC;
+
+	addattr_l(&req.n, sizeof(req), IFLA_IFNAME, prim, strlen(prim));
+	linkinfo = addattr_nest(&req.n, sizeof(req), IFLA_LINKINFO);
+	addattr_l(&req.n, sizeof(req), IFLA_INFO_KIND, type, strlen(type));
+	data = addattr_nest(&req.n, sizeof(req), IFLA_INFO_DATA);
+	addattr32(&req.n, sizeof(req), IFLA_NETKIT_MODE, mode);
+	peer_info = addattr_nest(&req.n, sizeof(req), IFLA_NETKIT_PEER_INFO);
+	req.n.nlmsg_len += sizeof(struct ifinfomsg);
+	addattr_l(&req.n, sizeof(req), IFLA_IFNAME, peer, strlen(peer));
+	addattr_nest_end(&req.n, peer_info);
+	addattr_nest_end(&req.n, data);
+	addattr_nest_end(&req.n, linkinfo);
+
+	err = rtnl_talk(&rth, &req.n, NULL);
+	ASSERT_OK(err, "talk_rtnetlink");
+	rtnl_close(&rth);
+	return err;
+}
+
 static int netns_setup_links_and_routes(struct netns_setup_result *result)
 {
 	struct nstoken *nstoken = NULL;
-	char veth_src_fwd_addr[IFADDR_STR_LEN+1] = {};
-
-	SYS(fail, "ip link add veth_src type veth peer name veth_src_fwd");
-	SYS(fail, "ip link add veth_dst type veth peer name veth_dst_fwd");
+	char src_fwd_addr[IFADDR_STR_LEN+1] = {};
+	int err;
 
-	SYS(fail, "ip link set veth_dst_fwd address " MAC_DST_FWD);
-	SYS(fail, "ip link set veth_dst address " MAC_DST);
+	if (result->dev_mode == MODE_VETH) {
+		SYS(fail, "ip link add src type veth peer name src_fwd");
+		SYS(fail, "ip link add dst type veth peer name dst_fwd");
+
+		SYS(fail, "ip link set dst_fwd address " MAC_DST_FWD);
+		SYS(fail, "ip link set dst address " MAC_DST);
+	} else if (result->dev_mode == MODE_NETKIT) {
+		err = create_netkit(NETKIT_L3, "src", "src_fwd");
+		if (!ASSERT_OK(err, "create_ifindex_src"))
+			goto fail;
+		err = create_netkit(NETKIT_L3, "dst", "dst_fwd");
+		if (!ASSERT_OK(err, "create_ifindex_dst"))
+			goto fail;
+	}
 
-	if (get_ifaddr("veth_src_fwd", veth_src_fwd_addr))
+	if (get_ifaddr("src_fwd", src_fwd_addr))
 		goto fail;
 
-	result->ifindex_veth_src = if_nametoindex("veth_src");
-	if (!ASSERT_GT(result->ifindex_veth_src, 0, "ifindex_veth_src"))
+	result->ifindex_src = if_nametoindex("src");
+	if (!ASSERT_GT(result->ifindex_src, 0, "ifindex_src"))
 		goto fail;
 
-	result->ifindex_veth_src_fwd = if_nametoindex("veth_src_fwd");
-	if (!ASSERT_GT(result->ifindex_veth_src_fwd, 0, "ifindex_veth_src_fwd"))
+	result->ifindex_src_fwd = if_nametoindex("src_fwd");
+	if (!ASSERT_GT(result->ifindex_src_fwd, 0, "ifindex_src_fwd"))
 		goto fail;
 
-	result->ifindex_veth_dst = if_nametoindex("veth_dst");
-	if (!ASSERT_GT(result->ifindex_veth_dst, 0, "ifindex_veth_dst"))
+	result->ifindex_dst = if_nametoindex("dst");
+	if (!ASSERT_GT(result->ifindex_dst, 0, "ifindex_dst"))
 		goto fail;
 
-	result->ifindex_veth_dst_fwd = if_nametoindex("veth_dst_fwd");
-	if (!ASSERT_GT(result->ifindex_veth_dst_fwd, 0, "ifindex_veth_dst_fwd"))
+	result->ifindex_dst_fwd = if_nametoindex("dst_fwd");
+	if (!ASSERT_GT(result->ifindex_dst_fwd, 0, "ifindex_dst_fwd"))
 		goto fail;
 
-	SYS(fail, "ip link set veth_src netns " NS_SRC);
-	SYS(fail, "ip link set veth_src_fwd netns " NS_FWD);
-	SYS(fail, "ip link set veth_dst_fwd netns " NS_FWD);
-	SYS(fail, "ip link set veth_dst netns " NS_DST);
+	SYS(fail, "ip link set src netns " NS_SRC);
+	SYS(fail, "ip link set src_fwd netns " NS_FWD);
+	SYS(fail, "ip link set dst_fwd netns " NS_FWD);
+	SYS(fail, "ip link set dst netns " NS_DST);
 
 	/** setup in 'src' namespace */
 	nstoken = open_netns(NS_SRC);
 	if (!ASSERT_OK_PTR(nstoken, "setns src"))
 		goto fail;
 
-	SYS(fail, "ip addr add " IP4_SRC "/32 dev veth_src");
-	SYS(fail, "ip addr add " IP6_SRC "/128 dev veth_src nodad");
-	SYS(fail, "ip link set dev veth_src up");
+	SYS(fail, "ip addr add " IP4_SRC "/32 dev src");
+	SYS(fail, "ip addr add " IP6_SRC "/128 dev src nodad");
+	SYS(fail, "ip link set dev src up");
 
-	SYS(fail, "ip route add " IP4_DST "/32 dev veth_src scope global");
-	SYS(fail, "ip route add " IP4_NET "/16 dev veth_src scope global");
-	SYS(fail, "ip route add " IP6_DST "/128 dev veth_src scope global");
+	SYS(fail, "ip route add " IP4_DST "/32 dev src scope global");
+	SYS(fail, "ip route add " IP4_NET "/16 dev src scope global");
+	SYS(fail, "ip route add " IP6_DST "/128 dev src scope global");
 
-	SYS(fail, "ip neigh add " IP4_DST " dev veth_src lladdr %s",
-	    veth_src_fwd_addr);
-	SYS(fail, "ip neigh add " IP6_DST " dev veth_src lladdr %s",
-	    veth_src_fwd_addr);
+	if (result->dev_mode == MODE_VETH) {
+		SYS(fail, "ip neigh add " IP4_DST " dev src lladdr %s",
+		    src_fwd_addr);
+		SYS(fail, "ip neigh add " IP6_DST " dev src lladdr %s",
+		    src_fwd_addr);
+	}
 
 	close_netns(nstoken);
 
@@ -201,15 +260,15 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result)
 	 * needs v4 one in order to start ARP probing. IP4_NET route is added
 	 * to the endpoints so that the ARP processing will reply.
 	 */
-	SYS(fail, "ip addr add " IP4_SLL "/32 dev veth_src_fwd");
-	SYS(fail, "ip addr add " IP4_DLL "/32 dev veth_dst_fwd");
-	SYS(fail, "ip link set dev veth_src_fwd up");
-	SYS(fail, "ip link set dev veth_dst_fwd up");
+	SYS(fail, "ip addr add " IP4_SLL "/32 dev src_fwd");
+	SYS(fail, "ip addr add " IP4_DLL "/32 dev dst_fwd");
+	SYS(fail, "ip link set dev src_fwd up");
+	SYS(fail, "ip link set dev dst_fwd up");
 
-	SYS(fail, "ip route add " IP4_SRC "/32 dev veth_src_fwd scope global");
-	SYS(fail, "ip route add " IP6_SRC "/128 dev veth_src_fwd scope global");
-	SYS(fail, "ip route add " IP4_DST "/32 dev veth_dst_fwd scope global");
-	SYS(fail, "ip route add " IP6_DST "/128 dev veth_dst_fwd scope global");
+	SYS(fail, "ip route add " IP4_SRC "/32 dev src_fwd scope global");
+	SYS(fail, "ip route add " IP6_SRC "/128 dev src_fwd scope global");
+	SYS(fail, "ip route add " IP4_DST "/32 dev dst_fwd scope global");
+	SYS(fail, "ip route add " IP6_DST "/128 dev dst_fwd scope global");
 
 	close_netns(nstoken);
 
@@ -218,16 +277,18 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result)
 	if (!ASSERT_OK_PTR(nstoken, "setns dst"))
 		goto fail;
 
-	SYS(fail, "ip addr add " IP4_DST "/32 dev veth_dst");
-	SYS(fail, "ip addr add " IP6_DST "/128 dev veth_dst nodad");
-	SYS(fail, "ip link set dev veth_dst up");
+	SYS(fail, "ip addr add " IP4_DST "/32 dev dst");
+	SYS(fail, "ip addr add " IP6_DST "/128 dev dst nodad");
+	SYS(fail, "ip link set dev dst up");
 
-	SYS(fail, "ip route add " IP4_SRC "/32 dev veth_dst scope global");
-	SYS(fail, "ip route add " IP4_NET "/16 dev veth_dst scope global");
-	SYS(fail, "ip route add " IP6_SRC "/128 dev veth_dst scope global");
+	SYS(fail, "ip route add " IP4_SRC "/32 dev dst scope global");
+	SYS(fail, "ip route add " IP4_NET "/16 dev dst scope global");
+	SYS(fail, "ip route add " IP6_SRC "/128 dev dst scope global");
 
-	SYS(fail, "ip neigh add " IP4_SRC " dev veth_dst lladdr " MAC_DST_FWD);
-	SYS(fail, "ip neigh add " IP6_SRC " dev veth_dst lladdr " MAC_DST_FWD);
+	if (result->dev_mode == MODE_VETH) {
+		SYS(fail, "ip neigh add " IP4_SRC " dev dst lladdr " MAC_DST_FWD);
+		SYS(fail, "ip neigh add " IP6_SRC " dev dst lladdr " MAC_DST_FWD);
+	}
 
 	close_netns(nstoken);
 
@@ -293,23 +354,23 @@ static int netns_load_bpf(const struct bpf_program *src_prog,
 			  const struct bpf_program *chk_prog,
 			  const struct netns_setup_result *setup_result)
 {
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_src_fwd);
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_dst_fwd);
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_src_fwd);
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_dst_fwd);
 	int err;
 
-	/* tc qdisc add dev veth_src_fwd clsact */
-	QDISC_CLSACT_CREATE(&qdisc_veth_src_fwd, setup_result->ifindex_veth_src_fwd);
-	/* tc filter add dev veth_src_fwd ingress bpf da src_prog */
-	XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_INGRESS, src_prog, 0);
-	/* tc filter add dev veth_src_fwd egress bpf da chk_prog */
-	XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_EGRESS, chk_prog, 0);
+	/* tc qdisc add dev src_fwd clsact */
+	QDISC_CLSACT_CREATE(&qdisc_src_fwd, setup_result->ifindex_src_fwd);
+	/* tc filter add dev src_fwd ingress bpf da src_prog */
+	XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_INGRESS, src_prog, 0);
+	/* tc filter add dev src_fwd egress bpf da chk_prog */
+	XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_EGRESS, chk_prog, 0);
 
-	/* tc qdisc add dev veth_dst_fwd clsact */
-	QDISC_CLSACT_CREATE(&qdisc_veth_dst_fwd, setup_result->ifindex_veth_dst_fwd);
-	/* tc filter add dev veth_dst_fwd ingress bpf da dst_prog */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_INGRESS, dst_prog, 0);
-	/* tc filter add dev veth_dst_fwd egress bpf da chk_prog */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_EGRESS, chk_prog, 0);
+	/* tc qdisc add dev dst_fwd clsact */
+	QDISC_CLSACT_CREATE(&qdisc_dst_fwd, setup_result->ifindex_dst_fwd);
+	/* tc filter add dev dst_fwd ingress bpf da dst_prog */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_INGRESS, dst_prog, 0);
+	/* tc filter add dev dst_fwd egress bpf da chk_prog */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_EGRESS, chk_prog, 0);
 
 	return 0;
 fail:
@@ -539,10 +600,10 @@ done:
 static int netns_load_dtime_bpf(struct test_tc_dtime *skel,
 				const struct netns_setup_result *setup_result)
 {
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_src_fwd);
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_dst_fwd);
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_src);
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_dst);
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_src_fwd);
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_dst_fwd);
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_src);
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_dst);
 	struct nstoken *nstoken;
 	int err;
 
@@ -550,58 +611,58 @@ static int netns_load_dtime_bpf(struct test_tc_dtime *skel,
 	nstoken = open_netns(NS_SRC);
 	if (!ASSERT_OK_PTR(nstoken, "setns " NS_SRC))
 		return -1;
-	/* tc qdisc add dev veth_src clsact */
-	QDISC_CLSACT_CREATE(&qdisc_veth_src, setup_result->ifindex_veth_src);
-	/* tc filter add dev veth_src ingress bpf da ingress_host */
-	XGRESS_FILTER_ADD(&qdisc_veth_src, BPF_TC_INGRESS, skel->progs.ingress_host, 0);
-	/* tc filter add dev veth_src egress bpf da egress_host */
-	XGRESS_FILTER_ADD(&qdisc_veth_src, BPF_TC_EGRESS, skel->progs.egress_host, 0);
+	/* tc qdisc add dev src clsact */
+	QDISC_CLSACT_CREATE(&qdisc_src, setup_result->ifindex_src);
+	/* tc filter add dev src ingress bpf da ingress_host */
+	XGRESS_FILTER_ADD(&qdisc_src, BPF_TC_INGRESS, skel->progs.ingress_host, 0);
+	/* tc filter add dev src egress bpf da egress_host */
+	XGRESS_FILTER_ADD(&qdisc_src, BPF_TC_EGRESS, skel->progs.egress_host, 0);
 	close_netns(nstoken);
 
 	/* setup ns_dst tc progs */
 	nstoken = open_netns(NS_DST);
 	if (!ASSERT_OK_PTR(nstoken, "setns " NS_DST))
 		return -1;
-	/* tc qdisc add dev veth_dst clsact */
-	QDISC_CLSACT_CREATE(&qdisc_veth_dst, setup_result->ifindex_veth_dst);
-	/* tc filter add dev veth_dst ingress bpf da ingress_host */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst, BPF_TC_INGRESS, skel->progs.ingress_host, 0);
-	/* tc filter add dev veth_dst egress bpf da egress_host */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst, BPF_TC_EGRESS, skel->progs.egress_host, 0);
+	/* tc qdisc add dev dst clsact */
+	QDISC_CLSACT_CREATE(&qdisc_dst, setup_result->ifindex_dst);
+	/* tc filter add dev dst ingress bpf da ingress_host */
+	XGRESS_FILTER_ADD(&qdisc_dst, BPF_TC_INGRESS, skel->progs.ingress_host, 0);
+	/* tc filter add dev dst egress bpf da egress_host */
+	XGRESS_FILTER_ADD(&qdisc_dst, BPF_TC_EGRESS, skel->progs.egress_host, 0);
 	close_netns(nstoken);
 
 	/* setup ns_fwd tc progs */
 	nstoken = open_netns(NS_FWD);
 	if (!ASSERT_OK_PTR(nstoken, "setns " NS_FWD))
 		return -1;
-	/* tc qdisc add dev veth_dst_fwd clsact */
-	QDISC_CLSACT_CREATE(&qdisc_veth_dst_fwd, setup_result->ifindex_veth_dst_fwd);
-	/* tc filter add dev veth_dst_fwd ingress prio 100 bpf da ingress_fwdns_prio100 */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_INGRESS,
+	/* tc qdisc add dev dst_fwd clsact */
+	QDISC_CLSACT_CREATE(&qdisc_dst_fwd, setup_result->ifindex_dst_fwd);
+	/* tc filter add dev dst_fwd ingress prio 100 bpf da ingress_fwdns_prio100 */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_INGRESS,
 			  skel->progs.ingress_fwdns_prio100, 100);
-	/* tc filter add dev veth_dst_fwd ingress prio 101 bpf da ingress_fwdns_prio101 */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_INGRESS,
+	/* tc filter add dev dst_fwd ingress prio 101 bpf da ingress_fwdns_prio101 */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_INGRESS,
 			  skel->progs.ingress_fwdns_prio101, 101);
-	/* tc filter add dev veth_dst_fwd egress prio 100 bpf da egress_fwdns_prio100 */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_EGRESS,
+	/* tc filter add dev dst_fwd egress prio 100 bpf da egress_fwdns_prio100 */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_EGRESS,
 			  skel->progs.egress_fwdns_prio100, 100);
-	/* tc filter add dev veth_dst_fwd egress prio 101 bpf da egress_fwdns_prio101 */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_EGRESS,
+	/* tc filter add dev dst_fwd egress prio 101 bpf da egress_fwdns_prio101 */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_EGRESS,
 			  skel->progs.egress_fwdns_prio101, 101);
 
-	/* tc qdisc add dev veth_src_fwd clsact */
-	QDISC_CLSACT_CREATE(&qdisc_veth_src_fwd, setup_result->ifindex_veth_src_fwd);
-	/* tc filter add dev veth_src_fwd ingress prio 100 bpf da ingress_fwdns_prio100 */
-	XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_INGRESS,
+	/* tc qdisc add dev src_fwd clsact */
+	QDISC_CLSACT_CREATE(&qdisc_src_fwd, setup_result->ifindex_src_fwd);
+	/* tc filter add dev src_fwd ingress prio 100 bpf da ingress_fwdns_prio100 */
+	XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_INGRESS,
 			  skel->progs.ingress_fwdns_prio100, 100);
-	/* tc filter add dev veth_src_fwd ingress prio 101 bpf da ingress_fwdns_prio101 */
-	XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_INGRESS,
+	/* tc filter add dev src_fwd ingress prio 101 bpf da ingress_fwdns_prio101 */
+	XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_INGRESS,
 			  skel->progs.ingress_fwdns_prio101, 101);
-	/* tc filter add dev veth_src_fwd egress prio 100 bpf da egress_fwdns_prio100 */
-	XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_EGRESS,
+	/* tc filter add dev src_fwd egress prio 100 bpf da egress_fwdns_prio100 */
+	XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_EGRESS,
 			  skel->progs.egress_fwdns_prio100, 100);
-	/* tc filter add dev veth_src_fwd egress prio 101 bpf da egress_fwdns_prio101 */
-	XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_EGRESS,
+	/* tc filter add dev src_fwd egress prio 101 bpf da egress_fwdns_prio101 */
+	XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_EGRESS,
 			  skel->progs.egress_fwdns_prio101, 101);
 	close_netns(nstoken);
 	return 0;
@@ -777,8 +838,8 @@ static void test_tc_redirect_dtime(struct netns_setup_result *setup_result)
 	if (!ASSERT_OK_PTR(skel, "test_tc_dtime__open"))
 		return;
 
-	skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd;
-	skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd;
+	skel->rodata->IFINDEX_SRC = setup_result->ifindex_src_fwd;
+	skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd;
 
 	err = test_tc_dtime__load(skel);
 	if (!ASSERT_OK(err, "test_tc_dtime__load"))
@@ -868,8 +929,8 @@ static void test_tc_redirect_neigh(struct netns_setup_result *setup_result)
 	if (!ASSERT_OK_PTR(skel, "test_tc_neigh__open"))
 		goto done;
 
-	skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd;
-	skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd;
+	skel->rodata->IFINDEX_SRC = setup_result->ifindex_src_fwd;
+	skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd;
 
 	err = test_tc_neigh__load(skel);
 	if (!ASSERT_OK(err, "test_tc_neigh__load"))
@@ -904,8 +965,8 @@ static void test_tc_redirect_peer(struct netns_setup_result *setup_result)
 	if (!ASSERT_OK_PTR(skel, "test_tc_peer__open"))
 		goto done;
 
-	skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd;
-	skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd;
+	skel->rodata->IFINDEX_SRC = setup_result->ifindex_src_fwd;
+	skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd;
 
 	err = test_tc_peer__load(skel);
 	if (!ASSERT_OK(err, "test_tc_peer__load"))
@@ -996,7 +1057,7 @@ static int tun_relay_loop(int src_fd, int target_fd)
 static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result)
 {
 	LIBBPF_OPTS(bpf_tc_hook, qdisc_tun_fwd);
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_dst_fwd);
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_dst_fwd);
 	struct test_tc_peer *skel = NULL;
 	struct nstoken *nstoken = NULL;
 	int err;
@@ -1045,7 +1106,7 @@ static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result)
 		goto fail;
 
 	skel->rodata->IFINDEX_SRC = ifindex;
-	skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd;
+	skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd;
 
 	err = test_tc_peer__load(skel);
 	if (!ASSERT_OK(err, "test_tc_peer__load"))
@@ -1053,19 +1114,19 @@ static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result)
 
 	/* Load "tc_src_l3" to the tun_fwd interface to redirect packets
 	 * towards dst, and "tc_dst" to redirect packets
-	 * and "tc_chk" on veth_dst_fwd to drop non-redirected packets.
+	 * and "tc_chk" on dst_fwd to drop non-redirected packets.
 	 */
 	/* tc qdisc add dev tun_fwd clsact */
 	QDISC_CLSACT_CREATE(&qdisc_tun_fwd, ifindex);
 	/* tc filter add dev tun_fwd ingress bpf da tc_src_l3 */
 	XGRESS_FILTER_ADD(&qdisc_tun_fwd, BPF_TC_INGRESS, skel->progs.tc_src_l3, 0);
 
-	/* tc qdisc add dev veth_dst_fwd clsact */
-	QDISC_CLSACT_CREATE(&qdisc_veth_dst_fwd, setup_result->ifindex_veth_dst_fwd);
-	/* tc filter add dev veth_dst_fwd ingress bpf da tc_dst_l3 */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_INGRESS, skel->progs.tc_dst_l3, 0);
-	/* tc filter add dev veth_dst_fwd egress bpf da tc_chk */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_EGRESS, skel->progs.tc_chk, 0);
+	/* tc qdisc add dev dst_fwd clsact */
+	QDISC_CLSACT_CREATE(&qdisc_dst_fwd, setup_result->ifindex_dst_fwd);
+	/* tc filter add dev dst_fwd ingress bpf da tc_dst_l3 */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_INGRESS, skel->progs.tc_dst_l3, 0);
+	/* tc filter add dev dst_fwd egress bpf da tc_chk */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_EGRESS, skel->progs.tc_chk, 0);
 
 	/* Setup route and neigh tables */
 	SYS(fail, "ip -netns " NS_SRC " addr add dev tun_src " IP4_TUN_SRC "/24");
@@ -1074,17 +1135,17 @@ static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result)
 	SYS(fail, "ip -netns " NS_SRC " addr add dev tun_src " IP6_TUN_SRC "/64 nodad");
 	SYS(fail, "ip -netns " NS_FWD " addr add dev tun_fwd " IP6_TUN_FWD "/64 nodad");
 
-	SYS(fail, "ip -netns " NS_SRC " route del " IP4_DST "/32 dev veth_src scope global");
+	SYS(fail, "ip -netns " NS_SRC " route del " IP4_DST "/32 dev src scope global");
 	SYS(fail, "ip -netns " NS_SRC " route add " IP4_DST "/32 via " IP4_TUN_FWD
 	    " dev tun_src scope global");
-	SYS(fail, "ip -netns " NS_DST " route add " IP4_TUN_SRC "/32 dev veth_dst scope global");
-	SYS(fail, "ip -netns " NS_SRC " route del " IP6_DST "/128 dev veth_src scope global");
+	SYS(fail, "ip -netns " NS_DST " route add " IP4_TUN_SRC "/32 dev dst scope global");
+	SYS(fail, "ip -netns " NS_SRC " route del " IP6_DST "/128 dev src scope global");
 	SYS(fail, "ip -netns " NS_SRC " route add " IP6_DST "/128 via " IP6_TUN_FWD
 	    " dev tun_src scope global");
-	SYS(fail, "ip -netns " NS_DST " route add " IP6_TUN_SRC "/128 dev veth_dst scope global");
+	SYS(fail, "ip -netns " NS_DST " route add " IP6_TUN_SRC "/128 dev dst scope global");
 
-	SYS(fail, "ip -netns " NS_DST " neigh add " IP4_TUN_SRC " dev veth_dst lladdr " MAC_DST_FWD);
-	SYS(fail, "ip -netns " NS_DST " neigh add " IP6_TUN_SRC " dev veth_dst lladdr " MAC_DST_FWD);
+	SYS(fail, "ip -netns " NS_DST " neigh add " IP4_TUN_SRC " dev dst lladdr " MAC_DST_FWD);
+	SYS(fail, "ip -netns " NS_DST " neigh add " IP6_TUN_SRC " dev dst lladdr " MAC_DST_FWD);
 
 	if (!ASSERT_OK(set_forwarding(false), "disable forwarding"))
 		goto fail;
@@ -1106,9 +1167,9 @@ fail:
 		close_netns(nstoken);
 }
 
-#define RUN_TEST(name)                                                                      \
+#define RUN_TEST(name, mode)                                                                \
 	({                                                                                  \
-		struct netns_setup_result setup_result;                                     \
+		struct netns_setup_result setup_result = { .dev_mode = mode, };             \
 		if (test__start_subtest(#name))                                             \
 			if (ASSERT_OK(netns_setup_namespaces("add"), "setup namespaces")) { \
 				if (ASSERT_OK(netns_setup_links_and_routes(&setup_result),  \
@@ -1122,11 +1183,13 @@ static void *test_tc_redirect_run_tests(void *arg)
 {
 	netns_setup_namespaces_nofail("delete");
 
-	RUN_TEST(tc_redirect_peer);
-	RUN_TEST(tc_redirect_peer_l3);
-	RUN_TEST(tc_redirect_neigh);
-	RUN_TEST(tc_redirect_neigh_fib);
-	RUN_TEST(tc_redirect_dtime);
+	RUN_TEST(tc_redirect_peer, MODE_VETH);
+	RUN_TEST(tc_redirect_peer, MODE_NETKIT);
+	RUN_TEST(tc_redirect_peer_l3, MODE_VETH);
+	RUN_TEST(tc_redirect_peer_l3, MODE_NETKIT);
+	RUN_TEST(tc_redirect_neigh, MODE_VETH);
+	RUN_TEST(tc_redirect_neigh_fib, MODE_VETH);
+	RUN_TEST(tc_redirect_dtime, MODE_VETH);
 	return NULL;
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c b/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c
index d3491a84b3b9..ccae0b31ac6c 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c
@@ -14,7 +14,8 @@ static void do_bpf_ma_test(const char *name)
 	struct test_bpf_ma *skel;
 	struct bpf_program *prog;
 	struct btf *btf;
-	int i, err;
+	int i, err, id;
+	char tname[32];
 
 	skel = test_bpf_ma__open();
 	if (!ASSERT_OK_PTR(skel, "open"))
@@ -25,16 +26,21 @@ static void do_bpf_ma_test(const char *name)
 		goto out;
 
 	for (i = 0; i < ARRAY_SIZE(skel->rodata->data_sizes); i++) {
-		char name[32];
-		int id;
-
-		snprintf(name, sizeof(name), "bin_data_%u", skel->rodata->data_sizes[i]);
-		id = btf__find_by_name_kind(btf, name, BTF_KIND_STRUCT);
-		if (!ASSERT_GT(id, 0, "bin_data"))
+		snprintf(tname, sizeof(tname), "bin_data_%u", skel->rodata->data_sizes[i]);
+		id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT);
+		if (!ASSERT_GT(id, 0, tname))
 			goto out;
 		skel->rodata->data_btf_ids[i] = id;
 	}
 
+	for (i = 0; i < ARRAY_SIZE(skel->rodata->percpu_data_sizes); i++) {
+		snprintf(tname, sizeof(tname), "percpu_bin_data_%u", skel->rodata->percpu_data_sizes[i]);
+		id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT);
+		if (!ASSERT_GT(id, 0, tname))
+			goto out;
+		skel->rodata->percpu_data_btf_ids[i] = id;
+	}
+
 	prog = bpf_object__find_program_by_name(skel->obj, name);
 	if (!ASSERT_OK_PTR(prog, "invalid prog name"))
 		goto out;
diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
index e0879df38639..67d4ef9e62b3 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
@@ -20,6 +20,109 @@
 #include "test_global_func17.skel.h"
 #include "test_global_func_ctx_args.skel.h"
 
+#include "bpf/libbpf_internal.h"
+#include "btf_helpers.h"
+
+static void check_ctx_arg_type(const struct btf *btf, const struct btf_param *p)
+{
+	const struct btf_type *t;
+	const char *s;
+
+	t = btf__type_by_id(btf, p->type);
+	if (!ASSERT_EQ(btf_kind(t), BTF_KIND_PTR, "ptr_t"))
+		return;
+
+	s = btf_type_raw_dump(btf, t->type);
+	if (!ASSERT_HAS_SUBSTR(s, "STRUCT 'bpf_perf_event_data' size=0 vlen=0",
+			       "ctx_struct_t"))
+		return;
+}
+
+static void subtest_ctx_arg_rewrite(void)
+{
+	struct test_global_func_ctx_args *skel = NULL;
+	struct bpf_prog_info info;
+	char func_info_buf[1024] __attribute__((aligned(8)));
+	struct bpf_func_info_min *rec;
+	struct btf *btf = NULL;
+	__u32 info_len = sizeof(info);
+	int err, fd, i;
+
+	skel = test_global_func_ctx_args__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	bpf_program__set_autoload(skel->progs.arg_tag_ctx_perf, true);
+
+	err = test_global_func_ctx_args__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto out;
+
+	memset(&info, 0, sizeof(info));
+	info.func_info = ptr_to_u64(&func_info_buf);
+	info.nr_func_info = 3;
+	info.func_info_rec_size = sizeof(struct bpf_func_info_min);
+
+	fd = bpf_program__fd(skel->progs.arg_tag_ctx_perf);
+	err = bpf_prog_get_info_by_fd(fd, &info, &info_len);
+	if (!ASSERT_OK(err, "prog_info"))
+		goto out;
+
+	if (!ASSERT_EQ(info.nr_func_info, 3, "nr_func_info"))
+		goto out;
+
+	btf = btf__load_from_kernel_by_id(info.btf_id);
+	if (!ASSERT_OK_PTR(btf, "obj_kern_btf"))
+		goto out;
+
+	rec = (struct bpf_func_info_min *)func_info_buf;
+	for (i = 0; i < info.nr_func_info; i++, rec = (void *)rec + info.func_info_rec_size) {
+		const struct btf_type *fn_t, *proto_t;
+		const char *name;
+
+		if (rec->insn_off == 0)
+			continue; /* main prog, skip */
+
+		fn_t = btf__type_by_id(btf, rec->type_id);
+		if (!ASSERT_OK_PTR(fn_t, "fn_type"))
+			goto out;
+		if (!ASSERT_EQ(btf_kind(fn_t), BTF_KIND_FUNC, "fn_type_kind"))
+			goto out;
+		proto_t = btf__type_by_id(btf, fn_t->type);
+		if (!ASSERT_OK_PTR(proto_t, "proto_type"))
+			goto out;
+
+		name = btf__name_by_offset(btf, fn_t->name_off);
+		if (strcmp(name, "subprog_ctx_tag") == 0) {
+			/* int subprog_ctx_tag(void *ctx __arg_ctx) */
+			if (!ASSERT_EQ(btf_vlen(proto_t), 1, "arg_cnt"))
+				goto out;
+
+			/* arg 0 is PTR -> STRUCT bpf_perf_event_data */
+			check_ctx_arg_type(btf, &btf_params(proto_t)[0]);
+		} else if (strcmp(name, "subprog_multi_ctx_tags") == 0) {
+			/* int subprog_multi_ctx_tags(void *ctx1 __arg_ctx,
+			 *			      struct my_struct *mem,
+			 *			      void *ctx2 __arg_ctx)
+			 */
+			if (!ASSERT_EQ(btf_vlen(proto_t), 3, "arg_cnt"))
+				goto out;
+
+			/* arg 0 is PTR -> STRUCT bpf_perf_event_data */
+			check_ctx_arg_type(btf, &btf_params(proto_t)[0]);
+			/* arg 2 is PTR -> STRUCT bpf_perf_event_data */
+			check_ctx_arg_type(btf, &btf_params(proto_t)[2]);
+		} else {
+			ASSERT_FAIL("unexpected subprog %s", name);
+			goto out;
+		}
+	}
+
+out:
+	btf__free(btf);
+	test_global_func_ctx_args__destroy(skel);
+}
+
 void test_test_global_funcs(void)
 {
 	RUN_TESTS(test_global_func1);
@@ -40,4 +143,7 @@ void test_test_global_funcs(void)
 	RUN_TESTS(test_global_func16);
 	RUN_TESTS(test_global_func17);
 	RUN_TESTS(test_global_func_ctx_args);
+
+	if (test__start_subtest("ctx_arg_rewrite"))
+		subtest_ctx_arg_rewrite();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c
index d149ab98798d..2b3c6dd66259 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c
@@ -50,6 +50,7 @@
  */
 
 #include <arpa/inet.h>
+#include <linux/if_link.h>
 #include <linux/if_tun.h>
 #include <linux/limits.h>
 #include <linux/sysctl.h>
@@ -92,6 +93,11 @@
 #define IPIP_TUNL_DEV0 "ipip00"
 #define IPIP_TUNL_DEV1 "ipip11"
 
+#define XFRM_AUTH "0x1111111111111111111111111111111111111111"
+#define XFRM_ENC "0x22222222222222222222222222222222"
+#define XFRM_SPI_IN_TO_OUT 0x1
+#define XFRM_SPI_OUT_TO_IN 0x2
+
 #define PING_ARGS "-i 0.01 -c 3 -w 10 -q"
 
 static int config_device(void)
@@ -264,6 +270,92 @@ static void delete_ipip_tunnel(void)
 	SYS_NOFAIL("ip fou del port 5555 2> /dev/null");
 }
 
+static int add_xfrm_tunnel(void)
+{
+	/* at_ns0 namespace
+	 * at_ns0 -> root
+	 */
+	SYS(fail,
+	    "ip netns exec at_ns0 "
+		"ip xfrm state add src %s dst %s proto esp "
+			"spi %d reqid 1 mode tunnel replay-window 42 "
+			"auth-trunc 'hmac(sha1)' %s 96 enc 'cbc(aes)' %s",
+	    IP4_ADDR_VETH0, IP4_ADDR1_VETH1, XFRM_SPI_IN_TO_OUT, XFRM_AUTH, XFRM_ENC);
+	SYS(fail,
+	    "ip netns exec at_ns0 "
+		"ip xfrm policy add src %s/32 dst %s/32 dir out "
+			"tmpl src %s dst %s proto esp reqid 1 "
+			"mode tunnel",
+	    IP4_ADDR_TUNL_DEV0, IP4_ADDR_TUNL_DEV1, IP4_ADDR_VETH0, IP4_ADDR1_VETH1);
+
+	/* root -> at_ns0 */
+	SYS(fail,
+	    "ip netns exec at_ns0 "
+		"ip xfrm state add src %s dst %s proto esp "
+			"spi %d reqid 2 mode tunnel "
+			"auth-trunc 'hmac(sha1)' %s 96 enc 'cbc(aes)' %s",
+	    IP4_ADDR1_VETH1, IP4_ADDR_VETH0, XFRM_SPI_OUT_TO_IN, XFRM_AUTH, XFRM_ENC);
+	SYS(fail,
+	    "ip netns exec at_ns0 "
+		"ip xfrm policy add src %s/32 dst %s/32 dir in "
+			"tmpl src %s dst %s proto esp reqid 2 "
+			"mode tunnel",
+	    IP4_ADDR_TUNL_DEV1, IP4_ADDR_TUNL_DEV0, IP4_ADDR1_VETH1, IP4_ADDR_VETH0);
+
+	/* address & route */
+	SYS(fail, "ip netns exec at_ns0 ip addr add dev veth0 %s/32",
+	    IP4_ADDR_TUNL_DEV0);
+	SYS(fail, "ip netns exec at_ns0 ip route add %s dev veth0 via %s src %s",
+	    IP4_ADDR_TUNL_DEV1, IP4_ADDR1_VETH1, IP4_ADDR_TUNL_DEV0);
+
+	/* root namespace
+	 * at_ns0 -> root
+	 */
+	SYS(fail,
+	    "ip xfrm state add src %s dst %s proto esp "
+		    "spi %d reqid 1 mode tunnel replay-window 42 "
+		    "auth-trunc 'hmac(sha1)' %s 96  enc 'cbc(aes)' %s",
+	    IP4_ADDR_VETH0, IP4_ADDR1_VETH1, XFRM_SPI_IN_TO_OUT, XFRM_AUTH, XFRM_ENC);
+	SYS(fail,
+	    "ip xfrm policy add src %s/32 dst %s/32 dir in "
+		    "tmpl src %s dst %s proto esp reqid 1 "
+		    "mode tunnel",
+	    IP4_ADDR_TUNL_DEV0, IP4_ADDR_TUNL_DEV1, IP4_ADDR_VETH0, IP4_ADDR1_VETH1);
+
+	/* root -> at_ns0 */
+	SYS(fail,
+	    "ip xfrm state add src %s dst %s proto esp "
+		    "spi %d reqid 2 mode tunnel "
+		    "auth-trunc 'hmac(sha1)' %s 96  enc 'cbc(aes)' %s",
+	    IP4_ADDR1_VETH1, IP4_ADDR_VETH0, XFRM_SPI_OUT_TO_IN, XFRM_AUTH, XFRM_ENC);
+	SYS(fail,
+	    "ip xfrm policy add src %s/32 dst %s/32 dir out "
+		    "tmpl src %s dst %s proto esp reqid 2 "
+		    "mode tunnel",
+	    IP4_ADDR_TUNL_DEV1, IP4_ADDR_TUNL_DEV0, IP4_ADDR1_VETH1, IP4_ADDR_VETH0);
+
+	/* address & route */
+	SYS(fail, "ip addr add dev veth1 %s/32", IP4_ADDR_TUNL_DEV1);
+	SYS(fail, "ip route add %s dev veth1 via %s src %s",
+	    IP4_ADDR_TUNL_DEV0, IP4_ADDR_VETH0, IP4_ADDR_TUNL_DEV1);
+
+	return 0;
+fail:
+	return -1;
+}
+
+static void delete_xfrm_tunnel(void)
+{
+	SYS_NOFAIL("ip xfrm policy delete dir out src %s/32 dst %s/32 2> /dev/null",
+		   IP4_ADDR_TUNL_DEV1, IP4_ADDR_TUNL_DEV0);
+	SYS_NOFAIL("ip xfrm policy delete dir in src %s/32 dst %s/32 2> /dev/null",
+		   IP4_ADDR_TUNL_DEV0, IP4_ADDR_TUNL_DEV1);
+	SYS_NOFAIL("ip xfrm state delete src %s dst %s proto esp spi %d 2> /dev/null",
+		   IP4_ADDR_VETH0, IP4_ADDR1_VETH1, XFRM_SPI_IN_TO_OUT);
+	SYS_NOFAIL("ip xfrm state delete src %s dst %s proto esp spi %d 2> /dev/null",
+		   IP4_ADDR1_VETH1, IP4_ADDR_VETH0, XFRM_SPI_OUT_TO_IN);
+}
+
 static int test_ping(int family, const char *addr)
 {
 	SYS(fail, "%s %s %s > /dev/null", ping_command(family), PING_ARGS, addr);
@@ -532,25 +624,85 @@ done:
 		test_tunnel_kern__destroy(skel);
 }
 
+static void test_xfrm_tunnel(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook,
+			    .attach_point = BPF_TC_INGRESS);
+	LIBBPF_OPTS(bpf_xdp_attach_opts, opts);
+	struct test_tunnel_kern *skel = NULL;
+	struct nstoken *nstoken;
+	int xdp_prog_fd;
+	int tc_prog_fd;
+	int ifindex;
+	int err;
+
+	err = add_xfrm_tunnel();
+	if (!ASSERT_OK(err, "add_xfrm_tunnel"))
+		return;
+
+	skel = test_tunnel_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+		goto done;
+
+	ifindex = if_nametoindex("veth1");
+	if (!ASSERT_NEQ(ifindex, 0, "veth1 ifindex"))
+		goto done;
+
+	/* attach tc prog to tunnel dev */
+	tc_hook.ifindex = ifindex;
+	tc_prog_fd = bpf_program__fd(skel->progs.xfrm_get_state);
+	if (!ASSERT_GE(tc_prog_fd, 0, "bpf_program__fd"))
+		goto done;
+	if (attach_tc_prog(&tc_hook, tc_prog_fd, -1))
+		goto done;
+
+	/* attach xdp prog to tunnel dev */
+	xdp_prog_fd = bpf_program__fd(skel->progs.xfrm_get_state_xdp);
+	if (!ASSERT_GE(xdp_prog_fd, 0, "bpf_program__fd"))
+		goto done;
+	err = bpf_xdp_attach(ifindex, xdp_prog_fd, XDP_FLAGS_REPLACE, &opts);
+	if (!ASSERT_OK(err, "bpf_xdp_attach"))
+		goto done;
+
+	/* ping from at_ns0 namespace test */
+	nstoken = open_netns("at_ns0");
+	err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV1);
+	close_netns(nstoken);
+	if (!ASSERT_OK(err, "test_ping"))
+		goto done;
+
+	if (!ASSERT_EQ(skel->bss->xfrm_reqid, 1, "req_id"))
+		goto done;
+	if (!ASSERT_EQ(skel->bss->xfrm_spi, XFRM_SPI_IN_TO_OUT, "spi"))
+		goto done;
+	if (!ASSERT_EQ(skel->bss->xfrm_remote_ip, 0xac100164, "remote_ip"))
+		goto done;
+	if (!ASSERT_EQ(skel->bss->xfrm_replay_window, 42, "replay_window"))
+		goto done;
+
+done:
+	delete_xfrm_tunnel();
+	if (skel)
+		test_tunnel_kern__destroy(skel);
+}
+
 #define RUN_TEST(name, ...)						\
 	({								\
 		if (test__start_subtest(#name)) {			\
+			config_device();				\
 			test_ ## name(__VA_ARGS__);			\
+			cleanup();					\
 		}							\
 	})
 
 static void *test_tunnel_run_tests(void *arg)
 {
-	cleanup();
-	config_device();
-
 	RUN_TEST(vxlan_tunnel);
 	RUN_TEST(ip6vxlan_tunnel);
 	RUN_TEST(ipip_tunnel, NONE);
 	RUN_TEST(ipip_tunnel, FOU);
 	RUN_TEST(ipip_tunnel, GUE);
-
-	cleanup();
+	RUN_TEST(xfrm_tunnel);
 
 	return NULL;
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/time_tai.c b/tools/testing/selftests/bpf/prog_tests/time_tai.c
index a31119823666..f45af1b0ef2c 100644
--- a/tools/testing/selftests/bpf/prog_tests/time_tai.c
+++ b/tools/testing/selftests/bpf/prog_tests/time_tai.c
@@ -56,7 +56,7 @@ void test_time_tai(void)
 	ASSERT_NEQ(ts2, 0, "tai_ts2");
 
 	/* TAI is moving forward only */
-	ASSERT_GT(ts2, ts1, "tai_forward");
+	ASSERT_GE(ts2, ts1, "tai_forward");
 
 	/* Check for future */
 	ret = clock_gettime(CLOCK_TAI, &now_tai);
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
index cd051d3901a9..8269cdee33ae 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
@@ -234,6 +234,177 @@ static void test_attach_api_syms(void)
 	test_attach_api("/proc/self/exe", NULL, &opts);
 }
 
+static void test_attach_api_fails(void)
+{
+	LIBBPF_OPTS(bpf_link_create_opts, opts);
+	const char *path = "/proc/self/exe";
+	struct uprobe_multi *skel = NULL;
+	int prog_fd, link_fd = -1;
+	unsigned long offset = 0;
+
+	skel = uprobe_multi__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi__open_and_load"))
+		goto cleanup;
+
+	prog_fd = bpf_program__fd(skel->progs.uprobe_extra);
+
+	/* abnormal cnt */
+	opts.uprobe_multi.path = path;
+	opts.uprobe_multi.offsets = &offset;
+	opts.uprobe_multi.cnt = INT_MAX;
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -E2BIG, "big cnt"))
+		goto cleanup;
+
+	/* cnt is 0 */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = path,
+		.uprobe_multi.offsets = (unsigned long *) &offset,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EINVAL, "cnt_is_zero"))
+		goto cleanup;
+
+	/* negative offset */
+	offset = -1;
+	opts.uprobe_multi.path = path;
+	opts.uprobe_multi.offsets = (unsigned long *) &offset;
+	opts.uprobe_multi.cnt = 1;
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EINVAL, "offset_is_negative"))
+		goto cleanup;
+
+	/* offsets is NULL */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = path,
+		.uprobe_multi.cnt = 1,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EINVAL, "offsets_is_null"))
+		goto cleanup;
+
+	/* wrong offsets pointer */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = path,
+		.uprobe_multi.offsets = (unsigned long *) 1,
+		.uprobe_multi.cnt = 1,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EFAULT, "offsets_is_wrong"))
+		goto cleanup;
+
+	/* path is NULL */
+	offset = 1;
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.offsets = (unsigned long *) &offset,
+		.uprobe_multi.cnt = 1,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EINVAL, "path_is_null"))
+		goto cleanup;
+
+	/* wrong path pointer  */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = (const char *) 1,
+		.uprobe_multi.offsets = (unsigned long *) &offset,
+		.uprobe_multi.cnt = 1,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EFAULT, "path_is_wrong"))
+		goto cleanup;
+
+	/* wrong path type */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = "/",
+		.uprobe_multi.offsets = (unsigned long *) &offset,
+		.uprobe_multi.cnt = 1,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EBADF, "path_is_wrong_type"))
+		goto cleanup;
+
+	/* wrong cookies pointer */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = path,
+		.uprobe_multi.offsets = (unsigned long *) &offset,
+		.uprobe_multi.cookies = (__u64 *) 1ULL,
+		.uprobe_multi.cnt = 1,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EFAULT, "cookies_is_wrong"))
+		goto cleanup;
+
+	/* wrong ref_ctr_offsets pointer */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = path,
+		.uprobe_multi.offsets = (unsigned long *) &offset,
+		.uprobe_multi.cookies = (__u64 *) &offset,
+		.uprobe_multi.ref_ctr_offsets = (unsigned long *) 1,
+		.uprobe_multi.cnt = 1,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EFAULT, "ref_ctr_offsets_is_wrong"))
+		goto cleanup;
+
+	/* wrong flags */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.flags = 1 << 31,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EINVAL, "wrong_flags"))
+		goto cleanup;
+
+	/* wrong pid */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = path,
+		.uprobe_multi.offsets = (unsigned long *) &offset,
+		.uprobe_multi.cnt = 1,
+		.uprobe_multi.pid = -2,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	ASSERT_EQ(link_fd, -ESRCH, "pid_is_wrong");
+
+cleanup:
+	if (link_fd >= 0)
+		close(link_fd);
+	uprobe_multi__destroy(skel);
+}
+
 static void __test_link_api(struct child *child)
 {
 	int prog_fd, link1_fd = -1, link2_fd = -1, link3_fd = -1, link4_fd = -1;
@@ -249,7 +420,7 @@ static void __test_link_api(struct child *child)
 	int link_extra_fd = -1;
 	int err;
 
-	err = elf_resolve_syms_offsets(path, 3, syms, (unsigned long **) &offsets);
+	err = elf_resolve_syms_offsets(path, 3, syms, (unsigned long **) &offsets, STT_FUNC);
 	if (!ASSERT_OK(err, "elf_resolve_syms_offsets"))
 		return;
 
@@ -311,7 +482,7 @@ cleanup:
 	free(offsets);
 }
 
-void test_link_api(void)
+static void test_link_api(void)
 {
 	struct child *child;
 
@@ -412,4 +583,6 @@ void test_uprobe_multi_test(void)
 		test_bench_attach_uprobe();
 	if (test__start_subtest("bench_usdt"))
 		test_bench_attach_usdt();
+	if (test__start_subtest("attach_api_fails"))
+		test_attach_api_fails();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index e5c61aa6604a..d62c5bf00e71 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -6,6 +6,7 @@
 #include "verifier_and.skel.h"
 #include "verifier_array_access.skel.h"
 #include "verifier_basic_stack.skel.h"
+#include "verifier_bitfield_write.skel.h"
 #include "verifier_bounds.skel.h"
 #include "verifier_bounds_deduction.skel.h"
 #include "verifier_bounds_deduction_non_const.skel.h"
@@ -13,6 +14,7 @@
 #include "verifier_bpf_get_stack.skel.h"
 #include "verifier_bswap.skel.h"
 #include "verifier_btf_ctx_access.skel.h"
+#include "verifier_btf_unreliable_prog.skel.h"
 #include "verifier_cfg.skel.h"
 #include "verifier_cgroup_inv_retcode.skel.h"
 #include "verifier_cgroup_skb.skel.h"
@@ -25,12 +27,14 @@
 #include "verifier_direct_stack_access_wraparound.skel.h"
 #include "verifier_div0.skel.h"
 #include "verifier_div_overflow.skel.h"
+#include "verifier_global_subprogs.skel.h"
 #include "verifier_gotol.skel.h"
 #include "verifier_helper_access_var_len.skel.h"
 #include "verifier_helper_packet_access.skel.h"
 #include "verifier_helper_restricted.skel.h"
 #include "verifier_helper_value_access.skel.h"
 #include "verifier_int_ptr.skel.h"
+#include "verifier_iterating_callbacks.skel.h"
 #include "verifier_jeq_infer_not_null.skel.h"
 #include "verifier_ld_ind.skel.h"
 #include "verifier_ldsx.skel.h"
@@ -114,6 +118,7 @@ static void run_tests_aux(const char *skel_name,
 
 void test_verifier_and(void)                  { RUN(verifier_and); }
 void test_verifier_basic_stack(void)          { RUN(verifier_basic_stack); }
+void test_verifier_bitfield_write(void)       { RUN(verifier_bitfield_write); }
 void test_verifier_bounds(void)               { RUN(verifier_bounds); }
 void test_verifier_bounds_deduction(void)     { RUN(verifier_bounds_deduction); }
 void test_verifier_bounds_deduction_non_const(void)     { RUN(verifier_bounds_deduction_non_const); }
@@ -121,6 +126,7 @@ void test_verifier_bounds_mix_sign_unsign(void) { RUN(verifier_bounds_mix_sign_u
 void test_verifier_bpf_get_stack(void)        { RUN(verifier_bpf_get_stack); }
 void test_verifier_bswap(void)                { RUN(verifier_bswap); }
 void test_verifier_btf_ctx_access(void)       { RUN(verifier_btf_ctx_access); }
+void test_verifier_btf_unreliable_prog(void)  { RUN(verifier_btf_unreliable_prog); }
 void test_verifier_cfg(void)                  { RUN(verifier_cfg); }
 void test_verifier_cgroup_inv_retcode(void)   { RUN(verifier_cgroup_inv_retcode); }
 void test_verifier_cgroup_skb(void)           { RUN(verifier_cgroup_skb); }
@@ -133,12 +139,14 @@ void test_verifier_direct_packet_access(void) { RUN(verifier_direct_packet_acces
 void test_verifier_direct_stack_access_wraparound(void) { RUN(verifier_direct_stack_access_wraparound); }
 void test_verifier_div0(void)                 { RUN(verifier_div0); }
 void test_verifier_div_overflow(void)         { RUN(verifier_div_overflow); }
+void test_verifier_global_subprogs(void)      { RUN(verifier_global_subprogs); }
 void test_verifier_gotol(void)                { RUN(verifier_gotol); }
 void test_verifier_helper_access_var_len(void) { RUN(verifier_helper_access_var_len); }
 void test_verifier_helper_packet_access(void) { RUN(verifier_helper_packet_access); }
 void test_verifier_helper_restricted(void)    { RUN(verifier_helper_restricted); }
 void test_verifier_helper_value_access(void)  { RUN(verifier_helper_value_access); }
 void test_verifier_int_ptr(void)              { RUN(verifier_int_ptr); }
+void test_verifier_iterating_callbacks(void)  { RUN(verifier_iterating_callbacks); }
 void test_verifier_jeq_infer_not_null(void)   { RUN(verifier_jeq_infer_not_null); }
 void test_verifier_ld_ind(void)               { RUN(verifier_ld_ind); }
 void test_verifier_ldsx(void)                  { RUN(verifier_ldsx); }
diff --git a/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c b/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c
index dd7f2bc70048..ab0f02faa80c 100644
--- a/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c
+++ b/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c
@@ -16,9 +16,12 @@
 #include <sys/wait.h>
 #include <sys/mman.h>
 #include <linux/keyctl.h>
+#include <sys/xattr.h>
+#include <linux/fsverity.h>
 #include <test_progs.h>
 
 #include "test_verify_pkcs7_sig.skel.h"
+#include "test_sig_in_xattr.skel.h"
 
 #define MAX_DATA_SIZE (1024 * 1024)
 #define MAX_SIG_SIZE 1024
@@ -26,6 +29,10 @@
 #define VERIFY_USE_SECONDARY_KEYRING (1UL)
 #define VERIFY_USE_PLATFORM_KEYRING  (2UL)
 
+#ifndef SHA256_DIGEST_SIZE
+#define SHA256_DIGEST_SIZE      32
+#endif
+
 /* In stripped ARM and x86-64 modules, ~ is surprisingly rare. */
 #define MODULE_SIG_STRING "~Module signature appended~\n"
 
@@ -254,7 +261,7 @@ out:
 	return ret;
 }
 
-void test_verify_pkcs7_sig(void)
+static void test_verify_pkcs7_sig_from_map(void)
 {
 	libbpf_print_fn_t old_print_cb;
 	char tmp_dir_template[] = "/tmp/verify_sigXXXXXX";
@@ -400,3 +407,159 @@ close_prog:
 	skel->bss->monitored_pid = 0;
 	test_verify_pkcs7_sig__destroy(skel);
 }
+
+static int get_signature_size(const char *sig_path)
+{
+	struct stat st;
+
+	if (stat(sig_path, &st) == -1)
+		return -1;
+
+	return st.st_size;
+}
+
+static int add_signature_to_xattr(const char *data_path, const char *sig_path)
+{
+	char sig[MAX_SIG_SIZE] = {0};
+	int fd, size, ret;
+
+	if (sig_path) {
+		fd = open(sig_path, O_RDONLY);
+		if (fd < 0)
+			return -1;
+
+		size = read(fd, sig, MAX_SIG_SIZE);
+		close(fd);
+		if (size <= 0)
+			return -1;
+	} else {
+		/* no sig_path, just write 32 bytes of zeros */
+		size = 32;
+	}
+	ret = setxattr(data_path, "user.sig", sig, size, 0);
+	if (!ASSERT_OK(ret, "setxattr"))
+		return -1;
+
+	return 0;
+}
+
+static int test_open_file(struct test_sig_in_xattr *skel, char *data_path,
+			  pid_t pid, bool should_success, char *name)
+{
+	int ret;
+
+	skel->bss->monitored_pid = pid;
+	ret = open(data_path, O_RDONLY);
+	close(ret);
+	skel->bss->monitored_pid = 0;
+
+	if (should_success) {
+		if (!ASSERT_GE(ret, 0, name))
+			return -1;
+	} else {
+		if (!ASSERT_LT(ret, 0, name))
+			return -1;
+	}
+	return 0;
+}
+
+static void test_pkcs7_sig_fsverity(void)
+{
+	char data_path[PATH_MAX];
+	char sig_path[PATH_MAX];
+	char tmp_dir_template[] = "/tmp/verify_sigXXXXXX";
+	char *tmp_dir;
+	struct test_sig_in_xattr *skel = NULL;
+	pid_t pid;
+	int ret;
+
+	tmp_dir = mkdtemp(tmp_dir_template);
+	if (!ASSERT_OK_PTR(tmp_dir, "mkdtemp"))
+		return;
+
+	snprintf(data_path, PATH_MAX, "%s/data-file", tmp_dir);
+	snprintf(sig_path, PATH_MAX, "%s/sig-file", tmp_dir);
+
+	ret = _run_setup_process(tmp_dir, "setup");
+	if (!ASSERT_OK(ret, "_run_setup_process"))
+		goto out;
+
+	ret = _run_setup_process(tmp_dir, "fsverity-create-sign");
+
+	if (ret) {
+		printf("%s: SKIP: fsverity [sign|enable] doesn't work.\n"
+		       "To run this test, try enable CONFIG_FS_VERITY and enable FSVerity for the filesystem.\n",
+		       __func__);
+		test__skip();
+		goto out;
+	}
+
+	skel = test_sig_in_xattr__open();
+	if (!ASSERT_OK_PTR(skel, "test_sig_in_xattr__open"))
+		goto out;
+	ret = get_signature_size(sig_path);
+	if (!ASSERT_GT(ret, 0, "get_signature_size"))
+		goto out;
+	skel->bss->sig_size = ret;
+	skel->bss->user_keyring_serial = syscall(__NR_request_key, "keyring",
+						 "ebpf_testing_keyring", NULL,
+						 KEY_SPEC_SESSION_KEYRING);
+	memcpy(skel->bss->digest, "FSVerity", 8);
+
+	ret = test_sig_in_xattr__load(skel);
+	if (!ASSERT_OK(ret, "test_sig_in_xattr__load"))
+		goto out;
+
+	ret = test_sig_in_xattr__attach(skel);
+	if (!ASSERT_OK(ret, "test_sig_in_xattr__attach"))
+		goto out;
+
+	pid = getpid();
+
+	/* Case 1: fsverity is not enabled, open should succeed */
+	if (test_open_file(skel, data_path, pid, true, "open_1"))
+		goto out;
+
+	/* Case 2: fsverity is enabled, xattr is missing, open should
+	 * fail
+	 */
+	ret = _run_setup_process(tmp_dir, "fsverity-enable");
+	if (!ASSERT_OK(ret, "fsverity-enable"))
+		goto out;
+	if (test_open_file(skel, data_path, pid, false, "open_2"))
+		goto out;
+
+	/* Case 3: fsverity is enabled, xattr has valid signature, open
+	 * should succeed
+	 */
+	ret = add_signature_to_xattr(data_path, sig_path);
+	if (!ASSERT_OK(ret, "add_signature_to_xattr_1"))
+		goto out;
+
+	if (test_open_file(skel, data_path, pid, true, "open_3"))
+		goto out;
+
+	/* Case 4: fsverity is enabled, xattr has invalid signature, open
+	 * should fail
+	 */
+	ret = add_signature_to_xattr(data_path, NULL);
+	if (!ASSERT_OK(ret, "add_signature_to_xattr_2"))
+		goto out;
+	test_open_file(skel, data_path, pid, false, "open_4");
+
+out:
+	_run_setup_process(tmp_dir, "cleanup");
+	if (!skel)
+		return;
+
+	skel->bss->monitored_pid = 0;
+	test_sig_in_xattr__destroy(skel);
+}
+
+void test_verify_pkcs7_sig(void)
+{
+	if (test__start_subtest("pkcs7_sig_from_map"))
+		test_verify_pkcs7_sig_from_map();
+	if (test__start_subtest("pkcs7_sig_fsverity"))
+		test_pkcs7_sig_fsverity();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/vmlinux.c b/tools/testing/selftests/bpf/prog_tests/vmlinux.c
index 72310cfc6474..6fb2217d940b 100644
--- a/tools/testing/selftests/bpf/prog_tests/vmlinux.c
+++ b/tools/testing/selftests/bpf/prog_tests/vmlinux.c
@@ -16,27 +16,27 @@ static void nsleep()
 
 void test_vmlinux(void)
 {
-	int duration = 0, err;
+	int err;
 	struct test_vmlinux* skel;
 	struct test_vmlinux__bss *bss;
 
 	skel = test_vmlinux__open_and_load();
-	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+	if (!ASSERT_OK_PTR(skel, "test_vmlinux__open_and_load"))
 		return;
 	bss = skel->bss;
 
 	err = test_vmlinux__attach(skel);
-	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+	if (!ASSERT_OK(err, "test_vmlinux__attach"))
 		goto cleanup;
 
 	/* trigger everything */
 	nsleep();
 
-	CHECK(!bss->tp_called, "tp", "not called\n");
-	CHECK(!bss->raw_tp_called, "raw_tp", "not called\n");
-	CHECK(!bss->tp_btf_called, "tp_btf", "not called\n");
-	CHECK(!bss->kprobe_called, "kprobe", "not called\n");
-	CHECK(!bss->fentry_called, "fentry", "not called\n");
+	ASSERT_TRUE(bss->tp_called, "tp");
+	ASSERT_TRUE(bss->raw_tp_called, "raw_tp");
+	ASSERT_TRUE(bss->tp_btf_called, "tp_btf");
+	ASSERT_TRUE(bss->kprobe_called, "kprobe");
+	ASSERT_TRUE(bss->fentry_called, "fentry");
 
 cleanup:
 	test_vmlinux__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
index ab4952b9fb1d..e6a783c7f5db 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
@@ -77,8 +77,8 @@ void test_xdp_context_test_run(void)
 	test_xdp_context_error(prog_fd, opts, 4, sizeof(__u32), sizeof(data),
 			       0, 0, 0);
 
-	/* Meta data must be 32 bytes or smaller */
-	test_xdp_context_error(prog_fd, opts, 0, 36, sizeof(data), 0, 0, 0);
+	/* Meta data must be 255 bytes or smaller */
+	test_xdp_context_error(prog_fd, opts, 0, 256, sizeof(data), 0, 0, 0);
 
 	/* Total size of data must match data_end - data_meta */
 	test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32),
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
index 4439ba9392f8..05edcf32f528 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
@@ -20,7 +20,7 @@
 
 #define UDP_PAYLOAD_BYTES 4
 
-#define AF_XDP_SOURCE_PORT 1234
+#define UDP_SOURCE_PORT 1234
 #define AF_XDP_CONSUMER_PORT 8080
 
 #define UMEM_NUM 16
@@ -33,6 +33,18 @@
 #define RX_ADDR "10.0.0.2"
 #define PREFIX_LEN "8"
 #define FAMILY AF_INET
+#define TX_NETNS_NAME "xdp_metadata_tx"
+#define RX_NETNS_NAME "xdp_metadata_rx"
+#define TX_MAC "00:00:00:00:00:01"
+#define RX_MAC "00:00:00:00:00:02"
+
+#define VLAN_ID 59
+#define VLAN_PROTO "802.1Q"
+#define VLAN_PID htons(ETH_P_8021Q)
+#define TX_NAME_VLAN TX_NAME "." TO_STR(VLAN_ID)
+
+#define XDP_RSS_TYPE_L4 BIT(3)
+#define VLAN_VID_MASK 0xfff
 
 struct xsk {
 	void *umem_area;
@@ -56,7 +68,8 @@ static int open_xsk(int ifindex, struct xsk *xsk)
 		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
 		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
 		.frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE,
-		.flags = XDP_UMEM_UNALIGNED_CHUNK_FLAG,
+		.flags = XDP_UMEM_UNALIGNED_CHUNK_FLAG | XDP_UMEM_TX_SW_CSUM,
+		.tx_metadata_len = sizeof(struct xsk_tx_metadata),
 	};
 	__u32 idx;
 	u64 addr;
@@ -138,6 +151,7 @@ static void ip_csum(struct iphdr *iph)
 
 static int generate_packet(struct xsk *xsk, __u16 dst_port)
 {
+	struct xsk_tx_metadata *meta;
 	struct xdp_desc *tx_desc;
 	struct udphdr *udph;
 	struct ethhdr *eth;
@@ -151,10 +165,14 @@ static int generate_packet(struct xsk *xsk, __u16 dst_port)
 		return -1;
 
 	tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx);
-	tx_desc->addr = idx % (UMEM_NUM / 2) * UMEM_FRAME_SIZE;
+	tx_desc->addr = idx % (UMEM_NUM / 2) * UMEM_FRAME_SIZE + sizeof(struct xsk_tx_metadata);
 	printf("%p: tx_desc[%u]->addr=%llx\n", xsk, idx, tx_desc->addr);
 	data = xsk_umem__get_data(xsk->umem_area, tx_desc->addr);
 
+	meta = data - sizeof(struct xsk_tx_metadata);
+	memset(meta, 0, sizeof(*meta));
+	meta->flags = XDP_TXMD_FLAGS_TIMESTAMP;
+
 	eth = data;
 	iph = (void *)(eth + 1);
 	udph = (void *)(iph + 1);
@@ -175,14 +193,20 @@ static int generate_packet(struct xsk *xsk, __u16 dst_port)
 	ASSERT_EQ(inet_pton(FAMILY, RX_ADDR, &iph->daddr), 1, "inet_pton(RX_ADDR)");
 	ip_csum(iph);
 
-	udph->source = htons(AF_XDP_SOURCE_PORT);
+	udph->source = htons(UDP_SOURCE_PORT);
 	udph->dest = htons(dst_port);
 	udph->len = htons(sizeof(*udph) + UDP_PAYLOAD_BYTES);
-	udph->check = 0;
+	udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
+					 ntohs(udph->len), IPPROTO_UDP, 0);
 
 	memset(udph + 1, 0xAA, UDP_PAYLOAD_BYTES);
 
+	meta->flags |= XDP_TXMD_FLAGS_CHECKSUM;
+	meta->request.csum_start = sizeof(*eth) + sizeof(*iph);
+	meta->request.csum_offset = offsetof(struct udphdr, check);
+
 	tx_desc->len = sizeof(*eth) + sizeof(*iph) + sizeof(*udph) + UDP_PAYLOAD_BYTES;
+	tx_desc->options |= XDP_TX_METADATA;
 	xsk_ring_prod__submit(&xsk->tx, 1);
 
 	ret = sendto(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, 0);
@@ -192,15 +216,47 @@ static int generate_packet(struct xsk *xsk, __u16 dst_port)
 	return 0;
 }
 
+static int generate_packet_inet(void)
+{
+	char udp_payload[UDP_PAYLOAD_BYTES];
+	struct sockaddr_in rx_addr;
+	int sock_fd, err = 0;
+
+	/* Build a packet */
+	memset(udp_payload, 0xAA, UDP_PAYLOAD_BYTES);
+	rx_addr.sin_addr.s_addr = inet_addr(RX_ADDR);
+	rx_addr.sin_family = AF_INET;
+	rx_addr.sin_port = htons(AF_XDP_CONSUMER_PORT);
+
+	sock_fd = socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP);
+	if (!ASSERT_GE(sock_fd, 0, "socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP)"))
+		return sock_fd;
+
+	err = sendto(sock_fd, udp_payload, UDP_PAYLOAD_BYTES, MSG_DONTWAIT,
+		     (void *)&rx_addr, sizeof(rx_addr));
+	ASSERT_GE(err, 0, "sendto");
+
+	close(sock_fd);
+	return err;
+}
+
 static void complete_tx(struct xsk *xsk)
 {
-	__u32 idx;
+	struct xsk_tx_metadata *meta;
 	__u64 addr;
+	void *data;
+	__u32 idx;
 
 	if (ASSERT_EQ(xsk_ring_cons__peek(&xsk->comp, 1, &idx), 1, "xsk_ring_cons__peek")) {
 		addr = *xsk_ring_cons__comp_addr(&xsk->comp, idx);
 
 		printf("%p: complete tx idx=%u addr=%llx\n", xsk, idx, addr);
+
+		data = xsk_umem__get_data(xsk->umem_area, addr);
+		meta = data - sizeof(struct xsk_tx_metadata);
+
+		ASSERT_NEQ(meta->completion.tx_timestamp, 0, "tx_timestamp");
+
 		xsk_ring_cons__release(&xsk->comp, 1);
 	}
 }
@@ -216,11 +272,12 @@ static void refill_rx(struct xsk *xsk, __u64 addr)
 	}
 }
 
-static int verify_xsk_metadata(struct xsk *xsk)
+static int verify_xsk_metadata(struct xsk *xsk, bool sent_from_af_xdp)
 {
 	const struct xdp_desc *rx_desc;
 	struct pollfd fds = {};
 	struct xdp_meta *meta;
+	struct udphdr *udph;
 	struct ethhdr *eth;
 	struct iphdr *iph;
 	__u64 comp_addr;
@@ -257,6 +314,7 @@ static int verify_xsk_metadata(struct xsk *xsk)
 	ASSERT_EQ(eth->h_proto, htons(ETH_P_IP), "eth->h_proto");
 	iph = (void *)(eth + 1);
 	ASSERT_EQ((int)iph->version, 4, "iph->version");
+	udph = (void *)(iph + 1);
 
 	/* custom metadata */
 
@@ -268,14 +326,42 @@ static int verify_xsk_metadata(struct xsk *xsk)
 	if (!ASSERT_NEQ(meta->rx_hash, 0, "rx_hash"))
 		return -1;
 
+	if (!sent_from_af_xdp) {
+		if (!ASSERT_NEQ(meta->rx_hash_type & XDP_RSS_TYPE_L4, 0, "rx_hash_type"))
+			return -1;
+
+		if (!ASSERT_EQ(meta->rx_vlan_tci & VLAN_VID_MASK, VLAN_ID, "rx_vlan_tci"))
+			return -1;
+
+		if (!ASSERT_EQ(meta->rx_vlan_proto, VLAN_PID, "rx_vlan_proto"))
+			return -1;
+		goto done;
+	}
+
 	ASSERT_EQ(meta->rx_hash_type, 0, "rx_hash_type");
 
+	/* checksum offload */
+	ASSERT_EQ(udph->check, htons(0x721c), "csum");
+
+done:
 	xsk_ring_cons__release(&xsk->rx, 1);
 	refill_rx(xsk, comp_addr);
 
 	return 0;
 }
 
+static void switch_ns_to_rx(struct nstoken **tok)
+{
+	close_netns(*tok);
+	*tok = open_netns(RX_NETNS_NAME);
+}
+
+static void switch_ns_to_tx(struct nstoken **tok)
+{
+	close_netns(*tok);
+	*tok = open_netns(TX_NETNS_NAME);
+}
+
 void test_xdp_metadata(void)
 {
 	struct xdp_metadata2 *bpf_obj2 = NULL;
@@ -293,27 +379,35 @@ void test_xdp_metadata(void)
 	int sock_fd;
 	int ret;
 
-	/* Setup new networking namespace, with a veth pair. */
+	/* Setup new networking namespaces, with a veth pair. */
+	SYS(out, "ip netns add " TX_NETNS_NAME);
+	SYS(out, "ip netns add " RX_NETNS_NAME);
 
-	SYS(out, "ip netns add xdp_metadata");
-	tok = open_netns("xdp_metadata");
+	tok = open_netns(TX_NETNS_NAME);
 	SYS(out, "ip link add numtxqueues 1 numrxqueues 1 " TX_NAME
 	    " type veth peer " RX_NAME " numtxqueues 1 numrxqueues 1");
-	SYS(out, "ip link set dev " TX_NAME " address 00:00:00:00:00:01");
-	SYS(out, "ip link set dev " RX_NAME " address 00:00:00:00:00:02");
+	SYS(out, "ip link set " RX_NAME " netns " RX_NETNS_NAME);
+
+	SYS(out, "ip link set dev " TX_NAME " address " TX_MAC);
 	SYS(out, "ip link set dev " TX_NAME " up");
+
+	SYS(out, "ip link add link " TX_NAME " " TX_NAME_VLAN
+		 " type vlan proto " VLAN_PROTO " id " TO_STR(VLAN_ID));
+	SYS(out, "ip link set dev " TX_NAME_VLAN " up");
+	SYS(out, "ip addr add " TX_ADDR "/" PREFIX_LEN " dev " TX_NAME_VLAN);
+
+	/* Avoid ARP calls */
+	SYS(out, "ip -4 neigh add " RX_ADDR " lladdr " RX_MAC " dev " TX_NAME_VLAN);
+
+	switch_ns_to_rx(&tok);
+
+	SYS(out, "ip link set dev " RX_NAME " address " RX_MAC);
 	SYS(out, "ip link set dev " RX_NAME " up");
-	SYS(out, "ip addr add " TX_ADDR "/" PREFIX_LEN " dev " TX_NAME);
 	SYS(out, "ip addr add " RX_ADDR "/" PREFIX_LEN " dev " RX_NAME);
 
 	rx_ifindex = if_nametoindex(RX_NAME);
-	tx_ifindex = if_nametoindex(TX_NAME);
 
-	/* Setup separate AF_XDP for TX and RX interfaces. */
-
-	ret = open_xsk(tx_ifindex, &tx_xsk);
-	if (!ASSERT_OK(ret, "open_xsk(TX_NAME)"))
-		goto out;
+	/* Setup separate AF_XDP for RX interface. */
 
 	ret = open_xsk(rx_ifindex, &rx_xsk);
 	if (!ASSERT_OK(ret, "open_xsk(RX_NAME)"))
@@ -354,18 +448,38 @@ void test_xdp_metadata(void)
 	if (!ASSERT_GE(ret, 0, "bpf_map_update_elem"))
 		goto out;
 
-	/* Send packet destined to RX AF_XDP socket. */
+	switch_ns_to_tx(&tok);
+
+	/* Setup separate AF_XDP for TX interface nad send packet to the RX socket. */
+	tx_ifindex = if_nametoindex(TX_NAME);
+	ret = open_xsk(tx_ifindex, &tx_xsk);
+	if (!ASSERT_OK(ret, "open_xsk(TX_NAME)"))
+		goto out;
+
 	if (!ASSERT_GE(generate_packet(&tx_xsk, AF_XDP_CONSUMER_PORT), 0,
 		       "generate AF_XDP_CONSUMER_PORT"))
 		goto out;
 
-	/* Verify AF_XDP RX packet has proper metadata. */
-	if (!ASSERT_GE(verify_xsk_metadata(&rx_xsk), 0,
+	switch_ns_to_rx(&tok);
+
+	/* Verify packet sent from AF_XDP has proper metadata. */
+	if (!ASSERT_GE(verify_xsk_metadata(&rx_xsk, true), 0,
 		       "verify_xsk_metadata"))
 		goto out;
 
+	switch_ns_to_tx(&tok);
 	complete_tx(&tx_xsk);
 
+	/* Now check metadata of packet, generated with network stack */
+	if (!ASSERT_GE(generate_packet_inet(), 0, "generate UDP packet"))
+		goto out;
+
+	switch_ns_to_rx(&tok);
+
+	if (!ASSERT_GE(verify_xsk_metadata(&rx_xsk, false), 0,
+		       "verify_xsk_metadata"))
+		goto out;
+
 	/* Make sure freplace correctly picks up original bound device
 	 * and doesn't crash.
 	 */
@@ -383,11 +497,15 @@ void test_xdp_metadata(void)
 	if (!ASSERT_OK(xdp_metadata2__attach(bpf_obj2), "attach freplace"))
 		goto out;
 
+	switch_ns_to_tx(&tok);
+
 	/* Send packet to trigger . */
 	if (!ASSERT_GE(generate_packet(&tx_xsk, AF_XDP_CONSUMER_PORT), 0,
 		       "generate freplace packet"))
 		goto out;
 
+	switch_ns_to_rx(&tok);
+
 	while (!retries--) {
 		if (bpf_obj2->bss->called)
 			break;
@@ -402,5 +520,6 @@ out:
 	xdp_metadata__destroy(bpf_obj);
 	if (tok)
 		close_netns(tok);
-	SYS_NOFAIL("ip netns del xdp_metadata");
+	SYS_NOFAIL("ip netns del " RX_NETNS_NAME);
+	SYS_NOFAIL("ip netns del " TX_NETNS_NAME);
 }
diff --git a/tools/testing/selftests/bpf/progs/access_map_in_map.c b/tools/testing/selftests/bpf/progs/access_map_in_map.c
new file mode 100644
index 000000000000..1126871c2ebd
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/access_map_in_map.c
@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <linux/bpf.h>
+#include <time.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+
+struct inner_map_type {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(key_size, 4);
+	__uint(value_size, 4);
+	__uint(max_entries, 1);
+} inner_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 1);
+	__array(values, struct inner_map_type);
+} outer_array_map SEC(".maps") = {
+	.values = {
+		[0] = &inner_map,
+	},
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 1);
+	__array(values, struct inner_map_type);
+} outer_htab_map SEC(".maps") = {
+	.values = {
+		[0] = &inner_map,
+	},
+};
+
+char _license[] SEC("license") = "GPL";
+
+int tgid = 0;
+
+static int acc_map_in_map(void *outer_map)
+{
+	int i, key, value = 0xdeadbeef;
+	void *inner_map;
+
+	if ((bpf_get_current_pid_tgid() >> 32) != tgid)
+		return 0;
+
+	/* Find nonexistent inner map */
+	key = 1;
+	inner_map = bpf_map_lookup_elem(outer_map, &key);
+	if (inner_map)
+		return 0;
+
+	/* Find the old inner map */
+	key = 0;
+	inner_map = bpf_map_lookup_elem(outer_map, &key);
+	if (!inner_map)
+		return 0;
+
+	/* Wait for the old inner map to be replaced */
+	for (i = 0; i < 2048; i++)
+		bpf_map_update_elem(inner_map, &key, &value, 0);
+
+	return 0;
+}
+
+SEC("?kprobe/" SYS_PREFIX "sys_getpgid")
+int access_map_in_array(void *ctx)
+{
+	return acc_map_in_map(&outer_array_map);
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int sleepable_access_map_in_array(void *ctx)
+{
+	return acc_map_in_map(&outer_array_map);
+}
+
+SEC("?kprobe/" SYS_PREFIX "sys_getpgid")
+int access_map_in_htab(void *ctx)
+{
+	return acc_map_in_map(&outer_htab_map);
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int sleepable_access_map_in_htab(void *ctx)
+{
+	return acc_map_in_map(&outer_htab_map);
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c
index feaaa2b89c57..5014a17d6c02 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c
@@ -20,7 +20,7 @@ struct {
 } hashmap1 SEC(".maps");
 
 /* will set before prog run */
-volatile const __u32 num_cpus = 0;
+volatile const __s32 num_cpus = 0;
 
 /* will collect results during prog run */
 __u32 key_sum_a = 0, key_sum_b = 0, key_sum_c = 0;
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c
index f2b8167b72a8..442f4ca39fd7 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c
@@ -35,6 +35,8 @@ int dump_task_stack(struct bpf_iter__task *ctx)
 	return 0;
 }
 
+int num_user_stacks = 0;
+
 SEC("iter/task")
 int get_task_user_stacks(struct bpf_iter__task *ctx)
 {
@@ -51,6 +53,9 @@ int get_task_user_stacks(struct bpf_iter__task *ctx)
 	if (res <= 0)
 		return 0;
 
+	/* Only one task, the current one, should succeed */
+	++num_user_stacks;
+
 	buf_sz += res;
 
 	/* If the verifier doesn't refine bpf_get_task_stack res, and instead
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c
index dd923dc637d5..423b39e60b6f 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c
@@ -35,7 +35,7 @@ SEC("iter/task_vma") int proc_maps(struct bpf_iter__task_vma *ctx)
 		return 0;
 
 	file = vma->vm_file;
-	if (task->tgid != pid) {
+	if (task->tgid != (pid_t)pid) {
 		if (one_task)
 			one_task_error = 1;
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c
index 96131b9a1caa..6cbb3393f243 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c
@@ -22,7 +22,7 @@ int dump_task(struct bpf_iter__task *ctx)
 		return 0;
 	}
 
-	if (task->pid != tid)
+	if (task->pid != (pid_t)tid)
 		num_unknown_tid++;
 	else
 		num_known_tid++;
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c
index 400fdf8d6233..dbf61c44acac 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c
@@ -45,7 +45,7 @@ int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
 	}
 
 	/* fill seq_file buffer */
-	for (i = 0; i < print_len; i++)
+	for (i = 0; i < (int)print_len; i++)
 		bpf_seq_write(seq, &seq_num, sizeof(seq_num));
 
 	return ret;
diff --git a/tools/testing/selftests/bpf/progs/bpf_loop_bench.c b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c
index 4ce76eb064c4..d461746fd3c1 100644
--- a/tools/testing/selftests/bpf/progs/bpf_loop_bench.c
+++ b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c
@@ -15,13 +15,16 @@ static int empty_callback(__u32 index, void *data)
 	return 0;
 }
 
+static int outer_loop(__u32 index, void *data)
+{
+	bpf_loop(nr_loops, empty_callback, NULL, 0);
+	__sync_add_and_fetch(&hits, nr_loops);
+	return 0;
+}
+
 SEC("fentry/" SYS_PREFIX "sys_getpgid")
 int benchmark(void *ctx)
 {
-	for (int i = 0; i < 1000; i++) {
-		bpf_loop(nr_loops, empty_callback, NULL, 0);
-
-		__sync_add_and_fetch(&hits, nr_loops);
-	}
+	bpf_loop(1000, outer_loop, NULL, 0);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index 799fff4995d8..2fd59970c43a 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
@@ -71,6 +71,7 @@
 #define __retval_unpriv(val)	__attribute__((btf_decl_tag("comment:test_retval_unpriv="#val)))
 #define __auxiliary		__attribute__((btf_decl_tag("comment:test_auxiliary")))
 #define __auxiliary_unpriv	__attribute__((btf_decl_tag("comment:test_auxiliary_unpriv")))
+#define __btf_path(path)	__attribute__((btf_decl_tag("comment:test_btf_path=" path)))
 
 /* Convenience macro for use with 'asm volatile' blocks */
 #define __naked __attribute__((naked))
diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
index 0b793a102791..1bdc680b0e0e 100644
--- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
+++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
@@ -26,6 +26,7 @@
 #define IPV6_AUTOFLOWLABEL	70
 
 #define TC_ACT_UNSPEC		(-1)
+#define TC_ACT_OK		0
 #define TC_ACT_SHOT		2
 
 #define SOL_TCP			6
diff --git a/tools/testing/selftests/bpf/progs/cb_refs.c b/tools/testing/selftests/bpf/progs/cb_refs.c
index 76d661b20e87..56c764df8196 100644
--- a/tools/testing/selftests/bpf/progs/cb_refs.c
+++ b/tools/testing/selftests/bpf/progs/cb_refs.c
@@ -33,6 +33,7 @@ int underflow_prog(void *ctx)
 	if (!p)
 		return 0;
 	bpf_for_each_map_elem(&array_map, cb1, &p, 0);
+	bpf_kfunc_call_test_release(p);
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c
index b7fa8804e19d..45a0e9f492a9 100644
--- a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c
+++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c
@@ -11,7 +11,7 @@
 __u32 invocations = 0;
 __u32 assertion_error = 0;
 __u32 retval_value = 0;
-__u32 page_size = 0;
+__s32 page_size = 0;
 
 SEC("cgroup/setsockopt")
 int get_retval(struct bpf_sockopt *ctx)
diff --git a/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c b/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c
index 0fa564a5cc5b..9fe9c4a4e8f6 100644
--- a/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c
+++ b/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c
@@ -78,7 +78,7 @@ int BPF_PROG(cgrp_kfunc_acquire_fp, struct cgroup *cgrp, const char *path)
 }
 
 SEC("kretprobe/cgroup_destroy_locked")
-__failure __msg("reg type unsupported for arg#0 function")
+__failure __msg("calling kernel function bpf_cgroup_acquire is not allowed")
 int BPF_PROG(cgrp_kfunc_acquire_unsafe_kretprobe, struct cgroup *cgrp)
 {
 	struct cgroup *acquired;
diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c b/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c
index a043d8fefdac..610c2427fd93 100644
--- a/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c
+++ b/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c
@@ -21,50 +21,100 @@ struct {
 	__type(value, long);
 } map_b SEC(".maps");
 
+int target_hid = 0;
+bool is_cgroup1 = 0;
+
+struct cgroup *bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id) __ksym;
+void bpf_cgroup_release(struct cgroup *cgrp) __ksym;
+
+static void __on_lookup(struct cgroup *cgrp)
+{
+	bpf_cgrp_storage_delete(&map_a, cgrp);
+	bpf_cgrp_storage_delete(&map_b, cgrp);
+}
+
 SEC("fentry/bpf_local_storage_lookup")
 int BPF_PROG(on_lookup)
 {
 	struct task_struct *task = bpf_get_current_task_btf();
+	struct cgroup *cgrp;
+
+	if (is_cgroup1) {
+		cgrp = bpf_task_get_cgroup1(task, target_hid);
+		if (!cgrp)
+			return 0;
 
-	bpf_cgrp_storage_delete(&map_a, task->cgroups->dfl_cgrp);
-	bpf_cgrp_storage_delete(&map_b, task->cgroups->dfl_cgrp);
+		__on_lookup(cgrp);
+		bpf_cgroup_release(cgrp);
+		return 0;
+	}
+
+	__on_lookup(task->cgroups->dfl_cgrp);
 	return 0;
 }
 
-SEC("fentry/bpf_local_storage_update")
-int BPF_PROG(on_update)
+static void __on_update(struct cgroup *cgrp)
 {
-	struct task_struct *task = bpf_get_current_task_btf();
 	long *ptr;
 
-	ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0,
-				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (ptr)
 		*ptr += 1;
 
-	ptr = bpf_cgrp_storage_get(&map_b, task->cgroups->dfl_cgrp, 0,
-				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	ptr = bpf_cgrp_storage_get(&map_b, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (ptr)
 		*ptr += 1;
+}
 
+SEC("fentry/bpf_local_storage_update")
+int BPF_PROG(on_update)
+{
+	struct task_struct *task = bpf_get_current_task_btf();
+	struct cgroup *cgrp;
+
+	if (is_cgroup1) {
+		cgrp = bpf_task_get_cgroup1(task, target_hid);
+		if (!cgrp)
+			return 0;
+
+		__on_update(cgrp);
+		bpf_cgroup_release(cgrp);
+		return 0;
+	}
+
+	__on_update(task->cgroups->dfl_cgrp);
 	return 0;
 }
 
-SEC("tp_btf/sys_enter")
-int BPF_PROG(on_enter, struct pt_regs *regs, long id)
+static void __on_enter(struct pt_regs *regs, long id, struct cgroup *cgrp)
 {
-	struct task_struct *task;
 	long *ptr;
 
-	task = bpf_get_current_task_btf();
-	ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0,
-				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (ptr)
 		*ptr = 200;
 
-	ptr = bpf_cgrp_storage_get(&map_b, task->cgroups->dfl_cgrp, 0,
-				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	ptr = bpf_cgrp_storage_get(&map_b, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (ptr)
 		*ptr = 100;
+}
+
+SEC("tp_btf/sys_enter")
+int BPF_PROG(on_enter, struct pt_regs *regs, long id)
+{
+	struct task_struct *task = bpf_get_current_task_btf();
+	struct cgroup *cgrp;
+
+	if (is_cgroup1) {
+		cgrp = bpf_task_get_cgroup1(task, target_hid);
+		if (!cgrp)
+			return 0;
+
+		__on_enter(regs, id, cgrp);
+		bpf_cgroup_release(cgrp);
+		return 0;
+	}
+
+	__on_enter(regs, id, task->cgroups->dfl_cgrp);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c b/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c
index 4c7844e1dbfa..5e282c16eadc 100644
--- a/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c
+++ b/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c
@@ -15,9 +15,13 @@ struct {
 	__type(value, long);
 } map_a SEC(".maps");
 
-__u32 target_pid;
+__s32 target_pid;
 __u64 cgroup_id;
+int target_hid;
+bool is_cgroup1;
 
+struct cgroup *bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id) __ksym;
+void bpf_cgroup_release(struct cgroup *cgrp) __ksym;
 void bpf_rcu_read_lock(void) __ksym;
 void bpf_rcu_read_unlock(void) __ksym;
 
@@ -37,23 +41,50 @@ int cgroup_iter(struct bpf_iter__cgroup *ctx)
 	return 0;
 }
 
+static void __no_rcu_lock(struct cgroup *cgrp)
+{
+	long *ptr;
+
+	/* Note that trace rcu is held in sleepable prog, so we can use
+	 * bpf_cgrp_storage_get() in sleepable prog.
+	 */
+	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0,
+				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (ptr)
+		cgroup_id = cgrp->kn->id;
+}
+
 SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
-int no_rcu_lock(void *ctx)
+int cgrp1_no_rcu_lock(void *ctx)
 {
 	struct task_struct *task;
 	struct cgroup *cgrp;
-	long *ptr;
+
+	task = bpf_get_current_task_btf();
+	if (task->pid != target_pid)
+		return 0;
+
+	/* bpf_task_get_cgroup1 can work in sleepable prog */
+	cgrp = bpf_task_get_cgroup1(task, target_hid);
+	if (!cgrp)
+		return 0;
+
+	__no_rcu_lock(cgrp);
+	bpf_cgroup_release(cgrp);
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int no_rcu_lock(void *ctx)
+{
+	struct task_struct *task;
 
 	task = bpf_get_current_task_btf();
 	if (task->pid != target_pid)
 		return 0;
 
 	/* task->cgroups is untrusted in sleepable prog outside of RCU CS */
-	cgrp = task->cgroups->dfl_cgrp;
-	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0,
-				   BPF_LOCAL_STORAGE_GET_F_CREATE);
-	if (ptr)
-		cgroup_id = cgrp->kn->id;
+	__no_rcu_lock(task->cgroups->dfl_cgrp);
 	return 0;
 }
 
@@ -68,6 +99,22 @@ int yes_rcu_lock(void *ctx)
 	if (task->pid != target_pid)
 		return 0;
 
+	if (is_cgroup1) {
+		bpf_rcu_read_lock();
+		cgrp = bpf_task_get_cgroup1(task, target_hid);
+		if (!cgrp) {
+			bpf_rcu_read_unlock();
+			return 0;
+		}
+
+		ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE);
+		if (ptr)
+			cgroup_id = cgrp->kn->id;
+		bpf_cgroup_release(cgrp);
+		bpf_rcu_read_unlock();
+		return 0;
+	}
+
 	bpf_rcu_read_lock();
 	cgrp = task->cgroups->dfl_cgrp;
 	/* cgrp is trusted under RCU CS */
diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c b/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c
index 9ebb8e2fe541..1c348f000f38 100644
--- a/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c
+++ b/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c
@@ -27,62 +27,100 @@ pid_t target_pid = 0;
 int mismatch_cnt = 0;
 int enter_cnt = 0;
 int exit_cnt = 0;
+int target_hid = 0;
+bool is_cgroup1 = 0;
 
-SEC("tp_btf/sys_enter")
-int BPF_PROG(on_enter, struct pt_regs *regs, long id)
+struct cgroup *bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id) __ksym;
+void bpf_cgroup_release(struct cgroup *cgrp) __ksym;
+
+static void __on_enter(struct pt_regs *regs, long id, struct cgroup *cgrp)
 {
-	struct task_struct *task;
 	long *ptr;
 	int err;
 
-	task = bpf_get_current_task_btf();
-	if (task->pid != target_pid)
-		return 0;
-
 	/* populate value 0 */
-	ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0,
+	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0,
 				   BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!ptr)
-		return 0;
+		return;
 
 	/* delete value 0 */
-	err = bpf_cgrp_storage_delete(&map_a, task->cgroups->dfl_cgrp);
+	err = bpf_cgrp_storage_delete(&map_a, cgrp);
 	if (err)
-		return 0;
+		return;
 
 	/* value is not available */
-	ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0, 0);
+	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, 0);
 	if (ptr)
-		return 0;
+		return;
 
 	/* re-populate the value */
-	ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0,
+	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0,
 				   BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!ptr)
-		return 0;
+		return;
 	__sync_fetch_and_add(&enter_cnt, 1);
 	*ptr = MAGIC_VALUE + enter_cnt;
-
-	return 0;
 }
 
-SEC("tp_btf/sys_exit")
-int BPF_PROG(on_exit, struct pt_regs *regs, long id)
+SEC("tp_btf/sys_enter")
+int BPF_PROG(on_enter, struct pt_regs *regs, long id)
 {
 	struct task_struct *task;
-	long *ptr;
+	struct cgroup *cgrp;
 
 	task = bpf_get_current_task_btf();
 	if (task->pid != target_pid)
 		return 0;
 
-	ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0,
+	if (is_cgroup1) {
+		cgrp = bpf_task_get_cgroup1(task, target_hid);
+		if (!cgrp)
+			return 0;
+
+		__on_enter(regs, id, cgrp);
+		bpf_cgroup_release(cgrp);
+		return 0;
+	}
+
+	__on_enter(regs, id, task->cgroups->dfl_cgrp);
+	return 0;
+}
+
+static void __on_exit(struct pt_regs *regs, long id, struct cgroup *cgrp)
+{
+	long *ptr;
+
+	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0,
 				   BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!ptr)
-		return 0;
+		return;
 
 	__sync_fetch_and_add(&exit_cnt, 1);
 	if (*ptr != MAGIC_VALUE + exit_cnt)
 		__sync_fetch_and_add(&mismatch_cnt, 1);
+}
+
+SEC("tp_btf/sys_exit")
+int BPF_PROG(on_exit, struct pt_regs *regs, long id)
+{
+	struct task_struct *task;
+	struct cgroup *cgrp;
+
+	task = bpf_get_current_task_btf();
+	if (task->pid != target_pid)
+		return 0;
+
+	if (is_cgroup1) {
+		cgrp = bpf_task_get_cgroup1(task, target_hid);
+		if (!cgrp)
+			return 0;
+
+		__on_exit(regs, id, cgrp);
+		bpf_cgroup_release(cgrp);
+		return 0;
+	}
+
+	__on_exit(regs, id, task->cgroups->dfl_cgrp);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/cpumask_common.h b/tools/testing/selftests/bpf/progs/cpumask_common.h
index b15c588ace15..0cd4aebb97cf 100644
--- a/tools/testing/selftests/bpf/progs/cpumask_common.h
+++ b/tools/testing/selftests/bpf/progs/cpumask_common.h
@@ -54,6 +54,7 @@ bool bpf_cpumask_full(const struct cpumask *cpumask) __ksym;
 void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) __ksym;
 u32 bpf_cpumask_any_distribute(const struct cpumask *src) __ksym;
 u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1, const struct cpumask *src2) __ksym;
+u32 bpf_cpumask_weight(const struct cpumask *cpumask) __ksym;
 
 void bpf_rcu_read_lock(void) __ksym;
 void bpf_rcu_read_unlock(void) __ksym;
diff --git a/tools/testing/selftests/bpf/progs/cpumask_success.c b/tools/testing/selftests/bpf/progs/cpumask_success.c
index 674a63424dee..7a1e64c6c065 100644
--- a/tools/testing/selftests/bpf/progs/cpumask_success.c
+++ b/tools/testing/selftests/bpf/progs/cpumask_success.c
@@ -332,7 +332,7 @@ SEC("tp_btf/task_newtask")
 int BPF_PROG(test_copy_any_anyand, struct task_struct *task, u64 clone_flags)
 {
 	struct bpf_cpumask *mask1, *mask2, *dst1, *dst2;
-	u32 cpu;
+	int cpu;
 
 	if (!is_test_task())
 		return 0;
@@ -461,6 +461,49 @@ int BPF_PROG(test_global_mask_rcu, struct task_struct *task, u64 clone_flags)
 }
 
 SEC("tp_btf/task_newtask")
+int BPF_PROG(test_cpumask_weight, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *local;
+
+	if (!is_test_task())
+		return 0;
+
+	local = create_cpumask();
+	if (!local)
+		return 0;
+
+	if (bpf_cpumask_weight(cast(local)) != 0) {
+		err = 3;
+		goto out;
+	}
+
+	bpf_cpumask_set_cpu(0, local);
+	if (bpf_cpumask_weight(cast(local)) != 1) {
+		err = 4;
+		goto out;
+	}
+
+	/*
+	 * Make sure that adding additional CPUs changes the weight. Test to
+	 * see whether the CPU was set to account for running on UP machines.
+	 */
+	bpf_cpumask_set_cpu(1, local);
+	if (bpf_cpumask_test_cpu(1, cast(local)) && bpf_cpumask_weight(cast(local)) != 2) {
+		err = 5;
+		goto out;
+	}
+
+	bpf_cpumask_clear(local);
+	if (bpf_cpumask_weight(cast(local)) != 0) {
+		err = 6;
+		goto out;
+	}
+out:
+	bpf_cpumask_release(local);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
 __success
 int BPF_PROG(test_refcount_null_tracking, struct task_struct *task, u64 clone_flags)
 {
diff --git a/tools/testing/selftests/bpf/progs/exceptions.c b/tools/testing/selftests/bpf/progs/exceptions.c
index 2811ee842b01..f09cd14d8e04 100644
--- a/tools/testing/selftests/bpf/progs/exceptions.c
+++ b/tools/testing/selftests/bpf/progs/exceptions.c
@@ -210,7 +210,7 @@ __noinline int assert_zero_gfunc(u64 c)
 {
 	volatile u64 cookie = c;
 
-	bpf_assert_eq(cookie, 0);
+	bpf_assert(bpf_cmp_unlikely(cookie, ==, 0));
 	return 0;
 }
 
@@ -218,7 +218,7 @@ __noinline int assert_neg_gfunc(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_lt(cookie, 0);
+	bpf_assert(bpf_cmp_unlikely(cookie, <, 0));
 	return 0;
 }
 
@@ -226,7 +226,7 @@ __noinline int assert_pos_gfunc(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_gt(cookie, 0);
+	bpf_assert(bpf_cmp_unlikely(cookie, >, 0));
 	return 0;
 }
 
@@ -234,7 +234,7 @@ __noinline int assert_negeq_gfunc(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_le(cookie, -1);
+	bpf_assert(bpf_cmp_unlikely(cookie, <=, -1));
 	return 0;
 }
 
@@ -242,7 +242,7 @@ __noinline int assert_poseq_gfunc(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_ge(cookie, 1);
+	bpf_assert(bpf_cmp_unlikely(cookie, >=, 1));
 	return 0;
 }
 
@@ -258,7 +258,7 @@ __noinline int assert_zero_gfunc_with(u64 c)
 {
 	volatile u64 cookie = c;
 
-	bpf_assert_eq_with(cookie, 0, cookie + 100);
+	bpf_assert_with(bpf_cmp_unlikely(cookie, ==, 0), cookie + 100);
 	return 0;
 }
 
@@ -266,7 +266,7 @@ __noinline int assert_neg_gfunc_with(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_lt_with(cookie, 0, cookie + 100);
+	bpf_assert_with(bpf_cmp_unlikely(cookie, <, 0), cookie + 100);
 	return 0;
 }
 
@@ -274,7 +274,7 @@ __noinline int assert_pos_gfunc_with(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_gt_with(cookie, 0, cookie + 100);
+	bpf_assert_with(bpf_cmp_unlikely(cookie, >, 0), cookie + 100);
 	return 0;
 }
 
@@ -282,7 +282,7 @@ __noinline int assert_negeq_gfunc_with(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_le_with(cookie, -1, cookie + 100);
+	bpf_assert_with(bpf_cmp_unlikely(cookie, <=, -1), cookie + 100);
 	return 0;
 }
 
@@ -290,7 +290,7 @@ __noinline int assert_poseq_gfunc_with(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_ge_with(cookie, 1, cookie + 100);
+	bpf_assert_with(bpf_cmp_unlikely(cookie, >=, 1), cookie + 100);
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/exceptions_assert.c b/tools/testing/selftests/bpf/progs/exceptions_assert.c
index e1e5c54a6a11..5e0a1ca96d4e 100644
--- a/tools/testing/selftests/bpf/progs/exceptions_assert.c
+++ b/tools/testing/selftests/bpf/progs/exceptions_assert.c
@@ -11,55 +11,55 @@
 #define check_assert(type, op, name, value)				\
 	SEC("?tc")							\
 	__log_level(2) __failure					\
-	int check_assert_##op##_##name(void *ctx)			\
+	int check_assert_##name(void *ctx)				\
 	{								\
 		type num = bpf_ktime_get_ns();				\
-		bpf_assert_##op(num, value);				\
+		bpf_assert(bpf_cmp_unlikely(num, op, value));		\
 		return *(u64 *)num;					\
 	}
 
-__msg(": R0_w=-2147483648 R10=fp0")
-check_assert(s64, eq, int_min, INT_MIN);
-__msg(": R0_w=2147483647 R10=fp0")
-check_assert(s64, eq, int_max, INT_MAX);
-__msg(": R0_w=0 R10=fp0")
-check_assert(s64, eq, zero, 0);
-__msg(": R0_w=-9223372036854775808 R1_w=-9223372036854775808 R10=fp0")
-check_assert(s64, eq, llong_min, LLONG_MIN);
-__msg(": R0_w=9223372036854775807 R1_w=9223372036854775807 R10=fp0")
-check_assert(s64, eq, llong_max, LLONG_MAX);
-
-__msg(": R0_w=scalar(smax=2147483646) R10=fp0")
-check_assert(s64, lt, pos, INT_MAX);
-__msg(": R0_w=scalar(smax=-1,umin=9223372036854775808,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
-check_assert(s64, lt, zero, 0);
-__msg(": R0_w=scalar(smax=-2147483649,umin=9223372036854775808,umax=18446744071562067967,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
-check_assert(s64, lt, neg, INT_MIN);
-
-__msg(": R0_w=scalar(smax=2147483647) R10=fp0")
-check_assert(s64, le, pos, INT_MAX);
-__msg(": R0_w=scalar(smax=0) R10=fp0")
-check_assert(s64, le, zero, 0);
-__msg(": R0_w=scalar(smax=-2147483648,umin=9223372036854775808,umax=18446744071562067968,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
-check_assert(s64, le, neg, INT_MIN);
-
-__msg(": R0_w=scalar(smin=umin=2147483648,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))")
-check_assert(s64, gt, pos, INT_MAX);
-__msg(": R0_w=scalar(smin=umin=1,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))")
-check_assert(s64, gt, zero, 0);
-__msg(": R0_w=scalar(smin=-2147483647) R10=fp0")
-check_assert(s64, gt, neg, INT_MIN);
-
-__msg(": R0_w=scalar(smin=umin=2147483647,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))")
-check_assert(s64, ge, pos, INT_MAX);
-__msg(": R0_w=scalar(smin=0,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff)) R10=fp0")
-check_assert(s64, ge, zero, 0);
-__msg(": R0_w=scalar(smin=-2147483648) R10=fp0")
-check_assert(s64, ge, neg, INT_MIN);
+__msg(": R0_w=0xffffffff80000000")
+check_assert(s64, ==, eq_int_min, INT_MIN);
+__msg(": R0_w=0x7fffffff")
+check_assert(s64, ==, eq_int_max, INT_MAX);
+__msg(": R0_w=0")
+check_assert(s64, ==, eq_zero, 0);
+__msg(": R0_w=0x8000000000000000 R1_w=0x8000000000000000")
+check_assert(s64, ==, eq_llong_min, LLONG_MIN);
+__msg(": R0_w=0x7fffffffffffffff R1_w=0x7fffffffffffffff")
+check_assert(s64, ==, eq_llong_max, LLONG_MAX);
+
+__msg(": R0_w=scalar(id=1,smax=0x7ffffffe)")
+check_assert(s64, <, lt_pos, INT_MAX);
+__msg(": R0_w=scalar(id=1,smax=-1,umin=0x8000000000000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
+check_assert(s64, <, lt_zero, 0);
+__msg(": R0_w=scalar(id=1,smax=0xffffffff7fffffff")
+check_assert(s64, <, lt_neg, INT_MIN);
+
+__msg(": R0_w=scalar(id=1,smax=0x7fffffff)")
+check_assert(s64, <=, le_pos, INT_MAX);
+__msg(": R0_w=scalar(id=1,smax=0)")
+check_assert(s64, <=, le_zero, 0);
+__msg(": R0_w=scalar(id=1,smax=0xffffffff80000000")
+check_assert(s64, <=, le_neg, INT_MIN);
+
+__msg(": R0_w=scalar(id=1,smin=umin=0x80000000,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+check_assert(s64, >, gt_pos, INT_MAX);
+__msg(": R0_w=scalar(id=1,smin=umin=1,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+check_assert(s64, >, gt_zero, 0);
+__msg(": R0_w=scalar(id=1,smin=0xffffffff80000001")
+check_assert(s64, >, gt_neg, INT_MIN);
+
+__msg(": R0_w=scalar(id=1,smin=umin=0x7fffffff,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+check_assert(s64, >=, ge_pos, INT_MAX);
+__msg(": R0_w=scalar(id=1,smin=0,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+check_assert(s64, >=, ge_zero, 0);
+__msg(": R0_w=scalar(id=1,smin=0xffffffff80000000")
+check_assert(s64, >=, ge_neg, INT_MIN);
 
 SEC("?tc")
 __log_level(2) __failure
-__msg(": R0=0 R1=ctx(off=0,imm=0) R2=scalar(smin=smin32=-2147483646,smax=smax32=2147483645) R10=fp0")
+__msg(": R0=0 R1=ctx() R2=scalar(smin=0xffffffff80000002,smax=smax32=0x7ffffffd,smin32=0x80000002) R10=fp0")
 int check_assert_range_s64(struct __sk_buff *ctx)
 {
 	struct bpf_sock *sk = ctx->sk;
@@ -75,7 +75,7 @@ int check_assert_range_s64(struct __sk_buff *ctx)
 
 SEC("?tc")
 __log_level(2) __failure
-__msg(": R1=ctx(off=0,imm=0) R2=scalar(smin=umin=smin32=umin32=4096,smax=umax=smax32=umax32=8192,var_off=(0x0; 0x3fff))")
+__msg(": R1=ctx() R2=scalar(smin=umin=smin32=umin32=4096,smax=umax=smax32=umax32=8192,var_off=(0x0; 0x3fff))")
 int check_assert_range_u64(struct __sk_buff *ctx)
 {
 	u64 num = ctx->len;
@@ -86,7 +86,7 @@ int check_assert_range_u64(struct __sk_buff *ctx)
 
 SEC("?tc")
 __log_level(2) __failure
-__msg(": R0=0 R1=ctx(off=0,imm=0) R2=4096 R10=fp0")
+__msg(": R0=0 R1=ctx() R2=4096 R10=fp0")
 int check_assert_single_range_s64(struct __sk_buff *ctx)
 {
 	struct bpf_sock *sk = ctx->sk;
@@ -103,7 +103,7 @@ int check_assert_single_range_s64(struct __sk_buff *ctx)
 
 SEC("?tc")
 __log_level(2) __failure
-__msg(": R1=ctx(off=0,imm=0) R2=4096 R10=fp0")
+__msg(": R1=ctx() R2=4096 R10=fp0")
 int check_assert_single_range_u64(struct __sk_buff *ctx)
 {
 	u64 num = ctx->len;
@@ -114,7 +114,7 @@ int check_assert_single_range_u64(struct __sk_buff *ctx)
 
 SEC("?tc")
 __log_level(2) __failure
-__msg(": R1=pkt(off=64,r=64,imm=0) R2=pkt_end(off=0,imm=0) R6=pkt(off=0,r=64,imm=0) R10=fp0")
+__msg(": R1=pkt(off=64,r=64) R2=pkt_end() R6=pkt(r=64) R10=fp0")
 int check_assert_generic(struct __sk_buff *ctx)
 {
 	u8 *data_end = (void *)(long)ctx->data_end;
@@ -125,7 +125,7 @@ int check_assert_generic(struct __sk_buff *ctx)
 }
 
 SEC("?fentry/bpf_check")
-__failure __msg("At program exit the register R0 has value (0x40; 0x0)")
+__failure __msg("At program exit the register R1 has smin=64 smax=64")
 int check_assert_with_return(void *ctx)
 {
 	bpf_assert_with(!ctx, 64);
diff --git a/tools/testing/selftests/bpf/progs/exceptions_fail.c b/tools/testing/selftests/bpf/progs/exceptions_fail.c
index 4c39e920dac2..9cceb6521143 100644
--- a/tools/testing/selftests/bpf/progs/exceptions_fail.c
+++ b/tools/testing/selftests/bpf/progs/exceptions_fail.c
@@ -171,6 +171,7 @@ int reject_with_rbtree_add_throw(void *ctx)
 		return 0;
 	bpf_spin_lock(&lock);
 	bpf_rbtree_add(&rbtree, &f->node, rbless);
+	bpf_spin_unlock(&lock);
 	return 0;
 }
 
@@ -214,6 +215,7 @@ int reject_with_cb_reference(void *ctx)
 	if (!f)
 		return 0;
 	bpf_loop(5, subprog_cb_ref, NULL, 0);
+	bpf_obj_drop(f);
 	return 0;
 }
 
@@ -306,7 +308,7 @@ int reject_set_exception_cb_bad_ret1(void *ctx)
 }
 
 SEC("?fentry/bpf_check")
-__failure __msg("At program exit the register R0 has value (0x40; 0x0) should")
+__failure __msg("At program exit the register R1 has smin=64 smax=64 should")
 int reject_set_exception_cb_bad_ret2(void *ctx)
 {
 	bpf_throw(64);
diff --git a/tools/testing/selftests/bpf/progs/fentry_recursive.c b/tools/testing/selftests/bpf/progs/fentry_recursive.c
new file mode 100644
index 000000000000..2c9fb5ac42b2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fentry_recursive.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Red Hat, Inc. */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+/* Dummy fentry bpf prog for testing fentry attachment chains */
+SEC("fentry/XXX")
+int BPF_PROG(recursive_attach, int a)
+{
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/fentry_recursive_target.c b/tools/testing/selftests/bpf/progs/fentry_recursive_target.c
new file mode 100644
index 000000000000..267c876d0aba
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fentry_recursive_target.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Red Hat, Inc. */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+/* Dummy fentry bpf prog for testing fentry attachment chains. It's going to be
+ * a start of the chain.
+ */
+SEC("fentry/bpf_testmod_fentry_test1")
+int BPF_PROG(test1, int a)
+{
+	return 0;
+}
+
+/* Dummy bpf prog for testing attach_btf presence when attaching an fentry
+ * program.
+ */
+SEC("raw_tp/sys_enter")
+int BPF_PROG(fentry_target, struct pt_regs *regs, long id)
+{
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/freplace_dead_global_func.c b/tools/testing/selftests/bpf/progs/freplace_dead_global_func.c
new file mode 100644
index 000000000000..e6a75f86cac6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/freplace_dead_global_func.c
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+SEC("freplace")
+int freplace_prog(void)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/freplace_unreliable_prog.c b/tools/testing/selftests/bpf/progs/freplace_unreliable_prog.c
new file mode 100644
index 000000000000..624078abf3de
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/freplace_unreliable_prog.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+SEC("freplace/btf_unreliable_kprobe")
+/* context type is what BPF verifier expects for kprobe context, but target
+ * program has `stuct whatever *ctx` argument, so freplace operation will be
+ * rejected with the following message:
+ *
+ * arg0 replace_btf_unreliable_kprobe(struct pt_regs *) doesn't match btf_unreliable_kprobe(struct whatever *)
+ */
+int replace_btf_unreliable_kprobe(bpf_user_pt_regs_t *ctx)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c
index c20c4e38b71c..fe971992e635 100644
--- a/tools/testing/selftests/bpf/progs/iters.c
+++ b/tools/testing/selftests/bpf/progs/iters.c
@@ -6,7 +6,7 @@
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
 
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#define ARRAY_SIZE(x) (int)(sizeof(x) / sizeof((x)[0]))
 
 static volatile int zero = 0;
 
@@ -676,7 +676,7 @@ static __noinline int sum(struct bpf_iter_num *it, int *arr, __u32 n)
 
 	while ((t = bpf_iter_num_next(it))) {
 		i = *t;
-		if (i >= n)
+		if ((__u32)i >= n)
 			break;
 		sum += arr[i];
 	}
@@ -846,7 +846,7 @@ __naked int delayed_precision_mark(void)
 		"call %[bpf_iter_num_next];"
 		"if r0 == 0 goto 2f;"
 		"if r6 != 42 goto 3f;"
-		"r7 = -32;"
+		"r7 = -33;"
 		"call %[bpf_get_prandom_u32];"
 		"r6 = r0;"
 		"goto 1b;\n"
@@ -1411,4 +1411,26 @@ __naked int checkpoint_states_deletion(void)
 	);
 }
 
+struct {
+	int data[32];
+	int n;
+} loop_data;
+
+SEC("raw_tp")
+__success
+int iter_arr_with_actual_elem_count(const void *ctx)
+{
+	int i, n = loop_data.n, sum = 0;
+
+	if (n > ARRAY_SIZE(loop_data.data))
+		return 0;
+
+	bpf_for(i, 0, n) {
+		/* no rechecking of i against ARRAY_SIZE(loop_data.n) */
+		sum += loop_data.data[i];
+	}
+
+	return sum;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/iters_task_vma.c b/tools/testing/selftests/bpf/progs/iters_task_vma.c
index e085a51d153e..dc0c3691dcc2 100644
--- a/tools/testing/selftests/bpf/progs/iters_task_vma.c
+++ b/tools/testing/selftests/bpf/progs/iters_task_vma.c
@@ -28,9 +28,8 @@ int iter_task_vma_for_each(const void *ctx)
 		return 0;
 
 	bpf_for_each(task_vma, vma, task, 0) {
-		if (seen >= 1000)
+		if (bpf_cmp_unlikely(seen, >=, 1000))
 			break;
-		barrier_var(seen);
 
 		vm_ranges[seen].vm_start = vma->vm_start;
 		vm_ranges[seen].vm_end = vma->vm_end;
diff --git a/tools/testing/selftests/bpf/progs/linked_funcs1.c b/tools/testing/selftests/bpf/progs/linked_funcs1.c
index c4b49ceea967..cc79dddac182 100644
--- a/tools/testing/selftests/bpf/progs/linked_funcs1.c
+++ b/tools/testing/selftests/bpf/progs/linked_funcs1.c
@@ -8,7 +8,7 @@
 #include "bpf_misc.h"
 
 /* weak and shared between two files */
-const volatile int my_tid __weak;
+const volatile __u32 my_tid __weak;
 long syscall_id __weak;
 
 int output_val1;
diff --git a/tools/testing/selftests/bpf/progs/linked_funcs2.c b/tools/testing/selftests/bpf/progs/linked_funcs2.c
index 013ff0645f0c..942cc5526ddf 100644
--- a/tools/testing/selftests/bpf/progs/linked_funcs2.c
+++ b/tools/testing/selftests/bpf/progs/linked_funcs2.c
@@ -68,7 +68,7 @@ int BPF_PROG(handler2, struct pt_regs *regs, long id)
 {
 	static volatile int whatever;
 
-	if (my_tid != (u32)bpf_get_current_pid_tgid() || id != syscall_id)
+	if (my_tid != (s32)bpf_get_current_pid_tgid() || id != syscall_id)
 		return 0;
 
 	/* make sure we have CO-RE relocations in main program */
diff --git a/tools/testing/selftests/bpf/progs/linked_list.c b/tools/testing/selftests/bpf/progs/linked_list.c
index 84d1777a9e6c..26205ca80679 100644
--- a/tools/testing/selftests/bpf/progs/linked_list.c
+++ b/tools/testing/selftests/bpf/progs/linked_list.c
@@ -6,7 +6,7 @@
 #include "bpf_experimental.h"
 
 #ifndef ARRAY_SIZE
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#define ARRAY_SIZE(x) (int)(sizeof(x) / sizeof((x)[0]))
 #endif
 
 #include "linked_list.h"
diff --git a/tools/testing/selftests/bpf/progs/local_kptr_stash.c b/tools/testing/selftests/bpf/progs/local_kptr_stash.c
index b567a666d2b8..75043ffc5dad 100644
--- a/tools/testing/selftests/bpf/progs/local_kptr_stash.c
+++ b/tools/testing/selftests/bpf/progs/local_kptr_stash.c
@@ -14,16 +14,41 @@ struct node_data {
 	struct bpf_rb_node node;
 };
 
+struct refcounted_node {
+	long data;
+	struct bpf_rb_node rb_node;
+	struct bpf_refcount refcount;
+};
+
+struct stash {
+	struct bpf_spin_lock l;
+	struct refcounted_node __kptr *stashed;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct stash);
+	__uint(max_entries, 10);
+} refcounted_node_stash SEC(".maps");
+
 struct plain_local {
 	long key;
 	long data;
 };
 
+struct local_with_root {
+	long key;
+	struct bpf_spin_lock l;
+	struct bpf_rb_root r __contains(node_data, node);
+};
+
 struct map_value {
 	struct prog_test_ref_kfunc *not_kptr;
 	struct prog_test_ref_kfunc __kptr *val;
 	struct node_data __kptr *node;
 	struct plain_local __kptr *plain;
+	struct local_with_root __kptr *local_root;
 };
 
 /* This is necessary so that LLVM generates BTF for node_data struct
@@ -38,6 +63,7 @@ struct map_value {
  * Had to do the same w/ bpf_kfunc_call_test_release below
  */
 struct node_data *just_here_because_btf_bug;
+struct refcounted_node *just_here_because_btf_bug2;
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
@@ -46,6 +72,17 @@ struct {
 	__uint(max_entries, 2);
 } some_nodes SEC(".maps");
 
+static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	struct node_data *node_a;
+	struct node_data *node_b;
+
+	node_a = container_of(a, struct node_data, node);
+	node_b = container_of(b, struct node_data, node);
+
+	return node_a->key < node_b->key;
+}
+
 static int create_and_stash(int idx, int val)
 {
 	struct map_value *mapval;
@@ -95,6 +132,41 @@ long stash_plain(void *ctx)
 }
 
 SEC("tc")
+long stash_local_with_root(void *ctx)
+{
+	struct local_with_root *res;
+	struct map_value *mapval;
+	struct node_data *n;
+	int idx = 0;
+
+	mapval = bpf_map_lookup_elem(&some_nodes, &idx);
+	if (!mapval)
+		return 1;
+
+	res = bpf_obj_new(typeof(*res));
+	if (!res)
+		return 2;
+	res->key = 41;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n) {
+		bpf_obj_drop(res);
+		return 3;
+	}
+
+	bpf_spin_lock(&res->l);
+	bpf_rbtree_add(&res->r, &n->node, less);
+	bpf_spin_unlock(&res->l);
+
+	res = bpf_kptr_xchg(&mapval->local_root, res);
+	if (res) {
+		bpf_obj_drop(res);
+		return 4;
+	}
+	return 0;
+}
+
+SEC("tc")
 long unstash_rb_node(void *ctx)
 {
 	struct map_value *mapval;
@@ -132,4 +204,56 @@ long stash_test_ref_kfunc(void *ctx)
 	return 0;
 }
 
+SEC("tc")
+long refcount_acquire_without_unstash(void *ctx)
+{
+	struct refcounted_node *p;
+	struct stash *s;
+	int ret = 0;
+
+	s = bpf_map_lookup_elem(&refcounted_node_stash, &ret);
+	if (!s)
+		return 1;
+
+	if (!s->stashed)
+		/* refcount_acquire failure is expected when no refcounted_node
+		 * has been stashed before this program executes
+		 */
+		return 2;
+
+	p = bpf_refcount_acquire(s->stashed);
+	if (!p)
+		return 3;
+
+	ret = s->stashed ? s->stashed->data : -1;
+	bpf_obj_drop(p);
+	return ret;
+}
+
+/* Helper for refcount_acquire_without_unstash test */
+SEC("tc")
+long stash_refcounted_node(void *ctx)
+{
+	struct refcounted_node *p;
+	struct stash *s;
+	int key = 0;
+
+	s = bpf_map_lookup_elem(&refcounted_node_stash, &key);
+	if (!s)
+		return 1;
+
+	p = bpf_obj_new(typeof(*p));
+	if (!p)
+		return 2;
+	p->data = 42;
+
+	p = bpf_kptr_xchg(&s->stashed, p);
+	if (p) {
+		bpf_obj_drop(p);
+		return 3;
+	}
+
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/local_storage.c b/tools/testing/selftests/bpf/progs/local_storage.c
index bc8ea56671a1..e5e3a8b8dd07 100644
--- a/tools/testing/selftests/bpf/progs/local_storage.c
+++ b/tools/testing/selftests/bpf/progs/local_storage.c
@@ -13,7 +13,7 @@ char _license[] SEC("license") = "GPL";
 
 #define DUMMY_STORAGE_VALUE 0xdeadbeef
 
-int monitored_pid = 0;
+__u32 monitored_pid = 0;
 int inode_storage_result = -1;
 int sk_storage_result = -1;
 int task_storage_result = -1;
diff --git a/tools/testing/selftests/bpf/progs/lsm.c b/tools/testing/selftests/bpf/progs/lsm.c
index fadfdd98707c..0c13b7409947 100644
--- a/tools/testing/selftests/bpf/progs/lsm.c
+++ b/tools/testing/selftests/bpf/progs/lsm.c
@@ -92,7 +92,7 @@ int BPF_PROG(test_int_hook, struct vm_area_struct *vma,
 	if (ret != 0)
 		return ret;
 
-	__u32 pid = bpf_get_current_pid_tgid() >> 32;
+	__s32 pid = bpf_get_current_pid_tgid() >> 32;
 	int is_stack = 0;
 
 	is_stack = (vma->vm_start <= vma->vm_mm->start_stack &&
diff --git a/tools/testing/selftests/bpf/progs/map_in_map_btf.c b/tools/testing/selftests/bpf/progs/map_in_map_btf.c
new file mode 100644
index 000000000000..7a1336d7b16a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/map_in_map_btf.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+struct node_data {
+	__u64 data;
+	struct bpf_list_node node;
+};
+
+struct map_value {
+	struct bpf_list_head head __contains(node_data, node);
+	struct bpf_spin_lock lock;
+};
+
+struct inner_array_type {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 1);
+} inner_array SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__uint(key_size, 4);
+	__uint(value_size, 4);
+	__uint(max_entries, 1);
+	__array(values, struct inner_array_type);
+} outer_array SEC(".maps") = {
+	.values = {
+		[0] = &inner_array,
+	},
+};
+
+char _license[] SEC("license") = "GPL";
+
+int pid = 0;
+bool done = false;
+
+SEC("fentry/" SYS_PREFIX "sys_nanosleep")
+int add_to_list_in_inner_array(void *ctx)
+{
+	struct map_value *value;
+	struct node_data *new;
+	struct bpf_map *map;
+	int zero = 0;
+
+	if (done || (u32)bpf_get_current_pid_tgid() != pid)
+		return 0;
+
+	map = bpf_map_lookup_elem(&outer_array, &zero);
+	if (!map)
+		return 0;
+
+	value = bpf_map_lookup_elem(map, &zero);
+	if (!value)
+		return 0;
+
+	new = bpf_obj_new(typeof(*new));
+	if (!new)
+		return 0;
+
+	bpf_spin_lock(&value->lock);
+	bpf_list_push_back(&value->head, &new->node);
+	bpf_spin_unlock(&value->lock);
+	done = true;
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/normal_map_btf.c b/tools/testing/selftests/bpf/progs/normal_map_btf.c
new file mode 100644
index 000000000000..a45c9299552c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/normal_map_btf.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+struct node_data {
+	__u64 data;
+	struct bpf_list_node node;
+};
+
+struct map_value {
+	struct bpf_list_head head __contains(node_data, node);
+	struct bpf_spin_lock lock;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 1);
+} array SEC(".maps");
+
+char _license[] SEC("license") = "GPL";
+
+int pid = 0;
+bool done = false;
+
+SEC("fentry/" SYS_PREFIX "sys_nanosleep")
+int add_to_list_in_array(void *ctx)
+{
+	struct map_value *value;
+	struct node_data *new;
+	int zero = 0;
+
+	if (done || (int)bpf_get_current_pid_tgid() != pid)
+		return 0;
+
+	value = bpf_map_lookup_elem(&array, &zero);
+	if (!value)
+		return 0;
+
+	new = bpf_obj_new(typeof(*new));
+	if (!new)
+		return 0;
+
+	bpf_spin_lock(&value->lock);
+	bpf_list_push_back(&value->head, &new->node);
+	bpf_spin_unlock(&value->lock);
+	done = true;
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c b/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c
index 1a891d30f1fe..f2b8eb2ff76f 100644
--- a/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c
+++ b/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c
@@ -17,6 +17,10 @@ struct val_with_rb_root_t {
 	struct bpf_spin_lock lock;
 };
 
+struct val_600b_t {
+	char b[600];
+};
+
 struct elem {
 	long sum;
 	struct val_t __percpu_kptr *pc;
@@ -161,4 +165,18 @@ int BPF_PROG(test_array_map_7)
 	return 0;
 }
 
+SEC("?fentry.s/bpf_fentry_test1")
+__failure __msg("bpf_percpu_obj_new type size (600) is greater than 512")
+int BPF_PROG(test_array_map_8)
+{
+	struct val_600b_t __percpu_kptr *p;
+
+	p = bpf_percpu_obj_new(struct val_600b_t);
+	if (!p)
+		return 0;
+
+	bpf_percpu_obj_drop(p);
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h
index 897061930cb7..de3b6e4e4d0a 100644
--- a/tools/testing/selftests/bpf/progs/profiler.inc.h
+++ b/tools/testing/selftests/bpf/progs/profiler.inc.h
@@ -7,6 +7,7 @@
 
 #include "profiler.h"
 #include "err.h"
+#include "bpf_experimental.h"
 
 #ifndef NULL
 #define NULL 0
@@ -132,7 +133,7 @@ struct {
 } disallowed_exec_inodes SEC(".maps");
 
 #ifndef ARRAY_SIZE
-#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(arr[0]))
+#define ARRAY_SIZE(arr) (int)(sizeof(arr) / sizeof(arr[0]))
 #endif
 
 static INLINE bool IS_ERR(const void* ptr)
@@ -221,8 +222,7 @@ static INLINE void* read_full_cgroup_path(struct kernfs_node* cgroup_node,
 			return payload;
 		if (cgroup_node == cgroup_root_node)
 			*root_pos = payload - payload_start;
-		if (filepart_length <= MAX_PATH) {
-			barrier_var(filepart_length);
+		if (bpf_cmp_likely(filepart_length, <=, MAX_PATH)) {
 			payload += filepart_length;
 		}
 		cgroup_node = BPF_CORE_READ(cgroup_node, parent);
@@ -305,9 +305,7 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data,
 	size_t cgroup_root_length =
 		bpf_probe_read_kernel_str(payload, MAX_PATH,
 					  BPF_CORE_READ(root_kernfs, name));
-	barrier_var(cgroup_root_length);
-	if (cgroup_root_length <= MAX_PATH) {
-		barrier_var(cgroup_root_length);
+	if (bpf_cmp_likely(cgroup_root_length, <=, MAX_PATH)) {
 		cgroup_data->cgroup_root_length = cgroup_root_length;
 		payload += cgroup_root_length;
 	}
@@ -315,9 +313,7 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data,
 	size_t cgroup_proc_length =
 		bpf_probe_read_kernel_str(payload, MAX_PATH,
 					  BPF_CORE_READ(proc_kernfs, name));
-	barrier_var(cgroup_proc_length);
-	if (cgroup_proc_length <= MAX_PATH) {
-		barrier_var(cgroup_proc_length);
+	if (bpf_cmp_likely(cgroup_proc_length, <=, MAX_PATH)) {
 		cgroup_data->cgroup_proc_length = cgroup_proc_length;
 		payload += cgroup_proc_length;
 	}
@@ -347,9 +343,7 @@ static INLINE void* populate_var_metadata(struct var_metadata_t* metadata,
 	metadata->comm_length = 0;
 
 	size_t comm_length = bpf_core_read_str(payload, TASK_COMM_LEN, &task->comm);
-	barrier_var(comm_length);
-	if (comm_length <= TASK_COMM_LEN) {
-		barrier_var(comm_length);
+	if (bpf_cmp_likely(comm_length, <=, TASK_COMM_LEN)) {
 		metadata->comm_length = comm_length;
 		payload += comm_length;
 	}
@@ -494,10 +488,9 @@ read_absolute_file_path_from_dentry(struct dentry* filp_dentry, void* payload)
 		filepart_length =
 			bpf_probe_read_kernel_str(payload, MAX_PATH,
 						  BPF_CORE_READ(filp_dentry, d_name.name));
-		barrier_var(filepart_length);
-		if (filepart_length > MAX_PATH)
+		bpf_nop_mov(filepart_length);
+		if (bpf_cmp_unlikely(filepart_length, >, MAX_PATH))
 			break;
-		barrier_var(filepart_length);
 		payload += filepart_length;
 		length += filepart_length;
 
@@ -579,9 +572,7 @@ ssize_t BPF_KPROBE(kprobe__proc_sys_write,
 
 	size_t sysctl_val_length = bpf_probe_read_kernel_str(payload,
 							     CTL_MAXNAME, buf);
-	barrier_var(sysctl_val_length);
-	if (sysctl_val_length <= CTL_MAXNAME) {
-		barrier_var(sysctl_val_length);
+	if (bpf_cmp_likely(sysctl_val_length, <=, CTL_MAXNAME)) {
 		sysctl_data->sysctl_val_length = sysctl_val_length;
 		payload += sysctl_val_length;
 	}
@@ -590,9 +581,7 @@ ssize_t BPF_KPROBE(kprobe__proc_sys_write,
 		bpf_probe_read_kernel_str(payload, MAX_PATH,
 					  BPF_CORE_READ(filp, f_path.dentry,
 							d_name.name));
-	barrier_var(sysctl_path_length);
-	if (sysctl_path_length <= MAX_PATH) {
-		barrier_var(sysctl_path_length);
+	if (bpf_cmp_likely(sysctl_path_length, <=, MAX_PATH)) {
 		sysctl_data->sysctl_path_length = sysctl_path_length;
 		payload += sysctl_path_length;
 	}
@@ -645,7 +634,7 @@ int raw_tracepoint__sched_process_exit(void* ctx)
 	for (int i = 0; i < ARRAY_SIZE(arr_struct->array); i++) {
 		struct var_kill_data_t* past_kill_data = &arr_struct->array[i];
 
-		if (past_kill_data != NULL && past_kill_data->kill_target_pid == tpid) {
+		if (past_kill_data != NULL && past_kill_data->kill_target_pid == (pid_t)tpid) {
 			bpf_probe_read_kernel(kill_data, sizeof(*past_kill_data),
 					      past_kill_data);
 			void* payload = kill_data->payload;
@@ -658,9 +647,7 @@ int raw_tracepoint__sched_process_exit(void* ctx)
 			kill_data->kill_target_cgroup_proc_length = 0;
 
 			size_t comm_length = bpf_core_read_str(payload, TASK_COMM_LEN, &task->comm);
-			barrier_var(comm_length);
-			if (comm_length <= TASK_COMM_LEN) {
-				barrier_var(comm_length);
+			if (bpf_cmp_likely(comm_length, <=, TASK_COMM_LEN)) {
 				kill_data->kill_target_name_length = comm_length;
 				payload += comm_length;
 			}
@@ -669,9 +656,7 @@ int raw_tracepoint__sched_process_exit(void* ctx)
 				bpf_probe_read_kernel_str(payload,
 							  KILL_TARGET_LEN,
 							  BPF_CORE_READ(proc_kernfs, name));
-			barrier_var(cgroup_proc_length);
-			if (cgroup_proc_length <= KILL_TARGET_LEN) {
-				barrier_var(cgroup_proc_length);
+			if (bpf_cmp_likely(cgroup_proc_length, <=, KILL_TARGET_LEN)) {
 				kill_data->kill_target_cgroup_proc_length = cgroup_proc_length;
 				payload += cgroup_proc_length;
 			}
@@ -731,9 +716,7 @@ int raw_tracepoint__sched_process_exec(struct bpf_raw_tracepoint_args* ctx)
 	const char* filename = BPF_CORE_READ(bprm, filename);
 	size_t bin_path_length =
 		bpf_probe_read_kernel_str(payload, MAX_FILENAME_LEN, filename);
-	barrier_var(bin_path_length);
-	if (bin_path_length <= MAX_FILENAME_LEN) {
-		barrier_var(bin_path_length);
+	if (bpf_cmp_likely(bin_path_length, <=, MAX_FILENAME_LEN)) {
 		proc_exec_data->bin_path_length = bin_path_length;
 		payload += bin_path_length;
 	}
@@ -743,8 +726,7 @@ int raw_tracepoint__sched_process_exec(struct bpf_raw_tracepoint_args* ctx)
 	unsigned int cmdline_length = probe_read_lim(payload, arg_start,
 						     arg_end - arg_start, MAX_ARGS_LEN);
 
-	if (cmdline_length <= MAX_ARGS_LEN) {
-		barrier_var(cmdline_length);
+	if (bpf_cmp_likely(cmdline_length, <=, MAX_ARGS_LEN)) {
 		proc_exec_data->cmdline_length = cmdline_length;
 		payload += cmdline_length;
 	}
@@ -821,9 +803,7 @@ int kprobe_ret__do_filp_open(struct pt_regs* ctx)
 	payload = populate_cgroup_info(&filemod_data->cgroup_data, task, payload);
 
 	size_t len = read_absolute_file_path_from_dentry(filp_dentry, payload);
-	barrier_var(len);
-	if (len <= MAX_FILEPATH_LENGTH) {
-		barrier_var(len);
+	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
 		payload += len;
 		filemod_data->dst_filepath_length = len;
 	}
@@ -876,17 +856,13 @@ int BPF_KPROBE(kprobe__vfs_link,
 	payload = populate_cgroup_info(&filemod_data->cgroup_data, task, payload);
 
 	size_t len = read_absolute_file_path_from_dentry(old_dentry, payload);
-	barrier_var(len);
-	if (len <= MAX_FILEPATH_LENGTH) {
-		barrier_var(len);
+	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
 		payload += len;
 		filemod_data->src_filepath_length = len;
 	}
 
 	len = read_absolute_file_path_from_dentry(new_dentry, payload);
-	barrier_var(len);
-	if (len <= MAX_FILEPATH_LENGTH) {
-		barrier_var(len);
+	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
 		payload += len;
 		filemod_data->dst_filepath_length = len;
 	}
@@ -936,16 +912,12 @@ int BPF_KPROBE(kprobe__vfs_symlink, struct inode* dir, struct dentry* dentry,
 
 	size_t len = bpf_probe_read_kernel_str(payload, MAX_FILEPATH_LENGTH,
 					       oldname);
-	barrier_var(len);
-	if (len <= MAX_FILEPATH_LENGTH) {
-		barrier_var(len);
+	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
 		payload += len;
 		filemod_data->src_filepath_length = len;
 	}
 	len = read_absolute_file_path_from_dentry(dentry, payload);
-	barrier_var(len);
-	if (len <= MAX_FILEPATH_LENGTH) {
-		barrier_var(len);
+	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
 		payload += len;
 		filemod_data->dst_filepath_length = len;
 	}
diff --git a/tools/testing/selftests/bpf/progs/pyperf180.c b/tools/testing/selftests/bpf/progs/pyperf180.c
index c39f559d3100..42c4a8b62e36 100644
--- a/tools/testing/selftests/bpf/progs/pyperf180.c
+++ b/tools/testing/selftests/bpf/progs/pyperf180.c
@@ -1,4 +1,26 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2019 Facebook
 #define STACK_MAX_LEN 180
+
+/* llvm upstream commit at clang18
+ *   https://github.com/llvm/llvm-project/commit/1a2e77cf9e11dbf56b5720c607313a566eebb16e
+ * changed inlining behavior and caused compilation failure as some branch
+ * target distance exceeded 16bit representation which is the maximum for
+ * cpu v1/v2/v3. Macro __BPF_CPU_VERSION__ is later implemented in clang18
+ * to specify which cpu version is used for compilation. So a smaller
+ * unroll_count can be set if __BPF_CPU_VERSION__ is less than 4, which
+ * reduced some branch target distances and resolved the compilation failure.
+ *
+ * To capture the case where a developer/ci uses clang18 but the corresponding
+ * repo checkpoint does not have __BPF_CPU_VERSION__, a smaller unroll_count
+ * will be set as well to prevent potential compilation failures.
+ */
+#ifdef __BPF_CPU_VERSION__
+#if __BPF_CPU_VERSION__ < 4
+#define UNROLL_COUNT 90
+#endif
+#elif __clang_major__ == 18
+#define UNROLL_COUNT 90
+#endif
+
 #include "pyperf.h"
diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c
index 1ef07f6ee580..1553b9c16aa7 100644
--- a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c
+++ b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c
@@ -54,6 +54,25 @@ long rbtree_refcounted_node_ref_escapes(void *ctx)
 }
 
 SEC("?tc")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
+long refcount_acquire_maybe_null(void *ctx)
+{
+	struct node_acquire *n, *m;
+
+	n = bpf_obj_new(typeof(*n));
+	/* Intentionally not testing !n
+	 * it's MAYBE_NULL for refcount_acquire
+	 */
+	m = bpf_refcount_acquire(n);
+	if (m)
+		bpf_obj_drop(m);
+	if (n)
+		bpf_obj_drop(n);
+
+	return 0;
+}
+
+SEC("?tc")
 __failure __msg("Unreleased reference id=3 alloc_insn=9")
 long rbtree_refcounted_node_ref_escapes_owning_input(void *ctx)
 {
diff --git a/tools/testing/selftests/bpf/progs/sockopt_inherit.c b/tools/testing/selftests/bpf/progs/sockopt_inherit.c
index c8f59caa4639..a3434b840928 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_inherit.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_inherit.c
@@ -9,7 +9,7 @@ char _license[] SEC("license") = "GPL";
 #define CUSTOM_INHERIT2			1
 #define CUSTOM_LISTENER			2
 
-__u32 page_size = 0;
+__s32 page_size = 0;
 
 struct sockopt_inherit {
 	__u8 val;
diff --git a/tools/testing/selftests/bpf/progs/sockopt_multi.c b/tools/testing/selftests/bpf/progs/sockopt_multi.c
index 96f29fce050b..db67278e12d4 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_multi.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_multi.c
@@ -5,7 +5,7 @@
 
 char _license[] SEC("license") = "GPL";
 
-__u32 page_size = 0;
+__s32 page_size = 0;
 
 SEC("cgroup/getsockopt")
 int _getsockopt_child(struct bpf_sockopt *ctx)
diff --git a/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c
index dbe235ede7f3..83753b00a556 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c
@@ -9,7 +9,7 @@
 
 char _license[] SEC("license") = "GPL";
 
-__u32 page_size = 0;
+__s32 page_size = 0;
 
 SEC("cgroup/setsockopt")
 int sockopt_qos_to_cc(struct bpf_sockopt *ctx)
diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h
index e02cfd380746..40df2cc26eaf 100644
--- a/tools/testing/selftests/bpf/progs/strobemeta.h
+++ b/tools/testing/selftests/bpf/progs/strobemeta.h
@@ -24,9 +24,11 @@ struct task_struct {};
 #define STACK_TABLE_EPOCH_SHIFT 20
 #define STROBE_MAX_STR_LEN 1
 #define STROBE_MAX_CFGS 32
+#define READ_MAP_VAR_PAYLOAD_CAP					\
+	((1 + STROBE_MAX_MAP_ENTRIES * 2) * STROBE_MAX_STR_LEN)
 #define STROBE_MAX_PAYLOAD						\
 	(STROBE_MAX_STRS * STROBE_MAX_STR_LEN +				\
-	STROBE_MAX_MAPS * (1 + STROBE_MAX_MAP_ENTRIES * 2) * STROBE_MAX_STR_LEN)
+	 STROBE_MAX_MAPS * READ_MAP_VAR_PAYLOAD_CAP)
 
 struct strobe_value_header {
 	/*
@@ -355,7 +357,7 @@ static __always_inline uint64_t read_str_var(struct strobemeta_cfg *cfg,
 					     size_t idx, void *tls_base,
 					     struct strobe_value_generic *value,
 					     struct strobemeta_payload *data,
-					     void *payload)
+					     size_t off)
 {
 	void *location;
 	uint64_t len;
@@ -366,7 +368,7 @@ static __always_inline uint64_t read_str_var(struct strobemeta_cfg *cfg,
 		return 0;
 
 	bpf_probe_read_user(value, sizeof(struct strobe_value_generic), location);
-	len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN, value->ptr);
+	len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN, value->ptr);
 	/*
 	 * if bpf_probe_read_user_str returns error (<0), due to casting to
 	 * unsinged int, it will become big number, so next check is
@@ -378,14 +380,14 @@ static __always_inline uint64_t read_str_var(struct strobemeta_cfg *cfg,
 		return 0;
 
 	data->str_lens[idx] = len;
-	return len;
+	return off + len;
 }
 
-static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
-					  size_t idx, void *tls_base,
-					  struct strobe_value_generic *value,
-					  struct strobemeta_payload *data,
-					  void *payload)
+static __always_inline uint64_t read_map_var(struct strobemeta_cfg *cfg,
+					     size_t idx, void *tls_base,
+					     struct strobe_value_generic *value,
+					     struct strobemeta_payload *data,
+					     size_t off)
 {
 	struct strobe_map_descr* descr = &data->map_descrs[idx];
 	struct strobe_map_raw map;
@@ -397,11 +399,11 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
 
 	location = calc_location(&cfg->map_locs[idx], tls_base);
 	if (!location)
-		return payload;
+		return off;
 
 	bpf_probe_read_user(value, sizeof(struct strobe_value_generic), location);
 	if (bpf_probe_read_user(&map, sizeof(struct strobe_map_raw), value->ptr))
-		return payload;
+		return off;
 
 	descr->id = map.id;
 	descr->cnt = map.cnt;
@@ -410,10 +412,10 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
 		data->req_meta_valid = 1;
 	}
 
-	len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN, map.tag);
+	len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN, map.tag);
 	if (len <= STROBE_MAX_STR_LEN) {
 		descr->tag_len = len;
-		payload += len;
+		off += len;
 	}
 
 #ifdef NO_UNROLL
@@ -426,22 +428,22 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
 			break;
 
 		descr->key_lens[i] = 0;
-		len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN,
+		len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN,
 					      map.entries[i].key);
 		if (len <= STROBE_MAX_STR_LEN) {
 			descr->key_lens[i] = len;
-			payload += len;
+			off += len;
 		}
 		descr->val_lens[i] = 0;
-		len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN,
+		len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN,
 					      map.entries[i].val);
 		if (len <= STROBE_MAX_STR_LEN) {
 			descr->val_lens[i] = len;
-			payload += len;
+			off += len;
 		}
 	}
 
-	return payload;
+	return off;
 }
 
 #ifdef USE_BPF_LOOP
@@ -455,14 +457,20 @@ struct read_var_ctx {
 	struct strobemeta_payload *data;
 	void *tls_base;
 	struct strobemeta_cfg *cfg;
-	void *payload;
+	size_t payload_off;
 	/* value gets mutated */
 	struct strobe_value_generic *value;
 	enum read_type type;
 };
 
-static int read_var_callback(__u32 index, struct read_var_ctx *ctx)
+static int read_var_callback(__u64 index, struct read_var_ctx *ctx)
 {
+	/* lose precision info for ctx->payload_off, verifier won't track
+	 * double xor, barrier_var() is needed to force clang keep both xors.
+	 */
+	ctx->payload_off ^= index;
+	barrier_var(ctx->payload_off);
+	ctx->payload_off ^= index;
 	switch (ctx->type) {
 	case READ_INT_VAR:
 		if (index >= STROBE_MAX_INTS)
@@ -472,14 +480,18 @@ static int read_var_callback(__u32 index, struct read_var_ctx *ctx)
 	case READ_MAP_VAR:
 		if (index >= STROBE_MAX_MAPS)
 			return 1;
-		ctx->payload = read_map_var(ctx->cfg, index, ctx->tls_base,
-					    ctx->value, ctx->data, ctx->payload);
+		if (ctx->payload_off > sizeof(ctx->data->payload) - READ_MAP_VAR_PAYLOAD_CAP)
+			return 1;
+		ctx->payload_off = read_map_var(ctx->cfg, index, ctx->tls_base,
+						ctx->value, ctx->data, ctx->payload_off);
 		break;
 	case READ_STR_VAR:
 		if (index >= STROBE_MAX_STRS)
 			return 1;
-		ctx->payload += read_str_var(ctx->cfg, index, ctx->tls_base,
-					     ctx->value, ctx->data, ctx->payload);
+		if (ctx->payload_off > sizeof(ctx->data->payload) - STROBE_MAX_STR_LEN)
+			return 1;
+		ctx->payload_off = read_str_var(ctx->cfg, index, ctx->tls_base,
+						ctx->value, ctx->data, ctx->payload_off);
 		break;
 	}
 	return 0;
@@ -501,7 +513,8 @@ static void *read_strobe_meta(struct task_struct *task,
 	pid_t pid = bpf_get_current_pid_tgid() >> 32;
 	struct strobe_value_generic value = {0};
 	struct strobemeta_cfg *cfg;
-	void *tls_base, *payload;
+	size_t payload_off;
+	void *tls_base;
 
 	cfg = bpf_map_lookup_elem(&strobemeta_cfgs, &pid);
 	if (!cfg)
@@ -509,7 +522,7 @@ static void *read_strobe_meta(struct task_struct *task,
 
 	data->int_vals_set_mask = 0;
 	data->req_meta_valid = 0;
-	payload = data->payload;
+	payload_off = 0;
 	/*
 	 * we don't have struct task_struct definition, it should be:
 	 * tls_base = (void *)task->thread.fsbase;
@@ -522,7 +535,7 @@ static void *read_strobe_meta(struct task_struct *task,
 		.tls_base = tls_base,
 		.value = &value,
 		.data = data,
-		.payload = payload,
+		.payload_off = 0,
 	};
 	int err;
 
@@ -540,6 +553,11 @@ static void *read_strobe_meta(struct task_struct *task,
 	err = bpf_loop(STROBE_MAX_MAPS, read_var_callback, &ctx, 0);
 	if (err != STROBE_MAX_MAPS)
 		return NULL;
+
+	payload_off = ctx.payload_off;
+	/* this should not really happen, here only to satisfy verifer */
+	if (payload_off > sizeof(data->payload))
+		payload_off = sizeof(data->payload);
 #else
 #ifdef NO_UNROLL
 #pragma clang loop unroll(disable)
@@ -555,7 +573,7 @@ static void *read_strobe_meta(struct task_struct *task,
 #pragma unroll
 #endif /* NO_UNROLL */
 	for (int i = 0; i < STROBE_MAX_STRS; ++i) {
-		payload += read_str_var(cfg, i, tls_base, &value, data, payload);
+		payload_off = read_str_var(cfg, i, tls_base, &value, data, payload_off);
 	}
 #ifdef NO_UNROLL
 #pragma clang loop unroll(disable)
@@ -563,7 +581,7 @@ static void *read_strobe_meta(struct task_struct *task,
 #pragma unroll
 #endif /* NO_UNROLL */
 	for (int i = 0; i < STROBE_MAX_MAPS; ++i) {
-		payload = read_map_var(cfg, i, tls_base, &value, data, payload);
+		payload_off = read_map_var(cfg, i, tls_base, &value, data, payload_off);
 	}
 #endif /* USE_BPF_LOOP */
 
@@ -571,7 +589,7 @@ static void *read_strobe_meta(struct task_struct *task,
 	 * return pointer right after end of payload, so it's possible to
 	 * calculate exact amount of useful data that needs to be sent
 	 */
-	return payload;
+	return &data->payload[payload_off];
 }
 
 SEC("raw_tracepoint/kfree_skb")
diff --git a/tools/testing/selftests/bpf/progs/syscall.c b/tools/testing/selftests/bpf/progs/syscall.c
index e550f728962d..3d3cafdebe72 100644
--- a/tools/testing/selftests/bpf/progs/syscall.c
+++ b/tools/testing/selftests/bpf/progs/syscall.c
@@ -6,9 +6,15 @@
 #include <bpf/bpf_tracing.h>
 #include <../../../tools/include/linux/filter.h>
 #include <linux/btf.h>
+#include <string.h>
+#include <errno.h>
 
 char _license[] SEC("license") = "GPL";
 
+struct bpf_map {
+	int id;
+}  __attribute__((preserve_access_index));
+
 struct args {
 	__u64 log_buf;
 	__u32 log_size;
@@ -27,6 +33,37 @@ struct args {
 	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \
 	BTF_INT_ENC(encoding, bits_offset, bits)
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, union bpf_attr);
+	__uint(max_entries, 1);
+} bpf_attr_array SEC(".maps");
+
+struct inner_map_type {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(key_size, 4);
+	__uint(value_size, 4);
+	__uint(max_entries, 1);
+} inner_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 1);
+	__array(values, struct inner_map_type);
+} outer_array_map SEC(".maps") = {
+	.values = {
+		[0] = &inner_map,
+	},
+};
+
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+	return (__u64) (unsigned long) ptr;
+}
+
 static int btf_load(void)
 {
 	struct btf_blob {
@@ -58,7 +95,7 @@ static int btf_load(void)
 }
 
 SEC("syscall")
-int bpf_prog(struct args *ctx)
+int load_prog(struct args *ctx)
 {
 	static char license[] = "GPL";
 	static struct bpf_insn insns[] = {
@@ -94,8 +131,8 @@ int bpf_prog(struct args *ctx)
 	map_create_attr.max_entries = ctx->max_entries;
 	map_create_attr.btf_fd = ret;
 
-	prog_load_attr.license = (long) license;
-	prog_load_attr.insns = (long) insns;
+	prog_load_attr.license = ptr_to_u64(license);
+	prog_load_attr.insns = ptr_to_u64(insns);
 	prog_load_attr.log_buf = ctx->log_buf;
 	prog_load_attr.log_size = ctx->log_size;
 	prog_load_attr.log_level = 1;
@@ -107,8 +144,8 @@ int bpf_prog(struct args *ctx)
 	insns[3].imm = ret;
 
 	map_update_attr.map_fd = ret;
-	map_update_attr.key = (long) &key;
-	map_update_attr.value = (long) &value;
+	map_update_attr.key = ptr_to_u64(&key);
+	map_update_attr.value = ptr_to_u64(&value);
 	ret = bpf_sys_bpf(BPF_MAP_UPDATE_ELEM, &map_update_attr, sizeof(map_update_attr));
 	if (ret < 0)
 		return ret;
@@ -119,3 +156,52 @@ int bpf_prog(struct args *ctx)
 	ctx->prog_fd = ret;
 	return 1;
 }
+
+SEC("syscall")
+int update_outer_map(void *ctx)
+{
+	int zero = 0, ret = 0, outer_fd = -1, inner_fd = -1, err;
+	const int attr_sz = sizeof(union bpf_attr);
+	union bpf_attr *attr;
+
+	attr = bpf_map_lookup_elem((struct bpf_map *)&bpf_attr_array, &zero);
+	if (!attr)
+		goto out;
+
+	memset(attr, 0, attr_sz);
+	attr->map_id = ((struct bpf_map *)&outer_array_map)->id;
+	outer_fd = bpf_sys_bpf(BPF_MAP_GET_FD_BY_ID, attr, attr_sz);
+	if (outer_fd < 0)
+		goto out;
+
+	memset(attr, 0, attr_sz);
+	attr->map_type = BPF_MAP_TYPE_ARRAY;
+	attr->key_size = 4;
+	attr->value_size = 4;
+	attr->max_entries = 1;
+	inner_fd = bpf_sys_bpf(BPF_MAP_CREATE, attr, attr_sz);
+	if (inner_fd < 0)
+		goto out;
+
+	memset(attr, 0, attr_sz);
+	attr->map_fd = outer_fd;
+	attr->key = ptr_to_u64(&zero);
+	attr->value = ptr_to_u64(&inner_fd);
+	err = bpf_sys_bpf(BPF_MAP_UPDATE_ELEM, attr, attr_sz);
+	if (err)
+		goto out;
+
+	memset(attr, 0, attr_sz);
+	attr->map_fd = outer_fd;
+	attr->key = ptr_to_u64(&zero);
+	err = bpf_sys_bpf(BPF_MAP_DELETE_ELEM, attr, attr_sz);
+	if (err)
+		goto out;
+	ret = 1;
+out:
+	if (inner_fd >= 0)
+		bpf_sys_close(inner_fd);
+	if (outer_fd >= 0)
+		bpf_sys_close(outer_fd);
+	return ret;
+}
diff --git a/tools/testing/selftests/bpf/progs/tailcall_poke.c b/tools/testing/selftests/bpf/progs/tailcall_poke.c
new file mode 100644
index 000000000000..c78b94b75e83
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_poke.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+SEC("?fentry/bpf_fentry_test1")
+int BPF_PROG(test, int a)
+{
+	bpf_tail_call_static(ctx, &jmp_table, 0);
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(call1, int a)
+{
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(call2, int a)
+{
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_failure.c b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c
index dcdea3127086..ad88a3796ddf 100644
--- a/tools/testing/selftests/bpf/progs/task_kfunc_failure.c
+++ b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c
@@ -248,7 +248,7 @@ int BPF_PROG(task_kfunc_from_pid_no_null_check, struct task_struct *task, u64 cl
 }
 
 SEC("lsm/task_free")
-__failure __msg("reg type unsupported for arg#0 function")
+__failure __msg("R1 must be a rcu pointer")
 int BPF_PROG(task_kfunc_from_lsm_task_free, struct task_struct *task)
 {
 	struct task_struct *acquired;
diff --git a/tools/testing/selftests/bpf/progs/test_bpf_ma.c b/tools/testing/selftests/bpf/progs/test_bpf_ma.c
index b685a4aba6bd..3494ca30fa7f 100644
--- a/tools/testing/selftests/bpf/progs/test_bpf_ma.c
+++ b/tools/testing/selftests/bpf/progs/test_bpf_ma.c
@@ -17,20 +17,23 @@ struct generic_map_value {
 
 char _license[] SEC("license") = "GPL";
 
-const unsigned int data_sizes[] = {8, 16, 32, 64, 96, 128, 192, 256, 512, 1024, 2048, 4096};
+const unsigned int data_sizes[] = {16, 32, 64, 96, 128, 192, 256, 512, 1024, 2048, 4096};
 const volatile unsigned int data_btf_ids[ARRAY_SIZE(data_sizes)] = {};
 
+const unsigned int percpu_data_sizes[] = {8, 16, 32, 64, 96, 128, 192, 256, 512};
+const volatile unsigned int percpu_data_btf_ids[ARRAY_SIZE(data_sizes)] = {};
+
 int err = 0;
-int pid = 0;
+u32 pid = 0;
 
 #define DEFINE_ARRAY_WITH_KPTR(_size) \
 	struct bin_data_##_size { \
 		char data[_size - sizeof(void *)]; \
 	}; \
+	/* See Commit 5d8d6634ccc, force btf generation for type bin_data_##_size */	\
+	struct bin_data_##_size *__bin_data_##_size; \
 	struct map_value_##_size { \
 		struct bin_data_##_size __kptr * data; \
-		/* To emit BTF info for bin_data_xx */ \
-		struct bin_data_##_size not_used; \
 	}; \
 	struct { \
 		__uint(type, BPF_MAP_TYPE_ARRAY); \
@@ -40,8 +43,12 @@ int pid = 0;
 	} array_##_size SEC(".maps")
 
 #define DEFINE_ARRAY_WITH_PERCPU_KPTR(_size) \
+	struct percpu_bin_data_##_size { \
+		char data[_size]; \
+	}; \
+	struct percpu_bin_data_##_size *__percpu_bin_data_##_size; \
 	struct map_value_percpu_##_size { \
-		struct bin_data_##_size __percpu_kptr * data; \
+		struct percpu_bin_data_##_size __percpu_kptr * data; \
 	}; \
 	struct { \
 		__uint(type, BPF_MAP_TYPE_ARRAY); \
@@ -114,7 +121,7 @@ static __always_inline void batch_percpu_alloc(struct bpf_map *map, unsigned int
 			return;
 		}
 		/* per-cpu allocator may not be able to refill in time */
-		new = bpf_percpu_obj_new_impl(data_btf_ids[idx], NULL);
+		new = bpf_percpu_obj_new_impl(percpu_data_btf_ids[idx], NULL);
 		if (!new)
 			continue;
 
@@ -166,7 +173,7 @@ static __always_inline void batch_percpu_free(struct bpf_map *map, unsigned int
 		batch_percpu_free((struct bpf_map *)(&array_percpu_##size), batch, idx); \
 	} while (0)
 
-DEFINE_ARRAY_WITH_KPTR(8);
+/* kptr doesn't support bin_data_8 which is a zero-sized array */
 DEFINE_ARRAY_WITH_KPTR(16);
 DEFINE_ARRAY_WITH_KPTR(32);
 DEFINE_ARRAY_WITH_KPTR(64);
@@ -179,7 +186,7 @@ DEFINE_ARRAY_WITH_KPTR(1024);
 DEFINE_ARRAY_WITH_KPTR(2048);
 DEFINE_ARRAY_WITH_KPTR(4096);
 
-/* per-cpu kptr doesn't support bin_data_8 which is a zero-sized array */
+DEFINE_ARRAY_WITH_PERCPU_KPTR(8);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(16);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(32);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(64);
@@ -188,9 +195,6 @@ DEFINE_ARRAY_WITH_PERCPU_KPTR(128);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(192);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(256);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(512);
-DEFINE_ARRAY_WITH_PERCPU_KPTR(1024);
-DEFINE_ARRAY_WITH_PERCPU_KPTR(2048);
-DEFINE_ARRAY_WITH_PERCPU_KPTR(4096);
 
 SEC("?fentry/" SYS_PREFIX "sys_nanosleep")
 int test_batch_alloc_free(void *ctx)
@@ -198,21 +202,20 @@ int test_batch_alloc_free(void *ctx)
 	if ((u32)bpf_get_current_pid_tgid() != pid)
 		return 0;
 
-	/* Alloc 128 8-bytes objects in batch to trigger refilling,
-	 * then free 128 8-bytes objects in batch to trigger freeing.
+	/* Alloc 128 16-bytes objects in batch to trigger refilling,
+	 * then free 128 16-bytes objects in batch to trigger freeing.
 	 */
-	CALL_BATCH_ALLOC_FREE(8, 128, 0);
-	CALL_BATCH_ALLOC_FREE(16, 128, 1);
-	CALL_BATCH_ALLOC_FREE(32, 128, 2);
-	CALL_BATCH_ALLOC_FREE(64, 128, 3);
-	CALL_BATCH_ALLOC_FREE(96, 128, 4);
-	CALL_BATCH_ALLOC_FREE(128, 128, 5);
-	CALL_BATCH_ALLOC_FREE(192, 128, 6);
-	CALL_BATCH_ALLOC_FREE(256, 128, 7);
-	CALL_BATCH_ALLOC_FREE(512, 64, 8);
-	CALL_BATCH_ALLOC_FREE(1024, 32, 9);
-	CALL_BATCH_ALLOC_FREE(2048, 16, 10);
-	CALL_BATCH_ALLOC_FREE(4096, 8, 11);
+	CALL_BATCH_ALLOC_FREE(16, 128, 0);
+	CALL_BATCH_ALLOC_FREE(32, 128, 1);
+	CALL_BATCH_ALLOC_FREE(64, 128, 2);
+	CALL_BATCH_ALLOC_FREE(96, 128, 3);
+	CALL_BATCH_ALLOC_FREE(128, 128, 4);
+	CALL_BATCH_ALLOC_FREE(192, 128, 5);
+	CALL_BATCH_ALLOC_FREE(256, 128, 6);
+	CALL_BATCH_ALLOC_FREE(512, 64, 7);
+	CALL_BATCH_ALLOC_FREE(1024, 32, 8);
+	CALL_BATCH_ALLOC_FREE(2048, 16, 9);
+	CALL_BATCH_ALLOC_FREE(4096, 8, 10);
 
 	return 0;
 }
@@ -223,21 +226,20 @@ int test_free_through_map_free(void *ctx)
 	if ((u32)bpf_get_current_pid_tgid() != pid)
 		return 0;
 
-	/* Alloc 128 8-bytes objects in batch to trigger refilling,
+	/* Alloc 128 16-bytes objects in batch to trigger refilling,
 	 * then free these objects through map free.
 	 */
-	CALL_BATCH_ALLOC(8, 128, 0);
-	CALL_BATCH_ALLOC(16, 128, 1);
-	CALL_BATCH_ALLOC(32, 128, 2);
-	CALL_BATCH_ALLOC(64, 128, 3);
-	CALL_BATCH_ALLOC(96, 128, 4);
-	CALL_BATCH_ALLOC(128, 128, 5);
-	CALL_BATCH_ALLOC(192, 128, 6);
-	CALL_BATCH_ALLOC(256, 128, 7);
-	CALL_BATCH_ALLOC(512, 64, 8);
-	CALL_BATCH_ALLOC(1024, 32, 9);
-	CALL_BATCH_ALLOC(2048, 16, 10);
-	CALL_BATCH_ALLOC(4096, 8, 11);
+	CALL_BATCH_ALLOC(16, 128, 0);
+	CALL_BATCH_ALLOC(32, 128, 1);
+	CALL_BATCH_ALLOC(64, 128, 2);
+	CALL_BATCH_ALLOC(96, 128, 3);
+	CALL_BATCH_ALLOC(128, 128, 4);
+	CALL_BATCH_ALLOC(192, 128, 5);
+	CALL_BATCH_ALLOC(256, 128, 6);
+	CALL_BATCH_ALLOC(512, 64, 7);
+	CALL_BATCH_ALLOC(1024, 32, 8);
+	CALL_BATCH_ALLOC(2048, 16, 9);
+	CALL_BATCH_ALLOC(4096, 8, 10);
 
 	return 0;
 }
@@ -248,9 +250,10 @@ int test_batch_percpu_alloc_free(void *ctx)
 	if ((u32)bpf_get_current_pid_tgid() != pid)
 		return 0;
 
-	/* Alloc 128 16-bytes per-cpu objects in batch to trigger refilling,
-	 * then free 128 16-bytes per-cpu objects in batch to trigger freeing.
+	/* Alloc 128 8-bytes per-cpu objects in batch to trigger refilling,
+	 * then free 128 8-bytes per-cpu objects in batch to trigger freeing.
 	 */
+	CALL_BATCH_PERCPU_ALLOC_FREE(8, 128, 0);
 	CALL_BATCH_PERCPU_ALLOC_FREE(16, 128, 1);
 	CALL_BATCH_PERCPU_ALLOC_FREE(32, 128, 2);
 	CALL_BATCH_PERCPU_ALLOC_FREE(64, 128, 3);
@@ -259,9 +262,6 @@ int test_batch_percpu_alloc_free(void *ctx)
 	CALL_BATCH_PERCPU_ALLOC_FREE(192, 128, 6);
 	CALL_BATCH_PERCPU_ALLOC_FREE(256, 128, 7);
 	CALL_BATCH_PERCPU_ALLOC_FREE(512, 64, 8);
-	CALL_BATCH_PERCPU_ALLOC_FREE(1024, 32, 9);
-	CALL_BATCH_PERCPU_ALLOC_FREE(2048, 16, 10);
-	CALL_BATCH_PERCPU_ALLOC_FREE(4096, 8, 11);
 
 	return 0;
 }
@@ -272,9 +272,10 @@ int test_percpu_free_through_map_free(void *ctx)
 	if ((u32)bpf_get_current_pid_tgid() != pid)
 		return 0;
 
-	/* Alloc 128 16-bytes per-cpu objects in batch to trigger refilling,
+	/* Alloc 128 8-bytes per-cpu objects in batch to trigger refilling,
 	 * then free these object through map free.
 	 */
+	CALL_BATCH_PERCPU_ALLOC(8, 128, 0);
 	CALL_BATCH_PERCPU_ALLOC(16, 128, 1);
 	CALL_BATCH_PERCPU_ALLOC(32, 128, 2);
 	CALL_BATCH_PERCPU_ALLOC(64, 128, 3);
@@ -283,9 +284,6 @@ int test_percpu_free_through_map_free(void *ctx)
 	CALL_BATCH_PERCPU_ALLOC(192, 128, 6);
 	CALL_BATCH_PERCPU_ALLOC(256, 128, 7);
 	CALL_BATCH_PERCPU_ALLOC(512, 64, 8);
-	CALL_BATCH_PERCPU_ALLOC(1024, 32, 9);
-	CALL_BATCH_PERCPU_ALLOC(2048, 16, 10);
-	CALL_BATCH_PERCPU_ALLOC(4096, 8, 11);
 
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c b/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c
new file mode 100644
index 000000000000..44628865fe1d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+__u32 target_ancestor_level;
+__u64 target_ancestor_cgid;
+int target_pid, target_hid;
+
+struct cgroup *bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id) __ksym;
+struct cgroup *bpf_cgroup_ancestor(struct cgroup *cgrp, int level) __ksym;
+void bpf_cgroup_release(struct cgroup *cgrp) __ksym;
+
+static int bpf_link_create_verify(int cmd)
+{
+	struct cgroup *cgrp, *ancestor;
+	struct task_struct *task;
+	int ret = 0;
+
+	if (cmd != BPF_LINK_CREATE)
+		return 0;
+
+	task = bpf_get_current_task_btf();
+
+	/* Then it can run in parallel with others */
+	if (task->pid != target_pid)
+		return 0;
+
+	cgrp = bpf_task_get_cgroup1(task, target_hid);
+	if (!cgrp)
+		return 0;
+
+	/* Refuse it if its cgid or its ancestor's cgid is the target cgid */
+	if (cgrp->kn->id == target_ancestor_cgid)
+		ret = -1;
+
+	ancestor = bpf_cgroup_ancestor(cgrp, target_ancestor_level);
+	if (!ancestor)
+		goto out;
+
+	if (ancestor->kn->id == target_ancestor_cgid)
+		ret = -1;
+	bpf_cgroup_release(ancestor);
+
+out:
+	bpf_cgroup_release(cgrp);
+	return ret;
+}
+
+SEC("lsm/bpf")
+int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size)
+{
+	return bpf_link_create_verify(cmd);
+}
+
+SEC("lsm.s/bpf")
+int BPF_PROG(lsm_s_run, int cmd, union bpf_attr *attr, unsigned int size)
+{
+	return bpf_link_create_verify(cmd);
+}
+
+SEC("fentry")
+int BPF_PROG(fentry_run)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c
index a17dd83eae67..ee4a601dcb06 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c
@@ -53,7 +53,7 @@ int test_core_kernel(void *ctx)
 	struct task_struct *task = (void *)bpf_get_current_task();
 	struct core_reloc_kernel_output *out = (void *)&data.out;
 	uint64_t pid_tgid = bpf_get_current_pid_tgid();
-	uint32_t real_tgid = (uint32_t)pid_tgid;
+	int32_t real_tgid = (int32_t)pid_tgid;
 	int pid, tgid;
 
 	if (data.my_pid_tgid != pid_tgid)
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_module.c b/tools/testing/selftests/bpf/progs/test_core_reloc_module.c
index f59f175c7baf..bcb31ff92dcc 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_module.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_module.c
@@ -43,8 +43,8 @@ int BPF_PROG(test_core_module_probed,
 #if __has_builtin(__builtin_preserve_enum_value)
 	struct core_reloc_module_output *out = (void *)&data.out;
 	__u64 pid_tgid = bpf_get_current_pid_tgid();
-	__u32 real_tgid = (__u32)(pid_tgid >> 32);
-	__u32 real_pid = (__u32)pid_tgid;
+	__s32 real_tgid = (__s32)(pid_tgid >> 32);
+	__s32 real_pid = (__s32)pid_tgid;
 
 	if (data.my_pid_tgid != pid_tgid)
 		return 0;
@@ -77,8 +77,8 @@ int BPF_PROG(test_core_module_direct,
 #if __has_builtin(__builtin_preserve_enum_value)
 	struct core_reloc_module_output *out = (void *)&data.out;
 	__u64 pid_tgid = bpf_get_current_pid_tgid();
-	__u32 real_tgid = (__u32)(pid_tgid >> 32);
-	__u32 real_pid = (__u32)pid_tgid;
+	__s32 real_tgid = (__s32)(pid_tgid >> 32);
+	__s32 real_pid = (__s32)pid_tgid;
 
 	if (data.my_pid_tgid != pid_tgid)
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_fill_link_info.c b/tools/testing/selftests/bpf/progs/test_fill_link_info.c
index 564f402d56fe..69509f8bb680 100644
--- a/tools/testing/selftests/bpf/progs/test_fill_link_info.c
+++ b/tools/testing/selftests/bpf/progs/test_fill_link_info.c
@@ -39,4 +39,10 @@ int BPF_PROG(kmulti_run)
 	return 0;
 }
 
+SEC("uprobe.multi")
+int BPF_PROG(umulti_run)
+{
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_fsverity.c b/tools/testing/selftests/bpf/progs/test_fsverity.c
new file mode 100644
index 000000000000..9e0f73e8189c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_fsverity.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_kfuncs.h"
+
+char _license[] SEC("license") = "GPL";
+
+#ifndef SHA256_DIGEST_SIZE
+#define SHA256_DIGEST_SIZE      32
+#endif
+
+#define SIZEOF_STRUCT_FSVERITY_DIGEST 4  /* sizeof(struct fsverity_digest) */
+
+char expected_digest[SIZEOF_STRUCT_FSVERITY_DIGEST + SHA256_DIGEST_SIZE];
+char digest[SIZEOF_STRUCT_FSVERITY_DIGEST + SHA256_DIGEST_SIZE];
+__u32 monitored_pid;
+__u32 got_fsverity;
+__u32 digest_matches;
+
+SEC("lsm.s/file_open")
+int BPF_PROG(test_file_open, struct file *f)
+{
+	struct bpf_dynptr digest_ptr;
+	__u32 pid;
+	int ret;
+	int i;
+
+	pid = bpf_get_current_pid_tgid() >> 32;
+	if (pid != monitored_pid)
+		return 0;
+
+	bpf_dynptr_from_mem(digest, sizeof(digest), 0, &digest_ptr);
+	ret = bpf_get_fsverity_digest(f, &digest_ptr);
+	if (ret < 0)
+		return 0;
+	got_fsverity = 1;
+
+	for (i = 0; i < (int)sizeof(digest); i++) {
+		if (digest[i] != expected_digest[i])
+			return 0;
+	}
+
+	digest_matches = 1;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_get_xattr.c b/tools/testing/selftests/bpf/progs/test_get_xattr.c
new file mode 100644
index 000000000000..7eb2a4e5a3e5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_get_xattr.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_kfuncs.h"
+
+char _license[] SEC("license") = "GPL";
+
+__u32 monitored_pid;
+__u32 found_xattr;
+
+static const char expected_value[] = "hello";
+char value[32];
+
+SEC("lsm.s/file_open")
+int BPF_PROG(test_file_open, struct file *f)
+{
+	struct bpf_dynptr value_ptr;
+	__u32 pid;
+	int ret;
+
+	pid = bpf_get_current_pid_tgid() >> 32;
+	if (pid != monitored_pid)
+		return 0;
+
+	bpf_dynptr_from_mem(value, sizeof(value), 0, &value_ptr);
+
+	ret = bpf_get_file_xattr(f, "user.kfuncs", &value_ptr);
+	if (ret != sizeof(expected_value))
+		return 0;
+	if (bpf_strncmp(value, ret, expected_value))
+		return 0;
+	found_xattr = 1;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_func12.c b/tools/testing/selftests/bpf/progs/test_global_func12.c
index 7f159d83c6f6..6e03d42519a6 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func12.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func12.c
@@ -19,5 +19,7 @@ int global_func12(struct __sk_buff *skb)
 {
 	const struct S s = {.x = skb->len };
 
-	return foo(&s);
+	foo(&s);
+
+	return 1;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_global_func15.c b/tools/testing/selftests/bpf/progs/test_global_func15.c
index b512d6a6c75e..b4e089d6981d 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func15.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func15.c
@@ -13,7 +13,7 @@ __noinline int foo(unsigned int *v)
 }
 
 SEC("cgroup_skb/ingress")
-__failure __msg("At program exit the register R0 has value")
+__failure __msg("At program exit the register R0 has ")
 int global_func15(struct __sk_buff *skb)
 {
 	unsigned int v = 1;
@@ -22,3 +22,35 @@ int global_func15(struct __sk_buff *skb)
 
 	return v;
 }
+
+SEC("cgroup_skb/ingress")
+__log_level(2) __flag(BPF_F_TEST_STATE_FREQ)
+__failure
+/* check that fallthrough code path marks r0 as precise */
+__msg("mark_precise: frame0: regs=r0 stack= before 2: (b7) r0 = 1")
+/* check that branch code path marks r0 as precise */
+__msg("mark_precise: frame0: regs=r0 stack= before 0: (85) call bpf_get_prandom_u32#7")
+__msg("At program exit the register R0 has ")
+__naked int global_func15_tricky_pruning(void)
+{
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+		"if r0 s> 1000 goto 1f;"
+		"r0 = 1;"
+	"1:"
+		"goto +0;" /* checkpoint */
+		/* cgroup_skb/ingress program is expected to return [0, 1]
+		 * values, so branch above makes sure that in a fallthrough
+		 * case we have a valid 1 stored in R0 register, but in
+		 * a branch case we assign some random value to R0.  So if
+		 * there is something wrong with precision tracking for R0 at
+		 * program exit, we might erronenously prune branch case,
+		 * because R0 in fallthrough case is imprecise (and thus any
+		 * value is valid from POV of verifier is_state_equal() logic)
+		 */
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32)
+		: __clobber_common
+	);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_func16.c b/tools/testing/selftests/bpf/progs/test_global_func16.c
index e7206304632e..e3e64bc472cd 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func16.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func16.c
@@ -13,7 +13,7 @@ __noinline int foo(int (*arr)[10])
 }
 
 SEC("cgroup_skb/ingress")
-__failure __msg("invalid indirect read from stack")
+__success
 int global_func16(struct __sk_buff *skb)
 {
 	int array[10];
diff --git a/tools/testing/selftests/bpf/progs/test_global_func17.c b/tools/testing/selftests/bpf/progs/test_global_func17.c
index a32e11c7d933..5de44b09e8ec 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func17.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func17.c
@@ -5,6 +5,7 @@
 
 __noinline int foo(int *p)
 {
+	barrier_var(p);
 	return p ? (*p = 42) : 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_global_func5.c b/tools/testing/selftests/bpf/progs/test_global_func5.c
index cc55aedaf82d..257c0569ff98 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func5.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func5.c
@@ -26,7 +26,7 @@ int f3(int val, struct __sk_buff *skb)
 }
 
 SEC("tc")
-__failure __msg("expected pointer to ctx, but got PTR")
+__failure __msg("expects pointer to ctx")
 int global_func5(struct __sk_buff *skb)
 {
 	return f1(skb) + f2(2, skb) + f3(3, skb);
diff --git a/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c b/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c
index 7faa8eef0598..9a06e5eb1fbe 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c
@@ -102,3 +102,52 @@ int perf_event_ctx(void *ctx)
 {
 	return perf_event_ctx_subprog(ctx);
 }
+
+/* this global subprog can be now called from many types of entry progs, each
+ * with different context type
+ */
+__weak int subprog_ctx_tag(void *ctx __arg_ctx)
+{
+	return bpf_get_stack(ctx, stack, sizeof(stack), 0);
+}
+
+struct my_struct { int x; };
+
+__weak int subprog_multi_ctx_tags(void *ctx1 __arg_ctx,
+				  struct my_struct *mem,
+				  void *ctx2 __arg_ctx)
+{
+	if (!mem)
+		return 0;
+
+	return bpf_get_stack(ctx1, stack, sizeof(stack), 0) +
+	       mem->x +
+	       bpf_get_stack(ctx2, stack, sizeof(stack), 0);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+int arg_tag_ctx_raw_tp(void *ctx)
+{
+	struct my_struct x = { .x = 123 };
+
+	return subprog_ctx_tag(ctx) + subprog_multi_ctx_tags(ctx, &x, ctx);
+}
+
+SEC("?perf_event")
+__success __log_level(2)
+int arg_tag_ctx_perf(void *ctx)
+{
+	struct my_struct x = { .x = 123 };
+
+	return subprog_ctx_tag(ctx) + subprog_multi_ctx_tags(ctx, &x, ctx);
+}
+
+SEC("?kprobe")
+__success __log_level(2)
+int arg_tag_ctx_kprobe(void *ctx)
+{
+	struct my_struct x = { .x = 123 };
+
+	return subprog_ctx_tag(ctx) + subprog_multi_ctx_tags(ctx, &x, ctx);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c b/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c
new file mode 100644
index 000000000000..2f0eb1334d65
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_kfuncs.h"
+
+char _license[] SEC("license") = "GPL";
+
+#ifndef SHA256_DIGEST_SIZE
+#define SHA256_DIGEST_SIZE      32
+#endif
+
+#define MAX_SIG_SIZE 1024
+
+/* By default, "fsverity sign" signs a file with fsverity_formatted_digest
+ * of the file. fsverity_formatted_digest on the kernel side is only used
+ * with CONFIG_FS_VERITY_BUILTIN_SIGNATURES. However, BPF LSM doesn't not
+ * require CONFIG_FS_VERITY_BUILTIN_SIGNATURES, so vmlinux.h may not have
+ * fsverity_formatted_digest. In this test, we intentionally avoid using
+ * fsverity_formatted_digest.
+ *
+ * Luckily, fsverity_formatted_digest is simply 8-byte magic followed by
+ * fsverity_digest. We use a char array of size fsverity_formatted_digest
+ * plus SHA256_DIGEST_SIZE. The magic part of it is filled by user space,
+ * and the rest of it is filled by bpf_get_fsverity_digest.
+ *
+ * Note that, generating signatures based on fsverity_formatted_digest is
+ * the design choice of this selftest (and "fsverity sign"). With BPF
+ * LSM, we have the flexibility to generate signature based on other data
+ * sets, for example, fsverity_digest or only the digest[] part of it.
+ */
+#define MAGIC_SIZE 8
+#define SIZEOF_STRUCT_FSVERITY_DIGEST 4  /* sizeof(struct fsverity_digest) */
+char digest[MAGIC_SIZE + SIZEOF_STRUCT_FSVERITY_DIGEST + SHA256_DIGEST_SIZE];
+
+__u32 monitored_pid;
+char sig[MAX_SIG_SIZE];
+__u32 sig_size;
+__u32 user_keyring_serial;
+
+SEC("lsm.s/file_open")
+int BPF_PROG(test_file_open, struct file *f)
+{
+	struct bpf_dynptr digest_ptr, sig_ptr;
+	struct bpf_key *trusted_keyring;
+	__u32 pid;
+	int ret;
+
+	pid = bpf_get_current_pid_tgid() >> 32;
+	if (pid != monitored_pid)
+		return 0;
+
+	/* digest_ptr points to fsverity_digest */
+	bpf_dynptr_from_mem(digest + MAGIC_SIZE, sizeof(digest) - MAGIC_SIZE, 0, &digest_ptr);
+
+	ret = bpf_get_fsverity_digest(f, &digest_ptr);
+	/* No verity, allow access */
+	if (ret < 0)
+		return 0;
+
+	/* Move digest_ptr to fsverity_formatted_digest */
+	bpf_dynptr_from_mem(digest, sizeof(digest), 0, &digest_ptr);
+
+	/* Read signature from xattr */
+	bpf_dynptr_from_mem(sig, sizeof(sig), 0, &sig_ptr);
+	ret = bpf_get_file_xattr(f, "user.sig", &sig_ptr);
+	/* No signature, reject access */
+	if (ret < 0)
+		return -EPERM;
+
+	trusted_keyring = bpf_lookup_user_key(user_keyring_serial, 0);
+	if (!trusted_keyring)
+		return -ENOENT;
+
+	/* Verify signature */
+	ret = bpf_verify_pkcs7_signature(&digest_ptr, &sig_ptr, trusted_keyring);
+
+	bpf_key_put(trusted_keyring);
+	return ret;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c b/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c
index eacda9fe07eb..4cfa42aa9436 100644
--- a/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c
+++ b/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c
@@ -29,7 +29,7 @@ int BPF_PROG(unix_listen, struct socket *sock, int backlog)
 	len = unix_sk->addr->len - sizeof(short);
 	path[0] = '@';
 	for (i = 1; i < len; i++) {
-		if (i >= sizeof(struct sockaddr_un))
+		if (i >= (int)sizeof(struct sockaddr_un))
 			break;
 
 		path[i] = unix_sk->addr->name->sun_path[i];
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
index 464d35bd57c7..b7250eb9c30c 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
@@ -15,6 +15,13 @@ struct {
 } sock_map SEC(".maps");
 
 struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 2);
+	__type(key, __u32);
+	__type(value, __u64);
+} nop_map SEC(".maps");
+
+struct {
 	__uint(type, BPF_MAP_TYPE_SOCKHASH);
 	__uint(max_entries, 2);
 	__type(key, __u32);
diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
index f66af753bbbb..3e436e6f7312 100644
--- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
@@ -6,66 +6,34 @@
  * modify it under the terms of version 2 of the GNU General Public
  * License as published by the Free Software Foundation.
  */
-#include <stddef.h>
-#include <string.h>
-#include <arpa/inet.h>
-#include <linux/bpf.h>
-#include <linux/if_ether.h>
-#include <linux/if_packet.h>
-#include <linux/if_tunnel.h>
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-#include <linux/icmp.h>
-#include <linux/types.h>
-#include <linux/socket.h>
-#include <linux/pkt_cls.h>
-#include <linux/erspan.h>
-#include <linux/udp.h>
+#include "vmlinux.h"
+#include <bpf/bpf_core_read.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
+#include "bpf_kfuncs.h"
+#include "bpf_tracing_net.h"
 
 #define log_err(__ret) bpf_printk("ERROR line:%d ret:%d\n", __LINE__, __ret)
 
-#define VXLAN_UDP_PORT 4789
+#define VXLAN_UDP_PORT		4789
+#define ETH_P_IP		0x0800
+#define PACKET_HOST		0
+#define TUNNEL_CSUM		bpf_htons(0x01)
+#define TUNNEL_KEY		bpf_htons(0x04)
 
 /* Only IPv4 address assigned to veth1.
  * 172.16.1.200
  */
 #define ASSIGNED_ADDR_VETH1 0xac1001c8
 
-struct geneve_opt {
-	__be16	opt_class;
-	__u8	type;
-	__u8	length:5;
-	__u8	r3:1;
-	__u8	r2:1;
-	__u8	r1:1;
-	__u8	opt_data[8]; /* hard-coded to 8 byte */
-};
-
-struct vxlanhdr {
-	__be32 vx_flags;
-	__be32 vx_vni;
-} __attribute__((packed));
-
-struct vxlan_metadata {
-	__u32     gbp;
-};
-
-struct bpf_fou_encap {
-	__be16 sport;
-	__be16 dport;
-};
-
-enum bpf_fou_encap_type {
-	FOU_BPF_ENCAP_FOU,
-	FOU_BPF_ENCAP_GUE,
-};
-
 int bpf_skb_set_fou_encap(struct __sk_buff *skb_ctx,
 			  struct bpf_fou_encap *encap, int type) __ksym;
 int bpf_skb_get_fou_encap(struct __sk_buff *skb_ctx,
 			  struct bpf_fou_encap *encap) __ksym;
+struct xfrm_state *
+bpf_xdp_get_xfrm_state(struct xdp_md *ctx, struct bpf_xfrm_state_opts *opts,
+		       u32 opts__sz) __ksym;
+void bpf_xdp_xfrm_state_release(struct xfrm_state *x) __ksym;
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
@@ -205,9 +173,9 @@ int erspan_set_tunnel(struct __sk_buff *skb)
 	__u8 hwid = 7;
 
 	md.version = 2;
-	md.u.md2.dir = direction;
-	md.u.md2.hwid = hwid & 0xf;
-	md.u.md2.hwid_upper = (hwid >> 4) & 0x3;
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, dir, direction);
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid, (hwid & 0xf));
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid_upper, (hwid >> 4) & 0x3);
 #endif
 
 	ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
@@ -246,8 +214,9 @@ int erspan_get_tunnel(struct __sk_buff *skb)
 	bpf_printk("\tindex %x\n", index);
 #else
 	bpf_printk("\tdirection %d hwid %x timestamp %u\n",
-		   md.u.md2.dir,
-		   (md.u.md2.hwid_upper << 4) + md.u.md2.hwid,
+		   BPF_CORE_READ_BITFIELD(&md.u.md2, dir),
+		   (BPF_CORE_READ_BITFIELD(&md.u.md2, hwid_upper) << 4) +
+		   BPF_CORE_READ_BITFIELD(&md.u.md2, hwid),
 		   bpf_ntohl(md.u.md2.timestamp));
 #endif
 
@@ -284,9 +253,9 @@ int ip4ip6erspan_set_tunnel(struct __sk_buff *skb)
 	__u8 hwid = 17;
 
 	md.version = 2;
-	md.u.md2.dir = direction;
-	md.u.md2.hwid = hwid & 0xf;
-	md.u.md2.hwid_upper = (hwid >> 4) & 0x3;
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, dir, direction);
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid, (hwid & 0xf));
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid_upper, (hwid >> 4) & 0x3);
 #endif
 
 	ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
@@ -326,8 +295,9 @@ int ip4ip6erspan_get_tunnel(struct __sk_buff *skb)
 	bpf_printk("\tindex %x\n", index);
 #else
 	bpf_printk("\tdirection %d hwid %x timestamp %u\n",
-		   md.u.md2.dir,
-		   (md.u.md2.hwid_upper << 4) + md.u.md2.hwid,
+		   BPF_CORE_READ_BITFIELD(&md.u.md2, dir),
+		   (BPF_CORE_READ_BITFIELD(&md.u.md2, hwid_upper) << 4) +
+		   BPF_CORE_READ_BITFIELD(&md.u.md2, hwid),
 		   bpf_ntohl(md.u.md2.timestamp));
 #endif
 
@@ -963,6 +933,10 @@ int ip6ip6_get_tunnel(struct __sk_buff *skb)
 	return TC_ACT_OK;
 }
 
+volatile int xfrm_reqid = 0;
+volatile int xfrm_spi = 0;
+volatile int xfrm_remote_ip = 0;
+
 SEC("tc")
 int xfrm_get_state(struct __sk_buff *skb)
 {
@@ -973,10 +947,58 @@ int xfrm_get_state(struct __sk_buff *skb)
 	if (ret < 0)
 		return TC_ACT_OK;
 
-	bpf_printk("reqid %d spi 0x%x remote ip 0x%x\n",
-		   x.reqid, bpf_ntohl(x.spi),
-		   bpf_ntohl(x.remote_ipv4));
+	xfrm_reqid = x.reqid;
+	xfrm_spi = bpf_ntohl(x.spi);
+	xfrm_remote_ip = bpf_ntohl(x.remote_ipv4);
+
 	return TC_ACT_OK;
 }
 
+volatile int xfrm_replay_window = 0;
+
+SEC("xdp")
+int xfrm_get_state_xdp(struct xdp_md *xdp)
+{
+	struct bpf_xfrm_state_opts opts = {};
+	struct xfrm_state *x = NULL;
+	struct ip_esp_hdr *esph;
+	struct bpf_dynptr ptr;
+	u8 esph_buf[8] = {};
+	u8 iph_buf[20] = {};
+	struct iphdr *iph;
+	u32 off;
+
+	if (bpf_dynptr_from_xdp(xdp, 0, &ptr))
+		goto out;
+
+	off = sizeof(struct ethhdr);
+	iph = bpf_dynptr_slice(&ptr, off, iph_buf, sizeof(iph_buf));
+	if (!iph || iph->protocol != IPPROTO_ESP)
+		goto out;
+
+	off += sizeof(struct iphdr);
+	esph = bpf_dynptr_slice(&ptr, off, esph_buf, sizeof(esph_buf));
+	if (!esph)
+		goto out;
+
+	opts.netns_id = BPF_F_CURRENT_NETNS;
+	opts.daddr.a4 = iph->daddr;
+	opts.spi = esph->spi;
+	opts.proto = IPPROTO_ESP;
+	opts.family = AF_INET;
+
+	x = bpf_xdp_get_xfrm_state(xdp, &opts, sizeof(opts));
+	if (!x)
+		goto out;
+
+	if (!x->replay_esn)
+		goto out;
+
+	xfrm_replay_window = x->replay_esn->replay_window;
+out:
+	if (x)
+		bpf_xdp_xfrm_state_release(x);
+	return XDP_PASS;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c
index 7748cc23de8a..f42e9f3831a1 100644
--- a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c
+++ b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c
@@ -10,17 +10,11 @@
 #include <errno.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
+#include "bpf_kfuncs.h"
 
 #define MAX_DATA_SIZE (1024 * 1024)
 #define MAX_SIG_SIZE 1024
 
-extern struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym;
-extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym;
-extern void bpf_key_put(struct bpf_key *key) __ksym;
-extern int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_ptr,
-				      struct bpf_dynptr *sig_ptr,
-				      struct bpf_key *trusted_keyring) __ksym;
-
 __u32 monitored_pid;
 __u32 user_keyring_serial;
 __u64 system_keyring_id;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c
index 5baaafed0d2d..3abf068b8446 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c
@@ -38,7 +38,7 @@ int xdp_redirect(struct xdp_md *xdp)
 	if (payload + 1 > data_end)
 		return XDP_ABORTED;
 
-	if (xdp->ingress_ifindex != ifindex_in)
+	if (xdp->ingress_ifindex != (__u32)ifindex_in)
 		return XDP_ABORTED;
 
 	if (metadata + 1 > data)
diff --git a/tools/testing/selftests/bpf/progs/timer_failure.c b/tools/testing/selftests/bpf/progs/timer_failure.c
index 226d33b5a05c..0996c2486f05 100644
--- a/tools/testing/selftests/bpf/progs/timer_failure.c
+++ b/tools/testing/selftests/bpf/progs/timer_failure.c
@@ -21,17 +21,38 @@ struct {
 	__type(value, struct elem);
 } timer_map SEC(".maps");
 
-static int timer_cb_ret1(void *map, int *key, struct bpf_timer *timer)
+__naked __noinline __used
+static unsigned long timer_cb_ret_bad()
 {
-	if (bpf_get_smp_processor_id() % 2)
-		return 1;
-	else
-		return 0;
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+		"if r0 s> 1000 goto 1f;"
+		"r0 = 0;"
+	"1:"
+		"goto +0;" /* checkpoint */
+		/* async callback is expected to return 0, so branch above
+		 * skipping r0 = 0; should lead to a failure, but if exit
+		 * instruction doesn't enforce r0's precision, this callback
+		 * will be successfully verified
+		 */
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32)
+		: __clobber_common
+	);
 }
 
 SEC("fentry/bpf_fentry_test1")
-__failure __msg("should have been in (0x0; 0x0)")
-int BPF_PROG2(test_ret_1, int, a)
+__log_level(2)
+__flag(BPF_F_TEST_STATE_FREQ)
+__failure
+/* check that fallthrough code path marks r0 as precise */
+__msg("mark_precise: frame0: regs=r0 stack= before")
+__msg(": (85) call bpf_get_prandom_u32#7") /* anchor message */
+/* check that branch code path marks r0 as precise */
+__msg("mark_precise: frame0: regs=r0 stack= before ") __msg(": (85) call bpf_get_prandom_u32#7")
+__msg("should have been in [0, 0]")
+long BPF_PROG2(test_bad_ret, int, a)
 {
 	int key = 0;
 	struct bpf_timer *timer;
@@ -39,7 +60,7 @@ int BPF_PROG2(test_ret_1, int, a)
 	timer = bpf_map_lookup_elem(&timer_map, &key);
 	if (timer) {
 		bpf_timer_init(timer, &timer_map, CLOCK_BOOTTIME);
-		bpf_timer_set_callback(timer, timer_cb_ret1);
+		bpf_timer_set_callback(timer, timer_cb_ret_bad);
 		bpf_timer_start(timer, 1000, 0);
 	}
 
diff --git a/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c b/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c
index 03ee946c6bf7..11ab25c42c36 100644
--- a/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c
+++ b/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c
@@ -184,7 +184,7 @@ invalid_drain_callback_return(struct bpf_dynptr *dynptr, void *context)
  * not be able to write to that pointer.
  */
 SEC("?raw_tp")
-__failure __msg("At callback return the register R0 has value")
+__failure __msg("At callback return the register R0 has ")
 int user_ringbuf_callback_invalid_return(void *ctx)
 {
 	bpf_user_ringbuf_drain(&user_ringbuf, invalid_drain_callback_return, NULL, 0);
diff --git a/tools/testing/selftests/bpf/progs/verifier_basic_stack.c b/tools/testing/selftests/bpf/progs/verifier_basic_stack.c
index 359df865a8f3..8d77cc5323d3 100644
--- a/tools/testing/selftests/bpf/progs/verifier_basic_stack.c
+++ b/tools/testing/selftests/bpf/progs/verifier_basic_stack.c
@@ -27,8 +27,8 @@ __naked void stack_out_of_bounds(void)
 
 SEC("socket")
 __description("uninitialized stack1")
-__failure __msg("invalid indirect read from stack")
-__failure_unpriv
+__success __log_level(4) __msg("stack depth 8")
+__failure_unpriv __msg_unpriv("invalid indirect read from stack")
 __naked void uninitialized_stack1(void)
 {
 	asm volatile ("					\
@@ -45,8 +45,8 @@ __naked void uninitialized_stack1(void)
 
 SEC("socket")
 __description("uninitialized stack2")
-__failure __msg("invalid read from stack")
-__failure_unpriv
+__success __log_level(4) __msg("stack depth 8")
+__failure_unpriv __msg_unpriv("invalid read from stack")
 __naked void uninitialized_stack2(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/progs/verifier_bitfield_write.c b/tools/testing/selftests/bpf/progs/verifier_bitfield_write.c
new file mode 100644
index 000000000000..623f130a3198
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_bitfield_write.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <stdint.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+
+#include "bpf_misc.h"
+
+struct core_reloc_bitfields {
+	/* unsigned bitfields */
+	uint8_t		ub1: 1;
+	uint8_t		ub2: 2;
+	uint32_t	ub7: 7;
+	/* signed bitfields */
+	int8_t		sb4: 4;
+	int32_t		sb20: 20;
+	/* non-bitfields */
+	uint32_t	u32;
+	int32_t		s32;
+} __attribute__((preserve_access_index));
+
+SEC("tc")
+__description("single CO-RE bitfield roundtrip")
+__btf_path("btf__core_reloc_bitfields.bpf.o")
+__success
+__retval(3)
+int single_field_roundtrip(struct __sk_buff *ctx)
+{
+	struct core_reloc_bitfields bitfields;
+
+	__builtin_memset(&bitfields, 0, sizeof(bitfields));
+	BPF_CORE_WRITE_BITFIELD(&bitfields, ub2, 3);
+	return BPF_CORE_READ_BITFIELD(&bitfields, ub2);
+}
+
+SEC("tc")
+__description("multiple CO-RE bitfield roundtrip")
+__btf_path("btf__core_reloc_bitfields.bpf.o")
+__success
+__retval(0x3FD)
+int multiple_field_roundtrip(struct __sk_buff *ctx)
+{
+	struct core_reloc_bitfields bitfields;
+	uint8_t ub2;
+	int8_t sb4;
+
+	__builtin_memset(&bitfields, 0, sizeof(bitfields));
+	BPF_CORE_WRITE_BITFIELD(&bitfields, ub2, 1);
+	BPF_CORE_WRITE_BITFIELD(&bitfields, sb4, -1);
+
+	ub2 = BPF_CORE_READ_BITFIELD(&bitfields, ub2);
+	sb4 = BPF_CORE_READ_BITFIELD(&bitfields, sb4);
+
+	return (((uint8_t)sb4) << 2) | ub2;
+}
+
+SEC("tc")
+__description("adjacent CO-RE bitfield roundtrip")
+__btf_path("btf__core_reloc_bitfields.bpf.o")
+__success
+__retval(7)
+int adjacent_field_roundtrip(struct __sk_buff *ctx)
+{
+	struct core_reloc_bitfields bitfields;
+	uint8_t ub1, ub2;
+
+	__builtin_memset(&bitfields, 0, sizeof(bitfields));
+	BPF_CORE_WRITE_BITFIELD(&bitfields, ub1, 1);
+	BPF_CORE_WRITE_BITFIELD(&bitfields, ub2, 3);
+
+	ub1 = BPF_CORE_READ_BITFIELD(&bitfields, ub1);
+	ub2 = BPF_CORE_READ_BITFIELD(&bitfields, ub2);
+
+	return (ub2 << 1) | ub1;
+}
+
+SEC("tc")
+__description("multibyte CO-RE bitfield roundtrip")
+__btf_path("btf__core_reloc_bitfields.bpf.o")
+__success
+__retval(0x21)
+int multibyte_field_roundtrip(struct __sk_buff *ctx)
+{
+	struct core_reloc_bitfields bitfields;
+	uint32_t ub7;
+	uint8_t ub1;
+
+	__builtin_memset(&bitfields, 0, sizeof(bitfields));
+	BPF_CORE_WRITE_BITFIELD(&bitfields, ub1, 1);
+	BPF_CORE_WRITE_BITFIELD(&bitfields, ub7, 16);
+
+	ub1 = BPF_CORE_READ_BITFIELD(&bitfields, ub1);
+	ub7 = BPF_CORE_READ_BITFIELD(&bitfields, ub7);
+
+	return (ub7 << 1) | ub1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c
index c5588a14fe2e..960998f16306 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bounds.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c
@@ -965,6 +965,7 @@ l0_%=:	r0 = 0;						\
 SEC("xdp")
 __description("bound check with JMP_JSLT for crossing 64-bit signed boundary")
 __success __retval(0)
+__flag(!BPF_F_TEST_REG_INVARIANTS) /* known invariants violation */
 __naked void crossing_64_bit_signed_boundary_2(void)
 {
 	asm volatile ("					\
@@ -1046,6 +1047,7 @@ l0_%=:	r0 = 0;						\
 SEC("xdp")
 __description("bound check with JMP32_JSLT for crossing 32-bit signed boundary")
 __success __retval(0)
+__flag(!BPF_F_TEST_REG_INVARIANTS) /* known invariants violation */
 __naked void crossing_32_bit_signed_boundary_2(void)
 {
 	asm volatile ("					\
@@ -1073,4 +1075,66 @@ l0_%=:	r0 = 0;						\
 	: __clobber_all);
 }
 
+SEC("tc")
+__description("bounds check with JMP_NE for reg edge")
+__success __retval(0)
+__naked void reg_not_equal_const(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	call %[bpf_get_prandom_u32];			\
+	r4 = r0;					\
+	r4 &= 7;					\
+	if r4 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r1 = r6;					\
+	r2 = 0;						\
+	r3 = r10;					\
+	r3 += -8;					\
+	r5 = 0;						\
+	/* The 4th argument of bpf_skb_store_bytes is defined as \
+	 * ARG_CONST_SIZE, so 0 is not allowed. The 'r4 != 0' \
+	 * is providing us this exclusion of zero from initial \
+	 * [0, 7] range.				\
+	 */						\
+	call %[bpf_skb_store_bytes];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_skb_store_bytes)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("bounds check with JMP_EQ for reg edge")
+__success __retval(0)
+__naked void reg_equal_const(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	call %[bpf_get_prandom_u32];			\
+	r4 = r0;					\
+	r4 &= 7;					\
+	if r4 == 0 goto l0_%=;				\
+	r1 = r6;					\
+	r2 = 0;						\
+	r3 = r10;					\
+	r3 += -8;					\
+	r5 = 0;						\
+	/* Just the same as what we do in reg_not_equal_const() */ \
+	call %[bpf_skb_store_bytes];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_skb_store_bytes)
+	: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_btf_unreliable_prog.c b/tools/testing/selftests/bpf/progs/verifier_btf_unreliable_prog.c
new file mode 100644
index 000000000000..36e033a2e02c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_btf_unreliable_prog.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2017 Facebook
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_misc.h"
+
+struct whatever {};
+
+SEC("kprobe")
+__success __log_level(2)
+/* context type is wrong, making it impossible to freplace this program */
+int btf_unreliable_kprobe(struct whatever *ctx)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_cfg.c b/tools/testing/selftests/bpf/progs/verifier_cfg.c
index df7697b94007..c1f55e1d80a4 100644
--- a/tools/testing/selftests/bpf/progs/verifier_cfg.c
+++ b/tools/testing/selftests/bpf/progs/verifier_cfg.c
@@ -97,4 +97,66 @@ l0_%=:	r2 = r0;					\
 "	::: __clobber_all);
 }
 
+SEC("socket")
+__description("conditional loop (2)")
+__success
+__failure_unpriv __msg_unpriv("back-edge from insn 10 to 11")
+__naked void conditional_loop2(void)
+{
+	asm volatile ("					\
+	r9 = 2 ll;					\
+	r3 = 0x20 ll;					\
+	r4 = 0x35 ll;					\
+	r8 = r4;					\
+	goto l1_%=;					\
+l0_%=:	r9 -= r3;					\
+	r9 -= r4;					\
+	r9 -= r8;					\
+l1_%=:	r8 += r4;					\
+	if r8 < 0x64 goto l0_%=;			\
+	r0 = r9;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unconditional loop after conditional jump")
+__failure __msg("infinite loop detected")
+__failure_unpriv __msg_unpriv("back-edge from insn 3 to 2")
+__naked void uncond_loop_after_cond_jmp(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	if r0 > 0 goto l1_%=;				\
+l0_%=:	r0 = 1;						\
+	goto l0_%=;					\
+l1_%=:	exit;						\
+"	::: __clobber_all);
+}
+
+
+__naked __noinline __used
+static unsigned long never_ending_subprog()
+{
+	asm volatile ("					\
+	r0 = r1;					\
+	goto -1;					\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unconditional loop after conditional jump")
+/* infinite loop is detected *after* check_cfg() */
+__failure __msg("infinite loop detected")
+__naked void uncond_loop_in_subprog_after_cond_jmp(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	if r0 > 0 goto l1_%=;				\
+l0_%=:	r0 += 1;					\
+	call never_ending_subprog;			\
+l1_%=:	exit;						\
+"	::: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_cgroup_inv_retcode.c b/tools/testing/selftests/bpf/progs/verifier_cgroup_inv_retcode.c
index d6c4a7f3f790..6e0f349f8f15 100644
--- a/tools/testing/selftests/bpf/progs/verifier_cgroup_inv_retcode.c
+++ b/tools/testing/selftests/bpf/progs/verifier_cgroup_inv_retcode.c
@@ -7,7 +7,7 @@
 
 SEC("cgroup/sock")
 __description("bpf_exit with invalid return code. test1")
-__failure __msg("R0 has value (0x0; 0xffffffff)")
+__failure __msg("smin=0 smax=4294967295 should have been in [0, 1]")
 __naked void with_invalid_return_code_test1(void)
 {
 	asm volatile ("					\
@@ -30,7 +30,7 @@ __naked void with_invalid_return_code_test2(void)
 
 SEC("cgroup/sock")
 __description("bpf_exit with invalid return code. test3")
-__failure __msg("R0 has value (0x0; 0x3)")
+__failure __msg("smin=0 smax=3 should have been in [0, 1]")
 __naked void with_invalid_return_code_test3(void)
 {
 	asm volatile ("					\
@@ -53,7 +53,7 @@ __naked void with_invalid_return_code_test4(void)
 
 SEC("cgroup/sock")
 __description("bpf_exit with invalid return code. test5")
-__failure __msg("R0 has value (0x2; 0x0)")
+__failure __msg("smin=2 smax=2 should have been in [0, 1]")
 __naked void with_invalid_return_code_test5(void)
 {
 	asm volatile ("					\
@@ -75,7 +75,7 @@ __naked void with_invalid_return_code_test6(void)
 
 SEC("cgroup/sock")
 __description("bpf_exit with invalid return code. test7")
-__failure __msg("R0 has unknown scalar value")
+__failure __msg("R0 has unknown scalar value should have been in [0, 1]")
 __naked void with_invalid_return_code_test7(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c b/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c
index 99a23dea8233..be95570ab382 100644
--- a/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c
+++ b/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c
@@ -411,7 +411,7 @@ l0_%=:	r0 = 0;						\
 
 SEC("tc")
 __description("direct packet access: test17 (pruning, alignment)")
-__failure __msg("misaligned packet access off 2+(0x0; 0x0)+15+-4 size 4")
+__failure __msg("misaligned packet access off 2+0+15+-4 size 4")
 __flag(BPF_F_STRICT_ALIGNMENT)
 __naked void packet_access_test17_pruning_alignment(void)
 {
diff --git a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
new file mode 100644
index 000000000000..9eeb2d89cda8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
@@ -0,0 +1,192 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "xdp_metadata.h"
+#include "bpf_kfuncs.h"
+
+int arr[1];
+int unkn_idx;
+const volatile bool call_dead_subprog = false;
+
+__noinline long global_bad(void)
+{
+	return arr[unkn_idx]; /* BOOM */
+}
+
+__noinline long global_good(void)
+{
+	return arr[0];
+}
+
+__noinline long global_calls_bad(void)
+{
+	return global_good() + global_bad() /* does BOOM indirectly */;
+}
+
+__noinline long global_calls_good_only(void)
+{
+	return global_good();
+}
+
+__noinline long global_dead(void)
+{
+	return arr[0] * 2;
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+/* main prog is validated completely first */
+__msg("('global_calls_good_only') is global and assumed valid.")
+/* eventually global_good() is transitively validated as well */
+__msg("Validating global_good() func")
+__msg("('global_good') is safe for any args that match its prototype")
+int chained_global_func_calls_success(void)
+{
+	int sum = 0;
+
+	if (call_dead_subprog)
+		sum += global_dead();
+	return global_calls_good_only() + sum;
+}
+
+SEC("?raw_tp")
+__failure __log_level(2)
+/* main prog validated successfully first */
+__msg("('global_calls_bad') is global and assumed valid.")
+/* eventually we validate global_bad() and fail */
+__msg("Validating global_bad() func")
+__msg("math between map_value pointer and register") /* BOOM */
+int chained_global_func_calls_bad(void)
+{
+	return global_calls_bad();
+}
+
+/* do out of bounds access forcing verifier to fail verification if this
+ * global func is called
+ */
+__noinline int global_unsupp(const int *mem)
+{
+	if (!mem)
+		return 0;
+	return mem[100]; /* BOOM */
+}
+
+const volatile bool skip_unsupp_global = true;
+
+SEC("?raw_tp")
+__success
+int guarded_unsupp_global_called(void)
+{
+	if (!skip_unsupp_global)
+		return global_unsupp(NULL);
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __log_level(2)
+__msg("Func#1 ('global_unsupp') is global and assumed valid.")
+__msg("Validating global_unsupp() func#1...")
+__msg("value is outside of the allowed memory range")
+int unguarded_unsupp_global_called(void)
+{
+	int x = 0;
+
+	return global_unsupp(&x);
+}
+
+long stack[128];
+
+__weak int subprog_nullable_ptr_bad(int *p)
+{
+	return (*p) * 2; /* bad, missing null check */
+}
+
+SEC("?raw_tp")
+__failure __log_level(2)
+__msg("invalid mem access 'mem_or_null'")
+int arg_tag_nullable_ptr_fail(void *ctx)
+{
+	int x = 42;
+
+	return subprog_nullable_ptr_bad(&x);
+}
+
+__noinline __weak int subprog_nonnull_ptr_good(int *p1 __arg_nonnull, int *p2 __arg_nonnull)
+{
+	return (*p1) * (*p2); /* good, no need for NULL checks */
+}
+
+int x = 47;
+
+SEC("?raw_tp")
+__success __log_level(2)
+int arg_tag_nonnull_ptr_good(void *ctx)
+{
+	int y = 74;
+
+	return subprog_nonnull_ptr_good(&x, &y);
+}
+
+/* this global subprog can be now called from many types of entry progs, each
+ * with different context type
+ */
+__weak int subprog_ctx_tag(void *ctx __arg_ctx)
+{
+	return bpf_get_stack(ctx, stack, sizeof(stack), 0);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+int arg_tag_ctx_raw_tp(void *ctx)
+{
+	return subprog_ctx_tag(ctx);
+}
+
+SEC("?tp")
+__success __log_level(2)
+int arg_tag_ctx_tp(void *ctx)
+{
+	return subprog_ctx_tag(ctx);
+}
+
+SEC("?kprobe")
+__success __log_level(2)
+int arg_tag_ctx_kprobe(void *ctx)
+{
+	return subprog_ctx_tag(ctx);
+}
+
+__weak int subprog_dynptr(struct bpf_dynptr *dptr)
+{
+	long *d, t, buf[1] = {};
+
+	d = bpf_dynptr_data(dptr, 0, sizeof(long));
+	if (!d)
+		return 0;
+
+	t = *d + 1;
+
+	d = bpf_dynptr_slice(dptr, 0, &buf, sizeof(long));
+	if (!d)
+		return t;
+
+	t = *d + 2;
+
+	return t;
+}
+
+SEC("?xdp")
+__success __log_level(2)
+int arg_tag_dynptr(struct xdp_md *ctx)
+{
+	struct bpf_dynptr dptr;
+
+	bpf_dynptr_from_xdp(ctx, 0, &dptr);
+
+	return subprog_dynptr(&dptr);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_gotol.c b/tools/testing/selftests/bpf/progs/verifier_gotol.c
index d1edbcff9a18..05a329ee45ee 100644
--- a/tools/testing/selftests/bpf/progs/verifier_gotol.c
+++ b/tools/testing/selftests/bpf/progs/verifier_gotol.c
@@ -33,6 +33,25 @@ l3_%=:							\
 	: __clobber_all);
 }
 
+SEC("socket")
+__description("gotol, large_imm")
+__success __failure_unpriv __retval(40000)
+__naked void gotol_large_imm(void)
+{
+	asm volatile ("					\
+	gotol 1f;					\
+0:							\
+	r0 = 0;						\
+	.rept 40000;					\
+	r0 += 1;					\
+	.endr;						\
+	exit;						\
+1:	gotol 0b;					\
+"	:
+	:
+	: __clobber_all);
+}
+
 #else
 
 SEC("socket")
diff --git a/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c b/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c
index 692216c0ad3d..886498b5e6f3 100644
--- a/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c
+++ b/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c
@@ -89,9 +89,14 @@ l0_%=:	exit;						\
 	: __clobber_all);
 }
 
+/* Call a function taking a pointer and a size which doesn't allow the size to
+ * be zero (i.e. bpf_trace_printk() declares the second argument to be
+ * ARG_CONST_SIZE, not ARG_CONST_SIZE_OR_ZERO). We attempt to pass zero for the
+ * size and expect to fail.
+ */
 SEC("tracepoint")
 __description("helper access to map: empty range")
-__failure __msg("invalid access to map value, value_size=48 off=0 size=0")
+__failure __msg("R2 invalid zero-sized read: u64=[0,0]")
 __naked void access_to_map_empty_range(void)
 {
 	asm volatile ("					\
@@ -113,6 +118,38 @@ l0_%=:	exit;						\
 	: __clobber_all);
 }
 
+/* Like the test above, but this time the size register is not known to be zero;
+ * its lower-bound is zero though, which is still unacceptable.
+ */
+SEC("tracepoint")
+__description("helper access to map: possibly-empty ange")
+__failure __msg("R2 invalid zero-sized read: u64=[0,4]")
+__naked void access_to_map_possibly_empty_range(void)
+{
+	asm volatile ("                                         \
+	r2 = r10;                                               \
+	r2 += -8;                                               \
+	r1 = 0;                                                 \
+	*(u64*)(r2 + 0) = r1;                                   \
+	r1 = %[map_hash_48b] ll;                                \
+	call %[bpf_map_lookup_elem];                            \
+	if r0 == 0 goto l0_%=;                                  \
+	r1 = r0;                                                \
+	/* Read an unknown value */                             \
+	r7 = *(u64*)(r0 + 0);                                   \
+	/* Make it small and positive, to avoid other errors */ \
+	r7 &= 4;                                                \
+	r2 = 0;                                                 \
+	r2 += r7;                                               \
+	call %[bpf_trace_printk];                               \
+l0_%=:	exit;                                               \
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_trace_printk),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
 SEC("tracepoint")
 __description("helper access to map: out-of-bound range")
 __failure __msg("invalid access to map value, value_size=48 off=0 size=56")
@@ -221,7 +258,7 @@ l0_%=:	exit;						\
 
 SEC("tracepoint")
 __description("helper access to adjusted map (via const imm): empty range")
-__failure __msg("invalid access to map value, value_size=48 off=4 size=0")
+__failure __msg("R2 invalid zero-sized read")
 __naked void via_const_imm_empty_range(void)
 {
 	asm volatile ("					\
@@ -386,7 +423,7 @@ l0_%=:	exit;						\
 
 SEC("tracepoint")
 __description("helper access to adjusted map (via const reg): empty range")
-__failure __msg("R1 min value is outside of the allowed memory range")
+__failure __msg("R2 invalid zero-sized read")
 __naked void via_const_reg_empty_range(void)
 {
 	asm volatile ("					\
@@ -556,7 +593,7 @@ l0_%=:	exit;						\
 
 SEC("tracepoint")
 __description("helper access to adjusted map (via variable): empty range")
-__failure __msg("R1 min value is outside of the allowed memory range")
+__failure __msg("R2 invalid zero-sized read")
 __naked void map_via_variable_empty_range(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/progs/verifier_int_ptr.c b/tools/testing/selftests/bpf/progs/verifier_int_ptr.c
index b054f9c48143..9fc3fae5cd83 100644
--- a/tools/testing/selftests/bpf/progs/verifier_int_ptr.c
+++ b/tools/testing/selftests/bpf/progs/verifier_int_ptr.c
@@ -5,9 +5,10 @@
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
 
-SEC("cgroup/sysctl")
+SEC("socket")
 __description("ARG_PTR_TO_LONG uninitialized")
-__failure __msg("invalid indirect read from stack R4 off -16+0 size 8")
+__success
+__failure_unpriv __msg_unpriv("invalid indirect read from stack R4 off -16+0 size 8")
 __naked void arg_ptr_to_long_uninitialized(void)
 {
 	asm volatile ("					\
@@ -67,7 +68,7 @@ __naked void ptr_to_long_half_uninitialized(void)
 
 SEC("cgroup/sysctl")
 __description("ARG_PTR_TO_LONG misaligned")
-__failure __msg("misaligned stack access off (0x0; 0x0)+-20+0 size 8")
+__failure __msg("misaligned stack access off 0+-20+0 size 8")
 __naked void arg_ptr_to_long_misaligned(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
new file mode 100644
index 000000000000..5905e036e0ea
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
@@ -0,0 +1,242 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 8);
+	__type(key, __u32);
+	__type(value, __u64);
+} map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_USER_RINGBUF);
+	__uint(max_entries, 8);
+} ringbuf SEC(".maps");
+
+struct vm_area_struct;
+struct bpf_map;
+
+struct buf_context {
+	char *buf;
+};
+
+struct num_context {
+	__u64 i;
+	__u64 j;
+};
+
+__u8 choice_arr[2] = { 0, 1 };
+
+static int unsafe_on_2nd_iter_cb(__u32 idx, struct buf_context *ctx)
+{
+	if (idx == 0) {
+		ctx->buf = (char *)(0xDEAD);
+		return 0;
+	}
+
+	if (bpf_probe_read_user(ctx->buf, 8, (void *)(0xBADC0FFEE)))
+		return 1;
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("R1 type=scalar expected=fp")
+int unsafe_on_2nd_iter(void *unused)
+{
+	char buf[4];
+	struct buf_context loop_ctx = { .buf = buf };
+
+	bpf_loop(100, unsafe_on_2nd_iter_cb, &loop_ctx, 0);
+	return 0;
+}
+
+static int unsafe_on_zero_iter_cb(__u32 idx, struct num_context *ctx)
+{
+	ctx->i = 0;
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("invalid access to map value, value_size=2 off=32 size=1")
+int unsafe_on_zero_iter(void *unused)
+{
+	struct num_context loop_ctx = { .i = 32 };
+
+	bpf_loop(100, unsafe_on_zero_iter_cb, &loop_ctx, 0);
+	return choice_arr[loop_ctx.i];
+}
+
+static int widening_cb(__u32 idx, struct num_context *ctx)
+{
+	++ctx->i;
+	return 0;
+}
+
+SEC("?raw_tp")
+__success
+int widening(void *unused)
+{
+	struct num_context loop_ctx = { .i = 0, .j = 1 };
+
+	bpf_loop(100, widening_cb, &loop_ctx, 0);
+	/* loop_ctx.j is not changed during callback iteration,
+	 * verifier should not apply widening to it.
+	 */
+	return choice_arr[loop_ctx.j];
+}
+
+static int loop_detection_cb(__u32 idx, struct num_context *ctx)
+{
+	for (;;) {}
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("infinite loop detected")
+int loop_detection(void *unused)
+{
+	struct num_context loop_ctx = { .i = 0 };
+
+	bpf_loop(100, loop_detection_cb, &loop_ctx, 0);
+	return 0;
+}
+
+static __always_inline __u64 oob_state_machine(struct num_context *ctx)
+{
+	switch (ctx->i) {
+	case 0:
+		ctx->i = 1;
+		break;
+	case 1:
+		ctx->i = 32;
+		break;
+	}
+	return 0;
+}
+
+static __u64 for_each_map_elem_cb(struct bpf_map *map, __u32 *key, __u64 *val, void *data)
+{
+	return oob_state_machine(data);
+}
+
+SEC("?raw_tp")
+__failure __msg("invalid access to map value, value_size=2 off=32 size=1")
+int unsafe_for_each_map_elem(void *unused)
+{
+	struct num_context loop_ctx = { .i = 0 };
+
+	bpf_for_each_map_elem(&map, for_each_map_elem_cb, &loop_ctx, 0);
+	return choice_arr[loop_ctx.i];
+}
+
+static __u64 ringbuf_drain_cb(struct bpf_dynptr *dynptr, void *data)
+{
+	return oob_state_machine(data);
+}
+
+SEC("?raw_tp")
+__failure __msg("invalid access to map value, value_size=2 off=32 size=1")
+int unsafe_ringbuf_drain(void *unused)
+{
+	struct num_context loop_ctx = { .i = 0 };
+
+	bpf_user_ringbuf_drain(&ringbuf, ringbuf_drain_cb, &loop_ctx, 0);
+	return choice_arr[loop_ctx.i];
+}
+
+static __u64 find_vma_cb(struct task_struct *task, struct vm_area_struct *vma, void *data)
+{
+	return oob_state_machine(data);
+}
+
+SEC("?raw_tp")
+__failure __msg("invalid access to map value, value_size=2 off=32 size=1")
+int unsafe_find_vma(void *unused)
+{
+	struct task_struct *task = bpf_get_current_task_btf();
+	struct num_context loop_ctx = { .i = 0 };
+
+	bpf_find_vma(task, 0, find_vma_cb, &loop_ctx, 0);
+	return choice_arr[loop_ctx.i];
+}
+
+static int iter_limit_cb(__u32 idx, struct num_context *ctx)
+{
+	ctx->i++;
+	return 0;
+}
+
+SEC("?raw_tp")
+__success
+int bpf_loop_iter_limit_ok(void *unused)
+{
+	struct num_context ctx = { .i = 0 };
+
+	bpf_loop(1, iter_limit_cb, &ctx, 0);
+	return choice_arr[ctx.i];
+}
+
+SEC("?raw_tp")
+__failure __msg("invalid access to map value, value_size=2 off=2 size=1")
+int bpf_loop_iter_limit_overflow(void *unused)
+{
+	struct num_context ctx = { .i = 0 };
+
+	bpf_loop(2, iter_limit_cb, &ctx, 0);
+	return choice_arr[ctx.i];
+}
+
+static int iter_limit_level2a_cb(__u32 idx, struct num_context *ctx)
+{
+	ctx->i += 100;
+	return 0;
+}
+
+static int iter_limit_level2b_cb(__u32 idx, struct num_context *ctx)
+{
+	ctx->i += 10;
+	return 0;
+}
+
+static int iter_limit_level1_cb(__u32 idx, struct num_context *ctx)
+{
+	ctx->i += 1;
+	bpf_loop(1, iter_limit_level2a_cb, ctx, 0);
+	bpf_loop(1, iter_limit_level2b_cb, ctx, 0);
+	return 0;
+}
+
+/* Check that path visiting every callback function once had been
+ * reached by verifier. Variables 'ctx{1,2}i' below serve as flags,
+ * with each decimal digit corresponding to a callback visit marker.
+ */
+SEC("socket")
+__success __retval(111111)
+int bpf_loop_iter_limit_nested(void *unused)
+{
+	struct num_context ctx1 = { .i = 0 };
+	struct num_context ctx2 = { .i = 0 };
+	__u64 a, b, c;
+
+	bpf_loop(1, iter_limit_level1_cb, &ctx1, 0);
+	bpf_loop(1, iter_limit_level1_cb, &ctx2, 0);
+	a = ctx1.i;
+	b = ctx2.i;
+	/* Force 'ctx1.i' and 'ctx2.i' precise. */
+	c = choice_arr[(a + b) % 2];
+	/* This makes 'c' zero, but neither clang nor verifier know it. */
+	c /= 10;
+	/* Make sure that verifier does not visit 'impossible' states:
+	 * enumerate all possible callback visit masks.
+	 */
+	if (a != 0 && a != 1 && a != 11 && a != 101 && a != 111 &&
+	    b != 0 && b != 1 && b != 11 && b != 101 && b != 111)
+		asm volatile ("r0 /= 0;" ::: "r0");
+	return 1000 * a + b + c;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_loops1.c b/tools/testing/selftests/bpf/progs/verifier_loops1.c
index 5bc86af80a9a..71735dbf33d4 100644
--- a/tools/testing/selftests/bpf/progs/verifier_loops1.c
+++ b/tools/testing/selftests/bpf/progs/verifier_loops1.c
@@ -75,9 +75,10 @@ l0_%=:	r0 += 1;					\
 "	::: __clobber_all);
 }
 
-SEC("tracepoint")
+SEC("socket")
 __description("bounded loop, start in the middle")
-__failure __msg("back-edge")
+__success
+__failure_unpriv __msg_unpriv("back-edge")
 __naked void loop_start_in_the_middle(void)
 {
 	asm volatile ("					\
@@ -136,7 +137,9 @@ l0_%=:	exit;						\
 
 SEC("tracepoint")
 __description("bounded recursion")
-__failure __msg("back-edge")
+__failure
+/* verifier limitation in detecting max stack depth */
+__msg("the call stack of 8 frames is too deep !")
 __naked void bounded_recursion(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/progs/verifier_netfilter_retcode.c b/tools/testing/selftests/bpf/progs/verifier_netfilter_retcode.c
index 353ae6da00e1..e1ffa5d32ff0 100644
--- a/tools/testing/selftests/bpf/progs/verifier_netfilter_retcode.c
+++ b/tools/testing/selftests/bpf/progs/verifier_netfilter_retcode.c
@@ -39,7 +39,7 @@ __naked void with_valid_return_code_test3(void)
 
 SEC("netfilter")
 __description("bpf_exit with invalid return code. test4")
-__failure __msg("R0 has value (0x2; 0x0)")
+__failure __msg("R0 has smin=2 smax=2 should have been in [0, 1]")
 __naked void with_invalid_return_code_test4(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/progs/verifier_precision.c b/tools/testing/selftests/bpf/progs/verifier_precision.c
index 193c0f8272d0..6b564d4c0986 100644
--- a/tools/testing/selftests/bpf/progs/verifier_precision.c
+++ b/tools/testing/selftests/bpf/progs/verifier_precision.c
@@ -91,3 +91,43 @@ __naked int bpf_end_bswap(void)
 }
 
 #endif /* v4 instruction */
+
+SEC("?raw_tp")
+__success __log_level(2)
+/*
+ * Without the bug fix there will be no history between "last_idx 3 first_idx 3"
+ * and "parent state regs=" lines. "R0_w=6" parts are here to help anchor
+ * expected log messages to the one specific mark_chain_precision operation.
+ *
+ * This is quite fragile: if verifier checkpointing heuristic changes, this
+ * might need adjusting.
+ */
+__msg("2: (07) r0 += 1                       ; R0_w=6")
+__msg("3: (35) if r0 >= 0xa goto pc+1")
+__msg("mark_precise: frame0: last_idx 3 first_idx 3 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r0 stack= before 2: (07) r0 += 1")
+__msg("mark_precise: frame0: regs=r0 stack= before 1: (07) r0 += 1")
+__msg("mark_precise: frame0: regs=r0 stack= before 4: (05) goto pc-4")
+__msg("mark_precise: frame0: regs=r0 stack= before 3: (35) if r0 >= 0xa goto pc+1")
+__msg("mark_precise: frame0: parent state regs= stack=:  R0_rw=P4")
+__msg("3: R0_w=6")
+__naked int state_loop_first_last_equal(void)
+{
+	asm volatile (
+		"r0 = 0;"
+	"l0_%=:"
+		"r0 += 1;"
+		"r0 += 1;"
+		/* every few iterations we'll have a checkpoint here with
+		 * first_idx == last_idx, potentially confusing precision
+		 * backtracking logic
+		 */
+		"if r0 >= 10 goto l1_%=;"	/* checkpoint + mark_precise */
+		"goto l0_%=;"
+	"l1_%=:"
+		"exit;"
+		::: __clobber_common
+	);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_raw_stack.c b/tools/testing/selftests/bpf/progs/verifier_raw_stack.c
index efbfc3a4ad6a..7cc83acac727 100644
--- a/tools/testing/selftests/bpf/progs/verifier_raw_stack.c
+++ b/tools/testing/selftests/bpf/progs/verifier_raw_stack.c
@@ -5,9 +5,10 @@
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
 
-SEC("tc")
+SEC("socket")
 __description("raw_stack: no skb_load_bytes")
-__failure __msg("invalid read from stack R6 off=-8 size=8")
+__success
+__failure_unpriv __msg_unpriv("invalid read from stack R6 off=-8 size=8")
 __naked void stack_no_skb_load_bytes(void)
 {
 	asm volatile ("					\
@@ -63,7 +64,7 @@ __naked void load_bytes_negative_len_2(void)
 
 SEC("tc")
 __description("raw_stack: skb_load_bytes, zero len")
-__failure __msg("invalid zero-sized read")
+__failure __msg("R4 invalid zero-sized read: u64=[0,0]")
 __naked void skb_load_bytes_zero_len(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
index 6115520154e3..39fe3372e0e0 100644
--- a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
+++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
@@ -4,6 +4,7 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
+#include <../../../tools/include/linux/filter.h>
 
 struct {
 	__uint(type, BPF_MAP_TYPE_RINGBUF);
@@ -450,4 +451,290 @@ l0_%=:	r1 >>= 16;					\
 	: __clobber_all);
 }
 
+SEC("raw_tp")
+__log_level(2)
+__success
+__msg("fp-8=0m??mmmm")
+__msg("fp-16=00mm??mm")
+__msg("fp-24=00mm???m")
+__naked void spill_subregs_preserve_stack_zero(void)
+{
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+
+		/* 32-bit subreg spill with ZERO, MISC, and INVALID */
+		".8byte %[fp1_u8_st_zero];"   /* ZERO, LLVM-18+: *(u8 *)(r10 -1) = 0; */
+		"*(u8 *)(r10 -2) = r0;"       /* MISC */
+		/* fp-3 and fp-4 stay INVALID */
+		"*(u32 *)(r10 -8) = r0;"
+
+		/* 16-bit subreg spill with ZERO, MISC, and INVALID */
+		".8byte %[fp10_u16_st_zero];" /* ZERO, LLVM-18+: *(u16 *)(r10 -10) = 0; */
+		"*(u16 *)(r10 -12) = r0;"     /* MISC */
+		/* fp-13 and fp-14 stay INVALID */
+		"*(u16 *)(r10 -16) = r0;"
+
+		/* 8-bit subreg spill with ZERO, MISC, and INVALID */
+		".8byte %[fp18_u16_st_zero];" /* ZERO, LLVM-18+: *(u16 *)(r18 -10) = 0; */
+		"*(u16 *)(r10 -20) = r0;"     /* MISC */
+		/* fp-21, fp-22, and fp-23 stay INVALID */
+		"*(u8 *)(r10 -24) = r0;"
+
+		"r0 = 0;"
+		"exit;"
+	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm_insn(fp1_u8_st_zero, BPF_ST_MEM(BPF_B, BPF_REG_FP, -1, 0)),
+	  __imm_insn(fp10_u16_st_zero, BPF_ST_MEM(BPF_H, BPF_REG_FP, -10, 0)),
+	  __imm_insn(fp18_u16_st_zero, BPF_ST_MEM(BPF_H, BPF_REG_FP, -18, 0))
+	: __clobber_all);
+}
+
+char single_byte_buf[1] SEC(".data.single_byte_buf");
+
+SEC("raw_tp")
+__log_level(2)
+__success
+/* make sure fp-8 is all STACK_ZERO */
+__msg("2: (7a) *(u64 *)(r10 -8) = 0          ; R10=fp0 fp-8_w=00000000")
+/* but fp-16 is spilled IMPRECISE zero const reg */
+__msg("4: (7b) *(u64 *)(r10 -16) = r0        ; R0_w=0 R10=fp0 fp-16_w=0")
+/* validate that assigning R2 from STACK_ZERO doesn't mark register
+ * precise immediately; if necessary, it will be marked precise later
+ */
+__msg("6: (71) r2 = *(u8 *)(r10 -1)          ; R2_w=0 R10=fp0 fp-8_w=00000000")
+/* similarly, when R2 is assigned from spilled register, it is initially
+ * imprecise, but will be marked precise later once it is used in precise context
+ */
+__msg("10: (71) r2 = *(u8 *)(r10 -9)         ; R2_w=0 R10=fp0 fp-16_w=0")
+__msg("11: (0f) r1 += r2")
+__msg("mark_precise: frame0: last_idx 11 first_idx 0 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r2 stack= before 10: (71) r2 = *(u8 *)(r10 -9)")
+__msg("mark_precise: frame0: regs= stack=-16 before 9: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs= stack=-16 before 8: (73) *(u8 *)(r1 +0) = r2")
+__msg("mark_precise: frame0: regs= stack=-16 before 7: (0f) r1 += r2")
+__msg("mark_precise: frame0: regs= stack=-16 before 6: (71) r2 = *(u8 *)(r10 -1)")
+__msg("mark_precise: frame0: regs= stack=-16 before 5: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs= stack=-16 before 4: (7b) *(u64 *)(r10 -16) = r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 3: (b7) r0 = 0")
+__naked void partial_stack_load_preserves_zeros(void)
+{
+	asm volatile (
+		/* fp-8 is all STACK_ZERO */
+		".8byte %[fp8_st_zero];" /* LLVM-18+: *(u64 *)(r10 -8) = 0; */
+
+		/* fp-16 is const zero register */
+		"r0 = 0;"
+		"*(u64 *)(r10 -16) = r0;"
+
+		/* load single U8 from non-aligned STACK_ZERO slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u8 *)(r10 -1);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U8 from non-aligned ZERO REG slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u8 *)(r10 -9);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U16 from non-aligned STACK_ZERO slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u16 *)(r10 -2);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U16 from non-aligned ZERO REG slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u16 *)(r10 -10);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U32 from non-aligned STACK_ZERO slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u32 *)(r10 -4);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U32 from non-aligned ZERO REG slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u32 *)(r10 -12);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* for completeness, load U64 from STACK_ZERO slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u64 *)(r10 -8);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* for completeness, load U64 from ZERO REG slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u64 *)(r10 -16);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		"r0 = 0;"
+		"exit;"
+	:
+	: __imm_ptr(single_byte_buf),
+	  __imm_insn(fp8_st_zero, BPF_ST_MEM(BPF_DW, BPF_REG_FP, -8, 0))
+	: __clobber_common);
+}
+
+char two_byte_buf[2] SEC(".data.two_byte_buf");
+
+SEC("raw_tp")
+__log_level(2) __flag(BPF_F_TEST_STATE_FREQ)
+__success
+/* make sure fp-8 is IMPRECISE fake register spill */
+__msg("3: (7a) *(u64 *)(r10 -8) = 1          ; R10=fp0 fp-8_w=1")
+/* and fp-16 is spilled IMPRECISE const reg */
+__msg("5: (7b) *(u64 *)(r10 -16) = r0        ; R0_w=1 R10=fp0 fp-16_w=1")
+/* validate load from fp-8, which was initialized using BPF_ST_MEM */
+__msg("8: (79) r2 = *(u64 *)(r10 -8)         ; R2_w=1 R10=fp0 fp-8=1")
+__msg("9: (0f) r1 += r2")
+__msg("mark_precise: frame0: last_idx 9 first_idx 7 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r2 stack= before 8: (79) r2 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r1 = r6")
+/* note, fp-8 is precise, fp-16 is not yet precise, we'll get there */
+__msg("mark_precise: frame0: parent state regs= stack=-8:  R0_w=1 R1=ctx() R6_r=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8_rw=P1 fp-16_w=1")
+__msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7")
+__msg("mark_precise: frame0: regs= stack=-8 before 6: (05) goto pc+0")
+__msg("mark_precise: frame0: regs= stack=-8 before 5: (7b) *(u64 *)(r10 -16) = r0")
+__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r0 = 1")
+__msg("mark_precise: frame0: regs= stack=-8 before 3: (7a) *(u64 *)(r10 -8) = 1")
+__msg("10: R1_w=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2_w=1")
+/* validate load from fp-16, which was initialized using BPF_STX_MEM */
+__msg("12: (79) r2 = *(u64 *)(r10 -16)       ; R2_w=1 R10=fp0 fp-16=1")
+__msg("13: (0f) r1 += r2")
+__msg("mark_precise: frame0: last_idx 13 first_idx 7 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r2 stack= before 12: (79) r2 = *(u64 *)(r10 -16)")
+__msg("mark_precise: frame0: regs= stack=-16 before 11: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs= stack=-16 before 10: (73) *(u8 *)(r1 +0) = r2")
+__msg("mark_precise: frame0: regs= stack=-16 before 9: (0f) r1 += r2")
+__msg("mark_precise: frame0: regs= stack=-16 before 8: (79) r2 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: regs= stack=-16 before 7: (bf) r1 = r6")
+/* now both fp-8 and fp-16 are precise, very good */
+__msg("mark_precise: frame0: parent state regs= stack=-16:  R0_w=1 R1=ctx() R6_r=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8_rw=P1 fp-16_rw=P1")
+__msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7")
+__msg("mark_precise: frame0: regs= stack=-16 before 6: (05) goto pc+0")
+__msg("mark_precise: frame0: regs= stack=-16 before 5: (7b) *(u64 *)(r10 -16) = r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 4: (b7) r0 = 1")
+__msg("14: R1_w=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2_w=1")
+__naked void stack_load_preserves_const_precision(void)
+{
+	asm volatile (
+		/* establish checkpoint with state that has no stack slots;
+		 * if we bubble up to this state without finding desired stack
+		 * slot, then it's a bug and should be caught
+		 */
+		"goto +0;"
+
+		/* fp-8 is const 1 *fake* register */
+		".8byte %[fp8_st_one];" /* LLVM-18+: *(u64 *)(r10 -8) = 1; */
+
+		/* fp-16 is const 1 register */
+		"r0 = 1;"
+		"*(u64 *)(r10 -16) = r0;"
+
+		/* force checkpoint to check precision marks preserved in parent states */
+		"goto +0;"
+
+		/* load single U64 from aligned FAKE_REG=1 slot */
+		"r1 = %[two_byte_buf];"
+		"r2 = *(u64 *)(r10 -8);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U64 from aligned REG=1 slot */
+		"r1 = %[two_byte_buf];"
+		"r2 = *(u64 *)(r10 -16);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		"r0 = 0;"
+		"exit;"
+	:
+	: __imm_ptr(two_byte_buf),
+	  __imm_insn(fp8_st_one, BPF_ST_MEM(BPF_DW, BPF_REG_FP, -8, 1))
+	: __clobber_common);
+}
+
+SEC("raw_tp")
+__log_level(2) __flag(BPF_F_TEST_STATE_FREQ)
+__success
+/* make sure fp-8 is 32-bit FAKE subregister spill */
+__msg("3: (62) *(u32 *)(r10 -8) = 1          ; R10=fp0 fp-8=????1")
+/* but fp-16 is spilled IMPRECISE zero const reg */
+__msg("5: (63) *(u32 *)(r10 -16) = r0        ; R0_w=1 R10=fp0 fp-16=????1")
+/* validate load from fp-8, which was initialized using BPF_ST_MEM */
+__msg("8: (61) r2 = *(u32 *)(r10 -8)         ; R2_w=1 R10=fp0 fp-8=????1")
+__msg("9: (0f) r1 += r2")
+__msg("mark_precise: frame0: last_idx 9 first_idx 7 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r2 stack= before 8: (61) r2 = *(u32 *)(r10 -8)")
+__msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r1 = r6")
+__msg("mark_precise: frame0: parent state regs= stack=-8:  R0_w=1 R1=ctx() R6_r=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8_r=????P1 fp-16=????1")
+__msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7")
+__msg("mark_precise: frame0: regs= stack=-8 before 6: (05) goto pc+0")
+__msg("mark_precise: frame0: regs= stack=-8 before 5: (63) *(u32 *)(r10 -16) = r0")
+__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r0 = 1")
+__msg("mark_precise: frame0: regs= stack=-8 before 3: (62) *(u32 *)(r10 -8) = 1")
+__msg("10: R1_w=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2_w=1")
+/* validate load from fp-16, which was initialized using BPF_STX_MEM */
+__msg("12: (61) r2 = *(u32 *)(r10 -16)       ; R2_w=1 R10=fp0 fp-16=????1")
+__msg("13: (0f) r1 += r2")
+__msg("mark_precise: frame0: last_idx 13 first_idx 7 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r2 stack= before 12: (61) r2 = *(u32 *)(r10 -16)")
+__msg("mark_precise: frame0: regs= stack=-16 before 11: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs= stack=-16 before 10: (73) *(u8 *)(r1 +0) = r2")
+__msg("mark_precise: frame0: regs= stack=-16 before 9: (0f) r1 += r2")
+__msg("mark_precise: frame0: regs= stack=-16 before 8: (61) r2 = *(u32 *)(r10 -8)")
+__msg("mark_precise: frame0: regs= stack=-16 before 7: (bf) r1 = r6")
+__msg("mark_precise: frame0: parent state regs= stack=-16:  R0_w=1 R1=ctx() R6_r=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8_r=????P1 fp-16_r=????P1")
+__msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7")
+__msg("mark_precise: frame0: regs= stack=-16 before 6: (05) goto pc+0")
+__msg("mark_precise: frame0: regs= stack=-16 before 5: (63) *(u32 *)(r10 -16) = r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 4: (b7) r0 = 1")
+__msg("14: R1_w=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2_w=1")
+__naked void stack_load_preserves_const_precision_subreg(void)
+{
+	asm volatile (
+		/* establish checkpoint with state that has no stack slots;
+		 * if we bubble up to this state without finding desired stack
+		 * slot, then it's a bug and should be caught
+		 */
+		"goto +0;"
+
+		/* fp-8 is const 1 *fake* SUB-register */
+		".8byte %[fp8_st_one];" /* LLVM-18+: *(u32 *)(r10 -8) = 1; */
+
+		/* fp-16 is const 1 SUB-register */
+		"r0 = 1;"
+		"*(u32 *)(r10 -16) = r0;"
+
+		/* force checkpoint to check precision marks preserved in parent states */
+		"goto +0;"
+
+		/* load single U32 from aligned FAKE_REG=1 slot */
+		"r1 = %[two_byte_buf];"
+		"r2 = *(u32 *)(r10 -8);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U32 from aligned REG=1 slot */
+		"r1 = %[two_byte_buf];"
+		"r2 = *(u32 *)(r10 -16);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		"r0 = 0;"
+		"exit;"
+	:
+	: __imm_ptr(two_byte_buf),
+	  __imm_insn(fp8_st_one, BPF_ST_MEM(BPF_W, BPF_REG_FP, -8, 1)) /* 32-bit spill */
+	: __clobber_common);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c b/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c
index e0f77e3e7869..417c61cd4b19 100644
--- a/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c
+++ b/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c
@@ -37,7 +37,7 @@ __naked void ptr_to_stack_store_load(void)
 
 SEC("socket")
 __description("PTR_TO_STACK store/load - bad alignment on off")
-__failure __msg("misaligned stack access off (0x0; 0x0)+-8+2 size 8")
+__failure __msg("misaligned stack access off 0+-8+2 size 8")
 __failure_unpriv
 __naked void load_bad_alignment_on_off(void)
 {
@@ -53,7 +53,7 @@ __naked void load_bad_alignment_on_off(void)
 
 SEC("socket")
 __description("PTR_TO_STACK store/load - bad alignment on reg")
-__failure __msg("misaligned stack access off (0x0; 0x0)+-10+8 size 8")
+__failure __msg("misaligned stack access off 0+-10+8 size 8")
 __failure_unpriv
 __naked void load_bad_alignment_on_reg(void)
 {
diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
index db6b3143338b..6f5d19665cf6 100644
--- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
+++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
@@ -117,17 +117,93 @@ __naked int global_subprog_result_precise(void)
 	);
 }
 
+__naked __noinline __used
+static unsigned long loop_callback_bad()
+{
+	/* bpf_loop() callback that can return values outside of [0, 1] range */
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+		"if r0 s> 1000 goto 1f;"
+		"r0 = 0;"
+	"1:"
+		"goto +0;" /* checkpoint */
+		/* bpf_loop() expects [0, 1] values, so branch above skipping
+		 * r0 = 0; should lead to a failure, but if exit instruction
+		 * doesn't enforce r0's precision, this callback will be
+		 * successfully verified
+		 */
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32)
+		: __clobber_common
+	);
+}
+
+SEC("?raw_tp")
+__failure __log_level(2)
+__flag(BPF_F_TEST_STATE_FREQ)
+/* check that fallthrough code path marks r0 as precise */
+__msg("mark_precise: frame1: regs=r0 stack= before 11: (b7) r0 = 0")
+/* check that we have branch code path doing its own validation */
+__msg("from 10 to 12: frame1: R0=scalar(smin=umin=1001")
+/* check that branch code path marks r0 as precise, before failing */
+__msg("mark_precise: frame1: regs=r0 stack= before 9: (85) call bpf_get_prandom_u32#7")
+__msg("At callback return the register R0 has smin=1001 should have been in [0, 1]")
+__naked int callback_precise_return_fail(void)
+{
+	asm volatile (
+		"r1 = 1;"			/* nr_loops */
+		"r2 = %[loop_callback_bad];"	/* callback_fn */
+		"r3 = 0;"			/* callback_ctx */
+		"r4 = 0;"			/* flags */
+		"call %[bpf_loop];"
+
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm_ptr(loop_callback_bad),
+		  __imm(bpf_loop)
+		: __clobber_common
+	);
+}
+
 SEC("?raw_tp")
 __success __log_level(2)
+/* First simulated path does not include callback body,
+ * r1 and r4 are always precise for bpf_loop() calls.
+ */
+__msg("9: (85) call bpf_loop#181")
+__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1")
+__msg("mark_precise: frame0: parent state regs=r4 stack=:")
+__msg("mark_precise: frame0: last_idx 8 first_idx 0 subseq_idx 9")
+__msg("mark_precise: frame0: regs=r4 stack= before 8: (b7) r4 = 0")
+__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1")
+__msg("mark_precise: frame0: parent state regs=r1 stack=:")
+__msg("mark_precise: frame0: last_idx 8 first_idx 0 subseq_idx 9")
+__msg("mark_precise: frame0: regs=r1 stack= before 8: (b7) r4 = 0")
+__msg("mark_precise: frame0: regs=r1 stack= before 7: (b7) r3 = 0")
+__msg("mark_precise: frame0: regs=r1 stack= before 6: (bf) r2 = r8")
+__msg("mark_precise: frame0: regs=r1 stack= before 5: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3")
+/* r6 precision propagation */
 __msg("14: (0f) r1 += r6")
-__msg("mark_precise: frame0: last_idx 14 first_idx 10")
+__msg("mark_precise: frame0: last_idx 14 first_idx 9")
 __msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7")
 __msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4")
 __msg("mark_precise: frame0: regs=r6 stack= before 11: (25) if r6 > 0x3 goto pc+4")
 __msg("mark_precise: frame0: regs=r6 stack= before 10: (bf) r6 = r0")
-__msg("mark_precise: frame0: parent state regs=r0 stack=:")
-__msg("mark_precise: frame0: last_idx 18 first_idx 0")
-__msg("mark_precise: frame0: regs=r0 stack= before 18: (95) exit")
+__msg("mark_precise: frame0: regs=r0 stack= before 9: (85) call bpf_loop")
+/* State entering callback body popped from states stack */
+__msg("from 9 to 17: frame1:")
+__msg("17: frame1: R1=scalar() R2=0 R10=fp0 cb")
+__msg("17: (b7) r0 = 0")
+__msg("18: (95) exit")
+__msg("returning from callee:")
+__msg("to caller at 9:")
+__msg("frame 0: propagating r1,r4")
+__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r1,r4 stack= before 18: (95) exit")
+__msg("from 18 to 9: safe")
 __naked int callback_result_precise(void)
 {
 	asm volatile (
@@ -233,20 +309,36 @@ __naked int parent_callee_saved_reg_precise_global(void)
 
 SEC("?raw_tp")
 __success __log_level(2)
+/* First simulated path does not include callback body */
 __msg("12: (0f) r1 += r6")
-__msg("mark_precise: frame0: last_idx 12 first_idx 10")
+__msg("mark_precise: frame0: last_idx 12 first_idx 9")
 __msg("mark_precise: frame0: regs=r6 stack= before 11: (bf) r1 = r7")
 __msg("mark_precise: frame0: regs=r6 stack= before 10: (27) r6 *= 4")
+__msg("mark_precise: frame0: regs=r6 stack= before 9: (85) call bpf_loop")
 __msg("mark_precise: frame0: parent state regs=r6 stack=:")
-__msg("mark_precise: frame0: last_idx 16 first_idx 0")
-__msg("mark_precise: frame0: regs=r6 stack= before 16: (95) exit")
-__msg("mark_precise: frame1: regs= stack= before 15: (b7) r0 = 0")
-__msg("mark_precise: frame1: regs= stack= before 9: (85) call bpf_loop#181")
+__msg("mark_precise: frame0: last_idx 8 first_idx 0 subseq_idx 9")
 __msg("mark_precise: frame0: regs=r6 stack= before 8: (b7) r4 = 0")
 __msg("mark_precise: frame0: regs=r6 stack= before 7: (b7) r3 = 0")
 __msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r2 = r8")
 __msg("mark_precise: frame0: regs=r6 stack= before 5: (b7) r1 = 1")
 __msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3")
+/* State entering callback body popped from states stack */
+__msg("from 9 to 15: frame1:")
+__msg("15: frame1: R1=scalar() R2=0 R10=fp0 cb")
+__msg("15: (b7) r0 = 0")
+__msg("16: (95) exit")
+__msg("returning from callee:")
+__msg("to caller at 9:")
+/* r1, r4 are always precise for bpf_loop(),
+ * r6 was marked before backtracking to callback body.
+ */
+__msg("frame 0: propagating r1,r4,r6")
+__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r1,r4,r6 stack= before 16: (95) exit")
+__msg("mark_precise: frame1: regs= stack= before 15: (b7) r0 = 0")
+__msg("mark_precise: frame1: regs= stack= before 9: (85) call bpf_loop")
+__msg("mark_precise: frame0: parent state regs= stack=:")
+__msg("from 16 to 9: safe")
 __naked int parent_callee_saved_reg_precise_with_callback(void)
 {
 	asm volatile (
@@ -328,12 +420,10 @@ __naked int parent_stack_slot_precise(void)
 SEC("?raw_tp")
 __success __log_level(2)
 __msg("9: (0f) r1 += r6")
-__msg("mark_precise: frame0: last_idx 9 first_idx 6")
+__msg("mark_precise: frame0: last_idx 9 first_idx 0")
 __msg("mark_precise: frame0: regs=r6 stack= before 8: (bf) r1 = r7")
 __msg("mark_precise: frame0: regs=r6 stack= before 7: (27) r6 *= 4")
 __msg("mark_precise: frame0: regs=r6 stack= before 6: (79) r6 = *(u64 *)(r10 -8)")
-__msg("mark_precise: frame0: parent state regs= stack=-8:")
-__msg("mark_precise: frame0: last_idx 5 first_idx 0")
 __msg("mark_precise: frame0: regs= stack=-8 before 5: (85) call pc+6")
 __msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r1 = 0")
 __msg("mark_precise: frame0: regs= stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r6")
@@ -373,22 +463,38 @@ __naked int parent_stack_slot_precise_global(void)
 
 SEC("?raw_tp")
 __success __log_level(2)
+/* First simulated path does not include callback body */
 __msg("14: (0f) r1 += r6")
-__msg("mark_precise: frame0: last_idx 14 first_idx 11")
+__msg("mark_precise: frame0: last_idx 14 first_idx 10")
 __msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7")
 __msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4")
 __msg("mark_precise: frame0: regs=r6 stack= before 11: (79) r6 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: regs= stack=-8 before 10: (85) call bpf_loop")
 __msg("mark_precise: frame0: parent state regs= stack=-8:")
-__msg("mark_precise: frame0: last_idx 18 first_idx 0")
-__msg("mark_precise: frame0: regs= stack=-8 before 18: (95) exit")
-__msg("mark_precise: frame1: regs= stack= before 17: (b7) r0 = 0")
-__msg("mark_precise: frame1: regs= stack= before 10: (85) call bpf_loop#181")
+__msg("mark_precise: frame0: last_idx 9 first_idx 0 subseq_idx 10")
 __msg("mark_precise: frame0: regs= stack=-8 before 9: (b7) r4 = 0")
 __msg("mark_precise: frame0: regs= stack=-8 before 8: (b7) r3 = 0")
 __msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r2 = r8")
 __msg("mark_precise: frame0: regs= stack=-8 before 6: (bf) r1 = r6")
 __msg("mark_precise: frame0: regs= stack=-8 before 5: (7b) *(u64 *)(r10 -8) = r6")
 __msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3")
+/* State entering callback body popped from states stack */
+__msg("from 10 to 17: frame1:")
+__msg("17: frame1: R1=scalar() R2=0 R10=fp0 cb")
+__msg("17: (b7) r0 = 0")
+__msg("18: (95) exit")
+__msg("returning from callee:")
+__msg("to caller at 10:")
+/* r1, r4 are always precise for bpf_loop(),
+ * fp-8 was marked before backtracking to callback body.
+ */
+__msg("frame 0: propagating r1,r4,fp-8")
+__msg("mark_precise: frame0: last_idx 10 first_idx 10 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r1,r4 stack=-8 before 18: (95) exit")
+__msg("mark_precise: frame1: regs= stack= before 17: (b7) r0 = 0")
+__msg("mark_precise: frame1: regs= stack= before 10: (85) call bpf_loop#181")
+__msg("mark_precise: frame0: parent state regs= stack=:")
+__msg("from 18 to 10: safe")
 __naked int parent_stack_slot_precise_with_callback(void)
 {
 	asm volatile (
@@ -483,11 +589,24 @@ static __u64 subprog_spill_reg_precise(void)
 
 SEC("?raw_tp")
 __success __log_level(2)
-/* precision backtracking can't currently handle stack access not through r10,
- * so we won't be able to mark stack slot fp-8 as precise, and so will
- * fallback to forcing all as precise
- */
-__msg("mark_precise: frame0: falling back to forcing all scalars precise")
+__msg("10: (0f) r1 += r7")
+__msg("mark_precise: frame0: last_idx 10 first_idx 7 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r7 stack= before 9: (bf) r1 = r8")
+__msg("mark_precise: frame0: regs=r7 stack= before 8: (27) r7 *= 4")
+__msg("mark_precise: frame0: regs=r7 stack= before 7: (79) r7 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: parent state regs= stack=-8:  R0_w=2 R6_w=1 R8_rw=map_value(map=.data.vals,ks=4,vs=16) R10=fp0 fp-8_rw=P1")
+__msg("mark_precise: frame0: last_idx 18 first_idx 0 subseq_idx 7")
+__msg("mark_precise: frame0: regs= stack=-8 before 18: (95) exit")
+__msg("mark_precise: frame1: regs= stack= before 17: (0f) r0 += r2")
+__msg("mark_precise: frame1: regs= stack= before 16: (79) r2 = *(u64 *)(r1 +0)")
+__msg("mark_precise: frame1: regs= stack= before 15: (79) r0 = *(u64 *)(r10 -16)")
+__msg("mark_precise: frame1: regs= stack= before 14: (7b) *(u64 *)(r10 -16) = r2")
+__msg("mark_precise: frame1: regs= stack= before 13: (7b) *(u64 *)(r1 +0) = r2")
+__msg("mark_precise: frame1: regs=r2 stack= before 6: (85) call pc+6")
+__msg("mark_precise: frame0: regs=r2 stack= before 5: (bf) r2 = r6")
+__msg("mark_precise: frame0: regs=r6 stack= before 4: (07) r1 += -8")
+__msg("mark_precise: frame0: regs=r6 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 1")
 __naked int subprog_spill_into_parent_stack_slot_precise(void)
 {
 	asm volatile (
@@ -522,14 +641,68 @@ __naked int subprog_spill_into_parent_stack_slot_precise(void)
 	);
 }
 
-__naked __noinline __used
-static __u64 subprog_with_checkpoint(void)
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("17: (0f) r1 += r0")
+__msg("mark_precise: frame0: last_idx 17 first_idx 0 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r0 stack= before 16: (bf) r1 = r7")
+__msg("mark_precise: frame0: regs=r0 stack= before 15: (27) r0 *= 4")
+__msg("mark_precise: frame0: regs=r0 stack= before 14: (79) r0 = *(u64 *)(r10 -16)")
+__msg("mark_precise: frame0: regs= stack=-16 before 13: (7b) *(u64 *)(r7 -8) = r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 12: (79) r0 = *(u64 *)(r8 +16)")
+__msg("mark_precise: frame0: regs= stack=-16 before 11: (7b) *(u64 *)(r8 +16) = r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 10: (79) r0 = *(u64 *)(r7 -8)")
+__msg("mark_precise: frame0: regs= stack=-16 before 9: (7b) *(u64 *)(r10 -16) = r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 8: (07) r8 += -32")
+__msg("mark_precise: frame0: regs=r0 stack= before 7: (bf) r8 = r10")
+__msg("mark_precise: frame0: regs=r0 stack= before 6: (07) r7 += -8")
+__msg("mark_precise: frame0: regs=r0 stack= before 5: (bf) r7 = r10")
+__msg("mark_precise: frame0: regs=r0 stack= before 21: (95) exit")
+__msg("mark_precise: frame1: regs=r0 stack= before 20: (bf) r0 = r1")
+__msg("mark_precise: frame1: regs=r1 stack= before 4: (85) call pc+15")
+__msg("mark_precise: frame0: regs=r1 stack= before 3: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 1")
+__naked int stack_slot_aliases_precision(void)
 {
 	asm volatile (
-		"r0 = 0;"
-		/* guaranteed checkpoint if BPF_F_TEST_STATE_FREQ is used */
-		"goto +0;"
+		"r6 = 1;"
+		/* pass r6 through r1 into subprog to get it back as r0;
+		 * this whole chain will have to be marked as precise later
+		 */
+		"r1 = r6;"
+		"call identity_subprog;"
+		/* let's setup two registers that are aliased to r10 */
+		"r7 = r10;"
+		"r7 += -8;"			/* r7 = r10 - 8 */
+		"r8 = r10;"
+		"r8 += -32;"			/* r8 = r10 - 32 */
+		/* now spill subprog's return value (a r6 -> r1 -> r0 chain)
+		 * a few times through different stack pointer regs, making
+		 * sure to use r10, r7, and r8 both in LDX and STX insns, and
+		 * *importantly* also using a combination of const var_off and
+		 * insn->off to validate that we record final stack slot
+		 * correctly, instead of relying on just insn->off derivation,
+		 * which is only valid for r10-based stack offset
+		 */
+		"*(u64 *)(r10 - 16) = r0;"
+		"r0 = *(u64 *)(r7 - 8);"	/* r7 - 8 == r10 - 16 */
+		"*(u64 *)(r8 + 16) = r0;"	/* r8 + 16 = r10 - 16 */
+		"r0 = *(u64 *)(r8 + 16);"
+		"*(u64 *)(r7 - 8) = r0;"
+		"r0 = *(u64 *)(r10 - 16);"
+		/* get ready to use r0 as an index into array to force precision */
+		"r0 *= 4;"
+		"r1 = %[vals];"
+		/* here r0->r1->r6 chain is forced to be precise and has to be
+		 * propagated back to the beginning, including through the
+		 * subprog call and all the stack spills and loads
+		 */
+		"r1 += r0;"
+		"r0 = *(u32 *)(r1 + 0);"
 		"exit;"
+		:
+		: __imm_ptr(vals)
+		: __clobber_common, "r6"
 	);
 }
 
diff --git a/tools/testing/selftests/bpf/progs/verifier_var_off.c b/tools/testing/selftests/bpf/progs/verifier_var_off.c
index 83a90afba785..c810f4f6f479 100644
--- a/tools/testing/selftests/bpf/progs/verifier_var_off.c
+++ b/tools/testing/selftests/bpf/progs/verifier_var_off.c
@@ -59,9 +59,10 @@ __naked void stack_read_priv_vs_unpriv(void)
 "	::: __clobber_all);
 }
 
-SEC("lwt_in")
+SEC("cgroup/skb")
 __description("variable-offset stack read, uninitialized")
-__failure __msg("invalid variable-offset read from stack R2")
+__success
+__failure_unpriv __msg_unpriv("R2 variable stack access prohibited for !root")
 __naked void variable_offset_stack_read_uninitialized(void)
 {
 	asm volatile ("					\
@@ -83,13 +84,56 @@ __naked void variable_offset_stack_read_uninitialized(void)
 
 SEC("socket")
 __description("variable-offset stack write, priv vs unpriv")
-__success __failure_unpriv
+__success
+/* Check that the maximum stack depth is correctly maintained according to the
+ * maximum possible variable offset.
+ */
+__log_level(4) __msg("stack depth 16")
+__failure_unpriv
 /* Variable stack access is rejected for unprivileged.
  */
 __msg_unpriv("R2 variable stack access prohibited for !root")
 __retval(0)
 __naked void stack_write_priv_vs_unpriv(void)
 {
+	asm volatile ("                               \
+	/* Get an unknown value */                    \
+	r2 = *(u32*)(r1 + 0);                         \
+	/* Make it small and 8-byte aligned */        \
+	r2 &= 8;                                      \
+	r2 -= 16;                                     \
+	/* Add it to fp. We now have either fp-8 or   \
+	 * fp-16, but we don't know which             \
+	 */                                           \
+	r2 += r10;                                    \
+	/* Dereference it for a stack write */        \
+	r0 = 0;                                       \
+	*(u64*)(r2 + 0) = r0;                         \
+	exit;                                         \
+"	::: __clobber_all);
+}
+
+/* Similar to the previous test, but this time also perform a read from the
+ * address written to with a variable offset. The read is allowed, showing that,
+ * after a variable-offset write, a priviledged program can read the slots that
+ * were in the range of that write (even if the verifier doesn't actually know if
+ * the slot being read was really written to or not.
+ *
+ * Despite this test being mostly a superset, the previous test is also kept for
+ * the sake of it checking the stack depth in the case where there is no read.
+ */
+SEC("socket")
+__description("variable-offset stack write followed by read")
+__success
+/* Check that the maximum stack depth is correctly maintained according to the
+ * maximum possible variable offset.
+ */
+__log_level(4) __msg("stack depth 16")
+__failure_unpriv
+__msg_unpriv("R2 variable stack access prohibited for !root")
+__retval(0)
+__naked void stack_write_followed_by_read(void)
+{
 	asm volatile ("					\
 	/* Get an unknown value */			\
 	r2 = *(u32*)(r1 + 0);				\
@@ -103,12 +147,7 @@ __naked void stack_write_priv_vs_unpriv(void)
 	/* Dereference it for a stack write */		\
 	r0 = 0;						\
 	*(u64*)(r2 + 0) = r0;				\
-	/* Now read from the address we just wrote. This shows\
-	 * that, after a variable-offset write, a priviledged\
-	 * program can read the slots that were in the range of\
-	 * that write (even if the verifier doesn't actually know\
-	 * if the slot being read was really written to or not.\
-	 */						\
+	/* Now read from the address we just wrote. */ \
 	r3 = *(u64*)(r2 + 0);				\
 	r0 = 0;						\
 	exit;						\
@@ -224,6 +263,35 @@ __naked void access_max_out_of_bound(void)
 	: __clobber_all);
 }
 
+/* Similar to the test above, but this time check the special case of a
+ * zero-sized stack access. We used to have a bug causing crashes for zero-sized
+ * out-of-bounds accesses.
+ */
+SEC("socket")
+__description("indirect variable-offset stack access, zero-sized, max out of bound")
+__failure __msg("invalid variable-offset indirect access to stack R1")
+__naked void zero_sized_access_max_out_of_bound(void)
+{
+	asm volatile ("                      \
+	r0 = 0;                              \
+	/* Fill some stack */                \
+	*(u64*)(r10 - 16) = r0;              \
+	*(u64*)(r10 - 8) = r0;               \
+	/* Get an unknown value */           \
+	r1 = *(u32*)(r1 + 0);                \
+	r1 &= 63;                            \
+	r1 += -16;                           \
+	/* r1 is now anywhere in [-16,48) */ \
+	r1 += r10;                           \
+	r2 = 0;                              \
+	r3 = 0;                              \
+	call %[bpf_probe_read_kernel];       \
+	exit;                                \
+"	:
+	: __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
 SEC("lwt_in")
 __description("indirect variable-offset stack access, min out of bound")
 __failure __msg("invalid variable-offset indirect access to stack R2")
@@ -253,9 +321,10 @@ __naked void access_min_out_of_bound(void)
 	: __clobber_all);
 }
 
-SEC("lwt_in")
+SEC("cgroup/skb")
 __description("indirect variable-offset stack access, min_off < min_initialized")
-__failure __msg("invalid indirect read from stack R2 var_off")
+__success
+__failure_unpriv __msg_unpriv("R2 variable stack access prohibited for !root")
 __naked void access_min_off_min_initialized(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
index f6d1cc9ad892..330ece2eabdb 100644
--- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
@@ -20,21 +20,32 @@ extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx,
 					 __u64 *timestamp) __ksym;
 extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash,
 				    enum xdp_rss_hash_type *rss_type) __ksym;
+extern int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx,
+					__be16 *vlan_proto,
+					__u16 *vlan_tci) __ksym;
 
 SEC("xdp.frags")
 int rx(struct xdp_md *ctx)
 {
 	void *data, *data_meta, *data_end;
 	struct ipv6hdr *ip6h = NULL;
-	struct ethhdr *eth = NULL;
 	struct udphdr *udp = NULL;
 	struct iphdr *iph = NULL;
 	struct xdp_meta *meta;
+	struct ethhdr *eth;
 	int err;
 
 	data = (void *)(long)ctx->data;
 	data_end = (void *)(long)ctx->data_end;
 	eth = data;
+
+	if (eth + 1 < data_end && (eth->h_proto == bpf_htons(ETH_P_8021AD) ||
+				   eth->h_proto == bpf_htons(ETH_P_8021Q)))
+		eth = (void *)eth + sizeof(struct vlan_hdr);
+
+	if (eth + 1 < data_end && eth->h_proto == bpf_htons(ETH_P_8021Q))
+		eth = (void *)eth + sizeof(struct vlan_hdr);
+
 	if (eth + 1 < data_end) {
 		if (eth->h_proto == bpf_htons(ETH_P_IP)) {
 			iph = (void *)(eth + 1);
@@ -76,15 +87,28 @@ int rx(struct xdp_md *ctx)
 		return XDP_PASS;
 	}
 
+	meta->hint_valid = 0;
+
+	meta->xdp_timestamp = bpf_ktime_get_tai_ns();
 	err = bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp);
-	if (!err)
-		meta->xdp_timestamp = bpf_ktime_get_tai_ns();
+	if (err)
+		meta->rx_timestamp_err = err;
 	else
-		meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */
+		meta->hint_valid |= XDP_META_FIELD_TS;
 
-	err = bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type);
-	if (err < 0)
-		meta->rx_hash_err = err; /* Used by AF_XDP as no hash signal */
+	err = bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash,
+				       &meta->rx_hash_type);
+	if (err)
+		meta->rx_hash_err = err;
+	else
+		meta->hint_valid |= XDP_META_FIELD_RSS;
+
+	err = bpf_xdp_metadata_rx_vlan_tag(ctx, &meta->rx_vlan_proto,
+					   &meta->rx_vlan_tci);
+	if (err)
+		meta->rx_vlan_tag_err = err;
+	else
+		meta->hint_valid |= XDP_META_FIELD_VLAN_TAG;
 
 	__sync_add_and_fetch(&pkts_redir, 1);
 	return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS);
diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata.c b/tools/testing/selftests/bpf/progs/xdp_metadata.c
index d151d406a123..31ca229bb3c0 100644
--- a/tools/testing/selftests/bpf/progs/xdp_metadata.c
+++ b/tools/testing/selftests/bpf/progs/xdp_metadata.c
@@ -23,15 +23,47 @@ extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx,
 					 __u64 *timestamp) __ksym;
 extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash,
 				    enum xdp_rss_hash_type *rss_type) __ksym;
+extern int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx,
+					__be16 *vlan_proto,
+					__u16 *vlan_tci) __ksym;
 
 SEC("xdp")
 int rx(struct xdp_md *ctx)
 {
-	void *data, *data_meta;
+	void *data, *data_meta, *data_end;
+	struct ipv6hdr *ip6h = NULL;
+	struct ethhdr *eth = NULL;
+	struct udphdr *udp = NULL;
+	struct iphdr *iph = NULL;
 	struct xdp_meta *meta;
 	u64 timestamp = -1;
 	int ret;
 
+	data = (void *)(long)ctx->data;
+	data_end = (void *)(long)ctx->data_end;
+	eth = data;
+	if (eth + 1 < data_end) {
+		if (eth->h_proto == bpf_htons(ETH_P_IP)) {
+			iph = (void *)(eth + 1);
+			if (iph + 1 < data_end && iph->protocol == IPPROTO_UDP)
+				udp = (void *)(iph + 1);
+		}
+		if (eth->h_proto == bpf_htons(ETH_P_IPV6)) {
+			ip6h = (void *)(eth + 1);
+			if (ip6h + 1 < data_end && ip6h->nexthdr == IPPROTO_UDP)
+				udp = (void *)(ip6h + 1);
+		}
+		if (udp && udp + 1 > data_end)
+			udp = NULL;
+	}
+
+	if (!udp)
+		return XDP_PASS;
+
+	/* Forwarding UDP:8080 to AF_XDP */
+	if (udp->dest != bpf_htons(8080))
+		return XDP_PASS;
+
 	/* Reserve enough for all custom metadata. */
 
 	ret = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta));
@@ -57,6 +89,8 @@ int rx(struct xdp_md *ctx)
 		meta->rx_timestamp = 1;
 
 	bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type);
+	bpf_xdp_metadata_rx_vlan_tag(ctx, &meta->rx_vlan_proto,
+				     &meta->rx_vlan_tci);
 
 	return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS);
 }
diff --git a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
index e959336c7a73..518329c666e9 100644
--- a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
+++ b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
@@ -53,6 +53,8 @@
 #define DEFAULT_TTL 64
 #define MAX_ALLOWED_PORTS 8
 
+#define MAX_PACKET_OFF 0xffff
+
 #define swap(a, b) \
 	do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
 
@@ -183,63 +185,76 @@ static __always_inline __u32 tcp_clock_ms(void)
 }
 
 struct tcpopt_context {
-	__u8 *ptr;
-	__u8 *end;
+	void *data;
 	void *data_end;
 	__be32 *tsecr;
 	__u8 wscale;
 	bool option_timestamp;
 	bool option_sack;
+	__u32 off;
 };
 
-static int tscookie_tcpopt_parse(struct tcpopt_context *ctx)
+static __always_inline u8 *next(struct tcpopt_context *ctx, __u32 sz)
 {
-	__u8 opcode, opsize;
+	__u64 off = ctx->off;
+	__u8 *data;
 
-	if (ctx->ptr >= ctx->end)
-		return 1;
-	if (ctx->ptr >= ctx->data_end)
-		return 1;
+	/* Verifier forbids access to packet when offset exceeds MAX_PACKET_OFF */
+	if (off > MAX_PACKET_OFF - sz)
+		return NULL;
 
-	opcode = ctx->ptr[0];
+	data = ctx->data + off;
+	barrier_var(data);
+	if (data + sz >= ctx->data_end)
+		return NULL;
 
-	if (opcode == TCPOPT_EOL)
-		return 1;
-	if (opcode == TCPOPT_NOP) {
-		++ctx->ptr;
-		return 0;
-	}
+	ctx->off += sz;
+	return data;
+}
 
-	if (ctx->ptr + 1 >= ctx->end)
-		return 1;
-	if (ctx->ptr + 1 >= ctx->data_end)
+static int tscookie_tcpopt_parse(struct tcpopt_context *ctx)
+{
+	__u8 *opcode, *opsize, *wscale, *tsecr;
+	__u32 off = ctx->off;
+
+	opcode = next(ctx, 1);
+	if (!opcode)
 		return 1;
-	opsize = ctx->ptr[1];
-	if (opsize < 2)
+
+	if (*opcode == TCPOPT_EOL)
 		return 1;
+	if (*opcode == TCPOPT_NOP)
+		return 0;
 
-	if (ctx->ptr + opsize > ctx->end)
+	opsize = next(ctx, 1);
+	if (!opsize || *opsize < 2)
 		return 1;
 
-	switch (opcode) {
+	switch (*opcode) {
 	case TCPOPT_WINDOW:
-		if (opsize == TCPOLEN_WINDOW && ctx->ptr + TCPOLEN_WINDOW <= ctx->data_end)
-			ctx->wscale = ctx->ptr[2] < TCP_MAX_WSCALE ? ctx->ptr[2] : TCP_MAX_WSCALE;
+		wscale = next(ctx, 1);
+		if (!wscale)
+			return 1;
+		if (*opsize == TCPOLEN_WINDOW)
+			ctx->wscale = *wscale < TCP_MAX_WSCALE ? *wscale : TCP_MAX_WSCALE;
 		break;
 	case TCPOPT_TIMESTAMP:
-		if (opsize == TCPOLEN_TIMESTAMP && ctx->ptr + TCPOLEN_TIMESTAMP <= ctx->data_end) {
+		tsecr = next(ctx, 4);
+		if (!tsecr)
+			return 1;
+		if (*opsize == TCPOLEN_TIMESTAMP) {
 			ctx->option_timestamp = true;
 			/* Client's tsval becomes our tsecr. */
-			*ctx->tsecr = get_unaligned((__be32 *)(ctx->ptr + 2));
+			*ctx->tsecr = get_unaligned((__be32 *)tsecr);
 		}
 		break;
 	case TCPOPT_SACK_PERM:
-		if (opsize == TCPOLEN_SACK_PERM)
+		if (*opsize == TCPOLEN_SACK_PERM)
 			ctx->option_sack = true;
 		break;
 	}
 
-	ctx->ptr += opsize;
+	ctx->off = off + *opsize;
 
 	return 0;
 }
@@ -256,16 +271,21 @@ static int tscookie_tcpopt_parse_batch(__u32 index, void *context)
 
 static __always_inline bool tscookie_init(struct tcphdr *tcp_header,
 					  __u16 tcp_len, __be32 *tsval,
-					  __be32 *tsecr, void *data_end)
+					  __be32 *tsecr, void *data, void *data_end)
 {
 	struct tcpopt_context loop_ctx = {
-		.ptr = (__u8 *)(tcp_header + 1),
-		.end = (__u8 *)tcp_header + tcp_len,
+		.data = data,
 		.data_end = data_end,
 		.tsecr = tsecr,
 		.wscale = TS_OPT_WSCALE_MASK,
 		.option_timestamp = false,
 		.option_sack = false,
+		/* Note: currently verifier would track .off as unbound scalar.
+		 *       In case if verifier would at some point get smarter and
+		 *       compute bounded value for this var, beware that it might
+		 *       hinder bpf_loop() convergence validation.
+		 */
+		.off = (__u8 *)(tcp_header + 1) - (__u8 *)data,
 	};
 	u32 cookie;
 
@@ -447,13 +467,13 @@ static __always_inline int tcp_lookup(void *ctx, struct header_pointers *hdr, bo
 		unsigned long status = ct->status;
 
 		bpf_ct_release(ct);
-		if (status & IPS_CONFIRMED_BIT)
+		if (status & IPS_CONFIRMED)
 			return XDP_PASS;
 	} else if (ct_lookup_opts.error != -ENOENT) {
 		return XDP_ABORTED;
 	}
 
-	/* error == -ENOENT || !(status & IPS_CONFIRMED_BIT) */
+	/* error == -ENOENT || !(status & IPS_CONFIRMED) */
 	return XDP_TX;
 }
 
@@ -635,7 +655,7 @@ static __always_inline int syncookie_handle_syn(struct header_pointers *hdr,
 	cookie = (__u32)value;
 
 	if (tscookie_init((void *)hdr->tcp, hdr->tcp_len,
-			  &tsopt_buf[0], &tsopt_buf[1], data_end))
+			  &tsopt_buf[0], &tsopt_buf[1], data, data_end))
 		tsopt = tsopt_buf;
 
 	/* Check that there is enough space for a SYNACK. It also covers
diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
index 37ffa57f28a1..f01391021218 100644
--- a/tools/testing/selftests/bpf/test_loader.c
+++ b/tools/testing/selftests/bpf/test_loader.c
@@ -12,7 +12,7 @@
 #define str_has_pfx(str, pfx) \
 	(strncmp(str, pfx, __builtin_constant_p(pfx) ? sizeof(pfx) - 1 : strlen(pfx)) == 0)
 
-#define TEST_LOADER_LOG_BUF_SZ 1048576
+#define TEST_LOADER_LOG_BUF_SZ 2097152
 
 #define TEST_TAG_EXPECT_FAILURE "comment:test_expect_failure"
 #define TEST_TAG_EXPECT_SUCCESS "comment:test_expect_success"
@@ -27,6 +27,7 @@
 #define TEST_TAG_RETVAL_PFX_UNPRIV "comment:test_retval_unpriv="
 #define TEST_TAG_AUXILIARY "comment:test_auxiliary"
 #define TEST_TAG_AUXILIARY_UNPRIV "comment:test_auxiliary_unpriv"
+#define TEST_BTF_PATH "comment:test_btf_path="
 
 /* Warning: duplicated in bpf_misc.h */
 #define POINTER_VALUE	0xcafe4all
@@ -58,6 +59,7 @@ struct test_spec {
 	const char *prog_name;
 	struct test_subspec priv;
 	struct test_subspec unpriv;
+	const char *btf_custom_path;
 	int log_level;
 	int prog_flags;
 	int mode_mask;
@@ -153,6 +155,14 @@ static int parse_retval(const char *str, int *val, const char *name)
 	return parse_int(str, val, name);
 }
 
+static void update_flags(int *flags, int flag, bool clear)
+{
+	if (clear)
+		*flags &= ~flag;
+	else
+		*flags |= flag;
+}
+
 /* Uses btf_decl_tag attributes to describe the expected test
  * behavior, see bpf_misc.h for detailed description of each attribute
  * and attribute combinations.
@@ -171,6 +181,7 @@ static int parse_test_spec(struct test_loader *tester,
 	memset(spec, 0, sizeof(*spec));
 
 	spec->prog_name = bpf_program__name(prog);
+	spec->prog_flags = BPF_F_TEST_REG_INVARIANTS; /* by default be strict */
 
 	btf = bpf_object__btf(obj);
 	if (!btf) {
@@ -187,7 +198,8 @@ static int parse_test_spec(struct test_loader *tester,
 	for (i = 1; i < btf__type_cnt(btf); i++) {
 		const char *s, *val, *msg;
 		const struct btf_type *t;
-		int tmp;
+		bool clear;
+		int flags;
 
 		t = btf__type_by_id(btf, i);
 		if (!btf_is_decl_tag(t))
@@ -253,24 +265,33 @@ static int parse_test_spec(struct test_loader *tester,
 				goto cleanup;
 		} else if (str_has_pfx(s, TEST_TAG_PROG_FLAGS_PFX)) {
 			val = s + sizeof(TEST_TAG_PROG_FLAGS_PFX) - 1;
+
+			clear = val[0] == '!';
+			if (clear)
+				val++;
+
 			if (strcmp(val, "BPF_F_STRICT_ALIGNMENT") == 0) {
-				spec->prog_flags |= BPF_F_STRICT_ALIGNMENT;
+				update_flags(&spec->prog_flags, BPF_F_STRICT_ALIGNMENT, clear);
 			} else if (strcmp(val, "BPF_F_ANY_ALIGNMENT") == 0) {
-				spec->prog_flags |= BPF_F_ANY_ALIGNMENT;
+				update_flags(&spec->prog_flags, BPF_F_ANY_ALIGNMENT, clear);
 			} else if (strcmp(val, "BPF_F_TEST_RND_HI32") == 0) {
-				spec->prog_flags |= BPF_F_TEST_RND_HI32;
+				update_flags(&spec->prog_flags, BPF_F_TEST_RND_HI32, clear);
 			} else if (strcmp(val, "BPF_F_TEST_STATE_FREQ") == 0) {
-				spec->prog_flags |= BPF_F_TEST_STATE_FREQ;
+				update_flags(&spec->prog_flags, BPF_F_TEST_STATE_FREQ, clear);
 			} else if (strcmp(val, "BPF_F_SLEEPABLE") == 0) {
-				spec->prog_flags |= BPF_F_SLEEPABLE;
+				update_flags(&spec->prog_flags, BPF_F_SLEEPABLE, clear);
 			} else if (strcmp(val, "BPF_F_XDP_HAS_FRAGS") == 0) {
-				spec->prog_flags |= BPF_F_XDP_HAS_FRAGS;
+				update_flags(&spec->prog_flags, BPF_F_XDP_HAS_FRAGS, clear);
+			} else if (strcmp(val, "BPF_F_TEST_REG_INVARIANTS") == 0) {
+				update_flags(&spec->prog_flags, BPF_F_TEST_REG_INVARIANTS, clear);
 			} else /* assume numeric value */ {
-				err = parse_int(val, &tmp, "test prog flags");
+				err = parse_int(val, &flags, "test prog flags");
 				if (err)
 					goto cleanup;
-				spec->prog_flags |= tmp;
+				update_flags(&spec->prog_flags, flags, clear);
 			}
+		} else if (str_has_pfx(s, TEST_BTF_PATH)) {
+			spec->btf_custom_path = s + sizeof(TEST_BTF_PATH) - 1;
 		}
 	}
 
@@ -561,6 +582,9 @@ void run_subtest(struct test_loader *tester,
 		}
 	}
 
+	/* Implicitly reset to NULL if next test case doesn't specify */
+	open_opts->btf_custom_path = spec->btf_custom_path;
+
 	tobj = bpf_object__open_mem(obj_bytes, obj_byte_cnt, open_opts);
 	if (!ASSERT_OK_PTR(tobj, "obj_open_mem")) /* shouldn't happen */
 		goto subtest_cleanup;
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 7fc00e423e4d..767e0693df10 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -1396,13 +1396,18 @@ static void test_map_stress(void)
 #define MAX_DELAY_US 50000
 #define MIN_DELAY_RANGE_US 5000
 
-static int map_update_retriable(int map_fd, const void *key, const void *value,
-				int flags, int attempts)
+static bool retry_for_again_or_busy(int err)
+{
+	return (err == EAGAIN || err == EBUSY);
+}
+
+int map_update_retriable(int map_fd, const void *key, const void *value, int flags, int attempts,
+			 retry_for_error_fn need_retry)
 {
 	int delay = rand() % MIN_DELAY_RANGE_US;
 
 	while (bpf_map_update_elem(map_fd, key, value, flags)) {
-		if (!attempts || (errno != EAGAIN && errno != EBUSY))
+		if (!attempts || !need_retry(errno))
 			return -errno;
 
 		if (delay <= MAX_DELAY_US / 2)
@@ -1445,11 +1450,13 @@ static void test_update_delete(unsigned int fn, void *data)
 		key = value = i;
 
 		if (do_update) {
-			err = map_update_retriable(fd, &key, &value, BPF_NOEXIST, MAP_RETRIES);
+			err = map_update_retriable(fd, &key, &value, BPF_NOEXIST, MAP_RETRIES,
+						   retry_for_again_or_busy);
 			if (err)
 				printf("error %d %d\n", err, errno);
 			assert(err == 0);
-			err = map_update_retriable(fd, &key, &value, BPF_EXIST, MAP_RETRIES);
+			err = map_update_retriable(fd, &key, &value, BPF_EXIST, MAP_RETRIES,
+						   retry_for_again_or_busy);
 			if (err)
 				printf("error %d %d\n", err, errno);
 			assert(err == 0);
diff --git a/tools/testing/selftests/bpf/test_maps.h b/tools/testing/selftests/bpf/test_maps.h
index f6fbca761732..e4ac704a536c 100644
--- a/tools/testing/selftests/bpf/test_maps.h
+++ b/tools/testing/selftests/bpf/test_maps.h
@@ -4,6 +4,7 @@
 
 #include <stdio.h>
 #include <stdlib.h>
+#include <stdbool.h>
 
 #define CHECK(condition, tag, format...) ({				\
 	int __ret = !!(condition);					\
@@ -16,4 +17,8 @@
 
 extern int skips;
 
+typedef bool (*retry_for_error_fn)(int err);
+int map_update_retriable(int map_fd, const void *key, const void *value, int flags, int attempts,
+			 retry_for_error_fn need_retry);
+
 #endif
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index 40cba8d368d9..6157f884d091 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -169,12 +169,14 @@ def bpftool(args, JSON=True, ns="", fail=True, include_stderr=False):
     return tool("bpftool", args, {"json":"-p"}, JSON=JSON, ns=ns,
                 fail=fail, include_stderr=include_stderr)
 
-def bpftool_prog_list(expected=None, ns=""):
+def bpftool_prog_list(expected=None, ns="", exclude_orphaned=True):
     _, progs = bpftool("prog show", JSON=True, ns=ns, fail=True)
     # Remove the base progs
     for p in base_progs:
         if p in progs:
             progs.remove(p)
+    if exclude_orphaned:
+        progs = [ p for p in progs if not p['orphaned'] ]
     if expected is not None:
         if len(progs) != expected:
             fail(True, "%d BPF programs loaded, expected %d" %
@@ -612,11 +614,9 @@ def pin_map(file_name, idx=0, expected=1):
 
 def check_dev_info_removed(prog_file=None, map_file=None):
     bpftool_prog_list(expected=0)
+    bpftool_prog_list(expected=1, exclude_orphaned=False)
     ret, err = bpftool("prog show pin %s" % (prog_file), fail=False)
-    fail(ret == 0, "Showing prog with removed device did not fail")
-    fail(err["error"].find("No such device") == -1,
-         "Showing prog with removed device expected ENODEV, error is %s" %
-         (err["error"]))
+    fail(ret != 0, "failed to show prog with removed device")
 
     bpftool_map_list(expected=0)
     ret, err = bpftool("map show pin %s" % (map_file), fail=False)
@@ -1395,10 +1395,7 @@ try:
 
     start_test("Test multi-dev ASIC cross-dev destruction - orphaned...")
     ret, out = bpftool("prog show %s" % (progB), fail=False)
-    fail(ret == 0, "got information about orphaned program")
-    fail("error" not in out, "no error reported for get info on orphaned")
-    fail(out["error"] != "can't get prog info: No such device",
-         "wrong error for get info on orphaned")
+    fail(ret != 0, "couldn't get information about orphaned program")
 
     print("%s: OK" % (os.path.basename(__file__)))
 
diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
index 2c89674fc62c..b0068a9d2cfe 100644
--- a/tools/testing/selftests/bpf/test_sock_addr.c
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -679,7 +679,7 @@ static int load_path(const struct sock_addr_test *test, const char *path)
 
 	bpf_program__set_type(prog, BPF_PROG_TYPE_CGROUP_SOCK_ADDR);
 	bpf_program__set_expected_attach_type(prog, test->expected_attach_type);
-	bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32);
+	bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS);
 
 	err = bpf_object__load(obj);
 	if (err) {
diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh
index 2dec7dbf29a2..d9661b9988ba 100755
--- a/tools/testing/selftests/bpf/test_tunnel.sh
+++ b/tools/testing/selftests/bpf/test_tunnel.sh
@@ -517,90 +517,6 @@ test_ip6ip6()
         echo -e ${GREEN}"PASS: ip6$TYPE"${NC}
 }
 
-setup_xfrm_tunnel()
-{
-	auth=0x$(printf '1%.0s' {1..40})
-	enc=0x$(printf '2%.0s' {1..32})
-	spi_in_to_out=0x1
-	spi_out_to_in=0x2
-	# at_ns0 namespace
-	# at_ns0 -> root
-	ip netns exec at_ns0 \
-		ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \
-			spi $spi_in_to_out reqid 1 mode tunnel \
-			auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
-	ip netns exec at_ns0 \
-		ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir out \
-		tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \
-		mode tunnel
-	# root -> at_ns0
-	ip netns exec at_ns0 \
-		ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \
-			spi $spi_out_to_in reqid 2 mode tunnel \
-			auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
-	ip netns exec at_ns0 \
-		ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir in \
-		tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \
-		mode tunnel
-	# address & route
-	ip netns exec at_ns0 \
-		ip addr add dev veth0 10.1.1.100/32
-	ip netns exec at_ns0 \
-		ip route add 10.1.1.200 dev veth0 via 172.16.1.200 \
-			src 10.1.1.100
-
-	# root namespace
-	# at_ns0 -> root
-	ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \
-		spi $spi_in_to_out reqid 1 mode tunnel \
-		auth-trunc 'hmac(sha1)' $auth 96  enc 'cbc(aes)' $enc
-	ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir in \
-		tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \
-		mode tunnel
-	# root -> at_ns0
-	ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \
-		spi $spi_out_to_in reqid 2 mode tunnel \
-		auth-trunc 'hmac(sha1)' $auth 96  enc 'cbc(aes)' $enc
-	ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir out \
-		tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \
-		mode tunnel
-	# address & route
-	ip addr add dev veth1 10.1.1.200/32
-	ip route add 10.1.1.100 dev veth1 via 172.16.1.100 src 10.1.1.200
-}
-
-test_xfrm_tunnel()
-{
-	if [[ -e /sys/kernel/tracing/trace ]]; then
-		TRACE=/sys/kernel/tracing/trace
-	else
-		TRACE=/sys/kernel/debug/tracing/trace
-	fi
-	config_device
-	> ${TRACE}
-	setup_xfrm_tunnel
-	mkdir -p ${BPF_PIN_TUNNEL_DIR}
-	bpftool prog loadall ${BPF_FILE} ${BPF_PIN_TUNNEL_DIR}
-	tc qdisc add dev veth1 clsact
-	tc filter add dev veth1 proto ip ingress bpf da object-pinned \
-		${BPF_PIN_TUNNEL_DIR}/xfrm_get_state
-	ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
-	sleep 1
-	grep "reqid 1" ${TRACE}
-	check_err $?
-	grep "spi 0x1" ${TRACE}
-	check_err $?
-	grep "remote ip 0xac100164" ${TRACE}
-	check_err $?
-	cleanup
-
-	if [ $ret -ne 0 ]; then
-		echo -e ${RED}"FAIL: xfrm tunnel"${NC}
-		return 1
-	fi
-	echo -e ${GREEN}"PASS: xfrm tunnel"${NC}
-}
-
 attach_bpf()
 {
 	DEV=$1
@@ -630,10 +546,6 @@ cleanup()
 	ip link del ip6geneve11 2> /dev/null
 	ip link del erspan11 2> /dev/null
 	ip link del ip6erspan11 2> /dev/null
-	ip xfrm policy delete dir out src 10.1.1.200/32 dst 10.1.1.100/32 2> /dev/null
-	ip xfrm policy delete dir in src 10.1.1.100/32 dst 10.1.1.200/32 2> /dev/null
-	ip xfrm state delete src 172.16.1.100 dst 172.16.1.200 proto esp spi 0x1 2> /dev/null
-	ip xfrm state delete src 172.16.1.200 dst 172.16.1.100 proto esp spi 0x2 2> /dev/null
 }
 
 cleanup_exit()
@@ -716,10 +628,6 @@ bpf_tunnel_test()
 	test_ip6ip6
 	errors=$(( $errors + $? ))
 
-	echo "Testing IPSec tunnel..."
-	test_xfrm_tunnel
-	errors=$(( $errors + $? ))
-
 	return $errors
 }
 
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 98107e0452d3..f36e41435be7 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -1588,7 +1588,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	if (fixup_skips != skips)
 		return;
 
-	pflags = BPF_F_TEST_RND_HI32;
+	pflags = BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS;
 	if (test->flags & F_LOAD_WITH_STRICT_ALIGNMENT)
 		pflags |= BPF_F_STRICT_ALIGNMENT;
 	if (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS)
diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c
index 8d994884c7b4..d2458c1b1671 100644
--- a/tools/testing/selftests/bpf/testing_helpers.c
+++ b/tools/testing/selftests/bpf/testing_helpers.c
@@ -276,7 +276,7 @@ int bpf_prog_test_load(const char *file, enum bpf_prog_type type,
 	if (type != BPF_PROG_TYPE_UNSPEC && bpf_program__type(prog) != type)
 		bpf_program__set_type(prog, type);
 
-	flags = bpf_program__flags(prog) | BPF_F_TEST_RND_HI32;
+	flags = bpf_program__flags(prog) | BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS;
 	bpf_program__set_flags(prog, flags);
 
 	err = bpf_object__load(obj);
@@ -299,7 +299,7 @@ int bpf_test_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 {
 	LIBBPF_OPTS(bpf_prog_load_opts, opts,
 		.kern_version = kern_version,
-		.prog_flags = BPF_F_TEST_RND_HI32,
+		.prog_flags = BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS,
 		.log_level = extra_prog_load_log_flags,
 		.log_buf = log_buf,
 		.log_size = log_buf_sz,
diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h
index 5b7a55136741..35284faff4f2 100644
--- a/tools/testing/selftests/bpf/testing_helpers.h
+++ b/tools/testing/selftests/bpf/testing_helpers.h
@@ -9,6 +9,9 @@
 #include <bpf/libbpf.h>
 #include <time.h>
 
+#define __TO_STR(x) #x
+#define TO_STR(x) __TO_STR(x)
+
 int parse_num_list(const char *s, bool **set, int *set_len);
 __u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info);
 int bpf_prog_test_load(const char *file, enum bpf_prog_type type,
diff --git a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c
index 319337bdcfc8..9a7b1106fda8 100644
--- a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c
+++ b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c
@@ -84,17 +84,6 @@
 	.errstr = "!read_ok",
 },
 {
-	"Can't use cmpxchg on uninit memory",
-	.insns = {
-		BPF_MOV64_IMM(BPF_REG_0, 3),
-		BPF_MOV64_IMM(BPF_REG_2, 4),
-		BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, BPF_REG_10, BPF_REG_2, -8),
-		BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid read from stack",
-},
-{
 	"BPF_W cmpxchg should zero top 32 bits",
 	.insns = {
 		/* r0 = U64_MAX; */
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index 1bdf2b43e49e..ab25a81fd3a1 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -442,7 +442,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-	.errstr = "back-edge from insn 0 to 0",
+	.errstr = "the call stack of 9 frames is too deep",
 	.result = REJECT,
 },
 {
@@ -799,7 +799,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-	.errstr = "back-edge",
+	.errstr = "the call stack of 9 frames is too deep",
 	.result = REJECT,
 },
 {
@@ -811,7 +811,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-	.errstr = "back-edge",
+	.errstr = "the call stack of 9 frames is too deep",
 	.result = REJECT,
 },
 {
@@ -1505,7 +1505,9 @@
 	.prog_type = BPF_PROG_TYPE_XDP,
 	.fixup_map_hash_8b = { 23 },
 	.result = REJECT,
-	.errstr = "invalid read from stack R7 off=-16 size=8",
+	.errstr = "R0 invalid mem access 'scalar'",
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "invalid read from stack R7 off=-16 size=8",
 },
 {
 	"calls: two calls that receive map_value via arg=ptr_stack_of_caller. test1",
diff --git a/tools/testing/selftests/bpf/verifier/ld_imm64.c b/tools/testing/selftests/bpf/verifier/ld_imm64.c
index f9297900cea6..78f19c255f20 100644
--- a/tools/testing/selftests/bpf/verifier/ld_imm64.c
+++ b/tools/testing/selftests/bpf/verifier/ld_imm64.c
@@ -9,8 +9,8 @@
 	BPF_MOV64_IMM(BPF_REG_0, 2),
 	BPF_EXIT_INSN(),
 	},
-	.errstr = "invalid BPF_LD_IMM insn",
-	.errstr_unpriv = "R1 pointer comparison",
+	.errstr = "jump into the middle of ldimm64 insn 1",
+	.errstr_unpriv = "jump into the middle of ldimm64 insn 1",
 	.result = REJECT,
 },
 {
@@ -23,8 +23,8 @@
 	BPF_LD_IMM64(BPF_REG_0, 1),
 	BPF_EXIT_INSN(),
 	},
-	.errstr = "invalid BPF_LD_IMM insn",
-	.errstr_unpriv = "R1 pointer comparison",
+	.errstr = "jump into the middle of ldimm64 insn 1",
+	.errstr_unpriv = "jump into the middle of ldimm64 insn 1",
 	.result = REJECT,
 },
 {
diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c
index 0d84dd1f38b6..8a2ff81d8350 100644
--- a/tools/testing/selftests/bpf/verifier/precise.c
+++ b/tools/testing/selftests/bpf/verifier/precise.c
@@ -140,10 +140,11 @@
 	.result = REJECT,
 },
 {
-	"precise: ST insn causing spi > allocated_stack",
+	"precise: ST zero to stack insn is supported",
 	.insns = {
 	BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_3, 123, 0),
+	/* not a register spill, so we stop precision propagation for R4 here */
 	BPF_ST_MEM(BPF_DW, BPF_REG_3, -8, 0),
 	BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
 	BPF_MOV64_IMM(BPF_REG_0, -1),
@@ -157,11 +158,11 @@
 	mark_precise: frame0: last_idx 4 first_idx 2\
 	mark_precise: frame0: regs=r4 stack= before 4\
 	mark_precise: frame0: regs=r4 stack= before 3\
-	mark_precise: frame0: regs= stack=-8 before 2\
-	mark_precise: frame0: falling back to forcing all scalars precise\
-	force_precise: frame0: forcing r0 to be precise\
 	mark_precise: frame0: last_idx 5 first_idx 5\
-	mark_precise: frame0: parent state regs= stack=:",
+	mark_precise: frame0: parent state regs=r0 stack=:\
+	mark_precise: frame0: last_idx 4 first_idx 2\
+	mark_precise: frame0: regs=r0 stack= before 4\
+	5: R0=-1 R4=0",
 	.result = VERBOSE_ACCEPT,
 	.retval = -1,
 },
@@ -169,6 +170,8 @@
 	"precise: STX insn causing spi > allocated_stack",
 	.insns = {
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
+	/* make later reg spill more interesting by having somewhat known scalar */
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xff),
 	BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_3, 123, 0),
 	BPF_STX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, -8),
@@ -179,18 +182,21 @@
 	},
 	.prog_type = BPF_PROG_TYPE_XDP,
 	.flags = BPF_F_TEST_STATE_FREQ,
-	.errstr = "mark_precise: frame0: last_idx 6 first_idx 6\
+	.errstr = "mark_precise: frame0: last_idx 7 first_idx 7\
 	mark_precise: frame0: parent state regs=r4 stack=:\
-	mark_precise: frame0: last_idx 5 first_idx 3\
-	mark_precise: frame0: regs=r4 stack= before 5\
-	mark_precise: frame0: regs=r4 stack= before 4\
-	mark_precise: frame0: regs= stack=-8 before 3\
-	mark_precise: frame0: falling back to forcing all scalars precise\
-	force_precise: frame0: forcing r0 to be precise\
-	force_precise: frame0: forcing r0 to be precise\
-	force_precise: frame0: forcing r0 to be precise\
-	force_precise: frame0: forcing r0 to be precise\
-	mark_precise: frame0: last_idx 6 first_idx 6\
+	mark_precise: frame0: last_idx 6 first_idx 4\
+	mark_precise: frame0: regs=r4 stack= before 6: (b7) r0 = -1\
+	mark_precise: frame0: regs=r4 stack= before 5: (79) r4 = *(u64 *)(r10 -8)\
+	mark_precise: frame0: regs= stack=-8 before 4: (7b) *(u64 *)(r3 -8) = r0\
+	mark_precise: frame0: parent state regs=r0 stack=:\
+	mark_precise: frame0: last_idx 3 first_idx 3\
+	mark_precise: frame0: regs=r0 stack= before 3: (55) if r3 != 0x7b goto pc+0\
+	mark_precise: frame0: regs=r0 stack= before 2: (bf) r3 = r10\
+	mark_precise: frame0: regs=r0 stack= before 1: (57) r0 &= 255\
+	mark_precise: frame0: parent state regs=r0 stack=:\
+	mark_precise: frame0: last_idx 0 first_idx 0\
+	mark_precise: frame0: regs=r0 stack= before 0: (85) call bpf_get_prandom_u32#7\
+	mark_precise: frame0: last_idx 7 first_idx 7\
 	mark_precise: frame0: parent state regs= stack=:",
 	.result = VERBOSE_ACCEPT,
 	.retval = -1,
diff --git a/tools/testing/selftests/bpf/verify_sig_setup.sh b/tools/testing/selftests/bpf/verify_sig_setup.sh
index ba08922b4a27..f2cac42298ba 100755
--- a/tools/testing/selftests/bpf/verify_sig_setup.sh
+++ b/tools/testing/selftests/bpf/verify_sig_setup.sh
@@ -60,6 +60,27 @@ cleanup() {
 	rm -rf ${tmp_dir}
 }
 
+fsverity_create_sign_file() {
+	local tmp_dir="$1"
+
+	data_file=${tmp_dir}/data-file
+	sig_file=${tmp_dir}/sig-file
+	dd if=/dev/urandom of=$data_file bs=1 count=12345 2> /dev/null
+	fsverity sign --key ${tmp_dir}/signing_key.pem $data_file $sig_file
+
+	# We do not want to enable fsverity on $data_file yet. Try whether
+	# the file system support fsverity on a different file.
+	touch ${tmp_dir}/tmp-file
+	fsverity enable ${tmp_dir}/tmp-file
+}
+
+fsverity_enable_file() {
+	local tmp_dir="$1"
+
+	data_file=${tmp_dir}/data-file
+	fsverity enable $data_file
+}
+
 catch()
 {
 	local exit_code="$1"
@@ -86,6 +107,10 @@ main()
 		setup "${tmp_dir}"
 	elif [[ "${action}" == "cleanup" ]]; then
 		cleanup "${tmp_dir}"
+	elif [[ "${action}" == "fsverity-create-sign" ]]; then
+		fsverity_create_sign_file "${tmp_dir}"
+	elif [[ "${action}" == "fsverity-enable" ]]; then
+		fsverity_enable_file "${tmp_dir}"
 	else
 		echo "Unknown action: ${action}"
 		exit 1
diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c
index 655095810d4a..244d4996e06e 100644
--- a/tools/testing/selftests/bpf/veristat.c
+++ b/tools/testing/selftests/bpf/veristat.c
@@ -18,6 +18,7 @@
 #include <libelf.h>
 #include <gelf.h>
 #include <float.h>
+#include <math.h>
 
 #ifndef ARRAY_SIZE
 #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
@@ -99,6 +100,7 @@ struct stat_specs {
 	enum stat_id ids[ALL_STATS_CNT];
 	enum stat_variant variants[ALL_STATS_CNT];
 	bool asc[ALL_STATS_CNT];
+	bool abs[ALL_STATS_CNT];
 	int lens[ALL_STATS_CNT * 3]; /* 3x for comparison mode */
 };
 
@@ -133,6 +135,7 @@ struct filter {
 	int stat_id;
 	enum stat_variant stat_var;
 	long value;
+	bool abs;
 };
 
 static struct env {
@@ -142,10 +145,12 @@ static struct env {
 	bool debug;
 	bool quiet;
 	bool force_checkpoints;
+	bool force_reg_invariants;
 	enum resfmt out_fmt;
 	bool show_version;
 	bool comparison_mode;
 	bool replay_mode;
+	int top_n;
 
 	int log_level;
 	int log_size;
@@ -210,8 +215,7 @@ static const struct argp_option opts[] = {
 	{ "log-level", 'l', "LEVEL", 0, "Verifier log level (default 0 for normal mode, 1 for verbose mode)" },
 	{ "log-fixed", OPT_LOG_FIXED, NULL, 0, "Disable verifier log rotation" },
 	{ "log-size", OPT_LOG_SIZE, "BYTES", 0, "Customize verifier log size (default to 16MB)" },
-	{ "test-states", 't', NULL, 0,
-	  "Force frequent BPF verifier state checkpointing (set BPF_F_TEST_STATE_FREQ program flag)" },
+	{ "top-n", 'n', "N", 0, "Emit only up to first N results." },
 	{ "quiet", 'q', NULL, 0, "Quiet mode" },
 	{ "emit", 'e', "SPEC", 0, "Specify stats to be emitted" },
 	{ "sort", 's', "SPEC", 0, "Specify sort order" },
@@ -219,6 +223,10 @@ static const struct argp_option opts[] = {
 	{ "compare", 'C', NULL, 0, "Comparison mode" },
 	{ "replay", 'R', NULL, 0, "Replay mode" },
 	{ "filter", 'f', "FILTER", 0, "Filter expressions (or @filename for file with expressions)." },
+	{ "test-states", 't', NULL, 0,
+	  "Force frequent BPF verifier state checkpointing (set BPF_F_TEST_STATE_FREQ program flag)" },
+	{ "test-reg-invariants", 'r', NULL, 0,
+	  "Force BPF verifier failure on register invariant violation (BPF_F_TEST_REG_INVARIANTS program flag)" },
 	{},
 };
 
@@ -290,6 +298,16 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 	case 't':
 		env.force_checkpoints = true;
 		break;
+	case 'r':
+		env.force_reg_invariants = true;
+		break;
+	case 'n':
+		errno = 0;
+		env.top_n = strtol(arg, NULL, 10);
+		if (errno) {
+			fprintf(stderr, "invalid top N specifier: %s\n", arg);
+			argp_usage(state);
+		}
 	case 'C':
 		env.comparison_mode = true;
 		break;
@@ -455,7 +473,8 @@ static struct {
 	{ OP_EQ, "=" },
 };
 
-static bool parse_stat_id_var(const char *name, size_t len, int *id, enum stat_variant *var);
+static bool parse_stat_id_var(const char *name, size_t len, int *id,
+			      enum stat_variant *var, bool *is_abs);
 
 static int append_filter(struct filter **filters, int *cnt, const char *str)
 {
@@ -488,13 +507,14 @@ static int append_filter(struct filter **filters, int *cnt, const char *str)
 		long val;
 		const char *end = str;
 		const char *op_str;
+		bool is_abs;
 
 		op_str = operators[i].op_str;
 		p = strstr(str, op_str);
 		if (!p)
 			continue;
 
-		if (!parse_stat_id_var(str, p - str, &id, &var)) {
+		if (!parse_stat_id_var(str, p - str, &id, &var, &is_abs)) {
 			fprintf(stderr, "Unrecognized stat name in '%s'!\n", str);
 			return -EINVAL;
 		}
@@ -533,6 +553,7 @@ static int append_filter(struct filter **filters, int *cnt, const char *str)
 		f->stat_id = id;
 		f->stat_var = var;
 		f->op = operators[i].op_kind;
+		f->abs = true;
 		f->value = val;
 
 		*cnt += 1;
@@ -657,7 +678,8 @@ static struct stat_def {
 	[MARK_READ_MAX_LEN] = { "Max mark read length", {"max_mark_read_len", "mark_read"}, },
 };
 
-static bool parse_stat_id_var(const char *name, size_t len, int *id, enum stat_variant *var)
+static bool parse_stat_id_var(const char *name, size_t len, int *id,
+			      enum stat_variant *var, bool *is_abs)
 {
 	static const char *var_sfxs[] = {
 		[VARIANT_A] = "_a",
@@ -667,6 +689,14 @@ static bool parse_stat_id_var(const char *name, size_t len, int *id, enum stat_v
 	};
 	int i, j, k;
 
+	/* |<stat>| means we take absolute value of given stat */
+	*is_abs = false;
+	if (len > 2 && name[0] == '|' && name[len - 1] == '|') {
+		*is_abs = true;
+		name += 1;
+		len -= 2;
+	}
+
 	for (i = 0; i < ARRAY_SIZE(stat_defs); i++) {
 		struct stat_def *def = &stat_defs[i];
 		size_t alias_len, sfx_len;
@@ -722,7 +752,7 @@ static bool is_desc_sym(char c)
 static int parse_stat(const char *stat_name, struct stat_specs *specs)
 {
 	int id;
-	bool has_order = false, is_asc = false;
+	bool has_order = false, is_asc = false, is_abs = false;
 	size_t len = strlen(stat_name);
 	enum stat_variant var;
 
@@ -737,7 +767,7 @@ static int parse_stat(const char *stat_name, struct stat_specs *specs)
 		len -= 1;
 	}
 
-	if (!parse_stat_id_var(stat_name, len, &id, &var)) {
+	if (!parse_stat_id_var(stat_name, len, &id, &var, &is_abs)) {
 		fprintf(stderr, "Unrecognized stat name '%s'\n", stat_name);
 		return -ESRCH;
 	}
@@ -745,6 +775,7 @@ static int parse_stat(const char *stat_name, struct stat_specs *specs)
 	specs->ids[specs->spec_cnt] = id;
 	specs->variants[specs->spec_cnt] = var;
 	specs->asc[specs->spec_cnt] = has_order ? is_asc : stat_defs[id].asc_by_default;
+	specs->abs[specs->spec_cnt] = is_abs;
 	specs->spec_cnt++;
 
 	return 0;
@@ -997,6 +1028,8 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf
 
 	if (env.force_checkpoints)
 		bpf_program__set_flags(prog, bpf_program__flags(prog) | BPF_F_TEST_STATE_FREQ);
+	if (env.force_reg_invariants)
+		bpf_program__set_flags(prog, bpf_program__flags(prog) | BPF_F_TEST_REG_INVARIANTS);
 
 	err = bpf_object__load(obj);
 	env.progs_processed++;
@@ -1103,7 +1136,7 @@ cleanup:
 }
 
 static int cmp_stat(const struct verif_stats *s1, const struct verif_stats *s2,
-		    enum stat_id id, bool asc)
+		    enum stat_id id, bool asc, bool abs)
 {
 	int cmp = 0;
 
@@ -1124,6 +1157,11 @@ static int cmp_stat(const struct verif_stats *s1, const struct verif_stats *s2,
 		long v1 = s1->stats[id];
 		long v2 = s2->stats[id];
 
+		if (abs) {
+			v1 = v1 < 0 ? -v1 : v1;
+			v2 = v2 < 0 ? -v2 : v2;
+		}
+
 		if (v1 != v2)
 			cmp = v1 < v2 ? -1 : 1;
 		break;
@@ -1142,7 +1180,8 @@ static int cmp_prog_stats(const void *v1, const void *v2)
 	int i, cmp;
 
 	for (i = 0; i < env.sort_spec.spec_cnt; i++) {
-		cmp = cmp_stat(s1, s2, env.sort_spec.ids[i], env.sort_spec.asc[i]);
+		cmp = cmp_stat(s1, s2, env.sort_spec.ids[i],
+			       env.sort_spec.asc[i], env.sort_spec.abs[i]);
 		if (cmp != 0)
 			return cmp;
 	}
@@ -1211,15 +1250,21 @@ static void fetch_join_stat_value(const struct verif_stats_join *s,
 
 static int cmp_join_stat(const struct verif_stats_join *s1,
 			 const struct verif_stats_join *s2,
-			 enum stat_id id, enum stat_variant var, bool asc)
+			 enum stat_id id, enum stat_variant var,
+			 bool asc, bool abs)
 {
 	const char *str1 = NULL, *str2 = NULL;
-	double v1, v2;
+	double v1 = 0.0, v2 = 0.0;
 	int cmp = 0;
 
 	fetch_join_stat_value(s1, id, var, &str1, &v1);
 	fetch_join_stat_value(s2, id, var, &str2, &v2);
 
+	if (abs) {
+		v1 = fabs(v1);
+		v2 = fabs(v2);
+	}
+
 	if (str1)
 		cmp = strcmp(str1, str2);
 	else if (v1 != v2)
@@ -1237,7 +1282,8 @@ static int cmp_join_stats(const void *v1, const void *v2)
 		cmp = cmp_join_stat(s1, s2,
 				    env.sort_spec.ids[i],
 				    env.sort_spec.variants[i],
-				    env.sort_spec.asc[i]);
+				    env.sort_spec.asc[i],
+				    env.sort_spec.abs[i]);
 		if (cmp != 0)
 			return cmp;
 	}
@@ -1720,6 +1766,9 @@ static bool is_join_stat_filter_matched(struct filter *f, const struct verif_sta
 
 	fetch_join_stat_value(stats, f->stat_id, f->stat_var, &str, &value);
 
+	if (f->abs)
+		value = fabs(value);
+
 	switch (f->op) {
 	case OP_EQ: return value > f->value - eps && value < f->value + eps;
 	case OP_NEQ: return value < f->value - eps || value > f->value + eps;
@@ -1766,7 +1815,7 @@ static int handle_comparison_mode(void)
 	struct stat_specs base_specs = {}, comp_specs = {};
 	struct stat_specs tmp_sort_spec;
 	enum resfmt cur_fmt;
-	int err, i, j, last_idx;
+	int err, i, j, last_idx, cnt;
 
 	if (env.filename_cnt != 2) {
 		fprintf(stderr, "Comparison mode expects exactly two input CSV files!\n\n");
@@ -1879,7 +1928,7 @@ static int handle_comparison_mode(void)
 		env.join_stat_cnt += 1;
 	}
 
-	/* now sort joined results accorsing to sort spec */
+	/* now sort joined results according to sort spec */
 	qsort(env.join_stats, env.join_stat_cnt, sizeof(*env.join_stats), cmp_join_stats);
 
 	/* for human-readable table output we need to do extra pass to
@@ -1896,16 +1945,22 @@ one_more_time:
 	output_comp_headers(cur_fmt);
 
 	last_idx = -1;
+	cnt = 0;
 	for (i = 0; i < env.join_stat_cnt; i++) {
 		const struct verif_stats_join *join = &env.join_stats[i];
 
 		if (!should_output_join_stats(join))
 			continue;
 
+		if (env.top_n && cnt >= env.top_n)
+			break;
+
 		if (cur_fmt == RESFMT_TABLE_CALCLEN)
 			last_idx = i;
 
 		output_comp_stats(join, cur_fmt, i == last_idx);
+
+		cnt++;
 	}
 
 	if (cur_fmt == RESFMT_TABLE_CALCLEN) {
@@ -1920,6 +1975,9 @@ static bool is_stat_filter_matched(struct filter *f, const struct verif_stats *s
 {
 	long value = stats->stats[f->stat_id];
 
+	if (f->abs)
+		value = value < 0 ? -value : value;
+
 	switch (f->op) {
 	case OP_EQ: return value == f->value;
 	case OP_NEQ: return value != f->value;
@@ -1964,7 +2022,7 @@ static bool should_output_stats(const struct verif_stats *stats)
 static void output_prog_stats(void)
 {
 	const struct verif_stats *stats;
-	int i, last_stat_idx = 0;
+	int i, last_stat_idx = 0, cnt = 0;
 
 	if (env.out_fmt == RESFMT_TABLE) {
 		/* calculate column widths */
@@ -1984,7 +2042,10 @@ static void output_prog_stats(void)
 		stats = &env.prog_stats[i];
 		if (!should_output_stats(stats))
 			continue;
+		if (env.top_n && cnt >= env.top_n)
+			break;
 		output_stats(stats, env.out_fmt, i == last_stat_idx);
+		cnt++;
 	}
 }
 
diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh
index 685034528018..65d14f3bbe30 100755
--- a/tools/testing/selftests/bpf/vmtest.sh
+++ b/tools/testing/selftests/bpf/vmtest.sh
@@ -36,7 +36,9 @@ DEFAULT_COMMAND="./test_progs"
 MOUNT_DIR="mnt"
 ROOTFS_IMAGE="root.img"
 OUTPUT_DIR="$HOME/.bpf_selftests"
-KCONFIG_REL_PATHS=("tools/testing/selftests/bpf/config" "tools/testing/selftests/bpf/config.${ARCH}")
+KCONFIG_REL_PATHS=("tools/testing/selftests/bpf/config"
+	"tools/testing/selftests/bpf/config.vm"
+	"tools/testing/selftests/bpf/config.${ARCH}")
 INDEX_URL="https://raw.githubusercontent.com/libbpf/ci/master/INDEX"
 NUM_COMPILE_JOBS="$(nproc)"
 LOG_FILE_BASE="$(date +"bpf_selftests.%Y-%m-%d_%H-%M-%S")"
diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c
index c3ba40d0b9de..878d68db0325 100644
--- a/tools/testing/selftests/bpf/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c
@@ -10,7 +10,9 @@
  *   - rx_hash
  *
  * TX:
- * - TBD
+ * - UDP 9091 packets trigger TX reply
+ * - TX HW timestamp is requested and reported back upon completion
+ * - TX checksum is requested
  */
 
 #include <test_progs.h>
@@ -19,20 +21,26 @@
 #include "xsk.h"
 
 #include <error.h>
+#include <linux/kernel.h>
+#include <linux/bits.h>
+#include <linux/bitfield.h>
 #include <linux/errqueue.h>
 #include <linux/if_link.h>
 #include <linux/net_tstamp.h>
 #include <linux/udp.h>
 #include <linux/sockios.h>
+#include <linux/if_xdp.h>
 #include <sys/mman.h>
 #include <net/if.h>
 #include <ctype.h>
 #include <poll.h>
 #include <time.h>
+#include <unistd.h>
+#include <libgen.h>
 
 #include "xdp_metadata.h"
 
-#define UMEM_NUM 16
+#define UMEM_NUM 256
 #define UMEM_FRAME_SIZE XSK_UMEM__DEFAULT_FRAME_SIZE
 #define UMEM_SIZE (UMEM_FRAME_SIZE * UMEM_NUM)
 #define XDP_FLAGS (XDP_FLAGS_DRV_MODE | XDP_FLAGS_REPLACE)
@@ -48,11 +56,14 @@ struct xsk {
 };
 
 struct xdp_hw_metadata *bpf_obj;
-__u16 bind_flags = XDP_COPY;
+__u16 bind_flags = XDP_USE_NEED_WAKEUP | XDP_ZEROCOPY;
 struct xsk *rx_xsk;
 const char *ifname;
 int ifindex;
 int rxq;
+bool skip_tx;
+__u64 last_hw_rx_timestamp;
+__u64 last_xdp_rx_timestamp;
 
 void test__fail(void) { /* for network_helpers.c */ }
 
@@ -68,9 +79,10 @@ static int open_xsk(int ifindex, struct xsk *xsk, __u32 queue_id)
 		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
 		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
 		.frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE,
-		.flags = XDP_UMEM_UNALIGNED_CHUNK_FLAG,
+		.flags = XSK_UMEM__DEFAULT_FLAGS,
+		.tx_metadata_len = sizeof(struct xsk_tx_metadata),
 	};
-	__u32 idx;
+	__u32 idx = 0;
 	u64 addr;
 	int ret;
 	int i;
@@ -110,7 +122,7 @@ static int open_xsk(int ifindex, struct xsk *xsk, __u32 queue_id)
 	for (i = 0; i < UMEM_NUM / 2; i++) {
 		addr = (UMEM_NUM / 2 + i) * UMEM_FRAME_SIZE;
 		printf("%p: rx_desc[%d] -> %lx\n", xsk, i, addr);
-		*xsk_ring_prod__fill_addr(&xsk->fill, i) = addr;
+		*xsk_ring_prod__fill_addr(&xsk->fill, idx + i) = addr;
 	}
 	xsk_ring_prod__submit(&xsk->fill, ret);
 
@@ -131,12 +143,22 @@ static void refill_rx(struct xsk *xsk, __u64 addr)
 	__u32 idx;
 
 	if (xsk_ring_prod__reserve(&xsk->fill, 1, &idx) == 1) {
-		printf("%p: complete idx=%u addr=%llx\n", xsk, idx, addr);
+		printf("%p: complete rx idx=%u addr=%llx\n", xsk, idx, addr);
 		*xsk_ring_prod__fill_addr(&xsk->fill, idx) = addr;
 		xsk_ring_prod__submit(&xsk->fill, 1);
 	}
 }
 
+static int kick_tx(struct xsk *xsk)
+{
+	return sendto(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, 0);
+}
+
+static int kick_rx(struct xsk *xsk)
+{
+	return recvfrom(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, NULL);
+}
+
 #define NANOSEC_PER_SEC 1000000000 /* 10^9 */
 static __u64 gettime(clockid_t clock_id)
 {
@@ -152,37 +174,64 @@ static __u64 gettime(clockid_t clock_id)
 	return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec;
 }
 
+static void print_tstamp_delta(const char *name, const char *refname,
+			       __u64 tstamp, __u64 reference)
+{
+	__s64 delta = (__s64)reference - (__s64)tstamp;
+
+	printf("%s:   %llu (sec:%0.4f) delta to %s sec:%0.4f (%0.3f usec)\n",
+	       name, tstamp, (double)tstamp / NANOSEC_PER_SEC, refname,
+	       (double)delta / NANOSEC_PER_SEC,
+	       (double)delta / 1000);
+}
+
+#define VLAN_PRIO_MASK		GENMASK(15, 13) /* Priority Code Point */
+#define VLAN_DEI_MASK		GENMASK(12, 12) /* Drop Eligible Indicator */
+#define VLAN_VID_MASK		GENMASK(11, 0)	/* VLAN Identifier */
+static void print_vlan_tci(__u16 tag)
+{
+	__u16 vlan_id = FIELD_GET(VLAN_VID_MASK, tag);
+	__u8 pcp = FIELD_GET(VLAN_PRIO_MASK, tag);
+	bool dei = FIELD_GET(VLAN_DEI_MASK, tag);
+
+	printf("PCP=%u, DEI=%d, VID=0x%X\n", pcp, dei, vlan_id);
+}
+
 static void verify_xdp_metadata(void *data, clockid_t clock_id)
 {
 	struct xdp_meta *meta;
 
 	meta = data - sizeof(*meta);
 
-	if (meta->rx_hash_err < 0)
-		printf("No rx_hash err=%d\n", meta->rx_hash_err);
-	else
+	if (meta->hint_valid & XDP_META_FIELD_RSS)
 		printf("rx_hash: 0x%X with RSS type:0x%X\n",
 		       meta->rx_hash, meta->rx_hash_type);
+	else
+		printf("No rx_hash, err=%d\n", meta->rx_hash_err);
+
+	if (meta->hint_valid & XDP_META_FIELD_TS) {
+		__u64 ref_tstamp = gettime(clock_id);
+
+		/* store received timestamps to calculate a delta at tx */
+		last_hw_rx_timestamp = meta->rx_timestamp;
+		last_xdp_rx_timestamp = meta->xdp_timestamp;
 
-	printf("rx_timestamp:  %llu (sec:%0.4f)\n", meta->rx_timestamp,
-	       (double)meta->rx_timestamp / NANOSEC_PER_SEC);
-	if (meta->rx_timestamp) {
-		__u64 usr_clock = gettime(clock_id);
-		__u64 xdp_clock = meta->xdp_timestamp;
-		__s64 delta_X = xdp_clock - meta->rx_timestamp;
-		__s64 delta_X2U = usr_clock - xdp_clock;
-
-		printf("XDP RX-time:   %llu (sec:%0.4f) delta sec:%0.4f (%0.3f usec)\n",
-		       xdp_clock, (double)xdp_clock / NANOSEC_PER_SEC,
-		       (double)delta_X / NANOSEC_PER_SEC,
-		       (double)delta_X / 1000);
-
-		printf("AF_XDP time:   %llu (sec:%0.4f) delta sec:%0.4f (%0.3f usec)\n",
-		       usr_clock, (double)usr_clock / NANOSEC_PER_SEC,
-		       (double)delta_X2U / NANOSEC_PER_SEC,
-		       (double)delta_X2U / 1000);
+		print_tstamp_delta("HW RX-time", "User RX-time",
+				   meta->rx_timestamp, ref_tstamp);
+		print_tstamp_delta("XDP RX-time", "User RX-time",
+				   meta->xdp_timestamp, ref_tstamp);
+	} else {
+		printf("No rx_timestamp, err=%d\n", meta->rx_timestamp_err);
 	}
 
+	if (meta->hint_valid & XDP_META_FIELD_VLAN_TAG) {
+		printf("rx_vlan_proto: 0x%X\n", ntohs(meta->rx_vlan_proto));
+		printf("rx_vlan_tci: ");
+		print_vlan_tci(meta->rx_vlan_tci);
+	} else {
+		printf("No rx_vlan_tci or rx_vlan_proto, err=%d\n",
+		       meta->rx_vlan_tag_err);
+	}
 }
 
 static void verify_skb_metadata(int fd)
@@ -230,6 +279,129 @@ static void verify_skb_metadata(int fd)
 	printf("skb hwtstamp is not found!\n");
 }
 
+static bool complete_tx(struct xsk *xsk, clockid_t clock_id)
+{
+	struct xsk_tx_metadata *meta;
+	__u64 addr;
+	void *data;
+	__u32 idx;
+
+	if (!xsk_ring_cons__peek(&xsk->comp, 1, &idx))
+		return false;
+
+	addr = *xsk_ring_cons__comp_addr(&xsk->comp, idx);
+	data = xsk_umem__get_data(xsk->umem_area, addr);
+	meta = data - sizeof(struct xsk_tx_metadata);
+
+	printf("%p: complete tx idx=%u addr=%llx\n", xsk, idx, addr);
+
+	if (meta->completion.tx_timestamp) {
+		__u64 ref_tstamp = gettime(clock_id);
+
+		print_tstamp_delta("HW TX-complete-time", "User TX-complete-time",
+				   meta->completion.tx_timestamp, ref_tstamp);
+		print_tstamp_delta("XDP RX-time", "User TX-complete-time",
+				   last_xdp_rx_timestamp, ref_tstamp);
+		print_tstamp_delta("HW RX-time", "HW TX-complete-time",
+				   last_hw_rx_timestamp, meta->completion.tx_timestamp);
+	} else {
+		printf("No tx_timestamp\n");
+	}
+
+	xsk_ring_cons__release(&xsk->comp, 1);
+
+	return true;
+}
+
+#define swap(a, b, len) do { \
+	for (int i = 0; i < len; i++) { \
+		__u8 tmp = ((__u8 *)a)[i]; \
+		((__u8 *)a)[i] = ((__u8 *)b)[i]; \
+		((__u8 *)b)[i] = tmp; \
+	} \
+} while (0)
+
+static void ping_pong(struct xsk *xsk, void *rx_packet, clockid_t clock_id)
+{
+	struct xsk_tx_metadata *meta;
+	struct ipv6hdr *ip6h = NULL;
+	struct iphdr *iph = NULL;
+	struct xdp_desc *tx_desc;
+	struct udphdr *udph;
+	struct ethhdr *eth;
+	__sum16 want_csum;
+	void *data;
+	__u32 idx;
+	int ret;
+	int len;
+
+	ret = xsk_ring_prod__reserve(&xsk->tx, 1, &idx);
+	if (ret != 1) {
+		printf("%p: failed to reserve tx slot\n", xsk);
+		return;
+	}
+
+	tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx);
+	tx_desc->addr = idx % (UMEM_NUM / 2) * UMEM_FRAME_SIZE + sizeof(struct xsk_tx_metadata);
+	data = xsk_umem__get_data(xsk->umem_area, tx_desc->addr);
+
+	meta = data - sizeof(struct xsk_tx_metadata);
+	memset(meta, 0, sizeof(*meta));
+	meta->flags = XDP_TXMD_FLAGS_TIMESTAMP;
+
+	eth = rx_packet;
+
+	if (eth->h_proto == htons(ETH_P_IP)) {
+		iph = (void *)(eth + 1);
+		udph = (void *)(iph + 1);
+	} else if (eth->h_proto == htons(ETH_P_IPV6)) {
+		ip6h = (void *)(eth + 1);
+		udph = (void *)(ip6h + 1);
+	} else {
+		printf("%p: failed to detect IP version for ping pong %04x\n", xsk, eth->h_proto);
+		xsk_ring_prod__cancel(&xsk->tx, 1);
+		return;
+	}
+
+	len = ETH_HLEN;
+	if (ip6h)
+		len += sizeof(*ip6h) + ntohs(ip6h->payload_len);
+	if (iph)
+		len += ntohs(iph->tot_len);
+
+	swap(eth->h_dest, eth->h_source, ETH_ALEN);
+	if (iph)
+		swap(&iph->saddr, &iph->daddr, 4);
+	else
+		swap(&ip6h->saddr, &ip6h->daddr, 16);
+	swap(&udph->source, &udph->dest, 2);
+
+	want_csum = udph->check;
+	if (ip6h)
+		udph->check = ~csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
+					       ntohs(udph->len), IPPROTO_UDP, 0);
+	else
+		udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
+						 ntohs(udph->len), IPPROTO_UDP, 0);
+
+	meta->flags |= XDP_TXMD_FLAGS_CHECKSUM;
+	if (iph)
+		meta->request.csum_start = sizeof(*eth) + sizeof(*iph);
+	else
+		meta->request.csum_start = sizeof(*eth) + sizeof(*ip6h);
+	meta->request.csum_offset = offsetof(struct udphdr, check);
+
+	printf("%p: ping-pong with csum=%04x (want %04x) csum_start=%d csum_offset=%d\n",
+	       xsk, ntohs(udph->check), ntohs(want_csum),
+	       meta->request.csum_start, meta->request.csum_offset);
+
+	memcpy(data, rx_packet, len); /* don't share umem chunk for simplicity */
+	tx_desc->options |= XDP_TX_METADATA;
+	tx_desc->len = len;
+
+	xsk_ring_prod__submit(&xsk->tx, 1);
+}
+
 static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t clock_id)
 {
 	const struct xdp_desc *rx_desc;
@@ -252,6 +424,13 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t
 
 	while (true) {
 		errno = 0;
+
+		for (i = 0; i < rxq; i++) {
+			ret = kick_rx(&rx_xsk[i]);
+			if (ret)
+				printf("kick_rx ret=%d\n", ret);
+		}
+
 		ret = poll(fds, rxq + 1, 1000);
 		printf("poll: %d (%d) skip=%llu fail=%llu redir=%llu\n",
 		       ret, errno, bpf_obj->bss->pkts_skip,
@@ -288,6 +467,22 @@ peek:
 				verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr),
 						    clock_id);
 				first_seg = false;
+
+				if (!skip_tx) {
+					/* mirror first chunk back */
+					ping_pong(xsk, xsk_umem__get_data(xsk->umem_area, addr),
+						  clock_id);
+
+					ret = kick_tx(xsk);
+					if (ret)
+						printf("kick_tx ret=%d\n", ret);
+
+					for (int j = 0; j < 500; j++) {
+						if (complete_tx(xsk, clock_id))
+							break;
+						usleep(10*1000);
+					}
+				}
 			}
 
 			xsk_ring_cons__release(&xsk->rx, 1);
@@ -420,8 +615,10 @@ static void print_usage(void)
 {
 	const char *usage =
 		"Usage: xdp_hw_metadata [OPTIONS] [IFNAME]\n"
-		"  -m    Enable multi-buffer XDP for larger MTU\n"
+		"  -c    Run in copy mode (zerocopy is default)\n"
 		"  -h    Display this help and exit\n\n"
+		"  -m    Enable multi-buffer XDP for larger MTU\n"
+		"  -r    Don't generate AF_XDP reply (rx metadata only)\n"
 		"Generate test packets on the other machine with:\n"
 		"  echo -n xdp | nc -u -q1 <dst_ip> 9091\n";
 
@@ -432,14 +629,22 @@ static void read_args(int argc, char *argv[])
 {
 	int opt;
 
-	while ((opt = getopt(argc, argv, "mh")) != -1) {
+	while ((opt = getopt(argc, argv, "chmr")) != -1) {
 		switch (opt) {
-		case 'm':
-			bind_flags |= XDP_USE_SG;
+		case 'c':
+			bind_flags &= ~XDP_USE_NEED_WAKEUP;
+			bind_flags &= ~XDP_ZEROCOPY;
+			bind_flags |= XDP_COPY;
 			break;
 		case 'h':
 			print_usage();
 			exit(0);
+		case 'm':
+			bind_flags |= XDP_USE_SG;
+			break;
+		case 'r':
+			skip_tx = true;
+			break;
 		case '?':
 			if (isprint(optopt))
 				fprintf(stderr, "Unknown option: -%c\n", optopt);
diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h
index 938a729bd307..87318ad1117a 100644
--- a/tools/testing/selftests/bpf/xdp_metadata.h
+++ b/tools/testing/selftests/bpf/xdp_metadata.h
@@ -9,12 +9,44 @@
 #define ETH_P_IPV6 0x86DD
 #endif
 
+#ifndef ETH_P_8021Q
+#define ETH_P_8021Q 0x8100
+#endif
+
+#ifndef ETH_P_8021AD
+#define ETH_P_8021AD 0x88A8
+#endif
+
+#ifndef BIT
+#define BIT(nr)			(1 << (nr))
+#endif
+
+/* Non-existent checksum status */
+#define XDP_CHECKSUM_MAGIC	BIT(2)
+
+enum xdp_meta_field {
+	XDP_META_FIELD_TS	= BIT(0),
+	XDP_META_FIELD_RSS	= BIT(1),
+	XDP_META_FIELD_VLAN_TAG	= BIT(2),
+};
+
 struct xdp_meta {
-	__u64 rx_timestamp;
+	union {
+		__u64 rx_timestamp;
+		__s32 rx_timestamp_err;
+	};
 	__u64 xdp_timestamp;
 	__u32 rx_hash;
 	union {
 		__u32 rx_hash_type;
 		__s32 rx_hash_err;
 	};
+	union {
+		struct {
+			__be16 rx_vlan_proto;
+			__u16 rx_vlan_tci;
+		};
+		__s32 rx_vlan_tag_err;
+	};
+	enum xdp_meta_field hint_valid;
 };
diff --git a/tools/testing/selftests/bpf/xsk.c b/tools/testing/selftests/bpf/xsk.c
index e574711eeb84..25d568abf0f2 100644
--- a/tools/testing/selftests/bpf/xsk.c
+++ b/tools/testing/selftests/bpf/xsk.c
@@ -115,6 +115,7 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg,
 		cfg->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
 		cfg->frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM;
 		cfg->flags = XSK_UMEM__DEFAULT_FLAGS;
+		cfg->tx_metadata_len = 0;
 		return;
 	}
 
@@ -123,6 +124,7 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg,
 	cfg->frame_size = usr_cfg->frame_size;
 	cfg->frame_headroom = usr_cfg->frame_headroom;
 	cfg->flags = usr_cfg->flags;
+	cfg->tx_metadata_len = usr_cfg->tx_metadata_len;
 }
 
 static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
@@ -252,6 +254,7 @@ int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area,
 	mr.chunk_size = umem->config.frame_size;
 	mr.headroom = umem->config.frame_headroom;
 	mr.flags = umem->config.flags;
+	mr.tx_metadata_len = umem->config.tx_metadata_len;
 
 	err = setsockopt(umem->fd, SOL_XDP, XDP_UMEM_REG, &mr, sizeof(mr));
 	if (err) {
diff --git a/tools/testing/selftests/bpf/xsk.h b/tools/testing/selftests/bpf/xsk.h
index 771570bc3731..93c2cc413cfc 100644
--- a/tools/testing/selftests/bpf/xsk.h
+++ b/tools/testing/selftests/bpf/xsk.h
@@ -200,6 +200,7 @@ struct xsk_umem_config {
 	__u32 frame_size;
 	__u32 frame_headroom;
 	__u32 flags;
+	__u32 tx_metadata_len;
 };
 
 int xsk_attach_xdp_program(struct bpf_program *prog, int ifindex, u32 xdp_flags);
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 591ca9637b23..b1102ee13faa 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -634,16 +634,24 @@ static u32 pkt_nb_frags(u32 frame_size, struct pkt_stream *pkt_stream, struct pk
 	return nb_frags;
 }
 
+static bool set_pkt_valid(int offset, u32 len)
+{
+	return len <= MAX_ETH_JUMBO_SIZE;
+}
+
 static void pkt_set(struct pkt_stream *pkt_stream, struct pkt *pkt, int offset, u32 len)
 {
 	pkt->offset = offset;
 	pkt->len = len;
-	if (len > MAX_ETH_JUMBO_SIZE) {
-		pkt->valid = false;
-	} else {
-		pkt->valid = true;
-		pkt_stream->nb_valid_entries++;
-	}
+	pkt->valid = set_pkt_valid(offset, len);
+}
+
+static void pkt_stream_pkt_set(struct pkt_stream *pkt_stream, struct pkt *pkt, int offset, u32 len)
+{
+	bool prev_pkt_valid = pkt->valid;
+
+	pkt_set(pkt_stream, pkt, offset, len);
+	pkt_stream->nb_valid_entries += pkt->valid - prev_pkt_valid;
 }
 
 static u32 pkt_get_buffer_len(struct xsk_umem_info *umem, u32 len)
@@ -665,7 +673,7 @@ static struct pkt_stream *__pkt_stream_generate(u32 nb_pkts, u32 pkt_len, u32 nb
 	for (i = 0; i < nb_pkts; i++) {
 		struct pkt *pkt = &pkt_stream->pkts[i];
 
-		pkt_set(pkt_stream, pkt, 0, pkt_len);
+		pkt_stream_pkt_set(pkt_stream, pkt, 0, pkt_len);
 		pkt->pkt_nb = nb_start + i * nb_off;
 	}
 
@@ -700,10 +708,9 @@ static void __pkt_stream_replace_half(struct ifobject *ifobj, u32 pkt_len,
 
 	pkt_stream = pkt_stream_clone(ifobj->xsk->pkt_stream);
 	for (i = 1; i < ifobj->xsk->pkt_stream->nb_pkts; i += 2)
-		pkt_set(pkt_stream, &pkt_stream->pkts[i], offset, pkt_len);
+		pkt_stream_pkt_set(pkt_stream, &pkt_stream->pkts[i], offset, pkt_len);
 
 	ifobj->xsk->pkt_stream = pkt_stream;
-	pkt_stream->nb_valid_entries /= 2;
 }
 
 static void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, int offset)
@@ -908,8 +915,9 @@ static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr)
 	struct xdp_info *meta = data - sizeof(struct xdp_info);
 
 	if (meta->count != pkt->pkt_nb) {
-		ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%d]\n",
-			       __func__, pkt->pkt_nb, meta->count);
+		ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%llu]\n",
+			       __func__, pkt->pkt_nb,
+			       (unsigned long long)meta->count);
 		return false;
 	}
 
@@ -926,11 +934,13 @@ static bool is_frag_valid(struct xsk_umem_info *umem, u64 addr, u32 len, u32 exp
 
 	if (addr >= umem->num_frames * umem->frame_size ||
 	    addr + len > umem->num_frames * umem->frame_size) {
-		ksft_print_msg("Frag invalid addr: %llx len: %u\n", addr, len);
+		ksft_print_msg("Frag invalid addr: %llx len: %u\n",
+			       (unsigned long long)addr, len);
 		return false;
 	}
 	if (!umem->unaligned_mode && addr % umem->frame_size + len > umem->frame_size) {
-		ksft_print_msg("Frag crosses frame boundary addr: %llx len: %u\n", addr, len);
+		ksft_print_msg("Frag crosses frame boundary addr: %llx len: %u\n",
+			       (unsigned long long)addr, len);
 		return false;
 	}
 
@@ -1029,7 +1039,8 @@ static int complete_pkts(struct xsk_socket_info *xsk, int batch_size)
 			u64 addr = *xsk_ring_cons__comp_addr(&xsk->umem->cq, idx + rcvd - 1);
 
 			ksft_print_msg("[%s] Too many packets completed\n", __func__);
-			ksft_print_msg("Last completion address: %llx\n", addr);
+			ksft_print_msg("Last completion address: %llx\n",
+				       (unsigned long long)addr);
 			return TEST_FAILURE;
 		}
 
@@ -1513,8 +1524,9 @@ static int validate_tx_invalid_descs(struct ifobject *ifobject)
 	}
 
 	if (stats.tx_invalid_descs != ifobject->xsk->pkt_stream->nb_pkts / 2) {
-		ksft_print_msg("[%s] tx_invalid_descs incorrect. Got [%u] expected [%u]\n",
-			       __func__, stats.tx_invalid_descs,
+		ksft_print_msg("[%s] tx_invalid_descs incorrect. Got [%llu] expected [%u]\n",
+			       __func__,
+			       (unsigned long long)stats.tx_invalid_descs,
 			       ifobject->xsk->pkt_stream->nb_pkts);
 		return TEST_FAILURE;
 	}
diff --git a/tools/testing/selftests/breakpoints/breakpoint_test.c b/tools/testing/selftests/breakpoints/breakpoint_test.c
index 3266cc9293fe..d46962a24724 100644
--- a/tools/testing/selftests/breakpoints/breakpoint_test.c
+++ b/tools/testing/selftests/breakpoints/breakpoint_test.c
@@ -284,9 +284,9 @@ static void check_success(const char *msg)
 	nr_tests++;
 
 	if (ret)
-		ksft_test_result_pass(msg);
+		ksft_test_result_pass("%s", msg);
 	else
-		ksft_test_result_fail(msg);
+		ksft_test_result_fail("%s", msg);
 }
 
 static void launch_instruction_breakpoints(char *buf, int local, int global)
diff --git a/tools/testing/selftests/breakpoints/step_after_suspend_test.c b/tools/testing/selftests/breakpoints/step_after_suspend_test.c
index 2cf6f10ab7c4..b8703c499d28 100644
--- a/tools/testing/selftests/breakpoints/step_after_suspend_test.c
+++ b/tools/testing/selftests/breakpoints/step_after_suspend_test.c
@@ -89,7 +89,7 @@ int run_test(int cpu)
 
 	wpid = waitpid(pid, &status, __WALL);
 	if (wpid != pid) {
-		ksft_print_msg("waitpid() failed: $s\n", strerror(errno));
+		ksft_print_msg("waitpid() failed: %s\n", strerror(errno));
 		return KSFT_FAIL;
 	}
 	if (WIFEXITED(status)) {
diff --git a/tools/testing/selftests/capabilities/test_execve.c b/tools/testing/selftests/capabilities/test_execve.c
index e3a352b020a7..7cde07a5df78 100644
--- a/tools/testing/selftests/capabilities/test_execve.c
+++ b/tools/testing/selftests/capabilities/test_execve.c
@@ -88,11 +88,7 @@ static bool create_and_enter_ns(uid_t inner_uid)
 	outer_uid = getuid();
 	outer_gid = getgid();
 
-	/*
-	 * TODO: If we're already root, we could skip creating the userns.
-	 */
-
-	if (unshare(CLONE_NEWNS) == 0) {
+	if (outer_uid == 0 && unshare(CLONE_NEWNS) == 0) {
 		ksft_print_msg("[NOTE]\tUsing global UIDs for tests\n");
 		if (prctl(PR_SET_KEEPCAPS, 1, 0, 0, 0) != 0)
 			ksft_exit_fail_msg("PR_SET_KEEPCAPS - %s\n",
diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index a6e9848189d6..b5eb1be2248c 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -147,71 +147,6 @@ test_add_proc()
 }
 
 #
-# Testing the new "isolated" partition root type
-#
-test_isolated()
-{
-	cd $CGROUP2/test
-	echo 2-3 > cpuset.cpus
-	TYPE=$(cat cpuset.cpus.partition)
-	[[ $TYPE = member ]] || echo member > cpuset.cpus.partition
-
-	console_msg "Change from member to root"
-	test_partition root
-
-	console_msg "Change from root to isolated"
-	test_partition isolated
-
-	console_msg "Change from isolated to member"
-	test_partition member
-
-	console_msg "Change from member to isolated"
-	test_partition isolated
-
-	console_msg "Change from isolated to root"
-	test_partition root
-
-	console_msg "Change from root to member"
-	test_partition member
-
-	#
-	# Testing partition root with no cpu
-	#
-	console_msg "Distribute all cpus to child partition"
-	echo +cpuset > cgroup.subtree_control
-	test_partition root
-
-	mkdir A1
-	cd A1
-	echo 2-3 > cpuset.cpus
-	test_partition root
-	test_effective_cpus 2-3
-	cd ..
-	test_effective_cpus ""
-
-	console_msg "Moving task to partition test"
-	test_add_proc "No space left"
-	cd A1
-	test_add_proc ""
-	cd ..
-
-	console_msg "Shrink and expand child partition"
-	cd A1
-	echo 2 > cpuset.cpus
-	cd ..
-	test_effective_cpus 3
-	cd A1
-	echo 2-3 > cpuset.cpus
-	cd ..
-	test_effective_cpus ""
-
-	# Cleaning up
-	console_msg "Cleaning up"
-	echo $$ > $CGROUP2/cgroup.procs
-	[[ -d A1 ]] && rmdir A1
-}
-
-#
 # Cpuset controller state transition test matrix.
 #
 # Cgroup test hierarchy
@@ -297,14 +232,14 @@ TEST_MATRIX=(
 	" C0-3:S+ C1-3:S+ C2-3   C4-5   X2-3  X2-3:P1   P2     P1    0 A1:0-1,A2:,A3:2-3,B1:4-5 \
 								       A1:P0,A2:P1,A3:P2,B1:P1 2-3"
 	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3  X2-3:P1   P2     P1    0 A1:0-1,A2:,A3:2-3,B1:4 \
-								       A1:P0,A2:P1,A3:P2,B1:P1 2-4"
+								       A1:P0,A2:P1,A3:P2,B1:P1 2-4,2-3"
 	" C0-3:S+ C1-3:S+  C3     C4    X2-3  X2-3:P1   P2     P1    0 A1:0-1,A2:2,A3:3,B1:4 \
-								       A1:P0,A2:P1,A3:P2,B1:P1 2-4"
+								       A1:P0,A2:P1,A3:P2,B1:P1 2-4,3"
 	" C0-4:S+ C1-4:S+ C2-4     .    X2-4  X2-4:P2  X4:P1    .    0 A1:0-1,A2:2-3,A3:4 \
-								       A1:P0,A2:P2,A3:P1 2-4"
+								       A1:P0,A2:P2,A3:P1 2-4,2-3"
 	" C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \
 				   .      .      X5      .      .    0 A1:0-4,A2:1-4,A3:2-4 \
-								       A1:P0,A2:P-2,A3:P-1 ."
+								       A1:P0,A2:P-2,A3:P-1"
 	" C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \
 				   .      .      .      X1      .    0 A1:0-1,A2:2-4,A3:2-4 \
 								       A1:P0,A2:P2,A3:P-1 2-4"
@@ -313,7 +248,7 @@ TEST_MATRIX=(
 	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3 X2-3:P2:O2=0 .   0 A1:0-1,A2:1,A3:3 A1:P0,A3:P2 2-3"
 	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1,A2:1,A3:2-3 A1:P0,A3:P2 2-3"
 	" C0-3:S+ C1-3:S+  C3      .    X2-3   X2-3    P2:O3=0   .   0 A1:0-2,A2:1-2,A3: A1:P0,A3:P2 3"
-	" C0-3:S+ C1-3:S+  C3      .    X2-3   X2-3   T:P2:O3=0  .   0 A1:0-2,A2:1-2,A3:1-2 A1:P0,A3:P-2 3"
+	" C0-3:S+ C1-3:S+  C3      .    X2-3   X2-3   T:P2:O3=0  .   0 A1:0-2,A2:1-2,A3:1-2 A1:P0,A3:P-2 3,"
 
 	# An invalidated remote partition cannot self-recover from hotplug
 	" C0-3:S+ C1-3:S+  C2      .    X2-3   X2-3   T:P2:O2=0 O2=1 0 A1:0-3,A2:1-3,A3:2 A1:P0,A3:P-2"
@@ -347,10 +282,10 @@ TEST_MATRIX=(
 	# cpus_allowed/exclusive_cpus update tests
 	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
 				   .     C4      .      P2     .     0 A1:4,A2:4,XA2:,XA3:,A3:4 \
-								       A1:P0,A3:P-2 ."
+								       A1:P0,A3:P-2"
 	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
 				   .     X1      .      P2     .     0 A1:0-3,A2:1-3,XA1:1,XA2:,XA3:,A3:2-3 \
-								       A1:P0,A3:P-2 ."
+								       A1:P0,A3:P-2"
 	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
 				   .      .     C3      P2     .     0 A1:0-2,A2:0-2,XA2:3,XA3:3,A3:3 \
 								       A1:P0,A3:P2 3"
@@ -359,13 +294,13 @@ TEST_MATRIX=(
 								       A1:P0,A3:P2 3"
 	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \
 				   .      .     X3      .      .     0 A1:0-3,A2:1-3,XA2:3,XA3:3,A3:2-3 \
-								       A1:P0,A3:P-2 ."
+								       A1:P0,A3:P-2"
 	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \
 				   .      .     C3      .      .     0 A1:0-3,A2:3,XA2:3,XA3:3,A3:3 \
-								       A1:P0,A3:P-2 ."
+								       A1:P0,A3:P-2"
 	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \
 				   .     C4      .      .      .     0 A1:4,A2:4,A3:4,XA1:,XA2:,XA3 \
-								       A1:P0,A3:P-2 ."
+								       A1:P0,A3:P-2"
 
 	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
 	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
@@ -441,7 +376,7 @@ write_cpu_online()
 		}
 	fi
 	echo $VAL > $CPUFILE
-	pause 0.01
+	pause 0.05
 }
 
 #
@@ -573,12 +508,14 @@ dump_states()
 		XECPUS=$DIR/cpuset.cpus.exclusive.effective
 		PRS=$DIR/cpuset.cpus.partition
 		PCPUS=$DIR/.__DEBUG__.cpuset.cpus.subpartitions
+		ISCPUS=$DIR/cpuset.cpus.isolated
 		[[ -e $CPUS   ]] && echo "$CPUS: $(cat $CPUS)"
 		[[ -e $XCPUS  ]] && echo "$XCPUS: $(cat $XCPUS)"
 		[[ -e $ECPUS  ]] && echo "$ECPUS: $(cat $ECPUS)"
 		[[ -e $XECPUS ]] && echo "$XECPUS: $(cat $XECPUS)"
 		[[ -e $PRS    ]] && echo "$PRS: $(cat $PRS)"
 		[[ -e $PCPUS  ]] && echo "$PCPUS: $(cat $PCPUS)"
+		[[ -e $ISCPUS ]] && echo "$ISCPUS: $(cat $ISCPUS)"
 	done
 }
 
@@ -656,11 +593,17 @@ check_cgroup_states()
 
 #
 # Get isolated (including offline) CPUs by looking at
-# /sys/kernel/debug/sched/domains and compare that with the expected value.
+# /sys/kernel/debug/sched/domains and cpuset.cpus.isolated control file,
+# if available, and compare that with the expected value.
 #
-# Note that a sched domain of just 1 CPU will be considered isolated.
+# Note that isolated CPUs from the sched/domains context include offline
+# CPUs as well as CPUs in non-isolated 1-CPU partition. Those CPUs may
+# not be included in the cpuset.cpus.isolated control file which contains
+# only CPUs in isolated partitions.
 #
-# $1 - expected isolated cpu list
+# $1 - expected isolated cpu list(s) <isolcpus1>{,<isolcpus2>}
+# <isolcpus1> - expected sched/domains value
+# <isolcpus2> - cpuset.cpus.isolated value = <isolcpus1> if not defined
 #
 check_isolcpus()
 {
@@ -668,8 +611,38 @@ check_isolcpus()
 	ISOLCPUS=
 	LASTISOLCPU=
 	SCHED_DOMAINS=/sys/kernel/debug/sched/domains
+	ISCPUS=${CGROUP2}/cpuset.cpus.isolated
+	if [[ $EXPECT_VAL = . ]]
+	then
+		EXPECT_VAL=
+		EXPECT_VAL2=
+	elif [[ $(expr $EXPECT_VAL : ".*,.*") > 0 ]]
+	then
+		set -- $(echo $EXPECT_VAL | sed -e "s/,/ /g")
+		EXPECT_VAL=$1
+		EXPECT_VAL2=$2
+	else
+		EXPECT_VAL2=$EXPECT_VAL
+	fi
+
+	#
+	# Check the debug isolated cpumask, if present
+	#
+	[[ -f $ISCPUS ]] && {
+		ISOLCPUS=$(cat $ISCPUS)
+		[[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && {
+			# Take a 50ms pause and try again
+			pause 0.05
+			ISOLCPUS=$(cat $ISCPUS)
+		}
+		[[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && return 1
+		ISOLCPUS=
+	}
+
+	#
+	# Use the sched domain in debugfs to check isolated CPUs, if available
+	#
 	[[ -d $SCHED_DOMAINS ]] || return 0
-	[[ $EXPECT_VAL = . ]] && EXPECT_VAL=
 
 	for ((CPU=0; CPU < $NR_CPUS; CPU++))
 	do
@@ -714,6 +687,26 @@ test_fail()
 }
 
 #
+# Check to see if there are unexpected isolated CPUs left
+#
+null_isolcpus_check()
+{
+	[[ $VERBOSE -gt 0 ]] || return 0
+	# Retry a few times before printing error
+	RETRY=0
+	while [[ $RETRY -lt 5 ]]
+	do
+		pause 0.01
+		check_isolcpus "."
+		[[ $? -eq 0 ]] && return 0
+		((RETRY++))
+	done
+	echo "Unexpected isolated CPUs: $ISOLCPUS"
+	dump_states
+	exit 1
+}
+
+#
 # Run cpuset state transition test
 #  $1 - test matrix name
 #
@@ -787,7 +780,7 @@ run_state_test()
 		#
 		NEWLIST=$(cat cpuset.cpus.effective)
 		RETRY=0
-		while [[ $NEWLIST != $CPULIST && $RETRY -lt 5 ]]
+		while [[ $NEWLIST != $CPULIST && $RETRY -lt 8 ]]
 		do
 			# Wait a bit longer & recheck a few times
 			pause 0.01
@@ -798,6 +791,7 @@ run_state_test()
 			echo "Effective cpus changed to $NEWLIST after test $I!"
 			exit 1
 		}
+		null_isolcpus_check
 		[[ $VERBOSE -gt 0 ]] && echo "Test $I done."
 		((I++))
 	done
@@ -805,6 +799,72 @@ run_state_test()
 }
 
 #
+# Testing the new "isolated" partition root type
+#
+test_isolated()
+{
+	cd $CGROUP2/test
+	echo 2-3 > cpuset.cpus
+	TYPE=$(cat cpuset.cpus.partition)
+	[[ $TYPE = member ]] || echo member > cpuset.cpus.partition
+
+	console_msg "Change from member to root"
+	test_partition root
+
+	console_msg "Change from root to isolated"
+	test_partition isolated
+
+	console_msg "Change from isolated to member"
+	test_partition member
+
+	console_msg "Change from member to isolated"
+	test_partition isolated
+
+	console_msg "Change from isolated to root"
+	test_partition root
+
+	console_msg "Change from root to member"
+	test_partition member
+
+	#
+	# Testing partition root with no cpu
+	#
+	console_msg "Distribute all cpus to child partition"
+	echo +cpuset > cgroup.subtree_control
+	test_partition root
+
+	mkdir A1
+	cd A1
+	echo 2-3 > cpuset.cpus
+	test_partition root
+	test_effective_cpus 2-3
+	cd ..
+	test_effective_cpus ""
+
+	console_msg "Moving task to partition test"
+	test_add_proc "No space left"
+	cd A1
+	test_add_proc ""
+	cd ..
+
+	console_msg "Shrink and expand child partition"
+	cd A1
+	echo 2 > cpuset.cpus
+	cd ..
+	test_effective_cpus 3
+	cd A1
+	echo 2-3 > cpuset.cpus
+	cd ..
+	test_effective_cpus ""
+
+	# Cleaning up
+	console_msg "Cleaning up"
+	echo $$ > $CGROUP2/cgroup.procs
+	[[ -d A1 ]] && rmdir A1
+	null_isolcpus_check
+}
+
+#
 # Wait for inotify event for the given file and read it
 # $1: cgroup file to wait for
 # $2: file to store the read result
diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c
index ff519029f6f4..8845353aca53 100644
--- a/tools/testing/selftests/cgroup/test_freezer.c
+++ b/tools/testing/selftests/cgroup/test_freezer.c
@@ -740,7 +740,7 @@ static int test_cgfreezer_ptraced(const char *root)
 
 	/*
 	 * cg_check_frozen(cgroup, true) will fail here,
-	 * because the task in in the TRACEd state.
+	 * because the task is in the TRACEd state.
 	 */
 	if (cg_freeze_wait(cgroup, false))
 		goto cleanup;
diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c
index c99d2adaca3f..47fdaa146443 100644
--- a/tools/testing/selftests/cgroup/test_zswap.c
+++ b/tools/testing/selftests/cgroup/test_zswap.c
@@ -50,9 +50,9 @@ static int get_zswap_stored_pages(size_t *value)
 	return read_int("/sys/kernel/debug/zswap/stored_pages", value);
 }
 
-static int get_zswap_written_back_pages(size_t *value)
+static int get_cg_wb_count(const char *cg)
 {
-	return read_int("/sys/kernel/debug/zswap/written_back_pages", value);
+	return cg_read_key_long(cg, "memory.stat", "zswp_wb");
 }
 
 static long get_zswpout(const char *cgroup)
@@ -73,6 +73,24 @@ static int allocate_bytes(const char *cgroup, void *arg)
 	return 0;
 }
 
+static char *setup_test_group_1M(const char *root, const char *name)
+{
+	char *group_name = cg_name(root, name);
+
+	if (!group_name)
+		return NULL;
+	if (cg_create(group_name))
+		goto fail;
+	if (cg_write(group_name, "memory.max", "1M")) {
+		cg_destroy(group_name);
+		goto fail;
+	}
+	return group_name;
+fail:
+	free(group_name);
+	return NULL;
+}
+
 /*
  * Sanity test to check that pages are written into zswap.
  */
@@ -117,43 +135,51 @@ out:
 
 /*
  * When trying to store a memcg page in zswap, if the memcg hits its memory
- * limit in zswap, writeback should not be triggered.
- *
- * This was fixed with commit 0bdf0efa180a("zswap: do not shrink if cgroup may
- * not zswap"). Needs to be revised when a per memcg writeback mechanism is
- * implemented.
+ * limit in zswap, writeback should affect only the zswapped pages of that
+ * memcg.
  */
 static int test_no_invasive_cgroup_shrink(const char *root)
 {
-	size_t written_back_before, written_back_after;
 	int ret = KSFT_FAIL;
-	char *test_group;
+	size_t control_allocation_size = MB(10);
+	char *control_allocation, *wb_group = NULL, *control_group = NULL;
 
 	/* Set up */
-	test_group = cg_name(root, "no_shrink_test");
-	if (!test_group)
-		goto out;
-	if (cg_create(test_group))
+	wb_group = setup_test_group_1M(root, "per_memcg_wb_test1");
+	if (!wb_group)
+		return KSFT_FAIL;
+	if (cg_write(wb_group, "memory.zswap.max", "10K"))
 		goto out;
-	if (cg_write(test_group, "memory.max", "1M"))
+	control_group = setup_test_group_1M(root, "per_memcg_wb_test2");
+	if (!control_group)
 		goto out;
-	if (cg_write(test_group, "memory.zswap.max", "10K"))
+
+	/* Push some test_group2 memory into zswap */
+	if (cg_enter_current(control_group))
 		goto out;
-	if (get_zswap_written_back_pages(&written_back_before))
+	control_allocation = malloc(control_allocation_size);
+	for (int i = 0; i < control_allocation_size; i += 4095)
+		control_allocation[i] = 'a';
+	if (cg_read_key_long(control_group, "memory.stat", "zswapped") < 1)
 		goto out;
 
-	/* Allocate 10x memory.max to push memory into zswap */
-	if (cg_run(test_group, allocate_bytes, (void *)MB(10)))
+	/* Allocate 10x memory.max to push wb_group memory into zswap and trigger wb */
+	if (cg_run(wb_group, allocate_bytes, (void *)MB(10)))
 		goto out;
 
-	/* Verify that no writeback happened because of the memcg allocation */
-	if (get_zswap_written_back_pages(&written_back_after))
-		goto out;
-	if (written_back_after == written_back_before)
+	/* Verify that only zswapped memory from gwb_group has been written back */
+	if (get_cg_wb_count(wb_group) > 0 && get_cg_wb_count(control_group) == 0)
 		ret = KSFT_PASS;
 out:
-	cg_destroy(test_group);
-	free(test_group);
+	cg_enter_current(root);
+	if (control_group) {
+		cg_destroy(control_group);
+		free(control_group);
+	}
+	cg_destroy(wb_group);
+	free(wb_group);
+	if (control_allocation)
+		free(control_allocation);
 	return ret;
 }
 
diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile
index b71247ba7196..8a1cc2bf1864 100644
--- a/tools/testing/selftests/damon/Makefile
+++ b/tools/testing/selftests/damon/Makefile
@@ -2,6 +2,7 @@
 # Makefile for damon selftests
 
 TEST_GEN_FILES += huge_count_read_write
+TEST_GEN_FILES += access_memory
 
 TEST_FILES = _chk_dependency.sh _debugfs_common.sh
 TEST_PROGS = debugfs_attrs.sh debugfs_schemes.sh debugfs_target_ids.sh
@@ -9,6 +10,8 @@ TEST_PROGS += debugfs_empty_targets.sh debugfs_huge_count_read_write.sh
 TEST_PROGS += debugfs_duplicate_context_creation.sh
 TEST_PROGS += debugfs_rm_non_contexts.sh
 TEST_PROGS += sysfs.sh sysfs_update_removed_scheme_dir.sh
+TEST_PROGS += sysfs_update_schemes_tried_regions_hang.py
+TEST_PROGS += sysfs_update_schemes_tried_regions_wss_estimation.py
 TEST_PROGS += reclaim.sh lru_sort.sh
 
 include ../lib.mk
diff --git a/tools/testing/selftests/damon/_damon_sysfs.py b/tools/testing/selftests/damon/_damon_sysfs.py
new file mode 100644
index 000000000000..e98cf4b6a4b7
--- /dev/null
+++ b/tools/testing/selftests/damon/_damon_sysfs.py
@@ -0,0 +1,322 @@
+# SPDX-License-Identifier: GPL-2.0
+
+import os
+
+sysfs_root = '/sys/kernel/mm/damon/admin'
+
+def write_file(path, string):
+    "Returns error string if failed, or None otherwise"
+    string = '%s' % string
+    try:
+        with open(path, 'w') as f:
+            f.write(string)
+    except Exception as e:
+        return '%s' % e
+    return None
+
+def read_file(path):
+    '''Returns the read content and error string.  The read content is None if
+    the reading failed'''
+    try:
+        with open(path, 'r') as f:
+            return f.read(), None
+    except Exception as e:
+        return None, '%s' % e
+
+class DamosAccessPattern:
+    size = None
+    nr_accesses = None
+    age = None
+    scheme = None
+
+    def __init__(self, size=None, nr_accesses=None, age=None):
+        self.size = size
+        self.nr_accesses = nr_accesses
+        self.age = age
+
+        if self.size == None:
+            self.size = [0, 2**64 - 1]
+        if self.nr_accesses == None:
+            self.nr_accesses = [0, 2**64 - 1]
+        if self.age == None:
+            self.age = [0, 2**64 - 1]
+
+    def sysfs_dir(self):
+        return os.path.join(self.scheme.sysfs_dir(), 'access_pattern')
+
+    def stage(self):
+        err = write_file(
+                os.path.join(self.sysfs_dir(), 'sz', 'min'), self.size[0])
+        if err != None:
+            return err
+        err = write_file(
+                os.path.join(self.sysfs_dir(), 'sz', 'max'), self.size[1])
+        if err != None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'nr_accesses', 'min'),
+                self.nr_accesses[0])
+        if err != None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'nr_accesses', 'max'),
+                self.nr_accesses[1])
+        if err != None:
+            return err
+        err = write_file(
+                os.path.join(self.sysfs_dir(), 'age', 'min'), self.age[0])
+        if err != None:
+            return err
+        err = write_file(
+                os.path.join(self.sysfs_dir(), 'age', 'max'), self.age[1])
+        if err != None:
+            return err
+
+class Damos:
+    action = None
+    access_pattern = None
+    # todo: Support quotas, watermarks, stats, tried_regions
+    idx = None
+    context = None
+    tried_bytes = None
+
+    def __init__(self, action='stat', access_pattern=DamosAccessPattern()):
+        self.action = action
+        self.access_pattern = access_pattern
+        self.access_pattern.scheme = self
+
+    def sysfs_dir(self):
+        return os.path.join(
+                self.context.sysfs_dir(), 'schemes', '%d' % self.idx)
+
+    def stage(self):
+        err = write_file(os.path.join(self.sysfs_dir(), 'action'), self.action)
+        if err != None:
+            return err
+        err = self.access_pattern.stage()
+        if err != None:
+            return err
+
+        # disable quotas
+        err = write_file(os.path.join(self.sysfs_dir(), 'quotas', 'ms'), '0')
+        if err != None:
+            return err
+        err = write_file(
+                os.path.join(self.sysfs_dir(), 'quotas', 'bytes'), '0')
+        if err != None:
+            return err
+
+        # disable watermarks
+        err = write_file(
+                os.path.join(self.sysfs_dir(), 'watermarks', 'metric'), 'none')
+        if err != None:
+            return err
+
+        # disable filters
+        err = write_file(
+                os.path.join(self.sysfs_dir(), 'filters', 'nr_filters'), '0')
+        if err != None:
+            return err
+
+class DamonTarget:
+    pid = None
+    # todo: Support target regions if test is made
+    idx = None
+    context = None
+
+    def __init__(self, pid):
+        self.pid = pid
+
+    def sysfs_dir(self):
+        return os.path.join(
+                self.context.sysfs_dir(), 'targets', '%d' % self.idx)
+
+    def stage(self):
+        err = write_file(
+                os.path.join(self.sysfs_dir(), 'regions', 'nr_regions'), '0')
+        if err != None:
+            return err
+        return write_file(
+                os.path.join(self.sysfs_dir(), 'pid_target'), self.pid)
+
+class DamonAttrs:
+    sample_us = None
+    aggr_us = None
+    update_us = None
+    min_nr_regions = None
+    max_nr_regions = None
+    context = None
+
+    def __init__(self, sample_us=5000, aggr_us=100000, update_us=1000000,
+            min_nr_regions=10, max_nr_regions=1000):
+        self.sample_us = sample_us
+        self.aggr_us = aggr_us
+        self.update_us = update_us
+        self.min_nr_regions = min_nr_regions
+        self.max_nr_regions = max_nr_regions
+
+    def interval_sysfs_dir(self):
+        return os.path.join(self.context.sysfs_dir(), 'monitoring_attrs',
+                'intervals')
+
+    def nr_regions_range_sysfs_dir(self):
+        return os.path.join(self.context.sysfs_dir(), 'monitoring_attrs',
+                'nr_regions')
+
+    def stage(self):
+        err = write_file(os.path.join(self.interval_sysfs_dir(), 'sample_us'),
+                self.sample_us)
+        if err != None:
+            return err
+        err = write_file(os.path.join(self.interval_sysfs_dir(), 'aggr_us'),
+                self.aggr_us)
+        if err != None:
+            return err
+        err = write_file(os.path.join(self.interval_sysfs_dir(), 'update_us'),
+                self.update_us)
+        if err != None:
+            return err
+
+        err = write_file(
+                os.path.join(self.nr_regions_range_sysfs_dir(), 'min'),
+                self.min_nr_regions)
+        if err != None:
+            return err
+
+        err = write_file(
+                os.path.join(self.nr_regions_range_sysfs_dir(), 'max'),
+                self.max_nr_regions)
+        if err != None:
+            return err
+
+class DamonCtx:
+    ops = None
+    monitoring_attrs = None
+    targets = None
+    schemes = None
+    kdamond = None
+    idx = None
+
+    def __init__(self, ops='paddr', monitoring_attrs=DamonAttrs(), targets=[],
+            schemes=[]):
+        self.ops = ops
+        self.monitoring_attrs = monitoring_attrs
+        self.monitoring_attrs.context = self
+
+        self.targets = targets
+        for idx, target in enumerate(self.targets):
+            target.idx = idx
+            target.context = self
+
+        self.schemes = schemes
+        for idx, scheme in enumerate(self.schemes):
+            scheme.idx = idx
+            scheme.context = self
+
+    def sysfs_dir(self):
+        return os.path.join(self.kdamond.sysfs_dir(), 'contexts',
+                '%d' % self.idx)
+
+    def stage(self):
+        err = write_file(
+                os.path.join(self.sysfs_dir(), 'operations'), self.ops)
+        if err != None:
+            return err
+        err = self.monitoring_attrs.stage()
+        if err != None:
+            return err
+
+        nr_targets_file = os.path.join(
+                self.sysfs_dir(), 'targets', 'nr_targets')
+        content, err = read_file(nr_targets_file)
+        if err != None:
+            return err
+        if int(content) != len(self.targets):
+            err = write_file(nr_targets_file, '%d' % len(self.targets))
+            if err != None:
+                return err
+        for target in self.targets:
+            err = target.stage()
+            if err != None:
+                return err
+
+        nr_schemes_file = os.path.join(
+                self.sysfs_dir(), 'schemes', 'nr_schemes')
+        content, err = read_file(nr_schemes_file)
+        if int(content) != len(self.schemes):
+            err = write_file(nr_schemes_file, '%d' % len(self.schemes))
+            if err != None:
+                return err
+        for scheme in self.schemes:
+            err = scheme.stage()
+            if err != None:
+                return err
+        return None
+
+class Kdamond:
+    state = None
+    pid = None
+    contexts = None
+    idx = None      # index of this kdamond between siblings
+    kdamonds = None # parent
+
+    def __init__(self, contexts=[]):
+        self.contexts = contexts
+        for idx, context in enumerate(self.contexts):
+            context.idx = idx
+            context.kdamond = self
+
+    def sysfs_dir(self):
+        return os.path.join(self.kdamonds.sysfs_dir(), '%d' % self.idx)
+
+    def start(self):
+        nr_contexts_file = os.path.join(self.sysfs_dir(),
+                'contexts', 'nr_contexts')
+        content, err = read_file(nr_contexts_file)
+        if err != None:
+            return err
+        if int(content) != len(self.contexts):
+            err = write_file(nr_contexts_file, '%d' % len(self.contexts))
+            if err != None:
+                return err
+
+        for context in self.contexts:
+            err = context.stage()
+            if err != None:
+                return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'state'), 'on')
+        return err
+
+    def update_schemes_tried_bytes(self):
+        err = write_file(os.path.join(self.sysfs_dir(), 'state'),
+                'update_schemes_tried_bytes')
+        if err != None:
+            return err
+        for context in self.contexts:
+            for scheme in context.schemes:
+                content, err = read_file(os.path.join(scheme.sysfs_dir(),
+                    'tried_regions', 'total_bytes'))
+                if err != None:
+                    return err
+                scheme.tried_bytes = int(content)
+
+class Kdamonds:
+    kdamonds = []
+
+    def __init__(self, kdamonds=[]):
+        self.kdamonds = kdamonds
+        for idx, kdamond in enumerate(self.kdamonds):
+            kdamond.idx = idx
+            kdamond.kdamonds = self
+
+    def sysfs_dir(self):
+        return os.path.join(sysfs_root, 'kdamonds')
+
+    def start(self):
+        err = write_file(os.path.join(self.sysfs_dir(),  'nr_kdamonds'),
+                '%s' % len(self.kdamonds))
+        if err != None:
+            return err
+        for kdamond in self.kdamonds:
+            err = kdamond.start()
+            if err != None:
+                return err
+        return None
diff --git a/tools/testing/selftests/damon/access_memory.c b/tools/testing/selftests/damon/access_memory.c
new file mode 100644
index 000000000000..585a2fa54329
--- /dev/null
+++ b/tools/testing/selftests/damon/access_memory.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Artificial memory access program for testing DAMON.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+
+int main(int argc, char *argv[])
+{
+	char **regions;
+	clock_t start_clock;
+	int nr_regions;
+	int sz_region;
+	int access_time_ms;
+	int i;
+
+	if (argc != 4) {
+		printf("Usage: %s <number> <size (bytes)> <time (ms)>\n",
+				argv[0]);
+		return -1;
+	}
+
+	nr_regions = atoi(argv[1]);
+	sz_region = atoi(argv[2]);
+	access_time_ms = atoi(argv[3]);
+
+	regions = malloc(sizeof(*regions) * nr_regions);
+	for (i = 0; i < nr_regions; i++)
+		regions[i] = malloc(sz_region);
+
+	for (i = 0; i < nr_regions; i++) {
+		start_clock = clock();
+		while ((clock() - start_clock) * 1000 / CLOCKS_PER_SEC <
+				access_time_ms)
+			memset(regions[i], i, 1024 * 1024 * 10);
+	}
+	return 0;
+}
diff --git a/tools/testing/selftests/damon/sysfs.sh b/tools/testing/selftests/damon/sysfs.sh
index 56f0230a8b92..e9a976d296e2 100755
--- a/tools/testing/selftests/damon/sysfs.sh
+++ b/tools/testing/selftests/damon/sysfs.sh
@@ -150,6 +150,32 @@ test_weights()
 	ensure_file "$weights_dir/age_permil" "exist" "600"
 }
 
+test_goal()
+{
+	goal_dir=$1
+	ensure_dir "$goal_dir" "exist"
+	ensure_file "$goal_dir/target_value" "exist" "600"
+	ensure_file "$goal_dir/current_value" "exist" "600"
+}
+
+test_goals()
+{
+	goals_dir=$1
+	ensure_dir "$goals_dir" "exist"
+	ensure_file "$goals_dir/nr_goals" "exist" "600"
+
+	ensure_write_succ  "$goals_dir/nr_goals" "1" "valid input"
+	test_goal "$goals_dir/0"
+
+	ensure_write_succ  "$goals_dir/nr_goals" "2" "valid input"
+	test_goal "$goals_dir/0"
+	test_goal "$goals_dir/1"
+
+	ensure_write_succ  "$goals_dir/nr_goals" "0" "valid input"
+	ensure_dir "$goals_dir/0" "not_exist"
+	ensure_dir "$goals_dir/1" "not_exist"
+}
+
 test_quotas()
 {
 	quotas_dir=$1
@@ -158,6 +184,7 @@ test_quotas()
 	ensure_file "$quotas_dir/bytes" "exist" 600
 	ensure_file "$quotas_dir/reset_interval_ms" "exist" 600
 	test_weights "$quotas_dir/weights"
+	test_goals "$quotas_dir/goals"
 }
 
 test_access_pattern()
diff --git a/tools/testing/selftests/damon/sysfs_update_schemes_tried_regions_hang.py b/tools/testing/selftests/damon/sysfs_update_schemes_tried_regions_hang.py
new file mode 100644
index 000000000000..8c690ba1a573
--- /dev/null
+++ b/tools/testing/selftests/damon/sysfs_update_schemes_tried_regions_hang.py
@@ -0,0 +1,33 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import subprocess
+import time
+
+import _damon_sysfs
+
+def main():
+    proc = subprocess.Popen(['sleep', '2'])
+    kdamonds = _damon_sysfs.Kdamonds([_damon_sysfs.Kdamond(
+            contexts=[_damon_sysfs.DamonCtx(
+                ops='vaddr',
+                targets=[_damon_sysfs.DamonTarget(pid=proc.pid)],
+                schemes=[_damon_sysfs.Damos(
+                    access_pattern=_damon_sysfs.DamosAccessPattern(
+                        nr_accesses=[200, 200]))] # schemes
+                )] # contexts
+            )]) # kdamonds
+
+    err = kdamonds.start()
+    if err != None:
+        print('kdmaond start failed: %s' % err)
+        exit(1)
+
+    while proc.poll() == None:
+        err = kdamonds.kdamonds[0].update_schemes_tried_bytes()
+        if err != None:
+            print('tried bytes update failed: %s' % err)
+            exit(1)
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/testing/selftests/damon/sysfs_update_schemes_tried_regions_wss_estimation.py b/tools/testing/selftests/damon/sysfs_update_schemes_tried_regions_wss_estimation.py
new file mode 100644
index 000000000000..cdbf19b442c9
--- /dev/null
+++ b/tools/testing/selftests/damon/sysfs_update_schemes_tried_regions_wss_estimation.py
@@ -0,0 +1,55 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import subprocess
+import time
+
+import _damon_sysfs
+
+def main():
+    # access two 10 MiB memory regions, 2 second per each
+    sz_region = 10 * 1024 * 1024
+    proc = subprocess.Popen(['./access_memory', '2', '%d' % sz_region, '2000'])
+    kdamonds = _damon_sysfs.Kdamonds([_damon_sysfs.Kdamond(
+            contexts=[_damon_sysfs.DamonCtx(
+                ops='vaddr',
+                targets=[_damon_sysfs.DamonTarget(pid=proc.pid)],
+                schemes=[_damon_sysfs.Damos(
+                    access_pattern=_damon_sysfs.DamosAccessPattern(
+                        # >= 25% access rate, >= 200ms age
+                        nr_accesses=[5, 20], age=[2, 2**64 - 1]))] # schemes
+                )] # contexts
+            )]) # kdamonds
+
+    err = kdamonds.start()
+    if err != None:
+        print('kdmaond start failed: %s' % err)
+        exit(1)
+
+    wss_collected = []
+    while proc.poll() == None:
+        time.sleep(0.1)
+        err = kdamonds.kdamonds[0].update_schemes_tried_bytes()
+        if err != None:
+            print('tried bytes update failed: %s' % err)
+            exit(1)
+
+        wss_collected.append(
+                kdamonds.kdamonds[0].contexts[0].schemes[0].tried_bytes)
+
+    wss_collected.sort()
+    acceptable_error_rate = 0.2
+    for percentile in [50, 75]:
+        sample = wss_collected[int(len(wss_collected) * percentile / 100)]
+        error_rate = abs(sample - sz_region) / sz_region
+        print('%d-th percentile (%d) error %f' %
+                (percentile, sample, error_rate))
+        if error_rate > acceptable_error_rate:
+            print('the error rate is not acceptable (> %f)' %
+                    acceptable_error_rate)
+            print('samples are as below')
+            print('\n'.join(['%d' % wss for wss in wss_collected]))
+            exit(1)
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh
index 4917dbb35a44..5667febee328 100755
--- a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh
+++ b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh
@@ -30,16 +30,16 @@ ip netns exec server ip addr add ${server_ip4}/24 dev eth0
 
 ip netns exec client ip link add dev bond0 down type bond mode 1 \
 	miimon 100 all_slaves_active 1
-ip netns exec client ip link set dev eth0 down master bond0
+ip netns exec client ip link set dev eth0 master bond0
 ip netns exec client ip link set dev bond0 up
 ip netns exec client ip addr add ${client_ip4}/24 dev bond0
 ip netns exec client ping -c 5 $server_ip4 >/dev/null
 
-ip netns exec client ip link set dev eth0 down nomaster
+ip netns exec client ip link set dev eth0 nomaster
 ip netns exec client ip link set dev bond0 down
 ip netns exec client ip link set dev bond0 type bond mode 0 \
 	arp_interval 1000 arp_ip_target "+${server_ip4}"
-ip netns exec client ip link set dev eth0 down master bond0
+ip netns exec client ip link set dev eth0 master bond0
 ip netns exec client ip link set dev bond0 up
 ip netns exec client ping -c 5 $server_ip4 >/dev/null
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/pci_reset.sh b/tools/testing/selftests/drivers/net/mlxsw/pci_reset.sh
new file mode 100755
index 000000000000..fe0343b95e6c
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/pci_reset.sh
@@ -0,0 +1,58 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test that PCI reset works correctly by verifying that only the expected reset
+# methods are supported and that after issuing the reset the ifindex of the
+# port changes.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+	pci_reset_test
+"
+NUM_NETIFS=1
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+pci_reset_test()
+{
+	RET=0
+
+	local bus=$(echo $DEVLINK_DEV | cut -d '/' -f 1)
+	local bdf=$(echo $DEVLINK_DEV | cut -d '/' -f 2)
+
+	if [ $bus != "pci" ]; then
+		check_err 1 "devlink device is not a PCI device"
+		log_test "pci reset"
+		return
+	fi
+
+	if [ ! -f /sys/bus/pci/devices/$bdf/reset_method ]; then
+		check_err 1 "reset is not supported"
+		log_test "pci reset"
+		return
+	fi
+
+	[[ $(cat /sys/bus/pci/devices/$bdf/reset_method) == "bus" ]]
+	check_err $? "only \"bus\" reset method should be supported"
+
+	local ifindex_pre=$(ip -j link show dev $swp1 | jq '.[]["ifindex"]')
+
+	echo 1 > /sys/bus/pci/devices/$bdf/reset
+	check_err $? "reset failed"
+
+	# Wait for udev to rename newly created netdev.
+	udevadm settle
+
+	local ifindex_post=$(ip -j link show dev $swp1 | jq '.[]["ifindex"]')
+
+	[[ $ifindex_pre != $ifindex_post ]]
+	check_err $? "reset not performed"
+
+	log_test "pci reset"
+}
+
+swp1=${NETIFS[p1]}
+tests_run
+
+exit $EXIT_STATUS
diff --git a/net/bpfilter/.gitignore b/tools/testing/selftests/filesystems/overlayfs/.gitignore
index f34e85ee8204..52ae618fdd98 100644
--- a/net/bpfilter/.gitignore
+++ b/tools/testing/selftests/filesystems/overlayfs/.gitignore
@@ -1,2 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
-bpfilter_umh
+dev_in_maps
diff --git a/tools/testing/selftests/filesystems/overlayfs/Makefile b/tools/testing/selftests/filesystems/overlayfs/Makefile
new file mode 100644
index 000000000000..56b2b48a765b
--- /dev/null
+++ b/tools/testing/selftests/filesystems/overlayfs/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+
+TEST_GEN_PROGS := dev_in_maps
+
+CFLAGS := -Wall -Werror
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c b/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c
new file mode 100644
index 000000000000..e19ab0e85709
--- /dev/null
+++ b/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c
@@ -0,0 +1,182 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <inttypes.h>
+#include <unistd.h>
+#include <stdio.h>
+
+#include <linux/unistd.h>
+#include <linux/types.h>
+#include <linux/mount.h>
+#include <sys/syscall.h>
+#include <sys/stat.h>
+#include <sys/mount.h>
+#include <sys/mman.h>
+#include <sched.h>
+#include <fcntl.h>
+
+#include "../../kselftest.h"
+#include "log.h"
+
+static int sys_fsopen(const char *fsname, unsigned int flags)
+{
+	return syscall(__NR_fsopen, fsname, flags);
+}
+
+static int sys_fsconfig(int fd, unsigned int cmd, const char *key, const char *value, int aux)
+{
+	return syscall(__NR_fsconfig, fd, cmd, key, value, aux);
+}
+
+static int sys_fsmount(int fd, unsigned int flags, unsigned int attr_flags)
+{
+	return syscall(__NR_fsmount, fd, flags, attr_flags);
+}
+
+static int sys_move_mount(int from_dfd, const char *from_pathname,
+			  int to_dfd, const char *to_pathname,
+			  unsigned int flags)
+{
+	return syscall(__NR_move_mount, from_dfd, from_pathname, to_dfd, to_pathname, flags);
+}
+
+static long get_file_dev_and_inode(void *addr, struct statx *stx)
+{
+	char buf[4096];
+	FILE *mapf;
+
+	mapf = fopen("/proc/self/maps", "r");
+	if (mapf == NULL)
+		return pr_perror("fopen(/proc/self/maps)");
+
+	while (fgets(buf, sizeof(buf), mapf)) {
+		unsigned long start, end;
+		uint32_t maj, min;
+		__u64 ino;
+
+		if (sscanf(buf, "%lx-%lx %*s %*s %x:%x %llu",
+				&start, &end, &maj, &min, &ino) != 5)
+			return pr_perror("unable to parse: %s", buf);
+		if (start == (unsigned long)addr) {
+			stx->stx_dev_major = maj;
+			stx->stx_dev_minor = min;
+			stx->stx_ino = ino;
+			return 0;
+		}
+	}
+
+	return pr_err("unable to find the mapping");
+}
+
+static int ovl_mount(void)
+{
+	int tmpfs, fsfd, ovl;
+
+	fsfd = sys_fsopen("tmpfs", 0);
+	if (fsfd == -1)
+		return pr_perror("fsopen(tmpfs)");
+
+	if (sys_fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0) == -1)
+		return pr_perror("FSCONFIG_CMD_CREATE");
+
+	tmpfs = sys_fsmount(fsfd, 0, 0);
+	if (tmpfs == -1)
+		return pr_perror("fsmount");
+
+	close(fsfd);
+
+	/* overlayfs can't be constructed on top of a detached mount. */
+	if (sys_move_mount(tmpfs, "", AT_FDCWD, "/tmp", MOVE_MOUNT_F_EMPTY_PATH))
+		return pr_perror("move_mount");
+	close(tmpfs);
+
+	if (mkdir("/tmp/w", 0755) == -1 ||
+	    mkdir("/tmp/u", 0755) == -1 ||
+	    mkdir("/tmp/l", 0755) == -1)
+		return pr_perror("mkdir");
+
+	fsfd = sys_fsopen("overlay", 0);
+	if (fsfd == -1)
+		return pr_perror("fsopen(overlay)");
+	if (sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "source", "test", 0) == -1 ||
+	    sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "lowerdir", "/tmp/l", 0) == -1 ||
+	    sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "upperdir", "/tmp/u", 0) == -1 ||
+	    sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "workdir", "/tmp/w", 0) == -1)
+		return pr_perror("fsconfig");
+	if (sys_fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0) == -1)
+		return pr_perror("fsconfig");
+	ovl = sys_fsmount(fsfd, 0, 0);
+	if (ovl == -1)
+		return pr_perror("fsmount");
+
+	return ovl;
+}
+
+/*
+ * Check that the file device and inode shown in /proc/pid/maps match values
+ * returned by stat(2).
+ */
+static int test(void)
+{
+	struct statx stx, mstx;
+	int ovl, fd;
+	void *addr;
+
+	ovl = ovl_mount();
+	if (ovl == -1)
+		return -1;
+
+	fd = openat(ovl, "test", O_RDWR | O_CREAT, 0644);
+	if (fd == -1)
+		return pr_perror("openat");
+
+	addr = mmap(NULL, 4096, PROT_READ | PROT_WRITE, MAP_FILE | MAP_SHARED, fd, 0);
+	if (addr == MAP_FAILED)
+		return pr_perror("mmap");
+
+	if (get_file_dev_and_inode(addr, &mstx))
+		return -1;
+	if (statx(fd, "", AT_EMPTY_PATH | AT_STATX_SYNC_AS_STAT, STATX_INO, &stx))
+		return pr_perror("statx");
+
+	if (stx.stx_dev_major != mstx.stx_dev_major ||
+	    stx.stx_dev_minor != mstx.stx_dev_minor ||
+	    stx.stx_ino != mstx.stx_ino)
+		return pr_fail("unmatched dev:ino %x:%x:%llx (expected %x:%x:%llx)\n",
+			mstx.stx_dev_major, mstx.stx_dev_minor, mstx.stx_ino,
+			stx.stx_dev_major, stx.stx_dev_minor, stx.stx_ino);
+
+	ksft_test_result_pass("devices are matched\n");
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	int fsfd;
+
+	fsfd = sys_fsopen("overlay", 0);
+	if (fsfd == -1) {
+		ksft_test_result_skip("unable to create overlay mount\n");
+		return 1;
+	}
+	close(fsfd);
+
+	/* Create a new mount namespace to not care about cleaning test mounts. */
+	if (unshare(CLONE_NEWNS) == -1) {
+		ksft_test_result_skip("unable to create a new mount namespace\n");
+		return 1;
+	}
+
+	if (mount(NULL, "/", NULL, MS_SLAVE | MS_REC, NULL) == -1) {
+		pr_perror("mount");
+		return 1;
+	}
+
+	ksft_set_plan(1);
+
+	if (test())
+		return 1;
+
+	ksft_exit_pass();
+	return 0;
+}
diff --git a/tools/testing/selftests/filesystems/overlayfs/log.h b/tools/testing/selftests/filesystems/overlayfs/log.h
new file mode 100644
index 000000000000..db64df2a8483
--- /dev/null
+++ b/tools/testing/selftests/filesystems/overlayfs/log.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __SELFTEST_TIMENS_LOG_H__
+#define __SELFTEST_TIMENS_LOG_H__
+
+#define pr_msg(fmt, lvl, ...)						\
+	ksft_print_msg("[%s] (%s:%d)\t" fmt "\n",			\
+			lvl, __FILE__, __LINE__, ##__VA_ARGS__)
+
+#define pr_p(func, fmt, ...)	func(fmt ": %m", ##__VA_ARGS__)
+
+#define pr_err(fmt, ...)						\
+	({								\
+		ksft_test_result_error(fmt "\n", ##__VA_ARGS__);		\
+		-1;							\
+	})
+
+#define pr_fail(fmt, ...)					\
+	({							\
+		ksft_test_result_fail(fmt, ##__VA_ARGS__);	\
+		-1;						\
+	})
+
+#define pr_perror(fmt, ...)	pr_p(pr_err, fmt, ##__VA_ARGS__)
+
+#endif
diff --git a/arch/arm/mach-airoha/Makefile b/tools/testing/selftests/filesystems/statmount/.gitignore
index a5857d0d02eb..82a4846cbc4b 100644
--- a/arch/arm/mach-airoha/Makefile
+++ b/tools/testing/selftests/filesystems/statmount/.gitignore
@@ -1,2 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-y			+= airoha.o
+/*_test
diff --git a/tools/testing/selftests/filesystems/statmount/Makefile b/tools/testing/selftests/filesystems/statmount/Makefile
new file mode 100644
index 000000000000..07a0d5b545ca
--- /dev/null
+++ b/tools/testing/selftests/filesystems/statmount/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES)
+TEST_GEN_PROGS := statmount_test
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/filesystems/statmount/statmount_test.c b/tools/testing/selftests/filesystems/statmount/statmount_test.c
new file mode 100644
index 000000000000..3eafd7da58e2
--- /dev/null
+++ b/tools/testing/selftests/filesystems/statmount/statmount_test.c
@@ -0,0 +1,612 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#define _GNU_SOURCE
+
+#include <assert.h>
+#include <stdint.h>
+#include <sched.h>
+#include <fcntl.h>
+#include <sys/param.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/statfs.h>
+#include <linux/mount.h>
+#include <linux/stat.h>
+#include <asm/unistd.h>
+
+#include "../../kselftest.h"
+
+static const char *const known_fs[] = {
+	"9p", "adfs", "affs", "afs", "aio", "anon_inodefs", "apparmorfs",
+	"autofs", "bcachefs", "bdev", "befs", "bfs", "binder", "binfmt_misc",
+	"bpf", "btrfs", "btrfs_test_fs", "ceph", "cgroup", "cgroup2", "cifs",
+	"coda", "configfs", "cpuset", "cramfs", "cxl", "dax", "debugfs",
+	"devpts", "devtmpfs", "dmabuf", "drm", "ecryptfs", "efivarfs", "efs",
+	"erofs", "exfat", "ext2", "ext3", "ext4", "f2fs", "functionfs",
+	"fuse", "fuseblk", "fusectl", "gadgetfs", "gfs2", "gfs2meta", "hfs",
+	"hfsplus", "hostfs", "hpfs", "hugetlbfs", "ibmasmfs", "iomem",
+	"ipathfs", "iso9660", "jffs2", "jfs", "minix", "mqueue", "msdos",
+	"nfs", "nfs4", "nfsd", "nilfs2", "nsfs", "ntfs", "ntfs3", "ocfs2",
+	"ocfs2_dlmfs", "ocxlflash", "omfs", "openpromfs", "overlay", "pipefs",
+	"proc", "pstore", "pvfs2", "qnx4", "qnx6", "ramfs", "reiserfs",
+	"resctrl", "romfs", "rootfs", "rpc_pipefs", "s390_hypfs", "secretmem",
+	"securityfs", "selinuxfs", "smackfs", "smb3", "sockfs", "spufs",
+	"squashfs", "sysfs", "sysv", "tmpfs", "tracefs", "ubifs", "udf",
+	"ufs", "v7", "vboxsf", "vfat", "virtiofs", "vxfs", "xenfs", "xfs",
+	"zonefs", NULL };
+
+static int statmount(uint64_t mnt_id, uint64_t mask, struct statmount *buf,
+		     size_t bufsize, unsigned int flags)
+{
+	struct mnt_id_req req = {
+		.size = MNT_ID_REQ_SIZE_VER0,
+		.mnt_id = mnt_id,
+		.param = mask,
+	};
+
+	return syscall(__NR_statmount, &req, buf, bufsize, flags);
+}
+
+static struct statmount *statmount_alloc(uint64_t mnt_id, uint64_t mask, unsigned int flags)
+{
+	size_t bufsize = 1 << 15;
+	struct statmount *buf = NULL, *tmp = alloca(bufsize);
+	int tofree = 0;
+	int ret;
+
+	for (;;) {
+		ret = statmount(mnt_id, mask, tmp, bufsize, flags);
+		if (ret != -1)
+			break;
+		if (tofree)
+			free(tmp);
+		if (errno != EOVERFLOW)
+			return NULL;
+		bufsize <<= 1;
+		tofree = 1;
+		tmp = malloc(bufsize);
+		if (!tmp)
+			return NULL;
+	}
+	buf = malloc(tmp->size);
+	if (buf)
+		memcpy(buf, tmp, tmp->size);
+	if (tofree)
+		free(tmp);
+
+	return buf;
+}
+
+static void write_file(const char *path, const char *val)
+{
+	int fd = open(path, O_WRONLY);
+	size_t len = strlen(val);
+	int ret;
+
+	if (fd == -1)
+		ksft_exit_fail_msg("opening %s for write: %s\n", path, strerror(errno));
+
+	ret = write(fd, val, len);
+	if (ret == -1)
+		ksft_exit_fail_msg("writing to %s: %s\n", path, strerror(errno));
+	if (ret != len)
+		ksft_exit_fail_msg("short write to %s\n", path);
+
+	ret = close(fd);
+	if (ret == -1)
+		ksft_exit_fail_msg("closing %s\n", path);
+}
+
+static uint64_t get_mnt_id(const char *name, const char *path, uint64_t mask)
+{
+	struct statx sx;
+	int ret;
+
+	ret = statx(AT_FDCWD, path, 0, mask, &sx);
+	if (ret == -1)
+		ksft_exit_fail_msg("retrieving %s mount ID for %s: %s\n",
+				   mask & STATX_MNT_ID_UNIQUE ? "unique" : "old",
+				   name, strerror(errno));
+	if (!(sx.stx_mask & mask))
+		ksft_exit_fail_msg("no %s mount ID available for %s\n",
+				   mask & STATX_MNT_ID_UNIQUE ? "unique" : "old",
+				   name);
+
+	return sx.stx_mnt_id;
+}
+
+
+static char root_mntpoint[] = "/tmp/statmount_test_root.XXXXXX";
+static int orig_root;
+static uint64_t root_id, parent_id;
+static uint32_t old_root_id, old_parent_id;
+
+
+static void cleanup_namespace(void)
+{
+	fchdir(orig_root);
+	chroot(".");
+	umount2(root_mntpoint, MNT_DETACH);
+	rmdir(root_mntpoint);
+}
+
+static void setup_namespace(void)
+{
+	int ret;
+	char buf[32];
+	uid_t uid = getuid();
+	gid_t gid = getgid();
+
+	ret = unshare(CLONE_NEWNS|CLONE_NEWUSER);
+	if (ret == -1)
+		ksft_exit_fail_msg("unsharing mountns and userns: %s\n",
+				   strerror(errno));
+
+	sprintf(buf, "0 %d 1", uid);
+	write_file("/proc/self/uid_map", buf);
+	write_file("/proc/self/setgroups", "deny");
+	sprintf(buf, "0 %d 1", gid);
+	write_file("/proc/self/gid_map", buf);
+
+	ret = mount("", "/", NULL, MS_REC|MS_PRIVATE, NULL);
+	if (ret == -1)
+		ksft_exit_fail_msg("making mount tree private: %s\n",
+				   strerror(errno));
+
+	if (!mkdtemp(root_mntpoint))
+		ksft_exit_fail_msg("creating temporary directory %s: %s\n",
+				   root_mntpoint, strerror(errno));
+
+	old_parent_id = get_mnt_id("parent", root_mntpoint, STATX_MNT_ID);
+	parent_id = get_mnt_id("parent", root_mntpoint, STATX_MNT_ID_UNIQUE);
+
+	orig_root = open("/", O_PATH);
+	if (orig_root == -1)
+		ksft_exit_fail_msg("opening root directory: %s",
+				   strerror(errno));
+
+	atexit(cleanup_namespace);
+
+	ret = mount(root_mntpoint, root_mntpoint, NULL, MS_BIND, NULL);
+	if (ret == -1)
+		ksft_exit_fail_msg("mounting temp root %s: %s\n",
+				   root_mntpoint, strerror(errno));
+
+	ret = chroot(root_mntpoint);
+	if (ret == -1)
+		ksft_exit_fail_msg("chroot to temp root %s: %s\n",
+				   root_mntpoint, strerror(errno));
+
+	ret = chdir("/");
+	if (ret == -1)
+		ksft_exit_fail_msg("chdir to root: %s\n", strerror(errno));
+
+	old_root_id = get_mnt_id("root", "/", STATX_MNT_ID);
+	root_id = get_mnt_id("root", "/", STATX_MNT_ID_UNIQUE);
+}
+
+static int setup_mount_tree(int log2_num)
+{
+	int ret, i;
+
+	ret = mount("", "/", NULL, MS_REC|MS_SHARED, NULL);
+	if (ret == -1) {
+		ksft_test_result_fail("making mount tree shared: %s\n",
+				   strerror(errno));
+		return -1;
+	}
+
+	for (i = 0; i < log2_num; i++) {
+		ret = mount("/", "/", NULL, MS_BIND, NULL);
+		if (ret == -1) {
+			ksft_test_result_fail("mounting submount %s: %s\n",
+					      root_mntpoint, strerror(errno));
+			return -1;
+		}
+	}
+	return 0;
+}
+
+static ssize_t listmount(uint64_t mnt_id, uint64_t last_mnt_id,
+			 uint64_t list[], size_t num, unsigned int flags)
+{
+	struct mnt_id_req req = {
+		.size = MNT_ID_REQ_SIZE_VER0,
+		.mnt_id = mnt_id,
+		.param = last_mnt_id,
+	};
+
+	return syscall(__NR_listmount, &req, list, num, flags);
+}
+
+static void test_listmount_empty_root(void)
+{
+	ssize_t res;
+	const unsigned int size = 32;
+	uint64_t list[size];
+
+	res = listmount(LSMT_ROOT, 0, list, size, 0);
+	if (res == -1) {
+		ksft_test_result_fail("listmount: %s\n", strerror(errno));
+		return;
+	}
+	if (res != 1) {
+		ksft_test_result_fail("listmount result is %zi != 1\n", res);
+		return;
+	}
+
+	if (list[0] != root_id) {
+		ksft_test_result_fail("listmount ID doesn't match 0x%llx != 0x%llx\n",
+				      (unsigned long long) list[0],
+				      (unsigned long long) root_id);
+		return;
+	}
+
+	ksft_test_result_pass("listmount empty root\n");
+}
+
+static void test_statmount_zero_mask(void)
+{
+	struct statmount sm;
+	int ret;
+
+	ret = statmount(root_id, 0, &sm, sizeof(sm), 0);
+	if (ret == -1) {
+		ksft_test_result_fail("statmount zero mask: %s\n",
+				      strerror(errno));
+		return;
+	}
+	if (sm.size != sizeof(sm)) {
+		ksft_test_result_fail("unexpected size: %u != %u\n",
+				      sm.size, (uint32_t) sizeof(sm));
+		return;
+	}
+	if (sm.mask != 0) {
+		ksft_test_result_fail("unexpected mask: 0x%llx != 0x0\n",
+				      (unsigned long long) sm.mask);
+		return;
+	}
+
+	ksft_test_result_pass("statmount zero mask\n");
+}
+
+static void test_statmount_mnt_basic(void)
+{
+	struct statmount sm;
+	int ret;
+	uint64_t mask = STATMOUNT_MNT_BASIC;
+
+	ret = statmount(root_id, mask, &sm, sizeof(sm), 0);
+	if (ret == -1) {
+		ksft_test_result_fail("statmount mnt basic: %s\n",
+				      strerror(errno));
+		return;
+	}
+	if (sm.size != sizeof(sm)) {
+		ksft_test_result_fail("unexpected size: %u != %u\n",
+				      sm.size, (uint32_t) sizeof(sm));
+		return;
+	}
+	if (sm.mask != mask) {
+		ksft_test_result_skip("statmount mnt basic unavailable\n");
+		return;
+	}
+
+	if (sm.mnt_id != root_id) {
+		ksft_test_result_fail("unexpected root ID: 0x%llx != 0x%llx\n",
+				      (unsigned long long) sm.mnt_id,
+				      (unsigned long long) root_id);
+		return;
+	}
+
+	if (sm.mnt_id_old != old_root_id) {
+		ksft_test_result_fail("unexpected old root ID: %u != %u\n",
+				      sm.mnt_id_old, old_root_id);
+		return;
+	}
+
+	if (sm.mnt_parent_id != parent_id) {
+		ksft_test_result_fail("unexpected parent ID: 0x%llx != 0x%llx\n",
+				      (unsigned long long) sm.mnt_parent_id,
+				      (unsigned long long) parent_id);
+		return;
+	}
+
+	if (sm.mnt_parent_id_old != old_parent_id) {
+		ksft_test_result_fail("unexpected old parent ID: %u != %u\n",
+				      sm.mnt_parent_id_old, old_parent_id);
+		return;
+	}
+
+	if (sm.mnt_propagation != MS_PRIVATE) {
+		ksft_test_result_fail("unexpected propagation: 0x%llx\n",
+				      (unsigned long long) sm.mnt_propagation);
+		return;
+	}
+
+	ksft_test_result_pass("statmount mnt basic\n");
+}
+
+
+static void test_statmount_sb_basic(void)
+{
+	struct statmount sm;
+	int ret;
+	uint64_t mask = STATMOUNT_SB_BASIC;
+	struct statx sx;
+	struct statfs sf;
+
+	ret = statmount(root_id, mask, &sm, sizeof(sm), 0);
+	if (ret == -1) {
+		ksft_test_result_fail("statmount sb basic: %s\n",
+				      strerror(errno));
+		return;
+	}
+	if (sm.size != sizeof(sm)) {
+		ksft_test_result_fail("unexpected size: %u != %u\n",
+				      sm.size, (uint32_t) sizeof(sm));
+		return;
+	}
+	if (sm.mask != mask) {
+		ksft_test_result_skip("statmount sb basic unavailable\n");
+		return;
+	}
+
+	ret = statx(AT_FDCWD, "/", 0, 0, &sx);
+	if (ret == -1) {
+		ksft_test_result_fail("stat root failed: %s\n",
+				      strerror(errno));
+		return;
+	}
+
+	if (sm.sb_dev_major != sx.stx_dev_major ||
+	    sm.sb_dev_minor != sx.stx_dev_minor) {
+		ksft_test_result_fail("unexpected sb dev %u:%u != %u:%u\n",
+				      sm.sb_dev_major, sm.sb_dev_minor,
+				      sx.stx_dev_major, sx.stx_dev_minor);
+		return;
+	}
+
+	ret = statfs("/", &sf);
+	if (ret == -1) {
+		ksft_test_result_fail("statfs root failed: %s\n",
+				      strerror(errno));
+		return;
+	}
+
+	if (sm.sb_magic != sf.f_type) {
+		ksft_test_result_fail("unexpected sb magic: 0x%llx != 0x%lx\n",
+				      (unsigned long long) sm.sb_magic,
+				      sf.f_type);
+		return;
+	}
+
+	ksft_test_result_pass("statmount sb basic\n");
+}
+
+static void test_statmount_mnt_point(void)
+{
+	struct statmount *sm;
+
+	sm = statmount_alloc(root_id, STATMOUNT_MNT_POINT, 0);
+	if (!sm) {
+		ksft_test_result_fail("statmount mount point: %s\n",
+				      strerror(errno));
+		return;
+	}
+
+	if (strcmp(sm->str + sm->mnt_point, "/") != 0) {
+		ksft_test_result_fail("unexpected mount point: '%s' != '/'\n",
+				      sm->str + sm->mnt_point);
+		goto out;
+	}
+	ksft_test_result_pass("statmount mount point\n");
+out:
+	free(sm);
+}
+
+static void test_statmount_mnt_root(void)
+{
+	struct statmount *sm;
+	const char *mnt_root, *last_dir, *last_root;
+
+	last_dir = strrchr(root_mntpoint, '/');
+	assert(last_dir);
+	last_dir++;
+
+	sm = statmount_alloc(root_id, STATMOUNT_MNT_ROOT, 0);
+	if (!sm) {
+		ksft_test_result_fail("statmount mount root: %s\n",
+				      strerror(errno));
+		return;
+	}
+	mnt_root = sm->str + sm->mnt_root;
+	last_root = strrchr(mnt_root, '/');
+	if (last_root)
+		last_root++;
+	else
+		last_root = mnt_root;
+
+	if (strcmp(last_dir, last_root) != 0) {
+		ksft_test_result_fail("unexpected mount root last component: '%s' != '%s'\n",
+				      last_root, last_dir);
+		goto out;
+	}
+	ksft_test_result_pass("statmount mount root\n");
+out:
+	free(sm);
+}
+
+static void test_statmount_fs_type(void)
+{
+	struct statmount *sm;
+	const char *fs_type;
+	const char *const *s;
+
+	sm = statmount_alloc(root_id, STATMOUNT_FS_TYPE, 0);
+	if (!sm) {
+		ksft_test_result_fail("statmount fs type: %s\n",
+				      strerror(errno));
+		return;
+	}
+	fs_type = sm->str + sm->fs_type;
+	for (s = known_fs; s != NULL; s++) {
+		if (strcmp(fs_type, *s) == 0)
+			break;
+	}
+	if (!s)
+		ksft_print_msg("unknown filesystem type: %s\n", fs_type);
+
+	ksft_test_result_pass("statmount fs type\n");
+	free(sm);
+}
+
+static void test_statmount_string(uint64_t mask, size_t off, const char *name)
+{
+	struct statmount *sm;
+	size_t len, shortsize, exactsize;
+	uint32_t start, i;
+	int ret;
+
+	sm = statmount_alloc(root_id, mask, 0);
+	if (!sm) {
+		ksft_test_result_fail("statmount %s: %s\n", name,
+				      strerror(errno));
+		goto out;
+	}
+	if (sm->size < sizeof(*sm)) {
+		ksft_test_result_fail("unexpected size: %u < %u\n",
+				      sm->size, (uint32_t) sizeof(*sm));
+		goto out;
+	}
+	if (sm->mask != mask) {
+		ksft_test_result_skip("statmount %s unavailable\n", name);
+		goto out;
+	}
+	len = sm->size - sizeof(*sm);
+	start = ((uint32_t *) sm)[off];
+
+	for (i = start;; i++) {
+		if (i >= len) {
+			ksft_test_result_fail("string out of bounds\n");
+			goto out;
+		}
+		if (!sm->str[i])
+			break;
+	}
+	exactsize = sm->size;
+	shortsize = sizeof(*sm) + i;
+
+	ret = statmount(root_id, mask, sm, exactsize, 0);
+	if (ret == -1) {
+		ksft_test_result_fail("statmount exact size: %s\n",
+				      strerror(errno));
+		goto out;
+	}
+	errno = 0;
+	ret = statmount(root_id, mask, sm, shortsize, 0);
+	if (ret != -1 || errno != EOVERFLOW) {
+		ksft_test_result_fail("should have failed with EOVERFLOW: %s\n",
+				      strerror(errno));
+		goto out;
+	}
+
+	ksft_test_result_pass("statmount string %s\n", name);
+out:
+	free(sm);
+}
+
+static void test_listmount_tree(void)
+{
+	ssize_t res;
+	const unsigned int log2_num = 4;
+	const unsigned int step = 3;
+	const unsigned int size = (1 << log2_num) + step + 1;
+	size_t num, expect = 1 << log2_num;
+	uint64_t list[size];
+	uint64_t list2[size];
+	size_t i;
+
+
+	res = setup_mount_tree(log2_num);
+	if (res == -1)
+		return;
+
+	num = res = listmount(LSMT_ROOT, 0, list, size, 0);
+	if (res == -1) {
+		ksft_test_result_fail("listmount: %s\n", strerror(errno));
+		return;
+	}
+	if (num != expect) {
+		ksft_test_result_fail("listmount result is %zi != %zi\n",
+				      res, expect);
+		return;
+	}
+
+	for (i = 0; i < size - step;) {
+		res = listmount(LSMT_ROOT, i ? list2[i - 1] : 0, list2 + i, step, 0);
+		if (res == -1)
+			ksft_test_result_fail("short listmount: %s\n",
+					      strerror(errno));
+		i += res;
+		if (res < step)
+			break;
+	}
+	if (i != num) {
+		ksft_test_result_fail("different number of entries: %zu != %zu\n",
+				      i, num);
+		return;
+	}
+	for (i = 0; i < num; i++) {
+		if (list2[i] != list[i]) {
+			ksft_test_result_fail("different value for entry %zu: 0x%llx != 0x%llx\n",
+					      i,
+					      (unsigned long long) list2[i],
+					      (unsigned long long) list[i]);
+		}
+	}
+
+	ksft_test_result_pass("listmount tree\n");
+}
+
+#define str_off(memb) (offsetof(struct statmount, memb) / sizeof(uint32_t))
+
+int main(void)
+{
+	int ret;
+	uint64_t all_mask = STATMOUNT_SB_BASIC | STATMOUNT_MNT_BASIC |
+		STATMOUNT_PROPAGATE_FROM | STATMOUNT_MNT_ROOT |
+		STATMOUNT_MNT_POINT | STATMOUNT_FS_TYPE;
+
+	ksft_print_header();
+
+	ret = statmount(0, 0, NULL, 0, 0);
+	assert(ret == -1);
+	if (errno == ENOSYS)
+		ksft_exit_skip("statmount() syscall not supported\n");
+
+	setup_namespace();
+
+	ksft_set_plan(14);
+	test_listmount_empty_root();
+	test_statmount_zero_mask();
+	test_statmount_mnt_basic();
+	test_statmount_sb_basic();
+	test_statmount_mnt_root();
+	test_statmount_mnt_point();
+	test_statmount_fs_type();
+	test_statmount_string(STATMOUNT_MNT_ROOT, str_off(mnt_root), "mount root");
+	test_statmount_string(STATMOUNT_MNT_POINT, str_off(mnt_point), "mount point");
+	test_statmount_string(STATMOUNT_FS_TYPE, str_off(fs_type), "fs type");
+	test_statmount_string(all_mask, str_off(mnt_root), "mount root & all");
+	test_statmount_string(all_mask, str_off(mnt_point), "mount point & all");
+	test_statmount_string(all_mask, str_off(fs_type), "fs type & all");
+
+	test_listmount_tree();
+
+
+	if (ksft_get_fail_cnt() + ksft_get_error_cnt() > 0)
+		ksft_exit_fail();
+	else
+		ksft_exit_pass();
+}
diff --git a/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc b/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc
new file mode 100644
index 000000000000..add7d5bf585d
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc
@@ -0,0 +1,114 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Test file and directory owership changes for eventfs
+
+original_group=`stat -c "%g" .`
+original_owner=`stat -c "%u" .`
+
+mount_point=`stat -c '%m' .`
+mount_options=`mount | grep "$mount_point" | sed -e 's/.*(\(.*\)).*/\1/'`
+
+# find another owner and group that is not the original
+other_group=`tac /etc/group | grep -v ":$original_group:" | head -1 | cut -d: -f3`
+other_owner=`tac /etc/passwd | grep -v ":$original_owner:" | head -1 | cut -d: -f3`
+
+# Remove any group ownership already
+new_options=`echo "$mount_options" | sed -e "s/gid=[0-9]*/gid=$other_group/"`
+
+if [ "$new_options" = "$mount_options" ]; then
+	new_options="$mount_options,gid=$other_group"
+	mount_options="$mount_options,gid=$original_group"
+fi
+
+canary="events/timer events/timer/timer_cancel events/timer/timer_cancel/format"
+
+test() {
+	file=$1
+	test_group=$2
+
+	owner=`stat -c "%u" $file`
+	group=`stat -c "%g" $file`
+
+	echo "testing $file $owner=$original_owner and $group=$test_group"
+	if [ $owner -ne $original_owner ]; then
+		exit_fail
+	fi
+	if [ $group -ne $test_group ]; then
+		exit_fail
+	fi
+
+	# Note, the remount does not update ownership so test going to and from owner
+	echo "test owner $file to $other_owner"
+	chown $other_owner $file
+	owner=`stat -c "%u" $file`
+	if [ $owner -ne $other_owner ]; then
+		exit_fail
+	fi
+
+	chown $original_owner $file
+	owner=`stat -c "%u" $file`
+	if [ $owner -ne $original_owner ]; then
+		exit_fail
+	fi
+
+}
+
+run_tests() {
+	for d in "." "events" "events/sched" "events/sched/sched_switch" "events/sched/sched_switch/enable" $canary; do
+		test "$d" $other_group
+	done
+
+	chgrp $original_group events
+	test "events" $original_group
+	for d in "." "events/sched" "events/sched/sched_switch" "events/sched/sched_switch/enable" $canary; do
+		test "$d" $other_group
+	done
+
+	chgrp $original_group events/sched
+	test "events/sched" $original_group
+	for d in "." "events/sched/sched_switch" "events/sched/sched_switch/enable" $canary; do
+		test "$d" $other_group
+	done
+
+	chgrp $original_group events/sched/sched_switch
+	test "events/sched/sched_switch" $original_group
+	for d in "." "events/sched/sched_switch/enable" $canary; do
+		test "$d" $other_group
+	done
+
+	chgrp $original_group events/sched/sched_switch/enable
+	test "events/sched/sched_switch/enable" $original_group
+	for d in "." $canary; do
+		test "$d" $other_group
+	done
+}
+
+mount -o remount,"$new_options" .
+
+run_tests
+
+mount -o remount,"$mount_options" .
+
+for d in "." "events" "events/sched" "events/sched/sched_switch" "events/sched/sched_switch/enable" $canary; do
+	test "$d" $original_group
+done
+
+# check instances as well
+
+chgrp $other_group instances
+
+instance="$(mktemp -u test-XXXXXX)"
+
+mkdir instances/$instance
+
+cd instances/$instance
+
+run_tests
+
+cd ../..
+
+rmdir instances/$instance
+
+chgrp $original_group instances
+
+exit 0
diff --git a/tools/testing/selftests/hid/config b/tools/testing/selftests/hid/config
index 4f425178b56f..1758b055f295 100644
--- a/tools/testing/selftests/hid/config
+++ b/tools/testing/selftests/hid/config
@@ -1,5 +1,4 @@
 CONFIG_BPF_EVENTS=y
-CONFIG_BPFILTER=y
 CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_JIT=y
 CONFIG_BPF_KPROBE_OVERRIDE=y
diff --git a/tools/testing/selftests/hid/config.common b/tools/testing/selftests/hid/config.common
index 0617275d93cc..0f456dbab62f 100644
--- a/tools/testing/selftests/hid/config.common
+++ b/tools/testing/selftests/hid/config.common
@@ -46,7 +46,6 @@ CONFIG_CRYPTO_SEQIV=y
 CONFIG_CRYPTO_XXHASH=y
 CONFIG_DCB=y
 CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_DEBUG_CREDENTIALS=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_DEBUG_MEMORY_INIT=y
 CONFIG_DEFAULT_FQ_CODEL=y
diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h
index 050e9751321c..ad9202335656 100644
--- a/tools/testing/selftests/iommu/iommufd_utils.h
+++ b/tools/testing/selftests/iommu/iommufd_utils.h
@@ -293,15 +293,13 @@ static int _test_mock_dirty_bitmaps(int fd, __u32 hwpt_id, size_t length,
 				    __u64 bitmap_size, __u32 flags,
 				    struct __test_metadata *_metadata)
 {
-	unsigned long i, count, nbits = bitmap_size * BITS_PER_BYTE;
+	unsigned long i, nbits = bitmap_size * BITS_PER_BYTE;
 	unsigned long nr = nbits / 2;
 	__u64 out_dirty = 0;
 
 	/* Mark all even bits as dirty in the mock domain */
-	for (count = 0, i = 0; i < nbits; count += !(i % 2), i++)
-		if (!(i % 2))
-			set_bit(i, (unsigned long *)bitmap);
-	ASSERT_EQ(nr, count);
+	for (i = 0; i < nbits; i += 2)
+		set_bit(i, (unsigned long *)bitmap);
 
 	test_cmd_mock_domain_set_dirty(fd, hwpt_id, length, iova, page_size,
 				       bitmap, &out_dirty);
@@ -311,9 +309,10 @@ static int _test_mock_dirty_bitmaps(int fd, __u32 hwpt_id, size_t length,
 	memset(bitmap, 0, bitmap_size);
 	test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, page_size, bitmap,
 				  flags);
-	for (count = 0, i = 0; i < nbits; count += !(i % 2), i++)
+	/* Beware ASSERT_EQ() is two statements -- braces are not redundant! */
+	for (i = 0; i < nbits; i++) {
 		ASSERT_EQ(!(i % 2), test_bit(i, (unsigned long *)bitmap));
-	ASSERT_EQ(count, out_dirty);
+	}
 
 	memset(bitmap, 0, bitmap_size);
 	test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, page_size, bitmap,
diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh
index cd2fb43eea61..74954f6a8f94 100644
--- a/tools/testing/selftests/kselftest/runner.sh
+++ b/tools/testing/selftests/kselftest/runner.sh
@@ -6,6 +6,7 @@ export skip_rc=4
 export timeout_rc=124
 export logfile=/dev/stdout
 export per_test_logging=
+export RUN_IN_NETNS=
 
 # Defaults for "settings" file fields:
 # "timeout" how many seconds to let each test run before running
@@ -47,7 +48,7 @@ run_one()
 {
 	DIR="$1"
 	TEST="$2"
-	NUM="$3"
+	local test_num="$3"
 
 	BASENAME_TEST=$(basename $TEST)
 
@@ -141,6 +142,33 @@ run_one()
 	fi
 }
 
+in_netns()
+{
+	local name=$1
+	ip netns exec $name bash <<-EOF
+		BASE_DIR=$BASE_DIR
+		source $BASE_DIR/kselftest/runner.sh
+		logfile=$logfile
+		run_one $DIR $TEST $test_num
+	EOF
+}
+
+run_in_netns()
+{
+	local netns=$(mktemp -u ${BASENAME_TEST}-XXXXXX)
+	local tmplog="/tmp/$(mktemp -u ${BASENAME_TEST}-XXXXXX)"
+	ip netns add $netns
+	if [ $? -ne 0 ]; then
+		echo "# Warning: Create namespace failed for $BASENAME_TEST"
+		echo "not ok $test_num selftests: $DIR: $BASENAME_TEST # Create NS failed"
+	fi
+	ip -n $netns link set lo up
+	in_netns $netns &> $tmplog
+	ip netns del $netns &> /dev/null
+	cat $tmplog
+	rm -f $tmplog
+}
+
 run_many()
 {
 	echo "TAP version 13"
@@ -155,6 +183,12 @@ run_many()
 			logfile="/tmp/$BASENAME_TEST"
 			cat /dev/null > "$logfile"
 		fi
-		run_one "$DIR" "$TEST" "$test_num"
+		if [ -n "$RUN_IN_NETNS" ]; then
+			run_in_netns &
+		else
+			run_one "$DIR" "$TEST" "$test_num"
+		fi
 	done
+
+	wait
 }
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index a5963ab9215b..3e0c36b8ddd5 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -17,15 +17,6 @@ else
 	ARCH_DIR := $(ARCH)
 endif
 
-ifeq ($(ARCH),arm64)
-arm64_tools_dir := $(top_srcdir)/tools/arch/arm64/tools/
-GEN_HDRS := $(top_srcdir)/tools/arch/arm64/include/generated/
-CFLAGS += -I$(GEN_HDRS)
-
-$(GEN_HDRS): $(wildcard $(arm64_tools_dir)/*)
-	$(MAKE) -C $(arm64_tools_dir)
-endif
-
 LIBKVM += lib/assert.c
 LIBKVM += lib/elf.c
 LIBKVM += lib/guest_modes.c
@@ -223,7 +214,7 @@ else
 LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include
 endif
 CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
-	-Wno-gnu-variable-sized-type-not-at-end -MD\
+	-Wno-gnu-variable-sized-type-not-at-end -MD -MP \
 	-fno-builtin-memcmp -fno-builtin-memcpy -fno-builtin-memset \
 	-fno-builtin-strnlen \
 	-fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \
@@ -233,6 +224,22 @@ CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
 ifeq ($(ARCH),s390)
 	CFLAGS += -march=z10
 endif
+ifeq ($(ARCH),arm64)
+tools_dir := $(top_srcdir)/tools
+arm64_tools_dir := $(tools_dir)/arch/arm64/tools/
+
+ifneq ($(abs_objdir),)
+arm64_hdr_outdir := $(abs_objdir)/tools/
+else
+arm64_hdr_outdir := $(tools_dir)/
+endif
+
+GEN_HDRS := $(arm64_hdr_outdir)arch/arm64/include/generated/
+CFLAGS += -I$(GEN_HDRS)
+
+$(GEN_HDRS): $(wildcard $(arm64_tools_dir)/*)
+	$(MAKE) -C $(arm64_tools_dir) OUTPUT=$(arm64_hdr_outdir)
+endif
 
 no-pie-option := $(call try-run, echo 'int main(void) { return 0; }' | \
         $(CC) -Werror $(CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie)
diff --git a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
index 5ea78986e665..9d51b5691349 100644
--- a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
+++ b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
@@ -42,13 +42,12 @@ struct pmreg_sets {
 
 static uint64_t get_pmcr_n(uint64_t pmcr)
 {
-	return (pmcr >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK;
+	return FIELD_GET(ARMV8_PMU_PMCR_N, pmcr);
 }
 
 static void set_pmcr_n(uint64_t *pmcr, uint64_t pmcr_n)
 {
-	*pmcr = *pmcr & ~(ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT);
-	*pmcr |= (pmcr_n << ARMV8_PMU_PMCR_N_SHIFT);
+	u64p_replace_bits((__u64 *) pmcr, pmcr_n, ARMV8_PMU_PMCR_N);
 }
 
 static uint64_t get_counters_mask(uint64_t n)
diff --git a/tools/testing/selftests/kvm/get-reg-list.c b/tools/testing/selftests/kvm/get-reg-list.c
index be7bf5224434..8274ef04301f 100644
--- a/tools/testing/selftests/kvm/get-reg-list.c
+++ b/tools/testing/selftests/kvm/get-reg-list.c
@@ -71,11 +71,12 @@ static const char *config_name(struct vcpu_reg_list *c)
 	for_each_sublist(c, s) {
 		if (!strcmp(s->name, "base"))
 			continue;
-		strcat(c->name + len, s->name);
-		len += strlen(s->name) + 1;
-		c->name[len - 1] = '+';
+		if (len)
+			c->name[len++] = '+';
+		strcpy(c->name + len, s->name);
+		len += strlen(s->name);
 	}
-	c->name[len - 1] = '\0';
+	c->name[len] = '\0';
 
 	return c->name;
 }
diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 6bedaea95395..25de4b8bc347 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -458,8 +458,9 @@ void print_reg(const char *prefix, __u64 id)
 		reg_size = "KVM_REG_SIZE_U128";
 		break;
 	default:
-		printf("\tKVM_REG_RISCV | (%lld << KVM_REG_SIZE_SHIFT) | 0x%llx /* UNKNOWN */,",
-		       (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id & REG_MASK);
+		printf("\tKVM_REG_RISCV | (%lld << KVM_REG_SIZE_SHIFT) | 0x%llx /* UNKNOWN */,\n",
+		       (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id & ~REG_MASK);
+		return;
 	}
 
 	switch (id & KVM_REG_RISCV_TYPE_MASK) {
@@ -496,8 +497,9 @@ void print_reg(const char *prefix, __u64 id)
 				reg_size, sbi_ext_id_to_str(prefix, id));
 		break;
 	default:
-		printf("\tKVM_REG_RISCV | %s | 0x%llx /* UNKNOWN */,",
-				reg_size, id & REG_MASK);
+		printf("\tKVM_REG_RISCV | %s | 0x%llx /* UNKNOWN */,\n",
+				reg_size, id & ~REG_MASK);
+		return;
 	}
 }
 
diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
index 18ac5c1952a3..83e25bccc139 100644
--- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
+++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
@@ -259,7 +259,7 @@ int main(int argc, char **argv)
 	__TEST_REQUIRE(token == MAGIC_TOKEN,
 		       "This test must be run with the magic token %d.\n"
 		       "This is done by nx_huge_pages_test.sh, which\n"
-		       "also handles environment setup for the test.");
+		       "also handles environment setup for the test.", MAGIC_TOKEN);
 
 	run_test(reclaim_period_ms, false, reboot_permissions);
 	run_test(reclaim_period_ms, true, reboot_permissions);
diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c
index 18e1f86a6234..50818904397c 100644
--- a/tools/testing/selftests/landlock/fs_test.c
+++ b/tools/testing/selftests/landlock/fs_test.c
@@ -589,7 +589,7 @@ TEST_F_FORK(layout1, file_and_dir_access_rights)
 	ASSERT_EQ(0, close(ruleset_fd));
 }
 
-TEST_F_FORK(layout0, unknown_access_rights)
+TEST_F_FORK(layout0, ruleset_with_unknown_access)
 {
 	__u64 access_mask;
 
@@ -605,6 +605,67 @@ TEST_F_FORK(layout0, unknown_access_rights)
 	}
 }
 
+TEST_F_FORK(layout0, rule_with_unknown_access)
+{
+	__u64 access;
+	struct landlock_path_beneath_attr path_beneath = {};
+	const struct landlock_ruleset_attr ruleset_attr = {
+		.handled_access_fs = ACCESS_ALL,
+	};
+	const int ruleset_fd =
+		landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
+
+	ASSERT_LE(0, ruleset_fd);
+
+	path_beneath.parent_fd =
+		open(TMP_DIR, O_PATH | O_DIRECTORY | O_CLOEXEC);
+	ASSERT_LE(0, path_beneath.parent_fd);
+
+	for (access = 1ULL << 63; access != ACCESS_LAST; access >>= 1) {
+		path_beneath.allowed_access = access;
+		EXPECT_EQ(-1, landlock_add_rule(ruleset_fd,
+						LANDLOCK_RULE_PATH_BENEATH,
+						&path_beneath, 0));
+		EXPECT_EQ(EINVAL, errno);
+	}
+	ASSERT_EQ(0, close(path_beneath.parent_fd));
+	ASSERT_EQ(0, close(ruleset_fd));
+}
+
+TEST_F_FORK(layout1, rule_with_unhandled_access)
+{
+	struct landlock_ruleset_attr ruleset_attr = {
+		.handled_access_fs = LANDLOCK_ACCESS_FS_EXECUTE,
+	};
+	struct landlock_path_beneath_attr path_beneath = {};
+	int ruleset_fd;
+	__u64 access;
+
+	ruleset_fd =
+		landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
+	ASSERT_LE(0, ruleset_fd);
+
+	path_beneath.parent_fd = open(file1_s1d2, O_PATH | O_CLOEXEC);
+	ASSERT_LE(0, path_beneath.parent_fd);
+
+	for (access = 1; access > 0; access <<= 1) {
+		int err;
+
+		path_beneath.allowed_access = access;
+		err = landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
+					&path_beneath, 0);
+		if (access == ruleset_attr.handled_access_fs) {
+			EXPECT_EQ(0, err);
+		} else {
+			EXPECT_EQ(-1, err);
+			EXPECT_EQ(EINVAL, errno);
+		}
+	}
+
+	EXPECT_EQ(0, close(path_beneath.parent_fd));
+	EXPECT_EQ(0, close(ruleset_fd));
+}
+
 static void add_path_beneath(struct __test_metadata *const _metadata,
 			     const int ruleset_fd, const __u64 allowed_access,
 			     const char *const path)
@@ -3627,7 +3688,7 @@ FIXTURE_TEARDOWN(ftruncate)
 FIXTURE_VARIANT(ftruncate)
 {
 	const __u64 handled;
-	const __u64 permitted;
+	const __u64 allowed;
 	const int expected_open_result;
 	const int expected_ftruncate_result;
 };
@@ -3636,7 +3697,7 @@ FIXTURE_VARIANT(ftruncate)
 FIXTURE_VARIANT_ADD(ftruncate, w_w) {
 	/* clang-format on */
 	.handled = LANDLOCK_ACCESS_FS_WRITE_FILE,
-	.permitted = LANDLOCK_ACCESS_FS_WRITE_FILE,
+	.allowed = LANDLOCK_ACCESS_FS_WRITE_FILE,
 	.expected_open_result = 0,
 	.expected_ftruncate_result = 0,
 };
@@ -3645,7 +3706,7 @@ FIXTURE_VARIANT_ADD(ftruncate, w_w) {
 FIXTURE_VARIANT_ADD(ftruncate, t_t) {
 	/* clang-format on */
 	.handled = LANDLOCK_ACCESS_FS_TRUNCATE,
-	.permitted = LANDLOCK_ACCESS_FS_TRUNCATE,
+	.allowed = LANDLOCK_ACCESS_FS_TRUNCATE,
 	.expected_open_result = 0,
 	.expected_ftruncate_result = 0,
 };
@@ -3654,7 +3715,7 @@ FIXTURE_VARIANT_ADD(ftruncate, t_t) {
 FIXTURE_VARIANT_ADD(ftruncate, wt_w) {
 	/* clang-format on */
 	.handled = LANDLOCK_ACCESS_FS_WRITE_FILE | LANDLOCK_ACCESS_FS_TRUNCATE,
-	.permitted = LANDLOCK_ACCESS_FS_WRITE_FILE,
+	.allowed = LANDLOCK_ACCESS_FS_WRITE_FILE,
 	.expected_open_result = 0,
 	.expected_ftruncate_result = EACCES,
 };
@@ -3663,8 +3724,7 @@ FIXTURE_VARIANT_ADD(ftruncate, wt_w) {
 FIXTURE_VARIANT_ADD(ftruncate, wt_wt) {
 	/* clang-format on */
 	.handled = LANDLOCK_ACCESS_FS_WRITE_FILE | LANDLOCK_ACCESS_FS_TRUNCATE,
-	.permitted = LANDLOCK_ACCESS_FS_WRITE_FILE |
-		     LANDLOCK_ACCESS_FS_TRUNCATE,
+	.allowed = LANDLOCK_ACCESS_FS_WRITE_FILE | LANDLOCK_ACCESS_FS_TRUNCATE,
 	.expected_open_result = 0,
 	.expected_ftruncate_result = 0,
 };
@@ -3673,7 +3733,7 @@ FIXTURE_VARIANT_ADD(ftruncate, wt_wt) {
 FIXTURE_VARIANT_ADD(ftruncate, wt_t) {
 	/* clang-format on */
 	.handled = LANDLOCK_ACCESS_FS_WRITE_FILE | LANDLOCK_ACCESS_FS_TRUNCATE,
-	.permitted = LANDLOCK_ACCESS_FS_TRUNCATE,
+	.allowed = LANDLOCK_ACCESS_FS_TRUNCATE,
 	.expected_open_result = EACCES,
 };
 
@@ -3683,7 +3743,7 @@ TEST_F_FORK(ftruncate, open_and_ftruncate)
 	const struct rule rules[] = {
 		{
 			.path = path,
-			.access = variant->permitted,
+			.access = variant->allowed,
 		},
 		{},
 	};
@@ -3724,7 +3784,7 @@ TEST_F_FORK(ftruncate, open_and_ftruncate_in_different_processes)
 		const struct rule rules[] = {
 			{
 				.path = path,
-				.access = variant->permitted,
+				.access = variant->allowed,
 			},
 			{},
 		};
diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c
index 929e21c4db05..ea5f727dd257 100644
--- a/tools/testing/selftests/landlock/net_test.c
+++ b/tools/testing/selftests/landlock/net_test.c
@@ -1260,7 +1260,7 @@ TEST_F(mini, network_access_rights)
 }
 
 /* Checks invalid attribute, out of landlock network access range. */
-TEST_F(mini, unknown_access_rights)
+TEST_F(mini, ruleset_with_unknown_access)
 {
 	__u64 access_mask;
 
@@ -1276,6 +1276,63 @@ TEST_F(mini, unknown_access_rights)
 	}
 }
 
+TEST_F(mini, rule_with_unknown_access)
+{
+	const struct landlock_ruleset_attr ruleset_attr = {
+		.handled_access_net = ACCESS_ALL,
+	};
+	struct landlock_net_port_attr net_port = {
+		.port = sock_port_start,
+	};
+	int ruleset_fd;
+	__u64 access;
+
+	ruleset_fd =
+		landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
+	ASSERT_LE(0, ruleset_fd);
+
+	for (access = 1ULL << 63; access != ACCESS_LAST; access >>= 1) {
+		net_port.allowed_access = access;
+		EXPECT_EQ(-1,
+			  landlock_add_rule(ruleset_fd, LANDLOCK_RULE_NET_PORT,
+					    &net_port, 0));
+		EXPECT_EQ(EINVAL, errno);
+	}
+	EXPECT_EQ(0, close(ruleset_fd));
+}
+
+TEST_F(mini, rule_with_unhandled_access)
+{
+	struct landlock_ruleset_attr ruleset_attr = {
+		.handled_access_net = LANDLOCK_ACCESS_NET_BIND_TCP,
+	};
+	struct landlock_net_port_attr net_port = {
+		.port = sock_port_start,
+	};
+	int ruleset_fd;
+	__u64 access;
+
+	ruleset_fd =
+		landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
+	ASSERT_LE(0, ruleset_fd);
+
+	for (access = 1; access > 0; access <<= 1) {
+		int err;
+
+		net_port.allowed_access = access;
+		err = landlock_add_rule(ruleset_fd, LANDLOCK_RULE_NET_PORT,
+					&net_port, 0);
+		if (access == ruleset_attr.handled_access_net) {
+			EXPECT_EQ(0, err);
+		} else {
+			EXPECT_EQ(-1, err);
+			EXPECT_EQ(EINVAL, errno);
+		}
+	}
+
+	EXPECT_EQ(0, close(ruleset_fd));
+}
+
 TEST_F(mini, inval)
 {
 	const struct landlock_ruleset_attr ruleset_attr = {
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 118e0964bda9..aa646e0661f3 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -44,26 +44,10 @@ endif
 selfdir = $(realpath $(dir $(filter %/lib.mk,$(MAKEFILE_LIST))))
 top_srcdir = $(selfdir)/../../..
 
-ifeq ("$(origin O)", "command line")
-  KBUILD_OUTPUT := $(O)
+ifeq ($(KHDR_INCLUDES),)
+KHDR_INCLUDES := -isystem $(top_srcdir)/usr/include
 endif
 
-ifneq ($(KBUILD_OUTPUT),)
-  # Make's built-in functions such as $(abspath ...), $(realpath ...) cannot
-  # expand a shell special character '~'. We use a somewhat tedious way here.
-  abs_objtree := $(shell cd $(top_srcdir) && mkdir -p $(KBUILD_OUTPUT) && cd $(KBUILD_OUTPUT) && pwd)
-  $(if $(abs_objtree),, \
-    $(error failed to create output directory "$(KBUILD_OUTPUT)"))
-  # $(realpath ...) resolves symlinks
-  abs_objtree := $(realpath $(abs_objtree))
-  KHDR_DIR := ${abs_objtree}/usr/include
-else
-  abs_srctree := $(shell cd $(top_srcdir) && pwd)
-  KHDR_DIR := ${abs_srctree}/usr/include
-endif
-
-KHDR_INCLUDES := -isystem $(KHDR_DIR)
-
 # The following are built by lib.mk common compile rules.
 # TEST_CUSTOM_PROGS should be used by tests that require
 # custom build rule and prevent common build rule use.
@@ -74,25 +58,7 @@ TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS))
 TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED))
 TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES))
 
-all: kernel_header_files $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) \
-     $(TEST_GEN_FILES)
-
-kernel_header_files:
-	@ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null;                      \
-	if [ $$? -ne 0 ]; then                                                 \
-            RED='\033[1;31m';                                                  \
-            NOCOLOR='\033[0m';                                                 \
-            echo;                                                              \
-            echo -e "$${RED}error$${NOCOLOR}: missing kernel header files.";   \
-            echo "Please run this and try again:";                             \
-            echo;                                                              \
-            echo "    cd $(top_srcdir)";                                       \
-            echo "    make headers";                                           \
-            echo;                                                              \
-	    exit 1; \
-	fi
-
-.PHONY: kernel_header_files
+all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
 
 define RUN_TESTS
 	BASE_DIR="$(selfdir)";			\
diff --git a/tools/testing/selftests/lsm/.gitignore b/tools/testing/selftests/lsm/.gitignore
new file mode 100644
index 000000000000..bd68f6c3fd07
--- /dev/null
+++ b/tools/testing/selftests/lsm/.gitignore
@@ -0,0 +1 @@
+/*_test
diff --git a/tools/testing/selftests/lsm/Makefile b/tools/testing/selftests/lsm/Makefile
new file mode 100644
index 000000000000..3f80c0bc093d
--- /dev/null
+++ b/tools/testing/selftests/lsm/Makefile
@@ -0,0 +1,17 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# First run: make -C ../../../.. headers_install
+
+CFLAGS += -Wall -O2 $(KHDR_INCLUDES)
+LOCAL_HDRS += common.h
+
+TEST_GEN_PROGS := lsm_get_self_attr_test lsm_list_modules_test \
+		  lsm_set_self_attr_test
+
+include ../lib.mk
+
+$(OUTPUT)/lsm_get_self_attr_test: lsm_get_self_attr_test.c common.c
+$(OUTPUT)/lsm_set_self_attr_test: lsm_set_self_attr_test.c common.c
+$(OUTPUT)/lsm_list_modules_test: lsm_list_modules_test.c common.c
+
+EXTRA_CLEAN = $(OUTPUT)/common.o
diff --git a/tools/testing/selftests/lsm/common.c b/tools/testing/selftests/lsm/common.c
new file mode 100644
index 000000000000..9ad258912646
--- /dev/null
+++ b/tools/testing/selftests/lsm/common.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Linux Security Module infrastructure tests
+ *
+ * Copyright © 2023 Casey Schaufler <casey@schaufler-ca.com>
+ */
+
+#define _GNU_SOURCE
+#include <linux/lsm.h>
+#include <fcntl.h>
+#include <string.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include "common.h"
+
+#define PROCATTR "/proc/self/attr/"
+
+int read_proc_attr(const char *attr, char *value, size_t size)
+{
+	int fd;
+	int len;
+	char *path;
+
+	len = strlen(PROCATTR) + strlen(attr) + 1;
+	path = calloc(len, 1);
+	if (path == NULL)
+		return -1;
+	sprintf(path, "%s%s", PROCATTR, attr);
+
+	fd = open(path, O_RDONLY);
+	free(path);
+
+	if (fd < 0)
+		return -1;
+	len = read(fd, value, size);
+
+	close(fd);
+
+	/* Ensure value is terminated */
+	if (len <= 0 || len == size)
+		return -1;
+	value[len] = '\0';
+
+	path = strchr(value, '\n');
+	if (path)
+		*path = '\0';
+
+	return 0;
+}
+
+int read_sysfs_lsms(char *lsms, size_t size)
+{
+	FILE *fp;
+	size_t red;
+
+	fp = fopen("/sys/kernel/security/lsm", "r");
+	if (fp == NULL)
+		return -1;
+	red = fread(lsms, 1, size, fp);
+	fclose(fp);
+
+	if (red <= 0 || red == size)
+		return -1;
+	lsms[red] = '\0';
+	return 0;
+}
+
+int attr_lsm_count(void)
+{
+	char *names = calloc(sysconf(_SC_PAGESIZE), 1);
+	int count = 0;
+
+	if (!names)
+		return 0;
+
+	if (read_sysfs_lsms(names, sysconf(_SC_PAGESIZE)))
+		return 0;
+
+	if (strstr(names, "selinux"))
+		count++;
+	if (strstr(names, "smack"))
+		count++;
+	if (strstr(names, "apparmor"))
+		count++;
+
+	return count;
+}
diff --git a/tools/testing/selftests/lsm/common.h b/tools/testing/selftests/lsm/common.h
new file mode 100644
index 000000000000..d404329e5eeb
--- /dev/null
+++ b/tools/testing/selftests/lsm/common.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Linux Security Module infrastructure tests
+ *
+ * Copyright © 2023 Casey Schaufler <casey@schaufler-ca.com>
+ */
+
+#ifndef lsm_get_self_attr
+static inline int lsm_get_self_attr(unsigned int attr, struct lsm_ctx *ctx,
+				    size_t *size, __u32 flags)
+{
+	return syscall(__NR_lsm_get_self_attr, attr, ctx, size, flags);
+}
+#endif
+
+#ifndef lsm_set_self_attr
+static inline int lsm_set_self_attr(unsigned int attr, struct lsm_ctx *ctx,
+				    size_t size, __u32 flags)
+{
+	return syscall(__NR_lsm_set_self_attr, attr, ctx, size, flags);
+}
+#endif
+
+#ifndef lsm_list_modules
+static inline int lsm_list_modules(__u64 *ids, size_t *size, __u32 flags)
+{
+	return syscall(__NR_lsm_list_modules, ids, size, flags);
+}
+#endif
+
+extern int read_proc_attr(const char *attr, char *value, size_t size);
+extern int read_sysfs_lsms(char *lsms, size_t size);
+int attr_lsm_count(void);
diff --git a/tools/testing/selftests/lsm/config b/tools/testing/selftests/lsm/config
new file mode 100644
index 000000000000..1c0c4c020f9c
--- /dev/null
+++ b/tools/testing/selftests/lsm/config
@@ -0,0 +1,3 @@
+CONFIG_SYSFS=y
+CONFIG_SECURITY=y
+CONFIG_SECURITYFS=y
diff --git a/tools/testing/selftests/lsm/lsm_get_self_attr_test.c b/tools/testing/selftests/lsm/lsm_get_self_attr_test.c
new file mode 100644
index 000000000000..e0e313d9047a
--- /dev/null
+++ b/tools/testing/selftests/lsm/lsm_get_self_attr_test.c
@@ -0,0 +1,275 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Linux Security Module infrastructure tests
+ * Tests for the lsm_get_self_attr system call
+ *
+ * Copyright © 2022 Casey Schaufler <casey@schaufler-ca.com>
+ */
+
+#define _GNU_SOURCE
+#include <linux/lsm.h>
+#include <fcntl.h>
+#include <string.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include "../kselftest_harness.h"
+#include "common.h"
+
+static struct lsm_ctx *next_ctx(struct lsm_ctx *ctxp)
+{
+	void *vp;
+
+	vp = (void *)ctxp + sizeof(*ctxp) + ctxp->ctx_len;
+	return (struct lsm_ctx *)vp;
+}
+
+TEST(size_null_lsm_get_self_attr)
+{
+	const long page_size = sysconf(_SC_PAGESIZE);
+	struct lsm_ctx *ctx = calloc(page_size, 1);
+
+	ASSERT_NE(NULL, ctx);
+	errno = 0;
+	ASSERT_EQ(-1, lsm_get_self_attr(LSM_ATTR_CURRENT, ctx, NULL, 0));
+	ASSERT_EQ(EINVAL, errno);
+
+	free(ctx);
+}
+
+TEST(ctx_null_lsm_get_self_attr)
+{
+	const long page_size = sysconf(_SC_PAGESIZE);
+	size_t size = page_size;
+	int rc;
+
+	rc = lsm_get_self_attr(LSM_ATTR_CURRENT, NULL, &size, 0);
+
+	if (attr_lsm_count()) {
+		ASSERT_NE(-1, rc);
+		ASSERT_NE(1, size);
+	} else {
+		ASSERT_EQ(-1, rc);
+	}
+}
+
+TEST(size_too_small_lsm_get_self_attr)
+{
+	const long page_size = sysconf(_SC_PAGESIZE);
+	struct lsm_ctx *ctx = calloc(page_size, 1);
+	size_t size = 1;
+
+	ASSERT_NE(NULL, ctx);
+	errno = 0;
+	ASSERT_EQ(-1, lsm_get_self_attr(LSM_ATTR_CURRENT, ctx, &size, 0));
+	if (attr_lsm_count()) {
+		ASSERT_EQ(E2BIG, errno);
+	} else {
+		ASSERT_EQ(EOPNOTSUPP, errno);
+	}
+	ASSERT_NE(1, size);
+
+	free(ctx);
+}
+
+TEST(flags_zero_lsm_get_self_attr)
+{
+	const long page_size = sysconf(_SC_PAGESIZE);
+	struct lsm_ctx *ctx = calloc(page_size, 1);
+	__u64 *syscall_lsms = calloc(page_size, 1);
+	size_t size;
+	int lsmcount;
+	int i;
+
+	ASSERT_NE(NULL, ctx);
+	errno = 0;
+	size = page_size;
+	ASSERT_EQ(-1, lsm_get_self_attr(LSM_ATTR_CURRENT, ctx, &size,
+					LSM_FLAG_SINGLE));
+	ASSERT_EQ(EINVAL, errno);
+	ASSERT_EQ(page_size, size);
+
+	lsmcount = syscall(__NR_lsm_list_modules, syscall_lsms, &size, 0);
+	ASSERT_LE(1, lsmcount);
+	ASSERT_NE(NULL, syscall_lsms);
+
+	for (i = 0; i < lsmcount; i++) {
+		errno = 0;
+		size = page_size;
+		ctx->id = syscall_lsms[i];
+
+		if (syscall_lsms[i] == LSM_ID_SELINUX ||
+		    syscall_lsms[i] == LSM_ID_SMACK ||
+		    syscall_lsms[i] == LSM_ID_APPARMOR) {
+			ASSERT_EQ(1, lsm_get_self_attr(LSM_ATTR_CURRENT, ctx,
+						       &size, LSM_FLAG_SINGLE));
+		} else {
+			ASSERT_EQ(-1, lsm_get_self_attr(LSM_ATTR_CURRENT, ctx,
+							&size,
+							LSM_FLAG_SINGLE));
+		}
+	}
+
+	free(ctx);
+}
+
+TEST(flags_overset_lsm_get_self_attr)
+{
+	const long page_size = sysconf(_SC_PAGESIZE);
+	struct lsm_ctx *ctx = calloc(page_size, 1);
+	size_t size;
+
+	ASSERT_NE(NULL, ctx);
+
+	errno = 0;
+	size = page_size;
+	ASSERT_EQ(-1, lsm_get_self_attr(LSM_ATTR_CURRENT | LSM_ATTR_PREV, ctx,
+					&size, 0));
+	ASSERT_EQ(EOPNOTSUPP, errno);
+
+	errno = 0;
+	size = page_size;
+	ASSERT_EQ(-1, lsm_get_self_attr(LSM_ATTR_CURRENT, ctx, &size,
+					LSM_FLAG_SINGLE |
+					(LSM_FLAG_SINGLE << 1)));
+	ASSERT_EQ(EINVAL, errno);
+
+	free(ctx);
+}
+
+TEST(basic_lsm_get_self_attr)
+{
+	const long page_size = sysconf(_SC_PAGESIZE);
+	size_t size = page_size;
+	struct lsm_ctx *ctx = calloc(page_size, 1);
+	struct lsm_ctx *tctx = NULL;
+	__u64 *syscall_lsms = calloc(page_size, 1);
+	char *attr = calloc(page_size, 1);
+	int cnt_current = 0;
+	int cnt_exec = 0;
+	int cnt_fscreate = 0;
+	int cnt_keycreate = 0;
+	int cnt_prev = 0;
+	int cnt_sockcreate = 0;
+	int lsmcount;
+	int count;
+	int i;
+
+	ASSERT_NE(NULL, ctx);
+	ASSERT_NE(NULL, syscall_lsms);
+
+	lsmcount = syscall(__NR_lsm_list_modules, syscall_lsms, &size, 0);
+	ASSERT_LE(1, lsmcount);
+
+	for (i = 0; i < lsmcount; i++) {
+		switch (syscall_lsms[i]) {
+		case LSM_ID_SELINUX:
+			cnt_current++;
+			cnt_exec++;
+			cnt_fscreate++;
+			cnt_keycreate++;
+			cnt_prev++;
+			cnt_sockcreate++;
+			break;
+		case LSM_ID_SMACK:
+			cnt_current++;
+			break;
+		case LSM_ID_APPARMOR:
+			cnt_current++;
+			cnt_exec++;
+			cnt_prev++;
+			break;
+		default:
+			break;
+		}
+	}
+
+	if (cnt_current) {
+		size = page_size;
+		count = lsm_get_self_attr(LSM_ATTR_CURRENT, ctx, &size, 0);
+		ASSERT_EQ(cnt_current, count);
+		tctx = ctx;
+		ASSERT_EQ(0, read_proc_attr("current", attr, page_size));
+		ASSERT_EQ(0, strcmp((char *)tctx->ctx, attr));
+		for (i = 1; i < count; i++) {
+			tctx = next_ctx(tctx);
+			ASSERT_NE(0, strcmp((char *)tctx->ctx, attr));
+		}
+	}
+	if (cnt_exec) {
+		size = page_size;
+		count = lsm_get_self_attr(LSM_ATTR_EXEC, ctx, &size, 0);
+		ASSERT_GE(cnt_exec, count);
+		if (count > 0) {
+			tctx = ctx;
+			if (read_proc_attr("exec", attr, page_size) == 0)
+				ASSERT_EQ(0, strcmp((char *)tctx->ctx, attr));
+		}
+		for (i = 1; i < count; i++) {
+			tctx = next_ctx(tctx);
+			ASSERT_NE(0, strcmp((char *)tctx->ctx, attr));
+		}
+	}
+	if (cnt_fscreate) {
+		size = page_size;
+		count = lsm_get_self_attr(LSM_ATTR_FSCREATE, ctx, &size, 0);
+		ASSERT_GE(cnt_fscreate, count);
+		if (count > 0) {
+			tctx = ctx;
+			if (read_proc_attr("fscreate", attr, page_size) == 0)
+				ASSERT_EQ(0, strcmp((char *)tctx->ctx, attr));
+		}
+		for (i = 1; i < count; i++) {
+			tctx = next_ctx(tctx);
+			ASSERT_NE(0, strcmp((char *)tctx->ctx, attr));
+		}
+	}
+	if (cnt_keycreate) {
+		size = page_size;
+		count = lsm_get_self_attr(LSM_ATTR_KEYCREATE, ctx, &size, 0);
+		ASSERT_GE(cnt_keycreate, count);
+		if (count > 0) {
+			tctx = ctx;
+			if (read_proc_attr("keycreate", attr, page_size) == 0)
+				ASSERT_EQ(0, strcmp((char *)tctx->ctx, attr));
+		}
+		for (i = 1; i < count; i++) {
+			tctx = next_ctx(tctx);
+			ASSERT_NE(0, strcmp((char *)tctx->ctx, attr));
+		}
+	}
+	if (cnt_prev) {
+		size = page_size;
+		count = lsm_get_self_attr(LSM_ATTR_PREV, ctx, &size, 0);
+		ASSERT_GE(cnt_prev, count);
+		if (count > 0) {
+			tctx = ctx;
+			ASSERT_EQ(0, read_proc_attr("prev", attr, page_size));
+			ASSERT_EQ(0, strcmp((char *)tctx->ctx, attr));
+			for (i = 1; i < count; i++) {
+				tctx = next_ctx(tctx);
+				ASSERT_NE(0, strcmp((char *)tctx->ctx, attr));
+			}
+		}
+	}
+	if (cnt_sockcreate) {
+		size = page_size;
+		count = lsm_get_self_attr(LSM_ATTR_SOCKCREATE, ctx, &size, 0);
+		ASSERT_GE(cnt_sockcreate, count);
+		if (count > 0) {
+			tctx = ctx;
+			if (read_proc_attr("sockcreate", attr, page_size) == 0)
+				ASSERT_EQ(0, strcmp((char *)tctx->ctx, attr));
+		}
+		for (i = 1; i < count; i++) {
+			tctx = next_ctx(tctx);
+			ASSERT_NE(0, strcmp((char *)tctx->ctx, attr));
+		}
+	}
+
+	free(ctx);
+	free(attr);
+	free(syscall_lsms);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/lsm/lsm_list_modules_test.c b/tools/testing/selftests/lsm/lsm_list_modules_test.c
new file mode 100644
index 000000000000..9df29b1e3497
--- /dev/null
+++ b/tools/testing/selftests/lsm/lsm_list_modules_test.c
@@ -0,0 +1,137 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Linux Security Module infrastructure tests
+ * Tests for the lsm_list_modules system call
+ *
+ * Copyright © 2022 Casey Schaufler <casey@schaufler-ca.com>
+ */
+
+#define _GNU_SOURCE
+#include <linux/lsm.h>
+#include <string.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include "../kselftest_harness.h"
+#include "common.h"
+
+TEST(size_null_lsm_list_modules)
+{
+	const long page_size = sysconf(_SC_PAGESIZE);
+	__u64 *syscall_lsms = calloc(page_size, 1);
+
+	ASSERT_NE(NULL, syscall_lsms);
+	errno = 0;
+	ASSERT_EQ(-1, lsm_list_modules(syscall_lsms, NULL, 0));
+	ASSERT_EQ(EFAULT, errno);
+
+	free(syscall_lsms);
+}
+
+TEST(ids_null_lsm_list_modules)
+{
+	const long page_size = sysconf(_SC_PAGESIZE);
+	size_t size = page_size;
+
+	errno = 0;
+	ASSERT_EQ(-1, lsm_list_modules(NULL, &size, 0));
+	ASSERT_EQ(EFAULT, errno);
+	ASSERT_NE(1, size);
+}
+
+TEST(size_too_small_lsm_list_modules)
+{
+	const long page_size = sysconf(_SC_PAGESIZE);
+	__u64 *syscall_lsms = calloc(page_size, 1);
+	size_t size = 1;
+
+	ASSERT_NE(NULL, syscall_lsms);
+	errno = 0;
+	ASSERT_EQ(-1, lsm_list_modules(syscall_lsms, &size, 0));
+	ASSERT_EQ(E2BIG, errno);
+	ASSERT_NE(1, size);
+
+	free(syscall_lsms);
+}
+
+TEST(flags_set_lsm_list_modules)
+{
+	const long page_size = sysconf(_SC_PAGESIZE);
+	__u64 *syscall_lsms = calloc(page_size, 1);
+	size_t size = page_size;
+
+	ASSERT_NE(NULL, syscall_lsms);
+	errno = 0;
+	ASSERT_EQ(-1, lsm_list_modules(syscall_lsms, &size, 7));
+	ASSERT_EQ(EINVAL, errno);
+	ASSERT_EQ(page_size, size);
+
+	free(syscall_lsms);
+}
+
+TEST(correct_lsm_list_modules)
+{
+	const long page_size = sysconf(_SC_PAGESIZE);
+	size_t size = page_size;
+	__u64 *syscall_lsms = calloc(page_size, 1);
+	char *sysfs_lsms = calloc(page_size, 1);
+	char *name;
+	char *cp;
+	int count;
+	int i;
+
+	ASSERT_NE(NULL, sysfs_lsms);
+	ASSERT_NE(NULL, syscall_lsms);
+	ASSERT_EQ(0, read_sysfs_lsms(sysfs_lsms, page_size));
+
+	count = lsm_list_modules(syscall_lsms, &size, 0);
+	ASSERT_LE(1, count);
+	cp = sysfs_lsms;
+	for (i = 0; i < count; i++) {
+		switch (syscall_lsms[i]) {
+		case LSM_ID_CAPABILITY:
+			name = "capability";
+			break;
+		case LSM_ID_SELINUX:
+			name = "selinux";
+			break;
+		case LSM_ID_SMACK:
+			name = "smack";
+			break;
+		case LSM_ID_TOMOYO:
+			name = "tomoyo";
+			break;
+		case LSM_ID_APPARMOR:
+			name = "apparmor";
+			break;
+		case LSM_ID_YAMA:
+			name = "yama";
+			break;
+		case LSM_ID_LOADPIN:
+			name = "loadpin";
+			break;
+		case LSM_ID_SAFESETID:
+			name = "safesetid";
+			break;
+		case LSM_ID_LOCKDOWN:
+			name = "lockdown";
+			break;
+		case LSM_ID_BPF:
+			name = "bpf";
+			break;
+		case LSM_ID_LANDLOCK:
+			name = "landlock";
+			break;
+		default:
+			name = "INVALID";
+			break;
+		}
+		ASSERT_EQ(0, strncmp(cp, name, strlen(name)));
+		cp += strlen(name) + 1;
+	}
+
+	free(sysfs_lsms);
+	free(syscall_lsms);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/lsm/lsm_set_self_attr_test.c b/tools/testing/selftests/lsm/lsm_set_self_attr_test.c
new file mode 100644
index 000000000000..e9712c6cf596
--- /dev/null
+++ b/tools/testing/selftests/lsm/lsm_set_self_attr_test.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Linux Security Module infrastructure tests
+ * Tests for the lsm_set_self_attr system call
+ *
+ * Copyright © 2022 Casey Schaufler <casey@schaufler-ca.com>
+ */
+
+#define _GNU_SOURCE
+#include <linux/lsm.h>
+#include <string.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include "../kselftest_harness.h"
+#include "common.h"
+
+TEST(ctx_null_lsm_set_self_attr)
+{
+	ASSERT_EQ(-1, lsm_set_self_attr(LSM_ATTR_CURRENT, NULL,
+					sizeof(struct lsm_ctx), 0));
+}
+
+TEST(size_too_small_lsm_set_self_attr)
+{
+	const long page_size = sysconf(_SC_PAGESIZE);
+	struct lsm_ctx *ctx = calloc(page_size, 1);
+	size_t size = page_size;
+
+	ASSERT_NE(NULL, ctx);
+	if (attr_lsm_count()) {
+		ASSERT_LE(1, lsm_get_self_attr(LSM_ATTR_CURRENT, ctx, &size,
+					       0));
+	}
+	ASSERT_EQ(-1, lsm_set_self_attr(LSM_ATTR_CURRENT, ctx, 1, 0));
+
+	free(ctx);
+}
+
+TEST(flags_zero_lsm_set_self_attr)
+{
+	const long page_size = sysconf(_SC_PAGESIZE);
+	struct lsm_ctx *ctx = calloc(page_size, 1);
+	size_t size = page_size;
+
+	ASSERT_NE(NULL, ctx);
+	if (attr_lsm_count()) {
+		ASSERT_LE(1, lsm_get_self_attr(LSM_ATTR_CURRENT, ctx, &size,
+					       0));
+	}
+	ASSERT_EQ(-1, lsm_set_self_attr(LSM_ATTR_CURRENT, ctx, size, 1));
+
+	free(ctx);
+}
+
+TEST(flags_overset_lsm_set_self_attr)
+{
+	const long page_size = sysconf(_SC_PAGESIZE);
+	char *ctx = calloc(page_size, 1);
+	size_t size = page_size;
+	struct lsm_ctx *tctx = (struct lsm_ctx *)ctx;
+
+	ASSERT_NE(NULL, ctx);
+	if (attr_lsm_count()) {
+		ASSERT_LE(1, lsm_get_self_attr(LSM_ATTR_CURRENT, tctx, &size,
+					       0));
+	}
+	ASSERT_EQ(-1, lsm_set_self_attr(LSM_ATTR_CURRENT | LSM_ATTR_PREV, tctx,
+					size, 0));
+
+	free(ctx);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore
index cc920c79ff1c..4ff10ea61461 100644
--- a/tools/testing/selftests/mm/.gitignore
+++ b/tools/testing/selftests/mm/.gitignore
@@ -45,3 +45,4 @@ mdwe_test
 gup_longterm
 mkdirty
 va_high_addr_switch
+hugetlb_fault_after_madv
diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
index 78dfec8bc676..2453add65d12 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -60,7 +60,7 @@ TEST_GEN_FILES += mrelease_test
 TEST_GEN_FILES += mremap_dontunmap
 TEST_GEN_FILES += mremap_test
 TEST_GEN_FILES += on-fault-limit
-TEST_GEN_PROGS += pagemap_ioctl
+TEST_GEN_FILES += pagemap_ioctl
 TEST_GEN_FILES += thuge-gen
 TEST_GEN_FILES += transhuge-stress
 TEST_GEN_FILES += uffd-stress
@@ -72,7 +72,7 @@ TEST_GEN_FILES += mdwe_test
 TEST_GEN_FILES += hugetlb_fault_after_madv
 
 ifneq ($(ARCH),arm64)
-TEST_GEN_PROGS += soft-dirty
+TEST_GEN_FILES += soft-dirty
 endif
 
 ifeq ($(ARCH),x86_64)
@@ -117,8 +117,8 @@ TEST_FILES += va_high_addr_switch.sh
 
 include ../lib.mk
 
-$(TEST_GEN_PROGS): vm_util.c
-$(TEST_GEN_FILES): vm_util.c
+$(TEST_GEN_PROGS): vm_util.c thp_settings.c
+$(TEST_GEN_FILES): vm_util.c thp_settings.c
 
 $(OUTPUT)/uffd-stress: uffd-common.c
 $(OUTPUT)/uffd-unit-tests: uffd-common.c
diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c
index 9b420140ba2b..656afba02dbc 100644
--- a/tools/testing/selftests/mm/compaction_test.c
+++ b/tools/testing/selftests/mm/compaction_test.c
@@ -33,7 +33,7 @@ int read_memory_info(unsigned long *memfree, unsigned long *hugepagesize)
 	FILE *cmdfile = popen(cmd, "r");
 
 	if (!(fgets(buffer, sizeof(buffer), cmdfile))) {
-		perror("Failed to read meminfo\n");
+		ksft_print_msg("Failed to read meminfo: %s\n", strerror(errno));
 		return -1;
 	}
 
@@ -44,7 +44,7 @@ int read_memory_info(unsigned long *memfree, unsigned long *hugepagesize)
 	cmdfile = popen(cmd, "r");
 
 	if (!(fgets(buffer, sizeof(buffer), cmdfile))) {
-		perror("Failed to read meminfo\n");
+		ksft_print_msg("Failed to read meminfo: %s\n", strerror(errno));
 		return -1;
 	}
 
@@ -62,14 +62,14 @@ int prereq(void)
 	fd = open("/proc/sys/vm/compact_unevictable_allowed",
 		  O_RDONLY | O_NONBLOCK);
 	if (fd < 0) {
-		perror("Failed to open\n"
-		       "/proc/sys/vm/compact_unevictable_allowed\n");
+		ksft_print_msg("Failed to open /proc/sys/vm/compact_unevictable_allowed: %s\n",
+			       strerror(errno));
 		return -1;
 	}
 
 	if (read(fd, &allowed, sizeof(char)) != sizeof(char)) {
-		perror("Failed to read from\n"
-		       "/proc/sys/vm/compact_unevictable_allowed\n");
+		ksft_print_msg("Failed to read from /proc/sys/vm/compact_unevictable_allowed: %s\n",
+			       strerror(errno));
 		close(fd);
 		return -1;
 	}
@@ -78,12 +78,13 @@ int prereq(void)
 	if (allowed == '1')
 		return 0;
 
+	ksft_print_msg("Compaction isn't allowed\n");
 	return -1;
 }
 
 int check_compaction(unsigned long mem_free, unsigned int hugepage_size)
 {
-	int fd;
+	int fd, ret = -1;
 	int compaction_index = 0;
 	char initial_nr_hugepages[10] = {0};
 	char nr_hugepages[10] = {0};
@@ -94,18 +95,21 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size)
 
 	fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK);
 	if (fd < 0) {
-		perror("Failed to open /proc/sys/vm/nr_hugepages");
+		ksft_test_result_fail("Failed to open /proc/sys/vm/nr_hugepages: %s\n",
+				      strerror(errno));
 		return -1;
 	}
 
 	if (read(fd, initial_nr_hugepages, sizeof(initial_nr_hugepages)) <= 0) {
-		perror("Failed to read from /proc/sys/vm/nr_hugepages");
+		ksft_test_result_fail("Failed to read from /proc/sys/vm/nr_hugepages: %s\n",
+				      strerror(errno));
 		goto close_fd;
 	}
 
 	/* Start with the initial condition of 0 huge pages*/
 	if (write(fd, "0", sizeof(char)) != sizeof(char)) {
-		perror("Failed to write 0 to /proc/sys/vm/nr_hugepages\n");
+		ksft_test_result_fail("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n",
+				      strerror(errno));
 		goto close_fd;
 	}
 
@@ -114,14 +118,16 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size)
 	/* Request a large number of huge pages. The Kernel will allocate
 	   as much as it can */
 	if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) {
-		perror("Failed to write 100000 to /proc/sys/vm/nr_hugepages\n");
+		ksft_test_result_fail("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n",
+				      strerror(errno));
 		goto close_fd;
 	}
 
 	lseek(fd, 0, SEEK_SET);
 
 	if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) {
-		perror("Failed to re-read from /proc/sys/vm/nr_hugepages\n");
+		ksft_test_result_fail("Failed to re-read from /proc/sys/vm/nr_hugepages: %s\n",
+				      strerror(errno));
 		goto close_fd;
 	}
 
@@ -129,67 +135,58 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size)
 	   huge pages */
 	compaction_index = mem_free/(atoi(nr_hugepages) * hugepage_size);
 
-	if (compaction_index > 3) {
-		printf("No of huge pages allocated = %d\n",
-		       (atoi(nr_hugepages)));
-		fprintf(stderr, "ERROR: Less that 1/%d of memory is available\n"
-			"as huge pages\n", compaction_index);
-		goto close_fd;
-	}
-
-	printf("No of huge pages allocated = %d\n",
-	       (atoi(nr_hugepages)));
-
 	lseek(fd, 0, SEEK_SET);
 
 	if (write(fd, initial_nr_hugepages, strlen(initial_nr_hugepages))
 	    != strlen(initial_nr_hugepages)) {
-		perror("Failed to write value to /proc/sys/vm/nr_hugepages\n");
+		ksft_test_result_fail("Failed to write value to /proc/sys/vm/nr_hugepages: %s\n",
+				      strerror(errno));
 		goto close_fd;
 	}
 
-	close(fd);
-	return 0;
+	if (compaction_index > 3) {
+		ksft_print_msg("ERROR: Less that 1/%d of memory is available\n"
+			       "as huge pages\n", compaction_index);
+		ksft_test_result_fail("No of huge pages allocated = %d\n", (atoi(nr_hugepages)));
+		goto close_fd;
+	}
+
+	ksft_test_result_pass("Memory compaction succeeded. No of huge pages allocated = %d\n",
+			      (atoi(nr_hugepages)));
+	ret = 0;
 
  close_fd:
 	close(fd);
-	printf("Not OK. Compaction test failed.");
-	return -1;
+	return ret;
 }
 
 
 int main(int argc, char **argv)
 {
 	struct rlimit lim;
-	struct map_list *list, *entry;
+	struct map_list *list = NULL, *entry;
 	size_t page_size, i;
 	void *map = NULL;
 	unsigned long mem_free = 0;
 	unsigned long hugepage_size = 0;
 	long mem_fragmentable_MB = 0;
 
-	if (prereq() != 0) {
-		printf("Either the sysctl compact_unevictable_allowed is not\n"
-		       "set to 1 or couldn't read the proc file.\n"
-		       "Skipping the test\n");
-		return KSFT_SKIP;
-	}
+	ksft_print_header();
+
+	if (prereq() || geteuid())
+		return ksft_exit_pass();
+
+	ksft_set_plan(1);
 
 	lim.rlim_cur = RLIM_INFINITY;
 	lim.rlim_max = RLIM_INFINITY;
-	if (setrlimit(RLIMIT_MEMLOCK, &lim)) {
-		perror("Failed to set rlimit:\n");
-		return -1;
-	}
+	if (setrlimit(RLIMIT_MEMLOCK, &lim))
+		ksft_exit_fail_msg("Failed to set rlimit: %s\n", strerror(errno));
 
 	page_size = getpagesize();
 
-	list = NULL;
-
-	if (read_memory_info(&mem_free, &hugepage_size) != 0) {
-		printf("ERROR: Cannot read meminfo\n");
-		return -1;
-	}
+	if (read_memory_info(&mem_free, &hugepage_size) != 0)
+		ksft_exit_fail_msg("Failed to get meminfo\n");
 
 	mem_fragmentable_MB = mem_free * 0.8 / 1024;
 
@@ -225,7 +222,7 @@ int main(int argc, char **argv)
 	}
 
 	if (check_compaction(mem_free, hugepage_size) == 0)
-		return 0;
+		return ksft_exit_pass();
 
-	return -1;
+	return ksft_exit_fail();
 }
diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c
index 7324ce5363c0..363bf5f801be 100644
--- a/tools/testing/selftests/mm/cow.c
+++ b/tools/testing/selftests/mm/cow.c
@@ -29,15 +29,49 @@
 #include "../../../../mm/gup_test.h"
 #include "../kselftest.h"
 #include "vm_util.h"
+#include "thp_settings.h"
 
 static size_t pagesize;
 static int pagemap_fd;
-static size_t thpsize;
+static size_t pmdsize;
+static int nr_thpsizes;
+static size_t thpsizes[20];
 static int nr_hugetlbsizes;
 static size_t hugetlbsizes[10];
 static int gup_fd;
 static bool has_huge_zeropage;
 
+static int sz2ord(size_t size)
+{
+	return __builtin_ctzll(size / pagesize);
+}
+
+static int detect_thp_sizes(size_t sizes[], int max)
+{
+	int count = 0;
+	unsigned long orders;
+	size_t kb;
+	int i;
+
+	/* thp not supported at all. */
+	if (!pmdsize)
+		return 0;
+
+	orders = 1UL << sz2ord(pmdsize);
+	orders |= thp_supported_orders();
+
+	for (i = 0; orders && count < max; i++) {
+		if (!(orders & (1UL << i)))
+			continue;
+		orders &= ~(1UL << i);
+		kb = (pagesize >> 10) << i;
+		sizes[count++] = kb * 1024;
+		ksft_print_msg("[INFO] detected THP size: %zu KiB\n", kb);
+	}
+
+	return count;
+}
+
 static void detect_huge_zeropage(void)
 {
 	int fd = open("/sys/kernel/mm/transparent_hugepage/use_zero_page",
@@ -734,7 +768,7 @@ enum thp_run {
 	THP_RUN_PARTIAL_SHARED,
 };
 
-static void do_run_with_thp(test_fn fn, enum thp_run thp_run)
+static void do_run_with_thp(test_fn fn, enum thp_run thp_run, size_t thpsize)
 {
 	char *mem, *mmap_mem, *tmp, *mremap_mem = MAP_FAILED;
 	size_t size, mmap_size, mremap_size;
@@ -759,11 +793,11 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run)
 	}
 
 	/*
-	 * Try to populate a THP. Touch the first sub-page and test if we get
-	 * another sub-page populated automatically.
+	 * Try to populate a THP. Touch the first sub-page and test if
+	 * we get the last sub-page populated automatically.
 	 */
 	mem[0] = 0;
-	if (!pagemap_is_populated(pagemap_fd, mem + pagesize)) {
+	if (!pagemap_is_populated(pagemap_fd, mem + thpsize - pagesize)) {
 		ksft_test_result_skip("Did not get a THP populated\n");
 		goto munmap;
 	}
@@ -773,12 +807,14 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run)
 	switch (thp_run) {
 	case THP_RUN_PMD:
 	case THP_RUN_PMD_SWAPOUT:
+		assert(thpsize == pmdsize);
 		break;
 	case THP_RUN_PTE:
 	case THP_RUN_PTE_SWAPOUT:
 		/*
 		 * Trigger PTE-mapping the THP by temporarily mapping a single
-		 * subpage R/O.
+		 * subpage R/O. This is a noop if the THP is not pmdsize (and
+		 * therefore already PTE-mapped).
 		 */
 		ret = mprotect(mem + pagesize, pagesize, PROT_READ);
 		if (ret) {
@@ -875,52 +911,60 @@ munmap:
 		munmap(mremap_mem, mremap_size);
 }
 
-static void run_with_thp(test_fn fn, const char *desc)
+static void run_with_thp(test_fn fn, const char *desc, size_t size)
 {
-	ksft_print_msg("[RUN] %s ... with THP\n", desc);
-	do_run_with_thp(fn, THP_RUN_PMD);
+	ksft_print_msg("[RUN] %s ... with THP (%zu kB)\n",
+		desc, size / 1024);
+	do_run_with_thp(fn, THP_RUN_PMD, size);
 }
 
-static void run_with_thp_swap(test_fn fn, const char *desc)
+static void run_with_thp_swap(test_fn fn, const char *desc, size_t size)
 {
-	ksft_print_msg("[RUN] %s ... with swapped-out THP\n", desc);
-	do_run_with_thp(fn, THP_RUN_PMD_SWAPOUT);
+	ksft_print_msg("[RUN] %s ... with swapped-out THP (%zu kB)\n",
+		desc, size / 1024);
+	do_run_with_thp(fn, THP_RUN_PMD_SWAPOUT, size);
 }
 
-static void run_with_pte_mapped_thp(test_fn fn, const char *desc)
+static void run_with_pte_mapped_thp(test_fn fn, const char *desc, size_t size)
 {
-	ksft_print_msg("[RUN] %s ... with PTE-mapped THP\n", desc);
-	do_run_with_thp(fn, THP_RUN_PTE);
+	ksft_print_msg("[RUN] %s ... with PTE-mapped THP (%zu kB)\n",
+		desc, size / 1024);
+	do_run_with_thp(fn, THP_RUN_PTE, size);
 }
 
-static void run_with_pte_mapped_thp_swap(test_fn fn, const char *desc)
+static void run_with_pte_mapped_thp_swap(test_fn fn, const char *desc, size_t size)
 {
-	ksft_print_msg("[RUN] %s ... with swapped-out, PTE-mapped THP\n", desc);
-	do_run_with_thp(fn, THP_RUN_PTE_SWAPOUT);
+	ksft_print_msg("[RUN] %s ... with swapped-out, PTE-mapped THP (%zu kB)\n",
+		desc, size / 1024);
+	do_run_with_thp(fn, THP_RUN_PTE_SWAPOUT, size);
 }
 
-static void run_with_single_pte_of_thp(test_fn fn, const char *desc)
+static void run_with_single_pte_of_thp(test_fn fn, const char *desc, size_t size)
 {
-	ksft_print_msg("[RUN] %s ... with single PTE of THP\n", desc);
-	do_run_with_thp(fn, THP_RUN_SINGLE_PTE);
+	ksft_print_msg("[RUN] %s ... with single PTE of THP (%zu kB)\n",
+		desc, size / 1024);
+	do_run_with_thp(fn, THP_RUN_SINGLE_PTE, size);
 }
 
-static void run_with_single_pte_of_thp_swap(test_fn fn, const char *desc)
+static void run_with_single_pte_of_thp_swap(test_fn fn, const char *desc, size_t size)
 {
-	ksft_print_msg("[RUN] %s ... with single PTE of swapped-out THP\n", desc);
-	do_run_with_thp(fn, THP_RUN_SINGLE_PTE_SWAPOUT);
+	ksft_print_msg("[RUN] %s ... with single PTE of swapped-out THP (%zu kB)\n",
+		desc, size / 1024);
+	do_run_with_thp(fn, THP_RUN_SINGLE_PTE_SWAPOUT, size);
 }
 
-static void run_with_partial_mremap_thp(test_fn fn, const char *desc)
+static void run_with_partial_mremap_thp(test_fn fn, const char *desc, size_t size)
 {
-	ksft_print_msg("[RUN] %s ... with partially mremap()'ed THP\n", desc);
-	do_run_with_thp(fn, THP_RUN_PARTIAL_MREMAP);
+	ksft_print_msg("[RUN] %s ... with partially mremap()'ed THP (%zu kB)\n",
+		desc, size / 1024);
+	do_run_with_thp(fn, THP_RUN_PARTIAL_MREMAP, size);
 }
 
-static void run_with_partial_shared_thp(test_fn fn, const char *desc)
+static void run_with_partial_shared_thp(test_fn fn, const char *desc, size_t size)
 {
-	ksft_print_msg("[RUN] %s ... with partially shared THP\n", desc);
-	do_run_with_thp(fn, THP_RUN_PARTIAL_SHARED);
+	ksft_print_msg("[RUN] %s ... with partially shared THP (%zu kB)\n",
+		desc, size / 1024);
+	do_run_with_thp(fn, THP_RUN_PARTIAL_SHARED, size);
 }
 
 static void run_with_hugetlb(test_fn fn, const char *desc, size_t hugetlbsize)
@@ -1091,15 +1135,27 @@ static void run_anon_test_case(struct test_case const *test_case)
 
 	run_with_base_page(test_case->fn, test_case->desc);
 	run_with_base_page_swap(test_case->fn, test_case->desc);
-	if (thpsize) {
-		run_with_thp(test_case->fn, test_case->desc);
-		run_with_thp_swap(test_case->fn, test_case->desc);
-		run_with_pte_mapped_thp(test_case->fn, test_case->desc);
-		run_with_pte_mapped_thp_swap(test_case->fn, test_case->desc);
-		run_with_single_pte_of_thp(test_case->fn, test_case->desc);
-		run_with_single_pte_of_thp_swap(test_case->fn, test_case->desc);
-		run_with_partial_mremap_thp(test_case->fn, test_case->desc);
-		run_with_partial_shared_thp(test_case->fn, test_case->desc);
+	for (i = 0; i < nr_thpsizes; i++) {
+		size_t size = thpsizes[i];
+		struct thp_settings settings = *thp_current_settings();
+
+		settings.hugepages[sz2ord(pmdsize)].enabled = THP_NEVER;
+		settings.hugepages[sz2ord(size)].enabled = THP_ALWAYS;
+		thp_push_settings(&settings);
+
+		if (size == pmdsize) {
+			run_with_thp(test_case->fn, test_case->desc, size);
+			run_with_thp_swap(test_case->fn, test_case->desc, size);
+		}
+
+		run_with_pte_mapped_thp(test_case->fn, test_case->desc, size);
+		run_with_pte_mapped_thp_swap(test_case->fn, test_case->desc, size);
+		run_with_single_pte_of_thp(test_case->fn, test_case->desc, size);
+		run_with_single_pte_of_thp_swap(test_case->fn, test_case->desc, size);
+		run_with_partial_mremap_thp(test_case->fn, test_case->desc, size);
+		run_with_partial_shared_thp(test_case->fn, test_case->desc, size);
+
+		thp_pop_settings();
 	}
 	for (i = 0; i < nr_hugetlbsizes; i++)
 		run_with_hugetlb(test_case->fn, test_case->desc,
@@ -1120,8 +1176,9 @@ static int tests_per_anon_test_case(void)
 {
 	int tests = 2 + nr_hugetlbsizes;
 
-	if (thpsize)
-		tests += 8;
+	tests += 6 * nr_thpsizes;
+	if (pmdsize)
+		tests += 2;
 	return tests;
 }
 
@@ -1329,7 +1386,7 @@ static void run_anon_thp_test_cases(void)
 {
 	int i;
 
-	if (!thpsize)
+	if (!pmdsize)
 		return;
 
 	ksft_print_msg("[INFO] Anonymous THP tests\n");
@@ -1338,13 +1395,13 @@ static void run_anon_thp_test_cases(void)
 		struct test_case const *test_case = &anon_thp_test_cases[i];
 
 		ksft_print_msg("[RUN] %s\n", test_case->desc);
-		do_run_with_thp(test_case->fn, THP_RUN_PMD);
+		do_run_with_thp(test_case->fn, THP_RUN_PMD, pmdsize);
 	}
 }
 
 static int tests_per_anon_thp_test_case(void)
 {
-	return thpsize ? 1 : 0;
+	return pmdsize ? 1 : 0;
 }
 
 typedef void (*non_anon_test_fn)(char *mem, const char *smem, size_t size);
@@ -1419,7 +1476,7 @@ static void run_with_huge_zeropage(non_anon_test_fn fn, const char *desc)
 	}
 
 	/* For alignment purposes, we need twice the thp size. */
-	mmap_size = 2 * thpsize;
+	mmap_size = 2 * pmdsize;
 	mmap_mem = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE,
 			MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
 	if (mmap_mem == MAP_FAILED) {
@@ -1434,11 +1491,11 @@ static void run_with_huge_zeropage(non_anon_test_fn fn, const char *desc)
 	}
 
 	/* We need a THP-aligned memory area. */
-	mem = (char *)(((uintptr_t)mmap_mem + thpsize) & ~(thpsize - 1));
-	smem = (char *)(((uintptr_t)mmap_smem + thpsize) & ~(thpsize - 1));
+	mem = (char *)(((uintptr_t)mmap_mem + pmdsize) & ~(pmdsize - 1));
+	smem = (char *)(((uintptr_t)mmap_smem + pmdsize) & ~(pmdsize - 1));
 
-	ret = madvise(mem, thpsize, MADV_HUGEPAGE);
-	ret |= madvise(smem, thpsize, MADV_HUGEPAGE);
+	ret = madvise(mem, pmdsize, MADV_HUGEPAGE);
+	ret |= madvise(smem, pmdsize, MADV_HUGEPAGE);
 	if (ret) {
 		ksft_test_result_fail("MADV_HUGEPAGE failed\n");
 		goto munmap;
@@ -1457,7 +1514,7 @@ static void run_with_huge_zeropage(non_anon_test_fn fn, const char *desc)
 		goto munmap;
 	}
 
-	fn(mem, smem, thpsize);
+	fn(mem, smem, pmdsize);
 munmap:
 	munmap(mmap_mem, mmap_size);
 	if (mmap_smem != MAP_FAILED)
@@ -1650,7 +1707,7 @@ static void run_non_anon_test_case(struct non_anon_test_case const *test_case)
 	run_with_zeropage(test_case->fn, test_case->desc);
 	run_with_memfd(test_case->fn, test_case->desc);
 	run_with_tmpfile(test_case->fn, test_case->desc);
-	if (thpsize)
+	if (pmdsize)
 		run_with_huge_zeropage(test_case->fn, test_case->desc);
 	for (i = 0; i < nr_hugetlbsizes; i++)
 		run_with_memfd_hugetlb(test_case->fn, test_case->desc,
@@ -1671,7 +1728,7 @@ static int tests_per_non_anon_test_case(void)
 {
 	int tests = 3 + nr_hugetlbsizes;
 
-	if (thpsize)
+	if (pmdsize)
 		tests += 1;
 	return tests;
 }
@@ -1679,17 +1736,27 @@ static int tests_per_non_anon_test_case(void)
 int main(int argc, char **argv)
 {
 	int err;
+	struct thp_settings default_settings;
+
+	ksft_print_header();
 
 	pagesize = getpagesize();
-	thpsize = read_pmd_pagesize();
-	if (thpsize)
-		ksft_print_msg("[INFO] detected THP size: %zu KiB\n",
-			       thpsize / 1024);
+	pmdsize = read_pmd_pagesize();
+	if (pmdsize) {
+		/* Only if THP is supported. */
+		thp_read_settings(&default_settings);
+		default_settings.hugepages[sz2ord(pmdsize)].enabled = THP_INHERIT;
+		thp_save_settings();
+		thp_push_settings(&default_settings);
+
+		ksft_print_msg("[INFO] detected PMD size: %zu KiB\n",
+			       pmdsize / 1024);
+		nr_thpsizes = detect_thp_sizes(thpsizes, ARRAY_SIZE(thpsizes));
+	}
 	nr_hugetlbsizes = detect_hugetlb_page_sizes(hugetlbsizes,
 						    ARRAY_SIZE(hugetlbsizes));
 	detect_huge_zeropage();
 
-	ksft_print_header();
 	ksft_set_plan(ARRAY_SIZE(anon_test_cases) * tests_per_anon_test_case() +
 		      ARRAY_SIZE(anon_thp_test_cases) * tests_per_anon_thp_test_case() +
 		      ARRAY_SIZE(non_anon_test_cases) * tests_per_non_anon_test_case());
@@ -1703,6 +1770,11 @@ int main(int argc, char **argv)
 	run_anon_thp_test_cases();
 	run_non_anon_test_cases();
 
+	if (pmdsize) {
+		/* Only if THP is supported. */
+		thp_restore_settings();
+	}
+
 	err = ksft_get_fail_cnt();
 	if (err)
 		ksft_exit_fail_msg("%d out of %d tests failed\n",
diff --git a/tools/testing/selftests/mm/gup_test.c b/tools/testing/selftests/mm/gup_test.c
index ec2229136384..cbe99594d319 100644
--- a/tools/testing/selftests/mm/gup_test.c
+++ b/tools/testing/selftests/mm/gup_test.c
@@ -50,39 +50,41 @@ static char *cmd_to_str(unsigned long cmd)
 void *gup_thread(void *data)
 {
 	struct gup_test gup = *(struct gup_test *)data;
-	int i;
+	int i, status;
 
 	/* Only report timing information on the *_BENCHMARK commands: */
 	if ((cmd == PIN_FAST_BENCHMARK) || (cmd == GUP_FAST_BENCHMARK) ||
 	     (cmd == PIN_LONGTERM_BENCHMARK)) {
 		for (i = 0; i < repeats; i++) {
 			gup.size = size;
-			if (ioctl(gup_fd, cmd, &gup))
-				perror("ioctl"), exit(1);
+			status = ioctl(gup_fd, cmd, &gup);
+			if (status)
+				break;
 
 			pthread_mutex_lock(&print_mutex);
-			printf("%s: Time: get:%lld put:%lld us",
-			       cmd_to_str(cmd), gup.get_delta_usec,
-			       gup.put_delta_usec);
+			ksft_print_msg("%s: Time: get:%lld put:%lld us",
+				       cmd_to_str(cmd), gup.get_delta_usec,
+				       gup.put_delta_usec);
 			if (gup.size != size)
-				printf(", truncated (size: %lld)", gup.size);
-			printf("\n");
+				ksft_print_msg(", truncated (size: %lld)", gup.size);
+			ksft_print_msg("\n");
 			pthread_mutex_unlock(&print_mutex);
 		}
 	} else {
 		gup.size = size;
-		if (ioctl(gup_fd, cmd, &gup)) {
-			perror("ioctl");
-			exit(1);
-		}
+		status = ioctl(gup_fd, cmd, &gup);
+		if (status)
+			goto return_;
 
 		pthread_mutex_lock(&print_mutex);
-		printf("%s: done\n", cmd_to_str(cmd));
+		ksft_print_msg("%s: done\n", cmd_to_str(cmd));
 		if (gup.size != size)
-			printf("Truncated (size: %lld)\n", gup.size);
+			ksft_print_msg("Truncated (size: %lld)\n", gup.size);
 		pthread_mutex_unlock(&print_mutex);
 	}
 
+return_:
+	ksft_test_result(!status, "ioctl status %d\n", status);
 	return NULL;
 }
 
@@ -170,7 +172,7 @@ int main(int argc, char **argv)
 			touch = 1;
 			break;
 		default:
-			return -1;
+			ksft_exit_fail_msg("Wrong argument\n");
 		}
 	}
 
@@ -198,11 +200,12 @@ int main(int argc, char **argv)
 		}
 	}
 
+	ksft_print_header();
+	ksft_set_plan(nthreads);
+
 	filed = open(file, O_RDWR|O_CREAT);
-	if (filed < 0) {
-		perror("open");
-		exit(filed);
-	}
+	if (filed < 0)
+		ksft_exit_fail_msg("Unable to open %s: %s\n", file, strerror(errno));
 
 	gup.nr_pages_per_call = nr_pages;
 	if (write)
@@ -213,27 +216,24 @@ int main(int argc, char **argv)
 		switch (errno) {
 		case EACCES:
 			if (getuid())
-				printf("Please run this test as root\n");
+				ksft_print_msg("Please run this test as root\n");
 			break;
 		case ENOENT:
-			if (opendir("/sys/kernel/debug") == NULL) {
-				printf("mount debugfs at /sys/kernel/debug\n");
-				break;
-			}
-			printf("check if CONFIG_GUP_TEST is enabled in kernel config\n");
+			if (opendir("/sys/kernel/debug") == NULL)
+				ksft_print_msg("mount debugfs at /sys/kernel/debug\n");
+			ksft_print_msg("check if CONFIG_GUP_TEST is enabled in kernel config\n");
 			break;
 		default:
-			perror("failed to open " GUP_TEST_FILE);
+			ksft_print_msg("failed to open %s: %s\n", GUP_TEST_FILE, strerror(errno));
 			break;
 		}
-		exit(KSFT_SKIP);
+		ksft_test_result_skip("Please run this test as root\n");
+		return ksft_exit_pass();
 	}
 
 	p = mmap(NULL, size, PROT_READ | PROT_WRITE, flags, filed, 0);
-	if (p == MAP_FAILED) {
-		perror("mmap");
-		exit(1);
-	}
+	if (p == MAP_FAILED)
+		ksft_exit_fail_msg("mmap: %s\n", strerror(errno));
 	gup.addr = (unsigned long)p;
 
 	if (thp == 1)
@@ -264,7 +264,8 @@ int main(int argc, char **argv)
 		ret = pthread_join(tid[i], NULL);
 		assert(ret == 0);
 	}
+
 	free(tid);
 
-	return 0;
+	return ksft_exit_pass();
 }
diff --git a/tools/testing/selftests/mm/hugepage-mmap.c b/tools/testing/selftests/mm/hugepage-mmap.c
index 955ef87f382c..267eea2e0e0b 100644
--- a/tools/testing/selftests/mm/hugepage-mmap.c
+++ b/tools/testing/selftests/mm/hugepage-mmap.c
@@ -22,6 +22,7 @@
 #include <unistd.h>
 #include <sys/mman.h>
 #include <fcntl.h>
+#include "../kselftest.h"
 
 #define LENGTH (256UL*1024*1024)
 #define PROTECTION (PROT_READ | PROT_WRITE)
@@ -37,7 +38,7 @@
 
 static void check_bytes(char *addr)
 {
-	printf("First hex is %x\n", *((unsigned int *)addr));
+	ksft_print_msg("First hex is %x\n", *((unsigned int *)addr));
 }
 
 static void write_bytes(char *addr)
@@ -55,7 +56,7 @@ static int read_bytes(char *addr)
 	check_bytes(addr);
 	for (i = 0; i < LENGTH; i++)
 		if (*(addr + i) != (char)i) {
-			printf("Mismatch at %lu\n", i);
+			ksft_print_msg("Error: Mismatch at %lu\n", i);
 			return 1;
 		}
 	return 0;
@@ -66,20 +67,20 @@ int main(void)
 	void *addr;
 	int fd, ret;
 
+	ksft_print_header();
+	ksft_set_plan(1);
+
 	fd = memfd_create("hugepage-mmap", MFD_HUGETLB);
-	if (fd < 0) {
-		perror("memfd_create() failed");
-		exit(1);
-	}
+	if (fd < 0)
+		ksft_exit_fail_msg("memfd_create() failed: %s\n", strerror(errno));
 
 	addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, fd, 0);
 	if (addr == MAP_FAILED) {
-		perror("mmap");
 		close(fd);
-		exit(1);
+		ksft_exit_fail_msg("mmap(): %s\n", strerror(errno));
 	}
 
-	printf("Returned address is %p\n", addr);
+	ksft_print_msg("Returned address is %p\n", addr);
 	check_bytes(addr);
 	write_bytes(addr);
 	ret = read_bytes(addr);
@@ -87,5 +88,7 @@ int main(void)
 	munmap(addr, LENGTH);
 	close(fd);
 
-	return ret;
+	ksft_test_result(!ret, "Read same data\n");
+
+	ksft_exit(!ret);
 }
diff --git a/tools/testing/selftests/mm/hugepage-mremap.c b/tools/testing/selftests/mm/hugepage-mremap.c
index cabd0084f57b..c463d1c09c9b 100644
--- a/tools/testing/selftests/mm/hugepage-mremap.c
+++ b/tools/testing/selftests/mm/hugepage-mremap.c
@@ -24,6 +24,7 @@
 #include <sys/ioctl.h>
 #include <string.h>
 #include <stdbool.h>
+#include "../kselftest.h"
 #include "vm_util.h"
 
 #define DEFAULT_LENGTH_MB 10UL
@@ -34,7 +35,7 @@
 
 static void check_bytes(char *addr)
 {
-	printf("First hex is %x\n", *((unsigned int *)addr));
+	ksft_print_msg("First hex is %x\n", *((unsigned int *)addr));
 }
 
 static void write_bytes(char *addr, size_t len)
@@ -52,7 +53,7 @@ static int read_bytes(char *addr, size_t len)
 	check_bytes(addr);
 	for (i = 0; i < len; i++)
 		if (*(addr + i) != (char)i) {
-			printf("Mismatch at %lu\n", i);
+			ksft_print_msg("Mismatch at %lu\n", i);
 			return 1;
 		}
 	return 0;
@@ -66,17 +67,13 @@ static void register_region_with_uffd(char *addr, size_t len)
 	/* Create and enable userfaultfd object. */
 
 	uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
-	if (uffd == -1) {
-		perror("userfaultfd");
-		exit(1);
-	}
+	if (uffd == -1)
+		ksft_exit_fail_msg("userfaultfd: %s\n", strerror(errno));
 
 	uffdio_api.api = UFFD_API;
 	uffdio_api.features = 0;
-	if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1) {
-		perror("ioctl-UFFDIO_API");
-		exit(1);
-	}
+	if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1)
+		ksft_exit_fail_msg("ioctl-UFFDIO_API: %s\n", strerror(errno));
 
 	/* Create a private anonymous mapping. The memory will be
 	 * demand-zero paged--that is, not yet allocated. When we
@@ -86,21 +83,17 @@ static void register_region_with_uffd(char *addr, size_t len)
 
 	addr = mmap(NULL, len, PROT_READ | PROT_WRITE,
 		    MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
-	if (addr == MAP_FAILED) {
-		perror("mmap");
-		exit(1);
-	}
+	if (addr == MAP_FAILED)
+		ksft_exit_fail_msg("mmap: %s\n", strerror(errno));
 
-	printf("Address returned by mmap() = %p\n", addr);
+	ksft_print_msg("Address returned by mmap() = %p\n", addr);
 
 	/* Register the memory range of the mapping we just created for
 	 * handling by the userfaultfd object. In mode, we request to track
 	 * missing pages (i.e., pages that have not yet been faulted in).
 	 */
-	if (uffd_register(uffd, addr, len, true, false, false)) {
-		perror("ioctl-UFFDIO_REGISTER");
-		exit(1);
-	}
+	if (uffd_register(uffd, addr, len, true, false, false))
+		ksft_exit_fail_msg("ioctl-UFFDIO_REGISTER: %s\n", strerror(errno));
 }
 
 int main(int argc, char *argv[])
@@ -108,10 +101,11 @@ int main(int argc, char *argv[])
 	size_t length = 0;
 	int ret = 0, fd;
 
-	if (argc >= 2 && !strcmp(argv[1], "-h")) {
-		printf("Usage: %s [length_in_MB]\n", argv[0]);
-		exit(1);
-	}
+	ksft_print_header();
+	ksft_set_plan(1);
+
+	if (argc >= 2 && !strcmp(argv[1], "-h"))
+		ksft_exit_fail_msg("Usage: %s [length_in_MB]\n", argv[0]);
 
 	/* Read memory length as the first arg if valid, otherwise fallback to
 	 * the default length.
@@ -123,50 +117,40 @@ int main(int argc, char *argv[])
 
 	length = MB_TO_BYTES(length);
 	fd = memfd_create(argv[0], MFD_HUGETLB);
-	if (fd < 0) {
-		perror("Open failed");
-		exit(1);
-	}
+	if (fd < 0)
+		ksft_exit_fail_msg("Open failed: %s\n", strerror(errno));
 
 	/* mmap to a PUD aligned address to hopefully trigger pmd sharing. */
 	unsigned long suggested_addr = 0x7eaa40000000;
 	void *haddr = mmap((void *)suggested_addr, length, PROTECTION,
 			   MAP_HUGETLB | MAP_SHARED | MAP_POPULATE, fd, 0);
-	printf("Map haddr: Returned address is %p\n", haddr);
-	if (haddr == MAP_FAILED) {
-		perror("mmap1");
-		exit(1);
-	}
+	ksft_print_msg("Map haddr: Returned address is %p\n", haddr);
+	if (haddr == MAP_FAILED)
+		ksft_exit_fail_msg("mmap1: %s\n", strerror(errno));
 
 	/* mmap again to a dummy address to hopefully trigger pmd sharing. */
 	suggested_addr = 0x7daa40000000;
 	void *daddr = mmap((void *)suggested_addr, length, PROTECTION,
 			   MAP_HUGETLB | MAP_SHARED | MAP_POPULATE, fd, 0);
-	printf("Map daddr: Returned address is %p\n", daddr);
-	if (daddr == MAP_FAILED) {
-		perror("mmap3");
-		exit(1);
-	}
+	ksft_print_msg("Map daddr: Returned address is %p\n", daddr);
+	if (daddr == MAP_FAILED)
+		ksft_exit_fail_msg("mmap3: %s\n", strerror(errno));
 
 	suggested_addr = 0x7faa40000000;
 	void *vaddr =
 		mmap((void *)suggested_addr, length, PROTECTION, FLAGS, -1, 0);
-	printf("Map vaddr: Returned address is %p\n", vaddr);
-	if (vaddr == MAP_FAILED) {
-		perror("mmap2");
-		exit(1);
-	}
+	ksft_print_msg("Map vaddr: Returned address is %p\n", vaddr);
+	if (vaddr == MAP_FAILED)
+		ksft_exit_fail_msg("mmap2: %s\n", strerror(errno));
 
 	register_region_with_uffd(haddr, length);
 
 	void *addr = mremap(haddr, length, length,
 			    MREMAP_MAYMOVE | MREMAP_FIXED, vaddr);
-	if (addr == MAP_FAILED) {
-		perror("mremap");
-		exit(1);
-	}
+	if (addr == MAP_FAILED)
+		ksft_exit_fail_msg("mremap: %s\n", strerror(errno));
 
-	printf("Mremap: Returned address is %p\n", addr);
+	ksft_print_msg("Mremap: Returned address is %p\n", addr);
 	check_bytes(addr);
 	write_bytes(addr, length);
 	ret = read_bytes(addr, length);
@@ -174,12 +158,11 @@ int main(int argc, char *argv[])
 	munmap(addr, length);
 
 	addr = mremap(addr, length, length, 0);
-	if (addr != MAP_FAILED) {
-		printf("mremap: Expected failure, but call succeeded\n");
-		exit(1);
-	}
+	if (addr != MAP_FAILED)
+		ksft_exit_fail_msg("mremap: Expected failure, but call succeeded\n");
 
 	close(fd);
 
-	return ret;
+	ksft_test_result(!ret, "Read same data\n");
+	ksft_exit(!ret);
 }
diff --git a/tools/testing/selftests/mm/khugepaged.c b/tools/testing/selftests/mm/khugepaged.c
index 030667cb5533..829320a519e7 100644
--- a/tools/testing/selftests/mm/khugepaged.c
+++ b/tools/testing/selftests/mm/khugepaged.c
@@ -22,13 +22,14 @@
 #include "linux/magic.h"
 
 #include "vm_util.h"
+#include "thp_settings.h"
 
 #define BASE_ADDR ((void *)(1UL << 30))
 static unsigned long hpage_pmd_size;
 static unsigned long page_size;
 static int hpage_pmd_nr;
+static int anon_order;
 
-#define THP_SYSFS "/sys/kernel/mm/transparent_hugepage/"
 #define PID_SMAPS "/proc/self/smaps"
 #define TEST_FILE "collapse_test_file"
 
@@ -71,78 +72,7 @@ struct file_info {
 };
 
 static struct file_info finfo;
-
-enum thp_enabled {
-	THP_ALWAYS,
-	THP_MADVISE,
-	THP_NEVER,
-};
-
-static const char *thp_enabled_strings[] = {
-	"always",
-	"madvise",
-	"never",
-	NULL
-};
-
-enum thp_defrag {
-	THP_DEFRAG_ALWAYS,
-	THP_DEFRAG_DEFER,
-	THP_DEFRAG_DEFER_MADVISE,
-	THP_DEFRAG_MADVISE,
-	THP_DEFRAG_NEVER,
-};
-
-static const char *thp_defrag_strings[] = {
-	"always",
-	"defer",
-	"defer+madvise",
-	"madvise",
-	"never",
-	NULL
-};
-
-enum shmem_enabled {
-	SHMEM_ALWAYS,
-	SHMEM_WITHIN_SIZE,
-	SHMEM_ADVISE,
-	SHMEM_NEVER,
-	SHMEM_DENY,
-	SHMEM_FORCE,
-};
-
-static const char *shmem_enabled_strings[] = {
-	"always",
-	"within_size",
-	"advise",
-	"never",
-	"deny",
-	"force",
-	NULL
-};
-
-struct khugepaged_settings {
-	bool defrag;
-	unsigned int alloc_sleep_millisecs;
-	unsigned int scan_sleep_millisecs;
-	unsigned int max_ptes_none;
-	unsigned int max_ptes_swap;
-	unsigned int max_ptes_shared;
-	unsigned long pages_to_scan;
-};
-
-struct settings {
-	enum thp_enabled thp_enabled;
-	enum thp_defrag thp_defrag;
-	enum shmem_enabled shmem_enabled;
-	bool use_zero_page;
-	struct khugepaged_settings khugepaged;
-	unsigned long read_ahead_kb;
-};
-
-static struct settings saved_settings;
 static bool skip_settings_restore;
-
 static int exit_status;
 
 static void success(const char *msg)
@@ -161,260 +91,34 @@ static void skip(const char *msg)
 	printf(" \e[33m%s\e[0m\n", msg);
 }
 
-static int read_file(const char *path, char *buf, size_t buflen)
-{
-	int fd;
-	ssize_t numread;
-
-	fd = open(path, O_RDONLY);
-	if (fd == -1)
-		return 0;
-
-	numread = read(fd, buf, buflen - 1);
-	if (numread < 1) {
-		close(fd);
-		return 0;
-	}
-
-	buf[numread] = '\0';
-	close(fd);
-
-	return (unsigned int) numread;
-}
-
-static int write_file(const char *path, const char *buf, size_t buflen)
-{
-	int fd;
-	ssize_t numwritten;
-
-	fd = open(path, O_WRONLY);
-	if (fd == -1) {
-		printf("open(%s)\n", path);
-		exit(EXIT_FAILURE);
-		return 0;
-	}
-
-	numwritten = write(fd, buf, buflen - 1);
-	close(fd);
-	if (numwritten < 1) {
-		printf("write(%s)\n", buf);
-		exit(EXIT_FAILURE);
-		return 0;
-	}
-
-	return (unsigned int) numwritten;
-}
-
-static int read_string(const char *name, const char *strings[])
+static void restore_settings_atexit(void)
 {
-	char path[PATH_MAX];
-	char buf[256];
-	char *c;
-	int ret;
-
-	ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name);
-	if (ret >= PATH_MAX) {
-		printf("%s: Pathname is too long\n", __func__);
-		exit(EXIT_FAILURE);
-	}
-
-	if (!read_file(path, buf, sizeof(buf))) {
-		perror(path);
-		exit(EXIT_FAILURE);
-	}
-
-	c = strchr(buf, '[');
-	if (!c) {
-		printf("%s: Parse failure\n", __func__);
-		exit(EXIT_FAILURE);
-	}
-
-	c++;
-	memmove(buf, c, sizeof(buf) - (c - buf));
-
-	c = strchr(buf, ']');
-	if (!c) {
-		printf("%s: Parse failure\n", __func__);
-		exit(EXIT_FAILURE);
-	}
-	*c = '\0';
-
-	ret = 0;
-	while (strings[ret]) {
-		if (!strcmp(strings[ret], buf))
-			return ret;
-		ret++;
-	}
-
-	printf("Failed to parse %s\n", name);
-	exit(EXIT_FAILURE);
-}
-
-static void write_string(const char *name, const char *val)
-{
-	char path[PATH_MAX];
-	int ret;
-
-	ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name);
-	if (ret >= PATH_MAX) {
-		printf("%s: Pathname is too long\n", __func__);
-		exit(EXIT_FAILURE);
-	}
-
-	if (!write_file(path, val, strlen(val) + 1)) {
-		perror(path);
-		exit(EXIT_FAILURE);
-	}
-}
-
-static const unsigned long _read_num(const char *path)
-{
-	char buf[21];
-
-	if (read_file(path, buf, sizeof(buf)) < 0) {
-		perror("read_file(read_num)");
-		exit(EXIT_FAILURE);
-	}
-
-	return strtoul(buf, NULL, 10);
-}
-
-static const unsigned long read_num(const char *name)
-{
-	char path[PATH_MAX];
-	int ret;
-
-	ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name);
-	if (ret >= PATH_MAX) {
-		printf("%s: Pathname is too long\n", __func__);
-		exit(EXIT_FAILURE);
-	}
-	return _read_num(path);
-}
-
-static void _write_num(const char *path, unsigned long num)
-{
-	char buf[21];
-
-	sprintf(buf, "%ld", num);
-	if (!write_file(path, buf, strlen(buf) + 1)) {
-		perror(path);
-		exit(EXIT_FAILURE);
-	}
-}
-
-static void write_num(const char *name, unsigned long num)
-{
-	char path[PATH_MAX];
-	int ret;
-
-	ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name);
-	if (ret >= PATH_MAX) {
-		printf("%s: Pathname is too long\n", __func__);
-		exit(EXIT_FAILURE);
-	}
-	_write_num(path, num);
-}
-
-static void write_settings(struct settings *settings)
-{
-	struct khugepaged_settings *khugepaged = &settings->khugepaged;
-
-	write_string("enabled", thp_enabled_strings[settings->thp_enabled]);
-	write_string("defrag", thp_defrag_strings[settings->thp_defrag]);
-	write_string("shmem_enabled",
-			shmem_enabled_strings[settings->shmem_enabled]);
-	write_num("use_zero_page", settings->use_zero_page);
-
-	write_num("khugepaged/defrag", khugepaged->defrag);
-	write_num("khugepaged/alloc_sleep_millisecs",
-			khugepaged->alloc_sleep_millisecs);
-	write_num("khugepaged/scan_sleep_millisecs",
-			khugepaged->scan_sleep_millisecs);
-	write_num("khugepaged/max_ptes_none", khugepaged->max_ptes_none);
-	write_num("khugepaged/max_ptes_swap", khugepaged->max_ptes_swap);
-	write_num("khugepaged/max_ptes_shared", khugepaged->max_ptes_shared);
-	write_num("khugepaged/pages_to_scan", khugepaged->pages_to_scan);
-
-	if (file_ops && finfo.type == VMA_FILE)
-		_write_num(finfo.dev_queue_read_ahead_path,
-			   settings->read_ahead_kb);
-}
-
-#define MAX_SETTINGS_DEPTH 4
-static struct settings settings_stack[MAX_SETTINGS_DEPTH];
-static int settings_index;
-
-static struct settings *current_settings(void)
-{
-	if (!settings_index) {
-		printf("Fail: No settings set");
-		exit(EXIT_FAILURE);
-	}
-	return settings_stack + settings_index - 1;
-}
+	if (skip_settings_restore)
+		return;
 
-static void push_settings(struct settings *settings)
-{
-	if (settings_index >= MAX_SETTINGS_DEPTH) {
-		printf("Fail: Settings stack exceeded");
-		exit(EXIT_FAILURE);
-	}
-	settings_stack[settings_index++] = *settings;
-	write_settings(current_settings());
-}
+	printf("Restore THP and khugepaged settings...");
+	thp_restore_settings();
+	success("OK");
 
-static void pop_settings(void)
-{
-	if (settings_index <= 0) {
-		printf("Fail: Settings stack empty");
-		exit(EXIT_FAILURE);
-	}
-	--settings_index;
-	write_settings(current_settings());
+	skip_settings_restore = true;
 }
 
 static void restore_settings(int sig)
 {
-	if (skip_settings_restore)
-		goto out;
-
-	printf("Restore THP and khugepaged settings...");
-	write_settings(&saved_settings);
-	success("OK");
-	if (sig)
-		exit(EXIT_FAILURE);
-out:
-	exit(exit_status);
+	/* exit() will invoke the restore_settings_atexit handler. */
+	exit(sig ? EXIT_FAILURE : exit_status);
 }
 
 static void save_settings(void)
 {
 	printf("Save THP and khugepaged settings...");
-	saved_settings = (struct settings) {
-		.thp_enabled = read_string("enabled", thp_enabled_strings),
-		.thp_defrag = read_string("defrag", thp_defrag_strings),
-		.shmem_enabled =
-			read_string("shmem_enabled", shmem_enabled_strings),
-		.use_zero_page = read_num("use_zero_page"),
-	};
-	saved_settings.khugepaged = (struct khugepaged_settings) {
-		.defrag = read_num("khugepaged/defrag"),
-		.alloc_sleep_millisecs =
-			read_num("khugepaged/alloc_sleep_millisecs"),
-		.scan_sleep_millisecs =
-			read_num("khugepaged/scan_sleep_millisecs"),
-		.max_ptes_none = read_num("khugepaged/max_ptes_none"),
-		.max_ptes_swap = read_num("khugepaged/max_ptes_swap"),
-		.max_ptes_shared = read_num("khugepaged/max_ptes_shared"),
-		.pages_to_scan = read_num("khugepaged/pages_to_scan"),
-	};
 	if (file_ops && finfo.type == VMA_FILE)
-		saved_settings.read_ahead_kb =
-				_read_num(finfo.dev_queue_read_ahead_path);
+		thp_set_read_ahead_path(finfo.dev_queue_read_ahead_path);
+	thp_save_settings();
 
 	success("OK");
 
+	atexit(restore_settings_atexit);
 	signal(SIGTERM, restore_settings);
 	signal(SIGINT, restore_settings);
 	signal(SIGHUP, restore_settings);
@@ -793,7 +497,7 @@ static void __madvise_collapse(const char *msg, char *p, int nr_hpages,
 			       struct mem_ops *ops, bool expect)
 {
 	int ret;
-	struct settings settings = *current_settings();
+	struct thp_settings settings = *thp_current_settings();
 
 	printf("%s...", msg);
 
@@ -803,7 +507,7 @@ static void __madvise_collapse(const char *msg, char *p, int nr_hpages,
 	 */
 	settings.thp_enabled = THP_NEVER;
 	settings.shmem_enabled = SHMEM_NEVER;
-	push_settings(&settings);
+	thp_push_settings(&settings);
 
 	/* Clear VM_NOHUGEPAGE */
 	madvise(p, nr_hpages * hpage_pmd_size, MADV_HUGEPAGE);
@@ -815,7 +519,7 @@ static void __madvise_collapse(const char *msg, char *p, int nr_hpages,
 	else
 		success("OK");
 
-	pop_settings();
+	thp_pop_settings();
 }
 
 static void madvise_collapse(const char *msg, char *p, int nr_hpages,
@@ -845,13 +549,13 @@ static bool wait_for_scan(const char *msg, char *p, int nr_hpages,
 	madvise(p, nr_hpages * hpage_pmd_size, MADV_HUGEPAGE);
 
 	/* Wait until the second full_scan completed */
-	full_scans = read_num("khugepaged/full_scans") + 2;
+	full_scans = thp_read_num("khugepaged/full_scans") + 2;
 
 	printf("%s...", msg);
 	while (timeout--) {
 		if (ops->check_huge(p, nr_hpages))
 			break;
-		if (read_num("khugepaged/full_scans") >= full_scans)
+		if (thp_read_num("khugepaged/full_scans") >= full_scans)
 			break;
 		printf(".");
 		usleep(TICK);
@@ -904,13 +608,18 @@ static bool is_tmpfs(struct mem_ops *ops)
 	return ops == &__file_ops && finfo.type == VMA_SHMEM;
 }
 
+static bool is_anon(struct mem_ops *ops)
+{
+	return ops == &__anon_ops;
+}
+
 static void alloc_at_fault(void)
 {
-	struct settings settings = *current_settings();
+	struct thp_settings settings = *thp_current_settings();
 	char *p;
 
 	settings.thp_enabled = THP_ALWAYS;
-	push_settings(&settings);
+	thp_push_settings(&settings);
 
 	p = alloc_mapping(1);
 	*p = 1;
@@ -920,7 +629,7 @@ static void alloc_at_fault(void)
 	else
 		fail("Fail");
 
-	pop_settings();
+	thp_pop_settings();
 
 	madvise(p, page_size, MADV_DONTNEED);
 	printf("Split huge PMD on MADV_DONTNEED...");
@@ -968,11 +677,12 @@ static void collapse_single_pte_entry(struct collapse_context *c, struct mem_ops
 static void collapse_max_ptes_none(struct collapse_context *c, struct mem_ops *ops)
 {
 	int max_ptes_none = hpage_pmd_nr / 2;
-	struct settings settings = *current_settings();
+	struct thp_settings settings = *thp_current_settings();
 	void *p;
+	int fault_nr_pages = is_anon(ops) ? 1 << anon_order : 1;
 
 	settings.khugepaged.max_ptes_none = max_ptes_none;
-	push_settings(&settings);
+	thp_push_settings(&settings);
 
 	p = ops->setup_area(1);
 
@@ -983,10 +693,10 @@ static void collapse_max_ptes_none(struct collapse_context *c, struct mem_ops *o
 		goto skip;
 	}
 
-	ops->fault(p, 0, (hpage_pmd_nr - max_ptes_none - 1) * page_size);
+	ops->fault(p, 0, (hpage_pmd_nr - max_ptes_none - fault_nr_pages) * page_size);
 	c->collapse("Maybe collapse with max_ptes_none exceeded", p, 1,
 		    ops, !c->enforce_pte_scan_limits);
-	validate_memory(p, 0, (hpage_pmd_nr - max_ptes_none - 1) * page_size);
+	validate_memory(p, 0, (hpage_pmd_nr - max_ptes_none - fault_nr_pages) * page_size);
 
 	if (c->enforce_pte_scan_limits) {
 		ops->fault(p, 0, (hpage_pmd_nr - max_ptes_none) * page_size);
@@ -997,7 +707,7 @@ static void collapse_max_ptes_none(struct collapse_context *c, struct mem_ops *o
 	}
 skip:
 	ops->cleanup_area(p, hpage_pmd_size);
-	pop_settings();
+	thp_pop_settings();
 }
 
 static void collapse_swapin_single_pte(struct collapse_context *c, struct mem_ops *ops)
@@ -1028,7 +738,7 @@ out:
 
 static void collapse_max_ptes_swap(struct collapse_context *c, struct mem_ops *ops)
 {
-	int max_ptes_swap = read_num("khugepaged/max_ptes_swap");
+	int max_ptes_swap = thp_read_num("khugepaged/max_ptes_swap");
 	void *p;
 
 	p = ops->setup_area(1);
@@ -1245,11 +955,11 @@ static void collapse_fork_compound(struct collapse_context *c, struct mem_ops *o
 			fail("Fail");
 		ops->fault(p, 0, page_size);
 
-		write_num("khugepaged/max_ptes_shared", hpage_pmd_nr - 1);
+		thp_write_num("khugepaged/max_ptes_shared", hpage_pmd_nr - 1);
 		c->collapse("Collapse PTE table full of compound pages in child",
 			    p, 1, ops, true);
-		write_num("khugepaged/max_ptes_shared",
-			  current_settings()->khugepaged.max_ptes_shared);
+		thp_write_num("khugepaged/max_ptes_shared",
+			  thp_current_settings()->khugepaged.max_ptes_shared);
 
 		validate_memory(p, 0, hpage_pmd_size);
 		ops->cleanup_area(p, hpage_pmd_size);
@@ -1270,7 +980,7 @@ static void collapse_fork_compound(struct collapse_context *c, struct mem_ops *o
 
 static void collapse_max_ptes_shared(struct collapse_context *c, struct mem_ops *ops)
 {
-	int max_ptes_shared = read_num("khugepaged/max_ptes_shared");
+	int max_ptes_shared = thp_read_num("khugepaged/max_ptes_shared");
 	int wstatus;
 	void *p;
 
@@ -1373,7 +1083,7 @@ static void madvise_retracted_page_tables(struct collapse_context *c,
 
 static void usage(void)
 {
-	fprintf(stderr, "\nUsage: ./khugepaged <test type> [dir]\n\n");
+	fprintf(stderr, "\nUsage: ./khugepaged [OPTIONS] <test type> [dir]\n\n");
 	fprintf(stderr, "\t<test type>\t: <context>:<mem_type>\n");
 	fprintf(stderr, "\t<context>\t: [all|khugepaged|madvise]\n");
 	fprintf(stderr, "\t<mem_type>\t: [all|anon|file|shmem]\n");
@@ -1382,15 +1092,34 @@ static void usage(void)
 	fprintf(stderr,	"\tCONFIG_READ_ONLY_THP_FOR_FS=y\n");
 	fprintf(stderr, "\n\tif [dir] is a (sub)directory of a tmpfs mount, tmpfs must be\n");
 	fprintf(stderr,	"\tmounted with huge=madvise option for khugepaged tests to work\n");
+	fprintf(stderr,	"\n\tSupported Options:\n");
+	fprintf(stderr,	"\t\t-h: This help message.\n");
+	fprintf(stderr,	"\t\t-s: mTHP size, expressed as page order.\n");
+	fprintf(stderr,	"\t\t    Defaults to 0. Use this size for anon allocations.\n");
 	exit(1);
 }
 
-static void parse_test_type(int argc, const char **argv)
+static void parse_test_type(int argc, char **argv)
 {
+	int opt;
 	char *buf;
 	const char *token;
 
-	if (argc == 1) {
+	while ((opt = getopt(argc, argv, "s:h")) != -1) {
+		switch (opt) {
+		case 's':
+			anon_order = atoi(optarg);
+			break;
+		case 'h':
+		default:
+			usage();
+		}
+	}
+
+	argv += optind;
+	argc -= optind;
+
+	if (argc == 0) {
 		/* Backwards compatibility */
 		khugepaged_context =  &__khugepaged_context;
 		madvise_context =  &__madvise_context;
@@ -1398,7 +1127,7 @@ static void parse_test_type(int argc, const char **argv)
 		return;
 	}
 
-	buf = strdup(argv[1]);
+	buf = strdup(argv[0]);
 	token = strsep(&buf, ":");
 
 	if (!strcmp(token, "all")) {
@@ -1432,13 +1161,16 @@ static void parse_test_type(int argc, const char **argv)
 	if (!file_ops)
 		return;
 
-	if (argc != 3)
+	if (argc != 2)
 		usage();
+
+	get_finfo(argv[1]);
 }
 
-int main(int argc, const char **argv)
+int main(int argc, char **argv)
 {
-	struct settings default_settings = {
+	int hpage_pmd_order;
+	struct thp_settings default_settings = {
 		.thp_enabled = THP_MADVISE,
 		.thp_defrag = THP_DEFRAG_ALWAYS,
 		.shmem_enabled = SHMEM_ADVISE,
@@ -1460,9 +1192,6 @@ int main(int argc, const char **argv)
 
 	parse_test_type(argc, argv);
 
-	if (file_ops)
-		get_finfo(argv[2]);
-
 	setbuf(stdout, NULL);
 
 	page_size = getpagesize();
@@ -1472,14 +1201,17 @@ int main(int argc, const char **argv)
 		exit(EXIT_FAILURE);
 	}
 	hpage_pmd_nr = hpage_pmd_size / page_size;
+	hpage_pmd_order = __builtin_ctz(hpage_pmd_nr);
 
 	default_settings.khugepaged.max_ptes_none = hpage_pmd_nr - 1;
 	default_settings.khugepaged.max_ptes_swap = hpage_pmd_nr / 8;
 	default_settings.khugepaged.max_ptes_shared = hpage_pmd_nr / 2;
 	default_settings.khugepaged.pages_to_scan = hpage_pmd_nr * 8;
+	default_settings.hugepages[hpage_pmd_order].enabled = THP_INHERIT;
+	default_settings.hugepages[anon_order].enabled = THP_ALWAYS;
 
 	save_settings();
-	push_settings(&default_settings);
+	thp_push_settings(&default_settings);
 
 	alloc_at_fault();
 
diff --git a/tools/testing/selftests/mm/memfd_secret.c b/tools/testing/selftests/mm/memfd_secret.c
index 957b9e18c729..9b298f6a04b3 100644
--- a/tools/testing/selftests/mm/memfd_secret.c
+++ b/tools/testing/selftests/mm/memfd_secret.c
@@ -62,6 +62,9 @@ static void test_mlock_limit(int fd)
 	char *mem;
 
 	len = mlock_limit_cur;
+	if (len % page_size != 0)
+		len = (len/page_size) * page_size;
+
 	mem = mmap(NULL, len, prot, mode, fd, 0);
 	if (mem == MAP_FAILED) {
 		fail("unable to mmap secret memory\n");
diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c
index 0161fb49fc6e..d59517ed3d48 100644
--- a/tools/testing/selftests/mm/pagemap_ioctl.c
+++ b/tools/testing/selftests/mm/pagemap_ioctl.c
@@ -36,6 +36,7 @@ int pagemap_fd;
 int uffd;
 int page_size;
 int hpage_size;
+const char *progname;
 
 #define LEN(region)	((region.end - region.start)/page_size)
 
@@ -94,19 +95,19 @@ int init_uffd(void)
 
 	uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY);
 	if (uffd == -1)
-		ksft_exit_fail_msg("uffd syscall failed\n");
+		return uffd;
 
 	uffdio_api.api = UFFD_API;
 	uffdio_api.features = UFFD_FEATURE_WP_UNPOPULATED | UFFD_FEATURE_WP_ASYNC |
 			      UFFD_FEATURE_WP_HUGETLBFS_SHMEM;
 	if (ioctl(uffd, UFFDIO_API, &uffdio_api))
-		ksft_exit_fail_msg("UFFDIO_API\n");
+		return -1;
 
 	if (!(uffdio_api.api & UFFDIO_REGISTER_MODE_WP) ||
 	    !(uffdio_api.features & UFFD_FEATURE_WP_UNPOPULATED) ||
 	    !(uffdio_api.features & UFFD_FEATURE_WP_ASYNC) ||
 	    !(uffdio_api.features & UFFD_FEATURE_WP_HUGETLBFS_SHMEM))
-		ksft_exit_fail_msg("UFFDIO_API error %llu\n", uffdio_api.api);
+		return -1;
 
 	return 0;
 }
@@ -1149,17 +1150,17 @@ int sanity_tests(void)
 	munmap(mem, mem_size);
 
 	/* 9. Memory mapped file */
-	fd = open(__FILE__, O_RDONLY);
+	fd = open(progname, O_RDONLY);
 	if (fd < 0)
-		ksft_exit_fail_msg("%s Memory mapped file\n");
+		ksft_exit_fail_msg("%s Memory mapped file\n", __func__);
 
-	ret = stat(__FILE__, &sbuf);
+	ret = stat(progname, &sbuf);
 	if (ret < 0)
 		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
 
 	fmem = mmap(NULL, sbuf.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
 	if (fmem == MAP_FAILED)
-		ksft_exit_fail_msg("error nomem %ld %s\n", errno, strerror(errno));
+		ksft_exit_fail_msg("error nomem %d %s\n", errno, strerror(errno));
 
 	tmp_buf = malloc(sbuf.st_size);
 	memcpy(tmp_buf, fmem, sbuf.st_size);
@@ -1189,7 +1190,7 @@ int sanity_tests(void)
 
 	fmem = mmap(NULL, buf_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
 	if (fmem == MAP_FAILED)
-		ksft_exit_fail_msg("error nomem %ld %s\n", errno, strerror(errno));
+		ksft_exit_fail_msg("error nomem %d %s\n", errno, strerror(errno));
 
 	wp_init(fmem, buf_size);
 	wp_addr_range(fmem, buf_size);
@@ -1472,13 +1473,19 @@ static void transact_test(int page_size)
 			      extra_thread_faults);
 }
 
-int main(void)
+int main(int argc, char *argv[])
 {
 	int mem_size, shmid, buf_size, fd, i, ret;
 	char *mem, *map, *fmem;
 	struct stat sbuf;
 
+	progname = argv[0];
+
 	ksft_print_header();
+
+	if (init_uffd())
+		return ksft_exit_pass();
+
 	ksft_set_plan(115);
 
 	page_size = getpagesize();
@@ -1488,9 +1495,6 @@ int main(void)
 	if (pagemap_fd < 0)
 		return -EINVAL;
 
-	if (init_uffd())
-		ksft_exit_fail_msg("uffd init failed\n");
-
 	/* 1. Sanity testing */
 	sanity_tests_sd();
 
@@ -1595,7 +1599,7 @@ int main(void)
 
 	fmem = mmap(NULL, sbuf.st_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
 	if (fmem == MAP_FAILED)
-		ksft_exit_fail_msg("error nomem %ld %s\n", errno, strerror(errno));
+		ksft_exit_fail_msg("error nomem %d %s\n", errno, strerror(errno));
 
 	wp_init(fmem, sbuf.st_size);
 	wp_addr_range(fmem, sbuf.st_size);
@@ -1623,7 +1627,7 @@ int main(void)
 
 	fmem = mmap(NULL, buf_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
 	if (fmem == MAP_FAILED)
-		ksft_exit_fail_msg("error nomem %ld %s\n", errno, strerror(errno));
+		ksft_exit_fail_msg("error nomem %d %s\n", errno, strerror(errno));
 
 	wp_init(fmem, buf_size);
 	wp_addr_range(fmem, buf_size);
diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
index cc16f6ca8533..246d53a5d7f2 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -5,6 +5,7 @@
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
 
+count_total=0
 count_pass=0
 count_fail=0
 count_skip=0
@@ -17,6 +18,7 @@ usage: ${BASH_SOURCE[0]:-$0} [ options ]
   -a: run all tests, including extra ones
   -t: specify specific categories to tests to run
   -h: display this message
+  -n: disable TAP output
 
 The default behavior is to run required tests only.  If -a is specified,
 will run all tests.
@@ -77,12 +79,14 @@ EOF
 }
 
 RUN_ALL=false
+TAP_PREFIX="# "
 
-while getopts "aht:" OPT; do
+while getopts "aht:n" OPT; do
 	case ${OPT} in
 		"a") RUN_ALL=true ;;
 		"h") usage ;;
 		"t") VM_SELFTEST_ITEMS=${OPTARG} ;;
+		"n") TAP_PREFIX= ;;
 	esac
 done
 shift $((OPTIND -1))
@@ -184,30 +188,52 @@ fi
 VADDR64=0
 echo "$ARCH64STR" | grep "$ARCH" &>/dev/null && VADDR64=1
 
+tap_prefix() {
+	sed -e "s/^/${TAP_PREFIX}/"
+}
+
+tap_output() {
+	if [[ ! -z "$TAP_PREFIX" ]]; then
+		read str
+		echo $str
+	fi
+}
+
+pretty_name() {
+	echo "$*" | sed -e 's/^\(bash \)\?\.\///'
+}
+
 # Usage: run_test [test binary] [arbitrary test arguments...]
 run_test() {
 	if test_selected ${CATEGORY}; then
+		local test=$(pretty_name "$*")
 		local title="running $*"
 		local sep=$(echo -n "$title" | tr "[:graph:][:space:]" -)
-		printf "%s\n%s\n%s\n" "$sep" "$title" "$sep"
+		printf "%s\n%s\n%s\n" "$sep" "$title" "$sep" | tap_prefix
 
-		"$@"
-		local ret=$?
+		("$@" 2>&1) | tap_prefix
+		local ret=${PIPESTATUS[0]}
+		count_total=$(( count_total + 1 ))
 		if [ $ret -eq 0 ]; then
 			count_pass=$(( count_pass + 1 ))
-			echo "[PASS]"
+			echo "[PASS]" | tap_prefix
+			echo "ok ${count_total} ${test}" | tap_output
 		elif [ $ret -eq $ksft_skip ]; then
 			count_skip=$(( count_skip + 1 ))
-			echo "[SKIP]"
+			echo "[SKIP]" | tap_prefix
+			echo "ok ${count_total} ${test} # SKIP" | tap_output
 			exitcode=$ksft_skip
 		else
 			count_fail=$(( count_fail + 1 ))
-			echo "[FAIL]"
+			echo "[FAIL]" | tap_prefix
+			echo "not ok ${count_total} ${test} # exit=$ret" | tap_output
 			exitcode=1
 		fi
 	fi # test_selected
 }
 
+echo "TAP version 13" | tap_output
+
 CATEGORY="hugetlb" run_test ./hugepage-mmap
 
 shmmax=$(cat /proc/sys/kernel/shmmax)
@@ -223,14 +249,17 @@ CATEGORY="hugetlb" run_test ./hugepage-mremap
 CATEGORY="hugetlb" run_test ./hugepage-vmemmap
 CATEGORY="hugetlb" run_test ./hugetlb-madvise
 
+nr_hugepages_tmp=$(cat /proc/sys/vm/nr_hugepages)
 # For this test, we need one and just one huge page
 echo 1 > /proc/sys/vm/nr_hugepages
 CATEGORY="hugetlb" run_test ./hugetlb_fault_after_madv
+# Restore the previous number of huge pages, since further tests rely on it
+echo "$nr_hugepages_tmp" > /proc/sys/vm/nr_hugepages
 
 if test_selected "hugetlb"; then
-	echo "NOTE: These hugetlb tests provide minimal coverage.  Use"
-	echo "      https://github.com/libhugetlbfs/libhugetlbfs.git for"
-	echo "      hugetlb regression testing."
+	echo "NOTE: These hugetlb tests provide minimal coverage.  Use"	  | tap_prefix
+	echo "      https://github.com/libhugetlbfs/libhugetlbfs.git for" | tap_prefix
+	echo "      hugetlb regression testing."			  | tap_prefix
 fi
 
 CATEGORY="mmap" run_test ./map_fixed_noreplace
@@ -309,7 +338,7 @@ CATEGORY="hmm" run_test bash ./test_hmm.sh smoke
 # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests
 CATEGORY="madv_populate" run_test ./madv_populate
 
-echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope
+(echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope 2>&1) | tap_prefix
 CATEGORY="memfd_secret" run_test ./memfd_secret
 
 # KSM KSM_MERGE_TIME_HUGE_PAGES test with size of 100
@@ -331,8 +360,6 @@ CATEGORY="ksm_numa" run_test ./ksm_tests -N -m 0
 
 CATEGORY="ksm" run_test ./ksm_functional_tests
 
-run_test ./ksm_functional_tests
-
 # protection_keys tests
 if [ -x ./protection_keys_32 ]
 then
@@ -356,6 +383,8 @@ CATEGORY="cow" run_test ./cow
 
 CATEGORY="thp" run_test ./khugepaged
 
+CATEGORY="thp" run_test ./khugepaged -s 2
+
 CATEGORY="thp" run_test ./transhuge-stress -d 20
 
 CATEGORY="thp" run_test ./split_huge_page_test
@@ -366,6 +395,7 @@ CATEGORY="mkdirty" run_test ./mkdirty
 
 CATEGORY="mdwe" run_test ./mdwe_test
 
-echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}"
+echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" | tap_prefix
+echo "1..${count_total}" | tap_output
 
 exit $exitcode
diff --git a/tools/testing/selftests/mm/thp_settings.c b/tools/testing/selftests/mm/thp_settings.c
new file mode 100644
index 000000000000..a4163438108e
--- /dev/null
+++ b/tools/testing/selftests/mm/thp_settings.c
@@ -0,0 +1,349 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <fcntl.h>
+#include <limits.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "thp_settings.h"
+
+#define THP_SYSFS "/sys/kernel/mm/transparent_hugepage/"
+#define MAX_SETTINGS_DEPTH 4
+static struct thp_settings settings_stack[MAX_SETTINGS_DEPTH];
+static int settings_index;
+static struct thp_settings saved_settings;
+static char dev_queue_read_ahead_path[PATH_MAX];
+
+static const char * const thp_enabled_strings[] = {
+	"never",
+	"always",
+	"inherit",
+	"madvise",
+	NULL
+};
+
+static const char * const thp_defrag_strings[] = {
+	"always",
+	"defer",
+	"defer+madvise",
+	"madvise",
+	"never",
+	NULL
+};
+
+static const char * const shmem_enabled_strings[] = {
+	"always",
+	"within_size",
+	"advise",
+	"never",
+	"deny",
+	"force",
+	NULL
+};
+
+int read_file(const char *path, char *buf, size_t buflen)
+{
+	int fd;
+	ssize_t numread;
+
+	fd = open(path, O_RDONLY);
+	if (fd == -1)
+		return 0;
+
+	numread = read(fd, buf, buflen - 1);
+	if (numread < 1) {
+		close(fd);
+		return 0;
+	}
+
+	buf[numread] = '\0';
+	close(fd);
+
+	return (unsigned int) numread;
+}
+
+int write_file(const char *path, const char *buf, size_t buflen)
+{
+	int fd;
+	ssize_t numwritten;
+
+	fd = open(path, O_WRONLY);
+	if (fd == -1) {
+		printf("open(%s)\n", path);
+		exit(EXIT_FAILURE);
+		return 0;
+	}
+
+	numwritten = write(fd, buf, buflen - 1);
+	close(fd);
+	if (numwritten < 1) {
+		printf("write(%s)\n", buf);
+		exit(EXIT_FAILURE);
+		return 0;
+	}
+
+	return (unsigned int) numwritten;
+}
+
+const unsigned long read_num(const char *path)
+{
+	char buf[21];
+
+	if (read_file(path, buf, sizeof(buf)) < 0) {
+		perror("read_file()");
+		exit(EXIT_FAILURE);
+	}
+
+	return strtoul(buf, NULL, 10);
+}
+
+void write_num(const char *path, unsigned long num)
+{
+	char buf[21];
+
+	sprintf(buf, "%ld", num);
+	if (!write_file(path, buf, strlen(buf) + 1)) {
+		perror(path);
+		exit(EXIT_FAILURE);
+	}
+}
+
+int thp_read_string(const char *name, const char * const strings[])
+{
+	char path[PATH_MAX];
+	char buf[256];
+	char *c;
+	int ret;
+
+	ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name);
+	if (ret >= PATH_MAX) {
+		printf("%s: Pathname is too long\n", __func__);
+		exit(EXIT_FAILURE);
+	}
+
+	if (!read_file(path, buf, sizeof(buf))) {
+		perror(path);
+		exit(EXIT_FAILURE);
+	}
+
+	c = strchr(buf, '[');
+	if (!c) {
+		printf("%s: Parse failure\n", __func__);
+		exit(EXIT_FAILURE);
+	}
+
+	c++;
+	memmove(buf, c, sizeof(buf) - (c - buf));
+
+	c = strchr(buf, ']');
+	if (!c) {
+		printf("%s: Parse failure\n", __func__);
+		exit(EXIT_FAILURE);
+	}
+	*c = '\0';
+
+	ret = 0;
+	while (strings[ret]) {
+		if (!strcmp(strings[ret], buf))
+			return ret;
+		ret++;
+	}
+
+	printf("Failed to parse %s\n", name);
+	exit(EXIT_FAILURE);
+}
+
+void thp_write_string(const char *name, const char *val)
+{
+	char path[PATH_MAX];
+	int ret;
+
+	ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name);
+	if (ret >= PATH_MAX) {
+		printf("%s: Pathname is too long\n", __func__);
+		exit(EXIT_FAILURE);
+	}
+
+	if (!write_file(path, val, strlen(val) + 1)) {
+		perror(path);
+		exit(EXIT_FAILURE);
+	}
+}
+
+const unsigned long thp_read_num(const char *name)
+{
+	char path[PATH_MAX];
+	int ret;
+
+	ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name);
+	if (ret >= PATH_MAX) {
+		printf("%s: Pathname is too long\n", __func__);
+		exit(EXIT_FAILURE);
+	}
+	return read_num(path);
+}
+
+void thp_write_num(const char *name, unsigned long num)
+{
+	char path[PATH_MAX];
+	int ret;
+
+	ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name);
+	if (ret >= PATH_MAX) {
+		printf("%s: Pathname is too long\n", __func__);
+		exit(EXIT_FAILURE);
+	}
+	write_num(path, num);
+}
+
+void thp_read_settings(struct thp_settings *settings)
+{
+	unsigned long orders = thp_supported_orders();
+	char path[PATH_MAX];
+	int i;
+
+	*settings = (struct thp_settings) {
+		.thp_enabled = thp_read_string("enabled", thp_enabled_strings),
+		.thp_defrag = thp_read_string("defrag", thp_defrag_strings),
+		.shmem_enabled =
+			thp_read_string("shmem_enabled", shmem_enabled_strings),
+		.use_zero_page = thp_read_num("use_zero_page"),
+	};
+	settings->khugepaged = (struct khugepaged_settings) {
+		.defrag = thp_read_num("khugepaged/defrag"),
+		.alloc_sleep_millisecs =
+			thp_read_num("khugepaged/alloc_sleep_millisecs"),
+		.scan_sleep_millisecs =
+			thp_read_num("khugepaged/scan_sleep_millisecs"),
+		.max_ptes_none = thp_read_num("khugepaged/max_ptes_none"),
+		.max_ptes_swap = thp_read_num("khugepaged/max_ptes_swap"),
+		.max_ptes_shared = thp_read_num("khugepaged/max_ptes_shared"),
+		.pages_to_scan = thp_read_num("khugepaged/pages_to_scan"),
+	};
+	if (dev_queue_read_ahead_path[0])
+		settings->read_ahead_kb = read_num(dev_queue_read_ahead_path);
+
+	for (i = 0; i < NR_ORDERS; i++) {
+		if (!((1 << i) & orders)) {
+			settings->hugepages[i].enabled = THP_NEVER;
+			continue;
+		}
+		snprintf(path, PATH_MAX, "hugepages-%ukB/enabled",
+			(getpagesize() >> 10) << i);
+		settings->hugepages[i].enabled =
+			thp_read_string(path, thp_enabled_strings);
+	}
+}
+
+void thp_write_settings(struct thp_settings *settings)
+{
+	struct khugepaged_settings *khugepaged = &settings->khugepaged;
+	unsigned long orders = thp_supported_orders();
+	char path[PATH_MAX];
+	int enabled;
+	int i;
+
+	thp_write_string("enabled", thp_enabled_strings[settings->thp_enabled]);
+	thp_write_string("defrag", thp_defrag_strings[settings->thp_defrag]);
+	thp_write_string("shmem_enabled",
+			shmem_enabled_strings[settings->shmem_enabled]);
+	thp_write_num("use_zero_page", settings->use_zero_page);
+
+	thp_write_num("khugepaged/defrag", khugepaged->defrag);
+	thp_write_num("khugepaged/alloc_sleep_millisecs",
+			khugepaged->alloc_sleep_millisecs);
+	thp_write_num("khugepaged/scan_sleep_millisecs",
+			khugepaged->scan_sleep_millisecs);
+	thp_write_num("khugepaged/max_ptes_none", khugepaged->max_ptes_none);
+	thp_write_num("khugepaged/max_ptes_swap", khugepaged->max_ptes_swap);
+	thp_write_num("khugepaged/max_ptes_shared", khugepaged->max_ptes_shared);
+	thp_write_num("khugepaged/pages_to_scan", khugepaged->pages_to_scan);
+
+	if (dev_queue_read_ahead_path[0])
+		write_num(dev_queue_read_ahead_path, settings->read_ahead_kb);
+
+	for (i = 0; i < NR_ORDERS; i++) {
+		if (!((1 << i) & orders))
+			continue;
+		snprintf(path, PATH_MAX, "hugepages-%ukB/enabled",
+			(getpagesize() >> 10) << i);
+		enabled = settings->hugepages[i].enabled;
+		thp_write_string(path, thp_enabled_strings[enabled]);
+	}
+}
+
+struct thp_settings *thp_current_settings(void)
+{
+	if (!settings_index) {
+		printf("Fail: No settings set");
+		exit(EXIT_FAILURE);
+	}
+	return settings_stack + settings_index - 1;
+}
+
+void thp_push_settings(struct thp_settings *settings)
+{
+	if (settings_index >= MAX_SETTINGS_DEPTH) {
+		printf("Fail: Settings stack exceeded");
+		exit(EXIT_FAILURE);
+	}
+	settings_stack[settings_index++] = *settings;
+	thp_write_settings(thp_current_settings());
+}
+
+void thp_pop_settings(void)
+{
+	if (settings_index <= 0) {
+		printf("Fail: Settings stack empty");
+		exit(EXIT_FAILURE);
+	}
+	--settings_index;
+	thp_write_settings(thp_current_settings());
+}
+
+void thp_restore_settings(void)
+{
+	thp_write_settings(&saved_settings);
+}
+
+void thp_save_settings(void)
+{
+	thp_read_settings(&saved_settings);
+}
+
+void thp_set_read_ahead_path(char *path)
+{
+	if (!path) {
+		dev_queue_read_ahead_path[0] = '\0';
+		return;
+	}
+
+	strncpy(dev_queue_read_ahead_path, path,
+		sizeof(dev_queue_read_ahead_path));
+	dev_queue_read_ahead_path[sizeof(dev_queue_read_ahead_path) - 1] = '\0';
+}
+
+unsigned long thp_supported_orders(void)
+{
+	unsigned long orders = 0;
+	char path[PATH_MAX];
+	char buf[256];
+	int ret;
+	int i;
+
+	for (i = 0; i < NR_ORDERS; i++) {
+		ret = snprintf(path, PATH_MAX, THP_SYSFS "hugepages-%ukB/enabled",
+			(getpagesize() >> 10) << i);
+		if (ret >= PATH_MAX) {
+			printf("%s: Pathname is too long\n", __func__);
+			exit(EXIT_FAILURE);
+		}
+
+		ret = read_file(path, buf, sizeof(buf));
+		if (ret)
+			orders |= 1UL << i;
+	}
+
+	return orders;
+}
diff --git a/tools/testing/selftests/mm/thp_settings.h b/tools/testing/selftests/mm/thp_settings.h
new file mode 100644
index 000000000000..71cbff05f4c7
--- /dev/null
+++ b/tools/testing/selftests/mm/thp_settings.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __THP_SETTINGS_H__
+#define __THP_SETTINGS_H__
+
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdint.h>
+
+enum thp_enabled {
+	THP_NEVER,
+	THP_ALWAYS,
+	THP_INHERIT,
+	THP_MADVISE,
+};
+
+enum thp_defrag {
+	THP_DEFRAG_ALWAYS,
+	THP_DEFRAG_DEFER,
+	THP_DEFRAG_DEFER_MADVISE,
+	THP_DEFRAG_MADVISE,
+	THP_DEFRAG_NEVER,
+};
+
+enum shmem_enabled {
+	SHMEM_ALWAYS,
+	SHMEM_WITHIN_SIZE,
+	SHMEM_ADVISE,
+	SHMEM_NEVER,
+	SHMEM_DENY,
+	SHMEM_FORCE,
+};
+
+#define NR_ORDERS 20
+
+struct hugepages_settings {
+	enum thp_enabled enabled;
+};
+
+struct khugepaged_settings {
+	bool defrag;
+	unsigned int alloc_sleep_millisecs;
+	unsigned int scan_sleep_millisecs;
+	unsigned int max_ptes_none;
+	unsigned int max_ptes_swap;
+	unsigned int max_ptes_shared;
+	unsigned long pages_to_scan;
+};
+
+struct thp_settings {
+	enum thp_enabled thp_enabled;
+	enum thp_defrag thp_defrag;
+	enum shmem_enabled shmem_enabled;
+	bool use_zero_page;
+	struct khugepaged_settings khugepaged;
+	unsigned long read_ahead_kb;
+	struct hugepages_settings hugepages[NR_ORDERS];
+};
+
+int read_file(const char *path, char *buf, size_t buflen);
+int write_file(const char *path, const char *buf, size_t buflen);
+const unsigned long read_num(const char *path);
+void write_num(const char *path, unsigned long num);
+
+int thp_read_string(const char *name, const char * const strings[]);
+void thp_write_string(const char *name, const char *val);
+const unsigned long thp_read_num(const char *name);
+void thp_write_num(const char *name, unsigned long num);
+
+void thp_write_settings(struct thp_settings *settings);
+void thp_read_settings(struct thp_settings *settings);
+struct thp_settings *thp_current_settings(void);
+void thp_push_settings(struct thp_settings *settings);
+void thp_pop_settings(void);
+void thp_restore_settings(void);
+void thp_save_settings(void);
+
+void thp_set_read_ahead_path(char *path);
+unsigned long thp_supported_orders(void);
+
+#endif /* __THP_SETTINGS_H__ */
diff --git a/tools/testing/selftests/mm/thuge-gen.c b/tools/testing/selftests/mm/thuge-gen.c
index 16ed4dfa7359..622987f12c89 100644
--- a/tools/testing/selftests/mm/thuge-gen.c
+++ b/tools/testing/selftests/mm/thuge-gen.c
@@ -3,7 +3,8 @@
 
    Before running this huge pages for each huge page size must have been
    reserved.
-   For large pages beyond MAX_ORDER (like 1GB on x86) boot options must be used.
+   For large pages beyond MAX_PAGE_ORDER (like 1GB on x86) boot options must
+   be used.
    Also shmmax must be increased.
    And you need to run as root to work around some weird permissions in shm.
    And nothing using huge pages should run in parallel.
diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c
index 02b89860e193..b0ac0ec2356d 100644
--- a/tools/testing/selftests/mm/uffd-common.c
+++ b/tools/testing/selftests/mm/uffd-common.c
@@ -17,6 +17,7 @@ bool map_shared;
 bool test_uffdio_wp = true;
 unsigned long long *count_verify;
 uffd_test_ops_t *uffd_test_ops;
+uffd_test_case_ops_t *uffd_test_case_ops;
 
 static int uffd_mem_fd_create(off_t mem_size, bool hugetlb)
 {
@@ -262,7 +263,7 @@ static inline void munmap_area(void **area)
 	*area = NULL;
 }
 
-static void uffd_test_ctx_clear(void)
+void uffd_test_ctx_clear(void)
 {
 	size_t i;
 
@@ -298,7 +299,11 @@ int uffd_test_ctx_init(uint64_t features, const char **errmsg)
 	unsigned long nr, cpu;
 	int ret;
 
-	uffd_test_ctx_clear();
+	if (uffd_test_case_ops && uffd_test_case_ops->pre_alloc) {
+		ret = uffd_test_case_ops->pre_alloc(errmsg);
+		if (ret)
+			return ret;
+	}
 
 	ret = uffd_test_ops->allocate_area((void **)&area_src, true);
 	ret |= uffd_test_ops->allocate_area((void **)&area_dst, false);
@@ -308,6 +313,12 @@ int uffd_test_ctx_init(uint64_t features, const char **errmsg)
 		return ret;
 	}
 
+	if (uffd_test_case_ops && uffd_test_case_ops->post_alloc) {
+		ret = uffd_test_case_ops->post_alloc(errmsg);
+		if (ret)
+			return ret;
+	}
+
 	ret = userfaultfd_open(&features);
 	if (ret) {
 		if (errmsg)
@@ -620,6 +631,30 @@ int copy_page(int ufd, unsigned long offset, bool wp)
 	return __copy_page(ufd, offset, false, wp);
 }
 
+int move_page(int ufd, unsigned long offset, unsigned long len)
+{
+	struct uffdio_move uffdio_move;
+
+	if (offset + len > nr_pages * page_size)
+		err("unexpected offset %lu and length %lu\n", offset, len);
+	uffdio_move.dst = (unsigned long) area_dst + offset;
+	uffdio_move.src = (unsigned long) area_src + offset;
+	uffdio_move.len = len;
+	uffdio_move.mode = UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES;
+	uffdio_move.move = 0;
+	if (ioctl(ufd, UFFDIO_MOVE, &uffdio_move)) {
+		/* real retval in uffdio_move.move */
+		if (uffdio_move.move != -EEXIST)
+			err("UFFDIO_MOVE error: %"PRId64,
+			    (int64_t)uffdio_move.move);
+		wake_range(ufd, uffdio_move.dst, len);
+	} else if (uffdio_move.move != len) {
+		err("UFFDIO_MOVE error: %"PRId64, (int64_t)uffdio_move.move);
+	} else
+		return 1;
+	return 0;
+}
+
 int uffd_open_dev(unsigned int flags)
 {
 	int fd, uffd;
diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h
index 7c4fa964c3b0..cb055282c89c 100644
--- a/tools/testing/selftests/mm/uffd-common.h
+++ b/tools/testing/selftests/mm/uffd-common.h
@@ -90,6 +90,12 @@ struct uffd_test_ops {
 };
 typedef struct uffd_test_ops uffd_test_ops_t;
 
+struct uffd_test_case_ops {
+	int (*pre_alloc)(const char **errmsg);
+	int (*post_alloc)(const char **errmsg);
+};
+typedef struct uffd_test_case_ops uffd_test_case_ops_t;
+
 extern unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size;
 extern char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap;
 extern int uffd, uffd_flags, finished, *pipefd, test_type;
@@ -102,15 +108,18 @@ extern uffd_test_ops_t anon_uffd_test_ops;
 extern uffd_test_ops_t shmem_uffd_test_ops;
 extern uffd_test_ops_t hugetlb_uffd_test_ops;
 extern uffd_test_ops_t *uffd_test_ops;
+extern uffd_test_case_ops_t *uffd_test_case_ops;
 
 void uffd_stats_report(struct uffd_args *args, int n_cpus);
 int uffd_test_ctx_init(uint64_t features, const char **errmsg);
+void uffd_test_ctx_clear(void);
 int userfaultfd_open(uint64_t *features);
 int uffd_read_msg(int ufd, struct uffd_msg *msg);
 void wp_range(int ufd, __u64 start, __u64 len, bool wp);
 void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args);
 int __copy_page(int ufd, unsigned long offset, bool retry, bool wp);
 int copy_page(int ufd, unsigned long offset, bool wp);
+int move_page(int ufd, unsigned long offset, unsigned long len);
 void *uffd_poll_thread(void *arg);
 
 int uffd_open_dev(unsigned int flags);
diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c
index 469e0476af26..7e83829bbb33 100644
--- a/tools/testing/selftests/mm/uffd-stress.c
+++ b/tools/testing/selftests/mm/uffd-stress.c
@@ -323,8 +323,10 @@ static int userfaultfd_stress(void)
 		uffd_stats_reset(args, nr_cpus);
 
 		/* bounce pass */
-		if (stress(args))
+		if (stress(args)) {
+			uffd_test_ctx_clear();
 			return 1;
+		}
 
 		/* Clear all the write protections if there is any */
 		if (test_uffdio_wp)
@@ -354,6 +356,7 @@ static int userfaultfd_stress(void)
 
 		uffd_stats_report(args, nr_cpus);
 	}
+	uffd_test_ctx_clear();
 
 	return 0;
 }
diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c
index 2709a34a39c5..cce90a10515a 100644
--- a/tools/testing/selftests/mm/uffd-unit-tests.c
+++ b/tools/testing/selftests/mm/uffd-unit-tests.c
@@ -23,6 +23,9 @@
 #define  MEM_ALL  (MEM_ANON | MEM_SHMEM | MEM_SHMEM_PRIVATE | \
 		   MEM_HUGETLB | MEM_HUGETLB_PRIVATE)
 
+#define ALIGN_UP(x, align_to) \
+	((__typeof__(x))((((unsigned long)(x)) + ((align_to)-1)) & ~((align_to)-1)))
+
 struct mem_type {
 	const char *name;
 	unsigned int mem_flag;
@@ -78,6 +81,7 @@ typedef struct {
 	uffd_test_fn uffd_fn;
 	unsigned int mem_targets;
 	uint64_t uffd_feature_required;
+	uffd_test_case_ops_t *test_case_ops;
 } uffd_test_case_t;
 
 static void uffd_test_report(void)
@@ -185,6 +189,7 @@ uffd_setup_environment(uffd_test_args_t *args, uffd_test_case_t *test,
 {
 	map_shared = mem_type->shared;
 	uffd_test_ops = mem_type->mem_ops;
+	uffd_test_case_ops = test->test_case_ops;
 
 	if (mem_type->mem_flag & (MEM_HUGETLB_PRIVATE | MEM_HUGETLB))
 		page_size = default_huge_page_size();
@@ -1062,6 +1067,188 @@ static void uffd_poison_test(uffd_test_args_t *targs)
 	uffd_test_pass();
 }
 
+static void
+uffd_move_handle_fault_common(struct uffd_msg *msg, struct uffd_args *args,
+			      unsigned long len)
+{
+	unsigned long offset;
+
+	if (msg->event != UFFD_EVENT_PAGEFAULT)
+		err("unexpected msg event %u", msg->event);
+
+	if (msg->arg.pagefault.flags &
+	    (UFFD_PAGEFAULT_FLAG_WP | UFFD_PAGEFAULT_FLAG_MINOR | UFFD_PAGEFAULT_FLAG_WRITE))
+		err("unexpected fault type %llu", msg->arg.pagefault.flags);
+
+	offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst;
+	offset &= ~(len-1);
+
+	if (move_page(uffd, offset, len))
+		args->missing_faults++;
+}
+
+static void uffd_move_handle_fault(struct uffd_msg *msg,
+				   struct uffd_args *args)
+{
+	uffd_move_handle_fault_common(msg, args, page_size);
+}
+
+static void uffd_move_pmd_handle_fault(struct uffd_msg *msg,
+				       struct uffd_args *args)
+{
+	uffd_move_handle_fault_common(msg, args, read_pmd_pagesize());
+}
+
+static void
+uffd_move_test_common(uffd_test_args_t *targs, unsigned long chunk_size,
+		      void (*handle_fault)(struct uffd_msg *msg, struct uffd_args *args))
+{
+	unsigned long nr;
+	pthread_t uffd_mon;
+	char c;
+	unsigned long long count;
+	struct uffd_args args = { 0 };
+	char *orig_area_src, *orig_area_dst;
+	unsigned long step_size, step_count;
+	unsigned long src_offs = 0;
+	unsigned long dst_offs = 0;
+
+	/* Prevent source pages from being mapped more than once */
+	if (madvise(area_src, nr_pages * page_size, MADV_DONTFORK))
+		err("madvise(MADV_DONTFORK) failure");
+
+	if (uffd_register(uffd, area_dst, nr_pages * page_size,
+			  true, false, false))
+		err("register failure");
+
+	args.handle_fault = handle_fault;
+	if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args))
+		err("uffd_poll_thread create");
+
+	step_size = chunk_size / page_size;
+	step_count = nr_pages / step_size;
+
+	if (chunk_size > page_size) {
+		char *aligned_src = ALIGN_UP(area_src, chunk_size);
+		char *aligned_dst = ALIGN_UP(area_dst, chunk_size);
+
+		if (aligned_src != area_src || aligned_dst != area_dst) {
+			src_offs = (aligned_src - area_src) / page_size;
+			dst_offs = (aligned_dst - area_dst) / page_size;
+			step_count--;
+		}
+		orig_area_src = area_src;
+		orig_area_dst = area_dst;
+		area_src = aligned_src;
+		area_dst = aligned_dst;
+	}
+
+	/*
+	 * Read each of the pages back using the UFFD-registered mapping. We
+	 * expect that the first time we touch a page, it will result in a missing
+	 * fault. uffd_poll_thread will resolve the fault by moving source
+	 * page to destination.
+	 */
+	for (nr = 0; nr < step_count * step_size; nr += step_size) {
+		unsigned long i;
+
+		/* Check area_src content */
+		for (i = 0; i < step_size; i++) {
+			count = *area_count(area_src, nr + i);
+			if (count != count_verify[src_offs + nr + i])
+				err("nr %lu source memory invalid %llu %llu\n",
+				    nr + i, count, count_verify[src_offs + nr + i]);
+		}
+
+		/* Faulting into area_dst should move the page or the huge page */
+		for (i = 0; i < step_size; i++) {
+			count = *area_count(area_dst, nr + i);
+			if (count != count_verify[dst_offs + nr + i])
+				err("nr %lu memory corruption %llu %llu\n",
+				    nr, count, count_verify[dst_offs + nr + i]);
+		}
+
+		/* Re-check area_src content which should be empty */
+		for (i = 0; i < step_size; i++) {
+			count = *area_count(area_src, nr + i);
+			if (count != 0)
+				err("nr %lu move failed %llu %llu\n",
+				    nr, count, count_verify[src_offs + nr + i]);
+		}
+	}
+	if (step_size > page_size) {
+		area_src = orig_area_src;
+		area_dst = orig_area_dst;
+	}
+
+	if (write(pipefd[1], &c, sizeof(c)) != sizeof(c))
+		err("pipe write");
+	if (pthread_join(uffd_mon, NULL))
+		err("join() failed");
+
+	if (args.missing_faults != step_count || args.minor_faults != 0)
+		uffd_test_fail("stats check error");
+	else
+		uffd_test_pass();
+}
+
+static void uffd_move_test(uffd_test_args_t *targs)
+{
+	uffd_move_test_common(targs, page_size, uffd_move_handle_fault);
+}
+
+static void uffd_move_pmd_test(uffd_test_args_t *targs)
+{
+	if (madvise(area_dst, nr_pages * page_size, MADV_HUGEPAGE))
+		err("madvise(MADV_HUGEPAGE) failure");
+	uffd_move_test_common(targs, read_pmd_pagesize(),
+			      uffd_move_pmd_handle_fault);
+}
+
+static void uffd_move_pmd_split_test(uffd_test_args_t *targs)
+{
+	if (madvise(area_dst, nr_pages * page_size, MADV_NOHUGEPAGE))
+		err("madvise(MADV_NOHUGEPAGE) failure");
+	uffd_move_test_common(targs, read_pmd_pagesize(),
+			      uffd_move_pmd_handle_fault);
+}
+
+static int prevent_hugepages(const char **errmsg)
+{
+	/* This should be done before source area is populated */
+	if (madvise(area_src, nr_pages * page_size, MADV_NOHUGEPAGE)) {
+		/* Ignore only if CONFIG_TRANSPARENT_HUGEPAGE=n */
+		if (errno != EINVAL) {
+			if (errmsg)
+				*errmsg = "madvise(MADV_NOHUGEPAGE) failed";
+			return -errno;
+		}
+	}
+	return 0;
+}
+
+static int request_hugepages(const char **errmsg)
+{
+	/* This should be done before source area is populated */
+	if (madvise(area_src, nr_pages * page_size, MADV_HUGEPAGE)) {
+		if (errmsg) {
+			*errmsg = (errno == EINVAL) ?
+				"CONFIG_TRANSPARENT_HUGEPAGE is not set" :
+				"madvise(MADV_HUGEPAGE) failed";
+		}
+		return -errno;
+	}
+	return 0;
+}
+
+struct uffd_test_case_ops uffd_move_test_case_ops = {
+	.post_alloc = prevent_hugepages,
+};
+
+struct uffd_test_case_ops uffd_move_test_pmd_case_ops = {
+	.post_alloc = request_hugepages,
+};
+
 /*
  * Test the returned uffdio_register.ioctls with different register modes.
  * Note that _UFFDIO_ZEROPAGE is tested separately in the zeropage test.
@@ -1140,6 +1327,27 @@ uffd_test_case_t uffd_tests[] = {
 		.uffd_feature_required = 0,
 	},
 	{
+		.name = "move",
+		.uffd_fn = uffd_move_test,
+		.mem_targets = MEM_ANON,
+		.uffd_feature_required = UFFD_FEATURE_MOVE,
+		.test_case_ops = &uffd_move_test_case_ops,
+	},
+	{
+		.name = "move-pmd",
+		.uffd_fn = uffd_move_pmd_test,
+		.mem_targets = MEM_ANON,
+		.uffd_feature_required = UFFD_FEATURE_MOVE,
+		.test_case_ops = &uffd_move_test_pmd_case_ops,
+	},
+	{
+		.name = "move-pmd-split",
+		.uffd_fn = uffd_move_pmd_split_test,
+		.mem_targets = MEM_ANON,
+		.uffd_feature_required = UFFD_FEATURE_MOVE,
+		.test_case_ops = &uffd_move_test_pmd_case_ops,
+	},
+	{
 		.name = "wp-fork",
 		.uffd_fn = uffd_wp_fork_test,
 		.mem_targets = MEM_ALL,
@@ -1319,6 +1527,7 @@ int main(int argc, char *argv[])
 				continue;
 			}
 			test->uffd_fn(&args);
+			uffd_test_ctx_clear();
 		}
 	}
 
diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c
index 3082b40492dd..05736c615734 100644
--- a/tools/testing/selftests/mm/vm_util.c
+++ b/tools/testing/selftests/mm/vm_util.c
@@ -4,6 +4,7 @@
 #include <dirent.h>
 #include <sys/ioctl.h>
 #include <linux/userfaultfd.h>
+#include <linux/fs.h>
 #include <sys/syscall.h>
 #include <unistd.h>
 #include "../kselftest.h"
@@ -28,19 +29,92 @@ uint64_t pagemap_get_entry(int fd, char *start)
 	return entry;
 }
 
+static uint64_t __pagemap_scan_get_categories(int fd, char *start, struct page_region *r)
+{
+	struct pm_scan_arg arg;
+
+	arg.start = (uintptr_t)start;
+	arg.end = (uintptr_t)(start + psize());
+	arg.vec = (uintptr_t)r;
+	arg.vec_len = 1;
+	arg.flags = 0;
+	arg.size = sizeof(struct pm_scan_arg);
+	arg.max_pages = 0;
+	arg.category_inverted = 0;
+	arg.category_mask = 0;
+	arg.category_anyof_mask = PAGE_IS_WPALLOWED | PAGE_IS_WRITTEN | PAGE_IS_FILE |
+				  PAGE_IS_PRESENT | PAGE_IS_SWAPPED | PAGE_IS_PFNZERO |
+				  PAGE_IS_HUGE | PAGE_IS_SOFT_DIRTY;
+	arg.return_mask = arg.category_anyof_mask;
+
+	return ioctl(fd, PAGEMAP_SCAN, &arg);
+}
+
+static uint64_t pagemap_scan_get_categories(int fd, char *start)
+{
+	struct page_region r;
+	long ret;
+
+	ret = __pagemap_scan_get_categories(fd, start, &r);
+	if (ret < 0)
+		ksft_exit_fail_msg("PAGEMAP_SCAN failed: %s\n", strerror(errno));
+	if (ret == 0)
+		return 0;
+	return r.categories;
+}
+
+/* `start` is any valid address. */
+static bool pagemap_scan_supported(int fd, char *start)
+{
+	static int supported = -1;
+	int ret;
+
+	if (supported != -1)
+		return supported;
+
+	/* Provide an invalid address in order to trigger EFAULT. */
+	ret = __pagemap_scan_get_categories(fd, start, (struct page_region *) ~0UL);
+	if (ret == 0)
+		ksft_exit_fail_msg("PAGEMAP_SCAN succeeded unexpectedly\n");
+
+	supported = errno == EFAULT;
+
+	return supported;
+}
+
+static bool page_entry_is(int fd, char *start, char *desc,
+			  uint64_t pagemap_flags, uint64_t pagescan_flags)
+{
+	bool m = pagemap_get_entry(fd, start) & pagemap_flags;
+
+	if (pagemap_scan_supported(fd, start)) {
+		bool s = pagemap_scan_get_categories(fd, start) & pagescan_flags;
+
+		if (m == s)
+			return m;
+
+		ksft_exit_fail_msg(
+			"read and ioctl return unmatched results for %s: %d %d", desc, m, s);
+	}
+	return m;
+}
+
 bool pagemap_is_softdirty(int fd, char *start)
 {
-	return pagemap_get_entry(fd, start) & PM_SOFT_DIRTY;
+	return page_entry_is(fd, start, "soft-dirty",
+				PM_SOFT_DIRTY, PAGE_IS_SOFT_DIRTY);
 }
 
 bool pagemap_is_swapped(int fd, char *start)
 {
-	return pagemap_get_entry(fd, start) & PM_SWAP;
+	return page_entry_is(fd, start, "swap", PM_SWAP, PAGE_IS_SWAPPED);
 }
 
 bool pagemap_is_populated(int fd, char *start)
 {
-	return pagemap_get_entry(fd, start) & (PM_PRESENT | PM_SWAP);
+	return page_entry_is(fd, start, "populated",
+				PM_PRESENT | PM_SWAP,
+				PAGE_IS_PRESENT | PAGE_IS_SWAPPED);
 }
 
 unsigned long pagemap_get_pfn(int fd, char *start)
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 5b2aca4c5f10..50818075e566 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -54,7 +54,7 @@ TEST_PROGS += ip_local_port_range.sh
 TEST_PROGS += rps_default_mask.sh
 TEST_PROGS += big_tcp.sh
 TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh
-TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh
+TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh lib.sh
 TEST_GEN_FILES =  socket nettest
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
 TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite
@@ -91,6 +91,8 @@ TEST_PROGS += test_bridge_neigh_suppress.sh
 TEST_PROGS += test_vxlan_nolocalbypass.sh
 TEST_PROGS += test_bridge_backup_port.sh
 TEST_PROGS += fdb_flush.sh
+TEST_PROGS += fq_band_pktlimit.sh
+TEST_PROGS += vlan_hw_filter.sh
 
 TEST_FILES := settings
 
diff --git a/tools/testing/selftests/net/af_unix/diag_uid.c b/tools/testing/selftests/net/af_unix/diag_uid.c
index 5b88f7129fea..79a3dd75590e 100644
--- a/tools/testing/selftests/net/af_unix/diag_uid.c
+++ b/tools/testing/selftests/net/af_unix/diag_uid.c
@@ -148,7 +148,6 @@ void receive_response(struct __test_metadata *_metadata,
 		.msg_iov = &iov,
 		.msg_iovlen = 1
 	};
-	struct unix_diag_req *udr;
 	struct nlmsghdr *nlh;
 	int ret;
 
diff --git a/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh b/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh
index 4a110bb01e53..92eb880c52f2 100755
--- a/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh
+++ b/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh
@@ -12,7 +12,8 @@
 # {arp,ndisc}_evict_nocarrer=0 should still contain the single ARP/ND entry
 #
 
-readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
+source lib.sh
+
 readonly V4_ADDR0=10.0.10.1
 readonly V4_ADDR1=10.0.10.2
 readonly V6_ADDR0=2001:db8:91::1
@@ -22,43 +23,29 @@ ret=0
 
 cleanup_v6()
 {
-    ip netns del me
-    ip netns del peer
+    cleanup_ns ${me} ${peer}
 
     sysctl -w net.ipv6.conf.veth1.ndisc_evict_nocarrier=1 >/dev/null 2>&1
     sysctl -w net.ipv6.conf.all.ndisc_evict_nocarrier=1 >/dev/null 2>&1
 }
 
-create_ns()
-{
-    local n=${1}
-
-    ip netns del ${n} 2>/dev/null
-
-    ip netns add ${n}
-    ip netns set ${n} $((nsid++))
-    ip -netns ${n} link set lo up
-}
-
-
 setup_v6() {
-    create_ns me
-    create_ns peer
+    setup_ns me peer
 
-    IP="ip -netns me"
+    IP="ip -netns ${me}"
 
     $IP li add veth1 type veth peer name veth2
     $IP li set veth1 up
     $IP -6 addr add $V6_ADDR0/64 dev veth1 nodad
-    $IP li set veth2 netns peer up
-    ip -netns peer -6 addr add $V6_ADDR1/64 dev veth2 nodad
+    $IP li set veth2 netns ${peer} up
+    ip -netns ${peer} -6 addr add $V6_ADDR1/64 dev veth2 nodad
 
-    ip netns exec me sysctl -w $1 >/dev/null 2>&1
+    ip netns exec ${me} sysctl -w $1 >/dev/null 2>&1
 
     # Establish an ND cache entry
-    ip netns exec me ping -6 -c1 -Iveth1 $V6_ADDR1 >/dev/null 2>&1
+    ip netns exec ${me} ping -6 -c1 -Iveth1 $V6_ADDR1 >/dev/null 2>&1
     # Should have the veth1 entry in ND table
-    ip netns exec me ip -6 neigh get $V6_ADDR1 dev veth1 >/dev/null 2>&1
+    ip netns exec ${me} ip -6 neigh get $V6_ADDR1 dev veth1 >/dev/null 2>&1
     if [ $? -ne 0 ]; then
         cleanup_v6
         echo "failed"
@@ -66,11 +53,11 @@ setup_v6() {
     fi
 
     # Set veth2 down, which will put veth1 in NOCARRIER state
-    ip netns exec peer ip link set veth2 down
+    ip netns exec ${peer} ip link set veth2 down
 }
 
 setup_v4() {
-    ip netns add "${PEER_NS}"
+    setup_ns PEER_NS
     ip link add name veth0 type veth peer name veth1
     ip link set dev veth0 up
     ip link set dev veth1 netns "${PEER_NS}"
@@ -99,8 +86,7 @@ setup_v4() {
 cleanup_v4() {
     ip neigh flush dev veth0
     ip link del veth0
-    local -r ns="$(ip netns list|grep $PEER_NS)"
-    [ -n "$ns" ] && ip netns del $ns 2>/dev/null
+    cleanup_ns $PEER_NS
 
     sysctl -w net.ipv4.conf.veth0.arp_evict_nocarrier=1 >/dev/null 2>&1
     sysctl -w net.ipv4.conf.all.arp_evict_nocarrier=1 >/dev/null 2>&1
@@ -163,7 +149,7 @@ run_ndisc_evict_nocarrier_enabled() {
 
     setup_v6 "net.ipv6.conf.veth1.ndisc_evict_nocarrier=1"
 
-    ip netns exec me ip -6 neigh get $V6_ADDR1 dev veth1 >/dev/null 2>&1
+    ip netns exec ${me} ip -6 neigh get $V6_ADDR1 dev veth1 >/dev/null 2>&1
 
     if [ $? -eq 0 ];then
         echo "failed"
@@ -180,7 +166,7 @@ run_ndisc_evict_nocarrier_disabled() {
 
     setup_v6 "net.ipv6.conf.veth1.ndisc_evict_nocarrier=0"
 
-    ip netns exec me ip -6 neigh get $V6_ADDR1 dev veth1 >/dev/null 2>&1
+    ip netns exec ${me} ip -6 neigh get $V6_ADDR1 dev veth1 >/dev/null 2>&1
 
     if [ $? -eq 0 ];then
         echo "ok"
@@ -197,7 +183,7 @@ run_ndisc_evict_nocarrier_disabled_all() {
 
     setup_v6 "net.ipv6.conf.all.ndisc_evict_nocarrier=0"
 
-    ip netns exec me ip -6 neigh get $V6_ADDR1 dev veth1 >/dev/null 2>&1
+    ip netns exec ${me} ip -6 neigh get $V6_ADDR1 dev veth1 >/dev/null 2>&1
 
     if [ $? -eq 0 ];then
         echo "ok"
diff --git a/tools/testing/selftests/net/arp_ndisc_untracked_subnets.sh b/tools/testing/selftests/net/arp_ndisc_untracked_subnets.sh
index c899b446acb6..a40c0e9bd023 100755
--- a/tools/testing/selftests/net/arp_ndisc_untracked_subnets.sh
+++ b/tools/testing/selftests/net/arp_ndisc_untracked_subnets.sh
@@ -5,16 +5,14 @@
 # garp to the router. Router accepts or ignores based on its arp_accept
 # or accept_untracked_na configuration.
 
+source lib.sh
+
 TESTS="arp ndisc"
 
-ROUTER_NS="ns-router"
-ROUTER_NS_V6="ns-router-v6"
 ROUTER_INTF="veth-router"
 ROUTER_ADDR="10.0.10.1"
 ROUTER_ADDR_V6="2001:db8:abcd:0012::1"
 
-HOST_NS="ns-host"
-HOST_NS_V6="ns-host-v6"
 HOST_INTF="veth-host"
 HOST_ADDR="10.0.10.2"
 HOST_ADDR_V6="2001:db8:abcd:0012::2"
@@ -23,13 +21,11 @@ SUBNET_WIDTH=24
 PREFIX_WIDTH_V6=64
 
 cleanup() {
-	ip netns del ${HOST_NS}
-	ip netns del ${ROUTER_NS}
+	cleanup_ns ${HOST_NS} ${ROUTER_NS}
 }
 
 cleanup_v6() {
-	ip netns del ${HOST_NS_V6}
-	ip netns del ${ROUTER_NS_V6}
+	cleanup_ns ${HOST_NS_V6} ${ROUTER_NS_V6}
 }
 
 setup() {
@@ -37,8 +33,7 @@ setup() {
 	local arp_accept=$1
 
 	# Set up two namespaces
-	ip netns add ${ROUTER_NS}
-	ip netns add ${HOST_NS}
+	setup_ns HOST_NS ROUTER_NS
 
 	# Set up interfaces veth0 and veth1, which are pairs in separate
 	# namespaces. veth0 is veth-router, veth1 is veth-host.
@@ -72,8 +67,7 @@ setup_v6() {
 	local accept_untracked_na=$1
 
 	# Set up two namespaces
-	ip netns add ${ROUTER_NS_V6}
-	ip netns add ${HOST_NS_V6}
+	setup_ns HOST_NS_V6 ROUTER_NS_V6
 
 	# Set up interfaces veth0 and veth1, which are pairs in separate
 	# namespaces. veth0 is veth-router, veth1 is veth-host.
@@ -150,7 +144,7 @@ arp_test_gratuitous() {
 	fi
 	# Supply arp_accept option to set up which sets it in sysctl
 	setup ${arp_accept}
-	ip netns exec ${HOST_NS} arping -A -U ${HOST_ADDR} -c1 2>&1 >/dev/null
+	ip netns exec ${HOST_NS} arping -A -I ${HOST_INTF} -U ${HOST_ADDR} -c1 2>&1 >/dev/null
 
 	if verify_arp $1 $2; then
 		printf "    TEST: %-60s  [ OK ]\n" "${test_msg[*]}"
diff --git a/tools/testing/selftests/net/cmsg_ipv6.sh b/tools/testing/selftests/net/cmsg_ipv6.sh
index 330d0b1ceced..f30bd57d5e38 100755
--- a/tools/testing/selftests/net/cmsg_ipv6.sh
+++ b/tools/testing/selftests/net/cmsg_ipv6.sh
@@ -1,9 +1,8 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-ksft_skip=4
+source lib.sh
 
-NS=ns
 IP6=2001:db8:1::1/64
 TGT6=2001:db8:1::2
 TMPF=$(mktemp --suffix ".pcap")
@@ -11,13 +10,11 @@ TMPF=$(mktemp --suffix ".pcap")
 cleanup()
 {
     rm -f $TMPF
-    ip netns del $NS
+    cleanup_ns $NS
 }
 
 trap cleanup EXIT
 
-NSEXE="ip netns exec $NS"
-
 tcpdump -h | grep immediate-mode >> /dev/null
 if [ $? -ne 0 ]; then
     echo "SKIP - tcpdump with --immediate-mode option required"
@@ -25,7 +22,8 @@ if [ $? -ne 0 ]; then
 fi
 
 # Namespaces
-ip netns add $NS
+setup_ns NS
+NSEXE="ip netns exec $NS"
 
 $NSEXE sysctl -w net.ipv4.ping_group_range='0 2147483647' > /dev/null
 
diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c
index 24b21b15ed3f..c79e65581dc3 100644
--- a/tools/testing/selftests/net/cmsg_sender.c
+++ b/tools/testing/selftests/net/cmsg_sender.c
@@ -45,11 +45,13 @@ struct options {
 	const char *host;
 	const char *service;
 	unsigned int size;
+	unsigned int num_pkt;
 	struct {
 		unsigned int mark;
 		unsigned int dontfrag;
 		unsigned int tclass;
 		unsigned int hlimit;
+		unsigned int priority;
 	} sockopt;
 	struct {
 		unsigned int family;
@@ -72,6 +74,7 @@ struct options {
 	} v6;
 } opt = {
 	.size = 13,
+	.num_pkt = 1,
 	.sock = {
 		.family	= AF_UNSPEC,
 		.type	= SOCK_DGRAM,
@@ -112,7 +115,7 @@ static void cs_parse_args(int argc, char *argv[])
 {
 	int o;
 
-	while ((o = getopt(argc, argv, "46sS:p:m:M:d:tf:F:c:C:l:L:H:")) != -1) {
+	while ((o = getopt(argc, argv, "46sS:p:P:m:M:n:d:tf:F:c:C:l:L:H:")) != -1) {
 		switch (o) {
 		case 's':
 			opt.silent_send = true;
@@ -138,7 +141,9 @@ static void cs_parse_args(int argc, char *argv[])
 				cs_usage(argv[0]);
 			}
 			break;
-
+		case 'P':
+			opt.sockopt.priority = atoi(optarg);
+			break;
 		case 'm':
 			opt.mark.ena = true;
 			opt.mark.val = atoi(optarg);
@@ -146,6 +151,9 @@ static void cs_parse_args(int argc, char *argv[])
 		case 'M':
 			opt.sockopt.mark = atoi(optarg);
 			break;
+		case 'n':
+			opt.num_pkt = atoi(optarg);
+			break;
 		case 'd':
 			opt.txtime.ena = true;
 			opt.txtime.delay = atoi(optarg);
@@ -410,17 +418,22 @@ static void ca_set_sockopts(int fd)
 	    setsockopt(fd, SOL_IPV6, IPV6_UNICAST_HOPS,
 		       &opt.sockopt.hlimit, sizeof(opt.sockopt.hlimit)))
 		error(ERN_SOCKOPT, errno, "setsockopt IPV6_HOPLIMIT");
+	if (opt.sockopt.priority &&
+	    setsockopt(fd, SOL_SOCKET, SO_PRIORITY,
+		       &opt.sockopt.priority, sizeof(opt.sockopt.priority)))
+		error(ERN_SOCKOPT, errno, "setsockopt SO_PRIORITY");
 }
 
 int main(int argc, char *argv[])
 {
 	struct addrinfo hints, *ai;
 	struct iovec iov[1];
+	unsigned char *buf;
 	struct msghdr msg;
 	char cbuf[1024];
-	char *buf;
 	int err;
 	int fd;
+	int i;
 
 	cs_parse_args(argc, argv);
 
@@ -480,24 +493,27 @@ int main(int argc, char *argv[])
 
 	cs_write_cmsg(fd, &msg, cbuf, sizeof(cbuf));
 
-	err = sendmsg(fd, &msg, 0);
-	if (err < 0) {
-		if (!opt.silent_send)
-			fprintf(stderr, "send failed: %s\n", strerror(errno));
-		err = ERN_SEND;
-		goto err_out;
-	} else if (err != (int)opt.size) {
-		fprintf(stderr, "short send\n");
-		err = ERN_SEND_SHORT;
-		goto err_out;
-	} else {
-		err = ERN_SUCCESS;
+	for (i = 0; i < opt.num_pkt; i++) {
+		err = sendmsg(fd, &msg, 0);
+		if (err < 0) {
+			if (!opt.silent_send)
+				fprintf(stderr, "send failed: %s\n", strerror(errno));
+			err = ERN_SEND;
+			goto err_out;
+		} else if (err != (int)opt.size) {
+			fprintf(stderr, "short send\n");
+			err = ERN_SEND_SHORT;
+			goto err_out;
+		}
 	}
+	err = ERN_SUCCESS;
 
-	/* Make sure all timestamps have time to loop back */
-	usleep(opt.txtime.delay);
+	if (opt.ts.ena) {
+		/* Make sure all timestamps have time to loop back */
+		usleep(opt.txtime.delay);
 
-	cs_read_cmsg(fd, &msg, cbuf, sizeof(cbuf));
+		cs_read_cmsg(fd, &msg, cbuf, sizeof(cbuf));
+	}
 
 err_out:
 	close(fd);
diff --git a/tools/testing/selftests/net/cmsg_so_mark.sh b/tools/testing/selftests/net/cmsg_so_mark.sh
index 1650b8622f2f..772ad0cc2630 100755
--- a/tools/testing/selftests/net/cmsg_so_mark.sh
+++ b/tools/testing/selftests/net/cmsg_so_mark.sh
@@ -1,7 +1,8 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-NS=ns
+source lib.sh
+
 IP4=172.16.0.1/24
 TGT4=172.16.0.2
 IP6=2001:db8:1::1/64
@@ -10,13 +11,13 @@ MARK=1000
 
 cleanup()
 {
-    ip netns del $NS
+    cleanup_ns $NS
 }
 
 trap cleanup EXIT
 
 # Namespaces
-ip netns add $NS
+setup_ns NS
 
 ip netns exec $NS sysctl -w net.ipv4.ping_group_range='0 2147483647' > /dev/null
 
diff --git a/tools/testing/selftests/net/cmsg_time.sh b/tools/testing/selftests/net/cmsg_time.sh
index 91161e1da734..af85267ad1e3 100755
--- a/tools/testing/selftests/net/cmsg_time.sh
+++ b/tools/testing/selftests/net/cmsg_time.sh
@@ -1,7 +1,8 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-NS=ns
+source lib.sh
+
 IP4=172.16.0.1/24
 TGT4=172.16.0.2
 IP6=2001:db8:1::1/64
@@ -9,13 +10,13 @@ TGT6=2001:db8:1::2
 
 cleanup()
 {
-    ip netns del $NS
+    cleanup_ns $NS
 }
 
 trap cleanup EXIT
 
 # Namespaces
-ip netns add $NS
+setup_ns NS
 
 ip netns exec $NS sysctl -w net.ipv4.ping_group_range='0 2147483647' > /dev/null
 
diff --git a/tools/testing/selftests/net/drop_monitor_tests.sh b/tools/testing/selftests/net/drop_monitor_tests.sh
index b7650e30d18b..7c4818c971fc 100755
--- a/tools/testing/selftests/net/drop_monitor_tests.sh
+++ b/tools/testing/selftests/net/drop_monitor_tests.sh
@@ -2,10 +2,8 @@
 # SPDX-License-Identifier: GPL-2.0
 
 # This test is for checking drop monitor functionality.
-
+source lib.sh
 ret=0
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
 
 # all tests in this script. Can be overridden with -t option
 TESTS="
@@ -13,10 +11,6 @@ TESTS="
 	hw_drops
 "
 
-IP="ip -netns ns1"
-TC="tc -netns ns1"
-DEVLINK="devlink -N ns1"
-NS_EXEC="ip netns exec ns1"
 NETDEVSIM_PATH=/sys/bus/netdevsim/
 DEV_ADDR=1337
 DEV=netdevsim${DEV_ADDR}
@@ -43,7 +37,7 @@ setup()
 	modprobe netdevsim &> /dev/null
 
 	set -e
-	ip netns add ns1
+	setup_ns NS1
 	$IP link add dummy10 up type dummy
 
 	$NS_EXEC echo "$DEV_ADDR 1" > ${NETDEVSIM_PATH}/new_device
@@ -57,7 +51,7 @@ setup()
 cleanup()
 {
 	$NS_EXEC echo "$DEV_ADDR" > ${NETDEVSIM_PATH}/del_device
-	ip netns del ns1
+	cleanup_ns ${NS1}
 }
 
 sw_drops_test()
@@ -194,8 +188,15 @@ if [ $? -ne 0 ]; then
 	exit $ksft_skip
 fi
 
-# start clean
+# create netns first so we can get the namespace name
+setup_ns NS1
 cleanup &> /dev/null
+trap cleanup EXIT
+
+IP="ip -netns ${NS1}"
+TC="tc -netns ${NS1}"
+DEVLINK="devlink -N ${NS1}"
+NS_EXEC="ip netns exec ${NS1}"
 
 for t in $TESTS
 do
diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index d32a14ba069a..0d4f252427e2 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -37,9 +37,7 @@
 #
 # server / client nomenclature relative to ns-A
 
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
+source lib.sh
 VERBOSE=0
 
 NSA_DEV=eth1
@@ -82,14 +80,6 @@ MCAST=ff02::1
 NSA_LINKIP6=
 NSB_LINKIP6=
 
-NSA=ns-A
-NSB=ns-B
-NSC=ns-C
-
-NSA_CMD="ip netns exec ${NSA}"
-NSB_CMD="ip netns exec ${NSB}"
-NSC_CMD="ip netns exec ${NSC}"
-
 which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
 
 # Check if FIPS mode is enabled
@@ -406,9 +396,6 @@ create_ns()
 	local addr=$2
 	local addr6=$3
 
-	ip netns add ${ns}
-
-	ip -netns ${ns} link set lo up
 	if [ "${addr}" != "-" ]; then
 		ip -netns ${ns} addr add dev lo ${addr}
 	fi
@@ -467,13 +454,12 @@ cleanup()
 		ip -netns ${NSA} link del dev ${NSA_DEV}
 
 		ip netns pids ${NSA} | xargs kill 2>/dev/null
-		ip netns del ${NSA}
+		cleanup_ns ${NSA}
 	fi
 
 	ip netns pids ${NSB} | xargs kill 2>/dev/null
-	ip netns del ${NSB}
 	ip netns pids ${NSC} | xargs kill 2>/dev/null
-	ip netns del ${NSC} >/dev/null 2>&1
+	cleanup_ns ${NSB} ${NSC}
 }
 
 cleanup_vrf_dup()
@@ -487,6 +473,8 @@ setup_vrf_dup()
 {
 	# some VRF tests use ns-C which has the same config as
 	# ns-B but for a device NOT in the VRF
+	setup_ns NSC
+	NSC_CMD="ip netns exec ${NSC}"
 	create_ns ${NSC} "-" "-"
 	connect_ns ${NSA} ${NSA_DEV2} ${NSA_IP}/24 ${NSA_IP6}/64 \
 		   ${NSC} ${NSC_DEV} ${NSB_IP}/24 ${NSB_IP6}/64
@@ -503,6 +491,10 @@ setup()
 	log_debug "Configuring network namespaces"
 	set -e
 
+	setup_ns NSA NSB
+	NSA_CMD="ip netns exec ${NSA}"
+	NSB_CMD="ip netns exec ${NSB}"
+
 	create_ns ${NSA} ${NSA_LO_IP}/32 ${NSA_LO_IP6}/128
 	create_ns ${NSB} ${NSB_LO_IP}/32 ${NSB_LO_IP6}/128
 	connect_ns ${NSA} ${NSA_DEV} ${NSA_IP}/24 ${NSA_IP6}/64 \
@@ -545,6 +537,10 @@ setup_lla_only()
 	log_debug "Configuring network namespaces"
 	set -e
 
+	setup_ns NSA NSB NSC
+	NSA_CMD="ip netns exec ${NSA}"
+	NSB_CMD="ip netns exec ${NSB}"
+	NSC_CMD="ip netns exec ${NSC}"
 	create_ns ${NSA} "-" "-"
 	create_ns ${NSB} "-" "-"
 	create_ns ${NSC} "-" "-"
diff --git a/tools/testing/selftests/net/fdb_flush.sh b/tools/testing/selftests/net/fdb_flush.sh
index 90e7a29e0476..d5e3abb8658c 100755
--- a/tools/testing/selftests/net/fdb_flush.sh
+++ b/tools/testing/selftests/net/fdb_flush.sh
@@ -5,6 +5,8 @@
 # Check that flush works as expected with all the supported arguments and verify
 # some combinations of arguments.
 
+source lib.sh
+
 FLUSH_BY_STATE_TESTS="
 	vxlan_test_flush_by_permanent
 	vxlan_test_flush_by_nopermanent
@@ -739,10 +741,9 @@ bridge_vxlan_test_flush()
 
 setup()
 {
-	IP="ip -netns ns1"
-	BRIDGE="bridge -netns ns1"
-
-	ip netns add ns1
+	setup_ns NS
+	IP="ip -netns ${NS}"
+	BRIDGE="bridge -netns ${NS}"
 
 	$IP link add name vx10 type vxlan id 1000 dstport "$VXPORT"
 	$IP link add name vx20 type vxlan id 2000 dstport "$VXPORT"
@@ -759,7 +760,7 @@ cleanup()
 	$IP link del dev vx20
 	$IP link del dev vx10
 
-	ip netns del ns1
+	cleanup_ns ${NS}
 }
 
 ################################################################################
diff --git a/tools/testing/selftests/net/fib-onlink-tests.sh b/tools/testing/selftests/net/fib-onlink-tests.sh
index c287b90b8af8..ec2d6ceb1f08 100755
--- a/tools/testing/selftests/net/fib-onlink-tests.sh
+++ b/tools/testing/selftests/net/fib-onlink-tests.sh
@@ -3,6 +3,7 @@
 
 # IPv4 and IPv6 onlink tests
 
+source lib.sh
 PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
 VERBOSE=0
 
@@ -74,9 +75,6 @@ TEST_NET4IN6[2]=10.2.1.254
 # mcast address
 MCAST6=ff02::1
 
-
-PEER_NS=bart
-PEER_CMD="ip netns exec ${PEER_NS}"
 VRF=lisa
 VRF_TABLE=1101
 PBR_TABLE=101
@@ -176,8 +174,7 @@ setup()
 	set -e
 
 	# create namespace
-	ip netns add ${PEER_NS}
-	ip -netns ${PEER_NS} li set lo up
+	setup_ns PEER_NS
 
 	# add vrf table
 	ip li add ${VRF} type vrf table ${VRF_TABLE}
@@ -219,7 +216,7 @@ setup()
 cleanup()
 {
 	# make sure we start from a clean slate
-	ip netns del ${PEER_NS} 2>/dev/null
+	cleanup_ns ${PEER_NS} 2>/dev/null
 	for n in 1 3 5 7; do
 		ip link del ${NETIFS[p${n}]} 2>/dev/null
 	done
diff --git a/tools/testing/selftests/net/fib_nexthop_multiprefix.sh b/tools/testing/selftests/net/fib_nexthop_multiprefix.sh
index 51df5e305855..e85248609af4 100755
--- a/tools/testing/selftests/net/fib_nexthop_multiprefix.sh
+++ b/tools/testing/selftests/net/fib_nexthop_multiprefix.sh
@@ -12,6 +12,7 @@
 #
 # routing in h0 to hN is done with nexthop objects.
 
+source lib.sh
 PAUSE_ON_FAIL=no
 VERBOSE=0
 
@@ -72,12 +73,6 @@ create_ns()
 {
 	local ns=${1}
 
-	ip netns del ${ns} 2>/dev/null
-
-	ip netns add ${ns}
-	ip -netns ${ns} addr add 127.0.0.1/8 dev lo
-	ip -netns ${ns} link set lo up
-
 	ip netns exec ${ns} sysctl -q -w net.ipv6.conf.all.keep_addr_on_down=1
 	case ${ns} in
 	h*)
@@ -97,7 +92,13 @@ setup()
 
 	#set -e
 
-	for ns in h0 r1 h1 h2 h3
+	setup_ns h0 r1 h1 h2 h3
+	h[0]=$h0
+	h[1]=$h1
+	h[2]=$h2
+	h[3]=$h3
+	r[1]=$r1
+	for ns in ${h[0]} ${r[1]} ${h[1]} ${h[2]} ${h[3]}
 	do
 		create_ns ${ns}
 	done
@@ -108,35 +109,35 @@ setup()
 
 	for i in 0 1 2 3
 	do
-		ip -netns h${i} li add eth0 type veth peer name r1h${i}
-		ip -netns h${i} li set eth0 up
-		ip -netns h${i} li set r1h${i} netns r1 name eth${i} up
-
-		ip -netns h${i}    addr add dev eth0 172.16.10${i}.1/24
-		ip -netns h${i} -6 addr add dev eth0 2001:db8:10${i}::1/64
-		ip -netns r1    addr add dev eth${i} 172.16.10${i}.254/24
-		ip -netns r1 -6 addr add dev eth${i} 2001:db8:10${i}::64/64
+		ip -netns ${h[$i]} li add eth0 type veth peer name r1h${i}
+		ip -netns ${h[$i]} li set eth0 up
+		ip -netns ${h[$i]} li set r1h${i} netns ${r[1]} name eth${i} up
+
+		ip -netns ${h[$i]}    addr add dev eth0 172.16.10${i}.1/24
+		ip -netns ${h[$i]} -6 addr add dev eth0 2001:db8:10${i}::1/64
+		ip -netns ${r[1]}    addr add dev eth${i} 172.16.10${i}.254/24
+		ip -netns ${r[1]} -6 addr add dev eth${i} 2001:db8:10${i}::64/64
 	done
 
-	ip -netns h0 nexthop add id 4 via 172.16.100.254 dev eth0
-	ip -netns h0 nexthop add id 6 via 2001:db8:100::64 dev eth0
+	ip -netns ${h[0]} nexthop add id 4 via 172.16.100.254 dev eth0
+	ip -netns ${h[0]} nexthop add id 6 via 2001:db8:100::64 dev eth0
 
-	# routing from h0 to h1-h3 and back
+	# routing from ${h[0]} to h1-h3 and back
 	for i in 1 2 3
 	do
-		ip -netns h0    ro add 172.16.10${i}.0/24 nhid 4
-		ip -netns h${i} ro add 172.16.100.0/24 via 172.16.10${i}.254
+		ip -netns ${h[0]}    ro add 172.16.10${i}.0/24 nhid 4
+		ip -netns ${h[$i]} ro add 172.16.100.0/24 via 172.16.10${i}.254
 
-		ip -netns h0    -6 ro add 2001:db8:10${i}::/64 nhid 6
-		ip -netns h${i} -6 ro add 2001:db8:100::/64 via 2001:db8:10${i}::64
+		ip -netns ${h[0]}    -6 ro add 2001:db8:10${i}::/64 nhid 6
+		ip -netns ${h[$i]} -6 ro add 2001:db8:100::/64 via 2001:db8:10${i}::64
 	done
 
 	if [ "$VERBOSE" = "1" ]; then
 		echo
 		echo "host 1 config"
-		ip -netns h0 li sh
-		ip -netns h0 ro sh
-		ip -netns h0 -6 ro sh
+		ip -netns ${h[0]} li sh
+		ip -netns ${h[0]} ro sh
+		ip -netns ${h[0]} -6 ro sh
 	fi
 
 	#set +e
@@ -144,10 +145,7 @@ setup()
 
 cleanup()
 {
-	for n in h0 r1 h1 h2 h3
-	do
-		ip netns del ${n} 2>/dev/null
-	done
+	cleanup_all_ns
 }
 
 change_mtu()
@@ -156,7 +154,7 @@ change_mtu()
 	local mtu=$2
 
 	run_cmd ip -netns h${hostid} li set eth0 mtu ${mtu}
-	run_cmd ip -netns r1 li set eth${hostid} mtu ${mtu}
+	run_cmd ip -netns ${r1} li set eth${hostid} mtu ${mtu}
 }
 
 ################################################################################
@@ -168,23 +166,23 @@ validate_v4_exception()
 	local mtu=$2
 	local ping_sz=$3
 	local dst="172.16.10${i}.1"
-	local h0=172.16.100.1
-	local r1=172.16.100.254
+	local h0_ip=172.16.100.1
+	local r1_ip=172.16.100.254
 	local rc
 
 	if [ ${ping_sz} != "0" ]; then
-		run_cmd ip netns exec h0 ping -s ${ping_sz} -c5 -w5 ${dst}
+		run_cmd ip netns exec ${h0} ping -s ${ping_sz} -c5 -w5 ${dst}
 	fi
 
 	if [ "$VERBOSE" = "1" ]; then
 		echo "Route get"
-		ip -netns h0 ro get ${dst}
+		ip -netns ${h0} ro get ${dst}
 		echo "Searching for:"
 		echo "    cache .* mtu ${mtu}"
 		echo
 	fi
 
-	ip -netns h0 ro get ${dst} | \
+	ip -netns ${h0} ro get ${dst} | \
 	grep -q "cache .* mtu ${mtu}"
 	rc=$?
 
@@ -197,24 +195,24 @@ validate_v6_exception()
 	local mtu=$2
 	local ping_sz=$3
 	local dst="2001:db8:10${i}::1"
-	local h0=2001:db8:100::1
-	local r1=2001:db8:100::64
+	local h0_ip=2001:db8:100::1
+	local r1_ip=2001:db8:100::64
 	local rc
 
 	if [ ${ping_sz} != "0" ]; then
-		run_cmd ip netns exec h0 ${ping6} -s ${ping_sz} -c5 -w5 ${dst}
+		run_cmd ip netns exec ${h0} ${ping6} -s ${ping_sz} -c5 -w5 ${dst}
 	fi
 
 	if [ "$VERBOSE" = "1" ]; then
 		echo "Route get"
-		ip -netns h0 -6 ro get ${dst}
+		ip -netns ${h0} -6 ro get ${dst}
 		echo "Searching for:"
-		echo "    ${dst} from :: via ${r1} dev eth0 src ${h0} .* mtu ${mtu}"
+		echo "    ${dst}.* via ${r1_ip} dev eth0 src ${h0_ip} .* mtu ${mtu}"
 		echo
 	fi
 
-	ip -netns h0 -6 ro get ${dst} | \
-	grep -q "${dst} from :: via ${r1} dev eth0 src ${h0} .* mtu ${mtu}"
+	ip -netns ${h0} -6 ro get ${dst} | \
+	grep -q "${dst}.* via ${r1_ip} dev eth0 src ${h0_ip} .* mtu ${mtu}"
 	rc=$?
 
 	log_test $rc 0 "IPv6: host 0 to host ${i}, mtu ${mtu}"
@@ -242,11 +240,11 @@ for i in 1 2 3
 do
 	# generate a cached route per-cpu
 	for c in ${cpus}; do
-		run_cmd taskset -c ${c} ip netns exec h0 ping -c1 -w1 172.16.10${i}.1
-		[ $? -ne 0 ] && printf "\nERROR: ping to h${i} failed\n" && ret=1
+		run_cmd taskset -c ${c} ip netns exec ${h0} ping -c1 -w1 172.16.10${i}.1
+		[ $? -ne 0 ] && printf "\nERROR: ping to ${h[$i]} failed\n" && ret=1
 
-		run_cmd taskset -c ${c} ip netns exec h0 ${ping6} -c1 -w1 2001:db8:10${i}::1
-		[ $? -ne 0 ] && printf "\nERROR: ping6 to h${i} failed\n" && ret=1
+		run_cmd taskset -c ${c} ip netns exec ${h0} ${ping6} -c1 -w1 2001:db8:10${i}::1
+		[ $? -ne 0 ] && printf "\nERROR: ping6 to ${h[$i]} failed\n" && ret=1
 
 		[ $ret -ne 0 ] && break
 	done
@@ -282,11 +280,11 @@ if [ $ret -eq 0 ]; then
 	validate_v6_exception 3 1400 0
 
 	# targeted deletes to trigger cleanup paths in kernel
-	ip -netns h0 ro del 172.16.102.0/24 nhid 4
-	ip -netns h0 -6 ro del 2001:db8:102::/64 nhid 6
+	ip -netns ${h0} ro del 172.16.102.0/24 nhid 4
+	ip -netns ${h0} -6 ro del 2001:db8:102::/64 nhid 6
 
-	ip -netns h0 nexthop del id 4
-	ip -netns h0 nexthop del id 6
+	ip -netns ${h0} nexthop del id 4
+	ip -netns ${h0} nexthop del id 6
 fi
 
 cleanup
diff --git a/tools/testing/selftests/net/fib_nexthop_nongw.sh b/tools/testing/selftests/net/fib_nexthop_nongw.sh
index b7b928b38ce4..1ccf56f10171 100755
--- a/tools/testing/selftests/net/fib_nexthop_nongw.sh
+++ b/tools/testing/selftests/net/fib_nexthop_nongw.sh
@@ -8,6 +8,7 @@
 #            veth0 <---|---> veth1
 # Validate source address selection for route without gateway
 
+source lib.sh
 PAUSE_ON_FAIL=no
 VERBOSE=0
 ret=0
@@ -64,35 +65,31 @@ run_cmd()
 # config
 setup()
 {
-	ip netns add h1
-	ip -n h1 link set lo up
-	ip netns add h2
-	ip -n h2 link set lo up
+	setup_ns h1 h2
 
 	# Add a fake eth0 to support an ip address
-	ip -n h1 link add name eth0 type dummy
-	ip -n h1 link set eth0 up
-	ip -n h1 address add 192.168.0.1/24 dev eth0
+	ip -n $h1 link add name eth0 type dummy
+	ip -n $h1 link set eth0 up
+	ip -n $h1 address add 192.168.0.1/24 dev eth0
 
 	# Configure veths (same @mac, arp off)
-	ip -n h1 link add name veth0 type veth peer name veth1 netns h2
-	ip -n h1 link set veth0 up
+	ip -n $h1 link add name veth0 type veth peer name veth1 netns $h2
+	ip -n $h1 link set veth0 up
 
-	ip -n h2 link set veth1 up
+	ip -n $h2 link set veth1 up
 
 	# Configure @IP in the peer netns
-	ip -n h2 address add 192.168.1.1/32 dev veth1
-	ip -n h2 route add default dev veth1
+	ip -n $h2 address add 192.168.1.1/32 dev veth1
+	ip -n $h2 route add default dev veth1
 
 	# Add a nexthop without @gw and use it in a route
-	ip -n h1 nexthop add id 1 dev veth0
-	ip -n h1 route add 192.168.1.1 nhid 1
+	ip -n $h1 nexthop add id 1 dev veth0
+	ip -n $h1 route add 192.168.1.1 nhid 1
 }
 
 cleanup()
 {
-	ip netns del h1 2>/dev/null
-	ip netns del h2 2>/dev/null
+	cleanup_ns $h1 $h2
 }
 
 trap cleanup EXIT
@@ -108,12 +105,11 @@ do
 	esac
 done
 
-cleanup
 setup
 
-run_cmd ip -netns h1 route get 192.168.1.1
+run_cmd ip -netns $h1 route get 192.168.1.1
 log_test $? 0 "nexthop: get route with nexthop without gw"
-run_cmd ip netns exec h1 ping -c1 192.168.1.1
+run_cmd ip netns exec $h1 ping -c1 192.168.1.1
 log_test $? 0 "nexthop: ping through nexthop without gw"
 
 exit $ret
diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index a6f2c0b9555d..d5a281aadbac 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -14,6 +14,7 @@
 # objects. Device reference counts and network namespace cleanup tested
 # by use of network namespace for peer.
 
+source lib.sh
 ret=0
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
@@ -148,13 +149,7 @@ create_ns()
 {
 	local n=${1}
 
-	ip netns del ${n} 2>/dev/null
-
 	set -e
-	ip netns add ${n}
-	ip netns set ${n} $((nsid++))
-	ip -netns ${n} addr add 127.0.0.1/8 dev lo
-	ip -netns ${n} link set lo up
 
 	ip netns exec ${n} sysctl -qw net.ipv4.ip_forward=1
 	ip netns exec ${n} sysctl -qw net.ipv4.fib_multipath_use_neigh=1
@@ -173,12 +168,13 @@ setup()
 {
 	cleanup
 
-	create_ns me
-	create_ns peer
-	create_ns remote
+	setup_ns me peer remote
+	create_ns $me
+	create_ns $peer
+	create_ns $remote
 
-	IP="ip -netns me"
-	BRIDGE="bridge -netns me"
+	IP="ip -netns $me"
+	BRIDGE="bridge -netns $me"
 	set -e
 	$IP li add veth1 type veth peer name veth2
 	$IP li set veth1 up
@@ -190,24 +186,24 @@ setup()
 	$IP addr add 172.16.2.1/24 dev veth3
 	$IP -6 addr add 2001:db8:92::1/64 dev veth3 nodad
 
-	$IP li set veth2 netns peer up
-	ip -netns peer addr add 172.16.1.2/24 dev veth2
-	ip -netns peer -6 addr add 2001:db8:91::2/64 dev veth2 nodad
+	$IP li set veth2 netns $peer up
+	ip -netns $peer addr add 172.16.1.2/24 dev veth2
+	ip -netns $peer -6 addr add 2001:db8:91::2/64 dev veth2 nodad
 
-	$IP li set veth4 netns peer up
-	ip -netns peer addr add 172.16.2.2/24 dev veth4
-	ip -netns peer -6 addr add 2001:db8:92::2/64 dev veth4 nodad
+	$IP li set veth4 netns $peer up
+	ip -netns $peer addr add 172.16.2.2/24 dev veth4
+	ip -netns $peer -6 addr add 2001:db8:92::2/64 dev veth4 nodad
 
-	ip -netns remote li add veth5 type veth peer name veth6
-	ip -netns remote li set veth5 up
-	ip -netns remote addr add dev veth5 172.16.101.1/24
-	ip -netns remote -6 addr add dev veth5 2001:db8:101::1/64 nodad
-	ip -netns remote ro add 172.16.0.0/22 via 172.16.101.2
-	ip -netns remote -6 ro add 2001:db8:90::/40 via 2001:db8:101::2
+	ip -netns $remote li add veth5 type veth peer name veth6
+	ip -netns $remote li set veth5 up
+	ip -netns $remote addr add dev veth5 172.16.101.1/24
+	ip -netns $remote -6 addr add dev veth5 2001:db8:101::1/64 nodad
+	ip -netns $remote ro add 172.16.0.0/22 via 172.16.101.2
+	ip -netns $remote -6 ro add 2001:db8:90::/40 via 2001:db8:101::2
 
-	ip -netns remote li set veth6 netns peer up
-	ip -netns peer addr add dev veth6 172.16.101.2/24
-	ip -netns peer -6 addr add dev veth6 2001:db8:101::2/64 nodad
+	ip -netns $remote li set veth6 netns $peer up
+	ip -netns $peer addr add dev veth6 172.16.101.2/24
+	ip -netns $peer -6 addr add dev veth6 2001:db8:101::2/64 nodad
 	set +e
 }
 
@@ -215,7 +211,7 @@ cleanup()
 {
 	local ns
 
-	for ns in me peer remote; do
+	for ns in $me $peer $remote; do
 		ip netns del ${ns} 2>/dev/null
 	done
 }
@@ -779,7 +775,7 @@ ipv6_grp_refs()
 	run_cmd "$IP route add 2001:db8:101::1/128 nhid 102"
 
 	# create per-cpu dsts through nh 100
-	run_cmd "ip netns exec me mausezahn -6 veth1.10 -B 2001:db8:101::1 -A 2001:db8:91::1 -c 5 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1"
+	run_cmd "ip netns exec $me mausezahn -6 veth1.10 -B 2001:db8:101::1 -A 2001:db8:91::1 -c 5 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1"
 
 	# remove nh 100 from the group to delete the route potentially leaving
 	# a stale per-cpu dst which holds a reference to the nexthop's net
@@ -805,7 +801,7 @@ ipv6_grp_refs()
 
 	# if a reference was lost this command will hang because the net device
 	# cannot be removed
-	timeout -s KILL 5 ip netns exec me ip link del veth1.10 >/dev/null 2>&1
+	timeout -s KILL 5 ip netns exec $me ip link del veth1.10 >/dev/null 2>&1
 
 	# we can't cleanup if the command is hung trying to delete the netdev
 	if [ $? -eq 137 ]; then
@@ -1012,13 +1008,13 @@ ipv6_fcnal_runtime()
 	log_test $? 0 "Route delete"
 
 	run_cmd "$IP ro add 2001:db8:101::1/128 nhid 81"
-	run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 2001:db8:101::1"
+	run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 2001:db8:101::1"
 	log_test $? 0 "Ping with nexthop"
 
 	run_cmd "$IP nexthop add id 82 via 2001:db8:92::2 dev veth3"
 	run_cmd "$IP nexthop add id 122 group 81/82"
 	run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 122"
-	run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 2001:db8:101::1"
+	run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 2001:db8:101::1"
 	log_test $? 0 "Ping - multipath"
 
 	#
@@ -1026,26 +1022,26 @@ ipv6_fcnal_runtime()
 	#
 	run_cmd "$IP -6 nexthop add id 83 blackhole"
 	run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 83"
-	run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 2001:db8:101::1"
+	run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 2001:db8:101::1"
 	log_test $? 2 "Ping - blackhole"
 
 	run_cmd "$IP nexthop replace id 83 via 2001:db8:91::2 dev veth1"
-	run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 2001:db8:101::1"
+	run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 2001:db8:101::1"
 	log_test $? 0 "Ping - blackhole replaced with gateway"
 
 	run_cmd "$IP -6 nexthop replace id 83 blackhole"
-	run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 2001:db8:101::1"
+	run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 2001:db8:101::1"
 	log_test $? 2 "Ping - gateway replaced by blackhole"
 
 	run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 122"
-	run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 2001:db8:101::1"
+	run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 2001:db8:101::1"
 	if [ $? -eq 0 ]; then
 		run_cmd "$IP nexthop replace id 122 group 83"
-		run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 2001:db8:101::1"
+		run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 2001:db8:101::1"
 		log_test $? 2 "Ping - group with blackhole"
 
 		run_cmd "$IP nexthop replace id 122 group 81/82"
-		run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 2001:db8:101::1"
+		run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 2001:db8:101::1"
 		log_test $? 0 "Ping - group blackhole replaced with gateways"
 	else
 		log_test 2 0 "Ping - multipath failed"
@@ -1128,15 +1124,15 @@ ipv6_fcnal_runtime()
 
 	# rpfilter and default route
 	$IP nexthop flush >/dev/null 2>&1
-	run_cmd "ip netns exec me ip6tables -t mangle -I PREROUTING 1 -m rpfilter --invert -j DROP"
+	run_cmd "ip netns exec $me ip6tables -t mangle -I PREROUTING 1 -m rpfilter --invert -j DROP"
 	run_cmd "$IP nexthop add id 91 via 2001:db8:91::2 dev veth1"
 	run_cmd "$IP nexthop add id 92 via 2001:db8:92::2 dev veth3"
 	run_cmd "$IP nexthop add id 93 group 91/92"
 	run_cmd "$IP -6 ro add default nhid 91"
-	run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 2001:db8:101::1"
+	run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 2001:db8:101::1"
 	log_test $? 0 "Nexthop with default route and rpfilter"
 	run_cmd "$IP -6 ro replace default nhid 93"
-	run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 2001:db8:101::1"
+	run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 2001:db8:101::1"
 	log_test $? 0 "Nexthop with multipath default route and rpfilter"
 
 	# TO-DO:
@@ -1216,11 +1212,11 @@ ipv6_torture()
 	pid1=$!
 	ipv6_grp_replace_loop &
 	pid2=$!
-	ip netns exec me ping -f 2001:db8:101::1 >/dev/null 2>&1 &
+	ip netns exec $me ping -f 2001:db8:101::1 >/dev/null 2>&1 &
 	pid3=$!
-	ip netns exec me ping -f 2001:db8:101::2 >/dev/null 2>&1 &
+	ip netns exec $me ping -f 2001:db8:101::2 >/dev/null 2>&1 &
 	pid4=$!
-	ip netns exec me mausezahn -6 veth1 -B 2001:db8:101::2 -A 2001:db8:91::1 -c 0 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1 &
+	ip netns exec $me mausezahn -6 veth1 -B 2001:db8:101::2 -A 2001:db8:91::1 -c 0 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1 &
 	pid5=$!
 
 	sleep 300
@@ -1270,11 +1266,11 @@ ipv6_res_torture()
 	pid1=$!
 	ipv6_res_grp_replace_loop &
 	pid2=$!
-	ip netns exec me ping -f 2001:db8:101::1 >/dev/null 2>&1 &
+	ip netns exec $me ping -f 2001:db8:101::1 >/dev/null 2>&1 &
 	pid3=$!
-	ip netns exec me ping -f 2001:db8:101::2 >/dev/null 2>&1 &
+	ip netns exec $me ping -f 2001:db8:101::2 >/dev/null 2>&1 &
 	pid4=$!
-	ip netns exec me mausezahn -6 veth1 \
+	ip netns exec $me mausezahn -6 veth1 \
 			    -B 2001:db8:101::2 -A 2001:db8:91::1 -c 0 \
 			    -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1 &
 	pid5=$!
@@ -1544,7 +1540,7 @@ ipv4_withv6_fcnal()
 	local lladdr
 
 	set -e
-	lladdr=$(get_linklocal veth2 peer)
+	lladdr=$(get_linklocal veth2 $peer)
 	run_cmd "$IP nexthop add id 11 via ${lladdr} dev veth1"
 	set +e
 	run_cmd "$IP ro add 172.16.101.1/32 nhid 11"
@@ -1606,13 +1602,13 @@ ipv4_fcnal_runtime()
 	#
 	run_cmd "$IP nexthop replace id 21 via 172.16.1.2 dev veth1"
 	run_cmd "$IP ro replace 172.16.101.1/32 nhid 21"
-	run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
+	run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
 	log_test $? 0 "Basic ping"
 
 	run_cmd "$IP nexthop replace id 22 via 172.16.2.2 dev veth3"
 	run_cmd "$IP nexthop add id 122 group 21/22"
 	run_cmd "$IP ro replace 172.16.101.1/32 nhid 122"
-	run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
+	run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
 	log_test $? 0 "Ping - multipath"
 
 	run_cmd "$IP ro delete 172.16.101.1/32 nhid 122"
@@ -1623,7 +1619,7 @@ ipv4_fcnal_runtime()
 	run_cmd "$IP nexthop add id 501 via 172.16.1.2 dev veth1"
 	run_cmd "$IP ro add default nhid 501"
 	run_cmd "$IP ro add default via 172.16.1.3 dev veth1 metric 20"
-	run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
+	run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
 	log_test $? 0 "Ping - multiple default routes, nh first"
 
 	# flip the order
@@ -1632,7 +1628,7 @@ ipv4_fcnal_runtime()
 	run_cmd "$IP ro add default via 172.16.1.2 dev veth1 metric 20"
 	run_cmd "$IP nexthop replace id 501 via 172.16.1.3 dev veth1"
 	run_cmd "$IP ro add default nhid 501 metric 20"
-	run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
+	run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
 	log_test $? 0 "Ping - multiple default routes, nh second"
 
 	run_cmd "$IP nexthop delete nhid 501"
@@ -1643,26 +1639,26 @@ ipv4_fcnal_runtime()
 	#
 	run_cmd "$IP nexthop add id 23 blackhole"
 	run_cmd "$IP ro replace 172.16.101.1/32 nhid 23"
-	run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
+	run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
 	log_test $? 2 "Ping - blackhole"
 
 	run_cmd "$IP nexthop replace id 23 via 172.16.1.2 dev veth1"
-	run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
+	run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
 	log_test $? 0 "Ping - blackhole replaced with gateway"
 
 	run_cmd "$IP nexthop replace id 23 blackhole"
-	run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
+	run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
 	log_test $? 2 "Ping - gateway replaced by blackhole"
 
 	run_cmd "$IP ro replace 172.16.101.1/32 nhid 122"
-	run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
+	run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
 	if [ $? -eq 0 ]; then
 		run_cmd "$IP nexthop replace id 122 group 23"
-		run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
+		run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
 		log_test $? 2 "Ping - group with blackhole"
 
 		run_cmd "$IP nexthop replace id 122 group 21/22"
-		run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
+		run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
 		log_test $? 0 "Ping - group blackhole replaced with gateways"
 	else
 		log_test 2 0 "Ping - multipath failed"
@@ -1685,11 +1681,11 @@ ipv4_fcnal_runtime()
 	# IPv4 with IPv6
 	#
 	set -e
-	lladdr=$(get_linklocal veth2 peer)
+	lladdr=$(get_linklocal veth2 $peer)
 	run_cmd "$IP nexthop add id 24 via ${lladdr} dev veth1"
 	set +e
 	run_cmd "$IP ro replace 172.16.101.1/32 nhid 24"
-	run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
+	run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
 	log_test $? 0 "IPv6 nexthop with IPv4 route"
 
 	$IP neigh sh | grep -q "${lladdr} dev veth1"
@@ -1713,11 +1709,11 @@ ipv4_fcnal_runtime()
 
 	check_route "172.16.101.1" "172.16.101.1 nhid 101 nexthop via inet6 ${lladdr} dev veth1 weight 1 nexthop via 172.16.1.2 dev veth1 weight 1"
 
-	run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
+	run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
 	log_test $? 0 "IPv6 nexthop with IPv4 route"
 
 	run_cmd "$IP ro replace 172.16.101.1/32 via inet6 ${lladdr} dev veth1"
-	run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
+	run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
 	log_test $? 0 "IPv4 route with IPv6 gateway"
 
 	$IP neigh sh | grep -q "${lladdr} dev veth1"
@@ -1734,7 +1730,7 @@ ipv4_fcnal_runtime()
 
 	run_cmd "$IP ro del 172.16.101.1/32 via inet6 ${lladdr} dev veth1"
 	run_cmd "$IP -4 ro add default via inet6 ${lladdr} dev veth1"
-	run_cmd "ip netns exec me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
+	run_cmd "ip netns exec $me ping -c1 -w$PING_TIMEOUT 172.16.101.1"
 	log_test $? 0 "IPv4 default route with IPv6 gateway"
 
 	#
@@ -1785,7 +1781,7 @@ sysctl_nexthop_compat_mode_check()
 	local sysctlname="net.ipv4.nexthop_compat_mode"
 	local lprefix=$1
 
-	IPE="ip netns exec me"
+	IPE="ip netns exec $me"
 
 	$IPE sysctl -q $sysctlname 2>&1 >/dev/null
 	if [ $? -ne 0 ]; then
@@ -1804,7 +1800,7 @@ sysctl_nexthop_compat_mode_set()
 	local mode=$1
 	local lprefix=$2
 
-	IPE="ip netns exec me"
+	IPE="ip netns exec $me"
 
 	out=$($IPE sysctl -w $sysctlname=$mode)
 	log_test $? 0 "$lprefix set compat mode - $mode"
@@ -1988,11 +1984,11 @@ ipv4_torture()
 	pid1=$!
 	ipv4_grp_replace_loop &
 	pid2=$!
-	ip netns exec me ping -f 172.16.101.1 >/dev/null 2>&1 &
+	ip netns exec $me ping -f 172.16.101.1 >/dev/null 2>&1 &
 	pid3=$!
-	ip netns exec me ping -f 172.16.101.2 >/dev/null 2>&1 &
+	ip netns exec $me ping -f 172.16.101.2 >/dev/null 2>&1 &
 	pid4=$!
-	ip netns exec me mausezahn veth1 -B 172.16.101.2 -A 172.16.1.1 -c 0 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1 &
+	ip netns exec $me mausezahn veth1 -B 172.16.101.2 -A 172.16.1.1 -c 0 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1 &
 	pid5=$!
 
 	sleep 300
@@ -2042,11 +2038,11 @@ ipv4_res_torture()
 	pid1=$!
 	ipv4_res_grp_replace_loop &
 	pid2=$!
-	ip netns exec me ping -f 172.16.101.1 >/dev/null 2>&1 &
+	ip netns exec $me ping -f 172.16.101.1 >/dev/null 2>&1 &
 	pid3=$!
-	ip netns exec me ping -f 172.16.101.2 >/dev/null 2>&1 &
+	ip netns exec $me ping -f 172.16.101.2 >/dev/null 2>&1 &
 	pid4=$!
-	ip netns exec me mausezahn veth1 \
+	ip netns exec $me mausezahn veth1 \
 				-B 172.16.101.2 -A 172.16.1.1 -c 0 \
 				-t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1 &
 	pid5=$!
@@ -2081,10 +2077,10 @@ basic()
 
 	# create nh with linkdown device - fails
 	$IP li set veth1 up
-	ip -netns peer li set veth2 down
+	ip -netns $peer li set veth2 down
 	run_cmd "$IP nexthop add id 1 dev veth1"
 	log_test $? 2 "Nexthop with device that is linkdown"
-	ip -netns peer li set veth2 up
+	ip -netns $peer li set veth2 up
 
 	# device only
 	run_cmd "$IP nexthop add id 1 dev veth1"
@@ -2465,7 +2461,7 @@ fi
 for t in $TESTS
 do
 	case $t in
-	none) IP="ip -netns peer"; setup; exit 0;;
+	none) IP="ip -netns $peer"; setup; exit 0;;
 	*) setup; $t; cleanup;;
 	esac
 done
diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index 63c3eaec8d30..51157a5559b7 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -3,14 +3,9 @@
 
 # This test is for checking IPv4 and IPv6 FIB rules API
 
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
+source lib.sh
 ret=0
-
 PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
-IP="ip -netns testns"
-IP_PEER="ip -netns peerns"
 
 RTABLE=100
 RTABLE_PEER=101
@@ -84,8 +79,8 @@ check_nettest()
 setup()
 {
 	set -e
-	ip netns add testns
-	$IP link set dev lo up
+	setup_ns testns
+	IP="ip -netns $testns"
 
 	$IP link add dummy0 type dummy
 	$IP link set dev dummy0 up
@@ -98,18 +93,19 @@ setup()
 cleanup()
 {
 	$IP link del dev dummy0 &> /dev/null
-	ip netns del testns
+	cleanup_ns $testns
 }
 
 setup_peer()
 {
 	set -e
 
-	ip netns add peerns
+	setup_ns peerns
+	IP_PEER="ip -netns $peerns"
 	$IP_PEER link set dev lo up
 
-	ip link add name veth0 netns testns type veth \
-		peer name veth1 netns peerns
+	ip link add name veth0 netns $testns type veth \
+		peer name veth1 netns $peerns
 	$IP link set dev veth0 up
 	$IP_PEER link set dev veth1 up
 
@@ -131,7 +127,7 @@ setup_peer()
 cleanup_peer()
 {
 	$IP link del dev veth0
-	ip netns del peerns
+	ip netns del $peerns
 }
 
 fib_check_iproute_support()
@@ -270,11 +266,11 @@ fib_rule6_connect_test()
 	# (Not-ECT: 0, ECT(1): 1, ECT(0): 2, CE: 3).
 	# The ECN bits shouldn't influence the result of the test.
 	for dsfield in 0x04 0x05 0x06 0x07; do
-		nettest -q -6 -B -t 5 -N testns -O peerns -U -D \
+		nettest -q -6 -B -t 5 -N $testns -O $peerns -U -D \
 			-Q "${dsfield}" -l 2001:db8::1:11 -r 2001:db8::1:11
 		log_test $? 0 "rule6 dsfield udp connect (dsfield ${dsfield})"
 
-		nettest -q -6 -B -t 5 -N testns -O peerns -Q "${dsfield}" \
+		nettest -q -6 -B -t 5 -N $testns -O $peerns -Q "${dsfield}" \
 			-l 2001:db8::1:11 -r 2001:db8::1:11
 		log_test $? 0 "rule6 dsfield tcp connect (dsfield ${dsfield})"
 	done
@@ -337,11 +333,11 @@ fib_rule4_test()
 
 	# need enable forwarding and disable rp_filter temporarily as all the
 	# addresses are in the same subnet and egress device == ingress device.
-	ip netns exec testns sysctl -qw net.ipv4.ip_forward=1
-	ip netns exec testns sysctl -qw net.ipv4.conf.$DEV.rp_filter=0
+	ip netns exec $testns sysctl -qw net.ipv4.ip_forward=1
+	ip netns exec $testns sysctl -qw net.ipv4.conf.$DEV.rp_filter=0
 	match="from $SRC_IP iif $DEV"
 	fib_rule4_test_match_n_redirect "$match" "$match" "iif redirect to table"
-	ip netns exec testns sysctl -qw net.ipv4.ip_forward=0
+	ip netns exec $testns sysctl -qw net.ipv4.ip_forward=0
 
 	# Reject dsfield (tos) options which have ECN bits set
 	for cnt in $(seq 1 3); do
@@ -407,11 +403,11 @@ fib_rule4_connect_test()
 	# (Not-ECT: 0, ECT(1): 1, ECT(0): 2, CE: 3).
 	# The ECN bits shouldn't influence the result of the test.
 	for dsfield in 0x04 0x05 0x06 0x07; do
-		nettest -q -B -t 5 -N testns -O peerns -D -U -Q "${dsfield}" \
+		nettest -q -B -t 5 -N $testns -O $peerns -D -U -Q "${dsfield}" \
 			-l 198.51.100.11 -r 198.51.100.11
 		log_test $? 0 "rule4 dsfield udp connect (dsfield ${dsfield})"
 
-		nettest -q -B -t 5 -N testns -O peerns -Q "${dsfield}" \
+		nettest -q -B -t 5 -N $testns -O $peerns -Q "${dsfield}" \
 			-l 198.51.100.11 -r 198.51.100.11
 		log_test $? 0 "rule4 dsfield tcp connect (dsfield ${dsfield})"
 	done
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 66d0db7a2614..b3ecccbbfcd2 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -3,10 +3,8 @@
 
 # This test is for checking IPv4 and IPv6 FIB behavior in response to
 # different events.
-
+source lib.sh
 ret=0
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
 
 # all tests in this script. Can be overridden with -t option
 TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify \
@@ -18,8 +16,6 @@ TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify \
 VERBOSE=0
 PAUSE_ON_FAIL=no
 PAUSE=no
-IP="$(which ip) -netns ns1"
-NS_EXEC="$(which ip) netns exec ns1"
 
 which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
 
@@ -55,11 +51,11 @@ log_test()
 setup()
 {
 	set -e
-	ip netns add ns1
-	ip netns set ns1 auto
-	$IP link set dev lo up
-	ip netns exec ns1 sysctl -qw net.ipv4.ip_forward=1
-	ip netns exec ns1 sysctl -qw net.ipv6.conf.all.forwarding=1
+	setup_ns ns1
+	IP="$(which ip) -netns $ns1"
+	NS_EXEC="$(which ip) netns exec $ns1"
+	ip netns exec $ns1 sysctl -qw net.ipv4.ip_forward=1
+	ip netns exec $ns1 sysctl -qw net.ipv6.conf.all.forwarding=1
 
 	$IP link add dummy0 type dummy
 	$IP link set dev dummy0 up
@@ -72,8 +68,7 @@ setup()
 cleanup()
 {
 	$IP link del dev dummy0 &> /dev/null
-	ip netns del ns1 &> /dev/null
-	ip netns del ns2 &> /dev/null
+	cleanup_ns $ns1 $ns2
 }
 
 get_linklocal()
@@ -448,28 +443,25 @@ fib_rp_filter_test()
 	setup
 
 	set -e
-	ip netns add ns2
-	ip netns set ns2 auto
-
-	ip -netns ns2 link set dev lo up
+	setup_ns ns2
 
 	$IP link add name veth1 type veth peer name veth2
-	$IP link set dev veth2 netns ns2
+	$IP link set dev veth2 netns $ns2
 	$IP address add 192.0.2.1/24 dev veth1
-	ip -netns ns2 address add 192.0.2.1/24 dev veth2
+	ip -netns $ns2 address add 192.0.2.1/24 dev veth2
 	$IP link set dev veth1 up
-	ip -netns ns2 link set dev veth2 up
+	ip -netns $ns2 link set dev veth2 up
 
 	$IP link set dev lo address 52:54:00:6a:c7:5e
 	$IP link set dev veth1 address 52:54:00:6a:c7:5e
-	ip -netns ns2 link set dev lo address 52:54:00:6a:c7:5e
-	ip -netns ns2 link set dev veth2 address 52:54:00:6a:c7:5e
+	ip -netns $ns2 link set dev lo address 52:54:00:6a:c7:5e
+	ip -netns $ns2 link set dev veth2 address 52:54:00:6a:c7:5e
 
 	# 1. (ns2) redirect lo's egress to veth2's egress
-	ip netns exec ns2 tc qdisc add dev lo parent root handle 1: fq_codel
-	ip netns exec ns2 tc filter add dev lo parent 1: protocol arp basic \
+	ip netns exec $ns2 tc qdisc add dev lo parent root handle 1: fq_codel
+	ip netns exec $ns2 tc filter add dev lo parent 1: protocol arp basic \
 		action mirred egress redirect dev veth2
-	ip netns exec ns2 tc filter add dev lo parent 1: protocol ip basic \
+	ip netns exec $ns2 tc filter add dev lo parent 1: protocol ip basic \
 		action mirred egress redirect dev veth2
 
 	# 2. (ns1) redirect veth1's ingress to lo's ingress
@@ -487,24 +479,24 @@ fib_rp_filter_test()
 		action mirred egress redirect dev veth1
 
 	# 4. (ns2) redirect veth2's ingress to lo's ingress
-	ip netns exec ns2 tc qdisc add dev veth2 ingress
-	ip netns exec ns2 tc filter add dev veth2 ingress protocol arp basic \
+	ip netns exec $ns2 tc qdisc add dev veth2 ingress
+	ip netns exec $ns2 tc filter add dev veth2 ingress protocol arp basic \
 		action mirred ingress redirect dev lo
-	ip netns exec ns2 tc filter add dev veth2 ingress protocol ip basic \
+	ip netns exec $ns2 tc filter add dev veth2 ingress protocol ip basic \
 		action mirred ingress redirect dev lo
 
 	$NS_EXEC sysctl -qw net.ipv4.conf.all.rp_filter=1
 	$NS_EXEC sysctl -qw net.ipv4.conf.all.accept_local=1
 	$NS_EXEC sysctl -qw net.ipv4.conf.all.route_localnet=1
-	ip netns exec ns2 sysctl -qw net.ipv4.conf.all.rp_filter=1
-	ip netns exec ns2 sysctl -qw net.ipv4.conf.all.accept_local=1
-	ip netns exec ns2 sysctl -qw net.ipv4.conf.all.route_localnet=1
+	ip netns exec $ns2 sysctl -qw net.ipv4.conf.all.rp_filter=1
+	ip netns exec $ns2 sysctl -qw net.ipv4.conf.all.accept_local=1
+	ip netns exec $ns2 sysctl -qw net.ipv4.conf.all.route_localnet=1
 	set +e
 
-	run_cmd "ip netns exec ns2 ping -w1 -c1 192.0.2.1"
+	run_cmd "ip netns exec $ns2 ping -w1 -c1 192.0.2.1"
 	log_test $? 0 "rp_filter passes local packets"
 
-	run_cmd "ip netns exec ns2 ping -w1 -c1 127.0.0.1"
+	run_cmd "ip netns exec $ns2 ping -w1 -c1 127.0.0.1"
 	log_test $? 0 "rp_filter passes loopback packets"
 
 	cleanup
@@ -959,34 +951,32 @@ route_setup()
 	[ "${VERBOSE}" = "1" ] && set -x
 	set -e
 
-	ip netns add ns2
-	ip netns set ns2 auto
-	ip -netns ns2 link set dev lo up
-	ip netns exec ns2 sysctl -qw net.ipv4.ip_forward=1
-	ip netns exec ns2 sysctl -qw net.ipv6.conf.all.forwarding=1
+	setup_ns ns2
+	ip netns exec $ns2 sysctl -qw net.ipv4.ip_forward=1
+	ip netns exec $ns2 sysctl -qw net.ipv6.conf.all.forwarding=1
 
 	$IP li add veth1 type veth peer name veth2
 	$IP li add veth3 type veth peer name veth4
 
 	$IP li set veth1 up
 	$IP li set veth3 up
-	$IP li set veth2 netns ns2 up
-	$IP li set veth4 netns ns2 up
-	ip -netns ns2 li add dummy1 type dummy
-	ip -netns ns2 li set dummy1 up
+	$IP li set veth2 netns $ns2 up
+	$IP li set veth4 netns $ns2 up
+	ip -netns $ns2 li add dummy1 type dummy
+	ip -netns $ns2 li set dummy1 up
 
 	$IP -6 addr add 2001:db8:101::1/64 dev veth1 nodad
 	$IP -6 addr add 2001:db8:103::1/64 dev veth3 nodad
 	$IP addr add 172.16.101.1/24 dev veth1
 	$IP addr add 172.16.103.1/24 dev veth3
 
-	ip -netns ns2 -6 addr add 2001:db8:101::2/64 dev veth2 nodad
-	ip -netns ns2 -6 addr add 2001:db8:103::2/64 dev veth4 nodad
-	ip -netns ns2 -6 addr add 2001:db8:104::1/64 dev dummy1 nodad
+	ip -netns $ns2 -6 addr add 2001:db8:101::2/64 dev veth2 nodad
+	ip -netns $ns2 -6 addr add 2001:db8:103::2/64 dev veth4 nodad
+	ip -netns $ns2 -6 addr add 2001:db8:104::1/64 dev dummy1 nodad
 
-	ip -netns ns2 addr add 172.16.101.2/24 dev veth2
-	ip -netns ns2 addr add 172.16.103.2/24 dev veth4
-	ip -netns ns2 addr add 172.16.104.1/24 dev dummy1
+	ip -netns $ns2 addr add 172.16.101.2/24 dev veth2
+	ip -netns $ns2 addr add 172.16.103.2/24 dev veth4
+	ip -netns $ns2 addr add 172.16.104.1/24 dev dummy1
 
 	set +e
 }
@@ -1238,7 +1228,7 @@ ipv6_addr_metric_test()
 	log_test $rc 0 "Modify metric of address"
 
 	# verify prefix route removed on down
-	run_cmd "ip netns exec ns1 sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1"
+	run_cmd "ip netns exec $ns1 sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1"
 	run_cmd "$IP li set dev dummy2 down"
 	rc=$?
 	if [ $rc -eq 0 ]; then
@@ -1344,7 +1334,7 @@ ipv6_route_metrics_test()
 	log_test $rc 0 "Multipath route with mtu metric"
 
 	$IP -6 ro add 2001:db8:104::/64 via 2001:db8:101::2 mtu 1300
-	run_cmd "ip netns exec ns1 ${ping6} -w1 -c1 -s 1500 2001:db8:104::1"
+	run_cmd "ip netns exec $ns1 ${ping6} -w1 -c1 -s 1500 2001:db8:104::1"
 	log_test $? 0 "Using route with mtu metric"
 
 	run_cmd "$IP -6 ro add 2001:db8:114::/64 via  2001:db8:101::2  congctl lock foo"
@@ -1599,19 +1589,19 @@ ipv4_rt_replace()
 ipv4_local_rt_cache()
 {
 	run_cmd "ip addr add 10.0.0.1/32 dev lo"
-	run_cmd "ip netns add test-ns"
+	run_cmd "setup_ns test-ns"
 	run_cmd "ip link add veth-outside type veth peer name veth-inside"
 	run_cmd "ip link add vrf-100 type vrf table 1100"
 	run_cmd "ip link set veth-outside master vrf-100"
-	run_cmd "ip link set veth-inside netns test-ns"
+	run_cmd "ip link set veth-inside netns $test-ns"
 	run_cmd "ip link set veth-outside up"
 	run_cmd "ip link set vrf-100 up"
 	run_cmd "ip route add 10.1.1.1/32 dev veth-outside table 1100"
-	run_cmd "ip netns exec test-ns ip link set veth-inside up"
-	run_cmd "ip netns exec test-ns ip addr add 10.1.1.1/32 dev veth-inside"
-	run_cmd "ip netns exec test-ns ip route add 10.0.0.1/32 dev veth-inside"
-	run_cmd "ip netns exec test-ns ip route add default via 10.0.0.1"
-	run_cmd "ip netns exec test-ns ping 10.0.0.1 -c 1 -i 1"
+	run_cmd "ip netns exec $test-ns ip link set veth-inside up"
+	run_cmd "ip netns exec $test-ns ip addr add 10.1.1.1/32 dev veth-inside"
+	run_cmd "ip netns exec $test-ns ip route add 10.0.0.1/32 dev veth-inside"
+	run_cmd "ip netns exec $test-ns ip route add default via 10.0.0.1"
+	run_cmd "ip netns exec $test-ns ping 10.0.0.1 -c 1 -i 1"
 	run_cmd "ip link delete vrf-100"
 
 	# if we do not hang test is a success
@@ -1841,7 +1831,7 @@ ipv4_route_metrics_test()
 	log_test $rc 0 "Multipath route with mtu metric"
 
 	$IP ro add 172.16.104.0/24 via 172.16.101.2 mtu 1300
-	run_cmd "ip netns exec ns1 ping -w1 -c1 -s 1500 172.16.104.1"
+	run_cmd "ip netns exec $ns1 ping -w1 -c1 -s 1500 172.16.104.1"
 	log_test $? 0 "Using route with mtu metric"
 
 	run_cmd "$IP ro add 172.16.111.0/24 via 172.16.101.2 congctl lock foo"
@@ -2105,7 +2095,7 @@ ipv4_route_v6_gw_test()
 		check_route "172.16.104.0/24 via inet6 2001:db8:101::2 dev veth1"
 	fi
 
-	run_cmd "ip netns exec ns1 ping -w1 -c1 172.16.104.1"
+	run_cmd "ip netns exec $ns1 ping -w1 -c1 172.16.104.1"
 	log_test $rc 0 "Single path route with IPv6 gateway - ping"
 
 	run_cmd "$IP ro del 172.16.104.0/24 via inet6 2001:db8:101::2"
@@ -2196,7 +2186,7 @@ ipv4_mangle_test()
 	sleep 2
 
 	local tmp_file=$(mktemp)
-	ip netns exec ns2 socat UDP4-LISTEN:54321,fork $tmp_file &
+	ip netns exec $ns2 socat UDP4-LISTEN:54321,fork $tmp_file &
 
 	# Add a FIB rule and a route that will direct our connection to the
 	# listening server.
@@ -2254,7 +2244,7 @@ ipv6_mangle_test()
 	sleep 2
 
 	local tmp_file=$(mktemp)
-	ip netns exec ns2 socat UDP6-LISTEN:54321,fork $tmp_file &
+	ip netns exec $ns2 socat UDP6-LISTEN:54321,fork $tmp_file &
 
 	# Add a FIB rule and a route that will direct our connection to the
 	# listening server.
@@ -2423,37 +2413,37 @@ ipv4_mpath_list_test()
 	route_setup
 
 	set -e
-	run_cmd "ip netns exec ns1 ethtool -K veth1 tcp-segmentation-offload off"
-
-	run_cmd "ip netns exec ns2 bash -c \"echo 20000 > /sys/class/net/veth2/gro_flush_timeout\""
-	run_cmd "ip netns exec ns2 bash -c \"echo 1 > /sys/class/net/veth2/napi_defer_hard_irqs\""
-	run_cmd "ip netns exec ns2 ethtool -K veth2 generic-receive-offload on"
-	run_cmd "ip -n ns2 link add name nh1 up type dummy"
-	run_cmd "ip -n ns2 link add name nh2 up type dummy"
-	run_cmd "ip -n ns2 address add 172.16.201.1/24 dev nh1"
-	run_cmd "ip -n ns2 address add 172.16.202.1/24 dev nh2"
-	run_cmd "ip -n ns2 neigh add 172.16.201.2 lladdr 00:11:22:33:44:55 nud perm dev nh1"
-	run_cmd "ip -n ns2 neigh add 172.16.202.2 lladdr 00:aa:bb:cc:dd:ee nud perm dev nh2"
-	run_cmd "ip -n ns2 route add 203.0.113.0/24
+	run_cmd "ip netns exec $ns1 ethtool -K veth1 tcp-segmentation-offload off"
+
+	run_cmd "ip netns exec $ns2 bash -c \"echo 20000 > /sys/class/net/veth2/gro_flush_timeout\""
+	run_cmd "ip netns exec $ns2 bash -c \"echo 1 > /sys/class/net/veth2/napi_defer_hard_irqs\""
+	run_cmd "ip netns exec $ns2 ethtool -K veth2 generic-receive-offload on"
+	run_cmd "ip -n $ns2 link add name nh1 up type dummy"
+	run_cmd "ip -n $ns2 link add name nh2 up type dummy"
+	run_cmd "ip -n $ns2 address add 172.16.201.1/24 dev nh1"
+	run_cmd "ip -n $ns2 address add 172.16.202.1/24 dev nh2"
+	run_cmd "ip -n $ns2 neigh add 172.16.201.2 lladdr 00:11:22:33:44:55 nud perm dev nh1"
+	run_cmd "ip -n $ns2 neigh add 172.16.202.2 lladdr 00:aa:bb:cc:dd:ee nud perm dev nh2"
+	run_cmd "ip -n $ns2 route add 203.0.113.0/24
 		nexthop via 172.16.201.2 nexthop via 172.16.202.2"
-	run_cmd "ip netns exec ns2 sysctl -qw net.ipv4.fib_multipath_hash_policy=1"
-	run_cmd "ip netns exec ns2 sysctl -qw net.ipv4.conf.veth2.rp_filter=0"
-	run_cmd "ip netns exec ns2 sysctl -qw net.ipv4.conf.all.rp_filter=0"
-	run_cmd "ip netns exec ns2 sysctl -qw net.ipv4.conf.default.rp_filter=0"
+	run_cmd "ip netns exec $ns2 sysctl -qw net.ipv4.fib_multipath_hash_policy=1"
+	run_cmd "ip netns exec $ns2 sysctl -qw net.ipv4.conf.veth2.rp_filter=0"
+	run_cmd "ip netns exec $ns2 sysctl -qw net.ipv4.conf.all.rp_filter=0"
+	run_cmd "ip netns exec $ns2 sysctl -qw net.ipv4.conf.default.rp_filter=0"
 	set +e
 
-	local dmac=$(ip -n ns2 -j link show dev veth2 | jq -r '.[]["address"]')
+	local dmac=$(ip -n $ns2 -j link show dev veth2 | jq -r '.[]["address"]')
 	local tmp_file=$(mktemp)
-	local cmd="ip netns exec ns1 mausezahn veth1 -a own -b $dmac
+	local cmd="ip netns exec $ns1 mausezahn veth1 -a own -b $dmac
 		-A 172.16.101.1 -B 203.0.113.1 -t udp 'sp=12345,dp=0-65535' -q"
 
 	# Packets forwarded in a list using a multipath route must not reuse a
 	# cached result so that a flow always hits the same nexthop. In other
 	# words, the FIB lookup tracepoint needs to be triggered for every
 	# packet.
-	local t0_rx_pkts=$(link_stats_get ns2 veth2 rx packets)
+	local t0_rx_pkts=$(link_stats_get $ns2 veth2 rx packets)
 	run_cmd "perf stat -a -e fib:fib_table_lookup --filter 'err == 0' -j -o $tmp_file -- $cmd"
-	local t1_rx_pkts=$(link_stats_get ns2 veth2 rx packets)
+	local t1_rx_pkts=$(link_stats_get $ns2 veth2 rx packets)
 	local diff=$(echo $t1_rx_pkts - $t0_rx_pkts | bc -l)
 	list_rcv_eval $tmp_file $diff
 
@@ -2471,34 +2461,34 @@ ipv6_mpath_list_test()
 	route_setup
 
 	set -e
-	run_cmd "ip netns exec ns1 ethtool -K veth1 tcp-segmentation-offload off"
-
-	run_cmd "ip netns exec ns2 bash -c \"echo 20000 > /sys/class/net/veth2/gro_flush_timeout\""
-	run_cmd "ip netns exec ns2 bash -c \"echo 1 > /sys/class/net/veth2/napi_defer_hard_irqs\""
-	run_cmd "ip netns exec ns2 ethtool -K veth2 generic-receive-offload on"
-	run_cmd "ip -n ns2 link add name nh1 up type dummy"
-	run_cmd "ip -n ns2 link add name nh2 up type dummy"
-	run_cmd "ip -n ns2 -6 address add 2001:db8:201::1/64 dev nh1"
-	run_cmd "ip -n ns2 -6 address add 2001:db8:202::1/64 dev nh2"
-	run_cmd "ip -n ns2 -6 neigh add 2001:db8:201::2 lladdr 00:11:22:33:44:55 nud perm dev nh1"
-	run_cmd "ip -n ns2 -6 neigh add 2001:db8:202::2 lladdr 00:aa:bb:cc:dd:ee nud perm dev nh2"
-	run_cmd "ip -n ns2 -6 route add 2001:db8:301::/64
+	run_cmd "ip netns exec $ns1 ethtool -K veth1 tcp-segmentation-offload off"
+
+	run_cmd "ip netns exec $ns2 bash -c \"echo 20000 > /sys/class/net/veth2/gro_flush_timeout\""
+	run_cmd "ip netns exec $ns2 bash -c \"echo 1 > /sys/class/net/veth2/napi_defer_hard_irqs\""
+	run_cmd "ip netns exec $ns2 ethtool -K veth2 generic-receive-offload on"
+	run_cmd "ip -n $ns2 link add name nh1 up type dummy"
+	run_cmd "ip -n $ns2 link add name nh2 up type dummy"
+	run_cmd "ip -n $ns2 -6 address add 2001:db8:201::1/64 dev nh1"
+	run_cmd "ip -n $ns2 -6 address add 2001:db8:202::1/64 dev nh2"
+	run_cmd "ip -n $ns2 -6 neigh add 2001:db8:201::2 lladdr 00:11:22:33:44:55 nud perm dev nh1"
+	run_cmd "ip -n $ns2 -6 neigh add 2001:db8:202::2 lladdr 00:aa:bb:cc:dd:ee nud perm dev nh2"
+	run_cmd "ip -n $ns2 -6 route add 2001:db8:301::/64
 		nexthop via 2001:db8:201::2 nexthop via 2001:db8:202::2"
-	run_cmd "ip netns exec ns2 sysctl -qw net.ipv6.fib_multipath_hash_policy=1"
+	run_cmd "ip netns exec $ns2 sysctl -qw net.ipv6.fib_multipath_hash_policy=1"
 	set +e
 
-	local dmac=$(ip -n ns2 -j link show dev veth2 | jq -r '.[]["address"]')
+	local dmac=$(ip -n $ns2 -j link show dev veth2 | jq -r '.[]["address"]')
 	local tmp_file=$(mktemp)
-	local cmd="ip netns exec ns1 mausezahn -6 veth1 -a own -b $dmac
+	local cmd="ip netns exec $ns1 mausezahn -6 veth1 -a own -b $dmac
 		-A 2001:db8:101::1 -B 2001:db8:301::1 -t udp 'sp=12345,dp=0-65535' -q"
 
 	# Packets forwarded in a list using a multipath route must not reuse a
 	# cached result so that a flow always hits the same nexthop. In other
 	# words, the FIB lookup tracepoint needs to be triggered for every
 	# packet.
-	local t0_rx_pkts=$(link_stats_get ns2 veth2 rx packets)
+	local t0_rx_pkts=$(link_stats_get $ns2 veth2 rx packets)
 	run_cmd "perf stat -a -e fib6:fib6_table_lookup --filter 'err == 0' -j -o $tmp_file -- $cmd"
-	local t1_rx_pkts=$(link_stats_get ns2 veth2 rx packets)
+	local t1_rx_pkts=$(link_stats_get $ns2 veth2 rx packets)
 	local diff=$(echo $t1_rx_pkts - $t0_rx_pkts | bc -l)
 	list_rcv_eval $tmp_file $diff
 
diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index df593b7b3e6b..452693514be4 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -17,6 +17,7 @@ TEST_PROGS = bridge_fdb_learning_limit.sh \
 	dual_vxlan_bridge.sh \
 	ethtool_extended_state.sh \
 	ethtool_mm.sh \
+	ethtool_rmon.sh \
 	ethtool.sh \
 	gre_custom_multipath_hash.sh \
 	gre_inner_v4_multipath.sh \
diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh
index e4e3e9405056..61348f71728c 100755
--- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh
@@ -803,11 +803,198 @@ cfg_test_dump()
 	cfg_test_dump_common "L2" l2_grps_get
 }
 
+# Check flush functionality with different parameters.
+cfg_test_flush()
+{
+	local num_entries
+
+	# Add entries with different attributes and check that they are all
+	# flushed when the flush command is given with no parameters.
+
+	# Different port.
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.1 vid 10
+	bridge mdb add dev br0 port $swp2 grp 239.1.1.2 vid 10
+
+	# Different VLAN ID.
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.3 vid 10
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.4 vid 20
+
+	# Different routing protocol.
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.5 vid 10 proto bgp
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.6 vid 10 proto zebra
+
+	# Different state.
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.7 vid 10 permanent
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.8 vid 10 temp
+
+	bridge mdb flush dev br0
+	num_entries=$(bridge mdb show dev br0 | wc -l)
+	[[ $num_entries -eq 0 ]]
+	check_err $? 0 "Not all entries flushed after flush all"
+
+	# Check that when flushing by port only entries programmed with the
+	# specified port are flushed and the rest are not.
+
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.1 vid 10
+	bridge mdb add dev br0 port $swp2 grp 239.1.1.1 vid 10
+	bridge mdb add dev br0 port br0 grp 239.1.1.1 vid 10
+
+	bridge mdb flush dev br0 port $swp1
+
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port $swp1"
+	check_fail $? "Entry not flushed by specified port"
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port $swp2"
+	check_err $? "Entry flushed by wrong port"
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port br0"
+	check_err $? "Host entry flushed by wrong port"
+
+	bridge mdb flush dev br0 port br0
+
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port br0"
+	check_fail $? "Host entry not flushed by specified port"
+
+	bridge mdb flush dev br0
+
+	# Check that when flushing by VLAN ID only entries programmed with the
+	# specified VLAN ID are flushed and the rest are not.
+
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.1 vid 10
+	bridge mdb add dev br0 port $swp2 grp 239.1.1.1 vid 10
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.1 vid 20
+	bridge mdb add dev br0 port $swp2 grp 239.1.1.1 vid 20
+
+	bridge mdb flush dev br0 vid 10
+
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 &> /dev/null
+	check_fail $? "Entry not flushed by specified VLAN ID"
+	bridge mdb get dev br0 grp 239.1.1.1 vid 20 &> /dev/null
+	check_err $? "Entry flushed by wrong VLAN ID"
+
+	bridge mdb flush dev br0
+
+	# Check that all permanent entries are flushed when "permanent" is
+	# specified and that temporary entries are not.
+
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.1 permanent vid 10
+	bridge mdb add dev br0 port $swp2 grp 239.1.1.1 temp vid 10
+
+	bridge mdb flush dev br0 permanent
+
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port $swp1"
+	check_fail $? "Entry not flushed by \"permanent\" state"
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port $swp2"
+	check_err $? "Entry flushed by wrong state (\"permanent\")"
+
+	bridge mdb flush dev br0
+
+	# Check that all temporary entries are flushed when "nopermanent" is
+	# specified and that permanent entries are not.
+
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.1 permanent vid 10
+	bridge mdb add dev br0 port $swp2 grp 239.1.1.1 temp vid 10
+
+	bridge mdb flush dev br0 nopermanent
+
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port $swp1"
+	check_err $? "Entry flushed by wrong state (\"nopermanent\")"
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port $swp2"
+	check_fail $? "Entry not flushed by \"nopermanent\" state"
+
+	bridge mdb flush dev br0
+
+	# Check that L2 host entries are not flushed when "nopermanent" is
+	# specified, but flushed when "permanent" is specified.
+
+	bridge mdb add dev br0 port br0 grp 01:02:03:04:05:06 permanent vid 10
+
+	bridge mdb flush dev br0 nopermanent
+
+	bridge mdb get dev br0 grp 01:02:03:04:05:06 vid 10 &> /dev/null
+	check_err $? "L2 host entry flushed by wrong state (\"nopermanent\")"
+
+	bridge mdb flush dev br0 permanent
+
+	bridge mdb get dev br0 grp 01:02:03:04:05:06 vid 10 &> /dev/null
+	check_fail $? "L2 host entry not flushed by \"permanent\" state"
+
+	bridge mdb flush dev br0
+
+	# Check that IPv4 host entries are not flushed when "permanent" is
+	# specified, but flushed when "nopermanent" is specified.
+
+	bridge mdb add dev br0 port br0 grp 239.1.1.1 temp vid 10
+
+	bridge mdb flush dev br0 permanent
+
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 &> /dev/null
+	check_err $? "IPv4 host entry flushed by wrong state (\"permanent\")"
+
+	bridge mdb flush dev br0 nopermanent
+
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 &> /dev/null
+	check_fail $? "IPv4 host entry not flushed by \"nopermanent\" state"
+
+	bridge mdb flush dev br0
+
+	# Check that IPv6 host entries are not flushed when "permanent" is
+	# specified, but flushed when "nopermanent" is specified.
+
+	bridge mdb add dev br0 port br0 grp ff0e::1 temp vid 10
+
+	bridge mdb flush dev br0 permanent
+
+	bridge mdb get dev br0 grp ff0e::1 vid 10 &> /dev/null
+	check_err $? "IPv6 host entry flushed by wrong state (\"permanent\")"
+
+	bridge mdb flush dev br0 nopermanent
+
+	bridge mdb get dev br0 grp ff0e::1 vid 10 &> /dev/null
+	check_fail $? "IPv6 host entry not flushed by \"nopermanent\" state"
+
+	bridge mdb flush dev br0
+
+	# Check that when flushing by routing protocol only entries programmed
+	# with the specified routing protocol are flushed and the rest are not.
+
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.1 vid 10 proto bgp
+	bridge mdb add dev br0 port $swp2 grp 239.1.1.1 vid 10 proto zebra
+	bridge mdb add dev br0 port br0 grp 239.1.1.1 vid 10
+
+	bridge mdb flush dev br0 proto bgp
+
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port $swp1"
+	check_fail $? "Entry not flushed by specified routing protocol"
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port $swp2"
+	check_err $? "Entry flushed by wrong routing protocol"
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port br0"
+	check_err $? "Host entry flushed by wrong routing protocol"
+
+	bridge mdb flush dev br0
+
+	# Test that an error is returned when trying to flush using unsupported
+	# parameters.
+
+	bridge mdb flush dev br0 src_vni 10 &> /dev/null
+	check_fail $? "Managed to flush by source VNI"
+
+	bridge mdb flush dev br0 dst 198.51.100.1 &> /dev/null
+	check_fail $? "Managed to flush by destination IP"
+
+	bridge mdb flush dev br0 dst_port 4789 &> /dev/null
+	check_fail $? "Managed to flush by UDP destination port"
+
+	bridge mdb flush dev br0 vni 10 &> /dev/null
+	check_fail $? "Managed to flush by destination VNI"
+
+	log_test "Flush tests"
+}
+
 cfg_test()
 {
 	cfg_test_host
 	cfg_test_port
 	cfg_test_dump
+	cfg_test_flush
 }
 
 __fwd_test_host_ip()
@@ -1166,8 +1353,8 @@ ctrl_test()
 	ctrl_mldv2_is_in_test
 }
 
-if ! bridge mdb help 2>&1 | grep -q "get"; then
-	echo "SKIP: iproute2 too old, missing bridge mdb get support"
+if ! bridge mdb help 2>&1 | grep -q "flush"; then
+	echo "SKIP: iproute2 too old, missing bridge mdb flush support"
 	exit $ksft_skip
 fi
 
diff --git a/tools/testing/selftests/net/forwarding/ethtool_mm.sh b/tools/testing/selftests/net/forwarding/ethtool_mm.sh
index 39e736f30322..50d5bfb17ef1 100755
--- a/tools/testing/selftests/net/forwarding/ethtool_mm.sh
+++ b/tools/testing/selftests/net/forwarding/ethtool_mm.sh
@@ -25,6 +25,10 @@ traffic_test()
 	local after=
 	local delta=
 
+	if [ ${has_pmac_stats[$if]} = false ]; then
+		src="aggregate"
+	fi
+
 	before=$(ethtool_std_stats_get $if "eth-mac" "FramesTransmittedOK" $src)
 
 	$MZ $if -q -c $num_pkts -p 64 -b bcast -t ip -R $PREEMPTIBLE_PRIO
@@ -155,15 +159,48 @@ manual_failed_verification_h2_to_h1()
 	manual_failed_verification $h2 $h1
 }
 
+smallest_supported_add_frag_size()
+{
+	local iface=$1
+	local rx_min_frag_size=
+
+	rx_min_frag_size=$(ethtool --json --show-mm $iface | \
+		jq '.[]."rx-min-frag-size"')
+
+	if [ $rx_min_frag_size -le 60 ]; then
+		echo 0
+	elif [ $rx_min_frag_size -le 124 ]; then
+		echo 1
+	elif [ $rx_min_frag_size -le 188 ]; then
+		echo 2
+	elif [ $rx_min_frag_size -le 252 ]; then
+		echo 3
+	else
+		echo "$iface: RX min frag size $rx_min_frag_size cannot be advertised over LLDP"
+		exit 1
+	fi
+}
+
+expected_add_frag_size()
+{
+	local iface=$1
+	local requested=$2
+	local min=$(smallest_supported_add_frag_size $iface)
+
+	[ $requested -le $min ] && echo $min || echo $requested
+}
+
 lldp_change_add_frag_size()
 {
 	local add_frag_size=$1
+	local pattern=
 
 	lldptool -T -i $h1 -V addEthCaps addFragSize=$add_frag_size >/dev/null
 	# Wait for TLVs to be received
 	sleep 2
-	lldptool -i $h2 -t -n -V addEthCaps | \
-		grep -q "Additional fragment size: $add_frag_size"
+	pattern=$(printf "Additional fragment size: %d" \
+			 $(expected_add_frag_size $h1 $add_frag_size))
+	lldptool -i $h2 -t -n -V addEthCaps | grep -q "$pattern"
 }
 
 lldp()
@@ -284,6 +321,13 @@ for netif in ${NETIFS[@]}; do
 		echo "SKIP: $netif does not support MAC Merge"
 		exit $ksft_skip
 	fi
+
+	if check_ethtool_pmac_std_stats_support $netif eth-mac; then
+		has_pmac_stats[$netif]=true
+	else
+		has_pmac_stats[$netif]=false
+		echo "$netif does not report pMAC statistics, falling back to aggregate"
+	fi
 done
 
 trap cleanup EXIT
diff --git a/tools/testing/selftests/net/forwarding/ethtool_rmon.sh b/tools/testing/selftests/net/forwarding/ethtool_rmon.sh
new file mode 100755
index 000000000000..41a34a61f763
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/ethtool_rmon.sh
@@ -0,0 +1,143 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+	rmon_rx_histogram
+	rmon_tx_histogram
+"
+
+NUM_NETIFS=2
+source lib.sh
+
+ETH_FCS_LEN=4
+ETH_HLEN=$((6+6+2))
+
+declare -A netif_mtu
+
+ensure_mtu()
+{
+	local iface=$1; shift
+	local len=$1; shift
+	local current=$(ip -j link show dev $iface | jq -r '.[0].mtu')
+	local required=$((len - ETH_HLEN - ETH_FCS_LEN))
+
+	if [ $current -lt $required ]; then
+		ip link set dev $iface mtu $required || return 1
+	fi
+}
+
+bucket_test()
+{
+	local iface=$1; shift
+	local neigh=$1; shift
+	local set=$1; shift
+	local bucket=$1; shift
+	local len=$1; shift
+	local num_rx=10000
+	local num_tx=20000
+	local expected=
+	local before=
+	local after=
+	local delta=
+
+	# Mausezahn does not include FCS bytes in its length - but the
+	# histogram counters do
+	len=$((len - ETH_FCS_LEN))
+
+	before=$(ethtool --json -S $iface --groups rmon | \
+		jq -r ".[0].rmon[\"${set}-pktsNtoM\"][$bucket].val")
+
+	# Send 10k one way and 20k in the other, to detect counters
+	# mapped to the wrong direction
+	$MZ $neigh -q -c $num_rx -p $len -a own -b bcast -d 10us
+	$MZ $iface -q -c $num_tx -p $len -a own -b bcast -d 10us
+
+	after=$(ethtool --json -S $iface --groups rmon | \
+		jq -r ".[0].rmon[\"${set}-pktsNtoM\"][$bucket].val")
+
+	delta=$((after - before))
+
+	expected=$([ $set = rx ] && echo $num_rx || echo $num_tx)
+
+	# Allow some extra tolerance for other packets sent by the stack
+	[ $delta -ge $expected ] && [ $delta -le $((expected + 100)) ]
+}
+
+rmon_histogram()
+{
+	local iface=$1; shift
+	local neigh=$1; shift
+	local set=$1; shift
+	local nbuckets=0
+	local step=
+
+	RET=0
+
+	while read -r -a bucket; do
+		step="$set-pkts${bucket[0]}to${bucket[1]} on $iface"
+
+		for if in $iface $neigh; do
+			if ! ensure_mtu $if ${bucket[0]}; then
+				log_test_skip "$if does not support the required MTU for $step"
+				return
+			fi
+		done
+
+		if ! bucket_test $iface $neigh $set $nbuckets ${bucket[0]}; then
+			check_err 1 "$step failed"
+			return 1
+		fi
+		log_test "$step"
+		nbuckets=$((nbuckets + 1))
+	done < <(ethtool --json -S $iface --groups rmon | \
+		jq -r ".[0].rmon[\"${set}-pktsNtoM\"][]|[.low, .high]|@tsv" 2>/dev/null)
+
+	if [ $nbuckets -eq 0 ]; then
+		log_test_skip "$iface does not support $set histogram counters"
+		return
+	fi
+}
+
+rmon_rx_histogram()
+{
+	rmon_histogram $h1 $h2 rx
+	rmon_histogram $h2 $h1 rx
+}
+
+rmon_tx_histogram()
+{
+	rmon_histogram $h1 $h2 tx
+	rmon_histogram $h2 $h1 tx
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	h2=${NETIFS[p2]}
+
+	for iface in $h1 $h2; do
+		netif_mtu[$iface]=$(ip -j link show dev $iface | jq -r '.[0].mtu')
+		ip link set dev $iface up
+	done
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	for iface in $h2 $h1; do
+		ip link set dev $iface \
+			mtu ${netif_mtu[$iface]} \
+			down
+	done
+}
+
+check_ethtool_counter_group_support
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index e37a15eda6c2..8a61464ab6eb 100755
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -4,9 +4,6 @@
 ##############################################################################
 # Defines
 
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
 # Can be overridden by the configuration file.
 PING=${PING:=ping}
 PING6=${PING6:=ping6}
@@ -41,6 +38,32 @@ if [[ -f $relative_path/forwarding.config ]]; then
 	source "$relative_path/forwarding.config"
 fi
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+busywait()
+{
+	local timeout=$1; shift
+
+	local start_time="$(date -u +%s%3N)"
+	while true
+	do
+		local out
+		out=$("$@")
+		local ret=$?
+		if ((!ret)); then
+			echo -n "$out"
+			return 0
+		fi
+
+		local current_time="$(date -u +%s%3N)"
+		if ((current_time - start_time > timeout)); then
+			echo -n "$out"
+			return 1
+		fi
+	done
+}
+
 ##############################################################################
 # Sanity checks
 
@@ -148,6 +171,24 @@ check_ethtool_mm_support()
 	fi
 }
 
+check_ethtool_counter_group_support()
+{
+	ethtool --help 2>&1| grep -- '--all-groups' &> /dev/null
+	if [[ $? -ne 0 ]]; then
+		echo "SKIP: ethtool too old; it is missing standard counter group support"
+		exit $ksft_skip
+	fi
+}
+
+check_ethtool_pmac_std_stats_support()
+{
+	local dev=$1; shift
+	local grp=$1; shift
+
+	[ 0 -ne $(ethtool --json -S $dev --all-groups --src pmac 2>/dev/null \
+		| jq ".[].\"$grp\" | length") ]
+}
+
 check_locked_port_support()
 {
 	if ! bridge -d link show | grep -q " locked"; then
@@ -395,29 +436,6 @@ log_info()
 	echo "INFO: $msg"
 }
 
-busywait()
-{
-	local timeout=$1; shift
-
-	local start_time="$(date -u +%s%3N)"
-	while true
-	do
-		local out
-		out=$("$@")
-		local ret=$?
-		if ((!ret)); then
-			echo -n "$out"
-			return 0
-		fi
-
-		local current_time="$(date -u +%s%3N)"
-		if ((current_time - start_time > timeout)); then
-			echo -n "$out"
-			return 1
-		fi
-	done
-}
-
 not()
 {
 	"$@"
diff --git a/tools/testing/selftests/net/fq_band_pktlimit.sh b/tools/testing/selftests/net/fq_band_pktlimit.sh
new file mode 100755
index 000000000000..24b77bdf41ff
--- /dev/null
+++ b/tools/testing/selftests/net/fq_band_pktlimit.sh
@@ -0,0 +1,57 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Verify that FQ has a packet limit per band:
+#
+# 1. set the limit to 10 per band
+# 2. send 20 pkts on band A: verify that 10 are queued, 10 dropped
+# 3. send 20 pkts on band A: verify that  0 are queued, 20 dropped
+# 4. send 20 pkts on band B: verify that 10 are queued, 10 dropped
+#
+# Send packets with a 100ms delay to ensure that previously sent
+# packets are still queued when later ones are sent.
+# Use SO_TXTIME for this.
+
+die() {
+	echo "$1"
+	exit 1
+}
+
+# run inside private netns
+if [[ $# -eq 0 ]]; then
+	./in_netns.sh "$0" __subprocess
+	exit
+fi
+
+ip link add type dummy
+ip link set dev dummy0 up
+ip -6 addr add fdaa::1/128 dev dummy0
+ip -6 route add fdaa::/64 dev dummy0
+tc qdisc replace dev dummy0 root handle 1: fq quantum 1514 initial_quantum 1514 limit 10
+
+./cmsg_sender -6 -p u -d 100000 -n 20 fdaa::2 8000
+OUT1="$(tc -s qdisc show dev dummy0 | grep '^\ Sent')"
+
+./cmsg_sender -6 -p u -d 100000 -n 20 fdaa::2 8000
+OUT2="$(tc -s qdisc show dev dummy0 | grep '^\ Sent')"
+
+./cmsg_sender -6 -p u -d 100000 -n 20 -P 7 fdaa::2 8000
+OUT3="$(tc -s qdisc show dev dummy0 | grep '^\ Sent')"
+
+# Initial stats will report zero sent, as all packets are still
+# queued in FQ. Sleep for the delay period (100ms) and see that
+# twenty are now sent.
+sleep 0.1
+OUT4="$(tc -s qdisc show dev dummy0 | grep '^\ Sent')"
+
+# Log the output after the test
+echo "${OUT1}"
+echo "${OUT2}"
+echo "${OUT3}"
+echo "${OUT4}"
+
+# Test the output for expected values
+echo "${OUT1}" | grep -q '0\ pkt\ (dropped\ 10'  || die "unexpected drop count at 1"
+echo "${OUT2}" | grep -q '0\ pkt\ (dropped\ 30'  || die "unexpected drop count at 2"
+echo "${OUT3}" | grep -q '0\ pkt\ (dropped\ 40'  || die "unexpected drop count at 3"
+echo "${OUT4}" | grep -q '20\ pkt\ (dropped\ 40' || die "unexpected accept count at 4"
diff --git a/tools/testing/selftests/net/gre_gso.sh b/tools/testing/selftests/net/gre_gso.sh
index 3224651db97b..5100d90f92d2 100755
--- a/tools/testing/selftests/net/gre_gso.sh
+++ b/tools/testing/selftests/net/gre_gso.sh
@@ -2,10 +2,8 @@
 # SPDX-License-Identifier: GPL-2.0
 
 # This test is for checking GRE GSO.
-
+source lib.sh
 ret=0
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
 
 # all tests in this script. Can be overridden with -t option
 TESTS="gre_gso"
@@ -13,8 +11,6 @@ TESTS="gre_gso"
 VERBOSE=0
 PAUSE_ON_FAIL=no
 PAUSE=no
-IP="ip -netns ns1"
-NS_EXEC="ip netns exec ns1"
 TMPFILE=`mktemp`
 PID=
 
@@ -50,13 +46,13 @@ log_test()
 setup()
 {
 	set -e
-	ip netns add ns1
-	ip netns set ns1 auto
-	$IP link set dev lo up
+	setup_ns ns1
+	IP="ip -netns $ns1"
+	NS_EXEC="ip netns exec $ns1"
 
 	ip link add veth0 type veth peer name veth1
 	ip link set veth0 up
-	ip link set veth1 netns ns1
+	ip link set veth1 netns $ns1
 	$IP link set veth1 name veth0
 	$IP link set veth0 up
 
@@ -70,7 +66,7 @@ cleanup()
 	[ -n "$PID" ] && kill $PID
 	ip link del dev gre1 &> /dev/null
 	ip link del dev veth0 &> /dev/null
-	ip netns del ns1
+	cleanup_ns $ns1
 }
 
 get_linklocal()
@@ -145,7 +141,7 @@ gre6_gso_test()
 	setup
 
 	a1=$(get_linklocal veth0)
-	a2=$(get_linklocal veth0 ns1)
+	a2=$(get_linklocal veth0 $ns1)
 
 	gre_create_tun $a1 $a2
 
diff --git a/tools/testing/selftests/net/gro.c b/tools/testing/selftests/net/gro.c
index 30024d0ed373..353e1e867fbb 100644
--- a/tools/testing/selftests/net/gro.c
+++ b/tools/testing/selftests/net/gro.c
@@ -71,6 +71,12 @@
 #define MAX_PAYLOAD (IP_MAXPACKET - sizeof(struct tcphdr) - sizeof(struct ipv6hdr))
 #define NUM_LARGE_PKT (MAX_PAYLOAD / MSS)
 #define MAX_HDR_LEN (ETH_HLEN + sizeof(struct ipv6hdr) + sizeof(struct tcphdr))
+#define MIN_EXTHDR_SIZE 8
+#define EXT_PAYLOAD_1 "\x00\x00\x00\x00\x00\x00"
+#define EXT_PAYLOAD_2 "\x11\x11\x11\x11\x11\x11"
+
+#define ipv6_optlen(p)  (((p)->hdrlen+1) << 3) /* calculate IPv6 extension header len */
+#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
 
 static const char *addr6_src = "fdaa::2";
 static const char *addr6_dst = "fdaa::1";
@@ -104,7 +110,7 @@ static void setup_sock_filter(int fd)
 	const int dport_off = tcp_offset + offsetof(struct tcphdr, dest);
 	const int ethproto_off = offsetof(struct ethhdr, h_proto);
 	int optlen = 0;
-	int ipproto_off;
+	int ipproto_off, opt_ipproto_off;
 	int next_off;
 
 	if (proto == PF_INET)
@@ -116,14 +122,30 @@ static void setup_sock_filter(int fd)
 	if (strcmp(testname, "ip") == 0) {
 		if (proto == PF_INET)
 			optlen = sizeof(struct ip_timestamp);
-		else
-			optlen = sizeof(struct ip6_frag);
+		else {
+			BUILD_BUG_ON(sizeof(struct ip6_hbh) > MIN_EXTHDR_SIZE);
+			BUILD_BUG_ON(sizeof(struct ip6_dest) > MIN_EXTHDR_SIZE);
+			BUILD_BUG_ON(sizeof(struct ip6_frag) > MIN_EXTHDR_SIZE);
+
+			/* same size for HBH and Fragment extension header types */
+			optlen = MIN_EXTHDR_SIZE;
+			opt_ipproto_off = ETH_HLEN + sizeof(struct ipv6hdr)
+				+ offsetof(struct ip6_ext, ip6e_nxt);
+		}
 	}
 
+	/* this filter validates the following:
+	 *	- packet is IPv4/IPv6 according to the running test.
+	 *	- packet is TCP. Also handles the case of one extension header and then TCP.
+	 *	- checks the packet tcp dport equals to DPORT. Also handles the case of one
+	 *	  extension header and then TCP.
+	 */
 	struct sock_filter filter[] = {
 			BPF_STMT(BPF_LD  + BPF_H   + BPF_ABS, ethproto_off),
-			BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, ntohs(ethhdr_proto), 0, 7),
+			BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, ntohs(ethhdr_proto), 0, 9),
 			BPF_STMT(BPF_LD  + BPF_B   + BPF_ABS, ipproto_off),
+			BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, IPPROTO_TCP, 2, 0),
+			BPF_STMT(BPF_LD  + BPF_B   + BPF_ABS, opt_ipproto_off),
 			BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, IPPROTO_TCP, 0, 5),
 			BPF_STMT(BPF_LD  + BPF_H   + BPF_ABS, dport_off),
 			BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, DPORT, 2, 0),
@@ -576,6 +598,39 @@ static void add_ipv4_ts_option(void *buf, void *optpkt)
 	iph->check = checksum_fold(iph, sizeof(struct iphdr) + optlen, 0);
 }
 
+static void add_ipv6_exthdr(void *buf, void *optpkt, __u8 exthdr_type, char *ext_payload)
+{
+	struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr *)(optpkt + tcp_offset);
+	struct ipv6hdr *iph = (struct ipv6hdr *)(optpkt + ETH_HLEN);
+	char *exthdr_payload_start = (char *)(exthdr + 1);
+
+	exthdr->hdrlen = 0;
+	exthdr->nexthdr = IPPROTO_TCP;
+
+	memcpy(exthdr_payload_start, ext_payload, MIN_EXTHDR_SIZE - sizeof(*exthdr));
+
+	memcpy(optpkt, buf, tcp_offset);
+	memcpy(optpkt + tcp_offset + MIN_EXTHDR_SIZE, buf + tcp_offset,
+		sizeof(struct tcphdr) + PAYLOAD_LEN);
+
+	iph->nexthdr = exthdr_type;
+	iph->payload_len = htons(ntohs(iph->payload_len) + MIN_EXTHDR_SIZE);
+}
+
+static void send_ipv6_exthdr(int fd, struct sockaddr_ll *daddr, char *ext_data1, char *ext_data2)
+{
+	static char buf[MAX_HDR_LEN + PAYLOAD_LEN];
+	static char exthdr_pck[sizeof(buf) + MIN_EXTHDR_SIZE];
+
+	create_packet(buf, 0, 0, PAYLOAD_LEN, 0);
+	add_ipv6_exthdr(buf, exthdr_pck, IPPROTO_HOPOPTS, ext_data1);
+	write_packet(fd, exthdr_pck, total_hdr_len + PAYLOAD_LEN + MIN_EXTHDR_SIZE, daddr);
+
+	create_packet(buf, PAYLOAD_LEN * 1, 0, PAYLOAD_LEN, 0);
+	add_ipv6_exthdr(buf, exthdr_pck, IPPROTO_HOPOPTS, ext_data2);
+	write_packet(fd, exthdr_pck, total_hdr_len + PAYLOAD_LEN + MIN_EXTHDR_SIZE, daddr);
+}
+
 /* IPv4 options shouldn't coalesce */
 static void send_ip_options(int fd, struct sockaddr_ll *daddr)
 {
@@ -697,7 +752,7 @@ static void send_fragment6(int fd, struct sockaddr_ll *daddr)
 		create_packet(buf, PAYLOAD_LEN * i, 0, PAYLOAD_LEN, 0);
 		write_packet(fd, buf, bufpkt_len, daddr);
 	}
-
+	sleep(1);
 	create_packet(buf, PAYLOAD_LEN * 2, 0, PAYLOAD_LEN, 0);
 	memset(extpkt, 0, extpkt_len);
 
@@ -760,6 +815,7 @@ static void check_recv_pkts(int fd, int *correct_payload,
 	vlog("}, Total %d packets\nReceived {", correct_num_pkts);
 
 	while (1) {
+		ip_ext_len = 0;
 		pkt_size = recv(fd, buffer, IP_MAXPACKET + ETH_HLEN + 1, 0);
 		if (pkt_size < 0)
 			error(1, errno, "could not receive");
@@ -767,7 +823,7 @@ static void check_recv_pkts(int fd, int *correct_payload,
 		if (iph->version == 4)
 			ip_ext_len = (iph->ihl - 5) * 4;
 		else if (ip6h->version == 6 && ip6h->nexthdr != IPPROTO_TCP)
-			ip_ext_len = sizeof(struct ip6_frag);
+			ip_ext_len = MIN_EXTHDR_SIZE;
 
 		tcph = (struct tcphdr *)(buffer + tcp_offset + ip_ext_len);
 
@@ -880,7 +936,21 @@ static void gro_sender(void)
 			sleep(1);
 			write_packet(txfd, fin_pkt, total_hdr_len, &daddr);
 		} else if (proto == PF_INET6) {
+			sleep(1);
 			send_fragment6(txfd, &daddr);
+			sleep(1);
+			write_packet(txfd, fin_pkt, total_hdr_len, &daddr);
+
+			sleep(1);
+			/* send IPv6 packets with ext header with same payload */
+			send_ipv6_exthdr(txfd, &daddr, EXT_PAYLOAD_1, EXT_PAYLOAD_1);
+			sleep(1);
+			write_packet(txfd, fin_pkt, total_hdr_len, &daddr);
+
+			sleep(1);
+			/* send IPv6 packets with ext header with different payload */
+			send_ipv6_exthdr(txfd, &daddr, EXT_PAYLOAD_1, EXT_PAYLOAD_2);
+			sleep(1);
 			write_packet(txfd, fin_pkt, total_hdr_len, &daddr);
 		}
 	} else if (strcmp(testname, "large") == 0) {
@@ -997,6 +1067,17 @@ static void gro_receiver(void)
 			 */
 			printf("fragmented ip6 doesn't coalesce: ");
 			correct_payload[0] = PAYLOAD_LEN * 2;
+			correct_payload[1] = PAYLOAD_LEN;
+			correct_payload[2] = PAYLOAD_LEN;
+			check_recv_pkts(rxfd, correct_payload, 3);
+
+			printf("ipv6 with ext header does coalesce: ");
+			correct_payload[0] = PAYLOAD_LEN * 2;
+			check_recv_pkts(rxfd, correct_payload, 1);
+
+			printf("ipv6 with ext header with different payloads doesn't coalesce: ");
+			correct_payload[0] = PAYLOAD_LEN;
+			correct_payload[1] = PAYLOAD_LEN;
 			check_recv_pkts(rxfd, correct_payload, 2);
 		}
 	} else if (strcmp(testname, "large") == 0) {
diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh
index 342ad27f631b..19352f106c1d 100755
--- a/tools/testing/selftests/net/gro.sh
+++ b/tools/testing/selftests/net/gro.sh
@@ -23,11 +23,11 @@ run_test() {
   # on every try.
   for tries in {1..3}; do
     # Actual test starts here
-    ip netns exec server_ns ./gro "${ARGS[@]}" "--rx" "--iface" "server" \
+    ip netns exec $server_ns ./gro "${ARGS[@]}" "--rx" "--iface" "server" \
       1>>log.txt &
     server_pid=$!
     sleep 0.5  # to allow for socket init
-    ip netns exec client_ns ./gro "${ARGS[@]}" "--iface" "client" \
+    ip netns exec $client_ns ./gro "${ARGS[@]}" "--iface" "client" \
       1>>log.txt
     wait "${server_pid}"
     exit_code=$?
diff --git a/tools/testing/selftests/net/icmp.sh b/tools/testing/selftests/net/icmp.sh
index e4b04cd1644a..824cb0e35eff 100755
--- a/tools/testing/selftests/net/icmp.sh
+++ b/tools/testing/selftests/net/icmp.sh
@@ -18,8 +18,8 @@
 # that address space, so the kernel should substitute the dummy address
 # 192.0.0.8 defined in RFC7600.
 
-NS1=ns1
-NS2=ns2
+source lib.sh
+
 H1_IP=172.16.0.1/32
 H1_IP6=2001:db8:1::1
 RT1=172.16.1.0/24
@@ -32,15 +32,13 @@ TMPFILE=$(mktemp)
 cleanup()
 {
     rm -f "$TMPFILE"
-    ip netns del $NS1
-    ip netns del $NS2
+    cleanup_ns $NS1 $NS2
 }
 
 trap cleanup EXIT
 
 # Namespaces
-ip netns add $NS1
-ip netns add $NS2
+setup_ns NS1 NS2
 
 # Connectivity
 ip -netns $NS1 link add veth0 type veth peer name veth0 netns $NS2
diff --git a/tools/testing/selftests/net/icmp_redirect.sh b/tools/testing/selftests/net/icmp_redirect.sh
index 7b9d6e31b8e7..d6f0e449c029 100755
--- a/tools/testing/selftests/net/icmp_redirect.sh
+++ b/tools/testing/selftests/net/icmp_redirect.sh
@@ -19,6 +19,7 @@
 # Route on r1 changed to go to r2 via eth0. This causes a redirect to be sent
 # from r1 to h1 telling h1 to use r2 when talking to h2.
 
+source lib.sh
 VERBOSE=0
 PAUSE_ON_FAIL=no
 
@@ -140,11 +141,7 @@ get_linklocal()
 
 cleanup()
 {
-	local ns
-
-	for ns in h1 h2 r1 r2; do
-		ip netns del $ns 2>/dev/null
-	done
+	cleanup_ns $h1 $h2 $r1 $r2
 }
 
 create_vrf()
@@ -171,102 +168,99 @@ setup()
 
 	#
 	# create nodes as namespaces
-	#
-	for ns in h1 h2 r1 r2; do
-		ip netns add $ns
-		ip -netns $ns li set lo up
-
-		case "${ns}" in
-		h[12]) ip netns exec $ns sysctl -q -w net.ipv4.conf.all.accept_redirects=1
-		       ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=0
-		       ip netns exec $ns sysctl -q -w net.ipv6.conf.all.accept_redirects=1
-		       ip netns exec $ns sysctl -q -w net.ipv6.conf.all.keep_addr_on_down=1
-			;;
-		r[12]) ip netns exec $ns sysctl -q -w net.ipv4.ip_forward=1
-		       ip netns exec $ns sysctl -q -w net.ipv4.conf.all.send_redirects=1
-		       ip netns exec $ns sysctl -q -w net.ipv4.conf.default.rp_filter=0
-		       ip netns exec $ns sysctl -q -w net.ipv4.conf.all.rp_filter=0
-
-		       ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=1
-		       ip netns exec $ns sysctl -q -w net.ipv6.route.mtu_expires=10
-		esac
+	setup_ns h1 h2 r1 r2
+	for ns in $h1 $h2 $r1 $r2; do
+		if echo $ns | grep -q h[12]-; then
+			ip netns exec $ns sysctl -q -w net.ipv4.conf.all.accept_redirects=1
+			ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=0
+			ip netns exec $ns sysctl -q -w net.ipv6.conf.all.accept_redirects=1
+			ip netns exec $ns sysctl -q -w net.ipv6.conf.all.keep_addr_on_down=1
+		else
+			ip netns exec $ns sysctl -q -w net.ipv4.ip_forward=1
+			ip netns exec $ns sysctl -q -w net.ipv4.conf.all.send_redirects=1
+			ip netns exec $ns sysctl -q -w net.ipv4.conf.default.rp_filter=0
+			ip netns exec $ns sysctl -q -w net.ipv4.conf.all.rp_filter=0
+
+			ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=1
+			ip netns exec $ns sysctl -q -w net.ipv6.route.mtu_expires=10
+		fi
 	done
 
 	#
 	# create interconnects
 	#
-	ip -netns h1 li add eth0 type veth peer name r1h1
-	ip -netns h1 li set r1h1 netns r1 name eth0 up
+	ip -netns $h1 li add eth0 type veth peer name r1h1
+	ip -netns $h1 li set r1h1 netns $r1 name eth0 up
 
-	ip -netns h1 li add eth1 type veth peer name r2h1
-	ip -netns h1 li set r2h1 netns r2 name eth0 up
+	ip -netns $h1 li add eth1 type veth peer name r2h1
+	ip -netns $h1 li set r2h1 netns $r2 name eth0 up
 
-	ip -netns h2 li add eth0 type veth peer name r2h2
-	ip -netns h2 li set eth0 up
-	ip -netns h2 li set r2h2 netns r2 name eth2 up
+	ip -netns $h2 li add eth0 type veth peer name r2h2
+	ip -netns $h2 li set eth0 up
+	ip -netns $h2 li set r2h2 netns $r2 name eth2 up
 
-	ip -netns r1 li add eth1 type veth peer name r2r1
-	ip -netns r1 li set eth1 up
-	ip -netns r1 li set r2r1 netns r2 name eth1 up
+	ip -netns $r1 li add eth1 type veth peer name r2r1
+	ip -netns $r1 li set eth1 up
+	ip -netns $r1 li set r2r1 netns $r2 name eth1 up
 
 	#
 	# h1
 	#
 	if [ "${WITH_VRF}" = "yes" ]; then
-		create_vrf "h1"
+		create_vrf "$h1"
 		H1_VRF_ARG="vrf ${VRF}"
 		H1_PING_ARG="-I ${VRF}"
 	else
 		H1_VRF_ARG=
 		H1_PING_ARG=
 	fi
-	ip -netns h1 li add br0 type bridge
+	ip -netns $h1 li add br0 type bridge
 	if [ "${WITH_VRF}" = "yes" ]; then
-		ip -netns h1 li set br0 vrf ${VRF} up
+		ip -netns $h1 li set br0 vrf ${VRF} up
 	else
-		ip -netns h1 li set br0 up
+		ip -netns $h1 li set br0 up
 	fi
-	ip -netns h1 addr add dev br0 ${H1_N1_IP}/24
-	ip -netns h1 -6 addr add dev br0 ${H1_N1_IP6}/64 nodad
-	ip -netns h1 li set eth0 master br0 up
-	ip -netns h1 li set eth1 master br0 up
+	ip -netns $h1 addr add dev br0 ${H1_N1_IP}/24
+	ip -netns $h1 -6 addr add dev br0 ${H1_N1_IP6}/64 nodad
+	ip -netns $h1 li set eth0 master br0 up
+	ip -netns $h1 li set eth1 master br0 up
 
 	#
 	# h2
 	#
-	ip -netns h2 addr add dev eth0 ${H2_N2_IP}/24
-	ip -netns h2 ro add default via ${R2_N2_IP} dev eth0
-	ip -netns h2 -6 addr add dev eth0 ${H2_N2_IP6}/64 nodad
-	ip -netns h2 -6 ro add default via ${R2_N2_IP6} dev eth0
+	ip -netns $h2 addr add dev eth0 ${H2_N2_IP}/24
+	ip -netns $h2 ro add default via ${R2_N2_IP} dev eth0
+	ip -netns $h2 -6 addr add dev eth0 ${H2_N2_IP6}/64 nodad
+	ip -netns $h2 -6 ro add default via ${R2_N2_IP6} dev eth0
 
 	#
 	# r1
 	#
-	ip -netns r1 addr add dev eth0 ${R1_N1_IP}/24
-	ip -netns r1 -6 addr add dev eth0 ${R1_N1_IP6}/64 nodad
-	ip -netns r1 addr add dev eth1 ${R1_R2_N1_IP}/30
-	ip -netns r1 -6 addr add dev eth1 ${R1_R2_N1_IP6}/126 nodad
+	ip -netns $r1 addr add dev eth0 ${R1_N1_IP}/24
+	ip -netns $r1 -6 addr add dev eth0 ${R1_N1_IP6}/64 nodad
+	ip -netns $r1 addr add dev eth1 ${R1_R2_N1_IP}/30
+	ip -netns $r1 -6 addr add dev eth1 ${R1_R2_N1_IP6}/126 nodad
 
 	#
 	# r2
 	#
-	ip -netns r2 addr add dev eth0 ${R2_N1_IP}/24
-	ip -netns r2 -6 addr add dev eth0 ${R2_N1_IP6}/64 nodad
-	ip -netns r2 addr add dev eth1 ${R2_R1_N1_IP}/30
-	ip -netns r2 -6 addr add dev eth1 ${R2_R1_N1_IP6}/126 nodad
-	ip -netns r2 addr add dev eth2 ${R2_N2_IP}/24
-	ip -netns r2 -6 addr add dev eth2 ${R2_N2_IP6}/64 nodad
+	ip -netns $r2 addr add dev eth0 ${R2_N1_IP}/24
+	ip -netns $r2 -6 addr add dev eth0 ${R2_N1_IP6}/64 nodad
+	ip -netns $r2 addr add dev eth1 ${R2_R1_N1_IP}/30
+	ip -netns $r2 -6 addr add dev eth1 ${R2_R1_N1_IP6}/126 nodad
+	ip -netns $r2 addr add dev eth2 ${R2_N2_IP}/24
+	ip -netns $r2 -6 addr add dev eth2 ${R2_N2_IP6}/64 nodad
 
 	sleep 2
 
-	R1_LLADDR=$(get_linklocal r1 eth0)
+	R1_LLADDR=$(get_linklocal $r1 eth0)
 	if [ $? -ne 0 ]; then
 		echo "Error: Failed to get link-local address of r1's eth0"
 		exit 1
 	fi
 	log_debug "initial gateway is R1's lladdr = ${R1_LLADDR}"
 
-	R2_LLADDR=$(get_linklocal r2 eth0)
+	R2_LLADDR=$(get_linklocal $r2 eth0)
 	if [ $? -ne 0 ]; then
 		echo "Error: Failed to get link-local address of r2's eth0"
 		exit 1
@@ -278,8 +272,8 @@ change_h2_mtu()
 {
 	local mtu=$1
 
-	run_cmd ip -netns h2 li set eth0 mtu ${mtu}
-	run_cmd ip -netns r2 li set eth2 mtu ${mtu}
+	run_cmd ip -netns $h2 li set eth0 mtu ${mtu}
+	run_cmd ip -netns $r2 li set eth2 mtu ${mtu}
 }
 
 check_exception()
@@ -291,40 +285,40 @@ check_exception()
 	# From 172.16.1.101: icmp_seq=1 Redirect Host(New nexthop: 172.16.1.102)
 	if [ "$VERBOSE" = "1" ]; then
 		echo "Commands to check for exception:"
-		run_cmd ip -netns h1 ro get ${H1_VRF_ARG} ${H2_N2_IP}
-		run_cmd ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6}
+		run_cmd ip -netns $h1 ro get ${H1_VRF_ARG} ${H2_N2_IP}
+		run_cmd ip -netns $h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6}
 	fi
 
 	if [ -n "${mtu}" ]; then
 		mtu=" mtu ${mtu}"
 	fi
 	if [ "$with_redirect" = "yes" ]; then
-		ip -netns h1 ro get ${H1_VRF_ARG} ${H2_N2_IP} | \
+		ip -netns $h1 ro get ${H1_VRF_ARG} ${H2_N2_IP} | \
 		grep -q "cache <redirected> expires [0-9]*sec${mtu}"
 	elif [ -n "${mtu}" ]; then
-		ip -netns h1 ro get ${H1_VRF_ARG} ${H2_N2_IP} | \
+		ip -netns $h1 ro get ${H1_VRF_ARG} ${H2_N2_IP} | \
 		grep -q "cache expires [0-9]*sec${mtu}"
 	else
 		# want to verify that neither mtu nor redirected appears in
 		# the route get output. The -v will wipe out the cache line
 		# if either are set so the last grep -q will not find a match
-		ip -netns h1 ro get ${H1_VRF_ARG} ${H2_N2_IP} | \
+		ip -netns $h1 ro get ${H1_VRF_ARG} ${H2_N2_IP} | \
 		grep -E -v 'mtu|redirected' | grep -q "cache"
 	fi
 	log_test $? 0 "IPv4: ${desc}" 0
 
 	# No PMTU info for test "redirect" and "mtu exception plus redirect"
 	if [ "$with_redirect" = "yes" ] && [ "$desc" != "redirect exception plus mtu" ]; then
-		ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \
+		ip -netns $h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \
 		grep -v "mtu" | grep -q "${H2_N2_IP6} .*via ${R2_LLADDR} dev br0"
 	elif [ -n "${mtu}" ]; then
-		ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \
+		ip -netns $h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \
 		grep -q "${mtu}"
 	else
 		# IPv6 is a bit harder. First strip out the match if it
 		# contains an mtu exception and then look for the first
 		# gateway - R1's lladdr
-		ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \
+		ip -netns $h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \
 		grep -v "mtu" | grep -q "${R1_LLADDR}"
 	fi
 	log_test $? 0 "IPv6: ${desc}" 1
@@ -334,21 +328,21 @@ run_ping()
 {
 	local sz=$1
 
-	run_cmd ip netns exec h1 ping -q -M want -i 0.5 -c 10 -w 2 -s ${sz} ${H1_PING_ARG} ${H2_N2_IP}
-	run_cmd ip netns exec h1 ${ping6} -q -M want -i 0.5 -c 10 -w 2 -s ${sz} ${H1_PING_ARG} ${H2_N2_IP6}
+	run_cmd ip netns exec $h1 ping -q -M want -i 0.5 -c 10 -w 2 -s ${sz} ${H1_PING_ARG} ${H2_N2_IP}
+	run_cmd ip netns exec $h1 ${ping6} -q -M want -i 0.5 -c 10 -w 2 -s ${sz} ${H1_PING_ARG} ${H2_N2_IP6}
 }
 
 replace_route_new()
 {
 	# r1 to h2 via r2 and eth0
-	run_cmd ip -netns r1 nexthop replace id 1 via ${R2_N1_IP} dev eth0
-	run_cmd ip -netns r1 nexthop replace id 2 via ${R2_LLADDR} dev eth0
+	run_cmd ip -netns $r1 nexthop replace id 1 via ${R2_N1_IP} dev eth0
+	run_cmd ip -netns $r1 nexthop replace id 2 via ${R2_LLADDR} dev eth0
 }
 
 reset_route_new()
 {
-	run_cmd ip -netns r1 nexthop flush
-	run_cmd ip -netns h1 nexthop flush
+	run_cmd ip -netns $r1 nexthop flush
+	run_cmd ip -netns $h1 nexthop flush
 
 	initial_route_new
 }
@@ -356,34 +350,34 @@ reset_route_new()
 initial_route_new()
 {
 	# r1 to h2 via r2 and eth1
-	run_cmd ip -netns r1 nexthop add id 1 via ${R2_R1_N1_IP} dev eth1
-	run_cmd ip -netns r1 ro add ${H2_N2} nhid 1
+	run_cmd ip -netns $r1 nexthop add id 1 via ${R2_R1_N1_IP} dev eth1
+	run_cmd ip -netns $r1 ro add ${H2_N2} nhid 1
 
-	run_cmd ip -netns r1 nexthop add id 2 via ${R2_R1_N1_IP6} dev eth1
-	run_cmd ip -netns r1 -6 ro add ${H2_N2_6} nhid 2
+	run_cmd ip -netns $r1 nexthop add id 2 via ${R2_R1_N1_IP6} dev eth1
+	run_cmd ip -netns $r1 -6 ro add ${H2_N2_6} nhid 2
 
 	# h1 to h2 via r1
-	run_cmd ip -netns h1 nexthop add id 1 via ${R1_N1_IP} dev br0
-	run_cmd ip -netns h1 ro add ${H1_VRF_ARG} ${H2_N2} nhid 1
+	run_cmd ip -netns $h1 nexthop add id 1 via ${R1_N1_IP} dev br0
+	run_cmd ip -netns $h1 ro add ${H1_VRF_ARG} ${H2_N2} nhid 1
 
-	run_cmd ip -netns h1 nexthop add id 2 via ${R1_LLADDR} dev br0
-	run_cmd ip -netns h1 -6 ro add ${H1_VRF_ARG} ${H2_N2_6} nhid 2
+	run_cmd ip -netns $h1 nexthop add id 2 via ${R1_LLADDR} dev br0
+	run_cmd ip -netns $h1 -6 ro add ${H1_VRF_ARG} ${H2_N2_6} nhid 2
 }
 
 replace_route_legacy()
 {
 	# r1 to h2 via r2 and eth0
-	run_cmd ip -netns r1    ro replace ${H2_N2}   via ${R2_N1_IP}  dev eth0
-	run_cmd ip -netns r1 -6 ro replace ${H2_N2_6} via ${R2_LLADDR} dev eth0
+	run_cmd ip -netns $r1    ro replace ${H2_N2}   via ${R2_N1_IP}  dev eth0
+	run_cmd ip -netns $r1 -6 ro replace ${H2_N2_6} via ${R2_LLADDR} dev eth0
 }
 
 reset_route_legacy()
 {
-	run_cmd ip -netns r1    ro del ${H2_N2}
-	run_cmd ip -netns r1 -6 ro del ${H2_N2_6}
+	run_cmd ip -netns $r1    ro del ${H2_N2}
+	run_cmd ip -netns $r1 -6 ro del ${H2_N2_6}
 
-	run_cmd ip -netns h1    ro del ${H1_VRF_ARG} ${H2_N2}
-	run_cmd ip -netns h1 -6 ro del ${H1_VRF_ARG} ${H2_N2_6}
+	run_cmd ip -netns $h1    ro del ${H1_VRF_ARG} ${H2_N2}
+	run_cmd ip -netns $h1 -6 ro del ${H1_VRF_ARG} ${H2_N2_6}
 
 	initial_route_legacy
 }
@@ -391,22 +385,22 @@ reset_route_legacy()
 initial_route_legacy()
 {
 	# r1 to h2 via r2 and eth1
-	run_cmd ip -netns r1    ro add ${H2_N2}   via ${R2_R1_N1_IP}  dev eth1
-	run_cmd ip -netns r1 -6 ro add ${H2_N2_6} via ${R2_R1_N1_IP6} dev eth1
+	run_cmd ip -netns $r1    ro add ${H2_N2}   via ${R2_R1_N1_IP}  dev eth1
+	run_cmd ip -netns $r1 -6 ro add ${H2_N2_6} via ${R2_R1_N1_IP6} dev eth1
 
 	# h1 to h2 via r1
 	# - IPv6 redirect only works if gateway is the LLA
-	run_cmd ip -netns h1    ro add ${H1_VRF_ARG} ${H2_N2} via ${R1_N1_IP} dev br0
-	run_cmd ip -netns h1 -6 ro add ${H1_VRF_ARG} ${H2_N2_6} via ${R1_LLADDR} dev br0
+	run_cmd ip -netns $h1    ro add ${H1_VRF_ARG} ${H2_N2} via ${R1_N1_IP} dev br0
+	run_cmd ip -netns $h1 -6 ro add ${H1_VRF_ARG} ${H2_N2_6} via ${R1_LLADDR} dev br0
 }
 
 check_connectivity()
 {
 	local rc
 
-	run_cmd ip netns exec h1 ping -c1 -w1 ${H1_PING_ARG} ${H2_N2_IP}
+	run_cmd ip netns exec $h1 ping -c1 -w1 ${H1_PING_ARG} ${H2_N2_IP}
 	rc=$?
-	run_cmd ip netns exec h1 ${ping6} -c1 -w1 ${H1_PING_ARG} ${H2_N2_IP6}
+	run_cmd ip netns exec $h1 ${ping6} -c1 -w1 ${H1_PING_ARG} ${H2_N2_IP6}
 	[ $? -ne 0 ] && rc=$?
 
 	return $rc
diff --git a/tools/testing/selftests/net/io_uring_zerocopy_tx.sh b/tools/testing/selftests/net/io_uring_zerocopy_tx.sh
index 9ac4456d48fc..123439545013 100755
--- a/tools/testing/selftests/net/io_uring_zerocopy_tx.sh
+++ b/tools/testing/selftests/net/io_uring_zerocopy_tx.sh
@@ -76,23 +76,22 @@ case "${TXMODE}" in
 esac
 
 # Start of state changes: install cleanup handler
-save_sysctl_mem="$(sysctl -n ${path_sysctl_mem})"
 
 cleanup() {
 	ip netns del "${NS2}"
 	ip netns del "${NS1}"
-	sysctl -w -q "${path_sysctl_mem}=${save_sysctl_mem}"
 }
 
 trap cleanup EXIT
 
-# Configure system settings
-sysctl -w -q "${path_sysctl_mem}=1000000"
-
 # Create virtual ethernet pair between network namespaces
 ip netns add "${NS1}"
 ip netns add "${NS2}"
 
+# Configure system settings
+ip netns exec "${NS1}" sysctl -w -q "${path_sysctl_mem}=1000000"
+ip netns exec "${NS2}" sysctl -w -q "${path_sysctl_mem}=1000000"
+
 ip link add "${DEV}" mtu "${DEV_MTU}" netns "${NS1}" type veth \
   peer name "${DEV}" mtu "${DEV_MTU}" netns "${NS2}"
 
diff --git a/tools/testing/selftests/net/ioam6.sh b/tools/testing/selftests/net/ioam6.sh
index 4ceb401da1bf..fe59ca3e5596 100755
--- a/tools/testing/selftests/net/ioam6.sh
+++ b/tools/testing/selftests/net/ioam6.sh
@@ -117,8 +117,7 @@
 #        | Schema Data         |                                     |
 #        +-----------------------------------------------------------+
 
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
+source lib.sh
 
 ################################################################################
 #                                                                              #
@@ -195,32 +194,32 @@ TESTS_GLOBAL="
 
 check_kernel_compatibility()
 {
-  ip netns add ioam-tmp-node
-  ip link add name veth0 netns ioam-tmp-node type veth \
-         peer name veth1 netns ioam-tmp-node
+  setup_ns ioam_tmp_node
+  ip link add name veth0 netns $ioam_tmp_node type veth \
+         peer name veth1 netns $ioam_tmp_node
 
-  ip -netns ioam-tmp-node link set veth0 up
-  ip -netns ioam-tmp-node link set veth1 up
+  ip -netns $ioam_tmp_node link set veth0 up
+  ip -netns $ioam_tmp_node link set veth1 up
 
-  ip -netns ioam-tmp-node ioam namespace add 0
+  ip -netns $ioam_tmp_node ioam namespace add 0
   ns_ad=$?
 
-  ip -netns ioam-tmp-node ioam namespace show | grep -q "namespace 0"
+  ip -netns $ioam_tmp_node ioam namespace show | grep -q "namespace 0"
   ns_sh=$?
 
   if [[ $ns_ad != 0 || $ns_sh != 0 ]]
   then
     echo "SKIP: kernel version probably too old, missing ioam support"
     ip link del veth0 2>/dev/null || true
-    ip netns del ioam-tmp-node || true
+    cleanup_ns $ioam_tmp_node || true
     exit $ksft_skip
   fi
 
-  ip -netns ioam-tmp-node route add db02::/64 encap ioam6 mode inline \
+  ip -netns $ioam_tmp_node route add db02::/64 encap ioam6 mode inline \
          trace prealloc type 0x800000 ns 0 size 4 dev veth0
   tr_ad=$?
 
-  ip -netns ioam-tmp-node -6 route | grep -q "encap ioam6"
+  ip -netns $ioam_tmp_node -6 route | grep -q "encap ioam6"
   tr_sh=$?
 
   if [[ $tr_ad != 0 || $tr_sh != 0 ]]
@@ -228,12 +227,12 @@ check_kernel_compatibility()
     echo "SKIP: cannot attach an ioam trace to a route, did you compile" \
          "without CONFIG_IPV6_IOAM6_LWTUNNEL?"
     ip link del veth0 2>/dev/null || true
-    ip netns del ioam-tmp-node || true
+    cleanup_ns $ioam_tmp_node || true
     exit $ksft_skip
   fi
 
   ip link del veth0 2>/dev/null || true
-  ip netns del ioam-tmp-node || true
+  cleanup_ns $ioam_tmp_node || true
 
   lsmod | grep -q "ip6_tunnel"
   ip6tnl_loaded=$?
@@ -265,9 +264,7 @@ cleanup()
   ip link del ioam-veth-alpha 2>/dev/null || true
   ip link del ioam-veth-gamma 2>/dev/null || true
 
-  ip netns del ioam-node-alpha || true
-  ip netns del ioam-node-beta || true
-  ip netns del ioam-node-gamma || true
+  cleanup_ns $ioam_node_alpha $ioam_node_beta $ioam_node_gamma || true
 
   if [ $ip6tnl_loaded != 0 ]
   then
@@ -277,69 +274,67 @@ cleanup()
 
 setup()
 {
-  ip netns add ioam-node-alpha
-  ip netns add ioam-node-beta
-  ip netns add ioam-node-gamma
-
-  ip link add name ioam-veth-alpha netns ioam-node-alpha type veth \
-         peer name ioam-veth-betaL netns ioam-node-beta
-  ip link add name ioam-veth-betaR netns ioam-node-beta type veth \
-         peer name ioam-veth-gamma netns ioam-node-gamma
-
-  ip -netns ioam-node-alpha link set ioam-veth-alpha name veth0
-  ip -netns ioam-node-beta link set ioam-veth-betaL name veth0
-  ip -netns ioam-node-beta link set ioam-veth-betaR name veth1
-  ip -netns ioam-node-gamma link set ioam-veth-gamma name veth0
-
-  ip -netns ioam-node-alpha addr add db01::2/64 dev veth0
-  ip -netns ioam-node-alpha link set veth0 up
-  ip -netns ioam-node-alpha link set lo up
-  ip -netns ioam-node-alpha route add db02::/64 via db01::1 dev veth0
-  ip -netns ioam-node-alpha route del db01::/64
-  ip -netns ioam-node-alpha route add db01::/64 dev veth0
-
-  ip -netns ioam-node-beta addr add db01::1/64 dev veth0
-  ip -netns ioam-node-beta addr add db02::1/64 dev veth1
-  ip -netns ioam-node-beta link set veth0 up
-  ip -netns ioam-node-beta link set veth1 up
-  ip -netns ioam-node-beta link set lo up
-
-  ip -netns ioam-node-gamma addr add db02::2/64 dev veth0
-  ip -netns ioam-node-gamma link set veth0 up
-  ip -netns ioam-node-gamma link set lo up
-  ip -netns ioam-node-gamma route add db01::/64 via db02::1 dev veth0
+  setup_ns ioam_node_alpha ioam_node_beta ioam_node_gamma
+
+  ip link add name ioam-veth-alpha netns $ioam_node_alpha type veth \
+         peer name ioam-veth-betaL netns $ioam_node_beta
+  ip link add name ioam-veth-betaR netns $ioam_node_beta type veth \
+         peer name ioam-veth-gamma netns $ioam_node_gamma
+
+  ip -netns $ioam_node_alpha link set ioam-veth-alpha name veth0
+  ip -netns $ioam_node_beta link set ioam-veth-betaL name veth0
+  ip -netns $ioam_node_beta link set ioam-veth-betaR name veth1
+  ip -netns $ioam_node_gamma link set ioam-veth-gamma name veth0
+
+  ip -netns $ioam_node_alpha addr add db01::2/64 dev veth0
+  ip -netns $ioam_node_alpha link set veth0 up
+  ip -netns $ioam_node_alpha link set lo up
+  ip -netns $ioam_node_alpha route add db02::/64 via db01::1 dev veth0
+  ip -netns $ioam_node_alpha route del db01::/64
+  ip -netns $ioam_node_alpha route add db01::/64 dev veth0
+
+  ip -netns $ioam_node_beta addr add db01::1/64 dev veth0
+  ip -netns $ioam_node_beta addr add db02::1/64 dev veth1
+  ip -netns $ioam_node_beta link set veth0 up
+  ip -netns $ioam_node_beta link set veth1 up
+  ip -netns $ioam_node_beta link set lo up
+
+  ip -netns $ioam_node_gamma addr add db02::2/64 dev veth0
+  ip -netns $ioam_node_gamma link set veth0 up
+  ip -netns $ioam_node_gamma link set lo up
+  ip -netns $ioam_node_gamma route add db01::/64 via db02::1 dev veth0
 
   # - IOAM config -
-  ip netns exec ioam-node-alpha sysctl -wq net.ipv6.ioam6_id=${ALPHA[0]}
-  ip netns exec ioam-node-alpha sysctl -wq net.ipv6.ioam6_id_wide=${ALPHA[1]}
-  ip netns exec ioam-node-alpha sysctl -wq net.ipv6.conf.veth0.ioam6_id=${ALPHA[4]}
-  ip netns exec ioam-node-alpha sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${ALPHA[5]}
-  ip -netns ioam-node-alpha ioam namespace add 123 data ${ALPHA[6]} wide ${ALPHA[7]}
-  ip -netns ioam-node-alpha ioam schema add ${ALPHA[8]} "${ALPHA[9]}"
-  ip -netns ioam-node-alpha ioam namespace set 123 schema ${ALPHA[8]}
-
-  ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.all.forwarding=1
-  ip netns exec ioam-node-beta sysctl -wq net.ipv6.ioam6_id=${BETA[0]}
-  ip netns exec ioam-node-beta sysctl -wq net.ipv6.ioam6_id_wide=${BETA[1]}
-  ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1
-  ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth0.ioam6_id=${BETA[2]}
-  ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${BETA[3]}
-  ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth1.ioam6_id=${BETA[4]}
-  ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth1.ioam6_id_wide=${BETA[5]}
-  ip -netns ioam-node-beta ioam namespace add 123 data ${BETA[6]} wide ${BETA[7]}
-  ip -netns ioam-node-beta ioam schema add ${BETA[8]} "${BETA[9]}"
-  ip -netns ioam-node-beta ioam namespace set 123 schema ${BETA[8]}
-
-  ip netns exec ioam-node-gamma sysctl -wq net.ipv6.ioam6_id=${GAMMA[0]}
-  ip netns exec ioam-node-gamma sysctl -wq net.ipv6.ioam6_id_wide=${GAMMA[1]}
-  ip netns exec ioam-node-gamma sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1
-  ip netns exec ioam-node-gamma sysctl -wq net.ipv6.conf.veth0.ioam6_id=${GAMMA[2]}
-  ip netns exec ioam-node-gamma sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${GAMMA[3]}
-  ip -netns ioam-node-gamma ioam namespace add 123 data ${GAMMA[6]} wide ${GAMMA[7]}
+  ip netns exec $ioam_node_alpha sysctl -wq net.ipv6.ioam6_id=${ALPHA[0]}
+  ip netns exec $ioam_node_alpha sysctl -wq net.ipv6.ioam6_id_wide=${ALPHA[1]}
+  ip netns exec $ioam_node_alpha sysctl -wq net.ipv6.conf.veth0.ioam6_id=${ALPHA[4]}
+  ip netns exec $ioam_node_alpha sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${ALPHA[5]}
+  ip -netns $ioam_node_alpha ioam namespace add 123 data ${ALPHA[6]} wide ${ALPHA[7]}
+  ip -netns $ioam_node_alpha ioam schema add ${ALPHA[8]} "${ALPHA[9]}"
+  ip -netns $ioam_node_alpha ioam namespace set 123 schema ${ALPHA[8]}
+
+  ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.all.forwarding=1
+  ip netns exec $ioam_node_beta sysctl -wq net.ipv6.ioam6_id=${BETA[0]}
+  ip netns exec $ioam_node_beta sysctl -wq net.ipv6.ioam6_id_wide=${BETA[1]}
+  ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1
+  ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.veth0.ioam6_id=${BETA[2]}
+  ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${BETA[3]}
+  ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.veth1.ioam6_id=${BETA[4]}
+  ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.veth1.ioam6_id_wide=${BETA[5]}
+  ip -netns $ioam_node_beta ioam namespace add 123 data ${BETA[6]} wide ${BETA[7]}
+  ip -netns $ioam_node_beta ioam schema add ${BETA[8]} "${BETA[9]}"
+  ip -netns $ioam_node_beta ioam namespace set 123 schema ${BETA[8]}
+
+  ip netns exec $ioam_node_gamma sysctl -wq net.ipv6.ioam6_id=${GAMMA[0]}
+  ip netns exec $ioam_node_gamma sysctl -wq net.ipv6.ioam6_id_wide=${GAMMA[1]}
+  ip netns exec $ioam_node_gamma sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1
+  ip netns exec $ioam_node_gamma sysctl -wq net.ipv6.conf.veth0.ioam6_id=${GAMMA[2]}
+  ip netns exec $ioam_node_gamma sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${GAMMA[3]}
+  ip -netns $ioam_node_gamma ioam namespace add 123 data ${GAMMA[6]} wide ${GAMMA[7]}
 
   sleep 1
 
-  ip netns exec ioam-node-alpha ping6 -c 5 -W 1 db02::2 &>/dev/null
+  ip netns exec $ioam_node_alpha ping6 -c 5 -W 1 db02::2 &>/dev/null
   if [ $? != 0 ]
   then
     echo "Setup FAILED"
@@ -412,7 +407,7 @@ run()
   echo
 
   # set OUTPUT settings
-  ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=0
+  ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=0
 
   for t in $TESTS_OUTPUT
   do
@@ -421,8 +416,8 @@ run()
   done
 
   # clean OUTPUT settings
-  ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1
-  ip -netns ioam-node-alpha route change db01::/64 dev veth0
+  ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1
+  ip -netns $ioam_node_alpha route change db01::/64 dev veth0
 
 
   echo
@@ -433,7 +428,7 @@ run()
   echo
 
   # set INPUT settings
-  ip -netns ioam-node-alpha ioam namespace del 123
+  ip -netns $ioam_node_alpha ioam namespace del 123
 
   for t in $TESTS_INPUT
   do
@@ -442,10 +437,10 @@ run()
   done
 
   # clean INPUT settings
-  ip -netns ioam-node-alpha ioam namespace add 123 \
+  ip -netns $ioam_node_alpha ioam namespace add 123 \
          data ${ALPHA[6]} wide ${ALPHA[7]}
-  ip -netns ioam-node-alpha ioam namespace set 123 schema ${ALPHA[8]}
-  ip -netns ioam-node-alpha route change db01::/64 dev veth0
+  ip -netns $ioam_node_alpha ioam namespace set 123 schema ${ALPHA[8]}
+  ip -netns $ioam_node_alpha route change db01::/64 dev veth0
 
   echo
   printf "%0.s-" {1..74}
@@ -488,15 +483,15 @@ out_undef_ns()
   local desc="Unknown IOAM namespace"
 
   [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
-  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up
+  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up
 
-  ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \
+  ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \
          trace prealloc type 0x800000 ns 0 size 4 dev veth0
 
-  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \
+  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
          db01::2 db01::1 veth0 0x800000 0
 
-  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down
+  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
 
 out_no_room()
@@ -508,15 +503,15 @@ out_no_room()
   local desc="Missing trace room"
 
   [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
-  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up
+  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up
 
-  ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \
+  ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \
          trace prealloc type 0xc00000 ns 123 size 4 dev veth0
 
-  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \
+  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
          db01::2 db01::1 veth0 0xc00000 123
 
-  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down
+  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
 
 out_bits()
@@ -532,11 +527,11 @@ out_bits()
   bit2size[22]=$(( $tmp + ${#ALPHA[9]} + ((4 - (${#ALPHA[9]} % 4)) % 4) ))
 
   [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
-  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up
+  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up
 
   for i in {0..22}
   do
-    ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \
+    ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \
            trace prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} \
            dev veth0 &>/dev/null
 
@@ -554,12 +549,12 @@ out_bits()
         log_test_failed "$descr"
       fi
     else
-	run_test "out_bit$i" "$descr ($1 mode)" ioam-node-alpha \
-           ioam-node-beta db01::2 db01::1 veth0 ${bit2type[$i]} 123
+	run_test "out_bit$i" "$descr ($1 mode)" $ioam_node_alpha \
+           $ioam_node_beta db01::2 db01::1 veth0 ${bit2type[$i]} 123
     fi
   done
 
-  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down
+  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 
   bit2size[22]=$tmp
 }
@@ -573,15 +568,15 @@ out_full_supp_trace()
   local desc="Full supported trace"
 
   [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
-  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up
+  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up
 
-  ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \
+  ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \
          trace prealloc type 0xfff002 ns 123 size 100 dev veth0
 
-  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \
+  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
          db01::2 db01::1 veth0 0xfff002 123
 
-  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down
+  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
 
 
@@ -603,15 +598,15 @@ in_undef_ns()
   local desc="Unknown IOAM namespace"
 
   [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
-  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up
+  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up
 
-  ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \
+  ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \
          trace prealloc type 0x800000 ns 0 size 4 dev veth0
 
-  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \
+  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
          db01::2 db01::1 veth0 0x800000 0
 
-  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down
+  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
 
 in_no_room()
@@ -623,15 +618,15 @@ in_no_room()
   local desc="Missing trace room"
 
   [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
-  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up
+  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up
 
-  ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \
+  ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \
          trace prealloc type 0xc00000 ns 123 size 4 dev veth0
 
-  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \
+  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
          db01::2 db01::1 veth0 0xc00000 123
 
-  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down
+  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
 
 in_bits()
@@ -647,19 +642,19 @@ in_bits()
   bit2size[22]=$(( $tmp + ${#BETA[9]} + ((4 - (${#BETA[9]} % 4)) % 4) ))
 
   [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
-  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up
+  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up
 
   for i in {0..11} {22..22}
   do
-    ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \
+    ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \
            trace prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} \
            dev veth0
 
-    run_test "in_bit$i" "${desc/<n>/$i} ($1 mode)" ioam-node-alpha \
-           ioam-node-beta db01::2 db01::1 veth0 ${bit2type[$i]} 123
+    run_test "in_bit$i" "${desc/<n>/$i} ($1 mode)" $ioam_node_alpha \
+           $ioam_node_beta db01::2 db01::1 veth0 ${bit2type[$i]} 123
   done
 
-  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down
+  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 
   bit2size[22]=$tmp
 }
@@ -675,22 +670,22 @@ in_oflag()
   # Exception:
   #   Here, we need the sender to set the Overflow flag. For that, we will add
   #   back the IOAM namespace that was previously configured on the sender.
-  ip -netns ioam-node-alpha ioam namespace add 123
+  ip -netns $ioam_node_alpha ioam namespace add 123
 
   [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
-  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up
+  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up
 
-  ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \
+  ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \
          trace prealloc type 0xc00000 ns 123 size 4 dev veth0
 
-  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \
+  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
          db01::2 db01::1 veth0 0xc00000 123
 
-  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down
+  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 
   # And we clean the exception for this test to get things back to normal for
   # other INPUT tests
-  ip -netns ioam-node-alpha ioam namespace del 123
+  ip -netns $ioam_node_alpha ioam namespace del 123
 }
 
 in_full_supp_trace()
@@ -702,15 +697,15 @@ in_full_supp_trace()
   local desc="Full supported trace"
 
   [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
-  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up
+  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up
 
-  ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \
+  ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \
          trace prealloc type 0xfff002 ns 123 size 80 dev veth0
 
-  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \
+  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
          db01::2 db01::1 veth0 0xfff002 123
 
-  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down
+  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
 
 
@@ -730,15 +725,15 @@ fwd_full_supp_trace()
   local desc="Forward - Full supported trace"
 
   [ "$1" = "encap" ] && mode="$1 tundst db02::2" || mode="$1"
-  [ "$1" = "encap" ] && ip -netns ioam-node-gamma link set ip6tnl0 up
+  [ "$1" = "encap" ] && ip -netns $ioam_node_gamma link set ip6tnl0 up
 
-  ip -netns ioam-node-alpha route change db02::/64 encap ioam6 mode $mode \
+  ip -netns $ioam_node_alpha route change db02::/64 encap ioam6 mode $mode \
          trace prealloc type 0xfff002 ns 123 size 244 via db01::1 dev veth0
 
-  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-gamma \
+  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_gamma \
          db01::2 db02::2 veth0 0xfff002 123
 
-  [ "$1" = "encap" ] && ip -netns ioam-node-gamma link set ip6tnl0 down
+  [ "$1" = "encap" ] && ip -netns $ioam_node_gamma link set ip6tnl0 down
 }
 
 
diff --git a/tools/testing/selftests/net/ip_local_port_range.c b/tools/testing/selftests/net/ip_local_port_range.c
index 75e3fdacdf73..0f217a1cc837 100644
--- a/tools/testing/selftests/net/ip_local_port_range.c
+++ b/tools/testing/selftests/net/ip_local_port_range.c
@@ -146,6 +146,12 @@ FIXTURE_VARIANT_ADD(ip_local_port_range, ip4_stcp) {
 	.so_protocol	= IPPROTO_SCTP,
 };
 
+FIXTURE_VARIANT_ADD(ip_local_port_range, ip4_mptcp) {
+	.so_domain	= AF_INET,
+	.so_type	= SOCK_STREAM,
+	.so_protocol	= IPPROTO_MPTCP,
+};
+
 FIXTURE_VARIANT_ADD(ip_local_port_range, ip6_tcp) {
 	.so_domain	= AF_INET6,
 	.so_type	= SOCK_STREAM,
@@ -164,6 +170,12 @@ FIXTURE_VARIANT_ADD(ip_local_port_range, ip6_stcp) {
 	.so_protocol	= IPPROTO_SCTP,
 };
 
+FIXTURE_VARIANT_ADD(ip_local_port_range, ip6_mptcp) {
+	.so_domain	= AF_INET6,
+	.so_type	= SOCK_STREAM,
+	.so_protocol	= IPPROTO_MPTCP,
+};
+
 TEST_F(ip_local_port_range, invalid_option_value)
 {
 	__u16 val16;
diff --git a/tools/testing/selftests/net/ipsec.c b/tools/testing/selftests/net/ipsec.c
index 9a8229abfa02..be4a30a0d02a 100644
--- a/tools/testing/selftests/net/ipsec.c
+++ b/tools/testing/selftests/net/ipsec.c
@@ -2263,7 +2263,7 @@ static int check_results(void)
 
 int main(int argc, char **argv)
 {
-	unsigned int nr_process = 1;
+	long nr_process = 1;
 	int route_sock = -1, ret = KSFT_SKIP;
 	int test_desc_fd[2];
 	uint32_t route_seq;
@@ -2284,7 +2284,7 @@ int main(int argc, char **argv)
 			exit_usage(argv);
 		}
 
-		if (nr_process > MAX_PROCESSES || !nr_process) {
+		if (nr_process > MAX_PROCESSES || nr_process < 1) {
 			printk("nr_process should be between [1; %u]",
 					MAX_PROCESSES);
 			exit_usage(argv);
diff --git a/tools/testing/selftests/net/l2tp.sh b/tools/testing/selftests/net/l2tp.sh
index 5782433886fc..88de7166c8ae 100755
--- a/tools/testing/selftests/net/l2tp.sh
+++ b/tools/testing/selftests/net/l2tp.sh
@@ -13,6 +13,7 @@
 #                10.1.1.1    |            |   10.1.2.1
 #              2001:db8:1::1 |            | 2001:db8:2::1
 
+source lib.sh
 VERBOSE=0
 PAUSE_ON_FAIL=no
 
@@ -80,9 +81,6 @@ create_ns()
 	[ -z "${addr}" ] && addr="-"
 	[ -z "${addr6}" ] && addr6="-"
 
-	ip netns add ${ns}
-
-	ip -netns ${ns} link set lo up
 	if [ "${addr}" != "-" ]; then
 		ip -netns ${ns} addr add dev lo ${addr}
 	fi
@@ -133,12 +131,7 @@ connect_ns()
 
 cleanup()
 {
-	local ns
-
-	for ns in host-1 host-2 router
-	do
-		ip netns del ${ns} 2>/dev/null
-	done
+	cleanup_ns $host_1 $host_2 $router
 }
 
 setup_l2tp_ipv4()
@@ -146,28 +139,28 @@ setup_l2tp_ipv4()
 	#
 	# configure l2tpv3 tunnel on host-1
 	#
-	ip -netns host-1 l2tp add tunnel tunnel_id 1041 peer_tunnel_id 1042 \
+	ip -netns $host_1 l2tp add tunnel tunnel_id 1041 peer_tunnel_id 1042 \
 			 encap ip local 10.1.1.1 remote 10.1.2.1
-	ip -netns host-1 l2tp add session name l2tp4 tunnel_id 1041 \
+	ip -netns $host_1 l2tp add session name l2tp4 tunnel_id 1041 \
 			 session_id 1041 peer_session_id 1042
-	ip -netns host-1 link set dev l2tp4 up
-	ip -netns host-1 addr add dev l2tp4 172.16.1.1 peer 172.16.1.2
+	ip -netns $host_1 link set dev l2tp4 up
+	ip -netns $host_1 addr add dev l2tp4 172.16.1.1 peer 172.16.1.2
 
 	#
 	# configure l2tpv3 tunnel on host-2
 	#
-	ip -netns host-2 l2tp add tunnel tunnel_id 1042 peer_tunnel_id 1041 \
+	ip -netns $host_2 l2tp add tunnel tunnel_id 1042 peer_tunnel_id 1041 \
 			 encap ip local 10.1.2.1 remote 10.1.1.1
-	ip -netns host-2 l2tp add session name l2tp4 tunnel_id 1042 \
+	ip -netns $host_2 l2tp add session name l2tp4 tunnel_id 1042 \
 			 session_id 1042 peer_session_id 1041
-	ip -netns host-2 link set dev l2tp4 up
-	ip -netns host-2 addr add dev l2tp4 172.16.1.2 peer 172.16.1.1
+	ip -netns $host_2 link set dev l2tp4 up
+	ip -netns $host_2 addr add dev l2tp4 172.16.1.2 peer 172.16.1.1
 
 	#
 	# add routes to loopback addresses
 	#
-	ip -netns host-1 ro add 172.16.101.2/32 via 172.16.1.2
-	ip -netns host-2 ro add 172.16.101.1/32 via 172.16.1.1
+	ip -netns $host_1 ro add 172.16.101.2/32 via 172.16.1.2
+	ip -netns $host_2 ro add 172.16.101.1/32 via 172.16.1.1
 }
 
 setup_l2tp_ipv6()
@@ -175,28 +168,28 @@ setup_l2tp_ipv6()
 	#
 	# configure l2tpv3 tunnel on host-1
 	#
-	ip -netns host-1 l2tp add tunnel tunnel_id 1061 peer_tunnel_id 1062 \
+	ip -netns $host_1 l2tp add tunnel tunnel_id 1061 peer_tunnel_id 1062 \
 			 encap ip local 2001:db8:1::1 remote 2001:db8:2::1
-	ip -netns host-1 l2tp add session name l2tp6 tunnel_id 1061 \
+	ip -netns $host_1 l2tp add session name l2tp6 tunnel_id 1061 \
 			 session_id 1061 peer_session_id 1062
-	ip -netns host-1 link set dev l2tp6 up
-	ip -netns host-1 addr add dev l2tp6 fc00:1::1 peer fc00:1::2
+	ip -netns $host_1 link set dev l2tp6 up
+	ip -netns $host_1 addr add dev l2tp6 fc00:1::1 peer fc00:1::2
 
 	#
 	# configure l2tpv3 tunnel on host-2
 	#
-	ip -netns host-2 l2tp add tunnel tunnel_id 1062 peer_tunnel_id 1061 \
+	ip -netns $host_2 l2tp add tunnel tunnel_id 1062 peer_tunnel_id 1061 \
 			 encap ip local 2001:db8:2::1 remote 2001:db8:1::1
-	ip -netns host-2 l2tp add session name l2tp6 tunnel_id 1062 \
+	ip -netns $host_2 l2tp add session name l2tp6 tunnel_id 1062 \
 			 session_id 1062 peer_session_id 1061
-	ip -netns host-2 link set dev l2tp6 up
-	ip -netns host-2 addr add dev l2tp6 fc00:1::2 peer fc00:1::1
+	ip -netns $host_2 link set dev l2tp6 up
+	ip -netns $host_2 addr add dev l2tp6 fc00:1::2 peer fc00:1::1
 
 	#
 	# add routes to loopback addresses
 	#
-	ip -netns host-1 -6 ro add fc00:101::2/128 via fc00:1::2
-	ip -netns host-2 -6 ro add fc00:101::1/128 via fc00:1::1
+	ip -netns $host_1 -6 ro add fc00:101::2/128 via fc00:1::2
+	ip -netns $host_2 -6 ro add fc00:101::1/128 via fc00:1::1
 }
 
 setup()
@@ -205,21 +198,22 @@ setup()
 	cleanup
 
 	set -e
-	create_ns host-1 172.16.101.1/32 fc00:101::1/128
-	create_ns host-2 172.16.101.2/32 fc00:101::2/128
-	create_ns router
+	setup_ns host_1 host_2 router
+	create_ns $host_1 172.16.101.1/32 fc00:101::1/128
+	create_ns $host_2 172.16.101.2/32 fc00:101::2/128
+	create_ns $router
 
-	connect_ns host-1 eth0 10.1.1.1/24 2001:db8:1::1/64 \
-	           router eth1 10.1.1.2/24 2001:db8:1::2/64
+	connect_ns $host_1 eth0 10.1.1.1/24 2001:db8:1::1/64 \
+	           $router eth1 10.1.1.2/24 2001:db8:1::2/64
 
-	connect_ns host-2 eth0 10.1.2.1/24 2001:db8:2::1/64 \
-	           router eth2 10.1.2.2/24 2001:db8:2::2/64
+	connect_ns $host_2 eth0 10.1.2.1/24 2001:db8:2::1/64 \
+	           $router eth2 10.1.2.2/24 2001:db8:2::2/64
 
-	ip -netns host-1 ro add 10.1.2.0/24 via 10.1.1.2
-	ip -netns host-1 -6 ro add 2001:db8:2::/64 via 2001:db8:1::2
+	ip -netns $host_1 ro add 10.1.2.0/24 via 10.1.1.2
+	ip -netns $host_1 -6 ro add 2001:db8:2::/64 via 2001:db8:1::2
 
-	ip -netns host-2 ro add 10.1.1.0/24 via 10.1.2.2
-	ip -netns host-2 -6 ro add 2001:db8:1::/64 via 2001:db8:2::2
+	ip -netns $host_2 ro add 10.1.1.0/24 via 10.1.2.2
+	ip -netns $host_2 -6 ro add 2001:db8:1::/64 via 2001:db8:2::2
 
 	setup_l2tp_ipv4
 	setup_l2tp_ipv6
@@ -231,38 +225,38 @@ setup_ipsec()
 	#
 	# IPv4
 	#
-	run_cmd host-1 ip xfrm policy add \
+	run_cmd $host_1 ip xfrm policy add \
 		src 10.1.1.1 dst 10.1.2.1 dir out \
 		tmpl proto esp mode transport
 
-	run_cmd host-1 ip xfrm policy add \
+	run_cmd $host_1 ip xfrm policy add \
 		src 10.1.2.1 dst 10.1.1.1 dir in \
 		tmpl proto esp mode transport
 
-	run_cmd host-2 ip xfrm policy add \
+	run_cmd $host_2 ip xfrm policy add \
 		src 10.1.1.1 dst 10.1.2.1 dir in \
 		tmpl proto esp mode transport
 
-	run_cmd host-2 ip xfrm policy add \
+	run_cmd $host_2 ip xfrm policy add \
 		src 10.1.2.1 dst 10.1.1.1 dir out \
 		tmpl proto esp mode transport
 
-	ip -netns host-1 xfrm state add \
+	ip -netns $host_1 xfrm state add \
 		src 10.1.1.1 dst 10.1.2.1 \
 		spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' \
 		0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport
 
-	ip -netns host-1 xfrm state add \
+	ip -netns $host_1 xfrm state add \
 		src 10.1.2.1 dst 10.1.1.1 \
 		spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' \
 		0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport
 
-	ip -netns host-2 xfrm state add \
+	ip -netns $host_2 xfrm state add \
 		src 10.1.1.1 dst 10.1.2.1 \
 		spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' \
 		0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport
 
-	ip -netns host-2 xfrm state add \
+	ip -netns $host_2 xfrm state add \
 		src 10.1.2.1 dst 10.1.1.1 \
 		spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' \
 		0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport
@@ -270,38 +264,38 @@ setup_ipsec()
 	#
 	# IPV6
 	#
-	run_cmd host-1 ip -6 xfrm policy add \
+	run_cmd $host_1 ip -6 xfrm policy add \
 		src 2001:db8:1::1 dst 2001:db8:2::1 dir out \
 		tmpl proto esp mode transport
 
-	run_cmd host-1 ip -6 xfrm policy add \
+	run_cmd $host_1 ip -6 xfrm policy add \
 		src 2001:db8:2::1 dst 2001:db8:1::1 dir in \
 		tmpl proto esp mode transport
 
-	run_cmd host-2 ip -6 xfrm policy add \
+	run_cmd $host_2 ip -6 xfrm policy add \
 		src 2001:db8:1::1 dst 2001:db8:2::1 dir in \
 		tmpl proto esp mode transport
 
-	run_cmd host-2 ip -6 xfrm policy add \
+	run_cmd $host_2 ip -6 xfrm policy add \
 		src 2001:db8:2::1 dst 2001:db8:1::1 dir out \
 		tmpl proto esp mode transport
 
-	ip -netns host-1 -6 xfrm state add \
+	ip -netns $host_1 -6 xfrm state add \
 		src 2001:db8:1::1 dst 2001:db8:2::1 \
 		spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' \
 		0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport
 
-	ip -netns host-1 -6 xfrm state add \
+	ip -netns $host_1 -6 xfrm state add \
 		src 2001:db8:2::1 dst 2001:db8:1::1 \
 		spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' \
 		0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport
 
-	ip -netns host-2 -6 xfrm state add \
+	ip -netns $host_2 -6 xfrm state add \
 		src 2001:db8:1::1 dst 2001:db8:2::1 \
 		spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' \
 		0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport
 
-	ip -netns host-2 -6 xfrm state add \
+	ip -netns $host_2 -6 xfrm state add \
 		src 2001:db8:2::1 dst 2001:db8:1::1 \
 		spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' \
 		0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport
@@ -309,10 +303,10 @@ setup_ipsec()
 
 teardown_ipsec()
 {
-	run_cmd host-1 ip xfrm state flush
-	run_cmd host-1 ip xfrm policy flush
-	run_cmd host-2 ip xfrm state flush
-	run_cmd host-2 ip xfrm policy flush
+	run_cmd $host_1 ip xfrm state flush
+	run_cmd $host_1 ip xfrm policy flush
+	run_cmd $host_2 ip xfrm state flush
+	run_cmd $host_2 ip xfrm policy flush
 }
 
 ################################################################################
@@ -322,16 +316,16 @@ run_ping()
 {
 	local desc="$1"
 
-	run_cmd host-1 ping -c1 -w1 172.16.1.2
+	run_cmd $host_1 ping -c1 -w1 172.16.1.2
 	log_test $? 0 "IPv4 basic L2TP tunnel ${desc}"
 
-	run_cmd host-1 ping -c1 -w1 -I 172.16.101.1 172.16.101.2
+	run_cmd $host_1 ping -c1 -w1 -I 172.16.101.1 172.16.101.2
 	log_test $? 0 "IPv4 route through L2TP tunnel ${desc}"
 
-	run_cmd host-1 ${ping6} -c1 -w1 fc00:1::2
+	run_cmd $host_1 ${ping6} -c1 -w1 fc00:1::2
 	log_test $? 0 "IPv6 basic L2TP tunnel ${desc}"
 
-	run_cmd host-1 ${ping6} -c1 -w1 -I fc00:101::1 fc00:101::2
+	run_cmd $host_1 ${ping6} -c1 -w1 -I fc00:101::1 fc00:101::2
 	log_test $? 0 "IPv6 route through L2TP tunnel ${desc}"
 }
 
@@ -344,16 +338,16 @@ run_tests()
 
 	setup_ipsec
 	run_ping "- with IPsec"
-	run_cmd host-1 ping -c1 -w1 172.16.1.2
+	run_cmd $host_1 ping -c1 -w1 172.16.1.2
 	log_test $? 0 "IPv4 basic L2TP tunnel ${desc}"
 
-	run_cmd host-1 ping -c1 -w1 -I 172.16.101.1 172.16.101.2
+	run_cmd $host_1 ping -c1 -w1 -I 172.16.101.1 172.16.101.2
 	log_test $? 0 "IPv4 route through L2TP tunnel ${desc}"
 
-	run_cmd host-1 ${ping6} -c1 -w1 fc00:1::2
+	run_cmd $host_1 ${ping6} -c1 -w1 fc00:1::2
 	log_test $? 0 "IPv6 basic L2TP tunnel - with IPsec"
 
-	run_cmd host-1 ${ping6} -c1 -w1 -I fc00:101::1 fc00:101::2
+	run_cmd $host_1 ${ping6} -c1 -w1 -I fc00:101::1 fc00:101::2
 	log_test $? 0 "IPv6 route through L2TP tunnel - with IPsec"
 
 	teardown_ipsec
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
new file mode 100644
index 000000000000..dca549443801
--- /dev/null
+++ b/tools/testing/selftests/net/lib.sh
@@ -0,0 +1,93 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+##############################################################################
+# Defines
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+# namespace list created by setup_ns
+NS_LIST=""
+
+##############################################################################
+# Helpers
+busywait()
+{
+	local timeout=$1; shift
+
+	local start_time="$(date -u +%s%3N)"
+	while true
+	do
+		local out
+		out=$("$@")
+		local ret=$?
+		if ((!ret)); then
+			echo -n "$out"
+			return 0
+		fi
+
+		local current_time="$(date -u +%s%3N)"
+		if ((current_time - start_time > timeout)); then
+			echo -n "$out"
+			return 1
+		fi
+	done
+}
+
+cleanup_ns()
+{
+	local ns=""
+	local errexit=0
+	local ret=0
+
+	# disable errexit temporary
+	if [[ $- =~ "e" ]]; then
+		errexit=1
+		set +e
+	fi
+
+	for ns in "$@"; do
+		ip netns delete "${ns}" &> /dev/null
+		if ! busywait 2 ip netns list \| grep -vq "^$ns$" &> /dev/null; then
+			echo "Warn: Failed to remove namespace $ns"
+			ret=1
+		fi
+	done
+
+	[ $errexit -eq 1 ] && set -e
+	return $ret
+}
+
+cleanup_all_ns()
+{
+	cleanup_ns $NS_LIST
+}
+
+# setup netns with given names as prefix. e.g
+# setup_ns local remote
+setup_ns()
+{
+	local ns=""
+	local ns_name=""
+	local ns_list=""
+	for ns_name in "$@"; do
+		# Some test may setup/remove same netns multi times
+		if unset ${ns_name} 2> /dev/null; then
+			ns="${ns_name,,}-$(mktemp -u XXXXXX)"
+			eval readonly ${ns_name}="$ns"
+		else
+			eval ns='$'${ns_name}
+			cleanup_ns "$ns"
+
+		fi
+
+		if ! ip netns add "$ns"; then
+			echo "Failed to create namespace $ns_name"
+			cleanup_ns "$ns_list"
+			return $ksft_skip
+		fi
+		ip -n "$ns" link set lo up
+		ns_list="$ns_list $ns"
+	done
+	NS_LIST="$NS_LIST $ns_list"
+}
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 85a8ee9395b3..04fcb8a077c9 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -56,7 +56,7 @@ __chk_nr()
 	local command="$1"
 	local expected=$2
 	local msg="$3"
-	local skip="${4:-SKIP}"
+	local skip="${4-SKIP}"
 	local nr
 
 	nr=$(eval $command)
@@ -182,21 +182,13 @@ chk_msk_inuse()
 	__chk_nr get_msk_inuse $expected "$msg" 0
 }
 
-# $1: ns, $2: port
-wait_local_port_listen()
+# $1: cestab nr
+chk_msk_cestab()
 {
-	local listener_ns="${1}"
-	local port="${2}"
+	local cestab=$1
 
-	local port_hex i
-
-	port_hex="$(printf "%04X" "${port}")"
-	for i in $(seq 10); do
-		ip netns exec "${listener_ns}" cat /proc/net/tcp | \
-			awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" &&
-			break
-		sleep 0.1
-	done
+	__chk_nr "mptcp_lib_get_counter ${ns} MPTcpExtMPCurrEstab" \
+		 "${cestab}" "....chk ${cestab} cestab" ""
 }
 
 wait_connected()
@@ -222,7 +214,7 @@ echo "a" | \
 		ip netns exec $ns \
 			./mptcp_connect -p 10000 -l -t ${timeout_poll} -w 20 \
 				0.0.0.0 >/dev/null &
-wait_local_port_listen $ns 10000
+mptcp_lib_wait_local_port_listen $ns 10000
 chk_msk_nr 0 "no msk on netns creation"
 chk_msk_listen 10000
 
@@ -236,16 +228,18 @@ chk_msk_nr 2 "after MPC handshake "
 chk_msk_remote_key_nr 2 "....chk remote_key"
 chk_msk_fallback_nr 0 "....chk no fallback"
 chk_msk_inuse 2 "....chk 2 msk in use"
+chk_msk_cestab 2
 flush_pids
 
 chk_msk_inuse 0 "....chk 0 msk in use after flush"
+chk_msk_cestab 0
 
 echo "a" | \
 	timeout ${timeout_test} \
 		ip netns exec $ns \
 			./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} -w 20 \
 				0.0.0.0 >/dev/null &
-wait_local_port_listen $ns 10001
+mptcp_lib_wait_local_port_listen $ns 10001
 echo "b" | \
 	timeout ${timeout_test} \
 		ip netns exec $ns \
@@ -254,9 +248,11 @@ echo "b" | \
 wait_connected $ns 10001
 chk_msk_fallback_nr 1 "check fallback"
 chk_msk_inuse 1 "....chk 1 msk in use"
+chk_msk_cestab 1
 flush_pids
 
 chk_msk_inuse 0 "....chk 0 msk in use after flush"
+chk_msk_cestab 0
 
 NR_CLIENTS=100
 for I in `seq 1 $NR_CLIENTS`; do
@@ -266,7 +262,7 @@ for I in `seq 1 $NR_CLIENTS`; do
 				./mptcp_connect -p $((I+10001)) -l -w 20 \
 					-t ${timeout_poll} 0.0.0.0 >/dev/null &
 done
-wait_local_port_listen $ns $((NR_CLIENTS + 10001))
+mptcp_lib_wait_local_port_listen $ns $((NR_CLIENTS + 10001))
 
 for I in `seq 1 $NR_CLIENTS`; do
 	echo "b" | \
@@ -278,9 +274,11 @@ done
 
 wait_msk_nr $((NR_CLIENTS*2)) "many msk socket present"
 chk_msk_inuse $((NR_CLIENTS*2)) "....chk many msk in use"
+chk_msk_cestab $((NR_CLIENTS*2))
 flush_pids
 
 chk_msk_inuse 0 "....chk 0 msk in use after flush"
+chk_msk_cestab 0
 
 mptcp_lib_result_print_all_tap
 exit $ret
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index c7f9ebeebc2c..d2043ec3bf6d 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -18,6 +18,7 @@
 
 #include <sys/ioctl.h>
 #include <sys/poll.h>
+#include <sys/random.h>
 #include <sys/sendfile.h>
 #include <sys/stat.h>
 #include <sys/socket.h>
@@ -1125,15 +1126,11 @@ again:
 
 static void init_rng(void)
 {
-	int fd = open("/dev/urandom", O_RDONLY);
 	unsigned int foo;
 
-	if (fd > 0) {
-		int ret = read(fd, &foo, sizeof(foo));
-
-		if (ret < 0)
-			srand(fd + foo);
-		close(fd);
+	if (getrandom(&foo, sizeof(foo), 0) == -1) {
+		perror("getrandom");
+		exit(1);
 	}
 
 	srand(foo);
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index b1fc8afd072d..7898d62fce0b 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -254,31 +254,6 @@ else
 	set_ethtool_flags "$ns4" ns4eth3 "$ethtool_args"
 fi
 
-print_file_err()
-{
-	ls -l "$1" 1>&2
-	echo "Trailing bytes are: "
-	tail -c 27 "$1"
-}
-
-check_transfer()
-{
-	local in=$1
-	local out=$2
-	local what=$3
-
-	cmp "$in" "$out" > /dev/null 2>&1
-	if [ $? -ne 0 ] ;then
-		echo "[ FAIL ] $what does not match (in, out):"
-		print_file_err "$in"
-		print_file_err "$out"
-
-		return 1
-	fi
-
-	return 0
-}
-
 check_mptcp_disabled()
 {
 	local disabled_ns="ns_disabled-$rndh"
@@ -310,12 +285,6 @@ check_mptcp_disabled()
 	return 0
 }
 
-# $1: IP address
-is_v6()
-{
-	[ -z "${1##*:*}" ]
-}
-
 do_ping()
 {
 	local listener_ns="$1"
@@ -324,7 +293,7 @@ do_ping()
 	local ping_args="-q -c 1"
 	local rc=0
 
-	if is_v6 "${connect_addr}"; then
+	if mptcp_lib_is_v6 "${connect_addr}"; then
 		$ipv6 || return 0
 		ping_args="${ping_args} -6"
 	fi
@@ -341,38 +310,6 @@ do_ping()
 	return 0
 }
 
-# $1: ns, $2: MIB counter
-get_mib_counter()
-{
-	local listener_ns="${1}"
-	local mib="${2}"
-
-	# strip the header
-	ip netns exec "${listener_ns}" \
-		nstat -z -a "${mib}" | \
-			tail -n+2 | \
-			while read a count c rest; do
-				echo $count
-			done
-}
-
-# $1: ns, $2: port
-wait_local_port_listen()
-{
-	local listener_ns="${1}"
-	local port="${2}"
-
-	local port_hex i
-
-	port_hex="$(printf "%04X" "${port}")"
-	for i in $(seq 10); do
-		ip netns exec "${listener_ns}" cat /proc/net/tcp* | \
-			awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" &&
-			break
-		sleep 0.1
-	done
-}
-
 do_transfer()
 {
 	local listener_ns="$1"
@@ -441,12 +378,12 @@ do_transfer()
 			nstat -n
 	fi
 
-	local stat_synrx_last_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX")
-	local stat_ackrx_last_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
-	local stat_cookietx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent")
-	local stat_cookierx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv")
-	local stat_csum_err_s=$(get_mib_counter "${listener_ns}" "MPTcpExtDataCsumErr")
-	local stat_csum_err_c=$(get_mib_counter "${connector_ns}" "MPTcpExtDataCsumErr")
+	local stat_synrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX")
+	local stat_ackrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
+	local stat_cookietx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent")
+	local stat_cookierx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv")
+	local stat_csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr")
+	local stat_csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr")
 
 	timeout ${timeout_test} \
 		ip netns exec ${listener_ns} \
@@ -454,7 +391,7 @@ do_transfer()
 				$extra_args $local_addr < "$sin" > "$sout" &
 	local spid=$!
 
-	wait_local_port_listen "${listener_ns}" "${port}"
+	mptcp_lib_wait_local_port_listen "${listener_ns}" "${port}"
 
 	local start
 	start=$(date +%s%3N)
@@ -504,16 +441,16 @@ do_transfer()
 		return 1
 	fi
 
-	check_transfer $sin $cout "file received by client"
+	mptcp_lib_check_transfer $sin $cout "file received by client"
 	retc=$?
-	check_transfer $cin $sout "file received by server"
+	mptcp_lib_check_transfer $cin $sout "file received by server"
 	rets=$?
 
-	local stat_synrx_now_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX")
-	local stat_ackrx_now_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
-	local stat_cookietx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent")
-	local stat_cookierx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv")
-	local stat_ooo_now=$(get_mib_counter "${listener_ns}" "TcpExtTCPOFOQueue")
+	local stat_synrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX")
+	local stat_ackrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
+	local stat_cookietx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent")
+	local stat_cookierx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv")
+	local stat_ooo_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue")
 
 	expect_synrx=$((stat_synrx_last_l))
 	expect_ackrx=$((stat_ackrx_last_l))
@@ -542,8 +479,8 @@ do_transfer()
 	fi
 
 	if $checksum; then
-		local csum_err_s=$(get_mib_counter "${listener_ns}" "MPTcpExtDataCsumErr")
-		local csum_err_c=$(get_mib_counter "${connector_ns}" "MPTcpExtDataCsumErr")
+		local csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr")
+		local csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr")
 
 		local csum_err_s_nr=$((csum_err_s - stat_csum_err_s))
 		if [ $csum_err_s_nr -gt 0 ]; then
@@ -613,9 +550,8 @@ make_file()
 	ksize=$((SIZE / 1024))
 	rem=$((SIZE - (ksize * 1024)))
 
-	dd if=/dev/urandom of="$name" bs=1024 count=$ksize 2> /dev/null
-	dd if=/dev/urandom conv=notrunc of="$name" bs=1 count=$rem 2> /dev/null
-	echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name"
+	mptcp_lib_make_file $name 1024 $ksize
+	dd if=/dev/urandom conv=notrunc of="$name" oflag=append bs=1 count=$rem 2> /dev/null
 
 	echo "Created $name (size $(du -b "$name")) containing data sent by $who"
 }
@@ -635,12 +571,12 @@ run_tests_lo()
 	fi
 
 	# skip if we don't want v6
-	if ! $ipv6 && is_v6 "${connect_addr}"; then
+	if ! $ipv6 && mptcp_lib_is_v6 "${connect_addr}"; then
 		return 0
 	fi
 
 	local local_addr
-	if is_v6 "${connect_addr}"; then
+	if mptcp_lib_is_v6 "${connect_addr}"; then
 		local_addr="::"
 	else
 		local_addr="0.0.0.0"
@@ -708,7 +644,7 @@ run_test_transparent()
 	TEST_GROUP="${msg}"
 
 	# skip if we don't want v6
-	if ! $ipv6 && is_v6 "${connect_addr}"; then
+	if ! $ipv6 && mptcp_lib_is_v6 "${connect_addr}"; then
 		return 0
 	fi
 
@@ -741,7 +677,7 @@ EOF
 	fi
 
 	local local_addr
-	if is_v6 "${connect_addr}"; then
+	if mptcp_lib_is_v6 "${connect_addr}"; then
 		local_addr="::"
 		r6flag="-6"
 	else
diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c
index 8672d898f8cd..218aac467321 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_inq.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c
@@ -18,6 +18,7 @@
 #include <time.h>
 
 #include <sys/ioctl.h>
+#include <sys/random.h>
 #include <sys/socket.h>
 #include <sys/types.h>
 #include <sys/wait.h>
@@ -519,15 +520,11 @@ static int client(int unixfd)
 
 static void init_rng(void)
 {
-	int fd = open("/dev/urandom", O_RDONLY);
 	unsigned int foo;
 
-	if (fd > 0) {
-		int ret = read(fd, &foo, sizeof(foo));
-
-		if (ret < 0)
-			srand(fd + foo);
-		close(fd);
+	if (getrandom(&foo, sizeof(foo), 0) == -1) {
+		perror("getrandom");
+		exit(1);
 	}
 
 	srand(foo);
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 75a2438efdf3..3a5b63026191 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -56,6 +56,8 @@ unset FAILING_LINKS
 unset test_linkfail
 unset addr_nr_ns1
 unset addr_nr_ns2
+unset cestab_ns1
+unset cestab_ns2
 unset sflags
 unset fastclose
 unset fullmesh
@@ -511,13 +513,6 @@ get_failed_tests_ids()
 	done | sort -n
 }
 
-print_file_err()
-{
-	ls -l "$1" 1>&2
-	echo -n "Trailing bytes are: "
-	tail -c 27 "$1"
-}
-
 check_transfer()
 {
 	local in=$1
@@ -548,8 +543,8 @@ check_transfer()
 		local sum=$((0${a} + 0${b}))
 		if [ $check_invert -eq 0 ] || [ $sum -ne $((0xff)) ]; then
 			fail_test "$what does not match (in, out):"
-			print_file_err "$in"
-			print_file_err "$out"
+			mptcp_lib_print_file_err "$in"
+			mptcp_lib_print_file_err "$out"
 
 			return 1
 		else
@@ -587,49 +582,9 @@ link_failure()
 	done
 }
 
-# $1: IP address
-is_v6()
-{
-	[ -z "${1##*:*}" ]
-}
-
-# $1: ns, $2: port
-wait_local_port_listen()
-{
-	local listener_ns="${1}"
-	local port="${2}"
-
-	local port_hex
-	port_hex="$(printf "%04X" "${port}")"
-
-	local i
-	for i in $(seq 10); do
-		ip netns exec "${listener_ns}" cat /proc/net/tcp* | \
-			awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" &&
-			break
-		sleep 0.1
-	done
-}
-
-# $1: ns ; $2: counter
-get_counter()
-{
-	local ns="${1}"
-	local counter="${2}"
-	local count
-
-	count=$(ip netns exec ${ns} nstat -asz "${counter}" | awk 'NR==1 {next} {print $2}')
-	if [ -z "${count}" ]; then
-		mptcp_lib_fail_if_expected_feature "${counter} counter"
-		return 1
-	fi
-
-	echo "${count}"
-}
-
 rm_addr_count()
 {
-	get_counter "${1}" "MPTcpExtRmAddr"
+	mptcp_lib_get_counter "${1}" "MPTcpExtRmAddr"
 }
 
 # $1: ns, $2: old rm_addr counter in $ns
@@ -649,7 +604,7 @@ wait_rm_addr()
 
 rm_sf_count()
 {
-	get_counter "${1}" "MPTcpExtRmSubflow"
+	mptcp_lib_get_counter "${1}" "MPTcpExtRmSubflow"
 }
 
 # $1: ns, $2: old rm_sf counter in $ns
@@ -672,26 +627,20 @@ wait_mpj()
 	local ns="${1}"
 	local cnt old_cnt
 
-	old_cnt=$(get_counter ${ns} "MPTcpExtMPJoinAckRx")
+	old_cnt=$(mptcp_lib_get_counter ${ns} "MPTcpExtMPJoinAckRx")
 
 	local i
 	for i in $(seq 10); do
-		cnt=$(get_counter ${ns} "MPTcpExtMPJoinAckRx")
+		cnt=$(mptcp_lib_get_counter ${ns} "MPTcpExtMPJoinAckRx")
 		[ "$cnt" = "${old_cnt}" ] || break
 		sleep 0.1
 	done
 }
 
-kill_wait()
-{
-	kill $1 > /dev/null 2>&1
-	wait $1 2>/dev/null
-}
-
 kill_events_pids()
 {
-	kill_wait $evts_ns1_pid
-	kill_wait $evts_ns2_pid
+	mptcp_lib_kill_wait $evts_ns1_pid
+	mptcp_lib_kill_wait $evts_ns2_pid
 }
 
 kill_tests_wait()
@@ -901,7 +850,7 @@ pm_nl_set_endpoint()
 		local id=10
 		while [ $add_nr_ns1 -gt 0 ]; do
 			local addr
-			if is_v6 "${connect_addr}"; then
+			if mptcp_lib_is_v6 "${connect_addr}"; then
 				addr="dead:beef:$counter::1"
 			else
 				addr="10.0.$counter.1"
@@ -953,7 +902,7 @@ pm_nl_set_endpoint()
 		local id=20
 		while [ $add_nr_ns2 -gt 0 ]; do
 			local addr
-			if is_v6 "${connect_addr}"; then
+			if mptcp_lib_is_v6 "${connect_addr}"; then
 				addr="dead:beef:$counter::2"
 			else
 				addr="10.0.$counter.2"
@@ -995,7 +944,7 @@ pm_nl_set_endpoint()
 			pm_nl_flush_endpoint ${connector_ns}
 		elif [ $rm_nr_ns2 -eq 9 ]; then
 			local addr
-			if is_v6 "${connect_addr}"; then
+			if mptcp_lib_is_v6 "${connect_addr}"; then
 				addr="dead:beef:1::2"
 			else
 				addr="10.0.1.2"
@@ -1029,6 +978,34 @@ pm_nl_set_endpoint()
 	fi
 }
 
+chk_cestab_nr()
+{
+	local ns=$1
+	local cestab=$2
+	local count
+
+	print_check "cestab $cestab"
+	count=$(mptcp_lib_get_counter ${ns} "MPTcpExtMPCurrEstab")
+	if [ -z "$count" ]; then
+		print_skip
+	elif [ "$count" != "$cestab" ]; then
+		fail_test "got $count current establish[s] expected $cestab"
+	else
+		print_ok
+	fi
+}
+
+# $1 namespace 1, $2 namespace 2
+check_cestab()
+{
+	if [ -n "${cestab_ns1}" ]; then
+		chk_cestab_nr ${1} ${cestab_ns1}
+	fi
+	if [ -n "${cestab_ns2}" ]; then
+		chk_cestab_nr ${2} ${cestab_ns2}
+	fi
+}
+
 do_transfer()
 {
 	local listener_ns="$1"
@@ -1117,7 +1094,7 @@ do_transfer()
 	fi
 	local spid=$!
 
-	wait_local_port_listen "${listener_ns}" "${port}"
+	mptcp_lib_wait_local_port_listen "${listener_ns}" "${port}"
 
 	extra_cl_args="$extra_args $extra_cl_args"
 	if [ "$test_linkfail" -eq 0 ];then
@@ -1142,6 +1119,7 @@ do_transfer()
 	local cpid=$!
 
 	pm_nl_set_endpoint $listener_ns $connector_ns $connect_addr
+	check_cestab $listener_ns $connector_ns
 
 	wait $cpid
 	local retc=$?
@@ -1199,8 +1177,7 @@ make_file()
 	local who=$2
 	local size=$3
 
-	dd if=/dev/urandom of="$name" bs=1024 count=$size 2> /dev/null
-	echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name"
+	mptcp_lib_make_file $name 1024 $size
 
 	print_info "Test file (size $size KB) for $who"
 }
@@ -1284,7 +1261,7 @@ chk_csum_nr()
 	fi
 
 	print_check "sum"
-	count=$(get_counter ${ns1} "MPTcpExtDataCsumErr")
+	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtDataCsumErr")
 	if [ "$count" != "$csum_ns1" ]; then
 		extra_msg="$extra_msg ns1=$count"
 	fi
@@ -1297,7 +1274,7 @@ chk_csum_nr()
 		print_ok
 	fi
 	print_check "csum"
-	count=$(get_counter ${ns2} "MPTcpExtDataCsumErr")
+	count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtDataCsumErr")
 	if [ "$count" != "$csum_ns2" ]; then
 		extra_msg="$extra_msg ns2=$count"
 	fi
@@ -1341,7 +1318,7 @@ chk_fail_nr()
 	fi
 
 	print_check "ftx"
-	count=$(get_counter ${ns_tx} "MPTcpExtMPFailTx")
+	count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPFailTx")
 	if [ "$count" != "$fail_tx" ]; then
 		extra_msg="$extra_msg,tx=$count"
 	fi
@@ -1355,7 +1332,7 @@ chk_fail_nr()
 	fi
 
 	print_check "failrx"
-	count=$(get_counter ${ns_rx} "MPTcpExtMPFailRx")
+	count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPFailRx")
 	if [ "$count" != "$fail_rx" ]; then
 		extra_msg="$extra_msg,rx=$count"
 	fi
@@ -1388,7 +1365,7 @@ chk_fclose_nr()
 	fi
 
 	print_check "ctx"
-	count=$(get_counter ${ns_tx} "MPTcpExtMPFastcloseTx")
+	count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPFastcloseTx")
 	if [ -z "$count" ]; then
 		print_skip
 	elif [ "$count" != "$fclose_tx" ]; then
@@ -1399,7 +1376,7 @@ chk_fclose_nr()
 	fi
 
 	print_check "fclzrx"
-	count=$(get_counter ${ns_rx} "MPTcpExtMPFastcloseRx")
+	count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPFastcloseRx")
 	if [ -z "$count" ]; then
 		print_skip
 	elif [ "$count" != "$fclose_rx" ]; then
@@ -1429,7 +1406,7 @@ chk_rst_nr()
 	fi
 
 	print_check "rtx"
-	count=$(get_counter ${ns_tx} "MPTcpExtMPRstTx")
+	count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPRstTx")
 	if [ -z "$count" ]; then
 		print_skip
 	# accept more rst than expected except if we don't expect any
@@ -1441,7 +1418,7 @@ chk_rst_nr()
 	fi
 
 	print_check "rstrx"
-	count=$(get_counter ${ns_rx} "MPTcpExtMPRstRx")
+	count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPRstRx")
 	if [ -z "$count" ]; then
 		print_skip
 	# accept more rst than expected except if we don't expect any
@@ -1462,7 +1439,7 @@ chk_infi_nr()
 	local count
 
 	print_check "itx"
-	count=$(get_counter ${ns2} "MPTcpExtInfiniteMapTx")
+	count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtInfiniteMapTx")
 	if [ -z "$count" ]; then
 		print_skip
 	elif [ "$count" != "$infi_tx" ]; then
@@ -1472,7 +1449,7 @@ chk_infi_nr()
 	fi
 
 	print_check "infirx"
-	count=$(get_counter ${ns1} "MPTcpExtInfiniteMapRx")
+	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtInfiniteMapRx")
 	if [ -z "$count" ]; then
 		print_skip
 	elif [ "$count" != "$infi_rx" ]; then
@@ -1501,7 +1478,7 @@ chk_join_nr()
 	fi
 
 	print_check "syn"
-	count=$(get_counter ${ns1} "MPTcpExtMPJoinSynRx")
+	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinSynRx")
 	if [ -z "$count" ]; then
 		print_skip
 	elif [ "$count" != "$syn_nr" ]; then
@@ -1512,7 +1489,7 @@ chk_join_nr()
 
 	print_check "synack"
 	with_cookie=$(ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies)
-	count=$(get_counter ${ns2} "MPTcpExtMPJoinSynAckRx")
+	count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinSynAckRx")
 	if [ -z "$count" ]; then
 		print_skip
 	elif [ "$count" != "$syn_ack_nr" ]; then
@@ -1529,7 +1506,7 @@ chk_join_nr()
 	fi
 
 	print_check "ack"
-	count=$(get_counter ${ns1} "MPTcpExtMPJoinAckRx")
+	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinAckRx")
 	if [ -z "$count" ]; then
 		print_skip
 	elif [ "$count" != "$ack_nr" ]; then
@@ -1562,8 +1539,8 @@ chk_stale_nr()
 
 	print_check "stale"
 
-	stale_nr=$(get_counter ${ns} "MPTcpExtSubflowStale")
-	recover_nr=$(get_counter ${ns} "MPTcpExtSubflowRecover")
+	stale_nr=$(mptcp_lib_get_counter ${ns} "MPTcpExtSubflowStale")
+	recover_nr=$(mptcp_lib_get_counter ${ns} "MPTcpExtSubflowRecover")
 	if [ -z "$stale_nr" ] || [ -z "$recover_nr" ]; then
 		print_skip
 	elif [ $stale_nr -lt $stale_min ] ||
@@ -1600,7 +1577,7 @@ chk_add_nr()
 	timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout)
 
 	print_check "add"
-	count=$(get_counter ${ns2} "MPTcpExtAddAddr")
+	count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtAddAddr")
 	if [ -z "$count" ]; then
 		print_skip
 	# if the test configured a short timeout tolerate greater then expected
@@ -1612,7 +1589,7 @@ chk_add_nr()
 	fi
 
 	print_check "echo"
-	count=$(get_counter ${ns1} "MPTcpExtEchoAdd")
+	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtEchoAdd")
 	if [ -z "$count" ]; then
 		print_skip
 	elif [ "$count" != "$echo_nr" ]; then
@@ -1623,7 +1600,7 @@ chk_add_nr()
 
 	if [ $port_nr -gt 0 ]; then
 		print_check "pt"
-		count=$(get_counter ${ns2} "MPTcpExtPortAdd")
+		count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtPortAdd")
 		if [ -z "$count" ]; then
 			print_skip
 		elif [ "$count" != "$port_nr" ]; then
@@ -1633,7 +1610,7 @@ chk_add_nr()
 		fi
 
 		print_check "syn"
-		count=$(get_counter ${ns1} "MPTcpExtMPJoinPortSynRx")
+		count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinPortSynRx")
 		if [ -z "$count" ]; then
 			print_skip
 		elif [ "$count" != "$syn_nr" ]; then
@@ -1644,7 +1621,7 @@ chk_add_nr()
 		fi
 
 		print_check "synack"
-		count=$(get_counter ${ns2} "MPTcpExtMPJoinPortSynAckRx")
+		count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinPortSynAckRx")
 		if [ -z "$count" ]; then
 			print_skip
 		elif [ "$count" != "$syn_ack_nr" ]; then
@@ -1655,7 +1632,7 @@ chk_add_nr()
 		fi
 
 		print_check "ack"
-		count=$(get_counter ${ns1} "MPTcpExtMPJoinPortAckRx")
+		count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinPortAckRx")
 		if [ -z "$count" ]; then
 			print_skip
 		elif [ "$count" != "$ack_nr" ]; then
@@ -1666,7 +1643,7 @@ chk_add_nr()
 		fi
 
 		print_check "syn"
-		count=$(get_counter ${ns1} "MPTcpExtMismatchPortSynRx")
+		count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMismatchPortSynRx")
 		if [ -z "$count" ]; then
 			print_skip
 		elif [ "$count" != "$mis_syn_nr" ]; then
@@ -1677,7 +1654,7 @@ chk_add_nr()
 		fi
 
 		print_check "ack"
-		count=$(get_counter ${ns1} "MPTcpExtMismatchPortAckRx")
+		count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMismatchPortAckRx")
 		if [ -z "$count" ]; then
 			print_skip
 		elif [ "$count" != "$mis_ack_nr" ]; then
@@ -1699,7 +1676,7 @@ chk_add_tx_nr()
 	timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout)
 
 	print_check "add TX"
-	count=$(get_counter ${ns1} "MPTcpExtAddAddrTx")
+	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtAddAddrTx")
 	if [ -z "$count" ]; then
 		print_skip
 	# if the test configured a short timeout tolerate greater then expected
@@ -1711,7 +1688,7 @@ chk_add_tx_nr()
 	fi
 
 	print_check "echo TX"
-	count=$(get_counter ${ns2} "MPTcpExtEchoAddTx")
+	count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtEchoAddTx")
 	if [ -z "$count" ]; then
 		print_skip
 	elif [ "$count" != "$echo_tx_nr" ]; then
@@ -1749,7 +1726,7 @@ chk_rm_nr()
 	fi
 
 	print_check "rm"
-	count=$(get_counter ${addr_ns} "MPTcpExtRmAddr")
+	count=$(mptcp_lib_get_counter ${addr_ns} "MPTcpExtRmAddr")
 	if [ -z "$count" ]; then
 		print_skip
 	elif [ "$count" != "$rm_addr_nr" ]; then
@@ -1759,13 +1736,13 @@ chk_rm_nr()
 	fi
 
 	print_check "rmsf"
-	count=$(get_counter ${subflow_ns} "MPTcpExtRmSubflow")
+	count=$(mptcp_lib_get_counter ${subflow_ns} "MPTcpExtRmSubflow")
 	if [ -z "$count" ]; then
 		print_skip
 	elif [ -n "$simult" ]; then
 		local cnt suffix
 
-		cnt=$(get_counter ${addr_ns} "MPTcpExtRmSubflow")
+		cnt=$(mptcp_lib_get_counter ${addr_ns} "MPTcpExtRmSubflow")
 
 		# in case of simult flush, the subflow removal count on each side is
 		# unreliable
@@ -1794,7 +1771,7 @@ chk_rm_tx_nr()
 	local rm_addr_tx_nr=$1
 
 	print_check "rm TX"
-	count=$(get_counter ${ns2} "MPTcpExtRmAddrTx")
+	count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtRmAddrTx")
 	if [ -z "$count" ]; then
 		print_skip
 	elif [ "$count" != "$rm_addr_tx_nr" ]; then
@@ -1811,7 +1788,7 @@ chk_prio_nr()
 	local count
 
 	print_check "ptx"
-	count=$(get_counter ${ns1} "MPTcpExtMPPrioTx")
+	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPPrioTx")
 	if [ -z "$count" ]; then
 		print_skip
 	elif [ "$count" != "$mp_prio_nr_tx" ]; then
@@ -1821,7 +1798,7 @@ chk_prio_nr()
 	fi
 
 	print_check "prx"
-	count=$(get_counter ${ns1} "MPTcpExtMPPrioRx")
+	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPPrioRx")
 	if [ -z "$count" ]; then
 		print_skip
 	elif [ "$count" != "$mp_prio_nr_rx" ]; then
@@ -1867,12 +1844,10 @@ chk_mptcp_info()
 	local cnt2
 	local dump_stats
 
-	print_check "mptcp_info ${info1:0:8}=$exp1:$exp2"
+	print_check "mptcp_info ${info1:0:15}=$exp1:$exp2"
 
-	cnt1=$(ss -N $ns1 -inmHM | grep "$info1:" |
-	       sed -n 's/.*\('"$info1"':\)\([[:digit:]]*\).*$/\2/p;q')
-	cnt2=$(ss -N $ns2 -inmHM | grep "$info2:" |
-	       sed -n 's/.*\('"$info2"':\)\([[:digit:]]*\).*$/\2/p;q')
+	cnt1=$(ss -N $ns1 -inmHM | mptcp_lib_get_info_value "$info1" "$info1")
+	cnt2=$(ss -N $ns2 -inmHM | mptcp_lib_get_info_value "$info2" "$info2")
 	# 'ss' only display active connections and counters that are not 0.
 	[ -z "$cnt1" ] && cnt1=0
 	[ -z "$cnt2" ] && cnt2=0
@@ -1890,6 +1865,42 @@ chk_mptcp_info()
 	fi
 }
 
+# $1: subflows in ns1 ; $2: subflows in ns2
+# number of all subflows, including the initial subflow.
+chk_subflows_total()
+{
+	local cnt1
+	local cnt2
+	local info="subflows_total"
+	local dump_stats
+
+	# if subflows_total counter is supported, use it:
+	if [ -n "$(ss -N $ns1 -inmHM | mptcp_lib_get_info_value $info $info)" ]; then
+		chk_mptcp_info $info $1 $info $2
+		return
+	fi
+
+	print_check "$info $1:$2"
+
+	# if not, count the TCP connections that are in fact MPTCP subflows
+	cnt1=$(ss -N $ns1 -ti state established state syn-sent state syn-recv |
+	       grep -c tcp-ulp-mptcp)
+	cnt2=$(ss -N $ns2 -ti state established state syn-sent state syn-recv |
+	       grep -c tcp-ulp-mptcp)
+
+	if [ "$1" != "$cnt1" ] || [ "$2" != "$cnt2" ]; then
+		fail_test "got subflows $cnt1:$cnt2 expected $1:$2"
+		dump_stats=1
+	else
+		print_ok
+	fi
+
+	if [ "$dump_stats" = 1 ]; then
+		ss -N $ns1 -ti
+		ss -N $ns2 -ti
+	fi
+}
+
 chk_link_usage()
 {
 	local ns=$1
@@ -1921,7 +1932,7 @@ wait_attempt_fail()
 	while [ $time -lt $timeout_ms ]; do
 		local cnt
 
-		cnt=$(get_counter ${ns} "TcpAttemptFails")
+		cnt=$(mptcp_lib_get_counter ${ns} "TcpAttemptFails")
 
 		[ "$cnt" = 1 ] && return 1
 		time=$((time + 100))
@@ -2497,47 +2508,52 @@ add_tests()
 	if reset "add single subflow"; then
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_set_limits $ns2 0 1
-		addr_nr_ns2=1 speed=slow \
+		addr_nr_ns2=1 speed=slow cestab_ns2=1 \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
+		chk_cestab_nr $ns2 0
 	fi
 
 	# add signal address
 	if reset "add signal address"; then
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_set_limits $ns2 1 1
-		addr_nr_ns1=1 speed=slow \
+		addr_nr_ns1=1 speed=slow cestab_ns1=1 \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
 		chk_add_nr 1 1
+		chk_cestab_nr $ns1 0
 	fi
 
 	# add multiple subflows
 	if reset "add multiple subflows"; then
 		pm_nl_set_limits $ns1 0 2
 		pm_nl_set_limits $ns2 0 2
-		addr_nr_ns2=2 speed=slow \
+		addr_nr_ns2=2 speed=slow cestab_ns2=1 \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 2 2 2
+		chk_cestab_nr $ns2 0
 	fi
 
 	# add multiple subflows IPv6
 	if reset "add multiple subflows IPv6"; then
 		pm_nl_set_limits $ns1 0 2
 		pm_nl_set_limits $ns2 0 2
-		addr_nr_ns2=2 speed=slow \
+		addr_nr_ns2=2 speed=slow cestab_ns2=1 \
 			run_tests $ns1 $ns2 dead:beef:1::1
 		chk_join_nr 2 2 2
+		chk_cestab_nr $ns2 0
 	fi
 
 	# add multiple addresses IPv6
 	if reset "add multiple addresses IPv6"; then
 		pm_nl_set_limits $ns1 0 2
 		pm_nl_set_limits $ns2 2 2
-		addr_nr_ns1=2 speed=slow \
+		addr_nr_ns1=2 speed=slow cestab_ns1=1 \
 			run_tests $ns1 $ns2 dead:beef:1::1
 		chk_join_nr 2 2 2
 		chk_add_nr 2 2
+		chk_cestab_nr $ns1 0
 	fi
 }
 
@@ -2776,7 +2792,7 @@ backup_tests()
 	fi
 
 	if reset "mpc backup" &&
-	   continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then
+	   continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then
 		pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup
 		speed=slow \
 			run_tests $ns1 $ns2 10.0.1.1
@@ -2785,7 +2801,7 @@ backup_tests()
 	fi
 
 	if reset "mpc backup both sides" &&
-	   continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then
+	   continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then
 		pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow,backup
 		pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup
 		speed=slow \
@@ -2795,7 +2811,7 @@ backup_tests()
 	fi
 
 	if reset "mpc switch to backup" &&
-	   continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then
+	   continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then
 		pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow
 		sflags=backup speed=slow \
 			run_tests $ns1 $ns2 10.0.1.1
@@ -2804,7 +2820,7 @@ backup_tests()
 	fi
 
 	if reset "mpc switch to backup both sides" &&
-	   continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then
+	   continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then
 		pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow
 		pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow
 		sflags=backup speed=slow \
@@ -2814,6 +2830,7 @@ backup_tests()
 	fi
 }
 
+SUB_ESTABLISHED=10 # MPTCP_EVENT_SUB_ESTABLISHED
 LISTENER_CREATED=15 #MPTCP_EVENT_LISTENER_CREATED
 LISTENER_CLOSED=16  #MPTCP_EVENT_LISTENER_CLOSED
 
@@ -2848,13 +2865,13 @@ verify_listener_events()
 		return
 	fi
 
-	type=$(grep "type:$e_type," $evt | sed -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q')
-	family=$(grep "type:$e_type," $evt | sed -n 's/.*\(family:\)\([[:digit:]]*\).*$/\2/p;q')
-	sport=$(grep "type:$e_type," $evt | sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q')
+	type=$(mptcp_lib_evts_get_info type "$evt" "$e_type")
+	family=$(mptcp_lib_evts_get_info family "$evt" "$e_type")
+	sport=$(mptcp_lib_evts_get_info sport "$evt" "$e_type")
 	if [ $family ] && [ $family = $AF_INET6 ]; then
-		saddr=$(grep "type:$e_type," $evt | sed -n 's/.*\(saddr6:\)\([0-9a-f:.]*\).*$/\2/p;q')
+		saddr=$(mptcp_lib_evts_get_info saddr6 "$evt" "$e_type")
 	else
-		saddr=$(grep "type:$e_type," $evt | sed -n 's/.*\(saddr4:\)\([0-9.]*\).*$/\2/p;q')
+		saddr=$(mptcp_lib_evts_get_info saddr4 "$evt" "$e_type")
 	fi
 
 	if [ $type ] && [ $type = $e_type ] &&
@@ -3240,7 +3257,7 @@ fastclose_tests()
 	if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then
 		test_linkfail=1024 fastclose=server \
 			run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 0 0 0
+		chk_join_nr 0 0 0 0 0 0 1
 		chk_fclose_nr 1 1 invert
 		chk_rst_nr 1 1
 	fi
@@ -3249,8 +3266,7 @@ fastclose_tests()
 pedit_action_pkts()
 {
 	tc -n $ns2 -j -s action show action pedit index 100 | \
-		grep "packets" | \
-		sed 's/.*"packets":\([0-9]\+\),.*/\1/'
+		mptcp_lib_get_info_value \"packets\" packets
 }
 
 fail_tests()
@@ -3275,75 +3291,70 @@ fail_tests()
 	fi
 }
 
+# $1: ns ; $2: addr ; $3: id
 userspace_pm_add_addr()
 {
-	local addr=$1
-	local id=$2
+	local evts=$evts_ns1
 	local tk
 
-	tk=$(grep "type:1," "$evts_ns1" |
-	     sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q')
-	ip netns exec $ns1 ./pm_nl_ctl ann $addr token $tk id $id
+	[ "$1" == "$ns2" ] && evts=$evts_ns2
+	tk=$(mptcp_lib_evts_get_info token "$evts")
+
+	ip netns exec $1 ./pm_nl_ctl ann $2 token $tk id $3
 	sleep 1
 }
 
-userspace_pm_rm_sf_addr_ns1()
+# $1: ns ; $2: id
+userspace_pm_rm_addr()
 {
-	local addr=$1
-	local id=$2
-	local tk sp da dp
-	local cnt_addr cnt_sf
-
-	tk=$(grep "type:1," "$evts_ns1" |
-	     sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q')
-	sp=$(grep "type:10" "$evts_ns1" |
-	     sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q')
-	da=$(grep "type:10" "$evts_ns1" |
-	     sed -n 's/.*\(daddr6:\)\([0-9a-f:.]*\).*$/\2/p;q')
-	dp=$(grep "type:10" "$evts_ns1" |
-	     sed -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q')
-	cnt_addr=$(rm_addr_count ${ns1})
-	cnt_sf=$(rm_sf_count ${ns1})
-	ip netns exec $ns1 ./pm_nl_ctl rem token $tk id $id
-	ip netns exec $ns1 ./pm_nl_ctl dsf lip "::ffff:$addr" \
-				lport $sp rip $da rport $dp token $tk
-	wait_rm_addr $ns1 "${cnt_addr}"
-	wait_rm_sf $ns1 "${cnt_sf}"
+	local evts=$evts_ns1
+	local tk
+	local cnt
+
+	[ "$1" == "$ns2" ] && evts=$evts_ns2
+	tk=$(mptcp_lib_evts_get_info token "$evts")
+
+	cnt=$(rm_addr_count ${1})
+	ip netns exec $1 ./pm_nl_ctl rem token $tk id $2
+	wait_rm_addr $1 "${cnt}"
 }
 
+# $1: ns ; $2: addr ; $3: id
 userspace_pm_add_sf()
 {
-	local addr=$1
-	local id=$2
+	local evts=$evts_ns1
 	local tk da dp
 
-	tk=$(sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2")
-	da=$(sed -n 's/.*\(daddr4:\)\([0-9.]*\).*$/\2/p;q' "$evts_ns2")
-	dp=$(sed -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2")
-	ip netns exec $ns2 ./pm_nl_ctl csf lip $addr lid $id \
+	[ "$1" == "$ns2" ] && evts=$evts_ns2
+	tk=$(mptcp_lib_evts_get_info token "$evts")
+	da=$(mptcp_lib_evts_get_info daddr4 "$evts")
+	dp=$(mptcp_lib_evts_get_info dport "$evts")
+
+	ip netns exec $1 ./pm_nl_ctl csf lip $2 lid $3 \
 				rip $da rport $dp token $tk
 	sleep 1
 }
 
-userspace_pm_rm_sf_addr_ns2()
+# $1: ns ; $2: addr $3: event type
+userspace_pm_rm_sf()
 {
-	local addr=$1
-	local id=$2
+	local evts=$evts_ns1
+	local t=${3:-1}
+	local ip=4
 	local tk da dp sp
-	local cnt_addr cnt_sf
-
-	tk=$(sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2")
-	da=$(sed -n 's/.*\(daddr4:\)\([0-9.]*\).*$/\2/p;q' "$evts_ns2")
-	dp=$(sed -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2")
-	sp=$(grep "type:10" "$evts_ns2" |
-	     sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q')
-	cnt_addr=$(rm_addr_count ${ns2})
-	cnt_sf=$(rm_sf_count ${ns2})
-	ip netns exec $ns2 ./pm_nl_ctl rem token $tk id $id
-	ip netns exec $ns2 ./pm_nl_ctl dsf lip $addr lport $sp \
+	local cnt
+
+	[ "$1" == "$ns2" ] && evts=$evts_ns2
+	if mptcp_lib_is_v6 $2; then ip=6; fi
+	tk=$(mptcp_lib_evts_get_info token "$evts")
+	da=$(mptcp_lib_evts_get_info "daddr$ip" "$evts" $t)
+	dp=$(mptcp_lib_evts_get_info dport "$evts" $t)
+	sp=$(mptcp_lib_evts_get_info sport "$evts" $t)
+
+	cnt=$(rm_sf_count ${1})
+	ip netns exec $1 ./pm_nl_ctl dsf lip $2 lport $sp \
 				rip $da rport $dp token $tk
-	wait_rm_addr $ns2 "${cnt_addr}"
-	wait_rm_sf $ns2 "${cnt_sf}"
+	wait_rm_sf $1 "${cnt}"
 }
 
 userspace_tests()
@@ -3430,14 +3441,17 @@ userspace_tests()
 			run_tests $ns1 $ns2 10.0.1.1 &
 		local tests_pid=$!
 		wait_mpj $ns1
-		userspace_pm_add_addr 10.0.2.1 10
+		userspace_pm_add_addr $ns1 10.0.2.1 10
 		chk_join_nr 1 1 1
 		chk_add_nr 1 1
 		chk_mptcp_info subflows 1 subflows 1
+		chk_subflows_total 2 2
 		chk_mptcp_info add_addr_signal 1 add_addr_accepted 1
-		userspace_pm_rm_sf_addr_ns1 10.0.2.1 10
+		userspace_pm_rm_addr $ns1 10
+		userspace_pm_rm_sf $ns1 "::ffff:10.0.2.1" $SUB_ESTABLISHED
 		chk_rm_nr 1 1 invert
 		chk_mptcp_info subflows 0 subflows 0
+		chk_subflows_total 1 1
 		kill_events_pids
 		wait $tests_pid
 	fi
@@ -3451,12 +3465,84 @@ userspace_tests()
 			run_tests $ns1 $ns2 10.0.1.1 &
 		local tests_pid=$!
 		wait_mpj $ns2
-		userspace_pm_add_sf 10.0.3.2 20
+		userspace_pm_add_sf $ns2 10.0.3.2 20
 		chk_join_nr 1 1 1
 		chk_mptcp_info subflows 1 subflows 1
-		userspace_pm_rm_sf_addr_ns2 10.0.3.2 20
+		chk_subflows_total 2 2
+		userspace_pm_rm_addr $ns2 20
+		userspace_pm_rm_sf $ns2 10.0.3.2 $SUB_ESTABLISHED
 		chk_rm_nr 1 1
 		chk_mptcp_info subflows 0 subflows 0
+		chk_subflows_total 1 1
+		kill_events_pids
+		wait $tests_pid
+	fi
+
+	# userspace pm create id 0 subflow
+	if reset_with_events "userspace pm create id 0 subflow" &&
+	   continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
+		set_userspace_pm $ns2
+		pm_nl_set_limits $ns1 0 1
+		speed=5 \
+			run_tests $ns1 $ns2 10.0.1.1 &
+		local tests_pid=$!
+		wait_mpj $ns2
+		chk_mptcp_info subflows 0 subflows 0
+		chk_subflows_total 1 1
+		userspace_pm_add_sf $ns2 10.0.3.2 0
+		chk_join_nr 1 1 1
+		chk_mptcp_info subflows 1 subflows 1
+		chk_subflows_total 2 2
+		kill_events_pids
+		wait $tests_pid
+	fi
+
+	# userspace pm remove initial subflow
+	if reset_with_events "userspace pm remove initial subflow" &&
+	   continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
+		set_userspace_pm $ns2
+		pm_nl_set_limits $ns1 0 1
+		speed=5 \
+			run_tests $ns1 $ns2 10.0.1.1 &
+		local tests_pid=$!
+		wait_mpj $ns2
+		userspace_pm_add_sf $ns2 10.0.3.2 20
+		chk_join_nr 1 1 1
+		chk_mptcp_info subflows 1 subflows 1
+		chk_subflows_total 2 2
+		userspace_pm_rm_sf $ns2 10.0.1.2
+		# we don't look at the counter linked to the RM_ADDR but
+		# to the one linked to the subflows that have been removed
+		chk_rm_nr 0 1
+		chk_rst_nr 0 0 invert
+		chk_mptcp_info subflows 1 subflows 1
+		chk_subflows_total 1 1
+		kill_events_pids
+		wait $tests_pid
+	fi
+
+	# userspace pm send RM_ADDR for ID 0
+	if reset_with_events "userspace pm send RM_ADDR for ID 0" &&
+	   continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
+		set_userspace_pm $ns1
+		pm_nl_set_limits $ns2 1 1
+		speed=5 \
+			run_tests $ns1 $ns2 10.0.1.1 &
+		local tests_pid=$!
+		wait_mpj $ns1
+		userspace_pm_add_addr $ns1 10.0.2.1 10
+		chk_join_nr 1 1 1
+		chk_add_nr 1 1
+		chk_mptcp_info subflows 1 subflows 1
+		chk_subflows_total 2 2
+		chk_mptcp_info add_addr_signal 1 add_addr_accepted 1
+		userspace_pm_rm_addr $ns1 0
+		# we don't look at the counter linked to the subflows that
+		# have been removed but to the one linked to the RM_ADDR
+		chk_rm_nr 1 0 invert
+		chk_rst_nr 0 0 invert
+		chk_mptcp_info subflows 1 subflows 1
+		chk_subflows_total 1 1
 		kill_events_pids
 		wait $tests_pid
 	fi
diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index 92a5befe8039..022262a2cfe0 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -207,3 +207,94 @@ mptcp_lib_result_print_all_tap() {
 		printf "%s\n" "${subtest}"
 	done
 }
+
+# get the value of keyword $1 in the line marked by keyword $2
+mptcp_lib_get_info_value() {
+	grep "${2}" | sed -n 's/.*\('"${1}"':\)\([0-9a-f:.]*\).*$/\2/p;q'
+}
+
+# $1: info name ; $2: evts_ns ; $3: event type
+mptcp_lib_evts_get_info() {
+	mptcp_lib_get_info_value "${1}" "^type:${3:-1}," < "${2}"
+}
+
+# $1: PID
+mptcp_lib_kill_wait() {
+	[ "${1}" -eq 0 ] && return 0
+
+	kill -SIGUSR1 "${1}" > /dev/null 2>&1
+	kill "${1}" > /dev/null 2>&1
+	wait "${1}" 2>/dev/null
+}
+
+# $1: IP address
+mptcp_lib_is_v6() {
+	[ -z "${1##*:*}" ]
+}
+
+# $1: ns, $2: MIB counter
+mptcp_lib_get_counter() {
+	local ns="${1}"
+	local counter="${2}"
+	local count
+
+	count=$(ip netns exec "${ns}" nstat -asz "${counter}" |
+		awk 'NR==1 {next} {print $2}')
+	if [ -z "${count}" ]; then
+		mptcp_lib_fail_if_expected_feature "${counter} counter"
+		return 1
+	fi
+
+	echo "${count}"
+}
+
+mptcp_lib_make_file() {
+	local name="${1}"
+	local bs="${2}"
+	local size="${3}"
+
+	dd if=/dev/urandom of="${name}" bs="${bs}" count="${size}" 2> /dev/null
+	echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "${name}"
+}
+
+# $1: file
+mptcp_lib_print_file_err() {
+	ls -l "${1}" 1>&2
+	echo "Trailing bytes are: "
+	tail -c 27 "${1}"
+}
+
+# $1: input file ; $2: output file ; $3: what kind of file
+mptcp_lib_check_transfer() {
+	local in="${1}"
+	local out="${2}"
+	local what="${3}"
+
+	if ! cmp "$in" "$out" > /dev/null 2>&1; then
+		echo "[ FAIL ] $what does not match (in, out):"
+		mptcp_lib_print_file_err "$in"
+		mptcp_lib_print_file_err "$out"
+
+		return 1
+	fi
+
+	return 0
+}
+
+# $1: ns, $2: port
+mptcp_lib_wait_local_port_listen() {
+	local listener_ns="${1}"
+	local port="${2}"
+
+	local port_hex
+	port_hex="$(printf "%04X" "${port}")"
+
+	local _
+	for _ in $(seq 10); do
+		ip netns exec "${listener_ns}" cat /proc/net/tcp* | \
+			awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) \
+			     {rc=0; exit}} END {exit rc}" &&
+			break
+		sleep 0.1
+	done
+}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
index a817af6616ec..c643872ddf47 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
@@ -135,38 +135,6 @@ check_mark()
 	return 0
 }
 
-print_file_err()
-{
-	ls -l "$1" 1>&2
-	echo "Trailing bytes are: "
-	tail -c 27 "$1"
-}
-
-check_transfer()
-{
-	local in=$1
-	local out=$2
-	local what=$3
-
-	cmp "$in" "$out" > /dev/null 2>&1
-	if [ $? -ne 0 ] ;then
-		echo "[ FAIL ] $what does not match (in, out):"
-		print_file_err "$in"
-		print_file_err "$out"
-		ret=1
-
-		return 1
-	fi
-
-	return 0
-}
-
-# $1: IP address
-is_v6()
-{
-	[ -z "${1##*:*}" ]
-}
-
 do_transfer()
 {
 	local listener_ns="$1"
@@ -183,7 +151,7 @@ do_transfer()
 	local mptcp_connect="./mptcp_connect -r 20"
 
 	local local_addr ip
-	if is_v6 "${connect_addr}"; then
+	if mptcp_lib_is_v6 "${connect_addr}"; then
 		local_addr="::"
 		ip=ipv6
 	else
@@ -238,7 +206,7 @@ do_transfer()
 		check_mark $connector_ns 4 || retc=1
 	fi
 
-	check_transfer $cin $sout "file received by server"
+	mptcp_lib_check_transfer $cin $sout "file received by server"
 	rets=$?
 
 	mptcp_lib_result_code "${retc}" "mark ${ip}"
@@ -257,8 +225,7 @@ make_file()
 	local who=$2
 	local size=$3
 
-	dd if=/dev/urandom of="$name" bs=1024 count=$size 2> /dev/null
-	echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name"
+	mptcp_lib_make_file $name 1024 $size
 
 	echo "Created $name (size $size KB) containing data sent by $who"
 }
diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index ce9203b817f8..ae8ad5d6fb9d 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -123,23 +123,6 @@ setup()
 	grep -q ' kmemleak_init$\| lockdep_init$\| kasan_init$\| prove_locking$' /proc/kallsyms && slack=$((slack+550))
 }
 
-# $1: ns, $2: port
-wait_local_port_listen()
-{
-	local listener_ns="${1}"
-	local port="${2}"
-
-	local port_hex i
-
-	port_hex="$(printf "%04X" "${port}")"
-	for i in $(seq 10); do
-		ip netns exec "${listener_ns}" cat /proc/net/tcp* | \
-			awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" &&
-			break
-		sleep 0.1
-	done
-}
-
 do_transfer()
 {
 	local cin=$1
@@ -179,7 +162,7 @@ do_transfer()
 				0.0.0.0 < "$sin" > "$sout" &
 	local spid=$!
 
-	wait_local_port_listen "${ns3}" "${port}"
+	mptcp_lib_wait_local_port_listen "${ns3}" "${port}"
 
 	timeout ${timeout_test} \
 		ip netns exec ${ns1} \
diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh
index b25a3e33eb25..6167837f48e1 100755
--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh
+++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh
@@ -108,15 +108,6 @@ test_fail()
 	mptcp_lib_result_fail "${test_name}"
 }
 
-kill_wait()
-{
-	[ $1 -eq 0 ] && return 0
-
-	kill -SIGUSR1 $1 > /dev/null 2>&1
-	kill $1 > /dev/null 2>&1
-	wait $1 2>/dev/null
-}
-
 # This function is used in the cleanup trap
 #shellcheck disable=SC2317
 cleanup()
@@ -128,7 +119,7 @@ cleanup()
 	for pid in $client4_pid $server4_pid $client6_pid $server6_pid\
 		   $server_evts_pid $client_evts_pid
 	do
-		kill_wait $pid
+		mptcp_lib_kill_wait $pid
 	done
 
 	local netns
@@ -173,22 +164,12 @@ print_title "Init"
 print_test "Created network namespaces ns1, ns2"
 test_pass
 
-make_file()
-{
-	# Store a chunk of data in a file to transmit over an MPTCP connection
-	local name=$1
-	local ksize=1
-
-	dd if=/dev/urandom of="$name" bs=2 count=$ksize 2> /dev/null
-	echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name"
-}
-
 make_connection()
 {
 	if [ -z "$file" ]; then
 		file=$(mktemp)
 	fi
-	make_file "$file" "client"
+	mptcp_lib_make_file "$file" 2 1
 
 	local is_v6=$1
 	local app_port=$app4_port
@@ -210,7 +191,7 @@ make_connection()
 	fi
 	:>"$client_evts"
 	if [ $client_evts_pid -ne 0 ]; then
-		kill_wait $client_evts_pid
+		mptcp_lib_kill_wait $client_evts_pid
 	fi
 	ip netns exec "$ns2" ./pm_nl_ctl events >> "$client_evts" 2>&1 &
 	client_evts_pid=$!
@@ -219,7 +200,7 @@ make_connection()
 	fi
 	:>"$server_evts"
 	if [ $server_evts_pid -ne 0 ]; then
-		kill_wait $server_evts_pid
+		mptcp_lib_kill_wait $server_evts_pid
 	fi
 	ip netns exec "$ns1" ./pm_nl_ctl events >> "$server_evts" 2>&1 &
 	server_evts_pid=$!
@@ -247,14 +228,11 @@ make_connection()
 	local server_token
 	local server_serverside
 
-	client_token=$(sed --unbuffered -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts")
-	client_port=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts")
-	client_serverside=$(sed --unbuffered -n 's/.*\(server_side:\)\([[:digit:]]*\).*$/\2/p;q'\
-				      "$client_evts")
-	server_token=$(grep "type:1," "$server_evts" |
-		       sed --unbuffered -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q')
-	server_serverside=$(grep "type:1," "$server_evts" |
-			    sed --unbuffered -n 's/.*\(server_side:\)\([[:digit:]]*\).*$/\2/p;q')
+	client_token=$(mptcp_lib_evts_get_info token "$client_evts")
+	client_port=$(mptcp_lib_evts_get_info sport "$client_evts")
+	client_serverside=$(mptcp_lib_evts_get_info server_side "$client_evts")
+	server_token=$(mptcp_lib_evts_get_info token "$server_evts")
+	server_serverside=$(mptcp_lib_evts_get_info server_side "$server_evts")
 
 	print_test "Established IP${is_v6} MPTCP Connection ns2 => ns1"
 	if [ "$client_token" != "" ] && [ "$server_token" != "" ] && [ "$client_serverside" = 0 ] &&
@@ -340,16 +318,16 @@ verify_announce_event()
 	local dport
 	local id
 
-	type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$evt")
-	token=$(sed --unbuffered -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evt")
+	type=$(mptcp_lib_evts_get_info type "$evt" $e_type)
+	token=$(mptcp_lib_evts_get_info token "$evt" $e_type)
 	if [ "$e_af" = "v6" ]
 	then
-		addr=$(sed --unbuffered -n 's/.*\(daddr6:\)\([0-9a-f:.]*\).*$/\2/p;q' "$evt")
+		addr=$(mptcp_lib_evts_get_info daddr6 "$evt" $e_type)
 	else
-		addr=$(sed --unbuffered -n 's/.*\(daddr4:\)\([0-9.]*\).*$/\2/p;q' "$evt")
+		addr=$(mptcp_lib_evts_get_info daddr4 "$evt" $e_type)
 	fi
-	dport=$(sed --unbuffered -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q' "$evt")
-	id=$(sed --unbuffered -n 's/.*\(rem_id:\)\([[:digit:]]*\).*$/\2/p;q' "$evt")
+	dport=$(mptcp_lib_evts_get_info dport "$evt" $e_type)
+	id=$(mptcp_lib_evts_get_info rem_id "$evt" $e_type)
 
 	check_expected "type" "token" "addr" "dport" "id"
 }
@@ -367,7 +345,7 @@ test_announce()
 	   $client_addr_id dev ns2eth1 > /dev/null 2>&1
 
 	local type
-	type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts")
+	type=$(mptcp_lib_evts_get_info type "$server_evts")
 	print_test "ADD_ADDR 10.0.2.2 (ns2) => ns1, invalid token"
 	if [ "$type" = "" ]
 	then
@@ -446,9 +424,9 @@ verify_remove_event()
 	local token
 	local id
 
-	type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$evt")
-	token=$(sed --unbuffered -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evt")
-	id=$(sed --unbuffered -n 's/.*\(rem_id:\)\([[:digit:]]*\).*$/\2/p;q' "$evt")
+	type=$(mptcp_lib_evts_get_info type "$evt" $e_type)
+	token=$(mptcp_lib_evts_get_info token "$evt" $e_type)
+	id=$(mptcp_lib_evts_get_info rem_id "$evt" $e_type)
 
 	check_expected "type" "token" "id"
 }
@@ -466,7 +444,7 @@ test_remove()
 	   $client_addr_id > /dev/null 2>&1
 	print_test "RM_ADDR id:${client_addr_id} ns2 => ns1, invalid token"
 	local type
-	type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts")
+	type=$(mptcp_lib_evts_get_info type "$server_evts")
 	if [ "$type" = "" ]
 	then
 		test_pass
@@ -479,7 +457,7 @@ test_remove()
 	ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\
 	   $invalid_id > /dev/null 2>&1
 	print_test "RM_ADDR id:${invalid_id} ns2 => ns1, invalid id"
-	type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts")
+	type=$(mptcp_lib_evts_get_info type "$server_evts")
 	if [ "$type" = "" ]
 	then
 		test_pass
@@ -583,19 +561,19 @@ verify_subflow_events()
 		fi
 	fi
 
-	type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$evt")
-	token=$(sed --unbuffered -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evt")
-	family=$(sed --unbuffered -n 's/.*\(family:\)\([[:digit:]]*\).*$/\2/p;q' "$evt")
-	dport=$(sed --unbuffered -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q' "$evt")
-	locid=$(sed --unbuffered -n 's/.*\(loc_id:\)\([[:digit:]]*\).*$/\2/p;q' "$evt")
-	remid=$(sed --unbuffered -n 's/.*\(rem_id:\)\([[:digit:]]*\).*$/\2/p;q' "$evt")
+	type=$(mptcp_lib_evts_get_info type "$evt" $e_type)
+	token=$(mptcp_lib_evts_get_info token "$evt" $e_type)
+	family=$(mptcp_lib_evts_get_info family "$evt" $e_type)
+	dport=$(mptcp_lib_evts_get_info dport "$evt" $e_type)
+	locid=$(mptcp_lib_evts_get_info loc_id "$evt" $e_type)
+	remid=$(mptcp_lib_evts_get_info rem_id "$evt" $e_type)
 	if [ "$family" = "$AF_INET6" ]
 	then
-		saddr=$(sed --unbuffered -n 's/.*\(saddr6:\)\([0-9a-f:.]*\).*$/\2/p;q' "$evt")
-		daddr=$(sed --unbuffered -n 's/.*\(daddr6:\)\([0-9a-f:.]*\).*$/\2/p;q' "$evt")
+		saddr=$(mptcp_lib_evts_get_info saddr6 "$evt" $e_type)
+		daddr=$(mptcp_lib_evts_get_info daddr6 "$evt" $e_type)
 	else
-		saddr=$(sed --unbuffered -n 's/.*\(saddr4:\)\([0-9.]*\).*$/\2/p;q' "$evt")
-		daddr=$(sed --unbuffered -n 's/.*\(daddr4:\)\([0-9.]*\).*$/\2/p;q' "$evt")
+		saddr=$(mptcp_lib_evts_get_info saddr4 "$evt" $e_type)
+		daddr=$(mptcp_lib_evts_get_info daddr4 "$evt" $e_type)
 	fi
 
 	check_expected "type" "token" "daddr" "dport" "family" "saddr" "locid" "remid"
@@ -627,10 +605,10 @@ test_subflows()
 			      "10.0.2.2" "$client4_port" "23" "$client_addr_id" "ns1" "ns2"
 
 	# Delete the listener from the client ns, if one was created
-	kill_wait $listener_pid
+	mptcp_lib_kill_wait $listener_pid
 
 	local sport
-	sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts")
+	sport=$(mptcp_lib_evts_get_info sport "$server_evts" $SUB_ESTABLISHED)
 
 	# DESTROY_SUBFLOW from server to client machine
 	:>"$server_evts"
@@ -666,9 +644,9 @@ test_subflows()
 			      "$client_addr_id" "ns1" "ns2"
 
 	# Delete the listener from the client ns, if one was created
-	kill_wait $listener_pid
+	mptcp_lib_kill_wait $listener_pid
 
-	sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts")
+	sport=$(mptcp_lib_evts_get_info sport "$server_evts" $SUB_ESTABLISHED)
 
 	# DESTROY_SUBFLOW6 from server to client machine
 	:>"$server_evts"
@@ -705,9 +683,9 @@ test_subflows()
 			      "$client_addr_id" "ns1" "ns2"
 
 	# Delete the listener from the client ns, if one was created
-	kill_wait $listener_pid
+	mptcp_lib_kill_wait $listener_pid
 
-	sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts")
+	sport=$(mptcp_lib_evts_get_info sport "$server_evts" $SUB_ESTABLISHED)
 
 	# DESTROY_SUBFLOW from server to client machine
 	:>"$server_evts"
@@ -743,9 +721,9 @@ test_subflows()
 			      "10.0.2.1" "$app4_port" "23" "$server_addr_id" "ns2" "ns1"
 
 	# Delete the listener from the server ns, if one was created
-	kill_wait $listener_pid
+	mptcp_lib_kill_wait $listener_pid
 
-	sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts")
+	sport=$(mptcp_lib_evts_get_info sport "$client_evts" $SUB_ESTABLISHED)
 
 	# DESTROY_SUBFLOW from client to server machine
 	:>"$client_evts"
@@ -782,9 +760,9 @@ test_subflows()
 			      "$server_addr_id" "ns2" "ns1"
 
 	# Delete the listener from the server ns, if one was created
-	kill_wait $listener_pid
+	mptcp_lib_kill_wait $listener_pid
 
-	sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts")
+	sport=$(mptcp_lib_evts_get_info sport "$client_evts" $SUB_ESTABLISHED)
 
 	# DESTROY_SUBFLOW6 from client to server machine
 	:>"$client_evts"
@@ -819,9 +797,9 @@ test_subflows()
 			      "10.0.2.2" "10.0.2.1" "$new4_port" "23" "$server_addr_id" "ns2" "ns1"
 
 	# Delete the listener from the server ns, if one was created
-	kill_wait $listener_pid
+	mptcp_lib_kill_wait $listener_pid
 
-	sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts")
+	sport=$(mptcp_lib_evts_get_info sport "$client_evts" $SUB_ESTABLISHED)
 
 	# DESTROY_SUBFLOW from client to server machine
 	:>"$client_evts"
@@ -865,9 +843,9 @@ test_subflows_v4_v6_mix()
 			      "$server_addr_id" "ns2" "ns1"
 
 	# Delete the listener from the server ns, if one was created
-	kill_wait $listener_pid
+	mptcp_lib_kill_wait $listener_pid
 
-	sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts")
+	sport=$(mptcp_lib_evts_get_info sport "$client_evts" $SUB_ESTABLISHED)
 
 	# DESTROY_SUBFLOW from client to server machine
 	:>"$client_evts"
@@ -896,9 +874,10 @@ test_prio()
 
 	# Check TX
 	print_test "MP_PRIO TX"
-	count=$(ip netns exec "$ns2" nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}')
-	[ -z "$count" ] && count=0
-	if [ $count != 1 ]; then
+	count=$(mptcp_lib_get_counter "$ns2" "MPTcpExtMPPrioTx")
+	if [ -z "$count" ]; then
+		test_skip
+	elif [ $count != 1 ]; then
 		test_fail "Count != 1: ${count}"
 	else
 		test_pass
@@ -906,9 +885,10 @@ test_prio()
 
 	# Check RX
 	print_test "MP_PRIO RX"
-	count=$(ip netns exec "$ns1" nstat -as | grep MPTcpExtMPPrioRx | awk '{print $2}')
-	[ -z "$count" ] && count=0
-	if [ $count != 1 ]; then
+	count=$(mptcp_lib_get_counter "$ns1" "MPTcpExtMPPrioRx")
+	if [ -z "$count" ]; then
+		test_skip
+	elif [ $count != 1 ]; then
 		test_fail "Count != 1: ${count}"
 	else
 		test_pass
@@ -933,18 +913,13 @@ verify_listener_events()
 		print_test "CLOSE_LISTENER $e_saddr:$e_sport"
 	fi
 
-	type=$(grep "type:$e_type," $evt |
-	       sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q')
-	family=$(grep "type:$e_type," $evt |
-		 sed --unbuffered -n 's/.*\(family:\)\([[:digit:]]*\).*$/\2/p;q')
-	sport=$(grep "type:$e_type," $evt |
-		sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q')
+	type=$(mptcp_lib_evts_get_info type $evt $e_type)
+	family=$(mptcp_lib_evts_get_info family $evt $e_type)
+	sport=$(mptcp_lib_evts_get_info sport $evt $e_type)
 	if [ $family ] && [ $family = $AF_INET6 ]; then
-		saddr=$(grep "type:$e_type," $evt |
-			sed --unbuffered -n 's/.*\(saddr6:\)\([0-9a-f:.]*\).*$/\2/p;q')
+		saddr=$(mptcp_lib_evts_get_info saddr6 $evt $e_type)
 	else
-		saddr=$(grep "type:$e_type," $evt |
-			sed --unbuffered -n 's/.*\(saddr4:\)\([0-9.]*\).*$/\2/p;q')
+		saddr=$(mptcp_lib_evts_get_info saddr4 $evt $e_type)
 	fi
 
 	check_expected "type" "family" "saddr" "sport"
@@ -982,7 +957,7 @@ test_listener()
 	sleep 0.5
 
 	# Delete the listener from the client ns, if one was created
-	kill_wait $listener_pid
+	mptcp_lib_kill_wait $listener_pid
 
 	sleep 0.5
 	verify_listener_events $client_evts $LISTENER_CLOSED $AF_INET 10.0.2.2 $client4_port
diff --git a/tools/testing/selftests/net/msg_zerocopy.sh b/tools/testing/selftests/net/msg_zerocopy.sh
index 825ffec85cea..89c22f5320e0 100755
--- a/tools/testing/selftests/net/msg_zerocopy.sh
+++ b/tools/testing/selftests/net/msg_zerocopy.sh
@@ -70,23 +70,22 @@ case "${TXMODE}" in
 esac
 
 # Start of state changes: install cleanup handler
-save_sysctl_mem="$(sysctl -n ${path_sysctl_mem})"
 
 cleanup() {
 	ip netns del "${NS2}"
 	ip netns del "${NS1}"
-	sysctl -w -q "${path_sysctl_mem}=${save_sysctl_mem}"
 }
 
 trap cleanup EXIT
 
-# Configure system settings
-sysctl -w -q "${path_sysctl_mem}=1000000"
-
 # Create virtual ethernet pair between network namespaces
 ip netns add "${NS1}"
 ip netns add "${NS2}"
 
+# Configure system settings
+ip netns exec "${NS1}" sysctl -w -q "${path_sysctl_mem}=1000000"
+ip netns exec "${NS2}" sysctl -w -q "${path_sysctl_mem}=1000000"
+
 ip link add "${DEV}" mtu "${DEV_MTU}" netns "${NS1}" type veth \
   peer name "${DEV}" mtu "${DEV_MTU}" netns "${NS2}"
 
diff --git a/tools/testing/selftests/net/ndisc_unsolicited_na_test.sh b/tools/testing/selftests/net/ndisc_unsolicited_na_test.sh
index 86e621b7b9c7..5db69dad0cfc 100755
--- a/tools/testing/selftests/net/ndisc_unsolicited_na_test.sh
+++ b/tools/testing/selftests/net/ndisc_unsolicited_na_test.sh
@@ -10,16 +10,12 @@
 #    0        1       0  Don't update NC
 #    0        1       1  Add a STALE NC entry
 
+source lib.sh
 ret=0
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
 
 PAUSE_ON_FAIL=no
 PAUSE=no
 
-HOST_NS="ns-host"
-ROUTER_NS="ns-router"
-
 HOST_INTF="veth-host"
 ROUTER_INTF="veth-router"
 
@@ -29,11 +25,6 @@ SUBNET_WIDTH=64
 ROUTER_ADDR_WITH_MASK="${ROUTER_ADDR}/${SUBNET_WIDTH}"
 HOST_ADDR_WITH_MASK="${HOST_ADDR}/${SUBNET_WIDTH}"
 
-IP_HOST="ip -6 -netns ${HOST_NS}"
-IP_HOST_EXEC="ip netns exec ${HOST_NS}"
-IP_ROUTER="ip -6 -netns ${ROUTER_NS}"
-IP_ROUTER_EXEC="ip netns exec ${ROUTER_NS}"
-
 tcpdump_stdout=
 tcpdump_stderr=
 
@@ -76,8 +67,12 @@ setup()
 
 	# Setup two namespaces and a veth tunnel across them.
 	# On end of the tunnel is a router and the other end is a host.
-	ip netns add ${HOST_NS}
-	ip netns add ${ROUTER_NS}
+	setup_ns HOST_NS ROUTER_NS
+	IP_HOST="ip -6 -netns ${HOST_NS}"
+	IP_HOST_EXEC="ip netns exec ${HOST_NS}"
+	IP_ROUTER="ip -6 -netns ${ROUTER_NS}"
+	IP_ROUTER_EXEC="ip netns exec ${ROUTER_NS}"
+
 	${IP_ROUTER} link add ${ROUTER_INTF} type veth \
                 peer name ${HOST_INTF} netns ${HOST_NS}
 
diff --git a/tools/testing/selftests/net/net_helper.sh b/tools/testing/selftests/net/net_helper.sh
new file mode 100755
index 000000000000..4fe0befa13fb
--- /dev/null
+++ b/tools/testing/selftests/net/net_helper.sh
@@ -0,0 +1,22 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Helper functions
+
+wait_local_port_listen()
+{
+	local listener_ns="${1}"
+	local port="${2}"
+	local protocol="${3}"
+	local port_hex
+	local i
+
+	port_hex="$(printf "%04X" "${port}")"
+	for i in $(seq 10); do
+		if ip netns exec "${listener_ns}" cat /proc/net/"${protocol}"* | \
+		   grep -q "${port_hex}"; then
+			break
+		fi
+		sleep 0.1
+	done
+}
diff --git a/tools/testing/selftests/net/netns-name.sh b/tools/testing/selftests/net/netns-name.sh
index 7d3d3fc99461..6974474c26f3 100755
--- a/tools/testing/selftests/net/netns-name.sh
+++ b/tools/testing/selftests/net/netns-name.sh
@@ -1,9 +1,9 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+source lib.sh
 set -o pipefail
 
-NS=netns-name-test
 DEV=dummy-dev0
 DEV2=dummy-dev1
 ALT_NAME=some-alt-name
@@ -11,7 +11,7 @@ ALT_NAME=some-alt-name
 RET_CODE=0
 
 cleanup() {
-    ip netns del $NS
+    cleanup_ns $NS $test_ns
 }
 
 trap cleanup EXIT
@@ -21,50 +21,50 @@ fail() {
     RET_CODE=1
 }
 
-ip netns add $NS
+setup_ns NS test_ns
 
 #
 # Test basic move without a rename
 #
 ip -netns $NS link add name $DEV type dummy || fail
-ip -netns $NS link set dev $DEV netns 1 ||
+ip -netns $NS link set dev $DEV netns $test_ns ||
     fail "Can't perform a netns move"
-ip link show dev $DEV >> /dev/null || fail "Device not found after move"
-ip link del $DEV || fail
+ip -netns $test_ns link show dev $DEV >> /dev/null || fail "Device not found after move"
+ip -netns $test_ns link del $DEV || fail
 
 #
 # Test move with a conflict
 #
-ip link add name $DEV type dummy
+ip -netns $test_ns link add name $DEV type dummy
 ip -netns $NS link add name $DEV type dummy || fail
-ip -netns $NS link set dev $DEV netns 1 2> /dev/null &&
+ip -netns $NS link set dev $DEV netns $test_ns 2> /dev/null &&
     fail "Performed a netns move with a name conflict"
-ip link show dev $DEV >> /dev/null || fail "Device not found after move"
+ip -netns $test_ns link show dev $DEV >> /dev/null || fail "Device not found after move"
 ip -netns $NS link del $DEV || fail
-ip link del $DEV || fail
+ip -netns $test_ns link del $DEV || fail
 
 #
 # Test move with a conflict and rename
 #
-ip link add name $DEV type dummy
+ip -netns $test_ns link add name $DEV type dummy
 ip -netns $NS link add name $DEV type dummy || fail
-ip -netns $NS link set dev $DEV netns 1 name $DEV2 ||
+ip -netns $NS link set dev $DEV netns $test_ns name $DEV2 ||
     fail "Can't perform a netns move with rename"
-ip link del $DEV2 || fail
-ip link del $DEV || fail
+ip -netns $test_ns link del $DEV2 || fail
+ip -netns $test_ns link del $DEV || fail
 
 #
 # Test dup alt-name with netns move
 #
-ip link add name $DEV type dummy || fail
-ip link property add dev $DEV altname $ALT_NAME || fail
+ip -netns $test_ns link add name $DEV type dummy || fail
+ip -netns $test_ns link property add dev $DEV altname $ALT_NAME || fail
 ip -netns $NS link add name $DEV2 type dummy || fail
 ip -netns $NS link property add dev $DEV2 altname $ALT_NAME || fail
 
-ip -netns $NS link set dev $DEV2 netns 1 2> /dev/null &&
+ip -netns $NS link set dev $DEV2 netns $test_ns 2> /dev/null &&
     fail "Moved with alt-name dup"
 
-ip link del $DEV || fail
+ip -netns $test_ns link del $DEV || fail
 ip -netns $NS link del $DEV2 || fail
 
 #
@@ -72,11 +72,11 @@ ip -netns $NS link del $DEV2 || fail
 #
 ip -netns $NS link add name $DEV type dummy || fail
 ip -netns $NS link property add dev $DEV altname $ALT_NAME || fail
-ip -netns $NS link set dev $DEV netns 1 || fail
-ip link show dev $ALT_NAME >> /dev/null || fail "Can't find alt-name after move"
-ip  -netns $NS link show dev $ALT_NAME 2> /dev/null &&
+ip -netns $NS link set dev $DEV netns $test_ns || fail
+ip -netns $test_ns link show dev $ALT_NAME >> /dev/null || fail "Can't find alt-name after move"
+ip -netns $NS link show dev $ALT_NAME 2> /dev/null &&
     fail "Can still find alt-name after move"
-ip link del $DEV || fail
+ip -netns $test_ns link del $DEV || fail
 
 echo -ne "$(basename $0) \t\t\t\t"
 if [ $RET_CODE -eq 0 ]; then
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index b3b2dc5a630c..f10879788f61 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 #
 # Check that route PMTU values match expectations, and that initial device MTU
@@ -198,8 +198,7 @@
 # - pmtu_ipv6_route_change
 #	Same as above but with IPv6
 
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
+source lib.sh
 
 PAUSE_ON_FAIL=no
 VERBOSE=0
@@ -268,16 +267,6 @@ tests="
 	pmtu_ipv4_route_change		ipv4: PMTU exception w/route replace	1
 	pmtu_ipv6_route_change		ipv6: PMTU exception w/route replace	1"
 
-NS_A="ns-A"
-NS_B="ns-B"
-NS_C="ns-C"
-NS_R1="ns-R1"
-NS_R2="ns-R2"
-ns_a="ip netns exec ${NS_A}"
-ns_b="ip netns exec ${NS_B}"
-ns_c="ip netns exec ${NS_C}"
-ns_r1="ip netns exec ${NS_R1}"
-ns_r2="ip netns exec ${NS_R2}"
 # Addressing and routing for tests with routers: four network segments, with
 # index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an
 # identifier ID, which is 1 for hosts (A and B), 2 for routers (R1 and R2).
@@ -543,13 +532,17 @@ setup_ip6ip6() {
 }
 
 setup_namespaces() {
+	setup_ns NS_A NS_B NS_C NS_R1 NS_R2
 	for n in ${NS_A} ${NS_B} ${NS_C} ${NS_R1} ${NS_R2}; do
-		ip netns add ${n} || return 1
-
 		# Disable DAD, so that we don't have to wait to use the
 		# configured IPv6 addresses
 		ip netns exec ${n} sysctl -q net/ipv6/conf/default/accept_dad=0
 	done
+	ns_a="ip netns exec ${NS_A}"
+	ns_b="ip netns exec ${NS_B}"
+	ns_c="ip netns exec ${NS_C}"
+	ns_r1="ip netns exec ${NS_R1}"
+	ns_r2="ip netns exec ${NS_R2}"
 }
 
 setup_veth() {
@@ -839,7 +832,7 @@ setup_bridge() {
 	run_cmd ${ns_a} ip link set br0 up
 
 	run_cmd ${ns_c} ip link add veth_C-A type veth peer name veth_A-C
-	run_cmd ${ns_c} ip link set veth_A-C netns ns-A
+	run_cmd ${ns_c} ip link set veth_A-C netns ${NS_A}
 
 	run_cmd ${ns_a} ip link set veth_A-C up
 	run_cmd ${ns_c} ip link set veth_C-A up
@@ -944,9 +937,7 @@ cleanup() {
 	done
 	socat_pids=
 
-	for n in ${NS_A} ${NS_B} ${NS_C} ${NS_R1} ${NS_R2}; do
-		ip netns del ${n} 2> /dev/null
-	done
+	cleanup_all_ns
 
 	ip link del veth_A-C			2>/dev/null
 	ip link del veth_A-R1			2>/dev/null
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 5f2b3f6c0d74..a10a32952f21 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -35,8 +35,7 @@ VERBOSE=0
 PAUSE=no
 PAUSE_ON_FAIL=no
 
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
+source lib.sh
 
 # set global exit status, but never reset nonzero one.
 check_err()
@@ -297,7 +296,7 @@ kci_test_addrlft()
 	done
 
 	sleep 5
-	run_cmd_grep "10.23.11." ip addr show dev "$devdummy"
+	run_cmd_grep_fail "10.23.11." ip addr show dev "$devdummy"
 	if [ $? -eq 0 ]; then
 		check_err 1
 		end_test "FAIL: preferred_lft addresses remaining"
@@ -517,9 +516,8 @@ kci_test_encap_fou()
 # test various encap methods, use netns to avoid unwanted interference
 kci_test_encap()
 {
-	testns="testns"
 	local ret=0
-	run_cmd ip netns add "$testns"
+	setup_ns testns
 	if [ $? -ne 0 ]; then
 		end_test "SKIP encap tests: cannot add net namespace $testns"
 		return $ksft_skip
@@ -574,6 +572,10 @@ kci_test_macsec_offload()
 		return $ksft_skip
 	fi
 
+	if ! mount | grep -q debugfs; then
+		mount -t debugfs none /sys/kernel/debug/ &> /dev/null
+	fi
+
 	# setup netdevsim since dummydev doesn't have offload support
 	if [ ! -w /sys/bus/netdevsim/new_device ] ; then
 		run_cmd modprobe -q netdevsim
@@ -738,6 +740,10 @@ kci_test_ipsec_offload()
 	sysfsnet=/sys/bus/netdevsim/devices/netdevsim0/net/
 	probed=false
 
+	if ! mount | grep -q debugfs; then
+		mount -t debugfs none /sys/kernel/debug/ &> /dev/null
+	fi
+
 	# setup netdevsim since dummydev doesn't have offload support
 	if [ ! -w /sys/bus/netdevsim/new_device ] ; then
 		run_cmd modprobe -q netdevsim
@@ -836,11 +842,10 @@ EOF
 
 kci_test_gretap()
 {
-	testns="testns"
 	DEV_NS=gretap00
 	local ret=0
 
-	run_cmd ip netns add "$testns"
+	setup_ns testns
 	if [ $? -ne 0 ]; then
 		end_test "SKIP gretap tests: cannot add net namespace $testns"
 		return $ksft_skip
@@ -859,7 +864,7 @@ kci_test_gretap()
 
 
 	run_cmd ip -netns "$testns" addr add dev "$DEV_NS" 10.1.1.100/24
-	run_cmd ip -netns "$testns" link set dev $DEV_NS ups
+	run_cmd ip -netns "$testns" link set dev $DEV_NS up
 	run_cmd ip -netns "$testns" link del "$DEV_NS"
 
 	# test external mode
@@ -878,11 +883,10 @@ kci_test_gretap()
 
 kci_test_ip6gretap()
 {
-	testns="testns"
 	DEV_NS=ip6gretap00
 	local ret=0
 
-	run_cmd ip netns add "$testns"
+	setup_ns testns
 	if [ $? -ne 0 ]; then
 		end_test "SKIP ip6gretap tests: cannot add net namespace $testns"
 		return $ksft_skip
@@ -920,7 +924,6 @@ kci_test_ip6gretap()
 
 kci_test_erspan()
 {
-	testns="testns"
 	DEV_NS=erspan00
 	local ret=0
 	run_cmd_grep "^Usage:" ip link help erspan
@@ -928,7 +931,7 @@ kci_test_erspan()
 		end_test "SKIP: erspan: iproute2 too old"
 		return $ksft_skip
 	fi
-	run_cmd ip netns add "$testns"
+	setup_ns testns
 	if [ $? -ne 0 ]; then
 		end_test "SKIP erspan tests: cannot add net namespace $testns"
 		return $ksft_skip
@@ -970,7 +973,6 @@ kci_test_erspan()
 
 kci_test_ip6erspan()
 {
-	testns="testns"
 	DEV_NS=ip6erspan00
 	local ret=0
 	run_cmd_grep "^Usage:" ip link help ip6erspan
@@ -978,7 +980,7 @@ kci_test_ip6erspan()
 		end_test "SKIP: ip6erspan: iproute2 too old"
 		return $ksft_skip
 	fi
-	run_cmd ip netns add "$testns"
+	setup_ns testns
 	if [ $? -ne 0 ]; then
 		end_test "SKIP ip6erspan tests: cannot add net namespace $testns"
 		return $ksft_skip
@@ -1022,8 +1024,6 @@ kci_test_ip6erspan()
 
 kci_test_fdb_get()
 {
-	IP="ip -netns testns"
-	BRIDGE="bridge -netns testns"
 	brdev="test-br0"
 	vxlandev="vxlan10"
 	test_mac=de:ad:be:ef:13:37
@@ -1037,11 +1037,13 @@ kci_test_fdb_get()
 		return $ksft_skip
 	fi
 
-	run_cmd ip netns add testns
+	setup_ns testns
 	if [ $? -ne 0 ]; then
 		end_test "SKIP fdb get tests: cannot add net namespace $testns"
 		return $ksft_skip
 	fi
+	IP="ip -netns $testns"
+	BRIDGE="bridge -netns $testns"
 	run_cmd $IP link add "$vxlandev" type vxlan id 10 local $localip \
                 dstport 4789
 	run_cmd $IP link add name "$brdev" type bridge
@@ -1052,7 +1054,7 @@ kci_test_fdb_get()
 	run_cmd_grep "dev $vxlandev master $brdev" $BRIDGE fdb get $test_mac br "$brdev"
 	run_cmd_grep "dev $vxlandev dst $dstip" $BRIDGE fdb get $test_mac dev "$vxlandev" self
 
-	ip netns del testns &>/dev/null
+	ip netns del $testns &>/dev/null
 
 	if [ $ret -ne 0 ]; then
 		end_test "FAIL: bridge fdb get"
diff --git a/tools/testing/selftests/net/sctp_vrf.sh b/tools/testing/selftests/net/sctp_vrf.sh
index c721e952e5f3..c854034b6aa1 100755
--- a/tools/testing/selftests/net/sctp_vrf.sh
+++ b/tools/testing/selftests/net/sctp_vrf.sh
@@ -6,13 +6,11 @@
 #                                                  SERVER_NS
 #       CLIENT_NS2 (veth1) <---> (veth2) -> vrf_s2
 
-CLIENT_NS1="client-ns1"
-CLIENT_NS2="client-ns2"
+source lib.sh
 CLIENT_IP4="10.0.0.1"
 CLIENT_IP6="2000::1"
 CLIENT_PORT=1234
 
-SERVER_NS="server-ns"
 SERVER_IP4="10.0.0.2"
 SERVER_IP6="2000::2"
 SERVER_PORT=1234
@@ -20,9 +18,7 @@ SERVER_PORT=1234
 setup() {
 	modprobe sctp
 	modprobe sctp_diag
-	ip netns add $CLIENT_NS1
-	ip netns add $CLIENT_NS2
-	ip netns add $SERVER_NS
+	setup_ns CLIENT_NS1 CLIENT_NS2 SERVER_NS
 
 	ip net exec $CLIENT_NS1 sysctl -w net.ipv6.conf.default.accept_dad=0 2>&1 >/dev/null
 	ip net exec $CLIENT_NS2 sysctl -w net.ipv6.conf.default.accept_dad=0 2>&1 >/dev/null
@@ -67,9 +63,7 @@ setup() {
 
 cleanup() {
 	ip netns exec $SERVER_NS pkill sctp_hello 2>&1 >/dev/null
-	ip netns del "$CLIENT_NS1"
-	ip netns del "$CLIENT_NS2"
-	ip netns del "$SERVER_NS"
+	cleanup_ns $CLIENT_NS1 $CLIENT_NS2 $SERVER_NS
 }
 
 wait_server() {
diff --git a/tools/testing/selftests/net/settings b/tools/testing/selftests/net/settings
index dfc27cdc6c05..ed8418e8217a 100644
--- a/tools/testing/selftests/net/settings
+++ b/tools/testing/selftests/net/settings
@@ -1 +1 @@
-timeout=1500
+timeout=3600
diff --git a/tools/testing/selftests/net/setup_loopback.sh b/tools/testing/selftests/net/setup_loopback.sh
index e57bbfbc5208..2070b57849de 100755
--- a/tools/testing/selftests/net/setup_loopback.sh
+++ b/tools/testing/selftests/net/setup_loopback.sh
@@ -5,6 +5,8 @@ readonly FLUSH_PATH="/sys/class/net/${dev}/gro_flush_timeout"
 readonly IRQ_PATH="/sys/class/net/${dev}/napi_defer_hard_irqs"
 readonly FLUSH_TIMEOUT="$(< ${FLUSH_PATH})"
 readonly HARD_IRQS="$(< ${IRQ_PATH})"
+readonly server_ns=$(mktemp -u server-XXXXXXXX)
+readonly client_ns=$(mktemp -u client-XXXXXXXX)
 
 netdev_check_for_carrier() {
 	local -r dev="$1"
@@ -97,12 +99,12 @@ setup_interrupt() {
 
 setup_ns() {
 	# Set up server_ns namespace and client_ns namespace
-	setup_macvlan_ns "${dev}" server_ns server "${SERVER_MAC}"
-	setup_macvlan_ns "${dev}" client_ns client "${CLIENT_MAC}"
+	setup_macvlan_ns "${dev}" ${server_ns} server "${SERVER_MAC}"
+	setup_macvlan_ns "${dev}" ${client_ns} client "${CLIENT_MAC}"
 }
 
 cleanup_ns() {
-	cleanup_macvlan_ns server_ns server client_ns client
+	cleanup_macvlan_ns ${server_ns} server ${client_ns} client
 }
 
 setup() {
diff --git a/tools/testing/selftests/net/setup_veth.sh b/tools/testing/selftests/net/setup_veth.sh
index 1003ddf7b3b2..a9a1759e035c 100644
--- a/tools/testing/selftests/net/setup_veth.sh
+++ b/tools/testing/selftests/net/setup_veth.sh
@@ -1,6 +1,9 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+readonly server_ns=$(mktemp -u server-XXXXXXXX)
+readonly client_ns=$(mktemp -u client-XXXXXXXX)
+
 setup_veth_ns() {
 	local -r link_dev="$1"
 	local -r ns_name="$2"
@@ -19,14 +22,14 @@ setup_ns() {
 	# Set up server_ns namespace and client_ns namespace
 	ip link add name server type veth peer name client
 
-	setup_veth_ns "${dev}" server_ns server "${SERVER_MAC}"
-	setup_veth_ns "${dev}" client_ns client "${CLIENT_MAC}"
+	setup_veth_ns "${dev}" ${server_ns} server "${SERVER_MAC}"
+	setup_veth_ns "${dev}" ${client_ns} client "${CLIENT_MAC}"
 }
 
 cleanup_ns() {
 	local ns_name
 
-	for ns_name in client_ns server_ns; do
+	for ns_name in ${client_ns} ${server_ns}; do
 		[[ -e /var/run/netns/"${ns_name}" ]] && ip netns del "${ns_name}"
 	done
 }
diff --git a/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh
index 441eededa031..02d617040793 100755
--- a/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh
@@ -193,8 +193,7 @@
 # +---------------------------------------------------+
 #
 
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
+source lib.sh
 
 readonly LOCALSID_TABLE_ID=90
 readonly IPv6_RT_NETWORK=fd00
@@ -250,26 +249,22 @@ cleanup()
 	ip link del veth-rt-1 2>/dev/null || true
 	ip link del veth-rt-2 2>/dev/null || true
 
-	# destroy routers rt-* and hosts hs-*
-	for ns in $(ip netns show | grep -E 'rt-*|hs-*'); do
-		ip netns del ${ns} || true
-	done
+	cleanup_all_ns
 }
 
 # Setup the basic networking for the routers
 setup_rt_networking()
 {
-	local rt=$1
-	local nsname=rt-${rt}
+	local id=$1
+	eval local nsname=\${rt_${id}}
 
-	ip netns add ${nsname}
-	ip link set veth-rt-${rt} netns ${nsname}
-	ip -netns ${nsname} link set veth-rt-${rt} name veth0
+	ip link set veth-rt-${id} netns ${nsname}
+	ip -netns ${nsname} link set veth-rt-${id} name veth0
 
 	ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec ${nsname} sysctl -wq net.ipv6.conf.default.accept_dad=0
 
-	ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 nodad
+	ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${id}/64 dev veth0 nodad
 	ip -netns ${nsname} link set veth0 up
 	ip -netns ${nsname} link set lo up
 
@@ -279,16 +274,14 @@ setup_rt_networking()
 
 setup_hs()
 {
-	local hs=$1
-	local rt=$2
+	local hid=$1
+	local rid=$2
 	local tid=$3
-	local hsname=hs-t${tid}-${hs}
-	local rtname=rt-${rt}
+	eval local hsname=\${hs_t${tid}_${hid}}
+	eval local rtname=\${rt_${rid}}
 	local rtveth=veth-t${tid}
 
 	# set the networking for the host
-	ip netns add ${hsname}
-
 	ip netns exec ${hsname} sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec ${hsname} sysctl -wq net.ipv6.conf.default.accept_dad=0
 
@@ -299,8 +292,8 @@ setup_hs()
 
 	ip -netns ${hsname} link add veth0 type veth peer name ${rtveth}
 	ip -netns ${hsname} link set ${rtveth} netns ${rtname}
-	ip -netns ${hsname} addr add ${IPv6_HS_NETWORK}::${hs}/64 dev veth0 nodad
-	ip -netns ${hsname} addr add ${IPv4_HS_NETWORK}.${hs}/24 dev veth0
+	ip -netns ${hsname} addr add ${IPv6_HS_NETWORK}::${hid}/64 dev veth0 nodad
+	ip -netns ${hsname} addr add ${IPv4_HS_NETWORK}.${hid}/24 dev veth0
 	ip -netns ${hsname} link set veth0 up
 	ip -netns ${hsname} link set lo up
 
@@ -332,10 +325,8 @@ setup_vpn_config()
 	local rtdst=$4
 	local tid=$5
 
-	local hssrc_name=hs-t${tid}-${hssrc}
-	local hsdst_name=hs-t${tid}-${hsdst}
-	local rtsrc_name=rt-${rtsrc}
-	local rtdst_name=rt-${rtdst}
+	eval local rtsrc_name=\${rt_${rtsrc}}
+	eval local rtdst_name=\${rt_${rtdst}}
 	local rtveth=veth-t${tid}
 	local vpn_sid=${VPN_LOCATOR_SERVICE}:${hssrc}${hsdst}:${tid}::6046
 
@@ -379,18 +370,21 @@ setup()
 {
 	ip link add veth-rt-1 type veth peer name veth-rt-2
 	# setup the networking for router rt-1 and router rt-2
+	setup_ns rt_1 rt_2
 	setup_rt_networking 1
 	setup_rt_networking 2
 
 	# setup two hosts for the tenant 100.
 	#  - host hs-1 is directly connected to the router rt-1;
 	#  - host hs-2 is directly connected to the router rt-2.
+	setup_ns hs_t100_1 hs_t100_2
 	setup_hs 1 1 100  #args: host router tenant
 	setup_hs 2 2 100
 
 	# setup two hosts for the tenant 200
 	#  - host hs-3 is directly connected to the router rt-1;
 	#  - host hs-4 is directly connected to the router rt-2.
+	setup_ns hs_t200_3 hs_t200_4
 	setup_hs 3 1 200
 	setup_hs 4 2 200
 
@@ -409,8 +403,9 @@ check_rt_connectivity()
 {
 	local rtsrc=$1
 	local rtdst=$2
+	eval local nsname=\${rt_${rtsrc}}
 
-	ip netns exec rt-${rtsrc} ping -c 1 -W 1 ${IPv6_RT_NETWORK}::${rtdst} \
+	ip netns exec ${nsname} ping -c 1 -W 1 ${IPv6_RT_NETWORK}::${rtdst} \
 		>/dev/null 2>&1
 }
 
@@ -428,8 +423,9 @@ check_hs_ipv6_connectivity()
 	local hssrc=$1
 	local hsdst=$2
 	local tid=$3
+	eval local nsname=\${hs_t${tid}_${hssrc}}
 
-	ip netns exec hs-t${tid}-${hssrc} ping -c 1 -W ${PING_TIMEOUT_SEC} \
+	ip netns exec ${nsname} ping -c 1 -W ${PING_TIMEOUT_SEC} \
 		${IPv6_HS_NETWORK}::${hsdst} >/dev/null 2>&1
 }
 
@@ -438,8 +434,9 @@ check_hs_ipv4_connectivity()
 	local hssrc=$1
 	local hsdst=$2
 	local tid=$3
+	eval local nsname=\${hs_t${tid}_${hssrc}}
 
-	ip netns exec hs-t${tid}-${hssrc} ping -c 1 -W ${PING_TIMEOUT_SEC} \
+	ip netns exec ${nsname} ping -c 1 -W ${PING_TIMEOUT_SEC} \
 		${IPv4_HS_NETWORK}.${hsdst} >/dev/null 2>&1
 }
 
diff --git a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh
index f96282362811..79fb81e63c59 100755
--- a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh
@@ -163,8 +163,7 @@
 # +---------------------------------------------------+
 #
 
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
+source lib.sh
 
 readonly LOCALSID_TABLE_ID=90
 readonly IPv6_RT_NETWORK=fd00
@@ -219,27 +218,22 @@ cleanup()
 	ip link del veth-rt-1 2>/dev/null || true
 	ip link del veth-rt-2 2>/dev/null || true
 
-	# destroy routers rt-* and hosts hs-*
-	for ns in $(ip netns show | grep -E 'rt-*|hs-*'); do
-		ip netns del ${ns} || true
-	done
+	cleanup_all_ns
 }
 
 # Setup the basic networking for the routers
 setup_rt_networking()
 {
-	local rt=$1
-	local nsname=rt-${rt}
-
-	ip netns add ${nsname}
+	local id=$1
+	eval local nsname=\${rt_${id}}
 
 	ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec ${nsname} sysctl -wq net.ipv6.conf.default.accept_dad=0
 
-	ip link set veth-rt-${rt} netns ${nsname}
-	ip -netns ${nsname} link set veth-rt-${rt} name veth0
+	ip link set veth-rt-${id} netns ${nsname}
+	ip -netns ${nsname} link set veth-rt-${id} name veth0
 
-	ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 nodad
+	ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${id}/64 dev veth0 nodad
 	ip -netns ${nsname} link set veth0 up
 	ip -netns ${nsname} link set lo up
 
@@ -249,16 +243,13 @@ setup_rt_networking()
 
 setup_hs()
 {
-	local hs=$1
-	local rt=$2
+	local hid=$1
+	local rid=$2
 	local tid=$3
-	local hsname=hs-t${tid}-${hs}
-	local rtname=rt-${rt}
+	eval local hsname=\${hs_t${tid}_${hid}}
+	eval local rtname=\${rt_${rid}}
 	local rtveth=veth-t${tid}
 
-	# set the networking for the host
-	ip netns add ${hsname}
-
 	# disable the rp_filter otherwise the kernel gets confused about how
 	# to route decap ipv4 packets.
 	ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0
@@ -266,7 +257,7 @@ setup_hs()
 
 	ip -netns ${hsname} link add veth0 type veth peer name ${rtveth}
 	ip -netns ${hsname} link set ${rtveth} netns ${rtname}
-	ip -netns ${hsname} addr add ${IPv4_HS_NETWORK}.${hs}/24 dev veth0
+	ip -netns ${hsname} addr add ${IPv4_HS_NETWORK}.${hid}/24 dev veth0
 	ip -netns ${hsname} link set veth0 up
 	ip -netns ${hsname} link set lo up
 
@@ -293,10 +284,8 @@ setup_vpn_config()
 	local rtdst=$4
 	local tid=$5
 
-	local hssrc_name=hs-t${tid}-${hssrc}
-	local hsdst_name=hs-t${tid}-${hsdst}
-	local rtsrc_name=rt-${rtsrc}
-	local rtdst_name=rt-${rtdst}
+	eval local rtsrc_name=\${rt_${rtsrc}}
+	eval local rtdst_name=\${rt_${rtdst}}
 	local vpn_sid=${VPN_LOCATOR_SERVICE}:${hssrc}${hsdst}:${tid}::6004
 
 	# set the encap route for encapsulating packets which arrive from the
@@ -328,18 +317,21 @@ setup()
 {
 	ip link add veth-rt-1 type veth peer name veth-rt-2
 	# setup the networking for router rt-1 and router rt-2
+	setup_ns rt_1 rt_2
 	setup_rt_networking 1
 	setup_rt_networking 2
 
 	# setup two hosts for the tenant 100.
 	#  - host hs-1 is directly connected to the router rt-1;
 	#  - host hs-2 is directly connected to the router rt-2.
+	setup_ns hs_t100_1 hs_t100_2
 	setup_hs 1 1 100  #args: host router tenant
 	setup_hs 2 2 100
 
 	# setup two hosts for the tenant 200
 	#  - host hs-3 is directly connected to the router rt-1;
 	#  - host hs-4 is directly connected to the router rt-2.
+	setup_ns hs_t200_3 hs_t200_4
 	setup_hs 3 1 200
 	setup_hs 4 2 200
 
@@ -358,8 +350,9 @@ check_rt_connectivity()
 {
 	local rtsrc=$1
 	local rtdst=$2
+	eval local nsname=\${rt_${rtsrc}}
 
-	ip netns exec rt-${rtsrc} ping -c 1 -W 1 ${IPv6_RT_NETWORK}::${rtdst} \
+	ip netns exec ${nsname} ping -c 1 -W 1 ${IPv6_RT_NETWORK}::${rtdst} \
 		>/dev/null 2>&1
 }
 
@@ -377,8 +370,9 @@ check_hs_connectivity()
 	local hssrc=$1
 	local hsdst=$2
 	local tid=$3
+	eval local nsname=\${hs_t${tid}_${hssrc}}
 
-	ip netns exec hs-t${tid}-${hssrc} ping -c 1 -W ${PING_TIMEOUT_SEC} \
+	ip netns exec ${nsname} ping -c 1 -W ${PING_TIMEOUT_SEC} \
 		${IPv4_HS_NETWORK}.${hsdst} >/dev/null 2>&1
 }
 
diff --git a/tools/testing/selftests/net/srv6_end_dt6_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt6_l3vpn_test.sh
index b9b06ef80d88..e408406d8489 100755
--- a/tools/testing/selftests/net/srv6_end_dt6_l3vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_end_dt6_l3vpn_test.sh
@@ -164,8 +164,7 @@
 # +---------------------------------------------------+
 #
 
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
+source lib.sh
 
 readonly LOCALSID_TABLE_ID=90
 readonly IPv6_RT_NETWORK=fd00
@@ -220,26 +219,22 @@ cleanup()
 	ip link del veth-rt-1 2>/dev/null || true
 	ip link del veth-rt-2 2>/dev/null || true
 
-	# destroy routers rt-* and hosts hs-*
-	for ns in $(ip netns show | grep -E 'rt-*|hs-*'); do
-		ip netns del ${ns} || true
-	done
+	cleanup_all_ns
 }
 
 # Setup the basic networking for the routers
 setup_rt_networking()
 {
-	local rt=$1
-	local nsname=rt-${rt}
+	local id=$1
+	eval local nsname=\${rt_${id}}
 
-	ip netns add ${nsname}
-	ip link set veth-rt-${rt} netns ${nsname}
-	ip -netns ${nsname} link set veth-rt-${rt} name veth0
+	ip link set veth-rt-${id} netns ${nsname}
+	ip -netns ${nsname} link set veth-rt-${id} name veth0
 
 	ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec ${nsname} sysctl -wq net.ipv6.conf.default.accept_dad=0
 
-	ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 nodad
+	ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${id}/64 dev veth0 nodad
 	ip -netns ${nsname} link set veth0 up
 	ip -netns ${nsname} link set lo up
 
@@ -248,22 +243,20 @@ setup_rt_networking()
 
 setup_hs()
 {
-	local hs=$1
-	local rt=$2
+	local hid=$1
+	local rid=$2
 	local tid=$3
-	local hsname=hs-t${tid}-${hs}
-	local rtname=rt-${rt}
+	eval local hsname=\${hs_t${tid}_${hid}}
+	eval local rtname=\${rt_${rid}}
 	local rtveth=veth-t${tid}
 
 	# set the networking for the host
-	ip netns add ${hsname}
-
 	ip netns exec ${hsname} sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec ${hsname} sysctl -wq net.ipv6.conf.default.accept_dad=0
 
 	ip -netns ${hsname} link add veth0 type veth peer name ${rtveth}
 	ip -netns ${hsname} link set ${rtveth} netns ${rtname}
-	ip -netns ${hsname} addr add ${IPv6_HS_NETWORK}::${hs}/64 dev veth0 nodad
+	ip -netns ${hsname} addr add ${IPv6_HS_NETWORK}::${hid}/64 dev veth0 nodad
 	ip -netns ${hsname} link set veth0 up
 	ip -netns ${hsname} link set lo up
 
@@ -293,10 +286,8 @@ setup_vpn_config()
 	local rtdst=$4
 	local tid=$5
 
-	local hssrc_name=hs-t${tid}-${hssrc}
-	local hsdst_name=hs-t${tid}-${hsdst}
-	local rtsrc_name=rt-${rtsrc}
-	local rtdst_name=rt-${rtdst}
+	eval local rtsrc_name=\${rt_${rtsrc}}
+	eval local rtdst_name=\${rt_${rtdst}}
 	local rtveth=veth-t${tid}
 	local vpn_sid=${VPN_LOCATOR_SERVICE}:${hssrc}${hsdst}:${tid}::6006
 
@@ -331,18 +322,21 @@ setup()
 {
 	ip link add veth-rt-1 type veth peer name veth-rt-2
 	# setup the networking for router rt-1 and router rt-2
+	setup_ns rt_1 rt_2
 	setup_rt_networking 1
 	setup_rt_networking 2
 
 	# setup two hosts for the tenant 100.
 	#  - host hs-1 is directly connected to the router rt-1;
 	#  - host hs-2 is directly connected to the router rt-2.
+	setup_ns hs_t100_1 hs_t100_2
 	setup_hs 1 1 100  #args: host router tenant
 	setup_hs 2 2 100
 
 	# setup two hosts for the tenant 200
 	#  - host hs-3 is directly connected to the router rt-1;
 	#  - host hs-4 is directly connected to the router rt-2.
+	setup_ns hs_t200_3 hs_t200_4
 	setup_hs 3 1 200
 	setup_hs 4 2 200
 
@@ -361,8 +355,9 @@ check_rt_connectivity()
 {
 	local rtsrc=$1
 	local rtdst=$2
+	eval local nsname=\${rt_${rtsrc}}
 
-	ip netns exec rt-${rtsrc} ping -c 1 -W 1 ${IPv6_RT_NETWORK}::${rtdst} \
+	ip netns exec ${nsname} ping -c 1 -W 1 ${IPv6_RT_NETWORK}::${rtdst} \
 		>/dev/null 2>&1
 }
 
@@ -380,8 +375,9 @@ check_hs_connectivity()
 	local hssrc=$1
 	local hsdst=$2
 	local tid=$3
+	eval local nsname=\${hs_t${tid}_${hssrc}}
 
-	ip netns exec hs-t${tid}-${hssrc} ping -c 1 -W ${PING_TIMEOUT_SEC} \
+	ip netns exec ${nsname} ping -c 1 -W ${PING_TIMEOUT_SEC} \
 		${IPv6_HS_NETWORK}::${hsdst} >/dev/null 2>&1
 }
 
diff --git a/tools/testing/selftests/net/stress_reuseport_listen.sh b/tools/testing/selftests/net/stress_reuseport_listen.sh
index 4de11da4092b..94d5d1a1c90f 100755
--- a/tools/testing/selftests/net/stress_reuseport_listen.sh
+++ b/tools/testing/selftests/net/stress_reuseport_listen.sh
@@ -2,18 +2,18 @@
 # SPDX-License-Identifier: GPL-2.0
 # Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
 
-NS='stress_reuseport_listen_ns'
+source lib.sh
 NR_FILES=24100
 SAVED_NR_FILES=$(ulimit -n)
 
 setup() {
-	ip netns add $NS
+	setup_ns NS
 	ip netns exec $NS sysctl -q -w net.ipv6.ip_nonlocal_bind=1
 	ulimit -n $NR_FILES
 }
 
 cleanup() {
-	ip netns del $NS
+	cleanup_ns $NS
 	ulimit -n $SAVED_NR_FILES
 }
 
diff --git a/tools/testing/selftests/net/tcp_ao/.gitignore b/tools/testing/selftests/net/tcp_ao/.gitignore
new file mode 100644
index 000000000000..e8bb81b715b7
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/.gitignore
@@ -0,0 +1,2 @@
+*_ipv4
+*_ipv6
diff --git a/tools/testing/selftests/net/tcp_ao/Makefile b/tools/testing/selftests/net/tcp_ao/Makefile
new file mode 100644
index 000000000000..8e60bae67aa9
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/Makefile
@@ -0,0 +1,56 @@
+# SPDX-License-Identifier: GPL-2.0
+TEST_BOTH_AF := bench-lookups
+TEST_BOTH_AF += connect
+TEST_BOTH_AF += connect-deny
+TEST_BOTH_AF += icmps-accept icmps-discard
+TEST_BOTH_AF += key-management
+TEST_BOTH_AF += restore
+TEST_BOTH_AF += rst
+TEST_BOTH_AF += self-connect
+TEST_BOTH_AF += seq-ext
+TEST_BOTH_AF += setsockopt-closed
+TEST_BOTH_AF += unsigned-md5
+
+TEST_IPV4_PROGS := $(TEST_BOTH_AF:%=%_ipv4)
+TEST_IPV6_PROGS := $(TEST_BOTH_AF:%=%_ipv6)
+
+TEST_GEN_PROGS := $(TEST_IPV4_PROGS) $(TEST_IPV6_PROGS)
+
+top_srcdir	  := ../../../../..
+include ../../lib.mk
+
+HOSTAR ?= ar
+
+LIBDIR	:= $(OUTPUT)/lib
+LIB	:= $(LIBDIR)/libaotst.a
+LDLIBS	+= $(LIB) -pthread
+LIBDEPS	:= lib/aolib.h Makefile
+
+CFLAGS	:= -Wall -O2 -g -D_GNU_SOURCE -fno-strict-aliasing
+CFLAGS	+= $(KHDR_INCLUDES)
+CFLAGS	+= -iquote ./lib/ -I ../../../../include/
+
+# Library
+LIBSRC	:= kconfig.c netlink.c proc.c repair.c setup.c sock.c utils.c
+LIBOBJ	:= $(LIBSRC:%.c=$(LIBDIR)/%.o)
+EXTRA_CLEAN += $(LIBOBJ) $(LIB)
+
+$(LIB): $(LIBOBJ)
+	$(HOSTAR) rcs $@ $^
+
+$(LIBDIR)/%.o: ./lib/%.c $(LIBDEPS)
+	mkdir -p $(LIBDIR)
+	$(CC) $< $(CFLAGS) $(CPPFLAGS) -o $@ -c
+
+$(TEST_GEN_PROGS): $(LIB)
+
+$(OUTPUT)/%_ipv4: %.c
+	$(LINK.c) $^ $(LDLIBS) -o $@
+
+$(OUTPUT)/%_ipv6: %.c
+	$(LINK.c) -DIPV6_TEST $^ $(LDLIBS) -o $@
+
+$(OUTPUT)/icmps-accept_ipv4: CFLAGS+= -DTEST_ICMPS_ACCEPT
+$(OUTPUT)/icmps-accept_ipv6: CFLAGS+= -DTEST_ICMPS_ACCEPT
+$(OUTPUT)/bench-lookups_ipv4: LDFLAGS+= -lm
+$(OUTPUT)/bench-lookups_ipv6: LDFLAGS+= -lm
diff --git a/tools/testing/selftests/net/tcp_ao/bench-lookups.c b/tools/testing/selftests/net/tcp_ao/bench-lookups.c
new file mode 100644
index 000000000000..a1e6e007c291
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/bench-lookups.c
@@ -0,0 +1,360 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Author: Dmitry Safonov <dima@arista.com> */
+#include <arpa/inet.h>
+#include <inttypes.h>
+#include <math.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <time.h>
+
+#include "../../../../include/linux/bits.h"
+#include "../../../../include/linux/kernel.h"
+#include "aolib.h"
+
+#define BENCH_NR_ITERS	100 /* number of times to run gathering statistics */
+
+static void gen_test_ips(union tcp_addr *ips, size_t ips_nr, bool use_rand)
+{
+	union tcp_addr net = {};
+	size_t i, j;
+
+	if (inet_pton(TEST_FAMILY, TEST_NETWORK, &net) != 1)
+		test_error("Can't convert ip address %s", TEST_NETWORK);
+
+	if (!use_rand) {
+		for (i = 0; i < ips_nr; i++)
+			ips[i] = gen_tcp_addr(net, 2 * i + 1);
+		return;
+	}
+	for (i = 0; i < ips_nr; i++) {
+		size_t r = (size_t)random() | 0x1;
+
+		ips[i] = gen_tcp_addr(net, r);
+
+		for (j = i - 1; j > 0 && i > 0; j--) {
+			if (!memcmp(&ips[i], &ips[j], sizeof(union tcp_addr))) {
+				i--; /* collision */
+				break;
+			}
+		}
+	}
+}
+
+static void test_add_routes(union tcp_addr *ips, size_t ips_nr)
+{
+	size_t i;
+
+	for (i = 0; i < ips_nr; i++) {
+		union tcp_addr *p = (union tcp_addr *)&ips[i];
+		int err;
+
+		err = ip_route_add(veth_name, TEST_FAMILY, this_ip_addr, *p);
+		if (err && err != -EEXIST)
+			test_error("Failed to add route");
+	}
+}
+
+static void server_apply_keys(int lsk, union tcp_addr *ips, size_t ips_nr)
+{
+	size_t i;
+
+	for (i = 0; i < ips_nr; i++) {
+		union tcp_addr *p = (union tcp_addr *)&ips[i];
+
+		if (test_add_key(lsk, DEFAULT_TEST_PASSWORD, *p, -1, 100, 100))
+			test_error("setsockopt(TCP_AO)");
+	}
+}
+
+static const size_t nr_keys[] = { 512, 1024, 2048, 4096, 8192 };
+static union tcp_addr *test_ips;
+
+struct bench_stats {
+	uint64_t min;
+	uint64_t max;
+	uint64_t nr;
+	double mean;
+	double s2;
+};
+
+static struct bench_tests {
+	struct bench_stats delete_last_key;
+	struct bench_stats add_key;
+	struct bench_stats delete_rand_key;
+	struct bench_stats connect_last_key;
+	struct bench_stats connect_rand_key;
+	struct bench_stats delete_async;
+} bench_results[ARRAY_SIZE(nr_keys)];
+
+#define NSEC_PER_SEC 1000000000ULL
+
+static void measure_call(struct bench_stats *st,
+			 void (*f)(int, void *), int sk, void *arg)
+{
+	struct timespec start = {}, end = {};
+	double delta;
+	uint64_t nsec;
+
+	if (clock_gettime(CLOCK_MONOTONIC, &start))
+		test_error("clock_gettime()");
+
+	f(sk, arg);
+
+	if (clock_gettime(CLOCK_MONOTONIC, &end))
+		test_error("clock_gettime()");
+
+	nsec = (end.tv_sec - start.tv_sec) * NSEC_PER_SEC;
+	if (end.tv_nsec >= start.tv_nsec)
+		nsec += end.tv_nsec - start.tv_nsec;
+	else
+		nsec -= start.tv_nsec - end.tv_nsec;
+
+	if (st->nr == 0) {
+		st->min = st->max = nsec;
+	} else {
+		if (st->min > nsec)
+			st->min = nsec;
+		if (st->max < nsec)
+			st->max = nsec;
+	}
+
+	/* Welford-Knuth algorithm */
+	st->nr++;
+	delta = (double)nsec - st->mean;
+	st->mean += delta / st->nr;
+	st->s2 += delta * ((double)nsec - st->mean);
+}
+
+static void delete_mkt(int sk, void *arg)
+{
+	struct tcp_ao_del *ao = arg;
+
+	if (setsockopt(sk, IPPROTO_TCP, TCP_AO_DEL_KEY, ao, sizeof(*ao)))
+		test_error("setsockopt(TCP_AO_DEL_KEY)");
+}
+
+static void add_back_mkt(int sk, void *arg)
+{
+	union tcp_addr *p = arg;
+
+	if (test_add_key(sk, DEFAULT_TEST_PASSWORD, *p, -1, 100, 100))
+		test_error("setsockopt(TCP_AO)");
+}
+
+static void bench_delete(int lsk, struct bench_stats *add,
+			 struct bench_stats *del,
+			 union tcp_addr *ips, size_t ips_nr,
+			 bool rand_order, bool async)
+{
+	struct tcp_ao_del ao_del = {};
+	union tcp_addr *p;
+	size_t i;
+
+	ao_del.sndid = 100;
+	ao_del.rcvid = 100;
+	ao_del.del_async = !!async;
+	ao_del.prefix = DEFAULT_TEST_PREFIX;
+
+	/* Remove the first added */
+	p = (union tcp_addr *)&ips[0];
+	tcp_addr_to_sockaddr_in(&ao_del.addr, p, 0);
+
+	for (i = 0; i < BENCH_NR_ITERS; i++) {
+		measure_call(del, delete_mkt, lsk, (void *)&ao_del);
+
+		/* Restore it back */
+		measure_call(add, add_back_mkt, lsk, (void *)p);
+
+		/*
+		 * Slowest for FILO-linked-list:
+		 * on (i) iteration removing ips[i] element. When it gets
+		 * added to the list back - it becomes first to fetch, so
+		 * on (i + 1) iteration go to ips[i + 1] element.
+		 */
+		if (rand_order)
+			p = (union tcp_addr *)&ips[rand() % ips_nr];
+		else
+			p = (union tcp_addr *)&ips[i % ips_nr];
+		tcp_addr_to_sockaddr_in(&ao_del.addr, p, 0);
+	}
+}
+
+static void bench_connect_srv(int lsk, union tcp_addr *ips, size_t ips_nr)
+{
+	size_t i;
+
+	for (i = 0; i < BENCH_NR_ITERS; i++) {
+		int sk;
+
+		synchronize_threads();
+
+		if (test_wait_fd(lsk, TEST_TIMEOUT_SEC, 0))
+			test_error("test_wait_fd()");
+
+		sk = accept(lsk, NULL, NULL);
+		if (sk < 0)
+			test_error("accept()");
+
+		close(sk);
+	}
+}
+
+static void test_print_stats(const char *desc, size_t nr, struct bench_stats *bs)
+{
+	test_ok("%-20s\t%zu keys: min=%" PRIu64 "ms max=%" PRIu64 "ms mean=%gms stddev=%g",
+		desc, nr, bs->min / 1000000, bs->max / 1000000,
+		bs->mean / 1000000, sqrt((bs->mean / 1000000) / bs->nr));
+}
+
+static void *server_fn(void *arg)
+{
+	size_t i;
+
+	for (i = 0; i < ARRAY_SIZE(nr_keys); i++) {
+		struct bench_tests *bt = &bench_results[i];
+		int lsk;
+
+		test_ips = malloc(nr_keys[i] * sizeof(union tcp_addr));
+		if (!test_ips)
+			test_error("malloc()");
+
+		lsk = test_listen_socket(this_ip_addr, test_server_port + i, 1);
+
+		gen_test_ips(test_ips, nr_keys[i], false);
+		test_add_routes(test_ips, nr_keys[i]);
+		test_set_optmem(KERNEL_TCP_AO_KEY_SZ_ROUND_UP * nr_keys[i]);
+		server_apply_keys(lsk, test_ips, nr_keys[i]);
+
+		synchronize_threads();
+		bench_connect_srv(lsk, test_ips, nr_keys[i]);
+		bench_connect_srv(lsk, test_ips, nr_keys[i]);
+
+		/* The worst case for FILO-list */
+		bench_delete(lsk, &bt->add_key, &bt->delete_last_key,
+			     test_ips, nr_keys[i], false, false);
+		test_print_stats("Add a new key",
+				nr_keys[i], &bt->add_key);
+		test_print_stats("Delete: worst case",
+				nr_keys[i], &bt->delete_last_key);
+
+		bench_delete(lsk, &bt->add_key, &bt->delete_rand_key,
+			     test_ips, nr_keys[i], true, false);
+		test_print_stats("Delete: random-search",
+				nr_keys[i], &bt->delete_rand_key);
+
+		bench_delete(lsk, &bt->add_key, &bt->delete_async,
+			     test_ips, nr_keys[i], false, true);
+		test_print_stats("Delete: async", nr_keys[i], &bt->delete_async);
+
+		free(test_ips);
+		close(lsk);
+	}
+
+	return NULL;
+}
+
+static void connect_client(int sk, void *arg)
+{
+	size_t *p = arg;
+
+	if (test_connect_socket(sk, this_ip_dest, test_server_port + *p) <= 0)
+		test_error("failed to connect()");
+}
+
+static void client_addr_setup(int sk, union tcp_addr taddr)
+{
+#ifdef IPV6_TEST
+	struct sockaddr_in6 addr = {
+		.sin6_family	= AF_INET6,
+		.sin6_port	= 0,
+		.sin6_addr	= taddr.a6,
+	};
+#else
+	struct sockaddr_in addr = {
+		.sin_family	= AF_INET,
+		.sin_port	= 0,
+		.sin_addr	= taddr.a4,
+	};
+#endif
+	int ret;
+
+	ret = ip_addr_add(veth_name, TEST_FAMILY, taddr, TEST_PREFIX);
+	if (ret && ret != -EEXIST)
+		test_error("Failed to add ip address");
+	ret = ip_route_add(veth_name, TEST_FAMILY, taddr, this_ip_dest);
+	if (ret && ret != -EEXIST)
+		test_error("Failed to add route");
+
+	if (bind(sk, &addr, sizeof(addr)))
+		test_error("bind()");
+}
+
+static void bench_connect_client(size_t port_off, struct bench_tests *bt,
+		union tcp_addr *ips, size_t ips_nr, bool rand_order)
+{
+	struct bench_stats *con;
+	union tcp_addr *p;
+	size_t i;
+
+	if (rand_order)
+		con = &bt->connect_rand_key;
+	else
+		con = &bt->connect_last_key;
+
+	p = (union tcp_addr *)&ips[0];
+
+	for (i = 0; i < BENCH_NR_ITERS; i++) {
+		int sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+
+		if (sk < 0)
+			test_error("socket()");
+
+		client_addr_setup(sk, *p);
+		if (test_add_key(sk, DEFAULT_TEST_PASSWORD, this_ip_dest,
+				 -1, 100, 100))
+			test_error("setsockopt(TCP_AO_ADD_KEY)");
+
+		synchronize_threads();
+
+		measure_call(con, connect_client, sk, (void *)&port_off);
+
+		close(sk);
+
+		/*
+		 * Slowest for FILO-linked-list:
+		 * on (i) iteration removing ips[i] element. When it gets
+		 * added to the list back - it becomes first to fetch, so
+		 * on (i + 1) iteration go to ips[i + 1] element.
+		 */
+		if (rand_order)
+			p = (union tcp_addr *)&ips[rand() % ips_nr];
+		else
+			p = (union tcp_addr *)&ips[i % ips_nr];
+	}
+}
+
+static void *client_fn(void *arg)
+{
+	size_t i;
+
+	for (i = 0; i < ARRAY_SIZE(nr_keys); i++) {
+		struct bench_tests *bt = &bench_results[i];
+
+		synchronize_threads();
+		bench_connect_client(i, bt, test_ips, nr_keys[i], false);
+		test_print_stats("Connect: worst case",
+				nr_keys[i], &bt->connect_last_key);
+
+		bench_connect_client(i, bt, test_ips, nr_keys[i], false);
+		test_print_stats("Connect: random-search",
+				nr_keys[i], &bt->connect_last_key);
+	}
+	synchronize_threads();
+	return NULL;
+}
+
+int main(int argc, char *argv[])
+{
+	test_init(30, server_fn, client_fn);
+	return 0;
+}
diff --git a/tools/testing/selftests/net/tcp_ao/connect-deny.c b/tools/testing/selftests/net/tcp_ao/connect-deny.c
new file mode 100644
index 000000000000..185a2f6e5ff3
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/connect-deny.c
@@ -0,0 +1,264 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Author: Dmitry Safonov <dima@arista.com> */
+#include <inttypes.h>
+#include "aolib.h"
+
+#define fault(type)	(inj == FAULT_ ## type)
+
+static inline int test_add_key_maclen(int sk, const char *key, uint8_t maclen,
+				      union tcp_addr in_addr, uint8_t prefix,
+				      uint8_t sndid, uint8_t rcvid)
+{
+	struct tcp_ao_add tmp = {};
+	int err;
+
+	if (prefix > DEFAULT_TEST_PREFIX)
+		prefix = DEFAULT_TEST_PREFIX;
+
+	err = test_prepare_key(&tmp, DEFAULT_TEST_ALGO, in_addr, false, false,
+			       prefix, 0, sndid, rcvid, maclen,
+			       0, strlen(key), key);
+	if (err)
+		return err;
+
+	err = setsockopt(sk, IPPROTO_TCP, TCP_AO_ADD_KEY, &tmp, sizeof(tmp));
+	if (err < 0)
+		return -errno;
+
+	return test_verify_socket_key(sk, &tmp);
+}
+
+static void try_accept(const char *tst_name, unsigned int port, const char *pwd,
+		       union tcp_addr addr, uint8_t prefix,
+		       uint8_t sndid, uint8_t rcvid, uint8_t maclen,
+		       const char *cnt_name, test_cnt cnt_expected,
+		       fault_t inj)
+{
+	struct tcp_ao_counters ao_cnt1, ao_cnt2;
+	uint64_t before_cnt = 0, after_cnt = 0; /* silence GCC */
+	int lsk, err, sk = 0;
+	time_t timeout;
+
+	lsk = test_listen_socket(this_ip_addr, port, 1);
+
+	if (pwd && test_add_key_maclen(lsk, pwd, maclen, addr, prefix, sndid, rcvid))
+		test_error("setsockopt(TCP_AO_ADD_KEY)");
+
+	if (cnt_name)
+		before_cnt = netstat_get_one(cnt_name, NULL);
+	if (pwd && test_get_tcp_ao_counters(lsk, &ao_cnt1))
+		test_error("test_get_tcp_ao_counters()");
+
+	synchronize_threads(); /* preparations done */
+
+	timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
+	err = test_wait_fd(lsk, timeout, 0);
+	if (err == -ETIMEDOUT) {
+		if (!fault(TIMEOUT))
+			test_fail("timed out for accept()");
+	} else if (err < 0) {
+		test_error("test_wait_fd()");
+	} else {
+		if (fault(TIMEOUT))
+			test_fail("ready to accept");
+
+		sk = accept(lsk, NULL, NULL);
+		if (sk < 0) {
+			test_error("accept()");
+		} else {
+			if (fault(TIMEOUT))
+				test_fail("%s: accepted", tst_name);
+		}
+	}
+
+	if (pwd && test_get_tcp_ao_counters(lsk, &ao_cnt2))
+		test_error("test_get_tcp_ao_counters()");
+
+	close(lsk);
+	if (pwd)
+		test_tcp_ao_counters_cmp(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected);
+
+	if (!cnt_name)
+		goto out;
+
+	after_cnt = netstat_get_one(cnt_name, NULL);
+
+	if (after_cnt <= before_cnt) {
+		test_fail("%s: %s counter did not increase: %zu <= %zu",
+				tst_name, cnt_name, after_cnt, before_cnt);
+	} else {
+		test_ok("%s: counter %s increased %zu => %zu",
+			tst_name, cnt_name, before_cnt, after_cnt);
+	}
+
+out:
+	synchronize_threads(); /* close() */
+	if (sk > 0)
+		close(sk);
+}
+
+static void *server_fn(void *arg)
+{
+	union tcp_addr wrong_addr, network_addr;
+	unsigned int port = test_server_port;
+
+	if (inet_pton(TEST_FAMILY, TEST_WRONG_IP, &wrong_addr) != 1)
+		test_error("Can't convert ip address %s", TEST_WRONG_IP);
+
+	try_accept("Non-AO server + AO client", port++, NULL,
+		   this_ip_dest, -1, 100, 100, 0,
+		   "TCPAOKeyNotFound", 0, FAULT_TIMEOUT);
+
+	try_accept("AO server + Non-AO client", port++, DEFAULT_TEST_PASSWORD,
+		   this_ip_dest, -1, 100, 100, 0,
+		   "TCPAORequired", TEST_CNT_AO_REQUIRED, FAULT_TIMEOUT);
+
+	try_accept("Wrong password", port++, "something that is not DEFAULT_TEST_PASSWORD",
+		   this_ip_dest, -1, 100, 100, 0,
+		   "TCPAOBad", TEST_CNT_BAD, FAULT_TIMEOUT);
+
+	try_accept("Wrong rcv id", port++, DEFAULT_TEST_PASSWORD,
+		   this_ip_dest, -1, 100, 101, 0,
+		   "TCPAOKeyNotFound", TEST_CNT_AO_KEY_NOT_FOUND, FAULT_TIMEOUT);
+
+	try_accept("Wrong snd id", port++, DEFAULT_TEST_PASSWORD,
+		   this_ip_dest, -1, 101, 100, 0,
+		   "TCPAOGood", TEST_CNT_GOOD, FAULT_TIMEOUT);
+
+	try_accept("Different maclen", port++, DEFAULT_TEST_PASSWORD,
+		   this_ip_dest, -1, 100, 100, 8,
+		   "TCPAOBad", TEST_CNT_BAD, FAULT_TIMEOUT);
+
+	try_accept("Server: Wrong addr", port++, DEFAULT_TEST_PASSWORD,
+		   wrong_addr, -1, 100, 100, 0,
+		   "TCPAOKeyNotFound", TEST_CNT_AO_KEY_NOT_FOUND, FAULT_TIMEOUT);
+
+	try_accept("Client: Wrong addr", port++, NULL,
+		   this_ip_dest, -1, 100, 100, 0, NULL, 0, FAULT_TIMEOUT);
+
+	try_accept("rcv id != snd id", port++, DEFAULT_TEST_PASSWORD,
+		   this_ip_dest, -1, 200, 100, 0,
+		   "TCPAOGood", TEST_CNT_GOOD, 0);
+
+	if (inet_pton(TEST_FAMILY, TEST_NETWORK, &network_addr) != 1)
+		test_error("Can't convert ip address %s", TEST_NETWORK);
+
+	try_accept("Server: prefix match", port++, DEFAULT_TEST_PASSWORD,
+		   network_addr, 16, 100, 100, 0,
+		   "TCPAOGood", TEST_CNT_GOOD, 0);
+
+	try_accept("Client: prefix match", port++, DEFAULT_TEST_PASSWORD,
+		   this_ip_dest, -1, 100, 100, 0,
+		   "TCPAOGood", TEST_CNT_GOOD, 0);
+
+	/* client exits */
+	synchronize_threads();
+	return NULL;
+}
+
+static void try_connect(const char *tst_name, unsigned int port,
+			const char *pwd, union tcp_addr addr, uint8_t prefix,
+			uint8_t sndid, uint8_t rcvid,
+			test_cnt cnt_expected, fault_t inj)
+{
+	struct tcp_ao_counters ao_cnt1, ao_cnt2;
+	time_t timeout;
+	int sk, ret;
+
+	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+	if (sk < 0)
+		test_error("socket()");
+
+	if (pwd && test_add_key(sk, pwd, addr, prefix, sndid, rcvid))
+		test_error("setsockopt(TCP_AO_ADD_KEY)");
+
+	if (pwd && test_get_tcp_ao_counters(sk, &ao_cnt1))
+		test_error("test_get_tcp_ao_counters()");
+
+	synchronize_threads(); /* preparations done */
+
+	timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
+	ret = _test_connect_socket(sk, this_ip_dest, port, timeout);
+
+	if (ret < 0) {
+		if (fault(KEYREJECT) && ret == -EKEYREJECTED) {
+			test_ok("%s: connect() was prevented", tst_name);
+		} else if (ret == -ETIMEDOUT && fault(TIMEOUT)) {
+			test_ok("%s", tst_name);
+		} else if (ret == -ECONNREFUSED &&
+				(fault(TIMEOUT) || fault(KEYREJECT))) {
+			test_ok("%s: refused to connect", tst_name);
+		} else {
+			test_error("%s: connect() returned %d", tst_name, ret);
+		}
+		goto out;
+	}
+
+	if (fault(TIMEOUT) || fault(KEYREJECT))
+		test_fail("%s: connected", tst_name);
+	else
+		test_ok("%s: connected", tst_name);
+	if (pwd && ret > 0) {
+		if (test_get_tcp_ao_counters(sk, &ao_cnt2))
+			test_error("test_get_tcp_ao_counters()");
+		test_tcp_ao_counters_cmp(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected);
+	}
+out:
+	synchronize_threads(); /* close() */
+
+	if (ret > 0)
+		close(sk);
+}
+
+static void *client_fn(void *arg)
+{
+	union tcp_addr wrong_addr, network_addr;
+	unsigned int port = test_server_port;
+
+	if (inet_pton(TEST_FAMILY, TEST_WRONG_IP, &wrong_addr) != 1)
+		test_error("Can't convert ip address %s", TEST_WRONG_IP);
+
+	try_connect("Non-AO server + AO client", port++, DEFAULT_TEST_PASSWORD,
+			this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT);
+
+	try_connect("AO server + Non-AO client", port++, NULL,
+			this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT);
+
+	try_connect("Wrong password", port++, DEFAULT_TEST_PASSWORD,
+			this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT);
+
+	try_connect("Wrong rcv id", port++, DEFAULT_TEST_PASSWORD,
+			this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT);
+
+	try_connect("Wrong snd id", port++, DEFAULT_TEST_PASSWORD,
+			this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT);
+
+	try_connect("Different maclen", port++, DEFAULT_TEST_PASSWORD,
+			this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT);
+
+	try_connect("Server: Wrong addr", port++, DEFAULT_TEST_PASSWORD,
+			this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT);
+
+	try_connect("Client: Wrong addr", port++, DEFAULT_TEST_PASSWORD,
+			wrong_addr, -1, 100, 100, 0, FAULT_KEYREJECT);
+
+	try_connect("rcv id != snd id", port++, DEFAULT_TEST_PASSWORD,
+			this_ip_dest, -1, 100, 200, TEST_CNT_GOOD, 0);
+
+	if (inet_pton(TEST_FAMILY, TEST_NETWORK, &network_addr) != 1)
+		test_error("Can't convert ip address %s", TEST_NETWORK);
+
+	try_connect("Server: prefix match", port++, DEFAULT_TEST_PASSWORD,
+			this_ip_dest, -1, 100, 100, TEST_CNT_GOOD, 0);
+
+	try_connect("Client: prefix match", port++, DEFAULT_TEST_PASSWORD,
+			network_addr, 16, 100, 100, TEST_CNT_GOOD, 0);
+
+	return NULL;
+}
+
+int main(int argc, char *argv[])
+{
+	test_init(21, server_fn, client_fn);
+	return 0;
+}
diff --git a/tools/testing/selftests/net/tcp_ao/connect.c b/tools/testing/selftests/net/tcp_ao/connect.c
new file mode 100644
index 000000000000..81653b47f303
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/connect.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Author: Dmitry Safonov <dima@arista.com> */
+#include <inttypes.h>
+#include "aolib.h"
+
+static void *server_fn(void *arg)
+{
+	int sk, lsk;
+	ssize_t bytes;
+
+	lsk = test_listen_socket(this_ip_addr, test_server_port, 1);
+
+	if (test_add_key(lsk, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100))
+		test_error("setsockopt(TCP_AO_ADD_KEY)");
+	synchronize_threads();
+
+	if (test_wait_fd(lsk, TEST_TIMEOUT_SEC, 0))
+		test_error("test_wait_fd()");
+
+	sk = accept(lsk, NULL, NULL);
+	if (sk < 0)
+		test_error("accept()");
+
+	synchronize_threads();
+
+	bytes = test_server_run(sk, 0, 0);
+
+	test_fail("server served: %zd", bytes);
+	return NULL;
+}
+
+static void *client_fn(void *arg)
+{
+	int sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+	uint64_t before_aogood, after_aogood;
+	const size_t nr_packets = 20;
+	struct netstat *ns_before, *ns_after;
+	struct tcp_ao_counters ao1, ao2;
+
+	if (sk < 0)
+		test_error("socket()");
+
+	if (test_add_key(sk, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100))
+		test_error("setsockopt(TCP_AO_ADD_KEY)");
+
+	synchronize_threads();
+	if (test_connect_socket(sk, this_ip_dest, test_server_port) <= 0)
+		test_error("failed to connect()");
+	synchronize_threads();
+
+	ns_before = netstat_read();
+	before_aogood = netstat_get(ns_before, "TCPAOGood", NULL);
+	if (test_get_tcp_ao_counters(sk, &ao1))
+		test_error("test_get_tcp_ao_counters()");
+
+	if (test_client_verify(sk, 100, nr_packets, TEST_TIMEOUT_SEC)) {
+		test_fail("verify failed");
+		return NULL;
+	}
+
+	ns_after = netstat_read();
+	after_aogood = netstat_get(ns_after, "TCPAOGood", NULL);
+	if (test_get_tcp_ao_counters(sk, &ao2))
+		test_error("test_get_tcp_ao_counters()");
+	netstat_print_diff(ns_before, ns_after);
+	netstat_free(ns_before);
+	netstat_free(ns_after);
+
+	if (nr_packets > (after_aogood - before_aogood)) {
+		test_fail("TCPAOGood counter mismatch: %zu > (%zu - %zu)",
+				nr_packets, after_aogood, before_aogood);
+		return NULL;
+	}
+	if (test_tcp_ao_counters_cmp("connect", &ao1, &ao2, TEST_CNT_GOOD))
+		return NULL;
+
+	test_ok("connect TCPAOGood %" PRIu64 "/%" PRIu64 "/%" PRIu64 " => %" PRIu64 "/%" PRIu64 "/%" PRIu64 ", sent %" PRIu64,
+			before_aogood, ao1.ao_info_pkt_good,
+			ao1.key_cnts[0].pkt_good,
+			after_aogood, ao2.ao_info_pkt_good,
+			ao2.key_cnts[0].pkt_good,
+			nr_packets);
+	return NULL;
+}
+
+int main(int argc, char *argv[])
+{
+	test_init(1, server_fn, client_fn);
+	return 0;
+}
diff --git a/tools/testing/selftests/net/tcp_ao/icmps-accept.c b/tools/testing/selftests/net/tcp_ao/icmps-accept.c
new file mode 120000
index 000000000000..0a5bb85eb260
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/icmps-accept.c
@@ -0,0 +1 @@
+icmps-discard.c
\ No newline at end of file
diff --git a/tools/testing/selftests/net/tcp_ao/icmps-discard.c b/tools/testing/selftests/net/tcp_ao/icmps-discard.c
new file mode 100644
index 000000000000..d69bcba3c929
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/icmps-discard.c
@@ -0,0 +1,449 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Selftest that verifies that incomping ICMPs are ignored,
+ * the TCP connection stays alive, no hard or soft errors get reported
+ * to the usespace and the counter for ignored ICMPs is updated.
+ *
+ * RFC5925, 7.8:
+ * >> A TCP-AO implementation MUST default to ignore incoming ICMPv4
+ * messages of Type 3 (destination unreachable), Codes 2-4 (protocol
+ * unreachable, port unreachable, and fragmentation needed -- ’hard
+ * errors’), and ICMPv6 Type 1 (destination unreachable), Code 1
+ * (administratively prohibited) and Code 4 (port unreachable) intended
+ * for connections in synchronized states (ESTABLISHED, FIN-WAIT-1, FIN-
+ * WAIT-2, CLOSE-WAIT, CLOSING, LAST-ACK, TIME-WAIT) that match MKTs.
+ *
+ * Author: Dmitry Safonov <dima@arista.com>
+ */
+#include <inttypes.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
+#include <linux/ipv6.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+#include <sys/socket.h>
+#include "aolib.h"
+#include "../../../../include/linux/compiler.h"
+
+const size_t packets_nr = 20;
+const size_t packet_size = 100;
+const char *tcpao_icmps	= "TCPAODroppedIcmps";
+
+#ifdef IPV6_TEST
+const char *dst_unreach	= "Icmp6InDestUnreachs";
+const int sk_ip_level	= SOL_IPV6;
+const int sk_recverr	= IPV6_RECVERR;
+#else
+const char *dst_unreach	= "InDestUnreachs";
+const int sk_ip_level	= SOL_IP;
+const int sk_recverr	= IP_RECVERR;
+#endif
+
+/* Server is expected to fail with hard error if ::accept_icmp is set */
+#ifdef TEST_ICMPS_ACCEPT
+# define test_icmps_fail test_ok
+# define test_icmps_ok test_fail
+#else
+# define test_icmps_fail test_fail
+# define test_icmps_ok test_ok
+#endif
+
+static void serve_interfered(int sk)
+{
+	ssize_t test_quota = packet_size * packets_nr * 10;
+	uint64_t dest_unreach_a, dest_unreach_b;
+	uint64_t icmp_ignored_a, icmp_ignored_b;
+	struct tcp_ao_counters ao_cnt1, ao_cnt2;
+	bool counter_not_found;
+	struct netstat *ns_after, *ns_before;
+	ssize_t bytes;
+
+	ns_before = netstat_read();
+	dest_unreach_a = netstat_get(ns_before, dst_unreach, NULL);
+	icmp_ignored_a = netstat_get(ns_before, tcpao_icmps, NULL);
+	if (test_get_tcp_ao_counters(sk, &ao_cnt1))
+		test_error("test_get_tcp_ao_counters()");
+	bytes = test_server_run(sk, test_quota, 0);
+	ns_after = netstat_read();
+	netstat_print_diff(ns_before, ns_after);
+	dest_unreach_b = netstat_get(ns_after, dst_unreach, NULL);
+	icmp_ignored_b = netstat_get(ns_after, tcpao_icmps,
+					&counter_not_found);
+	if (test_get_tcp_ao_counters(sk, &ao_cnt2))
+		test_error("test_get_tcp_ao_counters()");
+
+	netstat_free(ns_before);
+	netstat_free(ns_after);
+
+	if (dest_unreach_a >= dest_unreach_b) {
+		test_fail("%s counter didn't change: %" PRIu64 " >= %" PRIu64,
+				dst_unreach, dest_unreach_a, dest_unreach_b);
+		return;
+	}
+	test_ok("%s delivered %" PRIu64,
+		dst_unreach, dest_unreach_b - dest_unreach_a);
+	if (bytes < 0)
+		test_icmps_fail("Server failed with %zd: %s", bytes, strerrordesc_np(-bytes));
+	else
+		test_icmps_ok("Server survived %zd bytes of traffic", test_quota);
+	if (counter_not_found) {
+		test_fail("Not found %s counter", tcpao_icmps);
+		return;
+	}
+#ifdef TEST_ICMPS_ACCEPT
+	test_tcp_ao_counters_cmp(NULL, &ao_cnt1, &ao_cnt2, TEST_CNT_GOOD);
+#else
+	test_tcp_ao_counters_cmp(NULL, &ao_cnt1, &ao_cnt2, TEST_CNT_GOOD | TEST_CNT_AO_DROPPED_ICMP);
+#endif
+	if (icmp_ignored_a >= icmp_ignored_b) {
+		test_icmps_fail("%s counter didn't change: %" PRIu64 " >= %" PRIu64,
+				tcpao_icmps, icmp_ignored_a, icmp_ignored_b);
+		return;
+	}
+	test_icmps_ok("ICMPs ignored %" PRIu64, icmp_ignored_b - icmp_ignored_a);
+}
+
+static void *server_fn(void *arg)
+{
+	int val, sk, lsk;
+	bool accept_icmps = false;
+
+	lsk = test_listen_socket(this_ip_addr, test_server_port, 1);
+
+#ifdef TEST_ICMPS_ACCEPT
+	accept_icmps = true;
+#endif
+
+	if (test_set_ao_flags(lsk, false, accept_icmps))
+		test_error("setsockopt(TCP_AO_INFO)");
+
+	if (test_add_key(lsk, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100))
+		test_error("setsockopt(TCP_AO_ADD_KEY)");
+	synchronize_threads();
+
+	if (test_wait_fd(lsk, TEST_TIMEOUT_SEC, 0))
+		test_error("test_wait_fd()");
+
+	sk = accept(lsk, NULL, NULL);
+	if (sk < 0)
+		test_error("accept()");
+
+	/* Fail on hard ip errors, such as dest unreachable (RFC1122) */
+	val = 1;
+	if (setsockopt(sk, sk_ip_level, sk_recverr, &val, sizeof(val)))
+		test_error("setsockopt()");
+
+	synchronize_threads();
+
+	serve_interfered(sk);
+	return NULL;
+}
+
+static size_t packets_sent;
+static size_t icmps_sent;
+
+static uint32_t checksum4_nofold(void *data, size_t len, uint32_t sum)
+{
+	uint16_t *words = data;
+	size_t i;
+
+	for (i = 0; i < len / sizeof(uint16_t); i++)
+		sum += words[i];
+	if (len & 1)
+		sum += ((char *)data)[len - 1];
+	return sum;
+}
+
+static uint16_t checksum4_fold(void *data, size_t len, uint32_t sum)
+{
+	sum = checksum4_nofold(data, len, sum);
+	while (sum > 0xFFFF)
+		sum = (sum & 0xFFFF) + (sum >> 16);
+	return ~sum;
+}
+
+static void set_ip4hdr(struct iphdr *iph, size_t packet_len, int proto,
+		struct sockaddr_in *src, struct sockaddr_in *dst)
+{
+	iph->version	= 4;
+	iph->ihl	= 5;
+	iph->tos	= 0;
+	iph->tot_len	= htons(packet_len);
+	iph->ttl	= 2;
+	iph->protocol	= proto;
+	iph->saddr	= src->sin_addr.s_addr;
+	iph->daddr	= dst->sin_addr.s_addr;
+	iph->check	= checksum4_fold((void *)iph, iph->ihl << 1, 0);
+}
+
+static void icmp_interfere4(uint8_t type, uint8_t code, uint32_t rcv_nxt,
+		struct sockaddr_in *src, struct sockaddr_in *dst)
+{
+	int sk = socket(AF_INET, SOCK_RAW, IPPROTO_RAW);
+	struct {
+		struct iphdr iph;
+		struct icmphdr icmph;
+		struct iphdr iphe;
+		struct {
+			uint16_t sport;
+			uint16_t dport;
+			uint32_t seq;
+		} tcph;
+	} packet = {};
+	size_t packet_len;
+	ssize_t bytes;
+
+	if (sk < 0)
+		test_error("socket(AF_INET, SOCK_RAW, IPPROTO_RAW)");
+
+	packet_len = sizeof(packet);
+	set_ip4hdr(&packet.iph, packet_len, IPPROTO_ICMP, src, dst);
+
+	packet.icmph.type = type;
+	packet.icmph.code = code;
+	if (code == ICMP_FRAG_NEEDED) {
+		randomize_buffer(&packet.icmph.un.frag.mtu,
+				sizeof(packet.icmph.un.frag.mtu));
+	}
+
+	packet_len = sizeof(packet.iphe) + sizeof(packet.tcph);
+	set_ip4hdr(&packet.iphe, packet_len, IPPROTO_TCP, dst, src);
+
+	packet.tcph.sport = dst->sin_port;
+	packet.tcph.dport = src->sin_port;
+	packet.tcph.seq = htonl(rcv_nxt);
+
+	packet_len = sizeof(packet) - sizeof(packet.iph);
+	packet.icmph.checksum = checksum4_fold((void *)&packet.icmph,
+						packet_len, 0);
+
+	bytes = sendto(sk, &packet, sizeof(packet), 0,
+		       (struct sockaddr *)dst, sizeof(*dst));
+	if (bytes != sizeof(packet))
+		test_error("send(): %zd", bytes);
+	icmps_sent++;
+
+	close(sk);
+}
+
+static void set_ip6hdr(struct ipv6hdr *iph, size_t packet_len, int proto,
+		struct sockaddr_in6 *src, struct sockaddr_in6 *dst)
+{
+	iph->version		= 6;
+	iph->payload_len	= htons(packet_len);
+	iph->nexthdr		= proto;
+	iph->hop_limit		= 2;
+	iph->saddr		= src->sin6_addr;
+	iph->daddr		= dst->sin6_addr;
+}
+
+static inline uint16_t csum_fold(uint32_t csum)
+{
+	uint32_t sum = csum;
+
+	sum = (sum & 0xffff) + (sum >> 16);
+	sum = (sum & 0xffff) + (sum >> 16);
+	return (uint16_t)~sum;
+}
+
+static inline uint32_t csum_add(uint32_t csum, uint32_t addend)
+{
+	uint32_t res = csum;
+
+	res += addend;
+	return res + (res < addend);
+}
+
+noinline uint32_t checksum6_nofold(void *data, size_t len, uint32_t sum)
+{
+	uint16_t *words = data;
+	size_t i;
+
+	for (i = 0; i < len / sizeof(uint16_t); i++)
+		sum = csum_add(sum, words[i]);
+	if (len & 1)
+		sum = csum_add(sum, ((char *)data)[len - 1]);
+	return sum;
+}
+
+noinline uint16_t icmp6_checksum(struct sockaddr_in6 *src,
+				 struct sockaddr_in6 *dst,
+				 void *ptr, size_t len, uint8_t proto)
+{
+	struct {
+		struct in6_addr saddr;
+		struct in6_addr daddr;
+		uint32_t payload_len;
+		uint8_t zero[3];
+		uint8_t nexthdr;
+	} pseudo_header = {};
+	uint32_t sum;
+
+	pseudo_header.saddr		= src->sin6_addr;
+	pseudo_header.daddr		= dst->sin6_addr;
+	pseudo_header.payload_len	= htonl(len);
+	pseudo_header.nexthdr		= proto;
+
+	sum = checksum6_nofold(&pseudo_header, sizeof(pseudo_header), 0);
+	sum = checksum6_nofold(ptr, len, sum);
+
+	return csum_fold(sum);
+}
+
+static void icmp6_interfere(int type, int code, uint32_t rcv_nxt,
+		struct sockaddr_in6 *src, struct sockaddr_in6 *dst)
+{
+	int sk = socket(AF_INET6, SOCK_RAW, IPPROTO_RAW);
+	struct sockaddr_in6 dst_raw = *dst;
+	struct {
+		struct ipv6hdr iph;
+		struct icmp6hdr icmph;
+		struct ipv6hdr iphe;
+		struct {
+			uint16_t sport;
+			uint16_t dport;
+			uint32_t seq;
+		} tcph;
+	} packet = {};
+	size_t packet_len;
+	ssize_t bytes;
+
+
+	if (sk < 0)
+		test_error("socket(AF_INET6, SOCK_RAW, IPPROTO_RAW)");
+
+	packet_len = sizeof(packet) - sizeof(packet.iph);
+	set_ip6hdr(&packet.iph, packet_len, IPPROTO_ICMPV6, src, dst);
+
+	packet.icmph.icmp6_type = type;
+	packet.icmph.icmp6_code = code;
+
+	packet_len = sizeof(packet.iphe) + sizeof(packet.tcph);
+	set_ip6hdr(&packet.iphe, packet_len, IPPROTO_TCP, dst, src);
+
+	packet.tcph.sport = dst->sin6_port;
+	packet.tcph.dport = src->sin6_port;
+	packet.tcph.seq = htonl(rcv_nxt);
+
+	packet_len = sizeof(packet) - sizeof(packet.iph);
+
+	packet.icmph.icmp6_cksum = icmp6_checksum(src, dst,
+			(void *)&packet.icmph, packet_len, IPPROTO_ICMPV6);
+
+	dst_raw.sin6_port = htons(IPPROTO_RAW);
+	bytes = sendto(sk, &packet, sizeof(packet), 0,
+		       (struct sockaddr *)&dst_raw, sizeof(dst_raw));
+	if (bytes != sizeof(packet))
+		test_error("send(): %zd", bytes);
+	icmps_sent++;
+
+	close(sk);
+}
+
+static uint32_t get_rcv_nxt(int sk)
+{
+	int val = TCP_REPAIR_ON;
+	uint32_t ret;
+	socklen_t sz = sizeof(ret);
+
+	if (setsockopt(sk, SOL_TCP, TCP_REPAIR, &val, sizeof(val)))
+		test_error("setsockopt(TCP_REPAIR)");
+	val = TCP_RECV_QUEUE;
+	if (setsockopt(sk, SOL_TCP, TCP_REPAIR_QUEUE, &val, sizeof(val)))
+		test_error("setsockopt(TCP_REPAIR_QUEUE)");
+	if (getsockopt(sk, SOL_TCP, TCP_QUEUE_SEQ, &ret, &sz))
+		test_error("getsockopt(TCP_QUEUE_SEQ)");
+	val = TCP_REPAIR_OFF_NO_WP;
+	if (setsockopt(sk, SOL_TCP, TCP_REPAIR, &val, sizeof(val)))
+		test_error("setsockopt(TCP_REPAIR)");
+	return ret;
+}
+
+static void icmp_interfere(const size_t nr, uint32_t rcv_nxt, void *src, void *dst)
+{
+	struct sockaddr_in *saddr4 = src;
+	struct sockaddr_in *daddr4 = dst;
+	struct sockaddr_in6 *saddr6 = src;
+	struct sockaddr_in6 *daddr6 = dst;
+	size_t i;
+
+	if (saddr4->sin_family != daddr4->sin_family)
+		test_error("Different address families");
+
+	for (i = 0; i < nr; i++) {
+		if (saddr4->sin_family == AF_INET) {
+			icmp_interfere4(ICMP_DEST_UNREACH, ICMP_PROT_UNREACH,
+					rcv_nxt, saddr4, daddr4);
+			icmp_interfere4(ICMP_DEST_UNREACH, ICMP_PORT_UNREACH,
+					rcv_nxt, saddr4, daddr4);
+			icmp_interfere4(ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+					rcv_nxt, saddr4, daddr4);
+			icmps_sent += 3;
+		} else if (saddr4->sin_family == AF_INET6) {
+			icmp6_interfere(ICMPV6_DEST_UNREACH,
+					ICMPV6_ADM_PROHIBITED,
+					rcv_nxt, saddr6, daddr6);
+			icmp6_interfere(ICMPV6_DEST_UNREACH,
+					ICMPV6_PORT_UNREACH,
+					rcv_nxt, saddr6, daddr6);
+			icmps_sent += 2;
+		} else {
+			test_error("Not ip address family");
+		}
+	}
+}
+
+static void send_interfered(int sk)
+{
+	const unsigned int timeout = TEST_TIMEOUT_SEC;
+	struct sockaddr_in6 src, dst;
+	socklen_t addr_sz;
+
+	addr_sz = sizeof(src);
+	if (getsockname(sk, &src, &addr_sz))
+		test_error("getsockname()");
+	addr_sz = sizeof(dst);
+	if (getpeername(sk, &dst, &addr_sz))
+		test_error("getpeername()");
+
+	while (1) {
+		uint32_t rcv_nxt;
+
+		if (test_client_verify(sk, packet_size, packets_nr, timeout)) {
+			test_fail("client: connection is broken");
+			return;
+		}
+		packets_sent += packets_nr;
+		rcv_nxt = get_rcv_nxt(sk);
+		icmp_interfere(packets_nr, rcv_nxt, (void *)&src, (void *)&dst);
+	}
+}
+
+static void *client_fn(void *arg)
+{
+	int sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+
+	if (sk < 0)
+		test_error("socket()");
+
+	if (test_add_key(sk, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100))
+		test_error("setsockopt(TCP_AO_ADD_KEY)");
+
+	synchronize_threads();
+	if (test_connect_socket(sk, this_ip_dest, test_server_port) <= 0)
+		test_error("failed to connect()");
+	synchronize_threads();
+
+	send_interfered(sk);
+
+	/* Not expecting client to quit */
+	test_fail("client disconnected");
+
+	return NULL;
+}
+
+int main(int argc, char *argv[])
+{
+	test_init(3, server_fn, client_fn);
+	return 0;
+}
diff --git a/tools/testing/selftests/net/tcp_ao/key-management.c b/tools/testing/selftests/net/tcp_ao/key-management.c
new file mode 100644
index 000000000000..c48b4970ca17
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/key-management.c
@@ -0,0 +1,1180 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Author: Dmitry Safonov <dima@arista.com> */
+#include <inttypes.h>
+#include "../../../../include/linux/kernel.h"
+#include "aolib.h"
+
+const size_t nr_packets = 20;
+const size_t msg_len = 100;
+const size_t quota = nr_packets * msg_len;
+union tcp_addr wrong_addr;
+#define SECOND_PASSWORD	"at all times sincere friends of freedom have been rare"
+#define fault(type)	(inj == FAULT_ ## type)
+
+static const int test_vrf_ifindex = 200;
+static const uint8_t test_vrf_tabid = 42;
+static void setup_vrfs(void)
+{
+	int err;
+
+	if (!kernel_config_has(KCONFIG_NET_VRF))
+		return;
+
+	err = add_vrf("ksft-vrf", test_vrf_tabid, test_vrf_ifindex, -1);
+	if (err)
+		test_error("Failed to add a VRF: %d", err);
+
+	err = link_set_up("ksft-vrf");
+	if (err)
+		test_error("Failed to bring up a VRF");
+
+	err = ip_route_add_vrf(veth_name, TEST_FAMILY,
+			       this_ip_addr, this_ip_dest, test_vrf_tabid);
+	if (err)
+		test_error("Failed to add a route to VRF");
+}
+
+
+static int prepare_sk(union tcp_addr *addr, uint8_t sndid, uint8_t rcvid)
+{
+	int sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+
+	if (sk < 0)
+		test_error("socket()");
+
+	if (test_add_key(sk, DEFAULT_TEST_PASSWORD, this_ip_dest,
+			 DEFAULT_TEST_PREFIX, 100, 100))
+		test_error("test_add_key()");
+
+	if (addr && test_add_key(sk, SECOND_PASSWORD, *addr,
+				 DEFAULT_TEST_PREFIX, sndid, rcvid))
+		test_error("test_add_key()");
+
+	return sk;
+}
+
+static int prepare_lsk(union tcp_addr *addr, uint8_t sndid, uint8_t rcvid)
+{
+	int sk = prepare_sk(addr, sndid, rcvid);
+
+	if (listen(sk, 10))
+		test_error("listen()");
+
+	return sk;
+}
+
+static int test_del_key(int sk, uint8_t sndid, uint8_t rcvid, bool async,
+			int current_key, int rnext_key)
+{
+	struct tcp_ao_info_opt ao_info = {};
+	struct tcp_ao_getsockopt key = {};
+	struct tcp_ao_del del = {};
+	sockaddr_af sockaddr;
+	int err;
+
+	tcp_addr_to_sockaddr_in(&del.addr, &this_ip_dest, 0);
+	del.prefix = DEFAULT_TEST_PREFIX;
+	del.sndid = sndid;
+	del.rcvid = rcvid;
+
+	if (current_key >= 0) {
+		del.set_current = 1;
+		del.current_key = (uint8_t)current_key;
+	}
+	if (rnext_key >= 0) {
+		del.set_rnext = 1;
+		del.rnext = (uint8_t)rnext_key;
+	}
+
+	err = setsockopt(sk, IPPROTO_TCP, TCP_AO_DEL_KEY, &del, sizeof(del));
+	if (err < 0)
+		return -errno;
+
+	if (async)
+		return 0;
+
+	tcp_addr_to_sockaddr_in(&sockaddr, &this_ip_dest, 0);
+	err = test_get_one_ao(sk, &key, &sockaddr, sizeof(sockaddr),
+			      DEFAULT_TEST_PREFIX, sndid, rcvid);
+	if (!err)
+		return -EEXIST;
+	if (err != -E2BIG)
+		test_error("getsockopt()");
+	if (current_key < 0 && rnext_key < 0)
+		return 0;
+	if (test_get_ao_info(sk, &ao_info))
+		test_error("getsockopt(TCP_AO_INFO) failed");
+	if (current_key >= 0 && ao_info.current_key != (uint8_t)current_key)
+		return -ENOTRECOVERABLE;
+	if (rnext_key >= 0 && ao_info.rnext != (uint8_t)rnext_key)
+		return -ENOTRECOVERABLE;
+	return 0;
+}
+
+static void try_delete_key(char *tst_name, int sk, uint8_t sndid, uint8_t rcvid,
+			   bool async, int current_key, int rnext_key,
+			   fault_t inj)
+{
+	int err;
+
+	err = test_del_key(sk, sndid, rcvid, async, current_key, rnext_key);
+	if ((err == -EBUSY && fault(BUSY)) || (err == -EINVAL && fault(CURRNEXT))) {
+		test_ok("%s: key deletion was prevented", tst_name);
+		return;
+	}
+	if (err && fault(FIXME)) {
+		test_xfail("%s: failed to delete the key %u:%u %d",
+			   tst_name, sndid, rcvid, err);
+		return;
+	}
+	if (!err) {
+		if (fault(BUSY) || fault(CURRNEXT)) {
+			test_fail("%s: the key was deleted %u:%u %d", tst_name,
+				  sndid, rcvid, err);
+		} else {
+			test_ok("%s: the key was deleted", tst_name);
+		}
+		return;
+	}
+	test_fail("%s: can't delete the key %u:%u %d", tst_name, sndid, rcvid, err);
+}
+
+static int test_set_key(int sk, int current_keyid, int rnext_keyid)
+{
+	struct tcp_ao_info_opt ao_info = {};
+	int err;
+
+	if (current_keyid >= 0) {
+		ao_info.set_current = 1;
+		ao_info.current_key = (uint8_t)current_keyid;
+	}
+	if (rnext_keyid >= 0) {
+		ao_info.set_rnext = 1;
+		ao_info.rnext = (uint8_t)rnext_keyid;
+	}
+
+	err = test_set_ao_info(sk, &ao_info);
+	if (err)
+		return err;
+	if (test_get_ao_info(sk, &ao_info))
+		test_error("getsockopt(TCP_AO_INFO) failed");
+	if (current_keyid >= 0 && ao_info.current_key != (uint8_t)current_keyid)
+		return -ENOTRECOVERABLE;
+	if (rnext_keyid >= 0 && ao_info.rnext != (uint8_t)rnext_keyid)
+		return -ENOTRECOVERABLE;
+	return 0;
+}
+
+static int test_add_current_rnext_key(int sk, const char *key, uint8_t keyflags,
+				      union tcp_addr in_addr, uint8_t prefix,
+				      bool set_current, bool set_rnext,
+				      uint8_t sndid, uint8_t rcvid)
+{
+	struct tcp_ao_add tmp = {};
+	int err;
+
+	err = test_prepare_key(&tmp, DEFAULT_TEST_ALGO, in_addr,
+			       set_current, set_rnext,
+			       prefix, 0, sndid, rcvid, 0, keyflags,
+			       strlen(key), key);
+	if (err)
+		return err;
+
+
+	err = setsockopt(sk, IPPROTO_TCP, TCP_AO_ADD_KEY, &tmp, sizeof(tmp));
+	if (err < 0)
+		return -errno;
+
+	return test_verify_socket_key(sk, &tmp);
+}
+
+static int __try_add_current_rnext_key(int sk, const char *key, uint8_t keyflags,
+				       union tcp_addr in_addr, uint8_t prefix,
+				       bool set_current, bool set_rnext,
+				       uint8_t sndid, uint8_t rcvid)
+{
+	struct tcp_ao_info_opt ao_info = {};
+	int err;
+
+	err = test_add_current_rnext_key(sk, key, keyflags, in_addr, prefix,
+					 set_current, set_rnext, sndid, rcvid);
+	if (err)
+		return err;
+
+	if (test_get_ao_info(sk, &ao_info))
+		test_error("getsockopt(TCP_AO_INFO) failed");
+	if (set_current && ao_info.current_key != sndid)
+		return -ENOTRECOVERABLE;
+	if (set_rnext && ao_info.rnext != rcvid)
+		return -ENOTRECOVERABLE;
+	return 0;
+}
+
+static void try_add_current_rnext_key(char *tst_name, int sk, const char *key,
+				     uint8_t keyflags,
+				     union tcp_addr in_addr, uint8_t prefix,
+				     bool set_current, bool set_rnext,
+				     uint8_t sndid, uint8_t rcvid, fault_t inj)
+{
+	int err;
+
+	err = __try_add_current_rnext_key(sk, key, keyflags, in_addr, prefix,
+					  set_current, set_rnext, sndid, rcvid);
+	if (!err && !fault(CURRNEXT)) {
+		test_ok("%s", tst_name);
+		return;
+	}
+	if (err == -EINVAL && fault(CURRNEXT)) {
+		test_ok("%s", tst_name);
+		return;
+	}
+	test_fail("%s", tst_name);
+}
+
+static void check_closed_socket(void)
+{
+	int sk;
+
+	sk = prepare_sk(&this_ip_dest, 200, 200);
+	try_delete_key("closed socket, delete a key", sk, 200, 200, 0, -1, -1, 0);
+	try_delete_key("closed socket, delete all keys", sk, 100, 100, 0, -1, -1, 0);
+	close(sk);
+
+	sk = prepare_sk(&this_ip_dest, 200, 200);
+	if (test_set_key(sk, 100, 200))
+		test_error("failed to set current/rnext keys");
+	try_delete_key("closed socket, delete current key", sk, 100, 100, 0, -1, -1, FAULT_BUSY);
+	try_delete_key("closed socket, delete rnext key", sk, 200, 200, 0, -1, -1, FAULT_BUSY);
+	close(sk);
+
+	sk = prepare_sk(&this_ip_dest, 200, 200);
+	if (test_add_key(sk, "Glory to heros!", this_ip_dest,
+			 DEFAULT_TEST_PREFIX, 10, 11))
+		test_error("test_add_key()");
+	if (test_add_key(sk, "Glory to Ukraine!", this_ip_dest,
+			 DEFAULT_TEST_PREFIX, 12, 13))
+		test_error("test_add_key()");
+	try_delete_key("closed socket, delete a key + set current/rnext", sk, 100, 100, 0, 10, 13, 0);
+	try_delete_key("closed socket, force-delete current key", sk, 10, 11, 0, 200, -1, 0);
+	try_delete_key("closed socket, force-delete rnext key", sk, 12, 13, 0, -1, 200, 0);
+	try_delete_key("closed socket, delete current+rnext key", sk, 200, 200, 0, -1, -1, FAULT_BUSY);
+	close(sk);
+
+	sk = prepare_sk(&this_ip_dest, 200, 200);
+	if (test_set_key(sk, 100, 200))
+		test_error("failed to set current/rnext keys");
+	try_add_current_rnext_key("closed socket, add + change current key",
+				  sk, "Laaaa! Lalala-la-la-lalala...", 0,
+				  this_ip_dest, DEFAULT_TEST_PREFIX,
+				  true, false, 10, 20, 0);
+	try_add_current_rnext_key("closed socket, add + change rnext key",
+				  sk, "Laaaa! Lalala-la-la-lalala...", 0,
+				  this_ip_dest, DEFAULT_TEST_PREFIX,
+				  false, true, 20, 10, 0);
+	close(sk);
+}
+
+static void assert_no_current_rnext(const char *tst_msg, int sk)
+{
+	struct tcp_ao_info_opt ao_info = {};
+
+	if (test_get_ao_info(sk, &ao_info))
+		test_error("getsockopt(TCP_AO_INFO) failed");
+
+	errno = 0;
+	if (ao_info.set_current || ao_info.set_rnext) {
+		test_xfail("%s: the socket has current/rnext keys: %d:%d",
+			   tst_msg,
+			   (ao_info.set_current) ? ao_info.current_key : -1,
+			   (ao_info.set_rnext) ? ao_info.rnext : -1);
+	} else {
+		test_ok("%s: the socket has no current/rnext keys", tst_msg);
+	}
+}
+
+static void assert_no_tcp_repair(void)
+{
+	struct tcp_ao_repair ao_img = {};
+	socklen_t len = sizeof(ao_img);
+	int sk, err;
+
+	sk = prepare_sk(&this_ip_dest, 200, 200);
+	test_enable_repair(sk);
+	if (listen(sk, 10))
+		test_error("listen()");
+	errno = 0;
+	err = getsockopt(sk, SOL_TCP, TCP_AO_REPAIR, &ao_img, &len);
+	if (err && errno == EPERM)
+		test_ok("listen socket, getsockopt(TCP_AO_REPAIR) is restricted");
+	else
+		test_fail("listen socket, getsockopt(TCP_AO_REPAIR) works");
+	errno = 0;
+	err = setsockopt(sk, SOL_TCP, TCP_AO_REPAIR, &ao_img, sizeof(ao_img));
+	if (err && errno == EPERM)
+		test_ok("listen socket, setsockopt(TCP_AO_REPAIR) is restricted");
+	else
+		test_fail("listen socket, setsockopt(TCP_AO_REPAIR) works");
+	close(sk);
+}
+
+static void check_listen_socket(void)
+{
+	int sk, err;
+
+	sk = prepare_lsk(&this_ip_dest, 200, 200);
+	try_delete_key("listen socket, delete a key", sk, 200, 200, 0, -1, -1, 0);
+	try_delete_key("listen socket, delete all keys", sk, 100, 100, 0, -1, -1, 0);
+	close(sk);
+
+	sk = prepare_lsk(&this_ip_dest, 200, 200);
+	err = test_set_key(sk, 100, -1);
+	if (err == -EINVAL)
+		test_ok("listen socket, setting current key not allowed");
+	else
+		test_fail("listen socket, set current key");
+	err = test_set_key(sk, -1, 200);
+	if (err == -EINVAL)
+		test_ok("listen socket, setting rnext key not allowed");
+	else
+		test_fail("listen socket, set rnext key");
+	close(sk);
+
+	sk = prepare_sk(&this_ip_dest, 200, 200);
+	if (test_set_key(sk, 100, 200))
+		test_error("failed to set current/rnext keys");
+	if (listen(sk, 10))
+		test_error("listen()");
+	assert_no_current_rnext("listen() after current/rnext keys set", sk);
+	try_delete_key("listen socket, delete current key from before listen()", sk, 100, 100, 0, -1, -1, FAULT_FIXME);
+	try_delete_key("listen socket, delete rnext key from before listen()", sk, 200, 200, 0, -1, -1, FAULT_FIXME);
+	close(sk);
+
+	assert_no_tcp_repair();
+
+	sk = prepare_lsk(&this_ip_dest, 200, 200);
+	if (test_add_key(sk, "Glory to heros!", this_ip_dest,
+			 DEFAULT_TEST_PREFIX, 10, 11))
+		test_error("test_add_key()");
+	if (test_add_key(sk, "Glory to Ukraine!", this_ip_dest,
+			 DEFAULT_TEST_PREFIX, 12, 13))
+		test_error("test_add_key()");
+	try_delete_key("listen socket, delete a key + set current/rnext", sk,
+		       100, 100, 0, 10, 13, FAULT_CURRNEXT);
+	try_delete_key("listen socket, force-delete current key", sk,
+		       10, 11, 0, 200, -1, FAULT_CURRNEXT);
+	try_delete_key("listen socket, force-delete rnext key", sk,
+		       12, 13, 0, -1, 200, FAULT_CURRNEXT);
+	try_delete_key("listen socket, delete a key", sk,
+		       200, 200, 0, -1, -1, 0);
+	close(sk);
+
+	sk = prepare_lsk(&this_ip_dest, 200, 200);
+	try_add_current_rnext_key("listen socket, add + change current key",
+				  sk, "Laaaa! Lalala-la-la-lalala...", 0,
+				  this_ip_dest, DEFAULT_TEST_PREFIX,
+				  true, false, 10, 20, FAULT_CURRNEXT);
+	try_add_current_rnext_key("listen socket, add + change rnext key",
+				  sk, "Laaaa! Lalala-la-la-lalala...", 0,
+				  this_ip_dest, DEFAULT_TEST_PREFIX,
+				  false, true, 20, 10, FAULT_CURRNEXT);
+	close(sk);
+}
+
+static const char *fips_fpath = "/proc/sys/crypto/fips_enabled";
+static bool is_fips_enabled(void)
+{
+	static int fips_checked = -1;
+	FILE *fenabled;
+	int enabled;
+
+	if (fips_checked >= 0)
+		return !!fips_checked;
+	if (access(fips_fpath, R_OK)) {
+		if (errno != ENOENT)
+			test_error("Can't open %s", fips_fpath);
+		fips_checked = 0;
+		return false;
+	}
+	fenabled = fopen(fips_fpath, "r");
+	if (!fenabled)
+		test_error("Can't open %s", fips_fpath);
+	if (fscanf(fenabled, "%d", &enabled) != 1)
+		test_error("Can't read from %s", fips_fpath);
+	fclose(fenabled);
+	fips_checked = !!enabled;
+	return !!fips_checked;
+}
+
+struct test_key {
+	char password[TCP_AO_MAXKEYLEN];
+	const char *alg;
+	unsigned int len;
+	uint8_t client_keyid;
+	uint8_t server_keyid;
+	uint8_t maclen;
+	uint8_t matches_client		: 1,
+		matches_server		: 1,
+		matches_vrf		: 1,
+		is_current		: 1,
+		is_rnext		: 1,
+		used_on_handshake	: 1,
+		used_after_accept	: 1,
+		used_on_client		: 1;
+};
+
+struct key_collection {
+	unsigned int nr_keys;
+	struct test_key *keys;
+};
+
+static struct key_collection collection;
+
+#define TEST_MAX_MACLEN		16
+const char *test_algos[] = {
+	"cmac(aes128)",
+	"hmac(sha1)", "hmac(sha512)", "hmac(sha384)", "hmac(sha256)",
+	"hmac(sha224)", "hmac(sha3-512)",
+	/* only if !CONFIG_FIPS */
+#define TEST_NON_FIPS_ALGOS	2
+	"hmac(rmd160)", "hmac(md5)"
+};
+const unsigned int test_maclens[] = { 1, 4, 12, 16 };
+#define MACLEN_SHIFT		2
+#define ALGOS_SHIFT		4
+
+static unsigned int make_mask(unsigned int shift, unsigned int prev_shift)
+{
+	unsigned int ret = BIT(shift) - 1;
+
+	return ret << prev_shift;
+}
+
+static void init_key_in_collection(unsigned int index, bool randomized)
+{
+	struct test_key *key = &collection.keys[index];
+	unsigned int algos_nr, algos_index;
+
+	/* Same for randomized and non-randomized test flows */
+	key->client_keyid = index;
+	key->server_keyid = 127 + index;
+	key->matches_client = 1;
+	key->matches_server = 1;
+	key->matches_vrf = 1;
+	/* not really even random, but good enough for a test */
+	key->len = rand() % (TCP_AO_MAXKEYLEN - TEST_TCP_AO_MINKEYLEN);
+	key->len += TEST_TCP_AO_MINKEYLEN;
+	randomize_buffer(key->password, key->len);
+
+	if (randomized) {
+		key->maclen = (rand() % TEST_MAX_MACLEN) + 1;
+		algos_index = rand();
+	} else {
+		unsigned int shift = MACLEN_SHIFT;
+
+		key->maclen = test_maclens[index & make_mask(shift, 0)];
+		algos_index = index & make_mask(ALGOS_SHIFT, shift);
+	}
+	algos_nr = ARRAY_SIZE(test_algos);
+	if (is_fips_enabled())
+		algos_nr -= TEST_NON_FIPS_ALGOS;
+	key->alg = test_algos[algos_index % algos_nr];
+}
+
+static int init_default_key_collection(unsigned int nr_keys, bool randomized)
+{
+	size_t key_sz = sizeof(collection.keys[0]);
+
+	if (!nr_keys) {
+		free(collection.keys);
+		collection.keys = NULL;
+		return 0;
+	}
+
+	/*
+	 * All keys have uniq sndid/rcvid and sndid != rcvid in order to
+	 * check for any bugs/issues for different keyids, visible to both
+	 * peers. Keyid == 254 is unused.
+	 */
+	if (nr_keys > 127)
+		test_error("Test requires too many keys, correct the source");
+
+	collection.keys = reallocarray(collection.keys, nr_keys, key_sz);
+	if (!collection.keys)
+		return -ENOMEM;
+
+	memset(collection.keys, 0, nr_keys * key_sz);
+	collection.nr_keys = nr_keys;
+	while (nr_keys--)
+		init_key_in_collection(nr_keys, randomized);
+
+	return 0;
+}
+
+static void test_key_error(const char *msg, struct test_key *key)
+{
+	test_error("%s: key: { %s, %u:%u, %u, %u:%u:%u:%u:%u (%u)}",
+		   msg, key->alg, key->client_keyid, key->server_keyid,
+		   key->maclen, key->matches_client, key->matches_server,
+		   key->matches_vrf, key->is_current, key->is_rnext, key->len);
+}
+
+static int test_add_key_cr(int sk, const char *pwd, unsigned int pwd_len,
+			   union tcp_addr addr, uint8_t vrf,
+			   uint8_t sndid, uint8_t rcvid,
+			   uint8_t maclen, const char *alg,
+			   bool set_current, bool set_rnext)
+{
+	struct tcp_ao_add tmp = {};
+	uint8_t keyflags = 0;
+	int err;
+
+	if (!alg)
+		alg = DEFAULT_TEST_ALGO;
+
+	if (vrf)
+		keyflags |= TCP_AO_KEYF_IFINDEX;
+	err = test_prepare_key(&tmp, alg, addr, set_current, set_rnext,
+			       DEFAULT_TEST_PREFIX, vrf, sndid, rcvid, maclen,
+			       keyflags, pwd_len, pwd);
+	if (err)
+		return err;
+
+	err = setsockopt(sk, IPPROTO_TCP, TCP_AO_ADD_KEY, &tmp, sizeof(tmp));
+	if (err < 0)
+		return -errno;
+
+	return test_verify_socket_key(sk, &tmp);
+}
+
+static void verify_current_rnext(const char *tst, int sk,
+				 int current_keyid, int rnext_keyid)
+{
+	struct tcp_ao_info_opt ao_info = {};
+
+	if (test_get_ao_info(sk, &ao_info))
+		test_error("getsockopt(TCP_AO_INFO) failed");
+
+	errno = 0;
+	if (current_keyid >= 0) {
+		if (!ao_info.set_current)
+			test_fail("%s: the socket doesn't have current key", tst);
+		else if (ao_info.current_key != current_keyid)
+			test_fail("%s: current key is not the expected one %d != %u",
+				  tst, current_keyid, ao_info.current_key);
+		else
+			test_ok("%s: current key %u as expected",
+				tst, ao_info.current_key);
+	}
+	if (rnext_keyid >= 0) {
+		if (!ao_info.set_rnext)
+			test_fail("%s: the socket doesn't have rnext key", tst);
+		else if (ao_info.rnext != rnext_keyid)
+			test_fail("%s: rnext key is not the expected one %d != %u",
+				  tst, rnext_keyid, ao_info.rnext);
+		else
+			test_ok("%s: rnext key %u as expected", tst, ao_info.rnext);
+	}
+}
+
+
+static int key_collection_socket(bool server, unsigned int port)
+{
+	unsigned int i;
+	int sk;
+
+	if (server)
+		sk = test_listen_socket(this_ip_addr, port, 1);
+	else
+		sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+	if (sk < 0)
+		test_error("socket()");
+
+	for (i = 0; i < collection.nr_keys; i++) {
+		struct test_key *key = &collection.keys[i];
+		union tcp_addr *addr = &wrong_addr;
+		uint8_t sndid, rcvid, vrf;
+		bool set_current = false, set_rnext = false;
+
+		if (key->matches_vrf)
+			vrf = 0;
+		else
+			vrf = test_vrf_ifindex;
+		if (server) {
+			if (key->matches_client)
+				addr = &this_ip_dest;
+			sndid = key->server_keyid;
+			rcvid = key->client_keyid;
+		} else {
+			if (key->matches_server)
+				addr = &this_ip_dest;
+			sndid = key->client_keyid;
+			rcvid = key->server_keyid;
+			set_current = key->is_current;
+			set_rnext = key->is_rnext;
+		}
+
+		if (test_add_key_cr(sk, key->password, key->len,
+				    *addr, vrf, sndid, rcvid, key->maclen,
+				    key->alg, set_current, set_rnext))
+			test_key_error("setsockopt(TCP_AO_ADD_KEY)", key);
+		if (set_current || set_rnext)
+			key->used_on_handshake = 1;
+#ifdef DEBUG
+		test_print("%s [%u/%u] key: { %s, %u:%u, %u, %u:%u:%u:%u (%u)}",
+			   server ? "server" : "client", i, collection.nr_keys,
+			   key->alg, rcvid, sndid, key->maclen,
+			   key->matches_client, key->matches_server,
+			   key->is_current, key->is_rnext, key->len);
+#endif
+	}
+	return sk;
+}
+
+static void verify_counters(const char *tst_name, bool is_listen_sk, bool server,
+			    struct tcp_ao_counters *a, struct tcp_ao_counters *b)
+{
+	unsigned int i;
+
+	__test_tcp_ao_counters_cmp(tst_name, a, b, TEST_CNT_GOOD);
+
+	for (i = 0; i < collection.nr_keys; i++) {
+		struct test_key *key = &collection.keys[i];
+		uint8_t sndid, rcvid;
+		bool was_used;
+
+		if (server) {
+			sndid = key->server_keyid;
+			rcvid = key->client_keyid;
+			if (is_listen_sk)
+				was_used = key->used_on_handshake;
+			else
+				was_used = key->used_after_accept;
+		} else {
+			sndid = key->client_keyid;
+			rcvid = key->server_keyid;
+			was_used = key->used_on_client;
+		}
+
+		test_tcp_ao_key_counters_cmp(tst_name, a, b, was_used,
+					     sndid, rcvid);
+	}
+	test_tcp_ao_counters_free(a);
+	test_tcp_ao_counters_free(b);
+	test_ok("%s: passed counters checks", tst_name);
+}
+
+static struct tcp_ao_getsockopt *lookup_key(struct tcp_ao_getsockopt *buf,
+					    size_t len, int sndid, int rcvid)
+{
+	size_t i;
+
+	for (i = 0; i < len; i++) {
+		if (sndid >= 0 && buf[i].sndid != sndid)
+			continue;
+		if (rcvid >= 0 && buf[i].rcvid != rcvid)
+			continue;
+		return &buf[i];
+	}
+	return NULL;
+}
+
+static void verify_keys(const char *tst_name, int sk,
+			bool is_listen_sk, bool server)
+{
+	socklen_t len = sizeof(struct tcp_ao_getsockopt);
+	struct tcp_ao_getsockopt *keys;
+	bool passed_test = true;
+	unsigned int i;
+
+	keys = calloc(collection.nr_keys, len);
+	if (!keys)
+		test_error("calloc()");
+
+	keys->nkeys = collection.nr_keys;
+	keys->get_all = 1;
+
+	if (getsockopt(sk, IPPROTO_TCP, TCP_AO_GET_KEYS, keys, &len)) {
+		free(keys);
+		test_error("getsockopt(TCP_AO_GET_KEYS)");
+	}
+
+	for (i = 0; i < collection.nr_keys; i++) {
+		struct test_key *key = &collection.keys[i];
+		struct tcp_ao_getsockopt *dump_key;
+		bool is_kdf_aes_128_cmac = false;
+		bool is_cmac_aes = false;
+		uint8_t sndid, rcvid;
+		bool matches = false;
+
+		if (server) {
+			if (key->matches_client)
+				matches = true;
+			sndid = key->server_keyid;
+			rcvid = key->client_keyid;
+		} else {
+			if (key->matches_server)
+				matches = true;
+			sndid = key->client_keyid;
+			rcvid = key->server_keyid;
+		}
+		if (!key->matches_vrf)
+			matches = false;
+		/* no keys get removed on the original listener socket */
+		if (is_listen_sk)
+			matches = true;
+
+		dump_key = lookup_key(keys, keys->nkeys, sndid, rcvid);
+		if (matches != !!dump_key) {
+			test_fail("%s: key %u:%u %s%s on the socket",
+				  tst_name, sndid, rcvid,
+				  key->matches_vrf ? "" : "[vrf] ",
+				  matches ? "disappeared" : "yet present");
+			passed_test = false;
+			goto out;
+		}
+		if (!dump_key)
+			continue;
+
+		if (!strcmp("cmac(aes128)", key->alg)) {
+			is_kdf_aes_128_cmac = (key->len != 16);
+			is_cmac_aes = true;
+		}
+
+		if (is_cmac_aes) {
+			if (strcmp(dump_key->alg_name, "cmac(aes)")) {
+				test_fail("%s: key %u:%u cmac(aes) has unexpected alg %s",
+					  tst_name, sndid, rcvid,
+					  dump_key->alg_name);
+				passed_test = false;
+				continue;
+			}
+		} else if (strcmp(dump_key->alg_name, key->alg)) {
+			test_fail("%s: key %u:%u has unexpected alg %s != %s",
+				  tst_name, sndid, rcvid,
+				  dump_key->alg_name, key->alg);
+			passed_test = false;
+			continue;
+		}
+		if (is_kdf_aes_128_cmac) {
+			if (dump_key->keylen != 16) {
+				test_fail("%s: key %u:%u cmac(aes128) has unexpected len %u",
+					  tst_name, sndid, rcvid,
+					  dump_key->keylen);
+				continue;
+			}
+		} else if (dump_key->keylen != key->len) {
+			test_fail("%s: key %u:%u changed password len %u != %u",
+				  tst_name, sndid, rcvid,
+				  dump_key->keylen, key->len);
+			passed_test = false;
+			continue;
+		}
+		if (!is_kdf_aes_128_cmac &&
+		    memcmp(dump_key->key, key->password, key->len)) {
+			test_fail("%s: key %u:%u has different password",
+				  tst_name, sndid, rcvid);
+			passed_test = false;
+			continue;
+		}
+		if (dump_key->maclen != key->maclen) {
+			test_fail("%s: key %u:%u changed maclen %u != %u",
+				  tst_name, sndid, rcvid,
+				  dump_key->maclen, key->maclen);
+			passed_test = false;
+			continue;
+		}
+	}
+
+	if (passed_test)
+		test_ok("%s: The socket keys are consistent with the expectations",
+			tst_name);
+out:
+	free(keys);
+}
+
+static int start_server(const char *tst_name, unsigned int port, size_t quota,
+			struct tcp_ao_counters *begin,
+			unsigned int current_index, unsigned int rnext_index)
+{
+	struct tcp_ao_counters lsk_c1, lsk_c2;
+	ssize_t bytes;
+	int sk, lsk;
+
+	synchronize_threads(); /* 1: key collection initialized */
+	lsk = key_collection_socket(true, port);
+	if (test_get_tcp_ao_counters(lsk, &lsk_c1))
+		test_error("test_get_tcp_ao_counters()");
+	synchronize_threads(); /* 2: MKTs added => connect() */
+	if (test_wait_fd(lsk, TEST_TIMEOUT_SEC, 0))
+		test_error("test_wait_fd()");
+
+	sk = accept(lsk, NULL, NULL);
+	if (sk < 0)
+		test_error("accept()");
+	if (test_get_tcp_ao_counters(sk, begin))
+		test_error("test_get_tcp_ao_counters()");
+
+	synchronize_threads(); /* 3: accepted => send data */
+	if (test_get_tcp_ao_counters(lsk, &lsk_c2))
+		test_error("test_get_tcp_ao_counters()");
+	verify_keys(tst_name, lsk, true, true);
+	close(lsk);
+
+	bytes = test_server_run(sk, quota, TEST_TIMEOUT_SEC);
+	if (bytes != quota)
+		test_fail("%s: server served: %zd", tst_name, bytes);
+	else
+		test_ok("%s: server alive", tst_name);
+
+	verify_counters(tst_name, true, true, &lsk_c1, &lsk_c2);
+
+	return sk;
+}
+
+static void end_server(const char *tst_name, int sk,
+		       struct tcp_ao_counters *begin)
+{
+	struct tcp_ao_counters end;
+
+	if (test_get_tcp_ao_counters(sk, &end))
+		test_error("test_get_tcp_ao_counters()");
+	verify_keys(tst_name, sk, false, true);
+
+	synchronize_threads(); /* 4: verified => closed */
+	close(sk);
+
+	verify_counters(tst_name, true, false, begin, &end);
+	synchronize_threads(); /* 5: counters */
+}
+
+static void try_server_run(const char *tst_name, unsigned int port, size_t quota,
+			   unsigned int current_index, unsigned int rnext_index)
+{
+	struct tcp_ao_counters tmp;
+	int sk;
+
+	sk = start_server(tst_name, port, quota, &tmp,
+			  current_index, rnext_index);
+	end_server(tst_name, sk, &tmp);
+}
+
+static void server_rotations(const char *tst_name, unsigned int port,
+			     size_t quota, unsigned int rotations,
+			     unsigned int current_index, unsigned int rnext_index)
+{
+	struct tcp_ao_counters tmp;
+	unsigned int i;
+	int sk;
+
+	sk = start_server(tst_name, port, quota, &tmp,
+			  current_index, rnext_index);
+
+	for (i = current_index + 1; rotations > 0; i++, rotations--) {
+		ssize_t bytes;
+
+		if (i >= collection.nr_keys)
+			i = 0;
+		bytes = test_server_run(sk, quota, TEST_TIMEOUT_SEC);
+		if (bytes != quota) {
+			test_fail("%s: server served: %zd", tst_name, bytes);
+			return;
+		}
+		verify_current_rnext(tst_name, sk,
+				     collection.keys[i].server_keyid, -1);
+		synchronize_threads(); /* verify current/rnext */
+	}
+	end_server(tst_name, sk, &tmp);
+}
+
+static int run_client(const char *tst_name, unsigned int port,
+		      unsigned int nr_keys, int current_index, int rnext_index,
+		      struct tcp_ao_counters *before,
+		      const size_t msg_sz, const size_t msg_nr)
+{
+	int sk;
+
+	synchronize_threads(); /* 1: key collection initialized */
+	sk = key_collection_socket(false, port);
+
+	if (current_index >= 0 || rnext_index >= 0) {
+		int sndid = -1, rcvid = -1;
+
+		if (current_index >= 0)
+			sndid = collection.keys[current_index].client_keyid;
+		if (rnext_index >= 0)
+			rcvid = collection.keys[rnext_index].server_keyid;
+		if (test_set_key(sk, sndid, rcvid))
+			test_error("failed to set current/rnext keys");
+	}
+	if (before && test_get_tcp_ao_counters(sk, before))
+		test_error("test_get_tcp_ao_counters()");
+
+	synchronize_threads(); /* 2: MKTs added => connect() */
+	if (test_connect_socket(sk, this_ip_dest, port++) <= 0)
+		test_error("failed to connect()");
+	if (current_index < 0)
+		current_index = nr_keys - 1;
+	if (rnext_index < 0)
+		rnext_index = nr_keys - 1;
+	collection.keys[current_index].used_on_handshake = 1;
+	collection.keys[rnext_index].used_after_accept = 1;
+	collection.keys[rnext_index].used_on_client = 1;
+
+	synchronize_threads(); /* 3: accepted => send data */
+	if (test_client_verify(sk, msg_sz, msg_nr, TEST_TIMEOUT_SEC)) {
+		test_fail("verify failed");
+		close(sk);
+		if (before)
+			test_tcp_ao_counters_free(before);
+		return -1;
+	}
+
+	return sk;
+}
+
+static int start_client(const char *tst_name, unsigned int port,
+			unsigned int nr_keys, int current_index, int rnext_index,
+			struct tcp_ao_counters *before,
+			const size_t msg_sz, const size_t msg_nr)
+{
+	if (init_default_key_collection(nr_keys, true))
+		test_error("Failed to init the key collection");
+
+	return run_client(tst_name, port, nr_keys, current_index,
+			  rnext_index, before, msg_sz, msg_nr);
+}
+
+static void end_client(const char *tst_name, int sk, unsigned int nr_keys,
+		       int current_index, int rnext_index,
+		       struct tcp_ao_counters *start)
+{
+	struct tcp_ao_counters end;
+
+	/* Some application may become dependent on this kernel choice */
+	if (current_index < 0)
+		current_index = nr_keys - 1;
+	if (rnext_index < 0)
+		rnext_index = nr_keys - 1;
+	verify_current_rnext(tst_name, sk,
+			     collection.keys[current_index].client_keyid,
+			     collection.keys[rnext_index].server_keyid);
+	if (start && test_get_tcp_ao_counters(sk, &end))
+		test_error("test_get_tcp_ao_counters()");
+	verify_keys(tst_name, sk, false, false);
+	synchronize_threads(); /* 4: verify => closed */
+	close(sk);
+	if (start)
+		verify_counters(tst_name, false, false, start, &end);
+	synchronize_threads(); /* 5: counters */
+}
+
+static void try_unmatched_keys(int sk, int *rnext_index)
+{
+	struct test_key *key;
+	unsigned int i = 0;
+	int err;
+
+	do {
+		key = &collection.keys[i];
+		if (!key->matches_server)
+			break;
+	} while (++i < collection.nr_keys);
+	if (key->matches_server)
+		test_error("all keys on client match the server");
+
+	err = test_add_key_cr(sk, key->password, key->len, wrong_addr,
+			      0, key->client_keyid, key->server_keyid,
+			      key->maclen, key->alg, 0, 0);
+	if (!err) {
+		test_fail("Added a key with non-matching ip-address for established sk");
+		return;
+	}
+	if (err == -EINVAL)
+		test_ok("Can't add a key with non-matching ip-address for established sk");
+	else
+		test_error("Failed to add a key");
+
+	err = test_add_key_cr(sk, key->password, key->len, this_ip_dest,
+			      test_vrf_ifindex,
+			      key->client_keyid, key->server_keyid,
+			      key->maclen, key->alg, 0, 0);
+	if (!err) {
+		test_fail("Added a key with non-matching VRF for established sk");
+		return;
+	}
+	if (err == -EINVAL)
+		test_ok("Can't add a key with non-matching VRF for established sk");
+	else
+		test_error("Failed to add a key");
+
+	for (i = 0; i < collection.nr_keys; i++) {
+		key = &collection.keys[i];
+		if (!key->matches_client)
+			break;
+	}
+	if (key->matches_client)
+		test_error("all keys on server match the client");
+	if (test_set_key(sk, -1, key->server_keyid))
+		test_error("Can't change the current key");
+	if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC))
+		test_fail("verify failed");
+	*rnext_index = i;
+}
+
+static int client_non_matching(const char *tst_name, unsigned int port,
+			       unsigned int nr_keys,
+			       int current_index, int rnext_index,
+			       const size_t msg_sz, const size_t msg_nr)
+{
+	unsigned int i;
+
+	if (init_default_key_collection(nr_keys, true))
+		test_error("Failed to init the key collection");
+
+	for (i = 0; i < nr_keys; i++) {
+		/* key (0, 0) matches */
+		collection.keys[i].matches_client = !!((i + 3) % 4);
+		collection.keys[i].matches_server = !!((i + 2) % 4);
+		if (kernel_config_has(KCONFIG_NET_VRF))
+			collection.keys[i].matches_vrf = !!((i + 1) % 4);
+	}
+
+	return run_client(tst_name, port, nr_keys, current_index,
+			  rnext_index, NULL, msg_sz, msg_nr);
+}
+
+static void check_current_back(const char *tst_name, unsigned int port,
+			       unsigned int nr_keys,
+			       unsigned int current_index, unsigned int rnext_index,
+			       unsigned int rotate_to_index)
+{
+	struct tcp_ao_counters tmp;
+	int sk;
+
+	sk = start_client(tst_name, port, nr_keys, current_index, rnext_index,
+			  &tmp, msg_len, nr_packets);
+	if (sk < 0)
+		return;
+	if (test_set_key(sk, collection.keys[rotate_to_index].client_keyid, -1))
+		test_error("Can't change the current key");
+	if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC))
+		test_fail("verify failed");
+	collection.keys[rotate_to_index].used_after_accept = 1;
+
+	end_client(tst_name, sk, nr_keys, current_index, rnext_index, &tmp);
+}
+
+static void roll_over_keys(const char *tst_name, unsigned int port,
+			   unsigned int nr_keys, unsigned int rotations,
+			   unsigned int current_index, unsigned int rnext_index)
+{
+	struct tcp_ao_counters tmp;
+	unsigned int i;
+	int sk;
+
+	sk = start_client(tst_name, port, nr_keys, current_index, rnext_index,
+			  &tmp, msg_len, nr_packets);
+	if (sk < 0)
+		return;
+	for (i = rnext_index + 1; rotations > 0; i++, rotations--) {
+		if (i >= collection.nr_keys)
+			i = 0;
+		if (test_set_key(sk, -1, collection.keys[i].server_keyid))
+			test_error("Can't change the Rnext key");
+		if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC)) {
+			test_fail("verify failed");
+			close(sk);
+			test_tcp_ao_counters_free(&tmp);
+			return;
+		}
+		verify_current_rnext(tst_name, sk, -1,
+				     collection.keys[i].server_keyid);
+		collection.keys[i].used_on_client = 1;
+		synchronize_threads(); /* verify current/rnext */
+	}
+	end_client(tst_name, sk, nr_keys, current_index, rnext_index, &tmp);
+}
+
+static void try_client_run(const char *tst_name, unsigned int port,
+			   unsigned int nr_keys, int current_index, int rnext_index)
+{
+	struct tcp_ao_counters tmp;
+	int sk;
+
+	sk = start_client(tst_name, port, nr_keys, current_index, rnext_index,
+			  &tmp, msg_len, nr_packets);
+	if (sk < 0)
+		return;
+	end_client(tst_name, sk, nr_keys, current_index, rnext_index, &tmp);
+}
+
+static void try_client_match(const char *tst_name, unsigned int port,
+			     unsigned int nr_keys,
+			     int current_index, int rnext_index)
+{
+	int sk;
+
+	sk = client_non_matching(tst_name, port, nr_keys, current_index,
+				 rnext_index, msg_len, nr_packets);
+	if (sk < 0)
+		return;
+	try_unmatched_keys(sk, &rnext_index);
+	end_client(tst_name, sk, nr_keys, current_index, rnext_index, NULL);
+}
+
+static void *server_fn(void *arg)
+{
+	unsigned int port = test_server_port;
+
+	setup_vrfs();
+	try_server_run("server: Check current/rnext keys unset before connect()",
+		       port++, quota, 19, 19);
+	try_server_run("server: Check current/rnext keys set before connect()",
+		       port++, quota, 10, 10);
+	try_server_run("server: Check current != rnext keys set before connect()",
+		       port++, quota, 5, 10);
+	try_server_run("server: Check current flapping back on peer's RnextKey request",
+		       port++, quota * 2, 5, 10);
+	server_rotations("server: Rotate over all different keys", port++,
+			 quota, 20, 0, 0);
+	try_server_run("server: Check accept() => established key matching",
+		       port++, quota * 2, 0, 0);
+
+	synchronize_threads(); /* don't race to exit: client exits */
+	return NULL;
+}
+
+static void check_established_socket(void)
+{
+	unsigned int port = test_server_port;
+
+	setup_vrfs();
+	try_client_run("client: Check current/rnext keys unset before connect()",
+		       port++, 20, -1, -1);
+	try_client_run("client: Check current/rnext keys set before connect()",
+		       port++, 20, 10, 10);
+	try_client_run("client: Check current != rnext keys set before connect()",
+		       port++, 20, 10, 5);
+	check_current_back("client: Check current flapping back on peer's RnextKey request",
+			   port++, 20, 10, 5, 2);
+	roll_over_keys("client: Rotate over all different keys", port++,
+		       20, 20, 0, 0);
+	try_client_match("client: Check connect() => established key matching",
+			 port++, 20, 0, 0);
+}
+
+static void *client_fn(void *arg)
+{
+	if (inet_pton(TEST_FAMILY, TEST_WRONG_IP, &wrong_addr) != 1)
+		test_error("Can't convert ip address %s", TEST_WRONG_IP);
+	check_closed_socket();
+	check_listen_socket();
+	check_established_socket();
+	return NULL;
+}
+
+int main(int argc, char *argv[])
+{
+	test_init(120, server_fn, client_fn);
+	return 0;
+}
diff --git a/tools/testing/selftests/net/tcp_ao/lib/aolib.h b/tools/testing/selftests/net/tcp_ao/lib/aolib.h
new file mode 100644
index 000000000000..fbc7f6111815
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/lib/aolib.h
@@ -0,0 +1,605 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * TCP-AO selftest library. Provides helpers to unshare network
+ * namespaces, create veth, assign ip addresses, set routes,
+ * manipulate socket options, read network counter and etc.
+ * Author: Dmitry Safonov <dima@arista.com>
+ */
+#ifndef _AOLIB_H_
+#define _AOLIB_H_
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <linux/snmp.h>
+#include <linux/tcp.h>
+#include <netinet/in.h>
+#include <stdarg.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+#include "../../../../../include/linux/stringify.h"
+#include "../../../../../include/linux/bits.h"
+
+#ifndef SOL_TCP
+/* can't include <netinet/tcp.h> as including <linux/tcp.h> */
+# define SOL_TCP		6	/* TCP level */
+#endif
+
+/* Working around ksft, see the comment in lib/setup.c */
+extern void __test_msg(const char *buf);
+extern void __test_ok(const char *buf);
+extern void __test_fail(const char *buf);
+extern void __test_xfail(const char *buf);
+extern void __test_error(const char *buf);
+extern void __test_skip(const char *buf);
+
+__attribute__((__format__(__printf__, 2, 3)))
+static inline void __test_print(void (*fn)(const char *), const char *fmt, ...)
+{
+#define TEST_MSG_BUFFER_SIZE 4096
+	char buf[TEST_MSG_BUFFER_SIZE];
+	va_list arg;
+
+	va_start(arg, fmt);
+	vsnprintf(buf, sizeof(buf), fmt, arg);
+	va_end(arg);
+	fn(buf);
+}
+
+#define test_print(fmt, ...)						\
+	__test_print(__test_msg, "%ld[%s:%u] " fmt "\n",		\
+		     syscall(SYS_gettid),				\
+		     __FILE__, __LINE__, ##__VA_ARGS__)
+
+#define test_ok(fmt, ...)						\
+	__test_print(__test_ok, fmt "\n", ##__VA_ARGS__)
+#define test_skip(fmt, ...)						\
+	__test_print(__test_skip, fmt "\n", ##__VA_ARGS__)
+#define test_xfail(fmt, ...)						\
+	__test_print(__test_xfail, fmt "\n", ##__VA_ARGS__)
+
+#define test_fail(fmt, ...)						\
+do {									\
+	if (errno)							\
+		__test_print(__test_fail, fmt ": %m\n", ##__VA_ARGS__);	\
+	else								\
+		__test_print(__test_fail, fmt "\n", ##__VA_ARGS__);	\
+	test_failed();							\
+} while (0)
+
+#define KSFT_FAIL  1
+#define test_error(fmt, ...)						\
+do {									\
+	if (errno)							\
+		__test_print(__test_error, "%ld[%s:%u] " fmt ": %m\n",	\
+			     syscall(SYS_gettid), __FILE__, __LINE__,	\
+			     ##__VA_ARGS__);				\
+	else								\
+		__test_print(__test_error, "%ld[%s:%u] " fmt "\n",	\
+			     syscall(SYS_gettid), __FILE__, __LINE__,	\
+			     ##__VA_ARGS__);				\
+	exit(KSFT_FAIL);						\
+} while (0)
+
+enum test_fault {
+	FAULT_TIMEOUT = 1,
+	FAULT_KEYREJECT,
+	FAULT_PREINSTALL_AO,
+	FAULT_PREINSTALL_MD5,
+	FAULT_POSTINSTALL,
+	FAULT_BUSY,
+	FAULT_CURRNEXT,
+	FAULT_FIXME,
+};
+typedef enum test_fault fault_t;
+
+enum test_needs_kconfig {
+	KCONFIG_NET_NS = 0,		/* required */
+	KCONFIG_VETH,			/* required */
+	KCONFIG_TCP_AO,			/* required */
+	KCONFIG_TCP_MD5,		/* optional, for TCP-MD5 features */
+	KCONFIG_NET_VRF,		/* optional, for L3/VRF testing */
+	__KCONFIG_LAST__
+};
+extern bool kernel_config_has(enum test_needs_kconfig k);
+extern const char *tests_skip_reason[__KCONFIG_LAST__];
+static inline bool should_skip_test(const char *tst_name,
+				    enum test_needs_kconfig k)
+{
+	if (kernel_config_has(k))
+		return false;
+	test_skip("%s: %s", tst_name, tests_skip_reason[k]);
+	return true;
+}
+
+union tcp_addr {
+	struct in_addr a4;
+	struct in6_addr a6;
+};
+
+typedef void *(*thread_fn)(void *);
+extern void test_failed(void);
+extern void __test_init(unsigned int ntests, int family, unsigned int prefix,
+			union tcp_addr addr1, union tcp_addr addr2,
+			thread_fn peer1, thread_fn peer2);
+
+static inline void test_init2(unsigned int ntests,
+			      thread_fn peer1, thread_fn peer2,
+			      int family, unsigned int prefix,
+			      const char *addr1, const char *addr2)
+{
+	union tcp_addr taddr1, taddr2;
+
+	if (inet_pton(family, addr1, &taddr1) != 1)
+		test_error("Can't convert ip address %s", addr1);
+	if (inet_pton(family, addr2, &taddr2) != 1)
+		test_error("Can't convert ip address %s", addr2);
+
+	__test_init(ntests, family, prefix, taddr1, taddr2, peer1, peer2);
+}
+extern void test_add_destructor(void (*d)(void));
+
+/* To adjust optmem socket limit, approximately estimate a number,
+ * that is bigger than sizeof(struct tcp_ao_key).
+ */
+#define KERNEL_TCP_AO_KEY_SZ_ROUND_UP	300
+
+extern void test_set_optmem(size_t value);
+extern size_t test_get_optmem(void);
+
+extern const struct sockaddr_in6 addr_any6;
+extern const struct sockaddr_in addr_any4;
+
+#ifdef IPV6_TEST
+# define __TEST_CLIENT_IP(n)	("2001:db8:" __stringify(n) "::1")
+# define TEST_CLIENT_IP	__TEST_CLIENT_IP(1)
+# define TEST_WRONG_IP	"2001:db8:253::1"
+# define TEST_SERVER_IP	"2001:db8:254::1"
+# define TEST_NETWORK	"2001::"
+# define TEST_PREFIX	128
+# define TEST_FAMILY	AF_INET6
+# define SOCKADDR_ANY	addr_any6
+# define sockaddr_af	struct sockaddr_in6
+#else
+# define __TEST_CLIENT_IP(n)	("10.0." __stringify(n) ".1")
+# define TEST_CLIENT_IP	__TEST_CLIENT_IP(1)
+# define TEST_WRONG_IP	"10.0.253.1"
+# define TEST_SERVER_IP	"10.0.254.1"
+# define TEST_NETWORK	"10.0.0.0"
+# define TEST_PREFIX	32
+# define TEST_FAMILY	AF_INET
+# define SOCKADDR_ANY	addr_any4
+# define sockaddr_af	struct sockaddr_in
+#endif
+
+static inline union tcp_addr gen_tcp_addr(union tcp_addr net, size_t n)
+{
+	union tcp_addr ret = net;
+
+#ifdef IPV6_TEST
+	ret.a6.s6_addr32[3] = htonl(n & (BIT(32) - 1));
+	ret.a6.s6_addr32[2] = htonl((n >> 32) & (BIT(32) - 1));
+#else
+	ret.a4.s_addr = htonl(ntohl(net.a4.s_addr) + n);
+#endif
+
+	return ret;
+}
+
+static inline void tcp_addr_to_sockaddr_in(void *dest,
+					   const union tcp_addr *src,
+					   unsigned int port)
+{
+	sockaddr_af *out = dest;
+
+	memset(out, 0, sizeof(*out));
+#ifdef IPV6_TEST
+	out->sin6_family = AF_INET6;
+	out->sin6_port   = port;
+	out->sin6_addr   = src->a6;
+#else
+	out->sin_family  = AF_INET;
+	out->sin_port    = port;
+	out->sin_addr    = src->a4;
+#endif
+}
+
+static inline void test_init(unsigned int ntests,
+			     thread_fn peer1, thread_fn peer2)
+{
+	test_init2(ntests, peer1, peer2, TEST_FAMILY, TEST_PREFIX,
+			TEST_SERVER_IP, TEST_CLIENT_IP);
+}
+extern void synchronize_threads(void);
+extern void switch_ns(int fd);
+
+extern __thread union tcp_addr this_ip_addr;
+extern __thread union tcp_addr this_ip_dest;
+extern int test_family;
+
+extern void randomize_buffer(void *buf, size_t buflen);
+extern int open_netns(void);
+extern int unshare_open_netns(void);
+extern const char veth_name[];
+extern int add_veth(const char *name, int nsfda, int nsfdb);
+extern int add_vrf(const char *name, uint32_t tabid, int ifindex, int nsfd);
+extern int ip_addr_add(const char *intf, int family,
+		       union tcp_addr addr, uint8_t prefix);
+extern int ip_route_add(const char *intf, int family,
+			union tcp_addr src, union tcp_addr dst);
+extern int ip_route_add_vrf(const char *intf, int family,
+			    union tcp_addr src, union tcp_addr dst,
+			    uint8_t vrf);
+extern int link_set_up(const char *intf);
+
+extern const unsigned int test_server_port;
+extern int test_wait_fd(int sk, time_t sec, bool write);
+extern int __test_connect_socket(int sk, const char *device,
+				 void *addr, size_t addr_sz, time_t timeout);
+extern int __test_listen_socket(int backlog, void *addr, size_t addr_sz);
+
+static inline int test_listen_socket(const union tcp_addr taddr,
+				     unsigned int port, int backlog)
+{
+	sockaddr_af addr;
+
+	tcp_addr_to_sockaddr_in(&addr, &taddr, htons(port));
+	return __test_listen_socket(backlog, (void *)&addr, sizeof(addr));
+}
+
+/*
+ * In order for selftests to work under CONFIG_CRYPTO_FIPS=y,
+ * the password should be loger than 14 bytes, see hmac_setkey()
+ */
+#define TEST_TCP_AO_MINKEYLEN	14
+#define DEFAULT_TEST_PASSWORD	"In this hour, I do not believe that any darkness will endure."
+
+#ifndef DEFAULT_TEST_ALGO
+#define DEFAULT_TEST_ALGO	"cmac(aes128)"
+#endif
+
+#ifdef IPV6_TEST
+#define DEFAULT_TEST_PREFIX	128
+#else
+#define DEFAULT_TEST_PREFIX	32
+#endif
+
+/*
+ * Timeout on syscalls where failure is not expected.
+ * You may want to rise it if the test machine is very busy.
+ */
+#ifndef TEST_TIMEOUT_SEC
+#define TEST_TIMEOUT_SEC	5
+#endif
+
+/*
+ * Timeout on connect() where a failure is expected.
+ * If set to 0 - kernel will try to retransmit SYN number of times, set in
+ * /proc/sys/net/ipv4/tcp_syn_retries
+ * By default set to 1 to make tests pass faster on non-busy machine.
+ */
+#ifndef TEST_RETRANSMIT_SEC
+#define TEST_RETRANSMIT_SEC	1
+#endif
+
+static inline int _test_connect_socket(int sk, const union tcp_addr taddr,
+				       unsigned int port, time_t timeout)
+{
+	sockaddr_af addr;
+
+	tcp_addr_to_sockaddr_in(&addr, &taddr, htons(port));
+	return __test_connect_socket(sk, veth_name,
+				     (void *)&addr, sizeof(addr), timeout);
+}
+
+static inline int test_connect_socket(int sk, const union tcp_addr taddr,
+				      unsigned int port)
+{
+	return _test_connect_socket(sk, taddr, port, TEST_TIMEOUT_SEC);
+}
+
+extern int __test_set_md5(int sk, void *addr, size_t addr_sz,
+			  uint8_t prefix, int vrf, const char *password);
+static inline int test_set_md5(int sk, const union tcp_addr in_addr,
+			       uint8_t prefix, int vrf, const char *password)
+{
+	sockaddr_af addr;
+
+	if (prefix > DEFAULT_TEST_PREFIX)
+		prefix = DEFAULT_TEST_PREFIX;
+
+	tcp_addr_to_sockaddr_in(&addr, &in_addr, 0);
+	return __test_set_md5(sk, (void *)&addr, sizeof(addr),
+			prefix, vrf, password);
+}
+
+extern int test_prepare_key_sockaddr(struct tcp_ao_add *ao, const char *alg,
+		void *addr, size_t addr_sz, bool set_current, bool set_rnext,
+		uint8_t prefix, uint8_t vrf,
+		uint8_t sndid, uint8_t rcvid, uint8_t maclen,
+		uint8_t keyflags, uint8_t keylen, const char *key);
+
+static inline int test_prepare_key(struct tcp_ao_add *ao,
+		const char *alg, union tcp_addr taddr,
+		bool set_current, bool set_rnext,
+		uint8_t prefix, uint8_t vrf,
+		uint8_t sndid, uint8_t rcvid, uint8_t maclen,
+		uint8_t keyflags, uint8_t keylen, const char *key)
+{
+	sockaddr_af addr;
+
+	tcp_addr_to_sockaddr_in(&addr, &taddr, 0);
+	return test_prepare_key_sockaddr(ao, alg, (void *)&addr, sizeof(addr),
+			set_current, set_rnext, prefix, vrf, sndid, rcvid,
+			maclen, keyflags, keylen, key);
+}
+
+static inline int test_prepare_def_key(struct tcp_ao_add *ao,
+		const char *key, uint8_t keyflags,
+		union tcp_addr in_addr, uint8_t prefix, uint8_t vrf,
+		uint8_t sndid, uint8_t rcvid)
+{
+	if (prefix > DEFAULT_TEST_PREFIX)
+		prefix = DEFAULT_TEST_PREFIX;
+
+	return test_prepare_key(ao, DEFAULT_TEST_ALGO, in_addr, false, false,
+				prefix, vrf, sndid, rcvid, 0, keyflags,
+				strlen(key), key);
+}
+
+extern int test_get_one_ao(int sk, struct tcp_ao_getsockopt *out,
+			   void *addr, size_t addr_sz,
+			   uint8_t prefix, uint8_t sndid, uint8_t rcvid);
+extern int test_get_ao_info(int sk, struct tcp_ao_info_opt *out);
+extern int test_set_ao_info(int sk, struct tcp_ao_info_opt *in);
+extern int test_cmp_getsockopt_setsockopt(const struct tcp_ao_add *a,
+					  const struct tcp_ao_getsockopt *b);
+extern int test_cmp_getsockopt_setsockopt_ao(const struct tcp_ao_info_opt *a,
+					     const struct tcp_ao_info_opt *b);
+
+static inline int test_verify_socket_key(int sk, struct tcp_ao_add *key)
+{
+	struct tcp_ao_getsockopt key2 = {};
+	int err;
+
+	err = test_get_one_ao(sk, &key2, &key->addr, sizeof(key->addr),
+			      key->prefix, key->sndid, key->rcvid);
+	if (err)
+		return err;
+
+	return test_cmp_getsockopt_setsockopt(key, &key2);
+}
+
+static inline int test_add_key_vrf(int sk,
+				   const char *key, uint8_t keyflags,
+				   union tcp_addr in_addr, uint8_t prefix,
+				   uint8_t vrf, uint8_t sndid, uint8_t rcvid)
+{
+	struct tcp_ao_add tmp = {};
+	int err;
+
+	err = test_prepare_def_key(&tmp, key, keyflags, in_addr, prefix,
+				   vrf, sndid, rcvid);
+	if (err)
+		return err;
+
+	err = setsockopt(sk, IPPROTO_TCP, TCP_AO_ADD_KEY, &tmp, sizeof(tmp));
+	if (err < 0)
+		return -errno;
+
+	return test_verify_socket_key(sk, &tmp);
+}
+
+static inline int test_add_key(int sk, const char *key,
+			      union tcp_addr in_addr, uint8_t prefix,
+			      uint8_t sndid, uint8_t rcvid)
+{
+	return test_add_key_vrf(sk, key, 0, in_addr, prefix, 0, sndid, rcvid);
+}
+
+static inline int test_verify_socket_ao(int sk, struct tcp_ao_info_opt *ao)
+{
+	struct tcp_ao_info_opt ao2 = {};
+	int err;
+
+	err = test_get_ao_info(sk, &ao2);
+	if (err)
+		return err;
+
+	return test_cmp_getsockopt_setsockopt_ao(ao, &ao2);
+}
+
+static inline int test_set_ao_flags(int sk, bool ao_required, bool accept_icmps)
+{
+	struct tcp_ao_info_opt ao = {};
+	int err;
+
+	err = test_get_ao_info(sk, &ao);
+	/* Maybe ao_info wasn't allocated yet */
+	if (err && err != -ENOENT)
+		return err;
+
+	ao.ao_required = !!ao_required;
+	ao.accept_icmps = !!accept_icmps;
+	err = test_set_ao_info(sk, &ao);
+	if (err)
+		return err;
+
+	return test_verify_socket_ao(sk, &ao);
+}
+
+extern ssize_t test_server_run(int sk, ssize_t quota, time_t timeout_sec);
+extern ssize_t test_client_loop(int sk, char *buf, size_t buf_sz,
+				const size_t msg_len, time_t timeout_sec);
+extern int test_client_verify(int sk, const size_t msg_len, const size_t nr,
+			      time_t timeout_sec);
+
+struct tcp_ao_key_counters {
+	uint8_t sndid;
+	uint8_t rcvid;
+	uint64_t pkt_good;
+	uint64_t pkt_bad;
+};
+
+struct tcp_ao_counters {
+	/* per-netns */
+	uint64_t netns_ao_good;
+	uint64_t netns_ao_bad;
+	uint64_t netns_ao_key_not_found;
+	uint64_t netns_ao_required;
+	uint64_t netns_ao_dropped_icmp;
+	/* per-socket */
+	uint64_t ao_info_pkt_good;
+	uint64_t ao_info_pkt_bad;
+	uint64_t ao_info_pkt_key_not_found;
+	uint64_t ao_info_pkt_ao_required;
+	uint64_t ao_info_pkt_dropped_icmp;
+	/* per-key */
+	size_t nr_keys;
+	struct tcp_ao_key_counters *key_cnts;
+};
+extern int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out);
+
+#define TEST_CNT_KEY_GOOD		BIT(0)
+#define TEST_CNT_KEY_BAD		BIT(1)
+#define TEST_CNT_SOCK_GOOD		BIT(2)
+#define TEST_CNT_SOCK_BAD		BIT(3)
+#define TEST_CNT_SOCK_KEY_NOT_FOUND	BIT(4)
+#define TEST_CNT_SOCK_AO_REQUIRED	BIT(5)
+#define TEST_CNT_SOCK_DROPPED_ICMP	BIT(6)
+#define TEST_CNT_NS_GOOD		BIT(7)
+#define TEST_CNT_NS_BAD			BIT(8)
+#define TEST_CNT_NS_KEY_NOT_FOUND	BIT(9)
+#define TEST_CNT_NS_AO_REQUIRED		BIT(10)
+#define TEST_CNT_NS_DROPPED_ICMP	BIT(11)
+typedef uint16_t test_cnt;
+
+#define TEST_CNT_AO_GOOD		(TEST_CNT_SOCK_GOOD | TEST_CNT_NS_GOOD)
+#define TEST_CNT_AO_BAD			(TEST_CNT_SOCK_BAD | TEST_CNT_NS_BAD)
+#define TEST_CNT_AO_KEY_NOT_FOUND	(TEST_CNT_SOCK_KEY_NOT_FOUND | \
+					 TEST_CNT_NS_KEY_NOT_FOUND)
+#define TEST_CNT_AO_REQUIRED		(TEST_CNT_SOCK_AO_REQUIRED | \
+					 TEST_CNT_NS_AO_REQUIRED)
+#define TEST_CNT_AO_DROPPED_ICMP	(TEST_CNT_SOCK_DROPPED_ICMP | \
+					 TEST_CNT_NS_DROPPED_ICMP)
+#define TEST_CNT_GOOD			(TEST_CNT_KEY_GOOD | TEST_CNT_AO_GOOD)
+#define TEST_CNT_BAD			(TEST_CNT_KEY_BAD | TEST_CNT_AO_BAD)
+
+extern int __test_tcp_ao_counters_cmp(const char *tst_name,
+		struct tcp_ao_counters *before, struct tcp_ao_counters *after,
+		test_cnt expected);
+extern int test_tcp_ao_key_counters_cmp(const char *tst_name,
+		struct tcp_ao_counters *before, struct tcp_ao_counters *after,
+		test_cnt expected, int sndid, int rcvid);
+extern void test_tcp_ao_counters_free(struct tcp_ao_counters *cnts);
+/*
+ * Frees buffers allocated in test_get_tcp_ao_counters().
+ * The function doesn't expect new keys or keys removed between calls
+ * to test_get_tcp_ao_counters(). Check key counters manually if they
+ * may change.
+ */
+static inline int test_tcp_ao_counters_cmp(const char *tst_name,
+					   struct tcp_ao_counters *before,
+					   struct tcp_ao_counters *after,
+					   test_cnt expected)
+{
+	int ret;
+
+	ret = __test_tcp_ao_counters_cmp(tst_name, before, after, expected);
+	if (ret)
+		goto out;
+	ret = test_tcp_ao_key_counters_cmp(tst_name, before, after,
+					   expected, -1, -1);
+out:
+	test_tcp_ao_counters_free(before);
+	test_tcp_ao_counters_free(after);
+	return ret;
+}
+
+struct netstat;
+extern struct netstat *netstat_read(void);
+extern void netstat_free(struct netstat *ns);
+extern void netstat_print_diff(struct netstat *nsa, struct netstat *nsb);
+extern uint64_t netstat_get(struct netstat *ns,
+			    const char *name, bool *not_found);
+
+static inline uint64_t netstat_get_one(const char *name, bool *not_found)
+{
+	struct netstat *ns = netstat_read();
+	uint64_t ret;
+
+	ret = netstat_get(ns, name, not_found);
+
+	netstat_free(ns);
+	return ret;
+}
+
+struct tcp_sock_queue {
+	uint32_t seq;
+	void *buf;
+};
+
+struct tcp_sock_state {
+	struct tcp_info info;
+	struct tcp_repair_window trw;
+	struct tcp_sock_queue out;
+	int outq_len;		/* output queue size (not sent + not acked) */
+	int outq_nsd_len;	/* output queue size (not sent only) */
+	struct tcp_sock_queue in;
+	int inq_len;
+	int mss;
+	int timestamp;
+};
+
+extern void __test_sock_checkpoint(int sk, struct tcp_sock_state *state,
+				   void *addr, size_t addr_size);
+static inline void test_sock_checkpoint(int sk, struct tcp_sock_state *state,
+					sockaddr_af *saddr)
+{
+	__test_sock_checkpoint(sk, state, saddr, sizeof(*saddr));
+}
+extern void test_ao_checkpoint(int sk, struct tcp_ao_repair *state);
+extern void __test_sock_restore(int sk, const char *device,
+				struct tcp_sock_state *state,
+				void *saddr, void *daddr, size_t addr_size);
+static inline void test_sock_restore(int sk, struct tcp_sock_state *state,
+				     sockaddr_af *saddr,
+				     const union tcp_addr daddr,
+				     unsigned int dport)
+{
+	sockaddr_af addr;
+
+	tcp_addr_to_sockaddr_in(&addr, &daddr, htons(dport));
+	__test_sock_restore(sk, veth_name, state, saddr, &addr, sizeof(addr));
+}
+extern void test_ao_restore(int sk, struct tcp_ao_repair *state);
+extern void test_sock_state_free(struct tcp_sock_state *state);
+extern void test_enable_repair(int sk);
+extern void test_disable_repair(int sk);
+extern void test_kill_sk(int sk);
+static inline int test_add_repaired_key(int sk,
+					const char *key, uint8_t keyflags,
+					union tcp_addr in_addr, uint8_t prefix,
+					uint8_t sndid, uint8_t rcvid)
+{
+	struct tcp_ao_add tmp = {};
+	int err;
+
+	err = test_prepare_def_key(&tmp, key, keyflags, in_addr, prefix,
+				   0, sndid, rcvid);
+	if (err)
+		return err;
+
+	tmp.set_current = 1;
+	tmp.set_rnext = 1;
+	if (setsockopt(sk, IPPROTO_TCP, TCP_AO_ADD_KEY, &tmp, sizeof(tmp)) < 0)
+		return -errno;
+
+	return test_verify_socket_key(sk, &tmp);
+}
+
+#endif /* _AOLIB_H_ */
diff --git a/tools/testing/selftests/net/tcp_ao/lib/kconfig.c b/tools/testing/selftests/net/tcp_ao/lib/kconfig.c
new file mode 100644
index 000000000000..f279ffc3843b
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/lib/kconfig.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Check what features does the kernel support (where the selftest is running).
+ * Somewhat inspired by CRIU kerndat/kdat kernel features detector.
+ */
+#include <pthread.h>
+#include "aolib.h"
+
+struct kconfig_t {
+	int _errno;		/* the returned error if not supported */
+	int (*check_kconfig)(int *error);
+};
+
+static int has_net_ns(int *err)
+{
+	if (access("/proc/self/ns/net", F_OK) < 0) {
+		*err = errno;
+		if (errno == ENOENT)
+			return 0;
+		test_print("Unable to access /proc/self/ns/net: %m");
+		return -errno;
+	}
+	return *err = errno = 0;
+}
+
+static int has_veth(int *err)
+{
+	int orig_netns, ns_a, ns_b;
+
+	orig_netns = open_netns();
+	ns_a = unshare_open_netns();
+	ns_b = unshare_open_netns();
+
+	*err = add_veth("check_veth", ns_a, ns_b);
+
+	switch_ns(orig_netns);
+	close(orig_netns);
+	close(ns_a);
+	close(ns_b);
+	return 0;
+}
+
+static int has_tcp_ao(int *err)
+{
+	struct sockaddr_in addr = {
+		.sin_family = test_family,
+	};
+	struct tcp_ao_add tmp = {};
+	const char *password = DEFAULT_TEST_PASSWORD;
+	int sk, ret = 0;
+
+	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+	if (sk < 0) {
+		test_print("socket(): %m");
+		return -errno;
+	}
+
+	tmp.sndid = 100;
+	tmp.rcvid = 100;
+	tmp.keylen = strlen(password);
+	memcpy(tmp.key, password, strlen(password));
+	strcpy(tmp.alg_name, "hmac(sha1)");
+	memcpy(&tmp.addr, &addr, sizeof(addr));
+	*err = 0;
+	if (setsockopt(sk, IPPROTO_TCP, TCP_AO_ADD_KEY, &tmp, sizeof(tmp)) < 0) {
+		*err = errno;
+		if (errno != ENOPROTOOPT)
+			ret = -errno;
+	}
+	close(sk);
+	return ret;
+}
+
+static int has_tcp_md5(int *err)
+{
+	union tcp_addr addr_any = {};
+	int sk, ret = 0;
+
+	sk = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
+	if (sk < 0) {
+		test_print("socket(): %m");
+		return -errno;
+	}
+
+	/*
+	 * Under CONFIG_CRYPTO_FIPS=y it fails with ENOMEM, rather with
+	 * anything more descriptive. Oh well.
+	 */
+	*err = 0;
+	if (test_set_md5(sk, addr_any, 0, -1, DEFAULT_TEST_PASSWORD)) {
+		*err = errno;
+		if (errno != ENOPROTOOPT && errno == ENOMEM) {
+			test_print("setsockopt(TCP_MD5SIG_EXT): %m");
+			ret = -errno;
+		}
+	}
+	close(sk);
+	return ret;
+}
+
+static int has_vrfs(int *err)
+{
+	int orig_netns, ns_test, ret = 0;
+
+	orig_netns = open_netns();
+	ns_test = unshare_open_netns();
+
+	*err = add_vrf("ksft-check", 55, 101, ns_test);
+	if (*err && *err != -EOPNOTSUPP) {
+		test_print("Failed to add a VRF: %d", *err);
+		ret = *err;
+	}
+
+	switch_ns(orig_netns);
+	close(orig_netns);
+	close(ns_test);
+	return ret;
+}
+
+static pthread_mutex_t kconfig_lock = PTHREAD_MUTEX_INITIALIZER;
+static struct kconfig_t kconfig[__KCONFIG_LAST__] = {
+	{ -1, has_net_ns },
+	{ -1, has_veth },
+	{ -1, has_tcp_ao },
+	{ -1, has_tcp_md5 },
+	{ -1, has_vrfs },
+};
+
+const char *tests_skip_reason[__KCONFIG_LAST__] = {
+	"Tests require network namespaces support (CONFIG_NET_NS)",
+	"Tests require veth support (CONFIG_VETH)",
+	"Tests require TCP-AO support (CONFIG_TCP_AO)",
+	"setsockopt(TCP_MD5SIG_EXT) is not supported (CONFIG_TCP_MD5)",
+	"VRFs are not supported (CONFIG_NET_VRF)",
+};
+
+bool kernel_config_has(enum test_needs_kconfig k)
+{
+	bool ret;
+
+	pthread_mutex_lock(&kconfig_lock);
+	if (kconfig[k]._errno == -1) {
+		if (kconfig[k].check_kconfig(&kconfig[k]._errno))
+			test_error("Failed to initialize kconfig %u", k);
+	}
+	ret = kconfig[k]._errno == 0;
+	pthread_mutex_unlock(&kconfig_lock);
+	return ret;
+}
diff --git a/tools/testing/selftests/net/tcp_ao/lib/netlink.c b/tools/testing/selftests/net/tcp_ao/lib/netlink.c
new file mode 100644
index 000000000000..7f108493a29a
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/lib/netlink.c
@@ -0,0 +1,413 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Original from tools/testing/selftests/net/ipsec.c */
+#include <linux/netlink.h>
+#include <linux/random.h>
+#include <linux/rtnetlink.h>
+#include <linux/veth.h>
+#include <net/if.h>
+#include <stdint.h>
+#include <string.h>
+#include <sys/socket.h>
+
+#include "aolib.h"
+
+#define MAX_PAYLOAD		2048
+
+static int netlink_sock(int *sock, uint32_t *seq_nr, int proto)
+{
+	if (*sock > 0) {
+		seq_nr++;
+		return 0;
+	}
+
+	*sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, proto);
+	if (*sock < 0) {
+		test_print("socket(AF_NETLINK)");
+		return -1;
+	}
+
+	randomize_buffer(seq_nr, sizeof(*seq_nr));
+
+	return 0;
+}
+
+static int netlink_check_answer(int sock, bool quite)
+{
+	struct nlmsgerror {
+		struct nlmsghdr hdr;
+		int error;
+		struct nlmsghdr orig_msg;
+	} answer;
+
+	if (recv(sock, &answer, sizeof(answer), 0) < 0) {
+		test_print("recv()");
+		return -1;
+	} else if (answer.hdr.nlmsg_type != NLMSG_ERROR) {
+		test_print("expected NLMSG_ERROR, got %d",
+			   (int)answer.hdr.nlmsg_type);
+		return -1;
+	} else if (answer.error) {
+		if (!quite) {
+			test_print("NLMSG_ERROR: %d: %s",
+				answer.error, strerror(-answer.error));
+		}
+		return answer.error;
+	}
+
+	return 0;
+}
+
+static inline struct rtattr *rtattr_hdr(struct nlmsghdr *nh)
+{
+	return (struct rtattr *)((char *)(nh) + RTA_ALIGN((nh)->nlmsg_len));
+}
+
+static int rtattr_pack(struct nlmsghdr *nh, size_t req_sz,
+		unsigned short rta_type, const void *payload, size_t size)
+{
+	/* NLMSG_ALIGNTO == RTA_ALIGNTO, nlmsg_len already aligned */
+	struct rtattr *attr = rtattr_hdr(nh);
+	size_t nl_size = RTA_ALIGN(nh->nlmsg_len) + RTA_LENGTH(size);
+
+	if (req_sz < nl_size) {
+		test_print("req buf is too small: %zu < %zu", req_sz, nl_size);
+		return -1;
+	}
+	nh->nlmsg_len = nl_size;
+
+	attr->rta_len = RTA_LENGTH(size);
+	attr->rta_type = rta_type;
+	memcpy(RTA_DATA(attr), payload, size);
+
+	return 0;
+}
+
+static struct rtattr *_rtattr_begin(struct nlmsghdr *nh, size_t req_sz,
+		unsigned short rta_type, const void *payload, size_t size)
+{
+	struct rtattr *ret = rtattr_hdr(nh);
+
+	if (rtattr_pack(nh, req_sz, rta_type, payload, size))
+		return 0;
+
+	return ret;
+}
+
+static inline struct rtattr *rtattr_begin(struct nlmsghdr *nh, size_t req_sz,
+		unsigned short rta_type)
+{
+	return _rtattr_begin(nh, req_sz, rta_type, 0, 0);
+}
+
+static inline void rtattr_end(struct nlmsghdr *nh, struct rtattr *attr)
+{
+	char *nlmsg_end = (char *)nh + nh->nlmsg_len;
+
+	attr->rta_len = nlmsg_end - (char *)attr;
+}
+
+static int veth_pack_peerb(struct nlmsghdr *nh, size_t req_sz,
+		const char *peer, int ns)
+{
+	struct ifinfomsg pi;
+	struct rtattr *peer_attr;
+
+	memset(&pi, 0, sizeof(pi));
+	pi.ifi_family	= AF_UNSPEC;
+	pi.ifi_change	= 0xFFFFFFFF;
+
+	peer_attr = _rtattr_begin(nh, req_sz, VETH_INFO_PEER, &pi, sizeof(pi));
+	if (!peer_attr)
+		return -1;
+
+	if (rtattr_pack(nh, req_sz, IFLA_IFNAME, peer, strlen(peer)))
+		return -1;
+
+	if (rtattr_pack(nh, req_sz, IFLA_NET_NS_FD, &ns, sizeof(ns)))
+		return -1;
+
+	rtattr_end(nh, peer_attr);
+
+	return 0;
+}
+
+static int __add_veth(int sock, uint32_t seq, const char *name,
+		      int ns_a, int ns_b)
+{
+	uint16_t flags = NLM_F_REQUEST | NLM_F_ACK | NLM_F_EXCL | NLM_F_CREATE;
+	struct {
+		struct nlmsghdr		nh;
+		struct ifinfomsg	info;
+		char			attrbuf[MAX_PAYLOAD];
+	} req;
+	static const char veth_type[] = "veth";
+	struct rtattr *link_info, *info_data;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len	= NLMSG_LENGTH(sizeof(req.info));
+	req.nh.nlmsg_type	= RTM_NEWLINK;
+	req.nh.nlmsg_flags	= flags;
+	req.nh.nlmsg_seq	= seq;
+	req.info.ifi_family	= AF_UNSPEC;
+	req.info.ifi_change	= 0xFFFFFFFF;
+
+	if (rtattr_pack(&req.nh, sizeof(req), IFLA_IFNAME, name, strlen(name)))
+		return -1;
+
+	if (rtattr_pack(&req.nh, sizeof(req), IFLA_NET_NS_FD, &ns_a, sizeof(ns_a)))
+		return -1;
+
+	link_info = rtattr_begin(&req.nh, sizeof(req), IFLA_LINKINFO);
+	if (!link_info)
+		return -1;
+
+	if (rtattr_pack(&req.nh, sizeof(req), IFLA_INFO_KIND, veth_type, sizeof(veth_type)))
+		return -1;
+
+	info_data = rtattr_begin(&req.nh, sizeof(req), IFLA_INFO_DATA);
+	if (!info_data)
+		return -1;
+
+	if (veth_pack_peerb(&req.nh, sizeof(req), name, ns_b))
+		return -1;
+
+	rtattr_end(&req.nh, info_data);
+	rtattr_end(&req.nh, link_info);
+
+	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		test_print("send()");
+		return -1;
+	}
+	return netlink_check_answer(sock, false);
+}
+
+int add_veth(const char *name, int nsfda, int nsfdb)
+{
+	int route_sock = -1, ret;
+	uint32_t route_seq;
+
+	if (netlink_sock(&route_sock, &route_seq, NETLINK_ROUTE))
+		test_error("Failed to open netlink route socket\n");
+
+	ret = __add_veth(route_sock, route_seq++, name, nsfda, nsfdb);
+	close(route_sock);
+	return ret;
+}
+
+static int __ip_addr_add(int sock, uint32_t seq, const char *intf,
+			 int family, union tcp_addr addr, uint8_t prefix)
+{
+	uint16_t flags = NLM_F_REQUEST | NLM_F_ACK | NLM_F_EXCL | NLM_F_CREATE;
+	struct {
+		struct nlmsghdr		nh;
+		struct ifaddrmsg	info;
+		char			attrbuf[MAX_PAYLOAD];
+	} req;
+	size_t addr_len = (family == AF_INET) ? sizeof(struct in_addr) :
+						sizeof(struct in6_addr);
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len	= NLMSG_LENGTH(sizeof(req.info));
+	req.nh.nlmsg_type	= RTM_NEWADDR;
+	req.nh.nlmsg_flags	= flags;
+	req.nh.nlmsg_seq	= seq;
+	req.info.ifa_family	= family;
+	req.info.ifa_prefixlen	= prefix;
+	req.info.ifa_index	= if_nametoindex(intf);
+	req.info.ifa_flags	= IFA_F_NODAD;
+
+	if (rtattr_pack(&req.nh, sizeof(req), IFA_LOCAL, &addr, addr_len))
+		return -1;
+
+	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		test_print("send()");
+		return -1;
+	}
+	return netlink_check_answer(sock, true);
+}
+
+int ip_addr_add(const char *intf, int family,
+		union tcp_addr addr, uint8_t prefix)
+{
+	int route_sock = -1, ret;
+	uint32_t route_seq;
+
+	if (netlink_sock(&route_sock, &route_seq, NETLINK_ROUTE))
+		test_error("Failed to open netlink route socket\n");
+
+	ret = __ip_addr_add(route_sock, route_seq++, intf,
+			    family, addr, prefix);
+
+	close(route_sock);
+	return ret;
+}
+
+static int __ip_route_add(int sock, uint32_t seq, const char *intf, int family,
+			  union tcp_addr src, union tcp_addr dst, uint8_t vrf)
+{
+	struct {
+		struct nlmsghdr	nh;
+		struct rtmsg	rt;
+		char		attrbuf[MAX_PAYLOAD];
+	} req;
+	unsigned int index = if_nametoindex(intf);
+	size_t addr_len = (family == AF_INET) ? sizeof(struct in_addr) :
+						sizeof(struct in6_addr);
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len	= NLMSG_LENGTH(sizeof(req.rt));
+	req.nh.nlmsg_type	= RTM_NEWROUTE;
+	req.nh.nlmsg_flags	= NLM_F_REQUEST | NLM_F_ACK | NLM_F_CREATE;
+	req.nh.nlmsg_seq	= seq;
+	req.rt.rtm_family	= family;
+	req.rt.rtm_dst_len	= (family == AF_INET) ? 32 : 128;
+	req.rt.rtm_table	= vrf;
+	req.rt.rtm_protocol	= RTPROT_BOOT;
+	req.rt.rtm_scope	= RT_SCOPE_UNIVERSE;
+	req.rt.rtm_type		= RTN_UNICAST;
+
+	if (rtattr_pack(&req.nh, sizeof(req), RTA_DST, &dst, addr_len))
+		return -1;
+
+	if (rtattr_pack(&req.nh, sizeof(req), RTA_PREFSRC, &src, addr_len))
+		return -1;
+
+	if (rtattr_pack(&req.nh, sizeof(req), RTA_OIF, &index, sizeof(index)))
+		return -1;
+
+	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		test_print("send()");
+		return -1;
+	}
+
+	return netlink_check_answer(sock, true);
+}
+
+int ip_route_add_vrf(const char *intf, int family,
+		 union tcp_addr src, union tcp_addr dst, uint8_t vrf)
+{
+	int route_sock = -1, ret;
+	uint32_t route_seq;
+
+	if (netlink_sock(&route_sock, &route_seq, NETLINK_ROUTE))
+		test_error("Failed to open netlink route socket\n");
+
+	ret = __ip_route_add(route_sock, route_seq++, intf,
+			     family, src, dst, vrf);
+
+	close(route_sock);
+	return ret;
+}
+
+int ip_route_add(const char *intf, int family,
+		 union tcp_addr src, union tcp_addr dst)
+{
+	return ip_route_add_vrf(intf, family, src, dst, RT_TABLE_MAIN);
+}
+
+static int __link_set_up(int sock, uint32_t seq, const char *intf)
+{
+	struct {
+		struct nlmsghdr		nh;
+		struct ifinfomsg	info;
+		char			attrbuf[MAX_PAYLOAD];
+	} req;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len	= NLMSG_LENGTH(sizeof(req.info));
+	req.nh.nlmsg_type	= RTM_NEWLINK;
+	req.nh.nlmsg_flags	= NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_seq	= seq;
+	req.info.ifi_family	= AF_UNSPEC;
+	req.info.ifi_change	= 0xFFFFFFFF;
+	req.info.ifi_index	= if_nametoindex(intf);
+	req.info.ifi_flags	= IFF_UP;
+	req.info.ifi_change	= IFF_UP;
+
+	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		test_print("send()");
+		return -1;
+	}
+	return netlink_check_answer(sock, false);
+}
+
+int link_set_up(const char *intf)
+{
+	int route_sock = -1, ret;
+	uint32_t route_seq;
+
+	if (netlink_sock(&route_sock, &route_seq, NETLINK_ROUTE))
+		test_error("Failed to open netlink route socket\n");
+
+	ret = __link_set_up(route_sock, route_seq++, intf);
+
+	close(route_sock);
+	return ret;
+}
+
+static int __add_vrf(int sock, uint32_t seq, const char *name,
+		     uint32_t tabid, int ifindex, int nsfd)
+{
+	uint16_t flags = NLM_F_REQUEST | NLM_F_ACK | NLM_F_EXCL | NLM_F_CREATE;
+	struct {
+		struct nlmsghdr		nh;
+		struct ifinfomsg	info;
+		char			attrbuf[MAX_PAYLOAD];
+	} req;
+	static const char vrf_type[] = "vrf";
+	struct rtattr *link_info, *info_data;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len	= NLMSG_LENGTH(sizeof(req.info));
+	req.nh.nlmsg_type	= RTM_NEWLINK;
+	req.nh.nlmsg_flags	= flags;
+	req.nh.nlmsg_seq	= seq;
+	req.info.ifi_family	= AF_UNSPEC;
+	req.info.ifi_change	= 0xFFFFFFFF;
+	req.info.ifi_index	= ifindex;
+
+	if (rtattr_pack(&req.nh, sizeof(req), IFLA_IFNAME, name, strlen(name)))
+		return -1;
+
+	if (nsfd >= 0)
+		if (rtattr_pack(&req.nh, sizeof(req), IFLA_NET_NS_FD,
+				&nsfd, sizeof(nsfd)))
+			return -1;
+
+	link_info = rtattr_begin(&req.nh, sizeof(req), IFLA_LINKINFO);
+	if (!link_info)
+		return -1;
+
+	if (rtattr_pack(&req.nh, sizeof(req), IFLA_INFO_KIND, vrf_type, sizeof(vrf_type)))
+		return -1;
+
+	info_data = rtattr_begin(&req.nh, sizeof(req), IFLA_INFO_DATA);
+	if (!info_data)
+		return -1;
+
+	if (rtattr_pack(&req.nh, sizeof(req), IFLA_VRF_TABLE,
+			&tabid, sizeof(tabid)))
+		return -1;
+
+	rtattr_end(&req.nh, info_data);
+	rtattr_end(&req.nh, link_info);
+
+	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		test_print("send()");
+		return -1;
+	}
+	return netlink_check_answer(sock, true);
+}
+
+int add_vrf(const char *name, uint32_t tabid, int ifindex, int nsfd)
+{
+	int route_sock = -1, ret;
+	uint32_t route_seq;
+
+	if (netlink_sock(&route_sock, &route_seq, NETLINK_ROUTE))
+		test_error("Failed to open netlink route socket\n");
+
+	ret = __add_vrf(route_sock, route_seq++, name, tabid, ifindex, nsfd);
+	close(route_sock);
+	return ret;
+}
diff --git a/tools/testing/selftests/net/tcp_ao/lib/proc.c b/tools/testing/selftests/net/tcp_ao/lib/proc.c
new file mode 100644
index 000000000000..2fb6dd8adba6
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/lib/proc.c
@@ -0,0 +1,273 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <inttypes.h>
+#include <pthread.h>
+#include <stdio.h>
+#include "../../../../../include/linux/compiler.h"
+#include "../../../../../include/linux/kernel.h"
+#include "aolib.h"
+
+struct netstat_counter {
+	uint64_t val;
+	char *name;
+};
+
+struct netstat {
+	char *header_name;
+	struct netstat *next;
+	size_t counters_nr;
+	struct netstat_counter *counters;
+};
+
+static struct netstat *lookup_type(struct netstat *ns,
+		const char *type, size_t len)
+{
+	while (ns != NULL) {
+		size_t cmp = max(len, strlen(ns->header_name));
+
+		if (!strncmp(ns->header_name, type, cmp))
+			return ns;
+		ns = ns->next;
+	}
+	return NULL;
+}
+
+static struct netstat *lookup_get(struct netstat *ns,
+				  const char *type, const size_t len)
+{
+	struct netstat *ret;
+
+	ret = lookup_type(ns, type, len);
+	if (ret != NULL)
+		return ret;
+
+	ret = malloc(sizeof(struct netstat));
+	if (!ret)
+		test_error("malloc()");
+
+	ret->header_name = strndup(type, len);
+	if (ret->header_name == NULL)
+		test_error("strndup()");
+	ret->next = ns;
+	ret->counters_nr = 0;
+	ret->counters = NULL;
+
+	return ret;
+}
+
+static struct netstat *lookup_get_column(struct netstat *ns, const char *line)
+{
+	char *column;
+
+	column = strchr(line, ':');
+	if (!column)
+		test_error("can't parse netstat file");
+
+	return lookup_get(ns, line, column - line);
+}
+
+static void netstat_read_type(FILE *fnetstat, struct netstat **dest, char *line)
+{
+	struct netstat *type = lookup_get_column(*dest, line);
+	const char *pos = line;
+	size_t i, nr_elems = 0;
+	char tmp;
+
+	while ((pos = strchr(pos, ' '))) {
+		nr_elems++;
+		pos++;
+	}
+
+	*dest = type;
+	type->counters = reallocarray(type->counters,
+				type->counters_nr + nr_elems,
+				sizeof(struct netstat_counter));
+	if (!type->counters)
+		test_error("reallocarray()");
+
+	pos = strchr(line, ' ') + 1;
+
+	if (fscanf(fnetstat, type->header_name) == EOF)
+		test_error("fscanf(%s)", type->header_name);
+	if (fread(&tmp, 1, 1, fnetstat) != 1 || tmp != ':')
+		test_error("Unexpected netstat format (%c)", tmp);
+
+	for (i = type->counters_nr; i < type->counters_nr + nr_elems; i++) {
+		struct netstat_counter *nc = &type->counters[i];
+		const char *new_pos = strchr(pos, ' ');
+		const char *fmt = " %" PRIu64;
+
+		if (new_pos == NULL)
+			new_pos = strchr(pos, '\n');
+
+		nc->name = strndup(pos, new_pos - pos);
+		if (nc->name == NULL)
+			test_error("strndup()");
+
+		if (unlikely(!strcmp(nc->name, "MaxConn")))
+			fmt = " %" PRId64; /* MaxConn is signed, RFC 2012 */
+		if (fscanf(fnetstat, fmt, &nc->val) != 1)
+			test_error("fscanf(%s)", nc->name);
+		pos = new_pos + 1;
+	}
+	type->counters_nr += nr_elems;
+
+	if (fread(&tmp, 1, 1, fnetstat) != 1 || tmp != '\n')
+		test_error("Unexpected netstat format");
+}
+
+static const char *snmp6_name = "Snmp6";
+static void snmp6_read(FILE *fnetstat, struct netstat **dest)
+{
+	struct netstat *type = lookup_get(*dest, snmp6_name, strlen(snmp6_name));
+	char *counter_name;
+	size_t i;
+
+	for (i = type->counters_nr;; i++) {
+		struct netstat_counter *nc;
+		uint64_t counter;
+
+		if (fscanf(fnetstat, "%ms", &counter_name) == EOF)
+			break;
+		if (fscanf(fnetstat, "%" PRIu64, &counter) == EOF)
+			test_error("Unexpected snmp6 format");
+		type->counters = reallocarray(type->counters, i + 1,
+					sizeof(struct netstat_counter));
+		if (!type->counters)
+			test_error("reallocarray()");
+		nc = &type->counters[i];
+		nc->name = counter_name;
+		nc->val = counter;
+	}
+	type->counters_nr = i;
+	*dest = type;
+}
+
+struct netstat *netstat_read(void)
+{
+	struct netstat *ret = 0;
+	size_t line_sz = 0;
+	char *line = NULL;
+	FILE *fnetstat;
+
+	/*
+	 * Opening thread-self instead of /proc/net/... as the latter
+	 * points to /proc/self/net/ which instantiates thread-leader's
+	 * net-ns, see:
+	 * commit 155134fef2b6 ("Revert "proc: Point /proc/{mounts,net} at..")
+	 */
+	errno = 0;
+	fnetstat = fopen("/proc/thread-self/net/netstat", "r");
+	if (fnetstat == NULL)
+		test_error("failed to open /proc/net/netstat");
+
+	while (getline(&line, &line_sz, fnetstat) != -1)
+		netstat_read_type(fnetstat, &ret, line);
+	fclose(fnetstat);
+
+	errno = 0;
+	fnetstat = fopen("/proc/thread-self/net/snmp", "r");
+	if (fnetstat == NULL)
+		test_error("failed to open /proc/net/snmp");
+
+	while (getline(&line, &line_sz, fnetstat) != -1)
+		netstat_read_type(fnetstat, &ret, line);
+	fclose(fnetstat);
+
+	errno = 0;
+	fnetstat = fopen("/proc/thread-self/net/snmp6", "r");
+	if (fnetstat == NULL)
+		test_error("failed to open /proc/net/snmp6");
+
+	snmp6_read(fnetstat, &ret);
+	fclose(fnetstat);
+
+	free(line);
+	return ret;
+}
+
+void netstat_free(struct netstat *ns)
+{
+	while (ns != NULL) {
+		struct netstat *prev = ns;
+		size_t i;
+
+		free(ns->header_name);
+		for (i = 0; i < ns->counters_nr; i++)
+			free(ns->counters[i].name);
+		free(ns->counters);
+		ns = ns->next;
+		free(prev);
+	}
+}
+
+static inline void
+__netstat_print_diff(uint64_t a, struct netstat *nsb, size_t i)
+{
+	if (unlikely(!strcmp(nsb->header_name, "MaxConn"))) {
+		test_print("%8s %25s: %" PRId64 " => %" PRId64,
+				nsb->header_name, nsb->counters[i].name,
+				a, nsb->counters[i].val);
+		return;
+	}
+
+	test_print("%8s %25s: %" PRIu64 " => %" PRIu64, nsb->header_name,
+			nsb->counters[i].name, a, nsb->counters[i].val);
+}
+
+void netstat_print_diff(struct netstat *nsa, struct netstat *nsb)
+{
+	size_t i, j;
+
+	while (nsb != NULL) {
+		if (unlikely(strcmp(nsb->header_name, nsa->header_name))) {
+			for (i = 0; i < nsb->counters_nr; i++)
+				__netstat_print_diff(0, nsb, i);
+			nsb = nsb->next;
+			continue;
+		}
+
+		if (nsb->counters_nr < nsa->counters_nr)
+			test_error("Unexpected: some counters disappeared!");
+
+		for (j = 0, i = 0; i < nsb->counters_nr; i++) {
+			if (strcmp(nsb->counters[i].name, nsa->counters[j].name)) {
+				__netstat_print_diff(0, nsb, i);
+				continue;
+			}
+
+			if (nsa->counters[j].val == nsb->counters[i].val) {
+				j++;
+				continue;
+			}
+
+			__netstat_print_diff(nsa->counters[j].val, nsb, i);
+			j++;
+		}
+		if (j != nsa->counters_nr)
+			test_error("Unexpected: some counters disappeared!");
+
+		nsb = nsb->next;
+		nsa = nsa->next;
+	}
+}
+
+uint64_t netstat_get(struct netstat *ns, const char *name, bool *not_found)
+{
+	if (not_found)
+		*not_found = false;
+
+	while (ns != NULL) {
+		size_t i;
+
+		for (i = 0; i < ns->counters_nr; i++) {
+			if (!strcmp(name, ns->counters[i].name))
+				return ns->counters[i].val;
+		}
+
+		ns = ns->next;
+	}
+
+	if (not_found)
+		*not_found = true;
+	return 0;
+}
diff --git a/tools/testing/selftests/net/tcp_ao/lib/repair.c b/tools/testing/selftests/net/tcp_ao/lib/repair.c
new file mode 100644
index 000000000000..9893b3ba69f5
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/lib/repair.c
@@ -0,0 +1,254 @@
+// SPDX-License-Identifier: GPL-2.0
+/* This is over-simplified TCP_REPAIR for TCP_ESTABLISHED sockets
+ * It tests that TCP-AO enabled connection can be restored.
+ * For the proper socket repair see:
+ * https://github.com/checkpoint-restore/criu/blob/criu-dev/soccr/soccr.h
+ */
+#include <fcntl.h>
+#include <linux/sockios.h>
+#include <sys/ioctl.h>
+#include "aolib.h"
+
+#ifndef TCPOPT_MAXSEG
+# define TCPOPT_MAXSEG		2
+#endif
+#ifndef TCPOPT_WINDOW
+# define TCPOPT_WINDOW		3
+#endif
+#ifndef TCPOPT_SACK_PERMITTED
+# define TCPOPT_SACK_PERMITTED	4
+#endif
+#ifndef TCPOPT_TIMESTAMP
+# define TCPOPT_TIMESTAMP	8
+#endif
+
+enum {
+	TCP_ESTABLISHED = 1,
+	TCP_SYN_SENT,
+	TCP_SYN_RECV,
+	TCP_FIN_WAIT1,
+	TCP_FIN_WAIT2,
+	TCP_TIME_WAIT,
+	TCP_CLOSE,
+	TCP_CLOSE_WAIT,
+	TCP_LAST_ACK,
+	TCP_LISTEN,
+	TCP_CLOSING,	/* Now a valid state */
+	TCP_NEW_SYN_RECV,
+
+	TCP_MAX_STATES	/* Leave at the end! */
+};
+
+static void test_sock_checkpoint_queue(int sk, int queue, int qlen,
+				       struct tcp_sock_queue *q)
+{
+	socklen_t len;
+	int ret;
+
+	if (setsockopt(sk, SOL_TCP, TCP_REPAIR_QUEUE, &queue, sizeof(queue)))
+		test_error("setsockopt(TCP_REPAIR_QUEUE)");
+
+	len = sizeof(q->seq);
+	ret = getsockopt(sk, SOL_TCP, TCP_QUEUE_SEQ, &q->seq, &len);
+	if (ret || len != sizeof(q->seq))
+		test_error("getsockopt(TCP_QUEUE_SEQ): %d", (int)len);
+
+	if (!qlen) {
+		q->buf = NULL;
+		return;
+	}
+
+	q->buf = malloc(qlen);
+	if (q->buf == NULL)
+		test_error("malloc()");
+	ret = recv(sk, q->buf, qlen, MSG_PEEK | MSG_DONTWAIT);
+	if (ret != qlen)
+		test_error("recv(%d): %d", qlen, ret);
+}
+
+void __test_sock_checkpoint(int sk, struct tcp_sock_state *state,
+			    void *addr, size_t addr_size)
+{
+	socklen_t len = sizeof(state->info);
+	int ret;
+
+	memset(state, 0, sizeof(*state));
+
+	ret = getsockopt(sk, SOL_TCP, TCP_INFO, &state->info, &len);
+	if (ret || len != sizeof(state->info))
+		test_error("getsockopt(TCP_INFO): %d", (int)len);
+
+	len = addr_size;
+	if (getsockname(sk, addr, &len) || len != addr_size)
+		test_error("getsockname(): %d", (int)len);
+
+	len = sizeof(state->trw);
+	ret = getsockopt(sk, SOL_TCP, TCP_REPAIR_WINDOW, &state->trw, &len);
+	if (ret || len != sizeof(state->trw))
+		test_error("getsockopt(TCP_REPAIR_WINDOW): %d", (int)len);
+
+	if (ioctl(sk, SIOCOUTQ, &state->outq_len))
+		test_error("ioctl(SIOCOUTQ)");
+
+	if (ioctl(sk, SIOCOUTQNSD, &state->outq_nsd_len))
+		test_error("ioctl(SIOCOUTQNSD)");
+	test_sock_checkpoint_queue(sk, TCP_SEND_QUEUE, state->outq_len, &state->out);
+
+	if (ioctl(sk, SIOCINQ, &state->inq_len))
+		test_error("ioctl(SIOCINQ)");
+	test_sock_checkpoint_queue(sk, TCP_RECV_QUEUE, state->inq_len, &state->in);
+
+	if (state->info.tcpi_state == TCP_CLOSE)
+		state->outq_len = state->outq_nsd_len = 0;
+
+	len = sizeof(state->mss);
+	ret = getsockopt(sk, SOL_TCP, TCP_MAXSEG, &state->mss, &len);
+	if (ret || len != sizeof(state->mss))
+		test_error("getsockopt(TCP_MAXSEG): %d", (int)len);
+
+	len = sizeof(state->timestamp);
+	ret = getsockopt(sk, SOL_TCP, TCP_TIMESTAMP, &state->timestamp, &len);
+	if (ret || len != sizeof(state->timestamp))
+		test_error("getsockopt(TCP_TIMESTAMP): %d", (int)len);
+}
+
+void test_ao_checkpoint(int sk, struct tcp_ao_repair *state)
+{
+	socklen_t len = sizeof(*state);
+	int ret;
+
+	memset(state, 0, sizeof(*state));
+
+	ret = getsockopt(sk, SOL_TCP, TCP_AO_REPAIR, state, &len);
+	if (ret || len != sizeof(*state))
+		test_error("getsockopt(TCP_AO_REPAIR): %d", (int)len);
+}
+
+static void test_sock_restore_seq(int sk, int queue, uint32_t seq)
+{
+	if (setsockopt(sk, SOL_TCP, TCP_REPAIR_QUEUE, &queue, sizeof(queue)))
+		test_error("setsockopt(TCP_REPAIR_QUEUE)");
+
+	if (setsockopt(sk, SOL_TCP, TCP_QUEUE_SEQ, &seq, sizeof(seq)))
+		test_error("setsockopt(TCP_QUEUE_SEQ)");
+}
+
+static void test_sock_restore_queue(int sk, int queue, void *buf, int len)
+{
+	int chunk = len;
+	size_t off = 0;
+
+	if (len == 0)
+		return;
+
+	if (setsockopt(sk, SOL_TCP, TCP_REPAIR_QUEUE, &queue, sizeof(queue)))
+		test_error("setsockopt(TCP_REPAIR_QUEUE)");
+
+	do {
+		int ret;
+
+		ret = send(sk, buf + off, chunk, 0);
+		if (ret <= 0) {
+			if (chunk > 1024) {
+				chunk >>= 1;
+				continue;
+			}
+			test_error("send()");
+		}
+		off += ret;
+		len -= ret;
+	} while (len > 0);
+}
+
+void __test_sock_restore(int sk, const char *device,
+			 struct tcp_sock_state *state,
+			 void *saddr, void *daddr, size_t addr_size)
+{
+	struct tcp_repair_opt opts[4];
+	unsigned int opt_nr = 0;
+	long flags;
+
+	if (bind(sk, saddr, addr_size))
+		test_error("bind()");
+
+	flags = fcntl(sk, F_GETFL);
+	if ((flags < 0) || (fcntl(sk, F_SETFL, flags | O_NONBLOCK) < 0))
+		test_error("fcntl()");
+
+	test_sock_restore_seq(sk, TCP_RECV_QUEUE, state->in.seq - state->inq_len);
+	test_sock_restore_seq(sk, TCP_SEND_QUEUE, state->out.seq - state->outq_len);
+
+	if (device != NULL && setsockopt(sk, SOL_SOCKET, SO_BINDTODEVICE,
+					 device, strlen(device) + 1))
+		test_error("setsockopt(SO_BINDTODEVICE, %s)", device);
+
+	if (connect(sk, daddr, addr_size))
+		test_error("connect()");
+
+	if (state->info.tcpi_options & TCPI_OPT_SACK) {
+		opts[opt_nr].opt_code = TCPOPT_SACK_PERMITTED;
+		opts[opt_nr].opt_val = 0;
+		opt_nr++;
+	}
+	if (state->info.tcpi_options & TCPI_OPT_WSCALE) {
+		opts[opt_nr].opt_code = TCPOPT_WINDOW;
+		opts[opt_nr].opt_val = state->info.tcpi_snd_wscale +
+				(state->info.tcpi_rcv_wscale << 16);
+		opt_nr++;
+	}
+	if (state->info.tcpi_options & TCPI_OPT_TIMESTAMPS) {
+		opts[opt_nr].opt_code = TCPOPT_TIMESTAMP;
+		opts[opt_nr].opt_val = 0;
+		opt_nr++;
+	}
+	opts[opt_nr].opt_code = TCPOPT_MAXSEG;
+	opts[opt_nr].opt_val = state->mss;
+	opt_nr++;
+
+	if (setsockopt(sk, SOL_TCP, TCP_REPAIR_OPTIONS, opts, opt_nr * sizeof(opts[0])))
+		test_error("setsockopt(TCP_REPAIR_OPTIONS)");
+
+	if (state->info.tcpi_options & TCPI_OPT_TIMESTAMPS) {
+		if (setsockopt(sk, SOL_TCP, TCP_TIMESTAMP,
+			       &state->timestamp, opt_nr * sizeof(opts[0])))
+			test_error("setsockopt(TCP_TIMESTAMP)");
+	}
+	test_sock_restore_queue(sk, TCP_RECV_QUEUE, state->in.buf, state->inq_len);
+	test_sock_restore_queue(sk, TCP_SEND_QUEUE, state->out.buf, state->outq_len);
+	if (setsockopt(sk, SOL_TCP, TCP_REPAIR_WINDOW, &state->trw, sizeof(state->trw)))
+		test_error("setsockopt(TCP_REPAIR_WINDOW)");
+}
+
+void test_ao_restore(int sk, struct tcp_ao_repair *state)
+{
+	if (setsockopt(sk, SOL_TCP, TCP_AO_REPAIR, state, sizeof(*state)))
+		test_error("setsockopt(TCP_AO_REPAIR)");
+}
+
+void test_sock_state_free(struct tcp_sock_state *state)
+{
+	free(state->out.buf);
+	free(state->in.buf);
+}
+
+void test_enable_repair(int sk)
+{
+	int val = TCP_REPAIR_ON;
+
+	if (setsockopt(sk, SOL_TCP, TCP_REPAIR, &val, sizeof(val)))
+		test_error("setsockopt(TCP_REPAIR)");
+}
+
+void test_disable_repair(int sk)
+{
+	int val = TCP_REPAIR_OFF_NO_WP;
+
+	if (setsockopt(sk, SOL_TCP, TCP_REPAIR, &val, sizeof(val)))
+		test_error("setsockopt(TCP_REPAIR)");
+}
+
+void test_kill_sk(int sk)
+{
+	test_enable_repair(sk);
+	close(sk);
+}
diff --git a/tools/testing/selftests/net/tcp_ao/lib/setup.c b/tools/testing/selftests/net/tcp_ao/lib/setup.c
new file mode 100644
index 000000000000..92276f916f2f
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/lib/setup.c
@@ -0,0 +1,361 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <fcntl.h>
+#include <pthread.h>
+#include <sched.h>
+#include <signal.h>
+#include "aolib.h"
+
+/*
+ * Can't be included in the header: it defines static variables which
+ * will be unique to every object. Let's include it only once here.
+ */
+#include "../../../kselftest.h"
+
+/* Prevent overriding of one thread's output by another */
+static pthread_mutex_t ksft_print_lock = PTHREAD_MUTEX_INITIALIZER;
+
+void __test_msg(const char *buf)
+{
+	pthread_mutex_lock(&ksft_print_lock);
+	ksft_print_msg(buf);
+	pthread_mutex_unlock(&ksft_print_lock);
+}
+void __test_ok(const char *buf)
+{
+	pthread_mutex_lock(&ksft_print_lock);
+	ksft_test_result_pass(buf);
+	pthread_mutex_unlock(&ksft_print_lock);
+}
+void __test_fail(const char *buf)
+{
+	pthread_mutex_lock(&ksft_print_lock);
+	ksft_test_result_fail(buf);
+	pthread_mutex_unlock(&ksft_print_lock);
+}
+void __test_xfail(const char *buf)
+{
+	pthread_mutex_lock(&ksft_print_lock);
+	ksft_test_result_xfail(buf);
+	pthread_mutex_unlock(&ksft_print_lock);
+}
+void __test_error(const char *buf)
+{
+	pthread_mutex_lock(&ksft_print_lock);
+	ksft_test_result_error(buf);
+	pthread_mutex_unlock(&ksft_print_lock);
+}
+void __test_skip(const char *buf)
+{
+	pthread_mutex_lock(&ksft_print_lock);
+	ksft_test_result_skip(buf);
+	pthread_mutex_unlock(&ksft_print_lock);
+}
+
+static volatile int failed;
+static volatile int skipped;
+
+void test_failed(void)
+{
+	failed = 1;
+}
+
+static void test_exit(void)
+{
+	if (failed) {
+		ksft_exit_fail();
+	} else if (skipped) {
+		/* ksft_exit_skip() is different from ksft_exit_*() */
+		ksft_print_cnts();
+		exit(KSFT_SKIP);
+	} else {
+		ksft_exit_pass();
+	}
+}
+
+struct dlist_t {
+	void (*destruct)(void);
+	struct dlist_t *next;
+};
+static struct dlist_t *destructors_list;
+
+void test_add_destructor(void (*d)(void))
+{
+	struct dlist_t *p;
+
+	p = malloc(sizeof(struct dlist_t));
+	if (p == NULL)
+		test_error("malloc() failed");
+
+	p->next = destructors_list;
+	p->destruct = d;
+	destructors_list = p;
+}
+
+static void test_destructor(void) __attribute__((destructor));
+static void test_destructor(void)
+{
+	while (destructors_list) {
+		struct dlist_t *p = destructors_list->next;
+
+		destructors_list->destruct();
+		free(destructors_list);
+		destructors_list = p;
+	}
+	test_exit();
+}
+
+static void sig_int(int signo)
+{
+	test_error("Caught SIGINT - exiting");
+}
+
+int open_netns(void)
+{
+	const char *netns_path = "/proc/self/ns/net";
+	int fd;
+
+	fd = open(netns_path, O_RDONLY);
+	if (fd < 0)
+		test_error("open(%s)", netns_path);
+	return fd;
+}
+
+int unshare_open_netns(void)
+{
+	if (unshare(CLONE_NEWNET) != 0)
+		test_error("unshare()");
+
+	return open_netns();
+}
+
+void switch_ns(int fd)
+{
+	if (setns(fd, CLONE_NEWNET))
+		test_error("setns()");
+}
+
+int switch_save_ns(int new_ns)
+{
+	int ret = open_netns();
+
+	switch_ns(new_ns);
+	return ret;
+}
+
+static int nsfd_outside	= -1;
+static int nsfd_parent	= -1;
+static int nsfd_child	= -1;
+const char veth_name[]	= "ktst-veth";
+
+static void init_namespaces(void)
+{
+	nsfd_outside = open_netns();
+	nsfd_parent = unshare_open_netns();
+	nsfd_child = unshare_open_netns();
+}
+
+static void link_init(const char *veth, int family, uint8_t prefix,
+		      union tcp_addr addr, union tcp_addr dest)
+{
+	if (link_set_up(veth))
+		test_error("Failed to set link up");
+	if (ip_addr_add(veth, family, addr, prefix))
+		test_error("Failed to add ip address");
+	if (ip_route_add(veth, family, addr, dest))
+		test_error("Failed to add route");
+}
+
+static unsigned int nr_threads = 1;
+
+static pthread_mutex_t sync_lock = PTHREAD_MUTEX_INITIALIZER;
+static pthread_cond_t sync_cond = PTHREAD_COND_INITIALIZER;
+static volatile unsigned int stage_threads[2];
+static volatile unsigned int stage_nr;
+
+/* synchronize all threads in the same stage */
+void synchronize_threads(void)
+{
+	unsigned int q = stage_nr;
+
+	pthread_mutex_lock(&sync_lock);
+	stage_threads[q]++;
+	if (stage_threads[q] == nr_threads) {
+		stage_nr ^= 1;
+		stage_threads[stage_nr] = 0;
+		pthread_cond_signal(&sync_cond);
+	}
+	while (stage_threads[q] < nr_threads)
+		pthread_cond_wait(&sync_cond, &sync_lock);
+	pthread_mutex_unlock(&sync_lock);
+}
+
+__thread union tcp_addr this_ip_addr;
+__thread union tcp_addr this_ip_dest;
+int test_family;
+
+struct new_pthread_arg {
+	thread_fn	func;
+	union tcp_addr	my_ip;
+	union tcp_addr	dest_ip;
+};
+static void *new_pthread_entry(void *arg)
+{
+	struct new_pthread_arg *p = arg;
+
+	this_ip_addr = p->my_ip;
+	this_ip_dest = p->dest_ip;
+	p->func(NULL); /* shouldn't return */
+	exit(KSFT_FAIL);
+}
+
+static void __test_skip_all(const char *msg)
+{
+	ksft_set_plan(1);
+	ksft_print_header();
+	skipped = 1;
+	test_skip("%s", msg);
+	exit(KSFT_SKIP);
+}
+
+void __test_init(unsigned int ntests, int family, unsigned int prefix,
+		 union tcp_addr addr1, union tcp_addr addr2,
+		 thread_fn peer1, thread_fn peer2)
+{
+	struct sigaction sa = {
+		.sa_handler = sig_int,
+		.sa_flags = SA_RESTART,
+	};
+	time_t seed = time(NULL);
+
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(SIGINT, &sa, NULL))
+		test_error("Can't set SIGINT handler");
+
+	test_family = family;
+	if (!kernel_config_has(KCONFIG_NET_NS))
+		__test_skip_all(tests_skip_reason[KCONFIG_NET_NS]);
+	if (!kernel_config_has(KCONFIG_VETH))
+		__test_skip_all(tests_skip_reason[KCONFIG_VETH]);
+	if (!kernel_config_has(KCONFIG_TCP_AO))
+		__test_skip_all(tests_skip_reason[KCONFIG_TCP_AO]);
+
+	ksft_set_plan(ntests);
+	test_print("rand seed %u", (unsigned int)seed);
+	srand(seed);
+
+
+	ksft_print_header();
+	init_namespaces();
+
+	if (add_veth(veth_name, nsfd_parent, nsfd_child))
+		test_error("Failed to add veth");
+
+	switch_ns(nsfd_child);
+	link_init(veth_name, family, prefix, addr2, addr1);
+	if (peer2) {
+		struct new_pthread_arg targ;
+		pthread_t t;
+
+		targ.my_ip = addr2;
+		targ.dest_ip = addr1;
+		targ.func = peer2;
+		nr_threads++;
+		if (pthread_create(&t, NULL, new_pthread_entry, &targ))
+			test_error("Failed to create pthread");
+	}
+	switch_ns(nsfd_parent);
+	link_init(veth_name, family, prefix, addr1, addr2);
+
+	this_ip_addr = addr1;
+	this_ip_dest = addr2;
+	peer1(NULL);
+	if (failed)
+		exit(KSFT_FAIL);
+	else
+		exit(KSFT_PASS);
+}
+
+/* /proc/sys/net/core/optmem_max artifically limits the amount of memory
+ * that can be allocated with sock_kmalloc() on each socket in the system.
+ * It is not virtualized in v6.7, so it has to written outside test
+ * namespaces. To be nice a test will revert optmem back to the old value.
+ * Keeping it simple without any file lock, which means the tests that
+ * need to set/increase optmem value shouldn't run in parallel.
+ * Also, not re-entrant.
+ * Since commit f5769faeec36 ("net: Namespace-ify sysctl_optmem_max")
+ * it is per-namespace, keeping logic for non-virtualized optmem_max
+ * for v6.7, which supports TCP-AO.
+ */
+static const char *optmem_file = "/proc/sys/net/core/optmem_max";
+static size_t saved_optmem;
+static int optmem_ns = -1;
+
+static bool is_optmem_namespaced(void)
+{
+	if (optmem_ns == -1) {
+		int old_ns = switch_save_ns(nsfd_child);
+
+		optmem_ns = !access(optmem_file, F_OK);
+		switch_ns(old_ns);
+	}
+	return !!optmem_ns;
+}
+
+size_t test_get_optmem(void)
+{
+	int old_ns = 0;
+	FILE *foptmem;
+	size_t ret;
+
+	if (!is_optmem_namespaced())
+		old_ns = switch_save_ns(nsfd_outside);
+	foptmem = fopen(optmem_file, "r");
+	if (!foptmem)
+		test_error("failed to open %s", optmem_file);
+
+	if (fscanf(foptmem, "%zu", &ret) != 1)
+		test_error("can't read from %s", optmem_file);
+	fclose(foptmem);
+	if (!is_optmem_namespaced())
+		switch_ns(old_ns);
+	return ret;
+}
+
+static void __test_set_optmem(size_t new, size_t *old)
+{
+	int old_ns = 0;
+	FILE *foptmem;
+
+	if (old != NULL)
+		*old = test_get_optmem();
+
+	if (!is_optmem_namespaced())
+		old_ns = switch_save_ns(nsfd_outside);
+	foptmem = fopen(optmem_file, "w");
+	if (!foptmem)
+		test_error("failed to open %s", optmem_file);
+
+	if (fprintf(foptmem, "%zu", new) <= 0)
+		test_error("can't write %zu to %s", new, optmem_file);
+	fclose(foptmem);
+	if (!is_optmem_namespaced())
+		switch_ns(old_ns);
+}
+
+static void test_revert_optmem(void)
+{
+	if (saved_optmem == 0)
+		return;
+
+	__test_set_optmem(saved_optmem, NULL);
+}
+
+void test_set_optmem(size_t value)
+{
+	if (saved_optmem == 0) {
+		__test_set_optmem(value, &saved_optmem);
+		test_add_destructor(test_revert_optmem);
+	} else {
+		__test_set_optmem(value, NULL);
+	}
+}
diff --git a/tools/testing/selftests/net/tcp_ao/lib/sock.c b/tools/testing/selftests/net/tcp_ao/lib/sock.c
new file mode 100644
index 000000000000..c75d82885a2e
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/lib/sock.c
@@ -0,0 +1,592 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <alloca.h>
+#include <fcntl.h>
+#include <inttypes.h>
+#include <string.h>
+#include "../../../../../include/linux/kernel.h"
+#include "../../../../../include/linux/stringify.h"
+#include "aolib.h"
+
+const unsigned int test_server_port = 7010;
+int __test_listen_socket(int backlog, void *addr, size_t addr_sz)
+{
+	int err, sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+	long flags;
+
+	if (sk < 0)
+		test_error("socket()");
+
+	err = setsockopt(sk, SOL_SOCKET, SO_BINDTODEVICE, veth_name,
+			 strlen(veth_name) + 1);
+	if (err < 0)
+		test_error("setsockopt(SO_BINDTODEVICE)");
+
+	if (bind(sk, (struct sockaddr *)addr, addr_sz) < 0)
+		test_error("bind()");
+
+	flags = fcntl(sk, F_GETFL);
+	if ((flags < 0) || (fcntl(sk, F_SETFL, flags | O_NONBLOCK) < 0))
+		test_error("fcntl()");
+
+	if (listen(sk, backlog))
+		test_error("listen()");
+
+	return sk;
+}
+
+int test_wait_fd(int sk, time_t sec, bool write)
+{
+	struct timeval tv = { .tv_sec = sec };
+	struct timeval *ptv = NULL;
+	fd_set fds, efds;
+	int ret;
+	socklen_t slen = sizeof(ret);
+
+	FD_ZERO(&fds);
+	FD_SET(sk, &fds);
+	FD_ZERO(&efds);
+	FD_SET(sk, &efds);
+
+	if (sec)
+		ptv = &tv;
+
+	errno = 0;
+	if (write)
+		ret = select(sk + 1, NULL, &fds, &efds, ptv);
+	else
+		ret = select(sk + 1, &fds, NULL, &efds, ptv);
+	if (ret < 0)
+		return -errno;
+	if (ret == 0) {
+		errno = ETIMEDOUT;
+		return -ETIMEDOUT;
+	}
+
+	if (getsockopt(sk, SOL_SOCKET, SO_ERROR, &ret, &slen) || ret)
+		return -ret;
+	return 0;
+}
+
+int __test_connect_socket(int sk, const char *device,
+			  void *addr, size_t addr_sz, time_t timeout)
+{
+	long flags;
+	int err;
+
+	if (device != NULL) {
+		err = setsockopt(sk, SOL_SOCKET, SO_BINDTODEVICE, device,
+				 strlen(device) + 1);
+		if (err < 0)
+			test_error("setsockopt(SO_BINDTODEVICE, %s)", device);
+	}
+
+	if (!timeout) {
+		err = connect(sk, addr, addr_sz);
+		if (err) {
+			err = -errno;
+			goto out;
+		}
+		return 0;
+	}
+
+	flags = fcntl(sk, F_GETFL);
+	if ((flags < 0) || (fcntl(sk, F_SETFL, flags | O_NONBLOCK) < 0))
+		test_error("fcntl()");
+
+	if (connect(sk, addr, addr_sz) < 0) {
+		if (errno != EINPROGRESS) {
+			err = -errno;
+			goto out;
+		}
+		if (timeout < 0)
+			return sk;
+		err = test_wait_fd(sk, timeout, 1);
+		if (err)
+			goto out;
+	}
+	return sk;
+
+out:
+	close(sk);
+	return err;
+}
+
+int __test_set_md5(int sk, void *addr, size_t addr_sz, uint8_t prefix,
+		   int vrf, const char *password)
+{
+	size_t pwd_len = strlen(password);
+	struct tcp_md5sig md5sig = {};
+
+	md5sig.tcpm_keylen = pwd_len;
+	memcpy(md5sig.tcpm_key, password, pwd_len);
+	md5sig.tcpm_flags = TCP_MD5SIG_FLAG_PREFIX;
+	md5sig.tcpm_prefixlen = prefix;
+	if (vrf >= 0) {
+		md5sig.tcpm_flags |= TCP_MD5SIG_FLAG_IFINDEX;
+		md5sig.tcpm_ifindex = (uint8_t)vrf;
+	}
+	memcpy(&md5sig.tcpm_addr, addr, addr_sz);
+
+	errno = 0;
+	return setsockopt(sk, IPPROTO_TCP, TCP_MD5SIG_EXT,
+			&md5sig, sizeof(md5sig));
+}
+
+
+int test_prepare_key_sockaddr(struct tcp_ao_add *ao, const char *alg,
+		void *addr, size_t addr_sz, bool set_current, bool set_rnext,
+		uint8_t prefix, uint8_t vrf, uint8_t sndid, uint8_t rcvid,
+		uint8_t maclen, uint8_t keyflags,
+		uint8_t keylen, const char *key)
+{
+	memset(ao, 0, sizeof(struct tcp_ao_add));
+
+	ao->set_current	= !!set_current;
+	ao->set_rnext	= !!set_rnext;
+	ao->prefix	= prefix;
+	ao->sndid	= sndid;
+	ao->rcvid	= rcvid;
+	ao->maclen	= maclen;
+	ao->keyflags	= keyflags;
+	ao->keylen	= keylen;
+	ao->ifindex	= vrf;
+
+	memcpy(&ao->addr, addr, addr_sz);
+
+	if (strlen(alg) > 64)
+		return -ENOBUFS;
+	strncpy(ao->alg_name, alg, 64);
+
+	memcpy(ao->key, key,
+	       (keylen > TCP_AO_MAXKEYLEN) ? TCP_AO_MAXKEYLEN : keylen);
+	return 0;
+}
+
+static int test_get_ao_keys_nr(int sk)
+{
+	struct tcp_ao_getsockopt tmp = {};
+	socklen_t tmp_sz = sizeof(tmp);
+	int ret;
+
+	tmp.nkeys  = 1;
+	tmp.get_all = 1;
+
+	ret = getsockopt(sk, IPPROTO_TCP, TCP_AO_GET_KEYS, &tmp, &tmp_sz);
+	if (ret)
+		return -errno;
+	return (int)tmp.nkeys;
+}
+
+int test_get_one_ao(int sk, struct tcp_ao_getsockopt *out,
+		void *addr, size_t addr_sz, uint8_t prefix,
+		uint8_t sndid, uint8_t rcvid)
+{
+	struct tcp_ao_getsockopt tmp = {};
+	socklen_t tmp_sz = sizeof(tmp);
+	int ret;
+
+	memcpy(&tmp.addr, addr, addr_sz);
+	tmp.prefix = prefix;
+	tmp.sndid  = sndid;
+	tmp.rcvid  = rcvid;
+	tmp.nkeys  = 1;
+
+	ret = getsockopt(sk, IPPROTO_TCP, TCP_AO_GET_KEYS, &tmp, &tmp_sz);
+	if (ret)
+		return ret;
+	if (tmp.nkeys != 1)
+		return -E2BIG;
+	*out = tmp;
+	return 0;
+}
+
+int test_get_ao_info(int sk, struct tcp_ao_info_opt *out)
+{
+	socklen_t sz = sizeof(*out);
+
+	out->reserved = 0;
+	out->reserved2 = 0;
+	if (getsockopt(sk, IPPROTO_TCP, TCP_AO_INFO, out, &sz))
+		return -errno;
+	if (sz != sizeof(*out))
+		return -EMSGSIZE;
+	return 0;
+}
+
+int test_set_ao_info(int sk, struct tcp_ao_info_opt *in)
+{
+	socklen_t sz = sizeof(*in);
+
+	in->reserved = 0;
+	in->reserved2 = 0;
+	if (setsockopt(sk, IPPROTO_TCP, TCP_AO_INFO, in, sz))
+		return -errno;
+	return 0;
+}
+
+int test_cmp_getsockopt_setsockopt(const struct tcp_ao_add *a,
+				   const struct tcp_ao_getsockopt *b)
+{
+	bool is_kdf_aes_128_cmac = false;
+	bool is_cmac_aes = false;
+
+	if (!strcmp("cmac(aes128)", a->alg_name)) {
+		is_kdf_aes_128_cmac = (a->keylen != 16);
+		is_cmac_aes = true;
+	}
+
+#define __cmp_ao(member)						\
+do {									\
+	if (b->member != a->member) {					\
+		test_fail("getsockopt(): " __stringify(member) " %u != %u",	\
+				b->member, a->member);			\
+		return -1;						\
+	}								\
+} while(0)
+	__cmp_ao(sndid);
+	__cmp_ao(rcvid);
+	__cmp_ao(prefix);
+	__cmp_ao(keyflags);
+	__cmp_ao(ifindex);
+	if (a->maclen) {
+		__cmp_ao(maclen);
+	} else if (b->maclen != 12) {
+		test_fail("getsockopt(): expected default maclen 12, but it's %u",
+				b->maclen);
+		return -1;
+	}
+	if (!is_kdf_aes_128_cmac) {
+		__cmp_ao(keylen);
+	} else if (b->keylen != 16) {
+		test_fail("getsockopt(): expected keylen 16 for cmac(aes128), but it's %u",
+				b->keylen);
+		return -1;
+	}
+#undef __cmp_ao
+	if (!is_kdf_aes_128_cmac && memcmp(b->key, a->key, a->keylen)) {
+		test_fail("getsockopt(): returned key is different `%s' != `%s'",
+				b->key, a->key);
+		return -1;
+	}
+	if (memcmp(&b->addr, &a->addr, sizeof(b->addr))) {
+		test_fail("getsockopt(): returned address is different");
+		return -1;
+	}
+	if (!is_cmac_aes && strcmp(b->alg_name, a->alg_name)) {
+		test_fail("getsockopt(): returned algorithm %s is different than %s", b->alg_name, a->alg_name);
+		return -1;
+	}
+	if (is_cmac_aes && strcmp(b->alg_name, "cmac(aes)")) {
+		test_fail("getsockopt(): returned algorithm %s is different than cmac(aes)", b->alg_name);
+		return -1;
+	}
+	/* For a established key rotation test don't add a key with
+	 * set_current = 1, as it's likely to change by peer's request;
+	 * rather use setsockopt(TCP_AO_INFO)
+	 */
+	if (a->set_current != b->is_current) {
+		test_fail("getsockopt(): returned key is not Current_key");
+		return -1;
+	}
+	if (a->set_rnext != b->is_rnext) {
+		test_fail("getsockopt(): returned key is not RNext_key");
+		return -1;
+	}
+
+	return 0;
+}
+
+int test_cmp_getsockopt_setsockopt_ao(const struct tcp_ao_info_opt *a,
+				      const struct tcp_ao_info_opt *b)
+{
+	/* No check for ::current_key, as it may change by the peer */
+	if (a->ao_required != b->ao_required) {
+		test_fail("getsockopt(): returned ao doesn't have ao_required");
+		return -1;
+	}
+	if (a->accept_icmps != b->accept_icmps) {
+		test_fail("getsockopt(): returned ao doesn't accept ICMPs");
+		return -1;
+	}
+	if (a->set_rnext && a->rnext != b->rnext) {
+		test_fail("getsockopt(): RNext KeyID has changed");
+		return -1;
+	}
+#define __cmp_cnt(member)						\
+do {									\
+	if (b->member != a->member) {					\
+		test_fail("getsockopt(): " __stringify(member) " %llu != %llu",	\
+				b->member, a->member);			\
+		return -1;						\
+	}								\
+} while(0)
+	if (a->set_counters) {
+		__cmp_cnt(pkt_good);
+		__cmp_cnt(pkt_bad);
+		__cmp_cnt(pkt_key_not_found);
+		__cmp_cnt(pkt_ao_required);
+		__cmp_cnt(pkt_dropped_icmp);
+	}
+#undef __cmp_cnt
+	return 0;
+}
+
+int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out)
+{
+	struct tcp_ao_getsockopt *key_dump;
+	socklen_t key_dump_sz = sizeof(*key_dump);
+	struct tcp_ao_info_opt info = {};
+	bool c1, c2, c3, c4, c5;
+	struct netstat *ns;
+	int err, nr_keys;
+
+	memset(out, 0, sizeof(*out));
+
+	/* per-netns */
+	ns = netstat_read();
+	out->netns_ao_good = netstat_get(ns, "TCPAOGood", &c1);
+	out->netns_ao_bad = netstat_get(ns, "TCPAOBad", &c2);
+	out->netns_ao_key_not_found = netstat_get(ns, "TCPAOKeyNotFound", &c3);
+	out->netns_ao_required = netstat_get(ns, "TCPAORequired", &c4);
+	out->netns_ao_dropped_icmp = netstat_get(ns, "TCPAODroppedIcmps", &c5);
+	netstat_free(ns);
+	if (c1 || c2 || c3 || c4 || c5)
+		return -EOPNOTSUPP;
+
+	err = test_get_ao_info(sk, &info);
+	if (err)
+		return err;
+
+	/* per-socket */
+	out->ao_info_pkt_good		= info.pkt_good;
+	out->ao_info_pkt_bad		= info.pkt_bad;
+	out->ao_info_pkt_key_not_found	= info.pkt_key_not_found;
+	out->ao_info_pkt_ao_required	= info.pkt_ao_required;
+	out->ao_info_pkt_dropped_icmp	= info.pkt_dropped_icmp;
+
+	/* per-key */
+	nr_keys = test_get_ao_keys_nr(sk);
+	if (nr_keys < 0)
+		return nr_keys;
+	if (nr_keys == 0)
+		test_error("test_get_ao_keys_nr() == 0");
+	out->nr_keys = (size_t)nr_keys;
+	key_dump = calloc(nr_keys, key_dump_sz);
+	if (!key_dump)
+		return -errno;
+
+	key_dump[0].nkeys = nr_keys;
+	key_dump[0].get_all = 1;
+	key_dump[0].get_all = 1;
+	err = getsockopt(sk, IPPROTO_TCP, TCP_AO_GET_KEYS,
+			 key_dump, &key_dump_sz);
+	if (err) {
+		free(key_dump);
+		return -errno;
+	}
+
+	out->key_cnts = calloc(nr_keys, sizeof(out->key_cnts[0]));
+	if (!out->key_cnts) {
+		free(key_dump);
+		return -errno;
+	}
+
+	while (nr_keys--) {
+		out->key_cnts[nr_keys].sndid = key_dump[nr_keys].sndid;
+		out->key_cnts[nr_keys].rcvid = key_dump[nr_keys].rcvid;
+		out->key_cnts[nr_keys].pkt_good = key_dump[nr_keys].pkt_good;
+		out->key_cnts[nr_keys].pkt_bad = key_dump[nr_keys].pkt_bad;
+	}
+	free(key_dump);
+
+	return 0;
+}
+
+int __test_tcp_ao_counters_cmp(const char *tst_name,
+			       struct tcp_ao_counters *before,
+			       struct tcp_ao_counters *after,
+			       test_cnt expected)
+{
+#define __cmp_ao(cnt, expecting_inc)					\
+do {									\
+	if (before->cnt > after->cnt) {					\
+		test_fail("%s: Decreased counter " __stringify(cnt) " %" PRIu64 " > %" PRIu64, \
+			  tst_name ?: "", before->cnt, after->cnt);		\
+		return -1;						\
+	}								\
+	if ((before->cnt != after->cnt) != (expecting_inc)) {		\
+		test_fail("%s: Counter " __stringify(cnt) " was %sexpected to increase %" PRIu64 " => %" PRIu64, \
+			  tst_name ?: "", (expecting_inc) ? "" : "not ",	\
+			  before->cnt, after->cnt);			\
+		return -1;						\
+	}								\
+} while(0)
+
+	errno = 0;
+	/* per-netns */
+	__cmp_ao(netns_ao_good, !!(expected & TEST_CNT_NS_GOOD));
+	__cmp_ao(netns_ao_bad, !!(expected & TEST_CNT_NS_BAD));
+	__cmp_ao(netns_ao_key_not_found,
+		 !!(expected & TEST_CNT_NS_KEY_NOT_FOUND));
+	__cmp_ao(netns_ao_required, !!(expected & TEST_CNT_NS_AO_REQUIRED));
+	__cmp_ao(netns_ao_dropped_icmp,
+		 !!(expected & TEST_CNT_NS_DROPPED_ICMP));
+	/* per-socket */
+	__cmp_ao(ao_info_pkt_good, !!(expected & TEST_CNT_SOCK_GOOD));
+	__cmp_ao(ao_info_pkt_bad, !!(expected & TEST_CNT_SOCK_BAD));
+	__cmp_ao(ao_info_pkt_key_not_found,
+		 !!(expected & TEST_CNT_SOCK_KEY_NOT_FOUND));
+	__cmp_ao(ao_info_pkt_ao_required, !!(expected & TEST_CNT_SOCK_AO_REQUIRED));
+	__cmp_ao(ao_info_pkt_dropped_icmp,
+		 !!(expected & TEST_CNT_SOCK_DROPPED_ICMP));
+	return 0;
+#undef __cmp_ao
+}
+
+int test_tcp_ao_key_counters_cmp(const char *tst_name,
+				 struct tcp_ao_counters *before,
+				 struct tcp_ao_counters *after,
+				 test_cnt expected,
+				 int sndid, int rcvid)
+{
+	size_t i;
+#define __cmp_ao(i, cnt, expecting_inc)					\
+do {									\
+	if (before->key_cnts[i].cnt > after->key_cnts[i].cnt) {		\
+		test_fail("%s: Decreased counter " __stringify(cnt) " %" PRIu64 " > %" PRIu64 " for key %u:%u", \
+			  tst_name ?: "", before->key_cnts[i].cnt,	\
+			  after->key_cnts[i].cnt,			\
+			  before->key_cnts[i].sndid,			\
+			  before->key_cnts[i].rcvid);			\
+		return -1;						\
+	}								\
+	if ((before->key_cnts[i].cnt != after->key_cnts[i].cnt) != (expecting_inc)) {		\
+		test_fail("%s: Counter " __stringify(cnt) " was %sexpected to increase %" PRIu64 " => %" PRIu64 " for key %u:%u", \
+			  tst_name ?: "", (expecting_inc) ? "" : "not ",\
+			  before->key_cnts[i].cnt,			\
+			  after->key_cnts[i].cnt,			\
+			  before->key_cnts[i].sndid,			\
+			  before->key_cnts[i].rcvid);			\
+		return -1;						\
+	}								\
+} while(0)
+
+	if (before->nr_keys != after->nr_keys) {
+		test_fail("%s: Keys changed on the socket %zu != %zu",
+			  tst_name, before->nr_keys, after->nr_keys);
+		return -1;
+	}
+
+	/* per-key */
+	i = before->nr_keys;
+	while (i--) {
+		if (sndid >= 0 && before->key_cnts[i].sndid != sndid)
+			continue;
+		if (rcvid >= 0 && before->key_cnts[i].rcvid != rcvid)
+			continue;
+		__cmp_ao(i, pkt_good, !!(expected & TEST_CNT_KEY_GOOD));
+		__cmp_ao(i, pkt_bad, !!(expected & TEST_CNT_KEY_BAD));
+	}
+	return 0;
+#undef __cmp_ao
+}
+
+void test_tcp_ao_counters_free(struct tcp_ao_counters *cnts)
+{
+	free(cnts->key_cnts);
+}
+
+#define TEST_BUF_SIZE 4096
+ssize_t test_server_run(int sk, ssize_t quota, time_t timeout_sec)
+{
+	ssize_t total = 0;
+
+	do {
+		char buf[TEST_BUF_SIZE];
+		ssize_t bytes, sent;
+		int ret;
+
+		ret = test_wait_fd(sk, timeout_sec, 0);
+		if (ret)
+			return ret;
+
+		bytes = recv(sk, buf, sizeof(buf), 0);
+
+		if (bytes < 0)
+			test_error("recv(): %zd", bytes);
+		if (bytes == 0)
+			break;
+
+		ret = test_wait_fd(sk, timeout_sec, 1);
+		if (ret)
+			return ret;
+
+		sent = send(sk, buf, bytes, 0);
+		if (sent == 0)
+			break;
+		if (sent != bytes)
+			test_error("send()");
+		total += bytes;
+	} while (!quota || total < quota);
+
+	return total;
+}
+
+ssize_t test_client_loop(int sk, char *buf, size_t buf_sz,
+			 const size_t msg_len, time_t timeout_sec)
+{
+	char msg[msg_len];
+	int nodelay = 1;
+	size_t i;
+
+	if (setsockopt(sk, IPPROTO_TCP, TCP_NODELAY, &nodelay, sizeof(nodelay)))
+		test_error("setsockopt(TCP_NODELAY)");
+
+	for (i = 0; i < buf_sz; i += min(msg_len, buf_sz - i)) {
+		size_t sent, bytes = min(msg_len, buf_sz - i);
+		int ret;
+
+		ret = test_wait_fd(sk, timeout_sec, 1);
+		if (ret)
+			return ret;
+
+		sent = send(sk, buf + i, bytes, 0);
+		if (sent == 0)
+			break;
+		if (sent != bytes)
+			test_error("send()");
+
+		bytes = 0;
+		do {
+			ssize_t got;
+
+			ret = test_wait_fd(sk, timeout_sec, 0);
+			if (ret)
+				return ret;
+
+			got = recv(sk, msg + bytes, sizeof(msg) - bytes, 0);
+			if (got <= 0)
+				return i;
+			bytes += got;
+		} while (bytes < sent);
+		if (bytes > sent)
+			test_error("recv(): %zd > %zd", bytes, sent);
+		if (memcmp(buf + i, msg, bytes) != 0) {
+			test_fail("received message differs");
+			return -1;
+		}
+	}
+	return i;
+}
+
+int test_client_verify(int sk, const size_t msg_len, const size_t nr,
+		       time_t timeout_sec)
+{
+	size_t buf_sz = msg_len * nr;
+	char *buf = alloca(buf_sz);
+
+	randomize_buffer(buf, buf_sz);
+	if (test_client_loop(sk, buf, buf_sz, msg_len, timeout_sec) != buf_sz)
+		return -1;
+	return 0;
+}
diff --git a/tools/testing/selftests/net/tcp_ao/lib/utils.c b/tools/testing/selftests/net/tcp_ao/lib/utils.c
new file mode 100644
index 000000000000..372daca525f5
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/lib/utils.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "aolib.h"
+#include <string.h>
+
+void randomize_buffer(void *buf, size_t buflen)
+{
+	int *p = (int *)buf;
+	size_t words = buflen / sizeof(int);
+	size_t leftover = buflen % sizeof(int);
+
+	if (!buflen)
+		return;
+
+	while (words--)
+		*p++ = rand();
+
+	if (leftover) {
+		int tmp = rand();
+
+		memcpy(buf + buflen - leftover, &tmp, leftover);
+	}
+}
+
+const struct sockaddr_in6 addr_any6 = {
+	.sin6_family	= AF_INET6,
+};
+
+const struct sockaddr_in addr_any4 = {
+	.sin_family	= AF_INET,
+};
diff --git a/tools/testing/selftests/net/tcp_ao/restore.c b/tools/testing/selftests/net/tcp_ao/restore.c
new file mode 100644
index 000000000000..8fdc808df325
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/restore.c
@@ -0,0 +1,236 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Author: Dmitry Safonov <dima@arista.com> */
+/* This is over-simplified TCP_REPAIR for TCP_ESTABLISHED sockets
+ * It tests that TCP-AO enabled connection can be restored.
+ * For the proper socket repair see:
+ * https://github.com/checkpoint-restore/criu/blob/criu-dev/soccr/soccr.h
+ */
+#include <inttypes.h>
+#include "aolib.h"
+
+const size_t nr_packets = 20;
+const size_t msg_len = 100;
+const size_t quota = nr_packets * msg_len;
+#define fault(type)	(inj == FAULT_ ## type)
+
+static void try_server_run(const char *tst_name, unsigned int port,
+			   fault_t inj, test_cnt cnt_expected)
+{
+	const char *cnt_name = "TCPAOGood";
+	struct tcp_ao_counters ao1, ao2;
+	uint64_t before_cnt, after_cnt;
+	int sk, lsk;
+	time_t timeout;
+	ssize_t bytes;
+
+	if (fault(TIMEOUT))
+		cnt_name = "TCPAOBad";
+	lsk = test_listen_socket(this_ip_addr, port, 1);
+
+	if (test_add_key(lsk, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100))
+		test_error("setsockopt(TCP_AO_ADD_KEY)");
+	synchronize_threads(); /* 1: MKT added => connect() */
+
+	if (test_wait_fd(lsk, TEST_TIMEOUT_SEC, 0))
+		test_error("test_wait_fd()");
+
+	sk = accept(lsk, NULL, NULL);
+	if (sk < 0)
+		test_error("accept()");
+
+	synchronize_threads(); /* 2: accepted => send data */
+	close(lsk);
+
+	bytes = test_server_run(sk, quota, TEST_TIMEOUT_SEC);
+	if (bytes != quota) {
+		test_fail("%s: server served: %zd", tst_name, bytes);
+		goto out;
+	}
+
+	before_cnt = netstat_get_one(cnt_name, NULL);
+	if (test_get_tcp_ao_counters(sk, &ao1))
+		test_error("test_get_tcp_ao_counters()");
+
+	timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
+	bytes = test_server_run(sk, quota, timeout);
+	if (fault(TIMEOUT)) {
+		if (bytes > 0)
+			test_fail("%s: server served: %zd", tst_name, bytes);
+		else
+			test_ok("%s: server couldn't serve", tst_name);
+	} else {
+		if (bytes != quota)
+			test_fail("%s: server served: %zd", tst_name, bytes);
+		else
+			test_ok("%s: server alive", tst_name);
+	}
+	if (test_get_tcp_ao_counters(sk, &ao2))
+		test_error("test_get_tcp_ao_counters()");
+	after_cnt = netstat_get_one(cnt_name, NULL);
+
+	test_tcp_ao_counters_cmp(tst_name, &ao1, &ao2, cnt_expected);
+
+	if (after_cnt <= before_cnt) {
+		test_fail("%s: %s counter did not increase: %zu <= %zu",
+				tst_name, cnt_name, after_cnt, before_cnt);
+	} else {
+		test_ok("%s: counter %s increased %zu => %zu",
+			tst_name, cnt_name, before_cnt, after_cnt);
+	}
+
+	/*
+	 * Before close() as that will send FIN and move the peer in TCP_CLOSE
+	 * and that will prevent reading AO counters from the peer's socket.
+	 */
+	synchronize_threads(); /* 3: verified => closed */
+out:
+	close(sk);
+}
+
+static void *server_fn(void *arg)
+{
+	unsigned int port = test_server_port;
+
+	try_server_run("TCP-AO migrate to another socket", port++,
+		       0, TEST_CNT_GOOD);
+	try_server_run("TCP-AO with wrong send ISN", port++,
+		       FAULT_TIMEOUT, TEST_CNT_BAD);
+	try_server_run("TCP-AO with wrong receive ISN", port++,
+		       FAULT_TIMEOUT, TEST_CNT_BAD);
+	try_server_run("TCP-AO with wrong send SEQ ext number", port++,
+		       FAULT_TIMEOUT, TEST_CNT_BAD);
+	try_server_run("TCP-AO with wrong receive SEQ ext number", port++,
+		       FAULT_TIMEOUT, TEST_CNT_NS_BAD | TEST_CNT_GOOD);
+
+	synchronize_threads(); /* don't race to exit: client exits */
+	return NULL;
+}
+
+static void test_get_sk_checkpoint(unsigned int server_port, sockaddr_af *saddr,
+				   struct tcp_sock_state *img,
+				   struct tcp_ao_repair *ao_img)
+{
+	int sk;
+
+	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+	if (sk < 0)
+		test_error("socket()");
+
+	if (test_add_key(sk, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100))
+		test_error("setsockopt(TCP_AO_ADD_KEY)");
+
+	synchronize_threads(); /* 1: MKT added => connect() */
+	if (test_connect_socket(sk, this_ip_dest, server_port) <= 0)
+		test_error("failed to connect()");
+
+	synchronize_threads(); /* 2: accepted => send data */
+	if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC))
+		test_fail("pre-migrate verify failed");
+
+	test_enable_repair(sk);
+	test_sock_checkpoint(sk, img, saddr);
+	test_ao_checkpoint(sk, ao_img);
+	test_kill_sk(sk);
+}
+
+static void test_sk_restore(const char *tst_name, unsigned int server_port,
+			    sockaddr_af *saddr, struct tcp_sock_state *img,
+			    struct tcp_ao_repair *ao_img,
+			    fault_t inj, test_cnt cnt_expected)
+{
+	const char *cnt_name = "TCPAOGood";
+	struct tcp_ao_counters ao1, ao2;
+	uint64_t before_cnt, after_cnt;
+	time_t timeout;
+	int sk;
+
+	if (fault(TIMEOUT))
+		cnt_name = "TCPAOBad";
+
+	before_cnt = netstat_get_one(cnt_name, NULL);
+	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+	if (sk < 0)
+		test_error("socket()");
+
+	test_enable_repair(sk);
+	test_sock_restore(sk, img, saddr, this_ip_dest, server_port);
+	if (test_add_repaired_key(sk, DEFAULT_TEST_PASSWORD, 0, this_ip_dest, -1, 100, 100))
+		test_error("setsockopt(TCP_AO_ADD_KEY)");
+	test_ao_restore(sk, ao_img);
+
+	if (test_get_tcp_ao_counters(sk, &ao1))
+		test_error("test_get_tcp_ao_counters()");
+
+	test_disable_repair(sk);
+	test_sock_state_free(img);
+
+	timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
+	if (test_client_verify(sk, msg_len, nr_packets, timeout)) {
+		if (fault(TIMEOUT))
+			test_ok("%s: post-migrate connection is broken", tst_name);
+		else
+			test_fail("%s: post-migrate connection is working", tst_name);
+	} else {
+		if (fault(TIMEOUT))
+			test_fail("%s: post-migrate connection still working", tst_name);
+		else
+			test_ok("%s: post-migrate connection is alive", tst_name);
+	}
+	if (test_get_tcp_ao_counters(sk, &ao2))
+		test_error("test_get_tcp_ao_counters()");
+	after_cnt = netstat_get_one(cnt_name, NULL);
+
+	test_tcp_ao_counters_cmp(tst_name, &ao1, &ao2, cnt_expected);
+
+	if (after_cnt <= before_cnt) {
+		test_fail("%s: %s counter did not increase: %zu <= %zu",
+				tst_name, cnt_name, after_cnt, before_cnt);
+	} else {
+		test_ok("%s: counter %s increased %zu => %zu",
+			tst_name, cnt_name, before_cnt, after_cnt);
+	}
+	synchronize_threads(); /* 3: verified => closed */
+	close(sk);
+}
+
+static void *client_fn(void *arg)
+{
+	unsigned int port = test_server_port;
+	struct tcp_sock_state tcp_img;
+	struct tcp_ao_repair ao_img;
+	sockaddr_af saddr;
+
+	test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img);
+	test_sk_restore("TCP-AO migrate to another socket", port++,
+			&saddr, &tcp_img, &ao_img, 0, TEST_CNT_GOOD);
+
+	test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img);
+	ao_img.snt_isn += 1;
+	test_sk_restore("TCP-AO with wrong send ISN", port++,
+			&saddr, &tcp_img, &ao_img, FAULT_TIMEOUT, TEST_CNT_BAD);
+
+	test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img);
+	ao_img.rcv_isn += 1;
+	test_sk_restore("TCP-AO with wrong receive ISN", port++,
+			&saddr, &tcp_img, &ao_img, FAULT_TIMEOUT, TEST_CNT_BAD);
+
+	test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img);
+	ao_img.snd_sne += 1;
+	test_sk_restore("TCP-AO with wrong send SEQ ext number", port++,
+			&saddr, &tcp_img, &ao_img, FAULT_TIMEOUT,
+			TEST_CNT_NS_BAD | TEST_CNT_GOOD);
+
+	test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img);
+	ao_img.rcv_sne += 1;
+	test_sk_restore("TCP-AO with wrong receive SEQ ext number", port++,
+			&saddr, &tcp_img, &ao_img, FAULT_TIMEOUT,
+			TEST_CNT_NS_GOOD | TEST_CNT_BAD);
+
+	return NULL;
+}
+
+int main(int argc, char *argv[])
+{
+	test_init(20, server_fn, client_fn);
+	return 0;
+}
diff --git a/tools/testing/selftests/net/tcp_ao/rst.c b/tools/testing/selftests/net/tcp_ao/rst.c
new file mode 100644
index 000000000000..ac06009a7f5f
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/rst.c
@@ -0,0 +1,415 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Author: Dmitry Safonov <dima@arista.com> */
+#include <inttypes.h>
+#include "../../../../include/linux/kernel.h"
+#include "aolib.h"
+
+const size_t quota = 1000;
+/*
+ * Backlog == 0 means 1 connection in queue, see:
+ * commit 64a146513f8f ("[NET]: Revert incorrect accept queue...")
+ */
+const unsigned int backlog;
+
+static void netstats_check(struct netstat *before, struct netstat *after,
+			   char *msg)
+{
+	uint64_t before_cnt, after_cnt;
+
+	before_cnt = netstat_get(before, "TCPAORequired", NULL);
+	after_cnt = netstat_get(after, "TCPAORequired", NULL);
+	if (after_cnt > before_cnt)
+		test_fail("Segments without AO sign (%s): %" PRIu64 " => %" PRIu64,
+			  msg, before_cnt, after_cnt);
+	else
+		test_ok("No segments without AO sign (%s)", msg);
+
+	before_cnt = netstat_get(before, "TCPAOGood", NULL);
+	after_cnt = netstat_get(after, "TCPAOGood", NULL);
+	if (after_cnt <= before_cnt)
+		test_fail("Signed AO segments (%s): %" PRIu64 " => %" PRIu64,
+			  msg, before_cnt, after_cnt);
+	else
+		test_ok("Signed AO segments (%s): %" PRIu64 " => %" PRIu64,
+			  msg, before_cnt, after_cnt);
+
+	before_cnt = netstat_get(before, "TCPAOBad", NULL);
+	after_cnt = netstat_get(after, "TCPAOBad", NULL);
+	if (after_cnt > before_cnt)
+		test_fail("Segments with bad AO sign (%s): %" PRIu64 " => %" PRIu64,
+			  msg, before_cnt, after_cnt);
+	else
+		test_ok("No segments with bad AO sign (%s)", msg);
+}
+
+/*
+ * Another way to send RST, but not through tcp_v{4,6}_send_reset()
+ * is tcp_send_active_reset(), that is not in reply to inbound segment,
+ * but rather active send. It uses tcp_transmit_skb(), so that should
+ * work, but as it also sends RST - nice that it can be covered as well.
+ */
+static void close_forced(int sk)
+{
+	struct linger sl;
+
+	sl.l_onoff = 1;
+	sl.l_linger = 0;
+	if (setsockopt(sk, SOL_SOCKET, SO_LINGER, &sl, sizeof(sl)))
+		test_error("setsockopt(SO_LINGER)");
+	close(sk);
+}
+
+static int test_wait_for_exception(int sk, time_t sec)
+{
+	struct timeval tv = { .tv_sec = sec };
+	struct timeval *ptv = NULL;
+	fd_set efds;
+	int ret;
+
+	FD_ZERO(&efds);
+	FD_SET(sk, &efds);
+
+	if (sec)
+		ptv = &tv;
+
+	errno = 0;
+	ret = select(sk + 1, NULL, NULL, &efds, ptv);
+	if (ret < 0)
+		return -errno;
+	return ret ? sk : 0;
+}
+
+static void test_server_active_rst(unsigned int port)
+{
+	struct tcp_ao_counters cnt1, cnt2;
+	ssize_t bytes;
+	int sk, lsk;
+
+	lsk = test_listen_socket(this_ip_addr, port, backlog);
+	if (test_add_key(lsk, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100))
+		test_error("setsockopt(TCP_AO_ADD_KEY)");
+	if (test_get_tcp_ao_counters(lsk, &cnt1))
+		test_error("test_get_tcp_ao_counters()");
+
+	synchronize_threads(); /* 1: MKT added */
+	if (test_wait_fd(lsk, TEST_TIMEOUT_SEC, 0))
+		test_error("test_wait_fd()");
+
+	sk = accept(lsk, NULL, NULL);
+	if (sk < 0)
+		test_error("accept()");
+
+	synchronize_threads(); /* 2: connection accept()ed, another queued */
+	if (test_get_tcp_ao_counters(lsk, &cnt2))
+		test_error("test_get_tcp_ao_counters()");
+
+	synchronize_threads(); /* 3: close listen socket */
+	close(lsk);
+	bytes = test_server_run(sk, quota, 0);
+	if (bytes != quota)
+		test_error("servered only %zd bytes", bytes);
+	else
+		test_ok("servered %zd bytes", bytes);
+
+	synchronize_threads(); /* 4: finishing up */
+	close_forced(sk);
+
+	synchronize_threads(); /* 5: closed active sk */
+
+	synchronize_threads(); /* 6: counters checks */
+	if (test_tcp_ao_counters_cmp("active RST server", &cnt1, &cnt2, TEST_CNT_GOOD))
+		test_fail("MKT counters (server) have not only good packets");
+	else
+		test_ok("MKT counters are good on server");
+}
+
+static void test_server_passive_rst(unsigned int port)
+{
+	struct tcp_ao_counters ao1, ao2;
+	int sk, lsk;
+	ssize_t bytes;
+
+	lsk = test_listen_socket(this_ip_addr, port, 1);
+
+	if (test_add_key(lsk, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100))
+		test_error("setsockopt(TCP_AO_ADD_KEY)");
+
+	synchronize_threads(); /* 1: MKT added => connect() */
+	if (test_wait_fd(lsk, TEST_TIMEOUT_SEC, 0))
+		test_error("test_wait_fd()");
+
+	sk = accept(lsk, NULL, NULL);
+	if (sk < 0)
+		test_error("accept()");
+
+	synchronize_threads(); /* 2: accepted => send data */
+	close(lsk);
+	if (test_get_tcp_ao_counters(sk, &ao1))
+		test_error("test_get_tcp_ao_counters()");
+
+	bytes = test_server_run(sk, quota, TEST_TIMEOUT_SEC);
+	if (bytes != quota) {
+		if (bytes > 0)
+			test_fail("server served: %zd", bytes);
+		else
+			test_fail("server returned %zd", bytes);
+	}
+
+	synchronize_threads(); /* 3: chekpoint/restore the connection */
+	if (test_get_tcp_ao_counters(sk, &ao2))
+		test_error("test_get_tcp_ao_counters()");
+
+	synchronize_threads(); /* 4: terminate server + send more on client */
+	bytes = test_server_run(sk, quota, TEST_RETRANSMIT_SEC);
+	close(sk);
+	test_tcp_ao_counters_cmp("passive RST server", &ao1, &ao2, TEST_CNT_GOOD);
+
+	synchronize_threads(); /* 5: verified => closed */
+	close(sk);
+}
+
+static void *server_fn(void *arg)
+{
+	struct netstat *ns_before, *ns_after;
+	unsigned int port = test_server_port;
+
+	ns_before = netstat_read();
+
+	test_server_active_rst(port++);
+	test_server_passive_rst(port++);
+
+	ns_after = netstat_read();
+	netstats_check(ns_before, ns_after, "server");
+	netstat_free(ns_after);
+	netstat_free(ns_before);
+	synchronize_threads(); /* exit */
+
+	synchronize_threads(); /* don't race to exit() - client exits */
+	return NULL;
+}
+
+static int test_wait_fds(int sk[], size_t nr, bool is_writable[],
+			 ssize_t wait_for, time_t sec)
+{
+	struct timeval tv = { .tv_sec = sec };
+	struct timeval *ptv = NULL;
+	fd_set left;
+	size_t i;
+	int ret;
+
+	FD_ZERO(&left);
+	for (i = 0; i < nr; i++) {
+		FD_SET(sk[i], &left);
+		if (is_writable)
+			is_writable[i] = false;
+	}
+
+	if (sec)
+		ptv = &tv;
+
+	do {
+		bool is_empty = true;
+		fd_set fds, efds;
+		int nfd = 0;
+
+		FD_ZERO(&fds);
+		FD_ZERO(&efds);
+		for (i = 0; i < nr; i++) {
+			if (!FD_ISSET(sk[i], &left))
+				continue;
+
+			if (sk[i] > nfd)
+				nfd = sk[i];
+
+			FD_SET(sk[i], &fds);
+			FD_SET(sk[i], &efds);
+			is_empty = false;
+		}
+		if (is_empty)
+			return -ENOENT;
+
+		errno = 0;
+		ret = select(nfd + 1, NULL, &fds, &efds, ptv);
+		if (ret < 0)
+			return -errno;
+		if (!ret)
+			return -ETIMEDOUT;
+		for (i = 0; i < nr; i++) {
+			if (FD_ISSET(sk[i], &fds)) {
+				if (is_writable)
+					is_writable[i] = true;
+				FD_CLR(sk[i], &left);
+				wait_for--;
+				continue;
+			}
+			if (FD_ISSET(sk[i], &efds)) {
+				FD_CLR(sk[i], &left);
+				wait_for--;
+			}
+		}
+	} while (wait_for > 0);
+
+	return 0;
+}
+
+static void test_client_active_rst(unsigned int port)
+{
+	/* one in queue, another accept()ed */
+	unsigned int wait_for = backlog + 2;
+	int i, sk[3], err;
+	bool is_writable[ARRAY_SIZE(sk)] = {false};
+	unsigned int last = ARRAY_SIZE(sk) - 1;
+
+	for (i = 0; i < ARRAY_SIZE(sk); i++) {
+		sk[i] = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+		if (sk[i] < 0)
+			test_error("socket()");
+		if (test_add_key(sk[i], DEFAULT_TEST_PASSWORD,
+				 this_ip_dest, -1, 100, 100))
+			test_error("setsockopt(TCP_AO_ADD_KEY)");
+	}
+
+	synchronize_threads(); /* 1: MKT added */
+	for (i = 0; i < last; i++) {
+		err = _test_connect_socket(sk[i], this_ip_dest, port,
+					       (i == 0) ? TEST_TIMEOUT_SEC : -1);
+
+		if (err < 0)
+			test_error("failed to connect()");
+	}
+
+	synchronize_threads(); /* 2: connection accept()ed, another queued */
+	err = test_wait_fds(sk, last, is_writable, wait_for, TEST_TIMEOUT_SEC);
+	if (err < 0)
+		test_error("test_wait_fds(): %d", err);
+
+	synchronize_threads(); /* 3: close listen socket */
+	if (test_client_verify(sk[0], 100, quota / 100, TEST_TIMEOUT_SEC))
+		test_fail("Failed to send data on connected socket");
+	else
+		test_ok("Verified established tcp connection");
+
+	synchronize_threads(); /* 4: finishing up */
+	err = _test_connect_socket(sk[last], this_ip_dest, port, -1);
+	if (err < 0)
+		test_error("failed to connect()");
+
+	synchronize_threads(); /* 5: closed active sk */
+	err = test_wait_fds(sk, ARRAY_SIZE(sk), NULL,
+			    wait_for, TEST_TIMEOUT_SEC);
+	if (err < 0)
+		test_error("select(): %d", err);
+
+	for (i = 0; i < ARRAY_SIZE(sk); i++) {
+		socklen_t slen = sizeof(err);
+
+		if (getsockopt(sk[i], SOL_SOCKET, SO_ERROR, &err, &slen))
+			test_error("getsockopt()");
+		if (is_writable[i] && err != ECONNRESET) {
+			test_fail("sk[%d] = %d, err = %d, connection wasn't reset",
+				  i, sk[i], err);
+		} else {
+			test_ok("sk[%d] = %d%s", i, sk[i],
+				is_writable[i] ? ", connection was reset" : "");
+		}
+	}
+	synchronize_threads(); /* 6: counters checks */
+}
+
+static void test_client_passive_rst(unsigned int port)
+{
+	struct tcp_ao_counters ao1, ao2;
+	struct tcp_ao_repair ao_img;
+	struct tcp_sock_state img;
+	sockaddr_af saddr;
+	int sk, err;
+	socklen_t slen = sizeof(err);
+
+	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+	if (sk < 0)
+		test_error("socket()");
+
+	if (test_add_key(sk, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100))
+		test_error("setsockopt(TCP_AO_ADD_KEY)");
+
+	synchronize_threads(); /* 1: MKT added => connect() */
+	if (test_connect_socket(sk, this_ip_dest, port) <= 0)
+		test_error("failed to connect()");
+
+	synchronize_threads(); /* 2: accepted => send data */
+	if (test_client_verify(sk, 100, quota / 100, TEST_TIMEOUT_SEC))
+		test_fail("Failed to send data on connected socket");
+	else
+		test_ok("Verified established tcp connection");
+
+	synchronize_threads(); /* 3: chekpoint/restore the connection */
+	test_enable_repair(sk);
+	test_sock_checkpoint(sk, &img, &saddr);
+	test_ao_checkpoint(sk, &ao_img);
+	test_kill_sk(sk);
+
+	img.out.seq += quota;
+
+	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+	if (sk < 0)
+		test_error("socket()");
+
+	test_enable_repair(sk);
+	test_sock_restore(sk, &img, &saddr, this_ip_dest, port);
+	if (test_add_repaired_key(sk, DEFAULT_TEST_PASSWORD, 0, this_ip_dest, -1, 100, 100))
+		test_error("setsockopt(TCP_AO_ADD_KEY)");
+	test_ao_restore(sk, &ao_img);
+
+	if (test_get_tcp_ao_counters(sk, &ao1))
+		test_error("test_get_tcp_ao_counters()");
+
+	test_disable_repair(sk);
+	test_sock_state_free(&img);
+
+	synchronize_threads(); /* 4: terminate server + send more on client */
+	if (test_client_verify(sk, 100, quota / 100, 2 * TEST_TIMEOUT_SEC))
+		test_ok("client connection broken post-seq-adjust");
+	else
+		test_fail("client connection still works post-seq-adjust");
+
+	test_wait_for_exception(sk, TEST_TIMEOUT_SEC);
+
+	if (getsockopt(sk, SOL_SOCKET, SO_ERROR, &err, &slen))
+		test_error("getsockopt()");
+	if (err != ECONNRESET && err != EPIPE)
+		test_fail("client connection was not reset: %d", err);
+	else
+		test_ok("client connection was reset");
+
+	if (test_get_tcp_ao_counters(sk, &ao2))
+		test_error("test_get_tcp_ao_counters()");
+
+	synchronize_threads(); /* 5: verified => closed */
+	close(sk);
+	test_tcp_ao_counters_cmp("client passive RST", &ao1, &ao2, TEST_CNT_GOOD);
+}
+
+static void *client_fn(void *arg)
+{
+	struct netstat *ns_before, *ns_after;
+	unsigned int port = test_server_port;
+
+	ns_before = netstat_read();
+
+	test_client_active_rst(port++);
+	test_client_passive_rst(port++);
+
+	ns_after = netstat_read();
+	netstats_check(ns_before, ns_after, "client");
+	netstat_free(ns_after);
+	netstat_free(ns_before);
+
+	synchronize_threads(); /* exit */
+	return NULL;
+}
+
+int main(int argc, char *argv[])
+{
+	test_init(15, server_fn, client_fn);
+	return 0;
+}
diff --git a/tools/testing/selftests/net/tcp_ao/self-connect.c b/tools/testing/selftests/net/tcp_ao/self-connect.c
new file mode 100644
index 000000000000..e154d9e198a9
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/self-connect.c
@@ -0,0 +1,197 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Author: Dmitry Safonov <dima@arista.com> */
+#include <inttypes.h>
+#include "aolib.h"
+
+static union tcp_addr local_addr;
+
+static void __setup_lo_intf(const char *lo_intf,
+			    const char *addr_str, uint8_t prefix)
+{
+	if (inet_pton(TEST_FAMILY, addr_str, &local_addr) != 1)
+		test_error("Can't convert local ip address");
+
+	if (ip_addr_add(lo_intf, TEST_FAMILY, local_addr, prefix))
+		test_error("Failed to add %s ip address", lo_intf);
+
+	if (link_set_up(lo_intf))
+		test_error("Failed to bring %s up", lo_intf);
+}
+
+static void setup_lo_intf(const char *lo_intf)
+{
+#ifdef IPV6_TEST
+	__setup_lo_intf(lo_intf, "::1", 128);
+#else
+	__setup_lo_intf(lo_intf, "127.0.0.1", 8);
+#endif
+}
+
+static void tcp_self_connect(const char *tst, unsigned int port,
+			     bool different_keyids, bool check_restore)
+{
+	uint64_t before_challenge_ack, after_challenge_ack;
+	uint64_t before_syn_challenge, after_syn_challenge;
+	struct tcp_ao_counters before_ao, after_ao;
+	uint64_t before_aogood, after_aogood;
+	struct netstat *ns_before, *ns_after;
+	const size_t nr_packets = 20;
+	struct tcp_ao_repair ao_img;
+	struct tcp_sock_state img;
+	sockaddr_af addr;
+	int sk;
+
+	tcp_addr_to_sockaddr_in(&addr, &local_addr, htons(port));
+
+	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+	if (sk < 0)
+		test_error("socket()");
+
+	if (different_keyids) {
+		if (test_add_key(sk, DEFAULT_TEST_PASSWORD, local_addr, -1, 5, 7))
+			test_error("setsockopt(TCP_AO_ADD_KEY)");
+		if (test_add_key(sk, DEFAULT_TEST_PASSWORD, local_addr, -1, 7, 5))
+			test_error("setsockopt(TCP_AO_ADD_KEY)");
+	} else {
+		if (test_add_key(sk, DEFAULT_TEST_PASSWORD, local_addr, -1, 100, 100))
+			test_error("setsockopt(TCP_AO_ADD_KEY)");
+	}
+
+	if (bind(sk, (struct sockaddr *)&addr, sizeof(addr)) < 0)
+		test_error("bind()");
+
+	ns_before = netstat_read();
+	before_aogood = netstat_get(ns_before, "TCPAOGood", NULL);
+	before_challenge_ack = netstat_get(ns_before, "TCPChallengeACK", NULL);
+	before_syn_challenge = netstat_get(ns_before, "TCPSYNChallenge", NULL);
+	if (test_get_tcp_ao_counters(sk, &before_ao))
+		test_error("test_get_tcp_ao_counters()");
+
+	if (__test_connect_socket(sk, "lo", (struct sockaddr *)&addr,
+				  sizeof(addr), TEST_TIMEOUT_SEC) < 0) {
+		ns_after = netstat_read();
+		netstat_print_diff(ns_before, ns_after);
+		test_error("failed to connect()");
+	}
+
+	if (test_client_verify(sk, 100, nr_packets, TEST_TIMEOUT_SEC)) {
+		test_fail("%s: tcp connection verify failed", tst);
+		close(sk);
+		return;
+	}
+
+	ns_after = netstat_read();
+	after_aogood = netstat_get(ns_after, "TCPAOGood", NULL);
+	after_challenge_ack = netstat_get(ns_after, "TCPChallengeACK", NULL);
+	after_syn_challenge = netstat_get(ns_after, "TCPSYNChallenge", NULL);
+	if (test_get_tcp_ao_counters(sk, &after_ao))
+		test_error("test_get_tcp_ao_counters()");
+	if (!check_restore) {
+		/* to debug: netstat_print_diff(ns_before, ns_after); */
+		netstat_free(ns_before);
+	}
+	netstat_free(ns_after);
+
+	if (after_aogood <= before_aogood) {
+		test_fail("%s: TCPAOGood counter mismatch: %zu <= %zu",
+			  tst, after_aogood, before_aogood);
+		close(sk);
+		return;
+	}
+	if (after_challenge_ack <= before_challenge_ack ||
+	    after_syn_challenge <= before_syn_challenge) {
+		/*
+		 * It's also meant to test simultaneous open, so check
+		 * these counters as well.
+		 */
+		test_fail("%s: Didn't challenge SYN or ACK: %zu <= %zu OR %zu <= %zu",
+			  tst, after_challenge_ack, before_challenge_ack,
+			  after_syn_challenge, before_syn_challenge);
+		close(sk);
+		return;
+	}
+
+	if (test_tcp_ao_counters_cmp(tst, &before_ao, &after_ao, TEST_CNT_GOOD)) {
+		close(sk);
+		return;
+	}
+
+	if (!check_restore) {
+		test_ok("%s: connect TCPAOGood %" PRIu64 " => %" PRIu64,
+				tst, before_aogood, after_aogood);
+		close(sk);
+		return;
+	}
+
+	test_enable_repair(sk);
+	test_sock_checkpoint(sk, &img, &addr);
+#ifdef IPV6_TEST
+	addr.sin6_port = htons(port + 1);
+#else
+	addr.sin_port = htons(port + 1);
+#endif
+	test_ao_checkpoint(sk, &ao_img);
+	test_kill_sk(sk);
+
+	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+	if (sk < 0)
+		test_error("socket()");
+
+	test_enable_repair(sk);
+	__test_sock_restore(sk, "lo", &img, &addr, &addr, sizeof(addr));
+	if (different_keyids) {
+		if (test_add_repaired_key(sk, DEFAULT_TEST_PASSWORD, 0,
+					  local_addr, -1, 7, 5))
+			test_error("setsockopt(TCP_AO_ADD_KEY)");
+		if (test_add_repaired_key(sk, DEFAULT_TEST_PASSWORD, 0,
+					  local_addr, -1, 5, 7))
+			test_error("setsockopt(TCP_AO_ADD_KEY)");
+	} else {
+		if (test_add_repaired_key(sk, DEFAULT_TEST_PASSWORD, 0,
+					  local_addr, -1, 100, 100))
+			test_error("setsockopt(TCP_AO_ADD_KEY)");
+	}
+	test_ao_restore(sk, &ao_img);
+	test_disable_repair(sk);
+	test_sock_state_free(&img);
+	if (test_client_verify(sk, 100, nr_packets, TEST_TIMEOUT_SEC)) {
+		test_fail("%s: tcp connection verify failed", tst);
+		close(sk);
+		return;
+	}
+	ns_after = netstat_read();
+	after_aogood = netstat_get(ns_after, "TCPAOGood", NULL);
+	/* to debug: netstat_print_diff(ns_before, ns_after); */
+	netstat_free(ns_before);
+	netstat_free(ns_after);
+	close(sk);
+	if (after_aogood <= before_aogood) {
+		test_fail("%s: TCPAOGood counter mismatch: %zu <= %zu",
+			  tst, after_aogood, before_aogood);
+		return;
+	}
+	test_ok("%s: connect TCPAOGood %" PRIu64 " => %" PRIu64,
+			tst, before_aogood, after_aogood);
+}
+
+static void *client_fn(void *arg)
+{
+	unsigned int port = test_server_port;
+
+	setup_lo_intf("lo");
+
+	tcp_self_connect("self-connect(same keyids)", port++, false, false);
+	tcp_self_connect("self-connect(different keyids)", port++, true, false);
+	tcp_self_connect("self-connect(restore)", port, false, true);
+	port += 2;
+	tcp_self_connect("self-connect(restore, different keyids)", port, true, true);
+	port += 2;
+
+	return NULL;
+}
+
+int main(int argc, char *argv[])
+{
+	test_init(4, client_fn, NULL);
+	return 0;
+}
diff --git a/tools/testing/selftests/net/tcp_ao/seq-ext.c b/tools/testing/selftests/net/tcp_ao/seq-ext.c
new file mode 100644
index 000000000000..ad4e77d6823e
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/seq-ext.c
@@ -0,0 +1,245 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Check that after SEQ number wrap-around:
+ * 1. SEQ-extension has upper bytes set
+ * 2. TCP conneciton is alive and no TCPAOBad segments
+ * In order to test (2), the test doesn't just adjust seq number for a queue
+ * on a connected socket, but migrates it to another sk+port number, so
+ * that there won't be any delayed packets that will fail to verify
+ * with the new SEQ numbers.
+ */
+#include <inttypes.h>
+#include "aolib.h"
+
+const unsigned int nr_packets = 1000;
+const unsigned int msg_len = 1000;
+const unsigned int quota = nr_packets * msg_len;
+unsigned int client_new_port;
+
+/* Move them closer to roll-over */
+static void test_adjust_seqs(struct tcp_sock_state *img,
+			     struct tcp_ao_repair *ao_img,
+			     bool server)
+{
+	uint32_t new_seq1, new_seq2;
+
+	/* make them roll-over during quota, but on different segments */
+	if (server) {
+		new_seq1 = ((uint32_t)-1) - msg_len;
+		new_seq2 = ((uint32_t)-1) - (quota - 2 * msg_len);
+	} else {
+		new_seq1 = ((uint32_t)-1) - (quota - 2 * msg_len);
+		new_seq2 = ((uint32_t)-1) - msg_len;
+	}
+
+	img->in.seq = new_seq1;
+	img->trw.snd_wl1 = img->in.seq - msg_len;
+	img->out.seq = new_seq2;
+	img->trw.rcv_wup = img->in.seq;
+}
+
+static int test_sk_restore(struct tcp_sock_state *img,
+			   struct tcp_ao_repair *ao_img, sockaddr_af *saddr,
+			   const union tcp_addr daddr, unsigned int dport,
+			   struct tcp_ao_counters *cnt)
+{
+	int sk;
+
+	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+	if (sk < 0)
+		test_error("socket()");
+
+	test_enable_repair(sk);
+	test_sock_restore(sk, img, saddr, daddr, dport);
+	if (test_add_repaired_key(sk, DEFAULT_TEST_PASSWORD, 0, daddr, -1, 100, 100))
+		test_error("setsockopt(TCP_AO_ADD_KEY)");
+	test_ao_restore(sk, ao_img);
+
+	if (test_get_tcp_ao_counters(sk, cnt))
+		test_error("test_get_tcp_ao_counters()");
+
+	test_disable_repair(sk);
+	test_sock_state_free(img);
+	return sk;
+}
+
+static void *server_fn(void *arg)
+{
+	uint64_t before_good, after_good, after_bad;
+	struct tcp_ao_counters ao1, ao2;
+	struct tcp_sock_state img;
+	struct tcp_ao_repair ao_img;
+	sockaddr_af saddr;
+	ssize_t bytes;
+	int sk, lsk;
+
+	lsk = test_listen_socket(this_ip_addr, test_server_port, 1);
+
+	if (test_add_key(lsk, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100))
+		test_error("setsockopt(TCP_AO_ADD_KEY)");
+
+	synchronize_threads(); /* 1: MKT added => connect() */
+
+	if (test_wait_fd(lsk, TEST_TIMEOUT_SEC, 0))
+		test_error("test_wait_fd()");
+
+	sk = accept(lsk, NULL, NULL);
+	if (sk < 0)
+		test_error("accept()");
+
+	synchronize_threads(); /* 2: accepted => send data */
+	close(lsk);
+
+	bytes = test_server_run(sk, quota, TEST_TIMEOUT_SEC);
+	if (bytes != quota) {
+		if (bytes > 0)
+			test_fail("server served: %zd", bytes);
+		else
+			test_fail("server returned: %zd", bytes);
+		goto out;
+	}
+
+	before_good = netstat_get_one("TCPAOGood", NULL);
+
+	synchronize_threads(); /* 3: restore the connection on another port */
+
+	test_enable_repair(sk);
+	test_sock_checkpoint(sk, &img, &saddr);
+	test_ao_checkpoint(sk, &ao_img);
+	test_kill_sk(sk);
+#ifdef IPV6_TEST
+	saddr.sin6_port = htons(ntohs(saddr.sin6_port) + 1);
+#else
+	saddr.sin_port = htons(ntohs(saddr.sin_port) + 1);
+#endif
+	test_adjust_seqs(&img, &ao_img, true);
+	synchronize_threads(); /* 4: dump finished */
+	sk = test_sk_restore(&img, &ao_img, &saddr, this_ip_dest,
+			     client_new_port, &ao1);
+
+	synchronize_threads(); /* 5: verify counters during SEQ-number rollover */
+	bytes = test_server_run(sk, quota, TEST_TIMEOUT_SEC);
+	if (bytes != quota) {
+		if (bytes > 0)
+			test_fail("server served: %zd", bytes);
+		else
+			test_fail("server returned: %zd", bytes);
+	} else {
+		test_ok("server alive");
+	}
+
+	if (test_get_tcp_ao_counters(sk, &ao2))
+		test_error("test_get_tcp_ao_counters()");
+	after_good = netstat_get_one("TCPAOGood", NULL);
+
+	test_tcp_ao_counters_cmp(NULL, &ao1, &ao2, TEST_CNT_GOOD);
+
+	if (after_good <= before_good) {
+		test_fail("TCPAOGood counter did not increase: %zu <= %zu",
+			  after_good, before_good);
+	} else {
+		test_ok("TCPAOGood counter increased %zu => %zu",
+			before_good, after_good);
+	}
+	after_bad = netstat_get_one("TCPAOBad", NULL);
+	if (after_bad)
+		test_fail("TCPAOBad counter is non-zero: %zu", after_bad);
+	else
+		test_ok("TCPAOBad counter didn't increase");
+	test_enable_repair(sk);
+	test_ao_checkpoint(sk, &ao_img);
+	if (ao_img.snd_sne && ao_img.rcv_sne) {
+		test_ok("SEQ extension incremented: %u/%u",
+			ao_img.snd_sne, ao_img.rcv_sne);
+	} else {
+		test_fail("SEQ extension was not incremented: %u/%u",
+			  ao_img.snd_sne, ao_img.rcv_sne);
+	}
+
+	synchronize_threads(); /* 6: verified => closed */
+out:
+	close(sk);
+	return NULL;
+}
+
+static void *client_fn(void *arg)
+{
+	uint64_t before_good, after_good, after_bad;
+	struct tcp_ao_counters ao1, ao2;
+	struct tcp_sock_state img;
+	struct tcp_ao_repair ao_img;
+	sockaddr_af saddr;
+	int sk;
+
+	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+	if (sk < 0)
+		test_error("socket()");
+
+	if (test_add_key(sk, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100))
+		test_error("setsockopt(TCP_AO_ADD_KEY)");
+
+	synchronize_threads(); /* 1: MKT added => connect() */
+	if (test_connect_socket(sk, this_ip_dest, test_server_port) <= 0)
+		test_error("failed to connect()");
+
+	synchronize_threads(); /* 2: accepted => send data */
+	if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC)) {
+		test_fail("pre-migrate verify failed");
+		return NULL;
+	}
+
+	before_good = netstat_get_one("TCPAOGood", NULL);
+
+	synchronize_threads(); /* 3: restore the connection on another port */
+	test_enable_repair(sk);
+	test_sock_checkpoint(sk, &img, &saddr);
+	test_ao_checkpoint(sk, &ao_img);
+	test_kill_sk(sk);
+#ifdef IPV6_TEST
+	client_new_port = ntohs(saddr.sin6_port) + 1;
+	saddr.sin6_port = htons(ntohs(saddr.sin6_port) + 1);
+#else
+	client_new_port = ntohs(saddr.sin_port) + 1;
+	saddr.sin_port = htons(ntohs(saddr.sin_port) + 1);
+#endif
+	test_adjust_seqs(&img, &ao_img, false);
+	synchronize_threads(); /* 4: dump finished */
+	sk = test_sk_restore(&img, &ao_img, &saddr, this_ip_dest,
+			     test_server_port + 1, &ao1);
+
+	synchronize_threads(); /* 5: verify counters during SEQ-number rollover */
+	if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC))
+		test_fail("post-migrate verify failed");
+	else
+		test_ok("post-migrate connection alive");
+
+	if (test_get_tcp_ao_counters(sk, &ao2))
+		test_error("test_get_tcp_ao_counters()");
+	after_good = netstat_get_one("TCPAOGood", NULL);
+
+	test_tcp_ao_counters_cmp(NULL, &ao1, &ao2, TEST_CNT_GOOD);
+
+	if (after_good <= before_good) {
+		test_fail("TCPAOGood counter did not increase: %zu <= %zu",
+			  after_good, before_good);
+	} else {
+		test_ok("TCPAOGood counter increased %zu => %zu",
+			before_good, after_good);
+	}
+	after_bad = netstat_get_one("TCPAOBad", NULL);
+	if (after_bad)
+		test_fail("TCPAOBad counter is non-zero: %zu", after_bad);
+	else
+		test_ok("TCPAOBad counter didn't increase");
+
+	synchronize_threads(); /* 6: verified => closed */
+	close(sk);
+
+	synchronize_threads(); /* don't race to exit: let server exit() */
+	return NULL;
+}
+
+int main(int argc, char *argv[])
+{
+	test_init(7, server_fn, client_fn);
+	return 0;
+}
diff --git a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c
new file mode 100644
index 000000000000..452de131fa3a
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c
@@ -0,0 +1,835 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Author: Dmitry Safonov <dima@arista.com> */
+#include <inttypes.h>
+#include "../../../../include/linux/kernel.h"
+#include "aolib.h"
+
+static union tcp_addr tcp_md5_client;
+
+static int test_port = 7788;
+static void make_listen(int sk)
+{
+	sockaddr_af addr;
+
+	tcp_addr_to_sockaddr_in(&addr, &this_ip_addr, htons(test_port++));
+	if (bind(sk, (struct sockaddr *)&addr, sizeof(addr)) < 0)
+		test_error("bind()");
+	if (listen(sk, 1))
+		test_error("listen()");
+}
+
+static void test_vefify_ao_info(int sk, struct tcp_ao_info_opt *info,
+				const char *tst)
+{
+	struct tcp_ao_info_opt tmp;
+	socklen_t len = sizeof(tmp);
+
+	if (getsockopt(sk, IPPROTO_TCP, TCP_AO_INFO, &tmp, &len))
+		test_error("getsockopt(TCP_AO_INFO) failed");
+
+#define __cmp_ao(member)							\
+do {										\
+	if (info->member != tmp.member) {					\
+		test_fail("%s: getsockopt(): " __stringify(member) " %zu != %zu",	\
+			  tst, (size_t)info->member, (size_t)tmp.member);	\
+		return;								\
+	}									\
+} while(0)
+	if (info->set_current)
+		__cmp_ao(current_key);
+	if (info->set_rnext)
+		__cmp_ao(rnext);
+	if (info->set_counters) {
+		__cmp_ao(pkt_good);
+		__cmp_ao(pkt_bad);
+		__cmp_ao(pkt_key_not_found);
+		__cmp_ao(pkt_ao_required);
+		__cmp_ao(pkt_dropped_icmp);
+	}
+	__cmp_ao(ao_required);
+	__cmp_ao(accept_icmps);
+
+	test_ok("AO info get: %s", tst);
+#undef __cmp_ao
+}
+
+static void __setsockopt_checked(int sk, int optname, bool get,
+				 void *optval, socklen_t *len,
+				 int err, const char *tst, const char *tst2)
+{
+	int ret;
+
+	if (!tst)
+		tst = "";
+	if (!tst2)
+		tst2 = "";
+
+	errno = 0;
+	if (get)
+		ret = getsockopt(sk, IPPROTO_TCP, optname, optval, len);
+	else
+		ret = setsockopt(sk, IPPROTO_TCP, optname, optval, *len);
+	if (ret == -1) {
+		if (errno == err)
+			test_ok("%s%s", tst ?: "", tst2 ?: "");
+		else
+			test_fail("%s%s: %setsockopt() failed",
+				  tst, tst2, get ? "g" : "s");
+		close(sk);
+		return;
+	}
+
+	if (err) {
+		test_fail("%s%s: %setsockopt() was expected to fail with %d",
+			  tst, tst2, get ? "g" : "s", err);
+	} else {
+		test_ok("%s%s", tst ?: "", tst2 ?: "");
+		if (optname == TCP_AO_ADD_KEY) {
+			test_verify_socket_key(sk, optval);
+		} else if (optname == TCP_AO_INFO && !get) {
+			test_vefify_ao_info(sk, optval, tst2);
+		} else if (optname == TCP_AO_GET_KEYS) {
+			if (*len != sizeof(struct tcp_ao_getsockopt))
+				test_fail("%s%s: get keys returned wrong tcp_ao_getsockopt size",
+					  tst, tst2);
+		}
+	}
+	close(sk);
+}
+
+static void setsockopt_checked(int sk, int optname, void *optval,
+			       int err, const char *tst)
+{
+	const char *cmd = NULL;
+	socklen_t len;
+
+	switch (optname) {
+	case TCP_AO_ADD_KEY:
+		cmd = "key add: ";
+		len = sizeof(struct tcp_ao_add);
+		break;
+	case TCP_AO_DEL_KEY:
+		cmd = "key del: ";
+		len = sizeof(struct tcp_ao_del);
+		break;
+	case TCP_AO_INFO:
+		cmd = "AO info set: ";
+		len = sizeof(struct tcp_ao_info_opt);
+		break;
+	default:
+		break;
+	}
+
+	__setsockopt_checked(sk, optname, false, optval, &len, err, cmd, tst);
+}
+
+static int prepare_defs(int cmd, void *optval)
+{
+	int sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+
+	if (sk < 0)
+		test_error("socket()");
+
+	switch (cmd) {
+	case TCP_AO_ADD_KEY: {
+		struct tcp_ao_add *add = optval;
+
+		if (test_prepare_def_key(add, DEFAULT_TEST_PASSWORD, 0, this_ip_dest,
+					-1, 0, 100, 100))
+			test_error("prepare default tcp_ao_add");
+		break;
+		}
+	case TCP_AO_DEL_KEY: {
+		struct tcp_ao_del *del = optval;
+
+		if (test_add_key(sk, DEFAULT_TEST_PASSWORD, this_ip_dest,
+				 DEFAULT_TEST_PREFIX, 100, 100))
+			test_error("add default key");
+		memset(del, 0, sizeof(struct tcp_ao_del));
+		del->sndid = 100;
+		del->rcvid = 100;
+		del->prefix = DEFAULT_TEST_PREFIX;
+		tcp_addr_to_sockaddr_in(&del->addr, &this_ip_dest, 0);
+		break;
+		}
+	case TCP_AO_INFO: {
+		struct tcp_ao_info_opt *info = optval;
+
+		if (test_add_key(sk, DEFAULT_TEST_PASSWORD, this_ip_dest,
+				 DEFAULT_TEST_PREFIX, 100, 100))
+			test_error("add default key");
+		memset(info, 0, sizeof(struct tcp_ao_info_opt));
+		break;
+		}
+	case TCP_AO_GET_KEYS: {
+		struct tcp_ao_getsockopt *get = optval;
+
+		if (test_add_key(sk, DEFAULT_TEST_PASSWORD, this_ip_dest,
+				 DEFAULT_TEST_PREFIX, 100, 100))
+			test_error("add default key");
+		memset(get, 0, sizeof(struct tcp_ao_getsockopt));
+		get->nkeys = 1;
+		get->get_all = 1;
+		break;
+		}
+	default:
+		test_error("unknown cmd");
+	}
+
+	return sk;
+}
+
+static void test_extend(int cmd, bool get, const char *tst, socklen_t under_size)
+{
+	struct {
+		union {
+			struct tcp_ao_add add;
+			struct tcp_ao_del del;
+			struct tcp_ao_getsockopt get;
+			struct tcp_ao_info_opt info;
+		};
+		char *extend[100];
+	} tmp_opt;
+	socklen_t extended_size = sizeof(tmp_opt);
+	int sk;
+
+	memset(&tmp_opt, 0, sizeof(tmp_opt));
+	sk = prepare_defs(cmd, &tmp_opt);
+	__setsockopt_checked(sk, cmd, get, &tmp_opt, &under_size,
+			     EINVAL, tst, ": minimum size");
+
+	memset(&tmp_opt, 0, sizeof(tmp_opt));
+	sk = prepare_defs(cmd, &tmp_opt);
+	__setsockopt_checked(sk, cmd, get, &tmp_opt, &extended_size,
+			     0, tst, ": extended size");
+
+	memset(&tmp_opt, 0, sizeof(tmp_opt));
+	sk = prepare_defs(cmd, &tmp_opt);
+	__setsockopt_checked(sk, cmd, get, NULL, &extended_size,
+			     EFAULT, tst, ": null optval");
+
+	if (get) {
+		memset(&tmp_opt, 0, sizeof(tmp_opt));
+		sk = prepare_defs(cmd, &tmp_opt);
+		__setsockopt_checked(sk, cmd, get, &tmp_opt, NULL,
+				     EFAULT, tst, ": null optlen");
+	}
+}
+
+static void extend_tests(void)
+{
+	test_extend(TCP_AO_ADD_KEY, false, "AO add",
+		    offsetof(struct tcp_ao_add, key));
+	test_extend(TCP_AO_DEL_KEY, false, "AO del",
+		    offsetof(struct tcp_ao_del, keyflags));
+	test_extend(TCP_AO_INFO, false, "AO set info",
+		    offsetof(struct tcp_ao_info_opt, pkt_dropped_icmp));
+	test_extend(TCP_AO_INFO, true, "AO get info", -1);
+	test_extend(TCP_AO_GET_KEYS, true, "AO get keys", -1);
+}
+
+static void test_optmem_limit(void)
+{
+	size_t i, keys_limit, current_optmem = test_get_optmem();
+	struct tcp_ao_add ao;
+	union tcp_addr net = {};
+	int sk;
+
+	if (inet_pton(TEST_FAMILY, TEST_NETWORK, &net) != 1)
+		test_error("Can't convert ip address %s", TEST_NETWORK);
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	keys_limit = current_optmem / KERNEL_TCP_AO_KEY_SZ_ROUND_UP;
+	for (i = 0;; i++) {
+		union tcp_addr key_peer;
+		int err;
+
+		key_peer = gen_tcp_addr(net, i + 1);
+		tcp_addr_to_sockaddr_in(&ao.addr, &key_peer, 0);
+		err = setsockopt(sk, IPPROTO_TCP, TCP_AO_ADD_KEY,
+				 &ao, sizeof(ao));
+		if (!err) {
+			/*
+			 * TCP_AO_ADD_KEY should be the same order as the real
+			 * sizeof(struct tcp_ao_key) in kernel.
+			 */
+			if (i <= keys_limit * 10)
+				continue;
+			test_fail("optmem limit test failed: added %zu key", i);
+			break;
+		}
+		if (i < keys_limit) {
+			test_fail("optmem limit test failed: couldn't add %zu key", i);
+			break;
+		}
+		test_ok("optmem limit was hit on adding %zu key", i);
+		break;
+	}
+	close(sk);
+}
+
+static void test_einval_add_key(void)
+{
+	struct tcp_ao_add ao;
+	int sk;
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	ao.keylen = TCP_AO_MAXKEYLEN + 1;
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EINVAL, "too big keylen");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	ao.reserved = 1;
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EINVAL, "using reserved padding");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	ao.reserved2 = 1;
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EINVAL, "using reserved2 padding");
+
+	/* tcp_ao_verify_ipv{4,6}() checks */
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	ao.addr.ss_family = AF_UNIX;
+	memcpy(&ao.addr, &SOCKADDR_ANY, sizeof(SOCKADDR_ANY));
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EINVAL, "wrong address family");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	tcp_addr_to_sockaddr_in(&ao.addr, &this_ip_dest, 1234);
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EINVAL, "port (unsupported)");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	ao.prefix = 0;
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EINVAL, "no prefix, addr");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	ao.prefix = 0;
+	memcpy(&ao.addr, &SOCKADDR_ANY, sizeof(SOCKADDR_ANY));
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, 0, "no prefix, any addr");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	ao.prefix = 32;
+	memcpy(&ao.addr, &SOCKADDR_ANY, sizeof(SOCKADDR_ANY));
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EINVAL, "prefix, any addr");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	ao.prefix = 129;
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EINVAL, "too big prefix");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	ao.prefix = 2;
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EINVAL, "too short prefix");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	ao.keyflags = (uint8_t)(-1);
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EINVAL, "bad key flags");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	make_listen(sk);
+	ao.set_current = 1;
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EINVAL, "add current key on a listen socket");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	make_listen(sk);
+	ao.set_rnext = 1;
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EINVAL, "add rnext key on a listen socket");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	make_listen(sk);
+	ao.set_current = 1;
+	ao.set_rnext = 1;
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EINVAL, "add current+rnext key on a listen socket");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	ao.set_current = 1;
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, 0, "add key and set as current");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	ao.set_rnext = 1;
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, 0, "add key and set as rnext");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	ao.set_current = 1;
+	ao.set_rnext = 1;
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, 0, "add key and set as current+rnext");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	ao.ifindex = 42;
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EINVAL,
+			   "ifindex without TCP_AO_KEYF_IFNINDEX");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	ao.keyflags |= TCP_AO_KEYF_IFINDEX;
+	ao.ifindex = 42;
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EINVAL, "non-existent VRF");
+	/*
+	 * tcp_md5_do_lookup{,_any_l3index}() are checked in unsigned-md5
+	 * see client_vrf_tests().
+	 */
+
+	test_optmem_limit();
+
+	/* tcp_ao_parse_crypto() */
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	ao.maclen = 100;
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EMSGSIZE, "maclen bigger than TCP hdr");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	strcpy(ao.alg_name, "imaginary hash algo");
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, ENOENT, "bad algo");
+}
+
+static void test_einval_del_key(void)
+{
+	struct tcp_ao_del del;
+	int sk;
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	del.reserved = 1;
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, EINVAL, "using reserved padding");
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	del.reserved2 = 1;
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, EINVAL, "using reserved2 padding");
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	make_listen(sk);
+	if (test_add_key(sk, DEFAULT_TEST_PASSWORD, this_ip_dest, DEFAULT_TEST_PREFIX, 0, 0))
+		test_error("add key");
+	del.set_current = 1;
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, EINVAL, "del and set current key on a listen socket");
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	make_listen(sk);
+	if (test_add_key(sk, DEFAULT_TEST_PASSWORD, this_ip_dest, DEFAULT_TEST_PREFIX, 0, 0))
+		test_error("add key");
+	del.set_rnext = 1;
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, EINVAL, "del and set rnext key on a listen socket");
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	make_listen(sk);
+	if (test_add_key(sk, DEFAULT_TEST_PASSWORD, this_ip_dest, DEFAULT_TEST_PREFIX, 0, 0))
+		test_error("add key");
+	del.set_current = 1;
+	del.set_rnext = 1;
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, EINVAL, "del and set current+rnext key on a listen socket");
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	del.keyflags = (uint8_t)(-1);
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, EINVAL, "bad key flags");
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	del.ifindex = 42;
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, EINVAL,
+			   "ifindex without TCP_AO_KEYF_IFNINDEX");
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	del.keyflags |= TCP_AO_KEYF_IFINDEX;
+	del.ifindex = 42;
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, ENOENT, "non-existent VRF");
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	del.set_current = 1;
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, ENOENT, "set non-existing current key");
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	del.set_rnext = 1;
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, ENOENT, "set non-existing rnext key");
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	del.set_current = 1;
+	del.set_rnext = 1;
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, ENOENT, "set non-existing current+rnext key");
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	if (test_add_key(sk, DEFAULT_TEST_PASSWORD, this_ip_dest, DEFAULT_TEST_PREFIX, 0, 0))
+		test_error("add key");
+	del.set_current = 1;
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, 0, "set current key");
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	if (test_add_key(sk, DEFAULT_TEST_PASSWORD, this_ip_dest, DEFAULT_TEST_PREFIX, 0, 0))
+		test_error("add key");
+	del.set_rnext = 1;
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, 0, "set rnext key");
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	if (test_add_key(sk, DEFAULT_TEST_PASSWORD, this_ip_dest, DEFAULT_TEST_PREFIX, 0, 0))
+		test_error("add key");
+	del.set_current = 1;
+	del.set_rnext = 1;
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, 0, "set current+rnext key");
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	del.set_current = 1;
+	del.current_key = 100;
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, ENOENT, "set as current key to be removed");
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	del.set_rnext = 1;
+	del.rnext = 100;
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, ENOENT, "set as rnext key to be removed");
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	del.set_current = 1;
+	del.current_key = 100;
+	del.set_rnext = 1;
+	del.rnext = 100;
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, ENOENT, "set as current+rnext key to be removed");
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	del.del_async = 1;
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, EINVAL, "async on non-listen");
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	del.sndid = 101;
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, ENOENT, "non-existing sndid");
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	del.rcvid = 101;
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, ENOENT, "non-existing rcvid");
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	tcp_addr_to_sockaddr_in(&del.addr, &this_ip_addr, 0);
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, ENOENT, "incorrect addr");
+
+	sk = prepare_defs(TCP_AO_DEL_KEY, &del);
+	setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, 0, "correct key delete");
+}
+
+static void test_einval_ao_info(void)
+{
+	struct tcp_ao_info_opt info;
+	int sk;
+
+	sk = prepare_defs(TCP_AO_INFO, &info);
+	make_listen(sk);
+	info.set_current = 1;
+	setsockopt_checked(sk, TCP_AO_INFO, &info, EINVAL, "set current key on a listen socket");
+
+	sk = prepare_defs(TCP_AO_INFO, &info);
+	make_listen(sk);
+	info.set_rnext = 1;
+	setsockopt_checked(sk, TCP_AO_INFO, &info, EINVAL, "set rnext key on a listen socket");
+
+	sk = prepare_defs(TCP_AO_INFO, &info);
+	make_listen(sk);
+	info.set_current = 1;
+	info.set_rnext = 1;
+	setsockopt_checked(sk, TCP_AO_INFO, &info, EINVAL, "set current+rnext key on a listen socket");
+
+	sk = prepare_defs(TCP_AO_INFO, &info);
+	info.reserved = 1;
+	setsockopt_checked(sk, TCP_AO_INFO, &info, EINVAL, "using reserved padding");
+
+	sk = prepare_defs(TCP_AO_INFO, &info);
+	info.reserved2 = 1;
+	setsockopt_checked(sk, TCP_AO_INFO, &info, EINVAL, "using reserved2 padding");
+
+	sk = prepare_defs(TCP_AO_INFO, &info);
+	info.accept_icmps = 1;
+	setsockopt_checked(sk, TCP_AO_INFO, &info, 0, "accept_icmps");
+
+	sk = prepare_defs(TCP_AO_INFO, &info);
+	info.ao_required = 1;
+	setsockopt_checked(sk, TCP_AO_INFO, &info, 0, "ao required");
+
+	if (!should_skip_test("ao required with MD5 key", KCONFIG_TCP_MD5)) {
+		sk = prepare_defs(TCP_AO_INFO, &info);
+		info.ao_required = 1;
+		if (test_set_md5(sk, tcp_md5_client, TEST_PREFIX, -1,
+				 "long long secret")) {
+			test_error("setsockopt(TCP_MD5SIG_EXT)");
+			close(sk);
+		} else {
+			setsockopt_checked(sk, TCP_AO_INFO, &info, EKEYREJECTED,
+					   "ao required with MD5 key");
+		}
+	}
+
+	sk = prepare_defs(TCP_AO_INFO, &info);
+	info.set_current = 1;
+	setsockopt_checked(sk, TCP_AO_INFO, &info, ENOENT, "set non-existing current key");
+
+	sk = prepare_defs(TCP_AO_INFO, &info);
+	info.set_rnext = 1;
+	setsockopt_checked(sk, TCP_AO_INFO, &info, ENOENT, "set non-existing rnext key");
+
+	sk = prepare_defs(TCP_AO_INFO, &info);
+	info.set_current = 1;
+	info.set_rnext = 1;
+	setsockopt_checked(sk, TCP_AO_INFO, &info, ENOENT, "set non-existing current+rnext key");
+
+	sk = prepare_defs(TCP_AO_INFO, &info);
+	info.set_current = 1;
+	info.current_key = 100;
+	setsockopt_checked(sk, TCP_AO_INFO, &info, 0, "set current key");
+
+	sk = prepare_defs(TCP_AO_INFO, &info);
+	info.set_rnext = 1;
+	info.rnext = 100;
+	setsockopt_checked(sk, TCP_AO_INFO, &info, 0, "set rnext key");
+
+	sk = prepare_defs(TCP_AO_INFO, &info);
+	info.set_current = 1;
+	info.set_rnext = 1;
+	info.current_key = 100;
+	info.rnext = 100;
+	setsockopt_checked(sk, TCP_AO_INFO, &info, 0, "set current+rnext key");
+
+	sk = prepare_defs(TCP_AO_INFO, &info);
+	info.set_counters = 1;
+	info.pkt_good = 321;
+	info.pkt_bad = 888;
+	info.pkt_key_not_found = 654;
+	info.pkt_ao_required = 987654;
+	info.pkt_dropped_icmp = 10000;
+	setsockopt_checked(sk, TCP_AO_INFO, &info, 0, "set counters");
+
+	sk = prepare_defs(TCP_AO_INFO, &info);
+	setsockopt_checked(sk, TCP_AO_INFO, &info, 0, "no-op");
+}
+
+static void getsockopt_checked(int sk, struct tcp_ao_getsockopt *optval,
+			       int err, const char *tst)
+{
+	socklen_t len = sizeof(struct tcp_ao_getsockopt);
+
+	__setsockopt_checked(sk, TCP_AO_GET_KEYS, true, optval, &len, err,
+			     "get keys: ", tst);
+}
+
+static void test_einval_get_keys(void)
+{
+	struct tcp_ao_getsockopt out;
+	int sk;
+
+	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+	if (sk < 0)
+		test_error("socket()");
+	getsockopt_checked(sk, &out, ENOENT, "no ao_info");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	getsockopt_checked(sk, &out, 0, "proper tcp_ao_get_mkts()");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.pkt_good = 643;
+	getsockopt_checked(sk, &out, EINVAL, "set out-only pkt_good counter");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.pkt_bad = 94;
+	getsockopt_checked(sk, &out, EINVAL, "set out-only pkt_bad counter");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.keyflags = (uint8_t)(-1);
+	getsockopt_checked(sk, &out, EINVAL, "bad keyflags");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.ifindex = 42;
+	getsockopt_checked(sk, &out, EINVAL,
+			   "ifindex without TCP_AO_KEYF_IFNINDEX");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.reserved = 1;
+	getsockopt_checked(sk, &out, EINVAL, "using reserved field");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.get_all = 0;
+	out.prefix = 0;
+	tcp_addr_to_sockaddr_in(&out.addr, &this_ip_dest, 0);
+	getsockopt_checked(sk, &out, EINVAL, "no prefix, addr");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.get_all = 0;
+	out.prefix = 0;
+	memcpy(&out.addr, &SOCKADDR_ANY, sizeof(SOCKADDR_ANY));
+	getsockopt_checked(sk, &out, 0, "no prefix, any addr");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.get_all = 0;
+	out.prefix = 32;
+	memcpy(&out.addr, &SOCKADDR_ANY, sizeof(SOCKADDR_ANY));
+	getsockopt_checked(sk, &out, EINVAL, "prefix, any addr");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.get_all = 0;
+	out.prefix = 129;
+	tcp_addr_to_sockaddr_in(&out.addr, &this_ip_dest, 0);
+	getsockopt_checked(sk, &out, EINVAL, "too big prefix");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.get_all = 0;
+	out.prefix = 2;
+	tcp_addr_to_sockaddr_in(&out.addr, &this_ip_dest, 0);
+	getsockopt_checked(sk, &out, EINVAL, "too short prefix");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.get_all = 0;
+	out.prefix = DEFAULT_TEST_PREFIX;
+	tcp_addr_to_sockaddr_in(&out.addr, &this_ip_dest, 0);
+	getsockopt_checked(sk, &out, 0, "prefix + addr");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.get_all = 1;
+	out.prefix = DEFAULT_TEST_PREFIX;
+	getsockopt_checked(sk, &out, EINVAL, "get_all + prefix");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.get_all = 1;
+	tcp_addr_to_sockaddr_in(&out.addr, &this_ip_dest, 0);
+	getsockopt_checked(sk, &out, EINVAL, "get_all + addr");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.get_all = 1;
+	out.sndid = 1;
+	getsockopt_checked(sk, &out, EINVAL, "get_all + sndid");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.get_all = 1;
+	out.rcvid = 1;
+	getsockopt_checked(sk, &out, EINVAL, "get_all + rcvid");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.get_all = 0;
+	out.is_current = 1;
+	out.prefix = DEFAULT_TEST_PREFIX;
+	getsockopt_checked(sk, &out, EINVAL, "current + prefix");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.get_all = 0;
+	out.is_current = 1;
+	tcp_addr_to_sockaddr_in(&out.addr, &this_ip_dest, 0);
+	getsockopt_checked(sk, &out, EINVAL, "current + addr");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.get_all = 0;
+	out.is_current = 1;
+	out.sndid = 1;
+	getsockopt_checked(sk, &out, EINVAL, "current + sndid");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.get_all = 0;
+	out.is_current = 1;
+	out.rcvid = 1;
+	getsockopt_checked(sk, &out, EINVAL, "current + rcvid");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.get_all = 0;
+	out.is_rnext = 1;
+	out.prefix = DEFAULT_TEST_PREFIX;
+	getsockopt_checked(sk, &out, EINVAL, "rnext + prefix");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.get_all = 0;
+	out.is_rnext = 1;
+	tcp_addr_to_sockaddr_in(&out.addr, &this_ip_dest, 0);
+	getsockopt_checked(sk, &out, EINVAL, "rnext + addr");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.get_all = 0;
+	out.is_rnext = 1;
+	out.sndid = 1;
+	getsockopt_checked(sk, &out, EINVAL, "rnext + sndid");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.get_all = 0;
+	out.is_rnext = 1;
+	out.rcvid = 1;
+	getsockopt_checked(sk, &out, EINVAL, "rnext + rcvid");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.get_all = 1;
+	out.is_current = 1;
+	getsockopt_checked(sk, &out, EINVAL, "get_all + current");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.get_all = 1;
+	out.is_rnext = 1;
+	getsockopt_checked(sk, &out, EINVAL, "get_all + rnext");
+
+	sk = prepare_defs(TCP_AO_GET_KEYS, &out);
+	out.get_all = 0;
+	out.is_current = 1;
+	out.is_rnext = 1;
+	getsockopt_checked(sk, &out, 0, "current + rnext");
+}
+
+static void einval_tests(void)
+{
+	test_einval_add_key();
+	test_einval_del_key();
+	test_einval_ao_info();
+	test_einval_get_keys();
+}
+
+static void duplicate_tests(void)
+{
+	union tcp_addr network_dup;
+	struct tcp_ao_add ao, ao2;
+	int sk;
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	if (setsockopt(sk, IPPROTO_TCP, TCP_AO_ADD_KEY, &ao, sizeof(ao)))
+		test_error("setsockopt()");
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EEXIST, "duplicate: full copy");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	ao2 = ao;
+	memcpy(&ao2.addr, &SOCKADDR_ANY, sizeof(SOCKADDR_ANY));
+	ao2.prefix = 0;
+	if (setsockopt(sk, IPPROTO_TCP, TCP_AO_ADD_KEY, &ao2, sizeof(ao)))
+		test_error("setsockopt()");
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EEXIST, "duplicate: any addr key on the socket");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	if (setsockopt(sk, IPPROTO_TCP, TCP_AO_ADD_KEY, &ao, sizeof(ao)))
+		test_error("setsockopt()");
+	memcpy(&ao.addr, &SOCKADDR_ANY, sizeof(SOCKADDR_ANY));
+	ao.prefix = 0;
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EEXIST, "duplicate: add any addr key");
+
+	if (inet_pton(TEST_FAMILY, TEST_NETWORK, &network_dup) != 1)
+		test_error("Can't convert ip address %s", TEST_NETWORK);
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	if (setsockopt(sk, IPPROTO_TCP, TCP_AO_ADD_KEY, &ao, sizeof(ao)))
+		test_error("setsockopt()");
+	if (test_prepare_def_key(&ao, "password", 0, network_dup,
+				 16, 0, 100, 100))
+		test_error("prepare default tcp_ao_add");
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EEXIST, "duplicate: add any addr for the same subnet");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	if (setsockopt(sk, IPPROTO_TCP, TCP_AO_ADD_KEY, &ao, sizeof(ao)))
+		test_error("setsockopt()");
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EEXIST, "duplicate: full copy of a key");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	if (setsockopt(sk, IPPROTO_TCP, TCP_AO_ADD_KEY, &ao, sizeof(ao)))
+		test_error("setsockopt()");
+	ao.rcvid = 101;
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EEXIST, "duplicate: RecvID differs");
+
+	sk = prepare_defs(TCP_AO_ADD_KEY, &ao);
+	if (setsockopt(sk, IPPROTO_TCP, TCP_AO_ADD_KEY, &ao, sizeof(ao)))
+		test_error("setsockopt()");
+	ao.sndid = 101;
+	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EEXIST, "duplicate: SendID differs");
+}
+
+static void *client_fn(void *arg)
+{
+	if (inet_pton(TEST_FAMILY, __TEST_CLIENT_IP(2), &tcp_md5_client) != 1)
+		test_error("Can't convert ip address");
+	extend_tests();
+	einval_tests();
+	duplicate_tests();
+	/*
+	 * TODO: check getsockopt(TCP_AO_GET_KEYS) with different filters
+	 * returning proper nr & keys;
+	 */
+
+	return NULL;
+}
+
+int main(int argc, char *argv[])
+{
+	test_init(120, client_fn, NULL);
+	return 0;
+}
diff --git a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
new file mode 100644
index 000000000000..c5b568cd7d90
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
@@ -0,0 +1,741 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Author: Dmitry Safonov <dima@arista.com> */
+#include <inttypes.h>
+#include "aolib.h"
+
+#define fault(type)	(inj == FAULT_ ## type)
+static const char *md5_password = "Some evil genius, enemy to mankind, must have been the first contriver.";
+static const char *ao_password = DEFAULT_TEST_PASSWORD;
+
+static union tcp_addr client2;
+static union tcp_addr client3;
+
+static const int test_vrf_ifindex = 200;
+static const uint8_t test_vrf_tabid = 42;
+static void setup_vrfs(void)
+{
+	int err;
+
+	if (!kernel_config_has(KCONFIG_NET_VRF))
+		return;
+
+	err = add_vrf("ksft-vrf", test_vrf_tabid, test_vrf_ifindex, -1);
+	if (err)
+		test_error("Failed to add a VRF: %d", err);
+
+	err = link_set_up("ksft-vrf");
+	if (err)
+		test_error("Failed to bring up a VRF");
+
+	err = ip_route_add_vrf(veth_name, TEST_FAMILY,
+			       this_ip_addr, this_ip_dest, test_vrf_tabid);
+	if (err)
+		test_error("Failed to add a route to VRF: %d", err);
+}
+
+static void try_accept(const char *tst_name, unsigned int port,
+		       union tcp_addr *md5_addr, uint8_t md5_prefix,
+		       union tcp_addr *ao_addr, uint8_t ao_prefix,
+		       bool set_ao_required,
+		       uint8_t sndid, uint8_t rcvid, uint8_t vrf,
+		       const char *cnt_name, test_cnt cnt_expected,
+		       int needs_tcp_md5, fault_t inj)
+{
+	struct tcp_ao_counters ao_cnt1, ao_cnt2;
+	uint64_t before_cnt = 0, after_cnt = 0; /* silence GCC */
+	int lsk, err, sk = 0;
+	time_t timeout;
+
+	if (needs_tcp_md5 && should_skip_test(tst_name, KCONFIG_TCP_MD5))
+		return;
+
+	lsk = test_listen_socket(this_ip_addr, port, 1);
+
+	if (md5_addr && test_set_md5(lsk, *md5_addr, md5_prefix, -1, md5_password))
+		test_error("setsockopt(TCP_MD5SIG_EXT)");
+
+	if (ao_addr && test_add_key(lsk, ao_password,
+				    *ao_addr, ao_prefix, sndid, rcvid))
+		test_error("setsockopt(TCP_AO_ADD_KEY)");
+
+	if (set_ao_required && test_set_ao_flags(lsk, true, false))
+		test_error("setsockopt(TCP_AO_INFO)");
+
+	if (cnt_name)
+		before_cnt = netstat_get_one(cnt_name, NULL);
+	if (ao_addr && test_get_tcp_ao_counters(lsk, &ao_cnt1))
+		test_error("test_get_tcp_ao_counters()");
+
+	synchronize_threads(); /* preparations done */
+
+	timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
+	err = test_wait_fd(lsk, timeout, 0);
+	if (err == -ETIMEDOUT) {
+		if (!fault(TIMEOUT))
+			test_fail("timed out for accept()");
+	} else if (err < 0) {
+		test_error("test_wait_fd()");
+	} else {
+		if (fault(TIMEOUT))
+			test_fail("ready to accept");
+
+		sk = accept(lsk, NULL, NULL);
+		if (sk < 0) {
+			test_error("accept()");
+		} else {
+			if (fault(TIMEOUT))
+				test_fail("%s: accepted", tst_name);
+		}
+	}
+
+	if (ao_addr && test_get_tcp_ao_counters(lsk, &ao_cnt2))
+		test_error("test_get_tcp_ao_counters()");
+	close(lsk);
+
+	if (!cnt_name) {
+		test_ok("%s: no counter checks", tst_name);
+		goto out;
+	}
+
+	after_cnt = netstat_get_one(cnt_name, NULL);
+
+	if (after_cnt <= before_cnt) {
+		test_fail("%s: %s counter did not increase: %zu <= %zu",
+				tst_name, cnt_name, after_cnt, before_cnt);
+	} else {
+		test_ok("%s: counter %s increased %zu => %zu",
+			tst_name, cnt_name, before_cnt, after_cnt);
+	}
+	if (ao_addr)
+		test_tcp_ao_counters_cmp(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected);
+
+out:
+	synchronize_threads(); /* close() */
+	if (sk > 0)
+		close(sk);
+}
+
+static void server_add_routes(void)
+{
+	int family = TEST_FAMILY;
+
+	synchronize_threads(); /* client_add_ips() */
+
+	if (ip_route_add(veth_name, family, this_ip_addr, client2))
+		test_error("Failed to add route");
+	if (ip_route_add(veth_name, family, this_ip_addr, client3))
+		test_error("Failed to add route");
+}
+
+static void server_add_fail_tests(unsigned int *port)
+{
+	union tcp_addr addr_any = {};
+
+	try_accept("TCP-AO established: add TCP-MD5 key", (*port)++, NULL, 0,
+		   &addr_any, 0, 0, 100, 100, 0, "TCPAOGood", TEST_CNT_GOOD,
+		   1, 0);
+	try_accept("TCP-MD5 established: add TCP-AO key", (*port)++, &addr_any,
+		   0, NULL, 0, 0, 0, 0, 0, NULL, 0, 1, 0);
+	try_accept("non-signed established: add TCP-AO key", (*port)++, NULL, 0,
+		   NULL, 0, 0, 0, 0, 0, "CurrEstab", 0, 0, 0);
+}
+
+static void server_vrf_tests(unsigned int *port)
+{
+	setup_vrfs();
+}
+
+static void *server_fn(void *arg)
+{
+	unsigned int port = test_server_port;
+	union tcp_addr addr_any = {};
+
+	server_add_routes();
+
+	try_accept("AO server (INADDR_ANY): AO client", port++, NULL, 0,
+		   &addr_any, 0, 0, 100, 100, 0, "TCPAOGood",
+		   TEST_CNT_GOOD, 0, 0);
+	try_accept("AO server (INADDR_ANY): MD5 client", port++, NULL, 0,
+		   &addr_any, 0, 0, 100, 100, 0, "TCPMD5Unexpected",
+		   0, 1, FAULT_TIMEOUT);
+	try_accept("AO server (INADDR_ANY): no sign client", port++, NULL, 0,
+		   &addr_any, 0, 0, 100, 100, 0, "TCPAORequired",
+		   TEST_CNT_AO_REQUIRED, 0, FAULT_TIMEOUT);
+	try_accept("AO server (AO_REQUIRED): AO client", port++, NULL, 0,
+		   &this_ip_dest, TEST_PREFIX, true,
+		   100, 100, 0, "TCPAOGood", TEST_CNT_GOOD, 0, 0);
+	try_accept("AO server (AO_REQUIRED): unsigned client", port++, NULL, 0,
+		   &this_ip_dest, TEST_PREFIX, true,
+		   100, 100, 0, "TCPAORequired",
+		   TEST_CNT_AO_REQUIRED, 0, FAULT_TIMEOUT);
+
+	try_accept("MD5 server (INADDR_ANY): AO client", port++, &addr_any, 0,
+		   NULL, 0, 0, 0, 0, 0, "TCPAOKeyNotFound",
+		   0, 1, FAULT_TIMEOUT);
+	try_accept("MD5 server (INADDR_ANY): MD5 client", port++, &addr_any, 0,
+		   NULL, 0, 0, 0, 0, 0, NULL, 0, 1, 0);
+	try_accept("MD5 server (INADDR_ANY): no sign client", port++, &addr_any,
+		   0, NULL, 0, 0, 0, 0, 0, "TCPMD5NotFound",
+		   0, 1, FAULT_TIMEOUT);
+
+	try_accept("no sign server: AO client", port++, NULL, 0,
+		   NULL, 0, 0, 0, 0, 0, "TCPAOKeyNotFound",
+		   TEST_CNT_AO_KEY_NOT_FOUND, 0, FAULT_TIMEOUT);
+	try_accept("no sign server: MD5 client", port++, NULL, 0,
+		   NULL, 0, 0, 0, 0, 0, "TCPMD5Unexpected",
+		   0, 1, FAULT_TIMEOUT);
+	try_accept("no sign server: no sign client", port++, NULL, 0,
+		   NULL, 0, 0, 0, 0, 0, "CurrEstab", 0, 0, 0);
+
+	try_accept("AO+MD5 server: AO client (matching)", port++,
+		   &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
+		   100, 100, 0, "TCPAOGood", TEST_CNT_GOOD, 1, 0);
+	try_accept("AO+MD5 server: AO client (misconfig, matching MD5)", port++,
+		   &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
+		   100, 100, 0, "TCPAOKeyNotFound", TEST_CNT_AO_KEY_NOT_FOUND,
+		   1, FAULT_TIMEOUT);
+	try_accept("AO+MD5 server: AO client (misconfig, non-matching)", port++,
+		   &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
+		   100, 100, 0, "TCPAOKeyNotFound", TEST_CNT_AO_KEY_NOT_FOUND,
+		   1, FAULT_TIMEOUT);
+	try_accept("AO+MD5 server: MD5 client (matching)", port++,
+		   &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
+		   100, 100, 0, NULL, 0, 1, 0);
+	try_accept("AO+MD5 server: MD5 client (misconfig, matching AO)", port++,
+		   &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
+		   100, 100, 0, "TCPMD5Unexpected", 0, 1, FAULT_TIMEOUT);
+	try_accept("AO+MD5 server: MD5 client (misconfig, non-matching)", port++,
+		   &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
+		   100, 100, 0, "TCPMD5Unexpected", 0, 1, FAULT_TIMEOUT);
+	try_accept("AO+MD5 server: no sign client (unmatched)", port++,
+		   &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
+		   100, 100, 0, "CurrEstab", 0, 1, 0);
+	try_accept("AO+MD5 server: no sign client (misconfig, matching AO)",
+		   port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
+		   100, 100, 0, "TCPAORequired",
+		   TEST_CNT_AO_REQUIRED, 1, FAULT_TIMEOUT);
+	try_accept("AO+MD5 server: no sign client (misconfig, matching MD5)",
+		   port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
+		   100, 100, 0, "TCPMD5NotFound", 0, 1, FAULT_TIMEOUT);
+
+	try_accept("AO+MD5 server: client with both [TCP-MD5] and TCP-AO keys",
+		   port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
+		   100, 100, 0, NULL, 0, 1, FAULT_TIMEOUT);
+	try_accept("AO+MD5 server: client with both TCP-MD5 and [TCP-AO] keys",
+		   port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
+		   100, 100, 0, NULL, 0, 1, FAULT_TIMEOUT);
+
+	server_add_fail_tests(&port);
+
+	server_vrf_tests(&port);
+
+	/* client exits */
+	synchronize_threads();
+	return NULL;
+}
+
+static int client_bind(int sk, union tcp_addr bind_addr)
+{
+#ifdef IPV6_TEST
+	struct sockaddr_in6 addr = {
+		.sin6_family	= AF_INET6,
+		.sin6_port	= 0,
+		.sin6_addr	= bind_addr.a6,
+	};
+#else
+	struct sockaddr_in addr = {
+		.sin_family	= AF_INET,
+		.sin_port	= 0,
+		.sin_addr	= bind_addr.a4,
+	};
+#endif
+	return bind(sk, &addr, sizeof(addr));
+}
+
+static void try_connect(const char *tst_name, unsigned int port,
+		       union tcp_addr *md5_addr, uint8_t md5_prefix,
+		       union tcp_addr *ao_addr, uint8_t ao_prefix,
+		       uint8_t sndid, uint8_t rcvid, uint8_t vrf,
+		       fault_t inj, int needs_tcp_md5, union tcp_addr *bind_addr)
+{
+	time_t timeout;
+	int sk, ret;
+
+	if (needs_tcp_md5 && should_skip_test(tst_name, KCONFIG_TCP_MD5))
+		return;
+
+	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+	if (sk < 0)
+		test_error("socket()");
+
+	if (bind_addr && client_bind(sk, *bind_addr))
+		test_error("bind()");
+
+	if (md5_addr && test_set_md5(sk, *md5_addr, md5_prefix, -1, md5_password))
+		test_error("setsockopt(TCP_MD5SIG_EXT)");
+
+	if (ao_addr && test_add_key(sk, ao_password, *ao_addr,
+				    ao_prefix, sndid, rcvid))
+		test_error("setsockopt(TCP_AO_ADD_KEY)");
+
+	synchronize_threads(); /* preparations done */
+
+	timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
+	ret = _test_connect_socket(sk, this_ip_dest, port, timeout);
+
+	if (ret < 0) {
+		if (fault(KEYREJECT) && ret == -EKEYREJECTED)
+			test_ok("%s: connect() was prevented", tst_name);
+		else if (ret == -ETIMEDOUT && fault(TIMEOUT))
+			test_ok("%s", tst_name);
+		else if (ret == -ECONNREFUSED &&
+				(fault(TIMEOUT) || fault(KEYREJECT)))
+			test_ok("%s: refused to connect", tst_name);
+		else
+			test_error("%s: connect() returned %d", tst_name, ret);
+		goto out;
+	}
+
+	if (fault(TIMEOUT) || fault(KEYREJECT))
+		test_fail("%s: connected", tst_name);
+	else
+		test_ok("%s: connected", tst_name);
+
+out:
+	synchronize_threads(); /* close() */
+	/* _test_connect_socket() cleans up on failure */
+	if (ret > 0)
+		close(sk);
+}
+
+#define PREINSTALL_MD5_FIRST	BIT(0)
+#define PREINSTALL_AO		BIT(1)
+#define POSTINSTALL_AO		BIT(2)
+#define PREINSTALL_MD5		BIT(3)
+#define POSTINSTALL_MD5		BIT(4)
+
+static int try_add_key_vrf(int sk, union tcp_addr in_addr, uint8_t prefix,
+			   int vrf, uint8_t sndid, uint8_t rcvid,
+			   bool set_ao_required)
+{
+	uint8_t keyflags = 0;
+
+	if (vrf >= 0)
+		keyflags |= TCP_AO_KEYF_IFINDEX;
+	else
+		vrf = 0;
+	if (set_ao_required) {
+		int err = test_set_ao_flags(sk, true, 0);
+
+		if (err)
+			return err;
+	}
+	return test_add_key_vrf(sk, ao_password, keyflags, in_addr, prefix,
+				(uint8_t)vrf, sndid, rcvid);
+}
+
+static bool test_continue(const char *tst_name, int err,
+			  fault_t inj, bool added_ao)
+{
+	bool expected_to_fail;
+
+	expected_to_fail = fault(PREINSTALL_AO) && added_ao;
+	expected_to_fail |= fault(PREINSTALL_MD5) && !added_ao;
+
+	if (!err) {
+		if (!expected_to_fail)
+			return true;
+		test_fail("%s: setsockopt()s were expected to fail", tst_name);
+		return false;
+	}
+	if (err != -EKEYREJECTED || !expected_to_fail) {
+		test_error("%s: setsockopt(%s) = %d", tst_name,
+			   added_ao ? "TCP_AO_ADD_KEY" : "TCP_MD5SIG_EXT", err);
+		return false;
+	}
+	test_ok("%s: prefailed as expected: %m", tst_name);
+	return false;
+}
+
+static int open_add(const char *tst_name, unsigned int port,
+		    unsigned int strategy,
+		    union tcp_addr md5_addr, uint8_t md5_prefix, int md5_vrf,
+		    union tcp_addr ao_addr, uint8_t ao_prefix,
+		    int ao_vrf, bool set_ao_required,
+		    uint8_t sndid, uint8_t rcvid,
+		    fault_t inj)
+{
+	int sk;
+
+	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+	if (sk < 0)
+		test_error("socket()");
+
+	if (client_bind(sk, this_ip_addr))
+		test_error("bind()");
+
+	if (strategy & PREINSTALL_MD5_FIRST) {
+		if (test_set_md5(sk, md5_addr, md5_prefix, md5_vrf, md5_password))
+			test_error("setsockopt(TCP_MD5SIG_EXT)");
+	}
+
+	if (strategy & PREINSTALL_AO) {
+		int err = try_add_key_vrf(sk, ao_addr, ao_prefix, ao_vrf,
+					  sndid, rcvid, set_ao_required);
+
+		if (!test_continue(tst_name, err, inj, true)) {
+			close(sk);
+			return -1;
+		}
+	}
+
+	if (strategy & PREINSTALL_MD5) {
+		errno = 0;
+		test_set_md5(sk, md5_addr, md5_prefix, md5_vrf, md5_password);
+		if (!test_continue(tst_name, -errno, inj, false)) {
+			close(sk);
+			return -1;
+		}
+	}
+
+	return sk;
+}
+
+static void try_to_preadd(const char *tst_name, unsigned int port,
+			  unsigned int strategy,
+			  union tcp_addr md5_addr, uint8_t md5_prefix,
+			  int md5_vrf,
+			  union tcp_addr ao_addr, uint8_t ao_prefix,
+			  int ao_vrf, bool set_ao_required,
+			  uint8_t sndid, uint8_t rcvid,
+			  int needs_tcp_md5, int needs_vrf, fault_t inj)
+{
+	int sk;
+
+	if (needs_tcp_md5 && should_skip_test(tst_name, KCONFIG_TCP_MD5))
+		return;
+	if (needs_vrf && should_skip_test(tst_name, KCONFIG_NET_VRF))
+		return;
+
+	sk = open_add(tst_name, port, strategy, md5_addr, md5_prefix, md5_vrf,
+		      ao_addr, ao_prefix, ao_vrf, set_ao_required,
+		      sndid, rcvid, inj);
+	if (sk < 0)
+		return;
+
+	test_ok("%s", tst_name);
+	close(sk);
+}
+
+static void try_to_add(const char *tst_name, unsigned int port,
+		       unsigned int strategy,
+		       union tcp_addr md5_addr, uint8_t md5_prefix,
+		       int md5_vrf,
+		       union tcp_addr ao_addr, uint8_t ao_prefix,
+		       int ao_vrf, uint8_t sndid, uint8_t rcvid,
+		       int needs_tcp_md5, fault_t inj)
+{
+	time_t timeout;
+	int sk, ret;
+
+	if (needs_tcp_md5 && should_skip_test(tst_name, KCONFIG_TCP_MD5))
+		return;
+
+	sk = open_add(tst_name, port, strategy, md5_addr, md5_prefix, md5_vrf,
+		      ao_addr, ao_prefix, ao_vrf, 0, sndid, rcvid, inj);
+	if (sk < 0)
+		return;
+
+	synchronize_threads(); /* preparations done */
+
+	timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
+	ret = _test_connect_socket(sk, this_ip_dest, port, timeout);
+
+	if (ret <= 0) {
+		test_error("%s: connect() returned %d", tst_name, ret);
+		goto out;
+	}
+
+	if (strategy & POSTINSTALL_MD5) {
+		if (test_set_md5(sk, md5_addr, md5_prefix, md5_vrf, md5_password)) {
+			if (fault(POSTINSTALL)) {
+				test_ok("%s: postfailed as expected", tst_name);
+				goto out;
+			} else {
+				test_error("setsockopt(TCP_MD5SIG_EXT)");
+			}
+		} else if (fault(POSTINSTALL)) {
+			test_fail("%s: post setsockopt() was expected to fail", tst_name);
+			goto out;
+		}
+	}
+
+	if (strategy & POSTINSTALL_AO) {
+		if (try_add_key_vrf(sk, ao_addr, ao_prefix, ao_vrf,
+				   sndid, rcvid, 0)) {
+			if (fault(POSTINSTALL)) {
+				test_ok("%s: postfailed as expected", tst_name);
+				goto out;
+			} else {
+				test_error("setsockopt(TCP_AO_ADD_KEY)");
+			}
+		} else if (fault(POSTINSTALL)) {
+			test_fail("%s: post setsockopt() was expected to fail", tst_name);
+			goto out;
+		}
+	}
+
+out:
+	synchronize_threads(); /* close() */
+	/* _test_connect_socket() cleans up on failure */
+	if (ret > 0)
+		close(sk);
+}
+
+static void client_add_ip(union tcp_addr *client, const char *ip)
+{
+	int err, family = TEST_FAMILY;
+
+	if (inet_pton(family, ip, client) != 1)
+		test_error("Can't convert ip address %s", ip);
+
+	err = ip_addr_add(veth_name, family, *client, TEST_PREFIX);
+	if (err)
+		test_error("Failed to add ip address: %d", err);
+}
+
+static void client_add_ips(void)
+{
+	client_add_ip(&client2, __TEST_CLIENT_IP(2));
+	client_add_ip(&client3, __TEST_CLIENT_IP(3));
+	synchronize_threads(); /* server_add_routes() */
+}
+
+static void client_add_fail_tests(unsigned int *port)
+{
+	try_to_add("TCP-AO established: add TCP-MD5 key",
+		   (*port)++, POSTINSTALL_MD5 | PREINSTALL_AO,
+		   this_ip_dest, TEST_PREFIX, -1, this_ip_dest, TEST_PREFIX, 0,
+		   100, 100, 1, FAULT_POSTINSTALL);
+	try_to_add("TCP-MD5 established: add TCP-AO key",
+		   (*port)++, PREINSTALL_MD5 | POSTINSTALL_AO,
+		   this_ip_dest, TEST_PREFIX, -1, this_ip_dest, TEST_PREFIX, 0,
+		   100, 100, 1, FAULT_POSTINSTALL);
+	try_to_add("non-signed established: add TCP-AO key",
+		   (*port)++, POSTINSTALL_AO,
+		   this_ip_dest, TEST_PREFIX, -1, this_ip_dest, TEST_PREFIX, 0,
+		   100, 100, 0, FAULT_POSTINSTALL);
+
+	try_to_add("TCP-AO key intersects with existing TCP-MD5 key",
+		   (*port)++, PREINSTALL_MD5_FIRST | PREINSTALL_AO,
+		   this_ip_addr, TEST_PREFIX, -1, this_ip_addr, TEST_PREFIX, -1,
+		   100, 100, 1, FAULT_PREINSTALL_AO);
+	try_to_add("TCP-MD5 key intersects with existing TCP-AO key",
+		   (*port)++, PREINSTALL_MD5 | PREINSTALL_AO,
+		   this_ip_addr, TEST_PREFIX, -1, this_ip_addr, TEST_PREFIX, -1,
+		   100, 100, 1, FAULT_PREINSTALL_MD5);
+
+	try_to_preadd("TCP-MD5 key + TCP-AO required",
+		      (*port)++, PREINSTALL_MD5_FIRST | PREINSTALL_AO,
+		      this_ip_addr, TEST_PREFIX, -1,
+		      this_ip_addr, TEST_PREFIX, -1, true,
+		      100, 100, 1, 0, FAULT_PREINSTALL_AO);
+	try_to_preadd("TCP-AO required on socket + TCP-MD5 key",
+		      (*port)++, PREINSTALL_MD5 | PREINSTALL_AO,
+		      this_ip_addr, TEST_PREFIX, -1,
+		      this_ip_addr, TEST_PREFIX, -1, true,
+		      100, 100, 1, 0, FAULT_PREINSTALL_MD5);
+}
+
+static void client_vrf_tests(unsigned int *port)
+{
+	setup_vrfs();
+
+	/* The following restrictions for setsockopt()s are expected:
+	 *
+	 * |--------------|-----------------|-------------|-------------|
+	 * |              | MD5 key without |   MD5 key   |   MD5 key   |
+	 * |              |     l3index     |  l3index=0  |  l3index=N  |
+	 * |--------------|-----------------|-------------|-------------|
+	 * |  TCP-AO key  |                 |             |             |
+	 * |  without     |     reject      |    reject   |    reject   |
+	 * |  l3index     |                 |             |             |
+	 * |--------------|-----------------|-------------|-------------|
+	 * |  TCP-AO key  |                 |             |             |
+	 * |  l3index=0   |     reject      |    reject   |    allow    |
+	 * |--------------|-----------------|-------------|-------------|
+	 * |  TCP-AO key  |                 |             |             |
+	 * |  l3index=N   |     reject      |    allow    |    reject   |
+	 * |--------------|-----------------|-------------|-------------|
+	 */
+	try_to_preadd("VRF: TCP-AO key (no l3index) + TCP-MD5 key (no l3index)",
+		      (*port)++, PREINSTALL_MD5 | PREINSTALL_AO,
+		      this_ip_addr, TEST_PREFIX, -1,
+		      this_ip_addr, TEST_PREFIX, -1, 0, 100, 100,
+		      1, 1, FAULT_PREINSTALL_MD5);
+	try_to_preadd("VRF: TCP-MD5 key (no l3index) + TCP-AO key (no l3index)",
+		      (*port)++, PREINSTALL_MD5_FIRST | PREINSTALL_AO,
+		      this_ip_addr, TEST_PREFIX, -1,
+		      this_ip_addr, TEST_PREFIX, -1, 0, 100, 100,
+		      1, 1, FAULT_PREINSTALL_AO);
+	try_to_preadd("VRF: TCP-AO key (no l3index) + TCP-MD5 key (l3index=0)",
+		      (*port)++, PREINSTALL_MD5 | PREINSTALL_AO,
+		      this_ip_addr, TEST_PREFIX, 0,
+		      this_ip_addr, TEST_PREFIX, -1, 0, 100, 100,
+		      1, 1, FAULT_PREINSTALL_MD5);
+	try_to_preadd("VRF: TCP-MD5 key (l3index=0) + TCP-AO key (no l3index)",
+		      (*port)++, PREINSTALL_MD5_FIRST | PREINSTALL_AO,
+		      this_ip_addr, TEST_PREFIX, 0,
+		      this_ip_addr, TEST_PREFIX, -1, 0, 100, 100,
+		      1, 1, FAULT_PREINSTALL_AO);
+	try_to_preadd("VRF: TCP-AO key (no l3index) + TCP-MD5 key (l3index=N)",
+		      (*port)++, PREINSTALL_MD5 | PREINSTALL_AO,
+		      this_ip_addr, TEST_PREFIX, test_vrf_ifindex,
+		      this_ip_addr, TEST_PREFIX, -1, 0, 100, 100,
+		      1, 1, FAULT_PREINSTALL_MD5);
+	try_to_preadd("VRF: TCP-MD5 key (l3index=N) + TCP-AO key (no l3index)",
+		      (*port)++, PREINSTALL_MD5_FIRST | PREINSTALL_AO,
+		      this_ip_addr, TEST_PREFIX, test_vrf_ifindex,
+		      this_ip_addr, TEST_PREFIX, -1, 0, 100, 100,
+		      1, 1, FAULT_PREINSTALL_AO);
+
+	try_to_preadd("VRF: TCP-AO key (l3index=0) + TCP-MD5 key (no l3index)",
+		      (*port)++, PREINSTALL_MD5 | PREINSTALL_AO,
+		      this_ip_addr, TEST_PREFIX, -1,
+		      this_ip_addr, TEST_PREFIX, 0, 0, 100, 100,
+		      1, 1, FAULT_PREINSTALL_MD5);
+	try_to_preadd("VRF: TCP-MD5 key (no l3index) + TCP-AO key (l3index=0)",
+		      (*port)++, PREINSTALL_MD5_FIRST | PREINSTALL_AO,
+		      this_ip_addr, TEST_PREFIX, -1,
+		      this_ip_addr, TEST_PREFIX, 0, 0, 100, 100,
+		      1, 1, FAULT_PREINSTALL_AO);
+	try_to_preadd("VRF: TCP-AO key (l3index=0) + TCP-MD5 key (l3index=0)",
+		      (*port)++, PREINSTALL_MD5 | PREINSTALL_AO,
+		      this_ip_addr, TEST_PREFIX, 0,
+		      this_ip_addr, TEST_PREFIX, 0, 0, 100, 100,
+		      1, 1, FAULT_PREINSTALL_MD5);
+	try_to_preadd("VRF: TCP-MD5 key (l3index=0) + TCP-AO key (l3index=0)",
+		      (*port)++, PREINSTALL_MD5_FIRST | PREINSTALL_AO,
+		      this_ip_addr, TEST_PREFIX, 0,
+		      this_ip_addr, TEST_PREFIX, 0, 0, 100, 100,
+		      1, 1, FAULT_PREINSTALL_AO);
+	try_to_preadd("VRF: TCP-AO key (l3index=0) + TCP-MD5 key (l3index=N)",
+		      (*port)++, PREINSTALL_MD5 | PREINSTALL_AO,
+		      this_ip_addr, TEST_PREFIX, test_vrf_ifindex,
+		      this_ip_addr, TEST_PREFIX, 0, 0, 100, 100,
+		      1, 1, 0);
+	try_to_preadd("VRF: TCP-MD5 key (l3index=N) + TCP-AO key (l3index=0)",
+		      (*port)++, PREINSTALL_MD5_FIRST | PREINSTALL_AO,
+		      this_ip_addr, TEST_PREFIX, test_vrf_ifindex,
+		      this_ip_addr, TEST_PREFIX, 0, 0, 100, 100,
+		      1, 1, 0);
+
+	try_to_preadd("VRF: TCP-AO key (l3index=N) + TCP-MD5 key (no l3index)",
+		      (*port)++, PREINSTALL_MD5 | PREINSTALL_AO,
+		      this_ip_addr, TEST_PREFIX, test_vrf_ifindex,
+		      this_ip_addr, TEST_PREFIX, -1, 0, 100, 100,
+		      1, 1, FAULT_PREINSTALL_MD5);
+	try_to_preadd("VRF: TCP-MD5 key (no l3index) + TCP-AO key (l3index=N)",
+		      (*port)++, PREINSTALL_MD5_FIRST | PREINSTALL_AO,
+		      this_ip_addr, TEST_PREFIX, -1,
+		      this_ip_addr, TEST_PREFIX, test_vrf_ifindex, 0, 100, 100,
+		      1, 1, FAULT_PREINSTALL_AO);
+	try_to_preadd("VRF: TCP-AO key (l3index=N) + TCP-MD5 key (l3index=0)",
+		      (*port)++, PREINSTALL_MD5 | PREINSTALL_AO,
+		      this_ip_addr, TEST_PREFIX, 0,
+		      this_ip_addr, TEST_PREFIX, test_vrf_ifindex, 0, 100, 100,
+		      1, 1, 0);
+	try_to_preadd("VRF: TCP-MD5 key (l3index=0) + TCP-AO key (l3index=N)",
+		      (*port)++, PREINSTALL_MD5_FIRST | PREINSTALL_AO,
+		      this_ip_addr, TEST_PREFIX, 0,
+		      this_ip_addr, TEST_PREFIX, test_vrf_ifindex, 0, 100, 100,
+		      1, 1, 0);
+	try_to_preadd("VRF: TCP-AO key (l3index=N) + TCP-MD5 key (l3index=N)",
+		      (*port)++, PREINSTALL_MD5 | PREINSTALL_AO,
+		      this_ip_addr, TEST_PREFIX, test_vrf_ifindex,
+		      this_ip_addr, TEST_PREFIX, test_vrf_ifindex, 0, 100, 100,
+		      1, 1, FAULT_PREINSTALL_MD5);
+	try_to_preadd("VRF: TCP-MD5 key (l3index=N) + TCP-AO key (l3index=N)",
+		      (*port)++, PREINSTALL_MD5_FIRST | PREINSTALL_AO,
+		      this_ip_addr, TEST_PREFIX, test_vrf_ifindex,
+		      this_ip_addr, TEST_PREFIX, test_vrf_ifindex, 0, 100, 100,
+		      1, 1, FAULT_PREINSTALL_AO);
+}
+
+static void *client_fn(void *arg)
+{
+	unsigned int port = test_server_port;
+	union tcp_addr addr_any = {};
+
+	client_add_ips();
+
+	try_connect("AO server (INADDR_ANY): AO client", port++, NULL, 0,
+		    &addr_any, 0, 100, 100, 0, 0, 0, &this_ip_addr);
+	try_connect("AO server (INADDR_ANY): MD5 client", port++, &addr_any, 0,
+		    NULL, 0, 100, 100, 0, FAULT_TIMEOUT, 1, &this_ip_addr);
+	try_connect("AO server (INADDR_ANY): unsigned client", port++, NULL, 0,
+		    NULL, 0, 100, 100, 0, FAULT_TIMEOUT, 0, &this_ip_addr);
+	try_connect("AO server (AO_REQUIRED): AO client", port++, NULL, 0,
+		    &addr_any, 0, 100, 100, 0, 0, 0, &this_ip_addr);
+	try_connect("AO server (AO_REQUIRED): unsigned client", port++, NULL, 0,
+		    NULL, 0, 100, 100, 0, FAULT_TIMEOUT, 0, &client2);
+
+	try_connect("MD5 server (INADDR_ANY): AO client", port++, NULL, 0,
+		   &addr_any, 0, 100, 100, 0, FAULT_TIMEOUT, 1, &this_ip_addr);
+	try_connect("MD5 server (INADDR_ANY): MD5 client", port++, &addr_any, 0,
+		   NULL, 0, 100, 100, 0, 0, 1, &this_ip_addr);
+	try_connect("MD5 server (INADDR_ANY): no sign client", port++, NULL, 0,
+		   NULL, 0, 100, 100, 0, FAULT_TIMEOUT, 1, &this_ip_addr);
+
+	try_connect("no sign server: AO client", port++, NULL, 0,
+		   &addr_any, 0, 100, 100, 0, FAULT_TIMEOUT, 0, &this_ip_addr);
+	try_connect("no sign server: MD5 client", port++, &addr_any, 0,
+		   NULL, 0, 100, 100, 0, FAULT_TIMEOUT, 1, &this_ip_addr);
+	try_connect("no sign server: no sign client", port++, NULL, 0,
+		   NULL, 0, 100, 100, 0, 0, 0, &this_ip_addr);
+
+	try_connect("AO+MD5 server: AO client (matching)", port++, NULL, 0,
+		   &addr_any, 0, 100, 100, 0, 0, 1, &client2);
+	try_connect("AO+MD5 server: AO client (misconfig, matching MD5)",
+		   port++, NULL, 0, &addr_any, 0, 100, 100, 0,
+		   FAULT_TIMEOUT, 1, &this_ip_addr);
+	try_connect("AO+MD5 server: AO client (misconfig, non-matching)",
+		   port++, NULL, 0, &addr_any, 0, 100, 100, 0,
+		   FAULT_TIMEOUT, 1, &client3);
+	try_connect("AO+MD5 server: MD5 client (matching)", port++, &addr_any, 0,
+		   NULL, 0, 100, 100, 0, 0, 1, &this_ip_addr);
+	try_connect("AO+MD5 server: MD5 client (misconfig, matching AO)",
+		   port++, &addr_any, 0, NULL, 0, 100, 100, 0, FAULT_TIMEOUT,
+		   1, &client2);
+	try_connect("AO+MD5 server: MD5 client (misconfig, non-matching)",
+		   port++, &addr_any, 0, NULL, 0, 100, 100, 0, FAULT_TIMEOUT,
+		   1, &client3);
+	try_connect("AO+MD5 server: no sign client (unmatched)",
+		   port++, NULL, 0, NULL, 0, 100, 100, 0, 0, 1, &client3);
+	try_connect("AO+MD5 server: no sign client (misconfig, matching AO)",
+		   port++, NULL, 0, NULL, 0, 100, 100, 0, FAULT_TIMEOUT,
+		   1, &client2);
+	try_connect("AO+MD5 server: no sign client (misconfig, matching MD5)",
+		   port++, NULL, 0, NULL, 0, 100, 100, 0, FAULT_TIMEOUT,
+		   1, &this_ip_addr);
+
+	try_connect("AO+MD5 server: client with both [TCP-MD5] and TCP-AO keys",
+		   port++, &this_ip_addr, TEST_PREFIX,
+		   &client2, TEST_PREFIX, 100, 100, 0, FAULT_KEYREJECT,
+		   1, &this_ip_addr);
+	try_connect("AO+MD5 server: client with both TCP-MD5 and [TCP-AO] keys",
+		   port++, &this_ip_addr, TEST_PREFIX,
+		   &client2, TEST_PREFIX, 100, 100, 0, FAULT_KEYREJECT,
+		   1, &client2);
+
+	client_add_fail_tests(&port);
+	client_vrf_tests(&port);
+
+	return NULL;
+}
+
+int main(int argc, char *argv[])
+{
+	test_init(72, server_fn, client_fn);
+	return 0;
+}
diff --git a/tools/testing/selftests/net/test_bridge_backup_port.sh b/tools/testing/selftests/net/test_bridge_backup_port.sh
index 112cfd8a10ad..70a7d87ba2d2 100755
--- a/tools/testing/selftests/net/test_bridge_backup_port.sh
+++ b/tools/testing/selftests/net/test_bridge_backup_port.sh
@@ -35,9 +35,8 @@
 # | sw1                                | | sw2                                |
 # +------------------------------------+ +------------------------------------+
 
+source lib.sh
 ret=0
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
 
 # All tests in this script. Can be overridden with -t option.
 TESTS="
@@ -132,9 +131,6 @@ setup_topo_ns()
 {
 	local ns=$1; shift
 
-	ip netns add $ns
-	ip -n $ns link set dev lo up
-
 	ip netns exec $ns sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1
 	ip netns exec $ns sysctl -qw net.ipv6.conf.default.ignore_routes_with_linkdown=1
 	ip netns exec $ns sysctl -qw net.ipv6.conf.all.accept_dad=0
@@ -145,13 +141,14 @@ setup_topo()
 {
 	local ns
 
-	for ns in sw1 sw2; do
+	setup_ns sw1 sw2
+	for ns in $sw1 $sw2; do
 		setup_topo_ns $ns
 	done
 
 	ip link add name veth0 type veth peer name veth1
-	ip link set dev veth0 netns sw1 name veth0
-	ip link set dev veth1 netns sw2 name veth0
+	ip link set dev veth0 netns $sw1 name veth0
+	ip link set dev veth1 netns $sw2 name veth0
 }
 
 setup_sw_common()
@@ -190,7 +187,7 @@ setup_sw_common()
 
 setup_sw1()
 {
-	local ns=sw1
+	local ns=$sw1
 	local local_addr=192.0.2.33
 	local remote_addr=192.0.2.34
 	local veth_addr=192.0.2.49
@@ -203,7 +200,7 @@ setup_sw1()
 
 setup_sw2()
 {
-	local ns=sw2
+	local ns=$sw2
 	local local_addr=192.0.2.34
 	local remote_addr=192.0.2.33
 	local veth_addr=192.0.2.50
@@ -229,11 +226,7 @@ setup()
 
 cleanup()
 {
-	local ns
-
-	for ns in h1 h2 sw1 sw2; do
-		ip netns del $ns &> /dev/null
-	done
+	cleanup_ns $sw1 $sw2
 }
 
 ################################################################################
@@ -248,85 +241,85 @@ backup_port()
 	echo "Backup port"
 	echo "-----------"
 
-	run_cmd "tc -n sw1 qdisc replace dev swp1 clsact"
-	run_cmd "tc -n sw1 filter replace dev swp1 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass"
+	run_cmd "tc -n $sw1 qdisc replace dev swp1 clsact"
+	run_cmd "tc -n $sw1 filter replace dev swp1 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass"
 
-	run_cmd "tc -n sw1 qdisc replace dev vx0 clsact"
-	run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass"
+	run_cmd "tc -n $sw1 qdisc replace dev vx0 clsact"
+	run_cmd "tc -n $sw1 filter replace dev vx0 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass"
 
-	run_cmd "bridge -n sw1 fdb replace $dmac dev swp1 master static vlan 10"
+	run_cmd "bridge -n $sw1 fdb replace $dmac dev swp1 master static vlan 10"
 
 	# Initial state - check that packets are forwarded out of swp1 when it
 	# has a carrier and not forwarded out of any port when it does not have
 	# a carrier.
-	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
-	tc_check_packets sw1 "dev swp1 egress" 101 1
+	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets $sw1 "dev swp1 egress" 101 1
 	log_test $? 0 "Forwarding out of swp1"
-	tc_check_packets sw1 "dev vx0 egress" 101 0
+	tc_check_packets $sw1 "dev vx0 egress" 101 0
 	log_test $? 0 "No forwarding out of vx0"
 
-	run_cmd "ip -n sw1 link set dev swp1 carrier off"
+	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
 	log_test $? 0 "swp1 carrier off"
 
-	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
-	tc_check_packets sw1 "dev swp1 egress" 101 1
+	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets $sw1 "dev swp1 egress" 101 1
 	log_test $? 0 "No forwarding out of swp1"
-	tc_check_packets sw1 "dev vx0 egress" 101 0
+	tc_check_packets $sw1 "dev vx0 egress" 101 0
 	log_test $? 0 "No forwarding out of vx0"
 
-	run_cmd "ip -n sw1 link set dev swp1 carrier on"
+	run_cmd "ip -n $sw1 link set dev swp1 carrier on"
 	log_test $? 0 "swp1 carrier on"
 
 	# Configure vx0 as the backup port of swp1 and check that packets are
 	# forwarded out of swp1 when it has a carrier and out of vx0 when swp1
 	# does not have a carrier.
-	run_cmd "bridge -n sw1 link set dev swp1 backup_port vx0"
-	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_port vx0\""
+	run_cmd "bridge -n $sw1 link set dev swp1 backup_port vx0"
+	run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_port vx0\""
 	log_test $? 0 "vx0 configured as backup port of swp1"
 
-	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
-	tc_check_packets sw1 "dev swp1 egress" 101 2
+	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets $sw1 "dev swp1 egress" 101 2
 	log_test $? 0 "Forwarding out of swp1"
-	tc_check_packets sw1 "dev vx0 egress" 101 0
+	tc_check_packets $sw1 "dev vx0 egress" 101 0
 	log_test $? 0 "No forwarding out of vx0"
 
-	run_cmd "ip -n sw1 link set dev swp1 carrier off"
+	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
 	log_test $? 0 "swp1 carrier off"
 
-	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
-	tc_check_packets sw1 "dev swp1 egress" 101 2
+	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets $sw1 "dev swp1 egress" 101 2
 	log_test $? 0 "No forwarding out of swp1"
-	tc_check_packets sw1 "dev vx0 egress" 101 1
+	tc_check_packets $sw1 "dev vx0 egress" 101 1
 	log_test $? 0 "Forwarding out of vx0"
 
-	run_cmd "ip -n sw1 link set dev swp1 carrier on"
+	run_cmd "ip -n $sw1 link set dev swp1 carrier on"
 	log_test $? 0 "swp1 carrier on"
 
-	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
-	tc_check_packets sw1 "dev swp1 egress" 101 3
+	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets $sw1 "dev swp1 egress" 101 3
 	log_test $? 0 "Forwarding out of swp1"
-	tc_check_packets sw1 "dev vx0 egress" 101 1
+	tc_check_packets $sw1 "dev vx0 egress" 101 1
 	log_test $? 0 "No forwarding out of vx0"
 
 	# Remove vx0 as the backup port of swp1 and check that packets are no
 	# longer forwarded out of vx0 when swp1 does not have a carrier.
-	run_cmd "bridge -n sw1 link set dev swp1 nobackup_port"
-	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_port vx0\""
+	run_cmd "bridge -n $sw1 link set dev swp1 nobackup_port"
+	run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_port vx0\""
 	log_test $? 1 "vx0 not configured as backup port of swp1"
 
-	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
-	tc_check_packets sw1 "dev swp1 egress" 101 4
+	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets $sw1 "dev swp1 egress" 101 4
 	log_test $? 0 "Forwarding out of swp1"
-	tc_check_packets sw1 "dev vx0 egress" 101 1
+	tc_check_packets $sw1 "dev vx0 egress" 101 1
 	log_test $? 0 "No forwarding out of vx0"
 
-	run_cmd "ip -n sw1 link set dev swp1 carrier off"
+	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
 	log_test $? 0 "swp1 carrier off"
 
-	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
-	tc_check_packets sw1 "dev swp1 egress" 101 4
+	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets $sw1 "dev swp1 egress" 101 4
 	log_test $? 0 "No forwarding out of swp1"
-	tc_check_packets sw1 "dev vx0 egress" 101 1
+	tc_check_packets $sw1 "dev vx0 egress" 101 1
 	log_test $? 0 "No forwarding out of vx0"
 }
 
@@ -339,125 +332,125 @@ backup_nhid()
 	echo "Backup nexthop ID"
 	echo "-----------------"
 
-	run_cmd "tc -n sw1 qdisc replace dev swp1 clsact"
-	run_cmd "tc -n sw1 filter replace dev swp1 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass"
+	run_cmd "tc -n $sw1 qdisc replace dev swp1 clsact"
+	run_cmd "tc -n $sw1 filter replace dev swp1 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass"
 
-	run_cmd "tc -n sw1 qdisc replace dev vx0 clsact"
-	run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass"
+	run_cmd "tc -n $sw1 qdisc replace dev vx0 clsact"
+	run_cmd "tc -n $sw1 filter replace dev vx0 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass"
 
-	run_cmd "ip -n sw1 nexthop replace id 1 via 192.0.2.34 fdb"
-	run_cmd "ip -n sw1 nexthop replace id 2 via 192.0.2.34 fdb"
-	run_cmd "ip -n sw1 nexthop replace id 10 group 1/2 fdb"
+	run_cmd "ip -n $sw1 nexthop replace id 1 via 192.0.2.34 fdb"
+	run_cmd "ip -n $sw1 nexthop replace id 2 via 192.0.2.34 fdb"
+	run_cmd "ip -n $sw1 nexthop replace id 10 group 1/2 fdb"
 
-	run_cmd "bridge -n sw1 fdb replace $dmac dev swp1 master static vlan 10"
-	run_cmd "bridge -n sw1 fdb replace $dmac dev vx0 self static dst 192.0.2.36 src_vni 10010"
+	run_cmd "bridge -n $sw1 fdb replace $dmac dev swp1 master static vlan 10"
+	run_cmd "bridge -n $sw1 fdb replace $dmac dev vx0 self static dst 192.0.2.36 src_vni 10010"
 
-	run_cmd "ip -n sw2 address replace 192.0.2.36/32 dev lo"
+	run_cmd "ip -n $sw2 address replace 192.0.2.36/32 dev lo"
 
 	# The first filter matches on packets forwarded using the backup
 	# nexthop ID and the second filter matches on packets forwarded using a
 	# regular VXLAN FDB entry.
-	run_cmd "tc -n sw2 qdisc replace dev vx0 clsact"
-	run_cmd "tc -n sw2 filter replace dev vx0 ingress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac enc_key_id 10010 enc_dst_ip 192.0.2.34 action pass"
-	run_cmd "tc -n sw2 filter replace dev vx0 ingress pref 1 handle 102 proto ip flower src_mac $smac dst_mac $dmac enc_key_id 10010 enc_dst_ip 192.0.2.36 action pass"
+	run_cmd "tc -n $sw2 qdisc replace dev vx0 clsact"
+	run_cmd "tc -n $sw2 filter replace dev vx0 ingress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac enc_key_id 10010 enc_dst_ip 192.0.2.34 action pass"
+	run_cmd "tc -n $sw2 filter replace dev vx0 ingress pref 1 handle 102 proto ip flower src_mac $smac dst_mac $dmac enc_key_id 10010 enc_dst_ip 192.0.2.36 action pass"
 
 	# Configure vx0 as the backup port of swp1 and check that packets are
 	# forwarded out of swp1 when it has a carrier and out of vx0 when swp1
 	# does not have a carrier. When packets are forwarded out of vx0, check
 	# that they are forwarded by the VXLAN FDB entry.
-	run_cmd "bridge -n sw1 link set dev swp1 backup_port vx0"
-	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_port vx0\""
+	run_cmd "bridge -n $sw1 link set dev swp1 backup_port vx0"
+	run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_port vx0\""
 	log_test $? 0 "vx0 configured as backup port of swp1"
 
-	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
-	tc_check_packets sw1 "dev swp1 egress" 101 1
+	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets $sw1 "dev swp1 egress" 101 1
 	log_test $? 0 "Forwarding out of swp1"
-	tc_check_packets sw1 "dev vx0 egress" 101 0
+	tc_check_packets $sw1 "dev vx0 egress" 101 0
 	log_test $? 0 "No forwarding out of vx0"
 
-	run_cmd "ip -n sw1 link set dev swp1 carrier off"
+	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
 	log_test $? 0 "swp1 carrier off"
 
-	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
-	tc_check_packets sw1 "dev swp1 egress" 101 1
+	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets $sw1 "dev swp1 egress" 101 1
 	log_test $? 0 "No forwarding out of swp1"
-	tc_check_packets sw1 "dev vx0 egress" 101 1
+	tc_check_packets $sw1 "dev vx0 egress" 101 1
 	log_test $? 0 "Forwarding out of vx0"
-	tc_check_packets sw2 "dev vx0 ingress" 101 0
+	tc_check_packets $sw2 "dev vx0 ingress" 101 0
 	log_test $? 0 "No forwarding using backup nexthop ID"
-	tc_check_packets sw2 "dev vx0 ingress" 102 1
+	tc_check_packets $sw2 "dev vx0 ingress" 102 1
 	log_test $? 0 "Forwarding using VXLAN FDB entry"
 
-	run_cmd "ip -n sw1 link set dev swp1 carrier on"
+	run_cmd "ip -n $sw1 link set dev swp1 carrier on"
 	log_test $? 0 "swp1 carrier on"
 
 	# Configure nexthop ID 10 as the backup nexthop ID of swp1 and check
 	# that when packets are forwarded out of vx0, they are forwarded using
 	# the backup nexthop ID.
-	run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 10"
-	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 10\""
+	run_cmd "bridge -n $sw1 link set dev swp1 backup_nhid 10"
+	run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_nhid 10\""
 	log_test $? 0 "nexthop ID 10 configured as backup nexthop ID of swp1"
 
-	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
-	tc_check_packets sw1 "dev swp1 egress" 101 2
+	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets $sw1 "dev swp1 egress" 101 2
 	log_test $? 0 "Forwarding out of swp1"
-	tc_check_packets sw1 "dev vx0 egress" 101 1
+	tc_check_packets $sw1 "dev vx0 egress" 101 1
 	log_test $? 0 "No forwarding out of vx0"
 
-	run_cmd "ip -n sw1 link set dev swp1 carrier off"
+	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
 	log_test $? 0 "swp1 carrier off"
 
-	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
-	tc_check_packets sw1 "dev swp1 egress" 101 2
+	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets $sw1 "dev swp1 egress" 101 2
 	log_test $? 0 "No forwarding out of swp1"
-	tc_check_packets sw1 "dev vx0 egress" 101 2
+	tc_check_packets $sw1 "dev vx0 egress" 101 2
 	log_test $? 0 "Forwarding out of vx0"
-	tc_check_packets sw2 "dev vx0 ingress" 101 1
+	tc_check_packets $sw2 "dev vx0 ingress" 101 1
 	log_test $? 0 "Forwarding using backup nexthop ID"
-	tc_check_packets sw2 "dev vx0 ingress" 102 1
+	tc_check_packets $sw2 "dev vx0 ingress" 102 1
 	log_test $? 0 "No forwarding using VXLAN FDB entry"
 
-	run_cmd "ip -n sw1 link set dev swp1 carrier on"
+	run_cmd "ip -n $sw1 link set dev swp1 carrier on"
 	log_test $? 0 "swp1 carrier on"
 
-	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
-	tc_check_packets sw1 "dev swp1 egress" 101 3
+	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets $sw1 "dev swp1 egress" 101 3
 	log_test $? 0 "Forwarding out of swp1"
-	tc_check_packets sw1 "dev vx0 egress" 101 2
+	tc_check_packets $sw1 "dev vx0 egress" 101 2
 	log_test $? 0 "No forwarding out of vx0"
-	tc_check_packets sw2 "dev vx0 ingress" 101 1
+	tc_check_packets $sw2 "dev vx0 ingress" 101 1
 	log_test $? 0 "No forwarding using backup nexthop ID"
-	tc_check_packets sw2 "dev vx0 ingress" 102 1
+	tc_check_packets $sw2 "dev vx0 ingress" 102 1
 	log_test $? 0 "No forwarding using VXLAN FDB entry"
 
 	# Reset the backup nexthop ID to 0 and check that packets are no longer
 	# forwarded using the backup nexthop ID when swp1 does not have a
 	# carrier and are instead forwarded by the VXLAN FDB.
-	run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 0"
-	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid\""
+	run_cmd "bridge -n $sw1 link set dev swp1 backup_nhid 0"
+	run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_nhid\""
 	log_test $? 1 "No backup nexthop ID configured for swp1"
 
-	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
-	tc_check_packets sw1 "dev swp1 egress" 101 4
+	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets $sw1 "dev swp1 egress" 101 4
 	log_test $? 0 "Forwarding out of swp1"
-	tc_check_packets sw1 "dev vx0 egress" 101 2
+	tc_check_packets $sw1 "dev vx0 egress" 101 2
 	log_test $? 0 "No forwarding out of vx0"
-	tc_check_packets sw2 "dev vx0 ingress" 101 1
+	tc_check_packets $sw2 "dev vx0 ingress" 101 1
 	log_test $? 0 "No forwarding using backup nexthop ID"
-	tc_check_packets sw2 "dev vx0 ingress" 102 1
+	tc_check_packets $sw2 "dev vx0 ingress" 102 1
 	log_test $? 0 "No forwarding using VXLAN FDB entry"
 
-	run_cmd "ip -n sw1 link set dev swp1 carrier off"
+	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
 	log_test $? 0 "swp1 carrier off"
 
-	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
-	tc_check_packets sw1 "dev swp1 egress" 101 4
+	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets $sw1 "dev swp1 egress" 101 4
 	log_test $? 0 "No forwarding out of swp1"
-	tc_check_packets sw1 "dev vx0 egress" 101 3
+	tc_check_packets $sw1 "dev vx0 egress" 101 3
 	log_test $? 0 "Forwarding out of vx0"
-	tc_check_packets sw2 "dev vx0 ingress" 101 1
+	tc_check_packets $sw2 "dev vx0 ingress" 101 1
 	log_test $? 0 "No forwarding using backup nexthop ID"
-	tc_check_packets sw2 "dev vx0 ingress" 102 2
+	tc_check_packets $sw2 "dev vx0 ingress" 102 2
 	log_test $? 0 "Forwarding using VXLAN FDB entry"
 }
 
@@ -475,109 +468,109 @@ backup_nhid_invalid()
 	# is forwarded out of the VXLAN port, but dropped by the VXLAN driver
 	# and does not crash the host.
 
-	run_cmd "tc -n sw1 qdisc replace dev swp1 clsact"
-	run_cmd "tc -n sw1 filter replace dev swp1 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass"
+	run_cmd "tc -n $sw1 qdisc replace dev swp1 clsact"
+	run_cmd "tc -n $sw1 filter replace dev swp1 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass"
 
-	run_cmd "tc -n sw1 qdisc replace dev vx0 clsact"
-	run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass"
+	run_cmd "tc -n $sw1 qdisc replace dev vx0 clsact"
+	run_cmd "tc -n $sw1 filter replace dev vx0 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass"
 	# Drop all other Tx traffic to avoid changes to Tx drop counter.
-	run_cmd "tc -n sw1 filter replace dev vx0 egress pref 2 handle 102 proto all matchall action drop"
+	run_cmd "tc -n $sw1 filter replace dev vx0 egress pref 2 handle 102 proto all matchall action drop"
 
-	tx_drop=$(ip -n sw1 -s -j link show dev vx0 | jq '.[]["stats64"]["tx"]["dropped"]')
+	tx_drop=$(ip -n $sw1 -s -j link show dev vx0 | jq '.[]["stats64"]["tx"]["dropped"]')
 
-	run_cmd "ip -n sw1 nexthop replace id 1 via 192.0.2.34 fdb"
-	run_cmd "ip -n sw1 nexthop replace id 2 via 192.0.2.34 fdb"
-	run_cmd "ip -n sw1 nexthop replace id 10 group 1/2 fdb"
+	run_cmd "ip -n $sw1 nexthop replace id 1 via 192.0.2.34 fdb"
+	run_cmd "ip -n $sw1 nexthop replace id 2 via 192.0.2.34 fdb"
+	run_cmd "ip -n $sw1 nexthop replace id 10 group 1/2 fdb"
 
-	run_cmd "bridge -n sw1 fdb replace $dmac dev swp1 master static vlan 10"
+	run_cmd "bridge -n $sw1 fdb replace $dmac dev swp1 master static vlan 10"
 
-	run_cmd "tc -n sw2 qdisc replace dev vx0 clsact"
-	run_cmd "tc -n sw2 filter replace dev vx0 ingress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac enc_key_id 10010 enc_dst_ip 192.0.2.34 action pass"
+	run_cmd "tc -n $sw2 qdisc replace dev vx0 clsact"
+	run_cmd "tc -n $sw2 filter replace dev vx0 ingress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac enc_key_id 10010 enc_dst_ip 192.0.2.34 action pass"
 
 	# First, check that redirection works.
-	run_cmd "bridge -n sw1 link set dev swp1 backup_port vx0"
-	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_port vx0\""
+	run_cmd "bridge -n $sw1 link set dev swp1 backup_port vx0"
+	run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_port vx0\""
 	log_test $? 0 "vx0 configured as backup port of swp1"
 
-	run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 10"
-	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 10\""
+	run_cmd "bridge -n $sw1 link set dev swp1 backup_nhid 10"
+	run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_nhid 10\""
 	log_test $? 0 "Valid nexthop as backup nexthop"
 
-	run_cmd "ip -n sw1 link set dev swp1 carrier off"
+	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
 	log_test $? 0 "swp1 carrier off"
 
-	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
-	tc_check_packets sw1 "dev swp1 egress" 101 0
+	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets $sw1 "dev swp1 egress" 101 0
 	log_test $? 0 "No forwarding out of swp1"
-	tc_check_packets sw1 "dev vx0 egress" 101 1
+	tc_check_packets $sw1 "dev vx0 egress" 101 1
 	log_test $? 0 "Forwarding out of vx0"
-	tc_check_packets sw2 "dev vx0 ingress" 101 1
+	tc_check_packets $sw2 "dev vx0 ingress" 101 1
 	log_test $? 0 "Forwarding using backup nexthop ID"
-	run_cmd "ip -n sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $tx_drop'"
+	run_cmd "ip -n $sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $tx_drop'"
 	log_test $? 0 "No Tx drop increase"
 
 	# Use a non-existent nexthop ID.
-	run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 20"
-	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 20\""
+	run_cmd "bridge -n $sw1 link set dev swp1 backup_nhid 20"
+	run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_nhid 20\""
 	log_test $? 0 "Non-existent nexthop as backup nexthop"
 
-	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
-	tc_check_packets sw1 "dev swp1 egress" 101 0
+	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets $sw1 "dev swp1 egress" 101 0
 	log_test $? 0 "No forwarding out of swp1"
-	tc_check_packets sw1 "dev vx0 egress" 101 2
+	tc_check_packets $sw1 "dev vx0 egress" 101 2
 	log_test $? 0 "Forwarding out of vx0"
-	tc_check_packets sw2 "dev vx0 ingress" 101 1
+	tc_check_packets $sw2 "dev vx0 ingress" 101 1
 	log_test $? 0 "No forwarding using backup nexthop ID"
-	run_cmd "ip -n sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 1))'"
+	run_cmd "ip -n $sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 1))'"
 	log_test $? 0 "Tx drop increased"
 
 	# Use a blckhole nexthop.
-	run_cmd "ip -n sw1 nexthop replace id 30 blackhole"
-	run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 30"
-	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 30\""
+	run_cmd "ip -n $sw1 nexthop replace id 30 blackhole"
+	run_cmd "bridge -n $sw1 link set dev swp1 backup_nhid 30"
+	run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_nhid 30\""
 	log_test $? 0 "Blackhole nexthop as backup nexthop"
 
-	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
-	tc_check_packets sw1 "dev swp1 egress" 101 0
+	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets $sw1 "dev swp1 egress" 101 0
 	log_test $? 0 "No forwarding out of swp1"
-	tc_check_packets sw1 "dev vx0 egress" 101 3
+	tc_check_packets $sw1 "dev vx0 egress" 101 3
 	log_test $? 0 "Forwarding out of vx0"
-	tc_check_packets sw2 "dev vx0 ingress" 101 1
+	tc_check_packets $sw2 "dev vx0 ingress" 101 1
 	log_test $? 0 "No forwarding using backup nexthop ID"
-	run_cmd "ip -n sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 2))'"
+	run_cmd "ip -n $sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 2))'"
 	log_test $? 0 "Tx drop increased"
 
 	# Non-group FDB nexthop.
-	run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 1"
-	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 1\""
+	run_cmd "bridge -n $sw1 link set dev swp1 backup_nhid 1"
+	run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_nhid 1\""
 	log_test $? 0 "Non-group FDB nexthop as backup nexthop"
 
-	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
-	tc_check_packets sw1 "dev swp1 egress" 101 0
+	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets $sw1 "dev swp1 egress" 101 0
 	log_test $? 0 "No forwarding out of swp1"
-	tc_check_packets sw1 "dev vx0 egress" 101 4
+	tc_check_packets $sw1 "dev vx0 egress" 101 4
 	log_test $? 0 "Forwarding out of vx0"
-	tc_check_packets sw2 "dev vx0 ingress" 101 1
+	tc_check_packets $sw2 "dev vx0 ingress" 101 1
 	log_test $? 0 "No forwarding using backup nexthop ID"
-	run_cmd "ip -n sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 3))'"
+	run_cmd "ip -n $sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 3))'"
 	log_test $? 0 "Tx drop increased"
 
 	# IPv6 address family nexthop.
-	run_cmd "ip -n sw1 nexthop replace id 100 via 2001:db8:100::1 fdb"
-	run_cmd "ip -n sw1 nexthop replace id 200 via 2001:db8:100::1 fdb"
-	run_cmd "ip -n sw1 nexthop replace id 300 group 100/200 fdb"
-	run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 300"
-	run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 300\""
+	run_cmd "ip -n $sw1 nexthop replace id 100 via 2001:db8:100::1 fdb"
+	run_cmd "ip -n $sw1 nexthop replace id 200 via 2001:db8:100::1 fdb"
+	run_cmd "ip -n $sw1 nexthop replace id 300 group 100/200 fdb"
+	run_cmd "bridge -n $sw1 link set dev swp1 backup_nhid 300"
+	run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_nhid 300\""
 	log_test $? 0 "IPv6 address family nexthop as backup nexthop"
 
-	run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
-	tc_check_packets sw1 "dev swp1 egress" 101 0
+	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
+	tc_check_packets $sw1 "dev swp1 egress" 101 0
 	log_test $? 0 "No forwarding out of swp1"
-	tc_check_packets sw1 "dev vx0 egress" 101 5
+	tc_check_packets $sw1 "dev vx0 egress" 101 5
 	log_test $? 0 "Forwarding out of vx0"
-	tc_check_packets sw2 "dev vx0 ingress" 101 1
+	tc_check_packets $sw2 "dev vx0 ingress" 101 1
 	log_test $? 0 "No forwarding using backup nexthop ID"
-	run_cmd "ip -n sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 4))'"
+	run_cmd "ip -n $sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 4))'"
 	log_test $? 0 "Tx drop increased"
 }
 
@@ -591,44 +584,44 @@ backup_nhid_ping()
 	echo "------------------------"
 
 	# Test bidirectional traffic when traffic is redirected in both VTEPs.
-	sw1_mac=$(ip -n sw1 -j -p link show br0.10 | jq -r '.[]["address"]')
-	sw2_mac=$(ip -n sw2 -j -p link show br0.10 | jq -r '.[]["address"]')
+	sw1_mac=$(ip -n $sw1 -j -p link show br0.10 | jq -r '.[]["address"]')
+	sw2_mac=$(ip -n $sw2 -j -p link show br0.10 | jq -r '.[]["address"]')
 
-	run_cmd "bridge -n sw1 fdb replace $sw2_mac dev swp1 master static vlan 10"
-	run_cmd "bridge -n sw2 fdb replace $sw1_mac dev swp1 master static vlan 10"
+	run_cmd "bridge -n $sw1 fdb replace $sw2_mac dev swp1 master static vlan 10"
+	run_cmd "bridge -n $sw2 fdb replace $sw1_mac dev swp1 master static vlan 10"
 
-	run_cmd "ip -n sw1 neigh replace 192.0.2.66 lladdr $sw2_mac nud perm dev br0.10"
-	run_cmd "ip -n sw2 neigh replace 192.0.2.65 lladdr $sw1_mac nud perm dev br0.10"
+	run_cmd "ip -n $sw1 neigh replace 192.0.2.66 lladdr $sw2_mac nud perm dev br0.10"
+	run_cmd "ip -n $sw2 neigh replace 192.0.2.65 lladdr $sw1_mac nud perm dev br0.10"
 
-	run_cmd "ip -n sw1 nexthop replace id 1 via 192.0.2.34 fdb"
-	run_cmd "ip -n sw2 nexthop replace id 1 via 192.0.2.33 fdb"
-	run_cmd "ip -n sw1 nexthop replace id 10 group 1 fdb"
-	run_cmd "ip -n sw2 nexthop replace id 10 group 1 fdb"
+	run_cmd "ip -n $sw1 nexthop replace id 1 via 192.0.2.34 fdb"
+	run_cmd "ip -n $sw2 nexthop replace id 1 via 192.0.2.33 fdb"
+	run_cmd "ip -n $sw1 nexthop replace id 10 group 1 fdb"
+	run_cmd "ip -n $sw2 nexthop replace id 10 group 1 fdb"
 
-	run_cmd "bridge -n sw1 link set dev swp1 backup_port vx0"
-	run_cmd "bridge -n sw2 link set dev swp1 backup_port vx0"
-	run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 10"
-	run_cmd "bridge -n sw2 link set dev swp1 backup_nhid 10"
+	run_cmd "bridge -n $sw1 link set dev swp1 backup_port vx0"
+	run_cmd "bridge -n $sw2 link set dev swp1 backup_port vx0"
+	run_cmd "bridge -n $sw1 link set dev swp1 backup_nhid 10"
+	run_cmd "bridge -n $sw2 link set dev swp1 backup_nhid 10"
 
-	run_cmd "ip -n sw1 link set dev swp1 carrier off"
-	run_cmd "ip -n sw2 link set dev swp1 carrier off"
+	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+	run_cmd "ip -n $sw2 link set dev swp1 carrier off"
 
-	run_cmd "ip netns exec sw1 ping -i 0.1 -c 10 -w $PING_TIMEOUT 192.0.2.66"
+	run_cmd "ip netns exec $sw1 ping -i 0.1 -c 10 -w $PING_TIMEOUT 192.0.2.66"
 	log_test $? 0 "Ping with backup nexthop ID"
 
 	# Reset the backup nexthop ID to 0 and check that ping fails.
-	run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 0"
-	run_cmd "bridge -n sw2 link set dev swp1 backup_nhid 0"
+	run_cmd "bridge -n $sw1 link set dev swp1 backup_nhid 0"
+	run_cmd "bridge -n $sw2 link set dev swp1 backup_nhid 0"
 
-	run_cmd "ip netns exec sw1 ping -i 0.1 -c 10 -w $PING_TIMEOUT 192.0.2.66"
+	run_cmd "ip netns exec $sw1 ping -i 0.1 -c 10 -w $PING_TIMEOUT 192.0.2.66"
 	log_test $? 1 "Ping after disabling backup nexthop ID"
 }
 
 backup_nhid_add_del_loop()
 {
 	while true; do
-		ip -n sw1 nexthop del id 10
-		ip -n sw1 nexthop replace id 10 group 1/2 fdb
+		ip -n $sw1 nexthop del id 10
+		ip -n $sw1 nexthop replace id 10 group 1/2 fdb
 	done >/dev/null 2>&1
 }
 
@@ -648,19 +641,19 @@ backup_nhid_torture()
 	# deleting the group. The test is considered successful if nothing
 	# crashed.
 
-	run_cmd "ip -n sw1 nexthop replace id 1 via 192.0.2.34 fdb"
-	run_cmd "ip -n sw1 nexthop replace id 2 via 192.0.2.34 fdb"
-	run_cmd "ip -n sw1 nexthop replace id 10 group 1/2 fdb"
+	run_cmd "ip -n $sw1 nexthop replace id 1 via 192.0.2.34 fdb"
+	run_cmd "ip -n $sw1 nexthop replace id 2 via 192.0.2.34 fdb"
+	run_cmd "ip -n $sw1 nexthop replace id 10 group 1/2 fdb"
 
-	run_cmd "bridge -n sw1 fdb replace $dmac dev swp1 master static vlan 10"
+	run_cmd "bridge -n $sw1 fdb replace $dmac dev swp1 master static vlan 10"
 
-	run_cmd "bridge -n sw1 link set dev swp1 backup_port vx0"
-	run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 10"
-	run_cmd "ip -n sw1 link set dev swp1 carrier off"
+	run_cmd "bridge -n $sw1 link set dev swp1 backup_port vx0"
+	run_cmd "bridge -n $sw1 link set dev swp1 backup_nhid 10"
+	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
 
 	backup_nhid_add_del_loop &
 	pid1=$!
-	ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 0 &
+	ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 0 &
 	pid2=$!
 
 	sleep 30
diff --git a/tools/testing/selftests/net/test_bridge_neigh_suppress.sh b/tools/testing/selftests/net/test_bridge_neigh_suppress.sh
index d80f2cd87614..8533393a4f18 100755
--- a/tools/testing/selftests/net/test_bridge_neigh_suppress.sh
+++ b/tools/testing/selftests/net/test_bridge_neigh_suppress.sh
@@ -45,9 +45,8 @@
 # | sw1                                | | sw2                                |
 # +------------------------------------+ +------------------------------------+
 
+source lib.sh
 ret=0
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
 
 # All tests in this script. Can be overridden with -t option.
 TESTS="
@@ -140,9 +139,6 @@ setup_topo_ns()
 {
 	local ns=$1; shift
 
-	ip netns add $ns
-	ip -n $ns link set dev lo up
-
 	ip netns exec $ns sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1
 	ip netns exec $ns sysctl -qw net.ipv6.conf.default.ignore_routes_with_linkdown=1
 	ip netns exec $ns sysctl -qw net.ipv6.conf.all.accept_dad=0
@@ -153,21 +149,22 @@ setup_topo()
 {
 	local ns
 
-	for ns in h1 h2 sw1 sw2; do
+	setup_ns h1 h2 sw1 sw2
+	for ns in $h1 $h2 $sw1 $sw2; do
 		setup_topo_ns $ns
 	done
 
 	ip link add name veth0 type veth peer name veth1
-	ip link set dev veth0 netns h1 name eth0
-	ip link set dev veth1 netns sw1 name swp1
+	ip link set dev veth0 netns $h1 name eth0
+	ip link set dev veth1 netns $sw1 name swp1
 
 	ip link add name veth0 type veth peer name veth1
-	ip link set dev veth0 netns sw1 name veth0
-	ip link set dev veth1 netns sw2 name veth0
+	ip link set dev veth0 netns $sw1 name veth0
+	ip link set dev veth1 netns $sw2 name veth0
 
 	ip link add name veth0 type veth peer name veth1
-	ip link set dev veth0 netns h2 name eth0
-	ip link set dev veth1 netns sw2 name swp1
+	ip link set dev veth0 netns $h2 name eth0
+	ip link set dev veth1 netns $sw2 name swp1
 }
 
 setup_host_common()
@@ -190,7 +187,7 @@ setup_host_common()
 
 setup_h1()
 {
-	local ns=h1
+	local ns=$h1
 	local v4addr1=192.0.2.1/28
 	local v4addr2=192.0.2.17/28
 	local v6addr1=2001:db8:1::1/64
@@ -201,7 +198,7 @@ setup_h1()
 
 setup_h2()
 {
-	local ns=h2
+	local ns=$h2
 	local v4addr1=192.0.2.2/28
 	local v4addr2=192.0.2.18/28
 	local v6addr1=2001:db8:1::2/64
@@ -254,7 +251,7 @@ setup_sw_common()
 
 setup_sw1()
 {
-	local ns=sw1
+	local ns=$sw1
 	local local_addr=192.0.2.33
 	local remote_addr=192.0.2.34
 	local veth_addr=192.0.2.49
@@ -265,7 +262,7 @@ setup_sw1()
 
 setup_sw2()
 {
-	local ns=sw2
+	local ns=$sw2
 	local local_addr=192.0.2.34
 	local remote_addr=192.0.2.33
 	local veth_addr=192.0.2.50
@@ -291,11 +288,7 @@ setup()
 
 cleanup()
 {
-	local ns
-
-	for ns in h1 h2 sw1 sw2; do
-		ip netns del $ns &> /dev/null
-	done
+	cleanup_ns $h1 $h2 $sw1 $sw2
 }
 
 ################################################################################
@@ -312,80 +305,80 @@ neigh_suppress_arp_common()
 	echo "Per-port ARP suppression - VLAN $vid"
 	echo "----------------------------------"
 
-	run_cmd "tc -n sw1 qdisc replace dev vx0 clsact"
-	run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 101 proto 0x0806 flower indev swp1 arp_tip $tip arp_sip $sip arp_op request action pass"
+	run_cmd "tc -n $sw1 qdisc replace dev vx0 clsact"
+	run_cmd "tc -n $sw1 filter replace dev vx0 egress pref 1 handle 101 proto 0x0806 flower indev swp1 arp_tip $tip arp_sip $sip arp_op request action pass"
 
 	# Initial state - check that ARP requests are not suppressed and that
 	# ARP replies are received.
-	run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
+	run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
 	log_test $? 0 "arping"
-	tc_check_packets sw1 "dev vx0 egress" 101 1
+	tc_check_packets $sw1 "dev vx0 egress" 101 1
 	log_test $? 0 "ARP suppression"
 
 	# Enable neighbor suppression and check that nothing changes compared
 	# to the initial state.
-	run_cmd "bridge -n sw1 link set dev vx0 neigh_suppress on"
-	run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
+	run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress on"
+	run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
 	log_test $? 0 "\"neigh_suppress\" is on"
 
-	run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
+	run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
 	log_test $? 0 "arping"
-	tc_check_packets sw1 "dev vx0 egress" 101 2
+	tc_check_packets $sw1 "dev vx0 egress" 101 2
 	log_test $? 0 "ARP suppression"
 
 	# Install an FDB entry for the remote host and check that nothing
 	# changes compared to the initial state.
-	h2_mac=$(ip -n h2 -j -p link show eth0.$vid | jq -r '.[]["address"]')
-	run_cmd "bridge -n sw1 fdb replace $h2_mac dev vx0 master static vlan $vid"
+	h2_mac=$(ip -n $h2 -j -p link show eth0.$vid | jq -r '.[]["address"]')
+	run_cmd "bridge -n $sw1 fdb replace $h2_mac dev vx0 master static vlan $vid"
 	log_test $? 0 "FDB entry installation"
 
-	run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
+	run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
 	log_test $? 0 "arping"
-	tc_check_packets sw1 "dev vx0 egress" 101 3
+	tc_check_packets $sw1 "dev vx0 egress" 101 3
 	log_test $? 0 "ARP suppression"
 
 	# Install a neighbor on the matching SVI interface and check that ARP
 	# requests are suppressed.
-	run_cmd "ip -n sw1 neigh replace $tip lladdr $h2_mac nud permanent dev br0.$vid"
+	run_cmd "ip -n $sw1 neigh replace $tip lladdr $h2_mac nud permanent dev br0.$vid"
 	log_test $? 0 "Neighbor entry installation"
 
-	run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
+	run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
 	log_test $? 0 "arping"
-	tc_check_packets sw1 "dev vx0 egress" 101 3
+	tc_check_packets $sw1 "dev vx0 egress" 101 3
 	log_test $? 0 "ARP suppression"
 
 	# Take the second host down and check that ARP requests are suppressed
 	# and that ARP replies are received.
-	run_cmd "ip -n h2 link set dev eth0.$vid down"
+	run_cmd "ip -n $h2 link set dev eth0.$vid down"
 	log_test $? 0 "H2 down"
 
-	run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
+	run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
 	log_test $? 0 "arping"
-	tc_check_packets sw1 "dev vx0 egress" 101 3
+	tc_check_packets $sw1 "dev vx0 egress" 101 3
 	log_test $? 0 "ARP suppression"
 
-	run_cmd "ip -n h2 link set dev eth0.$vid up"
+	run_cmd "ip -n $h2 link set dev eth0.$vid up"
 	log_test $? 0 "H2 up"
 
 	# Disable neighbor suppression and check that ARP requests are no
 	# longer suppressed.
-	run_cmd "bridge -n sw1 link set dev vx0 neigh_suppress off"
-	run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_suppress off\""
+	run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress off"
+	run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress off\""
 	log_test $? 0 "\"neigh_suppress\" is off"
 
-	run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
+	run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
 	log_test $? 0 "arping"
-	tc_check_packets sw1 "dev vx0 egress" 101 4
+	tc_check_packets $sw1 "dev vx0 egress" 101 4
 	log_test $? 0 "ARP suppression"
 
 	# Take the second host down and check that ARP requests are not
 	# suppressed and that ARP replies are not received.
-	run_cmd "ip -n h2 link set dev eth0.$vid down"
+	run_cmd "ip -n $h2 link set dev eth0.$vid down"
 	log_test $? 0 "H2 down"
 
-	run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
+	run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
 	log_test $? 1 "arping"
-	tc_check_packets sw1 "dev vx0 egress" 101 5
+	tc_check_packets $sw1 "dev vx0 egress" 101 5
 	log_test $? 0 "ARP suppression"
 }
 
@@ -415,80 +408,80 @@ neigh_suppress_ns_common()
 	echo "Per-port NS suppression - VLAN $vid"
 	echo "---------------------------------"
 
-	run_cmd "tc -n sw1 qdisc replace dev vx0 clsact"
-	run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 101 proto ipv6 flower indev swp1 ip_proto icmpv6 dst_ip $maddr src_ip $saddr type 135 code 0 action pass"
+	run_cmd "tc -n $sw1 qdisc replace dev vx0 clsact"
+	run_cmd "tc -n $sw1 filter replace dev vx0 egress pref 1 handle 101 proto ipv6 flower indev swp1 ip_proto icmpv6 dst_ip $maddr src_ip $saddr type 135 code 0 action pass"
 
 	# Initial state - check that NS messages are not suppressed and that ND
 	# messages are received.
-	run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
+	run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
 	log_test $? 0 "ndisc6"
-	tc_check_packets sw1 "dev vx0 egress" 101 1
+	tc_check_packets $sw1 "dev vx0 egress" 101 1
 	log_test $? 0 "NS suppression"
 
 	# Enable neighbor suppression and check that nothing changes compared
 	# to the initial state.
-	run_cmd "bridge -n sw1 link set dev vx0 neigh_suppress on"
-	run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
+	run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress on"
+	run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
 	log_test $? 0 "\"neigh_suppress\" is on"
 
-	run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
+	run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
 	log_test $? 0 "ndisc6"
-	tc_check_packets sw1 "dev vx0 egress" 101 2
+	tc_check_packets $sw1 "dev vx0 egress" 101 2
 	log_test $? 0 "NS suppression"
 
 	# Install an FDB entry for the remote host and check that nothing
 	# changes compared to the initial state.
-	h2_mac=$(ip -n h2 -j -p link show eth0.$vid | jq -r '.[]["address"]')
-	run_cmd "bridge -n sw1 fdb replace $h2_mac dev vx0 master static vlan $vid"
+	h2_mac=$(ip -n $h2 -j -p link show eth0.$vid | jq -r '.[]["address"]')
+	run_cmd "bridge -n $sw1 fdb replace $h2_mac dev vx0 master static vlan $vid"
 	log_test $? 0 "FDB entry installation"
 
-	run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
+	run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
 	log_test $? 0 "ndisc6"
-	tc_check_packets sw1 "dev vx0 egress" 101 3
+	tc_check_packets $sw1 "dev vx0 egress" 101 3
 	log_test $? 0 "NS suppression"
 
 	# Install a neighbor on the matching SVI interface and check that NS
 	# messages are suppressed.
-	run_cmd "ip -n sw1 neigh replace $daddr lladdr $h2_mac nud permanent dev br0.$vid"
+	run_cmd "ip -n $sw1 neigh replace $daddr lladdr $h2_mac nud permanent dev br0.$vid"
 	log_test $? 0 "Neighbor entry installation"
 
-	run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
+	run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
 	log_test $? 0 "ndisc6"
-	tc_check_packets sw1 "dev vx0 egress" 101 3
+	tc_check_packets $sw1 "dev vx0 egress" 101 3
 	log_test $? 0 "NS suppression"
 
 	# Take the second host down and check that NS messages are suppressed
 	# and that ND messages are received.
-	run_cmd "ip -n h2 link set dev eth0.$vid down"
+	run_cmd "ip -n $h2 link set dev eth0.$vid down"
 	log_test $? 0 "H2 down"
 
-	run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
+	run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
 	log_test $? 0 "ndisc6"
-	tc_check_packets sw1 "dev vx0 egress" 101 3
+	tc_check_packets $sw1 "dev vx0 egress" 101 3
 	log_test $? 0 "NS suppression"
 
-	run_cmd "ip -n h2 link set dev eth0.$vid up"
+	run_cmd "ip -n $h2 link set dev eth0.$vid up"
 	log_test $? 0 "H2 up"
 
 	# Disable neighbor suppression and check that NS messages are no longer
 	# suppressed.
-	run_cmd "bridge -n sw1 link set dev vx0 neigh_suppress off"
-	run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_suppress off\""
+	run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress off"
+	run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress off\""
 	log_test $? 0 "\"neigh_suppress\" is off"
 
-	run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
+	run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
 	log_test $? 0 "ndisc6"
-	tc_check_packets sw1 "dev vx0 egress" 101 4
+	tc_check_packets $sw1 "dev vx0 egress" 101 4
 	log_test $? 0 "NS suppression"
 
 	# Take the second host down and check that NS messages are not
 	# suppressed and that ND messages are not received.
-	run_cmd "ip -n h2 link set dev eth0.$vid down"
+	run_cmd "ip -n $h2 link set dev eth0.$vid down"
 	log_test $? 0 "H2 down"
 
-	run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
+	run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
 	log_test $? 2 "ndisc6"
-	tc_check_packets sw1 "dev vx0 egress" 101 5
+	tc_check_packets $sw1 "dev vx0 egress" 101 5
 	log_test $? 0 "NS suppression"
 }
 
@@ -524,118 +517,118 @@ neigh_vlan_suppress_arp()
 	echo "Per-{Port, VLAN} ARP suppression"
 	echo "--------------------------------"
 
-	run_cmd "tc -n sw1 qdisc replace dev vx0 clsact"
-	run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 101 proto 0x0806 flower indev swp1 arp_tip $tip1 arp_sip $sip1 arp_op request action pass"
-	run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 102 proto 0x0806 flower indev swp1 arp_tip $tip2 arp_sip $sip2 arp_op request action pass"
+	run_cmd "tc -n $sw1 qdisc replace dev vx0 clsact"
+	run_cmd "tc -n $sw1 filter replace dev vx0 egress pref 1 handle 101 proto 0x0806 flower indev swp1 arp_tip $tip1 arp_sip $sip1 arp_op request action pass"
+	run_cmd "tc -n $sw1 filter replace dev vx0 egress pref 1 handle 102 proto 0x0806 flower indev swp1 arp_tip $tip2 arp_sip $sip2 arp_op request action pass"
 
-	h2_mac1=$(ip -n h2 -j -p link show eth0.$vid1 | jq -r '.[]["address"]')
-	h2_mac2=$(ip -n h2 -j -p link show eth0.$vid2 | jq -r '.[]["address"]')
-	run_cmd "bridge -n sw1 fdb replace $h2_mac1 dev vx0 master static vlan $vid1"
-	run_cmd "bridge -n sw1 fdb replace $h2_mac2 dev vx0 master static vlan $vid2"
-	run_cmd "ip -n sw1 neigh replace $tip1 lladdr $h2_mac1 nud permanent dev br0.$vid1"
-	run_cmd "ip -n sw1 neigh replace $tip2 lladdr $h2_mac2 nud permanent dev br0.$vid2"
+	h2_mac1=$(ip -n $h2 -j -p link show eth0.$vid1 | jq -r '.[]["address"]')
+	h2_mac2=$(ip -n $h2 -j -p link show eth0.$vid2 | jq -r '.[]["address"]')
+	run_cmd "bridge -n $sw1 fdb replace $h2_mac1 dev vx0 master static vlan $vid1"
+	run_cmd "bridge -n $sw1 fdb replace $h2_mac2 dev vx0 master static vlan $vid2"
+	run_cmd "ip -n $sw1 neigh replace $tip1 lladdr $h2_mac1 nud permanent dev br0.$vid1"
+	run_cmd "ip -n $sw1 neigh replace $tip2 lladdr $h2_mac2 nud permanent dev br0.$vid2"
 
 	# Enable per-{Port, VLAN} neighbor suppression and check that ARP
 	# requests are not suppressed and that ARP replies are received.
-	run_cmd "bridge -n sw1 link set dev vx0 neigh_vlan_suppress on"
-	run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_vlan_suppress on\""
+	run_cmd "bridge -n $sw1 link set dev vx0 neigh_vlan_suppress on"
+	run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_vlan_suppress on\""
 	log_test $? 0 "\"neigh_vlan_suppress\" is on"
 
-	run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
+	run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
 	log_test $? 0 "arping (VLAN $vid1)"
-	run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
+	run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
 	log_test $? 0 "arping (VLAN $vid2)"
 
-	tc_check_packets sw1 "dev vx0 egress" 101 1
+	tc_check_packets $sw1 "dev vx0 egress" 101 1
 	log_test $? 0 "ARP suppression (VLAN $vid1)"
-	tc_check_packets sw1 "dev vx0 egress" 102 1
+	tc_check_packets $sw1 "dev vx0 egress" 102 1
 	log_test $? 0 "ARP suppression (VLAN $vid2)"
 
 	# Enable neighbor suppression on VLAN 10 and check that only on this
 	# VLAN ARP requests are suppressed.
-	run_cmd "bridge -n sw1 vlan set vid $vid1 dev vx0 neigh_suppress on"
-	run_cmd "bridge -n sw1 -d vlan show dev vx0 vid $vid1 | grep \"neigh_suppress on\""
+	run_cmd "bridge -n $sw1 vlan set vid $vid1 dev vx0 neigh_suppress on"
+	run_cmd "bridge -n $sw1 -d vlan show dev vx0 vid $vid1 | grep \"neigh_suppress on\""
 	log_test $? 0 "\"neigh_suppress\" is on (VLAN $vid1)"
-	run_cmd "bridge -n sw1 -d vlan show dev vx0 vid $vid2 | grep \"neigh_suppress off\""
+	run_cmd "bridge -n $sw1 -d vlan show dev vx0 vid $vid2 | grep \"neigh_suppress off\""
 	log_test $? 0 "\"neigh_suppress\" is off (VLAN $vid2)"
 
-	run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
+	run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
 	log_test $? 0 "arping (VLAN $vid1)"
-	run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
+	run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
 	log_test $? 0 "arping (VLAN $vid2)"
 
-	tc_check_packets sw1 "dev vx0 egress" 101 1
+	tc_check_packets $sw1 "dev vx0 egress" 101 1
 	log_test $? 0 "ARP suppression (VLAN $vid1)"
-	tc_check_packets sw1 "dev vx0 egress" 102 2
+	tc_check_packets $sw1 "dev vx0 egress" 102 2
 	log_test $? 0 "ARP suppression (VLAN $vid2)"
 
 	# Enable neighbor suppression on the port and check that it has no
 	# effect compared to previous state.
-	run_cmd "bridge -n sw1 link set dev vx0 neigh_suppress on"
-	run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
+	run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress on"
+	run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
 	log_test $? 0 "\"neigh_suppress\" is on"
 
-	run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
+	run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
 	log_test $? 0 "arping (VLAN $vid1)"
-	run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
+	run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
 	log_test $? 0 "arping (VLAN $vid2)"
 
-	tc_check_packets sw1 "dev vx0 egress" 101 1
+	tc_check_packets $sw1 "dev vx0 egress" 101 1
 	log_test $? 0 "ARP suppression (VLAN $vid1)"
-	tc_check_packets sw1 "dev vx0 egress" 102 3
+	tc_check_packets $sw1 "dev vx0 egress" 102 3
 	log_test $? 0 "ARP suppression (VLAN $vid2)"
 
 	# Disable neighbor suppression on the port and check that it has no
 	# effect compared to previous state.
-	run_cmd "bridge -n sw1 link set dev vx0 neigh_suppress off"
-	run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_suppress off\""
+	run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress off"
+	run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress off\""
 	log_test $? 0 "\"neigh_suppress\" is off"
 
-	run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
+	run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
 	log_test $? 0 "arping (VLAN $vid1)"
-	run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
+	run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
 	log_test $? 0 "arping (VLAN $vid2)"
 
-	tc_check_packets sw1 "dev vx0 egress" 101 1
+	tc_check_packets $sw1 "dev vx0 egress" 101 1
 	log_test $? 0 "ARP suppression (VLAN $vid1)"
-	tc_check_packets sw1 "dev vx0 egress" 102 4
+	tc_check_packets $sw1 "dev vx0 egress" 102 4
 	log_test $? 0 "ARP suppression (VLAN $vid2)"
 
 	# Disable neighbor suppression on VLAN 10 and check that ARP requests
 	# are no longer suppressed on this VLAN.
-	run_cmd "bridge -n sw1 vlan set vid $vid1 dev vx0 neigh_suppress off"
-	run_cmd "bridge -n sw1 -d vlan show dev vx0 vid $vid1 | grep \"neigh_suppress off\""
+	run_cmd "bridge -n $sw1 vlan set vid $vid1 dev vx0 neigh_suppress off"
+	run_cmd "bridge -n $sw1 -d vlan show dev vx0 vid $vid1 | grep \"neigh_suppress off\""
 	log_test $? 0 "\"neigh_suppress\" is off (VLAN $vid1)"
 
-	run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
+	run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
 	log_test $? 0 "arping (VLAN $vid1)"
-	run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
+	run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
 	log_test $? 0 "arping (VLAN $vid2)"
 
-	tc_check_packets sw1 "dev vx0 egress" 101 2
+	tc_check_packets $sw1 "dev vx0 egress" 101 2
 	log_test $? 0 "ARP suppression (VLAN $vid1)"
-	tc_check_packets sw1 "dev vx0 egress" 102 5
+	tc_check_packets $sw1 "dev vx0 egress" 102 5
 	log_test $? 0 "ARP suppression (VLAN $vid2)"
 
 	# Disable per-{Port, VLAN} neighbor suppression, enable neighbor
 	# suppression on the port and check that on both VLANs ARP requests are
 	# suppressed.
-	run_cmd "bridge -n sw1 link set dev vx0 neigh_vlan_suppress off"
-	run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_vlan_suppress off\""
+	run_cmd "bridge -n $sw1 link set dev vx0 neigh_vlan_suppress off"
+	run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_vlan_suppress off\""
 	log_test $? 0 "\"neigh_vlan_suppress\" is off"
 
-	run_cmd "bridge -n sw1 link set dev vx0 neigh_suppress on"
-	run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
+	run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress on"
+	run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
 	log_test $? 0 "\"neigh_suppress\" is on"
 
-	run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
+	run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
 	log_test $? 0 "arping (VLAN $vid1)"
-	run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
+	run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
 	log_test $? 0 "arping (VLAN $vid2)"
 
-	tc_check_packets sw1 "dev vx0 egress" 101 2
+	tc_check_packets $sw1 "dev vx0 egress" 101 2
 	log_test $? 0 "ARP suppression (VLAN $vid1)"
-	tc_check_packets sw1 "dev vx0 egress" 102 5
+	tc_check_packets $sw1 "dev vx0 egress" 102 5
 	log_test $? 0 "ARP suppression (VLAN $vid2)"
 }
 
@@ -655,118 +648,118 @@ neigh_vlan_suppress_ns()
 	echo "Per-{Port, VLAN} NS suppression"
 	echo "-------------------------------"
 
-	run_cmd "tc -n sw1 qdisc replace dev vx0 clsact"
-	run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 101 proto ipv6 flower indev swp1 ip_proto icmpv6 dst_ip $maddr src_ip $saddr1 type 135 code 0 action pass"
-	run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 102 proto ipv6 flower indev swp1 ip_proto icmpv6 dst_ip $maddr src_ip $saddr2 type 135 code 0 action pass"
+	run_cmd "tc -n $sw1 qdisc replace dev vx0 clsact"
+	run_cmd "tc -n $sw1 filter replace dev vx0 egress pref 1 handle 101 proto ipv6 flower indev swp1 ip_proto icmpv6 dst_ip $maddr src_ip $saddr1 type 135 code 0 action pass"
+	run_cmd "tc -n $sw1 filter replace dev vx0 egress pref 1 handle 102 proto ipv6 flower indev swp1 ip_proto icmpv6 dst_ip $maddr src_ip $saddr2 type 135 code 0 action pass"
 
-	h2_mac1=$(ip -n h2 -j -p link show eth0.$vid1 | jq -r '.[]["address"]')
-	h2_mac2=$(ip -n h2 -j -p link show eth0.$vid2 | jq -r '.[]["address"]')
-	run_cmd "bridge -n sw1 fdb replace $h2_mac1 dev vx0 master static vlan $vid1"
-	run_cmd "bridge -n sw1 fdb replace $h2_mac2 dev vx0 master static vlan $vid2"
-	run_cmd "ip -n sw1 neigh replace $daddr1 lladdr $h2_mac1 nud permanent dev br0.$vid1"
-	run_cmd "ip -n sw1 neigh replace $daddr2 lladdr $h2_mac2 nud permanent dev br0.$vid2"
+	h2_mac1=$(ip -n $h2 -j -p link show eth0.$vid1 | jq -r '.[]["address"]')
+	h2_mac2=$(ip -n $h2 -j -p link show eth0.$vid2 | jq -r '.[]["address"]')
+	run_cmd "bridge -n $sw1 fdb replace $h2_mac1 dev vx0 master static vlan $vid1"
+	run_cmd "bridge -n $sw1 fdb replace $h2_mac2 dev vx0 master static vlan $vid2"
+	run_cmd "ip -n $sw1 neigh replace $daddr1 lladdr $h2_mac1 nud permanent dev br0.$vid1"
+	run_cmd "ip -n $sw1 neigh replace $daddr2 lladdr $h2_mac2 nud permanent dev br0.$vid2"
 
 	# Enable per-{Port, VLAN} neighbor suppression and check that NS
 	# messages are not suppressed and that ND messages are received.
-	run_cmd "bridge -n sw1 link set dev vx0 neigh_vlan_suppress on"
-	run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_vlan_suppress on\""
+	run_cmd "bridge -n $sw1 link set dev vx0 neigh_vlan_suppress on"
+	run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_vlan_suppress on\""
 	log_test $? 0 "\"neigh_vlan_suppress\" is on"
 
-	run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
+	run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
 	log_test $? 0 "ndisc6 (VLAN $vid1)"
-	run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
+	run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
 	log_test $? 0 "ndisc6 (VLAN $vid2)"
 
-	tc_check_packets sw1 "dev vx0 egress" 101 1
+	tc_check_packets $sw1 "dev vx0 egress" 101 1
 	log_test $? 0 "NS suppression (VLAN $vid1)"
-	tc_check_packets sw1 "dev vx0 egress" 102 1
+	tc_check_packets $sw1 "dev vx0 egress" 102 1
 	log_test $? 0 "NS suppression (VLAN $vid2)"
 
 	# Enable neighbor suppression on VLAN 10 and check that only on this
 	# VLAN NS messages are suppressed.
-	run_cmd "bridge -n sw1 vlan set vid $vid1 dev vx0 neigh_suppress on"
-	run_cmd "bridge -n sw1 -d vlan show dev vx0 vid $vid1 | grep \"neigh_suppress on\""
+	run_cmd "bridge -n $sw1 vlan set vid $vid1 dev vx0 neigh_suppress on"
+	run_cmd "bridge -n $sw1 -d vlan show dev vx0 vid $vid1 | grep \"neigh_suppress on\""
 	log_test $? 0 "\"neigh_suppress\" is on (VLAN $vid1)"
-	run_cmd "bridge -n sw1 -d vlan show dev vx0 vid $vid2 | grep \"neigh_suppress off\""
+	run_cmd "bridge -n $sw1 -d vlan show dev vx0 vid $vid2 | grep \"neigh_suppress off\""
 	log_test $? 0 "\"neigh_suppress\" is off (VLAN $vid2)"
 
-	run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
+	run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
 	log_test $? 0 "ndisc6 (VLAN $vid1)"
-	run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
+	run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
 	log_test $? 0 "ndisc6 (VLAN $vid2)"
 
-	tc_check_packets sw1 "dev vx0 egress" 101 1
+	tc_check_packets $sw1 "dev vx0 egress" 101 1
 	log_test $? 0 "NS suppression (VLAN $vid1)"
-	tc_check_packets sw1 "dev vx0 egress" 102 2
+	tc_check_packets $sw1 "dev vx0 egress" 102 2
 	log_test $? 0 "NS suppression (VLAN $vid2)"
 
 	# Enable neighbor suppression on the port and check that it has no
 	# effect compared to previous state.
-	run_cmd "bridge -n sw1 link set dev vx0 neigh_suppress on"
-	run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
+	run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress on"
+	run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
 	log_test $? 0 "\"neigh_suppress\" is on"
 
-	run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
+	run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
 	log_test $? 0 "ndisc6 (VLAN $vid1)"
-	run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
+	run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
 	log_test $? 0 "ndisc6 (VLAN $vid2)"
 
-	tc_check_packets sw1 "dev vx0 egress" 101 1
+	tc_check_packets $sw1 "dev vx0 egress" 101 1
 	log_test $? 0 "NS suppression (VLAN $vid1)"
-	tc_check_packets sw1 "dev vx0 egress" 102 3
+	tc_check_packets $sw1 "dev vx0 egress" 102 3
 	log_test $? 0 "NS suppression (VLAN $vid2)"
 
 	# Disable neighbor suppression on the port and check that it has no
 	# effect compared to previous state.
-	run_cmd "bridge -n sw1 link set dev vx0 neigh_suppress off"
-	run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_suppress off\""
+	run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress off"
+	run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress off\""
 	log_test $? 0 "\"neigh_suppress\" is off"
 
-	run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
+	run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
 	log_test $? 0 "ndisc6 (VLAN $vid1)"
-	run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
+	run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
 	log_test $? 0 "ndisc6 (VLAN $vid2)"
 
-	tc_check_packets sw1 "dev vx0 egress" 101 1
+	tc_check_packets $sw1 "dev vx0 egress" 101 1
 	log_test $? 0 "NS suppression (VLAN $vid1)"
-	tc_check_packets sw1 "dev vx0 egress" 102 4
+	tc_check_packets $sw1 "dev vx0 egress" 102 4
 	log_test $? 0 "NS suppression (VLAN $vid2)"
 
 	# Disable neighbor suppression on VLAN 10 and check that NS messages
 	# are no longer suppressed on this VLAN.
-	run_cmd "bridge -n sw1 vlan set vid $vid1 dev vx0 neigh_suppress off"
-	run_cmd "bridge -n sw1 -d vlan show dev vx0 vid $vid1 | grep \"neigh_suppress off\""
+	run_cmd "bridge -n $sw1 vlan set vid $vid1 dev vx0 neigh_suppress off"
+	run_cmd "bridge -n $sw1 -d vlan show dev vx0 vid $vid1 | grep \"neigh_suppress off\""
 	log_test $? 0 "\"neigh_suppress\" is off (VLAN $vid1)"
 
-	run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
+	run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
 	log_test $? 0 "ndisc6 (VLAN $vid1)"
-	run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
+	run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
 	log_test $? 0 "ndisc6 (VLAN $vid2)"
 
-	tc_check_packets sw1 "dev vx0 egress" 101 2
+	tc_check_packets $sw1 "dev vx0 egress" 101 2
 	log_test $? 0 "NS suppression (VLAN $vid1)"
-	tc_check_packets sw1 "dev vx0 egress" 102 5
+	tc_check_packets $sw1 "dev vx0 egress" 102 5
 	log_test $? 0 "NS suppression (VLAN $vid2)"
 
 	# Disable per-{Port, VLAN} neighbor suppression, enable neighbor
 	# suppression on the port and check that on both VLANs NS messages are
 	# suppressed.
-	run_cmd "bridge -n sw1 link set dev vx0 neigh_vlan_suppress off"
-	run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_vlan_suppress off\""
+	run_cmd "bridge -n $sw1 link set dev vx0 neigh_vlan_suppress off"
+	run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_vlan_suppress off\""
 	log_test $? 0 "\"neigh_vlan_suppress\" is off"
 
-	run_cmd "bridge -n sw1 link set dev vx0 neigh_suppress on"
-	run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
+	run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress on"
+	run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
 	log_test $? 0 "\"neigh_suppress\" is on"
 
-	run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
+	run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
 	log_test $? 0 "ndisc6 (VLAN $vid1)"
-	run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
+	run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
 	log_test $? 0 "ndisc6 (VLAN $vid2)"
 
-	tc_check_packets sw1 "dev vx0 egress" 101 2
+	tc_check_packets $sw1 "dev vx0 egress" 101 2
 	log_test $? 0 "NS suppression (VLAN $vid1)"
-	tc_check_packets sw1 "dev vx0 egress" 102 5
+	tc_check_packets $sw1 "dev vx0 egress" 102 5
 	log_test $? 0 "NS suppression (VLAN $vid2)"
 }
 
diff --git a/tools/testing/selftests/net/test_vxlan_mdb.sh b/tools/testing/selftests/net/test_vxlan_mdb.sh
index 6e996f8063cd..84a05a9e46d8 100755
--- a/tools/testing/selftests/net/test_vxlan_mdb.sh
+++ b/tools/testing/selftests/net/test_vxlan_mdb.sh
@@ -55,9 +55,8 @@
 # | ns2_v4                             | | ns2_v6                             |
 # +------------------------------------+ +------------------------------------+
 
+source lib.sh
 ret=0
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
 
 CONTROL_PATH_TESTS="
 	basic_star_g_ipv4_ipv4
@@ -80,6 +79,7 @@ CONTROL_PATH_TESTS="
 	dump_ipv6_ipv4
 	dump_ipv4_ipv6
 	dump_ipv6_ipv6
+	flush
 "
 
 DATA_PATH_TESTS="
@@ -260,9 +260,6 @@ setup_common()
 	local local_addr1=$1; shift
 	local local_addr2=$1; shift
 
-	ip netns add $ns1
-	ip netns add $ns2
-
 	ip link add name veth0 type veth peer name veth1
 	ip link set dev veth0 netns $ns1 name veth0
 	ip link set dev veth1 netns $ns2 name veth0
@@ -273,36 +270,36 @@ setup_common()
 
 setup_v4()
 {
-	setup_common ns1_v4 ns2_v4 192.0.2.1 192.0.2.2
+	setup_ns ns1_v4 ns2_v4
+	setup_common $ns1_v4 $ns2_v4 192.0.2.1 192.0.2.2
 
-	ip -n ns1_v4 address add 192.0.2.17/28 dev veth0
-	ip -n ns2_v4 address add 192.0.2.18/28 dev veth0
+	ip -n $ns1_v4 address add 192.0.2.17/28 dev veth0
+	ip -n $ns2_v4 address add 192.0.2.18/28 dev veth0
 
-	ip -n ns1_v4 route add default via 192.0.2.18
-	ip -n ns2_v4 route add default via 192.0.2.17
+	ip -n $ns1_v4 route add default via 192.0.2.18
+	ip -n $ns2_v4 route add default via 192.0.2.17
 }
 
 cleanup_v4()
 {
-	ip netns del ns2_v4
-	ip netns del ns1_v4
+	cleanup_ns $ns2_v4 $ns1_v4
 }
 
 setup_v6()
 {
-	setup_common ns1_v6 ns2_v6 2001:db8:1::1 2001:db8:1::2
+	setup_ns ns1_v6 ns2_v6
+	setup_common $ns1_v6 $ns2_v6 2001:db8:1::1 2001:db8:1::2
 
-	ip -n ns1_v6 address add 2001:db8:2::1/64 dev veth0 nodad
-	ip -n ns2_v6 address add 2001:db8:2::2/64 dev veth0 nodad
+	ip -n $ns1_v6 address add 2001:db8:2::1/64 dev veth0 nodad
+	ip -n $ns2_v6 address add 2001:db8:2::2/64 dev veth0 nodad
 
-	ip -n ns1_v6 route add default via 2001:db8:2::2
-	ip -n ns2_v6 route add default via 2001:db8:2::1
+	ip -n $ns1_v6 route add default via 2001:db8:2::2
+	ip -n $ns2_v6 route add default via 2001:db8:2::1
 }
 
 cleanup_v6()
 {
-	ip netns del ns2_v6
-	ip netns del ns1_v6
+	cleanup_ns $ns2_v6 $ns1_v6
 }
 
 setup()
@@ -433,7 +430,7 @@ basic_common()
 
 basic_star_g_ipv4_ipv4()
 {
-	local ns1=ns1_v4
+	local ns1=$ns1_v4
 	local grp_key="grp 239.1.1.1"
 	local vtep_ip=198.51.100.100
 
@@ -446,7 +443,7 @@ basic_star_g_ipv4_ipv4()
 
 basic_star_g_ipv6_ipv4()
 {
-	local ns1=ns1_v4
+	local ns1=$ns1_v4
 	local grp_key="grp ff0e::1"
 	local vtep_ip=198.51.100.100
 
@@ -459,7 +456,7 @@ basic_star_g_ipv6_ipv4()
 
 basic_star_g_ipv4_ipv6()
 {
-	local ns1=ns1_v6
+	local ns1=$ns1_v6
 	local grp_key="grp 239.1.1.1"
 	local vtep_ip=2001:db8:1000::1
 
@@ -472,7 +469,7 @@ basic_star_g_ipv4_ipv6()
 
 basic_star_g_ipv6_ipv6()
 {
-	local ns1=ns1_v6
+	local ns1=$ns1_v6
 	local grp_key="grp ff0e::1"
 	local vtep_ip=2001:db8:1000::1
 
@@ -485,7 +482,7 @@ basic_star_g_ipv6_ipv6()
 
 basic_sg_ipv4_ipv4()
 {
-	local ns1=ns1_v4
+	local ns1=$ns1_v4
 	local grp_key="grp 239.1.1.1 src 192.0.2.129"
 	local vtep_ip=198.51.100.100
 
@@ -498,7 +495,7 @@ basic_sg_ipv4_ipv4()
 
 basic_sg_ipv6_ipv4()
 {
-	local ns1=ns1_v4
+	local ns1=$ns1_v4
 	local grp_key="grp ff0e::1 src 2001:db8:100::1"
 	local vtep_ip=198.51.100.100
 
@@ -511,7 +508,7 @@ basic_sg_ipv6_ipv4()
 
 basic_sg_ipv4_ipv6()
 {
-	local ns1=ns1_v6
+	local ns1=$ns1_v6
 	local grp_key="grp 239.1.1.1 src 192.0.2.129"
 	local vtep_ip=2001:db8:1000::1
 
@@ -524,7 +521,7 @@ basic_sg_ipv4_ipv6()
 
 basic_sg_ipv6_ipv6()
 {
-	local ns1=ns1_v6
+	local ns1=$ns1_v6
 	local grp_key="grp ff0e::1 src 2001:db8:100::1"
 	local vtep_ip=2001:db8:1000::1
 
@@ -694,7 +691,7 @@ star_g_common()
 
 star_g_ipv4_ipv4()
 {
-	local ns1=ns1_v4
+	local ns1=$ns1_v4
 	local grp=239.1.1.1
 	local src1=192.0.2.129
 	local src2=192.0.2.130
@@ -711,7 +708,7 @@ star_g_ipv4_ipv4()
 
 star_g_ipv6_ipv4()
 {
-	local ns1=ns1_v4
+	local ns1=$ns1_v4
 	local grp=ff0e::1
 	local src1=2001:db8:100::1
 	local src2=2001:db8:100::2
@@ -728,7 +725,7 @@ star_g_ipv6_ipv4()
 
 star_g_ipv4_ipv6()
 {
-	local ns1=ns1_v6
+	local ns1=$ns1_v6
 	local grp=239.1.1.1
 	local src1=192.0.2.129
 	local src2=192.0.2.130
@@ -745,7 +742,7 @@ star_g_ipv4_ipv6()
 
 star_g_ipv6_ipv6()
 {
-	local ns1=ns1_v6
+	local ns1=$ns1_v6
 	local grp=ff0e::1
 	local src1=2001:db8:100::1
 	local src2=2001:db8:100::2
@@ -793,7 +790,7 @@ sg_common()
 
 sg_ipv4_ipv4()
 {
-	local ns1=ns1_v4
+	local ns1=$ns1_v4
 	local grp=239.1.1.1
 	local src=192.0.2.129
 	local vtep_ip=198.51.100.100
@@ -808,7 +805,7 @@ sg_ipv4_ipv4()
 
 sg_ipv6_ipv4()
 {
-	local ns1=ns1_v4
+	local ns1=$ns1_v4
 	local grp=ff0e::1
 	local src=2001:db8:100::1
 	local vtep_ip=198.51.100.100
@@ -823,7 +820,7 @@ sg_ipv6_ipv4()
 
 sg_ipv4_ipv6()
 {
-	local ns1=ns1_v6
+	local ns1=$ns1_v6
 	local grp=239.1.1.1
 	local src=192.0.2.129
 	local vtep_ip=2001:db8:1000::1
@@ -838,7 +835,7 @@ sg_ipv4_ipv6()
 
 sg_ipv6_ipv6()
 {
-	local ns1=ns1_v6
+	local ns1=$ns1_v6
 	local grp=ff0e::1
 	local src=2001:db8:100::1
 	local vtep_ip=2001:db8:1000::1
@@ -918,7 +915,7 @@ dump_common()
 
 dump_ipv4_ipv4()
 {
-	local ns1=ns1_v4
+	local ns1=$ns1_v4
 	local local_addr=192.0.2.1
 	local remote_prefix=198.51.100.
 	local fn=ipv4_grps_get
@@ -932,7 +929,7 @@ dump_ipv4_ipv4()
 
 dump_ipv6_ipv4()
 {
-	local ns1=ns1_v4
+	local ns1=$ns1_v4
 	local local_addr=192.0.2.1
 	local remote_prefix=198.51.100.
 	local fn=ipv6_grps_get
@@ -946,7 +943,7 @@ dump_ipv6_ipv4()
 
 dump_ipv4_ipv6()
 {
-	local ns1=ns1_v6
+	local ns1=$ns1_v6
 	local local_addr=2001:db8:1::1
 	local remote_prefix=2001:db8:1000::
 	local fn=ipv4_grps_get
@@ -960,7 +957,7 @@ dump_ipv4_ipv6()
 
 dump_ipv6_ipv6()
 {
-	local ns1=ns1_v6
+	local ns1=$ns1_v6
 	local local_addr=2001:db8:1::1
 	local remote_prefix=2001:db8:1000::
 	local fn=ipv6_grps_get
@@ -972,6 +969,202 @@ dump_ipv6_ipv6()
 	dump_common $ns1 $local_addr $remote_prefix $fn
 }
 
+flush()
+{
+	local num_entries
+
+	echo
+	echo "Control path: Flush"
+	echo "-------------------"
+
+	# Add entries with different attributes and check that they are all
+	# flushed when the flush command is given with no parameters.
+
+	# Different source VNI.
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.2 permanent dst 198.51.100.1 src_vni 10011"
+
+	# Different routing protocol.
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.3 permanent proto bgp dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.4 permanent proto zebra dst 198.51.100.1 src_vni 10010"
+
+	# Different destination IP.
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.5 permanent dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.6 permanent dst 198.51.100.2 src_vni 10010"
+
+	# Different destination port.
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.7 permanent dst 198.51.100.1 dst_port 11111 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.8 permanent dst 198.51.100.1 dst_port 22222 src_vni 10010"
+
+	# Different VNI.
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.9 permanent dst 198.51.100.1 vni 10010 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.10 permanent dst 198.51.100.1 vni 10020 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0"
+	num_entries=$(bridge -n $ns1_v4 mdb show dev vx0 | wc -l)
+	[[ $num_entries -eq 0 ]]
+	log_test $? 0 "Flush all"
+
+	# Check that entries are flushed when port is specified as the VXLAN
+	# device and that an error is returned when port is specified as a
+	# different net device.
+
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.2 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 port vx0"
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010"
+	log_test $? 254 "Flush by port"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 port veth0"
+	log_test $? 255 "Flush by wrong port"
+
+	# Check that when flushing by source VNI only entries programmed with
+	# the specified source VNI are flushed and the rest are not.
+
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.2 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.1 src_vni 10011"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.2 src_vni 10011"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010"
+	log_test $? 254 "Flush by specified source VNI"
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10011"
+	log_test $? 0 "Flush by unspecified source VNI"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0"
+
+	# Check that all entries are flushed when "permanent" is specified and
+	# that an error is returned when "nopermanent" is specified.
+
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.2 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 permanent"
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010"
+	log_test $? 254 "Flush by \"permanent\" state"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 nopermanent"
+	log_test $? 255 "Flush by \"nopermanent\" state"
+
+	# Check that when flushing by routing protocol only entries programmed
+	# with the specified routing protocol are flushed and the rest are not.
+
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent proto bgp dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent proto zebra dst 198.51.100.2 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 proto bgp"
+
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep \"proto bgp\""
+	log_test $? 1 "Flush by specified routing protocol"
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep \"proto zebra\""
+	log_test $? 0 "Flush by unspecified routing protocol"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0"
+
+	# Check that when flushing by destination IP only entries programmed
+	# with the specified destination IP are flushed and the rest are not.
+
+	# IPv4.
+
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.2 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 dst 198.51.100.2"
+
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep 198.51.100.2"
+	log_test $? 1 "Flush by specified destination IP - IPv4"
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep 198.51.100.1"
+	log_test $? 0 "Flush by unspecified destination IP - IPv4"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0"
+
+	# IPv6.
+
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 2001:db8:1000::1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 2001:db8:1000::2 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 dst 2001:db8:1000::2"
+
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep 2001:db8:1000::2"
+	log_test $? 1 "Flush by specified destination IP - IPv6"
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep 2001:db8:1000::1"
+	log_test $? 0 "Flush by unspecified destination IP - IPv6"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0"
+
+	# Check that when flushing by UDP destination port only entries
+	# programmed with the specified port are flushed and the rest are not.
+
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst_port 11111 dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst_port 22222 dst 198.51.100.2 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 dst_port 11111"
+
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep \"dst_port 11111\""
+	log_test $? 1 "Flush by specified UDP destination port"
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep \"dst_port 22222\""
+	log_test $? 0 "Flush by unspecified UDP destination port"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0"
+
+	# When not specifying a UDP destination port for an entry, traffic is
+	# encapsulated with the device's UDP destination port. Check that when
+	# flushing by the device's UDP destination port only entries programmed
+	# with this port are flushed and the rest are not.
+
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst_port 22222 dst 198.51.100.2 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 dst_port 4789"
+
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep 198.51.100.1"
+	log_test $? 1 "Flush by device's UDP destination port"
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep 198.51.100.2"
+	log_test $? 0 "Flush by unspecified UDP destination port"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0"
+
+	# Check that when flushing by destination VNI only entries programmed
+	# with the specified destination VNI are flushed and the rest are not.
+
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent vni 20010 dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent vni 20011 dst 198.51.100.2 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 vni 20010"
+
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep \" vni 20010\""
+	log_test $? 1 "Flush by specified destination VNI"
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep \" vni 20011\""
+	log_test $? 0 "Flush by unspecified destination VNI"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0"
+
+	# When not specifying a destination VNI for an entry, traffic is
+	# encapsulated with the source VNI. Check that when flushing by a
+	# destination VNI that is equal to the source VNI only such entries are
+	# flushed and the rest are not.
+
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent vni 20010 dst 198.51.100.2 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep 198.51.100.1"
+	log_test $? 1 "Flush by destination VNI equal to source VNI"
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep 198.51.100.2"
+	log_test $? 0 "Flush by unspecified destination VNI"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0"
+
+	# Test that an error is returned when trying to flush using VLAN ID.
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 vid 10"
+	log_test $? 255 "Flush by VLAN ID"
+}
+
 ################################################################################
 # Tests - Data path
 
@@ -1072,8 +1265,8 @@ encap_params_common()
 
 encap_params_ipv4_ipv4()
 {
-	local ns1=ns1_v4
-	local ns2=ns2_v4
+	local ns1=$ns1_v4
+	local ns2=$ns2_v4
 	local vtep1_ip=198.51.100.100
 	local vtep2_ip=198.51.100.200
 	local plen=32
@@ -1091,8 +1284,8 @@ encap_params_ipv4_ipv4()
 
 encap_params_ipv6_ipv4()
 {
-	local ns1=ns1_v4
-	local ns2=ns2_v4
+	local ns1=$ns1_v4
+	local ns2=$ns2_v4
 	local vtep1_ip=198.51.100.100
 	local vtep2_ip=198.51.100.200
 	local plen=32
@@ -1110,8 +1303,8 @@ encap_params_ipv6_ipv4()
 
 encap_params_ipv4_ipv6()
 {
-	local ns1=ns1_v6
-	local ns2=ns2_v6
+	local ns1=$ns1_v6
+	local ns2=$ns2_v6
 	local vtep1_ip=2001:db8:1000::1
 	local vtep2_ip=2001:db8:2000::1
 	local plen=128
@@ -1129,8 +1322,8 @@ encap_params_ipv4_ipv6()
 
 encap_params_ipv6_ipv6()
 {
-	local ns1=ns1_v6
-	local ns2=ns2_v6
+	local ns1=$ns1_v6
+	local ns2=$ns2_v6
 	local vtep1_ip=2001:db8:1000::1
 	local vtep2_ip=2001:db8:2000::1
 	local plen=128
@@ -1208,8 +1401,8 @@ starg_exclude_ir_common()
 
 starg_exclude_ir_ipv4_ipv4()
 {
-	local ns1=ns1_v4
-	local ns2=ns2_v4
+	local ns1=$ns1_v4
+	local ns2=$ns2_v4
 	local vtep1_ip=198.51.100.100
 	local vtep2_ip=198.51.100.200
 	local plen=32
@@ -1227,8 +1420,8 @@ starg_exclude_ir_ipv4_ipv4()
 
 starg_exclude_ir_ipv6_ipv4()
 {
-	local ns1=ns1_v4
-	local ns2=ns2_v4
+	local ns1=$ns1_v4
+	local ns2=$ns2_v4
 	local vtep1_ip=198.51.100.100
 	local vtep2_ip=198.51.100.200
 	local plen=32
@@ -1246,8 +1439,8 @@ starg_exclude_ir_ipv6_ipv4()
 
 starg_exclude_ir_ipv4_ipv6()
 {
-	local ns1=ns1_v6
-	local ns2=ns2_v6
+	local ns1=$ns1_v6
+	local ns2=$ns2_v6
 	local vtep1_ip=2001:db8:1000::1
 	local vtep2_ip=2001:db8:2000::1
 	local plen=128
@@ -1265,8 +1458,8 @@ starg_exclude_ir_ipv4_ipv6()
 
 starg_exclude_ir_ipv6_ipv6()
 {
-	local ns1=ns1_v6
-	local ns2=ns2_v6
+	local ns1=$ns1_v6
+	local ns2=$ns2_v6
 	local vtep1_ip=2001:db8:1000::1
 	local vtep2_ip=2001:db8:2000::1
 	local plen=128
@@ -1344,8 +1537,8 @@ starg_include_ir_common()
 
 starg_include_ir_ipv4_ipv4()
 {
-	local ns1=ns1_v4
-	local ns2=ns2_v4
+	local ns1=$ns1_v4
+	local ns2=$ns2_v4
 	local vtep1_ip=198.51.100.100
 	local vtep2_ip=198.51.100.200
 	local plen=32
@@ -1363,8 +1556,8 @@ starg_include_ir_ipv4_ipv4()
 
 starg_include_ir_ipv6_ipv4()
 {
-	local ns1=ns1_v4
-	local ns2=ns2_v4
+	local ns1=$ns1_v4
+	local ns2=$ns2_v4
 	local vtep1_ip=198.51.100.100
 	local vtep2_ip=198.51.100.200
 	local plen=32
@@ -1382,8 +1575,8 @@ starg_include_ir_ipv6_ipv4()
 
 starg_include_ir_ipv4_ipv6()
 {
-	local ns1=ns1_v6
-	local ns2=ns2_v6
+	local ns1=$ns1_v6
+	local ns2=$ns2_v6
 	local vtep1_ip=2001:db8:1000::1
 	local vtep2_ip=2001:db8:2000::1
 	local plen=128
@@ -1401,8 +1594,8 @@ starg_include_ir_ipv4_ipv6()
 
 starg_include_ir_ipv6_ipv6()
 {
-	local ns1=ns1_v6
-	local ns2=ns2_v6
+	local ns1=$ns1_v6
+	local ns2=$ns2_v6
 	local vtep1_ip=2001:db8:1000::1
 	local vtep2_ip=2001:db8:2000::1
 	local plen=128
@@ -1462,8 +1655,8 @@ starg_exclude_p2mp_common()
 
 starg_exclude_p2mp_ipv4_ipv4()
 {
-	local ns1=ns1_v4
-	local ns2=ns2_v4
+	local ns1=$ns1_v4
+	local ns2=$ns2_v4
 	local mcast_grp=238.1.1.1
 	local plen=32
 	local grp=239.1.1.1
@@ -1480,8 +1673,8 @@ starg_exclude_p2mp_ipv4_ipv4()
 
 starg_exclude_p2mp_ipv6_ipv4()
 {
-	local ns1=ns1_v4
-	local ns2=ns2_v4
+	local ns1=$ns1_v4
+	local ns2=$ns2_v4
 	local mcast_grp=238.1.1.1
 	local plen=32
 	local grp=ff0e::1
@@ -1498,8 +1691,8 @@ starg_exclude_p2mp_ipv6_ipv4()
 
 starg_exclude_p2mp_ipv4_ipv6()
 {
-	local ns1=ns1_v6
-	local ns2=ns2_v6
+	local ns1=$ns1_v6
+	local ns2=$ns2_v6
 	local mcast_grp=ff0e::2
 	local plen=128
 	local grp=239.1.1.1
@@ -1516,8 +1709,8 @@ starg_exclude_p2mp_ipv4_ipv6()
 
 starg_exclude_p2mp_ipv6_ipv6()
 {
-	local ns1=ns1_v6
-	local ns2=ns2_v6
+	local ns1=$ns1_v6
+	local ns2=$ns2_v6
 	local mcast_grp=ff0e::2
 	local plen=128
 	local grp=ff0e::1
@@ -1576,8 +1769,8 @@ starg_include_p2mp_common()
 
 starg_include_p2mp_ipv4_ipv4()
 {
-	local ns1=ns1_v4
-	local ns2=ns2_v4
+	local ns1=$ns1_v4
+	local ns2=$ns2_v4
 	local mcast_grp=238.1.1.1
 	local plen=32
 	local grp=239.1.1.1
@@ -1594,8 +1787,8 @@ starg_include_p2mp_ipv4_ipv4()
 
 starg_include_p2mp_ipv6_ipv4()
 {
-	local ns1=ns1_v4
-	local ns2=ns2_v4
+	local ns1=$ns1_v4
+	local ns2=$ns2_v4
 	local mcast_grp=238.1.1.1
 	local plen=32
 	local grp=ff0e::1
@@ -1612,8 +1805,8 @@ starg_include_p2mp_ipv6_ipv4()
 
 starg_include_p2mp_ipv4_ipv6()
 {
-	local ns1=ns1_v6
-	local ns2=ns2_v6
+	local ns1=$ns1_v6
+	local ns2=$ns2_v6
 	local mcast_grp=ff0e::2
 	local plen=128
 	local grp=239.1.1.1
@@ -1630,8 +1823,8 @@ starg_include_p2mp_ipv4_ipv6()
 
 starg_include_p2mp_ipv6_ipv6()
 {
-	local ns1=ns1_v6
-	local ns2=ns2_v6
+	local ns1=$ns1_v6
+	local ns2=$ns2_v6
 	local mcast_grp=ff0e::2
 	local plen=128
 	local grp=ff0e::1
@@ -1709,8 +1902,8 @@ egress_vni_translation_common()
 
 egress_vni_translation_ipv4_ipv4()
 {
-	local ns1=ns1_v4
-	local ns2=ns2_v4
+	local ns1=$ns1_v4
+	local ns2=$ns2_v4
 	local mcast_grp=238.1.1.1
 	local plen=32
 	local proto="ipv4"
@@ -1727,8 +1920,8 @@ egress_vni_translation_ipv4_ipv4()
 
 egress_vni_translation_ipv6_ipv4()
 {
-	local ns1=ns1_v4
-	local ns2=ns2_v4
+	local ns1=$ns1_v4
+	local ns2=$ns2_v4
 	local mcast_grp=238.1.1.1
 	local plen=32
 	local proto="ipv6"
@@ -1745,8 +1938,8 @@ egress_vni_translation_ipv6_ipv4()
 
 egress_vni_translation_ipv4_ipv6()
 {
-	local ns1=ns1_v6
-	local ns2=ns2_v6
+	local ns1=$ns1_v6
+	local ns2=$ns2_v6
 	local mcast_grp=ff0e::2
 	local plen=128
 	local proto="ipv4"
@@ -1763,8 +1956,8 @@ egress_vni_translation_ipv4_ipv6()
 
 egress_vni_translation_ipv6_ipv6()
 {
-	local ns1=ns1_v6
-	local ns2=ns2_v6
+	local ns1=$ns1_v6
+	local ns2=$ns2_v6
 	local mcast_grp=ff0e::2
 	local plen=128
 	local proto="ipv6"
@@ -1929,8 +2122,8 @@ all_zeros_mdb_common()
 
 all_zeros_mdb_ipv4()
 {
-	local ns1=ns1_v4
-	local ns2=ns2_v4
+	local ns1=$ns1_v4
+	local ns2=$ns2_v4
 	local vtep1_ip=198.51.100.101
 	local vtep2_ip=198.51.100.102
 	local vtep3_ip=198.51.100.103
@@ -1947,8 +2140,8 @@ all_zeros_mdb_ipv4()
 
 all_zeros_mdb_ipv6()
 {
-	local ns1=ns1_v6
-	local ns2=ns2_v6
+	local ns1=$ns1_v6
+	local ns2=$ns2_v6
 	local vtep1_ip=2001:db8:1000::1
 	local vtep2_ip=2001:db8:2000::1
 	local vtep3_ip=2001:db8:3000::1
@@ -2021,8 +2214,8 @@ mdb_fdb_common()
 
 mdb_fdb_ipv4_ipv4()
 {
-	local ns1=ns1_v4
-	local ns2=ns2_v4
+	local ns1=$ns1_v4
+	local ns2=$ns2_v4
 	local vtep1_ip=198.51.100.100
 	local vtep2_ip=198.51.100.200
 	local plen=32
@@ -2040,8 +2233,8 @@ mdb_fdb_ipv4_ipv4()
 
 mdb_fdb_ipv6_ipv4()
 {
-	local ns1=ns1_v4
-	local ns2=ns2_v4
+	local ns1=$ns1_v4
+	local ns2=$ns2_v4
 	local vtep1_ip=198.51.100.100
 	local vtep2_ip=198.51.100.200
 	local plen=32
@@ -2059,8 +2252,8 @@ mdb_fdb_ipv6_ipv4()
 
 mdb_fdb_ipv4_ipv6()
 {
-	local ns1=ns1_v6
-	local ns2=ns2_v6
+	local ns1=$ns1_v6
+	local ns2=$ns2_v6
 	local vtep1_ip=2001:db8:1000::1
 	local vtep2_ip=2001:db8:2000::1
 	local plen=128
@@ -2078,8 +2271,8 @@ mdb_fdb_ipv4_ipv6()
 
 mdb_fdb_ipv6_ipv6()
 {
-	local ns1=ns1_v6
-	local ns2=ns2_v6
+	local ns1=$ns1_v6
+	local ns2=$ns2_v6
 	local vtep1_ip=2001:db8:1000::1
 	local vtep2_ip=2001:db8:2000::1
 	local plen=128
@@ -2166,7 +2359,7 @@ mdb_torture_common()
 
 mdb_torture_ipv4_ipv4()
 {
-	local ns1=ns1_v4
+	local ns1=$ns1_v4
 	local vtep1_ip=198.51.100.100
 	local vtep2_ip=198.51.100.200
 	local grp1=239.1.1.1
@@ -2183,7 +2376,7 @@ mdb_torture_ipv4_ipv4()
 
 mdb_torture_ipv6_ipv4()
 {
-	local ns1=ns1_v4
+	local ns1=$ns1_v4
 	local vtep1_ip=198.51.100.100
 	local vtep2_ip=198.51.100.200
 	local grp1=ff0e::1
@@ -2200,7 +2393,7 @@ mdb_torture_ipv6_ipv4()
 
 mdb_torture_ipv4_ipv6()
 {
-	local ns1=ns1_v6
+	local ns1=$ns1_v6
 	local vtep1_ip=2001:db8:1000::1
 	local vtep2_ip=2001:db8:2000::1
 	local grp1=239.1.1.1
@@ -2217,7 +2410,7 @@ mdb_torture_ipv4_ipv6()
 
 mdb_torture_ipv6_ipv6()
 {
-	local ns1=ns1_v6
+	local ns1=$ns1_v6
 	local vtep1_ip=2001:db8:1000::1
 	local vtep2_ip=2001:db8:2000::1
 	local grp1=ff0e::1
@@ -2296,9 +2489,9 @@ if [ ! -x "$(command -v jq)" ]; then
 	exit $ksft_skip
 fi
 
-bridge mdb help 2>&1 | grep -q "get"
+bridge mdb help 2>&1 | grep -q "flush"
 if [ $? -ne 0 ]; then
-   echo "SKIP: iproute2 bridge too old, missing VXLAN MDB get support"
+   echo "SKIP: iproute2 bridge too old, missing VXLAN MDB flush support"
    exit $ksft_skip
 fi
 
diff --git a/tools/testing/selftests/net/test_vxlan_nolocalbypass.sh b/tools/testing/selftests/net/test_vxlan_nolocalbypass.sh
index f75212bf142c..b8805983b728 100755
--- a/tools/testing/selftests/net/test_vxlan_nolocalbypass.sh
+++ b/tools/testing/selftests/net/test_vxlan_nolocalbypass.sh
@@ -9,9 +9,8 @@
 # option and verifies that packets are no longer received by the second VXLAN
 # device.
 
+source lib.sh
 ret=0
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
 
 TESTS="
 	nolocalbypass
@@ -98,20 +97,19 @@ tc_check_packets()
 
 setup()
 {
-	ip netns add ns1
+	setup_ns ns1
 
-	ip -n ns1 link set dev lo up
-	ip -n ns1 address add 192.0.2.1/32 dev lo
-	ip -n ns1 address add 198.51.100.1/32 dev lo
+	ip -n $ns1 address add 192.0.2.1/32 dev lo
+	ip -n $ns1 address add 198.51.100.1/32 dev lo
 
-	ip -n ns1 link add name vx0 up type vxlan id 100 local 198.51.100.1 \
+	ip -n $ns1 link add name vx0 up type vxlan id 100 local 198.51.100.1 \
 		dstport 4789 nolearning
-	ip -n ns1 link add name vx1 up type vxlan id 100 dstport 4790
+	ip -n $ns1 link add name vx1 up type vxlan id 100 dstport 4790
 }
 
 cleanup()
 {
-	ip netns del ns1 &> /dev/null
+	cleanup_ns $ns1
 }
 
 ################################################################################
@@ -122,40 +120,40 @@ nolocalbypass()
 	local smac=00:01:02:03:04:05
 	local dmac=00:0a:0b:0c:0d:0e
 
-	run_cmd "bridge -n ns1 fdb add $dmac dev vx0 self static dst 192.0.2.1 port 4790"
+	run_cmd "bridge -n $ns1 fdb add $dmac dev vx0 self static dst 192.0.2.1 port 4790"
 
-	run_cmd "tc -n ns1 qdisc add dev vx1 clsact"
-	run_cmd "tc -n ns1 filter add dev vx1 ingress pref 1 handle 101 proto all flower src_mac $smac dst_mac $dmac action pass"
+	run_cmd "tc -n $ns1 qdisc add dev vx1 clsact"
+	run_cmd "tc -n $ns1 filter add dev vx1 ingress pref 1 handle 101 proto all flower src_mac $smac dst_mac $dmac action pass"
 
-	run_cmd "tc -n ns1 qdisc add dev lo clsact"
-	run_cmd "tc -n ns1 filter add dev lo ingress pref 1 handle 101 proto ip flower ip_proto udp dst_port 4790 action drop"
+	run_cmd "tc -n $ns1 qdisc add dev lo clsact"
+	run_cmd "tc -n $ns1 filter add dev lo ingress pref 1 handle 101 proto ip flower ip_proto udp dst_port 4790 action drop"
 
-	run_cmd "ip -n ns1 -d -j link show dev vx0 | jq -e '.[][\"linkinfo\"][\"info_data\"][\"localbypass\"] == true'"
+	run_cmd "ip -n $ns1 -d -j link show dev vx0 | jq -e '.[][\"linkinfo\"][\"info_data\"][\"localbypass\"] == true'"
 	log_test $? 0 "localbypass enabled"
 
-	run_cmd "ip netns exec ns1 mausezahn vx0 -a $smac -b $dmac -c 1 -p 100 -q"
+	run_cmd "ip netns exec $ns1 mausezahn vx0 -a $smac -b $dmac -c 1 -p 100 -q"
 
-	tc_check_packets "ns1" "dev vx1 ingress" 101 1
+	tc_check_packets "$ns1" "dev vx1 ingress" 101 1
 	log_test $? 0 "Packet received by local VXLAN device - localbypass"
 
-	run_cmd "ip -n ns1 link set dev vx0 type vxlan nolocalbypass"
+	run_cmd "ip -n $ns1 link set dev vx0 type vxlan nolocalbypass"
 
-	run_cmd "ip -n ns1 -d -j link show dev vx0 | jq -e '.[][\"linkinfo\"][\"info_data\"][\"localbypass\"] == false'"
+	run_cmd "ip -n $ns1 -d -j link show dev vx0 | jq -e '.[][\"linkinfo\"][\"info_data\"][\"localbypass\"] == false'"
 	log_test $? 0 "localbypass disabled"
 
-	run_cmd "ip netns exec ns1 mausezahn vx0 -a $smac -b $dmac -c 1 -p 100 -q"
+	run_cmd "ip netns exec $ns1 mausezahn vx0 -a $smac -b $dmac -c 1 -p 100 -q"
 
-	tc_check_packets "ns1" "dev vx1 ingress" 101 1
+	tc_check_packets "$ns1" "dev vx1 ingress" 101 1
 	log_test $? 0 "Packet not received by local VXLAN device - nolocalbypass"
 
-	run_cmd "ip -n ns1 link set dev vx0 type vxlan localbypass"
+	run_cmd "ip -n $ns1 link set dev vx0 type vxlan localbypass"
 
-	run_cmd "ip -n ns1 -d -j link show dev vx0 | jq -e '.[][\"linkinfo\"][\"info_data\"][\"localbypass\"] == true'"
+	run_cmd "ip -n $ns1 -d -j link show dev vx0 | jq -e '.[][\"linkinfo\"][\"info_data\"][\"localbypass\"] == true'"
 	log_test $? 0 "localbypass enabled"
 
-	run_cmd "ip netns exec ns1 mausezahn vx0 -a $smac -b $dmac -c 1 -p 100 -q"
+	run_cmd "ip netns exec $ns1 mausezahn vx0 -a $smac -b $dmac -c 1 -p 100 -q"
 
-	tc_check_packets "ns1" "dev vx1 ingress" 101 2
+	tc_check_packets "$ns1" "dev vx1 ingress" 101 2
 	log_test $? 0 "Packet received by local VXLAN device - localbypass"
 }
 
diff --git a/tools/testing/selftests/net/test_vxlan_under_vrf.sh b/tools/testing/selftests/net/test_vxlan_under_vrf.sh
index 1fd1250ebc66..ae8fbe3f0779 100755
--- a/tools/testing/selftests/net/test_vxlan_under_vrf.sh
+++ b/tools/testing/selftests/net/test_vxlan_under_vrf.sh
@@ -43,15 +43,14 @@
 # This tests both the connectivity between vm-1 and vm-2, and that the underlay
 # can be moved in and out of the vrf by unsetting and setting veth0's master.
 
+source lib.sh
 set -e
 
 cleanup() {
     ip link del veth-hv-1 2>/dev/null || true
     ip link del veth-tap 2>/dev/null || true
 
-    for ns in hv-1 hv-2 vm-1 vm-2; do
-        ip netns del $ns 2>/dev/null || true
-    done
+    cleanup_ns $hv_1 $hv_2 $vm_1 $vm_2
 }
 
 # Clean start
@@ -60,72 +59,75 @@ cleanup &> /dev/null
 [[ $1 == "clean" ]] && exit 0
 
 trap cleanup EXIT
+setup_ns hv_1 hv_2 vm_1 vm_2
+hv[1]=$hv_1
+hv[2]=$hv_2
+vm[1]=$vm_1
+vm[2]=$vm_2
 
 # Setup "Hypervisors" simulated with netns
 ip link add veth-hv-1 type veth peer name veth-hv-2
 setup-hv-networking() {
-    hv=$1
+    id=$1
 
-    ip netns add hv-$hv
-    ip link set veth-hv-$hv netns hv-$hv
-    ip -netns hv-$hv link set veth-hv-$hv name veth0
+    ip link set veth-hv-$id netns ${hv[$id]}
+    ip -netns ${hv[$id]} link set veth-hv-$id name veth0
 
-    ip -netns hv-$hv link add vrf-underlay type vrf table 1
-    ip -netns hv-$hv link set vrf-underlay up
-    ip -netns hv-$hv addr add 172.16.0.$hv/24 dev veth0
-    ip -netns hv-$hv link set veth0 up
+    ip -netns ${hv[$id]} link add vrf-underlay type vrf table 1
+    ip -netns ${hv[$id]} link set vrf-underlay up
+    ip -netns ${hv[$id]} addr add 172.16.0.$id/24 dev veth0
+    ip -netns ${hv[$id]} link set veth0 up
 
-    ip -netns hv-$hv link add br0 type bridge
-    ip -netns hv-$hv link set br0 up
+    ip -netns ${hv[$id]} link add br0 type bridge
+    ip -netns ${hv[$id]} link set br0 up
 
-    ip -netns hv-$hv link add vxlan0 type vxlan id 10 local 172.16.0.$hv dev veth0 dstport 4789
-    ip -netns hv-$hv link set vxlan0 master br0
-    ip -netns hv-$hv link set vxlan0 up
+    ip -netns ${hv[$id]} link add vxlan0 type vxlan id 10 local 172.16.0.$id dev veth0 dstport 4789
+    ip -netns ${hv[$id]} link set vxlan0 master br0
+    ip -netns ${hv[$id]} link set vxlan0 up
 }
 setup-hv-networking 1
 setup-hv-networking 2
 
 # Check connectivity between HVs by pinging hv-2 from hv-1
 echo -n "Checking HV connectivity                                           "
-ip netns exec hv-1 ping -c 1 -W 1 172.16.0.2 &> /dev/null || (echo "[FAIL]"; false)
+ip netns exec $hv_1 ping -c 1 -W 1 172.16.0.2 &> /dev/null || (echo "[FAIL]"; false)
 echo "[ OK ]"
 
 # Setups a "VM" simulated by a netns an a veth pair
 setup-vm() {
     id=$1
 
-    ip netns add vm-$id
     ip link add veth-tap type veth peer name veth-hv
 
-    ip link set veth-tap netns hv-$id
-    ip -netns hv-$id link set veth-tap master br0
-    ip -netns hv-$id link set veth-tap up
+    ip link set veth-tap netns ${hv[$id]}
+    ip -netns ${hv[$id]} link set veth-tap master br0
+    ip -netns ${hv[$id]} link set veth-tap up
 
     ip link set veth-hv address 02:1d:8d:dd:0c:6$id
 
-    ip link set veth-hv netns vm-$id
-    ip -netns vm-$id addr add 10.0.0.$id/24 dev veth-hv
-    ip -netns vm-$id link set veth-hv up
+    ip link set veth-hv netns ${vm[$id]}
+    ip -netns ${vm[$id]} addr add 10.0.0.$id/24 dev veth-hv
+    ip -netns ${vm[$id]} link set veth-hv up
 }
 setup-vm 1
 setup-vm 2
 
 # Setup VTEP routes to make ARP work
-bridge -netns hv-1 fdb add 00:00:00:00:00:00 dev vxlan0 dst 172.16.0.2 self permanent
-bridge -netns hv-2 fdb add 00:00:00:00:00:00 dev vxlan0 dst 172.16.0.1 self permanent
+bridge -netns $hv_1 fdb add 00:00:00:00:00:00 dev vxlan0 dst 172.16.0.2 self permanent
+bridge -netns $hv_2 fdb add 00:00:00:00:00:00 dev vxlan0 dst 172.16.0.1 self permanent
 
 echo -n "Check VM connectivity through VXLAN (underlay in the default VRF)  "
-ip netns exec vm-1 ping -c 1 -W 1 10.0.0.2 &> /dev/null || (echo "[FAIL]"; false)
+ip netns exec $vm_1 ping -c 1 -W 1 10.0.0.2 &> /dev/null || (echo "[FAIL]"; false)
 echo "[ OK ]"
 
 # Move the underlay to a non-default VRF
-ip -netns hv-1 link set veth0 vrf vrf-underlay
-ip -netns hv-1 link set vxlan0 down
-ip -netns hv-1 link set vxlan0 up
-ip -netns hv-2 link set veth0 vrf vrf-underlay
-ip -netns hv-2 link set vxlan0 down
-ip -netns hv-2 link set vxlan0 up
+ip -netns $hv_1 link set veth0 vrf vrf-underlay
+ip -netns $hv_1 link set vxlan0 down
+ip -netns $hv_1 link set vxlan0 up
+ip -netns $hv_2 link set veth0 vrf vrf-underlay
+ip -netns $hv_2 link set vxlan0 down
+ip -netns $hv_2 link set vxlan0 up
 
 echo -n "Check VM connectivity through VXLAN (underlay in a VRF)            "
-ip netns exec vm-1 ping -c 1 -W 1 10.0.0.2 &> /dev/null || (echo "[FAIL]"; false)
+ip netns exec $vm_1 ping -c 1 -W 1 10.0.0.2 &> /dev/null || (echo "[FAIL]"; false)
 echo "[ OK ]"
diff --git a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh
index 8c3ac0a72545..6127a78ee988 100755
--- a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh
+++ b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh
@@ -78,10 +78,8 @@
 #
 #
 # This test tests the new vxlan vnifiltering api
-
+source lib.sh
 ret=0
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
 
 # all tests in this script. Can be overridden with -t option
 TESTS="
@@ -148,18 +146,18 @@ run_cmd()
 }
 
 check_hv_connectivity() {
-	ip netns exec hv-1 ping -c 1 -W 1 $1 &>/dev/null
+	ip netns exec $hv_1 ping -c 1 -W 1 $1 &>/dev/null
 	sleep 1
-	ip netns exec hv-1 ping -c 1 -W 1 $2 &>/dev/null
+	ip netns exec $hv_1 ping -c 1 -W 1 $2 &>/dev/null
 
 	return $?
 }
 
 check_vm_connectivity() {
-	run_cmd "ip netns exec vm-11 ping -c 1 -W 1 10.0.10.12"
+	run_cmd "ip netns exec $vm_11 ping -c 1 -W 1 10.0.10.12"
 	log_test $? 0 "VM connectivity over $1 (ipv4 default rdst)"
 
-	run_cmd "ip netns exec vm-21 ping -c 1 -W 1 10.0.10.22"
+	run_cmd "ip netns exec $vm_21 ping -c 1 -W 1 10.0.10.22"
 	log_test $? 0 "VM connectivity over $1 (ipv6 default rdst)"
 }
 
@@ -167,26 +165,23 @@ cleanup() {
 	ip link del veth-hv-1 2>/dev/null || true
 	ip link del vethhv-11 vethhv-12 vethhv-21 vethhv-22 2>/dev/null || true
 
-	for ns in hv-1 hv-2 vm-11 vm-21 vm-12 vm-22 vm-31 vm-32; do
-		ip netns del $ns 2>/dev/null || true
-	done
+	cleanup_ns $hv_1 $hv_2 $vm_11 $vm_21 $vm_12 $vm_22 $vm_31 $vm_32
 }
 
 trap cleanup EXIT
 
 setup-hv-networking() {
-	hv=$1
+	id=$1
 	local1=$2
 	mask1=$3
 	local2=$4
 	mask2=$5
 
-	ip netns add hv-$hv
-	ip link set veth-hv-$hv netns hv-$hv
-	ip -netns hv-$hv link set veth-hv-$hv name veth0
-	ip -netns hv-$hv addr add $local1/$mask1 dev veth0
-	ip -netns hv-$hv addr add $local2/$mask2 dev veth0
-	ip -netns hv-$hv link set veth0 up
+	ip link set veth-hv-$id netns ${hv[$id]}
+	ip -netns ${hv[$id]} link set veth-hv-$id name veth0
+	ip -netns ${hv[$id]} addr add $local1/$mask1 dev veth0
+	ip -netns ${hv[$id]} addr add $local2/$mask2 dev veth0
+	ip -netns ${hv[$id]} link set veth0 up
 }
 
 # Setups a "VM" simulated by a netns an a veth pair
@@ -208,21 +203,20 @@ setup-vm() {
 	lastvxlandev=""
 
 	# create bridge
-	ip -netns hv-$hvid link add br$brid type bridge vlan_filtering 1 vlan_default_pvid 0 \
+	ip -netns ${hv[$hvid]} link add br$brid type bridge vlan_filtering 1 vlan_default_pvid 0 \
 		mcast_snooping 0
-	ip -netns hv-$hvid link set br$brid up
+	ip -netns ${hv[$hvid]} link set br$brid up
 
 	# create vm namespace and interfaces and connect to hypervisor
 	# namespace
-	ip netns add vm-$vmid
 	hvvethif="vethhv-$vmid"
 	vmvethif="veth-$vmid"
 	ip link add $hvvethif type veth peer name $vmvethif
-	ip link set $hvvethif netns hv-$hvid
-	ip link set $vmvethif netns vm-$vmid
-	ip -netns hv-$hvid link set $hvvethif up
-	ip -netns vm-$vmid link set $vmvethif up
-	ip -netns hv-$hvid link set $hvvethif master br$brid
+	ip link set $hvvethif netns ${hv[$hvid]}
+	ip link set $vmvethif netns ${vm[$vmid]}
+	ip -netns ${hv[$hvid]} link set $hvvethif up
+	ip -netns ${vm[$vmid]} link set $vmvethif up
+	ip -netns ${hv[$hvid]} link set $hvvethif master br$brid
 
 	# configure VM vlan/vni filtering on hypervisor
 	for vmap in $(echo $vattrs | cut -d "," -f1- --output-delimiter=' ')
@@ -234,9 +228,9 @@ setup-vm() {
 	local vtype=$(echo $vmap | awk -F'-' '{print ($5)}')
 	local port=$(echo $vmap | awk -F'-' '{print ($6)}')
 
-	ip -netns vm-$vmid link add name $vmvethif.$vid link $vmvethif type vlan id $vid
-	ip -netns vm-$vmid addr add 10.0.$vid.$vmid/24 dev $vmvethif.$vid
-	ip -netns vm-$vmid link set $vmvethif.$vid up
+	ip -netns ${vm[$vmid]} link add name $vmvethif.$vid link $vmvethif type vlan id $vid
+	ip -netns ${vm[$vmid]} addr add 10.0.$vid.$vmid/24 dev $vmvethif.$vid
+	ip -netns ${vm[$vmid]} link set $vmvethif.$vid up
 
 	tid=$vid
 	vxlandev="vxlan$brid"
@@ -268,35 +262,35 @@ setup-vm() {
 
 	# create vxlan device
 	if [ "$vxlandev" != "$lastvxlandev" ]; then
-	     ip -netns hv-$hvid link add $vxlandev type vxlan local $localip $vxlandevflags dev veth0 2>/dev/null
-	     ip -netns hv-$hvid link set $vxlandev master br$brid
-	     ip -netns hv-$hvid link set $vxlandev up
+	     ip -netns ${hv[$hvid]} link add $vxlandev type vxlan local $localip $vxlandevflags dev veth0 2>/dev/null
+	     ip -netns ${hv[$hvid]} link set $vxlandev master br$brid
+	     ip -netns ${hv[$hvid]} link set $vxlandev up
 	     lastvxlandev=$vxlandev
 	fi
 
 	# add vlan
-	bridge -netns hv-$hvid vlan add vid $vid dev $hvvethif
-	bridge -netns hv-$hvid vlan add vid $vid pvid dev $vxlandev
+	bridge -netns ${hv[$hvid]} vlan add vid $vid dev $hvvethif
+	bridge -netns ${hv[$hvid]} vlan add vid $vid pvid dev $vxlandev
 
 	# Add bridge vni filter for tx
 	if [[ -n $vtype && $vtype == "metadata" || $vtype == "vnifilter" || $vtype == "vnifilterg" ]]; then
-	   bridge -netns hv-$hvid link set dev $vxlandev vlan_tunnel on
-	   bridge -netns hv-$hvid vlan add dev $vxlandev vid $vid tunnel_info id $tid
+	   bridge -netns ${hv[$hvid]} link set dev $vxlandev vlan_tunnel on
+	   bridge -netns ${hv[$hvid]} vlan add dev $vxlandev vid $vid tunnel_info id $tid
 	fi
 
 	if [[ -n $vtype && $vtype == "metadata" ]]; then
-	   bridge -netns hv-$hvid fdb add 00:00:00:00:00:00 dev $vxlandev \
+	   bridge -netns ${hv[$hvid]} fdb add 00:00:00:00:00:00 dev $vxlandev \
 								src_vni $tid vni $tid dst $group self
 	elif [[ -n $vtype && $vtype == "vnifilter" ]]; then
 	   # Add per vni rx filter with 'bridge vni' api
-	   bridge -netns hv-$hvid vni add dev $vxlandev vni $tid
+	   bridge -netns ${hv[$hvid]} vni add dev $vxlandev vni $tid
 	elif [[ -n $vtype && $vtype == "vnifilterg" ]]; then
 	   # Add per vni group config with 'bridge vni' api
 	   if [ -n "$group" ]; then
 		if [ $mcast -eq 1 ]; then
-			bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group $group
+			bridge -netns ${hv[$hvid]} vni add dev $vxlandev vni $tid group $group
 		else
-			bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote $group
+			bridge -netns ${hv[$hvid]} vni add dev $vxlandev vni $tid remote $group
 		fi
 	   fi
 	fi
@@ -306,14 +300,14 @@ setup-vm() {
 setup_vnifilter_api()
 {
 	ip link add veth-host type veth peer name veth-testns
-	ip netns add testns
-	ip link set veth-testns netns testns
+	setup_ns testns
+	ip link set veth-testns netns $testns
 }
 
 cleanup_vnifilter_api()
 {
 	ip link del veth-host 2>/dev/null || true
-	ip netns del testns 2>/dev/null || true
+	ip netns del $testns 2>/dev/null || true
 }
 
 # tests vxlan filtering api
@@ -331,52 +325,52 @@ vxlan_vnifilter_api()
 
 	# Duplicate vni test
 	# create non-vnifiltering traditional vni device
-	run_cmd "ip -netns testns link add vxlan100 type vxlan id 100 local $localip dev veth-testns dstport 4789"
+	run_cmd "ip -netns $testns link add vxlan100 type vxlan id 100 local $localip dev veth-testns dstport 4789"
 	log_test $? 0 "Create traditional vxlan device"
 
 	# create vni filtering device
-	run_cmd "ip -netns testns link add vxlan-ext1 type vxlan vnifilter local $localip dev veth-testns dstport 4789"
+	run_cmd "ip -netns $testns link add vxlan-ext1 type vxlan vnifilter local $localip dev veth-testns dstport 4789"
 	log_test $? 1 "Cannot create vnifilter device without external flag"
 
-	run_cmd "ip -netns testns link add vxlan-ext1 type vxlan external vnifilter local $localip dev veth-testns dstport 4789"
+	run_cmd "ip -netns $testns link add vxlan-ext1 type vxlan external vnifilter local $localip dev veth-testns dstport 4789"
 	log_test $? 0 "Creating external vxlan device with vnifilter flag"
 
-	run_cmd "bridge -netns testns vni add dev vxlan-ext1 vni 100"
+	run_cmd "bridge -netns $testns vni add dev vxlan-ext1 vni 100"
 	log_test $? 0 "Cannot set in-use vni id on vnifiltering device"
 
-	run_cmd "bridge -netns testns vni add dev vxlan-ext1 vni 200"
+	run_cmd "bridge -netns $testns vni add dev vxlan-ext1 vni 200"
 	log_test $? 0 "Set new vni id on vnifiltering device"
 
-	run_cmd "ip -netns testns link add vxlan-ext2 type vxlan external vnifilter local $localip dev veth-testns dstport 4789"
+	run_cmd "ip -netns $testns link add vxlan-ext2 type vxlan external vnifilter local $localip dev veth-testns dstport 4789"
 	log_test $? 0 "Create second external vxlan device with vnifilter flag"
 
-	run_cmd "bridge -netns testns vni add dev vxlan-ext2 vni 200"
+	run_cmd "bridge -netns $testns vni add dev vxlan-ext2 vni 200"
 	log_test $? 255 "Cannot set in-use vni id on vnifiltering device"
 
-	run_cmd "bridge -netns testns vni add dev vxlan-ext2 vni 300"
+	run_cmd "bridge -netns $testns vni add dev vxlan-ext2 vni 300"
 	log_test $? 0 "Set new vni id on vnifiltering device"
 
 	# check in bridge vni show
-	run_cmd "bridge -netns testns vni add dev vxlan-ext2 vni 300"
+	run_cmd "bridge -netns $testns vni add dev vxlan-ext2 vni 300"
 	log_test $? 0 "Update vni id on vnifiltering device"
 
-	run_cmd "bridge -netns testns vni add dev vxlan-ext2 vni 400"
+	run_cmd "bridge -netns $testns vni add dev vxlan-ext2 vni 400"
 	log_test $? 0 "Add new vni id on vnifiltering device"
 
 	# add multicast group per vni
-	run_cmd "bridge -netns testns vni add dev vxlan-ext1 vni 200 group $group"
+	run_cmd "bridge -netns $testns vni add dev vxlan-ext1 vni 200 group $group"
 	log_test $? 0 "Set multicast group on existing vni"
 
 	# add multicast group per vni
-	run_cmd "bridge -netns testns vni add dev vxlan-ext2 vni 300 group $group"
+	run_cmd "bridge -netns $testns vni add dev vxlan-ext2 vni 300 group $group"
 	log_test $? 0 "Set multicast group on existing vni"
 
 	# set vnifilter on an existing external vxlan device
-	run_cmd "ip -netns testns link set dev vxlan-ext1 type vxlan external vnifilter"
+	run_cmd "ip -netns $testns link set dev vxlan-ext1 type vxlan external vnifilter"
 	log_test $? 2 "Cannot set vnifilter flag on a device"
 
 	# change vxlan vnifilter flag
-	run_cmd "ip -netns testns link set dev vxlan-ext1 type vxlan external novnifilter"
+	run_cmd "ip -netns $testns link set dev vxlan-ext1 type vxlan external novnifilter"
 	log_test $? 2 "Cannot unset vnifilter flag on a device"
 }
 
@@ -390,12 +384,20 @@ vxlan_vnifilter_datapath()
 	hv1addr2="2002:fee1::1"
 	hv2addr2="2002:fee1::2"
 
+	setup_ns hv_1 hv_2
+	hv[1]=$hv_1
+	hv[2]=$hv_2
 	ip link add veth-hv-1 type veth peer name veth-hv-2
 	setup-hv-networking 1 $hv1addr1 24 $hv1addr2 64 $hv2addr1 $hv2addr2
 	setup-hv-networking 2 $hv2addr1 24 $hv2addr2 64 $hv1addr1 $hv1addr2
 
         check_hv_connectivity hv2addr1 hv2addr2
 
+	setup_ns vm_11 vm_21 vm_12 vm_22
+	vm[11]=$vm_11
+	vm[21]=$vm_21
+	vm[12]=$vm_12
+	vm[22]=$vm_22
 	setup-vm 1 11 1 10-v4-$hv1addr1-$hv2addr1-vnifilter,20-v4-$hv1addr1-$hv2addr1-vnifilter 0
 	setup-vm 1 21 2 10-v6-$hv1addr2-$hv2addr2-vnifilter,20-v6-$hv1addr2-$hv2addr2-vnifilter 0
 
@@ -415,12 +417,20 @@ vxlan_vnifilter_datapath_pervni()
 	hv1addr2="2002:fee1::1"
 	hv2addr2="2002:fee1::2"
 
+	setup_ns hv_1 hv_2
+	hv[1]=$hv_1
+	hv[2]=$hv_2
 	ip link add veth-hv-1 type veth peer name veth-hv-2
 	setup-hv-networking 1 $hv1addr1 24 $hv1addr2 64
 	setup-hv-networking 2 $hv2addr1 24 $hv2addr2 64
 
         check_hv_connectivity hv2addr1 hv2addr2
 
+	setup_ns vm_11 vm_21 vm_12 vm_22
+	vm[11]=$vm_11
+	vm[21]=$vm_21
+	vm[12]=$vm_12
+	vm[22]=$vm_22
 	setup-vm 1 11 1 10-v4-$hv1addr1-$hv2addr1-vnifilterg,20-v4-$hv1addr1-$hv2addr1-vnifilterg 0
 	setup-vm 1 21 2 10-v6-$hv1addr2-$hv2addr2-vnifilterg,20-v6-$hv1addr2-$hv2addr2-vnifilterg 0
 
@@ -440,12 +450,20 @@ vxlan_vnifilter_datapath_mgroup()
         group="239.1.1.100"
         group6="ff07::1"
 
+	setup_ns hv_1 hv_2
+	hv[1]=$hv_1
+	hv[2]=$hv_2
 	ip link add veth-hv-1 type veth peer name veth-hv-2
 	setup-hv-networking 1 $hv1addr1 24 $hv1addr2 64
 	setup-hv-networking 2 $hv2addr1 24 $hv2addr2 64
 
         check_hv_connectivity hv2addr1 hv2addr2
 
+	setup_ns vm_11 vm_21 vm_12 vm_22
+	vm[11]=$vm_11
+	vm[21]=$vm_21
+	vm[12]=$vm_12
+	vm[22]=$vm_22
 	setup-vm 1 11 1 10-v4-$hv1addr1-$group-vnifilter,20-v4-$hv1addr1-$group-vnifilter 1
 	setup-vm 1 21 2 "10-v6-$hv1addr2-$group6-vnifilter,20-v6-$hv1addr2-$group6-vnifilter" 1
 
@@ -464,12 +482,20 @@ vxlan_vnifilter_datapath_mgroup_pervni()
         group="239.1.1.100"
         group6="ff07::1"
 
+	setup_ns hv_1 hv_2
+	hv[1]=$hv_1
+	hv[2]=$hv_2
 	ip link add veth-hv-1 type veth peer name veth-hv-2
 	setup-hv-networking 1 $hv1addr1 24 $hv1addr2 64
 	setup-hv-networking 2 $hv2addr1 24 $hv2addr2 64
 
         check_hv_connectivity hv2addr1 hv2addr2
 
+	setup_ns vm_11 vm_21 vm_12 vm_22
+	vm[11]=$vm_11
+	vm[21]=$vm_21
+	vm[12]=$vm_12
+	vm[22]=$vm_22
 	setup-vm 1 11 1 10-v4-$hv1addr1-$group-vnifilterg,20-v4-$hv1addr1-$group-vnifilterg 1
 	setup-vm 1 21 2 10-v6-$hv1addr2-$group6-vnifilterg,20-v6-$hv1addr2-$group6-vnifilterg 1
 
@@ -486,12 +512,22 @@ vxlan_vnifilter_metadata_and_traditional_mix()
 	hv1addr2="2002:fee1::1"
 	hv2addr2="2002:fee1::2"
 
+	setup_ns hv_1 hv_2
+	hv[1]=$hv_1
+	hv[2]=$hv_2
 	ip link add veth-hv-1 type veth peer name veth-hv-2
 	setup-hv-networking 1 $hv1addr1 24 $hv1addr2 64
 	setup-hv-networking 2 $hv2addr1 24 $hv2addr2 64
 
         check_hv_connectivity hv2addr1 hv2addr2
 
+	setup_ns vm_11 vm_21 vm_31 vm_12 vm_22 vm_32
+	vm[11]=$vm_11
+	vm[21]=$vm_21
+	vm[31]=$vm_31
+	vm[12]=$vm_12
+	vm[22]=$vm_22
+	vm[32]=$vm_32
 	setup-vm 1 11 1 10-v4-$hv1addr1-$hv2addr1-vnifilter,20-v4-$hv1addr1-$hv2addr1-vnifilter 0
 	setup-vm 1 21 2 10-v6-$hv1addr2-$hv2addr2-vnifilter,20-v6-$hv1addr2-$hv2addr2-vnifilter 0
 	setup-vm 1 31 3 30-v4-$hv1addr1-$hv2addr1-default-4790,40-v6-$hv1addr2-$hv2addr2-default-4790,50-v4-$hv1addr1-$hv2addr1-metadata-4791 0
@@ -504,13 +540,13 @@ vxlan_vnifilter_metadata_and_traditional_mix()
         check_vm_connectivity "vnifiltering vxlan pervni remote mix"
 
 	# check VM connectivity over traditional/non-vxlan filtering vxlan devices
-	run_cmd "ip netns exec vm-31 ping -c 1 -W 1 10.0.30.32"
+	run_cmd "ip netns exec $vm_31 ping -c 1 -W 1 10.0.30.32"
         log_test $? 0 "VM connectivity over traditional vxlan (ipv4 default rdst)"
 
-	run_cmd "ip netns exec vm-31 ping -c 1 -W 1 10.0.40.32"
+	run_cmd "ip netns exec $vm_31 ping -c 1 -W 1 10.0.40.32"
         log_test $? 0 "VM connectivity over traditional vxlan (ipv6 default rdst)"
 
-	run_cmd "ip netns exec vm-31 ping -c 1 -W 1 10.0.50.32"
+	run_cmd "ip netns exec $vm_31 ping -c 1 -W 1 10.0.50.32"
         log_test $? 0 "VM connectivity over metadata nonfiltering vxlan (ipv4 default rdst)"
 }
 
diff --git a/tools/testing/selftests/net/toeplitz.sh b/tools/testing/selftests/net/toeplitz.sh
index da5bfd834eff..8ff172f7bb1b 100755
--- a/tools/testing/selftests/net/toeplitz.sh
+++ b/tools/testing/selftests/net/toeplitz.sh
@@ -147,14 +147,14 @@ setup() {
 	setup_loopback_environment "${DEV}"
 
 	# Set up server_ns namespace and client_ns namespace
-	setup_macvlan_ns "${DEV}" server_ns server \
+	setup_macvlan_ns "${DEV}" $server_ns server \
 	"${SERVER_MAC}" "${SERVER_IP}"
-	setup_macvlan_ns "${DEV}" client_ns client \
+	setup_macvlan_ns "${DEV}" $client_ns client \
 	"${CLIENT_MAC}" "${CLIENT_IP}"
 }
 
 cleanup() {
-	cleanup_macvlan_ns server_ns server client_ns client
+	cleanup_macvlan_ns $server_ns server $client_ns client
 	cleanup_loopback "${DEV}"
 }
 
@@ -170,22 +170,22 @@ if [[ "${TEST_RSS}" = true ]]; then
 	# RPS/RFS must be disabled because they move packets between cpus,
 	# which breaks the PACKET_FANOUT_CPU identification of RSS decisions.
 	eval "$(get_disable_rfs_cmd) $(get_disable_rps_cmd)" \
-	  ip netns exec server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \
+	  ip netns exec $server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \
 	  -d "${PORT}" -i "${DEV}" -k "${KEY}" -T 1000 \
 	  -C "$(get_rx_irq_cpus)" -s -v &
 elif [[ ! -z "${RPS_MAP}" ]]; then
 	eval "$(get_disable_rfs_cmd) $(get_set_rps_bitmaps_cmd ${RPS_MAP})" \
-	  ip netns exec server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \
+	  ip netns exec $server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \
 	  -d "${PORT}" -i "${DEV}" -k "${KEY}" -T 1000 \
 	  -r "0x${RPS_MAP}" -s -v &
 else
-	ip netns exec server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \
+	ip netns exec $server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \
 	  -d "${PORT}" -i "${DEV}" -k "${KEY}" -T 1000 -s -v &
 fi
 
 server_pid=$!
 
-ip netns exec client_ns ./toeplitz_client.sh "${PROTO_FLAG}" \
+ip netns exec $client_ns ./toeplitz_client.sh "${PROTO_FLAG}" \
   "${IP_FLAG}" "${SERVER_IP%%/*}" "${PORT}" &
 
 client_pid=$!
diff --git a/tools/testing/selftests/net/traceroute.sh b/tools/testing/selftests/net/traceroute.sh
index de9ca97abc30..282f14760940 100755
--- a/tools/testing/selftests/net/traceroute.sh
+++ b/tools/testing/selftests/net/traceroute.sh
@@ -4,6 +4,7 @@
 # Run traceroute/traceroute6 tests
 #
 
+source lib.sh
 VERBOSE=0
 PAUSE_ON_FAIL=no
 
@@ -69,9 +70,6 @@ create_ns()
 	[ -z "${addr}" ] && addr="-"
 	[ -z "${addr6}" ] && addr6="-"
 
-	ip netns add ${ns}
-
-	ip netns exec ${ns} ip link set lo up
 	if [ "${addr}" != "-" ]; then
 		ip netns exec ${ns} ip addr add dev lo ${addr}
 	fi
@@ -160,12 +158,7 @@ connect_ns()
 
 cleanup_traceroute6()
 {
-	local ns
-
-	for ns in host-1 host-2 router-1 router-2
-	do
-		ip netns del ${ns} 2>/dev/null
-	done
+	cleanup_ns $h1 $h2 $r1 $r2
 }
 
 setup_traceroute6()
@@ -176,33 +169,34 @@ setup_traceroute6()
 	cleanup_traceroute6
 
 	set -e
-	create_ns host-1
-	create_ns host-2
-	create_ns router-1
-	create_ns router-2
+	setup_ns h1 h2 r1 r2
+	create_ns $h1
+	create_ns $h2
+	create_ns $r1
+	create_ns $r2
 
 	# Setup N3
-	connect_ns router-2 eth3 - 2000:103::2/64 host-2 eth3 - 2000:103::4/64
-	ip netns exec host-2 ip route add default via 2000:103::2
+	connect_ns $r2 eth3 - 2000:103::2/64 $h2 eth3 - 2000:103::4/64
+	ip netns exec $h2 ip route add default via 2000:103::2
 
 	# Setup N2
-	connect_ns router-1 eth2 - 2000:102::1/64 router-2 eth2 - 2000:102::2/64
-	ip netns exec router-1 ip route add default via 2000:102::2
+	connect_ns $r1 eth2 - 2000:102::1/64 $r2 eth2 - 2000:102::2/64
+	ip netns exec $r1 ip route add default via 2000:102::2
 
 	# Setup N1. host-1 and router-2 connect to a bridge in router-1.
-	ip netns exec router-1 ip link add name ${brdev} type bridge
-	ip netns exec router-1 ip link set ${brdev} up
-	ip netns exec router-1 ip addr add 2000:101::1/64 dev ${brdev}
+	ip netns exec $r1 ip link add name ${brdev} type bridge
+	ip netns exec $r1 ip link set ${brdev} up
+	ip netns exec $r1 ip addr add 2000:101::1/64 dev ${brdev}
 
-	connect_ns host-1 eth0 - 2000:101::3/64 router-1 eth0 - -
-	ip netns exec router-1 ip link set dev eth0 master ${brdev}
-	ip netns exec host-1 ip route add default via 2000:101::1
+	connect_ns $h1 eth0 - 2000:101::3/64 $r1 eth0 - -
+	ip netns exec $r1 ip link set dev eth0 master ${brdev}
+	ip netns exec $h1 ip route add default via 2000:101::1
 
-	connect_ns router-2 eth1 - 2000:101::2/64 router-1 eth1 - -
-	ip netns exec router-1 ip link set dev eth1 master ${brdev}
+	connect_ns $r2 eth1 - 2000:101::2/64 $r1 eth1 - -
+	ip netns exec $r1 ip link set dev eth1 master ${brdev}
 
 	# Prime the network
-	ip netns exec host-1 ping6 -c5 2000:103::4 >/dev/null 2>&1
+	ip netns exec $h1 ping6 -c5 2000:103::4 >/dev/null 2>&1
 
 	set +e
 }
@@ -217,7 +211,7 @@ run_traceroute6()
 	setup_traceroute6
 
 	# traceroute6 host-2 from host-1 (expects 2000:102::2)
-	run_cmd host-1 "traceroute6 2000:103::4 | grep -q 2000:102::2"
+	run_cmd $h1 "traceroute6 2000:103::4 | grep -q 2000:102::2"
 	log_test $? 0 "IPV6 traceroute"
 
 	cleanup_traceroute6
@@ -240,12 +234,7 @@ run_traceroute6()
 
 cleanup_traceroute()
 {
-	local ns
-
-	for ns in host-1 host-2 router
-	do
-		ip netns del ${ns} 2>/dev/null
-	done
+	cleanup_ns $h1 $h2 $router
 }
 
 setup_traceroute()
@@ -254,24 +243,25 @@ setup_traceroute()
 	cleanup_traceroute
 
 	set -e
-	create_ns host-1
-	create_ns host-2
-	create_ns router
+	setup_ns h1 h2 router
+	create_ns $h1
+	create_ns $h2
+	create_ns $router
 
-	connect_ns host-1 eth0 1.0.1.3/24 - \
-	           router eth1 1.0.3.1/24 -
-	ip netns exec host-1 ip route add default via 1.0.1.1
+	connect_ns $h1 eth0 1.0.1.3/24 - \
+	           $router eth1 1.0.3.1/24 -
+	ip netns exec $h1 ip route add default via 1.0.1.1
 
-	ip netns exec router ip addr add 1.0.1.1/24 dev eth1
-	ip netns exec router sysctl -qw \
+	ip netns exec $router ip addr add 1.0.1.1/24 dev eth1
+	ip netns exec $router sysctl -qw \
 				net.ipv4.icmp_errors_use_inbound_ifaddr=1
 
-	connect_ns host-2 eth0 1.0.2.4/24 - \
-	           router eth2 1.0.2.1/24 -
-	ip netns exec host-2 ip route add default via 1.0.2.1
+	connect_ns $h2 eth0 1.0.2.4/24 - \
+	           $router eth2 1.0.2.1/24 -
+	ip netns exec $h2 ip route add default via 1.0.2.1
 
 	# Prime the network
-	ip netns exec host-1 ping -c5 1.0.2.4 >/dev/null 2>&1
+	ip netns exec $h1 ping -c5 1.0.2.4 >/dev/null 2>&1
 
 	set +e
 }
@@ -286,7 +276,7 @@ run_traceroute()
 	setup_traceroute
 
 	# traceroute host-2 from host-1 (expects 1.0.1.1). Takes a while.
-	run_cmd host-1 "traceroute 1.0.2.4 | grep -q 1.0.1.1"
+	run_cmd $h1 "traceroute 1.0.2.4 | grep -q 1.0.1.1"
 	log_test $? 0 "IPV4 traceroute"
 
 	cleanup_traceroute
diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
index 0c743752669a..af5dc57c8ce9 100755
--- a/tools/testing/selftests/net/udpgro.sh
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -3,6 +3,8 @@
 #
 # Run a series of udpgro functional tests.
 
+source net_helper.sh
+
 readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
 
 BPF_FILE="../bpf/xdp_dummy.bpf.o"
@@ -51,8 +53,7 @@ run_one() {
 		echo "ok" || \
 		echo "failed" &
 
-	# Hack: let bg programs complete the startup
-	sleep 0.2
+	wait_local_port_listen ${PEER_NS} 8000 udp
 	./udpgso_bench_tx ${tx_args}
 	ret=$?
 	wait $(jobs -p)
@@ -97,7 +98,7 @@ run_one_nat() {
 		echo "ok" || \
 		echo "failed"&
 
-	sleep 0.1
+	wait_local_port_listen "${PEER_NS}" 8000 udp
 	./udpgso_bench_tx ${tx_args}
 	ret=$?
 	kill -INT $pid
@@ -118,11 +119,9 @@ run_one_2sock() {
 		echo "ok" || \
 		echo "failed" &
 
-	# Hack: let bg programs complete the startup
-	sleep 0.2
+	wait_local_port_listen "${PEER_NS}" 12345 udp
 	./udpgso_bench_tx ${tx_args} -p 12345
-	sleep 0.1
-	# first UDP GSO socket should be closed at this point
+	wait_local_port_listen "${PEER_NS}" 8000 udp
 	./udpgso_bench_tx ${tx_args}
 	ret=$?
 	wait $(jobs -p)
diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh
index 894972877e8b..cb664679b434 100755
--- a/tools/testing/selftests/net/udpgro_bench.sh
+++ b/tools/testing/selftests/net/udpgro_bench.sh
@@ -3,6 +3,8 @@
 #
 # Run a series of udpgro benchmarks
 
+source net_helper.sh
+
 readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
 
 BPF_FILE="../bpf/xdp_dummy.bpf.o"
@@ -40,8 +42,7 @@ run_one() {
 	ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r &
 	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -t ${rx_args} -r &
 
-	# Hack: let bg programs complete the startup
-	sleep 0.2
+	wait_local_port_listen "${PEER_NS}" 8000 udp
 	./udpgso_bench_tx ${tx_args}
 }
 
diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh
index 0a6359bed0b9..dd47fa96f6b3 100755
--- a/tools/testing/selftests/net/udpgro_frglist.sh
+++ b/tools/testing/selftests/net/udpgro_frglist.sh
@@ -3,6 +3,8 @@
 #
 # Run a series of udpgro benchmarks
 
+source net_helper.sh
+
 readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
 
 BPF_FILE="../bpf/xdp_dummy.bpf.o"
@@ -45,8 +47,7 @@ run_one() {
         echo ${rx_args}
 	ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r &
 
-	# Hack: let bg programs complete the startup
-	sleep 0.2
+	wait_local_port_listen "${PEER_NS}" 8000 udp
 	./udpgso_bench_tx ${tx_args}
 }
 
diff --git a/tools/testing/selftests/net/unicast_extensions.sh b/tools/testing/selftests/net/unicast_extensions.sh
index 2d10ccac898a..f52aa5f7da52 100755
--- a/tools/testing/selftests/net/unicast_extensions.sh
+++ b/tools/testing/selftests/net/unicast_extensions.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 #
 # By Seth Schoen (c) 2021, for the IPv4 Unicast Extensions Project
@@ -28,8 +28,7 @@
 # These tests provide an easy way to flip the expected result of any
 # of these behaviors for testing kernel patches that change them.
 
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
+source lib.sh
 
 # nettest can be run from PATH or from same directory as this selftest
 if ! which nettest >/dev/null; then
@@ -61,20 +60,20 @@ _do_segmenttest(){
 	# foo --- bar
 	# Arguments: ip_a ip_b prefix_length test_description
 	#
-	# Caller must set up foo-ns and bar-ns namespaces
+	# Caller must set up $foo_ns and $bar_ns namespaces
 	# containing linked veth devices foo and bar,
 	# respectively.
 
-	ip -n foo-ns address add $1/$3 dev foo || return 1
-	ip -n foo-ns link set foo up || return 1
-	ip -n bar-ns address add $2/$3 dev bar || return 1
-	ip -n bar-ns link set bar up || return 1
+	ip -n $foo_ns address add $1/$3 dev foo || return 1
+	ip -n $foo_ns link set foo up || return 1
+	ip -n $bar_ns address add $2/$3 dev bar || return 1
+	ip -n $bar_ns link set bar up || return 1
 
-	ip netns exec foo-ns timeout 2 ping -c 1 $2 || return 1
-	ip netns exec bar-ns timeout 2 ping -c 1 $1 || return 1
+	ip netns exec $foo_ns timeout 2 ping -c 1 $2 || return 1
+	ip netns exec $bar_ns timeout 2 ping -c 1 $1 || return 1
 
-	nettest -B -N bar-ns -O foo-ns -r $1 || return 1
-	nettest -B -N foo-ns -O bar-ns -r $2 || return 1
+	nettest -B -N $bar_ns -O $foo_ns -r $1 || return 1
+	nettest -B -N $foo_ns -O $bar_ns -r $2 || return 1
 
 	return 0
 }
@@ -88,31 +87,31 @@ _do_route_test(){
 	# Arguments: foo_ip foo1_ip bar1_ip bar_ip prefix_len test_description
 	# Displays test result and returns success or failure.
 
-	# Caller must set up foo-ns, bar-ns, and router-ns
+	# Caller must set up $foo_ns, $bar_ns, and $router_ns
 	# containing linked veth devices foo-foo1, bar1-bar
-	# (foo in foo-ns, foo1 and bar1 in router-ns, and
-	# bar in bar-ns).
-
-	ip -n foo-ns address add $1/$5 dev foo || return 1
-	ip -n foo-ns link set foo up || return 1
-	ip -n foo-ns route add default via $2 || return 1
-	ip -n bar-ns address add $4/$5 dev bar || return 1
-	ip -n bar-ns link set bar up || return 1
-	ip -n bar-ns route add default via $3 || return 1
-	ip -n router-ns address add $2/$5 dev foo1 || return 1
-	ip -n router-ns link set foo1 up || return 1
-	ip -n router-ns address add $3/$5 dev bar1 || return 1
-	ip -n router-ns link set bar1 up || return 1
-
-	echo 1 | ip netns exec router-ns tee /proc/sys/net/ipv4/ip_forward
-
-	ip netns exec foo-ns timeout 2 ping -c 1 $2 || return 1
-	ip netns exec foo-ns timeout 2 ping -c 1 $4 || return 1
-	ip netns exec bar-ns timeout 2 ping -c 1 $3 || return 1
-	ip netns exec bar-ns timeout 2 ping -c 1 $1 || return 1
-
-	nettest -B -N bar-ns -O foo-ns -r $1 || return 1
-	nettest -B -N foo-ns -O bar-ns -r $4 || return 1
+	# (foo in $foo_ns, foo1 and bar1 in $router_ns, and
+	# bar in $bar_ns).
+
+	ip -n $foo_ns address add $1/$5 dev foo || return 1
+	ip -n $foo_ns link set foo up || return 1
+	ip -n $foo_ns route add default via $2 || return 1
+	ip -n $bar_ns address add $4/$5 dev bar || return 1
+	ip -n $bar_ns link set bar up || return 1
+	ip -n $bar_ns route add default via $3 || return 1
+	ip -n $router_ns address add $2/$5 dev foo1 || return 1
+	ip -n $router_ns link set foo1 up || return 1
+	ip -n $router_ns address add $3/$5 dev bar1 || return 1
+	ip -n $router_ns link set bar1 up || return 1
+
+	echo 1 | ip netns exec $router_ns tee /proc/sys/net/ipv4/ip_forward
+
+	ip netns exec $foo_ns timeout 2 ping -c 1 $2 || return 1
+	ip netns exec $foo_ns timeout 2 ping -c 1 $4 || return 1
+	ip netns exec $bar_ns timeout 2 ping -c 1 $3 || return 1
+	ip netns exec $bar_ns timeout 2 ping -c 1 $1 || return 1
+
+	nettest -B -N $bar_ns -O $foo_ns -r $1 || return 1
+	nettest -B -N $foo_ns -O $bar_ns -r $4 || return 1
 
 	return 0
 }
@@ -121,17 +120,15 @@ segmenttest(){
 	# Sets up veth link and tries to connect over it.
 	# Arguments: ip_a ip_b prefix_len test_description
 	hide_output
-	ip netns add foo-ns
-	ip netns add bar-ns
-	ip link add foo netns foo-ns type veth peer name bar netns bar-ns
+	setup_ns foo_ns bar_ns
+	ip link add foo netns $foo_ns type veth peer name bar netns $bar_ns
 
 	test_result=0
 	_do_segmenttest "$@" || test_result=1
 
-	ip netns pids foo-ns | xargs -r kill -9
-	ip netns pids bar-ns | xargs -r kill -9
-	ip netns del foo-ns
-	ip netns del bar-ns
+	ip netns pids $foo_ns | xargs -r kill -9
+	ip netns pids $bar_ns | xargs -r kill -9
+	cleanup_ns $foo_ns $bar_ns
 	show_output
 
 	# inverted tests will expect failure instead of success
@@ -147,21 +144,17 @@ route_test(){
 	# Returns success or failure.
 
 	hide_output
-	ip netns add foo-ns
-	ip netns add bar-ns
-	ip netns add router-ns
-	ip link add foo netns foo-ns type veth peer name foo1 netns router-ns
-	ip link add bar netns bar-ns type veth peer name bar1 netns router-ns
+	setup_ns foo_ns bar_ns router_ns
+	ip link add foo netns $foo_ns type veth peer name foo1 netns $router_ns
+	ip link add bar netns $bar_ns type veth peer name bar1 netns $router_ns
 
 	test_result=0
 	_do_route_test "$@" || test_result=1
 
-	ip netns pids foo-ns | xargs -r kill -9
-	ip netns pids bar-ns | xargs -r kill -9
-	ip netns pids router-ns | xargs -r kill -9
-	ip netns del foo-ns
-	ip netns del bar-ns
-	ip netns del router-ns
+	ip netns pids $foo_ns | xargs -r kill -9
+	ip netns pids $bar_ns | xargs -r kill -9
+	ip netns pids $router_ns | xargs -r kill -9
+	cleanup_ns $foo_ns $bar_ns $router_ns
 
 	show_output
 
diff --git a/tools/testing/selftests/net/vlan_hw_filter.sh b/tools/testing/selftests/net/vlan_hw_filter.sh
new file mode 100755
index 000000000000..7bc804ffaf7c
--- /dev/null
+++ b/tools/testing/selftests/net/vlan_hw_filter.sh
@@ -0,0 +1,29 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+readonly NETNS="ns-$(mktemp -u XXXXXX)"
+
+ret=0
+
+cleanup() {
+	ip netns del $NETNS
+}
+
+trap cleanup EXIT
+
+fail() {
+    echo "ERROR: ${1:-unexpected return code} (ret: $_)" >&2
+    ret=1
+}
+
+ip netns add ${NETNS}
+ip netns exec ${NETNS} ip link add bond0 type bond mode 0
+ip netns exec ${NETNS} ip link add bond_slave_1 type veth peer veth2
+ip netns exec ${NETNS} ip link set bond_slave_1 master bond0
+ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter off
+ip netns exec ${NETNS} ip link add link bond_slave_1 name bond_slave_1.0 type vlan id 0
+ip netns exec ${NETNS} ip link add link bond0 name bond0.0 type vlan id 0
+ip netns exec ${NETNS} ip link set bond_slave_1 nomaster
+ip netns exec ${NETNS} ip link del veth2 || fail "Please check vlan HW filter function"
+
+exit $ret
diff --git a/tools/testing/selftests/net/vrf-xfrm-tests.sh b/tools/testing/selftests/net/vrf-xfrm-tests.sh
index 452638ae8aed..b64dd891699d 100755
--- a/tools/testing/selftests/net/vrf-xfrm-tests.sh
+++ b/tools/testing/selftests/net/vrf-xfrm-tests.sh
@@ -3,9 +3,7 @@
 #
 # Various combinations of VRF with xfrms and qdisc.
 
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
+source lib.sh
 PAUSE_ON_FAIL=no
 VERBOSE=0
 ret=0
@@ -67,7 +65,7 @@ run_cmd_host1()
 		printf "    COMMAND: $cmd\n"
 	fi
 
-	out=$(eval ip netns exec host1 $cmd 2>&1)
+	out=$(eval ip netns exec $host1 $cmd 2>&1)
 	rc=$?
 	if [ "$VERBOSE" = "1" ]; then
 		if [ -n "$out" ]; then
@@ -116,9 +114,6 @@ create_ns()
 	[ -z "${addr}" ] && addr="-"
 	[ -z "${addr6}" ] && addr6="-"
 
-	ip netns add ${ns}
-
-	ip -netns ${ns} link set lo up
 	if [ "${addr}" != "-" ]; then
 		ip -netns ${ns} addr add dev lo ${addr}
 	fi
@@ -177,25 +172,25 @@ connect_ns()
 
 cleanup()
 {
-	ip netns del host1
-	ip netns del host2
+	cleanup_ns $host1 $host2
 }
 
 setup()
 {
-	create_ns "host1"
-	create_ns "host2"
+	setup_ns host1 host2
+	create_ns "$host1"
+	create_ns "$host2"
 
-	connect_ns "host1" eth0 ${HOST1_4}/24 ${HOST1_6}/64 \
-	           "host2" eth0 ${HOST2_4}/24 ${HOST2_6}/64
+	connect_ns "$host1" eth0 ${HOST1_4}/24 ${HOST1_6}/64 \
+	           "$host2" eth0 ${HOST2_4}/24 ${HOST2_6}/64
 
-	create_vrf "host1" ${VRF} ${TABLE}
-	ip -netns host1 link set dev eth0 master ${VRF}
+	create_vrf "$host1" ${VRF} ${TABLE}
+	ip -netns $host1 link set dev eth0 master ${VRF}
 }
 
 cleanup_xfrm()
 {
-	for ns in host1 host2
+	for ns in $host1 $host2
 	do
 		for x in state policy
 		do
@@ -218,57 +213,57 @@ setup_xfrm()
 	#
 
 	# host1 - IPv4 out
-	ip -netns host1 xfrm policy add \
+	ip -netns $host1 xfrm policy add \
 	  src ${h1_4} dst ${h2_4} ${devarg} dir out \
 	  tmpl src ${HOST1_4} dst ${HOST2_4} proto esp mode tunnel
 
 	# host2 - IPv4 in
-	ip -netns host2 xfrm policy add \
+	ip -netns $host2 xfrm policy add \
 	  src ${h1_4} dst ${h2_4} dir in \
 	  tmpl src ${HOST1_4} dst ${HOST2_4} proto esp mode tunnel
 
 	# host1 - IPv4 in
-	ip -netns host1 xfrm policy add \
+	ip -netns $host1 xfrm policy add \
 	  src ${h2_4} dst ${h1_4} ${devarg} dir in \
 	  tmpl src ${HOST2_4} dst ${HOST1_4} proto esp mode tunnel
 
 	# host2 - IPv4 out
-	ip -netns host2 xfrm policy add \
+	ip -netns $host2 xfrm policy add \
 	  src ${h2_4} dst ${h1_4} dir out \
 	  tmpl src ${HOST2_4} dst ${HOST1_4} proto esp mode tunnel
 
 
 	# host1 - IPv6 out
-	ip -6 -netns host1 xfrm policy add \
+	ip -6 -netns $host1 xfrm policy add \
 	  src ${h1_6} dst ${h2_6} ${devarg} dir out \
 	  tmpl src ${HOST1_6} dst ${HOST2_6} proto esp mode tunnel
 
 	# host2 - IPv6 in
-	ip -6 -netns host2 xfrm policy add \
+	ip -6 -netns $host2 xfrm policy add \
 	  src ${h1_6} dst ${h2_6} dir in \
 	  tmpl src ${HOST1_6} dst ${HOST2_6} proto esp mode tunnel
 
 	# host1 - IPv6 in
-	ip -6 -netns host1 xfrm policy add \
+	ip -6 -netns $host1 xfrm policy add \
 	  src ${h2_6} dst ${h1_6} ${devarg} dir in \
 	  tmpl src ${HOST2_6} dst ${HOST1_6} proto esp mode tunnel
 
 	# host2 - IPv6 out
-	ip -6 -netns host2 xfrm policy add \
+	ip -6 -netns $host2 xfrm policy add \
 	  src ${h2_6} dst ${h1_6} dir out \
 	  tmpl src ${HOST2_6} dst ${HOST1_6} proto esp mode tunnel
 
 	#
 	# state
 	#
-	ip -netns host1 xfrm state add src ${HOST1_4} dst ${HOST2_4} \
+	ip -netns $host1 xfrm state add src ${HOST1_4} dst ${HOST2_4} \
 	    proto esp spi ${SPI_1} reqid 0 mode tunnel \
 	    replay-window 4 replay-oseq 0x4 \
 	    auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \
 	    enc 'cbc(aes)' ${ENC_1} \
 	    sel src ${h1_4} dst ${h2_4} ${devarg}
 
-	ip -netns host2 xfrm state add src ${HOST1_4} dst ${HOST2_4} \
+	ip -netns $host2 xfrm state add src ${HOST1_4} dst ${HOST2_4} \
 	    proto esp spi ${SPI_1} reqid 0 mode tunnel \
 	    replay-window 4 replay-oseq 0x4 \
 	    auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \
@@ -276,14 +271,14 @@ setup_xfrm()
 	    sel src ${h1_4} dst ${h2_4}
 
 
-	ip -netns host1 xfrm state add src ${HOST2_4} dst ${HOST1_4} \
+	ip -netns $host1 xfrm state add src ${HOST2_4} dst ${HOST1_4} \
 	    proto esp spi ${SPI_2} reqid 0 mode tunnel \
 	    replay-window 4 replay-oseq 0x4 \
 	    auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \
 	    enc 'cbc(aes)' ${ENC_2} \
 	    sel src ${h2_4} dst ${h1_4} ${devarg}
 
-	ip -netns host2 xfrm state add src ${HOST2_4} dst ${HOST1_4} \
+	ip -netns $host2 xfrm state add src ${HOST2_4} dst ${HOST1_4} \
 	    proto esp spi ${SPI_2} reqid 0 mode tunnel \
 	    replay-window 4 replay-oseq 0x4 \
 	    auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \
@@ -291,14 +286,14 @@ setup_xfrm()
 	    sel src ${h2_4} dst ${h1_4}
 
 
-	ip -6 -netns host1 xfrm state add src ${HOST1_6} dst ${HOST2_6} \
+	ip -6 -netns $host1 xfrm state add src ${HOST1_6} dst ${HOST2_6} \
 	    proto esp spi ${SPI_1} reqid 0 mode tunnel \
 	    replay-window 4 replay-oseq 0x4 \
 	    auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \
 	    enc 'cbc(aes)' ${ENC_1} \
 	    sel src ${h1_6} dst ${h2_6} ${devarg}
 
-	ip -6 -netns host2 xfrm state add src ${HOST1_6} dst ${HOST2_6} \
+	ip -6 -netns $host2 xfrm state add src ${HOST1_6} dst ${HOST2_6} \
 	    proto esp spi ${SPI_1} reqid 0 mode tunnel \
 	    replay-window 4 replay-oseq 0x4 \
 	    auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \
@@ -306,14 +301,14 @@ setup_xfrm()
 	    sel src ${h1_6} dst ${h2_6}
 
 
-	ip -6 -netns host1 xfrm state add src ${HOST2_6} dst ${HOST1_6} \
+	ip -6 -netns $host1 xfrm state add src ${HOST2_6} dst ${HOST1_6} \
 	    proto esp spi ${SPI_2} reqid 0 mode tunnel \
 	    replay-window 4 replay-oseq 0x4 \
 	    auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \
 	    enc 'cbc(aes)' ${ENC_2} \
 	    sel src ${h2_6} dst ${h1_6} ${devarg}
 
-	ip -6 -netns host2 xfrm state add src ${HOST2_6} dst ${HOST1_6} \
+	ip -6 -netns $host2 xfrm state add src ${HOST2_6} dst ${HOST1_6} \
 	    proto esp spi ${SPI_2} reqid 0 mode tunnel \
 	    replay-window 4 replay-oseq 0x4 \
 	    auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \
@@ -323,22 +318,22 @@ setup_xfrm()
 
 cleanup_xfrm_dev()
 {
-	ip -netns host1 li del xfrm0
-	ip -netns host2 addr del ${XFRM2_4}/24 dev eth0
-	ip -netns host2 addr del ${XFRM2_6}/64 dev eth0
+	ip -netns $host1 li del xfrm0
+	ip -netns $host2 addr del ${XFRM2_4}/24 dev eth0
+	ip -netns $host2 addr del ${XFRM2_6}/64 dev eth0
 }
 
 setup_xfrm_dev()
 {
 	local vrfarg="vrf ${VRF}"
 
-	ip -netns host1 li add type xfrm dev eth0 if_id ${IF_ID}
-	ip -netns host1 li set xfrm0 ${vrfarg} up
-	ip -netns host1 addr add ${XFRM1_4}/24 dev xfrm0
-	ip -netns host1 addr add ${XFRM1_6}/64 dev xfrm0
+	ip -netns $host1 li add type xfrm dev eth0 if_id ${IF_ID}
+	ip -netns $host1 li set xfrm0 ${vrfarg} up
+	ip -netns $host1 addr add ${XFRM1_4}/24 dev xfrm0
+	ip -netns $host1 addr add ${XFRM1_6}/64 dev xfrm0
 
-	ip -netns host2 addr add ${XFRM2_4}/24 dev eth0
-	ip -netns host2 addr add ${XFRM2_6}/64 dev eth0
+	ip -netns $host2 addr add ${XFRM2_4}/24 dev eth0
+	ip -netns $host2 addr add ${XFRM2_6}/64 dev eth0
 
 	setup_xfrm ${XFRM1_4} ${XFRM2_4} ${XFRM1_6} ${XFRM2_6} "if_id ${IF_ID}"
 }
diff --git a/tools/testing/selftests/net/vrf_route_leaking.sh b/tools/testing/selftests/net/vrf_route_leaking.sh
index dedc52562b4f..2da32f4c479b 100755
--- a/tools/testing/selftests/net/vrf_route_leaking.sh
+++ b/tools/testing/selftests/net/vrf_route_leaking.sh
@@ -58,6 +58,7 @@
 # to send an ICMP error back to the source when the ttl of a packet reaches 1
 # while it is forwarded between different vrfs.
 
+source lib.sh
 VERBOSE=0
 PAUSE_ON_FAIL=no
 DEFAULT_TTYPE=sym
@@ -171,11 +172,7 @@ run_cmd_grep()
 
 cleanup()
 {
-	local ns
-
-	for ns in h1 h2 r1 r2; do
-		ip netns del $ns 2>/dev/null
-	done
+	cleanup_ns $h1 $h2 $r1 $r2
 }
 
 setup_vrf()
@@ -212,72 +209,69 @@ setup_sym()
 
 	#
 	# create nodes as namespaces
-	#
-	for ns in h1 h2 r1; do
-		ip netns add $ns
-		ip -netns $ns link set lo up
-
-		case "${ns}" in
-		h[12]) ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=0
-		       ip netns exec $ns sysctl -q -w net.ipv6.conf.all.keep_addr_on_down=1
-			;;
-		r1)    ip netns exec $ns sysctl -q -w net.ipv4.ip_forward=1
-		       ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=1
-		esac
+	setup_ns h1 h2 r1
+	for ns in $h1 $h2 $r1; do
+		if echo $ns | grep -q h[12]-; then
+			ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=0
+			ip netns exec $ns sysctl -q -w net.ipv6.conf.all.keep_addr_on_down=1
+		else
+			ip netns exec $ns sysctl -q -w net.ipv4.ip_forward=1
+			ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=1
+		fi
 	done
 
 	#
 	# create interconnects
 	#
-	ip -netns h1 link add eth0 type veth peer name r1h1
-	ip -netns h1 link set r1h1 netns r1 name eth0 up
+	ip -netns $h1 link add eth0 type veth peer name r1h1
+	ip -netns $h1 link set r1h1 netns $r1 name eth0 up
 
-	ip -netns h2 link add eth0 type veth peer name r1h2
-	ip -netns h2 link set r1h2 netns r1 name eth1 up
+	ip -netns $h2 link add eth0 type veth peer name r1h2
+	ip -netns $h2 link set r1h2 netns $r1 name eth1 up
 
 	#
 	# h1
 	#
-	ip -netns h1 addr add dev eth0 ${H1_N1_IP}/24
-	ip -netns h1 -6 addr add dev eth0 ${H1_N1_IP6}/64 nodad
-	ip -netns h1 link set eth0 up
+	ip -netns $h1 addr add dev eth0 ${H1_N1_IP}/24
+	ip -netns $h1 -6 addr add dev eth0 ${H1_N1_IP6}/64 nodad
+	ip -netns $h1 link set eth0 up
 
 	# h1 to h2 via r1
-	ip -netns h1    route add ${H2_N2} via ${R1_N1_IP} dev eth0
-	ip -netns h1 -6 route add ${H2_N2_6} via "${R1_N1_IP6}" dev eth0
+	ip -netns $h1    route add ${H2_N2} via ${R1_N1_IP} dev eth0
+	ip -netns $h1 -6 route add ${H2_N2_6} via "${R1_N1_IP6}" dev eth0
 
 	#
 	# h2
 	#
-	ip -netns h2 addr add dev eth0 ${H2_N2_IP}/24
-	ip -netns h2 -6 addr add dev eth0 ${H2_N2_IP6}/64 nodad
-	ip -netns h2 link set eth0 up
+	ip -netns $h2 addr add dev eth0 ${H2_N2_IP}/24
+	ip -netns $h2 -6 addr add dev eth0 ${H2_N2_IP6}/64 nodad
+	ip -netns $h2 link set eth0 up
 
 	# h2 to h1 via r1
-	ip -netns h2 route add default via ${R1_N2_IP} dev eth0
-	ip -netns h2 -6 route add default via ${R1_N2_IP6} dev eth0
+	ip -netns $h2 route add default via ${R1_N2_IP} dev eth0
+	ip -netns $h2 -6 route add default via ${R1_N2_IP6} dev eth0
 
 	#
 	# r1
 	#
-	setup_vrf r1
-	create_vrf r1 blue 1101
-	create_vrf r1 red 1102
-	ip -netns r1 link set mtu 1400 dev eth1
-	ip -netns r1 link set eth0 vrf blue up
-	ip -netns r1 link set eth1 vrf red up
-	ip -netns r1 addr add dev eth0 ${R1_N1_IP}/24
-	ip -netns r1 -6 addr add dev eth0 ${R1_N1_IP6}/64 nodad
-	ip -netns r1 addr add dev eth1 ${R1_N2_IP}/24
-	ip -netns r1 -6 addr add dev eth1 ${R1_N2_IP6}/64 nodad
+	setup_vrf $r1
+	create_vrf $r1 blue 1101
+	create_vrf $r1 red 1102
+	ip -netns $r1 link set mtu 1400 dev eth1
+	ip -netns $r1 link set eth0 vrf blue up
+	ip -netns $r1 link set eth1 vrf red up
+	ip -netns $r1 addr add dev eth0 ${R1_N1_IP}/24
+	ip -netns $r1 -6 addr add dev eth0 ${R1_N1_IP6}/64 nodad
+	ip -netns $r1 addr add dev eth1 ${R1_N2_IP}/24
+	ip -netns $r1 -6 addr add dev eth1 ${R1_N2_IP6}/64 nodad
 
 	# Route leak from blue to red
-	ip -netns r1 route add vrf blue ${H2_N2} dev red
-	ip -netns r1 -6 route add vrf blue ${H2_N2_6} dev red
+	ip -netns $r1 route add vrf blue ${H2_N2} dev red
+	ip -netns $r1 -6 route add vrf blue ${H2_N2_6} dev red
 
 	# Route leak from red to blue
-	ip -netns r1 route add vrf red ${H1_N1} dev blue
-	ip -netns r1 -6 route add vrf red ${H1_N1_6} dev blue
+	ip -netns $r1 route add vrf red ${H1_N1} dev blue
+	ip -netns $r1 -6 route add vrf red ${H1_N1_6} dev blue
 
 
 	# Wait for ip config to settle
@@ -293,90 +287,87 @@ setup_asym()
 
 	#
 	# create nodes as namespaces
-	#
-	for ns in h1 h2 r1 r2; do
-		ip netns add $ns
-		ip -netns $ns link set lo up
-
-		case "${ns}" in
-		h[12]) ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=0
-		       ip netns exec $ns sysctl -q -w net.ipv6.conf.all.keep_addr_on_down=1
-			;;
-		r[12]) ip netns exec $ns sysctl -q -w net.ipv4.ip_forward=1
-		       ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=1
-		esac
+	setup_ns h1 h2 r1 r2
+	for ns in $h1 $h2 $r1 $r2; do
+		if echo $ns | grep -q h[12]-; then
+			ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=0
+			ip netns exec $ns sysctl -q -w net.ipv6.conf.all.keep_addr_on_down=1
+		else
+			ip netns exec $ns sysctl -q -w net.ipv4.ip_forward=1
+			ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=1
+		fi
 	done
 
 	#
 	# create interconnects
 	#
-	ip -netns h1 link add eth0 type veth peer name r1h1
-	ip -netns h1 link set r1h1 netns r1 name eth0 up
+	ip -netns $h1 link add eth0 type veth peer name r1h1
+	ip -netns $h1 link set r1h1 netns $r1 name eth0 up
 
-	ip -netns h1 link add eth1 type veth peer name r2h1
-	ip -netns h1 link set r2h1 netns r2 name eth0 up
+	ip -netns $h1 link add eth1 type veth peer name r2h1
+	ip -netns $h1 link set r2h1 netns $r2 name eth0 up
 
-	ip -netns h2 link add eth0 type veth peer name r1h2
-	ip -netns h2 link set r1h2 netns r1 name eth1 up
+	ip -netns $h2 link add eth0 type veth peer name r1h2
+	ip -netns $h2 link set r1h2 netns $r1 name eth1 up
 
-	ip -netns h2 link add eth1 type veth peer name r2h2
-	ip -netns h2 link set r2h2 netns r2 name eth1 up
+	ip -netns $h2 link add eth1 type veth peer name r2h2
+	ip -netns $h2 link set r2h2 netns $r2 name eth1 up
 
 	#
 	# h1
 	#
-	ip -netns h1 link add br0 type bridge
-	ip -netns h1 link set br0 up
-	ip -netns h1 addr add dev br0 ${H1_N1_IP}/24
-	ip -netns h1 -6 addr add dev br0 ${H1_N1_IP6}/64 nodad
-	ip -netns h1 link set eth0 master br0 up
-	ip -netns h1 link set eth1 master br0 up
+	ip -netns $h1 link add br0 type bridge
+	ip -netns $h1 link set br0 up
+	ip -netns $h1 addr add dev br0 ${H1_N1_IP}/24
+	ip -netns $h1 -6 addr add dev br0 ${H1_N1_IP6}/64 nodad
+	ip -netns $h1 link set eth0 master br0 up
+	ip -netns $h1 link set eth1 master br0 up
 
 	# h1 to h2 via r1
-	ip -netns h1    route add ${H2_N2} via ${R1_N1_IP} dev br0
-	ip -netns h1 -6 route add ${H2_N2_6} via "${R1_N1_IP6}" dev br0
+	ip -netns $h1    route add ${H2_N2} via ${R1_N1_IP} dev br0
+	ip -netns $h1 -6 route add ${H2_N2_6} via "${R1_N1_IP6}" dev br0
 
 	#
 	# h2
 	#
-	ip -netns h2 link add br0 type bridge
-	ip -netns h2 link set br0 up
-	ip -netns h2 addr add dev br0 ${H2_N2_IP}/24
-	ip -netns h2 -6 addr add dev br0 ${H2_N2_IP6}/64 nodad
-	ip -netns h2 link set eth0 master br0 up
-	ip -netns h2 link set eth1 master br0 up
+	ip -netns $h2 link add br0 type bridge
+	ip -netns $h2 link set br0 up
+	ip -netns $h2 addr add dev br0 ${H2_N2_IP}/24
+	ip -netns $h2 -6 addr add dev br0 ${H2_N2_IP6}/64 nodad
+	ip -netns $h2 link set eth0 master br0 up
+	ip -netns $h2 link set eth1 master br0 up
 
 	# h2 to h1 via r2
-	ip -netns h2 route add default via ${R2_N2_IP} dev br0
-	ip -netns h2 -6 route add default via ${R2_N2_IP6} dev br0
+	ip -netns $h2 route add default via ${R2_N2_IP} dev br0
+	ip -netns $h2 -6 route add default via ${R2_N2_IP6} dev br0
 
 	#
 	# r1
 	#
-	setup_vrf r1
-	create_vrf r1 blue 1101
-	create_vrf r1 red 1102
-	ip -netns r1 link set mtu 1400 dev eth1
-	ip -netns r1 link set eth0 vrf blue up
-	ip -netns r1 link set eth1 vrf red up
-	ip -netns r1 addr add dev eth0 ${R1_N1_IP}/24
-	ip -netns r1 -6 addr add dev eth0 ${R1_N1_IP6}/64 nodad
-	ip -netns r1 addr add dev eth1 ${R1_N2_IP}/24
-	ip -netns r1 -6 addr add dev eth1 ${R1_N2_IP6}/64 nodad
+	setup_vrf $r1
+	create_vrf $r1 blue 1101
+	create_vrf $r1 red 1102
+	ip -netns $r1 link set mtu 1400 dev eth1
+	ip -netns $r1 link set eth0 vrf blue up
+	ip -netns $r1 link set eth1 vrf red up
+	ip -netns $r1 addr add dev eth0 ${R1_N1_IP}/24
+	ip -netns $r1 -6 addr add dev eth0 ${R1_N1_IP6}/64 nodad
+	ip -netns $r1 addr add dev eth1 ${R1_N2_IP}/24
+	ip -netns $r1 -6 addr add dev eth1 ${R1_N2_IP6}/64 nodad
 
 	# Route leak from blue to red
-	ip -netns r1 route add vrf blue ${H2_N2} dev red
-	ip -netns r1 -6 route add vrf blue ${H2_N2_6} dev red
+	ip -netns $r1 route add vrf blue ${H2_N2} dev red
+	ip -netns $r1 -6 route add vrf blue ${H2_N2_6} dev red
 
 	# No route leak from red to blue
 
 	#
 	# r2
 	#
-	ip -netns r2 addr add dev eth0 ${R2_N1_IP}/24
-	ip -netns r2 -6 addr add dev eth0 ${R2_N1_IP6}/64 nodad
-	ip -netns r2 addr add dev eth1 ${R2_N2_IP}/24
-	ip -netns r2 -6 addr add dev eth1 ${R2_N2_IP6}/64 nodad
+	ip -netns $r2 addr add dev eth0 ${R2_N1_IP}/24
+	ip -netns $r2 -6 addr add dev eth0 ${R2_N1_IP6}/64 nodad
+	ip -netns $r2 addr add dev eth1 ${R2_N2_IP}/24
+	ip -netns $r2 -6 addr add dev eth1 ${R2_N2_IP6}/64 nodad
 
 	# Wait for ip config to settle
 	sleep 2
@@ -384,14 +375,14 @@ setup_asym()
 
 check_connectivity()
 {
-	ip netns exec h1 ping -c1 -w1 ${H2_N2_IP} >/dev/null 2>&1
+	ip netns exec $h1 ping -c1 -w1 ${H2_N2_IP} >/dev/null 2>&1
 	log_test $? 0 "Basic IPv4 connectivity"
 	return $?
 }
 
 check_connectivity6()
 {
-	ip netns exec h1 "${ping6}" -c1 -w1 ${H2_N2_IP6} >/dev/null 2>&1
+	ip netns exec $h1 "${ping6}" -c1 -w1 ${H2_N2_IP6} >/dev/null 2>&1
 	log_test $? 0 "Basic IPv6 connectivity"
 	return $?
 }
@@ -426,7 +417,7 @@ ipv4_traceroute()
 
 	check_connectivity || return
 
-	run_cmd_grep "${R1_N1_IP}" ip netns exec h1 traceroute ${H2_N2_IP}
+	run_cmd_grep "${R1_N1_IP}" ip netns exec $h1 traceroute ${H2_N2_IP}
 	log_test $? 0 "Traceroute reports a hop on r1"
 }
 
@@ -449,7 +440,7 @@ ipv6_traceroute()
 
 	check_connectivity6 || return
 
-	run_cmd_grep "${R1_N1_IP6}" ip netns exec h1 traceroute6 ${H2_N2_IP6}
+	run_cmd_grep "${R1_N1_IP6}" ip netns exec $h1 traceroute6 ${H2_N2_IP6}
 	log_test $? 0 "Traceroute6 reports a hop on r1"
 }
 
@@ -470,7 +461,7 @@ ipv4_ping_ttl()
 
 	check_connectivity || return
 
-	run_cmd_grep "Time to live exceeded" ip netns exec h1 ping -t1 -c1 -W2 ${H2_N2_IP}
+	run_cmd_grep "Time to live exceeded" ip netns exec $h1 ping -t1 -c1 -W2 ${H2_N2_IP}
 	log_test $? 0 "Ping received ICMP ttl exceeded"
 }
 
@@ -491,7 +482,7 @@ ipv4_ping_frag()
 
 	check_connectivity || return
 
-	run_cmd_grep "Frag needed" ip netns exec h1 ping -s 1450 -Mdo -c1 -W2 ${H2_N2_IP}
+	run_cmd_grep "Frag needed" ip netns exec $h1 ping -s 1450 -Mdo -c1 -W2 ${H2_N2_IP}
 	log_test $? 0 "Ping received ICMP Frag needed"
 }
 
@@ -512,7 +503,7 @@ ipv6_ping_ttl()
 
 	check_connectivity6 || return
 
-	run_cmd_grep "Time exceeded: Hop limit" ip netns exec h1 "${ping6}" -t1 -c1 -W2 ${H2_N2_IP6}
+	run_cmd_grep "Time exceeded: Hop limit" ip netns exec $h1 "${ping6}" -t1 -c1 -W2 ${H2_N2_IP6}
 	log_test $? 0 "Ping received ICMP Hop limit"
 }
 
@@ -533,7 +524,7 @@ ipv6_ping_frag()
 
 	check_connectivity6 || return
 
-	run_cmd_grep "Packet too big" ip netns exec h1 "${ping6}" -s 1450 -Mdo -c1 -W2 ${H2_N2_IP6}
+	run_cmd_grep "Packet too big" ip netns exec $h1 "${ping6}" -s 1450 -Mdo -c1 -W2 ${H2_N2_IP6}
 	log_test $? 0 "Ping received ICMP Packet too big"
 }
 
diff --git a/tools/testing/selftests/net/vrf_strict_mode_test.sh b/tools/testing/selftests/net/vrf_strict_mode_test.sh
index 417d214264f3..01552b542544 100755
--- a/tools/testing/selftests/net/vrf_strict_mode_test.sh
+++ b/tools/testing/selftests/net/vrf_strict_mode_test.sh
@@ -3,9 +3,7 @@
 
 # This test is designed for testing the new VRF strict_mode functionality.
 
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
+source lib.sh
 ret=0
 
 # identifies the "init" network namespace which is often called root network
@@ -247,13 +245,12 @@ setup()
 {
 	modprobe vrf
 
-	ip netns add testns
-	ip netns exec testns ip link set lo up
+	setup_ns testns
 }
 
 cleanup()
 {
-	ip netns del testns 2>/dev/null
+	ip netns del $testns 2>/dev/null
 
 	ip link del vrf100 2>/dev/null
 	ip link del vrf101 2>/dev/null
@@ -298,28 +295,28 @@ vrf_strict_mode_tests_testns()
 {
 	log_section "VRF strict_mode test on testns network namespace"
 
-	vrf_strict_mode_check_support testns
+	vrf_strict_mode_check_support $testns
 
-	strict_mode_check_default testns
+	strict_mode_check_default $testns
 
-	enable_strict_mode_and_check testns
+	enable_strict_mode_and_check $testns
 
-	add_vrf_and_check testns vrf100 100
-	config_vrf_and_check testns 10.0.100.1/24 vrf100
+	add_vrf_and_check $testns vrf100 100
+	config_vrf_and_check $testns 10.0.100.1/24 vrf100
 
-	add_vrf_and_check_fail testns vrf101 100
+	add_vrf_and_check_fail $testns vrf101 100
 
-	add_vrf_and_check_fail testns vrf102 100
+	add_vrf_and_check_fail $testns vrf102 100
 
-	add_vrf_and_check testns vrf200 200
+	add_vrf_and_check $testns vrf200 200
 
-	disable_strict_mode_and_check testns
+	disable_strict_mode_and_check $testns
 
-	add_vrf_and_check testns vrf101 100
+	add_vrf_and_check $testns vrf101 100
 
-	add_vrf_and_check testns vrf102 100
+	add_vrf_and_check $testns vrf102 100
 
-	#the strict_mode is disabled in the testns
+	#the strict_mode is disabled in the $testns
 }
 
 vrf_strict_mode_tests_mix()
@@ -328,25 +325,25 @@ vrf_strict_mode_tests_mix()
 
 	read_strict_mode_compare_and_check init 1
 
-	read_strict_mode_compare_and_check testns 0
+	read_strict_mode_compare_and_check $testns 0
 
-	del_vrf_and_check testns vrf101
+	del_vrf_and_check $testns vrf101
 
-	del_vrf_and_check testns vrf102
+	del_vrf_and_check $testns vrf102
 
 	disable_strict_mode_and_check init
 
-	enable_strict_mode_and_check testns
+	enable_strict_mode_and_check $testns
 
 	enable_strict_mode_and_check init
 	enable_strict_mode_and_check init
 
-	disable_strict_mode_and_check testns
-	disable_strict_mode_and_check testns
+	disable_strict_mode_and_check $testns
+	disable_strict_mode_and_check $testns
 
 	read_strict_mode_compare_and_check init 1
 
-	read_strict_mode_compare_and_check testns 0
+	read_strict_mode_compare_and_check $testns 0
 }
 
 ################################################################################
diff --git a/tools/testing/selftests/net/xfrm_policy.sh b/tools/testing/selftests/net/xfrm_policy.sh
index bdf450eaf60c..457789530645 100755
--- a/tools/testing/selftests/net/xfrm_policy.sh
+++ b/tools/testing/selftests/net/xfrm_policy.sh
@@ -18,8 +18,7 @@
 # ns1: ping 10.0.2.254: does NOT pass via ipsec tunnel (exception)
 # ns2: ping 10.0.1.254: does NOT pass via ipsec tunnel (exception)
 
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
+source lib.sh
 ret=0
 policy_checks_ok=1
 
@@ -204,24 +203,24 @@ check_xfrm() {
 	ip=$2
 	local lret=0
 
-	ip netns exec ns1 ping -q -c 1 10.0.2.$ip > /dev/null
+	ip netns exec ${ns[1]} ping -q -c 1 10.0.2.$ip > /dev/null
 
-	check_ipt_policy_count ns3
+	check_ipt_policy_count ${ns[3]}
 	if [ $? -ne $rval ] ; then
 		lret=1
 	fi
-	check_ipt_policy_count ns4
+	check_ipt_policy_count ${ns[4]}
 	if [ $? -ne $rval ] ; then
 		lret=1
 	fi
 
-	ip netns exec ns2 ping -q -c 1 10.0.1.$ip > /dev/null
+	ip netns exec ${ns[2]} ping -q -c 1 10.0.1.$ip > /dev/null
 
-	check_ipt_policy_count ns3
+	check_ipt_policy_count ${ns[3]}
 	if [ $? -ne $rval ] ; then
 		lret=1
 	fi
-	check_ipt_policy_count ns4
+	check_ipt_policy_count ${ns[4]}
 	if [ $? -ne $rval ] ; then
 		lret=1
 	fi
@@ -270,11 +269,11 @@ check_hthresh_repeat()
 	i=0
 
 	for i in $(seq 1 10);do
-		ip -net ns1 xfrm policy update src e000:0001::0000 dst ff01::0014:0000:0001 dir in tmpl src :: dst :: proto esp mode tunnel priority 100 action allow || break
-		ip -net ns1 xfrm policy set hthresh6 0 28 || break
+		ip -net ${ns[1]} xfrm policy update src e000:0001::0000 dst ff01::0014:0000:0001 dir in tmpl src :: dst :: proto esp mode tunnel priority 100 action allow || break
+		ip -net ${ns[1]} xfrm policy set hthresh6 0 28 || break
 
-		ip -net ns1 xfrm policy update src e000:0001::0000 dst ff01::01 dir in tmpl src :: dst :: proto esp mode tunnel priority 100 action allow || break
-		ip -net ns1 xfrm policy set hthresh6 0 28 || break
+		ip -net ${ns[1]} xfrm policy update src e000:0001::0000 dst ff01::01 dir in tmpl src :: dst :: proto esp mode tunnel priority 100 action allow || break
+		ip -net ${ns[1]} xfrm policy set hthresh6 0 28 || break
 	done
 
 	if [ $i -ne 10 ] ;then
@@ -347,79 +346,80 @@ if [ $? -ne 0 ];then
 	exit $ksft_skip
 fi
 
-for i in 1 2 3 4; do
-    ip netns add ns$i
-    ip -net ns$i link set lo up
-done
+setup_ns ns1 ns2 ns3 ns4
+ns[1]=$ns1
+ns[2]=$ns2
+ns[3]=$ns3
+ns[4]=$ns4
 
 DEV=veth0
-ip link add $DEV netns ns1 type veth peer name eth1 netns ns3
-ip link add $DEV netns ns2 type veth peer name eth1 netns ns4
+ip link add $DEV netns ${ns[1]} type veth peer name eth1 netns ${ns[3]}
+ip link add $DEV netns ${ns[2]} type veth peer name eth1 netns ${ns[4]}
 
-ip link add $DEV netns ns3 type veth peer name veth0 netns ns4
+ip link add $DEV netns ${ns[3]} type veth peer name veth0 netns ${ns[4]}
 
 DEV=veth0
 for i in 1 2; do
-    ip -net ns$i link set $DEV up
-    ip -net ns$i addr add 10.0.$i.2/24 dev $DEV
-    ip -net ns$i addr add dead:$i::2/64 dev $DEV
-
-    ip -net ns$i addr add 10.0.$i.253 dev $DEV
-    ip -net ns$i addr add 10.0.$i.254 dev $DEV
-    ip -net ns$i addr add dead:$i::fd dev $DEV
-    ip -net ns$i addr add dead:$i::fe dev $DEV
+    ip -net ${ns[$i]} link set $DEV up
+    ip -net ${ns[$i]} addr add 10.0.$i.2/24 dev $DEV
+    ip -net ${ns[$i]} addr add dead:$i::2/64 dev $DEV
+
+    ip -net ${ns[$i]} addr add 10.0.$i.253 dev $DEV
+    ip -net ${ns[$i]} addr add 10.0.$i.254 dev $DEV
+    ip -net ${ns[$i]} addr add dead:$i::fd dev $DEV
+    ip -net ${ns[$i]} addr add dead:$i::fe dev $DEV
 done
 
 for i in 3 4; do
-ip -net ns$i link set eth1 up
-ip -net ns$i link set veth0 up
+    ip -net ${ns[$i]} link set eth1 up
+    ip -net ${ns[$i]} link set veth0 up
 done
 
-ip -net ns1 route add default via 10.0.1.1
-ip -net ns2 route add default via 10.0.2.1
+ip -net ${ns[1]} route add default via 10.0.1.1
+ip -net ${ns[2]} route add default via 10.0.2.1
 
-ip -net ns3 addr add 10.0.1.1/24 dev eth1
-ip -net ns3 addr add 10.0.3.1/24 dev veth0
-ip -net ns3 addr add 2001:1::1/64 dev eth1
-ip -net ns3 addr add 2001:3::1/64 dev veth0
+ip -net ${ns[3]} addr add 10.0.1.1/24 dev eth1
+ip -net ${ns[3]} addr add 10.0.3.1/24 dev veth0
+ip -net ${ns[3]} addr add 2001:1::1/64 dev eth1
+ip -net ${ns[3]} addr add 2001:3::1/64 dev veth0
 
-ip -net ns3 route add default via 10.0.3.10
+ip -net ${ns[3]} route add default via 10.0.3.10
 
-ip -net ns4 addr add 10.0.2.1/24 dev eth1
-ip -net ns4 addr add 10.0.3.10/24 dev veth0
-ip -net ns4 addr add 2001:2::1/64 dev eth1
-ip -net ns4 addr add 2001:3::10/64 dev veth0
-ip -net ns4 route add default via 10.0.3.1
+ip -net ${ns[4]} addr add 10.0.2.1/24 dev eth1
+ip -net ${ns[4]} addr add 10.0.3.10/24 dev veth0
+ip -net ${ns[4]} addr add 2001:2::1/64 dev eth1
+ip -net ${ns[4]} addr add 2001:3::10/64 dev veth0
+ip -net ${ns[4]} route add default via 10.0.3.1
 
 for j in 4 6; do
 	for i in 3 4;do
-		ip netns exec ns$i sysctl net.ipv$j.conf.eth1.forwarding=1 > /dev/null
-		ip netns exec ns$i sysctl net.ipv$j.conf.veth0.forwarding=1 > /dev/null
+		ip netns exec ${ns[$i]} sysctl net.ipv$j.conf.eth1.forwarding=1 > /dev/null
+		ip netns exec ${ns[$i]} sysctl net.ipv$j.conf.veth0.forwarding=1 > /dev/null
 	done
 done
 
 # abuse iptables rule counter to check if ping matches a policy
-ip netns exec ns3 iptables -p icmp -A FORWARD -m policy --dir out --pol ipsec
-ip netns exec ns4 iptables -p icmp -A FORWARD -m policy --dir out --pol ipsec
+ip netns exec ${ns[3]} iptables -p icmp -A FORWARD -m policy --dir out --pol ipsec
+ip netns exec ${ns[4]} iptables -p icmp -A FORWARD -m policy --dir out --pol ipsec
 if [ $? -ne 0 ];then
 	echo "SKIP: Could not insert iptables rule"
-	for i in 1 2 3 4;do ip netns del ns$i;done
+	cleanup_ns $ns1 $ns2 $ns3 $ns4
 	exit $ksft_skip
 fi
 
 #          localip  remoteip  localnet    remotenet
-do_esp ns3 10.0.3.1 10.0.3.10 10.0.1.0/24 10.0.2.0/24 $SPI1 $SPI2
-do_esp ns3 dead:3::1 dead:3::10 dead:1::/64 dead:2::/64 $SPI1 $SPI2
-do_esp ns4 10.0.3.10 10.0.3.1 10.0.2.0/24 10.0.1.0/24 $SPI2 $SPI1
-do_esp ns4 dead:3::10 dead:3::1 dead:2::/64 dead:1::/64 $SPI2 $SPI1
+do_esp ${ns[3]} 10.0.3.1 10.0.3.10 10.0.1.0/24 10.0.2.0/24 $SPI1 $SPI2
+do_esp ${ns[3]} dead:3::1 dead:3::10 dead:1::/64 dead:2::/64 $SPI1 $SPI2
+do_esp ${ns[4]} 10.0.3.10 10.0.3.1 10.0.2.0/24 10.0.1.0/24 $SPI2 $SPI1
+do_esp ${ns[4]} dead:3::10 dead:3::1 dead:2::/64 dead:1::/64 $SPI2 $SPI1
 
-do_dummies4 ns3
-do_dummies6 ns4
+do_dummies4 ${ns[3]}
+do_dummies6 ${ns[4]}
 
-do_esp_policy_get_check ns3 10.0.1.0/24 10.0.2.0/24
-do_esp_policy_get_check ns4 10.0.2.0/24 10.0.1.0/24
-do_esp_policy_get_check ns3 dead:1::/64 dead:2::/64
-do_esp_policy_get_check ns4 dead:2::/64 dead:1::/64
+do_esp_policy_get_check ${ns[3]} 10.0.1.0/24 10.0.2.0/24
+do_esp_policy_get_check ${ns[4]} 10.0.2.0/24 10.0.1.0/24
+do_esp_policy_get_check ${ns[3]} dead:1::/64 dead:2::/64
+do_esp_policy_get_check ${ns[4]} dead:2::/64 dead:1::/64
 
 # ping to .254 should use ipsec, exception is not installed.
 check_xfrm 1 254
@@ -432,11 +432,11 @@ fi
 
 # installs exceptions
 #                localip  remoteip   encryptdst  plaindst
-do_exception ns3 10.0.3.1 10.0.3.10 10.0.2.253 10.0.2.240/28
-do_exception ns4 10.0.3.10 10.0.3.1 10.0.1.253 10.0.1.240/28
+do_exception ${ns[3]} 10.0.3.1 10.0.3.10 10.0.2.253 10.0.2.240/28
+do_exception ${ns[4]} 10.0.3.10 10.0.3.1 10.0.1.253 10.0.1.240/28
 
-do_exception ns3 dead:3::1 dead:3::10 dead:2::fd  dead:2:f0::/96
-do_exception ns4 dead:3::10 dead:3::1 dead:1::fd  dead:1:f0::/96
+do_exception ${ns[3]} dead:3::1 dead:3::10 dead:2::fd  dead:2:f0::/96
+do_exception ${ns[4]} dead:3::10 dead:3::1 dead:1::fd  dead:1:f0::/96
 
 check_exceptions "exceptions"
 if [ $? -ne 0 ]; then
@@ -444,14 +444,14 @@ if [ $? -ne 0 ]; then
 fi
 
 # insert block policies with adjacent/overlapping netmasks
-do_overlap ns3
+do_overlap ${ns[3]}
 
 check_exceptions "exceptions and block policies"
 if [ $? -ne 0 ]; then
 	ret=1
 fi
 
-for n in ns3 ns4;do
+for n in ${ns[3]} ${ns[4]};do
 	ip -net $n xfrm policy set hthresh4 28 24 hthresh6 126 125
 	sleep $((RANDOM%5))
 done
@@ -459,19 +459,19 @@ done
 check_exceptions "exceptions and block policies after hresh changes"
 
 # full flush of policy db, check everything gets freed incl. internal meta data
-ip -net ns3 xfrm policy flush
+ip -net ${ns[3]} xfrm policy flush
 
-do_esp_policy ns3 10.0.3.1 10.0.3.10 10.0.1.0/24 10.0.2.0/24
-do_exception ns3 10.0.3.1 10.0.3.10 10.0.2.253 10.0.2.240/28
+do_esp_policy ${ns[3]} 10.0.3.1 10.0.3.10 10.0.1.0/24 10.0.2.0/24
+do_exception ${ns[3]} 10.0.3.1 10.0.3.10 10.0.2.253 10.0.2.240/28
 
 # move inexact policies to hash table
-ip -net ns3 xfrm policy set hthresh4 16 16
+ip -net ${ns[3]} xfrm policy set hthresh4 16 16
 
 sleep $((RANDOM%5))
 check_exceptions "exceptions and block policies after hthresh change in ns3"
 
 # restore original hthresh settings -- move policies back to tables
-for n in ns3 ns4;do
+for n in ${ns[3]} ${ns[4]};do
 	ip -net $n xfrm policy set hthresh4 32 32 hthresh6 128 128
 	sleep $((RANDOM%5))
 done
@@ -479,8 +479,8 @@ check_exceptions "exceptions and block policies after htresh change to normal"
 
 check_hthresh_repeat "policies with repeated htresh change"
 
-check_random_order ns3 "policies inserted in random order"
+check_random_order ${ns[3]} "policies inserted in random order"
 
-for i in 1 2 3 4;do ip netns del ns$i;done
+cleanup_ns $ns1 $ns2 $ns3 $ns4
 
 exit $ret
diff --git a/tools/testing/selftests/netfilter/.gitignore b/tools/testing/selftests/netfilter/.gitignore
index 4b2928e1c19d..c2229b3e40d4 100644
--- a/tools/testing/selftests/netfilter/.gitignore
+++ b/tools/testing/selftests/netfilter/.gitignore
@@ -2,3 +2,5 @@
 nf-queue
 connect_close
 audit_logread
+conntrack_dump_flush
+sctp_collision
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index bced422b78f7..db27153eb4a0 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -14,6 +14,7 @@ HOSTPKG_CONFIG := pkg-config
 CFLAGS += $(shell $(HOSTPKG_CONFIG) --cflags libmnl 2>/dev/null)
 LDLIBS += $(shell $(HOSTPKG_CONFIG) --libs libmnl 2>/dev/null || echo -lmnl)
 
-TEST_GEN_FILES =  nf-queue connect_close audit_logread sctp_collision
+TEST_GEN_FILES =  nf-queue connect_close audit_logread sctp_collision \
+	conntrack_dump_flush
 
 include ../lib.mk
diff --git a/tools/testing/selftests/netfilter/conntrack_dump_flush.c b/tools/testing/selftests/netfilter/conntrack_dump_flush.c
new file mode 100644
index 000000000000..f18c6db13bbf
--- /dev/null
+++ b/tools/testing/selftests/netfilter/conntrack_dump_flush.c
@@ -0,0 +1,430 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <time.h>
+#include <libmnl/libmnl.h>
+#include <netinet/ip.h>
+
+#include <linux/netlink.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nfnetlink_conntrack.h>
+#include <linux/netfilter/nf_conntrack_tcp.h>
+#include "../kselftest_harness.h"
+
+#define TEST_ZONE_ID 123
+#define CTA_FILTER_F_CTA_TUPLE_ZONE (1 << 2)
+
+static int reply_counter;
+
+static int build_cta_tuple_v4(struct nlmsghdr *nlh, int type,
+			      uint32_t src_ip, uint32_t dst_ip,
+			      uint16_t src_port, uint16_t dst_port)
+{
+	struct nlattr *nest, *nest_ip, *nest_proto;
+
+	nest = mnl_attr_nest_start(nlh, type);
+	if (!nest)
+		return -1;
+
+	nest_ip = mnl_attr_nest_start(nlh, CTA_TUPLE_IP);
+	if (!nest_ip)
+		return -1;
+	mnl_attr_put_u32(nlh, CTA_IP_V4_SRC, src_ip);
+	mnl_attr_put_u32(nlh, CTA_IP_V4_DST, dst_ip);
+	mnl_attr_nest_end(nlh, nest_ip);
+
+	nest_proto = mnl_attr_nest_start(nlh, CTA_TUPLE_PROTO);
+	if (!nest_proto)
+		return -1;
+	mnl_attr_put_u8(nlh, CTA_PROTO_NUM, 6);
+	mnl_attr_put_u16(nlh, CTA_PROTO_SRC_PORT, htons(src_port));
+	mnl_attr_put_u16(nlh, CTA_PROTO_DST_PORT, htons(dst_port));
+	mnl_attr_nest_end(nlh, nest_proto);
+
+	mnl_attr_nest_end(nlh, nest);
+}
+
+static int build_cta_tuple_v6(struct nlmsghdr *nlh, int type,
+			      struct in6_addr src_ip, struct in6_addr dst_ip,
+			      uint16_t src_port, uint16_t dst_port)
+{
+	struct nlattr *nest, *nest_ip, *nest_proto;
+
+	nest = mnl_attr_nest_start(nlh, type);
+	if (!nest)
+		return -1;
+
+	nest_ip = mnl_attr_nest_start(nlh, CTA_TUPLE_IP);
+	if (!nest_ip)
+		return -1;
+	mnl_attr_put(nlh, CTA_IP_V6_SRC, sizeof(struct in6_addr), &src_ip);
+	mnl_attr_put(nlh, CTA_IP_V6_DST, sizeof(struct in6_addr), &dst_ip);
+	mnl_attr_nest_end(nlh, nest_ip);
+
+	nest_proto = mnl_attr_nest_start(nlh, CTA_TUPLE_PROTO);
+	if (!nest_proto)
+		return -1;
+	mnl_attr_put_u8(nlh, CTA_PROTO_NUM, 6);
+	mnl_attr_put_u16(nlh, CTA_PROTO_SRC_PORT, htons(src_port));
+	mnl_attr_put_u16(nlh, CTA_PROTO_DST_PORT, htons(dst_port));
+	mnl_attr_nest_end(nlh, nest_proto);
+
+	mnl_attr_nest_end(nlh, nest);
+}
+
+static int build_cta_proto(struct nlmsghdr *nlh)
+{
+	struct nlattr *nest, *nest_proto;
+
+	nest = mnl_attr_nest_start(nlh, CTA_PROTOINFO);
+	if (!nest)
+		return -1;
+
+	nest_proto = mnl_attr_nest_start(nlh, CTA_PROTOINFO_TCP);
+	if (!nest_proto)
+		return -1;
+	mnl_attr_put_u8(nlh, CTA_PROTOINFO_TCP_STATE, TCP_CONNTRACK_ESTABLISHED);
+	mnl_attr_put_u16(nlh, CTA_PROTOINFO_TCP_FLAGS_ORIGINAL, 0x0a0a);
+	mnl_attr_put_u16(nlh, CTA_PROTOINFO_TCP_FLAGS_REPLY, 0x0a0a);
+	mnl_attr_nest_end(nlh, nest_proto);
+
+	mnl_attr_nest_end(nlh, nest);
+}
+
+static int conntrack_data_insert(struct mnl_socket *sock, struct nlmsghdr *nlh,
+				 uint16_t zone)
+{
+	char buf[MNL_SOCKET_BUFFER_SIZE];
+	struct nlmsghdr *rplnlh;
+	unsigned int portid;
+	int err, ret;
+
+	portid = mnl_socket_get_portid(sock);
+
+	ret = build_cta_proto(nlh);
+	if (ret < 0) {
+		perror("build_cta_proto");
+		return -1;
+	}
+	mnl_attr_put_u32(nlh, CTA_TIMEOUT, htonl(20000));
+	mnl_attr_put_u16(nlh, CTA_ZONE, htons(zone));
+
+	if (mnl_socket_sendto(sock, nlh, nlh->nlmsg_len) < 0) {
+		perror("mnl_socket_sendto");
+		return -1;
+	}
+
+	ret = mnl_socket_recvfrom(sock, buf, MNL_SOCKET_BUFFER_SIZE);
+	if (ret < 0) {
+		perror("mnl_socket_recvfrom");
+		return ret;
+	}
+
+	ret = mnl_cb_run(buf, ret, nlh->nlmsg_seq, portid, NULL, NULL);
+	if (ret < 0) {
+		if (errno == EEXIST) {
+			/* The entries are probably still there from a previous
+			 * run. So we are good
+			 */
+			return 0;
+		}
+		perror("mnl_cb_run");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int conntrack_data_generate_v4(struct mnl_socket *sock, uint32_t src_ip,
+				      uint32_t dst_ip, uint16_t zone)
+{
+	char buf[MNL_SOCKET_BUFFER_SIZE];
+	struct nlmsghdr *nlh;
+	struct nfgenmsg *nfh;
+	int ret;
+
+	nlh = mnl_nlmsg_put_header(buf);
+	nlh->nlmsg_type = (NFNL_SUBSYS_CTNETLINK << 8) | IPCTNL_MSG_CT_NEW;
+	nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE |
+			   NLM_F_ACK | NLM_F_EXCL;
+	nlh->nlmsg_seq = time(NULL);
+
+	nfh = mnl_nlmsg_put_extra_header(nlh, sizeof(struct nfgenmsg));
+	nfh->nfgen_family = AF_INET;
+	nfh->version = NFNETLINK_V0;
+	nfh->res_id = 0;
+
+	ret = build_cta_tuple_v4(nlh, CTA_TUPLE_ORIG, src_ip, dst_ip, 12345, 443);
+	if (ret < 0) {
+		perror("build_cta_tuple_v4");
+		return ret;
+	}
+	ret = build_cta_tuple_v4(nlh, CTA_TUPLE_REPLY, dst_ip, src_ip, 443, 12345);
+	if (ret < 0) {
+		perror("build_cta_tuple_v4");
+		return ret;
+	}
+	return conntrack_data_insert(sock, nlh, zone);
+}
+
+static int conntrack_data_generate_v6(struct mnl_socket *sock,
+				      struct in6_addr src_ip,
+				      struct in6_addr dst_ip,
+				      uint16_t zone)
+{
+	char buf[MNL_SOCKET_BUFFER_SIZE];
+	struct nlmsghdr *nlh;
+	struct nfgenmsg *nfh;
+	int ret;
+
+	nlh = mnl_nlmsg_put_header(buf);
+	nlh->nlmsg_type = (NFNL_SUBSYS_CTNETLINK << 8) | IPCTNL_MSG_CT_NEW;
+	nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE |
+			   NLM_F_ACK | NLM_F_EXCL;
+	nlh->nlmsg_seq = time(NULL);
+
+	nfh = mnl_nlmsg_put_extra_header(nlh, sizeof(struct nfgenmsg));
+	nfh->nfgen_family = AF_INET6;
+	nfh->version = NFNETLINK_V0;
+	nfh->res_id = 0;
+
+	ret = build_cta_tuple_v6(nlh, CTA_TUPLE_ORIG, src_ip, dst_ip,
+				 12345, 443);
+	if (ret < 0) {
+		perror("build_cta_tuple_v6");
+		return ret;
+	}
+	ret = build_cta_tuple_v6(nlh, CTA_TUPLE_REPLY, dst_ip, src_ip,
+				 12345, 443);
+	if (ret < 0) {
+		perror("build_cta_tuple_v6");
+		return ret;
+	}
+	return conntrack_data_insert(sock, nlh, zone);
+}
+
+static int count_entries(const struct nlmsghdr *nlh, void *data)
+{
+	reply_counter++;
+}
+
+static int conntracK_count_zone(struct mnl_socket *sock, uint16_t zone)
+{
+	char buf[MNL_SOCKET_BUFFER_SIZE];
+	struct nlmsghdr *nlh, *rplnlh;
+	struct nfgenmsg *nfh;
+	struct nlattr *nest;
+	unsigned int portid;
+	int err, ret;
+
+	portid = mnl_socket_get_portid(sock);
+
+	nlh = mnl_nlmsg_put_header(buf);
+	nlh->nlmsg_type	= (NFNL_SUBSYS_CTNETLINK << 8) | IPCTNL_MSG_CT_GET;
+	nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP;
+	nlh->nlmsg_seq = time(NULL);
+
+	nfh = mnl_nlmsg_put_extra_header(nlh, sizeof(struct nfgenmsg));
+	nfh->nfgen_family = AF_UNSPEC;
+	nfh->version = NFNETLINK_V0;
+	nfh->res_id = 0;
+
+	mnl_attr_put_u16(nlh, CTA_ZONE, htons(zone));
+
+	ret = mnl_socket_sendto(sock, nlh, nlh->nlmsg_len);
+	if (ret < 0) {
+		perror("mnl_socket_sendto");
+		return ret;
+	}
+
+	reply_counter = 0;
+	ret = mnl_socket_recvfrom(sock, buf, MNL_SOCKET_BUFFER_SIZE);
+	while (ret > 0) {
+		ret = mnl_cb_run(buf, ret, nlh->nlmsg_seq, portid,
+				 count_entries, NULL);
+		if (ret <= MNL_CB_STOP)
+			break;
+
+		ret = mnl_socket_recvfrom(sock, buf, MNL_SOCKET_BUFFER_SIZE);
+	}
+	if (ret < 0) {
+		perror("mnl_socket_recvfrom");
+		return ret;
+	}
+
+	return reply_counter;
+}
+
+static int conntrack_flush_zone(struct mnl_socket *sock, uint16_t zone)
+{
+	char buf[MNL_SOCKET_BUFFER_SIZE];
+	struct nlmsghdr *nlh, *rplnlh;
+	struct nfgenmsg *nfh;
+	struct nlattr *nest;
+	unsigned int portid;
+	int err, ret;
+
+	portid = mnl_socket_get_portid(sock);
+
+	nlh = mnl_nlmsg_put_header(buf);
+	nlh->nlmsg_type	= (NFNL_SUBSYS_CTNETLINK << 8) | IPCTNL_MSG_CT_DELETE;
+	nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+	nlh->nlmsg_seq = time(NULL);
+
+	nfh = mnl_nlmsg_put_extra_header(nlh, sizeof(struct nfgenmsg));
+	nfh->nfgen_family = AF_UNSPEC;
+	nfh->version = NFNETLINK_V0;
+	nfh->res_id = 0;
+
+	mnl_attr_put_u16(nlh, CTA_ZONE, htons(zone));
+
+	ret = mnl_socket_sendto(sock, nlh, nlh->nlmsg_len);
+	if (ret < 0) {
+		perror("mnl_socket_sendto");
+		return ret;
+	}
+
+	ret = mnl_socket_recvfrom(sock, buf, MNL_SOCKET_BUFFER_SIZE);
+	if (ret < 0) {
+		perror("mnl_socket_recvfrom");
+		return ret;
+	}
+
+	ret = mnl_cb_run(buf, ret, nlh->nlmsg_seq, portid, NULL, NULL);
+	if (ret < 0) {
+		perror("mnl_cb_run");
+		return ret;
+	}
+
+	return 0;
+}
+
+FIXTURE(conntrack_dump_flush)
+{
+	struct mnl_socket *sock;
+};
+
+FIXTURE_SETUP(conntrack_dump_flush)
+{
+	struct in6_addr src, dst;
+	int ret;
+
+	self->sock = mnl_socket_open(NETLINK_NETFILTER);
+	if (!self->sock) {
+		perror("mnl_socket_open");
+		exit(EXIT_FAILURE);
+	}
+
+	if (mnl_socket_bind(self->sock, 0, MNL_SOCKET_AUTOPID) < 0) {
+		perror("mnl_socket_bind");
+		exit(EXIT_FAILURE);
+	}
+
+	ret = conntracK_count_zone(self->sock, TEST_ZONE_ID);
+	if (ret < 0 && errno == EPERM)
+		SKIP(return, "Needs to be run as root");
+	else if (ret < 0 && errno == EOPNOTSUPP)
+		SKIP(return, "Kernel does not seem to support conntrack zones");
+
+	ret = conntrack_data_generate_v4(self->sock, 0xf0f0f0f0, 0xf1f1f1f1,
+					 TEST_ZONE_ID);
+	EXPECT_EQ(ret, 0);
+	ret = conntrack_data_generate_v4(self->sock, 0xf2f2f2f2, 0xf3f3f3f3,
+					 TEST_ZONE_ID + 1);
+	EXPECT_EQ(ret, 0);
+	ret = conntrack_data_generate_v4(self->sock, 0xf4f4f4f4, 0xf5f5f5f5,
+					 TEST_ZONE_ID + 2);
+	EXPECT_EQ(ret, 0);
+
+	src = (struct in6_addr) {{
+		.__u6_addr32 = {
+			0xb80d0120,
+			0x00000000,
+			0x00000000,
+			0x01000000
+		}
+	}};
+	dst = (struct in6_addr) {{
+		.__u6_addr32 = {
+			0xb80d0120,
+			0x00000000,
+			0x00000000,
+			0x02000000
+		}
+	}};
+	ret = conntrack_data_generate_v6(self->sock, src, dst,
+					 TEST_ZONE_ID);
+	EXPECT_EQ(ret, 0);
+	src = (struct in6_addr) {{
+		.__u6_addr32 = {
+			0xb80d0120,
+			0x00000000,
+			0x00000000,
+			0x03000000
+		}
+	}};
+	dst = (struct in6_addr) {{
+		.__u6_addr32 = {
+			0xb80d0120,
+			0x00000000,
+			0x00000000,
+			0x04000000
+		}
+	}};
+	ret = conntrack_data_generate_v6(self->sock, src, dst,
+					 TEST_ZONE_ID + 1);
+	EXPECT_EQ(ret, 0);
+	src = (struct in6_addr) {{
+		.__u6_addr32 = {
+			0xb80d0120,
+			0x00000000,
+			0x00000000,
+			0x05000000
+		}
+	}};
+	dst = (struct in6_addr) {{
+		.__u6_addr32 = {
+			0xb80d0120,
+			0x00000000,
+			0x00000000,
+			0x06000000
+		}
+	}};
+	ret = conntrack_data_generate_v6(self->sock, src, dst,
+					 TEST_ZONE_ID + 2);
+	EXPECT_EQ(ret, 0);
+
+	ret = conntracK_count_zone(self->sock, TEST_ZONE_ID);
+	EXPECT_GE(ret, 2);
+	if (ret > 2)
+		SKIP(return, "kernel does not support filtering by zone");
+}
+
+FIXTURE_TEARDOWN(conntrack_dump_flush)
+{
+}
+
+TEST_F(conntrack_dump_flush, test_dump_by_zone)
+{
+	int ret;
+
+	ret = conntracK_count_zone(self->sock, TEST_ZONE_ID);
+	EXPECT_EQ(ret, 2);
+}
+
+TEST_F(conntrack_dump_flush, test_flush_by_zone)
+{
+	int ret;
+
+	ret = conntrack_flush_zone(self->sock, TEST_ZONE_ID);
+	EXPECT_EQ(ret, 0);
+	ret = conntracK_count_zone(self->sock, TEST_ZONE_ID);
+	EXPECT_EQ(ret, 0);
+	ret = conntracK_count_zone(self->sock, TEST_ZONE_ID + 1);
+	EXPECT_EQ(ret, 2);
+	ret = conntracK_count_zone(self->sock, TEST_ZONE_ID + 2);
+	EXPECT_EQ(ret, 2);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/nolibc/.gitignore b/tools/testing/selftests/nolibc/.gitignore
index 5119f9f7afd2..35d247a0d5bd 100644
--- a/tools/testing/selftests/nolibc/.gitignore
+++ b/tools/testing/selftests/nolibc/.gitignore
@@ -3,4 +3,5 @@
 /libc-test
 /nolibc-test
 /run.out
+/run.out.*
 /sysroot/
diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile
index a0fc07253baf..40dd95228051 100644
--- a/tools/testing/selftests/nolibc/Makefile
+++ b/tools/testing/selftests/nolibc/Makefile
@@ -1,9 +1,16 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for nolibc tests
 include ../../../scripts/Makefile.include
+include ../../../scripts/utilities.mak
 # We need this for the "cc-option" macro.
 include ../../../build/Build.include
 
+ifneq ($(O),)
+ifneq ($(call is-absolute,$(O)),y)
+$(error Only absolute O= parameters are supported)
+endif
+endif
+
 # we're in ".../tools/testing/selftests/nolibc"
 ifeq ($(srctree),)
 srctree := $(patsubst %/tools/testing/selftests/,%,$(dir $(CURDIR)))
@@ -14,6 +21,8 @@ include $(srctree)/scripts/subarch.include
 ARCH = $(SUBARCH)
 endif
 
+objtree ?= $(srctree)
+
 # XARCH extends the kernel's ARCH with a few variants of the same
 # architecture that only differ by the configuration, the toolchain
 # and the Qemu program used. It is copied as-is into ARCH except for
@@ -31,12 +40,15 @@ endif
 
 # configure default variants for target kernel supported architectures
 XARCH_powerpc    = ppc
+XARCH_mips       = mips32le
 XARCH            = $(or $(XARCH_$(ARCH)),$(ARCH))
 
 # map from user input variants to their kernel supported architectures
 ARCH_ppc         = powerpc
 ARCH_ppc64       = powerpc
 ARCH_ppc64le     = powerpc
+ARCH_mips32le    = mips
+ARCH_mips32be    = mips
 ARCH            := $(or $(ARCH_$(XARCH)),$(XARCH))
 
 # kernel image names by architecture
@@ -45,14 +57,15 @@ IMAGE_x86_64     = arch/x86/boot/bzImage
 IMAGE_x86        = arch/x86/boot/bzImage
 IMAGE_arm64      = arch/arm64/boot/Image
 IMAGE_arm        = arch/arm/boot/zImage
-IMAGE_mips       = vmlinuz
+IMAGE_mips32le   = vmlinuz
+IMAGE_mips32be   = vmlinuz
 IMAGE_ppc        = vmlinux
 IMAGE_ppc64      = vmlinux
 IMAGE_ppc64le    = arch/powerpc/boot/zImage
 IMAGE_riscv      = arch/riscv/boot/Image
 IMAGE_s390       = arch/s390/boot/bzImage
 IMAGE_loongarch  = arch/loongarch/boot/vmlinuz.efi
-IMAGE            = $(IMAGE_$(XARCH))
+IMAGE            = $(objtree)/$(IMAGE_$(XARCH))
 IMAGE_NAME       = $(notdir $(IMAGE))
 
 # default kernel configurations that appear to be usable
@@ -61,7 +74,8 @@ DEFCONFIG_x86_64     = defconfig
 DEFCONFIG_x86        = defconfig
 DEFCONFIG_arm64      = defconfig
 DEFCONFIG_arm        = multi_v7_defconfig
-DEFCONFIG_mips       = malta_defconfig
+DEFCONFIG_mips32le   = malta_defconfig
+DEFCONFIG_mips32be   = malta_defconfig
 DEFCONFIG_ppc        = pmac32_defconfig
 DEFCONFIG_ppc64      = powernv_be_defconfig
 DEFCONFIG_ppc64le    = powernv_defconfig
@@ -70,6 +84,9 @@ DEFCONFIG_s390       = defconfig
 DEFCONFIG_loongarch  = defconfig
 DEFCONFIG            = $(DEFCONFIG_$(XARCH))
 
+EXTRACONFIG_mips32be = -d CONFIG_CPU_LITTLE_ENDIAN -e CONFIG_CPU_BIG_ENDIAN
+EXTRACONFIG           = $(EXTRACONFIG_$(XARCH))
+
 # optional tests to run (default = all)
 TEST =
 
@@ -79,7 +96,8 @@ QEMU_ARCH_x86_64     = x86_64
 QEMU_ARCH_x86        = x86_64
 QEMU_ARCH_arm64      = aarch64
 QEMU_ARCH_arm        = arm
-QEMU_ARCH_mips       = mipsel  # works with malta_defconfig
+QEMU_ARCH_mips32le   = mipsel  # works with malta_defconfig
+QEMU_ARCH_mips32be  = mips
 QEMU_ARCH_ppc        = ppc
 QEMU_ARCH_ppc64      = ppc64
 QEMU_ARCH_ppc64le    = ppc64
@@ -88,20 +106,31 @@ QEMU_ARCH_s390       = s390x
 QEMU_ARCH_loongarch  = loongarch64
 QEMU_ARCH            = $(QEMU_ARCH_$(XARCH))
 
+QEMU_ARCH_USER_ppc64le = ppc64le
+QEMU_ARCH_USER         = $(or $(QEMU_ARCH_USER_$(XARCH)),$(QEMU_ARCH_$(XARCH)))
+
+QEMU_BIOS_DIR = /usr/share/edk2/
+QEMU_BIOS_loongarch = $(QEMU_BIOS_DIR)/loongarch64/OVMF_CODE.fd
+
+ifneq ($(QEMU_BIOS_$(XARCH)),)
+QEMU_ARGS_BIOS = -bios $(QEMU_BIOS_$(XARCH))
+endif
+
 # QEMU_ARGS : some arch-specific args to pass to qemu
 QEMU_ARGS_i386       = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)"
 QEMU_ARGS_x86_64     = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)"
 QEMU_ARGS_x86        = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)"
 QEMU_ARGS_arm64      = -M virt -cpu cortex-a53 -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)"
 QEMU_ARGS_arm        = -M virt -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)"
-QEMU_ARGS_mips       = -M malta -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)"
+QEMU_ARGS_mips32le   = -M malta -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)"
+QEMU_ARGS_mips32be   = -M malta -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)"
 QEMU_ARGS_ppc        = -M g3beige -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)"
 QEMU_ARGS_ppc64      = -M powernv -append "console=hvc0 panic=-1 $(TEST:%=NOLIBC_TEST=%)"
 QEMU_ARGS_ppc64le    = -M powernv -append "console=hvc0 panic=-1 $(TEST:%=NOLIBC_TEST=%)"
 QEMU_ARGS_riscv      = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)"
 QEMU_ARGS_s390       = -M s390-ccw-virtio -m 1G -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)"
 QEMU_ARGS_loongarch  = -M virt -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)"
-QEMU_ARGS            = $(QEMU_ARGS_$(XARCH)) $(QEMU_ARGS_EXTRA)
+QEMU_ARGS            = $(QEMU_ARGS_$(XARCH)) $(QEMU_ARGS_BIOS) $(QEMU_ARGS_EXTRA)
 
 # OUTPUT is only set when run from the main makefile, otherwise
 # it defaults to this nolibc directory.
@@ -118,7 +147,8 @@ CFLAGS_ppc = -m32 -mbig-endian -mno-vsx $(call cc-option,-mmultiple)
 CFLAGS_ppc64 = -m64 -mbig-endian -mno-vsx $(call cc-option,-mmultiple)
 CFLAGS_ppc64le = -m64 -mlittle-endian -mno-vsx $(call cc-option,-mabi=elfv2)
 CFLAGS_s390 = -m64
-CFLAGS_mips = -EL
+CFLAGS_mips32le = -EL -mabi=32 -fPIC
+CFLAGS_mips32be = -EB -mabi=32
 CFLAGS_STACKPROTECTOR ?= $(call cc-option,-mstack-protector-guard=global $(call cc-option,-fstack-protector-all))
 CFLAGS  ?= -Os -fno-ident -fno-asynchronous-unwind-tables -std=c89 -W -Wall -Wextra \
 		$(call cc-option,-fno-stack-protector) \
@@ -167,7 +197,8 @@ sysroot: sysroot/$(ARCH)/include
 sysroot/$(ARCH)/include:
 	$(Q)rm -rf sysroot/$(ARCH) sysroot/sysroot
 	$(QUIET_MKDIR)mkdir -p sysroot
-	$(Q)$(MAKE) -C ../../../include/nolibc ARCH=$(ARCH) OUTPUT=$(CURDIR)/sysroot/ headers_standalone
+	$(Q)$(MAKE) -C $(srctree) outputmakefile
+	$(Q)$(MAKE) -C $(srctree)/tools/include/nolibc ARCH=$(ARCH) OUTPUT=$(CURDIR)/sysroot/ headers_standalone
 	$(Q)mv sysroot/sysroot sysroot/$(ARCH)
 
 ifneq ($(NOLIBC_SYSROOT),0)
@@ -177,7 +208,7 @@ nolibc-test: nolibc-test.c nolibc-test-linkage.c sysroot/$(ARCH)/include
 else
 nolibc-test: nolibc-test.c nolibc-test-linkage.c
 	$(QUIET_CC)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ \
-	  -nostdlib -static -include ../../../include/nolibc/nolibc.h nolibc-test.c nolibc-test-linkage.c -lgcc
+	  -nostdlib -static -include $(srctree)/tools/include/nolibc/nolibc.h nolibc-test.c nolibc-test-linkage.c -lgcc
 endif
 
 libc-test: nolibc-test.c nolibc-test-linkage.c
@@ -195,11 +226,11 @@ run-nolibc-test: nolibc-test
 
 # qemu user-land test
 run-user: nolibc-test
-	$(Q)qemu-$(QEMU_ARCH) ./nolibc-test > "$(CURDIR)/run.out" || :
+	$(Q)qemu-$(QEMU_ARCH_USER) ./nolibc-test > "$(CURDIR)/run.out" || :
 	$(Q)$(REPORT) $(CURDIR)/run.out
 
 initramfs.cpio: kernel nolibc-test
-	$(QUIET_GEN)echo 'file /init nolibc-test 755 0 0' | $(srctree)/usr/gen_init_cpio - > initramfs.cpio
+	$(QUIET_GEN)echo 'file /init nolibc-test 755 0 0' | $(objtree)/usr/gen_init_cpio - > initramfs.cpio
 
 initramfs: nolibc-test
 	$(QUIET_MKDIR)mkdir -p initramfs
@@ -208,21 +239,25 @@ initramfs: nolibc-test
 
 defconfig:
 	$(Q)$(MAKE) -C $(srctree) ARCH=$(ARCH) CC=$(CC) CROSS_COMPILE=$(CROSS_COMPILE) mrproper $(DEFCONFIG) prepare
+	$(Q)if [ -n "$(EXTRACONFIG)" ]; then \
+		$(srctree)/scripts/config --file $(objtree)/.config $(EXTRACONFIG); \
+		$(MAKE) -C $(srctree) ARCH=$(ARCH) CC=$(CC) CROSS_COMPILE=$(CROSS_COMPILE) olddefconfig < /dev/null; \
+	fi
 
 kernel:
-	$(Q)$(MAKE) -C $(srctree) ARCH=$(ARCH) CC=$(CC) CROSS_COMPILE=$(CROSS_COMPILE) $(IMAGE_NAME)
+	$(Q)$(MAKE) -C $(srctree) ARCH=$(ARCH) CC=$(CC) CROSS_COMPILE=$(CROSS_COMPILE) $(IMAGE_NAME) < /dev/null
 
 kernel-standalone: initramfs
-	$(Q)$(MAKE) -C $(srctree) ARCH=$(ARCH) CC=$(CC) CROSS_COMPILE=$(CROSS_COMPILE) $(IMAGE_NAME) CONFIG_INITRAMFS_SOURCE=$(CURDIR)/initramfs
+	$(Q)$(MAKE) -C $(srctree) ARCH=$(ARCH) CC=$(CC) CROSS_COMPILE=$(CROSS_COMPILE) $(IMAGE_NAME) CONFIG_INITRAMFS_SOURCE=$(CURDIR)/initramfs < /dev/null
 
 # run the tests after building the kernel
 run: kernel initramfs.cpio
-	$(Q)qemu-system-$(QEMU_ARCH) -display none -no-reboot -kernel "$(srctree)/$(IMAGE)" -initrd initramfs.cpio -serial stdio $(QEMU_ARGS) > "$(CURDIR)/run.out"
+	$(Q)qemu-system-$(QEMU_ARCH) -display none -no-reboot -kernel "$(IMAGE)" -initrd initramfs.cpio -serial stdio $(QEMU_ARGS) > "$(CURDIR)/run.out"
 	$(Q)$(REPORT) $(CURDIR)/run.out
 
 # re-run the tests from an existing kernel
 rerun:
-	$(Q)qemu-system-$(QEMU_ARCH) -display none -no-reboot -kernel "$(srctree)/$(IMAGE)" -initrd initramfs.cpio -serial stdio $(QEMU_ARGS) > "$(CURDIR)/run.out"
+	$(Q)qemu-system-$(QEMU_ARCH) -display none -no-reboot -kernel "$(IMAGE)" -initrd initramfs.cpio -serial stdio $(QEMU_ARGS) > "$(CURDIR)/run.out"
 	$(Q)$(REPORT) $(CURDIR)/run.out
 
 # report with existing test log
diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c
index 2f10541e6f38..6ba4f8275ac4 100644
--- a/tools/testing/selftests/nolibc/nolibc-test.c
+++ b/tools/testing/selftests/nolibc/nolibc-test.c
@@ -22,6 +22,7 @@
 #include <sys/mount.h>
 #include <sys/prctl.h>
 #include <sys/reboot.h>
+#include <sys/resource.h>
 #include <sys/stat.h>
 #include <sys/syscall.h>
 #include <sys/sysmacros.h>
@@ -130,11 +131,17 @@ static const char *errorname(int err)
 	}
 }
 
-static void putcharn(char c, size_t n)
+static void align_result(size_t llen)
 {
-	char buf[64];
+	const size_t align = 64;
+	char buf[align];
+	size_t n;
 
-	memset(buf, c, n);
+	if (llen >= align)
+		return;
+
+	n = align - llen;
+	memset(buf, ' ', n);
 	buf[n] = '\0';
 	fputs(buf, stdout);
 }
@@ -150,14 +157,13 @@ static void result(int llen, enum RESULT r)
 	const char *msg;
 
 	if (r == OK)
-		msg = " [OK]";
+		msg = "  [OK]";
 	else if (r == SKIPPED)
 		msg = "[SKIPPED]";
 	else
-		msg = "[FAIL]";
+		msg = " [FAIL]";
 
-	if (llen < 64)
-		putcharn(' ', 64 - llen);
+	align_result(llen);
 	puts(msg);
 }
 
@@ -834,6 +840,33 @@ int test_pipe(void)
 	return !!memcmp(buf, msg, len);
 }
 
+int test_rlimit(void)
+{
+	struct rlimit rlim = {
+		.rlim_cur = 1 << 20,
+		.rlim_max = 1 << 21,
+	};
+	int ret;
+
+	ret = setrlimit(RLIMIT_CORE, &rlim);
+	if (ret)
+		return -1;
+
+	rlim.rlim_cur = 0;
+	rlim.rlim_max = 0;
+
+	ret = getrlimit(RLIMIT_CORE, &rlim);
+	if (ret)
+		return -1;
+
+	if (rlim.rlim_cur != 1 << 20)
+		return -1;
+	if (rlim.rlim_max != 1 << 21)
+		return -1;
+
+	return 0;
+}
+
 
 /* Run syscall tests between IDs <min> and <max>.
  * Return 0 on success, non-zero on failure.
@@ -905,7 +938,6 @@ int run_syscall(int min, int max)
 		CASE_TEST(gettimeofday_tv_tz);EXPECT_SYSZR(1, gettimeofday(&tv, &tz)); break;
 		CASE_TEST(getpagesize);       EXPECT_SYSZR(1, test_getpagesize()); break;
 		CASE_TEST(ioctl_tiocinq);     EXPECT_SYSZR(1, ioctl(0, TIOCINQ, &tmp)); break;
-		CASE_TEST(ioctl_tiocinq);     EXPECT_SYSZR(1, ioctl(0, TIOCINQ, &tmp)); break;
 		CASE_TEST(link_root1);        EXPECT_SYSER(1, link("/", "/"), -1, EEXIST); break;
 		CASE_TEST(link_blah);         EXPECT_SYSER(1, link("/proc/self/blah", "/blah"), -1, ENOENT); break;
 		CASE_TEST(link_dir);          EXPECT_SYSER(euid0, link("/", "/blah"), -1, EPERM); break;
@@ -924,6 +956,7 @@ int run_syscall(int min, int max)
 		CASE_TEST(poll_fault);        EXPECT_SYSER(1, poll(NULL, 1, 0), -1, EFAULT); break;
 		CASE_TEST(prctl);             EXPECT_SYSER(1, prctl(PR_SET_NAME, (unsigned long)NULL, 0, 0, 0), -1, EFAULT); break;
 		CASE_TEST(read_badf);         EXPECT_SYSER(1, read(-1, &tmp, 1), -1, EBADF); break;
+		CASE_TEST(rlimit);            EXPECT_SYSZR(1, test_rlimit()); break;
 		CASE_TEST(rmdir_blah);        EXPECT_SYSER(1, rmdir("/blah"), -1, ENOENT); break;
 		CASE_TEST(sched_yield);       EXPECT_SYSZR(1, sched_yield()); break;
 		CASE_TEST(select_null);       EXPECT_SYSZR(1, ({ struct timeval tv = { 0 }; select(0, NULL, NULL, NULL, &tv); })); break;
@@ -1133,6 +1166,7 @@ static int run_protection(int min __attribute__((unused)),
 {
 	pid_t pid;
 	int llen = 0, status;
+	struct rlimit rlimit = { 0, 0 };
 
 	llen += printf("0 -fstackprotector ");
 
@@ -1164,6 +1198,7 @@ static int run_protection(int min __attribute__((unused)),
 		close(STDERR_FILENO);
 
 		prctl(PR_SET_DUMPABLE, 0, 0, 0, 0);
+		setrlimit(RLIMIT_CORE, &rlimit);
 		smash_stack();
 		return 1;
 
diff --git a/tools/testing/selftests/nolibc/run-tests.sh b/tools/testing/selftests/nolibc/run-tests.sh
new file mode 100755
index 000000000000..c0a5a7cea9fa
--- /dev/null
+++ b/tools/testing/selftests/nolibc/run-tests.sh
@@ -0,0 +1,169 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test runner for nolibc tests
+
+set -e
+
+trap 'echo Aborting...' 'ERR'
+
+crosstool_version=13.2.0
+hostarch=x86_64
+nproc=$(( $(nproc) + 2))
+cache_dir="${XDG_CACHE_HOME:-"$HOME"/.cache}"
+download_location="${cache_dir}/crosstools/"
+build_location="$(realpath "${cache_dir}"/nolibc-tests/)"
+perform_download=0
+test_mode=system
+archs="i386 x86_64 arm64 arm mips32le mips32be ppc ppc64 ppc64le riscv s390 loongarch"
+
+TEMP=$(getopt -o 'j:d:c:b:a:m:ph' -n "$0" -- "$@")
+
+eval set -- "$TEMP"
+unset TEMP
+
+print_usage() {
+	cat <<EOF
+Run nolibc testsuite for multiple architectures with crosstools
+
+Usage:
+ $0 [options] <architectures>
+
+Known architectures:
+ ${archs}
+
+Options:
+ -j [N]         Allow N jobs at once (default: ${nproc})
+ -p             Allow download of toolchains
+ -d [DIR]       Download location for toolchains (default: ${download_location})
+ -c [VERSION]   Version of toolchains to use (default: ${crosstool_version})
+ -a [ARCH]      Host architecture of toolchains to use (default: ${hostarch})
+ -b [DIR]       Build location (default: ${build_location})
+ -m [MODE]      Test mode user/system (default: ${test_mode})
+EOF
+}
+
+while true; do
+	case "$1" in
+		'-j')
+			nproc="$2"
+			shift 2; continue ;;
+		'-p')
+			perform_download=1
+			shift; continue ;;
+		'-d')
+			download_location="$2"
+			shift 2; continue ;;
+		'-c')
+			crosstool_version="$2"
+			shift 2; continue ;;
+		'-a')
+			hostarch="$2"
+			shift 2; continue ;;
+		'-b')
+			build_location="$(realpath "$2")"
+			shift 2; continue ;;
+		'-m')
+			test_mode="$2"
+			shift 2; continue ;;
+		'-h')
+			print_usage
+			exit 0
+			;;
+		'--')
+			shift; break ;;
+		*)
+			echo 'Internal error!' >&2; exit 1 ;;
+	esac
+done
+
+if [[ -n "$*" ]]; then
+	archs="$*"
+fi
+
+crosstool_arch() {
+	case "$1" in
+	arm64) echo aarch64;;
+	ppc) echo powerpc;;
+	ppc64) echo powerpc64;;
+	ppc64le) echo powerpc64;;
+	riscv) echo riscv64;;
+	loongarch) echo loongarch64;;
+	mips*) echo mips;;
+	*) echo "$1";;
+	esac
+}
+
+crosstool_abi() {
+	case "$1" in
+	arm) echo linux-gnueabi;;
+	*) echo linux;;
+	esac
+}
+
+download_crosstool() {
+	arch="$(crosstool_arch "$1")"
+	abi="$(crosstool_abi "$1")"
+
+	archive_name="${hostarch}-gcc-${crosstool_version}-nolibc-${arch}-${abi}.tar.gz"
+	url="https://mirrors.edge.kernel.org/pub/tools/crosstool/files/bin/${hostarch}/${crosstool_version}/${archive_name}"
+	archive="${download_location}${archive_name}"
+	stamp="${archive}.stamp"
+
+	[ -f "${stamp}" ] && return
+
+	echo "Downloading crosstools ${arch} ${crosstool_version}"
+	mkdir -p "${download_location}"
+	curl -o "${archive}" --fail --continue-at - "${url}"
+	tar -C "${download_location}" -xf "${archive}"
+	touch "${stamp}"
+}
+
+# capture command output, print it on failure
+# mimics chronic(1) from moreutils
+function swallow_output() {
+	if ! OUTPUT="$("$@" 2>&1)"; then
+		echo "$OUTPUT"
+		return 1
+	fi
+	return 0
+}
+
+test_arch() {
+	arch=$1
+	ct_arch=$(crosstool_arch "$arch")
+	ct_abi=$(crosstool_abi "$1")
+	cross_compile=$(realpath "${download_location}gcc-${crosstool_version}-nolibc/${ct_arch}-${ct_abi}/bin/${ct_arch}-${ct_abi}-")
+	build_dir="${build_location}/${arch}"
+	MAKE=(make -j"${nproc}" XARCH="${arch}" CROSS_COMPILE="${cross_compile}" O="${build_dir}")
+
+	mkdir -p "$build_dir"
+	if [ "$test_mode" = "system" ] && [ ! -f "${build_dir}/.config" ]; then
+		swallow_output "${MAKE[@]}" defconfig
+	fi
+	case "$test_mode" in
+		'system')
+			test_target=run
+			;;
+		'user')
+			test_target=run-user
+			;;
+		*)
+			echo "Unknown mode $test_mode"
+			exit 1
+	esac
+	printf '%-15s' "$arch:"
+	swallow_output "${MAKE[@]}" "$test_target" V=1
+	cp run.out run.out."${arch}"
+	"${MAKE[@]}" report | grep passed
+}
+
+if [ "$perform_download" -ne 0 ]; then
+	for arch in $archs; do
+		download_crosstool "$arch"
+	done
+fi
+
+for arch in $archs; do
+	test_arch "$arch"
+done
diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile
index 7ea42fa02eab..c376151982c4 100644
--- a/tools/testing/selftests/powerpc/Makefile
+++ b/tools/testing/selftests/powerpc/Makefile
@@ -32,6 +32,8 @@ SUB_DIRS = alignment		\
 	   vphn         \
 	   math		\
 	   papr_attributes	\
+	   papr_vpd		\
+	   papr_sysparm		\
 	   ptrace	\
 	   security	\
 	   mce
diff --git a/tools/testing/selftests/powerpc/math/fpu.h b/tools/testing/selftests/powerpc/math/fpu.h
new file mode 100644
index 000000000000..a8ad0d42604e
--- /dev/null
+++ b/tools/testing/selftests/powerpc/math/fpu.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright 2023, Michael Ellerman, IBM Corporation.
+ */
+
+#ifndef _SELFTESTS_POWERPC_FPU_H
+#define _SELFTESTS_POWERPC_FPU_H
+
+static inline void randomise_darray(double *darray, int num)
+{
+	long val;
+
+	for (int i = 0; i < num; i++) {
+		val = random();
+		if (val & 1)
+			val *= -1;
+
+		if (val & 2)
+			darray[i] = 1.0 / val;
+		else
+			darray[i] = val * val;
+	}
+}
+
+#endif /* _SELFTESTS_POWERPC_FPU_H */
diff --git a/tools/testing/selftests/powerpc/math/fpu_asm.S b/tools/testing/selftests/powerpc/math/fpu_asm.S
index 9dc0c158f871..efe1e1be4695 100644
--- a/tools/testing/selftests/powerpc/math/fpu_asm.S
+++ b/tools/testing/selftests/powerpc/math/fpu_asm.S
@@ -66,6 +66,40 @@ FUNC_START(check_fpu)
 	li	r3,0 # Success!!!
 1:	blr
 
+
+// int check_all_fprs(double darray[32])
+FUNC_START(check_all_fprs)
+	PUSH_BASIC_STACK(8)
+	mr	r4, r3	// r4 = darray
+	li	r3, 1	// prepare for failure
+
+	stfd	f31, STACK_FRAME_LOCAL(0, 0)(sp) // backup f31
+
+	// Check regs f0-f30, using f31 as scratch
+	.set i, 0
+	.rept 31
+	lfd	f31, (8 * i)(r4)	// load expected value
+	fcmpu	cr0, i, f31		// compare
+	bne	cr0, 1f			// bail if mismatch
+	.set i, i + 1
+	.endr
+
+	lfd	f31, STACK_FRAME_LOCAL(0, 0)(sp) // reload f31
+	stfd	f30, STACK_FRAME_LOCAL(0, 0)(sp) // backup f30
+
+	lfd	f30, (8 * 31)(r4)	// load expected value of f31
+	fcmpu	cr0, f30, f31		// compare
+	bne	cr0, 1f			// bail if mismatch
+
+	lfd	f30, STACK_FRAME_LOCAL(0, 0)(sp) // reload f30
+
+	// Success
+	li	r3, 0
+
+1:	POP_BASIC_STACK(8)
+	blr
+FUNC_END(check_all_fprs)
+
 FUNC_START(test_fpu)
 	# r3 holds pointer to where to put the result of fork
 	# r4 holds pointer to the pid
@@ -75,8 +109,9 @@ FUNC_START(test_fpu)
 	std	r3,STACK_FRAME_PARAM(0)(sp) # Address of darray
 	std r4,STACK_FRAME_PARAM(1)(sp) # Address of pid
 
-	bl load_fpu
-	nop
+	// Load FPRs with expected values
+	OP_REGS lfd, 8, 0, 31, r3
+
 	li	r0,__NR_fork
 	sc
 
@@ -85,7 +120,7 @@ FUNC_START(test_fpu)
 	std	r3,0(r9)
 
 	ld r3,STACK_FRAME_PARAM(0)(sp)
-	bl check_fpu
+	bl check_all_fprs
 	nop
 
 	POP_FPU(256)
@@ -104,8 +139,8 @@ FUNC_START(preempt_fpu)
 	std r4,STACK_FRAME_PARAM(1)(sp) # int *threads_starting
 	std r5,STACK_FRAME_PARAM(2)(sp) # int *running
 
-	bl load_fpu
-	nop
+	// Load FPRs with expected values
+	OP_REGS lfd, 8, 0, 31, r3
 
 	sync
 	# Atomic DEC
@@ -116,8 +151,7 @@ FUNC_START(preempt_fpu)
 	bne- 1b
 
 2:	ld r3,STACK_FRAME_PARAM(0)(sp)
-	bl check_fpu
-	nop
+	bl check_all_fprs
 	cmpdi r3,0
 	bne 3f
 	ld r4,STACK_FRAME_PARAM(2)(sp)
diff --git a/tools/testing/selftests/powerpc/math/fpu_preempt.c b/tools/testing/selftests/powerpc/math/fpu_preempt.c
index 5235bdc8c0b1..9ddede0770ed 100644
--- a/tools/testing/selftests/powerpc/math/fpu_preempt.c
+++ b/tools/testing/selftests/powerpc/math/fpu_preempt.c
@@ -1,13 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2015, Cyril Bur, IBM Corp.
+ * Copyright 2023, Michael Ellerman, IBM Corp.
  *
  * This test attempts to see if the FPU registers change across preemption.
- * Two things should be noted here a) The check_fpu function in asm only checks
- * the non volatile registers as it is reused from the syscall test b) There is
- * no way to be sure preemption happened so this test just uses many threads
- * and a long wait. As such, a successful test doesn't mean much but a failure
- * is bad.
+ * There is no way to be sure preemption happened so this test just uses many
+ * threads and a long wait. As such, a successful test doesn't mean much but
+ * a failure is bad.
  */
 
 #include <stdio.h>
@@ -20,9 +19,10 @@
 #include <pthread.h>
 
 #include "utils.h"
+#include "fpu.h"
 
 /* Time to wait for workers to get preempted (seconds) */
-#define PREEMPT_TIME 20
+#define PREEMPT_TIME 60
 /*
  * Factor by which to multiply number of online CPUs for total number of
  * worker threads
@@ -30,26 +30,22 @@
 #define THREAD_FACTOR 8
 
 
-__thread double darray[] = {0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0,
-		     1.1, 1.2, 1.3, 1.4, 1.5, 1.6, 1.7, 1.8, 1.9, 2.0,
-		     2.1};
+__thread double darray[32];
 
 int threads_starting;
 int running;
 
-extern void preempt_fpu(double *darray, int *threads_starting, int *running);
+extern int preempt_fpu(double *darray, int *threads_starting, int *running);
 
 void *preempt_fpu_c(void *p)
 {
-	int i;
-	srand(pthread_self());
-	for (i = 0; i < 21; i++)
-		darray[i] = rand();
+	long rc;
 
-	/* Test failed if it ever returns */
-	preempt_fpu(darray, &threads_starting, &running);
+	srand(pthread_self());
+	randomise_darray(darray, ARRAY_SIZE(darray));
+	rc = preempt_fpu(darray, &threads_starting, &running);
 
-	return p;
+	return (void *)rc;
 }
 
 int test_preempt_fpu(void)
diff --git a/tools/testing/selftests/powerpc/math/fpu_syscall.c b/tools/testing/selftests/powerpc/math/fpu_syscall.c
index 694f225c7e45..751d46b133fc 100644
--- a/tools/testing/selftests/powerpc/math/fpu_syscall.c
+++ b/tools/testing/selftests/powerpc/math/fpu_syscall.c
@@ -14,12 +14,11 @@
 #include <stdlib.h>
 
 #include "utils.h"
+#include "fpu.h"
 
 extern int test_fpu(double *darray, pid_t *pid);
 
-double darray[] = {0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0,
-		     1.1, 1.2, 1.3, 1.4, 1.5, 1.6, 1.7, 1.8, 1.9, 2.0,
-		     2.1};
+double darray[32];
 
 int syscall_fpu(void)
 {
@@ -27,6 +26,9 @@ int syscall_fpu(void)
 	int i;
 	int ret;
 	int child_ret;
+
+	randomise_darray(darray, ARRAY_SIZE(darray));
+
 	for (i = 0; i < 1000; i++) {
 		/* test_fpu will fork() */
 		ret = test_fpu(darray, &fork_pid);
diff --git a/tools/testing/selftests/powerpc/math/vmx_preempt.c b/tools/testing/selftests/powerpc/math/vmx_preempt.c
index 6761d6ce30ec..6f7cf400c687 100644
--- a/tools/testing/selftests/powerpc/math/vmx_preempt.c
+++ b/tools/testing/selftests/powerpc/math/vmx_preempt.c
@@ -37,19 +37,21 @@ __thread vector int varray[] = {{1, 2, 3, 4}, {5, 6, 7, 8}, {9, 10,11,12},
 int threads_starting;
 int running;
 
-extern void preempt_vmx(vector int *varray, int *threads_starting, int *running);
+extern int preempt_vmx(vector int *varray, int *threads_starting, int *running);
 
 void *preempt_vmx_c(void *p)
 {
 	int i, j;
+	long rc;
+
 	srand(pthread_self());
 	for (i = 0; i < 12; i++)
 		for (j = 0; j < 4; j++)
 			varray[i][j] = rand();
 
-	/* Test fails if it ever returns */
-	preempt_vmx(varray, &threads_starting, &running);
-	return p;
+	rc = preempt_vmx(varray, &threads_starting, &running);
+
+	return (void *)rc;
 }
 
 int test_preempt_vmx(void)
diff --git a/tools/testing/selftests/powerpc/papr_sysparm/.gitignore b/tools/testing/selftests/powerpc/papr_sysparm/.gitignore
new file mode 100644
index 000000000000..f2a69bf59d40
--- /dev/null
+++ b/tools/testing/selftests/powerpc/papr_sysparm/.gitignore
@@ -0,0 +1 @@
+/papr_sysparm
diff --git a/tools/testing/selftests/powerpc/papr_sysparm/Makefile b/tools/testing/selftests/powerpc/papr_sysparm/Makefile
new file mode 100644
index 000000000000..7f79e437634a
--- /dev/null
+++ b/tools/testing/selftests/powerpc/papr_sysparm/Makefile
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0
+noarg:
+	$(MAKE) -C ../
+
+TEST_GEN_PROGS := papr_sysparm
+
+top_srcdir = ../../../../..
+include ../../lib.mk
+
+$(TEST_GEN_PROGS): ../harness.c ../utils.c
+
+$(OUTPUT)/papr_sysparm: CFLAGS += $(KHDR_INCLUDES)
diff --git a/tools/testing/selftests/powerpc/papr_sysparm/papr_sysparm.c b/tools/testing/selftests/powerpc/papr_sysparm/papr_sysparm.c
new file mode 100644
index 000000000000..f56c15a11e2f
--- /dev/null
+++ b/tools/testing/selftests/powerpc/papr_sysparm/papr_sysparm.c
@@ -0,0 +1,196 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <errno.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <sys/ioctl.h>
+#include <unistd.h>
+#include <asm/papr-sysparm.h>
+
+#include "utils.h"
+
+#define DEVPATH "/dev/papr-sysparm"
+
+static int open_close(void)
+{
+	const int devfd = open(DEVPATH, O_RDONLY);
+
+	SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+		    DEVPATH " not present");
+
+	FAIL_IF(devfd < 0);
+	FAIL_IF(close(devfd) != 0);
+
+	return 0;
+}
+
+static int get_splpar(void)
+{
+	struct papr_sysparm_io_block sp = {
+		.parameter = 20, // SPLPAR characteristics
+	};
+	const int devfd = open(DEVPATH, O_RDONLY);
+
+	SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+		    DEVPATH " not present");
+
+	FAIL_IF(devfd < 0);
+	FAIL_IF(ioctl(devfd, PAPR_SYSPARM_IOC_GET, &sp) != 0);
+	FAIL_IF(sp.length == 0);
+	FAIL_IF(sp.length > sizeof(sp.data));
+	FAIL_IF(close(devfd) != 0);
+
+	return 0;
+}
+
+static int get_bad_parameter(void)
+{
+	struct papr_sysparm_io_block sp = {
+		.parameter = UINT32_MAX, // there are only ~60 specified parameters
+	};
+	const int devfd = open(DEVPATH, O_RDONLY);
+
+	SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+		    DEVPATH " not present");
+
+	FAIL_IF(devfd < 0);
+
+	// Ensure expected error
+	FAIL_IF(ioctl(devfd, PAPR_SYSPARM_IOC_GET, &sp) != -1);
+	FAIL_IF(errno != EOPNOTSUPP);
+
+	// Ensure the buffer is unchanged
+	FAIL_IF(sp.length != 0);
+	for (size_t i = 0; i < ARRAY_SIZE(sp.data); ++i)
+		FAIL_IF(sp.data[i] != 0);
+
+	FAIL_IF(close(devfd) != 0);
+
+	return 0;
+}
+
+static int check_efault_common(unsigned long cmd)
+{
+	const int devfd = open(DEVPATH, O_RDWR);
+
+	SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+		    DEVPATH " not present");
+
+	FAIL_IF(devfd < 0);
+
+	// Ensure expected error
+	FAIL_IF(ioctl(devfd, cmd, NULL) != -1);
+	FAIL_IF(errno != EFAULT);
+
+	FAIL_IF(close(devfd) != 0);
+
+	return 0;
+}
+
+static int check_efault_get(void)
+{
+	return check_efault_common(PAPR_SYSPARM_IOC_GET);
+}
+
+static int check_efault_set(void)
+{
+	return check_efault_common(PAPR_SYSPARM_IOC_SET);
+}
+
+static int set_hmc0(void)
+{
+	struct papr_sysparm_io_block sp = {
+		.parameter = 0, // HMC0, not a settable parameter
+	};
+	const int devfd = open(DEVPATH, O_RDWR);
+
+	SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+		    DEVPATH " not present");
+
+	FAIL_IF(devfd < 0);
+
+	// Ensure expected error
+	FAIL_IF(ioctl(devfd, PAPR_SYSPARM_IOC_SET, &sp) != -1);
+	SKIP_IF_MSG(errno == EOPNOTSUPP, "operation not supported");
+	FAIL_IF(errno != EPERM);
+
+	FAIL_IF(close(devfd) != 0);
+
+	return 0;
+}
+
+static int set_with_ro_fd(void)
+{
+	struct papr_sysparm_io_block sp = {
+		.parameter = 0, // HMC0, not a settable parameter.
+	};
+	const int devfd = open(DEVPATH, O_RDONLY);
+
+	SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+		    DEVPATH " not present");
+
+	FAIL_IF(devfd < 0);
+
+	// Ensure expected error
+	FAIL_IF(ioctl(devfd, PAPR_SYSPARM_IOC_SET, &sp) != -1);
+	SKIP_IF_MSG(errno == EOPNOTSUPP, "operation not supported");
+
+	// HMC0 isn't a settable parameter and we would normally
+	// expect to get EPERM on attempts to modify it. However, when
+	// the file is open read-only, we expect the driver to prevent
+	// the attempt with a distinct error.
+	FAIL_IF(errno != EBADF);
+
+	FAIL_IF(close(devfd) != 0);
+
+	return 0;
+}
+
+struct sysparm_test {
+	int (*function)(void);
+	const char *description;
+};
+
+static const struct sysparm_test sysparm_tests[] = {
+	{
+		.function = open_close,
+		.description = "open and close " DEVPATH " without issuing commands",
+	},
+	{
+		.function = get_splpar,
+		.description = "retrieve SPLPAR characteristics",
+	},
+	{
+		.function = get_bad_parameter,
+		.description = "verify EOPNOTSUPP for known-bad parameter",
+	},
+	{
+		.function = check_efault_get,
+		.description = "PAPR_SYSPARM_IOC_GET returns EFAULT on bad address",
+	},
+	{
+		.function = check_efault_set,
+		.description = "PAPR_SYSPARM_IOC_SET returns EFAULT on bad address",
+	},
+	{
+		.function = set_hmc0,
+		.description = "ensure EPERM on attempt to update HMC0",
+	},
+	{
+		.function = set_with_ro_fd,
+		.description = "PAPR_IOC_SYSPARM_SET returns EACCES on read-only fd",
+	},
+};
+
+int main(void)
+{
+	size_t fails = 0;
+
+	for (size_t i = 0; i < ARRAY_SIZE(sysparm_tests); ++i) {
+		const struct sysparm_test *t = &sysparm_tests[i];
+
+		if (test_harness(t->function, t->description))
+			++fails;
+	}
+
+	return fails == 0 ? EXIT_SUCCESS : EXIT_FAILURE;
+}
diff --git a/tools/testing/selftests/powerpc/papr_vpd/.gitignore b/tools/testing/selftests/powerpc/papr_vpd/.gitignore
new file mode 100644
index 000000000000..49285031a656
--- /dev/null
+++ b/tools/testing/selftests/powerpc/papr_vpd/.gitignore
@@ -0,0 +1 @@
+/papr_vpd
diff --git a/tools/testing/selftests/powerpc/papr_vpd/Makefile b/tools/testing/selftests/powerpc/papr_vpd/Makefile
new file mode 100644
index 000000000000..06b719703bfd
--- /dev/null
+++ b/tools/testing/selftests/powerpc/papr_vpd/Makefile
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0
+noarg:
+	$(MAKE) -C ../
+
+TEST_GEN_PROGS := papr_vpd
+
+top_srcdir = ../../../../..
+include ../../lib.mk
+
+$(TEST_GEN_PROGS): ../harness.c ../utils.c
+
+$(OUTPUT)/papr_vpd: CFLAGS += $(KHDR_INCLUDES)
diff --git a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c
new file mode 100644
index 000000000000..98cbb9109ee6
--- /dev/null
+++ b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c
@@ -0,0 +1,352 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <unistd.h>
+
+#include <asm/papr-vpd.h>
+
+#include "utils.h"
+
+#define DEVPATH "/dev/papr-vpd"
+
+static int dev_papr_vpd_open_close(void)
+{
+	const int devfd = open(DEVPATH, O_RDONLY);
+
+	SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+		    DEVPATH " not present");
+
+	FAIL_IF(devfd < 0);
+	FAIL_IF(close(devfd) != 0);
+
+	return 0;
+}
+
+static int dev_papr_vpd_get_handle_all(void)
+{
+	const int devfd = open(DEVPATH, O_RDONLY);
+	struct papr_location_code lc = { .str = "", };
+	off_t size;
+	int fd;
+
+	SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+		    DEVPATH " not present");
+
+	FAIL_IF(devfd < 0);
+
+	errno = 0;
+	fd = ioctl(devfd, PAPR_VPD_IOC_CREATE_HANDLE, &lc);
+	FAIL_IF(errno != 0);
+	FAIL_IF(fd < 0);
+
+	FAIL_IF(close(devfd) != 0);
+
+	size = lseek(fd, 0, SEEK_END);
+	FAIL_IF(size <= 0);
+
+	void *buf = malloc((size_t)size);
+	FAIL_IF(!buf);
+
+	ssize_t consumed = pread(fd, buf, size, 0);
+	FAIL_IF(consumed != size);
+
+	/* Ensure EOF */
+	FAIL_IF(read(fd, buf, size) != 0);
+	FAIL_IF(close(fd));
+
+	/* Verify that the buffer looks like VPD */
+	static const char needle[] = "System VPD";
+	FAIL_IF(!memmem(buf, size, needle, strlen(needle)));
+
+	return 0;
+}
+
+static int dev_papr_vpd_get_handle_byte_at_a_time(void)
+{
+	const int devfd = open(DEVPATH, O_RDONLY);
+	struct papr_location_code lc = { .str = "", };
+	int fd;
+
+	SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+		    DEVPATH " not present");
+
+	FAIL_IF(devfd < 0);
+
+	errno = 0;
+	fd = ioctl(devfd, PAPR_VPD_IOC_CREATE_HANDLE, &lc);
+	FAIL_IF(errno != 0);
+	FAIL_IF(fd < 0);
+
+	FAIL_IF(close(devfd) != 0);
+
+	size_t consumed = 0;
+	while (1) {
+		ssize_t res;
+		char c;
+
+		errno = 0;
+		res = read(fd, &c, sizeof(c));
+		FAIL_IF(res > sizeof(c));
+		FAIL_IF(res < 0);
+		FAIL_IF(errno != 0);
+		consumed += res;
+		if (res == 0)
+			break;
+	}
+
+	FAIL_IF(consumed != lseek(fd, 0, SEEK_END));
+
+	FAIL_IF(close(fd));
+
+	return 0;
+}
+
+
+static int dev_papr_vpd_unterm_loc_code(void)
+{
+	const int devfd = open(DEVPATH, O_RDONLY);
+	struct papr_location_code lc = {};
+	int fd;
+
+	SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+		    DEVPATH " not present");
+
+	FAIL_IF(devfd < 0);
+
+	/*
+	 * Place a non-null byte in every element of loc_code; the
+	 * driver should reject this input.
+	 */
+	memset(lc.str, 'x', ARRAY_SIZE(lc.str));
+
+	errno = 0;
+	fd = ioctl(devfd, PAPR_VPD_IOC_CREATE_HANDLE, &lc);
+	FAIL_IF(fd != -1);
+	FAIL_IF(errno != EINVAL);
+
+	FAIL_IF(close(devfd) != 0);
+	return 0;
+}
+
+static int dev_papr_vpd_null_handle(void)
+{
+	const int devfd = open(DEVPATH, O_RDONLY);
+	int rc;
+
+	SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+		    DEVPATH " not present");
+
+	FAIL_IF(devfd < 0);
+
+	errno = 0;
+	rc = ioctl(devfd, PAPR_VPD_IOC_CREATE_HANDLE, NULL);
+	FAIL_IF(rc != -1);
+	FAIL_IF(errno != EFAULT);
+
+	FAIL_IF(close(devfd) != 0);
+	return 0;
+}
+
+static int papr_vpd_close_handle_without_reading(void)
+{
+	const int devfd = open(DEVPATH, O_RDONLY);
+	struct papr_location_code lc;
+	int fd;
+
+	SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+		    DEVPATH " not present");
+
+	FAIL_IF(devfd < 0);
+
+	errno = 0;
+	fd = ioctl(devfd, PAPR_VPD_IOC_CREATE_HANDLE, &lc);
+	FAIL_IF(errno != 0);
+	FAIL_IF(fd < 0);
+
+	/* close the handle without reading it */
+	FAIL_IF(close(fd) != 0);
+
+	FAIL_IF(close(devfd) != 0);
+	return 0;
+}
+
+static int papr_vpd_reread(void)
+{
+	const int devfd = open(DEVPATH, O_RDONLY);
+	struct papr_location_code lc = { .str = "", };
+	int fd;
+
+	SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+		    DEVPATH " not present");
+
+	FAIL_IF(devfd < 0);
+
+	errno = 0;
+	fd = ioctl(devfd, PAPR_VPD_IOC_CREATE_HANDLE, &lc);
+	FAIL_IF(errno != 0);
+	FAIL_IF(fd < 0);
+
+	FAIL_IF(close(devfd) != 0);
+
+	const off_t size = lseek(fd, 0, SEEK_END);
+	FAIL_IF(size <= 0);
+
+	char *bufs[2];
+
+	for (size_t i = 0; i < ARRAY_SIZE(bufs); ++i) {
+		bufs[i] = malloc(size);
+		FAIL_IF(!bufs[i]);
+		ssize_t consumed = pread(fd, bufs[i], size, 0);
+		FAIL_IF(consumed != size);
+	}
+
+	FAIL_IF(memcmp(bufs[0], bufs[1], size));
+
+	FAIL_IF(close(fd) != 0);
+
+	return 0;
+}
+
+static int get_system_loc_code(struct papr_location_code *lc)
+{
+	static const char system_id_path[] = "/sys/firmware/devicetree/base/system-id";
+	static const char model_path[] = "/sys/firmware/devicetree/base/model";
+	char *system_id;
+	char *model;
+	int err = -1;
+
+	if (read_file_alloc(model_path, &model, NULL))
+		return err;
+
+	if (read_file_alloc(system_id_path, &system_id, NULL))
+		goto free_model;
+
+	char *mtm;
+	int sscanf_ret = sscanf(model, "IBM,%ms", &mtm);
+	if (sscanf_ret != 1)
+		goto free_system_id;
+
+	char *plant_and_seq;
+	if (sscanf(system_id, "IBM,%*c%*c%ms", &plant_and_seq) != 1)
+		goto free_mtm;
+	/*
+	 * Replace - with . to build location code.
+	 */
+	char *sep = strchr(mtm, '-');
+	if (!sep)
+		goto free_mtm;
+	else
+		*sep = '.';
+
+	snprintf(lc->str, sizeof(lc->str),
+		 "U%s.%s", mtm, plant_and_seq);
+	err = 0;
+
+	free(plant_and_seq);
+free_mtm:
+	free(mtm);
+free_system_id:
+	free(system_id);
+free_model:
+	free(model);
+	return err;
+}
+
+static int papr_vpd_system_loc_code(void)
+{
+	struct papr_location_code lc;
+	const int devfd = open(DEVPATH, O_RDONLY);
+	off_t size;
+	int fd;
+
+	SKIP_IF_MSG(get_system_loc_code(&lc),
+		    "Cannot determine system location code");
+	SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
+		    DEVPATH " not present");
+
+	FAIL_IF(devfd < 0);
+
+	errno = 0;
+	fd = ioctl(devfd, PAPR_VPD_IOC_CREATE_HANDLE, &lc);
+	FAIL_IF(errno != 0);
+	FAIL_IF(fd < 0);
+
+	FAIL_IF(close(devfd) != 0);
+
+	size = lseek(fd, 0, SEEK_END);
+	FAIL_IF(size <= 0);
+
+	void *buf = malloc((size_t)size);
+	FAIL_IF(!buf);
+
+	ssize_t consumed = pread(fd, buf, size, 0);
+	FAIL_IF(consumed != size);
+
+	/* Ensure EOF */
+	FAIL_IF(read(fd, buf, size) != 0);
+	FAIL_IF(close(fd));
+
+	/* Verify that the buffer looks like VPD */
+	static const char needle[] = "System VPD";
+	FAIL_IF(!memmem(buf, size, needle, strlen(needle)));
+
+	return 0;
+}
+
+struct vpd_test {
+	int (*function)(void);
+	const char *description;
+};
+
+static const struct vpd_test vpd_tests[] = {
+	{
+		.function = dev_papr_vpd_open_close,
+		.description = "open/close " DEVPATH,
+	},
+	{
+		.function = dev_papr_vpd_unterm_loc_code,
+		.description = "ensure EINVAL on unterminated location code",
+	},
+	{
+		.function = dev_papr_vpd_null_handle,
+		.description = "ensure EFAULT on bad handle addr",
+	},
+	{
+		.function = dev_papr_vpd_get_handle_all,
+		.description = "get handle for all VPD"
+	},
+	{
+		.function = papr_vpd_close_handle_without_reading,
+		.description = "close handle without consuming VPD"
+	},
+	{
+		.function = dev_papr_vpd_get_handle_byte_at_a_time,
+		.description = "read all VPD one byte at a time"
+	},
+	{
+		.function = papr_vpd_reread,
+		.description = "ensure re-read yields same results"
+	},
+	{
+		.function = papr_vpd_system_loc_code,
+		.description = "get handle for system VPD"
+	},
+};
+
+int main(void)
+{
+	size_t fails = 0;
+
+	for (size_t i = 0; i < ARRAY_SIZE(vpd_tests); ++i) {
+		const struct vpd_test *t = &vpd_tests[i];
+
+		if (test_harness(t->function, t->description))
+			++fails;
+	}
+
+	return fails == 0 ? EXIT_SUCCESS : EXIT_FAILURE;
+}
diff --git a/tools/testing/selftests/prctl/set-process-name.c b/tools/testing/selftests/prctl/set-process-name.c
index 3bc5e0e09eb9..562f707ba771 100644
--- a/tools/testing/selftests/prctl/set-process-name.c
+++ b/tools/testing/selftests/prctl/set-process-name.c
@@ -12,6 +12,7 @@
 #define CHANGE_NAME "changename"
 #define EMPTY_NAME ""
 #define TASK_COMM_LEN 16
+#define MAX_PATH_LEN 50
 
 int set_name(char *name)
 {
@@ -47,6 +48,35 @@ int check_null_pointer(char *check_name)
 	return res;
 }
 
+int check_name(void)
+{
+
+	int pid;
+
+	pid = getpid();
+	FILE *fptr = NULL;
+	char path[MAX_PATH_LEN] = {};
+	char name[TASK_COMM_LEN] = {};
+	char output[TASK_COMM_LEN] = {};
+	int j;
+
+	j = snprintf(path, MAX_PATH_LEN, "/proc/self/task/%d/comm", pid);
+	fptr = fopen(path, "r");
+	if (!fptr)
+		return -EIO;
+
+	fscanf(fptr, "%s", output);
+	if (ferror(fptr))
+		return -EIO;
+
+	int res = prctl(PR_GET_NAME, name, NULL, NULL, NULL);
+
+	if (res < 0)
+		return -errno;
+
+	return !strcmp(output, name);
+}
+
 TEST(rename_process) {
 
 	EXPECT_GE(set_name(CHANGE_NAME), 0);
@@ -57,6 +87,8 @@ TEST(rename_process) {
 
 	EXPECT_GE(set_name(CHANGE_NAME), 0);
 	EXPECT_LT(check_null_pointer(CHANGE_NAME), 0);
+
+	EXPECT_TRUE(check_name());
 }
 
 TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/run_kselftest.sh b/tools/testing/selftests/run_kselftest.sh
index 92743980e553..a28c1416cb89 100755
--- a/tools/testing/selftests/run_kselftest.sh
+++ b/tools/testing/selftests/run_kselftest.sh
@@ -20,11 +20,13 @@ usage()
 {
 	cat <<EOF
 Usage: $0 [OPTIONS]
-  -s | --summary		Print summary with detailed log in output.log
+  -s | --summary		Print summary with detailed log in output.log (conflict with -p)
+  -p | --per_test_log		Print test log in /tmp with each test name (conflict with -s)
   -t | --test COLLECTION:TEST	Run TEST from COLLECTION
   -c | --collection COLLECTION	Run all tests from COLLECTION
   -l | --list			List the available collection:test entries
   -d | --dry-run		Don't actually run any tests
+  -n | --netns			Run each test in namespace
   -h | --help			Show this usage info
   -o | --override-timeout	Number of seconds after which we timeout
 EOF
@@ -41,6 +43,9 @@ while true; do
 			logfile="$BASE_DIR"/output.log
 			cat /dev/null > $logfile
 			shift ;;
+		-p | --per-test-log)
+			per_test_logging=1
+			shift ;;
 		-t | --test)
 			TESTS="$TESTS $2"
 			shift 2 ;;
@@ -53,6 +58,9 @@ while true; do
 		-d | --dry-run)
 			dryrun="echo"
 			shift ;;
+		-n | --netns)
+			RUN_IN_NETNS=1
+			shift ;;
 		-o | --override-timeout)
 			kselftest_override_timeout="$2"
 			shift 2 ;;
diff --git a/tools/testing/selftests/sched/cs_prctl_test.c b/tools/testing/selftests/sched/cs_prctl_test.c
index 3e1619b6bf2d..7ba057154343 100644
--- a/tools/testing/selftests/sched/cs_prctl_test.c
+++ b/tools/testing/selftests/sched/cs_prctl_test.c
@@ -72,7 +72,7 @@ struct child_args {
 
 static struct child_args procs[MAX_PROCESSES];
 static int num_processes = 2;
-static int need_cleanup = 0;
+static int need_cleanup;
 
 static int _prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4,
 		  unsigned long arg5)
diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh
index 444b2befda82..84472b436c07 100755
--- a/tools/testing/selftests/sysctl/sysctl.sh
+++ b/tools/testing/selftests/sysctl/sysctl.sh
@@ -35,6 +35,7 @@ ALL_TESTS="$ALL_TESTS 0007:1:1:boot_int:1"
 ALL_TESTS="$ALL_TESTS 0008:1:1:match_int:1"
 ALL_TESTS="$ALL_TESTS 0009:1:1:unregister_error:0"
 ALL_TESTS="$ALL_TESTS 0010:1:1:mnt/mnt_error:0"
+ALL_TESTS="$ALL_TESTS 0011:1:1:empty_add:0"
 
 function allow_user_defaults()
 {
@@ -63,7 +64,7 @@ function check_production_sysctl_writes_strict()
 	else
 		old_strict=$(cat ${WRITES_STRICT})
 		if [ "$old_strict" = "1" ]; then
-			echo "ok"
+			echo "OK"
 		else
 			echo "FAIL, strict value is 0 but force to 1 to continue" >&2
 			echo "1" > ${WRITES_STRICT}
@@ -225,7 +226,7 @@ run_numerictests()
 		echo "FAIL" >&2
 		exit 1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 
 	echo -n "Checking sysctl is not set to test value ... "
@@ -233,7 +234,7 @@ run_numerictests()
 		echo "FAIL" >&2
 		exit 1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 
 	echo -n "Writing sysctl from shell ... "
@@ -242,7 +243,7 @@ run_numerictests()
 		echo "FAIL" >&2
 		exit 1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 
 	echo -n "Resetting sysctl to original value ... "
@@ -251,7 +252,7 @@ run_numerictests()
 		echo "FAIL" >&2
 		exit 1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 
 	# Now that we've validated the sanity of "set_test" and "set_orig",
@@ -265,7 +266,7 @@ run_numerictests()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 
 	echo -n "Writing middle of sysctl after synchronized seek ... "
@@ -275,7 +276,7 @@ run_numerictests()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 
 	echo -n "Writing beyond end of sysctl ... "
@@ -285,7 +286,7 @@ run_numerictests()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 
 	echo -n "Writing sysctl with multiple long writes ... "
@@ -296,14 +297,14 @@ run_numerictests()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 	test_rc
 }
 
 check_failure()
 {
-	echo -n "Testing that $1 fails as expected..."
+	echo -n "Testing that $1 fails as expected ... "
 	reset_vals
 	TEST_STR="$1"
 	orig="$(cat $TARGET)"
@@ -314,7 +315,7 @@ check_failure()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 	test_rc
 }
@@ -356,7 +357,7 @@ run_wideint_tests()
 # Your test must accept digits 3 and 4 to use this
 run_limit_digit()
 {
-	echo -n "Checking ignoring spaces up to PAGE_SIZE works on write ..."
+	echo -n "Checking ignoring spaces up to PAGE_SIZE works on write ... "
 	reset_vals
 
 	LIMIT=$((MAX_DIGITS -1))
@@ -368,11 +369,11 @@ run_limit_digit()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 	test_rc
 
-	echo -n "Checking passing PAGE_SIZE of spaces fails on write ..."
+	echo -n "Checking passing PAGE_SIZE of spaces fails on write ... "
 	reset_vals
 
 	LIMIT=$((MAX_DIGITS))
@@ -384,7 +385,7 @@ run_limit_digit()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 	test_rc
 }
@@ -392,7 +393,7 @@ run_limit_digit()
 # You are using an int
 run_limit_digit_int()
 {
-	echo -n "Testing INT_MAX works ..."
+	echo -n "Testing INT_MAX works ... "
 	reset_vals
 	TEST_STR="$INT_MAX"
 	echo -n $TEST_STR > $TARGET
@@ -401,11 +402,11 @@ run_limit_digit_int()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 	test_rc
 
-	echo -n "Testing INT_MAX + 1 will fail as expected..."
+	echo -n "Testing INT_MAX + 1 will fail as expected ... "
 	reset_vals
 	let TEST_STR=$INT_MAX+1
 	echo -n $TEST_STR > $TARGET 2> /dev/null
@@ -414,11 +415,11 @@ run_limit_digit_int()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 	test_rc
 
-	echo -n "Testing negative values will work as expected..."
+	echo -n "Testing negative values will work as expected ... "
 	reset_vals
 	TEST_STR="-3"
 	echo -n $TEST_STR > $TARGET 2> /dev/null
@@ -426,7 +427,7 @@ run_limit_digit_int()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 	test_rc
 }
@@ -442,7 +443,7 @@ run_limit_digit_int_array()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 	test_rc
 
@@ -459,7 +460,7 @@ run_limit_digit_int_array()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 	test_rc
 
@@ -477,7 +478,7 @@ run_limit_digit_int_array()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 	test_rc
 
@@ -494,7 +495,7 @@ run_limit_digit_int_array()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 	test_rc
 }
@@ -502,7 +503,7 @@ run_limit_digit_int_array()
 # You are using an unsigned int
 run_limit_digit_uint()
 {
-	echo -n "Testing UINT_MAX works ..."
+	echo -n "Testing UINT_MAX works ... "
 	reset_vals
 	TEST_STR="$UINT_MAX"
 	echo -n $TEST_STR > $TARGET
@@ -511,11 +512,11 @@ run_limit_digit_uint()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 	test_rc
 
-	echo -n "Testing UINT_MAX + 1 will fail as expected..."
+	echo -n "Testing UINT_MAX + 1 will fail as expected ... "
 	reset_vals
 	TEST_STR=$(($UINT_MAX+1))
 	echo -n $TEST_STR > $TARGET 2> /dev/null
@@ -524,11 +525,11 @@ run_limit_digit_uint()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 	test_rc
 
-	echo -n "Testing negative values will not work as expected ..."
+	echo -n "Testing negative values will not work as expected ... "
 	reset_vals
 	TEST_STR="-3"
 	echo -n $TEST_STR > $TARGET 2> /dev/null
@@ -537,7 +538,7 @@ run_limit_digit_uint()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 	test_rc
 }
@@ -551,7 +552,7 @@ run_stringtests()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 
 	echo -n "Writing middle of sysctl after unsynchronized seek ... "
@@ -561,7 +562,7 @@ run_stringtests()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 
 	echo -n "Checking sysctl maxlen is at least $MAXLEN ... "
@@ -572,7 +573,7 @@ run_stringtests()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 
 	echo -n "Checking sysctl keeps original string on overflow append ... "
@@ -583,7 +584,7 @@ run_stringtests()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 
 	echo -n "Checking sysctl stays NULL terminated on write ... "
@@ -594,7 +595,7 @@ run_stringtests()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 
 	echo -n "Checking sysctl stays NULL terminated on overwrite ... "
@@ -605,7 +606,7 @@ run_stringtests()
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 	fi
 
 	test_rc
@@ -650,7 +651,7 @@ run_bitmaptest() {
 		fi
 	done
 
-	echo -n "Checking bitmap handler... "
+	echo -n "Checking bitmap handler ... "
 	TEST_FILE=$(mktemp)
 	echo -n "$TEST_STR" > $TEST_FILE
 
@@ -665,7 +666,7 @@ run_bitmaptest() {
 		echo "FAIL" >&2
 		rc=1
 	else
-		echo "ok"
+		echo "OK"
 		rc=0
 	fi
 	test_rc
@@ -742,89 +743,111 @@ sysctl_test_0006()
 sysctl_test_0007()
 {
 	TARGET="${SYSCTL}/$(get_test_target 0007)"
+	echo -n "Testing if $TARGET is set to 1 ... "
+
 	if [ ! -f $TARGET ]; then
-		echo "Skipping test for $TARGET as it is not present ..."
+		echo -e "SKIPPING\n$TARGET is not present"
 		return $ksft_skip
 	fi
 
 	if [ -d $DIR ]; then
-		echo "Boot param test only possible sysctl_test is built-in, not module:"
+		echo -e "SKIPPING\nTest only possible if sysctl_test is built-in, not module:"
 		cat $TEST_DIR/config >&2
 		return $ksft_skip
 	fi
 
-	echo -n "Testing if $TARGET is set to 1 ..."
 	ORIG=$(cat "${TARGET}")
 
 	if [ x$ORIG = "x1" ]; then
-		echo "ok"
+		echo "OK"
 		return 0
 	fi
-	echo "FAIL"
-	echo "Checking if /proc/cmdline contains setting of the expected parameter ..."
+
 	if [ ! -f /proc/cmdline ]; then
-		echo "/proc/cmdline does not exist, test inconclusive"
-		return 0
+		echo -e "SKIPPING\nThere is no /proc/cmdline to check for paramter"
+		return $ksft_skip
 	fi
 
 	FOUND=$(grep -c "sysctl[./]debug[./]test_sysctl[./]boot_int=1" /proc/cmdline)
 	if [ $FOUND = "1" ]; then
-		echo "Kernel param found but $TARGET is not 1, TEST FAILED"
+		echo -e "FAIL\nKernel param found but $TARGET is not 1." >&2
 		rc=1
 		test_rc
 	fi
 
-	echo "Skipping test, expected kernel parameter missing."
-	echo "To perform this test, make sure kernel is booted with parameter: sysctl.debug.test_sysctl.boot_int=1"
+	echo -e "SKIPPING\nExpected kernel parameter missing."
+	echo "Kernel must be booted with parameter: sysctl.debug.test_sysctl.boot_int=1"
 	return $ksft_skip
 }
 
 sysctl_test_0008()
 {
 	TARGET="${SYSCTL}/$(get_test_target 0008)"
+	echo -n "Testing if $TARGET is matched in kernel ... "
+
 	if [ ! -f $TARGET ]; then
-		echo "Skipping test for $TARGET as it is not present ..."
+		echo -e "SKIPPING\n$TARGET is not present"
 		return $ksft_skip
 	fi
 
-	echo -n "Testing if $TARGET is matched in kernel"
 	ORIG_VALUE=$(cat "${TARGET}")
 
 	if [ $ORIG_VALUE -ne 1 ]; then
-		echo "TEST FAILED"
+		echo "FAIL" >&2
 		rc=1
 		test_rc
 	fi
 
-	echo "ok"
+	echo "OK"
 	return 0
 }
 
 sysctl_test_0009()
 {
 	TARGET="${SYSCTL}/$(get_test_target 0009)"
-	echo -n "Testing if $TARGET unregistered correctly ..."
+	echo -n "Testing if $TARGET unregistered correctly ... "
 	if [ -d $TARGET ]; then
-		echo "TEST FAILED"
+		echo "FAIL" >&2
 		rc=1
 		test_rc
 	fi
 
-	echo "ok"
+	echo "OK"
 	return 0
 }
 
 sysctl_test_0010()
 {
 	TARGET="${SYSCTL}/$(get_test_target 0010)"
-	echo -n "Testing that $TARGET was not created  ..."
+	echo -n "Testing that $TARGET was not created ... "
 	if [ -d $TARGET ]; then
-		echo "TEST FAILED"
+		echo "FAIL" >&2
+		rc=1
+		test_rc
+	fi
+
+	echo "OK"
+	return 0
+}
+
+sysctl_test_0011()
+{
+	TARGET="${SYSCTL}/$(get_test_target 0011)"
+	echo -n "Testing empty dir handling in ${TARGET} ... "
+	if [ ! -d ${TARGET} ]; then
+		echo -e "FAIL\nCould not create ${TARGET}" >&2
+		rc=1
+		test_rc
+	fi
+
+	TARGET2="${TARGET}/empty"
+	if [ ! -d ${TARGET2} ]; then
+		echo -e "FAIL\nCould not create ${TARGET2}" >&2
 		rc=1
 		test_rc
 	fi
 
-	echo "ok"
+	echo "OK"
 	return 0
 }
 
@@ -846,6 +869,7 @@ list_tests()
 	echo "0008 x $(get_test_count 0008) - tests sysctl macro values match"
 	echo "0009 x $(get_test_count 0009) - tests sysct unregister"
 	echo "0010 x $(get_test_count 0010) - tests sysct mount point"
+	echo "0011 x $(get_test_count 0011) - tests empty directories"
 }
 
 usage()
@@ -934,7 +958,7 @@ function skip_test()
 	if target_exists $TEST_TARGET $TEST_ID; then
 		TEST_SKIP=$(get_test_skip_no_target $TEST_ID)
 		if [[ $TEST_SKIP -eq "1" ]]; then
-			echo "Target for test $TEST_ID: $TEST_TARGET not exist, skipping test ..."
+			echo "Target $TEST_TARGET for test $TEST_ID does not exist ... SKIPPING"
 			return 0
 		fi
 	fi
diff --git a/tools/testing/selftests/tc-testing/Makefile b/tools/testing/selftests/tc-testing/Makefile
index b1fa2e177e2f..9153e3428a77 100644
--- a/tools/testing/selftests/tc-testing/Makefile
+++ b/tools/testing/selftests/tc-testing/Makefile
@@ -1,31 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
-include ../../../scripts/Makefile.include
 
-top_srcdir = $(abspath ../../../..)
-APIDIR := $(top_scrdir)/include/uapi
-TEST_GEN_FILES = action.o
+TEST_PROGS += tdc.sh
+TEST_FILES := action-ebpf tdc*.py Tdc*.py plugins plugin-lib tc-tests scripts
 
 include ../lib.mk
-
-PROBE := $(shell $(LLC) -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1)
-
-ifeq ($(PROBE),)
-  CPU ?= probe
-else
-  CPU ?= generic
-endif
-
-CLANG_SYS_INCLUDES := $(shell $(CLANG) -v -E - </dev/null 2>&1 \
-	| sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }')
-
-CLANG_FLAGS = -I. -I$(APIDIR) \
-	      $(CLANG_SYS_INCLUDES) \
-	      -Wno-compare-distinct-pointer-types
-
-$(OUTPUT)/%.o: %.c
-	$(CLANG) $(CLANG_FLAGS) \
-		 -O2 --target=bpf -emit-llvm -c $< -o - |      \
-	$(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
-
-TEST_PROGS += ./tdc.sh
-TEST_FILES := tdc*.py Tdc*.py plugins plugin-lib tc-tests scripts
diff --git a/tools/testing/selftests/tc-testing/README b/tools/testing/selftests/tc-testing/README
index be7b00799b3e..fc8e858ff119 100644
--- a/tools/testing/selftests/tc-testing/README
+++ b/tools/testing/selftests/tc-testing/README
@@ -195,8 +195,6 @@ directory:
       and the other is a test whether the command leaked memory or not.
       (This one is a preliminary version, it may not work quite right yet,
       but the overall template is there and it should only need tweaks.)
-  - buildebpfPlugin.py:
-      builds all programs in $EBPFDIR.
 
 
 ACKNOWLEDGEMENTS
diff --git a/tools/testing/selftests/tc-testing/action-ebpf b/tools/testing/selftests/tc-testing/action-ebpf
new file mode 100644
index 000000000000..4879479b2ee5
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/action-ebpf
diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config
index 012aa33b341b..c60acba951c2 100644
--- a/tools/testing/selftests/tc-testing/config
+++ b/tools/testing/selftests/tc-testing/config
@@ -82,7 +82,6 @@ CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
 CONFIG_NET_ACT_SAMPLE=m
-CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
diff --git a/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py
deleted file mode 100644
index d34fe06268d2..000000000000
--- a/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py
+++ /dev/null
@@ -1,67 +0,0 @@
-'''
-build ebpf program
-'''
-
-import os
-import signal
-from string import Template
-import subprocess
-import time
-from TdcPlugin import TdcPlugin
-from tdc_config import *
-
-class SubPlugin(TdcPlugin):
-    def __init__(self):
-        self.sub_class = 'buildebpf/SubPlugin'
-        self.tap = ''
-        super().__init__()
-
-    def pre_suite(self, testcount, testidlist):
-        super().pre_suite(testcount, testidlist)
-
-        if self.args.buildebpf:
-            self._ebpf_makeall()
-
-    def post_suite(self, index):
-        super().post_suite(index)
-
-        self._ebpf_makeclean()
-
-    def add_args(self, parser):
-        super().add_args(parser)
-
-        self.argparser_group = self.argparser.add_argument_group(
-            'buildebpf',
-            'options for buildebpfPlugin')
-        self.argparser_group.add_argument(
-            '--nobuildebpf', action='store_false', default=True,
-            dest='buildebpf',
-            help='Don\'t build eBPF programs')
-
-        return self.argparser
-
-    def _ebpf_makeall(self):
-        if self.args.buildebpf:
-            self._make('all')
-
-    def _ebpf_makeclean(self):
-        if self.args.buildebpf:
-            self._make('clean')
-
-    def _make(self, target):
-        command = 'make -C {} {}'.format(self.args.NAMES['EBPFDIR'], target)
-        proc = subprocess.Popen(command,
-            shell=True,
-            stdout=subprocess.PIPE,
-            stderr=subprocess.PIPE,
-            env=os.environ.copy())
-        (rawout, serr) = proc.communicate()
-
-        if proc.returncode != 0 and len(serr) > 0:
-            foutput = serr.decode("utf-8")
-        else:
-            foutput = rawout.decode("utf-8")
-
-        proc.stdout.close()
-        proc.stderr.close()
-        return proc, foutput
diff --git a/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py
index b62429b0fcdb..bb19b8b76d3b 100644
--- a/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py
+++ b/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py
@@ -9,43 +9,13 @@ from TdcPlugin import TdcPlugin
 
 from tdc_config import *
 
-def prepare_suite(obj, test):
-    original = obj.args.NAMES
-
-    if 'skip' in test and test['skip'] == 'yes':
-        return
-
-    if 'nsPlugin' not in test['plugins']:
-        return
-
-    shadow = {}
-    shadow['IP'] = original['IP']
-    shadow['TC'] = original['TC']
-    shadow['NS'] = '{}-{}'.format(original['NS'], test['random'])
-    shadow['DEV0'] = '{}id{}'.format(original['DEV0'], test['id'])
-    shadow['DEV1'] = '{}id{}'.format(original['DEV1'], test['id'])
-    shadow['DUMMY'] = '{}id{}'.format(original['DUMMY'], test['id'])
-    shadow['DEV2'] = original['DEV2']
-    obj.args.NAMES = shadow
-
-    if obj.args.namespace:
-        obj._ns_create()
-    else:
-        obj._ports_create()
-
-    # Make sure the netns is visible in the fs
-    while True:
-        obj._proc_check()
-        try:
-            ns = obj.args.NAMES['NS']
-            f = open('/run/netns/{}'.format(ns))
-            f.close()
-            break
-        except:
-            time.sleep(0.1)
-            continue
-
-    obj.args.NAMES = original
+try:
+    from pyroute2 import netns
+    from pyroute2 import IPRoute
+    netlink = True
+except ImportError:
+    netlink = False
+    print("!!! Consider installing pyroute2 !!!")
 
 class SubPlugin(TdcPlugin):
     def __init__(self):
@@ -53,64 +23,71 @@ class SubPlugin(TdcPlugin):
         super().__init__()
 
     def pre_suite(self, testcount, testlist):
-        from itertools import cycle
-
         super().pre_suite(testcount, testlist)
 
-        print("Setting up namespaces and devices...")
+    def prepare_test(self, test):
+        if 'skip' in test and test['skip'] == 'yes':
+            return
 
-        with Pool(self.args.mp) as p:
-            it = zip(cycle([self]), testlist)
-            p.starmap(prepare_suite, it)
+        if 'nsPlugin' not in test['plugins']:
+            return
 
-    def pre_case(self, caseinfo, test_skip):
+        if netlink == True:
+            self._nl_ns_create()
+        else:
+            self._ipr2_ns_create()
+
+        # Make sure the netns is visible in the fs
+        ticks = 20
+        while True:
+            if ticks == 0:
+                raise TimeoutError
+            self._proc_check()
+            try:
+                ns = self.args.NAMES['NS']
+                f = open('/run/netns/{}'.format(ns))
+                f.close()
+                break
+            except:
+                time.sleep(0.1)
+                ticks -= 1
+                continue
+
+    def pre_case(self, test, test_skip):
         if self.args.verbose:
             print('{}.pre_case'.format(self.sub_class))
 
         if test_skip:
             return
 
+        self.prepare_test(test)
 
     def post_case(self):
         if self.args.verbose:
             print('{}.post_case'.format(self.sub_class))
 
-        if self.args.namespace:
-            self._ns_destroy()
+        if netlink == True:
+            self._nl_ns_destroy()
         else:
-            self._ports_destroy()
+            self._ipr2_ns_destroy()
 
     def post_suite(self, index):
         if self.args.verbose:
             print('{}.post_suite'.format(self.sub_class))
 
         # Make sure we don't leak resources
-        for f in os.listdir('/run/netns/'):
-            cmd = self._replace_keywords("$IP netns del {}".format(f))
+        cmd = self._replace_keywords("$IP -a netns del")
 
-            if self.args.verbose > 3:
-                print('_exec_cmd:  command "{}"'.format(cmd))
-
-            subprocess.run(cmd, shell=True, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
+        if self.args.verbose > 3:
+            print('_exec_cmd:  command "{}"'.format(cmd))
 
-    def add_args(self, parser):
-        super().add_args(parser)
-        self.argparser_group = self.argparser.add_argument_group(
-            'netns',
-            'options for nsPlugin(run commands in net namespace)')
-        self.argparser_group.add_argument(
-            '-N', '--no-namespace', action='store_false', default=True,
-            dest='namespace', help='Don\'t run commands in namespace')
-        return self.argparser
+        subprocess.run(cmd, shell=True, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
 
     def adjust_command(self, stage, command):
         super().adjust_command(stage, command)
         cmdform = 'list'
         cmdlist = list()
 
-        if not self.args.namespace:
-            return command
-
         if self.args.verbose:
             print('{}.adjust_command'.format(self.sub_class))
 
@@ -138,63 +115,90 @@ class SubPlugin(TdcPlugin):
             print('adjust_command:  return command [{}]'.format(command))
         return command
 
-    def _ports_create_cmds(self):
-        cmds = []
-
-        cmds.append(self._replace_keywords('link add $DEV0 type veth peer name $DEV1'))
-        cmds.append(self._replace_keywords('link set $DEV0 up'))
-        cmds.append(self._replace_keywords('link add $DUMMY type dummy'))
-        if not self.args.namespace:
-            cmds.append(self._replace_keywords('link set $DEV1 up'))
-
-        return cmds
-
-    def _ports_create(self):
-        self._exec_cmd_batched('pre', self._ports_create_cmds())
+    def _nl_ns_create(self):
+        ns = self.args.NAMES["NS"];
+        dev0 = self.args.NAMES["DEV0"];
+        dev1 = self.args.NAMES["DEV1"];
+        dummy = self.args.NAMES["DUMMY"];
 
-    def _ports_destroy_cmd(self):
-        return self._replace_keywords('link del $DEV0')
-
-    def _ports_destroy(self):
-        self._exec_cmd('post', self._ports_destroy_cmd())
-
-    def _ns_create_cmds(self):
+        if self.args.verbose:
+            print('{}._nl_ns_create'.format(self.sub_class))
+
+        netns.create(ns)
+        netns.pushns(newns=ns)
+        with IPRoute() as ip:
+            ip.link('add', ifname=dev1, kind='veth', peer={'ifname': dev0, 'net_ns_fd':'/proc/1/ns/net'})
+            ip.link('add', ifname=dummy, kind='dummy')
+            ticks = 20
+            while True:
+                if ticks == 0:
+                    raise TimeoutError
+                try:
+                    dev1_idx = ip.link_lookup(ifname=dev1)[0]
+                    dummy_idx = ip.link_lookup(ifname=dummy)[0]
+                    ip.link('set', index=dev1_idx, state='up')
+                    ip.link('set', index=dummy_idx, state='up')
+                    break
+                except:
+                    time.sleep(0.1)
+                    ticks -= 1
+                    continue
+        netns.popns()
+
+        with IPRoute() as ip:
+            ticks = 20
+            while True:
+                if ticks == 0:
+                    raise TimeoutError
+                try:
+                    dev0_idx = ip.link_lookup(ifname=dev0)[0]
+                    ip.link('set', index=dev0_idx, state='up')
+                    break
+                except:
+                    time.sleep(0.1)
+                    ticks -= 1
+                    continue
+
+    def _ipr2_ns_create_cmds(self):
         cmds = []
 
-        if self.args.namespace:
-            ns = self.args.NAMES['NS']
+        ns = self.args.NAMES['NS']
 
-            cmds.append(self._replace_keywords('netns add {}'.format(ns)))
-            cmds.append(self._replace_keywords('link set $DEV1 netns {}'.format(ns)))
-            cmds.append(self._replace_keywords('link set $DUMMY netns {}'.format(ns)))
-            cmds.append(self._replace_keywords('netns exec {} $IP link set $DEV1 up'.format(ns)))
-            cmds.append(self._replace_keywords('netns exec {} $IP link set $DUMMY up'.format(ns)))
+        cmds.append(self._replace_keywords('netns add {}'.format(ns)))
+        cmds.append(self._replace_keywords('link add $DEV1 type veth peer name $DEV0'))
+        cmds.append(self._replace_keywords('link set $DEV1 netns {}'.format(ns)))
+        cmds.append(self._replace_keywords('link add $DUMMY type dummy'.format(ns)))
+        cmds.append(self._replace_keywords('link set $DUMMY netns {}'.format(ns)))
+        cmds.append(self._replace_keywords('netns exec {} $IP link set $DEV1 up'.format(ns)))
+        cmds.append(self._replace_keywords('netns exec {} $IP link set $DUMMY up'.format(ns)))
+        cmds.append(self._replace_keywords('link set $DEV0 up'.format(ns)))
 
-            if self.args.device:
-                cmds.append(self._replace_keywords('link set $DEV2 netns {}'.format(ns)))
-                cmds.append(self._replace_keywords('netns exec {} $IP link set $DEV2 up'.format(ns)))
+        if self.args.device:
+            cmds.append(self._replace_keywords('link set $DEV2 netns {}'.format(ns)))
+            cmds.append(self._replace_keywords('netns exec {} $IP link set $DEV2 up'.format(ns)))
 
         return cmds
 
-    def _ns_create(self):
+    def _ipr2_ns_create(self):
         '''
         Create the network namespace in which the tests will be run and set up
         the required network devices for it.
         '''
-        self._ports_create()
-        self._exec_cmd_batched('pre', self._ns_create_cmds())
+        self._exec_cmd_batched('pre', self._ipr2_ns_create_cmds())
+
+    def _nl_ns_destroy(self):
+        ns = self.args.NAMES['NS']
+        netns.remove(ns)
 
-    def _ns_destroy_cmd(self):
+    def _ipr2_ns_destroy_cmd(self):
         return self._replace_keywords('netns delete {}'.format(self.args.NAMES['NS']))
 
-    def _ns_destroy(self):
+    def _ipr2_ns_destroy(self):
         '''
         Destroy the network namespace for testing (and any associated network
         devices as well)
         '''
-        if self.args.namespace:
-            self._exec_cmd('post', self._ns_destroy_cmd())
-            self._ports_destroy()
+        self._exec_cmd('post', self._ipr2_ns_destroy_cmd())
 
     @cached_property
     def _proc(self):
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
index 91832400ddbd..6e00bf32ef9a 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
@@ -54,9 +54,6 @@
             "actions",
             "bpf"
         ],
-        "plugins": {
-                "requires": "buildebpfPlugin"
-        },
         "setup": [
             [
                 "$TC action flush action bpf",
@@ -65,10 +62,10 @@
                 255
             ]
         ],
-        "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action.o section action-ok index 667",
+        "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action-ebpf section action-ok index 667",
         "expExitCode": "0",
         "verifyCmd": "$TC action get action bpf index 667",
-        "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ok\\] id [0-9].* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref",
+        "matchPattern": "action order [0-9]*: bpf action-ebpf:\\[action-ok\\] id [0-9].* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref",
         "matchCount": "1",
         "teardown": [
             "$TC action flush action bpf"
@@ -81,9 +78,6 @@
             "actions",
             "bpf"
         ],
-        "plugins": {
-                "requires": "buildebpfPlugin"
-        },
         "setup": [
             [
                 "$TC action flush action bpf",
@@ -92,10 +86,10 @@
                 255
             ]
         ],
-        "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action.o section action-ko index 667",
+        "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action-ebpf section action-ko index 667",
         "expExitCode": "255",
         "verifyCmd": "$TC action get action bpf index 667",
-        "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ko\\] id [0-9].*index 667 ref",
+        "matchPattern": "action order [0-9]*: bpf action-ebpf:\\[action-ko\\] id [0-9].*index 667 ref",
         "matchCount": "0",
         "teardown": [
             [
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/xt.json b/tools/testing/selftests/tc-testing/tc-tests/actions/xt.json
deleted file mode 100644
index 1a92e8898fec..000000000000
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/xt.json
+++ /dev/null
@@ -1,243 +0,0 @@
-[
-    {
-        "id": "2029",
-        "name": "Add xt action with log-prefix",
-        "category": [
-            "actions",
-            "xt"
-        ],
-        "plugins": {
-           "requires": "nsPlugin"
-        },
-        "setup": [
-            [
-                "$TC actions flush action xt",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC action add action xt -j LOG --log-prefix PONG index 100",
-        "expExitCode": "0",
-        "verifyCmd": "$TC action ls action xt",
-        "matchPattern": "action order [0-9]*:.*target  LOG level warning prefix \"PONG\".*index 100 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action xt"
-        ]
-    },
-    {
-        "id": "3562",
-        "name": "Replace xt action log-prefix",
-        "category": [
-            "actions",
-            "xt"
-        ],
-        "plugins": {
-           "requires": "nsPlugin"
-        },
-        "setup": [
-            [
-                "$TC actions flush action xt",
-                0,
-                1,
-                255
-            ],
-            [
-                "$TC action add action xt -j LOG --log-prefix PONG index 1",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC action replace action xt -j LOG --log-prefix WIN index 1",
-        "expExitCode": "0",
-        "verifyCmd": "$TC action get action xt index 1",
-        "matchPattern": "action order [0-9]*:.*target  LOG level warning prefix \"WIN\".*index 1 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC action flush action xt"
-        ]
-    },
-    {
-        "id": "8291",
-        "name": "Delete xt action with valid index",
-        "category": [
-            "actions",
-            "xt"
-        ],
-        "plugins": {
-           "requires": "nsPlugin"
-        },
-        "setup": [
-            [
-                "$TC actions flush action xt",
-                0,
-                1,
-                255
-            ],
-            [
-                "$TC action add action xt -j LOG --log-prefix PONG index 1000",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC action delete action xt index 1000",
-        "expExitCode": "0",
-        "verifyCmd": "$TC action get action xt index 1000",
-        "matchPattern": "action order [0-9]*:.*target  LOG level warning prefix \"PONG\".*index 1000 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC action flush action xt"
-        ]
-    },
-    {
-        "id": "5169",
-        "name": "Delete xt action with invalid index",
-        "category": [
-            "actions",
-            "xt"
-        ],
-        "plugins": {
-           "requires": "nsPlugin"
-        },
-        "setup": [
-            [
-                "$TC actions flush action xt",
-                0,
-                1,
-                255
-            ],
-            [
-                "$TC action add action xt -j LOG --log-prefix PONG index 1000",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC action delete action xt index 333",
-        "expExitCode": "255",
-        "verifyCmd": "$TC action get action xt index 1000",
-        "matchPattern": "action order [0-9]*:.*target  LOG level warning prefix \"PONG\".*index 1000 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC action flush action xt"
-        ]
-    },
-    {
-        "id": "7284",
-        "name": "List xt actions",
-        "category": [
-            "actions",
-            "xt"
-        ],
-        "plugins": {
-           "requires": "nsPlugin"
-        },
-        "setup": [
-            [
-                "$TC action flush action xt",
-                0,
-                1,
-                255
-            ],
-            "$TC action add action xt -j LOG --log-prefix PONG index 1001",
-            "$TC action add action xt -j LOG --log-prefix WIN index 1002",
-            "$TC action add action xt -j LOG --log-prefix LOSE index 1003"
-        ],
-        "cmdUnderTest": "$TC action list action xt",
-        "expExitCode": "0",
-        "verifyCmd": "$TC action list action xt",
-        "matchPattern": "action order [0-9]*: tablename:",
-        "matchCount": "3",
-        "teardown": [
-            "$TC actions flush action xt"
-        ]
-    },
-    {
-        "id": "5010",
-        "name": "Flush xt actions",
-        "category": [
-            "actions",
-            "xt"
-        ],
-        "plugins": {
-           "requires": "nsPlugin"
-        },
-        "setup": [
-            [
-		"$TC actions flush action xt",
-                0,
-                1,
-                255
-            ],
-            "$TC action add action xt -j LOG --log-prefix PONG index 1001",
-            "$TC action add action xt -j LOG --log-prefix WIN index 1002",
-            "$TC action add action xt -j LOG --log-prefix LOSE index 1003"
-	],
-        "cmdUnderTest": "$TC action flush action xt",
-        "expExitCode": "0",
-        "verifyCmd": "$TC action list action xt",
-        "matchPattern": "action order [0-9]*: tablename:",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action xt"
-        ]
-    },
-    {
-        "id": "8437",
-        "name": "Add xt action with duplicate index",
-        "category": [
-            "actions",
-            "xt"
-        ],
-        "plugins": {
-           "requires": "nsPlugin"
-        },
-        "setup": [
-            [
-                "$TC actions flush action xt",
-                0,
-                1,
-                255
-            ],
-            "$TC action add action xt -j LOG --log-prefix PONG index 101"
-        ],
-        "cmdUnderTest": "$TC action add action xt -j LOG --log-prefix WIN index 101",
-        "expExitCode": "255",
-        "verifyCmd": "$TC action get action xt index 101",
-        "matchPattern": "action order [0-9]*:.*target  LOG level warning prefix \"PONG\".*index 101",
-        "matchCount": "1",
-        "teardown": [
-            "$TC action flush action xt"
-        ]
-    },
-    {
-        "id": "2837",
-        "name": "Add xt action with invalid index",
-        "category": [
-            "actions",
-            "xt"
-        ],
-        "plugins": {
-           "requires": "nsPlugin"
-        },
-        "setup": [
-            [
-                "$TC actions flush action xt",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC action add action xt -j LOG --log-prefix WIN index 4294967296",
-        "expExitCode": "255",
-        "verifyCmd": "$TC action ls action xt",
-        "matchPattern": "action order [0-9]*:*target  LOG level warning prefix \"WIN\"",
-        "matchCount": "0",
-        "teardown": [
-            "$TC action flush action xt"
-        ]
-    }
-]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/filters/bpf.json
index 013fb983bc3f..725d406a30ac 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/bpf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/bpf.json
@@ -52,17 +52,16 @@
         ],
         "plugins": {
             "requires": [
-               "buildebpfPlugin",
                "nsPlugin"
             ]
         },
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
-        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 100 bpf object-file $EBPFDIR/action.o section action-ok",
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 100 bpf object-file $EBPFDIR/action-ebpf section action-ok",
         "expExitCode": "0",
         "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 protocol ip prio 100 bpf",
-        "matchPattern": "filter parent ffff: protocol ip pref 100 bpf chain [0-9]+ handle 0x1 action.o:\\[action-ok\\].*tag [0-9a-f]{16}( jited)?",
+        "matchPattern": "filter parent ffff: protocol ip pref 100 bpf chain [0-9]+ handle 0x1 action-ebpf:\\[action-ok\\].*tag [0-9a-f]{16}( jited)?",
         "matchCount": "1",
         "teardown": [
             "$TC qdisc del dev $DEV1 ingress"
@@ -77,17 +76,16 @@
         ],
         "plugins": {
             "requires": [
-               "buildebpfPlugin",
                "nsPlugin"
             ]
         },
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
-        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 100 bpf object-file $EBPFDIR/action.o section action-ko",
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 100 bpf object-file $EBPFDIR/action-ebpf section action-ko",
         "expExitCode": "1",
         "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 protocol ip prio 100 bpf",
-        "matchPattern": "filter parent ffff: protocol ip pref 100 bpf chain [0-9]+ handle 0x1 action.o:\\[action-ko\\].*tag [0-9a-f]{16}( jited)?",
+        "matchPattern": "filter parent ffff: protocol ip pref 100 bpf chain [0-9]+ handle 0x1 action-ebpf:\\[action-ko\\].*tag [0-9a-f]{16}( jited)?",
         "matchCount": "0",
         "teardown": [
             "$TC qdisc del dev $DEV1 ingress"
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/concurrency.json b/tools/testing/selftests/tc-testing/tc-tests/filters/flower.json
index c2a433a4737e..6b08c0642069 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/concurrency.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/flower.json
@@ -173,5 +173,103 @@
             "$TC qdisc del dev $DEV2 ingress",
             "/bin/rm -rf $BATCH_DIR"
         ]
+    },
+    {
+        "id": "2ff3",
+        "name": "Add flower with max handle and then dump it",
+        "category": [
+            "filter",
+            "flower"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV2 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress handle 0xffffffff flower action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV2 ingress",
+        "matchPattern": "filter protocol ip pref 1 flower.*handle 0xffffffff",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV2 ingress"
+        ]
+    },
+    {
+        "id": "d052",
+        "name": "Add 1M filters with the same action",
+        "category": [
+            "filter",
+            "flower"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV2 ingress",
+            "./tdc_batch.py $DEV2 $BATCH_FILE --share_action -n 1000000"
+        ],
+        "cmdUnderTest": "$TC -b $BATCH_FILE",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order 0: gact action drop.*index 1 ref 1000000 bind 1000000",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV2 ingress",
+            "/bin/rm $BATCH_FILE"
+        ]
+    },
+    {
+        "id": "4cbd",
+        "name": "Try to add filter with duplicate key",
+        "category": [
+            "filter",
+            "flower"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV2 ingress",
+            "$TC filter add dev $DEV2 protocol ip prio 1 ingress flower dst_mac e4:11:22:11:4a:51 src_mac e4:11:22:11:4a:50 ip_proto tcp src_ip 1.1.1.1 dst_ip 2.2.2.2 action drop"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip prio 1 ingress flower dst_mac e4:11:22:11:4a:51 src_mac e4:11:22:11:4a:50 ip_proto tcp src_ip 1.1.1.1 dst_ip 2.2.2.2 action drop",
+        "expExitCode": "2",
+        "verifyCmd": "$TC -s filter show dev $DEV2 ingress",
+        "matchPattern": "filter protocol ip pref 1 flower chain 0 handle",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV2 ingress"
+        ]
+    },
+    {
+        "id": "7c65",
+        "name": "Add flower filter and then terse dump it",
+        "category": [
+            "filter",
+            "flower"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV2 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -br filter show dev $DEV2 ingress",
+        "matchPattern": "filter protocol ip pref 1 flower.*handle",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV2 ingress"
+        ]
+    },
+    {
+        "id": "d45e",
+        "name": "Add flower filter and verify that terse dump doesn't output filter key",
+        "category": [
+            "filter",
+            "flower"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV2 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -br filter show dev $DEV2 ingress",
+        "matchPattern": "  dst_mac e4:11:22:11:4a:51",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV2 ingress"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/matchall.json b/tools/testing/selftests/tc-testing/tc-tests/filters/matchall.json
index afa1b9b0c856..f8d28c415bc3 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/matchall.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/matchall.json
@@ -480,5 +480,28 @@
             "$TC qdisc del dev $DUMMY ingress",
             "$TC actions del action police index 199"
         ]
+    },
+    {
+        "id": "2638",
+        "name": "Add matchall and try to get it",
+        "category": [
+            "filter",
+            "matchall"
+        ],
+        "plugins": {
+                "requires": "nsPlugin"
+        },
+        "setup": [
+            "$TC qdisc add dev $DEV1 clsact",
+            "$TC filter add dev $DEV1 protocol all pref 1 ingress handle 0x1234 matchall action ok"
+        ],
+        "cmdUnderTest": "$TC filter get dev $DEV1 protocol all pref 1 ingress handle 0x1234 matchall",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1 ingress",
+        "matchPattern": "filter protocol all pref 1 matchall chain 0 handle 0x1234",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 clsact"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
deleted file mode 100644
index 361235ad574b..000000000000
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
+++ /dev/null
@@ -1,129 +0,0 @@
-[
-    {
-        "id": "2638",
-        "name": "Add matchall and try to get it",
-        "category": [
-            "filter",
-            "matchall"
-        ],
-        "plugins": {
-                "requires": "nsPlugin"
-        },
-        "setup": [
-            "$TC qdisc add dev $DEV1 clsact",
-            "$TC filter add dev $DEV1 protocol all pref 1 ingress handle 0x1234 matchall action ok"
-        ],
-        "cmdUnderTest": "$TC filter get dev $DEV1 protocol all pref 1 ingress handle 0x1234 matchall",
-        "expExitCode": "0",
-        "verifyCmd": "$TC filter show dev $DEV1 ingress",
-        "matchPattern": "filter protocol all pref 1 matchall chain 0 handle 0x1234",
-        "matchCount": "1",
-        "teardown": [
-            "$TC qdisc del dev $DEV1 clsact"
-        ]
-    },
-    {
-        "id": "2ff3",
-        "name": "Add flower with max handle and then dump it",
-        "category": [
-            "filter",
-            "flower"
-        ],
-        "setup": [
-            "$TC qdisc add dev $DEV2 ingress"
-        ],
-        "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress handle 0xffffffff flower action ok",
-        "expExitCode": "0",
-        "verifyCmd": "$TC filter show dev $DEV2 ingress",
-        "matchPattern": "filter protocol ip pref 1 flower.*handle 0xffffffff",
-        "matchCount": "1",
-        "teardown": [
-            "$TC qdisc del dev $DEV2 ingress"
-        ]
-    },
-    {
-        "id": "d052",
-        "name": "Add 1M filters with the same action",
-        "category": [
-            "filter",
-            "flower"
-        ],
-        "plugins": {
-                "requires": "nsPlugin"
-        },
-        "setup": [
-            "$TC qdisc add dev $DEV2 ingress",
-            "./tdc_batch.py $DEV2 $BATCH_FILE --share_action -n 1000000"
-        ],
-        "cmdUnderTest": "$TC -b $BATCH_FILE",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order 0: gact action drop.*index 1 ref 1000000 bind 1000000",
-        "matchCount": "1",
-        "teardown": [
-            "$TC qdisc del dev $DEV2 ingress",
-            "/bin/rm $BATCH_FILE"
-        ]
-    },
-    {
-        "id": "4cbd",
-        "name": "Try to add filter with duplicate key",
-        "category": [
-            "filter",
-            "flower"
-        ],
-        "plugins": {
-                "requires": "nsPlugin"
-        },
-        "setup": [
-            "$TC qdisc add dev $DEV2 ingress",
-            "$TC filter add dev $DEV2 protocol ip prio 1 ingress flower dst_mac e4:11:22:11:4a:51 src_mac e4:11:22:11:4a:50 ip_proto tcp src_ip 1.1.1.1 dst_ip 2.2.2.2 action drop"
-        ],
-        "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip prio 1 ingress flower dst_mac e4:11:22:11:4a:51 src_mac e4:11:22:11:4a:50 ip_proto tcp src_ip 1.1.1.1 dst_ip 2.2.2.2 action drop",
-        "expExitCode": "2",
-        "verifyCmd": "$TC -s filter show dev $DEV2 ingress",
-        "matchPattern": "filter protocol ip pref 1 flower chain 0 handle",
-        "matchCount": "1",
-        "teardown": [
-            "$TC qdisc del dev $DEV2 ingress"
-        ]
-    },
-    {
-        "id": "7c65",
-        "name": "Add flower filter and then terse dump it",
-        "category": [
-            "filter",
-            "flower"
-        ],
-        "setup": [
-            "$TC qdisc add dev $DEV2 ingress"
-        ],
-        "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop",
-        "expExitCode": "0",
-        "verifyCmd": "$TC -br filter show dev $DEV2 ingress",
-        "matchPattern": "filter protocol ip pref 1 flower.*handle",
-        "matchCount": "1",
-        "teardown": [
-            "$TC qdisc del dev $DEV2 ingress"
-        ]
-    },
-    {
-        "id": "d45e",
-        "name": "Add flower filter and verify that terse dump doesn't output filter key",
-        "category": [
-            "filter",
-            "flower"
-        ],
-        "setup": [
-            "$TC qdisc add dev $DEV2 ingress"
-        ],
-        "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop",
-        "expExitCode": "0",
-        "verifyCmd": "$TC -br filter show dev $DEV2 ingress",
-        "matchPattern": "  dst_mac e4:11:22:11:4a:51",
-        "matchCount": "0",
-        "teardown": [
-            "$TC qdisc del dev $DEV2 ingress"
-        ]
-    }
-]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json
index ddc7c355be0a..24bd0c2a3014 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json
@@ -272,5 +272,62 @@
         "teardown": [
             "$TC qdisc del dev $DEV1 parent root drr"
         ]
+    },
+    {
+        "id": "bd32",
+        "name": "Try to delete hashtable referenced by another u32 filter",
+        "category": [
+            "filter",
+            "u32"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$TC qdisc add dev $DEV1 parent root handle 10: drr",
+            "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 handle 1: u32 divisor 1",
+            "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 u32 ht 800: match ip src any link 1:"
+        ],
+        "cmdUnderTest": "$TC filter delete dev $DEV1 parent 10: prio 2 handle 1: u32",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter show dev $DEV1",
+        "matchPattern": "protocol ip pref 2 u32 chain 0 fh 1:",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 parent root drr"
+        ]
+    },
+    {
+        "id": "4585",
+        "name": "Delete small tree of u32 hashtables and filters",
+        "category": [
+            "filter",
+            "u32"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$TC qdisc add dev $DEV1 parent root handle 10: drr",
+            "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 handle 1: u32 divisor 1",
+            "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 handle 2: u32 divisor 1",
+            "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 handle 3: u32 divisor 2",
+            "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 handle 4: u32 divisor 1",
+            "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 u32 ht 1: match ip src any action drop",
+            "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 u32 ht 2: match ip src any action drop",
+            "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 u32 ht 3: match ip src any link 2:",
+            "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 u32 ht 3: match ip src any link 1:",
+            "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 u32 ht 4: match ip src any action drop",
+            "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 u32 ht 800: match ip src any link 3:",
+            "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 u32 ht 800: match ip src any link 4:"
+        ],
+        "cmdUnderTest": "$TC filter delete dev $DEV1 parent 10:",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1",
+        "matchPattern": "protocol ip pref 2 u32",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 parent root drr"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
index a6718192aff3..caeacc691587 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -497,11 +497,6 @@ def prepare_run(pm, args, testlist):
         pm.call_post_suite(1)
         return emergency_exit_message
 
-    if args.verbose:
-        print('give test rig 2 seconds to stabilize')
-
-    time.sleep(2)
-
 def purge_run(pm, index):
     pm.call_post_suite(index)
 
@@ -616,7 +611,7 @@ def test_runner_mp(pm, args, alltests):
     batches.insert(0, serial)
 
     print("Executing {} tests in parallel and {} in serial".format(len(parallel), len(serial)))
-    print("Using {} batches".format(len(batches)))
+    print("Using {} batches and {} workers".format(len(batches), args.mp))
 
     # We can't pickle these objects so workaround them
     global mp_pm
@@ -1017,12 +1012,17 @@ def main():
     parser = pm.call_add_args(parser)
     (args, remaining) = parser.parse_known_args()
     args.NAMES = NAMES
+    args.mp = min(args.mp, 4)
     pm.set_args(args)
     check_default_settings(args, remaining, pm)
     if args.verbose > 2:
         print('args is {}'.format(args))
 
-    set_operation_mode(pm, parser, args, remaining)
+    try:
+        set_operation_mode(pm, parser, args, remaining)
+    except KeyboardInterrupt:
+        # Cleanup on Ctrl-C
+        pm.call_post_suite(None)
 
 if __name__ == "__main__":
     main()
diff --git a/tools/testing/selftests/tc-testing/tdc.sh b/tools/testing/selftests/tc-testing/tdc.sh
index eb357bd7923c..c53ede8b730d 100755
--- a/tools/testing/selftests/tc-testing/tdc.sh
+++ b/tools/testing/selftests/tc-testing/tdc.sh
@@ -1,7 +1,67 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 
-modprobe netdevsim
-modprobe sch_teql
-./tdc.py -c actions --nobuildebpf
-./tdc.py -c qdisc
+# If a module is required and was not compiled
+# the test that requires it will fail anyways
+try_modprobe() {
+   modprobe -q -R "$1"
+   if [ $? -ne 0 ]; then
+      echo "Module $1 not found... skipping."
+   else
+      modprobe "$1"
+   fi
+}
+
+try_modprobe netdevsim
+try_modprobe act_bpf
+try_modprobe act_connmark
+try_modprobe act_csum
+try_modprobe act_ct
+try_modprobe act_ctinfo
+try_modprobe act_gact
+try_modprobe act_gate
+try_modprobe act_mirred
+try_modprobe act_mpls
+try_modprobe act_nat
+try_modprobe act_pedit
+try_modprobe act_police
+try_modprobe act_sample
+try_modprobe act_simple
+try_modprobe act_skbedit
+try_modprobe act_skbmod
+try_modprobe act_tunnel_key
+try_modprobe act_vlan
+try_modprobe cls_basic
+try_modprobe cls_bpf
+try_modprobe cls_cgroup
+try_modprobe cls_flow
+try_modprobe cls_flower
+try_modprobe cls_fw
+try_modprobe cls_matchall
+try_modprobe cls_route
+try_modprobe cls_u32
+try_modprobe em_canid
+try_modprobe em_cmp
+try_modprobe em_ipset
+try_modprobe em_ipt
+try_modprobe em_meta
+try_modprobe em_nbyte
+try_modprobe em_text
+try_modprobe em_u32
+try_modprobe sch_cake
+try_modprobe sch_cbs
+try_modprobe sch_choke
+try_modprobe sch_codel
+try_modprobe sch_drr
+try_modprobe sch_etf
+try_modprobe sch_ets
+try_modprobe sch_fq
+try_modprobe sch_fq_codel
+try_modprobe sch_fq_pie
+try_modprobe sch_gred
+try_modprobe sch_hfsc
+try_modprobe sch_hhf
+try_modprobe sch_htb
+try_modprobe sch_teql
+./tdc.py -J`nproc` -c actions
+./tdc.py -J`nproc` -c qdisc
diff --git a/tools/testing/selftests/vDSO/vdso_test_abi.c b/tools/testing/selftests/vDSO/vdso_test_abi.c
index 883ca85424bc..96d32fd65b42 100644
--- a/tools/testing/selftests/vDSO/vdso_test_abi.c
+++ b/tools/testing/selftests/vDSO/vdso_test_abi.c
@@ -33,9 +33,20 @@ typedef long (*vdso_clock_gettime_t)(clockid_t clk_id, struct timespec *ts);
 typedef long (*vdso_clock_getres_t)(clockid_t clk_id, struct timespec *ts);
 typedef time_t (*vdso_time_t)(time_t *t);
 
-#define VDSO_TEST_PASS_MSG()	"\n%s(): PASS\n", __func__
-#define VDSO_TEST_FAIL_MSG(x)	"\n%s(): %s FAIL\n", __func__, x
-#define VDSO_TEST_SKIP_MSG(x)	"\n%s(): SKIP: Could not find %s\n", __func__, x
+const char *vdso_clock_name[12] = {
+	"CLOCK_REALTIME",
+	"CLOCK_MONOTONIC",
+	"CLOCK_PROCESS_CPUTIME_ID",
+	"CLOCK_THREAD_CPUTIME_ID",
+	"CLOCK_MONOTONIC_RAW",
+	"CLOCK_REALTIME_COARSE",
+	"CLOCK_MONOTONIC_COARSE",
+	"CLOCK_BOOTTIME",
+	"CLOCK_REALTIME_ALARM",
+	"CLOCK_BOOTTIME_ALARM",
+	"CLOCK_SGI_CYCLE",
+	"CLOCK_TAI",
+};
 
 static void vdso_test_gettimeofday(void)
 {
@@ -44,7 +55,8 @@ static void vdso_test_gettimeofday(void)
 		(vdso_gettimeofday_t)vdso_sym(version, name[0]);
 
 	if (!vdso_gettimeofday) {
-		ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[0]));
+		ksft_print_msg("Couldn't find %s\n", name[0]);
+		ksft_test_result_skip("%s\n", name[0]);
 		return;
 	}
 
@@ -54,9 +66,9 @@ static void vdso_test_gettimeofday(void)
 	if (ret == 0) {
 		ksft_print_msg("The time is %lld.%06lld\n",
 			       (long long)tv.tv_sec, (long long)tv.tv_usec);
-		ksft_test_result_pass(VDSO_TEST_PASS_MSG());
+		ksft_test_result_pass("%s\n", name[0]);
 	} else {
-		ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[0]));
+		ksft_test_result_fail("%s\n", name[0]);
 	}
 }
 
@@ -67,7 +79,9 @@ static void vdso_test_clock_gettime(clockid_t clk_id)
 		(vdso_clock_gettime_t)vdso_sym(version, name[1]);
 
 	if (!vdso_clock_gettime) {
-		ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[1]));
+		ksft_print_msg("Couldn't find %s\n", name[1]);
+		ksft_test_result_skip("%s %s\n", name[1],
+				      vdso_clock_name[clk_id]);
 		return;
 	}
 
@@ -77,9 +91,11 @@ static void vdso_test_clock_gettime(clockid_t clk_id)
 	if (ret == 0) {
 		ksft_print_msg("The time is %lld.%06lld\n",
 			       (long long)ts.tv_sec, (long long)ts.tv_nsec);
-		ksft_test_result_pass(VDSO_TEST_PASS_MSG());
+		ksft_test_result_pass("%s %s\n", name[1],
+				      vdso_clock_name[clk_id]);
 	} else {
-		ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[1]));
+		ksft_test_result_fail("%s %s\n", name[1],
+				      vdso_clock_name[clk_id]);
 	}
 }
 
@@ -90,7 +106,8 @@ static void vdso_test_time(void)
 		(vdso_time_t)vdso_sym(version, name[2]);
 
 	if (!vdso_time) {
-		ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[2]));
+		ksft_print_msg("Couldn't find %s\n", name[2]);
+		ksft_test_result_skip("%s\n", name[2]);
 		return;
 	}
 
@@ -99,9 +116,9 @@ static void vdso_test_time(void)
 	if (ret > 0) {
 		ksft_print_msg("The time in hours since January 1, 1970 is %lld\n",
 				(long long)(ret / 3600));
-		ksft_test_result_pass(VDSO_TEST_PASS_MSG());
+		ksft_test_result_pass("%s\n", name[2]);
 	} else {
-		ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[2]));
+		ksft_test_result_fail("%s\n", name[2]);
 	}
 }
 
@@ -114,7 +131,9 @@ static void vdso_test_clock_getres(clockid_t clk_id)
 		(vdso_clock_getres_t)vdso_sym(version, name[3]);
 
 	if (!vdso_clock_getres) {
-		ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[3]));
+		ksft_print_msg("Couldn't find %s\n", name[3]);
+		ksft_test_result_skip("%s %s\n", name[3],
+				      vdso_clock_name[clk_id]);
 		return;
 	}
 
@@ -137,34 +156,21 @@ static void vdso_test_clock_getres(clockid_t clk_id)
 		clock_getres_fail++;
 
 	if (clock_getres_fail > 0) {
-		ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[3]));
+		ksft_test_result_fail("%s %s\n", name[3],
+				      vdso_clock_name[clk_id]);
 	} else {
-		ksft_test_result_pass(VDSO_TEST_PASS_MSG());
+		ksft_test_result_pass("%s %s\n", name[3],
+				      vdso_clock_name[clk_id]);
 	}
 }
 
-const char *vdso_clock_name[12] = {
-	"CLOCK_REALTIME",
-	"CLOCK_MONOTONIC",
-	"CLOCK_PROCESS_CPUTIME_ID",
-	"CLOCK_THREAD_CPUTIME_ID",
-	"CLOCK_MONOTONIC_RAW",
-	"CLOCK_REALTIME_COARSE",
-	"CLOCK_MONOTONIC_COARSE",
-	"CLOCK_BOOTTIME",
-	"CLOCK_REALTIME_ALARM",
-	"CLOCK_BOOTTIME_ALARM",
-	"CLOCK_SGI_CYCLE",
-	"CLOCK_TAI",
-};
-
 /*
  * This function calls vdso_test_clock_gettime and vdso_test_clock_getres
  * with different values for clock_id.
  */
 static inline void vdso_test_clock(clockid_t clock_id)
 {
-	ksft_print_msg("\nclock_id: %s\n", vdso_clock_name[clock_id]);
+	ksft_print_msg("clock_id: %s\n", vdso_clock_name[clock_id]);
 
 	vdso_test_clock_gettime(clock_id);
 
@@ -181,14 +187,14 @@ int main(int argc, char **argv)
 	ksft_set_plan(VDSO_TEST_PLAN);
 
 	if (!sysinfo_ehdr) {
-		printf("AT_SYSINFO_EHDR is not present!\n");
+		ksft_print_msg("AT_SYSINFO_EHDR is not present!\n");
 		return KSFT_SKIP;
 	}
 
 	version = versions[VDSO_VERSION];
 	name = (const char **)&names[VDSO_NAMES];
 
-	printf("[vDSO kselftest] VDSO_VERSION: %s\n", version);
+	ksft_print_msg("[vDSO kselftest] VDSO_VERSION: %s\n", version);
 
 	vdso_init_from_sysinfo_ehdr(getauxval(AT_SYSINFO_EHDR));
 
diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c
index 8f9b06d9ce03..215b8150b7cc 100644
--- a/tools/testing/selftests/x86/lam.c
+++ b/tools/testing/selftests/x86/lam.c
@@ -817,7 +817,7 @@ static void run_test(struct testcases *test, int count)
 
 		/* return 3 is not support LA57, the case should be skipped */
 		if (ret == 3) {
-			ksft_test_result_skip(t->msg);
+			ksft_test_result_skip("%s", t->msg);
 			continue;
 		}
 
@@ -826,7 +826,7 @@ static void run_test(struct testcases *test, int count)
 		else
 			ret = !(t->expected);
 
-		ksft_test_result(ret, t->msg);
+		ksft_test_result(ret, "%s", t->msg);
 	}
 }
 
diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index 5b0e93f9996c..66246d81d654 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -353,11 +353,12 @@ static void test_stream_msg_peek_server(const struct test_opts *opts)
 }
 
 #define SOCK_BUF_SIZE (2 * 1024 * 1024)
-#define MAX_MSG_SIZE (32 * 1024)
+#define MAX_MSG_PAGES 4
 
 static void test_seqpacket_msg_bounds_client(const struct test_opts *opts)
 {
 	unsigned long curr_hash;
+	size_t max_msg_size;
 	int page_size;
 	int msg_count;
 	int fd;
@@ -373,7 +374,8 @@ static void test_seqpacket_msg_bounds_client(const struct test_opts *opts)
 
 	curr_hash = 0;
 	page_size = getpagesize();
-	msg_count = SOCK_BUF_SIZE / MAX_MSG_SIZE;
+	max_msg_size = MAX_MSG_PAGES * page_size;
+	msg_count = SOCK_BUF_SIZE / max_msg_size;
 
 	for (int i = 0; i < msg_count; i++) {
 		size_t buf_size;
@@ -383,7 +385,7 @@ static void test_seqpacket_msg_bounds_client(const struct test_opts *opts)
 		/* Use "small" buffers and "big" buffers. */
 		if (i & 1)
 			buf_size = page_size +
-					(rand() % (MAX_MSG_SIZE - page_size));
+					(rand() % (max_msg_size - page_size));
 		else
 			buf_size = 1 + (rand() % page_size);
 
@@ -429,7 +431,6 @@ static void test_seqpacket_msg_bounds_server(const struct test_opts *opts)
 	unsigned long remote_hash;
 	unsigned long curr_hash;
 	int fd;
-	char buf[MAX_MSG_SIZE];
 	struct msghdr msg = {0};
 	struct iovec iov = {0};
 
@@ -457,8 +458,13 @@ static void test_seqpacket_msg_bounds_server(const struct test_opts *opts)
 	control_writeln("SRVREADY");
 	/* Wait, until peer sends whole data. */
 	control_expectln("SENDDONE");
-	iov.iov_base = buf;
-	iov.iov_len = sizeof(buf);
+	iov.iov_len = MAX_MSG_PAGES * getpagesize();
+	iov.iov_base = malloc(iov.iov_len);
+	if (!iov.iov_base) {
+		perror("malloc");
+		exit(EXIT_FAILURE);
+	}
+
 	msg.msg_iov = &iov;
 	msg.msg_iovlen = 1;
 
@@ -483,6 +489,7 @@ static void test_seqpacket_msg_bounds_server(const struct test_opts *opts)
 		curr_hash += hash_djb2(msg.msg_iov[0].iov_base, recv_size);
 	}
 
+	free(iov.iov_base);
 	close(fd);
 	remote_hash = control_readulong();
 
@@ -1225,6 +1232,171 @@ static void test_double_bind_connect_client(const struct test_opts *opts)
 	}
 }
 
+#define RCVLOWAT_CREDIT_UPD_BUF_SIZE	(1024 * 128)
+/* This define is the same as in 'include/linux/virtio_vsock.h':
+ * it is used to decide when to send credit update message during
+ * reading from rx queue of a socket. Value and its usage in
+ * kernel is important for this test.
+ */
+#define VIRTIO_VSOCK_MAX_PKT_BUF_SIZE	(1024 * 64)
+
+static void test_stream_rcvlowat_def_cred_upd_client(const struct test_opts *opts)
+{
+	size_t buf_size;
+	void *buf;
+	int fd;
+
+	fd = vsock_stream_connect(opts->peer_cid, 1234);
+	if (fd < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	/* Send 1 byte more than peer's buffer size. */
+	buf_size = RCVLOWAT_CREDIT_UPD_BUF_SIZE + 1;
+
+	buf = malloc(buf_size);
+	if (!buf) {
+		perror("malloc");
+		exit(EXIT_FAILURE);
+	}
+
+	/* Wait until peer sets needed buffer size. */
+	recv_byte(fd, 1, 0);
+
+	if (send(fd, buf, buf_size, 0) != buf_size) {
+		perror("send failed");
+		exit(EXIT_FAILURE);
+	}
+
+	free(buf);
+	close(fd);
+}
+
+static void test_stream_credit_update_test(const struct test_opts *opts,
+					   bool low_rx_bytes_test)
+{
+	size_t recv_buf_size;
+	struct pollfd fds;
+	size_t buf_size;
+	void *buf;
+	int fd;
+
+	fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL);
+	if (fd < 0) {
+		perror("accept");
+		exit(EXIT_FAILURE);
+	}
+
+	buf_size = RCVLOWAT_CREDIT_UPD_BUF_SIZE;
+
+	if (setsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE,
+		       &buf_size, sizeof(buf_size))) {
+		perror("setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)");
+		exit(EXIT_FAILURE);
+	}
+
+	if (low_rx_bytes_test) {
+		/* Set new SO_RCVLOWAT here. This enables sending credit
+		 * update when number of bytes if our rx queue become <
+		 * SO_RCVLOWAT value.
+		 */
+		recv_buf_size = 1 + VIRTIO_VSOCK_MAX_PKT_BUF_SIZE;
+
+		if (setsockopt(fd, SOL_SOCKET, SO_RCVLOWAT,
+			       &recv_buf_size, sizeof(recv_buf_size))) {
+			perror("setsockopt(SO_RCVLOWAT)");
+			exit(EXIT_FAILURE);
+		}
+	}
+
+	/* Send one dummy byte here, because 'setsockopt()' above also
+	 * sends special packet which tells sender to update our buffer
+	 * size. This 'send_byte()' will serialize such packet with data
+	 * reads in a loop below. Sender starts transmission only when
+	 * it receives this single byte.
+	 */
+	send_byte(fd, 1, 0);
+
+	buf = malloc(buf_size);
+	if (!buf) {
+		perror("malloc");
+		exit(EXIT_FAILURE);
+	}
+
+	/* Wait until there will be 128KB of data in rx queue. */
+	while (1) {
+		ssize_t res;
+
+		res = recv(fd, buf, buf_size, MSG_PEEK);
+		if (res == buf_size)
+			break;
+
+		if (res <= 0) {
+			fprintf(stderr, "unexpected 'recv()' return: %zi\n", res);
+			exit(EXIT_FAILURE);
+		}
+	}
+
+	/* There is 128KB of data in the socket's rx queue, dequeue first
+	 * 64KB, credit update is sent if 'low_rx_bytes_test' == true.
+	 * Otherwise, credit update is sent in 'if (!low_rx_bytes_test)'.
+	 */
+	recv_buf_size = VIRTIO_VSOCK_MAX_PKT_BUF_SIZE;
+	recv_buf(fd, buf, recv_buf_size, 0, recv_buf_size);
+
+	if (!low_rx_bytes_test) {
+		recv_buf_size++;
+
+		/* Updating SO_RCVLOWAT will send credit update. */
+		if (setsockopt(fd, SOL_SOCKET, SO_RCVLOWAT,
+			       &recv_buf_size, sizeof(recv_buf_size))) {
+			perror("setsockopt(SO_RCVLOWAT)");
+			exit(EXIT_FAILURE);
+		}
+	}
+
+	fds.fd = fd;
+	fds.events = POLLIN | POLLRDNORM | POLLERR |
+		     POLLRDHUP | POLLHUP;
+
+	/* This 'poll()' will return once we receive last byte
+	 * sent by client.
+	 */
+	if (poll(&fds, 1, -1) < 0) {
+		perror("poll");
+		exit(EXIT_FAILURE);
+	}
+
+	if (fds.revents & POLLERR) {
+		fprintf(stderr, "'poll()' error\n");
+		exit(EXIT_FAILURE);
+	}
+
+	if (fds.revents & (POLLIN | POLLRDNORM)) {
+		recv_buf(fd, buf, recv_buf_size, MSG_DONTWAIT, recv_buf_size);
+	} else {
+		/* These flags must be set, as there is at
+		 * least 64KB of data ready to read.
+		 */
+		fprintf(stderr, "POLLIN | POLLRDNORM expected\n");
+		exit(EXIT_FAILURE);
+	}
+
+	free(buf);
+	close(fd);
+}
+
+static void test_stream_cred_upd_on_low_rx_bytes(const struct test_opts *opts)
+{
+	test_stream_credit_update_test(opts, true);
+}
+
+static void test_stream_cred_upd_on_set_rcvlowat(const struct test_opts *opts)
+{
+	test_stream_credit_update_test(opts, false);
+}
+
 static struct test_case test_cases[] = {
 	{
 		.name = "SOCK_STREAM connection reset",
@@ -1335,6 +1507,16 @@ static struct test_case test_cases[] = {
 		.run_client = test_double_bind_connect_client,
 		.run_server = test_double_bind_connect_server,
 	},
+	{
+		.name = "SOCK_STREAM virtio credit update + SO_RCVLOWAT",
+		.run_client = test_stream_rcvlowat_def_cred_upd_client,
+		.run_server = test_stream_cred_upd_on_set_rcvlowat,
+	},
+	{
+		.name = "SOCK_STREAM virtio credit update + low rx_bytes",
+		.run_client = test_stream_rcvlowat_def_cred_upd_client,
+		.run_server = test_stream_cred_upd_on_low_rx_bytes,
+	},
 	{},
 };
 
diff --git a/tools/thermal/tmon/tui.c b/tools/thermal/tmon/tui.c
index 031b258667d8..7f5dd2b87f15 100644
--- a/tools/thermal/tmon/tui.c
+++ b/tools/thermal/tmon/tui.c
@@ -213,7 +213,7 @@ void show_cooling_device(void)
 		 * cooling device instances. skip unused idr.
 		 */
 		mvwprintw(cooling_device_window, j + 2, 1,
-			"%02d %12.12s%6d %6d",
+			"%02d %12.12s%6lu %6lu",
 			ptdata.cdi[j].instance,
 			ptdata.cdi[j].type,
 			ptdata.cdi[j].cur_state,
diff --git a/usr/Kconfig b/usr/Kconfig
index 8bbcf699fe3b..9279a2893ab0 100644
--- a/usr/Kconfig
+++ b/usr/Kconfig
@@ -185,9 +185,9 @@ config INITRAMFS_COMPRESSION_LZO
 	bool "LZO"
 	depends on RD_LZO
 	help
-	  It's compression ratio is the second poorest amongst the choices. The
-	  kernel size is about 10% bigger than gzip. Despite that, it's
-	  decompression speed is the second fastest and it's compression speed
+	  Its compression ratio is the second poorest amongst the choices. The
+	  kernel size is about 10% bigger than gzip. Despite that, its
+	  decompression speed is the second fastest and its compression speed
 	  is quite fast too.
 
 	  If you choose this, keep in mind that you may need to install the lzop
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 89912a17f5d5..c0e230f4c3e9 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -61,7 +61,7 @@ static void irqfd_resampler_notify(struct kvm_kernel_irqfd_resampler *resampler)
 
 	list_for_each_entry_srcu(irqfd, &resampler->list, resampler_link,
 				 srcu_read_lock_held(&resampler->kvm->irq_srcu))
-		eventfd_signal(irqfd->resamplefd, 1);
+		eventfd_signal(irqfd->resamplefd);
 }
 
 /*
@@ -786,7 +786,7 @@ ioeventfd_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr,
 	if (!ioeventfd_in_range(p, addr, len, val))
 		return -EOPNOTSUPP;
 
-	eventfd_signal(p->eventfd, 1);
+	eventfd_signal(p->eventfd);
 	return 0;
 }
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 486800a7024b..7db96875ac46 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -115,8 +115,6 @@ EXPORT_SYMBOL_GPL(kvm_debugfs_dir);
 
 static const struct file_operations stat_fops_per_vm;
 
-static struct file_operations kvm_chardev_ops;
-
 static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
 			   unsigned long arg);
 #ifdef CONFIG_KVM_COMPAT
@@ -1157,9 +1155,6 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	if (!kvm)
 		return ERR_PTR(-ENOMEM);
 
-	/* KVM is pinned via open("/dev/kvm"), the fd passed to this ioctl(). */
-	__module_get(kvm_chardev_ops.owner);
-
 	KVM_MMU_LOCK_INIT(kvm);
 	mmgrab(current->mm);
 	kvm->mm = current->mm;
@@ -1279,7 +1274,6 @@ out_err_no_irq_srcu:
 out_err_no_srcu:
 	kvm_arch_free_vm(kvm);
 	mmdrop(current->mm);
-	module_put(kvm_chardev_ops.owner);
 	return ERR_PTR(r);
 }
 
@@ -1348,7 +1342,6 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	preempt_notifier_dec();
 	hardware_disable_all();
 	mmdrop(mm);
-	module_put(kvm_chardev_ops.owner);
 }
 
 void kvm_get_kvm(struct kvm *kvm)
@@ -3887,7 +3880,7 @@ static int kvm_vcpu_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-static const struct file_operations kvm_vcpu_fops = {
+static struct file_operations kvm_vcpu_fops = {
 	.release        = kvm_vcpu_release,
 	.unlocked_ioctl = kvm_vcpu_ioctl,
 	.mmap           = kvm_vcpu_mmap,
@@ -4081,6 +4074,7 @@ static int kvm_vcpu_stats_release(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations kvm_vcpu_stats_fops = {
+	.owner = THIS_MODULE,
 	.read = kvm_vcpu_stats_read,
 	.release = kvm_vcpu_stats_release,
 	.llseek = noop_llseek,
@@ -4431,7 +4425,7 @@ static int kvm_device_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-static const struct file_operations kvm_device_fops = {
+static struct file_operations kvm_device_fops = {
 	.unlocked_ioctl = kvm_device_ioctl,
 	.release = kvm_device_release,
 	KVM_COMPAT(kvm_device_ioctl),
@@ -4759,6 +4753,7 @@ static int kvm_vm_stats_release(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations kvm_vm_stats_fops = {
+	.owner = THIS_MODULE,
 	.read = kvm_vm_stats_read,
 	.release = kvm_vm_stats_release,
 	.llseek = noop_llseek,
@@ -5060,7 +5055,7 @@ static long kvm_vm_compat_ioctl(struct file *filp,
 }
 #endif
 
-static const struct file_operations kvm_vm_fops = {
+static struct file_operations kvm_vm_fops = {
 	.release        = kvm_vm_release,
 	.unlocked_ioctl = kvm_vm_ioctl,
 	.llseek		= noop_llseek,
@@ -5545,7 +5540,6 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
 	return r < 0 ? r : 0;
 }
 
-/* Caller must hold slots_lock. */
 int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 			    int len, struct kvm_io_device *dev)
 {
@@ -5553,6 +5547,8 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 	struct kvm_io_bus *new_bus, *bus;
 	struct kvm_io_range range;
 
+	lockdep_assert_held(&kvm->slots_lock);
+
 	bus = kvm_get_bus(kvm, bus_idx);
 	if (!bus)
 		return -ENOMEM;
@@ -6095,6 +6091,9 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module)
 		goto err_async_pf;
 
 	kvm_chardev_ops.owner = module;
+	kvm_vm_fops.owner = module;
+	kvm_vcpu_fops.owner = module;
+	kvm_device_fops.owner = module;
 
 	kvm_preempt_ops.sched_in = kvm_sched_in;
 	kvm_preempt_ops.sched_out = kvm_sched_out;